5266 files changed, 242457 insertions, 123330 deletions

diff --git a/.mailmap b/.mailmap
index 67dc22ffc9a8..1d6f4e7280dc 100644
--- a/.mailmap
+++ b/.mailmap
@@ -99,6 +99,8 @@ Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
 Mark Brown <broonie@sirena.org.uk>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
 Matthieu CASTET <castet.matthieu@free.fr>
 Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
 Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
@@ -171,6 +173,7 @@ Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
+Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
 Gustavo Padovan <padovan@profusion.mobi>
diff --git a/CREDITS b/CREDITS
index c5626bf06264..5d09c26d69cd 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1034,6 +1034,10 @@ S: 2037 Walnut #6
 S: Boulder, Colorado 80302
 S: USA
 
+N: Hans-Christian Noren Egtvedt
+E: egtvedt@samfundet.no
+D: AVR32 architecture maintainer.
+
 N: Heiko Eißfeldt
 E: heiko@colossus.escape.de heiko@unifix.de
 D: verify_area stuff, generic SCSI fixes
@@ -3398,6 +3402,10 @@ S: Suite 101
 S: Markham, Ontario L3R 2Z6
 S: Canada
 
+N: Haavard Skinnemoen
+M: Haavard Skinnemoen <hskinnemoen@gmail.com>
+D: AVR32 architecture port to Linux and maintainer.
+
 N: Rick Sladkey
 E: jrs@world.std.com
 D: utility hacker: Emacs, NFS server, mount, kmem-ps, UPS debugger, strace, GDB
diff --git a/Documentation/ABI/obsolete/sysfs-firmware-acpi b/Documentation/ABI/obsolete/sysfs-firmware-acpi
new file mode 100644
index 000000000000..6715a71bec3d
--- /dev/null
+++ b/Documentation/ABI/obsolete/sysfs-firmware-acpi
@@ -0,0 +1,8 @@
+What:		/sys/firmware/acpi/hotplug/force_remove
+Date:		Mar 2017
+Contact:	Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+Description:
+		Since the force_remove is inherently broken and dangerous to
+		use for some hotplugable resources like memory (because ignoring
+		the offline failure might lead to memory corruption and crashes)
+		enabling this knob is not safe and thus unsupported.
diff --git a/Documentation/ABI/stable/sysfs-bus-usb b/Documentation/ABI/stable/sysfs-bus-usb
index 831f15d9672f..b832eeff9999 100644
--- a/Documentation/ABI/stable/sysfs-bus-usb
+++ b/Documentation/ABI/stable/sysfs-bus-usb
@@ -9,7 +9,7 @@ Description:
 		hubs this facility is always enabled and their device
 		directories will not contain this file.
 
-		For more information, see Documentation/usb/persist.txt.
+		For more information, see Documentation/driver-api/usb/persist.rst.
 
 What:		/sys/bus/usb/devices/.../power/autosuspend
 Date:		March 2007
diff --git a/Documentation/ABI/stable/vdso b/Documentation/ABI/stable/vdso
index 7cdfc28cc2c6..55406ec8a35a 100644
--- a/Documentation/ABI/stable/vdso
+++ b/Documentation/ABI/stable/vdso
@@ -16,7 +16,8 @@ The vDSO uses symbol versioning; whenever you request a symbol from the
 vDSO, specify the version you are expecting.
 
 Programs that dynamically link to glibc will use the vDSO automatically.
-Otherwise, you can use the reference parser in Documentation/vDSO/parse_vdso.c.
+Otherwise, you can use the reference parser in
+tools/testing/selftests/vDSO/parse_vdso.c.
 
 Unless otherwise noted, the set of symbols with any given version and the
 ABI of those symbols is considered stable.  It may vary across architectures,
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 2da04ce6aeef..dea212db9df3 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -213,14 +213,8 @@ What:		/sys/block/<disk>/queue/discard_zeroes_data
 Date:		May 2011
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		Devices that support discard functionality may return
-		stale or random data when a previously discarded block
-		is read back. This can cause problems if the filesystem
-		expects discarded blocks to be explicitly cleared. If a
-		device reports that it deterministically returns zeroes
-		when a discarded area is read the discard_zeroes_data
-		parameter will be set to one. Otherwise it will be 0 and
-		the result of reading a discarded area is undefined.
+		Will always return 0.  Don't rely on any specific behavior
+		for discards, and don't read this file.
 
 What:		/sys/block/<disk>/queue/write_same_max_bytes
 Date:		January 2012
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 5a1732b78707..e4e90104d7c3 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -299,5 +299,5 @@ What:		/sys/bus/pci/devices/.../revision
 Date:		November 2016
 Contact:	Emil Velikov <emil.l.velikov@gmail.com>
 Description:
-		This file contains the revision field of the the PCI device.
+		This file contains the revision field of the PCI device.
 		The value comes from device config space. The file is read only.
diff --git a/Documentation/ABI/testing/sysfs-class-net-qmi b/Documentation/ABI/testing/sysfs-class-net-qmi
index fa5a00bb1143..7122d6264c49 100644
--- a/Documentation/ABI/testing/sysfs-class-net-qmi
+++ b/Documentation/ABI/testing/sysfs-class-net-qmi
@@ -21,3 +21,30 @@ Description:
 		is responsible for coordination of driver and firmware
 		link framing mode, changing this setting to 'Y' if the
 		firmware is configured for 'raw-ip' mode.
+
+What:		/sys/class/net/<iface>/qmi/add_mux
+Date:		March 2017
+KernelVersion:	4.11
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Unsigned integer.
+
+		Write a number ranging from 1 to 127 to add a qmap mux
+		based network device, supported by recent Qualcomm based
+		modems.
+
+		The network device will be called qmimux.
+
+		Userspace is in charge of managing the qmux network device
+		activation and data stream setup on the modem side by
+		using the proper QMI protocol requests.
+
+What:		/sys/class/net/<iface>/qmi/del_mux
+Date:		March 2017
+KernelVersion:	4.11
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Unsigned integer.
+
+		Write a number ranging from 1 to 127 to delete a previously
+		created qmap mux based network device.
diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi
index c7fc72d4495c..613f42a9d5cd 100644
--- a/Documentation/ABI/testing/sysfs-firmware-acpi
+++ b/Documentation/ABI/testing/sysfs-firmware-acpi
@@ -44,16 +44,6 @@ Description:
 		or 0 (unset).  Attempts to write any other values to it will
 		cause -EINVAL to be returned.
 
-What:		/sys/firmware/acpi/hotplug/force_remove
-Date:		May 2013
-Contact:	Rafael J. Wysocki <rafael.j.wysocki@intel.com>
-Description:
-		The number in this file (0 or 1) determines whether (1) or not
-		(0) the ACPI subsystem will allow devices to be hot-removed even
-		if they cannot be put offline gracefully (from the kernel's
-		viewpoint).  That number can be changed by writing a boolean
-		value to this file.
-
 What:		/sys/firmware/acpi/interrupts/
 Date:		February 2008
 Contact:	Len Brown <lenb@kernel.org>
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 164c1c76971f..85916f13d330 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -8,12 +8,11 @@
 
 DOCBOOKS := z8530book.xml  \
 	    kernel-hacking.xml kernel-locking.xml \
-	    writing_usb_driver.xml networking.xml \
-	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
-	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
-	    genericirq.xml s390-drivers.xml scsi.xml \
-	    sh.xml w1.xml \
-	    writing_musb_glue_layer.xml
+	    networking.xml \
+	    filesystems.xml lsm.xml kgdb.xml \
+	    libata.xml mtdnand.xml librs.xml rapidio.xml \
+	    s390-drivers.xml scsi.xml \
+	    sh.xml w1.xml
 
 ifeq ($(DOCBOOKS),)
 
@@ -62,11 +61,14 @@ MAN := $(patsubst %.xml, %.9, $(BOOKS))
 mandocs: $(MAN)
 	find $(obj)/man -name '*.9' | xargs gzip -nf
 
+# Default location for installed man pages
+export INSTALL_MAN_PATH = $(objtree)/usr
+
 installmandocs: mandocs
-	mkdir -p /usr/local/man/man9/
+	mkdir -p $(INSTALL_MAN_PATH)/man/man9/
 	find $(obj)/man -name '*.9.gz' -printf '%h %f\n' | \
 		sort -k 2 -k 1 | uniq -f 1 | sed -e 's: :/:' | \
-		xargs install -m 644 -t /usr/local/man/man9/
+		xargs install -m 644 -t $(INSTALL_MAN_PATH)/man/man9/
 
 # no-op for the DocBook toolchain
 epubdocs:
@@ -238,7 +240,9 @@ dochelp:
 	@echo  '  psdocs          - Postscript'
 	@echo  '  xmldocs         - XML DocBook'
 	@echo  '  mandocs         - man pages'
-	@echo  '  installmandocs  - install man pages generated by mandocs'
+	@echo  '  installmandocs  - install man pages generated by mandocs to INSTALL_MAN_PATH'; \
+	 echo  '                    (default: $(INSTALL_MAN_PATH))'; \
+	 echo  ''
 	@echo  '  cleandocs       - clean all generated DocBook files'
 	@echo
 	@echo  '  make DOCBOOKS="s1.xml s2.xml" [target] Generate only docs s1.xml s2.xml'
diff --git a/Documentation/DocBook/gadget.tmpl b/Documentation/DocBook/gadget.tmpl
deleted file mode 100644
index 641629221176..000000000000
--- a/Documentation/DocBook/gadget.tmpl
+++ /dev/null
@@ -1,793 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="USB-Gadget-API">
-  <bookinfo>
-    <title>USB Gadget API for Linux</title>
-    <date>20 August 2004</date>
-    <edition>20 August 2004</edition>
-  
-    <legalnotice>
-       <para>
-	 This documentation is free software; you can redistribute
-	 it and/or modify it under the terms of the GNU General Public
-	 License as published by the Free Software Foundation; either
-	 version 2 of the License, or (at your option) any later
-	 version.
-       </para>
-	  
-       <para>
-	 This program is distributed in the hope that it will be
-	 useful, but WITHOUT ANY WARRANTY; without even the implied
-	 warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-	 See the GNU General Public License for more details.
-       </para>
-	  
-       <para>
-	 You should have received a copy of the GNU General Public
-	 License along with this program; if not, write to the Free
-	 Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-	 MA 02111-1307 USA
-       </para>
-	  
-       <para>
-	 For more details see the file COPYING in the source
-	 distribution of Linux.
-       </para>
-    </legalnotice>
-    <copyright>
-      <year>2003-2004</year>
-      <holder>David Brownell</holder>
-    </copyright>
-
-    <author>
-      <firstname>David</firstname> 
-      <surname>Brownell</surname>
-      <affiliation>
-        <address><email>dbrownell@users.sourceforge.net</email></address>
-      </affiliation>
-    </author>
-  </bookinfo>
-
-<toc></toc>
-
-<chapter id="intro"><title>Introduction</title>
-
-<para>This document presents a Linux-USB "Gadget"
-kernel mode
-API, for use within peripherals and other USB devices
-that embed Linux.
-It provides an overview of the API structure,
-and shows how that fits into a system development project.
-This is the first such API released on Linux to address
-a number of important problems, including: </para>
-
-<itemizedlist>
-    <listitem><para>Supports USB 2.0, for high speed devices which
-	can stream data at several dozen megabytes per second.
-	</para></listitem>
-    <listitem><para>Handles devices with dozens of endpoints just as
-	well as ones with just two fixed-function ones.  Gadget drivers
-	can be written so they're easy to port to new hardware.
-	</para></listitem>
-    <listitem><para>Flexible enough to expose more complex USB device
-	capabilities such as multiple configurations, multiple interfaces,
-	composite devices,
-	and alternate interface settings.
-	</para></listitem>
-    <listitem><para>USB "On-The-Go" (OTG) support, in conjunction
-	with updates to the Linux-USB host side.
-	</para></listitem>
-    <listitem><para>Sharing data structures and API models with the
-	Linux-USB host side API.  This helps the OTG support, and
-	looks forward to more-symmetric frameworks (where the same
-	I/O model is used by both host and device side drivers).
-	</para></listitem>
-    <listitem><para>Minimalist, so it's easier to support new device
-	controller hardware.  I/O processing doesn't imply large
-	demands for memory or CPU resources.
-	</para></listitem>
-</itemizedlist>
-
-
-<para>Most Linux developers will not be able to use this API, since they
-have USB "host" hardware in a PC, workstation, or server.
-Linux users with embedded systems are more likely to
-have USB peripheral hardware.
-To distinguish drivers running inside such hardware from the
-more familiar Linux "USB device drivers",
-which are host side proxies for the real USB devices,
-a different term is used:
-the drivers inside the peripherals are "USB gadget drivers".
-In USB protocol interactions, the device driver is the master
-(or "client driver")
-and the gadget driver is the slave (or "function driver").
-</para>
-
-<para>The gadget API resembles the host side Linux-USB API in that both
-use queues of request objects to package I/O buffers, and those requests
-may be submitted or canceled.
-They share common definitions for the standard USB
-<emphasis>Chapter 9</emphasis> messages, structures, and constants.
-Also, both APIs bind and unbind drivers to devices.
-The APIs differ in detail, since the host side's current
-URB framework exposes a number of implementation details
-and assumptions that are inappropriate for a gadget API.
-While the model for control transfers and configuration
-management is necessarily different (one side is a hardware-neutral master,
-the other is a hardware-aware slave), the endpoint I/0 API used here
-should also be usable for an overhead-reduced host side API.
-</para>
-
-</chapter>
-
-<chapter id="structure"><title>Structure of Gadget Drivers</title>
-
-<para>A system running inside a USB peripheral
-normally has at least three layers inside the kernel to handle
-USB protocol processing, and may have additional layers in
-user space code.
-The "gadget" API is used by the middle layer to interact
-with the lowest level (which directly handles hardware).
-</para>
-
-<para>In Linux, from the bottom up, these layers are:
-</para>
-
-<variablelist>
-
-    <varlistentry>
-        <term><emphasis>USB Controller Driver</emphasis></term>
-
-	<listitem>
-	<para>This is the lowest software level.
-	It is the only layer that talks to hardware,
-	through registers, fifos, dma, irqs, and the like.
-	The <filename>&lt;linux/usb/gadget.h&gt;</filename> API abstracts
-	the peripheral controller endpoint hardware.
-	That hardware is exposed through endpoint objects, which accept
-	streams of IN/OUT buffers, and through callbacks that interact
-	with gadget drivers.
-	Since normal USB devices only have one upstream
-	port, they only have one of these drivers.
-	The controller driver can support any number of different
-	gadget drivers, but only one of them can be used at a time.
-	</para>
-
-	<para>Examples of such controller hardware include
-	the PCI-based NetChip 2280 USB 2.0 high speed controller,
-	the SA-11x0 or PXA-25x UDC (found within many PDAs),
-	and a variety of other products.
-	</para>
-
-	</listitem></varlistentry>
-
-    <varlistentry>
-	<term><emphasis>Gadget Driver</emphasis></term>
-
-	<listitem>
-	<para>The lower boundary of this driver implements hardware-neutral
-	USB functions, using calls to the controller driver.
-	Because such hardware varies widely in capabilities and restrictions,
-	and is used in embedded environments where space is at a premium,
-	the gadget driver is often configured at compile time
-	to work with endpoints supported by one particular controller.
-	Gadget drivers may be portable to several different controllers,
-	using conditional compilation.
-	(Recent kernels substantially simplify the work involved in
-	supporting new hardware, by <emphasis>autoconfiguring</emphasis>
-	endpoints automatically for many bulk-oriented drivers.)
-	Gadget driver responsibilities include:
-	</para>
-	<itemizedlist>
-	    <listitem><para>handling setup requests (ep0 protocol responses)
-		possibly including class-specific functionality
-		</para></listitem>
-	    <listitem><para>returning configuration and string descriptors
-		</para></listitem>
-	    <listitem><para>(re)setting configurations and interface
-		altsettings, including enabling and configuring endpoints
-		</para></listitem>
-	    <listitem><para>handling life cycle events, such as managing
-		bindings to hardware,
-		USB suspend/resume, remote wakeup,
-		and disconnection from the USB host.
-		</para></listitem>
-	    <listitem><para>managing IN and OUT transfers on all currently
-		enabled endpoints
-		</para></listitem>
-	</itemizedlist>
-
-	<para>
-	Such drivers may be modules of proprietary code, although
-	that approach is discouraged in the Linux community.
-	</para>
-	</listitem></varlistentry>
-
-    <varlistentry>
-	<term><emphasis>Upper Level</emphasis></term>
-
-	<listitem>
-	<para>Most gadget drivers have an upper boundary that connects
-	to some Linux driver or framework in Linux.
-	Through that boundary flows the data which the gadget driver
-	produces and/or consumes through protocol transfers over USB.
-	Examples include:
-	</para>
-	<itemizedlist>
-	    <listitem><para>user mode code, using generic (gadgetfs)
-	        or application specific files in
-		<filename>/dev</filename>
-		</para></listitem>
-	    <listitem><para>networking subsystem (for network gadgets,
-		like the CDC Ethernet Model gadget driver)
-		</para></listitem>
-	    <listitem><para>data capture drivers, perhaps video4Linux or
-		 a scanner driver; or test and measurement hardware.
-		 </para></listitem>
-	    <listitem><para>input subsystem (for HID gadgets)
-		</para></listitem>
-	    <listitem><para>sound subsystem (for audio gadgets)
-		</para></listitem>
-	    <listitem><para>file system (for PTP gadgets)
-		</para></listitem>
-	    <listitem><para>block i/o subsystem (for usb-storage gadgets)
-		</para></listitem>
-	    <listitem><para>... and more </para></listitem>
-	</itemizedlist>
-	</listitem></varlistentry>
-
-    <varlistentry>
-	<term><emphasis>Additional Layers</emphasis></term>
-
-	<listitem>
-	<para>Other layers may exist.
-	These could include kernel layers, such as network protocol stacks,
-	as well as user mode applications building on standard POSIX
-	system call APIs such as
-	<emphasis>open()</emphasis>, <emphasis>close()</emphasis>,
-	<emphasis>read()</emphasis> and <emphasis>write()</emphasis>.
-	On newer systems, POSIX Async I/O calls may be an option.
-	Such user mode code will not necessarily be subject to
-	the GNU General Public License (GPL).
-	</para>
-	</listitem></varlistentry>
-
-
-</variablelist>
-
-<para>OTG-capable systems will also need to include a standard Linux-USB
-host side stack,
-with <emphasis>usbcore</emphasis>,
-one or more <emphasis>Host Controller Drivers</emphasis> (HCDs),
-<emphasis>USB Device Drivers</emphasis> to support
-the OTG "Targeted Peripheral List",
-and so forth.
-There will also be an <emphasis>OTG Controller Driver</emphasis>,
-which is visible to gadget and device driver developers only indirectly.
-That helps the host and device side USB controllers implement the
-two new OTG protocols (HNP and SRP).
-Roles switch (host to peripheral, or vice versa) using HNP
-during USB suspend processing, and SRP can be viewed as a
-more battery-friendly kind of device wakeup protocol.
-</para>
-
-<para>Over time, reusable utilities are evolving to help make some
-gadget driver tasks simpler.
-For example, building configuration descriptors from vectors of
-descriptors for the configurations interfaces and endpoints is
-now automated, and many drivers now use autoconfiguration to
-choose hardware endpoints and initialize their descriptors.
-
-A potential example of particular interest
-is code implementing standard USB-IF protocols for
-HID, networking, storage, or audio classes.
-Some developers are interested in KDB or KGDB hooks, to let
-target hardware be remotely debugged.
-Most such USB protocol code doesn't need to be hardware-specific,
-any more than network protocols like X11, HTTP, or NFS are.
-Such gadget-side interface drivers should eventually be combined,
-to implement composite devices.
-</para>
-
-</chapter>
-
-
-<chapter id="api"><title>Kernel Mode Gadget API</title>
-
-<para>Gadget drivers declare themselves through a
-<emphasis>struct usb_gadget_driver</emphasis>, which is responsible for
-most parts of enumeration for a <emphasis>struct usb_gadget</emphasis>.
-The response to a set_configuration usually involves
-enabling one or more of the <emphasis>struct usb_ep</emphasis> objects
-exposed by the gadget, and submitting one or more
-<emphasis>struct usb_request</emphasis> buffers to transfer data.
-Understand those four data types, and their operations, and
-you will understand how this API works.
-</para> 
-
-<note><title>Incomplete Data Type Descriptions</title>
-
-<para>This documentation was prepared using the standard Linux
-kernel <filename>docproc</filename> tool, which turns text
-and in-code comments into SGML DocBook and then into usable
-formats such as HTML or PDF.
-Other than the "Chapter 9" data types, most of the significant
-data types and functions are described here.
-</para>
-
-<para>However, docproc does not understand all the C constructs
-that are used, so some relevant information is likely omitted from
-what you are reading.  
-One example of such information is endpoint autoconfiguration.
-You'll have to read the header file, and use example source
-code (such as that for "Gadget Zero"), to fully understand the API.
-</para>
-
-<para>The part of the API implementing some basic
-driver capabilities is specific to the version of the
-Linux kernel that's in use.
-The 2.6 kernel includes a <emphasis>driver model</emphasis>
-framework that has no analogue on earlier kernels;
-so those parts of the gadget API are not fully portable.
-(They are implemented on 2.4 kernels, but in a different way.)
-The driver model state is another part of this API that is
-ignored by the kerneldoc tools.
-</para>
-</note>
-
-<para>The core API does not expose
-every possible hardware feature, only the most widely available ones.
-There are significant hardware features, such as device-to-device DMA
-(without temporary storage in a memory buffer)
-that would be added using hardware-specific APIs.
-</para>
-
-<para>This API allows drivers to use conditional compilation to handle
-endpoint capabilities of different hardware, but doesn't require that.
-Hardware tends to have arbitrary restrictions, relating to
-transfer types, addressing, packet sizes, buffering, and availability.
-As a rule, such differences only matter for "endpoint zero" logic
-that handles device configuration and management.
-The API supports limited run-time
-detection of capabilities, through naming conventions for endpoints.
-Many drivers will be able to at least partially autoconfigure
-themselves.
-In particular, driver init sections will often have endpoint
-autoconfiguration logic that scans the hardware's list of endpoints
-to find ones matching the driver requirements
-(relying on those conventions), to eliminate some of the most
-common reasons for conditional compilation.
-</para>
-
-<para>Like the Linux-USB host side API, this API exposes
-the "chunky" nature of USB messages:  I/O requests are in terms
-of one or more "packets", and packet boundaries are visible to drivers.
-Compared to RS-232 serial protocols, USB resembles
-synchronous protocols like HDLC
-(N bytes per frame, multipoint addressing, host as the primary
-station and devices as secondary stations)
-more than asynchronous ones
-(tty style:  8 data bits per frame, no parity, one stop bit).
-So for example the controller drivers won't buffer
-two single byte writes into a single two-byte USB IN packet,
-although gadget drivers may do so when they implement
-protocols where packet boundaries (and "short packets")
-are not significant.
-</para>
-
-<sect1 id="lifecycle"><title>Driver Life Cycle</title>
-
-<para>Gadget drivers make endpoint I/O requests to hardware without
-needing to know many details of the hardware, but driver
-setup/configuration code needs to handle some differences.
-Use the API like this:
-</para>
-
-<orderedlist numeration='arabic'>
-
-<listitem><para>Register a driver for the particular device side
-usb controller hardware,
-such as the net2280 on PCI (USB 2.0),
-sa11x0 or pxa25x as found in Linux PDAs,
-and so on.
-At this point the device is logically in the USB ch9 initial state
-("attached"), drawing no power and not usable
-(since it does not yet support enumeration).
-Any host should not see the device, since it's not
-activated the data line pullup used by the host to
-detect a device, even if VBUS power is available.
-</para></listitem>
-
-<listitem><para>Register a gadget driver that implements some higher level
-device function.  That will then bind() to a usb_gadget, which
-activates the data line pullup sometime after detecting VBUS.
-</para></listitem>
-
-<listitem><para>The hardware driver can now start enumerating.
-The steps it handles are to accept USB power and set_address requests.
-Other steps are handled by the gadget driver.
-If the gadget driver module is unloaded before the host starts to
-enumerate, steps before step 7 are skipped.
-</para></listitem>
-
-<listitem><para>The gadget driver's setup() call returns usb descriptors,
-based both on what the bus interface hardware provides and on the
-functionality being implemented.
-That can involve alternate settings or configurations,
-unless the hardware prevents such operation.
-For OTG devices, each configuration descriptor includes
-an OTG descriptor.
-</para></listitem>
-
-<listitem><para>The gadget driver handles the last step of enumeration,
-when the USB host issues a set_configuration call.
-It enables all endpoints used in that configuration,
-with all interfaces in their default settings.
-That involves using a list of the hardware's endpoints, enabling each
-endpoint according to its descriptor.
-It may also involve using <function>usb_gadget_vbus_draw</function>
-to let more power be drawn from VBUS, as allowed by that configuration.
-For OTG devices, setting a configuration may also involve reporting
-HNP capabilities through a user interface.
-</para></listitem>
-
-<listitem><para>Do real work and perform data transfers, possibly involving
-changes to interface settings or switching to new configurations, until the
-device is disconnect()ed from the host.
-Queue any number of transfer requests to each endpoint.
-It may be suspended and resumed several times before being disconnected.
-On disconnect, the drivers go back to step 3 (above).
-</para></listitem>
-
-<listitem><para>When the gadget driver module is being unloaded,
-the driver unbind() callback is issued.  That lets the controller
-driver be unloaded.
-</para></listitem>
-
-</orderedlist>
-
-<para>Drivers will normally be arranged so that just loading the
-gadget driver module (or statically linking it into a Linux kernel)
-allows the peripheral device to be enumerated, but some drivers
-will defer enumeration until some higher level component (like
-a user mode daemon) enables it.
-Note that at this lowest level there are no policies about how
-ep0 configuration logic is implemented,
-except that it should obey USB specifications.
-Such issues are in the domain of gadget drivers,
-including knowing about implementation constraints
-imposed by some USB controllers
-or understanding that composite devices might happen to
-be built by integrating reusable components.
-</para>
-
-<para>Note that the lifecycle above can be slightly different
-for OTG devices.
-Other than providing an additional OTG descriptor in each
-configuration, only the HNP-related differences are particularly
-visible to driver code.
-They involve reporting requirements during the SET_CONFIGURATION
-request, and the option to invoke HNP during some suspend callbacks.
-Also, SRP changes the semantics of
-<function>usb_gadget_wakeup</function>
-slightly.
-</para>
-
-</sect1>
-
-<sect1 id="ch9"><title>USB 2.0 Chapter 9 Types and Constants</title>
-
-<para>Gadget drivers
-rely on common USB structures and constants
-defined in the
-<filename>&lt;linux/usb/ch9.h&gt;</filename>
-header file, which is standard in Linux 2.6 kernels.
-These are the same types and constants used by host
-side drivers (and usbcore).
-</para>
-
-!Iinclude/linux/usb/ch9.h
-</sect1>
-
-<sect1 id="core"><title>Core Objects and Methods</title>
-
-<para>These are declared in
-<filename>&lt;linux/usb/gadget.h&gt;</filename>,
-and are used by gadget drivers to interact with
-USB peripheral controller drivers.
-</para>
-
-	<!-- yeech, this is ugly in nsgmls PDF output.
-
-	     the PDF bookmark and refentry output nesting is wrong,
-	     and the member/argument documentation indents ugly.
-
-	     plus something (docproc?) adds whitespace before the
-	     descriptive paragraph text, so it can't line up right
-	     unless the explanations are trivial.
-	  -->
-
-!Iinclude/linux/usb/gadget.h
-</sect1>
-
-<sect1 id="utils"><title>Optional Utilities</title>
-
-<para>The core API is sufficient for writing a USB Gadget Driver,
-but some optional utilities are provided to simplify common tasks.
-These utilities include endpoint autoconfiguration.
-</para>
-
-!Edrivers/usb/gadget/usbstring.c
-!Edrivers/usb/gadget/config.c
-<!-- !Edrivers/usb/gadget/epautoconf.c -->
-</sect1>
-
-<sect1 id="composite"><title>Composite Device Framework</title>
-
-<para>The core API is sufficient for writing drivers for composite
-USB devices (with more than one function in a given configuration),
-and also multi-configuration devices (also more than one function,
-but not necessarily sharing a given configuration).
-There is however an optional framework which makes it easier to
-reuse and combine functions.
-</para>
-
-<para>Devices using this framework provide a <emphasis>struct
-usb_composite_driver</emphasis>, which in turn provides one or
-more <emphasis>struct usb_configuration</emphasis> instances.
-Each such configuration includes at least one
-<emphasis>struct usb_function</emphasis>, which packages a user
-visible role such as "network link" or "mass storage device".
-Management functions may also exist, such as "Device Firmware
-Upgrade".
-</para>
-
-!Iinclude/linux/usb/composite.h
-!Edrivers/usb/gadget/composite.c
-
-</sect1>
-
-<sect1 id="functions"><title>Composite Device Functions</title>
-
-<para>At this writing, a few of the current gadget drivers have
-been converted to this framework.
-Near-term plans include converting all of them, except for "gadgetfs".
-</para>
-
-!Edrivers/usb/gadget/function/f_acm.c
-!Edrivers/usb/gadget/function/f_ecm.c
-!Edrivers/usb/gadget/function/f_subset.c
-!Edrivers/usb/gadget/function/f_obex.c
-!Edrivers/usb/gadget/function/f_serial.c
-
-</sect1>
-
-
-</chapter>
-
-<chapter id="controllers"><title>Peripheral Controller Drivers</title>
-
-<para>The first hardware supporting this API was the NetChip 2280
-controller, which supports USB 2.0 high speed and is based on PCI.
-This is the <filename>net2280</filename> driver module.
-The driver supports Linux kernel versions 2.4 and 2.6;
-contact NetChip Technologies for development boards and product
-information.
-</para> 
-
-<para>Other hardware working in the "gadget" framework includes:
-Intel's PXA 25x and IXP42x series processors
-(<filename>pxa2xx_udc</filename>),
-Toshiba TC86c001 "Goku-S" (<filename>goku_udc</filename>),
-Renesas SH7705/7727 (<filename>sh_udc</filename>),
-MediaQ 11xx (<filename>mq11xx_udc</filename>),
-Hynix HMS30C7202 (<filename>h7202_udc</filename>),
-National 9303/4 (<filename>n9604_udc</filename>),
-Texas Instruments OMAP (<filename>omap_udc</filename>),
-Sharp LH7A40x (<filename>lh7a40x_udc</filename>),
-and more.
-Most of those are full speed controllers.
-</para>
-
-<para>At this writing, there are people at work on drivers in
-this framework for several other USB device controllers,
-with plans to make many of them be widely available.
-</para>
-
-<!-- !Edrivers/usb/gadget/net2280.c -->
-
-<para>A partial USB simulator,
-the <filename>dummy_hcd</filename> driver, is available.
-It can act like a net2280, a pxa25x, or an sa11x0 in terms
-of available endpoints and device speeds; and it simulates
-control, bulk, and to some extent interrupt transfers.
-That lets you develop some parts of a gadget driver on a normal PC,
-without any special hardware, and perhaps with the assistance
-of tools such as GDB running with User Mode Linux.
-At least one person has expressed interest in adapting that
-approach, hooking it up to a simulator for a microcontroller.
-Such simulators can help debug subsystems where the runtime hardware
-is unfriendly to software development, or is not yet available.
-</para>
-
-<para>Support for other controllers is expected to be developed
-and contributed
-over time, as this driver framework evolves.
-</para>
-
-</chapter>
-
-<chapter id="gadget"><title>Gadget Drivers</title>
-
-<para>In addition to <emphasis>Gadget Zero</emphasis>
-(used primarily for testing and development with drivers
-for usb controller hardware), other gadget drivers exist.
-</para>
-
-<para>There's an <emphasis>ethernet</emphasis> gadget
-driver, which implements one of the most useful
-<emphasis>Communications Device Class</emphasis> (CDC) models.  
-One of the standards for cable modem interoperability even
-specifies the use of this ethernet model as one of two
-mandatory options.
-Gadgets using this code look to a USB host as if they're
-an Ethernet adapter.
-It provides access to a network where the gadget's CPU is one host,
-which could easily be bridging, routing, or firewalling
-access to other networks.
-Since some hardware can't fully implement the CDC Ethernet
-requirements, this driver also implements a "good parts only"
-subset of CDC Ethernet.
-(That subset doesn't advertise itself as CDC Ethernet,
-to avoid creating problems.)
-</para>
-
-<para>Support for Microsoft's <emphasis>RNDIS</emphasis>
-protocol has been contributed by Pengutronix and Auerswald GmbH.
-This is like CDC Ethernet, but it runs on more slightly USB hardware
-(but less than the CDC subset).
-However, its main claim to fame is being able to connect directly to
-recent versions of Windows, using drivers that Microsoft bundles
-and supports, making it much simpler to network with Windows.
-</para>
-
-<para>There is also support for user mode gadget drivers,
-using <emphasis>gadgetfs</emphasis>.
-This provides a <emphasis>User Mode API</emphasis> that presents
-each endpoint as a single file descriptor.  I/O is done using
-normal <emphasis>read()</emphasis> and <emphasis>read()</emphasis> calls.
-Familiar tools like GDB and pthreads can be used to
-develop and debug user mode drivers, so that once a robust
-controller driver is available many applications for it
-won't require new kernel mode software.
-Linux 2.6 <emphasis>Async I/O (AIO)</emphasis>
-support is available, so that user mode software
-can stream data with only slightly more overhead
-than a kernel driver.
-</para>
-
-<para>There's a USB Mass Storage class driver, which provides
-a different solution for interoperability with systems such
-as MS-Windows and MacOS.
-That <emphasis>Mass Storage</emphasis> driver uses a
-file or block device as backing store for a drive,
-like the <filename>loop</filename> driver.
-The USB host uses the BBB, CB, or CBI versions of the mass
-storage class specification, using transparent SCSI commands
-to access the data from the backing store.
-</para>
-
-<para>There's a "serial line" driver, useful for TTY style
-operation over USB.
-The latest version of that driver supports CDC ACM style
-operation, like a USB modem, and so on most hardware it can
-interoperate easily with MS-Windows.
-One interesting use of that driver is in boot firmware (like a BIOS),
-which can sometimes use that model with very small systems without
-real serial lines.
-</para>
-
-<para>Support for other kinds of gadget is expected to
-be developed and contributed
-over time, as this driver framework evolves.
-</para>
-
-</chapter>
-
-<chapter id="otg"><title>USB On-The-GO (OTG)</title>
-
-<para>USB OTG support on Linux 2.6 was initially developed
-by Texas Instruments for
-<ulink url="http://www.omap.com">OMAP</ulink> 16xx and 17xx
-series processors.
-Other OTG systems should work in similar ways, but the
-hardware level details could be very different.
-</para> 
-
-<para>Systems need specialized hardware support to implement OTG,
-notably including a special <emphasis>Mini-AB</emphasis> jack
-and associated transceiver to support <emphasis>Dual-Role</emphasis>
-operation:
-they can act either as a host, using the standard
-Linux-USB host side driver stack,
-or as a peripheral, using this "gadget" framework.
-To do that, the system software relies on small additions
-to those programming interfaces,
-and on a new internal component (here called an "OTG Controller")
-affecting which driver stack connects to the OTG port.
-In each role, the system can re-use the existing pool of
-hardware-neutral drivers, layered on top of the controller
-driver interfaces (<emphasis>usb_bus</emphasis> or
-<emphasis>usb_gadget</emphasis>).
-Such drivers need at most minor changes, and most of the calls
-added to support OTG can also benefit non-OTG products.
-</para>
-
-<itemizedlist>
-    <listitem><para>Gadget drivers test the <emphasis>is_otg</emphasis>
-	flag, and use it to determine whether or not to include
-	an OTG descriptor in each of their configurations.
-	</para></listitem>
-    <listitem><para>Gadget drivers may need changes to support the
-	two new OTG protocols, exposed in new gadget attributes
-	such as <emphasis>b_hnp_enable</emphasis> flag.
-	HNP support should be reported through a user interface
-	(two LEDs could suffice), and is triggered in some cases
-	when the host suspends the peripheral.
-	SRP support can be user-initiated just like remote wakeup,
-	probably by pressing the same button.
-	</para></listitem>
-    <listitem><para>On the host side, USB device drivers need
-	to be taught to trigger HNP at appropriate moments, using
-	<function>usb_suspend_device()</function>.
-	That also conserves battery power, which is useful even
-	for non-OTG configurations.
-	</para></listitem>
-    <listitem><para>Also on the host side, a driver must support the
-	OTG "Targeted Peripheral List".  That's just a whitelist,
-	used to reject peripherals not supported with a given
-	Linux OTG host.
-	<emphasis>This whitelist is product-specific;
-	each product must modify <filename>otg_whitelist.h</filename>
-	to match its interoperability specification.
-	</emphasis>
-	</para>
-	<para>Non-OTG Linux hosts, like PCs and workstations,
-	normally have some solution for adding drivers, so that
-	peripherals that aren't recognized can eventually be supported.
-	That approach is unreasonable for consumer products that may
-	never have their firmware upgraded, and where it's usually
-	unrealistic to expect traditional PC/workstation/server kinds
-	of support model to work.
-	For example, it's often impractical to change device firmware
-	once the product has been distributed, so driver bugs can't
-	normally be fixed if they're found after shipment.
-	</para></listitem>
-</itemizedlist>
-
-<para>
-Additional changes are needed below those hardware-neutral
-<emphasis>usb_bus</emphasis> and <emphasis>usb_gadget</emphasis>
-driver interfaces; those aren't discussed here in any detail.
-Those affect the hardware-specific code for each USB Host or Peripheral
-controller, and how the HCD initializes (since OTG can be active only
-on a single port).
-They also involve what may be called an <emphasis>OTG Controller
-Driver</emphasis>, managing the OTG transceiver and the OTG state
-machine logic as well as much of the root hub behavior for the
-OTG port.
-The OTG controller driver needs to activate and deactivate USB
-controllers depending on the relevant device role.
-Some related changes were needed inside usbcore, so that it
-can identify OTG-capable devices and respond appropriately
-to HNP or SRP protocols.
-</para> 
-
-</chapter>
-
-</book>
-<!--
-	vim:syntax=sgml:sw=4
--->
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
deleted file mode 100644
index 59fb5c077541..000000000000
--- a/Documentation/DocBook/genericirq.tmpl
+++ /dev/null
@@ -1,520 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="Generic-IRQ-Guide">
- <bookinfo>
-  <title>Linux generic IRQ handling</title>
-
-  <authorgroup>
-   <author>
-    <firstname>Thomas</firstname>
-    <surname>Gleixner</surname>
-    <affiliation>
-     <address>
-      <email>tglx@linutronix.de</email>
-     </address>
-    </affiliation>
-   </author>
-   <author>
-    <firstname>Ingo</firstname>
-    <surname>Molnar</surname>
-    <affiliation>
-     <address>
-      <email>mingo@elte.hu</email>
-     </address>
-    </affiliation>
-   </author>
-  </authorgroup>
-
-  <copyright>
-   <year>2005-2010</year>
-   <holder>Thomas Gleixner</holder>
-  </copyright>
-  <copyright>
-   <year>2005-2006</year>
-   <holder>Ingo Molnar</holder>
-  </copyright>
-
-  <legalnotice>
-   <para>
-     This documentation is free software; you can redistribute
-     it and/or modify it under the terms of the GNU General Public
-     License version 2 as published by the Free Software Foundation.
-   </para>
-
-   <para>
-     This program is distributed in the hope that it will be
-     useful, but WITHOUT ANY WARRANTY; without even the implied
-     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-     See the GNU General Public License for more details.
-   </para>
-
-   <para>
-     You should have received a copy of the GNU General Public
-     License along with this program; if not, write to the Free
-     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-     MA 02111-1307 USA
-   </para>
-
-   <para>
-     For more details see the file COPYING in the source
-     distribution of Linux.
-   </para>
-  </legalnotice>
- </bookinfo>
-
-<toc></toc>
-
-  <chapter id="intro">
-    <title>Introduction</title>
-    <para>
-	The generic interrupt handling layer is designed to provide a
-	complete abstraction of interrupt handling for device drivers.
-	It is able to handle all the different types of interrupt controller
-	hardware. Device drivers use generic API functions to request, enable,
-	disable and free interrupts. The drivers do not have to know anything
-	about interrupt hardware details, so they can be used on different
-	platforms without code changes.
-    </para>
-    <para>
-  	This documentation is provided to developers who want to implement
-	an interrupt subsystem based for their architecture, with the help
-	of the generic IRQ handling layer.
-    </para>
-  </chapter>
-
-  <chapter id="rationale">
-    <title>Rationale</title>
-	<para>
-	The original implementation of interrupt handling in Linux uses
-	the __do_IRQ() super-handler, which is able to deal with every
-	type of interrupt logic.
-	</para>
-	<para>
-	Originally, Russell King identified different types of handlers to
-	build a quite universal set for the ARM interrupt handler
-	implementation in Linux 2.5/2.6. He distinguished between:
-	<itemizedlist>
-	  <listitem><para>Level type</para></listitem>
-	  <listitem><para>Edge type</para></listitem>
-	  <listitem><para>Simple type</para></listitem>
-	</itemizedlist>
-	During the implementation we identified another type:
-	<itemizedlist>
-	  <listitem><para>Fast EOI type</para></listitem>
-	</itemizedlist>
-	In the SMP world of the __do_IRQ() super-handler another type
-	was identified:
-	<itemizedlist>
-	  <listitem><para>Per CPU type</para></listitem>
-	</itemizedlist>
-	</para>
-	<para>
-	This split implementation of high-level IRQ handlers allows us to
-	optimize the flow of the interrupt handling for each specific
-	interrupt type. This reduces complexity in that particular code path
-	and allows the optimized handling of a given type.
-	</para>
-	<para>
-	The original general IRQ implementation used hw_interrupt_type
-	structures and their ->ack(), ->end() [etc.] callbacks to
-	differentiate the flow control in the super-handler. This leads to
-	a mix of flow logic and low-level hardware logic, and it also leads
-	to unnecessary code duplication: for example in i386, there is an
-	ioapic_level_irq and an ioapic_edge_irq IRQ-type which share many
-	of the low-level details but have different flow handling.
-	</para>
-	<para>
-	A more natural abstraction is the clean separation of the
-	'irq flow' and the 'chip details'.
-	</para>
-	<para>
-	Analysing a couple of architecture's IRQ subsystem implementations
-	reveals that most of them can use a generic set of 'irq flow'
-	methods and only need to add the chip-level specific code.
-	The separation is also valuable for (sub)architectures
-	which need specific quirks in the IRQ flow itself but not in the
-	chip details - and thus provides a more transparent IRQ subsystem
-	design.
-	</para>
-	<para>
-	Each interrupt descriptor is assigned its own high-level flow
-	handler, which is normally one of the generic
-	implementations. (This high-level flow handler implementation also
-	makes it simple to provide demultiplexing handlers which can be
-	found in embedded platforms on various architectures.)
-	</para>
-	<para>
-	The separation makes the generic interrupt handling layer more
-	flexible and extensible. For example, an (sub)architecture can
-	use a generic IRQ-flow implementation for 'level type' interrupts
-	and add a (sub)architecture specific 'edge type' implementation.
-	</para>
-	<para>
-	To make the transition to the new model easier and prevent the
-	breakage of existing implementations, the __do_IRQ() super-handler
-	is still available. This leads to a kind of duality for the time
-	being. Over time the new model should be used in more and more
-	architectures, as it enables smaller and cleaner IRQ subsystems.
-	It's deprecated for three years now and about to be removed.
-	</para>
-  </chapter>
-  <chapter id="bugs">
-    <title>Known Bugs And Assumptions</title>
-    <para>
-	None (knock on wood).
-    </para>
-  </chapter>
-
-  <chapter id="Abstraction">
-    <title>Abstraction layers</title>
-    <para>
-	There are three main levels of abstraction in the interrupt code:
-	<orderedlist>
-	  <listitem><para>High-level driver API</para></listitem>
-	  <listitem><para>High-level IRQ flow handlers</para></listitem>
-	  <listitem><para>Chip-level hardware encapsulation</para></listitem>
-	</orderedlist>
-    </para>
-    <sect1 id="Interrupt_control_flow">
-	<title>Interrupt control flow</title>
-	<para>
-	Each interrupt is described by an interrupt descriptor structure
-	irq_desc. The interrupt is referenced by an 'unsigned int' numeric
-	value which selects the corresponding interrupt description structure
-	in the descriptor structures array.
-	The descriptor structure contains status information and pointers
-	to the interrupt flow method and the interrupt chip structure
-	which are assigned to this interrupt.
-	</para>
-	<para>
-	Whenever an interrupt triggers, the low-level architecture code calls
-	into the generic interrupt code by calling desc->handle_irq().
-	This high-level IRQ handling function only uses desc->irq_data.chip
-	primitives referenced by the assigned chip descriptor structure.
-	</para>
-    </sect1>
-    <sect1 id="Highlevel_Driver_API">
-	<title>High-level Driver API</title>
-	<para>
-	  The high-level Driver API consists of following functions:
-	  <itemizedlist>
-	  <listitem><para>request_irq()</para></listitem>
-	  <listitem><para>free_irq()</para></listitem>
-	  <listitem><para>disable_irq()</para></listitem>
-	  <listitem><para>enable_irq()</para></listitem>
-	  <listitem><para>disable_irq_nosync() (SMP only)</para></listitem>
-	  <listitem><para>synchronize_irq() (SMP only)</para></listitem>
-	  <listitem><para>irq_set_irq_type()</para></listitem>
-	  <listitem><para>irq_set_irq_wake()</para></listitem>
-	  <listitem><para>irq_set_handler_data()</para></listitem>
-	  <listitem><para>irq_set_chip()</para></listitem>
-	  <listitem><para>irq_set_chip_data()</para></listitem>
-          </itemizedlist>
-	  See the autogenerated function documentation for details.
-	</para>
-    </sect1>
-    <sect1 id="Highlevel_IRQ_flow_handlers">
-	<title>High-level IRQ flow handlers</title>
-	<para>
-	  The generic layer provides a set of pre-defined irq-flow methods:
-	  <itemizedlist>
-	  <listitem><para>handle_level_irq</para></listitem>
-	  <listitem><para>handle_edge_irq</para></listitem>
-	  <listitem><para>handle_fasteoi_irq</para></listitem>
-	  <listitem><para>handle_simple_irq</para></listitem>
-	  <listitem><para>handle_percpu_irq</para></listitem>
-	  <listitem><para>handle_edge_eoi_irq</para></listitem>
-	  <listitem><para>handle_bad_irq</para></listitem>
-	  </itemizedlist>
-	  The interrupt flow handlers (either pre-defined or architecture
-	  specific) are assigned to specific interrupts by the architecture
-	  either during bootup or during device initialization.
-	</para>
-	<sect2 id="Default_flow_implementations">
-	<title>Default flow implementations</title>
-	    <sect3 id="Helper_functions">
-	 	<title>Helper functions</title>
-		<para>
-		The helper functions call the chip primitives and
-		are used by the default flow implementations.
-		The following helper functions are implemented (simplified excerpt):
-		<programlisting>
-default_enable(struct irq_data *data)
-{
-	desc->irq_data.chip->irq_unmask(data);
-}
-
-default_disable(struct irq_data *data)
-{
-	if (!delay_disable(data))
-		desc->irq_data.chip->irq_mask(data);
-}
-
-default_ack(struct irq_data *data)
-{
-	chip->irq_ack(data);
-}
-
-default_mask_ack(struct irq_data *data)
-{
-	if (chip->irq_mask_ack) {
-		chip->irq_mask_ack(data);
-	} else {
-		chip->irq_mask(data);
-		chip->irq_ack(data);
-	}
-}
-
-noop(struct irq_data *data))
-{
-}
-
-		</programlisting>
-	        </para>
-	    </sect3>
-	</sect2>
-	<sect2 id="Default_flow_handler_implementations">
-	<title>Default flow handler implementations</title>
-	    <sect3 id="Default_Level_IRQ_flow_handler">
-	 	<title>Default Level IRQ flow handler</title>
-		<para>
-		handle_level_irq provides a generic implementation
-		for level-triggered interrupts.
-		</para>
-		<para>
-		The following control flow is implemented (simplified excerpt):
-		<programlisting>
-desc->irq_data.chip->irq_mask_ack();
-handle_irq_event(desc->action);
-desc->irq_data.chip->irq_unmask();
-		</programlisting>
-		</para>
-	    </sect3>
-	    <sect3 id="Default_FASTEOI_IRQ_flow_handler">
-		<title>Default Fast EOI IRQ flow handler</title>
-		<para>
-		handle_fasteoi_irq provides a generic implementation
-		for interrupts, which only need an EOI at the end of
-		the handler.
-		</para>
-		<para>
-		The following control flow is implemented (simplified excerpt):
-		<programlisting>
-handle_irq_event(desc->action);
-desc->irq_data.chip->irq_eoi();
-		</programlisting>
-		</para>
-	    </sect3>
-	    <sect3 id="Default_Edge_IRQ_flow_handler">
-	 	<title>Default Edge IRQ flow handler</title>
-		<para>
-		handle_edge_irq provides a generic implementation
-		for edge-triggered interrupts.
-		</para>
-		<para>
-		The following control flow is implemented (simplified excerpt):
-		<programlisting>
-if (desc->status &amp; running) {
-	desc->irq_data.chip->irq_mask_ack();
-	desc->status |= pending | masked;
-	return;
-}
-desc->irq_data.chip->irq_ack();
-desc->status |= running;
-do {
-	if (desc->status &amp; masked)
-		desc->irq_data.chip->irq_unmask();
-	desc->status &amp;= ~pending;
-	handle_irq_event(desc->action);
-} while (status &amp; pending);
-desc->status &amp;= ~running;
-		</programlisting>
-		</para>
-   	    </sect3>
-	    <sect3 id="Default_simple_IRQ_flow_handler">
-	 	<title>Default simple IRQ flow handler</title>
-		<para>
-		handle_simple_irq provides a generic implementation
-		for simple interrupts.
-		</para>
-		<para>
-		Note: The simple flow handler does not call any
-		handler/chip primitives.
-		</para>
-		<para>
-		The following control flow is implemented (simplified excerpt):
-		<programlisting>
-handle_irq_event(desc->action);
-		</programlisting>
-		</para>
-   	    </sect3>
-	    <sect3 id="Default_per_CPU_flow_handler">
-	 	<title>Default per CPU flow handler</title>
-		<para>
-		handle_percpu_irq provides a generic implementation
-		for per CPU interrupts.
-		</para>
-		<para>
-		Per CPU interrupts are only available on SMP and
-		the handler provides a simplified version without
-		locking.
-		</para>
-		<para>
-		The following control flow is implemented (simplified excerpt):
-		<programlisting>
-if (desc->irq_data.chip->irq_ack)
-	desc->irq_data.chip->irq_ack();
-handle_irq_event(desc->action);
-if (desc->irq_data.chip->irq_eoi)
-        desc->irq_data.chip->irq_eoi();
-		</programlisting>
-		</para>
-   	    </sect3>
-	    <sect3 id="EOI_Edge_IRQ_flow_handler">
-	 	<title>EOI Edge IRQ flow handler</title>
-		<para>
-		handle_edge_eoi_irq provides an abnomination of the edge
-		handler which is solely used to tame a badly wreckaged
-		irq controller on powerpc/cell.
-		</para>
-   	    </sect3>
-	    <sect3 id="BAD_IRQ_flow_handler">
-	 	<title>Bad IRQ flow handler</title>
-		<para>
-		handle_bad_irq is used for spurious interrupts which
-		have no real handler assigned..
-		</para>
-   	    </sect3>
-	</sect2>
-	<sect2 id="Quirks_and_optimizations">
-	<title>Quirks and optimizations</title>
-	<para>
-	The generic functions are intended for 'clean' architectures and chips,
-	which have no platform-specific IRQ handling quirks. If an architecture
-	needs to implement quirks on the 'flow' level then it can do so by
-	overriding the high-level irq-flow handler.
-	</para>
-	</sect2>
-	<sect2 id="Delayed_interrupt_disable">
-	<title>Delayed interrupt disable</title>
-	<para>
-	This per interrupt selectable feature, which was introduced by Russell
-	King in the ARM interrupt implementation, does not mask an interrupt
-	at the hardware level when disable_irq() is called. The interrupt is
-	kept enabled and is masked in the flow handler when an interrupt event
-	happens. This prevents losing edge interrupts on hardware which does
-	not store an edge interrupt event while the interrupt is disabled at
-	the hardware level. When an interrupt arrives while the IRQ_DISABLED
-	flag is set, then the interrupt is masked at the hardware level and
-	the IRQ_PENDING bit is set. When the interrupt is re-enabled by
-	enable_irq() the pending bit is checked and if it is set, the
-	interrupt is resent either via hardware or by a software resend
-	mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
-	you want to use the delayed interrupt disable feature and your
-	hardware is not capable of retriggering	an interrupt.)
-	The delayed interrupt disable is not configurable.
-	</para>
-	</sect2>
-    </sect1>
-    <sect1 id="Chiplevel_hardware_encapsulation">
-	<title>Chip-level hardware encapsulation</title>
-	<para>
-	The chip-level hardware descriptor structure irq_chip
-	contains all the direct chip relevant functions, which
-	can be utilized by the irq flow implementations.
-	  <itemizedlist>
-	  <listitem><para>irq_ack()</para></listitem>
-	  <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
-	  <listitem><para>irq_mask()</para></listitem>
-	  <listitem><para>irq_unmask()</para></listitem>
-	  <listitem><para>irq_eoi() - Optional, required for EOI flow handlers</para></listitem>
-	  <listitem><para>irq_retrigger() - Optional</para></listitem>
-	  <listitem><para>irq_set_type() - Optional</para></listitem>
-	  <listitem><para>irq_set_wake() - Optional</para></listitem>
-	  </itemizedlist>
-	These primitives are strictly intended to mean what they say: ack means
-	ACK, masking means masking of an IRQ line, etc. It is up to the flow
-	handler(s) to use these basic units of low-level functionality.
-	</para>
-    </sect1>
-  </chapter>
-
-  <chapter id="doirq">
-     <title>__do_IRQ entry point</title>
-     <para>
-	The original implementation __do_IRQ() was an alternative entry
-	point for all types of interrupts. It no longer exists.
-     </para>
-     <para>
-	This handler turned out to be not suitable for all
-	interrupt hardware and was therefore reimplemented with split
-	functionality for edge/level/simple/percpu interrupts. This is not
-	only a functional optimization. It also shortens code paths for
-	interrupts.
-      </para>
-  </chapter>
-
-  <chapter id="locking">
-     <title>Locking on SMP</title>
-     <para>
-	The locking of chip registers is up to the architecture that
-	defines the chip primitives. The per-irq structure is
-	protected via desc->lock, by the generic layer.
-     </para>
-  </chapter>
-
-  <chapter id="genericchip">
-     <title>Generic interrupt chip</title>
-     <para>
-       To avoid copies of identical implementations of IRQ chips the
-       core provides a configurable generic interrupt chip
-       implementation. Developers should check carefully whether the
-       generic chip fits their needs before implementing the same
-       functionality slightly differently themselves.
-     </para>
-!Ekernel/irq/generic-chip.c
-  </chapter>
-
-  <chapter id="structs">
-     <title>Structures</title>
-     <para>
-     This chapter contains the autogenerated documentation of the structures which are
-     used in the generic IRQ layer.
-     </para>
-!Iinclude/linux/irq.h
-!Iinclude/linux/interrupt.h
-  </chapter>
-
-  <chapter id="pubfunctions">
-     <title>Public Functions Provided</title>
-     <para>
-     This chapter contains the autogenerated documentation of the kernel API functions
-      which are exported.
-     </para>
-!Ekernel/irq/manage.c
-!Ekernel/irq/chip.c
-  </chapter>
-
-  <chapter id="intfunctions">
-     <title>Internal Functions Provided</title>
-     <para>
-     This chapter contains the autogenerated documentation of the internal functions.
-     </para>
-!Ikernel/irq/irqdesc.c
-!Ikernel/irq/handle.c
-!Ikernel/irq/chip.c
-  </chapter>
-
-  <chapter id="credits">
-     <title>Credits</title>
-	<para>
-		The following people have contributed to this document:
-		<orderedlist>
-			<listitem><para>Thomas Gleixner<email>tglx@linutronix.de</email></para></listitem>
-			<listitem><para>Ingo Molnar<email>mingo@elte.hu</email></para></listitem>
-		</orderedlist>
-	</para>
-  </chapter>
-</book>
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
deleted file mode 100644
index ecfd0ea40661..000000000000
--- a/Documentation/DocBook/kernel-api.tmpl
+++ /dev/null
@@ -1,331 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="LinuxKernelAPI">
- <bookinfo>
-  <title>The Linux Kernel API</title>
-  
-  <legalnotice>
-   <para>
-     This documentation is free software; you can redistribute
-     it and/or modify it under the terms of the GNU General Public
-     License as published by the Free Software Foundation; either
-     version 2 of the License, or (at your option) any later
-     version.
-   </para>
-      
-   <para>
-     This program is distributed in the hope that it will be
-     useful, but WITHOUT ANY WARRANTY; without even the implied
-     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-     See the GNU General Public License for more details.
-   </para>
-      
-   <para>
-     You should have received a copy of the GNU General Public
-     License along with this program; if not, write to the Free
-     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-     MA 02111-1307 USA
-   </para>
-      
-   <para>
-     For more details see the file COPYING in the source
-     distribution of Linux.
-   </para>
-  </legalnotice>
- </bookinfo>
-
-<toc></toc>
-
-  <chapter id="adt">
-     <title>Data Types</title>
-     <sect1><title>Doubly Linked Lists</title>
-!Iinclude/linux/list.h
-     </sect1>
-  </chapter>
-
-  <chapter id="libc">
-     <title>Basic C Library Functions</title>
-
-     <para>
-       When writing drivers, you cannot in general use routines which are
-       from the C Library.  Some of the functions have been found generally
-       useful and they are listed below.  The behaviour of these functions
-       may vary slightly from those defined by ANSI, and these deviations
-       are noted in the text.
-     </para>
-
-     <sect1><title>String Conversions</title>
-!Elib/vsprintf.c
-!Finclude/linux/kernel.h kstrtol
-!Finclude/linux/kernel.h kstrtoul
-!Elib/kstrtox.c
-     </sect1>
-     <sect1><title>String Manipulation</title>
-<!-- All functions are exported at now
-X!Ilib/string.c
- -->
-!Elib/string.c
-     </sect1>
-     <sect1><title>Bit Operations</title>
-!Iarch/x86/include/asm/bitops.h
-     </sect1>
-  </chapter>
-
-  <chapter id="kernel-lib">
-     <title>Basic Kernel Library Functions</title>
-
-     <para>
-       The Linux kernel provides more basic utility functions.
-     </para>
-
-     <sect1><title>Bitmap Operations</title>
-!Elib/bitmap.c
-!Ilib/bitmap.c
-     </sect1>
-
-     <sect1><title>Command-line Parsing</title>
-!Elib/cmdline.c
-     </sect1>
-
-     <sect1 id="crc"><title>CRC Functions</title>
-!Elib/crc7.c
-!Elib/crc16.c
-!Elib/crc-itu-t.c
-!Elib/crc32.c
-!Elib/crc-ccitt.c
-     </sect1>
-
-     <sect1 id="idr"><title>idr/ida Functions</title>
-!Pinclude/linux/idr.h idr sync
-!Plib/idr.c IDA description
-!Elib/idr.c
-     </sect1>
-  </chapter>
-
-  <chapter id="mm">
-     <title>Memory Management in Linux</title>
-     <sect1><title>The Slab Cache</title>
-!Iinclude/linux/slab.h
-!Emm/slab.c
-!Emm/util.c
-     </sect1>
-     <sect1><title>User Space Memory Access</title>
-!Iarch/x86/include/asm/uaccess_32.h
-!Earch/x86/lib/usercopy_32.c
-     </sect1>
-     <sect1><title>More Memory Management Functions</title>
-!Emm/readahead.c
-!Emm/filemap.c
-!Emm/memory.c
-!Emm/vmalloc.c
-!Imm/page_alloc.c
-!Emm/mempool.c
-!Emm/dmapool.c
-!Emm/page-writeback.c
-!Emm/truncate.c
-     </sect1>
-  </chapter>
-
-
-  <chapter id="ipc">
-     <title>Kernel IPC facilities</title>
-
-     <sect1><title>IPC utilities</title>
-!Iipc/util.c
-     </sect1>
-  </chapter>
-
-  <chapter id="kfifo">
-     <title>FIFO Buffer</title>
-     <sect1><title>kfifo interface</title>
-!Iinclude/linux/kfifo.h
-     </sect1>
-  </chapter>
-
-  <chapter id="relayfs">
-     <title>relay interface support</title>
-
-     <para>
-	Relay interface support
-	is designed to provide an efficient mechanism for tools and
-	facilities to relay large amounts of data from kernel space to
-	user space.
-     </para>
-
-     <sect1><title>relay interface</title>
-!Ekernel/relay.c
-!Ikernel/relay.c
-     </sect1>
-  </chapter>
-
-  <chapter id="modload">
-     <title>Module Support</title>
-     <sect1><title>Module Loading</title>
-!Ekernel/kmod.c
-     </sect1>
-     <sect1><title>Inter Module support</title>
-        <para>
-           Refer to the file kernel/module.c for more information.
-        </para>
-<!-- FIXME: Removed for now since no structured comments in source
-X!Ekernel/module.c
--->
-     </sect1>
-  </chapter>
-
-  <chapter id="hardware">
-     <title>Hardware Interfaces</title>
-     <sect1><title>Interrupt Handling</title>
-!Ekernel/irq/manage.c
-     </sect1>
-
-     <sect1><title>DMA Channels</title>
-!Ekernel/dma.c
-     </sect1>
-
-     <sect1><title>Resources Management</title>
-!Ikernel/resource.c
-!Ekernel/resource.c
-     </sect1>
-
-     <sect1><title>MTRR Handling</title>
-!Earch/x86/kernel/cpu/mtrr/main.c
-     </sect1>
-
-     <sect1><title>PCI Support Library</title>
-!Edrivers/pci/pci.c
-!Edrivers/pci/pci-driver.c
-!Edrivers/pci/remove.c
-!Edrivers/pci/search.c
-!Edrivers/pci/msi.c
-!Edrivers/pci/bus.c
-!Edrivers/pci/access.c
-!Edrivers/pci/irq.c
-!Edrivers/pci/htirq.c
-<!-- FIXME: Removed for now since no structured comments in source
-X!Edrivers/pci/hotplug.c
--->
-!Edrivers/pci/probe.c
-!Edrivers/pci/slot.c
-!Edrivers/pci/rom.c
-!Edrivers/pci/iov.c
-!Idrivers/pci/pci-sysfs.c
-     </sect1>
-     <sect1><title>PCI Hotplug Support Library</title>
-!Edrivers/pci/hotplug/pci_hotplug_core.c
-     </sect1>
-  </chapter>
-
-  <chapter id="firmware">
-     <title>Firmware Interfaces</title>
-     <sect1><title>DMI Interfaces</title>
-!Edrivers/firmware/dmi_scan.c
-     </sect1>
-     <sect1><title>EDD Interfaces</title>
-!Idrivers/firmware/edd.c
-     </sect1>
-  </chapter>
-
-  <chapter id="security">
-     <title>Security Framework</title>
-!Isecurity/security.c
-!Esecurity/inode.c
-  </chapter>
-
-  <chapter id="audit">
-     <title>Audit Interfaces</title>
-!Ekernel/audit.c
-!Ikernel/auditsc.c
-!Ikernel/auditfilter.c
-  </chapter>
-
-  <chapter id="accounting">
-     <title>Accounting Framework</title>
-!Ikernel/acct.c
-  </chapter>
-
-  <chapter id="blkdev">
-     <title>Block Devices</title>
-!Eblock/blk-core.c
-!Iblock/blk-core.c
-!Eblock/blk-map.c
-!Iblock/blk-sysfs.c
-!Eblock/blk-settings.c
-!Eblock/blk-exec.c
-!Eblock/blk-flush.c
-!Eblock/blk-lib.c
-!Eblock/blk-tag.c
-!Iblock/blk-tag.c
-!Eblock/blk-integrity.c
-!Ikernel/trace/blktrace.c
-!Iblock/genhd.c
-!Eblock/genhd.c
-  </chapter>
-
-  <chapter id="chrdev">
-	<title>Char devices</title>
-!Efs/char_dev.c
-  </chapter>
-
-  <chapter id="miscdev">
-     <title>Miscellaneous Devices</title>
-!Edrivers/char/misc.c
-  </chapter>
-
-  <chapter id="clk">
-     <title>Clock Framework</title>
-
-     <para>
-	The clock framework defines programming interfaces to support
-	software management of the system clock tree.
-	This framework is widely used with System-On-Chip (SOC) platforms
-	to support power management and various devices which may need
-	custom clock rates.
-	Note that these "clocks" don't relate to timekeeping or real
-	time clocks (RTCs), each of which have separate frameworks.
-	These <structname>struct clk</structname> instances may be used
-	to manage for example a 96 MHz signal that is used to shift bits
-	into and out of peripherals or busses, or otherwise trigger
-	synchronous state machine transitions in system hardware.
-     </para>
-
-     <para>
-	Power management is supported by explicit software clock gating:
-	unused clocks are disabled, so the system doesn't waste power
-	changing the state of transistors that aren't in active use.
-	On some systems this may be backed by hardware clock gating,
-	where clocks are gated without being disabled in software.
-	Sections of chips that are powered but not clocked may be able
-	to retain their last state.
-	This low power state is often called a <emphasis>retention
-	mode</emphasis>.
-	This mode still incurs leakage currents, especially with finer
-	circuit geometries, but for CMOS circuits power is mostly used
-	by clocked state changes.
-     </para>
-
-     <para>
-	Power-aware drivers only enable their clocks when the device
-	they manage is in active use.  Also, system sleep states often
-	differ according to which clock domains are active:  while a
-	"standby" state may allow wakeup from several active domains, a
-	"mem" (suspend-to-RAM) state may require a more wholesale shutdown
-	of clocks derived from higher speed PLLs and oscillators, limiting
-	the number of possible wakeup event sources.  A driver's suspend
-	method may need to be aware of system-specific clock constraints
-	on the target sleep state.
-     </para>
-
-     <para>
-        Some platforms support programmable clock generators.  These
-	can be used by external chips of various kinds, such as other
-	CPUs, multimedia codecs, and devices with strict requirements
-	for interface clocking.
-     </para>
-
-!Iinclude/linux/clk.h
-  </chapter>
-
-</book>
diff --git a/Documentation/DocBook/writing_musb_glue_layer.tmpl b/Documentation/DocBook/writing_musb_glue_layer.tmpl
deleted file mode 100644
index 837eca77f274..000000000000
--- a/Documentation/DocBook/writing_musb_glue_layer.tmpl
+++ /dev/null
@@ -1,873 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="Writing-MUSB-Glue-Layer">
- <bookinfo>
-  <title>Writing an MUSB Glue Layer</title>
-
-  <authorgroup>
-   <author>
-    <firstname>Apelete</firstname>
-    <surname>Seketeli</surname>
-    <affiliation>
-     <address>
-      <email>apelete at seketeli.net</email>
-     </address>
-    </affiliation>
-   </author>
-  </authorgroup>
-
-  <copyright>
-   <year>2014</year>
-   <holder>Apelete Seketeli</holder>
-  </copyright>
-
-  <legalnotice>
-   <para>
-     This documentation is free software; you can redistribute it
-     and/or modify it under the terms of the GNU General Public
-     License as published by the Free Software Foundation; either
-     version 2 of the License, or (at your option) any later version.
-   </para>
-
-   <para>
-     This documentation is distributed in the hope that it will be
-     useful, but WITHOUT ANY WARRANTY; without even the implied
-     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-     See the GNU General Public License for more details.
-   </para>
-
-   <para>
-     You should have received a copy of the GNU General Public License
-     along with this documentation; if not, write to the Free Software
-     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
-     02111-1307 USA
-   </para>
-
-   <para>
-     For more details see the file COPYING in the Linux kernel source
-     tree.
-   </para>
-  </legalnotice>
- </bookinfo>
-
-<toc></toc>
-
-  <chapter id="introduction">
-    <title>Introduction</title>
-    <para>
-      The Linux MUSB subsystem is part of the larger Linux USB
-      subsystem. It provides support for embedded USB Device Controllers
-      (UDC) that do not use Universal Host Controller Interface (UHCI)
-      or Open Host Controller Interface (OHCI).
-    </para>
-    <para>
-      Instead, these embedded UDC rely on the USB On-the-Go (OTG)
-      specification which they implement at least partially. The silicon
-      reference design used in most cases is the Multipoint USB
-      Highspeed Dual-Role Controller (MUSB HDRC) found in the Mentor
-      Graphics Inventraâ„¢ design.
-    </para>
-    <para>
-      As a self-taught exercise I have written an MUSB glue layer for
-      the Ingenic JZ4740 SoC, modelled after the many MUSB glue layers
-      in the kernel source tree. This layer can be found at
-      drivers/usb/musb/jz4740.c. In this documentation I will walk
-      through the basics of the jz4740.c glue layer, explaining the
-      different pieces and what needs to be done in order to write your
-      own device glue layer.
-    </para>
-  </chapter>
-
-  <chapter id="linux-musb-basics">
-    <title>Linux MUSB Basics</title>
-    <para>
-      To get started on the topic, please read USB On-the-Go Basics (see
-      Resources) which provides an introduction of USB OTG operation at
-      the hardware level. A couple of wiki pages by Texas Instruments
-      and Analog Devices also provide an overview of the Linux kernel
-      MUSB configuration, albeit focused on some specific devices
-      provided by these companies. Finally, getting acquainted with the
-      USB specification at USB home page may come in handy, with
-      practical instance provided through the Writing USB Device Drivers
-      documentation (again, see Resources).
-    </para>
-    <para>
-      Linux USB stack is a layered architecture in which the MUSB
-      controller hardware sits at the lowest. The MUSB controller driver
-      abstract the MUSB controller hardware to the Linux USB stack.
-    </para>
-    <programlisting>
-      ------------------------
-      |                      | &lt;------- drivers/usb/gadget
-      | Linux USB Core Stack | &lt;------- drivers/usb/host
-      |                      | &lt;------- drivers/usb/core
-      ------------------------
-                 �
-     --------------------------
-     |                        | &lt;------ drivers/usb/musb/musb_gadget.c
-     | MUSB Controller driver | &lt;------ drivers/usb/musb/musb_host.c
-     |                        | &lt;------ drivers/usb/musb/musb_core.c
-     --------------------------
-                 �
-  ---------------------------------
-  | MUSB Platform Specific Driver |
-  |                               | &lt;-- drivers/usb/musb/jz4740.c
-  |       aka &quot;Glue Layer&quot;        |
-  ---------------------------------
-                 �
-  ---------------------------------
-  |   MUSB Controller Hardware    |
-  ---------------------------------
-    </programlisting>
-    <para>
-      As outlined above, the glue layer is actually the platform
-      specific code sitting in between the controller driver and the
-      controller hardware.
-    </para>
-    <para>
-      Just like a Linux USB driver needs to register itself with the
-      Linux USB subsystem, the MUSB glue layer needs first to register
-      itself with the MUSB controller driver. This will allow the
-      controller driver to know about which device the glue layer
-      supports and which functions to call when a supported device is
-      detected or released; remember we are talking about an embedded
-      controller chip here, so no insertion or removal at run-time.
-    </para>
-    <para>
-      All of this information is passed to the MUSB controller driver
-      through a platform_driver structure defined in the glue layer as:
-    </para>
-    <programlisting linenumbering="numbered">
-static struct platform_driver jz4740_driver = {
-	.probe		= jz4740_probe,
-	.remove		= jz4740_remove,
-	.driver		= {
-		.name	= "musb-jz4740",
-	},
-};
-    </programlisting>
-    <para>
-      The probe and remove function pointers are called when a matching
-      device is detected and, respectively, released. The name string
-      describes the device supported by this glue layer. In the current
-      case it matches a platform_device structure declared in
-      arch/mips/jz4740/platform.c. Note that we are not using device
-      tree bindings here.
-    </para>
-    <para>
-      In order to register itself to the controller driver, the glue
-      layer goes through a few steps, basically allocating the
-      controller hardware resources and initialising a couple of
-      circuits. To do so, it needs to keep track of the information used
-      throughout these steps. This is done by defining a private
-      jz4740_glue structure:
-    </para>
-    <programlisting linenumbering="numbered">
-struct jz4740_glue {
-	struct device           *dev;
-	struct platform_device  *musb;
-	struct clk		*clk;
-};
-    </programlisting>
-    <para>
-      The dev and musb members are both device structure variables. The
-      first one holds generic information about the device, since it's
-      the basic device structure, and the latter holds information more
-      closely related to the subsystem the device is registered to. The
-      clk variable keeps information related to the device clock
-      operation.
-    </para>
-    <para>
-      Let's go through the steps of the probe function that leads the
-      glue layer to register itself to the controller driver.
-    </para>
-    <para>
-      N.B.: For the sake of readability each function will be split in
-      logical parts, each part being shown as if it was independent from
-      the others.
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_probe(struct platform_device *pdev)
-{
-	struct platform_device		*musb;
-	struct jz4740_glue		*glue;
-	struct clk                      *clk;
-	int				ret;
-
-	glue = devm_kzalloc(&amp;pdev->dev, sizeof(*glue), GFP_KERNEL);
-	if (!glue)
-		return -ENOMEM;
-
-	musb = platform_device_alloc("musb-hdrc", PLATFORM_DEVID_AUTO);
-	if (!musb) {
-		dev_err(&amp;pdev->dev, "failed to allocate musb device\n");
-		return -ENOMEM;
-	}
-
-	clk = devm_clk_get(&amp;pdev->dev, "udc");
-	if (IS_ERR(clk)) {
-		dev_err(&amp;pdev->dev, "failed to get clock\n");
-		ret = PTR_ERR(clk);
-		goto err_platform_device_put;
-	}
-
-	ret = clk_prepare_enable(clk);
-	if (ret) {
-		dev_err(&amp;pdev->dev, "failed to enable clock\n");
-		goto err_platform_device_put;
-	}
-
-	musb->dev.parent		= &amp;pdev->dev;
-
-	glue->dev			= &amp;pdev->dev;
-	glue->musb			= musb;
-	glue->clk			= clk;
-
-	return 0;
-
-err_platform_device_put:
-	platform_device_put(musb);
-	return ret;
-}
-    </programlisting>
-    <para>
-      The first few lines of the probe function allocate and assign the
-      glue, musb and clk variables. The GFP_KERNEL flag (line 8) allows
-      the allocation process to sleep and wait for memory, thus being
-      usable in a blocking situation. The PLATFORM_DEVID_AUTO flag (line
-      12) allows automatic allocation and management of device IDs in
-      order to avoid device namespace collisions with explicit IDs. With
-      devm_clk_get() (line 18) the glue layer allocates the clock -- the
-      <literal>devm_</literal> prefix indicates that clk_get() is
-      managed: it automatically frees the allocated clock resource data
-      when the device is released -- and enable it.
-    </para>
-    <para>
-      Then comes the registration steps:
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_probe(struct platform_device *pdev)
-{
-	struct musb_hdrc_platform_data	*pdata = &amp;jz4740_musb_platform_data;
-
-	pdata->platform_ops		= &amp;jz4740_musb_ops;
-
-	platform_set_drvdata(pdev, glue);
-
-	ret = platform_device_add_resources(musb, pdev->resource,
-					    pdev->num_resources);
-	if (ret) {
-		dev_err(&amp;pdev->dev, "failed to add resources\n");
-		goto err_clk_disable;
-	}
-
-	ret = platform_device_add_data(musb, pdata, sizeof(*pdata));
-	if (ret) {
-		dev_err(&amp;pdev->dev, "failed to add platform_data\n");
-		goto err_clk_disable;
-	}
-
-	return 0;
-
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_platform_device_put:
-	platform_device_put(musb);
-	return ret;
-}
-    </programlisting>
-    <para>
-      The first step is to pass the device data privately held by the
-      glue layer on to the controller driver through
-      platform_set_drvdata() (line 7). Next is passing on the device
-      resources information, also privately held at that point, through
-      platform_device_add_resources() (line 9).
-    </para>
-    <para>
-      Finally comes passing on the platform specific data to the
-      controller driver (line 16). Platform data will be discussed in
-      <link linkend="device-platform-data">Chapter 4</link>, but here
-      we are looking at the platform_ops function pointer (line 5) in
-      musb_hdrc_platform_data structure (line 3).  This function
-      pointer allows the MUSB controller driver to know which function
-      to call for device operation:
-    </para>
-    <programlisting linenumbering="numbered">
-static const struct musb_platform_ops jz4740_musb_ops = {
-	.init		= jz4740_musb_init,
-	.exit		= jz4740_musb_exit,
-};
-    </programlisting>
-    <para>
-      Here we have the minimal case where only init and exit functions
-      are called by the controller driver when needed. Fact is the
-      JZ4740 MUSB controller is a basic controller, lacking some
-      features found in other controllers, otherwise we may also have
-      pointers to a few other functions like a power management function
-      or a function to switch between OTG and non-OTG modes, for
-      instance.
-    </para>
-    <para>
-      At that point of the registration process, the controller driver
-      actually calls the init function:
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_musb_init(struct musb *musb)
-{
-	musb->xceiv = usb_get_phy(USB_PHY_TYPE_USB2);
-	if (!musb->xceiv) {
-		pr_err("HS UDC: no transceiver configured\n");
-		return -ENODEV;
-	}
-
-	/* Silicon does not implement ConfigData register.
-	 * Set dyn_fifo to avoid reading EP config from hardware.
-	 */
-	musb->dyn_fifo = true;
-
-	musb->isr = jz4740_musb_interrupt;
-
-	return 0;
-}
-    </programlisting>
-    <para>
-      The goal of jz4740_musb_init() is to get hold of the transceiver
-      driver data of the MUSB controller hardware and pass it on to the
-      MUSB controller driver, as usual. The transceiver is the circuitry
-      inside the controller hardware responsible for sending/receiving
-      the USB data. Since it is an implementation of the physical layer
-      of the OSI model, the transceiver is also referred to as PHY.
-    </para>
-    <para>
-      Getting hold of the MUSB PHY driver data is done with
-      usb_get_phy() which returns a pointer to the structure
-      containing the driver instance data. The next couple of
-      instructions (line 12 and 14) are used as a quirk and to setup
-      IRQ handling respectively. Quirks and IRQ handling will be
-      discussed later in <link linkend="device-quirks">Chapter
-      5</link> and <link linkend="handling-irqs">Chapter 3</link>.
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_musb_exit(struct musb *musb)
-{
-	usb_put_phy(musb->xceiv);
-
-	return 0;
-}
-    </programlisting>
-    <para>
-      Acting as the counterpart of init, the exit function releases the
-      MUSB PHY driver when the controller hardware itself is about to be
-      released.
-    </para>
-    <para>
-      Again, note that init and exit are fairly simple in this case due
-      to the basic set of features of the JZ4740 controller hardware.
-      When writing an musb glue layer for a more complex controller
-      hardware, you might need to take care of more processing in those
-      two functions.
-    </para>
-    <para>
-      Returning from the init function, the MUSB controller driver jumps
-      back into the probe function:
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_probe(struct platform_device *pdev)
-{
-	ret = platform_device_add(musb);
-	if (ret) {
-		dev_err(&amp;pdev->dev, "failed to register musb device\n");
-		goto err_clk_disable;
-	}
-
-	return 0;
-
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_platform_device_put:
-	platform_device_put(musb);
-	return ret;
-}
-    </programlisting>
-    <para>
-      This is the last part of the device registration process where the
-      glue layer adds the controller hardware device to Linux kernel
-      device hierarchy: at this stage, all known information about the
-      device is passed on to the Linux USB core stack.
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_remove(struct platform_device *pdev)
-{
-	struct jz4740_glue	*glue = platform_get_drvdata(pdev);
-
-	platform_device_unregister(glue->musb);
-	clk_disable_unprepare(glue->clk);
-
-	return 0;
-}
-    </programlisting>
-    <para>
-      Acting as the counterpart of probe, the remove function unregister
-      the MUSB controller hardware (line 5) and disable the clock (line
-      6), allowing it to be gated.
-    </para>
-  </chapter>
-
-  <chapter id="handling-irqs">
-    <title>Handling IRQs</title>
-    <para>
-      Additionally to the MUSB controller hardware basic setup and
-      registration, the glue layer is also responsible for handling the
-      IRQs:
-    </para>
-    <programlisting linenumbering="numbered">
-static irqreturn_t jz4740_musb_interrupt(int irq, void *__hci)
-{
-	unsigned long   flags;
-	irqreturn_t     retval = IRQ_NONE;
-	struct musb     *musb = __hci;
-
-	spin_lock_irqsave(&amp;musb->lock, flags);
-
-	musb->int_usb = musb_readb(musb->mregs, MUSB_INTRUSB);
-	musb->int_tx = musb_readw(musb->mregs, MUSB_INTRTX);
-	musb->int_rx = musb_readw(musb->mregs, MUSB_INTRRX);
-
-	/*
-	 * The controller is gadget only, the state of the host mode IRQ bits is
-	 * undefined. Mask them to make sure that the musb driver core will
-	 * never see them set
-	 */
-	musb->int_usb &amp;= MUSB_INTR_SUSPEND | MUSB_INTR_RESUME |
-	    MUSB_INTR_RESET | MUSB_INTR_SOF;
-
-	if (musb->int_usb || musb->int_tx || musb->int_rx)
-		retval = musb_interrupt(musb);
-
-	spin_unlock_irqrestore(&amp;musb->lock, flags);
-
-	return retval;
-}
-    </programlisting>
-    <para>
-      Here the glue layer mostly has to read the relevant hardware
-      registers and pass their values on to the controller driver which
-      will handle the actual event that triggered the IRQ.
-    </para>
-    <para>
-      The interrupt handler critical section is protected by the
-      spin_lock_irqsave() and counterpart spin_unlock_irqrestore()
-      functions (line 7 and 24 respectively), which prevent the
-      interrupt handler code to be run by two different threads at the
-      same time.
-    </para>
-    <para>
-      Then the relevant interrupt registers are read (line 9 to 11):
-    </para>
-    <itemizedlist>
-      <listitem>
-        <para>
-          MUSB_INTRUSB: indicates which USB interrupts are currently
-          active,
-        </para>
-      </listitem>
-      <listitem>
-        <para>
-          MUSB_INTRTX: indicates which of the interrupts for TX
-          endpoints are currently active,
-        </para>
-      </listitem>
-      <listitem>
-        <para>
-          MUSB_INTRRX: indicates which of the interrupts for TX
-          endpoints are currently active.
-        </para>
-      </listitem>
-    </itemizedlist>
-    <para>
-      Note that musb_readb() is used to read 8-bit registers at most,
-      while musb_readw() allows us to read at most 16-bit registers.
-      There are other functions that can be used depending on the size
-      of your device registers. See musb_io.h for more information.
-    </para>
-    <para>
-      Instruction on line 18 is another quirk specific to the JZ4740
-      USB device controller, which will be discussed later in <link
-      linkend="device-quirks">Chapter 5</link>.
-    </para>
-    <para>
-      The glue layer still needs to register the IRQ handler though.
-      Remember the instruction on line 14 of the init function:
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_musb_init(struct musb *musb)
-{
-	musb->isr = jz4740_musb_interrupt;
-
-	return 0;
-}
-    </programlisting>
-    <para>
-      This instruction sets a pointer to the glue layer IRQ handler
-      function, in order for the controller hardware to call the handler
-      back when an IRQ comes from the controller hardware. The interrupt
-      handler is now implemented and registered.
-    </para>
-  </chapter>
-
-  <chapter id="device-platform-data">
-    <title>Device Platform Data</title>
-    <para>
-      In order to write an MUSB glue layer, you need to have some data
-      describing the hardware capabilities of your controller hardware,
-      which is called the platform data.
-    </para>
-    <para>
-      Platform data is specific to your hardware, though it may cover a
-      broad range of devices, and is generally found somewhere in the
-      arch/ directory, depending on your device architecture.
-    </para>
-    <para>
-      For instance, platform data for the JZ4740 SoC is found in
-      arch/mips/jz4740/platform.c. In the platform.c file each device of
-      the JZ4740 SoC is described through a set of structures.
-    </para>
-    <para>
-      Here is the part of arch/mips/jz4740/platform.c that covers the
-      USB Device Controller (UDC):
-    </para>
-    <programlisting linenumbering="numbered">
-/* USB Device Controller */
-struct platform_device jz4740_udc_xceiv_device = {
-	.name = "usb_phy_gen_xceiv",
-	.id   = 0,
-};
-
-static struct resource jz4740_udc_resources[] = {
-	[0] = {
-		.start = JZ4740_UDC_BASE_ADDR,
-		.end   = JZ4740_UDC_BASE_ADDR + 0x10000 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = JZ4740_IRQ_UDC,
-		.end   = JZ4740_IRQ_UDC,
-		.flags = IORESOURCE_IRQ,
-		.name  = "mc",
-	},
-};
-
-struct platform_device jz4740_udc_device = {
-	.name = "musb-jz4740",
-	.id   = -1,
-	.dev  = {
-		.dma_mask          = &amp;jz4740_udc_device.dev.coherent_dma_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-	},
-	.num_resources = ARRAY_SIZE(jz4740_udc_resources),
-	.resource      = jz4740_udc_resources,
-};
-    </programlisting>
-    <para>
-      The jz4740_udc_xceiv_device platform device structure (line 2)
-      describes the UDC transceiver with a name and id number.
-    </para>
-    <para>
-      At the time of this writing, note that
-      &quot;usb_phy_gen_xceiv&quot; is the specific name to be used for
-      all transceivers that are either built-in with reference USB IP or
-      autonomous and doesn't require any PHY programming. You will need
-      to set CONFIG_NOP_USB_XCEIV=y in the kernel configuration to make
-      use of the corresponding transceiver driver. The id field could be
-      set to -1 (equivalent to PLATFORM_DEVID_NONE), -2 (equivalent to
-      PLATFORM_DEVID_AUTO) or start with 0 for the first device of this
-      kind if we want a specific id number.
-    </para>
-    <para>
-      The jz4740_udc_resources resource structure (line 7) defines the
-      UDC registers base addresses.
-    </para>
-    <para>
-      The first array (line 9 to 11) defines the UDC registers base
-      memory addresses: start points to the first register memory
-      address, end points to the last register memory address and the
-      flags member defines the type of resource we are dealing with. So
-      IORESOURCE_MEM is used to define the registers memory addresses.
-      The second array (line 14 to 17) defines the UDC IRQ registers
-      addresses. Since there is only one IRQ register available for the
-      JZ4740 UDC, start and end point at the same address. The
-      IORESOURCE_IRQ flag tells that we are dealing with IRQ resources,
-      and the name &quot;mc&quot; is in fact hard-coded in the MUSB core
-      in order for the controller driver to retrieve this IRQ resource
-      by querying it by its name.
-    </para>
-    <para>
-      Finally, the jz4740_udc_device platform device structure (line 21)
-      describes the UDC itself.
-    </para>
-    <para>
-      The &quot;musb-jz4740&quot; name (line 22) defines the MUSB
-      driver that is used for this device; remember this is in fact
-      the name that we used in the jz4740_driver platform driver
-      structure in <link linkend="linux-musb-basics">Chapter
-      2</link>. The id field (line 23) is set to -1 (equivalent to
-      PLATFORM_DEVID_NONE) since we do not need an id for the device:
-      the MUSB controller driver was already set to allocate an
-      automatic id in <link linkend="linux-musb-basics">Chapter
-      2</link>. In the dev field we care for DMA related information
-      here. The dma_mask field (line 25) defines the width of the DMA
-      mask that is going to be used, and coherent_dma_mask (line 26)
-      has the same purpose but for the alloc_coherent DMA mappings: in
-      both cases we are using a 32 bits mask. Then the resource field
-      (line 29) is simply a pointer to the resource structure defined
-      before, while the num_resources field (line 28) keeps track of
-      the number of arrays defined in the resource structure (in this
-      case there were two resource arrays defined before).
-    </para>
-    <para>
-      With this quick overview of the UDC platform data at the arch/
-      level now done, let's get back to the MUSB glue layer specific
-      platform data in drivers/usb/musb/jz4740.c:
-    </para>
-    <programlisting linenumbering="numbered">
-static struct musb_hdrc_config jz4740_musb_config = {
-	/* Silicon does not implement USB OTG. */
-	.multipoint = 0,
-	/* Max EPs scanned, driver will decide which EP can be used. */
-	.num_eps    = 4,
-	/* RAMbits needed to configure EPs from table */
-	.ram_bits   = 9,
-	.fifo_cfg = jz4740_musb_fifo_cfg,
-	.fifo_cfg_size = ARRAY_SIZE(jz4740_musb_fifo_cfg),
-};
-
-static struct musb_hdrc_platform_data jz4740_musb_platform_data = {
-	.mode   = MUSB_PERIPHERAL,
-	.config = &amp;jz4740_musb_config,
-};
-    </programlisting>
-    <para>
-      First the glue layer configures some aspects of the controller
-      driver operation related to the controller hardware specifics.
-      This is done through the jz4740_musb_config musb_hdrc_config
-      structure.
-    </para>
-    <para>
-      Defining the OTG capability of the controller hardware, the
-      multipoint member (line 3) is set to 0 (equivalent to false)
-      since the JZ4740 UDC is not OTG compatible. Then num_eps (line
-      5) defines the number of USB endpoints of the controller
-      hardware, including endpoint 0: here we have 3 endpoints +
-      endpoint 0. Next is ram_bits (line 7) which is the width of the
-      RAM address bus for the MUSB controller hardware. This
-      information is needed when the controller driver cannot
-      automatically configure endpoints by reading the relevant
-      controller hardware registers. This issue will be discussed when
-      we get to device quirks in <link linkend="device-quirks">Chapter
-      5</link>. Last two fields (line 8 and 9) are also about device
-      quirks: fifo_cfg points to the USB endpoints configuration table
-      and fifo_cfg_size keeps track of the size of the number of
-      entries in that configuration table. More on that later in <link
-      linkend="device-quirks">Chapter 5</link>.
-    </para>
-    <para>
-      Then this configuration is embedded inside
-      jz4740_musb_platform_data musb_hdrc_platform_data structure (line
-      11): config is a pointer to the configuration structure itself,
-      and mode tells the controller driver if the controller hardware
-      may be used as MUSB_HOST only, MUSB_PERIPHERAL only or MUSB_OTG
-      which is a dual mode.
-    </para>
-    <para>
-      Remember that jz4740_musb_platform_data is then used to convey
-      platform data information as we have seen in the probe function
-      in <link linkend="linux-musb-basics">Chapter 2</link>
-    </para>
-  </chapter>
-
-  <chapter id="device-quirks">
-    <title>Device Quirks</title>
-    <para>
-      Completing the platform data specific to your device, you may also
-      need to write some code in the glue layer to work around some
-      device specific limitations. These quirks may be due to some
-      hardware bugs, or simply be the result of an incomplete
-      implementation of the USB On-the-Go specification.
-    </para>
-    <para>
-      The JZ4740 UDC exhibits such quirks, some of which we will discuss
-      here for the sake of insight even though these might not be found
-      in the controller hardware you are working on.
-    </para>
-    <para>
-      Let's get back to the init function first:
-    </para>
-    <programlisting linenumbering="numbered">
-static int jz4740_musb_init(struct musb *musb)
-{
-	musb->xceiv = usb_get_phy(USB_PHY_TYPE_USB2);
-	if (!musb->xceiv) {
-		pr_err("HS UDC: no transceiver configured\n");
-		return -ENODEV;
-	}
-
-	/* Silicon does not implement ConfigData register.
-	 * Set dyn_fifo to avoid reading EP config from hardware.
-	 */
-	musb->dyn_fifo = true;
-
-	musb->isr = jz4740_musb_interrupt;
-
-	return 0;
-}
-    </programlisting>
-    <para>
-      Instruction on line 12 helps the MUSB controller driver to work
-      around the fact that the controller hardware is missing registers
-      that are used for USB endpoints configuration.
-    </para>
-    <para>
-      Without these registers, the controller driver is unable to read
-      the endpoints configuration from the hardware, so we use line 12
-      instruction to bypass reading the configuration from silicon, and
-      rely on a hard-coded table that describes the endpoints
-      configuration instead:
-    </para>
-    <programlisting linenumbering="numbered">
-static struct musb_fifo_cfg jz4740_musb_fifo_cfg[] = {
-{ .hw_ep_num = 1, .style = FIFO_TX, .maxpacket = 512, },
-{ .hw_ep_num = 1, .style = FIFO_RX, .maxpacket = 512, },
-{ .hw_ep_num = 2, .style = FIFO_TX, .maxpacket = 64, },
-};
-    </programlisting>
-    <para>
-      Looking at the configuration table above, we see that each
-      endpoints is described by three fields: hw_ep_num is the endpoint
-      number, style is its direction (either FIFO_TX for the controller
-      driver to send packets in the controller hardware, or FIFO_RX to
-      receive packets from hardware), and maxpacket defines the maximum
-      size of each data packet that can be transmitted over that
-      endpoint. Reading from the table, the controller driver knows that
-      endpoint 1 can be used to send and receive USB data packets of 512
-      bytes at once (this is in fact a bulk in/out endpoint), and
-      endpoint 2 can be used to send data packets of 64 bytes at once
-      (this is in fact an interrupt endpoint).
-    </para>
-    <para>
-      Note that there is no information about endpoint 0 here: that one
-      is implemented by default in every silicon design, with a
-      predefined configuration according to the USB specification. For
-      more examples of endpoint configuration tables, see musb_core.c.
-    </para>
-    <para>
-      Let's now get back to the interrupt handler function:
-    </para>
-    <programlisting linenumbering="numbered">
-static irqreturn_t jz4740_musb_interrupt(int irq, void *__hci)
-{
-	unsigned long   flags;
-	irqreturn_t     retval = IRQ_NONE;
-	struct musb     *musb = __hci;
-
-	spin_lock_irqsave(&amp;musb->lock, flags);
-
-	musb->int_usb = musb_readb(musb->mregs, MUSB_INTRUSB);
-	musb->int_tx = musb_readw(musb->mregs, MUSB_INTRTX);
-	musb->int_rx = musb_readw(musb->mregs, MUSB_INTRRX);
-
-	/*
-	 * The controller is gadget only, the state of the host mode IRQ bits is
-	 * undefined. Mask them to make sure that the musb driver core will
-	 * never see them set
-	 */
-	musb->int_usb &amp;= MUSB_INTR_SUSPEND | MUSB_INTR_RESUME |
-	    MUSB_INTR_RESET | MUSB_INTR_SOF;
-
-	if (musb->int_usb || musb->int_tx || musb->int_rx)
-		retval = musb_interrupt(musb);
-
-	spin_unlock_irqrestore(&amp;musb->lock, flags);
-
-	return retval;
-}
-    </programlisting>
-    <para>
-      Instruction on line 18 above is a way for the controller driver to
-      work around the fact that some interrupt bits used for USB host
-      mode operation are missing in the MUSB_INTRUSB register, thus left
-      in an undefined hardware state, since this MUSB controller
-      hardware is used in peripheral mode only. As a consequence, the
-      glue layer masks these missing bits out to avoid parasite
-      interrupts by doing a logical AND operation between the value read
-      from MUSB_INTRUSB and the bits that are actually implemented in
-      the register.
-    </para>
-    <para>
-      These are only a couple of the quirks found in the JZ4740 USB
-      device controller. Some others were directly addressed in the MUSB
-      core since the fixes were generic enough to provide a better
-      handling of the issues for others controller hardware eventually.
-    </para>
-  </chapter>
-
-  <chapter id="conclusion">
-    <title>Conclusion</title>
-    <para>
-      Writing a Linux MUSB glue layer should be a more accessible task,
-      as this documentation tries to show the ins and outs of this
-      exercise.
-    </para>
-    <para>
-      The JZ4740 USB device controller being fairly simple, I hope its
-      glue layer serves as a good example for the curious mind. Used
-      with the current MUSB glue layers, this documentation should
-      provide enough guidance to get started; should anything gets out
-      of hand, the linux-usb mailing list archive is another helpful
-      resource to browse through.
-    </para>
-  </chapter>
-
-  <chapter id="acknowledgements">
-    <title>Acknowledgements</title>
-    <para>
-      Many thanks to Lars-Peter Clausen and Maarten ter Huurne for
-      answering my questions while I was writing the JZ4740 glue layer
-      and for helping me out getting the code in good shape.
-    </para>
-    <para>
-      I would also like to thank the Qi-Hardware community at large for
-      its cheerful guidance and support.
-    </para>
-  </chapter>
-
-  <chapter id="resources">
-    <title>Resources</title>
-    <para>
-      USB Home Page:
-      <ulink url="http://www.usb.org">http://www.usb.org</ulink>
-    </para>
-    <para>
-      linux-usb Mailing List Archives:
-      <ulink url="http://marc.info/?l=linux-usb">http://marc.info/?l=linux-usb</ulink>
-    </para>
-    <para>
-      USB On-the-Go Basics:
-      <ulink url="http://www.maximintegrated.com/app-notes/index.mvp/id/1822">http://www.maximintegrated.com/app-notes/index.mvp/id/1822</ulink>
-    </para>
-    <para>
-      Writing USB Device Drivers:
-      <ulink url="https://www.kernel.org/doc/htmldocs/writing_usb_driver/index.html">https://www.kernel.org/doc/htmldocs/writing_usb_driver/index.html</ulink>
-    </para>
-    <para>
-      Texas Instruments USB Configuration Wiki Page:
-      <ulink url="http://processors.wiki.ti.com/index.php/Usbgeneralpage">http://processors.wiki.ti.com/index.php/Usbgeneralpage</ulink>
-    </para>
-    <para>
-      Analog Devices Blackfin MUSB Configuration:
-      <ulink url="http://docs.blackfin.uclinux.org/doku.php?id=linux-kernel:drivers:musb">http://docs.blackfin.uclinux.org/doku.php?id=linux-kernel:drivers:musb</ulink>
-    </para>
-  </chapter>
-
-</book>
diff --git a/Documentation/DocBook/writing_usb_driver.tmpl b/Documentation/DocBook/writing_usb_driver.tmpl
deleted file mode 100644
index 3210dcf741c9..000000000000
--- a/Documentation/DocBook/writing_usb_driver.tmpl
+++ /dev/null
@@ -1,412 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="USBDeviceDriver">
- <bookinfo>
-  <title>Writing USB Device Drivers</title>
-  
-  <authorgroup>
-   <author>
-    <firstname>Greg</firstname>
-    <surname>Kroah-Hartman</surname>
-    <affiliation>
-     <address>
-      <email>greg@kroah.com</email>
-     </address>
-    </affiliation>
-   </author>
-  </authorgroup>
-
-  <copyright>
-   <year>2001-2002</year>
-   <holder>Greg Kroah-Hartman</holder>
-  </copyright>
-
-  <legalnotice>
-   <para>
-     This documentation is free software; you can redistribute
-     it and/or modify it under the terms of the GNU General Public
-     License as published by the Free Software Foundation; either
-     version 2 of the License, or (at your option) any later
-     version.
-   </para>
-      
-   <para>
-     This program is distributed in the hope that it will be
-     useful, but WITHOUT ANY WARRANTY; without even the implied
-     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-     See the GNU General Public License for more details.
-   </para>
-      
-   <para>
-     You should have received a copy of the GNU General Public
-     License along with this program; if not, write to the Free
-     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-     MA 02111-1307 USA
-   </para>
-      
-   <para>
-     For more details see the file COPYING in the source
-     distribution of Linux.
-   </para>
-
-   <para>
-     This documentation is based on an article published in 
-     Linux Journal Magazine, October 2001, Issue 90.
-   </para>
-  </legalnotice>
- </bookinfo>
-
-<toc></toc>
-
-  <chapter id="intro">
-      <title>Introduction</title>
-  <para>
-      The Linux USB subsystem has grown from supporting only two different
-      types of devices in the 2.2.7 kernel (mice and keyboards), to over 20
-      different types of devices in the 2.4 kernel. Linux currently supports
-      almost all USB class devices (standard types of devices like keyboards,
-      mice, modems, printers and speakers) and an ever-growing number of
-      vendor-specific devices (such as USB to serial converters, digital
-      cameras, Ethernet devices and MP3 players). For a full list of the
-      different USB devices currently supported, see Resources.
-  </para>
-  <para>
-      The remaining kinds of USB devices that do not have support on Linux are
-      almost all vendor-specific devices. Each vendor decides to implement a
-      custom protocol to talk to their device, so a custom driver usually needs
-      to be created. Some vendors are open with their USB protocols and help
-      with the creation of Linux drivers, while others do not publish them, and
-      developers are forced to reverse-engineer. See Resources for some links
-      to handy reverse-engineering tools.
-  </para>
-  <para>
-      Because each different protocol causes a new driver to be created, I have
-      written a generic USB driver skeleton, modelled after the pci-skeleton.c
-      file in the kernel source tree upon which many PCI network drivers have
-      been based. This USB skeleton can be found at drivers/usb/usb-skeleton.c
-      in the kernel source tree. In this article I will walk through the basics
-      of the skeleton driver, explaining the different pieces and what needs to
-      be done to customize it to your specific device.
-  </para>
-  </chapter>
-
-  <chapter id="basics">
-      <title>Linux USB Basics</title>
-  <para>
-      If you are going to write a Linux USB driver, please become familiar with
-      the USB protocol specification. It can be found, along with many other
-      useful documents, at the USB home page (see Resources). An excellent
-      introduction to the Linux USB subsystem can be found at the USB Working
-      Devices List (see Resources). It explains how the Linux USB subsystem is
-      structured and introduces the reader to the concept of USB urbs
-      (USB Request Blocks), which are essential to USB drivers.
-  </para>
-  <para>
-      The first thing a Linux USB driver needs to do is register itself with
-      the Linux USB subsystem, giving it some information about which devices
-      the driver supports and which functions to call when a device supported
-      by the driver is inserted or removed from the system. All of this
-      information is passed to the USB subsystem in the usb_driver structure.
-      The skeleton driver declares a usb_driver as:
-  </para>
-  <programlisting>
-static struct usb_driver skel_driver = {
-        .name        = "skeleton",
-        .probe       = skel_probe,
-        .disconnect  = skel_disconnect,
-        .fops        = &amp;skel_fops,
-        .minor       = USB_SKEL_MINOR_BASE,
-        .id_table    = skel_table,
-};
-  </programlisting>
-  <para>
-      The variable name is a string that describes the driver. It is used in
-      informational messages printed to the system log. The probe and
-      disconnect function pointers are called when a device that matches the
-      information provided in the id_table variable is either seen or removed.
-  </para>
-  <para>
-      The fops and minor variables are optional. Most USB drivers hook into
-      another kernel subsystem, such as the SCSI, network or TTY subsystem.
-      These types of drivers register themselves with the other kernel
-      subsystem, and any user-space interactions are provided through that
-      interface. But for drivers that do not have a matching kernel subsystem,
-      such as MP3 players or scanners, a method of interacting with user space
-      is needed. The USB subsystem provides a way to register a minor device
-      number and a set of file_operations function pointers that enable this
-      user-space interaction. The skeleton driver needs this kind of interface,
-      so it provides a minor starting number and a pointer to its
-      file_operations functions.
-  </para>
-  <para>
-      The USB driver is then registered with a call to usb_register, usually in
-      the driver's init function, as shown here:
-  </para>
-  <programlisting>
-static int __init usb_skel_init(void)
-{
-        int result;
-
-        /* register this driver with the USB subsystem */
-        result = usb_register(&amp;skel_driver);
-        if (result &lt; 0) {
-                err(&quot;usb_register failed for the &quot;__FILE__ &quot;driver.&quot;
-                    &quot;Error number %d&quot;, result);
-                return -1;
-        }
-
-        return 0;
-}
-module_init(usb_skel_init);
-  </programlisting>
-  <para>
-      When the driver is unloaded from the system, it needs to deregister
-      itself with the USB subsystem. This is done with the usb_deregister
-      function:
-  </para>
-  <programlisting>
-static void __exit usb_skel_exit(void)
-{
-        /* deregister this driver with the USB subsystem */
-        usb_deregister(&amp;skel_driver);
-}
-module_exit(usb_skel_exit);
-  </programlisting>
-  <para>
-     To enable the linux-hotplug system to load the driver automatically when
-     the device is plugged in, you need to create a MODULE_DEVICE_TABLE. The
-     following code tells the hotplug scripts that this module supports a
-     single device with a specific vendor and product ID:
-  </para>
-  <programlisting>
-/* table of devices that work with this driver */
-static struct usb_device_id skel_table [] = {
-        { USB_DEVICE(USB_SKEL_VENDOR_ID, USB_SKEL_PRODUCT_ID) },
-        { }                      /* Terminating entry */
-};
-MODULE_DEVICE_TABLE (usb, skel_table);
-  </programlisting>
-  <para>
-     There are other macros that can be used in describing a usb_device_id for
-     drivers that support a whole class of USB drivers. See usb.h for more
-     information on this.
-  </para>
-  </chapter>
-
-  <chapter id="device">
-      <title>Device operation</title>
-  <para>
-     When a device is plugged into the USB bus that matches the device ID
-     pattern that your driver registered with the USB core, the probe function
-     is called. The usb_device structure, interface number and the interface ID
-     are passed to the function:
-  </para>
-  <programlisting>
-static int skel_probe(struct usb_interface *interface,
-    const struct usb_device_id *id)
-  </programlisting>
-  <para>
-     The driver now needs to verify that this device is actually one that it
-     can accept. If so, it returns 0.
-     If not, or if any error occurs during initialization, an errorcode
-     (such as <literal>-ENOMEM</literal> or <literal>-ENODEV</literal>)
-     is returned from the probe function.
-  </para>
-  <para>
-     In the skeleton driver, we determine what end points are marked as bulk-in
-     and bulk-out. We create buffers to hold the data that will be sent and
-     received from the device, and a USB urb to write data to the device is
-     initialized.
-  </para>
-  <para>
-     Conversely, when the device is removed from the USB bus, the disconnect
-     function is called with the device pointer. The driver needs to clean any
-     private data that has been allocated at this time and to shut down any
-     pending urbs that are in the USB system.
-  </para>
-  <para>
-     Now that the device is plugged into the system and the driver is bound to
-     the device, any of the functions in the file_operations structure that
-     were passed to the USB subsystem will be called from a user program trying
-     to talk to the device. The first function called will be open, as the
-     program tries to open the device for I/O. We increment our private usage
-     count and save a pointer to our internal structure in the file
-     structure. This is done so that future calls to file operations will
-     enable the driver to determine which device the user is addressing.  All
-     of this is done with the following code:
-  </para>
-  <programlisting>
-/* increment our usage count for the module */
-++skel->open_count;
-
-/* save our object in the file's private structure */
-file->private_data = dev;
-  </programlisting>
-  <para>
-     After the open function is called, the read and write functions are called
-     to receive and send data to the device. In the skel_write function, we
-     receive a pointer to some data that the user wants to send to the device
-     and the size of the data. The function determines how much data it can
-     send to the device based on the size of the write urb it has created (this
-     size depends on the size of the bulk out end point that the device has).
-     Then it copies the data from user space to kernel space, points the urb to
-     the data and submits the urb to the USB subsystem.  This can be seen in
-     the following code:
-  </para>
-  <programlisting>
-/* we can only write as much as 1 urb will hold */
-bytes_written = (count > skel->bulk_out_size) ? skel->bulk_out_size : count;
-
-/* copy the data from user space into our urb */
-copy_from_user(skel->write_urb->transfer_buffer, buffer, bytes_written);
-
-/* set up our urb */
-usb_fill_bulk_urb(skel->write_urb,
-                  skel->dev,
-                  usb_sndbulkpipe(skel->dev, skel->bulk_out_endpointAddr),
-                  skel->write_urb->transfer_buffer,
-                  bytes_written,
-                  skel_write_bulk_callback,
-                  skel);
-
-/* send the data out the bulk port */
-result = usb_submit_urb(skel->write_urb);
-if (result) {
-        err(&quot;Failed submitting write urb, error %d&quot;, result);
-}
-  </programlisting>
-  <para>
-     When the write urb is filled up with the proper information using the
-     usb_fill_bulk_urb function, we point the urb's completion callback to call our
-     own skel_write_bulk_callback function. This function is called when the
-     urb is finished by the USB subsystem. The callback function is called in
-     interrupt context, so caution must be taken not to do very much processing
-     at that time. Our implementation of skel_write_bulk_callback merely
-     reports if the urb was completed successfully or not and then returns.
-  </para>
-  <para>
-     The read function works a bit differently from the write function in that
-     we do not use an urb to transfer data from the device to the driver.
-     Instead we call the usb_bulk_msg function, which can be used to send or
-     receive data from a device without having to create urbs and handle
-     urb completion callback functions. We call the usb_bulk_msg function,
-     giving it a buffer into which to place any data received from the device
-     and a timeout value. If the timeout period expires without receiving any
-     data from the device, the function will fail and return an error message.
-     This can be shown with the following code:
-  </para>
-  <programlisting>
-/* do an immediate bulk read to get data from the device */
-retval = usb_bulk_msg (skel->dev,
-                       usb_rcvbulkpipe (skel->dev,
-                       skel->bulk_in_endpointAddr),
-                       skel->bulk_in_buffer,
-                       skel->bulk_in_size,
-                       &amp;count, HZ*10);
-/* if the read was successful, copy the data to user space */
-if (!retval) {
-        if (copy_to_user (buffer, skel->bulk_in_buffer, count))
-                retval = -EFAULT;
-        else
-                retval = count;
-}
-  </programlisting>
-  <para>
-     The usb_bulk_msg function can be very useful for doing single reads or
-     writes to a device; however, if you need to read or write constantly to a
-     device, it is recommended to set up your own urbs and submit them to the
-     USB subsystem.
-  </para>
-  <para>
-     When the user program releases the file handle that it has been using to
-     talk to the device, the release function in the driver is called. In this
-     function we decrement our private usage count and wait for possible
-     pending writes:
-  </para>
-  <programlisting>
-/* decrement our usage count for the device */
---skel->open_count;
-  </programlisting>
-  <para>
-     One of the more difficult problems that USB drivers must be able to handle
-     smoothly is the fact that the USB device may be removed from the system at
-     any point in time, even if a program is currently talking to it. It needs
-     to be able to shut down any current reads and writes and notify the
-     user-space programs that the device is no longer there. The following
-     code (function <function>skel_delete</function>)
-     is an example of how to do this: </para>
-  <programlisting>
-static inline void skel_delete (struct usb_skel *dev)
-{
-    kfree (dev->bulk_in_buffer);
-    if (dev->bulk_out_buffer != NULL)
-        usb_free_coherent (dev->udev, dev->bulk_out_size,
-            dev->bulk_out_buffer,
-            dev->write_urb->transfer_dma);
-    usb_free_urb (dev->write_urb);
-    kfree (dev);
-}
-  </programlisting>
-  <para>
-     If a program currently has an open handle to the device, we reset the flag
-     <literal>device_present</literal>. For
-     every read, write, release and other functions that expect a device to be
-     present, the driver first checks this flag to see if the device is
-     still present. If not, it releases that the device has disappeared, and a
-     -ENODEV error is returned to the user-space program. When the release
-     function is eventually called, it determines if there is no device
-     and if not, it does the cleanup that the skel_disconnect
-     function normally does if there are no open files on the device (see
-     Listing 5).
-  </para>
-  </chapter>
-
-  <chapter id="iso">
-      <title>Isochronous Data</title>
-  <para>
-     This usb-skeleton driver does not have any examples of interrupt or
-     isochronous data being sent to or from the device. Interrupt data is sent
-     almost exactly as bulk data is, with a few minor exceptions.  Isochronous
-     data works differently with continuous streams of data being sent to or
-     from the device. The audio and video camera drivers are very good examples
-     of drivers that handle isochronous data and will be useful if you also
-     need to do this.
-  </para>
-  </chapter>
-  
-  <chapter id="Conclusion">
-      <title>Conclusion</title>
-  <para>
-     Writing Linux USB device drivers is not a difficult task as the
-     usb-skeleton driver shows. This driver, combined with the other current
-     USB drivers, should provide enough examples to help a beginning author
-     create a working driver in a minimal amount of time. The linux-usb-devel
-     mailing list archives also contain a lot of helpful information.
-  </para>
-  </chapter>
-
-  <chapter id="resources">
-      <title>Resources</title>
-  <para>
-     The Linux USB Project: <ulink url="http://www.linux-usb.org">http://www.linux-usb.org/</ulink>
-  </para>
-  <para>
-     Linux Hotplug Project: <ulink url="http://linux-hotplug.sourceforge.net">http://linux-hotplug.sourceforge.net/</ulink>
-  </para>
-  <para>
-     Linux USB Working Devices List: <ulink url="http://www.qbik.ch/usb/devices">http://www.qbik.ch/usb/devices/</ulink>
-  </para>
-  <para>
-     linux-usb-devel Mailing List Archives: <ulink url="http://marc.theaimsgroup.com/?l=linux-usb-devel">http://marc.theaimsgroup.com/?l=linux-usb-devel</ulink>
-  </para>
-  <para>
-     Programming Guide for Linux USB Device Drivers: <ulink url="http://usb.cs.tum.edu/usbdoc">http://usb.cs.tum.edu/usbdoc</ulink>
-  </para>
-  <para>
-     USB Home Page: <ulink url="http://www.usb.org">http://www.usb.org</ulink>
-  </para>
-  </chapter>
-
-</book>
diff --git a/Documentation/PCI/pci-error-recovery.txt b/Documentation/PCI/pci-error-recovery.txt
index da3b2176d5da..0b6bb3ef449e 100644
--- a/Documentation/PCI/pci-error-recovery.txt
+++ b/Documentation/PCI/pci-error-recovery.txt
@@ -11,7 +11,7 @@
 
 Many PCI bus controllers are able to detect a variety of hardware
 PCI errors on the bus, such as parity errors on the data and address
-busses, as well as SERR and PERR errors.  Some of the more advanced
+buses, as well as SERR and PERR errors.  Some of the more advanced
 chipsets are able to deal with these errors; these include PCI-E chipsets,
 and the PCI-host bridges found on IBM Power4, Power5 and Power6-based
 pSeries boxes. A typical action taken is to disconnect the affected device,
@@ -173,7 +173,7 @@ is STEP 6 (Permanent Failure).
 >>> a value of 0xff on read, and writes will be dropped. If more than
 >>> EEH_MAX_FAILS I/O's are attempted to a frozen adapter, EEH
 >>> assumes that the device driver has gone into an infinite loop
->>> and prints an error to syslog.  A reboot is then required to 
+>>> and prints an error to syslog.  A reboot is then required to
 >>> get the device working again.
 
 STEP 2: MMIO Enabled
@@ -231,14 +231,14 @@ proceeds to STEP 4 (Slot Reset)
 STEP 3: Link Reset
 ------------------
 The platform resets the link.  This is a PCI-Express specific step
-and is done whenever a non-fatal error has been detected that can be
+and is done whenever a fatal error has been detected that can be
 "solved" by resetting the link.
 
 STEP 4: Slot Reset
 ------------------
 
 In response to a return value of PCI_ERS_RESULT_NEED_RESET, the
-the platform will perform a slot reset on the requesting PCI device(s). 
+the platform will perform a slot reset on the requesting PCI device(s).
 The actual steps taken by a platform to perform a slot reset
 will be platform-dependent. Upon completion of slot reset, the
 platform will call the device slot_reset() callback.
@@ -258,7 +258,7 @@ configuration registers to initialize to their default conditions.
 
 For most PCI devices, a soft reset will be sufficient for recovery.
 Optional fundamental reset is provided to support a limited number
-of PCI Express PCI devices  for which a soft reset is not sufficient
+of PCI Express devices for which a soft reset is not sufficient
 for recovery.
 
 If the platform supports PCI hotplug, then the reset might be
@@ -303,7 +303,7 @@ driver performs device init only from PCI function 0:
 		Same as above.
 
 Drivers for PCI Express cards that require a fundamental reset must
-set the needs_freset bit in the pci_dev structure in their probe function.  
+set the needs_freset bit in the pci_dev structure in their probe function.
 For example, the QLogic qla2xxx driver sets the needs_freset bit for certain
 PCI card types:
 
diff --git a/Documentation/acpi/aml-debugger.txt b/Documentation/acpi/aml-debugger.txt
index 5f62aa4a493b..e851cc5de63f 100644
--- a/Documentation/acpi/aml-debugger.txt
+++ b/Documentation/acpi/aml-debugger.txt
@@ -15,7 +15,7 @@ kernel.
    CONFIG_ACPI_DEBUGGER=y
    CONFIG_ACPI_DEBUGGER_USER=m
 
-   The userspace utlities can be built from the kernel source tree using
+   The userspace utilities can be built from the kernel source tree using
    the following commands:
 
    $ cd tools
diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/acpi/dsd/graph.txt
new file mode 100644
index 000000000000..ac09e3138b79
--- /dev/null
+++ b/Documentation/acpi/dsd/graph.txt
@@ -0,0 +1,162 @@
+Graphs
+
+
+_DSD
+----
+
+_DSD (Device Specific Data) [7] is a predefined ACPI device
+configuration object that can be used to convey information on
+hardware features which are not specifically covered by the ACPI
+specification [1][6]. There are two _DSD extensions that are relevant
+for graphs: property [4] and hierarchical data extensions [5]. The
+property extension provides generic key-value pairs whereas the
+hierarchical data extension supports nodes with references to other
+nodes, forming a tree. The nodes in the tree may contain properties as
+defined by the property extension. The two extensions together provide
+a tree-like structure with zero or more properties (key-value pairs)
+in each node of the tree.
+
+The data structure may be accessed at runtime by using the device_*
+and fwnode_* functions defined in include/linux/fwnode.h .
+
+Fwnode represents a generic firmware node object. It is independent on
+the firmware type. In ACPI, fwnodes are _DSD hierarchical data
+extensions objects. A device's _DSD object is represented by an
+fwnode.
+
+The data structure may be referenced to elsewhere in the ACPI tables
+by using a hard reference to the device itself and an index to the
+hierarchical data extension array on each depth.
+
+
+Ports and endpoints
+-------------------
+
+The port and endpoint concepts are very similar to those in Devicetree
+[3]. A port represents an interface in a device, and an endpoint
+represents a connection to that interface.
+
+All port nodes are located under the device's "_DSD" node in the
+hierarchical data extension tree. The property extension related to
+each port node must contain the key "port" and an integer value which
+is the number of the port. The object it refers to should be called "PRTX",
+where "X" is the number of the port.
+
+Further on, endpoints are located under the individual port nodes. The
+first hierarchical data extension package list entry of the endpoint
+nodes must begin with "endpoint" and must be followed by the number
+of the endpoint. The object it refers to should be called "EPXY", where
+"X" is the number of the port and "Y" is the number of the endpoint.
+
+Each port node contains a property extension key "port", the value of
+which is the number of the port node. The each endpoint is similarly numbered
+with a property extension key "endpoint". Port numbers must be unique within a
+device and endpoint numbers must be unique within a port.
+
+The endpoint reference uses property extension with "remote-endpoint" property
+name followed by a reference in the same package. Such references consist of the
+the remote device reference, number of the port in the device and finally the
+number of the endpoint in that port. Individual references thus appear as:
+
+    Package() { device, port_number, endpoint_number }
+
+The references to endpoints must be always done both ways, to the
+remote endpoint and back from the referred remote endpoint node.
+
+A simple example of this is show below:
+
+    Scope (\_SB.PCI0.I2C2)
+    {
+	Device (CAM0)
+	{
+	    Name (_DSD, Package () {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "compatible", Package () { "nokia,smia" } },
+		},
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "port0", "PRT0" },
+		}
+	    })
+	    Name (PRT0, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "port", 0 },
+		},
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "endpoint0", "EP00" },
+		}
+	    })
+	    Name (EP00, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "endpoint", 0 },
+		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, 4, 0 } },
+		}
+	    })
+	}
+    }
+
+    Scope (\_SB.PCI0)
+    {
+	Device (ISP)
+	{
+	    Name (_DSD, Package () {
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "port4", "PRT4" },
+		}
+	    })
+
+	    Name (PRT4, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "port", 4 }, /* CSI-2 port number */
+		},
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "endpoint0", "EP40" },
+		}
+	    })
+
+	    Name (EP40, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "endpoint", 0 },
+		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, 0, 0 } },
+		}
+	    })
+	}
+    }
+
+Here, the port 0 of the "CAM0" device is connected to the port 4 of
+the "ISP" device and vice versa.
+
+
+References
+----------
+
+[1] _DSD (Device Specific Data) Implementation Guide.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel-1_1.htm>,
+    referenced 2016-10-03.
+
+[2] Devicetree. <URL:http://www.devicetree.org>, referenced 2016-10-03.
+
+[3] Documentation/devicetree/bindings/graph.txt
+
+[4] Device Properties UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+    referenced 2016-10-04.
+
+[5] Hierarchical Data Extension UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.pdf>,
+    referenced 2016-10-04.
+
+[6] Advanced Configuration and Power Interface Specification.
+    <URL:http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf>,
+    referenced 2016-10-04.
+
+[7] _DSD Device Properties Usage Rules.
+    Documentation/acpi/DSD-properties-rules.txt
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index 209a5eba6b87..7bcf9c3d9fbe 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -367,10 +367,10 @@ resulting child platform device.
 
 Device Tree namespace link device ID
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-The Device Tree protocol uses device indentification based on the "compatible"
+The Device Tree protocol uses device identification based on the "compatible"
 property whose value is a string or an array of strings recognized as device
 identifiers by drivers and the driver core.  The set of all those strings may be
-regarded as a device indentification namespace analogous to the ACPI/PNP device
+regarded as a device identification namespace analogous to the ACPI/PNP device
 ID namespace.  Consequently, in principle it should not be necessary to allocate
 a new (and arguably redundant) ACPI/PNP device ID for a devices with an existing
 identification string in the Device Tree (DT) namespace, especially if that ID
@@ -381,7 +381,7 @@ In ACPI, the device identification object called _CID (Compatible ID) is used to
 list the IDs of devices the given one is compatible with, but those IDs must
 belong to one of the namespaces prescribed by the ACPI specification (see
 Section 6.1.2 of ACPI 6.0 for details) and the DT namespace is not one of them.
-Moreover, the specification mandates that either a _HID or an _ADR identificaion
+Moreover, the specification mandates that either a _HID or an _ADR identification
 object be present for all ACPI objects representing devices (Section 6.1 of ACPI
 6.0).  For non-enumerable bus types that object must be _HID and its value must
 be a device ID from one of the namespaces prescribed by the specification too.
diff --git a/Documentation/acpi/linuxized-acpica.txt b/Documentation/acpi/linuxized-acpica.txt
index defe2eec5331..3ad7b0dfb083 100644
--- a/Documentation/acpi/linuxized-acpica.txt
+++ b/Documentation/acpi/linuxized-acpica.txt
@@ -24,7 +24,7 @@ upstream.
    The homepage of ACPICA project is: www.acpica.org, it is maintained and
    supported by Intel Corporation.
 
-   The following figure depicts the Linux ACPI subystem where the ACPICA
+   The following figure depicts the Linux ACPI subsystem where the ACPICA
    adaptation is included:
 
       +---------------------------------------------------------+
@@ -110,7 +110,7 @@ upstream.
    Linux patches.  The patches generated by this process are referred to as
    "linuxized ACPICA patches".  The release process is carried out on a local
    copy the ACPICA git repository.  Each commit in the monthly release is
-   converted into a linuxized ACPICA patch.  Together, they form the montly
+   converted into a linuxized ACPICA patch.  Together, they form the monthly
    ACPICA release patchset for the Linux ACPI community.  This process is
    illustrated in the following figure:
 
@@ -165,7 +165,7 @@ upstream.
        <http://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git>.
 
    Before the linuxized ACPICA patches are sent to the Linux ACPI community
-   for review, there is a quality ensurance build test process to reduce
+   for review, there is a quality assurance build test process to reduce
    porting issues.  Currently this build process only takes care of the
    following kernel configuration options:
    CONFIG_ACPI/CONFIG_ACPI_DEBUG/CONFIG_ACPI_DEBUGGER
@@ -195,12 +195,12 @@ upstream.
       release utilities (please refer to Section 4 below for the details).
    3. Linux specific features - Sometimes it's impossible to use the
       current ACPICA APIs to implement features required by the Linux kernel,
-      so Linux developers occasionaly have to change ACPICA code directly.
+      so Linux developers occasionally have to change ACPICA code directly.
       Those changes may not be acceptable by ACPICA upstream and in such cases
       they are left as committed ACPICA divergences unless the ACPICA side can
       implement new mechanisms as replacements for them.
    4. ACPICA release fixups - ACPICA only tests commits using a set of the
-      user space simulation utilies, thus the linuxized ACPICA patches may
+      user space simulation utilities, thus the linuxized ACPICA patches may
       break the Linux kernel, leaving us build/boot failures.  In order to
       avoid breaking Linux bisection, fixes are applied directly to the
       linuxized ACPICA patches during the release process.  When the release
diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index 697a00ccec25..02f639aab06e 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -27,7 +27,7 @@ On what hardware does it run?
   today Linux also runs on (at least) the Compaq Alpha AXP, Sun SPARC and
   UltraSPARC, Motorola 68000, PowerPC, PowerPC64, ARM, Hitachi SuperH, Cell,
   IBM S/390, MIPS, HP PA-RISC, Intel IA-64, DEC VAX, AMD x86-64, AXIS CRIS,
-  Xtensa, Tilera TILE, AVR32, ARC and Renesas M32R architectures.
+  Xtensa, Tilera TILE, ARC and Renesas M32R architectures.
 
   Linux is easily portable to most general-purpose 32- or 64-bit architectures
   as long as they have a paged memory management unit (PMMU) and a port of the
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 8ddae4e4299a..8c60a8a32a1a 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -60,6 +60,7 @@ configure specific aspects of kernel behavior to your liking.
    mono
    java
    ras
+   pm/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index b516164999a8..d76ab3907e2b 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -1,3 +1,5 @@
+.. _kernelparameters:
+
 The kernel's command-line parameters
 ====================================
 
@@ -86,7 +88,6 @@ parameter is applicable::
 	APIC	APIC support is enabled.
 	APM	Advanced Power Management support is enabled.
 	ARM	ARM architecture is enabled.
-	AVR32	AVR32 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	BLACKFIN Blackfin architecture is enabled.
 	CLK	Common clock infrastructure is enabled.
@@ -197,7 +198,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
 Finally, the [KMG] suffix is commonly described after a number of kernel
 parameter values. These 'K', 'M', and 'G' letters represent the _binary_
-multipliers 'Kilo', 'Mega', and 'Giga', equalling 2^10, 2^20, and 2^30
+multipliers 'Kilo', 'Mega', and 'Giga', equaling 2^10, 2^20, and 2^30
 bytes respectively. Such letter suffixes can also be entirely omitted:
 
 .. include:: kernel-parameters.txt
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 986e44387dad..e4c9e0e46b95 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -531,7 +531,6 @@
 			[ACPI] acpi_pm
 			[ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
 				pxa_timer,timer3,32k_counter,timer0_1
-			[AVR32] avr32
 			[X86-32] pit,hpet,tsc;
 				scx200_hrt on Geode; cyclone on IBM x440
 			[MIPS] MIPS
@@ -653,6 +652,9 @@
 	cpuidle.off=1	[CPU_IDLE]
 			disable the cpuidle sub-system
 
+	cpufreq.off=1	[CPU_FREQ]
+			disable the cpufreq sub-system
+
 	cpu_init_udelay=N
 			[X86] Delay for N microsec between assert and de-assert
 			of APIC INIT to start processors.  This delay occurs
@@ -986,6 +988,7 @@
 			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
 			earlyprintk=pciserial,bus:device.function[,baudrate]
+			earlyprintk=xdbc[xhciController#]
 
 			earlyprintk is useful when the kernel crashes before
 			the normal console is initialized. It is not enabled by
@@ -1183,6 +1186,12 @@
 			functions that can be changed at run time by the
 			set_graph_notrace file in the debugfs tracing directory.
 
+	ftrace_graph_max_depth=<uint>
+			[FTRACE] Used with the function graph tracer. This is
+			the max depth it will trace into a function. This value
+			can be changed at run time by the max_graph_depth file
+			in the tracefs tracing directory. default: 0 (no limit)
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)
@@ -1716,6 +1725,12 @@
 			kernel and module base offset ASLR (Address Space
 			Layout Randomization).
 
+	kasan_multi_shot
+			[KNL] Enforce KASAN (Kernel Address Sanitizer) to print
+			report on every invalid memory access. Without this
+			parameter KASAN will print report only for the first
+			invalid access.
+
 	keepinitrd	[HW,ARM]
 
 	kernelcore=	[KNL,X86,IA-64,PPC]
@@ -2410,7 +2425,7 @@
 			osd-targets. Please see:
 			Documentation/filesystems/pnfs.txt for more explanations
 
-	nmi_debug=	[KNL,AVR32,SH] Specify one or more actions to take
+	nmi_debug=	[KNL,SH] Specify one or more actions to take
 			when a NMI is triggered.
 			Format: [state][,regs][,debounce][,die]
 
@@ -3163,6 +3178,12 @@
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
+	ras=option[,option,...]	[KNL] RAS-specific options
+
+		cec_disable	[X86]
+				Disable the Correctable Errors Collector,
+				see CONFIG_RAS_CEC help text.
+
 	rcu_nocbs=	[KNL]
 			The argument is a cpu list, as described above.
 
@@ -4106,6 +4127,9 @@
 	usbhid.mousepoll=
 			[USBHID] The interval which mice are to be polled at.
 
+	usbhid.jspoll=
+			[USBHID] The interval which joysticks are to be polled at.
+
 	usb-storage.delay_use=
 			[UMS] The delay in seconds before a new device is
 			scanned for Logical Units (default 1).
diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst
new file mode 100644
index 000000000000..289c80f7760e
--- /dev/null
+++ b/Documentation/admin-guide/pm/cpufreq.rst
@@ -0,0 +1,700 @@
+.. |struct cpufreq_policy| replace:: :c:type:`struct cpufreq_policy <cpufreq_policy>`
+
+=======================
+CPU Performance Scaling
+=======================
+
+::
+
+ Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+The Concept of CPU Performance Scaling
+======================================
+
+The majority of modern processors are capable of operating in a number of
+different clock frequency and voltage configurations, often referred to as
+Operating Performance Points or P-states (in ACPI terminology).  As a rule,
+the higher the clock frequency and the higher the voltage, the more instructions
+can be retired by the CPU over a unit of time, but also the higher the clock
+frequency and the higher the voltage, the more energy is consumed over a unit of
+time (or the more power is drawn) by the CPU in the given P-state.  Therefore
+there is a natural tradeoff between the CPU capacity (the number of instructions
+that can be executed over a unit of time) and the power drawn by the CPU.
+
+In some situations it is desirable or even necessary to run the program as fast
+as possible and then there is no reason to use any P-states different from the
+highest one (i.e. the highest-performance frequency/voltage configuration
+available).  In some other cases, however, it may not be necessary to execute
+instructions so quickly and maintaining the highest available CPU capacity for a
+relatively long time without utilizing it entirely may be regarded as wasteful.
+It also may not be physically possible to maintain maximum CPU capacity for too
+long for thermal or power supply capacity reasons or similar.  To cover those
+cases, there are hardware interfaces allowing CPUs to be switched between
+different frequency/voltage configurations or (in the ACPI terminology) to be
+put into different P-states.
+
+Typically, they are used along with algorithms to estimate the required CPU
+capacity, so as to decide which P-states to put the CPUs into.  Of course, since
+the utilization of the system generally changes over time, that has to be done
+repeatedly on a regular basis.  The activity by which this happens is referred
+to as CPU performance scaling or CPU frequency scaling (because it involves
+adjusting the CPU clock frequency).
+
+
+CPU Performance Scaling in Linux
+================================
+
+The Linux kernel supports CPU performance scaling by means of the ``CPUFreq``
+(CPU Frequency scaling) subsystem that consists of three layers of code: the
+core, scaling governors and scaling drivers.
+
+The ``CPUFreq`` core provides the common code infrastructure and user space
+interfaces for all platforms that support CPU performance scaling.  It defines
+the basic framework in which the other components operate.
+
+Scaling governors implement algorithms to estimate the required CPU capacity.
+As a rule, each governor implements one, possibly parametrized, scaling
+algorithm.
+
+Scaling drivers talk to the hardware.  They provide scaling governors with
+information on the available P-states (or P-state ranges in some cases) and
+access platform-specific hardware interfaces to change CPU P-states as requested
+by scaling governors.
+
+In principle, all available scaling governors can be used with every scaling
+driver.  That design is based on the observation that the information used by
+performance scaling algorithms for P-state selection can be represented in a
+platform-independent form in the majority of cases, so it should be possible
+to use the same performance scaling algorithm implemented in exactly the same
+way regardless of which scaling driver is used.  Consequently, the same set of
+scaling governors should be suitable for every supported platform.
+
+However, that observation may not hold for performance scaling algorithms
+based on information provided by the hardware itself, for example through
+feedback registers, as that information is typically specific to the hardware
+interface it comes from and may not be easily represented in an abstract,
+platform-independent way.  For this reason, ``CPUFreq`` allows scaling drivers
+to bypass the governor layer and implement their own performance scaling
+algorithms.  That is done by the ``intel_pstate`` scaling driver.
+
+
+``CPUFreq`` Policy Objects
+==========================
+
+In some cases the hardware interface for P-state control is shared by multiple
+CPUs.  That is, for example, the same register (or set of registers) is used to
+control the P-state of multiple CPUs at the same time and writing to it affects
+all of those CPUs simultaneously.
+
+Sets of CPUs sharing hardware P-state control interfaces are represented by
+``CPUFreq`` as |struct cpufreq_policy| objects.  For consistency,
+|struct cpufreq_policy| is also used when there is only one CPU in the given
+set.
+
+The ``CPUFreq`` core maintains a pointer to a |struct cpufreq_policy| object for
+every CPU in the system, including CPUs that are currently offline.  If multiple
+CPUs share the same hardware P-state control interface, all of the pointers
+corresponding to them point to the same |struct cpufreq_policy| object.
+
+``CPUFreq`` uses |struct cpufreq_policy| as its basic data type and the design
+of its user space interface is based on the policy concept.
+
+
+CPU Initialization
+==================
+
+First of all, a scaling driver has to be registered for ``CPUFreq`` to work.
+It is only possible to register one scaling driver at a time, so the scaling
+driver is expected to be able to handle all CPUs in the system.
+
+The scaling driver may be registered before or after CPU registration.  If
+CPUs are registered earlier, the driver core invokes the ``CPUFreq`` core to
+take a note of all of the already registered CPUs during the registration of the
+scaling driver.  In turn, if any CPUs are registered after the registration of
+the scaling driver, the ``CPUFreq`` core will be invoked to take note of them
+at their registration time.
+
+In any case, the ``CPUFreq`` core is invoked to take note of any logical CPU it
+has not seen so far as soon as it is ready to handle that CPU.  [Note that the
+logical CPU may be a physical single-core processor, or a single core in a
+multicore processor, or a hardware thread in a physical processor or processor
+core.  In what follows "CPU" always means "logical CPU" unless explicitly stated
+otherwise and the word "processor" is used to refer to the physical part
+possibly including multiple logical CPUs.]
+
+Once invoked, the ``CPUFreq`` core checks if the policy pointer is already set
+for the given CPU and if so, it skips the policy object creation.  Otherwise,
+a new policy object is created and initialized, which involves the creation of
+a new policy directory in ``sysfs``, and the policy pointer corresponding to
+the given CPU is set to the new policy object's address in memory.
+
+Next, the scaling driver's ``->init()`` callback is invoked with the policy
+pointer of the new CPU passed to it as the argument.  That callback is expected
+to initialize the performance scaling hardware interface for the given CPU (or,
+more precisely, for the set of CPUs sharing the hardware interface it belongs
+to, represented by its policy object) and, if the policy object it has been
+called for is new, to set parameters of the policy, like the minimum and maximum
+frequencies supported by the hardware, the table of available frequencies (if
+the set of supported P-states is not a continuous range), and the mask of CPUs
+that belong to the same policy (including both online and offline CPUs).  That
+mask is then used by the core to populate the policy pointers for all of the
+CPUs in it.
+
+The next major initialization step for a new policy object is to attach a
+scaling governor to it (to begin with, that is the default scaling governor
+determined by the kernel configuration, but it may be changed later
+via ``sysfs``).  First, a pointer to the new policy object is passed to the
+governor's ``->init()`` callback which is expected to initialize all of the
+data structures necessary to handle the given policy and, possibly, to add
+a governor ``sysfs`` interface to it.  Next, the governor is started by
+invoking its ``->start()`` callback.
+
+That callback it expected to register per-CPU utilization update callbacks for
+all of the online CPUs belonging to the given policy with the CPU scheduler.
+The utilization update callbacks will be invoked by the CPU scheduler on
+important events, like task enqueue and dequeue, on every iteration of the
+scheduler tick or generally whenever the CPU utilization may change (from the
+scheduler's perspective).  They are expected to carry out computations needed
+to determine the P-state to use for the given policy going forward and to
+invoke the scaling driver to make changes to the hardware in accordance with
+the P-state selection.  The scaling driver may be invoked directly from
+scheduler context or asynchronously, via a kernel thread or workqueue, depending
+on the configuration and capabilities of the scaling driver and the governor.
+
+Similar steps are taken for policy objects that are not new, but were "inactive"
+previously, meaning that all of the CPUs belonging to them were offline.  The
+only practical difference in that case is that the ``CPUFreq`` core will attempt
+to use the scaling governor previously used with the policy that became
+"inactive" (and is re-initialized now) instead of the default governor.
+
+In turn, if a previously offline CPU is being brought back online, but some
+other CPUs sharing the policy object with it are online already, there is no
+need to re-initialize the policy object at all.  In that case, it only is
+necessary to restart the scaling governor so that it can take the new online CPU
+into account.  That is achieved by invoking the governor's ``->stop`` and
+``->start()`` callbacks, in this order, for the entire policy.
+
+As mentioned before, the ``intel_pstate`` scaling driver bypasses the scaling
+governor layer of ``CPUFreq`` and provides its own P-state selection algorithms.
+Consequently, if ``intel_pstate`` is used, scaling governors are not attached to
+new policy objects.  Instead, the driver's ``->setpolicy()`` callback is invoked
+to register per-CPU utilization update callbacks for each policy.  These
+callbacks are invoked by the CPU scheduler in the same way as for scaling
+governors, but in the ``intel_pstate`` case they both determine the P-state to
+use and change the hardware configuration accordingly in one go from scheduler
+context.
+
+The policy objects created during CPU initialization and other data structures
+associated with them are torn down when the scaling driver is unregistered
+(which happens when the kernel module containing it is unloaded, for example) or
+when the last CPU belonging to the given policy in unregistered.
+
+
+Policy Interface in ``sysfs``
+=============================
+
+During the initialization of the kernel, the ``CPUFreq`` core creates a
+``sysfs`` directory (kobject) called ``cpufreq`` under
+:file:`/sys/devices/system/cpu/`.
+
+That directory contains a ``policyX`` subdirectory (where ``X`` represents an
+integer number) for every policy object maintained by the ``CPUFreq`` core.
+Each ``policyX`` directory is pointed to by ``cpufreq`` symbolic links
+under :file:`/sys/devices/system/cpu/cpuY/` (where ``Y`` represents an integer
+that may be different from the one represented by ``X``) for all of the CPUs
+associated with (or belonging to) the given policy.  The ``policyX`` directories
+in :file:`/sys/devices/system/cpu/cpufreq` each contain policy-specific
+attributes (files) to control ``CPUFreq`` behavior for the corresponding policy
+objects (that is, for all of the CPUs associated with them).
+
+Some of those attributes are generic.  They are created by the ``CPUFreq`` core
+and their behavior generally does not depend on what scaling driver is in use
+and what scaling governor is attached to the given policy.  Some scaling drivers
+also add driver-specific attributes to the policy directories in ``sysfs`` to
+control policy-specific aspects of driver behavior.
+
+The generic attributes under :file:`/sys/devices/system/cpu/cpufreq/policyX/`
+are the following:
+
+``affected_cpus``
+	List of online CPUs belonging to this policy (i.e. sharing the hardware
+	performance scaling interface represented by the ``policyX`` policy
+	object).
+
+``bios_limit``
+	If the platform firmware (BIOS) tells the OS to apply an upper limit to
+	CPU frequencies, that limit will be reported through this attribute (if
+	present).
+
+	The existence of the limit may be a result of some (often unintentional)
+	BIOS settings, restrictions coming from a service processor or another
+	BIOS/HW-based mechanisms.
+
+	This does not cover ACPI thermal limitations which can be discovered
+	through a generic thermal driver.
+
+	This attribute is not present if the scaling driver in use does not
+	support it.
+
+``cpuinfo_max_freq``
+	Maximum possible operating frequency the CPUs belonging to this policy
+	can run at (in kHz).
+
+``cpuinfo_min_freq``
+	Minimum possible operating frequency the CPUs belonging to this policy
+	can run at (in kHz).
+
+``cpuinfo_transition_latency``
+	The time it takes to switch the CPUs belonging to this policy from one
+	P-state to another, in nanoseconds.
+
+	If unknown or if known to be so high that the scaling driver does not
+	work with the `ondemand`_ governor, -1 (:c:macro:`CPUFREQ_ETERNAL`)
+	will be returned by reads from this attribute.
+
+``related_cpus``
+	List of all (online and offline) CPUs belonging to this policy.
+
+``scaling_available_governors``
+	List of ``CPUFreq`` scaling governors present in the kernel that can
+	be attached to this policy or (if the ``intel_pstate`` scaling driver is
+	in use) list of scaling algorithms provided by the driver that can be
+	applied to this policy.
+
+	[Note that some governors are modular and it may be necessary to load a
+	kernel module for the governor held by it to become available and be
+	listed by this attribute.]
+
+``scaling_cur_freq``
+	Current frequency of all of the CPUs belonging to this policy (in kHz).
+
+	For the majority of scaling drivers, this is the frequency of the last
+	P-state requested by the driver from the hardware using the scaling
+	interface provided by it, which may or may not reflect the frequency
+	the CPU is actually running at (due to hardware design and other
+	limitations).
+
+	Some scaling drivers (e.g. ``intel_pstate``) attempt to provide
+	information more precisely reflecting the current CPU frequency through
+	this attribute, but that still may not be the exact current CPU
+	frequency as seen by the hardware at the moment.
+
+``scaling_driver``
+	The scaling driver currently in use.
+
+``scaling_governor``
+	The scaling governor currently attached to this policy or (if the
+	``intel_pstate`` scaling driver is in use) the scaling algorithm
+	provided by the driver that is currently applied to this policy.
+
+	This attribute is read-write and writing to it will cause a new scaling
+	governor to be attached to this policy or a new scaling algorithm
+	provided by the scaling driver to be applied to it (in the
+	``intel_pstate`` case), as indicated by the string written to this
+	attribute (which must be one of the names listed by the
+	``scaling_available_governors`` attribute described above).
+
+``scaling_max_freq``
+	Maximum frequency the CPUs belonging to this policy are allowed to be
+	running at (in kHz).
+
+	This attribute is read-write and writing a string representing an
+	integer to it will cause a new limit to be set (it must not be lower
+	than the value of the ``scaling_min_freq`` attribute).
+
+``scaling_min_freq``
+	Minimum frequency the CPUs belonging to this policy are allowed to be
+	running at (in kHz).
+
+	This attribute is read-write and writing a string representing a
+	non-negative integer to it will cause a new limit to be set (it must not
+	be higher than the value of the ``scaling_max_freq`` attribute).
+
+``scaling_setspeed``
+	This attribute is functional only if the `userspace`_ scaling governor
+	is attached to the given policy.
+
+	It returns the last frequency requested by the governor (in kHz) or can
+	be written to in order to set a new frequency for the policy.
+
+
+Generic Scaling Governors
+=========================
+
+``CPUFreq`` provides generic scaling governors that can be used with all
+scaling drivers.  As stated before, each of them implements a single, possibly
+parametrized, performance scaling algorithm.
+
+Scaling governors are attached to policy objects and different policy objects
+can be handled by different scaling governors at the same time (although that
+may lead to suboptimal results in some cases).
+
+The scaling governor for a given policy object can be changed at any time with
+the help of the ``scaling_governor`` policy attribute in ``sysfs``.
+
+Some governors expose ``sysfs`` attributes to control or fine-tune the scaling
+algorithms implemented by them.  Those attributes, referred to as governor
+tunables, can be either global (system-wide) or per-policy, depending on the
+scaling driver in use.  If the driver requires governor tunables to be
+per-policy, they are located in a subdirectory of each policy directory.
+Otherwise, they are located in a subdirectory under
+:file:`/sys/devices/system/cpu/cpufreq/`.  In either case the name of the
+subdirectory containing the governor tunables is the name of the governor
+providing them.
+
+``performance``
+---------------
+
+When attached to a policy object, this governor causes the highest frequency,
+within the ``scaling_max_freq`` policy limit, to be requested for that policy.
+
+The request is made once at that time the governor for the policy is set to
+``performance`` and whenever the ``scaling_max_freq`` or ``scaling_min_freq``
+policy limits change after that.
+
+``powersave``
+-------------
+
+When attached to a policy object, this governor causes the lowest frequency,
+within the ``scaling_min_freq`` policy limit, to be requested for that policy.
+
+The request is made once at that time the governor for the policy is set to
+``powersave`` and whenever the ``scaling_max_freq`` or ``scaling_min_freq``
+policy limits change after that.
+
+``userspace``
+-------------
+
+This governor does not do anything by itself.  Instead, it allows user space
+to set the CPU frequency for the policy it is attached to by writing to the
+``scaling_setspeed`` attribute of that policy.
+
+``schedutil``
+-------------
+
+This governor uses CPU utilization data available from the CPU scheduler.  It
+generally is regarded as a part of the CPU scheduler, so it can access the
+scheduler's internal data structures directly.
+
+It runs entirely in scheduler context, although in some cases it may need to
+invoke the scaling driver asynchronously when it decides that the CPU frequency
+should be changed for a given policy (that depends on whether or not the driver
+is capable of changing the CPU frequency from scheduler context).
+
+The actions of this governor for a particular CPU depend on the scheduling class
+invoking its utilization update callback for that CPU.  If it is invoked by the
+RT or deadline scheduling classes, the governor will increase the frequency to
+the allowed maximum (that is, the ``scaling_max_freq`` policy limit).  In turn,
+if it is invoked by the CFS scheduling class, the governor will use the
+Per-Entity Load Tracking (PELT) metric for the root control group of the
+given CPU as the CPU utilization estimate (see the `Per-entity load tracking`_
+LWN.net article for a description of the PELT mechanism).  Then, the new
+CPU frequency to apply is computed in accordance with the formula
+
+	f = 1.25 * ``f_0`` * ``util`` / ``max``
+
+where ``util`` is the PELT number, ``max`` is the theoretical maximum of
+``util``, and ``f_0`` is either the maximum possible CPU frequency for the given
+policy (if the PELT number is frequency-invariant), or the current CPU frequency
+(otherwise).
+
+This governor also employs a mechanism allowing it to temporarily bump up the
+CPU frequency for tasks that have been waiting on I/O most recently, called
+"IO-wait boosting".  That happens when the :c:macro:`SCHED_CPUFREQ_IOWAIT` flag
+is passed by the scheduler to the governor callback which causes the frequency
+to go up to the allowed maximum immediately and then draw back to the value
+returned by the above formula over time.
+
+This governor exposes only one tunable:
+
+``rate_limit_us``
+	Minimum time (in microseconds) that has to pass between two consecutive
+	runs of governor computations (default: 1000 times the scaling driver's
+	transition latency).
+
+	The purpose of this tunable is to reduce the scheduler context overhead
+	of the governor which might be excessive without it.
+
+This governor generally is regarded as a replacement for the older `ondemand`_
+and `conservative`_ governors (described below), as it is simpler and more
+tightly integrated with the CPU scheduler, its overhead in terms of CPU context
+switches and similar is less significant, and it uses the scheduler's own CPU
+utilization metric, so in principle its decisions should not contradict the
+decisions made by the other parts of the scheduler.
+
+``ondemand``
+------------
+
+This governor uses CPU load as a CPU frequency selection metric.
+
+In order to estimate the current CPU load, it measures the time elapsed between
+consecutive invocations of its worker routine and computes the fraction of that
+time in which the given CPU was not idle.  The ratio of the non-idle (active)
+time to the total CPU time is taken as an estimate of the load.
+
+If this governor is attached to a policy shared by multiple CPUs, the load is
+estimated for all of them and the greatest result is taken as the load estimate
+for the entire policy.
+
+The worker routine of this governor has to run in process context, so it is
+invoked asynchronously (via a workqueue) and CPU P-states are updated from
+there if necessary.  As a result, the scheduler context overhead from this
+governor is minimum, but it causes additional CPU context switches to happen
+relatively often and the CPU P-state updates triggered by it can be relatively
+irregular.  Also, it affects its own CPU load metric by running code that
+reduces the CPU idle time (even though the CPU idle time is only reduced very
+slightly by it).
+
+It generally selects CPU frequencies proportional to the estimated load, so that
+the value of the ``cpuinfo_max_freq`` policy attribute corresponds to the load of
+1 (or 100%), and the value of the ``cpuinfo_min_freq`` policy attribute
+corresponds to the load of 0, unless when the load exceeds a (configurable)
+speedup threshold, in which case it will go straight for the highest frequency
+it is allowed to use (the ``scaling_max_freq`` policy limit).
+
+This governor exposes the following tunables:
+
+``sampling_rate``
+	This is how often the governor's worker routine should run, in
+	microseconds.
+
+	Typically, it is set to values of the order of 10000 (10 ms).  Its
+	default value is equal to the value of ``cpuinfo_transition_latency``
+	for each policy this governor is attached to (but since the unit here
+	is greater by 1000, this means that the time represented by
+	``sampling_rate`` is 1000 times greater than the transition latency by
+	default).
+
+	If this tunable is per-policy, the following shell command sets the time
+	represented by it to be 750 times as high as the transition latency::
+
+	# echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate
+
+
+``min_sampling_rate``
+	The minimum value of ``sampling_rate``.
+
+	Equal to 10000 (10 ms) if :c:macro:`CONFIG_NO_HZ_COMMON` and
+	:c:data:`tick_nohz_active` are both set or to 20 times the value of
+	:c:data:`jiffies` in microseconds otherwise.
+
+``up_threshold``
+	If the estimated CPU load is above this value (in percent), the governor
+	will set the frequency to the maximum value allowed for the policy.
+	Otherwise, the selected frequency will be proportional to the estimated
+	CPU load.
+
+``ignore_nice_load``
+	If set to 1 (default 0), it will cause the CPU load estimation code to
+	treat the CPU time spent on executing tasks with "nice" levels greater
+	than 0 as CPU idle time.
+
+	This may be useful if there are tasks in the system that should not be
+	taken into account when deciding what frequency to run the CPUs at.
+	Then, to make that happen it is sufficient to increase the "nice" level
+	of those tasks above 0 and set this attribute to 1.
+
+``sampling_down_factor``
+	Temporary multiplier, between 1 (default) and 100 inclusive, to apply to
+	the ``sampling_rate`` value if the CPU load goes above ``up_threshold``.
+
+	This causes the next execution of the governor's worker routine (after
+	setting the frequency to the allowed maximum) to be delayed, so the
+	frequency stays at the maximum level for a longer time.
+
+	Frequency fluctuations in some bursty workloads may be avoided this way
+	at the cost of additional energy spent on maintaining the maximum CPU
+	capacity.
+
+``powersave_bias``
+	Reduction factor to apply to the original frequency target of the
+	governor (including the maximum value used when the ``up_threshold``
+	value is exceeded by the estimated CPU load) or sensitivity threshold
+	for the AMD frequency sensitivity powersave bias driver
+	(:file:`drivers/cpufreq/amd_freq_sensitivity.c`), between 0 and 1000
+	inclusive.
+
+	If the AMD frequency sensitivity powersave bias driver is not loaded,
+	the effective frequency to apply is given by
+
+		f * (1 - ``powersave_bias`` / 1000)
+
+	where f is the governor's original frequency target.  The default value
+	of this attribute is 0 in that case.
+
+	If the AMD frequency sensitivity powersave bias driver is loaded, the
+	value of this attribute is 400 by default and it is used in a different
+	way.
+
+	On Family 16h (and later) AMD processors there is a mechanism to get a
+	measured workload sensitivity, between 0 and 100% inclusive, from the
+	hardware.  That value can be used to estimate how the performance of the
+	workload running on a CPU will change in response to frequency changes.
+
+	The performance of a workload with the sensitivity of 0 (memory-bound or
+	IO-bound) is not expected to increase at all as a result of increasing
+	the CPU frequency, whereas workloads with the sensitivity of 100%
+	(CPU-bound) are expected to perform much better if the CPU frequency is
+	increased.
+
+	If the workload sensitivity is less than the threshold represented by
+	the ``powersave_bias`` value, the sensitivity powersave bias driver
+	will cause the governor to select a frequency lower than its original
+	target, so as to avoid over-provisioning workloads that will not benefit
+	from running at higher CPU frequencies.
+
+``conservative``
+----------------
+
+This governor uses CPU load as a CPU frequency selection metric.
+
+It estimates the CPU load in the same way as the `ondemand`_ governor described
+above, but the CPU frequency selection algorithm implemented by it is different.
+
+Namely, it avoids changing the frequency significantly over short time intervals
+which may not be suitable for systems with limited power supply capacity (e.g.
+battery-powered).  To achieve that, it changes the frequency in relatively
+small steps, one step at a time, up or down - depending on whether or not a
+(configurable) threshold has been exceeded by the estimated CPU load.
+
+This governor exposes the following tunables:
+
+``freq_step``
+	Frequency step in percent of the maximum frequency the governor is
+	allowed to set (the ``scaling_max_freq`` policy limit), between 0 and
+	100 (5 by default).
+
+	This is how much the frequency is allowed to change in one go.  Setting
+	it to 0 will cause the default frequency step (5 percent) to be used
+	and setting it to 100 effectively causes the governor to periodically
+	switch the frequency between the ``scaling_min_freq`` and
+	``scaling_max_freq`` policy limits.
+
+``down_threshold``
+	Threshold value (in percent, 20 by default) used to determine the
+	frequency change direction.
+
+	If the estimated CPU load is greater than this value, the frequency will
+	go up (by ``freq_step``).  If the load is less than this value (and the
+	``sampling_down_factor`` mechanism is not in effect), the frequency will
+	go down.  Otherwise, the frequency will not be changed.
+
+``sampling_down_factor``
+	Frequency decrease deferral factor, between 1 (default) and 10
+	inclusive.
+
+	It effectively causes the frequency to go down ``sampling_down_factor``
+	times slower than it ramps up.
+
+
+Frequency Boost Support
+=======================
+
+Background
+----------
+
+Some processors support a mechanism to raise the operating frequency of some
+cores in a multicore package temporarily (and above the sustainable frequency
+threshold for the whole package) under certain conditions, for example if the
+whole chip is not fully utilized and below its intended thermal or power budget.
+
+Different names are used by different vendors to refer to this functionality.
+For Intel processors it is referred to as "Turbo Boost", AMD calls it
+"Turbo-Core" or (in technical documentation) "Core Performance Boost" and so on.
+As a rule, it also is implemented differently by different vendors.  The simple
+term "frequency boost" is used here for brevity to refer to all of those
+implementations.
+
+The frequency boost mechanism may be either hardware-based or software-based.
+If it is hardware-based (e.g. on x86), the decision to trigger the boosting is
+made by the hardware (although in general it requires the hardware to be put
+into a special state in which it can control the CPU frequency within certain
+limits).  If it is software-based (e.g. on ARM), the scaling driver decides
+whether or not to trigger boosting and when to do that.
+
+The ``boost`` File in ``sysfs``
+-------------------------------
+
+This file is located under :file:`/sys/devices/system/cpu/cpufreq/` and controls
+the "boost" setting for the whole system.  It is not present if the underlying
+scaling driver does not support the frequency boost mechanism (or supports it,
+but provides a driver-specific interface for controlling it, like
+``intel_pstate``).
+
+If the value in this file is 1, the frequency boost mechanism is enabled.  This
+means that either the hardware can be put into states in which it is able to
+trigger boosting (in the hardware-based case), or the software is allowed to
+trigger boosting (in the software-based case).  It does not mean that boosting
+is actually in use at the moment on any CPUs in the system.  It only means a
+permission to use the frequency boost mechanism (which still may never be used
+for other reasons).
+
+If the value in this file is 0, the frequency boost mechanism is disabled and
+cannot be used at all.
+
+The only values that can be written to this file are 0 and 1.
+
+Rationale for Boost Control Knob
+--------------------------------
+
+The frequency boost mechanism is generally intended to help to achieve optimum
+CPU performance on time scales below software resolution (e.g. below the
+scheduler tick interval) and it is demonstrably suitable for many workloads, but
+it may lead to problems in certain situations.
+
+For this reason, many systems make it possible to disable the frequency boost
+mechanism in the platform firmware (BIOS) setup, but that requires the system to
+be restarted for the setting to be adjusted as desired, which may not be
+practical at least in some cases.  For example:
+
+  1. Boosting means overclocking the processor, although under controlled
+     conditions.  Generally, the processor's energy consumption increases
+     as a result of increasing its frequency and voltage, even temporarily.
+     That may not be desirable on systems that switch to power sources of
+     limited capacity, such as batteries, so the ability to disable the boost
+     mechanism while the system is running may help there (but that depends on
+     the workload too).
+
+  2. In some situations deterministic behavior is more important than
+     performance or energy consumption (or both) and the ability to disable
+     boosting while the system is running may be useful then.
+
+  3. To examine the impact of the frequency boost mechanism itself, it is useful
+     to be able to run tests with and without boosting, preferably without
+     restarting the system in the meantime.
+
+  4. Reproducible results are important when running benchmarks.  Since
+     the boosting functionality depends on the load of the whole package,
+     single-thread performance may vary because of it which may lead to
+     unreproducible results sometimes.  That can be avoided by disabling the
+     frequency boost mechanism before running benchmarks sensitive to that
+     issue.
+
+Legacy AMD ``cpb`` Knob
+-----------------------
+
+The AMD powernow-k8 scaling driver supports a ``sysfs`` knob very similar to
+the global ``boost`` one.  It is used for disabling/enabling the "Core
+Performance Boost" feature of some AMD processors.
+
+If present, that knob is located in every ``CPUFreq`` policy directory in
+``sysfs`` (:file:`/sys/devices/system/cpu/cpufreq/policyX/`) and is called
+``cpb``, which indicates a more fine grained control interface.  The actual
+implementation, however, works on the system-wide basis and setting that knob
+for one policy causes the same value of it to be set for all of the other
+policies at the same time.
+
+That knob is still supported on AMD processors that support its underlying
+hardware feature, but it may be configured out of the kernel (via the
+:c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option) and the global
+``boost`` knob is present regardless.  Thus it is always possible use the
+``boost`` knob instead of the ``cpb`` one which is highly recommended, as that
+is more consistent with what all of the other systems do (and the ``cpb`` knob
+may not be supported any more in the future).
+
+The ``cpb`` knob is never present for any processors without the underlying
+hardware feature (e.g. all Intel ones), even if the
+:c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option is set.
+
+
+.. _Per-entity load tracking: https://lwn.net/Articles/531853/
diff --git a/Documentation/admin-guide/pm/index.rst b/Documentation/admin-guide/pm/index.rst
new file mode 100644
index 000000000000..c80f087321fc
--- /dev/null
+++ b/Documentation/admin-guide/pm/index.rst
@@ -0,0 +1,15 @@
+================
+Power Management
+================
+
+.. toctree::
+   :maxdepth: 2
+
+   cpufreq
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst
index 1b90c6f00a92..8c7bbf2c88d2 100644
--- a/Documentation/admin-guide/ras.rst
+++ b/Documentation/admin-guide/ras.rst
@@ -8,7 +8,7 @@ RAS concepts
 ************
 
 Reliability, Availability and Serviceability (RAS) is a concept used on
-servers meant to measure their robusteness.
+servers meant to measure their robustness.
 
 Reliability
   is the probability that a system will produce correct outputs.
@@ -42,13 +42,13 @@ Among the monitoring measures, the most usual ones include:
 
 * CPU – detect errors at instruction execution and at L1/L2/L3 caches;
 * Memory – add error correction logic (ECC) to detect and correct errors;
-* I/O – add CRC checksums for tranfered data;
+* I/O – add CRC checksums for transferred data;
 * Storage – RAID, journal file systems, checksums,
   Self-Monitoring, Analysis and Reporting Technology (SMART).
 
 By monitoring the number of occurrences of error detections, it is possible
 to identify if the probability of hardware errors is increasing, and, on such
-case, do a preventive maintainance to replace a degrated component while
+case, do a preventive maintenance to replace a degraded component while
 those errors are correctable.
 
 Types of errors
@@ -121,7 +121,7 @@ using the ``dmidecode`` tool. For example, on a desktop machine, it shows::
 On the above example, a DDR4 SO-DIMM memory module is located at the
 system's memory labeled as "BANK 0", as given by the *bank locator* field.
 Please notice that, on such system, the *total width* is equal to the
-*data witdh*. It means that such memory module doesn't have error
+*data width*. It means that such memory module doesn't have error
 detection/correction mechanisms.
 
 Unfortunately, not all systems use the same field to specify the memory
@@ -145,7 +145,7 @@ bank. On this example, from an older server, ``dmidecode`` shows::
 
 There, the DDR3 RDIMM memory module is located at the system's memory labeled
 as "DIMM_A1", as given by the *locator* field. Please notice that this
-memory module has 64 bits of *data witdh* and 72 bits of *total width*. So,
+memory module has 64 bits of *data width* and 72 bits of *total width*. So,
 it has 8 extra bits to be used by error detection and correction mechanisms.
 Such kind of memory is called Error-correcting code memory (ECC memory).
 
@@ -186,7 +186,7 @@ Architecture (MCA)\ [#f3]_.
 .. [#f1] Please notice that several memory controllers allow operation on a
   mode called "Lock-Step", where it groups two memory modules together,
   doing 128-bit reads/writes. That gives 16 bits for error correction, with
-  significatively improves the error correction mechanism, at the expense
+  significantly improves the error correction mechanism, at the expense
   that, when an error happens, there's no way to know what memory module is
   to blame. So, it has to blame both memory modules.
 
diff --git a/Documentation/admin-guide/security-bugs.rst b/Documentation/admin-guide/security-bugs.rst
index 4f7414cad586..47574b382d75 100644
--- a/Documentation/admin-guide/security-bugs.rst
+++ b/Documentation/admin-guide/security-bugs.rst
@@ -14,14 +14,17 @@ Contact
 The Linux kernel security team can be contacted by email at
 <security@kernel.org>.  This is a private list of security officers
 who will help verify the bug report and develop and release a fix.
-It is possible that the security team will bring in extra help from
-area maintainers to understand and fix the security vulnerability.
+If you already have a fix, please include it with your report, as
+that can speed up the process considerably.  It is possible that the
+security team will bring in extra help from area maintainers to
+understand and fix the security vulnerability.
 
 As it is with any bug, the more information provided the easier it
 will be to diagnose and fix.  Please review the procedure outlined in
-admin-guide/reporting-bugs.rst if you are unclear about what information is helpful.
-Any exploit code is very helpful and will not be released without
-consent from the reporter unless it has already been made public.
+admin-guide/reporting-bugs.rst if you are unclear about what
+information is helpful.  Any exploit code is very helpful and will not
+be released without consent from the reporter unless it has already been
+made public.
 
 Disclosure
 ----------
@@ -39,6 +42,32 @@ disclosure is from immediate (esp. if it's already publicly known)
 to a few weeks.  As a basic default policy, we expect report date to
 disclosure date to be on the order of 7 days.
 
+Coordination
+------------
+
+Fixes for sensitive bugs, such as those that might lead to privilege
+escalations, may need to be coordinated with the private
+<linux-distros@vs.openwall.org> mailing list so that distribution vendors
+are well prepared to issue a fixed kernel upon public disclosure of the
+upstream fix. Distros will need some time to test the proposed patch and
+will generally request at least a few days of embargo, and vendor update
+publication prefers to happen Tuesday through Thursday. When appropriate,
+the security team can assist with this coordination, or the reporter can
+include linux-distros from the start. In this case, remember to prefix
+the email Subject line with "[vs]" as described in the linux-distros wiki:
+<http://oss-security.openwall.org/wiki/mailing-lists/distros#how-to-use-the-lists>
+
+CVE assignment
+--------------
+
+The security team does not normally assign CVEs, nor do we require them
+for reports or fixes, as this can needlessly complicate the process and
+may delay the bug handling. If a reporter wishes to have a CVE identifier
+assigned ahead of public disclosure, they will need to contact the private
+linux-distros list, described above. When such a CVE identifier is known
+before a patch is provided, it is desirable to mention it in the commit
+message, though.
+
 Non-disclosure agreements
 -------------------------
 
diff --git a/Documentation/admin-guide/sysrq.rst b/Documentation/admin-guide/sysrq.rst
index d1712ea2d314..7b9035c01a2e 100644
--- a/Documentation/admin-guide/sysrq.rst
+++ b/Documentation/admin-guide/sysrq.rst
@@ -212,7 +212,8 @@ I hit SysRq, but nothing seems to happen, what's wrong?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 There are some keyboards that produce a different keycode for SysRq than the
-pre-defined value of 99 (see ``KEY_SYSRQ`` in ``include/linux/input.h``), or
+pre-defined value of 99
+(see ``KEY_SYSRQ`` in ``include/uapi/linux/input-event-codes.h``), or
 which don't have a SysRq key at all. In these cases, run ``showkey -s`` to find
 an appropriate scancode sequence, and use ``setkeycodes <sequence> 99`` to map
 this sequence to the usual SysRq code (e.g., ``setkeycodes e05b 99``). It's
diff --git a/Documentation/arm/mem_alignment b/Documentation/arm/mem_alignment
index c7c7a114c78c..6335fcacbba9 100644
--- a/Documentation/arm/mem_alignment
+++ b/Documentation/arm/mem_alignment
@@ -48,7 +48,7 @@ Note that not all combinations are supported - only values 0 through 5.
 For example, the following will turn on the warnings, but without
 fixing up or sending SIGBUS signals:
 
-	echo 1 > /proc/sys/debug/alignment
+	echo 1 > /proc/cpu/alignment
 
 You can also read the content of the same file to get statistical
 information on unaligned access occurrences plus the current mode of
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index a71b8095dbd8..10f2dddbf449 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -54,6 +54,7 @@ stable kernels.
 | ARM            | Cortex-A57      | #852523         | N/A                         |
 | ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220        |
 | ARM            | Cortex-A72      | #853709         | N/A                         |
+| ARM            | Cortex-A73      | #858921         | ARM64_ERRATUM_858921        |
 | ARM            | MMU-500         | #841119,#826419 | N/A                         |
 |                |                 |                 |                             |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375        |
@@ -68,3 +69,4 @@ stable kernels.
 |                |                 |                 |                             |
 | Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
+| Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index e55103ace382..8d55b4bbb5e2 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
 	- This file
+bfq-iosched.txt
+	- BFQ IO scheduler and its tunables
 biodoc.txt
 	- Notes on the Generic Block Layer Rewrite in Linux 2.5
 biovecs.txt
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
new file mode 100644
index 000000000000..1b87df6cd476
--- /dev/null
+++ b/Documentation/block/bfq-iosched.txt
@@ -0,0 +1,531 @@
+BFQ (Budget Fair Queueing)
+==========================
+
+BFQ is a proportional-share I/O scheduler, with some extra
+low-latency capabilities. In addition to cgroups support (blkio or io
+controllers), BFQ's main features are:
+- BFQ guarantees a high system and application responsiveness, and a
+  low latency for time-sensitive applications, such as audio or video
+  players;
+- BFQ distributes bandwidth, and not just time, among processes or
+  groups (switching back to time distribution when needed to keep
+  throughput high).
+
+On average CPUs, the current version of BFQ can handle devices
+performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
+reference, 30-50 KIOPS correspond to very high bandwidths with
+sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
+to 120-200 MB/s with 4KB random I/O. BFQ has not yet been tested on
+multi-queue devices.
+
+The table of contents follow. Impatients can just jump to Section 3.
+
+CONTENTS
+
+1. When may BFQ be useful?
+ 1-1 Personal systems
+ 1-2 Server systems
+2. How does BFQ work?
+3. What are BFQ's tunable?
+4. BFQ group scheduling
+ 4-1 Service guarantees provided
+ 4-2 Interface
+
+1. When may BFQ be useful?
+==========================
+
+BFQ provides the following benefits on personal and server systems.
+
+1-1 Personal systems
+--------------------
+
+Low latency for interactive applications
+
+Regardless of the actual background workload, BFQ guarantees that, for
+interactive tasks, the storage device is virtually as responsive as if
+it was idle. For example, even if one or more of the following
+background workloads are being executed:
+- one or more large files are being read, written or copied,
+- a tree of source files is being compiled,
+- one or more virtual machines are performing I/O,
+- a software update is in progress,
+- indexing daemons are scanning filesystems and updating their
+  databases,
+starting an application or loading a file from within an application
+takes about the same time as if the storage device was idle. As a
+comparison, with CFQ, NOOP or DEADLINE, and in the same conditions,
+applications experience high latencies, or even become unresponsive
+until the background workload terminates (also on SSDs).
+
+Low latency for soft real-time applications
+
+Also soft real-time applications, such as audio and video
+players/streamers, enjoy a low latency and a low drop rate, regardless
+of the background I/O workload. As a consequence, these applications
+do not suffer from almost any glitch due to the background workload.
+
+Higher speed for code-development tasks
+
+If some additional workload happens to be executed in parallel, then
+BFQ executes the I/O-related components of typical code-development
+tasks (compilation, checkout, merge, ...) much more quickly than CFQ,
+NOOP or DEADLINE.
+
+High throughput
+
+On hard disks, BFQ achieves up to 30% higher throughput than CFQ, and
+up to 150% higher throughput than DEADLINE and NOOP, with all the
+sequential workloads considered in our tests. With random workloads,
+and with all the workloads on flash-based devices, BFQ achieves,
+instead, about the same throughput as the other schedulers.
+
+Strong fairness, bandwidth and delay guarantees
+
+BFQ distributes the device throughput, and not just the device time,
+among I/O-bound applications in proportion their weights, with any
+workload and regardless of the device parameters. From these bandwidth
+guarantees, it is possible to compute tight per-I/O-request delay
+guarantees by a simple formula. If not configured for strict service
+guarantees, BFQ switches to time-based resource sharing (only) for
+applications that would otherwise cause a throughput loss.
+
+1-2 Server systems
+------------------
+
+Most benefits for server systems follow from the same service
+properties as above. In particular, regardless of whether additional,
+possibly heavy workloads are being served, BFQ guarantees:
+
+. audio and video-streaming with zero or very low jitter and drop
+  rate;
+
+. fast retrieval of WEB pages and embedded objects;
+
+. real-time recording of data in live-dumping applications (e.g.,
+  packet logging);
+
+. responsiveness in local and remote access to a server.
+
+
+2. How does BFQ work?
+=====================
+
+BFQ is a proportional-share I/O scheduler, whose general structure,
+plus a lot of code, are borrowed from CFQ.
+
+- Each process doing I/O on a device is associated with a weight and a
+  (bfq_)queue.
+
+- BFQ grants exclusive access to the device, for a while, to one queue
+  (process) at a time, and implements this service model by
+  associating every queue with a budget, measured in number of
+  sectors.
+
+  - After a queue is granted access to the device, the budget of the
+    queue is decremented, on each request dispatch, by the size of the
+    request.
+
+  - The in-service queue is expired, i.e., its service is suspended,
+    only if one of the following events occurs: 1) the queue finishes
+    its budget, 2) the queue empties, 3) a "budget timeout" fires.
+
+    - The budget timeout prevents processes doing random I/O from
+      holding the device for too long and dramatically reducing
+      throughput.
+
+    - Actually, as in CFQ, a queue associated with a process issuing
+      sync requests may not be expired immediately when it empties. In
+      contrast, BFQ may idle the device for a short time interval,
+      giving the process the chance to go on being served if it issues
+      a new request in time. Device idling typically boosts the
+      throughput on rotational devices, if processes do synchronous
+      and sequential I/O. In addition, under BFQ, device idling is
+      also instrumental in guaranteeing the desired throughput
+      fraction to processes issuing sync requests (see the description
+      of the slice_idle tunable in this document, or [1, 2], for more
+      details).
+
+      - With respect to idling for service guarantees, if several
+	processes are competing for the device at the same time, but
+	all processes (and groups, after the following commit) have
+	the same weight, then BFQ guarantees the expected throughput
+	distribution without ever idling the device. Throughput is
+	thus as high as possible in this common scenario.
+
+  - If low-latency mode is enabled (default configuration), BFQ
+    executes some special heuristics to detect interactive and soft
+    real-time applications (e.g., video or audio players/streamers),
+    and to reduce their latency. The most important action taken to
+    achieve this goal is to give to the queues associated with these
+    applications more than their fair share of the device
+    throughput. For brevity, we call just "weight-raising" the whole
+    sets of actions taken by BFQ to privilege these queues. In
+    particular, BFQ provides a milder form of weight-raising for
+    interactive applications, and a stronger form for soft real-time
+    applications.
+
+  - BFQ automatically deactivates idling for queues born in a burst of
+    queue creations. In fact, these queues are usually associated with
+    the processes of applications and services that benefit mostly
+    from a high throughput. Examples are systemd during boot, or git
+    grep.
+
+  - As CFQ, BFQ merges queues performing interleaved I/O, i.e.,
+    performing random I/O that becomes mostly sequential if
+    merged. Differently from CFQ, BFQ achieves this goal with a more
+    reactive mechanism, called Early Queue Merge (EQM). EQM is so
+    responsive in detecting interleaved I/O (cooperating processes),
+    that it enables BFQ to achieve a high throughput, by queue
+    merging, even for queues for which CFQ needs a different
+    mechanism, preemption, to get a high throughput. As such EQM is a
+    unified mechanism to achieve a high throughput with interleaved
+    I/O.
+
+  - Queues are scheduled according to a variant of WF2Q+, named
+    B-WF2Q+, and implemented using an augmented rb-tree to preserve an
+    O(log N) overall complexity.  See [2] for more details. B-WF2Q+ is
+    also ready for hierarchical scheduling. However, for a cleaner
+    logical breakdown, the code that enables and completes
+    hierarchical support is provided in the next commit, which focuses
+    exactly on this feature.
+
+  - B-WF2Q+ guarantees a tight deviation with respect to an ideal,
+    perfectly fair, and smooth service. In particular, B-WF2Q+
+    guarantees that each queue receives a fraction of the device
+    throughput proportional to its weight, even if the throughput
+    fluctuates, and regardless of: the device parameters, the current
+    workload and the budgets assigned to the queue.
+
+  - The last, budget-independence, property (although probably
+    counterintuitive in the first place) is definitely beneficial, for
+    the following reasons:
+
+    - First, with any proportional-share scheduler, the maximum
+      deviation with respect to an ideal service is proportional to
+      the maximum budget (slice) assigned to queues. As a consequence,
+      BFQ can keep this deviation tight not only because of the
+      accurate service of B-WF2Q+, but also because BFQ *does not*
+      need to assign a larger budget to a queue to let the queue
+      receive a higher fraction of the device throughput.
+
+    - Second, BFQ is free to choose, for every process (queue), the
+      budget that best fits the needs of the process, or best
+      leverages the I/O pattern of the process. In particular, BFQ
+      updates queue budgets with a simple feedback-loop algorithm that
+      allows a high throughput to be achieved, while still providing
+      tight latency guarantees to time-sensitive applications. When
+      the in-service queue expires, this algorithm computes the next
+      budget of the queue so as to:
+
+      - Let large budgets be eventually assigned to the queues
+	associated with I/O-bound applications performing sequential
+	I/O: in fact, the longer these applications are served once
+	got access to the device, the higher the throughput is.
+
+      - Let small budgets be eventually assigned to the queues
+	associated with time-sensitive applications (which typically
+	perform sporadic and short I/O), because, the smaller the
+	budget assigned to a queue waiting for service is, the sooner
+	B-WF2Q+ will serve that queue (Subsec 3.3 in [2]).
+
+- If several processes are competing for the device at the same time,
+  but all processes and groups have the same weight, then BFQ
+  guarantees the expected throughput distribution without ever idling
+  the device. It uses preemption instead. Throughput is then much
+  higher in this common scenario.
+
+- ioprio classes are served in strict priority order, i.e.,
+  lower-priority queues are not served as long as there are
+  higher-priority queues.  Among queues in the same class, the
+  bandwidth is distributed in proportion to the weight of each
+  queue. A very thin extra bandwidth is however guaranteed to
+  the Idle class, to prevent it from starving.
+
+
+3. What are BFQ's tunable?
+==========================
+
+The tunables back_seek-max, back_seek_penalty, fifo_expire_async and
+fifo_expire_sync below are the same as in CFQ. Their description is
+just copied from that for CFQ. Some considerations in the description
+of slice_idle are copied from CFQ too.
+
+per-process ioprio and weight
+-----------------------------
+
+Unless the cgroups interface is used (see "4. BFQ group scheduling"),
+weights can be assigned to processes only indirectly, through I/O
+priorities, and according to the relation:
+weight = (IOPRIO_BE_NR - ioprio) * 10.
+
+Beware that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
+slice_idle
+----------
+
+This parameter specifies how long BFQ should idle for next I/O
+request, when certain sync BFQ queues become empty. By default
+slice_idle is a non-zero value. Idling has a double purpose: boosting
+throughput and making sure that the desired throughput distribution is
+respected (see the description of how BFQ works, and, if needed, the
+papers referred there).
+
+As for throughput, idling can be very helpful on highly seeky media
+like single spindle SATA/SAS disks where we can cut down on overall
+number of seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues and one
+should see an overall improved throughput on faster storage devices
+like multiple SATA/SAS disks in hardware RAID configuration.
+
+So depending on storage and workload, it might be useful to set
+slice_idle=0.  In general for SATA/SAS disks and software RAID of
+SATA/SAS disks keeping slice_idle enabled should be useful. For any
+configurations where there are multiple spindles behind single LUN
+(Host based hardware RAID controller or for storage arrays), setting
+slice_idle=0 might end up in better throughput and acceptable
+latencies.
+
+Idling is however necessary to have service guarantees enforced in
+case of differentiated weights or differentiated I/O-request lengths.
+To see why, suppose that a given BFQ queue A must get several I/O
+requests served for each request served for another queue B. Idling
+ensures that, if A makes a new I/O request slightly after becoming
+empty, then no request of B is dispatched in the middle, and thus A
+does not lose the possibility to get more than one request dispatched
+before the next request of B is dispatched. Note that idling
+guarantees the desired differentiated treatment of queues only in
+terms of I/O-request dispatches. To guarantee that the actual service
+order then corresponds to the dispatch order, the strict_guarantees
+tunable must be set too.
+
+There is an important flipside for idling: apart from the above cases
+where it is beneficial also for throughput, idling can severely impact
+throughput. One important case is random workload. Because of this
+issue, BFQ tends to avoid idling as much as possible, when it is not
+beneficial also for throughput. As a consequence of this behavior, and
+of further issues described for the strict_guarantees tunable,
+short-term service guarantees may be occasionally violated. And, in
+some cases, these guarantees may be more important than guaranteeing
+maximum throughput. For example, in video playing/streaming, a very
+low drop rate may be more important than maximum throughput. In these
+cases, consider setting the strict_guarantees parameter.
+
+strict_guarantees
+-----------------
+
+If this parameter is set (default: unset), then BFQ
+
+- always performs idling when the in-service queue becomes empty;
+
+- forces the device to serve one I/O request at a time, by dispatching a
+  new request only if there is no outstanding request.
+
+In the presence of differentiated weights or I/O-request sizes, both
+the above conditions are needed to guarantee that every BFQ queue
+receives its allotted share of the bandwidth. The first condition is
+needed for the reasons explained in the description of the slice_idle
+tunable.  The second condition is needed because all modern storage
+devices reorder internally-queued requests, which may trivially break
+the service guarantees enforced by the I/O scheduler.
+
+Setting strict_guarantees may evidently affect throughput.
+
+back_seek_max
+-------------
+
+This specifies, given in Kbytes, the maximum "distance" for backward seeking.
+The distance is the amount of space from the current head location to the
+sectors that are backward in terms of distance.
+
+This parameter allows the scheduler to anticipate requests in the "backward"
+direction and consider them as being the "next" if they are within this
+distance from the current head location.
+
+back_seek_penalty
+-----------------
+
+This parameter is used to compute the cost of backward seeking. If the
+backward distance of request is just 1/back_seek_penalty from a "front"
+request, then the seeking cost of two requests is considered equivalent.
+
+So scheduler will not bias toward one or the other request (otherwise scheduler
+will bias toward front request). Default value of back_seek_penalty is 2.
+
+fifo_expire_async
+-----------------
+
+This parameter is used to set the timeout of asynchronous requests. Default
+value of this is 248ms.
+
+fifo_expire_sync
+----------------
+
+This parameter is used to set the timeout of synchronous requests. Default
+value of this is 124ms. In case to favor synchronous requests over asynchronous
+one, this value should be decreased relative to fifo_expire_async.
+
+low_latency
+-----------
+
+This parameter is used to enable/disable BFQ's low latency mode. By
+default, low latency mode is enabled. If enabled, interactive and soft
+real-time applications are privileged and experience a lower latency,
+as explained in more detail in the description of how BFQ works.
+
+DO NOT enable this mode if you need full control on bandwidth
+distribution. In fact, if it is enabled, then BFQ automatically
+increases the bandwidth share of privileged applications, as the main
+means to guarantee a lower latency to them.
+
+timeout_sync
+------------
+
+Maximum amount of device time that can be given to a task (queue) once
+it has been selected for service. On devices with costly seeks,
+increasing this time usually increases maximum throughput. On the
+opposite end, increasing this time coarsens the granularity of the
+short-term bandwidth and latency guarantees, especially if the
+following parameter is set to zero.
+
+max_budget
+----------
+
+Maximum amount of service, measured in sectors, that can be provided
+to a BFQ queue once it is set in service (of course within the limits
+of the above timeout). According to what said in the description of
+the algorithm, larger values increase the throughput in proportion to
+the percentage of sequential I/O requests issued. The price of larger
+values is that they coarsen the granularity of short-term bandwidth
+and latency guarantees.
+
+The default value is 0, which enables auto-tuning: BFQ sets max_budget
+to the maximum number of sectors that can be served during
+timeout_sync, according to the estimated peak rate.
+
+weights
+-------
+
+Read-only parameter, used to show the weights of the currently active
+BFQ queues.
+
+
+wr_ tunables
+------------
+
+BFQ exports a few parameters to control/tune the behavior of
+low-latency heuristics.
+
+wr_coeff
+
+Factor by which the weight of a weight-raised queue is multiplied. If
+the queue is deemed soft real-time, then the weight is further
+multiplied by an additional, constant factor.
+
+wr_max_time
+
+Maximum duration of a weight-raising period for an interactive task
+(ms). If set to zero (default value), then this value is computed
+automatically, as a function of the peak rate of the device. In any
+case, when the value of this parameter is read, it always reports the
+current duration, regardless of whether it has been set manually or
+computed automatically.
+
+wr_max_softrt_rate
+
+Maximum service rate below which a queue is deemed to be associated
+with a soft real-time application, and is then weight-raised
+accordingly (sectors/sec).
+
+wr_min_idle_time
+
+Minimum idle period after which interactive weight-raising may be
+reactivated for a queue (in ms).
+
+wr_rt_max_time
+
+Maximum weight-raising duration for soft real-time queues (in ms). The
+start time from which this duration is considered is automatically
+moved forward if the queue is detected to be still soft real-time
+before the current soft real-time weight-raising period finishes.
+
+wr_min_inter_arr_async
+
+Minimum period between I/O request arrivals after which weight-raising
+may be reactivated for an already busy async queue (in ms).
+
+
+4. Group scheduling with BFQ
+============================
+
+BFQ supports both cgroups-v1 and cgroups-v2 io controllers, namely
+blkio and io. In particular, BFQ supports weight-based proportional
+share. To activate cgroups support, set BFQ_GROUP_IOSCHED.
+
+4-1 Service guarantees provided
+-------------------------------
+
+With BFQ, proportional share means true proportional share of the
+device bandwidth, according to group weights. For example, a group
+with weight 200 gets twice the bandwidth, and not just twice the time,
+of a group with weight 100.
+
+BFQ supports hierarchies (group trees) of any depth. Bandwidth is
+distributed among groups and processes in the expected way: for each
+group, the children of the group share the whole bandwidth of the
+group in proportion to their weights. In particular, this implies
+that, for each leaf group, every process of the group receives the
+same share of the whole group bandwidth, unless the ioprio of the
+process is modified.
+
+The resource-sharing guarantee for a group may partially or totally
+switch from bandwidth to time, if providing bandwidth guarantees to
+the group lowers the throughput too much. This switch occurs on a
+per-process basis: if a process of a leaf group causes throughput loss
+if served in such a way to receive its share of the bandwidth, then
+BFQ switches back to just time-based proportional share for that
+process.
+
+4-2 Interface
+-------------
+
+To get proportional sharing of bandwidth with BFQ for a given device,
+BFQ must of course be the active scheduler for that device.
+
+Within each group directory, the names of the files associated with
+BFQ-specific cgroup parameters and stats begin with the "bfq."
+prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for
+BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
+parameter to set the weight of a group with BFQ is blkio.bfq.weight
+or io.bfq.weight.
+
+Parameters to set
+-----------------
+
+For each group, there is only the following parameter to set.
+
+weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the
+group inside its parent. Available values: 1..10000 (default 100). The
+linear mapping between ioprio and weights, described at the beginning
+of the tunable section, is still valid, but all weights higher than
+IOPRIO_BE_NR*10 are mapped to ioprio 0.
+
+Recall that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
+
+[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+    Scheduler", Proceedings of the First Workshop on Mobile System
+    Technologies (MST-2015), May 2015.
+    http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+
+[2] P. Valente and M. Andreolini, "Improving Application
+    Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
+    the 5th Annual International Systems and Storage Conference
+    (SYSTOR '12), June 2012.
+    Slightly extended version:
+    http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
+							results.pdf
diff --git a/Documentation/block/kyber-iosched.txt b/Documentation/block/kyber-iosched.txt
new file mode 100644
index 000000000000..e94feacd7edc
--- /dev/null
+++ b/Documentation/block/kyber-iosched.txt
@@ -0,0 +1,14 @@
+Kyber I/O scheduler tunables
+===========================
+
+The only two tunables for the Kyber scheduler are the target latencies for
+reads and synchronous writes. Kyber will throttle requests in order to meet
+these target latencies.
+
+read_lat_nsec
+-------------
+Target latency for reads (in nanoseconds).
+
+write_lat_nsec
+--------------
+Target latency for synchronous writes (in nanoseconds).
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index c0a3bb5a6e4e..2c1e67058fd3 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -43,11 +43,6 @@ large discards are issued, setting this value lower will make Linux issue
 smaller discards and potentially help reduce latencies induced by large
 discard operations.
 
-discard_zeroes_data (RO)
-------------------------
-When read, this file will show if the discarded block are zeroed by the
-device or not. If its value is '1' the blocks are zeroed otherwise not.
-
 hw_sector_size (RO)
 -------------------
 This is the hardware sector size of the device, in bytes.
@@ -192,5 +187,11 @@ scaling back writes. Writing a value of '0' to this file disables the
 feature. Writing a value of '-1' to this file resets the value to the
 default setting.
 
+throttle_sample_time (RW)
+-------------------------
+This is the time window that blk-throttle samples data, in millisecond.
+blk-throttle makes decision based on the samplings. Lower time means cgroups
+have more smooth throughput, but higher CPU overhead. This exists only when
+CONFIG_BLK_DEV_THROTTLING_LOW is enabled.
 
 Jens Axboe <jens.axboe@oracle.com>, February 2009
diff --git a/Documentation/blockdev/mflash.txt b/Documentation/blockdev/mflash.txt
deleted file mode 100644
index f7e050551487..000000000000
--- a/Documentation/blockdev/mflash.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-This document describes m[g]flash support in linux.
-
-Contents
-  1. Overview
-  2. Reserved area configuration
-  3. Example of mflash platform driver registration
-
-1. Overview
-
-Mflash and gflash are embedded flash drive. The only difference is mflash is
-MCP(Multi Chip Package) device. These two device operate exactly same way.
-So the rest mflash repersents mflash and gflash altogether.
-
-Internally, mflash has nand flash and other hardware logics and supports
-2 different operation (ATA, IO) modes. ATA mode doesn't need any new
-driver and currently works well under standard IDE subsystem. Actually it's
-one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
-IDE interface.
-
-Following are brief descriptions about IO mode.
-A. IO mode based on ATA protocol and uses some custom command. (read confirm,
-write confirm)
-B. IO mode uses SRAM bus interface.
-C. IO mode supports 4kB boot area, so host can boot from mflash.
-
-2. Reserved area configuration
-If host boot from mflash, usually needs raw area for boot loader image. All of
-the mflash's block device operation will be taken this value as start offset.
-Note that boot loader's size of reserved area and kernel configuration value
-must be same.
-
-3. Example of mflash platform driver registration
-Working mflash is very straight forward. Adding platform device stuff to board
-configuration file is all. Here is some pseudo example.
-
-static struct mg_drv_data mflash_drv_data = {
-	/* If you want to polling driver set to 1 */
-	.use_polling = 0,
-	/* device attribution */
-	.dev_attr = MG_BOOT_DEV
-};
-
-static struct resource mg_mflash_rsc[] = {
-	/* Base address of mflash */
-	[0] = {
-		.start = 0x08000000,
-		.end = 0x08000000 + SZ_64K - 1,
-		.flags = IORESOURCE_MEM
-	},
-	/* mflash interrupt pin */
-	[1] = {
-		.start = IRQ_GPIO(84),
-		.end = IRQ_GPIO(84),
-		.flags = IORESOURCE_IRQ
-	},
-	/* mflash reset pin */
-	[2] = {
-		.start = 43,
-		.end = 43,
-		.name = MG_RST_PIN,
-		.flags = IORESOURCE_IO
-	},
-	/* mflash reset-out pin
-	 * If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
-	 * should assign this */
-	[3] = {
-		.start = 51,
-		.end = 51,
-		.name = MG_RSTOUT_PIN,
-		.flags = IORESOURCE_IO
-	}
-};
-
-static struct platform_device mflash_dev = {
-	.name = MG_DEV_NAME,
-	.id = -1,
-	.dev = {
-		.platform_data = &mflash_drv_data,
-	},
-	.num_resources = ARRAY_SIZE(mg_mflash_rsc),
-	.resource = mg_mflash_rsc
-};
-
-platform_device_register(&mflash_dev);
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 3b8449f8ac7e..49d7c997fa1e 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -1142,16 +1142,17 @@ used by the kernel.
 
   pids.max
 
- A read-write single value file which exists on non-root cgroups.  The
- default is "max".
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
 
- Hard limit of number of processes.
+	Hard limit of number of processes.
 
   pids.current
 
- A read-only single value file which exists on all cgroups.
+	A read-only single value file which exists on all cgroups.
 
- The number of processes currently in the cgroup and its descendants.
+	The number of processes currently in the cgroup and its
+	descendants.
 
 Organisational operations are not blocked by cgroup policies, so it is
 possible to have pids.current > pids.max.  This can be done by either
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 7fadb3b83293..08aef4595059 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -17,7 +17,7 @@ import os
 import sphinx
 
 # Get Sphinx version
-major, minor, patch = map(int, sphinx.__version__.split("."))
+major, minor, patch = sphinx.version_info[:3]
 
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -29,12 +29,12 @@ from load_config import loadConfig
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
-#needs_sphinx = '1.0'
+needs_sphinx = '1.2'
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain']
+extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure']
 
 # The name of the math extension changed on Sphinx 1.4
 if major == 1 and minor > 3:
diff --git a/Documentation/core-api/flexible-arrays.rst b/Documentation/core-api/flexible-arrays.rst
new file mode 100644
index 000000000000..b6b85a1b518e
--- /dev/null
+++ b/Documentation/core-api/flexible-arrays.rst
@@ -0,0 +1,130 @@
+
+===================================
+Using flexible arrays in the kernel
+===================================
+
+Large contiguous memory allocations can be unreliable in the Linux kernel.
+Kernel programmers will sometimes respond to this problem by allocating
+pages with :c:func:`vmalloc()`.  This solution not ideal, though.  On 32-bit
+systems, memory from vmalloc() must be mapped into a relatively small address
+space; it's easy to run out.  On SMP systems, the page table changes required
+by vmalloc() allocations can require expensive cross-processor interrupts on
+all CPUs.  And, on all systems, use of space in the vmalloc() range increases
+pressure on the translation lookaside buffer (TLB), reducing the performance
+of the system.
+
+In many cases, the need for memory from vmalloc() can be eliminated by piecing
+together an array from smaller parts; the flexible array library exists to make
+this task easier.
+
+A flexible array holds an arbitrary (within limits) number of fixed-sized
+objects, accessed via an integer index.  Sparse arrays are handled
+reasonably well.  Only single-page allocations are made, so memory
+allocation failures should be relatively rare.  The down sides are that the
+arrays cannot be indexed directly, individual object size cannot exceed the
+system page size, and putting data into a flexible array requires a copy
+operation.  It's also worth noting that flexible arrays do no internal
+locking at all; if concurrent access to an array is possible, then the
+caller must arrange for appropriate mutual exclusion.
+
+The creation of a flexible array is done with :c:func:`flex_array_alloc()`::
+
+    #include <linux/flex_array.h>
+
+    struct flex_array *flex_array_alloc(int element_size,
+					unsigned int total,
+					gfp_t flags);
+
+The individual object size is provided by ``element_size``, while total is the
+maximum number of objects which can be stored in the array.  The flags
+argument is passed directly to the internal memory allocation calls.  With
+the current code, using flags to ask for high memory is likely to lead to
+notably unpleasant side effects.
+
+It is also possible to define flexible arrays at compile time with::
+
+    DEFINE_FLEX_ARRAY(name, element_size, total);
+
+This macro will result in a definition of an array with the given name; the
+element size and total will be checked for validity at compile time.
+
+Storing data into a flexible array is accomplished with a call to
+:c:func:`flex_array_put()`::
+
+    int flex_array_put(struct flex_array *array, unsigned int element_nr,
+    		       void *src, gfp_t flags);
+
+This call will copy the data from src into the array, in the position
+indicated by ``element_nr`` (which must be less than the maximum specified when
+the array was created).  If any memory allocations must be performed, flags
+will be used.  The return value is zero on success, a negative error code
+otherwise.
+
+There might possibly be a need to store data into a flexible array while
+running in some sort of atomic context; in this situation, sleeping in the
+memory allocator would be a bad thing.  That can be avoided by using
+``GFP_ATOMIC`` for the flags value, but, often, there is a better way.  The
+trick is to ensure that any needed memory allocations are done before
+entering atomic context, using :c:func:`flex_array_prealloc()`::
+
+    int flex_array_prealloc(struct flex_array *array, unsigned int start,
+			    unsigned int nr_elements, gfp_t flags);
+
+This function will ensure that memory for the elements indexed in the range
+defined by ``start`` and ``nr_elements`` has been allocated.  Thereafter, a
+``flex_array_put()`` call on an element in that range is guaranteed not to
+block.
+
+Getting data back out of the array is done with :c:func:`flex_array_get()`::
+
+    void *flex_array_get(struct flex_array *fa, unsigned int element_nr);
+
+The return value is a pointer to the data element, or NULL if that
+particular element has never been allocated.
+
+Note that it is possible to get back a valid pointer for an element which
+has never been stored in the array.  Memory for array elements is allocated
+one page at a time; a single allocation could provide memory for several
+adjacent elements.  Flexible array elements are normally initialized to the
+value ``FLEX_ARRAY_FREE`` (defined as 0x6c in <linux/poison.h>), so errors
+involving that number probably result from use of unstored array entries.
+Note that, if array elements are allocated with ``__GFP_ZERO``, they will be
+initialized to zero and this poisoning will not happen.
+
+Individual elements in the array can be cleared with
+:c:func:`flex_array_clear()`::
+
+    int flex_array_clear(struct flex_array *array, unsigned int element_nr);
+
+This function will set the given element to ``FLEX_ARRAY_FREE`` and return
+zero.  If storage for the indicated element is not allocated for the array,
+``flex_array_clear()`` will return ``-EINVAL`` instead.  Note that clearing an
+element does not release the storage associated with it; to reduce the
+allocated size of an array, call :c:func:`flex_array_shrink()`::
+
+    int flex_array_shrink(struct flex_array *array);
+
+The return value will be the number of pages of memory actually freed.
+This function works by scanning the array for pages containing nothing but
+``FLEX_ARRAY_FREE`` bytes, so (1) it can be expensive, and (2) it will not work
+if the array's pages are allocated with ``__GFP_ZERO``.
+
+It is possible to remove all elements of an array with a call to
+:c:func:`flex_array_free_parts()`::
+
+    void flex_array_free_parts(struct flex_array *array);
+
+This call frees all elements, but leaves the array itself in place.
+Freeing the entire array is done with :c:func:`flex_array_free()`::
+
+    void flex_array_free(struct flex_array *array);
+
+As of this writing, there are no users of flexible arrays in the mainline
+kernel.  The functions described here are also not exported to modules;
+that will probably be fixed when somebody comes up with a need for it.
+
+
+Flexible array functions
+------------------------
+
+.. kernel-doc:: include/linux/flex_array.h
diff --git a/Documentation/core-api/genericirq.rst b/Documentation/core-api/genericirq.rst
new file mode 100644
index 000000000000..0054bd48be84
--- /dev/null
+++ b/Documentation/core-api/genericirq.rst
@@ -0,0 +1,440 @@
+.. include:: <isonum.txt>
+
+==========================
+Linux generic IRQ handling
+==========================
+
+:Copyright: |copy| 2005-2010: Thomas Gleixner
+:Copyright: |copy| 2005-2006:  Ingo Molnar
+
+Introduction
+============
+
+The generic interrupt handling layer is designed to provide a complete
+abstraction of interrupt handling for device drivers. It is able to
+handle all the different types of interrupt controller hardware. Device
+drivers use generic API functions to request, enable, disable and free
+interrupts. The drivers do not have to know anything about interrupt
+hardware details, so they can be used on different platforms without
+code changes.
+
+This documentation is provided to developers who want to implement an
+interrupt subsystem based for their architecture, with the help of the
+generic IRQ handling layer.
+
+Rationale
+=========
+
+The original implementation of interrupt handling in Linux uses the
+:c:func:`__do_IRQ` super-handler, which is able to deal with every type of
+interrupt logic.
+
+Originally, Russell King identified different types of handlers to build
+a quite universal set for the ARM interrupt handler implementation in
+Linux 2.5/2.6. He distinguished between:
+
+-  Level type
+
+-  Edge type
+
+-  Simple type
+
+During the implementation we identified another type:
+
+-  Fast EOI type
+
+In the SMP world of the :c:func:`__do_IRQ` super-handler another type was
+identified:
+
+-  Per CPU type
+
+This split implementation of high-level IRQ handlers allows us to
+optimize the flow of the interrupt handling for each specific interrupt
+type. This reduces complexity in that particular code path and allows
+the optimized handling of a given type.
+
+The original general IRQ implementation used hw_interrupt_type
+structures and their ``->ack``, ``->end`` [etc.] callbacks to differentiate
+the flow control in the super-handler. This leads to a mix of flow logic
+and low-level hardware logic, and it also leads to unnecessary code
+duplication: for example in i386, there is an ``ioapic_level_irq`` and an
+``ioapic_edge_irq`` IRQ-type which share many of the low-level details but
+have different flow handling.
+
+A more natural abstraction is the clean separation of the 'irq flow' and
+the 'chip details'.
+
+Analysing a couple of architecture's IRQ subsystem implementations
+reveals that most of them can use a generic set of 'irq flow' methods
+and only need to add the chip-level specific code. The separation is
+also valuable for (sub)architectures which need specific quirks in the
+IRQ flow itself but not in the chip details - and thus provides a more
+transparent IRQ subsystem design.
+
+Each interrupt descriptor is assigned its own high-level flow handler,
+which is normally one of the generic implementations. (This high-level
+flow handler implementation also makes it simple to provide
+demultiplexing handlers which can be found in embedded platforms on
+various architectures.)
+
+The separation makes the generic interrupt handling layer more flexible
+and extensible. For example, an (sub)architecture can use a generic
+IRQ-flow implementation for 'level type' interrupts and add a
+(sub)architecture specific 'edge type' implementation.
+
+To make the transition to the new model easier and prevent the breakage
+of existing implementations, the :c:func:`__do_IRQ` super-handler is still
+available. This leads to a kind of duality for the time being. Over time
+the new model should be used in more and more architectures, as it
+enables smaller and cleaner IRQ subsystems. It's deprecated for three
+years now and about to be removed.
+
+Known Bugs And Assumptions
+==========================
+
+None (knock on wood).
+
+Abstraction layers
+==================
+
+There are three main levels of abstraction in the interrupt code:
+
+1. High-level driver API
+
+2. High-level IRQ flow handlers
+
+3. Chip-level hardware encapsulation
+
+Interrupt control flow
+----------------------
+
+Each interrupt is described by an interrupt descriptor structure
+irq_desc. The interrupt is referenced by an 'unsigned int' numeric
+value which selects the corresponding interrupt description structure in
+the descriptor structures array. The descriptor structure contains
+status information and pointers to the interrupt flow method and the
+interrupt chip structure which are assigned to this interrupt.
+
+Whenever an interrupt triggers, the low-level architecture code calls
+into the generic interrupt code by calling :c:func:`desc->handle_irq`. This
+high-level IRQ handling function only uses desc->irq_data.chip
+primitives referenced by the assigned chip descriptor structure.
+
+High-level Driver API
+---------------------
+
+The high-level Driver API consists of following functions:
+
+-  :c:func:`request_irq`
+
+-  :c:func:`free_irq`
+
+-  :c:func:`disable_irq`
+
+-  :c:func:`enable_irq`
+
+-  :c:func:`disable_irq_nosync` (SMP only)
+
+-  :c:func:`synchronize_irq` (SMP only)
+
+-  :c:func:`irq_set_irq_type`
+
+-  :c:func:`irq_set_irq_wake`
+
+-  :c:func:`irq_set_handler_data`
+
+-  :c:func:`irq_set_chip`
+
+-  :c:func:`irq_set_chip_data`
+
+See the autogenerated function documentation for details.
+
+High-level IRQ flow handlers
+----------------------------
+
+The generic layer provides a set of pre-defined irq-flow methods:
+
+-  :c:func:`handle_level_irq`
+
+-  :c:func:`handle_edge_irq`
+
+-  :c:func:`handle_fasteoi_irq`
+
+-  :c:func:`handle_simple_irq`
+
+-  :c:func:`handle_percpu_irq`
+
+-  :c:func:`handle_edge_eoi_irq`
+
+-  :c:func:`handle_bad_irq`
+
+The interrupt flow handlers (either pre-defined or architecture
+specific) are assigned to specific interrupts by the architecture either
+during bootup or during device initialization.
+
+Default flow implementations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Helper functions
+^^^^^^^^^^^^^^^^
+
+The helper functions call the chip primitives and are used by the
+default flow implementations. The following helper functions are
+implemented (simplified excerpt)::
+
+    default_enable(struct irq_data *data)
+    {
+        desc->irq_data.chip->irq_unmask(data);
+    }
+
+    default_disable(struct irq_data *data)
+    {
+        if (!delay_disable(data))
+            desc->irq_data.chip->irq_mask(data);
+    }
+
+    default_ack(struct irq_data *data)
+    {
+        chip->irq_ack(data);
+    }
+
+    default_mask_ack(struct irq_data *data)
+    {
+        if (chip->irq_mask_ack) {
+            chip->irq_mask_ack(data);
+        } else {
+            chip->irq_mask(data);
+            chip->irq_ack(data);
+        }
+    }
+
+    noop(struct irq_data *data))
+    {
+    }
+
+
+
+Default flow handler implementations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Default Level IRQ flow handler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+handle_level_irq provides a generic implementation for level-triggered
+interrupts.
+
+The following control flow is implemented (simplified excerpt)::
+
+    :c:func:`desc->irq_data.chip->irq_mask_ack`;
+    handle_irq_event(desc->action);
+    :c:func:`desc->irq_data.chip->irq_unmask`;
+
+
+Default Fast EOI IRQ flow handler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+handle_fasteoi_irq provides a generic implementation for interrupts,
+which only need an EOI at the end of the handler.
+
+The following control flow is implemented (simplified excerpt)::
+
+    handle_irq_event(desc->action);
+    :c:func:`desc->irq_data.chip->irq_eoi`;
+
+
+Default Edge IRQ flow handler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+handle_edge_irq provides a generic implementation for edge-triggered
+interrupts.
+
+The following control flow is implemented (simplified excerpt)::
+
+    if (desc->status & running) {
+        :c:func:`desc->irq_data.chip->irq_mask_ack`;
+        desc->status |= pending | masked;
+        return;
+    }
+    :c:func:`desc->irq_data.chip->irq_ack`;
+    desc->status |= running;
+    do {
+        if (desc->status & masked)
+            :c:func:`desc->irq_data.chip->irq_unmask`;
+        desc->status &= ~pending;
+        handle_irq_event(desc->action);
+    } while (status & pending);
+    desc->status &= ~running;
+
+
+Default simple IRQ flow handler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+handle_simple_irq provides a generic implementation for simple
+interrupts.
+
+.. note::
+
+   The simple flow handler does not call any handler/chip primitives.
+
+The following control flow is implemented (simplified excerpt)::
+
+    handle_irq_event(desc->action);
+
+
+Default per CPU flow handler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+handle_percpu_irq provides a generic implementation for per CPU
+interrupts.
+
+Per CPU interrupts are only available on SMP and the handler provides a
+simplified version without locking.
+
+The following control flow is implemented (simplified excerpt)::
+
+    if (desc->irq_data.chip->irq_ack)
+        :c:func:`desc->irq_data.chip->irq_ack`;
+    handle_irq_event(desc->action);
+    if (desc->irq_data.chip->irq_eoi)
+            :c:func:`desc->irq_data.chip->irq_eoi`;
+
+
+EOI Edge IRQ flow handler
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+handle_edge_eoi_irq provides an abnomination of the edge handler
+which is solely used to tame a badly wreckaged irq controller on
+powerpc/cell.
+
+Bad IRQ flow handler
+^^^^^^^^^^^^^^^^^^^^
+
+handle_bad_irq is used for spurious interrupts which have no real
+handler assigned..
+
+Quirks and optimizations
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+The generic functions are intended for 'clean' architectures and chips,
+which have no platform-specific IRQ handling quirks. If an architecture
+needs to implement quirks on the 'flow' level then it can do so by
+overriding the high-level irq-flow handler.
+
+Delayed interrupt disable
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This per interrupt selectable feature, which was introduced by Russell
+King in the ARM interrupt implementation, does not mask an interrupt at
+the hardware level when :c:func:`disable_irq` is called. The interrupt is kept
+enabled and is masked in the flow handler when an interrupt event
+happens. This prevents losing edge interrupts on hardware which does not
+store an edge interrupt event while the interrupt is disabled at the
+hardware level. When an interrupt arrives while the IRQ_DISABLED flag
+is set, then the interrupt is masked at the hardware level and the
+IRQ_PENDING bit is set. When the interrupt is re-enabled by
+:c:func:`enable_irq` the pending bit is checked and if it is set, the interrupt
+is resent either via hardware or by a software resend mechanism. (It's
+necessary to enable CONFIG_HARDIRQS_SW_RESEND when you want to use
+the delayed interrupt disable feature and your hardware is not capable
+of retriggering an interrupt.) The delayed interrupt disable is not
+configurable.
+
+Chip-level hardware encapsulation
+---------------------------------
+
+The chip-level hardware descriptor structure :c:type:`irq_chip` contains all
+the direct chip relevant functions, which can be utilized by the irq flow
+implementations.
+
+-  ``irq_ack``
+
+-  ``irq_mask_ack`` - Optional, recommended for performance
+
+-  ``irq_mask``
+
+-  ``irq_unmask``
+
+-  ``irq_eoi`` - Optional, required for EOI flow handlers
+
+-  ``irq_retrigger`` - Optional
+
+-  ``irq_set_type`` - Optional
+
+-  ``irq_set_wake`` - Optional
+
+These primitives are strictly intended to mean what they say: ack means
+ACK, masking means masking of an IRQ line, etc. It is up to the flow
+handler(s) to use these basic units of low-level functionality.
+
+__do_IRQ entry point
+====================
+
+The original implementation :c:func:`__do_IRQ` was an alternative entry point
+for all types of interrupts. It no longer exists.
+
+This handler turned out to be not suitable for all interrupt hardware
+and was therefore reimplemented with split functionality for
+edge/level/simple/percpu interrupts. This is not only a functional
+optimization. It also shortens code paths for interrupts.
+
+Locking on SMP
+==============
+
+The locking of chip registers is up to the architecture that defines the
+chip primitives. The per-irq structure is protected via desc->lock, by
+the generic layer.
+
+Generic interrupt chip
+======================
+
+To avoid copies of identical implementations of IRQ chips the core
+provides a configurable generic interrupt chip implementation.
+Developers should check carefully whether the generic chip fits their
+needs before implementing the same functionality slightly differently
+themselves.
+
+.. kernel-doc:: kernel/irq/generic-chip.c
+   :export:
+
+Structures
+==========
+
+This chapter contains the autogenerated documentation of the structures
+which are used in the generic IRQ layer.
+
+.. kernel-doc:: include/linux/irq.h
+   :internal:
+
+.. kernel-doc:: include/linux/interrupt.h
+   :internal:
+
+Public Functions Provided
+=========================
+
+This chapter contains the autogenerated documentation of the kernel API
+functions which are exported.
+
+.. kernel-doc:: kernel/irq/manage.c
+
+.. kernel-doc:: kernel/irq/chip.c
+
+Internal Functions Provided
+===========================
+
+This chapter contains the autogenerated documentation of the internal
+functions.
+
+.. kernel-doc:: kernel/irq/irqdesc.c
+
+.. kernel-doc:: kernel/irq/handle.c
+
+.. kernel-doc:: kernel/irq/chip.c
+
+Credits
+=======
+
+The following people have contributed to this document:
+
+1. Thomas Gleixner tglx@linutronix.de
+
+2. Ingo Molnar mingo@elte.hu
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index 0d93d8089136..62abd36bfffb 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -11,11 +11,14 @@ Core utilities
 .. toctree::
    :maxdepth: 1
 
+   kernel-api
    assoc_array
    atomic_ops
    cpu_hotplug
    local_ops
    workqueue
+   genericirq
+   flexible-arrays
 
 Interfaces for kernel debugging
 ===============================
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
new file mode 100644
index 000000000000..9ec8488319dc
--- /dev/null
+++ b/Documentation/core-api/kernel-api.rst
@@ -0,0 +1,346 @@
+====================
+The Linux Kernel API
+====================
+
+Data Types
+==========
+
+Doubly Linked Lists
+-------------------
+
+.. kernel-doc:: include/linux/list.h
+   :internal:
+
+Basic C Library Functions
+=========================
+
+When writing drivers, you cannot in general use routines which are from
+the C Library. Some of the functions have been found generally useful
+and they are listed below. The behaviour of these functions may vary
+slightly from those defined by ANSI, and these deviations are noted in
+the text.
+
+String Conversions
+------------------
+
+.. kernel-doc:: lib/vsprintf.c
+   :export:
+
+.. kernel-doc:: include/linux/kernel.h
+   :functions: kstrtol
+
+.. kernel-doc:: include/linux/kernel.h
+   :functions: kstrtoul
+
+.. kernel-doc:: lib/kstrtox.c
+   :export:
+
+String Manipulation
+-------------------
+
+.. kernel-doc:: lib/string.c
+   :export:
+
+Bit Operations
+--------------
+
+.. kernel-doc:: arch/x86/include/asm/bitops.h
+   :internal:
+
+Basic Kernel Library Functions
+==============================
+
+The Linux kernel provides more basic utility functions.
+
+Bitmap Operations
+-----------------
+
+.. kernel-doc:: lib/bitmap.c
+   :export:
+
+.. kernel-doc:: lib/bitmap.c
+   :internal:
+
+Command-line Parsing
+--------------------
+
+.. kernel-doc:: lib/cmdline.c
+   :export:
+
+CRC Functions
+-------------
+
+.. kernel-doc:: lib/crc7.c
+   :export:
+
+.. kernel-doc:: lib/crc16.c
+   :export:
+
+.. kernel-doc:: lib/crc-itu-t.c
+   :export:
+
+.. kernel-doc:: lib/crc32.c
+
+.. kernel-doc:: lib/crc-ccitt.c
+   :export:
+
+idr/ida Functions
+-----------------
+
+.. kernel-doc:: include/linux/idr.h
+   :doc: idr sync
+
+.. kernel-doc:: lib/idr.c
+   :doc: IDA description
+
+.. kernel-doc:: lib/idr.c
+   :export:
+
+Memory Management in Linux
+==========================
+
+The Slab Cache
+--------------
+
+.. kernel-doc:: include/linux/slab.h
+   :internal:
+
+.. kernel-doc:: mm/slab.c
+   :export:
+
+.. kernel-doc:: mm/util.c
+   :export:
+
+User Space Memory Access
+------------------------
+
+.. kernel-doc:: arch/x86/include/asm/uaccess_32.h
+   :internal:
+
+.. kernel-doc:: arch/x86/lib/usercopy_32.c
+   :export:
+
+More Memory Management Functions
+--------------------------------
+
+.. kernel-doc:: mm/readahead.c
+   :export:
+
+.. kernel-doc:: mm/filemap.c
+   :export:
+
+.. kernel-doc:: mm/memory.c
+   :export:
+
+.. kernel-doc:: mm/vmalloc.c
+   :export:
+
+.. kernel-doc:: mm/page_alloc.c
+   :internal:
+
+.. kernel-doc:: mm/mempool.c
+   :export:
+
+.. kernel-doc:: mm/dmapool.c
+   :export:
+
+.. kernel-doc:: mm/page-writeback.c
+   :export:
+
+.. kernel-doc:: mm/truncate.c
+   :export:
+
+Kernel IPC facilities
+=====================
+
+IPC utilities
+-------------
+
+.. kernel-doc:: ipc/util.c
+   :internal:
+
+FIFO Buffer
+===========
+
+kfifo interface
+---------------
+
+.. kernel-doc:: include/linux/kfifo.h
+   :internal:
+
+relay interface support
+=======================
+
+Relay interface support is designed to provide an efficient mechanism
+for tools and facilities to relay large amounts of data from kernel
+space to user space.
+
+relay interface
+---------------
+
+.. kernel-doc:: kernel/relay.c
+   :export:
+
+.. kernel-doc:: kernel/relay.c
+   :internal:
+
+Module Support
+==============
+
+Module Loading
+--------------
+
+.. kernel-doc:: kernel/kmod.c
+   :export:
+
+Inter Module support
+--------------------
+
+Refer to the file kernel/module.c for more information.
+
+Hardware Interfaces
+===================
+
+Interrupt Handling
+------------------
+
+.. kernel-doc:: kernel/irq/manage.c
+   :export:
+
+DMA Channels
+------------
+
+.. kernel-doc:: kernel/dma.c
+   :export:
+
+Resources Management
+--------------------
+
+.. kernel-doc:: kernel/resource.c
+   :internal:
+
+.. kernel-doc:: kernel/resource.c
+   :export:
+
+MTRR Handling
+-------------
+
+.. kernel-doc:: arch/x86/kernel/cpu/mtrr/main.c
+   :export:
+
+Security Framework
+==================
+
+.. kernel-doc:: security/security.c
+   :internal:
+
+.. kernel-doc:: security/inode.c
+   :export:
+
+Audit Interfaces
+================
+
+.. kernel-doc:: kernel/audit.c
+   :export:
+
+.. kernel-doc:: kernel/auditsc.c
+   :internal:
+
+.. kernel-doc:: kernel/auditfilter.c
+   :internal:
+
+Accounting Framework
+====================
+
+.. kernel-doc:: kernel/acct.c
+   :internal:
+
+Block Devices
+=============
+
+.. kernel-doc:: block/blk-core.c
+   :export:
+
+.. kernel-doc:: block/blk-core.c
+   :internal:
+
+.. kernel-doc:: block/blk-map.c
+   :export:
+
+.. kernel-doc:: block/blk-sysfs.c
+   :internal:
+
+.. kernel-doc:: block/blk-settings.c
+   :export:
+
+.. kernel-doc:: block/blk-exec.c
+   :export:
+
+.. kernel-doc:: block/blk-flush.c
+   :export:
+
+.. kernel-doc:: block/blk-lib.c
+   :export:
+
+.. kernel-doc:: block/blk-tag.c
+   :export:
+
+.. kernel-doc:: block/blk-tag.c
+   :internal:
+
+.. kernel-doc:: block/blk-integrity.c
+   :export:
+
+.. kernel-doc:: kernel/trace/blktrace.c
+   :internal:
+
+.. kernel-doc:: block/genhd.c
+   :internal:
+
+.. kernel-doc:: block/genhd.c
+   :export:
+
+Char devices
+============
+
+.. kernel-doc:: fs/char_dev.c
+   :export:
+
+Clock Framework
+===============
+
+The clock framework defines programming interfaces to support software
+management of the system clock tree. This framework is widely used with
+System-On-Chip (SOC) platforms to support power management and various
+devices which may need custom clock rates. Note that these "clocks"
+don't relate to timekeeping or real time clocks (RTCs), each of which
+have separate frameworks. These :c:type:`struct clk <clk>`
+instances may be used to manage for example a 96 MHz signal that is used
+to shift bits into and out of peripherals or busses, or otherwise
+trigger synchronous state machine transitions in system hardware.
+
+Power management is supported by explicit software clock gating: unused
+clocks are disabled, so the system doesn't waste power changing the
+state of transistors that aren't in active use. On some systems this may
+be backed by hardware clock gating, where clocks are gated without being
+disabled in software. Sections of chips that are powered but not clocked
+may be able to retain their last state. This low power state is often
+called a *retention mode*. This mode still incurs leakage currents,
+especially with finer circuit geometries, but for CMOS circuits power is
+mostly used by clocked state changes.
+
+Power-aware drivers only enable their clocks when the device they manage
+is in active use. Also, system sleep states often differ according to
+which clock domains are active: while a "standby" state may allow wakeup
+from several active domains, a "mem" (suspend-to-RAM) state may require
+a more wholesale shutdown of clocks derived from higher speed PLLs and
+oscillators, limiting the number of possible wakeup event sources. A
+driver's suspend method may need to be aware of system-specific clock
+constraints on the target sleep state.
+
+Some platforms support programmable clock generators. These can be used
+by external chips of various kinds, such as other CPUs, multimedia
+codecs, and devices with strict requirements for interface clocking.
+
+.. kernel-doc:: include/linux/clk.h
+   :internal:
diff --git a/Documentation/cpu-freq/boost.txt b/Documentation/cpu-freq/boost.txt
deleted file mode 100644
index dd62e1334f0a..000000000000
--- a/Documentation/cpu-freq/boost.txt
+++ /dev/null
@@ -1,93 +0,0 @@
-Processor boosting control
-
-	- information for users -
-
-Quick guide for the impatient:
---------------------
-/sys/devices/system/cpu/cpufreq/boost
-controls the boost setting for the whole system. You can read and write
-that file with either "0" (boosting disabled) or "1" (boosting allowed).
-Reading or writing 1 does not mean that the system is boosting at this
-very moment, but only that the CPU _may_ raise the frequency at it's
-discretion.
---------------------
-
-Introduction
--------------
-Some CPUs support a functionality to raise the operating frequency of
-some cores in a multi-core package if certain conditions apply, mostly
-if the whole chip is not fully utilized and below it's intended thermal
-budget. The decision about boost disable/enable is made either at hardware
-(e.g. x86) or software (e.g ARM).
-On Intel CPUs this is called "Turbo Boost", AMD calls it "Turbo-Core",
-in technical documentation "Core performance boost". In Linux we use
-the term "boost" for convenience.
-
-Rationale for disable switch
-----------------------------
-
-Though the idea is to just give better performance without any user
-intervention, sometimes the need arises to disable this functionality.
-Most systems offer a switch in the (BIOS) firmware to disable the
-functionality at all, but a more fine-grained and dynamic control would
-be desirable:
-1. While running benchmarks, reproducible results are important. Since
-   the boosting functionality depends on the load of the whole package,
-   single thread performance can vary. By explicitly disabling the boost
-   functionality at least for the benchmark's run-time the system will run
-   at a fixed frequency and results are reproducible again.
-2. To examine the impact of the boosting functionality it is helpful
-   to do tests with and without boosting.
-3. Boosting means overclocking the processor, though under controlled
-   conditions. By raising the frequency and the voltage the processor
-   will consume more power than without the boosting, which may be
-   undesirable for instance for mobile users. Disabling boosting may
-   save power here, though this depends on the workload.
-
-
-User controlled switch
-----------------------
-
-To allow the user to toggle the boosting functionality, the cpufreq core
-driver exports a sysfs knob to enable or disable it. There is a file:
-/sys/devices/system/cpu/cpufreq/boost
-which can either read "0" (boosting disabled) or "1" (boosting enabled).
-The file is exported only when cpufreq driver supports boosting.
-Explicitly changing the permissions and writing to that file anyway will
-return EINVAL.
-
-On supported CPUs one can write either a "0" or a "1" into this file.
-This will either disable the boost functionality on all cores in the
-whole system (0) or will allow the software or hardware to boost at will
-(1).
-
-Writing a "1" does not explicitly boost the system, but just allows the
-CPU to boost at their discretion. Some implementations take external
-factors like the chip's temperature into account, so boosting once does
-not necessarily mean that it will occur every time even using the exact
-same software setup.
-
-
-AMD legacy cpb switch
----------------------
-The AMD powernow-k8 driver used to support a very similar switch to
-disable or enable the "Core Performance Boost" feature of some AMD CPUs.
-This switch was instantiated in each CPU's cpufreq directory
-(/sys/devices/system/cpu[0-9]*/cpufreq) and was called "cpb".
-Though the per CPU existence hints at a more fine grained control, the
-actual implementation only supported a system-global switch semantics,
-which was simply reflected into each CPU's file. Writing a 0 or 1 into it
-would pull the other CPUs to the same state.
-For compatibility reasons this file and its behavior is still supported
-on AMD CPUs, though it is now protected by a config switch
-(X86_ACPI_CPUFREQ_CPB). On Intel CPUs this file will never be created,
-even with the config option set.
-This functionality is considered legacy and will be removed in some future
-kernel version.
-
-More fine grained boosting control
-----------------------------------
-
-Technically it is possible to switch the boosting functionality at least
-on a per package basis, for some CPUs even per core. Currently the driver
-does not support it, but this may be implemented in the future.
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index f71e6be26b83..434c49cc7330 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -231,7 +231,7 @@ the reference implementation in drivers/cpufreq/longrun.c
 Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset.
 
 get_intermediate should return a stable intermediate frequency platform wants to
-switch to, and target_intermediate() should set CPU to to that frequency, before
+switch to, and target_intermediate() should set CPU to that frequency, before
 jumping to the frequency corresponding to 'index'. Core will take care of
 sending notifications and driver doesn't have to handle them in
 target_intermediate() or target_index().
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
deleted file mode 100644
index 61b3184b6c24..000000000000
--- a/Documentation/cpu-freq/governors.txt
+++ /dev/null
@@ -1,301 +0,0 @@
-     CPU frequency and voltage scaling code in the Linux(TM) kernel
-
-
-		         L i n u x    C P U F r e q
-
-		      C P U F r e q   G o v e r n o r s
-
-		   - information for users and developers -
-
-
-		    Dominik Brodowski  <linux@brodo.de>
-            some additions and corrections by Nico Golde <nico@ngolde.de>
-		Rafael J. Wysocki <rafael.j.wysocki@intel.com>
-		   Viresh Kumar <viresh.kumar@linaro.org>
-
-
-
-   Clock scaling allows you to change the clock speed of the CPUs on the
-    fly. This is a nice method to save battery power, because the lower
-            the clock speed, the less power the CPU consumes.
-
-
-Contents:
----------
-1.   What is a CPUFreq Governor?
-
-2.   Governors In the Linux Kernel
-2.1  Performance
-2.2  Powersave
-2.3  Userspace
-2.4  Ondemand
-2.5  Conservative
-2.6  Schedutil
-
-3.   The Governor Interface in the CPUfreq Core
-
-4.   References
-
-
-1. What Is A CPUFreq Governor?
-==============================
-
-Most cpufreq drivers (except the intel_pstate and longrun) or even most
-cpu frequency scaling algorithms only allow the CPU frequency to be set
-to predefined fixed values.  In order to offer dynamic frequency
-scaling, the cpufreq core must be able to tell these drivers of a
-"target frequency". So these specific drivers will be transformed to
-offer a "->target/target_index/fast_switch()" call instead of the
-"->setpolicy()" call. For set_policy drivers, all stays the same,
-though.
-
-How to decide what frequency within the CPUfreq policy should be used?
-That's done using "cpufreq governors".
-
-Basically, it's the following flow graph:
-
-CPU can be set to switch independently	 |	   CPU can only be set
-      within specific "limits"		 |       to specific frequencies
-
-                                 "CPUfreq policy"
-		consists of frequency limits (policy->{min,max})
-  		     and CPUfreq governor to be used
-			 /		      \
-			/		       \
-		       /		       the cpufreq governor decides
-		      /			       (dynamically or statically)
-		     /			       what target_freq to set within
-		    /			       the limits of policy->{min,max}
-		   /			            \
-		  /				     \
-	Using the ->setpolicy call,		 Using the ->target/target_index/fast_switch call,
-	    the limits and the			  the frequency closest
-	     "policy" is set.			  to target_freq is set.
-						  It is assured that it
-						  is within policy->{min,max}
-
-
-2. Governors In the Linux Kernel
-================================
-
-2.1 Performance
----------------
-
-The CPUfreq governor "performance" sets the CPU statically to the
-highest frequency within the borders of scaling_min_freq and
-scaling_max_freq.
-
-
-2.2 Powersave
--------------
-
-The CPUfreq governor "powersave" sets the CPU statically to the
-lowest frequency within the borders of scaling_min_freq and
-scaling_max_freq.
-
-
-2.3 Userspace
--------------
-
-The CPUfreq governor "userspace" allows the user, or any userspace
-program running with UID "root", to set the CPU to a specific frequency
-by making a sysfs file "scaling_setspeed" available in the CPU-device
-directory.
-
-
-2.4 Ondemand
-------------
-
-The CPUfreq governor "ondemand" sets the CPU frequency depending on the
-current system load. Load estimation is triggered by the scheduler
-through the update_util_data->func hook; when triggered, cpufreq checks
-the CPU-usage statistics over the last period and the governor sets the
-CPU accordingly.  The CPU must have the capability to switch the
-frequency very quickly.
-
-Sysfs files:
-
-* sampling_rate:
-
-  Measured in uS (10^-6 seconds), this is how often you want the kernel
-  to look at the CPU usage and to make decisions on what to do about the
-  frequency.  Typically this is set to values of around '10000' or more.
-  It's default value is (cmp. with users-guide.txt): transition_latency
-  * 1000.  Be aware that transition latency is in ns and sampling_rate
-  is in us, so you get the same sysfs value by default.  Sampling rate
-  should always get adjusted considering the transition latency to set
-  the sampling rate 750 times as high as the transition latency in the
-  bash (as said, 1000 is default), do:
-
-  $ echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate
-
-* sampling_rate_min:
-
-  The sampling rate is limited by the HW transition latency:
-  transition_latency * 100
-
-  Or by kernel restrictions:
-  - If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed.
-  - If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is
-    used, the limits depend on the CONFIG_HZ option:
-    HZ=1000: min=20000us  (20ms)
-    HZ=250:  min=80000us  (80ms)
-    HZ=100:  min=200000us (200ms)
-
-  The highest value of kernel and HW latency restrictions is shown and
-  used as the minimum sampling rate.
-
-* up_threshold:
-
-  This defines what the average CPU usage between the samplings of
-  'sampling_rate' needs to be for the kernel to make a decision on
-  whether it should increase the frequency.  For example when it is set
-  to its default value of '95' it means that between the checking
-  intervals the CPU needs to be on average more than 95% in use to then
-  decide that the CPU frequency needs to be increased.
-
-* ignore_nice_load:
-
-  This parameter takes a value of '0' or '1'. When set to '0' (its
-  default), all processes are counted towards the 'cpu utilisation'
-  value.  When set to '1', the processes that are run with a 'nice'
-  value will not count (and thus be ignored) in the overall usage
-  calculation.  This is useful if you are running a CPU intensive
-  calculation on your laptop that you do not care how long it takes to
-  complete as you can 'nice' it and prevent it from taking part in the
-  deciding process of whether to increase your CPU frequency.
-
-* sampling_down_factor:
-
-  This parameter controls the rate at which the kernel makes a decision
-  on when to decrease the frequency while running at top speed. When set
-  to 1 (the default) decisions to reevaluate load are made at the same
-  interval regardless of current clock speed. But when set to greater
-  than 1 (e.g. 100) it acts as a multiplier for the scheduling interval
-  for reevaluating load when the CPU is at its top speed due to high
-  load. This improves performance by reducing the overhead of load
-  evaluation and helping the CPU stay at its top speed when truly busy,
-  rather than shifting back and forth in speed. This tunable has no
-  effect on behavior at lower speeds/lower CPU loads.
-
-* powersave_bias:
-
-  This parameter takes a value between 0 to 1000. It defines the
-  percentage (times 10) value of the target frequency that will be
-  shaved off of the target. For example, when set to 100 -- 10%, when
-  ondemand governor would have targeted 1000 MHz, it will target
-  1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0
-  (disabled) by default.
-
-  When AMD frequency sensitivity powersave bias driver --
-  drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter
-  defines the workload frequency sensitivity threshold in which a lower
-  frequency is chosen instead of ondemand governor's original target.
-  The frequency sensitivity is a hardware reported (on AMD Family 16h
-  Processors and above) value between 0 to 100% that tells software how
-  the performance of the workload running on a CPU will change when
-  frequency changes. A workload with sensitivity of 0% (memory/IO-bound)
-  will not perform any better on higher core frequency, whereas a
-  workload with sensitivity of 100% (CPU-bound) will perform better
-  higher the frequency. When the driver is loaded, this is set to 400 by
-  default -- for CPUs running workloads with sensitivity value below
-  40%, a lower frequency is chosen. Unloading the driver or writing 0
-  will disable this feature.
-
-
-2.5 Conservative
-----------------
-
-The CPUfreq governor "conservative", much like the "ondemand"
-governor, sets the CPU frequency depending on the current usage.  It
-differs in behaviour in that it gracefully increases and decreases the
-CPU speed rather than jumping to max speed the moment there is any load
-on the CPU. This behaviour is more suitable in a battery powered
-environment.  The governor is tweaked in the same manner as the
-"ondemand" governor through sysfs with the addition of:
-
-* freq_step:
-
-  This describes what percentage steps the cpu freq should be increased
-  and decreased smoothly by.  By default the cpu frequency will increase
-  in 5% chunks of your maximum cpu frequency.  You can change this value
-  to anywhere between 0 and 100 where '0' will effectively lock your CPU
-  at a speed regardless of its load whilst '100' will, in theory, make
-  it behave identically to the "ondemand" governor.
-
-* down_threshold:
-
-  Same as the 'up_threshold' found for the "ondemand" governor but for
-  the opposite direction.  For example when set to its default value of
-  '20' it means that if the CPU usage needs to be below 20% between
-  samples to have the frequency decreased.
-
-* sampling_down_factor:
-
-  Similar functionality as in "ondemand" governor.  But in
-  "conservative", it controls the rate at which the kernel makes a
-  decision on when to decrease the frequency while running in any speed.
-  Load for frequency increase is still evaluated every sampling rate.
-
-
-2.6 Schedutil
--------------
-
-The "schedutil" governor aims at better integration with the Linux
-kernel scheduler.  Load estimation is achieved through the scheduler's
-Per-Entity Load Tracking (PELT) mechanism, which also provides
-information about the recent load [1].  This governor currently does
-load based DVFS only for tasks managed by CFS. RT and DL scheduler tasks
-are always run at the highest frequency.  Unlike all the other
-governors, the code is located under the kernel/sched/ directory.
-
-Sysfs files:
-
-* rate_limit_us:
-
-  This contains a value in microseconds. The governor waits for
-  rate_limit_us time before reevaluating the load again, after it has
-  evaluated the load once.
-
-For an in-depth comparison with the other governors refer to [2].
-
-
-3. The Governor Interface in the CPUfreq Core
-=============================================
-
-A new governor must register itself with the CPUfreq core using
-"cpufreq_register_governor". The struct cpufreq_governor, which has to
-be passed to that function, must contain the following values:
-
-governor->name - A unique name for this governor.
-governor->owner - .THIS_MODULE for the governor module (if appropriate).
-
-plus a set of hooks to the functions implementing the governor's logic.
-
-The CPUfreq governor may call the CPU processor driver using one of
-these two functions:
-
-int cpufreq_driver_target(struct cpufreq_policy *policy,
-                                 unsigned int target_freq,
-                                 unsigned int relation);
-
-int __cpufreq_driver_target(struct cpufreq_policy *policy,
-                                   unsigned int target_freq,
-                                   unsigned int relation);
-
-target_freq must be within policy->min and policy->max, of course.
-What's the difference between these two functions? When your governor is
-in a direct code path of a call to governor callbacks, like
-governor->start(), the policy->rwsem is still held in the cpufreq core,
-and there's no need to lock it again (in fact, this would cause a
-deadlock). So use __cpufreq_driver_target only in these cases. In all
-other cases (for example, when there's a "daemonized" function that
-wakes up every second), use cpufreq_driver_target to take policy->rwsem
-before the command is passed to the cpufreq driver.
-
-4. References
-=============
-
-[1] Per-entity load tracking: https://lwn.net/Articles/531853/
-[2] Improvements in CPU frequency management: https://lwn.net/Articles/682391/
-
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt
index ef1d39247b05..03a7cee6ac73 100644
--- a/Documentation/cpu-freq/index.txt
+++ b/Documentation/cpu-freq/index.txt
@@ -21,8 +21,6 @@ Documents in this directory:
 
 amd-powernow.txt -	AMD powernow driver specific file.
 
-boost.txt -		Frequency boosting support.
-
 core.txt	-	General description of the CPUFreq core and
 			of CPUFreq notifiers.
 
@@ -32,17 +30,12 @@ cpufreq-nforce2.txt -	nVidia nForce2 platform specific file.
 
 cpufreq-stats.txt -	General description of sysfs cpufreq stats.
 
-governors.txt	-	What are cpufreq governors and how to
-			implement them?
-
 index.txt	-	File index, Mailing list and Links (this document)
 
 intel-pstate.txt -	Intel pstate cpufreq driver specific file.
 
 pcc-cpufreq.txt -	PCC cpufreq driver specific file.
 
-user-guide.txt	-	User Guide to CPUFreq
-
 
 Mailing List
 ------------
diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
deleted file mode 100644
index 391da64e9492..000000000000
--- a/Documentation/cpu-freq/user-guide.txt
+++ /dev/null
@@ -1,228 +0,0 @@
-     CPU frequency and voltage scaling code in the Linux(TM) kernel
-
-
-		         L i n u x    C P U F r e q
-
-			     U S E R   G U I D E
-
-
-		    Dominik Brodowski  <linux@brodo.de>
-
-
-
-   Clock scaling allows you to change the clock speed of the CPUs on the
-    fly. This is a nice method to save battery power, because the lower
-            the clock speed, the less power the CPU consumes.
-
-
-Contents:
----------
-1. Supported Architectures and Processors
-1.1 ARM and ARM64
-1.2 x86
-1.3 sparc64
-1.4 ppc
-1.5 SuperH
-1.6 Blackfin
-
-2. "Policy" / "Governor"?
-2.1 Policy
-2.2 Governor
-
-3. How to change the CPU cpufreq policy and/or speed
-3.1 Preferred interface: sysfs
-
-
-
-1. Supported Architectures and Processors
-=========================================
-
-1.1 ARM and ARM64
------------------
-
-Almost all ARM and ARM64 platforms support CPU frequency scaling.
-
-1.2 x86
--------
-
-The following processors for the x86 architecture are supported by cpufreq:
-
-AMD Elan - SC400, SC410
-AMD mobile K6-2+
-AMD mobile K6-3+
-AMD mobile Duron
-AMD mobile Athlon
-AMD Opteron
-AMD Athlon 64
-Cyrix Media GXm
-Intel mobile PIII and Intel mobile PIII-M on certain chipsets
-Intel Pentium 4, Intel Xeon
-Intel Pentium M (Centrino)
-National Semiconductors Geode GX
-Transmeta Crusoe
-Transmeta Efficeon
-VIA Cyrix 3 / C3
-various processors on some ACPI 2.0-compatible systems [*]
-And many more
-
-[*] Only if "ACPI Processor Performance States" are available
-to the ACPI<->BIOS interface.
-
-
-1.3 sparc64
------------
-
-The following processors for the sparc64 architecture are supported by
-cpufreq:
-
-UltraSPARC-III
-
-
-1.4 ppc
--------
-
-Several "PowerBook" and "iBook2" notebooks are supported.
-The following POWER processors are supported in powernv mode:
-POWER8
-POWER9
-
-1.5 SuperH
-----------
-
-All SuperH processors supporting rate rounding through the clock
-framework are supported by cpufreq.
-
-1.6 Blackfin
-------------
-
-The following Blackfin processors are supported by cpufreq:
-
-BF522, BF523, BF524, BF525, BF526, BF527, Rev 0.1 or higher
-BF531, BF532, BF533, Rev 0.3 or higher
-BF534, BF536, BF537, Rev 0.2 or higher
-BF561, Rev 0.3 or higher
-BF542, BF544, BF547, BF548, BF549, Rev 0.1 or higher
-
-
-2. "Policy" / "Governor" ?
-==========================
-
-Some CPU frequency scaling-capable processor switch between various
-frequencies and operating voltages "on the fly" without any kernel or
-user involvement. This guarantees very fast switching to a frequency
-which is high enough to serve the user's needs, but low enough to save
-power.
-
-
-2.1 Policy
-----------
-
-On these systems, all you can do is select the lower and upper
-frequency limit as well as whether you want more aggressive
-power-saving or more instantly available processing power.
-
-
-2.2 Governor
-------------
-
-On all other cpufreq implementations, these boundaries still need to
-be set. Then, a "governor" must be selected. Such a "governor" decides
-what speed the processor shall run within the boundaries. One such
-"governor" is the "userspace" governor. This one allows the user - or
-a yet-to-implement userspace program - to decide what specific speed
-the processor shall run at.
-
-
-3. How to change the CPU cpufreq policy and/or speed
-====================================================
-
-3.1 Preferred Interface: sysfs
-------------------------------
-
-The preferred interface is located in the sysfs filesystem. If you
-mounted it at /sys, the cpufreq interface is located in a subdirectory
-"cpufreq" within the cpu-device directory
-(e.g. /sys/devices/system/cpu/cpu0/cpufreq/ for the first CPU).
-
-affected_cpus :			List of Online CPUs that require software
-				coordination of frequency.
-
-cpuinfo_cur_freq :		Current frequency of the CPU as obtained from
-				the hardware, in KHz. This is the frequency
-				the CPU actually runs at.
-
-cpuinfo_min_freq :		this file shows the minimum operating
-				frequency the processor can run at(in kHz) 
-
-cpuinfo_max_freq :		this file shows the maximum operating
-				frequency the processor can run at(in kHz) 
-
-cpuinfo_transition_latency	The time it takes on this CPU to
-				switch between two frequencies in nano
-				seconds. If unknown or known to be
-				that high that the driver does not
-				work with the ondemand governor, -1
-				(CPUFREQ_ETERNAL) will be returned.
-				Using this information can be useful
-				to choose an appropriate polling
-				frequency for a kernel governor or
-				userspace daemon. Make sure to not
-				switch the frequency too often
-				resulting in performance loss.
-
-related_cpus :			List of Online + Offline CPUs that need software
-				coordination of frequency.
-
-scaling_available_frequencies : List of available frequencies, in KHz.
-
-scaling_available_governors :	this file shows the CPUfreq governors
-				available in this kernel. You can see the
-				currently activated governor in
-
-scaling_cur_freq :		Current frequency of the CPU as determined by
-				the governor and cpufreq core, in KHz. This is
-				the frequency the kernel thinks the CPU runs
-				at.
-
-scaling_driver :		this file shows what cpufreq driver is
-				used to set the frequency on this CPU
-
-scaling_governor,		and by "echoing" the name of another
-				governor you can change it. Please note
-				that some governors won't load - they only
-				work on some specific architectures or
-				processors.
-
-scaling_min_freq and
-scaling_max_freq		show the current "policy limits" (in
-				kHz). By echoing new values into these
-				files, you can change these limits.
-				NOTE: when setting a policy you need to
-				first set scaling_max_freq, then
-				scaling_min_freq.
-
-scaling_setspeed		This can be read to get the currently programmed
-				value by the governor. This can be written to
-				change the current frequency for a group of
-				CPUs, represented by a policy. This is supported
-				currently only by the userspace governor.
-
-bios_limit :			If the BIOS tells the OS to limit a CPU to
-				lower frequencies, the user can read out the
-				maximum available frequency from this file.
-				This typically can happen through (often not
-				intended) BIOS settings, restrictions
-				triggered through a service processor or other
-				BIOS/HW based implementations.
-				This does not cover thermal ACPI limitations
-				which can be detected through the generic
-				thermal driver.
-
-If you have selected the "userspace" governor which allows you to
-set the CPU operating frequency to a specific value, you can read out
-the current frequency in
-
-scaling_setspeed.		By "echoing" a new frequency into this
-				you can change the speed of the CPU,
-				but only within the limits of
-				scaling_min_freq and scaling_max_freq.
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f722f227a73b..127c9d8c2174 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -100,7 +100,7 @@ not defined by include/asm-XXX/topology.h:
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().
-For architectures that don't support drawes (CONFIG_SCHED_DRAWER) there are
+For architectures that don't support drawers (CONFIG_SCHED_DRAWER) there are
 no default definitions for topology_drawer_id() and topology_drawer_cpumask().
 
 Additionally, CPU topology information is provided under
diff --git a/Documentation/crypto/api-samples.rst b/Documentation/crypto/api-samples.rst
index 0a10819f6107..d021fd96a76d 100644
--- a/Documentation/crypto/api-samples.rst
+++ b/Documentation/crypto/api-samples.rst
@@ -155,9 +155,9 @@ Code Example For Use of Operational State Memory With SHASH
         char ctx[];
     };
 
-    static struct sdescinit_sdesc(struct crypto_shash *alg)
+    static struct sdesc init_sdesc(struct crypto_shash *alg)
     {
-        struct sdescsdesc;
+        struct sdesc sdesc;
         int size;
 
         size = sizeof(struct shash_desc) + crypto_shash_descsize(alg);
@@ -172,7 +172,7 @@ Code Example For Use of Operational State Memory With SHASH
     static int calc_hash(struct crypto_shashalg,
                  const unsigned chardata, unsigned int datalen,
                  unsigned chardigest) {
-        struct sdescsdesc;
+        struct sdesc sdesc;
         int ret;
 
         sdesc = init_sdesc(alg);
diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt
index 03703afc4d30..9ff026d22b75 100644
--- a/Documentation/debugging-via-ohci1394.txt
+++ b/Documentation/debugging-via-ohci1394.txt
@@ -100,8 +100,8 @@ Step-by-step instructions for using firescope with early OHCI initialization:
    CardBus and even some Express cards which are fully compliant to OHCI-1394
    specification are available. If it requires no driver for Windows operating
    systems, it most likely is. Only specialized shops have cards which are not
-   compliant, they are based on TI PCILynx chips and require drivers for Win-
-   dows operating systems.
+   compliant, they are based on TI PCILynx chips and require drivers for Windows
+   operating systems.
 
    The mentioned kernel log message contains the string "physUB" if the
    controller implements a writable Physical Upper Bound register.  This is
diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst
index 2c41b713841f..44886c91e112 100644
--- a/Documentation/dev-tools/kcov.rst
+++ b/Documentation/dev-tools/kcov.rst
@@ -10,7 +10,7 @@ Note that kcov does not aim to collect as much coverage as possible. It aims
 to collect more or less stable coverage that is function of syscall inputs.
 To achieve this goal it does not collect coverage in soft/hard interrupts
 and instrumentation of some inherently non-deterministic parts of kernel is
-disbled (e.g. scheduler, locking).
+disabled (e.g. scheduler, locking).
 
 Usage
 -----
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index f228604ddbcd..cdfd0feb294e 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -290,7 +290,7 @@ message, which takes an arbitrary number of cblock ranges.  Each cblock
 range's end value is "one past the end", meaning 5-10 expresses a range
 of values from 5 to 9.  Each cblock must be expressed as a decimal
 value, in the future a variant message that takes cblock ranges
-expressed in hexidecimal may be needed to better support efficient
+expressed in hexadecimal may be needed to better support efficient
 invalidation of larger caches.  The cache must be in passthrough mode
 when invalidate_cblocks is used.
 
diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
index 30c546900b60..07dbb358182c 100644
--- a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
@@ -45,7 +45,7 @@ The following clocks are available:
    - 1 15	SATA
    - 1 16	SATA USB
    - 1 17	Main
-   - 1 18	SD/MMC
+   - 1 18	SD/MMC/GOP
    - 1 21	Slow IO (SPI, NOR, BootROM, I2C, UART)
    - 1 22	USB3H0
    - 1 23	USB3H1
@@ -65,7 +65,7 @@ Required properties:
 	"cpm-audio", "cpm-communit", "cpm-nand", "cpm-ppv2", "cpm-sdio",
 	"cpm-mg-domain", "cpm-mg-core", "cpm-xor1", "cpm-xor0", "cpm-gop-dp", "none",
 	"cpm-pcie_x10", "cpm-pcie_x11", "cpm-pcie_x4", "cpm-pcie-xor", "cpm-sata",
-	"cpm-sata-usb", "cpm-main", "cpm-sd-mmc", "none", "none", "cpm-slow-io",
+	"cpm-sata-usb", "cpm-main", "cpm-sd-mmc-gop", "none", "none", "cpm-slow-io",
 	"cpm-usb3h0", "cpm-usb3h1", "cpm-usb3dev", "cpm-eip150", "cpm-eip197";
 
 Example:
@@ -78,6 +78,6 @@ Example:
 		gate-clock-output-names = "cpm-audio", "cpm-communit", "cpm-nand", "cpm-ppv2", "cpm-sdio",
 			"cpm-mg-domain", "cpm-mg-core", "cpm-xor1", "cpm-xor0", "cpm-gop-dp", "none",
 			"cpm-pcie_x10", "cpm-pcie_x11", "cpm-pcie_x4", "cpm-pcie-xor", "cpm-sata",
-			"cpm-sata-usb", "cpm-main", "cpm-sd-mmc", "none", "none", "cpm-slow-io",
+			"cpm-sata-usb", "cpm-main", "cpm-sd-mmc-gop", "none", "none", "cpm-slow-io",
 			"cpm-usb3h0", "cpm-usb3h1", "cpm-usb3dev", "cpm-eip150", "cpm-eip197";
 	};
diff --git a/Documentation/devicetree/bindings/ata/ahci-dm816.txt b/Documentation/devicetree/bindings/ata/ahci-dm816.txt
new file mode 100644
index 000000000000..f8c535f3541f
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/ahci-dm816.txt
@@ -0,0 +1,21 @@
+Device tree binding for the TI DM816 AHCI SATA Controller
+---------------------------------------------------------
+
+Required properties:
+  - compatible: must be "ti,dm816-ahci"
+  - reg: physical base address and size of the register region used by
+         the controller (as defined by the AHCI 1.1 standard)
+  - interrupts: interrupt specifier (refer to the interrupt binding)
+  - clocks: list of phandle and clock specifier pairs (or only
+            phandles for clock providers with '0' defined for
+            #clock-cells); two clocks must be specified: the functional
+            clock and an external reference clock
+
+Example:
+
+	sata: sata@4a140000 {
+		compatible = "ti,dm816-ahci";
+		reg = <0x4a140000 0x10000>;
+		interrupts = <16>;
+		clocks = <&sysclk5_ck>, <&sata_refclk>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/armada3700-xtal-clock.txt b/Documentation/devicetree/bindings/clock/armada3700-xtal-clock.txt
index a88f1f05fbd6..4c0807f28cfa 100644
--- a/Documentation/devicetree/bindings/clock/armada3700-xtal-clock.txt
+++ b/Documentation/devicetree/bindings/clock/armada3700-xtal-clock.txt
@@ -5,6 +5,7 @@ reading the gpio latch register.
 
 This node must be a subnode of the node exposing the register address
 of the GPIO block where the gpio latch is located.
+See Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt
 
 Required properties:
 - compatible : shall be one of the following:
@@ -16,9 +17,9 @@ Optional properties:
 	output names ("xtal")
 
 Example:
-gpio1: gpio@13800 {
-	compatible = "marvell,armada-3700-gpio", "syscon", "simple-mfd";
-	reg = <0x13800 0x1000>;
+pinctrl_nb: pinctrl-nb@13800 {
+	compatible = "armada3710-nb-pinctrl", "syscon", "simple-mfd";
+	reg = <0x13800 0x100>, <0x13C00 0x20>;
 
 	xtalclk: xtal-clk {
 		compatible = "marvell,armada-3700-xtal-clock";
diff --git a/Documentation/devicetree/bindings/crypto/st,stm32-crc.txt b/Documentation/devicetree/bindings/crypto/st,stm32-crc.txt
new file mode 100644
index 000000000000..3ba92a5e9b36
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/st,stm32-crc.txt
@@ -0,0 +1,16 @@
+* STMicroelectronics STM32 CRC
+
+Required properties:
+- compatible: Should be "st,stm32f7-crc".
+- reg: The address and length of the peripheral registers space
+- clocks: The input clock of the CRC instance
+
+Optional properties: none
+
+Example:
+
+crc: crc@40023000 {
+	compatible = "st,stm32f7-crc";
+	reg = <0x40023000 0x400>;
+	clocks = <&rcc 0 12>;
+};
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt b/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
index a78265993665..ca5204b3bc21 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
@@ -4,7 +4,6 @@ Required properties:
   - compatible: value should be one of the following
 		"samsung,exynos3250-mipi-dsi" /* for Exynos3250/3472 SoCs */
 		"samsung,exynos4210-mipi-dsi" /* for Exynos4 SoCs */
-		"samsung,exynos4415-mipi-dsi" /* for Exynos4415 SoC */
 		"samsung,exynos5410-mipi-dsi" /* for Exynos5410/5420/5440 SoCs */
 		"samsung,exynos5422-mipi-dsi" /* for Exynos5422/5800 SoCs */
 		"samsung,exynos5433-mipi-dsi" /* for Exynos5433 SoCs */
diff --git a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
index 18645e0228b0..5837402c3ade 100644
--- a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
+++ b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
@@ -11,7 +11,6 @@ Required properties:
 		"samsung,s5pv210-fimd"; /* for S5PV210 SoC */
 		"samsung,exynos3250-fimd"; /* for Exynos3250/3472 SoCs */
 		"samsung,exynos4210-fimd"; /* for Exynos4 SoCs */
-		"samsung,exynos4415-fimd"; /* for Exynos4415 SoC */
 		"samsung,exynos5250-fimd"; /* for Exynos5250 SoCs */
 		"samsung,exynos5420-fimd"; /* for Exynos5420/5422/5800 SoCs */
 
diff --git a/Documentation/devicetree/bindings/hwmon/ads7828.txt b/Documentation/devicetree/bindings/hwmon/ads7828.txt
new file mode 100644
index 000000000000..fe0cc4ad7ea9
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/ads7828.txt
@@ -0,0 +1,25 @@
+ads7828 properties
+
+Required properties:
+- compatible: Should be one of
+	       ti,ads7828
+	       ti,ads7830
+- reg: I2C address
+
+Optional properties:
+
+- ti,differential-input
+  Set to use the device in differential mode.
+- vref-supply
+  The external reference on the device is set to this regulators output. If it
+  does not exists the internal reference will be used and output by the ads78xx
+  on the "external vref" pin.
+
+  Example ADS7828 node:
+
+  ads7828: ads@48 {
+	   comatible = "ti,ads7828";
+	   reg = <0x48>;
+	   vref-supply = <&vref>;
+	   ti,differential-input;
+  };
diff --git a/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt b/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt
new file mode 100644
index 000000000000..cf4460564adb
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt
@@ -0,0 +1,68 @@
+ASPEED AST2400/AST2500 PWM and Fan Tacho controller device driver
+
+The ASPEED PWM controller can support upto 8 PWM outputs. The ASPEED Fan Tacho
+controller can support upto 16 Fan tachometer inputs.
+
+There can be upto 8 fans supported. Each fan can have one PWM output and
+one/two Fan tach inputs.
+
+Required properties for pwm-tacho node:
+- #address-cells : should be 1.
+
+- #size-cells : should be 1.
+
+- reg : address and length of the register set for the device.
+
+- pinctrl-names : a pinctrl state named "default" must be defined.
+
+- pinctrl-0 : phandle referencing pin configuration of the PWM ports.
+
+- compatible : should be "aspeed,ast2400-pwm-tacho" for AST2400 and
+	       "aspeed,ast2500-pwm-tacho" for AST2500.
+
+- clocks : a fixed clock providing input clock frequency(PWM
+	   and Fan Tach clock)
+
+fan subnode format:
+===================
+Under fan subnode there can upto 8 child nodes, with each child node
+representing a fan. If there are 8 fans each fan can have one PWM port and
+one/two Fan tach inputs.
+
+Required properties for each child node:
+- reg : should specify PWM source port.
+	integer value in the range 0 to 7 with 0 indicating PWM port A and
+	7 indicating PWM port H.
+
+- aspeed,fan-tach-ch : should specify the Fan tach input channel.
+                integer value in the range 0 through 15, with 0 indicating
+		Fan tach channel 0 and 15 indicating Fan tach channel 15.
+		Atleast one Fan tach input channel is required.
+
+Examples:
+
+pwm_tacho_fixed_clk: fixedclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <24000000>;
+};
+
+pwm_tacho: pwmtachocontroller@1e786000 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	reg = <0x1E786000 0x1000>;
+	compatible = "aspeed,ast2500-pwm-tacho";
+	clocks = <&pwm_tacho_fixed_clk>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm0_default &pinctrl_pwm1_default>;
+
+	fan@0 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x00>;
+	};
+
+	fan@1 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x01 0x02>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/hwmon/lm87.txt b/Documentation/devicetree/bindings/hwmon/lm87.txt
new file mode 100644
index 000000000000..e1b79903f204
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/lm87.txt
@@ -0,0 +1,30 @@
+*LM87 hwmon sensor.
+
+Required properties:
+- compatible: Should be
+	"ti,lm87"
+
+- reg: I2C address
+
+optional properties:
+- has-temp3: This configures pins 18 and 19 to be used as a second
+             remote temperature sensing channel. By default the pins
+             are configured as voltage input pins in0 and in5.
+
+- has-in6: When set, pin 5 is configured to be used as voltage input
+           in6. Otherwise the pin is set as FAN1 input.
+
+- has-in7: When set, pin 6 is configured to be used as voltage input
+           in7. Otherwise the pin is set as FAN2 input.
+
+- vcc-supply: a Phandle for the regulator supplying power, can be
+              cofigured to measure 5.0V power supply. Default is 3.3V.
+
+Example:
+
+lm87@2e {
+	compatible = "ti,lm87";
+	reg = <0x2e>;
+	has-temp3;
+	vcc-supply = <&reg_5v0>;
+};
diff --git a/Documentation/devicetree/bindings/input/hid-over-i2c.txt b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
index 488edcb264c4..28e8bd8b7d64 100644
--- a/Documentation/devicetree/bindings/input/hid-over-i2c.txt
+++ b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
@@ -17,6 +17,22 @@ Required properties:
 - interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt line
 
+Additional optional properties:
+
+Some devices may support additional optional properties to help with, e.g.,
+power sequencing. The following properties can be supported by one or more
+device-specific compatible properties, which should be used in addition to the
+"hid-over-i2c" string.
+
+- compatible:
+  * "wacom,w9013" (Wacom W9013 digitizer). Supports:
+    - vdd-supply
+    - post-power-on-delay-ms
+
+- vdd-supply: phandle of the regulator that provides the supply voltage.
+- post-power-on-delay-ms: time required by the device after enabling its regulators
+  before it is ready for communication. Must be used with 'vdd-supply'.
+
 Example:
 
 	i2c-hid-dev@2c {
diff --git a/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/faraday,ftintc010.txt
index 97c1167fa533..24428d47f487 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/faraday,ftintc010.txt
@@ -1,9 +1,12 @@
-* Cortina Systems Gemini interrupt controller
+* Faraday Technologt FTINTC010 interrupt controller
 
-This interrupt controller is found on the Gemini SoCs.
+This interrupt controller is a stock IP block from Faraday Technology found
+in the Gemini SoCs and other designs.
 
 Required properties:
-- compatible: must be "cortina,gemini-interrupt-controller"
+- compatible: must be one of
+  "faraday,ftintc010"
+  "cortina,gemini-interrupt-controller" (deprecated)
 - reg: The register bank for the interrupt controller.
 - interrupt-controller: Identifies the node as an interrupt controller
 - #interrupt-cells: The number of cells to define the interrupts.
@@ -15,7 +18,7 @@ Required properties:
 Example:
 
 interrupt-controller@48000000 {
-	compatible = "cortina,gemini-interrupt-controller";
+	compatible = "faraday,ftintc010"
 	reg = <0x48000000 0x1000>;
 	interrupt-controller;
 	#interrupt-cells = <2>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
new file mode 100644
index 000000000000..a7efdbc3de5b
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
@@ -0,0 +1,35 @@
+* Mediatek 27xx cirq
+
+In Mediatek SOCs, the CIRQ is a low power interrupt controller designed to
+work outside MCUSYS which comprises with Cortex-Ax cores,CCI and GIC.
+The external interrupts (outside MCUSYS) will feed through CIRQ and connect
+to GIC in MCUSYS. When CIRQ is enabled, it will record the edge-sensitive
+interrupts and generate a pulse signal to parent interrupt controller when
+flush command is executed. With CIRQ, MCUSYS can be completely turned off
+to improve the system power consumption without losing interrupts.
+
+Required properties:
+- compatible: should be one of
+  - "mediatek,mt2701-cirq" for mt2701 CIRQ
+  - "mediatek,mt8135-cirq" for mt8135 CIRQ
+  - "mediatek,mt8173-cirq" for mt8173 CIRQ
+  and "mediatek,cirq" as a fallback.
+- interrupt-controller : Identifies the node as an interrupt controller.
+- #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt.
+- interrupt-parent: phandle of irq parent for cirq. The parent must
+  use the same interrupt-cells format as GIC.
+- reg: Physical base address of the cirq registers and length of memory
+  mapped region.
+- mediatek,ext-irq-range: Identifies external irq number range in different
+  SOCs.
+
+Example:
+	cirq: interrupt-controller@10204000 {
+		compatible = "mediatek,mt2701-cirq",
+			     "mediatek,mtk-cirq";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		interrupt-parent = <&sysirq>;
+		reg = <0 0x10204000 0 0x400>;
+		mediatek,ext-irq-start = <32 200>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
index 9d1d72c65489..a89c03bb1a81 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
@@ -21,13 +21,16 @@ Required properties:
 - interrupt-parent: phandle of irq parent for sysirq. The parent must
   use the same interrupt-cells format as GIC.
 - reg: Physical base address of the intpol registers and length of memory
-  mapped region.
+  mapped region. Could be multiple bases here. Ex: mt6797 needs 2 reg, others
+  need 1.
 
 Example:
-	sysirq: interrupt-controller@10200100 {
-		compatible = "mediatek,mt6589-sysirq", "mediatek,mt6577-sysirq";
+	sysirq: intpol-controller@10200620 {
+		compatible = "mediatek,mt6797-sysirq",
+			     "mediatek,mt6577-sysirq";
 		interrupt-controller;
 		#interrupt-cells = <3>;
 		interrupt-parent = <&gic>;
-		reg = <0 0x10200100 0 0x1c>;
+		reg = <0 0x10220620 0 0x20>,
+		      <0 0x10220690 0 0x10>;
 	};
diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt
index 6f28969af9dc..028268fd99ee 100644
--- a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt
+++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt
@@ -6,7 +6,9 @@ perform in-band IPMI communication with their host.
 
 Required properties:
 
-- compatible : should be "aspeed,ast2400-ibt-bmc"
+- compatible : should be one of
+	"aspeed,ast2400-ibt-bmc"
+	"aspeed,ast2500-ibt-bmc"
 - reg: physical address and size of the registers
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/leds/leds-cpcap.txt b/Documentation/devicetree/bindings/leds/leds-cpcap.txt
new file mode 100644
index 000000000000..ebf7cdc7f70c
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-cpcap.txt
@@ -0,0 +1,29 @@
+Motorola CPCAP PMIC LEDs
+------------------------
+
+This module is part of the CPCAP. For more details about the whole
+chip see Documentation/devicetree/bindings/mfd/motorola-cpcap.txt.
+
+Requires node properties:
+- compatible: should be one of
+   * "motorola,cpcap-led-mdl"		(Main Display Lighting)
+   * "motorola,cpcap-led-kl"		(Keyboard Lighting)
+   * "motorola,cpcap-led-adl"		(Aux Display Lighting)
+   * "motorola,cpcap-led-red"		(Red Triode)
+   * "motorola,cpcap-led-green"		(Green Triode)
+   * "motorola,cpcap-led-blue"		(Blue Triode)
+   * "motorola,cpcap-led-cf"		(Camera Flash)
+   * "motorola,cpcap-led-bt"		(Bluetooth)
+   * "motorola,cpcap-led-cp"		(Camera Privacy LED)
+- label: see Documentation/devicetree/bindings/leds/common.txt
+- vdd-supply: A phandle to the regulator powering the LED
+
+Example:
+
+&cpcap {
+	cpcap_led_red: red-led {
+		compatible = "motorola,cpcap-led-red";
+		label = "cpcap:red";
+		vdd-supply = <&sw5>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/leds/leds-mt6323.txt b/Documentation/devicetree/bindings/leds/leds-mt6323.txt
new file mode 100644
index 000000000000..45bf9f7d85f3
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-mt6323.txt
@@ -0,0 +1,60 @@
+Device Tree Bindings for LED support on MT6323 PMIC
+
+MT6323 LED controller is subfunction provided by MT6323 PMIC, so the LED
+controllers are defined as the subnode of the function node provided by MT6323
+PMIC controller that is being defined as one kind of Muti-Function Device (MFD)
+using shared bus called PMIC wrapper for each subfunction to access remote
+MT6323 PMIC hardware.
+
+For MT6323 MFD bindings see:
+Documentation/devicetree/bindings/mfd/mt6397.txt
+For MediaTek PMIC wrapper bindings see:
+Documentation/devicetree/bindings/soc/mediatek/pwrap.txt
+
+Required properties:
+- compatible : Must be "mediatek,mt6323-led"
+- address-cells : Must be 1
+- size-cells : Must be 0
+
+Each led is represented as a child node of the mediatek,mt6323-led that
+describes the initial behavior for each LED physically and currently only four
+LED child nodes can be supported.
+
+Required properties for the LED child node:
+- reg : LED channel number (0..3)
+
+Optional properties for the LED child node:
+- label : See Documentation/devicetree/bindings/leds/common.txt
+- linux,default-trigger : See Documentation/devicetree/bindings/leds/common.txt
+- default-state: See Documentation/devicetree/bindings/leds/common.txt
+
+Example:
+
+	mt6323: pmic {
+		compatible = "mediatek,mt6323";
+
+		...
+
+		mt6323led: leds {
+			compatible = "mediatek,mt6323-led";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			led@0 {
+				reg = <0>;
+				label = "LED0";
+				linux,default-trigger = "timer";
+				default-state = "on";
+			};
+			led@1 {
+				reg = <1>;
+				label = "LED1";
+				default-state = "off";
+			};
+			led@2 {
+				reg = <2>;
+				label = "LED2";
+				default-state = "on";
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/leds/leds-pca9532.txt b/Documentation/devicetree/bindings/leds/leds-pca9532.txt
index 198f3ba0e01f..f769c52e3643 100644
--- a/Documentation/devicetree/bindings/leds/leds-pca9532.txt
+++ b/Documentation/devicetree/bindings/leds/leds-pca9532.txt
@@ -17,6 +17,8 @@ Optional sub-node properties:
 	- label: see Documentation/devicetree/bindings/leds/common.txt
 	- type: Output configuration, see dt-bindings/leds/leds-pca9532.h (default NONE)
 	- linux,default-trigger: see Documentation/devicetree/bindings/leds/common.txt
+	- default-state: see Documentation/devicetree/bindings/leds/common.txt
+	  This property is only valid for sub-nodes of type <PCA9532_TYPE_LED>.
 
 Example:
   #include <dt-bindings/leds/leds-pca9532.h>
@@ -33,6 +35,14 @@ Example:
       label = "pca:green:power";
       type = <PCA9532_TYPE_LED>;
     };
+    kernel-booting {
+      type = <PCA9532_TYPE_LED>;
+      default-state = "on";
+    };
+    sys-stat {
+      type = <PCA9532_TYPE_LED>;
+      default-state = "keep"; // don't touch, was set by U-Boot
+    };
   };
 
 For more product information please see the link below:
diff --git a/Documentation/devicetree/bindings/mailbox/brcm,iproc-flexrm-mbox.txt b/Documentation/devicetree/bindings/mailbox/brcm,iproc-flexrm-mbox.txt
new file mode 100644
index 000000000000..752ae6b00d26
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/brcm,iproc-flexrm-mbox.txt
@@ -0,0 +1,59 @@
+Broadcom FlexRM Ring Manager
+============================
+The Broadcom FlexRM ring manager provides a set of rings which can be
+used to submit work to offload engines. An SoC may have multiple FlexRM
+hardware blocks. There is one device tree entry per FlexRM block. The
+FlexRM driver will create a mailbox-controller instance for given FlexRM
+hardware block where each mailbox channel is a separate FlexRM ring.
+
+Required properties:
+--------------------
+- compatible:	Should be "brcm,iproc-flexrm-mbox"
+- reg:		Specifies base physical address and size of the FlexRM
+		ring registers
+- msi-parent:	Phandles (and potential Device IDs) to MSI controllers
+		The FlexRM engine will send MSIs (instead of wired
+		interrupts) to CPU. There is one MSI for each FlexRM ring.
+		Refer devicetree/bindings/interrupt-controller/msi.txt
+- #mbox-cells:	Specifies the number of cells needed to encode a mailbox
+		channel. This should be 3.
+
+		The 1st cell is the mailbox channel number.
+
+		The 2nd cell contains MSI completion threshold. This is the
+		number of completion messages for which FlexRM will inject
+		one MSI interrupt to CPU.
+
+		The 3nd cell contains MSI timer value representing time for
+		which FlexRM will wait to accumulate N completion messages
+		where N is the value specified by 2nd cell above. If FlexRM
+		does not get required number of completion messages in time
+		specified by this cell then it will inject one MSI interrupt
+		to CPU provided atleast one completion message is available.
+
+Optional properties:
+--------------------
+- dma-coherent:	Present if DMA operations made by the FlexRM engine (such
+		as DMA descriptor access, access to buffers pointed by DMA
+		descriptors and read/write pointer updates to DDR) are
+		cache coherent with the CPU.
+
+Example:
+--------
+crypto_mbox: mbox@67000000 {
+	compatible = "brcm,iproc-flexrm-mbox";
+	reg = <0x67000000 0x200000>;
+	msi-parent = <&gic_its 0x7f00>;
+	#mbox-cells = <3>;
+};
+
+crypto@672c0000 {
+	compatible = "brcm,spu2-v2-crypto";
+	reg = <0x672c0000 0x1000>;
+	mboxes = <&crypto_mbox 0 0x1 0xffff>,
+		 <&crypto_mbox 1 0x1 0xffff>,
+		 <&crypto_mbox 16 0x1 0xffff>,
+		 <&crypto_mbox 17 0x1 0xffff>,
+		 <&crypto_mbox 30 0x1 0xffff>,
+		 <&crypto_mbox 31 0x1 0xffff>;
+};
diff --git a/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt b/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
index 411ccf421584..0f3ee81d92c2 100644
--- a/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
@@ -1,9 +1,11 @@
 The PDC driver manages data transfer to and from various offload engines
 on some Broadcom SoCs. An SoC may have multiple PDC hardware blocks. There is
-one device tree entry per block.
+one device tree entry per block.  On some chips, the PDC functionality is
+handled by the FA2 (Northstar Plus).
 
 Required properties:
-- compatible : Should be "brcm,iproc-pdc-mbox".
+- compatible : Should be "brcm,iproc-pdc-mbox" or "brcm,iproc-fa2-mbox" for
+  FA2/Northstar Plus.
 - reg: Should contain PDC registers location and length.
 - interrupts: Should contain the IRQ line for the PDC.
 - #mbox-cells: 1
diff --git a/Documentation/devicetree/bindings/mmc/brcm,bcm2835-sdhost.txt b/Documentation/devicetree/bindings/mmc/brcm,bcm2835-sdhost.txt
new file mode 100644
index 000000000000..d876580ae3b8
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/brcm,bcm2835-sdhost.txt
@@ -0,0 +1,23 @@
+Broadcom BCM2835 SDHOST controller
+
+This file documents differences between the core properties described
+by mmc.txt and the properties that represent the BCM2835 controller.
+
+Required properties:
+- compatible: Should be "brcm,bcm2835-sdhost".
+- clocks: The clock feeding the SDHOST controller.
+
+Optional properties:
+- dmas: DMA channel for read and write.
+          See Documentation/devicetree/bindings/dma/dma.txt for details
+
+Example:
+
+sdhost: mmc@7e202000 {
+	compatible = "brcm,bcm2835-sdhost";
+	reg = <0x7e202000 0x100>;
+	interrupts = <2 24>;
+	clocks = <&clocks BCM2835_CLOCK_VPU>;
+	dmas = <&dma 13>;
+	dma-names = "rx-tx";
+};
diff --git a/Documentation/devicetree/bindings/mmc/cavium-mmc.txt b/Documentation/devicetree/bindings/mmc/cavium-mmc.txt
new file mode 100644
index 000000000000..1433e6201dff
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/cavium-mmc.txt
@@ -0,0 +1,57 @@
+* Cavium Octeon & ThunderX MMC controller
+
+The highspeed MMC host controller on Caviums SoCs provides an interface
+for MMC and SD types of memory cards.
+
+Supported maximum speeds are the ones of the eMMC standard 4.41 as well
+as the speed of SD standard 4.0. Only 3.3 Volt is supported.
+
+Required properties:
+ - compatible : should be one of:
+   cavium,octeon-6130-mmc
+   cavium,octeon-7890-mmc
+   cavium,thunder-8190-mmc
+   cavium,thunder-8390-mmc
+   mmc-slot
+ - reg : mmc controller base registers
+ - clocks : phandle
+
+Optional properties:
+ - for cd, bus-width and additional generic mmc parameters
+   please refer to mmc.txt within this directory
+ - cavium,cmd-clk-skew : number of coprocessor clocks before sampling command
+ - cavium,dat-clk-skew : number of coprocessor clocks before sampling data
+
+Deprecated properties:
+- spi-max-frequency : use max-frequency instead
+- cavium,bus-max-width : use bus-width instead
+- power-gpios : use vmmc-supply instead
+- cavium,octeon-6130-mmc-slot : use mmc-slot instead
+
+Examples:
+	mmc_1_4: mmc@1,4 {
+		compatible = "cavium,thunder-8390-mmc";
+		reg = <0x0c00 0 0 0 0>;	/* DEVFN = 0x0c (1:4) */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clocks = <&sclk>;
+
+		mmc-slot@0 {
+			compatible = "mmc-slot";
+			reg = <0>;
+			vmmc-supply = <&mmc_supply_3v3>;
+			max-frequency = <42000000>;
+			bus-width = <4>;
+			cap-sd-highspeed;
+		};
+
+		mmc-slot@1 {
+			compatible = "mmc-slot";
+			reg = <1>;
+			vmmc-supply = <&mmc_supply_3v3>;
+			max-frequency = <42000000>;
+			bus-width = <8>;
+			cap-mmc-highspeed;
+			non-removable;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
new file mode 100644
index 000000000000..b878a1e305af
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
@@ -0,0 +1,170 @@
+Marvell Xenon SDHCI Controller device tree bindings
+This file documents differences between the core mmc properties
+described by mmc.txt and the properties used by the Xenon implementation.
+
+Multiple SDHCs might be put into a single Xenon IP, to save size and cost.
+Each SDHC is independent and owns independent resources, such as register sets,
+clock and PHY.
+Each SDHC should have an independent device tree node.
+
+Required Properties:
+- compatible: should be one of the following
+  - "marvell,armada-3700-sdhci": For controllers on Armada-3700 SoC.
+  Must provide a second register area and marvell,pad-type.
+  - "marvell,armada-ap806-sdhci": For controllers on Armada AP806.
+  - "marvell,armada-cp110-sdhci": For controllers on Armada CP110.
+
+- clocks:
+  Array of clocks required for SDHC.
+  Require at least input clock for Xenon IP core.
+
+- clock-names:
+  Array of names corresponding to clocks property.
+  The input clock for Xenon IP core should be named as "core".
+
+- reg:
+  * For "marvell,armada-3700-sdhci", two register areas.
+    The first one for Xenon IP register. The second one for the Armada 3700 SoC
+    PHY PAD Voltage Control register.
+    Please follow the examples with compatible "marvell,armada-3700-sdhci"
+    in below.
+    Please also check property marvell,pad-type in below.
+
+  * For other compatible strings, one register area for Xenon IP.
+
+Optional Properties:
+- marvell,xenon-sdhc-id:
+  Indicate the corresponding bit index of current SDHC in
+  SDHC System Operation Control Register Bit[7:0].
+  Set/clear the corresponding bit to enable/disable current SDHC.
+  If Xenon IP contains only one SDHC, this property is optional.
+
+- marvell,xenon-phy-type:
+  Xenon support multiple types of PHYs.
+  To select eMMC 5.1 PHY, set:
+  marvell,xenon-phy-type = "emmc 5.1 phy"
+  eMMC 5.1 PHY is the default choice if this property is not provided.
+  To select eMMC 5.0 PHY, set:
+  marvell,xenon-phy-type = "emmc 5.0 phy"
+
+  All those types of PHYs can support eMMC, SD and SDIO.
+  Please note that this property only presents the type of PHY.
+  It doesn't stand for the entire SDHC type or property.
+  For example, "emmc 5.1 phy" doesn't mean that this Xenon SDHC only
+  supports eMMC 5.1.
+
+- marvell,xenon-phy-znr:
+  Set PHY ZNR value.
+  Only available for eMMC PHY.
+  Valid range = [0:0x1F].
+  ZNR is set as 0xF by default if this property is not provided.
+
+- marvell,xenon-phy-zpr:
+  Set PHY ZPR value.
+  Only available for eMMC PHY.
+  Valid range = [0:0x1F].
+  ZPR is set as 0xF by default if this property is not provided.
+
+- marvell,xenon-phy-nr-success-tun:
+  Set the number of required consecutive successful sampling points
+  used to identify a valid sampling window, in tuning process.
+  Valid range = [1:7].
+  Set as 0x4 by default if this property is not provided.
+
+- marvell,xenon-phy-tun-step-divider:
+  Set the divider for calculating TUN_STEP.
+  Set as 64 by default if this property is not provided.
+
+- marvell,xenon-phy-slow-mode:
+  If this property is selected, transfers will bypass PHY.
+  Only available when bus frequency lower than 55MHz in SDR mode.
+  Disabled by default. Please only try this property if timing issues
+  always occur with PHY enabled in eMMC HS SDR, SD SDR12, SD SDR25,
+  SD Default Speed and HS mode and eMMC legacy speed mode.
+
+- marvell,xenon-tun-count:
+  Xenon SDHC SoC usually doesn't provide re-tuning counter in
+  Capabilities Register 3 Bit[11:8].
+  This property provides the re-tuning counter.
+  If this property is not set, default re-tuning counter will
+  be set as 0x9 in driver.
+
+- marvell,pad-type:
+  Type of Armada 3700 SoC PHY PAD Voltage Controller register.
+  Only valid when "marvell,armada-3700-sdhci" is selected.
+  Two types: "sd" and "fixed-1-8v".
+  If "sd" is selected, SoC PHY PAD is set as 3.3V at the beginning and is
+  switched to 1.8V when later in higher speed mode.
+  If "fixed-1-8v" is selected, SoC PHY PAD is fixed 1.8V, such as for eMMC.
+  Please follow the examples with compatible "marvell,armada-3700-sdhci"
+  in below.
+
+Example:
+- For eMMC:
+
+	sdhci@aa0000 {
+		compatible = "marvell,armada-ap806-sdhci";
+		reg = <0xaa0000 0x1000>;
+		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>
+		clocks = <&emmc_clk>;
+		clock-names = "core";
+		bus-width = <4>;
+		marvell,xenon-phy-slow-mode;
+		marvell,xenon-tun-count = <11>;
+		non-removable;
+		no-sd;
+		no-sdio;
+
+		/* Vmmc and Vqmmc are both fixed */
+	};
+
+- For SD/SDIO:
+
+	sdhci@ab0000 {
+		compatible = "marvell,armada-cp110-sdhci";
+		reg = <0xab0000 0x1000>;
+		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>
+		vqmmc-supply = <&sd_vqmmc_regulator>;
+		vmmc-supply = <&sd_vmmc_regulator>;
+		clocks = <&sdclk>;
+		clock-names = "core";
+		bus-width = <4>;
+		marvell,xenon-tun-count = <9>;
+	};
+
+- For eMMC with compatible "marvell,armada-3700-sdhci":
+
+	sdhci@aa0000 {
+		compatible = "marvell,armada-3700-sdhci";
+		reg = <0xaa0000 0x1000>,
+		      <phy_addr 0x4>;
+		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>
+		clocks = <&emmcclk>;
+		clock-names = "core";
+		bus-width = <8>;
+		mmc-ddr-1_8v;
+		mmc-hs400-1_8v;
+		non-removable;
+		no-sd;
+		no-sdio;
+
+		/* Vmmc and Vqmmc are both fixed */
+
+		marvell,pad-type = "fixed-1-8v";
+	};
+
+- For SD/SDIO with compatible "marvell,armada-3700-sdhci":
+
+	sdhci@ab0000 {
+		compatible = "marvell,armada-3700-sdhci";
+		reg = <0xab0000 0x1000>,
+		      <phy_addr 0x4>;
+		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>
+		vqmmc-supply = <&sd_regulator>;
+		/* Vmmc is fixed */
+		clocks = <&sdclk>;
+		clock-names = "core";
+		bus-width = <4>;
+
+		marvell,pad-type = "sd";
+	};
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
index 0120c7f1109c..4182ea36ca5b 100644
--- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -21,6 +21,15 @@ Optional properties:
 - assigned-clocks: PLL of the source clock
 - assigned-clock-parents: parent of source clock, used for HS400 mode to get 400Mhz source clock
 - hs400-ds-delay: HS400 DS delay setting
+- mediatek,hs200-cmd-int-delay: HS200 command internal delay setting.
+				This field has total 32 stages.
+				The value is an integer from 0 to 31.
+- mediatek,hs400-cmd-int-delay: HS400 command internal delay setting
+				This field has total 32 stages.
+				The value is an integer from 0 to 31.
+- mediatek,hs400-cmd-resp-sel-rising:  HS400 command response sample selection
+				       If present,HS400 command responses are sampled on rising edges.
+				       If not present,HS400 command responses are sampled on falling edges.
 
 Examples:
 mmc0: mmc@11230000 {
@@ -38,4 +47,7 @@ mmc0: mmc@11230000 {
 	assigned-clocks = <&topckgen CLK_TOP_MSDC50_0_SEL>;
 	assigned-clock-parents = <&topckgen CLK_TOP_MSDCPLL_D2>;
 	hs400-ds-delay = <0x14015>;
+	mediatek,hs200-cmd-int-delay = <26>;
+	mediatek,hs400-cmd-int-delay = <14>;
+	mediatek,hs400-cmd-resp-sel-rising;
 };
diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
index 15b8368ee1f2..9bce57862ed6 100644
--- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
@@ -7,11 +7,13 @@ This file documents differences between the core properties described
 by mmc.txt and the properties used by the sdhci-tegra driver.
 
 Required properties:
-- compatible : For Tegra20, must contain "nvidia,tegra20-sdhci".
-  For Tegra30, must contain "nvidia,tegra30-sdhci".  For Tegra114,
-  must contain "nvidia,tegra114-sdhci".  For Tegra124, must contain
-  "nvidia,tegra124-sdhci".  Otherwise, must contain "nvidia,<chip>-sdhci",
-  plus one of the above, where <chip> is tegra132 or tegra210.
+- compatible : should be one of:
+  - "nvidia,tegra20-sdhci": for Tegra20
+  - "nvidia,tegra30-sdhci": for Tegra30
+  - "nvidia,tegra114-sdhci": for Tegra114
+  - "nvidia,tegra124-sdhci": for Tegra124 and Tegra132
+  - "nvidia,tegra210-sdhci": for Tegra210
+  - "nvidia,tegra186-sdhci": for Tegra186
 - clocks : Must contain one entry, for the module clock.
   See ../clocks/clock-bindings.txt for details.
 - resets : Must contain an entry for each entry in reset-names.
diff --git a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
index e4ba92aa035e..c32dc5a9dbe6 100644
--- a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
+++ b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
@@ -8,6 +8,7 @@ Required properties:
 
 - compatible: should be "renesas,mmcif-<soctype>", "renesas,sh-mmcif" as a
   fallback. Examples with <soctype> are:
+	- "renesas,mmcif-r7s72100" for the MMCIF found in r7s72100 SoCs
 	- "renesas,mmcif-r8a73a4" for the MMCIF found in r8a73a4 SoCs
 	- "renesas,mmcif-r8a7740" for the MMCIF found in r8a7740 SoCs
 	- "renesas,mmcif-r8a7778" for the MMCIF found in r8a7778 SoCs
@@ -17,6 +18,13 @@ Required properties:
 	- "renesas,mmcif-r8a7794" for the MMCIF found in r8a7794 SoCs
 	- "renesas,mmcif-sh73a0" for the MMCIF found in sh73a0 SoCs
 
+- interrupts: Some SoCs have only 1 shared interrupt, while others have either
+  2 or 3 individual interrupts (error, int, card detect). Below is the number
+  of interrupts for each SoC:
+    1: r8a73a4, r8a7778, r8a7790, r8a7791, r8a7793, r8a7794
+    2: r8a7740, sh73a0
+    3: r7s72100
+
 - clocks: reference to the functional clock
 
 - dmas: reference to the DMA channels, one per channel name listed in the
diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
index ea9c1c9607f6..520d61dad6dd 100644
--- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
@@ -13,7 +13,7 @@ Required Properties:
 	- "rockchip,rk2928-dw-mshc": for Rockchip RK2928 and following,
 							before RK3288
 	- "rockchip,rk3288-dw-mshc": for Rockchip RK3288
-	- "rockchip,rk1108-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK1108
+	- "rockchip,rv1108-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RV1108
 	- "rockchip,rk3036-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK3036
 	- "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK3368
 	- "rockchip,rk3399-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK3399
diff --git a/Documentation/devicetree/bindings/mmc/samsung,s3cmci.txt b/Documentation/devicetree/bindings/mmc/samsung,s3cmci.txt
new file mode 100644
index 000000000000..5f68feb9f9d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/samsung,s3cmci.txt
@@ -0,0 +1,42 @@
+* Samsung's S3C24XX MMC/SD/SDIO controller device tree bindings
+
+Samsung's S3C24XX MMC/SD/SDIO controller is used as a connectivity interface
+with external MMC, SD and SDIO storage mediums.
+
+This file documents differences between the core mmc properties described by
+mmc.txt and the properties used by the Samsung S3C24XX MMC/SD/SDIO controller
+implementation.
+
+Required SoC Specific Properties:
+- compatible: should be one of the following
+  - "samsung,s3c2410-sdi": for controllers compatible with s3c2410
+  - "samsung,s3c2412-sdi": for controllers compatible with s3c2412
+  - "samsung,s3c2440-sdi": for controllers compatible with s3c2440
+- reg: register location and length
+- interrupts: mmc controller interrupt
+- clocks: Should reference the controller clock
+- clock-names: Should contain "sdi"
+
+Required Board Specific Properties:
+- pinctrl-0: Should specify pin control groups used for this controller.
+- pinctrl-names: Should contain only one value - "default".
+
+Optional Properties:
+- bus-width: number of data lines (see mmc.txt)
+- cd-gpios: gpio for card detection (see mmc.txt)
+- wp-gpios: gpio for write protection (see mmc.txt)
+
+Example:
+
+	mmc0: mmc@5a000000 {
+		compatible = "samsung,s3c2440-sdi";
+		pinctrl-names = "default";
+		pinctrl-0 = <&sdi_pins>;
+		reg = <0x5a000000 0x100000>;
+		interrupts = <0 0 21 3>;
+		clocks = <&clocks PCLK_SDI>;
+		clock-names = "sdi";
+		bus-width = <4>;
+		cd-gpios = <&gpg 8 GPIO_ACTIVE_LOW>;
+		wp-gpios = <&gph 8 GPIO_ACTIVE_LOW>;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt b/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt
index c0f37cb41a9b..fa423c277853 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt
+++ b/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt
@@ -19,6 +19,53 @@ if supported.  See mmc.txt for details.
 - mmc-hs400-1_8v
 - mmc-hs400-1_2v
 
+Some PHY delays can be configured by following properties.
+PHY DLL input delays:
+They are used to delay the data valid window, and align the window
+to sampling clock. The delay starts from 5ns (for delay parameter equal to 0)
+and it is increased by 2.5ns in each step.
+- cdns,phy-input-delay-sd-highspeed:
+  Value of the delay in the input path for SD high-speed timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-legacy:
+  Value of the delay in the input path for legacy timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-sd-uhs-sdr12:
+  Value of the delay in the input path for SD UHS SDR12 timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-sd-uhs-sdr25:
+  Value of the delay in the input path for SD UHS SDR25 timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-sd-uhs-sdr50:
+  Value of the delay in the input path for SD UHS SDR50 timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-sd-uhs-ddr50:
+  Value of the delay in the input path for SD UHS DDR50 timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-mmc-highspeed:
+  Value of the delay in the input path for MMC high-speed timing
+  Valid range = [0:0x1F].
+- cdns,phy-input-delay-mmc-ddr:
+  Value of the delay in the input path for eMMC high-speed DDR timing
+  Valid range = [0:0x1F].
+
+PHY DLL clock delays:
+Each delay property represents the fraction of the clock period.
+The approximate delay value will be
+(<delay property value>/128)*sdmclk_clock_period.
+- cdns,phy-dll-delay-sdclk:
+  Value of the delay introduced on the sdclk output
+  for all modes except HS200, HS400 and HS400_ES.
+  Valid range = [0:0x7F].
+- cdns,phy-dll-delay-sdclk-hsmmc:
+  Value of the delay introduced on the sdclk output
+  for HS200, HS400 and HS400_ES speed modes.
+  Valid range = [0:0x7F].
+- cdns,phy-dll-delay-strobe:
+  Value of the delay introduced on the dat_strobe input
+  used in HS400 / HS400_ES speed modes.
+  Valid range = [0:0x7F].
+
 Example:
 	emmc: sdhci@5a000000 {
 		compatible = "socionext,uniphier-sd4hc", "cdns,sd4hc";
@@ -29,4 +76,5 @@ Example:
 		mmc-ddr-1_8v;
 		mmc-hs200-1_8v;
 		mmc-hs400-1_8v;
+		cdns,phy-dll-delay-sdclk = <0>;
 	};
diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
index 10587bdadbbe..26c77d985faf 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
@@ -2,11 +2,14 @@
 
 Required properties:
 - compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2",
-  "brcm,genet-v3", "brcm,genet-v4".
+  "brcm,genet-v3", "brcm,genet-v4", "brcm,genet-v5".
 - reg: address and length of the register set for the device
-- interrupts: must be two cells, the first cell is the general purpose
-  interrupt line, while the second cell is the interrupt for the ring
-  RX and TX queues operating in ring mode
+- interrupts and/or interrupts-extended: must be two cells, the first cell
+  is the general purpose interrupt line, while the second cell is the
+  interrupt for the ring RX and TX queues operating in ring mode.  An
+  optional third interrupt cell for Wake-on-LAN can be specified.
+  See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+  for information on the property specifics.
 - phy-mode: see ethernet.txt file in the same directory
 - #address-cells: should be 1
 - #size-cells: should be 1
@@ -29,15 +32,15 @@ Optional properties:
 
 Required child nodes:
 
-- mdio bus node: this node should always be present regarless of the PHY
+- mdio bus node: this node should always be present regardless of the PHY
   configuration of the GENET instance
 
 MDIO bus node required properties:
 
 - compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2"
-  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the
-  parent node compatible property (e.g: brcm,genet-v4 pairs with
-  brcm,genet-mdio-v4)
+  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5", the version
+  has to match the parent node compatible property (e.g: brcm,genet-v4 pairs
+  with brcm,genet-mdio-v4)
 - reg: address and length relative to the parent node base register address
 - #address-cells: address cell for MDIO bus addressing, should be 1
 - #size-cells: size of the cells for MDIO bus addressing, should be 0
diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
index ab0bb4247d14..4648948f7c3b 100644
--- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
+++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
@@ -2,8 +2,9 @@
 
 Required properties:
 - compatible: should one from "brcm,genet-mdio-v1", "brcm,genet-mdio-v2",
-  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4" or "brcm,unimac-mdio"
-- reg: address and length of the regsiter set for the device, first one is the
+  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5" or
+  "brcm,unimac-mdio"
+- reg: address and length of the register set for the device, first one is the
   base register, and the second one is optional and for indirect accesses to
   larger than 16-bits MDIO transactions
 - reg-names: name(s) of the register must be "mdio" and optional "mdio_indir_rw"
diff --git a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
new file mode 100644
index 000000000000..23aa94eab207
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
@@ -0,0 +1,24 @@
+* Holt HI-311X stand-alone CAN controller device tree bindings
+
+Required properties:
+ - compatible: Should be one of the following:
+   - "holt,hi3110" for HI-3110
+ - reg: SPI chip select.
+ - clocks: The clock feeding the CAN controller.
+ - interrupt-parent: The parent interrupt controller.
+ - interrupts: Should contain IRQ line for the CAN controller.
+
+Optional properties:
+ - vdd-supply: Regulator that powers the CAN controller.
+ - xceiver-supply: Regulator that powers the CAN transceiver.
+
+Example:
+	can0: can@1 {
+		compatible = "holt,hi3110";
+		reg = <1>;
+		clocks = <&clk32m>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <13 IRQ_TYPE_EDGE_RISING>;
+		vdd-supply = <&reg5v0>;
+		xceiver-supply = <&reg5v0>;
+	};
diff --git a/Documentation/devicetree/bindings/net/can/ti_hecc.txt b/Documentation/devicetree/bindings/net/can/ti_hecc.txt
new file mode 100644
index 000000000000..e0f0a7cfe329
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/ti_hecc.txt
@@ -0,0 +1,32 @@
+Texas Instruments High End CAN Controller (HECC)
+================================================
+
+This file provides information, what the device node
+for the hecc interface contains.
+
+Required properties:
+- compatible: "ti,am3517-hecc"
+- reg: addresses and lengths of the register spaces for 'hecc', 'hecc-ram'
+       and 'mbx'
+- reg-names :"hecc", "hecc-ram", "mbx"
+- interrupts: interrupt mapping for the hecc interrupts sources
+- clocks: clock phandles (see clock bindings for details)
+
+Optional properties:
+- ti,use-hecc1int: if provided configures HECC to produce all interrupts
+		   on HECC1INT interrupt line. By default HECC0INT interrupt
+		   line will be used.
+- xceiver-supply: regulator that powers the CAN transceiver
+
+Example:
+
+For am3517evm board:
+	hecc: can@5c050000 {
+		compatible = "ti,am3517-hecc";
+		reg = <0x5c050000 0x80>,
+		      <0x5c053000 0x180>,
+		      <0x5c052000 0x200>;
+		reg-names = "hecc", "hecc-ram", "mbx";
+		interrupts = <24>;
+		clocks = <&hecc_ck>;
+	};
diff --git a/Documentation/devicetree/bindings/net/dsa/lan9303.txt b/Documentation/devicetree/bindings/net/dsa/lan9303.txt
new file mode 100644
index 000000000000..04f2965a4467
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/lan9303.txt
@@ -0,0 +1,105 @@
+SMSC/MicroChip LAN9303 three port ethernet switch
+-------------------------------------------------
+
+Required properties:
+
+- compatible: should be
+  - "smsc,lan9303-i2c" for I2C managed mode
+    or
+  - "smsc,lan9303-mdio" for mdio managed mode
+
+Optional properties:
+
+- reset-gpios: GPIO to be used to reset the whole device
+- reset-duration: reset duration in milliseconds, defaults to 200 ms
+
+Subnodes:
+
+The integrated switch subnode should be specified according to the binding
+described in dsa/dsa.txt. The CPU port of this switch is always port 0.
+
+Note: always use 'reg = <0/1/2>;' for the three DSA ports, even if the device is
+configured to use 1/2/3 instead. This hardware configuration will be
+auto-detected and mapped accordingly.
+
+Example:
+
+I2C managed mode:
+
+	master: masterdevice@X {
+		status = "okay";
+
+		fixed-link { /* RMII fixed link to LAN9303 */
+			speed = <100>;
+			full-duplex;
+		};
+	};
+
+	switch: switch@a {
+		compatible = "smsc,lan9303-i2c";
+		reg = <0xa>;
+		status = "okay";
+		reset-gpios = <&gpio7 6 GPIO_ACTIVE_LOW>;
+		reset-duration = <200>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 { /* RMII fixed link to master */
+				reg = <0>;
+				label = "cpu";
+				ethernet = <&master>;
+			};
+
+			port@1 { /* external port 1 */
+				reg = <1>;
+				label = "lan1;
+			};
+
+			port@2 { /* external port 2 */
+				reg = <2>;
+				label = "lan2";
+			};
+		};
+	};
+
+MDIO managed mode:
+
+	master: masterdevice@X {
+		status = "okay";
+		phy-handle = <&switch>;
+
+		mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			switch: switch-phy@0 {
+				compatible = "smsc,lan9303-mdio";
+				reg = <0>;
+				reset-gpios = <&gpio7 6 GPIO_ACTIVE_LOW>;
+				reset-duration = <100>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						label = "cpu";
+						ethernet = <&master>;
+					};
+
+					port@1 { /* external port 1 */
+						reg = <1>;
+						label = "lan1;
+					};
+
+					port@2 { /* external port 2 */
+						reg = <2>;
+						label = "lan2";
+					};
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt
new file mode 100644
index 000000000000..a9bc27b93ee3
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/mt7530.txt
@@ -0,0 +1,92 @@
+Mediatek MT7530 Ethernet switch
+================================
+
+Required properties:
+
+- compatible: Must be compatible = "mediatek,mt7530";
+- #address-cells: Must be 1.
+- #size-cells: Must be 0.
+- mediatek,mcm: Boolean; if defined, indicates that either MT7530 is the part
+	on multi-chip module belong to MT7623A has or the remotely standalone
+	chip as the function MT7623N reference board provided for.
+- core-supply: Phandle to the regulator node necessary for the core power.
+- io-supply: Phandle to the regulator node necessary for the I/O power.
+	See Documentation/devicetree/bindings/regulator/mt6323-regulator.txt
+	for details for the regulator setup on these boards.
+
+If the property mediatek,mcm isn't defined, following property is required
+
+- reset-gpios: Should be a gpio specifier for a reset line.
+
+Else, following properties are required
+
+- resets : Phandle pointing to the system reset controller with
+	line index for the ethsys.
+- reset-names : Should be set to "mcm".
+
+Required properties for the child nodes within ports container:
+
+- reg: Port address described must be 6 for CPU port and from 0 to 5 for
+	user ports.
+- phy-mode: String, must be either "trgmii" or "rgmii" for port labeled
+	 "cpu".
+
+See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional
+required, optional properties and how the integrated switch subnodes must
+be specified.
+
+Example:
+
+	&mdio0 {
+		switch@0 {
+			compatible = "mediatek,mt7530";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			core-supply = <&mt6323_vpa_reg>;
+			io-supply = <&mt6323_vemc3v3_reg>;
+			reset-gpios = <&pio 33 0>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				port@0 {
+					reg = <0>;
+					label = "lan0";
+				};
+
+				port@1 {
+					reg = <1>;
+					label = "lan1";
+				};
+
+				port@2 {
+					reg = <2>;
+					label = "lan2";
+				};
+
+				port@3 {
+					reg = <3>;
+					label = "lan3";
+				};
+
+				port@4 {
+					reg = <4>;
+					label = "wan";
+				};
+
+				port@6 {
+					reg = <6>;
+					label = "cpu";
+					ethernet = <&gmac0>;
+					phy-mode = "trgmii";
+					fixed-link {
+						speed = <1000>;
+						full-duplex;
+					};
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/ftgmac100.txt b/Documentation/devicetree/bindings/net/ftgmac100.txt
new file mode 100644
index 000000000000..c1ce1680246f
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ftgmac100.txt
@@ -0,0 +1,35 @@
+* Faraday Technology FTGMAC100 gigabit ethernet controller
+
+Required properties:
+- compatible: "faraday,ftgmac100"
+
+  Must also contain one of these if used as part of an Aspeed AST2400
+  or 2500 family SoC as they have some subtle tweaks to the
+  implementation:
+
+     - "aspeed,ast2400-mac"
+     - "aspeed,ast2500-mac"
+
+- reg: Address and length of the register set for the device
+- interrupts: Should contain ethernet controller interrupt
+
+Optional properties:
+- phy-mode: See ethernet.txt file in the same directory. If the property is
+  absent, "rgmii" is assumed. Supported values are "rgmii*" and "rmii" for
+  aspeed parts. Other (unknown) parts will accept any value.
+- use-ncsi: Use the NC-SI stack instead of an MDIO PHY. Currently assumes
+  rmii (100bT) but kept as a separate property in case NC-SI grows support
+  for a gigabit link.
+- no-hw-checksum: Used to disable HW checksum support. Here for backward
+  compatibility as the driver now should have correct defaults based on
+  the SoC.
+
+Example:
+
+	mac0: ethernet@1e660000 {
+		compatible = "aspeed,ast2500-mac", "faraday,ftgmac100";
+		reg = <0x1e660000 0x180>;
+		interrupts = <2>;
+		status = "okay";
+		use-ncsi;
+	};
diff --git a/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt b/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
new file mode 100644
index 000000000000..a1046e636fa1
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
@@ -0,0 +1,28 @@
+* CA8210 IEEE 802.15.4 *
+
+Required properties:
+	- compatible:           Should be "cascoda,ca8210"
+	- reg:                  Controlling chip select
+	- spi-max-frequency:    Maximum clock speed, should be *less than*
+	                        4000000
+	- spi-cpol:             Requires inverted clock polarity
+	- reset-gpio:           GPIO attached to reset
+	- irq-gpio:             GPIO attached to IRQ
+Optional properties:
+	- extclock-enable:      Include for the ca8210 to route its 16MHz clock
+	                        to an output
+	- extclock-freq:        Frequency in Hz of the external clock
+	- extclock-gpio:        GPIO of the ca8210 to output the clock on
+
+Example:
+	ca8210@0 {
+		compatible = "cascoda,ca8210";
+		reg = <0>;
+		spi-max-frequency = <3000000>;
+		spi-cpol;
+		reset-gpio = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+		irq-gpio = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+		extclock-enable;
+		extclock-freq = 16000000;
+		extclock-gpio = 2;
+	};
diff --git a/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt b/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt
index 9417e54c26c0..ccdabdcc8618 100644
--- a/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt
+++ b/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt
@@ -7,17 +7,20 @@ interface.
 
 Required properties:
 - compatible: "marvell,orion-mdio"
-- reg: address and length of the SMI register
+- reg: address and length of the MDIO registers.  When an interrupt is
+  not present, the length is the size of the SMI register (4 bytes)
+  otherwise it must be 0x84 bytes to cover the interrupt control
+  registers.
 
 Optional properties:
 - interrupts: interrupt line number for the SMI error/done interrupt
-- clocks: Phandle to the clock control device and gate bit
+- clocks: phandle for up to three required clocks for the MDIO instance
 
 The child nodes of the MDIO driver are the individual PHY devices
 connected to this MDIO bus. They must have a "reg" property given the
 PHY address on the MDIO bus.
 
-Example at the SoC level:
+Example at the SoC level without an interrupt property:
 
 mdio {
 	#address-cells = <1>;
@@ -26,6 +29,16 @@ mdio {
 	reg = <0xd0072004 0x4>;
 };
 
+Example with an interrupt property:
+
+mdio {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "marvell,orion-mdio";
+	reg = <0xd0072004 0x84>;
+	interrupts = <30>;
+};
+
 And at the board level:
 
 mdio {
diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 4754364df4c6..6b4956beff8c 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -1,17 +1,28 @@
-* Marvell Armada 375 Ethernet Controller (PPv2)
+* Marvell Armada 375 Ethernet Controller (PPv2.1)
+  Marvell Armada 7K/8K Ethernet Controller (PPv2.2)
 
 Required properties:
 
-- compatible: should be "marvell,armada-375-pp2"
+- compatible: should be one of:
+    "marvell,armada-375-pp2"
+    "marvell,armada-7k-pp2"
 - reg: addresses and length of the register sets for the device.
-  Must contain the following register sets:
+  For "marvell,armada-375-pp2", must contain the following register
+  sets:
 	- common controller registers
 	- LMS registers
-  In addition, at least one port register set is required.
-- clocks: a pointer to the reference clocks for this device, consequently:
-	- main controller clock
-	- GOP clock
-- clock-names: names of used clocks, must be "pp_clk" and "gop_clk".
+	- one register area per Ethernet port
+  For "marvell,armada-7k-pp2", must contain the following register
+  sets:
+	- packet processor registers
+	- networking interfaces registers
+
+- clocks: pointers to the reference clocks for this device, consequently:
+	- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
+	- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
+	- MG clock (only for armada-7k-pp2)
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and
+  "mg_clk" (the latter only for armada-7k-pp2).
 
 The ethernet ports are represented by subnodes. At least one port is
 required.
@@ -19,8 +30,10 @@ required.
 Required properties (port):
 
 - interrupts: interrupt for the port
-- port-id: should be '0' or '1' for ethernet ports, and '2' for the
-           loopback port
+- port-id: ID of the port from the MAC point of view
+- gop-port-id: only for marvell,armada-7k-pp2, ID of the port from the
+  GOP (Group Of Ports) point of view. This ID is used to index the
+  per-port registers in the second register area.
 - phy-mode: See ethernet.txt file in the same directory
 
 Optional properties (port):
@@ -29,7 +42,7 @@ Optional properties (port):
 - phy: a phandle to a phy node defining the PHY address (as the reg
   property, a single integer).
 
-Example:
+Example for marvell,armada-375-pp2:
 
 ethernet@f0000 {
 	compatible = "marvell,armada-375-pp2";
@@ -57,3 +70,30 @@ ethernet@f0000 {
 		phy-mode = "gmii";
 	};
 };
+
+Example for marvell,armada-7k-pp2:
+
+cpm_ethernet: ethernet@0 {
+	compatible = "marvell,armada-7k-pp22";
+	reg = <0x0 0x100000>, <0x129000 0xb000>;
+	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>;
+	clock-names = "pp_clk", "gop_clk", "gp_clk";
+
+	eth0: eth0 {
+		interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+		port-id = <0>;
+		gop-port-id = <0>;
+	};
+
+	eth1: eth1 {
+		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+		port-id = <1>;
+		gop-port-id = <2>;
+	};
+
+	eth2: eth2 {
+		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+		port-id = <2>;
+		gop-port-id = <3>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/mdio.txt b/Documentation/devicetree/bindings/net/mdio.txt
new file mode 100644
index 000000000000..96a53f89aa6e
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/mdio.txt
@@ -0,0 +1,37 @@
+Common MDIO bus properties.
+
+These are generic properties that can apply to any MDIO bus.
+
+Optional properties:
+- reset-gpios: One GPIO that control the RESET lines of all PHYs on that MDIO
+  bus.
+- reset-delay-us: RESET pulse width in microseconds.
+
+A list of child nodes, one per device on the bus is expected. These
+should follow the generic phy.txt, or a device specific binding document.
+
+The 'reset-delay-us' indicates the RESET signal pulse width in microseconds and
+applies to all PHY devices. It must therefore be appropriately determined based
+on all PHY requirements (maximum value of all per-PHY RESET pulse widths).
+
+Example :
+This example shows these optional properties, plus other properties
+required for the TI Davinci MDIO driver.
+
+	davinci_mdio: ethernet@0x5c030000 {
+		compatible = "ti,davinci_mdio";
+		reg = <0x5c030000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reset-gpios = <&gpio2 5 GPIO_ACTIVE_LOW>;
+		reset-delay-us = <2>;
+
+		ethphy0: ethernet-phy@1 {
+			reg = <1>;
+		};
+
+		ethphy1: ethernet-phy@3 {
+			reg = <3>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
index 32b35a07abe4..c627bbb3009e 100644
--- a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
+++ b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
@@ -5,8 +5,8 @@ Required properties:
 - spi-max-frequency: Maximum SPI frequency (<= 2000000).
 - interrupt-parent: phandle of parent interrupt handler.
 - interrupts: A single interrupt specifier.
-- ti,enable-gpios: Two GPIO entries used for 'EN' and 'EN2' pins on the
-  TRF7970A.
+- ti,enable-gpios: One or two GPIO entries used for 'EN' and 'EN2' pins on the
+  TRF7970A. EN2 is optional.
 - vin-supply: Regulator for supply voltage to VIN pin
 
 Optional SoC Specific Properties:
@@ -21,6 +21,8 @@ Optional SoC Specific Properties:
 - t5t-rmb-extra-byte-quirk: Specify that the trf7970a has the erratum
   where an extra byte is returned by Read Multiple Block commands issued
   to Type 5 tags.
+- vdd-io-supply: Regulator specifying voltage for vdd-io
+- clock-frequency: Set to specify that the input frequency to the trf7970a is 13560000Hz or 27120000Hz
 
 Example (for ARM-based BeagleBone with TRF7970A on SPI1):
 
@@ -39,10 +41,12 @@ Example (for ARM-based BeagleBone with TRF7970A on SPI1):
 				  <&gpio2 5 GPIO_ACTIVE_LOW>;
 		vin-supply = <&ldo3_reg>;
 		vin-voltage-override = <5000000>;
+		vdd-io-supply = <&ldo2_reg>;
 		autosuspend-delay = <30000>;
 		irq-status-read-quirk;
 		en2-rf-quirk;
 		t5t-rmb-extra-byte-quirk;
+		clock-frequency = <27120000>;
 		status = "okay";
 	};
 };
diff --git a/Documentation/devicetree/bindings/net/nokia-bluetooth.txt b/Documentation/devicetree/bindings/net/nokia-bluetooth.txt
new file mode 100644
index 000000000000..42be7dc9a70b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nokia-bluetooth.txt
@@ -0,0 +1,51 @@
+Nokia Bluetooth Chips
+---------------------
+
+Nokia phones often come with UART connected bluetooth chips from different
+vendors and modified device API. Those devices speak a protocol named H4+
+(also known as h4p) by Nokia, which is similar to the H4 protocol from the
+Bluetooth standard. In addition to the H4 protocol it specifies two more
+UART status lines for wakeup of UART transceivers to improve power management
+and a few new packet types used to negotiate uart speed.
+
+Required properties:
+
+ - compatible: should contain "nokia,h4p-bluetooth" as well as one of the following:
+   * "brcm,bcm2048-nokia"
+   * "ti,wl1271-bluetooth-nokia"
+ - reset-gpios: GPIO specifier, used to reset the BT module (active low)
+ - bluetooth-wakeup-gpios: GPIO specifier, used to wakeup the BT module (active high)
+ - host-wakeup-gpios: GPIO specifier, used to wakeup the host processor (active high)
+ - clock-names: should be "sysclk"
+ - clocks: should contain a clock specifier for every name in clock-names
+
+Optional properties:
+
+ - None
+
+Example:
+
+/ {
+       /* controlled (enabled/disabled) directly by BT module */
+       bluetooth_clk: vctcxo {
+               compatible = "fixed-clock";
+               #clock-cells = <0>;
+               clock-frequency = <38400000>;
+       };
+};
+
+&uart2 {
+       pinctrl-names = "default";
+       pinctrl-0 = <&uart2_pins>;
+
+       bluetooth {
+               compatible = "ti,wl1271-bluetooth-nokia", "nokia,h4p-bluetooth";
+
+               reset-gpios = <&gpio1 26 GPIO_ACTIVE_LOW>; /* gpio26 */
+               host-wakeup-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>; /* gpio101 */
+               bluetooth-wakeup-gpios = <&gpio2 5 GPIO_ACTIVE_HIGH>; /* gpio37 */
+
+               clocks = <&bluetooth_clk>;
+               clock-names = "sysclk";
+       };
+};
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index d3bfc2b30fb5..c3a7be6615c5 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -7,9 +7,12 @@ Required properties:
 - interrupt-parent: Should be the phandle for the interrupt controller
   that services interrupts for this device
 - interrupts: Should contain the STMMAC interrupts
-- interrupt-names: Should contain the interrupt names "macirq"
-  "eth_wake_irq" if this interrupt is supported in the "interrupts"
-  property
+- interrupt-names: Should contain a list of interrupt names corresponding to
+	the interrupts in the interrupts property, if available.
+	Valid interrupt names are:
+  - "macirq" (combined signal for various interrupt events)
+  - "eth_wake_irq" (the interrupt to manage the remote wake-up packet detection)
+  - "eth_lpi" (the interrupt that occurs when Tx or Rx enters/exits LPI state)
 - phy-mode: See ethernet.txt file in the same directory.
 - snps,reset-gpio 	gpio number for phy reset.
 - snps,reset-active-low boolean flag to indicate if phy reset is active low.
@@ -28,9 +31,9 @@ Optional properties:
   clocks may be specified in derived bindings.
 - clock-names: One name for each entry in the clocks property, the
   first one should be "stmmaceth" and the second one should be "pclk".
-- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is
-  available this clock is used for programming the Timestamp Addend Register.
-  If not passed then the system clock will be used and this is fine on some
+- ptp_ref: this is the PTP reference clock; in case of the PTP is available
+  this clock is used for programming the Timestamp Addend Register. If not
+  passed then the system clock will be used and this is fine on some
   platforms.
 - tx-fifo-depth: See ethernet.txt file in the same directory
 - rx-fifo-depth: See ethernet.txt file in the same directory
@@ -72,7 +75,45 @@ Optional properties:
 	- snps,mb: mixed-burst
 	- snps,rb: rebuild INCRx Burst
 - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus.
-
+- Multiple RX Queues parameters: below the list of all the parameters to
+				 configure the multiple RX queues:
+	- snps,rx-queues-to-use: number of RX queues to be used in the driver
+	- Choose one of these RX scheduling algorithms:
+		- snps,rx-sched-sp: Strict priority
+		- snps,rx-sched-wsp: Weighted Strict priority
+	- For each RX queue
+		- Choose one of these modes:
+			- snps,dcb-algorithm: Queue to be enabled as DCB
+			- snps,avb-algorithm: Queue to be enabled as AVB
+		- snps,map-to-dma-channel: Channel to map
+		- Specifiy specific packet routing:
+			- snps,route-avcp: AV Untagged Control packets
+			- snps,route-ptp: PTP Packets
+			- snps,route-dcbcp: DCB Control Packets
+			- snps,route-up: Untagged Packets
+			- snps,route-multi-broad: Multicast & Broadcast Packets
+		- snps,priority: RX queue priority (Range: 0x0 to 0xF)
+- Multiple TX Queues parameters: below the list of all the parameters to
+				 configure the multiple TX queues:
+	- snps,tx-queues-to-use: number of TX queues to be used in the driver
+	- Choose one of these TX scheduling algorithms:
+		- snps,tx-sched-wrr: Weighted Round Robin
+		- snps,tx-sched-wfq: Weighted Fair Queuing
+		- snps,tx-sched-dwrr: Deficit Weighted Round Robin
+		- snps,tx-sched-sp: Strict priority
+	- For each TX queue
+		- snps,weight: TX queue weight (if using a DCB weight algorithm)
+		- Choose one of these modes:
+			- snps,dcb-algorithm: TX queue will be working in DCB
+			- snps,avb-algorithm: TX queue will be working in AVB
+			  [Attention] Queue 0 is reserved for legacy traffic
+			  and so no AVB is available in this queue.
+		- Configure Credit Base Shaper (if AVB Mode selected):
+			- snps,send_slope: enable Low Power Interface
+			- snps,idle_slope: unlock on WoL
+			- snps,high_credit: max write outstanding req. limit
+			- snps,low_credit: max read outstanding req. limit
+		- snps,priority: TX queue priority (Range: 0x0 to 0xF)
 Examples:
 
 	stmmac_axi_setup: stmmac-axi-config {
@@ -81,12 +122,41 @@ Examples:
 		snps,blen = <256 128 64 32 0 0 0>;
 	};
 
+	mtl_rx_setup: rx-queues-config {
+		snps,rx-queues-to-use = <1>;
+		snps,rx-sched-sp;
+		queue0 {
+			snps,dcb-algorithm;
+			snps,map-to-dma-channel = <0x0>;
+			snps,priority = <0x0>;
+		};
+	};
+
+	mtl_tx_setup: tx-queues-config {
+		snps,tx-queues-to-use = <2>;
+		snps,tx-sched-wrr;
+		queue0 {
+			snps,weight = <0x10>;
+			snps,dcb-algorithm;
+			snps,priority = <0x0>;
+		};
+
+		queue1 {
+			snps,avb-algorithm;
+			snps,send_slope = <0x1000>;
+			snps,idle_slope = <0x1000>;
+			snps,high_credit = <0x3E800>;
+			snps,low_credit = <0xFFC18000>;
+			snps,priority = <0x1>;
+		};
+	};
+
 	gmac0: ethernet@e0800000 {
 		compatible = "st,spear600-gmac";
 		reg = <0xe0800000 0x8000>;
 		interrupt-parent = <&vic1>;
-		interrupts = <24 23>;
-		interrupt-names = "macirq", "eth_wake_irq";
+		interrupts = <24 23 22>;
+		interrupt-names = "macirq", "eth_wake_irq", "eth_lpi";
 		mac-address = [000000000000]; /* Filled in by U-Boot */
 		max-frame-size = <3800>;
 		phy-mode = "gmii";
@@ -104,4 +174,6 @@ Examples:
 			phy1: ethernet-phy@0 {
 			};
 		};
+		snps,mtl-rx-config = <&mtl_rx_setup>;
+		snps,mtl-tx-config = <&mtl_tx_setup>;
 	};
diff --git a/Documentation/devicetree/bindings/net/ti,wilink-st.txt b/Documentation/devicetree/bindings/net/ti,wilink-st.txt
new file mode 100644
index 000000000000..cbad73a84ac4
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ti,wilink-st.txt
@@ -0,0 +1,35 @@
+TI WiLink 7/8 (wl12xx/wl18xx) Shared Transport BT/FM/GPS devices
+
+TI WiLink devices have a UART interface for providing Bluetooth, FM radio,
+and GPS over what's called "shared transport". The shared transport is
+standard BT HCI protocol with additional channels for the other functions.
+
+These devices also have a separate WiFi interface as described in
+wireless/ti,wlcore.txt.
+
+This bindings follows the UART slave device binding in
+../serial/slave-device.txt.
+
+Required properties:
+ - compatible: should be one of the following:
+    "ti,wl1271-st"
+    "ti,wl1273-st"
+    "ti,wl1831-st"
+    "ti,wl1835-st"
+    "ti,wl1837-st"
+
+Optional properties:
+ - enable-gpios : GPIO signal controlling enabling of BT. Active high.
+ - vio-supply : Vio input supply (1.8V)
+ - vbat-supply : Vbat input supply (2.9-4.8V)
+
+Example:
+
+&serial0 {
+	compatible = "ns16550a";
+	...
+	bluetooth {
+		compatible = "ti,wl1835-st";
+		enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
index b7fa3b97986d..a339dbb15493 100644
--- a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
@@ -44,13 +44,19 @@ Hip05 Example (note that Hip06 is the same except compatible):
 	};
 
 HiSilicon Hip06/Hip07 PCIe host bridge DT (almost-ECAM) description.
+
+Some BIOSes place the host controller in a mode where it is ECAM
+compliant for all devices other than the root complex. In such cases,
+the host controller should be described as below.
+
 The properties and their meanings are identical to those described in
 host-generic-pci.txt except as listed below.
 
 Properties of the host controller node that differ from
 host-generic-pci.txt:
 
-- compatible     : Must be "hisilicon,pcie-almost-ecam"
+- compatible     : Must be "hisilicon,hip06-pcie-ecam", or
+		   "hisilicon,hip07-pcie-ecam"
 
 - reg            : Two entries: First the ECAM configuration space for any
 		   other bus underneath the root bus. Second, the base
@@ -59,7 +65,7 @@ host-generic-pci.txt:
 
 Example:
 	pcie0: pcie@a0090000 {
-		compatible = "hisilicon,pcie-almost-ecam";
+		compatible = "hisilicon,hip06-pcie-ecam";
 		reg = <0 0xb0000000 0 0x2000000>,  /*  ECAM configuration space */
 		      <0 0xa0090000 0 0x10000>; /* host bridge registers */
 		bus-range = <0  31>;
diff --git a/Documentation/devicetree/bindings/phy/brcm,nsp-usb3-phy.txt b/Documentation/devicetree/bindings/phy/brcm,nsp-usb3-phy.txt
deleted file mode 100644
index e68ae5dec9c9..000000000000
--- a/Documentation/devicetree/bindings/phy/brcm,nsp-usb3-phy.txt
+++ /dev/null
@@ -1,39 +0,0 @@
-Broadcom USB3 phy binding for northstar plus SoC
-The USB3 phy is internal to the SoC and is accessed using mdio interface.
-
-Required mdio bus properties:
-- reg: Should be 0x0 for SoC internal USB3 phy
-- #address-cells: must be 1
-- #size-cells: must be 0
-
-Required USB3 PHY properties:
-- compatible: should be "brcm,nsp-usb3-phy"
-- reg: USB3 Phy address on SoC internal MDIO bus and it should be 0x10.
-- usb3-ctrl-syscon: handler of syscon node defining physical address
-  of usb3 control register.
-- #phy-cells: must be 0
-
-Required usb3 control properties:
-- compatible: should be "brcm,nsp-usb3-ctrl"
-- reg: offset and length of the control registers
-
-Example:
-
-	mdio@0 {
-		reg = <0x0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		usb3_phy: usb-phy@10 {
-			compatible = "brcm,nsp-usb3-phy";
-			reg = <0x10>;
-			usb3-ctrl-syscon = <&usb3_ctrl>;
-			#phy-cells = <0>;
-			status = "disabled";
-		};
-	};
-
-	usb3_ctrl: syscon@104408 {
-		compatible = "brcm,nsp-usb3-ctrl", "syscon";
-		reg = <0x104408 0x3fc>;
-	};
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index 2fd688c8dbdb..b53224473672 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -23,7 +23,8 @@ Required properties:
   "allwinner,sun8i-h3-pinctrl"
   "allwinner,sun8i-h3-r-pinctrl"
   "allwinner,sun50i-a64-pinctrl"
-  "allwinner,sun50i-h5-r-pinctrl"
+  "allwinner,sun50i-a64-r-pinctrl"
+  "allwinner,sun50i-h5-pinctrl"
   "nextthing,gr8-pinctrl"
 
 - reg: Should contain the register physical address and length for the
diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
index 9a8a45d9d8ab..590e60378be3 100644
--- a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
@@ -4,7 +4,7 @@ The AT91 Pinmux Controller, enables the IC
 to share one PAD to several functional blocks. The sharing is done by
 multiplexing the PAD input/output signals. For each PAD there are up to
 8 muxing options (called periph modes). Since different modules require
-different PAD settings (like pull up, keeper, etc) the contoller controls
+different PAD settings (like pull up, keeper, etc) the controller controls
 also the PAD settings parameters.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
diff --git a/Documentation/devicetree/bindings/pinctrl/axis,artpec6-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/axis,artpec6-pinctrl.txt
new file mode 100644
index 000000000000..47284f85ec80
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/axis,artpec6-pinctrl.txt
@@ -0,0 +1,85 @@
+Axis ARTPEC-6 Pin Controller
+
+Required properties:
+- compatible: "axis,artpec6-pinctrl".
+- reg: Should contain the register physical address and length for the pin
+       controller.
+
+A pinctrl node should contain at least one subnode representing the pinctrl
+groups available on the machine. Each subnode will list the mux function
+required and what pin group it will use. Each subnode will also configure the
+drive strength and bias pullup of the pin group. If either of these options is
+not set, its actual value will be unspecified.
+
+
+Required subnode-properties:
+- function: Function to mux.
+- groups: Name of the pin group to use for the function above.
+
+	Available functions and groups (function: group0, group1...):
+		gpio: cpuclkoutgrp0, udlclkoutgrp0, i2c1grp0, i2c2grp0,
+		      i2c3grp0, i2s0grp0, i2s1grp0, i2srefclkgrp0, spi0grp0,
+		      spi1grp0, pciedebuggrp0, uart0grp0, uart0grp1, uart1grp0,
+		      uart2grp0, uart2grp1, uart3grp0, uart4grp0, uart5grp0
+		cpuclkout: cpuclkoutgrp0
+		udlclkout: udlclkoutgrp0
+		i2c1: i2c1grp0
+		i2c2: i2c2grp0
+		i2c3: i2c3grp0
+		i2s0: i2s0grp0
+		i2s1: i2s1grp0
+		i2srefclk: i2srefclkgrp0
+		spi0: spi0grp0
+		spi1: spi1grp0
+		pciedebug: pciedebuggrp0
+		uart0: uart0grp0, uart0grp1
+		uart1: uart1grp0
+		uart2: uart2grp0, uart2grp1
+		uart3: uart3grp0
+		uart4: uart4grp0
+		uart5: uart5grp0
+		nand: nandgrp0
+		sdio0: sdio0grp0
+		sdio1: sdio1grp0
+		ethernet: ethernetgrp0
+
+
+Optional subnode-properties (see pinctrl-bindings.txt):
+- drive-strength: 4, 6, 8, 9 mA.  For SD and NAND pins, this is for 3.3V VCCQ3.
+- bias-pull-up
+- bias-disable
+
+Examples:
+pinctrl@f801d000 {
+	compatible = "axis,artpec6-pinctrl";
+	reg = <0xf801d000 0x400>;
+
+	pinctrl_uart0: uart0grp {
+		function = "uart0";
+		groups = "uart0grp0";
+		drive-strength = <4>;
+		bias-pull-up;
+	};
+	pinctrl_uart3: uart3grp {
+		function = "uart3";
+		groups = "uart3grp0";
+	};
+};
+uart0: uart@f8036000 {
+	compatible = "arm,pl011", "arm,primecell";
+	reg = <0xf8036000 0x1000>;
+	interrupts = <0 104 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&pll2div24>, <&apb_pclk>;
+	clock-names = "uart_clk", "apb_pclk";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart0>;
+};
+uart3: uart@f8039000 {
+	compatible = "arm,pl011", "arm,primecell";
+	reg = <0xf8039000 0x1000>;
+	interrupts = <0 128 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&pll2div24>, <&apb_pclk>;
+	clock-names = "uart_clk", "apb_pclk";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3>;
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt
new file mode 100644
index 000000000000..f64060908d5a
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt
@@ -0,0 +1,183 @@
+* Marvell Armada 37xx SoC pin and gpio controller
+
+Each Armada 37xx SoC come with two pin and gpio controller one for the
+south bridge and the other for the north bridge.
+
+Inside this set of register the gpio latch allows exposing some
+configuration of the SoC and especially the clock frequency of the
+xtal. Hence, this node is a represent as syscon allowing sharing the
+register between multiple hardware block.
+
+GPIO and pin controller:
+------------------------
+
+Main node:
+
+Refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning
+of the phrase "pin configuration node".
+
+Required properties for pinctrl driver:
+
+- compatible:	"marvell,armada3710-sb-pinctrl", "syscon, "simple-mfd"
+		for the south bridge
+		"marvell,armada3710-nb-pinctrl", "syscon, "simple-mfd"
+		for the north bridge
+- reg: The first set of register are for pinctrl/gpio and the second
+  set for the interrupt controller
+- interrupts: list of the interrupt use by the gpio
+
+Available groups and functions for the North bridge:
+
+group: jtag
+ - pins 20-24
+ - functions jtag, gpio
+
+group sdio0
+ - pins 8-10
+ - functions sdio, gpio
+
+group emmc_nb
+ - pins 27-35
+ - functions emmc, gpio
+
+group pwm0
+ - pin 11 (GPIO1-11)
+ - functions pwm, gpio
+
+group pwm1
+ - pin 12
+ - functions pwm, gpio
+
+group pwm2
+ - pin 13
+ - functions pwm, gpio
+
+group pwm3
+ - pin 14
+ - functions pwm, gpio
+
+group pmic1
+ - pin 17
+ - functions pmic, gpio
+
+group pmic0
+ - pin 16
+ - functions pmic, gpio
+
+group i2c2
+ - pins 2-3
+ - functions i2c, gpio
+
+group i2c1
+ - pins 0-1
+ - functions i2c, gpio
+
+group spi_cs1
+ - pin 17
+ - functions spi, gpio
+
+group spi_cs2
+ - pin 18
+ - functions spi, gpio
+
+group spi_cs3
+ - pin 19
+ - functions spi, gpio
+
+group onewire
+ - pin 4
+ - functions onewire, gpio
+
+group uart1
+ - pins 25-26
+ - functions uart, gpio
+
+group spi_quad
+ - pins 15-16
+ - functions spi, gpio
+
+group uart_2
+ - pins 9-10
+ - functions uart, gpio
+
+Available groups and functions for the South bridge:
+
+group usb32_drvvbus0
+ - pin 36
+ - functions drvbus, gpio
+
+group usb2_drvvbus1
+ - pin 37
+ - functions drvbus, gpio
+
+group sdio_sb
+ - pins 60-64
+ - functions sdio, gpio
+
+group rgmii
+ - pins 42-55
+ - functions mii, gpio
+
+group pcie1
+ - pins 39-40
+ - functions pcie, gpio
+
+group ptp
+ - pins 56-58
+ - functions ptp, gpio
+
+group ptp_clk
+ - pin 57
+ - functions ptp, mii
+
+group ptp_trig
+ - pin 58
+ - functions ptp, mii
+
+group mii_col
+ - pin 59
+ - functions mii, mii_err
+
+GPIO subnode:
+
+Please refer to gpio.txt in this directory for details of gpio-ranges property
+and the common GPIO bindings used by client devices.
+
+Required properties for gpio driver under the gpio subnode:
+- interrupts: List of interrupt specifier for the controllers interrupt.
+- gpio-controller: Marks the device node as a gpio controller.
+- #gpio-cells: Should be 2. The first cell is the GPIO number and the
+   second cell specifies GPIO flags, as defined in
+   <dt-bindings/gpio/gpio.h>. Only the GPIO_ACTIVE_HIGH and
+   GPIO_ACTIVE_LOW flags are supported.
+- gpio-ranges: Range of pins managed by the GPIO controller.
+
+Xtal Clock bindings for Marvell Armada 37xx SoCs
+------------------------------------------------
+
+see Documentation/devicetree/bindings/clock/armada3700-xtal-clock.txt
+
+
+Example:
+pinctrl_sb: pinctrl-sb@18800 {
+	compatible = "marvell,armada3710-sb-pinctrl", "syscon", "simple-mfd";
+	reg = <0x18800 0x100>, <0x18C00 0x20>;
+	gpio {
+		#gpio-cells = <2>;
+		gpio-ranges = <&pinctrl_sb 0 0 29>;
+		gpio-controller;
+		interrupts =
+		<GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	rgmii_pins: mii-pins {
+		groups = "rgmii";
+		function = "mii";
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt
index b98e6f030da8..ca01710ee29a 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt
@@ -34,13 +34,28 @@ Documentation/devicetree/bindings/mfd/syscon.txt
 Subnode Format
 ==============
 
-The required properties of child nodes are (as defined in pinctrl-bindings):
-- function
-- groups
+The required properties of pinmux child nodes are:
+- function: the mux function to select
+- groups  : the list of groups to select with this function
 
-Each function has only one associated pin group. Each group is named by its
-function. The following values for the function and groups properties are
-supported:
+Required properties of pinconf child nodes are:
+- groups: A list of groups to select (either this or "pins" must be
+          specified)
+- pins  : A list of ball names as strings, eg "D14" (either this or "groups"
+          must be specified)
+
+Optional properties of pinconf child nodes are:
+- bias-disable  : disable any pin bias
+- bias-pull-down: pull down the pin
+- drive-strength: sink or source at most X mA
+
+Definitions are as specified in
+Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt, with any
+further limitations as described above.
+
+For pinmux, each mux function has only one associated pin group. Each group is
+named by its function. The following values for the function and groups
+properties are supported:
 
 aspeed,ast2400-pinctrl, aspeed,g4-pinctrl:
 
@@ -90,6 +105,11 @@ syscon: scu@1e6e2000 {
 			function = "I2C3";
 			groups = "I2C3";
 		};
+
+		pinctrl_gpioh0_unbiased_default: gpioh0 {
+			pins = "A8";
+			bias-disable;
+		};
 	};
 };
 
@@ -110,6 +130,11 @@ ahb {
 					function = "I2C3";
 					groups = "I2C3";
 				};
+
+				pinctrl_gpioh0_unbiased_default: gpioh0 {
+					pins = "A18";
+					bias-disable;
+				};
 			};
 		};
 
@@ -143,6 +168,3 @@ ahb {
 		};
 	};
 };
-
-Please refer to pinctrl-bindings.txt in this directory for details of the
-common pinctrl bindings used by client devices.
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
index bf3f7b014724..71a3c134af1b 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
@@ -162,8 +162,8 @@ state_2_node_a {
 	pins = "mfio29", "mfio30";
 };
 
-Optionally an altenative binding can be used if more suitable depending on the
-pin controller hardware. For hardaware where there is a large number of identical
+Optionally an alternative binding can be used if more suitable depending on the
+pin controller hardware. For hardware where there is a large number of identical
 pin controller instances, naming each pin and function can easily become
 unmaintainable. This is especially the case if the same controller is used for
 different pins and functions depending on the SoC revision and packaging.
@@ -198,6 +198,28 @@ registers, and must not be a virtual index of pin instances. The reason for
 this is to avoid mapping of the index in the dts files and the pin controller
 driver as it can change.
 
+For hardware where pin multiplexing configurations have to be specified for
+each single pin the number of required sub-nodes containing "pin" and
+"function" properties can quickly escalate and become hard to write and
+maintain.
+
+For cases like this, the pin controller driver may use the pinmux helper
+property, where the pin identifier is packed with mux configuration settings
+in a single integer.
+
+The pinmux property accepts an array of integers, each of them describing
+a single pin multiplexing configuration.
+
+pincontroller {
+	state_0_node_a {
+		pinmux = <PIN_ID_AND_MUX>, <PIN_ID_AND_MUX>, ...;
+	};
+};
+
+Each individual pin controller driver bindings documentation shall specify
+how those values (pin IDs and pin multiplexing configuration) are defined and
+assembled together.
+
 == Generic pin configuration node content ==
 
 Many data items that are represented in a pin configuration node are common
@@ -210,18 +232,22 @@ structure of the DT nodes that contain these properties.
 Supported generic properties are:
 
 pins			- the list of pins that properties in the node
-			  apply to (either this or "group" has to be
+			  apply to (either this, "group" or "pinmux" has to be
 			  specified)
 group			- the group to apply the properties to, if the driver
 			  supports configuration of whole groups rather than
-			  individual pins (either this or "pins" has to be
-			  specified)
+			  individual pins (either this, "pins" or "pinmux" has
+			  to be specified)
+pinmux			- the list of numeric pin ids and their mux settings
+			  that properties in the node apply to (either this,
+			  "pins" or "groups" have to be specified)
 bias-disable		- disable any pin bias
 bias-high-impedance	- high impedance mode ("third-state", "floating")
 bias-bus-hold		- latch weakly
 bias-pull-up		- pull up the pin
 bias-pull-down		- pull down the pin
 bias-pull-pin-default	- use pin-default pull state
+bi-directional		- pin supports simultaneous input/output operations
 drive-push-pull		- drive actively high and low
 drive-open-drain	- drive with open drain
 drive-open-source	- drive with open source
@@ -234,6 +260,7 @@ input-debounce		- debounce mode with debound time X
 power-source		- select between different power supplies
 low-power-enable	- enable low power mode
 low-power-disable	- disable low power mode
+output-enable		- enable output on pin regardless of output value
 output-low		- set the pin to output mode with low level
 output-high		- set the pin to output mode with high level
 slew-rate		- set the slew rate
@@ -258,6 +285,12 @@ state_2_node_a {
 		bias-pull-up;
 	};
 };
+state_3_node_a {
+	mux {
+		pinmux = <GPIOx_PINm_MUXn>, <GPIOx_PINj_MUXk)>;
+		input-enable;
+	};
+};
 
 Some of the generic properties take arguments. For those that do, the
 arguments are described below.
@@ -266,6 +299,11 @@ arguments are described below.
   binding for the hardware defines:
   - Whether the entries are integers or strings, and their meaning.
 
+- pinmux takes a list of pin IDs and mux settings as required argument. The
+  specific bindings for the hardware defines:
+  - How pin IDs and mux settings are defined and assembled together in a single
+    integer.
+
 - bias-pull-up, -down and -pin-default take as optional argument on hardware
   supporting it the pull strength in Ohm. bias-disable will disable the pull.
 
diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 4722bc61a1a2..ee01ab58224d 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -19,11 +19,18 @@ The pins are grouped into up to 5 individual pin banks which need to be
 defined as gpio sub-nodes of the pinmux controller.
 
 Required properties for iomux controller:
-  - compatible: one of "rockchip,rk1108-pinctrl", "rockchip,rk2928-pinctrl"
-		       "rockchip,rk3066a-pinctrl", "rockchip,rk3066b-pinctrl"
-		       "rockchip,rk3188-pinctrl", "rockchip,rk3228-pinctrl"
-		       "rockchip,rk3288-pinctrl", "rockchip,rk3368-pinctrl"
-		       "rockchip,rk3399-pinctrl"
+  - compatible: should be
+		"rockchip,rv1108-pinctrl":  for Rockchip RV1108
+		"rockchip,rk2928-pinctrl":  for Rockchip RK2928
+		"rockchip,rk3066a-pinctrl": for Rockchip RK3066a
+		"rockchip,rk3066b-pinctrl": for Rockchip RK3066b
+		"rockchip,rk3188-pinctrl":  for Rockchip RK3188
+		"rockchip,rk3228-pinctrl":  for Rockchip RK3228
+		"rockchip,rk3288-pinctrl":  for Rockchip RK3288
+		"rockchip,rk3328-pinctrl":  for Rockchip RK3328
+		"rockchip,rk3368-pinctrl":  for Rockchip RK3368
+		"rockchip,rk3399-pinctrl":  for Rockchip RK3399
+
   - rockchip,grf: phandle referencing a syscon providing the
 	 "general register files"
 
diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
index eac20aa33907..d907a74f8dc0 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -9,6 +9,7 @@ Pin controller node:
 Required properies:
  - compatible: value should be one of the following:
    "st,stm32f429-pinctrl"
+   "st,stm32f469-pinctrl"
    "st,stm32f746-pinctrl"
    "st,stm32h743-pinctrl"
  - #address-cells: The value of this property must be 1
@@ -38,8 +39,6 @@ Optional properties:
  - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
    which includes IRQ mux selection register, and the offset of the IRQ mux
    selection register.
- - ngpios: Number of gpios in a bank (to use if bank gpio numbers is less
-   than 16).
  - gpio-ranges: Define a dedicated mapping between a pin-controller and
    a gpio controller. Format is <&phandle a b c> with:
 	-(phandle): phandle of pin-controller.
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 723e1ad937da..940707d095cc 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -31,7 +31,9 @@ Optional properties:
 
 - domain-idle-states : A phandle of an idle-state that shall be soaked into a
                 generic domain power state. The idle state definitions are
-                compatible with domain-idle-state specified in [1].
+                compatible with domain-idle-state specified in [1]. phandles
+                that are not compatible with domain-idle-state will be
+                ignored.
   The domain-idle-state property reflects the idle state of this PM domain and
   not the idle states of the devices or sub-domains in the PM domain. Devices
   and sub-domains have their own idle-states independent of the parent
diff --git a/Documentation/devicetree/bindings/power/reset/gemini-poweroff.txt b/Documentation/devicetree/bindings/power/reset/gemini-poweroff.txt
new file mode 100644
index 000000000000..7fec3e100214
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/gemini-poweroff.txt
@@ -0,0 +1,17 @@
+* Device-Tree bindings for Cortina Systems Gemini Poweroff
+
+This is a special IP block in the Cortina Gemini SoC that only
+deals with different ways to power the system down.
+
+Required properties:
+- compatible: should be "cortina,gemini-power-controller"
+- reg: should contain the physical memory base and size
+- interrupts: should contain the power management interrupt
+
+Example:
+
+power-controller@4b000000 {
+	compatible = "cortina,gemini-power-controller";
+	reg = <0x4b000000 0x100>;
+	interrupts = <26 IRQ_TYPE_EDGE_FALLING>;
+};
diff --git a/Documentation/devicetree/bindings/power/reset/syscon-poweroff.txt b/Documentation/devicetree/bindings/power/reset/syscon-poweroff.txt
index 1e2546f8b08a..022ed1f3bc80 100644
--- a/Documentation/devicetree/bindings/power/reset/syscon-poweroff.txt
+++ b/Documentation/devicetree/bindings/power/reset/syscon-poweroff.txt
@@ -3,13 +3,20 @@ Generic SYSCON mapped register poweroff driver
 This is a generic poweroff driver using syscon to map the poweroff register.
 The poweroff is generally performed with a write to the poweroff register
 defined by the register map pointed by syscon reference plus the offset
-with the mask defined in the poweroff node.
+with the value and mask defined in the poweroff node.
 
 Required properties:
 - compatible: should contain "syscon-poweroff"
 - regmap: this is phandle to the register map node
 - offset: offset in the register map for the poweroff register (in bytes)
-- mask: the poweroff value written to the poweroff register (32 bit access)
+- value: the poweroff value written to the poweroff register (32 bit access)
+
+Optional properties:
+- mask: update only the register bits defined by the mask (32 bit)
+
+Legacy usage:
+If a node doesn't contain a value property but contains a mask property, the
+mask property is used as the value.
 
 Default will be little endian mode, 32 bit access only.
 
diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
index d23dc002a87e..d3a5a93a65cd 100644
--- a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
+++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
@@ -33,6 +33,7 @@ Required properties:
 - compatible: should be one of:
   - "rockchip,rk3188-io-voltage-domain" for rk3188
   - "rockchip,rk3288-io-voltage-domain" for rk3288
+  - "rockchip,rk3328-io-voltage-domain" for rk3328
   - "rockchip,rk3368-io-voltage-domain" for rk3368
   - "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains
   - "rockchip,rk3399-io-voltage-domain" for rk3399
diff --git a/Documentation/devicetree/bindings/power/supply/cpcap-charger.txt b/Documentation/devicetree/bindings/power/supply/cpcap-charger.txt
new file mode 100644
index 000000000000..80bd873c3b1d
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/cpcap-charger.txt
@@ -0,0 +1,37 @@
+Motorola CPCAP PMIC battery charger binding
+
+Required properties:
+- compatible: Shall be "motorola,mapphone-cpcap-charger"
+- interrupts: Interrupt specifier for each name in interrupt-names
+- interrupt-names: Should contain the following entries:
+		   "chrg_det", "rvrs_chrg", "chrg_se1b", "se0conn",
+		   "rvrs_mode", "chrgcurr1", "vbusvld", "battdetb"
+- io-channels: IIO ADC channel specifier for each name in io-channel-names
+- io-channel-names: Should contain the following entries:
+		    "battdetb", "battp", "vbus", "chg_isense", "batti"
+
+Optional properties:
+- mode-gpios: Optionally CPCAP charger can have a companion wireless
+	      charge controller that is controlled with two GPIOs
+	      that are active low.
+
+Example:
+
+cpcap_charger: charger {
+	compatible = "motorola,mapphone-cpcap-charger";
+	interrupts-extended = <
+		&cpcap 13 0 &cpcap 12 0 &cpcap 29 0 &cpcap 28 0
+		&cpcap 22 0 &cpcap 20 0 &cpcap 19 0 &cpcap 54 0
+	>;
+	interrupt-names =
+		"chrg_det", "rvrs_chrg", "chrg_se1b", "se0conn",
+		"rvrs_mode", "chrgcurr1", "vbusvld", "battdetb";
+	mode-gpios = <&gpio3 29 GPIO_ACTIVE_LOW
+		      &gpio3 23 GPIO_ACTIVE_LOW>;
+	io-channels = <&cpcap_adc 0 &cpcap_adc 1
+		       &cpcap_adc 2 &cpcap_adc 5
+		       &cpcap_adc 6>;
+	io-channel-names = "battdetb", "battp",
+			   "vbus", "chg_isense",
+			   "batti";
+};
diff --git a/Documentation/devicetree/bindings/power/supply/lego_ev3_battery.txt b/Documentation/devicetree/bindings/power/supply/lego_ev3_battery.txt
new file mode 100644
index 000000000000..5485633b1faa
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/lego_ev3_battery.txt
@@ -0,0 +1,21 @@
+LEGO MINDSTORMS EV3 Battery
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+LEGO MINDSTORMS EV3 has some built-in capability for monitoring the battery.
+It uses 6 AA batteries or a special Li-ion rechargeable battery pack that is
+detected by a key switch in the battery compartment.
+
+Required properties:
+ - compatible: Must be "lego,ev3-battery"
+ - io-channels: phandles to analog inputs for reading voltage and current
+ - io-channel-names: Must be "voltage", "current"
+ - rechargeable-gpios: phandle to the rechargeable battery indication gpio
+
+Example:
+
+	battery {
+		compatible = "lego,ev3-battery";
+		io-channels = <&adc 4>, <&adc 3>;
+		io-channel-names = "voltage", "current";
+		rechargeable-gpios = <&gpio 136 GPIO_ACTIVE_LOW>;
+	};
diff --git a/Documentation/devicetree/bindings/power/supply/ltc2941.txt b/Documentation/devicetree/bindings/power/supply/ltc2941.txt
index ea42ae12d924..a9d7aa60558b 100644
--- a/Documentation/devicetree/bindings/power/supply/ltc2941.txt
+++ b/Documentation/devicetree/bindings/power/supply/ltc2941.txt
@@ -6,8 +6,8 @@ temperature monitoring, and uses a slightly different conversion
 formula for the charge counter.
 
 Required properties:
-- compatible: Should contain "ltc2941" or "ltc2943" which also indicates the
-    type of I2C chip attached.
+- compatible: Should contain "lltc,ltc2941" or "lltc,ltc2943" which also
+    indicates the type of I2C chip attached.
 - reg: The 7-bit I2C address.
 - lltc,resistor-sense: The sense resistor value in milli-ohms. Can be a 32-bit
     negative value when the battery has been connected to the wrong end of the
@@ -20,7 +20,7 @@ Required properties:
 Example from the Topic Miami Florida board:
 
 	fuelgauge: ltc2943@64 {
-		compatible = "ltc2943";
+		compatible = "lltc,ltc2943";
 		reg = <0x64>;
 		lltc,resistor-sense = <15>;
 		lltc,prescaler-exponent = <5>; /* 2^(2*5) = 1024 */
diff --git a/Documentation/devicetree/bindings/power/supply/max8925_batter.txt b/Documentation/devicetree/bindings/power/supply/max8925_battery.txt
index d7e3e0c0f71d..d7e3e0c0f71d 100644
--- a/Documentation/devicetree/bindings/power/supply/max8925_batter.txt
+++ b/Documentation/devicetree/bindings/power/supply/max8925_battery.txt
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/emac.txt b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt
index 712baf6c3e24..44b842b6ca15 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/emac.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt
@@ -71,6 +71,9 @@
 			  For Axon it can be absent, though my current driver
 			  doesn't handle phy-address yet so for now, keep
 			  0x00ffffff in it.
+    - phy-handle	: Used to describe configurations where a external PHY
+			  is used. Please refer to:
+			  Documentation/devicetree/bindings/net/ethernet.txt
     - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
 			  operations (if absent the value is the same as
 			  rx-fifo-size).  For Axon, either absent or 2048.
@@ -81,8 +84,22 @@
 			  offload, phandle of the TAH device node.
     - tah-channel       : 1 cell, optional. If appropriate, channel used on the
 			  TAH engine.
+    - fixed-link	: Fixed-link subnode describing a link to a non-MDIO
+			  managed entity. See
+			  Documentation/devicetree/bindings/net/fixed-link.txt
+			  for details.
+    - mdio subnode	: When the EMAC has a phy connected to its local
+			  mdio, which us supported by the kernel's network
+			  PHY library in drivers/net/phy, there must be device
+			  tree subnode with the following required properties:
+				- #address-cells: Must be <1>.
+				- #size-cells: Must be <0>.
 
-    Example:
+			  For PHY definitions: Please refer to
+			  Documentation/devicetree/bindings/net/phy.txt and
+			  Documentation/devicetree/bindings/net/ethernet.txt
+
+    Examples:
 
 	EMAC0: ethernet@40000800 {
 		device_type = "network";
@@ -104,6 +121,48 @@
 		zmii-channel = <0>;
 	};
 
+	EMAC1: ethernet@ef600c00 {
+		device_type = "network";
+		compatible = "ibm,emac-apm821xx", "ibm,emac4sync";
+		interrupt-parent = <&EMAC1>;
+		interrupts = <0 1>;
+		#interrupt-cells = <1>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		interrupt-map = <0 &UIC2 0x10 IRQ_TYPE_LEVEL_HIGH /* Status */
+				 1 &UIC2 0x14 IRQ_TYPE_LEVEL_HIGH /* Wake */>;
+		reg = <0xef600c00 0x000000c4>;
+		local-mac-address = [000000000000]; /* Filled in by U-Boot */
+		mal-device = <&MAL0>;
+		mal-tx-channel = <0>;
+		mal-rx-channel = <0>;
+		cell-index = <0>;
+		max-frame-size = <9000>;
+		rx-fifo-size = <16384>;
+		tx-fifo-size = <2048>;
+		fifo-entry-size = <10>;
+		phy-mode = "rgmii";
+		phy-handle = <&phy0>;
+		phy-map = <0x00000000>;
+		rgmii-device = <&RGMII0>;
+		rgmii-channel = <0>;
+		tah-device = <&TAH0>;
+		tah-channel = <0>;
+		has-inverted-stacr-oc;
+		has-new-stacr-staopc;
+
+	        mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			phy0: ethernet-phy@0 {
+				compatible = "ethernet-phy-ieee802.3-c22";
+				reg = <0>;
+			};
+		};
+	};
+
+
       ii) McMAL node
 
     Required properties:
@@ -145,4 +204,3 @@
     - revision           : as provided by the RGMII new version register if
 			   available.
 			   For Axon: 0x0000012a
-
diff --git a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
index c3f6546ebac7..6a23ad9ac53a 100644
--- a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
@@ -45,7 +45,7 @@ Required Properties:
 Optional Properties:
 - reg-names: In addition to the required properties, the following are optional
   - "efuse-address"	- Contains efuse base address used to pick up ABB info.
-  - "ldo-address"	- Contains address of ABB LDO overide register address.
+  - "ldo-address"	- Contains address of ABB LDO override register.
 	"efuse-address" is required for this.
 - ti,ldovbb-vset-mask	- Required if ldo-address is set, mask for LDO override
 	register to provide override vset value.
diff --git a/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt b/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt
index 202f2d09a23f..4d403645ac9b 100644
--- a/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt
+++ b/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt
@@ -6,9 +6,16 @@ Required properties:
 - compatible : should be "amlogic,meson-rng"
 - reg : Specifies base physical address and size of the registers.
 
+Optional properties:
+
+- clocks : phandle to the following named clocks
+- clock-names: Name of core clock, must be "core"
+
 Example:
 
 rng {
-        compatible = "amlogic,meson-rng";
-        reg = <0x0 0xc8834000 0x0 0x4>;
+	compatible = "amlogic,meson-rng";
+	reg = <0x0 0xc8834000 0x0 0x4>;
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
 };
diff --git a/Documentation/devicetree/bindings/rng/mtk-rng.txt b/Documentation/devicetree/bindings/rng/mtk-rng.txt
new file mode 100644
index 000000000000..a6d62a2abd39
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/mtk-rng.txt
@@ -0,0 +1,18 @@
+Device-Tree bindings for Mediatek random number generator
+found in Mediatek SoC family
+
+Required properties:
+- compatible	    : Should be "mediatek,mt7623-rng"
+- clocks	    : list of clock specifiers, corresponding to
+		      entries in clock-names property;
+- clock-names	    : Should contain "rng" entries;
+- reg 		    : Specifies base physical address and size of the registers
+
+Example:
+
+rng: rng@1020f000 {
+	compatible = "mediatek,mt7623-rng";
+	reg = <0 0x1020f000 0 0x1000>;
+	clocks = <&infracfg CLK_INFRA_TRNG>;
+	clock-names = "rng";
+};
diff --git a/Documentation/devicetree/bindings/rng/omap_rng.txt b/Documentation/devicetree/bindings/rng/omap_rng.txt
index 471477299ece..9cf7876ab434 100644
--- a/Documentation/devicetree/bindings/rng/omap_rng.txt
+++ b/Documentation/devicetree/bindings/rng/omap_rng.txt
@@ -12,7 +12,8 @@ Required properties:
 - reg : Offset and length of the register set for the module
 - interrupts : the interrupt number for the RNG module.
 		Used for "ti,omap4-rng" and "inside-secure,safexcel-eip76"
-- clocks: the trng clock source
+- clocks: the trng clock source. Only mandatory for the
+  "inside-secure,safexcel-eip76" compatible.
 
 Example:
 /* AM335x */
diff --git a/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt
deleted file mode 100644
index 16ea1d3b2e9e..000000000000
--- a/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-Cortina Systems Gemini timer
-
-This timer is embedded in the Cortina Systems Gemini SoCs.
-
-Required properties:
-
-- compatible : Must be "cortina,gemini-timer"
-- reg : Should contain registers location and length
-- interrupts : Should contain the three timer interrupts with
-  flags for rising edge
-- syscon : a phandle to the global Gemini system controller
-
-Example:
-
-timer@43000000 {
-	compatible = "cortina,gemini-timer";
-	reg = <0x43000000 0x1000>;
-	interrupts = <14 IRQ_TYPE_EDGE_RISING>, /* Timer 1 */
-		   <15 IRQ_TYPE_EDGE_RISING>, /* Timer 2 */
-		   <16 IRQ_TYPE_EDGE_RISING>; /* Timer 3 */
-	syscon = <&syscon>;
-};
diff --git a/Documentation/devicetree/bindings/timer/faraday,fttmr010.txt b/Documentation/devicetree/bindings/timer/faraday,fttmr010.txt
new file mode 100644
index 000000000000..b73ca6cd07f8
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/faraday,fttmr010.txt
@@ -0,0 +1,33 @@
+Faraday Technology timer
+
+This timer is a generic IP block from Faraday Technology, embedded in the
+Cortina Systems Gemini SoCs and other designs.
+
+Required properties:
+
+- compatible : Must be one of
+  "faraday,fttmr010"
+  "cortina,gemini-timer"
+- reg : Should contain registers location and length
+- interrupts : Should contain the three timer interrupts usually with
+  flags for falling edge
+
+Optionally required properties:
+
+- clocks : a clock to provide the tick rate for "faraday,fttmr010"
+- clock-names : should be "EXTCLK" and "PCLK" for the external tick timer
+  and peripheral clock respectively, for "faraday,fttmr010"
+- syscon : a phandle to the global Gemini system controller if the compatible
+  type is "cortina,gemini-timer"
+
+Example:
+
+timer@43000000 {
+	compatible = "faraday,fttmr010";
+	reg = <0x43000000 0x1000>;
+	interrupts = <14 IRQ_TYPE_EDGE_FALLING>, /* Timer 1 */
+		   <15 IRQ_TYPE_EDGE_FALLING>, /* Timer 2 */
+		   <16 IRQ_TYPE_EDGE_FALLING>; /* Timer 3 */
+	clocks = <&extclk>, <&pclk>;
+	clock-names = "EXTCLK", "PCLK";
+};
diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt
index a41b184d5538..16a5f4577a61 100644
--- a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt
+++ b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt
@@ -1,9 +1,15 @@
 Rockchip rk timer
 
 Required properties:
-- compatible: shall be one of:
-  "rockchip,rk3288-timer" - for rk3066, rk3036, rk3188, rk322x, rk3288, rk3368
-  "rockchip,rk3399-timer" - for rk3399
+- compatible: should be:
+  "rockchip,rk3036-timer", "rockchip,rk3288-timer": for Rockchip RK3036
+  "rockchip,rk3066-timer", "rockchip,rk3288-timer": for Rockchip RK3066
+  "rockchip,rk3188-timer", "rockchip,rk3288-timer": for Rockchip RK3188
+  "rockchip,rk3228-timer", "rockchip,rk3288-timer": for Rockchip RK3228
+  "rockchip,rk3229-timer", "rockchip,rk3288-timer": for Rockchip RK3229
+  "rockchip,rk3288-timer": for Rockchip RK3288
+  "rockchip,rk3368-timer", "rockchip,rk3288-timer": for Rockchip RK3368
+  "rockchip,rk3399-timer": for Rockchip RK3399
 - reg: base address of the timer register starting with TIMERS CONTROL register
 - interrupts: should contain the interrupts for Timer0
 - clocks : must contain an entry for each entry in clock-names
diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt
index 0c065f77658f..3957d4edaa74 100644
--- a/Documentation/devicetree/bindings/usb/usb251xb.txt
+++ b/Documentation/devicetree/bindings/usb/usb251xb.txt
@@ -7,18 +7,18 @@ Required properties :
  - compatible : Should be "microchip,usb251xb" or one of the specific types:
 	"microchip,usb2512b", "microchip,usb2512bi", "microchip,usb2513b",
 	"microchip,usb2513bi", "microchip,usb2514b", "microchip,usb2514bi"
- - hub-reset-gpios : Should specify the gpio for hub reset
+ - reset-gpios : Should specify the gpio for hub reset
+ - reg : I2C address on the selected bus (default is <0x2C>)
 
 Optional properties :
- - reg : I2C address on the selected bus (default is <0x2C>)
  - skip-config : Skip Hub configuration, but only send the USB-Attach command
- - vendor-id : USB Vendor ID of the hub (16 bit, default is 0x0424)
- - product-id : USB Product ID of the hub (16 bit, default depends on type)
- - device-id : USB Device ID of the hub (16 bit, default is 0x0bb3)
- - language-id : USB Language ID (16 bit, default is 0x0000)
- - manufacturer : USB Manufacturer string (max 31 characters long)
- - product : USB Product string (max 31 characters long)
- - serial : USB Serial string (max 31 characters long)
+ - vendor-id : Set USB Vendor ID of the hub (16 bit, default is 0x0424)
+ - product-id : Set USB Product ID of the hub (16 bit, default depends on type)
+ - device-id : Set USB Device ID of the hub (16 bit, default is 0x0bb3)
+ - language-id : Set USB Language ID (16 bit, default is 0x0000)
+ - manufacturer : Set USB Manufacturer string (max 31 characters long)
+ - product : Set USB Product string (max 31 characters long)
+ - serial : Set USB Serial string (max 31 characters long)
  - {bus,self}-powered : selects between self- and bus-powered operation (default
 	is self-powered)
  - disable-hi-speed : disable USB Hi-Speed support
@@ -31,8 +31,10 @@ Optional properties :
 	(default is individual)
  - dynamic-power-switching : enable auto-switching from self- to bus-powered
 	operation if the local power source is removed or unavailable
- - oc-delay-{100us,4ms,8ms,16ms} : set over current timer delay (default is 8ms)
- - compound-device : indicated the hub is part of a compound device
+ - oc-delay-us : Delay time (in microseconds) for filtering the over-current
+	sense inputs. Valid values are 100, 4000, 8000 (default) and 16000. If
+	an invalid value is given, the default is used instead.
+ - compound-device : indicate the hub is part of a compound device
  - port-mapping-mode : enable port mapping mode
  - string-support : enable string descriptor support (required for manufacturer,
 	product and serial string configuration)
@@ -40,34 +42,15 @@ Optional properties :
 	device connected.
  - sp-disabled-ports : Specifies the ports which will be self-power disabled
  - bp-disabled-ports : Specifies the ports which will be bus-power disabled
- - max-sp-power : Specifies the maximum current the hub consumes from an
-	upstream port when operating as self-powered hub including the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 2).
- - max-bp-power : Specifies the maximum current the hub consumes from an
-	upstream port when operating as bus-powered hub including the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 100).
- - max-sp-current : Specifies the maximum current the hub consumes from an
-	upstream port when operating as self-powered hub EXCLUDING the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 2).
- - max-bp-current : Specifies the maximum current the hub consumes from an
-	upstream port when operating as bus-powered hub EXCLUDING the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 100).
- - power-on-time : Specifies the time it takes from the time the host initiates
-	the power-on sequence to a port until the port has adequate power. The
-	value is given in ms in a 0 - 510 range (default is 100ms).
+ - power-on-time-ms : Specifies the time it takes from the time the host
+	initiates the power-on sequence to a port until the port has adequate
+	power. The value is given in ms in a 0 - 510 range (default is 100ms).
 
 Examples:
 	usb2512b@2c {
 		compatible = "microchip,usb2512b";
-		hub-reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+		reg = <0x2c>;
+		reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	};
 
 	usb2514b@2c {
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index ec0bfb9bbebd..b685d13539e8 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -51,6 +51,7 @@ brcm	Broadcom Corporation
 buffalo	Buffalo, Inc.
 calxeda	Calxeda
 capella	Capella Microsystems, Inc
+cascoda	Cascoda, Ltd.
 cavium	Cavium, Inc.
 cdns	Cadence Design Systems Inc.
 ceva	Ceva, Inc.
@@ -265,6 +266,7 @@ sbs	Smart Battery System
 schindler	Schindler
 seagate	Seagate Technology PLC
 semtech	Semtech Corporation
+sensirion	Sensirion AG
 sgx	SGX Sensortech
 sharp	Sharp Corporation
 si-en	Si-En Technology Ltd.
diff --git a/Documentation/doc-guide/hello.dot b/Documentation/doc-guide/hello.dot
new file mode 100644
index 000000000000..504621dfc595
--- /dev/null
+++ b/Documentation/doc-guide/hello.dot
@@ -0,0 +1,3 @@
+graph G {
+      Hello -- World
+}
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index 96fe7ccb2c67..731334de3efd 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -34,8 +34,9 @@ format-specific subdirectories under ``Documentation/output``.
 
 To generate documentation, Sphinx (``sphinx-build``) must obviously be
 installed. For prettier HTML output, the Read the Docs Sphinx theme
-(``sphinx_rtd_theme``) is used if available. For PDF output, ``rst2pdf`` is also
-needed. All of these are widely available and packaged in distributions.
+(``sphinx_rtd_theme``) is used if available. For PDF output you'll also need
+``XeLaTeX`` and ``convert(1)`` from ImageMagick (https://www.imagemagick.org).
+All of these are widely available and packaged in distributions.
 
 To pass extra options to Sphinx, you can use the ``SPHINXOPTS`` make
 variable. For example, use ``make SPHINXOPTS=-v htmldocs`` to get more verbose
@@ -73,7 +74,16 @@ Specific guidelines for the kernel documentation
 
 Here are some specific guidelines for the kernel documentation:
 
-* Please don't go overboard with reStructuredText markup. Keep it simple.
+* Please don't go overboard with reStructuredText markup. Keep it
+  simple. For the most part the documentation should be plain text with
+  just enough consistency in formatting that it can be converted to
+  other formats.
+
+* Please keep the formatting changes minimal when converting existing
+  documentation to reStructuredText.
+
+* Also update the content, not just the formatting, when converting
+  documentation.
 
 * Please stick to this order of heading adornments:
 
@@ -103,6 +113,12 @@ Here are some specific guidelines for the kernel documentation:
   the order as encountered."), having the higher levels the same overall makes
   it easier to follow the documents.
 
+* For inserting fixed width text blocks (for code examples, use case
+  examples, etc.), use ``::`` for anything that doesn't really benefit
+  from syntax highlighting, especially short snippets. Use
+  ``.. code-block:: <language>`` for longer code blocks that benefit
+  from highlighting.
+
 
 the C domain
 ------------
@@ -217,3 +233,96 @@ Rendered as:
       * .. _`last row`:
 
         - column 3
+
+
+Figures & Images
+================
+
+If you want to add an image, you should use the ``kernel-figure`` and
+``kernel-image`` directives. E.g. to insert a figure with a scalable
+image format use SVG (:ref:`svg_image_example`)::
+
+    .. kernel-figure::  svg_image.svg
+       :alt:    simple SVG image
+
+       SVG image example
+
+.. _svg_image_example:
+
+.. kernel-figure::  svg_image.svg
+   :alt:    simple SVG image
+
+   SVG image example
+
+The kernel figure (and image) directive support **DOT** formated files, see
+
+* DOT: http://graphviz.org/pdf/dotguide.pdf
+* Graphviz: http://www.graphviz.org/content/dot-language
+
+A simple example (:ref:`hello_dot_file`)::
+
+  .. kernel-figure::  hello.dot
+     :alt:    hello world
+
+     DOT's hello world example
+
+.. _hello_dot_file:
+
+.. kernel-figure::  hello.dot
+   :alt:    hello world
+
+   DOT's hello world example
+
+Embed *render* markups (or languages) like Graphviz's **DOT** is provided by the
+``kernel-render`` directives.::
+
+  .. kernel-render:: DOT
+     :alt: foobar digraph
+     :caption: Embedded **DOT** (Graphviz) code
+
+     digraph foo {
+      "bar" -> "baz";
+     }
+
+How this will be rendered depends on the installed tools. If Graphviz is
+installed, you will see an vector image. If not the raw markup is inserted as
+*literal-block* (:ref:`hello_dot_render`).
+
+.. _hello_dot_render:
+
+.. kernel-render:: DOT
+   :alt: foobar digraph
+   :caption: Embedded **DOT** (Graphviz) code
+
+   digraph foo {
+      "bar" -> "baz";
+   }
+
+The *render* directive has all the options known from the *figure* directive,
+plus option ``caption``.  If ``caption`` has a value, a *figure* node is
+inserted. If not, a *image* node is inserted. A ``caption`` is also needed, if
+you want to refer it (:ref:`hello_svg_render`).
+
+Embedded **SVG**::
+
+  .. kernel-render:: SVG
+     :caption: Embedded **SVG** markup
+     :alt: so-nw-arrow
+
+     <?xml version="1.0" encoding="UTF-8"?>
+     <svg xmlns="http://www.w3.org/2000/svg" version="1.1" ...>
+        ...
+     </svg>
+
+.. _hello_svg_render:
+
+.. kernel-render:: SVG
+   :caption: Embedded **SVG** markup
+   :alt: so-nw-arrow
+
+   <?xml version="1.0" encoding="UTF-8"?>
+   <svg xmlns="http://www.w3.org/2000/svg"
+     version="1.1" baseProfile="full" width="70px" height="40px" viewBox="0 0 700 400">
+   <line x1="180" y1="370" x2="500" y2="50" stroke="black" stroke-width="15px"/>
+   <polygon points="585 0 525 25 585 50" transform="rotate(135 525 25)"/>
+   </svg>
diff --git a/Documentation/doc-guide/svg_image.svg b/Documentation/doc-guide/svg_image.svg
new file mode 100644
index 000000000000..5405f85b8137
--- /dev/null
+++ b/Documentation/doc-guide/svg_image.svg
@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- originate: https://commons.wikimedia.org/wiki/File:Variable_Resistor.svg -->
+<svg xmlns="http://www.w3.org/2000/svg"
+	version="1.1" baseProfile="full"
+	width="70px" height="40px" viewBox="0 0 700 400">
+	<line x1="0" y1="200" x2="700" y2="200" stroke="black" stroke-width="20px"/>
+	<rect x="100" y="100" width="500" height="200" fill="white" stroke="black" stroke-width="20px"/>
+	<line x1="180" y1="370" x2="500" y2="50" stroke="black" stroke-width="15px"/>
+	<polygon points="585 0 525 25 585 50" transform="rotate(135 525 25)"/>
+</svg>
diff --git a/Documentation/driver-api/80211/cfg80211.rst b/Documentation/driver-api/80211/cfg80211.rst
index eca534ab6172..8ffac57e1f5b 100644
--- a/Documentation/driver-api/80211/cfg80211.rst
+++ b/Documentation/driver-api/80211/cfg80211.rst
@@ -2,6 +2,9 @@
 cfg80211 subsystem
 ==================
 
+.. kernel-doc:: include/net/cfg80211.h
+   :doc: Introduction
+
 Device registration
 ===================
 
@@ -180,6 +183,12 @@ Actions and configuration
    :functions: cfg80211_ibss_joined
 
 .. kernel-doc:: include/net/cfg80211.h
+   :functions: cfg80211_connect_resp_params
+
+.. kernel-doc:: include/net/cfg80211.h
+   :functions: cfg80211_connect_done
+
+.. kernel-doc:: include/net/cfg80211.h
    :functions: cfg80211_connect_result
 
 .. kernel-doc:: include/net/cfg80211.h
diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst
index 935b9b8d456c..472e7a664d13 100644
--- a/Documentation/driver-api/basics.rst
+++ b/Documentation/driver-api/basics.rst
@@ -7,6 +7,12 @@ Driver Entry and Exit points
 .. kernel-doc:: include/linux/init.h
    :internal:
 
+Driver device table
+-------------------
+
+.. kernel-doc:: include/linux/mod_devicetable.h
+   :internal:
+
 Atomic and pointer manipulation
 -------------------------------
 
diff --git a/Documentation/driver-api/firmware/index.rst b/Documentation/driver-api/firmware/index.rst
index 1abe01793031..29da39ec4b8a 100644
--- a/Documentation/driver-api/firmware/index.rst
+++ b/Documentation/driver-api/firmware/index.rst
@@ -7,6 +7,7 @@ Linux Firmware API
    introduction
    core
    request_firmware
+   other_interfaces
 
 .. only::  subproject and html
 
diff --git a/Documentation/driver-api/firmware/other_interfaces.rst b/Documentation/driver-api/firmware/other_interfaces.rst
new file mode 100644
index 000000000000..36c47b1e9824
--- /dev/null
+++ b/Documentation/driver-api/firmware/other_interfaces.rst
@@ -0,0 +1,15 @@
+Other Firmware Interfaces
+=========================
+
+DMI Interfaces
+--------------
+
+.. kernel-doc:: drivers/firmware/dmi_scan.c
+   :export:
+
+EDD Interfaces
+--------------
+
+.. kernel-doc:: drivers/firmware/edd.c
+   :internal:
+
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 60db00d1532b..8058a87c1c74 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -26,7 +26,8 @@ available subsections can be seen below.
    regulator
    iio/index
    input
-   usb
+   usb/index
+   pci
    spi
    i2c
    hsi
@@ -36,6 +37,7 @@ available subsections can be seen below.
    80211/index
    uio-howto
    firmware/index
+   misc_devices
 
 .. only::  subproject and html
 
diff --git a/Documentation/driver-api/misc_devices.rst b/Documentation/driver-api/misc_devices.rst
new file mode 100644
index 000000000000..c7ee7b02ba88
--- /dev/null
+++ b/Documentation/driver-api/misc_devices.rst
@@ -0,0 +1,5 @@
+Miscellaneous Devices
+=====================
+
+.. kernel-doc:: drivers/char/misc.c
+   :export:
diff --git a/Documentation/driver-api/pci.rst b/Documentation/driver-api/pci.rst
new file mode 100644
index 000000000000..01a6c8b7d3a7
--- /dev/null
+++ b/Documentation/driver-api/pci.rst
@@ -0,0 +1,50 @@
+PCI Support Library
+-------------------
+
+.. kernel-doc:: drivers/pci/pci.c
+   :export:
+
+.. kernel-doc:: drivers/pci/pci-driver.c
+   :export:
+
+.. kernel-doc:: drivers/pci/remove.c
+   :export:
+
+.. kernel-doc:: drivers/pci/search.c
+   :export:
+
+.. kernel-doc:: drivers/pci/msi.c
+   :export:
+
+.. kernel-doc:: drivers/pci/bus.c
+   :export:
+
+.. kernel-doc:: drivers/pci/access.c
+   :export:
+
+.. kernel-doc:: drivers/pci/irq.c
+   :export:
+
+.. kernel-doc:: drivers/pci/htirq.c
+   :export:
+
+.. kernel-doc:: drivers/pci/probe.c
+   :export:
+
+.. kernel-doc:: drivers/pci/slot.c
+   :export:
+
+.. kernel-doc:: drivers/pci/rom.c
+   :export:
+
+.. kernel-doc:: drivers/pci/iov.c
+   :export:
+
+.. kernel-doc:: drivers/pci/pci-sysfs.c
+   :internal:
+
+PCI Hotplug Support Library
+---------------------------
+
+.. kernel-doc:: drivers/pci/hotplug/pci_hotplug_core.c
+   :export:
diff --git a/Documentation/usb/URB.txt b/Documentation/driver-api/usb/URB.rst
index 50da0d455444..61a54da9fce9 100644
--- a/Documentation/usb/URB.txt
+++ b/Documentation/driver-api/usb/URB.rst
@@ -1,28 +1,37 @@
-Revised: 2000-Dec-05.
-Again:   2002-Jul-06
-Again:   2005-Sep-19
+.. _usb-urb:
 
-    NOTE:
+USB Request Block (URB)
+~~~~~~~~~~~~~~~~~~~~~~~
 
-    The USB subsystem now has a substantial section in "The Linux Kernel API"
-    guide (in Documentation/DocBook), generated from the current source
-    code.  This particular documentation file isn't particularly current or
-    complete; don't rely on it except for a quick overview.
+:Revised: 2000-Dec-05
+:Again:   2002-Jul-06
+:Again:   2005-Sep-19
+:Again:   2017-Mar-29
 
 
-1.1. Basic concept or 'What is an URB?'
+.. note::
 
-The basic idea of the new driver is message passing, the message itself is 
-called USB Request Block, or URB for short. 
+    The USB subsystem now has a substantial section at :ref:`usb-hostside-api`
+    section, generated from the current source code.
+    This particular documentation file isn't complete and may not be
+    updated to the last version; don't rely on it except for a quick
+    overview.
 
-- An URB consists of all relevant information to execute any USB transaction 
-  and deliver the data and status back. 
+Basic concept or 'What is an URB?'
+==================================
 
-- Execution of an URB is inherently an asynchronous operation, i.e. the 
-  usb_submit_urb(urb) call returns immediately after it has successfully
+The basic idea of the new driver is message passing, the message itself is
+called USB Request Block, or URB for short.
+
+- An URB consists of all relevant information to execute any USB transaction
+  and deliver the data and status back.
+
+- Execution of an URB is inherently an asynchronous operation, i.e. the
+  :c:func:`usb_submit_urb` call returns immediately after it has successfully
   queued the requested action.
 
-- Transfers for one URB can be canceled with usb_unlink_urb(urb) at any time. 
+- Transfers for one URB can be canceled with :c:func:`usb_unlink_urb`
+  at any time.
 
 - Each URB has a completion handler, which is called after the action
   has been successfully completed or canceled. The URB also contains a
@@ -35,53 +44,55 @@ called USB Request Block, or URB for short.
   of data to (or from) devices when using periodic transfer modes.
 
 
-1.2. The URB structure
+The URB structure
+=================
 
-Some of the fields in an URB are:
+Some of the fields in struct :c:type:`urb` are::
 
-struct urb
-{
-// (IN) device and pipe specify the endpoint queue
+  struct urb
+  {
+  // (IN) device and pipe specify the endpoint queue
 	struct usb_device *dev;         // pointer to associated USB device
 	unsigned int pipe;              // endpoint information
 
-	unsigned int transfer_flags;    // ISO_ASAP, SHORT_NOT_OK, etc.
+	unsigned int transfer_flags;    // URB_ISO_ASAP, URB_SHORT_NOT_OK, etc.
 
-// (IN) all urbs need completion routines
+  // (IN) all urbs need completion routines
 	void *context;                  // context for completion routine
-	void (*complete)(struct urb *); // pointer to completion routine
+	usb_complete_t complete;        // pointer to completion routine
 
-// (OUT) status after each completion
+  // (OUT) status after each completion
 	int status;                     // returned status
 
-// (IN) buffer used for data transfers
+  // (IN) buffer used for data transfers
 	void *transfer_buffer;          // associated data buffer
-	int transfer_buffer_length;     // data buffer length
+	u32 transfer_buffer_length;     // data buffer length
 	int number_of_packets;          // size of iso_frame_desc
 
-// (OUT) sometimes only part of CTRL/BULK/INTR transfer_buffer is used
-	int actual_length;              // actual data buffer length
+  // (OUT) sometimes only part of CTRL/BULK/INTR transfer_buffer is used
+	u32 actual_length;              // actual data buffer length
 
-// (IN) setup stage for CTRL (pass a struct usb_ctrlrequest)
-	unsigned char* setup_packet;    // setup packet (control only)
+  // (IN) setup stage for CTRL (pass a struct usb_ctrlrequest)
+	unsigned char *setup_packet;    // setup packet (control only)
 
-// Only for PERIODIC transfers (ISO, INTERRUPT)
-    // (IN/OUT) start_frame is set unless ISO_ASAP isn't set
+  // Only for PERIODIC transfers (ISO, INTERRUPT)
+    // (IN/OUT) start_frame is set unless URB_ISO_ASAP isn't set
 	int start_frame;                // start frame
 	int interval;                   // polling interval
 
     // ISO only: packets are only "best effort"; each can have errors
 	int error_count;                // number of errors
 	struct usb_iso_packet_descriptor iso_frame_desc[0];
-};
+  };
 
 Your driver must create the "pipe" value using values from the appropriate
 endpoint descriptor in an interface that it's claimed.
 
 
-1.3. How to get an URB?
+How to get an URB?
+==================
 
-URBs are allocated with the following call
+URBs are allocated by calling :c:func:`usb_alloc_urb`::
 
 	struct urb *usb_alloc_urb(int isoframes, int mem_flags)
 
@@ -91,7 +102,7 @@ you want to schedule. For CTRL/BULK/INT, use 0.  The mem_flags parameter
 holds standard memory allocation flags, letting you control (among other
 things) whether the underlying code may block or not.
 
-To free an URB, use
+To free an URB, use :c:func:`usb_free_urb`::
 
 	void usb_free_urb(struct urb *urb)
 
@@ -100,78 +111,84 @@ returned to you in a completion callback.  It will automatically be
 deallocated when it is no longer in use.
 
 
-1.4. What has to be filled in?
+What has to be filled in?
+=========================
 
-Depending on the type of transaction, there are some inline functions 
-defined in <linux/usb.h> to simplify the initialization, such as
-fill_control_urb() and fill_bulk_urb().  In general, they need the usb
-device pointer, the pipe (usual format from usb.h), the transfer buffer,
-the desired transfer length, the completion  handler, and its context. 
-Take a look at the some existing drivers to see how they're used.
+Depending on the type of transaction, there are some inline functions
+defined in ``linux/usb.h`` to simplify the initialization, such as
+:c:func:`usb_fill_control_urb`, :c:func:`usb_fill_bulk_urb` and
+:c:func:`usb_fill_int_urb`.  In general, they need the usb device pointer,
+the pipe (usual format from usb.h), the transfer buffer, the desired transfer
+length, the completion handler, and its context. Take a look at the some
+existing drivers to see how they're used.
 
 Flags:
-For ISO there are two startup behaviors: Specified start_frame or ASAP.
-For ASAP set URB_ISO_ASAP in transfer_flags.
 
-If short packets should NOT be tolerated, set URB_SHORT_NOT_OK in 
+- For ISO there are two startup behaviors: Specified start_frame or ASAP.
+- For ASAP set ``URB_ISO_ASAP`` in transfer_flags.
+
+If short packets should NOT be tolerated, set ``URB_SHORT_NOT_OK`` in
 transfer_flags.
 
 
-1.5. How to submit an URB?
+How to submit an URB?
+=====================
 
-Just call
+Just call :c:func:`usb_submit_urb`::
 
 	int usb_submit_urb(struct urb *urb, int mem_flags)
 
-The mem_flags parameter, such as SLAB_ATOMIC, controls memory allocation,
-such as whether the lower levels may block when memory is tight.
+The ``mem_flags`` parameter, such as ``GFP_ATOMIC``, controls memory
+allocation, such as whether the lower levels may block when memory is tight.
 
 It immediately returns, either with status 0 (request queued) or some
 error code, usually caused by the following:
 
-- Out of memory (-ENOMEM)
-- Unplugged device (-ENODEV)
-- Stalled endpoint (-EPIPE)
-- Too many queued ISO transfers (-EAGAIN)
-- Too many requested ISO frames (-EFBIG)
-- Invalid INT interval (-EINVAL)
-- More than one packet for INT (-EINVAL)
+- Out of memory (``-ENOMEM``)
+- Unplugged device (``-ENODEV``)
+- Stalled endpoint (``-EPIPE``)
+- Too many queued ISO transfers (``-EAGAIN``)
+- Too many requested ISO frames (``-EFBIG``)
+- Invalid INT interval (``-EINVAL``)
+- More than one packet for INT (``-EINVAL``)
 
-After submission, urb->status is -EINPROGRESS; however, you should never
-look at that value except in your completion callback.
+After submission, ``urb->status`` is ``-EINPROGRESS``; however, you should
+never look at that value except in your completion callback.
 
 For isochronous endpoints, your completion handlers should (re)submit
-URBs to the same endpoint with the ISO_ASAP flag, using multi-buffering,
-to get seamless ISO streaming.
+URBs to the same endpoint with the ``URB_ISO_ASAP`` flag, using
+multi-buffering, to get seamless ISO streaming.
 
 
-1.6. How to cancel an already running URB?
+How to cancel an already running URB?
+=====================================
 
 There are two ways to cancel an URB you've submitted but which hasn't
 been returned to your driver yet.  For an asynchronous cancel, call
+:c:func:`usb_unlink_urb`::
 
 	int usb_unlink_urb(struct urb *urb)
 
 It removes the urb from the internal list and frees all allocated
 HW descriptors. The status is changed to reflect unlinking.  Note
-that the URB will not normally have finished when usb_unlink_urb()
+that the URB will not normally have finished when :c:func:`usb_unlink_urb`
 returns; you must still wait for the completion handler to be called.
 
-To cancel an URB synchronously, call
+To cancel an URB synchronously, call :c:func:`usb_kill_urb`::
 
 	void usb_kill_urb(struct urb *urb)
 
-It does everything usb_unlink_urb does, and in addition it waits
+It does everything :c:func:`usb_unlink_urb` does, and in addition it waits
 until after the URB has been returned and the completion handler
 has finished.  It also marks the URB as temporarily unusable, so
 that if the completion handler or anyone else tries to resubmit it
-they will get a -EPERM error.  Thus you can be sure that when
-usb_kill_urb() returns, the URB is totally idle.
+they will get a ``-EPERM`` error.  Thus you can be sure that when
+:c:func:`usb_kill_urb` returns, the URB is totally idle.
 
 There is a lifetime issue to consider.  An URB may complete at any
 time, and the completion handler may free the URB.  If this happens
-while usb_unlink_urb or usb_kill_urb is running, it will cause a
-memory-access violation.  The driver is responsible for avoiding this,
+while :c:func:`usb_unlink_urb` or :c:func:`usb_kill_urb` is running, it will
+cause a memory-access violation.  The driver is responsible for avoiding this,
 which often means some sort of lock will be needed to prevent the URB
 from being deallocated while it is still in use.
 
@@ -181,24 +198,25 @@ when usb_unlink_urb is invoked.  The general solution to this problem
 is to increment the URB's reference count while holding the lock, then
 drop the lock and call usb_unlink_urb or usb_kill_urb, and then
 decrement the URB's reference count.  You increment the reference
-count by calling
+count by calling :c:func`usb_get_urb`::
 
 	struct urb *usb_get_urb(struct urb *urb)
 
 (ignore the return value; it is the same as the argument) and
-decrement the reference count by calling usb_free_urb.  Of course,
+decrement the reference count by calling :c:func:`usb_free_urb`.  Of course,
 none of this is necessary if there's no danger of the URB being freed
 by the completion handler.
 
 
-1.7. What about the completion handler?
+What about the completion handler?
+==================================
 
-The handler is of the following type:
+The handler is of the following type::
 
 	typedef void (*usb_complete_t)(struct urb *)
 
 I.e., it gets the URB that caused the completion call. In the completion
-handler, you should have a look at urb->status to detect any USB errors.
+handler, you should have a look at ``urb->status`` to detect any USB errors.
 Since the context parameter is included in the URB, you can pass
 information to the completion handler.
 
@@ -208,54 +226,65 @@ sixteen packets to transfer your 1KByte buffer, and ten of them might
 have transferred successfully before the completion was called.
 
 
-NOTE:  ***** WARNING *****
-NEVER SLEEP IN A COMPLETION HANDLER.  These are often called in atomic
-context.
+.. warning::
+
+   NEVER SLEEP IN A COMPLETION HANDLER.
+
+   These are often called in atomic context.
 
 In the current kernel, completion handlers run with local interrupts
 disabled, but in the future this will be changed, so don't assume that
 local IRQs are always disabled inside completion handlers.
 
-1.8. How to do isochronous (ISO) transfers?
+How to do isochronous (ISO) transfers?
+======================================
+
+Besides the fields present on a bulk transfer, for ISO, you also
+also have to set ``urb->interval`` to say how often to make transfers; it's
+often one per frame (which is once every microframe for highspeed devices).
+The actual interval used will be a power of two that's no bigger than what
+you specify. You can use the :c:func:`usb_fill_int_urb` macro to fill
+most ISO transfer fields.
 
-For ISO transfers you have to fill a usb_iso_packet_descriptor structure,
-allocated at the end of the URB by usb_alloc_urb(n,mem_flags), for each
-packet you want to schedule.   You also have to set urb->interval to say
-how often to make transfers; it's often one per frame (which is once
-every microframe for highspeed devices).  The actual interval used will
-be a power of two that's no bigger than what you specify.
+For ISO transfers you also have to fill a :c:type:`usb_iso_packet_descriptor`
+structure, allocated at the end of the URB by :c:func:`usb_alloc_urb`, for
+each packet you want to schedule.
 
-The usb_submit_urb() call modifies urb->interval to the implemented interval
-value that is less than or equal to the requested interval value.  If
-ISO_ASAP scheduling is used, urb->start_frame is also updated.
+The :c:func:`usb_submit_urb` call modifies ``urb->interval`` to the implemented
+interval value that is less than or equal to the requested interval value.  If
+``URB_ISO_ASAP`` scheduling is used, ``urb->start_frame`` is also updated.
 
 For each entry you have to specify the data offset for this frame (base is
 transfer_buffer), and the length you want to write/expect to read.
-After completion, actual_length contains the actual transferred length and 
+After completion, actual_length contains the actual transferred length and
 status contains the resulting status for the ISO transfer for this frame.
 It is allowed to specify a varying length from frame to frame (e.g. for
-audio synchronisation/adaptive transfer rates). You can also use the length 
+audio synchronisation/adaptive transfer rates). You can also use the length
 0 to omit one or more frames (striping).
 
-For scheduling you can choose your own start frame or ISO_ASAP. As explained
-earlier, if you always keep at least one URB queued and your completion
-keeps (re)submitting a later URB, you'll get smooth ISO streaming (if usb
-bandwidth utilization allows).
+For scheduling you can choose your own start frame or ``URB_ISO_ASAP``. As
+explained earlier, if you always keep at least one URB queued and your
+completion keeps (re)submitting a later URB, you'll get smooth ISO streaming
+(if usb bandwidth utilization allows).
 
 If you specify your own start frame, make sure it's several frames in advance
 of the current frame.  You might want this model if you're synchronizing
 ISO data with some other event stream.
 
 
-1.9. How to start interrupt (INT) transfers?
+How to start interrupt (INT) transfers?
+=======================================
 
 Interrupt transfers, like isochronous transfers, are periodic, and happen
 in intervals that are powers of two (1, 2, 4 etc) units.  Units are frames
 for full and low speed devices, and microframes for high speed ones.
-The usb_submit_urb() call modifies urb->interval to the implemented interval
-value that is less than or equal to the requested interval value.
+You can use the :c:func:`usb_fill_int_urb` macro to fill INT transfer fields.
+
+The :c:func:`usb_submit_urb` call modifies ``urb->interval`` to the implemented
+interval value that is less than or equal to the requested interval value.
 
 In Linux 2.6, unlike earlier versions, interrupt URBs are not automagically
 restarted when they complete.  They end when the completion handler is
 called, just like other URBs.  If you want an interrupt URB to be restarted,
 your completion handler must resubmit it.
+s
diff --git a/Documentation/usb/anchors.txt b/Documentation/driver-api/usb/anchors.rst
index fe6a99a32bbd..4b248e691bd6 100644
--- a/Documentation/usb/anchors.txt
+++ b/Documentation/driver-api/usb/anchors.rst
@@ -1,3 +1,6 @@
+USB Anchors
+~~~~~~~~~~~
+
 What is anchor?
 ===============
 
@@ -13,7 +16,7 @@ Allocation and Initialisation
 =============================
 
 There's no API to allocate an anchor. It is simply declared
-as struct usb_anchor. init_usb_anchor() must be called to
+as struct usb_anchor. :c:func:`init_usb_anchor` must be called to
 initialise the data structure.
 
 Deallocation
@@ -26,52 +29,53 @@ Association and disassociation of URBs with anchors
 ===================================================
 
 An association of URBs to an anchor is made by an explicit
-call to usb_anchor_urb(). The association is maintained until
+call to :c:func:`usb_anchor_urb`. The association is maintained until
 an URB is finished by (successful) completion. Thus disassociation
 is automatic. A function is provided to forcibly finish (kill)
 all URBs associated with an anchor.
-Furthermore, disassociation can be made with usb_unanchor_urb()
+Furthermore, disassociation can be made with :c:func:`usb_unanchor_urb`
 
 Operations on multitudes of URBs
 ================================
 
-usb_kill_anchored_urbs()
-------------------------
+:c:func:`usb_kill_anchored_urbs`
+--------------------------------
 
 This function kills all URBs associated with an anchor. The URBs
 are called in the reverse temporal order they were submitted.
 This way no data can be reordered.
 
-usb_unlink_anchored_urbs()
---------------------------
+:c:func:`usb_unlink_anchored_urbs`
+----------------------------------
+
 
 This function unlinks all URBs associated with an anchor. The URBs
 are processed in the reverse temporal order they were submitted.
-This is similar to usb_kill_anchored_urbs(), but it will not sleep.
+This is similar to :c:func:`usb_kill_anchored_urbs`, but it will not sleep.
 Therefore no guarantee is made that the URBs have been unlinked when
 the call returns. They may be unlinked later but will be unlinked in
 finite time.
 
-usb_scuttle_anchored_urbs()
----------------------------
+:c:func:`usb_scuttle_anchored_urbs`
+-----------------------------------
 
 All URBs of an anchor are unanchored en masse.
 
-usb_wait_anchor_empty_timeout()
--------------------------------
+:c:func:`usb_wait_anchor_empty_timeout`
+---------------------------------------
 
 This function waits for all URBs associated with an anchor to finish
 or a timeout, whichever comes first. Its return value will tell you
 whether the timeout was reached.
 
-usb_anchor_empty()
-------------------
+:c:func:`usb_anchor_empty`
+--------------------------
 
 Returns true if no URBs are associated with an anchor. Locking
 is the caller's responsibility.
 
-usb_get_from_anchor()
----------------------
+:c:func:`usb_get_from_anchor`
+-----------------------------
 
 Returns the oldest anchored URB of an anchor. The URB is unanchored
 and returned with a reference. As you may mix URBs to several
diff --git a/Documentation/usb/bulk-streams.txt b/Documentation/driver-api/usb/bulk-streams.rst
index ffc02021863e..99b515babdeb 100644
--- a/Documentation/usb/bulk-streams.txt
+++ b/Documentation/driver-api/usb/bulk-streams.rst
@@ -1,3 +1,6 @@
+USB bulk streams
+~~~~~~~~~~~~~~~~
+
 Background
 ==========
 
@@ -25,7 +28,9 @@ time.
 Driver implications
 ===================
 
-int usb_alloc_streams(struct usb_interface *interface,
+::
+
+  int usb_alloc_streams(struct usb_interface *interface,
 		struct usb_host_endpoint **eps, unsigned int num_eps,
 		unsigned int num_streams, gfp_t mem_flags);
 
@@ -53,7 +58,7 @@ controller driver, and may change in the future.
 
 
 Picking new Stream IDs to use
-============================
+=============================
 
 Stream ID 0 is reserved, and should not be used to communicate with devices.  If
 usb_alloc_streams() returns with a value of N, you may use streams 1 though N.
@@ -68,9 +73,9 @@ Clean up
 ========
 
 If a driver wishes to stop using streams to communicate with the device, it
-should call
+should call::
 
-void usb_free_streams(struct usb_interface *interface,
+  void usb_free_streams(struct usb_interface *interface,
 		struct usb_host_endpoint **eps, unsigned int num_eps,
 		gfp_t mem_flags);
 
diff --git a/Documentation/usb/callbacks.txt b/Documentation/driver-api/usb/callbacks.rst
index 9e85846bdb98..2b80cf54bcc3 100644
--- a/Documentation/usb/callbacks.txt
+++ b/Documentation/driver-api/usb/callbacks.rst
@@ -1,3 +1,6 @@
+USB core callbacks
+~~~~~~~~~~~~~~~~~~
+
 What callbacks will usbcore do?
 ===============================
 
@@ -5,40 +8,52 @@ Usbcore will call into a driver through callbacks defined in the driver
 structure and through the completion handler of URBs a driver submits.
 Only the former are in the scope of this document. These two kinds of
 callbacks are completely independent of each other. Information on the
-completion callback can be found in Documentation/usb/URB.txt.
+completion callback can be found in :ref:`usb-urb`.
 
 The callbacks defined in the driver structure are:
 
 1. Hotplugging callbacks:
 
- * @probe: Called to see if the driver is willing to manage a particular
- *	interface on a device.
- * @disconnect: Called when the interface is no longer accessible, usually
- *	because its device has been (or is being) disconnected or the
- *	driver module is being unloaded.
+ - @probe:
+	Called to see if the driver is willing to manage a particular
+	interface on a device.
+
+ - @disconnect:
+	Called when the interface is no longer accessible, usually
+	because its device has been (or is being) disconnected or the
+	driver module is being unloaded.
 
 2. Odd backdoor through usbfs:
 
- * @ioctl: Used for drivers that want to talk to userspace through
- *	the "usbfs" filesystem.  This lets devices provide ways to
- *	expose information to user space regardless of where they
- *	do (or don't) show up otherwise in the filesystem.
+ - @ioctl:
+	Used for drivers that want to talk to userspace through
+	the "usbfs" filesystem.  This lets devices provide ways to
+	expose information to user space regardless of where they
+	do (or don't) show up otherwise in the filesystem.
 
 3. Power management (PM) callbacks:
 
- * @suspend: Called when the device is going to be suspended.
- * @resume: Called when the device is being resumed.
- * @reset_resume: Called when the suspended device has been reset instead
- *	of being resumed.
+ - @suspend:
+	Called when the device is going to be suspended.
+
+ - @resume:
+	Called when the device is being resumed.
+
+ - @reset_resume:
+	Called when the suspended device has been reset instead
+	of being resumed.
 
 4. Device level operations:
 
- * @pre_reset: Called when the device is about to be reset.
- * @post_reset: Called after the device has been reset
+ - @pre_reset:
+	Called when the device is about to be reset.
+
+ - @post_reset:
+	Called after the device has been reset
 
 The ioctl interface (2) should be used only if you have a very good
 reason. Sysfs is preferred these days. The PM callbacks are covered
-separately in Documentation/usb/power-management.txt.
+separately in :ref:`usb-power-management`.
 
 Calling conventions
 ===================
@@ -58,7 +73,9 @@ an interface. A driver's bond to an interface is exclusive.
 The probe() callback
 --------------------
 
-int (*probe) (struct usb_interface *intf,
+::
+
+  int (*probe) (struct usb_interface *intf,
 		const struct usb_device_id *id);
 
 Accept or decline an interface. If you accept the device return 0,
@@ -75,7 +92,9 @@ initialisation that doesn't take too long is a good idea here.
 The disconnect() callback
 -------------------------
 
-void (*disconnect) (struct usb_interface *intf);
+::
+
+  void (*disconnect) (struct usb_interface *intf);
 
 This callback is a signal to break any connection with an interface.
 You are not allowed any IO to a device after returning from this
@@ -93,7 +112,9 @@ Device level callbacks
 pre_reset
 ---------
 
-int (*pre_reset)(struct usb_interface *intf);
+::
+
+  int (*pre_reset)(struct usb_interface *intf);
 
 A driver or user space is triggering a reset on the device which
 contains the interface passed as an argument. Cease IO, wait for all
@@ -107,7 +128,9 @@ are in atomic context.
 post_reset
 ----------
 
-int (*post_reset)(struct usb_interface *intf);
+::
+
+  int (*post_reset)(struct usb_interface *intf);
 
 The reset has completed.  Restore any saved device state and begin
 using the device again.
diff --git a/Documentation/usb/dma.txt b/Documentation/driver-api/usb/dma.rst
index 444651e70d95..59d5aee89e37 100644
--- a/Documentation/usb/dma.txt
+++ b/Documentation/driver-api/usb/dma.rst
@@ -1,16 +1,19 @@
+USB DMA
+~~~~~~~
+
 In Linux 2.5 kernels (and later), USB device drivers have additional control
 over how DMA may be used to perform I/O operations.  The APIs are detailed
 in the kernel usb programming guide (kerneldoc, from the source code).
 
-
-API OVERVIEW
+API overview
+============
 
 The big picture is that USB drivers can continue to ignore most DMA issues,
 though they still must provide DMA-ready buffers (see
-Documentation/DMA-API-HOWTO.txt).  That's how they've worked through
-the 2.4 (and earlier) kernels.
+``Documentation/DMA-API-HOWTO.txt``).  That's how they've worked through
+the 2.4 (and earlier) kernels, or they can now be DMA-aware.
 
-OR:  they can now be DMA-aware.
+DMA-aware usb drivers:
 
 - New calls enable DMA-aware drivers, letting them allocate dma buffers and
   manage dma mappings for existing dma-ready buffers (see below).
@@ -20,15 +23,15 @@ OR:  they can now be DMA-aware.
   drivers must not use it.)
 
 - "usbcore" will map this DMA address, if a DMA-aware driver didn't do
-  it first and set URB_NO_TRANSFER_DMA_MAP.  HCDs
+  it first and set ``URB_NO_TRANSFER_DMA_MAP``.  HCDs
   don't manage dma mappings for URBs.
 
 - There's a new "generic DMA API", parts of which are usable by USB device
   drivers.  Never use dma_set_mask() on any USB interface or device; that
   would potentially break all devices sharing that bus.
 
-
-ELIMINATING COPIES
+Eliminating copies
+==================
 
 It's good to avoid making CPUs copy data needlessly.  The costs can add up,
 and effects like cache-trashing can impose subtle penalties.
@@ -41,7 +44,7 @@ and effects like cache-trashing can impose subtle penalties.
   For those specific cases, USB has primitives to allocate less expensive
   memory.  They work like kmalloc and kfree versions that give you the right
   kind of addresses to store in urb->transfer_buffer and urb->transfer_dma.
-  You'd also set URB_NO_TRANSFER_DMA_MAP in urb->transfer_flags:
+  You'd also set ``URB_NO_TRANSFER_DMA_MAP`` in urb->transfer_flags::
 
 	void *usb_alloc_coherent (struct usb_device *dev, size_t size,
 		int mem_flags, dma_addr_t *dma);
@@ -49,15 +52,15 @@ and effects like cache-trashing can impose subtle penalties.
 	void usb_free_coherent (struct usb_device *dev, size_t size,
 		void *addr, dma_addr_t dma);
 
-  Most drivers should *NOT* be using these primitives; they don't need
+  Most drivers should **NOT** be using these primitives; they don't need
   to use this type of memory ("dma-coherent"), and memory returned from
-  kmalloc() will work just fine.
+  :c:func:`kmalloc` will work just fine.
 
   The memory buffer returned is "dma-coherent"; sometimes you might need to
   force a consistent memory access ordering by using memory barriers.  It's
   not using a streaming DMA mapping, so it's good for small transfers on
   systems where the I/O would otherwise thrash an IOMMU mapping.  (See
-  Documentation/DMA-API-HOWTO.txt for definitions of "coherent" and
+  ``Documentation/DMA-API-HOWTO.txt`` for definitions of "coherent" and
   "streaming" DMA mappings.)
 
   Asking for 1/Nth of a page (as well as asking for N pages) is reasonably
@@ -75,15 +78,15 @@ and effects like cache-trashing can impose subtle penalties.
   way to expose these capabilities ... and in any case, HIGHMEM is mostly a
   design wart specific to x86_32.  So your best bet is to ensure you never
   pass a highmem buffer into a USB driver.  That's easy; it's the default
-  behavior.  Just don't override it; e.g. with NETIF_F_HIGHDMA.
+  behavior.  Just don't override it; e.g. with ``NETIF_F_HIGHDMA``.
 
   This may force your callers to do some bounce buffering, copying from
   high memory to "normal" DMA memory.  If you can come up with a good way
   to fix this issue (for x86_32 machines with over 1 GByte of memory),
   feel free to submit patches.
 
-
-WORKING WITH EXISTING BUFFERS
+Working with existing buffers
+=============================
 
 Existing buffers aren't usable for DMA without first being mapped into the
 DMA address space of the device.  However, most buffers passed to your
@@ -92,7 +95,7 @@ of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
 
 - When you're using scatterlists, you can map everything at once.  On some
   systems, this kicks in an IOMMU and turns the scatterlists into single
-  DMA transactions:
+  DMA transactions::
 
 	int usb_buffer_map_sg (struct usb_device *dev, unsigned pipe,
 		struct scatterlist *sg, int nents);
@@ -103,7 +106,7 @@ of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
 	void usb_buffer_unmap_sg (struct usb_device *dev, unsigned pipe,
 		struct scatterlist *sg, int n_hw_ents);
 
-  It's probably easier to use the new usb_sg_*() calls, which do the DMA
+  It's probably easier to use the new ``usb_sg_*()`` calls, which do the DMA
   mapping and apply other tweaks to make scatterlist i/o be fast.
 
 - Some drivers may prefer to work with the model that they're mapping large
@@ -112,10 +115,10 @@ of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
   here, since it's cheaper to just synchronize the buffer than to unmap it
   each time an urb completes and then re-map it on during resubmission.
 
-  These calls all work with initialized urbs:  urb->dev, urb->pipe,
-  urb->transfer_buffer, and urb->transfer_buffer_length must all be
-  valid when these calls are used (urb->setup_packet must be valid too
-  if urb is a control request):
+  These calls all work with initialized urbs:  ``urb->dev``, ``urb->pipe``,
+  ``urb->transfer_buffer``, and ``urb->transfer_buffer_length`` must all be
+  valid when these calls are used (``urb->setup_packet`` must be valid too
+  if urb is a control request)::
 
 	struct urb *usb_buffer_map (struct urb *urb);
 
@@ -123,9 +126,9 @@ of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
 
 	void usb_buffer_unmap (struct urb *urb);
 
-  The calls manage urb->transfer_dma for you, and set URB_NO_TRANSFER_DMA_MAP
-  so that usbcore won't map or unmap the buffer.  They cannot be used for
-  setup_packet buffers in control requests.
+  The calls manage ``urb->transfer_dma`` for you, and set
+  ``URB_NO_TRANSFER_DMA_MAP`` so that usbcore won't map or unmap the buffer.
+  They cannot be used for setup_packet buffers in control requests.
 
 Note that several of those interfaces are currently commented out, since
 they don't have current users.  See the source code.  Other than the dmasync
diff --git a/Documentation/driver-api/usb/error-codes.rst b/Documentation/driver-api/usb/error-codes.rst
new file mode 100644
index 000000000000..a3e84bfac776
--- /dev/null
+++ b/Documentation/driver-api/usb/error-codes.rst
@@ -0,0 +1,207 @@
+.. _usb-error-codes:
+
+USB Error codes
+~~~~~~~~~~~~~~~
+
+:Revised: 2004-Oct-21
+
+This is the documentation of (hopefully) all possible error codes (and
+their interpretation) that can be returned from usbcore.
+
+Some of them are returned by the Host Controller Drivers (HCDs), which
+device drivers only see through usbcore.  As a rule, all the HCDs should
+behave the same except for transfer speed dependent behaviors and the
+way certain faults are reported.
+
+
+Error codes returned by :c:func:`usb_submit_urb`
+================================================
+
+Non-USB-specific:
+
+
+=============== ===============================================
+0		URB submission went fine
+
+``-ENOMEM``	no memory for allocation of internal structures
+=============== ===============================================
+
+USB-specific:
+
+=======================	=======================================================
+``-EBUSY``		The URB is already active.
+
+``-ENODEV``		specified USB-device or bus doesn't exist
+
+``-ENOENT``		specified interface or endpoint does not exist or
+			is not enabled
+
+``-ENXIO``		host controller driver does not support queuing of
+			this type of urb.  (treat as a host controller bug.)
+
+``-EINVAL``		a) Invalid transfer type specified (or not supported)
+			b) Invalid or unsupported periodic transfer interval
+			c) ISO: attempted to change transfer interval
+			d) ISO: ``number_of_packets`` is < 0
+			e) various other cases
+
+``-EXDEV``		ISO: ``URB_ISO_ASAP`` wasn't specified and all the
+			frames the URB would be scheduled in have already
+			expired.
+
+``-EFBIG``		Host controller driver can't schedule that many ISO
+			frames.
+
+``-EPIPE``		The pipe type specified in the URB doesn't match the
+			endpoint's actual type.
+
+``-EMSGSIZE``		(a) endpoint maxpacket size is zero; it is not usable
+			    in the current interface altsetting.
+			(b) ISO packet is larger than the endpoint maxpacket.
+			(c) requested data transfer length is invalid: negative
+			    or too large for the host controller.
+
+``-ENOSPC``		This request would overcommit the usb bandwidth reserved
+			for periodic transfers (interrupt, isochronous).
+
+``-ESHUTDOWN``		The device or host controller has been disabled due to
+			some problem that could not be worked around.
+
+``-EPERM``		Submission failed because ``urb->reject`` was set.
+
+``-EHOSTUNREACH``	URB was rejected because the device is suspended.
+
+``-ENOEXEC``		A control URB doesn't contain a Setup packet.
+=======================	=======================================================
+
+Error codes returned by ``in urb->status`` or in ``iso_frame_desc[n].status`` (for ISO)
+=======================================================================================
+
+USB device drivers may only test urb status values in completion handlers.
+This is because otherwise there would be a race between HCDs updating
+these values on one CPU, and device drivers testing them on another CPU.
+
+A transfer's actual_length may be positive even when an error has been
+reported.  That's because transfers often involve several packets, so that
+one or more packets could finish before an error stops further endpoint I/O.
+
+For isochronous URBs, the urb status value is non-zero only if the URB is
+unlinked, the device is removed, the host controller is disabled, or the total
+transferred length is less than the requested length and the
+``URB_SHORT_NOT_OK`` flag is set.  Completion handlers for isochronous URBs
+should only see ``urb->status`` set to zero, ``-ENOENT``, ``-ECONNRESET``,
+``-ESHUTDOWN``, or ``-EREMOTEIO``. Individual frame descriptor status fields
+may report more status codes.
+
+
+===============================	===============================================
+0				Transfer completed successfully
+
+``-ENOENT``			URB was synchronously unlinked by
+				:c:func:`usb_unlink_urb`
+
+``-EINPROGRESS``		URB still pending, no results yet
+				(That is, if drivers see this it's a bug.)
+
+``-EPROTO`` [#f1]_, [#f2]_	a) bitstuff error
+				b) no response packet received within the
+				   prescribed bus turn-around time
+				c) unknown USB error
+
+``-EILSEQ`` [#f1]_, [#f2]_	a) CRC mismatch
+				b) no response packet received within the
+				   prescribed bus turn-around time
+				c) unknown USB error
+
+				Note that often the controller hardware does
+				not distinguish among cases a), b), and c), so
+				a driver cannot tell whether there was a
+				protocol error, a failure to respond (often
+				caused by device disconnect), or some other
+				fault.
+
+``-ETIME`` [#f2]_		No response packet received within the
+				prescribed bus turn-around time.  This error
+				may instead be reported as
+				``-EPROTO`` or ``-EILSEQ``.
+
+``-ETIMEDOUT``			Synchronous USB message functions use this code
+				to indicate timeout expired before the transfer
+				completed, and no other error was reported
+				by HC.
+
+``-EPIPE`` [#f2]_		Endpoint stalled.  For non-control endpoints,
+				reset this status with
+				:c:func:`usb_clear_halt`.
+
+``-ECOMM``			During an IN transfer, the host controller
+				received data from an endpoint faster than it
+				could be written to system memory
+
+``-ENOSR``			During an OUT transfer, the host controller
+				could not retrieve data from system memory fast
+				enough to keep up with the USB data rate
+
+``-EOVERFLOW`` [#f1]_		The amount of data returned by the endpoint was
+				greater than either the max packet size of the
+				endpoint or the remaining buffer size.
+				"Babble".
+
+``-EREMOTEIO``			The data read from the endpoint did not fill
+				the specified buffer, and ``URB_SHORT_NOT_OK``
+				was set in ``urb->transfer_flags``.
+
+``-ENODEV``			Device was removed.  Often preceded by a burst
+				of other errors, since the hub driver doesn't
+				detect device removal events immediately.
+
+``-EXDEV``			ISO transfer only partially completed
+				(only set in ``iso_frame_desc[n].status``,
+				not ``urb->status``)
+
+``-EINVAL``			ISO madness, if this happens: Log off and
+				go home
+
+``-ECONNRESET``			URB was asynchronously unlinked by
+				:c:func:`usb_unlink_urb`
+
+``-ESHUTDOWN``			The device or host controller has been
+				disabled due to some problem that could not
+				be worked around, such as a physical
+				disconnect.
+===============================	===============================================
+
+
+.. [#f1]
+
+   Error codes like ``-EPROTO``, ``-EILSEQ`` and ``-EOVERFLOW`` normally
+   indicate hardware problems such as bad devices (including firmware)
+   or cables.
+
+.. [#f2]
+
+   This is also one of several codes that different kinds of host
+   controller use to indicate a transfer has failed because of device
+   disconnect.  In the interval before the hub driver starts disconnect
+   processing, devices may receive such fault reports for every request.
+
+
+
+Error codes returned by usbcore-functions
+=========================================
+
+.. note:: expect also other submit and transfer status codes
+
+:c:func:`usb_register`:
+
+======================= ===================================
+``-EINVAL``		error during registering new driver
+======================= ===================================
+
+``usb_get_*/usb_set_*()``,
+:c:func:`usb_control_msg`,
+:c:func:`usb_bulk_msg()`:
+
+======================= ==============================================
+``-ETIMEDOUT``		Timeout expired before the transfer completed.
+======================= ==============================================
diff --git a/Documentation/driver-api/usb/gadget.rst b/Documentation/driver-api/usb/gadget.rst
new file mode 100644
index 000000000000..3e8a3809c0b8
--- /dev/null
+++ b/Documentation/driver-api/usb/gadget.rst
@@ -0,0 +1,510 @@
+========================
+USB Gadget API for Linux
+========================
+
+:Author: David Brownell
+:Date:   20 August 2004
+
+Introduction
+============
+
+This document presents a Linux-USB "Gadget" kernel mode API, for use
+within peripherals and other USB devices that embed Linux. It provides
+an overview of the API structure, and shows how that fits into a system
+development project. This is the first such API released on Linux to
+address a number of important problems, including:
+
+-  Supports USB 2.0, for high speed devices which can stream data at
+   several dozen megabytes per second.
+
+-  Handles devices with dozens of endpoints just as well as ones with
+   just two fixed-function ones. Gadget drivers can be written so
+   they're easy to port to new hardware.
+
+-  Flexible enough to expose more complex USB device capabilities such
+   as multiple configurations, multiple interfaces, composite devices,
+   and alternate interface settings.
+
+-  USB "On-The-Go" (OTG) support, in conjunction with updates to the
+   Linux-USB host side.
+
+-  Sharing data structures and API models with the Linux-USB host side
+   API. This helps the OTG support, and looks forward to more-symmetric
+   frameworks (where the same I/O model is used by both host and device
+   side drivers).
+
+-  Minimalist, so it's easier to support new device controller hardware.
+   I/O processing doesn't imply large demands for memory or CPU
+   resources.
+
+Most Linux developers will not be able to use this API, since they have
+USB ``host`` hardware in a PC, workstation, or server. Linux users with
+embedded systems are more likely to have USB peripheral hardware. To
+distinguish drivers running inside such hardware from the more familiar
+Linux "USB device drivers", which are host side proxies for the real USB
+devices, a different term is used: the drivers inside the peripherals
+are "USB gadget drivers". In USB protocol interactions, the device
+driver is the master (or "client driver") and the gadget driver is the
+slave (or "function driver").
+
+The gadget API resembles the host side Linux-USB API in that both use
+queues of request objects to package I/O buffers, and those requests may
+be submitted or canceled. They share common definitions for the standard
+USB *Chapter 9* messages, structures, and constants. Also, both APIs
+bind and unbind drivers to devices. The APIs differ in detail, since the
+host side's current URB framework exposes a number of implementation
+details and assumptions that are inappropriate for a gadget API. While
+the model for control transfers and configuration management is
+necessarily different (one side is a hardware-neutral master, the other
+is a hardware-aware slave), the endpoint I/0 API used here should also
+be usable for an overhead-reduced host side API.
+
+Structure of Gadget Drivers
+===========================
+
+A system running inside a USB peripheral normally has at least three
+layers inside the kernel to handle USB protocol processing, and may have
+additional layers in user space code. The ``gadget`` API is used by the
+middle layer to interact with the lowest level (which directly handles
+hardware).
+
+In Linux, from the bottom up, these layers are:
+
+*USB Controller Driver*
+    This is the lowest software level. It is the only layer that talks
+    to hardware, through registers, fifos, dma, irqs, and the like. The
+    ``<linux/usb/gadget.h>`` API abstracts the peripheral controller
+    endpoint hardware. That hardware is exposed through endpoint
+    objects, which accept streams of IN/OUT buffers, and through
+    callbacks that interact with gadget drivers. Since normal USB
+    devices only have one upstream port, they only have one of these
+    drivers. The controller driver can support any number of different
+    gadget drivers, but only one of them can be used at a time.
+
+    Examples of such controller hardware include the PCI-based NetChip
+    2280 USB 2.0 high speed controller, the SA-11x0 or PXA-25x UDC
+    (found within many PDAs), and a variety of other products.
+
+*Gadget Driver*
+    The lower boundary of this driver implements hardware-neutral USB
+    functions, using calls to the controller driver. Because such
+    hardware varies widely in capabilities and restrictions, and is used
+    in embedded environments where space is at a premium, the gadget
+    driver is often configured at compile time to work with endpoints
+    supported by one particular controller. Gadget drivers may be
+    portable to several different controllers, using conditional
+    compilation. (Recent kernels substantially simplify the work
+    involved in supporting new hardware, by *autoconfiguring* endpoints
+    automatically for many bulk-oriented drivers.) Gadget driver
+    responsibilities include:
+
+    -  handling setup requests (ep0 protocol responses) possibly
+       including class-specific functionality
+
+    -  returning configuration and string descriptors
+
+    -  (re)setting configurations and interface altsettings, including
+       enabling and configuring endpoints
+
+    -  handling life cycle events, such as managing bindings to
+       hardware, USB suspend/resume, remote wakeup, and disconnection
+       from the USB host.
+
+    -  managing IN and OUT transfers on all currently enabled endpoints
+
+    Such drivers may be modules of proprietary code, although that
+    approach is discouraged in the Linux community.
+
+*Upper Level*
+    Most gadget drivers have an upper boundary that connects to some
+    Linux driver or framework in Linux. Through that boundary flows the
+    data which the gadget driver produces and/or consumes through
+    protocol transfers over USB. Examples include:
+
+    -  user mode code, using generic (gadgetfs) or application specific
+       files in ``/dev``
+
+    -  networking subsystem (for network gadgets, like the CDC Ethernet
+       Model gadget driver)
+
+    -  data capture drivers, perhaps video4Linux or a scanner driver; or
+       test and measurement hardware.
+
+    -  input subsystem (for HID gadgets)
+
+    -  sound subsystem (for audio gadgets)
+
+    -  file system (for PTP gadgets)
+
+    -  block i/o subsystem (for usb-storage gadgets)
+
+    -  ... and more
+
+*Additional Layers*
+    Other layers may exist. These could include kernel layers, such as
+    network protocol stacks, as well as user mode applications building
+    on standard POSIX system call APIs such as ``open()``, ``close()``,
+    ``read()`` and ``write()``. On newer systems, POSIX Async I/O calls may
+    be an option. Such user mode code will not necessarily be subject to
+    the GNU General Public License (GPL).
+
+OTG-capable systems will also need to include a standard Linux-USB host
+side stack, with ``usbcore``, one or more *Host Controller Drivers*
+(HCDs), *USB Device Drivers* to support the OTG "Targeted Peripheral
+List", and so forth. There will also be an *OTG Controller Driver*,
+which is visible to gadget and device driver developers only indirectly.
+That helps the host and device side USB controllers implement the two
+new OTG protocols (HNP and SRP). Roles switch (host to peripheral, or
+vice versa) using HNP during USB suspend processing, and SRP can be
+viewed as a more battery-friendly kind of device wakeup protocol.
+
+Over time, reusable utilities are evolving to help make some gadget
+driver tasks simpler. For example, building configuration descriptors
+from vectors of descriptors for the configurations interfaces and
+endpoints is now automated, and many drivers now use autoconfiguration
+to choose hardware endpoints and initialize their descriptors. A
+potential example of particular interest is code implementing standard
+USB-IF protocols for HID, networking, storage, or audio classes. Some
+developers are interested in KDB or KGDB hooks, to let target hardware
+be remotely debugged. Most such USB protocol code doesn't need to be
+hardware-specific, any more than network protocols like X11, HTTP, or
+NFS are. Such gadget-side interface drivers should eventually be
+combined, to implement composite devices.
+
+Kernel Mode Gadget API
+======================
+
+Gadget drivers declare themselves through a struct
+:c:type:`usb_gadget_driver`, which is responsible for most parts of enumeration
+for a struct :c:type:`usb_gadget`. The response to a set_configuration usually
+involves enabling one or more of the struct :c:type:`usb_ep` objects exposed by
+the gadget, and submitting one or more struct :c:type:`usb_request` buffers to
+transfer data. Understand those four data types, and their operations,
+and you will understand how this API works.
+
+.. Note::
+
+    Other than the "Chapter 9" data types, most of the significant data
+    types and functions are described here.
+
+    However, some relevant information is likely omitted from what you
+    are reading. One example of such information is endpoint
+    autoconfiguration. You'll have to read the header file, and use
+    example source code (such as that for "Gadget Zero"), to fully
+    understand the API.
+
+    The part of the API implementing some basic driver capabilities is
+    specific to the version of the Linux kernel that's in use. The 2.6
+    and upper kernel versions include a *driver model* framework that has
+    no analogue on earlier kernels; so those parts of the gadget API are
+    not fully portable. (They are implemented on 2.4 kernels, but in a
+    different way.) The driver model state is another part of this API that is
+    ignored by the kerneldoc tools.
+
+The core API does not expose every possible hardware feature, only the
+most widely available ones. There are significant hardware features,
+such as device-to-device DMA (without temporary storage in a memory
+buffer) that would be added using hardware-specific APIs.
+
+This API allows drivers to use conditional compilation to handle
+endpoint capabilities of different hardware, but doesn't require that.
+Hardware tends to have arbitrary restrictions, relating to transfer
+types, addressing, packet sizes, buffering, and availability. As a rule,
+such differences only matter for "endpoint zero" logic that handles
+device configuration and management. The API supports limited run-time
+detection of capabilities, through naming conventions for endpoints.
+Many drivers will be able to at least partially autoconfigure
+themselves. In particular, driver init sections will often have endpoint
+autoconfiguration logic that scans the hardware's list of endpoints to
+find ones matching the driver requirements (relying on those
+conventions), to eliminate some of the most common reasons for
+conditional compilation.
+
+Like the Linux-USB host side API, this API exposes the "chunky" nature
+of USB messages: I/O requests are in terms of one or more "packets", and
+packet boundaries are visible to drivers. Compared to RS-232 serial
+protocols, USB resembles synchronous protocols like HDLC (N bytes per
+frame, multipoint addressing, host as the primary station and devices as
+secondary stations) more than asynchronous ones (tty style: 8 data bits
+per frame, no parity, one stop bit). So for example the controller
+drivers won't buffer two single byte writes into a single two-byte USB
+IN packet, although gadget drivers may do so when they implement
+protocols where packet boundaries (and "short packets") are not
+significant.
+
+Driver Life Cycle
+-----------------
+
+Gadget drivers make endpoint I/O requests to hardware without needing to
+know many details of the hardware, but driver setup/configuration code
+needs to handle some differences. Use the API like this:
+
+1. Register a driver for the particular device side usb controller
+   hardware, such as the net2280 on PCI (USB 2.0), sa11x0 or pxa25x as
+   found in Linux PDAs, and so on. At this point the device is logically
+   in the USB ch9 initial state (``attached``), drawing no power and not
+   usable (since it does not yet support enumeration). Any host should
+   not see the device, since it's not activated the data line pullup
+   used by the host to detect a device, even if VBUS power is available.
+
+2. Register a gadget driver that implements some higher level device
+   function. That will then bind() to a :c:type:`usb_gadget`, which activates
+   the data line pullup sometime after detecting VBUS.
+
+3. The hardware driver can now start enumerating. The steps it handles
+   are to accept USB ``power`` and ``set_address`` requests. Other steps are
+   handled by the gadget driver. If the gadget driver module is unloaded
+   before the host starts to enumerate, steps before step 7 are skipped.
+
+4. The gadget driver's ``setup()`` call returns usb descriptors, based both
+   on what the bus interface hardware provides and on the functionality
+   being implemented. That can involve alternate settings or
+   configurations, unless the hardware prevents such operation. For OTG
+   devices, each configuration descriptor includes an OTG descriptor.
+
+5. The gadget driver handles the last step of enumeration, when the USB
+   host issues a ``set_configuration`` call. It enables all endpoints used
+   in that configuration, with all interfaces in their default settings.
+   That involves using a list of the hardware's endpoints, enabling each
+   endpoint according to its descriptor. It may also involve using
+   ``usb_gadget_vbus_draw`` to let more power be drawn from VBUS, as
+   allowed by that configuration. For OTG devices, setting a
+   configuration may also involve reporting HNP capabilities through a
+   user interface.
+
+6. Do real work and perform data transfers, possibly involving changes
+   to interface settings or switching to new configurations, until the
+   device is disconnect()ed from the host. Queue any number of transfer
+   requests to each endpoint. It may be suspended and resumed several
+   times before being disconnected. On disconnect, the drivers go back
+   to step 3 (above).
+
+7. When the gadget driver module is being unloaded, the driver unbind()
+   callback is issued. That lets the controller driver be unloaded.
+
+Drivers will normally be arranged so that just loading the gadget driver
+module (or statically linking it into a Linux kernel) allows the
+peripheral device to be enumerated, but some drivers will defer
+enumeration until some higher level component (like a user mode daemon)
+enables it. Note that at this lowest level there are no policies about
+how ep0 configuration logic is implemented, except that it should obey
+USB specifications. Such issues are in the domain of gadget drivers,
+including knowing about implementation constraints imposed by some USB
+controllers or understanding that composite devices might happen to be
+built by integrating reusable components.
+
+Note that the lifecycle above can be slightly different for OTG devices.
+Other than providing an additional OTG descriptor in each configuration,
+only the HNP-related differences are particularly visible to driver
+code. They involve reporting requirements during the ``SET_CONFIGURATION``
+request, and the option to invoke HNP during some suspend callbacks.
+Also, SRP changes the semantics of ``usb_gadget_wakeup`` slightly.
+
+USB 2.0 Chapter 9 Types and Constants
+-------------------------------------
+
+Gadget drivers rely on common USB structures and constants defined in
+the :ref:`linux/usb/ch9.h <usb_chapter9>` header file, which is standard in
+Linux 2.6+ kernels. These are the same types and constants used by host side
+drivers (and usbcore).
+
+Core Objects and Methods
+------------------------
+
+These are declared in ``<linux/usb/gadget.h>``, and are used by gadget
+drivers to interact with USB peripheral controller drivers.
+
+.. kernel-doc:: include/linux/usb/gadget.h
+   :internal:
+
+Optional Utilities
+------------------
+
+The core API is sufficient for writing a USB Gadget Driver, but some
+optional utilities are provided to simplify common tasks. These
+utilities include endpoint autoconfiguration.
+
+.. kernel-doc:: drivers/usb/gadget/usbstring.c
+   :export:
+
+.. kernel-doc:: drivers/usb/gadget/config.c
+   :export:
+
+Composite Device Framework
+--------------------------
+
+The core API is sufficient for writing drivers for composite USB devices
+(with more than one function in a given configuration), and also
+multi-configuration devices (also more than one function, but not
+necessarily sharing a given configuration). There is however an optional
+framework which makes it easier to reuse and combine functions.
+
+Devices using this framework provide a struct :c:type:`usb_composite_driver`,
+which in turn provides one or more struct :c:type:`usb_configuration`
+instances. Each such configuration includes at least one struct
+:c:type:`usb_function`, which packages a user visible role such as "network
+link" or "mass storage device". Management functions may also exist,
+such as "Device Firmware Upgrade".
+
+.. kernel-doc:: include/linux/usb/composite.h
+   :internal:
+
+.. kernel-doc:: drivers/usb/gadget/composite.c
+   :export:
+
+Composite Device Functions
+--------------------------
+
+At this writing, a few of the current gadget drivers have been converted
+to this framework. Near-term plans include converting all of them,
+except for ``gadgetfs``.
+
+Peripheral Controller Drivers
+=============================
+
+The first hardware supporting this API was the NetChip 2280 controller,
+which supports USB 2.0 high speed and is based on PCI. This is the
+``net2280`` driver module. The driver supports Linux kernel versions 2.4
+and 2.6; contact NetChip Technologies for development boards and product
+information.
+
+Other hardware working in the ``gadget`` framework includes: Intel's PXA
+25x and IXP42x series processors (``pxa2xx_udc``), Toshiba TC86c001
+"Goku-S" (``goku_udc``), Renesas SH7705/7727 (``sh_udc``), MediaQ 11xx
+(``mq11xx_udc``), Hynix HMS30C7202 (``h7202_udc``), National 9303/4
+(``n9604_udc``), Texas Instruments OMAP (``omap_udc``), Sharp LH7A40x
+(``lh7a40x_udc``), and more. Most of those are full speed controllers.
+
+At this writing, there are people at work on drivers in this framework
+for several other USB device controllers, with plans to make many of
+them be widely available.
+
+A partial USB simulator, the ``dummy_hcd`` driver, is available. It can
+act like a net2280, a pxa25x, or an sa11x0 in terms of available
+endpoints and device speeds; and it simulates control, bulk, and to some
+extent interrupt transfers. That lets you develop some parts of a gadget
+driver on a normal PC, without any special hardware, and perhaps with
+the assistance of tools such as GDB running with User Mode Linux. At
+least one person has expressed interest in adapting that approach,
+hooking it up to a simulator for a microcontroller. Such simulators can
+help debug subsystems where the runtime hardware is unfriendly to
+software development, or is not yet available.
+
+Support for other controllers is expected to be developed and
+contributed over time, as this driver framework evolves.
+
+Gadget Drivers
+==============
+
+In addition to *Gadget Zero* (used primarily for testing and development
+with drivers for usb controller hardware), other gadget drivers exist.
+
+There's an ``ethernet`` gadget driver, which implements one of the most
+useful *Communications Device Class* (CDC) models. One of the standards
+for cable modem interoperability even specifies the use of this ethernet
+model as one of two mandatory options. Gadgets using this code look to a
+USB host as if they're an Ethernet adapter. It provides access to a
+network where the gadget's CPU is one host, which could easily be
+bridging, routing, or firewalling access to other networks. Since some
+hardware can't fully implement the CDC Ethernet requirements, this
+driver also implements a "good parts only" subset of CDC Ethernet. (That
+subset doesn't advertise itself as CDC Ethernet, to avoid creating
+problems.)
+
+Support for Microsoft's ``RNDIS`` protocol has been contributed by
+Pengutronix and Auerswald GmbH. This is like CDC Ethernet, but it runs
+on more slightly USB hardware (but less than the CDC subset). However,
+its main claim to fame is being able to connect directly to recent
+versions of Windows, using drivers that Microsoft bundles and supports,
+making it much simpler to network with Windows.
+
+There is also support for user mode gadget drivers, using ``gadgetfs``.
+This provides a *User Mode API* that presents each endpoint as a single
+file descriptor. I/O is done using normal ``read()`` and ``read()`` calls.
+Familiar tools like GDB and pthreads can be used to develop and debug
+user mode drivers, so that once a robust controller driver is available
+many applications for it won't require new kernel mode software. Linux
+2.6 *Async I/O (AIO)* support is available, so that user mode software
+can stream data with only slightly more overhead than a kernel driver.
+
+There's a USB Mass Storage class driver, which provides a different
+solution for interoperability with systems such as MS-Windows and MacOS.
+That *Mass Storage* driver uses a file or block device as backing store
+for a drive, like the ``loop`` driver. The USB host uses the BBB, CB, or
+CBI versions of the mass storage class specification, using transparent
+SCSI commands to access the data from the backing store.
+
+There's a "serial line" driver, useful for TTY style operation over USB.
+The latest version of that driver supports CDC ACM style operation, like
+a USB modem, and so on most hardware it can interoperate easily with
+MS-Windows. One interesting use of that driver is in boot firmware (like
+a BIOS), which can sometimes use that model with very small systems
+without real serial lines.
+
+Support for other kinds of gadget is expected to be developed and
+contributed over time, as this driver framework evolves.
+
+USB On-The-GO (OTG)
+===================
+
+USB OTG support on Linux 2.6 was initially developed by Texas
+Instruments for `OMAP <http://www.omap.com>`__ 16xx and 17xx series
+processors. Other OTG systems should work in similar ways, but the
+hardware level details could be very different.
+
+Systems need specialized hardware support to implement OTG, notably
+including a special *Mini-AB* jack and associated transceiver to support
+*Dual-Role* operation: they can act either as a host, using the standard
+Linux-USB host side driver stack, or as a peripheral, using this
+``gadget`` framework. To do that, the system software relies on small
+additions to those programming interfaces, and on a new internal
+component (here called an "OTG Controller") affecting which driver stack
+connects to the OTG port. In each role, the system can re-use the
+existing pool of hardware-neutral drivers, layered on top of the
+controller driver interfaces (:c:type:`usb_bus` or :c:type:`usb_gadget`).
+Such drivers need at most minor changes, and most of the calls added to
+support OTG can also benefit non-OTG products.
+
+-  Gadget drivers test the ``is_otg`` flag, and use it to determine
+   whether or not to include an OTG descriptor in each of their
+   configurations.
+
+-  Gadget drivers may need changes to support the two new OTG protocols,
+   exposed in new gadget attributes such as ``b_hnp_enable`` flag. HNP
+   support should be reported through a user interface (two LEDs could
+   suffice), and is triggered in some cases when the host suspends the
+   peripheral. SRP support can be user-initiated just like remote
+   wakeup, probably by pressing the same button.
+
+-  On the host side, USB device drivers need to be taught to trigger HNP
+   at appropriate moments, using ``usb_suspend_device()``. That also
+   conserves battery power, which is useful even for non-OTG
+   configurations.
+
+-  Also on the host side, a driver must support the OTG "Targeted
+   Peripheral List". That's just a whitelist, used to reject peripherals
+   not supported with a given Linux OTG host. *This whitelist is
+   product-specific; each product must modify* ``otg_whitelist.h`` *to
+   match its interoperability specification.*
+
+   Non-OTG Linux hosts, like PCs and workstations, normally have some
+   solution for adding drivers, so that peripherals that aren't
+   recognized can eventually be supported. That approach is unreasonable
+   for consumer products that may never have their firmware upgraded,
+   and where it's usually unrealistic to expect traditional
+   PC/workstation/server kinds of support model to work. For example,
+   it's often impractical to change device firmware once the product has
+   been distributed, so driver bugs can't normally be fixed if they're
+   found after shipment.
+
+Additional changes are needed below those hardware-neutral :c:type:`usb_bus`
+and :c:type:`usb_gadget` driver interfaces; those aren't discussed here in any
+detail. Those affect the hardware-specific code for each USB Host or
+Peripheral controller, and how the HCD initializes (since OTG can be
+active only on a single port). They also involve what may be called an
+*OTG Controller Driver*, managing the OTG transceiver and the OTG state
+machine logic as well as much of the root hub behavior for the OTG port.
+The OTG controller driver needs to activate and deactivate USB
+controllers depending on the relevant device role. Some related changes
+were needed inside usbcore, so that it can identify OTG-capable devices
+and respond appropriately to HNP or SRP protocols.
diff --git a/Documentation/usb/hotplug.txt b/Documentation/driver-api/usb/hotplug.rst
index 5b243f315b2c..79663e653ca1 100644
--- a/Documentation/usb/hotplug.txt
+++ b/Documentation/driver-api/usb/hotplug.rst
@@ -1,4 +1,9 @@
-LINUX HOTPLUGGING
+USB hotplugging
+~~~~~~~~~~~~~~~
+
+Linux Hotplugging
+=================
+
 
 In hotpluggable busses like USB (and Cardbus PCI), end-users plug devices
 into the bus with power on.  In most cases, users expect the devices to become
@@ -30,11 +35,11 @@ Because some of those actions rely on information about drivers (metadata)
 that is currently available only when the drivers are dynamically linked,
 you get the best hotplugging when you configure a highly modular system.
 
+Kernel Hotplug Helper (``/sbin/hotplug``)
+=========================================
 
-KERNEL HOTPLUG HELPER (/sbin/hotplug)
-
-There is a kernel parameter: /proc/sys/kernel/hotplug, which normally
-holds the pathname "/sbin/hotplug".  That parameter names a program
+There is a kernel parameter: ``/proc/sys/kernel/hotplug``, which normally
+holds the pathname ``/sbin/hotplug``.  That parameter names a program
 which the kernel may invoke at various times.
 
 The /sbin/hotplug program can be invoked by any subsystem as part of its
@@ -51,26 +56,26 @@ Hotplug software and other resources is available at:
 Mailing list information is also available at that site.
 
 
---------------------------------------------------------------------------
-
+USB Policy Agent
+================
 
-USB POLICY AGENT
-
-The USB subsystem currently invokes /sbin/hotplug when USB devices
+The USB subsystem currently invokes ``/sbin/hotplug`` when USB devices
 are added or removed from system.  The invocation is done by the kernel
 hub workqueue [hub_wq], or else as part of root hub initialization
 (done by init, modprobe, kapmd, etc).  Its single command line parameter
 is the string "usb", and it passes these environment variables:
 
-    ACTION ... "add", "remove"
-    PRODUCT ... USB vendor, product, and version codes (hex)
-    TYPE ... device class codes (decimal)
-    INTERFACE ... interface 0 class codes (decimal)
+========== ============================================
+ACTION     ``add``, ``remove``
+PRODUCT    USB vendor, product, and version codes (hex)
+TYPE       device class codes (decimal)
+INTERFACE  interface 0 class codes (decimal)
+========== ============================================
 
 If "usbdevfs" is configured, DEVICE and DEVFS are also passed.  DEVICE is
 the pathname of the device, and is useful for devices with multiple and/or
 alternate interfaces that complicate driver selection.  By design, USB
-hotplugging is independent of "usbdevfs":  you can do most essential parts
+hotplugging is independent of ``usbdevfs``:  you can do most essential parts
 of USB device setup without using that filesystem, and without running a
 user mode daemon to detect changes in system configuration.
 
@@ -79,19 +84,20 @@ modules, and can invoke driver-specific setup scripts.  The newest ones
 leverage USB module-init-tools support.  Later agents might unload drivers.
 
 
-USB MODUTILS SUPPORT
+USB Modutils Support
+====================
 
-Current versions of module-init-tools will create a "modules.usbmap" file
-which contains the entries from each driver's MODULE_DEVICE_TABLE.  Such
+Current versions of module-init-tools will create a ``modules.usbmap`` file
+which contains the entries from each driver's ``MODULE_DEVICE_TABLE``.  Such
 files can be used by various user mode policy agents to make sure all the
 right driver modules get loaded, either at boot time or later.
 
-See <linux/usb.h> for full information about such table entries; or look
+See ``linux/usb.h`` for full information about such table entries; or look
 at existing drivers.  Each table entry describes one or more criteria to
 be used when matching a driver to a device or class of devices.  The
 specific criteria are identified by bits set in "match_flags", paired
 with field values.  You can construct the criteria directly, or with
-macros such as these, and use driver_info to store more information.
+macros such as these, and use driver_info to store more information::
 
     USB_DEVICE (vendorId, productId)
 	... matching devices with specified vendor and product ids
@@ -103,7 +109,7 @@ macros such as these, and use driver_info to store more information.
 	... matching specified device class info
 
 A short example, for a driver that supports several specific USB devices
-and their quirks, might have a MODULE_DEVICE_TABLE like this:
+and their quirks, might have a MODULE_DEVICE_TABLE like this::
 
     static const struct usb_device_id mydriver_id_table[] = {
 	{ USB_DEVICE (0x9999, 0xaaaa), driver_info: QUIRK_X },
@@ -116,10 +122,10 @@ and their quirks, might have a MODULE_DEVICE_TABLE like this:
 Most USB device drivers should pass these tables to the USB subsystem as
 well as to the module management subsystem.  Not all, though: some driver
 frameworks connect using interfaces layered over USB, and so they won't
-need such a "struct usb_driver".
+need such a struct :c:type:`usb_driver`.
 
 Drivers that connect directly to the USB subsystem should be declared
-something like this:
+something like this::
 
     static struct usb_driver mydriver = {
 	.name		= "mydriver",
@@ -138,11 +144,11 @@ something like this:
 
 When the USB subsystem knows about a driver's device ID table, it's used when
 choosing drivers to probe().  The thread doing new device processing checks
-drivers' device ID entries from the MODULE_DEVICE_TABLE against interface and
-device descriptors for the device.  It will only call probe() if there is a
-match, and the third argument to probe() will be the entry that matched.
-
-If you don't provide an id_table for your driver, then your driver may get
-probed for each new device; the third parameter to probe() will be null.
-
-
+drivers' device ID entries from the ``MODULE_DEVICE_TABLE`` against interface
+and device descriptors for the device.  It will only call ``probe()`` if there
+is a match, and the third argument to ``probe()`` will be the entry that
+matched.
+
+If you don't provide an ``id_table`` for your driver, then your driver may get
+probed for each new device; the third parameter to ``probe()`` will be
+``NULL``.
diff --git a/Documentation/driver-api/usb/index.rst b/Documentation/driver-api/usb/index.rst
new file mode 100644
index 000000000000..1bf64edc8c8a
--- /dev/null
+++ b/Documentation/driver-api/usb/index.rst
@@ -0,0 +1,26 @@
+=============
+Linux USB API
+=============
+
+.. toctree::
+
+   usb
+   gadget
+   anchors
+   bulk-streams
+   callbacks
+   dma
+   URB
+   power-management
+   hotplug
+   persist
+   error-codes
+   writing_usb_driver
+   writing_musb_glue_layer
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/usb/persist.txt b/Documentation/driver-api/usb/persist.rst
index 35d70eda9ad6..08cafc6292c1 100644
--- a/Documentation/usb/persist.txt
+++ b/Documentation/driver-api/usb/persist.rst
@@ -1,11 +1,14 @@
-		USB device persistence during system suspend
+.. _usb-persist:
 
-		   Alan Stern <stern@rowland.harvard.edu>
+USB device persistence during system suspend
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-		September 2, 2006 (Updated February 25, 2008)
+:Author: Alan Stern <stern@rowland.harvard.edu>
+:Date: September 2, 2006 (Updated February 25, 2008)
 
 
-	What is the problem?
+What is the problem?
+====================
 
 According to the USB specification, when a USB bus is suspended the
 bus must continue to supply suspend current (around 1-5 mA).  This
@@ -63,7 +66,8 @@ suspended -- but it will crash as soon as it wakes up, which isn't
 much better.)
 
 
-	What is the solution?
+What is the solution?
+=====================
 
 The kernel includes a feature called USB-persist.  It tries to work
 around these issues by allowing the core USB device data structures to
@@ -99,7 +103,7 @@ now a good and happy place.
 
 Note that the "USB-persist" feature will be applied only to those
 devices for which it is enabled.  You can enable the feature by doing
-(as root):
+(as root)::
 
 	echo 1 >/sys/bus/usb/devices/.../power/persist
 
@@ -110,7 +114,8 @@ doesn't even exist, so you only have to worry about setting it for
 devices where it really matters.
 
 
-	Is this the best solution?
+Is this the best solution?
+==========================
 
 Perhaps not.  Arguably, keeping track of mounted filesystems and
 memory mappings across device disconnects should be handled by a
@@ -130,7 +135,8 @@ just mass-storage devices.  It might turn out to be equally useful for
 other device types, such as network interfaces.
 
 
-	WARNING: USB-persist can be dangerous!!
+WARNING: USB-persist can be dangerous!!
+=======================================
 
 When recovering an interrupted power session the kernel does its best
 to make sure the USB device hasn't been changed; that is, the same
diff --git a/Documentation/usb/power-management.txt b/Documentation/driver-api/usb/power-management.rst
index 00e706997130..79beb807996b 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/driver-api/usb/power-management.rst
@@ -1,10 +1,12 @@
-			Power Management for USB
+.. _usb-power-management:
 
-		 Alan Stern <stern@rowland.harvard.edu>
-
-		       Last-updated: February 2014
+Power Management for USB
+~~~~~~~~~~~~~~~~~~~~~~~~
 
+:Author: Alan Stern <stern@rowland.harvard.edu>
+:Date: Last-updated: February 2014
 
+..
 	Contents:
 	---------
 	* What is Power Management?
@@ -25,14 +27,14 @@
 	* Suggested Userspace Port Power Policy
 
 
-	What is Power Management?
-	-------------------------
+What is Power Management?
+-------------------------
 
 Power Management (PM) is the practice of saving energy by suspending
 parts of a computer system when they aren't being used.  While a
-component is "suspended" it is in a nonfunctional low-power state; it
+component is ``suspended`` it is in a nonfunctional low-power state; it
 might even be turned off completely.  A suspended component can be
-"resumed" (returned to a functional full-power state) when the kernel
+``resumed`` (returned to a functional full-power state) when the kernel
 needs to use it.  (There also are forms of PM in which components are
 placed in a less functional but still usable state instead of being
 suspended; an example would be reducing the CPU's clock rate.  This
@@ -44,22 +46,25 @@ device is turned off while the system as a whole remains running, we
 call it a "dynamic suspend" (also known as a "runtime suspend" or
 "selective suspend").  This document concentrates mostly on how
 dynamic PM is implemented in the USB subsystem, although system PM is
-covered to some extent (see Documentation/power/*.txt for more
+covered to some extent (see ``Documentation/power/*.txt`` for more
 information about system PM).
 
-System PM support is present only if the kernel was built with CONFIG_SUSPEND
-or CONFIG_HIBERNATION enabled.  Dynamic PM support for USB is present whenever
-the kernel was built with CONFIG_PM enabled.
+System PM support is present only if the kernel was built with
+``CONFIG_SUSPEND`` or ``CONFIG_HIBERNATION`` enabled.  Dynamic PM support
+
+for USB is present whenever
+the kernel was built with ``CONFIG_PM`` enabled.
 
 [Historically, dynamic PM support for USB was present only if the
-kernel had been built with CONFIG_USB_SUSPEND enabled (which depended on
-CONFIG_PM_RUNTIME).  Starting with the 3.10 kernel release, dynamic PM support
-for USB was present whenever the kernel was built with CONFIG_PM_RUNTIME
-enabled.  The CONFIG_USB_SUSPEND option had been eliminated.]
+kernel had been built with ``CONFIG_USB_SUSPEND`` enabled (which depended on
+``CONFIG_PM_RUNTIME``).  Starting with the 3.10 kernel release, dynamic PM
+support for USB was present whenever the kernel was built with
+``CONFIG_PM_RUNTIME`` enabled.  The ``CONFIG_USB_SUSPEND`` option had been
+eliminated.]
 
 
-	What is Remote Wakeup?
-	----------------------
+What is Remote Wakeup?
+----------------------
 
 When a device has been suspended, it generally doesn't resume until
 the computer tells it to.  Likewise, if the entire computer has been
@@ -76,8 +81,8 @@ event.  Examples include a suspended keyboard resuming when a key is
 pressed, or a suspended USB hub resuming when a device is plugged in.
 
 
-	When is a USB device idle?
-	--------------------------
+When is a USB device idle?
+--------------------------
 
 A device is idle whenever the kernel thinks it's not busy doing
 anything important and thus is a candidate for being suspended.  The
@@ -92,11 +97,11 @@ If a USB device has no driver, its usbfs file isn't open, and it isn't
 being accessed through sysfs, then it definitely is idle.
 
 
-	Forms of dynamic PM
-	-------------------
+Forms of dynamic PM
+-------------------
 
 Dynamic suspends occur when the kernel decides to suspend an idle
-device.  This is called "autosuspend" for short.  In general, a device
+device.  This is called ``autosuspend`` for short.  In general, a device
 won't be autosuspended unless it has been idle for some minimum period
 of time, the so-called idle-delay time.
 
@@ -125,51 +130,51 @@ all dynamic suspend events are internal; external agents are not
 allowed to issue dynamic suspends.
 
 
-	The user interface for dynamic PM
-	---------------------------------
+The user interface for dynamic PM
+---------------------------------
 
-The user interface for controlling dynamic PM is located in the power/
+The user interface for controlling dynamic PM is located in the ``power/``
 subdirectory of each USB device's sysfs directory, that is, in
-/sys/bus/usb/devices/.../power/ where "..." is the device's ID.  The
+``/sys/bus/usb/devices/.../power/`` where "..." is the device's ID.  The
 relevant attribute files are: wakeup, control, and
-autosuspend_delay_ms.  (There may also be a file named "level"; this
+``autosuspend_delay_ms``.  (There may also be a file named ``level``; this
 file was deprecated as of the 2.6.35 kernel and replaced by the
-"control" file.  In 2.6.38 the "autosuspend" file will be deprecated
-and replaced by the "autosuspend_delay_ms" file.  The only difference
+``control`` file.  In 2.6.38 the ``autosuspend`` file will be deprecated
+and replaced by the ``autosuspend_delay_ms`` file.  The only difference
 is that the newer file expresses the delay in milliseconds whereas the
 older file uses seconds.  Confusingly, both files are present in 2.6.37
-but only "autosuspend" works.)
+but only ``autosuspend`` works.)
 
-	power/wakeup
+	``power/wakeup``
 
 		This file is empty if the device does not support
 		remote wakeup.  Otherwise the file contains either the
-		word "enabled" or the word "disabled", and you can
+		word ``enabled`` or the word ``disabled``, and you can
 		write those words to the file.  The setting determines
 		whether or not remote wakeup will be enabled when the
 		device is next suspended.  (If the setting is changed
 		while the device is suspended, the change won't take
 		effect until the following suspend.)
 
-	power/control
+	``power/control``
 
-		This file contains one of two words: "on" or "auto".
+		This file contains one of two words: ``on`` or ``auto``.
 		You can write those words to the file to change the
 		device's setting.
 
-		"on" means that the device should be resumed and
-		autosuspend is not allowed.  (Of course, system
-		suspends are still allowed.)
+		- ``on`` means that the device should be resumed and
+		  autosuspend is not allowed.  (Of course, system
+		  suspends are still allowed.)
 
-		"auto" is the normal state in which the kernel is
-		allowed to autosuspend and autoresume the device.
+		- ``auto`` is the normal state in which the kernel is
+		  allowed to autosuspend and autoresume the device.
 
 		(In kernels up to 2.6.32, you could also specify
-		"suspend", meaning that the device should remain
+		``suspend``, meaning that the device should remain
 		suspended and autoresume was not allowed.  This
 		setting is no longer supported.)
 
-	power/autosuspend_delay_ms
+	``power/autosuspend_delay_ms``
 
 		This file contains an integer value, which is the
 		number of milliseconds the device should remain idle
@@ -180,31 +185,31 @@ but only "autosuspend" works.)
 		number to the file to change the autosuspend
 		idle-delay time.
 
-Writing "-1" to power/autosuspend_delay_ms and writing "on" to
-power/control do essentially the same thing -- they both prevent the
+Writing ``-1`` to ``power/autosuspend_delay_ms`` and writing ``on`` to
+``power/control`` do essentially the same thing -- they both prevent the
 device from being autosuspended.  Yes, this is a redundancy in the
 API.
 
-(In 2.6.21 writing "0" to power/autosuspend would prevent the device
+(In 2.6.21 writing ``0`` to ``power/autosuspend`` would prevent the device
 from being autosuspended; the behavior was changed in 2.6.22.  The
-power/autosuspend attribute did not exist prior to 2.6.21, and the
-power/level attribute did not exist prior to 2.6.22.  power/control
-was added in 2.6.34, and power/autosuspend_delay_ms was added in
+``power/autosuspend`` attribute did not exist prior to 2.6.21, and the
+``power/level`` attribute did not exist prior to 2.6.22.  ``power/control``
+was added in 2.6.34, and ``power/autosuspend_delay_ms`` was added in
 2.6.37 but did not become functional until 2.6.38.)
 
 
-	Changing the default idle-delay time
-	------------------------------------
+Changing the default idle-delay time
+------------------------------------
 
 The default autosuspend idle-delay time (in seconds) is controlled by
 a module parameter in usbcore.  You can specify the value when usbcore
 is loaded.  For example, to set it to 5 seconds instead of 2 you would
-do:
+do::
 
 	modprobe usbcore autosuspend=5
 
 Equivalently, you could add to a configuration file in /etc/modprobe.d
-a line saying:
+a line saying::
 
 	options usbcore autosuspend=5
 
@@ -214,14 +219,14 @@ image.  To alter the parameter value you would have to rebuild that
 image.
 
 If usbcore is compiled into the kernel rather than built as a loadable
-module, you can add
+module, you can add::
 
 	usbcore.autosuspend=5
 
 to the kernel's boot command line.
 
 Finally, the parameter value can be changed while the system is
-running.  If you do:
+running.  If you do::
 
 	echo 5 >/sys/module/usbcore/parameters/autosuspend
 
@@ -234,8 +239,8 @@ autosuspend of any USB device.  This has the benefit of allowing you
 then to enable autosuspend for selected devices.
 
 
-	Warnings
-	--------
+Warnings
+--------
 
 The USB specification states that all USB devices must support power
 management.  Nevertheless, the sad fact is that many devices do not
@@ -246,7 +251,7 @@ among printers and scanners, but plenty of other types of device have
 the same deficiency.
 
 For this reason, by default the kernel disables autosuspend (the
-power/control attribute is initialized to "on") for all devices other
+``power/control`` attribute is initialized to ``on``) for all devices other
 than hubs.  Hubs, at least, appear to be reasonably well-behaved in
 this regard.
 
@@ -284,30 +289,30 @@ device by suspending it at the wrong time.  (Highly unlikely, but
 possible.)  Take care.
 
 
-	The driver interface for Power Management
-	-----------------------------------------
+The driver interface for Power Management
+-----------------------------------------
 
 The requirements for a USB driver to support external power management
-are pretty modest; the driver need only define
+are pretty modest; the driver need only define::
 
 	.suspend
 	.resume
 	.reset_resume
 
-methods in its usb_driver structure, and the reset_resume method is
-optional.  The methods' jobs are quite simple:
+methods in its :c:type:`usb_driver` structure, and the ``reset_resume`` method
+is optional.  The methods' jobs are quite simple:
 
-	The suspend method is called to warn the driver that the
+      - The ``suspend`` method is called to warn the driver that the
 	device is going to be suspended.  If the driver returns a
 	negative error code, the suspend will be aborted.  Normally
 	the driver will return 0, in which case it must cancel all
-	outstanding URBs (usb_kill_urb()) and not submit any more.
+	outstanding URBs (:c:func:`usb_kill_urb`) and not submit any more.
 
-	The resume method is called to tell the driver that the
+      - The ``resume`` method is called to tell the driver that the
 	device has been resumed and the driver can return to normal
 	operation.  URBs may once more be submitted.
 
-	The reset_resume method is called to tell the driver that
+      - The ``reset_resume`` method is called to tell the driver that
 	the device has been resumed and it also has been reset.
 	The driver should redo any necessary device initialization,
 	since the device has probably lost most or all of its state
@@ -315,22 +320,22 @@ optional.  The methods' jobs are quite simple:
 	before the suspend).
 
 If the device is disconnected or powered down while it is suspended,
-the disconnect method will be called instead of the resume or
-reset_resume method.  This is also quite likely to happen when
+the ``disconnect`` method will be called instead of the ``resume`` or
+``reset_resume`` method.  This is also quite likely to happen when
 waking up from hibernation, as many systems do not maintain suspend
 current to the USB host controllers during hibernation.  (It's
 possible to work around the hibernation-forces-disconnect problem by
 using the USB Persist facility.)
 
-The reset_resume method is used by the USB Persist facility (see
-Documentation/usb/persist.txt) and it can also be used under certain
-circumstances when CONFIG_USB_PERSIST is not enabled.  Currently, if a
+The ``reset_resume`` method is used by the USB Persist facility (see
+:ref:`usb-persist`) and it can also be used under certain
+circumstances when ``CONFIG_USB_PERSIST`` is not enabled.  Currently, if a
 device is reset during a resume and the driver does not have a
-reset_resume method, the driver won't receive any notification about
-the resume.  Later kernels will call the driver's disconnect method;
+``reset_resume`` method, the driver won't receive any notification about
+the resume.  Later kernels will call the driver's ``disconnect`` method;
 2.6.23 doesn't do this.
 
-USB drivers are bound to interfaces, so their suspend and resume
+USB drivers are bound to interfaces, so their ``suspend`` and ``resume``
 methods get called when the interfaces are suspended or resumed.  In
 principle one might want to suspend some interfaces on a device (i.e.,
 force the drivers for those interface to stop all activity) without
@@ -341,15 +346,15 @@ to suspend or resume some but not all of a device's interfaces.  The
 closest you can come is to unbind the interfaces' drivers.
 
 
-	The driver interface for autosuspend and autoresume
-	---------------------------------------------------
+The driver interface for autosuspend and autoresume
+---------------------------------------------------
 
 To support autosuspend and autoresume, a driver should implement all
 three of the methods listed above.  In addition, a driver indicates
-that it supports autosuspend by setting the .supports_autosuspend flag
+that it supports autosuspend by setting the ``.supports_autosuspend`` flag
 in its usb_driver structure.  It is then responsible for informing the
 USB core whenever one of its interfaces becomes busy or idle.  The
-driver does so by calling these six functions:
+driver does so by calling these six functions::
 
 	int  usb_autopm_get_interface(struct usb_interface *intf);
 	void usb_autopm_put_interface(struct usb_interface *intf);
@@ -368,41 +373,41 @@ autosuspend the device.
 Drivers need not be concerned about balancing changes to the usage
 counter; the USB core will undo any remaining "get"s when a driver
 is unbound from its interface.  As a corollary, drivers must not call
-any of the usb_autopm_* functions after their disconnect() routine has
-returned.
+any of the ``usb_autopm_*`` functions after their ``disconnect``
+routine has returned.
 
 Drivers using the async routines are responsible for their own
 synchronization and mutual exclusion.
 
-	usb_autopm_get_interface() increments the usage counter and
+	:c:func:`usb_autopm_get_interface` increments the usage counter and
 	does an autoresume if the device is suspended.  If the
 	autoresume fails, the counter is decremented back.
 
-	usb_autopm_put_interface() decrements the usage counter and
+	:c:func:`usb_autopm_put_interface` decrements the usage counter and
 	attempts an autosuspend if the new value is = 0.
 
-	usb_autopm_get_interface_async() and
-	usb_autopm_put_interface_async() do almost the same things as
+	:c:func:`usb_autopm_get_interface_async` and
+	:c:func:`usb_autopm_put_interface_async` do almost the same things as
 	their non-async counterparts.  The big difference is that they
 	use a workqueue to do the resume or suspend part of their
 	jobs.  As a result they can be called in an atomic context,
 	such as an URB's completion handler, but when they return the
 	device will generally not yet be in the desired state.
 
-	usb_autopm_get_interface_no_resume() and
-	usb_autopm_put_interface_no_suspend() merely increment or
+	:c:func:`usb_autopm_get_interface_no_resume` and
+	:c:func:`usb_autopm_put_interface_no_suspend` merely increment or
 	decrement the usage counter; they do not attempt to carry out
 	an autoresume or an autosuspend.  Hence they can be called in
 	an atomic context.
 
 The simplest usage pattern is that a driver calls
-usb_autopm_get_interface() in its open routine and
-usb_autopm_put_interface() in its close or release routine.  But other
+:c:func:`usb_autopm_get_interface` in its open routine and
+:c:func:`usb_autopm_put_interface` in its close or release routine.  But other
 patterns are possible.
 
 The autosuspend attempts mentioned above will often fail for one
-reason or another.  For example, the power/control attribute might be
-set to "on", or another interface in the same device might not be
+reason or another.  For example, the ``power/control`` attribute might be
+set to ``on``, or another interface in the same device might not be
 idle.  This is perfectly normal.  If the reason for failure was that
 the device hasn't been idle for long enough, a timer is scheduled to
 carry out the operation automatically when the autosuspend idle-delay
@@ -413,37 +418,37 @@ the device is no longer present or operating properly.  Unlike
 autosuspend, there's no idle-delay for an autoresume.
 
 
-	Other parts of the driver interface
-	-----------------------------------
+Other parts of the driver interface
+-----------------------------------
 
-Drivers can enable autosuspend for their devices by calling
+Drivers can enable autosuspend for their devices by calling::
 
 	usb_enable_autosuspend(struct usb_device *udev);
 
-in their probe() routine, if they know that the device is capable of
+in their :c:func:`probe` routine, if they know that the device is capable of
 suspending and resuming correctly.  This is exactly equivalent to
-writing "auto" to the device's power/control attribute.  Likewise,
-drivers can disable autosuspend by calling
+writing ``auto`` to the device's ``power/control`` attribute.  Likewise,
+drivers can disable autosuspend by calling::
 
 	usb_disable_autosuspend(struct usb_device *udev);
 
-This is exactly the same as writing "on" to the power/control attribute.
+This is exactly the same as writing ``on`` to the ``power/control`` attribute.
 
 Sometimes a driver needs to make sure that remote wakeup is enabled
 during autosuspend.  For example, there's not much point
 autosuspending a keyboard if the user can't cause the keyboard to do a
 remote wakeup by typing on it.  If the driver sets
-intf->needs_remote_wakeup to 1, the kernel won't autosuspend the
+``intf->needs_remote_wakeup`` to 1, the kernel won't autosuspend the
 device if remote wakeup isn't available.  (If the device is already
 autosuspended, though, setting this flag won't cause the kernel to
-autoresume it.  Normally a driver would set this flag in its probe
+autoresume it.  Normally a driver would set this flag in its ``probe``
 method, at which time the device is guaranteed not to be
 autosuspended.)
 
 If a driver does its I/O asynchronously in interrupt context, it
-should call usb_autopm_get_interface_async() before starting output and
-usb_autopm_put_interface_async() when the output queue drains.  When
-it receives an input event, it should call
+should call :c:func:`usb_autopm_get_interface_async` before starting output and
+:c:func:`usb_autopm_put_interface_async` when the output queue drains.  When
+it receives an input event, it should call::
 
 	usb_mark_last_busy(struct usb_device *udev);
 
@@ -453,41 +458,41 @@ be pushed back.  Many of the usb_autopm_* routines also make this call,
 so drivers need to worry only when interrupt-driven input arrives.
 
 Asynchronous operation is always subject to races.  For example, a
-driver may call the usb_autopm_get_interface_async() routine at a time
+driver may call the :c:func:`usb_autopm_get_interface_async` routine at a time
 when the core has just finished deciding the device has been idle for
-long enough but not yet gotten around to calling the driver's suspend
-method.  The suspend method must be responsible for synchronizing with
+long enough but not yet gotten around to calling the driver's ``suspend``
+method.  The ``suspend`` method must be responsible for synchronizing with
 the I/O request routine and the URB completion handler; it should
 cause autosuspends to fail with -EBUSY if the driver needs to use the
 device.
 
 External suspend calls should never be allowed to fail in this way,
 only autosuspend calls.  The driver can tell them apart by applying
-the PMSG_IS_AUTO() macro to the message argument to the suspend
+the :c:func:`PMSG_IS_AUTO` macro to the message argument to the ``suspend``
 method; it will return True for internal PM events (autosuspend) and
 False for external PM events.
 
 
-	Mutual exclusion
-	----------------
+Mutual exclusion
+----------------
 
 For external events -- but not necessarily for autosuspend or
 autoresume -- the device semaphore (udev->dev.sem) will be held when a
-suspend or resume method is called.  This implies that external
-suspend/resume events are mutually exclusive with calls to probe,
-disconnect, pre_reset, and post_reset; the USB core guarantees that
+``suspend`` or ``resume`` method is called.  This implies that external
+suspend/resume events are mutually exclusive with calls to ``probe``,
+``disconnect``, ``pre_reset``, and ``post_reset``; the USB core guarantees that
 this is true of autosuspend/autoresume events as well.
 
 If a driver wants to block all suspend/resume calls during some
 critical section, the best way is to lock the device and call
-usb_autopm_get_interface() (and do the reverse at the end of the
+:c:func:`usb_autopm_get_interface` (and do the reverse at the end of the
 critical section).  Holding the device semaphore will block all
-external PM calls, and the usb_autopm_get_interface() will prevent any
+external PM calls, and the :c:func:`usb_autopm_get_interface` will prevent any
 internal PM calls, even if it fails.  (Exercise: Why?)
 
 
-	Interaction between dynamic PM and system PM
-	--------------------------------------------
+Interaction between dynamic PM and system PM
+--------------------------------------------
 
 Dynamic power management and system power management can interact in
 a couple of ways.
@@ -512,8 +517,8 @@ wakeup may fail and get lost.  Which outcome occurs depends on timing
 and on the hardware and firmware design.
 
 
-	xHCI hardware link PM
-	---------------------
+xHCI hardware link PM
+---------------------
 
 xHCI host controller provides hardware link power management to usb2.0
 (xHCI 1.0 feature) and usb3.0 devices which support link PM. By
@@ -522,11 +527,11 @@ lower power state(L1 for usb2.0 devices, or U1/U2 for usb3.0 devices),
 which state device can enter and resume very quickly.
 
 The user interface for controlling hardware LPM is located in the
-power/ subdirectory of each USB device's sysfs directory, that is, in
-/sys/bus/usb/devices/.../power/ where "..." is the device's ID. The
-relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm.
+``power/`` subdirectory of each USB device's sysfs directory, that is, in
+``/sys/bus/usb/devices/.../power/`` where "..." is the device's ID. The
+relevant attribute files are ``usb2_hardware_lpm`` and ``usb3_hardware_lpm``.
 
-	power/usb2_hardware_lpm
+	``power/usb2_hardware_lpm``
 
 		When a USB2 device which support LPM is plugged to a
 		xHCI host root hub which support software LPM, the
@@ -537,8 +542,8 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm.
 		can write y/Y/1 or n/N/0 to the file to	enable/disable
 		USB2 hardware LPM manually. This is for	test purpose mainly.
 
-	power/usb3_hardware_lpm_u1
-	power/usb3_hardware_lpm_u2
+	``power/usb3_hardware_lpm_u1``
+	``power/usb3_hardware_lpm_u2``
 
 		When a USB 3.0 lpm-capable device is plugged in to a
 		xHCI host which supports link PM, it will check if U1
@@ -550,29 +555,31 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm.
 		indicating whether or not USB3 hardware LPM U1 or U2
 		is enabled for the device.
 
-	USB Port Power Control
-	----------------------
+USB Port Power Control
+----------------------
 
 In addition to suspending endpoint devices and enabling hardware
 controlled link power management, the USB subsystem also has the
 capability to disable power to ports under some conditions.  Power is
-controlled through Set/ClearPortFeature(PORT_POWER) requests to a hub.
+controlled through ``Set/ClearPortFeature(PORT_POWER)`` requests to a hub.
 In the case of a root or platform-internal hub the host controller
-driver translates PORT_POWER requests into platform firmware (ACPI)
+driver translates ``PORT_POWER`` requests into platform firmware (ACPI)
 method calls to set the port power state. For more background see the
-Linux Plumbers Conference 2012 slides [1] and video [2]:
+Linux Plumbers Conference 2012 slides [#f1]_ and video [#f2]_:
 
-Upon receiving a ClearPortFeature(PORT_POWER) request a USB port is
-logically off, and may trigger the actual loss of VBUS to the port [3].
+Upon receiving a ``ClearPortFeature(PORT_POWER)`` request a USB port is
+logically off, and may trigger the actual loss of VBUS to the port [#f3]_.
 VBUS may be maintained in the case where a hub gangs multiple ports into
 a shared power well causing power to remain until all ports in the gang
 are turned off.  VBUS may also be maintained by hub ports configured for
 a charging application.  In any event a logically off port will lose
 connection with its device, not respond to hotplug events, and not
-respond to remote wakeup events*.
+respond to remote wakeup events.
+
+.. warning::
 
-WARNING: turning off a port may result in the inability to hot add a device.
-Please see "User Interface for Port Power Control" for details.
+   turning off a port may result in the inability to hot add a device.
+   Please see "User Interface for Port Power Control" for details.
 
 As far as the effect on the device itself it is similar to what a device
 goes through during system suspend, i.e. the power session is lost.  Any
@@ -581,38 +588,49 @@ similarly affected by a port power cycle event.  For this reason the
 implementation shares the same device recovery path (and honors the same
 quirks) as the system resume path for the hub.
 
-[1]: http://dl.dropbox.com/u/96820575/sarah-sharp-lpt-port-power-off2-mini.pdf
-[2]: http://linuxplumbers.ubicast.tv/videos/usb-port-power-off-kerneluserspace-api/
-[3]: USB 3.1 Section 10.12
-* wakeup note: if a device is configured to send wakeup events the port
+.. [#f1]
+
+  http://dl.dropbox.com/u/96820575/sarah-sharp-lpt-port-power-off2-mini.pdf
+
+.. [#f2]
+
+  http://linuxplumbers.ubicast.tv/videos/usb-port-power-off-kerneluserspace-api/
+
+.. [#f3]
+
+  USB 3.1 Section 10.12
+
+  wakeup note: if a device is configured to send wakeup events the port
   power control implementation will block poweroff attempts on that
   port.
 
 
-	User Interface for Port Power Control
-	-------------------------------------
+User Interface for Port Power Control
+-------------------------------------
 
 The port power control mechanism uses the PM runtime system.  Poweroff is
-requested by clearing the power/pm_qos_no_power_off flag of the port device
+requested by clearing the ``power/pm_qos_no_power_off`` flag of the port device
 (defaults to 1).  If the port is disconnected it will immediately receive a
-ClearPortFeature(PORT_POWER) request.  Otherwise, it will honor the pm runtime
-rules and require the attached child device and all descendants to be suspended.
-This mechanism is dependent on the hub advertising port power switching in its
-hub descriptor (wHubCharacteristics logical power switching mode field).
+``ClearPortFeature(PORT_POWER)`` request.  Otherwise, it will honor the pm
+runtime rules and require the attached child device and all descendants to be
+suspended. This mechanism is dependent on the hub advertising port power
+switching in its hub descriptor (wHubCharacteristics logical power switching
+mode field).
 
 Note, some interface devices/drivers do not support autosuspend.  Userspace may
-need to unbind the interface drivers before the usb_device will suspend.  An
-unbound interface device is suspended by default.  When unbinding, be careful
-to unbind interface drivers, not the driver of the parent usb device.  Also,
-leave hub interface drivers bound.  If the driver for the usb device (not
-interface) is unbound the kernel is no longer able to resume the device.  If a
-hub interface driver is unbound, control of its child ports is lost and all
-attached child-devices will disconnect.  A good rule of thumb is that if the
-'driver/module' link for a device points to /sys/module/usbcore then unbinding
-it will interfere with port power control.
+need to unbind the interface drivers before the :c:type:`usb_device` will
+suspend.  An unbound interface device is suspended by default.  When unbinding,
+be careful to unbind interface drivers, not the driver of the parent usb
+device.  Also, leave hub interface drivers bound.  If the driver for the usb
+device (not interface) is unbound the kernel is no longer able to resume the
+device.  If a hub interface driver is unbound, control of its child ports is
+lost and all attached child-devices will disconnect.  A good rule of thumb is
+that if the 'driver/module' link for a device points to
+``/sys/module/usbcore`` then unbinding it will interfere with port power
+control.
 
 Example of the relevant files for port power control.  Note, in this example
-these files are relative to a usb hub device (prefix).
+these files are relative to a usb hub device (prefix)::
 
      prefix=/sys/devices/pci0000:00/0000:00:14.0/usb3/3-1
 
@@ -631,10 +649,10 @@ these files are relative to a usb hub device (prefix).
 
 In addition to these files some ports may have a 'peer' link to a port on
 another hub.  The expectation is that all superspeed ports have a
-hi-speed peer.
+hi-speed peer::
 
-$prefix/3-1:1.0/3-1-port1/peer -> ../../../../usb2/2-1/2-1:1.0/2-1-port1
-../../../../usb2/2-1/2-1:1.0/2-1-port1/peer -> ../../../../usb3/3-1/3-1:1.0/3-1-port1
+  $prefix/3-1:1.0/3-1-port1/peer -> ../../../../usb2/2-1/2-1:1.0/2-1-port1
+  ../../../../usb2/2-1/2-1:1.0/2-1-port1/peer -> ../../../../usb3/3-1/3-1:1.0/3-1-port1
 
 Distinct from 'companion ports', or 'ehci/xhci shared switchover ports'
 peer ports are simply the hi-speed and superspeed interface pins that
@@ -645,24 +663,26 @@ While a superspeed port is powered off a device may downgrade its
 connection and attempt to connect to the hi-speed pins.  The
 implementation takes steps to prevent this:
 
-1/ Port suspend is sequenced to guarantee that hi-speed ports are powered-off
+1. Port suspend is sequenced to guarantee that hi-speed ports are powered-off
    before their superspeed peer is permitted to power-off.  The implication is
-   that the setting pm_qos_no_power_off to zero on a superspeed port may not cause
-   the port to power-off until its highspeed peer has gone to its runtime suspend
-   state.  Userspace must take care to order the suspensions if it wants to
-   guarantee that a superspeed port will power-off.
+   that the setting ``pm_qos_no_power_off`` to zero on a superspeed port may
+   not cause the port to power-off until its highspeed peer has gone to its
+   runtime suspend state.  Userspace must take care to order the suspensions
+   if it wants to guarantee that a superspeed port will power-off.
 
-2/ Port resume is sequenced to force a superspeed port to power-on prior to its
+2. Port resume is sequenced to force a superspeed port to power-on prior to its
    highspeed peer.
 
-3/ Port resume always triggers an attached child device to resume.  After a
+3. Port resume always triggers an attached child device to resume.  After a
    power session is lost the device may have been removed, or need reset.
    Resuming the child device when the parent port regains power resolves those
-   states and clamps the maximum port power cycle frequency at the rate the child
-   device can suspend (autosuspend-delay) and resume (reset-resume latency).
+   states and clamps the maximum port power cycle frequency at the rate the
+   child device can suspend (autosuspend-delay) and resume (reset-resume
+   latency).
 
 Sysfs files relevant for port power control:
-	<hubdev-portX>/power/pm_qos_no_power_off:
+
+	``<hubdev-portX>/power/pm_qos_no_power_off``:
 		This writable flag controls the state of an idle port.
 		Once all children and descendants have suspended the
 		port may suspend/poweroff provided that
@@ -670,24 +690,24 @@ Sysfs files relevant for port power control:
 		'1' the port will remain active/powered regardless of
 		the stats of descendants.  Defaults to 1.
 
-	<hubdev-portX>/power/runtime_status:
+	``<hubdev-portX>/power/runtime_status``:
 		This file reflects whether the port is 'active' (power is on)
 		or 'suspended' (logically off).  There is no indication to
 		userspace whether VBUS is still supplied.
 
-	<hubdev-portX>/connect_type:
+	``<hubdev-portX>/connect_type``:
 		An advisory read-only flag to userspace indicating the
 		location and connection type of the port.  It returns
 		one of four values 'hotplug', 'hardwired', 'not used',
 		and 'unknown'.  All values, besides unknown, are set by
 		platform firmware.
 
-		"hotplug" indicates an externally connectable/visible
+		``hotplug`` indicates an externally connectable/visible
 		port on the platform.  Typically userspace would choose
 		to keep such a port powered to handle new device
 		connection events.
 
-		"hardwired" refers to a port that is not visible but
+		``hardwired`` refers to a port that is not visible but
 		connectable. Examples are internal ports for USB
 		bluetooth that can be disconnected via an external
 		switch or a port with a hardwired USB camera.  It is
@@ -698,48 +718,50 @@ Sysfs files relevant for port power control:
 		powering off, or to activate the port prior to enabling
 		connection via a switch.
 
-		"not used" refers to an internal port that is expected
+		``not used`` refers to an internal port that is expected
 		to never have a device connected to it.  These may be
 		empty internal ports, or ports that are not physically
 		exposed on a platform.  Considered safe to be
 		powered-off at all times.
 
-		"unknown" means platform firmware does not provide
+		``unknown`` means platform firmware does not provide
 		information for this port.  Most commonly refers to
 		external hub ports which should be considered 'hotplug'
 		for policy decisions.
 
-		NOTE1: since we are relying on the BIOS to get this ACPI
-		information correct, the USB port descriptions may be
-		missing or wrong.
+		.. note::
+
+			- since we are relying on the BIOS to get this ACPI
+			  information correct, the USB port descriptions may
+			  be missing or wrong.
 
-		NOTE2: Take care in clearing pm_qos_no_power_off.  Once
-		power is off this port will
-		not respond to new connect events.
+			- Take care in clearing ``pm_qos_no_power_off``. Once
+			  power is off this port will
+			  not respond to new connect events.
 
 	Once a child device is attached additional constraints are
 	applied before the port is allowed to poweroff.
 
-	<child>/power/control:
-		Must be 'auto', and the port will not
-		power down until <child>/power/runtime_status
+	``<child>/power/control``:
+		Must be ``auto``, and the port will not
+		power down until ``<child>/power/runtime_status``
 		reflects the 'suspended' state.  Default
 		value is controlled by child device driver.
 
-	<child>/power/persist:
-		This defaults to '1' for most devices and indicates if
+	``<child>/power/persist``:
+		This defaults to ``1`` for most devices and indicates if
 		kernel can persist the device's configuration across a
 		power session loss (suspend / port-power event).  When
-		this value is '0' (quirky devices), port poweroff is
+		this value is ``0`` (quirky devices), port poweroff is
 		disabled.
 
-	<child>/driver/unbind:
+	``<child>/driver/unbind``:
 		Wakeup capable devices will block port poweroff.  At
 		this time the only mechanism to clear the usb-internal
 		wakeup-capability for an interface device is to unbind
 		its driver.
 
-Summary of poweroff pre-requisite settings relative to a port device:
+Summary of poweroff pre-requisite settings relative to a port device::
 
 	echo 0 > power/pm_qos_no_power_off
 	echo 0 > peer/power/pm_qos_no_power_off # if it exists
@@ -747,14 +769,14 @@ Summary of poweroff pre-requisite settings relative to a port device:
 	echo auto > <child>/power/control
 	echo 1 > <child>/power/persist # this is the default value
 
-	Suggested Userspace Port Power Policy
-	-------------------------------------
+Suggested Userspace Port Power Policy
+-------------------------------------
 
 As noted above userspace needs to be careful and deliberate about what
 ports are enabled for poweroff.
 
 The default configuration is that all ports start with
-power/pm_qos_no_power_off set to '1' causing ports to always remain
+``power/pm_qos_no_power_off`` set to ``1`` causing ports to always remain
 active.
 
 Given confidence in the platform firmware's description of the ports
@@ -764,7 +786,7 @@ done for 'hardwired' ports provided poweroff is coordinated with any
 connection switch for the port.
 
 A more aggressive userspace policy is to enable USB port power off for
-all ports (set <hubdev-portX>/power/pm_qos_no_power_off to '0') when
+all ports (set ``<hubdev-portX>/power/pm_qos_no_power_off`` to ``0``) when
 some external factor indicates the user has stopped interacting with the
 system.  For example, a distro may want to enable power off all USB
 ports when the screen blanks, and re-power them when the screen becomes
diff --git a/Documentation/driver-api/usb.rst b/Documentation/driver-api/usb/usb.rst
index 851cc40b66b5..dba0f876b36f 100644
--- a/Documentation/driver-api/usb.rst
+++ b/Documentation/driver-api/usb/usb.rst
@@ -1,3 +1,5 @@
+.. _usb-hostside-api:
+
 ===========================
 The Linux-USB Host Side API
 ===========================
@@ -102,16 +104,21 @@ disconnect testing (while the device is active) with each different host
 controller driver, to make sure drivers don't have bugs of their own as
 well as to make sure they aren't relying on some HCD-specific behavior.
 
+.. _usb_chapter9:
+
 USB-Standard Types
 ==================
 
 In ``<linux/usb/ch9.h>`` you will find the USB data types defined in
 chapter 9 of the USB specification. These data types are used throughout
-USB, and in APIs including this host side API, gadget APIs, and usbfs.
+USB, and in APIs including this host side API, gadget APIs, usb character
+devices and debugfs interfaces.
 
 .. kernel-doc:: include/linux/usb/ch9.h
    :internal:
 
+.. _usb_header:
+
 Host-Side Data Types and Macros
 ===============================
 
@@ -198,173 +205,110 @@ significantly reduce hcd-specific behaviors.
 .. kernel-doc:: drivers/usb/core/buffer.c
    :internal:
 
-The USB Filesystem (usbfs)
-==========================
+The USB character device nodes
+==============================
 
-This chapter presents the Linux *usbfs*. You may prefer to avoid writing
-new kernel code for your USB driver; that's the problem that usbfs set
-out to solve. User mode device drivers are usually packaged as
-applications or libraries, and may use usbfs through some programming
-library that wraps it. Such libraries include
-`libusb <http://libusb.sourceforge.net>`__ for C/C++, and
-`jUSB <http://jUSB.sourceforge.net>`__ for Java.
+This chapter presents the Linux character device nodes. You may prefer
+to avoid writing new kernel code for your USB driver. User mode device
+drivers are usually packaged as applications or libraries, and may use
+character devices through some programming library that wraps it.
+Such libraries include:
 
-    **Note**
+ - `libusb <http://libusb.sourceforge.net>`__ for C/C++, and
+ - `jUSB <http://jUSB.sourceforge.net>`__ for Java.
 
-    This particular documentation is incomplete, especially with respect
-    to the asynchronous mode. As of kernel 2.5.66 the code and this
-    (new) documentation need to be cross-reviewed.
+Some old information about it can be seen at the "USB Device Filesystem"
+section of the USB Guide. The latest copy of the USB Guide can be found
+at http://www.linux-usb.org/
 
-Configure usbfs into Linux kernels by enabling the *USB filesystem*
-option (CONFIG_USB_DEVICEFS), and you get basic support for user mode
-USB device drivers. Until relatively recently it was often (confusingly)
-called *usbdevfs* although it wasn't solving what *devfs* was. Every USB
-device will appear in usbfs, regardless of whether or not it has a
-kernel driver.
+.. note::
 
-What files are in "usbfs"?
---------------------------
+  - They were used to be implemented via *usbfs*, but this is not part of
+    the sysfs debug interface.
 
-Conventionally mounted at ``/proc/bus/usb``, usbfs features include:
+   - This particular documentation is incomplete, especially with respect
+     to the asynchronous mode. As of kernel 2.5.66 the code and this
+     (new) documentation need to be cross-reviewed.
 
--  ``/proc/bus/usb/devices`` ... a text file showing each of the USB
-   devices on known to the kernel, and their configuration descriptors.
-   You can also poll() this to learn about new devices.
+What files are in "devtmpfs"?
+-----------------------------
 
--  ``/proc/bus/usb/BBB/DDD`` ... magic files exposing the each device's
+Conventionally mounted at ``/dev/bus/usb/``, usbfs features include:
+
+-  ``/dev/bus/usb/BBB/DDD`` ... magic files exposing the each device's
    configuration descriptors, and supporting a series of ioctls for
    making device requests, including I/O to devices. (Purely for access
    by programs.)
 
-Each bus is given a number (BBB) based on when it was enumerated; within
-each bus, each device is given a similar number (DDD). Those BBB/DDD
+Each bus is given a number (``BBB``) based on when it was enumerated; within
+each bus, each device is given a similar number (``DDD``). Those ``BBB/DDD``
 paths are not "stable" identifiers; expect them to change even if you
 always leave the devices plugged in to the same hub port. *Don't even
 think of saving these in application configuration files.* Stable
 identifiers are available, for user mode applications that want to use
 them. HID and networking devices expose these stable IDs, so that for
 example you can be sure that you told the right UPS to power down its
-second server. "usbfs" doesn't (yet) expose those IDs.
-
-Mounting and Access Control
----------------------------
-
-There are a number of mount options for usbfs, which will be of most
-interest to you if you need to override the default access control
-policy. That policy is that only root may read or write device files
-(``/proc/bus/BBB/DDD``) although anyone may read the ``devices`` or
-``drivers`` files. I/O requests to the device also need the
-CAP_SYS_RAWIO capability,
-
-The significance of that is that by default, all user mode device
-drivers need super-user privileges. You can change modes or ownership in
-a driver setup when the device hotplugs, or maye just start the driver
-right then, as a privileged server (or some activity within one). That's
-the most secure approach for multi-user systems, but for single user
-systems ("trusted" by that user) it's more convenient just to grant
-everyone all access (using the *devmode=0666* option) so the driver can
-start whenever it's needed.
-
-The mount options for usbfs, usable in /etc/fstab or in command line
-invocations of *mount*, are:
-
-*busgid*\ =NNNNN
-    Controls the GID used for the /proc/bus/usb/BBB directories.
-    (Default: 0)
-
-*busmode*\ =MMM
-    Controls the file mode used for the /proc/bus/usb/BBB directories.
-    (Default: 0555)
-
-*busuid*\ =NNNNN
-    Controls the UID used for the /proc/bus/usb/BBB directories.
-    (Default: 0)
-
-*devgid*\ =NNNNN
-    Controls the GID used for the /proc/bus/usb/BBB/DDD files. (Default:
-    0)
-
-*devmode*\ =MMM
-    Controls the file mode used for the /proc/bus/usb/BBB/DDD files.
-    (Default: 0644)
-
-*devuid*\ =NNNNN
-    Controls the UID used for the /proc/bus/usb/BBB/DDD files. (Default:
-    0)
-
-*listgid*\ =NNNNN
-    Controls the GID used for the /proc/bus/usb/devices and drivers
-    files. (Default: 0)
-
-*listmode*\ =MMM
-    Controls the file mode used for the /proc/bus/usb/devices and
-    drivers files. (Default: 0444)
+second server. Pleast note that it doesn't (yet) expose those IDs.
 
-*listuid*\ =NNNNN
-    Controls the UID used for the /proc/bus/usb/devices and drivers
-    files. (Default: 0)
-
-Note that many Linux distributions hard-wire the mount options for usbfs
-in their init scripts, such as ``/etc/rc.d/rc.sysinit``, rather than
-making it easy to set this per-system policy in ``/etc/fstab``.
-
-/proc/bus/usb/devices
----------------------
-
-This file is handy for status viewing tools in user mode, which can scan
-the text format and ignore most of it. More detailed device status
-(including class and vendor status) is available from device-specific
-files. For information about the current format of this file, see the
-``Documentation/usb/proc_usb_info.txt`` file in your Linux kernel
-sources.
-
-This file, in combination with the poll() system call, can also be used
-to detect when devices are added or removed:
-
-::
-
-    int fd;
-    struct pollfd pfd;
-
-    fd = open("/proc/bus/usb/devices", O_RDONLY);
-    pfd = { fd, POLLIN, 0 };
-    for (;;) {
-        /* The first time through, this call will return immediately. */
-        poll(&pfd, 1, -1);
-
-        /* To see what's changed, compare the file's previous and current
-           contents or scan the filesystem.  (Scanning is more precise.) */
-    }
-
-Note that this behavior is intended to be used for informational and
-debug purposes. It would be more appropriate to use programs such as
-udev or HAL to initialize a device or start a user-mode helper program,
-for instance.
-
-/proc/bus/usb/BBB/DDD
----------------------
+/dev/bus/usb/BBB/DDD
+--------------------
 
 Use these files in one of these basic ways:
 
-*They can be read,* producing first the device descriptor (18 bytes) and
-then the descriptors for the current configuration. See the USB 2.0 spec
-for details about those binary data formats. You'll need to convert most
-multibyte values from little endian format to your native host byte
-order, although a few of the fields in the device descriptor (both of
-the BCD-encoded fields, and the vendor and product IDs) will be
-byteswapped for you. Note that configuration descriptors include
-descriptors for interfaces, altsettings, endpoints, and maybe additional
-class descriptors.
-
-*Perform USB operations* using *ioctl()* requests to make endpoint I/O
-requests (synchronously or asynchronously) or manage the device. These
-requests need the CAP_SYS_RAWIO capability, as well as filesystem
-access permissions. Only one ioctl request can be made on one of these
-device files at a time. This means that if you are synchronously reading
-an endpoint from one thread, you won't be able to write to a different
-endpoint from another thread until the read completes. This works for
-*half duplex* protocols, but otherwise you'd use asynchronous i/o
-requests.
+- *They can be read,* producing first the device descriptor (18 bytes) and
+  then the descriptors for the current configuration. See the USB 2.0 spec
+  for details about those binary data formats. You'll need to convert most
+  multibyte values from little endian format to your native host byte
+  order, although a few of the fields in the device descriptor (both of
+  the BCD-encoded fields, and the vendor and product IDs) will be
+  byteswapped for you. Note that configuration descriptors include
+  descriptors for interfaces, altsettings, endpoints, and maybe additional
+  class descriptors.
+
+- *Perform USB operations* using *ioctl()* requests to make endpoint I/O
+  requests (synchronously or asynchronously) or manage the device. These
+  requests need the ``CAP_SYS_RAWIO`` capability, as well as filesystem
+  access permissions. Only one ioctl request can be made on one of these
+  device files at a time. This means that if you are synchronously reading
+  an endpoint from one thread, you won't be able to write to a different
+  endpoint from another thread until the read completes. This works for
+  *half duplex* protocols, but otherwise you'd use asynchronous i/o
+  requests.
+
+Each connected USB device has one file.  The ``BBB`` indicates the bus
+number.  The ``DDD`` indicates the device address on that bus.  Both
+of these numbers are assigned sequentially, and can be reused, so
+you can't rely on them for stable access to devices.  For example,
+it's relatively common for devices to re-enumerate while they are
+still connected (perhaps someone jostled their power supply, hub,
+or USB cable), so a device might be ``002/027`` when you first connect
+it and ``002/048`` sometime later.
+
+These files can be read as binary data.  The binary data consists
+of first the device descriptor, then the descriptors for each
+configuration of the device.  Multi-byte fields in the device descriptor
+are converted to host endianness by the kernel.  The configuration
+descriptors are in bus endian format! The configuration descriptor
+are wTotalLength bytes apart. If a device returns less configuration
+descriptor data than indicated by wTotalLength there will be a hole in
+the file for the missing bytes.  This information is also shown
+in text form by the ``/sys/kernel/debug/usb/devices`` file, described later.
+
+These files may also be used to write user-level drivers for the USB
+devices.  You would open the ``/dev/bus/usb/BBB/DDD`` file read/write,
+read its descriptors to make sure it's the device you expect, and then
+bind to an interface (or perhaps several) using an ioctl call.  You
+would issue more ioctls to the device to communicate to it using
+control, bulk, or other kinds of USB transfers.  The IOCTLs are
+listed in the ``<linux/usbdevice_fs.h>`` file, and at this writing the
+source code (``linux/drivers/usb/core/devio.c``) is the primary reference
+for how to access devices through those files.
+
+Note that since by default these ``BBB/DDD`` files are writable only by
+root, only root can write such user mode drivers.  You can selectively
+grant read/write permissions to other users by using ``chmod``.  Also,
+usbfs mount options such as ``devmode=0666`` may be helpful.
+
 
 Life Cycle of User Mode Drivers
 -------------------------------
@@ -372,7 +316,7 @@ Life Cycle of User Mode Drivers
 Such a driver first needs to find a device file for a device it knows
 how to handle. Maybe it was told about it because a ``/sbin/hotplug``
 event handling agent chose that driver to handle the new device. Or
-maybe it's an application that scans all the /proc/bus/usb device files,
+maybe it's an application that scans all the ``/dev/bus/usb`` device files,
 and ignores most devices. In either case, it should :c:func:`read()`
 all the descriptors from the device file, and check them against what it
 knows how to handle. It might just reject everything except a particular
@@ -407,9 +351,7 @@ The ioctl() Requests
 --------------------
 
 To use these ioctls, you need to include the following headers in your
-userspace program:
-
-::
+userspace program::
 
     #include <linux/usb.h>
     #include <linux/usbdevice_fs.h>
@@ -422,8 +364,8 @@ header.
 Unless noted otherwise, the ioctl requests described here will update
 the modification time on the usbfs file to which they are applied
 (unless they fail). A return of zero indicates success; otherwise, a
-standard USB error code is returned. (These are documented in
-``Documentation/usb/error-codes.txt`` in your kernel sources.)
+standard USB error code is returned (These are documented in
+:ref:`usb-error-codes`).
 
 Each of these files multiplexes access to several I/O streams, one per
 endpoint. Each device has one control endpoint (endpoint zero) which
@@ -458,14 +400,12 @@ USBDEVFS_CLAIMINTERFACE
 
 USBDEVFS_CONNECTINFO
     Says whether the device is lowspeed. The ioctl parameter points to a
-    structure like this:
-
-    ::
+    structure like this::
 
-        struct usbdevfs_connectinfo {
-                unsigned int   devnum;
-                unsigned char  slow;
-        };
+	struct usbdevfs_connectinfo {
+		unsigned int   devnum;
+		unsigned char  slow;
+	};
 
     File modification time is not updated by this request.
 
@@ -477,45 +417,41 @@ USBDEVFS_CONNECTINFO
 USBDEVFS_GETDRIVER
     Returns the name of the kernel driver bound to a given interface (a
     string). Parameter is a pointer to this structure, which is
-    modified:
+    modified::
 
-    ::
-
-        struct usbdevfs_getdriver {
-                unsigned int  interface;
-                char          driver[USBDEVFS_MAXDRIVERNAME + 1];
-        };
+	struct usbdevfs_getdriver {
+		unsigned int  interface;
+		char          driver[USBDEVFS_MAXDRIVERNAME + 1];
+	};
 
     File modification time is not updated by this request.
 
 USBDEVFS_IOCTL
     Passes a request from userspace through to a kernel driver that has
-    an ioctl entry in the *struct usb_driver* it registered.
-
-    ::
-
-        struct usbdevfs_ioctl {
-                int     ifno;
-                int     ioctl_code;
-                void    *data;
-        };
-
-        /* user mode call looks like this.
-         * 'request' becomes the driver->ioctl() 'code' parameter.
-         * the size of 'param' is encoded in 'request', and that data
-         * is copied to or from the driver->ioctl() 'buf' parameter.
-         */
-        static int
-        usbdev_ioctl (int fd, int ifno, unsigned request, void *param)
-        {
-                struct usbdevfs_ioctl   wrapper;
-
-                wrapper.ifno = ifno;
-                wrapper.ioctl_code = request;
-                wrapper.data = param;
-
-                return ioctl (fd, USBDEVFS_IOCTL, &wrapper);
-        }
+    an ioctl entry in the *struct usb_driver* it registered::
+
+	struct usbdevfs_ioctl {
+		int     ifno;
+		int     ioctl_code;
+		void    *data;
+	};
+
+	/* user mode call looks like this.
+	 * 'request' becomes the driver->ioctl() 'code' parameter.
+	 * the size of 'param' is encoded in 'request', and that data
+	 * is copied to or from the driver->ioctl() 'buf' parameter.
+	 */
+	static int
+	usbdev_ioctl (int fd, int ifno, unsigned request, void *param)
+	{
+		struct usbdevfs_ioctl   wrapper;
+
+		wrapper.ifno = ifno;
+		wrapper.ioctl_code = request;
+		wrapper.data = param;
+
+		return ioctl (fd, USBDEVFS_IOCTL, &wrapper);
+	}
 
     File modification time is not updated by this request.
 
@@ -534,11 +470,11 @@ USBDEVFS_RELEASEINTERFACE
     the number of the interface (bInterfaceNumber from descriptor); File
     modification time is not updated by this request.
 
-        **Warning**
+    .. warning::
 
-        *No security check is made to ensure that the task which made
-        the claim is the one which is releasing it. This means that user
-        mode driver may interfere other ones.*
+	*No security check is made to ensure that the task which made
+	the claim is the one which is releasing it. This means that user
+	mode driver may interfere other ones.*
 
 USBDEVFS_RESETEP
     Resets the data toggle value for an endpoint (bulk or interrupt) to
@@ -546,13 +482,13 @@ USBDEVFS_RESETEP
     as identified in the endpoint descriptor), with USB_DIR_IN added
     if the device's endpoint sends data to the host.
 
-        **Warning**
+    .. Warning::
 
-        *Avoid using this request. It should probably be removed.* Using
-        it typically means the device and driver will lose toggle
-        synchronization. If you really lost synchronization, you likely
-        need to completely handshake with the device, using a request
-        like CLEAR_HALT or SET_INTERFACE.
+	*Avoid using this request. It should probably be removed.* Using
+	it typically means the device and driver will lose toggle
+	synchronization. If you really lost synchronization, you likely
+	need to completely handshake with the device, using a request
+	like CLEAR_HALT or SET_INTERFACE.
 
 USBDEVFS_DROP_PRIVILEGES
     This is used to relinquish the ability to do certain operations
@@ -574,21 +510,19 @@ a time.
 
 USBDEVFS_BULK
     Issues a bulk read or write request to the device. The ioctl
-    parameter is a pointer to this structure:
-
-    ::
+    parameter is a pointer to this structure::
 
-        struct usbdevfs_bulktransfer {
-                unsigned int  ep;
-                unsigned int  len;
-                unsigned int  timeout; /* in milliseconds */
-                void          *data;
-        };
+	struct usbdevfs_bulktransfer {
+		unsigned int  ep;
+		unsigned int  len;
+		unsigned int  timeout; /* in milliseconds */
+		void          *data;
+	};
 
-    The "ep" value identifies a bulk endpoint number (1 to 15, as
+    The ``ep`` value identifies a bulk endpoint number (1 to 15, as
     identified in an endpoint descriptor), masked with USB_DIR_IN when
     referring to an endpoint which sends data to the host from the
-    device. The length of the data buffer is identified by "len"; Recent
+    device. The length of the data buffer is identified by ``len``; Recent
     kernels support requests up to about 128KBytes. *FIXME say how read
     length is returned, and how short reads are handled.*.
 
@@ -600,31 +534,29 @@ USBDEVFS_CLEAR_HALT
     which sends data to the host from the device.
 
     Use this on bulk or interrupt endpoints which have stalled,
-    returning *-EPIPE* status to a data transfer request. Do not issue
+    returning ``-EPIPE`` status to a data transfer request. Do not issue
     the control request directly, since that could invalidate the host's
     record of the data toggle.
 
 USBDEVFS_CONTROL
     Issues a control request to the device. The ioctl parameter points
-    to a structure like this:
-
-    ::
-
-        struct usbdevfs_ctrltransfer {
-                __u8   bRequestType;
-                __u8   bRequest;
-                __u16  wValue;
-                __u16  wIndex;
-                __u16  wLength;
-                __u32  timeout;  /* in milliseconds */
-                void   *data;
-        };
+    to a structure like this::
+
+	struct usbdevfs_ctrltransfer {
+		__u8   bRequestType;
+		__u8   bRequest;
+		__u16  wValue;
+		__u16  wIndex;
+		__u16  wLength;
+		__u32  timeout;  /* in milliseconds */
+		void   *data;
+	};
 
     The first eight bytes of this structure are the contents of the
     SETUP packet to be sent to the device; see the USB 2.0 specification
     for details. The bRequestType value is composed by combining a
-    USB_TYPE_\* value, a USB_DIR_\* value, and a USB_RECIP_\*
-    value (from *<linux/usb.h>*). If wLength is nonzero, it describes
+    ``USB_TYPE_*`` value, a ``USB_DIR_*`` value, and a ``USB_RECIP_*``
+    value (from ``linux/usb.h``). If wLength is nonzero, it describes
     the length of the data buffer, which is either written to the device
     (USB_DIR_OUT) or read from the device (USB_DIR_IN).
 
@@ -638,22 +570,20 @@ USBDEVFS_RESET
     the reset, this rebinds all device interfaces. File modification
     time is not updated by this request.
 
-        **Warning**
+.. warning::
 
-        *Avoid using this call* until some usbcore bugs get fixed, since
-        it does not fully synchronize device, interface, and driver (not
-        just usbfs) state.
+	*Avoid using this call* until some usbcore bugs get fixed, since
+	it does not fully synchronize device, interface, and driver (not
+	just usbfs) state.
 
 USBDEVFS_SETINTERFACE
     Sets the alternate setting for an interface. The ioctl parameter is
-    a pointer to a structure like this:
+    a pointer to a structure like this::
 
-    ::
-
-        struct usbdevfs_setinterface {
-                unsigned int  interface;
-                unsigned int  altsetting;
-        };
+	struct usbdevfs_setinterface {
+		unsigned int  interface;
+		unsigned int  altsetting;
+	};
 
     File modification time is not updated by this request.
 
@@ -669,11 +599,11 @@ USBDEVFS_SETCONFIGURATION
     configuration (bConfigurationValue from descriptor). File
     modification time is not updated by this request.
 
-        **Warning**
+.. warning::
 
-        *Avoid using this call* until some usbcore bugs get fixed, since
-        it does not fully synchronize device, interface, and driver (not
-        just usbfs) state.
+	*Avoid using this call* until some usbcore bugs get fixed, since
+	it does not fully synchronize device, interface, and driver (not
+	just usbfs) state.
 
 Asynchronous I/O Support
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -688,7 +618,7 @@ the blocking is separate.
 
 These requests are packaged into a structure that resembles the URB used
 by kernel device drivers. (No POSIX Async I/O support here, sorry.) It
-identifies the endpoint type (USBDEVFS_URB_TYPE_\*), endpoint
+identifies the endpoint type (``USBDEVFS_URB_TYPE_*``), endpoint
 (number, masked with USB_DIR_IN as appropriate), buffer and length,
 and a user "context" value serving to uniquely identify each request.
 (It's usually a pointer to per-request data.) Flags can modify requests
@@ -702,30 +632,28 @@ When usbfs returns these urbs, the status value is updated, and the
 buffer may have been modified. Except for isochronous transfers, the
 actual_length is updated to say how many bytes were transferred; if the
 USBDEVFS_URB_DISABLE_SPD flag is set ("short packets are not OK"), if
-fewer bytes were read than were requested then you get an error report.
-
-::
+fewer bytes were read than were requested then you get an error report::
 
     struct usbdevfs_iso_packet_desc {
-            unsigned int                     length;
-            unsigned int                     actual_length;
-            unsigned int                     status;
+	    unsigned int                     length;
+	    unsigned int                     actual_length;
+	    unsigned int                     status;
     };
 
     struct usbdevfs_urb {
-            unsigned char                    type;
-            unsigned char                    endpoint;
-            int                              status;
-            unsigned int                     flags;
-            void                             *buffer;
-            int                              buffer_length;
-            int                              actual_length;
-            int                              start_frame;
-            int                              number_of_packets;
-            int                              error_count;
-            unsigned int                     signr;
-            void                             *usercontext;
-            struct usbdevfs_iso_packet_desc  iso_frame_desc[];
+	    unsigned char                    type;
+	    unsigned char                    endpoint;
+	    int                              status;
+	    unsigned int                     flags;
+	    void                             *buffer;
+	    int                              buffer_length;
+	    int                              actual_length;
+	    int                              start_frame;
+	    int                              number_of_packets;
+	    int                              error_count;
+	    unsigned int                     signr;
+	    void                             *usercontext;
+	    struct usbdevfs_iso_packet_desc  iso_frame_desc[];
     };
 
 For these asynchronous requests, the file modification time reflects
@@ -746,3 +674,374 @@ USBDEVFS_REAPURBNDELAY
 
 USBDEVFS_SUBMITURB
     *TBS*
+
+The USB devices
+===============
+
+The USB devices are now exported via debugfs:
+
+-  ``/sys/kernel/debug/usb/devices`` ... a text file showing each of the USB
+   devices on known to the kernel, and their configuration descriptors.
+   You can also poll() this to learn about new devices.
+
+/sys/kernel/debug/usb/devices
+-----------------------------
+
+This file is handy for status viewing tools in user mode, which can scan
+the text format and ignore most of it. More detailed device status
+(including class and vendor status) is available from device-specific
+files. For information about the current format of this file, see the
+``Documentation/usb/proc_usb_info.txt`` file in your Linux kernel
+sources.
+
+This file, in combination with the poll() system call, can also be used
+to detect when devices are added or removed::
+
+    int fd;
+    struct pollfd pfd;
+
+    fd = open("/sys/kernel/debug/usb/devices", O_RDONLY);
+    pfd = { fd, POLLIN, 0 };
+    for (;;) {
+	/* The first time through, this call will return immediately. */
+	poll(&pfd, 1, -1);
+
+	/* To see what's changed, compare the file's previous and current
+	   contents or scan the filesystem.  (Scanning is more precise.) */
+    }
+
+Note that this behavior is intended to be used for informational and
+debug purposes. It would be more appropriate to use programs such as
+udev or HAL to initialize a device or start a user-mode helper program,
+for instance.
+
+In this file, each device's output has multiple lines of ASCII output.
+
+I made it ASCII instead of binary on purpose, so that someone
+can obtain some useful data from it without the use of an
+auxiliary program.  However, with an auxiliary program, the numbers
+in the first 4 columns of each ``T:`` line (topology info:
+Lev, Prnt, Port, Cnt) can be used to build a USB topology diagram.
+
+Each line is tagged with a one-character ID for that line::
+
+	T = Topology (etc.)
+	B = Bandwidth (applies only to USB host controllers, which are
+	virtualized as root hubs)
+	D = Device descriptor info.
+	P = Product ID info. (from Device descriptor, but they won't fit
+	together on one line)
+	S = String descriptors.
+	C = Configuration descriptor info. (* = active configuration)
+	I = Interface descriptor info.
+	E = Endpoint descriptor info.
+
+/sys/kernel/debug/usb/devices output format
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Legend::
+  d = decimal number (may have leading spaces or 0's)
+  x = hexadecimal number (may have leading spaces or 0's)
+  s = string
+
+
+
+Topology info
+^^^^^^^^^^^^^
+
+::
+
+	T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=dddd MxCh=dd
+	|   |      |      |       |       |      |        |        |__MaxChildren
+	|   |      |      |       |       |      |        |__Device Speed in Mbps
+	|   |      |      |       |       |      |__DeviceNumber
+	|   |      |      |       |       |__Count of devices at this level
+	|   |      |      |       |__Connector/Port on Parent for this device
+	|   |      |      |__Parent DeviceNumber
+	|   |      |__Level in topology for this bus
+	|   |__Bus number
+	|__Topology info tag
+
+Speed may be:
+
+	======= ======================================================
+	1.5	Mbit/s for low speed USB
+	12	Mbit/s for full speed USB
+	480	Mbit/s for high speed USB (added for USB 2.0);
+		also used for Wireless USB, which has no fixed speed
+	5000	Mbit/s for SuperSpeed USB (added for USB 3.0)
+	======= ======================================================
+
+For reasons lost in the mists of time, the Port number is always
+too low by 1.  For example, a device plugged into port 4 will
+show up with ``Port=03``.
+
+Bandwidth info
+^^^^^^^^^^^^^^
+
+::
+
+	B:  Alloc=ddd/ddd us (xx%), #Int=ddd, #Iso=ddd
+	|   |                       |         |__Number of isochronous requests
+	|   |                       |__Number of interrupt requests
+	|   |__Total Bandwidth allocated to this bus
+	|__Bandwidth info tag
+
+Bandwidth allocation is an approximation of how much of one frame
+(millisecond) is in use.  It reflects only periodic transfers, which
+are the only transfers that reserve bandwidth.  Control and bulk
+transfers use all other bandwidth, including reserved bandwidth that
+is not used for transfers (such as for short packets).
+
+The percentage is how much of the "reserved" bandwidth is scheduled by
+those transfers.  For a low or full speed bus (loosely, "USB 1.1"),
+90% of the bus bandwidth is reserved.  For a high speed bus (loosely,
+"USB 2.0") 80% is reserved.
+
+
+Device descriptor info & Product ID info
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+::
+
+	D:  Ver=x.xx Cls=xx(s) Sub=xx Prot=xx MxPS=dd #Cfgs=dd
+	P:  Vendor=xxxx ProdID=xxxx Rev=xx.xx
+
+where::
+
+	D:  Ver=x.xx Cls=xx(sssss) Sub=xx Prot=xx MxPS=dd #Cfgs=dd
+	|   |        |             |      |       |       |__NumberConfigurations
+	|   |        |             |      |       |__MaxPacketSize of Default Endpoint
+	|   |        |             |      |__DeviceProtocol
+	|   |        |             |__DeviceSubClass
+	|   |        |__DeviceClass
+	|   |__Device USB version
+	|__Device info tag #1
+
+where::
+
+	P:  Vendor=xxxx ProdID=xxxx Rev=xx.xx
+	|   |           |           |__Product revision number
+	|   |           |__Product ID code
+	|   |__Vendor ID code
+	|__Device info tag #2
+
+
+String descriptor info
+^^^^^^^^^^^^^^^^^^^^^^
+::
+
+	S:  Manufacturer=ssss
+	|   |__Manufacturer of this device as read from the device.
+	|      For USB host controller drivers (virtual root hubs) this may
+	|      be omitted, or (for newer drivers) will identify the kernel
+	|      version and the driver which provides this hub emulation.
+	|__String info tag
+
+	S:  Product=ssss
+	|   |__Product description of this device as read from the device.
+	|      For older USB host controller drivers (virtual root hubs) this
+	|      indicates the driver; for newer ones, it's a product (and vendor)
+	|      description that often comes from the kernel's PCI ID database.
+	|__String info tag
+
+	S:  SerialNumber=ssss
+	|   |__Serial Number of this device as read from the device.
+	|      For USB host controller drivers (virtual root hubs) this is
+	|      some unique ID, normally a bus ID (address or slot name) that
+	|      can't be shared with any other device.
+	|__String info tag
+
+
+
+Configuration descriptor info
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+::
+
+	C:* #Ifs=dd Cfg#=dd Atr=xx MPwr=dddmA
+	| | |       |       |      |__MaxPower in mA
+	| | |       |       |__Attributes
+	| | |       |__ConfiguratioNumber
+	| | |__NumberOfInterfaces
+	| |__ "*" indicates the active configuration (others are " ")
+	|__Config info tag
+
+USB devices may have multiple configurations, each of which act
+rather differently.  For example, a bus-powered configuration
+might be much less capable than one that is self-powered.  Only
+one device configuration can be active at a time; most devices
+have only one configuration.
+
+Each configuration consists of one or more interfaces.  Each
+interface serves a distinct "function", which is typically bound
+to a different USB device driver.  One common example is a USB
+speaker with an audio interface for playback, and a HID interface
+for use with software volume control.
+
+Interface descriptor info (can be multiple per Config)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+::
+
+	I:* If#=dd Alt=dd #EPs=dd Cls=xx(sssss) Sub=xx Prot=xx Driver=ssss
+	| | |      |      |       |             |      |       |__Driver name
+	| | |      |      |       |             |      |          or "(none)"
+	| | |      |      |       |             |      |__InterfaceProtocol
+	| | |      |      |       |             |__InterfaceSubClass
+	| | |      |      |       |__InterfaceClass
+	| | |      |      |__NumberOfEndpoints
+	| | |      |__AlternateSettingNumber
+	| | |__InterfaceNumber
+	| |__ "*" indicates the active altsetting (others are " ")
+	|__Interface info tag
+
+A given interface may have one or more "alternate" settings.
+For example, default settings may not use more than a small
+amount of periodic bandwidth.  To use significant fractions
+of bus bandwidth, drivers must select a non-default altsetting.
+
+Only one setting for an interface may be active at a time, and
+only one driver may bind to an interface at a time.  Most devices
+have only one alternate setting per interface.
+
+
+Endpoint descriptor info (can be multiple per Interface)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+::
+
+	E:  Ad=xx(s) Atr=xx(ssss) MxPS=dddd Ivl=dddss
+	|   |        |            |         |__Interval (max) between transfers
+	|   |        |            |__EndpointMaxPacketSize
+	|   |        |__Attributes(EndpointType)
+	|   |__EndpointAddress(I=In,O=Out)
+	|__Endpoint info tag
+
+The interval is nonzero for all periodic (interrupt or isochronous)
+endpoints.  For high speed endpoints the transfer interval may be
+measured in microseconds rather than milliseconds.
+
+For high speed periodic endpoints, the ``EndpointMaxPacketSize`` reflects
+the per-microframe data transfer size.  For "high bandwidth"
+endpoints, that can reflect two or three packets (for up to
+3KBytes every 125 usec) per endpoint.
+
+With the Linux-USB stack, periodic bandwidth reservations use the
+transfer intervals and sizes provided by URBs, which can be less
+than those found in endpoint descriptor.
+
+Usage examples
+~~~~~~~~~~~~~~
+
+If a user or script is interested only in Topology info, for
+example, use something like ``grep ^T: /sys/kernel/debug/usb/devices``
+for only the Topology lines.  A command like
+``grep -i ^[tdp]: /sys/kernel/debug/usb/devices`` can be used to list
+only the lines that begin with the characters in square brackets,
+where the valid characters are TDPCIE.  With a slightly more able
+script, it can display any selected lines (for example, only T, D,
+and P lines) and change their output format.  (The ``procusb``
+Perl script is the beginning of this idea.  It will list only
+selected lines [selected from TBDPSCIE] or "All" lines from
+``/sys/kernel/debug/usb/devices``.)
+
+The Topology lines can be used to generate a graphic/pictorial
+of the USB devices on a system's root hub.  (See more below
+on how to do this.)
+
+The Interface lines can be used to determine what driver is
+being used for each device, and which altsetting it activated.
+
+The Configuration lines could be used to list maximum power
+(in milliamps) that a system's USB devices are using.
+For example, ``grep ^C: /sys/kernel/debug/usb/devices``.
+
+
+Here's an example, from a system which has a UHCI root hub,
+an external hub connected to the root hub, and a mouse and
+a serial converter connected to the external hub.
+
+::
+
+	T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
+	B:  Alloc= 28/900 us ( 3%), #Int=  2, #Iso=  0
+	D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
+	P:  Vendor=0000 ProdID=0000 Rev= 0.00
+	S:  Product=USB UHCI Root Hub
+	S:  SerialNumber=dce0
+	C:* #Ifs= 1 Cfg#= 1 Atr=40 MxPwr=  0mA
+	I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
+	E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=255ms
+
+	T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
+	D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
+	P:  Vendor=0451 ProdID=1446 Rev= 1.00
+	C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA
+	I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
+	E:  Ad=81(I) Atr=03(Int.) MxPS=   1 Ivl=255ms
+
+	T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
+	D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
+	P:  Vendor=04b4 ProdID=0001 Rev= 0.00
+	C:* #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=100mA
+	I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
+	E:  Ad=81(I) Atr=03(Int.) MxPS=   3 Ivl= 10ms
+
+	T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
+	D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
+	P:  Vendor=0565 ProdID=0001 Rev= 1.08
+	S:  Manufacturer=Peracom Networks, Inc.
+	S:  Product=Peracom USB to Serial Converter
+	C:* #Ifs= 1 Cfg#= 1 Atr=a0 MxPwr=100mA
+	I:  If#= 0 Alt= 0 #EPs= 3 Cls=00(>ifc ) Sub=00 Prot=00 Driver=serial
+	E:  Ad=81(I) Atr=02(Bulk) MxPS=  64 Ivl= 16ms
+	E:  Ad=01(O) Atr=02(Bulk) MxPS=  16 Ivl= 16ms
+	E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=  8ms
+
+
+Selecting only the ``T:`` and ``I:`` lines from this (for example, by using
+``procusb ti``), we have
+
+::
+
+	T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
+	T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
+	I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
+	T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
+	I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
+	T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
+	I:  If#= 0 Alt= 0 #EPs= 3 Cls=00(>ifc ) Sub=00 Prot=00 Driver=serial
+
+
+Physically this looks like (or could be converted to)::
+
+                      +------------------+
+                      |  PC/root_hub (12)|   Dev# = 1
+                      +------------------+   (nn) is Mbps.
+    Level 0           |  CN.0   |  CN.1  |   [CN = connector/port #]
+                      +------------------+
+                          /
+                         /
+            +-----------------------+
+  Level 1   | Dev#2: 4-port hub (12)|
+            +-----------------------+
+            |CN.0 |CN.1 |CN.2 |CN.3 |
+            +-----------------------+
+                \           \____________________
+                 \_____                          \
+                       \                          \
+               +--------------------+      +--------------------+
+  Level 2      | Dev# 3: mouse (1.5)|      | Dev# 4: serial (12)|
+               +--------------------+      +--------------------+
+
+
+
+Or, in a more tree-like structure (ports [Connectors] without
+connections could be omitted)::
+
+	PC:  Dev# 1, root hub, 2 ports, 12 Mbps
+	|_ CN.0:  Dev# 2, hub, 4 ports, 12 Mbps
+	     |_ CN.0:  Dev #3, mouse, 1.5 Mbps
+	     |_ CN.1:
+	     |_ CN.2:  Dev #4, serial, 12 Mbps
+	     |_ CN.3:
+	|_ CN.1:
diff --git a/Documentation/driver-api/usb/writing_musb_glue_layer.rst b/Documentation/driver-api/usb/writing_musb_glue_layer.rst
new file mode 100644
index 000000000000..e90e8fa95600
--- /dev/null
+++ b/Documentation/driver-api/usb/writing_musb_glue_layer.rst
@@ -0,0 +1,723 @@
+=========================
+Writing a MUSB Glue Layer
+=========================
+
+:Author: Apelete Seketeli
+
+Introduction
+============
+
+The Linux MUSB subsystem is part of the larger Linux USB subsystem. It
+provides support for embedded USB Device Controllers (UDC) that do not
+use Universal Host Controller Interface (UHCI) or Open Host Controller
+Interface (OHCI).
+
+Instead, these embedded UDC rely on the USB On-the-Go (OTG)
+specification which they implement at least partially. The silicon
+reference design used in most cases is the Multipoint USB Highspeed
+Dual-Role Controller (MUSB HDRC) found in the Mentor Graphics Inventraâ„¢
+design.
+
+As a self-taught exercise I have written an MUSB glue layer for the
+Ingenic JZ4740 SoC, modelled after the many MUSB glue layers in the
+kernel source tree. This layer can be found at
+``drivers/usb/musb/jz4740.c``. In this documentation I will walk through the
+basics of the ``jz4740.c`` glue layer, explaining the different pieces and
+what needs to be done in order to write your own device glue layer.
+
+.. _musb-basics:
+
+Linux MUSB Basics
+=================
+
+To get started on the topic, please read USB On-the-Go Basics (see
+Resources) which provides an introduction of USB OTG operation at the
+hardware level. A couple of wiki pages by Texas Instruments and Analog
+Devices also provide an overview of the Linux kernel MUSB configuration,
+albeit focused on some specific devices provided by these companies.
+Finally, getting acquainted with the USB specification at USB home page
+may come in handy, with practical instance provided through the Writing
+USB Device Drivers documentation (again, see Resources).
+
+Linux USB stack is a layered architecture in which the MUSB controller
+hardware sits at the lowest. The MUSB controller driver abstract the
+MUSB controller hardware to the Linux USB stack::
+
+	  ------------------------
+	  |                      | <------- drivers/usb/gadget
+	  | Linux USB Core Stack | <------- drivers/usb/host
+	  |                      | <------- drivers/usb/core
+	  ------------------------
+		     �
+	 --------------------------
+	 |                        | <------ drivers/usb/musb/musb_gadget.c
+	 | MUSB Controller driver | <------ drivers/usb/musb/musb_host.c
+	 |                        | <------ drivers/usb/musb/musb_core.c
+	 --------------------------
+		     �
+      ---------------------------------
+      | MUSB Platform Specific Driver |
+      |                               | <-- drivers/usb/musb/jz4740.c
+      |       aka "Glue Layer"        |
+      ---------------------------------
+		     �
+      ---------------------------------
+      |   MUSB Controller Hardware    |
+      ---------------------------------
+
+As outlined above, the glue layer is actually the platform specific code
+sitting in between the controller driver and the controller hardware.
+
+Just like a Linux USB driver needs to register itself with the Linux USB
+subsystem, the MUSB glue layer needs first to register itself with the
+MUSB controller driver. This will allow the controller driver to know
+about which device the glue layer supports and which functions to call
+when a supported device is detected or released; remember we are talking
+about an embedded controller chip here, so no insertion or removal at
+run-time.
+
+All of this information is passed to the MUSB controller driver through
+a :c:type:`platform_driver` structure defined in the glue layer as::
+
+    static struct platform_driver jz4740_driver = {
+	.probe      = jz4740_probe,
+	.remove     = jz4740_remove,
+	.driver     = {
+	    .name   = "musb-jz4740",
+	},
+    };
+
+The probe and remove function pointers are called when a matching device
+is detected and, respectively, released. The name string describes the
+device supported by this glue layer. In the current case it matches a
+platform_device structure declared in ``arch/mips/jz4740/platform.c``. Note
+that we are not using device tree bindings here.
+
+In order to register itself to the controller driver, the glue layer
+goes through a few steps, basically allocating the controller hardware
+resources and initialising a couple of circuits. To do so, it needs to
+keep track of the information used throughout these steps. This is done
+by defining a private ``jz4740_glue`` structure::
+
+    struct jz4740_glue {
+	struct device           *dev;
+	struct platform_device  *musb;
+	struct clk      *clk;
+    };
+
+
+The dev and musb members are both device structure variables. The first
+one holds generic information about the device, since it's the basic
+device structure, and the latter holds information more closely related
+to the subsystem the device is registered to. The clk variable keeps
+information related to the device clock operation.
+
+Let's go through the steps of the probe function that leads the glue
+layer to register itself to the controller driver.
+
+.. note::
+
+   For the sake of readability each function will be split in logical
+   parts, each part being shown as if it was independent from the others.
+
+.. code-block:: c
+    :emphasize-lines: 8,12,18
+
+    static int jz4740_probe(struct platform_device *pdev)
+    {
+	struct platform_device      *musb;
+	struct jz4740_glue      *glue;
+	struct clk                      *clk;
+	int             ret;
+
+	glue = devm_kzalloc(&pdev->dev, sizeof(*glue), GFP_KERNEL);
+	if (!glue)
+	    return -ENOMEM;
+
+	musb = platform_device_alloc("musb-hdrc", PLATFORM_DEVID_AUTO);
+	if (!musb) {
+	    dev_err(&pdev->dev, "failed to allocate musb device\n");
+	    return -ENOMEM;
+	}
+
+	clk = devm_clk_get(&pdev->dev, "udc");
+	if (IS_ERR(clk)) {
+	    dev_err(&pdev->dev, "failed to get clock\n");
+	    ret = PTR_ERR(clk);
+	    goto err_platform_device_put;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+	    dev_err(&pdev->dev, "failed to enable clock\n");
+	    goto err_platform_device_put;
+	}
+
+	musb->dev.parent        = &pdev->dev;
+
+	glue->dev           = &pdev->dev;
+	glue->musb          = musb;
+	glue->clk           = clk;
+
+	return 0;
+
+    err_platform_device_put:
+	platform_device_put(musb);
+	return ret;
+    }
+
+The first few lines of the probe function allocate and assign the glue,
+musb and clk variables. The ``GFP_KERNEL`` flag (line 8) allows the
+allocation process to sleep and wait for memory, thus being usable in a
+locking situation. The ``PLATFORM_DEVID_AUTO`` flag (line 12) allows
+automatic allocation and management of device IDs in order to avoid
+device namespace collisions with explicit IDs. With :c:func:`devm_clk_get`
+(line 18) the glue layer allocates the clock -- the ``devm_`` prefix
+indicates that :c:func:`clk_get` is managed: it automatically frees the
+allocated clock resource data when the device is released -- and enable
+it.
+
+
+
+Then comes the registration steps:
+
+.. code-block:: c
+    :emphasize-lines: 3,5,7,9,16
+
+    static int jz4740_probe(struct platform_device *pdev)
+    {
+	struct musb_hdrc_platform_data  *pdata = &jz4740_musb_platform_data;
+
+	pdata->platform_ops     = &jz4740_musb_ops;
+
+	platform_set_drvdata(pdev, glue);
+
+	ret = platform_device_add_resources(musb, pdev->resource,
+			    pdev->num_resources);
+	if (ret) {
+	    dev_err(&pdev->dev, "failed to add resources\n");
+	    goto err_clk_disable;
+	}
+
+	ret = platform_device_add_data(musb, pdata, sizeof(*pdata));
+	if (ret) {
+	    dev_err(&pdev->dev, "failed to add platform_data\n");
+	    goto err_clk_disable;
+	}
+
+	return 0;
+
+    err_clk_disable:
+	clk_disable_unprepare(clk);
+    err_platform_device_put:
+	platform_device_put(musb);
+	return ret;
+    }
+
+The first step is to pass the device data privately held by the glue
+layer on to the controller driver through :c:func:`platform_set_drvdata`
+(line 7). Next is passing on the device resources information, also privately
+held at that point, through :c:func:`platform_device_add_resources` (line 9).
+
+Finally comes passing on the platform specific data to the controller
+driver (line 16). Platform data will be discussed in
+:ref:`musb-dev-platform-data`, but here we are looking at the
+``platform_ops`` function pointer (line 5) in ``musb_hdrc_platform_data``
+structure (line 3). This function pointer allows the MUSB controller
+driver to know which function to call for device operation::
+
+    static const struct musb_platform_ops jz4740_musb_ops = {
+	.init       = jz4740_musb_init,
+	.exit       = jz4740_musb_exit,
+    };
+
+Here we have the minimal case where only init and exit functions are
+called by the controller driver when needed. Fact is the JZ4740 MUSB
+controller is a basic controller, lacking some features found in other
+controllers, otherwise we may also have pointers to a few other
+functions like a power management function or a function to switch
+between OTG and non-OTG modes, for instance.
+
+At that point of the registration process, the controller driver
+actually calls the init function:
+
+   .. code-block:: c
+    :emphasize-lines: 12,14
+
+    static int jz4740_musb_init(struct musb *musb)
+    {
+	musb->xceiv = usb_get_phy(USB_PHY_TYPE_USB2);
+	if (!musb->xceiv) {
+	    pr_err("HS UDC: no transceiver configured\n");
+	    return -ENODEV;
+	}
+
+	/* Silicon does not implement ConfigData register.
+	 * Set dyn_fifo to avoid reading EP config from hardware.
+	 */
+	musb->dyn_fifo = true;
+
+	musb->isr = jz4740_musb_interrupt;
+
+	return 0;
+    }
+
+The goal of ``jz4740_musb_init()`` is to get hold of the transceiver
+driver data of the MUSB controller hardware and pass it on to the MUSB
+controller driver, as usual. The transceiver is the circuitry inside the
+controller hardware responsible for sending/receiving the USB data.
+Since it is an implementation of the physical layer of the OSI model,
+the transceiver is also referred to as PHY.
+
+Getting hold of the ``MUSB PHY`` driver data is done with ``usb_get_phy()``
+which returns a pointer to the structure containing the driver instance
+data. The next couple of instructions (line 12 and 14) are used as a
+quirk and to setup IRQ handling respectively. Quirks and IRQ handling
+will be discussed later in :ref:`musb-dev-quirks` and
+:ref:`musb-handling-irqs`\ ::
+
+    static int jz4740_musb_exit(struct musb *musb)
+    {
+	usb_put_phy(musb->xceiv);
+
+	return 0;
+    }
+
+Acting as the counterpart of init, the exit function releases the MUSB
+PHY driver when the controller hardware itself is about to be released.
+
+Again, note that init and exit are fairly simple in this case due to the
+basic set of features of the JZ4740 controller hardware. When writing an
+musb glue layer for a more complex controller hardware, you might need
+to take care of more processing in those two functions.
+
+Returning from the init function, the MUSB controller driver jumps back
+into the probe function::
+
+    static int jz4740_probe(struct platform_device *pdev)
+    {
+	ret = platform_device_add(musb);
+	if (ret) {
+	    dev_err(&pdev->dev, "failed to register musb device\n");
+	    goto err_clk_disable;
+	}
+
+	return 0;
+
+    err_clk_disable:
+	clk_disable_unprepare(clk);
+    err_platform_device_put:
+	platform_device_put(musb);
+	return ret;
+    }
+
+This is the last part of the device registration process where the glue
+layer adds the controller hardware device to Linux kernel device
+hierarchy: at this stage, all known information about the device is
+passed on to the Linux USB core stack:
+
+   .. code-block:: c
+    :emphasize-lines: 5,6
+
+    static int jz4740_remove(struct platform_device *pdev)
+    {
+	struct jz4740_glue  *glue = platform_get_drvdata(pdev);
+
+	platform_device_unregister(glue->musb);
+	clk_disable_unprepare(glue->clk);
+
+	return 0;
+    }
+
+Acting as the counterpart of probe, the remove function unregister the
+MUSB controller hardware (line 5) and disable the clock (line 6),
+allowing it to be gated.
+
+.. _musb-handling-irqs:
+
+Handling IRQs
+=============
+
+Additionally to the MUSB controller hardware basic setup and
+registration, the glue layer is also responsible for handling the IRQs:
+
+   .. code-block:: c
+    :emphasize-lines: 7,9-11,14,24
+
+    static irqreturn_t jz4740_musb_interrupt(int irq, void *__hci)
+    {
+	unsigned long   flags;
+	irqreturn_t     retval = IRQ_NONE;
+	struct musb     *musb = __hci;
+
+	spin_lock_irqsave(&musb->lock, flags);
+
+	musb->int_usb = musb_readb(musb->mregs, MUSB_INTRUSB);
+	musb->int_tx = musb_readw(musb->mregs, MUSB_INTRTX);
+	musb->int_rx = musb_readw(musb->mregs, MUSB_INTRRX);
+
+	/*
+	 * The controller is gadget only, the state of the host mode IRQ bits is
+	 * undefined. Mask them to make sure that the musb driver core will
+	 * never see them set
+	 */
+	musb->int_usb &= MUSB_INTR_SUSPEND | MUSB_INTR_RESUME |
+	    MUSB_INTR_RESET | MUSB_INTR_SOF;
+
+	if (musb->int_usb || musb->int_tx || musb->int_rx)
+	    retval = musb_interrupt(musb);
+
+	spin_unlock_irqrestore(&musb->lock, flags);
+
+	return retval;
+    }
+
+Here the glue layer mostly has to read the relevant hardware registers
+and pass their values on to the controller driver which will handle the
+actual event that triggered the IRQ.
+
+The interrupt handler critical section is protected by the
+:c:func:`spin_lock_irqsave` and counterpart :c:func:`spin_unlock_irqrestore`
+functions (line 7 and 24 respectively), which prevent the interrupt
+handler code to be run by two different threads at the same time.
+
+Then the relevant interrupt registers are read (line 9 to 11):
+
+-  ``MUSB_INTRUSB``: indicates which USB interrupts are currently active,
+
+-  ``MUSB_INTRTX``: indicates which of the interrupts for TX endpoints are
+   currently active,
+
+-  ``MUSB_INTRRX``: indicates which of the interrupts for TX endpoints are
+   currently active.
+
+Note that :c:func:`musb_readb` is used to read 8-bit registers at most, while
+:c:func:`musb_readw` allows us to read at most 16-bit registers. There are
+other functions that can be used depending on the size of your device
+registers. See ``musb_io.h`` for more information.
+
+Instruction on line 18 is another quirk specific to the JZ4740 USB
+device controller, which will be discussed later in :ref:`musb-dev-quirks`.
+
+The glue layer still needs to register the IRQ handler though. Remember
+the instruction on line 14 of the init function::
+
+    static int jz4740_musb_init(struct musb *musb)
+    {
+	musb->isr = jz4740_musb_interrupt;
+
+	return 0;
+    }
+
+This instruction sets a pointer to the glue layer IRQ handler function,
+in order for the controller hardware to call the handler back when an
+IRQ comes from the controller hardware. The interrupt handler is now
+implemented and registered.
+
+.. _musb-dev-platform-data:
+
+Device Platform Data
+====================
+
+In order to write an MUSB glue layer, you need to have some data
+describing the hardware capabilities of your controller hardware, which
+is called the platform data.
+
+Platform data is specific to your hardware, though it may cover a broad
+range of devices, and is generally found somewhere in the ``arch/``
+directory, depending on your device architecture.
+
+For instance, platform data for the JZ4740 SoC is found in
+``arch/mips/jz4740/platform.c``. In the ``platform.c`` file each device of the
+JZ4740 SoC is described through a set of structures.
+
+Here is the part of ``arch/mips/jz4740/platform.c`` that covers the USB
+Device Controller (UDC):
+
+   .. code-block:: c
+    :emphasize-lines: 2,7,14-17,21,22,25,26,28,29
+
+    /* USB Device Controller */
+    struct platform_device jz4740_udc_xceiv_device = {
+	.name = "usb_phy_gen_xceiv",
+	.id   = 0,
+    };
+
+    static struct resource jz4740_udc_resources[] = {
+	[0] = {
+	    .start = JZ4740_UDC_BASE_ADDR,
+	    .end   = JZ4740_UDC_BASE_ADDR + 0x10000 - 1,
+	    .flags = IORESOURCE_MEM,
+	},
+	[1] = {
+	    .start = JZ4740_IRQ_UDC,
+	    .end   = JZ4740_IRQ_UDC,
+	    .flags = IORESOURCE_IRQ,
+	    .name  = "mc",
+	},
+    };
+
+    struct platform_device jz4740_udc_device = {
+	.name = "musb-jz4740",
+	.id   = -1,
+	.dev  = {
+	    .dma_mask          = &jz4740_udc_device.dev.coherent_dma_mask,
+	    .coherent_dma_mask = DMA_BIT_MASK(32),
+	},
+	.num_resources = ARRAY_SIZE(jz4740_udc_resources),
+	.resource      = jz4740_udc_resources,
+    };
+
+The ``jz4740_udc_xceiv_device`` platform device structure (line 2)
+describes the UDC transceiver with a name and id number.
+
+At the time of this writing, note that ``usb_phy_gen_xceiv`` is the
+specific name to be used for all transceivers that are either built-in
+with reference USB IP or autonomous and doesn't require any PHY
+programming. You will need to set ``CONFIG_NOP_USB_XCEIV=y`` in the
+kernel configuration to make use of the corresponding transceiver
+driver. The id field could be set to -1 (equivalent to
+``PLATFORM_DEVID_NONE``), -2 (equivalent to ``PLATFORM_DEVID_AUTO``) or
+start with 0 for the first device of this kind if we want a specific id
+number.
+
+The ``jz4740_udc_resources`` resource structure (line 7) defines the UDC
+registers base addresses.
+
+The first array (line 9 to 11) defines the UDC registers base memory
+addresses: start points to the first register memory address, end points
+to the last register memory address and the flags member defines the
+type of resource we are dealing with. So ``IORESOURCE_MEM`` is used to
+define the registers memory addresses. The second array (line 14 to 17)
+defines the UDC IRQ registers addresses. Since there is only one IRQ
+register available for the JZ4740 UDC, start and end point at the same
+address. The ``IORESOURCE_IRQ`` flag tells that we are dealing with IRQ
+resources, and the name ``mc`` is in fact hard-coded in the MUSB core in
+order for the controller driver to retrieve this IRQ resource by
+querying it by its name.
+
+Finally, the ``jz4740_udc_device`` platform device structure (line 21)
+describes the UDC itself.
+
+The ``musb-jz4740`` name (line 22) defines the MUSB driver that is used
+for this device; remember this is in fact the name that we used in the
+``jz4740_driver`` platform driver structure in :ref:`musb-basics`.
+The id field (line 23) is set to -1 (equivalent to ``PLATFORM_DEVID_NONE``)
+since we do not need an id for the device: the MUSB controller driver was
+already set to allocate an automatic id in :ref:`musb-basics`. In the dev field
+we care for DMA related information here. The ``dma_mask`` field (line 25)
+defines the width of the DMA mask that is going to be used, and
+``coherent_dma_mask`` (line 26) has the same purpose but for the
+``alloc_coherent`` DMA mappings: in both cases we are using a 32 bits mask.
+Then the resource field (line 29) is simply a pointer to the resource
+structure defined before, while the ``num_resources`` field (line 28) keeps
+track of the number of arrays defined in the resource structure (in this
+case there were two resource arrays defined before).
+
+With this quick overview of the UDC platform data at the ``arch/`` level now
+done, let's get back to the MUSB glue layer specific platform data in
+``drivers/usb/musb/jz4740.c``:
+
+   .. code-block:: c
+    :emphasize-lines: 3,5,7-9,11
+
+    static struct musb_hdrc_config jz4740_musb_config = {
+	/* Silicon does not implement USB OTG. */
+	.multipoint = 0,
+	/* Max EPs scanned, driver will decide which EP can be used. */
+	.num_eps    = 4,
+	/* RAMbits needed to configure EPs from table */
+	.ram_bits   = 9,
+	.fifo_cfg = jz4740_musb_fifo_cfg,
+	.fifo_cfg_size = ARRAY_SIZE(jz4740_musb_fifo_cfg),
+    };
+
+    static struct musb_hdrc_platform_data jz4740_musb_platform_data = {
+	.mode   = MUSB_PERIPHERAL,
+	.config = &jz4740_musb_config,
+    };
+
+First the glue layer configures some aspects of the controller driver
+operation related to the controller hardware specifics. This is done
+through the ``jz4740_musb_config`` :c:type:`musb_hdrc_config` structure.
+
+Defining the OTG capability of the controller hardware, the multipoint
+member (line 3) is set to 0 (equivalent to false) since the JZ4740 UDC
+is not OTG compatible. Then ``num_eps`` (line 5) defines the number of USB
+endpoints of the controller hardware, including endpoint 0: here we have
+3 endpoints + endpoint 0. Next is ``ram_bits`` (line 7) which is the width
+of the RAM address bus for the MUSB controller hardware. This
+information is needed when the controller driver cannot automatically
+configure endpoints by reading the relevant controller hardware
+registers. This issue will be discussed when we get to device quirks in
+:ref:`musb-dev-quirks`. Last two fields (line 8 and 9) are also
+about device quirks: ``fifo_cfg`` points to the USB endpoints configuration
+table and ``fifo_cfg_size`` keeps track of the size of the number of
+entries in that configuration table. More on that later in
+:ref:`musb-dev-quirks`.
+
+Then this configuration is embedded inside ``jz4740_musb_platform_data``
+:c:type:`musb_hdrc_platform_data` structure (line 11): config is a pointer to
+the configuration structure itself, and mode tells the controller driver
+if the controller hardware may be used as ``MUSB_HOST`` only,
+``MUSB_PERIPHERAL`` only or ``MUSB_OTG`` which is a dual mode.
+
+Remember that ``jz4740_musb_platform_data`` is then used to convey
+platform data information as we have seen in the probe function in
+:ref:`musb-basics`.
+
+.. _musb-dev-quirks:
+
+Device Quirks
+=============
+
+Completing the platform data specific to your device, you may also need
+to write some code in the glue layer to work around some device specific
+limitations. These quirks may be due to some hardware bugs, or simply be
+the result of an incomplete implementation of the USB On-the-Go
+specification.
+
+The JZ4740 UDC exhibits such quirks, some of which we will discuss here
+for the sake of insight even though these might not be found in the
+controller hardware you are working on.
+
+Let's get back to the init function first:
+
+   .. code-block:: c
+    :emphasize-lines: 12
+
+    static int jz4740_musb_init(struct musb *musb)
+    {
+	musb->xceiv = usb_get_phy(USB_PHY_TYPE_USB2);
+	if (!musb->xceiv) {
+	    pr_err("HS UDC: no transceiver configured\n");
+	    return -ENODEV;
+	}
+
+	/* Silicon does not implement ConfigData register.
+	 * Set dyn_fifo to avoid reading EP config from hardware.
+	 */
+	musb->dyn_fifo = true;
+
+	musb->isr = jz4740_musb_interrupt;
+
+	return 0;
+    }
+
+Instruction on line 12 helps the MUSB controller driver to work around
+the fact that the controller hardware is missing registers that are used
+for USB endpoints configuration.
+
+Without these registers, the controller driver is unable to read the
+endpoints configuration from the hardware, so we use line 12 instruction
+to bypass reading the configuration from silicon, and rely on a
+hard-coded table that describes the endpoints configuration instead::
+
+    static struct musb_fifo_cfg jz4740_musb_fifo_cfg[] = {
+	{ .hw_ep_num = 1, .style = FIFO_TX, .maxpacket = 512, },
+	{ .hw_ep_num = 1, .style = FIFO_RX, .maxpacket = 512, },
+	{ .hw_ep_num = 2, .style = FIFO_TX, .maxpacket = 64, },
+    };
+
+Looking at the configuration table above, we see that each endpoints is
+described by three fields: ``hw_ep_num`` is the endpoint number, style is
+its direction (either ``FIFO_TX`` for the controller driver to send packets
+in the controller hardware, or ``FIFO_RX`` to receive packets from
+hardware), and maxpacket defines the maximum size of each data packet
+that can be transmitted over that endpoint. Reading from the table, the
+controller driver knows that endpoint 1 can be used to send and receive
+USB data packets of 512 bytes at once (this is in fact a bulk in/out
+endpoint), and endpoint 2 can be used to send data packets of 64 bytes
+at once (this is in fact an interrupt endpoint).
+
+Note that there is no information about endpoint 0 here: that one is
+implemented by default in every silicon design, with a predefined
+configuration according to the USB specification. For more examples of
+endpoint configuration tables, see ``musb_core.c``.
+
+Let's now get back to the interrupt handler function:
+
+   .. code-block:: c
+    :emphasize-lines: 18-19
+
+    static irqreturn_t jz4740_musb_interrupt(int irq, void *__hci)
+    {
+	unsigned long   flags;
+	irqreturn_t     retval = IRQ_NONE;
+	struct musb     *musb = __hci;
+
+	spin_lock_irqsave(&musb->lock, flags);
+
+	musb->int_usb = musb_readb(musb->mregs, MUSB_INTRUSB);
+	musb->int_tx = musb_readw(musb->mregs, MUSB_INTRTX);
+	musb->int_rx = musb_readw(musb->mregs, MUSB_INTRRX);
+
+	/*
+	 * The controller is gadget only, the state of the host mode IRQ bits is
+	 * undefined. Mask them to make sure that the musb driver core will
+	 * never see them set
+	 */
+	musb->int_usb &= MUSB_INTR_SUSPEND | MUSB_INTR_RESUME |
+	    MUSB_INTR_RESET | MUSB_INTR_SOF;
+
+	if (musb->int_usb || musb->int_tx || musb->int_rx)
+	    retval = musb_interrupt(musb);
+
+	spin_unlock_irqrestore(&musb->lock, flags);
+
+	return retval;
+    }
+
+Instruction on line 18 above is a way for the controller driver to work
+around the fact that some interrupt bits used for USB host mode
+operation are missing in the ``MUSB_INTRUSB`` register, thus left in an
+undefined hardware state, since this MUSB controller hardware is used in
+peripheral mode only. As a consequence, the glue layer masks these
+missing bits out to avoid parasite interrupts by doing a logical AND
+operation between the value read from ``MUSB_INTRUSB`` and the bits that
+are actually implemented in the register.
+
+These are only a couple of the quirks found in the JZ4740 USB device
+controller. Some others were directly addressed in the MUSB core since
+the fixes were generic enough to provide a better handling of the issues
+for others controller hardware eventually.
+
+Conclusion
+==========
+
+Writing a Linux MUSB glue layer should be a more accessible task, as
+this documentation tries to show the ins and outs of this exercise.
+
+The JZ4740 USB device controller being fairly simple, I hope its glue
+layer serves as a good example for the curious mind. Used with the
+current MUSB glue layers, this documentation should provide enough
+guidance to get started; should anything gets out of hand, the linux-usb
+mailing list archive is another helpful resource to browse through.
+
+Acknowledgements
+================
+
+Many thanks to Lars-Peter Clausen and Maarten ter Huurne for answering
+my questions while I was writing the JZ4740 glue layer and for helping
+me out getting the code in good shape.
+
+I would also like to thank the Qi-Hardware community at large for its
+cheerful guidance and support.
+
+Resources
+=========
+
+USB Home Page: http://www.usb.org
+
+linux-usb Mailing List Archives: http://marc.info/?l=linux-usb
+
+USB On-the-Go Basics:
+http://www.maximintegrated.com/app-notes/index.mvp/id/1822
+
+:ref:`Writing USB Device Drivers <writing-usb-driver>`
+
+Texas Instruments USB Configuration Wiki Page:
+http://processors.wiki.ti.com/index.php/Usbgeneralpage
+
+Analog Devices Blackfin MUSB Configuration:
+http://docs.blackfin.uclinux.org/doku.php?id=linux-kernel:drivers:musb
diff --git a/Documentation/driver-api/usb/writing_usb_driver.rst b/Documentation/driver-api/usb/writing_usb_driver.rst
new file mode 100644
index 000000000000..69f077dcdb78
--- /dev/null
+++ b/Documentation/driver-api/usb/writing_usb_driver.rst
@@ -0,0 +1,326 @@
+.. _writing-usb-driver:
+
+==========================
+Writing USB Device Drivers
+==========================
+
+:Author: Greg Kroah-Hartman
+
+Introduction
+============
+
+The Linux USB subsystem has grown from supporting only two different
+types of devices in the 2.2.7 kernel (mice and keyboards), to over 20
+different types of devices in the 2.4 kernel. Linux currently supports
+almost all USB class devices (standard types of devices like keyboards,
+mice, modems, printers and speakers) and an ever-growing number of
+vendor-specific devices (such as USB to serial converters, digital
+cameras, Ethernet devices and MP3 players). For a full list of the
+different USB devices currently supported, see Resources.
+
+The remaining kinds of USB devices that do not have support on Linux are
+almost all vendor-specific devices. Each vendor decides to implement a
+custom protocol to talk to their device, so a custom driver usually
+needs to be created. Some vendors are open with their USB protocols and
+help with the creation of Linux drivers, while others do not publish
+them, and developers are forced to reverse-engineer. See Resources for
+some links to handy reverse-engineering tools.
+
+Because each different protocol causes a new driver to be created, I
+have written a generic USB driver skeleton, modelled after the
+pci-skeleton.c file in the kernel source tree upon which many PCI
+network drivers have been based. This USB skeleton can be found at
+drivers/usb/usb-skeleton.c in the kernel source tree. In this article I
+will walk through the basics of the skeleton driver, explaining the
+different pieces and what needs to be done to customize it to your
+specific device.
+
+Linux USB Basics
+================
+
+If you are going to write a Linux USB driver, please become familiar
+with the USB protocol specification. It can be found, along with many
+other useful documents, at the USB home page (see Resources). An
+excellent introduction to the Linux USB subsystem can be found at the
+USB Working Devices List (see Resources). It explains how the Linux USB
+subsystem is structured and introduces the reader to the concept of USB
+urbs (USB Request Blocks), which are essential to USB drivers.
+
+The first thing a Linux USB driver needs to do is register itself with
+the Linux USB subsystem, giving it some information about which devices
+the driver supports and which functions to call when a device supported
+by the driver is inserted or removed from the system. All of this
+information is passed to the USB subsystem in the :c:type:`usb_driver`
+structure. The skeleton driver declares a :c:type:`usb_driver` as::
+
+    static struct usb_driver skel_driver = {
+	    .name        = "skeleton",
+	    .probe       = skel_probe,
+	    .disconnect  = skel_disconnect,
+	    .fops        = &skel_fops,
+	    .minor       = USB_SKEL_MINOR_BASE,
+	    .id_table    = skel_table,
+    };
+
+
+The variable name is a string that describes the driver. It is used in
+informational messages printed to the system log. The probe and
+disconnect function pointers are called when a device that matches the
+information provided in the ``id_table`` variable is either seen or
+removed.
+
+The fops and minor variables are optional. Most USB drivers hook into
+another kernel subsystem, such as the SCSI, network or TTY subsystem.
+These types of drivers register themselves with the other kernel
+subsystem, and any user-space interactions are provided through that
+interface. But for drivers that do not have a matching kernel subsystem,
+such as MP3 players or scanners, a method of interacting with user space
+is needed. The USB subsystem provides a way to register a minor device
+number and a set of :c:type:`file_operations` function pointers that enable
+this user-space interaction. The skeleton driver needs this kind of
+interface, so it provides a minor starting number and a pointer to its
+:c:type:`file_operations` functions.
+
+The USB driver is then registered with a call to :c:func:`usb_register`,
+usually in the driver's init function, as shown here::
+
+    static int __init usb_skel_init(void)
+    {
+	    int result;
+
+	    /* register this driver with the USB subsystem */
+	    result = usb_register(&skel_driver);
+	    if (result < 0) {
+		    err("usb_register failed for the "__FILE__ "driver."
+			"Error number %d", result);
+		    return -1;
+	    }
+
+	    return 0;
+    }
+    module_init(usb_skel_init);
+
+
+When the driver is unloaded from the system, it needs to deregister
+itself with the USB subsystem. This is done with the :c:func:`usb_deregister`
+function::
+
+    static void __exit usb_skel_exit(void)
+    {
+	    /* deregister this driver with the USB subsystem */
+	    usb_deregister(&skel_driver);
+    }
+    module_exit(usb_skel_exit);
+
+
+To enable the linux-hotplug system to load the driver automatically when
+the device is plugged in, you need to create a ``MODULE_DEVICE_TABLE``.
+The following code tells the hotplug scripts that this module supports a
+single device with a specific vendor and product ID::
+
+    /* table of devices that work with this driver */
+    static struct usb_device_id skel_table [] = {
+	    { USB_DEVICE(USB_SKEL_VENDOR_ID, USB_SKEL_PRODUCT_ID) },
+	    { }                      /* Terminating entry */
+    };
+    MODULE_DEVICE_TABLE (usb, skel_table);
+
+
+There are other macros that can be used in describing a struct
+:c:type:`usb_device_id` for drivers that support a whole class of USB
+drivers. See :ref:`usb.h <usb_header>` for more information on this.
+
+Device operation
+================
+
+When a device is plugged into the USB bus that matches the device ID
+pattern that your driver registered with the USB core, the probe
+function is called. The :c:type:`usb_device` structure, interface number and
+the interface ID are passed to the function::
+
+    static int skel_probe(struct usb_interface *interface,
+	const struct usb_device_id *id)
+
+
+The driver now needs to verify that this device is actually one that it
+can accept. If so, it returns 0. If not, or if any error occurs during
+initialization, an errorcode (such as ``-ENOMEM`` or ``-ENODEV``) is
+returned from the probe function.
+
+In the skeleton driver, we determine what end points are marked as
+bulk-in and bulk-out. We create buffers to hold the data that will be
+sent and received from the device, and a USB urb to write data to the
+device is initialized.
+
+Conversely, when the device is removed from the USB bus, the disconnect
+function is called with the device pointer. The driver needs to clean
+any private data that has been allocated at this time and to shut down
+any pending urbs that are in the USB system.
+
+Now that the device is plugged into the system and the driver is bound
+to the device, any of the functions in the :c:type:`file_operations` structure
+that were passed to the USB subsystem will be called from a user program
+trying to talk to the device. The first function called will be open, as
+the program tries to open the device for I/O. We increment our private
+usage count and save a pointer to our internal structure in the file
+structure. This is done so that future calls to file operations will
+enable the driver to determine which device the user is addressing. All
+of this is done with the following code::
+
+    /* increment our usage count for the module */
+    ++skel->open_count;
+
+    /* save our object in the file's private structure */
+    file->private_data = dev;
+
+
+After the open function is called, the read and write functions are
+called to receive and send data to the device. In the ``skel_write``
+function, we receive a pointer to some data that the user wants to send
+to the device and the size of the data. The function determines how much
+data it can send to the device based on the size of the write urb it has
+created (this size depends on the size of the bulk out end point that
+the device has). Then it copies the data from user space to kernel
+space, points the urb to the data and submits the urb to the USB
+subsystem. This can be seen in the following code::
+
+    /* we can only write as much as 1 urb will hold */
+    bytes_written = (count > skel->bulk_out_size) ? skel->bulk_out_size : count;
+
+    /* copy the data from user space into our urb */
+    copy_from_user(skel->write_urb->transfer_buffer, buffer, bytes_written);
+
+    /* set up our urb */
+    usb_fill_bulk_urb(skel->write_urb,
+		      skel->dev,
+		      usb_sndbulkpipe(skel->dev, skel->bulk_out_endpointAddr),
+		      skel->write_urb->transfer_buffer,
+		      bytes_written,
+		      skel_write_bulk_callback,
+		      skel);
+
+    /* send the data out the bulk port */
+    result = usb_submit_urb(skel->write_urb);
+    if (result) {
+	    err("Failed submitting write urb, error %d", result);
+    }
+
+
+When the write urb is filled up with the proper information using the
+:c:func:`usb_fill_bulk_urb` function, we point the urb's completion callback
+to call our own ``skel_write_bulk_callback`` function. This function is
+called when the urb is finished by the USB subsystem. The callback
+function is called in interrupt context, so caution must be taken not to
+do very much processing at that time. Our implementation of
+``skel_write_bulk_callback`` merely reports if the urb was completed
+successfully or not and then returns.
+
+The read function works a bit differently from the write function in
+that we do not use an urb to transfer data from the device to the
+driver. Instead we call the :c:func:`usb_bulk_msg` function, which can be used
+to send or receive data from a device without having to create urbs and
+handle urb completion callback functions. We call the :c:func:`usb_bulk_msg`
+function, giving it a buffer into which to place any data received from
+the device and a timeout value. If the timeout period expires without
+receiving any data from the device, the function will fail and return an
+error message. This can be shown with the following code::
+
+    /* do an immediate bulk read to get data from the device */
+    retval = usb_bulk_msg (skel->dev,
+			   usb_rcvbulkpipe (skel->dev,
+			   skel->bulk_in_endpointAddr),
+			   skel->bulk_in_buffer,
+			   skel->bulk_in_size,
+			   &count, HZ*10);
+    /* if the read was successful, copy the data to user space */
+    if (!retval) {
+	    if (copy_to_user (buffer, skel->bulk_in_buffer, count))
+		    retval = -EFAULT;
+	    else
+		    retval = count;
+    }
+
+
+The :c:func:`usb_bulk_msg` function can be very useful for doing single reads
+or writes to a device; however, if you need to read or write constantly to
+a device, it is recommended to set up your own urbs and submit them to
+the USB subsystem.
+
+When the user program releases the file handle that it has been using to
+talk to the device, the release function in the driver is called. In
+this function we decrement our private usage count and wait for possible
+pending writes::
+
+    /* decrement our usage count for the device */
+    --skel->open_count;
+
+
+One of the more difficult problems that USB drivers must be able to
+handle smoothly is the fact that the USB device may be removed from the
+system at any point in time, even if a program is currently talking to
+it. It needs to be able to shut down any current reads and writes and
+notify the user-space programs that the device is no longer there. The
+following code (function ``skel_delete``) is an example of how to do
+this::
+
+    static inline void skel_delete (struct usb_skel *dev)
+    {
+	kfree (dev->bulk_in_buffer);
+	if (dev->bulk_out_buffer != NULL)
+	    usb_free_coherent (dev->udev, dev->bulk_out_size,
+		dev->bulk_out_buffer,
+		dev->write_urb->transfer_dma);
+	usb_free_urb (dev->write_urb);
+	kfree (dev);
+    }
+
+
+If a program currently has an open handle to the device, we reset the
+flag ``device_present``. For every read, write, release and other
+functions that expect a device to be present, the driver first checks
+this flag to see if the device is still present. If not, it releases
+that the device has disappeared, and a ``-ENODEV`` error is returned to the
+user-space program. When the release function is eventually called, it
+determines if there is no device and if not, it does the cleanup that
+the ``skel_disconnect`` function normally does if there are no open files
+on the device (see Listing 5).
+
+Isochronous Data
+================
+
+This usb-skeleton driver does not have any examples of interrupt or
+isochronous data being sent to or from the device. Interrupt data is
+sent almost exactly as bulk data is, with a few minor exceptions.
+Isochronous data works differently with continuous streams of data being
+sent to or from the device. The audio and video camera drivers are very
+good examples of drivers that handle isochronous data and will be useful
+if you also need to do this.
+
+Conclusion
+==========
+
+Writing Linux USB device drivers is not a difficult task as the
+usb-skeleton driver shows. This driver, combined with the other current
+USB drivers, should provide enough examples to help a beginning author
+create a working driver in a minimal amount of time. The linux-usb-devel
+mailing list archives also contain a lot of helpful information.
+
+Resources
+=========
+
+The Linux USB Project:
+http://www.linux-usb.org/
+
+Linux Hotplug Project:
+http://linux-hotplug.sourceforge.net/
+
+Linux USB Working Devices List:
+http://www.qbik.ch/usb/devices/
+
+linux-usb-devel Mailing List Archives:
+http://marc.theaimsgroup.com/?l=linux-usb-devel
+
+Programming Guide for Linux USB Device Drivers:
+http://usb.cs.tum.edu/usbdoc
+
+USB Home Page: http://www.usb.org
diff --git a/Documentation/early-userspace/README b/Documentation/early-userspace/README
index 93e63a9af30b..2c00b072a4c8 100644
--- a/Documentation/early-userspace/README
+++ b/Documentation/early-userspace/README
@@ -86,7 +86,7 @@ early userspace useful.  The klibc distribution is currently
 maintained separately from the kernel.
 
 You can obtain somewhat infrequent snapshots of klibc from
-ftp://ftp.kernel.org/pub/linux/libs/klibc/
+https://www.kernel.org/pub/linux/libs/klibc/
 
 For active users, you are better off using the klibc git
 repository, at http://git.kernel.org/?p=libs/klibc/klibc.git
diff --git a/Documentation/extcon/intel-int3496.txt b/Documentation/extcon/intel-int3496.txt
index af0b366c25b7..8155dbc7fad3 100644
--- a/Documentation/extcon/intel-int3496.txt
+++ b/Documentation/extcon/intel-int3496.txt
@@ -20,3 +20,8 @@ Index 1: The output gpio for enabling Vbus output from the device to the otg
 Index 2: The output gpio for muxing of the data pins between the USB host and
          the USB peripheral controller, write 1 to mux to the peripheral
          controller
+
+There is a mapping between indices and GPIO connection IDs as follows
+	id	index 0
+	vbus	index 1
+	mux	index 2
diff --git a/Documentation/features/core/BPF-JIT/arch-support.txt b/Documentation/features/core/BPF-JIT/arch-support.txt
index c1b4f917238f..5575d2d09625 100644
--- a/Documentation/features/core/BPF-JIT/arch-support.txt
+++ b/Documentation/features/core/BPF-JIT/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/core/generic-idle-thread/arch-support.txt b/Documentation/features/core/generic-idle-thread/arch-support.txt
index 6d930fcbe519..abb5f271a792 100644
--- a/Documentation/features/core/generic-idle-thread/arch-support.txt
+++ b/Documentation/features/core/generic-idle-thread/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: |  ok  |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/core/jump-labels/arch-support.txt b/Documentation/features/core/jump-labels/arch-support.txt
index 136868b636e6..dbdaffcc5110 100644
--- a/Documentation/features/core/jump-labels/arch-support.txt
+++ b/Documentation/features/core/jump-labels/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/core/tracehook/arch-support.txt b/Documentation/features/core/tracehook/arch-support.txt
index 728061d763b1..5e97a89420ef 100644
--- a/Documentation/features/core/tracehook/arch-support.txt
+++ b/Documentation/features/core/tracehook/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: |  ok  |
     |         c6x: |  ok  |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index 703f5784bc90..76bbd7fe27b3 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt
index 38dea8eeba0a..830dbe801aaf 100644
--- a/Documentation/features/debug/gcov-profile-all/arch-support.txt
+++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/kgdb/arch-support.txt b/Documentation/features/debug/kgdb/arch-support.txt
index 862e15d6f79e..0217bf6e942d 100644
--- a/Documentation/features/debug/kgdb/arch-support.txt
+++ b/Documentation/features/debug/kgdb/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: |  ok  |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
index 40f44d041fb4..f9133a921d5a 100644
--- a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
+++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/kprobes/arch-support.txt b/Documentation/features/debug/kprobes/arch-support.txt
index a44bfff6940b..529f66eda679 100644
--- a/Documentation/features/debug/kprobes/arch-support.txt
+++ b/Documentation/features/debug/kprobes/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: | TODO |
-    |       avr32: |  ok  |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/kretprobes/arch-support.txt b/Documentation/features/debug/kretprobes/arch-support.txt
index d87c1ce24204..43353242e439 100644
--- a/Documentation/features/debug/kretprobes/arch-support.txt
+++ b/Documentation/features/debug/kretprobes/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/optprobes/arch-support.txt b/Documentation/features/debug/optprobes/arch-support.txt
index b8999d8544ca..f559f1ba5416 100644
--- a/Documentation/features/debug/optprobes/arch-support.txt
+++ b/Documentation/features/debug/optprobes/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/stackprotector/arch-support.txt b/Documentation/features/debug/stackprotector/arch-support.txt
index 0fa423313409..d7acd7bd3619 100644
--- a/Documentation/features/debug/stackprotector/arch-support.txt
+++ b/Documentation/features/debug/stackprotector/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/uprobes/arch-support.txt b/Documentation/features/debug/uprobes/arch-support.txt
index d605c3fc38fd..53ed42b0e7e5 100644
--- a/Documentation/features/debug/uprobes/arch-support.txt
+++ b/Documentation/features/debug/uprobes/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/debug/user-ret-profiler/arch-support.txt b/Documentation/features/debug/user-ret-profiler/arch-support.txt
index 44cc1ff3f603..149443936de9 100644
--- a/Documentation/features/debug/user-ret-profiler/arch-support.txt
+++ b/Documentation/features/debug/user-ret-profiler/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/io/dma-api-debug/arch-support.txt b/Documentation/features/io/dma-api-debug/arch-support.txt
index ffa522a9bdfd..6be920643be6 100644
--- a/Documentation/features/io/dma-api-debug/arch-support.txt
+++ b/Documentation/features/io/dma-api-debug/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: |  ok  |
     |        cris: | TODO |
diff --git a/Documentation/features/io/dma-contiguous/arch-support.txt b/Documentation/features/io/dma-contiguous/arch-support.txt
index 83d2cf989ea3..0eb08e1e32b8 100644
--- a/Documentation/features/io/dma-contiguous/arch-support.txt
+++ b/Documentation/features/io/dma-contiguous/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/io/sg-chain/arch-support.txt b/Documentation/features/io/sg-chain/arch-support.txt
index 6ca98f9911bb..514ad3468aa5 100644
--- a/Documentation/features/io/sg-chain/arch-support.txt
+++ b/Documentation/features/io/sg-chain/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/lib/strncasecmp/arch-support.txt b/Documentation/features/lib/strncasecmp/arch-support.txt
index 12b1c9358e57..532c6f0fc15c 100644
--- a/Documentation/features/lib/strncasecmp/arch-support.txt
+++ b/Documentation/features/lib/strncasecmp/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/locking/cmpxchg-local/arch-support.txt b/Documentation/features/locking/cmpxchg-local/arch-support.txt
index d9c310889bc1..f3eec26c8cf8 100644
--- a/Documentation/features/locking/cmpxchg-local/arch-support.txt
+++ b/Documentation/features/locking/cmpxchg-local/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/locking/lockdep/arch-support.txt b/Documentation/features/locking/lockdep/arch-support.txt
index cf90635bdcbb..9756abc680a7 100644
--- a/Documentation/features/locking/lockdep/arch-support.txt
+++ b/Documentation/features/locking/lockdep/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: |  ok  |
     |    blackfin: |  ok  |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/locking/queued-rwlocks/arch-support.txt b/Documentation/features/locking/queued-rwlocks/arch-support.txt
index 68c3a5ddd9b9..62f4ee5c156c 100644
--- a/Documentation/features/locking/queued-rwlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-rwlocks/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt
index e973b1a9572f..321b32f6e63c 100644
--- a/Documentation/features/locking/queued-spinlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/locking/rwsem-optimized/arch-support.txt b/Documentation/features/locking/rwsem-optimized/arch-support.txt
index ac93d7ab66c4..79bfa4d6e41f 100644
--- a/Documentation/features/locking/rwsem-optimized/arch-support.txt
+++ b/Documentation/features/locking/rwsem-optimized/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/perf/kprobes-event/arch-support.txt b/Documentation/features/perf/kprobes-event/arch-support.txt
index 4660bf222db1..00f1606bbf45 100644
--- a/Documentation/features/perf/kprobes-event/arch-support.txt
+++ b/Documentation/features/perf/kprobes-event/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/perf/perf-regs/arch-support.txt b/Documentation/features/perf/perf-regs/arch-support.txt
index f179b1fb26ef..7d516eacf7b9 100644
--- a/Documentation/features/perf/perf-regs/arch-support.txt
+++ b/Documentation/features/perf/perf-regs/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/perf/perf-stackdump/arch-support.txt b/Documentation/features/perf/perf-stackdump/arch-support.txt
index 85777c5c6353..f974b8df5d82 100644
--- a/Documentation/features/perf/perf-stackdump/arch-support.txt
+++ b/Documentation/features/perf/perf-stackdump/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/sched/numa-balancing/arch-support.txt b/Documentation/features/sched/numa-balancing/arch-support.txt
index ac7cd6b1502b..1d3c0f669152 100644
--- a/Documentation/features/sched/numa-balancing/arch-support.txt
+++ b/Documentation/features/sched/numa-balancing/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ..  |
     |         arm: |  ..  |
     |       arm64: |  ..  |
-    |       avr32: |  ..  |
     |    blackfin: |  ..  |
     |         c6x: |  ..  |
     |        cris: |  ..  |
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
index 4f66ec133951..a32d5b207679 100644
--- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
index 8acb439a4a17..caee8f64d1bc 100644
--- a/Documentation/features/time/arch-tick-broadcast/arch-support.txt
+++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/time/clockevents/arch-support.txt b/Documentation/features/time/clockevents/arch-support.txt
index ff670b2207f1..1cd87f6cd07d 100644
--- a/Documentation/features/time/clockevents/arch-support.txt
+++ b/Documentation/features/time/clockevents/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: |  ok  |
     |    blackfin: |  ok  |
     |         c6x: |  ok  |
     |        cris: |  ok  |
diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt
index a1e3eea7003f..e6d7c7b2253c 100644
--- a/Documentation/features/time/context-tracking/arch-support.txt
+++ b/Documentation/features/time/context-tracking/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt
index 4199ffecc0ff..15c6071788ae 100644
--- a/Documentation/features/time/irq-time-acct/arch-support.txt
+++ b/Documentation/features/time/irq-time-acct/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
index 17f68a02e84d..baee7611ba3d 100644
--- a/Documentation/features/time/modern-timekeeping/arch-support.txt
+++ b/Documentation/features/time/modern-timekeeping/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: | TODO |
     |       arm64: |  ok  |
-    |       avr32: |  ok  |
     |    blackfin: | TODO |
     |         c6x: |  ok  |
     |        cris: | TODO |
diff --git a/Documentation/features/time/virt-cpuacct/arch-support.txt b/Documentation/features/time/virt-cpuacct/arch-support.txt
index cf3c3e383d15..9129530cb73c 100644
--- a/Documentation/features/time/virt-cpuacct/arch-support.txt
+++ b/Documentation/features/time/virt-cpuacct/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/vm/ELF-ASLR/arch-support.txt b/Documentation/features/vm/ELF-ASLR/arch-support.txt
index ec4dd28e1297..f6829af3255f 100644
--- a/Documentation/features/vm/ELF-ASLR/arch-support.txt
+++ b/Documentation/features/vm/ELF-ASLR/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/vm/PG_uncached/arch-support.txt b/Documentation/features/vm/PG_uncached/arch-support.txt
index 991974275a3e..1a09ea99d486 100644
--- a/Documentation/features/vm/PG_uncached/arch-support.txt
+++ b/Documentation/features/vm/PG_uncached/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/vm/THP/arch-support.txt b/Documentation/features/vm/THP/arch-support.txt
index 523f8307b9cd..d170e6236503 100644
--- a/Documentation/features/vm/THP/arch-support.txt
+++ b/Documentation/features/vm/THP/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: |  ..  |
     |    blackfin: |  ..  |
     |         c6x: |  ..  |
     |        cris: |  ..  |
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 261b92e2fb1a..abfab4080a91 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: |  ..  |
     |    blackfin: | TODO |
     |         c6x: |  ..  |
     |        cris: |  ..  |
diff --git a/Documentation/features/vm/huge-vmap/arch-support.txt b/Documentation/features/vm/huge-vmap/arch-support.txt
index df1d1f3c9af2..f81f09b22b08 100644
--- a/Documentation/features/vm/huge-vmap/arch-support.txt
+++ b/Documentation/features/vm/huge-vmap/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: | TODO |
     |         arm: | TODO |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt
index 90c53749fde7..0cc3e11c42e2 100644
--- a/Documentation/features/vm/ioremap_prot/arch-support.txt
+++ b/Documentation/features/vm/ioremap_prot/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: | TODO |
     |       arm64: | TODO |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/features/vm/numa-memblock/arch-support.txt b/Documentation/features/vm/numa-memblock/arch-support.txt
index e7c252a0c531..9a3fdac42ce1 100644
--- a/Documentation/features/vm/numa-memblock/arch-support.txt
+++ b/Documentation/features/vm/numa-memblock/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ..  |
     |         arm: |  ..  |
     |       arm64: |  ..  |
-    |       avr32: |  ..  |
     |    blackfin: |  ..  |
     |         c6x: |  ..  |
     |        cris: |  ..  |
diff --git a/Documentation/features/vm/pte_special/arch-support.txt b/Documentation/features/vm/pte_special/arch-support.txt
index 3de5434c857c..dfaa39e664ff 100644
--- a/Documentation/features/vm/pte_special/arch-support.txt
+++ b/Documentation/features/vm/pte_special/arch-support.txt
@@ -10,7 +10,6 @@
     |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
-    |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
     |        cris: | TODO |
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index fdcfdd79682a..fe25787ff6d4 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -58,8 +58,7 @@ prototypes:
 	int (*permission) (struct inode *, int, unsigned int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
-	int (*getattr) (const struct path *, struct dentry *, struct kstat *,
-			u32, unsigned int);
+	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 	void (*update_time)(struct inode *, struct timespec *, int);
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 3698ed3146e3..5a8f7f4d2bca 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -25,7 +25,7 @@ Note: More extensive information for getting started with ext4 can be
 	
 	or
 
-    ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
+    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
 
 	or grab the latest git repository from:
 
diff --git a/Documentation/filesystems/nfs/nfs-rdma.txt b/Documentation/filesystems/nfs/nfs-rdma.txt
index 1e6564545edf..22dc0dd6889c 100644
--- a/Documentation/filesystems/nfs/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs/nfs-rdma.txt
@@ -110,10 +110,10 @@ Installation
   - Install a Linux kernel with NFS/RDMA
 
     The NFS/RDMA client and server are both included in the mainline Linux
-    kernel version 2.6.25 and later. This and other versions of the 2.6 Linux
+    kernel version 2.6.25 and later. This and other versions of the Linux
     kernel can be found at:
 
-    ftp://ftp.kernel.org/pub/linux/kernel/v2.6/
+    https://www.kernel.org/pub/linux/kernel/
 
     Download the sources and place them in an appropriate location.
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 95280079c0b3..5fb17f49f7a2 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -600,3 +600,9 @@ in your dentry operations instead.
 [recommended]
 	->readlink is optional for symlinks.  Don't set, unless filesystem needs
 	to fake something for readlink(2).
+--
+[mandatory]
+	->getattr() is now passed a struct path rather than a vfsmount and
+	dentry separately, and it now has request_mask and query_flags arguments
+	to specify the fields and sync type requested by statx.  Filesystems not
+	supporting any statx-specific features may ignore the new arguments.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 569211703721..94dd27ef4a76 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -382,8 +382,7 @@ struct inode_operations {
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
-	int (*getattr) (const struct path *, struct dentry *, struct kstat *,
-			u32, unsigned int);
+	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
diff --git a/Documentation/gcc-plugins.txt b/Documentation/gcc-plugins.txt
index 891c69464434..433eaefb4aa1 100644
--- a/Documentation/gcc-plugins.txt
+++ b/Documentation/gcc-plugins.txt
@@ -18,8 +18,8 @@ because gcc versions 4.5 and 4.6 are compiled by a C compiler,
 gcc-4.7 can be compiled by a C or a C++ compiler,
 and versions 4.8+ can only be compiled by a C++ compiler.
 
-Currently the GCC plugin infrastructure supports only the x86, arm and arm64
-architectures.
+Currently the GCC plugin infrastructure supports only the x86, arm, arm64 and
+powerpc architectures.
 
 This infrastructure was ported from grsecurity [6] and PaX [7].
 
diff --git a/Documentation/hid/hidraw.txt b/Documentation/hid/hidraw.txt
index 029e6cb9a7e8..c8436e354f44 100644
--- a/Documentation/hid/hidraw.txt
+++ b/Documentation/hid/hidraw.txt
@@ -81,7 +81,7 @@ of:
 	BUS_HIL
 	BUS_BLUETOOTH
 	BUS_VIRTUAL
-which are defined in linux/input.h.
+which are defined in uapi/linux/input.h.
 
 HIDIOCGRAWNAME(len): Get Raw Name
 This ioctl returns a string containing the vendor and product strings of
diff --git a/Documentation/hwmon/aspeed-pwm-tacho b/Documentation/hwmon/aspeed-pwm-tacho
new file mode 100644
index 000000000000..7cfb34977460
--- /dev/null
+++ b/Documentation/hwmon/aspeed-pwm-tacho
@@ -0,0 +1,22 @@
+Kernel driver aspeed-pwm-tacho
+==============================
+
+Supported chips:
+	ASPEED AST2400/2500
+
+Authors:
+	<jaghu@google.com>
+
+Description:
+------------
+This driver implements support for ASPEED AST2400/2500 PWM and Fan Tacho
+controller. The PWM controller supports upto 8 PWM outputs. The Fan tacho
+controller supports up to 16 tachometer inputs.
+
+The driver provides the following sensor accesses in sysfs:
+
+fanX_input	ro	provide current fan rotation value in RPM as reported
+			by the fan to the device.
+
+pwmX		rw	get or set PWM fan control value. This is an integer
+			value between 0(off) and 255(full speed).
diff --git a/Documentation/hwmon/tc654 b/Documentation/hwmon/tc654
index 91a2843f5f98..47636a8077b4 100644
--- a/Documentation/hwmon/tc654
+++ b/Documentation/hwmon/tc654
@@ -2,7 +2,7 @@ Kernel driver tc654
 ===================
 
 Supported chips:
-  * Microship TC654 and TC655
+  * Microchip TC654 and TC655
     Prefix: 'tc654'
     Datasheet: http://ww1.microchip.com/downloads/en/DeviceDoc/20001734C.pdf
 
diff --git a/Documentation/index.rst b/Documentation/index.rst
index f6e641a54bbc..61306a22888d 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -24,6 +24,18 @@ trying to get it to work optimally on a given system.
 
    admin-guide/index
 
+Application-developer documentation
+-----------------------------------
+
+The user-space API manual gathers together documents describing aspects of
+the kernel interface as seen by application developers.
+
+.. toctree::
+   :maxdepth: 2
+
+   userspace-api/index	      
+
+
 Introduction to kernel development
 ----------------------------------
 
@@ -76,6 +88,14 @@ Chinese translations
 
    translations/zh_CN/index
 
+Japanese translations
+---------------------
+
+.. toctree::
+   :maxdepth: 1
+
+   translations/ja_JP/index
+
 Indices and tables
 ==================
 
diff --git a/Documentation/input/event-codes.txt b/Documentation/input/event-codes.txt
index 36ea940e5bb9..575415f4cef0 100644
--- a/Documentation/input/event-codes.txt
+++ b/Documentation/input/event-codes.txt
@@ -301,7 +301,10 @@ them as any other INPUT_PROP_BUTTONPAD device.
 INPUT_PROP_ACCELEROMETER
 -------------------------
 Directional axes on this device (absolute and/or relative x, y, z) represent
-accelerometer data. All other axes retain their meaning. A device must not mix
+accelerometer data. Some devices also report gyroscope data, which devices
+can report through the rotational axes (absolute and/or relative rx, ry, rz).
+
+All other axes retain their meaning. A device must not mix
 regular directional axes and accelerometer axes on the same event node.
 
 Guidelines:
diff --git a/Documentation/input/ff.txt b/Documentation/input/ff.txt
index b3867bf49f8f..be742eec7aab 100644
--- a/Documentation/input/ff.txt
+++ b/Documentation/input/ff.txt
@@ -106,9 +106,9 @@ allocate a new effect.
 
 Effects are file descriptor specific.
 
-See <linux/input.h> for a description of the ff_effect struct. You should also
-find help in a few sketches, contained in files shape.fig and interactive.fig.
-You need xfig to visualize these files.
+See <uapi/linux/input.h> for a description of the ff_effect struct. You should
+also find help in a few sketches, contained in files shape.fig and
+interactive.fig. You need xfig to visualize these files.
 
 3.3 Removing an effect from the device
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/input/input-programming.txt b/Documentation/input/input-programming.txt
index 7f8b9d97bc47..c3b940baba42 100644
--- a/Documentation/input/input-programming.txt
+++ b/Documentation/input/input-programming.txt
@@ -174,8 +174,8 @@ It's reported to the input system via:
 
 	input_report_key(struct input_dev *dev, int code, int value)
 
-See linux/input.h for the allowable values of code (from 0 to KEY_MAX).
-Value is interpreted as a truth value, ie any nonzero value means key
+See uapi/linux/input-event-codes.h for the allowable values of code (from 0 to
+KEY_MAX). Value is interpreted as a truth value, ie any nonzero value means key
 pressed, zero value means key released. The input code generates events only
 in case the value is different from before.
 
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 08244bea5048..a77ead911956 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -212,7 +212,7 @@ Code  Seq#(hex)	Include File		Comments
 'c'	00-1F	linux/chio.h		conflict!
 'c'	80-9F	arch/s390/include/asm/chsc.h	conflict!
 'c'	A0-AF   arch/x86/include/asm/msr.h	conflict!
-'d'	00-FF	linux/char/drm/drm/h	conflict!
+'d'	00-FF	linux/char/drm/drm.h	conflict!
 'd'	02-40	pcmcia/ds.h		conflict!
 'd'	F0-FF	linux/digi1.h
 'e'	all	linux/digi1.h		conflict!
diff --git a/Documentation/leds/leds-lp55xx.txt b/Documentation/leds/leds-lp55xx.txt
index bcea12a0c584..e23fa91ea722 100644
--- a/Documentation/leds/leds-lp55xx.txt
+++ b/Documentation/leds/leds-lp55xx.txt
@@ -117,7 +117,7 @@ As soon as 'loading' is set to 0, registered callback is called.
 Inside the callback, the selected engine is loaded and memory is updated.
 To run programmed pattern, 'run_engine' attribute should be enabled.
 
-The pattern sqeuence of LP8501 is similar to LP5523.
+The pattern sequence of LP8501 is similar to LP5523.
 However pattern data is specific.
 Ex 1) Engine 1 is used
 echo 1 > /sys/bus/i2c/devices/xxxx/select_engine
diff --git a/Documentation/lightnvm/pblk.txt b/Documentation/lightnvm/pblk.txt
new file mode 100644
index 000000000000..1040ed1cec81
--- /dev/null
+++ b/Documentation/lightnvm/pblk.txt
@@ -0,0 +1,21 @@
+pblk: Physical Block Device Target
+==================================
+
+pblk implements a fully associative, host-based FTL that exposes a traditional
+block I/O interface. Its primary responsibilities are:
+
+  - Map logical addresses onto physical addresses (4KB granularity) in a
+    logical-to-physical (L2P) table.
+  - Maintain the integrity and consistency of the L2P table as well as its
+    recovery from normal tear down and power outage.
+  - Deal with controller- and media-specific constrains.
+  - Handle I/O errors.
+  - Implement garbage collection.
+  - Maintain consistency across the I/O stack during synchronization points.
+
+For more information please refer to:
+
+  http://lightnvm.io
+
+which maintains updated FAQs, manual pages, technical documentation, tools,
+contacts, etc.
diff --git a/Documentation/md/md-cluster.txt b/Documentation/md/md-cluster.txt
index 38883276d31c..d22103994aef 100644
--- a/Documentation/md/md-cluster.txt
+++ b/Documentation/md/md-cluster.txt
@@ -77,7 +77,7 @@ There are three groups of locks for managing the device:
  3.1.2 RESYNCING: informs other nodes that a resync is initiated or
    ended so that each node may suspend or resume the region.  Each
    RESYNCING message identifies a range of the devices that the
-   sending node is about to resync. This over-rides any pervious
+   sending node is about to resync. This overrides any previous
    notification from that node: only one ranged can be resynced at a
    time per-node.
 
diff --git a/Documentation/media/Makefile b/Documentation/media/Makefile
index 9b3e70b2cab2..36166952d555 100644
--- a/Documentation/media/Makefile
+++ b/Documentation/media/Makefile
@@ -1,51 +1,6 @@
-# Rules to convert DOT and SVG to Sphinx images
-
-SRC_DIR=$(srctree)/Documentation/media
-
-DOTS = \
-	uapi/v4l/pipeline.dot \
-
-IMAGES = \
-	typical_media_device.svg \
-	uapi/dvb/dvbstb.svg \
-	uapi/v4l/bayer.svg \
-	uapi/v4l/constraints.svg \
-	uapi/v4l/crop.svg \
-	uapi/v4l/fieldseq_bt.svg \
-	uapi/v4l/fieldseq_tb.svg \
-	uapi/v4l/nv12mt.svg \
-	uapi/v4l/nv12mt_example.svg \
-	uapi/v4l/pipeline.svg \
-	uapi/v4l/selection.svg \
-	uapi/v4l/subdev-image-processing-full.svg \
-	uapi/v4l/subdev-image-processing-scaling-multi-source.svg \
-	uapi/v4l/subdev-image-processing-crop.svg \
-	uapi/v4l/vbi_525.svg \
-	uapi/v4l/vbi_625.svg \
-	uapi/v4l/vbi_hsync.svg \
-
-DOTTGT := $(patsubst %.dot,%.svg,$(DOTS))
-IMGDOT := $(patsubst %,$(SRC_DIR)/%,$(DOTTGT))
-
-IMGTGT := $(patsubst %.svg,%.pdf,$(IMAGES))
-IMGPDF := $(patsubst %,$(SRC_DIR)/%,$(IMGTGT))
-
-cmd = $(echo-cmd) $(cmd_$(1))
-
-quiet_cmd_genpdf = GENPDF  $2
-      cmd_genpdf = convert $2 $3
-
-quiet_cmd_gendot = DOT     $2
-      cmd_gendot = dot -Tsvg $2 > $3 || { rm -f $3; exit 1; }
-
-%.pdf: %.svg
-	@$(call cmd,genpdf,$<,$@)
-
-%.svg: %.dot
-	@$(call cmd,gendot,$<,$@)
-
 # Rules to convert a .h file to inline RST documentation
 
+SRC_DIR=$(srctree)/Documentation/media
 PARSER = $(srctree)/Documentation/sphinx/parse-headers.pl
 UAPI = $(srctree)/include/uapi/linux
 KAPI = $(srctree)/include/linux
diff --git a/Documentation/media/intro.rst b/Documentation/media/intro.rst
index 8f7490c9a8ef..9ce2e23a0236 100644
--- a/Documentation/media/intro.rst
+++ b/Documentation/media/intro.rst
@@ -13,9 +13,9 @@ A typical media device hardware is shown at :ref:`typical_media_device`.
 
 .. _typical_media_device:
 
-.. figure::  typical_media_device.*
-    :alt:    typical_media_device.pdf / typical_media_device.svg
-    :align:  center
+.. kernel-figure:: typical_media_device.svg
+    :alt:   typical_media_device.svg
+    :align: center
 
     Typical Media Device
 
diff --git a/Documentation/media/uapi/dvb/intro.rst b/Documentation/media/uapi/dvb/intro.rst
index 2ed5c23102b4..652c4aacd2c6 100644
--- a/Documentation/media/uapi/dvb/intro.rst
+++ b/Documentation/media/uapi/dvb/intro.rst
@@ -55,9 +55,9 @@ Overview
 
 .. _stb_components:
 
-.. figure::  dvbstb.*
-    :alt:    dvbstb.pdf / dvbstb.svg
-    :align:  center
+.. kernel-figure:: dvbstb.svg
+    :alt:   dvbstb.svg
+    :align: center
 
     Components of a DVB card/STB
 
diff --git a/Documentation/media/uapi/v4l/crop.rst b/Documentation/media/uapi/v4l/crop.rst
index be58894c9c89..182565b9ace4 100644
--- a/Documentation/media/uapi/v4l/crop.rst
+++ b/Documentation/media/uapi/v4l/crop.rst
@@ -53,8 +53,8 @@ Cropping Structures
 
 .. _crop-scale:
 
-.. figure::  crop.*
-    :alt:    crop.pdf / crop.svg
+.. kernel-figure:: crop.svg
+    :alt:    crop.svg
     :align:  center
 
     Image Cropping, Insertion and Scaling
diff --git a/Documentation/media/uapi/v4l/dev-raw-vbi.rst b/Documentation/media/uapi/v4l/dev-raw-vbi.rst
index baf5f2483927..2e6878b624f6 100644
--- a/Documentation/media/uapi/v4l/dev-raw-vbi.rst
+++ b/Documentation/media/uapi/v4l/dev-raw-vbi.rst
@@ -221,33 +221,29 @@ and always returns default parameters as :ref:`VIDIOC_G_FMT <VIDIOC_G_FMT>` does
 
 .. _vbi-hsync:
 
-.. figure::  vbi_hsync.*
-    :alt:    vbi_hsync.pdf / vbi_hsync.svg
-    :align:  center
+.. kernel-figure:: vbi_hsync.svg
+    :alt:   vbi_hsync.svg
+    :align: center
 
     **Figure 4.1. Line synchronization**
 
 
 .. _vbi-525:
 
-.. figure::  vbi_525.*
-    :alt:    vbi_525.pdf / vbi_525.svg
-    :align:  center
+.. kernel-figure:: vbi_525.svg
+    :alt:   vbi_525.svg
+    :align: center
 
     **Figure 4.2. ITU-R 525 line numbering (M/NTSC and M/PAL)**
 
-
-
 .. _vbi-625:
 
-.. figure::  vbi_625.*
-    :alt:    vbi_625.pdf / vbi_625.svg
-    :align:  center
+.. kernel-figure:: vbi_625.svg
+    :alt:   vbi_625.svg
+    :align: center
 
     **Figure 4.3. ITU-R 625 line numbering**
 
-
-
 Remember the VBI image format depends on the selected video standard,
 therefore the application must choose a new standard or query the
 current standard first. Attempts to read or write data ahead of format
diff --git a/Documentation/media/uapi/v4l/dev-subdev.rst b/Documentation/media/uapi/v4l/dev-subdev.rst
index cd2870180208..f0e762167730 100644
--- a/Documentation/media/uapi/v4l/dev-subdev.rst
+++ b/Documentation/media/uapi/v4l/dev-subdev.rst
@@ -99,9 +99,9 @@ the video sensor and the host image processing hardware.
 
 .. _pipeline-scaling:
 
-.. figure::  pipeline.*
-    :alt:    pipeline.pdf / pipeline.svg
-    :align:  center
+.. kernel-figure:: pipeline.dot
+    :alt:   pipeline.dot
+    :align: center
 
     Image Format Negotiation on Pipelines
 
@@ -404,9 +404,9 @@ selection will refer to the sink pad format dimensions instead.
 
 .. _subdev-image-processing-crop:
 
-.. figure::  subdev-image-processing-crop.*
-    :alt:    subdev-image-processing-crop.pdf / subdev-image-processing-crop.svg
-    :align:  center
+.. kernel-figure:: subdev-image-processing-crop.svg
+    :alt:   subdev-image-processing-crop.svg
+    :align: center
 
     **Figure 4.5. Image processing in subdevs: simple crop example**
 
@@ -421,9 +421,9 @@ pad.
 
 .. _subdev-image-processing-scaling-multi-source:
 
-.. figure::  subdev-image-processing-scaling-multi-source.*
-    :alt:    subdev-image-processing-scaling-multi-source.pdf / subdev-image-processing-scaling-multi-source.svg
-    :align:  center
+.. kernel-figure:: subdev-image-processing-scaling-multi-source.svg
+    :alt:   subdev-image-processing-scaling-multi-source.svg
+    :align: center
 
     **Figure 4.6. Image processing in subdevs: scaling with multiple sources**
 
@@ -437,8 +437,8 @@ an area at location specified by the source crop rectangle from it.
 
 .. _subdev-image-processing-full:
 
-.. figure::  subdev-image-processing-full.*
-    :alt:    subdev-image-processing-full.pdf / subdev-image-processing-full.svg
+.. kernel-figure:: subdev-image-processing-full.svg
+    :alt:    subdev-image-processing-full.svg
     :align:  center
 
     **Figure 4.7. Image processing in subdevs: scaling and composition with multiple sinks and sources**
diff --git a/Documentation/media/uapi/v4l/field-order.rst b/Documentation/media/uapi/v4l/field-order.rst
index e05fb1041363..5f3f82cbfa34 100644
--- a/Documentation/media/uapi/v4l/field-order.rst
+++ b/Documentation/media/uapi/v4l/field-order.rst
@@ -141,17 +141,20 @@ enum v4l2_field
 Field Order, Top Field First Transmitted
 ========================================
 
-.. figure::  fieldseq_tb.*
-    :alt:    fieldseq_tb.pdf / fieldseq_tb.svg
+.. kernel-figure:: fieldseq_tb.svg
+    :alt:    fieldseq_tb.svg
     :align:  center
 
+    Field Order, Top Field First Transmitted
+
 
 .. _fieldseq-bt:
 
 Field Order, Bottom Field First Transmitted
 ===========================================
 
-.. figure::  fieldseq_bt.*
-    :alt:    fieldseq_bt.pdf / fieldseq_bt.svg
+.. kernel-figure:: fieldseq_bt.svg
+    :alt:    fieldseq_bt.svg
     :align:  center
 
+    Field Order, Bottom Field First Transmitted
diff --git a/Documentation/media/uapi/v4l/pixfmt-nv12mt.rst b/Documentation/media/uapi/v4l/pixfmt-nv12mt.rst
index 32d0c8743460..172a3825604e 100644
--- a/Documentation/media/uapi/v4l/pixfmt-nv12mt.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-nv12mt.rst
@@ -33,8 +33,8 @@ Layout of macroblocks in memory is presented in the following figure.
 
 .. _nv12mt:
 
-.. figure::  nv12mt.*
-    :alt:    nv12mt.pdf / nv12mt.svg
+.. kernel-figure:: nv12mt.svg
+    :alt:    nv12mt.svg
     :align:  center
 
     V4L2_PIX_FMT_NV12MT macroblock Z shape memory layout
@@ -50,8 +50,8 @@ interleaved. Height of the buffer is aligned to 32.
 
 .. _nv12mt_ex:
 
-.. figure::  nv12mt_example.*
-    :alt:    nv12mt_example.pdf / nv12mt_example.svg
+.. kernel-figure:: nv12mt_example.svg
+    :alt:    nv12mt_example.svg
     :align:  center
 
     Example V4L2_PIX_FMT_NV12MT memory layout of macroblocks
diff --git a/Documentation/media/uapi/v4l/selection-api-003.rst b/Documentation/media/uapi/v4l/selection-api-003.rst
index 21686f93c38f..bf7e76dfbdf9 100644
--- a/Documentation/media/uapi/v4l/selection-api-003.rst
+++ b/Documentation/media/uapi/v4l/selection-api-003.rst
@@ -7,9 +7,9 @@ Selection targets
 
 .. _sel-targets-capture:
 
-.. figure::  selection.*
-    :alt:    selection.pdf / selection.svg
-    :align:  center
+.. kernel-figure:: selection.svg
+    :alt:   selection.svg
+    :align: center
 
     Cropping and composing targets
 
diff --git a/Documentation/media/uapi/v4l/subdev-formats.rst b/Documentation/media/uapi/v4l/subdev-formats.rst
index d6152c907b8b..89a1fb959314 100644
--- a/Documentation/media/uapi/v4l/subdev-formats.rst
+++ b/Documentation/media/uapi/v4l/subdev-formats.rst
@@ -1514,8 +1514,8 @@ be named ``MEDIA_BUS_FMT_SRGGB10_2X8_PADHI_LE``.
 
 .. _bayer-patterns:
 
-.. figure::  bayer.*
-    :alt:    bayer.pdf / bayer.svg
+.. kernel-figure:: bayer.svg
+    :alt:    bayer.svg
     :align:  center
 
     **Figure 4.8 Bayer Patterns**
diff --git a/Documentation/media/v4l-drivers/index.rst b/Documentation/media/v4l-drivers/index.rst
index a606d1cdac13..90fe22a6414a 100644
--- a/Documentation/media/v4l-drivers/index.rst
+++ b/Documentation/media/v4l-drivers/index.rst
@@ -45,6 +45,7 @@ For more details see the file COPYING in the source distribution of Linux.
 	meye
 	omap3isp
 	omap4_camera
+	philips
 	pvrusb2
 	pxa_camera
 	radiotrack
diff --git a/drivers/media/usb/pwc/philips.txt b/Documentation/media/v4l-drivers/philips.rst
index d38dd791511e..620bcfea7af0 100644
--- a/drivers/media/usb/pwc/philips.txt
+++ b/Documentation/media/v4l-drivers/philips.rst
@@ -1,8 +1,12 @@
+Philips webcams (pwc driver)
+============================
+
 This file contains some additional information for the Philips and OEM webcams.
 E-mail: webcam@smcc.demon.nl                        Last updated: 2004-01-19
 Site: http://www.smcc.demon.nl/webcam/
 
 As of this moment, the following cameras are supported:
+
  * Philips PCA645
  * Philips PCA646
  * Philips PCVC675
@@ -89,7 +93,8 @@ power_save
 compression (only useful with the plugin)
    With this option you can control the compression factor that the camera
    uses to squeeze the image through the USB bus. You can set the
-   parameter between 0 and 3:
+   parameter between 0 and 3::
+
      0 = prefer uncompressed images; if the requested mode is not available
 	 in an uncompressed format, the driver will silently switch to low
 	 compression.
@@ -109,11 +114,11 @@ compression (only useful with the plugin)
 leds
    This settings takes 2 integers, that define the on/off time for the LED
    (in milliseconds). One of the interesting things that you can do with
-   this is let the LED blink while the camera is in use. This:
+   this is let the LED blink while the camera is in use. This::
 
      leds=500,500
 
-   will blink the LED once every second. But with:
+   will blink the LED once every second. But with::
 
      leds=0,0
 
@@ -141,7 +146,7 @@ dev_hint
    A camera is specified by its type (the number from the camera model,
    like PCA645, PCVC750VC, etc) and optionally the serial number (visible
    in /proc/bus/usb/devices). A hint consists of a string with the following
-   format:
+   format::
 
       [type[.serialnumber]:]node
 
@@ -150,7 +155,7 @@ dev_hint
    would be rather pointless). The serialnumber is separated from the type
    by a '.'; the node number by a ':'.
 
-   This somewhat cryptic syntax is best explained by a few examples:
+   This somewhat cryptic syntax is best explained by a few examples::
 
      dev_hint=3,5              The first detected cam gets assigned
 			       /dev/video3, the second /dev/video5. Any
@@ -170,6 +175,7 @@ dev_hint
 				through /dev/video6.
 
    Some points worth knowing:
+
    - Serialnumbers are case sensitive and must be written full, including
      leading zeroes (it's treated as a string).
    - If a device node is already occupied, registration will fail and
@@ -189,8 +195,10 @@ trace
    If you want to trace something, look up the bit value(s) in the table
    below, add the values together and supply that to the trace variable.
 
+   ====== ======= ================================================ =======
    Value  Value   Description					   Default
    (dec)  (hex)
+   ====== ======= ================================================ =======
        1    0x1   Module initialization; this will log messages       On
 		  while loading and unloading the module
 
@@ -208,6 +216,7 @@ trace
       64   0x40   Show viewport and image sizes                       Off
 
      128   0x80   PWCX debugging                                      Off
+   ====== ======= ================================================ =======
 
    For example, to trace the open() & read() functions, sum 8 + 4 = 12,
    so you would supply trace=12 during insmod or modprobe. If
@@ -216,7 +225,7 @@ trace
 
 
 
-Example:
+Example::
 
      # modprobe pwc size=cif fps=15 power_save=1
 
diff --git a/Documentation/media/v4l-drivers/soc-camera.rst b/Documentation/media/v4l-drivers/soc-camera.rst
index ba0c15dd092c..79d09e423700 100644
--- a/Documentation/media/v4l-drivers/soc-camera.rst
+++ b/Documentation/media/v4l-drivers/soc-camera.rst
@@ -12,7 +12,7 @@ The following terms are used in this document:
    control and configuration, and a parallel or a serial bus for data.
  - camera host - an interface, to which a camera is connected. Typically a
    specialised interface, present on many SoCs, e.g. PXA27x and PXA3xx, SuperH,
-   AVR32, i.MX27, i.MX31.
+   i.MX27, i.MX31.
  - camera host bus - a connection between a camera host and a camera. Can be
    parallel or serial, consists of data and control lines, e.g. clock, vertical
    and horizontal synchronization signals.
diff --git a/Documentation/media/v4l-drivers/zr364xx.rst b/Documentation/media/v4l-drivers/zr364xx.rst
index f5280e366826..3d193f01d8bb 100644
--- a/Documentation/media/v4l-drivers/zr364xx.rst
+++ b/Documentation/media/v4l-drivers/zr364xx.rst
@@ -30,7 +30,7 @@ You can try the experience changing the vendor/product ID values (look
 at the source code).
 
 You can get these values by looking at /var/log/messages when you plug
-your camera, or by typing : cat /proc/bus/usb/devices.
+your camera, or by typing : cat /sys/kernel/debug/usb/devices.
 
 If you manage to use your cam with this code, you can send me a mail
 (royale@zerezo.com) with the name of your cam and a patch if needed.
diff --git a/Documentation/mmc/mmc-dev-attrs.txt b/Documentation/mmc/mmc-dev-attrs.txt
index 404a0e9e92b0..4ad0bb17f343 100644
--- a/Documentation/mmc/mmc-dev-attrs.txt
+++ b/Documentation/mmc/mmc-dev-attrs.txt
@@ -13,7 +13,7 @@ SD and MMC Device Attributes
 
 All attributes are read-only.
 
-	cid			Card Identifaction Register
+	cid			Card Identification Register
 	csd			Card Specific Data Register
 	scr			SD Card Configuration Register (SD only)
 	date			Manufacturing Date (from CID Register)
@@ -30,6 +30,7 @@ All attributes are read-only.
 	rel_sectors		Reliable write sector count
 	ocr 			Operation Conditions Register
 	dsr			Driver Stage Register
+	cmdq_en			Command Queue enabled: 1 => enabled, 0 => not enabled
 
 Note on Erase Size and Preferred Erase Size:
 
@@ -71,6 +72,6 @@ Note on Erase Size and Preferred Erase Size:
 	"preferred_erase_size" is in bytes.
 
 Note on raw_rpmb_size_mult:
-	"raw_rpmb_size_mult" is a mutliple of 128kB block.
+	"raw_rpmb_size_mult" is a multiple of 128kB block.
 	RPMB size in byte is calculated by using the following equation:
 	RPMB partition size = 128kB x raw_rpmb_size_mult
diff --git a/Documentation/networking/cdc_mbim.txt b/Documentation/networking/cdc_mbim.txt
index b9482ca10254..e4c376abbdad 100644
--- a/Documentation/networking/cdc_mbim.txt
+++ b/Documentation/networking/cdc_mbim.txt
@@ -332,7 +332,7 @@ References
 [5] "MBIM (Mobile Broadband Interface Model) Registry"
        - http://compliance.usb.org/mbim/
 
-[6] "/proc/bus/usb filesystem output"
+[6] "/dev/bus/usb filesystem output"
        - Documentation/usb/proc_usb_info.txt
 
 [7] "/sys/bus/usb/devices/.../descriptors"
diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt
index 42ddbd4b52a9..54810b82c01a 100644
--- a/Documentation/networking/e100.txt
+++ b/Documentation/networking/e100.txt
@@ -130,7 +130,7 @@ Additional Configurations
   version 1.6 or later is required for this functionality.
 
   The latest release of ethtool can be found from
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://www.kernel.org/pub/software/network/ethtool/
 
   Enabling Wake on LAN* (WoL)
   ---------------------------
diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt
index 437b2099cced..1f6ed848363d 100644
--- a/Documentation/networking/e1000.txt
+++ b/Documentation/networking/e1000.txt
@@ -435,7 +435,7 @@ Additional Configurations
   version 1.6 or later is required for this functionality.
 
   The latest release of ethtool can be found from
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://www.kernel.org/pub/software/network/ethtool/
 
   Enabling Wake on LAN* (WoL)
   ---------------------------
diff --git a/Documentation/networking/e1000e.txt b/Documentation/networking/e1000e.txt
index ad2d9f38ce14..12089547baed 100644
--- a/Documentation/networking/e1000e.txt
+++ b/Documentation/networking/e1000e.txt
@@ -274,7 +274,7 @@ Additional Configurations
   diagnostics, as well as displaying statistical information.  We
   strongly recommend downloading the latest version of ethtool at:
 
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://kernel.org/pub/software/network/ethtool/
 
   NOTE: When validating enable/disable tests on some parts (82578, for example)
   you need to add a few seconds between tests when working with ethtool.
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 683ada5ad81d..b69b205501de 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -595,10 +595,9 @@ got from bpf_prog_create(), and 'ctx' the given context (e.g.
 skb pointer). All constraints and restrictions from bpf_check_classic() apply
 before a conversion to the new layout is being done behind the scenes!
 
-Currently, the classic BPF format is being used for JITing on most of the
-architectures. x86-64, aarch64 and s390x perform JIT compilation from eBPF
-instruction set, however, future work will migrate other JIT compilers as well,
-so that they will profit from the very same benefits.
+Currently, the classic BPF format is being used for JITing on most 32-bit
+architectures, whereas x86-64, aarch64, s390x, powerpc64, sparc64 perform JIT
+compilation from eBPF instruction set.
 
 Some core changes of the new internal format:
 
diff --git a/Documentation/networking/i40e.txt b/Documentation/networking/i40e.txt
index a251bf4fe9c9..57e616ed10b0 100644
--- a/Documentation/networking/i40e.txt
+++ b/Documentation/networking/i40e.txt
@@ -63,6 +63,78 @@ Additional Configurations
   The latest release of ethtool can be found from
   https://www.kernel.org/pub/software/network/ethtool
 
+
+  Flow Director n-ntuple traffic filters (FDir)
+  ---------------------------------------------
+  The driver utilizes the ethtool interface for configuring ntuple filters,
+  via "ethtool -N <device> <filter>".
+
+  The sctp4, ip4, udp4, and tcp4 flow types are supported with the standard
+  fields including src-ip, dst-ip, src-port and dst-port. The driver only
+  supports fully enabling or fully masking the fields, so use of the mask
+  fields for partial matches is not supported.
+
+  Additionally, the driver supports using the action to specify filters for a
+  Virtual Function. You can specify the action as a 64bit value, where the
+  lower 32 bits represents the queue number, while the next 8 bits represent
+  which VF. Note that 0 is the PF, so the VF identifier is offset by 1. For
+  example:
+
+    ... action 0x800000002 ...
+
+  Would indicate to direct traffic for Virtual Function 7 (8 minus 1) on queue
+  2 of that VF.
+
+  The driver also supports using the user-defined field to specify 2 bytes of
+  arbitrary data to match within the packet payload in addition to the regular
+  fields. The data is specified in the lower 32bits of the user-def field in
+  the following way:
+
+  +----------------------------+---------------------------+
+  | 31    28    24    20    16 | 15    12     8     4     0|
+  +----------------------------+---------------------------+
+  | offset into packet payload |  2 bytes of flexible data |
+  +----------------------------+---------------------------+
+
+  As an example,
+
+    ... user-def 0x4FFFF ....
+
+  means to match the value 0xFFFF 4 bytes into the packet payload. Note that
+  the offset is based on the beginning of the payload, and not the beginning
+  of the packet. Thus
+
+    flow-type tcp4 ... user-def 0x8BEAF ....
+
+  would match TCP/IPv4 packets which have the value 0xBEAF 8bytes into the
+  TCP/IPv4 payload.
+
+  For ICMP, the hardware parses the ICMP header as 4 bytes of header and 4
+  bytes of payload, so if you want to match an ICMP frames payload you may need
+  to add 4 to the offset in order to match the data.
+
+  Furthermore, the offset can only be up to a value of 64, as the hardware
+  will only read up to 64 bytes of data from the payload. It must also be even
+  as the flexible data is 2 bytes long and must be aligned to byte 0 of the
+  packet payload.
+
+  When programming filters, the hardware is limited to using a single input
+  set for each flow type. This means that it is an error to program two
+  different filters with the same type that don't match on the same fields.
+  Thus the second of the following two commands will fail:
+
+    ethtool -N <device> flow-type tcp4 src-ip 192.168.0.7 action 5
+    ethtool -N <device> flow-type tcp4 dst-ip 192.168.15.18 action 1
+
+  This is because the first filter will be accepted and reprogram the input
+  set for TCPv4 filters, but the second filter will be unable to reprogram the
+  input set until all the conflicting TCPv4 filters are first removed.
+
+  Note that the user-defined flexible offset is also considered part of the
+  input set and cannot be programmed separately for multiple filters of the
+  same type. However, the flexible data is not part of the input set and
+  multiple filters may use the same offset but match against different data.
+
   Data Center Bridging (DCB)
   --------------------------
   DCB configuration is not currently supported.
diff --git a/Documentation/networking/igb.txt b/Documentation/networking/igb.txt
index 15534fdd09a8..f90643ef39c9 100644
--- a/Documentation/networking/igb.txt
+++ b/Documentation/networking/igb.txt
@@ -63,7 +63,7 @@ Additional Configurations
   diagnostics, as well as displaying statistical information. The latest
   version of ethtool can be found at:
 
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://www.kernel.org/pub/software/network/ethtool/
 
   Enabling Wake on LAN* (WoL)
   ---------------------------
diff --git a/Documentation/networking/igbvf.txt b/Documentation/networking/igbvf.txt
index 40db17a6665b..bd404735fb46 100644
--- a/Documentation/networking/igbvf.txt
+++ b/Documentation/networking/igbvf.txt
@@ -62,7 +62,7 @@ Additional Configurations
   version 3.0 or later is required for this functionality, although we
   strongly recommend downloading the latest version at:
 
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://www.kernel.org/pub/software/network/ethtool/
 
 Support
 =======
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index fc73eeb7b3b8..974ab47ae53a 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -73,6 +73,14 @@ fib_multipath_use_neigh - BOOLEAN
 	0 - disabled
 	1 - enabled
 
+fib_multipath_hash_policy - INTEGER
+	Controls which hash policy to use for multipath routes. Only valid
+	for kernels built with CONFIG_IP_ROUTE_MULTIPATH enabled.
+	Default: 0 (Layer 3)
+	Possible values:
+	0 - Layer 3
+	1 - Layer 4
+
 route/max_size - INTEGER
 	Maximum number of routes allowed in the kernel.  Increase
 	this when using large numbers of interfaces and/or routes.
@@ -594,6 +602,14 @@ tcp_fastopen - INTEGER
 	Note that that additional client or server features are only
 	effective if the basic support (0x1 and 0x2) are enabled respectively.
 
+tcp_fastopen_blackhole_timeout_sec - INTEGER
+	Initial time period in second to disable Fastopen on active TCP sockets
+	when a TFO firewall blackhole issue happens.
+	This time period will grow exponentially when more blackhole issues
+	get detected right after Fastopen is re-enabled and will reset to
+	initial value when the blackhole issue goes away.
+	By default, it is set to 1hr.
+
 tcp_syn_retries - INTEGER
 	Number of times initial SYNs for an active TCP connection attempt
 	will be retransmitted. Should not be higher than 127. Default value
@@ -640,11 +656,6 @@ tcp_tso_win_divisor - INTEGER
 	building larger TSO frames.
 	Default: 3
 
-tcp_tw_recycle - BOOLEAN
-	Enable fast recycling TIME-WAIT sockets. Default value is 0.
-	It should not be changed without advice/request of technical
-	experts.
-
 tcp_tw_reuse - BOOLEAN
 	Allow to reuse TIME-WAIT sockets for new connections when it is
 	safe from protocol viewpoint. Default value is 0.
@@ -853,12 +864,21 @@ ip_dynaddr - BOOLEAN
 ip_early_demux - BOOLEAN
 	Optimize input packet processing down to one demux for
 	certain kinds of local sockets.  Currently we only do this
-	for established TCP sockets.
+	for established TCP and connected UDP sockets.
 
 	It may add an additional cost for pure routing workloads that
 	reduces overall throughput, in such case you should disable it.
 	Default: 1
 
+tcp_early_demux - BOOLEAN
+	Enable early demux for established TCP sockets.
+	Default: 1
+
+udp_early_demux - BOOLEAN
+	Enable early demux for connected UDP sockets. Disable this if
+	your system could experience more unconnected load.
+	Default: 1
+
 icmp_echo_ignore_all - BOOLEAN
 	If set non-zero, then the kernel will ignore all ICMP ECHO
 	requests sent to it.
@@ -1006,7 +1026,8 @@ accept_redirects - BOOLEAN
 		FALSE (router)
 
 forwarding - BOOLEAN
-	Enable IP forwarding on this interface.
+	Enable IP forwarding on this interface.  This controls whether packets
+	received _on_ this interface can be forwarded.
 
 mc_forwarding - BOOLEAN
 	Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
@@ -1457,11 +1478,20 @@ accept_ra_pinfo - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+accept_ra_rt_info_min_plen - INTEGER
+	Minimum prefix length of Route Information in RA.
+
+	Route Information w/ prefix smaller than this variable shall
+	be ignored.
+
+	Functional default: 0 if accept_ra_rtr_pref is enabled.
+			    -1 if accept_ra_rtr_pref is disabled.
+
 accept_ra_rt_info_max_plen - INTEGER
 	Maximum prefix length of Route Information in RA.
 
-	Route Information w/ prefix larger than or equal to this
-	variable shall be ignored.
+	Route Information w/ prefix larger than this variable shall
+	be ignored.
 
 	Functional default: 0 if accept_ra_rtr_pref is enabled.
 			    -1 if accept_ra_rtr_pref is disabled.
diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index e6b1c025fdd8..056898685d40 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -175,6 +175,14 @@ nat_icmp_send - BOOLEAN
         for VS/NAT when the load balancer receives packets from real
         servers but the connection entries don't exist.
 
+pmtu_disc - BOOLEAN
+	0 - disabled
+	not 0 - enabled (default)
+
+	By default, reject with FRAG_NEEDED all DF packets that exceed
+	the PMTU, irrespective of the forwarding method. For TUN method
+	the flag can be disabled to fragment such packets.
+
 secure_tcp - INTEGER
         0  - disabled (default)
 
@@ -185,15 +193,59 @@ secure_tcp - INTEGER
         The value definition is the same as that of drop_entry and
         drop_packet.
 
-sync_threshold - INTEGER
-        default 3
+sync_threshold - vector of 2 INTEGERs: sync_threshold, sync_period
+	default 3 50
+
+	It sets synchronization threshold, which is the minimum number
+	of incoming packets that a connection needs to receive before
+	the connection will be synchronized. A connection will be
+	synchronized, every time the number of its incoming packets
+	modulus sync_period equals the threshold. The range of the
+	threshold is from 0 to sync_period.
+
+	When sync_period and sync_refresh_period are 0, send sync only
+	for state changes or only once when pkts matches sync_threshold
+
+sync_refresh_period - UNSIGNED INTEGER
+	default 0
+
+	In seconds, difference in reported connection timer that triggers
+	new sync message. It can be used to avoid sync messages for the
+	specified period (or half of the connection timeout if it is lower)
+	if connection state is not changed since last sync.
+
+	This is useful for normal connections with high traffic to reduce
+	sync rate. Additionally, retry sync_retries times with period of
+	sync_refresh_period/8.
+
+sync_retries - INTEGER
+	default 0
+
+	Defines sync retries with period of sync_refresh_period/8. Useful
+	to protect against loss of sync messages. The range of the
+	sync_retries is from 0 to 3.
+
+sync_qlen_max - UNSIGNED LONG
+
+	Hard limit for queued sync messages that are not sent yet. It
+	defaults to 1/32 of the memory pages but actually represents
+	number of messages. It will protect us from allocating large
+	parts of memory when the sending rate is lower than the queuing
+	rate.
+
+sync_sock_size - INTEGER
+	default 0
+
+	Configuration of SNDBUF (master) or RCVBUF (slave) socket limit.
+	Default value is 0 (preserve system defaults).
+
+sync_ports - INTEGER
+	default 1
 
-        It sets synchronization threshold, which is the minimum number
-        of incoming packets that a connection needs to receive before
-        the connection will be synchronized. A connection will be
-        synchronized, every time the number of its incoming packets
-        modulus 50 equals the threshold. The range of the threshold is
-        from 0 to 49.
+	The number of threads that master and backup servers can use for
+	sync traffic. Every thread will use single UDP port, thread 0 will
+	use the default port 8848 while last thread will use port
+	8848+sync_ports-1.
 
 snat_reroute - BOOLEAN
 	0 - disabled
diff --git a/Documentation/networking/ixgb.txt b/Documentation/networking/ixgb.txt
index 9b4a10a1cf50..09f71d71920a 100644
--- a/Documentation/networking/ixgb.txt
+++ b/Documentation/networking/ixgb.txt
@@ -313,7 +313,7 @@ Additional Configurations
   version 1.6 or later is required for this functionality.
 
   The latest release of ethtool can be found from
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://www.kernel.org/pub/software/network/ethtool/
 
   NOTE: The ethtool version 1.6 only supports a limited set of ethtool options.
         Support for a more complete ethtool feature set can be enabled by
diff --git a/Documentation/networking/ixgbe.txt b/Documentation/networking/ixgbe.txt
index 6f0cb57b59c6..687835415707 100644
--- a/Documentation/networking/ixgbe.txt
+++ b/Documentation/networking/ixgbe.txt
@@ -272,7 +272,7 @@ Additional Configurations
   ethtool version is required for this functionality.
 
   The latest release of ethtool can be found from
-  http://ftp.kernel.org/pub/software/network/ethtool/
+  https://www.kernel.org/pub/software/network/ethtool/
 
   FCoE
   ----
diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt
index 15d8d16934fd..2f24a1912a48 100644
--- a/Documentation/networking/mpls-sysctl.txt
+++ b/Documentation/networking/mpls-sysctl.txt
@@ -19,6 +19,25 @@ platform_labels - INTEGER
 	Possible values: 0 - 1048575
 	Default: 0
 
+ip_ttl_propagate - BOOL
+	Control whether TTL is propagated from the IPv4/IPv6 header to
+	the MPLS header on imposing labels and propagated from the
+	MPLS header to the IPv4/IPv6 header on popping the last label.
+
+	If disabled, the MPLS transport network will appear as a
+	single hop to transit traffic.
+
+	0 - disabled / RFC 3443 [Short] Pipe Model
+	1 - enabled / RFC 3443 Uniform Model (default)
+
+default_ttl - BOOL
+	Default TTL value to use for MPLS packets where it cannot be
+	propagated from an IP header, either because one isn't present
+	or ip_ttl_propagate has been disabled.
+
+	Possible values: 1 - 255
+	Default: 255
+
 conf/<interface>/input - BOOL
 	Control whether packets can be input on this interface.
 
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index 2bbac05ab9e2..3e7b946dea27 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -13,43 +13,43 @@ an example setup using a data-center-class switch ASIC chip.  Other setups
 with SR-IOV or soft switches, such as OVS, are possible.
 
 
-                             User-space tools                                 
-                                                                              
-       user space                   |                                         
-      +-------------------------------------------------------------------+   
-       kernel                       | Netlink                                 
-                                    |                                         
-                     +--------------+-------------------------------+         
-                     |         Network stack                        |         
-                     |           (Linux)                            |         
-                     |                                              |         
-                     +----------------------------------------------+         
-                                                                              
+                             User-space tools
+
+       user space                   |
+      +-------------------------------------------------------------------+
+       kernel                       | Netlink
+                                    |
+                     +--------------+-------------------------------+
+                     |         Network stack                        |
+                     |           (Linux)                            |
+                     |                                              |
+                     +----------------------------------------------+
+
                            sw1p2     sw1p4     sw1p6
-                      sw1p1  +  sw1p3  +  sw1p5  +          eth1             
-                        +    |    +    |    +    |            +               
-                        |    |    |    |    |    |            |               
-                     +--+----+----+----+-+--+----+---+  +-----+-----+         
-                     |         Switch driver         |  |    mgmt   |         
-                     |        (this document)        |  |   driver  |         
-                     |                               |  |           |         
-                     +--------------+----------------+  +-----------+         
-                                    |                                         
-       kernel                       | HW bus (eg PCI)                         
-      +-------------------------------------------------------------------+   
-       hardware                     |                                         
-                     +--------------+---+------------+                        
-                     |         Switch device (sw1)   |                        
-                     |  +----+                       +--------+               
-                     |  |    v offloaded data path   | mgmt port              
-                     |  |    |                       |                        
-                     +--|----|----+----+----+----+---+                        
-                        |    |    |    |    |    |                            
-                        +    +    +    +    +    +                            
+                      sw1p1  +  sw1p3  +  sw1p5  +          eth1
+                        +    |    +    |    +    |            +
+                        |    |    |    |    |    |            |
+                     +--+----+----+----+-+--+----+---+  +-----+-----+
+                     |         Switch driver         |  |    mgmt   |
+                     |        (this document)        |  |   driver  |
+                     |                               |  |           |
+                     +--------------+----------------+  +-----------+
+                                    |
+       kernel                       | HW bus (eg PCI)
+      +-------------------------------------------------------------------+
+       hardware                     |
+                     +--------------+---+------------+
+                     |         Switch device (sw1)   |
+                     |  +----+                       +--------+
+                     |  |    v offloaded data path   | mgmt port
+                     |  |    |                       |
+                     +--|----|----+----+----+----+---+
+                        |    |    |    |    |    |
+                        +    +    +    +    +    +
                        p1   p2   p3   p4   p5   p6
-                                       
-                             front-panel ports                                
-                                                                              
+
+                             front-panel ports
+
 
                                     Fig 1.
 
diff --git a/Documentation/phy.txt b/Documentation/phy.txt
index 0aa994bd9a91..383cdd863f08 100644
--- a/Documentation/phy.txt
+++ b/Documentation/phy.txt
@@ -97,7 +97,7 @@ should contain the phy name as given in the dt data and in the case of
 non-dt boot, it should contain the label of the PHY.  The two
 devm_phy_get associates the device with the PHY using devres on
 successful PHY get. On driver detach, release function is invoked on
-the the devres data and devres data is freed. phy_optional_get and
+the devres data and devres data is freed. phy_optional_get and
 devm_phy_optional_get should be used when the phy is optional. These
 two functions will never return -ENODEV, but instead returns NULL when
 the phy cannot be found.Some generic drivers, such as ehci, may use multiple
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index 54bd5faa8782..f2af35f6d6b2 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -77,9 +77,15 @@ static struct pinctrl_desc foo_desc = {
 
 int __init foo_probe(void)
 {
+	int error;
+
 	struct pinctrl_dev *pctl;
 
-	return pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+	error = pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+	if (error)
+		return error;
+
+	return pinctrl_enable(pctl);
 }
 
 To enable the pinctrl subsystem and the subgroups for PINMUX and PINCONF and
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 64546eb9a16a..ee69d7532172 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -478,15 +478,23 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
     - set the power.last_busy field to the current time
 
   void pm_runtime_use_autosuspend(struct device *dev);
-    - set the power.use_autosuspend flag, enabling autosuspend delays
+    - set the power.use_autosuspend flag, enabling autosuspend delays; call
+      pm_runtime_get_sync if the flag was previously cleared and
+      power.autosuspend_delay is negative
 
   void pm_runtime_dont_use_autosuspend(struct device *dev);
-    - clear the power.use_autosuspend flag, disabling autosuspend delays
+    - clear the power.use_autosuspend flag, disabling autosuspend delays;
+      decrement the device's usage counter if the flag was previously set and
+      power.autosuspend_delay is negative; call pm_runtime_idle
 
   void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
     - set the power.autosuspend_delay value to 'delay' (expressed in
       milliseconds); if 'delay' is negative then runtime suspends are
-      prevented
+      prevented; if power.use_autosuspend is set, pm_runtime_get_sync may be
+      called or the device's usage counter may be decremented and
+      pm_runtime_idle called depending on if power.autosuspend_delay is
+      changed to or from a negative value; if power.use_autosuspend is clear,
+      pm_runtime_idle is called
 
   unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
     - calculate the time when the current autosuspend delay period will expire,
@@ -836,9 +844,8 @@ of the non-autosuspend counterparts:
 	Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
 
 Drivers may also continue to use the non-autosuspend helper functions; they
-will behave normally, not taking the autosuspend delay into account.
-Similarly, if the power.use_autosuspend field isn't set then the autosuspend
-helper functions will behave just like the non-autosuspend counterparts.
+will behave normally, which means sometimes taking the autosuspend delay into
+account (see pm_runtime_idle).
 
 Under some circumstances a driver or subsystem may want to prevent a device
 from autosuspending immediately, even though the usage counter is zero and the
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 8cc17ca71813..9f2f942a01cf 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -406,7 +406,7 @@ Firewire, CompactFlash, MMC, external SATA, or even IDE hotplug bays)
 before suspending; then remount them after resuming.
 
 There is a work-around for this problem.  For more information, see
-Documentation/usb/persist.txt.
+Documentation/driver-api/usb/persist.rst.
 
 Q: Can I suspend-to-disk using a swap partition under LVM?
 
diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index 2a728d898fc5..6df19943dd4d 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -22,11 +22,11 @@ Coding style
 ************
 
 The kernel has long had a standard coding style, described in
-Documentation/process/coding-style.rst.  For much of that time, the policies described
-in that file were taken as being, at most, advisory.  As a result, there is
-a substantial amount of code in the kernel which does not meet the coding
-style guidelines.  The presence of that code leads to two independent
-hazards for kernel developers.
+:ref:`Documentation/process/coding-style.rst <codingstyle>`.  For much of
+that time, the policies described in that file were taken as being, at most,
+advisory.  As a result, there is a substantial amount of code in the kernel
+which does not meet the coding style guidelines.  The presence of that code
+leads to two independent hazards for kernel developers.
 
 The first of these is to believe that the kernel coding standards do not
 matter and are not enforced.  The truth of the matter is that adding new
@@ -343,9 +343,10 @@ user-space developers to know what they are working with.  See
 Documentation/ABI/README for a description of how this documentation should
 be formatted and what information needs to be provided.
 
-The file Documentation/admin-guide/kernel-parameters.rst describes all of the kernel's
-boot-time parameters.  Any patch which adds new parameters should add the
-appropriate entries to this file.
+The file :ref:`Documentation/admin-guide/kernel-parameters.rst
+<kernelparameters>` describes all of the kernel's boot-time parameters.
+Any patch which adds new parameters should add the appropriate entries to
+this file.
 
 Any new configuration options must be accompanied by help text which
 clearly explains the options and when the user might want to select them.
diff --git a/Documentation/process/applying-patches.rst b/Documentation/process/applying-patches.rst
index 87825cf96f33..a0d058cc6d25 100644
--- a/Documentation/process/applying-patches.rst
+++ b/Documentation/process/applying-patches.rst
@@ -250,17 +250,11 @@ specific homes.
 
 The 4.x.y (-stable) and 4.x patches live at
 
-	ftp://ftp.kernel.org/pub/linux/kernel/v4.x/
+	https://www.kernel.org/pub/linux/kernel/v4.x/
 
 The -rc patches live at
 
-	ftp://ftp.kernel.org/pub/linux/kernel/v4.x/testing/
-
-In place of ``ftp.kernel.org`` you can use ``ftp.cc.kernel.org``, where cc is a
-country code. This way you'll be downloading from a mirror site that's most
-likely geographically closer to you, resulting in faster downloads for you,
-less bandwidth used globally and less load on the main kernel.org servers --
-these are good things, so do use mirrors when possible.
+	https://www.kernel.org/pub/linux/kernel/v4.x/testing/
 
 
 The 4.x kernels
@@ -317,7 +311,7 @@ the current stable kernel.
  The -stable team usually do make incremental patches available as well
  as patches against the latest mainline release, but I only cover the
  non-incremental ones below. The incremental ones can be found at
- ftp://ftp.kernel.org/pub/linux/kernel/v4.x/incr/
+ https://www.kernel.org/pub/linux/kernel/v4.x/incr/
 
 These patches are not incremental, meaning that for example the 4.7.3
 patch does not apply on top of the 4.7.2 kernel source, but rather on top
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 56ce66114665..01c5dbcd0f84 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -318,9 +318,10 @@ PDF outputs, it is recommended to use version 1.4.6.
 .. note::
 
   Please notice that, for PDF and LaTeX output, you'll also need ``XeLaTeX``
-  version 3.14159265. Depending on the distribution, you may also need
-  to install a series of ``texlive`` packages that provide the minimal
-  set of functionalities required for ``XeLaTex`` to work.
+  version 3.14159265. Depending on the distribution, you may also need to
+  install a series of ``texlive`` packages that provide the minimal set of
+  functionalities required for ``XeLaTex`` to work. For PDF output you'll also
+  need ``convert(1)`` from ImageMagick (https://www.imagemagick.org).
 
 Other tools
 -----------
@@ -348,7 +349,7 @@ Make
 Binutils
 --------
 
-- <ftp://ftp.kernel.org/pub/linux/devel/binutils/>
+- <https://www.kernel.org/pub/linux/devel/binutils/>
 
 OpenSSL
 -------
@@ -361,17 +362,17 @@ System utilities
 Util-linux
 ----------
 
-- <ftp://ftp.kernel.org/pub/linux/utils/util-linux/>
+- <https://www.kernel.org/pub/linux/utils/util-linux/>
 
 Ksymoops
 --------
 
-- <ftp://ftp.kernel.org/pub/linux/utils/kernel/ksymoops/v2.4/>
+- <https://www.kernel.org/pub/linux/utils/kernel/ksymoops/v2.4/>
 
 Module-Init-Tools
 -----------------
 
-- <ftp://ftp.kernel.org/pub/linux/kernel/people/rusty/modules/>
+- <https://www.kernel.org/pub/linux/utils/kernel/module-init-tools/>
 
 Mkinitrd
 --------
@@ -401,7 +402,7 @@ Xfsprogs
 Pcmciautils
 -----------
 
-- <ftp://ftp.kernel.org/pub/linux/utils/kernel/pcmcia/>
+- <https://www.kernel.org/pub/linux/utils/kernel/pcmcia/>
 
 Quota-tools
 -----------
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index 11ec2d93a5e0..61e9c78bd6d1 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -124,7 +124,7 @@ specified in the following format in the sign-off area:
 
 .. code-block:: none
 
-     Cc: <stable@vger.kernel.org> # 3.3.x-
+     Cc: <stable@vger.kernel.org> # 3.3.x
 
 The tag has the meaning of:
 
diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX
index 9189535f6cd2..317f0378ae01 100644
--- a/Documentation/s390/00-INDEX
+++ b/Documentation/s390/00-INDEX
@@ -22,5 +22,7 @@ qeth.txt
 	- HiperSockets Bridge Port Support.
 s390dbf.txt
 	- information on using the s390 debug feature.
+vfio-ccw.txt
+	  information on the vfio-ccw I/O subchannel driver.
 zfcpdump.txt
 	- information on the s390 SCSI dump tool.
diff --git a/Documentation/s390/vfio-ccw.txt b/Documentation/s390/vfio-ccw.txt
new file mode 100644
index 000000000000..90b3dfead81b
--- /dev/null
+++ b/Documentation/s390/vfio-ccw.txt
@@ -0,0 +1,303 @@
+vfio-ccw: the basic infrastructure
+==================================
+
+Introduction
+------------
+
+Here we describe the vfio support for I/O subchannel devices for
+Linux/s390. Motivation for vfio-ccw is to passthrough subchannels to a
+virtual machine, while vfio is the means.
+
+Different than other hardware architectures, s390 has defined a unified
+I/O access method, which is so called Channel I/O. It has its own access
+patterns:
+- Channel programs run asynchronously on a separate (co)processor.
+- The channel subsystem will access any memory designated by the caller
+  in the channel program directly, i.e. there is no iommu involved.
+Thus when we introduce vfio support for these devices, we realize it
+with a mediated device (mdev) implementation. The vfio mdev will be
+added to an iommu group, so as to make itself able to be managed by the
+vfio framework. And we add read/write callbacks for special vfio I/O
+regions to pass the channel programs from the mdev to its parent device
+(the real I/O subchannel device) to do further address translation and
+to perform I/O instructions.
+
+This document does not intend to explain the s390 I/O architecture in
+every detail. More information/reference could be found here:
+- A good start to know Channel I/O in general:
+  https://en.wikipedia.org/wiki/Channel_I/O
+- s390 architecture:
+  s390 Principles of Operation manual (IBM Form. No. SA22-7832)
+- The existing Qemu code which implements a simple emulated channel
+  subsystem could also be a good reference. It makes it easier to follow
+  the flow.
+  qemu/hw/s390x/css.c
+
+For vfio mediated device framework:
+- Documentation/vfio-mediated-device.txt
+
+Motivation of vfio-ccw
+----------------------
+
+Currently, a guest virtualized via qemu/kvm on s390 only sees
+paravirtualized virtio devices via the "Virtio Over Channel I/O
+(virtio-ccw)" transport. This makes virtio devices discoverable via
+standard operating system algorithms for handling channel devices.
+
+However this is not enough. On s390 for the majority of devices, which
+use the standard Channel I/O based mechanism, we also need to provide
+the functionality of passing through them to a Qemu virtual machine.
+This includes devices that don't have a virtio counterpart (e.g. tape
+drives) or that have specific characteristics which guests want to
+exploit.
+
+For passing a device to a guest, we want to use the same interface as
+everybody else, namely vfio. Thus, we would like to introduce vfio
+support for channel devices. And we would like to name this new vfio
+device "vfio-ccw".
+
+Access patterns of CCW devices
+------------------------------
+
+s390 architecture has implemented a so called channel subsystem, that
+provides a unified view of the devices physically attached to the
+systems. Though the s390 hardware platform knows about a huge variety of
+different peripheral attachments like disk devices (aka. DASDs), tapes,
+communication controllers, etc. They can all be accessed by a well
+defined access method and they are presenting I/O completion a unified
+way: I/O interruptions.
+
+All I/O requires the use of channel command words (CCWs). A CCW is an
+instruction to a specialized I/O channel processor. A channel program is
+a sequence of CCWs which are executed by the I/O channel subsystem.  To
+issue a channel program to the channel subsystem, it is required to
+build an operation request block (ORB), which can be used to point out
+the format of the CCW and other control information to the system. The
+operating system signals the I/O channel subsystem to begin executing
+the channel program with a SSCH (start sub-channel) instruction. The
+central processor is then free to proceed with non-I/O instructions
+until interrupted. The I/O completion result is received by the
+interrupt handler in the form of interrupt response block (IRB).
+
+Back to vfio-ccw, in short:
+- ORBs and channel programs are built in guest kernel (with guest
+  physical addresses).
+- ORBs and channel programs are passed to the host kernel.
+- Host kernel translates the guest physical addresses to real addresses
+  and starts the I/O with issuing a privileged Channel I/O instruction
+  (e.g SSCH).
+- channel programs run asynchronously on a separate processor.
+- I/O completion will be signaled to the host with I/O interruptions.
+  And it will be copied as IRB to user space to pass it back to the
+  guest.
+
+Physical vfio ccw device and its child mdev
+-------------------------------------------
+
+As mentioned above, we realize vfio-ccw with a mdev implementation.
+
+Channel I/O does not have IOMMU hardware support, so the physical
+vfio-ccw device does not have an IOMMU level translation or isolation.
+
+Sub-channel I/O instructions are all privileged instructions, When
+handling the I/O instruction interception, vfio-ccw has the software
+policing and translation how the channel program is programmed before
+it gets sent to hardware.
+
+Within this implementation, we have two drivers for two types of
+devices:
+- The vfio_ccw driver for the physical subchannel device.
+  This is an I/O subchannel driver for the real subchannel device.  It
+  realizes a group of callbacks and registers to the mdev framework as a
+  parent (physical) device. As a consequence, mdev provides vfio_ccw a
+  generic interface (sysfs) to create mdev devices. A vfio mdev could be
+  created by vfio_ccw then and added to the mediated bus. It is the vfio
+  device that added to an IOMMU group and a vfio group.
+  vfio_ccw also provides an I/O region to accept channel program
+  request from user space and store I/O interrupt result for user
+  space to retrieve. To notify user space an I/O completion, it offers
+  an interface to setup an eventfd fd for asynchronous signaling.
+
+- The vfio_mdev driver for the mediated vfio ccw device.
+  This is provided by the mdev framework. It is a vfio device driver for
+  the mdev that created by vfio_ccw.
+  It realize a group of vfio device driver callbacks, adds itself to a
+  vfio group, and registers itself to the mdev framework as a mdev
+  driver.
+  It uses a vfio iommu backend that uses the existing map and unmap
+  ioctls, but rather than programming them into an IOMMU for a device,
+  it simply stores the translations for use by later requests. This
+  means that a device programmed in a VM with guest physical addresses
+  can have the vfio kernel convert that address to process virtual
+  address, pin the page and program the hardware with the host physical
+  address in one step.
+  For a mdev, the vfio iommu backend will not pin the pages during the
+  VFIO_IOMMU_MAP_DMA ioctl. Mdev framework will only maintain a database
+  of the iova<->vaddr mappings in this operation. And they export a
+  vfio_pin_pages and a vfio_unpin_pages interfaces from the vfio iommu
+  backend for the physical devices to pin and unpin pages by demand.
+
+Below is a high Level block diagram.
+
+ +-------------+
+ |             |
+ | +---------+ | mdev_register_driver() +--------------+
+ | |  Mdev   | +<-----------------------+              |
+ | |  bus    | |                        | vfio_mdev.ko |
+ | | driver  | +----------------------->+              |<-> VFIO user
+ | +---------+ |    probe()/remove()    +--------------+    APIs
+ |             |
+ |  MDEV CORE  |
+ |   MODULE    |
+ |   mdev.ko   |
+ | +---------+ | mdev_register_device() +--------------+
+ | |Physical | +<-----------------------+              |
+ | | device  | |                        |  vfio_ccw.ko |<-> subchannel
+ | |interface| +----------------------->+              |     device
+ | +---------+ |       callback         +--------------+
+ +-------------+
+
+The process of how these work together.
+1. vfio_ccw.ko drives the physical I/O subchannel, and registers the
+   physical device (with callbacks) to mdev framework.
+   When vfio_ccw probing the subchannel device, it registers device
+   pointer and callbacks to the mdev framework. Mdev related file nodes
+   under the device node in sysfs would be created for the subchannel
+   device, namely 'mdev_create', 'mdev_destroy' and
+   'mdev_supported_types'.
+2. Create a mediated vfio ccw device.
+   Use the 'mdev_create' sysfs file, we need to manually create one (and
+   only one for our case) mediated device.
+3. vfio_mdev.ko drives the mediated ccw device.
+   vfio_mdev is also the vfio device drvier. It will probe the mdev and
+   add it to an iommu_group and a vfio_group. Then we could pass through
+   the mdev to a guest.
+
+vfio-ccw I/O region
+-------------------
+
+An I/O region is used to accept channel program request from user
+space and store I/O interrupt result for user space to retrieve. The
+defination of the region is:
+
+struct ccw_io_region {
+#define ORB_AREA_SIZE 12
+	__u8	orb_area[ORB_AREA_SIZE];
+#define SCSW_AREA_SIZE 12
+	__u8	scsw_area[SCSW_AREA_SIZE];
+#define IRB_AREA_SIZE 96
+	__u8	irb_area[IRB_AREA_SIZE];
+	__u32	ret_code;
+} __packed;
+
+While starting an I/O request, orb_area should be filled with the
+guest ORB, and scsw_area should be filled with the SCSW of the Virtual
+Subchannel.
+
+irb_area stores the I/O result.
+
+ret_code stores a return code for each access of the region.
+
+vfio-ccw patches overview
+-------------------------
+
+For now, our patches are rebased on the latest mdev implementation.
+vfio-ccw follows what vfio-pci did on the s390 paltform and uses
+vfio-iommu-type1 as the vfio iommu backend. It's a good start to launch
+the code review for vfio-ccw. Note that the implementation is far from
+complete yet; but we'd like to get feedback for the general
+architecture.
+
+* CCW translation APIs
+- Description:
+  These introduce a group of APIs (start with 'cp_') to do CCW
+  translation. The CCWs passed in by a user space program are
+  organized with their guest physical memory addresses. These APIs
+  will copy the CCWs into the kernel space, and assemble a runnable
+  kernel channel program by updating the guest physical addresses with
+  their corresponding host physical addresses.
+- Patches:
+  vfio: ccw: introduce channel program interfaces
+
+* vfio_ccw device driver
+- Description:
+  The following patches utilizes the CCW translation APIs and introduce
+  vfio_ccw, which is the driver for the I/O subchannel devices you want
+  to pass through.
+  vfio_ccw implements the following vfio ioctls:
+    VFIO_DEVICE_GET_INFO
+    VFIO_DEVICE_GET_IRQ_INFO
+    VFIO_DEVICE_GET_REGION_INFO
+    VFIO_DEVICE_RESET
+    VFIO_DEVICE_SET_IRQS
+  This provides an I/O region, so that the user space program can pass a
+  channel program to the kernel, to do further CCW translation before
+  issuing them to a real device.
+  This also provides the SET_IRQ ioctl to setup an event notifier to
+  notify the user space program the I/O completion in an asynchronous
+  way.
+- Patches:
+  vfio: ccw: basic implementation for vfio_ccw driver
+  vfio: ccw: introduce ccw_io_region
+  vfio: ccw: realize VFIO_DEVICE_GET_REGION_INFO ioctl
+  vfio: ccw: realize VFIO_DEVICE_RESET ioctl
+  vfio: ccw: realize VFIO_DEVICE_G(S)ET_IRQ_INFO ioctls
+
+The user of vfio-ccw is not limited to Qemu, while Qemu is definitely a
+good example to get understand how these patches work. Here is a little
+bit more detail how an I/O request triggered by the Qemu guest will be
+handled (without error handling).
+
+Explanation:
+Q1-Q7: Qemu side process.
+K1-K5: Kernel side process.
+
+Q1. Get I/O region info during initialization.
+Q2. Setup event notifier and handler to handle I/O completion.
+
+... ...
+
+Q3. Intercept a ssch instruction.
+Q4. Write the guest channel program and ORB to the I/O region.
+    K1. Copy from guest to kernel.
+    K2. Translate the guest channel program to a host kernel space
+        channel program, which becomes runnable for a real device.
+    K3. With the necessary information contained in the orb passed in
+        by Qemu, issue the ccwchain to the device.
+    K4. Return the ssch CC code.
+Q5. Return the CC code to the guest.
+
+... ...
+
+    K5. Interrupt handler gets the I/O result and write the result to
+        the I/O region.
+    K6. Signal Qemu to retrieve the result.
+Q6. Get the signal and event handler reads out the result from the I/O
+    region.
+Q7. Update the irb for the guest.
+
+Limitations
+-----------
+
+The current vfio-ccw implementation focuses on supporting basic commands
+needed to implement block device functionality (read/write) of DASD/ECKD
+device only. Some commands may need special handling in the future, for
+example, anything related to path grouping.
+
+DASD is a kind of storage device. While ECKD is a data recording format.
+More information for DASD and ECKD could be found here:
+https://en.wikipedia.org/wiki/Direct-access_storage_device
+https://en.wikipedia.org/wiki/Count_key_data
+
+Together with the corresponding work in Qemu, we can bring the passed
+through DASD/ECKD device online in a guest now and use it as a block
+device.
+
+Reference
+---------
+1. ESA/s390 Principles of Operation manual (IBM Form. No. SA22-7832)
+2. ESA/390 Common I/O Device Commands manual (IBM Form. No. SA22-7204)
+3. https://en.wikipedia.org/wiki/Channel_I/O
+4. Documentation/s390/cds.txt
+5. Documentation/vfio.txt
+6. Documentation/vfio-mediated-device.txt
diff --git a/Documentation/scheduler/sched-pelt.c b/Documentation/scheduler/sched-pelt.c
new file mode 100644
index 000000000000..e4219139386a
--- /dev/null
+++ b/Documentation/scheduler/sched-pelt.c
@@ -0,0 +1,108 @@
+/*
+ * The following program is used to generate the constants for
+ * computing sched averages.
+ *
+ * ==============================================================
+ *		C program (compile with -lm)
+ * ==============================================================
+ */
+
+#include <math.h>
+#include <stdio.h>
+
+#define HALFLIFE 32
+#define SHIFT 32
+
+double y;
+
+void calc_runnable_avg_yN_inv(void)
+{
+	int i;
+	unsigned int x;
+
+	printf("static const u32 runnable_avg_yN_inv[] = {");
+	for (i = 0; i < HALFLIFE; i++) {
+		x = ((1UL<<32)-1)*pow(y, i);
+
+		if (i % 6 == 0) printf("\n\t");
+		printf("0x%8x, ", x);
+	}
+	printf("\n};\n\n");
+}
+
+int sum = 1024;
+
+void calc_runnable_avg_yN_sum(void)
+{
+	int i;
+
+	printf("static const u32 runnable_avg_yN_sum[] = {\n\t    0,");
+	for (i = 1; i <= HALFLIFE; i++) {
+		if (i == 1)
+			sum *= y;
+		else
+			sum = sum*y + 1024*y;
+
+		if (i % 11 == 0)
+			printf("\n\t");
+
+		printf("%5d,", sum);
+	}
+	printf("\n};\n\n");
+}
+
+int n = -1;
+/* first period */
+long max = 1024;
+
+void calc_converged_max(void)
+{
+	long last = 0, y_inv = ((1UL<<32)-1)*y;
+
+	for (; ; n++) {
+		if (n > -1)
+			max = ((max*y_inv)>>SHIFT) + 1024;
+			/*
+			 * This is the same as:
+			 * max = max*y + 1024;
+			 */
+
+		if (last == max)
+			break;
+
+		last = max;
+	}
+	n--;
+	printf("#define LOAD_AVG_PERIOD %d\n", HALFLIFE);
+	printf("#define LOAD_AVG_MAX %ld\n", max);
+//	printf("#define LOAD_AVG_MAX_N %d\n\n", n);
+}
+
+void calc_accumulated_sum_32(void)
+{
+	int i, x = sum;
+
+	printf("static const u32 __accumulated_sum_N32[] = {\n\t     0,");
+	for (i = 1; i <= n/HALFLIFE+1; i++) {
+		if (i > 1)
+			x = x/2 + sum;
+
+		if (i % 6 == 0)
+			printf("\n\t");
+
+		printf("%6d,", x);
+	}
+	printf("\n};\n\n");
+}
+
+void main(void)
+{
+	printf("/* Generated by Documentation/scheduler/sched-pelt; do not modify. */\n\n");
+
+	y = pow(0.5, 1/(double)HALFLIFE);
+
+	calc_runnable_avg_yN_inv();
+//	calc_runnable_avg_yN_sum();
+	calc_converged_max();
+//	calc_accumulated_sum_32();
+}
diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py
index df0419c62096..cf13ff3a656c 100644
--- a/Documentation/sphinx/cdomain.py
+++ b/Documentation/sphinx/cdomain.py
@@ -44,7 +44,7 @@ from sphinx.domains.c import CDomain as Base_CDomain
 __version__  = '1.0'
 
 # Get Sphinx version
-major, minor, patch = map(int, sphinx.__version__.split("."))
+major, minor, patch = sphinx.version_info[:3]
 
 def setup(app):
 
diff --git a/Documentation/sphinx/kfigure.py b/Documentation/sphinx/kfigure.py
new file mode 100644
index 000000000000..cef4ad19624c
--- /dev/null
+++ b/Documentation/sphinx/kfigure.py
@@ -0,0 +1,551 @@
+# -*- coding: utf-8; mode: python -*-
+# pylint: disable=C0103, R0903, R0912, R0915
+u"""
+    scalable figure and image handling
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Sphinx extension which implements scalable image handling.
+
+    :copyright:  Copyright (C) 2016  Markus Heiser
+    :license:    GPL Version 2, June 1991 see Linux/COPYING for details.
+
+    The build for image formats depend on image's source format and output's
+    destination format. This extension implement methods to simplify image
+    handling from the author's POV. Directives like ``kernel-figure`` implement
+    methods *to* always get the best output-format even if some tools are not
+    installed. For more details take a look at ``convert_image(...)`` which is
+    the core of all conversions.
+
+    * ``.. kernel-image``: for image handling / a ``.. image::`` replacement
+
+    * ``.. kernel-figure``: for figure handling / a ``.. figure::`` replacement
+
+    * ``.. kernel-render``: for render markup / a concept to embed *render*
+      markups (or languages). Supported markups (see ``RENDER_MARKUP_EXT``)
+
+      - ``DOT``: render embedded Graphviz's **DOC**
+      - ``SVG``: render embedded Scalable Vector Graphics (**SVG**)
+      - ... *developable*
+
+    Used tools:
+
+    * ``dot(1)``: Graphviz (http://www.graphviz.org). If Graphviz is not
+      available, the DOT language is inserted as literal-block.
+
+    * SVG to PDF: To generate PDF, you need at least one of this tools:
+
+      - ``convert(1)``: ImageMagick (https://www.imagemagick.org)
+
+    List of customizations:
+
+    * generate PDF from SVG / used by PDF (LaTeX) builder
+
+    * generate SVG (html-builder) and PDF (latex-builder) from DOT files.
+      DOT: see http://www.graphviz.org/content/dot-language
+
+    """
+
+import os
+from os import path
+import subprocess
+from hashlib import sha1
+import sys
+
+from docutils import nodes
+from docutils.statemachine import ViewList
+from docutils.parsers.rst import directives
+from docutils.parsers.rst.directives import images
+import sphinx
+
+from sphinx.util.nodes import clean_astext
+from six import iteritems
+
+PY3 = sys.version_info[0] == 3
+
+if PY3:
+    _unicode = str
+else:
+    _unicode = unicode
+
+# Get Sphinx version
+major, minor, patch = sphinx.version_info[:3]
+if major == 1 and minor > 3:
+    # patches.Figure only landed in Sphinx 1.4
+    from sphinx.directives.patches import Figure  # pylint: disable=C0413
+else:
+    Figure = images.Figure
+
+__version__  = '1.0.0'
+
+# simple helper
+# -------------
+
+def which(cmd):
+    """Searches the ``cmd`` in the ``PATH`` enviroment.
+
+    This *which* searches the PATH for executable ``cmd`` . First match is
+    returned, if nothing is found, ``None` is returned.
+    """
+    envpath = os.environ.get('PATH', None) or os.defpath
+    for folder in envpath.split(os.pathsep):
+        fname = folder + os.sep + cmd
+        if path.isfile(fname):
+            return fname
+
+def mkdir(folder, mode=0o775):
+    if not path.isdir(folder):
+        os.makedirs(folder, mode)
+
+def file2literal(fname):
+    with open(fname, "r") as src:
+        data = src.read()
+        node = nodes.literal_block(data, data)
+    return node
+
+def isNewer(path1, path2):
+    """Returns True if ``path1`` is newer than ``path2``
+
+    If ``path1`` exists and is newer than ``path2`` the function returns
+    ``True`` is returned otherwise ``False``
+    """
+    return (path.exists(path1)
+            and os.stat(path1).st_ctime > os.stat(path2).st_ctime)
+
+def pass_handle(self, node):           # pylint: disable=W0613
+    pass
+
+# setup conversion tools and sphinx extension
+# -------------------------------------------
+
+# Graphviz's dot(1) support
+dot_cmd = None
+
+# ImageMagick' convert(1) support
+convert_cmd = None
+
+
+def setup(app):
+    # check toolchain first
+    app.connect('builder-inited', setupTools)
+
+    # image handling
+    app.add_directive("kernel-image",  KernelImage)
+    app.add_node(kernel_image,
+                 html    = (visit_kernel_image, pass_handle),
+                 latex   = (visit_kernel_image, pass_handle),
+                 texinfo = (visit_kernel_image, pass_handle),
+                 text    = (visit_kernel_image, pass_handle),
+                 man     = (visit_kernel_image, pass_handle), )
+
+    # figure handling
+    app.add_directive("kernel-figure", KernelFigure)
+    app.add_node(kernel_figure,
+                 html    = (visit_kernel_figure, pass_handle),
+                 latex   = (visit_kernel_figure, pass_handle),
+                 texinfo = (visit_kernel_figure, pass_handle),
+                 text    = (visit_kernel_figure, pass_handle),
+                 man     = (visit_kernel_figure, pass_handle), )
+
+    # render handling
+    app.add_directive('kernel-render', KernelRender)
+    app.add_node(kernel_render,
+                 html    = (visit_kernel_render, pass_handle),
+                 latex   = (visit_kernel_render, pass_handle),
+                 texinfo = (visit_kernel_render, pass_handle),
+                 text    = (visit_kernel_render, pass_handle),
+                 man     = (visit_kernel_render, pass_handle), )
+
+    app.connect('doctree-read', add_kernel_figure_to_std_domain)
+
+    return dict(
+        version = __version__,
+        parallel_read_safe = True,
+        parallel_write_safe = True
+    )
+
+
+def setupTools(app):
+    u"""
+    Check available build tools and log some *verbose* messages.
+
+    This function is called once, when the builder is initiated.
+    """
+    global dot_cmd, convert_cmd   # pylint: disable=W0603
+    app.verbose("kfigure: check installed tools ...")
+
+    dot_cmd = which('dot')
+    convert_cmd = which('convert')
+
+    if dot_cmd:
+        app.verbose("use dot(1) from: " + dot_cmd)
+    else:
+        app.warn("dot(1) not found, for better output quality install "
+                 "graphviz from http://www.graphviz.org")
+    if convert_cmd:
+        app.verbose("use convert(1) from: " + convert_cmd)
+    else:
+        app.warn(
+            "convert(1) not found, for SVG to PDF conversion install "
+            "ImageMagick (https://www.imagemagick.org)")
+
+
+# integrate conversion tools
+# --------------------------
+
+RENDER_MARKUP_EXT = {
+    # The '.ext' must be handled by convert_image(..) function's *in_ext* input.
+    # <name> : <.ext>
+    'DOT' : '.dot',
+    'SVG' : '.svg'
+}
+
+def convert_image(img_node, translator, src_fname=None):
+    """Convert a image node for the builder.
+
+    Different builder prefer different image formats, e.g. *latex* builder
+    prefer PDF while *html* builder prefer SVG format for images.
+
+    This function handles output image formats in dependence of source the
+    format (of the image) and the translator's output format.
+    """
+    app = translator.builder.app
+
+    fname, in_ext = path.splitext(path.basename(img_node['uri']))
+    if src_fname is None:
+        src_fname = path.join(translator.builder.srcdir, img_node['uri'])
+        if not path.exists(src_fname):
+            src_fname = path.join(translator.builder.outdir, img_node['uri'])
+
+    dst_fname = None
+
+    # in kernel builds, use 'make SPHINXOPTS=-v' to see verbose messages
+
+    app.verbose('assert best format for: ' + img_node['uri'])
+
+    if in_ext == '.dot':
+
+        if not dot_cmd:
+            app.verbose("dot from graphviz not available / include DOT raw.")
+            img_node.replace_self(file2literal(src_fname))
+
+        elif translator.builder.format == 'latex':
+            dst_fname = path.join(translator.builder.outdir, fname + '.pdf')
+            img_node['uri'] = fname + '.pdf'
+            img_node['candidates'] = {'*': fname + '.pdf'}
+
+
+        elif translator.builder.format == 'html':
+            dst_fname = path.join(
+                translator.builder.outdir,
+                translator.builder.imagedir,
+                fname + '.svg')
+            img_node['uri'] = path.join(
+                translator.builder.imgpath, fname + '.svg')
+            img_node['candidates'] = {
+                '*': path.join(translator.builder.imgpath, fname + '.svg')}
+
+        else:
+            # all other builder formats will include DOT as raw
+            img_node.replace_self(file2literal(src_fname))
+
+    elif in_ext == '.svg':
+
+        if translator.builder.format == 'latex':
+            if convert_cmd is None:
+                app.verbose("no SVG to PDF conversion available / include SVG raw.")
+                img_node.replace_self(file2literal(src_fname))
+            else:
+                dst_fname = path.join(translator.builder.outdir, fname + '.pdf')
+                img_node['uri'] = fname + '.pdf'
+                img_node['candidates'] = {'*': fname + '.pdf'}
+
+    if dst_fname:
+        # the builder needs not to copy one more time, so pop it if exists.
+        translator.builder.images.pop(img_node['uri'], None)
+        _name = dst_fname[len(translator.builder.outdir) + 1:]
+
+        if isNewer(dst_fname, src_fname):
+            app.verbose("convert: {out}/%s already exists and is newer" % _name)
+
+        else:
+            ok = False
+            mkdir(path.dirname(dst_fname))
+
+            if in_ext == '.dot':
+                app.verbose('convert DOT to: {out}/' + _name)
+                ok = dot2format(app, src_fname, dst_fname)
+
+            elif in_ext == '.svg':
+                app.verbose('convert SVG to: {out}/' + _name)
+                ok = svg2pdf(app, src_fname, dst_fname)
+
+            if not ok:
+                img_node.replace_self(file2literal(src_fname))
+
+
+def dot2format(app, dot_fname, out_fname):
+    """Converts DOT file to ``out_fname`` using ``dot(1)``.
+
+    * ``dot_fname`` pathname of the input DOT file, including extension ``.dot``
+    * ``out_fname`` pathname of the output file, including format extension
+
+    The *format extension* depends on the ``dot`` command (see ``man dot``
+    option ``-Txxx``). Normally you will use one of the following extensions:
+
+    - ``.ps`` for PostScript,
+    - ``.svg`` or ``svgz`` for Structured Vector Graphics,
+    - ``.fig`` for XFIG graphics and
+    - ``.png`` or ``gif`` for common bitmap graphics.
+
+    """
+    out_format = path.splitext(out_fname)[1][1:]
+    cmd = [dot_cmd, '-T%s' % out_format, dot_fname]
+    exit_code = 42
+
+    with open(out_fname, "w") as out:
+        exit_code = subprocess.call(cmd, stdout = out)
+        if exit_code != 0:
+            app.warn("Error #%d when calling: %s" % (exit_code, " ".join(cmd)))
+    return bool(exit_code == 0)
+
+def svg2pdf(app, svg_fname, pdf_fname):
+    """Converts SVG to PDF with ``convert(1)`` command.
+
+    Uses ``convert(1)`` from ImageMagick (https://www.imagemagick.org) for
+    conversion.  Returns ``True`` on success and ``False`` if an error occurred.
+
+    * ``svg_fname`` pathname of the input SVG file with extension (``.svg``)
+    * ``pdf_name``  pathname of the output PDF file with extension (``.pdf``)
+
+    """
+    cmd = [convert_cmd, svg_fname, pdf_fname]
+    # use stdout and stderr from parent
+    exit_code = subprocess.call(cmd)
+    if exit_code != 0:
+        app.warn("Error #%d when calling: %s" % (exit_code, " ".join(cmd)))
+    return bool(exit_code == 0)
+
+
+# image handling
+# ---------------------
+
+def visit_kernel_image(self, node):    # pylint: disable=W0613
+    """Visitor of the ``kernel_image`` Node.
+
+    Handles the ``image`` child-node with the ``convert_image(...)``.
+    """
+    img_node = node[0]
+    convert_image(img_node, self)
+
+class kernel_image(nodes.image):
+    """Node for ``kernel-image`` directive."""
+    pass
+
+class KernelImage(images.Image):
+    u"""KernelImage directive
+
+    Earns everything from ``.. image::`` directive, except *remote URI* and
+    *glob* pattern. The KernelImage wraps a image node into a
+    kernel_image node. See ``visit_kernel_image``.
+    """
+
+    def run(self):
+        uri = self.arguments[0]
+        if uri.endswith('.*') or uri.find('://') != -1:
+            raise self.severe(
+                'Error in "%s: %s": glob pattern and remote images are not allowed'
+                % (self.name, uri))
+        result = images.Image.run(self)
+        if len(result) == 2 or isinstance(result[0], nodes.system_message):
+            return result
+        (image_node,) = result
+        # wrap image node into a kernel_image node / see visitors
+        node = kernel_image('', image_node)
+        return [node]
+
+# figure handling
+# ---------------------
+
+def visit_kernel_figure(self, node):   # pylint: disable=W0613
+    """Visitor of the ``kernel_figure`` Node.
+
+    Handles the ``image`` child-node with the ``convert_image(...)``.
+    """
+    img_node = node[0][0]
+    convert_image(img_node, self)
+
+class kernel_figure(nodes.figure):
+    """Node for ``kernel-figure`` directive."""
+
+class KernelFigure(Figure):
+    u"""KernelImage directive
+
+    Earns everything from ``.. figure::`` directive, except *remote URI* and
+    *glob* pattern.  The KernelFigure wraps a figure node into a kernel_figure
+    node. See ``visit_kernel_figure``.
+    """
+
+    def run(self):
+        uri = self.arguments[0]
+        if uri.endswith('.*') or uri.find('://') != -1:
+            raise self.severe(
+                'Error in "%s: %s":'
+                ' glob pattern and remote images are not allowed'
+                % (self.name, uri))
+        result = Figure.run(self)
+        if len(result) == 2 or isinstance(result[0], nodes.system_message):
+            return result
+        (figure_node,) = result
+        # wrap figure node into a kernel_figure node / see visitors
+        node = kernel_figure('', figure_node)
+        return [node]
+
+
+# render handling
+# ---------------------
+
+def visit_kernel_render(self, node):
+    """Visitor of the ``kernel_render`` Node.
+
+    If rendering tools available, save the markup of the ``literal_block`` child
+    node into a file and replace the ``literal_block`` node with a new created
+    ``image`` node, pointing to the saved markup file. Afterwards, handle the
+    image child-node with the ``convert_image(...)``.
+    """
+    app = self.builder.app
+    srclang = node.get('srclang')
+
+    app.verbose('visit kernel-render node lang: "%s"' % (srclang))
+
+    tmp_ext = RENDER_MARKUP_EXT.get(srclang, None)
+    if tmp_ext is None:
+        app.warn('kernel-render: "%s" unknow / include raw.' % (srclang))
+        return
+
+    if not dot_cmd and tmp_ext == '.dot':
+        app.verbose("dot from graphviz not available / include raw.")
+        return
+
+    literal_block = node[0]
+
+    code      = literal_block.astext()
+    hashobj   = code.encode('utf-8') #  str(node.attributes)
+    fname     = path.join('%s-%s' % (srclang, sha1(hashobj).hexdigest()))
+
+    tmp_fname = path.join(
+        self.builder.outdir, self.builder.imagedir, fname + tmp_ext)
+
+    if not path.isfile(tmp_fname):
+        mkdir(path.dirname(tmp_fname))
+        with open(tmp_fname, "w") as out:
+            out.write(code)
+
+    img_node = nodes.image(node.rawsource, **node.attributes)
+    img_node['uri'] = path.join(self.builder.imgpath, fname + tmp_ext)
+    img_node['candidates'] = {
+        '*': path.join(self.builder.imgpath, fname + tmp_ext)}
+
+    literal_block.replace_self(img_node)
+    convert_image(img_node, self, tmp_fname)
+
+
+class kernel_render(nodes.General, nodes.Inline, nodes.Element):
+    """Node for ``kernel-render`` directive."""
+    pass
+
+class KernelRender(Figure):
+    u"""KernelRender directive
+
+    Render content by external tool.  Has all the options known from the
+    *figure*  directive, plus option ``caption``.  If ``caption`` has a
+    value, a figure node with the *caption* is inserted. If not, a image node is
+    inserted.
+
+    The KernelRender directive wraps the text of the directive into a
+    literal_block node and wraps it into a kernel_render node. See
+    ``visit_kernel_render``.
+    """
+    has_content = True
+    required_arguments = 1
+    optional_arguments = 0
+    final_argument_whitespace = False
+
+    # earn options from 'figure'
+    option_spec = Figure.option_spec.copy()
+    option_spec['caption'] = directives.unchanged
+
+    def run(self):
+        return [self.build_node()]
+
+    def build_node(self):
+
+        srclang = self.arguments[0].strip()
+        if srclang not in RENDER_MARKUP_EXT.keys():
+            return [self.state_machine.reporter.warning(
+                'Unknow source language "%s", use one of: %s.' % (
+                    srclang, ",".join(RENDER_MARKUP_EXT.keys())),
+                line=self.lineno)]
+
+        code = '\n'.join(self.content)
+        if not code.strip():
+            return [self.state_machine.reporter.warning(
+                'Ignoring "%s" directive without content.' % (
+                    self.name),
+                line=self.lineno)]
+
+        node = kernel_render()
+        node['alt'] = self.options.get('alt','')
+        node['srclang'] = srclang
+        literal_node = nodes.literal_block(code, code)
+        node += literal_node
+
+        caption = self.options.get('caption')
+        if caption:
+            # parse caption's content
+            parsed = nodes.Element()
+            self.state.nested_parse(
+                ViewList([caption], source=''), self.content_offset, parsed)
+            caption_node = nodes.caption(
+                parsed[0].rawsource, '', *parsed[0].children)
+            caption_node.source = parsed[0].source
+            caption_node.line = parsed[0].line
+
+            figure_node = nodes.figure('', node)
+            for k,v in self.options.items():
+                figure_node[k] = v
+            figure_node += caption_node
+
+            node = figure_node
+
+        return node
+
+def add_kernel_figure_to_std_domain(app, doctree):
+    """Add kernel-figure anchors to 'std' domain.
+
+    The ``StandardDomain.process_doc(..)`` method does not know how to resolve
+    the caption (label) of ``kernel-figure`` directive (it only knows about
+    standard nodes, e.g. table, figure etc.). Without any additional handling
+    this will result in a 'undefined label' for kernel-figures.
+
+    This handle adds labels of kernel-figure to the 'std' domain labels.
+    """
+
+    std = app.env.domains["std"]
+    docname = app.env.docname
+    labels = std.data["labels"]
+
+    for name, explicit in iteritems(doctree.nametypes):
+        if not explicit:
+            continue
+        labelid = doctree.nameids[name]
+        if labelid is None:
+            continue
+        node = doctree.ids[labelid]
+
+        if node.tagname == 'kernel_figure':
+            for n in node.next_node():
+                if n.tagname == 'caption':
+                    sectname = clean_astext(n)
+                    # add label to std domain
+                    labels[name] = docname, labelid, sectname
+                    break
diff --git a/Documentation/sphinx/tmplcvt b/Documentation/sphinx/tmplcvt
index 909a73065e0a..6848f0a26fa5 100755
--- a/Documentation/sphinx/tmplcvt
+++ b/Documentation/sphinx/tmplcvt
@@ -7,13 +7,22 @@
 # fix \_
 # title line?
 #
+set -eu
+
+if [ "$#" != "2" ]; then
+	echo "$0 <docbook file> <rst file>"
+	exit
+fi
+
+DIR=$(dirname $0)
 
 in=$1
 rst=$2
 tmp=$rst.tmp
 
 cp $in $tmp
-sed --in-place -f convert_template.sed $tmp
+sed --in-place -f $DIR/convert_template.sed $tmp
 pandoc -s -S -f docbook -t rst -o $rst $tmp
-sed --in-place -f post_convert.sed $rst
+sed --in-place -f $DIR/post_convert.sed $rst
 rm $tmp
+echo "book writen to $rst"
diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt
index 32a25fad0c1b..ef419fd0897f 100644
--- a/Documentation/static-keys.txt
+++ b/Documentation/static-keys.txt
@@ -118,7 +118,7 @@ Or:
 
 Keys defined via DEFINE_STATIC_KEY_TRUE(), or DEFINE_STATIC_KEY_FALSE, may
 be used in either static_branch_likely() or static_branch_unlikely()
-statemnts.
+statements.
 
 Branch(es) can be set true via:
 
diff --git a/Documentation/sync_file.txt b/Documentation/sync_file.txt
index 269681a6faec..c3d033a06e8d 100644
--- a/Documentation/sync_file.txt
+++ b/Documentation/sync_file.txt
@@ -37,7 +37,7 @@ dma_fence_signal(), when it has finished using (or processing) that buffer.
 Out-fences are fences that the driver creates.
 
 On the other hand if the driver receives fence(s) through a sync_file from
-userspace we call these fence(s) 'in-fences'. Receiveing in-fences means that
+userspace we call these fence(s) 'in-fences'. Receiving in-fences means that
 we need to wait for the fence(s) to signal before using any buffer related to
 the in-fences.
 
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 2ebabc93014a..14db18c970b1 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -188,7 +188,16 @@ netdev_budget
 
 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
 poll). In one polling cycle interfaces which are registered to polling are
-probed in a round-robin manner.
+probed in a round-robin manner. Also, a polling cycle may not exceed
+netdev_budget_usecs microseconds, even if netdev_budget has not been
+exhausted.
+
+netdev_budget_usecs
+---------------------
+
+Maximum number of microseconds in one NAPI polling cycle. Polling
+will exit when either netdev_budget_usecs have elapsed during the
+poll cycle or the number of packets processed reaches netdev_budget.
 
 netdev_max_backlog
 ------------------
diff --git a/Documentation/thermal/intel_powerclamp.txt b/Documentation/thermal/intel_powerclamp.txt
index 60073dc9f748..b5df21168fbc 100644
--- a/Documentation/thermal/intel_powerclamp.txt
+++ b/Documentation/thermal/intel_powerclamp.txt
@@ -268,6 +268,15 @@ cur_state:0
 max_state:50
 type:intel_powerclamp
 
+cur_state allows user to set the desired idle percentage. Writing 0 to
+cur_state will stop idle injection. Writing a value between 1 and
+max_state will start the idle injection. Reading cur_state returns the
+actual and current idle percentage. This may not be the same value
+set by the user in that current idle percentage depends on workload
+and includes natural idle. When idle injection is disabled, reading
+cur_state returns value -1 instead of 0 which is to avoid confusing
+100% busy state with the disabled state.
+
 Example usage:
 - To inject 25% idle time
 $ sudo sh -c "echo 25 > /sys/class/thermal/cooling_device80/cur_state
@@ -278,11 +287,12 @@ then the powerclamp driver will not start idle injection. Using Top
 will not show idle injection kernel threads.
 
 If the system is busy (spin test below) and has less than 25% natural
-idle time, powerclamp kernel threads will do idle injection, which
-appear running to the scheduler. But the overall system idle is still
-reflected. In this example, 24.1% idle is shown. This helps the
-system admin or user determine the cause of slowdown, when a
-powerclamp driver is in action.
+idle time, powerclamp kernel threads will do idle injection. Forced
+idle time is accounted as normal idle in that common code path is
+taken as the idle task.
+
+In this example, 24.1% idle is shown. This helps the system admin or
+user determine the cause of slowdown, when a powerclamp driver is in action.
 
 
 Tasks: 197 total,   1 running, 196 sleeping,   0 stopped,   0 zombie
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index e4991fb1eedc..5ea85059db3b 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -8,11 +8,12 @@ Overview
 --------
 These events are similar to tracepoint based events. Instead of Tracepoint,
 this is based on kprobes (kprobe and kretprobe). So it can probe wherever
-kprobes can probe (this means, all functions body except for __kprobes
-functions). Unlike the Tracepoint based event, this can be added and removed
+kprobes can probe (this means, all functions except those with
+__kprobes/nokprobe_inline annotation and those marked NOKPROBE_SYMBOL).
+Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
index fa7b680ee8a0..bf526a7c5559 100644
--- a/Documentation/trace/uprobetracer.txt
+++ b/Documentation/trace/uprobetracer.txt
@@ -7,7 +7,7 @@
 Overview
 --------
 Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/Documentation/translations/ja_JP/HOWTO b/Documentation/translations/ja_JP/howto.rst
index 4ebd20750ef1..4511eed0fabb 100644
--- a/Documentation/translations/ja_JP/HOWTO
+++ b/Documentation/translations/ja_JP/howto.rst
@@ -1,95 +1,81 @@
 NOTE:
 This is a version of Documentation/HOWTO translated into Japanese.
 This document is maintained by Tsugikazu Shibata <tshibata@ab.jp.nec.com>
-and the JF Project team <www.linux.or.jp/JF>.
-If you find any difference between this document and the original file
-or a problem with the translation,
-please contact the maintainer of this file or JF project.
-
-Please also note that the purpose of this file is to be easier to read
-for non English (read: Japanese) speakers and is not intended as a
-fork. So if you have any comments or updates for this file, please try
-to update the original English file first.
-
-Last Updated: 2013/07/19
-==================================
-�れ��
-linux-3.10/Documentation/HOWTO
+If you find any difference between this document and the original file or
+a problem with the translation, please contact the maintainer of this file.
+
+Please also note that the purpose of this file is to be easier to
+read for non English (read: Japanese) speakers and is not intended as
+a fork. So if you have any comments or updates for this file, please
+try to update the original English file first.
+
+----------------------------------
+
+��文書��
+Documentation/process/howto.rst
 �和訳��。
 
-翻訳団体： JF プロジェクト < http://linuxjf.sourceforge.jp/ >
-翻訳日： 2013/7/19
-翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
-校正者： �倉�ん <nbh--mats at nifty dot com>
-         �林 雅典�ん (Masanori Kobayasi) <zap03216 at nifty dot ne dot jp>
-         武井伸光�ん�<takei at webmasters dot gr dot jp>
-         ����ん (Seiji Kaneko) <skaneko at a2 dot mbn dot or dot jp>
-         野��ん (Kenji Noguchi) <tokyo246 at gmail dot com>
-         河内�ん (Takayoshi Kochi) <t-kochi at bq dot jp dot nec dot com>
-         岩本�ん (iwamoto) <iwamoto.kn at ncos dot nec dot co dot jp>
-         内田�ん (Satoshi Uchida) <s-uchida at ap dot jp dot nec dot com>
-==================================
+翻訳者： Tsugikazu Shibata <tshibata@ab.jp.nec.com>
+
+----------------------------------
 
 Linux カー�ル開発�やり方
--------------------------------
+==========================
 
 �れ�上�トピック( Linux カー�ル開発�やり方)����事柄を網羅��
-ドキュメント��。���� Linux カー�ル開発者��る���方法�
-Linux カー�ル開発コミュニティ�共�活動�るやり方を学�方法���れ�
-���。カー�ルプログラミング�関�る技術的�項目�関�る���何も�
-���よ���������カー�ル開発者��る���正��方�����
-手助���り��。
+ドキュメント��。���� Linux カー�ル開発者��る���方法�Linux
+カー�ル開発コミュニティ�共�活動�るやり方を学�方法���れ����。
+カー�ルプログラミング�関�る技術的�項目�関�る���何も����よ
+���������カー�ル開発者��る���正��方�����手助��
+�り��。
 
-も����ドキュメント������������場������ドキュメン
-ト�最後�リスト��メンテナ�パッ�を�������。
+も����ドキュメント������������場������ドキュメント
+�最後�リスト��メンテナ�パッ�を�������。
 
 ����
 ---------
 
-����　Linux カー�ル�開発者��る方法を学������ょ��？　�
-れ�も����上��ら「��デ�イス� Linux ドライ�を書�よ����
-言�れ��る���ょ��？　
-��文書�目的�������む��手順��コミュニティ�一緒�����
-�ヒントを書�下���������知る��全����を教�る����。
-�����コミュニティ���今��������る������由�一部も
-説明�よ��試�����。
-
-
-カー�ル� 少��アーキテク�ャ�存部分�アセンブリ言語�書�れ��る
-以外�大部分� C 言語�書�れ����。C言語をよ��解���る���カー
-�ル開発者��必���。アーキテク�ャ���低レベル部分�開発を�る�
-���れ��(�ん�アーキテク�ャ�も)アセンブリ(訳注: 言語)�必��り
-��ん。以下�本��C 言語��分�知識や何年も�経験����代�るも�
-���り��ん��少���もリファレンス����良�本��。
+���� Linux カー�ル�開発者��る方法を学������ょ��？　�
+れ�も上��ら「��デ�イス� Linux ドライ�を書�よ����言�れ�
+��も�れ��ん。��文書�目的�������む��手順��コミュニティ
+�一緒������ヒントを書�下���������知る��全����を
+教�る����。�����コミュニティ���今��������る���
+���由も説明�よ��試�����。
+
+カー�ル�少��アーキテク�ャ�存部分�アセンブリ言語�書�れ��る以
+外�大部分� C 言語�書�れ����。C言語をよ��解���る���カー
+�ル開発�必���。低レベル�アーキテク�ャ開発を�る����れ��
+(�ん�アーキテク�ャ�も)アセンブリ(訳注: 言語)�必��り��ん。以下
+�本��C 言語��分�知識や何年も�経験����代�るも����り��
+ん��少���もリファレンス����良�本��。
+
  - "The C Programming Language" by Kernighan and Ritchie [Prentice Hall]
- -『プログラミング言語Ｃ第2版�(B.W. カーニ�ン/D.M. リッ�ー著 石田晴久訳) [共立出版]
+ - 『プログラミング言語Ｃ第2版�(B.W. カーニ�ン/D.M. リッ�ー著 石田晴久訳) [共立出版]
  - "Practical C Programming" by Steve Oualline [O'Reilly]
  - 『C実践プログラミング第3版�(Steve Oualline著 望月康�監訳 谷�功訳) [オライリージャパン]
  - "C:  A Reference Manual" by Harbison and Steele [Prentice Hall]
- - 『新・詳説 C 言語 H&S リファレンス�
-       (サミュエル P �ービソン/ガイ L スティール共著 斉藤 信男監訳)[ソフト�ンク]
+ - 『新・詳説 C 言語 H&S リファレンス� (サミュエル P �ービソン/ガイ L スティール共著 斉藤 信男監訳)[ソフト�ンク]
 
 カー�ル� GNU C � GNU ツール�ェインを使��書�れ����。カー�ル
 � ISO C89 仕様�準拠��書�一方��標準��無�言語拡張を多�使��
-���。カー�ル�標準 C ライブラリ��関係��������C 言語フリー
-スタンディング環境��。�����C �標準�使���も�も�り��。任
-�� long long �除算や浮動�数点�使���ん。
-�����カー�ル�ツール�ェインや C 言語拡張�置���る�����
-����る����り�������り����残念����決定的�リファ
-レンス�存在���ん。情報を得る���gcc � info ページ( info gcc )を
-見�����。
+���。カー�ル�標準 C ライブラリ��存����C 言語��存環境��。
+�����C �標準�中�使���も�も�り��。特�任�� long long
+�除算や浮動�数点�使���ん。カー�ル�ツール�ェインや C 言語拡張
+�置���る���������る����り������時々�り����
+残念����決定的�リファレンス�存在���ん。情報を得る���gcc �
+info ページ( info gcc )を見�����。
 
 ����既存�開発コミュニティ�一緒�作業�る方法を学������る�
-��留�������。��コミュニティ��コーディング�スタイル�
-開発手順����高度�標準を���多様�人�集�り��。
-地�的�分散��大�模��ーム�対��も��も������������
-をベース����ら��れら�標準�長�時間を���築�れ�����。
-�れら���ん�文書化�れ�����ら�事���れら�標準������
-る�����ん学ん�����。��皆����や����会社�やり方���
-���れる����������。
+����出������。��コミュニティ��コーディング�スタイル�開
+発手順����高度�標準を���多様�人�集�り��。地�的�分散��
+大�模��ーム�対��も��も������������をベース����
+ら��れら�標準�長�時間を���築�れ�����。�れら���ん�文
+書化�れ�����ら�事���れら�標準����事����る�����
+ん学ん�����。��皆����や����会社�やり方������れる
+����������。
 
 法的�題
-------------
+--------
 
 Linux カー�ル�ソースコード� GPL ライセンス�下�リリース�れ���
 �。ライセンス�詳細������ソースツリー�メインディレクトリ�存在
@@ -98,8 +84,9 @@ Linux カー�ル�ソースコード� GPL ライセンス�下�リリー
 法律家�相談������。メーリングリスト�人��法律家�����法的
 �題�����彼ら�声明�����る�����り��ん。
 
-GPL �関�る共通�質�や回答������以下を�照������。
-	http://www.gnu.org/licenses/gpl-faq.html
+GPL �関�る共通�質�や回答������以下を�照������-
+
+	https://www.gnu.org/licenses/gpl-faq.html
 
 ドキュメント
 ------------
@@ -119,111 +106,129 @@ linux-api@vger.kernel.org ��る��を勧���。
   README
     ��ファイル� Linuxカー�ル�簡��背景�カー�ルを設定(訳注
     configure )��生�(訳注 build )�る���必�����何��書�れ
-    ����。カー�ル�関������人����らスタート�る�良��
-    �ょ�。
+    ����。 カー�ル�関������人����らスタート�る�良�
+    ��ょ�。
 
-  Documentation/Changes
-     ��ファイル�カー�ルを���生�(訳注 build )��走ら�る��最
-     ���レベル�必��数々�ソフトウェアパッケージ�一覧を示���
-     ��。
+  :ref:`Documentation/Process/changes.rst <changes>`
+    ��ファイル�カー�ルを���生�(訳注 build )��走ら�る��最
+    ���レベル�必��数々�ソフトウェアパッケージ�一覧を示���
+    ��。
 
-  Documentation/process/coding-style.rst
+  :ref:`Documentation/process/coding-style.rst <codingstyle>`
     �れ� Linux カー�ル�コーディングスタイル�背景��る�由を記述
     �����。全��新��コード���ドキュメント��るガイドライン
     �従���る��を期待�れ����。大部分�メンテナ��れら�ルー
     ル�従���るも���を��付��多��人�正��スタイル�コード
     ��をレビュー���。
 
-  Documentation/process/submitting-patches.rst
-  Documentation/process/submitting-drivers.rst
-     �れら�ファイル�����や�����パッ�を作��投稿�る��
-     ����常�詳��書�れ��り�以下を����(�れ����ら��
-     �れ�も)
-        - Email ��む��
-        - Email �形�
-        - �れ��る�
-     �れら�ルール�従���������を�証�る�����り��ん
-     � (����パッ��内容�スタイル����精査を��る��)�
-     ルール�従���れ�間�������������ょ�。
-
-     ��他�パッ�を作る方法�����よ����記述�-
-
-	"The Perfect Patch"
+  :ref:`Documentation/process/submitting-patches.rst <codingstyle>` � :ref:`Documentation/process/submitting-drivers.rst <submittingdrivers>`
+    �れら�ファイル�����や�����パッ�を作��投稿�る���
+    ���常�詳��書�れ��り�以下を���� (�れ����ら��
+    �れ�も)
+
+      - Email ��む��
+      - Email �形�
+      - �れ��る�
+
+    �れら�ルール�従���������を�証�る�����り��ん
+    � (����パッ��内容�スタイル����精査を��る��)�
+    ルール�従���れ�間�������������ょ�。
+
+    ��他�パッ�を作る方法�����よ����記述�-
+
+       "The Perfect Patch"
 		http://www.ozlabs.org/~akpm/stuff/tpp.txt
-	"Linux kernel patch submission format"
+       "Linux kernel patch submission format"
 		http://linux.yyz.us/patch-format.html
 
-  Documentation/process/stable-api-nonsense.rst
-     ��ファイル�カー�ル�中��変�APIを����������識的�
-     決断�背景��る�由����書�れ����。以下�よ����を�
-     ん����-
-       - サブシステム��間�層を作る��(コンパ�ビリティ���?)
-       - オペレーティングシステム間�ドライ��移�性
-       - カー�ルソースツリー�素早�変更を�ら�る(も���素早�変更
-         を妨�る)
-     ��ドキュメント� Linux 開発��想を�解�る���常�����。
-     ����他�OS��開発者� Linux �移る時���も����。
-
-  Documentation/admin-guide/security-bugs.rst
+  :ref:`Documentation/process/stable-api-nonsense.rst <stable_api_nonsense>`
+    ��ファイル�カー�ル�中��変� API を����������識的
+    �決断�背景��る�由����書�れ����。以下�よ����を�
+    ん����-
+
+      - サブシステム��間�層を作る��(コンパ�ビリティ���?)
+      - オペレーティングシステム間�ドライ��移�性
+      - カー�ルソースツリー�素早�変更を�ら�る(も���素早�変更を妨�る)
+
+    ��ドキュメント� Linux 開発��想を�解�る���常�����。
+    ����他�OS��開発者� Linux �移る時���も����。
+
+  :ref:`Documentation/admin-guide/security-bugs.rst <securitybugs>`
     も� Linux カー�ル�セキュリティ�題を発見��よ�����ら��
     �ドキュメント�ステップ�従��カー�ル開発者�連絡���題解決を
     支�������。
 
-  Documentation/process/management-style.rst
+  :ref:`Documentation/process/management-style.rst <managementstyle>`
     ��ドキュメント� Linux カー�ル�メンテナ����行動�る��
     彼ら�手法�背景��る共有�れ��る精神����記述�����。�
     れ�カー�ル開発��心者�ら（も������興味��る���人�も）
     ����。���ら��ドキュメント��カー�ルメンテナ��独特�
     行動�����多��誤解や混乱を解消�る�ら��。
 
-  Documentation/process/stable-kernel-rules.rst
+  :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
     ��ファイル���よ�� stable カー�ル�リリース�行�れる��ルー
     ル�記述�れ����。����れら�リリース�中�����変更を�
     り入れ�もら���場��何を�れ�良���示�れ����。
 
-  Documentation/process/kernel-docs.rst
-　　カー�ル開発�付��る外部ドキュメント�リスト��。も�����
-    探���るも��カー�ル内�ドキュメント����ら����場��
-    ��リストを����������。
+  :Ref:`Documentation/process/kernel-docs.rst <kernel_docs>`
+    カー�ル開発�付��る外部ドキュメント�リスト��。も�����探
+    ���るも��カー�ル内�ドキュメント����ら����場����
+    リストを����������。
 
-  Documentation/process/applying-patches.rst
+  :ref:`Documentation/process/applying-patches.rst <applying_patches>`
     パッ�������パッ�を��や��様々�カー�ル�開発ブラン��
     �用�る������正確�記述��良�入門書��。
 
-カー�ル�ソースコード�ら自動的�生��能�多数�ドキュメントを自分自
-身�も�����。�れ��カー�ル内 API �����記述や���正��
-ロックを��る���則���れ��。��ドキュメント�
-Documentation/DocBook/ ディレクトリ�作られ�以下�よ��
-	make pdfdocs
-	make psdocs
-	make htmldocs
-	make mandocs
-コマンドを実行�る�メインカー�ル�ソースディレクトリ�ら
-�れ�れ�PDF, Postscript, HTML, man page �形��生��れ��。
+カー�ル�ソースコード��も�や���ファイル�よ��リストラク�ャー
+ドテキストマークアップ(ReST)�ら自動的�生��能�多数�ドキュメントを
+も�����。�れ��カー�ル内API�完全�記述や�正��ロックを��
+る����則�����れ��。
+
+�れら全��ドキュメントを PDF や HTML �生��る��以下を実行��� - ::
+
+        make pdfdocs
+        make htmldocs
+
+�れ�れメインカー�ル�ソースディレクトリ�ら実行���。
+
+ReSTマークアップを使��ドキュメント� Documentation/output�生��れ
+��。Latex �ePub 形��生��る�� - ::
+
+        make latexdocs
+        make epubdocs
+
+�在�幾��� DocBook形��書�れ�ドキュメント� ReST形��転�中�
+�。�れら�ドキュメント�Documentation/DocBook ディレクトリ�生��れ�
+Postscript ��� man ページ�形�を生��る��以下�よ����� - ::
+
+        make psdocs
+        make mandocs
 
 カー�ル開発者��る��
----------------------------
+------------------------
 
-も������Linux カー�ル開発����何も知ら���ら��
+も������Linux カー�ル開発����何も知ら����ら��
 KernelNewbies プロジェクトを見る����
-	http://kernelnewbies.org
+
+	https://kernelnewbies.org
 
 ��サイト��役�立�メーリングリスト��り�基本的�カー�ル開発�関
 �る��ん��ん�種類�質�も���� (既�回答�れ��るよ����を
-�������アーカイブを調������)。
-�������リアルタイム�質�を�������る IRC �ャ�ルや�Linux
-カー�ル�開発�関��学���便利����ん�役�立�ドキュメント��
-り��。
+�������アーカイブを調������)。�������リアルタイム
+�質�を�������る IRC �ャ�ルや�Linuxカー�ル�開発�関��学
+���便利����ん�役�立�ドキュメント��り��。
 
-web サイト���コード�構��サブシステム��在存在�るプロジェクト(ツ
-リー��るも�無�も��両方)�基本的�管�情報��り��。
-��������カー�ル�コンパイル�やり方やパッ��当�方���間接
-的�基本情報も記述�れ����。
+Web サイト���コード�構��サブシステム��在存在�るプロジェクト
+(ツリー��るも�無�も��両方)�基本的�管�情報��り��。�����
+���カー�ル�コンパイル�やり方やパッ��当�方���間接的�基本情
+報も記述�れ����。
 
 �������らスタート��良����ら����Linux カー�ル開発コミュ
-ニティ��加��何��る��を�����る場����Linux kernel
+ニティ��加��何��る��を�����る���れ��Linux kernel
 Janitor's プロジェクト����良���ょ� -
-	http://kernelnewbies.org/KernelJanitors
+
+        https://kernelnewbies.org/KernelJanitors
+
 �����よ��スタートを�る��������場所��。�����
 Linux カー�ルソースツリー�中���れる��れ����修正���れ��
 ら����純��題�リスト�記述�れ����。��プロジェクト�関�る
@@ -232,10 +237,11 @@ Linux カーãƒ�ルソースツリーã�®ä¸­ã�«å�«ã�¾ã‚Œã‚‹ã€�ã��ã‚Œã�„ã�«ã�—ã€�ä¿
 ����場����次�やる仕事�方�性�見���る�も�れ��ん。
 
 も��������������りコードを書�����カー�ルツリー�入
-れ��������り��れ�関�る�切�支�を求���場��カー�ル
-メンターズプロジェクト���よ��皆�んを助�る��������。
-����メーリングリスト��り�以下�ら�照����
-	http://selenic.com/mailman/listinfo/kernel-mentors
+れ��������り��れ�関�る�切�支�を求���場��カー�ルメ
+ンターズプロジェクト���よ��皆�んを助�る��������。���
+�メーリングリスト��り�以下�ら�照���� -
+
+	https://selenic.com/mailman/listinfo/kernel-mentors
 
 実際� Linux カー�ル�コード����修正を加�る�����や����
 コード�動作�る��を�解�る���必���。�������特別�ツー
@@ -244,27 +250,29 @@ Linux カーãƒ�ルソースツリーã�®ä¸­ã�«å�«ã�¾ã‚Œã‚‹ã€�ã��ã‚Œã�„ã�«ã�—ã€�ä¿
 特���������Linux クロスリファレンスプロジェクト��。�れ��
 自己�照方���索引���� web 形���ソースコードを�照�る���
 ����。��最新�素晴��カー�ルコード�リ�ジトリ�以下�見��り
-��-
+�� -
+
 	http://lxr.free-electrons.com/
 
 開発プロセス
------------------------
+------------
 
 Linux カー�ル�開発プロセス��在幾���異�るメインカー�ル「ブラン
-���多数�サブシステム毎�カー�ルブラン��ら構��れ��。
-�れら�ブラン���-
-  - メイン� 3.x カー�ルツリー
-  - 3.x.y -stable カー�ルツリー
-  - 3.x -git カー�ルパッ�
+���多数�サブシステム毎�カー�ルブラン��ら構��れ��。�れら�
+ブラン��� -
+
+  - メイン� 4.x カー�ルツリー
+  - 4.x.y -stable カー�ルツリー
+  - 4.x -git カー�ルパッ�
   - サブシステム毎�カー�ルツリー�パッ�
-  - 統�テスト���� 3.x -next カー�ルツリー
+  - 統�テスト���� 4.x -next カー�ルツリー
 
-3.x カー�ルツリー
------------------
+4.x カー�ルツリー
+~~~~~~~~~~~~~~~~~~
 
-3.x カー�ル� Linus Torvalds �よ��メンテナンス�れ�kernel.org
-� pub/linux/kernel/v3.x/ ディレクトリ�存在���。��開発プロセス�
-以下���り-
+4.x カー�ル� Linus Torvalds �よ��メンテナンス�れ�
+https://kernel.org � pub/linux/kernel/v4.x/ ディレクトリ�存在���。
+��開発プロセス�以下���り -
 
   - 新��カー�ル�リリース�れ�直後��2週間�特別期間�設�られ�
     ��期間中��メンテナ�� Linus �大��差分を�る�������。
@@ -272,7 +280,6 @@ Linux カーãƒ�ルã�®é–‹ç™ºãƒ—ロセスã�¯ç�¾åœ¨å¹¾ã�¤ã�‹ã�®ç•°ã�ªã‚‹ãƒ¡ã‚¤ãƒ³ã‚
     大��変更� git(カー�ル�ソース管�ツール�詳細�
     http://git-scm.com/ �照) を使���る��好���やり方����パッ
     �ファイル�形�����る��も�分��。
-
   - 2週間後�-rc1 カー�ル�リリース�れ���後��カー�ル全体�安定
     性�影響を���るよ��新機能�����類�パッ����り込む��
     �����ん。新��ドライ�(も���ファイルシステム)�パッ��
@@ -282,44 +289,45 @@ Linux カーãƒ�ルã�®é–‹ç™ºãƒ—ロセスã�¯ç�¾åœ¨å¹¾ã�¤ã�‹ã�®ç•°ã�ªã‚‹ãƒ¡ã‚¤ãƒ³ã‚
     Linus �パッ�を�付�る�� git を使���も������パッ��
     レビュー�����パブリック�メーリングリスト�も�時��る必��
     �り��。
-
   - 新�� -rc � Linus ��最新� git ツリー�テスト目的��れ��分
     �安定��状態��る�判断�����リリース�れ��。目標�毎週新
     �� -rc カー�ルをリリース�る����。
-
   - ��プロセス�カー�ル� 「準備������考�られる��継続��
     �。��プロセス����� 6週間継続���。
 
 Andrew Morton � Linux-kernel メーリングリスト�カー�ルリリース���
-�書����を���言�������価値��り��-
-  「カー�ル���リリース�れる��誰も知り��ん。���ら��れ��
-  実��識�れ��グ�状��よりリリース�れる���り��も��決�ら
-  れ�計画�よ��リリース�れるも������ら��。�
+�書����を���言�������価値��り�� -
+
+        *「カー�ル���リリース�れる��誰も知り��ん。���ら�
+        �れ��実��識�れ��グ�状��よりリリース�れる���り�
+        �も��決�られ�計画�よ��リリース�れるも������ら
+        ��。�*
 
-3.x.y -stable カー�ルツリー
----------------------------
+4.x.y -stable カー�ルツリー
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 �ージョン番��3��数字�分�れ��るカー�ル� -stable カー�ル��。
-�れ���3.x カー�ル�見����セキュリティ�題や�大�後戻り�対
-�る比較的������修正���れ��。
+�れ���4.x カー�ル�見����セキュリティ�題や�大�後戻り�対�
+る比較的������修正���れ��。
 
-�れ��開発/実験的�ージョン�テスト��力�る���興味�無��
-最新�安定��カー�ルを使���ユーザ�推奨�るブラン���。
+�れ��開発/実験的�ージョン�テスト��力�る���興味�無��最新
+�安定��カー�ルを使���ユーザ�推奨�るブラン���。
 
-も��3.x.y カー�ル�存在���場����番��一番大�� 3.x �
-最新�安定版カー�ル��。
+も��4.x.y カー�ル�存在���場����番��一番大�� 4.x �最新
+�安定版カー�ル��。
 
-3.x.y � "stable" �ーム <stable@vger.kernel.org> �メンテ�れ��り�必
-��応��リリース�れ��。通常�リリース期間� 2週間毎����差�迫�
-��題���れ�も�少�長��る��も�り��。セキュリティ関連��題
-�場���れ�対�������場�����リリース��れ��。
+4.x.y � "stable" �ーム <stable@vger.kernel.org> �メンテ�れ��り�
+必��応��リリース�れ��。通常�リリース期間� 2週間毎����差
+�迫���題���れ�も�少�長��る��も�り��。セキュリティ関
+連��題�場���れ�対�������場�����リリース��れ��。
 
-カー�ルツリー�入���る�Documentation/process/stable-kernel-rules.rst ファ
-イル����よ��種類�変更� -stable ツリー���入れ�能����リ
-リースプロセス���動���記述�れ����。
+カー�ルツリー�入���る�
+Documentation/process/stable-kernel-rules.rst ファイル����よ��種
+類�変更� -stable ツリー���入れ�能����リリースプロセス���
+動���記述�れ����。
 
-3.x -git パッ�
-------------------
+4.x -git パッ�
+~~~~~~~~~~~~~~~
 
 git リ�ジトリ�管��れ��るLinus �カー�ルツリー�毎日�スナップ
 ショット��り��。(��ら -git ������������)。�れら�パッ
@@ -328,7 +336,7 @@ git リãƒ�ジトリã�§ç®¡ç�†ã�•ã‚Œã�¦ã�„ã‚‹Linus ã�®ã‚«ãƒ¼ãƒ�ルツリーã�®æ¯Žæ
 �生��れる���より実験的��。
 
 サブシステム毎�カー�ルツリー�パッ�
--------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 �れ�れ�カー�ルサブシステム�メンテナ�� --- ���多��カー�ル
 サブシステム�開発者�も --- �自�最新�開発状�をソースリ�ジトリ�
@@ -340,42 +348,45 @@ git リãƒ�ジトリã�§ç®¡ç�†ã�•ã‚Œã�¦ã�„ã‚‹Linus ã�®ã‚«ãƒ¼ãƒ�ルツリーã�®æ¯Žæ
 大部分��れら�リ�ジトリ� git ツリー��。�����他� SCM や
 quilt シリーズ���公開�れ��るパッ�キューも使�れ����。�れら
 �サブシステムリ�ジトリ�アドレス� MAINTAINERS ファイル�リスト�れ
-����。�れら�多�� http://git.kernel.org/ ��照�る������
+����。�れら�多�� https://git.kernel.org/ ��照�る������
 �。
 
 �案�れ�パッ����よ��サブシステムツリー�コミット�れる���メー
 リングリスト�事��レビュー���られ��（以下�対応�るセクションを
-�照）。�����カー�ルサブシステム�����レビュー� patchwork
-���ツール�よ��追跡�れ��。Patchwork � web インターフェイス�
-よ��パッ�投稿�表示�パッ���コメント付�や改訂���������
-メンテナ�パッ��対���レビュー中��付済��拒����よ��マーク
-を��る�������。大部分��れら� patchwork �サイト�
-http://patchwork.kernel.org/ �リスト�れ����。
-
-統�テスト���� 3.x -next カー�ルツリー
----------------------------------------------
-
-サブシステムツリー�更新内容�メインライン� 3.x ツリー�マージ�れ
-る����れら�統�テスト�れる必���り��。��目的����実質的
-�全サブシステムツリー�ら��毎日プル�れ���る特別�テスト用�リ
-�ジトリ�存在���-
-       http://git.kernel.org/?p=linux/kernel/git/next/linux-next.git
+�照）。�����カー�ルサブシステム�����レビュー� patchwork�
+��ツール�よ��追跡�れ��。Patchwork � web インターフェイス�よ�
+�パッ�投稿�表示�パッ���コメント付�や改訂���������メン
+テナ�パッ��対���レビュー中��付済��拒����よ��マークを�
+�る�������。大部分��れら� patchwork �サイト�
+https://patchwork.kernel.org/ �リスト�れ����。
+
+統�テスト���� 4.x -next カー�ルツリー
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+サブシステムツリー�更新内容�メインライン� 4.x ツリー�マージ�れる
+����れら�統�テスト�れる必���り��。��目的����実質的�
+全サブシステムツリー�ら��毎日プル�れ���る特別�テスト用�リ�ジ
+トリ�存在���-
+
+       https://git.kernel.org/?p=linux/kernel/git/next/linux-next.git
 
 ��やり方�よ���-next カー�ル�次�マージ機会��ん�も��メイン
-ラインカー�ル�マージ�れる��������展望を�供���。-next 
-カー�ル�実行テストを行�冒険好��テスター�大��歓迎�れ��
+ラインカー�ル�マージ�れる��������展望を�供���。-next カー
+�ル�実行テストを行�冒険好��テスター�大��歓迎�れ��。
 
 �グレ�ート
 -------------
 
-bugzilla.kernel.org � Linux カー�ル開発者�カー�ル��グを追跡�る
-場所��。ユーザ�見����グ�全�を��ツール�報告�����。
-�� kernel bugzilla を使���詳細��以下を�照������-
-	http://bugzilla.kernel.org/page.cgi?id=faq.html
-メインカー�ルソースディレクトリ��るファイル admin-guide/reporting-bugs.rst �カー�
-ル�グら��も�������レ�ート�る��良�テンプレート��り��
-題�追跡を助�る���カー�ル開発者�����ん�情報�必�����詳
-細�書�れ����。
+https://bugzilla.kernel.org � Linux カー�ル開発者�カー�ル��グを追跡�る
+場所��。ユーザ�見����グ�全�を��ツール�報告�����。��
+kernel bugzilla を使���詳細��以下を�照������ -
+
+	https://bugzilla.kernel.org/page.cgi?id=faq.html
+
+メインカー�ルソースディレクトリ��るファイル
+admin-guide/reporting-bugs.rst�カー�ル�グら��も�������レ�ー
+ト�る��良�テンプレート��り��題�追跡を助�る���カー�ル開発
+者�����ん�情報�必�����詳細�書�れ����。
 
 �グレ�ート�管�
 -------------------
@@ -383,74 +394,78 @@ bugzilla.kernel.org ã�¯ Linux カーãƒ�ル開発者ã�Œã‚«ãƒ¼ãƒ�ルã�®ãƒ�ã‚°ã‚’è¿
 �����ッキング�スキルを訓練�る最高�方法������他人�レ�ー
 ト���グを修正�る����り��。����カー�ルをより安定化��る
 ��寄与�る��������������� �実��題を修正�る��を
-学��自分�スキルも強化�����他�開発者�����存在�気���
-��。�グを修正�る����多��開発者�中�ら自分�功績を��る最善
-��������ら多��人�他人��グ�修正�時間を浪費�る��を好�
-���ら��。
+学��自分�スキルも強化�����他�開発者�����存在�気����
+�。�グを修正�る����多��開発者�中�ら自分�功績を��る最善�
+�������ら多��人�他人��グ�修正�時間を浪費�る��を好��
+��ら��。
 
 ���レ�ート�れ��グ����仕事を�る�����
-http://bugzilla.kernel.org �行������。も�今後��グレ�ート�
+https://bugzilla.kernel.org �行������。も�今後��グレ�ート�
 ���アド�イスを�������れ��bugme-new メーリングリスト(新�
 ��グレ�ート������メール�れる) ��� bugme-janitor メーリン
 グリスト(bugzilla �変更毎����メール�れる)を購読����。
 
-	http://lists.linux-foundation.org/mailman/listinfo/bugme-new
-	http://lists.linux-foundation.org/mailman/listinfo/bugme-janitors
+	https://lists.linux-foundation.org/mailman/listinfo/bugme-new
+
+	https://lists.linux-foundation.org/mailman/listinfo/bugme-janitors
 
 メーリングリスト
--------------
+----------------
 
 上������ドキュメント�述�������コアカー�ル開発者�大部分
 � Linux kernel メーリングリスト��加�����。��リスト�登録/脱
 退�方法�����以下を�照������-
+
 	http://vger.kernel.org/vger-lists.html#linux-kernel
 
 ��メーリングリスト�アーカイブ� web 上�多数�場所�存在���。�
 れら�アーカイブを探���サー�エンジンを使���ょ�。例��-
+
 	http://dir.gmane.org/gmane.linux.kernel
 
 リスト�投稿�る�������話題�アーカイブ�存在�る����を検索
-�る��を是�や������。多数�事����詳細�渡��議論�れ�
-�り�アーカイブ���記録�れ����。
+�る��を是�や������。多数�事����詳細�渡��議論�れ��
+り�アーカイブ���記録�れ����。
 
 大部分�カー�ルサブシステムも自分�個別�開発を実施�るメーリングリス
 トを������。個々�グループ��ん�リストを����る���
 MAINTAINERS ファイル�リスト��り�����照������。
 
 多��リスト� kernel.org �ホスト�れ����。�れら�情報�以下��
-り��-
+り�� -
+
 	http://vger.kernel.org/vger-lists.html
 
-メーリングリストを使�場��良�行動習慣�従�よ�����ょ�。
-少�安�����以下� URL �上�リスト(や他�リスト)�会話�る場��
-シンプル�ガイドラインを示�����-
+メーリングリストを使�場��良�行動習慣�従�よ�����ょ�。少�安�
+����以下� URL �上�リスト(や他�リスト)�会話�る場��シンプル
+�ガイドラインを示����� -
+
 	http://www.albion.com/netiquette/
 
 も�複数�人�����メール�返事を��場��CC: ���る人�リスト�
-���多��る��ょ�。良��由���場��CC: リスト�ら誰�を削除を
-���よ������メーリングリスト�アドレス���リプライ�る���
-��よ�����ょ�。1���信者�ら�も�1��リスト�ら�よ���メー
-ルを2回��る������も�れ�慣れ��ゃれ�メールヘッダーを追加�
-���状態を変�よ�����よ��。人々���よ�����好���ん。
+���多��る��ょ�。正当��由����り�CC: リスト�ら誰�を削除
+を���よ������メーリングリスト�アドレス���リプライ�る��
+���よ�����ょ�。1���信者�ら�も�1��リスト�ら�よ���
+メールを2回��る������も�れ�慣れ��ゃれ�メールヘッダーを追
+加����状態を変�よ�����よ��。人々���よ�����好���
+ん。
 
 今���メール��やり�り���間�����発言�����残��
 "John Kernelhacker wrote ...:" �行を����リプライ�先頭行����
 メール�先頭�����引用行�間�����言�����を追加�る���
 �。
 
-も�パッ�をメール�付�る場���Documentation/process/submitting-patches.rst ��
-示�れ��るよ����れ� プレーン��読テキスト��る��を忘れ��
-よ�����ょ�。カー�ル開発者� 添付や圧縮��パッ�を扱���り�
-�ん-
-彼ら�����パッ��行毎�コメントを入れ��������������
-る���り��ん。����メールプログラム�空白やタブを圧縮���よ�
-�確���方�良���。最��良�テスト�����自分�メールを���
-�����パッ�を自分�当���る����。も��れ����行����
-ら�����メールプログラムを直��もら���正��動�よ��変�る�
-���。
+も�パッ�をメール�付�る場���
+Documentation/process/submitting-patches.rst ��示�れ��るよ����
+れ� プレーン��読テキスト��る��を忘れ��よ�����ょ�。カー
+�ル開発者� 添付や圧縮��パッ�を扱���り��ん。彼ら�����パッ
+��行毎�コメントを入れ��������る���り��ん。����メー
+ルプログラム�空白やタブを圧縮���よ��確����ょ�。最��良�テ
+スト�����自分�メールを��������パッ�を自分�当���る�
+���。も��れ����行����ら�����メールプログラムを直��
+もら���正��動�よ��変�る����。
 
-�り���他�登録者�対�る尊敬を表�よ���る��を覚�������
-��。
+何を���も�他�購読者�対�る敬�を表���を忘れ�������。
 
 コミュニティ�共�����
 --------------------------
@@ -459,21 +474,22 @@ MAINTAINERS ファイルã�«ãƒªã‚¹ãƒˆã�Œã�‚ã‚Šã�¾ã�™ã�®ã�§å�‚ç…§ã�—ã�¦ã��ã� ã�•ã�
 ��。����パッ�を��入れ�もら����投稿��場���れ��技術
 的メリット���レビュー�れ��。��際�����何を予想�����ょ
 ��?
+
   - 批判
   - コメント
   - 変更��求
   - パッ��正当性�証明�求
   - 沈黙
 
-��出��������������パッ�をカー�ル�入れる話��。�
-��������パッ��対�る批判�コメントを��入れる�����れら
-を技術的レベル�評価���パッ�を�作��る�����れら�変更を��
-�����を明確�簡潔��由�説明を�供������。
-も������パッ��何も�応���場������メール�山�埋もれ�
-見逃�れ�����投稿�忘れられ������も�る���数日待���度
-投稿������。
+��出��������れ�����パッ�をカー�ル�入れる話��。��
+�������パッ��対�る批判�コメントを��入れる�����れらを
+技術的レベル�評価���パッ�を�作��る�����れら�変更を���
+����を明確�簡潔��由�説明を�供������。も������パッ
+��何も�応���場������メール�山�埋もれ�見逃�れ�����
+投稿�忘れられ������も�る���数日待���度投稿������。
+
+����やる��������?
 
-����やる�����も��?
   - 質��������パッ����入れられる�想��る��
   - 守り�入る��
   - コメントを無視�る��
@@ -489,37 +505,37 @@ MAINTAINERS ファイルã�«ãƒªã‚¹ãƒˆã�Œã�‚ã‚Šã�¾ã�™ã�®ã�§å�‚ç…§ã�—ã�¦ã��ã� ã�•ã�
 
 ����最��パッ���� 1ダースも�修正を求�るリスト�返答��る�
 �も普通�����。�れ�����パッ����入れられ��������
-� *�り��ん*�������自身��対�る��を�味�る��も *�り�
-�ん*。��自分�パッ��対��指摘�れ��題を全�修正�����れ�
-良����。
+� **�り��ん**�������自身��対�る��を�味�る��も **�
+り��ん**。��自分�パッ��対��指摘�れ��題を全�修正�����
+れ�良����。
 
 
 カー�ルコミュニティ��業組織����
 -----------------------------------------------------------------
 
 カー�ルコミュニティ�大部分��統的�会社�開発環境��異��やり方�
-動�����。以下��題を��る�����る�良����リスト��-
+動�����。以下��題を��る�����る�良����リスト��。
 
-  �����案�る変更����言�������言�方：
+  �����案�る変更����言�������言�方 -
 
     - "�れ�複数��題を解決���"
     - "�れ�2000行�コードを削除���"
     - "以下�パッ�����言������る��を説明�るも���"
     - "���れを5��異�るアーキテク�ャ�テスト������..."
     - "以下�一連����パッ�群���..."
-    - "�れ�典型的�マシン��性能を�上����.."
+    - "�れ�典型的�マシン��性能を�上����..."
 
-  や��方�良�悪�言�方：
+  や��方�良�悪�言�方 -
 
-    - ��やり方� AIX/ptx/Solaris ����������る���
-    - ���れを20年も�間や�������ら
-    - �れ����会社�金儲�を�る���必��
-    - �れ�我々�エンタープライズ��商�ライン�����る
-    - �れ� ��自分�アイディアを記述���1000ページ�設計資料��る
-    - ���れ�����6ケ月作業���る。
-    - 以下� ... �関�る5000行�パッ���
-    - ���在���ゃ��ゃを全部書�直����れ�以下��...
-    - ��〆切��る�������パッ��今���用�れる必���る
+    - "��やり方� AIX/ptx/Solaris ����������る���..."
+    - "���れを20年も�間や�������ら..."
+    - "�れ���会社�金儲�を�る���必��"
+    - "�れ�我々�エンタープライズ��商�ライン�����る"
+    - "�れ���自分�アイディアを記述���1000ページ�設計資料��る"
+    - "���れ�����6ケ月作業���る..."
+    - "以下� ... �関�る5000行�パッ���"
+    - "���在���ゃ��ゃを全部書�直����れ�以下��..."
+    - "��〆切��る�������パッ��今���用�れる必���る"
 
 カー�ルコミュニティ�大部分��統的�ソフトウェアエンジニアリング�労
 �環境�異�るも�一��点��やり�り�顔を������������。
@@ -535,13 +551,13 @@ Patricia (主�女性�)や Patrick (主�男性�)�略称)。
 Linux カー�ル�活動を����見を表明������る大部分�女性���
 ���経験をも�����。
 
-言葉���英語�得����一部�人���題��り��。
-メーリングリスト�中���ん�アイディアを交��る���相当���英語
-を�れる必���る��も�り��。���������自分�メール
-を�る��英語��味�通���る�を�ェック�る��を�薦����。
+言葉���英語�得����一部�人���題��り��。メーリングリスト
+�中����ん�アイディアを交��る���相当���英語を�れる必��
+�る��も�り��。�����自分�メールを�る��英語��味�通��
+�る�を�ェック�る��を�薦����。
 
 変更を分割�る
----------------------
+--------------
 
 Linux カー�ルコミュニティ��一度�大��コード�塊を喜ん��容�る�
 ���り��ん。変更�正確�説明�れる必���り�議論�れ�����個
@@ -555,7 +571,7 @@ Linux カーãƒ�ルコミュニティã�¯ã€�一度ã�«å¤§é‡�ã�®ã‚³ãƒ¼ãƒ‰ã�®å¡Šã‚’å–
 や�������ん�����パッ�群���も�ん�時�も�れより���
 ���れ��り��ん。
 
-パッ�を分割�る�由�以下��-
+パッ�を分割�る�由�以下 -
 
 1) ���パッ������パッ���用�れる見込�を大������カー
    �ル�人��パッ��正������を確��る時間や労力を�����
@@ -571,41 +587,41 @@ Linux カーãƒ�ルコミュニティã�¯ã€�一度ã�«å¤§é‡�ã�®ã‚³ãƒ¼ãƒ‰ã�®å¡Šã‚’å–
 2) ���パッ�を�る�������る����書�直���シンプル��
    る(も������順番を変�る���も)��も���も����。
 
-以下�カー�ル開発者� Al Viro ����話��：
+以下�カー�ル開発者� Al Viro ����話�� -
 
-        "生徒�数学�宿題を採点�る先生���を考���������先
-        生�生徒�解�到��る���試行錯誤を見����������ょ
-        �。先生�簡潔�最高�解を見�����。良�生徒��れを知��
-        �り����最終解���中間作業を�出�る���決������
-        �"
+        *"生徒�数学�宿題を採点�る先生���を考���������
+        先生�生徒�解�到��る���試行錯誤を見����������
+        ょ�。先生�簡潔�最高�解を見�����。良�生徒��れを知�
+        ��り����最終解���中間作業を�出�る���決�����
+        ��*
 
-        カー�ル開発�も�れ�����。メンテナ��レビューア���
+        *カー�ル開発�も�れ�����。メンテナ��レビューア���
         �題を解決�る解�背後��る�考プロセスを見��������ん。
-        彼ら��純���や��解決方法を見�����。
+        彼ら��純���や��解決方法を見�����。"*
 
 ��や��解を説明�る���コミュニティ�共�仕事を��未解決�仕事を
-議論�る����ランスをキープ�る��難���も�れ��ん。
-���ら�開発プロセス�早期段階�改善����フィード�ックをもら�よ
-���る�も良�����変更点を���部分�分割��全体����完��
-����仕事を(部分的�)�り込ん�もら�るよ���る��も良�����。
+議論�る����ランスをキープ�る��難���も�れ��ん。���ら�
+開発プロセス�早期段階�改善����フィード�ックをもら�よ���る�
+も良�����変更点を���部分�分割��全体����完������仕
+事を(部分的�)�り込ん�もら�るよ���る��も良�����。
 
 �����上������も�や�"将�直�" よ��パッ�を�本����
 �もら�よ�����も��れ���付�られ����を�解������。
 
 ����変更を正当化�る
--------------------
+------------------------
 
 ����パッ�を分割�る���時������変更を追加���れ��ら�
 ��を Linux コミュニティ�知ら�る�����も����。新機能�必�
 性�有用性�正当化�れ��れ��り��ん。
 
-����変更�説明
---------------------
+����変更を説明�る
+----------------------
 
 ����パッ�を�付�る場����メール�中�テキスト�何を言����
 ���特別�注�を払������。��情報�パッ�� ChangeLog �使�
 れ���も皆��られるよ���管�れ��。�れ�次�よ��項目を���
-パッ�を完全�記述�る����-
+パッ�を完全�記述�る���� -
 
   - ��変更�必��
   - パッ�全体�設計アプロー�
@@ -613,18 +629,24 @@ Linux カーãƒ�ルコミュニティã�¯ã€�一度ã�«å¤§é‡�ã�®ã‚³ãƒ¼ãƒ‰ã�®å¡Šã‚’å–
   - テスト�果
 
 �れ����全����よ���る��������詳細��以下�ドキュメ
-ント� ChangeLog セクションを見�����-
+ント� ChangeLog セクションを見����� -
+
   "The Perfect Patch"
       http://www.ozlabs.org/~akpm/stuff/tpp.txt
 
-�れら��れも��時����も困難��。�れら�慣例を完璧�実施�る�
-�数年��る�も�れ��ん。�れ�継続的�改善�プロセス��り����
-���多数����決�を必���るも���。�も�諦������れ��
-能�����。多数�人������������彼らも皆最�������
-�����らスタート������ら。
+�れら��れも�実行�る���時����も困難��。�れら�例を完璧�
+実施�る��数年��る�も�れ��ん。�れ�継続的�改善�プロセス��
+り�多�����決�を必���るも���。�も諦�����実���能�
+�。多数�人������������彼らも最������������ら
+スタート������ら。
+
+
+
+
+----------
 
 Paolo Ciarrocchi �感��彼�彼�書�� "Development Process"
-(http://lwn.net/Articles/94386/) セクションを��テキスト�原型��る
+(https://lwn.net/Articles/94386/) セクションを��テキスト�原型��る
 ��を許����れ���。Rundy Dunlap � Gerrit Huizenga �メーリング
 リスト�やる�����や����������リストを�供���れ���。
 以下�人々�レビュー�コメント�貢献�感�。
@@ -634,4 +656,6 @@ Kleen, Vadim Lobanov, Jesper Juhl, Adrian Bunk, Keri Harris, Frans Pop,
 David A. Wheeler, Junio Hamano, Michael Kerrisk, � Alex Shepard
 彼ら�支��������ドキュメント���������ょ�。
 
+
+
 Maintainer: Greg Kroah-Hartman <greg@kroah.com>
diff --git a/Documentation/translations/ja_JP/index.rst b/Documentation/translations/ja_JP/index.rst
new file mode 100644
index 000000000000..2f91b895e3c2
--- /dev/null
+++ b/Documentation/translations/ja_JP/index.rst
@@ -0,0 +1,12 @@
+.. raw:: latex
+
+        \renewcommand\thesection*
+        \renewcommand\thesubsection*
+
+Japanese translations
+=====================
+
+.. toctree::
+   :maxdepth: 1
+
+   howto
diff --git a/Documentation/translations/zh_CN/sparse.txt b/Documentation/translations/zh_CN/sparse.txt
index e41dc940e162..2f728962a8e2 100644
--- a/Documentation/translations/zh_CN/sparse.txt
+++ b/Documentation/translations/zh_CN/sparse.txt
@@ -1,4 +1,4 @@
-Chinese translated version of Documentation/sparse.txt
+Chinese translated version of Documentation/dev-tools/sparse.rst
 
 If you have any comment or update to the content, please contact the
 original document maintainer directly.  However, if you have a problem
@@ -8,7 +8,7 @@ or if there is a problem with the translation.
 
 Chinese maintainer: Li Yang <leo@zh-kernel.org>
 ---------------------------------------------------------------------
-Documentation/sparse.txt 的中文翻译
+Documentation/dev-tools/sparse.rst 的中文翻译
 
 如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
 交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
diff --git a/Documentation/usb/acm.txt b/Documentation/usb/acm.txt
index 17f5c2e1a570..903abca10517 100644
--- a/Documentation/usb/acm.txt
+++ b/Documentation/usb/acm.txt
@@ -64,7 +64,7 @@ minicom, ppp and mgetty with them.
 
 2. Verifying that it works
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
-  The first step would be to check /proc/bus/usb/devices, it should look
+  The first step would be to check /sys/kernel/debug/usb/devices, it should look
 like this:
 
 T:  Bus=01 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12  MxCh= 2
diff --git a/Documentation/usb/error-codes.txt b/Documentation/usb/error-codes.txt
deleted file mode 100644
index 9c3eb845ebe5..000000000000
--- a/Documentation/usb/error-codes.txt
+++ /dev/null
@@ -1,175 +0,0 @@
-Revised: 2004-Oct-21
-
-This is the documentation of (hopefully) all possible error codes (and
-their interpretation) that can be returned from usbcore.
-
-Some of them are returned by the Host Controller Drivers (HCDs), which
-device drivers only see through usbcore.  As a rule, all the HCDs should
-behave the same except for transfer speed dependent behaviors and the
-way certain faults are reported.
-
-
-**************************************************************************
-*                   Error codes returned by usb_submit_urb               *
-**************************************************************************
-
-Non-USB-specific:
-
-0		URB submission went fine
-
--ENOMEM		no memory for allocation of internal structures	
-
-USB-specific:
-
--EBUSY		The URB is already active.
-
--ENODEV		specified USB-device or bus doesn't exist
-
--ENOENT		specified interface or endpoint does not exist or
-		is not enabled
-
--ENXIO		host controller driver does not support queuing of this type
-		of urb.  (treat as a host controller bug.)
-
--EINVAL		a) Invalid transfer type specified (or not supported)
-		b) Invalid or unsupported periodic transfer interval
-		c) ISO: attempted to change transfer interval
-		d) ISO: number_of_packets is < 0
-		e) various other cases
-
--EXDEV		ISO: URB_ISO_ASAP wasn't specified and all the frames
-		the URB would be scheduled in have already expired.
-
--EFBIG		Host controller driver can't schedule that many ISO frames.
-
--EPIPE		The pipe type specified in the URB doesn't match the
-		endpoint's actual type.
-
--EMSGSIZE	(a) endpoint maxpacket size is zero; it is not usable
-		    in the current interface altsetting.
-		(b) ISO packet is larger than the endpoint maxpacket.
-		(c) requested data transfer length is invalid: negative
-		    or too large for the host controller.
-
--ENOSPC		This request would overcommit the usb bandwidth reserved
-		for periodic transfers (interrupt, isochronous).
-
--ESHUTDOWN	The device or host controller has been disabled due to some
-		problem that could not be worked around.
-
--EPERM		Submission failed because urb->reject was set.
-
--EHOSTUNREACH	URB was rejected because the device is suspended.
-
--ENOEXEC	A control URB doesn't contain a Setup packet.
-
-
-**************************************************************************
-*                   Error codes returned by in urb->status               *
-*                   or in iso_frame_desc[n].status (for ISO)             *
-**************************************************************************
-
-USB device drivers may only test urb status values in completion handlers.
-This is because otherwise there would be a race between HCDs updating
-these values on one CPU, and device drivers testing them on another CPU.
-
-A transfer's actual_length may be positive even when an error has been
-reported.  That's because transfers often involve several packets, so that
-one or more packets could finish before an error stops further endpoint I/O.
-
-For isochronous URBs, the urb status value is non-zero only if the URB is
-unlinked, the device is removed, the host controller is disabled, or the total
-transferred length is less than the requested length and the URB_SHORT_NOT_OK
-flag is set.  Completion handlers for isochronous URBs should only see
-urb->status set to zero, -ENOENT, -ECONNRESET, -ESHUTDOWN, or -EREMOTEIO.
-Individual frame descriptor status fields may report more status codes.
-
-
-0			Transfer completed successfully
-
--ENOENT			URB was synchronously unlinked by usb_unlink_urb
-
--EINPROGRESS		URB still pending, no results yet
-			(That is, if drivers see this it's a bug.)
-
--EPROTO (*, **)		a) bitstuff error
-			b) no response packet received within the
-			   prescribed bus turn-around time
-			c) unknown USB error 
-
--EILSEQ (*, **)		a) CRC mismatch
-			b) no response packet received within the
-			   prescribed bus turn-around time
-			c) unknown USB error 
-
-			Note that often the controller hardware does not
-			distinguish among cases a), b), and c), so a
-			driver cannot tell whether there was a protocol
-			error, a failure to respond (often caused by
-			device disconnect), or some other fault.
-
--ETIME (**)		No response packet received within the prescribed
-			bus turn-around time.  This error may instead be
-			reported as -EPROTO or -EILSEQ.
-
--ETIMEDOUT		Synchronous USB message functions use this code
-			to indicate timeout expired before the transfer
-			completed, and no other error was reported by HC.
-
--EPIPE (**)		Endpoint stalled.  For non-control endpoints,
-			reset this status with usb_clear_halt().
-
--ECOMM			During an IN transfer, the host controller
-			received data from an endpoint faster than it
-			could be written to system memory
-
--ENOSR			During an OUT transfer, the host controller
-			could not retrieve data from system memory fast
-			enough to keep up with the USB data rate
-
--EOVERFLOW (*)		The amount of data returned by the endpoint was
-			greater than either the max packet size of the
-			endpoint or the remaining buffer size.  "Babble".
-
--EREMOTEIO		The data read from the endpoint did not fill the
-			specified buffer, and URB_SHORT_NOT_OK was set in
-			urb->transfer_flags.
-
--ENODEV			Device was removed.  Often preceded by a burst of
-			other errors, since the hub driver doesn't detect
-			device removal events immediately.
-
--EXDEV			ISO transfer only partially completed
-			(only set in iso_frame_desc[n].status, not urb->status)
-
--EINVAL			ISO madness, if this happens: Log off and go home
-
--ECONNRESET		URB was asynchronously unlinked by usb_unlink_urb
-
--ESHUTDOWN		The device or host controller has been disabled due
-			to some problem that could not be worked around,
-			such as a physical disconnect.
-
-
-(*) Error codes like -EPROTO, -EILSEQ and -EOVERFLOW normally indicate
-hardware problems such as bad devices (including firmware) or cables.
-
-(**) This is also one of several codes that different kinds of host
-controller use to indicate a transfer has failed because of device
-disconnect.  In the interval before the hub driver starts disconnect
-processing, devices may receive such fault reports for every request.
-
-
-
-**************************************************************************
-*              Error codes returned by usbcore-functions                 *
-*           (expect also other submit and transfer status codes)         *
-**************************************************************************
-
-usb_register():
--EINVAL			error during registering new driver
-
-usb_get_*/usb_set_*():
-usb_control_msg():
-usb_bulk_msg():
--ETIMEDOUT		Timeout expired before the transfer completed.
diff --git a/Documentation/usb/gadget_serial.txt b/Documentation/usb/gadget_serial.txt
index 6b4a88a8c8e3..d1def3186782 100644
--- a/Documentation/usb/gadget_serial.txt
+++ b/Documentation/usb/gadget_serial.txt
@@ -189,7 +189,7 @@ Once the gadget serial driver is loaded and the USB device connected
 to the Linux host with a USB cable, the host system should recognize
 the gadget serial device.  For example, the command
 
-  cat /proc/bus/usb/devices
+  cat /sys/kernel/debug/usb/devices
 
 should show something like this:
 
@@ -221,7 +221,7 @@ Once the gadget serial driver is loaded and the USB device connected
 to the Linux host with a USB cable, the host system should recognize
 the gadget serial device.  For example, the command
 
-  cat /proc/bus/usb/devices
+  cat /sys/kernel/debug/usb/devices
 
 should show something like this:
 
diff --git a/Documentation/usb/proc_usb_info.txt b/Documentation/usb/proc_usb_info.txt
deleted file mode 100644
index 98be91982677..000000000000
--- a/Documentation/usb/proc_usb_info.txt
+++ /dev/null
@@ -1,390 +0,0 @@
-/proc/bus/usb filesystem output
-===============================
-(version 2010.09.13)
-
-
-The usbfs filesystem for USB devices is traditionally mounted at
-/proc/bus/usb.  It provides the /proc/bus/usb/devices file, as well as
-the /proc/bus/usb/BBB/DDD files.
-
-In many modern systems the usbfs filesystem isn't used at all.  Instead
-USB device nodes are created under /dev/usb/ or someplace similar.  The
-"devices" file is available in debugfs, typically as
-/sys/kernel/debug/usb/devices.
-
-
-**NOTE**: If /proc/bus/usb appears empty, and a host controller
-	  driver has been linked, then you need to mount the
-	  filesystem.  Issue the command (as root):
-
-      mount -t usbfs none /proc/bus/usb
-
-	  An alternative and more permanent method would be to add
-
-      none  /proc/bus/usb  usbfs  defaults  0  0
-
-	  to /etc/fstab.  This will mount usbfs at each reboot.
-	  You can then issue `cat /proc/bus/usb/devices` to extract
-	  USB device information, and user mode drivers can use usbfs
-	  to interact with USB devices.
-
-	  There are a number of mount options supported by usbfs.
-	  Consult the source code (linux/drivers/usb/core/inode.c) for
-	  information about those options.
-
-**NOTE**: The filesystem has been renamed from "usbdevfs" to
-	  "usbfs", to reduce confusion with "devfs".  You may
-	  still see references to the older "usbdevfs" name.
-
-For more information on mounting the usbfs file system, see the
-"USB Device Filesystem" section of the USB Guide. The latest copy
-of the USB Guide can be found at http://www.linux-usb.org/
-
-
-THE /proc/bus/usb/BBB/DDD FILES:
---------------------------------
-Each connected USB device has one file.  The BBB indicates the bus
-number.  The DDD indicates the device address on that bus.  Both
-of these numbers are assigned sequentially, and can be reused, so
-you can't rely on them for stable access to devices.  For example,
-it's relatively common for devices to re-enumerate while they are
-still connected (perhaps someone jostled their power supply, hub,
-or USB cable), so a device might be 002/027 when you first connect
-it and 002/048 sometime later.
-
-These files can be read as binary data.  The binary data consists
-of first the device descriptor, then the descriptors for each
-configuration of the device.  Multi-byte fields in the device descriptor
-are converted to host endianness by the kernel.  The configuration
-descriptors are in bus endian format! The configuration descriptor
-are wTotalLength bytes apart. If a device returns less configuration
-descriptor data than indicated by wTotalLength there will be a hole in
-the file for the missing bytes.  This information is also shown
-in text form by the /proc/bus/usb/devices file, described later.
-
-These files may also be used to write user-level drivers for the USB
-devices.  You would open the /proc/bus/usb/BBB/DDD file read/write,
-read its descriptors to make sure it's the device you expect, and then
-bind to an interface (or perhaps several) using an ioctl call.  You
-would issue more ioctls to the device to communicate to it using
-control, bulk, or other kinds of USB transfers.  The IOCTLs are
-listed in the <linux/usbdevice_fs.h> file, and at this writing the
-source code (linux/drivers/usb/core/devio.c) is the primary reference
-for how to access devices through those files.
-
-Note that since by default these BBB/DDD files are writable only by
-root, only root can write such user mode drivers.  You can selectively
-grant read/write permissions to other users by using "chmod".  Also,
-usbfs mount options such as "devmode=0666" may be helpful.
-
-
-
-THE /proc/bus/usb/devices FILE:
--------------------------------
-In /proc/bus/usb/devices, each device's output has multiple
-lines of ASCII output.
-I made it ASCII instead of binary on purpose, so that someone
-can obtain some useful data from it without the use of an
-auxiliary program.  However, with an auxiliary program, the numbers
-in the first 4 columns of each "T:" line (topology info:
-Lev, Prnt, Port, Cnt) can be used to build a USB topology diagram.
-
-Each line is tagged with a one-character ID for that line:
-
-T = Topology (etc.)
-B = Bandwidth (applies only to USB host controllers, which are
-    virtualized as root hubs)
-D = Device descriptor info.
-P = Product ID info. (from Device descriptor, but they won't fit
-    together on one line)
-S = String descriptors.
-C = Configuration descriptor info. (* = active configuration)
-I = Interface descriptor info.
-E = Endpoint descriptor info.
-
-=======================================================================
-
-/proc/bus/usb/devices output format:
-
-Legend:
-  d = decimal number (may have leading spaces or 0's)
-  x = hexadecimal number (may have leading spaces or 0's)
-  s = string
-
-
-Topology info:
-
-T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=dddd MxCh=dd
-|   |      |      |       |       |      |        |        |__MaxChildren
-|   |      |      |       |       |      |        |__Device Speed in Mbps
-|   |      |      |       |       |      |__DeviceNumber
-|   |      |      |       |       |__Count of devices at this level
-|   |      |      |       |__Connector/Port on Parent for this device
-|   |      |      |__Parent DeviceNumber
-|   |      |__Level in topology for this bus
-|   |__Bus number
-|__Topology info tag
-
-    Speed may be:
-    	1.5	Mbit/s for low speed USB
-	12	Mbit/s for full speed USB
-	480	Mbit/s for high speed USB (added for USB 2.0);
-		  also used for Wireless USB, which has no fixed speed
-	5000	Mbit/s for SuperSpeed USB (added for USB 3.0)
-
-    For reasons lost in the mists of time, the Port number is always
-    too low by 1.  For example, a device plugged into port 4 will
-    show up with "Port=03".
-
-Bandwidth info:
-B:  Alloc=ddd/ddd us (xx%), #Int=ddd, #Iso=ddd
-|   |                       |         |__Number of isochronous requests
-|   |                       |__Number of interrupt requests
-|   |__Total Bandwidth allocated to this bus
-|__Bandwidth info tag
-
-    Bandwidth allocation is an approximation of how much of one frame
-    (millisecond) is in use.  It reflects only periodic transfers, which
-    are the only transfers that reserve bandwidth.  Control and bulk
-    transfers use all other bandwidth, including reserved bandwidth that
-    is not used for transfers (such as for short packets).
-
-    The percentage is how much of the "reserved" bandwidth is scheduled by
-    those transfers.  For a low or full speed bus (loosely, "USB 1.1"),
-    90% of the bus bandwidth is reserved.  For a high speed bus (loosely,
-    "USB 2.0") 80% is reserved.
-
-
-Device descriptor info & Product ID info:
-
-D:  Ver=x.xx Cls=xx(s) Sub=xx Prot=xx MxPS=dd #Cfgs=dd
-P:  Vendor=xxxx ProdID=xxxx Rev=xx.xx
-
-where
-D:  Ver=x.xx Cls=xx(sssss) Sub=xx Prot=xx MxPS=dd #Cfgs=dd
-|   |        |             |      |       |       |__NumberConfigurations
-|   |        |             |      |       |__MaxPacketSize of Default Endpoint
-|   |        |             |      |__DeviceProtocol
-|   |        |             |__DeviceSubClass
-|   |        |__DeviceClass
-|   |__Device USB version
-|__Device info tag #1
-
-where
-P:  Vendor=xxxx ProdID=xxxx Rev=xx.xx
-|   |           |           |__Product revision number
-|   |           |__Product ID code
-|   |__Vendor ID code
-|__Device info tag #2
-
-
-String descriptor info:
-
-S:  Manufacturer=ssss
-|   |__Manufacturer of this device as read from the device.
-|      For USB host controller drivers (virtual root hubs) this may
-|      be omitted, or (for newer drivers) will identify the kernel
-|      version and the driver which provides this hub emulation.
-|__String info tag
-
-S:  Product=ssss
-|   |__Product description of this device as read from the device.
-|      For older USB host controller drivers (virtual root hubs) this
-|      indicates the driver; for newer ones, it's a product (and vendor)
-|      description that often comes from the kernel's PCI ID database.
-|__String info tag
-
-S:  SerialNumber=ssss
-|   |__Serial Number of this device as read from the device.
-|      For USB host controller drivers (virtual root hubs) this is
-|      some unique ID, normally a bus ID (address or slot name) that
-|      can't be shared with any other device.
-|__String info tag
-
-
-
-Configuration descriptor info:
-
-C:* #Ifs=dd Cfg#=dd Atr=xx MPwr=dddmA
-| | |       |       |      |__MaxPower in mA
-| | |       |       |__Attributes
-| | |       |__ConfiguratioNumber
-| | |__NumberOfInterfaces
-| |__ "*" indicates the active configuration (others are " ")
-|__Config info tag
-
-    USB devices may have multiple configurations, each of which act
-    rather differently.  For example, a bus-powered configuration
-    might be much less capable than one that is self-powered.  Only
-    one device configuration can be active at a time; most devices
-    have only one configuration.
-
-    Each configuration consists of one or more interfaces.  Each
-    interface serves a distinct "function", which is typically bound
-    to a different USB device driver.  One common example is a USB
-    speaker with an audio interface for playback, and a HID interface
-    for use with software volume control.
-
-
-Interface descriptor info (can be multiple per Config):
-
-I:* If#=dd Alt=dd #EPs=dd Cls=xx(sssss) Sub=xx Prot=xx Driver=ssss
-| | |      |      |       |             |      |       |__Driver name
-| | |      |      |       |             |      |          or "(none)"
-| | |      |      |       |             |      |__InterfaceProtocol
-| | |      |      |       |             |__InterfaceSubClass
-| | |      |      |       |__InterfaceClass
-| | |      |      |__NumberOfEndpoints
-| | |      |__AlternateSettingNumber
-| | |__InterfaceNumber
-| |__ "*" indicates the active altsetting (others are " ")
-|__Interface info tag
-
-    A given interface may have one or more "alternate" settings.
-    For example, default settings may not use more than a small
-    amount of periodic bandwidth.  To use significant fractions
-    of bus bandwidth, drivers must select a non-default altsetting.
-
-    Only one setting for an interface may be active at a time, and
-    only one driver may bind to an interface at a time.  Most devices
-    have only one alternate setting per interface.
-
-
-Endpoint descriptor info (can be multiple per Interface):
-
-E:  Ad=xx(s) Atr=xx(ssss) MxPS=dddd Ivl=dddss
-|   |        |            |         |__Interval (max) between transfers
-|   |        |            |__EndpointMaxPacketSize
-|   |        |__Attributes(EndpointType)
-|   |__EndpointAddress(I=In,O=Out)
-|__Endpoint info tag
-
-    The interval is nonzero for all periodic (interrupt or isochronous)
-    endpoints.  For high speed endpoints the transfer interval may be
-    measured in microseconds rather than milliseconds.
-
-    For high speed periodic endpoints, the "MaxPacketSize" reflects
-    the per-microframe data transfer size.  For "high bandwidth"
-    endpoints, that can reflect two or three packets (for up to
-    3KBytes every 125 usec) per endpoint.
-
-    With the Linux-USB stack, periodic bandwidth reservations use the
-    transfer intervals and sizes provided by URBs, which can be less
-    than those found in endpoint descriptor.
-
-
-=======================================================================
-
-
-If a user or script is interested only in Topology info, for
-example, use something like "grep ^T: /proc/bus/usb/devices"
-for only the Topology lines.  A command like
-"grep -i ^[tdp]: /proc/bus/usb/devices" can be used to list
-only the lines that begin with the characters in square brackets,
-where the valid characters are TDPCIE.  With a slightly more able
-script, it can display any selected lines (for example, only T, D,
-and P lines) and change their output format.  (The "procusb"
-Perl script is the beginning of this idea.  It will list only
-selected lines [selected from TBDPSCIE] or "All" lines from
-/proc/bus/usb/devices.)
-
-The Topology lines can be used to generate a graphic/pictorial
-of the USB devices on a system's root hub.  (See more below
-on how to do this.)
-
-The Interface lines can be used to determine what driver is
-being used for each device, and which altsetting it activated.
-
-The Configuration lines could be used to list maximum power
-(in milliamps) that a system's USB devices are using.
-For example, "grep ^C: /proc/bus/usb/devices".
-
-
-Here's an example, from a system which has a UHCI root hub,
-an external hub connected to the root hub, and a mouse and
-a serial converter connected to the external hub.
-
-T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
-B:  Alloc= 28/900 us ( 3%), #Int=  2, #Iso=  0
-D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
-P:  Vendor=0000 ProdID=0000 Rev= 0.00
-S:  Product=USB UHCI Root Hub
-S:  SerialNumber=dce0
-C:* #Ifs= 1 Cfg#= 1 Atr=40 MxPwr=  0mA
-I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
-E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=255ms
-
-T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
-D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
-P:  Vendor=0451 ProdID=1446 Rev= 1.00
-C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA
-I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
-E:  Ad=81(I) Atr=03(Int.) MxPS=   1 Ivl=255ms
-
-T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
-D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
-P:  Vendor=04b4 ProdID=0001 Rev= 0.00
-C:* #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=100mA
-I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
-E:  Ad=81(I) Atr=03(Int.) MxPS=   3 Ivl= 10ms
-
-T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
-D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
-P:  Vendor=0565 ProdID=0001 Rev= 1.08
-S:  Manufacturer=Peracom Networks, Inc.
-S:  Product=Peracom USB to Serial Converter
-C:* #Ifs= 1 Cfg#= 1 Atr=a0 MxPwr=100mA
-I:  If#= 0 Alt= 0 #EPs= 3 Cls=00(>ifc ) Sub=00 Prot=00 Driver=serial
-E:  Ad=81(I) Atr=02(Bulk) MxPS=  64 Ivl= 16ms
-E:  Ad=01(O) Atr=02(Bulk) MxPS=  16 Ivl= 16ms
-E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=  8ms
-
-
-Selecting only the "T:" and "I:" lines from this (for example, by using
-"procusb ti"), we have:
-
-T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
-T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
-I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
-T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
-I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
-T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
-I:  If#= 0 Alt= 0 #EPs= 3 Cls=00(>ifc ) Sub=00 Prot=00 Driver=serial
-
-
-Physically this looks like (or could be converted to):
-
-                      +------------------+
-                      |  PC/root_hub (12)|   Dev# = 1
-                      +------------------+   (nn) is Mbps.
-    Level 0           |  CN.0   |  CN.1  |   [CN = connector/port #]
-                      +------------------+
-                          /
-                         /
-            +-----------------------+
-  Level 1   | Dev#2: 4-port hub (12)|
-            +-----------------------+
-            |CN.0 |CN.1 |CN.2 |CN.3 |
-            +-----------------------+
-                \           \____________________
-                 \_____                          \
-                       \                          \
-               +--------------------+      +--------------------+
-  Level 2      | Dev# 3: mouse (1.5)|      | Dev# 4: serial (12)|
-               +--------------------+      +--------------------+
-
-
-
-Or, in a more tree-like structure (ports [Connectors] without
-connections could be omitted):
-
-PC:  Dev# 1, root hub, 2 ports, 12 Mbps
-|_ CN.0:  Dev# 2, hub, 4 ports, 12 Mbps
-     |_ CN.0:  Dev #3, mouse, 1.5 Mbps
-     |_ CN.1:
-     |_ CN.2:  Dev #4, serial, 12 Mbps
-     |_ CN.3:
-|_ CN.1:
-
-
-                         ### END ###
diff --git a/Documentation/usb/usb3-debug-port.rst b/Documentation/usb/usb3-debug-port.rst
new file mode 100644
index 000000000000..feb1a36a65b7
--- /dev/null
+++ b/Documentation/usb/usb3-debug-port.rst
@@ -0,0 +1,100 @@
+===============
+USB3 debug port
+===============
+
+:Author: Lu Baolu <baolu.lu@linux.intel.com>
+:Date: March 2017
+
+GENERAL
+=======
+
+This is a HOWTO for using the USB3 debug port on x86 systems.
+
+Before using any kernel debugging functionality based on USB3
+debug port, you need to::
+
+	1) check whether any USB3 debug port is available in
+	   your system;
+	2) check which port is used for debugging purposes;
+	3) have a USB 3.0 super-speed A-to-A debugging cable.
+
+INTRODUCTION
+============
+
+The xHCI debug capability (DbC) is an optional but standalone
+functionality provided by the xHCI host controller. The xHCI
+specification describes DbC in the section 7.6.
+
+When DbC is initialized and enabled, it will present a debug
+device through the debug port (normally the first USB3
+super-speed port). The debug device is fully compliant with
+the USB framework and provides the equivalent of a very high
+performance full-duplex serial link between the debug target
+(the system under debugging) and a debug host.
+
+EARLY PRINTK
+============
+
+DbC has been designed to log early printk messages. One use for
+this feature is kernel debugging. For example, when your machine
+crashes very early before the regular console code is initialized.
+Other uses include simpler, lockless logging instead of a full-
+blown printk console driver and klogd.
+
+On the debug target system, you need to customize a debugging
+kernel with CONFIG_EARLY_PRINTK_USB_XDBC enabled. And, add below
+kernel boot parameter::
+
+	"earlyprintk=xdbc"
+
+If there are multiple xHCI controllers in your system, you can
+append a host contoller index to this kernel parameter. This
+index starts from 0.
+
+Current design doesn't support DbC runtime suspend/resume. As
+the result, you'd better disable runtime power management for
+USB subsystem by adding below kernel boot parameter::
+
+	"usbcore.autosuspend=-1"
+
+Before starting the debug target, you should connect the debug
+port to a USB port (root port or port of any external hub) on
+the debug host. The cable used to connect these two ports
+should be a USB 3.0 super-speed A-to-A debugging cable.
+
+During early boot of the debug target, DbC will be detected and
+initialized. After initialization, the debug host should be able
+to enumerate the debug device in debug target. The debug host
+will then bind the debug device with the usb_debug driver module
+and create the /dev/ttyUSB device.
+
+If the debug device enumeration goes smoothly, you should be able
+to see below kernel messages on the debug host::
+
+	# tail -f /var/log/kern.log
+	[ 1815.983374] usb 4-3: new SuperSpeed USB device number 4 using xhci_hcd
+	[ 1815.999595] usb 4-3: LPM exit latency is zeroed, disabling LPM.
+	[ 1815.999899] usb 4-3: New USB device found, idVendor=1d6b, idProduct=0004
+	[ 1815.999902] usb 4-3: New USB device strings: Mfr=1, Product=2, SerialNumber=3
+	[ 1815.999903] usb 4-3: Product: Remote GDB
+	[ 1815.999904] usb 4-3: Manufacturer: Linux
+	[ 1815.999905] usb 4-3: SerialNumber: 0001
+	[ 1816.000240] usb_debug 4-3:1.0: xhci_dbc converter detected
+	[ 1816.000360] usb 4-3: xhci_dbc converter now attached to ttyUSB0
+
+You can use any communication program, for example minicom, to
+read and view the messages. Below simple bash scripts can help
+you to check the sanity of the setup.
+
+.. code-block:: sh
+
+	===== start of bash scripts =============
+	#!/bin/bash
+
+	while true ; do
+		while [ ! -d /sys/class/tty/ttyUSB0 ] ; do
+			:
+		done
+	cat /dev/ttyUSB0
+	done
+	===== end of bash scripts ===============
diff --git a/Documentation/userspace-api/conf.py b/Documentation/userspace-api/conf.py
new file mode 100644
index 000000000000..2eaf59f844e5
--- /dev/null
+++ b/Documentation/userspace-api/conf.py
@@ -0,0 +1,10 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = "The Linux kernel user-space API guide"
+
+tags.add("subproject")
+
+latex_documents = [
+    ('index', 'userspace-api.tex', project,
+     'The kernel development community', 'manual'),
+]
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
new file mode 100644
index 000000000000..a9d01b44a659
--- /dev/null
+++ b/Documentation/userspace-api/index.rst
@@ -0,0 +1,26 @@
+=====================================
+The Linux kernel user-space API guide
+=====================================
+
+.. _man-pages: https://www.kernel.org/doc/man-pages/
+
+While much of the kernel's user-space API is documented elsewhere
+(particularly in the man-pages_ project), some user-space information can
+also be found in the kernel tree itself.  This manual is intended to be the
+place where this information is gathered.
+
+.. class:: toc-title
+
+	   Table of contents
+
+.. toctree::
+   :maxdepth: 2
+
+   unshare
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/unshare.txt b/Documentation/userspace-api/unshare.rst
index a8643513a5f6..737c192cf4e7 100644
--- a/Documentation/unshare.txt
+++ b/Documentation/userspace-api/unshare.rst
@@ -1,17 +1,17 @@
+unshare system call
+===================
 
-unshare system call:
---------------------
-This document describes the new system call, unshare. The document
+This document describes the new system call, unshare(). The document
 provides an overview of the feature, why it is needed, how it can
 be used, its interface specification, design, implementation and
 how it can be tested.
 
-Change Log:
------------
+Change Log
+----------
 version 0.1  Initial document, Janak Desai (janak@us.ibm.com), Jan 11, 2006
 
-Contents:
----------
+Contents
+--------
 	1) Overview
 	2) Benefits
 	3) Cost
@@ -24,6 +24,7 @@ Contents:
 
 1) Overview
 -----------
+
 Most legacy operating system kernels support an abstraction of threads
 as multiple execution contexts within a process. These kernels provide
 special resources and mechanisms to maintain these "threads". The Linux
@@ -38,33 +39,35 @@ threads. On Linux, at the time of thread creation using the clone system
 call, applications can selectively choose which resources to share
 between threads.
 
-unshare system call adds a primitive to the Linux thread model that
+unshare() system call adds a primitive to the Linux thread model that
 allows threads to selectively 'unshare' any resources that were being
-shared at the time of their creation. unshare was conceptualized by
+shared at the time of their creation. unshare() was conceptualized by
 Al Viro in the August of 2000, on the Linux-Kernel mailing list, as part
-of the discussion on POSIX threads on Linux.  unshare augments the
+of the discussion on POSIX threads on Linux.  unshare() augments the
 usefulness of Linux threads for applications that would like to control
-shared resources without creating a new process. unshare is a natural
+shared resources without creating a new process. unshare() is a natural
 addition to the set of available primitives on Linux that implement
 the concept of process/thread as a virtual machine.
 
 2) Benefits
 -----------
-unshare would be useful to large application frameworks such as PAM
+
+unshare() would be useful to large application frameworks such as PAM
 where creating a new process to control sharing/unsharing of process
 resources is not possible. Since namespaces are shared by default
-when creating a new process using fork or clone, unshare can benefit
+when creating a new process using fork or clone, unshare() can benefit
 even non-threaded applications if they have a need to disassociate
 from default shared namespace. The following lists two use-cases
-where unshare can be used.
+where unshare() can be used.
 
 2.1 Per-security context namespaces
------------------------------------
-unshare can be used to implement polyinstantiated directories using
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+unshare() can be used to implement polyinstantiated directories using
 the kernel's per-process namespace mechanism. Polyinstantiated directories,
 such as per-user and/or per-security context instance of /tmp, /var/tmp or
 per-security context instance of a user's home directory, isolate user
-processes when working with these directories. Using unshare, a PAM
+processes when working with these directories. Using unshare(), a PAM
 module can easily setup a private namespace for a user at login.
 Polyinstantiated directories are required for Common Criteria certification
 with Labeled System Protection Profile, however, with the availability
@@ -74,33 +77,36 @@ polyinstantiating /tmp, /var/tmp and other directories deemed
 appropriate by system administrators.
 
 2.2 unsharing of virtual memory and/or open files
--------------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
 Consider a client/server application where the server is processing
 client requests by creating processes that share resources such as
-virtual memory and open files. Without unshare, the server has to
+virtual memory and open files. Without unshare(), the server has to
 decide what needs to be shared at the time of creating the process
-which services the request. unshare allows the server an ability to
+which services the request. unshare() allows the server an ability to
 disassociate parts of the context during the servicing of the
 request. For large and complex middleware application frameworks, this
-ability to unshare after the process was created can be very
+ability to unshare() after the process was created can be very
 useful.
 
 3) Cost
 -------
-In order to not duplicate code and to handle the fact that unshare
+
+In order to not duplicate code and to handle the fact that unshare()
 works on an active task (as opposed to clone/fork working on a newly
-allocated inactive task) unshare had to make minor reorganizational
+allocated inactive task) unshare() had to make minor reorganizational
 changes to copy_* functions utilized by clone/fork system call.
 There is a cost associated with altering existing, well tested and
 stable code to implement a new feature that may not get exercised
 extensively in the beginning. However, with proper design and code
-review of the changes and creation of an unshare test for the LTP
+review of the changes and creation of an unshare() test for the LTP
 the benefits of this new feature can exceed its cost.
 
 4) Requirements
 ---------------
-unshare reverses sharing that was done using clone(2) system call,
-so unshare should have a similar interface as clone(2). That is,
+
+unshare() reverses sharing that was done using clone(2) system call,
+so unshare() should have a similar interface as clone(2). That is,
 since flags in clone(int flags, void *stack) specifies what should
 be shared, similar flags in unshare(int flags) should specify
 what should be unshared. Unfortunately, this may appear to invert
@@ -108,13 +114,14 @@ the meaning of the flags from the way they are used in clone(2).
 However, there was no easy solution that was less confusing and that
 allowed incremental context unsharing in future without an ABI change.
 
-unshare interface should accommodate possible future addition of
+unshare() interface should accommodate possible future addition of
 new context flags without requiring a rebuild of old applications.
-If and when new context flags are added, unshare design should allow
+If and when new context flags are added, unshare() design should allow
 incremental unsharing of those resources on an as needed basis.
 
 5) Functional Specification
 ---------------------------
+
 NAME
 	unshare - disassociate parts of the process execution context
 
@@ -124,7 +131,7 @@ SYNOPSIS
 	int unshare(int flags);
 
 DESCRIPTION
-	unshare allows a process to disassociate parts of its execution
+	unshare() allows a process to disassociate parts of its execution
 	context that are currently being shared with other processes. Part
 	of execution context, such as the namespace, is shared by default
 	when a new process is created using fork(2), while other parts,
@@ -132,7 +139,7 @@ DESCRIPTION
 	shared by explicit request to share them when creating a process
 	using clone(2).
 
-	The main use of unshare is to allow a process to control its
+	The main use of unshare() is to allow a process to control its
 	shared execution context without creating a new process.
 
 	The flags argument specifies one or bitwise-or'ed of several of
@@ -176,17 +183,20 @@ SEE ALSO
 
 6) High Level Design
 --------------------
-Depending on the flags argument, the unshare system call allocates
+
+Depending on the flags argument, the unshare() system call allocates
 appropriate process context structures, populates it with values from
 the current shared version, associates newly duplicated structures
 with the current task structure and releases corresponding shared
 versions. Helper functions of clone (copy_*) could not be used
-directly by unshare because of the following two reasons.
+directly by unshare() because of the following two reasons.
+
   1) clone operates on a newly allocated not-yet-active task
-     structure, where as unshare operates on the current active
-     task. Therefore unshare has to take appropriate task_lock()
+     structure, where as unshare() operates on the current active
+     task. Therefore unshare() has to take appropriate task_lock()
      before associating newly duplicated context structures
-  2) unshare has to allocate and duplicate all context structures
+
+  2) unshare() has to allocate and duplicate all context structures
      that are being unshared, before associating them with the
      current task and releasing older shared structures. Failure
      do so will create race conditions and/or oops when trying
@@ -202,94 +212,121 @@ Therefore code from copy_* functions that allocated and duplicated
 current context structure was moved into new dup_* functions. Now,
 copy_* functions call dup_* functions to allocate and duplicate
 appropriate context structures and then associate them with the
-task structure that is being constructed. unshare system call on
+task structure that is being constructed. unshare() system call on
 the other hand performs the following:
+
   1) Check flags to force missing, but implied, flags
-  2) For each context structure, call the corresponding unshare
+
+  2) For each context structure, call the corresponding unshare()
      helper function to allocate and duplicate a new context
      structure, if the appropriate bit is set in the flags argument.
+
   3) If there is no error in allocation and duplication and there
      are new context structures then lock the current task structure,
      associate new context structures with the current task structure,
      and release the lock on the current task structure.
+
   4) Appropriately release older, shared, context structures.
 
 7) Low Level Design
 -------------------
-Implementation of unshare can be grouped in the following 4 different
+
+Implementation of unshare() can be grouped in the following 4 different
 items:
+
   a) Reorganization of existing copy_* functions
-  b) unshare system call service function
-  c) unshare helper functions for each different process context
+
+  b) unshare() system call service function
+
+  c) unshare() helper functions for each different process context
+
   d) Registration of system call number for different architectures
 
-  7.1) Reorganization of copy_* functions
-       Each copy function such as copy_mm, copy_namespace, copy_files,
-       etc, had roughly two components. The first component allocated
-       and duplicated the appropriate structure and the second component
-       linked it to the task structure passed in as an argument to the copy
-       function. The first component was split into its own function.
-       These dup_* functions allocated and duplicated the appropriate
-       context structure. The reorganized copy_* functions invoked
-       their corresponding dup_* functions and then linked the newly
-       duplicated structures to the task structure with which the
-       copy function was called.
-
-  7.2) unshare system call service function
+7.1) Reorganization of copy_* functions
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Each copy function such as copy_mm, copy_namespace, copy_files,
+etc, had roughly two components. The first component allocated
+and duplicated the appropriate structure and the second component
+linked it to the task structure passed in as an argument to the copy
+function. The first component was split into its own function.
+These dup_* functions allocated and duplicated the appropriate
+context structure. The reorganized copy_* functions invoked
+their corresponding dup_* functions and then linked the newly
+duplicated structures to the task structure with which the
+copy function was called.
+
+7.2) unshare() system call service function
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
        * Check flags
 	 Force implied flags. If CLONE_THREAD is set force CLONE_VM.
 	 If CLONE_VM is set, force CLONE_SIGHAND. If CLONE_SIGHAND is
 	 set and signals are also being shared, force CLONE_THREAD. If
 	 CLONE_NEWNS is set, force CLONE_FS.
+
        * For each context flag, invoke the corresponding unshare_*
 	 helper routine with flags passed into the system call and a
 	 reference to pointer pointing the new unshared structure
+
        * If any new structures are created by unshare_* helper
 	 functions, take the task_lock() on the current task,
 	 modify appropriate context pointers, and release the
          task lock.
+
        * For all newly unshared structures, release the corresponding
          older, shared, structures.
 
-  7.3) unshare_* helper functions
-       For unshare_* helpers corresponding to CLONE_SYSVSEM, CLONE_SIGHAND,
-       and CLONE_THREAD, return -EINVAL since they are not implemented yet.
-       For others, check the flag value to see if the unsharing is
-       required for that structure. If it is, invoke the corresponding
-       dup_* function to allocate and duplicate the structure and return
-       a pointer to it.
+7.3) unshare_* helper functions
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-  7.4) Appropriately modify architecture specific code to register the
-       new system call.
+For unshare_* helpers corresponding to CLONE_SYSVSEM, CLONE_SIGHAND,
+and CLONE_THREAD, return -EINVAL since they are not implemented yet.
+For others, check the flag value to see if the unsharing is
+required for that structure. If it is, invoke the corresponding
+dup_* function to allocate and duplicate the structure and return
+a pointer to it.
+
+7.4) Finally
+~~~~~~~~~~~~
+
+Appropriately modify architecture specific code to register the
+new system call.
 
 8) Test Specification
 ---------------------
-The test for unshare should test the following:
+
+The test for unshare() should test the following:
+
   1) Valid flags: Test to check that clone flags for signal and
-	signal handlers, for which unsharing is not implemented
-	yet, return -EINVAL.
+     signal handlers, for which unsharing is not implemented
+     yet, return -EINVAL.
+
   2) Missing/implied flags: Test to make sure that if unsharing
-	namespace without specifying unsharing of filesystem, correctly
-	unshares both namespace and filesystem information.
+     namespace without specifying unsharing of filesystem, correctly
+     unshares both namespace and filesystem information.
+
   3) For each of the four (namespace, filesystem, files and vm)
-	supported unsharing, verify that the system call correctly
-	unshares the appropriate structure. Verify that unsharing
-	them individually as well as in combination with each
-	other works as expected.
+     supported unsharing, verify that the system call correctly
+     unshares the appropriate structure. Verify that unsharing
+     them individually as well as in combination with each
+     other works as expected.
+
   4) Concurrent execution: Use shared memory segments and futex on
-	an address in the shm segment to synchronize execution of
-	about 10 threads. Have a couple of threads execute execve,
-	a couple _exit and the rest unshare with different combination
-	of flags. Verify that unsharing is performed as expected and
-	that there are no oops or hangs.
+     an address in the shm segment to synchronize execution of
+     about 10 threads. Have a couple of threads execute execve,
+     a couple _exit and the rest unshare with different combination
+     of flags. Verify that unsharing is performed as expected and
+     that there are no oops or hangs.
 
 9) Future Work
 --------------
-The current implementation of unshare does not allow unsharing of
+
+The current implementation of unshare() does not allow unsharing of
 signals and signal handlers. Signals are complex to begin with and
 to unshare signals and/or signal handlers of a currently running
 process is even more complex. If in the future there is a specific
 need to allow unsharing of signals and/or signal handlers, it can
-be incrementally added to unshare without affecting legacy
-applications using unshare.
+be incrementally added to unshare() without affecting legacy
+applications using unshare().
 
diff --git a/Documentation/vfio-mediated-device.txt b/Documentation/vfio-mediated-device.txt
index d226c7a5ba8b..e5e57b40f8af 100644
--- a/Documentation/vfio-mediated-device.txt
+++ b/Documentation/vfio-mediated-device.txt
@@ -217,9 +217,9 @@ Directories and files under the sysfs for Each Physical Device
 
 * [<type-id>]
 
-  The [<type-id>] name is created by adding the the device driver string as a
-  prefix to the string provided by the vendor driver. This format of this name
-  is as follows:
+  The [<type-id>] name is created by adding the device driver string as a prefix
+  to the string provided by the vendor driver. This format of this name is as
+  follows:
 
 	sprintf(buf, "%s-%s", dev_driver_string(parent->dev), group->name);
 
@@ -380,7 +380,7 @@ card.
    /dev/ttyS1, UART: 16550A, Port: 0xc150, IRQ: 10
    /dev/ttyS2, UART: 16550A, Port: 0xc158, IRQ: 10
 
-6. Using a minicom or any terminal enulation program, open port /dev/ttyS1 or
+6. Using minicom or any terminal emulation program, open port /dev/ttyS1 or
    /dev/ttyS2 with hardware flow control disabled.
 
 7. Type data on the minicom terminal or send data to the terminal emulation
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 069450938b79..fd106899afd1 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -951,6 +951,10 @@ This ioctl allows the user to create or modify a guest physical memory
 slot.  When changing an existing slot, it may be moved in the guest
 physical memory space, or its flags may be modified.  It may not be
 resized.  Slots may not overlap in guest physical address space.
+Bits 0-15 of "slot" specifies the slot id and this value should be
+less than the maximum number of user memory slots supported per VM.
+The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
+if this capability is supported by the architecture.
 
 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
 specifies the address space which is being modified.  They must be
@@ -3373,6 +3377,69 @@ struct kvm_ppc_resize_hpt {
 	__u32 pad;
 };
 
+4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: system ioctl
+Parameters: u64 mce_cap (out)
+Returns: 0 on success, -1 on error
+
+Returns supported MCE capabilities. The u64 mce_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register. Supported
+capabilities will have the corresponding bits set.
+
+4.105 KVM_X86_SETUP_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: u64 mcg_cap (in)
+Returns: 0 on success,
+         -EFAULT if u64 mcg_cap cannot be read,
+         -EINVAL if the requested number of banks is invalid,
+         -EINVAL if requested MCE capability is not supported.
+
+Initializes MCE support for use. The u64 mcg_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register and
+specifies which capabilities should be enabled. The maximum
+supported number of error-reporting banks can be retrieved when
+checking for KVM_CAP_MCE. The supported capabilities can be
+retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
+
+4.106 KVM_X86_SET_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_x86_mce (in)
+Returns: 0 on success,
+         -EFAULT if struct kvm_x86_mce cannot be read,
+         -EINVAL if the bank number is invalid,
+         -EINVAL if VAL bit is not set in status field.
+
+Inject a machine check error (MCE) into the guest. The input
+parameter is:
+
+struct kvm_x86_mce {
+	__u64 status;
+	__u64 addr;
+	__u64 misc;
+	__u64 mcg_status;
+	__u8 bank;
+	__u8 pad1[7];
+	__u64 pad2[3];
+};
+
+If the MCE being reported is an uncorrected error, KVM will
+inject it as an MCE exception into the guest. If the guest
+MCG_STATUS register reports that an MCE is in progress, KVM
+causes an KVM_EXIT_SHUTDOWN vmexit.
+
+Otherwise, if the MCE is a corrected error, KVM will just
+store it in the corresponding bank (provided this bank is
+not holding a previously reported uncorrected error).
+
 5. The kvm_run structure
 ------------------------
 
diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt
index 76e61c883347..b2f60ca8b60c 100644
--- a/Documentation/virtual/kvm/devices/arm-vgic.txt
+++ b/Documentation/virtual/kvm/devices/arm-vgic.txt
@@ -83,6 +83,12 @@ Groups:
 
     Bits for undefined preemption levels are RAZ/WI.
 
+    For historical reasons and to provide ABI compatibility with userspace we
+    export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
+    field in the lower 5 bits of a word, meaning that userspace must always
+    use the lower 5 bits to communicate with the KVM device and must shift the
+    value left by 3 places to obtain the actual priority mask level.
+
   Limitations:
     - Priorities are not implemented, and registers are RAZ/WI
     - Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/vm/userfaultfd.txt
index 0e5543a920e5..bb2f945f87ab 100644
--- a/Documentation/vm/userfaultfd.txt
+++ b/Documentation/vm/userfaultfd.txt
@@ -172,10 +172,6 @@ the same read(2) protocol as for the page fault notifications. The
 manager has to explicitly enable these events by setting appropriate
 bits in uffdio_api.features passed to UFFDIO_API ioctl:
 
-UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the
-non-cooperative process. When the monitored process exits, the uffd
-manager will get UFFD_EVENT_EXIT.
-
 UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
 this feature is enabled, the userfaultfd context of the parent process
 is duplicated into the newly created process. The manager receives
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index 51cf6fa5591f..0f6d8477b66c 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -4,6 +4,7 @@ Copyright (C) 2016 Intel Corporation
 
 Fenghua Yu <fenghua.yu@intel.com>
 Tony Luck <tony.luck@intel.com>
+Vikas Shivappa <vikas.shivappa@intel.com>
 
 This feature is enabled by the CONFIG_INTEL_RDT_A Kconfig and the
 X86 /proc/cpuinfo flag bits "rdt", "cat_l3" and "cdp_l3".
@@ -22,19 +23,34 @@ Info directory
 
 The 'info' directory contains information about the enabled
 resources. Each resource has its own subdirectory. The subdirectory
-names reflect the resource names. Each subdirectory contains the
-following files:
+names reflect the resource names.
+Cache resource(L3/L2)  subdirectory contains the following files:
 
-"num_closids":  The number of CLOSIDs which are valid for this
-	        resource. The kernel uses the smallest number of
-		CLOSIDs of all enabled resources as limit.
+"num_closids":  	The number of CLOSIDs which are valid for this
+			resource. The kernel uses the smallest number of
+			CLOSIDs of all enabled resources as limit.
 
-"cbm_mask":     The bitmask which is valid for this resource. This
-		mask is equivalent to 100%.
+"cbm_mask":     	The bitmask which is valid for this resource.
+			This mask is equivalent to 100%.
 
-"min_cbm_bits": The minimum number of consecutive bits which must be
-		set when writing a mask.
+"min_cbm_bits": 	The minimum number of consecutive bits which
+			must be set when writing a mask.
 
+Memory bandwitdh(MB) subdirectory contains the following files:
+
+"min_bandwidth":	The minimum memory bandwidth percentage which
+			user can request.
+
+"bandwidth_gran":	The granularity in which the memory bandwidth
+			percentage is allocated. The allocated
+			b/w percentage is rounded off to the next
+			control step available on the hardware. The
+			available bandwidth control steps are:
+			min_bandwidth + N * bandwidth_gran.
+
+"delay_linear": 	Indicates if the delay scale is linear or
+			non-linear. This field is purely informational
+			only.
 
 Resource groups
 ---------------
@@ -59,6 +75,9 @@ There are three files associated with each group:
 	given to the default (root) group. You cannot remove CPUs
 	from the default group.
 
+"cpus_list": One or more CPU ranges of logical CPUs assigned to this
+	     group. Same rules apply like for the "cpus" file.
+
 "schemata": A list of all the resources available to this group.
 	Each resource has its own line and format - see below for
 	details.
@@ -107,6 +126,22 @@ and 0xA are not.  On a system with a 20-bit mask each bit represents 5%
 of the capacity of the cache. You could partition the cache into four
 equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Memory bandwidth(b/w) percentage
+--------------------------------
+For Memory b/w resource, user controls the resource by indicating the
+percentage of total memory b/w.
+
+The minimum bandwidth percentage value for each cpu model is predefined
+and can be looked up through "info/MB/min_bandwidth". The bandwidth
+granularity that is allocated is also dependent on the cpu model and can
+be looked up at "info/MB/bandwidth_gran". The available bandwidth
+control steps are: min_bw + N * bw_gran. Intermediate values are rounded
+to the next control step available on the hardware.
+
+The bandwidth throttling is a core specific mechanism on some of Intel
+SKUs. Using a high bandwidth and a low bandwidth setting on two threads
+sharing a core will result in both threads being throttled to use the
+low bandwidth.
 
 L3 details (code and data prioritization disabled)
 --------------------------------------------------
@@ -129,16 +164,38 @@ schemata format is always:
 
 	L2:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
 
+Memory b/w Allocation details
+-----------------------------
+
+Memory b/w domain is L3 cache.
+
+	MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
+
+Reading/writing the schemata file
+---------------------------------
+Reading the schemata file will show the state of all resources
+on all domains. When writing you only need to specify those values
+which you wish to change.  E.g.
+
+# cat schemata
+L3DATA:0=fffff;1=fffff;2=fffff;3=fffff
+L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
+# echo "L3DATA:2=3c0;" > schemata
+# cat schemata
+L3DATA:0=fffff;1=fffff;2=3c0;3=fffff
+L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
+
 Example 1
 ---------
 On a two socket machine (one L3 cache per socket) with just four bits
-for cache bit masks
+for cache bit masks, minimum b/w of 10% with a memory bandwidth
+granularity of 10%
 
 # mount -t resctrl resctrl /sys/fs/resctrl
 # cd /sys/fs/resctrl
 # mkdir p0 p1
-# echo "L3:0=3;1=c" > /sys/fs/resctrl/p0/schemata
-# echo "L3:0=3;1=3" > /sys/fs/resctrl/p1/schemata
+# echo "L3:0=3;1=c\nMB:0=50;1=50" > /sys/fs/resctrl/p0/schemata
+# echo "L3:0=3;1=3\nMB:0=50;1=50" > /sys/fs/resctrl/p1/schemata
 
 The default resource group is unmodified, so we have access to all parts
 of all caches (its schemata file reads "L3:0=f;1=f").
@@ -147,6 +204,14 @@ Tasks that are under the control of group "p0" may only allocate from the
 "lower" 50% on cache ID 0, and the "upper" 50% of cache ID 1.
 Tasks in group "p1" use the "lower" 50% of cache on both sockets.
 
+Similarly, tasks that are under the control of group "p0" may use a
+maximum memory b/w of 50% on socket0 and 50% on socket 1.
+Tasks in group "p1" may also use 50% memory b/w on both sockets.
+Note that unlike cache masks, memory b/w cannot specify whether these
+allocations can overlap or not. The allocations specifies the maximum
+b/w that the group may be able to use and the system admin can configure
+the b/w accordingly.
+
 Example 2
 ---------
 Again two sockets, but this time with a more realistic 20-bit mask.
@@ -160,9 +225,10 @@ of L3 cache on socket 0.
 # cd /sys/fs/resctrl
 
 First we reset the schemata for the default group so that the "upper"
-50% of the L3 cache on socket 0 cannot be used by ordinary tasks:
+50% of the L3 cache on socket 0 and 50% of memory b/w cannot be used by
+ordinary tasks:
 
-# echo "L3:0=3ff;1=fffff" > schemata
+# echo "L3:0=3ff;1=fffff\nMB:0=50;1=100" > schemata
 
 Next we make a resource group for our first real time task and give
 it access to the "top" 25% of the cache on socket 0.
@@ -185,6 +251,20 @@ Ditto for the second real time task (with the remaining 25% of cache):
 # echo 5678 > p1/tasks
 # taskset -cp 2 5678
 
+For the same 2 socket system with memory b/w resource and CAT L3 the
+schemata would look like(Assume min_bandwidth 10 and bandwidth_gran is
+10):
+
+For our first real time task this would request 20% memory b/w on socket
+0.
+
+# echo -e "L3:0=f8000;1=fffff\nMB:0=20;1=100" > p0/schemata
+
+For our second real time task this would request an other 20% memory b/w
+on socket 0.
+
+# echo -e "L3:0=f8000;1=fffff\nMB:0=20;1=100" > p0/schemata
+
 Example 3
 ---------
 
@@ -198,18 +278,22 @@ the tasks.
 # cd /sys/fs/resctrl
 
 First we reset the schemata for the default group so that the "upper"
-50% of the L3 cache on socket 0 cannot be used by ordinary tasks:
+50% of the L3 cache on socket 0, and 50% of memory bandwidth on socket 0
+cannot be used by ordinary tasks:
 
-# echo "L3:0=3ff" > schemata
+# echo "L3:0=3ff\nMB:0=50" > schemata
 
-Next we make a resource group for our real time cores and give
-it access to the "top" 50% of the cache on socket 0.
+Next we make a resource group for our real time cores and give it access
+to the "top" 50% of the cache on socket 0 and 50% of memory bandwidth on
+socket 0.
 
 # mkdir p0
-# echo "L3:0=ffc00;" > p0/schemata
+# echo "L3:0=ffc00\nMB:0=50" > p0/schemata
 
 Finally we move core 4-7 over to the new group and make sure that the
-kernel and the tasks running there get 50% of the cache.
+kernel and the tasks running there get 50% of the cache. They should
+also get 50% of memory bandwidth assuming that the cores 4-7 are SMT
+siblings and only the real time threads are scheduled on the cores 4-7.
 
 # echo C0 > p0/cpus
 
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 5724092db811..b0798e281aa6 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -4,7 +4,7 @@
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
-hole caused by [48:63] sign extension
+hole caused by [47:63] sign extension
 ffff800000000000 - ffff87ffffffffff (=43 bits) guard hole, reserved for hypervisor
 ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
 ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
@@ -19,16 +19,43 @@ ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
+ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
+ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
+
+Virtual memory map with 5 level page tables:
+
+0000000000000000 - 00ffffffffffffff (=56 bits) user space, different per mm
+hole caused by [56:63] sign extension
+ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
+ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
+ff90000000000000 - ff91ffffffffffff (=49 bits) hole
+ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
+ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
+... unused hole ...
+ffd8000000000000 - fff7ffffffffffff (=53 bits) kasan shadow memory (8PB)
+... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
+ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
+... unused hole ...
+ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
+Architecture defines a 64-bit virtual address. Implementations can support
+less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
+through to the most-significant implemented bit are set to either all ones
+or all zero. This causes hole between user space and kernel addresses.
+
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
 holes).
 
-vmalloc space is lazily synchronized into the different PML4 pages of
-the processes using the page fault handler, with init_level4_pgt as
+vmalloc space is lazily synchronized into the different PML4/PML5 pages of
+the processes using the page fault handler, with init_top_pgt as
 reference.
 
 Current X86-64 implementations support up to 46 bits of address space (64 TB),
@@ -39,6 +66,9 @@ memory window (this size is arbitrary, it can be raised later if needed).
 The mappings are not part of any other kernel PGD and are only available
 during EFI runtime calls.
 
+The module mapping space size changes based on the CONFIG requirements for the
+following fixmap section.
+
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt
index b8527c6b7646..97b7adbceda4 100644
--- a/Documentation/x86/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
@@ -27,7 +27,7 @@ Offset	Proto	Name		Meaning
 1C0/020	ALL	efi_info	EFI 32 information (struct efi_info)
 1E0/004	ALL	alk_mem_k	Alternative mem check, in KB
 1E4/004	ALL	scratch		Scratch field for the kernel setup code
-1E8/001	ALL	e820_entries	Number of entries in e820_map (below)
+1E8/001	ALL	e820_entries	Number of entries in e820_table (below)
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)
 1EA/001	ALL	edd_mbr_sig_buf_entries	Number of entries in edd_mbr_sig_buffer
 				(below)
@@ -35,6 +35,6 @@ Offset	Proto	Name		Meaning
 1EC/001	ALL     secure_boot	Secure boot is enabled in the firmware
 1EF/001	ALL	sentinel	Used to detect broken bootloaders
 290/040	ALL	edd_mbr_sig_buffer EDD MBR signatures
-2D0/A00	ALL	e820_map	E820 memory map table
-				(array of struct e820entry)
+2D0/A00	ALL	e820_table	E820 memory map table
+				(array of struct e820_entry)
 D00/1EC	ALL	eddbuf		EDD data (array of struct edd_info)
diff --git a/Documentation/zorro.txt b/Documentation/zorro.txt
index 90a64d52bea2..d530971beb00 100644
--- a/Documentation/zorro.txt
+++ b/Documentation/zorro.txt
@@ -11,7 +11,7 @@ Last revised: September 5, 2003
 The Zorro bus is the bus used in the Amiga family of computers. Thanks to
 AutoConfig(tm), it's 100% Plug-and-Play.
 
-There are two types of Zorro busses, Zorro II and Zorro III:
+There are two types of Zorro buses, Zorro II and Zorro III:
 
   - The Zorro II address space is 24-bit and lies within the first 16 MB of the
     Amiga's address map.
diff --git a/MAINTAINERS b/MAINTAINERS
index c265a5fe4848..bb4c9773a83c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -896,12 +896,19 @@ F:	arch/arm64/boot/dts/apm/
 APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER
 M:	Iyappan Subramanian <isubramanian@apm.com>
 M:	Keyur Chudgar <kchudgar@apm.com>
+M:	Quan Nguyen <qnguyen@apm.com>
 S:	Supported
 F:	drivers/net/ethernet/apm/xgene/
 F:	drivers/net/phy/mdio-xgene.c
 F:	Documentation/devicetree/bindings/net/apm-xgene-enet.txt
 F:	Documentation/devicetree/bindings/net/apm-xgene-mdio.txt
 
+APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER
+M:	Iyappan Subramanian <isubramanian@apm.com>
+M:	Keyur Chudgar <kchudgar@apm.com>
+S:	Supported
+F:	drivers/net/ethernet/apm/xgene-v2/
+
 APPLIED MICRO (APM) X-GENE SOC PMU
 M:	Tai Nguyen <ttnguyen@apm.com>
 S:	Supported
@@ -1088,6 +1095,8 @@ L:	linux-arm-kernel@axis.com
 F:	arch/arm/mach-artpec
 F:	arch/arm/boot/dts/artpec6*
 F:	drivers/clk/axis
+F:	drivers/pinctrl/pinctrl-artpec*
+F:	Documentation/devicetree/bindings/pinctrl/axis,artpec6-pinctrl.txt
 
 ARM/ASPEED MACHINE SUPPORT
 M:	Joel Stanley <joel@jms.id.au>
@@ -2327,21 +2336,6 @@ S:	Maintained
 F:	drivers/auxdisplay/
 F:	include/linux/cfag12864b.h
 
-AVR32 ARCHITECTURE
-M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
-M:	Hans-Christian Egtvedt <egtvedt@samfundet.no>
-W:	http://www.atmel.com/products/AVR32/
-W:	http://mirror.egtvedt.no/avr32linux.org/
-W:	http://avrfreaks.net/
-S:	Maintained
-F:	arch/avr32/
-
-AVR32/AT32AP MACHINE SUPPORT
-M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
-M:	Hans-Christian Egtvedt <egtvedt@samfundet.no>
-S:	Maintained
-F:	arch/avr32/mach-at32ap/
-
 AX.25 NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
@@ -2544,6 +2538,14 @@ F:	block/
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 
+BFQ I/O SCHEDULER
+M:	Paolo Valente <paolo.valente@linaro.org>
+M:	Jens Axboe <axboe@kernel.dk>
+L:	linux-block@vger.kernel.org
+S:	Maintained
+F:	block/bfq-*
+F:	Documentation/block/bfq-iosched.txt
+
 BLOCK2MTD DRIVER
 M:	Joern Engel <joern@lazybastard.org>
 L:	linux-mtd@lists.infradead.org
@@ -2585,12 +2587,26 @@ F:	include/uapi/linux/if_bonding.h
 
 BPF (Safe dynamic programs and tools)
 M:	Alexei Starovoitov <ast@kernel.org>
+M:	Daniel Borkmann <daniel@iogearbox.net>
 L:	netdev@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
 S:	Supported
+F:	arch/x86/net/bpf_jit*
+F:	Documentation/networking/filter.txt
+F:	include/linux/bpf*
+F:	include/linux/filter.h
+F:	include/uapi/linux/bpf*
+F:	include/uapi/linux/filter.h
 F:	kernel/bpf/
-F:	tools/testing/selftests/bpf/
+F:	kernel/trace/bpf_trace.c
 F:	lib/test_bpf.c
+F:	net/bpf/
+F:	net/core/filter.c
+F:	net/sched/act_bpf.c
+F:	net/sched/cls_bpf.c
+F:	samples/bpf/
+F:	tools/net/bpf*
+F:	tools/testing/selftests/bpf/
 
 BROADCOM B44 10/100 ETHERNET DRIVER
 M:	Michael Chan <michael.chan@broadcom.com>
@@ -2937,6 +2953,15 @@ W:	http://www.linux-c6x.org/wiki/index.php/Main_Page
 S:	Maintained
 F:	arch/c6x/
 
+CA8210 IEEE-802.15.4 RADIO DRIVER
+M:	Harry Morris <h.morris@cascoda.com>
+M:	linuxdev@cascoda.com
+L:	linux-wpan@vger.kernel.org
+W:	https://github.com/Cascoda/ca8210-linux.git
+S:	Maintained
+F:	drivers/net/ieee802154/ca8210.c
+F:	Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
+
 CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS
 M:	David Howells <dhowells@redhat.com>
 L:	linux-cachefs@redhat.com (moderated for non-subscribers)
@@ -3041,6 +3066,14 @@ S:	Supported
 F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
 
+CAVIUM MMC DRIVER
+M:	Jan Glauber <jglauber@cavium.com>
+M:	David Daney <david.daney@cavium.com>
+M:	Steven J. Hill <Steven.Hill@cavium.com>
+W:	http://www.cavium.com
+S:	Supported
+F:	drivers/mmc/host/cavium*
+
 CAVIUM LIQUIDIO NETWORK DRIVER
 M:     Derek Chickles <derek.chickles@caviumnetworks.com>
 M:     Satanand Burla <satananda.burla@caviumnetworks.com>
@@ -3216,7 +3249,6 @@ F:	drivers/platform/chrome/
 
 CISCO VIC ETHERNET NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
-M:	Sujith Sankar <ssujith@cisco.com>
 M:	Govindarajulu Varadarajan <_govind@gmx.com>
 M:	Neel Patel <neepatel@cisco.com>
 S:	Supported
@@ -3450,6 +3482,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 T:	git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates)
 B:	https://bugzilla.kernel.org
 F:	Documentation/cpu-freq/
+F:	Documentation/devicetree/bindings/cpufreq/
 F:	drivers/cpufreq/
 F:	include/linux/cpufreq.h
 F:	tools/testing/selftests/cpufreq/
@@ -4118,14 +4151,13 @@ F:	drivers/block/drbd/
 F:	lib/lru_cache.c
 F:	Documentation/blockdev/drbd/
 
-DRIVER CORE, KOBJECTS, DEBUGFS, KERNFS AND SYSFS
+DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
 S:	Supported
 F:	Documentation/kobject.txt
 F:	drivers/base/
 F:	fs/debugfs/
-F:	fs/kernfs/
 F:	fs/sysfs/
 F:	include/linux/debugfs.h
 F:	include/linux/kobj*
@@ -4695,6 +4727,7 @@ L:	linux-edac@vger.kernel.org
 L:	linux-mips@linux-mips.org
 S:	Supported
 F:	drivers/edac/octeon_edac*
+F:	drivers/edac/thunderx_edac*
 
 EDAC-E752X
 M:	Mark Gross <mark.gross@intel.com>
@@ -4776,6 +4809,12 @@ L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/mpc85xx_edac.[ch]
 
+EDAC-PND2
+M:	Tony Luck <tony.luck@intel.com>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/edac/pnd2_edac.[ch]
+
 EDAC-PASEMI
 M:	Egor Martovetsky <egor@pasemi.com>
 L:	linux-edac@vger.kernel.org
@@ -4923,6 +4962,7 @@ F:	include/linux/netfilter_bridge/
 F:	net/bridge/
 
 ETHERNET PHY LIBRARY
+M:	Andrew Lunn <andrew@lunn.ch>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -5401,6 +5441,23 @@ F:	fs/fuse/
 F:	include/uapi/linux/fuse.h
 F:	Documentation/filesystems/fuse.txt
 
+FUTEX SUBSYSTEM
+M:	Thomas Gleixner <tglx@linutronix.de>
+M:	Ingo Molnar <mingo@redhat.com>
+R:	Peter Zijlstra <peterz@infradead.org>
+R:	Darren Hart <dvhart@infradead.org>
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
+S:	Maintained
+F:	kernel/futex.c
+F:	kernel/futex_compat.c
+F:	include/asm-generic/futex.h
+F:	include/linux/futex.h
+F:	include/uapi/linux/futex.h
+F:	tools/testing/selftests/futex/
+F:	tools/perf/bench/futex*
+F:	Documentation/*futex*
+
 FUTURE DOMAIN TMC-16x0 SCSI DRIVER (16-bit)
 M:	Rik Faith <faith@cs.unc.edu>
 L:	linux-scsi@vger.kernel.org
@@ -6005,7 +6062,7 @@ M:	Sebastian Reichel <sre@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sre/linux-hsi.git
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-bus-hsi
-F:	Documentation/device-drivers/serial-interfaces.rst
+F:	Documentation/driver-api/hsi.rst
 F:	drivers/hsi/
 F:	include/linux/hsi/
 F:	include/uapi/linux/hsi/
@@ -6211,7 +6268,7 @@ F:	drivers/crypto/nx/nx_csbcpb.h
 F:	drivers/crypto/nx/nx_debugfs.h
 
 IBM Power 842 compression accelerator
-M:	Dan Streetman <ddstreet@ieee.org>
+M:	Haren Myneni <haren@us.ibm.com>
 S:	Supported
 F:	drivers/crypto/nx/Makefile
 F:	drivers/crypto/nx/Kconfig
@@ -7084,9 +7141,9 @@ S:	Maintained
 F:	fs/autofs4/
 
 KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
+M:	Masahiro Yamada <yamada.masahiro@socionext.com>
 M:	Michal Marek <mmarek@suse.com>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git
 L:	linux-kbuild@vger.kernel.org
 S:	Maintained
 F:	Documentation/kbuild/
@@ -7170,6 +7227,7 @@ S:	Supported
 F:	Documentation/s390/kvm.txt
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/kvm/
+F:	arch/s390/mm/gmap.c
 
 KERNEL VIRTUAL MACHINE (KVM) FOR ARM
 M:	Christoffer Dall <christoffer.dall@linaro.org>
@@ -7203,6 +7261,14 @@ F:	arch/mips/include/uapi/asm/kvm*
 F:	arch/mips/include/asm/kvm*
 F:	arch/mips/kvm/
 
+KERNFS
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+M:	Tejun Heo <tj@kernel.org>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+S:	Supported
+F:	include/linux/kernfs.h
+F:	fs/kernfs/
+
 KEXEC
 M:	Eric Biederman <ebiederm@xmission.com>
 W:	http://kernel.org/pub/linux/utils/kernel/kexec/
@@ -7774,13 +7840,6 @@ F:	include/net/mac80211.h
 F:	net/mac80211/
 F:	drivers/net/wireless/mac80211_hwsim.[ch]
 
-MACVLAN DRIVER
-M:	Patrick McHardy <kaber@trash.net>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/net/macvlan.c
-F:	include/linux/if_macvlan.h
-
 MAILBOX API
 M:	Jassi Brar <jassisinghbrar@gmail.com>
 L:	linux-kernel@vger.kernel.org
@@ -7851,8 +7910,10 @@ S:	Maintained
 F:	drivers/net/ethernet/marvell/mvneta.*
 
 MARVELL MWIFIEX WIRELESS DRIVER
-M:	Amitkumar Karwar <akarwar@marvell.com>
+M:	Amitkumar Karwar <amitkarwar@gmail.com>
 M:	Nishant Sarmukadam <nishants@marvell.com>
+M:	Ganapathi Bhat <gbhat@marvell.com>
+M:	Xinming Hu <huxm@marvell.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wireless/marvell/mwifiex/
@@ -7868,6 +7929,13 @@ M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Odd Fixes
 F:	drivers/mmc/host/mvsdio.*
 
+MARVELL XENON MMC/SD/SDIO HOST CONTROLLER DRIVER
+M:	Hu Ziji <huziji@marvell.com>
+L:	linux-mmc@vger.kernel.org
+S:	Supported
+F:	drivers/mmc/host/sdhci-xenon*
+F:	Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
+
 MATROX FRAMEBUFFER DRIVER
 L:	linux-fbdev@vger.kernel.org
 S:	Orphan
@@ -8307,7 +8375,6 @@ M:	Richard Leitner <richard.leitner@skidata.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/misc/usb251xb.c
-F:	include/linux/platform_data/usb251xb.h
 F:	Documentation/devicetree/bindings/usb/usb251xb.txt
 
 MICROSOFT SURFACE PRO 3 BUTTON DRIVER
@@ -8754,6 +8821,7 @@ W:	http://www.linuxfoundation.org/en/Net
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
+B:	mailto:netdev@vger.kernel.org
 S:	Maintained
 F:	net/
 F:	include/net/
@@ -8794,12 +8862,12 @@ F:	net/core/flow.c
 F:	net/xfrm/
 F:	net/key/
 F:	net/ipv4/xfrm*
-F:	net/ipv4/esp4.c
+F:	net/ipv4/esp4*
 F:	net/ipv4/ah4.c
 F:	net/ipv4/ipcomp.c
 F:	net/ipv4/ip_vti.c
 F:	net/ipv6/xfrm*
-F:	net/ipv6/esp6.c
+F:	net/ipv6/esp6*
 F:	net/ipv6/ah6.c
 F:	net/ipv6/ipcomp6.c
 F:	net/ipv6/ip6_vti.c
@@ -8853,8 +8921,6 @@ S:	Supported
 F:	drivers/net/ethernet/qlogic/netxen/
 
 NFC SUBSYSTEM
-M:	Lauro Ramos Venancio <lauro.venancio@openbossa.org>
-M:	Aloisio Almeida Jr <aloisio.almeida@openbossa.org>
 M:	Samuel Ortiz <sameo@linux.intel.com>
 L:	linux-wireless@vger.kernel.org
 L:	linux-nfc@lists.01.org (subscribers-only)
@@ -9909,6 +9975,8 @@ M:	Krzysztof Kozlowski <krzk@kernel.org>
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
+Q:	https://patchwork.kernel.org/project/linux-samsung-soc/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/samsung.git
 S:	Maintained
 F:	drivers/pinctrl/samsung/
 F:	include/dt-bindings/pinctrl/samsung.h
@@ -10815,6 +10883,7 @@ F:	drivers/s390/block/dasd*
 F:	block/partitions/ibm.c
 
 S390 NETWORK DRIVERS
+M:	Julian Wiedmann <jwi@linux.vnet.ibm.com>
 M:	Ursula Braun <ubraun@linux.vnet.ibm.com>
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -10845,6 +10914,7 @@ S:	Supported
 F:	drivers/s390/scsi/zfcp_*
 
 S390 IUCV NETWORK LAYER
+M:	Julian Wiedmann <jwi@linux.vnet.ibm.com>
 M:	Ursula Braun <ubraun@linux.vnet.ibm.com>
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -10860,6 +10930,16 @@ W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
 F:	drivers/iommu/s390-iommu.c
 
+S390 VFIO-CCW DRIVER
+M:	Cornelia Huck <cornelia.huck@de.ibm.com>
+M:	Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+L:	linux-s390@vger.kernel.org
+L:	kvm@vger.kernel.org
+S:	Supported
+F:	drivers/s390/cio/vfio_ccw*
+F:	Documentation/s390/vfio-ccw.txt
+F:	include/uapi/linux/vfio_ccw.h
+
 S3C24XX SD/MMC Driver
 M:	Ben Dooks <ben-linux@fluff.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -10907,6 +10987,14 @@ L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/samsung/
 
+SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER
+M:	Krzysztof Kozlowski <krzk@kernel.org>
+L:	linux-crypto@vger.kernel.org
+L:	linux-samsung-soc@vger.kernel.org
+S:	Maintained
+F:	drivers/crypto/exynos-rng.c
+F:	Documentation/devicetree/bindings/rng/samsung,exynos-rng4.txt
+
 SAMSUNG FRAMEBUFFER DRIVER
 M:	Jingoo Han <jingoohan1@gmail.com>
 L:	linux-fbdev@vger.kernel.org
@@ -10931,6 +11019,14 @@ F:	Documentation/devicetree/bindings/regulator/samsung,s2m*.txt
 F:	Documentation/devicetree/bindings/regulator/samsung,s5m*.txt
 F:	Documentation/devicetree/bindings/clock/samsung,s2mps11.txt
 
+SAMSUNG S5P Security SubSystem (SSS) DRIVER
+M:	Krzysztof Kozlowski <krzk@kernel.org>
+M:	Vladimir Zapolskiy <vz@mleia.com>
+L:	linux-crypto@vger.kernel.org
+L:	linux-samsung-soc@vger.kernel.org
+S:	Maintained
+F:	drivers/crypto/s5p-sss.c
+
 SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS
 M:	Kyungmin Park <kyungmin.park@samsung.com>
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
@@ -11062,6 +11158,12 @@ F:	include/linux/dma/dw.h
 F:	include/linux/platform_data/dma-dw.h
 F:	drivers/dma/dw/
 
+SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER
+M:	Jie Deng <jiedeng@synopsys.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/synopsys/
+
 SYNOPSYS DESIGNWARE I2C DRIVER
 M:	Jarkko Nikula <jarkko.nikula@linux.intel.com>
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
@@ -11100,6 +11202,7 @@ F:	drivers/power/supply/bq27xxx_battery_i2c.c
 TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER
 M:	John Stultz <john.stultz@linaro.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
+R:	Stephen Boyd <sboyd@codeaurora.org>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
 S:	Supported
@@ -12165,12 +12268,19 @@ F:	Documentation/accounting/taskstats*
 F:	include/linux/taskstats*
 F:	kernel/taskstats.c
 
-TC CLASSIFIER
+TC subsystem
 M:	Jamal Hadi Salim <jhs@mojatatu.com>
+M:	Cong Wang <xiyou.wangcong@gmail.com>
+M:	Jiri Pirko <jiri@resnulli.us>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	include/net/pkt_cls.h
+F:	include/net/pkt_sched.h
+F:	include/net/tc_act/
 F:	include/uapi/linux/pkt_cls.h
+F:	include/uapi/linux/pkt_sched.h
+F:	include/uapi/linux/tc_act/
+F:	include/uapi/linux/tc_ematch/
 F:	net/sched/
 
 TCP LOW PRIORITY MODULE
@@ -12455,7 +12565,6 @@ F:	drivers/clk/ti/
 F:	include/linux/clk/ti.h
 
 TI ETHERNET SWITCH DRIVER (CPSW)
-M:	Mugunthan V N <mugunthanvnm@ti.com>
 R:	Grygorii Strashko <grygorii.strashko@ti.com>
 L:	linux-omap@vger.kernel.org
 L:	netdev@vger.kernel.org
@@ -13267,8 +13376,11 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	include/linux/virtio_vsock.h
 F:	include/uapi/linux/virtio_vsock.h
+F:	include/uapi/linux/vsockmon.h
+F:	net/vmw_vsock/af_vsock_tap.c
 F:	net/vmw_vsock/virtio_transport_common.c
 F:	net/vmw_vsock/virtio_transport.c
+F:	drivers/net/vsockmon.c
 F:	drivers/vhost/vsock.c
 F:	drivers/vhost/vsock.h
 
@@ -13296,7 +13408,7 @@ F:	drivers/virtio/
 F:	tools/virtio/
 F:	drivers/net/virtio_net.c
 F:	drivers/block/virtio_blk.c
-F:	include/linux/virtio_*.h
+F:	include/linux/virtio*.h
 F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
 
@@ -13384,14 +13496,6 @@ W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/platform/vivid/*
 
-VLAN (802.1Q)
-M:	Patrick McHardy <kaber@trash.net>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/net/macvlan.c
-F:	include/linux/if_*vlan.h
-F:	net/8021q/
-
 VLYNQ BUS
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
diff --git a/Makefile b/Makefile
index 165cf9783a5d..43534cca1de9 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -172,8 +172,8 @@ MAKEFLAGS += --no-print-directory
 # Use 'make C=2' to enable checking of *all* source files, regardless
 # of whether they are re-compiled or not.
 #
-# See the file "Documentation/sparse.txt" for more details, including
-# where to get the "sparse" utility.
+# See the file "Documentation/dev-tools/sparse.rst" for more details,
+# including where to get the "sparse" utility.
 
 ifeq ("$(origin C)", "command line")
   KBUILD_CHECKSRC = $(C)
@@ -372,7 +372,7 @@ LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
 LDFLAGS_vmlinux =
-CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
+CFLAGS_GCOV	:= -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
 CFLAGS_KCOV	:= $(call cc-option,-fsanitize-coverage=trace-pc,)
 
 
@@ -653,6 +653,12 @@ KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0409, \
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 include scripts/Makefile.gcc-plugins
 
 ifdef CONFIG_READABLE_ASM
@@ -798,12 +804,6 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=incompatible-pointer-types)
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)
 
-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
-	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
-	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 include scripts/Makefile.ubsan
diff --git a/arch/Kconfig b/arch/Kconfig
index 6ad00ad73459..640999412d11 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -700,6 +700,13 @@ config ARCH_MMAP_RND_COMPAT_BITS
 	  This value can be changed after boot using the
 	  /proc/sys/vm/mmap_rnd_compat_bits tunable
 
+config HAVE_ARCH_COMPAT_MMAP_BASES
+	bool
+	help
+	  This allows 64bit applications to invoke 32-bit mmap() syscall
+	  and vice-versa 32-bit applications to call 64-bit mmap().
+	  Required for applications doing different bitness syscalls.
+
 config HAVE_COPY_THREAD_TLS
 	bool
 	help
diff --git a/arch/alpha/include/asm/extable.h b/arch/alpha/include/asm/extable.h
new file mode 100644
index 000000000000..048e209e524c
--- /dev/null
+++ b/arch/alpha/include/asm/extable.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_EXTABLE_H
+#define _ASM_EXTABLE_H
+
+/*
+ * About the exception table:
+ *
+ * - insn is a 32-bit pc-relative offset from the faulting insn.
+ * - nextinsn is a 16-bit offset off of the faulting instruction
+ *   (not off of the *next* instruction as branches are).
+ * - errreg is the register in which to place -EFAULT.
+ * - valreg is the final target register for the load sequence
+ *   and will be zeroed.
+ *
+ * Either errreg or valreg may be $31, in which case nothing happens.
+ *
+ * The exception fixup information "just so happens" to be arranged
+ * as in a MEM format instruction.  This lets us emit our three
+ * values like so:
+ *
+ *      lda valreg, nextinsn(errreg)
+ *
+ */
+
+struct exception_table_entry
+{
+	signed int insn;
+	union exception_fixup {
+		unsigned unit;
+		struct {
+			signed int nextinsn : 16;
+			unsigned int errreg : 5;
+			unsigned int valreg : 5;
+		} bits;
+	} fixup;
+};
+
+/* Returns the new pc */
+#define fixup_exception(map_reg, _fixup, pc)			\
+({								\
+	if ((_fixup)->fixup.bits.valreg != 31)			\
+		map_reg((_fixup)->fixup.bits.valreg) = 0;	\
+	if ((_fixup)->fixup.bits.errreg != 31)			\
+		map_reg((_fixup)->fixup.bits.errreg) = -EFAULT;	\
+	(pc) + (_fixup)->fixup.bits.nextinsn;			\
+})
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#define swap_ex_entry_fixup(a, b, tmp, delta)			\
+	do {							\
+		(a)->fixup.unit = (b)->fixup.unit;		\
+		(b)->fixup.unit = (tmp).fixup.unit;		\
+	} while (0)
+
+#endif
diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index f939794363ac..fb01dfb760c2 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -19,12 +19,8 @@
 	"3:	.subsection 2\n"				\
 	"4:	br	1b\n"					\
 	"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"			\
-	"	.long	1b-.\n"					\
-	"	lda	$31,3b-1b(%1)\n"			\
-	"	.long	2b-.\n"					\
-	"	lda	$31,3b-2b(%1)\n"			\
-	"	.previous\n"					\
+	EXC(1b,3b,%1,$31)					\
+	EXC(2b,3b,%1,$31)					\
 	:	"=&r" (oldval), "=&r"(ret)			\
 	:	"r" (uaddr), "r"(oparg)				\
 	:	"memory")
@@ -101,12 +97,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	"3:	.subsection 2\n"
 	"4:	br	1b\n"
 	"	.previous\n"
-	"	.section __ex_table,\"a\"\n"
-	"	.long	1b-.\n"
-	"	lda	$31,3b-1b(%0)\n"
-	"	.long	2b-.\n"
-	"	lda	$31,3b-2b(%0)\n"
-	"	.previous\n"
+	EXC(1b,3b,%0,$31)
+	EXC(2b,3b,%0,$31)
 	:	"+r"(ret), "=&r"(prev), "=&r"(cmp)
 	:	"r"(uaddr), "r"((long)(int)oldval), "r"(newval)
 	:	"memory");
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 94f587535dee..7b82dc9a8556 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -1,10 +1,6 @@
 #ifndef __ALPHA_UACCESS_H
 #define __ALPHA_UACCESS_H
 
-#include <linux/errno.h>
-#include <linux/sched.h>
-
-
 /*
  * The fs value determines whether argument validity checking should be
  * performed or not.  If get_fs() == USER_DS, checking is performed, with
@@ -20,9 +16,6 @@
 #define KERNEL_DS	((mm_segment_t) { 0UL })
 #define USER_DS		((mm_segment_t) { -0x40000000000UL })
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define get_fs()  (current_thread_info()->addr_limit)
 #define get_ds()  (KERNEL_DS)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
@@ -39,13 +32,13 @@
  *  - AND "addr+size" doesn't have any high-bits set
  *  - OR we are in kernel mode.
  */
-#define __access_ok(addr, size, segment) \
-	(((segment).seg & (addr | size | (addr+size))) == 0)
+#define __access_ok(addr, size) \
+	((get_fs().seg & (addr | size | (addr+size))) == 0)
 
-#define access_ok(type, addr, size)				\
-({								\
-	__chk_user_ptr(addr);					\
-	__access_ok(((unsigned long)(addr)), (size), get_fs());	\
+#define access_ok(type, addr, size)			\
+({							\
+	__chk_user_ptr(addr);				\
+	__access_ok(((unsigned long)(addr)), (size));	\
 })
 
 /*
@@ -61,9 +54,9 @@
  * (b) require any knowledge of processes at this stage
  */
 #define put_user(x, ptr) \
-  __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), get_fs())
+  __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 #define get_user(x, ptr) \
-  __get_user_check((x), (ptr), sizeof(*(ptr)), get_fs())
+  __get_user_check((x), (ptr), sizeof(*(ptr)))
 
 /*
  * The "__xxx" versions do not do address space checking, useful when
@@ -81,6 +74,11 @@
  * more extensive comments with fixup_inline_exception below for
  * more information.
  */
+#define EXC(label,cont,res,err)				\
+	".section __ex_table,\"a\"\n"			\
+	"	.long "#label"-.\n"			\
+	"	lda "#res","#cont"-"#label"("#err")\n"	\
+	".previous\n"
 
 extern void __get_user_unknown(void);
 
@@ -100,23 +98,23 @@ extern void __get_user_unknown(void);
 	__gu_err;						\
 })
 
-#define __get_user_check(x, ptr, size, segment)				\
-({									\
-	long __gu_err = -EFAULT;					\
-	unsigned long __gu_val = 0;					\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
-	if (__access_ok((unsigned long)__gu_addr, size, segment)) {	\
-		__gu_err = 0;						\
-		switch (size) {						\
-		  case 1: __get_user_8(__gu_addr); break;		\
-		  case 2: __get_user_16(__gu_addr); break;		\
-		  case 4: __get_user_32(__gu_addr); break;		\
-		  case 8: __get_user_64(__gu_addr); break;		\
-		  default: __get_user_unknown(); break;			\
-		}							\
-	}								\
-	(x) = (__force __typeof__(*(ptr))) __gu_val;			\
-	__gu_err;							\
+#define __get_user_check(x, ptr, size)				\
+({								\
+	long __gu_err = -EFAULT;				\
+	unsigned long __gu_val = 0;				\
+	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	if (__access_ok((unsigned long)__gu_addr, size)) {	\
+		__gu_err = 0;					\
+		switch (size) {					\
+		  case 1: __get_user_8(__gu_addr); break;	\
+		  case 2: __get_user_16(__gu_addr); break;	\
+		  case 4: __get_user_32(__gu_addr); break;	\
+		  case 8: __get_user_64(__gu_addr); break;	\
+		  default: __get_user_unknown(); break;		\
+		}						\
+	}							\
+	(x) = (__force __typeof__(*(ptr))) __gu_val;		\
+	__gu_err;						\
 })
 
 struct __large_struct { unsigned long buf[100]; };
@@ -125,20 +123,14 @@ struct __large_struct { unsigned long buf[100]; };
 #define __get_user_64(addr)				\
 	__asm__("1: ldq %0,%2\n"			\
 	"2:\n"						\
-	".section __ex_table,\"a\"\n"			\
-	"	.long 1b - .\n"				\
-	"	lda %0, 2b-1b(%1)\n"			\
-	".previous"					\
+	EXC(1b,2b,%0,%1)				\
 		: "=r"(__gu_val), "=r"(__gu_err)	\
 		: "m"(__m(addr)), "1"(__gu_err))
 
 #define __get_user_32(addr)				\
 	__asm__("1: ldl %0,%2\n"			\
 	"2:\n"						\
-	".section __ex_table,\"a\"\n"			\
-	"	.long 1b - .\n"				\
-	"	lda %0, 2b-1b(%1)\n"			\
-	".previous"					\
+	EXC(1b,2b,%0,%1)				\
 		: "=r"(__gu_val), "=r"(__gu_err)	\
 		: "m"(__m(addr)), "1"(__gu_err))
 
@@ -148,20 +140,14 @@ struct __large_struct { unsigned long buf[100]; };
 #define __get_user_16(addr)				\
 	__asm__("1: ldwu %0,%2\n"			\
 	"2:\n"						\
-	".section __ex_table,\"a\"\n"			\
-	"	.long 1b - .\n"				\
-	"	lda %0, 2b-1b(%1)\n"			\
-	".previous"					\
+	EXC(1b,2b,%0,%1)				\
 		: "=r"(__gu_val), "=r"(__gu_err)	\
 		: "m"(__m(addr)), "1"(__gu_err))
 
 #define __get_user_8(addr)				\
 	__asm__("1: ldbu %0,%2\n"			\
 	"2:\n"						\
-	".section __ex_table,\"a\"\n"			\
-	"	.long 1b - .\n"				\
-	"	lda %0, 2b-1b(%1)\n"			\
-	".previous"					\
+	EXC(1b,2b,%0,%1)				\
 		: "=r"(__gu_val), "=r"(__gu_err)	\
 		: "m"(__m(addr)), "1"(__gu_err))
 #else
@@ -177,12 +163,8 @@ struct __large_struct { unsigned long buf[100]; };
 	"	extwh %1,%3,%1\n"					\
 	"	or %0,%1,%0\n"						\
 	"3:\n"								\
-	".section __ex_table,\"a\"\n"					\
-	"	.long 1b - .\n"						\
-	"	lda %0, 3b-1b(%2)\n"					\
-	"	.long 2b - .\n"						\
-	"	lda %0, 3b-2b(%2)\n"					\
-	".previous"							\
+	EXC(1b,3b,%0,%2)						\
+	EXC(2b,3b,%0,%2)						\
 		: "=&r"(__gu_val), "=&r"(__gu_tmp), "=r"(__gu_err)	\
 		: "r"(addr), "2"(__gu_err));				\
 }
@@ -191,10 +173,7 @@ struct __large_struct { unsigned long buf[100]; };
 	__asm__("1: ldq_u %0,0(%2)\n"					\
 	"	extbl %0,%2,%0\n"					\
 	"2:\n"								\
-	".section __ex_table,\"a\"\n"					\
-	"	.long 1b - .\n"						\
-	"	lda %0, 2b-1b(%1)\n"					\
-	".previous"							\
+	EXC(1b,2b,%0,%1)						\
 		: "=&r"(__gu_val), "=r"(__gu_err)			\
 		: "r"(addr), "1"(__gu_err))
 #endif
@@ -215,21 +194,21 @@ extern void __put_user_unknown(void);
 	__pu_err;						\
 })
 
-#define __put_user_check(x, ptr, size, segment)				\
-({									\
-	long __pu_err = -EFAULT;					\
-	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
-	if (__access_ok((unsigned long)__pu_addr, size, segment)) {	\
-		__pu_err = 0;						\
-		switch (size) {						\
-		  case 1: __put_user_8(x, __pu_addr); break;		\
-		  case 2: __put_user_16(x, __pu_addr); break;		\
-		  case 4: __put_user_32(x, __pu_addr); break;		\
-		  case 8: __put_user_64(x, __pu_addr); break;		\
-		  default: __put_user_unknown(); break;			\
-		}							\
-	}								\
-	__pu_err;							\
+#define __put_user_check(x, ptr, size)				\
+({								\
+	long __pu_err = -EFAULT;				\
+	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
+	if (__access_ok((unsigned long)__pu_addr, size)) {	\
+		__pu_err = 0;					\
+		switch (size) {					\
+		  case 1: __put_user_8(x, __pu_addr); break;	\
+		  case 2: __put_user_16(x, __pu_addr); break;	\
+		  case 4: __put_user_32(x, __pu_addr); break;	\
+		  case 8: __put_user_64(x, __pu_addr); break;	\
+		  default: __put_user_unknown(); break;		\
+		}						\
+	}							\
+	__pu_err;						\
 })
 
 /*
@@ -240,20 +219,14 @@ extern void __put_user_unknown(void);
 #define __put_user_64(x, addr)					\
 __asm__ __volatile__("1: stq %r2,%1\n"				\
 	"2:\n"							\
-	".section __ex_table,\"a\"\n"				\
-	"	.long 1b - .\n"					\
-	"	lda $31,2b-1b(%0)\n"				\
-	".previous"						\
+	EXC(1b,2b,$31,%0)					\
 		: "=r"(__pu_err)				\
 		: "m" (__m(addr)), "rJ" (x), "0"(__pu_err))
 
 #define __put_user_32(x, addr)					\
 __asm__ __volatile__("1: stl %r2,%1\n"				\
 	"2:\n"							\
-	".section __ex_table,\"a\"\n"				\
-	"	.long 1b - .\n"					\
-	"	lda $31,2b-1b(%0)\n"				\
-	".previous"						\
+	EXC(1b,2b,$31,%0)					\
 		: "=r"(__pu_err)				\
 		: "m"(__m(addr)), "rJ"(x), "0"(__pu_err))
 
@@ -263,20 +236,14 @@ __asm__ __volatile__("1: stl %r2,%1\n"				\
 #define __put_user_16(x, addr)					\
 __asm__ __volatile__("1: stw %r2,%1\n"				\
 	"2:\n"							\
-	".section __ex_table,\"a\"\n"				\
-	"	.long 1b - .\n"					\
-	"	lda $31,2b-1b(%0)\n"				\
-	".previous"						\
+	EXC(1b,2b,$31,%0)					\
 		: "=r"(__pu_err)				\
 		: "m"(__m(addr)), "rJ"(x), "0"(__pu_err))
 
 #define __put_user_8(x, addr)					\
 __asm__ __volatile__("1: stb %r2,%1\n"				\
 	"2:\n"							\
-	".section __ex_table,\"a\"\n"				\
-	"	.long 1b - .\n"					\
-	"	lda $31,2b-1b(%0)\n"				\
-	".previous"						\
+	EXC(1b,2b,$31,%0)					\
 		: "=r"(__pu_err)				\
 		: "m"(__m(addr)), "rJ"(x), "0"(__pu_err))
 #else
@@ -298,16 +265,10 @@ __asm__ __volatile__("1: stb %r2,%1\n"				\
 	"3:	stq_u %2,1(%5)\n"				\
 	"4:	stq_u %1,0(%5)\n"				\
 	"5:\n"							\
-	".section __ex_table,\"a\"\n"				\
-	"	.long 1b - .\n"					\
-	"	lda $31, 5b-1b(%0)\n"				\
-	"	.long 2b - .\n"					\
-	"	lda $31, 5b-2b(%0)\n"				\
-	"	.long 3b - .\n"					\
-	"	lda $31, 5b-3b(%0)\n"				\
-	"	.long 4b - .\n"					\
-	"	lda $31, 5b-4b(%0)\n"				\
-	".previous"						\
+	EXC(1b,5b,$31,%0)					\
+	EXC(2b,5b,$31,%0)					\
+	EXC(3b,5b,$31,%0)					\
+	EXC(4b,5b,$31,%0)					\
 		: "=r"(__pu_err), "=&r"(__pu_tmp1), 		\
 		  "=&r"(__pu_tmp2), "=&r"(__pu_tmp3), 		\
 		  "=&r"(__pu_tmp4)				\
@@ -324,12 +285,8 @@ __asm__ __volatile__("1: stb %r2,%1\n"				\
 	"	or %1,%2,%1\n"					\
 	"2:	stq_u %1,0(%4)\n"				\
 	"3:\n"							\
-	".section __ex_table,\"a\"\n"				\
-	"	.long 1b - .\n"					\
-	"	lda $31, 3b-1b(%0)\n"				\
-	"	.long 2b - .\n"					\
-	"	lda $31, 3b-2b(%0)\n"				\
-	".previous"						\
+	EXC(1b,3b,$31,%0)					\
+	EXC(2b,3b,$31,%0)					\
 		: "=r"(__pu_err), 				\
 	  	  "=&r"(__pu_tmp1), "=&r"(__pu_tmp2)		\
 		: "r"((unsigned long)(x)), "r"(addr), "0"(__pu_err)); \
@@ -341,153 +298,37 @@ __asm__ __volatile__("1: stb %r2,%1\n"				\
  * Complex access routines
  */
 
-/* This little bit of silliness is to get the GP loaded for a function
-   that ordinarily wouldn't.  Otherwise we could have it done by the macro
-   directly, which can be optimized the linker.  */
-#ifdef MODULE
-#define __module_address(sym)		"r"(sym),
-#define __module_call(ra, arg, sym)	"jsr $" #ra ",(%" #arg ")," #sym
-#else
-#define __module_address(sym)
-#define __module_call(ra, arg, sym)	"bsr $" #ra "," #sym " !samegp"
-#endif
-
-extern void __copy_user(void);
-
-extern inline long
-__copy_tofrom_user_nocheck(void *to, const void *from, long len)
-{
-	register void * __cu_to __asm__("$6") = to;
-	register const void * __cu_from __asm__("$7") = from;
-	register long __cu_len __asm__("$0") = len;
-
-	__asm__ __volatile__(
-		__module_call(28, 3, __copy_user)
-		: "=r" (__cu_len), "=r" (__cu_from), "=r" (__cu_to)
-		: __module_address(__copy_user)
-		  "0" (__cu_len), "1" (__cu_from), "2" (__cu_to)
-		: "$1", "$2", "$3", "$4", "$5", "$28", "memory");
-
-	return __cu_len;
-}
-
-#define __copy_to_user(to, from, n)					\
-({									\
-	__chk_user_ptr(to);						\
-	__copy_tofrom_user_nocheck((__force void *)(to), (from), (n));	\
-})
-#define __copy_from_user(to, from, n)					\
-({									\
-	__chk_user_ptr(from);						\
-	__copy_tofrom_user_nocheck((to), (__force void *)(from), (n));	\
-})
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+extern long __copy_user(void *to, const void *from, long len);
 
-extern inline long
-copy_to_user(void __user *to, const void *from, long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long len)
 {
-	if (likely(__access_ok((unsigned long)to, n, get_fs())))
-		n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
-	return n;
+	return __copy_user(to, (__force const void *)from, len);
 }
 
-extern inline long
-copy_from_user(void *to, const void __user *from, long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long len)
 {
-	long res = n;
-	if (likely(__access_ok((unsigned long)from, n, get_fs())))
-		res = __copy_from_user_inatomic(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
+	return __copy_user((__force void *)to, from, len);
 }
 
-extern void __do_clear_user(void);
-
-extern inline long
-__clear_user(void __user *to, long len)
-{
-	register void __user * __cl_to __asm__("$6") = to;
-	register long __cl_len __asm__("$0") = len;
-	__asm__ __volatile__(
-		__module_call(28, 2, __do_clear_user)
-		: "=r"(__cl_len), "=r"(__cl_to)
-		: __module_address(__do_clear_user)
-		  "0"(__cl_len), "1"(__cl_to)
-		: "$1", "$2", "$3", "$4", "$5", "$28", "memory");
-	return __cl_len;
-}
+extern long __clear_user(void __user *to, long len);
 
 extern inline long
 clear_user(void __user *to, long len)
 {
-	if (__access_ok((unsigned long)to, len, get_fs()))
+	if (__access_ok((unsigned long)to, len))
 		len = __clear_user(to, len);
 	return len;
 }
 
-#undef __module_address
-#undef __module_call
-
 #define user_addr_max() \
-        (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+        (uaccess_kernel() ? ~0UL : TASK_SIZE)
 
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-/*
- * About the exception table:
- *
- * - insn is a 32-bit pc-relative offset from the faulting insn.
- * - nextinsn is a 16-bit offset off of the faulting instruction
- *   (not off of the *next* instruction as branches are).
- * - errreg is the register in which to place -EFAULT.
- * - valreg is the final target register for the load sequence
- *   and will be zeroed.
- *
- * Either errreg or valreg may be $31, in which case nothing happens.
- *
- * The exception fixup information "just so happens" to be arranged
- * as in a MEM format instruction.  This lets us emit our three
- * values like so:
- *
- *      lda valreg, nextinsn(errreg)
- *
- */
-
-struct exception_table_entry
-{
-	signed int insn;
-	union exception_fixup {
-		unsigned unit;
-		struct {
-			signed int nextinsn : 16;
-			unsigned int errreg : 5;
-			unsigned int valreg : 5;
-		} bits;
-	} fixup;
-};
-
-/* Returns the new pc */
-#define fixup_exception(map_reg, _fixup, pc)			\
-({								\
-	if ((_fixup)->fixup.bits.valreg != 31)			\
-		map_reg((_fixup)->fixup.bits.valreg) = 0;	\
-	if ((_fixup)->fixup.bits.errreg != 31)			\
-		map_reg((_fixup)->fixup.bits.errreg) = -EFAULT;	\
-	(pc) + (_fixup)->fixup.bits.nextinsn;			\
-})
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-#define swap_ex_entry_fixup(a, b, tmp, delta)			\
-	do {							\
-		(a)->fixup.unit = (b)->fixup.unit;		\
-		(b)->fixup.unit = (tmp).fixup.unit;		\
-	} while (0)
-
+#include <asm/extable.h>
 
 #endif /* __ALPHA_UACCESS_H */
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index afc901b7a6f6..148d7a32754e 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -99,4 +99,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 0b961093ca5c..9ec56dc97374 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1016,6 +1016,7 @@ SYSCALL_DEFINE2(osf_gettimeofday, struct timeval32 __user *, tv,
 SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
 		struct timezone __user *, tz)
 {
+	struct timespec64 kts64;
 	struct timespec kts;
 	struct timezone ktz;
 
@@ -1023,13 +1024,14 @@ SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
 		if (get_tv32((struct timeval *)&kts, tv))
 			return -EFAULT;
 		kts.tv_nsec *= 1000;
+		kts64 = timespec_to_timespec64(kts);
 	}
 	if (tz) {
 		if (copy_from_user(&ktz, tz, sizeof(*tz)))
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+	return do_sys_settimeofday64(tv ? &kts64 : NULL, tz ? &ktz : NULL);
 }
 
 asmlinkage long sys_ni_posix_timers(void);
@@ -1290,7 +1292,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p)
 	/* copy relevant bits of struct timex. */
 	if (copy_from_user(&txc, txc_p, offsetof(struct timex32, time)) ||
 	    copy_from_user(&txc.tick, &txc_p->tick, sizeof(struct timex32) - 
-			   offsetof(struct timex32, time)))
+			   offsetof(struct timex32, tick)))
 	  return -EFAULT;
 
 	ret = do_adjtimex(&txc);	
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index b137390e87e7..65bb102d985b 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -482,12 +482,8 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		"	extwl %1,%3,%1\n"
 		"	extwh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -502,12 +498,8 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		"	extll %1,%3,%1\n"
 		"	extlh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -522,12 +514,8 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		"	extql %1,%3,%1\n"
 		"	extqh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -551,16 +539,10 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		"3:	stq_u %2,1(%5)\n"
 		"4:	stq_u %1,0(%5)\n"
 		"5:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %2,5b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %1,5b-2b(%0)\n"
-		"	.long 3b - .\n"
-		"	lda $31,5b-3b(%0)\n"
-		"	.long 4b - .\n"
-		"	lda $31,5b-4b(%0)\n"
-		".previous"
+		EXC(1b,5b,%2,%0)
+		EXC(2b,5b,%1,%0)
+		EXC(3b,5b,$31,%0)
+		EXC(4b,5b,$31,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
 			  "=&r"(tmp3), "=&r"(tmp4)
 			: "r"(va), "r"(una_reg(reg)), "0"(0));
@@ -581,16 +563,10 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		"3:	stq_u %2,3(%5)\n"
 		"4:	stq_u %1,0(%5)\n"
 		"5:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %2,5b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %1,5b-2b(%0)\n"
-		"	.long 3b - .\n"
-		"	lda $31,5b-3b(%0)\n"
-		"	.long 4b - .\n"
-		"	lda $31,5b-4b(%0)\n"
-		".previous"
+		EXC(1b,5b,%2,%0)
+		EXC(2b,5b,%1,%0)
+		EXC(3b,5b,$31,%0)
+		EXC(4b,5b,$31,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
 			  "=&r"(tmp3), "=&r"(tmp4)
 			: "r"(va), "r"(una_reg(reg)), "0"(0));
@@ -611,16 +587,10 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		"3:	stq_u %2,7(%5)\n"
 		"4:	stq_u %1,0(%5)\n"
 		"5:\n"
-		".section __ex_table,\"a\"\n\t"
-		"	.long 1b - .\n"
-		"	lda %2,5b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %1,5b-2b(%0)\n"
-		"	.long 3b - .\n"
-		"	lda $31,5b-3b(%0)\n"
-		"	.long 4b - .\n"
-		"	lda $31,5b-4b(%0)\n"
-		".previous"
+		EXC(1b,5b,%2,%0)
+		EXC(2b,5b,%1,%0)
+		EXC(3b,5b,$31,%0)
+		EXC(4b,5b,$31,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
 			  "=&r"(tmp3), "=&r"(tmp4)
 			: "r"(va), "r"(una_reg(reg)), "0"(0));
@@ -802,7 +772,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 	/* Don't bother reading ds in the access check since we already
 	   know that this came from the user.  Also rely on the fact that
 	   the page at TASK_SIZE is unmapped and so can't be touched anyway. */
-	if (!__access_ok((unsigned long)va, 0, USER_DS))
+	if ((unsigned long)va >= TASK_SIZE)
 		goto give_sigsegv;
 
 	++unaligned[1].count;
@@ -835,12 +805,8 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"	extwl %1,%3,%1\n"
 		"	extwh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -855,12 +821,8 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"	extll %1,%3,%1\n"
 		"	extlh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -875,12 +837,8 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"	extql %1,%3,%1\n"
 		"	extqh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -895,12 +853,8 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"	extll %1,%3,%1\n"
 		"	extlh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -915,12 +869,8 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"	extql %1,%3,%1\n"
 		"	extqh %2,%3,%2\n"
 		"3:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %1,3b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %2,3b-2b(%0)\n"
-		".previous"
+		EXC(1b,3b,%1,%0)
+		EXC(2b,3b,%2,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
 			: "r"(va), "0"(0));
 		if (error)
@@ -944,16 +894,10 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"3:	stq_u %2,1(%5)\n"
 		"4:	stq_u %1,0(%5)\n"
 		"5:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %2,5b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %1,5b-2b(%0)\n"
-		"	.long 3b - .\n"
-		"	lda $31,5b-3b(%0)\n"
-		"	.long 4b - .\n"
-		"	lda $31,5b-4b(%0)\n"
-		".previous"
+		EXC(1b,5b,%2,%0)
+		EXC(2b,5b,%1,%0)
+		EXC(3b,5b,$31,%0)
+		EXC(4b,5b,$31,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
 			  "=&r"(tmp3), "=&r"(tmp4)
 			: "r"(va), "r"(*reg_addr), "0"(0));
@@ -978,16 +922,10 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"3:	stq_u %2,3(%5)\n"
 		"4:	stq_u %1,0(%5)\n"
 		"5:\n"
-		".section __ex_table,\"a\"\n"
-		"	.long 1b - .\n"
-		"	lda %2,5b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %1,5b-2b(%0)\n"
-		"	.long 3b - .\n"
-		"	lda $31,5b-3b(%0)\n"
-		"	.long 4b - .\n"
-		"	lda $31,5b-4b(%0)\n"
-		".previous"
+		EXC(1b,5b,%2,%0)
+		EXC(2b,5b,%1,%0)
+		EXC(3b,5b,$31,%0)
+		EXC(4b,5b,$31,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
 			  "=&r"(tmp3), "=&r"(tmp4)
 			: "r"(va), "r"(*reg_addr), "0"(0));
@@ -1012,16 +950,10 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		"3:	stq_u %2,7(%5)\n"
 		"4:	stq_u %1,0(%5)\n"
 		"5:\n"
-		".section __ex_table,\"a\"\n\t"
-		"	.long 1b - .\n"
-		"	lda %2,5b-1b(%0)\n"
-		"	.long 2b - .\n"
-		"	lda %1,5b-2b(%0)\n"
-		"	.long 3b - .\n"
-		"	lda $31,5b-3b(%0)\n"
-		"	.long 4b - .\n"
-		"	lda $31,5b-4b(%0)\n"
-		".previous"
+		EXC(1b,5b,%2,%0)
+		EXC(2b,5b,%1,%0)
+		EXC(3b,5b,$31,%0)
+		EXC(4b,5b,$31,%0)
 			: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
 			  "=&r"(tmp3), "=&r"(tmp4)
 			: "r"(va), "r"(*reg_addr), "0"(0));
@@ -1047,7 +979,7 @@ give_sigsegv:
 	/* We need to replicate some of the logic in mm/fault.c,
 	   since we don't have access to the fault code in the
 	   exception handling return path.  */
-	if (!__access_ok((unsigned long)va, 0, USER_DS))
+	if ((unsigned long)va >= TASK_SIZE)
 		info.si_code = SEGV_ACCERR;
 	else {
 		struct mm_struct *mm = current->mm;
diff --git a/arch/alpha/lib/clear_user.S b/arch/alpha/lib/clear_user.S
index bf5b931866ba..006f469fef73 100644
--- a/arch/alpha/lib/clear_user.S
+++ b/arch/alpha/lib/clear_user.S
@@ -8,21 +8,6 @@
  * right "bytes left to zero" value (and that it is updated only _after_
  * a successful copy).  There is also some rather minor exception setup
  * stuff.
- *
- * NOTE! This is not directly C-callable, because the calling semantics
- * are different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	exception pointer in $7
- *	return address in $28 (exceptions expect it there)
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6
  */
 #include <asm/export.h>
 
@@ -38,62 +23,63 @@
 	.set noreorder
 	.align 4
 
-	.globl __do_clear_user
-	.ent __do_clear_user
-	.frame	$30, 0, $28
+	.globl __clear_user
+	.ent __clear_user
+	.frame	$30, 0, $26
 	.prologue 0
 
 $loop:
 	and	$1, 3, $4	# e0    :
 	beq	$4, 1f		# .. e1 :
 
-0:	EX( stq_u $31, 0($6) )	# e0    : zero one word
+0:	EX( stq_u $31, 0($16) )	# e0    : zero one word
 	subq	$0, 8, $0	# .. e1 :
 	subq	$4, 1, $4	# e0    :
-	addq	$6, 8, $6	# .. e1 :
+	addq	$16, 8, $16	# .. e1 :
 	bne	$4, 0b		# e1    :
 	unop			#       :
 
 1:	bic	$1, 3, $1	# e0    :
 	beq	$1, $tail	# .. e1 :
 
-2:	EX( stq_u $31, 0($6) )	# e0    : zero four words
+2:	EX( stq_u $31, 0($16) )	# e0    : zero four words
 	subq	$0, 8, $0	# .. e1 :
-	EX( stq_u $31, 8($6) )	# e0    :
+	EX( stq_u $31, 8($16) )	# e0    :
 	subq	$0, 8, $0	# .. e1 :
-	EX( stq_u $31, 16($6) )	# e0    :
+	EX( stq_u $31, 16($16) )	# e0    :
 	subq	$0, 8, $0	# .. e1 :
-	EX( stq_u $31, 24($6) )	# e0    :
+	EX( stq_u $31, 24($16) )	# e0    :
 	subq	$0, 8, $0	# .. e1 :
 	subq	$1, 4, $1	# e0    :
-	addq	$6, 32, $6	# .. e1 :
+	addq	$16, 32, $16	# .. e1 :
 	bne	$1, 2b		# e1    :
 
 $tail:
 	bne	$2, 1f		# e1    : is there a tail to do?
-	ret	$31, ($28), 1	# .. e1 :
+	ret	$31, ($26), 1	# .. e1 :
 
-1:	EX( ldq_u $5, 0($6) )	# e0    :
+1:	EX( ldq_u $5, 0($16) )	# e0    :
 	clr	$0		# .. e1 :
 	nop			# e1    :
 	mskqh	$5, $0, $5	# e0    :
-	EX( stq_u $5, 0($6) )	# e0    :
-	ret	$31, ($28), 1	# .. e1 :
+	EX( stq_u $5, 0($16) )	# e0    :
+	ret	$31, ($26), 1	# .. e1 :
 
-__do_clear_user:
-	and	$6, 7, $4	# e0    : find dest misalignment
+__clear_user:
+	and	$17, $17, $0
+	and	$16, 7, $4	# e0    : find dest misalignment
 	beq	$0, $zerolength # .. e1 :
 	addq	$0, $4, $1	# e0    : bias counter
 	and	$1, 7, $2	# e1    : number of bytes in tail
 	srl	$1, 3, $1	# e0    :
 	beq	$4, $loop	# .. e1 :
 
-	EX( ldq_u $5, 0($6) )	# e0    : load dst word to mask back in
+	EX( ldq_u $5, 0($16) )	# e0    : load dst word to mask back in
 	beq	$1, $oneword	# .. e1 : sub-word store?
 
-	mskql	$5, $6, $5	# e0    : take care of misaligned head
-	addq	$6, 8, $6	# .. e1 :
-	EX( stq_u $5, -8($6) )	# e0    :
+	mskql	$5, $16, $5	# e0    : take care of misaligned head
+	addq	$16, 8, $16	# .. e1 :
+	EX( stq_u $5, -8($16) )	# e0    :
 	addq	$0, $4, $0	# .. e1 : bytes left -= 8 - misalignment
 	subq	$1, 1, $1	# e0    :
 	subq	$0, 8, $0	# .. e1 :
@@ -101,15 +87,15 @@ __do_clear_user:
 	unop			#       :
 
 $oneword:
-	mskql	$5, $6, $4	# e0    :
+	mskql	$5, $16, $4	# e0    :
 	mskqh	$5, $2, $5	# e0    :
 	or	$5, $4, $5	# e1    :
-	EX( stq_u $5, 0($6) )	# e0    :
+	EX( stq_u $5, 0($16) )	# e0    :
 	clr	$0		# .. e1 :
 
 $zerolength:
 $exception:
-	ret	$31, ($28), 1	# .. e1 :
+	ret	$31, ($26), 1	# .. e1 :
 
-	.end __do_clear_user
-	EXPORT_SYMBOL(__do_clear_user)
+	.end __clear_user
+	EXPORT_SYMBOL(__clear_user)
diff --git a/arch/alpha/lib/copy_user.S b/arch/alpha/lib/copy_user.S
index 509f62b65311..159f1b7e6e49 100644
--- a/arch/alpha/lib/copy_user.S
+++ b/arch/alpha/lib/copy_user.S
@@ -9,21 +9,6 @@
  * contains the right "bytes left to copy" value (and that it is updated
  * only _after_ a successful copy). There is also some rather minor
  * exception setup stuff..
- *
- * NOTE! This is not directly C-callable, because the calling semantics are
- * different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	source address in $7
- *	return address in $28
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6,$7
  */
 
 #include <asm/export.h>
@@ -49,58 +34,59 @@
 	.ent __copy_user
 __copy_user:
 	.prologue 0
-	and $6,7,$3
+	and $18,$18,$0
+	and $16,7,$3
 	beq $0,$35
 	beq $3,$36
 	subq $3,8,$3
 	.align 4
 $37:
-	EXI( ldq_u $1,0($7) )
-	EXO( ldq_u $2,0($6) )
-	extbl $1,$7,$1
-	mskbl $2,$6,$2
-	insbl $1,$6,$1
+	EXI( ldq_u $1,0($17) )
+	EXO( ldq_u $2,0($16) )
+	extbl $1,$17,$1
+	mskbl $2,$16,$2
+	insbl $1,$16,$1
 	addq $3,1,$3
 	bis $1,$2,$1
-	EXO( stq_u $1,0($6) )
+	EXO( stq_u $1,0($16) )
 	subq $0,1,$0
-	addq $6,1,$6
-	addq $7,1,$7
+	addq $16,1,$16
+	addq $17,1,$17
 	beq $0,$41
 	bne $3,$37
 $36:
-	and $7,7,$1
+	and $17,7,$1
 	bic $0,7,$4
 	beq $1,$43
 	beq $4,$48
-	EXI( ldq_u $3,0($7) )
+	EXI( ldq_u $3,0($17) )
 	.align 4
 $50:
-	EXI( ldq_u $2,8($7) )
+	EXI( ldq_u $2,8($17) )
 	subq $4,8,$4
-	extql $3,$7,$3
-	extqh $2,$7,$1
+	extql $3,$17,$3
+	extqh $2,$17,$1
 	bis $3,$1,$1
-	EXO( stq $1,0($6) )
-	addq $7,8,$7
+	EXO( stq $1,0($16) )
+	addq $17,8,$17
 	subq $0,8,$0
-	addq $6,8,$6
+	addq $16,8,$16
 	bis $2,$2,$3
 	bne $4,$50
 $48:
 	beq $0,$41
 	.align 4
 $57:
-	EXI( ldq_u $1,0($7) )
-	EXO( ldq_u $2,0($6) )
-	extbl $1,$7,$1
-	mskbl $2,$6,$2
-	insbl $1,$6,$1
+	EXI( ldq_u $1,0($17) )
+	EXO( ldq_u $2,0($16) )
+	extbl $1,$17,$1
+	mskbl $2,$16,$2
+	insbl $1,$16,$1
 	bis $1,$2,$1
-	EXO( stq_u $1,0($6) )
+	EXO( stq_u $1,0($16) )
 	subq $0,1,$0
-	addq $6,1,$6
-	addq $7,1,$7
+	addq $16,1,$16
+	addq $17,1,$17
 	bne $0,$57
 	br $31,$41
 	.align 4
@@ -108,27 +94,27 @@ $43:
 	beq $4,$65
 	.align 4
 $66:
-	EXI( ldq $1,0($7) )
+	EXI( ldq $1,0($17) )
 	subq $4,8,$4
-	EXO( stq $1,0($6) )
-	addq $7,8,$7
+	EXO( stq $1,0($16) )
+	addq $17,8,$17
 	subq $0,8,$0
-	addq $6,8,$6
+	addq $16,8,$16
 	bne $4,$66
 $65:
 	beq $0,$41
-	EXI( ldq $2,0($7) )
-	EXO( ldq $1,0($6) )
+	EXI( ldq $2,0($17) )
+	EXO( ldq $1,0($16) )
 	mskql $2,$0,$2
 	mskqh $1,$0,$1
 	bis $2,$1,$2
-	EXO( stq $2,0($6) )
+	EXO( stq $2,0($16) )
 	bis $31,$31,$0
 $41:
 $35:
 $exitin:
 $exitout:
-	ret $31,($28),1
+	ret $31,($26),1
 
 	.end __copy_user
 EXPORT_SYMBOL(__copy_user)
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index 5dfb7975895f..ab42afba1720 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -45,10 +45,7 @@ __asm__ __volatile__("insqh %1,%2,%0":"=r" (z):"r" (x),"r" (y))
 	__asm__ __volatile__(				\
 	"1:	ldq_u %0,%2\n"				\
 	"2:\n"						\
-	".section __ex_table,\"a\"\n"			\
-	"	.long 1b - .\n"				\
-	"	lda %0,2b-1b(%1)\n"			\
-	".previous"					\
+	EXC(1b,2b,%0,%1)				\
 		: "=r"(x), "=r"(__guu_err)		\
 		: "m"(__m(ptr)), "1"(0));		\
 	__guu_err;					\
@@ -60,10 +57,7 @@ __asm__ __volatile__("insqh %1,%2,%0":"=r" (z):"r" (x),"r" (y))
 	__asm__ __volatile__(				\
 	"1:	stq_u %2,%1\n"				\
 	"2:\n"						\
-	".section __ex_table,\"a\"\n"			\
-	"	.long 1b - ."				\
-	"	lda $31,2b-1b(%0)\n"			\
-	".previous"					\
+	EXC(1b,2b,$31,%0)				\
 		: "=r"(__puu_err)			\
 		: "m"(__m(addr)), "rJ"(x), "0"(0));	\
 	__puu_err;					\
diff --git a/arch/alpha/lib/ev6-clear_user.S b/arch/alpha/lib/ev6-clear_user.S
index 05bef6b50598..e179e4757ef8 100644
--- a/arch/alpha/lib/ev6-clear_user.S
+++ b/arch/alpha/lib/ev6-clear_user.S
@@ -9,21 +9,6 @@
  * a successful copy).  There is also some rather minor exception setup
  * stuff.
  *
- * NOTE! This is not directly C-callable, because the calling semantics
- * are different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	exception pointer in $7
- *	return address in $28 (exceptions expect it there)
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6
- *
  * Much of the information about 21264 scheduling/coding comes from:
  *	Compiler Writer's Guide for the Alpha 21264
  *	abbreviated as 'CWG' in other comments here
@@ -56,14 +41,15 @@
 	.set noreorder
 	.align 4
 
-	.globl __do_clear_user
-	.ent __do_clear_user
-	.frame	$30, 0, $28
+	.globl __clear_user
+	.ent __clear_user
+	.frame	$30, 0, $26
 	.prologue 0
 
 				# Pipeline info : Slotting & Comments
-__do_clear_user:
-	and	$6, 7, $4	# .. E  .. ..	: find dest head misalignment
+__clear_user:
+	and	$17, $17, $0
+	and	$16, 7, $4	# .. E  .. ..	: find dest head misalignment
 	beq	$0, $zerolength # U  .. .. ..	:  U L U L
 
 	addq	$0, $4, $1	# .. .. .. E	: bias counter
@@ -75,14 +61,14 @@ __do_clear_user:
 
 /*
  * Head is not aligned.  Write (8 - $4) bytes to head of destination
- * This means $6 is known to be misaligned
+ * This means $16 is known to be misaligned
  */
-	EX( ldq_u $5, 0($6) )	# .. .. .. L	: load dst word to mask back in
+	EX( ldq_u $5, 0($16) )	# .. .. .. L	: load dst word to mask back in
 	beq	$1, $onebyte	# .. .. U  ..	: sub-word store?
-	mskql	$5, $6, $5	# .. U  .. ..	: take care of misaligned head
-	addq	$6, 8, $6	# E  .. .. .. 	: L U U L
+	mskql	$5, $16, $5	# .. U  .. ..	: take care of misaligned head
+	addq	$16, 8, $16	# E  .. .. .. 	: L U U L
 
-	EX( stq_u $5, -8($6) )	# .. .. .. L	:
+	EX( stq_u $5, -8($16) )	# .. .. .. L	:
 	subq	$1, 1, $1	# .. .. E  ..	:
 	addq	$0, $4, $0	# .. E  .. ..	: bytes left -= 8 - misalignment
 	subq	$0, 8, $0	# E  .. .. ..	: U L U L
@@ -93,11 +79,11 @@ __do_clear_user:
  * values upon initial entry to the loop
  * $1 is number of quadwords to clear (zero is a valid value)
  * $2 is number of trailing bytes (0..7) ($2 never used...)
- * $6 is known to be aligned 0mod8
+ * $16 is known to be aligned 0mod8
  */
 $headalign:
 	subq	$1, 16, $4	# .. .. .. E	: If < 16, we can not use the huge loop
-	and	$6, 0x3f, $2	# .. .. E  ..	: Forward work for huge loop
+	and	$16, 0x3f, $2	# .. .. E  ..	: Forward work for huge loop
 	subq	$2, 0x40, $3	# .. E  .. ..	: bias counter (huge loop)
 	blt	$4, $trailquad	# U  .. .. ..	: U L U L
 
@@ -114,21 +100,21 @@ $headalign:
 	beq	$3, $bigalign	# U  .. .. ..	: U L U L : Aligned 0mod64
 
 $alignmod64:
-	EX( stq_u $31, 0($6) )	# .. .. .. L
+	EX( stq_u $31, 0($16) )	# .. .. .. L
 	addq	$3, 8, $3	# .. .. E  ..
 	subq	$0, 8, $0	# .. E  .. ..
 	nop			# E  .. .. ..	: U L U L
 
 	nop			# .. .. .. E
 	subq	$1, 1, $1	# .. .. E  ..
-	addq	$6, 8, $6	# .. E  .. ..
+	addq	$16, 8, $16	# .. E  .. ..
 	blt	$3, $alignmod64	# U  .. .. ..	: U L U L
 
 $bigalign:
 /*
  * $0 is the number of bytes left
  * $1 is the number of quads left
- * $6 is aligned 0mod64
+ * $16 is aligned 0mod64
  * we know that we'll be taking a minimum of one trip through
  * CWG Section 3.7.6: do not expect a sustained store rate of > 1/cycle
  * We are _not_ going to update $0 after every single store.  That
@@ -145,39 +131,39 @@ $bigalign:
 	nop			# E :
 	nop			# E :
 	nop			# E :
-	bis	$6,$6,$3	# E : U L U L : Initial wh64 address is dest
+	bis	$16,$16,$3	# E : U L U L : Initial wh64 address is dest
 	/* This might actually help for the current trip... */
 
 $do_wh64:
 	wh64	($3)		# .. .. .. L1	: memory subsystem hint
 	subq	$1, 16, $4	# .. .. E  ..	: Forward calculation - repeat the loop?
-	EX( stq_u $31, 0($6) )	# .. L  .. ..
+	EX( stq_u $31, 0($16) )	# .. L  .. ..
 	subq	$0, 8, $0	# E  .. .. ..	: U L U L
 
-	addq	$6, 128, $3	# E : Target address of wh64
-	EX( stq_u $31, 8($6) )	# L :
-	EX( stq_u $31, 16($6) )	# L :
+	addq	$16, 128, $3	# E : Target address of wh64
+	EX( stq_u $31, 8($16) )	# L :
+	EX( stq_u $31, 16($16) )	# L :
 	subq	$0, 16, $0	# E : U L L U
 
 	nop			# E :
-	EX( stq_u $31, 24($6) )	# L :
-	EX( stq_u $31, 32($6) )	# L :
+	EX( stq_u $31, 24($16) )	# L :
+	EX( stq_u $31, 32($16) )	# L :
 	subq	$0, 168, $5	# E : U L L U : two trips through the loop left?
 	/* 168 = 192 - 24, since we've already completed some stores */
 
 	subq	$0, 16, $0	# E :
-	EX( stq_u $31, 40($6) )	# L :
-	EX( stq_u $31, 48($6) )	# L :
-	cmovlt	$5, $6, $3	# E : U L L U : Latency 2, extra mapping cycle
+	EX( stq_u $31, 40($16) )	# L :
+	EX( stq_u $31, 48($16) )	# L :
+	cmovlt	$5, $16, $3	# E : U L L U : Latency 2, extra mapping cycle
 
 	subq	$1, 8, $1	# E :
 	subq	$0, 16, $0	# E :
-	EX( stq_u $31, 56($6) )	# L :
+	EX( stq_u $31, 56($16) )	# L :
 	nop			# E : U L U L
 
 	nop			# E :
 	subq	$0, 8, $0	# E :
-	addq	$6, 64, $6	# E :
+	addq	$16, 64, $16	# E :
 	bge	$4, $do_wh64	# U : U L U L
 
 $trailquad:
@@ -190,14 +176,14 @@ $trailquad:
 	beq	$1, $trailbytes	# U  .. .. ..	: U L U L : Only 0..7 bytes to go
 
 $onequad:
-	EX( stq_u $31, 0($6) )	# .. .. .. L
+	EX( stq_u $31, 0($16) )	# .. .. .. L
 	subq	$1, 1, $1	# .. .. E  ..
 	subq	$0, 8, $0	# .. E  .. ..
 	nop			# E  .. .. ..	: U L U L
 
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
-	addq	$6, 8, $6	# .. E  .. ..
+	addq	$16, 8, $16	# .. E  .. ..
 	bgt	$1, $onequad	# U  .. .. ..	: U L U L
 
 	# We have an unknown number of bytes left to go.
@@ -211,9 +197,9 @@ $trailbytes:
 	# so we will use $0 as the loop counter
 	# We know for a fact that $0 > 0 zero due to previous context
 $onebyte:
-	EX( stb $31, 0($6) )	# .. .. .. L
+	EX( stb $31, 0($16) )	# .. .. .. L
 	subq	$0, 1, $0	# .. .. E  ..	:
-	addq	$6, 1, $6	# .. E  .. ..	:
+	addq	$16, 1, $16	# .. E  .. ..	:
 	bgt	$0, $onebyte	# U  .. .. ..	: U L U L
 
 $zerolength:
@@ -221,6 +207,6 @@ $exception:			# Destination for exception recovery(?)
 	nop			# .. .. .. E	:
 	nop			# .. .. E  ..	:
 	nop			# .. E  .. ..	:
-	ret	$31, ($28), 1	# L0 .. .. ..	: L U L U
-	.end __do_clear_user
-	EXPORT_SYMBOL(__do_clear_user)
+	ret	$31, ($26), 1	# L0 .. .. ..	: L U L U
+	.end __clear_user
+	EXPORT_SYMBOL(__clear_user)
diff --git a/arch/alpha/lib/ev6-copy_user.S b/arch/alpha/lib/ev6-copy_user.S
index be720b518af9..35e6710d0700 100644
--- a/arch/alpha/lib/ev6-copy_user.S
+++ b/arch/alpha/lib/ev6-copy_user.S
@@ -12,21 +12,6 @@
  * only _after_ a successful copy). There is also some rather minor
  * exception setup stuff..
  *
- * NOTE! This is not directly C-callable, because the calling semantics are
- * different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	source address in $7
- *	return address in $28
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6,$7
- *
  * Much of the information about 21264 scheduling/coding comes from:
  *	Compiler Writer's Guide for the Alpha 21264
  *	abbreviated as 'CWG' in other comments here
@@ -60,10 +45,11 @@
 				# Pipeline info: Slotting & Comments
 __copy_user:
 	.prologue 0
-	subq $0, 32, $1		# .. E  .. ..	: Is this going to be a small copy?
+	andq $18, $18, $0
+	subq $18, 32, $1	# .. E  .. ..	: Is this going to be a small copy?
 	beq $0, $zerolength	# U  .. .. ..	: U L U L
 
-	and $6,7,$3		# .. .. .. E	: is leading dest misalignment
+	and $16,7,$3		# .. .. .. E	: is leading dest misalignment
 	ble $1, $onebyteloop	# .. .. U  ..	: 1st branch : small amount of data
 	beq $3, $destaligned	# .. U  .. ..	: 2nd (one cycle fetcher stall)
 	subq $3, 8, $3		# E  .. .. ..	: L U U L : trip counter
@@ -73,17 +59,17 @@ __copy_user:
  * We know we have at least one trip through this loop
  */
 $aligndest:
-	EXI( ldbu $1,0($7) )	# .. .. .. L	: Keep loads separate from stores
-	addq $6,1,$6		# .. .. E  ..	: Section 3.8 in the CWG
+	EXI( ldbu $1,0($17) )	# .. .. .. L	: Keep loads separate from stores
+	addq $16,1,$16		# .. .. E  ..	: Section 3.8 in the CWG
 	addq $3,1,$3		# .. E  .. ..	:
 	nop			# E  .. .. ..	: U L U L
 
 /*
- * the -1 is to compensate for the inc($6) done in a previous quadpack
+ * the -1 is to compensate for the inc($16) done in a previous quadpack
  * which allows us zero dependencies within either quadpack in the loop
  */
-	EXO( stb $1,-1($6) )	# .. .. .. L	:
-	addq $7,1,$7		# .. .. E  ..	: Section 3.8 in the CWG
+	EXO( stb $1,-1($16) )	# .. .. .. L	:
+	addq $17,1,$17		# .. .. E  ..	: Section 3.8 in the CWG
 	subq $0,1,$0		# .. E  .. ..	:
 	bne $3, $aligndest	# U  .. .. ..	: U L U L
 
@@ -92,29 +78,29 @@ $aligndest:
  * If we arrived via branch, we have a minimum of 32 bytes
  */
 $destaligned:
-	and $7,7,$1		# .. .. .. E	: Check _current_ source alignment
+	and $17,7,$1		# .. .. .. E	: Check _current_ source alignment
 	bic $0,7,$4		# .. .. E  ..	: number bytes as a quadword loop
-	EXI( ldq_u $3,0($7) )	# .. L  .. ..	: Forward fetch for fallthrough code
+	EXI( ldq_u $3,0($17) )	# .. L  .. ..	: Forward fetch for fallthrough code
 	beq $1,$quadaligned	# U  .. .. ..	: U L U L
 
 /*
- * In the worst case, we've just executed an ldq_u here from 0($7)
+ * In the worst case, we've just executed an ldq_u here from 0($17)
  * and we'll repeat it once if we take the branch
  */
 
 /* Misaligned quadword loop - not unrolled.  Leave it that way. */
 $misquad:
-	EXI( ldq_u $2,8($7) )	# .. .. .. L	:
+	EXI( ldq_u $2,8($17) )	# .. .. .. L	:
 	subq $4,8,$4		# .. .. E  ..	:
-	extql $3,$7,$3		# .. U  .. ..	:
-	extqh $2,$7,$1		# U  .. .. ..	: U U L L
+	extql $3,$17,$3		# .. U  .. ..	:
+	extqh $2,$17,$1		# U  .. .. ..	: U U L L
 
 	bis $3,$1,$1		# .. .. .. E	:
-	EXO( stq $1,0($6) )	# .. .. L  ..	:
-	addq $7,8,$7		# .. E  .. ..	:
+	EXO( stq $1,0($16) )	# .. .. L  ..	:
+	addq $17,8,$17		# .. E  .. ..	:
 	subq $0,8,$0		# E  .. .. ..	: U L L U
 
-	addq $6,8,$6		# .. .. .. E	:
+	addq $16,8,$16		# .. .. .. E	:
 	bis $2,$2,$3		# .. .. E  ..	:
 	nop			# .. E  .. ..	:
 	bne $4,$misquad		# U  .. .. ..	: U L U L
@@ -125,8 +111,8 @@ $misquad:
 	beq $0,$zerolength	# U  .. .. ..	: U L U L
 
 /* We know we have at least one trip through the byte loop */
-	EXI ( ldbu $2,0($7) )	# .. .. .. L	: No loads in the same quad
-	addq $6,1,$6		# .. .. E  ..	: as the store (Section 3.8 in CWG)
+	EXI ( ldbu $2,0($17) )	# .. .. .. L	: No loads in the same quad
+	addq $16,1,$16		# .. .. E  ..	: as the store (Section 3.8 in CWG)
 	nop			# .. E  .. ..	:
 	br $31, $dirtyentry	# L0 .. .. ..	: L U U L
 /* Do the trailing byte loop load, then hop into the store part of the loop */
@@ -136,8 +122,8 @@ $misquad:
  * Based upon the usage context, it's worth the effort to unroll this loop
  * $0 - number of bytes to be moved
  * $4 - number of bytes to move as quadwords
- * $6 is current destination address
- * $7 is current source address
+ * $16 is current destination address
+ * $17 is current source address
  */
 $quadaligned:
 	subq	$4, 32, $2	# .. .. .. E	: do not unroll for small stuff
@@ -155,29 +141,29 @@ $quadaligned:
  * instruction memory hint instruction).
  */
 $unroll4:
-	EXI( ldq $1,0($7) )	# .. .. .. L
-	EXI( ldq $2,8($7) )	# .. .. L  ..
+	EXI( ldq $1,0($17) )	# .. .. .. L
+	EXI( ldq $2,8($17) )	# .. .. L  ..
 	subq	$4,32,$4	# .. E  .. ..
 	nop			# E  .. .. ..	: U U L L
 
-	addq	$7,16,$7	# .. .. .. E
-	EXO( stq $1,0($6) )	# .. .. L  ..
-	EXO( stq $2,8($6) )	# .. L  .. ..
+	addq	$17,16,$17	# .. .. .. E
+	EXO( stq $1,0($16) )	# .. .. L  ..
+	EXO( stq $2,8($16) )	# .. L  .. ..
 	subq	$0,16,$0	# E  .. .. ..	: U L L U
 
-	addq	$6,16,$6	# .. .. .. E
-	EXI( ldq $1,0($7) )	# .. .. L  ..
-	EXI( ldq $2,8($7) )	# .. L  .. ..
+	addq	$16,16,$16	# .. .. .. E
+	EXI( ldq $1,0($17) )	# .. .. L  ..
+	EXI( ldq $2,8($17) )	# .. L  .. ..
 	subq	$4, 32, $3	# E  .. .. ..	: U U L L : is there enough for another trip?
 
-	EXO( stq $1,0($6) )	# .. .. .. L
-	EXO( stq $2,8($6) )	# .. .. L  ..
+	EXO( stq $1,0($16) )	# .. .. .. L
+	EXO( stq $2,8($16) )	# .. .. L  ..
 	subq	$0,16,$0	# .. E  .. ..
-	addq	$7,16,$7	# E  .. .. ..	: U L L U
+	addq	$17,16,$17	# E  .. .. ..	: U L L U
 
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
-	addq	$6,16,$6	# .. E  .. ..
+	addq	$16,16,$16	# .. E  .. ..
 	bgt	$3,$unroll4	# U  .. .. ..	: U L U L
 
 	nop
@@ -186,14 +172,14 @@ $unroll4:
 	beq	$4, $noquads
 
 $onequad:
-	EXI( ldq $1,0($7) )
+	EXI( ldq $1,0($17) )
 	subq	$4,8,$4
-	addq	$7,8,$7
+	addq	$17,8,$17
 	nop
 
-	EXO( stq $1,0($6) )
+	EXO( stq $1,0($16) )
 	subq	$0,8,$0
-	addq	$6,8,$6
+	addq	$16,8,$16
 	bne	$4,$onequad
 
 $noquads:
@@ -207,23 +193,23 @@ $noquads:
  * There's no point in doing a lot of complex alignment calculations to try to
  * to quadword stuff for a small amount of data.
  *	$0 - remaining number of bytes left to copy
- *	$6 - current dest addr
- *	$7 - current source addr
+ *	$16 - current dest addr
+ *	$17 - current source addr
  */
 
 $onebyteloop:
-	EXI ( ldbu $2,0($7) )	# .. .. .. L	: No loads in the same quad
-	addq $6,1,$6		# .. .. E  ..	: as the store (Section 3.8 in CWG)
+	EXI ( ldbu $2,0($17) )	# .. .. .. L	: No loads in the same quad
+	addq $16,1,$16		# .. .. E  ..	: as the store (Section 3.8 in CWG)
 	nop			# .. E  .. ..	:
 	nop			# E  .. .. ..	: U L U L
 
 $dirtyentry:
 /*
- * the -1 is to compensate for the inc($6) done in a previous quadpack
+ * the -1 is to compensate for the inc($16) done in a previous quadpack
  * which allows us zero dependencies within either quadpack in the loop
  */
-	EXO ( stb $2,-1($6) )	# .. .. .. L	:
-	addq $7,1,$7		# .. .. E  ..	: quadpack as the load
+	EXO ( stb $2,-1($16) )	# .. .. .. L	:
+	addq $17,1,$17		# .. .. E  ..	: quadpack as the load
 	subq $0,1,$0		# .. E  .. ..	: change count _after_ copy
 	bgt $0,$onebyteloop	# U  .. .. ..	: U L U L
 
@@ -233,7 +219,7 @@ $exitout:			# Destination for exception recovery(?)
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
 	nop			# .. E  .. ..
-	ret $31,($28),1		# L0 .. .. ..	: L U L U
+	ret $31,($26),1		# L0 .. .. ..	: L U L U
 
 	.end __copy_user
 	EXPORT_SYMBOL(__copy_user)
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index c9f30f4763ab..5d7fb3e7cb97 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -406,6 +406,14 @@ config ARC_HAS_DIV_REM
 	bool "Insn: div, divu, rem, remu"
 	default y
 
+config ARC_HAS_ACCL_REGS
+	bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)"
+	default n
+	help
+	  Depending on the configuration, CPU can contain accumulator reg-pair
+	  (also referred to as r58:r59). These can also be used by gcc as GPR so
+	  kernel needs to save/restore per process
+
 endif	# ISA_ARCV2
 
 endmenu   # "ARC CPU Configuration"
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
index 65808fe0a290..2891cb266cf0 100644
--- a/arch/arc/boot/dts/skeleton.dtsi
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -26,6 +26,7 @@
 			device_type = "cpu";
 			compatible = "snps,arc770d";
 			reg = <0>;
+			clocks = <&core_clk>;
 		};
 	};
 
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
index 2dfe8037dfbb..5e944d3e5b74 100644
--- a/arch/arc/boot/dts/skeleton_hs.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -21,6 +21,7 @@
 			device_type = "cpu";
 			compatible = "snps,archs38";
 			reg = <0>;
+			clocks = <&core_clk>;
 		};
 	};
 
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
index 4c11079f3565..54b277d7dea0 100644
--- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -19,8 +19,27 @@
 
 		cpu@0 {
 			device_type = "cpu";
-			compatible = "snps,archs38xN";
+			compatible = "snps,archs38";
 			reg = <0>;
+			clocks = <&core_clk>;
+		};
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <1>;
+			clocks = <&core_clk>;
+		};
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <2>;
+			clocks = <&core_clk>;
+		};
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "snps,archs38";
+			reg = <3>;
+			clocks = <&core_clk>;
 		};
 	};
 
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
index f0df59b23e21..459fc656b759 100644
--- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -112,13 +112,19 @@
 			interrupts = <7>;
 			bus-width = <4>;
 		};
+	};
 
-		/* Embedded Vision subsystem UIO mappings; only relevant for EV VDK */
-		uio_ev: uio@0xD0000000 {
-			compatible = "generic-uio";
-			reg = <0xD0000000 0x2000 0xD1000000 0x2000 0x90000000 0x10000000 0xC0000000 0x10000000>;
-			reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
-			interrupts = <23>;
-		};
+	/*
+	 * Embedded Vision subsystem UIO mappings; only relevant for EV VDK
+	 *
+	 * This node is intentionally put outside of MB above becase
+	 * it maps areas outside of MB's 0xEz-0xFz.
+	 */
+	uio_ev: uio@0xD0000000 {
+		compatible = "generic-uio";
+		reg = <0xD0000000 0x2000 0xD1000000 0x2000 0x90000000 0x10000000 0xC0000000 0x10000000>;
+		reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
+		interrupt-parent = <&mb_intc>;
+		interrupts = <23>;
 	};
 };
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 63a04013d05a..7bee4e4799fd 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index b65930a49589..54b54da6384c 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -17,10 +17,11 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
+#define ATOMIC_INIT(i)	{ (i) }
+
 #ifndef CONFIG_ARC_PLAT_EZNPS
 
 #define atomic_read(v)  READ_ONCE((v)->counter)
-#define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index aee1a77934cf..ac85380d14a4 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -16,6 +16,11 @@
 	;
 	; Now manually save: r12, sp, fp, gp, r25
 
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	PUSH	r59
+	PUSH	r58
+#endif
+
 	PUSH	r30
 	PUSH	r12
 
@@ -75,6 +80,11 @@
 	POP	r12
 	POP	r30
 
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	POP	r58
+	POP	r59
+#endif
+
 .endm
 
 /*------------------------------------------------------------------------*/
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 317ff773e1ca..b18fcb606908 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -11,6 +11,7 @@
 #define _ASM_ARC_HUGEPAGE_H
 
 #include <linux/types.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline pte_t pmd_pte(pmd_t pmd)
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index 00bdbe167615..2e52d18e6bc7 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -54,9 +54,7 @@ int kprobe_fault_handler(struct pt_regs *regs, unsigned long cause);
 void kretprobe_trampoline(void);
 void trap_is_kprobe(unsigned long address, struct pt_regs *regs);
 #else
-static void trap_is_kprobe(unsigned long address, struct pt_regs *regs)
-{
-}
+#define trap_is_kprobe(address, regs)
 #endif /* CONFIG_KPROBES */
 
 #endif /* _ARC_KPROBES_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index e94ca72b974e..ee22d40afef4 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -37,6 +37,7 @@
 
 #include <asm/page.h>
 #include <asm/mmu.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <linux/const.h>
 
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 47111d565a95..5297faa8a378 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -86,6 +86,10 @@ struct pt_regs {
 
 	unsigned long r12, r30;
 
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+	unsigned long r58, r59;	/* ACCL/ACCH used by FPU / DSP MPY */
+#endif
+
 	/*------- Below list auto saved by h/w -----------*/
 	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 41faf17cd28d..f35974ee7264 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -24,12 +24,10 @@
 #ifndef _ASM_ARC_UACCESS_H
 #define _ASM_ARC_UACCESS_H
 
-#include <linux/sched.h>
-#include <asm/errno.h>
 #include <linux/string.h>	/* for generic string functions */
 
 
-#define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok		(uaccess_kernel())
 
 /*
  * Algorithmically, for __user_ok() we want do:
@@ -170,7 +168,7 @@
 
 
 static inline unsigned long
-__arc_copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	long res = 0;
 	char val;
@@ -396,11 +394,8 @@ __arc_copy_from_user(void *to, const void __user *from, unsigned long n)
 	return res;
 }
 
-extern unsigned long slowpath_copy_to_user(void __user *to, const void *from,
-					   unsigned long n);
-
 static inline unsigned long
-__arc_copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	long res = 0;
 	char val;
@@ -726,24 +721,20 @@ static inline long __arc_strnlen_user(const char __user *s, long n)
 }
 
 #ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
-#define __copy_from_user(t, f, n)	__arc_copy_from_user(t, f, n)
-#define __copy_to_user(t, f, n)		__arc_copy_to_user(t, f, n)
+
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
+
 #define __clear_user(d, n)		__arc_clear_user(d, n)
 #define __strncpy_from_user(d, s, n)	__arc_strncpy_from_user(d, s, n)
 #define __strnlen_user(s, n)		__arc_strnlen_user(s, n)
 #else
-extern long arc_copy_from_user_noinline(void *to, const void __user * from,
-		unsigned long n);
-extern long arc_copy_to_user_noinline(void __user *to, const void *from,
-		unsigned long n);
 extern unsigned long arc_clear_user_noinline(void __user *to,
 		unsigned long n);
 extern long arc_strncpy_from_user_noinline (char *dst, const char __user *src,
 		long count);
 extern long arc_strnlen_user_noinline(const char __user *src, long n);
 
-#define __copy_from_user(t, f, n)	arc_copy_from_user_noinline(t, f, n)
-#define __copy_to_user(t, f, n)		arc_copy_to_user_noinline(t, f, n)
 #define __clear_user(d, n)		arc_clear_user_noinline(d, n)
 #define __strncpy_from_user(d, s, n)	arc_strncpy_from_user_noinline(d, s, n)
 #define __strnlen_user(s, n)		arc_strnlen_user_noinline(s, n)
@@ -752,6 +743,4 @@ extern long arc_strnlen_user_noinline(const char __user *src, long n);
 
 #include <asm-generic/uaccess.h>
 
-extern int fixup_exception(struct pt_regs *regs);
-
 #endif
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index 2585632eaa68..cc558a25b8fa 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -100,15 +100,21 @@ END(handle_interrupt)
 ;################### Non TLB Exception Handling #############################
 
 ENTRY(EV_SWI)
-	flag 1
+	; TODO: implement this
+	EXCEPTION_PROLOGUE
+	b   ret_from_exception
 END(EV_SWI)
 
 ENTRY(EV_DivZero)
-	flag 1
+	; TODO: implement this
+	EXCEPTION_PROLOGUE
+	b   ret_from_exception
 END(EV_DivZero)
 
 ENTRY(EV_DCError)
-	flag 1
+	; TODO: implement this
+	EXCEPTION_PROLOGUE
+	b   ret_from_exception
 END(EV_DCError)
 
 ; ---------------------------------------------
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 3093fa898a23..fc8211f338ad 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/delay.h>
 #include <linux/root_dev.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clocksource.h>
 #include <linux/console.h>
@@ -318,7 +319,8 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 static void arc_chk_core_config(void)
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
-	int fpu_enabled;
+	int saved = 0, present = 0;
+	char *opt_nm = NULL;;
 
 	if (!cpu->extn.timer0)
 		panic("Timer0 is not present!\n");
@@ -345,17 +347,28 @@ static void arc_chk_core_config(void)
 
 	/*
 	 * FP hardware/software config sanity
-	 * -If hardware contains DPFP, kernel needs to save/restore FPU state
+	 * -If hardware present, kernel needs to save/restore FPU state
 	 * -If not, it will crash trying to save/restore the non-existant regs
-	 *
-	 * (only DPDP checked since SP has no arch visible regs)
 	 */
-	fpu_enabled = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE);
 
-	if (cpu->extn.fpu_dp && !fpu_enabled)
-		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
-	else if (!cpu->extn.fpu_dp && fpu_enabled)
-		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
+	if (is_isa_arcompact()) {
+		opt_nm = "CONFIG_ARC_FPU_SAVE_RESTORE";
+		saved = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE);
+
+		/* only DPDP checked since SP has no arch visible regs */
+		present = cpu->extn.fpu_dp;
+	} else {
+		opt_nm = "CONFIG_ARC_HAS_ACCL_REGS";
+		saved = IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS);
+
+		/* Accumulator Low:High pair (r58:59) present if DSP MPY or FPU */
+		present = cpu->extn_mpy.dsp | cpu->extn.fpu_sp | cpu->extn.fpu_dp;
+	}
+
+	if (present && !saved)
+		pr_warn("Enable %s for working apps\n", opt_nm);
+	else if (!present && saved)
+		panic("Disable %s, hardware NOT present\n", opt_nm);
 }
 
 /*
@@ -488,8 +501,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	char *str;
 	int cpu_id = ptr_to_cpu(v);
-	struct device_node *core_clk = of_find_node_by_name(NULL, "core_clk");
-	u32 freq = 0;
+	struct device *cpu_dev = get_cpu_device(cpu_id);
+	struct clk *cpu_clk;
+	unsigned long freq = 0;
 
 	if (!cpu_online(cpu_id)) {
 		seq_printf(m, "processor [%d]\t: Offline\n", cpu_id);
@@ -502,9 +516,15 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 
 	seq_printf(m, arc_cpu_mumbojumbo(cpu_id, str, PAGE_SIZE));
 
-	of_property_read_u32(core_clk, "clock-frequency", &freq);
+	cpu_clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(cpu_clk)) {
+		seq_printf(m, "CPU speed \t: Cannot get clock for processor [%d]\n",
+			   cpu_id);
+	} else {
+		freq = clk_get_rate(cpu_clk);
+	}
 	if (freq)
-		seq_printf(m, "CPU speed\t: %u.%02u Mhz\n",
+		seq_printf(m, "CPU speed\t: %lu.%02lu Mhz\n",
 			   freq / 1000000, (freq / 10000) % 100);
 
 	seq_printf(m, "Bogo MIPS\t: %lu.%02lu\n",
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index d408fa21a07c..928562967f3c 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -633,6 +633,9 @@ noinline static void slc_entire_op(const int op)
 
 	write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
 
+	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
+	read_aux_reg(r);
+
 	/* Important to wait for flush to complete */
 	while (read_aux_reg(r) & SLC_CTRL_BUSY);
 }
diff --git a/arch/arc/mm/extable.c b/arch/arc/mm/extable.c
index c86906b41bfe..72125a34e780 100644
--- a/arch/arc/mm/extable.c
+++ b/arch/arc/mm/extable.c
@@ -28,20 +28,6 @@ int fixup_exception(struct pt_regs *regs)
 
 #ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 
-long arc_copy_from_user_noinline(void *to, const void __user *from,
-		unsigned long n)
-{
-	return __arc_copy_from_user(to, from, n);
-}
-EXPORT_SYMBOL(arc_copy_from_user_noinline);
-
-long arc_copy_to_user_noinline(void __user *to, const void *from,
-		unsigned long n)
-{
-	return __arc_copy_to_user(to, from, n);
-}
-EXPORT_SYMBOL(arc_copy_to_user_noinline);
-
 unsigned long arc_clear_user_noinline(void __user *to,
 		unsigned long n)
 {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0d4e71b42c77..8a7ab5e73af9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -41,7 +41,6 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi
index efb5eae290a8..d42b98f15e8b 100644
--- a/arch/arm/boot/dts/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/am335x-baltos.dtsi
@@ -371,6 +371,8 @@
 
 	phy1: ethernet-phy@1 {
 		reg = <7>;
+		eee-broken-100tx;
+		eee-broken-1000t;
 	};
 };
 
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 9e43c443738a..9ba4b18c0cb2 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -672,6 +672,7 @@
 	ti,non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
+	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins>;
 
diff --git a/arch/arm/boot/dts/am335x-pcm-953.dtsi b/arch/arm/boot/dts/am335x-pcm-953.dtsi
index 02981eae96b9..1ec8e0d80191 100644
--- a/arch/arm/boot/dts/am335x-pcm-953.dtsi
+++ b/arch/arm/boot/dts/am335x-pcm-953.dtsi
@@ -63,14 +63,14 @@
 			label = "home";
 			linux,code = <KEY_HOME>;
 			gpios = <&gpio3 7 GPIO_ACTIVE_HIGH>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button@1 {
 			label = "menu";
 			linux,code = <KEY_MENU>;
 			gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 	};
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index 0d341c545b01..e5ac1d81d15c 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -315,6 +315,13 @@
 			/* ID & VBUS GPIOs provided in board dts */
 		};
 	};
+
+	tpic2810: tpic2810@60 {
+		compatible = "ti,tpic2810";
+		reg = <0x60>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
 };
 
 &mcspi3 {
@@ -330,13 +337,6 @@
 		spi-max-frequency = <1000000>;
 		spi-cpol;
 	};
-
-	tpic2810: tpic2810@60 {
-		compatible = "ti,tpic2810";
-		reg = <0x60>;
-		gpio-controller;
-		#gpio-cells = <2>;
-	};
 };
 
 &uart3 {
diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi
index 0b4932cc02a8..c79c937b0a8a 100644
--- a/arch/arm/boot/dts/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed-g4.dtsi
@@ -42,18 +42,16 @@
 		};
 
 		mac0: ethernet@1e660000 {
-			compatible = "faraday,ftgmac100";
+			compatible = "aspeed,ast2400-mac", "faraday,ftgmac100";
 			reg = <0x1e660000 0x180>;
 			interrupts = <2>;
-			no-hw-checksum;
 			status = "disabled";
 		};
 
 		mac1: ethernet@1e680000 {
-			compatible = "faraday,ftgmac100";
+			compatible = "aspeed,ast2400-mac", "faraday,ftgmac100";
 			reg = <0x1e680000 0x180>;
 			interrupts = <3>;
-			no-hw-checksum;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi
index b664fe380936..b6596633036c 100644
--- a/arch/arm/boot/dts/aspeed-g5.dtsi
+++ b/arch/arm/boot/dts/aspeed-g5.dtsi
@@ -33,18 +33,16 @@
 		};
 
 		mac0: ethernet@1e660000 {
-			compatible = "faraday,ftgmac100";
+			compatible = "aspeed,ast2500-mac", "faraday,ftgmac100";
 			reg = <0x1e660000 0x180>;
 			interrupts = <2>;
-			no-hw-checksum;
 			status = "disabled";
 		};
 
 		mac1: ethernet@1e680000 {
-			compatible = "faraday,ftgmac100";
+			compatible = "aspeed,ast2500-mac", "faraday,ftgmac100";
 			reg = <0x1e680000 0x180>;
 			interrupts = <3>;
-			no-hw-checksum;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 4fbb089cf5ad..00de62dc0042 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -66,14 +66,14 @@
 		timer@20200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x20200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&periph_clk>;
 		};
 
 		local-timer@20600 {
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x20600 0x100>;
-			interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&periph_clk>;
 		};
 
diff --git a/arch/arm/boot/dts/bcm953012k.dts b/arch/arm/boot/dts/bcm953012k.dts
index bfd923096a8c..ae31a5826e91 100644
--- a/arch/arm/boot/dts/bcm953012k.dts
+++ b/arch/arm/boot/dts/bcm953012k.dts
@@ -48,15 +48,14 @@
 	};
 
 	memory {
-		reg = <0x00000000 0x10000000>;
+		reg = <0x80000000 0x10000000>;
 	};
 };
 
 &uart0 {
-	clock-frequency = <62499840>;
+	status = "okay";
 };
 
 &uart1 {
-	clock-frequency = <62499840>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts
index 3f04a40eb90c..df05e7f568af 100644
--- a/arch/arm/boot/dts/bcm958522er.dts
+++ b/arch/arm/boot/dts/bcm958522er.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts
index 9fd542200d3d..4a3ab19c6281 100644
--- a/arch/arm/boot/dts/bcm958525er.dts
+++ b/arch/arm/boot/dts/bcm958525er.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts
index 41e7fd350fcd..81f78435d8c7 100644
--- a/arch/arm/boot/dts/bcm958525xmc.dts
+++ b/arch/arm/boot/dts/bcm958525xmc.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 31 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts
index 477c4860db52..c88b8fefcb2f 100644
--- a/arch/arm/boot/dts/bcm958622hr.dts
+++ b/arch/arm/boot/dts/bcm958622hr.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts
index c0a499d5ba44..d503fa0dde31 100644
--- a/arch/arm/boot/dts/bcm958623hr.dts
+++ b/arch/arm/boot/dts/bcm958623hr.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index f7eb5854a224..cc0363b843c1 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm988312hr.dts b/arch/arm/boot/dts/bcm988312hr.dts
index 16666324fda8..74e15a3cd9f8 100644
--- a/arch/arm/boot/dts/bcm988312hr.dts
+++ b/arch/arm/boot/dts/bcm988312hr.dts
@@ -55,6 +55,7 @@
 	gpio-restart {
 		compatible = "gpio-restart";
 		gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+		open-source;
 		priority = <200>;
 	};
 };
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 2c9e56f4aac5..bbfb9d5a70a9 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -283,6 +283,7 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x20013000 0x13000 0 0xffed000>;
+				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
 				linux,pci-domain = <0>;
@@ -319,6 +320,7 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x30013000 0x13000 0 0xffed000>;
+				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
 				linux,pci-domain = <1>;
diff --git a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi
index 49f466fe0b1d..dcfc97591433 100644
--- a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi
+++ b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi
@@ -121,11 +121,6 @@
 	};
 };
 
-&cpu0 {
-	arm-supply = <&sw1a_reg>;
-	soc-supply = <&sw1c_reg>;
-};
-
 &fec1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet1>;
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 8f9a69ca818c..efe53998c961 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -121,7 +121,7 @@
 &i2c3 {
 	clock-frequency = <400000>;
 	at24@50 {
-		compatible = "at24,24c02";
+		compatible = "atmel,24c64";
 		readonly;
 		reg = <0x50>;
 	};
diff --git a/arch/arm/boot/dts/rk1108.dtsi b/arch/arm/boot/dts/rk1108.dtsi
index d6194bff7afe..6c8fc19d0ecd 100644
--- a/arch/arm/boot/dts/rk1108.dtsi
+++ b/arch/arm/boot/dts/rk1108.dtsi
@@ -222,7 +222,7 @@
 	};
 
 	pinctrl: pinctrl {
-		compatible = "rockchip,rk1108-pinctrl";
+		compatible = "rockchip,rv1108-pinctrl";
 		rockchip,grf = <&grf>;
 		rockchip,pmu = <&pmugrf>;
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/rk3188.dtsi b/arch/arm/boot/dts/rk3188.dtsi
index cf91254d0a43..1aff4ad22fc4 100644
--- a/arch/arm/boot/dts/rk3188.dtsi
+++ b/arch/arm/boot/dts/rk3188.dtsi
@@ -106,6 +106,22 @@
 		};
 	};
 
+	timer3: timer@2000e000 {
+		compatible = "rockchip,rk3188-timer", "rockchip,rk3288-timer";
+		reg = <0x2000e000 0x20>;
+		interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru SCLK_TIMER3>, <&cru PCLK_TIMER3>;
+		clock-names = "timer", "pclk";
+	};
+
+	timer6: timer@200380a0 {
+		compatible = "rockchip,rk3188-timer", "rockchip,rk3288-timer";
+		reg = <0x200380a0 0x20>;
+		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru SCLK_TIMER6>, <&cru PCLK_TIMER0>;
+		clock-names = "timer", "pclk";
+	};
+
 	i2s0: i2s@1011a000 {
 		compatible = "rockchip,rk3188-i2s", "rockchip,rk3066-i2s";
 		reg = <0x1011a000 0x2000>;
@@ -530,6 +546,7 @@
 
 &global_timer {
 	interrupts = <GIC_PPI 11 0xf04>;
+	status = "disabled";
 };
 
 &local_timer {
diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index 9dff8221112c..641607d9ad29 100644
--- a/arch/arm/boot/dts/rk322x.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -325,7 +325,7 @@
 	};
 
 	timer: timer@110c0000 {
-		compatible = "rockchip,rk3288-timer";
+		compatible = "rockchip,rk3228-timer", "rockchip,rk3288-timer";
 		reg = <0x110c0000 0x20>;
 		interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&xin24m>, <&cru PCLK_TIMER>;
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 22332be72140..528b4e9c6d3d 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -266,7 +266,7 @@
 		};
 
 		usb1: ohci@00400000 {
-			compatible = "atmel,sama5d2-ohci", "usb-ohci";
+			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00400000 0x100000>;
 			interrupts = <41 IRQ_TYPE_LEVEL_HIGH 2>;
 			clocks = <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index 82d8c4771293..6c5affe2d0f5 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -14,6 +14,7 @@
 #include <dt-bindings/mfd/dbx500-prcmu.h>
 #include <dt-bindings/arm/ux500_pm_domains.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/clock/ste-ab8500.h>
 #include "skeleton.dtsi"
 
 / {
@@ -603,6 +604,11 @@
 				interrupt-controller;
 				#interrupt-cells = <2>;
 
+				ab8500_clock: clock-controller {
+					compatible = "stericsson,ab8500-clk";
+					#clock-cells = <1>;
+				};
+
 				ab8500_gpio: ab8500-gpio {
 					compatible = "stericsson,ab8500-gpio";
 					gpio-controller;
@@ -686,6 +692,8 @@
 
 				ab8500-pwm {
 					compatible = "stericsson,ab8500-pwm";
+					clocks = <&ab8500_clock AB8500_SYSCLK_INT>;
+					clock-names = "intclk";
 				};
 
 				ab8500-debugfs {
@@ -700,6 +708,9 @@
 					V-AMIC2-supply = <&ab8500_ldo_anamic2_reg>;
 					V-DMIC-supply = <&ab8500_ldo_dmic_reg>;
 
+					clocks = <&ab8500_clock AB8500_SYSCLK_AUDIO>;
+					clock-names = "audioclk";
+
 					stericsson,earpeice-cmv = <950>; /* Units in mV. */
 				};
 
@@ -1095,6 +1106,14 @@
 			status = "disabled";
 		};
 
+		sound {
+			compatible = "stericsson,snd-soc-mop500";
+			stericsson,cpu-dai = <&msp1 &msp3>;
+			stericsson,audio-codec = <&codec>;
+			clocks = <&prcmu_clk PRCMU_SYSCLK>, <&ab8500_clock AB8500_SYSCLK_ULP>, <&ab8500_clock AB8500_SYSCLK_INT>;
+			clock-names = "sysclk", "ulpclk", "intclk";
+		};
+
 		msp0: msp@80123000 {
 			compatible = "stericsson,ux500-msp-i2s";
 			reg = <0x80123000 0x1000>;
@@ -1170,11 +1189,6 @@
 			status = "disabled";
 		};
 
-		cpufreq-cooling {
-			compatible = "stericsson,db8500-cpufreq-cooling";
-			status = "disabled";
-		};
-
 		mcde@a0350000 {
 			compatible = "stericsson,mcde";
 			reg = <0xa0350000 0x1000>, /* MCDE */
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index f37f9e10713c..9e359e4f342e 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -186,15 +186,6 @@
 			status = "okay";
 		};
 
-		sound {
-			compatible = "stericsson,snd-soc-mop500";
-
-			stericsson,cpu-dai = <&msp1 &msp3>;
-			stericsson,audio-codec = <&codec>;
-			clocks = <&prcmu_clk PRCMU_SYSCLK>;
-			clock-names = "sysclk";
-		};
-
 		msp0: msp@80123000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&msp0_default_mode>;
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index dd5514def604..ade1d0d4e5f4 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -159,15 +159,6 @@
 				     "", "", "", "", "", "", "", "";
 		};
 
-		sound {
-			compatible = "stericsson,snd-soc-mop500";
-
-			stericsson,cpu-dai = <&msp1 &msp3>;
-			stericsson,audio-codec = <&codec>;
-			clocks = <&prcmu_clk PRCMU_SYSCLK>;
-			clock-names = "sysclk";
-		};
-
 		msp0: msp@80123000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&msp0_default_mode>;
diff --git a/arch/arm/boot/dts/stm32746g-eval.dts b/arch/arm/boot/dts/stm32746g-eval.dts
index aa03fac1ec55..0dc18a0f0940 100644
--- a/arch/arm/boot/dts/stm32746g-eval.dts
+++ b/arch/arm/boot/dts/stm32746g-eval.dts
@@ -89,6 +89,10 @@
 	clock-frequency = <25000000>;
 };
 
+&crc {
+	status = "okay";
+};
+
 &usart1 {
 	pinctrl-0 = <&usart1_pins_a>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/stm32f746.dtsi b/arch/arm/boot/dts/stm32f746.dtsi
index f321ffe87144..755fb923c07b 100644
--- a/arch/arm/boot/dts/stm32f746.dtsi
+++ b/arch/arm/boot/dts/stm32f746.dtsi
@@ -289,6 +289,13 @@
 			};
 		};
 
+		crc: crc@40023000 {
+			compatible = "st,stm32f7-crc";
+			reg = <0x40023000 0x400>;
+			clocks = <&rcc 0 12>;
+			status = "disabled";
+		};
+
 		rcc: rcc@40023800 {
 			#clock-cells = <2>;
 			compatible = "st,stm32f42xx-rcc", "st,stm32-rcc";
diff --git a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
index 72ec0d5ae052..bbf1c8cbaac6 100644
--- a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
+++ b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
@@ -167,7 +167,7 @@
 					reg = <8>;
 					label = "cpu";
 					ethernet = <&gmac>;
-					phy-mode = "rgmii";
+					phy-mode = "rgmii-txid";
 					fixed-link {
 						speed = <1000>;
 						full-duplex;
diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
index a952cc0703cc..8a3ed21cb7bc 100644
--- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
@@ -495,7 +495,7 @@
 			resets = <&ccu RST_BUS_GPU>;
 
 			assigned-clocks = <&ccu CLK_GPU>;
-			assigned-clock-rates = <408000000>;
+			assigned-clock-rates = <384000000>;
 		};
 
 		gic: interrupt-controller@01c81000 {
diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi
index 18c174fef84f..306af6cadf26 100644
--- a/arch/arm/boot/dts/sun8i-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a33.dtsi
@@ -66,12 +66,6 @@
 			opp-microvolt = <1200000>;
 			clock-latency-ns = <244144>; /* 8 32k periods */
 		};
-
-		opp@1200000000 {
-			opp-hz = /bits/ 64 <1200000000>;
-			opp-microvolt = <1320000>;
-			clock-latency-ns = <244144>; /* 8 32k periods */
-		};
 	};
 
 	cpus {
@@ -81,16 +75,22 @@
 			operating-points-v2 = <&cpu0_opp_table>;
 		};
 
+		cpu@1 {
+			operating-points-v2 = <&cpu0_opp_table>;
+		};
+
 		cpu@2 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <2>;
+			operating-points-v2 = <&cpu0_opp_table>;
 		};
 
 		cpu@3 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <3>;
+			operating-points-v2 = <&cpu0_opp_table>;
 		};
 	};
 
@@ -113,8 +113,8 @@
 		simple-audio-card,mclk-fs = <512>;
 		simple-audio-card,aux-devs = <&codec_analog>;
 		simple-audio-card,routing =
-			"Left DAC", "Digital Left DAC",
-			"Right DAC", "Digital Right DAC";
+			"Left DAC", "AIF1 Slot 0 Left",
+			"Right DAC", "AIF1 Slot 0 Right";
 		status = "disabled";
 
 		simple-audio-card,cpu {
diff --git a/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi b/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
index 7097c18ff487..d6bd15898db6 100644
--- a/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
+++ b/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
@@ -50,8 +50,6 @@
 
 	backlight: backlight {
 		compatible = "pwm-backlight";
-		pinctrl-names = "default";
-		pinctrl-0 = <&bl_en_pin>;
 		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
 		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
 		default-brightness-level = <8>;
@@ -93,11 +91,6 @@
 };
 
 &pio {
-	bl_en_pin: bl_en_pin@0 {
-		pins = "PH6";
-		function = "gpio_in";
-	};
-
 	mmc0_cd_pin: mmc0_cd_pin@0 {
 		pins = "PB4";
 		function = "gpio_in";
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index a94126fb02c2..6aa7be191f1a 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -748,7 +748,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_LEDS_TRIGGER_TRANSIENT=y
 CONFIG_LEDS_TRIGGER_CAMERA=y
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_HIGHBANK_MC=y
 CONFIG_EDAC_HIGHBANK_L2=y
 CONFIG_RTC_CLASS=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index f2462a6bdba6..decd388d613d 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -188,6 +188,7 @@ CONFIG_WL12XX=m
 CONFIG_WL18XX=m
 CONFIG_WLCORE_SPI=m
 CONFIG_WLCORE_SDIO=m
+CONFIG_INPUT_MOUSEDEV=m
 CONFIG_INPUT_JOYDEV=m
 CONFIG_INPUT_EVDEV=m
 CONFIG_KEYBOARD_ATKBD=m
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 2aac99fd1c41..1318f61589dc 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -635,8 +635,7 @@ CONFIG_LEDS_TRIGGER_GPIO=m
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
 CONFIG_LEDS_TRIGGER_TRANSIENT=m
 CONFIG_LEDS_TRIGGER_CAMERA=m
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=m
+CONFIG_EDAC=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DEBUG=y
 CONFIG_RTC_DRV_DS1307=m
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index a9d8e3c9b487..03437f8f9ad1 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -75,5 +75,7 @@ CONFIG_MAGIC_SYSRQ=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_BUGVERBOSE is not set
 # CONFIG_FTRACE is not set
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_DEV_STM32=y
 CONFIG_CRC_ITU_T=y
 CONFIG_CRC7=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index a8fce93137fb..b9adedcc5b2e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -73,7 +73,7 @@ config CRYPTO_AES_ARM_BS
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_SIMD
-	select CRYPTO_AES_ARM
+	select CRYPTO_AES
 	help
 	  Use a faster and more secure NEON based implementation of AES in CBC,
 	  CTR and XTS modes
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index 2920b96dbd36..c76377961444 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -42,9 +42,6 @@ asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
 asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]);
 
-asmlinkage void __aes_arm_encrypt(const u32 rk[], int rounds, const u8 in[],
-				  u8 out[]);
-
 struct aesbs_ctx {
 	int	rounds;
 	u8	rk[13 * (8 * AES_BLOCK_SIZE) + 32] __aligned(AES_BLOCK_SIZE);
@@ -52,12 +49,12 @@ struct aesbs_ctx {
 
 struct aesbs_cbc_ctx {
 	struct aesbs_ctx	key;
-	u32			enc[AES_MAX_KEYLENGTH_U32];
+	struct crypto_cipher	*enc_tfm;
 };
 
 struct aesbs_xts_ctx {
 	struct aesbs_ctx	key;
-	u32			twkey[AES_MAX_KEYLENGTH_U32];
+	struct crypto_cipher	*tweak_tfm;
 };
 
 static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
@@ -132,20 +129,18 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 
 	ctx->key.rounds = 6 + key_len / 4;
 
-	memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc));
-
 	kernel_neon_begin();
 	aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
 	kernel_neon_end();
 
-	return 0;
+	return crypto_cipher_setkey(ctx->enc_tfm, in_key, key_len);
 }
 
 static void cbc_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
 {
 	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	__aes_arm_encrypt(ctx->enc, ctx->key.rounds, src, dst);
+	crypto_cipher_encrypt_one(ctx->enc_tfm, dst, src);
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
@@ -181,6 +176,23 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
+static int cbc_init(struct crypto_tfm *tfm)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->enc_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(ctx->enc_tfm))
+		return PTR_ERR(ctx->enc_tfm);
+	return 0;
+}
+
+static void cbc_exit(struct crypto_tfm *tfm)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_cipher(ctx->enc_tfm);
+}
+
 static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -228,7 +240,6 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_aes_ctx rk;
 	int err;
 
 	err = xts_verify_key(tfm, in_key, key_len);
@@ -236,15 +247,30 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 		return err;
 
 	key_len /= 2;
-	err = crypto_aes_expand_key(&rk, in_key + key_len, key_len);
+	err = crypto_cipher_setkey(ctx->tweak_tfm, in_key + key_len, key_len);
 	if (err)
 		return err;
 
-	memcpy(ctx->twkey, rk.key_enc, sizeof(ctx->twkey));
-
 	return aesbs_setkey(tfm, in_key, key_len);
 }
 
+static int xts_init(struct crypto_tfm *tfm)
+{
+	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->tweak_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(ctx->tweak_tfm))
+		return PTR_ERR(ctx->tweak_tfm);
+	return 0;
+}
+
+static void xts_exit(struct crypto_tfm *tfm)
+{
+	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_cipher(ctx->tweak_tfm);
+}
+
 static int __xts_crypt(struct skcipher_request *req,
 		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]))
@@ -256,7 +282,7 @@ static int __xts_crypt(struct skcipher_request *req,
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	__aes_arm_encrypt(ctx->twkey, ctx->key.rounds, walk.iv, walk.iv);
+	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 
 	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
@@ -309,6 +335,8 @@ static struct skcipher_alg aes_algs[] = { {
 	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_init		= cbc_init,
+	.base.cra_exit		= cbc_exit,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -342,6 +370,8 @@ static struct skcipher_alg aes_algs[] = { {
 	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_init		= xts_init,
+	.base.cra_exit		= xts_exit,
 
 	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
@@ -402,5 +432,5 @@ unregister_simds:
 	return err;
 }
 
-module_init(aes_init);
+late_initcall(aes_init);
 module_exit(aes_exit);
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index b14e8c7d71bd..3a36d99ff836 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index e4e6a9d6a825..17f1f1a814ff 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -85,6 +85,18 @@ static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
  */
 #define ZIMAGE_OFFSET_LIMIT	SZ_128M
 #define MIN_ZIMAGE_OFFSET	MAX_UNCOMP_KERNEL_SIZE
-#define MAX_FDT_OFFSET		ZIMAGE_OFFSET_LIMIT
+
+/* on ARM, the FDT should be located in the first 128 MB of RAM */
+static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
+{
+	return dram_base + ZIMAGE_OFFSET_LIMIT;
+}
+
+/* on ARM, the initrd should be loaded in a lowmem region */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
+						    unsigned long image_addr)
+{
+	return dram_base + SZ_512M;
+}
 
 #endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index e22089fb44dc..a3f0b3d50089 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -209,6 +209,7 @@
 #define HSR_EC_IABT_HYP	(0x21)
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
+#define HSR_EC_MAX	(0x3f)
 
 #define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index cc495d799c67..31ee468ce667 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -30,7 +30,6 @@
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
 #define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
 #define KVM_HALT_POLL_NS_DEFAULT 500000
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index a8d656d9aec7..1c462381c225 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -20,6 +20,7 @@
 
 #else
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index b7e0125c0bbf..2577405d082d 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -12,8 +12,6 @@
  * User space memory access functions
  */
 #include <linux/string.h>
-#include <linux/thread_info.h>
-#include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/domain.h>
 #include <asm/unified.h>
@@ -26,28 +24,7 @@
 #define __put_user_unaligned __put_user
 #endif
 
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 /*
  * These two functions allow hooking accesses to userspace to increase
@@ -271,7 +248,7 @@ static inline void set_fs(mm_segment_t fs)
 #define access_ok(type, addr, size)	(__range_ok(addr, size) == 0)
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
+	(uaccess_kernel() ? ~0UL : get_fs())
 
 /*
  * The "__xxx" versions of the user access functions do not verify the
@@ -478,7 +455,7 @@ extern unsigned long __must_check
 arm_copy_from_user(void *to, const void __user *from, unsigned long n);
 
 static inline unsigned long __must_check
-__arch_copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned int __ua_flags;
 
@@ -494,7 +471,7 @@ extern unsigned long __must_check
 __copy_to_user_std(void __user *to, const void *from, unsigned long n);
 
 static inline unsigned long __must_check
-__arch_copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 #ifndef CONFIG_UACCESS_WITH_MEMCPY
 	unsigned int __ua_flags;
@@ -522,54 +499,22 @@ __clear_user(void __user *addr, unsigned long n)
 }
 
 #else
-#define __arch_copy_from_user(to, from, n)	\
-					(memcpy(to, (void __force *)from, n), 0)
-#define __arch_copy_to_user(to, from, n)	\
-					(memcpy((void __force *)to, from, n), 0)
-#define __clear_user(addr, n)		(memset((void __force *)addr, 0, n), 0)
-#endif
-
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	check_object_size(to, n, false);
-	return __arch_copy_from_user(to, from, n);
-}
-
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	unsigned long res = n;
-
-	check_object_size(to, n, false);
-
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		res = __arch_copy_from_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
-}
-
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	check_object_size(from, n, true);
-
-	return __arch_copy_to_user(to, from, n);
+	memcpy(to, (const void __force *)from, n);
+	return 0;
 }
-
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	check_object_size(from, n, true);
-
-	if (access_ok(VERIFY_WRITE, to, n))
-		n = __arch_copy_to_user(to, from, n);
-	return n;
+	memcpy((void __force *)to, from, n);
+	return 0;
 }
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define __clear_user(addr, n)		(memset((void __force *)addr, 0, n), 0)
+#endif
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
 
 static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 37b2a11af345..8265b116218d 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -242,6 +242,8 @@ SECTIONS
 	}
 	_edata_loc = __data_loc + SIZEOF(.data);
 
+	BUG_TABLE
+
 #ifdef CONFIG_HAVE_TCM
         /*
 	 * We align everything to a page boundary so we can
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index ce18007f9e4e..c83a7ba737d6 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -262,6 +262,8 @@ SECTIONS
 	}
 	_edata_loc = __data_loc + SIZEOF(.data);
 
+	BUG_TABLE
+
 #ifdef CONFIG_HAVE_TCM
         /*
 	 * We align everything to a page boundary so we can
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index c9a2103faeb9..314eb6abe1ff 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -221,6 +221,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
 	case KVM_CAP_MSI_DEVID:
 		if (!kvm)
 			r = -EINVAL;
@@ -1121,6 +1124,9 @@ static void cpu_hyp_reinit(void)
 		if (__hyp_get_vectors() == hyp_default_vectors)
 			cpu_init_hyp_mode(NULL);
 	}
+
+	if (vgic_present)
+		kvm_vgic_init_cpu_hardware();
 }
 
 static void cpu_hyp_reset(void)
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 4e40d1955e35..96af65a30d78 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -79,7 +79,19 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n",
+		      hsr);
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... HSR_EC_MAX]	= kvm_handle_unknown_ec,
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -98,13 +110,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
 	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x\n",
-			(unsigned int)kvm_vcpu_get_hsr(vcpu));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 962616fd4ddd..582a972371cf 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -292,11 +292,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
+	assert_spin_locked(&kvm->mmu_lock);
 	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
 	do {
 		next = stage2_pgd_addr_end(addr, end);
 		if (!stage2_pgd_none(*pgd))
 			unmap_stage2_puds(kvm, pgd, addr, next);
+		/*
+		 * If the range is too large, release the kvm->mmu_lock
+		 * to prevent starvation and lockup detector warnings.
+		 */
+		if (next != end)
+			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -803,6 +810,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
+	down_read(&current->mm->mmap_sem);
 	spin_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
@@ -810,6 +818,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 		stage2_unmap_memslot(kvm, memslot);
 
 	spin_unlock(&kvm->mmu_lock);
+	up_read(&current->mm->mmap_sem);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -829,7 +838,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 	if (kvm->arch.pgd == NULL)
 		return;
 
+	spin_lock(&kvm->mmu_lock);
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	spin_unlock(&kvm->mmu_lock);
+
 	/* Free the HW pgd, one page at a time */
 	free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
 	kvm->arch.pgd = NULL;
@@ -1801,6 +1813,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
 		return -EFAULT;
 
+	down_read(&current->mm->mmap_sem);
 	/*
 	 * A memory region could potentially cover multiple VMAs, and any holes
 	 * between them, so iterate over all of them to find out if we can map
@@ -1844,8 +1857,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 			pa += vm_start - vma->vm_start;
 
 			/* IO region dirty page logging not allowed */
-			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
-				return -EINVAL;
+			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+				ret = -EINVAL;
+				goto out;
+			}
 
 			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
 						    vm_end - vm_start,
@@ -1857,7 +1872,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	} while (hva < reg_end);
 
 	if (change == KVM_MR_FLAGS_ONLY)
-		return ret;
+		goto out;
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
@@ -1865,6 +1880,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	else
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
+out:
+	up_read(&current->mm->mmap_sem);
 	return ret;
 }
 
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 6bd1089b07e0..9b4ed1728616 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -90,7 +90,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 	unsigned long ua_flags;
 	int atomic;
 
-	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
+	if (uaccess_kernel()) {
 		memcpy((void *)to, from, n);
 		return 0;
 	}
@@ -162,7 +162,7 @@ __clear_user_memset(void __user *addr, unsigned long n)
 {
 	unsigned long ua_flags;
 
-	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
+	if (uaccess_kernel()) {
 		memset((void *)addr, 0, n);
 		return 0;
 	}
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 3d89b7905bd9..a277981f414d 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -289,6 +289,22 @@ static void at91_ddr_standby(void)
 		at91_ramc_write(1, AT91_DDRSDRC_LPR, saved_lpr1);
 }
 
+static void sama5d3_ddr_standby(void)
+{
+	u32 lpr0;
+	u32 saved_lpr0;
+
+	saved_lpr0 = at91_ramc_read(0, AT91_DDRSDRC_LPR);
+	lpr0 = saved_lpr0 & ~AT91_DDRSDRC_LPCB;
+	lpr0 |= AT91_DDRSDRC_LPCB_POWER_DOWN;
+
+	at91_ramc_write(0, AT91_DDRSDRC_LPR, lpr0);
+
+	cpu_do_idle();
+
+	at91_ramc_write(0, AT91_DDRSDRC_LPR, saved_lpr0);
+}
+
 /* We manage both DDRAM/SDRAM controllers, we need more than one value to
  * remember.
  */
@@ -323,7 +339,7 @@ static const struct of_device_id const ramc_ids[] __initconst = {
 	{ .compatible = "atmel,at91rm9200-sdramc", .data = at91rm9200_standby },
 	{ .compatible = "atmel,at91sam9260-sdramc", .data = at91sam9_sdram_standby },
 	{ .compatible = "atmel,at91sam9g45-ddramc", .data = at91_ddr_standby },
-	{ .compatible = "atmel,sama5d3-ddramc", .data = at91_ddr_standby },
+	{ .compatible = "atmel,sama5d3-ddramc", .data = sama5d3_ddr_standby },
 	{ /*sentinel*/ }
 };
 
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index f69e28b85e88..70db2abf6163 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -3,8 +3,8 @@ menuconfig ARCH_MOXART
 	depends on ARCH_MULTI_V4
 	select CPU_FA526
 	select ARM_DMA_MEM_BUFFERABLE
+	select FARADAY_FTINTC010
 	select MOXART_TIMER
-	select GENERIC_IRQ_CHIP
 	select GPIOLIB
 	select PHYLIB if NETDEVICES
 	help
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 093458b62c8d..c89757abb0ae 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -241,6 +241,3 @@ obj-$(CONFIG_MACH_OMAP2_TUSB6010)	+= usb-tusb6010.o
 
 onenand-$(CONFIG_MTD_ONENAND_OMAP2)	:= gpmc-onenand.o
 obj-y					+= $(onenand-m) $(onenand-y)
-
-nand-$(CONFIG_MTD_NAND_OMAP2)		:= gpmc-nand.o
-obj-y					+= $(nand-m) $(nand-y)
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index c4f2ace91ea2..3089d3bfa19b 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -270,6 +270,7 @@ extern const struct smp_operations omap4_smp_ops;
 extern int omap4_mpuss_init(void);
 extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state);
 extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state);
+extern u32 omap4_get_cpu1_ns_pa_addr(void);
 #else
 static inline int omap4_enter_lowpower(unsigned int cpu,
 					unsigned int power_state)
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
deleted file mode 100644
index f6ac027f3c3b..000000000000
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ /dev/null
@@ -1,154 +0,0 @@
-/*
- * gpmc-nand.c
- *
- * Copyright (C) 2009 Texas Instruments
- * Vimal Singh <vimalsingh@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/omap-gpmc.h>
-#include <linux/mtd/nand.h>
-#include <linux/platform_data/mtd-nand-omap2.h>
-
-#include <asm/mach/flash.h>
-
-#include "soc.h"
-
-/* minimum size for IO mapping */
-#define	NAND_IO_SIZE	4
-
-static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
-{
-	/* platforms which support all ECC schemes */
-	if (soc_is_am33xx() || soc_is_am43xx() || cpu_is_omap44xx() ||
-		 soc_is_omap54xx() || soc_is_dra7xx())
-		return 1;
-
-	if (ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW ||
-		 ecc_opt == OMAP_ECC_BCH8_CODE_HW_DETECTION_SW) {
-		if (cpu_is_omap24xx())
-			return 0;
-		else if (cpu_is_omap3630() && (GET_OMAP_REVISION() == 0))
-			return 0;
-		else
-			return 1;
-	}
-
-	/* OMAP3xxx do not have ELM engine, so cannot support ECC schemes
-	 * which require H/W based ECC error detection */
-	if ((cpu_is_omap34xx() || cpu_is_omap3630()) &&
-	    ((ecc_opt == OMAP_ECC_BCH4_CODE_HW) ||
-		 (ecc_opt == OMAP_ECC_BCH8_CODE_HW)))
-		return 0;
-
-	/* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */
-	if (ecc_opt == OMAP_ECC_HAM1_CODE_HW ||
-	    ecc_opt == OMAP_ECC_HAM1_CODE_SW)
-		return 1;
-	else
-		return 0;
-}
-
-/* This function will go away once the device-tree convertion is complete */
-static void gpmc_set_legacy(struct omap_nand_platform_data *gpmc_nand_data,
-			    struct gpmc_settings *s)
-{
-	/* Enable RD PIN Monitoring Reg */
-	if (gpmc_nand_data->dev_ready) {
-		s->wait_on_read = true;
-		s->wait_on_write = true;
-	}
-
-	if (gpmc_nand_data->devsize == NAND_BUSWIDTH_16)
-		s->device_width = GPMC_DEVWIDTH_16BIT;
-	else
-		s->device_width = GPMC_DEVWIDTH_8BIT;
-}
-
-int gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data,
-		   struct gpmc_timings *gpmc_t)
-{
-	int err	= 0;
-	struct gpmc_settings s;
-	struct platform_device *pdev;
-	struct resource gpmc_nand_res[] = {
-		{ .flags = IORESOURCE_MEM, },
-		{ .flags = IORESOURCE_IRQ, },
-		{ .flags = IORESOURCE_IRQ, },
-	};
-
-	BUG_ON(gpmc_nand_data->cs >= GPMC_CS_NUM);
-
-	err = gpmc_cs_request(gpmc_nand_data->cs, NAND_IO_SIZE,
-			      (unsigned long *)&gpmc_nand_res[0].start);
-	if (err < 0) {
-		pr_err("omap2-gpmc: Cannot request GPMC CS %d, error %d\n",
-		       gpmc_nand_data->cs, err);
-		return err;
-	}
-	gpmc_nand_res[0].end = gpmc_nand_res[0].start + NAND_IO_SIZE - 1;
-	gpmc_nand_res[1].start = gpmc_get_client_irq(GPMC_IRQ_FIFOEVENTENABLE);
-	gpmc_nand_res[2].start = gpmc_get_client_irq(GPMC_IRQ_COUNT_EVENT);
-
-	memset(&s, 0, sizeof(struct gpmc_settings));
-	gpmc_set_legacy(gpmc_nand_data, &s);
-
-	s.device_nand = true;
-
-	if (gpmc_t) {
-		err = gpmc_cs_set_timings(gpmc_nand_data->cs, gpmc_t, &s);
-		if (err < 0) {
-			pr_err("omap2-gpmc: Unable to set gpmc timings: %d\n",
-			       err);
-			return err;
-		}
-	}
-
-	err = gpmc_cs_program_settings(gpmc_nand_data->cs, &s);
-	if (err < 0)
-		goto out_free_cs;
-
-	err = gpmc_configure(GPMC_CONFIG_WP, 0);
-	if (err < 0)
-		goto out_free_cs;
-
-	if (!gpmc_hwecc_bch_capable(gpmc_nand_data->ecc_opt)) {
-		pr_err("omap2-nand: Unsupported NAND ECC scheme selected\n");
-		err = -EINVAL;
-		goto out_free_cs;
-	}
-
-
-	pdev = platform_device_alloc("omap2-nand", gpmc_nand_data->cs);
-	if (pdev) {
-		err = platform_device_add_resources(pdev, gpmc_nand_res,
-						    ARRAY_SIZE(gpmc_nand_res));
-		if (!err)
-			pdev->dev.platform_data = gpmc_nand_data;
-	} else {
-		err = -ENOMEM;
-	}
-	if (err)
-		goto out_free_pdev;
-
-	err = platform_device_add(pdev);
-	if (err) {
-		dev_err(&pdev->dev, "Unable to register NAND device\n");
-		goto out_free_pdev;
-	}
-
-	return 0;
-
-out_free_pdev:
-	platform_device_put(pdev);
-out_free_cs:
-	gpmc_cs_free(gpmc_nand_data->cs);
-
-	return err;
-}
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 8633c703546a..2944af820558 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -367,7 +367,7 @@ static int gpmc_onenand_setup(void __iomem *onenand_base, int *freq_ptr)
 	return ret;
 }
 
-void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
+int gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
 {
 	int err;
 	struct device *dev = &gpmc_onenand_device.dev;
@@ -393,15 +393,17 @@ void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
 	if (err < 0) {
 		dev_err(dev, "Cannot request GPMC CS %d, error %d\n",
 			gpmc_onenand_data->cs, err);
-		return;
+		return err;
 	}
 
 	gpmc_onenand_resource.end = gpmc_onenand_resource.start +
 							ONENAND_IO_SIZE - 1;
 
-	if (platform_device_register(&gpmc_onenand_device) < 0) {
+	err = platform_device_register(&gpmc_onenand_device);
+	if (err) {
 		dev_err(dev, "Unable to register OneNAND device\n");
 		gpmc_cs_free(gpmc_onenand_data->cs);
-		return;
 	}
+
+	return err;
 }
diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S
index fe36ce2734d4..4c6f14cf92a8 100644
--- a/arch/arm/mach-omap2/omap-headsmp.S
+++ b/arch/arm/mach-omap2/omap-headsmp.S
@@ -17,6 +17,7 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 
 #include "omap44xx.h"
 
@@ -66,7 +67,7 @@ wait_2:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
 	cmp	r0, r4
 	bne	wait_2
 	ldr	r12, =API_HYP_ENTRY
-	adr	r0, hyp_boot
+	badr	r0, hyp_boot
 	smc	#0
 hyp_boot:
 	b	omap_secondary_startup
diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c
index d3fb5661bb5d..433db6d0b073 100644
--- a/arch/arm/mach-omap2/omap-hotplug.c
+++ b/arch/arm/mach-omap2/omap-hotplug.c
@@ -50,7 +50,7 @@ void omap4_cpu_die(unsigned int cpu)
 		omap4_hotplug_cpu(cpu, PWRDM_POWER_OFF);
 
 		if (omap_secure_apis_support())
-			boot_cpu = omap_read_auxcoreboot0();
+			boot_cpu = omap_read_auxcoreboot0() >> 9;
 		else
 			boot_cpu =
 				readl_relaxed(base + OMAP_AUX_CORE_BOOT_0) >> 5;
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 113ab2dd2ee9..03ec6d307c82 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -64,6 +64,7 @@
 #include "prm-regbits-44xx.h"
 
 static void __iomem *sar_base;
+static u32 old_cpu1_ns_pa_addr;
 
 #if defined(CONFIG_PM) && defined(CONFIG_SMP)
 
@@ -212,6 +213,11 @@ static void __init save_l2x0_context(void)
 {}
 #endif
 
+u32 omap4_get_cpu1_ns_pa_addr(void)
+{
+	return old_cpu1_ns_pa_addr;
+}
+
 /**
  * omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function
  * The purpose of this function is to manage low power programming
@@ -460,22 +466,30 @@ int __init omap4_mpuss_init(void)
 void __init omap4_mpuss_early_init(void)
 {
 	unsigned long startup_pa;
+	void __iomem *ns_pa_addr;
 
-	if (!(cpu_is_omap44xx() || soc_is_omap54xx()))
+	if (!(soc_is_omap44xx() || soc_is_omap54xx()))
 		return;
 
 	sar_base = omap4_get_sar_ram_base();
 
-	if (cpu_is_omap443x())
+	/* Save old NS_PA_ADDR for validity checks later on */
+	if (soc_is_omap44xx())
+		ns_pa_addr = sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+	else
+		ns_pa_addr = sar_base + OMAP5_CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+	old_cpu1_ns_pa_addr = readl_relaxed(ns_pa_addr);
+
+	if (soc_is_omap443x())
 		startup_pa = __pa_symbol(omap4_secondary_startup);
-	else if (cpu_is_omap446x())
+	else if (soc_is_omap446x())
 		startup_pa = __pa_symbol(omap4460_secondary_startup);
 	else if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
 		startup_pa = __pa_symbol(omap5_secondary_hyp_startup);
 	else
 		startup_pa = __pa_symbol(omap5_secondary_startup);
 
-	if (cpu_is_omap44xx())
+	if (soc_is_omap44xx())
 		writel_relaxed(startup_pa, sar_base +
 			       CPU1_WAKEUP_NS_PA_ADDR_OFFSET);
 	else
diff --git a/arch/arm/mach-omap2/omap-smc.S b/arch/arm/mach-omap2/omap-smc.S
index fd90125bffc7..72506e6cf9e7 100644
--- a/arch/arm/mach-omap2/omap-smc.S
+++ b/arch/arm/mach-omap2/omap-smc.S
@@ -94,6 +94,5 @@ ENTRY(omap_read_auxcoreboot0)
 	ldr	r12, =0x103
 	dsb
 	smc	#0
-	mov	r0, r0, lsr #9
 	ldmfd   sp!, {r2-r12, pc}
 ENDPROC(omap_read_auxcoreboot0)
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 003353b0b794..3faf454ba487 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -21,6 +21,7 @@
 #include <linux/io.h>
 #include <linux/irqchip/arm-gic.h>
 
+#include <asm/sections.h>
 #include <asm/smp_scu.h>
 #include <asm/virt.h>
 
@@ -40,10 +41,14 @@
 
 #define OMAP5_CORE_COUNT	0x2
 
+#define AUX_CORE_BOOT0_GP_RELEASE	0x020
+#define AUX_CORE_BOOT0_HS_RELEASE	0x200
+
 struct omap_smp_config {
 	unsigned long cpu1_rstctrl_pa;
 	void __iomem *cpu1_rstctrl_va;
 	void __iomem *scu_base;
+	void __iomem *wakeupgen_base;
 	void *startup_addr;
 };
 
@@ -140,7 +145,6 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	static struct clockdomain *cpu1_clkdm;
 	static bool booted;
 	static struct powerdomain *cpu1_pwrdm;
-	void __iomem *base = omap_get_wakeupgen_base();
 
 	/*
 	 * Set synchronisation state between this boot processor
@@ -155,9 +159,11 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * A barrier is added to ensure that write buffer is drained
 	 */
 	if (omap_secure_apis_support())
-		omap_modify_auxcoreboot0(0x200, 0xfffffdff);
+		omap_modify_auxcoreboot0(AUX_CORE_BOOT0_HS_RELEASE,
+					 0xfffffdff);
 	else
-		writel_relaxed(0x20, base + OMAP_AUX_CORE_BOOT_0);
+		writel_relaxed(AUX_CORE_BOOT0_GP_RELEASE,
+			       cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_0);
 
 	if (!cpu1_clkdm && !cpu1_pwrdm) {
 		cpu1_clkdm = clkdm_lookup("mpu1_clkdm");
@@ -261,9 +267,72 @@ static void __init omap4_smp_init_cpus(void)
 		set_cpu_possible(i, true);
 }
 
+/*
+ * For now, just make sure the start-up address is not within the booting
+ * kernel space as that means we just overwrote whatever secondary_startup()
+ * code there was.
+ */
+static bool __init omap4_smp_cpu1_startup_valid(unsigned long addr)
+{
+	if ((addr >= __pa(PAGE_OFFSET)) && (addr <= __pa(__bss_start)))
+		return false;
+
+	return true;
+}
+
+/*
+ * We may need to reset CPU1 before configuring, otherwise kexec boot can end
+ * up trying to use old kernel startup address or suspend-resume will
+ * occasionally fail to bring up CPU1 on 4430 if CPU1 fails to enter deeper
+ * idle states.
+ */
+static void __init omap4_smp_maybe_reset_cpu1(struct omap_smp_config *c)
+{
+	unsigned long cpu1_startup_pa, cpu1_ns_pa_addr;
+	bool needs_reset = false;
+	u32 released;
+
+	if (omap_secure_apis_support())
+		released = omap_read_auxcoreboot0() & AUX_CORE_BOOT0_HS_RELEASE;
+	else
+		released = readl_relaxed(cfg.wakeupgen_base +
+					 OMAP_AUX_CORE_BOOT_0) &
+						AUX_CORE_BOOT0_GP_RELEASE;
+	if (released) {
+		pr_warn("smp: CPU1 not parked?\n");
+
+		return;
+	}
+
+	cpu1_startup_pa = readl_relaxed(cfg.wakeupgen_base +
+					OMAP_AUX_CORE_BOOT_1);
+	cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr();
+
+	/* Did the configured secondary_startup() get overwritten? */
+	if (!omap4_smp_cpu1_startup_valid(cpu1_startup_pa))
+		needs_reset = true;
+
+	/*
+	 * If omap4 or 5 has NS_PA_ADDR configured, CPU1 may be in a
+	 * deeper idle state in WFI and will wake to an invalid address.
+	 */
+	if ((soc_is_omap44xx() || soc_is_omap54xx()) &&
+	    !omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr))
+		needs_reset = true;
+
+	if (!needs_reset || !c->cpu1_rstctrl_va)
+		return;
+
+	pr_info("smp: CPU1 parked within kernel, needs reset (0x%lx 0x%lx)\n",
+		cpu1_startup_pa, cpu1_ns_pa_addr);
+
+	writel_relaxed(1, c->cpu1_rstctrl_va);
+	readl_relaxed(c->cpu1_rstctrl_va);
+	writel_relaxed(0, c->cpu1_rstctrl_va);
+}
+
 static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 {
-	void __iomem *base = omap_get_wakeupgen_base();
 	const struct omap_smp_config *c = NULL;
 
 	if (soc_is_omap443x())
@@ -281,6 +350,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 	/* Must preserve cfg.scu_base set earlier */
 	cfg.cpu1_rstctrl_pa = c->cpu1_rstctrl_pa;
 	cfg.startup_addr = c->startup_addr;
+	cfg.wakeupgen_base = omap_get_wakeupgen_base();
 
 	if (soc_is_dra74x() || soc_is_omap54xx()) {
 		if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
@@ -299,15 +369,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 	if (cfg.scu_base)
 		scu_enable(cfg.scu_base);
 
-	/*
-	 * Reset CPU1 before configuring, otherwise kexec will
-	 * end up trying to use old kernel startup address.
-	 */
-	if (cfg.cpu1_rstctrl_va) {
-		writel_relaxed(1, cfg.cpu1_rstctrl_va);
-		readl_relaxed(cfg.cpu1_rstctrl_va);
-		writel_relaxed(0, cfg.cpu1_rstctrl_va);
-	}
+	omap4_smp_maybe_reset_cpu1(&cfg);
 
 	/*
 	 * Write the address of secondary startup routine into the
@@ -319,7 +381,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 		omap_auxcoreboot_addr(__pa_symbol(cfg.startup_addr));
 	else
 		writel_relaxed(__pa_symbol(cfg.startup_addr),
-			       base + OMAP_AUX_CORE_BOOT_1);
+			       cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_1);
 }
 
 const struct smp_operations omap4_smp_ops __initconst = {
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index e920dd83e443..f989145480c8 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -222,6 +222,14 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 				dev_err(dev, "failed to idle\n");
 		}
 		break;
+	case BUS_NOTIFY_BIND_DRIVER:
+		od = to_omap_device(pdev);
+		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
+		    pm_runtime_status_suspended(dev)) {
+			od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
+			pm_runtime_set_active(dev);
+		}
+		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 56f917ec8621..1435fee39a89 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -2112,11 +2112,20 @@ static struct omap_hwmod_ocp_if omap3_l4_core__i2c3 = {
 };
 
 /* L4 CORE -> SR1 interface */
+static struct omap_hwmod_addr_space omap3_sr1_addr_space[] = {
+	{
+		.pa_start	= OMAP34XX_SR1_BASE,
+		.pa_end		= OMAP34XX_SR1_BASE + SZ_1K - 1,
+		.flags		= ADDR_TYPE_RT,
+	},
+	{ },
+};
 
 static struct omap_hwmod_ocp_if omap34xx_l4_core__sr1 = {
 	.master		= &omap3xxx_l4_core_hwmod,
 	.slave		= &omap34xx_sr1_hwmod,
 	.clk		= "sr_l4_ick",
+	.addr		= omap3_sr1_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
@@ -2124,15 +2133,25 @@ static struct omap_hwmod_ocp_if omap36xx_l4_core__sr1 = {
 	.master		= &omap3xxx_l4_core_hwmod,
 	.slave		= &omap36xx_sr1_hwmod,
 	.clk		= "sr_l4_ick",
+	.addr		= omap3_sr1_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
 /* L4 CORE -> SR1 interface */
+static struct omap_hwmod_addr_space omap3_sr2_addr_space[] = {
+	{
+		.pa_start	= OMAP34XX_SR2_BASE,
+		.pa_end		= OMAP34XX_SR2_BASE + SZ_1K - 1,
+		.flags		= ADDR_TYPE_RT,
+	},
+	{ },
+};
 
 static struct omap_hwmod_ocp_if omap34xx_l4_core__sr2 = {
 	.master		= &omap3xxx_l4_core_hwmod,
 	.slave		= &omap34xx_sr2_hwmod,
 	.clk		= "sr_l4_ick",
+	.addr		= omap3_sr2_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
@@ -2140,6 +2159,7 @@ static struct omap_hwmod_ocp_if omap36xx_l4_core__sr2 = {
 	.master		= &omap3xxx_l4_core_hwmod,
 	.slave		= &omap36xx_sr2_hwmod,
 	.clk		= "sr_l4_ick",
+	.addr		= omap3_sr2_addr_space,
 	.user		= OCP_USER_MPU,
 };
 
@@ -3111,16 +3131,20 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_hwmod_ocp_ifs[] __initdata = {
  * Return: 0 if device named @dev_name is not likely to be accessible,
  * or 1 if it is likely to be accessible.
  */
-static int __init omap3xxx_hwmod_is_hs_ip_block_usable(struct device_node *bus,
-						       const char *dev_name)
+static bool __init omap3xxx_hwmod_is_hs_ip_block_usable(struct device_node *bus,
+							const char *dev_name)
 {
+	struct device_node *node;
+	bool available;
+
 	if (!bus)
-		return (omap_type() == OMAP2_DEVICE_TYPE_GP) ? 1 : 0;
+		return omap_type() == OMAP2_DEVICE_TYPE_GP;
 
-	if (of_device_is_available(of_find_node_by_name(bus, dev_name)))
-		return 1;
+	node = of_get_child_by_name(bus, dev_name);
+	available = of_device_is_available(node);
+	of_node_put(node);
 
-	return 0;
+	return available;
 }
 
 int __init omap3xxx_hwmod_init(void)
@@ -3189,15 +3213,20 @@ int __init omap3xxx_hwmod_init(void)
 
 	if (h_sham && omap3xxx_hwmod_is_hs_ip_block_usable(bus, "sham")) {
 		r = omap_hwmod_register_links(h_sham);
-		if (r < 0)
+		if (r < 0) {
+			of_node_put(bus);
 			return r;
+		}
 	}
 
 	if (h_aes && omap3xxx_hwmod_is_hs_ip_block_usable(bus, "aes")) {
 		r = omap_hwmod_register_links(h_aes);
-		if (r < 0)
+		if (r < 0) {
+			of_node_put(bus);
 			return r;
+		}
 	}
+	of_node_put(bus);
 
 	/*
 	 * Register hwmod links specific to certain ES levels of a
diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig
index 633442ad4e4c..2a7bb6ccdcb7 100644
--- a/arch/arm/mach-orion5x/Kconfig
+++ b/arch/arm/mach-orion5x/Kconfig
@@ -6,6 +6,7 @@ menuconfig ARCH_ORION5X
 	select GPIOLIB
 	select MVEBU_MBUS
 	select PCI
+	select PHYLIB if NETDEVICES
 	select PLAT_ORION_LEGACY
 	help
 	  Support for the following Marvell Orion 5x series SoCs:
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 63eabb06f9f1..475811f5383a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -935,13 +935,31 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add
 	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
 }
 
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable.  This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ *    a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ *    as we will try to flush the memory through a different alias to that
+ *    actually being used (and the flushes are redundant.)
+ */
 int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t handle, size_t size,
 		 unsigned long attrs)
 {
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	unsigned long pfn = dma_to_pfn(dev, handle);
+	struct page *page;
 	int ret;
 
+	/* If the PFN is not valid, we do not have a struct page */
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+
+	page = pfn_to_page(pfn);
+
 	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 	if (unlikely(ret))
 		return ret;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 3b5c7aaf9c76..33a45bd96860 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -303,7 +303,10 @@ static inline void set_vbar(unsigned long val)
  */
 static inline bool security_extensions_enabled(void)
 {
-	return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+	/* Check CPUID Identification Scheme before ID_PFR1 read */
+	if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
+		return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+	return 0;
 }
 
 static unsigned long __init setup_vectors_base(void)
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 9255b6d67ba5..aff6994950ba 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -468,6 +468,7 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data,
 		    eth_data, &orion_ge11);
 }
 
+#ifdef CONFIG_ARCH_ORION5X
 /*****************************************************************************
  * Ethernet switch
  ****************************************************************************/
@@ -480,6 +481,9 @@ void __init orion_ge00_switch_init(struct dsa_chip_data *d)
 	struct mdio_board_info *bd;
 	unsigned int i;
 
+	if (!IS_BUILTIN(CONFIG_PHYLIB))
+		return;
+
 	for (i = 0; i < ARRAY_SIZE(d->port_names); i++)
 		if (!strcmp(d->port_names[i], "cpu"))
 			break;
@@ -493,6 +497,7 @@ void __init orion_ge00_switch_init(struct dsa_chip_data *d)
 
 	mdiobus_register_board_info(&orion_ge00_switch_board_info, 1);
 }
+#endif
 
 /*****************************************************************************
  * I2C
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index b6dc9d838a9a..ad1f4e6a9e33 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -266,11 +266,20 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 #endif
 
 	if (p) {
-		if (cur) {
+		if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+			/*
+			 * Probe hit but conditional execution check failed,
+			 * so just skip the instruction and continue as if
+			 * nothing had happened.
+			 * In this case, we can skip recursing check too.
+			 */
+			singlestep_skip(p, regs);
+		} else if (cur) {
 			/* Kprobe is pending, so we're recursing. */
 			switch (kcb->kprobe_status) {
 			case KPROBE_HIT_ACTIVE:
 			case KPROBE_HIT_SSDONE:
+			case KPROBE_HIT_SS:
 				/* A pre- or post-handler probe got us here. */
 				kprobes_inc_nmissed_count(p);
 				save_previous_kprobe(kcb);
@@ -279,11 +288,16 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				singlestep(p, regs, kcb);
 				restore_previous_kprobe(kcb);
 				break;
+			case KPROBE_REENTER:
+				/* A nested probe was hit in FIQ, it is a BUG */
+				pr_warn("Unrecoverable kprobe detected at %p.\n",
+					p->addr);
+				/* fall through */
 			default:
 				/* impossible cases */
 				BUG();
 			}
-		} else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+		} else {
 			/* Probe hit and conditional execution check ok. */
 			set_current_kprobe(p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
@@ -304,13 +318,6 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				}
 				reset_current_kprobe();
 			}
-		} else {
-			/*
-			 * Probe hit but conditional execution check failed,
-			 * so just skip the instruction and continue as if
-			 * nothing had happened.
-			 */
-			singlestep_skip(p, regs);
 		}
 	} else if (cur) {
 		/* We probably hit a jprobe.  Call its break handler. */
@@ -434,6 +441,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -456,14 +464,34 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			/* another task is sharing our hash bucket */
 			continue;
 
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
 			__this_cpu_write(current_kprobe, NULL);
 		}
 
-		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)
@@ -475,7 +503,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			break;
 	}
 
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index c893726aa52d..1c98a87786ca 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -977,7 +977,10 @@ static void coverage_end(void)
 void __naked __kprobes_test_case_start(void)
 {
 	__asm__ __volatile__ (
-		"stmdb	sp!, {r4-r11}				\n\t"
+		"mov	r2, sp					\n\t"
+		"bic	r3, r2, #7				\n\t"
+		"mov	sp, r3					\n\t"
+		"stmdb	sp!, {r2-r11}				\n\t"
 		"sub	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
 		"bic	r0, lr, #1  @ r0 = inline data		\n\t"
 		"mov	r1, sp					\n\t"
@@ -997,7 +1000,8 @@ void __naked __kprobes_test_case_end_32(void)
 		"movne	pc, r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"mov	pc, r0					\n\t"
 	);
 }
@@ -1013,7 +1017,8 @@ void __naked __kprobes_test_case_end_16(void)
 		"bxne	r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"bx	r0					\n\t"
 	);
 }
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 3c2cb5d5adfa..0bb0e9c6376c 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -411,3 +411,4 @@
 394	common	pkey_mprotect		sys_pkey_mprotect
 395	common	pkey_alloc		sys_pkey_alloc
 396	common	pkey_free		sys_pkey_free
+397	common	statx			sys_statx
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index ce18c91b50a1..f0325d96b97a 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -198,6 +198,8 @@ static const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.set_dma_mask = xen_swiotlb_set_dma_mask,
+	.mmap = xen_swiotlb_dma_mmap,
+	.get_sgtable = xen_swiotlb_get_sgtable,
 };
 
 int __init xen_mm_init(void)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a39029b5414e..67695fadae96 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,6 +2,7 @@ config ARM64
 	def_bool y
 	select ACPI_CCA_REQUIRED if ACPI
 	select ACPI_GENERIC_GSI if ACPI
+	select ACPI_GTDT if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
 	select ACPI_MCFG if ACPI
 	select ACPI_SPCR_TABLE if ACPI
@@ -60,7 +61,6 @@ config ARM64
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
-	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
@@ -508,6 +508,16 @@ config QCOM_FALKOR_ERRATUM_1009
 
 	  If unsure, say Y.
 
+config QCOM_QDF2400_ERRATUM_0065
+	bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size"
+	default y
+	help
+	  On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports
+	  ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have
+	  been indicated as 16Bytes (0xf), not 8Bytes (0x7).
+
+	  If unsure, say Y.
+
 endmenu
 
 
@@ -1063,6 +1073,10 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
+config KEYS_COMPAT
+	def_bool y
+	depends on COMPAT && KEYS
+
 endmenu
 
 menu "Power management options"
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 1c64ea2d23f9..0565779e66fa 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -179,8 +179,10 @@
 		usbphy: phy@01c19400 {
 			compatible = "allwinner,sun50i-a64-usb-phy";
 			reg = <0x01c19400 0x14>,
+			      <0x01c1a800 0x4>,
 			      <0x01c1b800 0x4>;
 			reg-names = "phy_ctrl",
+				    "pmu0",
 				    "pmu1";
 			clocks = <&ccu CLK_USB_PHY0>,
 				 <&ccu CLK_USB_PHY1>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 5d995f7724af..620495a43363 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -380,7 +380,7 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>;
 
-			rng {
+			hwrng: rng {
 				compatible = "amlogic,meson-rng";
 				reg = <0x0 0x0 0x0 0x4>;
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 04b3324bc132..a375cb21cc8b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -524,3 +524,8 @@
 &vpu {
 	compatible = "amlogic,meson-gxbb-vpu", "amlogic,meson-gx-vpu";
 };
+
+&hwrng {
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index 9f9e203c09c5..bcb03fc32665 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -114,6 +114,7 @@
 	pcie0: pcie@20020000 {
 		compatible = "brcm,iproc-pcie";
 		reg = <0 0x20020000 0 0x1000>;
+		dma-coherent;
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
@@ -144,6 +145,7 @@
 	pcie4: pcie@50020000 {
 		compatible = "brcm,iproc-pcie";
 		reg = <0 0x50020000 0 0x1000>;
+		dma-coherent;
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
@@ -174,6 +176,7 @@
 	pcie8: pcie@60c00000 {
 		compatible = "brcm,iproc-pcie-paxc";
 		reg = <0 0x60c00000 0 0x1000>;
+		dma-coherent;
 		linux,pci-domain = <8>;
 
 		bus-range = <0x0 0x1>;
@@ -203,6 +206,7 @@
 			      <0x61030000 0x100>;
 			reg-names = "amac_base", "idm_base", "nicpm_base";
 			interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
+			dma-coherent;
 			phy-handle = <&gphy0>;
 			phy-mode = "rgmii";
 			status = "disabled";
@@ -213,6 +217,7 @@
 			reg = <0x612c0000 0x445>;  /* PDC FS0 regs */
 			interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
+			dma-coherent;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
 		};
@@ -222,6 +227,7 @@
 			reg = <0x612e0000 0x445>;  /* PDC FS1 regs */
 			interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
+			dma-coherent;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
 		};
@@ -231,6 +237,7 @@
 			reg = <0x61300000 0x445>;  /* PDC FS2 regs */
 			interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
+			dma-coherent;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
 		};
@@ -240,6 +247,7 @@
 			reg = <0x61320000 0x445>;  /* PDC FS3 regs */
 			interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
+			dma-coherent;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
 		};
@@ -644,6 +652,7 @@
 		sata: ahci@663f2000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
 			reg = <0x663f2000 0x1000>;
+			dma-coherent;
 			reg-names = "ahci";
 			interrupts = <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
@@ -667,6 +676,7 @@
 			compatible = "brcm,sdhci-iproc-cygnus";
 			reg = <0x66420000 0x100>;
 			interrupts = <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>;
+			dma-coherent;
 			bus-width = <8>;
 			clocks = <&genpll_sw BCM_NS2_GENPLL_SW_SDIO_CLK>;
 			status = "disabled";
@@ -676,6 +686,7 @@
 			compatible = "brcm,sdhci-iproc-cygnus";
 			reg = <0x66430000 0x100>;
 			interrupts = <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
+			dma-coherent;
 			bus-width = <8>;
 			clocks = <&genpll_sw BCM_NS2_GENPLL_SW_SDIO_CLK>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index dba3c131c62c..9b4ba7169210 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -98,6 +98,11 @@
 			assigned-clocks = <&sys_ctrl HI6220_UART1_SRC>;
 			assigned-clock-rates = <150000000>;
 			status = "ok";
+
+			bluetooth {
+				compatible = "ti,wl1835-st";
+				enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+			};
 		};
 
 		uart2: uart@f7112000 {
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index a749ba2edec4..5019c8f4acd0 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -235,7 +235,8 @@
 				#clock-cells = <1>;
 				clock-output-names = "ap-cpu-cluster-0",
 						     "ap-cpu-cluster-1",
-						     "ap-fixed", "ap-mss";
+						     "ap-fixed", "ap-mss",
+						     "ap-emmc";
 				reg = <0x6f4000 0x1000>;
 			};
 		};
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index b4b34004a21e..74d08e44a651 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -25,6 +25,7 @@
 #include <linux/bug.h>
 #include <linux/init.h>
 #include <linux/jump_label.h>
+#include <linux/smp.h>
 #include <linux/types.h>
 
 #include <clocksource/arm_arch_timer.h>
@@ -37,24 +38,44 @@ extern struct static_key_false arch_timer_read_ool_enabled;
 #define needs_unstable_timer_counter_workaround()  false
 #endif
 
+enum arch_timer_erratum_match_type {
+	ate_match_dt,
+	ate_match_local_cap_id,
+	ate_match_acpi_oem_info,
+};
+
+struct clock_event_device;
 
 struct arch_timer_erratum_workaround {
-	const char *id;		/* Indicate the Erratum ID */
+	enum arch_timer_erratum_match_type match_type;
+	const void *id;
+	const char *desc;
 	u32 (*read_cntp_tval_el0)(void);
 	u32 (*read_cntv_tval_el0)(void);
 	u64 (*read_cntvct_el0)(void);
+	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
+	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
 };
 
-extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround;
-
-#define arch_timer_reg_read_stable(reg) 		\
-({							\
-	u64 _val;					\
-	if (needs_unstable_timer_counter_workaround())		\
-		_val = timer_unstable_counter_workaround->read_##reg();\
-	else						\
-		_val = read_sysreg(reg);		\
-	_val;						\
+DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
+		timer_unstable_counter_workaround);
+
+#define arch_timer_reg_read_stable(reg)					\
+({									\
+	u64 _val;							\
+	if (needs_unstable_timer_counter_workaround()) {		\
+		const struct arch_timer_erratum_workaround *wa;		\
+		preempt_disable();					\
+		wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		if (wa && wa->read_##reg)				\
+			_val = wa->read_##reg();			\
+		else							\
+			_val = read_sysreg(reg);			\
+		preempt_enable();					\
+	} else {							\
+		_val = read_sysreg(reg);				\
+	}								\
+	_val;								\
 })
 
 /*
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
index 561190d15881..a9be1072933c 100644
--- a/arch/arm64/include/asm/bug.h
+++ b/arch/arm64/include/asm/bug.h
@@ -55,7 +55,7 @@ _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 	unreachable();				\
 } while (0)
 
-#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint))
+#define __WARN_FLAGS(flags) _BUG_FLAGS(BUGFLAG_WARNING|(flags))
 
 #endif /* ! CONFIG_GENERIC_BUG */
 
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index fb78a5d3b60b..b3aab8a17868 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -37,7 +37,8 @@
 #define ARM64_HAS_NO_FPSIMD			16
 #define ARM64_WORKAROUND_REPEAT_TLBI		17
 #define ARM64_WORKAROUND_QCOM_FALKOR_E1003	18
+#define ARM64_WORKAROUND_858921			19
 
-#define ARM64_NCAPS				19
+#define ARM64_NCAPS				20
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 05310ad8c5ab..f31c48d0cd68 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -251,7 +251,7 @@ static inline bool system_supports_fpsimd(void)
 static inline bool system_uses_ttbr0_pan(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
-		!cpus_have_cap(ARM64_HAS_PAN);
+		!cpus_have_const_cap(ARM64_HAS_PAN);
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index fc502713ab37..0984d1b3a8f2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -80,6 +80,7 @@
 #define ARM_CPU_PART_FOUNDATION		0xD00
 #define ARM_CPU_PART_CORTEX_A57		0xD07
 #define ARM_CPU_PART_CORTEX_A53		0xD03
+#define ARM_CPU_PART_CORTEX_A73		0xD09
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -92,6 +93,7 @@
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
index 86c404171305..f6580d4afb0e 100644
--- a/arch/arm64/include/asm/current.h
+++ b/arch/arm64/include/asm/current.h
@@ -3,8 +3,6 @@
 
 #include <linux/compiler.h>
 
-#include <asm/sysreg.h>
-
 #ifndef __ASSEMBLY__
 
 struct task_struct;
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index e7445281e534..8f3043aba873 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_EFI_H
 #define _ASM_EFI_H
 
+#include <asm/boot.h>
 #include <asm/cpufeature.h>
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -46,7 +47,28 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
  * 2MiB so we know it won't cross a 2MiB boundary.
  */
 #define EFI_FDT_ALIGN	SZ_2M   /* used by allocate_new_fdt_and_exit_boot() */
-#define MAX_FDT_OFFSET	SZ_512M
+
+/* on arm64, the FDT may be located anywhere in system RAM */
+static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
+{
+	return ULONG_MAX;
+}
+
+/*
+ * On arm64, we have to ensure that the initrd ends up in the linear region,
+ * which is a 1 GB aligned region of size '1UL << (VA_BITS - 1)' that is
+ * guaranteed to cover the kernel Image.
+ *
+ * Since the EFI stub is part of the kernel Image, we can relax the
+ * usual requirements in Documentation/arm64/booting.txt, which still
+ * apply to other bootloaders, and are required for some kernel
+ * configurations.
+ */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
+						    unsigned long image_addr)
+{
+	return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS - 1));
+}
 
 #define efi_call_early(f, ...)		sys_table_arg->boottime->f(__VA_ARGS__)
 #define __efi_call_early(f, ...)	f(__VA_ARGS__)
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d14c478976d0..ad42e79a5d4d 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -175,6 +175,8 @@
 #define ESR_ELx_SYS64_ISS_SYS_CTR_READ	(ESR_ELx_SYS64_ISS_SYS_CTR | \
 					 ESR_ELx_SYS64_ISS_DIR_READ)
 
+#define ESR_ELx_SYS64_ISS_SYS_CNTVCT	(ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 2, 14, 0) | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
new file mode 100644
index 000000000000..42f50f15a44c
--- /dev/null
+++ b/arch/arm64/include/asm/extable.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative offsets: the first
+ * is the relative offset to an instruction that is allowed to fault,
+ * and the second is the relative offset at which the program should
+ * continue. No registers are modified, so it is entirely up to the
+ * continuation code to figure out what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	int insn, fixup;
+};
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+extern int fixup_exception(struct pt_regs *regs);
+#endif
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index aecc07e09a18..29cb2ca756f6 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -80,6 +80,7 @@ enum aarch64_insn_register_type {
 	AARCH64_INSN_REGTYPE_RM,
 	AARCH64_INSN_REGTYPE_RD,
 	AARCH64_INSN_REGTYPE_RA,
+	AARCH64_INSN_REGTYPE_RS,
 };
 
 enum aarch64_insn_register {
@@ -188,6 +189,8 @@ enum aarch64_insn_ldst_type {
 	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
 	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
 	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_LOAD_EX,
+	AARCH64_INSN_LDST_STORE_EX,
 };
 
 enum aarch64_insn_adsb_type {
@@ -240,6 +243,23 @@ enum aarch64_insn_logic_type {
 	AARCH64_INSN_LOGIC_BIC_SETFLAGS
 };
 
+enum aarch64_insn_prfm_type {
+	AARCH64_INSN_PRFM_TYPE_PLD,
+	AARCH64_INSN_PRFM_TYPE_PLI,
+	AARCH64_INSN_PRFM_TYPE_PST,
+};
+
+enum aarch64_insn_prfm_target {
+	AARCH64_INSN_PRFM_TARGET_L1,
+	AARCH64_INSN_PRFM_TARGET_L2,
+	AARCH64_INSN_PRFM_TARGET_L3,
+};
+
+enum aarch64_insn_prfm_policy {
+	AARCH64_INSN_PRFM_POLICY_KEEP,
+	AARCH64_INSN_PRFM_POLICY_STRM,
+};
+
 #define	__AARCH64_INSN_FUNCS(abbr, mask, val)	\
 static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
 { return (code & (mask)) == (val); } \
@@ -248,6 +268,7 @@ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
 
 __AARCH64_INSN_FUNCS(adr,	0x9F000000, 0x10000000)
 __AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
+__AARCH64_INSN_FUNCS(prfm,	0x3FC00000, 0x39800000)
 __AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
 __AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
@@ -357,6 +378,11 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 				     int offset,
 				     enum aarch64_insn_variant variant,
 				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
+				   enum aarch64_insn_register base,
+				   enum aarch64_insn_register state,
+				   enum aarch64_insn_size_type size,
+				   enum aarch64_insn_ldst_type type);
 u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 				 enum aarch64_insn_register src,
 				 int imm, enum aarch64_insn_variant variant,
@@ -397,6 +423,10 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 					 int shift,
 					 enum aarch64_insn_variant variant,
 					 enum aarch64_insn_logic_type type);
+u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
+			      enum aarch64_insn_prfm_type type,
+			      enum aarch64_insn_prfm_target target,
+			      enum aarch64_insn_prfm_policy policy);
 s32 aarch64_get_branch_offset(u32 insn);
 u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f21fd3894370..e7705e7bb07b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,8 +30,7 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 512
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
index 69b2fd41503c..345a072b5856 100644
--- a/arch/arm64/include/asm/pgtable-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -55,9 +55,13 @@ typedef struct { pteval_t pgprot; } pgprot_t;
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
 #if CONFIG_PGTABLE_LEVELS == 2
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #elif CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 4
+#include <asm-generic/5level-fixup.h>
 #endif
 
 #endif	/* __ASM_PGTABLE_TYPES_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 5308d696311b..ba497172610d 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -28,38 +28,12 @@
 #include <linux/bitops.h>
 #include <linux/kasan-checks.h>
 #include <linux/string.h>
-#include <linux/thread_info.h>
 
 #include <asm/cpufeature.h>
 #include <asm/ptrace.h>
-#include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The exception table consists of pairs of relative offsets: the first
- * is the relative offset to an instruction that is allowed to fault,
- * and the second is the relative offset at which the program should
- * continue. No registers are modified, so it is entirely up to the
- * continuation code to figure out what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	int insn, fixup;
-};
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 #define KERNEL_DS	(-1UL)
 #define get_ds()	(KERNEL_DS)
@@ -357,58 +331,13 @@ do {									\
 })
 
 extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
+#define raw_copy_from_user __arch_copy_from_user
 extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
+#define raw_copy_to_user __arch_copy_to_user
+extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
 extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-
-static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	kasan_check_write(to, n);
-	check_object_size(to, n, false);
-	return __arch_copy_from_user(to, from, n);
-}
-
-static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	kasan_check_read(from, n);
-	check_object_size(from, n, true);
-	return __arch_copy_to_user(to, from, n);
-}
-
-static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	unsigned long res = n;
-	kasan_check_write(to, n);
-	check_object_size(to, n, false);
-
-	if (access_ok(VERIFY_READ, from, n)) {
-		res = __arch_copy_from_user(to, from, n);
-	}
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
-}
-
-static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	kasan_check_read(from, n);
-	check_object_size(from, n, true);
-
-	if (access_ok(VERIFY_WRITE, to, n)) {
-		n = __arch_copy_to_user(to, from, n);
-	}
-	return n;
-}
-
-static inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-	if (access_ok(VERIFY_READ, from, n) && access_ok(VERIFY_WRITE, to, n))
-		n = __copy_in_user(to, from, n);
-	return n;
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
 
 static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index e78ac26324bd..a0baa9af5487 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -14,7 +14,6 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #ifdef CONFIG_COMPAT
-#define __ARCH_WANT_COMPAT_SYS_GETDENTS64
 #define __ARCH_WANT_COMPAT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
@@ -44,7 +43,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		394
+#define __NR_compat_syscalls		398
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index b7e8ef16ff0d..ef292160748c 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -456,7 +456,7 @@ __SYSCALL(__NR_setfsuid32, sys_setfsuid)
 #define __NR_setfsgid32 216
 __SYSCALL(__NR_setfsgid32, sys_setfsgid)
 #define __NR_getdents64 217
-__SYSCALL(__NR_getdents64, compat_sys_getdents64)
+__SYSCALL(__NR_getdents64, sys_getdents64)
 #define __NR_pivot_root 218
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 #define __NR_mincore 219
@@ -809,6 +809,14 @@ __SYSCALL(__NR_copy_file_range, sys_copy_file_range)
 __SYSCALL(__NR_preadv2, compat_sys_preadv2)
 #define __NR_pwritev2 393
 __SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 394
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 395
+__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
+#define __NR_pkey_free 396
+__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 397
+__SYSCALL(__NR_statx, sys_statx)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 64d9cbd61678..e25c11e727fe 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -18,6 +18,7 @@
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/cpumask.h>
+#include <linux/efi-bgrt.h>
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
@@ -233,6 +234,8 @@ done:
 			early_init_dt_scan_chosen_stdout();
 	} else {
 		parse_spcr(earlycon_init_is_deferred);
+		if (IS_ENABLED(CONFIG_ACPI_BGRT))
+			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
 	}
 }
 
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index e9c4dc9e0ada..67368c7329c0 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -38,7 +38,7 @@ EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(__arch_copy_from_user);
 EXPORT_SYMBOL(__arch_copy_to_user);
 EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
 
 	/* physical memory */
 EXPORT_SYMBOL(memstart_addr);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index f6cc67e7626e..2ed2a7657711 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -53,6 +53,13 @@ static int cpu_enable_trap_ctr_access(void *__unused)
 	.midr_range_min = min, \
 	.midr_range_max = max
 
+#define MIDR_ALL_VERSIONS(model) \
+	.def_scope = SCOPE_LOCAL_CPU, \
+	.matches = is_affected_midr_range, \
+	.midr_model = model, \
+	.midr_range_min = 0, \
+	.midr_range_max = (MIDR_VARIANT_MASK | MIDR_REVISION_MASK)
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #if	defined(CONFIG_ARM64_ERRATUM_826319) || \
 	defined(CONFIG_ARM64_ERRATUM_827319) || \
@@ -151,6 +158,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 			   MIDR_CPU_VAR_REV(0, 0)),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_858921
+	{
+	/* Cortex-A73 all versions */
+		.desc = "ARM erratum 858921",
+		.capability = ARM64_WORKAROUND_858921,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index abda8e861865..6eb77ae99b79 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1090,20 +1090,29 @@ static void __init setup_feature_capabilities(void)
  * Check if the current CPU has a given feature capability.
  * Should be called from non-preemptible context.
  */
-bool this_cpu_has_cap(unsigned int cap)
+static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
+			       unsigned int cap)
 {
 	const struct arm64_cpu_capabilities *caps;
 
 	if (WARN_ON(preemptible()))
 		return false;
 
-	for (caps = arm64_features; caps->desc; caps++)
+	for (caps = cap_array; caps->desc; caps++)
 		if (caps->capability == cap && caps->matches)
 			return caps->matches(caps, SCOPE_LOCAL_CPU);
 
 	return false;
 }
 
+extern const struct arm64_cpu_capabilities arm64_errata[];
+
+bool this_cpu_has_cap(unsigned int cap)
+{
+	return (__this_cpu_has_cap(arm64_features, cap) ||
+		__this_cpu_has_cap(arm64_errata, cap));
+}
+
 void __init setup_cpu_features(void)
 {
 	u32 cwg;
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 75a0f8acef66..fd691087dc9a 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -30,7 +30,7 @@ int arm_cpuidle_init(unsigned int cpu)
 }
 
 /**
- * cpu_suspend() - function to enter a low-power idle state
+ * arm_cpuidle_suspend() - function to enter a low-power idle state
  * @arg: argument to pass to CPU suspend operations
  *
  * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 3a63954a8b14..b884a926a632 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -474,6 +474,7 @@ static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type,
 		shift = 10;
 		break;
 	case AARCH64_INSN_REGTYPE_RM:
+	case AARCH64_INSN_REGTYPE_RS:
 		shift = 16;
 		break;
 	default:
@@ -757,6 +758,111 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 					     offset >> shift);
 }
 
+u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
+				   enum aarch64_insn_register base,
+				   enum aarch64_insn_register state,
+				   enum aarch64_insn_size_type size,
+				   enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_EX:
+		insn = aarch64_insn_get_load_ex_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_EX:
+		insn = aarch64_insn_get_store_ex_value();
+		break;
+	default:
+		pr_err("%s: unknown load/store exclusive encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn,
+					    AARCH64_INSN_REG_ZR);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+					    state);
+}
+
+static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type,
+					enum aarch64_insn_prfm_target target,
+					enum aarch64_insn_prfm_policy policy,
+					u32 insn)
+{
+	u32 imm_type = 0, imm_target = 0, imm_policy = 0;
+
+	switch (type) {
+	case AARCH64_INSN_PRFM_TYPE_PLD:
+		break;
+	case AARCH64_INSN_PRFM_TYPE_PLI:
+		imm_type = BIT(0);
+		break;
+	case AARCH64_INSN_PRFM_TYPE_PST:
+		imm_type = BIT(1);
+		break;
+	default:
+		pr_err("%s: unknown prfm type encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (target) {
+	case AARCH64_INSN_PRFM_TARGET_L1:
+		break;
+	case AARCH64_INSN_PRFM_TARGET_L2:
+		imm_target = BIT(0);
+		break;
+	case AARCH64_INSN_PRFM_TARGET_L3:
+		imm_target = BIT(1);
+		break;
+	default:
+		pr_err("%s: unknown prfm target encoding %d\n", __func__, target);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (policy) {
+	case AARCH64_INSN_PRFM_POLICY_KEEP:
+		break;
+	case AARCH64_INSN_PRFM_POLICY_STRM:
+		imm_policy = BIT(0);
+		break;
+	default:
+		pr_err("%s: unknown prfm policy encoding %d\n", __func__, policy);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	/* In this case, imm5 is encoded into Rt field. */
+	insn &= ~GENMASK(4, 0);
+	insn |= imm_policy | (imm_target << 1) | (imm_type << 3);
+
+	return insn;
+}
+
+u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
+			      enum aarch64_insn_prfm_type type,
+			      enum aarch64_insn_prfm_target target,
+			      enum aarch64_insn_prfm_policy policy)
+{
+	u32 insn = aarch64_insn_get_prfm_value();
+
+	insn = aarch64_insn_encode_ldst_size(AARCH64_INSN_SIZE_64, insn);
+
+	insn = aarch64_insn_encode_prfm_imm(type, target, policy, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, 0);
+}
+
 u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 				 enum aarch64_insn_register src,
 				 int imm, enum aarch64_insn_variant variant,
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 769f24ef628c..d7e90d97f5c4 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -131,11 +131,15 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 	/*
 	 * The kernel Image should not extend across a 1GB/32MB/512MB alignment
 	 * boundary (for 4KB/16KB/64KB granule kernels, respectively). If this
-	 * happens, increase the KASLR offset by the size of the kernel image.
+	 * happens, increase the KASLR offset by the size of the kernel image
+	 * rounded up by SWAPPER_BLOCK_SIZE.
 	 */
 	if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) !=
-	    (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT))
-		offset = (offset + (u64)(_end - _text)) & mask;
+	    (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT)) {
+		u64 kimg_sz = _end - _text;
+		offset = (offset + round_up(kimg_sz, SWAPPER_BLOCK_SIZE))
+				& mask;
+	}
 
 	if (IS_ENABLED(CONFIG_KASAN))
 		/*
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 2a07aae5b8a2..c5c45942fb6e 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -372,12 +372,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 	return 0;
 }
 
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-				       unsigned long val, void *data)
-{
-	return NOTIFY_DONE;
-}
-
 static void __kprobes kprobe_handler(struct pt_regs *regs)
 {
 	struct kprobe *p, *cur_kprobe;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ef1caae02110..9b1036570586 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -944,7 +944,7 @@ static bool have_cpu_die(void)
 #ifdef CONFIG_HOTPLUG_CPU
 	int any_cpu = raw_smp_processor_id();
 
-	if (cpu_ops[any_cpu]->cpu_die)
+	if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
 		return true;
 #endif
 	return false;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e52be6aa44ee..1de444e6c669 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -505,6 +505,14 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	regs->pc += 4;
 }
 
+static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+	pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+	regs->pc += 4;
+}
+
 struct sys64_hook {
 	unsigned int esr_mask;
 	unsigned int esr_val;
@@ -523,6 +531,12 @@ static struct sys64_hook sys64_hooks[] = {
 		.esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
 		.handler = ctr_read_handler,
 	},
+	{
+		/* Trap read access to CNTVCT_EL0 */
+		.esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+		.esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCT,
+		.handler = cntvct_read_handler,
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/vdso/.gitignore b/arch/arm64/kernel/vdso/.gitignore
index b8cc94e9698b..f8b69d84238e 100644
--- a/arch/arm64/kernel/vdso/.gitignore
+++ b/arch/arm64/kernel/vdso/.gitignore
@@ -1,2 +1 @@
 vdso.lds
-vdso-offsets.h
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 1bfe30dfbfe7..fa1b18e364fc 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -135,7 +135,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return ret;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
+		      hsr, esr_get_class_string(hsr));
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
 	[ESR_ELx_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -162,13 +174,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	u8 hsr_ec = ESR_ELx_EC(hsr);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
-			hsr, esr_get_class_string(hsr));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index e8e7ba2bc11f..9e1d2b75eecd 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -18,14 +18,62 @@
 #include <asm/kvm_hyp.h>
 #include <asm/tlbflush.h>
 
+static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
+{
+	u64 val;
+
+	/*
+	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+	 * most TLB operations target EL2/EL0. In order to affect the
+	 * guest TLBs (EL1/EL0), we need to change one of these two
+	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+	 * let's flip TGE before executing the TLB operation.
+	 */
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	val = read_sysreg(hcr_el2);
+	val &= ~HCR_TGE;
+	write_sysreg(val, hcr_el2);
+	isb();
+}
+
+static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
+{
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	isb();
+}
+
+static hyp_alternate_select(__tlb_switch_to_guest,
+			    __tlb_switch_to_guest_nvhe,
+			    __tlb_switch_to_guest_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm)
+{
+	/*
+	 * We're done with the TLB operation, let's restore the host's
+	 * view of HCR_EL2.
+	 */
+	write_sysreg(0, vttbr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+}
+
+static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__tlb_switch_to_host,
+			    __tlb_switch_to_host_nvhe,
+			    __tlb_switch_to_host_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	dsb(ishst);
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -46,7 +94,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -55,14 +103,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -70,14 +117,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 
 	/* Switch to requested VMID */
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_flush_vm_context(void)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 47184c3a97da..b24a830419ad 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -64,14 +64,14 @@
 	.endm
 
 end	.req	x5
-ENTRY(__copy_in_user)
+ENTRY(raw_copy_in_user)
 	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
 	uaccess_disable_not_uao x3
 	mov	x0, #0
 	ret
-ENDPROC(__copy_in_user)
+ENDPROC(raw_copy_in_user)
 
 	.section .fixup,"ax"
 	.align	2
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4bf899fb451b..1b35b8bddbfb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -42,7 +42,20 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
-static const char *fault_name(unsigned int esr);
+struct fault_info {
+	int	(*fn)(unsigned long addr, unsigned int esr,
+		      struct pt_regs *regs);
+	int	sig;
+	int	code;
+	const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+	return fault_info + (esr & 63);
+}
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
@@ -197,10 +210,12 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 			    struct pt_regs *regs)
 {
 	struct siginfo si;
+	const struct fault_info *inf;
 
 	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
+		inf = esr_to_fault_info(esr);
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
-			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+			tsk->comm, task_pid_nr(tsk), inf->name, sig,
 			addr, esr);
 		show_pte(tsk->mm, addr);
 		show_regs(regs);
@@ -219,14 +234,16 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->active_mm;
+	const struct fault_info *inf;
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
 	 * handle this fault with.
 	 */
-	if (user_mode(regs))
-		__do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
-	else
+	if (user_mode(regs)) {
+		inf = esr_to_fault_info(esr);
+		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+	} else
 		__do_kernel_fault(mm, addr, esr, regs);
 }
 
@@ -488,12 +505,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
-static const struct fault_info {
-	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
-	int	sig;
-	int	code;
-	const char *name;
-} fault_info[] = {
+static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 2 address size fault"	},
@@ -560,19 +572,13 @@ static const struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
-static const char *fault_name(unsigned int esr)
-{
-	const struct fault_info *inf = fault_info + (esr & 63);
-	return inf->name;
-}
-
 /*
  * Dispatch a data abort to the relevant handler.
  */
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 					 struct pt_regs *regs)
 {
-	const struct fault_info *inf = fault_info + (esr & 63);
+	const struct fault_info *inf = esr_to_fault_info(esr);
 	struct siginfo info;
 
 	if (!inf->fn(addr, esr, regs))
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index e25584d72396..7514a000e361 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -294,10 +294,6 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
-	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
-		hugetlb_add_hstate(CONT_PTE_SHIFT);
-	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
-		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -306,13 +302,3 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
-	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
-		hugetlb_add_hstate(CONT_PTE_SHIFT);
-	return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 55d1e9205543..687a358a3733 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -162,7 +162,7 @@ void __init kasan_init(void)
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
 	vmemmap_populate(kimg_shadow_start, kimg_shadow_end,
-			 pfn_to_nid(virt_to_pfn(_text)));
+			 pfn_to_nid(virt_to_pfn(lm_alias(_text))));
 
 	/*
 	 * vmemmap_populate() has populated the shadow region that covers the
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 7c16e547ccb2..b02a9268dfbf 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -83,6 +83,25 @@
 /* Rt = Rn[0]; Rt2 = Rn[8]; Rn += 16; */
 #define A64_POP(Rt, Rt2, Rn)  A64_LS_PAIR(Rt, Rt2, Rn, 16, LOAD, POST_INDEX)
 
+/* Load/store exclusive */
+#define A64_SIZE(sf) \
+	((sf) ? AARCH64_INSN_SIZE_64 : AARCH64_INSN_SIZE_32)
+#define A64_LSX(sf, Rt, Rn, Rs, type) \
+	aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
+				       AARCH64_INSN_LDST_##type)
+/* Rt = [Rn]; (atomic) */
+#define A64_LDXR(sf, Rt, Rn) \
+	A64_LSX(sf, Rt, Rn, A64_ZR, LOAD_EX)
+/* [Rn] = Rt; (atomic) Rs = [state] */
+#define A64_STXR(sf, Rt, Rn, Rs) \
+	A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
+
+/* Prefetch */
+#define A64_PRFM(Rn, type, target, policy) \
+	aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \
+				  AARCH64_INSN_PRFM_TARGET_##target, \
+				  AARCH64_INSN_PRFM_POLICY_##policy)
+
 /* Add/subtract (immediate) */
 #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
 	aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a785554916c0..d68abde52740 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -321,6 +321,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+	const bool isdw = BPF_SIZE(code) == BPF_DW;
 	u8 jmp_cond;
 	s32 jmp_offset;
 
@@ -604,15 +605,6 @@ emit_cond_jmp:
 		const struct bpf_insn insn1 = insn[1];
 		u64 imm64;
 
-		if (insn1.code != 0 || insn1.src_reg != 0 ||
-		    insn1.dst_reg != 0 || insn1.off != 0) {
-			/* Note: verifier in BPF core must catch invalid
-			 * instructions.
-			 */
-			pr_err_once("Invalid BPF_LD_IMM64 instruction\n");
-			return -EINVAL;
-		}
-
 		imm64 = (u64)insn1.imm << 32 | (u32)imm;
 		emit_a64_mov_i64(dst, imm64, ctx);
 
@@ -690,7 +682,16 @@ emit_cond_jmp:
 	case BPF_STX | BPF_XADD | BPF_W:
 	/* STX XADD: lock *(u64 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_DW:
-		goto notyet;
+		emit_a64_mov_i(1, tmp, off, ctx);
+		emit(A64_ADD(1, tmp, tmp, dst), ctx);
+		emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
+		emit(A64_LDXR(isdw, tmp2, tmp), ctx);
+		emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
+		emit(A64_STXR(isdw, tmp2, tmp, tmp2), ctx);
+		jmp_offset = -3;
+		check_imm19(jmp_offset);
+		emit(A64_CBNZ(0, tmp2, jmp_offset), ctx);
+		break;
 
 	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
 	case BPF_LD | BPF_ABS | BPF_W:
@@ -757,10 +758,6 @@ emit_cond_jmp:
 		}
 		break;
 	}
-notyet:
-		pr_info_once("*** NOT YET: opcode %02x ***\n", code);
-		return -EFAULT;
-
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
 		return -EINVAL;
@@ -779,14 +776,14 @@ static int build_body(struct jit_ctx *ctx)
 		int ret;
 
 		ret = build_insn(insn, ctx);
-
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
-
 		if (ret > 0) {
 			i++;
+			if (ctx->image == NULL)
+				ctx->offset[i] = ctx->idx;
 			continue;
 		}
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
deleted file mode 100644
index 7e75d45e20cd..000000000000
--- a/arch/avr32/Kconfig
+++ /dev/null
@@ -1,288 +0,0 @@
-config AVR32
-	def_bool y
-	# With EXPERT=n, we get lots of stuff automatically selected
-	# that we usually don't need on AVR32.
-	select EXPERT
-	select HAVE_CLK
-	select HAVE_EXIT_THREAD
-	select HAVE_OPROFILE
-	select HAVE_KPROBES
-	select VIRT_TO_BUS
-	select GENERIC_IRQ_PROBE
-	select GENERIC_ATOMIC64
-	select HARDIRQS_SW_RESEND
-	select GENERIC_IRQ_SHOW
-	select ARCH_HAVE_CUSTOM_GPIO_H
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select GENERIC_CLOCKEVENTS
-	select HAVE_MOD_ARCH_SPECIFIC
-	select MODULES_USE_ELF_RELA
-	select HAVE_NMI
-	help
-	  AVR32 is a high-performance 32-bit RISC microprocessor core,
-	  designed for cost-sensitive embedded applications, with particular
-	  emphasis on low power consumption and high code density.
-
-	  There is an AVR32 Linux project with a web page at
-	  http://avr32linux.org/.
-
-config STACKTRACE_SUPPORT
-	def_bool y
-
-config LOCKDEP_SUPPORT
-	def_bool y
-
-config TRACE_IRQFLAGS_SUPPORT
-	def_bool y
-
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool n
-
-config ARCH_HAS_ILOG2_U32
-	def_bool n
-
-config ARCH_HAS_ILOG2_U64
-	def_bool n
-
-config GENERIC_HWEIGHT
-	def_bool y
-
-config GENERIC_CALIBRATE_DELAY
-	def_bool y
-
-config GENERIC_BUG
-	def_bool y
-	depends on BUG
-
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
-menu "System Type and features"
-
-config SUBARCH_AVR32B
-	bool
-config MMU
-	bool
-config PERFORMANCE_COUNTERS
-	bool
-
-config PLATFORM_AT32AP
-	bool
-	select SUBARCH_AVR32B
-	select MMU
-	select PERFORMANCE_COUNTERS
-	select GPIOLIB
-	select GENERIC_ALLOCATOR
-	select HAVE_FB_ATMEL
-
-#
-# CPU types
-#
-
-# AP7000 derivatives
-config CPU_AT32AP700X
-	bool
-	select PLATFORM_AT32AP
-config CPU_AT32AP7000
-	bool
-	select CPU_AT32AP700X
-config CPU_AT32AP7001
-	bool
-	select CPU_AT32AP700X
-config CPU_AT32AP7002
-	bool
-	select CPU_AT32AP700X
-
-# AP700X boards
-config BOARD_ATNGW100_COMMON
-	bool
-	select CPU_AT32AP7000
-
-choice
-	prompt "AVR32 board type"
-	default BOARD_ATSTK1000
-
-config BOARD_ATSTK1000
-	bool "ATSTK1000 evaluation board"
-
-config BOARD_ATNGW100_MKI
-	bool "ATNGW100 Network Gateway"
-	select BOARD_ATNGW100_COMMON
-
-config BOARD_ATNGW100_MKII
-	bool "ATNGW100 mkII Network Gateway"
-	select BOARD_ATNGW100_COMMON
-
-config BOARD_HAMMERHEAD
-	bool "Hammerhead board"
-	select CPU_AT32AP7000
-	select USB_ARCH_HAS_HCD
-	help
-	  The Hammerhead platform is built around an AVR32 32-bit microcontroller from Atmel.
-	  It offers versatile peripherals, such as ethernet, usb device, usb host etc.
-
-	  The board also incorporates a power supply and is a Power over Ethernet (PoE) Powered
-	  Device (PD).
-
-	  Additionally, a Cyclone III FPGA from Altera is integrated on the board. The FPGA is
-	  mapped into the 32-bit AVR memory bus. The FPGA offers two DDR2 SDRAM interfaces, which
-	  will cover even the most exceptional need of memory bandwidth. Together with the onboard
-	  video decoder the board is ready for video processing.
-
-	  For more information see: http://www.miromico.ch/index.php/hammerhead.html 
-
-config BOARD_FAVR_32
-	bool "Favr-32 LCD-board"
-	select CPU_AT32AP7000
-
-config BOARD_MERISC
-	bool "Merisc board"
-	select CPU_AT32AP7000
-	help
-	  Merisc is the family name for a range of AVR32-based boards.
-
-	  The boards are designed to be used in a man-machine
-	  interfacing environment, utilizing a touch-based graphical
-	  user interface. They host a vast range of I/O peripherals as
-	  well as a large SDRAM & Flash memory bank.
-
-	  For more information see: http://www.martinsson.se/merisc
-
-config BOARD_MIMC200
-	bool "MIMC200 CPU board"
-	select CPU_AT32AP7000
-endchoice
-
-source "arch/avr32/boards/atstk1000/Kconfig"
-source "arch/avr32/boards/atngw100/Kconfig"
-source "arch/avr32/boards/hammerhead/Kconfig"
-source "arch/avr32/boards/favr-32/Kconfig"
-source "arch/avr32/boards/merisc/Kconfig"
-
-choice
-	prompt "Boot loader type"
-	default LOADER_U_BOOT
-
-config	LOADER_U_BOOT
-	bool "U-Boot (or similar) bootloader"
-endchoice
-
-source "arch/avr32/mach-at32ap/Kconfig"
-
-config LOAD_ADDRESS
-	hex
-	default 0x10000000 if LOADER_U_BOOT=y && CPU_AT32AP700X=y
-
-config ENTRY_ADDRESS
-	hex
-	default 0x90000000 if LOADER_U_BOOT=y && CPU_AT32AP700X=y
-
-config PHYS_OFFSET
-	hex
-	default 0x10000000 if CPU_AT32AP700X=y
-
-source "kernel/Kconfig.preempt"
-
-config QUICKLIST
-	def_bool y
-
-config ARCH_HAVE_MEMORY_PRESENT
-	def_bool n
-
-config NEED_NODE_MEMMAP_SIZE
-	def_bool n
-
-config ARCH_FLATMEM_ENABLE
-	def_bool y
-
-config ARCH_DISCONTIGMEM_ENABLE
-	def_bool n
-
-config ARCH_SPARSEMEM_ENABLE
-	def_bool n
-
-config NODES_SHIFT
-	int
-	default "2"
-	depends on NEED_MULTIPLE_NODES
-
-source "mm/Kconfig"
-
-config OWNERSHIP_TRACE
-	bool "Ownership trace support"
-	default y
-	help
-	  Say Y to generate an Ownership Trace message on every context switch,
-	  enabling Nexus-compliant debuggers to keep track of the PID of the
-	  currently executing task.
-
-config NMI_DEBUGGING
-	bool "NMI Debugging"
-	default n
-	help
-	  Say Y here and pass the nmi_debug command-line parameter to
-	  the kernel to turn on NMI debugging. Depending on the value
-	  of the nmi_debug option, various pieces of information will
-	  be dumped to the console when a Non-Maskable Interrupt
-	  happens.
-
-# FPU emulation goes here
-
-source "kernel/Kconfig.hz"
-
-config CMDLINE
-	string "Default kernel command line"
-	default ""
-	help
-	  If you don't have a boot loader capable of passing a command line string
-	  to the kernel, you may specify one here. As a minimum, you should specify
-	  the memory size and the root device (e.g., mem=8M, root=/dev/nfs).
-
-endmenu
-
-menu "Power management options"
-
-source "kernel/power/Kconfig"
-
-config ARCH_SUSPEND_POSSIBLE
-	def_bool y
-
-menu "CPU Frequency scaling"
-source "drivers/cpufreq/Kconfig"
-endmenu
-
-endmenu
-
-menu "Bus options"
-
-config PCI
-	bool
-
-source "drivers/pci/Kconfig"
-
-source "drivers/pcmcia/Kconfig"
-
-endmenu
-
-menu "Executable file formats"
-source "fs/Kconfig.binfmt"
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
-source "arch/avr32/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/avr32/Kconfig.debug b/arch/avr32/Kconfig.debug
deleted file mode 100644
index 2283933a9a93..000000000000
--- a/arch/avr32/Kconfig.debug
+++ /dev/null
@@ -1,9 +0,0 @@
-menu "Kernel hacking"
-
-config TRACE_IRQFLAGS_SUPPORT
-	bool
-	default y
-
-source "lib/Kconfig.debug"
-
-endmenu
diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile
deleted file mode 100644
index dba48a5d5bb9..000000000000
--- a/arch/avr32/Makefile
+++ /dev/null
@@ -1,84 +0,0 @@
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# Copyright (C) 2004-2006 Atmel Corporation.
-
-# Default target when executing plain make
-.PHONY: all
-all: uImage vmlinux.elf
-
-KBUILD_DEFCONFIG	:= atstk1002_defconfig
-
-KBUILD_CFLAGS	+= -pipe -fno-builtin -mno-pic -D__linux__
-KBUILD_AFLAGS	+= -mrelax -mno-pic
-KBUILD_CFLAGS_MODULE += -mno-relax
-LDFLAGS_vmlinux	+= --relax
-
-cpuflags-$(CONFIG_PLATFORM_AT32AP)	+= -march=ap
-
-KBUILD_CFLAGS	+= $(cpuflags-y)
-KBUILD_AFLAGS	+= $(cpuflags-y)
-
-CHECKFLAGS	+= -D__avr32__ -D__BIG_ENDIAN
-
-machine-$(CONFIG_PLATFORM_AT32AP) := at32ap
-machdirs	:= $(patsubst %,arch/avr32/mach-%/, $(machine-y))
-
-KBUILD_CPPFLAGS	+= $(patsubst %,-I$(srctree)/%include,$(machdirs))
-
-head-$(CONFIG_LOADER_U_BOOT)		+= arch/avr32/boot/u-boot/head.o
-head-y					+= arch/avr32/kernel/head.o
-core-y					+= $(machdirs)
-core-$(CONFIG_BOARD_ATSTK1000)		+= arch/avr32/boards/atstk1000/
-core-$(CONFIG_BOARD_ATNGW100_COMMON)	+= arch/avr32/boards/atngw100/
-core-$(CONFIG_BOARD_HAMMERHEAD)		+= arch/avr32/boards/hammerhead/
-core-$(CONFIG_BOARD_FAVR_32)		+= arch/avr32/boards/favr-32/
-core-$(CONFIG_BOARD_MERISC)		+= arch/avr32/boards/merisc/
-core-$(CONFIG_BOARD_MIMC200)		+= arch/avr32/boards/mimc200/
-core-$(CONFIG_LOADER_U_BOOT)		+= arch/avr32/boot/u-boot/
-core-y					+= arch/avr32/kernel/
-core-y					+= arch/avr32/mm/
-drivers-$(CONFIG_OPROFILE)		+= arch/avr32/oprofile/
-libs-y					+= arch/avr32/lib/
-
-BOOT_TARGETS := vmlinux.elf vmlinux.bin uImage uImage.srec
-
-.PHONY: $(BOOT_TARGETS) install
-
-boot := arch/$(ARCH)/boot/images
-
-             KBUILD_IMAGE := $(boot)/uImage
-vmlinux.elf: KBUILD_IMAGE := $(boot)/vmlinux.elf
-vmlinux.cso: KBUILD_IMAGE := $(boot)/vmlinux.cso
-uImage.srec: KBUILD_IMAGE := $(boot)/uImage.srec
-uImage:      KBUILD_IMAGE := $(boot)/uImage
-
-quiet_cmd_listing = LST     $@
-      cmd_listing = avr32-linux-objdump $(OBJDUMPFLAGS) -lS $< > $@
-quiet_cmd_disasm  = DIS     $@
-      cmd_disasm  = avr32-linux-objdump $(OBJDUMPFLAGS) -d $< > $@
-
-vmlinux.elf vmlinux.bin uImage.srec uImage vmlinux.cso: vmlinux
-	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-
-install: vmlinux
-	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@
-
-vmlinux.s: vmlinux
-	$(call if_changed,disasm)
-
-vmlinux.lst: vmlinux
-	$(call if_changed,listing)
-
-CLEAN_FILES += vmlinux.s vmlinux.lst
-
-archclean:
-	$(Q)$(MAKE) $(clean)=$(boot)
-
-define archhelp
-  @echo '* vmlinux.elf		- ELF image with load address 0'
-  @echo '  vmlinux.cso		- PathFinder CSO image'
-  @echo '* uImage		- Create a bootable image for U-Boot'
-endef
diff --git a/arch/avr32/boards/atngw100/Kconfig b/arch/avr32/boards/atngw100/Kconfig
deleted file mode 100644
index 4e55617ade2d..000000000000
--- a/arch/avr32/boards/atngw100/Kconfig
+++ /dev/null
@@ -1,65 +0,0 @@
-# NGW100 customization
-
-if BOARD_ATNGW100_COMMON
-
-config BOARD_ATNGW100_MKII_LCD
-	bool "Enable ATNGW100 mkII LCD interface"
-	depends on BOARD_ATNGW100_MKII
-	help
-	  This enables the LCD controller (LCDC) in the AT32AP7000. Since the
-	  LCDC is multiplexed with MACB1 (LAN) Ethernet port, only one can be
-	  enabled at a time.
-
-	  This choice enables the LCDC and disables the MACB1 interface marked
-	  LAN on the PCB.
-
-choice
-	prompt "Select an NGW100 add-on board to support"
-	default BOARD_ATNGW100_ADDON_NONE
-
-config BOARD_ATNGW100_ADDON_NONE
-	bool "None"
-
-config BOARD_ATNGW100_EVKLCD10X
-	bool "EVKLCD10X addon board"
-	depends on BOARD_ATNGW100_MKI || BOARD_ATNGW100_MKII_LCD
-	help
-	  This enables support for the EVKLCD100 (QVGA) or EVKLCD101 (VGA)
-	  addon board for the NGW100 and NGW100 mkII. By enabling this the LCD
-	  controller and AC97 controller is added as platform devices.
-
-config BOARD_ATNGW100_MRMT
-	bool "Mediama RMT1/2 add-on board"
-	help
-	  This enables support for the Mediama RMT1 or RMT2 board.
-	  RMT provides LCD support, AC97 codec and other
-	  optional peripherals to the Atmel NGW100.
-
-	  This choice disables the detect pin and the write-protect pin for the
-	  MCI platform device, since it conflicts with the LCD platform device.
-	  The MCI pins can be reenabled by editing the "add device function" but
-	  this may break the setup for other displays that use these pins.
-
-endchoice
-
-choice
-	prompt "LCD panel resolution on EVKLCD10X"
-	depends on BOARD_ATNGW100_EVKLCD10X
-	default BOARD_ATNGW100_EVKLCD10X_VGA
-
-config BOARD_ATNGW100_EVKLCD10X_QVGA
-	bool "QVGA (320x240)"
-
-config BOARD_ATNGW100_EVKLCD10X_VGA
-	bool "VGA (640x480)"
-
-config BOARD_ATNGW100_EVKLCD10X_POW_QVGA
-	bool "Powertip QVGA (320x240)"
-
-endchoice
-
-if BOARD_ATNGW100_MRMT
-source	"arch/avr32/boards/atngw100/Kconfig_mrmt"
-endif
-
-endif	# BOARD_ATNGW100_COMMON
diff --git a/arch/avr32/boards/atngw100/Kconfig_mrmt b/arch/avr32/boards/atngw100/Kconfig_mrmt
deleted file mode 100644
index 9a199a207f3c..000000000000
--- a/arch/avr32/boards/atngw100/Kconfig_mrmt
+++ /dev/null
@@ -1,80 +0,0 @@
-# RMT for NGW100 customization
-
-choice
-	prompt "RMT Version"
-	help
-	  Select the RMTx board version.
-
-config BOARD_MRMT_REV1
-	bool "RMT1"
-config BOARD_MRMT_REV2
-	bool "RMT2"
-
-endchoice
-
-config BOARD_MRMT_AC97
-	bool "Enable AC97 CODEC"
-	help
-	  Enable the UCB1400 AC97 CODEC driver.
-
-choice
-	prompt "Touchscreen Driver"
-	default BOARD_MRMT_ADS7846_TS
-
-config BOARD_MRMT_UCB1400_TS
-	bool "Use UCB1400 Touchscreen"
-
-config BOARD_MRMT_ADS7846_TS
-	bool "Use ADS7846 Touchscreen"
-
-endchoice
-
-choice
-	prompt "RMTx LCD Selection"
-	default BOARD_MRMT_LCD_DISABLE
-
-config BOARD_MRMT_LCD_DISABLE
-	bool "LCD Disabled"
-
-config BOARD_MRMT_LCD_LQ043T3DX0X
-	bool "Sharp LQ043T3DX0x or compatible"
-	help
-	  If using RMT2, be sure to load the resistor pack selectors accordingly
-
-if BOARD_MRMT_REV2
-config BOARD_MRMT_LCD_KWH043GM08
-	bool "Formike KWH043GM08 or compatible"
-	help
-	  Be sure to load the RMT2 resistor pack selectors accordingly
-endif
-
-endchoice
-
-if !BOARD_MRMT_LCD_DISABLE
-config BOARD_MRMT_BL_PWM
-	bool "Use PWM control for LCD Backlight"
-	help
-		Use PWM driver for controlling LCD Backlight.
-		Otherwise, LCD Backlight is always on.
-endif
-
-config BOARD_MRMT_RTC_I2C
-	bool "Use External RTC on I2C Bus"
-	help
-		RMT1 has an optional RTC device on the I2C bus.
-		It is a SII S35390A.  Be sure to select the
-		matching RTC driver.
-
-choice
-	prompt "Wireless Module on ttyS2"
-	default BOARD_MRMT_WIRELESS_ZB
-
-config BOARD_MRMT_WIRELESS_ZB
-	bool "Use ZigBee/802.15.4 Module"
-
-config BOARD_MRMT_WIRELESS_BT
-	bool "Use Bluetooth (HCI) Module"
-
-config BOARD_MRMT_WIRELESS_NONE
-	bool "Not Installed"
-endchoice
diff --git a/arch/avr32/boards/atngw100/Makefile b/arch/avr32/boards/atngw100/Makefile
deleted file mode 100644
index f4ebe42a8254..000000000000
--- a/arch/avr32/boards/atngw100/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-obj-y					+= setup.o flash.o
-obj-$(CONFIG_BOARD_ATNGW100_EVKLCD10X)	+= evklcd10x.o
-obj-$(CONFIG_BOARD_ATNGW100_MRMT)	+= mrmt.o
diff --git a/arch/avr32/boards/atngw100/evklcd10x.c b/arch/avr32/boards/atngw100/evklcd10x.c
deleted file mode 100644
index 64919b0da7aa..000000000000
--- a/arch/avr32/boards/atngw100/evklcd10x.c
+++ /dev/null
@@ -1,178 +0,0 @@
-/*
- * Board-specific setup code for the ATEVKLCD10X addon board to the ATNGW100
- * Network Gateway
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/gpio.h>
-#include <linux/fb.h>
-#include <linux/platform_device.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/portmux.h>
-#include <mach/board.h>
-
-#include <sound/atmel-ac97c.h>
-
-static struct ac97c_platform_data __initdata ac97c0_data = {
-	.reset_pin = GPIO_PIN_PB(19),
-};
-
-#ifdef CONFIG_BOARD_ATNGW100_EVKLCD10X_VGA
-static struct fb_videomode __initdata tcg057vglad_modes[] = {
-	{
-		.name		= "640x480 @ 50",
-		.refresh	= 50,
-		.xres		= 640,		.yres		= 480,
-		.pixclock	= KHZ2PICOS(25180),
-
-		.left_margin	= 64,		.right_margin	= 96,
-		.upper_margin	= 34,		.lower_margin	= 11,
-		.hsync_len	= 64,		.vsync_len	= 15,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
-	.manufacturer		= "KYO",
-	.monitor		= "TCG057VGLAD",
-	.modedb			= tcg057vglad_modes,
-	.modedb_len		= ARRAY_SIZE(tcg057vglad_modes),
-	.hfmin			= 19948,
-	.hfmax			= 31478,
-	.vfmin			= 50,
-	.vfmax			= 67,
-	.dclkmax		= 28330000,
-};
-
-static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
-	.default_bpp		= 16,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &atevklcd10x_default_monspecs,
-	.guard_time		= 2,
-};
-#elif CONFIG_BOARD_ATNGW100_EVKLCD10X_QVGA
-static struct fb_videomode __initdata tcg057qvlad_modes[] = {
-	{
-		.name		= "320x240 @ 50",
-		.refresh	= 50,
-		.xres		= 320,		.yres		= 240,
-		.pixclock	= KHZ2PICOS(6300),
-
-		.left_margin	= 34,		.right_margin	= 46,
-		.upper_margin	= 7,		.lower_margin	= 15,
-		.hsync_len	= 64,		.vsync_len	= 12,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
-	.manufacturer		= "KYO",
-	.monitor		= "TCG057QVLAD",
-	.modedb			= tcg057qvlad_modes,
-	.modedb_len		= ARRAY_SIZE(tcg057qvlad_modes),
-	.hfmin			= 19948,
-	.hfmax			= 31478,
-	.vfmin			= 50,
-	.vfmax			= 67,
-	.dclkmax		= 7000000,
-};
-
-static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
-	.default_bpp		= 16,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &atevklcd10x_default_monspecs,
-	.guard_time		= 2,
-};
-#elif CONFIG_BOARD_ATNGW100_EVKLCD10X_POW_QVGA
-static struct fb_videomode __initdata ph320240t_modes[] = {
-	{
-		.name		= "320x240 @ 60",
-		.refresh	= 60,
-		.xres		= 320,		.yres		= 240,
-		.pixclock	= KHZ2PICOS(6300),
-
-		.left_margin	= 38,		.right_margin	= 20,
-		.upper_margin	= 15,		.lower_margin	= 5,
-		.hsync_len	= 30,		.vsync_len	= 3,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
-	.manufacturer		= "POW",
-	.monitor		= "PH320240T",
-	.modedb			= ph320240t_modes,
-	.modedb_len		= ARRAY_SIZE(ph320240t_modes),
-	.hfmin			= 14400,
-	.hfmax			= 21600,
-	.vfmin			= 50,
-	.vfmax			= 90,
-	.dclkmax		= 6400000,
-};
-
-static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
-	.default_bpp		= 16,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &atevklcd10x_default_monspecs,
-	.guard_time		= 2,
-};
-#endif
-
-static void atevklcd10x_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on)
-{
-	gpio_set_value(GPIO_PIN_PB(15), on);
-}
-
-static int __init atevklcd10x_init(void)
-{
-	/* PB15 is connected to the enable line on the boost regulator
-	 * controlling the backlight for the LCD panel.
-	 */
-	at32_select_gpio(GPIO_PIN_PB(15), AT32_GPIOF_OUTPUT);
-	gpio_request(GPIO_PIN_PB(15), "backlight");
-	gpio_direction_output(GPIO_PIN_PB(15), 0);
-
-	atevklcd10x_lcdc_data.atmel_lcdfb_power_control =
-		atevklcd10x_lcdc_power_control;
-
-	at32_add_device_lcdc(0, &atevklcd10x_lcdc_data,
-			fbmem_start, fbmem_size,
-#ifdef CONFIG_BOARD_ATNGW100_MKII
-			ATMEL_LCDC_PRI_18BIT | ATMEL_LCDC_PC_DVAL
-#else
-			ATMEL_LCDC_ALT_18BIT | ATMEL_LCDC_PE_DVAL
-#endif
-			);
-
-	at32_add_device_ac97c(0, &ac97c0_data, AC97C_BOTH);
-
-	return 0;
-}
-postcore_initcall(atevklcd10x_init);
diff --git a/arch/avr32/boards/atngw100/flash.c b/arch/avr32/boards/atngw100/flash.c
deleted file mode 100644
index 55ccc9ce4892..000000000000
--- a/arch/avr32/boards/atngw100/flash.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * ATNGW100 board-specific flash initialization
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 40,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 10,
-
-	.ncs_read_pulse		= 80,
-	.nrd_pulse		= 40,
-	.ncs_write_pulse	= 65,
-	.nwe_pulse		= 55,
-
-	.read_cycle		= 120,
-	.write_cycle		= 120,
-};
-
-static struct smc_config flash_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 1,
-};
-
-static struct mtd_partition flash_parts[] = {
-	{
-		.name           = "u-boot",
-		.offset         = 0x00000000,
-		.size           = 0x00020000,           /* 128 KiB */
-		.mask_flags     = MTD_WRITEABLE,
-	},
-	{
-		.name           = "root",
-		.offset         = 0x00020000,
-		.size           = 0x007d0000,
-	},
-	{
-		.name           = "env",
-		.offset         = 0x007f0000,
-		.size           = 0x00010000,
-		.mask_flags     = MTD_WRITEABLE,
-	},
-};
-
-static struct physmap_flash_data flash_data = {
-	.width		= 2,
-	.nr_parts	= ARRAY_SIZE(flash_parts),
-	.parts		= flash_parts,
-};
-
-static struct resource flash_resource = {
-	.start		= 0x00000000,
-	.end		= 0x007fffff,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.resource	= &flash_resource,
-	.num_resources	= 1,
-	.dev		= {
-		.platform_data = &flash_data,
-	},
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init atngw100_flash_init(void)
-{
-	int ret;
-
-	smc_set_timing(&flash_config, &flash_timing);
-	ret = smc_set_configuration(0, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "atngw100: failed to set NOR flash timing\n");
-		return ret;
-	}
-
-	platform_device_register(&flash_device);
-
-	return 0;
-}
-device_initcall(atngw100_flash_init);
diff --git a/arch/avr32/boards/atngw100/mrmt.c b/arch/avr32/boards/atngw100/mrmt.c
deleted file mode 100644
index 99b0a7984950..000000000000
--- a/arch/avr32/boards/atngw100/mrmt.c
+++ /dev/null
@@ -1,382 +0,0 @@
-/*
- * Board-specific setup code for Remote Media Terminal 1 (RMT1)
- * add-on board for the ATNGW100 Network Gateway
- *
- * Copyright (C) 2008 Mediama Technologies
- * Based on ATNGW100 Network Gateway (Copyright (C) Atmel)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/gpio.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/fb.h>
-#include <linux/leds.h>
-#include <linux/pwm.h>
-#include <linux/leds_pwm.h>
-#include <linux/input.h>
-#include <linux/gpio_keys.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/ads7846.h>
-
-#include <video/atmel_lcdc.h>
-#include <sound/atmel-ac97c.h>
-
-#include <asm/delay.h>
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-/* Define board-specifoic GPIO assignments */
-#define PIN_LCD_BL	GPIO_PIN_PA(28)
-#define PWM_CH_BL	0	/* Must match with GPIO pin definition */
-#define PIN_LCD_DISP	GPIO_PIN_PA(31)
-#define	PIN_AC97_RST_N	GPIO_PIN_PA(30)
-#define PB_EXTINT_BASE	25
-#define TS_IRQ		0
-#define PIN_TS_EXTINT	GPIO_PIN_PB(PB_EXTINT_BASE+TS_IRQ)
-#define PIN_PB_LEFT	GPIO_PIN_PB(11)
-#define PIN_PB_RIGHT	GPIO_PIN_PB(12)
-#define PIN_PWR_SW_N	GPIO_PIN_PB(14)
-#define PIN_PWR_ON	GPIO_PIN_PB(13)
-#define PIN_ZB_RST_N	GPIO_PIN_PA(21)
-#define PIN_BT_RST	GPIO_PIN_PA(22)
-#define PIN_LED_SYS	GPIO_PIN_PA(16)
-#define PIN_LED_A	GPIO_PIN_PA(19)
-#define PIN_LED_B	GPIO_PIN_PE(19)
-
-#ifdef CONFIG_BOARD_MRMT_LCD_LQ043T3DX0X
-/* Sharp LQ043T3DX0x (or compatible) panel */
-static struct fb_videomode __initdata lcd_fb_modes[] = {
-	{
-		.name		= "480x272 @ 59.94Hz",
-		.refresh	= 59.94,
-		.xres		= 480,		.yres		= 272,
-		.pixclock	= KHZ2PICOS(9000),
-
-		.left_margin	= 2,		.right_margin	= 2,
-		.upper_margin	= 3,		.lower_margin	= 9,
-		.hsync_len	= 41,		.vsync_len	= 1,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata lcd_fb_default_monspecs = {
-	.manufacturer		= "SHA",
-	.monitor		= "LQ043T3DX02",
-	.modedb			= lcd_fb_modes,
-	.modedb_len		= ARRAY_SIZE(lcd_fb_modes),
-	.hfmin			= 14915,
-	.hfmax			= 17638,
-	.vfmin			= 53,
-	.vfmax			= 61,
-	.dclkmax		= 9260000,
-};
-
-static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = {
-	.default_bpp		= 24,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_INVCLK_NORMAL
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.lcd_wiring_mode	= ATMEL_LCDC_WIRING_RGB,
-	.default_monspecs	= &lcd_fb_default_monspecs,
-	.guard_time		= 2,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_LCD_KWH043GM08
-/* Sharp KWH043GM08-Fxx (or compatible) panel */
-static struct fb_videomode __initdata lcd_fb_modes[] = {
-	{
-		.name		= "480x272 @ 59.94Hz",
-		.refresh	= 59.94,
-		.xres		= 480,		.yres		= 272,
-		.pixclock	= KHZ2PICOS(9000),
-
-		.left_margin	= 2,		.right_margin	= 2,
-		.upper_margin	= 3,		.lower_margin	= 9,
-		.hsync_len	= 41,		.vsync_len	= 1,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata lcd_fb_default_monspecs = {
-	.manufacturer		= "FOR",
-	.monitor		= "KWH043GM08",
-	.modedb			= lcd_fb_modes,
-	.modedb_len		= ARRAY_SIZE(lcd_fb_modes),
-	.hfmin			= 14915,
-	.hfmax			= 17638,
-	.vfmin			= 53,
-	.vfmax			= 61,
-	.dclkmax		= 9260000,
-};
-
-static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = {
-	.default_bpp		= 24,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_INVCLK_INVERTED
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.lcd_wiring_mode	= ATMEL_LCDC_WIRING_RGB,
-	.default_monspecs	= &lcd_fb_default_monspecs,
-	.guard_time		= 2,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_AC97
-static struct ac97c_platform_data __initdata ac97c0_data = {
-	.reset_pin		= PIN_AC97_RST_N,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_UCB1400_TS
-/* NOTE: IRQ assignment relies on kernel module parameter */
-static struct platform_device rmt_ts_device = {
-	.name	= "ucb1400_ts",
-	.id	= -1,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_BL_PWM
-/* PWM LEDs: LCD Backlight, etc */
-static struct pwm_lookup pwm_lookup[] = {
-	PWM_LOOKUP("at91sam9rl-pwm", PWM_CH_BL, "leds_pwm", "ds1",
-		   5000, PWM_POLARITY_INVERSED),
-};
-
-static struct led_pwm pwm_leds[] = {
-	{
-		.name = "backlight",
-		.max_brightness = 255,
-	},
-};
-
-static struct led_pwm_platform_data pwm_data = {
-	.num_leds       = ARRAY_SIZE(pwm_leds),
-	.leds           = pwm_leds,
-};
-
-static struct platform_device leds_pwm = {
-	.name   = "leds_pwm",
-	.id     = -1,
-	.dev    = {
-		.platform_data = &pwm_data,
-	},
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_ADS7846_TS
-static int ads7846_pendown_state(void)
-{
-	return !gpio_get_value( PIN_TS_EXTINT );	/* PENIRQ.*/
-}
-
-static struct ads7846_platform_data ads_info = {
-	.model				= 7846,
-	.keep_vref_on			= 0,	/* Use external VREF pin */
-	.vref_delay_usecs		= 0,
-	.vref_mv			= 3300,	/* VREF = 3.3V */
-	.settle_delay_usecs		= 800,
-	.penirq_recheck_delay_usecs	= 800,
-	.x_plate_ohms			= 750,
-	.y_plate_ohms			= 300,
-	.pressure_max			= 4096,
-	.debounce_max			= 1,
-	.debounce_rep			= 0,
-	.debounce_tol			= (~0),
-	.get_pendown_state		= ads7846_pendown_state,
-	.filter				= NULL,
-	.filter_init			= NULL,
-};
-
-static struct spi_board_info spi01_board_info[] __initdata = {
-	{
-		.modalias	= "ads7846",
-		.max_speed_hz	= 31250*26,
-		.bus_num	= 0,
-		.chip_select	= 1,
-		.platform_data	= &ads_info,
-		.irq		= AT32_EXTINT(TS_IRQ),
-	},
-};
-#endif
-
-/* GPIO Keys: left, right, power, etc */
-static const struct gpio_keys_button rmt_gpio_keys_buttons[] = {
-	[0] = {
-		.type		= EV_KEY,
-		.code		= KEY_POWER,
-		.gpio		= PIN_PWR_SW_N,
-		.active_low	= 1,
-		.desc		= "power button",
-	},
-	[1] = {
-		.type		= EV_KEY,
-		.code		= KEY_LEFT,
-		.gpio		= PIN_PB_LEFT,
-		.active_low	= 1,
-		.desc		= "left button",
-	},
-	[2] = {
-		.type		= EV_KEY,
-		.code		= KEY_RIGHT,
-		.gpio		= PIN_PB_RIGHT,
-		.active_low	= 1,
-		.desc		= "right button",
-	},
-};
-
-static const struct gpio_keys_platform_data rmt_gpio_keys_data = {
-	.nbuttons =	ARRAY_SIZE(rmt_gpio_keys_buttons),
-	.buttons =	(void *) rmt_gpio_keys_buttons,
-};
-
-static struct platform_device rmt_gpio_keys = {
-	.name =		"gpio-keys",
-	.id =		-1,
-	.dev = {
-		.platform_data = (void *) &rmt_gpio_keys_data,
-	}
-};
-
-#ifdef CONFIG_BOARD_MRMT_RTC_I2C
-static struct i2c_board_info __initdata mrmt1_i2c_rtc = {
-	I2C_BOARD_INFO("s35390a", 0x30),
-	.irq		= 0,
-};
-#endif
-
-static void mrmt_power_off(void)
-{
-	/* PWR_ON=0 will force power off */
-	gpio_set_value( PIN_PWR_ON, 0 );
-}
-
-static int __init mrmt1_init(void)
-{
-	gpio_set_value( PIN_PWR_ON, 1 );	/* Ensure PWR_ON is enabled */
-
-	pm_power_off = mrmt_power_off;
-
-	/* Setup USARTS (other than console) */
-	at32_map_usart(2, 1, 0);	/* USART 2: /dev/ttyS1, RMT1:DB9M */
-	at32_map_usart(3, 2, ATMEL_USART_RTS | ATMEL_USART_CTS);
-			/* USART 3: /dev/ttyS2, RMT1:Wireless, w/ RTS/CTS */
-	at32_add_device_usart(1);
-	at32_add_device_usart(2);
-
-	/* Select GPIO Key pins */
-	at32_select_gpio( PIN_PWR_SW_N, AT32_GPIOF_DEGLITCH);
-	at32_select_gpio( PIN_PB_LEFT, AT32_GPIOF_DEGLITCH);
-	at32_select_gpio( PIN_PB_RIGHT, AT32_GPIOF_DEGLITCH);
-	platform_device_register(&rmt_gpio_keys);
-
-#ifdef CONFIG_BOARD_MRMT_RTC_I2C
-	i2c_register_board_info(0, &mrmt1_i2c_rtc, 1);
-#endif
-
-#ifndef CONFIG_BOARD_MRMT_LCD_DISABLE
-	/* User "alternate" LCDC inferface on Port E & D */
-	/* NB: exclude LCDC_CC pin, as NGW100 reserves it for other use */
-	at32_add_device_lcdc(0, &rmt_lcdc_data,
-		fbmem_start, fbmem_size,
-		(ATMEL_LCDC_ALT_24BIT | ATMEL_LCDC_PE_DVAL ) );
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_AC97
-	at32_add_device_ac97c(0, &ac97c0_data, AC97C_BOTH);
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_ADS7846_TS
-	/* Select the Touchscreen interrupt pin mode */
-	at32_select_periph( GPIO_PIOB_BASE, 1 << (PB_EXTINT_BASE+TS_IRQ),
-			GPIO_PERIPH_A, AT32_GPIOF_DEGLITCH);
-	irq_set_irq_type(AT32_EXTINT(TS_IRQ), IRQ_TYPE_EDGE_FALLING);
-	at32_spi_setup_slaves(0,spi01_board_info,ARRAY_SIZE(spi01_board_info));
-	spi_register_board_info(spi01_board_info,ARRAY_SIZE(spi01_board_info));
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_UCB1400_TS
-	/* Select the Touchscreen interrupt pin mode */
-	at32_select_periph( GPIO_PIOB_BASE, 1 << (PB_EXTINT_BASE+TS_IRQ),
-			GPIO_PERIPH_A, AT32_GPIOF_DEGLITCH);
-	platform_device_register(&rmt_ts_device);
-#endif
-
-	at32_select_gpio( PIN_LCD_DISP, AT32_GPIOF_OUTPUT );
-	gpio_request( PIN_LCD_DISP, "LCD_DISP" );
-	gpio_direction_output( PIN_LCD_DISP, 0 );	/* LCD DISP */
-#ifdef CONFIG_BOARD_MRMT_LCD_DISABLE
-	/* Keep Backlight and DISP off */
-	at32_select_gpio( PIN_LCD_BL, AT32_GPIOF_OUTPUT );
-	gpio_request( PIN_LCD_BL, "LCD_BL" );
-	gpio_direction_output( PIN_LCD_BL, 0 );		/* Backlight */
-#else
-	gpio_set_value( PIN_LCD_DISP, 1 );	/* DISP asserted first */
-#ifdef CONFIG_BOARD_MRMT_BL_PWM
-	/* Use PWM for Backlight controls */
-	at32_add_device_pwm(1 << PWM_CH_BL);
-	pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
-	platform_device_register(&leds_pwm);
-#else
-	/* Backlight always on */
-	udelay( 1 );
-	at32_select_gpio( PIN_LCD_BL, AT32_GPIOF_OUTPUT );
-	gpio_request( PIN_LCD_BL, "LCD_BL" );
-	gpio_direction_output( PIN_LCD_BL, 1 );
-#endif
-#endif
-
-	/* Make sure BT and Zigbee modules in reset */
-	at32_select_gpio( PIN_BT_RST, AT32_GPIOF_OUTPUT );
-	gpio_request( PIN_BT_RST, "BT_RST" );
-	gpio_direction_output( PIN_BT_RST, 1 );
-	/* BT Module in Reset */
-
-	at32_select_gpio( PIN_ZB_RST_N, AT32_GPIOF_OUTPUT );
-	gpio_request( PIN_ZB_RST_N, "ZB_RST_N" );
-	gpio_direction_output( PIN_ZB_RST_N, 0 );
-	/* XBee Module in Reset */
-
-#ifdef CONFIG_BOARD_MRMT_WIRELESS_ZB
-	udelay( 1000 );
-	/* Unreset the XBee Module */
-	gpio_set_value( PIN_ZB_RST_N, 1 );
-#endif
-#ifdef CONFIG_BOARD_MRMT_WIRELESS_BT
-	udelay( 1000 );
-	/* Unreset the BT Module */
-	gpio_set_value( PIN_BT_RST, 0 );
-#endif
-
-	return 0;
-}
-arch_initcall(mrmt1_init);
-
-static int __init mrmt1_early_init(void)
-{
-	/* To maintain power-on signal in case boot loader did not already */
-	at32_select_gpio( PIN_PWR_ON, AT32_GPIOF_OUTPUT );
-	gpio_request( PIN_PWR_ON, "PIN_PWR_ON" );
-	gpio_direction_output( PIN_PWR_ON, 1 );
-
-	return 0;
-}
-core_initcall(mrmt1_early_init);
diff --git a/arch/avr32/boards/atngw100/setup.c b/arch/avr32/boards/atngw100/setup.c
deleted file mode 100644
index afeae8978a8d..000000000000
--- a/arch/avr32/boards/atngw100/setup.c
+++ /dev/null
@@ -1,324 +0,0 @@
-/*
- * Board-specific setup code for the ATNGW100 Network Gateway
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/gpio.h>
-#include <linux/irq.h>
-#include <linux/i2c.h>
-#include <linux/i2c-gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/atmel-mci.h>
-#include <linux/usb/atmel_usba_udc.h>
-
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 20000000,	/* 20 MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-/*
- * The ATNGW100 mkII is very similar to the ATNGW100. Both have the AT32AP7000
- * chip on board; the difference is that the ATNGW100 mkII has 128 MB 32-bit
- * SDRAM (the ATNGW100 has 32 MB 16-bit SDRAM) and 256 MB 16-bit NAND flash
- * (the ATNGW100 has none.)
- *
- * The RAM difference is handled by the boot loader, so the only difference we
- * end up handling here is the NAND flash, EBI pin reservation and if LCDC or
- * MACB1 should be enabled.
- */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
-#include <linux/mtd/partitions.h>
-#include <mach/smc.h>
-
-static struct smc_timing nand_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 10,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 10,
-
-	.ncs_read_pulse		= 30,
-	.nrd_pulse		= 15,
-	.ncs_write_pulse	= 30,
-	.nwe_pulse		= 15,
-
-	.read_cycle		= 30,
-	.write_cycle		= 30,
-
-	.ncs_read_recover	= 0,
-	.nrd_recover		= 15,
-	.ncs_write_recover	= 0,
-	/* WE# high -> RE# low min 60 ns */
-	.nwe_recover		= 50,
-};
-
-static struct smc_config nand_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.nwait_mode		= 0,
-	.byte_write		= 0,
-	.tdf_cycles		= 2,
-	.tdf_mode		= 0,
-};
-
-static struct mtd_partition nand_partitions[] = {
-	{
-		.name		= "main",
-		.offset		= 0x00000000,
-		.size		= MTDPART_SIZ_FULL,
-	},
-};
-
-
-static struct atmel_nand_data atngw100mkii_nand_data __initdata = {
-	.cle		= 21,
-	.ale		= 22,
-	.rdy_pin	= GPIO_PIN_PB(28),
-	.enable_pin	= GPIO_PIN_PE(23),
-	.bus_width_16	= true,
-	.ecc_mode	= NAND_ECC_SOFT,
-	.parts		= nand_partitions,
-	.num_parts	= ARRAY_SIZE(nand_partitions),
-};
-#endif
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-struct eth_addr {
-	u8 addr[6];
-};
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2];
-
-static struct spi_board_info spi0_board_info[] __initdata = {
-	{
-		.modalias	= "mtd_dataflash",
-		.max_speed_hz	= 8000000,
-		.chip_select	= 0,
-	},
-};
-
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-#if defined(CONFIG_BOARD_ATNGW100_MKII)
-		.detect_pin	= GPIO_PIN_PC(25),
-		.wp_pin		= GPIO_PIN_PE(22),
-#else
-		.detect_pin	= GPIO_PIN_PC(25),
-		.wp_pin		= GPIO_PIN_PE(0),
-#endif
-	},
-};
-
-static struct usba_platform_data atngw100_usba_data __initdata = {
-#if defined(CONFIG_BOARD_ATNGW100_MKII)
-	.vbus_pin	= GPIO_PIN_PE(26),
-#else
-	.vbus_pin	= -ENODEV,
-#endif
-};
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
-	int i;
-
-	i = tag->u.ethernet.mac_index;
-	if (i < ARRAY_SIZE(hw_addr))
-		memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
-		       sizeof(hw_addr[i].addr));
-
-	return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const u8 *addr;
-	void __iomem *regs;
-	struct clk *pclk;
-
-	if (!res)
-		return;
-	if (pdev->id >= ARRAY_SIZE(hw_addr))
-		return;
-
-	addr = hw_addr[pdev->id].addr;
-	if (!is_valid_ether_addr(addr))
-		return;
-
-	/*
-	 * Since this is board-specific code, we'll cheat and use the
-	 * physical address directly as we happen to know that it's
-	 * the same as the virtual address.
-	 */
-	regs = (void __iomem __force *)res->start;
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk))
-		return;
-
-	clk_enable(pclk);
-	__raw_writel((addr[3] << 24) | (addr[2] << 16)
-		     | (addr[1] << 8) | addr[0], regs + 0x98);
-	__raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-	clk_disable(pclk);
-	clk_put(pclk);
-}
-
-void __init setup_board(void)
-{
-	at32_map_usart(1, 0, 0);	/* USART 1: /dev/ttyS0, DB9 */
-	at32_setup_serial_console(0);
-}
-
-static const struct gpio_led ngw_leds[] = {
-	{ .name = "sys", .gpio = GPIO_PIN_PA(16), .active_low = 1,
-		.default_trigger = "heartbeat",
-	},
-	{ .name = "a", .gpio = GPIO_PIN_PA(19), .active_low = 1, },
-	{ .name = "b", .gpio = GPIO_PIN_PE(19), .active_low = 1, },
-};
-
-static const struct gpio_led_platform_data ngw_led_data = {
-	.num_leds =	ARRAY_SIZE(ngw_leds),
-	.leds =		(void *) ngw_leds,
-};
-
-static struct platform_device ngw_gpio_leds = {
-	.name =		"leds-gpio",
-	.id =		-1,
-	.dev = {
-		.platform_data = (void *) &ngw_led_data,
-	}
-};
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
-	.sda_pin		= GPIO_PIN_PA(6),
-	.scl_pin		= GPIO_PIN_PA(7),
-	.sda_is_open_drain	= 1,
-	.scl_is_open_drain	= 1,
-	.udelay			= 2,	/* close to 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
-	.name		= "i2c-gpio",
-	.id		= 0,
-	.dev		= {
-		.platform_data	= &i2c_gpio_data,
-	},
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {
-	/* NOTE:  original ATtiny24 firmware is at address 0x0b */
-};
-
-static int __init atngw100_init(void)
-{
-	unsigned	i;
-
-	/*
-	 * ATNGW100 mkII uses 32-bit SDRAM interface. Reserve the
-	 * SDRAM-specific pins so that nobody messes with them.
-	 */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
-	at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-	smc_set_timing(&nand_config, &nand_timing);
-	smc_set_configuration(3, &nand_config);
-	at32_add_device_nand(0, &atngw100mkii_nand_data);
-#endif
-
-	at32_add_device_usart(0);
-
-	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
-#ifndef CONFIG_BOARD_ATNGW100_MKII_LCD
-	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
-#endif
-
-	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-	at32_add_device_mci(0, &mci0_data);
-	at32_add_device_usba(0, &atngw100_usba_data);
-
-	for (i = 0; i < ARRAY_SIZE(ngw_leds); i++) {
-		at32_select_gpio(ngw_leds[i].gpio,
-				AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	}
-	platform_device_register(&ngw_gpio_leds);
-
-	/* all these i2c/smbus pins should have external pullups for
-	 * open-drain sharing among all I2C devices.  SDA and SCL do;
-	 * PB28/EXTINT3 (ATNGW100) and PE21 (ATNGW100 mkII) doesn't; it should
-	 * be SMBALERT# (for PMBus), but it's not available off-board.
-	 */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
-	at32_select_periph(GPIO_PIOE_BASE, 1 << 21, 0, AT32_GPIOF_PULLUP);
-#else
-	at32_select_periph(GPIO_PIOB_BASE, 1 << 28, 0, AT32_GPIOF_PULLUP);
-#endif
-	at32_select_gpio(i2c_gpio_data.sda_pin,
-		AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	at32_select_gpio(i2c_gpio_data.scl_pin,
-		AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	platform_device_register(&i2c_gpio_device);
-	i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
-	return 0;
-}
-postcore_initcall(atngw100_init);
-
-static int __init atngw100_arch_init(void)
-{
-	/* PB30 (ATNGW100) and PE30 (ATNGW100 mkII) is the otherwise unused
-	 * jumper on the mainboard, with an external pullup; the jumper grounds
-	 * it. Use it however you like, including letting U-Boot or Linux tweak
-	 * boot sequences.
-	 */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
-	at32_select_gpio(GPIO_PIN_PE(30), 0);
-	gpio_request(GPIO_PIN_PE(30), "j15");
-	gpio_direction_input(GPIO_PIN_PE(30));
-	gpio_export(GPIO_PIN_PE(30), false);
-#else
-	at32_select_gpio(GPIO_PIN_PB(30), 0);
-	gpio_request(GPIO_PIN_PB(30), "j15");
-	gpio_direction_input(GPIO_PIN_PB(30));
-	gpio_export(GPIO_PIN_PB(30), false);
-#endif
-
-	/* set_irq_type() after the arch_initcall for EIC has run, and
-	 * before the I2C subsystem could try using this IRQ.
-	 */
-	return irq_set_irq_type(AT32_EXTINT(3), IRQ_TYPE_EDGE_FALLING);
-}
-arch_initcall(atngw100_arch_init);
diff --git a/arch/avr32/boards/atstk1000/Kconfig b/arch/avr32/boards/atstk1000/Kconfig
deleted file mode 100644
index 8dc48214f0b7..000000000000
--- a/arch/avr32/boards/atstk1000/Kconfig
+++ /dev/null
@@ -1,109 +0,0 @@
-# STK1000 customization
-
-if BOARD_ATSTK1000
-
-choice
-	prompt "ATSTK1000 CPU daughterboard type"
-	default BOARD_ATSTK1002
-
-config BOARD_ATSTK1002
-	bool "ATSTK1002"
-	select CPU_AT32AP7000
-
-config BOARD_ATSTK1003
-	bool "ATSTK1003"
-	select CPU_AT32AP7001
-
-config BOARD_ATSTK1004
-	bool "ATSTK1004"
-	select CPU_AT32AP7002
-
-config BOARD_ATSTK1006
-	bool "ATSTK1006"
-	select CPU_AT32AP7000
-
-endchoice
-
-
-config BOARD_ATSTK100X_CUSTOM
-	bool "Non-default STK1002/STK1003/STK1004 jumper settings"
-	help
-	  You will normally leave the jumpers on the CPU card at their
-	  default settings.  If you need to use certain peripherals,
-	  you will need to change some of those jumpers.
-
-if BOARD_ATSTK100X_CUSTOM
-
-config BOARD_ATSTK100X_SW1_CUSTOM
-	bool "SW1: use SSC1 (not SPI0)"
-	help
-	  This also prevents using the external DAC as an audio interface,
-	  and means you can't initialize the on-board QVGA display.
-
-config BOARD_ATSTK100X_SW2_CUSTOM
-	bool "SW2: use IRDA or TIMER0 (not UART-A, MMC/SD, and PS2-A)"
-	help
-	  If you change this you'll want an updated boot loader putting
-	  the console on UART-C not UART-A.
-
-config BOARD_ATSTK100X_SW3_CUSTOM
-	bool "SW3: use TIMER1 (not SSC0 and GCLK)"
-	help
-	  This also prevents using the external DAC as an audio interface.
-
-config BOARD_ATSTK100X_SW4_CUSTOM
-	bool "SW4: use ISI/Camera (not GPIOs, SPI1, and PS2-B)"
-	help
-	  To use the camera interface you'll need a custom card (on the
-	  PCI-format connector) connect a video sensor.
-
-config BOARD_ATSTK1002_SW5_CUSTOM
-	bool "SW5: use MACB1 (not LCDC)"
-	depends on BOARD_ATSTK1002
-
-config BOARD_ATSTK1002_SW6_CUSTOM
-	bool "SW6: more GPIOs (not MACB0)"
-	depends on BOARD_ATSTK1002
-
-endif	# custom
-
-config BOARD_ATSTK100X_SPI1
-	bool "Configure SPI1 controller"
-	depends on !BOARD_ATSTK100X_SW4_CUSTOM
-	help
-	  All the signals for the second SPI controller are available on
-	  GPIO lines and accessed through the J1 jumper block.  Say "y"
-	  here to configure that SPI controller.
-
-config BOARD_ATSTK1000_J2_LED
-	bool
-	default BOARD_ATSTK1000_J2_LED8 || BOARD_ATSTK1000_J2_RGB
-
-choice
-	prompt "LEDs connected to J2:"
-	depends on LEDS_GPIO && !BOARD_ATSTK100X_SW4_CUSTOM
-	optional
-	help
-	  Select this if you have jumpered the J2 jumper block to the
-	  LED0..LED7 amber leds, or to the RGB leds, using a ten-pin
-	  IDC cable.  A default "heartbeat" trigger is provided, but
-	  you can of course override this.
-
-config BOARD_ATSTK1000_J2_LED8
-	bool "LED0..LED7"
-	help
-	  Select this if J2 is jumpered to LED0..LED7 amber leds.
-
-config BOARD_ATSTK1000_J2_RGB
-	bool "RGB leds"
-	help
-	  Select this if J2 is jumpered to the RGB leds.
-
-endchoice
-
-config BOARD_ATSTK1000_EXTDAC
-	bool
-	depends on !BOARD_ATSTK100X_SW1_CUSTOM && !BOARD_ATSTK100X_SW3_CUSTOM
-	default y
-
-endif	# stk 1000
diff --git a/arch/avr32/boards/atstk1000/Makefile b/arch/avr32/boards/atstk1000/Makefile
deleted file mode 100644
index edecee03742d..000000000000
--- a/arch/avr32/boards/atstk1000/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-obj-y				+= setup.o flash.o
-obj-$(CONFIG_BOARD_ATSTK1002)	+= atstk1002.o
-obj-$(CONFIG_BOARD_ATSTK1003)	+= atstk1003.o
-obj-$(CONFIG_BOARD_ATSTK1004)	+= atstk1004.o
-obj-$(CONFIG_BOARD_ATSTK1006)	+= atstk1002.o
diff --git a/arch/avr32/boards/atstk1000/atstk1000.h b/arch/avr32/boards/atstk1000/atstk1000.h
deleted file mode 100644
index 653cc09e536c..000000000000
--- a/arch/avr32/boards/atstk1000/atstk1000.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * ATSTK1000 setup code: Daughterboard interface
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H
-#define __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H
-
-extern struct atmel_lcdfb_pdata atstk1000_lcdc_data;
-
-void atstk1000_setup_j2_leds(void);
-
-#endif /* __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H */
diff --git a/arch/avr32/boards/atstk1000/atstk1002.c b/arch/avr32/boards/atstk1000/atstk1002.c
deleted file mode 100644
index 6c80aba7bf96..000000000000
--- a/arch/avr32/boards/atstk1000/atstk1002.c
+++ /dev/null
@@ -1,330 +0,0 @@
-/*
- * ATSTK1002/ATSTK1006 daughterboard-specific init code
- *
- * Copyright (C) 2005-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/at73c213.h>
-#include <linux/atmel-mci.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 20000000,	/* 20 MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-/*
- * The ATSTK1006 daughterboard is very similar to the ATSTK1002. Both
- * have the AT32AP7000 chip on board; the difference is that the
- * STK1006 has 128 MB SDRAM (the STK1002 uses the 8 MB SDRAM chip on
- * the STK1000 motherboard) and 256 MB NAND flash (the STK1002 has
- * none.)
- *
- * The RAM difference is handled by the boot loader, so the only
- * difference we end up handling here is the NAND flash.
- */
-#ifdef CONFIG_BOARD_ATSTK1006
-#include <linux/mtd/partitions.h>
-#include <mach/smc.h>
-
-static struct smc_timing nand_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 10,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 10,
-
-	.ncs_read_pulse		= 30,
-	.nrd_pulse		= 15,
-	.ncs_write_pulse	= 30,
-	.nwe_pulse		= 15,
-
-	.read_cycle		= 30,
-	.write_cycle		= 30,
-
-	.ncs_read_recover	= 0,
-	.nrd_recover		= 15,
-	.ncs_write_recover	= 0,
-	/* WE# high -> RE# low min 60 ns */
-	.nwe_recover		= 50,
-};
-
-static struct smc_config nand_config __initdata = {
-	.bus_width		= 1,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.nwait_mode		= 0,
-	.byte_write		= 0,
-	.tdf_cycles		= 2,
-	.tdf_mode		= 0,
-};
-
-static struct mtd_partition nand_partitions[] = {
-	{
-		.name		= "main",
-		.offset		= 0x00000000,
-		.size		= MTDPART_SIZ_FULL,
-	},
-};
-
-static struct atmel_nand_data atstk1006_nand_data __initdata = {
-	.cle		= 21,
-	.ale		= 22,
-	.rdy_pin	= GPIO_PIN_PB(30),
-	.enable_pin	= GPIO_PIN_PB(29),
-	.ecc_mode	= NAND_ECC_SOFT,
-	.parts		= nand_partitions,
-	.num_parts	= ARRAY_SIZE(nand_partitions),
-};
-#endif
-
-struct eth_addr {
-	u8 addr[6];
-};
-
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2] = {
-	{
-		/*
-		 * The MDIO pullups on STK1000 are a bit too weak for
-		 * the autodetection to work properly, so we have to
-		 * mask out everything but the correct address.
-		 */
-		.phy_mask	= ~(1U << 16),
-	},
-	{
-		.phy_mask	= ~(1U << 17),
-	},
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static struct at73c213_board_info at73c213_data = {
-	.ssc_id		= 0,
-	.shortname	= "AVR32 STK1000 external DAC",
-};
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-static struct spi_board_info spi0_board_info[] __initdata = {
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-	{
-		/* AT73C213 */
-		.modalias	= "at73c213",
-		.max_speed_hz	= 200000,
-		.chip_select	= 0,
-		.mode		= SPI_MODE_1,
-		.platform_data	= &at73c213_data,
-	},
-#endif
-	{
-		/* QVGA display */
-		.modalias	= "ltv350qv",
-		.max_speed_hz	= 16000000,
-		.chip_select	= 1,
-		.mode		= SPI_MODE_3,
-	},
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-static struct spi_board_info spi1_board_info[] __initdata = { {
-	/* patch in custom entries here */
-} };
-#endif
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
-	int i;
-
-	i = tag->u.ethernet.mac_index;
-	if (i < ARRAY_SIZE(hw_addr))
-		memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
-		       sizeof(hw_addr[i].addr));
-
-	return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const u8 *addr;
-	void __iomem *regs;
-	struct clk *pclk;
-
-	if (!res)
-		return;
-	if (pdev->id >= ARRAY_SIZE(hw_addr))
-		return;
-
-	addr = hw_addr[pdev->id].addr;
-	if (!is_valid_ether_addr(addr))
-		return;
-
-	/*
-	 * Since this is board-specific code, we'll cheat and use the
-	 * physical address directly as we happen to know that it's
-	 * the same as the virtual address.
-	 */
-	regs = (void __iomem __force *)res->start;
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk))
-		return;
-
-	clk_enable(pclk);
-	__raw_writel((addr[3] << 24) | (addr[2] << 16)
-		     | (addr[1] << 8) | addr[0], regs + 0x98);
-	__raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-	clk_disable(pclk);
-	clk_put(pclk);
-}
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static void __init atstk1002_setup_extdac(void)
-{
-	struct clk *gclk;
-	struct clk *pll;
-
-	gclk = clk_get(NULL, "gclk0");
-	if (IS_ERR(gclk))
-		goto err_gclk;
-	pll = clk_get(NULL, "pll0");
-	if (IS_ERR(pll))
-		goto err_pll;
-
-	if (clk_set_parent(gclk, pll)) {
-		pr_debug("STK1000: failed to set pll0 as parent for DAC clock\n");
-		goto err_set_clk;
-	}
-
-	at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
-	at73c213_data.dac_clk = gclk;
-
-err_set_clk:
-	clk_put(pll);
-err_pll:
-	clk_put(gclk);
-err_gclk:
-	return;
-}
-#else
-static void __init atstk1002_setup_extdac(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_EXTDAC */
-
-void __init setup_board(void)
-{
-#ifdef	CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_map_usart(0, 1, 0);	/* USART 0/B: /dev/ttyS1, IRDA */
-#else
-	at32_map_usart(1, 0, 0);	/* USART 1/A: /dev/ttyS0, DB9 */
-#endif
-	/* USART 2/unused: expansion connector */
-	at32_map_usart(3, 2, 0);	/* USART 3/C: /dev/ttyS2, DB9 */
-
-	at32_setup_serial_console(0);
-}
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-
-/* MMC card detect requires MACB0 *NOT* be used */
-#ifdef CONFIG_BOARD_ATSTK1002_SW6_CUSTOM
-		.detect_pin	= GPIO_PIN_PC(14), /* gpio30/sdcd */
-		.wp_pin		= GPIO_PIN_PC(15), /* gpio31/sdwp */
-#else
-		.detect_pin	= -ENODEV,
-		.wp_pin		= -ENODEV,
-#endif	/* SW6 for sd{cd,wp} routing */
-	},
-};
-
-#endif	/* SW2 for MMC signal routing */
-
-static int __init atstk1002_init(void)
-{
-	/*
-	 * ATSTK1000 uses 32-bit SDRAM interface. Reserve the
-	 * SDRAM-specific pins so that nobody messes with them.
-	 */
-	at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-#ifdef CONFIG_BOARD_ATSTK1006
-	smc_set_timing(&nand_config, &nand_timing);
-	smc_set_configuration(3, &nand_config);
-	at32_add_device_nand(0, &atstk1006_nand_data);
-#endif
-
-#ifdef	CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_usart(1);
-#else
-	at32_add_device_usart(0);
-#endif
-	at32_add_device_usart(2);
-
-#ifndef CONFIG_BOARD_ATSTK1002_SW6_CUSTOM
-	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-#endif
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_mci(0, &mci0_data);
-#endif
-#ifdef CONFIG_BOARD_ATSTK1002_SW5_CUSTOM
-	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
-#else
-	at32_add_device_lcdc(0, &atstk1000_lcdc_data,
-			     fbmem_start, fbmem_size,
-			     ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL);
-#endif
-	at32_add_device_usba(0, NULL);
-#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
-	at32_add_device_ssc(0, ATMEL_SSC_TX);
-#endif
-
-	atstk1000_setup_j2_leds();
-	atstk1002_setup_extdac();
-
-	return 0;
-}
-postcore_initcall(atstk1002_init);
diff --git a/arch/avr32/boards/atstk1000/atstk1003.c b/arch/avr32/boards/atstk1000/atstk1003.c
deleted file mode 100644
index ff7e23298827..000000000000
--- a/arch/avr32/boards/atstk1000/atstk1003.c
+++ /dev/null
@@ -1,162 +0,0 @@
-/*
- * ATSTK1003 daughterboard-specific init code
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <linux/spi/at73c213.h>
-#include <linux/spi/spi.h>
-#include <linux/atmel-mci.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 20000000,	/* 20 MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static struct at73c213_board_info at73c213_data = {
-	.ssc_id		= 0,
-	.shortname	= "AVR32 STK1000 external DAC",
-};
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-static struct spi_board_info spi0_board_info[] __initdata = {
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-	{
-		/* AT73C213 */
-		.modalias	= "at73c213",
-		.max_speed_hz	= 200000,
-		.chip_select	= 0,
-		.mode		= SPI_MODE_1,
-		.platform_data	= &at73c213_data,
-	},
-#endif
-	/*
-	 * We can control the LTV350QV LCD panel, but it isn't much
-	 * point since we don't have an LCD controller...
-	 */
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-static struct spi_board_info spi1_board_info[] __initdata = { {
-	/* patch in custom entries here */
-} };
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-		.detect_pin	= -ENODEV,
-		.wp_pin		= -ENODEV,
-	},
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static void __init atstk1003_setup_extdac(void)
-{
-	struct clk *gclk;
-	struct clk *pll;
-
-	gclk = clk_get(NULL, "gclk0");
-	if (IS_ERR(gclk))
-		goto err_gclk;
-	pll = clk_get(NULL, "pll0");
-	if (IS_ERR(pll))
-		goto err_pll;
-
-	if (clk_set_parent(gclk, pll)) {
-		pr_debug("STK1000: failed to set pll0 as parent for DAC clock\n");
-		goto err_set_clk;
-	}
-
-	at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
-	at73c213_data.dac_clk = gclk;
-
-err_set_clk:
-	clk_put(pll);
-err_pll:
-	clk_put(gclk);
-err_gclk:
-	return;
-}
-#else
-static void __init atstk1003_setup_extdac(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_EXTDAC */
-
-void __init setup_board(void)
-{
-#ifdef	CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_map_usart(0, 1, 0);	/* USART 0/B: /dev/ttyS1, IRDA */
-#else
-	at32_map_usart(1, 0, 0);	/* USART 1/A: /dev/ttyS0, DB9 */
-#endif
-	/* USART 2/unused: expansion connector */
-	at32_map_usart(3, 2, 0);	/* USART 3/C: /dev/ttyS2, DB9 */
-
-	at32_setup_serial_console(0);
-}
-
-static int __init atstk1003_init(void)
-{
-	/*
-	 * ATSTK1000 uses 32-bit SDRAM interface. Reserve the
-	 * SDRAM-specific pins so that nobody messes with them.
-	 */
-	at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-#ifdef	CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_usart(1);
-#else
-	at32_add_device_usart(0);
-#endif
-	at32_add_device_usart(2);
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-#endif
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_mci(0, &mci0_data);
-#endif
-	at32_add_device_usba(0, NULL);
-#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
-	at32_add_device_ssc(0, ATMEL_SSC_TX);
-#endif
-
-	atstk1000_setup_j2_leds();
-	atstk1003_setup_extdac();
-
-	return 0;
-}
-postcore_initcall(atstk1003_init);
diff --git a/arch/avr32/boards/atstk1000/atstk1004.c b/arch/avr32/boards/atstk1000/atstk1004.c
deleted file mode 100644
index 69a9f0f08c6e..000000000000
--- a/arch/avr32/boards/atstk1000/atstk1004.c
+++ /dev/null
@@ -1,164 +0,0 @@
-/*
- * ATSTK1003 daughterboard-specific init code
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <linux/spi/at73c213.h>
-#include <linux/spi/spi.h>
-#include <linux/atmel-mci.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 20000000,	/* 20 MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static struct at73c213_board_info at73c213_data = {
-	.ssc_id		= 0,
-	.shortname	= "AVR32 STK1000 external DAC",
-};
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-static struct spi_board_info spi0_board_info[] __initdata = {
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-	{
-		/* AT73C213 */
-		.modalias	= "at73c213",
-		.max_speed_hz	= 200000,
-		.chip_select	= 0,
-		.mode		= SPI_MODE_1,
-		.platform_data	= &at73c213_data,
-	},
-#endif
-	{
-		/* QVGA display */
-		.modalias	= "ltv350qv",
-		.max_speed_hz	= 16000000,
-		.chip_select	= 1,
-		.mode		= SPI_MODE_3,
-	},
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-static struct spi_board_info spi1_board_info[] __initdata = { {
-	/* patch in custom entries here */
-} };
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-		.detect_pin	= -ENODEV,
-		.wp_pin		= -ENODEV,
-	},
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static void __init atstk1004_setup_extdac(void)
-{
-	struct clk *gclk;
-	struct clk *pll;
-
-	gclk = clk_get(NULL, "gclk0");
-	if (IS_ERR(gclk))
-		goto err_gclk;
-	pll = clk_get(NULL, "pll0");
-	if (IS_ERR(pll))
-		goto err_pll;
-
-	if (clk_set_parent(gclk, pll)) {
-		pr_debug("STK1000: failed to set pll0 as parent for DAC clock\n");
-		goto err_set_clk;
-	}
-
-	at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
-	at73c213_data.dac_clk = gclk;
-
-err_set_clk:
-	clk_put(pll);
-err_pll:
-	clk_put(gclk);
-err_gclk:
-	return;
-}
-#else
-static void __init atstk1004_setup_extdac(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_EXTDAC */
-
-void __init setup_board(void)
-{
-#ifdef	CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_map_usart(0, 1, 0);	/* USART 0/B: /dev/ttyS1, IRDA */
-#else
-	at32_map_usart(1, 0, 0);	/* USART 1/A: /dev/ttyS0, DB9 */
-#endif
-	/* USART 2/unused: expansion connector */
-	at32_map_usart(3, 2, 0);	/* USART 3/C: /dev/ttyS2, DB9 */
-
-	at32_setup_serial_console(0);
-}
-
-static int __init atstk1004_init(void)
-{
-#ifdef	CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_usart(1);
-#else
-	at32_add_device_usart(0);
-#endif
-	at32_add_device_usart(2);
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-#endif
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_mci(0, &mci0_data);
-#endif
-	at32_add_device_lcdc(0, &atstk1000_lcdc_data,
-			     fbmem_start, fbmem_size,
-			     ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL);
-	at32_add_device_usba(0, NULL);
-#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
-	at32_add_device_ssc(0, ATMEL_SSC_TX);
-#endif
-
-	atstk1000_setup_j2_leds();
-	atstk1004_setup_extdac();
-
-	return 0;
-}
-postcore_initcall(atstk1004_init);
diff --git a/arch/avr32/boards/atstk1000/flash.c b/arch/avr32/boards/atstk1000/flash.c
deleted file mode 100644
index 6e4d561977ff..000000000000
--- a/arch/avr32/boards/atstk1000/flash.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * ATSTK1000 board-specific flash initialization
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 40,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 10,
-
-	.ncs_read_pulse		= 80,
-	.nrd_pulse		= 40,
-	.ncs_write_pulse	= 65,
-	.nwe_pulse		= 55,
-
-	.read_cycle		= 120,
-	.write_cycle		= 120,
-};
-
-static struct smc_config flash_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 1,
-};
-
-static struct mtd_partition flash_parts[] = {
-	{
-		.name           = "u-boot",
-		.offset         = 0x00000000,
-		.size           = 0x00020000,           /* 128 KiB */
-		.mask_flags     = MTD_WRITEABLE,
-	},
-	{
-		.name           = "root",
-		.offset         = 0x00020000,
-		.size           = 0x007d0000,
-	},
-	{
-		.name           = "env",
-		.offset         = 0x007f0000,
-		.size           = 0x00010000,
-		.mask_flags     = MTD_WRITEABLE,
-	},
-};
-
-static struct physmap_flash_data flash_data = {
-	.width		= 2,
-	.nr_parts	= ARRAY_SIZE(flash_parts),
-	.parts		= flash_parts,
-};
-
-static struct resource flash_resource = {
-	.start		= 0x00000000,
-	.end		= 0x007fffff,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.resource	= &flash_resource,
-	.num_resources	= 1,
-	.dev		= {
-		.platform_data = &flash_data,
-	},
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init atstk1000_flash_init(void)
-{
-	int ret;
-
-	smc_set_timing(&flash_config, &flash_timing);
-	ret = smc_set_configuration(0, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "atstk1000: failed to set NOR flash timing\n");
-		return ret;
-	}
-
-	platform_device_register(&flash_device);
-
-	return 0;
-}
-device_initcall(atstk1000_flash_init);
diff --git a/arch/avr32/boards/atstk1000/setup.c b/arch/avr32/boards/atstk1000/setup.c
deleted file mode 100644
index b6b88f5e0b43..000000000000
--- a/arch/avr32/boards/atstk1000/setup.c
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * ATSTK1000 board-specific setup code.
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/bootmem.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/linkage.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-static struct fb_videomode __initdata ltv350qv_modes[] = {
-	{
-		.name		= "320x240 @ 75",
-		.refresh	= 75,
-		.xres		= 320,		.yres		= 240,
-		.pixclock	= KHZ2PICOS(6891),
-
-		.left_margin	= 17,		.right_margin	= 33,
-		.upper_margin	= 10,		.lower_margin	= 10,
-		.hsync_len	= 16,		.vsync_len	= 1,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata atstk1000_default_monspecs = {
-	.manufacturer		= "SNG",
-	.monitor		= "LTV350QV",
-	.modedb			= ltv350qv_modes,
-	.modedb_len		= ARRAY_SIZE(ltv350qv_modes),
-	.hfmin			= 14820,
-	.hfmax			= 22230,
-	.vfmin			= 60,
-	.vfmax			= 90,
-	.dclkmax		= 30000000,
-};
-
-struct atmel_lcdfb_pdata __initdata atstk1000_lcdc_data = {
-	.default_bpp		= 24,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_INVCLK
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &atstk1000_default_monspecs,
-	.guard_time		= 2,
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_J2_LED
-#include <linux/leds.h>
-
-static struct gpio_led stk1000_j2_led[] = {
-#ifdef CONFIG_BOARD_ATSTK1000_J2_LED8
-#define LEDSTRING "J2 jumpered to LED8"
-	{ .name = "led0:amber", .gpio = GPIO_PIN_PB( 8), },
-	{ .name = "led1:amber", .gpio = GPIO_PIN_PB( 9), },
-	{ .name = "led2:amber", .gpio = GPIO_PIN_PB(10), },
-	{ .name = "led3:amber", .gpio = GPIO_PIN_PB(13), },
-	{ .name = "led4:amber", .gpio = GPIO_PIN_PB(14), },
-	{ .name = "led5:amber", .gpio = GPIO_PIN_PB(15), },
-	{ .name = "led6:amber", .gpio = GPIO_PIN_PB(16), },
-	{ .name = "led7:amber", .gpio = GPIO_PIN_PB(30),
-			.default_trigger = "heartbeat", },
-#else	/* RGB */
-#define LEDSTRING "J2 jumpered to RGB LEDs"
-	{ .name = "r1:red",     .gpio = GPIO_PIN_PB( 8), },
-	{ .name = "g1:green",   .gpio = GPIO_PIN_PB(10), },
-	{ .name = "b1:blue",    .gpio = GPIO_PIN_PB(14), },
-
-	{ .name = "r2:red",     .gpio = GPIO_PIN_PB( 9),
-			.default_trigger = "heartbeat", },
-	{ .name = "g2:green",   .gpio = GPIO_PIN_PB(13), },
-	{ .name = "b2:blue",    .gpio = GPIO_PIN_PB(15),
-			.default_trigger = "heartbeat", },
-	/* PB16, PB30 unused */
-#endif
-};
-
-static struct gpio_led_platform_data stk1000_j2_led_data = {
-	.num_leds	= ARRAY_SIZE(stk1000_j2_led),
-	.leds		= stk1000_j2_led,
-};
-
-static struct platform_device stk1000_j2_led_dev = {
-	.name		= "leds-gpio",
-	.id		= 2,	/* gpio block J2 */
-	.dev		= {
-		.platform_data	= &stk1000_j2_led_data,
-	},
-};
-
-void __init atstk1000_setup_j2_leds(void)
-{
-	unsigned	i;
-
-	for (i = 0; i < ARRAY_SIZE(stk1000_j2_led); i++)
-		at32_select_gpio(stk1000_j2_led[i].gpio, AT32_GPIOF_OUTPUT);
-
-	printk("STK1000: " LEDSTRING "\n");
-	platform_device_register(&stk1000_j2_led_dev);
-}
-#else /* CONFIG_BOARD_ATSTK1000_J2_LED */
-void __init atstk1000_setup_j2_leds(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_J2_LED */
diff --git a/arch/avr32/boards/favr-32/Kconfig b/arch/avr32/boards/favr-32/Kconfig
deleted file mode 100644
index 2c83d1ddcaec..000000000000
--- a/arch/avr32/boards/favr-32/Kconfig
+++ /dev/null
@@ -1,22 +0,0 @@
-# Favr-32 customization
-
-if BOARD_FAVR_32
-
-config BOARD_FAVR32_ABDAC_RATE
-	int "DAC target rate"
-	default 44100
-	range 32000 50000
-	help
-	  Specify the target rate the internal DAC should try to match. This
-	  will use PLL1 to generate a frequency as close as possible to this
-	  rate.
-
-	  Must be within the range 32000 to 50000, which should be suitable to
-	  generate most other frequencies in power of 2 steps.
-
-	  Ex:
-		48000 will also suit 24000 and 12000
-		44100 will also suit 22050 and 11025
-		32000 will also suit 16000 and 8000
-
-endif # BOARD_FAVR_32
diff --git a/arch/avr32/boards/favr-32/Makefile b/arch/avr32/boards/favr-32/Makefile
deleted file mode 100644
index 234f21508e4b..000000000000
--- a/arch/avr32/boards/favr-32/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y	+= setup.o flash.o
diff --git a/arch/avr32/boards/favr-32/flash.c b/arch/avr32/boards/favr-32/flash.c
deleted file mode 100644
index 604bbd5e41d9..000000000000
--- a/arch/avr32/boards/favr-32/flash.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Favr-32 board-specific flash initialization
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 40,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 10,
-
-	.ncs_read_pulse		= 80,
-	.nrd_pulse		= 40,
-	.ncs_write_pulse	= 65,
-	.nwe_pulse		= 55,
-
-	.read_cycle		= 120,
-	.write_cycle		= 120,
-};
-
-static struct smc_config flash_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 1,
-};
-
-static struct mtd_partition flash_parts[] = {
-	{
-		.name           = "u-boot",
-		.offset         = 0x00000000,
-		.size           = 0x00020000,           /* 128 KiB */
-		.mask_flags     = MTD_WRITEABLE,
-	},
-	{
-		.name           = "root",
-		.offset         = 0x00020000,
-		.size           = 0x007d0000,
-	},
-	{
-		.name           = "env",
-		.offset         = 0x007f0000,
-		.size           = 0x00010000,
-		.mask_flags     = MTD_WRITEABLE,
-	},
-};
-
-static struct physmap_flash_data flash_data = {
-	.width		= 2,
-	.nr_parts	= ARRAY_SIZE(flash_parts),
-	.parts		= flash_parts,
-};
-
-static struct resource flash_resource = {
-	.start		= 0x00000000,
-	.end		= 0x007fffff,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.resource	= &flash_resource,
-	.num_resources	= 1,
-	.dev		= {
-		.platform_data = &flash_data,
-	},
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init favr32_flash_init(void)
-{
-	int ret;
-
-	smc_set_timing(&flash_config, &flash_timing);
-	ret = smc_set_configuration(0, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "Favr-32: failed to set NOR flash timing\n");
-		return ret;
-	}
-
-	platform_device_register(&flash_device);
-
-	return 0;
-}
-device_initcall(favr32_flash_init);
diff --git a/arch/avr32/boards/favr-32/setup.c b/arch/avr32/boards/favr-32/setup.c
deleted file mode 100644
index 234cb071c601..000000000000
--- a/arch/avr32/boards/favr-32/setup.c
+++ /dev/null
@@ -1,366 +0,0 @@
-/*
- * Favr-32 board-specific setup code.
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/bootmem.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/linkage.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <linux/atmel-mci.h>
-#include <linux/pwm.h>
-#include <linux/pwm_backlight.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/ads7846.h>
-
-#include <sound/atmel-abdac.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/init.h>
-#include <mach/board.h>
-#include <mach/portmux.h>
-
-#define PWM_BL_CH 2
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 20000000,	/* 20 MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-static struct atmel_abdac_pdata __initdata abdac0_data = {
-};
-
-struct eth_addr {
-	u8 addr[6];
-};
-static struct eth_addr __initdata hw_addr[1];
-static struct macb_platform_data __initdata eth_data[1] = {
-	{
-		.phy_mask	= ~(1U << 1),
-	},
-};
-
-static int ads7843_get_pendown_state(void)
-{
-	return !gpio_get_value(GPIO_PIN_PB(3));
-}
-
-static struct ads7846_platform_data ads7843_data = {
-	.model			= 7843,
-	.get_pendown_state	= ads7843_get_pendown_state,
-	.pressure_max		= 255,
-	/*
-	 * Values below are for debounce filtering, these can be experimented
-	 * with further.
-	 */
-	.debounce_max		= 20,
-	.debounce_rep		= 4,
-	.debounce_tol		= 5,
-
-	.keep_vref_on		= true,
-	.settle_delay_usecs	= 500,
-	.penirq_recheck_delay_usecs = 100,
-};
-
-static struct spi_board_info __initdata spi1_board_info[] = {
-	{
-		/* ADS7843 touch controller */
-		.modalias	= "ads7846",
-		.max_speed_hz	= 2000000,
-		.chip_select	= 0,
-		.bus_num	= 1,
-		.platform_data	= &ads7843_data,
-	},
-};
-
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-		.detect_pin	= -ENODEV,
-		.wp_pin		= -ENODEV,
-	},
-};
-
-static struct fb_videomode __initdata lb104v03_modes[] = {
-	{
-		.name		= "640x480 @ 50",
-		.refresh	= 50,
-		.xres		= 640,		.yres		= 480,
-		.pixclock	= KHZ2PICOS(25100),
-
-		.left_margin	= 90,		.right_margin	= 70,
-		.upper_margin	= 30,		.lower_margin	= 15,
-		.hsync_len	= 12,		.vsync_len	= 2,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata favr32_default_monspecs = {
-	.manufacturer		= "LG",
-	.monitor		= "LB104V03",
-	.modedb			= lb104v03_modes,
-	.modedb_len		= ARRAY_SIZE(lb104v03_modes),
-	.hfmin			= 27273,
-	.hfmax			= 31111,
-	.vfmin			= 45,
-	.vfmax			= 60,
-	.dclkmax		= 28000000,
-};
-
-struct atmel_lcdfb_pdata __initdata favr32_lcdc_data = {
-	.default_bpp		= 16,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &favr32_default_monspecs,
-	.guard_time		= 2,
-};
-
-static struct gpio_led favr32_leds[] = {
-	{
-		.name		 = "green",
-		.gpio		 = GPIO_PIN_PE(19),
-		.default_trigger = "heartbeat",
-		.active_low	 = 1,
-	},
-	{
-		.name		 = "red",
-		.gpio		 = GPIO_PIN_PE(20),
-		.active_low	 = 1,
-	},
-};
-
-static struct gpio_led_platform_data favr32_led_data = {
-	.num_leds	= ARRAY_SIZE(favr32_leds),
-	.leds		= favr32_leds,
-};
-
-static struct platform_device favr32_led_dev = {
-	.name		= "leds-gpio",
-	.id		= 0,
-	.dev		= {
-		.platform_data	= &favr32_led_data,
-	},
-};
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
-	int i;
-
-	i = tag->u.ethernet.mac_index;
-	if (i < ARRAY_SIZE(hw_addr))
-		memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
-		       sizeof(hw_addr[i].addr));
-
-	return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const u8 *addr;
-	void __iomem *regs;
-	struct clk *pclk;
-
-	if (!res)
-		return;
-	if (pdev->id >= ARRAY_SIZE(hw_addr))
-		return;
-
-	addr = hw_addr[pdev->id].addr;
-	if (!is_valid_ether_addr(addr))
-		return;
-
-	/*
-	 * Since this is board-specific code, we'll cheat and use the
-	 * physical address directly as we happen to know that it's
-	 * the same as the virtual address.
-	 */
-	regs = (void __iomem __force *)res->start;
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk))
-		return;
-
-	clk_enable(pclk);
-	__raw_writel((addr[3] << 24) | (addr[2] << 16)
-		     | (addr[1] << 8) | addr[0], regs + 0x98);
-	__raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-	clk_disable(pclk);
-	clk_put(pclk);
-}
-
-void __init favr32_setup_leds(void)
-{
-	unsigned i;
-
-	for (i = 0; i < ARRAY_SIZE(favr32_leds); i++)
-		at32_select_gpio(favr32_leds[i].gpio, AT32_GPIOF_OUTPUT);
-
-	platform_device_register(&favr32_led_dev);
-}
-
-static struct pwm_lookup pwm_lookup[] = {
-	PWM_LOOKUP("at91sam9rl-pwm", PWM_BL_CH, "pwm-backlight.0", NULL,
-		   5000, PWM_POLARITY_INVERSED),
-};
-
-static struct regulator_consumer_supply fixed_power_consumers[] = {
-	REGULATOR_SUPPLY("power", "pwm-backlight.0"),
-};
-
-static struct platform_pwm_backlight_data pwm_bl_data = {
-	.enable_gpio		= GPIO_PIN_PA(28),
-	.max_brightness		= 255,
-	.dft_brightness		= 255,
-	.lth_brightness		= 50,
-};
-
-static struct platform_device pwm_bl_device = {
-	.name = "pwm-backlight",
-	.dev = {
-		.platform_data = &pwm_bl_data,
-	},
-};
-
-static void __init favr32_setup_atmel_pwm_bl(void)
-{
-	pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
-	regulator_register_always_on(0, "fixed", fixed_power_consumers,
-				    ARRAY_SIZE(fixed_power_consumers), 3300000);
-	platform_device_register(&pwm_bl_device);
-	at32_select_gpio(pwm_bl_data.enable_gpio, 0);
-}
-
-void __init setup_board(void)
-{
-	at32_map_usart(3, 0, 0);	/* USART 3 => /dev/ttyS0 */
-	at32_setup_serial_console(0);
-}
-
-static int __init set_abdac_rate(struct platform_device *pdev)
-{
-	int retval;
-	struct clk *osc1;
-	struct clk *pll1;
-	struct clk *abdac;
-
-	if (pdev == NULL)
-		return -ENXIO;
-
-	osc1 = clk_get(NULL, "osc1");
-	if (IS_ERR(osc1)) {
-		retval = PTR_ERR(osc1);
-		goto out;
-	}
-
-	pll1 = clk_get(NULL, "pll1");
-	if (IS_ERR(pll1)) {
-		retval = PTR_ERR(pll1);
-		goto out_osc1;
-	}
-
-	abdac = clk_get(&pdev->dev, "sample_clk");
-	if (IS_ERR(abdac)) {
-		retval = PTR_ERR(abdac);
-		goto out_pll1;
-	}
-
-	retval = clk_set_parent(pll1, osc1);
-	if (retval != 0)
-		goto out_abdac;
-
-	/*
-	 * Rate is 32000 to 50000 and ABDAC oversamples 256x. Multiply, in
-	 * power of 2, to a value above 80 MHz. Power of 2 so it is possible
-	 * for the generic clock to divide it down again and 80 MHz is the
-	 * lowest frequency for the PLL.
-	 */
-	retval = clk_round_rate(pll1,
-			CONFIG_BOARD_FAVR32_ABDAC_RATE * 256 * 16);
-	if (retval <= 0) {
-		retval = -EINVAL;
-		goto out_abdac;
-	}
-
-	retval = clk_set_rate(pll1, retval);
-	if (retval != 0)
-		goto out_abdac;
-
-	retval = clk_set_parent(abdac, pll1);
-	if (retval != 0)
-		goto out_abdac;
-
-out_abdac:
-	clk_put(abdac);
-out_pll1:
-	clk_put(pll1);
-out_osc1:
-	clk_put(osc1);
-out:
-	return retval;
-}
-
-static int __init favr32_init(void)
-{
-	/*
-	 * Favr-32 uses 32-bit SDRAM interface. Reserve the SDRAM-specific
-	 * pins so that nobody messes with them.
-	 */
-	at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-	at32_select_gpio(GPIO_PIN_PB(3), 0);	/* IRQ from ADS7843 */
-
-	at32_add_device_usart(0);
-
-	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
-
-	spi1_board_info[0].irq = gpio_to_irq(GPIO_PIN_PB(3));
-
-	set_abdac_rate(at32_add_device_abdac(0, &abdac0_data));
-
-	at32_add_device_pwm(1 << PWM_BL_CH);
-	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-	at32_add_device_mci(0, &mci0_data);
-	at32_add_device_usba(0, NULL);
-	at32_add_device_lcdc(0, &favr32_lcdc_data, fbmem_start, fbmem_size, 0);
-
-	favr32_setup_leds();
-
-	favr32_setup_atmel_pwm_bl();
-
-	return 0;
-}
-postcore_initcall(favr32_init);
diff --git a/arch/avr32/boards/hammerhead/Kconfig b/arch/avr32/boards/hammerhead/Kconfig
deleted file mode 100644
index 5c13d785cc70..000000000000
--- a/arch/avr32/boards/hammerhead/Kconfig
+++ /dev/null
@@ -1,43 +0,0 @@
-# Hammerhead customization
-
-if BOARD_HAMMERHEAD
-
-config BOARD_HAMMERHEAD_USB
-	bool "Philips ISP116x-hcd USB support"
-	help
-	  This enables USB support for Hammerheads internal ISP116x
-	  controller from Philips.
-
-	  Choose 'Y' here if you want to have your board USB driven.
-
-config BOARD_HAMMERHEAD_LCD
-	bool "Atmel AT91/AT32 LCD support"
-	help
-	  This enables LCD support for the Hammerhead board. You may
-	  also add support for framebuffer devices (AT91/AT32 LCD Controller)
-	  and framebuffer console support to get the most out of your LCD.
-
-	  Choose 'Y' here if you have ordered a Corona daugther board and
-	  want to have support for your Hantronix HDA-351T-LV LCD.
-
-config BOARD_HAMMERHEAD_SND
-	bool "Atmel AC97 Sound support"
-	help
-	  This enables Sound support for the Hammerhead board. You may
-	  also go through the ALSA settings to get it working.
-
-	  Choose 'Y' here if you have ordered a Corona daugther board and
-	  want to make your board funky.
-
-config BOARD_HAMMERHEAD_FPGA
-	bool "Hammerhead FPGA Support"
-	default y
-	help
-	  This adds support for the Cyclone III FPGA from Altera
-	  found on Miromico's Hammerhead board.
-
-	  Choose 'Y' here if you want to have FPGA support enabled.
-	  You will have to choose the "Hammerhead FPGA Device Support" in
-	  Device Drivers->Misc to be able to use FPGA functionality.
-
-endif	# BOARD_ATNGW100
diff --git a/arch/avr32/boards/hammerhead/Makefile b/arch/avr32/boards/hammerhead/Makefile
deleted file mode 100644
index c740aa116755..000000000000
--- a/arch/avr32/boards/hammerhead/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y				+= setup.o flash.o
diff --git a/arch/avr32/boards/hammerhead/flash.c b/arch/avr32/boards/hammerhead/flash.c
deleted file mode 100644
index e86280ccd8fa..000000000000
--- a/arch/avr32/boards/hammerhead/flash.c
+++ /dev/null
@@ -1,381 +0,0 @@
-/*
- * Hammerhead board-specific flash initialization
- *
- * Copyright (C) 2008 Miromico AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-#include <linux/usb/isp116x.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-
-#include <mach/portmux.h>
-#include <mach/at32ap700x.h>
-#include <mach/smc.h>
-
-#include "../../mach-at32ap/clock.h"
-#include "flash.h"
-
-
-#define HAMMERHEAD_USB_PERIPH_GCLK0	0x40000000
-#define HAMMERHEAD_USB_PERIPH_CS2	0x02000000
-#define HAMMERHEAD_USB_PERIPH_EXTINT0	0x02000000
-
-#define HAMMERHEAD_FPGA_PERIPH_MOSI	0x00000002
-#define HAMMERHEAD_FPGA_PERIPH_SCK	0x00000020
-#define HAMMERHEAD_FPGA_PERIPH_EXTINT3	0x10000000
-
-static struct smc_timing flash_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 40,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 10,
-
-	.ncs_read_pulse		= 80,
-	.nrd_pulse		= 40,
-	.ncs_write_pulse	= 65,
-	.nwe_pulse		= 55,
-
-	.read_cycle		= 120,
-	.write_cycle		= 120,
-};
-
-static struct smc_config flash_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 1,
-};
-
-static struct mtd_partition flash_parts[] = {
-	{
-		.name		= "u-boot",
-		.offset		= 0x00000000,
-		.size		= 0x00020000,           /* 128 KiB */
-		.mask_flags	= MTD_WRITEABLE,
-	},
-	{
-		.name		= "root",
-		.offset		= 0x00020000,
-		.size		= 0x007d0000,
-	},
-	{
-		.name		= "env",
-		.offset		= 0x007f0000,
-		.size		= 0x00010000,
-		.mask_flags	= MTD_WRITEABLE,
-	},
-};
-
-static struct physmap_flash_data flash_data = {
-	.width		= 2,
-	.nr_parts	= ARRAY_SIZE(flash_parts),
-	.parts		= flash_parts,
-};
-
-static struct resource flash_resource = {
-	.start		= 0x00000000,
-	.end		= 0x007fffff,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.resource	= &flash_resource,
-	.num_resources	= 1,
-	.dev		= { .platform_data = &flash_data, },
-};
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
-
-static struct smc_timing isp1160_timing __initdata = {
-	.ncs_read_setup		= 75,
-	.nrd_setup		= 75,
-	.ncs_write_setup	= 75,
-	.nwe_setup		= 75,
-
-
-	/* We use conservative timing settings, as the minimal settings aren't
-	   stable. There may be room for tweaking. */
-	.ncs_read_pulse		= 75,  /* min. 33ns */
-	.nrd_pulse		= 75,  /* min. 33ns */
-	.ncs_write_pulse	= 75,  /* min. 26ns */
-	.nwe_pulse		= 75,  /* min. 26ns */
-
-	.read_cycle		= 225, /* min. 143ns */
-	.write_cycle		= 225, /* min. 136ns */
-};
-
-static struct smc_config isp1160_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 0,
-};
-
-/*
- * The platform delay function is only used to enforce the strange
- * read to write delay. This can not be configured in the SMC. All other
- * timings are controlled by the SMC (see timings obove)
- * So in isp116x-hcd.c we should comment out USE_PLATFORM_DELAY
- */
-void isp116x_delay(struct device *dev, int delay)
-{
-	if (delay > 150)
-		ndelay(delay - 150);
-}
-
-static struct  isp116x_platform_data isp1160_data = {
-	.sel15Kres		= 1,	/* use internal downstream resistors */
-	.oc_enable		= 0,	/* external overcurrent detection */
-	.int_edge_triggered	= 0,	/* interrupt is level triggered */
-	.int_act_high		= 0,	/* interrupt is active low */
-	.delay = isp116x_delay,		/* platform delay function */
-};
-
-static struct resource isp1160_resource[] = {
-	{
-		.start		= 0x08000000,
-		.end		= 0x08000001,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= 0x08000002,
-		.end		= 0x08000003,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= 64,
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device isp1160_device = {
-	.name		= "isp116x-hcd",
-	.id		= 0,
-	.resource	= isp1160_resource,
-	.num_resources	= 3,
-	.dev		= {
-		.platform_data = &isp1160_data,
-	},
-};
-#endif
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
-static int __init hammerhead_usbh_init(void)
-{
-	struct clk *gclk;
-	struct clk *osc;
-
-	int ret;
-
-	/* setup smc for usbh */
-	smc_set_timing(&isp1160_config, &isp1160_timing);
-	ret = smc_set_configuration(2, &isp1160_config);
-
-	if (ret < 0) {
-		printk(KERN_ERR
-		       "hammerhead: failed to set ISP1160 USBH timing\n");
-		return ret;
-	}
-
-	/* setup gclk0 to run from osc1 */
-	gclk = clk_get(NULL, "gclk0");
-	if (IS_ERR(gclk)) {
-		ret = PTR_ERR(gclk);
-		goto err_gclk;
-	}
-
-	osc = clk_get(NULL, "osc1");
-	if (IS_ERR(osc)) {
-		ret = PTR_ERR(osc);
-		goto err_osc;
-	}
-
-	ret = clk_set_parent(gclk, osc);
-	if (ret < 0) {
-		pr_debug("hammerhead: failed to set osc1 for USBH clock\n");
-		goto err_set_clk;
-	}
-
-	/* set clock to 6MHz */
-	clk_set_rate(gclk, 6000000);
-
-	/* and enable */
-	clk_enable(gclk);
-
-	/* select GCLK0 peripheral function */
-	at32_select_periph(GPIO_PIOA_BASE, HAMMERHEAD_USB_PERIPH_GCLK0,
-			   GPIO_PERIPH_A, 0);
-
-	/* enable CS2 peripheral function */
-	at32_select_periph(GPIO_PIOE_BASE, HAMMERHEAD_USB_PERIPH_CS2,
-			   GPIO_PERIPH_A, 0);
-
-	/* H_WAKEUP must be driven low */
-	at32_select_gpio(GPIO_PIN_PA(8), AT32_GPIOF_OUTPUT);
-
-	/* Select EXTINT0 for PB25 */
-	at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_USB_PERIPH_EXTINT0,
-			   GPIO_PERIPH_A, 0);
-
-	/* register usbh device driver */
-	platform_device_register(&isp1160_device);
-
- err_set_clk:
-	clk_put(osc);
- err_osc:
-	clk_put(gclk);
- err_gclk:
-	return ret;
-}
-#endif
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_FPGA
-static struct smc_timing fpga_timing __initdata = {
-	.ncs_read_setup		= 16,
-	.nrd_setup		= 32,
-	.ncs_read_pulse		= 48,
-	.nrd_pulse		= 32,
-	.read_cycle		= 64,
-
-	.ncs_write_setup	= 16,
-	.nwe_setup		= 16,
-	.ncs_write_pulse	= 32,
-	.nwe_pulse		= 32,
-	.write_cycle		= 64,
-};
-
-static struct smc_config fpga_config __initdata = {
-	.bus_width		= 4,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 0,
-};
-
-static struct resource hh_fpga0_resource[] = {
-	{
-		.start		= 0xffe00400,
-		.end		= 0xffe00400 + 0x3ff,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= 4,
-		.end		= 4,
-		.flags		= IORESOURCE_IRQ,
-	},
-	{
-		.start		= 0x0c000000,
-		.end		= 0x0c000100,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= 67,
-		.end		= 67,
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static u64 hh_fpga0_dma_mask = DMA_BIT_MASK(32);
-static struct platform_device hh_fpga0_device = {
-	.name		= "hh_fpga",
-	.id		= 0,
-	.dev		= {
-		.dma_mask = &hh_fpga0_dma_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-	},
-	.resource	= hh_fpga0_resource,
-	.num_resources	= ARRAY_SIZE(hh_fpga0_resource),
-};
-
-static struct clk hh_fpga0_spi_clk = {
-	.name		= "spi_clk",
-	.dev		= &hh_fpga0_device.dev,
-	.mode		= pba_clk_mode,
-	.get_rate	= pba_clk_get_rate,
-	.index		= 1,
-};
-
-struct platform_device *__init at32_add_device_hh_fpga(void)
-{
-	/* Select peripheral functionallity for SPI SCK and MOSI */
-	at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_FPGA_PERIPH_SCK,
-			   GPIO_PERIPH_B, 0);
-	at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_FPGA_PERIPH_MOSI,
-			   GPIO_PERIPH_B, 0);
-
-	/* reserve all other needed gpio
-	 * We have on board pull ups, so there is no need
-	 * to enable gpio pull ups */
-	/* INIT_DONE (input) */
-	at32_select_gpio(GPIO_PIN_PB(0), 0);
-
-	/* nSTATUS (input) */
-	at32_select_gpio(GPIO_PIN_PB(2), 0);
-
-	/* nCONFIG (output, low) */
-	at32_select_gpio(GPIO_PIN_PB(3), AT32_GPIOF_OUTPUT);
-
-	/* CONF_DONE (input) */
-	at32_select_gpio(GPIO_PIN_PB(4), 0);
-
-	/* Select EXTINT3 for PB28 (Interrupt from FPGA) */
-	at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_FPGA_PERIPH_EXTINT3,
-			   GPIO_PERIPH_A, 0);
-
-	/* Get our parent clock */
-	hh_fpga0_spi_clk.parent = clk_get(NULL, "pba");
-	clk_put(hh_fpga0_spi_clk.parent);
-
-	/* Register clock in at32 clock tree */
-	at32_clk_register(&hh_fpga0_spi_clk);
-
-	platform_device_register(&hh_fpga0_device);
-	return &hh_fpga0_device;
-}
-#endif
-
-/* This needs to be called after the SMC has been initialized */
-static int __init hammerhead_flash_init(void)
-{
-	int ret;
-
-	smc_set_timing(&flash_config, &flash_timing);
-	ret = smc_set_configuration(0, &flash_config);
-
-	if (ret < 0) {
-		printk(KERN_ERR "hammerhead: failed to set NOR flash timing\n");
-		return ret;
-	}
-
-	platform_device_register(&flash_device);
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
-	hammerhead_usbh_init();
-#endif
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_FPGA
-	/* Setup SMC for FPGA interface */
-	smc_set_timing(&fpga_config, &fpga_timing);
-	ret = smc_set_configuration(3, &fpga_config);
-#endif
-
-
-	if (ret < 0) {
-		printk(KERN_ERR "hammerhead: failed to set FPGA timing\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-device_initcall(hammerhead_flash_init);
diff --git a/arch/avr32/boards/hammerhead/flash.h b/arch/avr32/boards/hammerhead/flash.h
deleted file mode 100644
index ea70c626587b..000000000000
--- a/arch/avr32/boards/hammerhead/flash.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __BOARDS_HAMMERHEAD_FLASH_H
-#define __BOARDS_HAMMERHEAD_FLASH_H
-
-struct platform_device *at32_add_device_hh_fpga(void);
-
-#endif /* __BOARDS_HAMMERHEAD_FLASH_H */
diff --git a/arch/avr32/boards/hammerhead/setup.c b/arch/avr32/boards/hammerhead/setup.c
deleted file mode 100644
index dc0e317f2ecd..000000000000
--- a/arch/avr32/boards/hammerhead/setup.c
+++ /dev/null
@@ -1,247 +0,0 @@
-/*
- * Board-specific setup code for the Miromico Hammerhead board
- *
- * Copyright (C) 2008 Miromico AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/atmel-mci.h>
-#include <linux/clk.h>
-#include <linux/fb.h>
-#include <linux/etherdevice.h>
-#include <linux/i2c.h>
-#include <linux/i2c-gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/spi/spi.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <linux/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include <sound/atmel-ac97c.h>
-
-#include "../../mach-at32ap/clock.h"
-#include "flash.h"
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 25000000, /* 25MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_LCD
-static struct fb_videomode __initdata hda350tlv_modes[] = {
-	{
-		.name		= "320x240 @ 75",
-		.refresh	= 75,
-		.xres		= 320,
-		.yres		= 240,
-		.pixclock	= KHZ2PICOS(6891),
-
-		.left_margin	= 48,
-		.right_margin	= 18,
-		.upper_margin	= 18,
-		.lower_margin	= 4,
-		.hsync_len	= 20,
-		.vsync_len	= 2,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata hammerhead_hda350t_monspecs = {
-	.manufacturer		= "HAN",
-	.monitor		= "HDA350T-LV",
-	.modedb			= hda350tlv_modes,
-	.modedb_len		= ARRAY_SIZE(hda350tlv_modes),
-	.hfmin			= 14900,
-	.hfmax			= 22350,
-	.vfmin			= 60,
-	.vfmax			= 90,
-	.dclkmax		= 10000000,
-};
-
-struct atmel_lcdfb_pdata __initdata hammerhead_lcdc_data = {
-	.default_bpp		= 24,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_INVCLK
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &hammerhead_hda350t_monspecs,
-	.guard_time		= 2,
-};
-#endif
-
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-		.detect_pin	= -ENODEV,
-		.wp_pin		= -ENODEV,
-	},
-};
-
-struct eth_addr {
-	u8 addr[6];
-};
-
-static struct eth_addr __initdata hw_addr[1];
-static struct macb_platform_data __initdata eth_data[1];
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
-	int i = tag->u.ethernet.mac_index;
-
-	if (i < ARRAY_SIZE(hw_addr))
-		memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
-		       sizeof(hw_addr[i].addr));
-
-	return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const u8 *addr;
-	void __iomem *regs;
-	struct clk *pclk;
-
-	if (!res)
-		return;
-
-	if (pdev->id >= ARRAY_SIZE(hw_addr))
-		return;
-
-	addr = hw_addr[pdev->id].addr;
-
-	if (!is_valid_ether_addr(addr))
-		return;
-
-	/*
-	 * Since this is board-specific code, we'll cheat and use the
-	 * physical address directly as we happen to know that it's
-	 * the same as the virtual address.
-	 */
-	regs = (void __iomem __force *)res->start;
-	pclk = clk_get(&pdev->dev, "pclk");
-
-	if (IS_ERR(pclk))
-		return;
-
-	clk_enable(pclk);
-
-	__raw_writel((addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) |
-		     addr[0], regs + 0x98);
-	__raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-
-	clk_disable(pclk);
-	clk_put(pclk);
-}
-
-void __init setup_board(void)
-{
-	at32_map_usart(1, 0, 0);	/* USART 1: /dev/ttyS0, DB9 */
-	at32_setup_serial_console(0);
-}
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
-	.sda_pin		= GPIO_PIN_PA(6),
-	.scl_pin		= GPIO_PIN_PA(7),
-	.sda_is_open_drain	= 1,
-	.scl_is_open_drain	= 1,
-	.udelay			= 2,	/* close to 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
-	.name		= "i2c-gpio",
-	.id		= 0,
-	.dev		= { .platform_data = &i2c_gpio_data, },
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {};
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_SND
-static struct ac97c_platform_data ac97c_data = {
-	.reset_pin = GPIO_PIN_PA(16),
-};
-#endif
-
-static int __init hammerhead_init(void)
-{
-	/*
-	 * Hammerhead uses 32-bit SDRAM interface. Reserve the
-	 * SDRAM-specific pins so that nobody messes with them.
-	 */
-	at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-	at32_add_device_usart(0);
-
-	/* Reserve PB29 (GCLK3). This pin is used as clock source
-	 * for ETH PHY (25MHz). GCLK3 setup is done by U-Boot.
-	 */
-	at32_reserve_pin(GPIO_PIOB_BASE, (1<<29));
-
-	/*
-	 * Hammerhead uses only one ethernet port, so we don't set
-	 * address of second port
-	 */
-	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_FPGA
-	at32_add_device_hh_fpga();
-#endif
-	at32_add_device_mci(0, &mci0_data);
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
-	at32_add_device_usba(0, NULL);
-#endif
-#ifdef CONFIG_BOARD_HAMMERHEAD_LCD
-	at32_add_device_lcdc(0, &hammerhead_lcdc_data, fbmem_start,
-			     fbmem_size, ATMEL_LCDC_PRI_24BIT);
-#endif
-
-	at32_select_gpio(i2c_gpio_data.sda_pin,
-			 AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT |
-			 AT32_GPIOF_HIGH);
-	at32_select_gpio(i2c_gpio_data.scl_pin,
-			 AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT |
-			 AT32_GPIOF_HIGH);
-	platform_device_register(&i2c_gpio_device);
-	i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_SND
-	at32_add_device_ac97c(0, &ac97c_data, AC97C_BOTH);
-#endif
-
-	/* Select the Touchscreen interrupt pin mode */
-	at32_select_periph(GPIO_PIOB_BASE, 0x08000000, GPIO_PERIPH_A, 0);
-
-	return 0;
-}
-
-postcore_initcall(hammerhead_init);
diff --git a/arch/avr32/boards/merisc/Kconfig b/arch/avr32/boards/merisc/Kconfig
deleted file mode 100644
index 7e043275d5a9..000000000000
--- a/arch/avr32/boards/merisc/Kconfig
+++ /dev/null
@@ -1,5 +0,0 @@
-# Merisc customization
-
-if BOARD_MERISC
-
-endif	# BOARD_MERISC
diff --git a/arch/avr32/boards/merisc/Makefile b/arch/avr32/boards/merisc/Makefile
deleted file mode 100644
index d24c78729bd1..000000000000
--- a/arch/avr32/boards/merisc/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y					+= setup.o flash.o display.o merisc_sysfs.o
diff --git a/arch/avr32/boards/merisc/display.c b/arch/avr32/boards/merisc/display.c
deleted file mode 100644
index e7683ee7ed40..000000000000
--- a/arch/avr32/boards/merisc/display.c
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Display setup code for the Merisc board
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/fb.h>
-#include <video/atmel_lcdc.h>
-#include <asm/setup.h>
-#include <mach/board.h>
-#include "merisc.h"
-
-static struct fb_videomode merisc_fb_videomode[] = {
-	{
-		.refresh	= 44,
-		.xres		= 640,
-		.yres		= 480,
-		.left_margin	= 96,
-		.right_margin	= 96,
-		.upper_margin	= 34,
-		.lower_margin	= 8,
-		.hsync_len	= 64,
-		.vsync_len	= 64,
-		.name		= "640x480 @ 44",
-		.pixclock	= KHZ2PICOS(25180),
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs merisc_fb_monspecs = {
-	.manufacturer	= "Kyo",
-	.monitor	= "TCG075VG2AD",
-	.modedb		= merisc_fb_videomode,
-	.modedb_len	= ARRAY_SIZE(merisc_fb_videomode),
-	.hfmin		= 30000,
-	.hfmax		= 33333,
-	.vfmin		= 60,
-	.vfmax		= 90,
-	.dclkmax	= 30000000,
-};
-
-struct atmel_lcdfb_pdata merisc_lcdc_data = {
-	.default_bpp		= 24,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &merisc_fb_monspecs,
-	.guard_time		= 2,
-};
-
-static int __init merisc_display_init(void)
-{
-	at32_add_device_lcdc(0, &merisc_lcdc_data, fbmem_start,
-			     fbmem_size, 0);
-
-	return 0;
-}
-device_initcall(merisc_display_init);
diff --git a/arch/avr32/boards/merisc/flash.c b/arch/avr32/boards/merisc/flash.c
deleted file mode 100644
index 8e856fd6f013..000000000000
--- a/arch/avr32/boards/merisc/flash.c
+++ /dev/null
@@ -1,139 +0,0 @@
-/*
- * Merisc board-specific flash initialization
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-#include <mach/smc.h>
-
-/* Will be translated to units of 14.3 ns, rounded up */
-static struct smc_timing flash_timing __initdata = {
-	.ncs_read_setup		= 1 * 14,
-	.nrd_setup		= 5 * 14,
-	.ncs_write_setup	= 1 * 14,
-	.nwe_setup		= 2 * 14,
-
-	.ncs_read_pulse		= 12 * 14,
-	.nrd_pulse		= 7 * 14,
-	.ncs_write_pulse	= 8 * 14,
-	.nwe_pulse		= 4 * 14,
-
-	.read_cycle		= 14 * 14,
-	.write_cycle		= 10 * 14,
-};
-
-static struct smc_config flash_config __initdata = {
-	.bus_width	= 2,
-	.nrd_controlled	= 1,
-	.nwe_controlled	= 1,
-	.byte_write	= 1,
-	.tdf_cycles	= 3,
-};
-
-static struct mtd_partition flash_0_parts[] = {
-	{
-		.name		= "boot",
-		.offset		= 0x00000000,
-		.size		= 0x00060000,
-		.mask_flags	= 0,
-	},
-	{
-		.name		= "kernel",
-		.offset		= 0x00060000,
-		.size		= 0x00200000,
-		.mask_flags	= 0,
-	},
-	{
-		.name		= "root",
-		.offset		= 0x00260000,
-		.size		= MTDPART_SIZ_FULL,
-		.mask_flags	= 0,
-	},
-};
-
-static struct mtd_partition flash_1_parts[] = {
-	{
-		.name		= "2ndflash",
-		.offset		= 0x00000000,
-		.size		= MTDPART_SIZ_FULL,
-		.mask_flags	= 0,
-	},
-};
-
-static struct physmap_flash_data flash_data[] = {
-	{
-		.width		= 2,
-		.nr_parts	= ARRAY_SIZE(flash_0_parts),
-		.parts		= flash_0_parts,
-	},
-	{
-		.width		= 2,
-		.nr_parts	= ARRAY_SIZE(flash_1_parts),
-		.parts		= flash_1_parts,
-	}
-};
-
-static struct resource flash_resource[] = {
-	{
-		.start		= 0x00000000,
-		.end		= 0x03ffffff,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= 0x04000000,
-		.end		= 0x07ffffff,
-		.flags		= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device flash_device[] = {
-	{
-		.name		= "physmap-flash",
-		.id		= 0,
-		.resource	= &flash_resource[0],
-		.num_resources	= 1,
-		.dev		= {
-			.platform_data	= &flash_data[0],
-		},
-	},
-	{
-		.name		= "physmap-flash",
-		.id		= 1,
-		.resource	= &flash_resource[1],
-		.num_resources	= 1,
-		.dev		= {
-			.platform_data	= &flash_data[1],
-		},
-	},
-};
-
-static int __init merisc_flash_init(void)
-{
-	int ret;
-	smc_set_timing(&flash_config, &flash_timing);
-
-	ret = smc_set_configuration(0, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "Merisc: failed to set NOR flash timing #0\n");
-		return ret;
-	}
-
-	ret = smc_set_configuration(4, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "Merisc: failed to set NOR flash timing #1\n");
-		return ret;
-	}
-
-	platform_device_register(&flash_device[0]);
-	platform_device_register(&flash_device[1]);
-	return 0;
-}
-device_initcall(merisc_flash_init);
diff --git a/arch/avr32/boards/merisc/merisc.h b/arch/avr32/boards/merisc/merisc.h
deleted file mode 100644
index 50ffb2f3fcbf..000000000000
--- a/arch/avr32/boards/merisc/merisc.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * Merisc exports
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AVR32_BOARDS_MERISC_MERISC_H
-#define __ARCH_AVR32_BOARDS_MERISC_MERISC_H
-
-const char *merisc_revision(void);
-const char *merisc_model(void);
-
-extern struct class merisc_class;
-
-#endif /* __ARCH_AVR32_BOARDS_MERISC_MERISC_H */
diff --git a/arch/avr32/boards/merisc/merisc_sysfs.c b/arch/avr32/boards/merisc/merisc_sysfs.c
deleted file mode 100644
index 5a252318f4bd..000000000000
--- a/arch/avr32/boards/merisc/merisc_sysfs.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * Merisc sysfs exports
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include <linux/timer.h>
-#include <linux/err.h>
-#include <linux/ctype.h>
-#include "merisc.h"
-
-static ssize_t merisc_model_show(struct class *class, char *buf)
-{
-	ssize_t ret = 0;
-
-	sprintf(buf, "%s\n", merisc_model());
-	ret = strlen(buf) + 1;
-
-	return ret;
-}
-
-static ssize_t merisc_revision_show(struct class *class, char *buf)
-{
-	ssize_t ret = 0;
-
-	sprintf(buf, "%s\n", merisc_revision());
-	ret = strlen(buf) + 1;
-
-	return ret;
-}
-
-static struct class_attribute merisc_class_attrs[] = {
-	__ATTR(model, S_IRUGO, merisc_model_show, NULL),
-	__ATTR(revision, S_IRUGO, merisc_revision_show, NULL),
-	__ATTR_NULL,
-};
-
-struct class merisc_class = {
-	.name =		"merisc",
-	.owner =	THIS_MODULE,
-	.class_attrs =	merisc_class_attrs,
-};
-
-static int __init merisc_sysfs_init(void)
-{
-	int status;
-
-	status = class_register(&merisc_class);
-	if (status < 0)
-		return status;
-
-	return 0;
-}
-
-postcore_initcall(merisc_sysfs_init);
diff --git a/arch/avr32/boards/merisc/setup.c b/arch/avr32/boards/merisc/setup.c
deleted file mode 100644
index 718a6d7eb808..000000000000
--- a/arch/avr32/boards/merisc/setup.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/*
- * Board-specific setup code for the Merisc
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/i2c.h>
-#include <linux/i2c-gpio.h>
-#include <linux/gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/ads7846.h>
-#include <linux/irq.h>
-#include <linux/fb.h>
-#include <linux/atmel-mci.h>
-#include <linux/pwm.h>
-#include <linux/leds_pwm.h>
-
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "merisc.h"
-
-/* Holds the autodetected board model and revision */
-static int merisc_board_id;
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0]	= 32768,	/* 32.768 kHz on RTC osc */
-	[1]	= 20000000,	/* 20 MHz on osc0 */
-	[2]	= 12000000,	/* 12 MHz on osc1 */
-};
-
-struct eth_addr {
-	u8 addr[6];
-};
-
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2];
-
-static int ads7846_get_pendown_state_PB26(void)
-{
-	return !gpio_get_value(GPIO_PIN_PB(26));
-}
-
-static int ads7846_get_pendown_state_PB28(void)
-{
-	return !gpio_get_value(GPIO_PIN_PB(28));
-}
-
-static struct ads7846_platform_data __initdata ads7846_data = {
-	.model				= 7846,
-	.vref_delay_usecs		= 100,
-	.vref_mv			= 0,
-	.keep_vref_on			= 0,
-	.settle_delay_usecs		= 150,
-	.penirq_recheck_delay_usecs	= 1,
-	.x_plate_ohms			= 800,
-	.debounce_rep			= 4,
-	.debounce_max			= 10,
-	.debounce_tol			= 50,
-	.get_pendown_state		= ads7846_get_pendown_state_PB26,
-	.filter_init			= NULL,
-	.filter				= NULL,
-	.filter_cleanup			= NULL,
-};
-
-static struct spi_board_info __initdata spi0_board_info[] = {
-	{
-		.modalias	= "ads7846",
-		.max_speed_hz	= 3250000,
-		.chip_select	= 0,
-		.bus_num	= 0,
-		.platform_data	= &ads7846_data,
-		.mode		= SPI_MODE_0,
-	},
-};
-
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width		= 4,
-		.detect_pin		= GPIO_PIN_PE(19),
-		.wp_pin			= GPIO_PIN_PE(20),
-		.detect_is_active_high	= true,
-	},
-};
-
-static int __init parse_tag_ethernet(struct tag *tag)
-{
-	int i;
-
-	i = tag->u.ethernet.mac_index;
-	if (i < ARRAY_SIZE(hw_addr)) {
-		memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
-		       sizeof(hw_addr[i].addr));
-	}
-
-	return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const u8 *addr;
-	void __iomem *regs;
-	struct clk *pclk;
-
-	if (!res)
-		return;
-
-	if (pdev->id >= ARRAY_SIZE(hw_addr))
-		return;
-
-	addr = hw_addr[pdev->id].addr;
-	if (!is_valid_ether_addr(addr))
-		return;
-
-	regs = (void __iomem __force *)res->start;
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk))
-		return;
-
-	clk_enable(pclk);
-	__raw_writel((addr[3] << 24) | (addr[2] << 16)
-		     | (addr[1] << 8) | addr[0], regs + 0x98);
-	__raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-	clk_disable(pclk);
-	clk_put(pclk);
-}
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
-	.sda_pin		= GPIO_PIN_PA(6),
-	.scl_pin		= GPIO_PIN_PA(7),
-	.sda_is_open_drain	= 1,
-	.scl_is_open_drain	= 1,
-	.udelay			= 2,
-};
-
-static struct platform_device i2c_gpio_device = {
-	.name	= "i2c-gpio",
-	.id	= 0,
-	.dev	= {
-		.platform_data	= &i2c_gpio_data,
-	},
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {
-	{
-		I2C_BOARD_INFO("pcf8563", 0x51)
-	},
-};
-
-#if IS_ENABLED(CONFIG_LEDS_PWM)
-static struct pwm_lookup pwm_lookup[] = {
-	PWM_LOOKUP("at91sam9rl-pwm", 0, "leds_pwm", "backlight",
-		   5000, PWM_POLARITY_NORMAL),
-};
-
-static struct led_pwm pwm_leds[] = {
-	{
-		.name	= "backlight",
-		.max_brightness = 255,
-	},
-};
-
-static struct led_pwm_platform_data pwm_data = {
-	.num_leds       = ARRAY_SIZE(pwm_leds),
-	.leds           = pwm_leds,
-};
-
-static struct platform_device leds_pwm = {
-	.name   = "leds_pwm",
-	.id     = -1,
-	.dev    = {
-		.platform_data = &pwm_data,
-	},
-};
-#endif
-
-const char *merisc_model(void)
-{
-	switch (merisc_board_id) {
-	case 0:
-	case 1:
-		return "500-01";
-	case 2:
-		return "BT";
-	default:
-		return "Unknown";
-	}
-}
-
-const char *merisc_revision(void)
-{
-	switch (merisc_board_id) {
-	case 0:
-		return "B";
-	case 1:
-		return "D";
-	case 2:
-		return "A";
-	default:
-		return "Unknown";
-	}
-}
-
-static void detect_merisc_board_id(void)
-{
-	/* Board ID pins MUST be set as input or the board may be damaged */
-	at32_select_gpio(GPIO_PIN_PA(24), AT32_GPIOF_PULLUP);
-	at32_select_gpio(GPIO_PIN_PA(25), AT32_GPIOF_PULLUP);
-	at32_select_gpio(GPIO_PIN_PA(26), AT32_GPIOF_PULLUP);
-	at32_select_gpio(GPIO_PIN_PA(27), AT32_GPIOF_PULLUP);
-
-	merisc_board_id = !gpio_get_value(GPIO_PIN_PA(24)) +
-		!gpio_get_value(GPIO_PIN_PA(25)) * 2 +
-		!gpio_get_value(GPIO_PIN_PA(26)) * 4 +
-		!gpio_get_value(GPIO_PIN_PA(27)) * 8;
-}
-
-void __init setup_board(void)
-{
-	at32_map_usart(0, 0, 0);
-	at32_map_usart(1, 1, 0);
-	at32_map_usart(3, 3, 0);
-	at32_setup_serial_console(1);
-}
-
-static int __init merisc_init(void)
-{
-	detect_merisc_board_id();
-
-	printk(KERN_NOTICE "BOARD: Merisc %s revision %s\n", merisc_model(),
-	       merisc_revision());
-
-	/* Reserve pins for SDRAM */
-	at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL | (1 << 26));
-
-	if (merisc_board_id >= 1)
-		at32_map_usart(2, 2, 0);
-
-	at32_add_device_usart(0);
-	at32_add_device_usart(1);
-	if (merisc_board_id >= 1)
-		at32_add_device_usart(2);
-	at32_add_device_usart(3);
-	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
-
-	/* ADS7846 PENIRQ */
-	if (merisc_board_id == 0) {
-		ads7846_data.get_pendown_state = ads7846_get_pendown_state_PB26;
-		at32_select_periph(GPIO_PIOB_BASE, 1 << 26,
-				   GPIO_PERIPH_A, AT32_GPIOF_PULLUP);
-		spi0_board_info[0].irq = AT32_EXTINT(1);
-	} else {
-		ads7846_data.get_pendown_state = ads7846_get_pendown_state_PB28;
-		at32_select_periph(GPIO_PIOB_BASE, 1 << 28, GPIO_PERIPH_A,
-				   AT32_GPIOF_PULLUP);
-		spi0_board_info[0].irq = AT32_EXTINT(3);
-	}
-
-	/* ADS7846 busy pin */
-	at32_select_gpio(GPIO_PIN_PA(4), AT32_GPIOF_PULLUP);
-
-	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-
-	at32_add_device_mci(0, &mci0_data);
-
-#if IS_ENABLED(CONFIG_LEDS_PWM)
-	pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
-	at32_add_device_pwm((1 << 0) | (1 << 2));
-	platform_device_register(&leds_pwm);
-#else
-	at32_add_device_pwm((1 << 2));
-#endif
-
-	at32_select_gpio(i2c_gpio_data.sda_pin,
-		AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	at32_select_gpio(i2c_gpio_data.scl_pin,
-		AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	platform_device_register(&i2c_gpio_device);
-
-	i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
-	return 0;
-}
-postcore_initcall(merisc_init);
diff --git a/arch/avr32/boards/mimc200/Makefile b/arch/avr32/boards/mimc200/Makefile
deleted file mode 100644
index c740aa116755..000000000000
--- a/arch/avr32/boards/mimc200/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y				+= setup.o flash.o
diff --git a/arch/avr32/boards/mimc200/flash.c b/arch/avr32/boards/mimc200/flash.c
deleted file mode 100644
index d83d650fc13f..000000000000
--- a/arch/avr32/boards/mimc200/flash.c
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * MIMC200 board-specific flash initialization
- *
- * Copyright (C) 2008 Mercury IMC Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 15,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 0,
-
-	.ncs_read_pulse		= 115,
-	.nrd_pulse		= 110,
-	.ncs_write_pulse	= 60,
-	.nwe_pulse		= 60,
-
-	.read_cycle		= 115,
-	.write_cycle		= 100,
-};
-
-static struct smc_config flash_config __initdata = {
-	.bus_width		= 2,
-	.nrd_controlled		= 1,
-	.nwe_controlled		= 1,
-	.byte_write		= 1,
-};
-
-/* system flash definition */
-
-static struct mtd_partition flash_parts_system[] = {
-	{
-		.name           = "u-boot",
-		.offset         = 0x00000000,
-		.size           = 0x00020000,           /* 128 KiB */
-		.mask_flags     = MTD_WRITEABLE,
-	},
-	{
-		.name           = "root",
-		.offset         = 0x00020000,
-		.size           = 0x007c0000,
-	},
-	{
-		.name		= "splash",
-		.offset		= 0x007e0000,
-		.size		= 0x00010000,		/* 64KiB */
-	},
-	{
-		.name           = "env",
-		.offset         = 0x007f0000,
-		.size           = 0x00010000,
-		.mask_flags     = MTD_WRITEABLE,
-	},
-};
-
-static struct physmap_flash_data flash_system = {
-	.width		= 2,
-	.nr_parts	= ARRAY_SIZE(flash_parts_system),
-	.parts		= flash_parts_system,
-};
-
-static struct resource flash_resource_system = {
-	.start		= 0x00000000,
-	.end		= 0x007fffff,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device_system = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.resource	= &flash_resource_system,
-	.num_resources	= 1,
-	.dev		= {
-		.platform_data = &flash_system,
-	},
-};
-
-/* data flash definition */
-
-static struct mtd_partition flash_parts_data[] = {
-	{
-		.name		= "data",
-		.offset		= 0x00000000,
-		.size		= 0x00800000,
-	},
-};
-
-static struct physmap_flash_data flash_data = {
-	.width		= 2,
-	.nr_parts	= ARRAY_SIZE(flash_parts_data),
-	.parts		= flash_parts_data,
-};
-
-static struct resource flash_resource_data = {
-	.start		= 0x08000000,
-	.end		= 0x087fffff,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device_data = {
-	.name		= "physmap-flash",
-	.id		= 1,
-	.resource	= &flash_resource_data,
-	.num_resources	= 1,
-	.dev		= {
-		.platform_data = &flash_data,
-	},
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init mimc200_flash_init(void)
-{
-	int ret;
-
-	smc_set_timing(&flash_config, &flash_timing);
-	ret = smc_set_configuration(0, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "mimc200: failed to set 'System' NOR flash timing\n");
-		return ret;
-	}
-	ret = smc_set_configuration(1, &flash_config);
-	if (ret < 0) {
-		printk(KERN_ERR "mimc200: failed to set 'Data' NOR flash timing\n");
-		return ret;
-	}
-
-	platform_device_register(&flash_device_system);
-	platform_device_register(&flash_device_data);
-
-	return 0;
-}
-device_initcall(mimc200_flash_init);
diff --git a/arch/avr32/boards/mimc200/setup.c b/arch/avr32/boards/mimc200/setup.c
deleted file mode 100644
index 1cb8e9cc5cfa..000000000000
--- a/arch/avr32/boards/mimc200/setup.c
+++ /dev/null
@@ -1,236 +0,0 @@
-/*
- * Board-specific setup code for the MIMC200
- *
- * Copyright (C) 2008 Mercury IMC Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-extern struct atmel_lcdfb_pdata mimc200_lcdc_data;
-
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/i2c-gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/eeprom.h>
-
-#include <video/atmel_lcdc.h>
-#include <linux/fb.h>
-
-#include <linux/atmel-mci.h>
-#include <linux/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
-	[0] = 32768,	/* 32.768 kHz on RTC osc */
-	[1] = 10000000,	/* 10 MHz on osc0 */
-	[2] = 12000000,	/* 12 MHz on osc1 */
-};
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-static struct fb_videomode __initdata pt0434827_modes[] = {
-	{
-		.name		= "480x272 @ 72",
-		.refresh	= 72,
-		.xres		= 480,		.yres		= 272,
-		.pixclock	= KHZ2PICOS(10000),
-
-		.left_margin	= 1,		.right_margin	= 1,
-		.upper_margin	= 12,		.lower_margin	= 1,
-		.hsync_len	= 42,		.vsync_len	= 1,
-
-		.sync		= 0,
-		.vmode		= FB_VMODE_NONINTERLACED,
-	},
-};
-
-static struct fb_monspecs __initdata mimc200_default_monspecs = {
-	.manufacturer		= "PT",
-	.monitor		= "PT0434827-A401",
-	.modedb			= pt0434827_modes,
-	.modedb_len		= ARRAY_SIZE(pt0434827_modes),
-	.hfmin			= 14820,
-	.hfmax			= 22230,
-	.vfmin			= 60,
-	.vfmax			= 85,
-	.dclkmax		= 25200000,
-};
-
-struct atmel_lcdfb_pdata __initdata mimc200_lcdc_data = {
-	.default_bpp		= 16,
-	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
-	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
-				   | ATMEL_LCDC_INVCLK
-				   | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
-				   | ATMEL_LCDC_MEMOR_BIG),
-	.default_monspecs	= &mimc200_default_monspecs,
-	.guard_time		= 2,
-};
-
-struct eth_addr {
-	u8 addr[6];
-};
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2];
-
-static struct spi_eeprom eeprom_25lc010 = {
-		.name = "25lc010",
-		.byte_len = 128,
-		.page_size = 16,
-		.flags = EE_ADDR1,
-};
-
-static struct spi_board_info spi0_board_info[] __initdata = {
-	{
-		.modalias	= "rtc-ds1390",
-		.max_speed_hz	= 4000000,
-		.chip_select	= 2,
-	},
-	{
-		.modalias	= "at25",
-		.max_speed_hz	= 1000000,
-		.chip_select	= 1,
-		.mode		= SPI_MODE_3,
-		.platform_data	= &eeprom_25lc010,
-	},
-};
-
-static struct mci_platform_data __initdata mci0_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-		.detect_pin	= GPIO_PIN_PA(26),
-		.wp_pin		= GPIO_PIN_PA(27),
-	},
-};
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
-	int i;
-
-	i = tag->u.ethernet.mac_index;
-	if (i < ARRAY_SIZE(hw_addr))
-		memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
-		       sizeof(hw_addr[i].addr));
-
-	return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const u8 *addr;
-	void __iomem *regs;
-	struct clk *pclk;
-
-	if (!res)
-		return;
-	if (pdev->id >= ARRAY_SIZE(hw_addr))
-		return;
-
-	addr = hw_addr[pdev->id].addr;
-	if (!is_valid_ether_addr(addr))
-		return;
-
-	/*
-	 * Since this is board-specific code, we'll cheat and use the
-	 * physical address directly as we happen to know that it's
-	 * the same as the virtual address.
-	 */
-	regs = (void __iomem __force *)res->start;
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk))
-		return;
-
-	clk_enable(pclk);
-	__raw_writel((addr[3] << 24) | (addr[2] << 16)
-		     | (addr[1] << 8) | addr[0], regs + 0x98);
-	__raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-	clk_disable(pclk);
-	clk_put(pclk);
-}
-
-void __init setup_board(void)
-{
-	at32_map_usart(0, 0, 0);	/* USART 0: /dev/ttyS0 (TTL --> Altera) */
-	at32_map_usart(1, 1, 0);	/* USART 1: /dev/ttyS1 (RS232) */
-	at32_map_usart(2, 2, 0);	/* USART 2: /dev/ttyS2 (RS485) */
-	at32_map_usart(3, 3, 0);	/* USART 3: /dev/ttyS3 (RS422 Multidrop) */
-}
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
-	.sda_pin		= GPIO_PIN_PA(6),
-	.scl_pin		= GPIO_PIN_PA(7),
-	.sda_is_open_drain	= 1,
-	.scl_is_open_drain	= 1,
-	.udelay			= 2,	/* close to 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
-	.name		= "i2c-gpio",
-	.id		= 0,
-	.dev		= {
-	.platform_data	= &i2c_gpio_data,
-	},
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {
-};
-
-static int __init mimc200_init(void)
-{
-	/*
-	 * MIMC200 uses 16-bit SDRAM interface, so we don't need to
-	 * reserve any pins for it.
-	 */
-
-	at32_add_device_usart(0);
-	at32_add_device_usart(1);
-	at32_add_device_usart(2);
-	at32_add_device_usart(3);
-
-	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
-	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
-
-	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-	at32_add_device_mci(0, &mci0_data);
-	at32_add_device_usba(0, NULL);
-
-	at32_select_periph(GPIO_PIOB_BASE, 1 << 28, 0, AT32_GPIOF_PULLUP);
-	at32_select_gpio(i2c_gpio_data.sda_pin,
-		AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	at32_select_gpio(i2c_gpio_data.scl_pin,
-		AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	platform_device_register(&i2c_gpio_device);
-	i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
-	at32_add_device_lcdc(0, &mimc200_lcdc_data,
-			     fbmem_start, fbmem_size,
-			     ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_CONTROL | ATMEL_LCDC_ALT_24B_DATA);
-
-	return 0;
-}
-postcore_initcall(mimc200_init);
diff --git a/arch/avr32/boot/images/.gitignore b/arch/avr32/boot/images/.gitignore
deleted file mode 100644
index 64ea9d0141d2..000000000000
--- a/arch/avr32/boot/images/.gitignore
+++ /dev/null
@@ -1,4 +0,0 @@
-uImage
-uImage.srec
-vmlinux.cso
-sfdwarf.log
diff --git a/arch/avr32/boot/images/Makefile b/arch/avr32/boot/images/Makefile
deleted file mode 100644
index 2a3b53978a3b..000000000000
--- a/arch/avr32/boot/images/Makefile
+++ /dev/null
@@ -1,57 +0,0 @@
-#
-# Copyright (C) 2004-2006 Atmel Corporation
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-
-extra-y		:= vmlinux.bin vmlinux.gz
-
-OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note.gnu.build-id
-$(obj)/vmlinux.bin: vmlinux FORCE
-	$(call if_changed,objcopy)
-
-$(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-
-UIMAGE_LOADADDR = $(CONFIG_LOAD_ADDRESS)
-UIMAGE_ENTRYADDR = $(CONFIG_ENTRY_ADDRESS)
-UIMAGE_COMPRESSION = gzip
-
-targets += uImage uImage.srec
-$(obj)/uImage: $(obj)/vmlinux.gz
-	$(call if_changed,uimage)
-	@echo '  Image $@ is ready'
-
-OBJCOPYFLAGS_uImage.srec := -I binary -O srec
-$(obj)/uImage.srec: $(obj)/uImage
-	$(call if_changed,objcopy)
-
-OBJCOPYFLAGS_vmlinux.elf := --change-section-lma .text-0x80000000 \
-			    --change-section-lma __ex_table-0x80000000 \
-			    --change-section-lma .rodata-0x80000000 \
-			    --change-section-lma .data-0x80000000 \
-			    --change-section-lma .init-0x80000000 \
-			    --change-section-lma .bss-0x80000000 \
-			    --change-section-lma __param-0x80000000 \
-			    --change-section-lma __ksymtab-0x80000000 \
-			    --change-section-lma __ksymtab_gpl-0x80000000 \
-			    --change-section-lma __kcrctab-0x80000000 \
-			    --change-section-lma __kcrctab_gpl-0x80000000 \
-			    --change-section-lma __ksymtab_strings-0x80000000 \
-			    --set-start 0xa0000000
-$(obj)/vmlinux.elf: vmlinux FORCE
-	$(call if_changed,objcopy)
-
-quiet_cmd_sfdwarf = SFDWARF $@
-      cmd_sfdwarf = sfdwarf $< TO $@ GNUAVR IW $(SFDWARF_FLAGS) > $(obj)/sfdwarf.log
-
-$(obj)/vmlinux.cso: $(obj)/vmlinux.elf FORCE
-	$(call if_changed,sfdwarf)
-
-install: $(BOOTIMAGE)
-	sh $(srctree)/install-kernel.sh $<
-
-# Generated files to be removed upon make clean
-clean-files	:= vmlinux.elf vmlinux.bin vmlinux.gz uImage uImage.srec
diff --git a/arch/avr32/boot/u-boot/Makefile b/arch/avr32/boot/u-boot/Makefile
deleted file mode 100644
index 125ddc96c275..000000000000
--- a/arch/avr32/boot/u-boot/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-extra-y		:= head.o
-
-obj-y		:= empty.o
diff --git a/arch/avr32/boot/u-boot/empty.S b/arch/avr32/boot/u-boot/empty.S
deleted file mode 100644
index 8ac91a5f12f0..000000000000
--- a/arch/avr32/boot/u-boot/empty.S
+++ /dev/null
@@ -1 +0,0 @@
-/* Empty file */
diff --git a/arch/avr32/boot/u-boot/head.S b/arch/avr32/boot/u-boot/head.S
deleted file mode 100644
index 2ffc298f061b..000000000000
--- a/arch/avr32/boot/u-boot/head.S
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Startup code for use with the u-boot bootloader.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/setup.h>
-#include <asm/thread_info.h>
-#include <asm/sysreg.h>
-
-	/*
-	 * The kernel is loaded where we want it to be and all caches
-	 * have just been flushed. We get two parameters from u-boot:
-	 *
-	 * r12 contains a magic number (ATAG_MAGIC)
-	 * r11 points to a tag table providing information about
-	 *     the system.
-	 */
-	.section .init.text,"ax"
-	.global _start
-_start:
-	/* Initialize .bss */
-	lddpc	r2, bss_start_addr
-	lddpc   r3, end_addr
-	mov	r0, 0
-	mov	r1, 0
-1:      st.d    r2++, r0
-	cp      r2, r3
-	brlo    1b
-
-	/* Initialize status register */
-	lddpc	r0, init_sr
-	mtsr	SYSREG_SR, r0
-
-	/* Set initial stack pointer */
-	lddpc	sp, stack_addr
-	sub	sp, -THREAD_SIZE
-
-#ifdef CONFIG_FRAME_POINTER
-	/* Mark last stack frame */
-	mov	lr, 0
-	mov	r7, 0
-#endif
-
-	/* Check if the boot loader actually provided a tag table */
-	lddpc	r0, magic_number
-	cp.w	r12, r0
-	brne	no_tag_table
-
-	/*
-	 * Save the tag table address for later use. This must be done
-	 * _after_ .bss has been initialized...
-	 */
-	lddpc	r0, tag_table_addr
-	st.w	r0[0], r11
-
-	/* Jump to loader-independent setup code */
-	rjmp	kernel_entry
-
-	.align	2
-magic_number:
-	.long	ATAG_MAGIC
-tag_table_addr:
-	.long	bootloader_tags
-bss_start_addr:
-	.long   __bss_start
-end_addr:
-	.long   _end
-init_sr:
-	.long	0x007f0000	/* Supervisor mode, everything masked */
-stack_addr:
-	.long	init_thread_union
-panic_addr:
-	.long	panic
-
-no_tag_table:
-	sub	r12, pc, (. - 2f)
-	/* branch to panic() which can be far away with that construct */
-	lddpc	pc, panic_addr
-2:	.asciz	"Boot loader didn't provide correct magic number\n"
diff --git a/arch/avr32/configs/atngw100_defconfig b/arch/avr32/configs/atngw100_defconfig
deleted file mode 100644
index ce0030020c25..000000000000
--- a/arch/avr32/configs/atngw100_defconfig
+++ /dev/null
@@ -1,142 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKI=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atngw100_evklcd100_defconfig b/arch/avr32/configs/atngw100_evklcd100_defconfig
deleted file mode 100644
index 01ff632249c0..000000000000
--- a/arch/avr32/configs/atngw100_evklcd100_defconfig
+++ /dev/null
@@ -1,158 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKI=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X_QVGA=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atngw100_evklcd101_defconfig b/arch/avr32/configs/atngw100_evklcd101_defconfig
deleted file mode 100644
index c4021dfd5347..000000000000
--- a/arch/avr32/configs/atngw100_evklcd101_defconfig
+++ /dev/null
@@ -1,157 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKI=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atngw100_mrmt_defconfig b/arch/avr32/configs/atngw100_mrmt_defconfig
deleted file mode 100644
index ffcc28df9dbc..000000000000
--- a/arch/avr32/configs/atngw100_mrmt_defconfig
+++ /dev/null
@@ -1,136 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_SLUB_DEBUG is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_OWNERSHIP_TRACE is not set
-# CONFIG_SUSPEND is not set
-CONFIG_PM=y
-CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_GOV_POWERSAVE=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_BT=m
-CONFIG_BT_RFCOMM=m
-CONFIG_BT_RFCOMM_TTY=y
-CONFIG_BT_HIDP=m
-CONFIG_BT_HCIUART=m
-CONFIG_BT_HCIUART_H4=y
-CONFIG_BT_HCIUART_BCSP=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=y
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=m
-# CONFIG_SERIO is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_GPIO=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=y
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=m
-CONFIG_USB_GADGET_DEBUG_FILES=y
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_MMC=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_PWM=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_S35390A=m
-CONFIG_RTC_DRV_AT32AP700X=m
-CONFIG_DMADEVICES=y
-CONFIG_UIO=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRC_CCITT=y
diff --git a/arch/avr32/configs/atngw100mkii_defconfig b/arch/avr32/configs/atngw100mkii_defconfig
deleted file mode 100644
index 04962641c936..000000000000
--- a/arch/avr32/configs/atngw100mkii_defconfig
+++ /dev/null
@@ -1,144 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKII=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atngw100mkii_evklcd100_defconfig b/arch/avr32/configs/atngw100mkii_evklcd100_defconfig
deleted file mode 100644
index 89c2cda573da..000000000000
--- a/arch/avr32/configs/atngw100mkii_evklcd100_defconfig
+++ /dev/null
@@ -1,161 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKII=y
-CONFIG_BOARD_ATNGW100_MKII_LCD=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X_QVGA=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atngw100mkii_evklcd101_defconfig b/arch/avr32/configs/atngw100mkii_evklcd101_defconfig
deleted file mode 100644
index 1b4d4a87a356..000000000000
--- a/arch/avr32/configs/atngw100mkii_evklcd101_defconfig
+++ /dev/null
@@ -1,160 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKII=y
-CONFIG_BOARD_ATNGW100_MKII_LCD=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atstk1002_defconfig b/arch/avr32/configs/atstk1002_defconfig
deleted file mode 100644
index 9b8b52e54b79..000000000000
--- a/arch/avr32/configs/atstk1002_defconfig
+++ /dev/null
@@ -1,157 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE_DEMUX=m
-CONFIG_NET_IPGRE=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_LCD_LTV350QV=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_AT73C213=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atstk1003_defconfig b/arch/avr32/configs/atstk1003_defconfig
deleted file mode 100644
index ccce1a0b7917..000000000000
--- a/arch/avr32/configs/atstk1003_defconfig
+++ /dev/null
@@ -1,137 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATSTK1003=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_AT73C213=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atstk1004_defconfig b/arch/avr32/configs/atstk1004_defconfig
deleted file mode 100644
index e64288fc794d..000000000000
--- a/arch/avr32/configs/atstk1004_defconfig
+++ /dev/null
@@ -1,135 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATSTK1004=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_LCD_LTV350QV=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/atstk1006_defconfig b/arch/avr32/configs/atstk1006_defconfig
deleted file mode 100644
index 7d669f79ff74..000000000000
--- a/arch/avr32/configs/atstk1006_defconfig
+++ /dev/null
@@ -1,160 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATSTK1006=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE_DEMUX=m
-CONFIG_NET_IPGRE=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_LCD_LTV350QV=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_AT73C213=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/avr32/configs/favr-32_defconfig b/arch/avr32/configs/favr-32_defconfig
deleted file mode 100644
index 560c52f87d45..000000000000
--- a/arch/avr32/configs/favr-32_defconfig
+++ /dev/null
@@ -1,143 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_FAVR_32=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_NET_IPIP=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_IPV6_SIT=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT_MOUSEDEV=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=m
-# CONFIG_SERIO is not set
-# CONFIG_CONSOLE_TRANSLATIONS is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_BACKLIGHT_PWM=m
-CONFIG_SOUND=m
-CONFIG_SOUND_PRIME=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-# CONFIG_JFFS2_FS_WRITEBUFFER is not set
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/avr32/configs/hammerhead_defconfig b/arch/avr32/configs/hammerhead_defconfig
deleted file mode 100644
index d57fadb9e6b6..000000000000
--- a/arch/avr32/configs/hammerhead_defconfig
+++ /dev/null
@@ -1,145 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_HAMMERHEAD=y
-CONFIG_BOARD_HAMMERHEAD_USB=y
-CONFIG_BOARD_HAMMERHEAD_LCD=y
-CONFIG_BOARD_HAMMERHEAD_SND=y
-# CONFIG_BOARD_HAMMERHEAD_FPGA is not set
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_SCSI=m
-CONFIG_BLK_DEV_SD=m
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-CONFIG_INPUT_FF_MEMLESS=m
-CONFIG_INPUT_EVDEV=m
-CONFIG_INPUT_TOUCHSCREEN=y
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-CONFIG_HID_A4TECH=m
-CONFIG_HID_APPLE=m
-CONFIG_HID_BELKIN=m
-CONFIG_HID_CHERRY=m
-CONFIG_HID_CHICONY=m
-CONFIG_HID_CYPRESS=m
-CONFIG_HID_EZKEY=m
-CONFIG_HID_GYRATION=m
-CONFIG_HID_LOGITECH=m
-CONFIG_HID_MICROSOFT=m
-CONFIG_HID_MONTEREY=m
-CONFIG_HID_PANTHERLORD=m
-CONFIG_HID_PETALYNX=m
-CONFIG_HID_SAMSUNG=m
-CONFIG_HID_SUNPLUS=m
-CONFIG_USB=m
-CONFIG_USB_MON=m
-CONFIG_USB_ISP116X_HCD=m
-CONFIG_USB_STORAGE=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_MMC=m
-CONFIG_MMC_ATMELMCI=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_EXT2_FS=m
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_ARC4=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_ITU_T=m
-CONFIG_CRC7=m
diff --git a/arch/avr32/configs/merisc_defconfig b/arch/avr32/configs/merisc_defconfig
deleted file mode 100644
index e6a9cb7d574e..000000000000
--- a/arch/avr32/configs/merisc_defconfig
+++ /dev/null
@@ -1,115 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_MERISC=y
-CONFIG_AP700X_32_BIT_SMC=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_CAN=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_ABSENT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_BLOCK2MTD=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_ATMEL_SSC=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_UINPUT=y
-# CONFIG_SERIO is not set
-# CONFIG_CONSOLE_TRANSLATIONS is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_GPIO=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=y
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-CONFIG_MMC=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_PWM=y
-CONFIG_RTC_CLASS=y
-# CONFIG_RTC_HCTOSYS is not set
-CONFIG_RTC_DRV_PCF8563=y
-CONFIG_DMADEVICES=y
-CONFIG_UIO=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_FS_WBUF_VERIFY=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/avr32/configs/mimc200_defconfig b/arch/avr32/configs/mimc200_defconfig
deleted file mode 100644
index 49c7e890af7b..000000000000
--- a/arch/avr32/configs/mimc200_defconfig
+++ /dev/null
@@ -1,114 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_MIMC200=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_ATMEL_TCLIB=y
-CONFIG_EEPROM_AT24=y
-CONFIG_EEPROM_AT25=y
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_GPIO=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_MMC=y
-CONFIG_MMC_TEST=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_MMC_SPI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1390=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_ARC4=y
-CONFIG_CRC_CCITT=y
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
deleted file mode 100644
index 3d7ef2c17a7c..000000000000
--- a/arch/avr32/include/asm/Kbuild
+++ /dev/null
@@ -1,23 +0,0 @@
-
-generic-y += clkdev.h
-generic-y += delay.h
-generic-y += device.h
-generic-y += div64.h
-generic-y += emergency-restart.h
-generic-y += exec.h
-generic-y += futex.h
-generic-y += irq_regs.h
-generic-y += irq_work.h
-generic-y += local.h
-generic-y += local64.h
-generic-y += mcs_spinlock.h
-generic-y += mm-arch-hooks.h
-generic-y += param.h
-generic-y += percpu.h
-generic-y += preempt.h
-generic-y += sections.h
-generic-y += topology.h
-generic-y += trace_clock.h
-generic-y += vga.h
-generic-y += word-at-a-time.h
-generic-y += xor.h
diff --git a/arch/avr32/include/asm/addrspace.h b/arch/avr32/include/asm/addrspace.h
deleted file mode 100644
index 5a47a7979648..000000000000
--- a/arch/avr32/include/asm/addrspace.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Definitions for the address spaces of the AVR32 CPUs. Heavily based on
- * include/asm-sh/addrspace.h
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ADDRSPACE_H
-#define __ASM_AVR32_ADDRSPACE_H
-
-#ifdef CONFIG_MMU
-
-/* Memory segments when segmentation is enabled */
-#define P0SEG		0x00000000
-#define P1SEG		0x80000000
-#define P2SEG		0xa0000000
-#define P3SEG		0xc0000000
-#define P4SEG		0xe0000000
-
-/* Returns the privileged segment base of a given address */
-#define PXSEG(a)	(((unsigned long)(a)) & 0xe0000000)
-
-/* Returns the physical address of a PnSEG (n=1,2) address */
-#define PHYSADDR(a)	(((unsigned long)(a)) & 0x1fffffff)
-
-/*
- * Map an address to a certain privileged segment
- */
-#define P1SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
-				      | P1SEG))
-#define P2SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
-				      | P2SEG))
-#define P3SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
-				      | P3SEG))
-#define P4SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
-				      | P4SEG))
-
-#endif /* CONFIG_MMU */
-
-#endif /* __ASM_AVR32_ADDRSPACE_H */
diff --git a/arch/avr32/include/asm/asm-offsets.h b/arch/avr32/include/asm/asm-offsets.h
deleted file mode 100644
index d370ee36a182..000000000000
--- a/arch/avr32/include/asm/asm-offsets.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <generated/asm-offsets.h>
diff --git a/arch/avr32/include/asm/asm.h b/arch/avr32/include/asm/asm.h
deleted file mode 100644
index a2c64f404b98..000000000000
--- a/arch/avr32/include/asm/asm.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ASM_H__
-#define __ASM_AVR32_ASM_H__
-
-#include <asm/sysreg.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-
-#define mask_interrupts		ssrf	SYSREG_GM_OFFSET
-#define mask_exceptions		ssrf	SYSREG_EM_OFFSET
-#define unmask_interrupts	csrf	SYSREG_GM_OFFSET
-#define unmask_exceptions	csrf	SYSREG_EM_OFFSET
-
-#ifdef CONFIG_FRAME_POINTER
-	.macro	save_fp
-	st.w	--sp, r7
-	.endm
-	.macro	restore_fp
-	ld.w	r7, sp++
-	.endm
-	.macro	zero_fp
-	mov	r7, 0
-	.endm
-#else
-	.macro	save_fp
-	.endm
-	.macro	restore_fp
-	.endm
-	.macro	zero_fp
-	.endm
-#endif
-	.macro	get_thread_info reg
-	mov	\reg, sp
-	andl	\reg, ~(THREAD_SIZE - 1) & 0xffff
-	.endm
-
-	/* Save and restore registers */
-	.macro	save_min sr, tmp=lr
-	pushm	lr
-	mfsr	\tmp, \sr
-	zero_fp
-	st.w	--sp, \tmp
-	.endm
-
-	.macro	restore_min sr, tmp=lr
-	ld.w	\tmp, sp++
-	mtsr	\sr, \tmp
-	popm	lr
-	.endm
-
-	.macro	save_half sr, tmp=lr
-	save_fp
-	pushm	r8-r9,r10,r11,r12,lr
-	zero_fp
-	mfsr	\tmp, \sr
-	st.w	--sp, \tmp
-	.endm
-
-	.macro	restore_half sr, tmp=lr
-	ld.w	\tmp, sp++
-	mtsr	\sr, \tmp
-	popm	r8-r9,r10,r11,r12,lr
-	restore_fp
-	.endm
-
-	.macro	save_full_user sr, tmp=lr
-	stmts	--sp, r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,sp,lr
-	st.w	--sp, lr
-	zero_fp
-	mfsr	\tmp, \sr
-	st.w	--sp, \tmp
-	.endm
-
-	.macro	restore_full_user sr, tmp=lr
-	ld.w	\tmp, sp++
-	mtsr	\sr, \tmp
-	ld.w	lr, sp++
-	ldmts	sp++, r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,sp,lr
-	.endm
-
-	/* uaccess macros */
-	.macro branch_if_kernel scratch, label
-	get_thread_info \scratch
-	ld.w	\scratch, \scratch[TI_flags]
-	bld	\scratch, TIF_USERSPACE
-	brcc	\label
-	.endm
-
-	.macro ret_if_privileged scratch, addr, size, ret
-	sub	\scratch, \size, 1
-	add	\scratch, \addr
-	retcs	\ret
-	retmi	\ret
-	.endm
-
-#endif /* __ASM_AVR32_ASM_H__ */
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
deleted file mode 100644
index 3d5ce38a6f0b..000000000000
--- a/arch/avr32/include/asm/atomic.h
+++ /dev/null
@@ -1,243 +0,0 @@
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc.
- *
- * But use these as seldom as possible since they are slower than
- * regular operations.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ATOMIC_H
-#define __ASM_AVR32_ATOMIC_H
-
-#include <linux/types.h>
-#include <asm/cmpxchg.h>
-
-#define ATOMIC_INIT(i)  { (i) }
-
-#define atomic_read(v)		READ_ONCE((v)->counter)
-#define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
-
-#define ATOMIC_OP_RETURN(op, asm_op, asm_con)				\
-static inline int __atomic_##op##_return(int i, atomic_t *v)		\
-{									\
-	int result;							\
-									\
-	asm volatile(							\
-		"/* atomic_" #op "_return */\n"				\
-		"1:	ssrf	5\n"					\
-		"	ld.w	%0, %2\n"				\
-		"	" #asm_op "	%0, %3\n"			\
-		"	stcond	%1, %0\n"				\
-		"	brne	1b"					\
-		: "=&r" (result), "=o" (v->counter)			\
-		: "m" (v->counter), #asm_con (i)			\
-		: "cc");						\
-									\
-	return result;							\
-}
-
-#define ATOMIC_FETCH_OP(op, asm_op, asm_con)				\
-static inline int __atomic_fetch_##op(int i, atomic_t *v)		\
-{									\
-	int result, val;						\
-									\
-	asm volatile(							\
-		"/* atomic_fetch_" #op " */\n"				\
-		"1:	ssrf	5\n"					\
-		"	ld.w	%0, %3\n"				\
-		"	mov	%1, %0\n"				\
-		"	" #asm_op "	%1, %4\n"			\
-		"	stcond	%2, %1\n"				\
-		"	brne	1b"					\
-		: "=&r" (result), "=&r" (val), "=o" (v->counter)	\
-		: "m" (v->counter), #asm_con (i)			\
-		: "cc");						\
-									\
-	return result;							\
-}
-
-ATOMIC_OP_RETURN(sub, sub, rKs21)
-ATOMIC_OP_RETURN(add, add, r)
-ATOMIC_FETCH_OP (sub, sub, rKs21)
-ATOMIC_FETCH_OP (add, add, r)
-
-#define ATOMIC_OPS(op, asm_op)						\
-ATOMIC_OP_RETURN(op, asm_op, r)						\
-static inline void atomic_##op(int i, atomic_t *v)			\
-{									\
-	(void)__atomic_##op##_return(i, v);				\
-}									\
-ATOMIC_FETCH_OP(op, asm_op, r)						\
-static inline int atomic_fetch_##op(int i, atomic_t *v)		\
-{									\
-	return __atomic_fetch_##op(i, v);				\
-}
-
-ATOMIC_OPS(and, and)
-ATOMIC_OPS(or, or)
-ATOMIC_OPS(xor, eor)
-
-#undef ATOMIC_OPS
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
-/*
- * Probably found the reason why we want to use sub with the signed 21-bit
- * limit, it uses one less register than the add instruction that can add up to
- * 32-bit values.
- *
- * Both instructions are 32-bit, to use a 16-bit instruction the immediate is
- * very small; 4 bit.
- *
- * sub 32-bit, type IV, takes a register and subtracts a 21-bit immediate.
- * add 32-bit, type II, adds two register values together.
- */
-#define IS_21BIT_CONST(i)						\
-	(__builtin_constant_p(i) && ((i) >= -1048575) && ((i) <= 1048576))
-
-/*
- * atomic_add_return - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v. Returns the resulting value.
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	if (IS_21BIT_CONST(i))
-		return __atomic_sub_return(-i, v);
-
-	return __atomic_add_return(i, v);
-}
-
-static inline int atomic_fetch_add(int i, atomic_t *v)
-{
-	if (IS_21BIT_CONST(i))
-		return __atomic_fetch_sub(-i, v);
-
-	return __atomic_fetch_add(i, v);
-}
-
-/*
- * atomic_sub_return - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v. Returns the resulting value.
- */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	if (IS_21BIT_CONST(i))
-		return __atomic_sub_return(i, v);
-
-	return __atomic_add_return(-i, v);
-}
-
-static inline int atomic_fetch_sub(int i, atomic_t *v)
-{
-	if (IS_21BIT_CONST(i))
-		return __atomic_fetch_sub(i, v);
-
-	return __atomic_fetch_add(-i, v);
-}
-
-/*
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
-*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int tmp, old = atomic_read(v);
-
-	if (IS_21BIT_CONST(a)) {
-		asm volatile(
-			"/* __atomic_sub_unless */\n"
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %2\n"
-			"	cp.w	%0, %4\n"
-			"	breq	1f\n"
-			"	sub	%0, %3\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b\n"
-			"1:"
-			: "=&r"(tmp), "=o"(v->counter)
-			: "m"(v->counter), "rKs21"(-a), "rKs21"(u)
-			: "cc", "memory");
-	} else {
-		asm volatile(
-			"/* __atomic_add_unless */\n"
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %2\n"
-			"	cp.w	%0, %4\n"
-			"	breq	1f\n"
-			"	add	%0, %3\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b\n"
-			"1:"
-			: "=&r"(tmp), "=o"(v->counter)
-			: "m"(v->counter), "r"(a), "ir"(u)
-			: "cc", "memory");
-	}
-
-	return old;
-}
-
-#undef IS_21BIT_CONST
-
-/*
- * atomic_sub_if_positive - conditionally subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically test @v and subtract @i if @v is greater or equal than @i.
- * The function returns the old value of @v minus @i.
- */
-static inline int atomic_sub_if_positive(int i, atomic_t *v)
-{
-	int result;
-
-	asm volatile(
-		"/* atomic_sub_if_positive */\n"
-		"1:	ssrf	5\n"
-		"	ld.w	%0, %2\n"
-		"	sub	%0, %3\n"
-		"	brlt	1f\n"
-		"	stcond	%1, %0\n"
-		"	brne	1b\n"
-		"1:"
-		: "=&r"(result), "=o"(v->counter)
-		: "m"(v->counter), "ir"(i)
-		: "cc", "memory");
-
-	return result;
-}
-
-#define atomic_xchg(v, new)	(xchg(&((v)->counter), new))
-#define atomic_cmpxchg(v, o, n)	(cmpxchg(&((v)->counter), (o), (n)))
-
-#define atomic_sub(i, v)	(void)atomic_sub_return(i, v)
-#define atomic_add(i, v)	(void)atomic_add_return(i, v)
-#define atomic_dec(v)		atomic_sub(1, (v))
-#define atomic_inc(v)		atomic_add(1, (v))
-
-#define atomic_dec_return(v)	atomic_sub_return(1, v)
-#define atomic_inc_return(v)	atomic_add_return(1, v)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-
-#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
-
-#endif /*  __ASM_AVR32_ATOMIC_H */
diff --git a/arch/avr32/include/asm/barrier.h b/arch/avr32/include/asm/barrier.h
deleted file mode 100644
index 715100790fd0..000000000000
--- a/arch/avr32/include/asm/barrier.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_BARRIER_H
-#define __ASM_AVR32_BARRIER_H
-
-/*
- * Weirdest thing ever.. no full barrier, but it has a write barrier!
- */
-#define wmb()	asm volatile("sync 0" : : : "memory")
-
-#ifdef CONFIG_SMP
-# error "The AVR32 port does not support SMP"
-#endif
-
-#include <asm-generic/barrier.h>
-
-#endif /* __ASM_AVR32_BARRIER_H */
diff --git a/arch/avr32/include/asm/bitops.h b/arch/avr32/include/asm/bitops.h
deleted file mode 100644
index 910d5374ce59..000000000000
--- a/arch/avr32/include/asm/bitops.h
+++ /dev/null
@@ -1,314 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_BITOPS_H
-#define __ASM_AVR32_BITOPS_H
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <asm/byteorder.h>
-#include <asm/barrier.h>
-
-/*
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile void * addr)
-{
-	unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
-	unsigned long tmp;
-
-	if (__builtin_constant_p(nr)) {
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %2\n"
-			"	sbr	%0, %3\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p)
-			: "m"(*p), "i"(nr)
-			: "cc");
-	} else {
-		unsigned long mask = 1UL << (nr % BITS_PER_LONG);
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %2\n"
-			"	or	%0, %3\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p)
-			: "m"(*p), "r"(mask)
-			: "cc");
-	}
-}
-
-/*
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile void * addr)
-{
-	unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
-	unsigned long tmp;
-
-	if (__builtin_constant_p(nr)) {
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %2\n"
-			"	cbr	%0, %3\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p)
-			: "m"(*p), "i"(nr)
-			: "cc");
-	} else {
-		unsigned long mask = 1UL << (nr % BITS_PER_LONG);
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %2\n"
-			"	andn	%0, %3\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p)
-			: "m"(*p), "r"(mask)
-			: "cc");
-	}
-}
-
-/*
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile void * addr)
-{
-	unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
-	unsigned long mask = 1UL << (nr % BITS_PER_LONG);
-	unsigned long tmp;
-
-	asm volatile(
-		"1:	ssrf	5\n"
-		"	ld.w	%0, %2\n"
-		"	eor	%0, %3\n"
-		"	stcond	%1, %0\n"
-		"	brne	1b"
-		: "=&r"(tmp), "=o"(*p)
-		: "m"(*p), "r"(mask)
-		: "cc");
-}
-
-/*
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile void * addr)
-{
-	unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
-	unsigned long mask = 1UL << (nr % BITS_PER_LONG);
-	unsigned long tmp, old;
-
-	if (__builtin_constant_p(nr)) {
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %3\n"
-			"	mov	%2, %0\n"
-			"	sbr	%0, %4\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p), "=&r"(old)
-			: "m"(*p), "i"(nr)
-			: "memory", "cc");
-	} else {
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%2, %3\n"
-			"	or	%0, %2, %4\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p), "=&r"(old)
-			: "m"(*p), "r"(mask)
-			: "memory", "cc");
-	}
-
-	return (old & mask) != 0;
-}
-
-/*
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile void * addr)
-{
-	unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
-	unsigned long mask = 1UL << (nr % BITS_PER_LONG);
-	unsigned long tmp, old;
-
-	if (__builtin_constant_p(nr)) {
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %3\n"
-			"	mov	%2, %0\n"
-			"	cbr	%0, %4\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p), "=&r"(old)
-			: "m"(*p), "i"(nr)
-			: "memory", "cc");
-	} else {
-		asm volatile(
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %3\n"
-			"	mov	%2, %0\n"
-			"	andn	%0, %4\n"
-			"	stcond	%1, %0\n"
-			"	brne	1b"
-			: "=&r"(tmp), "=o"(*p), "=&r"(old)
-			: "m"(*p), "r"(mask)
-			: "memory", "cc");
-	}
-
-	return (old & mask) != 0;
-}
-
-/*
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile void * addr)
-{
-	unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
-	unsigned long mask = 1UL << (nr % BITS_PER_LONG);
-	unsigned long tmp, old;
-
-	asm volatile(
-		"1:	ssrf	5\n"
-		"	ld.w	%2, %3\n"
-		"	eor	%0, %2, %4\n"
-		"	stcond	%1, %0\n"
-		"	brne	1b"
-		: "=&r"(tmp), "=o"(*p), "=&r"(old)
-		: "m"(*p), "r"(mask)
-		: "memory", "cc");
-
-	return (old & mask) != 0;
-}
-
-#include <asm-generic/bitops/non-atomic.h>
-
-/* Find First bit Set */
-static inline unsigned long __ffs(unsigned long word)
-{
-	unsigned long result;
-
-	asm("brev %1\n\t"
-	    "clz %0,%1"
-	    : "=r"(result), "=&r"(word)
-	    : "1"(word));
-	return result;
-}
-
-/* Find First Zero */
-static inline unsigned long ffz(unsigned long word)
-{
-	return __ffs(~word);
-}
-
-/* Find Last bit Set */
-static inline int fls(unsigned long word)
-{
-	unsigned long result;
-
-	asm("clz %0,%1" : "=r"(result) : "r"(word));
-	return 32 - result;
-}
-
-static inline int __fls(unsigned long word)
-{
-	return fls(word) - 1;
-}
-
-unsigned long find_first_zero_bit(const unsigned long *addr,
-				  unsigned long size);
-#define find_first_zero_bit find_first_zero_bit
-
-unsigned long find_next_zero_bit(const unsigned long *addr,
-				 unsigned long size,
-				 unsigned long offset);
-#define find_next_zero_bit find_next_zero_bit
-
-unsigned long find_first_bit(const unsigned long *addr,
-			     unsigned long size);
-#define find_first_bit find_first_bit
-
-unsigned long find_next_bit(const unsigned long *addr,
-				 unsigned long size,
-				 unsigned long offset);
-#define find_next_bit find_next_bit
-
-/*
- * ffs: find first bit set. This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- *
- * The difference is that bit numbering starts at 1, and if no bit is set,
- * the function returns 0.
- */
-static inline int ffs(unsigned long word)
-{
-	if(word == 0)
-		return 0;
-	return __ffs(word) + 1;
-}
-
-#include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
-
-extern unsigned long find_next_zero_bit_le(const void *addr,
-		unsigned long size, unsigned long offset);
-#define find_next_zero_bit_le find_next_zero_bit_le
-
-extern unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset);
-#define find_next_bit_le find_next_bit_le
-
-#include <asm-generic/bitops/le.h>
-#include <asm-generic/bitops/ext2-atomic.h>
-
-#endif /* __ASM_AVR32_BITOPS_H */
diff --git a/arch/avr32/include/asm/bug.h b/arch/avr32/include/asm/bug.h
deleted file mode 100644
index 85a92d099adb..000000000000
--- a/arch/avr32/include/asm/bug.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_BUG_H
-#define __ASM_AVR32_BUG_H
-
-#ifdef CONFIG_BUG
-
-/*
- * According to our Chief Architect, this compact opcode is very
- * unlikely to ever be implemented.
- */
-#define AVR32_BUG_OPCODE	0x5df0
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-
-#define _BUG_OR_WARN(flags)						\
-	asm volatile(							\
-		"1:	.hword	%0\n"					\
-		"	.section __bug_table,\"a\",@progbits\n"		\
-		"2:	.long	1b\n"					\
-		"	.long	%1\n"					\
-		"	.short	%2\n"					\
-		"	.short	%3\n"					\
-		"	.org	2b + %4\n"				\
-		"	.previous"					\
-		:							\
-		: "i"(AVR32_BUG_OPCODE), "i"(__FILE__),			\
-		  "i"(__LINE__), "i"(flags),				\
-		  "i"(sizeof(struct bug_entry)))
-
-#else
-
-#define _BUG_OR_WARN(flags)						\
-	asm volatile(							\
-		"1:	.hword	%0\n"					\
-		"	.section __bug_table,\"a\",@progbits\n"		\
-		"2:	.long	1b\n"					\
-		"	.short	%1\n"					\
-		"	.org	2b + %2\n"				\
-		"	.previous"					\
-		:							\
-		: "i"(AVR32_BUG_OPCODE), "i"(flags),			\
-		  "i"(sizeof(struct bug_entry)))
-
-#endif /* CONFIG_DEBUG_BUGVERBOSE */
-
-#define BUG()								\
-	do {								\
-		_BUG_OR_WARN(0);					\
-		unreachable();						\
-	} while (0)
-
-#define WARN_ON(condition)							\
-	({								\
-		int __ret_warn_on = !!(condition);			\
-		if (unlikely(__ret_warn_on))				\
-			_BUG_OR_WARN(BUGFLAG_WARNING);			\
-		unlikely(__ret_warn_on);				\
-	})
-
-#define HAVE_ARCH_BUG
-#define HAVE_ARCH_WARN_ON
-
-#endif /* CONFIG_BUG */
-
-#include <asm-generic/bug.h>
-
-struct pt_regs;
-void die(const char *str, struct pt_regs *regs, long err);
-void _exception(long signr, struct pt_regs *regs, int code,
-		unsigned long addr);
-
-#endif /* __ASM_AVR32_BUG_H */
diff --git a/arch/avr32/include/asm/bugs.h b/arch/avr32/include/asm/bugs.h
deleted file mode 100644
index 278661bbd1b0..000000000000
--- a/arch/avr32/include/asm/bugs.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *      void check_bugs(void);
- */
-#ifndef __ASM_AVR32_BUGS_H
-#define __ASM_AVR32_BUGS_H
-
-static void __init check_bugs(void)
-{
-	boot_cpu_data.loops_per_jiffy = loops_per_jiffy;
-}
-
-#endif /* __ASM_AVR32_BUGS_H */
diff --git a/arch/avr32/include/asm/cache.h b/arch/avr32/include/asm/cache.h
deleted file mode 100644
index c3a58a189a91..000000000000
--- a/arch/avr32/include/asm/cache.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef __ASM_AVR32_CACHE_H
-#define __ASM_AVR32_CACHE_H
-
-#define L1_CACHE_SHIFT 5
-#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
-
-/*
- * Memory returned by kmalloc() may be used for DMA, so we must make
- * sure that all such allocations are cache aligned. Otherwise,
- * unrelated code may cause parts of the buffer to be read into the
- * cache before the transfer is done, causing old data to be seen by
- * the CPU.
- */
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
-
-#ifndef __ASSEMBLER__
-struct cache_info {
-	unsigned int ways;
-	unsigned int sets;
-	unsigned int linesz;
-};
-#endif /* __ASSEMBLER */
-
-/* Cache operation constants */
-#define ICACHE_FLUSH		0x00
-#define ICACHE_INVALIDATE	0x01
-#define ICACHE_LOCK		0x02
-#define ICACHE_UNLOCK		0x03
-#define ICACHE_PREFETCH		0x04
-
-#define DCACHE_FLUSH		0x08
-#define DCACHE_LOCK		0x09
-#define DCACHE_UNLOCK		0x0a
-#define DCACHE_INVALIDATE	0x0b
-#define DCACHE_CLEAN		0x0c
-#define DCACHE_CLEAN_INVAL	0x0d
-
-#endif /* __ASM_AVR32_CACHE_H */
diff --git a/arch/avr32/include/asm/cacheflush.h b/arch/avr32/include/asm/cacheflush.h
deleted file mode 100644
index 96e53820bbbd..000000000000
--- a/arch/avr32/include/asm/cacheflush.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_CACHEFLUSH_H
-#define __ASM_AVR32_CACHEFLUSH_H
-
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
-#define CACHE_OP_ICACHE_INVALIDATE	0x01
-#define CACHE_OP_DCACHE_INVALIDATE	0x0b
-#define CACHE_OP_DCACHE_CLEAN		0x0c
-#define CACHE_OP_DCACHE_CLEAN_INVAL	0x0d
-
-/*
- * Invalidate any cacheline containing virtual address vaddr without
- * writing anything back to memory.
- *
- * Note that this function may corrupt unrelated data structures when
- * applied on buffers that are not cacheline aligned in both ends.
- */
-static inline void invalidate_dcache_line(void *vaddr)
-{
-	asm volatile("cache %0[0], %1"
-		     :
-		     : "r"(vaddr), "n"(CACHE_OP_DCACHE_INVALIDATE)
-		     : "memory");
-}
-
-/*
- * Make sure any cacheline containing virtual address vaddr is written
- * to memory.
- */
-static inline void clean_dcache_line(void *vaddr)
-{
-	asm volatile("cache %0[0], %1"
-		     :
-		     : "r"(vaddr), "n"(CACHE_OP_DCACHE_CLEAN)
-		     : "memory");
-}
-
-/*
- * Make sure any cacheline containing virtual address vaddr is written
- * to memory and then invalidate it.
- */
-static inline void flush_dcache_line(void *vaddr)
-{
-	asm volatile("cache %0[0], %1"
-		     :
-		     : "r"(vaddr), "n"(CACHE_OP_DCACHE_CLEAN_INVAL)
-		     : "memory");
-}
-
-/*
- * Invalidate any instruction cacheline containing virtual address
- * vaddr.
- */
-static inline void invalidate_icache_line(void *vaddr)
-{
-	asm volatile("cache %0[0], %1"
-		     :
-		     : "r"(vaddr), "n"(CACHE_OP_ICACHE_INVALIDATE)
-		     : "memory");
-}
-
-/*
- * Applies the above functions on all lines that are touched by the
- * specified virtual address range.
- */
-void invalidate_dcache_region(void *start, size_t len);
-void clean_dcache_region(void *start, size_t len);
-void flush_dcache_region(void *start, size_t len);
-void invalidate_icache_region(void *start, size_t len);
-
-/*
- * Make sure any pending writes are completed before continuing.
- */
-#define flush_write_buffer() asm volatile("sync 0" : : : "memory")
-
-/*
- * The following functions are called when a virtual mapping changes.
- * We do not need to flush anything in this case.
- */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
-/*
- * I think we need to implement this one to be able to reliably
- * execute pages from RAMDISK. However, if we implement the
- * flush_dcache_*() functions, it might not be needed anymore.
- *
- * #define flush_icache_page(vma, page)		do { } while (0)
- */
-extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);
-
-/*
- * These are (I think) related to D-cache aliasing.  We might need to
- * do something here, but only for certain configurations.  No such
- * configurations exist at this time.
- */
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(page)		do { } while (0)
-#define flush_dcache_mmap_unlock(page)		do { } while (0)
-
-/*
- * These are for I/D cache coherency. In this case, we do need to
- * flush with all configurations.
- */
-extern void flush_icache_range(unsigned long start, unsigned long end);
-
-extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
-		unsigned long vaddr, void *dst, const void *src,
-		unsigned long len);
-
-static inline void copy_from_user_page(struct vm_area_struct *vma,
-		struct page *page, unsigned long vaddr, void *dst,
-		const void *src, unsigned long len)
-{
-	memcpy(dst, src, len);
-}
-
-#endif /* __ASM_AVR32_CACHEFLUSH_H */
diff --git a/arch/avr32/include/asm/checksum.h b/arch/avr32/include/asm/checksum.h
deleted file mode 100644
index 4ab7d5bdaf53..000000000000
--- a/arch/avr32/include/asm/checksum.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_CHECKSUM_H
-#define __ASM_AVR32_CHECKSUM_H
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-__wsum csum_partial(const void *buff, int len, __wsum sum);
-
-/*
- * the same as csum_partial, but copies from src while it
- * checksums, and handles user-space pointer exceptions correctly, when needed.
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-__wsum csum_partial_copy_generic(const void *src, void *dst, int len,
-				       __wsum sum, int *src_err_ptr,
-				       int *dst_err_ptr);
-
-/*
- *	Note: when you get a NULL pointer exception here this means someone
- *	passed in an incorrect kernel address to one of these functions.
- *
- *	If you use these functions directly please don't forget the
- *	access_ok().
- */
-static inline
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum)
-{
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
-}
-
-static inline
-__wsum csum_partial_copy_from_user(const void __user *src, void *dst,
-					  int len, __wsum sum, int *err_ptr)
-{
-	return csum_partial_copy_generic((const void __force *)src, dst, len,
-					 sum, err_ptr, NULL);
-}
-
-/*
- *	This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	unsigned int sum, tmp;
-
-	__asm__ __volatile__(
-		"	ld.w	%0, %1++\n"
-		"	ld.w	%3, %1++\n"
-		"	sub	%2, 4\n"
-		"	add	%0, %3\n"
-		"	ld.w	%3, %1++\n"
-		"	adc	%0, %0, %3\n"
-		"	ld.w	%3, %1++\n"
-		"	adc	%0, %0, %3\n"
-		"	acr	%0\n"
-		"1:	ld.w	%3, %1++\n"
-		"	add	%0, %3\n"
-		"	acr	%0\n"
-		"	sub	%2, 1\n"
-		"	brne	1b\n"
-		"	lsl	%3, %0, 16\n"
-		"	andl	%0, 0\n"
-		"	mov	%2, 0xffff\n"
-		"	add	%0, %3\n"
-		"	adc	%0, %0, %2\n"
-		"	com	%0\n"
-		"	lsr	%0, 16\n"
-		: "=r"(sum), "=r"(iph), "=r"(ihl), "=r"(tmp)
-		: "1"(iph), "2"(ihl)
-		: "memory", "cc");
-	return (__force __sum16)sum;
-}
-
-/*
- *	Fold a partial checksum
- */
-
-static inline __sum16 csum_fold(__wsum sum)
-{
-	unsigned int tmp;
-
-	asm("	bfextu	%1, %0, 0, 16\n"
-	    "	lsr	%0, 16\n"
-	    "	add	%0, %1\n"
-	    "	bfextu	%1, %0, 16, 16\n"
-	    "	add	%0, %1"
-	    : "=&r"(sum), "=&r"(tmp)
-	    : "0"(sum));
-
-	return (__force __sum16)~sum;
-}
-
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					__u32 len, __u8 proto,
-					__wsum sum)
-{
-	asm("	add	%0, %1\n"
-	    "	adc	%0, %0, %2\n"
-	    "	adc	%0, %0, %3\n"
-	    "	acr	%0"
-	    : "=r"(sum)
-	    : "r"(daddr), "r"(saddr), "r"(len + proto),
-	      "0"(sum)
-	    : "cc");
-
-	return sum;
-}
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					__u32 len, __u8 proto,
-					__wsum sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
-}
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-
-static inline __sum16 ip_compute_csum(const void *buff, int len)
-{
-    return csum_fold(csum_partial(buff, len, 0));
-}
-
-#endif /* __ASM_AVR32_CHECKSUM_H */
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
deleted file mode 100644
index 572739b4c4b4..000000000000
--- a/arch/avr32/include/asm/cmpxchg.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc.
- *
- * But use these as seldom as possible since they are slower than
- * regular operations.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_CMPXCHG_H
-#define __ASM_AVR32_CMPXCHG_H
-
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-extern void __xchg_called_with_bad_pointer(void);
-
-static inline unsigned long xchg_u32(u32 val, volatile u32 *m)
-{
-	u32 ret;
-
-	asm volatile("xchg %[ret], %[m], %[val]"
-			: [ret] "=&r"(ret), "=m"(*m)
-			: "m"(*m), [m] "r"(m), [val] "r"(val)
-			: "memory");
-	return ret;
-}
-
-static inline unsigned long __xchg(unsigned long x,
-				       volatile void *ptr,
-				       int size)
-{
-	switch(size) {
-	case 4:
-		return xchg_u32(x, ptr);
-	default:
-		__xchg_called_with_bad_pointer();
-		return x;
-	}
-}
-
-static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
-					  unsigned long new)
-{
-	__u32 ret;
-
-	asm volatile(
-		"1:	ssrf	5\n"
-		"	ld.w	%[ret], %[m]\n"
-		"	cp.w	%[ret], %[old]\n"
-		"	brne	2f\n"
-		"	stcond	%[m], %[new]\n"
-		"	brne	1b\n"
-		"2:\n"
-		: [ret] "=&r"(ret), [m] "=m"(*m)
-		: "m"(m), [old] "Ks21r"(old), [new] "r"(new)
-		: "memory", "cc");
-	return ret;
-}
-
-extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
-        volatile int * m, unsigned long old, unsigned long new);
-#define __cmpxchg_u64 __cmpxchg_u64_unsupported_on_32bit_kernels
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32(ptr, old, new);
-	case 8:
-		return __cmpxchg_u64(ptr, old, new);
-	}
-
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr, old, new)					\
-	((typeof(*(ptr)))__cmpxchg((ptr), (unsigned long)(old),	\
-				   (unsigned long)(new),	\
-				   sizeof(*(ptr))))
-
-#include <asm-generic/cmpxchg-local.h>
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-				      unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32(ptr, old, new);
-	default:
-		return __cmpxchg_local_generic(ptr, old, new, size);
-	}
-
-	return old;
-}
-
-#define cmpxchg_local(ptr, old, new)					\
-	((typeof(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(old),	\
-				   (unsigned long)(new),		\
-				   sizeof(*(ptr))))
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#endif /* __ASM_AVR32_CMPXCHG_H */
diff --git a/arch/avr32/include/asm/current.h b/arch/avr32/include/asm/current.h
deleted file mode 100644
index c7b0549eab8a..000000000000
--- a/arch/avr32/include/asm/current.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef __ASM_AVR32_CURRENT_H
-#define __ASM_AVR32_CURRENT_H
-
-#include <linux/thread_info.h>
-
-struct task_struct;
-
-inline static struct task_struct * get_current(void)
-{
-	return current_thread_info()->task;
-}
-
-#define current get_current()
-
-#endif /* __ASM_AVR32_CURRENT_H */
diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h
deleted file mode 100644
index 7388451f9905..000000000000
--- a/arch/avr32/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_AVR32_DMA_MAPPING_H
-#define __ASM_AVR32_DMA_MAPPING_H
-
-extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	int direction);
-
-extern const struct dma_map_ops avr32_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &avr32_dma_ops;
-}
-
-#endif /* __ASM_AVR32_DMA_MAPPING_H */
diff --git a/arch/avr32/include/asm/dma.h b/arch/avr32/include/asm/dma.h
deleted file mode 100644
index 9e91205590ac..000000000000
--- a/arch/avr32/include/asm/dma.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_AVR32_DMA_H
-#define __ASM_AVR32_DMA_H
-
-/* The maximum address that we can perform a DMA transfer to on this platform.
- * Not really applicable to AVR32, but some functions need it. */
-#define MAX_DMA_ADDRESS		0xffffffff
-
-#endif /* __ASM_AVR32_DMA_H */
diff --git a/arch/avr32/include/asm/elf.h b/arch/avr32/include/asm/elf.h
deleted file mode 100644
index 0388ece75b02..000000000000
--- a/arch/avr32/include/asm/elf.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef __ASM_AVR32_ELF_H
-#define __ASM_AVR32_ELF_H
-
-/* AVR32 relocation numbers */
-#define R_AVR32_NONE		0
-#define R_AVR32_32		1
-#define R_AVR32_16		2
-#define R_AVR32_8		3
-#define R_AVR32_32_PCREL	4
-#define R_AVR32_16_PCREL	5
-#define R_AVR32_8_PCREL		6
-#define R_AVR32_DIFF32		7
-#define R_AVR32_DIFF16		8
-#define R_AVR32_DIFF8		9
-#define R_AVR32_GOT32		10
-#define R_AVR32_GOT16		11
-#define R_AVR32_GOT8		12
-#define R_AVR32_21S		13
-#define R_AVR32_16U		14
-#define R_AVR32_16S		15
-#define R_AVR32_8S		16
-#define R_AVR32_8S_EXT		17
-#define R_AVR32_22H_PCREL	18
-#define R_AVR32_18W_PCREL	19
-#define R_AVR32_16B_PCREL	20
-#define R_AVR32_16N_PCREL	21
-#define R_AVR32_14UW_PCREL	22
-#define R_AVR32_11H_PCREL	23
-#define R_AVR32_10UW_PCREL	24
-#define R_AVR32_9H_PCREL	25
-#define R_AVR32_9UW_PCREL	26
-#define R_AVR32_HI16		27
-#define R_AVR32_LO16		28
-#define R_AVR32_GOTPC		29
-#define R_AVR32_GOTCALL		30
-#define R_AVR32_LDA_GOT		31
-#define R_AVR32_GOT21S		32
-#define R_AVR32_GOT18SW		33
-#define R_AVR32_GOT16S		34
-#define R_AVR32_GOT7UW		35
-#define R_AVR32_32_CPENT	36
-#define R_AVR32_CPCALL		37
-#define R_AVR32_16_CP		38
-#define R_AVR32_9W_CP		39
-#define R_AVR32_RELATIVE	40
-#define R_AVR32_GLOB_DAT	41
-#define R_AVR32_JMP_SLOT	42
-#define R_AVR32_ALIGN		43
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct pt_regs) / sizeof (elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_fpu_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) ( (x)->e_machine == EM_AVR32 )
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS32
-#ifdef __LITTLE_ENDIAN__
-#define ELF_DATA	ELFDATA2LSB
-#else
-#define ELF_DATA	ELFDATA2MSB
-#endif
-#define ELF_ARCH	EM_AVR32
-
-#define ELF_EXEC_PAGESIZE	4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE         (TASK_SIZE / 3 * 2)
-
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this CPU supports.  This could be done in user space,
-   but it's not easy, and we've already done it here.  */
-
-#define ELF_HWCAP	(0)
-
-/* This yields a string that ld.so will use to load implementation
-   specific libraries for optimization.  This is more specific in
-   intent than poking at uname or /proc/cpuinfo.
-
-   For the moment, we have only optimizations for the Intel generations,
-   but that could change... */
-
-#define ELF_PLATFORM  (NULL)
-
-#endif /* __ASM_AVR32_ELF_H */
diff --git a/arch/avr32/include/asm/fb.h b/arch/avr32/include/asm/fb.h
deleted file mode 100644
index 41baf84ad402..000000000000
--- a/arch/avr32/include/asm/fb.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-				unsigned long off)
-{
-	vma->vm_page_prot = __pgprot((pgprot_val(vma->vm_page_prot)
-				      & ~_PAGE_CACHABLE)
-				     | (_PAGE_BUFFER | _PAGE_DIRTY));
-}
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/arch/avr32/include/asm/ftrace.h b/arch/avr32/include/asm/ftrace.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/avr32/include/asm/ftrace.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/avr32/include/asm/gpio.h b/arch/avr32/include/asm/gpio.h
deleted file mode 100644
index b771f7105964..000000000000
--- a/arch/avr32/include/asm/gpio.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_GPIO_H
-#define __ASM_AVR32_GPIO_H
-
-#include <mach/gpio.h>
-
-#endif /* __ASM_AVR32_GPIO_H */
diff --git a/arch/avr32/include/asm/hardirq.h b/arch/avr32/include/asm/hardirq.h
deleted file mode 100644
index 9e36e3ff77d2..000000000000
--- a/arch/avr32/include/asm/hardirq.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_HARDIRQ_H
-#define __ASM_AVR32_HARDIRQ_H
-#ifndef __ASSEMBLY__
-#include <asm-generic/hardirq.h>
-#endif /* __ASSEMBLY__ */
-#endif /* __ASM_AVR32_HARDIRQ_H */
diff --git a/arch/avr32/include/asm/hw_irq.h b/arch/avr32/include/asm/hw_irq.h
deleted file mode 100644
index a36f9fcb8fcd..000000000000
--- a/arch/avr32/include/asm/hw_irq.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_AVR32_HW_IRQ_H
-#define __ASM_AVR32_HW_IRQ_H
-
-static inline void hw_resend_irq(struct irq_chip *h, unsigned int i)
-{
-	/* Nothing to do */
-}
-
-#endif /* __ASM_AVR32_HW_IRQ_H */
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
deleted file mode 100644
index f855646e0db7..000000000000
--- a/arch/avr32/include/asm/io.h
+++ /dev/null
@@ -1,329 +0,0 @@
-#ifndef __ASM_AVR32_IO_H
-#define __ASM_AVR32_IO_H
-
-#include <linux/bug.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <asm/addrspace.h>
-#include <asm/byteorder.h>
-
-#include <mach/io.h>
-
-/* virt_to_phys will only work when address is in P1 or P2 */
-static __inline__ unsigned long virt_to_phys(volatile void *address)
-{
-	return PHYSADDR(address);
-}
-
-static __inline__ void * phys_to_virt(unsigned long address)
-{
-	return (void *)P1SEGADDR(address);
-}
-
-#define cached_to_phys(addr)	((unsigned long)PHYSADDR(addr))
-#define uncached_to_phys(addr)	((unsigned long)PHYSADDR(addr))
-#define phys_to_cached(addr)	((void *)P1SEGADDR(addr))
-#define phys_to_uncached(addr)	((void *)P2SEGADDR(addr))
-
-/*
- * Generic IO read/write.  These perform native-endian accesses.  Note
- * that some architectures will want to re-define __raw_{read,write}w.
- */
-extern void __raw_writesb(void __iomem *addr, const void *data, int bytelen);
-extern void __raw_writesw(void __iomem *addr, const void *data, int wordlen);
-extern void __raw_writesl(void __iomem *addr, const void *data, int longlen);
-
-extern void __raw_readsb(const void __iomem *addr, void *data, int bytelen);
-extern void __raw_readsw(const void __iomem *addr, void *data, int wordlen);
-extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
-
-static inline void __raw_writeb(u8 v, volatile void __iomem *addr)
-{
-	*(volatile u8 __force *)addr = v;
-}
-static inline void __raw_writew(u16 v, volatile void __iomem *addr)
-{
-	*(volatile u16 __force *)addr = v;
-}
-static inline void __raw_writel(u32 v, volatile void __iomem *addr)
-{
-	*(volatile u32 __force *)addr = v;
-}
-
-static inline u8 __raw_readb(const volatile void __iomem *addr)
-{
-	return *(const volatile u8 __force *)addr;
-}
-static inline u16 __raw_readw(const volatile void __iomem *addr)
-{
-	return *(const volatile u16 __force *)addr;
-}
-static inline u32 __raw_readl(const volatile void __iomem *addr)
-{
-	return *(const volatile u32 __force *)addr;
-}
-
-/* Convert I/O port address to virtual address */
-#ifndef __io
-# define __io(p)	((void *)phys_to_uncached(p))
-#endif
-
-/*
- * Not really sure about the best way to slow down I/O on
- * AVR32. Defining it as a no-op until we have an actual test case.
- */
-#define SLOW_DOWN_IO	do { } while (0)
-
-#define __BUILD_MEMORY_SINGLE(pfx, bwl, type)				\
-static inline void							\
-pfx##write##bwl(type val, volatile void __iomem *addr)			\
-{									\
-	volatile type *__addr;						\
-	type __val;							\
-									\
-	__addr = (void *)__swizzle_addr_##bwl((unsigned long)(addr));	\
-	__val = pfx##ioswab##bwl(__addr, val);				\
-									\
-	BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long));		\
-									\
-	*__addr = __val;						\
-}									\
-									\
-static inline type pfx##read##bwl(const volatile void __iomem *addr)	\
-{									\
-	volatile type *__addr;						\
-	type __val;							\
-									\
-	__addr = (void *)__swizzle_addr_##bwl((unsigned long)(addr));	\
-									\
-	BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long));		\
-									\
-	__val = *__addr;						\
-	return pfx##ioswab##bwl(__addr, __val);				\
-}
-
-#define __BUILD_IOPORT_SINGLE(pfx, bwl, type, p, slow)			\
-static inline void pfx##out##bwl##p(type val, unsigned long port)	\
-{									\
-	volatile type *__addr;						\
-	type __val;							\
-									\
-	__addr = __io(__swizzle_addr_##bwl(port));			\
-	__val = pfx##ioswab##bwl(__addr, val);				\
-									\
-	BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long));		\
-									\
-	*__addr = __val;						\
-	slow;								\
-}									\
-									\
-static inline type pfx##in##bwl##p(unsigned long port)			\
-{									\
-	volatile type *__addr;						\
-	type __val;							\
-									\
-	__addr = __io(__swizzle_addr_##bwl(port));			\
-									\
-	BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long));		\
-									\
-	__val = *__addr;						\
-	slow;								\
-									\
-	return pfx##ioswab##bwl(__addr, __val);				\
-}
-
-#define __BUILD_MEMORY_PFX(bus, bwl, type)				\
-	__BUILD_MEMORY_SINGLE(bus, bwl, type)
-
-#define BUILDIO_MEM(bwl, type)						\
-	__BUILD_MEMORY_PFX(, bwl, type)					\
-	__BUILD_MEMORY_PFX(__mem_, bwl, type)
-
-#define __BUILD_IOPORT_PFX(bus, bwl, type)				\
-	__BUILD_IOPORT_SINGLE(bus, bwl, type, ,)			\
-	__BUILD_IOPORT_SINGLE(bus, bwl, type, _p, SLOW_DOWN_IO)
-
-#define BUILDIO_IOPORT(bwl, type)					\
-	__BUILD_IOPORT_PFX(, bwl, type)					\
-	__BUILD_IOPORT_PFX(__mem_, bwl, type)
-
-BUILDIO_MEM(b, u8)
-BUILDIO_MEM(w, u16)
-BUILDIO_MEM(l, u32)
-
-BUILDIO_IOPORT(b, u8)
-BUILDIO_IOPORT(w, u16)
-BUILDIO_IOPORT(l, u32)
-
-#define readb_relaxed			readb
-#define readw_relaxed			readw
-#define readl_relaxed			readl
-
-#define readb_be			__raw_readb
-#define readw_be			__raw_readw
-#define readl_be			__raw_readl
-
-#define writeb_relaxed			writeb
-#define writew_relaxed			writew
-#define writel_relaxed			writel
-
-#define writeb_be			__raw_writeb
-#define writew_be			__raw_writew
-#define writel_be			__raw_writel
-
-#define __BUILD_MEMORY_STRING(bwl, type)				\
-static inline void writes##bwl(volatile void __iomem *addr,		\
-			       const void *data, unsigned int count)	\
-{									\
-	const type *__data = data;					\
-									\
-	while (count--)							\
-		__mem_write##bwl(*__data++, addr);			\
-}									\
-									\
-static inline void reads##bwl(const volatile void __iomem *addr,	\
-			      void *data, unsigned int count)		\
-{									\
-	type *__data = data;						\
-									\
-	while (count--)							\
-		*__data++ = __mem_read##bwl(addr);			\
-}
-
-#define __BUILD_IOPORT_STRING(bwl, type)				\
-static inline void outs##bwl(unsigned long port, const void *data,	\
-			     unsigned int count)			\
-{									\
-	const type *__data = data;					\
-									\
-	while (count--)							\
-		__mem_out##bwl(*__data++, port);			\
-}									\
-									\
-static inline void ins##bwl(unsigned long port, void *data,		\
-			   unsigned int count)				\
-{									\
-	type *__data = data;						\
-									\
-	while (count--)							\
-		*__data++ = __mem_in##bwl(port);			\
-}
-
-#define BUILDSTRING(bwl, type)						\
-	__BUILD_MEMORY_STRING(bwl, type)				\
-	__BUILD_IOPORT_STRING(bwl, type)
-
-BUILDSTRING(b, u8)
-BUILDSTRING(w, u16)
-BUILDSTRING(l, u32)
-
-/*
- * io{read,write}{8,16,32} macros in both le (for PCI style consumers) and native be
- */
-#ifndef ioread8
-
-#define ioread8(p)		((unsigned int)readb(p))
-
-#define ioread16(p)		((unsigned int)readw(p))
-#define ioread16be(p)		((unsigned int)__raw_readw(p))
-
-#define ioread32(p)		((unsigned int)readl(p))
-#define ioread32be(p)		((unsigned int)__raw_readl(p))
-
-#define iowrite8(v,p)		writeb(v, p)
-
-#define iowrite16(v,p)		writew(v, p)
-#define iowrite16be(v,p)	__raw_writew(v, p)
-
-#define iowrite32(v,p)		writel(v, p)
-#define iowrite32be(v,p)	__raw_writel(v, p)
-
-#define ioread8_rep(p,d,c)	readsb(p,d,c)
-#define ioread16_rep(p,d,c)	readsw(p,d,c)
-#define ioread32_rep(p,d,c)	readsl(p,d,c)
-
-#define iowrite8_rep(p,s,c)	writesb(p,s,c)
-#define iowrite16_rep(p,s,c)	writesw(p,s,c)
-#define iowrite32_rep(p,s,c)	writesl(p,s,c)
-
-#endif
-
-static inline void memcpy_fromio(void * to, const volatile void __iomem *from,
-				 unsigned long count)
-{
-	memcpy(to, (const void __force *)from, count);
-}
-
-static inline void  memcpy_toio(volatile void __iomem *to, const void * from,
-				unsigned long count)
-{
-	memcpy((void __force *)to, from, count);
-}
-
-static inline void memset_io(volatile void __iomem *addr, unsigned char val,
-			     unsigned long count)
-{
-	memset((void __force *)addr, val, count);
-}
-
-#define mmiowb()
-
-#define IO_SPACE_LIMIT	0xffffffff
-
-extern void __iomem *__ioremap(unsigned long offset, size_t size,
-			       unsigned long flags);
-extern void __iounmap(void __iomem *addr);
-
-/*
- * ioremap	-   map bus memory into CPU space
- * @offset	bus address of the memory
- * @size	size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to make
- * bus memory CPU accessible via the readb/.../writel functions and
- * the other mmio helpers. The returned address is not guaranteed to
- * be usable directly as a virtual address.
- */
-#define ioremap(offset, size)			\
-	__ioremap((offset), (size), 0)
-
-#define ioremap_nocache(offset, size)		\
-	__ioremap((offset), (size), 0)
-
-#define iounmap(addr)				\
-	__iounmap(addr)
-
-#define ioremap_wc ioremap_nocache
-#define ioremap_wt ioremap_nocache
-#define ioremap_uc ioremap_nocache
-
-#define cached(addr) P1SEGADDR(addr)
-#define uncached(addr) P2SEGADDR(addr)
-
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-#define page_to_bus page_to_phys
-#define bus_to_page phys_to_page
-
-/*
- * Create a virtual mapping cookie for an IO port range.  There exists
- * no such thing as port-based I/O on AVR32, so a regular ioremap()
- * should do what we need.
- */
-#define ioport_map(port, nr)	ioremap(port, nr)
-#define ioport_unmap(port)	iounmap(port)
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)    __va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)   p
-
-#endif /* __ASM_AVR32_IO_H */
diff --git a/arch/avr32/include/asm/irq.h b/arch/avr32/include/asm/irq.h
deleted file mode 100644
index 6fa8913f8548..000000000000
--- a/arch/avr32/include/asm/irq.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef __ASM_AVR32_IRQ_H
-#define __ASM_AVR32_IRQ_H
-
-#define NR_INTERNAL_IRQS	64
-
-#include <mach/irq.h>
-
-#ifndef NR_IRQS
-#define NR_IRQS			(NR_INTERNAL_IRQS)
-#endif
-
-#define irq_canonicalize(i)	(i)
-
-#ifndef __ASSEMBLER__
-int nmi_enable(void);
-void nmi_disable(void);
-
-/*
- * Returns a bitmask of pending interrupts in a group.
- */
-extern unsigned long intc_get_pending(unsigned int group);
-#endif
-
-#endif /* __ASM_AVR32_IOCTLS_H */
diff --git a/arch/avr32/include/asm/irqflags.h b/arch/avr32/include/asm/irqflags.h
deleted file mode 100644
index 006e9487372d..000000000000
--- a/arch/avr32/include/asm/irqflags.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_IRQFLAGS_H
-#define __ASM_AVR32_IRQFLAGS_H
-
-#include <linux/types.h>
-#include <asm/sysreg.h>
-
-static inline unsigned long arch_local_save_flags(void)
-{
-	return sysreg_read(SR);
-}
-
-/*
- * This will restore ALL status register flags, not only the interrupt
- * mask flag.
- *
- * The empty asm statement informs the compiler of this fact while
- * also serving as a barrier.
- */
-static inline void arch_local_irq_restore(unsigned long flags)
-{
-	sysreg_write(SR, flags);
-	asm volatile("" : : : "memory", "cc");
-}
-
-static inline void arch_local_irq_disable(void)
-{
-	asm volatile("ssrf %0" : : "n"(SYSREG_GM_OFFSET) : "memory");
-}
-
-static inline void arch_local_irq_enable(void)
-{
-	asm volatile("csrf %0" : : "n"(SYSREG_GM_OFFSET) : "memory");
-}
-
-static inline bool arch_irqs_disabled_flags(unsigned long flags)
-{
-	return (flags & SYSREG_BIT(GM)) != 0;
-}
-
-static inline bool arch_irqs_disabled(void)
-{
-	return arch_irqs_disabled_flags(arch_local_save_flags());
-}
-
-static inline unsigned long arch_local_irq_save(void)
-{
-	unsigned long flags = arch_local_save_flags();
-
-	arch_local_irq_disable();
-
-	return flags;
-}
-
-#endif /* __ASM_AVR32_IRQFLAGS_H */
diff --git a/arch/avr32/include/asm/kdebug.h b/arch/avr32/include/asm/kdebug.h
deleted file mode 100644
index f930ce286803..000000000000
--- a/arch/avr32/include/asm/kdebug.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __ASM_AVR32_KDEBUG_H
-#define __ASM_AVR32_KDEBUG_H
-
-/* Grossly misnamed. */
-enum die_val {
-	DIE_BREAKPOINT,
-	DIE_SSTEP,
-	DIE_NMI,
-	DIE_OOPS,
-};
-
-#endif /* __ASM_AVR32_KDEBUG_H */
diff --git a/arch/avr32/include/asm/kmap_types.h b/arch/avr32/include/asm/kmap_types.h
deleted file mode 100644
index 479330b89796..000000000000
--- a/arch/avr32/include/asm/kmap_types.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_AVR32_KMAP_TYPES_H
-#define __ASM_AVR32_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-# define KM_TYPE_NR 29
-#else
-# define KM_TYPE_NR 14
-#endif
-
-#endif /* __ASM_AVR32_KMAP_TYPES_H */
diff --git a/arch/avr32/include/asm/kprobes.h b/arch/avr32/include/asm/kprobes.h
deleted file mode 100644
index 28dfc61ad384..000000000000
--- a/arch/avr32/include/asm/kprobes.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Kernel Probes (KProbes)
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- * Copyright (C) IBM Corporation, 2002, 2004
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_KPROBES_H
-#define __ASM_AVR32_KPROBES_H
-
-#include <asm-generic/kprobes.h>
-
-#define BREAKPOINT_INSTRUCTION	0xd673	/* breakpoint */
-
-#ifdef CONFIG_KPROBES
-#include <linux/types.h>
-
-typedef u16	kprobe_opcode_t;
-#define MAX_INSN_SIZE		2
-#define MAX_STACK_SIZE		64	/* 32 would probably be OK */
-
-#define kretprobe_blacklist_size 0
-
-#define arch_remove_kprobe(p)	do { } while (0)
-
-/* Architecture specific copy of original instruction */
-struct arch_specific_insn {
-	kprobe_opcode_t	insn[MAX_INSN_SIZE];
-};
-
-struct prev_kprobe {
-	struct kprobe *kp;
-	unsigned int status;
-};
-
-/* per-cpu kprobe control block */
-struct kprobe_ctlblk {
-	unsigned int kprobe_status;
-	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
-};
-
-extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
-
-#define flush_insn_slot(p)	do { } while (0)
-
-#endif /* CONFIG_KPROBES */
-#endif /* __ASM_AVR32_KPROBES_H */
diff --git a/arch/avr32/include/asm/linkage.h b/arch/avr32/include/asm/linkage.h
deleted file mode 100644
index f7b285e910d4..000000000000
--- a/arch/avr32/include/asm/linkage.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
-
-#define __ALIGN .balign 2
-#define __ALIGN_STR ".balign 2"
-
-#endif /* __ASM_LINKAGE_H */
diff --git a/arch/avr32/include/asm/mmu.h b/arch/avr32/include/asm/mmu.h
deleted file mode 100644
index 60c2d2650d32..000000000000
--- a/arch/avr32/include/asm/mmu.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_AVR32_MMU_H
-#define __ASM_AVR32_MMU_H
-
-/* Default "unsigned long" context */
-typedef unsigned long mm_context_t;
-
-#define MMU_ITLB_ENTRIES	64
-#define MMU_DTLB_ENTRIES	64
-
-#endif /* __ASM_AVR32_MMU_H */
diff --git a/arch/avr32/include/asm/mmu_context.h b/arch/avr32/include/asm/mmu_context.h
deleted file mode 100644
index cd87abba8db7..000000000000
--- a/arch/avr32/include/asm/mmu_context.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * ASID handling taken from SH implementation.
- *   Copyright (C) 1999 Niibe Yutaka
- *   Copyright (C) 2003 Paul Mundt
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_MMU_CONTEXT_H
-#define __ASM_AVR32_MMU_CONTEXT_H
-
-#include <linux/mm_types.h>
-
-#include <asm/tlbflush.h>
-#include <asm/sysreg.h>
-#include <asm-generic/mm_hooks.h>
-
-/*
- * The MMU "context" consists of two things:
- *    (a) TLB cache version
- *    (b) ASID (Address Space IDentifier)
- */
-#define MMU_CONTEXT_ASID_MASK		0x000000ff
-#define MMU_CONTEXT_VERSION_MASK	0xffffff00
-#define MMU_CONTEXT_FIRST_VERSION       0x00000100
-#define NO_CONTEXT			0
-
-#define MMU_NO_ASID			0x100
-
-/* Virtual Page Number mask */
-#define MMU_VPN_MASK	0xfffff000
-
-/* Cache of MMU context last used */
-extern unsigned long mmu_context_cache;
-
-/*
- * Get MMU context if needed
- */
-static inline void
-get_mmu_context(struct mm_struct *mm)
-{
-	unsigned long mc = mmu_context_cache;
-
-	if (((mm->context ^ mc) & MMU_CONTEXT_VERSION_MASK) == 0)
-		/* It's up to date, do nothing */
-		return;
-
-	/* It's old, we need to get new context with new version */
-	mc = ++mmu_context_cache;
-	if (!(mc & MMU_CONTEXT_ASID_MASK)) {
-		/*
-		 * We have exhausted all ASIDs of this version.
-		 * Flush the TLB and start new cycle.
-		 */
-		flush_tlb_all();
-		/*
-		 * Fix version. Note that we avoid version #0
-		 * to distinguish NO_CONTEXT.
-		 */
-		if (!mc)
-			mmu_context_cache = mc = MMU_CONTEXT_FIRST_VERSION;
-	}
-	mm->context = mc;
-}
-
-/*
- * Initialize the context related info for a new mm_struct
- * instance.
- */
-static inline int init_new_context(struct task_struct *tsk,
-				       struct mm_struct *mm)
-{
-	mm->context = NO_CONTEXT;
-	return 0;
-}
-
-/*
- * Destroy context related info for an mm_struct that is about
- * to be put to rest.
- */
-static inline void destroy_context(struct mm_struct *mm)
-{
-	/* Do nothing */
-}
-
-static inline void set_asid(unsigned long asid)
-{
-	/* XXX: We're destroying TLBEHI[8:31] */
-	sysreg_write(TLBEHI, asid & MMU_CONTEXT_ASID_MASK);
-	cpu_sync_pipeline();
-}
-
-static inline unsigned long get_asid(void)
-{
-	unsigned long asid;
-
-	asid = sysreg_read(TLBEHI);
-	return asid & MMU_CONTEXT_ASID_MASK;
-}
-
-static inline void activate_context(struct mm_struct *mm)
-{
-	get_mmu_context(mm);
-	set_asid(mm->context & MMU_CONTEXT_ASID_MASK);
-}
-
-static inline void switch_mm(struct mm_struct *prev,
-				 struct mm_struct *next,
-				 struct task_struct *tsk)
-{
-	if (likely(prev != next)) {
-		unsigned long __pgdir = (unsigned long)next->pgd;
-
-		sysreg_write(PTBR, __pgdir);
-		activate_context(next);
-	}
-}
-
-#define deactivate_mm(tsk,mm) do { } while(0)
-
-#define activate_mm(prev, next) switch_mm((prev), (next), NULL)
-
-static inline void
-enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-
-static inline void enable_mmu(void)
-{
-	sysreg_write(MMUCR, (SYSREG_BIT(MMUCR_S)
-			     | SYSREG_BIT(E)
-			     | SYSREG_BIT(MMUCR_I)));
-	nop(); nop(); nop(); nop(); nop(); nop(); nop(); nop();
-
-	if (mmu_context_cache == NO_CONTEXT)
-		mmu_context_cache = MMU_CONTEXT_FIRST_VERSION;
-
-	set_asid(mmu_context_cache & MMU_CONTEXT_ASID_MASK);
-}
-
-static inline void disable_mmu(void)
-{
-	sysreg_write(MMUCR, SYSREG_BIT(MMUCR_S));
-}
-
-#endif /* __ASM_AVR32_MMU_CONTEXT_H */
diff --git a/arch/avr32/include/asm/module.h b/arch/avr32/include/asm/module.h
deleted file mode 100644
index 3f083d385a64..000000000000
--- a/arch/avr32/include/asm/module.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __ASM_AVR32_MODULE_H
-#define __ASM_AVR32_MODULE_H
-
-#include <asm-generic/module.h>
-
-struct mod_arch_syminfo {
-	unsigned long got_offset;
-	int got_initialized;
-};
-
-struct mod_arch_specific {
-	/* Starting offset of got in the module core memory. */
-	unsigned long got_offset;
-	/* Size of the got. */
-	unsigned long got_size;
-	/* Number of symbols in syminfo. */
-	int nsyms;
-	/* Additional symbol information (got offsets). */
-	struct mod_arch_syminfo *syminfo;
-};
-
-#define MODULE_PROC_FAMILY "AVR32v1"
-
-#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-
-#endif /* __ASM_AVR32_MODULE_H */
diff --git a/arch/avr32/include/asm/ocd.h b/arch/avr32/include/asm/ocd.h
deleted file mode 100644
index 6bef09490235..000000000000
--- a/arch/avr32/include/asm/ocd.h
+++ /dev/null
@@ -1,543 +0,0 @@
-/*
- * AVR32 OCD Interface and register definitions
- *
- * Copyright (C) 2004-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_OCD_H
-#define __ASM_AVR32_OCD_H
-
-/* OCD Register offsets. Abbreviations used below:
- *
- *      BP      Breakpoint
- *      Comm    Communication
- *      DT      Data Trace
- *      PC      Program Counter
- *      PID     Process ID
- *      R/W     Read/Write
- *      WP      Watchpoint
- */
-#define OCD_DID				0x0000  /* Device ID */
-#define OCD_DC				0x0008  /* Development Control */
-#define OCD_DS				0x0010  /* Development Status */
-#define OCD_RWCS			0x001c  /* R/W Access Control */
-#define OCD_RWA				0x0024  /* R/W Access Address */
-#define OCD_RWD				0x0028  /* R/W Access Data */
-#define OCD_WT				0x002c  /* Watchpoint Trigger */
-#define OCD_DTC				0x0034  /* Data Trace Control */
-#define OCD_DTSA0			0x0038  /* DT Start Addr Channel 0 */
-#define OCD_DTSA1			0x003c  /* DT Start Addr Channel 1 */
-#define OCD_DTEA0			0x0048  /* DT End Addr Channel 0 */
-#define OCD_DTEA1			0x004c  /* DT End Addr Channel 1 */
-#define OCD_BWC0A			0x0058  /* PC BP/WP Control 0A */
-#define OCD_BWC0B			0x005c  /* PC BP/WP Control 0B */
-#define OCD_BWC1A			0x0060  /* PC BP/WP Control 1A */
-#define OCD_BWC1B			0x0064  /* PC BP/WP Control 1B */
-#define OCD_BWC2A			0x0068  /* PC BP/WP Control 2A */
-#define OCD_BWC2B			0x006c  /* PC BP/WP Control 2B */
-#define OCD_BWC3A			0x0070  /* Data BP/WP Control 3A */
-#define OCD_BWC3B			0x0074  /* Data BP/WP Control 3B */
-#define OCD_BWA0A			0x0078  /* PC BP/WP Address 0A */
-#define OCD_BWA0B			0x007c  /* PC BP/WP Address 0B */
-#define OCD_BWA1A			0x0080  /* PC BP/WP Address 1A */
-#define OCD_BWA1B			0x0084  /* PC BP/WP Address 1B */
-#define OCD_BWA2A			0x0088  /* PC BP/WP Address 2A */
-#define OCD_BWA2B			0x008c  /* PC BP/WP Address 2B */
-#define OCD_BWA3A			0x0090  /* Data BP/WP Address 3A */
-#define OCD_BWA3B			0x0094  /* Data BP/WP Address 3B */
-#define OCD_NXCFG			0x0100  /* Nexus Configuration */
-#define OCD_DINST			0x0104  /* Debug Instruction */
-#define OCD_DPC				0x0108  /* Debug Program Counter */
-#define OCD_CPUCM			0x010c  /* CPU Control Mask */
-#define OCD_DCCPU			0x0110  /* Debug Comm CPU */
-#define OCD_DCEMU			0x0114  /* Debug Comm Emulator */
-#define OCD_DCSR			0x0118  /* Debug Comm Status */
-#define OCD_PID				0x011c  /* Ownership Trace PID */
-#define OCD_EPC0			0x0120  /* Event Pair Control 0 */
-#define OCD_EPC1			0x0124  /* Event Pair Control 1 */
-#define OCD_EPC2			0x0128  /* Event Pair Control 2 */
-#define OCD_EPC3			0x012c  /* Event Pair Control 3 */
-#define OCD_AXC				0x0130  /* AUX port Control */
-
-/* Bits in DID */
-#define OCD_DID_MID_START		1
-#define OCD_DID_MID_SIZE		11
-#define OCD_DID_PN_START		12
-#define OCD_DID_PN_SIZE			16
-#define OCD_DID_RN_START		28
-#define OCD_DID_RN_SIZE			4
-
-/* Bits in DC */
-#define OCD_DC_TM_START			0
-#define OCD_DC_TM_SIZE			2
-#define OCD_DC_EIC_START		3
-#define OCD_DC_EIC_SIZE			2
-#define OCD_DC_OVC_START		5
-#define OCD_DC_OVC_SIZE			3
-#define OCD_DC_SS_BIT			8
-#define OCD_DC_DBR_BIT			12
-#define OCD_DC_DBE_BIT			13
-#define OCD_DC_EOS_START		20
-#define OCD_DC_EOS_SIZE			2
-#define OCD_DC_SQA_BIT			22
-#define OCD_DC_IRP_BIT			23
-#define OCD_DC_IFM_BIT			24
-#define OCD_DC_TOZ_BIT			25
-#define OCD_DC_TSR_BIT			26
-#define OCD_DC_RID_BIT			27
-#define OCD_DC_ORP_BIT			28
-#define OCD_DC_MM_BIT			29
-#define OCD_DC_RES_BIT			30
-#define OCD_DC_ABORT_BIT		31
-
-/* Bits in DS */
-#define OCD_DS_SSS_BIT			0
-#define OCD_DS_SWB_BIT			1
-#define OCD_DS_HWB_BIT			2
-#define OCD_DS_HWE_BIT			3
-#define OCD_DS_STP_BIT			4
-#define OCD_DS_DBS_BIT			5
-#define OCD_DS_BP_START			8
-#define OCD_DS_BP_SIZE			8
-#define OCD_DS_INC_BIT			24
-#define OCD_DS_BOZ_BIT			25
-#define OCD_DS_DBA_BIT			26
-#define OCD_DS_EXB_BIT			27
-#define OCD_DS_NTBF_BIT			28
-
-/* Bits in RWCS */
-#define OCD_RWCS_DV_BIT			0
-#define OCD_RWCS_ERR_BIT		1
-#define OCD_RWCS_CNT_START		2
-#define OCD_RWCS_CNT_SIZE		14
-#define OCD_RWCS_CRC_BIT		19
-#define OCD_RWCS_NTBC_START		20
-#define OCD_RWCS_NTBC_SIZE		2
-#define OCD_RWCS_NTE_BIT		22
-#define OCD_RWCS_NTAP_BIT		23
-#define OCD_RWCS_WRAPPED_BIT		24
-#define OCD_RWCS_CCTRL_START		25
-#define OCD_RWCS_CCTRL_SIZE		2
-#define OCD_RWCS_SZ_START		27
-#define OCD_RWCS_SZ_SIZE		3
-#define OCD_RWCS_RW_BIT			30
-#define OCD_RWCS_AC_BIT			31
-
-/* Bits in RWA */
-#define OCD_RWA_RWA_START		0
-#define OCD_RWA_RWA_SIZE		32
-
-/* Bits in RWD */
-#define OCD_RWD_RWD_START		0
-#define OCD_RWD_RWD_SIZE		32
-
-/* Bits in WT */
-#define OCD_WT_DTE_START		20
-#define OCD_WT_DTE_SIZE			3
-#define OCD_WT_DTS_START		23
-#define OCD_WT_DTS_SIZE			3
-#define OCD_WT_PTE_START		26
-#define OCD_WT_PTE_SIZE			3
-#define OCD_WT_PTS_START		29
-#define OCD_WT_PTS_SIZE			3
-
-/* Bits in DTC */
-#define OCD_DTC_T0WP_BIT		0
-#define OCD_DTC_T1WP_BIT		1
-#define OCD_DTC_ASID0EN_BIT		2
-#define OCD_DTC_ASID0_START		3
-#define OCD_DTC_ASID0_SIZE		8
-#define OCD_DTC_ASID1EN_BIT		11
-#define OCD_DTC_ASID1_START		12
-#define OCD_DTC_ASID1_SIZE		8
-#define OCD_DTC_RWT1_START		28
-#define OCD_DTC_RWT1_SIZE		2
-#define OCD_DTC_RWT0_START		30
-#define OCD_DTC_RWT0_SIZE		2
-
-/* Bits in DTSA0 */
-#define OCD_DTSA0_DTSA_START		0
-#define OCD_DTSA0_DTSA_SIZE		32
-
-/* Bits in DTSA1 */
-#define OCD_DTSA1_DTSA_START		0
-#define OCD_DTSA1_DTSA_SIZE		32
-
-/* Bits in DTEA0 */
-#define OCD_DTEA0_DTEA_START		0
-#define OCD_DTEA0_DTEA_SIZE		32
-
-/* Bits in DTEA1 */
-#define OCD_DTEA1_DTEA_START		0
-#define OCD_DTEA1_DTEA_SIZE		32
-
-/* Bits in BWC0A */
-#define OCD_BWC0A_ASIDEN_BIT		0
-#define OCD_BWC0A_ASID_START		1
-#define OCD_BWC0A_ASID_SIZE		8
-#define OCD_BWC0A_EOC_BIT		14
-#define OCD_BWC0A_AME_BIT		25
-#define OCD_BWC0A_BWE_START		30
-#define OCD_BWC0A_BWE_SIZE		2
-
-/* Bits in BWC0B */
-#define OCD_BWC0B_ASIDEN_BIT		0
-#define OCD_BWC0B_ASID_START		1
-#define OCD_BWC0B_ASID_SIZE		8
-#define OCD_BWC0B_EOC_BIT		14
-#define OCD_BWC0B_AME_BIT		25
-#define OCD_BWC0B_BWE_START		30
-#define OCD_BWC0B_BWE_SIZE		2
-
-/* Bits in BWC1A */
-#define OCD_BWC1A_ASIDEN_BIT		0
-#define OCD_BWC1A_ASID_START		1
-#define OCD_BWC1A_ASID_SIZE		8
-#define OCD_BWC1A_EOC_BIT		14
-#define OCD_BWC1A_AME_BIT		25
-#define OCD_BWC1A_BWE_START		30
-#define OCD_BWC1A_BWE_SIZE		2
-
-/* Bits in BWC1B */
-#define OCD_BWC1B_ASIDEN_BIT		0
-#define OCD_BWC1B_ASID_START		1
-#define OCD_BWC1B_ASID_SIZE		8
-#define OCD_BWC1B_EOC_BIT		14
-#define OCD_BWC1B_AME_BIT		25
-#define OCD_BWC1B_BWE_START		30
-#define OCD_BWC1B_BWE_SIZE		2
-
-/* Bits in BWC2A */
-#define OCD_BWC2A_ASIDEN_BIT		0
-#define OCD_BWC2A_ASID_START		1
-#define OCD_BWC2A_ASID_SIZE		8
-#define OCD_BWC2A_EOC_BIT		14
-#define OCD_BWC2A_AMB_START		20
-#define OCD_BWC2A_AMB_SIZE		5
-#define OCD_BWC2A_AME_BIT		25
-#define OCD_BWC2A_BWE_START		30
-#define OCD_BWC2A_BWE_SIZE		2
-
-/* Bits in BWC2B */
-#define OCD_BWC2B_ASIDEN_BIT		0
-#define OCD_BWC2B_ASID_START		1
-#define OCD_BWC2B_ASID_SIZE		8
-#define OCD_BWC2B_EOC_BIT		14
-#define OCD_BWC2B_AME_BIT		25
-#define OCD_BWC2B_BWE_START		30
-#define OCD_BWC2B_BWE_SIZE		2
-
-/* Bits in BWC3A */
-#define OCD_BWC3A_ASIDEN_BIT		0
-#define OCD_BWC3A_ASID_START		1
-#define OCD_BWC3A_ASID_SIZE		8
-#define OCD_BWC3A_SIZE_START		9
-#define OCD_BWC3A_SIZE_SIZE		3
-#define OCD_BWC3A_EOC_BIT		14
-#define OCD_BWC3A_BWO_START		16
-#define OCD_BWC3A_BWO_SIZE		2
-#define OCD_BWC3A_BME_START		20
-#define OCD_BWC3A_BME_SIZE		4
-#define OCD_BWC3A_BRW_START		28
-#define OCD_BWC3A_BRW_SIZE		2
-#define OCD_BWC3A_BWE_START		30
-#define OCD_BWC3A_BWE_SIZE		2
-
-/* Bits in BWC3B */
-#define OCD_BWC3B_ASIDEN_BIT		0
-#define OCD_BWC3B_ASID_START		1
-#define OCD_BWC3B_ASID_SIZE		8
-#define OCD_BWC3B_SIZE_START		9
-#define OCD_BWC3B_SIZE_SIZE		3
-#define OCD_BWC3B_EOC_BIT		14
-#define OCD_BWC3B_BWO_START		16
-#define OCD_BWC3B_BWO_SIZE		2
-#define OCD_BWC3B_BME_START		20
-#define OCD_BWC3B_BME_SIZE		4
-#define OCD_BWC3B_BRW_START		28
-#define OCD_BWC3B_BRW_SIZE		2
-#define OCD_BWC3B_BWE_START		30
-#define OCD_BWC3B_BWE_SIZE		2
-
-/* Bits in BWA0A */
-#define OCD_BWA0A_BWA_START		0
-#define OCD_BWA0A_BWA_SIZE		32
-
-/* Bits in BWA0B */
-#define OCD_BWA0B_BWA_START		0
-#define OCD_BWA0B_BWA_SIZE		32
-
-/* Bits in BWA1A */
-#define OCD_BWA1A_BWA_START		0
-#define OCD_BWA1A_BWA_SIZE		32
-
-/* Bits in BWA1B */
-#define OCD_BWA1B_BWA_START		0
-#define OCD_BWA1B_BWA_SIZE		32
-
-/* Bits in BWA2A */
-#define OCD_BWA2A_BWA_START		0
-#define OCD_BWA2A_BWA_SIZE		32
-
-/* Bits in BWA2B */
-#define OCD_BWA2B_BWA_START		0
-#define OCD_BWA2B_BWA_SIZE		32
-
-/* Bits in BWA3A */
-#define OCD_BWA3A_BWA_START		0
-#define OCD_BWA3A_BWA_SIZE		32
-
-/* Bits in BWA3B */
-#define OCD_BWA3B_BWA_START		0
-#define OCD_BWA3B_BWA_SIZE		32
-
-/* Bits in NXCFG */
-#define OCD_NXCFG_NXARCH_START		0
-#define OCD_NXCFG_NXARCH_SIZE		4
-#define OCD_NXCFG_NXOCD_START		4
-#define OCD_NXCFG_NXOCD_SIZE		4
-#define OCD_NXCFG_NXPCB_START		8
-#define OCD_NXCFG_NXPCB_SIZE		4
-#define OCD_NXCFG_NXDB_START		12
-#define OCD_NXCFG_NXDB_SIZE		4
-#define OCD_NXCFG_MXMSEO_BIT		16
-#define OCD_NXCFG_NXMDO_START		17
-#define OCD_NXCFG_NXMDO_SIZE		4
-#define OCD_NXCFG_NXPT_BIT		21
-#define OCD_NXCFG_NXOT_BIT		22
-#define OCD_NXCFG_NXDWT_BIT		23
-#define OCD_NXCFG_NXDRT_BIT		24
-#define OCD_NXCFG_NXDTC_START		25
-#define OCD_NXCFG_NXDTC_SIZE		3
-#define OCD_NXCFG_NXDMA_BIT		28
-
-/* Bits in DINST */
-#define OCD_DINST_DINST_START		0
-#define OCD_DINST_DINST_SIZE		32
-
-/* Bits in CPUCM */
-#define OCD_CPUCM_BEM_BIT		1
-#define OCD_CPUCM_FEM_BIT		2
-#define OCD_CPUCM_REM_BIT		3
-#define OCD_CPUCM_IBEM_BIT		4
-#define OCD_CPUCM_IEEM_BIT		5
-
-/* Bits in DCCPU */
-#define OCD_DCCPU_DATA_START		0
-#define OCD_DCCPU_DATA_SIZE		32
-
-/* Bits in DCEMU */
-#define OCD_DCEMU_DATA_START		0
-#define OCD_DCEMU_DATA_SIZE		32
-
-/* Bits in DCSR */
-#define OCD_DCSR_CPUD_BIT		0
-#define OCD_DCSR_EMUD_BIT		1
-
-/* Bits in PID */
-#define OCD_PID_PROCESS_START		0
-#define OCD_PID_PROCESS_SIZE		32
-
-/* Bits in EPC0 */
-#define OCD_EPC0_RNG_START		0
-#define OCD_EPC0_RNG_SIZE		2
-#define OCD_EPC0_CE_BIT			4
-#define OCD_EPC0_ECNT_START		16
-#define OCD_EPC0_ECNT_SIZE		16
-
-/* Bits in EPC1 */
-#define OCD_EPC1_RNG_START		0
-#define OCD_EPC1_RNG_SIZE		2
-#define OCD_EPC1_ATB_BIT		5
-#define OCD_EPC1_AM_BIT			6
-
-/* Bits in EPC2 */
-#define OCD_EPC2_RNG_START		0
-#define OCD_EPC2_RNG_SIZE		2
-#define OCD_EPC2_DB_START		2
-#define OCD_EPC2_DB_SIZE		2
-
-/* Bits in EPC3 */
-#define OCD_EPC3_RNG_START		0
-#define OCD_EPC3_RNG_SIZE		2
-#define OCD_EPC3_DWE_BIT		2
-
-/* Bits in AXC */
-#define OCD_AXC_DIV_START		0
-#define OCD_AXC_DIV_SIZE		4
-#define OCD_AXC_AXE_BIT			8
-#define OCD_AXC_AXS_BIT			9
-#define OCD_AXC_DDR_BIT			10
-#define OCD_AXC_LS_BIT			11
-#define OCD_AXC_REX_BIT			12
-#define OCD_AXC_REXTEN_BIT		13
-
-/* Constants for DC:EIC */
-#define OCD_EIC_PROGRAM_AND_DATA_TRACE	0
-#define OCD_EIC_BREAKPOINT		1
-#define OCD_EIC_NOP			2
-
-/* Constants for DC:OVC */
-#define OCD_OVC_OVERRUN			0
-#define OCD_OVC_DELAY_CPU_BTM		1
-#define OCD_OVC_DELAY_CPU_DTM		2
-#define OCD_OVC_DELAY_CPU_BTM_DTM	3
-
-/* Constants for DC:EOS */
-#define OCD_EOS_NOP			0
-#define OCD_EOS_DEBUG_MODE		1
-#define OCD_EOS_BREAKPOINT_WATCHPOINT	2
-#define OCD_EOS_THQ			3
-
-/* Constants for RWCS:NTBC */
-#define OCD_NTBC_OVERWRITE		0
-#define OCD_NTBC_DISABLE		1
-#define OCD_NTBC_BREAKPOINT		2
-
-/* Constants for RWCS:CCTRL */
-#define OCD_CCTRL_AUTO			0
-#define OCD_CCTRL_CACHED		1
-#define OCD_CCTRL_UNCACHED		2
-
-/* Constants for RWCS:SZ */
-#define OCD_SZ_BYTE			0
-#define OCD_SZ_HALFWORD			1
-#define OCD_SZ_WORD			2
-
-/* Constants for WT:PTS */
-#define OCD_PTS_DISABLED		0
-#define OCD_PTS_PROGRAM_0B		1
-#define OCD_PTS_PROGRAM_1A		2
-#define OCD_PTS_PROGRAM_1B		3
-#define OCD_PTS_PROGRAM_2A		4
-#define OCD_PTS_PROGRAM_2B		5
-#define OCD_PTS_DATA_3A			6
-#define OCD_PTS_DATA_3B			7
-
-/* Constants for DTC:RWT1 */
-#define OCD_RWT1_NO_TRACE		0
-#define OCD_RWT1_DATA_READ		1
-#define OCD_RWT1_DATA_WRITE		2
-#define OCD_RWT1_DATA_READ_WRITE	3
-
-/* Constants for DTC:RWT0 */
-#define OCD_RWT0_NO_TRACE		0
-#define OCD_RWT0_DATA_READ		1
-#define OCD_RWT0_DATA_WRITE		2
-#define OCD_RWT0_DATA_READ_WRITE	3
-
-/* Constants for BWC0A:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC0B:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC1A:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC1B:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC2A:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC2B:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC3A:SIZE */
-#define OCD_SIZE_BYTE_ACCESS		4
-#define OCD_SIZE_HALFWORD_ACCESS	5
-#define OCD_SIZE_WORD_ACCESS		6
-#define OCD_SIZE_DOUBLE_WORD_ACCESS	7
-
-/* Constants for BWC3A:BRW */
-#define OCD_BRW_READ_BREAK		0
-#define OCD_BRW_WRITE_BREAK		1
-#define OCD_BRW_ANY_ACCES_BREAK		2
-
-/* Constants for BWC3A:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for BWC3B:SIZE */
-#define OCD_SIZE_BYTE_ACCESS		4
-#define OCD_SIZE_HALFWORD_ACCESS	5
-#define OCD_SIZE_WORD_ACCESS		6
-#define OCD_SIZE_DOUBLE_WORD_ACCESS	7
-
-/* Constants for BWC3B:BRW */
-#define OCD_BRW_READ_BREAK		0
-#define OCD_BRW_WRITE_BREAK		1
-#define OCD_BRW_ANY_ACCES_BREAK		2
-
-/* Constants for BWC3B:BWE */
-#define OCD_BWE_DISABLED		0
-#define OCD_BWE_BREAKPOINT_ENABLED	1
-#define OCD_BWE_WATCHPOINT_ENABLED	3
-
-/* Constants for EPC0:RNG */
-#define OCD_RNG_DISABLED		0
-#define OCD_RNG_EXCLUSIVE		1
-#define OCD_RNG_INCLUSIVE		2
-
-/* Constants for EPC1:RNG */
-#define OCD_RNG_DISABLED		0
-#define OCD_RNG_EXCLUSIVE		1
-#define OCD_RNG_INCLUSIVE		2
-
-/* Constants for EPC2:RNG */
-#define OCD_RNG_DISABLED		0
-#define OCD_RNG_EXCLUSIVE		1
-#define OCD_RNG_INCLUSIVE		2
-
-/* Constants for EPC2:DB */
-#define OCD_DB_DISABLED			0
-#define OCD_DB_CHAINED_B		1
-#define OCD_DB_CHAINED_A		2
-#define OCD_DB_AHAINED_A_AND_B		3
-
-/* Constants for EPC3:RNG */
-#define OCD_RNG_DISABLED		0
-#define OCD_RNG_EXCLUSIVE		1
-#define OCD_RNG_INCLUSIVE		2
-
-#ifndef __ASSEMBLER__
-
-/* Register access macros */
-static inline unsigned long __ocd_read(unsigned int reg)
-{
-	return __builtin_mfdr(reg);
-}
-
-static inline void __ocd_write(unsigned int reg, unsigned long value)
-{
-	__builtin_mtdr(reg, value);
-}
-
-#define ocd_read(reg)			__ocd_read(OCD_##reg)
-#define ocd_write(reg, value)		__ocd_write(OCD_##reg, value)
-
-struct task_struct;
-
-void ocd_enable(struct task_struct *child);
-void ocd_disable(struct task_struct *child);
-
-#endif /* !__ASSEMBLER__ */
-
-#endif /* __ASM_AVR32_OCD_H */
diff --git a/arch/avr32/include/asm/page.h b/arch/avr32/include/asm/page.h
deleted file mode 100644
index c5d2a3e2c62f..000000000000
--- a/arch/avr32/include/asm/page.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PAGE_H
-#define __ASM_AVR32_PAGE_H
-
-#include <linux/const.h>
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	12
-#define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE-1))
-#define PTE_MASK	PAGE_MASK
-
-#ifndef __ASSEMBLY__
-
-#include <asm/addrspace.h>
-
-extern void clear_page(void *to);
-extern void copy_page(void *to, void *from);
-
-#define clear_user_page(page, vaddr, pg)	clear_page(page)
-#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
-
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { unsigned long pte; } pte_t;
-typedef struct { unsigned long pgd; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-typedef struct page *pgtable_t;
-
-#define pte_val(x)		((x).pte)
-#define pgd_val(x)		((x).pgd)
-#define pgprot_val(x)		((x).pgprot)
-
-#define __pte(x)		((pte_t) { (x) })
-#define __pgd(x)		((pgd_t) { (x) })
-#define __pgprot(x)		((pgprot_t) { (x) })
-
-/* FIXME: These should be removed soon */
-extern unsigned long memory_start, memory_end;
-
-/* Pure 2^n version of get_order */
-static inline int get_order(unsigned long size)
-{
-	unsigned lz;
-
-	size = (size - 1) >> PAGE_SHIFT;
-	asm("clz %0, %1" : "=r"(lz) : "r"(size));
-	return 32 - lz;
-}
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * The hardware maps the virtual addresses 0x80000000 -> 0x9fffffff
- * permanently to the physical addresses 0x00000000 -> 0x1fffffff when
- * segmentation is enabled. We want to make use of this in order to
- * minimize TLB pressure.
- */
-#define PAGE_OFFSET		(0x80000000UL)
-
-/*
- * ALSA uses virt_to_page() on DMA pages, which I'm not entirely sure
- * is a good idea. Anyway, we can't simply subtract PAGE_OFFSET here
- * in that case, so we'll have to mask out the three most significant
- * bits of the address instead...
- *
- * What's the difference between __pa() and virt_to_phys() anyway?
- */
-#define __pa(x)		PHYSADDR(x)
-#define __va(x)		((void *)(P1SEGADDR(x)))
-
-#define MAP_NR(addr)	(((unsigned long)(addr) - PAGE_OFFSET) >> PAGE_SHIFT)
-
-#define phys_to_page(phys)	(pfn_to_page(phys >> PAGE_SHIFT))
-#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
-
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-
-#define ARCH_PFN_OFFSET		(CONFIG_PHYS_OFFSET >> PAGE_SHIFT)
-
-#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr))
-#endif /* CONFIG_NEED_MULTIPLE_NODES */
-
-#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
-
-#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE |	\
-				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-/*
- * Memory above this physical address will be considered highmem.
- */
-#define HIGHMEM_START		0x20000000UL
-
-#include <asm-generic/memory_model.h>
-
-#endif /* __ASM_AVR32_PAGE_H */
diff --git a/arch/avr32/include/asm/pci.h b/arch/avr32/include/asm/pci.h
deleted file mode 100644
index 0f5f134b896a..000000000000
--- a/arch/avr32/include/asm/pci.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_AVR32_PCI_H__
-#define __ASM_AVR32_PCI_H__
-
-/* We don't support PCI yet, but some drivers require this file anyway */
-
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
-#endif /* __ASM_AVR32_PCI_H__ */
diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h
deleted file mode 100644
index db039cb368be..000000000000
--- a/arch/avr32/include/asm/pgalloc.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PGALLOC_H
-#define __ASM_AVR32_PGALLOC_H
-
-#include <linux/mm.h>
-#include <linux/quicklist.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-
-#define QUICK_PGD	0	/* Preserve kernel mappings over free */
-#define QUICK_PT	1	/* Zero on free */
-
-static inline void pmd_populate_kernel(struct mm_struct *mm,
-				       pmd_t *pmd, pte_t *pte)
-{
-	set_pmd(pmd, __pmd((unsigned long)pte));
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-				    pgtable_t pte)
-{
-	set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
-}
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-static inline void pgd_ctor(void *x)
-{
-	pgd_t *pgd = x;
-
-	memcpy(pgd + USER_PTRS_PER_PGD,
-		swapper_pg_dir + USER_PTRS_PER_PGD,
-		(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
-}
-
-/*
- * Allocate and free page tables
- */
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor);
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	quicklist_free(QUICK_PGD, NULL, pgd);
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-					  unsigned long address)
-{
-	return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
-					 unsigned long address)
-{
-	struct page *page;
-	void *pg;
-
-	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
-	if (!pg)
-		return NULL;
-
-	page = virt_to_page(pg);
-	if (!pgtable_page_ctor(page)) {
-		quicklist_free(QUICK_PT, NULL, pg);
-		return NULL;
-	}
-
-	return page;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	quicklist_free(QUICK_PT, NULL, pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	quicklist_free_page(QUICK_PT, NULL, pte);
-}
-
-#define __pte_free_tlb(tlb,pte,addr)			\
-do {							\
-	pgtable_page_dtor(pte);				\
-	tlb_remove_page((tlb), pte);			\
-} while (0)
-
-static inline void check_pgt_cache(void)
-{
-	quicklist_trim(QUICK_PGD, NULL, 25, 16);
-	quicklist_trim(QUICK_PT, NULL, 25, 16);
-}
-
-#endif /* __ASM_AVR32_PGALLOC_H */
diff --git a/arch/avr32/include/asm/pgtable-2level.h b/arch/avr32/include/asm/pgtable-2level.h
deleted file mode 100644
index 425dd567b5b9..000000000000
--- a/arch/avr32/include/asm/pgtable-2level.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PGTABLE_2LEVEL_H
-#define __ASM_AVR32_PGTABLE_2LEVEL_H
-
-#include <asm-generic/pgtable-nopmd.h>
-
-/*
- * Traditional 2-level paging structure
- */
-#define PGDIR_SHIFT	22
-#define PTRS_PER_PGD	1024
-
-#define PTRS_PER_PTE	1024
-
-#ifndef __ASSEMBLY__
-#define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
-#define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-
-/*
- * Certain architectures need to do special things when PTEs
- * within a page table are directly modified.  Thus, the following
- * hook is made available.
- */
-#define set_pte(pteptr, pteval) (*(pteptr) = pteval)
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep, pteval)
-
-/*
- * (pmds are folded into pgds so this doesn't get actually called,
- * but the define is needed for a generic inline function.)
- */
-#define set_pmd(pmdptr, pmdval) (*(pmdptr) = pmdval)
-
-#define pte_pfn(x)		((unsigned long)(((x).pte >> PAGE_SHIFT)))
-#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define pfn_pmd(pfn, prot)	__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_PGTABLE_2LEVEL_H */
diff --git a/arch/avr32/include/asm/pgtable.h b/arch/avr32/include/asm/pgtable.h
deleted file mode 100644
index 35800664076e..000000000000
--- a/arch/avr32/include/asm/pgtable.h
+++ /dev/null
@@ -1,347 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PGTABLE_H
-#define __ASM_AVR32_PGTABLE_H
-
-#include <asm/addrspace.h>
-
-#ifndef __ASSEMBLY__
-#include <linux/sched.h>
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Use two-level page tables just as the i386 (without PAE)
- */
-#include <asm/pgtable-2level.h>
-
-/*
- * The following code might need some cleanup when the values are
- * final...
- */
-#define PMD_SIZE	(1UL << PMD_SHIFT)
-#define PMD_MASK	(~(PMD_SIZE-1))
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK	(~(PGDIR_SIZE-1))
-
-#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
-#define FIRST_USER_ADDRESS	0UL
-
-#ifndef __ASSEMBLY__
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern void paging_init(void);
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used for
- * zero-mapped memory areas etc.
- */
-extern struct page *empty_zero_page;
-#define ZERO_PAGE(vaddr) (empty_zero_page)
-
-/*
- * Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8 MiB value just means that there will be a 8 MiB "hole"
- * after the uncached physical memory (P2 segment) until the vmalloc
- * area starts. That means that any out-of-bounds memory accesses will
- * hopefully be caught; we don't know if the end of the P1/P2 segments
- * are actually used for anything, but it is anyway safer to let the
- * MMU catch these kinds of errors than to rely on the memory bus.
- *
- * A "hole" of the same size is added to the end of the P3 segment as
- * well. It might seem wasteful to use 16 MiB of virtual address space
- * on this, but we do have 512 MiB of it...
- *
- * The vmalloc() routines leave a hole of 4 KiB between each vmalloced
- * area for the same reason.
- */
-#define VMALLOC_OFFSET	(8 * 1024 * 1024)
-#define VMALLOC_START	(P3SEG + VMALLOC_OFFSET)
-#define VMALLOC_END	(P4SEG - VMALLOC_OFFSET)
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Page flags. Some of these flags are not directly supported by
- * hardware, so we have to emulate them.
- */
-#define _TLBEHI_BIT_VALID	9
-#define _TLBEHI_VALID		(1 << _TLBEHI_BIT_VALID)
-
-#define _PAGE_BIT_WT		0  /* W-bit   : write-through */
-#define _PAGE_BIT_DIRTY		1  /* D-bit   : page changed */
-#define _PAGE_BIT_SZ0		2  /* SZ0-bit : Size of page */
-#define _PAGE_BIT_SZ1		3  /* SZ1-bit : Size of page */
-#define _PAGE_BIT_EXECUTE	4  /* X-bit   : execute access allowed */
-#define _PAGE_BIT_RW		5  /* AP0-bit : write access allowed */
-#define _PAGE_BIT_USER		6  /* AP1-bit : user space access allowed */
-#define _PAGE_BIT_BUFFER	7  /* B-bit   : bufferable */
-#define _PAGE_BIT_GLOBAL	8  /* G-bit   : global (ignore ASID) */
-#define _PAGE_BIT_CACHABLE	9  /* C-bit   : cachable */
-
-/* If we drop support for 1K pages, we get two extra bits */
-#define _PAGE_BIT_PRESENT	10
-#define _PAGE_BIT_ACCESSED	11 /* software: page was accessed */
-
-#define _PAGE_WT		(1 << _PAGE_BIT_WT)
-#define _PAGE_DIRTY		(1 << _PAGE_BIT_DIRTY)
-#define _PAGE_EXECUTE		(1 << _PAGE_BIT_EXECUTE)
-#define _PAGE_RW		(1 << _PAGE_BIT_RW)
-#define _PAGE_USER		(1 << _PAGE_BIT_USER)
-#define _PAGE_BUFFER		(1 << _PAGE_BIT_BUFFER)
-#define _PAGE_GLOBAL		(1 << _PAGE_BIT_GLOBAL)
-#define _PAGE_CACHABLE		(1 << _PAGE_BIT_CACHABLE)
-
-/* Software flags */
-#define _PAGE_ACCESSED		(1 << _PAGE_BIT_ACCESSED)
-#define _PAGE_PRESENT		(1 << _PAGE_BIT_PRESENT)
-
-/*
- * Page types, i.e. sizes. _PAGE_TYPE_NONE corresponds to what is
- * usually called _PAGE_PROTNONE on other architectures.
- *
- * XXX: Find out if _PAGE_PROTNONE is equivalent with !_PAGE_USER. If
- * so, we can encode all possible page sizes (although we can't really
- * support 1K pages anyway due to the _PAGE_PRESENT and _PAGE_ACCESSED
- * bits)
- *
- */
-#define _PAGE_TYPE_MASK		((1 << _PAGE_BIT_SZ0) | (1 << _PAGE_BIT_SZ1))
-#define _PAGE_TYPE_NONE		(0 << _PAGE_BIT_SZ0)
-#define _PAGE_TYPE_SMALL	(1 << _PAGE_BIT_SZ0)
-#define _PAGE_TYPE_MEDIUM	(2 << _PAGE_BIT_SZ0)
-#define _PAGE_TYPE_LARGE	(3 << _PAGE_BIT_SZ0)
-
-/*
- * Mask which drop software flags. We currently can't handle more than
- * 512 MiB of physical memory, so we can use bits 29-31 for other
- * stuff.  With a fixed 4K page size, we can use bits 10-11 as well as
- * bits 2-3 (SZ)
- */
-#define _PAGE_FLAGS_HARDWARE_MASK	0xfffff3ff
-
-#define _PAGE_FLAGS_CACHE_MASK	(_PAGE_CACHABLE | _PAGE_BUFFER | _PAGE_WT)
-
-/* Flags that may be modified by software */
-#define _PAGE_CHG_MASK		(PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY \
-				 | _PAGE_FLAGS_CACHE_MASK)
-
-#define _PAGE_FLAGS_READ	(_PAGE_CACHABLE	| _PAGE_BUFFER)
-#define _PAGE_FLAGS_WRITE	(_PAGE_FLAGS_READ | _PAGE_RW | _PAGE_DIRTY)
-
-#define _PAGE_NORMAL(x)	__pgprot((x) | _PAGE_PRESENT | _PAGE_TYPE_SMALL	\
-				 | _PAGE_ACCESSED)
-
-#define PAGE_NONE	(_PAGE_ACCESSED | _PAGE_TYPE_NONE)
-#define PAGE_READ	(_PAGE_FLAGS_READ | _PAGE_USER)
-#define PAGE_EXEC	(_PAGE_FLAGS_READ | _PAGE_EXECUTE | _PAGE_USER)
-#define PAGE_WRITE	(_PAGE_FLAGS_WRITE | _PAGE_USER)
-#define PAGE_KERNEL	_PAGE_NORMAL(_PAGE_FLAGS_WRITE | _PAGE_EXECUTE | _PAGE_GLOBAL)
-#define PAGE_KERNEL_RO	_PAGE_NORMAL(_PAGE_FLAGS_READ | _PAGE_EXECUTE | _PAGE_GLOBAL)
-
-#define _PAGE_P(x)	_PAGE_NORMAL((x) & ~(_PAGE_RW | _PAGE_DIRTY))
-#define _PAGE_S(x)	_PAGE_NORMAL(x)
-
-#define PAGE_COPY	_PAGE_P(PAGE_WRITE | PAGE_READ)
-#define PAGE_SHARED	_PAGE_S(PAGE_WRITE | PAGE_READ)
-
-#ifndef __ASSEMBLY__
-/*
- * The hardware supports flags for write- and execute access. Read is
- * always allowed if the page is loaded into the TLB, so the "-w-",
- * "--x" and "-wx" mappings are implemented as "rw-", "r-x" and "rwx",
- * respectively.
- *
- * The "---" case is handled by software; the page will simply not be
- * loaded into the TLB if the page type is _PAGE_TYPE_NONE.
- */
-
-#define __P000	__pgprot(PAGE_NONE)
-#define __P001	_PAGE_P(PAGE_READ)
-#define __P010	_PAGE_P(PAGE_WRITE)
-#define __P011	_PAGE_P(PAGE_WRITE | PAGE_READ)
-#define __P100	_PAGE_P(PAGE_EXEC)
-#define __P101	_PAGE_P(PAGE_EXEC | PAGE_READ)
-#define __P110	_PAGE_P(PAGE_EXEC | PAGE_WRITE)
-#define __P111	_PAGE_P(PAGE_EXEC | PAGE_WRITE | PAGE_READ)
-
-#define __S000	__pgprot(PAGE_NONE)
-#define __S001	_PAGE_S(PAGE_READ)
-#define __S010	_PAGE_S(PAGE_WRITE)
-#define __S011	_PAGE_S(PAGE_WRITE | PAGE_READ)
-#define __S100	_PAGE_S(PAGE_EXEC)
-#define __S101	_PAGE_S(PAGE_EXEC | PAGE_READ)
-#define __S110	_PAGE_S(PAGE_EXEC | PAGE_WRITE)
-#define __S111	_PAGE_S(PAGE_EXEC | PAGE_WRITE | PAGE_READ)
-
-#define pte_none(x)	(!pte_val(x))
-#define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
-
-#define pte_clear(mm,addr,xp)					\
-	do {							\
-		set_pte_at(mm, addr, xp, __pte(0));		\
-	} while (0)
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_write(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_RW;
-}
-static inline int pte_dirty(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_DIRTY;
-}
-static inline int pte_young(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_ACCESSED;
-}
-static inline int pte_special(pte_t pte)
-{
-	return 0;
-}
-
-/* Mutator functions for PTE bits */
-static inline pte_t pte_wrprotect(pte_t pte)
-{
-	set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW));
-	return pte;
-}
-static inline pte_t pte_mkclean(pte_t pte)
-{
-	set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY));
-	return pte;
-}
-static inline pte_t pte_mkold(pte_t pte)
-{
-	set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED));
-	return pte;
-}
-static inline pte_t pte_mkwrite(pte_t pte)
-{
-	set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW));
-	return pte;
-}
-static inline pte_t pte_mkdirty(pte_t pte)
-{
-	set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY));
-	return pte;
-}
-static inline pte_t pte_mkyoung(pte_t pte)
-{
-	set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED));
-	return pte;
-}
-static inline pte_t pte_mkspecial(pte_t pte)
-{
-	return pte;
-}
-
-#define pmd_none(x)	(!pmd_val(x))
-#define pmd_present(x)	(pmd_val(x))
-
-static inline void pmd_clear(pmd_t *pmdp)
-{
-	set_pmd(pmdp, __pmd(0));
-}
-
-#define	pmd_bad(x)	(pmd_val(x) & ~PAGE_MASK)
-
-/*
- * Permanent address of a page. We don't support highmem, so this is
- * trivial.
- */
-#define pages_to_mb(x)	((x) >> (20-PAGE_SHIFT))
-#define pte_page(x)	(pfn_to_page(pte_pfn(x)))
-
-/*
- * Mark the prot value as uncacheable and unbufferable
- */
-#define pgprot_noncached(prot)						\
-	__pgprot(pgprot_val(prot) & ~(_PAGE_BUFFER | _PAGE_CACHABLE))
-
-/*
- * Mark the prot value as uncacheable but bufferable
- */
-#define pgprot_writecombine(prot)					\
-	__pgprot((pgprot_val(prot) & ~_PAGE_CACHABLE) | _PAGE_BUFFER)
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * extern pte_t mk_pte(struct page *page, pgprot_t pgprot)
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
-	set_pte(&pte, __pte((pte_val(pte) & _PAGE_CHG_MASK)
-			    | pgprot_val(newprot)));
-	return pte;
-}
-
-#define page_pte(page)	page_pte_prot(page, __pgprot(0))
-
-#define pmd_page_vaddr(pmd)	pmd_val(pmd)
-#define pmd_page(pmd)		(virt_to_page(pmd_val(pmd)))
-
-/* to find an entry in a page-table-directory. */
-#define pgd_index(address)	(((address) >> PGDIR_SHIFT)	\
-				 & (PTRS_PER_PGD - 1))
-#define pgd_offset(mm, address)	((mm)->pgd + pgd_index(address))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(address)	pgd_offset(&init_mm, address)
-
-/* Find an entry in the third-level page table.. */
-#define pte_index(address)				\
-	((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset(dir, address)					\
-	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
-#define pte_offset_kernel(dir, address)					\
-	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
-#define pte_offset_map(dir, address) pte_offset_kernel(dir, address)
-#define pte_unmap(pte)		do { } while (0)
-
-struct vm_area_struct;
-extern void update_mmu_cache(struct vm_area_struct * vma,
-			     unsigned long address, pte_t *ptep);
-
-/*
- * Encode and decode a swap entry
- *
- * Constraints:
- *   _PAGE_TYPE_* at bits 2-3 (for emulating _PAGE_PROTNONE)
- *   _PAGE_PRESENT at bit 10
- *
- * We encode the type into bits 4-9 and offset into bits 11-31. This
- * gives us a 21 bits offset, or 2**21 * 4K = 8G usable swap space per
- * device, and 64 possible types.
- *
- * NOTE: We should set ZEROs at the position of _PAGE_PRESENT
- *       and _PAGE_PROTNONE bits
- */
-#define __swp_type(x)		(((x).val >> 4) & 0x3f)
-#define __swp_offset(x)		((x).val >> 11)
-#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 4) | ((offset) << 11) })
-#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
-
-typedef pte_t *pte_addr_t;
-
-#define kern_addr_valid(addr)	(1)
-
-/* No page table caches to initialize (?) */
-#define pgtable_cache_init()	do { } while(0)
-
-#include <asm-generic/pgtable.h>
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_PGTABLE_H */
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
deleted file mode 100644
index 972adcc1e8f4..000000000000
--- a/arch/avr32/include/asm/processor.h
+++ /dev/null
@@ -1,166 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PROCESSOR_H
-#define __ASM_AVR32_PROCESSOR_H
-
-#include <asm/page.h>
-#include <asm/cache.h>
-
-#define TASK_SIZE	0x80000000
-
-#ifdef __KERNEL__
-#define STACK_TOP	TASK_SIZE
-#define STACK_TOP_MAX	STACK_TOP
-#endif
-
-#ifndef __ASSEMBLY__
-
-static inline void *current_text_addr(void)
-{
-	register void *pc asm("pc");
-	return pc;
-}
-
-enum arch_type {
-	ARCH_AVR32A,
-	ARCH_AVR32B,
-	ARCH_MAX
-};
-
-enum cpu_type {
-	CPU_MORGAN,
-	CPU_AT32AP,
-	CPU_MAX
-};
-
-enum tlb_config {
-	TLB_NONE,
-	TLB_SPLIT,
-	TLB_UNIFIED,
-	TLB_INVALID
-};
-
-#define AVR32_FEATURE_RMW	(1 << 0)
-#define AVR32_FEATURE_DSP	(1 << 1)
-#define AVR32_FEATURE_SIMD	(1 << 2)
-#define AVR32_FEATURE_OCD	(1 << 3)
-#define AVR32_FEATURE_PCTR	(1 << 4)
-#define AVR32_FEATURE_JAVA	(1 << 5)
-#define AVR32_FEATURE_FPU	(1 << 6)
-
-struct avr32_cpuinfo {
-	struct clk *clk;
-	unsigned long loops_per_jiffy;
-	enum arch_type arch_type;
-	enum cpu_type cpu_type;
-	unsigned short arch_revision;
-	unsigned short cpu_revision;
-	enum tlb_config tlb_config;
-	unsigned long features;
-	u32 device_id;
-
-	struct cache_info icache;
-	struct cache_info dcache;
-};
-
-static inline unsigned int avr32_get_manufacturer_id(struct avr32_cpuinfo *cpu)
-{
-	return (cpu->device_id >> 1) & 0x7f;
-}
-static inline unsigned int avr32_get_product_number(struct avr32_cpuinfo *cpu)
-{
-	return (cpu->device_id >> 12) & 0xffff;
-}
-static inline unsigned int avr32_get_chip_revision(struct avr32_cpuinfo *cpu)
-{
-	return (cpu->device_id >> 28) & 0x0f;
-}
-
-extern struct avr32_cpuinfo boot_cpu_data;
-
-/* No SMP support so far */
-#define current_cpu_data boot_cpu_data
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's
- */
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
-
-#define cpu_relax()		barrier()
-#define cpu_sync_pipeline()	asm volatile("sub pc, -2" : : : "memory")
-
-struct cpu_context {
-	unsigned long sr;
-	unsigned long pc;
-	unsigned long ksp;	/* Kernel stack pointer */
-	unsigned long r7;
-	unsigned long r6;
-	unsigned long r5;
-	unsigned long r4;
-	unsigned long r3;
-	unsigned long r2;
-	unsigned long r1;
-	unsigned long r0;
-};
-
-/* This struct contains the CPU context as stored by switch_to() */
-struct thread_struct {
-	struct cpu_context cpu_context;
-	unsigned long single_step_addr;
-	u16 single_step_insn;
-};
-
-#define INIT_THREAD {						\
-	.cpu_context = {					\
-		.ksp = sizeof(init_stack) + (long)&init_stack,	\
-	},							\
-}
-
-/*
- * Do necessary setup to start up a newly executed thread.
- */
-#define start_thread(regs, new_pc, new_sp)	 \
-	do {					 \
-		memset(regs, 0, sizeof(*regs));	 \
-		regs->sr = MODE_USER;		 \
-		regs->pc = new_pc & ~1;		 \
-		regs->sp = new_sp;		 \
-	} while(0)
-
-struct task_struct;
-
-/* Free all resources held by a thread */
-extern void release_thread(struct task_struct *);
-
-/* Return saved PC of a blocked thread */
-#define thread_saved_pc(tsk)    ((tsk)->thread.cpu_context.pc)
-
-struct pt_regs;
-extern unsigned long get_wchan(struct task_struct *p);
-extern void show_regs_log_lvl(struct pt_regs *regs, const char *log_lvl);
-extern void show_stack_log_lvl(struct task_struct *tsk, unsigned long sp,
-			       struct pt_regs *regs, const char *log_lvl);
-
-#define task_pt_regs(p) \
-	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
-
-#define KSTK_EIP(tsk)	((tsk)->thread.cpu_context.pc)
-#define KSTK_ESP(tsk)	((tsk)->thread.cpu_context.ksp)
-
-#define ARCH_HAS_PREFETCH
-
-static inline void prefetch(const void *x)
-{
-	const char *c = x;
-	asm volatile("pref %0" : : "r"(c));
-}
-#define PREFETCH_STRIDE	L1_CACHE_BYTES
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_PROCESSOR_H */
diff --git a/arch/avr32/include/asm/ptrace.h b/arch/avr32/include/asm/ptrace.h
deleted file mode 100644
index 630e4f9bf5f0..000000000000
--- a/arch/avr32/include/asm/ptrace.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PTRACE_H
-#define __ASM_AVR32_PTRACE_H
-
-#include <uapi/asm/ptrace.h>
-
-#ifndef __ASSEMBLY__
-
-#include <asm/ocd.h>
-
-#define arch_has_single_step()		(1)
-
-#define arch_ptrace_attach(child)       ocd_enable(child)
-
-#define user_mode(regs)                 (((regs)->sr & MODE_MASK) == MODE_USER)
-#define instruction_pointer(regs)       ((regs)->pc)
-#define profile_pc(regs)                instruction_pointer(regs)
-#define user_stack_pointer(regs)	((regs)->sp)
-
-static __inline__ int valid_user_regs(struct pt_regs *regs)
-{
-	/*
-	 * Some of the Java bits might be acceptable if/when we
-	 * implement some support for that stuff...
-	 */
-	if ((regs->sr & 0xffff0000) == 0)
-		return 1;
-
-	/*
-	 * Force status register flags to be sane and report this
-	 * illegal behaviour...
-	 */
-	regs->sr &= 0x0000ffff;
-	return 0;
-}
-
-
-#endif /* ! __ASSEMBLY__ */
-#endif /* __ASM_AVR32_PTRACE_H */
diff --git a/arch/avr32/include/asm/serial.h b/arch/avr32/include/asm/serial.h
deleted file mode 100644
index 5ecaebc22b02..000000000000
--- a/arch/avr32/include/asm/serial.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _ASM_SERIAL_H
-#define _ASM_SERIAL_H
-
-/*
- * This assumes you have a 1.8432 MHz clock for your UART.
- *
- * It'd be nice if someone built a serial card with a 24.576 MHz
- * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
- */
-#define BASE_BAUD (1843200 / 16)
-
-#endif /* _ASM_SERIAL_H */
diff --git a/arch/avr32/include/asm/setup.h b/arch/avr32/include/asm/setup.h
deleted file mode 100644
index 73490ae0c476..000000000000
--- a/arch/avr32/include/asm/setup.h
+++ /dev/null
@@ -1,144 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/include/asm-arm/setup.h
- *   Copyright (C) 1997-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SETUP_H__
-#define __ASM_AVR32_SETUP_H__
-
-#include <uapi/asm/setup.h>
-
-
-/* Magic number indicating that a tag table is present */
-#define ATAG_MAGIC	0xa2a25441
-
-#ifndef __ASSEMBLY__
-
-/*
- * Generic memory range, used by several tags.
- *
- *   addr is always physical.
- *   size is measured in bytes.
- *   next is for use by the OS, e.g. for grouping regions into
- *        linked lists.
- */
-struct tag_mem_range {
-	u32			addr;
-	u32			size;
-	struct tag_mem_range *	next;
-};
-
-/* The list ends with an ATAG_NONE node. */
-#define ATAG_NONE	0x00000000
-
-struct tag_header {
-	u32 size;
-	u32 tag;
-};
-
-/* The list must start with an ATAG_CORE node */
-#define ATAG_CORE	0x54410001
-
-struct tag_core {
-	u32 flags;
-	u32 pagesize;
-	u32 rootdev;
-};
-
-/* it is allowed to have multiple ATAG_MEM nodes */
-#define ATAG_MEM	0x54410002
-/* ATAG_MEM uses tag_mem_range */
-
-/* command line: \0 terminated string */
-#define ATAG_CMDLINE	0x54410003
-
-struct tag_cmdline {
-	char	cmdline[1];	/* this is the minimum size */
-};
-
-/* Ramdisk image (may be compressed) */
-#define ATAG_RDIMG	0x54410004
-/* ATAG_RDIMG uses tag_mem_range */
-
-/* Information about various clocks present in the system */
-#define ATAG_CLOCK	0x54410005
-
-struct tag_clock {
-	u32	clock_id;	/* Which clock are we talking about? */
-	u32	clock_flags;	/* Special features */
-	u64	clock_hz;	/* Clock speed in Hz */
-};
-
-/* The clock types we know about */
-#define CLOCK_BOOTCPU	0
-
-/* Memory reserved for the system (e.g. the bootloader) */
-#define ATAG_RSVD_MEM	0x54410006
-/* ATAG_RSVD_MEM uses tag_mem_range */
-
-/* Ethernet information */
-
-#define ATAG_ETHERNET	0x54410007
-
-struct tag_ethernet {
-	u8	mac_index;
-	u8	mii_phy_addr;
-	u8	hw_address[6];
-};
-
-#define ETH_INVALID_PHY	0xff
-
-/* board information */
-#define ATAG_BOARDINFO	0x54410008
-
-struct tag_boardinfo {
-	u32	board_number;
-};
-
-struct tag {
-	struct tag_header hdr;
-	union {
-		struct tag_core core;
-		struct tag_mem_range mem_range;
-		struct tag_cmdline cmdline;
-		struct tag_clock clock;
-		struct tag_ethernet ethernet;
-		struct tag_boardinfo boardinfo;
-	} u;
-};
-
-struct tagtable {
-	u32	tag;
-	int	(*parse)(struct tag *);
-};
-
-#define __tag __used __attribute__((__section__(".taglist.init")))
-#define __tagtable(tag, fn)						\
-	static struct tagtable __tagtable_##fn __tag = { tag, fn }
-
-#define tag_member_present(tag,member)					\
-	((unsigned long)(&((struct tag *)0L)->member + 1)		\
-	 <= (tag)->hdr.size * 4)
-
-#define tag_next(t)	((struct tag *)((u32 *)(t) + (t)->hdr.size))
-#define tag_size(type)	((sizeof(struct tag_header) + sizeof(struct type)) >> 2)
-
-#define for_each_tag(t,base)						\
-	for (t = base; t->hdr.size; t = tag_next(t))
-
-extern struct tag *bootloader_tags;
-
-extern resource_size_t fbmem_start;
-extern resource_size_t fbmem_size;
-extern u32 board_number;
-
-void setup_processor(void);
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_SETUP_H__ */
diff --git a/arch/avr32/include/asm/shmparam.h b/arch/avr32/include/asm/shmparam.h
deleted file mode 100644
index 3681266c77f7..000000000000
--- a/arch/avr32/include/asm/shmparam.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_SHMPARAM_H
-#define __ASM_AVR32_SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE	/* attach addr a multiple of this */
-
-#endif /* __ASM_AVR32_SHMPARAM_H */
diff --git a/arch/avr32/include/asm/signal.h b/arch/avr32/include/asm/signal.h
deleted file mode 100644
index d875eb6a3f3c..000000000000
--- a/arch/avr32/include/asm/signal.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SIGNAL_H
-#define __ASM_AVR32_SIGNAL_H
-
-#include <uapi/asm/signal.h>
-
-/* Most things should be clean enough to redefine this at will, if care
-   is taken to make libc match.  */
-
-#define _NSIG		64
-#define _NSIG_BPW	32
-#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
-
-typedef unsigned long old_sigset_t;		/* at least 32 bits */
-
-typedef struct {
-	unsigned long sig[_NSIG_WORDS];
-} sigset_t;
-
-#define __ARCH_HAS_SA_RESTORER
-
-#include <asm/sigcontext.h>
-#undef __HAVE_ARCH_SIG_BITOPS
-
-#endif
diff --git a/arch/avr32/include/asm/string.h b/arch/avr32/include/asm/string.h
deleted file mode 100644
index c91a623cd585..000000000000
--- a/arch/avr32/include/asm/string.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_STRING_H
-#define __ASM_AVR32_STRING_H
-
-#define __HAVE_ARCH_MEMSET
-extern void *memset(void *b, int c, size_t len);
-
-#define __HAVE_ARCH_MEMCPY
-extern void *memcpy(void *to, const void *from, size_t len);
-
-#endif /* __ASM_AVR32_STRING_H */
diff --git a/arch/avr32/include/asm/switch_to.h b/arch/avr32/include/asm/switch_to.h
deleted file mode 100644
index 6f00581c3d4f..000000000000
--- a/arch/avr32/include/asm/switch_to.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SWITCH_TO_H
-#define __ASM_AVR32_SWITCH_TO_H
-
-/*
- * Help PathFinder and other Nexus-compliant debuggers keep track of
- * the current PID by emitting an Ownership Trace Message each time we
- * switch task.
- */
-#ifdef CONFIG_OWNERSHIP_TRACE
-#include <asm/ocd.h>
-#define ocd_switch(prev, next)				\
-	do {						\
-		ocd_write(PID, prev->pid);		\
-		ocd_write(PID, next->pid);		\
-	} while(0)
-#else
-#define ocd_switch(prev, next)
-#endif
-
-/*
- * switch_to(prev, next, last) should switch from task `prev' to task
- * `next'. `prev' will never be the same as `next'.
- *
- * We just delegate everything to the __switch_to assembly function,
- * which is implemented in arch/avr32/kernel/switch_to.S
- *
- * mb() tells GCC not to cache `current' across this call.
- */
-struct cpu_context;
-struct task_struct;
-extern struct task_struct *__switch_to(struct task_struct *,
-				       struct cpu_context *,
-				       struct cpu_context *);
-#define switch_to(prev, next, last)					\
-	do {								\
-		ocd_switch(prev, next);					\
-		last = __switch_to(prev, &prev->thread.cpu_context + 1,	\
-				   &next->thread.cpu_context);		\
-	} while (0)
-
-
-#endif /* __ASM_AVR32_SWITCH_TO_H */
diff --git a/arch/avr32/include/asm/syscalls.h b/arch/avr32/include/asm/syscalls.h
deleted file mode 100644
index 244f2acab546..000000000000
--- a/arch/avr32/include/asm/syscalls.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * syscalls.h - Linux syscall interfaces (arch-specific)
- *
- * Copyright (c) 2008 Jaswinder Singh
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#ifndef _ASM_AVR32_SYSCALLS_H
-#define _ASM_AVR32_SYSCALLS_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/types.h>
-#include <linux/signal.h>
-
-/* mm/cache.c */
-asmlinkage int sys_cacheflush(int, void __user *, size_t);
-
-#endif /* _ASM_AVR32_SYSCALLS_H */
diff --git a/arch/avr32/include/asm/sysreg.h b/arch/avr32/include/asm/sysreg.h
deleted file mode 100644
index d4e0950170ca..000000000000
--- a/arch/avr32/include/asm/sysreg.h
+++ /dev/null
@@ -1,291 +0,0 @@
-/*
- * AVR32 System Registers
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SYSREG_H
-#define __ASM_AVR32_SYSREG_H
-
-/* sysreg register offsets */
-#define SYSREG_SR				0x0000
-#define SYSREG_EVBA				0x0004
-#define SYSREG_ACBA				0x0008
-#define SYSREG_CPUCR				0x000c
-#define SYSREG_ECR				0x0010
-#define SYSREG_RSR_SUP				0x0014
-#define SYSREG_RSR_INT0				0x0018
-#define SYSREG_RSR_INT1				0x001c
-#define SYSREG_RSR_INT2				0x0020
-#define SYSREG_RSR_INT3				0x0024
-#define SYSREG_RSR_EX				0x0028
-#define SYSREG_RSR_NMI				0x002c
-#define SYSREG_RSR_DBG				0x0030
-#define SYSREG_RAR_SUP				0x0034
-#define SYSREG_RAR_INT0				0x0038
-#define SYSREG_RAR_INT1				0x003c
-#define SYSREG_RAR_INT2				0x0040
-#define SYSREG_RAR_INT3				0x0044
-#define SYSREG_RAR_EX				0x0048
-#define SYSREG_RAR_NMI				0x004c
-#define SYSREG_RAR_DBG				0x0050
-#define SYSREG_JECR				0x0054
-#define SYSREG_JOSP				0x0058
-#define SYSREG_JAVA_LV0				0x005c
-#define SYSREG_JAVA_LV1				0x0060
-#define SYSREG_JAVA_LV2				0x0064
-#define SYSREG_JAVA_LV3				0x0068
-#define SYSREG_JAVA_LV4				0x006c
-#define SYSREG_JAVA_LV5				0x0070
-#define SYSREG_JAVA_LV6				0x0074
-#define SYSREG_JAVA_LV7				0x0078
-#define SYSREG_JTBA				0x007c
-#define SYSREG_JBCR				0x0080
-#define SYSREG_CONFIG0				0x0100
-#define SYSREG_CONFIG1				0x0104
-#define SYSREG_COUNT				0x0108
-#define SYSREG_COMPARE				0x010c
-#define SYSREG_TLBEHI				0x0110
-#define SYSREG_TLBELO				0x0114
-#define SYSREG_PTBR				0x0118
-#define SYSREG_TLBEAR				0x011c
-#define SYSREG_MMUCR				0x0120
-#define SYSREG_TLBARLO				0x0124
-#define SYSREG_TLBARHI				0x0128
-#define SYSREG_PCCNT				0x012c
-#define SYSREG_PCNT0				0x0130
-#define SYSREG_PCNT1				0x0134
-#define SYSREG_PCCR				0x0138
-#define SYSREG_BEAR				0x013c
-#define SYSREG_SABAL				0x0300
-#define SYSREG_SABAH				0x0304
-#define SYSREG_SABD				0x0308
-
-/* Bitfields in SR */
-#define SYSREG_SR_C_OFFSET			0
-#define SYSREG_SR_C_SIZE			1
-#define SYSREG_Z_OFFSET				1
-#define SYSREG_Z_SIZE				1
-#define SYSREG_SR_N_OFFSET			2
-#define SYSREG_SR_N_SIZE			1
-#define SYSREG_SR_V_OFFSET			3
-#define SYSREG_SR_V_SIZE			1
-#define SYSREG_Q_OFFSET				4
-#define SYSREG_Q_SIZE				1
-#define SYSREG_L_OFFSET				5
-#define SYSREG_L_SIZE				1
-#define SYSREG_T_OFFSET				14
-#define SYSREG_T_SIZE				1
-#define SYSREG_SR_R_OFFSET			15
-#define SYSREG_SR_R_SIZE			1
-#define SYSREG_GM_OFFSET			16
-#define SYSREG_GM_SIZE				1
-#define SYSREG_I0M_OFFSET			17
-#define SYSREG_I0M_SIZE				1
-#define SYSREG_I1M_OFFSET			18
-#define SYSREG_I1M_SIZE				1
-#define SYSREG_I2M_OFFSET			19
-#define SYSREG_I2M_SIZE				1
-#define SYSREG_I3M_OFFSET			20
-#define SYSREG_I3M_SIZE				1
-#define SYSREG_EM_OFFSET			21
-#define SYSREG_EM_SIZE				1
-#define SYSREG_MODE_OFFSET			22
-#define SYSREG_MODE_SIZE			3
-#define SYSREG_M0_OFFSET			22
-#define SYSREG_M0_SIZE				1
-#define SYSREG_M1_OFFSET			23
-#define SYSREG_M1_SIZE				1
-#define SYSREG_M2_OFFSET			24
-#define SYSREG_M2_SIZE				1
-#define SYSREG_SR_D_OFFSET			26
-#define SYSREG_SR_D_SIZE			1
-#define SYSREG_DM_OFFSET			27
-#define SYSREG_DM_SIZE				1
-#define SYSREG_SR_J_OFFSET			28
-#define SYSREG_SR_J_SIZE			1
-#define SYSREG_H_OFFSET				29
-#define SYSREG_H_SIZE				1
-
-/* Bitfields in CPUCR */
-#define SYSREG_BI_OFFSET			0
-#define SYSREG_BI_SIZE				1
-#define SYSREG_BE_OFFSET			1
-#define SYSREG_BE_SIZE				1
-#define SYSREG_FE_OFFSET			2
-#define SYSREG_FE_SIZE				1
-#define SYSREG_RE_OFFSET			3
-#define SYSREG_RE_SIZE				1
-#define SYSREG_IBE_OFFSET			4
-#define SYSREG_IBE_SIZE				1
-#define SYSREG_IEE_OFFSET			5
-#define SYSREG_IEE_SIZE				1
-
-/* Bitfields in CONFIG0 */
-#define SYSREG_CONFIG0_R_OFFSET			0
-#define SYSREG_CONFIG0_R_SIZE			1
-#define SYSREG_CONFIG0_D_OFFSET			1
-#define SYSREG_CONFIG0_D_SIZE			1
-#define SYSREG_CONFIG0_S_OFFSET			2
-#define SYSREG_CONFIG0_S_SIZE			1
-#define SYSREG_CONFIG0_O_OFFSET			3
-#define SYSREG_CONFIG0_O_SIZE			1
-#define SYSREG_CONFIG0_P_OFFSET			4
-#define SYSREG_CONFIG0_P_SIZE			1
-#define SYSREG_CONFIG0_J_OFFSET			5
-#define SYSREG_CONFIG0_J_SIZE			1
-#define SYSREG_CONFIG0_F_OFFSET			6
-#define SYSREG_CONFIG0_F_SIZE			1
-#define SYSREG_MMUT_OFFSET			7
-#define SYSREG_MMUT_SIZE			3
-#define SYSREG_AR_OFFSET			10
-#define SYSREG_AR_SIZE				3
-#define SYSREG_AT_OFFSET			13
-#define SYSREG_AT_SIZE				3
-#define SYSREG_PROCESSORREVISION_OFFSET		16
-#define SYSREG_PROCESSORREVISION_SIZE		8
-#define SYSREG_PROCESSORID_OFFSET		24
-#define SYSREG_PROCESSORID_SIZE			8
-
-/* Bitfields in CONFIG1 */
-#define SYSREG_DASS_OFFSET			0
-#define SYSREG_DASS_SIZE			3
-#define SYSREG_DLSZ_OFFSET			3
-#define SYSREG_DLSZ_SIZE			3
-#define SYSREG_DSET_OFFSET			6
-#define SYSREG_DSET_SIZE			4
-#define SYSREG_IASS_OFFSET			10
-#define SYSREG_IASS_SIZE			3
-#define SYSREG_ILSZ_OFFSET			13
-#define SYSREG_ILSZ_SIZE			3
-#define SYSREG_ISET_OFFSET			16
-#define SYSREG_ISET_SIZE			4
-#define SYSREG_DMMUSZ_OFFSET			20
-#define SYSREG_DMMUSZ_SIZE			6
-#define SYSREG_IMMUSZ_OFFSET			26
-#define SYSREG_IMMUSZ_SIZE			6
-
-/* Bitfields in TLBEHI */
-#define SYSREG_ASID_OFFSET			0
-#define SYSREG_ASID_SIZE			8
-#define SYSREG_TLBEHI_I_OFFSET			8
-#define SYSREG_TLBEHI_I_SIZE			1
-#define SYSREG_TLBEHI_V_OFFSET			9
-#define SYSREG_TLBEHI_V_SIZE			1
-#define SYSREG_VPN_OFFSET			10
-#define SYSREG_VPN_SIZE				22
-
-/* Bitfields in TLBELO */
-#define SYSREG_W_OFFSET				0
-#define SYSREG_W_SIZE				1
-#define SYSREG_TLBELO_D_OFFSET			1
-#define SYSREG_TLBELO_D_SIZE			1
-#define SYSREG_SZ_OFFSET			2
-#define SYSREG_SZ_SIZE				2
-#define SYSREG_AP_OFFSET			4
-#define SYSREG_AP_SIZE				3
-#define SYSREG_B_OFFSET				7
-#define SYSREG_B_SIZE				1
-#define SYSREG_G_OFFSET				8
-#define SYSREG_G_SIZE				1
-#define SYSREG_TLBELO_C_OFFSET			9
-#define SYSREG_TLBELO_C_SIZE			1
-#define SYSREG_PFN_OFFSET			10
-#define SYSREG_PFN_SIZE				22
-
-/* Bitfields in MMUCR */
-#define SYSREG_E_OFFSET				0
-#define SYSREG_E_SIZE				1
-#define SYSREG_M_OFFSET				1
-#define SYSREG_M_SIZE				1
-#define SYSREG_MMUCR_I_OFFSET			2
-#define SYSREG_MMUCR_I_SIZE			1
-#define SYSREG_MMUCR_N_OFFSET			3
-#define SYSREG_MMUCR_N_SIZE			1
-#define SYSREG_MMUCR_S_OFFSET			4
-#define SYSREG_MMUCR_S_SIZE			1
-#define SYSREG_DLA_OFFSET			8
-#define SYSREG_DLA_SIZE				6
-#define SYSREG_DRP_OFFSET			14
-#define SYSREG_DRP_SIZE				6
-#define SYSREG_ILA_OFFSET			20
-#define SYSREG_ILA_SIZE				6
-#define SYSREG_IRP_OFFSET			26
-#define SYSREG_IRP_SIZE				6
-
-/* Bitfields in PCCR */
-#define SYSREG_PCCR_E_OFFSET			0
-#define SYSREG_PCCR_E_SIZE			1
-#define SYSREG_PCCR_R_OFFSET			1
-#define SYSREG_PCCR_R_SIZE			1
-#define SYSREG_PCCR_C_OFFSET			2
-#define SYSREG_PCCR_C_SIZE			1
-#define SYSREG_PCCR_S_OFFSET			3
-#define SYSREG_PCCR_S_SIZE			1
-#define SYSREG_IEC_OFFSET			4
-#define SYSREG_IEC_SIZE				1
-#define SYSREG_IE0_OFFSET			5
-#define SYSREG_IE0_SIZE				1
-#define SYSREG_IE1_OFFSET			6
-#define SYSREG_IE1_SIZE				1
-#define SYSREG_FC_OFFSET			8
-#define SYSREG_FC_SIZE				1
-#define SYSREG_F0_OFFSET			9
-#define SYSREG_F0_SIZE				1
-#define SYSREG_F1_OFFSET			10
-#define SYSREG_F1_SIZE				1
-#define SYSREG_CONF0_OFFSET			12
-#define SYSREG_CONF0_SIZE			6
-#define SYSREG_CONF1_OFFSET			18
-#define SYSREG_CONF1_SIZE			6
-
-/* Constants for ECR */
-#define ECR_UNRECOVERABLE			0
-#define ECR_TLB_MULTIPLE			1
-#define ECR_BUS_ERROR_WRITE			2
-#define ECR_BUS_ERROR_READ			3
-#define ECR_NMI					4
-#define ECR_ADDR_ALIGN_X			5
-#define ECR_PROTECTION_X			6
-#define ECR_DEBUG				7
-#define ECR_ILLEGAL_OPCODE			8
-#define ECR_UNIMPL_INSTRUCTION			9
-#define ECR_PRIVILEGE_VIOLATION			10
-#define ECR_FPE					11
-#define ECR_COPROC_ABSENT			12
-#define ECR_ADDR_ALIGN_R			13
-#define ECR_ADDR_ALIGN_W			14
-#define ECR_PROTECTION_R			15
-#define ECR_PROTECTION_W			16
-#define ECR_DTLB_MODIFIED			17
-#define ECR_TLB_MISS_X				20
-#define ECR_TLB_MISS_R				24
-#define ECR_TLB_MISS_W				28
-
-/* Bit manipulation macros */
-#define SYSREG_BIT(name)				\
-	(1 << SYSREG_##name##_OFFSET)
-#define SYSREG_BF(name,value)				\
-	(((value) & ((1 << SYSREG_##name##_SIZE) - 1))	\
-	 << SYSREG_##name##_OFFSET)
-#define SYSREG_BFEXT(name,value)\
-	(((value) >> SYSREG_##name##_OFFSET)		\
-	 & ((1 << SYSREG_##name##_SIZE) - 1))
-#define SYSREG_BFINS(name,value,old)			\
-	(((old) & ~(((1 << SYSREG_##name##_SIZE) - 1)	\
-		    << SYSREG_##name##_OFFSET))		\
-	 | SYSREG_BF(name,value))
-
-/* Register access macros */
-#ifdef __CHECKER__
-extern unsigned long __builtin_mfsr(unsigned long reg);
-extern void __builtin_mtsr(unsigned long reg, unsigned long value);
-#endif
-
-#define sysreg_read(reg)		__builtin_mfsr(SYSREG_##reg)
-#define sysreg_write(reg, value)	__builtin_mtsr(SYSREG_##reg, value)
-
-#endif /* __ASM_AVR32_SYSREG_H */
diff --git a/arch/avr32/include/asm/termios.h b/arch/avr32/include/asm/termios.h
deleted file mode 100644
index 9d594376dbd6..000000000000
--- a/arch/avr32/include/asm/termios.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TERMIOS_H
-#define __ASM_AVR32_TERMIOS_H
-
-#include <uapi/asm/termios.h>
-
-/*	intr=^C		quit=^\		erase=del	kill=^U
-	eof=^D		vtime=\0	vmin=\1		sxtc=\0
-	start=^Q	stop=^S		susp=^Z		eol=\0
-	reprint=^R	discard=^U	werase=^W	lnext=^V
-	eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-#include <asm-generic/termios-base.h>
-
-#endif	/* __ASM_AVR32_TERMIOS_H */
diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h
deleted file mode 100644
index d4d3079541ea..000000000000
--- a/arch/avr32/include/asm/thread_info.h
+++ /dev/null
@@ -1,103 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_THREAD_INFO_H
-#define __ASM_AVR32_THREAD_INFO_H
-
-#include <asm/page.h>
-
-#define THREAD_SIZE_ORDER	1
-#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
-
-#ifndef __ASSEMBLY__
-#include <asm/types.h>
-
-struct task_struct;
-
-struct thread_info {
-	struct task_struct	*task;		/* main task structure */
-	unsigned long		flags;		/* low level flags */
-	__u32			cpu;
-	__s32			preempt_count;	/* 0 => preemptable, <0 => BUG */
-	__u32			rar_saved;	/* return address... */
-	__u32			rsr_saved;	/* ...and status register
-						   saved by debug handler
-						   when setting up
-						   trampoline */
-	__u8			supervisor_stack[0];
-};
-
-#define INIT_THREAD_INFO(tsk)						\
-{									\
-	.task		= &tsk,						\
-	.flags		= 0,						\
-	.cpu		= 0,						\
-	.preempt_count	= INIT_PREEMPT_COUNT,				\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-/*
- * Get the thread information struct from C.
- * We do the usual trick and use the lower end of the stack for this
- */
-static inline struct thread_info *current_thread_info(void)
-{
-	unsigned long addr = ~(THREAD_SIZE - 1);
-
-	asm("and %0, sp" : "=r"(addr) : "0"(addr));
-	return (struct thread_info *)addr;
-}
-
-#define get_thread_info(ti) get_task_struct((ti)->task)
-#define put_thread_info(ti) put_task_struct((ti)->task)
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Thread information flags
- * - these are process state flags that various assembly files may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- */
-#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
-#define TIF_SIGPENDING          1       /* signal pending */
-#define TIF_NEED_RESCHED        2       /* rescheduling necessary */
-#define TIF_BREAKPOINT		4	/* enter monitor mode on return */
-#define TIF_SINGLE_STEP		5	/* single step in progress */
-#define TIF_MEMDIE		6	/* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK	7	/* restore signal mask in do_signal */
-#define TIF_CPU_GOING_TO_SLEEP	8	/* CPU is entering sleep 0 mode */
-#define TIF_NOTIFY_RESUME	9	/* callback before returning to user */
-#define TIF_DEBUG		30	/* debugging enabled */
-#define TIF_USERSPACE		31      /* true if FS sets userspace */
-
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_BREAKPOINT		(1 << TIF_BREAKPOINT)
-#define _TIF_SINGLE_STEP	(1 << TIF_SINGLE_STEP)
-#define _TIF_MEMDIE		(1 << TIF_MEMDIE)
-#define _TIF_CPU_GOING_TO_SLEEP (1 << TIF_CPU_GOING_TO_SLEEP)
-#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
-
-/* Note: The masks below must never span more than 16 bits! */
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK				\
-	(_TIF_SIGPENDING			\
-	 | _TIF_NOTIFY_RESUME			\
-	 | _TIF_NEED_RESCHED			\
-	 | _TIF_BREAKPOINT)
-
-/* work to do on any return to userspace */
-#define _TIF_ALLWORK_MASK	(_TIF_WORK_MASK | _TIF_SYSCALL_TRACE)
-/* work to do on return from debug mode */
-#define _TIF_DBGWORK_MASK	(_TIF_WORK_MASK & ~_TIF_BREAKPOINT)
-
-#endif /* __ASM_AVR32_THREAD_INFO_H */
diff --git a/arch/avr32/include/asm/timex.h b/arch/avr32/include/asm/timex.h
deleted file mode 100644
index 187dcf38b210..000000000000
--- a/arch/avr32/include/asm/timex.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TIMEX_H
-#define __ASM_AVR32_TIMEX_H
-
-/*
- * This is the frequency of the timer used for Linux's timer interrupt.
- * The value should be defined as accurate as possible or under certain
- * circumstances Linux timekeeping might become inaccurate or fail.
- *
- * For many system the exact clockrate of the timer isn't known but due to
- * the way this value is used we can get away with a wrong value as long
- * as this value is:
- *
- *  - a multiple of HZ
- *  - a divisor of the actual rate
- *
- * 500000 is a good such cheat value.
- *
- * The obscure number 1193182 is the same as used by the original i8254
- * time in legacy PC hardware; the chip is never found in AVR32 systems.
- */
-#define CLOCK_TICK_RATE		500000	/* Underlying HZ */
-
-typedef unsigned long cycles_t;
-
-static inline cycles_t get_cycles (void)
-{
-	return 0;
-}
-
-#define ARCH_HAS_READ_CURRENT_TIMER
-
-#endif /* __ASM_AVR32_TIMEX_H */
diff --git a/arch/avr32/include/asm/tlb.h b/arch/avr32/include/asm/tlb.h
deleted file mode 100644
index 5c55f9ce7c7d..000000000000
--- a/arch/avr32/include/asm/tlb.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TLB_H
-#define __ASM_AVR32_TLB_H
-
-#define tlb_start_vma(tlb, vma) \
-	flush_cache_range(vma, vma->vm_start, vma->vm_end)
-
-#define tlb_end_vma(tlb, vma) \
-	flush_tlb_range(vma, vma->vm_start, vma->vm_end)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while(0)
-
-/*
- * Flush whole TLB for MM
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-#include <asm-generic/tlb.h>
-
-/*
- * For debugging purposes
- */
-extern void show_dtlb_entry(unsigned int index);
-extern void dump_dtlb(void);
-
-#endif /* __ASM_AVR32_TLB_H */
diff --git a/arch/avr32/include/asm/tlbflush.h b/arch/avr32/include/asm/tlbflush.h
deleted file mode 100644
index bf90a786f6be..000000000000
--- a/arch/avr32/include/asm/tlbflush.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TLBFLUSH_H
-#define __ASM_AVR32_TLBFLUSH_H
-
-#include <asm/mmu.h>
-
-/*
- * TLB flushing:
- *
- *  - flush_tlb() flushes the current mm struct TLBs
- *  - flush_tlb_all() flushes all processes' TLB entries
- *  - flush_tlb_mm(mm) flushes the specified mm context TLBs
- *  - flush_tlb_page(vma, vmaddr) flushes one page
- *  - flush_tlb_range(vma, start, end) flushes a range of pages
- *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
- */
-extern void flush_tlb(void);
-extern void flush_tlb_all(void);
-extern void flush_tlb_mm(struct mm_struct *mm);
-extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
-			    unsigned long end);
-extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
-
-extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
-
-#endif /* __ASM_AVR32_TLBFLUSH_H */
diff --git a/arch/avr32/include/asm/traps.h b/arch/avr32/include/asm/traps.h
deleted file mode 100644
index 6a8fb944f414..000000000000
--- a/arch/avr32/include/asm/traps.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TRAPS_H
-#define __ASM_AVR32_TRAPS_H
-
-#include <linux/list.h>
-
-struct undef_hook {
-	struct list_head node;
-	u32 insn_mask;
-	u32 insn_val;
-	int (*fn)(struct pt_regs *regs, u32 insn);
-};
-
-void register_undef_hook(struct undef_hook *hook);
-void unregister_undef_hook(struct undef_hook *hook);
-
-#endif /* __ASM_AVR32_TRAPS_H */
diff --git a/arch/avr32/include/asm/types.h b/arch/avr32/include/asm/types.h
deleted file mode 100644
index 59324058069c..000000000000
--- a/arch/avr32/include/asm/types.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TYPES_H
-#define __ASM_AVR32_TYPES_H
-
-#include <uapi/asm/types.h>
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-
-#define BITS_PER_LONG 32
-
-#endif /* __ASM_AVR32_TYPES_H */
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
deleted file mode 100644
index b1ec1fa06463..000000000000
--- a/arch/avr32/include/asm/uaccess.h
+++ /dev/null
@@ -1,337 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_UACCESS_H
-#define __ASM_AVR32_UACCESS_H
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
-typedef struct {
-	unsigned int is_user_space;
-} mm_segment_t;
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons (Data Segment Register?), these macros are misnamed.
- */
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-#define segment_eq(a, b)	((a).is_user_space == (b).is_user_space)
-
-#define USER_ADDR_LIMIT 0x80000000
-
-#define KERNEL_DS	MAKE_MM_SEG(0)
-#define USER_DS		MAKE_MM_SEG(1)
-
-#define get_ds()	(KERNEL_DS)
-
-static inline mm_segment_t get_fs(void)
-{
-	return MAKE_MM_SEG(test_thread_flag(TIF_USERSPACE));
-}
-
-static inline void set_fs(mm_segment_t s)
-{
-	if (s.is_user_space)
-		set_thread_flag(TIF_USERSPACE);
-	else
-		clear_thread_flag(TIF_USERSPACE);
-}
-
-/*
- * Test whether a block of memory is a valid user space address.
- * Returns 0 if the range is valid, nonzero otherwise.
- *
- * We do the following checks:
- *   1. Is the access from kernel space?
- *   2. Does (addr + size) set the carry bit?
- *   3. Is (addr + size) a negative number (i.e. >= 0x80000000)?
- *
- * If yes on the first check, access is granted.
- * If no on any of the others, access is denied.
- */
-#define __range_ok(addr, size)						\
-	(test_thread_flag(TIF_USERSPACE)				\
-	 && (((unsigned long)(addr) >= 0x80000000)			\
-	     || ((unsigned long)(size) > 0x80000000)			\
-	     || (((unsigned long)(addr) + (unsigned long)(size)) > 0x80000000)))
-
-#define access_ok(type, addr, size) (likely(__range_ok(addr, size) == 0))
-
-/* Generic arbitrary sized copy. Return the number of bytes NOT copied */
-extern __kernel_size_t __copy_user(void *to, const void *from,
-				   __kernel_size_t n);
-
-extern __kernel_size_t copy_to_user(void __user *to, const void *from,
-				    __kernel_size_t n);
-extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
-				      __kernel_size_t n);
-
-static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
-					     __kernel_size_t n)
-{
-	return __copy_user((void __force *)to, from, n);
-}
-static inline __kernel_size_t __copy_from_user(void *to,
-					       const void __user *from,
-					       __kernel_size_t n)
-{
-	return __copy_user(to, (const void __force *)from, n);
-}
-static inline __kernel_size_t copy_from_user(void *to,
-					       const void __user *from,
-					       __kernel_size_t n)
-{
-	size_t res = ___copy_from_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/*
- * put_user: - Write a simple value into user space.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define put_user(x, ptr)	\
-	__put_user_check((x), (ptr), sizeof(*(ptr)))
-
-/*
- * get_user: - Get a simple variable from user space.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define get_user(x, ptr) \
-	__get_user_check((x), (ptr), sizeof(*(ptr)))
-
-/*
- * __put_user: - Write a simple value into user space, with less checking.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define __put_user(x, ptr) \
-	__put_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
-/*
- * __get_user: - Get a simple variable from user space, with less checking.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define __get_user(x, ptr) \
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
-extern int __get_user_bad(void);
-extern int __put_user_bad(void);
-
-#define __get_user_nocheck(x, ptr, size)				\
-({									\
-	unsigned long __gu_val = 0;					\
-	int __gu_err = 0;						\
-									\
-	switch (size) {							\
-	case 1: __get_user_asm("ub", __gu_val, ptr, __gu_err); break;	\
-	case 2: __get_user_asm("uh", __gu_val, ptr, __gu_err); break;	\
-	case 4: __get_user_asm("w", __gu_val, ptr, __gu_err); break;	\
-	default: __gu_err = __get_user_bad(); break;			\
-	}								\
-									\
-	x = (__force typeof(*(ptr)))__gu_val;				\
-	__gu_err;							\
-})
-
-#define __get_user_check(x, ptr, size)					\
-({									\
-	unsigned long __gu_val = 0;					\
-	const typeof(*(ptr)) __user * __gu_addr = (ptr);		\
-	int __gu_err = 0;						\
-									\
-	if (access_ok(VERIFY_READ, __gu_addr, size)) {			\
-		switch (size) {						\
-		case 1:							\
-			__get_user_asm("ub", __gu_val, __gu_addr,	\
-				       __gu_err);			\
-			break;						\
-		case 2:							\
-			__get_user_asm("uh", __gu_val, __gu_addr,	\
-				       __gu_err);			\
-			break;						\
-		case 4:							\
-			__get_user_asm("w", __gu_val, __gu_addr,	\
-				       __gu_err);			\
-			break;						\
-		default:						\
-			__gu_err = __get_user_bad();			\
-			break;						\
-		}							\
-	} else {							\
-		__gu_err = -EFAULT;					\
-	}								\
-	x = (__force typeof(*(ptr)))__gu_val;				\
-	__gu_err;							\
-})
-
-#define __get_user_asm(suffix, __gu_val, ptr, __gu_err)			\
-	asm volatile(							\
-		"1:	ld." suffix "	%1, %3			\n"	\
-		"2:						\n"	\
-		"	.subsection 1				\n"	\
-		"3:	mov	%0, %4				\n"	\
-		"	rjmp	2b				\n"	\
-		"	.subsection 0				\n"	\
-		"	.section __ex_table, \"a\"		\n"	\
-		"	.long	1b, 3b				\n"	\
-		"	.previous				\n"	\
-		: "=r"(__gu_err), "=r"(__gu_val)			\
-		: "0"(__gu_err), "m"(*(ptr)), "i"(-EFAULT))
-
-#define __put_user_nocheck(x, ptr, size)				\
-({									\
-	typeof(*(ptr)) __pu_val;					\
-	int __pu_err = 0;						\
-									\
-	__pu_val = (x);							\
-	switch (size) {							\
-	case 1: __put_user_asm("b", ptr, __pu_val, __pu_err); break;	\
-	case 2: __put_user_asm("h", ptr, __pu_val, __pu_err); break;	\
-	case 4: __put_user_asm("w", ptr, __pu_val, __pu_err); break;	\
-	case 8: __put_user_asm("d", ptr, __pu_val, __pu_err); break;	\
-	default: __pu_err = __put_user_bad(); break;			\
-	}								\
-	__pu_err;							\
-})
-
-#define __put_user_check(x, ptr, size)					\
-({									\
-	typeof(*(ptr)) __pu_val;					\
-	typeof(*(ptr)) __user *__pu_addr = (ptr);			\
-	int __pu_err = 0;						\
-									\
-	__pu_val = (x);							\
-	if (access_ok(VERIFY_WRITE, __pu_addr, size)) {			\
-		switch (size) {						\
-		case 1:							\
-			__put_user_asm("b", __pu_addr, __pu_val,	\
-				       __pu_err);			\
-			break;						\
-		case 2:							\
-			__put_user_asm("h", __pu_addr, __pu_val,	\
-				       __pu_err);			\
-			break;						\
-		case 4:							\
-			__put_user_asm("w", __pu_addr, __pu_val,	\
-				       __pu_err);			\
-			break;						\
-		case 8:							\
-			__put_user_asm("d", __pu_addr, __pu_val,	\
-				       __pu_err);			\
-			break;						\
-		default:						\
-			__pu_err = __put_user_bad();			\
-			break;						\
-		}							\
-	} else {							\
-		__pu_err = -EFAULT;					\
-	}								\
-	__pu_err;							\
-})
-
-#define __put_user_asm(suffix, ptr, __pu_val, __gu_err)			\
-	asm volatile(							\
-		"1:	st." suffix "	%1, %3			\n"	\
-		"2:						\n"	\
-		"	.subsection 1				\n"	\
-		"3:	mov	%0, %4				\n"	\
-		"	rjmp	2b				\n"	\
-		"	.subsection 0				\n"	\
-		"	.section __ex_table, \"a\"		\n"	\
-		"	.long	1b, 3b				\n"	\
-		"	.previous				\n"	\
-		: "=r"(__gu_err), "=m"(*(ptr))				\
-		: "0"(__gu_err), "r"(__pu_val), "i"(-EFAULT))
-
-extern __kernel_size_t clear_user(void __user *addr, __kernel_size_t size);
-extern __kernel_size_t __clear_user(void __user *addr, __kernel_size_t size);
-
-extern long strncpy_from_user(char *dst, const char __user *src, long count);
-extern long __strncpy_from_user(char *dst, const char __user *src, long count);
-
-extern long strnlen_user(const char __user *__s, long __n);
-extern long __strnlen_user(const char __user *__s, long __n);
-
-#define strlen_user(s) strnlen_user(s, ~0UL >> 1)
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-#endif /* __ASM_AVR32_UACCESS_H */
diff --git a/arch/avr32/include/asm/ucontext.h b/arch/avr32/include/asm/ucontext.h
deleted file mode 100644
index ac7259c2a799..000000000000
--- a/arch/avr32/include/asm/ucontext.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __ASM_AVR32_UCONTEXT_H
-#define __ASM_AVR32_UCONTEXT_H
-
-struct ucontext {
-	unsigned long		uc_flags;
-	struct ucontext	*	uc_link;
-	stack_t			uc_stack;
-	struct sigcontext	uc_mcontext;
-	sigset_t		uc_sigmask;
-};
-
-#endif /* __ASM_AVR32_UCONTEXT_H */
diff --git a/arch/avr32/include/asm/unaligned.h b/arch/avr32/include/asm/unaligned.h
deleted file mode 100644
index 041877290470..000000000000
--- a/arch/avr32/include/asm/unaligned.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef _ASM_AVR32_UNALIGNED_H
-#define _ASM_AVR32_UNALIGNED_H
-
-/*
- * AVR32 can handle some unaligned accesses, depending on the
- * implementation.  The AVR32 AP implementation can handle unaligned
- * words, but halfwords must be halfword-aligned, and doublewords must
- * be word-aligned.
- *
- * However, swapped word loads must be word-aligned so we can't
- * optimize word loads in general.
- */
-
-#include <linux/unaligned/be_struct.h>
-#include <linux/unaligned/le_byteshift.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned	__get_unaligned_be
-#define put_unaligned	__put_unaligned_be
-
-#endif /* _ASM_AVR32_UNALIGNED_H */
diff --git a/arch/avr32/include/asm/unistd.h b/arch/avr32/include/asm/unistd.h
deleted file mode 100644
index 2011bee3f252..000000000000
--- a/arch/avr32/include/asm/unistd.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_UNISTD_H
-#define __ASM_AVR32_UNISTD_H
-
-#include <uapi/asm/unistd.h>
-
-#define NR_syscalls		321
-
-/* Old stuff */
-#define __IGNORE_uselib
-#define __IGNORE_mmap
-
-/* NUMA stuff */
-#define __IGNORE_mbind
-#define __IGNORE_get_mempolicy
-#define __IGNORE_set_mempolicy
-#define __IGNORE_migrate_pages
-#define __IGNORE_move_pages
-
-/* SMP stuff */
-#define __IGNORE_getcpu
-
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_FORK
-#define __ARCH_WANT_SYS_VFORK
-#define __ARCH_WANT_SYS_CLONE
-
-#endif /* __ASM_AVR32_UNISTD_H */
diff --git a/arch/avr32/include/asm/user.h b/arch/avr32/include/asm/user.h
deleted file mode 100644
index 7e9152f81f5e..000000000000
--- a/arch/avr32/include/asm/user.h
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Note: We may not need these definitions for AVR32, as we don't
- * support a.out.
- */
-#ifndef __ASM_AVR32_USER_H
-#define __ASM_AVR32_USER_H
-
-#include <linux/types.h>
-#include <asm/ptrace.h>
-#include <asm/page.h>
-
-/*
- * Core file format: The core file is written in such a way that gdb
- * can understand it and provide useful information to the user (under
- * linux we use the `trad-core' bfd).  The file contents are as follows:
- *
- *  upage: 1 page consisting of a user struct that tells gdb
- *	what is present in the file.  Directly after this is a
- *	copy of the task_struct, which is currently not used by gdb,
- *	but it may come in handy at some point.  All of the registers
- *	are stored as part of the upage.  The upage should always be
- *	only one page long.
- *  data: The data segment follows next.  We use current->end_text to
- *	current->brk to pick up all of the user variables, plus any memory
- *	that may have been sbrk'ed.  No attempt is made to determine if a
- *	page is demand-zero or if a page is totally unused, we just cover
- *	the entire range.  All of the addresses are rounded in such a way
- *	that an integral number of pages is written.
- *  stack: We need the stack information in order to get a meaningful
- *	backtrace.  We need to write the data from usp to
- *	current->start_stack, so we round each of these in order to be able
- *	to write an integer number of pages.
- */
-
-struct user_fpu_struct {
-	/* We have no FPU (yet) */
-};
-
-struct user {
-	struct pt_regs	regs;			/* entire machine state */
-	size_t		u_tsize;		/* text size (pages) */
-	size_t		u_dsize;		/* data size (pages) */
-	size_t		u_ssize;		/* stack size (pages) */
-	unsigned long	start_code;		/* text starting address */
-	unsigned long	start_data;		/* data starting address */
-	unsigned long	start_stack;		/* stack starting address */
-	long int	signal;			/* signal causing core dump */
-	unsigned long	u_ar0;			/* help gdb find registers */
-	unsigned long	magic;			/* identifies a core file */
-	char		u_comm[32];		/* user command name */
-};
-
-#define NBPG			PAGE_SIZE
-#define UPAGES			1
-#define HOST_TEXT_START_ADDR	(u.start_code)
-#define HOST_DATA_START_ADDR	(u.start_data)
-#define HOST_STACK_END_ADDR	(u.start_stack + u.u_ssize * NBPG)
-
-#endif /* __ASM_AVR32_USER_H */
diff --git a/arch/avr32/include/uapi/asm/Kbuild b/arch/avr32/include/uapi/asm/Kbuild
deleted file mode 100644
index 08d8a3d76ea8..000000000000
--- a/arch/avr32/include/uapi/asm/Kbuild
+++ /dev/null
@@ -1,36 +0,0 @@
-# UAPI Header export list
-include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
-generic-y += bitsperlong.h
-generic-y += errno.h
-generic-y += fcntl.h
-generic-y += ioctl.h
-generic-y += ioctls.h
-generic-y += ipcbuf.h
-generic-y += kvm_para.h
-generic-y += mman.h
-generic-y += param.h
-generic-y += poll.h
-generic-y += resource.h
-generic-y += siginfo.h
-generic-y += statfs.h
diff --git a/arch/avr32/include/uapi/asm/auxvec.h b/arch/avr32/include/uapi/asm/auxvec.h
deleted file mode 100644
index 4f02da3ffefa..000000000000
--- a/arch/avr32/include/uapi/asm/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_AUXVEC_H
-#define _UAPI__ASM_AVR32_AUXVEC_H
-
-#endif /* _UAPI__ASM_AVR32_AUXVEC_H */
diff --git a/arch/avr32/include/uapi/asm/byteorder.h b/arch/avr32/include/uapi/asm/byteorder.h
deleted file mode 100644
index 71242f0d39c6..000000000000
--- a/arch/avr32/include/uapi/asm/byteorder.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * AVR32 endian-conversion functions.
- */
-#ifndef _UAPI__ASM_AVR32_BYTEORDER_H
-#define _UAPI__ASM_AVR32_BYTEORDER_H
-
-#include <linux/byteorder/big_endian.h>
-
-#endif /* _UAPI__ASM_AVR32_BYTEORDER_H */
diff --git a/arch/avr32/include/uapi/asm/cachectl.h b/arch/avr32/include/uapi/asm/cachectl.h
deleted file mode 100644
index 573a9584dd57..000000000000
--- a/arch/avr32/include/uapi/asm/cachectl.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_CACHECTL_H
-#define _UAPI__ASM_AVR32_CACHECTL_H
-
-/*
- * Operations that can be performed through the cacheflush system call
- */
-
-/* Clean the data cache, then invalidate the icache */
-#define CACHE_IFLUSH	0
-
-#endif /* _UAPI__ASM_AVR32_CACHECTL_H */
diff --git a/arch/avr32/include/uapi/asm/msgbuf.h b/arch/avr32/include/uapi/asm/msgbuf.h
deleted file mode 100644
index 9eae6effad14..000000000000
--- a/arch/avr32/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_MSGBUF_H
-#define _UAPI__ASM_AVR32_MSGBUF_H
-
-/*
- * The msqid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-	unsigned long	__unused1;
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	unsigned long	__unused2;
-	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned long	__unused3;
-	unsigned long  msg_cbytes;	/* current number of bytes on queue */
-	unsigned long  msg_qnum;	/* number of messages in queue */
-	unsigned long  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long  __unused4;
-	unsigned long  __unused5;
-};
-
-#endif /* _UAPI__ASM_AVR32_MSGBUF_H */
diff --git a/arch/avr32/include/uapi/asm/posix_types.h b/arch/avr32/include/uapi/asm/posix_types.h
deleted file mode 100644
index 5b813a8abf09..000000000000
--- a/arch/avr32/include/uapi/asm/posix_types.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_POSIX_TYPES_H
-#define _UAPI__ASM_AVR32_POSIX_TYPES_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- */
-
-typedef unsigned short  __kernel_mode_t;
-#define __kernel_mode_t __kernel_mode_t
-
-typedef unsigned short  __kernel_ipc_pid_t;
-#define __kernel_ipc_pid_t __kernel_ipc_pid_t
-
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef int             __kernel_ptrdiff_t;
-#define __kernel_size_t __kernel_size_t
-
-typedef unsigned short  __kernel_old_uid_t;
-typedef unsigned short  __kernel_old_gid_t;
-#define __kernel_old_uid_t __kernel_old_uid_t
-
-typedef unsigned short  __kernel_old_dev_t;
-#define __kernel_old_dev_t __kernel_old_dev_t
-
-#include <asm-generic/posix_types.h>
-
-#endif /* _UAPI__ASM_AVR32_POSIX_TYPES_H */
diff --git a/arch/avr32/include/uapi/asm/ptrace.h b/arch/avr32/include/uapi/asm/ptrace.h
deleted file mode 100644
index fe8c16275bc0..000000000000
--- a/arch/avr32/include/uapi/asm/ptrace.h
+++ /dev/null
@@ -1,126 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_PTRACE_H
-#define _UAPI__ASM_AVR32_PTRACE_H
-
-#define PTRACE_GETREGS		12
-#define PTRACE_SETREGS		13
-
-/*
- * Status Register bits
- */
-#define SR_H		0x20000000
-#define SR_J		0x10000000
-#define SR_DM		0x08000000
-#define SR_D		0x04000000
-#define MODE_NMI	0x01c00000
-#define MODE_EXCEPTION	0x01800000
-#define MODE_INT3	0x01400000
-#define MODE_INT2	0x01000000
-#define MODE_INT1	0x00c00000
-#define MODE_INT0	0x00800000
-#define MODE_SUPERVISOR	0x00400000
-#define MODE_USER	0x00000000
-#define MODE_MASK	0x01c00000
-#define SR_EM		0x00200000
-#define SR_I3M		0x00100000
-#define SR_I2M		0x00080000
-#define SR_I1M		0x00040000
-#define SR_I0M		0x00020000
-#define SR_GM		0x00010000
-
-#define SR_H_BIT	29
-#define SR_J_BIT	28
-#define SR_DM_BIT	27
-#define SR_D_BIT	26
-#define MODE_SHIFT	22
-#define SR_EM_BIT	21
-#define SR_I3M_BIT	20
-#define SR_I2M_BIT	19
-#define SR_I1M_BIT	18
-#define SR_I0M_BIT	17
-#define SR_GM_BIT	16
-
-/* The user-visible part */
-#define SR_L		0x00000020
-#define SR_Q		0x00000010
-#define SR_V		0x00000008
-#define SR_N		0x00000004
-#define SR_Z		0x00000002
-#define SR_C		0x00000001
-
-#define SR_L_BIT	5
-#define SR_Q_BIT	4
-#define SR_V_BIT	3
-#define SR_N_BIT	2
-#define SR_Z_BIT	1
-#define SR_C_BIT	0
-
-/*
- * The order is defined by the stmts instruction. r0 is stored first,
- * so it gets the highest address.
- *
- * Registers 0-12 are general-purpose registers (r12 is normally used for
- * the function return value).
- * Register 13 is the stack pointer
- * Register 14 is the link register
- * Register 15 is the program counter (retrieved from the RAR sysreg)
- */
-#define FRAME_SIZE_FULL 72
-#define REG_R12_ORIG	68
-#define REG_R0		64
-#define REG_R1		60
-#define REG_R2		56
-#define REG_R3		52
-#define REG_R4		48
-#define REG_R5		44
-#define REG_R6		40
-#define REG_R7		36
-#define REG_R8		32
-#define REG_R9		28
-#define REG_R10		24
-#define REG_R11		20
-#define REG_R12		16
-#define REG_SP		12
-#define REG_LR		 8
-
-#define FRAME_SIZE_MIN	 8
-#define REG_PC		 4
-#define REG_SR		 0
-
-#ifndef __ASSEMBLY__
-struct pt_regs {
-	/* These are always saved */
-	unsigned long sr;
-	unsigned long pc;
-
-	/* These are sometimes saved */
-	unsigned long lr;
-	unsigned long sp;
-	unsigned long r12;
-	unsigned long r11;
-	unsigned long r10;
-	unsigned long r9;
-	unsigned long r8;
-	unsigned long r7;
-	unsigned long r6;
-	unsigned long r5;
-	unsigned long r4;
-	unsigned long r3;
-	unsigned long r2;
-	unsigned long r1;
-	unsigned long r0;
-
-	/* Only saved on system call */
-	unsigned long r12_orig;
-};
-
-
-#endif /* ! __ASSEMBLY__ */
-
-#endif /* _UAPI__ASM_AVR32_PTRACE_H */
diff --git a/arch/avr32/include/uapi/asm/sembuf.h b/arch/avr32/include/uapi/asm/sembuf.h
deleted file mode 100644
index 6c6f7cf1e75a..000000000000
--- a/arch/avr32/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_SEMBUF_H
-#define _UAPI__ASM_AVR32_SEMBUF_H
-
-/*
-* The semid64_ds structure for AVR32 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
-        struct ipc64_perm sem_perm;             /* permissions .. see ipc.h */
-        __kernel_time_t sem_otime;              /* last semop time */
-        unsigned long   __unused1;
-        __kernel_time_t sem_ctime;              /* last change time */
-        unsigned long   __unused2;
-        unsigned long   sem_nsems;              /* no. of semaphores in array */
-        unsigned long   __unused3;
-        unsigned long   __unused4;
-};
-
-#endif /* _UAPI__ASM_AVR32_SEMBUF_H */
diff --git a/arch/avr32/include/uapi/asm/setup.h b/arch/avr32/include/uapi/asm/setup.h
deleted file mode 100644
index a654df7dba46..000000000000
--- a/arch/avr32/include/uapi/asm/setup.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/include/asm-arm/setup.h
- *   Copyright (C) 1997-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_SETUP_H__
-#define _UAPI__ASM_AVR32_SETUP_H__
-
-#define COMMAND_LINE_SIZE 256
-
-#endif /* _UAPI__ASM_AVR32_SETUP_H__ */
diff --git a/arch/avr32/include/uapi/asm/shmbuf.h b/arch/avr32/include/uapi/asm/shmbuf.h
deleted file mode 100644
index b94cf8b60b73..000000000000
--- a/arch/avr32/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_SHMBUF_H
-#define _UAPI__ASM_AVR32_SHMBUF_H
-
-/*
- * The shmid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-	unsigned long		__unused1;
-	__kernel_time_t		shm_dtime;	/* last detach time */
-	unsigned long		__unused2;
-	__kernel_time_t		shm_ctime;	/* last change time */
-	unsigned long		__unused3;
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused4;
-	unsigned long		__unused5;
-};
-
-struct shminfo64 {
-	unsigned long	shmmax;
-	unsigned long	shmmin;
-	unsigned long	shmmni;
-	unsigned long	shmseg;
-	unsigned long	shmall;
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _UAPI__ASM_AVR32_SHMBUF_H */
diff --git a/arch/avr32/include/uapi/asm/sigcontext.h b/arch/avr32/include/uapi/asm/sigcontext.h
deleted file mode 100644
index 27e56bf6377f..000000000000
--- a/arch/avr32/include/uapi/asm/sigcontext.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_SIGCONTEXT_H
-#define _UAPI__ASM_AVR32_SIGCONTEXT_H
-
-struct sigcontext {
-	unsigned long	oldmask;
-
-	/* CPU registers */
-	unsigned long	sr;
-	unsigned long	pc;
-	unsigned long	lr;
-	unsigned long	sp;
-	unsigned long	r12;
-	unsigned long	r11;
-	unsigned long	r10;
-	unsigned long	r9;
-	unsigned long	r8;
-	unsigned long	r7;
-	unsigned long	r6;
-	unsigned long	r5;
-	unsigned long	r4;
-	unsigned long	r3;
-	unsigned long	r2;
-	unsigned long	r1;
-	unsigned long	r0;
-};
-
-#endif /* _UAPI__ASM_AVR32_SIGCONTEXT_H */
diff --git a/arch/avr32/include/uapi/asm/signal.h b/arch/avr32/include/uapi/asm/signal.h
deleted file mode 100644
index ffe8c770cafd..000000000000
--- a/arch/avr32/include/uapi/asm/signal.h
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_SIGNAL_H
-#define _UAPI__ASM_AVR32_SIGNAL_H
-
-#include <linux/types.h>
-
-/* Avoid too many header ordering problems.  */
-struct siginfo;
-
-#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers.  */
-
-#define NSIG		32
-typedef unsigned long sigset_t;
-
-#endif /* __KERNEL__ */
-
-#define SIGHUP		 1
-#define SIGINT		 2
-#define SIGQUIT		 3
-#define SIGILL		 4
-#define SIGTRAP		 5
-#define SIGABRT		 6
-#define SIGIOT		 6
-#define SIGBUS		 7
-#define SIGFPE		 8
-#define SIGKILL		 9
-#define SIGUSR1		10
-#define SIGSEGV		11
-#define SIGUSR2		12
-#define SIGPIPE		13
-#define SIGALRM		14
-#define SIGTERM		15
-#define SIGSTKFLT	16
-#define SIGCHLD		17
-#define SIGCONT		18
-#define SIGSTOP		19
-#define SIGTSTP		20
-#define SIGTTIN		21
-#define SIGTTOU		22
-#define SIGURG		23
-#define SIGXCPU		24
-#define SIGXFSZ		25
-#define SIGVTALRM	26
-#define SIGPROF		27
-#define SIGWINCH	28
-#define SIGIO		29
-#define SIGPOLL		SIGIO
-/*
-#define SIGLOST		29
-*/
-#define SIGPWR		30
-#define SIGSYS		31
-#define	SIGUNUSED	31
-
-/* These should not be considered constants from userland.  */
-#define SIGRTMIN	32
-#define SIGRTMAX	(_NSIG-1)
-
-/*
- * SA_FLAGS values:
- *
- * SA_NOCLDSTOP		flag to turn off SIGCHLD when children stop.
- * SA_NOCLDWAIT		flag on SIGCHLD to inhibit zombies.
- * SA_SIGINFO		deliver the signal with SIGINFO structs
- * SA_ONSTACK		indicates that a registered stack_t will be used.
- * SA_RESTART		flag to get restarting signals (which were the default long ago)
- * SA_NODEFER		prevents the current signal from being masked in the handler.
- * SA_RESETHAND		clears the handler when the signal is delivered.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_NOCLDSTOP	0x00000001
-#define SA_NOCLDWAIT	0x00000002
-#define SA_SIGINFO	0x00000004
-#define SA_RESTORER	0x04000000
-#define SA_ONSTACK	0x08000000
-#define SA_RESTART	0x10000000
-#define SA_NODEFER	0x40000000
-#define SA_RESETHAND	0x80000000
-
-#define SA_NOMASK	SA_NODEFER
-#define SA_ONESHOT	SA_RESETHAND
-
-#define MINSIGSTKSZ	2048
-#define SIGSTKSZ	8192
-
-#include <asm-generic/signal-defs.h>
-
-#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers.  */
-
-struct sigaction {
-	union {
-		__sighandler_t _sa_handler;
-		void (*_sa_sigaction)(int, struct siginfo *, void *);
-	} _u;
-	sigset_t sa_mask;
-	unsigned long sa_flags;
-	void (*sa_restorer)(void);
-};
-
-#define sa_handler	_u._sa_handler
-#define sa_sigaction	_u._sa_sigaction
-
-#endif /* __KERNEL__ */
-
-typedef struct sigaltstack {
-	void __user *ss_sp;
-	int ss_flags;
-	size_t ss_size;
-} stack_t;
-
-#endif /* _UAPI__ASM_AVR32_SIGNAL_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
deleted file mode 100644
index 5a650426f357..000000000000
--- a/arch/avr32/include/uapi/asm/socket.h
+++ /dev/null
@@ -1,95 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_SOCKET_H
-#define _UAPI__ASM_AVR32_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockopt(2) */
-#define SOL_SOCKET	1
-
-#define SO_DEBUG	1
-#define SO_REUSEADDR	2
-#define SO_TYPE		3
-#define SO_ERROR	4
-#define SO_DONTROUTE	5
-#define SO_BROADCAST	6
-#define SO_SNDBUF	7
-#define SO_RCVBUF	8
-#define SO_SNDBUFFORCE	32
-#define SO_RCVBUFFORCE	33
-#define SO_KEEPALIVE	9
-#define SO_OOBINLINE	10
-#define SO_NO_CHECK	11
-#define SO_PRIORITY	12
-#define SO_LINGER	13
-#define SO_BSDCOMPAT	14
-#define SO_REUSEPORT	15
-#define SO_PASSCRED	16
-#define SO_PEERCRED	17
-#define SO_RCVLOWAT	18
-#define SO_SNDLOWAT	19
-#define SO_RCVTIMEO	20
-#define SO_SNDTIMEO	21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION		22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
-#define SO_SECURITY_ENCRYPTION_NETWORK		24
-
-#define SO_BINDTODEVICE	25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER        26
-#define SO_DETACH_FILTER        27
-#define SO_GET_FILTER		SO_ATTACH_FILTER
-
-#define SO_PEERNAME		28
-#define SO_TIMESTAMP		29
-#define SCM_TIMESTAMP		SO_TIMESTAMP
-
-#define SO_ACCEPTCONN		30
-
-#define SO_PEERSEC		31
-#define SO_PASSSEC		34
-#define SO_TIMESTAMPNS		35
-#define SCM_TIMESTAMPNS		SO_TIMESTAMPNS
-
-#define SO_MARK			36
-
-#define SO_TIMESTAMPING		37
-#define SCM_TIMESTAMPING	SO_TIMESTAMPING
-
-#define SO_PROTOCOL		38
-#define SO_DOMAIN		39
-
-#define SO_RXQ_OVFL             40
-
-#define SO_WIFI_STATUS		41
-#define SCM_WIFI_STATUS		SO_WIFI_STATUS
-#define SO_PEEK_OFF		42
-
-/* Instruct lower device to use last 4-bytes of skb data as FCS */
-#define SO_NOFCS		43
-
-#define SO_LOCK_FILTER		44
-
-#define SO_SELECT_ERR_QUEUE	45
-
-#define SO_BUSY_POLL		46
-
-#define SO_MAX_PACING_RATE	47
-
-#define SO_BPF_EXTENSIONS	48
-
-#define SO_INCOMING_CPU		49
-
-#define SO_ATTACH_BPF		50
-#define SO_DETACH_BPF		SO_DETACH_FILTER
-
-#define SO_ATTACH_REUSEPORT_CBPF	51
-#define SO_ATTACH_REUSEPORT_EBPF	52
-
-#define SO_CNX_ADVICE		53
-
-#define SCM_TIMESTAMPING_OPT_STATS	54
-
-#endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/sockios.h b/arch/avr32/include/uapi/asm/sockios.h
deleted file mode 100644
index d04785453532..000000000000
--- a/arch/avr32/include/uapi/asm/sockios.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_SOCKIOS_H
-#define _UAPI__ASM_AVR32_SOCKIOS_H
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN 	0x8901
-#define SIOCSPGRP	0x8902
-#define FIOGETOWN	0x8903
-#define SIOCGPGRP	0x8904
-#define SIOCATMARK	0x8905
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
-
-#endif /* _UAPI__ASM_AVR32_SOCKIOS_H */
diff --git a/arch/avr32/include/uapi/asm/stat.h b/arch/avr32/include/uapi/asm/stat.h
deleted file mode 100644
index c06acef7fce7..000000000000
--- a/arch/avr32/include/uapi/asm/stat.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_STAT_H
-#define _UAPI__ASM_AVR32_STAT_H
-
-struct __old_kernel_stat {
-        unsigned short st_dev;
-        unsigned short st_ino;
-        unsigned short st_mode;
-        unsigned short st_nlink;
-        unsigned short st_uid;
-        unsigned short st_gid;
-        unsigned short st_rdev;
-        unsigned long  st_size;
-        unsigned long  st_atime;
-        unsigned long  st_mtime;
-        unsigned long  st_ctime;
-};
-
-struct stat {
-        unsigned long st_dev;
-        unsigned long st_ino;
-        unsigned short st_mode;
-        unsigned short st_nlink;
-        unsigned short st_uid;
-        unsigned short st_gid;
-        unsigned long  st_rdev;
-        unsigned long  st_size;
-        unsigned long  st_blksize;
-        unsigned long  st_blocks;
-        unsigned long  st_atime;
-        unsigned long  st_atime_nsec;
-        unsigned long  st_mtime;
-        unsigned long  st_mtime_nsec;
-        unsigned long  st_ctime;
-        unsigned long  st_ctime_nsec;
-        unsigned long  __unused4;
-        unsigned long  __unused5;
-};
-
-#define STAT_HAVE_NSEC 1
-
-struct stat64 {
-	unsigned long long st_dev;
-
-	unsigned long long st_ino;
-	unsigned int	st_mode;
-	unsigned int	st_nlink;
-
-	unsigned long	st_uid;
-	unsigned long	st_gid;
-
-	unsigned long long st_rdev;
-
-	long long	st_size;
-	unsigned long	__pad1;		/* align 64-bit st_blocks */
-	unsigned long	st_blksize;
-
-	unsigned long long st_blocks;	/* Number 512-byte blocks allocated. */
-
-	unsigned long	st_atime;
-	unsigned long	st_atime_nsec;
-
-	unsigned long	st_mtime;
-	unsigned long	st_mtime_nsec;
-
-	unsigned long	st_ctime;
-	unsigned long	st_ctime_nsec;
-
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-};
-
-#endif /* _UAPI__ASM_AVR32_STAT_H */
diff --git a/arch/avr32/include/uapi/asm/swab.h b/arch/avr32/include/uapi/asm/swab.h
deleted file mode 100644
index 1a03549e7dc5..000000000000
--- a/arch/avr32/include/uapi/asm/swab.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * AVR32 byteswapping functions.
- */
-#ifndef _UAPI__ASM_AVR32_SWAB_H
-#define _UAPI__ASM_AVR32_SWAB_H
-
-#include <linux/types.h>
-#include <linux/compiler.h>
-
-#define __SWAB_64_THRU_32__
-
-#ifdef __CHECKER__
-extern unsigned long __builtin_bswap_32(unsigned long x);
-extern unsigned short __builtin_bswap_16(unsigned short x);
-#endif
-
-/*
- * avr32-linux-gcc versions earlier than 4.2 improperly sign-extends
- * the result.
- */
-#if !(__GNUC__ == 4 && __GNUC_MINOR__ < 2)
-static inline __attribute_const__ __u16 __arch_swab16(__u16 val)
-{
-	return __builtin_bswap_16(val);
-}
-#define __arch_swab16 __arch_swab16
-
-static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
-{
-	return __builtin_bswap_32(val);
-}
-#define __arch_swab32 __arch_swab32
-#endif
-
-#endif /* _UAPI__ASM_AVR32_SWAB_H */
diff --git a/arch/avr32/include/uapi/asm/termbits.h b/arch/avr32/include/uapi/asm/termbits.h
deleted file mode 100644
index 32789ccb38f8..000000000000
--- a/arch/avr32/include/uapi/asm/termbits.h
+++ /dev/null
@@ -1,196 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_TERMBITS_H
-#define _UAPI__ASM_AVR32_TERMBITS_H
-
-#include <linux/posix_types.h>
-
-typedef unsigned char	cc_t;
-typedef unsigned int	speed_t;
-typedef unsigned int	tcflag_t;
-
-#define NCCS 19
-struct termios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-};
-
-struct termios2 {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-struct ktermios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK	0000001
-#define BRKINT	0000002
-#define IGNPAR	0000004
-#define PARMRK	0000010
-#define INPCK	0000020
-#define ISTRIP	0000040
-#define INLCR	0000100
-#define IGNCR	0000200
-#define ICRNL	0000400
-#define IUCLC	0001000
-#define IXON	0002000
-#define IXANY	0004000
-#define IXOFF	0010000
-#define IMAXBEL	0020000
-#define IUTF8	0040000
-
-/* c_oflag bits */
-#define OPOST	0000001
-#define OLCUC	0000002
-#define ONLCR	0000004
-#define OCRNL	0000010
-#define ONOCR	0000020
-#define ONLRET	0000040
-#define OFILL	0000100
-#define OFDEL	0000200
-#define NLDLY	0000400
-#define   NL0	0000000
-#define   NL1	0000400
-#define CRDLY	0003000
-#define   CR0	0000000
-#define   CR1	0001000
-#define   CR2	0002000
-#define   CR3	0003000
-#define TABDLY	0014000
-#define   TAB0	0000000
-#define   TAB1	0004000
-#define   TAB2	0010000
-#define   TAB3	0014000
-#define   XTABS	0014000
-#define BSDLY	0020000
-#define   BS0	0000000
-#define   BS1	0020000
-#define VTDLY	0040000
-#define   VT0	0000000
-#define   VT1	0040000
-#define FFDLY	0100000
-#define   FF0	0000000
-#define   FF1	0100000
-
-/* c_cflag bit meaning */
-#define CBAUD	0010017
-#define  B0	0000000		/* hang up */
-#define  B50	0000001
-#define  B75	0000002
-#define  B110	0000003
-#define  B134	0000004
-#define  B150	0000005
-#define  B200	0000006
-#define  B300	0000007
-#define  B600	0000010
-#define  B1200	0000011
-#define  B1800	0000012
-#define  B2400	0000013
-#define  B4800	0000014
-#define  B9600	0000015
-#define  B19200	0000016
-#define  B38400	0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE	0000060
-#define   CS5	0000000
-#define   CS6	0000020
-#define   CS7	0000040
-#define   CS8	0000060
-#define CSTOPB	0000100
-#define CREAD	0000200
-#define PARENB	0000400
-#define PARODD	0001000
-#define HUPCL	0002000
-#define CLOCAL	0004000
-#define CBAUDEX 0010000
-#define    B57600 0010001
-#define   B115200 0010002
-#define   B230400 0010003
-#define   B460800 0010004
-#define   B500000 0010005
-#define   B576000 0010006
-#define   B921600 0010007
-#define  B1000000 0010010
-#define  B1152000 0010011
-#define  B1500000 0010012
-#define  B2000000 0010013
-#define  B2500000 0010014
-#define  B3000000 0010015
-#define  B3500000 0010016
-#define  B4000000 0010017
-#define CIBAUD	  002003600000	/* input baud rate (not used) */
-#define CMSPAR	  010000000000		/* mark or space (stick) parity */
-#define CRTSCTS	  020000000000		/* flow control */
-
-/* c_lflag bits */
-#define ISIG	0000001
-#define ICANON	0000002
-#define XCASE	0000004
-#define ECHO	0000010
-#define ECHOE	0000020
-#define ECHOK	0000040
-#define ECHONL	0000100
-#define NOFLSH	0000200
-#define TOSTOP	0000400
-#define ECHOCTL	0001000
-#define ECHOPRT	0002000
-#define ECHOKE	0004000
-#define FLUSHO	0010000
-#define PENDIN	0040000
-#define IEXTEN	0100000
-#define EXTPROC	0200000
-
-/* tcflow() and TCXONC use these */
-#define	TCOOFF		0
-#define	TCOON		1
-#define	TCIOFF		2
-#define	TCION		3
-
-/* tcflush() and TCFLSH use these */
-#define	TCIFLUSH	0
-#define	TCOFLUSH	1
-#define	TCIOFLUSH	2
-
-/* tcsetattr uses these */
-#define	TCSANOW		0
-#define	TCSADRAIN	1
-#define	TCSAFLUSH	2
-
-#endif /* _UAPI__ASM_AVR32_TERMBITS_H */
diff --git a/arch/avr32/include/uapi/asm/termios.h b/arch/avr32/include/uapi/asm/termios.h
deleted file mode 100644
index c8a0081556c4..000000000000
--- a/arch/avr32/include/uapi/asm/termios.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_TERMIOS_H
-#define _UAPI__ASM_AVR32_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
-	unsigned short ws_row;
-	unsigned short ws_col;
-	unsigned short ws_xpixel;
-	unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
-	unsigned short c_iflag;		/* input mode flags */
-	unsigned short c_oflag;		/* output mode flags */
-	unsigned short c_cflag;		/* control mode flags */
-	unsigned short c_lflag;		/* local mode flags */
-	unsigned char c_line;		/* line discipline */
-	unsigned char c_cc[NCC];	/* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE	0x001
-#define TIOCM_DTR	0x002
-#define TIOCM_RTS	0x004
-#define TIOCM_ST	0x008
-#define TIOCM_SR	0x010
-#define TIOCM_CTS	0x020
-#define TIOCM_CAR	0x040
-#define TIOCM_RNG	0x080
-#define TIOCM_DSR	0x100
-#define TIOCM_CD	TIOCM_CAR
-#define TIOCM_RI	TIOCM_RNG
-#define TIOCM_OUT1	0x2000
-#define TIOCM_OUT2	0x4000
-#define TIOCM_LOOP	0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#endif /* _UAPI__ASM_AVR32_TERMIOS_H */
diff --git a/arch/avr32/include/uapi/asm/types.h b/arch/avr32/include/uapi/asm/types.h
deleted file mode 100644
index 7c986c4e99b5..000000000000
--- a/arch/avr32/include/uapi/asm/types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_TYPES_H
-#define _UAPI__ASM_AVR32_TYPES_H
-
-#include <asm-generic/int-ll64.h>
-
-#endif /* _UAPI__ASM_AVR32_TYPES_H */
diff --git a/arch/avr32/include/uapi/asm/unistd.h b/arch/avr32/include/uapi/asm/unistd.h
deleted file mode 100644
index 236505d889d0..000000000000
--- a/arch/avr32/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,347 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_UNISTD_H
-#define _UAPI__ASM_AVR32_UNISTD_H
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_restart_syscall    0
-#define __NR_exit               1
-#define __NR_fork               2
-#define __NR_read               3
-#define __NR_write              4
-#define __NR_open               5
-#define __NR_close              6
-#define __NR_umask              7
-#define __NR_creat              8
-#define __NR_link               9
-#define __NR_unlink             10
-#define __NR_execve             11
-#define __NR_chdir              12
-#define __NR_time               13
-#define __NR_mknod              14
-#define __NR_chmod              15
-#define __NR_chown              16
-#define __NR_lchown             17
-#define __NR_lseek              18
-#define __NR__llseek            19
-#define __NR_getpid             20
-#define __NR_mount              21
-#define __NR_umount2            22
-#define __NR_setuid             23
-#define __NR_getuid             24
-#define __NR_stime              25
-#define __NR_ptrace             26
-#define __NR_alarm              27
-#define __NR_pause              28
-#define __NR_utime              29
-#define __NR_stat               30
-#define __NR_fstat              31
-#define __NR_lstat              32
-#define __NR_access             33
-#define __NR_chroot             34
-#define __NR_sync               35
-#define __NR_fsync              36
-#define __NR_kill               37
-#define __NR_rename             38
-#define __NR_mkdir              39
-#define __NR_rmdir              40
-#define __NR_dup                41
-#define __NR_pipe               42
-#define __NR_times              43
-#define __NR_clone              44
-#define __NR_brk                45
-#define __NR_setgid             46
-#define __NR_getgid             47
-#define __NR_getcwd             48
-#define __NR_geteuid            49
-#define __NR_getegid            50
-#define __NR_acct               51
-#define __NR_setfsuid           52
-#define __NR_setfsgid           53
-#define __NR_ioctl              54
-#define __NR_fcntl              55
-#define __NR_setpgid            56
-#define __NR_mremap             57
-#define __NR_setresuid          58
-#define __NR_getresuid          59
-#define __NR_setreuid           60
-#define __NR_setregid           61
-#define __NR_ustat              62
-#define __NR_dup2               63
-#define __NR_getppid            64
-#define __NR_getpgrp            65
-#define __NR_setsid             66
-#define __NR_rt_sigaction       67
-#define __NR_rt_sigreturn       68
-#define __NR_rt_sigprocmask     69
-#define __NR_rt_sigpending      70
-#define __NR_rt_sigtimedwait    71
-#define __NR_rt_sigqueueinfo    72
-#define __NR_rt_sigsuspend      73
-#define __NR_sethostname        74
-#define __NR_setrlimit          75
-#define __NR_getrlimit          76 /* SuS compliant getrlimit */
-#define __NR_getrusage          77
-#define __NR_gettimeofday       78
-#define __NR_settimeofday       79
-#define __NR_getgroups          80
-#define __NR_setgroups          81
-#define __NR_select             82
-#define __NR_symlink            83
-#define __NR_fchdir             84
-#define __NR_readlink           85
-#define __NR_pread              86
-#define __NR_pwrite             87
-#define __NR_swapon             88
-#define __NR_reboot             89
-#define __NR_mmap2              90
-#define __NR_munmap             91
-#define __NR_truncate           92
-#define __NR_ftruncate          93
-#define __NR_fchmod             94
-#define __NR_fchown             95
-#define __NR_getpriority        96
-#define __NR_setpriority        97
-#define __NR_wait4              98
-#define __NR_statfs             99
-#define __NR_fstatfs            100
-#define __NR_vhangup            101
-#define __NR_sigaltstack        102
-#define __NR_syslog             103
-#define __NR_setitimer          104
-#define __NR_getitimer          105
-#define __NR_swapoff            106
-#define __NR_sysinfo            107
-/* 108 was __NR_ipc for a little while */
-#define __NR_sendfile           109
-#define __NR_setdomainname      110
-#define __NR_uname              111
-#define __NR_adjtimex           112
-#define __NR_mprotect           113
-#define __NR_vfork              114
-#define __NR_init_module        115
-#define __NR_delete_module      116
-#define __NR_quotactl           117
-#define __NR_getpgid            118
-#define __NR_bdflush            119
-#define __NR_sysfs              120
-#define __NR_personality        121
-#define __NR_afs_syscall        122 /* Syscall for Andrew File System */
-#define __NR_getdents           123
-#define __NR_flock              124
-#define __NR_msync              125
-#define __NR_readv              126
-#define __NR_writev             127
-#define __NR_getsid             128
-#define __NR_fdatasync          129
-#define __NR__sysctl            130
-#define __NR_mlock              131
-#define __NR_munlock            132
-#define __NR_mlockall           133
-#define __NR_munlockall         134
-#define __NR_sched_setparam     135
-#define __NR_sched_getparam     136
-#define __NR_sched_setscheduler 137
-#define __NR_sched_getscheduler 138
-#define __NR_sched_yield        139
-#define __NR_sched_get_priority_max     140
-#define __NR_sched_get_priority_min     141
-#define __NR_sched_rr_get_interval      142
-#define __NR_nanosleep          143
-#define __NR_poll               144
-#define __NR_nfsservctl         145
-#define __NR_setresgid          146
-#define __NR_getresgid          147
-#define __NR_prctl              148
-#define __NR_socket             149
-#define __NR_bind               150
-#define __NR_connect            151
-#define __NR_listen             152
-#define __NR_accept             153
-#define __NR_getsockname        154
-#define __NR_getpeername        155
-#define __NR_socketpair         156
-#define __NR_send               157
-#define __NR_recv               158
-#define __NR_sendto             159
-#define __NR_recvfrom           160
-#define __NR_shutdown           161
-#define __NR_setsockopt         162
-#define __NR_getsockopt         163
-#define __NR_sendmsg            164
-#define __NR_recvmsg            165
-#define __NR_truncate64         166
-#define __NR_ftruncate64        167
-#define __NR_stat64             168
-#define __NR_lstat64            169
-#define __NR_fstat64            170
-#define __NR_pivot_root         171
-#define __NR_mincore            172
-#define __NR_madvise            173
-#define __NR_getdents64         174
-#define __NR_fcntl64            175
-#define __NR_gettid             176
-#define __NR_readahead          177
-#define __NR_setxattr           178
-#define __NR_lsetxattr          179
-#define __NR_fsetxattr          180
-#define __NR_getxattr           181
-#define __NR_lgetxattr          182
-#define __NR_fgetxattr          183
-#define __NR_listxattr          184
-#define __NR_llistxattr         185
-#define __NR_flistxattr         186
-#define __NR_removexattr        187
-#define __NR_lremovexattr       188
-#define __NR_fremovexattr       189
-#define __NR_tkill              190
-#define __NR_sendfile64         191
-#define __NR_futex              192
-#define __NR_sched_setaffinity  193
-#define __NR_sched_getaffinity  194
-#define __NR_capget             195
-#define __NR_capset             196
-#define __NR_io_setup           197
-#define __NR_io_destroy         198
-#define __NR_io_getevents       199
-#define __NR_io_submit          200
-#define __NR_io_cancel          201
-#define __NR_fadvise64          202
-#define __NR_exit_group         203
-#define __NR_lookup_dcookie     204
-#define __NR_epoll_create       205
-#define __NR_epoll_ctl          206
-#define __NR_epoll_wait         207
-#define __NR_remap_file_pages   208
-#define __NR_set_tid_address    209
-#define __NR_timer_create       210
-#define __NR_timer_settime      211
-#define __NR_timer_gettime      212
-#define __NR_timer_getoverrun   213
-#define __NR_timer_delete       214
-#define __NR_clock_settime      215
-#define __NR_clock_gettime      216
-#define __NR_clock_getres       217
-#define __NR_clock_nanosleep    218
-#define __NR_statfs64           219
-#define __NR_fstatfs64          220
-#define __NR_tgkill             221
-/* 222 reserved for tux */
-#define __NR_utimes             223
-#define __NR_fadvise64_64       224
-#define __NR_cacheflush         225
-#define __NR_vserver            226
-#define __NR_mq_open            227
-#define __NR_mq_unlink          228
-#define __NR_mq_timedsend       229
-#define __NR_mq_timedreceive    230
-#define __NR_mq_notify          231
-#define __NR_mq_getsetattr      232
-#define __NR_kexec_load         233
-#define __NR_waitid             234
-#define __NR_add_key            235
-#define __NR_request_key        236
-#define __NR_keyctl             237
-#define __NR_ioprio_set         238
-#define __NR_ioprio_get         239
-#define __NR_inotify_init       240
-#define __NR_inotify_add_watch  241
-#define __NR_inotify_rm_watch   242
-#define __NR_openat             243
-#define __NR_mkdirat            244
-#define __NR_mknodat            245
-#define __NR_fchownat           246
-#define __NR_futimesat          247
-#define __NR_fstatat64          248
-#define __NR_unlinkat           249
-#define __NR_renameat           250
-#define __NR_linkat             251
-#define __NR_symlinkat          252
-#define __NR_readlinkat         253
-#define __NR_fchmodat           254
-#define __NR_faccessat          255
-#define __NR_pselect6           256
-#define __NR_ppoll              257
-#define __NR_unshare            258
-#define __NR_set_robust_list    259
-#define __NR_get_robust_list    260
-#define __NR_splice             261
-#define __NR_sync_file_range    262
-#define __NR_tee                263
-#define __NR_vmsplice           264
-#define __NR_epoll_pwait        265
-#define __NR_msgget             266
-#define __NR_msgsnd             267
-#define __NR_msgrcv             268
-#define __NR_msgctl             269
-#define __NR_semget             270
-#define __NR_semop              271
-#define __NR_semctl             272
-#define __NR_semtimedop         273
-#define __NR_shmat              274
-#define __NR_shmget             275
-#define __NR_shmdt              276
-#define __NR_shmctl             277
-#define __NR_utimensat          278
-#define __NR_signalfd           279
-/* 280 was __NR_timerfd */
-#define __NR_eventfd            281
-/* 282 was half-implemented __NR_recvmmsg */
-#define __NR_setns              283
-#define __NR_pread64            284
-#define __NR_pwrite64           285
-#define __NR_timerfd_create     286
-#define __NR_fallocate          287
-#define __NR_timerfd_settime    288
-#define __NR_timerfd_gettime    289
-#define __NR_signalfd4          290
-#define __NR_eventfd2           291
-#define __NR_epoll_create1      292
-#define __NR_dup3               293
-#define __NR_pipe2              294
-#define __NR_inotify_init1      295
-#define __NR_preadv             296
-#define __NR_pwritev            297
-#define __NR_rt_tgsigqueueinfo  298
-#define __NR_perf_event_open    299
-#define __NR_recvmmsg           300
-#define __NR_fanotify_init      301
-#define __NR_fanotify_mark      302
-#define __NR_prlimit64          303
-#define __NR_name_to_handle_at  304
-#define __NR_open_by_handle_at  305
-#define __NR_clock_adjtime      306
-#define __NR_syncfs             307
-#define __NR_sendmmsg           308
-#define __NR_process_vm_readv   309
-#define __NR_process_vm_writev  310
-#define __NR_kcmp               311
-#define __NR_finit_module       312
-#define __NR_sched_setattr      313
-#define __NR_sched_getattr      314
-#define __NR_renameat2          315
-#define __NR_seccomp            316
-#define __NR_getrandom          317
-#define __NR_memfd_create       318
-#define __NR_bpf                319
-#define __NR_execveat           320
-#define __NR_accept4            321
-#define __NR_userfaultfd        322
-#define __NR_membarrier         323
-#define __NR_mlock2             324
-#define __NR_copy_file_range    325
-#define __NR_preadv2            326
-#define __NR_pwritev2           327
-#define __NR_pkey_mprotect      328
-#define __NR_pkey_alloc         329
-#define __NR_pkey_free          330
-
-#endif /* _UAPI__ASM_AVR32_UNISTD_H */
diff --git a/arch/avr32/kernel/.gitignore b/arch/avr32/kernel/.gitignore
deleted file mode 100644
index c5f676c3c224..000000000000
--- a/arch/avr32/kernel/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-vmlinux.lds
diff --git a/arch/avr32/kernel/Makefile b/arch/avr32/kernel/Makefile
deleted file mode 100644
index 119a2e41defe..000000000000
--- a/arch/avr32/kernel/Makefile
+++ /dev/null
@@ -1,15 +0,0 @@
-#
-# Makefile for the Linux/AVR32 kernel.
-#
-
-extra-y				:= head.o vmlinux.lds
-
-obj-$(CONFIG_SUBARCH_AVR32B)	+= entry-avr32b.o
-obj-y				+= syscall_table.o syscall-stubs.o irq.o
-obj-y				+= setup.o traps.o ocd.o ptrace.o
-obj-y				+= signal.o process.o time.o
-obj-y				+= switch_to.o cpu.o
-obj-$(CONFIG_MODULES)		+= module.o avr32_ksyms.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
-obj-$(CONFIG_NMI_DEBUGGING)	+= nmi_debug.o
diff --git a/arch/avr32/kernel/asm-offsets.c b/arch/avr32/kernel/asm-offsets.c
deleted file mode 100644
index 2c9764fe3532..000000000000
--- a/arch/avr32/kernel/asm-offsets.c
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed
- * to extract and format the required data.
- */
-
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/thread_info.h>
-#include <linux/kbuild.h>
-
-void foo(void)
-{
-	OFFSET(TI_task, thread_info, task);
-	OFFSET(TI_flags, thread_info, flags);
-	OFFSET(TI_cpu, thread_info, cpu);
-	OFFSET(TI_preempt_count, thread_info, preempt_count);
-	OFFSET(TI_rar_saved, thread_info, rar_saved);
-	OFFSET(TI_rsr_saved, thread_info, rsr_saved);
-	BLANK();
-	OFFSET(TSK_active_mm, task_struct, active_mm);
-	BLANK();
-	OFFSET(MM_pgd, mm_struct, pgd);
-}
diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c
deleted file mode 100644
index 0d05fd095468..000000000000
--- a/arch/avr32/kernel/avr32_ksyms.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Export AVR32-specific functions for loadable modules.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/module.h>
-
-#include <asm/checksum.h>
-#include <linux/uaccess.h>
-
-/*
- * GCC functions
- */
-extern unsigned long long __avr32_lsl64(unsigned long long u, unsigned long b);
-extern unsigned long long __avr32_lsr64(unsigned long long u, unsigned long b);
-extern unsigned long long __avr32_asr64(unsigned long long u, unsigned long b);
-EXPORT_SYMBOL(__avr32_lsl64);
-EXPORT_SYMBOL(__avr32_lsr64);
-EXPORT_SYMBOL(__avr32_asr64);
-
-/*
- * String functions
- */
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-
-EXPORT_SYMBOL(clear_page);
-EXPORT_SYMBOL(copy_page);
-
-/*
- * Userspace access stuff.
- */
-EXPORT_SYMBOL(___copy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(__copy_user);
-EXPORT_SYMBOL(strncpy_from_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(clear_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(strnlen_user);
-
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_generic);
-
-/* Delay loops (lib/delay.S) */
-EXPORT_SYMBOL(__ndelay);
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__const_udelay);
-
-/* Bit operations (lib/findbit.S) */
-EXPORT_SYMBOL(find_first_zero_bit);
-EXPORT_SYMBOL(find_next_zero_bit);
-EXPORT_SYMBOL(find_first_bit);
-EXPORT_SYMBOL(find_next_bit);
-EXPORT_SYMBOL(find_next_bit_le);
-EXPORT_SYMBOL(find_next_zero_bit_le);
-
-/* I/O primitives (lib/io-*.S) */
-EXPORT_SYMBOL(__raw_readsb);
-EXPORT_SYMBOL(__raw_readsw);
-EXPORT_SYMBOL(__raw_readsl);
-EXPORT_SYMBOL(__raw_writesb);
-EXPORT_SYMBOL(__raw_writesw);
-EXPORT_SYMBOL(__raw_writesl);
diff --git a/arch/avr32/kernel/cpu.c b/arch/avr32/kernel/cpu.c
deleted file mode 100644
index 0341ae27c9ec..000000000000
--- a/arch/avr32/kernel/cpu.c
+++ /dev/null
@@ -1,410 +0,0 @@
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/seq_file.h>
-#include <linux/cpu.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/param.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-
-#include <asm/setup.h>
-#include <asm/sysreg.h>
-
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-
-#ifdef CONFIG_PERFORMANCE_COUNTERS
-
-/*
- * XXX: If/when a SMP-capable implementation of AVR32 will ever be
- * made, we must make sure that the code executes on the correct CPU.
- */
-static ssize_t show_pc0event(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	unsigned long pccr;
-
-	pccr = sysreg_read(PCCR);
-	return sprintf(buf, "0x%lx\n", (pccr >> 12) & 0x3f);
-}
-static ssize_t store_pc0event(struct device *dev,
-			struct device_attribute *attr, const char *buf,
-			      size_t count)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-	if (val > 0x3f)
-		return -EINVAL;
-	val = (val << 12) | (sysreg_read(PCCR) & 0xfffc0fff);
-	sysreg_write(PCCR, val);
-	return count;
-}
-static ssize_t show_pc0count(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	unsigned long pcnt0;
-
-	pcnt0 = sysreg_read(PCNT0);
-	return sprintf(buf, "%lu\n", pcnt0);
-}
-static ssize_t store_pc0count(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-	sysreg_write(PCNT0, val);
-
-	return count;
-}
-
-static ssize_t show_pc1event(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	unsigned long pccr;
-
-	pccr = sysreg_read(PCCR);
-	return sprintf(buf, "0x%lx\n", (pccr >> 18) & 0x3f);
-}
-static ssize_t store_pc1event(struct device *dev,
-			      struct device_attribute *attr, const char *buf,
-			      size_t count)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-	if (val > 0x3f)
-		return -EINVAL;
-	val = (val << 18) | (sysreg_read(PCCR) & 0xff03ffff);
-	sysreg_write(PCCR, val);
-	return count;
-}
-static ssize_t show_pc1count(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	unsigned long pcnt1;
-
-	pcnt1 = sysreg_read(PCNT1);
-	return sprintf(buf, "%lu\n", pcnt1);
-}
-static ssize_t store_pc1count(struct device *dev,
-				struct device_attribute *attr, const char *buf,
-			      size_t count)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-	sysreg_write(PCNT1, val);
-
-	return count;
-}
-
-static ssize_t show_pccycles(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	unsigned long pccnt;
-
-	pccnt = sysreg_read(PCCNT);
-	return sprintf(buf, "%lu\n", pccnt);
-}
-static ssize_t store_pccycles(struct device *dev,
-				struct device_attribute *attr, const char *buf,
-			      size_t count)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-	sysreg_write(PCCNT, val);
-
-	return count;
-}
-
-static ssize_t show_pcenable(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	unsigned long pccr;
-
-	pccr = sysreg_read(PCCR);
-	return sprintf(buf, "%c\n", (pccr & 1)?'1':'0');
-}
-static ssize_t store_pcenable(struct device *dev,
-			      struct device_attribute *attr, const char *buf,
-			      size_t count)
-{
-	unsigned long pccr, val;
-	int ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-	if (val)
-		val = 1;
-
-	pccr = sysreg_read(PCCR);
-	pccr = (pccr & ~1UL) | val;
-	sysreg_write(PCCR, pccr);
-
-	return count;
-}
-
-static DEVICE_ATTR(pc0event, 0600, show_pc0event, store_pc0event);
-static DEVICE_ATTR(pc0count, 0600, show_pc0count, store_pc0count);
-static DEVICE_ATTR(pc1event, 0600, show_pc1event, store_pc1event);
-static DEVICE_ATTR(pc1count, 0600, show_pc1count, store_pc1count);
-static DEVICE_ATTR(pccycles, 0600, show_pccycles, store_pccycles);
-static DEVICE_ATTR(pcenable, 0600, show_pcenable, store_pcenable);
-
-#endif /* CONFIG_PERFORMANCE_COUNTERS */
-
-static int __init topology_init(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct cpu *c = &per_cpu(cpu_devices, cpu);
-
-		register_cpu(c, cpu);
-
-#ifdef CONFIG_PERFORMANCE_COUNTERS
-		device_create_file(&c->dev, &dev_attr_pc0event);
-		device_create_file(&c->dev, &dev_attr_pc0count);
-		device_create_file(&c->dev, &dev_attr_pc1event);
-		device_create_file(&c->dev, &dev_attr_pc1count);
-		device_create_file(&c->dev, &dev_attr_pccycles);
-		device_create_file(&c->dev, &dev_attr_pcenable);
-#endif
-	}
-
-	return 0;
-}
-
-subsys_initcall(topology_init);
-
-struct chip_id_map {
-	u16	mid;
-	u16	pn;
-	const char *name;
-};
-
-static const struct chip_id_map chip_names[] = {
-	{ .mid = 0x1f, .pn = 0x1e82, .name = "AT32AP700x" },
-};
-#define NR_CHIP_NAMES ARRAY_SIZE(chip_names)
-
-static const char *cpu_names[] = {
-	"Morgan",
-	"AP7",
-};
-#define NR_CPU_NAMES ARRAY_SIZE(cpu_names)
-
-static const char *arch_names[] = {
-	"AVR32A",
-	"AVR32B",
-};
-#define NR_ARCH_NAMES ARRAY_SIZE(arch_names)
-
-static const char *mmu_types[] = {
-	"No MMU",
-	"ITLB and DTLB",
-	"Shared TLB",
-	"MPU"
-};
-
-static const char *cpu_feature_flags[] = {
-	"rmw", "dsp", "simd", "ocd", "perfctr", "java", "fpu",
-};
-
-static const char *get_chip_name(struct avr32_cpuinfo *cpu)
-{
-	unsigned int i;
-	unsigned int mid = avr32_get_manufacturer_id(cpu);
-	unsigned int pn = avr32_get_product_number(cpu);
-
-	for (i = 0; i < NR_CHIP_NAMES; i++) {
-		if (chip_names[i].mid == mid && chip_names[i].pn == pn)
-			return chip_names[i].name;
-	}
-
-	return "(unknown)";
-}
-
-void __init setup_processor(void)
-{
-	unsigned long config0, config1;
-	unsigned long features;
-	unsigned cpu_id, cpu_rev, arch_id, arch_rev, mmu_type;
-	unsigned device_id;
-	unsigned tmp;
-	unsigned i;
-
-	config0 = sysreg_read(CONFIG0);
-	config1 = sysreg_read(CONFIG1);
-	cpu_id = SYSREG_BFEXT(PROCESSORID, config0);
-	cpu_rev = SYSREG_BFEXT(PROCESSORREVISION, config0);
-	arch_id = SYSREG_BFEXT(AT, config0);
-	arch_rev = SYSREG_BFEXT(AR, config0);
-	mmu_type = SYSREG_BFEXT(MMUT, config0);
-
-	device_id = ocd_read(DID);
-
-	boot_cpu_data.arch_type = arch_id;
-	boot_cpu_data.cpu_type = cpu_id;
-	boot_cpu_data.arch_revision = arch_rev;
-	boot_cpu_data.cpu_revision = cpu_rev;
-	boot_cpu_data.tlb_config = mmu_type;
-	boot_cpu_data.device_id = device_id;
-
-	tmp = SYSREG_BFEXT(ILSZ, config1);
-	if (tmp) {
-		boot_cpu_data.icache.ways = 1 << SYSREG_BFEXT(IASS, config1);
-		boot_cpu_data.icache.sets = 1 << SYSREG_BFEXT(ISET, config1);
-		boot_cpu_data.icache.linesz = 1 << (tmp + 1);
-	}
-	tmp = SYSREG_BFEXT(DLSZ, config1);
-	if (tmp) {
-		boot_cpu_data.dcache.ways = 1 << SYSREG_BFEXT(DASS, config1);
-		boot_cpu_data.dcache.sets = 1 << SYSREG_BFEXT(DSET, config1);
-		boot_cpu_data.dcache.linesz = 1 << (tmp + 1);
-	}
-
-	if ((cpu_id >= NR_CPU_NAMES) || (arch_id >= NR_ARCH_NAMES)) {
-		printk ("Unknown CPU configuration (ID %02x, arch %02x), "
-			"continuing anyway...\n",
-			cpu_id, arch_id);
-		return;
-	}
-
-	printk ("CPU: %s chip revision %c\n", get_chip_name(&boot_cpu_data),
-			avr32_get_chip_revision(&boot_cpu_data) + 'A');
-	printk ("CPU: %s [%02x] core revision %d (%s arch revision %d)\n",
-		cpu_names[cpu_id], cpu_id, cpu_rev,
-		arch_names[arch_id], arch_rev);
-	printk ("CPU: MMU configuration: %s\n", mmu_types[mmu_type]);
-
-	printk ("CPU: features:");
-	features = 0;
-	if (config0 & SYSREG_BIT(CONFIG0_R))
-		features |= AVR32_FEATURE_RMW;
-	if (config0 & SYSREG_BIT(CONFIG0_D))
-		features |= AVR32_FEATURE_DSP;
-	if (config0 & SYSREG_BIT(CONFIG0_S))
-		features |= AVR32_FEATURE_SIMD;
-	if (config0 & SYSREG_BIT(CONFIG0_O))
-		features |= AVR32_FEATURE_OCD;
-	if (config0 & SYSREG_BIT(CONFIG0_P))
-		features |= AVR32_FEATURE_PCTR;
-	if (config0 & SYSREG_BIT(CONFIG0_J))
-		features |= AVR32_FEATURE_JAVA;
-	if (config0 & SYSREG_BIT(CONFIG0_F))
-		features |= AVR32_FEATURE_FPU;
-
-	for (i = 0; i < ARRAY_SIZE(cpu_feature_flags); i++)
-		if (features & (1 << i))
-			printk(" %s", cpu_feature_flags[i]);
-
-	printk("\n");
-	boot_cpu_data.features = features;
-}
-
-#ifdef CONFIG_PROC_FS
-static int c_show(struct seq_file *m, void *v)
-{
-	unsigned int icache_size, dcache_size;
-	unsigned int cpu = smp_processor_id();
-	unsigned int freq;
-	unsigned int i;
-
-	icache_size = boot_cpu_data.icache.ways *
-		boot_cpu_data.icache.sets *
-		boot_cpu_data.icache.linesz;
-	dcache_size = boot_cpu_data.dcache.ways *
-		boot_cpu_data.dcache.sets *
-		boot_cpu_data.dcache.linesz;
-
-	seq_printf(m, "processor\t: %d\n", cpu);
-
-	seq_printf(m, "chip type\t: %s revision %c\n",
-			get_chip_name(&boot_cpu_data),
-			avr32_get_chip_revision(&boot_cpu_data) + 'A');
-	if (boot_cpu_data.arch_type < NR_ARCH_NAMES)
-		seq_printf(m, "cpu arch\t: %s revision %d\n",
-			   arch_names[boot_cpu_data.arch_type],
-			   boot_cpu_data.arch_revision);
-	if (boot_cpu_data.cpu_type < NR_CPU_NAMES)
-		seq_printf(m, "cpu core\t: %s revision %d\n",
-			   cpu_names[boot_cpu_data.cpu_type],
-			   boot_cpu_data.cpu_revision);
-
-	freq = (clk_get_rate(boot_cpu_data.clk) + 500) / 1000;
-	seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, freq % 1000);
-
-	seq_printf(m, "i-cache\t\t: %dK (%u ways x %u sets x %u)\n",
-		   icache_size >> 10,
-		   boot_cpu_data.icache.ways,
-		   boot_cpu_data.icache.sets,
-		   boot_cpu_data.icache.linesz);
-	seq_printf(m, "d-cache\t\t: %dK (%u ways x %u sets x %u)\n",
-		   dcache_size >> 10,
-		   boot_cpu_data.dcache.ways,
-		   boot_cpu_data.dcache.sets,
-		   boot_cpu_data.dcache.linesz);
-
-	seq_printf(m, "features\t:");
-	for (i = 0; i < ARRAY_SIZE(cpu_feature_flags); i++)
-		if (boot_cpu_data.features & (1 << i))
-			seq_printf(m, " %s", cpu_feature_flags[i]);
-
-	seq_printf(m, "\nbogomips\t: %lu.%02lu\n",
-		   boot_cpu_data.loops_per_jiffy / (500000/HZ),
-		   (boot_cpu_data.loops_per_jiffy / (5000/HZ)) % 100);
-
-	return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
-	return *pos < 1 ? (void *)1 : NULL;
-}
-
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	++*pos;
-	return NULL;
-}
-
-static void c_stop(struct seq_file *m, void *v)
-{
-
-}
-
-const struct seq_operations cpuinfo_op = {
-	.start	= c_start,
-	.next	= c_next,
-	.stop	= c_stop,
-	.show	= c_show
-};
-#endif /* CONFIG_PROC_FS */
diff --git a/arch/avr32/kernel/entry-avr32b.S b/arch/avr32/kernel/entry-avr32b.S
deleted file mode 100644
index 7301f4806bbe..000000000000
--- a/arch/avr32/kernel/entry-avr32b.S
+++ /dev/null
@@ -1,877 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * This file contains the low-level entry-points into the kernel, that is,
- * exception handlers, debug trap handlers, interrupt handlers and the
- * system call handler.
- */
-#include <linux/errno.h>
-
-#include <asm/asm.h>
-#include <asm/hardirq.h>
-#include <asm/irq.h>
-#include <asm/ocd.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/ptrace.h>
-#include <asm/sysreg.h>
-#include <asm/thread_info.h>
-#include <asm/unistd.h>
-
-#ifdef CONFIG_PREEMPT
-# define preempt_stop		mask_interrupts
-#else
-# define preempt_stop
-# define fault_resume_kernel	fault_restore_all
-#endif
-
-#define __MASK(x)	((1 << (x)) - 1)
-#define IRQ_MASK	((__MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) | \
-			 (__MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT))
-
-	.section .ex.text,"ax",@progbits
-	.align	2
-exception_vectors:
-	bral	handle_critical
-	.align	2
-	bral	handle_critical
-	.align	2
-	bral	do_bus_error_write
-	.align	2
-	bral	do_bus_error_read
-	.align	2
-	bral	do_nmi_ll
-	.align	2
-	bral	handle_address_fault
-	.align	2
-	bral	handle_protection_fault
-	.align	2
-	bral	handle_debug
-	.align	2
-	bral	do_illegal_opcode_ll
-	.align	2
-	bral	do_illegal_opcode_ll
-	.align	2
-	bral	do_illegal_opcode_ll
-	.align	2
-	bral	do_fpe_ll
-	.align	2
-	bral	do_illegal_opcode_ll
-	.align	2
-	bral	handle_address_fault
-	.align	2
-	bral	handle_address_fault
-	.align	2
-	bral	handle_protection_fault
-	.align	2
-	bral	handle_protection_fault
-	.align	2
-	bral	do_dtlb_modified
-
-#define	tlbmiss_save	pushm	r0-r3
-#define tlbmiss_restore	popm	r0-r3
-
-	.org	0x50
-	.global	itlb_miss
-itlb_miss:
-	tlbmiss_save
-	rjmp	tlb_miss_common
-
-	.org	0x60
-dtlb_miss_read:
-	tlbmiss_save
-	rjmp	tlb_miss_common
-
-	.org	0x70
-dtlb_miss_write:
-	tlbmiss_save
-
-	.global	tlb_miss_common
-	.align	2
-tlb_miss_common:
-	mfsr	r0, SYSREG_TLBEAR
-	mfsr	r1, SYSREG_PTBR
-
-	/*
-	 * First level lookup: The PGD contains virtual pointers to
-	 * the second-level page tables, but they may be NULL if not
-	 * present.
-	 */
-pgtbl_lookup:
-	lsr	r2, r0, PGDIR_SHIFT
-	ld.w	r3, r1[r2 << 2]
-	bfextu	r1, r0, PAGE_SHIFT, PGDIR_SHIFT - PAGE_SHIFT
-	cp.w	r3, 0
-	breq	page_table_not_present
-
-	/* Second level lookup */
-	ld.w	r2, r3[r1 << 2]
-	mfsr	r0, SYSREG_TLBARLO
-	bld	r2, _PAGE_BIT_PRESENT
-	brcc	page_not_present
-
-	/* Mark the page as accessed */
-	sbr	r2, _PAGE_BIT_ACCESSED
-	st.w	r3[r1 << 2], r2
-
-	/* Drop software flags */
-	andl	r2, _PAGE_FLAGS_HARDWARE_MASK & 0xffff
-	mtsr	SYSREG_TLBELO, r2
-
-	/* Figure out which entry we want to replace */
-	mfsr	r1, SYSREG_MMUCR
-	clz	r2, r0
-	brcc	1f
-	mov	r3, -1			/* All entries have been accessed, */
-	mov	r2, 0			/* so start at 0 */
-	mtsr	SYSREG_TLBARLO, r3	/* and reset TLBAR */
-
-1:	bfins	r1, r2, SYSREG_DRP_OFFSET, SYSREG_DRP_SIZE
-	mtsr	SYSREG_MMUCR, r1
-	tlbw
-
-	tlbmiss_restore
-	rete
-
-	/* The slow path of the TLB miss handler */
-	.align	2
-page_table_not_present:
-	/* Do we need to synchronize with swapper_pg_dir? */
-	bld	r0, 31
-	brcs	sync_with_swapper_pg_dir
-
-page_not_present:
-	tlbmiss_restore
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	mfsr	r12, SYSREG_ECR
-	mov	r11, sp
-	call	do_page_fault
-	rjmp	ret_from_exception
-
-	.align	2
-sync_with_swapper_pg_dir:
-	/*
-	 * If swapper_pg_dir contains a non-NULL second-level page
-	 * table pointer, copy it into the current PGD. If not, we
-	 * must handle it as a full-blown page fault.
-	 *
-	 * Jumping back to pgtbl_lookup causes an unnecessary lookup,
-	 * but it is guaranteed to be a cache hit, it won't happen
-	 * very often, and we absolutely do not want to sacrifice any
-	 * performance in the fast path in order to improve this.
-	 */
-	mov	r1, lo(swapper_pg_dir)
-	orh	r1, hi(swapper_pg_dir)
-	ld.w	r3, r1[r2 << 2]
-	cp.w	r3, 0
-	breq	page_not_present
-	mfsr	r1, SYSREG_PTBR
-	st.w	r1[r2 << 2], r3
-	rjmp	pgtbl_lookup
-
-	/*
-	 * We currently have two bytes left at this point until we
-	 * crash into the system call handler...
-	 *
-	 * Don't worry, the assembler will let us know.
-	 */
-
-
-	/* ---                    System Call                    --- */
-
-	.org	0x100
-system_call:
-#ifdef CONFIG_PREEMPT
-	mask_interrupts
-#endif
-	pushm	r12		/* r12_orig */
-	stmts	--sp, r0-lr
-
-	mfsr	r0, SYSREG_RAR_SUP
-	mfsr	r1, SYSREG_RSR_SUP
-#ifdef CONFIG_PREEMPT
-	unmask_interrupts
-#endif
-	zero_fp
-	stm	--sp, r0-r1
-
-	/* check for syscall tracing */
-	get_thread_info r0
-	ld.w	r1, r0[TI_flags]
-	bld	r1, TIF_SYSCALL_TRACE
-	brcs	syscall_trace_enter
-
-syscall_trace_cont:
-	cp.w	r8, NR_syscalls
-	brhs	syscall_badsys
-
-	lddpc   lr, syscall_table_addr
-	ld.w    lr, lr[r8 << 2]
-	mov	r8, r5		/* 5th argument (6th is pushed by stub) */
-	icall   lr
-
-	.global	syscall_return
-syscall_return:
-	get_thread_info r0
-	mask_interrupts		/* make sure we don't miss an interrupt
-				   setting need_resched or sigpending
-				   between sampling and the rets */
-
-	/* Store the return value so that the correct value is loaded below */
-	stdsp   sp[REG_R12], r12
-
-	ld.w	r1, r0[TI_flags]
-	andl	r1, _TIF_ALLWORK_MASK, COH
-	brne	syscall_exit_work
-
-syscall_exit_cont:
-	popm	r8-r9
-	mtsr	SYSREG_RAR_SUP, r8
-	mtsr	SYSREG_RSR_SUP, r9
-	ldmts	sp++, r0-lr
-	sub	sp, -4		/* r12_orig */
-	rets
-
-	.align	2
-syscall_table_addr:
-	.long   sys_call_table
-
-syscall_badsys:
-	mov	r12, -ENOSYS
-	rjmp	syscall_return
-
-	.global ret_from_fork
-ret_from_fork:
-	call   schedule_tail
-	mov	r12, 0
-	rjmp	syscall_return
-
-	.global ret_from_kernel_thread
-ret_from_kernel_thread:
-	call   schedule_tail
-	mov	r12, r0
-	mov	lr, r2	/* syscall_return */
-	mov	pc, r1
-
-syscall_trace_enter:
-	pushm	r8-r12
-	call	syscall_trace
-	popm	r8-r12
-	rjmp	syscall_trace_cont
-
-syscall_exit_work:
-	bld	r1, TIF_SYSCALL_TRACE
-	brcc	1f
-	unmask_interrupts
-	call	syscall_trace
-	mask_interrupts
-	ld.w	r1, r0[TI_flags]
-
-1:	bld	r1, TIF_NEED_RESCHED
-	brcc	2f
-	unmask_interrupts
-	call	schedule
-	mask_interrupts
-	ld.w	r1, r0[TI_flags]
-	rjmp	1b
-
-2:	mov	r2, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME
-	tst	r1, r2
-	breq	3f
-	unmask_interrupts
-	mov	r12, sp
-	mov	r11, r0
-	call	do_notify_resume
-	mask_interrupts
-	ld.w	r1, r0[TI_flags]
-	rjmp	1b
-
-3:	bld	r1, TIF_BREAKPOINT
-	brcc	syscall_exit_cont
-	rjmp	enter_monitor_mode
-
-	/* This function expects to find offending PC in SYSREG_RAR_EX */
-	.type	save_full_context_ex, @function
-	.align	2
-save_full_context_ex:
-	mfsr	r11, SYSREG_RAR_EX
-	sub	r9, pc, . - debug_trampoline
-	mfsr	r8, SYSREG_RSR_EX
-	cp.w	r9, r11
-	breq	3f
-	mov	r12, r8
-	andh	r8, (MODE_MASK >> 16), COH
-	brne	2f
-
-1:	pushm	r11, r12	/* PC and SR */
-	unmask_exceptions
-	ret	r12
-
-2:	sub	r10, sp, -(FRAME_SIZE_FULL - REG_LR)
-	stdsp	sp[4], r10	/* replace saved SP */
-	rjmp	1b
-
-	/*
-	 * The debug handler set up a trampoline to make us
-	 * automatically enter monitor mode upon return, but since
-	 * we're saving the full context, we must assume that the
-	 * exception handler might want to alter the return address
-	 * and/or status register. So we need to restore the original
-	 * context and enter monitor mode manually after the exception
-	 * has been handled.
-	 */
-3:	get_thread_info r8
-	ld.w	r11, r8[TI_rar_saved]
-	ld.w	r12, r8[TI_rsr_saved]
-	rjmp	1b
-	.size	save_full_context_ex, . - save_full_context_ex
-
-	/* Low-level exception handlers */
-handle_critical:
-	/*
-	 * AT32AP700x errata:
-	 *
-	 * After a Java stack overflow or underflow trap, any CPU
-	 * memory access may cause erratic behavior. This will happen
-	 * when the four least significant bits of the JOSP system
-	 * register contains any value between 9 and 15 (inclusive).
-	 *
-	 * Possible workarounds:
-	 *   - Don't use the Java Extension Module
-	 *   - Ensure that the stack overflow and underflow trap
-	 *     handlers do not do any memory access or trigger any
-	 *     exceptions before the overflow/underflow condition is
-	 *     cleared (by incrementing or decrementing the JOSP)
-	 *   - Make sure that JOSP does not contain any problematic
-	 *     value before doing any exception or interrupt
-	 *     processing.
-	 *   - Set up a critical exception handler which writes a
-	 *     known-to-be-safe value, e.g. 4, to JOSP before doing
-	 *     any further processing.
-	 *
-	 * We'll use the last workaround for now since we cannot
-	 * guarantee that user space processes don't use Java mode.
-	 * Non-well-behaving userland will be terminated with extreme
-	 * prejudice.
-	 */
-#ifdef CONFIG_CPU_AT32AP700X
-	/*
-	 * There's a chance we can't touch memory, so temporarily
-	 * borrow PTBR to save the stack pointer while we fix things
-	 * up...
-	 */
-	mtsr	SYSREG_PTBR, sp
-	mov	sp, 4
-	mtsr	SYSREG_JOSP, sp
-	mfsr	sp, SYSREG_PTBR
-	sub	pc, -2
-
-	/* Push most of pt_regs on stack. We'll do the rest later */
-	sub	sp, 4
-	pushm	r0-r12
-
-	/* PTBR mirrors current_thread_info()->task->active_mm->pgd */
-	get_thread_info r0
-	ld.w	r1, r0[TI_task]
-	ld.w	r2, r1[TSK_active_mm]
-	ld.w	r3, r2[MM_pgd]
-	mtsr	SYSREG_PTBR, r3
-#else
-	sub	sp, 4
-	pushm	r0-r12
-#endif
-	sub	r0, sp, -(14 * 4)
-	mov	r1, lr
-	mfsr	r2, SYSREG_RAR_EX
-	mfsr	r3, SYSREG_RSR_EX
-	pushm	r0-r3
-
-	mfsr	r12, SYSREG_ECR
-	mov	r11, sp
-	call	do_critical_exception
-
-	/* We should never get here... */
-bad_return:
-	sub	r12, pc, (. - 1f)
-	lddpc	pc, 2f
-	.align	2
-1:	.asciz	"Return from critical exception!"
-2:	.long	panic
-
-	.align	1
-do_bus_error_write:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	mov	r11, 1
-	rjmp	1f
-
-do_bus_error_read:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	mov	r11, 0
-1:	mfsr	r12, SYSREG_BEAR
-	mov	r10, sp
-	call	do_bus_error
-	rjmp	ret_from_exception
-
-	.align	1
-do_nmi_ll:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	mfsr	r9, SYSREG_RSR_NMI
-	mfsr	r8, SYSREG_RAR_NMI
-	bfextu	r0, r9, MODE_SHIFT, 3
-	brne	2f
-
-1:	pushm	r8, r9	/* PC and SR */
-	mfsr	r12, SYSREG_ECR
-	mov	r11, sp
-	call	do_nmi
-	popm	r8-r9
-	mtsr	SYSREG_RAR_NMI, r8
-	tst	r0, r0
-	mtsr	SYSREG_RSR_NMI, r9
-	brne	3f
-
-	ldmts	sp++, r0-lr
-	sub	sp, -4		/* skip r12_orig */
-	rete
-
-2:	sub	r10, sp, -(FRAME_SIZE_FULL - REG_LR)
-	stdsp	sp[4], r10	/* replace saved SP */
-	rjmp	1b
-
-3:	popm	lr
-	sub	sp, -4		/* skip sp */
-	popm	r0-r12
-	sub	sp, -4		/* skip r12_orig */
-	rete
-
-handle_address_fault:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	mfsr	r12, SYSREG_ECR
-	mov	r11, sp
-	call	do_address_exception
-	rjmp	ret_from_exception
-
-handle_protection_fault:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	mfsr	r12, SYSREG_ECR
-	mov	r11, sp
-	call	do_page_fault
-	rjmp	ret_from_exception
-
-	.align	1
-do_illegal_opcode_ll:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	mfsr	r12, SYSREG_ECR
-	mov	r11, sp
-	call	do_illegal_opcode
-	rjmp	ret_from_exception
-
-do_dtlb_modified:
-	pushm	r0-r3
-	mfsr	r1, SYSREG_TLBEAR
-	mfsr	r0, SYSREG_PTBR
-	lsr	r2, r1, PGDIR_SHIFT
-	ld.w	r0, r0[r2 << 2]
-	lsl	r1, (32 - PGDIR_SHIFT)
-	lsr	r1, (32 - PGDIR_SHIFT) + PAGE_SHIFT
-
-	/* Translate to virtual address in P1 */
-	andl	r0, 0xf000
-	sbr	r0, 31
-	add	r2, r0, r1 << 2
-	ld.w	r3, r2[0]
-	sbr	r3, _PAGE_BIT_DIRTY
-	mov	r0, r3
-	st.w	r2[0], r3
-
-	/* The page table is up-to-date. Update the TLB entry as well */
-	andl	r0, lo(_PAGE_FLAGS_HARDWARE_MASK)
-	mtsr	SYSREG_TLBELO, r0
-
-	/* MMUCR[DRP] is updated automatically, so let's go... */
-	tlbw
-
-	popm	r0-r3
-	rete
-
-do_fpe_ll:
-	sub	sp, 4
-	stmts	--sp, r0-lr
-	call	save_full_context_ex
-	unmask_interrupts
-	mov	r12, 26
-	mov	r11, sp
-	call	do_fpe
-	rjmp	ret_from_exception
-
-ret_from_exception:
-	mask_interrupts
-	lddsp	r4, sp[REG_SR]
-
-	andh	r4, (MODE_MASK >> 16), COH
-	brne	fault_resume_kernel
-
-	get_thread_info r0
-	ld.w	r1, r0[TI_flags]
-	andl	r1, _TIF_WORK_MASK, COH
-	brne	fault_exit_work
-
-fault_resume_user:
-	popm	r8-r9
-	mask_exceptions
-	mtsr	SYSREG_RAR_EX, r8
-	mtsr	SYSREG_RSR_EX, r9
-	ldmts	sp++, r0-lr
-	sub	sp, -4
-	rete
-
-fault_resume_kernel:
-#ifdef CONFIG_PREEMPT
-	get_thread_info	r0
-	ld.w	r2, r0[TI_preempt_count]
-	cp.w	r2, 0
-	brne	1f
-	ld.w	r1, r0[TI_flags]
-	bld	r1, TIF_NEED_RESCHED
-	brcc	1f
-	lddsp	r4, sp[REG_SR]
-	bld	r4, SYSREG_GM_OFFSET
-	brcs	1f
-	call	preempt_schedule_irq
-1:
-#endif
-
-	popm	r8-r9
-	mask_exceptions
-	mfsr	r1, SYSREG_SR
-	mtsr	SYSREG_RAR_EX, r8
-	mtsr	SYSREG_RSR_EX, r9
-	popm	lr
-	sub	sp, -4		/* ignore SP */
-	popm	r0-r12
-	sub	sp, -4		/* ignore r12_orig */
-	rete
-
-irq_exit_work:
-	/* Switch to exception mode so that we can share the same code. */
-	mfsr	r8, SYSREG_SR
-	cbr	r8, SYSREG_M0_OFFSET
-	orh	r8, hi(SYSREG_BIT(M1) | SYSREG_BIT(M2))
-	mtsr	SYSREG_SR, r8
-	sub	pc, -2
-	get_thread_info r0
-	ld.w	r1, r0[TI_flags]
-
-fault_exit_work:
-	bld	r1, TIF_NEED_RESCHED
-	brcc	1f
-	unmask_interrupts
-	call	schedule
-	mask_interrupts
-	ld.w	r1, r0[TI_flags]
-	rjmp	fault_exit_work
-
-1:	mov	r2, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME
-	tst	r1, r2
-	breq	2f
-	unmask_interrupts
-	mov	r12, sp
-	mov	r11, r0
-	call	do_notify_resume
-	mask_interrupts
-	ld.w	r1, r0[TI_flags]
-	rjmp	fault_exit_work
-
-2:	bld	r1, TIF_BREAKPOINT
-	brcc	fault_resume_user
-	rjmp	enter_monitor_mode
-
-	.section .kprobes.text, "ax", @progbits
-	.type	handle_debug, @function
-handle_debug:
-	sub	sp, 4		/* r12_orig */
-	stmts	--sp, r0-lr
-	mfsr	r8, SYSREG_RAR_DBG
-	mfsr	r9, SYSREG_RSR_DBG
-	unmask_exceptions
-	pushm	r8-r9
-	bfextu	r9, r9, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
-	brne	debug_fixup_regs
-
-.Ldebug_fixup_cont:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	call	trace_hardirqs_off
-#endif
-	mov	r12, sp
-	call	do_debug
-	mov	sp, r12
-
-	lddsp	r2, sp[REG_SR]
-	bfextu	r3, r2, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
-	brne	debug_resume_kernel
-
-	get_thread_info r0
-	ld.w	r1, r0[TI_flags]
-	mov	r2, _TIF_DBGWORK_MASK
-	tst	r1, r2
-	brne	debug_exit_work
-
-	bld	r1, TIF_SINGLE_STEP
-	brcc	1f
-	mfdr	r4, OCD_DC
-	sbr	r4, OCD_DC_SS_BIT
-	mtdr	OCD_DC, r4
-
-1:	popm	r10,r11
-	mask_exceptions
-	mtsr	SYSREG_RSR_DBG, r11
-	mtsr	SYSREG_RAR_DBG, r10
-#ifdef CONFIG_TRACE_IRQFLAGS
-	call	trace_hardirqs_on
-1:
-#endif
-	ldmts	sp++, r0-lr
-	sub	sp, -4
-	retd
-	.size	handle_debug, . - handle_debug
-
-	/* Mode of the trapped context is in r9 */
-	.type	debug_fixup_regs, @function
-debug_fixup_regs:
-	mfsr	r8, SYSREG_SR
-	mov	r10, r8
-	bfins	r8, r9, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
-	mtsr	SYSREG_SR, r8
-	sub	pc, -2
-	stdsp	sp[REG_LR], lr
-	mtsr	SYSREG_SR, r10
-	sub	pc, -2
-	sub	r8, sp, -FRAME_SIZE_FULL
-	stdsp	sp[REG_SP], r8
-	rjmp	.Ldebug_fixup_cont
-	.size	debug_fixup_regs, . - debug_fixup_regs
-
-	.type	debug_resume_kernel, @function
-debug_resume_kernel:
-	mask_exceptions
-	popm	r10, r11
-	mtsr	SYSREG_RAR_DBG, r10
-	mtsr	SYSREG_RSR_DBG, r11
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bld	r11, SYSREG_GM_OFFSET
-	brcc	1f
-	call	trace_hardirqs_on
-1:
-#endif
-	mfsr	r2, SYSREG_SR
-	mov	r1, r2
-	bfins	r2, r3, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
-	mtsr	SYSREG_SR, r2
-	sub	pc, -2
-	popm	lr
-	mtsr	SYSREG_SR, r1
-	sub	pc, -2
-	sub	sp, -4		/* skip SP */
-	popm	r0-r12
-	sub	sp, -4
-	retd
-	.size	debug_resume_kernel, . - debug_resume_kernel
-
-	.type	debug_exit_work, @function
-debug_exit_work:
-	/*
-	 * We must return from Monitor Mode using a retd, and we must
-	 * not schedule since that involves the D bit in SR getting
-	 * cleared by something other than the debug hardware. This
-	 * may cause undefined behaviour according to the Architecture
-	 * manual.
-	 *
-	 * So we fix up the return address and status and return to a
-	 * stub below in Exception mode. From there, we can follow the
-	 * normal exception return path.
-	 *
-	 * The real return address and status registers are stored on
-	 * the stack in the way the exception return path understands,
-	 * so no need to fix anything up there.
-	 */
-	sub	r8, pc, . - fault_exit_work
-	mtsr	SYSREG_RAR_DBG, r8
-	mov	r9, 0
-	orh	r9, hi(SR_EM | SR_GM | MODE_EXCEPTION)
-	mtsr	SYSREG_RSR_DBG, r9
-	sub	pc, -2
-	retd
-	.size	debug_exit_work, . - debug_exit_work
-
-	.set	rsr_int0,	SYSREG_RSR_INT0
-	.set	rsr_int1,	SYSREG_RSR_INT1
-	.set	rsr_int2,	SYSREG_RSR_INT2
-	.set	rsr_int3,	SYSREG_RSR_INT3
-	.set	rar_int0,	SYSREG_RAR_INT0
-	.set	rar_int1,	SYSREG_RAR_INT1
-	.set	rar_int2,	SYSREG_RAR_INT2
-	.set	rar_int3,	SYSREG_RAR_INT3
-
-	.macro	IRQ_LEVEL level
-	.type	irq_level\level, @function
-irq_level\level:
-	sub	sp, 4		/* r12_orig */
-	stmts	--sp,r0-lr
-	mfsr	r8, rar_int\level
-	mfsr	r9, rsr_int\level
-
-#ifdef CONFIG_PREEMPT
-	sub	r11, pc, (. - system_call)
-	cp.w	r11, r8
-	breq	4f
-#endif
-
-	pushm	r8-r9
-
-	mov	r11, sp
-	mov	r12, \level
-
-	call	do_IRQ
-
-	lddsp	r4, sp[REG_SR]
-	bfextu	r4, r4, SYSREG_M0_OFFSET, 3
-	cp.w	r4, MODE_SUPERVISOR >> SYSREG_M0_OFFSET
-	breq	2f
-	cp.w	r4, MODE_USER >> SYSREG_M0_OFFSET
-#ifdef CONFIG_PREEMPT
-	brne	3f
-#else
-	brne	1f
-#endif
-
-	get_thread_info	r0
-	ld.w	r1, r0[TI_flags]
-	andl	r1, _TIF_WORK_MASK, COH
-	brne	irq_exit_work
-
-1:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	call	trace_hardirqs_on
-#endif
-	popm	r8-r9
-	mtsr	rar_int\level, r8
-	mtsr	rsr_int\level, r9
-	ldmts	sp++,r0-lr
-	sub	sp, -4		/* ignore r12_orig */
-	rete
-
-#ifdef CONFIG_PREEMPT
-4:	mask_interrupts
-	mfsr	r8, rsr_int\level
-	sbr	r8, 16
-	mtsr	rsr_int\level, r8
-	ldmts	sp++, r0-lr
-	sub	sp, -4		/* ignore r12_orig */
-	rete
-#endif
-
-2:	get_thread_info	r0
-	ld.w	r1, r0[TI_flags]
-	bld	r1, TIF_CPU_GOING_TO_SLEEP
-#ifdef CONFIG_PREEMPT
-	brcc	3f
-#else
-	brcc	1b
-#endif
-	sub	r1, pc, . - cpu_idle_skip_sleep
-	stdsp	sp[REG_PC], r1
-#ifdef CONFIG_PREEMPT
-3:	get_thread_info r0
-	ld.w	r2, r0[TI_preempt_count]
-	cp.w	r2, 0
-	brne	1b
-	ld.w	r1, r0[TI_flags]
-	bld	r1, TIF_NEED_RESCHED
-	brcc	1b
-	lddsp	r4, sp[REG_SR]
-	bld	r4, SYSREG_GM_OFFSET
-	brcs	1b
-	call	preempt_schedule_irq
-#endif
-	rjmp	1b
-	.endm
-
-	.section .irq.text,"ax",@progbits
-
-	.global	irq_level0
-	.global	irq_level1
-	.global	irq_level2
-	.global	irq_level3
-	IRQ_LEVEL 0
-	IRQ_LEVEL 1
-	IRQ_LEVEL 2
-	IRQ_LEVEL 3
-
-	.section .kprobes.text, "ax", @progbits
-	.type	enter_monitor_mode, @function
-enter_monitor_mode:
-	/*
-	 * We need to enter monitor mode to do a single step. The
-	 * monitor code will alter the return address so that we
-	 * return directly to the user instead of returning here.
-	 */
-	breakpoint
-	rjmp	breakpoint_failed
-
-	.size	enter_monitor_mode, . - enter_monitor_mode
-
-	.type	debug_trampoline, @function
-	.global	debug_trampoline
-debug_trampoline:
-	/*
-	 * Save the registers on the stack so that the monitor code
-	 * can find them easily.
-	 */
-	sub	sp, 4		/* r12_orig */
-	stmts	--sp, r0-lr
-	get_thread_info	r0
-	ld.w	r8, r0[TI_rar_saved]
-	ld.w	r9, r0[TI_rsr_saved]
-	pushm	r8-r9
-
-	/*
-	 * The monitor code will alter the return address so we don't
-	 * return here.
-	 */
-	breakpoint
-	rjmp	breakpoint_failed
-	.size	debug_trampoline, . - debug_trampoline
-
-	.type breakpoint_failed, @function
-breakpoint_failed:
-	/*
-	 * Something went wrong. Perhaps the debug hardware isn't
-	 * enabled?
-	 */
-	lda.w	r12, msg_breakpoint_failed
-	mov	r11, sp
-	mov	r10, 9		/* SIGKILL */
-	call	die
-1:	rjmp	1b
-
-msg_breakpoint_failed:
-	.asciz	"Failed to enter Debug Mode"
diff --git a/arch/avr32/kernel/head.S b/arch/avr32/kernel/head.S
deleted file mode 100644
index 59eae6dfbed2..000000000000
--- a/arch/avr32/kernel/head.S
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Non-board-specific low-level startup code
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-
-#include <asm/page.h>
-
-	.section .init.text,"ax"
-	.global kernel_entry
-kernel_entry:
-	/* Start the show */
-	lddpc   pc, kernel_start_addr
-
-	.align  2
-kernel_start_addr:
-	.long   start_kernel
diff --git a/arch/avr32/kernel/irq.c b/arch/avr32/kernel/irq.c
deleted file mode 100644
index 900e49b2258b..000000000000
--- a/arch/avr32/kernel/irq.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on arch/i386/kernel/irq.c
- *   Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/device.h>
-
-/* May be overridden by platform code */
-int __weak nmi_enable(void)
-{
-	return -ENOSYS;
-}
-
-void __weak nmi_disable(void)
-{
-
-}
diff --git a/arch/avr32/kernel/kprobes.c b/arch/avr32/kernel/kprobes.c
deleted file mode 100644
index a94ece4a72c8..000000000000
--- a/arch/avr32/kernel/kprobes.c
+++ /dev/null
@@ -1,267 +0,0 @@
-/*
- *  Kernel Probes (KProbes)
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * Based on arch/ppc64/kernel/kprobes.c
- *  Copyright (C) IBM Corporation, 2002, 2004
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-
-#include <asm/cacheflush.h>
-#include <linux/kdebug.h>
-#include <asm/ocd.h>
-
-DEFINE_PER_CPU(struct kprobe *, current_kprobe);
-static unsigned long kprobe_status;
-static struct pt_regs jprobe_saved_regs;
-
-struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
-
-int __kprobes arch_prepare_kprobe(struct kprobe *p)
-{
-	int ret = 0;
-
-	if ((unsigned long)p->addr & 0x01) {
-		printk("Attempt to register kprobe at an unaligned address\n");
-		ret = -EINVAL;
-	}
-
-	/* XXX: Might be a good idea to check if p->addr is a valid
-	 * kernel address as well... */
-
-	if (!ret) {
-		pr_debug("copy kprobe at %p\n", p->addr);
-		memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-		p->opcode = *p->addr;
-	}
-
-	return ret;
-}
-
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
-	pr_debug("arming kprobe at %p\n", p->addr);
-	ocd_enable(NULL);
-	*p->addr = BREAKPOINT_INSTRUCTION;
-	flush_icache_range((unsigned long)p->addr,
-			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-void __kprobes arch_disarm_kprobe(struct kprobe *p)
-{
-	pr_debug("disarming kprobe at %p\n", p->addr);
-	ocd_disable(NULL);
-	*p->addr = p->opcode;
-	flush_icache_range((unsigned long)p->addr,
-			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
-{
-	unsigned long dc;
-
-	pr_debug("preparing to singlestep over %p (PC=%08lx)\n",
-		 p->addr, regs->pc);
-
-	BUG_ON(!(sysreg_read(SR) & SYSREG_BIT(SR_D)));
-
-	dc = ocd_read(DC);
-	dc |= 1 << OCD_DC_SS_BIT;
-	ocd_write(DC, dc);
-
-	/*
-	 * We must run the instruction from its original location
-	 * since it may actually reference PC.
-	 *
-	 * TODO: Do the instruction replacement directly in icache.
-	 */
-	*p->addr = p->opcode;
-	flush_icache_range((unsigned long)p->addr,
-			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
-{
-	unsigned long dc;
-
-	pr_debug("resuming execution at PC=%08lx\n", regs->pc);
-
-	dc = ocd_read(DC);
-	dc &= ~(1 << OCD_DC_SS_BIT);
-	ocd_write(DC, dc);
-
-	*p->addr = BREAKPOINT_INSTRUCTION;
-	flush_icache_range((unsigned long)p->addr,
-			   (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-static void __kprobes set_current_kprobe(struct kprobe *p)
-{
-	__this_cpu_write(current_kprobe, p);
-}
-
-static int __kprobes kprobe_handler(struct pt_regs *regs)
-{
-	struct kprobe *p;
-	void *addr = (void *)regs->pc;
-	int ret = 0;
-
-	pr_debug("kprobe_handler: kprobe_running=%p\n",
-		 kprobe_running());
-
-	/*
-	 * We don't want to be preempted for the entire
-	 * duration of kprobe processing
-	 */
-	preempt_disable();
-
-	/* Check that we're not recursing */
-	if (kprobe_running()) {
-		p = get_kprobe(addr);
-		if (p) {
-			if (kprobe_status == KPROBE_HIT_SS) {
-				printk("FIXME: kprobe hit while single-stepping!\n");
-				goto no_kprobe;
-			}
-
-			printk("FIXME: kprobe hit while handling another kprobe\n");
-			goto no_kprobe;
-		} else {
-			p = kprobe_running();
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
-		}
-		/* If it's not ours, can't be delete race, (we hold lock). */
-		goto no_kprobe;
-	}
-
-	p = get_kprobe(addr);
-	if (!p)
-		goto no_kprobe;
-
-	kprobe_status = KPROBE_HIT_ACTIVE;
-	set_current_kprobe(p);
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/* handler has already set things up, so skip ss setup */
-		return 1;
-
-ss_probe:
-	prepare_singlestep(p, regs);
-	kprobe_status = KPROBE_HIT_SS;
-	return 1;
-
-no_kprobe:
-	preempt_enable_no_resched();
-	return ret;
-}
-
-static int __kprobes post_kprobe_handler(struct pt_regs *regs)
-{
-	struct kprobe *cur = kprobe_running();
-
-	pr_debug("post_kprobe_handler, cur=%p\n", cur);
-
-	if (!cur)
-		return 0;
-
-	if (cur->post_handler) {
-		kprobe_status = KPROBE_HIT_SSDONE;
-		cur->post_handler(cur, regs, 0);
-	}
-
-	resume_execution(cur, regs);
-	reset_current_kprobe();
-	preempt_enable_no_resched();
-
-	return 1;
-}
-
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
-{
-	struct kprobe *cur = kprobe_running();
-
-	pr_debug("kprobe_fault_handler: trapnr=%d\n", trapnr);
-
-	if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-		return 1;
-
-	if (kprobe_status & KPROBE_HIT_SS) {
-		resume_execution(cur, regs);
-		preempt_enable_no_resched();
-	}
-	return 0;
-}
-
-/*
- * Wrapper routine to for handling exceptions.
- */
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-				       unsigned long val, void *data)
-{
-	struct die_args *args = (struct die_args *)data;
-	int ret = NOTIFY_DONE;
-
-	pr_debug("kprobe_exceptions_notify: val=%lu, data=%p\n",
-		 val, data);
-
-	switch (val) {
-	case DIE_BREAKPOINT:
-		if (kprobe_handler(args->regs))
-			ret = NOTIFY_STOP;
-		break;
-	case DIE_SSTEP:
-		if (post_kprobe_handler(args->regs))
-			ret = NOTIFY_STOP;
-		break;
-	default:
-		break;
-	}
-
-	return ret;
-}
-
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	memcpy(&jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/*
-	 * TODO: We should probably save some of the stack here as
-	 * well, since gcc may pass arguments on the stack for certain
-	 * functions (lots of arguments, large aggregates, varargs)
-	 */
-
-	/* setup return addr to the jprobe handler routine */
-	regs->pc = (unsigned long)jp->entry;
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	asm volatile("breakpoint" ::: "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	/*
-	 * FIXME - we should ideally be validating that we got here 'cos
-	 * of the "trap" in jprobe_return() above, before restoring the
-	 * saved regs...
-	 */
-	memcpy(regs, &jprobe_saved_regs, sizeof(struct pt_regs));
-	return 1;
-}
-
-int __init arch_init_kprobes(void)
-{
-	/* TODO: Register kretprobe trampoline */
-	return 0;
-}
diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c
deleted file mode 100644
index 2b4c54c04cb6..000000000000
--- a/arch/avr32/kernel/module.c
+++ /dev/null
@@ -1,291 +0,0 @@
-/*
- * AVR32-specific kernel module loader
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * GOT initialization parts are based on the s390 version
- *   Copyright (C) 2002, 2003 IBM Deutschland Entwicklung GmbH,
- *                            IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/bug.h>
-#include <linux/elf.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleloader.h>
-#include <linux/vmalloc.h>
-
-void module_arch_freeing_init(struct module *mod)
-{
-	vfree(mod->arch.syminfo);
-	mod->arch.syminfo = NULL;
-}
-
-static inline int check_rela(Elf32_Rela *rela, struct module *module,
-			     char *strings, Elf32_Sym *symbols)
-{
-	struct mod_arch_syminfo *info;
-
-	info = module->arch.syminfo + ELF32_R_SYM(rela->r_info);
-	switch (ELF32_R_TYPE(rela->r_info)) {
-	case R_AVR32_GOT32:
-	case R_AVR32_GOT16:
-	case R_AVR32_GOT8:
-	case R_AVR32_GOT21S:
-	case R_AVR32_GOT18SW:	/* mcall */
-	case R_AVR32_GOT16S:	/* ld.w */
-		if (rela->r_addend != 0) {
-			printk(KERN_ERR
-			       "GOT relocation against %s at offset %u with addend\n",
-			       strings + symbols[ELF32_R_SYM(rela->r_info)].st_name,
-			       rela->r_offset);
-			return -ENOEXEC;
-		}
-		if (info->got_offset == -1UL) {
-			info->got_offset = module->arch.got_size;
-			module->arch.got_size += sizeof(void *);
-		}
-		pr_debug("GOT[%3lu] %s\n", info->got_offset,
-			 strings + symbols[ELF32_R_SYM(rela->r_info)].st_name);
-		break;
-	}
-
-	return 0;
-}
-
-int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
-			      char *secstrings, struct module *module)
-{
-	Elf32_Shdr *symtab;
-	Elf32_Sym *symbols;
-	Elf32_Rela *rela;
-	char *strings;
-	int nrela, i, j;
-	int ret;
-
-	/* Find the symbol table */
-	symtab = NULL;
-	for (i = 0; i < hdr->e_shnum; i++)
-		switch (sechdrs[i].sh_type) {
-		case SHT_SYMTAB:
-			symtab = &sechdrs[i];
-			break;
-		}
-	if (!symtab) {
-		printk(KERN_ERR "module %s: no symbol table\n", module->name);
-		return -ENOEXEC;
-	}
-
-	/* Allocate room for one syminfo structure per symbol. */
-	module->arch.nsyms = symtab->sh_size / sizeof(Elf_Sym);
-	module->arch.syminfo = vmalloc(module->arch.nsyms
-				   * sizeof(struct mod_arch_syminfo));
-	if (!module->arch.syminfo)
-		return -ENOMEM;
-
-	symbols = (void *)hdr + symtab->sh_offset;
-	strings = (void *)hdr + sechdrs[symtab->sh_link].sh_offset;
-	for (i = 0; i < module->arch.nsyms; i++) {
-		if (symbols[i].st_shndx == SHN_UNDEF &&
-		    strcmp(strings + symbols[i].st_name,
-			   "_GLOBAL_OFFSET_TABLE_") == 0)
-			/* "Define" it as absolute. */
-			symbols[i].st_shndx = SHN_ABS;
-		module->arch.syminfo[i].got_offset = -1UL;
-		module->arch.syminfo[i].got_initialized = 0;
-	}
-
-	/* Allocate GOT entries for symbols that need it. */
-	module->arch.got_size = 0;
-	for (i = 0; i < hdr->e_shnum; i++) {
-		if (sechdrs[i].sh_type != SHT_RELA)
-			continue;
-		nrela = sechdrs[i].sh_size / sizeof(Elf32_Rela);
-		rela = (void *)hdr + sechdrs[i].sh_offset;
-		for (j = 0; j < nrela; j++) {
-			ret = check_rela(rela + j, module,
-					 strings, symbols);
-			if (ret)
-				goto out_free_syminfo;
-		}
-	}
-
-	/*
-	 * Increase core size to make room for GOT and set start
-	 * offset for GOT.
-	 */
-	module->core_layout.size = ALIGN(module->core_layout.size, 4);
-	module->arch.got_offset = module->core_layout.size;
-	module->core_layout.size += module->arch.got_size;
-
-	return 0;
-
-out_free_syminfo:
-	vfree(module->arch.syminfo);
-	module->arch.syminfo = NULL;
-
-	return ret;
-}
-
-static inline int reloc_overflow(struct module *module, const char *reloc_name,
-				 Elf32_Addr relocation)
-{
-	printk(KERN_ERR "module %s: Value %lx does not fit relocation %s\n",
-	       module->name, (unsigned long)relocation, reloc_name);
-	return -ENOEXEC;
-}
-
-#define get_u16(loc)		(*((uint16_t *)loc))
-#define put_u16(loc, val)	(*((uint16_t *)loc) = (val))
-
-int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
-		       unsigned int symindex, unsigned int relindex,
-		       struct module *module)
-{
-	Elf32_Shdr *symsec = sechdrs + symindex;
-	Elf32_Shdr *relsec = sechdrs + relindex;
-	Elf32_Shdr *dstsec = sechdrs + relsec->sh_info;
-	Elf32_Rela *rel = (void *)relsec->sh_addr;
-	unsigned int i;
-	int ret = 0;
-
-	for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rela); i++, rel++) {
-		struct mod_arch_syminfo *info;
-		Elf32_Sym *sym;
-		Elf32_Addr relocation;
-		uint32_t *location;
-		uint32_t value;
-
-		location = (void *)dstsec->sh_addr + rel->r_offset;
-		sym = (Elf32_Sym *)symsec->sh_addr + ELF32_R_SYM(rel->r_info);
-		relocation = sym->st_value + rel->r_addend;
-
-		info = module->arch.syminfo + ELF32_R_SYM(rel->r_info);
-
-		/* Initialize GOT entry if necessary */
-		switch (ELF32_R_TYPE(rel->r_info)) {
-		case R_AVR32_GOT32:
-		case R_AVR32_GOT16:
-		case R_AVR32_GOT8:
-		case R_AVR32_GOT21S:
-		case R_AVR32_GOT18SW:
-		case R_AVR32_GOT16S:
-			if (!info->got_initialized) {
-				Elf32_Addr *gotent;
-
-				gotent = (module->core_layout.base
-					  + module->arch.got_offset
-					  + info->got_offset);
-				*gotent = relocation;
-				info->got_initialized = 1;
-			}
-
-			relocation = info->got_offset;
-			break;
-		}
-
-		switch (ELF32_R_TYPE(rel->r_info)) {
-		case R_AVR32_32:
-		case R_AVR32_32_CPENT:
-			*location = relocation;
-			break;
-		case R_AVR32_22H_PCREL:
-			relocation -= (Elf32_Addr)location;
-			if ((relocation & 0xffe00001) != 0
-			    && (relocation & 0xffc00001) != 0xffc00000)
-				return reloc_overflow(module,
-						      "R_AVR32_22H_PCREL",
-						      relocation);
-			relocation >>= 1;
-
-			value = *location;
-			value = ((value & 0xe1ef0000)
-				 | (relocation & 0xffff)
-				 | ((relocation & 0x10000) << 4)
-				 | ((relocation & 0x1e0000) << 8));
-			*location = value;
-			break;
-		case R_AVR32_11H_PCREL:
-			relocation -= (Elf32_Addr)location;
-			if ((relocation & 0xfffffc01) != 0
-			    && (relocation & 0xfffff801) != 0xfffff800)
-				return reloc_overflow(module,
-						      "R_AVR32_11H_PCREL",
-						      relocation);
-			value = get_u16(location);
-			value = ((value & 0xf00c)
-				 | ((relocation & 0x1fe) << 3)
-				 | ((relocation & 0x600) >> 9));
-			put_u16(location, value);
-			break;
-		case R_AVR32_9H_PCREL:
-			relocation -= (Elf32_Addr)location;
-			if ((relocation & 0xffffff01) != 0
-			    && (relocation & 0xfffffe01) != 0xfffffe00)
-				return reloc_overflow(module,
-						      "R_AVR32_9H_PCREL",
-						      relocation);
-			value = get_u16(location);
-			value = ((value & 0xf00f)
-				 | ((relocation & 0x1fe) << 3));
-			put_u16(location, value);
-			break;
-		case R_AVR32_9UW_PCREL:
-			relocation -= ((Elf32_Addr)location) & 0xfffffffc;
-			if ((relocation & 0xfffffc03) != 0)
-				return reloc_overflow(module,
-						      "R_AVR32_9UW_PCREL",
-						      relocation);
-			value = get_u16(location);
-			value = ((value & 0xf80f)
-				 | ((relocation & 0x1fc) << 2));
-			put_u16(location, value);
-			break;
-		case R_AVR32_GOTPC:
-			/*
-			 * R6 = PC - (PC - GOT)
-			 *
-			 * At this point, relocation contains the
-			 * value of PC.  Just subtract the value of
-			 * GOT, and we're done.
-			 */
-			pr_debug("GOTPC: PC=0x%x, got_offset=0x%lx, core=0x%p\n",
-				 relocation, module->arch.got_offset,
-				 module->core_layout.base);
-			relocation -= ((unsigned long)module->core_layout.base
-				       + module->arch.got_offset);
-			*location = relocation;
-			break;
-		case R_AVR32_GOT18SW:
-			if ((relocation & 0xfffe0003) != 0
-			    && (relocation & 0xfffc0000) != 0xfffc0000)
-				return reloc_overflow(module, "R_AVR32_GOT18SW",
-						     relocation);
-			relocation >>= 2;
-			/* fall through */
-		case R_AVR32_GOT16S:
-			if ((relocation & 0xffff8000) != 0
-			    && (relocation & 0xffff0000) != 0xffff0000)
-				return reloc_overflow(module, "R_AVR32_GOT16S",
-						      relocation);
-			pr_debug("GOT reloc @ 0x%x -> %u\n",
-				 rel->r_offset, relocation);
-			value = *location;
-			value = ((value & 0xffff0000)
-				 | (relocation & 0xffff));
-			*location = value;
-			break;
-
-		default:
-			printk(KERN_ERR "module %s: Unknown relocation: %u\n",
-			       module->name, ELF32_R_TYPE(rel->r_info));
-			return -ENOEXEC;
-		}
-	}
-
-	return ret;
-}
diff --git a/arch/avr32/kernel/nmi_debug.c b/arch/avr32/kernel/nmi_debug.c
deleted file mode 100644
index 25823049bb99..000000000000
--- a/arch/avr32/kernel/nmi_debug.c
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/delay.h>
-#include <linux/kdebug.h>
-#include <linux/notifier.h>
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-
-#include <asm/irq.h>
-
-enum nmi_action {
-	NMI_SHOW_STATE	= 1 << 0,
-	NMI_SHOW_REGS	= 1 << 1,
-	NMI_DIE		= 1 << 2,
-	NMI_DEBOUNCE	= 1 << 3,
-};
-
-static unsigned long nmi_actions;
-
-static int nmi_debug_notify(struct notifier_block *self,
-		unsigned long val, void *data)
-{
-	struct die_args *args = data;
-
-	if (likely(val != DIE_NMI))
-		return NOTIFY_DONE;
-
-	if (nmi_actions & NMI_SHOW_STATE)
-		show_state();
-	if (nmi_actions & NMI_SHOW_REGS)
-		show_regs(args->regs);
-	if (nmi_actions & NMI_DEBOUNCE)
-		mdelay(10);
-	if (nmi_actions & NMI_DIE)
-		return NOTIFY_BAD;
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block nmi_debug_nb = {
-	.notifier_call = nmi_debug_notify,
-};
-
-static int __init nmi_debug_setup(char *str)
-{
-	char *p, *sep;
-
-	register_die_notifier(&nmi_debug_nb);
-	if (nmi_enable()) {
-		printk(KERN_WARNING "Unable to enable NMI.\n");
-		return 0;
-	}
-
-	if (*str != '=')
-		return 0;
-
-	for (p = str + 1; *p; p = sep + 1) {
-		sep = strchr(p, ',');
-		if (sep)
-			*sep = 0;
-		if (strcmp(p, "state") == 0)
-			nmi_actions |= NMI_SHOW_STATE;
-		else if (strcmp(p, "regs") == 0)
-			nmi_actions |= NMI_SHOW_REGS;
-		else if (strcmp(p, "debounce") == 0)
-			nmi_actions |= NMI_DEBOUNCE;
-		else if (strcmp(p, "die") == 0)
-			nmi_actions |= NMI_DIE;
-		else
-			printk(KERN_WARNING "NMI: Unrecognized action `%s'\n",
-				p);
-		if (!sep)
-			break;
-	}
-
-	return 0;
-}
-__setup("nmi_debug", nmi_debug_setup);
diff --git a/arch/avr32/kernel/ocd.c b/arch/avr32/kernel/ocd.c
deleted file mode 100644
index 1b0245d4e0ca..000000000000
--- a/arch/avr32/kernel/ocd.c
+++ /dev/null
@@ -1,167 +0,0 @@
-/*
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-
-#include <asm/ocd.h>
-
-static long ocd_count;
-static spinlock_t ocd_lock;
-
-/**
- * ocd_enable - enable on-chip debugging
- * @child: task to be debugged
- *
- * If @child is non-NULL, ocd_enable() first checks if debugging has
- * already been enabled for @child, and if it has, does nothing.
- *
- * If @child is NULL (e.g. when debugging the kernel), or debugging
- * has not already been enabled for it, ocd_enable() increments the
- * reference count and enables the debugging hardware.
- */
-void ocd_enable(struct task_struct *child)
-{
-	u32 dc;
-
-	if (child)
-		pr_debug("ocd_enable: child=%s [%u]\n",
-				child->comm, child->pid);
-	else
-		pr_debug("ocd_enable (no child)\n");
-
-	if (!child || !test_and_set_tsk_thread_flag(child, TIF_DEBUG)) {
-		spin_lock(&ocd_lock);
-		ocd_count++;
-		dc = ocd_read(DC);
-		dc |= (1 << OCD_DC_MM_BIT) | (1 << OCD_DC_DBE_BIT);
-		ocd_write(DC, dc);
-		spin_unlock(&ocd_lock);
-	}
-}
-
-/**
- * ocd_disable - disable on-chip debugging
- * @child: task that was being debugged, but isn't anymore
- *
- * If @child is non-NULL, ocd_disable() checks if debugging is enabled
- * for @child, and if it isn't, does nothing.
- *
- * If @child is NULL (e.g. when debugging the kernel), or debugging is
- * enabled, ocd_disable() decrements the reference count, and if it
- * reaches zero, disables the debugging hardware.
- */
-void ocd_disable(struct task_struct *child)
-{
-	u32 dc;
-
-	if (!child)
-		pr_debug("ocd_disable (no child)\n");
-	else if (test_tsk_thread_flag(child, TIF_DEBUG))
-		pr_debug("ocd_disable: child=%s [%u]\n",
-				child->comm, child->pid);
-
-	if (!child || test_and_clear_tsk_thread_flag(child, TIF_DEBUG)) {
-		spin_lock(&ocd_lock);
-		ocd_count--;
-
-		WARN_ON(ocd_count < 0);
-
-		if (ocd_count <= 0) {
-			dc = ocd_read(DC);
-			dc &= ~((1 << OCD_DC_MM_BIT) | (1 << OCD_DC_DBE_BIT));
-			ocd_write(DC, dc);
-		}
-		spin_unlock(&ocd_lock);
-	}
-}
-
-#ifdef CONFIG_DEBUG_FS
-#include <linux/debugfs.h>
-#include <linux/module.h>
-
-static struct dentry *ocd_debugfs_root;
-static struct dentry *ocd_debugfs_DC;
-static struct dentry *ocd_debugfs_DS;
-static struct dentry *ocd_debugfs_count;
-
-static int ocd_DC_get(void *data, u64 *val)
-{
-	*val = ocd_read(DC);
-	return 0;
-}
-static int ocd_DC_set(void *data, u64 val)
-{
-	ocd_write(DC, val);
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_DC, ocd_DC_get, ocd_DC_set, "0x%08llx\n");
-
-static int ocd_DS_get(void *data, u64 *val)
-{
-	*val = ocd_read(DS);
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_DS, ocd_DS_get, NULL, "0x%08llx\n");
-
-static int ocd_count_get(void *data, u64 *val)
-{
-	*val = ocd_count;
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_count, ocd_count_get, NULL, "%lld\n");
-
-static void ocd_debugfs_init(void)
-{
-	struct dentry *root;
-
-	root = debugfs_create_dir("ocd", NULL);
-	if (IS_ERR(root) || !root)
-		goto err_root;
-	ocd_debugfs_root = root;
-
-	ocd_debugfs_DC = debugfs_create_file("DC", S_IRUSR | S_IWUSR,
-				root, NULL, &fops_DC);
-	if (!ocd_debugfs_DC)
-		goto err_DC;
-
-	ocd_debugfs_DS = debugfs_create_file("DS", S_IRUSR, root,
-				NULL, &fops_DS);
-	if (!ocd_debugfs_DS)
-		goto err_DS;
-
-	ocd_debugfs_count = debugfs_create_file("count", S_IRUSR, root,
-				NULL, &fops_count);
-	if (!ocd_debugfs_count)
-		goto err_count;
-
-	return;
-
-err_count:
-	debugfs_remove(ocd_debugfs_DS);
-err_DS:
-	debugfs_remove(ocd_debugfs_DC);
-err_DC:
-	debugfs_remove(ocd_debugfs_root);
-err_root:
-	printk(KERN_WARNING "OCD: Failed to create debugfs entries\n");
-}
-#else
-static inline void ocd_debugfs_init(void)
-{
-
-}
-#endif
-
-static int __init ocd_init(void)
-{
-	spin_lock_init(&ocd_lock);
-	ocd_debugfs_init();
-	return 0;
-}
-arch_initcall(ocd_init);
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
deleted file mode 100644
index ad0dfccedb79..000000000000
--- a/arch/avr32/kernel/process.c
+++ /dev/null
@@ -1,358 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/task.h>
-#include <linux/sched/task_stack.h>
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/fs.h>
-#include <linux/pm.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/reboot.h>
-#include <linux/tick.h>
-#include <linux/uaccess.h>
-#include <linux/unistd.h>
-
-#include <asm/sysreg.h>
-#include <asm/ocd.h>
-#include <asm/syscalls.h>
-
-#include <mach/pm.h>
-
-void (*pm_power_off)(void);
-EXPORT_SYMBOL(pm_power_off);
-
-/*
- * This file handles the architecture-dependent parts of process handling..
- */
-
-void arch_cpu_idle(void)
-{
-	cpu_enter_idle();
-}
-
-void machine_halt(void)
-{
-	/*
-	 * Enter Stop mode. The 32 kHz oscillator will keep running so
-	 * the RTC will keep the time properly and the system will
-	 * boot quickly.
-	 */
-	asm volatile("sleep 3\n\t"
-		     "sub pc, -2");
-}
-
-void machine_power_off(void)
-{
-	if (pm_power_off)
-		pm_power_off();
-}
-
-void machine_restart(char *cmd)
-{
-	ocd_write(DC, (1 << OCD_DC_DBE_BIT));
-	ocd_write(DC, (1 << OCD_DC_RES_BIT));
-	while (1) ;
-}
-
-/*
- * Free current thread data structures etc
- */
-void exit_thread(struct task_struct *tsk)
-{
-	ocd_disable(tsk);
-}
-
-void flush_thread(void)
-{
-	/* nothing to do */
-}
-
-void release_thread(struct task_struct *dead_task)
-{
-	/* do nothing */
-}
-
-static void dump_mem(const char *str, const char *log_lvl,
-		     unsigned long bottom, unsigned long top)
-{
-	unsigned long p;
-	int i;
-
-	printk("%s%s(0x%08lx to 0x%08lx)\n", log_lvl, str, bottom, top);
-
-	for (p = bottom & ~31; p < top; ) {
-		printk("%s%04lx: ", log_lvl, p & 0xffff);
-
-		for (i = 0; i < 8; i++, p += 4) {
-			unsigned int val;
-
-			if (p < bottom || p >= top)
-				printk("         ");
-			else {
-				if (__get_user(val, (unsigned int __user *)p)) {
-					printk("\n");
-					goto out;
-				}
-				printk("%08x ", val);
-			}
-		}
-		printk("\n");
-	}
-
-out:
-	return;
-}
-
-static inline int valid_stack_ptr(struct thread_info *tinfo, unsigned long p)
-{
-	return (p > (unsigned long)tinfo)
-		&& (p < (unsigned long)tinfo + THREAD_SIZE - 3);
-}
-
-#ifdef CONFIG_FRAME_POINTER
-static void show_trace_log_lvl(struct task_struct *tsk, unsigned long *sp,
-			       struct pt_regs *regs, const char *log_lvl)
-{
-	unsigned long lr, fp;
-	struct thread_info *tinfo;
-
-	if (regs)
-		fp = regs->r7;
-	else if (tsk == current)
-		asm("mov %0, r7" : "=r"(fp));
-	else
-		fp = tsk->thread.cpu_context.r7;
-
-	/*
-	 * Walk the stack as long as the frame pointer (a) is within
-	 * the kernel stack of the task, and (b) it doesn't move
-	 * downwards.
-	 */
-	tinfo = task_thread_info(tsk);
-	printk("%sCall trace:\n", log_lvl);
-	while (valid_stack_ptr(tinfo, fp)) {
-		unsigned long new_fp;
-
-		lr = *(unsigned long *)fp;
-#ifdef CONFIG_KALLSYMS
-		printk("%s [<%08lx>] ", log_lvl, lr);
-#else
-		printk(" [<%08lx>] ", lr);
-#endif
-		print_symbol("%s\n", lr);
-
-		new_fp = *(unsigned long *)(fp + 4);
-		if (new_fp <= fp)
-			break;
-		fp = new_fp;
-	}
-	printk("\n");
-}
-#else
-static void show_trace_log_lvl(struct task_struct *tsk, unsigned long *sp,
-			       struct pt_regs *regs, const char *log_lvl)
-{
-	unsigned long addr;
-
-	printk("%sCall trace:\n", log_lvl);
-
-	while (!kstack_end(sp)) {
-		addr = *sp++;
-		if (kernel_text_address(addr)) {
-#ifdef CONFIG_KALLSYMS
-			printk("%s [<%08lx>] ", log_lvl, addr);
-#else
-			printk(" [<%08lx>] ", addr);
-#endif
-			print_symbol("%s\n", addr);
-		}
-	}
-	printk("\n");
-}
-#endif
-
-void show_stack_log_lvl(struct task_struct *tsk, unsigned long sp,
-			struct pt_regs *regs, const char *log_lvl)
-{
-	struct thread_info *tinfo;
-
-	if (sp == 0) {
-		if (tsk)
-			sp = tsk->thread.cpu_context.ksp;
-		else
-			sp = (unsigned long)&tinfo;
-	}
-	if (!tsk)
-		tsk = current;
-
-	tinfo = task_thread_info(tsk);
-
-	if (valid_stack_ptr(tinfo, sp)) {
-		dump_mem("Stack: ", log_lvl, sp,
-			 THREAD_SIZE + (unsigned long)tinfo);
-		show_trace_log_lvl(tsk, (unsigned long *)sp, regs, log_lvl);
-	}
-}
-
-void show_stack(struct task_struct *tsk, unsigned long *stack)
-{
-	show_stack_log_lvl(tsk, (unsigned long)stack, NULL, "");
-}
-
-static const char *cpu_modes[] = {
-	"Application", "Supervisor", "Interrupt level 0", "Interrupt level 1",
-	"Interrupt level 2", "Interrupt level 3", "Exception", "NMI"
-};
-
-void show_regs_log_lvl(struct pt_regs *regs, const char *log_lvl)
-{
-	unsigned long sp = regs->sp;
-	unsigned long lr = regs->lr;
-	unsigned long mode = (regs->sr & MODE_MASK) >> MODE_SHIFT;
-
-	show_regs_print_info(log_lvl);
-
-	if (!user_mode(regs)) {
-		sp = (unsigned long)regs + FRAME_SIZE_FULL;
-
-		printk("%s", log_lvl);
-		print_symbol("PC is at %s\n", instruction_pointer(regs));
-		printk("%s", log_lvl);
-		print_symbol("LR is at %s\n", lr);
-	}
-
-	printk("%spc : [<%08lx>]    lr : [<%08lx>]    %s\n"
-	       "%ssp : %08lx  r12: %08lx  r11: %08lx\n",
-	       log_lvl, instruction_pointer(regs), lr, print_tainted(),
-	       log_lvl, sp, regs->r12, regs->r11);
-	printk("%sr10: %08lx  r9 : %08lx  r8 : %08lx\n",
-	       log_lvl, regs->r10, regs->r9, regs->r8);
-	printk("%sr7 : %08lx  r6 : %08lx  r5 : %08lx  r4 : %08lx\n",
-	       log_lvl, regs->r7, regs->r6, regs->r5, regs->r4);
-	printk("%sr3 : %08lx  r2 : %08lx  r1 : %08lx  r0 : %08lx\n",
-	       log_lvl, regs->r3, regs->r2, regs->r1, regs->r0);
-	printk("%sFlags: %c%c%c%c%c\n", log_lvl,
-	       regs->sr & SR_Q ? 'Q' : 'q',
-	       regs->sr & SR_V ? 'V' : 'v',
-	       regs->sr & SR_N ? 'N' : 'n',
-	       regs->sr & SR_Z ? 'Z' : 'z',
-	       regs->sr & SR_C ? 'C' : 'c');
-	printk("%sMode bits: %c%c%c%c%c%c%c%c%c%c\n", log_lvl,
-	       regs->sr & SR_H ? 'H' : 'h',
-	       regs->sr & SR_J ? 'J' : 'j',
-	       regs->sr & SR_DM ? 'M' : 'm',
-	       regs->sr & SR_D ? 'D' : 'd',
-	       regs->sr & SR_EM ? 'E' : 'e',
-	       regs->sr & SR_I3M ? '3' : '.',
-	       regs->sr & SR_I2M ? '2' : '.',
-	       regs->sr & SR_I1M ? '1' : '.',
-	       regs->sr & SR_I0M ? '0' : '.',
-	       regs->sr & SR_GM ? 'G' : 'g');
-	printk("%sCPU Mode: %s\n", log_lvl, cpu_modes[mode]);
-}
-
-void show_regs(struct pt_regs *regs)
-{
-	unsigned long sp = regs->sp;
-
-	if (!user_mode(regs))
-		sp = (unsigned long)regs + FRAME_SIZE_FULL;
-
-	show_regs_log_lvl(regs, "");
-	show_trace_log_lvl(current, (unsigned long *)sp, regs, "");
-}
-EXPORT_SYMBOL(show_regs);
-
-/* Fill in the fpu structure for a core dump. This is easy -- we don't have any */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
-{
-	/* Not valid */
-	return 0;
-}
-
-asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
-asmlinkage void syscall_return(void);
-
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
-		struct task_struct *p)
-{
-	struct pt_regs *childregs = task_pt_regs(p);
-
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		memset(childregs, 0, sizeof(struct pt_regs));
-		p->thread.cpu_context.r0 = arg;
-		p->thread.cpu_context.r1 = usp; /* fn */
-		p->thread.cpu_context.r2 = (unsigned long)syscall_return;
-		p->thread.cpu_context.pc = (unsigned long)ret_from_kernel_thread;
-		childregs->sr = MODE_SUPERVISOR;
-	} else {
-		*childregs = *current_pt_regs();
-		if (usp)
-			childregs->sp = usp;
-		childregs->r12 = 0; /* Set return value for child */
-		p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
-	}
-
-	p->thread.cpu_context.sr = MODE_SUPERVISOR | SR_GM;
-	p->thread.cpu_context.ksp = (unsigned long)childregs;
-
-	clear_tsk_thread_flag(p, TIF_DEBUG);
-	if ((clone_flags & CLONE_PTRACE) && test_thread_flag(TIF_DEBUG))
-		ocd_enable(p);
-
-	return 0;
-}
-
-/*
- * This function is supposed to answer the question "who called
- * schedule()?"
- */
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long pc;
-	unsigned long stack_page;
-
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-
-	stack_page = (unsigned long)task_stack_page(p);
-	BUG_ON(!stack_page);
-
-	/*
-	 * The stored value of PC is either the address right after
-	 * the call to __switch_to() or ret_from_fork.
-	 */
-	pc = thread_saved_pc(p);
-	if (in_sched_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
-		unsigned long fp = p->thread.cpu_context.r7;
-		BUG_ON(fp < stack_page || fp > (THREAD_SIZE + stack_page));
-		pc = *(unsigned long *)fp;
-#else
-		/*
-		 * We depend on the frame size of schedule here, which
-		 * is actually quite ugly. It might be possible to
-		 * determine the frame size automatically at build
-		 * time by doing this:
-		 *   - compile sched/core.c
-		 *   - disassemble the resulting sched.o
-		 *   - look for 'sub sp,??' shortly after '<schedule>:'
-		 */
-		unsigned long sp = p->thread.cpu_context.ksp + 16;
-		BUG_ON(sp < stack_page || sp > (THREAD_SIZE + stack_page));
-		pc = *(unsigned long *)sp;
-#endif
-	}
-
-	return pc;
-}
diff --git a/arch/avr32/kernel/ptrace.c b/arch/avr32/kernel/ptrace.c
deleted file mode 100644
index 41a14e96a1db..000000000000
--- a/arch/avr32/kernel/ptrace.c
+++ /dev/null
@@ -1,357 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/mm.h>
-#include <linux/ptrace.h>
-#include <linux/errno.h>
-#include <linux/user.h>
-#include <linux/security.h>
-#include <linux/unistd.h>
-#include <linux/notifier.h>
-
-#include <asm/traps.h>
-#include <linux/uaccess.h>
-#include <asm/ocd.h>
-#include <asm/mmu_context.h>
-#include <linux/kdebug.h>
-
-static struct pt_regs *get_user_regs(struct task_struct *tsk)
-{
-	return (struct pt_regs *)((unsigned long)task_stack_page(tsk) +
-				  THREAD_SIZE - sizeof(struct pt_regs));
-}
-
-void user_enable_single_step(struct task_struct *tsk)
-{
-	pr_debug("user_enable_single_step: pid=%u, PC=0x%08lx, SR=0x%08lx\n",
-		 tsk->pid, task_pt_regs(tsk)->pc, task_pt_regs(tsk)->sr);
-
-	/*
-	 * We can't schedule in Debug mode, so when TIF_BREAKPOINT is
-	 * set, the system call or exception handler will do a
-	 * breakpoint to enter monitor mode before returning to
-	 * userspace.
-	 *
-	 * The monitor code will then notice that TIF_SINGLE_STEP is
-	 * set and return to userspace with single stepping enabled.
-	 * The CPU will then enter monitor mode again after exactly
-	 * one instruction has been executed, and the monitor code
-	 * will then send a SIGTRAP to the process.
-	 */
-	set_tsk_thread_flag(tsk, TIF_BREAKPOINT);
-	set_tsk_thread_flag(tsk, TIF_SINGLE_STEP);
-}
-
-void user_disable_single_step(struct task_struct *child)
-{
-	/* XXX(hch): a no-op here seems wrong.. */
-}
-
-/*
- * Called by kernel/ptrace.c when detaching
- *
- * Make sure any single step bits, etc. are not set
- */
-void ptrace_disable(struct task_struct *child)
-{
-	clear_tsk_thread_flag(child, TIF_SINGLE_STEP);
-	clear_tsk_thread_flag(child, TIF_BREAKPOINT);
-	ocd_disable(child);
-}
-
-/*
- * Read the word at offset "offset" into the task's "struct user". We
- * actually access the pt_regs struct stored on the kernel stack.
- */
-static int ptrace_read_user(struct task_struct *tsk, unsigned long offset,
-			    unsigned long __user *data)
-{
-	unsigned long *regs;
-	unsigned long value;
-
-	if (offset & 3 || offset >= sizeof(struct user)) {
-		printk("ptrace_read_user: invalid offset 0x%08lx\n", offset);
-		return -EIO;
-	}
-
-	regs = (unsigned long *)get_user_regs(tsk);
-
-	value = 0;
-	if (offset < sizeof(struct pt_regs))
-		value = regs[offset / sizeof(regs[0])];
-
-	pr_debug("ptrace_read_user(%s[%u], %#lx, %p) -> %#lx\n",
-		 tsk->comm, tsk->pid, offset, data, value);
-
-	return put_user(value, data);
-}
-
-/*
- * Write the word "value" to offset "offset" into the task's "struct
- * user". We actually access the pt_regs struct stored on the kernel
- * stack.
- */
-static int ptrace_write_user(struct task_struct *tsk, unsigned long offset,
-			     unsigned long value)
-{
-	unsigned long *regs;
-
-	pr_debug("ptrace_write_user(%s[%u], %#lx, %#lx)\n",
-			tsk->comm, tsk->pid, offset, value);
-
-	if (offset & 3 || offset >= sizeof(struct user)) {
-		pr_debug("  invalid offset 0x%08lx\n", offset);
-		return -EIO;
-	}
-
-	if (offset >= sizeof(struct pt_regs))
-		return 0;
-
-	regs = (unsigned long *)get_user_regs(tsk);
-	regs[offset / sizeof(regs[0])] = value;
-
-	return 0;
-}
-
-static int ptrace_getregs(struct task_struct *tsk, void __user *uregs)
-{
-	struct pt_regs *regs = get_user_regs(tsk);
-
-	return copy_to_user(uregs, regs, sizeof(*regs)) ? -EFAULT : 0;
-}
-
-static int ptrace_setregs(struct task_struct *tsk, const void __user *uregs)
-{
-	struct pt_regs newregs;
-	int ret;
-
-	ret = -EFAULT;
-	if (copy_from_user(&newregs, uregs, sizeof(newregs)) == 0) {
-		struct pt_regs *regs = get_user_regs(tsk);
-
-		ret = -EINVAL;
-		if (valid_user_regs(&newregs)) {
-			*regs = newregs;
-			ret = 0;
-		}
-	}
-
-	return ret;
-}
-
-long arch_ptrace(struct task_struct *child, long request,
-		 unsigned long addr, unsigned long data)
-{
-	int ret;
-	void __user *datap = (void __user *) data;
-
-	switch (request) {
-	/* Read the word at location addr in the child process */
-	case PTRACE_PEEKTEXT:
-	case PTRACE_PEEKDATA:
-		ret = generic_ptrace_peekdata(child, addr, data);
-		break;
-
-	case PTRACE_PEEKUSR:
-		ret = ptrace_read_user(child, addr, datap);
-		break;
-
-	/* Write the word in data at location addr */
-	case PTRACE_POKETEXT:
-	case PTRACE_POKEDATA:
-		ret = generic_ptrace_pokedata(child, addr, data);
-		break;
-
-	case PTRACE_POKEUSR:
-		ret = ptrace_write_user(child, addr, data);
-		break;
-
-	case PTRACE_GETREGS:
-		ret = ptrace_getregs(child, datap);
-		break;
-
-	case PTRACE_SETREGS:
-		ret = ptrace_setregs(child, datap);
-		break;
-
-	default:
-		ret = ptrace_request(child, request, addr, data);
-		break;
-	}
-
-	return ret;
-}
-
-asmlinkage void syscall_trace(void)
-{
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return;
-	if (!(current->ptrace & PT_PTRACED))
-		return;
-
-	/* The 0x80 provides a way for the tracing parent to
-	 * distinguish between a syscall stop and SIGTRAP delivery */
-	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-				 ? 0x80 : 0));
-
-	/*
-	 * this isn't the same as continuing with a signal, but it
-	 * will do for normal use.  strace only continues with a
-	 * signal if the stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		pr_debug("syscall_trace: sending signal %d to PID %u\n",
-			 current->exit_code, current->pid);
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
-}
-
-/*
- * debug_trampoline() is an assembly stub which will store all user
- * registers on the stack and execute a breakpoint instruction.
- *
- * If we single-step into an exception handler which runs with
- * interrupts disabled the whole time so it doesn't have to check for
- * pending work, its return address will be modified so that it ends
- * up returning to debug_trampoline.
- *
- * If the exception handler decides to store the user context and
- * enable interrupts after all, it will restore the original return
- * address and status register value. Before it returns, it will
- * notice that TIF_BREAKPOINT is set and execute a breakpoint
- * instruction.
- */
-extern void debug_trampoline(void);
-
-asmlinkage struct pt_regs *do_debug(struct pt_regs *regs)
-{
-	struct thread_info	*ti;
-	unsigned long		trampoline_addr;
-	u32			status;
-	u32			ctrl;
-	int			code;
-
-	status = ocd_read(DS);
-	ti = current_thread_info();
-	code = TRAP_BRKPT;
-
-	pr_debug("do_debug: status=0x%08x PC=0x%08lx SR=0x%08lx tif=0x%08lx\n",
-			status, regs->pc, regs->sr, ti->flags);
-
-	if (!user_mode(regs)) {
-		unsigned long	die_val = DIE_BREAKPOINT;
-
-		if (status & (1 << OCD_DS_SSS_BIT))
-			die_val = DIE_SSTEP;
-
-		if (notify_die(die_val, "ptrace", regs, 0, 0, SIGTRAP)
-				== NOTIFY_STOP)
-			return regs;
-
-		if ((status & (1 << OCD_DS_SWB_BIT))
-				&& test_and_clear_ti_thread_flag(
-					ti, TIF_BREAKPOINT)) {
-			/*
-			 * Explicit breakpoint from trampoline or
-			 * exception/syscall/interrupt handler.
-			 *
-			 * The real saved regs are on the stack right
-			 * after the ones we saved on entry.
-			 */
-			regs++;
-			pr_debug("  -> TIF_BREAKPOINT done, adjusted regs:"
-					"PC=0x%08lx SR=0x%08lx\n",
-					regs->pc, regs->sr);
-			BUG_ON(!user_mode(regs));
-
-			if (test_thread_flag(TIF_SINGLE_STEP)) {
-				pr_debug("Going to do single step...\n");
-				return regs;
-			}
-
-			/*
-			 * No TIF_SINGLE_STEP means we're done
-			 * stepping over a syscall. Do the trap now.
-			 */
-			code = TRAP_TRACE;
-		} else if ((status & (1 << OCD_DS_SSS_BIT))
-				&& test_ti_thread_flag(ti, TIF_SINGLE_STEP)) {
-
-			pr_debug("Stepped into something, "
-					"setting TIF_BREAKPOINT...\n");
-			set_ti_thread_flag(ti, TIF_BREAKPOINT);
-
-			/*
-			 * We stepped into an exception, interrupt or
-			 * syscall handler. Some exception handlers
-			 * don't check for pending work, so we need to
-			 * set up a trampoline just in case.
-			 *
-			 * The exception entry code will undo the
-			 * trampoline stuff if it does a full context
-			 * save (which also means that it'll check for
-			 * pending work later.)
-			 */
-			if ((regs->sr & MODE_MASK) == MODE_EXCEPTION) {
-				trampoline_addr
-					= (unsigned long)&debug_trampoline;
-
-				pr_debug("Setting up trampoline...\n");
-				ti->rar_saved = sysreg_read(RAR_EX);
-				ti->rsr_saved = sysreg_read(RSR_EX);
-				sysreg_write(RAR_EX, trampoline_addr);
-				sysreg_write(RSR_EX, (MODE_EXCEPTION
-							| SR_EM | SR_GM));
-				BUG_ON(ti->rsr_saved & MODE_MASK);
-			}
-
-			/*
-			 * If we stepped into a system call, we
-			 * shouldn't do a single step after we return
-			 * since the return address is right after the
-			 * "scall" instruction we were told to step
-			 * over.
-			 */
-			if ((regs->sr & MODE_MASK) == MODE_SUPERVISOR) {
-				pr_debug("Supervisor; no single step\n");
-				clear_ti_thread_flag(ti, TIF_SINGLE_STEP);
-			}
-
-			ctrl = ocd_read(DC);
-			ctrl &= ~(1 << OCD_DC_SS_BIT);
-			ocd_write(DC, ctrl);
-
-			return regs;
-		} else {
-			printk(KERN_ERR "Unexpected OCD_DS value: 0x%08x\n",
-					status);
-			printk(KERN_ERR "Thread flags: 0x%08lx\n", ti->flags);
-			die("Unhandled debug trap in kernel mode",
-					regs, SIGTRAP);
-		}
-	} else if (status & (1 << OCD_DS_SSS_BIT)) {
-		/* Single step in user mode */
-		code = TRAP_TRACE;
-
-		ctrl = ocd_read(DC);
-		ctrl &= ~(1 << OCD_DC_SS_BIT);
-		ocd_write(DC, ctrl);
-	}
-
-	pr_debug("Sending SIGTRAP: code=%d PC=0x%08lx SR=0x%08lx\n",
-			code, regs->pc, regs->sr);
-
-	clear_thread_flag(TIF_SINGLE_STEP);
-	_exception(SIGTRAP, regs, code, instruction_pointer(regs));
-
-	return regs;
-}
diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c
deleted file mode 100644
index e6928896da2a..000000000000
--- a/arch/avr32/kernel/setup.c
+++ /dev/null
@@ -1,609 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/init.h>
-#include <linux/initrd.h>
-#include <linux/sched.h>
-#include <linux/console.h>
-#include <linux/ioport.h>
-#include <linux/bootmem.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/pfn.h>
-#include <linux/root_dev.h>
-#include <linux/cpu.h>
-#include <linux/kernel.h>
-
-#include <asm/sections.h>
-#include <asm/processor.h>
-#include <asm/pgtable.h>
-#include <asm/setup.h>
-#include <asm/sysreg.h>
-
-#include <mach/board.h>
-#include <mach/init.h>
-
-extern int root_mountflags;
-
-/*
- * Initialize loops_per_jiffy as 5000000 (500MIPS).
- * Better make it too large than too small...
- */
-struct avr32_cpuinfo boot_cpu_data = {
-	.loops_per_jiffy = 5000000
-};
-EXPORT_SYMBOL(boot_cpu_data);
-
-static char __initdata command_line[COMMAND_LINE_SIZE];
-
-/*
- * Standard memory resources
- */
-static struct resource __initdata kernel_data = {
-	.name	= "Kernel data",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_SYSTEM_RAM,
-};
-static struct resource __initdata kernel_code = {
-	.name	= "Kernel code",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_SYSTEM_RAM,
-	.sibling = &kernel_data,
-};
-
-/*
- * Available system RAM and reserved regions as singly linked
- * lists. These lists are traversed using the sibling pointer in
- * struct resource and are kept sorted at all times.
- */
-static struct resource *__initdata system_ram;
-static struct resource *__initdata reserved = &kernel_code;
-
-/*
- * We need to allocate these before the bootmem allocator is up and
- * running, so we need this "cache". 32 entries are probably enough
- * for all but the most insanely complex systems.
- */
-static struct resource __initdata res_cache[32];
-static unsigned int __initdata res_cache_next_free;
-
-static void __init resource_init(void)
-{
-	struct resource *mem, *res;
-	struct resource *new;
-
-	kernel_code.start = __pa(init_mm.start_code);
-
-	for (mem = system_ram; mem; mem = mem->sibling) {
-		new = alloc_bootmem_low(sizeof(struct resource));
-		memcpy(new, mem, sizeof(struct resource));
-
-		new->sibling = NULL;
-		if (request_resource(&iomem_resource, new))
-			printk(KERN_WARNING "Bad RAM resource %08x-%08x\n",
-			       mem->start, mem->end);
-	}
-
-	for (res = reserved; res; res = res->sibling) {
-		new = alloc_bootmem_low(sizeof(struct resource));
-		memcpy(new, res, sizeof(struct resource));
-
-		new->sibling = NULL;
-		if (insert_resource(&iomem_resource, new))
-			printk(KERN_WARNING
-			       "Bad reserved resource %s (%08x-%08x)\n",
-			       res->name, res->start, res->end);
-	}
-}
-
-static void __init
-add_physical_memory(resource_size_t start, resource_size_t end)
-{
-	struct resource *new, *next, **pprev;
-
-	for (pprev = &system_ram, next = system_ram; next;
-	     pprev = &next->sibling, next = next->sibling) {
-		if (end < next->start)
-			break;
-		if (start <= next->end) {
-			printk(KERN_WARNING
-			       "Warning: Physical memory map is broken\n");
-			printk(KERN_WARNING
-			       "Warning: %08x-%08x overlaps %08x-%08x\n",
-			       start, end, next->start, next->end);
-			return;
-		}
-	}
-
-	if (res_cache_next_free >= ARRAY_SIZE(res_cache)) {
-		printk(KERN_WARNING
-		       "Warning: Failed to add physical memory %08x-%08x\n",
-		       start, end);
-		return;
-	}
-
-	new = &res_cache[res_cache_next_free++];
-	new->start = start;
-	new->end = end;
-	new->name = "System RAM";
-	new->flags = IORESOURCE_SYSTEM_RAM;
-
-	*pprev = new;
-}
-
-static int __init
-add_reserved_region(resource_size_t start, resource_size_t end,
-		    const char *name)
-{
-	struct resource *new, *next, **pprev;
-
-	if (end < start)
-		return -EINVAL;
-
-	if (res_cache_next_free >= ARRAY_SIZE(res_cache))
-		return -ENOMEM;
-
-	for (pprev = &reserved, next = reserved; next;
-	     pprev = &next->sibling, next = next->sibling) {
-		if (end < next->start)
-			break;
-		if (start <= next->end)
-			return -EBUSY;
-	}
-
-	new = &res_cache[res_cache_next_free++];
-	new->start = start;
-	new->end = end;
-	new->name = name;
-	new->sibling = next;
-	new->flags = IORESOURCE_MEM;
-
-	*pprev = new;
-
-	return 0;
-}
-
-static unsigned long __init
-find_free_region(const struct resource *mem, resource_size_t size,
-		 resource_size_t align)
-{
-	struct resource *res;
-	unsigned long target;
-
-	target = ALIGN(mem->start, align);
-	for (res = reserved; res; res = res->sibling) {
-		if ((target + size) <= res->start)
-			break;
-		if (target <= res->end)
-			target = ALIGN(res->end + 1, align);
-	}
-
-	if ((target + size) > (mem->end + 1))
-		return mem->end + 1;
-
-	return target;
-}
-
-static int __init
-alloc_reserved_region(resource_size_t *start, resource_size_t size,
-		      resource_size_t align, const char *name)
-{
-	struct resource *mem;
-	resource_size_t target;
-	int ret;
-
-	for (mem = system_ram; mem; mem = mem->sibling) {
-		target = find_free_region(mem, size, align);
-		if (target <= mem->end) {
-			ret = add_reserved_region(target, target + size - 1,
-						  name);
-			if (!ret)
-				*start = target;
-			return ret;
-		}
-	}
-
-	return -ENOMEM;
-}
-
-/*
- * Early framebuffer allocation. Works as follows:
- *   - If fbmem_size is zero, nothing will be allocated or reserved.
- *   - If fbmem_start is zero when setup_bootmem() is called,
- *     a block of fbmem_size bytes will be reserved before bootmem
- *     initialization. It will be aligned to the largest page size
- *     that fbmem_size is a multiple of.
- *   - If fbmem_start is nonzero, an area of size fbmem_size will be
- *     reserved at the physical address fbmem_start if possible. If
- *     it collides with other reserved memory, a different block of
- *     same size will be allocated, just as if fbmem_start was zero.
- *
- * Board-specific code may use these variables to set up platform data
- * for the framebuffer driver if fbmem_size is nonzero.
- */
-resource_size_t __initdata fbmem_start;
-resource_size_t __initdata fbmem_size;
-
-/*
- * "fbmem=xxx[kKmM]" allocates the specified amount of boot memory for
- * use as framebuffer.
- *
- * "fbmem=xxx[kKmM]@yyy[kKmM]" defines a memory region of size xxx and
- * starting at yyy to be reserved for use as framebuffer.
- *
- * The kernel won't verify that the memory region starting at yyy
- * actually contains usable RAM.
- */
-static int __init early_parse_fbmem(char *p)
-{
-	int ret;
-	unsigned long align;
-
-	fbmem_size = memparse(p, &p);
-	if (*p == '@') {
-		fbmem_start = memparse(p + 1, &p);
-		ret = add_reserved_region(fbmem_start,
-					  fbmem_start + fbmem_size - 1,
-					  "Framebuffer");
-		if (ret) {
-			printk(KERN_WARNING
-			       "Failed to reserve framebuffer memory\n");
-			fbmem_start = 0;
-		}
-	}
-
-	if (!fbmem_start) {
-		if ((fbmem_size & 0x000fffffUL) == 0)
-			align = 0x100000;	/* 1 MiB */
-		else if ((fbmem_size & 0x0000ffffUL) == 0)
-			align = 0x10000;	/* 64 KiB */
-		else
-			align = 0x1000;		/* 4 KiB */
-
-		ret = alloc_reserved_region(&fbmem_start, fbmem_size,
-					    align, "Framebuffer");
-		if (ret) {
-			printk(KERN_WARNING
-			       "Failed to allocate framebuffer memory\n");
-			fbmem_size = 0;
-		} else {
-			memset(__va(fbmem_start), 0, fbmem_size);
-		}
-	}
-
-	return 0;
-}
-early_param("fbmem", early_parse_fbmem);
-
-/*
- * Pick out the memory size.  We look for mem=size@start,
- * where start and size are "size[KkMmGg]"
- */
-static int __init early_mem(char *p)
-{
-	resource_size_t size, start;
-
-	start = system_ram->start;
-	size  = memparse(p, &p);
-	if (*p == '@')
-		start = memparse(p + 1, &p);
-
-	system_ram->start = start;
-	system_ram->end = system_ram->start + size - 1;
-	return 0;
-}
-early_param("mem", early_mem);
-
-static int __init parse_tag_core(struct tag *tag)
-{
-	if (tag->hdr.size > 2) {
-		if ((tag->u.core.flags & 1) == 0)
-			root_mountflags &= ~MS_RDONLY;
-		ROOT_DEV = new_decode_dev(tag->u.core.rootdev);
-	}
-	return 0;
-}
-__tagtable(ATAG_CORE, parse_tag_core);
-
-static int __init parse_tag_mem(struct tag *tag)
-{
-	unsigned long start, end;
-
-	/*
-	 * Ignore zero-sized entries. If we're running standalone, the
-	 * SDRAM code may emit such entries if something goes
-	 * wrong...
-	 */
-	if (tag->u.mem_range.size == 0)
-		return 0;
-
-	start = tag->u.mem_range.addr;
-	end = tag->u.mem_range.addr + tag->u.mem_range.size - 1;
-
-	add_physical_memory(start, end);
-	return 0;
-}
-__tagtable(ATAG_MEM, parse_tag_mem);
-
-static int __init parse_tag_rdimg(struct tag *tag)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	struct tag_mem_range *mem = &tag->u.mem_range;
-	int ret;
-
-	if (initrd_start) {
-		printk(KERN_WARNING
-		       "Warning: Only the first initrd image will be used\n");
-		return 0;
-	}
-
-	ret = add_reserved_region(mem->addr, mem->addr + mem->size - 1,
-				  "initrd");
-	if (ret) {
-		printk(KERN_WARNING
-		       "Warning: Failed to reserve initrd memory\n");
-		return ret;
-	}
-
-	initrd_start = (unsigned long)__va(mem->addr);
-	initrd_end = initrd_start + mem->size;
-#else
-	printk(KERN_WARNING "RAM disk image present, but "
-	       "no initrd support in kernel, ignoring\n");
-#endif
-
-	return 0;
-}
-__tagtable(ATAG_RDIMG, parse_tag_rdimg);
-
-static int __init parse_tag_rsvd_mem(struct tag *tag)
-{
-	struct tag_mem_range *mem = &tag->u.mem_range;
-
-	return add_reserved_region(mem->addr, mem->addr + mem->size - 1,
-				   "Reserved");
-}
-__tagtable(ATAG_RSVD_MEM, parse_tag_rsvd_mem);
-
-static int __init parse_tag_cmdline(struct tag *tag)
-{
-	strlcpy(boot_command_line, tag->u.cmdline.cmdline, COMMAND_LINE_SIZE);
-	return 0;
-}
-__tagtable(ATAG_CMDLINE, parse_tag_cmdline);
-
-static int __init parse_tag_clock(struct tag *tag)
-{
-	/*
-	 * We'll figure out the clocks by peeking at the system
-	 * manager regs directly.
-	 */
-	return 0;
-}
-__tagtable(ATAG_CLOCK, parse_tag_clock);
-
-/*
- * The board_number correspond to the bd->bi_board_number in U-Boot. This
- * parameter is only available during initialisation and can be used in some
- * kind of board identification.
- */
-u32 __initdata board_number;
-
-static int __init parse_tag_boardinfo(struct tag *tag)
-{
-	board_number = tag->u.boardinfo.board_number;
-
-	return 0;
-}
-__tagtable(ATAG_BOARDINFO, parse_tag_boardinfo);
-
-/*
- * Scan the tag table for this tag, and call its parse function. The
- * tag table is built by the linker from all the __tagtable
- * declarations.
- */
-static int __init parse_tag(struct tag *tag)
-{
-	extern struct tagtable __tagtable_begin, __tagtable_end;
-	struct tagtable *t;
-
-	for (t = &__tagtable_begin; t < &__tagtable_end; t++)
-		if (tag->hdr.tag == t->tag) {
-			t->parse(tag);
-			break;
-		}
-
-	return t < &__tagtable_end;
-}
-
-/*
- * Parse all tags in the list we got from the boot loader
- */
-static void __init parse_tags(struct tag *t)
-{
-	for (; t->hdr.tag != ATAG_NONE; t = tag_next(t))
-		if (!parse_tag(t))
-			printk(KERN_WARNING
-			       "Ignoring unrecognised tag 0x%08x\n",
-			       t->hdr.tag);
-}
-
-/*
- * Find a free memory region large enough for storing the
- * bootmem bitmap.
- */
-static unsigned long __init
-find_bootmap_pfn(const struct resource *mem)
-{
-	unsigned long bootmap_pages, bootmap_len;
-	unsigned long node_pages = PFN_UP(resource_size(mem));
-	unsigned long bootmap_start;
-
-	bootmap_pages = bootmem_bootmap_pages(node_pages);
-	bootmap_len = bootmap_pages << PAGE_SHIFT;
-
-	/*
-	 * Find a large enough region without reserved pages for
-	 * storing the bootmem bitmap. We can take advantage of the
-	 * fact that all lists have been sorted.
-	 *
-	 * We have to check that we don't collide with any reserved
-	 * regions, which includes the kernel image and any RAMDISK
-	 * images.
-	 */
-	bootmap_start = find_free_region(mem, bootmap_len, PAGE_SIZE);
-
-	return bootmap_start >> PAGE_SHIFT;
-}
-
-#define MAX_LOWMEM	HIGHMEM_START
-#define MAX_LOWMEM_PFN	PFN_DOWN(MAX_LOWMEM)
-
-static void __init setup_bootmem(void)
-{
-	unsigned bootmap_size;
-	unsigned long first_pfn, bootmap_pfn, pages;
-	unsigned long max_pfn, max_low_pfn;
-	unsigned node = 0;
-	struct resource *res;
-
-	printk(KERN_INFO "Physical memory:\n");
-	for (res = system_ram; res; res = res->sibling)
-		printk("  %08x-%08x\n", res->start, res->end);
-	printk(KERN_INFO "Reserved memory:\n");
-	for (res = reserved; res; res = res->sibling)
-		printk("  %08x-%08x: %s\n",
-		       res->start, res->end, res->name);
-
-	nodes_clear(node_online_map);
-
-	if (system_ram->sibling)
-		printk(KERN_WARNING "Only using first memory bank\n");
-
-	for (res = system_ram; res; res = NULL) {
-		first_pfn = PFN_UP(res->start);
-		max_low_pfn = max_pfn = PFN_DOWN(res->end + 1);
-		bootmap_pfn = find_bootmap_pfn(res);
-		if (bootmap_pfn > max_pfn)
-			panic("No space for bootmem bitmap!\n");
-
-		if (max_low_pfn > MAX_LOWMEM_PFN) {
-			max_low_pfn = MAX_LOWMEM_PFN;
-#ifndef CONFIG_HIGHMEM
-			/*
-			 * Lowmem is memory that can be addressed
-			 * directly through P1/P2
-			 */
-			printk(KERN_WARNING
-			       "Node %u: Only %ld MiB of memory will be used.\n",
-			       node, MAX_LOWMEM >> 20);
-			printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
-#else
-#error HIGHMEM is not supported by AVR32 yet
-#endif
-		}
-
-		/* Initialize the boot-time allocator with low memory only. */
-		bootmap_size = init_bootmem_node(NODE_DATA(node), bootmap_pfn,
-						 first_pfn, max_low_pfn);
-
-		/*
-		 * Register fully available RAM pages with the bootmem
-		 * allocator.
-		 */
-		pages = max_low_pfn - first_pfn;
-		free_bootmem_node (NODE_DATA(node), PFN_PHYS(first_pfn),
-				   PFN_PHYS(pages));
-
-		/* Reserve space for the bootmem bitmap... */
-		reserve_bootmem_node(NODE_DATA(node),
-				     PFN_PHYS(bootmap_pfn),
-				     bootmap_size,
-				     BOOTMEM_DEFAULT);
-
-		/* ...and any other reserved regions. */
-		for (res = reserved; res; res = res->sibling) {
-			if (res->start > PFN_PHYS(max_pfn))
-				break;
-
-			/*
-			 * resource_init will complain about partial
-			 * overlaps, so we'll just ignore such
-			 * resources for now.
-			 */
-			if (res->start >= PFN_PHYS(first_pfn)
-			    && res->end < PFN_PHYS(max_pfn))
-				reserve_bootmem_node(NODE_DATA(node),
-						     res->start,
-						     resource_size(res),
-						     BOOTMEM_DEFAULT);
-		}
-
-		node_set_online(node);
-	}
-}
-
-void __init setup_arch (char **cmdline_p)
-{
-	struct clk *cpu_clk;
-
-	init_mm.start_code = (unsigned long)_stext;
-	init_mm.end_code = (unsigned long)_etext;
-	init_mm.end_data = (unsigned long)_edata;
-	init_mm.brk = (unsigned long)_end;
-
-	/*
-	 * Include .init section to make allocations easier. It will
-	 * be removed before the resource is actually requested.
-	 */
-	kernel_code.start = __pa(__init_begin);
-	kernel_code.end = __pa(init_mm.end_code - 1);
-	kernel_data.start = __pa(init_mm.end_code);
-	kernel_data.end = __pa(init_mm.brk - 1);
-
-	parse_tags(bootloader_tags);
-
-	setup_processor();
-	setup_platform();
-	setup_board();
-
-	cpu_clk = clk_get(NULL, "cpu");
-	if (IS_ERR(cpu_clk)) {
-		printk(KERN_WARNING "Warning: Unable to get CPU clock\n");
-	} else {
-		unsigned long cpu_hz = clk_get_rate(cpu_clk);
-
-		/*
-		 * Well, duh, but it's probably a good idea to
-		 * increment the use count.
-		 */
-		clk_enable(cpu_clk);
-
-		boot_cpu_data.clk = cpu_clk;
-		boot_cpu_data.loops_per_jiffy = cpu_hz * 4;
-		printk("CPU: Running at %lu.%03lu MHz\n",
-		       ((cpu_hz + 500) / 1000) / 1000,
-		       ((cpu_hz + 500) / 1000) % 1000);
-	}
-
-	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
-	*cmdline_p = command_line;
-	parse_early_param();
-
-	setup_bootmem();
-
-#ifdef CONFIG_VT
-	conswitchp = &dummy_con;
-#endif
-
-	paging_init();
-	resource_init();
-}
diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c
deleted file mode 100644
index b5fcc4914fe4..000000000000
--- a/arch/avr32/kernel/signal.c
+++ /dev/null
@@ -1,288 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/arch/sh/kernel/signal.c
- *  Copyright (C) 1999, 2000  Niibe Yutaka & Kaz Kojima
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/unistd.h>
-#include <linux/tracehook.h>
-
-#include <linux/uaccess.h>
-#include <asm/ucontext.h>
-#include <asm/syscalls.h>
-
-struct rt_sigframe
-{
-	struct siginfo info;
-	struct ucontext uc;
-	unsigned long retcode;
-};
-
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
-{
-	int err = 0;
-
-#define COPY(x)		err |= __get_user(regs->x, &sc->x)
-	COPY(sr);
-	COPY(pc);
-	COPY(lr);
-	COPY(sp);
-	COPY(r12);
-	COPY(r11);
-	COPY(r10);
-	COPY(r9);
-	COPY(r8);
-	COPY(r7);
-	COPY(r6);
-	COPY(r5);
-	COPY(r4);
-	COPY(r3);
-	COPY(r2);
-	COPY(r1);
-	COPY(r0);
-#undef	COPY
-
-	/*
-	 * Don't allow anyone to pretend they're running in supervisor
-	 * mode or something...
-	 */
-	err |= !valid_user_regs(regs);
-
-	return err;
-}
-
-
-asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame;
-	sigset_t set;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current->restart_block.fn = do_no_restart_syscall;
-
-	frame = (struct rt_sigframe __user *)regs->sp;
-	pr_debug("SIG return: frame = %p\n", frame);
-
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-
-	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
-		goto badframe;
-
-	set_current_blocked(&set);
-
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
-		goto badframe;
-
-	if (restore_altstack(&frame->uc.uc_stack))
-		goto badframe;
-
-	pr_debug("Context restored: pc = %08lx, lr = %08lx, sp = %08lx\n",
-		 regs->pc, regs->lr, regs->sp);
-
-	return regs->r12;
-
-badframe:
-	force_sig(SIGSEGV, current);
-	return 0;
-}
-
-static int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs)
-{
-	int err = 0;
-
-#define COPY(x)		err |= __put_user(regs->x, &sc->x)
-	COPY(sr);
-	COPY(pc);
-	COPY(lr);
-	COPY(sp);
-	COPY(r12);
-	COPY(r11);
-	COPY(r10);
-	COPY(r9);
-	COPY(r8);
-	COPY(r7);
-	COPY(r6);
-	COPY(r5);
-	COPY(r4);
-	COPY(r3);
-	COPY(r2);
-	COPY(r1);
-	COPY(r0);
-#undef	COPY
-
-	return err;
-}
-
-static inline void __user *
-get_sigframe(struct ksignal *ksig, struct pt_regs *regs, int framesize)
-{
-	unsigned long sp = sigsp(regs->sp, ksig);
-
-	return (void __user *)((sp - framesize) & ~3);
-}
-
-static int
-setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame;
-	int err = 0;
-
-	frame = get_sigframe(ksig, regs, sizeof(*frame));
-	err = -EFAULT;
-	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
-		goto out;
-
-	/*
-	 * Set up the return code:
-	 *
-	 *	mov	r8, __NR_rt_sigreturn
-	 *	scall
-	 *
-	 * Note: This will blow up since we're using a non-executable
-	 * stack. Better use SA_RESTORER.
-	 */
-#if __NR_rt_sigreturn > 127
-# error __NR_rt_sigreturn must be < 127 to fit in a short mov
-#endif
-	err = __put_user(0x3008d733 | (__NR_rt_sigreturn << 20),
-			 &frame->retcode);
-
-	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
-
-	/* Set up the ucontext */
-	err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(NULL, &frame->uc.uc_link);
-	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
-	if (err)
-		goto out;
-
-	regs->r12 = ksig->sig;
-	regs->r11 = (unsigned long) &frame->info;
-	regs->r10 = (unsigned long) &frame->uc;
-	regs->sp = (unsigned long) frame;
-	if (ksig->ka.sa.sa_flags & SA_RESTORER)
-		regs->lr = (unsigned long)ksig->ka.sa.sa_restorer;
-	else {
-		printk(KERN_NOTICE "[%s:%d] did not set SA_RESTORER\n",
-		       current->comm, current->pid);
-		regs->lr = (unsigned long) &frame->retcode;
-	}
-
-	pr_debug("SIG deliver [%s:%d]: sig=%d sp=0x%lx pc=0x%lx->0x%p lr=0x%lx\n",
-		 current->comm, current->pid, ksig->sig, regs->sp,
-		 regs->pc, ksig->ka.sa.sa_handler, regs->lr);
-
-	regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
-
-out:
-	return err;
-}
-
-static inline void setup_syscall_restart(struct pt_regs *regs)
-{
-	if (regs->r12 == -ERESTART_RESTARTBLOCK)
-		regs->r8 = __NR_restart_syscall;
-	else
-		regs->r12 = regs->r12_orig;
-	regs->pc -= 2;
-}
-
-static inline void
-handle_signal(struct ksignal *ksig, struct pt_regs *regs, int syscall)
-{
-	int ret;
-
-	/*
-	 * Set up the stack frame
-	 */
-	ret = setup_rt_frame(ksig, sigmask_to_save(), regs);
-
-	/*
-	 * Check that the resulting registers are sane
-	 */
-	ret |= !valid_user_regs(regs);
-
-	/*
-	 * Block the signal if we were successful.
-	 */
-	signal_setup_done(ret, ksig, 0);
-}
-
-/*
- * Note that 'init' is a special process: it doesn't get signals it
- * doesn't want to handle. Thus you cannot kill init even with a
- * SIGKILL even by mistake.
- */
-static void do_signal(struct pt_regs *regs, int syscall)
-{
-	struct ksignal ksig;
-
-	/*
-	 * We want the common case to go fast, which is why we may in
-	 * certain cases get here from kernel mode. Just return
-	 * without doing anything if so.
-	 */
-	if (!user_mode(regs))
-		return;
-
-	get_signal(&ksig);
-	if (syscall) {
-		switch (regs->r12) {
-		case -ERESTART_RESTARTBLOCK:
-		case -ERESTARTNOHAND:
-			if (ksig.sig > 0) {
-				regs->r12 = -EINTR;
-				break;
-			}
-			/* fall through */
-		case -ERESTARTSYS:
-			if (ksig.sig > 0 && !(ksig.ka.sa.sa_flags & SA_RESTART)) {
-				regs->r12 = -EINTR;
-				break;
-			}
-			/* fall through */
-		case -ERESTARTNOINTR:
-			setup_syscall_restart(regs);
-		}
-	}
-
-	if (!ksig.sig) {
-		/* No signal to deliver -- put the saved sigmask back */
-		restore_saved_sigmask();
-		return;
-	}
-
-	handle_signal(&ksig, regs, syscall);
-}
-
-asmlinkage void do_notify_resume(struct pt_regs *regs, struct thread_info *ti)
-{
-	int syscall = 0;
-
-	if ((sysreg_read(SR) & MODE_MASK) == MODE_SUPERVISOR)
-		syscall = 1;
-
-	if (ti->flags & _TIF_SIGPENDING)
-		do_signal(regs, syscall);
-
-	if (ti->flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-}
diff --git a/arch/avr32/kernel/stacktrace.c b/arch/avr32/kernel/stacktrace.c
deleted file mode 100644
index f8cc995cf0e0..000000000000
--- a/arch/avr32/kernel/stacktrace.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Stack trace management functions
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/stacktrace.h>
-#include <linux/thread_info.h>
-#include <linux/module.h>
-
-register unsigned long current_frame_pointer asm("r7");
-
-struct stackframe {
-	unsigned long lr;
-	unsigned long fp;
-};
-
-/*
- * Save stack-backtrace addresses into a stack_trace buffer.
- */
-void save_stack_trace(struct stack_trace *trace)
-{
-	unsigned long low, high;
-	unsigned long fp;
-	struct stackframe *frame;
-	int skip = trace->skip;
-
-	low = (unsigned long)task_stack_page(current);
-	high = low + THREAD_SIZE;
-	fp = current_frame_pointer;
-
-	while (fp >= low && fp <= (high - 8)) {
-		frame = (struct stackframe *)fp;
-
-		if (skip) {
-			skip--;
-		} else {
-			trace->entries[trace->nr_entries++] = frame->lr;
-			if (trace->nr_entries >= trace->max_entries)
-				break;
-		}
-
-		/*
-		 * The next frame must be at a higher address than the
-		 * current frame.
-		 */
-		low = fp + 8;
-		fp = frame->fp;
-	}
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
diff --git a/arch/avr32/kernel/switch_to.S b/arch/avr32/kernel/switch_to.S
deleted file mode 100644
index a48d046723c5..000000000000
--- a/arch/avr32/kernel/switch_to.S
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <asm/sysreg.h>
-
-	.text
-	.global	__switch_to
-	.type	__switch_to, @function
-
-	/* Switch thread context from "prev" to "next", returning "last"
-	 *   r12 :	prev
-	 *   r11 :	&prev->thread + 1
-	 *   r10 :	&next->thread
-	 */
-__switch_to:
-	stm	--r11, r0,r1,r2,r3,r4,r5,r6,r7,sp,lr
-	mfsr	r9, SYSREG_SR
-	st.w	--r11, r9
-	ld.w	r8, r10++
-	/*
-	 * schedule() may have been called from a mode with a different
-	 * set of registers. Make sure we don't lose anything here.
-	 */
-	pushm	r10,r12
-	mtsr	SYSREG_SR, r8
-	frs			/* flush the return stack */
-	sub	pc, -2		/* flush the pipeline */
-	popm	r10,r12
-	ldm	r10++, r0,r1,r2,r3,r4,r5,r6,r7,sp,pc
-	.size	__switch_to, . - __switch_to
diff --git a/arch/avr32/kernel/syscall-stubs.S b/arch/avr32/kernel/syscall-stubs.S
deleted file mode 100644
index cb256534ed92..000000000000
--- a/arch/avr32/kernel/syscall-stubs.S
+++ /dev/null
@@ -1,153 +0,0 @@
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * Stubs for syscalls that require access to pt_regs or that take more
- * than five parameters.
- */
-
-#define ARG6	r3
-
-	.text
-	.global __sys_rt_sigsuspend
-	.type	__sys_rt_sigsuspend,@function
-__sys_rt_sigsuspend:
-	mov	r10, sp
-	rjmp	sys_rt_sigsuspend
-
-	.global	__sys_rt_sigreturn
-	.type	__sys_rt_sigreturn,@function
-__sys_rt_sigreturn:
-	mov	r12, sp
-	rjmp	sys_rt_sigreturn
-
-	.global	__sys_mmap2
-	.type	__sys_mmap2,@function
-__sys_mmap2:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_mmap_pgoff
-	sub	sp, -4
-	popm	pc
-
-	.global	__sys_sendto
-	.type	__sys_sendto,@function
-__sys_sendto:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_sendto
-	sub	sp, -4
-	popm	pc
-
-	.global	__sys_recvfrom
-	.type	__sys_recvfrom,@function
-__sys_recvfrom:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_recvfrom
-	sub	sp, -4
-	popm	pc
-
-	.global	__sys_pselect6
-	.type	__sys_pselect6,@function
-__sys_pselect6:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_pselect6
-	sub	sp, -4
-	popm	pc
-
-	.global	__sys_splice
-	.type	__sys_splice,@function
-__sys_splice:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_splice
-	sub	sp, -4
-	popm	pc
-
-	.global	__sys_epoll_pwait
-	.type	__sys_epoll_pwait,@function
-__sys_epoll_pwait:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_epoll_pwait
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_sync_file_range
-	.type	__sys_sync_file_range,@function
-__sys_sync_file_range:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_sync_file_range
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_fallocate
-	.type	__sys_fallocate,@function
-__sys_fallocate:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_fallocate
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_fanotify_mark
-	.type	__sys_fanotify_mark,@function
-__sys_fanotify_mark:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_fanotify_mark
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_process_vm_readv
-	.type	__sys_process_vm_readv,@function
-__sys_process_vm_readv:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_process_vm_readv
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_process_vm_writev
-	.type	__sys_process_vm_writev,@function
-__sys_process_vm_writev:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_process_vm_writev
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_copy_file_range
-	.type	__sys_copy_file_range,@function
-__sys_copy_file_range:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_copy_file_range
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_preadv2
-	.type	__sys_preadv2,@function
-__sys_preadv2:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_preadv2
-	sub	sp, -4
-	popm	pc
-
-	.global __sys_pwritev2
-	.type	__sys_pwritev2,@function
-__sys_pwritev2:
-	pushm	lr
-	st.w	--sp, ARG6
-	call	sys_pwritev2
-	sub	sp, -4
-	popm	pc
diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S
deleted file mode 100644
index 774ce57f4948..000000000000
--- a/arch/avr32/kernel/syscall_table.S
+++ /dev/null
@@ -1,347 +0,0 @@
-/*
- * AVR32 system call table
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	.section .rodata,"a",@progbits
-	.type sys_call_table,@object
-	.global sys_call_table
-	.align 2
-sys_call_table:
-	.long sys_restart_syscall
-	.long sys_exit
-	.long sys_fork
-	.long sys_read
-	.long sys_write
-	.long sys_open
-	.long sys_close
-	.long sys_umask
-	.long sys_creat
-	.long sys_link
-	.long sys_unlink /* 10 */
-	.long sys_execve
-	.long sys_chdir
-	.long sys_time
-	.long sys_mknod
-	.long sys_chmod
-	.long sys_chown
-	.long sys_lchown
-	.long sys_lseek
-	.long sys_llseek
-	.long sys_getpid /* 20 */
-	.long sys_mount
-	.long sys_umount
-	.long sys_setuid
-	.long sys_getuid
-	.long sys_stime
-	.long sys_ptrace
-	.long sys_alarm
-	.long sys_pause
-	.long sys_utime
-	.long sys_newstat /* 30 */
-	.long sys_newfstat
-	.long sys_newlstat
-	.long sys_access
-	.long sys_chroot
-	.long sys_sync
-	.long sys_fsync
-	.long sys_kill
-	.long sys_rename
-	.long sys_mkdir
-	.long sys_rmdir /* 40 */
-	.long sys_dup
-	.long sys_pipe
-	.long sys_times
-	.long sys_clone
-	.long sys_brk
-	.long sys_setgid
-	.long sys_getgid
-	.long sys_getcwd
-	.long sys_geteuid
-	.long sys_getegid /* 50 */
-	.long sys_acct
-	.long sys_setfsuid
-	.long sys_setfsgid
-	.long sys_ioctl
-	.long sys_fcntl
-	.long sys_setpgid
-	.long sys_mremap
-	.long sys_setresuid
-	.long sys_getresuid
-	.long sys_setreuid /* 60 */
-	.long sys_setregid
-	.long sys_ustat
-	.long sys_dup2
-	.long sys_getppid
-	.long sys_getpgrp
-	.long sys_setsid
-	.long sys_rt_sigaction
-	.long __sys_rt_sigreturn
-	.long sys_rt_sigprocmask
-	.long sys_rt_sigpending /* 70 */
-	.long sys_rt_sigtimedwait
-	.long sys_rt_sigqueueinfo
-	.long __sys_rt_sigsuspend
-	.long sys_sethostname
-	.long sys_setrlimit
-	.long sys_getrlimit
-	.long sys_getrusage
-	.long sys_gettimeofday
-	.long sys_settimeofday
-	.long sys_getgroups /* 80 */
-	.long sys_setgroups
-	.long sys_select
-	.long sys_symlink
-	.long sys_fchdir
-	.long sys_readlink
-	.long sys_pread64
-	.long sys_pwrite64
-	.long sys_swapon
-	.long sys_reboot
-	.long __sys_mmap2 /* 90 */
-	.long sys_munmap
-	.long sys_truncate
-	.long sys_ftruncate
-	.long sys_fchmod
-	.long sys_fchown
-	.long sys_getpriority
-	.long sys_setpriority
-	.long sys_wait4
-	.long sys_statfs
-	.long sys_fstatfs /* 100 */
-	.long sys_vhangup
-	.long sys_sigaltstack
-	.long sys_syslog
-	.long sys_setitimer
-	.long sys_getitimer
-	.long sys_swapoff
-	.long sys_sysinfo
-	.long sys_ni_syscall /* was sys_ipc briefly */
-	.long sys_sendfile
-	.long sys_setdomainname /* 110 */
-	.long sys_newuname
-	.long sys_adjtimex
-	.long sys_mprotect
-	.long sys_vfork
-	.long sys_init_module
-	.long sys_delete_module
-	.long sys_quotactl
-	.long sys_getpgid
-	.long sys_bdflush
-	.long sys_sysfs /* 120 */
-	.long sys_personality
-	.long sys_ni_syscall /* reserved for afs_syscall */
-	.long sys_getdents
-	.long sys_flock
-	.long sys_msync
-	.long sys_readv
-	.long sys_writev
-	.long sys_getsid
-	.long sys_fdatasync
-	.long sys_sysctl /* 130 */
-	.long sys_mlock
-	.long sys_munlock
-	.long sys_mlockall
-	.long sys_munlockall
-	.long sys_sched_setparam
-	.long sys_sched_getparam
-	.long sys_sched_setscheduler
-	.long sys_sched_getscheduler
-	.long sys_sched_yield
-	.long sys_sched_get_priority_max  /* 140 */
-	.long sys_sched_get_priority_min
-	.long sys_sched_rr_get_interval
-	.long sys_nanosleep
-	.long sys_poll
-	.long sys_ni_syscall /* 145 was nfsservctl */
-	.long sys_setresgid
-	.long sys_getresgid
-	.long sys_prctl
-	.long sys_socket
-	.long sys_bind /* 150 */
-	.long sys_connect
-	.long sys_listen
-	.long sys_accept
-	.long sys_getsockname
-	.long sys_getpeername
-	.long sys_socketpair
-	.long sys_send
-	.long sys_recv
-	.long __sys_sendto
-	.long __sys_recvfrom /* 160 */
-	.long sys_shutdown
-	.long sys_setsockopt
-	.long sys_getsockopt
-	.long sys_sendmsg
-	.long sys_recvmsg
-	.long sys_truncate64
-	.long sys_ftruncate64
-	.long sys_stat64
-	.long sys_lstat64
-	.long sys_fstat64 /* 170 */
-	.long sys_pivot_root
-	.long sys_mincore
-	.long sys_madvise
-	.long sys_getdents64
-	.long sys_fcntl64
-	.long sys_gettid
-	.long sys_readahead
-	.long sys_setxattr
-	.long sys_lsetxattr
-	.long sys_fsetxattr /* 180 */
-	.long sys_getxattr
-	.long sys_lgetxattr
-	.long sys_fgetxattr
-	.long sys_listxattr
-	.long sys_llistxattr
-	.long sys_flistxattr
-	.long sys_removexattr
-	.long sys_lremovexattr
-	.long sys_fremovexattr
-	.long sys_tkill /* 190 */
-	.long sys_sendfile64
-	.long sys_futex
-	.long sys_sched_setaffinity
-	.long sys_sched_getaffinity
-	.long sys_capget
-	.long sys_capset
-	.long sys_io_setup
-	.long sys_io_destroy
-	.long sys_io_getevents
-	.long sys_io_submit /* 200 */
-	.long sys_io_cancel
-	.long sys_fadvise64
-	.long sys_exit_group
-	.long sys_lookup_dcookie
-	.long sys_epoll_create
-	.long sys_epoll_ctl
-	.long sys_epoll_wait
-	.long sys_remap_file_pages
-	.long sys_set_tid_address
-	.long sys_timer_create /* 210 */
-	.long sys_timer_settime
-	.long sys_timer_gettime
-	.long sys_timer_getoverrun
-	.long sys_timer_delete
-	.long sys_clock_settime
-	.long sys_clock_gettime
-	.long sys_clock_getres
-	.long sys_clock_nanosleep
-	.long sys_statfs64
-	.long sys_fstatfs64 /* 220 */
-	.long sys_tgkill
-	.long sys_ni_syscall /* reserved for TUX */
-	.long sys_utimes
-	.long sys_fadvise64_64
-	.long sys_cacheflush
-	.long sys_ni_syscall /* sys_vserver */
-	.long sys_mq_open
-	.long sys_mq_unlink
-	.long sys_mq_timedsend
-	.long sys_mq_timedreceive /* 230 */
-	.long sys_mq_notify
-	.long sys_mq_getsetattr
-	.long sys_kexec_load
-	.long sys_waitid
-	.long sys_add_key
-	.long sys_request_key
-	.long sys_keyctl
-	.long sys_ioprio_set
-	.long sys_ioprio_get
-	.long sys_inotify_init /* 240 */
-	.long sys_inotify_add_watch
-	.long sys_inotify_rm_watch
-	.long sys_openat
-	.long sys_mkdirat
-	.long sys_mknodat
-	.long sys_fchownat
-	.long sys_futimesat
-	.long sys_fstatat64
-	.long sys_unlinkat
-	.long sys_renameat /* 250 */
-	.long sys_linkat
-	.long sys_symlinkat
-	.long sys_readlinkat
-	.long sys_fchmodat
-	.long sys_faccessat
-	.long __sys_pselect6
-	.long sys_ppoll
-	.long sys_unshare
-	.long sys_set_robust_list
-	.long sys_get_robust_list /* 260 */
-	.long __sys_splice
-	.long __sys_sync_file_range
-	.long sys_tee
-	.long sys_vmsplice
-	.long __sys_epoll_pwait
-	.long sys_msgget
-	.long sys_msgsnd
-	.long sys_msgrcv
-	.long sys_msgctl
-	.long sys_semget /* 270 */
-	.long sys_semop
-	.long sys_semctl
-	.long sys_semtimedop
-	.long sys_shmat
-	.long sys_shmget
-	.long sys_shmdt
-	.long sys_shmctl
-	.long sys_utimensat
-	.long sys_signalfd
-	.long sys_ni_syscall /* 280, was sys_timerfd */
-	.long sys_eventfd
-	.long sys_ni_syscall /* 282, was half-implemented recvmmsg */
-	.long sys_setns
-	.long sys_pread64
-	.long sys_pwrite64
-	.long sys_timerfd_create
-	.long __sys_fallocate
-	.long sys_timerfd_settime
-	.long sys_timerfd_gettime
-	.long sys_signalfd4 /* 290 */
-	.long sys_eventfd2
-	.long sys_epoll_create1
-	.long sys_dup3
-	.long sys_pipe2
-	.long sys_inotify_init1
-	.long sys_preadv
-	.long sys_pwritev
-	.long sys_rt_tgsigqueueinfo
-	.long sys_perf_event_open
-	.long sys_recvmmsg /* 300 */
-	.long sys_fanotify_init
-	.long __sys_fanotify_mark
-	.long sys_prlimit64
-	.long sys_name_to_handle_at
-	.long sys_open_by_handle_at
-	.long sys_clock_adjtime
-	.long sys_syncfs
-	.long sys_sendmmsg
-	.long __sys_process_vm_readv
-	.long __sys_process_vm_writev /* 310 */
-	.long sys_kcmp
-	.long sys_finit_module
-	.long sys_sched_setattr
-	.long sys_sched_getattr
-	.long sys_renameat2
-	.long sys_seccomp
-	.long sys_getrandom
-	.long sys_memfd_create
-	.long sys_bpf
-	.long sys_execveat /* 320 */
-	.long sys_accept4
-	.long sys_userfaultfd
-	.long sys_membarrier
-	.long sys_mlock2
-	.long __sys_copy_file_range
-	.long __sys_preadv2
-	.long __sys_pwritev2
-	.long sys_pkey_mprotect
-	.long sys_pkey_alloc
-	.long sys_pkey_free /* 330 */
-	.long sys_ni_syscall /* r8 is saturated at nr_syscalls */
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
deleted file mode 100644
index 4d9b69615979..000000000000
--- a/arch/avr32/kernel/time.c
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- * Copyright (C) 2004-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/cpu.h>
-
-#include <asm/sysreg.h>
-
-#include <mach/pm.h>
-
-static bool disable_cpu_idle_poll;
-
-static u64 read_cycle_count(struct clocksource *cs)
-{
-	return (u64)sysreg_read(COUNT);
-}
-
-/*
- * The architectural cycle count registers are a fine clocksource unless
- * the system idle loop use sleep states like "idle":  the CPU cycles
- * measured by COUNT (and COMPARE) don't happen during sleep states.
- * Their duration also changes if cpufreq changes the CPU clock rate.
- * So we rate the clocksource using COUNT as very low quality.
- */
-static struct clocksource counter = {
-	.name		= "avr32_counter",
-	.rating		= 50,
-	.read		= read_cycle_count,
-	.mask		= CLOCKSOURCE_MASK(32),
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	struct clock_event_device *evdev = dev_id;
-
-	if (unlikely(!(intc_get_pending(0) & 1)))
-		return IRQ_NONE;
-
-	/*
-	 * Disable the interrupt until the clockevent subsystem
-	 * reprograms it.
-	 */
-	sysreg_write(COMPARE, 0);
-
-	evdev->event_handler(evdev);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction timer_irqaction = {
-	.handler	= timer_interrupt,
-	/* Oprofile uses the same irq as the timer, so allow it to be shared */
-	.flags		= IRQF_TIMER | IRQF_SHARED,
-	.name		= "avr32_comparator",
-};
-
-static int comparator_next_event(unsigned long delta,
-		struct clock_event_device *evdev)
-{
-	unsigned long	flags;
-
-	raw_local_irq_save(flags);
-
-	/* The time to read COUNT then update COMPARE must be less
-	 * than the min_delta_ns value for this clockevent source.
-	 */
-	sysreg_write(COMPARE, (sysreg_read(COUNT) + delta) ? : 1);
-
-	raw_local_irq_restore(flags);
-
-	return 0;
-}
-
-static int comparator_shutdown(struct clock_event_device *evdev)
-{
-	pr_debug("%s: %s\n", __func__, evdev->name);
-	sysreg_write(COMPARE, 0);
-
-	if (disable_cpu_idle_poll) {
-		disable_cpu_idle_poll = false;
-		/*
-		 * Only disable idle poll if we have forced that
-		 * in a previous call.
-		 */
-		cpu_idle_poll_ctrl(false);
-	}
-	return 0;
-}
-
-static int comparator_set_oneshot(struct clock_event_device *evdev)
-{
-	pr_debug("%s: %s\n", __func__, evdev->name);
-
-	disable_cpu_idle_poll = true;
-	/*
-	 * If we're using the COUNT and COMPARE registers we
-	 * need to force idle poll.
-	 */
-	cpu_idle_poll_ctrl(true);
-
-	return 0;
-}
-
-static struct clock_event_device comparator = {
-	.name			= "avr32_comparator",
-	.features		= CLOCK_EVT_FEAT_ONESHOT,
-	.shift			= 16,
-	.rating			= 50,
-	.set_next_event		= comparator_next_event,
-	.set_state_shutdown	= comparator_shutdown,
-	.set_state_oneshot	= comparator_set_oneshot,
-	.tick_resume		= comparator_set_oneshot,
-};
-
-void read_persistent_clock(struct timespec *ts)
-{
-	ts->tv_sec = mktime(2007, 1, 1, 0, 0, 0);
-	ts->tv_nsec = 0;
-}
-
-void __init time_init(void)
-{
-	unsigned long counter_hz;
-	int ret;
-
-	/* figure rate for counter */
-	counter_hz = clk_get_rate(boot_cpu_data.clk);
-	ret = clocksource_register_hz(&counter, counter_hz);
-	if (ret)
-		pr_debug("timer: could not register clocksource: %d\n", ret);
-
-	/* setup COMPARE clockevent */
-	comparator.mult = div_sc(counter_hz, NSEC_PER_SEC, comparator.shift);
-	comparator.max_delta_ns = clockevent_delta2ns((u32)~0, &comparator);
-	comparator.min_delta_ns = clockevent_delta2ns(50, &comparator) + 1;
-	comparator.cpumask = cpumask_of(0);
-
-	sysreg_write(COMPARE, 0);
-	timer_irqaction.dev_id = &comparator;
-
-	ret = setup_irq(0, &timer_irqaction);
-	if (ret)
-		pr_debug("timer: could not request IRQ 0: %d\n", ret);
-	else {
-		clockevents_register_device(&comparator);
-
-		pr_info("%s: irq 0, %lu.%03lu MHz\n", comparator.name,
-				((counter_hz + 500) / 1000) / 1000,
-				((counter_hz + 500) / 1000) % 1000);
-	}
-}
diff --git a/arch/avr32/kernel/traps.c b/arch/avr32/kernel/traps.c
deleted file mode 100644
index 50b541325025..000000000000
--- a/arch/avr32/kernel/traps.c
+++ /dev/null
@@ -1,262 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/bug.h>
-#include <linux/hardirq.h>
-#include <linux/init.h>
-#include <linux/kallsyms.h>
-#include <linux/kdebug.h>
-#include <linux/extable.h>
-#include <linux/module.h>	/* print_modules */
-#include <linux/notifier.h>
-#include <linux/sched/signal.h>
-#include <linux/uaccess.h>
-
-#include <asm/addrspace.h>
-#include <asm/mmu_context.h>
-#include <asm/ocd.h>
-#include <asm/sysreg.h>
-#include <asm/traps.h>
-
-static DEFINE_SPINLOCK(die_lock);
-
-void die(const char *str, struct pt_regs *regs, long err)
-{
-	static int die_counter;
-
-	console_verbose();
-	spin_lock_irq(&die_lock);
-	bust_spinlocks(1);
-
-	printk(KERN_ALERT "Oops: %s, sig: %ld [#%d]\n",
-	       str, err, ++die_counter);
-
-	printk(KERN_EMERG);
-
-#ifdef CONFIG_PREEMPT
-	printk(KERN_CONT "PREEMPT ");
-#endif
-#ifdef CONFIG_FRAME_POINTER
-	printk(KERN_CONT "FRAME_POINTER ");
-#endif
-	if (current_cpu_data.features & AVR32_FEATURE_OCD) {
-		unsigned long did = ocd_read(DID);
-		printk(KERN_CONT "chip: 0x%03lx:0x%04lx rev %lu\n",
-		       (did >> 1) & 0x7ff,
-		       (did >> 12) & 0x7fff,
-		       (did >> 28) & 0xf);
-	} else {
-		printk(KERN_CONT "cpu: arch %u r%u / core %u r%u\n",
-		       current_cpu_data.arch_type,
-		       current_cpu_data.arch_revision,
-		       current_cpu_data.cpu_type,
-		       current_cpu_data.cpu_revision);
-	}
-
-	print_modules();
-	show_regs_log_lvl(regs, KERN_EMERG);
-	show_stack_log_lvl(current, regs->sp, regs, KERN_EMERG);
-	bust_spinlocks(0);
-	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-	spin_unlock_irq(&die_lock);
-
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
-
-	if (panic_on_oops)
-		panic("Fatal exception");
-
-	do_exit(err);
-}
-
-void _exception(long signr, struct pt_regs *regs, int code,
-		unsigned long addr)
-{
-	siginfo_t info;
-
-	if (!user_mode(regs)) {
-		const struct exception_table_entry *fixup;
-
-		/* Are we prepared to handle this kernel fault? */
-		fixup = search_exception_tables(regs->pc);
-		if (fixup) {
-			regs->pc = fixup->fixup;
-			return;
-		}
-		die("Unhandled exception in kernel mode", regs, signr);
-	}
-
-	memset(&info, 0, sizeof(info));
-	info.si_signo = signr;
-	info.si_code = code;
-	info.si_addr = (void __user *)addr;
-	force_sig_info(signr, &info, current);
-}
-
-asmlinkage void do_nmi(unsigned long ecr, struct pt_regs *regs)
-{
-	int ret;
-
-	nmi_enter();
-
-	ret = notify_die(DIE_NMI, "NMI", regs, 0, ecr, SIGINT);
-	switch (ret) {
-	case NOTIFY_OK:
-	case NOTIFY_STOP:
-		break;
-	case NOTIFY_BAD:
-		die("Fatal Non-Maskable Interrupt", regs, SIGINT);
-	default:
-		printk(KERN_ALERT "Got NMI, but nobody cared. Disabling...\n");
-		nmi_disable();
-		break;
-	}
-	nmi_exit();
-}
-
-asmlinkage void do_critical_exception(unsigned long ecr, struct pt_regs *regs)
-{
-	die("Critical exception", regs, SIGKILL);
-}
-
-asmlinkage void do_address_exception(unsigned long ecr, struct pt_regs *regs)
-{
-	_exception(SIGBUS, regs, BUS_ADRALN, regs->pc);
-}
-
-/* This way of handling undefined instructions is stolen from ARM */
-static LIST_HEAD(undef_hook);
-static DEFINE_SPINLOCK(undef_lock);
-
-void register_undef_hook(struct undef_hook *hook)
-{
-	spin_lock_irq(&undef_lock);
-	list_add(&hook->node, &undef_hook);
-	spin_unlock_irq(&undef_lock);
-}
-
-void unregister_undef_hook(struct undef_hook *hook)
-{
-	spin_lock_irq(&undef_lock);
-	list_del(&hook->node);
-	spin_unlock_irq(&undef_lock);
-}
-
-static int do_cop_absent(u32 insn)
-{
-	int cop_nr;
-	u32 cpucr;
-
-	if ((insn & 0xfdf00000) == 0xf1900000)
-		/* LDC0 */
-		cop_nr = 0;
-	else
-		cop_nr = (insn >> 13) & 0x7;
-
-	/* Try enabling the coprocessor */
-	cpucr = sysreg_read(CPUCR);
-	cpucr |= (1 << (24 + cop_nr));
-	sysreg_write(CPUCR, cpucr);
-
-	cpucr = sysreg_read(CPUCR);
-	if (!(cpucr & (1 << (24 + cop_nr))))
-		return -ENODEV;
-
-	return 0;
-}
-
-#ifdef CONFIG_BUG
-int is_valid_bugaddr(unsigned long pc)
-{
-	unsigned short opcode;
-
-	if (pc < PAGE_OFFSET)
-		return 0;
-	if (probe_kernel_address((u16 *)pc, opcode))
-		return 0;
-
-	return opcode == AVR32_BUG_OPCODE;
-}
-#endif
-
-asmlinkage void do_illegal_opcode(unsigned long ecr, struct pt_regs *regs)
-{
-	u32 insn;
-	struct undef_hook *hook;
-	void __user *pc;
-	long code;
-
-#ifdef CONFIG_BUG
-	if (!user_mode(regs) && (ecr == ECR_ILLEGAL_OPCODE)) {
-		enum bug_trap_type type;
-
-		type = report_bug(regs->pc, regs);
-		switch (type) {
-		case BUG_TRAP_TYPE_NONE:
-			break;
-		case BUG_TRAP_TYPE_WARN:
-			regs->pc += 2;
-			return;
-		case BUG_TRAP_TYPE_BUG:
-			die("Kernel BUG", regs, SIGKILL);
-		}
-	}
-#endif
-
-	local_irq_enable();
-
-	if (user_mode(regs)) {
-		pc = (void __user *)instruction_pointer(regs);
-		if (get_user(insn, (u32 __user *)pc))
-			goto invalid_area;
-
-		if (ecr == ECR_COPROC_ABSENT && !do_cop_absent(insn))
-			return;
-
-		spin_lock_irq(&undef_lock);
-		list_for_each_entry(hook, &undef_hook, node) {
-			if ((insn & hook->insn_mask) == hook->insn_val) {
-				if (hook->fn(regs, insn) == 0) {
-					spin_unlock_irq(&undef_lock);
-					return;
-				}
-			}
-		}
-		spin_unlock_irq(&undef_lock);
-	}
-
-	switch (ecr) {
-	case ECR_PRIVILEGE_VIOLATION:
-		code = ILL_PRVOPC;
-		break;
-	case ECR_COPROC_ABSENT:
-		code = ILL_COPROC;
-		break;
-	default:
-		code = ILL_ILLOPC;
-		break;
-	}
-
-	_exception(SIGILL, regs, code, regs->pc);
-	return;
-
-invalid_area:
-	_exception(SIGSEGV, regs, SEGV_MAPERR, regs->pc);
-}
-
-asmlinkage void do_fpe(unsigned long ecr, struct pt_regs *regs)
-{
-	/* We have no FPU yet */
-	_exception(SIGILL, regs, ILL_COPROC, regs->pc);
-}
-
-
-void __init trap_init(void)
-{
-
-}
diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S
deleted file mode 100644
index 17f2730eb497..000000000000
--- a/arch/avr32/kernel/vmlinux.lds.S
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * AVR32 linker script for the Linux kernel
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#define LOAD_OFFSET 0x00000000
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/cache.h>
-#include <asm/thread_info.h>
-
-OUTPUT_FORMAT("elf32-avr32", "elf32-avr32", "elf32-avr32")
-OUTPUT_ARCH(avr32)
-ENTRY(_start)
-
-/* Big endian */
-jiffies = jiffies_64 + 4;
-
-SECTIONS
-{
-	. = CONFIG_ENTRY_ADDRESS;
-	.init		: AT(ADDR(.init) - LOAD_OFFSET) {
-		_text = .;
-		__init_begin = .;
-			_sinittext = .;
-			*(.text.reset)
-			INIT_TEXT
-			/*
-			 * .exit.text is discarded at runtime, not
-			 * link time, to deal with references from
-			 * __bug_table
-			 */
-			EXIT_TEXT
-			_einittext = .;
-		. = ALIGN(4);
-		__tagtable_begin = .;
-			*(.taglist.init)
-		__tagtable_end = .;
-	}
-	INIT_DATA_SECTION(16)
-	. = ALIGN(PAGE_SIZE);
-	__init_end = .;
-
-	.text		: AT(ADDR(.text) - LOAD_OFFSET) {
-		_evba = .;
-		_stext = .;
-		*(.ex.text)
-		*(.irq.text)
-		KPROBES_TEXT
-		TEXT_TEXT
-		SCHED_TEXT
-		CPUIDLE_TEXT
-		LOCK_TEXT
-		*(.fixup)
-		*(.gnu.warning)
-		_etext = .;
-	} = 0xd703d703
-
-	EXCEPTION_TABLE(4)
-	RODATA
-
-	.data		: AT(ADDR(.data) - LOAD_OFFSET) {
-		_data = .;
-		_sdata = .;
-
-		INIT_TASK_DATA(THREAD_SIZE)
-		PAGE_ALIGNED_DATA(PAGE_SIZE);
-		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
-		*(.data.rel*)
-		DATA_DATA
-		CONSTRUCTORS
-
-		_edata = .;
-	}
-
-	BSS_SECTION(0, 8, 8)
-	_end = .;
-
-	DWARF_DEBUG
-
-	/* When something in the kernel is NOT compiled as a module, the module
-	 * cleanup code and data are put into these segments. Both can then be
-	 * thrown away, as cleanup code is never called unless it's a module.
-	 */
-	DISCARDS
-}
diff --git a/arch/avr32/lib/Makefile b/arch/avr32/lib/Makefile
deleted file mode 100644
index 084d95bac5e7..000000000000
--- a/arch/avr32/lib/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-#
-# Makefile for AVR32-specific library files
-#
-
-lib-y	:= copy_user.o clear_user.o
-lib-y	+= strncpy_from_user.o strnlen_user.o
-lib-y	+= delay.o memset.o memcpy.o findbit.o
-lib-y	+= csum_partial.o csum_partial_copy_generic.o
-lib-y	+= io-readsw.o io-readsl.o io-writesw.o io-writesl.o
-lib-y	+= io-readsb.o io-writesb.o
-lib-y	+= __avr32_lsl64.o __avr32_lsr64.o __avr32_asr64.o
diff --git a/arch/avr32/lib/__avr32_asr64.S b/arch/avr32/lib/__avr32_asr64.S
deleted file mode 100644
index 368b6bca4c76..000000000000
--- a/arch/avr32/lib/__avr32_asr64.S
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	/*
-	 * DWtype __avr32_asr64(DWtype u, word_type b)
-	 */
-	.text
-	.global	__avr32_asr64
-	.type	__avr32_asr64,@function
-__avr32_asr64:
-	cp.w	r12, 0
-	reteq	r12
-
-	rsub	r9, r12, 32
-	brle	1f
-
-	lsl	r8, r11, r9
-	lsr	r10, r10, r12
-	asr	r11, r11, r12
-	or	r10, r8
-	retal	r12
-
-1:	neg	r9
-	asr	r10, r11, r9
-	asr	r11, 31
-	retal	r12
diff --git a/arch/avr32/lib/__avr32_lsl64.S b/arch/avr32/lib/__avr32_lsl64.S
deleted file mode 100644
index f1dbc2b36257..000000000000
--- a/arch/avr32/lib/__avr32_lsl64.S
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	/*
-	 * DWtype __avr32_lsl64(DWtype u, word_type b)
-	 */
-	.text
-	.global	__avr32_lsl64
-	.type	__avr32_lsl64,@function
-__avr32_lsl64:
-	cp.w	r12, 0
-	reteq	r12
-
-	rsub	r9, r12, 32
-	brle	1f
-
-	lsr	r8, r10, r9
-	lsl	r10, r10, r12
-	lsl	r11, r11, r12
-	or	r11, r8
-	retal	r12
-
-1:	neg	r9
-	lsl	r11, r10, r9
-	mov	r10, 0
-	retal	r12
diff --git a/arch/avr32/lib/__avr32_lsr64.S b/arch/avr32/lib/__avr32_lsr64.S
deleted file mode 100644
index e65bb7f0d24c..000000000000
--- a/arch/avr32/lib/__avr32_lsr64.S
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	/*
-	 * DWtype __avr32_lsr64(DWtype u, word_type b)
-	 */
-	.text
-	.global	__avr32_lsr64
-	.type	__avr32_lsr64,@function
-__avr32_lsr64:
-	cp.w	r12, 0
-	reteq	r12
-
-	rsub	r9, r12, 32
-	brle	1f
-
-	lsl	r8, r11, r9
-	lsr	r11, r11, r12
-	lsr	r10, r10, r12
-	or	r10, r8
-	retal	r12
-
-1:	neg	r9
-	lsr	r10, r11, r9
-	mov	r11, 0
-	retal	r12
diff --git a/arch/avr32/lib/clear_user.S b/arch/avr32/lib/clear_user.S
deleted file mode 100644
index d8991b6f8eb7..000000000000
--- a/arch/avr32/lib/clear_user.S
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
-	.text
-	.align	1
-	.global	clear_user
-	.type	clear_user, "function"
-clear_user:
-	branch_if_kernel r8, __clear_user
-	ret_if_privileged r8, r12, r11, r11
-
-	.global	__clear_user
-	.type	__clear_user, "function"
-__clear_user:
-	mov	r9, r12
-	mov	r8, 0
-	andl	r9, 3, COH
-	brne	5f
-
-1:	sub	r11, 4
-	brlt	2f
-
-10:	st.w	r12++, r8
-	sub	r11, 4
-	brge	10b
-
-2:	sub	r11, -4
-	reteq	0
-
-	/* Unaligned count or address */
-	bld	r11, 1
-	brcc	12f
-11:	st.h	r12++, r8
-	sub	r11, 2
-	reteq	0
-12:	st.b	r12++, r8
-	retal	0
-
-	/* Unaligned address */
-5:	cp.w	r11, 4
-	brlt	2b
-
-	lsl	r9, 2
-	add	pc, pc, r9
-13:	st.b	r12++, r8
-	sub	r11, 1
-14:	st.b	r12++, r8
-	sub	r11, 1
-15:	st.b	r12++, r8
-	sub	r11, 1
-	rjmp	1b
-
-	.size	clear_user, . - clear_user
-	.size	__clear_user, . - __clear_user
-
-	.section .fixup, "ax"
-	.align	1
-18:	sub	r11, -4
-19:	retal	r11
-
-	.section __ex_table, "a"
-	.align	2
-	.long	10b, 18b
-	.long	11b, 19b
-	.long	12b, 19b
-	.long	13b, 19b
-	.long	14b, 19b
-	.long	15b, 19b
diff --git a/arch/avr32/lib/copy_user.S b/arch/avr32/lib/copy_user.S
deleted file mode 100644
index 075373471da1..000000000000
--- a/arch/avr32/lib/copy_user.S
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * Copy to/from userspace with optional address space checking.
- *
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
-	/*
-	 * __kernel_size_t
-	 * __copy_user(void *to, const void *from, __kernel_size_t n)
-	 *
-	 * Returns the number of bytes not copied. Might be off by
-	 * max 3 bytes if we get a fault in the main loop.
-	 *
-	 * The address-space checking functions simply fall through to
-	 * the non-checking version.
-	 */
-	.text
-	.align	1
-	.global	___copy_from_user
-	.type	___copy_from_user, @function
-___copy_from_user:
-	branch_if_kernel r8, __copy_user
-	ret_if_privileged r8, r11, r10, r10
-	rjmp	__copy_user
-	.size	___copy_from_user, . - ___copy_from_user
-
-	.global	copy_to_user
-	.type	copy_to_user, @function
-copy_to_user:
-	branch_if_kernel r8, __copy_user
-	ret_if_privileged r8, r12, r10, r10
-	.size	copy_to_user, . - copy_to_user
-
-	.global	__copy_user
-	.type	__copy_user, @function
-__copy_user:
-	mov	r9, r11
-	andl	r9, 3, COH
-	brne	6f
-
-	/* At this point, from is word-aligned */
-1:	sub	r10, 4
-	brlt	3f
-
-2:
-10:	ld.w	r8, r11++
-11:	st.w	r12++, r8
-	sub	r10, 4
-	brge	2b
-
-3:	sub	r10, -4
-	reteq	0
-
-	/*
-	 * Handle unaligned count. Need to be careful with r10 here so
-	 * that we return the correct value even if we get a fault
-	 */
-4:
-20:	ld.ub	r8, r11++
-21:	st.b	r12++, r8
-	sub	r10, 1
-	reteq	0
-22:	ld.ub	r8, r11++
-23:	st.b	r12++, r8
-	sub	r10, 1
-	reteq	0
-24:	ld.ub	r8, r11++
-25:	st.b	r12++, r8
-	retal	0
-
-	/* Handle unaligned from-pointer */
-6:	cp.w	r10, 4
-	brlt	4b
-	rsub	r9, r9, 4
-
-30:	ld.ub	r8, r11++
-31:	st.b	r12++, r8
-	sub	r10, 1
-	sub	r9, 1
-	breq	1b
-32:	ld.ub	r8, r11++
-33:	st.b	r12++, r8
-	sub	r10, 1
-	sub	r9, 1
-	breq	1b
-34:	ld.ub	r8, r11++
-35:	st.b	r12++, r8
-	sub	r10, 1
-	rjmp	1b
-	.size	__copy_user, . - __copy_user
-
-	.section .fixup,"ax"
-	.align	1
-19:	sub	r10, -4
-29:	retal	r10
-
-	.section __ex_table,"a"
-	.align	2
-	.long	10b, 19b
-	.long	11b, 19b
-	.long	20b, 29b
-	.long	21b, 29b
-	.long	22b, 29b
-	.long	23b, 29b
-	.long	24b, 29b
-	.long	25b, 29b
-	.long	30b, 29b
-	.long	31b, 29b
-	.long	32b, 29b
-	.long	33b, 29b
-	.long	34b, 29b
-	.long	35b, 29b
diff --git a/arch/avr32/lib/csum_partial.S b/arch/avr32/lib/csum_partial.S
deleted file mode 100644
index 6a262b528eb7..000000000000
--- a/arch/avr32/lib/csum_partial.S
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	/*
-	 * unsigned int csum_partial(const unsigned char *buff,
-	 *			     int len, unsigned int sum)
-	 */
-	.text
-	.global	csum_partial
-	.type	csum_partial,"function"
-	.align	1
-csum_partial:
-	/* checksum complete words, aligned or not */
-3:	sub	r11, 4
-	brlt	5f
-4:	ld.w	r9, r12++
-	add	r10, r9
-	acr	r10
-	sub	r11, 4
-	brge	4b
-
-	/* return if we had a whole number of words */
-5:	sub	r11, -4
-	reteq	r10
-
-	/* checksum any remaining bytes at the end */
-	mov	r9, 0
-	mov	r8, 0
-	cp	r11, 2
-	brlt	6f
-	ld.uh	r9, r12++
-	sub	r11, 2
-	breq	7f
-	lsl	r9, 16
-6:	ld.ub	r8, r12++
-	lsl	r8, 8
-7:	or	r9, r8
-	add	r10, r9
-	acr	r10
-
-	retal	r10
-	.size	csum_partial, . - csum_partial
diff --git a/arch/avr32/lib/csum_partial_copy_generic.S b/arch/avr32/lib/csum_partial_copy_generic.S
deleted file mode 100644
index a3a0f9b8929c..000000000000
--- a/arch/avr32/lib/csum_partial_copy_generic.S
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/errno.h>
-#include <asm/asm.h>
-
-	/*
-	 * unsigned int csum_partial_copy_generic(const char *src, char *dst, int len
-	 *					  int sum, int *src_err_ptr,
-	 *					  int *dst_err_ptr)
-	 *
-	 * Copy src to dst while checksumming, otherwise like csum_partial.
-	 */
-
-	.macro ld_src size, reg, ptr
-9999:	ld.\size \reg, \ptr
-	.section __ex_table, "a"
-	.long	9999b, fixup_ld_src
-	.previous
-	.endm
-
-	.macro st_dst size, ptr, reg
-9999:	st.\size \ptr, \reg
-	.section __ex_table, "a"
-	.long	9999b, fixup_st_dst
-	.previous
-	.endm
-
-	.text
-	.global	csum_partial_copy_generic
-	.type	csum_partial_copy_generic,"function"
-	.align	1
-csum_partial_copy_generic:
-	pushm	r4-r7,lr
-
-	/* The inner loop */
-1:	sub	r10, 4
-	brlt	5f
-2:	ld_src	w, r5, r12++
-	st_dst	w, r11++, r5
-	add	r9, r5
-	acr	r9
-	sub	r10, 4
-	brge	2b
-
-	/* return if we had a whole number of words */
-5:	sub	r10, -4
-	brne	7f
-
-6:	mov	r12, r9
-	popm	r4-r7,pc
-
-	/* handle additional bytes at the tail */
-7:	mov	r5, 0
-	mov	r4, 32
-8:	ld_src	ub, r6, r12++
-	st_dst	b, r11++, r6
-	lsl	r5, 8
-	sub	r4, 8
-	bfins	r5, r6, 0, 8
-	sub	r10, 1
-	brne	8b
-
-	lsl	r5, r5, r4
-	add	r9, r5
-	acr	r9
-	rjmp	6b
-
-	/* Exception handler */
-	.section .fixup,"ax"
-	.align	1
-fixup_ld_src:
-	mov	r9, -EFAULT
-	cp.w	r8, 0
-	breq	1f
-	st.w	r8[0], r9
-
-1:	/*
-	 * TODO: zero the complete destination - computing the rest
-	 * is too much work
-	 */
-
-	mov	r9, 0
-	rjmp	6b
-
-fixup_st_dst:
-	mov	r9, -EFAULT
-	lddsp	r8, sp[20]
-	cp.w	r8, 0
-	breq	1f
-	st.w	r8[0], r9
-1:	mov	r9, 0
-	rjmp	6b
-
-	.previous
diff --git a/arch/avr32/lib/delay.c b/arch/avr32/lib/delay.c
deleted file mode 100644
index c2f4a07dcda1..000000000000
--- a/arch/avr32/lib/delay.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- *      Precise Delay Loops for avr32
- *
- *      Copyright (C) 1993 Linus Torvalds
- *      Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
- *	Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/timex.h>
-#include <linux/param.h>
-#include <linux/types.h>
-#include <linux/init.h>
-
-#include <asm/processor.h>
-#include <asm/sysreg.h>
-
-int read_current_timer(unsigned long *timer_value)
-{
-	*timer_value = sysreg_read(COUNT);
-	return 0;
-}
-
-void __delay(unsigned long loops)
-{
-	unsigned bclock, now;
-
-	bclock = sysreg_read(COUNT);
-	do {
-		now = sysreg_read(COUNT);
-	} while ((now - bclock) < loops);
-}
-
-inline void __const_udelay(unsigned long xloops)
-{
-	unsigned long long loops;
-
-	asm("mulu.d %0, %1, %2"
-	    : "=r"(loops)
-	    : "r"(current_cpu_data.loops_per_jiffy * HZ), "r"(xloops));
-	__delay(loops >> 32);
-}
-
-void __udelay(unsigned long usecs)
-{
-	__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
-}
-
-void __ndelay(unsigned long nsecs)
-{
-	__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
-}
diff --git a/arch/avr32/lib/findbit.S b/arch/avr32/lib/findbit.S
deleted file mode 100644
index b93586460be6..000000000000
--- a/arch/avr32/lib/findbit.S
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-
-	.text
-	/*
-	 * unsigned long find_first_zero_bit(const unsigned long *addr,
-	 *				     unsigned long size)
-	 */
-ENTRY(find_first_zero_bit)
-	cp.w	r11, 0
-	reteq	r11
-	mov	r9, r11
-1:	ld.w	r8, r12[0]
-	com	r8
-	brne	.L_found
-	sub	r12, -4
-	sub	r9, 32
-	brgt	1b
-	retal	r11
-
-	/*
-	 * unsigned long find_next_zero_bit(const unsigned long *addr,
-	 *				    unsigned long size,
-	 *				    unsigned long offset)
-	 */
-ENTRY(find_next_zero_bit)
-	lsr	r8, r10, 5
-	sub	r9, r11, r10
-	retle	r11
-
-	lsl	r8, 2
-	add	r12, r8
-	andl	r10, 31, COH
-	breq	1f
-
-	/* offset is not word-aligned. Handle the first (32 - r10) bits */
-	ld.w	r8, r12[0]
-	com	r8
-	sub	r12, -4
-	lsr	r8, r8, r10
-	brne	.L_found
-
-	/* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
-	add	r9, r10
-	sub	r9, 32
-	retle	r11
-
-	/* Main loop. offset must be word-aligned */
-1:	ld.w	r8, r12[0]
-	com	r8
-	brne	.L_found
-	sub	r12, -4
-	sub	r9, 32
-	brgt	1b
-	retal	r11
-
-	/* Common return path for when a bit is actually found. */
-.L_found:
-	brev	r8
-	clz	r10, r8
-	rsub	r9, r11
-	add	r10, r9
-
-	/* XXX: If we don't have to return exactly "size" when the bit
-	   is not found, we may drop this "min" thing */
-	min	r12, r11, r10
-	retal	r12
-
-	/*
-	 * unsigned long find_first_bit(const unsigned long *addr,
-	 *				unsigned long size)
-	 */
-ENTRY(find_first_bit)
-	cp.w	r11, 0
-	reteq	r11
-	mov	r9, r11
-1:	ld.w	r8, r12[0]
-	cp.w	r8, 0
-	brne	.L_found
-	sub	r12, -4
-	sub	r9, 32
-	brgt	1b
-	retal	r11
-
-	/*
-	 * unsigned long find_next_bit(const unsigned long *addr,
-	 *			       unsigned long size,
-	 *			       unsigned long offset)
-	 */
-ENTRY(find_next_bit)
-	lsr	r8, r10, 5
-	sub	r9, r11, r10
-	retle	r11
-
-	lsl	r8, 2
-	add	r12, r8
-	andl	r10, 31, COH
-	breq	1f
-
-	/* offset is not word-aligned. Handle the first (32 - r10) bits */
-	ld.w	r8, r12[0]
-	sub	r12, -4
-	lsr	r8, r8, r10
-	brne	.L_found
-
-	/* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
-	add	r9, r10
-	sub	r9, 32
-	retle	r11
-
-	/* Main loop. offset must be word-aligned */
-1:	ld.w	r8, r12[0]
-	cp.w	r8, 0
-	brne	.L_found
-	sub	r12, -4
-	sub	r9, 32
-	brgt	1b
-	retal	r11
-
-ENTRY(find_next_bit_le)
-	lsr	r8, r10, 5
-	sub	r9, r11, r10
-	retle	r11
-
-	lsl	r8, 2
-	add	r12, r8
-	andl	r10, 31, COH
-	breq	1f
-
-	/* offset is not word-aligned. Handle the first (32 - r10) bits */
-	ldswp.w	r8, r12[0]
-	sub	r12, -4
-	lsr	r8, r8, r10
-	brne	.L_found
-
-	/* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
-	add	r9, r10
-	sub	r9, 32
-	retle	r11
-
-	/* Main loop. offset must be word-aligned */
-1:	ldswp.w	r8, r12[0]
-	cp.w	r8, 0
-	brne	.L_found
-	sub	r12, -4
-	sub	r9, 32
-	brgt	1b
-	retal	r11
-
-ENTRY(find_next_zero_bit_le)
-	lsr	r8, r10, 5
-	sub	r9, r11, r10
-	retle	r11
-
-	lsl	r8, 2
-	add	r12, r8
-	andl	r10, 31, COH
-	breq	1f
-
-	/* offset is not word-aligned. Handle the first (32 - r10) bits */
-	ldswp.w	r8, r12[0]
-	sub	r12, -4
-	com	r8
-	lsr	r8, r8, r10
-	brne	.L_found
-
-	/* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
-	add	r9, r10
-	sub	r9, 32
-	retle	r11
-
-	/* Main loop. offset must be word-aligned */
-1:	ldswp.w	r8, r12[0]
-	com	r8
-	brne	.L_found
-	sub	r12, -4
-	sub	r9, 32
-	brgt	1b
-	retal	r11
diff --git a/arch/avr32/lib/io-readsb.S b/arch/avr32/lib/io-readsb.S
deleted file mode 100644
index cb2d86945559..000000000000
--- a/arch/avr32/lib/io-readsb.S
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	.text
-.Lnot_word_aligned:
-1:	ld.ub	r8, r12[0]
-	sub	r10, 1
-	st.b	r11++, r8
-	reteq	r12
-	tst	r11, r9
-	brne	1b
-
-	/* fall through */
-
-	.global	__raw_readsb
-	.type	__raw_readsb,@function
-__raw_readsb:
-	cp.w	r10, 0
-	mov	r9, 3
-	reteq	r12
-
-	tst	r11, r9
-	brne	.Lnot_word_aligned
-
-	sub	r10, 4
-	brlt	2f
-
-1:	ldins.b	r8:t, r12[0]
-	ldins.b	r8:u, r12[0]
-	ldins.b	r8:l, r12[0]
-	ldins.b r8:b, r12[0]
-	st.w	r11++, r8
-	sub	r10, 4
-	brge	1b
-
-2:	sub	r10, -4
-	reteq	r12
-
-3:	ld.ub	r8, r12[0]
-	sub	r10, 1
-	st.b	r11++, r8
-	brne	3b
-
-	retal	r12
diff --git a/arch/avr32/lib/io-readsl.S b/arch/avr32/lib/io-readsl.S
deleted file mode 100644
index b103511ed6c4..000000000000
--- a/arch/avr32/lib/io-readsl.S
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	.global	__raw_readsl
-	.type	__raw_readsl,@function
-__raw_readsl:
-	cp.w	r10, 0
-	reteq	r12
-
-	/*
-	 * If r11 isn't properly aligned, we might get an exception on
-	 * some implementations. But there's not much we can do about it.
-	 */
-1:	ld.w	r8, r12[0]
-	sub	r10, 1
-	st.w	r11++, r8
-	brne	1b
-
-	retal	r12
diff --git a/arch/avr32/lib/io-readsw.S b/arch/avr32/lib/io-readsw.S
deleted file mode 100644
index 456be9909027..000000000000
--- a/arch/avr32/lib/io-readsw.S
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-.Lnot_word_aligned:
-	/*
-	 * Bad alignment will cause a hardware exception, which is as
-	 * good as anything. No need for us to check for proper alignment.
-	 */
-	ld.uh	r8, r12[0]
-	sub	r10, 1
-	st.h	r11++, r8
-
-	/* fall through */
-
-	.global	__raw_readsw
-	.type	__raw_readsw,@function
-__raw_readsw:
-	cp.w	r10, 0
-	reteq	r12
-	mov	r9, 3
-	tst	r11, r9
-	brne	.Lnot_word_aligned
-
-	sub	r10, 2
-	brlt	2f
-
-1:	ldins.h	r8:t, r12[0]
-	ldins.h	r8:b, r12[0]
-	st.w	r11++, r8
-	sub	r10, 2
-	brge	1b
-
-2:	sub	r10, -2
-	reteq	r12
-
-	ld.uh	r8, r12[0]
-	st.h	r11++, r8
-	retal	r12
diff --git a/arch/avr32/lib/io-writesb.S b/arch/avr32/lib/io-writesb.S
deleted file mode 100644
index b4ebaacccf68..000000000000
--- a/arch/avr32/lib/io-writesb.S
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	.text
-.Lnot_word_aligned:
-1:	ld.ub	r8, r11++
-	sub	r10, 1
-	st.b	r12[0], r8
-	reteq	r12
-	tst	r11, r9
-	brne	1b
-
-	/* fall through */
-
-	.global	__raw_writesb
-	.type	__raw_writesb,@function
-__raw_writesb:
-	cp.w	r10, 0
-	mov	r9, 3
-	reteq	r12
-
-	tst	r11, r9
-	brne	.Lnot_word_aligned
-
-	sub	r10, 4
-	brlt	2f
-
-1:	ld.w	r8, r11++
-	bfextu	r9, r8, 24, 8
-	st.b	r12[0], r9
-	bfextu	r9, r8, 16, 8
-	st.b	r12[0], r9
-	bfextu	r9, r8, 8, 8
-	st.b	r12[0], r9
-	st.b	r12[0], r8
-	sub	r10, 4
-	brge	1b
-
-2:	sub	r10, -4
-	reteq	r12
-
-3:	ld.ub	r8, r11++
-	sub	r10, 1
-	st.b	r12[0], r8
-	brne	3b
-
-	retal	r12
diff --git a/arch/avr32/lib/io-writesl.S b/arch/avr32/lib/io-writesl.S
deleted file mode 100644
index 22138b3a16e5..000000000000
--- a/arch/avr32/lib/io-writesl.S
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	.global	__raw_writesl
-	.type	__raw_writesl,@function
-__raw_writesl:
-	cp.w	r10, 0
-	reteq	r12
-
-1:	ld.w	r8, r11++
-	sub	r10, 1
-	st.w	r12[0], r8
-	brne	1b
-
-	retal	r12
diff --git a/arch/avr32/lib/io-writesw.S b/arch/avr32/lib/io-writesw.S
deleted file mode 100644
index 8c4a53f1c52a..000000000000
--- a/arch/avr32/lib/io-writesw.S
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-.Lnot_word_aligned:
-	ld.uh	r8, r11++
-	sub	r10, 1
-	st.h	r12[0], r8
-
-	.global	__raw_writesw
-	.type	__raw_writesw,@function
-__raw_writesw:
-	cp.w	r10, 0
-	mov	r9, 3
-	reteq	r12
-	tst	r11, r9
-	brne	.Lnot_word_aligned
-
-	sub	r10, 2
-	brlt	2f
-
-1:	ld.w	r8, r11++
-	bfextu	r9, r8, 16, 16
-	st.h	r12[0], r9
-	st.h	r12[0], r8
-	sub	r10, 2
-	brge	1b
-
-2:	sub	r10, -2
-	reteq	r12
-
-	ld.uh	r8, r11++
-	st.h	r12[0], r8
-	retal	r12
diff --git a/arch/avr32/lib/memcpy.S b/arch/avr32/lib/memcpy.S
deleted file mode 100644
index c2ca49d705af..000000000000
--- a/arch/avr32/lib/memcpy.S
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	/*
-	 * void *memcpy(void *to, const void *from, unsigned long n)
-	 *
-	 * This implementation does word-aligned loads in the main loop,
-	 * possibly sacrificing alignment of stores.
-	 *
-	 * Hopefully, in most cases, both "to" and "from" will be
-	 * word-aligned to begin with.
-	 */
-	.text
-	.global	memcpy
-	.type	memcpy, @function
-memcpy:
-	mov	r9, r11
-	andl	r9, 3, COH
-	brne	1f
-
-	/* At this point, "from" is word-aligned */
-2:	mov	r9, r12
-5:	sub	r10, 4
-	brlt	4f
-
-3:	ld.w	r8, r11++
-	sub	r10, 4
-	st.w	r12++, r8
-	brge	3b
-
-4:	neg	r10
-	reteq	r9
-
-	/* Handle unaligned count */
-	lsl	r10, 2
-	add	pc, pc, r10
-	ld.ub	r8, r11++
-	st.b	r12++, r8
-	ld.ub	r8, r11++
-	st.b	r12++, r8
-	ld.ub	r8, r11++
-	st.b	r12++, r8
-	retal	r9
-
-	/* Handle unaligned "from" pointer */
-1:	sub	r10, 4
-	movlt	r9, r12
-	brlt	4b
-	add	r10, r9
-	lsl	r9, 2
-	add	pc, pc, r9
-	ld.ub	r8, r11++
-	st.b	r12++, r8
-	ld.ub	r8, r11++
-	st.b	r12++, r8
-	ld.ub	r8, r11++
-	st.b	r12++, r8
-	mov	r8, r12
-	add	pc, pc, r9
-	sub	r8, 1
-	nop
-	sub	r8, 1
-	nop
-	sub	r8, 1
-	nop
-	mov	r9, r8
-	rjmp	5b
diff --git a/arch/avr32/lib/memset.S b/arch/avr32/lib/memset.S
deleted file mode 100644
index 40da32c0480c..000000000000
--- a/arch/avr32/lib/memset.S
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/arch/arm/lib/memset.S
- *   Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * ASM optimised string functions
- */
-#include <asm/asm.h>
-
-	/*
-	 * r12:	void *b
-	 * r11:	int c
-	 * r10:	size_t len
-	 *
-	 * Returns b in r12
-	 */
-	.text
-	.global	memset
-	.type	memset, @function
-	.align	5
-memset:
-	mov	r9, r12
-	mov	r8, r12
-	or	r11, r11, r11 << 8
-	andl	r9, 3, COH
-	brne	1f
-
-2:	or	r11, r11, r11 << 16
-	sub	r10, 4
-	brlt	5f
-
-	/* Let's do some real work */
-4:	st.w	r8++, r11
-	sub	r10, 4
-	brge	4b
-
-	/*
-	 * When we get here, we've got less than 4 bytes to set. r10
-	 * might be negative.
-	 */
-5:	sub	r10, -4
-	reteq	r12
-
-	/* Fastpath ends here, exactly 32 bytes from memset */
-
-	/* Handle unaligned count or pointer */
-	bld	r10, 1
-	brcc	6f
-	st.b	r8++, r11
-	st.b	r8++, r11
-	bld	r10, 0
-	retcc	r12
-6:	st.b	r8++, r11
-	retal	r12
-
-	/* Handle unaligned pointer */
-1:	sub	r10, 4
-	brlt	5b
-	add	r10, r9
-	lsl	r9, 1
-	add	pc, r9
-	st.b	r8++, r11
-	st.b	r8++, r11
-	st.b	r8++, r11
-	rjmp	2b
-
-	.size	memset, . - memset
diff --git a/arch/avr32/lib/strncpy_from_user.S b/arch/avr32/lib/strncpy_from_user.S
deleted file mode 100644
index 72bd50599ec6..000000000000
--- a/arch/avr32/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * Copy to/from userspace with optional address space checking.
- *
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/errno.h>
-
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
-	/*
-	 * long strncpy_from_user(char *dst, const char *src, long count)
-	 *
-	 * On success, returns the length of the string, not including
-	 * the terminating NUL.
-	 *
-	 * If the string is longer than count, returns count
-	 *
-	 * If userspace access fails, returns -EFAULT
-	 */
-	.text
-	.align	1
-	.global	strncpy_from_user
-	.type	strncpy_from_user, "function"
-strncpy_from_user:
-	mov	r9, -EFAULT
-	branch_if_kernel r8, __strncpy_from_user
-	ret_if_privileged r8, r11, r10, r9
-
-	.global	__strncpy_from_user
-	.type	__strncpy_from_user, "function"
-__strncpy_from_user:
-	cp.w	r10, 0
-	reteq	0
-
-	mov	r9, r10
-
-1:	ld.ub	r8, r11++
-	st.b	r12++, r8
-	cp.w	r8, 0
-	breq	2f
-	sub	r9, 1
-	brne	1b
-
-2:	sub	r10, r9
-	retal	r10
-
-	.section .fixup, "ax"
-	.align	1
-3:	mov	r12, -EFAULT
-	retal	r12
-
-	.section __ex_table, "a"
-	.align	2
-	.long	1b, 3b
diff --git a/arch/avr32/lib/strnlen_user.S b/arch/avr32/lib/strnlen_user.S
deleted file mode 100644
index e46f4724962b..000000000000
--- a/arch/avr32/lib/strnlen_user.S
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * Copy to/from userspace with optional address space checking.
- *
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/processor.h>
-#include <asm/asm.h>
-
-	.text
-	.align	1
-	.global	strnlen_user
-	.type	strnlen_user, "function"
-strnlen_user:
-	branch_if_kernel r8, __strnlen_user
-	sub	r8, r11, 1
-	add	r8, r12
-	retcs	0
-	brmi	adjust_length	/* do a closer inspection */
-
-	.global	__strnlen_user
-	.type	__strnlen_user, "function"
-__strnlen_user:
-	mov	r10, r12
-
-10:	ld.ub	r8, r12++
-	cp.w	r8, 0
-	breq	2f
-	sub	r11, 1
-	brne	10b
-
-	sub	r12, -1
-2:	sub	r12, r10
-	retal	r12
-
-
-	.type	adjust_length, "function"
-adjust_length:
-	cp.w	r12, 0		/* addr must always be < TASK_SIZE */
-	retmi	0
-
-	pushm	lr
-	lddpc	lr, _task_size
-	sub	r11, lr, r12
-	mov	r9, r11
-	call	__strnlen_user
-	cp.w	r12, r9
-	brgt	1f
-	popm	pc
-1:	popm	pc, r12=0
-
-	.align	2
-_task_size:
-	.long	TASK_SIZE
-
-	.section .fixup, "ax"
-	.align	1
-19:	retal	0
-
-	.section __ex_table, "a"
-	.align	2
-	.long	10b, 19b
diff --git a/arch/avr32/mach-at32ap/Kconfig b/arch/avr32/mach-at32ap/Kconfig
deleted file mode 100644
index a7bbcc82058e..000000000000
--- a/arch/avr32/mach-at32ap/Kconfig
+++ /dev/null
@@ -1,31 +0,0 @@
-if PLATFORM_AT32AP
-
-menu "Atmel AVR32 AP options"
-
-choice
-	prompt "AT32AP700x static memory bus width"
-	depends on CPU_AT32AP700X
-	default AP700X_16_BIT_SMC
-	help
-	  Define the width of the AP7000 external static memory interface.
-	  This is used to determine how to mangle the address and/or data
-	  when doing little-endian port access.
-
-	  The current code can only support a single external memory bus
-	  width for all chip selects, excluding the flash (which is using
-	  raw access and is thus not affected by any of this.)
-
-config AP700X_32_BIT_SMC
-	bool "32 bit"
-
-config AP700X_16_BIT_SMC
-	bool "16 bit"
-
-config AP700X_8_BIT_SMC
-	bool "8 bit"
-
-endchoice
-
-endmenu
-
-endif # PLATFORM_AT32AP
diff --git a/arch/avr32/mach-at32ap/Makefile b/arch/avr32/mach-at32ap/Makefile
deleted file mode 100644
index fc09ec4bc725..000000000000
--- a/arch/avr32/mach-at32ap/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-obj-y				+= pdc.o clock.o intc.o extint.o pio.o hsmc.o
-obj-y				+= hmatrix.o
-obj-$(CONFIG_CPU_AT32AP700X)	+= at32ap700x.o pm-at32ap700x.o
-obj-$(CONFIG_PM)		+= pm.o
-
-ifeq ($(CONFIG_PM_DEBUG),y)
-CFLAGS_pm.o	+= -DDEBUG
-endif
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
deleted file mode 100644
index 00d6dcc1d9b6..000000000000
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ /dev/null
@@ -1,2368 +0,0 @@
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/platform_data/dma-dw.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/spi/spi.h>
-#include <linux/usb/atmel_usba_udc.h>
-
-#include <linux/atmel-mci.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/hmatrix.h>
-#include <mach/portmux.h>
-#include <mach/sram.h>
-
-#include <sound/atmel-abdac.h>
-#include <sound/atmel-ac97c.h>
-
-#include <video/atmel_lcdc.h>
-
-#include "clock.h"
-#include "pio.h"
-#include "pm.h"
-
-
-#define PBMEM(base)					\
-	{						\
-		.start		= base,			\
-		.end		= base + 0x3ff,		\
-		.flags		= IORESOURCE_MEM,	\
-	}
-#define IRQ(num)					\
-	{						\
-		.start		= num,			\
-		.end		= num,			\
-		.flags		= IORESOURCE_IRQ,	\
-	}
-#define NAMED_IRQ(num, _name)				\
-	{						\
-		.start		= num,			\
-		.end		= num,			\
-		.name		= _name,		\
-		.flags		= IORESOURCE_IRQ,	\
-	}
-
-/* REVISIT these assume *every* device supports DMA, but several
- * don't ... tc, smc, pio, rtc, watchdog, pwm, ps2, and more.
- */
-#define DEFINE_DEV(_name, _id)					\
-static u64 _name##_id##_dma_mask = DMA_BIT_MASK(32);		\
-static struct platform_device _name##_id##_device = {		\
-	.name		= #_name,				\
-	.id		= _id,					\
-	.dev		= {					\
-		.dma_mask = &_name##_id##_dma_mask,		\
-		.coherent_dma_mask = DMA_BIT_MASK(32),		\
-	},							\
-	.resource	= _name##_id##_resource,		\
-	.num_resources	= ARRAY_SIZE(_name##_id##_resource),	\
-}
-#define DEFINE_DEV_DATA(_name, _id)				\
-static u64 _name##_id##_dma_mask = DMA_BIT_MASK(32);		\
-static struct platform_device _name##_id##_device = {		\
-	.name		= #_name,				\
-	.id		= _id,					\
-	.dev		= {					\
-		.dma_mask = &_name##_id##_dma_mask,		\
-		.platform_data	= &_name##_id##_data,		\
-		.coherent_dma_mask = DMA_BIT_MASK(32),		\
-	},							\
-	.resource	= _name##_id##_resource,		\
-	.num_resources	= ARRAY_SIZE(_name##_id##_resource),	\
-}
-
-#define select_peripheral(port, pin_mask, periph, flags)	\
-	at32_select_periph(GPIO_##port##_BASE, pin_mask,	\
-			   GPIO_##periph, flags)
-
-#define DEV_CLK(_name, devname, bus, _index)			\
-static struct clk devname##_##_name = {				\
-	.name		= #_name,				\
-	.dev		= &devname##_device.dev,		\
-	.parent		= &bus##_clk,				\
-	.mode		= bus##_clk_mode,			\
-	.get_rate	= bus##_clk_get_rate,			\
-	.index		= _index,				\
-}
-
-static DEFINE_SPINLOCK(pm_lock);
-
-static struct clk osc0;
-static struct clk osc1;
-
-static unsigned long osc_get_rate(struct clk *clk)
-{
-	return at32_board_osc_rates[clk->index];
-}
-
-static unsigned long pll_get_rate(struct clk *clk, unsigned long control)
-{
-	unsigned long div, mul, rate;
-
-	div = PM_BFEXT(PLLDIV, control) + 1;
-	mul = PM_BFEXT(PLLMUL, control) + 1;
-
-	rate = clk->parent->get_rate(clk->parent);
-	rate = (rate + div / 2) / div;
-	rate *= mul;
-
-	return rate;
-}
-
-static long pll_set_rate(struct clk *clk, unsigned long rate,
-			 u32 *pll_ctrl)
-{
-	unsigned long mul;
-	unsigned long mul_best_fit = 0;
-	unsigned long div;
-	unsigned long div_min;
-	unsigned long div_max;
-	unsigned long div_best_fit = 0;
-	unsigned long base;
-	unsigned long pll_in;
-	unsigned long actual = 0;
-	unsigned long rate_error;
-	unsigned long rate_error_prev = ~0UL;
-	u32 ctrl;
-
-	/* Rate must be between 80 MHz and 200 Mhz. */
-	if (rate < 80000000UL || rate > 200000000UL)
-		return -EINVAL;
-
-	ctrl = PM_BF(PLLOPT, 4);
-	base = clk->parent->get_rate(clk->parent);
-
-	/* PLL input frequency must be between 6 MHz and 32 MHz. */
-	div_min = DIV_ROUND_UP(base, 32000000UL);
-	div_max = base / 6000000UL;
-
-	if (div_max < div_min)
-		return -EINVAL;
-
-	for (div = div_min; div <= div_max; div++) {
-		pll_in = (base + div / 2) / div;
-		mul = (rate + pll_in / 2) / pll_in;
-
-		if (mul == 0)
-			continue;
-
-		actual = pll_in * mul;
-		rate_error = abs(actual - rate);
-
-		if (rate_error < rate_error_prev) {
-			mul_best_fit = mul;
-			div_best_fit = div;
-			rate_error_prev = rate_error;
-		}
-
-		if (rate_error == 0)
-			break;
-	}
-
-	if (div_best_fit == 0)
-		return -EINVAL;
-
-	ctrl |= PM_BF(PLLMUL, mul_best_fit - 1);
-	ctrl |= PM_BF(PLLDIV, div_best_fit - 1);
-	ctrl |= PM_BF(PLLCOUNT, 16);
-
-	if (clk->parent == &osc1)
-		ctrl |= PM_BIT(PLLOSC);
-
-	*pll_ctrl = ctrl;
-
-	return actual;
-}
-
-static unsigned long pll0_get_rate(struct clk *clk)
-{
-	u32 control;
-
-	control = pm_readl(PLL0);
-
-	return pll_get_rate(clk, control);
-}
-
-static void pll1_mode(struct clk *clk, int enabled)
-{
-	unsigned long timeout;
-	u32 status;
-	u32 ctrl;
-
-	ctrl = pm_readl(PLL1);
-
-	if (enabled) {
-		if (!PM_BFEXT(PLLMUL, ctrl) && !PM_BFEXT(PLLDIV, ctrl)) {
-			pr_debug("clk %s: failed to enable, rate not set\n",
-					clk->name);
-			return;
-		}
-
-		ctrl |= PM_BIT(PLLEN);
-		pm_writel(PLL1, ctrl);
-
-		/* Wait for PLL lock. */
-		for (timeout = 10000; timeout; timeout--) {
-			status = pm_readl(ISR);
-			if (status & PM_BIT(LOCK1))
-				break;
-			udelay(10);
-		}
-
-		if (!(status & PM_BIT(LOCK1)))
-			printk(KERN_ERR "clk %s: timeout waiting for lock\n",
-					clk->name);
-	} else {
-		ctrl &= ~PM_BIT(PLLEN);
-		pm_writel(PLL1, ctrl);
-	}
-}
-
-static unsigned long pll1_get_rate(struct clk *clk)
-{
-	u32 control;
-
-	control = pm_readl(PLL1);
-
-	return pll_get_rate(clk, control);
-}
-
-static long pll1_set_rate(struct clk *clk, unsigned long rate, int apply)
-{
-	u32 ctrl = 0;
-	unsigned long actual_rate;
-
-	actual_rate = pll_set_rate(clk, rate, &ctrl);
-
-	if (apply) {
-		if (actual_rate != rate)
-			return -EINVAL;
-		if (clk->users > 0)
-			return -EBUSY;
-		pr_debug(KERN_INFO "clk %s: new rate %lu (actual rate %lu)\n",
-				clk->name, rate, actual_rate);
-		pm_writel(PLL1, ctrl);
-	}
-
-	return actual_rate;
-}
-
-static int pll1_set_parent(struct clk *clk, struct clk *parent)
-{
-	u32 ctrl;
-
-	if (clk->users > 0)
-		return -EBUSY;
-
-	ctrl = pm_readl(PLL1);
-	WARN_ON(ctrl & PM_BIT(PLLEN));
-
-	if (parent == &osc0)
-		ctrl &= ~PM_BIT(PLLOSC);
-	else if (parent == &osc1)
-		ctrl |= PM_BIT(PLLOSC);
-	else
-		return -EINVAL;
-
-	pm_writel(PLL1, ctrl);
-	clk->parent = parent;
-
-	return 0;
-}
-
-/*
- * The AT32AP7000 has five primary clock sources: One 32kHz
- * oscillator, two crystal oscillators and two PLLs.
- */
-static struct clk osc32k = {
-	.name		= "osc32k",
-	.get_rate	= osc_get_rate,
-	.users		= 1,
-	.index		= 0,
-};
-static struct clk osc0 = {
-	.name		= "osc0",
-	.get_rate	= osc_get_rate,
-	.users		= 1,
-	.index		= 1,
-};
-static struct clk osc1 = {
-	.name		= "osc1",
-	.get_rate	= osc_get_rate,
-	.index		= 2,
-};
-static struct clk pll0 = {
-	.name		= "pll0",
-	.get_rate	= pll0_get_rate,
-	.parent		= &osc0,
-};
-static struct clk pll1 = {
-	.name		= "pll1",
-	.mode		= pll1_mode,
-	.get_rate	= pll1_get_rate,
-	.set_rate	= pll1_set_rate,
-	.set_parent	= pll1_set_parent,
-	.parent		= &osc0,
-};
-
-/*
- * The main clock can be either osc0 or pll0.  The boot loader may
- * have chosen one for us, so we don't really know which one until we
- * have a look at the SM.
- */
-static struct clk *main_clock;
-
-/*
- * Synchronous clocks are generated from the main clock. The clocks
- * must satisfy the constraint
- *   fCPU >= fHSB >= fPB
- * i.e. each clock must not be faster than its parent.
- */
-static unsigned long bus_clk_get_rate(struct clk *clk, unsigned int shift)
-{
-	return main_clock->get_rate(main_clock) >> shift;
-};
-
-static void cpu_clk_mode(struct clk *clk, int enabled)
-{
-	unsigned long flags;
-	u32 mask;
-
-	spin_lock_irqsave(&pm_lock, flags);
-	mask = pm_readl(CPU_MASK);
-	if (enabled)
-		mask |= 1 << clk->index;
-	else
-		mask &= ~(1 << clk->index);
-	pm_writel(CPU_MASK, mask);
-	spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-static unsigned long cpu_clk_get_rate(struct clk *clk)
-{
-	unsigned long cksel, shift = 0;
-
-	cksel = pm_readl(CKSEL);
-	if (cksel & PM_BIT(CPUDIV))
-		shift = PM_BFEXT(CPUSEL, cksel) + 1;
-
-	return bus_clk_get_rate(clk, shift);
-}
-
-static long cpu_clk_set_rate(struct clk *clk, unsigned long rate, int apply)
-{
-	u32 control;
-	unsigned long parent_rate, child_div, actual_rate, div;
-
-	parent_rate = clk->parent->get_rate(clk->parent);
-	control = pm_readl(CKSEL);
-
-	if (control & PM_BIT(HSBDIV))
-		child_div = 1 << (PM_BFEXT(HSBSEL, control) + 1);
-	else
-		child_div = 1;
-
-	if (rate > 3 * (parent_rate / 4) || child_div == 1) {
-		actual_rate = parent_rate;
-		control &= ~PM_BIT(CPUDIV);
-	} else {
-		unsigned int cpusel;
-		div = (parent_rate + rate / 2) / rate;
-		if (div > child_div)
-			div = child_div;
-		cpusel = (div > 1) ? (fls(div) - 2) : 0;
-		control = PM_BIT(CPUDIV) | PM_BFINS(CPUSEL, cpusel, control);
-		actual_rate = parent_rate / (1 << (cpusel + 1));
-	}
-
-	pr_debug("clk %s: new rate %lu (actual rate %lu)\n",
-			clk->name, rate, actual_rate);
-
-	if (apply)
-		pm_writel(CKSEL, control);
-
-	return actual_rate;
-}
-
-static void hsb_clk_mode(struct clk *clk, int enabled)
-{
-	unsigned long flags;
-	u32 mask;
-
-	spin_lock_irqsave(&pm_lock, flags);
-	mask = pm_readl(HSB_MASK);
-	if (enabled)
-		mask |= 1 << clk->index;
-	else
-		mask &= ~(1 << clk->index);
-	pm_writel(HSB_MASK, mask);
-	spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-static unsigned long hsb_clk_get_rate(struct clk *clk)
-{
-	unsigned long cksel, shift = 0;
-
-	cksel = pm_readl(CKSEL);
-	if (cksel & PM_BIT(HSBDIV))
-		shift = PM_BFEXT(HSBSEL, cksel) + 1;
-
-	return bus_clk_get_rate(clk, shift);
-}
-
-void pba_clk_mode(struct clk *clk, int enabled)
-{
-	unsigned long flags;
-	u32 mask;
-
-	spin_lock_irqsave(&pm_lock, flags);
-	mask = pm_readl(PBA_MASK);
-	if (enabled)
-		mask |= 1 << clk->index;
-	else
-		mask &= ~(1 << clk->index);
-	pm_writel(PBA_MASK, mask);
-	spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-unsigned long pba_clk_get_rate(struct clk *clk)
-{
-	unsigned long cksel, shift = 0;
-
-	cksel = pm_readl(CKSEL);
-	if (cksel & PM_BIT(PBADIV))
-		shift = PM_BFEXT(PBASEL, cksel) + 1;
-
-	return bus_clk_get_rate(clk, shift);
-}
-
-static void pbb_clk_mode(struct clk *clk, int enabled)
-{
-	unsigned long flags;
-	u32 mask;
-
-	spin_lock_irqsave(&pm_lock, flags);
-	mask = pm_readl(PBB_MASK);
-	if (enabled)
-		mask |= 1 << clk->index;
-	else
-		mask &= ~(1 << clk->index);
-	pm_writel(PBB_MASK, mask);
-	spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-static unsigned long pbb_clk_get_rate(struct clk *clk)
-{
-	unsigned long cksel, shift = 0;
-
-	cksel = pm_readl(CKSEL);
-	if (cksel & PM_BIT(PBBDIV))
-		shift = PM_BFEXT(PBBSEL, cksel) + 1;
-
-	return bus_clk_get_rate(clk, shift);
-}
-
-static struct clk cpu_clk = {
-	.name		= "cpu",
-	.get_rate	= cpu_clk_get_rate,
-	.set_rate	= cpu_clk_set_rate,
-	.users		= 1,
-};
-static struct clk hsb_clk = {
-	.name		= "hsb",
-	.parent		= &cpu_clk,
-	.get_rate	= hsb_clk_get_rate,
-};
-static struct clk pba_clk = {
-	.name		= "pba",
-	.parent		= &hsb_clk,
-	.mode		= hsb_clk_mode,
-	.get_rate	= pba_clk_get_rate,
-	.index		= 1,
-};
-static struct clk pbb_clk = {
-	.name		= "pbb",
-	.parent		= &hsb_clk,
-	.mode		= hsb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.users		= 1,
-	.index		= 2,
-};
-
-/* --------------------------------------------------------------------
- *  Generic Clock operations
- * -------------------------------------------------------------------- */
-
-static void genclk_mode(struct clk *clk, int enabled)
-{
-	u32 control;
-
-	control = pm_readl(GCCTRL(clk->index));
-	if (enabled)
-		control |= PM_BIT(CEN);
-	else
-		control &= ~PM_BIT(CEN);
-	pm_writel(GCCTRL(clk->index), control);
-}
-
-static unsigned long genclk_get_rate(struct clk *clk)
-{
-	u32 control;
-	unsigned long div = 1;
-
-	control = pm_readl(GCCTRL(clk->index));
-	if (control & PM_BIT(DIVEN))
-		div = 2 * (PM_BFEXT(DIV, control) + 1);
-
-	return clk->parent->get_rate(clk->parent) / div;
-}
-
-static long genclk_set_rate(struct clk *clk, unsigned long rate, int apply)
-{
-	u32 control;
-	unsigned long parent_rate, actual_rate, div;
-
-	parent_rate = clk->parent->get_rate(clk->parent);
-	control = pm_readl(GCCTRL(clk->index));
-
-	if (rate > 3 * parent_rate / 4) {
-		actual_rate = parent_rate;
-		control &= ~PM_BIT(DIVEN);
-	} else {
-		div = (parent_rate + rate) / (2 * rate) - 1;
-		control = PM_BFINS(DIV, div, control) | PM_BIT(DIVEN);
-		actual_rate = parent_rate / (2 * (div + 1));
-	}
-
-	dev_dbg(clk->dev, "clk %s: new rate %lu (actual rate %lu)\n",
-		clk->name, rate, actual_rate);
-
-	if (apply)
-		pm_writel(GCCTRL(clk->index), control);
-
-	return actual_rate;
-}
-
-int genclk_set_parent(struct clk *clk, struct clk *parent)
-{
-	u32 control;
-
-	dev_dbg(clk->dev, "clk %s: new parent %s (was %s)\n",
-		clk->name, parent->name, clk->parent->name);
-
-	control = pm_readl(GCCTRL(clk->index));
-
-	if (parent == &osc1 || parent == &pll1)
-		control |= PM_BIT(OSCSEL);
-	else if (parent == &osc0 || parent == &pll0)
-		control &= ~PM_BIT(OSCSEL);
-	else
-		return -EINVAL;
-
-	if (parent == &pll0 || parent == &pll1)
-		control |= PM_BIT(PLLSEL);
-	else
-		control &= ~PM_BIT(PLLSEL);
-
-	pm_writel(GCCTRL(clk->index), control);
-	clk->parent = parent;
-
-	return 0;
-}
-
-static void __init genclk_init_parent(struct clk *clk)
-{
-	u32 control;
-	struct clk *parent;
-
-	BUG_ON(clk->index > 7);
-
-	control = pm_readl(GCCTRL(clk->index));
-	if (control & PM_BIT(OSCSEL))
-		parent = (control & PM_BIT(PLLSEL)) ? &pll1 : &osc1;
-	else
-		parent = (control & PM_BIT(PLLSEL)) ? &pll0 : &osc0;
-
-	clk->parent = parent;
-}
-
-static struct resource dw_dmac0_resource[] = {
-	PBMEM(0xff200000),
-	IRQ(2),
-};
-DEFINE_DEV(dw_dmac, 0);
-DEV_CLK(hclk, dw_dmac0, hsb, 10);
-
-/* --------------------------------------------------------------------
- *  System peripherals
- * -------------------------------------------------------------------- */
-static struct resource at32_pm0_resource[] = {
-	{
-		.start	= 0xfff00000,
-		.end	= 0xfff0007f,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(20),
-};
-
-static struct resource at32ap700x_rtc0_resource[] = {
-	{
-		.start	= 0xfff00080,
-		.end	= 0xfff000af,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(21),
-};
-
-static struct resource at32_wdt0_resource[] = {
-	{
-		.start	= 0xfff000b0,
-		.end	= 0xfff000cf,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct resource at32_eic0_resource[] = {
-	{
-		.start	= 0xfff00100,
-		.end	= 0xfff0013f,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(19),
-};
-
-DEFINE_DEV(at32_pm, 0);
-DEFINE_DEV(at32ap700x_rtc, 0);
-DEFINE_DEV(at32_wdt, 0);
-DEFINE_DEV(at32_eic, 0);
-
-/*
- * Peripheral clock for PM, RTC, WDT and EIC. PM will ensure that this
- * is always running.
- */
-static struct clk at32_pm_pclk = {
-	.name		= "pclk",
-	.dev		= &at32_pm0_device.dev,
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.users		= 1,
-	.index		= 0,
-};
-
-static struct resource intc0_resource[] = {
-	PBMEM(0xfff00400),
-};
-struct platform_device at32_intc0_device = {
-	.name		= "intc",
-	.id		= 0,
-	.resource	= intc0_resource,
-	.num_resources	= ARRAY_SIZE(intc0_resource),
-};
-DEV_CLK(pclk, at32_intc0, pbb, 1);
-
-static struct clk ebi_clk = {
-	.name		= "ebi",
-	.parent		= &hsb_clk,
-	.mode		= hsb_clk_mode,
-	.get_rate	= hsb_clk_get_rate,
-	.users		= 1,
-};
-static struct clk hramc_clk = {
-	.name		= "hramc",
-	.parent		= &hsb_clk,
-	.mode		= hsb_clk_mode,
-	.get_rate	= hsb_clk_get_rate,
-	.users		= 1,
-	.index		= 3,
-};
-static struct clk sdramc_clk = {
-	.name		= "sdramc_clk",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.users		= 1,
-	.index		= 14,
-};
-
-static struct resource smc0_resource[] = {
-	PBMEM(0xfff03400),
-};
-DEFINE_DEV(smc, 0);
-DEV_CLK(pclk, smc0, pbb, 13);
-DEV_CLK(mck, smc0, hsb, 0);
-
-static struct platform_device pdc_device = {
-	.name		= "pdc",
-	.id		= 0,
-};
-DEV_CLK(hclk, pdc, hsb, 4);
-DEV_CLK(pclk, pdc, pba, 16);
-
-static struct clk pico_clk = {
-	.name		= "pico",
-	.parent		= &cpu_clk,
-	.mode		= cpu_clk_mode,
-	.get_rate	= cpu_clk_get_rate,
-	.users		= 1,
-};
-
-/* --------------------------------------------------------------------
- * HMATRIX
- * -------------------------------------------------------------------- */
-
-struct clk at32_hmatrix_clk = {
-	.name		= "hmatrix_clk",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.index		= 2,
-	.users		= 1,
-};
-
-/*
- * Set bits in the HMATRIX Special Function Register (SFR) used by the
- * External Bus Interface (EBI). This can be used to enable special
- * features like CompactFlash support, NAND Flash support, etc. on
- * certain chipselects.
- */
-static inline void set_ebi_sfr_bits(u32 mask)
-{
-	hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, mask);
-}
-
-/* --------------------------------------------------------------------
- *  Timer/Counter (TC)
- * -------------------------------------------------------------------- */
-
-static struct resource at32_tcb0_resource[] = {
-	PBMEM(0xfff00c00),
-	IRQ(22),
-};
-static struct platform_device at32_tcb0_device = {
-	.name		= "atmel_tcb",
-	.id		= 0,
-	.resource	= at32_tcb0_resource,
-	.num_resources	= ARRAY_SIZE(at32_tcb0_resource),
-};
-DEV_CLK(t0_clk, at32_tcb0, pbb, 3);
-
-static struct resource at32_tcb1_resource[] = {
-	PBMEM(0xfff01000),
-	IRQ(23),
-};
-static struct platform_device at32_tcb1_device = {
-	.name		= "atmel_tcb",
-	.id		= 1,
-	.resource	= at32_tcb1_resource,
-	.num_resources	= ARRAY_SIZE(at32_tcb1_resource),
-};
-DEV_CLK(t0_clk, at32_tcb1, pbb, 4);
-
-/* --------------------------------------------------------------------
- *  PIO
- * -------------------------------------------------------------------- */
-
-static struct resource pio0_resource[] = {
-	PBMEM(0xffe02800),
-	IRQ(13),
-};
-DEFINE_DEV(pio, 0);
-DEV_CLK(mck, pio0, pba, 10);
-
-static struct resource pio1_resource[] = {
-	PBMEM(0xffe02c00),
-	IRQ(14),
-};
-DEFINE_DEV(pio, 1);
-DEV_CLK(mck, pio1, pba, 11);
-
-static struct resource pio2_resource[] = {
-	PBMEM(0xffe03000),
-	IRQ(15),
-};
-DEFINE_DEV(pio, 2);
-DEV_CLK(mck, pio2, pba, 12);
-
-static struct resource pio3_resource[] = {
-	PBMEM(0xffe03400),
-	IRQ(16),
-};
-DEFINE_DEV(pio, 3);
-DEV_CLK(mck, pio3, pba, 13);
-
-static struct resource pio4_resource[] = {
-	PBMEM(0xffe03800),
-	IRQ(17),
-};
-DEFINE_DEV(pio, 4);
-DEV_CLK(mck, pio4, pba, 14);
-
-static int __init system_device_init(void)
-{
-	platform_device_register(&at32_pm0_device);
-	platform_device_register(&at32_intc0_device);
-	platform_device_register(&at32ap700x_rtc0_device);
-	platform_device_register(&at32_wdt0_device);
-	platform_device_register(&at32_eic0_device);
-	platform_device_register(&smc0_device);
-	platform_device_register(&pdc_device);
-	platform_device_register(&dw_dmac0_device);
-
-	platform_device_register(&at32_tcb0_device);
-	platform_device_register(&at32_tcb1_device);
-
-	platform_device_register(&pio0_device);
-	platform_device_register(&pio1_device);
-	platform_device_register(&pio2_device);
-	platform_device_register(&pio3_device);
-	platform_device_register(&pio4_device);
-
-	return 0;
-}
-core_initcall(system_device_init);
-
-/* --------------------------------------------------------------------
- *  PSIF
- * -------------------------------------------------------------------- */
-static struct resource atmel_psif0_resource[] __initdata = {
-	{
-		.start	= 0xffe03c00,
-		.end	= 0xffe03cff,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(18),
-};
-static struct clk atmel_psif0_pclk = {
-	.name		= "pclk",
-	.parent		= &pba_clk,
-	.mode		= pba_clk_mode,
-	.get_rate	= pba_clk_get_rate,
-	.index		= 15,
-};
-
-static struct resource atmel_psif1_resource[] __initdata = {
-	{
-		.start	= 0xffe03d00,
-		.end	= 0xffe03dff,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(18),
-};
-static struct clk atmel_psif1_pclk = {
-	.name		= "pclk",
-	.parent		= &pba_clk,
-	.mode		= pba_clk_mode,
-	.get_rate	= pba_clk_get_rate,
-	.index		= 15,
-};
-
-struct platform_device *__init at32_add_device_psif(unsigned int id)
-{
-	struct platform_device *pdev;
-	u32 pin_mask;
-
-	if (!(id == 0 || id == 1))
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_psif", id);
-	if (!pdev)
-		return NULL;
-
-	switch (id) {
-	case 0:
-		pin_mask  = (1 << 8) | (1 << 9); /* CLOCK & DATA */
-
-		if (platform_device_add_resources(pdev, atmel_psif0_resource,
-					ARRAY_SIZE(atmel_psif0_resource)))
-			goto err_add_resources;
-		atmel_psif0_pclk.dev = &pdev->dev;
-		select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-		break;
-	case 1:
-		pin_mask  = (1 << 11) | (1 << 12); /* CLOCK & DATA */
-
-		if (platform_device_add_resources(pdev, atmel_psif1_resource,
-					ARRAY_SIZE(atmel_psif1_resource)))
-			goto err_add_resources;
-		atmel_psif1_pclk.dev = &pdev->dev;
-		select_peripheral(PIOB, pin_mask, PERIPH_A, 0);
-		break;
-	default:
-		return NULL;
-	}
-
-	platform_device_add(pdev);
-	return pdev;
-
-err_add_resources:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- *  USART
- * -------------------------------------------------------------------- */
-
-static struct atmel_uart_data atmel_usart0_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-static struct resource atmel_usart0_resource[] = {
-	PBMEM(0xffe00c00),
-	IRQ(6),
-};
-DEFINE_DEV_DATA(atmel_usart, 0);
-DEV_CLK(usart, atmel_usart0, pba, 3);
-
-static struct atmel_uart_data atmel_usart1_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-static struct resource atmel_usart1_resource[] = {
-	PBMEM(0xffe01000),
-	IRQ(7),
-};
-DEFINE_DEV_DATA(atmel_usart, 1);
-DEV_CLK(usart, atmel_usart1, pba, 4);
-
-static struct atmel_uart_data atmel_usart2_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-static struct resource atmel_usart2_resource[] = {
-	PBMEM(0xffe01400),
-	IRQ(8),
-};
-DEFINE_DEV_DATA(atmel_usart, 2);
-DEV_CLK(usart, atmel_usart2, pba, 5);
-
-static struct atmel_uart_data atmel_usart3_data = {
-	.use_dma_tx	= 1,
-	.use_dma_rx	= 1,
-};
-static struct resource atmel_usart3_resource[] = {
-	PBMEM(0xffe01800),
-	IRQ(9),
-};
-DEFINE_DEV_DATA(atmel_usart, 3);
-DEV_CLK(usart, atmel_usart3, pba, 6);
-
-static inline void configure_usart0_pins(int flags)
-{
-	u32 pin_mask = (1 << 8) | (1 << 9); /* RXD & TXD */
-	if (flags & ATMEL_USART_RTS)	pin_mask |= (1 << 6);
-	if (flags & ATMEL_USART_CTS)	pin_mask |= (1 << 7);
-	if (flags & ATMEL_USART_CLK)	pin_mask |= (1 << 10);
-
-	select_peripheral(PIOA, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
-}
-
-static inline void configure_usart1_pins(int flags)
-{
-	u32 pin_mask = (1 << 17) | (1 << 18); /* RXD & TXD */
-	if (flags & ATMEL_USART_RTS)	pin_mask |= (1 << 19);
-	if (flags & ATMEL_USART_CTS)	pin_mask |= (1 << 20);
-	if (flags & ATMEL_USART_CLK)	pin_mask |= (1 << 16);
-
-	select_peripheral(PIOA, pin_mask, PERIPH_A, AT32_GPIOF_PULLUP);
-}
-
-static inline void configure_usart2_pins(int flags)
-{
-	u32 pin_mask = (1 << 26) | (1 << 27); /* RXD & TXD */
-	if (flags & ATMEL_USART_RTS)	pin_mask |= (1 << 30);
-	if (flags & ATMEL_USART_CTS)	pin_mask |= (1 << 29);
-	if (flags & ATMEL_USART_CLK)	pin_mask |= (1 << 28);
-
-	select_peripheral(PIOB, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
-}
-
-static inline void configure_usart3_pins(int flags)
-{
-	u32 pin_mask = (1 << 18) | (1 << 17); /* RXD & TXD */
-	if (flags & ATMEL_USART_RTS)	pin_mask |= (1 << 16);
-	if (flags & ATMEL_USART_CTS)	pin_mask |= (1 << 15);
-	if (flags & ATMEL_USART_CLK)	pin_mask |= (1 << 19);
-
-	select_peripheral(PIOB, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
-}
-
-static struct platform_device *__initdata at32_usarts[4];
-
-void __init at32_map_usart(unsigned int hw_id, unsigned int line, int flags)
-{
-	struct platform_device *pdev;
-	struct atmel_uart_data *pdata;
-
-	switch (hw_id) {
-	case 0:
-		pdev = &atmel_usart0_device;
-		configure_usart0_pins(flags);
-		break;
-	case 1:
-		pdev = &atmel_usart1_device;
-		configure_usart1_pins(flags);
-		break;
-	case 2:
-		pdev = &atmel_usart2_device;
-		configure_usart2_pins(flags);
-		break;
-	case 3:
-		pdev = &atmel_usart3_device;
-		configure_usart3_pins(flags);
-		break;
-	default:
-		return;
-	}
-
-	if (PXSEG(pdev->resource[0].start) == P4SEG) {
-		/* Addresses in the P4 segment are permanently mapped 1:1 */
-		struct atmel_uart_data *data = pdev->dev.platform_data;
-		data->regs = (void __iomem *)pdev->resource[0].start;
-	}
-
-	pdev->id = line;
-	pdata = pdev->dev.platform_data;
-	pdata->num = line;
-	at32_usarts[line] = pdev;
-}
-
-struct platform_device *__init at32_add_device_usart(unsigned int id)
-{
-	platform_device_register(at32_usarts[id]);
-	return at32_usarts[id];
-}
-
-void __init at32_setup_serial_console(unsigned int usart_id)
-{
-#ifdef CONFIG_SERIAL_ATMEL
-	atmel_default_console_device = at32_usarts[usart_id];
-#endif
-}
-
-/* --------------------------------------------------------------------
- *  Ethernet
- * -------------------------------------------------------------------- */
-
-#ifdef CONFIG_CPU_AT32AP7000
-static struct macb_platform_data macb0_data;
-static struct resource macb0_resource[] = {
-	PBMEM(0xfff01800),
-	IRQ(25),
-};
-DEFINE_DEV_DATA(macb, 0);
-DEV_CLK(hclk, macb0, hsb, 8);
-DEV_CLK(pclk, macb0, pbb, 6);
-
-static struct macb_platform_data macb1_data;
-static struct resource macb1_resource[] = {
-	PBMEM(0xfff01c00),
-	IRQ(26),
-};
-DEFINE_DEV_DATA(macb, 1);
-DEV_CLK(hclk, macb1, hsb, 9);
-DEV_CLK(pclk, macb1, pbb, 7);
-
-struct platform_device *__init
-at32_add_device_eth(unsigned int id, struct macb_platform_data *data)
-{
-	struct platform_device *pdev;
-	u32 pin_mask;
-
-	switch (id) {
-	case 0:
-		pdev = &macb0_device;
-
-		pin_mask  = (1 << 3);	/* TXD0 */
-		pin_mask |= (1 << 4);	/* TXD1 */
-		pin_mask |= (1 << 7);	/* TXEN */
-		pin_mask |= (1 << 8);	/* TXCK */
-		pin_mask |= (1 << 9);	/* RXD0 */
-		pin_mask |= (1 << 10);	/* RXD1 */
-		pin_mask |= (1 << 13);	/* RXER */
-		pin_mask |= (1 << 15);	/* RXDV */
-		pin_mask |= (1 << 16);	/* MDC  */
-		pin_mask |= (1 << 17);	/* MDIO */
-
-		if (!data->is_rmii) {
-			pin_mask |= (1 << 0);	/* COL  */
-			pin_mask |= (1 << 1);	/* CRS  */
-			pin_mask |= (1 << 2);	/* TXER */
-			pin_mask |= (1 << 5);	/* TXD2 */
-			pin_mask |= (1 << 6);	/* TXD3 */
-			pin_mask |= (1 << 11);	/* RXD2 */
-			pin_mask |= (1 << 12);	/* RXD3 */
-			pin_mask |= (1 << 14);	/* RXCK */
-#ifndef CONFIG_BOARD_MIMC200
-			pin_mask |= (1 << 18);	/* SPD  */
-#endif
-		}
-
-		select_peripheral(PIOC, pin_mask, PERIPH_A, 0);
-
-		break;
-
-	case 1:
-		pdev = &macb1_device;
-
-		pin_mask  = (1 << 13);	/* TXD0 */
-		pin_mask |= (1 << 14);	/* TXD1 */
-		pin_mask |= (1 << 11);	/* TXEN */
-		pin_mask |= (1 << 12);	/* TXCK */
-		pin_mask |= (1 << 10);	/* RXD0 */
-		pin_mask |= (1 << 6);	/* RXD1 */
-		pin_mask |= (1 << 5);	/* RXER */
-		pin_mask |= (1 << 4);	/* RXDV */
-		pin_mask |= (1 << 3);	/* MDC  */
-		pin_mask |= (1 << 2);	/* MDIO */
-
-#ifndef CONFIG_BOARD_MIMC200
-		if (!data->is_rmii)
-			pin_mask |= (1 << 15);	/* SPD  */
-#endif
-
-		select_peripheral(PIOD, pin_mask, PERIPH_B, 0);
-
-		if (!data->is_rmii) {
-			pin_mask  = (1 << 19);	/* COL  */
-			pin_mask |= (1 << 23);	/* CRS  */
-			pin_mask |= (1 << 26);	/* TXER */
-			pin_mask |= (1 << 27);	/* TXD2 */
-			pin_mask |= (1 << 28);	/* TXD3 */
-			pin_mask |= (1 << 29);	/* RXD2 */
-			pin_mask |= (1 << 30);	/* RXD3 */
-			pin_mask |= (1 << 24);	/* RXCK */
-
-			select_peripheral(PIOC, pin_mask, PERIPH_B, 0);
-		}
-		break;
-
-	default:
-		return NULL;
-	}
-
-	memcpy(pdev->dev.platform_data, data, sizeof(struct macb_platform_data));
-	platform_device_register(pdev);
-
-	return pdev;
-}
-#endif
-
-/* --------------------------------------------------------------------
- *  SPI
- * -------------------------------------------------------------------- */
-static struct resource atmel_spi0_resource[] = {
-	PBMEM(0xffe00000),
-	IRQ(3),
-};
-DEFINE_DEV(atmel_spi, 0);
-DEV_CLK(spi_clk, atmel_spi0, pba, 0);
-
-static struct resource atmel_spi1_resource[] = {
-	PBMEM(0xffe00400),
-	IRQ(4),
-};
-DEFINE_DEV(atmel_spi, 1);
-DEV_CLK(spi_clk, atmel_spi1, pba, 1);
-
-void __init
-at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n)
-{
-	/*
-	 * Manage the chipselects as GPIOs, normally using the same pins
-	 * the SPI controller expects; but boards can use other pins.
-	 */
-	static u8 __initdata spi_pins[][4] = {
-		{ GPIO_PIN_PA(3), GPIO_PIN_PA(4),
-		  GPIO_PIN_PA(5), GPIO_PIN_PA(20) },
-		{ GPIO_PIN_PB(2), GPIO_PIN_PB(3),
-		  GPIO_PIN_PB(4), GPIO_PIN_PA(27) },
-	};
-	unsigned int pin, mode;
-
-	/* There are only 2 SPI controllers */
-	if (bus_num > 1)
-		return;
-
-	for (; n; n--, b++) {
-		b->bus_num = bus_num;
-		if (b->chip_select >= 4)
-			continue;
-		pin = (unsigned)b->controller_data;
-		if (!pin) {
-			pin = spi_pins[bus_num][b->chip_select];
-			b->controller_data = (void *)pin;
-		}
-		mode = AT32_GPIOF_OUTPUT;
-		if (!(b->mode & SPI_CS_HIGH))
-			mode |= AT32_GPIOF_HIGH;
-		at32_select_gpio(pin, mode);
-	}
-}
-
-struct platform_device *__init
-at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n)
-{
-	struct platform_device *pdev;
-	u32 pin_mask;
-
-	switch (id) {
-	case 0:
-		pdev = &atmel_spi0_device;
-		pin_mask  = (1 << 1) | (1 << 2);	/* MOSI & SCK */
-
-		/* pullup MISO so a level is always defined */
-		select_peripheral(PIOA, (1 << 0), PERIPH_A, AT32_GPIOF_PULLUP);
-		select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
-		at32_spi_setup_slaves(0, b, n);
-		break;
-
-	case 1:
-		pdev = &atmel_spi1_device;
-		pin_mask  = (1 << 1) | (1 << 5);	/* MOSI */
-
-		/* pullup MISO so a level is always defined */
-		select_peripheral(PIOB, (1 << 0), PERIPH_B, AT32_GPIOF_PULLUP);
-		select_peripheral(PIOB, pin_mask, PERIPH_B, 0);
-
-		at32_spi_setup_slaves(1, b, n);
-		break;
-
-	default:
-		return NULL;
-	}
-
-	spi_register_board_info(b, n);
-	platform_device_register(pdev);
-	return pdev;
-}
-
-/* --------------------------------------------------------------------
- *  TWI
- * -------------------------------------------------------------------- */
-static struct resource atmel_twi0_resource[] __initdata = {
-	PBMEM(0xffe00800),
-	IRQ(5),
-};
-static struct clk atmel_twi0_pclk = {
-	.name		= "twi_pclk",
-	.parent		= &pba_clk,
-	.mode		= pba_clk_mode,
-	.get_rate	= pba_clk_get_rate,
-	.index		= 2,
-};
-
-struct platform_device *__init at32_add_device_twi(unsigned int id,
-						    struct i2c_board_info *b,
-						    unsigned int n)
-{
-	struct platform_device *pdev;
-	u32 pin_mask;
-
-	if (id != 0)
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_twi", id);
-	if (!pdev)
-		return NULL;
-
-	if (platform_device_add_resources(pdev, atmel_twi0_resource,
-				ARRAY_SIZE(atmel_twi0_resource)))
-		goto err_add_resources;
-
-	pin_mask  = (1 << 6) | (1 << 7);	/* SDA & SDL */
-
-	select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
-	atmel_twi0_pclk.dev = &pdev->dev;
-
-	if (b)
-		i2c_register_board_info(id, b, n);
-
-	platform_device_add(pdev);
-	return pdev;
-
-err_add_resources:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- * MMC
- * -------------------------------------------------------------------- */
-static struct resource atmel_mci0_resource[] __initdata = {
-	PBMEM(0xfff02400),
-	IRQ(28),
-};
-static struct clk atmel_mci0_pclk = {
-	.name		= "mci_clk",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.index		= 9,
-};
-
-static bool at32_mci_dma_filter(struct dma_chan *chan, void *pdata)
-{
-	struct dw_dma_slave *sl = pdata;
-
-	if (!sl)
-		return false;
-
-	if (sl->dma_dev == chan->device->dev) {
-		chan->private = sl;
-		return true;
-	}
-
-	return false;
-}
-
-struct platform_device *__init
-at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
-{
-	struct platform_device		*pdev;
-	struct dw_dma_slave	        *slave;
-	u32				pioa_mask;
-	u32				piob_mask;
-
-	if (id != 0 || !data)
-		return NULL;
-
-	/* Must have at least one usable slot */
-	if (!data->slot[0].bus_width && !data->slot[1].bus_width)
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_mci", id);
-	if (!pdev)
-		goto fail;
-
-	if (platform_device_add_resources(pdev, atmel_mci0_resource,
-				ARRAY_SIZE(atmel_mci0_resource)))
-		goto fail;
-
-	slave = kzalloc(sizeof(*slave), GFP_KERNEL);
-	if (!slave)
-		goto fail;
-
-	slave->dma_dev = &dw_dmac0_device.dev;
-	slave->src_id = 0;
-	slave->dst_id = 1;
-	slave->m_master = 1;
-	slave->p_master = 0;
-
-	data->dma_slave = slave;
-	data->dma_filter = at32_mci_dma_filter;
-
-	if (platform_device_add_data(pdev, data,
-				sizeof(struct mci_platform_data)))
-		goto fail_free;
-
-	/* CLK line is common to both slots */
-	pioa_mask = 1 << 10;
-
-	switch (data->slot[0].bus_width) {
-	case 4:
-		pioa_mask |= 1 << 13;		/* DATA1 */
-		pioa_mask |= 1 << 14;		/* DATA2 */
-		pioa_mask |= 1 << 15;		/* DATA3 */
-		/* fall through */
-	case 1:
-		pioa_mask |= 1 << 11;		/* CMD	 */
-		pioa_mask |= 1 << 12;		/* DATA0 */
-
-		if (gpio_is_valid(data->slot[0].detect_pin))
-			at32_select_gpio(data->slot[0].detect_pin, 0);
-		if (gpio_is_valid(data->slot[0].wp_pin))
-			at32_select_gpio(data->slot[0].wp_pin, 0);
-		break;
-	case 0:
-		/* Slot is unused */
-		break;
-	default:
-		goto fail_free;
-	}
-
-	select_peripheral(PIOA, pioa_mask, PERIPH_A, 0);
-	piob_mask = 0;
-
-	switch (data->slot[1].bus_width) {
-	case 4:
-		piob_mask |= 1 <<  8;		/* DATA1 */
-		piob_mask |= 1 <<  9;		/* DATA2 */
-		piob_mask |= 1 << 10;		/* DATA3 */
-		/* fall through */
-	case 1:
-		piob_mask |= 1 <<  6;		/* CMD	 */
-		piob_mask |= 1 <<  7;		/* DATA0 */
-		select_peripheral(PIOB, piob_mask, PERIPH_B, 0);
-
-		if (gpio_is_valid(data->slot[1].detect_pin))
-			at32_select_gpio(data->slot[1].detect_pin, 0);
-		if (gpio_is_valid(data->slot[1].wp_pin))
-			at32_select_gpio(data->slot[1].wp_pin, 0);
-		break;
-	case 0:
-		/* Slot is unused */
-		break;
-	default:
-		if (!data->slot[0].bus_width)
-			goto fail_free;
-
-		data->slot[1].bus_width = 0;
-		break;
-	}
-
-	atmel_mci0_pclk.dev = &pdev->dev;
-
-	platform_device_add(pdev);
-	return pdev;
-
-fail_free:
-	kfree(slave);
-fail:
-	data->dma_slave = NULL;
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- *  LCDC
- * -------------------------------------------------------------------- */
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
-static struct atmel_lcdfb_pdata atmel_lcdfb0_data;
-static struct resource atmel_lcdfb0_resource[] = {
-	{
-		.start		= 0xff000000,
-		.end		= 0xff000fff,
-		.flags		= IORESOURCE_MEM,
-	},
-	IRQ(1),
-	{
-		/* Placeholder for pre-allocated fb memory */
-		.start		= 0x00000000,
-		.end		= 0x00000000,
-		.flags		= 0,
-	},
-};
-DEFINE_DEV_DATA(atmel_lcdfb, 0);
-DEV_CLK(hclk, atmel_lcdfb0, hsb, 7);
-static struct clk atmel_lcdfb0_pixclk = {
-	.name		= "lcdc_clk",
-	.dev		= &atmel_lcdfb0_device.dev,
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 7,
-};
-
-struct platform_device *__init
-at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data,
-		     unsigned long fbmem_start, unsigned long fbmem_len,
-		     u64 pin_mask)
-{
-	struct platform_device *pdev;
-	struct atmel_lcdfb_pdata *info;
-	struct fb_monspecs *monspecs;
-	struct fb_videomode *modedb;
-	unsigned int modedb_size;
-	u32 portc_mask, portd_mask, porte_mask;
-
-	/*
-	 * Do a deep copy of the fb data, monspecs and modedb. Make
-	 * sure all allocations are done before setting up the
-	 * portmux.
-	 */
-	monspecs = kmemdup(data->default_monspecs,
-			   sizeof(struct fb_monspecs), GFP_KERNEL);
-	if (!monspecs)
-		return NULL;
-
-	modedb_size = sizeof(struct fb_videomode) * monspecs->modedb_len;
-	modedb = kmemdup(monspecs->modedb, modedb_size, GFP_KERNEL);
-	if (!modedb)
-		goto err_dup_modedb;
-	monspecs->modedb = modedb;
-
-	switch (id) {
-	case 0:
-		pdev = &atmel_lcdfb0_device;
-
-		if (pin_mask == 0ULL)
-			/* Default to "full" lcdc control signals and 24bit */
-			pin_mask = ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL;
-
-		/* LCDC on port C */
-		portc_mask = pin_mask & 0xfff80000;
-		select_peripheral(PIOC, portc_mask, PERIPH_A, 0);
-
-		/* LCDC on port D */
-		portd_mask = pin_mask & 0x0003ffff;
-		select_peripheral(PIOD, portd_mask, PERIPH_A, 0);
-
-		/* LCDC on port E */
-		porte_mask = (pin_mask >> 32) & 0x0007ffff;
-		select_peripheral(PIOE, porte_mask, PERIPH_B, 0);
-
-		clk_set_parent(&atmel_lcdfb0_pixclk, &pll0);
-		clk_set_rate(&atmel_lcdfb0_pixclk, clk_get_rate(&pll0));
-		break;
-
-	default:
-		goto err_invalid_id;
-	}
-
-	if (fbmem_len) {
-		pdev->resource[2].start = fbmem_start;
-		pdev->resource[2].end = fbmem_start + fbmem_len - 1;
-		pdev->resource[2].flags = IORESOURCE_MEM;
-	}
-
-	info = pdev->dev.platform_data;
-	memcpy(info, data, sizeof(struct atmel_lcdfb_pdata));
-	info->default_monspecs = monspecs;
-
-	pdev->name = "at32ap-lcdfb";
-
-	platform_device_register(pdev);
-	return pdev;
-
-err_invalid_id:
-	kfree(modedb);
-err_dup_modedb:
-	kfree(monspecs);
-	return NULL;
-}
-#endif
-
-/* --------------------------------------------------------------------
- *  PWM
- * -------------------------------------------------------------------- */
-static struct resource atmel_pwm0_resource[] __initdata = {
-	PBMEM(0xfff01400),
-	IRQ(24),
-};
-static struct clk atmel_pwm0_mck = {
-	.name		= "at91sam9rl-pwm",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.index		= 5,
-};
-
-struct platform_device *__init at32_add_device_pwm(u32 mask)
-{
-	struct platform_device *pdev;
-	u32 pin_mask;
-
-	if (!mask)
-		return NULL;
-
-	pdev = platform_device_alloc("at91sam9rl-pwm", 0);
-	if (!pdev)
-		return NULL;
-
-	if (platform_device_add_resources(pdev, atmel_pwm0_resource,
-				ARRAY_SIZE(atmel_pwm0_resource)))
-		goto out_free_pdev;
-
-	pin_mask = 0;
-	if (mask & (1 << 0))
-		pin_mask |= (1 << 28);
-	if (mask & (1 << 1))
-		pin_mask |= (1 << 29);
-	if (pin_mask > 0)
-		select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
-	pin_mask = 0;
-	if (mask & (1 << 2))
-		pin_mask |= (1 << 21);
-	if (mask & (1 << 3))
-		pin_mask |= (1 << 22);
-	if (pin_mask > 0)
-		select_peripheral(PIOA, pin_mask, PERIPH_B, 0);
-
-	atmel_pwm0_mck.dev = &pdev->dev;
-
-	platform_device_add(pdev);
-
-	return pdev;
-
-out_free_pdev:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- *  SSC
- * -------------------------------------------------------------------- */
-static struct resource ssc0_resource[] = {
-	PBMEM(0xffe01c00),
-	IRQ(10),
-};
-DEFINE_DEV(ssc, 0);
-DEV_CLK(pclk, ssc0, pba, 7);
-
-static struct resource ssc1_resource[] = {
-	PBMEM(0xffe02000),
-	IRQ(11),
-};
-DEFINE_DEV(ssc, 1);
-DEV_CLK(pclk, ssc1, pba, 8);
-
-static struct resource ssc2_resource[] = {
-	PBMEM(0xffe02400),
-	IRQ(12),
-};
-DEFINE_DEV(ssc, 2);
-DEV_CLK(pclk, ssc2, pba, 9);
-
-struct platform_device *__init
-at32_add_device_ssc(unsigned int id, unsigned int flags)
-{
-	struct platform_device *pdev;
-	u32 pin_mask = 0;
-
-	switch (id) {
-	case 0:
-		pdev = &ssc0_device;
-		if (flags & ATMEL_SSC_RF)
-			pin_mask |= (1 << 21);	/* RF */
-		if (flags & ATMEL_SSC_RK)
-			pin_mask |= (1 << 22);	/* RK */
-		if (flags & ATMEL_SSC_TK)
-			pin_mask |= (1 << 23);	/* TK */
-		if (flags & ATMEL_SSC_TF)
-			pin_mask |= (1 << 24);	/* TF */
-		if (flags & ATMEL_SSC_TD)
-			pin_mask |= (1 << 25);	/* TD */
-		if (flags & ATMEL_SSC_RD)
-			pin_mask |= (1 << 26);	/* RD */
-
-		if (pin_mask > 0)
-			select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
-		break;
-	case 1:
-		pdev = &ssc1_device;
-		if (flags & ATMEL_SSC_RF)
-			pin_mask |= (1 << 0);	/* RF */
-		if (flags & ATMEL_SSC_RK)
-			pin_mask |= (1 << 1);	/* RK */
-		if (flags & ATMEL_SSC_TK)
-			pin_mask |= (1 << 2);	/* TK */
-		if (flags & ATMEL_SSC_TF)
-			pin_mask |= (1 << 3);	/* TF */
-		if (flags & ATMEL_SSC_TD)
-			pin_mask |= (1 << 4);	/* TD */
-		if (flags & ATMEL_SSC_RD)
-			pin_mask |= (1 << 5);	/* RD */
-
-		if (pin_mask > 0)
-			select_peripheral(PIOA, pin_mask, PERIPH_B, 0);
-
-		break;
-	case 2:
-		pdev = &ssc2_device;
-		if (flags & ATMEL_SSC_TD)
-			pin_mask |= (1 << 13);	/* TD */
-		if (flags & ATMEL_SSC_RD)
-			pin_mask |= (1 << 14);	/* RD */
-		if (flags & ATMEL_SSC_TK)
-			pin_mask |= (1 << 15);	/* TK */
-		if (flags & ATMEL_SSC_TF)
-			pin_mask |= (1 << 16);	/* TF */
-		if (flags & ATMEL_SSC_RF)
-			pin_mask |= (1 << 17);	/* RF */
-		if (flags & ATMEL_SSC_RK)
-			pin_mask |= (1 << 18);	/* RK */
-
-		if (pin_mask > 0)
-			select_peripheral(PIOB, pin_mask, PERIPH_A, 0);
-
-		break;
-	default:
-		return NULL;
-	}
-
-	platform_device_register(pdev);
-	return pdev;
-}
-
-/* --------------------------------------------------------------------
- *  USB Device Controller
- * -------------------------------------------------------------------- */
-static struct resource usba0_resource[] __initdata = {
-	{
-		.start		= 0xff300000,
-		.end		= 0xff3fffff,
-		.flags		= IORESOURCE_MEM,
-	}, {
-		.start		= 0xfff03000,
-		.end		= 0xfff033ff,
-		.flags		= IORESOURCE_MEM,
-	},
-	IRQ(31),
-};
-static struct clk usba0_pclk = {
-	.name		= "pclk",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.index		= 12,
-};
-static struct clk usba0_hclk = {
-	.name		= "hclk",
-	.parent		= &hsb_clk,
-	.mode		= hsb_clk_mode,
-	.get_rate	= hsb_clk_get_rate,
-	.index		= 6,
-};
-
-#define EP(nam, idx, maxpkt, maxbk, dma, isoc)			\
-	[idx] = {						\
-		.name		= nam,				\
-		.index		= idx,				\
-		.fifo_size	= maxpkt,			\
-		.nr_banks	= maxbk,			\
-		.can_dma	= dma,				\
-		.can_isoc	= isoc,				\
-	}
-
-static struct usba_ep_data at32_usba_ep[] __initdata = {
-	EP("ep0",     0,   64, 1, 0, 0),
-	EP("ep1",     1,  512, 2, 1, 1),
-	EP("ep2",     2,  512, 2, 1, 1),
-	EP("ep3-int", 3,   64, 3, 1, 0),
-	EP("ep4-int", 4,   64, 3, 1, 0),
-	EP("ep5",     5, 1024, 3, 1, 1),
-	EP("ep6",     6, 1024, 3, 1, 1),
-};
-
-#undef EP
-
-struct platform_device *__init
-at32_add_device_usba(unsigned int id, struct usba_platform_data *data)
-{
-	/*
-	 * pdata doesn't have room for any endpoints, so we need to
-	 * append room for the ones we need right after it.
-	 */
-	struct {
-		struct usba_platform_data pdata;
-		struct usba_ep_data ep[7];
-	} usba_data;
-	struct platform_device *pdev;
-
-	if (id != 0)
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_usba_udc", 0);
-	if (!pdev)
-		return NULL;
-
-	if (platform_device_add_resources(pdev, usba0_resource,
-					  ARRAY_SIZE(usba0_resource)))
-		goto out_free_pdev;
-
-	if (data) {
-		usba_data.pdata.vbus_pin = data->vbus_pin;
-		usba_data.pdata.vbus_pin_inverted = data->vbus_pin_inverted;
-	} else {
-		usba_data.pdata.vbus_pin = -EINVAL;
-		usba_data.pdata.vbus_pin_inverted = -EINVAL;
-	}
-
-	data = &usba_data.pdata;
-	data->num_ep = ARRAY_SIZE(at32_usba_ep);
-	memcpy(data->ep, at32_usba_ep, sizeof(at32_usba_ep));
-
-	if (platform_device_add_data(pdev, data, sizeof(usba_data)))
-		goto out_free_pdev;
-
-	if (gpio_is_valid(data->vbus_pin))
-		at32_select_gpio(data->vbus_pin, 0);
-
-	usba0_pclk.dev = &pdev->dev;
-	usba0_hclk.dev = &pdev->dev;
-
-	platform_device_add(pdev);
-
-	return pdev;
-
-out_free_pdev:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- * IDE / CompactFlash
- * -------------------------------------------------------------------- */
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7001)
-static struct resource at32_smc_cs4_resource[] __initdata = {
-	{
-		.start	= 0x04000000,
-		.end	= 0x07ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(~0UL), /* Magic IRQ will be overridden */
-};
-static struct resource at32_smc_cs5_resource[] __initdata = {
-	{
-		.start	= 0x20000000,
-		.end	= 0x23ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(~0UL), /* Magic IRQ will be overridden */
-};
-
-static int __init at32_init_ide_or_cf(struct platform_device *pdev,
-		unsigned int cs, unsigned int extint)
-{
-	static unsigned int extint_pin_map[4] __initdata = {
-		(1 << 25),
-		(1 << 26),
-		(1 << 27),
-		(1 << 28),
-	};
-	static bool common_pins_initialized __initdata = false;
-	unsigned int extint_pin;
-	int ret;
-	u32 pin_mask;
-
-	if (extint >= ARRAY_SIZE(extint_pin_map))
-		return -EINVAL;
-	extint_pin = extint_pin_map[extint];
-
-	switch (cs) {
-	case 4:
-		ret = platform_device_add_resources(pdev,
-				at32_smc_cs4_resource,
-				ARRAY_SIZE(at32_smc_cs4_resource));
-		if (ret)
-			return ret;
-
-		/* NCS4   -> OE_N  */
-		select_peripheral(PIOE, (1 << 21), PERIPH_A, 0);
-		hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, HMATRIX_EBI_CF0_ENABLE);
-		break;
-	case 5:
-		ret = platform_device_add_resources(pdev,
-				at32_smc_cs5_resource,
-				ARRAY_SIZE(at32_smc_cs5_resource));
-		if (ret)
-			return ret;
-
-		/* NCS5   -> OE_N  */
-		select_peripheral(PIOE, (1 << 22), PERIPH_A, 0);
-		hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, HMATRIX_EBI_CF1_ENABLE);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (!common_pins_initialized) {
-		pin_mask  = (1 << 19);	/* CFCE1  -> CS0_N */
-		pin_mask |= (1 << 20);	/* CFCE2  -> CS1_N */
-		pin_mask |= (1 << 23);	/* CFRNW  -> DIR   */
-		pin_mask |= (1 << 24);	/* NWAIT  <- IORDY */
-
-		select_peripheral(PIOE, pin_mask, PERIPH_A, 0);
-
-		common_pins_initialized = true;
-	}
-
-	select_peripheral(PIOB, extint_pin, PERIPH_A, AT32_GPIOF_DEGLITCH);
-
-	pdev->resource[1].start = EIM_IRQ_BASE + extint;
-	pdev->resource[1].end = pdev->resource[1].start;
-
-	return 0;
-}
-
-struct platform_device *__init
-at32_add_device_ide(unsigned int id, unsigned int extint,
-		    struct ide_platform_data *data)
-{
-	struct platform_device *pdev;
-
-	pdev = platform_device_alloc("at32_ide", id);
-	if (!pdev)
-		goto fail;
-
-	if (platform_device_add_data(pdev, data,
-				sizeof(struct ide_platform_data)))
-		goto fail;
-
-	if (at32_init_ide_or_cf(pdev, data->cs, extint))
-		goto fail;
-
-	platform_device_add(pdev);
-	return pdev;
-
-fail:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-struct platform_device *__init
-at32_add_device_cf(unsigned int id, unsigned int extint,
-		    struct cf_platform_data *data)
-{
-	struct platform_device *pdev;
-
-	pdev = platform_device_alloc("at32_cf", id);
-	if (!pdev)
-		goto fail;
-
-	if (platform_device_add_data(pdev, data,
-				sizeof(struct cf_platform_data)))
-		goto fail;
-
-	if (at32_init_ide_or_cf(pdev, data->cs, extint))
-		goto fail;
-
-	if (gpio_is_valid(data->detect_pin))
-		at32_select_gpio(data->detect_pin, AT32_GPIOF_DEGLITCH);
-	if (gpio_is_valid(data->reset_pin))
-		at32_select_gpio(data->reset_pin, 0);
-	if (gpio_is_valid(data->vcc_pin))
-		at32_select_gpio(data->vcc_pin, 0);
-	/* READY is used as extint, so we can't select it as gpio */
-
-	platform_device_add(pdev);
-	return pdev;
-
-fail:
-	platform_device_put(pdev);
-	return NULL;
-}
-#endif
-
-/* --------------------------------------------------------------------
- * NAND Flash / SmartMedia
- * -------------------------------------------------------------------- */
-static struct resource smc_cs3_resource[] __initdata = {
-	{
-		.start	= 0x0c000000,
-		.end	= 0x0fffffff,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= 0xfff03c00,
-		.end	= 0xfff03fff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-struct platform_device *__init
-at32_add_device_nand(unsigned int id, struct atmel_nand_data *data)
-{
-	struct platform_device *pdev;
-
-	if (id != 0 || !data)
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_nand", id);
-	if (!pdev)
-		goto fail;
-
-	if (platform_device_add_resources(pdev, smc_cs3_resource,
-				ARRAY_SIZE(smc_cs3_resource)))
-		goto fail;
-
-	/* For at32ap7000, we use the reset workaround for nand driver */
-	data->need_reset_workaround = true;
-
-	if (platform_device_add_data(pdev, data,
-				sizeof(struct atmel_nand_data)))
-		goto fail;
-
-	hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, HMATRIX_EBI_NAND_ENABLE);
-	if (data->enable_pin)
-		at32_select_gpio(data->enable_pin,
-				AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-	if (data->rdy_pin)
-		at32_select_gpio(data->rdy_pin, 0);
-	if (data->det_pin)
-		at32_select_gpio(data->det_pin, 0);
-
-	platform_device_add(pdev);
-	return pdev;
-
-fail:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- * AC97C
- * -------------------------------------------------------------------- */
-static struct resource atmel_ac97c0_resource[] __initdata = {
-	PBMEM(0xfff02800),
-	IRQ(29),
-};
-static struct clk atmel_ac97c0_pclk = {
-	.name		= "pclk",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.index		= 10,
-};
-
-struct platform_device *__init
-at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
-		      unsigned int flags)
-{
-	struct platform_device		*pdev;
-	struct dw_dma_slave		*rx_dws;
-	struct dw_dma_slave		*tx_dws;
-	struct ac97c_platform_data	_data;
-	u32				pin_mask;
-
-	if (id != 0)
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_ac97c", id);
-	if (!pdev)
-		return NULL;
-
-	if (platform_device_add_resources(pdev, atmel_ac97c0_resource,
-				ARRAY_SIZE(atmel_ac97c0_resource)))
-		goto out_free_resources;
-
-	if (!data) {
-		data = &_data;
-		memset(data, 0, sizeof(struct ac97c_platform_data));
-		data->reset_pin = -ENODEV;
-	}
-
-	rx_dws = &data->rx_dws;
-	tx_dws = &data->tx_dws;
-
-	/* Check if DMA slave interface for capture should be configured. */
-	if (flags & AC97C_CAPTURE) {
-		rx_dws->dma_dev = &dw_dmac0_device.dev;
-		rx_dws->src_id = 3;
-		rx_dws->m_master = 0;
-		rx_dws->p_master = 1;
-	}
-
-	/* Check if DMA slave interface for playback should be configured. */
-	if (flags & AC97C_PLAYBACK) {
-		tx_dws->dma_dev = &dw_dmac0_device.dev;
-		tx_dws->dst_id = 4;
-		tx_dws->m_master = 0;
-		tx_dws->p_master = 1;
-	}
-
-	if (platform_device_add_data(pdev, data,
-				sizeof(struct ac97c_platform_data)))
-		goto out_free_resources;
-
-	/* SDO | SYNC | SCLK | SDI */
-	pin_mask = (1 << 20) | (1 << 21) | (1 << 22) | (1 << 23);
-
-	select_peripheral(PIOB, pin_mask, PERIPH_B, 0);
-
-	if (gpio_is_valid(data->reset_pin))
-		at32_select_gpio(data->reset_pin, AT32_GPIOF_OUTPUT
-				| AT32_GPIOF_HIGH);
-
-	atmel_ac97c0_pclk.dev = &pdev->dev;
-
-	platform_device_add(pdev);
-	return pdev;
-
-out_free_resources:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- * ABDAC
- * -------------------------------------------------------------------- */
-static struct resource abdac0_resource[] __initdata = {
-	PBMEM(0xfff02000),
-	IRQ(27),
-};
-static struct clk abdac0_pclk = {
-	.name		= "pclk",
-	.parent		= &pbb_clk,
-	.mode		= pbb_clk_mode,
-	.get_rate	= pbb_clk_get_rate,
-	.index		= 8,
-};
-static struct clk abdac0_sample_clk = {
-	.name		= "sample_clk",
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 6,
-};
-
-struct platform_device *__init
-at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
-{
-	struct platform_device	*pdev;
-	struct dw_dma_slave	*dws;
-	u32			pin_mask;
-
-	if (id != 0 || !data)
-		return NULL;
-
-	pdev = platform_device_alloc("atmel_abdac", id);
-	if (!pdev)
-		return NULL;
-
-	if (platform_device_add_resources(pdev, abdac0_resource,
-				ARRAY_SIZE(abdac0_resource)))
-		goto out_free_resources;
-
-	dws = &data->dws;
-
-	dws->dma_dev = &dw_dmac0_device.dev;
-	dws->dst_id = 2;
-	dws->m_master = 0;
-	dws->p_master = 1;
-
-	if (platform_device_add_data(pdev, data,
-				sizeof(struct atmel_abdac_pdata)))
-		goto out_free_resources;
-
-	pin_mask  = (1 << 20) | (1 << 22);	/* DATA1 & DATAN1 */
-	pin_mask |= (1 << 21) | (1 << 23);	/* DATA0 & DATAN0 */
-
-	select_peripheral(PIOB, pin_mask, PERIPH_A, 0);
-
-	abdac0_pclk.dev = &pdev->dev;
-	abdac0_sample_clk.dev = &pdev->dev;
-
-	platform_device_add(pdev);
-	return pdev;
-
-out_free_resources:
-	platform_device_put(pdev);
-	return NULL;
-}
-
-/* --------------------------------------------------------------------
- *  GCLK
- * -------------------------------------------------------------------- */
-static struct clk gclk0 = {
-	.name		= "gclk0",
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 0,
-};
-static struct clk gclk1 = {
-	.name		= "gclk1",
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 1,
-};
-static struct clk gclk2 = {
-	.name		= "gclk2",
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 2,
-};
-static struct clk gclk3 = {
-	.name		= "gclk3",
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 3,
-};
-static struct clk gclk4 = {
-	.name		= "gclk4",
-	.mode		= genclk_mode,
-	.get_rate	= genclk_get_rate,
-	.set_rate	= genclk_set_rate,
-	.set_parent	= genclk_set_parent,
-	.index		= 4,
-};
-
-static __initdata struct clk *init_clocks[] = {
-	&osc32k,
-	&osc0,
-	&osc1,
-	&pll0,
-	&pll1,
-	&cpu_clk,
-	&hsb_clk,
-	&pba_clk,
-	&pbb_clk,
-	&at32_pm_pclk,
-	&at32_intc0_pclk,
-	&at32_hmatrix_clk,
-	&ebi_clk,
-	&hramc_clk,
-	&sdramc_clk,
-	&smc0_pclk,
-	&smc0_mck,
-	&pdc_hclk,
-	&pdc_pclk,
-	&dw_dmac0_hclk,
-	&pico_clk,
-	&pio0_mck,
-	&pio1_mck,
-	&pio2_mck,
-	&pio3_mck,
-	&pio4_mck,
-	&at32_tcb0_t0_clk,
-	&at32_tcb1_t0_clk,
-	&atmel_psif0_pclk,
-	&atmel_psif1_pclk,
-	&atmel_usart0_usart,
-	&atmel_usart1_usart,
-	&atmel_usart2_usart,
-	&atmel_usart3_usart,
-	&atmel_pwm0_mck,
-#if defined(CONFIG_CPU_AT32AP7000)
-	&macb0_hclk,
-	&macb0_pclk,
-	&macb1_hclk,
-	&macb1_pclk,
-#endif
-	&atmel_spi0_spi_clk,
-	&atmel_spi1_spi_clk,
-	&atmel_twi0_pclk,
-	&atmel_mci0_pclk,
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
-	&atmel_lcdfb0_hclk,
-	&atmel_lcdfb0_pixclk,
-#endif
-	&ssc0_pclk,
-	&ssc1_pclk,
-	&ssc2_pclk,
-	&usba0_hclk,
-	&usba0_pclk,
-	&atmel_ac97c0_pclk,
-	&abdac0_pclk,
-	&abdac0_sample_clk,
-	&gclk0,
-	&gclk1,
-	&gclk2,
-	&gclk3,
-	&gclk4,
-};
-
-void __init setup_platform(void)
-{
-	u32 cpu_mask = 0, hsb_mask = 0, pba_mask = 0, pbb_mask = 0;
-	int i;
-
-	if (pm_readl(MCCTRL) & PM_BIT(PLLSEL)) {
-		main_clock = &pll0;
-		cpu_clk.parent = &pll0;
-	} else {
-		main_clock = &osc0;
-		cpu_clk.parent = &osc0;
-	}
-
-	if (pm_readl(PLL0) & PM_BIT(PLLOSC))
-		pll0.parent = &osc1;
-	if (pm_readl(PLL1) & PM_BIT(PLLOSC))
-		pll1.parent = &osc1;
-
-	genclk_init_parent(&gclk0);
-	genclk_init_parent(&gclk1);
-	genclk_init_parent(&gclk2);
-	genclk_init_parent(&gclk3);
-	genclk_init_parent(&gclk4);
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
-	genclk_init_parent(&atmel_lcdfb0_pixclk);
-#endif
-	genclk_init_parent(&abdac0_sample_clk);
-
-	/*
-	 * Build initial dynamic clock list by registering all clocks
-	 * from the array.
-	 * At the same time, turn on all clocks that have at least one
-	 * user already, and turn off everything else. We only do this
-	 * for module clocks, and even though it isn't particularly
-	 * pretty to  check the address of the mode function, it should
-	 * do the trick...
-	 */
-	for (i = 0; i < ARRAY_SIZE(init_clocks); i++) {
-		struct clk *clk = init_clocks[i];
-
-		/* first, register clock */
-		at32_clk_register(clk);
-
-		if (clk->users == 0)
-			continue;
-
-		if (clk->mode == &cpu_clk_mode)
-			cpu_mask |= 1 << clk->index;
-		else if (clk->mode == &hsb_clk_mode)
-			hsb_mask |= 1 << clk->index;
-		else if (clk->mode == &pba_clk_mode)
-			pba_mask |= 1 << clk->index;
-		else if (clk->mode == &pbb_clk_mode)
-			pbb_mask |= 1 << clk->index;
-	}
-
-	pm_writel(CPU_MASK, cpu_mask);
-	pm_writel(HSB_MASK, hsb_mask);
-	pm_writel(PBA_MASK, pba_mask);
-	pm_writel(PBB_MASK, pbb_mask);
-
-	/* Initialize the port muxes */
-	at32_init_pio(&pio0_device);
-	at32_init_pio(&pio1_device);
-	at32_init_pio(&pio2_device);
-	at32_init_pio(&pio3_device);
-	at32_init_pio(&pio4_device);
-}
-
-struct gen_pool *sram_pool;
-
-static int __init sram_init(void)
-{
-	struct gen_pool *pool;
-
-	/* 1KiB granularity */
-	pool = gen_pool_create(10, -1);
-	if (!pool)
-		goto fail;
-
-	if (gen_pool_add(pool, 0x24000000, 0x8000, -1))
-		goto err_pool_add;
-
-	sram_pool = pool;
-	return 0;
-
-err_pool_add:
-	gen_pool_destroy(pool);
-fail:
-	pr_err("Failed to create SRAM pool\n");
-	return -ENOMEM;
-}
-core_initcall(sram_init);
diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c
deleted file mode 100644
index fdf1caecb7b9..000000000000
--- a/arch/avr32/mach-at32ap/clock.c
+++ /dev/null
@@ -1,334 +0,0 @@
-/*
- * Clock management for AT32AP CPUs
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * Based on arch/arm/mach-at91/clock.c
- *   Copyright (C) 2005 David Brownell
- *   Copyright (C) 2005 Ivan Kokshaysky
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/device.h>
-#include <linux/string.h>
-#include <linux/list.h>
-
-#include <mach/chip.h>
-
-#include "clock.h"
-
-/* at32 clock list */
-static LIST_HEAD(at32_clock_list);
-
-static DEFINE_SPINLOCK(clk_lock);
-static DEFINE_SPINLOCK(clk_list_lock);
-
-void at32_clk_register(struct clk *clk)
-{
-	spin_lock(&clk_list_lock);
-	/* add the new item to the end of the list */
-	list_add_tail(&clk->list, &at32_clock_list);
-	spin_unlock(&clk_list_lock);
-}
-
-static struct clk *__clk_get(struct device *dev, const char *id)
-{
-	struct clk *clk;
-
-	list_for_each_entry(clk, &at32_clock_list, list) {
-		if (clk->dev == dev && strcmp(id, clk->name) == 0) {
-			return clk;
-		}
-	}
-
-	return ERR_PTR(-ENOENT);
-}
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *clk;
-
-	spin_lock(&clk_list_lock);
-	clk = __clk_get(dev, id);
-	spin_unlock(&clk_list_lock);
-
-	return clk;
-}
-
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-	/* clocks are static for now, we can't free them */
-}
-EXPORT_SYMBOL(clk_put);
-
-static void __clk_enable(struct clk *clk)
-{
-	if (clk->parent)
-		__clk_enable(clk->parent);
-	if (clk->users++ == 0 && clk->mode)
-		clk->mode(clk, 1);
-}
-
-int clk_enable(struct clk *clk)
-{
-	unsigned long flags;
-
-	if (!clk)
-		return 0;
-
-	spin_lock_irqsave(&clk_lock, flags);
-	__clk_enable(clk);
-	spin_unlock_irqrestore(&clk_lock, flags);
-
-	return 0;
-}
-EXPORT_SYMBOL(clk_enable);
-
-static void __clk_disable(struct clk *clk)
-{
-	if (clk->users == 0) {
-		printk(KERN_ERR "%s: mismatched disable\n", clk->name);
-		WARN_ON(1);
-		return;
-	}
-
-	if (--clk->users == 0 && clk->mode)
-		clk->mode(clk, 0);
-	if (clk->parent)
-		__clk_disable(clk->parent);
-}
-
-void clk_disable(struct clk *clk)
-{
-	unsigned long flags;
-
-	if (IS_ERR_OR_NULL(clk))
-		return;
-
-	spin_lock_irqsave(&clk_lock, flags);
-	__clk_disable(clk);
-	spin_unlock_irqrestore(&clk_lock, flags);
-}
-EXPORT_SYMBOL(clk_disable);
-
-unsigned long clk_get_rate(struct clk *clk)
-{
-	unsigned long flags;
-	unsigned long rate;
-
-	if (!clk)
-		return 0;
-
-	spin_lock_irqsave(&clk_lock, flags);
-	rate = clk->get_rate(clk);
-	spin_unlock_irqrestore(&clk_lock, flags);
-
-	return rate;
-}
-EXPORT_SYMBOL(clk_get_rate);
-
-long clk_round_rate(struct clk *clk, unsigned long rate)
-{
-	unsigned long flags, actual_rate;
-
-	if (!clk)
-		return 0;
-
-	if (!clk->set_rate)
-		return -ENOSYS;
-
-	spin_lock_irqsave(&clk_lock, flags);
-	actual_rate = clk->set_rate(clk, rate, 0);
-	spin_unlock_irqrestore(&clk_lock, flags);
-
-	return actual_rate;
-}
-EXPORT_SYMBOL(clk_round_rate);
-
-int clk_set_rate(struct clk *clk, unsigned long rate)
-{
-	unsigned long flags;
-	long ret;
-
-	if (!clk)
-		return 0;
-
-	if (!clk->set_rate)
-		return -ENOSYS;
-
-	spin_lock_irqsave(&clk_lock, flags);
-	ret = clk->set_rate(clk, rate, 1);
-	spin_unlock_irqrestore(&clk_lock, flags);
-
-	return (ret < 0) ? ret : 0;
-}
-EXPORT_SYMBOL(clk_set_rate);
-
-int clk_set_parent(struct clk *clk, struct clk *parent)
-{
-	unsigned long flags;
-	int ret;
-
-	if (!clk)
-		return 0;
-
-	if (!clk->set_parent)
-		return -ENOSYS;
-
-	spin_lock_irqsave(&clk_lock, flags);
-	ret = clk->set_parent(clk, parent);
-	spin_unlock_irqrestore(&clk_lock, flags);
-
-	return ret;
-}
-EXPORT_SYMBOL(clk_set_parent);
-
-struct clk *clk_get_parent(struct clk *clk)
-{
-	return !clk ? NULL : clk->parent;
-}
-EXPORT_SYMBOL(clk_get_parent);
-
-
-
-#ifdef CONFIG_DEBUG_FS
-
-/* /sys/kernel/debug/at32ap_clk */
-
-#include <linux/io.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include "pm.h"
-
-
-#define	NEST_DELTA	2
-#define	NEST_MAX	6
-
-struct clkinf {
-	struct seq_file	*s;
-	unsigned	nest;
-};
-
-static void
-dump_clock(struct clk *parent, struct clkinf *r)
-{
-	unsigned	nest = r->nest;
-	char		buf[16 + NEST_MAX];
-	struct clk	*clk;
-	unsigned	i;
-
-	/* skip clocks coupled to devices that aren't registered */
-	if (parent->dev && !dev_name(parent->dev) && !parent->users)
-		return;
-
-	/* <nest spaces> name <pad to end> */
-	memset(buf, ' ', sizeof(buf) - 1);
-	buf[sizeof(buf) - 1] = 0;
-	i = strlen(parent->name);
-	memcpy(buf + nest, parent->name,
-			min(i, (unsigned)(sizeof(buf) - 1 - nest)));
-
-	seq_printf(r->s, "%s%c users=%2d %-3s %9ld Hz",
-		buf, parent->set_parent ? '*' : ' ',
-		parent->users,
-		parent->users ? "on" : "off",	/* NOTE: not-paranoid!! */
-		clk_get_rate(parent));
-	if (parent->dev)
-		seq_printf(r->s, ", for %s", dev_name(parent->dev));
-	seq_putc(r->s, '\n');
-
-	/* cost of this scan is small, but not linear... */
-	r->nest = nest + NEST_DELTA;
-
-	list_for_each_entry(clk, &at32_clock_list, list) {
-		if (clk->parent == parent)
-			dump_clock(clk, r);
-	}
-	r->nest = nest;
-}
-
-static int clk_show(struct seq_file *s, void *unused)
-{
-	struct clkinf	r;
-	int		i;
-	struct clk 	*clk;
-
-	/* show all the power manager registers */
-	seq_printf(s,
-		   "MCCTRL  = %8x\n"
-		   "CKSEL   = %8x\n"
-		   "CPUMASK = %8x\n"
-		   "HSBMASK = %8x\n"
-		   "PBAMASK = %8x\n"
-		   "PBBMASK = %8x\n"
-		   "PLL0    = %8x\n"
-		   "PLL1    = %8x\n"
-		   "IMR     = %8x\n",
-		   pm_readl(MCCTRL),
-		   pm_readl(CKSEL),
-		   pm_readl(CPU_MASK),
-		   pm_readl(HSB_MASK),
-		   pm_readl(PBA_MASK),
-		   pm_readl(PBB_MASK),
-		   pm_readl(PLL0),
-		   pm_readl(PLL1),
-		   pm_readl(IMR));
-	for (i = 0; i < 8; i++) {
-		if (i == 5)
-			continue;
-		seq_printf(s, "GCCTRL%d = %8x\n", i, pm_readl(GCCTRL(i)));
-	}
-
-	seq_putc(s, '\n');
-	r.s = s;
-	r.nest = 0;
-	/* protected from changes on the list while dumping */
-	spin_lock(&clk_list_lock);
-
-	/* show clock tree as derived from the three oscillators */
-	clk = __clk_get(NULL, "osc32k");
-	dump_clock(clk, &r);
-	clk_put(clk);
-
-	clk = __clk_get(NULL, "osc0");
-	dump_clock(clk, &r);
-	clk_put(clk);
-
-	clk = __clk_get(NULL, "osc1");
-	dump_clock(clk, &r);
-	clk_put(clk);
-
-	spin_unlock(&clk_list_lock);
-
-	return 0;
-}
-
-static int clk_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, clk_show, NULL);
-}
-
-static const struct file_operations clk_operations = {
-	.open		= clk_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int __init clk_debugfs_init(void)
-{
-	(void) debugfs_create_file("at32ap_clk", S_IFREG | S_IRUGO,
-			NULL, NULL, &clk_operations);
-
-	return 0;
-}
-postcore_initcall(clk_debugfs_init);
-
-#endif
diff --git a/arch/avr32/mach-at32ap/clock.h b/arch/avr32/mach-at32ap/clock.h
deleted file mode 100644
index 4c7ebbdc6dfa..000000000000
--- a/arch/avr32/mach-at32ap/clock.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Clock management for AT32AP CPUs
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * Based on arch/arm/mach-at91/clock.c
- *   Copyright (C) 2005 David Brownell
- *   Copyright (C) 2005 Ivan Kokshaysky
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/list.h>
-
-
-void at32_clk_register(struct clk *clk);
-
-struct clk {
-	struct list_head list;		/* linking element */
-	const char	*name;		/* Clock name/function */
-	struct device	*dev;		/* Device the clock is used by */
-	struct clk	*parent;	/* Parent clock, if any */
-	void		(*mode)(struct clk *clk, int enabled);
-	unsigned long	(*get_rate)(struct clk *clk);
-	long		(*set_rate)(struct clk *clk, unsigned long rate,
-				    int apply);
-	int		(*set_parent)(struct clk *clk, struct clk *parent);
-	u16		users;		/* Enabled if non-zero */
-	u16		index;		/* Sibling index */
-};
-
-unsigned long pba_clk_get_rate(struct clk *clk);
-void pba_clk_mode(struct clk *clk, int enabled);
diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c
deleted file mode 100644
index 96cabad68489..000000000000
--- a/arch/avr32/mach-at32ap/extint.c
+++ /dev/null
@@ -1,271 +0,0 @@
-/*
- * External interrupt handling for AT32AP CPUs
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/platform_device.h>
-#include <linux/random.h>
-#include <linux/slab.h>
-
-#include <asm/io.h>
-
-/* EIC register offsets */
-#define EIC_IER					0x0000
-#define EIC_IDR					0x0004
-#define EIC_IMR					0x0008
-#define EIC_ISR					0x000c
-#define EIC_ICR					0x0010
-#define EIC_MODE				0x0014
-#define EIC_EDGE				0x0018
-#define EIC_LEVEL				0x001c
-#define EIC_NMIC				0x0024
-
-/* Bitfields in NMIC */
-#define EIC_NMIC_ENABLE				(1 << 0)
-
-/* Bit manipulation macros */
-#define EIC_BIT(name)					\
-	(1 << EIC_##name##_OFFSET)
-#define EIC_BF(name,value)				\
-	(((value) & ((1 << EIC_##name##_SIZE) - 1))	\
-	 << EIC_##name##_OFFSET)
-#define EIC_BFEXT(name,value)				\
-	(((value) >> EIC_##name##_OFFSET)		\
-	 & ((1 << EIC_##name##_SIZE) - 1))
-#define EIC_BFINS(name,value,old)			\
-	(((old) & ~(((1 << EIC_##name##_SIZE) - 1)	\
-		    << EIC_##name##_OFFSET))		\
-	 | EIC_BF(name,value))
-
-/* Register access macros */
-#define eic_readl(port,reg)				\
-	__raw_readl((port)->regs + EIC_##reg)
-#define eic_writel(port,reg,value)			\
-	__raw_writel((value), (port)->regs + EIC_##reg)
-
-struct eic {
-	void __iomem *regs;
-	struct irq_chip *chip;
-	unsigned int first_irq;
-};
-
-static struct eic *nmi_eic;
-static bool nmi_enabled;
-
-static void eic_ack_irq(struct irq_data *d)
-{
-	struct eic *eic = irq_data_get_irq_chip_data(d);
-	eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq));
-}
-
-static void eic_mask_irq(struct irq_data *d)
-{
-	struct eic *eic = irq_data_get_irq_chip_data(d);
-	eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq));
-}
-
-static void eic_mask_ack_irq(struct irq_data *d)
-{
-	struct eic *eic = irq_data_get_irq_chip_data(d);
-	eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq));
-	eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq));
-}
-
-static void eic_unmask_irq(struct irq_data *d)
-{
-	struct eic *eic = irq_data_get_irq_chip_data(d);
-	eic_writel(eic, IER, 1 << (d->irq - eic->first_irq));
-}
-
-static int eic_set_irq_type(struct irq_data *d, unsigned int flow_type)
-{
-	struct eic *eic = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->irq;
-	unsigned int i = irq - eic->first_irq;
-	u32 mode, edge, level;
-
-	flow_type &= IRQ_TYPE_SENSE_MASK;
-	if (flow_type == IRQ_TYPE_NONE)
-		flow_type = IRQ_TYPE_LEVEL_LOW;
-
-	mode = eic_readl(eic, MODE);
-	edge = eic_readl(eic, EDGE);
-	level = eic_readl(eic, LEVEL);
-
-	switch (flow_type) {
-	case IRQ_TYPE_LEVEL_LOW:
-		mode |= 1 << i;
-		level &= ~(1 << i);
-		break;
-	case IRQ_TYPE_LEVEL_HIGH:
-		mode |= 1 << i;
-		level |= 1 << i;
-		break;
-	case IRQ_TYPE_EDGE_RISING:
-		mode &= ~(1 << i);
-		edge |= 1 << i;
-		break;
-	case IRQ_TYPE_EDGE_FALLING:
-		mode &= ~(1 << i);
-		edge &= ~(1 << i);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	eic_writel(eic, MODE, mode);
-	eic_writel(eic, EDGE, edge);
-	eic_writel(eic, LEVEL, level);
-
-	irqd_set_trigger_type(d, flow_type);
-	if (flow_type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
-		irq_set_handler_locked(d, handle_level_irq);
-	else
-		irq_set_handler_locked(d, handle_edge_irq);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip eic_chip = {
-	.name		= "eic",
-	.irq_ack	= eic_ack_irq,
-	.irq_mask	= eic_mask_irq,
-	.irq_mask_ack	= eic_mask_ack_irq,
-	.irq_unmask	= eic_unmask_irq,
-	.irq_set_type	= eic_set_irq_type,
-};
-
-static void demux_eic_irq(struct irq_desc *desc)
-{
-	struct eic *eic = irq_desc_get_handler_data(desc);
-	unsigned long status, pending;
-	unsigned int i;
-
-	status = eic_readl(eic, ISR);
-	pending = status & eic_readl(eic, IMR);
-
-	while (pending) {
-		i = fls(pending) - 1;
-		pending &= ~(1 << i);
-
-		generic_handle_irq(i + eic->first_irq);
-	}
-}
-
-int nmi_enable(void)
-{
-	nmi_enabled = true;
-
-	if (nmi_eic)
-		eic_writel(nmi_eic, NMIC, EIC_NMIC_ENABLE);
-
-	return 0;
-}
-
-void nmi_disable(void)
-{
-	if (nmi_eic)
-		eic_writel(nmi_eic, NMIC, 0);
-
-	nmi_enabled = false;
-}
-
-static int __init eic_probe(struct platform_device *pdev)
-{
-	struct eic *eic;
-	struct resource *regs;
-	unsigned int i;
-	unsigned int nr_of_irqs;
-	unsigned int int_irq;
-	int ret;
-	u32 pattern;
-
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	int_irq = platform_get_irq(pdev, 0);
-	if (!regs || (int)int_irq <= 0) {
-		dev_dbg(&pdev->dev, "missing regs and/or irq resource\n");
-		return -ENXIO;
-	}
-
-	ret = -ENOMEM;
-	eic = kzalloc(sizeof(struct eic), GFP_KERNEL);
-	if (!eic) {
-		dev_dbg(&pdev->dev, "no memory for eic structure\n");
-		goto err_kzalloc;
-	}
-
-	eic->first_irq = EIM_IRQ_BASE + 32 * pdev->id;
-	eic->regs = ioremap(regs->start, resource_size(regs));
-	if (!eic->regs) {
-		dev_dbg(&pdev->dev, "failed to map regs\n");
-		goto err_ioremap;
-	}
-
-	/*
-	 * Find out how many interrupt lines that are actually
-	 * implemented in hardware.
-	 */
-	eic_writel(eic, IDR, ~0UL);
-	eic_writel(eic, MODE, ~0UL);
-	pattern = eic_readl(eic, MODE);
-	nr_of_irqs = fls(pattern);
-
-	/* Trigger on low level unless overridden by driver */
-	eic_writel(eic, EDGE, 0UL);
-	eic_writel(eic, LEVEL, 0UL);
-
-	eic->chip = &eic_chip;
-
-	for (i = 0; i < nr_of_irqs; i++) {
-		irq_set_chip_and_handler(eic->first_irq + i, &eic_chip,
-					 handle_level_irq);
-		irq_set_chip_data(eic->first_irq + i, eic);
-	}
-
-	irq_set_chained_handler_and_data(int_irq, demux_eic_irq, eic);
-
-	if (pdev->id == 0) {
-		nmi_eic = eic;
-		if (nmi_enabled)
-			/*
-			 * Someone tried to enable NMI before we were
-			 * ready. Do it now.
-			 */
-			nmi_enable();
-	}
-
-	dev_info(&pdev->dev,
-		 "External Interrupt Controller at 0x%p, IRQ %u\n",
-		 eic->regs, int_irq);
-	dev_info(&pdev->dev,
-		 "Handling %u external IRQs, starting with IRQ %u\n",
-		 nr_of_irqs, eic->first_irq);
-
-	return 0;
-
-err_ioremap:
-	kfree(eic);
-err_kzalloc:
-	return ret;
-}
-
-static struct platform_driver eic_driver = {
-	.driver = {
-		.name = "at32_eic",
-	},
-};
-
-static int __init eic_init(void)
-{
-	return platform_driver_probe(&eic_driver, eic_probe);
-}
-arch_initcall(eic_init);
diff --git a/arch/avr32/mach-at32ap/hmatrix.c b/arch/avr32/mach-at32ap/hmatrix.c
deleted file mode 100644
index 48f5ede77468..000000000000
--- a/arch/avr32/mach-at32ap/hmatrix.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * High-Speed Bus Matrix helper functions
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include <mach/chip.h>
-#include <mach/hmatrix.h>
-
-static inline void __hmatrix_write_reg(unsigned long offset, u32 value)
-{
-	__raw_writel(value, (void __iomem __force *)(HMATRIX_BASE + offset));
-}
-
-static inline u32 __hmatrix_read_reg(unsigned long offset)
-{
-	return __raw_readl((void __iomem __force *)(HMATRIX_BASE + offset));
-}
-
-/**
- * hmatrix_write_reg - write HMATRIX configuration register
- * @offset: register offset
- * @value: value to be written to the register at @offset
- */
-void hmatrix_write_reg(unsigned long offset, u32 value)
-{
-	clk_enable(&at32_hmatrix_clk);
-	__hmatrix_write_reg(offset, value);
-	__hmatrix_read_reg(offset);
-	clk_disable(&at32_hmatrix_clk);
-}
-
-/**
- * hmatrix_read_reg - read HMATRIX configuration register
- * @offset: register offset
- *
- * Returns the value of the register at @offset.
- */
-u32 hmatrix_read_reg(unsigned long offset)
-{
-	u32 value;
-
-	clk_enable(&at32_hmatrix_clk);
-	value = __hmatrix_read_reg(offset);
-	clk_disable(&at32_hmatrix_clk);
-
-	return value;
-}
-
-/**
- * hmatrix_sfr_set_bits - set bits in a slave's Special Function Register
- * @slave_id: operate on the SFR belonging to this slave
- * @mask: mask of bits to be set in the SFR
- */
-void hmatrix_sfr_set_bits(unsigned int slave_id, u32 mask)
-{
-	u32 value;
-
-	clk_enable(&at32_hmatrix_clk);
-	value = __hmatrix_read_reg(HMATRIX_SFR(slave_id));
-	value |= mask;
-	__hmatrix_write_reg(HMATRIX_SFR(slave_id), value);
-	__hmatrix_read_reg(HMATRIX_SFR(slave_id));
-	clk_disable(&at32_hmatrix_clk);
-}
-
-/**
- * hmatrix_sfr_set_bits - clear bits in a slave's Special Function Register
- * @slave_id: operate on the SFR belonging to this slave
- * @mask: mask of bits to be cleared in the SFR
- */
-void hmatrix_sfr_clear_bits(unsigned int slave_id, u32 mask)
-{
-	u32 value;
-
-	clk_enable(&at32_hmatrix_clk);
-	value = __hmatrix_read_reg(HMATRIX_SFR(slave_id));
-	value &= ~mask;
-	__hmatrix_write_reg(HMATRIX_SFR(slave_id), value);
-	__hmatrix_read_reg(HMATRIX_SFR(slave_id));
-	clk_disable(&at32_hmatrix_clk);
-}
diff --git a/arch/avr32/mach-at32ap/hsmc.c b/arch/avr32/mach-at32ap/hsmc.c
deleted file mode 100644
index f66245e6e63e..000000000000
--- a/arch/avr32/mach-at32ap/hsmc.c
+++ /dev/null
@@ -1,282 +0,0 @@
-/*
- * Static Memory Controller for AT32 chips
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-#include <asm/io.h>
-#include <mach/smc.h>
-
-#include "hsmc.h"
-
-#define NR_CHIP_SELECTS 6
-
-struct hsmc {
-	void __iomem *regs;
-	struct clk *pclk;
-	struct clk *mck;
-};
-
-static struct hsmc *hsmc;
-
-void smc_set_timing(struct smc_config *config,
-		    const struct smc_timing *timing)
-{
-	int recover;
-	int cycle;
-
-	unsigned long mul;
-
-	/* Reset all SMC timings */
-	config->ncs_read_setup	= 0;
-	config->nrd_setup	= 0;
-	config->ncs_write_setup	= 0;
-	config->nwe_setup	= 0;
-	config->ncs_read_pulse	= 0;
-	config->nrd_pulse	= 0;
-	config->ncs_write_pulse	= 0;
-	config->nwe_pulse	= 0;
-	config->read_cycle	= 0;
-	config->write_cycle	= 0;
-
-	/*
-	 * cycles = x / T = x * f
-	 *   = ((x * 1000000000) * ((f * 65536) / 1000000000)) / 65536
-	 *   = ((x * 1000000000) * (((f / 10000) * 65536) / 100000)) / 65536
-	 */
-	mul = (clk_get_rate(hsmc->mck) / 10000) << 16;
-	mul /= 100000;
-
-#define ns2cyc(x) ((((x) * mul) + 65535) >> 16)
-
-	if (timing->ncs_read_setup > 0)
-		config->ncs_read_setup = ns2cyc(timing->ncs_read_setup);
-
-	if (timing->nrd_setup > 0)
-		config->nrd_setup = ns2cyc(timing->nrd_setup);
-
-	if (timing->ncs_write_setup > 0)
-		config->ncs_write_setup = ns2cyc(timing->ncs_write_setup);
-
-	if (timing->nwe_setup > 0)
-		config->nwe_setup = ns2cyc(timing->nwe_setup);
-
-	if (timing->ncs_read_pulse > 0)
-		config->ncs_read_pulse = ns2cyc(timing->ncs_read_pulse);
-
-	if (timing->nrd_pulse > 0)
-		config->nrd_pulse = ns2cyc(timing->nrd_pulse);
-
-	if (timing->ncs_write_pulse > 0)
-		config->ncs_write_pulse = ns2cyc(timing->ncs_write_pulse);
-
-	if (timing->nwe_pulse > 0)
-		config->nwe_pulse = ns2cyc(timing->nwe_pulse);
-
-	if (timing->read_cycle > 0)
-		config->read_cycle = ns2cyc(timing->read_cycle);
-
-	if (timing->write_cycle > 0)
-		config->write_cycle = ns2cyc(timing->write_cycle);
-
-	/* Extend read cycle in needed */
-	if (timing->ncs_read_recover > 0)
-		recover = ns2cyc(timing->ncs_read_recover);
-	else
-		recover = 1;
-
-	cycle = config->ncs_read_setup + config->ncs_read_pulse + recover;
-
-	if (config->read_cycle < cycle)
-		config->read_cycle = cycle;
-
-	/* Extend read cycle in needed */
-	if (timing->nrd_recover > 0)
-		recover = ns2cyc(timing->nrd_recover);
-	else
-		recover = 1;
-
-	cycle = config->nrd_setup + config->nrd_pulse + recover;
-
-	if (config->read_cycle < cycle)
-		config->read_cycle = cycle;
-
-	/* Extend write cycle in needed */
-	if (timing->ncs_write_recover > 0)
-		recover = ns2cyc(timing->ncs_write_recover);
-	else
-		recover = 1;
-
-	cycle = config->ncs_write_setup + config->ncs_write_pulse + recover;
-
-	if (config->write_cycle < cycle)
-		config->write_cycle = cycle;
-
-	/* Extend write cycle in needed */
-	if (timing->nwe_recover > 0)
-		recover = ns2cyc(timing->nwe_recover);
-	else
-		recover = 1;
-
-	cycle = config->nwe_setup + config->nwe_pulse + recover;
-
-	if (config->write_cycle < cycle)
-		config->write_cycle = cycle;
-}
-EXPORT_SYMBOL(smc_set_timing);
-
-int smc_set_configuration(int cs, const struct smc_config *config)
-{
-	unsigned long offset;
-	u32 setup, pulse, cycle, mode;
-
-	if (!hsmc)
-		return -ENODEV;
-	if (cs >= NR_CHIP_SELECTS)
-		return -EINVAL;
-
-	setup = (HSMC_BF(NWE_SETUP, config->nwe_setup)
-		 | HSMC_BF(NCS_WR_SETUP, config->ncs_write_setup)
-		 | HSMC_BF(NRD_SETUP, config->nrd_setup)
-		 | HSMC_BF(NCS_RD_SETUP, config->ncs_read_setup));
-	pulse = (HSMC_BF(NWE_PULSE, config->nwe_pulse)
-		 | HSMC_BF(NCS_WR_PULSE, config->ncs_write_pulse)
-		 | HSMC_BF(NRD_PULSE, config->nrd_pulse)
-		 | HSMC_BF(NCS_RD_PULSE, config->ncs_read_pulse));
-	cycle = (HSMC_BF(NWE_CYCLE, config->write_cycle)
-		 | HSMC_BF(NRD_CYCLE, config->read_cycle));
-
-	switch (config->bus_width) {
-	case 1:
-		mode = HSMC_BF(DBW, HSMC_DBW_8_BITS);
-		break;
-	case 2:
-		mode = HSMC_BF(DBW, HSMC_DBW_16_BITS);
-		break;
-	case 4:
-		mode = HSMC_BF(DBW, HSMC_DBW_32_BITS);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (config->nwait_mode) {
-	case 0:
-		mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_DISABLED);
-		break;
-	case 1:
-		mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_RESERVED);
-		break;
-	case 2:
-		mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_FROZEN);
-		break;
-	case 3:
-		mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_READY);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (config->tdf_cycles) {
-		mode |= HSMC_BF(TDF_CYCLES, config->tdf_cycles);
-	}
-
-	if (config->nrd_controlled)
-		mode |= HSMC_BIT(READ_MODE);
-	if (config->nwe_controlled)
-		mode |= HSMC_BIT(WRITE_MODE);
-	if (config->byte_write)
-		mode |= HSMC_BIT(BAT);
-	if (config->tdf_mode)
-		mode |= HSMC_BIT(TDF_MODE);
-
-	pr_debug("smc cs%d: setup/%08x pulse/%08x cycle/%08x mode/%08x\n",
-		 cs, setup, pulse, cycle, mode);
-
-	offset = cs * 0x10;
-	hsmc_writel(hsmc, SETUP0 + offset, setup);
-	hsmc_writel(hsmc, PULSE0 + offset, pulse);
-	hsmc_writel(hsmc, CYCLE0 + offset, cycle);
-	hsmc_writel(hsmc, MODE0 + offset, mode);
-	hsmc_readl(hsmc, MODE0); /* I/O barrier */
-
-	return 0;
-}
-EXPORT_SYMBOL(smc_set_configuration);
-
-static int hsmc_probe(struct platform_device *pdev)
-{
-	struct resource *regs;
-	struct clk *pclk, *mck;
-	int ret;
-
-	if (hsmc)
-		return -EBUSY;
-
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!regs)
-		return -ENXIO;
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk))
-		return PTR_ERR(pclk);
-	mck = clk_get(&pdev->dev, "mck");
-	if (IS_ERR(mck)) {
-		ret = PTR_ERR(mck);
-		goto out_put_pclk;
-	}
-
-	ret = -ENOMEM;
-	hsmc = kzalloc(sizeof(struct hsmc), GFP_KERNEL);
-	if (!hsmc)
-		goto out_put_clocks;
-
-	clk_enable(pclk);
-	clk_enable(mck);
-
-	hsmc->pclk = pclk;
-	hsmc->mck = mck;
-	hsmc->regs = ioremap(regs->start, resource_size(regs));
-	if (!hsmc->regs)
-		goto out_disable_clocks;
-
-	dev_info(&pdev->dev, "Atmel Static Memory Controller at 0x%08lx\n",
-		 (unsigned long)regs->start);
-
-	platform_set_drvdata(pdev, hsmc);
-
-	return 0;
-
-out_disable_clocks:
-	clk_disable(mck);
-	clk_disable(pclk);
-	kfree(hsmc);
-out_put_clocks:
-	clk_put(mck);
-out_put_pclk:
-	clk_put(pclk);
-	hsmc = NULL;
-	return ret;
-}
-
-static struct platform_driver hsmc_driver = {
-	.probe		= hsmc_probe,
-	.driver		= {
-		.name	= "smc",
-	},
-};
-
-static int __init hsmc_init(void)
-{
-	return platform_driver_register(&hsmc_driver);
-}
-core_initcall(hsmc_init);
diff --git a/arch/avr32/mach-at32ap/hsmc.h b/arch/avr32/mach-at32ap/hsmc.h
deleted file mode 100644
index d1d48e26e393..000000000000
--- a/arch/avr32/mach-at32ap/hsmc.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * Register definitions for Atmel Static Memory Controller (SMC)
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_HSMC_H__
-#define __ASM_AVR32_HSMC_H__
-
-/* HSMC register offsets */
-#define HSMC_SETUP0				0x0000
-#define HSMC_PULSE0				0x0004
-#define HSMC_CYCLE0				0x0008
-#define HSMC_MODE0				0x000c
-#define HSMC_SETUP1				0x0010
-#define HSMC_PULSE1				0x0014
-#define HSMC_CYCLE1				0x0018
-#define HSMC_MODE1				0x001c
-#define HSMC_SETUP2				0x0020
-#define HSMC_PULSE2				0x0024
-#define HSMC_CYCLE2				0x0028
-#define HSMC_MODE2				0x002c
-#define HSMC_SETUP3				0x0030
-#define HSMC_PULSE3				0x0034
-#define HSMC_CYCLE3				0x0038
-#define HSMC_MODE3				0x003c
-#define HSMC_SETUP4				0x0040
-#define HSMC_PULSE4				0x0044
-#define HSMC_CYCLE4				0x0048
-#define HSMC_MODE4				0x004c
-#define HSMC_SETUP5				0x0050
-#define HSMC_PULSE5				0x0054
-#define HSMC_CYCLE5				0x0058
-#define HSMC_MODE5				0x005c
-
-/* Bitfields in SETUP0 */
-#define HSMC_NWE_SETUP_OFFSET			0
-#define HSMC_NWE_SETUP_SIZE			6
-#define HSMC_NCS_WR_SETUP_OFFSET		8
-#define HSMC_NCS_WR_SETUP_SIZE			6
-#define HSMC_NRD_SETUP_OFFSET			16
-#define HSMC_NRD_SETUP_SIZE			6
-#define HSMC_NCS_RD_SETUP_OFFSET		24
-#define HSMC_NCS_RD_SETUP_SIZE			6
-
-/* Bitfields in PULSE0 */
-#define HSMC_NWE_PULSE_OFFSET			0
-#define HSMC_NWE_PULSE_SIZE			7
-#define HSMC_NCS_WR_PULSE_OFFSET		8
-#define HSMC_NCS_WR_PULSE_SIZE			7
-#define HSMC_NRD_PULSE_OFFSET			16
-#define HSMC_NRD_PULSE_SIZE			7
-#define HSMC_NCS_RD_PULSE_OFFSET		24
-#define HSMC_NCS_RD_PULSE_SIZE			7
-
-/* Bitfields in CYCLE0 */
-#define HSMC_NWE_CYCLE_OFFSET			0
-#define HSMC_NWE_CYCLE_SIZE			9
-#define HSMC_NRD_CYCLE_OFFSET			16
-#define HSMC_NRD_CYCLE_SIZE			9
-
-/* Bitfields in MODE0 */
-#define HSMC_READ_MODE_OFFSET			0
-#define HSMC_READ_MODE_SIZE			1
-#define HSMC_WRITE_MODE_OFFSET			1
-#define HSMC_WRITE_MODE_SIZE			1
-#define HSMC_EXNW_MODE_OFFSET			4
-#define HSMC_EXNW_MODE_SIZE			2
-#define HSMC_BAT_OFFSET				8
-#define HSMC_BAT_SIZE				1
-#define HSMC_DBW_OFFSET				12
-#define HSMC_DBW_SIZE				2
-#define HSMC_TDF_CYCLES_OFFSET			16
-#define HSMC_TDF_CYCLES_SIZE			4
-#define HSMC_TDF_MODE_OFFSET			20
-#define HSMC_TDF_MODE_SIZE			1
-#define HSMC_PMEN_OFFSET			24
-#define HSMC_PMEN_SIZE				1
-#define HSMC_PS_OFFSET				28
-#define HSMC_PS_SIZE				2
-
-/* Constants for READ_MODE */
-#define HSMC_READ_MODE_NCS_CONTROLLED		0
-#define HSMC_READ_MODE_NRD_CONTROLLED		1
-
-/* Constants for WRITE_MODE */
-#define HSMC_WRITE_MODE_NCS_CONTROLLED		0
-#define HSMC_WRITE_MODE_NWE_CONTROLLED		1
-
-/* Constants for EXNW_MODE */
-#define HSMC_EXNW_MODE_DISABLED			0
-#define HSMC_EXNW_MODE_RESERVED			1
-#define HSMC_EXNW_MODE_FROZEN			2
-#define HSMC_EXNW_MODE_READY			3
-
-/* Constants for BAT */
-#define HSMC_BAT_BYTE_SELECT			0
-#define HSMC_BAT_BYTE_WRITE			1
-
-/* Constants for DBW */
-#define HSMC_DBW_8_BITS				0
-#define HSMC_DBW_16_BITS			1
-#define HSMC_DBW_32_BITS			2
-
-/* Bit manipulation macros */
-#define HSMC_BIT(name)							\
-	(1 << HSMC_##name##_OFFSET)
-#define HSMC_BF(name,value)						\
-	(((value) & ((1 << HSMC_##name##_SIZE) - 1))			\
-	 << HSMC_##name##_OFFSET)
-#define HSMC_BFEXT(name,value)						\
-	(((value) >> HSMC_##name##_OFFSET)				\
-	 & ((1 << HSMC_##name##_SIZE) - 1))
-#define HSMC_BFINS(name,value,old)					\
-	(((old) & ~(((1 << HSMC_##name##_SIZE) - 1)			\
-		    << HSMC_##name##_OFFSET)) | HSMC_BF(name,value))
-
-/* Register access macros */
-#define hsmc_readl(port,reg)						\
-	__raw_readl((port)->regs + HSMC_##reg)
-#define hsmc_writel(port,reg,value)					\
-	__raw_writel((value), (port)->regs + HSMC_##reg)
-
-#endif /* __ASM_AVR32_HSMC_H__ */
diff --git a/arch/avr32/mach-at32ap/include/mach/at32ap700x.h b/arch/avr32/mach-at32ap/include/mach/at32ap700x.h
deleted file mode 100644
index b9222bf895bc..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/at32ap700x.h
+++ /dev/null
@@ -1,245 +0,0 @@
-/*
- * Pin definitions for AT32AP7000.
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_AT32AP700X_H__
-#define __ASM_ARCH_AT32AP700X_H__
-
-#define GPIO_PERIPH_A	0
-#define GPIO_PERIPH_B	1
-
-/*
- * Pin numbers identifying specific GPIO pins on the chip. They can
- * also be converted to IRQ numbers by passing them through
- * gpio_to_irq().
- */
-#define GPIO_PIOA_BASE	(0)
-#define GPIO_PIOB_BASE	(GPIO_PIOA_BASE + 32)
-#define GPIO_PIOC_BASE	(GPIO_PIOB_BASE + 32)
-#define GPIO_PIOD_BASE	(GPIO_PIOC_BASE + 32)
-#define GPIO_PIOE_BASE	(GPIO_PIOD_BASE + 32)
-
-#define GPIO_PIN_PA(N)	(GPIO_PIOA_BASE + (N))
-#define GPIO_PIN_PB(N)	(GPIO_PIOB_BASE + (N))
-#define GPIO_PIN_PC(N)	(GPIO_PIOC_BASE + (N))
-#define GPIO_PIN_PD(N)	(GPIO_PIOD_BASE + (N))
-#define GPIO_PIN_PE(N)	(GPIO_PIOE_BASE + (N))
-
-
-/*
- * DMAC peripheral hardware handshaking interfaces, used with dw_dmac
- */
-#define DMAC_MCI_RX		0
-#define DMAC_MCI_TX		1
-#define DMAC_DAC_TX		2
-#define DMAC_AC97_A_RX		3
-#define DMAC_AC97_A_TX		4
-#define DMAC_AC97_B_RX		5
-#define DMAC_AC97_B_TX		6
-#define DMAC_DMAREQ_0		7
-#define DMAC_DMAREQ_1		8
-#define DMAC_DMAREQ_2		9
-#define DMAC_DMAREQ_3		10
-
-/* HSB master IDs */
-#define HMATRIX_MASTER_CPU_DCACHE		0
-#define HMATRIX_MASTER_CPU_ICACHE		1
-#define HMATRIX_MASTER_PDC			2
-#define HMATRIX_MASTER_ISI			3
-#define HMATRIX_MASTER_USBA			4
-#define HMATRIX_MASTER_LCDC			5
-#define HMATRIX_MASTER_MACB0			6
-#define HMATRIX_MASTER_MACB1			7
-#define HMATRIX_MASTER_DMACA_M0			8
-#define HMATRIX_MASTER_DMACA_M1			9
-
-/* HSB slave IDs */
-#define HMATRIX_SLAVE_SRAM0			0
-#define HMATRIX_SLAVE_SRAM1			1
-#define HMATRIX_SLAVE_PBA			2
-#define HMATRIX_SLAVE_PBB			3
-#define HMATRIX_SLAVE_EBI			4
-#define HMATRIX_SLAVE_USBA			5
-#define HMATRIX_SLAVE_LCDC			6
-#define HMATRIX_SLAVE_DMACA			7
-
-/* Bits in HMATRIX SFR4 (EBI) */
-#define HMATRIX_EBI_SDRAM_ENABLE		(1 << 1)
-#define HMATRIX_EBI_NAND_ENABLE			(1 << 3)
-#define HMATRIX_EBI_CF0_ENABLE			(1 << 4)
-#define HMATRIX_EBI_CF1_ENABLE			(1 << 5)
-#define HMATRIX_EBI_PULLUP_DISABLE		(1 << 8)
-
-/*
- * Base addresses of controllers that may be accessed early by
- * platform code.
- */
-#define PM_BASE		0xfff00000
-#define HMATRIX_BASE	0xfff00800
-#define SDRAMC_BASE	0xfff03800
-
-/* LCDC on port C */
-#define ATMEL_LCDC_PC_CC	(1ULL << 19)
-#define ATMEL_LCDC_PC_HSYNC	(1ULL << 20)
-#define ATMEL_LCDC_PC_PCLK	(1ULL << 21)
-#define ATMEL_LCDC_PC_VSYNC	(1ULL << 22)
-#define ATMEL_LCDC_PC_DVAL	(1ULL << 23)
-#define ATMEL_LCDC_PC_MODE	(1ULL << 24)
-#define ATMEL_LCDC_PC_PWR	(1ULL << 25)
-#define ATMEL_LCDC_PC_DATA0	(1ULL << 26)
-#define ATMEL_LCDC_PC_DATA1	(1ULL << 27)
-#define ATMEL_LCDC_PC_DATA2	(1ULL << 28)
-#define ATMEL_LCDC_PC_DATA3	(1ULL << 29)
-#define ATMEL_LCDC_PC_DATA4	(1ULL << 30)
-#define ATMEL_LCDC_PC_DATA5	(1ULL << 31)
-
-/* LCDC on port D */
-#define ATMEL_LCDC_PD_DATA6	(1ULL << 0)
-#define ATMEL_LCDC_PD_DATA7	(1ULL << 1)
-#define ATMEL_LCDC_PD_DATA8	(1ULL << 2)
-#define ATMEL_LCDC_PD_DATA9	(1ULL << 3)
-#define ATMEL_LCDC_PD_DATA10	(1ULL << 4)
-#define ATMEL_LCDC_PD_DATA11	(1ULL << 5)
-#define ATMEL_LCDC_PD_DATA12	(1ULL << 6)
-#define ATMEL_LCDC_PD_DATA13	(1ULL << 7)
-#define ATMEL_LCDC_PD_DATA14	(1ULL << 8)
-#define ATMEL_LCDC_PD_DATA15	(1ULL << 9)
-#define ATMEL_LCDC_PD_DATA16	(1ULL << 10)
-#define ATMEL_LCDC_PD_DATA17	(1ULL << 11)
-#define ATMEL_LCDC_PD_DATA18	(1ULL << 12)
-#define ATMEL_LCDC_PD_DATA19	(1ULL << 13)
-#define ATMEL_LCDC_PD_DATA20	(1ULL << 14)
-#define ATMEL_LCDC_PD_DATA21	(1ULL << 15)
-#define ATMEL_LCDC_PD_DATA22	(1ULL << 16)
-#define ATMEL_LCDC_PD_DATA23	(1ULL << 17)
-
-/* LCDC on port E */
-#define ATMEL_LCDC_PE_CC	(1ULL << (32 + 0))
-#define ATMEL_LCDC_PE_DVAL	(1ULL << (32 + 1))
-#define ATMEL_LCDC_PE_MODE	(1ULL << (32 + 2))
-#define ATMEL_LCDC_PE_DATA0	(1ULL << (32 + 3))
-#define ATMEL_LCDC_PE_DATA1	(1ULL << (32 + 4))
-#define ATMEL_LCDC_PE_DATA2	(1ULL << (32 + 5))
-#define ATMEL_LCDC_PE_DATA3	(1ULL << (32 + 6))
-#define ATMEL_LCDC_PE_DATA4	(1ULL << (32 + 7))
-#define ATMEL_LCDC_PE_DATA8	(1ULL << (32 + 8))
-#define ATMEL_LCDC_PE_DATA9	(1ULL << (32 + 9))
-#define ATMEL_LCDC_PE_DATA10	(1ULL << (32 + 10))
-#define ATMEL_LCDC_PE_DATA11	(1ULL << (32 + 11))
-#define ATMEL_LCDC_PE_DATA12	(1ULL << (32 + 12))
-#define ATMEL_LCDC_PE_DATA16	(1ULL << (32 + 13))
-#define ATMEL_LCDC_PE_DATA17	(1ULL << (32 + 14))
-#define ATMEL_LCDC_PE_DATA18	(1ULL << (32 + 15))
-#define ATMEL_LCDC_PE_DATA19	(1ULL << (32 + 16))
-#define ATMEL_LCDC_PE_DATA20	(1ULL << (32 + 17))
-#define ATMEL_LCDC_PE_DATA21	(1ULL << (32 + 18))
-
-
-#define ATMEL_LCDC(PORT, PIN)	(ATMEL_LCDC_##PORT##_##PIN)
-
-
-#define ATMEL_LCDC_PRI_24B_DATA	(					\
-		ATMEL_LCDC(PC, DATA0)  | ATMEL_LCDC(PC, DATA1)  |	\
-		ATMEL_LCDC(PC, DATA2)  | ATMEL_LCDC(PC, DATA3)  |	\
-		ATMEL_LCDC(PC, DATA4)  | ATMEL_LCDC(PC, DATA5)  |	\
-		ATMEL_LCDC(PD, DATA6)  | ATMEL_LCDC(PD, DATA7)  |	\
-		ATMEL_LCDC(PD, DATA8)  | ATMEL_LCDC(PD, DATA9)  |	\
-		ATMEL_LCDC(PD, DATA10) | ATMEL_LCDC(PD, DATA11) |	\
-		ATMEL_LCDC(PD, DATA12) | ATMEL_LCDC(PD, DATA13) |	\
-		ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) |	\
-		ATMEL_LCDC(PD, DATA16) | ATMEL_LCDC(PD, DATA17) |	\
-		ATMEL_LCDC(PD, DATA18) | ATMEL_LCDC(PD, DATA19) |	\
-		ATMEL_LCDC(PD, DATA20) | ATMEL_LCDC(PD, DATA21) |	\
-		ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_ALT_24B_DATA (					\
-		ATMEL_LCDC(PE, DATA0)  | ATMEL_LCDC(PE, DATA1)  |	\
-		ATMEL_LCDC(PE, DATA2)  | ATMEL_LCDC(PE, DATA3)  |	\
-		ATMEL_LCDC(PE, DATA4)  | ATMEL_LCDC(PC, DATA5)  |	\
-		ATMEL_LCDC(PD, DATA6)  | ATMEL_LCDC(PD, DATA7)  |	\
-		ATMEL_LCDC(PE, DATA8)  | ATMEL_LCDC(PE, DATA9)  |	\
-		ATMEL_LCDC(PE, DATA10) | ATMEL_LCDC(PE, DATA11) |	\
-		ATMEL_LCDC(PE, DATA12) | ATMEL_LCDC(PD, DATA13) |	\
-		ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) |	\
-		ATMEL_LCDC(PE, DATA16) | ATMEL_LCDC(PE, DATA17) |	\
-		ATMEL_LCDC(PE, DATA18) | ATMEL_LCDC(PE, DATA19) |	\
-		ATMEL_LCDC(PE, DATA20) | ATMEL_LCDC(PE, DATA21) |	\
-		ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_PRI_18B_DATA (					\
-		ATMEL_LCDC(PC, DATA2)  | ATMEL_LCDC(PC, DATA3)  |	\
-		ATMEL_LCDC(PC, DATA4)  | ATMEL_LCDC(PC, DATA5)  |	\
-		ATMEL_LCDC(PD, DATA6)  | ATMEL_LCDC(PD, DATA7)  |	\
-		ATMEL_LCDC(PD, DATA10) | ATMEL_LCDC(PD, DATA11) |	\
-		ATMEL_LCDC(PD, DATA12) | ATMEL_LCDC(PD, DATA13) |	\
-		ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) |	\
-		ATMEL_LCDC(PD, DATA18) | ATMEL_LCDC(PD, DATA19) |	\
-		ATMEL_LCDC(PD, DATA20) | ATMEL_LCDC(PD, DATA21) |	\
-		ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_ALT_18B_DATA	(					\
-		ATMEL_LCDC(PE, DATA2)  | ATMEL_LCDC(PE, DATA3)  |	\
-		ATMEL_LCDC(PE, DATA4)  | ATMEL_LCDC(PC, DATA5)  |	\
-		ATMEL_LCDC(PD, DATA6)  | ATMEL_LCDC(PD, DATA7)  |	\
-		ATMEL_LCDC(PE, DATA10) | ATMEL_LCDC(PE, DATA11) |	\
-		ATMEL_LCDC(PE, DATA12) | ATMEL_LCDC(PD, DATA13) |	\
-		ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) |	\
-		ATMEL_LCDC(PE, DATA18) | ATMEL_LCDC(PE, DATA19) |	\
-		ATMEL_LCDC(PE, DATA20) | ATMEL_LCDC(PE, DATA21) |	\
-		ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_PRI_15B_DATA (					\
-		ATMEL_LCDC(PC, DATA3)  | ATMEL_LCDC(PC, DATA4)  |	\
-		ATMEL_LCDC(PC, DATA5)  | ATMEL_LCDC(PD, DATA6)  |	\
-		ATMEL_LCDC(PD, DATA7)  |				\
-		ATMEL_LCDC(PD, DATA11) | ATMEL_LCDC(PD, DATA12) |	\
-		ATMEL_LCDC(PD, DATA13) | ATMEL_LCDC(PD, DATA14) |	\
-		ATMEL_LCDC(PD, DATA15) |				\
-		ATMEL_LCDC(PD, DATA19) | ATMEL_LCDC(PD, DATA20) |	\
-		ATMEL_LCDC(PD, DATA21) | ATMEL_LCDC(PD, DATA22) |	\
-		ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_ALT_15B_DATA	(					\
-		ATMEL_LCDC(PE, DATA3)  | ATMEL_LCDC(PE, DATA4)  |	\
-		ATMEL_LCDC(PC, DATA5)  | ATMEL_LCDC(PD, DATA6)  |	\
-		ATMEL_LCDC(PD, DATA7)  |				\
-		ATMEL_LCDC(PE, DATA11) | ATMEL_LCDC(PE, DATA12) |	\
-		ATMEL_LCDC(PD, DATA13) | ATMEL_LCDC(PD, DATA14) |	\
-		ATMEL_LCDC(PD, DATA15) |				\
-		ATMEL_LCDC(PE, DATA19) | ATMEL_LCDC(PE, DATA20) |	\
-		ATMEL_LCDC(PE, DATA21) | ATMEL_LCDC(PD, DATA22) |	\
-		ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_PRI_CONTROL (					\
-		ATMEL_LCDC(PC, CC)   | ATMEL_LCDC(PC, DVAL) |		\
-		ATMEL_LCDC(PC, MODE) | ATMEL_LCDC(PC, PWR))
-
-#define ATMEL_LCDC_ALT_CONTROL (					\
-		ATMEL_LCDC(PE, CC)   | ATMEL_LCDC(PE, DVAL) |		\
-		ATMEL_LCDC(PE, MODE) | ATMEL_LCDC(PC, PWR))
-
-#define ATMEL_LCDC_CONTROL (						\
-		ATMEL_LCDC(PC, HSYNC) | ATMEL_LCDC(PC, VSYNC) |		\
-		ATMEL_LCDC(PC, PCLK))
-
-#define ATMEL_LCDC_PRI_24BIT	(ATMEL_LCDC_CONTROL | ATMEL_LCDC_PRI_24B_DATA)
-
-#define ATMEL_LCDC_ALT_24BIT	(ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_24B_DATA)
-
-#define ATMEL_LCDC_PRI_18BIT	(ATMEL_LCDC_CONTROL | ATMEL_LCDC_PRI_18B_DATA)
-
-#define ATMEL_LCDC_ALT_18BIT	(ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_18B_DATA)
-
-#define ATMEL_LCDC_PRI_15BIT	(ATMEL_LCDC_CONTROL | ATMEL_LCDC_PRI_15B_DATA)
-
-#define ATMEL_LCDC_ALT_15BIT	(ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_15B_DATA)
-
-/* Bitmask for all EBI data (D16..D31) pins on port E */
-#define ATMEL_EBI_PE_DATA_ALL  (0x0000FFFF)
-
-#endif /* __ASM_ARCH_AT32AP700X_H__ */
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
deleted file mode 100644
index f1a316d52c73..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- * Platform data definitions.
- */
-#ifndef __ASM_ARCH_BOARD_H
-#define __ASM_ARCH_BOARD_H
-
-#include <linux/types.h>
-#include <linux/serial.h>
-#include <linux/platform_data/macb.h>
-#include <linux/platform_data/atmel.h>
-
-#define GPIO_PIN_NONE	(-1)
-
-/*
- * Clock rates for various on-board oscillators. The number of entries
- * in this array is chip-dependent.
- */
-extern unsigned long at32_board_osc_rates[];
-
-/*
- * This used to add essential system devices, but this is now done
- * automatically. Please don't use it in new board code.
- */
-static inline void __deprecated at32_add_system_devices(void)
-{
-
-}
-
-extern struct platform_device *atmel_default_console_device;
-
-/* Flags for selecting USART extra pins */
-#define	ATMEL_USART_RTS		0x01
-#define	ATMEL_USART_CTS		0x02
-#define	ATMEL_USART_CLK		0x04
-
-void at32_map_usart(unsigned int hw_id, unsigned int line, int flags);
-struct platform_device *at32_add_device_usart(unsigned int id);
-
-struct platform_device *
-at32_add_device_eth(unsigned int id, struct macb_platform_data *data);
-
-struct spi_board_info;
-struct platform_device *
-at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n);
-void at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n);
-
-struct atmel_lcdfb_pdata;
-struct platform_device *
-at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data,
-		     unsigned long fbmem_start, unsigned long fbmem_len,
-		     u64 pin_mask);
-
-struct usba_platform_data;
-struct platform_device *
-at32_add_device_usba(unsigned int id, struct usba_platform_data *data);
-
-struct ide_platform_data {
-	u8      cs;
-};
-struct platform_device *
-at32_add_device_ide(unsigned int id, unsigned int extint,
-		    struct ide_platform_data *data);
-
-/* mask says which PWM channels to mux */
-struct platform_device *at32_add_device_pwm(u32 mask);
-
-/* depending on what's hooked up, not all SSC pins will be used */
-#define	ATMEL_SSC_TK		0x01
-#define	ATMEL_SSC_TF		0x02
-#define	ATMEL_SSC_TD		0x04
-#define	ATMEL_SSC_TX		(ATMEL_SSC_TK | ATMEL_SSC_TF | ATMEL_SSC_TD)
-
-#define	ATMEL_SSC_RK		0x10
-#define	ATMEL_SSC_RF		0x20
-#define	ATMEL_SSC_RD		0x40
-#define	ATMEL_SSC_RX		(ATMEL_SSC_RK | ATMEL_SSC_RF | ATMEL_SSC_RD)
-
-struct platform_device *
-at32_add_device_ssc(unsigned int id, unsigned int flags);
-
-struct i2c_board_info;
-struct platform_device *at32_add_device_twi(unsigned int id,
-					    struct i2c_board_info *b,
-					    unsigned int n);
-
-struct mci_platform_data;
-struct platform_device *
-at32_add_device_mci(unsigned int id, struct mci_platform_data *data);
-
-struct ac97c_platform_data;
-struct platform_device *
-at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
-		      unsigned int flags);
-
-struct atmel_abdac_pdata;
-struct platform_device *
-at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data);
-
-struct platform_device *at32_add_device_psif(unsigned int id);
-
-struct cf_platform_data {
-	int	detect_pin;
-	int	reset_pin;
-	int	vcc_pin;
-	int	ready_pin;
-	u8	cs;
-};
-struct platform_device *
-at32_add_device_cf(unsigned int id, unsigned int extint,
-		struct cf_platform_data *data);
-
-struct platform_device *
-at32_add_device_nand(unsigned int id, struct atmel_nand_data *data);
-
-#endif /* __ASM_ARCH_BOARD_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/chip.h b/arch/avr32/mach-at32ap/include/mach/chip.h
deleted file mode 100644
index 5efca6da6acb..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/chip.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * AVR32 chip-specific definitions
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ARCH_CHIP_H__
-#define __ASM_AVR32_ARCH_CHIP_H__
-
-#if defined(CONFIG_CPU_AT32AP700X)
-# include <mach/at32ap700x.h>
-#else
-# error Unknown chip type selected
-#endif
-
-#endif /* __ASM_AVR32_ARCH_CHIP_H__ */
diff --git a/arch/avr32/mach-at32ap/include/mach/cpu.h b/arch/avr32/mach-at32ap/include/mach/cpu.h
deleted file mode 100644
index 4181086f4ddc..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/cpu.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * AVR32 CPU identification
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_CPU_H
-#define __ASM_ARCH_CPU_H
-
-/*
- * Only AT32AP7000 is defined for now. We can identify the specific
- * chip at runtime, but I'm not sure if it's really worth it.
- */
-#ifdef CONFIG_CPU_AT32AP700X
-# define cpu_is_at32ap7000()	(1)
-#else
-# define cpu_is_at32ap7000()	(0)
-#endif
-
-#endif /* __ASM_ARCH_CPU_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/gpio.h b/arch/avr32/mach-at32ap/include/mach/gpio.h
deleted file mode 100644
index 0180f584ef03..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/gpio.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef __ASM_AVR32_ARCH_GPIO_H
-#define __ASM_AVR32_ARCH_GPIO_H
-
-#include <linux/compiler.h>
-#include <asm/irq.h>
-
-
-/* Some GPIO chips can manage IRQs; some can't.  The exact numbers can
- * be changed if needed, but for the moment they're not configurable.
- */
-#define ARCH_NR_GPIOS	(NR_GPIO_IRQS + 2 * 32)
-
-
-/* Arch-neutral GPIO API, supporting both "native" and external GPIOs. */
-#include <asm-generic/gpio.h>
-
-static inline int gpio_get_value(unsigned int gpio)
-{
-	return __gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned int gpio, int value)
-{
-	__gpio_set_value(gpio, value);
-}
-
-static inline int gpio_cansleep(unsigned int gpio)
-{
-	return __gpio_cansleep(gpio);
-}
-
-
-static inline int gpio_to_irq(unsigned int gpio)
-{
-	if (gpio < NR_GPIO_IRQS)
-		return gpio + GPIO_IRQ_BASE;
-	return -EINVAL;
-}
-
-static inline int irq_to_gpio(unsigned int irq)
-{
-	return irq - GPIO_IRQ_BASE;
-}
-
-#endif /* __ASM_AVR32_ARCH_GPIO_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/hmatrix.h b/arch/avr32/mach-at32ap/include/mach/hmatrix.h
deleted file mode 100644
index 7a368f227ebc..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/hmatrix.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * High-Speed Bus Matrix configuration registers
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __HMATRIX_H
-#define __HMATRIX_H
-
-extern struct clk at32_hmatrix_clk;
-
-void hmatrix_write_reg(unsigned long offset, u32 value);
-u32 hmatrix_read_reg(unsigned long offset);
-
-void hmatrix_sfr_set_bits(unsigned int slave_id, u32 mask);
-void hmatrix_sfr_clear_bits(unsigned int slave_id, u32 mask);
-
-/* Master Configuration register */
-#define HMATRIX_MCFG(m)			(0x0000 + 4 * (m))
-/* Undefined length burst limit */
-# define HMATRIX_MCFG_ULBT_INFINITE	0	/* Infinite length */
-# define HMATRIX_MCFG_ULBT_SINGLE	1	/* Single Access */
-# define HMATRIX_MCFG_ULBT_FOUR_BEAT	2	/* Four beat */
-# define HMATRIX_MCFG_ULBT_EIGHT_BEAT	3	/* Eight beat */
-# define HMATRIX_MCFG_ULBT_SIXTEEN_BEAT	4	/* Sixteen beat */
-
-/* Slave Configuration register */
-#define HMATRIX_SCFG(s)			(0x0040 + 4 * (s))
-# define HMATRIX_SCFG_SLOT_CYCLE(x)	((x) <<  0)	/* Max burst cycles */
-# define HMATRIX_SCFG_DEFMSTR_NONE	(  0 << 16)	/* No default master */
-# define HMATRIX_SCFG_DEFMSTR_LAST	(  1 << 16)	/* Last def master */
-# define HMATRIX_SCFG_DEFMSTR_FIXED	(  2 << 16)	/* Fixed def master */
-# define HMATRIX_SCFG_FIXED_DEFMSTR(m)	((m) << 18)	/* Fixed master ID */
-# define HMATRIX_SCFG_ARBT_ROUND_ROBIN	(  0 << 24)	/* RR arbitration */
-# define HMATRIX_SCFG_ARBT_FIXED_PRIO	(  1 << 24)	/* Fixed priority */
-
-/* Slave Priority register A (master 0..7) */
-#define HMATRIX_PRAS(s)			(0x0080 + 8 * (s))
-# define HMATRIX_PRAS_PRIO(m, p)	((p) << ((m) * 4))
-
-/* Slave Priority register A (master 8..15) */
-#define HMATRIX_PRBS(s)			(0x0084 + 8 * (s))
-# define HMATRIX_PRBS_PRIO(m, p)	((p) << (((m) - 8) * 4))
-
-/* Master Remap Control Register */
-#define HMATRIX_MRCR				0x0100
-# define HMATRIX_MRCR_REMAP(m)		(  1 << (m))	/* Remap master m */
-
-/* Special Function Register. Bit definitions are chip-specific */
-#define HMATRIX_SFR(s)			(0x0110 + 4 * (s))
-
-#endif /* __HMATRIX_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/init.h b/arch/avr32/mach-at32ap/include/mach/init.h
deleted file mode 100644
index bc40e3d46150..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/init.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * AT32AP platform initialization calls.
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_AT32AP_INIT_H__
-#define __ASM_AVR32_AT32AP_INIT_H__
-
-void setup_platform(void);
-void setup_board(void);
-
-void at32_setup_serial_console(unsigned int usart_id);
-
-#endif /* __ASM_AVR32_AT32AP_INIT_H__ */
diff --git a/arch/avr32/mach-at32ap/include/mach/io.h b/arch/avr32/mach-at32ap/include/mach/io.h
deleted file mode 100644
index 22ea79b74052..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/io.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef __ASM_AVR32_ARCH_AT32AP_IO_H
-#define __ASM_AVR32_ARCH_AT32AP_IO_H
-
-#include <linux/swab.h>
-
-#if defined(CONFIG_AP700X_32_BIT_SMC)
-# define __swizzle_addr_b(addr)	(addr ^ 3UL)
-# define __swizzle_addr_w(addr)	(addr ^ 2UL)
-# define __swizzle_addr_l(addr)	(addr)
-# define ioswabb(a, x)		(x)
-# define ioswabw(a, x)		(x)
-# define ioswabl(a, x)		(x)
-# define __mem_ioswabb(a, x)	(x)
-# define __mem_ioswabw(a, x)	swab16(x)
-# define __mem_ioswabl(a, x)	swab32(x)
-#elif defined(CONFIG_AP700X_16_BIT_SMC)
-# define __swizzle_addr_b(addr)	(addr ^ 1UL)
-# define __swizzle_addr_w(addr)	(addr)
-# define __swizzle_addr_l(addr)	(addr)
-# define ioswabb(a, x)		(x)
-# define ioswabw(a, x)		(x)
-# define ioswabl(a, x)		swahw32(x)
-# define __mem_ioswabb(a, x)	(x)
-# define __mem_ioswabw(a, x)	swab16(x)
-# define __mem_ioswabl(a, x)	swahb32(x)
-#else
-# define __swizzle_addr_b(addr)	(addr)
-# define __swizzle_addr_w(addr)	(addr)
-# define __swizzle_addr_l(addr)	(addr)
-# define ioswabb(a, x)		(x)
-# define ioswabw(a, x)		swab16(x)
-# define ioswabl(a, x)		swab32(x)
-# define __mem_ioswabb(a, x)	(x)
-# define __mem_ioswabw(a, x)	(x)
-# define __mem_ioswabl(a, x)	(x)
-#endif
-
-#endif /* __ASM_AVR32_ARCH_AT32AP_IO_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/irq.h b/arch/avr32/mach-at32ap/include/mach/irq.h
deleted file mode 100644
index 608e350368c7..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/irq.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_AVR32_ARCH_IRQ_H
-#define __ASM_AVR32_ARCH_IRQ_H
-
-#define EIM_IRQ_BASE	NR_INTERNAL_IRQS
-#define NR_EIM_IRQS	32
-#define AT32_EXTINT(n)	(EIM_IRQ_BASE + (n))
-
-#define GPIO_IRQ_BASE	(EIM_IRQ_BASE + NR_EIM_IRQS)
-#define NR_GPIO_CTLR	(5 /*internal*/ + 1 /*external*/)
-#define NR_GPIO_IRQS	(NR_GPIO_CTLR * 32)
-
-#define NR_IRQS		(GPIO_IRQ_BASE + NR_GPIO_IRQS)
-
-#endif /* __ASM_AVR32_ARCH_IRQ_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/pm.h b/arch/avr32/mach-at32ap/include/mach/pm.h
deleted file mode 100644
index f29ff2cd23d3..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/pm.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * AVR32 AP Power Management.
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ARCH_PM_H
-#define __ASM_AVR32_ARCH_PM_H
-
-/* Possible arguments to the "sleep" instruction */
-#define CPU_SLEEP_IDLE		0
-#define CPU_SLEEP_FROZEN	1
-#define CPU_SLEEP_STANDBY	2
-#define CPU_SLEEP_STOP		3
-#define CPU_SLEEP_STATIC	5
-
-#ifndef __ASSEMBLY__
-extern void cpu_enter_idle(void);
-extern void cpu_enter_standby(unsigned long sdramc_base);
-
-void intc_set_suspend_handler(unsigned long offset);
-#endif
-
-#endif /* __ASM_AVR32_ARCH_PM_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/portmux.h b/arch/avr32/mach-at32ap/include/mach/portmux.h
deleted file mode 100644
index 4873024e3b96..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/portmux.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * AT32 portmux interface.
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_PORTMUX_H__
-#define __ASM_ARCH_PORTMUX_H__
-
-/*
- * Set up pin multiplexing, called from board init only.
- *
- * The following flags determine the initial state of the pin.
- */
-#define AT32_GPIOF_PULLUP	0x00000001	/* (not-OUT) Enable pull-up */
-#define AT32_GPIOF_OUTPUT	0x00000002	/* (OUT) Enable output driver */
-#define AT32_GPIOF_HIGH		0x00000004	/* (OUT) Set output high */
-#define AT32_GPIOF_DEGLITCH	0x00000008	/* (IN) Filter glitches */
-#define AT32_GPIOF_MULTIDRV	0x00000010	/* Enable multidriver option */
-
-void at32_select_periph(unsigned int port, unsigned int pin,
-			unsigned int periph, unsigned long flags);
-void at32_select_gpio(unsigned int pin, unsigned long flags);
-void at32_deselect_pin(unsigned int pin);
-void at32_reserve_pin(unsigned int port, u32 pin_mask);
-
-#endif /* __ASM_ARCH_PORTMUX_H__ */
diff --git a/arch/avr32/mach-at32ap/include/mach/smc.h b/arch/avr32/mach-at32ap/include/mach/smc.h
deleted file mode 100644
index c98eea44a70a..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/smc.h
+++ /dev/null
@@ -1,113 +0,0 @@
-/*
- * Static Memory Controller for AT32 chips
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * Inspired by the OMAP2 General-Purpose Memory Controller interface
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AT32AP_SMC_H
-#define __ARCH_AT32AP_SMC_H
-
-/*
- * All timing parameters are in nanoseconds.
- */
-struct smc_timing {
-	/* Delay from address valid to assertion of given strobe */
-	int ncs_read_setup;
-	int nrd_setup;
-	int ncs_write_setup;
-	int nwe_setup;
-
-	/* Pulse length of given strobe */
-	int ncs_read_pulse;
-	int nrd_pulse;
-	int ncs_write_pulse;
-	int nwe_pulse;
-
-	/* Total cycle length of given operation */
-	int read_cycle;
-	int write_cycle;
-
-	/* Minimal recovery times, will extend cycle if needed */
-	int ncs_read_recover;
-	int nrd_recover;
-	int ncs_write_recover;
-	int nwe_recover;
-};
-
-/*
- * All timing parameters are in clock cycles.
- */
-struct smc_config {
-
-	/* Delay from address valid to assertion of given strobe */
-	u8		ncs_read_setup;
-	u8		nrd_setup;
-	u8		ncs_write_setup;
-	u8		nwe_setup;
-
-	/* Pulse length of given strobe */
-	u8		ncs_read_pulse;
-	u8		nrd_pulse;
-	u8		ncs_write_pulse;
-	u8		nwe_pulse;
-
-	/* Total cycle length of given operation */
-	u8		read_cycle;
-	u8		write_cycle;
-
-	/* Bus width in bytes */
-	u8		bus_width;
-
-	/*
-	 * 0: Data is sampled on rising edge of NCS
-	 * 1: Data is sampled on rising edge of NRD
-	 */
-	unsigned int	nrd_controlled:1;
-
-	/*
-	 * 0: Data is driven on falling edge of NCS
-	 * 1: Data is driven on falling edge of NWR
-	 */
-	unsigned int	nwe_controlled:1;
-
-	/*
-	 * 0: NWAIT is disabled
-	 * 1: Reserved
-	 * 2: NWAIT is frozen mode
-	 * 3: NWAIT in ready mode
-	 */
-	unsigned int	nwait_mode:2;
-
-	/*
-	 * 0: Byte select access type
-	 * 1: Byte write access type
-	 */
-	unsigned int	byte_write:1;
-
-	/*
-	 * Number of clock cycles before data is released after
-	 * the rising edge of the read controlling signal
-	 *
-	 * Total cycles from SMC is tdf_cycles + 1
-	 */
-	unsigned int	tdf_cycles:4;
-
-	/*
-	 * 0: TDF optimization disabled
-	 * 1: TDF optimization enabled
-	 */
-	unsigned int	tdf_mode:1;
-};
-
-extern void smc_set_timing(struct smc_config *config,
-			   const struct smc_timing *timing);
-
-extern int smc_set_configuration(int cs, const struct smc_config *config);
-extern struct smc_config *smc_get_configuration(int cs);
-
-#endif /* __ARCH_AT32AP_SMC_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/sram.h b/arch/avr32/mach-at32ap/include/mach/sram.h
deleted file mode 100644
index 4838dae7601a..000000000000
--- a/arch/avr32/mach-at32ap/include/mach/sram.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Simple SRAM allocator
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ARCH_SRAM_H
-#define __ASM_AVR32_ARCH_SRAM_H
-
-#include <linux/genalloc.h>
-
-extern struct gen_pool *sram_pool;
-
-static inline unsigned long sram_alloc(size_t len)
-{
-	if (!sram_pool)
-		return 0UL;
-
-	return gen_pool_alloc(sram_pool, len);
-}
-
-static inline void sram_free(unsigned long addr, size_t len)
-{
-	return gen_pool_free(sram_pool, addr, len);
-}
-
-#endif /* __ASM_AVR32_ARCH_SRAM_H */
diff --git a/arch/avr32/mach-at32ap/intc.c b/arch/avr32/mach-at32ap/intc.c
deleted file mode 100644
index aaff83cc50f0..000000000000
--- a/arch/avr32/mach-at32ap/intc.c
+++ /dev/null
@@ -1,200 +0,0 @@
-/*
- * Copyright (C) 2006, 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/platform_device.h>
-#include <linux/syscore_ops.h>
-#include <linux/export.h>
-
-#include <asm/io.h>
-
-#include "intc.h"
-
-struct intc {
-	void __iomem		*regs;
-	struct irq_chip		chip;
-#ifdef CONFIG_PM
-	unsigned long		suspend_ipr;
-	unsigned long		saved_ipr[64];
-#endif
-};
-
-extern struct platform_device at32_intc0_device;
-
-/*
- * TODO: We may be able to implement mask/unmask by setting IxM flags
- * in the status register.
- */
-static void intc_mask_irq(struct irq_data *d)
-{
-
-}
-
-static void intc_unmask_irq(struct irq_data *d)
-{
-
-}
-
-static struct intc intc0 = {
-	.chip = {
-		.name		= "intc",
-		.irq_mask	= intc_mask_irq,
-		.irq_unmask	= intc_unmask_irq,
-	},
-};
-
-/*
- * All interrupts go via intc at some point.
- */
-asmlinkage void do_IRQ(int level, struct pt_regs *regs)
-{
-	struct pt_regs *old_regs;
-	unsigned int irq;
-	unsigned long status_reg;
-
-	local_irq_disable();
-
-	old_regs = set_irq_regs(regs);
-
-	irq_enter();
-
-	irq = intc_readl(&intc0, INTCAUSE0 - 4 * level);
-	generic_handle_irq(irq);
-
-	/*
-	 * Clear all interrupt level masks so that we may handle
-	 * interrupts during softirq processing.  If this is a nested
-	 * interrupt, interrupts must stay globally disabled until we
-	 * return.
-	 */
-	status_reg = sysreg_read(SR);
-	status_reg &= ~(SYSREG_BIT(I0M) | SYSREG_BIT(I1M)
-			| SYSREG_BIT(I2M) | SYSREG_BIT(I3M));
-	sysreg_write(SR, status_reg);
-
-	irq_exit();
-
-	set_irq_regs(old_regs);
-}
-
-void __init init_IRQ(void)
-{
-	extern void _evba(void);
-	extern void irq_level0(void);
-	struct resource *regs;
-	struct clk *pclk;
-	unsigned int i;
-	u32 offset, readback;
-
-	regs = platform_get_resource(&at32_intc0_device, IORESOURCE_MEM, 0);
-	if (!regs) {
-		printk(KERN_EMERG "intc: no mmio resource defined\n");
-		goto fail;
-	}
-	pclk = clk_get(&at32_intc0_device.dev, "pclk");
-	if (IS_ERR(pclk)) {
-		printk(KERN_EMERG "intc: no clock defined\n");
-		goto fail;
-	}
-
-	clk_enable(pclk);
-
-	intc0.regs = ioremap(regs->start, resource_size(regs));
-	if (!intc0.regs) {
-		printk(KERN_EMERG "intc: failed to map registers (0x%08lx)\n",
-		       (unsigned long)regs->start);
-		goto fail;
-	}
-
-	/*
-	 * Initialize all interrupts to level 0 (lowest priority). The
-	 * priority level may be changed by calling
-	 * irq_set_priority().
-	 *
-	 */
-	offset = (unsigned long)&irq_level0 - (unsigned long)&_evba;
-	for (i = 0; i < NR_INTERNAL_IRQS; i++) {
-		intc_writel(&intc0, INTPR0 + 4 * i, offset);
-		readback = intc_readl(&intc0, INTPR0 + 4 * i);
-		if (readback == offset)
-			irq_set_chip_and_handler(i, &intc0.chip,
-						 handle_simple_irq);
-	}
-
-	/* Unmask all interrupt levels */
-	sysreg_write(SR, (sysreg_read(SR)
-			  & ~(SR_I3M | SR_I2M | SR_I1M | SR_I0M)));
-
-	return;
-
-fail:
-	panic("Interrupt controller initialization failed!\n");
-}
-
-#ifdef CONFIG_PM
-void intc_set_suspend_handler(unsigned long offset)
-{
-	intc0.suspend_ipr = offset;
-}
-
-static int intc_suspend(void)
-{
-	int i;
-
-	if (unlikely(!irqs_disabled())) {
-		pr_err("intc_suspend: called with interrupts enabled\n");
-		return -EINVAL;
-	}
-
-	if (unlikely(!intc0.suspend_ipr)) {
-		pr_err("intc_suspend: suspend_ipr not initialized\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < 64; i++) {
-		intc0.saved_ipr[i] = intc_readl(&intc0, INTPR0 + 4 * i);
-		intc_writel(&intc0, INTPR0 + 4 * i, intc0.suspend_ipr);
-	}
-
-	return 0;
-}
-
-static void intc_resume(void)
-{
-	int i;
-
-	for (i = 0; i < 64; i++)
-		intc_writel(&intc0, INTPR0 + 4 * i, intc0.saved_ipr[i]);
-}
-#else
-#define intc_suspend	NULL
-#define intc_resume	NULL
-#endif
-
-static struct syscore_ops intc_syscore_ops = {
-	.suspend	= intc_suspend,
-	.resume		= intc_resume,
-};
-
-static int __init intc_init_syscore(void)
-{
-	register_syscore_ops(&intc_syscore_ops);
-
-	return 0;
-}
-device_initcall(intc_init_syscore);
-
-unsigned long intc_get_pending(unsigned int group)
-{
-	return intc_readl(&intc0, INTREQ0 + 4 * group);
-}
-EXPORT_SYMBOL_GPL(intc_get_pending);
diff --git a/arch/avr32/mach-at32ap/intc.h b/arch/avr32/mach-at32ap/intc.h
deleted file mode 100644
index 4d3664e43a8e..000000000000
--- a/arch/avr32/mach-at32ap/intc.h
+++ /dev/null
@@ -1,329 +0,0 @@
-/*
- * Automatically generated by gen-header.xsl
- */
-#ifndef __ASM_AVR32_PERIHP_INTC_H__
-#define __ASM_AVR32_PERIHP_INTC_H__
-
-#define INTC_NUM_INT_GRPS            33
-
-#define INTC_INTPR0                  0x0
-# define INTC_INTPR0_INTLEV_OFFSET   30
-# define INTC_INTPR0_INTLEV_SIZE     2
-# define INTC_INTPR0_OFFSET_OFFSET   0
-# define INTC_INTPR0_OFFSET_SIZE     24
-#define INTC_INTREQ0                 0x100
-# define INTC_INTREQ0_IREQUEST0_OFFSET 0
-# define INTC_INTREQ0_IREQUEST0_SIZE 1
-# define INTC_INTREQ0_IREQUEST1_OFFSET 1
-# define INTC_INTREQ0_IREQUEST1_SIZE 1
-#define INTC_INTPR1                  0x4
-# define INTC_INTPR1_INTLEV_OFFSET   30
-# define INTC_INTPR1_INTLEV_SIZE     2
-# define INTC_INTPR1_OFFSET_OFFSET   0
-# define INTC_INTPR1_OFFSET_SIZE     24
-#define INTC_INTREQ1                 0x104
-# define INTC_INTREQ1_IREQUEST32_OFFSET 0
-# define INTC_INTREQ1_IREQUEST32_SIZE 1
-# define INTC_INTREQ1_IREQUEST33_OFFSET 1
-# define INTC_INTREQ1_IREQUEST33_SIZE 1
-# define INTC_INTREQ1_IREQUEST34_OFFSET 2
-# define INTC_INTREQ1_IREQUEST34_SIZE 1
-# define INTC_INTREQ1_IREQUEST35_OFFSET 3
-# define INTC_INTREQ1_IREQUEST35_SIZE 1
-# define INTC_INTREQ1_IREQUEST36_OFFSET 4
-# define INTC_INTREQ1_IREQUEST36_SIZE 1
-# define INTC_INTREQ1_IREQUEST37_OFFSET 5
-# define INTC_INTREQ1_IREQUEST37_SIZE 1
-#define INTC_INTPR2                  0x8
-# define INTC_INTPR2_INTLEV_OFFSET   30
-# define INTC_INTPR2_INTLEV_SIZE     2
-# define INTC_INTPR2_OFFSET_OFFSET   0
-# define INTC_INTPR2_OFFSET_SIZE     24
-#define INTC_INTREQ2                 0x108
-# define INTC_INTREQ2_IREQUEST64_OFFSET 0
-# define INTC_INTREQ2_IREQUEST64_SIZE 1
-# define INTC_INTREQ2_IREQUEST65_OFFSET 1
-# define INTC_INTREQ2_IREQUEST65_SIZE 1
-# define INTC_INTREQ2_IREQUEST66_OFFSET 2
-# define INTC_INTREQ2_IREQUEST66_SIZE 1
-# define INTC_INTREQ2_IREQUEST67_OFFSET 3
-# define INTC_INTREQ2_IREQUEST67_SIZE 1
-# define INTC_INTREQ2_IREQUEST68_OFFSET 4
-# define INTC_INTREQ2_IREQUEST68_SIZE 1
-#define INTC_INTPR3                  0xc
-# define INTC_INTPR3_INTLEV_OFFSET   30
-# define INTC_INTPR3_INTLEV_SIZE     2
-# define INTC_INTPR3_OFFSET_OFFSET   0
-# define INTC_INTPR3_OFFSET_SIZE     24
-#define INTC_INTREQ3                 0x10c
-# define INTC_INTREQ3_IREQUEST96_OFFSET 0
-# define INTC_INTREQ3_IREQUEST96_SIZE 1
-#define INTC_INTPR4                  0x10
-# define INTC_INTPR4_INTLEV_OFFSET   30
-# define INTC_INTPR4_INTLEV_SIZE     2
-# define INTC_INTPR4_OFFSET_OFFSET   0
-# define INTC_INTPR4_OFFSET_SIZE     24
-#define INTC_INTREQ4                 0x110
-# define INTC_INTREQ4_IREQUEST128_OFFSET 0
-# define INTC_INTREQ4_IREQUEST128_SIZE 1
-#define INTC_INTPR5                  0x14
-# define INTC_INTPR5_INTLEV_OFFSET   30
-# define INTC_INTPR5_INTLEV_SIZE     2
-# define INTC_INTPR5_OFFSET_OFFSET   0
-# define INTC_INTPR5_OFFSET_SIZE     24
-#define INTC_INTREQ5                 0x114
-# define INTC_INTREQ5_IREQUEST160_OFFSET 0
-# define INTC_INTREQ5_IREQUEST160_SIZE 1
-#define INTC_INTPR6                  0x18
-# define INTC_INTPR6_INTLEV_OFFSET   30
-# define INTC_INTPR6_INTLEV_SIZE     2
-# define INTC_INTPR6_OFFSET_OFFSET   0
-# define INTC_INTPR6_OFFSET_SIZE     24
-#define INTC_INTREQ6                 0x118
-# define INTC_INTREQ6_IREQUEST192_OFFSET 0
-# define INTC_INTREQ6_IREQUEST192_SIZE 1
-#define INTC_INTPR7                  0x1c
-# define INTC_INTPR7_INTLEV_OFFSET   30
-# define INTC_INTPR7_INTLEV_SIZE     2
-# define INTC_INTPR7_OFFSET_OFFSET   0
-# define INTC_INTPR7_OFFSET_SIZE     24
-#define INTC_INTREQ7                 0x11c
-# define INTC_INTREQ7_IREQUEST224_OFFSET 0
-# define INTC_INTREQ7_IREQUEST224_SIZE 1
-#define INTC_INTPR8                  0x20
-# define INTC_INTPR8_INTLEV_OFFSET   30
-# define INTC_INTPR8_INTLEV_SIZE     2
-# define INTC_INTPR8_OFFSET_OFFSET   0
-# define INTC_INTPR8_OFFSET_SIZE     24
-#define INTC_INTREQ8                 0x120
-# define INTC_INTREQ8_IREQUEST256_OFFSET 0
-# define INTC_INTREQ8_IREQUEST256_SIZE 1
-#define INTC_INTPR9                  0x24
-# define INTC_INTPR9_INTLEV_OFFSET   30
-# define INTC_INTPR9_INTLEV_SIZE     2
-# define INTC_INTPR9_OFFSET_OFFSET   0
-# define INTC_INTPR9_OFFSET_SIZE     24
-#define INTC_INTREQ9                 0x124
-# define INTC_INTREQ9_IREQUEST288_OFFSET 0
-# define INTC_INTREQ9_IREQUEST288_SIZE 1
-#define INTC_INTPR10                 0x28
-# define INTC_INTPR10_INTLEV_OFFSET  30
-# define INTC_INTPR10_INTLEV_SIZE    2
-# define INTC_INTPR10_OFFSET_OFFSET  0
-# define INTC_INTPR10_OFFSET_SIZE    24
-#define INTC_INTREQ10                0x128
-# define INTC_INTREQ10_IREQUEST320_OFFSET 0
-# define INTC_INTREQ10_IREQUEST320_SIZE 1
-#define INTC_INTPR11                 0x2c
-# define INTC_INTPR11_INTLEV_OFFSET  30
-# define INTC_INTPR11_INTLEV_SIZE    2
-# define INTC_INTPR11_OFFSET_OFFSET  0
-# define INTC_INTPR11_OFFSET_SIZE    24
-#define INTC_INTREQ11                0x12c
-# define INTC_INTREQ11_IREQUEST352_OFFSET 0
-# define INTC_INTREQ11_IREQUEST352_SIZE 1
-#define INTC_INTPR12                 0x30
-# define INTC_INTPR12_INTLEV_OFFSET  30
-# define INTC_INTPR12_INTLEV_SIZE    2
-# define INTC_INTPR12_OFFSET_OFFSET  0
-# define INTC_INTPR12_OFFSET_SIZE    24
-#define INTC_INTREQ12                0x130
-# define INTC_INTREQ12_IREQUEST384_OFFSET 0
-# define INTC_INTREQ12_IREQUEST384_SIZE 1
-#define INTC_INTPR13                 0x34
-# define INTC_INTPR13_INTLEV_OFFSET  30
-# define INTC_INTPR13_INTLEV_SIZE    2
-# define INTC_INTPR13_OFFSET_OFFSET  0
-# define INTC_INTPR13_OFFSET_SIZE    24
-#define INTC_INTREQ13                0x134
-# define INTC_INTREQ13_IREQUEST416_OFFSET 0
-# define INTC_INTREQ13_IREQUEST416_SIZE 1
-#define INTC_INTPR14                 0x38
-# define INTC_INTPR14_INTLEV_OFFSET  30
-# define INTC_INTPR14_INTLEV_SIZE    2
-# define INTC_INTPR14_OFFSET_OFFSET  0
-# define INTC_INTPR14_OFFSET_SIZE    24
-#define INTC_INTREQ14                0x138
-# define INTC_INTREQ14_IREQUEST448_OFFSET 0
-# define INTC_INTREQ14_IREQUEST448_SIZE 1
-#define INTC_INTPR15                 0x3c
-# define INTC_INTPR15_INTLEV_OFFSET  30
-# define INTC_INTPR15_INTLEV_SIZE    2
-# define INTC_INTPR15_OFFSET_OFFSET  0
-# define INTC_INTPR15_OFFSET_SIZE    24
-#define INTC_INTREQ15                0x13c
-# define INTC_INTREQ15_IREQUEST480_OFFSET 0
-# define INTC_INTREQ15_IREQUEST480_SIZE 1
-#define INTC_INTPR16                 0x40
-# define INTC_INTPR16_INTLEV_OFFSET  30
-# define INTC_INTPR16_INTLEV_SIZE    2
-# define INTC_INTPR16_OFFSET_OFFSET  0
-# define INTC_INTPR16_OFFSET_SIZE    24
-#define INTC_INTREQ16                0x140
-# define INTC_INTREQ16_IREQUEST512_OFFSET 0
-# define INTC_INTREQ16_IREQUEST512_SIZE 1
-#define INTC_INTPR17                 0x44
-# define INTC_INTPR17_INTLEV_OFFSET  30
-# define INTC_INTPR17_INTLEV_SIZE    2
-# define INTC_INTPR17_OFFSET_OFFSET  0
-# define INTC_INTPR17_OFFSET_SIZE    24
-#define INTC_INTREQ17                0x144
-# define INTC_INTREQ17_IREQUEST544_OFFSET 0
-# define INTC_INTREQ17_IREQUEST544_SIZE 1
-#define INTC_INTPR18                 0x48
-# define INTC_INTPR18_INTLEV_OFFSET  30
-# define INTC_INTPR18_INTLEV_SIZE    2
-# define INTC_INTPR18_OFFSET_OFFSET  0
-# define INTC_INTPR18_OFFSET_SIZE    24
-#define INTC_INTREQ18                0x148
-# define INTC_INTREQ18_IREQUEST576_OFFSET 0
-# define INTC_INTREQ18_IREQUEST576_SIZE 1
-#define INTC_INTPR19                 0x4c
-# define INTC_INTPR19_INTLEV_OFFSET  30
-# define INTC_INTPR19_INTLEV_SIZE    2
-# define INTC_INTPR19_OFFSET_OFFSET  0
-# define INTC_INTPR19_OFFSET_SIZE    24
-#define INTC_INTREQ19                0x14c
-# define INTC_INTREQ19_IREQUEST608_OFFSET 0
-# define INTC_INTREQ19_IREQUEST608_SIZE 1
-# define INTC_INTREQ19_IREQUEST609_OFFSET 1
-# define INTC_INTREQ19_IREQUEST609_SIZE 1
-# define INTC_INTREQ19_IREQUEST610_OFFSET 2
-# define INTC_INTREQ19_IREQUEST610_SIZE 1
-# define INTC_INTREQ19_IREQUEST611_OFFSET 3
-# define INTC_INTREQ19_IREQUEST611_SIZE 1
-#define INTC_INTPR20                 0x50
-# define INTC_INTPR20_INTLEV_OFFSET  30
-# define INTC_INTPR20_INTLEV_SIZE    2
-# define INTC_INTPR20_OFFSET_OFFSET  0
-# define INTC_INTPR20_OFFSET_SIZE    24
-#define INTC_INTREQ20                0x150
-# define INTC_INTREQ20_IREQUEST640_OFFSET 0
-# define INTC_INTREQ20_IREQUEST640_SIZE 1
-#define INTC_INTPR21                 0x54
-# define INTC_INTPR21_INTLEV_OFFSET  30
-# define INTC_INTPR21_INTLEV_SIZE    2
-# define INTC_INTPR21_OFFSET_OFFSET  0
-# define INTC_INTPR21_OFFSET_SIZE    24
-#define INTC_INTREQ21                0x154
-# define INTC_INTREQ21_IREQUEST672_OFFSET 0
-# define INTC_INTREQ21_IREQUEST672_SIZE 1
-#define INTC_INTPR22                 0x58
-# define INTC_INTPR22_INTLEV_OFFSET  30
-# define INTC_INTPR22_INTLEV_SIZE    2
-# define INTC_INTPR22_OFFSET_OFFSET  0
-# define INTC_INTPR22_OFFSET_SIZE    24
-#define INTC_INTREQ22                0x158
-# define INTC_INTREQ22_IREQUEST704_OFFSET 0
-# define INTC_INTREQ22_IREQUEST704_SIZE 1
-# define INTC_INTREQ22_IREQUEST705_OFFSET 1
-# define INTC_INTREQ22_IREQUEST705_SIZE 1
-# define INTC_INTREQ22_IREQUEST706_OFFSET 2
-# define INTC_INTREQ22_IREQUEST706_SIZE 1
-#define INTC_INTPR23                 0x5c
-# define INTC_INTPR23_INTLEV_OFFSET  30
-# define INTC_INTPR23_INTLEV_SIZE    2
-# define INTC_INTPR23_OFFSET_OFFSET  0
-# define INTC_INTPR23_OFFSET_SIZE    24
-#define INTC_INTREQ23                0x15c
-# define INTC_INTREQ23_IREQUEST736_OFFSET 0
-# define INTC_INTREQ23_IREQUEST736_SIZE 1
-# define INTC_INTREQ23_IREQUEST737_OFFSET 1
-# define INTC_INTREQ23_IREQUEST737_SIZE 1
-# define INTC_INTREQ23_IREQUEST738_OFFSET 2
-# define INTC_INTREQ23_IREQUEST738_SIZE 1
-#define INTC_INTPR24                 0x60
-# define INTC_INTPR24_INTLEV_OFFSET  30
-# define INTC_INTPR24_INTLEV_SIZE    2
-# define INTC_INTPR24_OFFSET_OFFSET  0
-# define INTC_INTPR24_OFFSET_SIZE    24
-#define INTC_INTREQ24                0x160
-# define INTC_INTREQ24_IREQUEST768_OFFSET 0
-# define INTC_INTREQ24_IREQUEST768_SIZE 1
-#define INTC_INTPR25                 0x64
-# define INTC_INTPR25_INTLEV_OFFSET  30
-# define INTC_INTPR25_INTLEV_SIZE    2
-# define INTC_INTPR25_OFFSET_OFFSET  0
-# define INTC_INTPR25_OFFSET_SIZE    24
-#define INTC_INTREQ25                0x164
-# define INTC_INTREQ25_IREQUEST800_OFFSET 0
-# define INTC_INTREQ25_IREQUEST800_SIZE 1
-#define INTC_INTPR26                 0x68
-# define INTC_INTPR26_INTLEV_OFFSET  30
-# define INTC_INTPR26_INTLEV_SIZE    2
-# define INTC_INTPR26_OFFSET_OFFSET  0
-# define INTC_INTPR26_OFFSET_SIZE    24
-#define INTC_INTREQ26                0x168
-# define INTC_INTREQ26_IREQUEST832_OFFSET 0
-# define INTC_INTREQ26_IREQUEST832_SIZE 1
-#define INTC_INTPR27                 0x6c
-# define INTC_INTPR27_INTLEV_OFFSET  30
-# define INTC_INTPR27_INTLEV_SIZE    2
-# define INTC_INTPR27_OFFSET_OFFSET  0
-# define INTC_INTPR27_OFFSET_SIZE    24
-#define INTC_INTREQ27                0x16c
-# define INTC_INTREQ27_IREQUEST864_OFFSET 0
-# define INTC_INTREQ27_IREQUEST864_SIZE 1
-#define INTC_INTPR28                 0x70
-# define INTC_INTPR28_INTLEV_OFFSET  30
-# define INTC_INTPR28_INTLEV_SIZE    2
-# define INTC_INTPR28_OFFSET_OFFSET  0
-# define INTC_INTPR28_OFFSET_SIZE    24
-#define INTC_INTREQ28                0x170
-# define INTC_INTREQ28_IREQUEST896_OFFSET 0
-# define INTC_INTREQ28_IREQUEST896_SIZE 1
-#define INTC_INTPR29                 0x74
-# define INTC_INTPR29_INTLEV_OFFSET  30
-# define INTC_INTPR29_INTLEV_SIZE    2
-# define INTC_INTPR29_OFFSET_OFFSET  0
-# define INTC_INTPR29_OFFSET_SIZE    24
-#define INTC_INTREQ29                0x174
-# define INTC_INTREQ29_IREQUEST928_OFFSET 0
-# define INTC_INTREQ29_IREQUEST928_SIZE 1
-#define INTC_INTPR30                 0x78
-# define INTC_INTPR30_INTLEV_OFFSET  30
-# define INTC_INTPR30_INTLEV_SIZE    2
-# define INTC_INTPR30_OFFSET_OFFSET  0
-# define INTC_INTPR30_OFFSET_SIZE    24
-#define INTC_INTREQ30                0x178
-# define INTC_INTREQ30_IREQUEST960_OFFSET 0
-# define INTC_INTREQ30_IREQUEST960_SIZE 1
-#define INTC_INTPR31                 0x7c
-# define INTC_INTPR31_INTLEV_OFFSET  30
-# define INTC_INTPR31_INTLEV_SIZE    2
-# define INTC_INTPR31_OFFSET_OFFSET  0
-# define INTC_INTPR31_OFFSET_SIZE    24
-#define INTC_INTREQ31                0x17c
-# define INTC_INTREQ31_IREQUEST992_OFFSET 0
-# define INTC_INTREQ31_IREQUEST992_SIZE 1
-#define INTC_INTPR32                 0x80
-# define INTC_INTPR32_INTLEV_OFFSET  30
-# define INTC_INTPR32_INTLEV_SIZE    2
-# define INTC_INTPR32_OFFSET_OFFSET  0
-# define INTC_INTPR32_OFFSET_SIZE    24
-#define INTC_INTREQ32                0x180
-# define INTC_INTREQ32_IREQUEST1024_OFFSET 0
-# define INTC_INTREQ32_IREQUEST1024_SIZE 1
-#define INTC_INTCAUSE0               0x20c
-# define INTC_INTCAUSE0_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE0_CAUSEGRP_SIZE 6
-#define INTC_INTCAUSE1               0x208
-# define INTC_INTCAUSE1_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE1_CAUSEGRP_SIZE 6
-#define INTC_INTCAUSE2               0x204
-# define INTC_INTCAUSE2_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE2_CAUSEGRP_SIZE 6
-#define INTC_INTCAUSE3               0x200
-# define INTC_INTCAUSE3_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE3_CAUSEGRP_SIZE 6
-
-#define INTC_BIT(name)               (1 << INTC_##name##_OFFSET)
-#define INTC_MKBF(name, value)       (((value) & ((1 << INTC_##name##_SIZE) - 1)) << INTC_##name##_OFFSET)
-#define INTC_GETBF(name, value)      (((value) >> INTC_##name##_OFFSET) & ((1 << INTC_##name##_SIZE) - 1))
-
-#define intc_readl(port,reg)					\
-	__raw_readl((port)->regs + INTC_##reg)
-#define intc_writel(port,reg,value)				\
-	__raw_writel((value), (port)->regs + INTC_##reg)
-
-#endif /* __ASM_AVR32_PERIHP_INTC_H__ */
diff --git a/arch/avr32/mach-at32ap/pdc.c b/arch/avr32/mach-at32ap/pdc.c
deleted file mode 100644
index 61ab15aae970..000000000000
--- a/arch/avr32/mach-at32ap/pdc.c
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-
-static int __init pdc_probe(struct platform_device *pdev)
-{
-	struct clk *pclk, *hclk;
-
-	pclk = clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(pclk)) {
-		dev_err(&pdev->dev, "no pclk defined\n");
-		return PTR_ERR(pclk);
-	}
-	hclk = clk_get(&pdev->dev, "hclk");
-	if (IS_ERR(hclk)) {
-		dev_err(&pdev->dev, "no hclk defined\n");
-		clk_put(pclk);
-		return PTR_ERR(hclk);
-	}
-
-	clk_enable(pclk);
-	clk_enable(hclk);
-
-	dev_info(&pdev->dev, "Atmel Peripheral DMA Controller enabled\n");
-	return 0;
-}
-
-static struct platform_driver pdc_driver = {
-	.driver		= {
-		.name	= "pdc",
-	},
-};
-
-static int __init pdc_init(void)
-{
-	return platform_driver_probe(&pdc_driver, pdc_probe);
-}
-arch_initcall(pdc_init);
diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c
deleted file mode 100644
index 7fae6ec7e8ec..000000000000
--- a/arch/avr32/mach-at32ap/pio.c
+++ /dev/null
@@ -1,470 +0,0 @@
-/*
- * Atmel PIO2 Port Multiplexer support
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/debugfs.h>
-#include <linux/export.h>
-#include <linux/fs.h>
-#include <linux/platform_device.h>
-#include <linux/irq.h>
-#include <linux/gpio.h>
-
-#include <asm/io.h>
-
-#include <mach/portmux.h>
-
-#include "pio.h"
-
-#define MAX_NR_PIO_DEVICES		8
-
-struct pio_device {
-	struct gpio_chip chip;
-	void __iomem *regs;
-	const struct platform_device *pdev;
-	struct clk *clk;
-	u32 pinmux_mask;
-	char name[8];
-};
-
-static struct pio_device pio_dev[MAX_NR_PIO_DEVICES];
-
-static struct pio_device *gpio_to_pio(unsigned int gpio)
-{
-	struct pio_device *pio;
-	unsigned int index;
-
-	index = gpio >> 5;
-	if (index >= MAX_NR_PIO_DEVICES)
-		return NULL;
-	pio = &pio_dev[index];
-	if (!pio->regs)
-		return NULL;
-
-	return pio;
-}
-
-/* Pin multiplexing API */
-static DEFINE_SPINLOCK(pio_lock);
-
-void __init at32_select_periph(unsigned int port, u32 pin_mask,
-			       unsigned int periph, unsigned long flags)
-{
-	struct pio_device *pio;
-
-	/* assign and verify pio */
-	pio = gpio_to_pio(port);
-	if (unlikely(!pio)) {
-		printk(KERN_WARNING "pio: invalid port %u\n", port);
-		goto fail;
-	}
-
-	/* Test if any of the requested pins is already muxed */
-	spin_lock(&pio_lock);
-	if (unlikely(pio->pinmux_mask & pin_mask)) {
-		printk(KERN_WARNING "%s: pin(s) busy (requested 0x%x, busy 0x%x)\n",
-		       pio->name, pin_mask, pio->pinmux_mask & pin_mask);
-		spin_unlock(&pio_lock);
-		goto fail;
-	}
-
-	pio->pinmux_mask |= pin_mask;
-
-	/* enable pull ups */
-	pio_writel(pio, PUER, pin_mask);
-
-	/* select either peripheral A or B */
-	if (periph)
-		pio_writel(pio, BSR, pin_mask);
-	else
-		pio_writel(pio, ASR, pin_mask);
-
-	/* enable peripheral control */
-	pio_writel(pio, PDR, pin_mask);
-
-	/* Disable pull ups if not requested. */
-	if (!(flags & AT32_GPIOF_PULLUP))
-		pio_writel(pio, PUDR, pin_mask);
-
-	spin_unlock(&pio_lock);
-
-	return;
-
-fail:
-	dump_stack();
-}
-
-void __init at32_select_gpio(unsigned int pin, unsigned long flags)
-{
-	struct pio_device *pio;
-	unsigned int pin_index = pin & 0x1f;
-	u32 mask = 1 << pin_index;
-
-	pio = gpio_to_pio(pin);
-	if (unlikely(!pio)) {
-		printk("pio: invalid pin %u\n", pin);
-		goto fail;
-	}
-
-	if (unlikely(test_and_set_bit(pin_index, &pio->pinmux_mask))) {
-		printk("%s: pin %u is busy\n", pio->name, pin_index);
-		goto fail;
-	}
-
-	if (flags & AT32_GPIOF_OUTPUT) {
-		if (flags & AT32_GPIOF_HIGH)
-			pio_writel(pio, SODR, mask);
-		else
-			pio_writel(pio, CODR, mask);
-		if (flags & AT32_GPIOF_MULTIDRV)
-			pio_writel(pio, MDER, mask);
-		else
-			pio_writel(pio, MDDR, mask);
-		pio_writel(pio, PUDR, mask);
-		pio_writel(pio, OER, mask);
-	} else {
-		if (flags & AT32_GPIOF_PULLUP)
-			pio_writel(pio, PUER, mask);
-		else
-			pio_writel(pio, PUDR, mask);
-		if (flags & AT32_GPIOF_DEGLITCH)
-			pio_writel(pio, IFER, mask);
-		else
-			pio_writel(pio, IFDR, mask);
-		pio_writel(pio, ODR, mask);
-	}
-
-	pio_writel(pio, PER, mask);
-
-	return;
-
-fail:
-	dump_stack();
-}
-
-/*
- * Undo a previous pin reservation. Will not affect the hardware
- * configuration.
- */
-void at32_deselect_pin(unsigned int pin)
-{
-	struct pio_device *pio;
-	unsigned int pin_index = pin & 0x1f;
-
-	pio = gpio_to_pio(pin);
-	if (unlikely(!pio)) {
-		printk("pio: invalid pin %u\n", pin);
-		dump_stack();
-		return;
-	}
-
-	clear_bit(pin_index, &pio->pinmux_mask);
-}
-
-/* Reserve a pin, preventing anyone else from changing its configuration. */
-void __init at32_reserve_pin(unsigned int port, u32 pin_mask)
-{
-	struct pio_device *pio;
-
-	/* assign and verify pio */
-	pio = gpio_to_pio(port);
-	if (unlikely(!pio)) {
-		printk(KERN_WARNING "pio: invalid port %u\n", port);
-		goto fail;
-	}
-
-	/* Test if any of the requested pins is already muxed */
-	spin_lock(&pio_lock);
-	if (unlikely(pio->pinmux_mask & pin_mask)) {
-		printk(KERN_WARNING "%s: pin(s) busy (req. 0x%x, busy 0x%x)\n",
-		       pio->name, pin_mask, pio->pinmux_mask & pin_mask);
-		spin_unlock(&pio_lock);
-		goto fail;
-	}
-
-	/* Reserve pins */
-	pio->pinmux_mask |= pin_mask;
-	spin_unlock(&pio_lock);
-	return;
-
-fail:
-	dump_stack();
-}
-
-/*--------------------------------------------------------------------------*/
-
-/* GPIO API */
-
-static int direction_input(struct gpio_chip *chip, unsigned offset)
-{
-	struct pio_device *pio = gpiochip_get_data(chip);
-	u32 mask = 1 << offset;
-
-	if (!(pio_readl(pio, PSR) & mask))
-		return -EINVAL;
-
-	pio_writel(pio, ODR, mask);
-	return 0;
-}
-
-static int gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	struct pio_device *pio = gpiochip_get_data(chip);
-
-	return (pio_readl(pio, PDSR) >> offset) & 1;
-}
-
-static void gpio_set(struct gpio_chip *chip, unsigned offset, int value);
-
-static int direction_output(struct gpio_chip *chip, unsigned offset, int value)
-{
-	struct pio_device *pio = gpiochip_get_data(chip);
-	u32 mask = 1 << offset;
-
-	if (!(pio_readl(pio, PSR) & mask))
-		return -EINVAL;
-
-	gpio_set(chip, offset, value);
-	pio_writel(pio, OER, mask);
-	return 0;
-}
-
-static void gpio_set(struct gpio_chip *chip, unsigned offset, int value)
-{
-	struct pio_device *pio = gpiochip_get_data(chip);
-	u32 mask = 1 << offset;
-
-	if (value)
-		pio_writel(pio, SODR, mask);
-	else
-		pio_writel(pio, CODR, mask);
-}
-
-/*--------------------------------------------------------------------------*/
-
-/* GPIO IRQ support */
-
-static void gpio_irq_mask(struct irq_data *d)
-{
-	unsigned		gpio = irq_to_gpio(d->irq);
-	struct pio_device	*pio = &pio_dev[gpio >> 5];
-
-	pio_writel(pio, IDR, 1 << (gpio & 0x1f));
-}
-
-static void gpio_irq_unmask(struct irq_data *d)
-{
-	unsigned		gpio = irq_to_gpio(d->irq);
-	struct pio_device	*pio = &pio_dev[gpio >> 5];
-
-	pio_writel(pio, IER, 1 << (gpio & 0x1f));
-}
-
-static int gpio_irq_type(struct irq_data *d, unsigned type)
-{
-	if (type != IRQ_TYPE_EDGE_BOTH && type != IRQ_TYPE_NONE)
-		return -EINVAL;
-
-	return 0;
-}
-
-static struct irq_chip gpio_irqchip = {
-	.name		= "gpio",
-	.irq_mask	= gpio_irq_mask,
-	.irq_unmask	= gpio_irq_unmask,
-	.irq_set_type	= gpio_irq_type,
-};
-
-static void gpio_irq_handler(struct irq_desc *desc)
-{
-	struct pio_device	*pio = irq_desc_get_chip_data(desc);
-	unsigned		gpio_irq;
-
-	gpio_irq = (unsigned) irq_desc_get_handler_data(desc);
-	for (;;) {
-		u32		isr;
-
-		/* ack pending GPIO interrupts */
-		isr = pio_readl(pio, ISR) & pio_readl(pio, IMR);
-		if (!isr)
-			break;
-		do {
-			int i;
-
-			i = ffs(isr) - 1;
-			isr &= ~(1 << i);
-
-			i += gpio_irq;
-			generic_handle_irq(i);
-		} while (isr);
-	}
-}
-
-static void __init
-gpio_irq_setup(struct pio_device *pio, int irq, int gpio_irq)
-{
-	unsigned	i;
-
-	irq_set_chip_data(irq, pio);
-
-	for (i = 0; i < 32; i++, gpio_irq++) {
-		irq_set_chip_data(gpio_irq, pio);
-		irq_set_chip_and_handler(gpio_irq, &gpio_irqchip,
-					 handle_simple_irq);
-	}
-
-	irq_set_chained_handler_and_data(irq, gpio_irq_handler,
-					 (void *)gpio_irq);
-}
-
-/*--------------------------------------------------------------------------*/
-
-#ifdef CONFIG_DEBUG_FS
-
-#include <linux/seq_file.h>
-
-/*
- * This shows more info than the generic gpio dump code:
- * pullups, deglitching, open drain drive.
- */
-static void pio_bank_show(struct seq_file *s, struct gpio_chip *chip)
-{
-	struct pio_device *pio = gpiochip_get_data(chip);
-	u32			psr, osr, imr, pdsr, pusr, ifsr, mdsr;
-	unsigned		i;
-	u32			mask;
-	char			bank;
-
-	psr = pio_readl(pio, PSR);
-	osr = pio_readl(pio, OSR);
-	imr = pio_readl(pio, IMR);
-	pdsr = pio_readl(pio, PDSR);
-	pusr = pio_readl(pio, PUSR);
-	ifsr = pio_readl(pio, IFSR);
-	mdsr = pio_readl(pio, MDSR);
-
-	bank = 'A' + pio->pdev->id;
-
-	for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
-		const char *label;
-
-		label = gpiochip_is_requested(chip, i);
-		if (!label && (imr & mask))
-			label = "[irq]";
-		if (!label)
-			continue;
-
-		seq_printf(s, " gpio-%-3d P%c%-2d (%-12s) %s %s %s",
-			chip->base + i, bank, i,
-			label,
-			(osr & mask) ? "out" : "in ",
-			(mask & pdsr) ? "hi" : "lo",
-			(mask & pusr) ? "  " : "up");
-		if (ifsr & mask)
-			seq_puts(s, " deglitch");
-		if ((osr & mdsr) & mask)
-			seq_puts(s, " open-drain");
-		if (imr & mask)
-			seq_printf(s, " irq-%d edge-both",
-				gpio_to_irq(chip->base + i));
-		seq_putc(s, '\n');
-	}
-}
-
-#else
-#define pio_bank_show	NULL
-#endif
-
-
-/*--------------------------------------------------------------------------*/
-
-static int __init pio_probe(struct platform_device *pdev)
-{
-	struct pio_device *pio = NULL;
-	int irq = platform_get_irq(pdev, 0);
-	int gpio_irq_base = GPIO_IRQ_BASE + pdev->id * 32;
-
-	BUG_ON(pdev->id >= MAX_NR_PIO_DEVICES);
-	pio = &pio_dev[pdev->id];
-	BUG_ON(!pio->regs);
-
-	pio->chip.label = pio->name;
-	pio->chip.base = pdev->id * 32;
-	pio->chip.ngpio = 32;
-	pio->chip.parent = &pdev->dev;
-	pio->chip.owner = THIS_MODULE;
-
-	pio->chip.direction_input = direction_input;
-	pio->chip.get = gpio_get;
-	pio->chip.direction_output = direction_output;
-	pio->chip.set = gpio_set;
-	pio->chip.dbg_show = pio_bank_show;
-
-	gpiochip_add_data(&pio->chip, pio);
-
-	gpio_irq_setup(pio, irq, gpio_irq_base);
-
-	platform_set_drvdata(pdev, pio);
-
-	printk(KERN_DEBUG "%s: base 0x%p, irq %d chains %d..%d\n",
-	       pio->name, pio->regs, irq, gpio_irq_base, gpio_irq_base + 31);
-
-	return 0;
-}
-
-static struct platform_driver pio_driver = {
-	.driver		= {
-		.name		= "pio",
-	},
-};
-
-static int __init pio_init(void)
-{
-	return platform_driver_probe(&pio_driver, pio_probe);
-}
-postcore_initcall(pio_init);
-
-void __init at32_init_pio(struct platform_device *pdev)
-{
-	struct resource *regs;
-	struct pio_device *pio;
-
-	if (pdev->id >= MAX_NR_PIO_DEVICES) {
-		dev_err(&pdev->dev, "only %d PIO devices supported\n",
-			MAX_NR_PIO_DEVICES);
-		return;
-	}
-
-	pio = &pio_dev[pdev->id];
-	snprintf(pio->name, sizeof(pio->name), "pio%d", pdev->id);
-
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!regs) {
-		dev_err(&pdev->dev, "no mmio resource defined\n");
-		return;
-	}
-
-	pio->clk = clk_get(&pdev->dev, "mck");
-	if (IS_ERR(pio->clk))
-		/*
-		 * This is a fatal error, but if we continue we might
-		 * be so lucky that we manage to initialize the
-		 * console and display this message...
-		 */
-		dev_err(&pdev->dev, "no mck clock defined\n");
-	else
-		clk_enable(pio->clk);
-
-	pio->pdev = pdev;
-	pio->regs = ioremap(regs->start, resource_size(regs));
-
-	/* start with irqs disabled and acked */
-	pio_writel(pio, IDR, ~0UL);
-	(void) pio_readl(pio, ISR);
-}
diff --git a/arch/avr32/mach-at32ap/pio.h b/arch/avr32/mach-at32ap/pio.h
deleted file mode 100644
index 9484dfcc08f2..000000000000
--- a/arch/avr32/mach-at32ap/pio.h
+++ /dev/null
@@ -1,180 +0,0 @@
-/*
- * Atmel PIO2 Port Multiplexer support
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AVR32_AT32AP_PIO_H__
-#define __ARCH_AVR32_AT32AP_PIO_H__
-
-/* PIO register offsets */
-#define PIO_PER                                0x0000
-#define PIO_PDR                                0x0004
-#define PIO_PSR                                0x0008
-#define PIO_OER                                0x0010
-#define PIO_ODR                                0x0014
-#define PIO_OSR                                0x0018
-#define PIO_IFER                               0x0020
-#define PIO_IFDR                               0x0024
-#define PIO_IFSR                               0x0028
-#define PIO_SODR                               0x0030
-#define PIO_CODR                               0x0034
-#define PIO_ODSR                               0x0038
-#define PIO_PDSR                               0x003c
-#define PIO_IER                                0x0040
-#define PIO_IDR                                0x0044
-#define PIO_IMR                                0x0048
-#define PIO_ISR                                0x004c
-#define PIO_MDER                               0x0050
-#define PIO_MDDR                               0x0054
-#define PIO_MDSR                               0x0058
-#define PIO_PUDR                               0x0060
-#define PIO_PUER                               0x0064
-#define PIO_PUSR                               0x0068
-#define PIO_ASR                                0x0070
-#define PIO_BSR                                0x0074
-#define PIO_ABSR                               0x0078
-#define PIO_OWER                               0x00a0
-#define PIO_OWDR                               0x00a4
-#define PIO_OWSR                               0x00a8
-
-/* Bitfields in PER */
-
-/* Bitfields in PDR */
-
-/* Bitfields in PSR */
-
-/* Bitfields in OER */
-
-/* Bitfields in ODR */
-
-/* Bitfields in OSR */
-
-/* Bitfields in IFER */
-
-/* Bitfields in IFDR */
-
-/* Bitfields in IFSR */
-
-/* Bitfields in SODR */
-
-/* Bitfields in CODR */
-
-/* Bitfields in ODSR */
-
-/* Bitfields in PDSR */
-
-/* Bitfields in IER */
-
-/* Bitfields in IDR */
-
-/* Bitfields in IMR */
-
-/* Bitfields in ISR */
-
-/* Bitfields in MDER */
-
-/* Bitfields in MDDR */
-
-/* Bitfields in MDSR */
-
-/* Bitfields in PUDR */
-
-/* Bitfields in PUER */
-
-/* Bitfields in PUSR */
-
-/* Bitfields in ASR */
-
-/* Bitfields in BSR */
-
-/* Bitfields in ABSR */
-#define PIO_P0_OFFSET                          0
-#define PIO_P0_SIZE                            1
-#define PIO_P1_OFFSET                          1
-#define PIO_P1_SIZE                            1
-#define PIO_P2_OFFSET                          2
-#define PIO_P2_SIZE                            1
-#define PIO_P3_OFFSET                          3
-#define PIO_P3_SIZE                            1
-#define PIO_P4_OFFSET                          4
-#define PIO_P4_SIZE                            1
-#define PIO_P5_OFFSET                          5
-#define PIO_P5_SIZE                            1
-#define PIO_P6_OFFSET                          6
-#define PIO_P6_SIZE                            1
-#define PIO_P7_OFFSET                          7
-#define PIO_P7_SIZE                            1
-#define PIO_P8_OFFSET                          8
-#define PIO_P8_SIZE                            1
-#define PIO_P9_OFFSET                          9
-#define PIO_P9_SIZE                            1
-#define PIO_P10_OFFSET                         10
-#define PIO_P10_SIZE                           1
-#define PIO_P11_OFFSET                         11
-#define PIO_P11_SIZE                           1
-#define PIO_P12_OFFSET                         12
-#define PIO_P12_SIZE                           1
-#define PIO_P13_OFFSET                         13
-#define PIO_P13_SIZE                           1
-#define PIO_P14_OFFSET                         14
-#define PIO_P14_SIZE                           1
-#define PIO_P15_OFFSET                         15
-#define PIO_P15_SIZE                           1
-#define PIO_P16_OFFSET                         16
-#define PIO_P16_SIZE                           1
-#define PIO_P17_OFFSET                         17
-#define PIO_P17_SIZE                           1
-#define PIO_P18_OFFSET                         18
-#define PIO_P18_SIZE                           1
-#define PIO_P19_OFFSET                         19
-#define PIO_P19_SIZE                           1
-#define PIO_P20_OFFSET                         20
-#define PIO_P20_SIZE                           1
-#define PIO_P21_OFFSET                         21
-#define PIO_P21_SIZE                           1
-#define PIO_P22_OFFSET                         22
-#define PIO_P22_SIZE                           1
-#define PIO_P23_OFFSET                         23
-#define PIO_P23_SIZE                           1
-#define PIO_P24_OFFSET                         24
-#define PIO_P24_SIZE                           1
-#define PIO_P25_OFFSET                         25
-#define PIO_P25_SIZE                           1
-#define PIO_P26_OFFSET                         26
-#define PIO_P26_SIZE                           1
-#define PIO_P27_OFFSET                         27
-#define PIO_P27_SIZE                           1
-#define PIO_P28_OFFSET                         28
-#define PIO_P28_SIZE                           1
-#define PIO_P29_OFFSET                         29
-#define PIO_P29_SIZE                           1
-#define PIO_P30_OFFSET                         30
-#define PIO_P30_SIZE                           1
-#define PIO_P31_OFFSET                         31
-#define PIO_P31_SIZE                           1
-
-/* Bitfields in OWER */
-
-/* Bitfields in OWDR */
-
-/* Bitfields in OWSR */
-
-/* Bit manipulation macros */
-#define PIO_BIT(name)                          (1 << PIO_##name##_OFFSET)
-#define PIO_BF(name,value)                     (((value) & ((1 << PIO_##name##_SIZE) - 1)) << PIO_##name##_OFFSET)
-#define PIO_BFEXT(name,value)                  (((value) >> PIO_##name##_OFFSET) & ((1 << PIO_##name##_SIZE) - 1))
-#define PIO_BFINS(name,value,old)              (((old) & ~(((1 << PIO_##name##_SIZE) - 1) << PIO_##name##_OFFSET)) | PIO_BF(name,value))
-
-/* Register access macros */
-#define pio_readl(port,reg)					\
-	__raw_readl((port)->regs + PIO_##reg)
-#define pio_writel(port,reg,value)				\
-	__raw_writel((value), (port)->regs + PIO_##reg)
-
-void at32_init_pio(struct platform_device *pdev);
-
-#endif /* __ARCH_AVR32_AT32AP_PIO_H__ */
diff --git a/arch/avr32/mach-at32ap/pm-at32ap700x.S b/arch/avr32/mach-at32ap/pm-at32ap700x.S
deleted file mode 100644
index 1c8e4e6bff03..000000000000
--- a/arch/avr32/mach-at32ap/pm-at32ap700x.S
+++ /dev/null
@@ -1,167 +0,0 @@
-/*
- * Low-level Power Management code.
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <mach/pm.h>
-
-#include "pm.h"
-#include "sdramc.h"
-
-/* Same as 0xfff00000 but fits in a 21 bit signed immediate */
-#define PM_BASE	-0x100000
-
-	/* Keep this close to the irq handlers */
-	.section .irq.text, "ax", @progbits
-
-	/*
-	 * void cpu_enter_idle(void)
-	 *
-	 * Put the CPU into "idle" mode, in which it will consume
-	 * significantly less power.
-	 *
-	 * If an interrupt comes along in the window between
-	 * unmask_interrupts and the sleep instruction below, the
-	 * interrupt code will adjust the return address so that we
-	 * never execute the sleep instruction. This is required
-	 * because the AP7000 doesn't unmask interrupts when entering
-	 * sleep modes; later CPUs may not need this workaround.
-	 */
-	.global	cpu_enter_idle
-	.type	cpu_enter_idle, @function
-cpu_enter_idle:
-	mask_interrupts
-	get_thread_info r8
-	ld.w	r9, r8[TI_flags]
-	bld	r9, TIF_NEED_RESCHED
-	brcs	.Lret_from_sleep
-	sbr	r9, TIF_CPU_GOING_TO_SLEEP
-	st.w	r8[TI_flags], r9
-	unmask_interrupts
-	sleep	CPU_SLEEP_IDLE
-	.size	cpu_enter_idle, . - cpu_enter_idle
-
-	/*
-	 * Common return path for PM functions that don't run from
-	 * SRAM.
-	 */
-	.global cpu_idle_skip_sleep
-	.type	cpu_idle_skip_sleep, @function
-cpu_idle_skip_sleep:
-	mask_interrupts
-	ld.w	r9, r8[TI_flags]
-	cbr	r9, TIF_CPU_GOING_TO_SLEEP
-	st.w	r8[TI_flags], r9
-.Lret_from_sleep:
-	unmask_interrupts
-	retal	r12
-	.size	cpu_idle_skip_sleep, . - cpu_idle_skip_sleep
-
-#ifdef CONFIG_PM
-	.section .init.text, "ax", @progbits
-
-	.global	pm_exception
-	.type	pm_exception, @function
-pm_exception:
-	/*
-	 * Exceptions are masked when we switch to this handler, so
-	 * we'll only get "unrecoverable" exceptions (offset 0.)
-	 */
-	sub	r12, pc, . - .Lpanic_msg
-	lddpc	pc, .Lpanic_addr
-
-	.align	2
-.Lpanic_addr:
-	.long	panic
-.Lpanic_msg:
-	.asciz	"Unrecoverable exception during suspend\n"
-	.size	pm_exception, . - pm_exception
-
-	.global	pm_irq0
-	.type	pm_irq0, @function
-pm_irq0:
-	/* Disable interrupts and return after the sleep instruction */
-	mfsr	r9, SYSREG_RSR_INT0
-	mtsr	SYSREG_RAR_INT0, r8
-	sbr	r9, SYSREG_GM_OFFSET
-	mtsr	SYSREG_RSR_INT0, r9
-	rete
-
-	/*
-	 * void cpu_enter_standby(unsigned long sdramc_base)
-	 *
-	 * Enter PM_SUSPEND_STANDBY mode. At this point, all drivers
-	 * are suspended and interrupts are disabled. Interrupts
-	 * marked as 'wakeup' event sources may still come along and
-	 * get us out of here.
-	 *
-	 * The SDRAM will be put into self-refresh mode (which does
-	 * not require a clock from the CPU), and the CPU will be put
-	 * into "frozen" mode (HSB bus stopped). The SDRAM controller
-	 * will automatically bring the SDRAM into normal mode on the
-	 * first access, and the power manager will automatically
-	 * start the HSB and CPU clocks upon a wakeup event.
-	 *
-	 * This code uses the same "skip sleep" technique as above.
-	 * It is very important that we jump directly to
-	 * cpu_after_sleep after the sleep instruction since that's
-	 * where we'll end up if the interrupt handler decides that we
-	 * need to skip the sleep instruction.
-	 */
-	.global	pm_standby
-	.type	pm_standby, @function
-pm_standby:
-	/*
-	 * interrupts are already masked at this point, and EVBA
-	 * points to pm_exception above.
-	 */
-	ld.w	r10, r12[SDRAMC_LPR]
-	sub	r8, pc, . - 1f		/* return address for irq handler */
-	mov	r11, SDRAMC_LPR_LPCB_SELF_RFR
-	bfins	r10, r11, 0, 2		/* LPCB <- self Refresh */
-	sync	0			/* flush write buffer */
-	st.w	r12[SDRAMC_LPR], r10	/* put SDRAM in self-refresh mode */
-	ld.w	r11, r12[SDRAMC_LPR]
-	unmask_interrupts
-	sleep	CPU_SLEEP_FROZEN
-1:	mask_interrupts
-	retal	r12
-	.size	pm_standby, . - pm_standby
-
-	.global	pm_suspend_to_ram
-	.type	pm_suspend_to_ram, @function
-pm_suspend_to_ram:
-	/*
-	 * interrupts are already masked at this point, and EVBA
-	 * points to pm_exception above.
-	 */
-	mov	r11, 0
-	cache	r11[2], 8		/* clean all dcache lines */
-	sync	0			/* flush write buffer */
-	ld.w	r10, r12[SDRAMC_LPR]
-	sub	r8, pc, . - 1f		/* return address for irq handler */
-	mov	r11, SDRAMC_LPR_LPCB_SELF_RFR
-	bfins	r10, r11, 0, 2		/* LPCB <- self refresh */
-	st.w	r12[SDRAMC_LPR], r10	/* put SDRAM in self-refresh mode */
-	ld.w	r11, r12[SDRAMC_LPR]
-
-	unmask_interrupts
-	sleep	CPU_SLEEP_STOP
-1:	mask_interrupts
-
-	retal	r12
-	.size	pm_suspend_to_ram, . - pm_suspend_to_ram
-
-	.global	pm_sram_end
-	.type	pm_sram_end, @function
-pm_sram_end:
-	.size	pm_sram_end, 0
-
-#endif /* CONFIG_PM */
diff --git a/arch/avr32/mach-at32ap/pm.c b/arch/avr32/mach-at32ap/pm.c
deleted file mode 100644
index db190842b80c..000000000000
--- a/arch/avr32/mach-at32ap/pm.c
+++ /dev/null
@@ -1,243 +0,0 @@
-/*
- * AVR32 AP Power Management
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- */
-#include <linux/io.h>
-#include <linux/suspend.h>
-#include <linux/vmalloc.h>
-
-#include <asm/cacheflush.h>
-#include <asm/sysreg.h>
-
-#include <mach/chip.h>
-#include <mach/pm.h>
-#include <mach/sram.h>
-
-#include "sdramc.h"
-
-#define SRAM_PAGE_FLAGS	(SYSREG_BIT(TLBELO_D) | SYSREG_BF(SZ, 1)	\
-				| SYSREG_BF(AP, 3) | SYSREG_BIT(G))
-
-
-static unsigned long	pm_sram_start;
-static size_t		pm_sram_size;
-static struct vm_struct	*pm_sram_area;
-
-static void (*avr32_pm_enter_standby)(unsigned long sdramc_base);
-static void (*avr32_pm_enter_str)(unsigned long sdramc_base);
-
-/*
- * Must be called with interrupts disabled. Exceptions will be masked
- * on return (i.e. all exceptions will be "unrecoverable".)
- */
-static void *avr32_pm_map_sram(void)
-{
-	unsigned long	vaddr;
-	unsigned long	page_addr;
-	u32		tlbehi;
-	u32		mmucr;
-
-	vaddr = (unsigned long)pm_sram_area->addr;
-	page_addr = pm_sram_start & PAGE_MASK;
-
-	/*
-	 * Mask exceptions and grab the first TLB entry. We won't be
-	 * needing it while sleeping.
-	 */
-	asm volatile("ssrf	%0" : : "i"(SYSREG_EM_OFFSET) : "memory");
-
-	mmucr = sysreg_read(MMUCR);
-	tlbehi = sysreg_read(TLBEHI);
-	sysreg_write(MMUCR, SYSREG_BFINS(DRP, 0, mmucr));
-
-	tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
-	tlbehi |= vaddr & PAGE_MASK;
-	tlbehi |= SYSREG_BIT(TLBEHI_V);
-
-	sysreg_write(TLBELO, page_addr | SRAM_PAGE_FLAGS);
-	sysreg_write(TLBEHI, tlbehi);
-	__builtin_tlbw();
-
-	return (void *)(vaddr + pm_sram_start - page_addr);
-}
-
-/*
- * Must be called with interrupts disabled. Exceptions will be
- * unmasked on return.
- */
-static void avr32_pm_unmap_sram(void)
-{
-	u32	mmucr;
-	u32	tlbehi;
-	u32	tlbarlo;
-
-	/* Going to update TLB entry at index 0 */
-	mmucr = sysreg_read(MMUCR);
-	tlbehi = sysreg_read(TLBEHI);
-	sysreg_write(MMUCR, SYSREG_BFINS(DRP, 0, mmucr));
-
-	/* Clear the "valid" bit */
-	tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
-	sysreg_write(TLBEHI, tlbehi);
-
-	/* Mark it as "not accessed" */
-	tlbarlo = sysreg_read(TLBARLO);
-	sysreg_write(TLBARLO, tlbarlo | 0x80000000U);
-
-	/* Update the TLB */
-	__builtin_tlbw();
-
-	/* Unmask exceptions */
-	asm volatile("csrf	%0" : : "i"(SYSREG_EM_OFFSET) : "memory");
-}
-
-static int avr32_pm_valid_state(suspend_state_t state)
-{
-	switch (state) {
-	case PM_SUSPEND_ON:
-	case PM_SUSPEND_STANDBY:
-	case PM_SUSPEND_MEM:
-		return 1;
-
-	default:
-		return 0;
-	}
-}
-
-static int avr32_pm_enter(suspend_state_t state)
-{
-	u32		lpr_saved;
-	u32		evba_saved;
-	void		*sram;
-
-	switch (state) {
-	case PM_SUSPEND_STANDBY:
-		sram = avr32_pm_map_sram();
-
-		/* Switch to in-sram exception handlers */
-		evba_saved = sysreg_read(EVBA);
-		sysreg_write(EVBA, (unsigned long)sram);
-
-		/*
-		 * Save the LPR register so that we can re-enable
-		 * SDRAM Low Power mode on resume.
-		 */
-		lpr_saved = sdramc_readl(LPR);
-		pr_debug("%s: Entering standby...\n", __func__);
-		avr32_pm_enter_standby(SDRAMC_BASE);
-		sdramc_writel(LPR, lpr_saved);
-
-		/* Switch back to regular exception handlers */
-		sysreg_write(EVBA, evba_saved);
-
-		avr32_pm_unmap_sram();
-		break;
-
-	case PM_SUSPEND_MEM:
-		sram = avr32_pm_map_sram();
-
-		/* Switch to in-sram exception handlers */
-		evba_saved = sysreg_read(EVBA);
-		sysreg_write(EVBA, (unsigned long)sram);
-
-		/*
-		 * Save the LPR register so that we can re-enable
-		 * SDRAM Low Power mode on resume.
-		 */
-		lpr_saved = sdramc_readl(LPR);
-		pr_debug("%s: Entering suspend-to-ram...\n", __func__);
-		avr32_pm_enter_str(SDRAMC_BASE);
-		sdramc_writel(LPR, lpr_saved);
-
-		/* Switch back to regular exception handlers */
-		sysreg_write(EVBA, evba_saved);
-
-		avr32_pm_unmap_sram();
-		break;
-
-	case PM_SUSPEND_ON:
-		pr_debug("%s: Entering idle...\n", __func__);
-		cpu_enter_idle();
-		break;
-
-	default:
-		pr_debug("%s: Invalid suspend state %d\n", __func__, state);
-		goto out;
-	}
-
-	pr_debug("%s: wakeup\n", __func__);
-
-out:
-	return 0;
-}
-
-static const struct platform_suspend_ops avr32_pm_ops = {
-	.valid	= avr32_pm_valid_state,
-	.enter	= avr32_pm_enter,
-};
-
-static unsigned long __init avr32_pm_offset(void *symbol)
-{
-	extern u8 pm_exception[];
-
-	return (unsigned long)symbol - (unsigned long)pm_exception;
-}
-
-static int __init avr32_pm_init(void)
-{
-	extern u8 pm_exception[];
-	extern u8 pm_irq0[];
-	extern u8 pm_standby[];
-	extern u8 pm_suspend_to_ram[];
-	extern u8 pm_sram_end[];
-	void *dst;
-
-	/*
-	 * To keep things simple, we depend on not needing more than a
-	 * single page.
-	 */
-	pm_sram_size = avr32_pm_offset(pm_sram_end);
-	if (pm_sram_size > PAGE_SIZE)
-		goto err;
-
-	pm_sram_start = sram_alloc(pm_sram_size);
-	if (!pm_sram_start)
-		goto err_alloc_sram;
-
-	/* Grab a virtual area we can use later on. */
-	pm_sram_area = get_vm_area(pm_sram_size, VM_IOREMAP);
-	if (!pm_sram_area)
-		goto err_vm_area;
-	pm_sram_area->phys_addr = pm_sram_start;
-
-	local_irq_disable();
-	dst = avr32_pm_map_sram();
-	memcpy(dst, pm_exception, pm_sram_size);
-	flush_dcache_region(dst, pm_sram_size);
-	invalidate_icache_region(dst, pm_sram_size);
-	avr32_pm_unmap_sram();
-	local_irq_enable();
-
-	avr32_pm_enter_standby = dst + avr32_pm_offset(pm_standby);
-	avr32_pm_enter_str = dst + avr32_pm_offset(pm_suspend_to_ram);
-	intc_set_suspend_handler(avr32_pm_offset(pm_irq0));
-
-	suspend_set_ops(&avr32_pm_ops);
-
-	printk("AVR32 AP Power Management enabled\n");
-
-	return 0;
-
-err_vm_area:
-	sram_free(pm_sram_start, pm_sram_size);
-err_alloc_sram:
-err:
-	pr_err("AVR32 Power Management initialization failed\n");
-	return -ENOMEM;
-}
-arch_initcall(avr32_pm_init);
diff --git a/arch/avr32/mach-at32ap/pm.h b/arch/avr32/mach-at32ap/pm.h
deleted file mode 100644
index 532a3732c214..000000000000
--- a/arch/avr32/mach-at32ap/pm.h
+++ /dev/null
@@ -1,112 +0,0 @@
-/*
- * Register definitions for the Power Manager (PM)
- */
-#ifndef __ARCH_AVR32_MACH_AT32AP_PM_H__
-#define __ARCH_AVR32_MACH_AT32AP_PM_H__
-
-/* PM register offsets */
-#define PM_MCCTRL				0x0000
-#define PM_CKSEL				0x0004
-#define PM_CPU_MASK				0x0008
-#define PM_HSB_MASK				0x000c
-#define PM_PBA_MASK				0x0010
-#define PM_PBB_MASK				0x0014
-#define PM_PLL0					0x0020
-#define PM_PLL1					0x0024
-#define PM_IER					0x0040
-#define PM_IDR					0x0044
-#define PM_IMR					0x0048
-#define PM_ISR					0x004c
-#define PM_ICR					0x0050
-#define PM_GCCTRL(x)				(0x0060 + 4 * (x))
-#define PM_RCAUSE				0x00c0
-
-/* Bitfields in CKSEL */
-#define PM_CPUSEL_OFFSET			0
-#define PM_CPUSEL_SIZE				3
-#define PM_CPUDIV_OFFSET			7
-#define PM_CPUDIV_SIZE				1
-#define PM_HSBSEL_OFFSET			8
-#define PM_HSBSEL_SIZE				3
-#define PM_HSBDIV_OFFSET			15
-#define PM_HSBDIV_SIZE				1
-#define PM_PBASEL_OFFSET			16
-#define PM_PBASEL_SIZE				3
-#define PM_PBADIV_OFFSET			23
-#define PM_PBADIV_SIZE				1
-#define PM_PBBSEL_OFFSET			24
-#define PM_PBBSEL_SIZE				3
-#define PM_PBBDIV_OFFSET			31
-#define PM_PBBDIV_SIZE				1
-
-/* Bitfields in PLL0 */
-#define PM_PLLEN_OFFSET				0
-#define PM_PLLEN_SIZE				1
-#define PM_PLLOSC_OFFSET			1
-#define PM_PLLOSC_SIZE				1
-#define PM_PLLOPT_OFFSET			2
-#define PM_PLLOPT_SIZE				3
-#define PM_PLLDIV_OFFSET			8
-#define PM_PLLDIV_SIZE				8
-#define PM_PLLMUL_OFFSET			16
-#define PM_PLLMUL_SIZE				8
-#define PM_PLLCOUNT_OFFSET			24
-#define PM_PLLCOUNT_SIZE			6
-#define PM_PLLTEST_OFFSET			31
-#define PM_PLLTEST_SIZE				1
-
-/* Bitfields in ICR */
-#define PM_LOCK0_OFFSET				0
-#define PM_LOCK0_SIZE				1
-#define PM_LOCK1_OFFSET				1
-#define PM_LOCK1_SIZE				1
-#define PM_WAKE_OFFSET				2
-#define PM_WAKE_SIZE				1
-#define PM_CKRDY_OFFSET				5
-#define PM_CKRDY_SIZE				1
-#define PM_MSKRDY_OFFSET			6
-#define PM_MSKRDY_SIZE				1
-
-/* Bitfields in GCCTRL0 */
-#define PM_OSCSEL_OFFSET			0
-#define PM_OSCSEL_SIZE				1
-#define PM_PLLSEL_OFFSET			1
-#define PM_PLLSEL_SIZE				1
-#define PM_CEN_OFFSET				2
-#define PM_CEN_SIZE				1
-#define PM_DIVEN_OFFSET				4
-#define PM_DIVEN_SIZE				1
-#define PM_DIV_OFFSET				8
-#define PM_DIV_SIZE				8
-
-/* Bitfields in RCAUSE */
-#define PM_POR_OFFSET				0
-#define PM_POR_SIZE				1
-#define PM_EXT_OFFSET				2
-#define PM_EXT_SIZE				1
-#define PM_WDT_OFFSET				3
-#define PM_WDT_SIZE				1
-#define PM_NTAE_OFFSET				4
-#define PM_NTAE_SIZE				1
-
-/* Bit manipulation macros */
-#define PM_BIT(name)					\
-	(1 << PM_##name##_OFFSET)
-#define PM_BF(name,value)				\
-	(((value) & ((1 << PM_##name##_SIZE) - 1))	\
-	 << PM_##name##_OFFSET)
-#define PM_BFEXT(name,value)				\
-	(((value) >> PM_##name##_OFFSET)		\
-	 & ((1 << PM_##name##_SIZE) - 1))
-#define PM_BFINS(name,value,old)\
-	(((old) & ~(((1 << PM_##name##_SIZE) - 1)	\
-		    << PM_##name##_OFFSET))		\
-	 | PM_BF(name,value))
-
-/* Register access macros */
-#define pm_readl(reg)							\
-	__raw_readl((void __iomem __force *)PM_BASE + PM_##reg)
-#define pm_writel(reg,value)						\
-	__raw_writel((value), (void __iomem __force *)PM_BASE + PM_##reg)
-
-#endif /* __ARCH_AVR32_MACH_AT32AP_PM_H__ */
diff --git a/arch/avr32/mach-at32ap/sdramc.h b/arch/avr32/mach-at32ap/sdramc.h
deleted file mode 100644
index 66eeaed49073..000000000000
--- a/arch/avr32/mach-at32ap/sdramc.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Register definitions for the AT32AP SDRAM Controller
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- */
-
-/* Register offsets */
-#define SDRAMC_MR			0x0000
-#define SDRAMC_TR			0x0004
-#define SDRAMC_CR			0x0008
-#define SDRAMC_HSR			0x000c
-#define SDRAMC_LPR			0x0010
-#define SDRAMC_IER			0x0014
-#define SDRAMC_IDR			0x0018
-#define SDRAMC_IMR			0x001c
-#define SDRAMC_ISR			0x0020
-#define SDRAMC_MDR			0x0024
-
-/* MR - Mode Register */
-#define SDRAMC_MR_MODE_NORMAL		(  0 <<  0)
-#define SDRAMC_MR_MODE_NOP		(  1 <<  0)
-#define SDRAMC_MR_MODE_BANKS_PRECHARGE	(  2 <<  0)
-#define SDRAMC_MR_MODE_LOAD_MODE	(  3 <<  0)
-#define SDRAMC_MR_MODE_AUTO_REFRESH	(  4 <<  0)
-#define SDRAMC_MR_MODE_EXT_LOAD_MODE	(  5 <<  0)
-#define SDRAMC_MR_MODE_POWER_DOWN	(  6 <<  0)
-
-/* CR - Configuration Register */
-#define SDRAMC_CR_NC_8_BITS		(  0 <<  0)
-#define SDRAMC_CR_NC_9_BITS		(  1 <<  0)
-#define SDRAMC_CR_NC_10_BITS		(  2 <<  0)
-#define SDRAMC_CR_NC_11_BITS		(  3 <<  0)
-#define SDRAMC_CR_NR_11_BITS		(  0 <<  2)
-#define SDRAMC_CR_NR_12_BITS		(  1 <<  2)
-#define SDRAMC_CR_NR_13_BITS		(  2 <<  2)
-#define SDRAMC_CR_NB_2_BANKS		(  0 <<  4)
-#define SDRAMC_CR_NB_4_BANKS		(  1 <<  4)
-#define SDRAMC_CR_CAS(x)		((x) <<  5)
-#define SDRAMC_CR_DBW_32_BITS		(  0 <<  7)
-#define SDRAMC_CR_DBW_16_BITS		(  1 <<  7)
-#define SDRAMC_CR_TWR(x)		((x) <<  8)
-#define SDRAMC_CR_TRC(x)		((x) << 12)
-#define SDRAMC_CR_TRP(x)		((x) << 16)
-#define SDRAMC_CR_TRCD(x)		((x) << 20)
-#define SDRAMC_CR_TRAS(x)		((x) << 24)
-#define SDRAMC_CR_TXSR(x)		((x) << 28)
-
-/* HSR - High Speed Register */
-#define SDRAMC_HSR_DA			(  1 <<  0)
-
-/* LPR - Low Power Register */
-#define SDRAMC_LPR_LPCB_INHIBIT		(  0 <<  0)
-#define SDRAMC_LPR_LPCB_SELF_RFR	(  1 <<  0)
-#define SDRAMC_LPR_LPCB_PDOWN		(  2 <<  0)
-#define SDRAMC_LPR_LPCB_DEEP_PDOWN	(  3 <<  0)
-#define SDRAMC_LPR_PASR(x)		((x) <<  4)
-#define SDRAMC_LPR_TCSR(x)		((x) <<  8)
-#define SDRAMC_LPR_DS(x)		((x) << 10)
-#define SDRAMC_LPR_TIMEOUT(x)		((x) << 12)
-
-/* IER/IDR/IMR/ISR - Interrupt Enable/Disable/Mask/Status Register */
-#define SDRAMC_ISR_RES			(  1 <<  0)
-
-/* MDR - Memory Device Register */
-#define SDRAMC_MDR_MD_SDRAM		(  0 <<  0)
-#define SDRAMC_MDR_MD_LOW_PWR_SDRAM	(  1 <<  0)
-
-/* Register access macros */
-#define sdramc_readl(reg) \
-	__raw_readl((void __iomem __force *)SDRAMC_BASE + SDRAMC_##reg)
-#define sdramc_writel(reg, value) \
-	__raw_writel(value, (void __iomem __force *)SDRAMC_BASE + SDRAMC_##reg)
diff --git a/arch/avr32/mm/Makefile b/arch/avr32/mm/Makefile
deleted file mode 100644
index 0066491f90d4..000000000000
--- a/arch/avr32/mm/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-#
-# Makefile for the Linux/AVR32 kernel.
-#
-
-obj-y				+= init.o clear_page.o copy_page.o dma-coherent.o
-obj-y				+= ioremap.o cache.o fault.o tlb.o
diff --git a/arch/avr32/mm/cache.c b/arch/avr32/mm/cache.c
deleted file mode 100644
index d9476825fc43..000000000000
--- a/arch/avr32/mm/cache.c
+++ /dev/null
@@ -1,163 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/highmem.h>
-#include <linux/unistd.h>
-
-#include <asm/cacheflush.h>
-#include <asm/cachectl.h>
-#include <asm/processor.h>
-#include <linux/uaccess.h>
-#include <asm/syscalls.h>
-
-/*
- * If you attempt to flush anything more than this, you need superuser
- * privileges.  The value is completely arbitrary.
- */
-#define CACHEFLUSH_MAX_LEN	1024
-
-void invalidate_dcache_region(void *start, size_t size)
-{
-	unsigned long v, begin, end, linesz, mask;
-
-	linesz = boot_cpu_data.dcache.linesz;
-	mask = linesz - 1;
-
-	/* when first and/or last cachelines are shared, flush them
-	 * instead of invalidating ... never discard valid data!
-	 */
-	begin = (unsigned long)start;
-	end = begin + size;
-
-	if (begin & mask) {
-		flush_dcache_line(start);
-		begin += linesz;
-	}
-	if (end & mask) {
-		flush_dcache_line((void *)end);
-		end &= ~mask;
-	}
-
-	/* remaining cachelines only need invalidation */
-	for (v = begin; v < end; v += linesz)
-		invalidate_dcache_line((void *)v);
-	flush_write_buffer();
-}
-
-void clean_dcache_region(void *start, size_t size)
-{
-	unsigned long v, begin, end, linesz;
-
-	linesz = boot_cpu_data.dcache.linesz;
-	begin = (unsigned long)start & ~(linesz - 1);
-	end = ((unsigned long)start + size + linesz - 1) & ~(linesz - 1);
-
-	for (v = begin; v < end; v += linesz)
-		clean_dcache_line((void *)v);
-	flush_write_buffer();
-}
-
-void flush_dcache_region(void *start, size_t size)
-{
-	unsigned long v, begin, end, linesz;
-
-	linesz = boot_cpu_data.dcache.linesz;
-	begin = (unsigned long)start & ~(linesz - 1);
-	end = ((unsigned long)start + size + linesz - 1) & ~(linesz - 1);
-
-	for (v = begin; v < end; v += linesz)
-		flush_dcache_line((void *)v);
-	flush_write_buffer();
-}
-
-void invalidate_icache_region(void *start, size_t size)
-{
-	unsigned long v, begin, end, linesz;
-
-	linesz = boot_cpu_data.icache.linesz;
-	begin = (unsigned long)start & ~(linesz - 1);
-	end = ((unsigned long)start + size + linesz - 1) & ~(linesz - 1);
-
-	for (v = begin; v < end; v += linesz)
-		invalidate_icache_line((void *)v);
-}
-
-static inline void __flush_icache_range(unsigned long start, unsigned long end)
-{
-	unsigned long v, linesz;
-
-	linesz = boot_cpu_data.dcache.linesz;
-	for (v = start; v < end; v += linesz) {
-		clean_dcache_line((void *)v);
-		invalidate_icache_line((void *)v);
-	}
-
-	flush_write_buffer();
-}
-
-/*
- * This one is called after a module has been loaded.
- */
-void flush_icache_range(unsigned long start, unsigned long end)
-{
-	unsigned long linesz;
-
-	linesz = boot_cpu_data.dcache.linesz;
-	__flush_icache_range(start & ~(linesz - 1),
-			     (end + linesz - 1) & ~(linesz - 1));
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-/*
- * This one is called from __do_fault() and do_swap_page().
- */
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	if (vma->vm_flags & VM_EXEC) {
-		void *v = page_address(page);
-		__flush_icache_range((unsigned long)v, (unsigned long)v + PAGE_SIZE);
-	}
-}
-
-asmlinkage int sys_cacheflush(int operation, void __user *addr, size_t len)
-{
-	int ret;
-
-	if (len > CACHEFLUSH_MAX_LEN) {
-		ret = -EPERM;
-		if (!capable(CAP_SYS_ADMIN))
-			goto out;
-	}
-
-	ret = -EFAULT;
-	if (!access_ok(VERIFY_WRITE, addr, len))
-		goto out;
-
-	switch (operation) {
-	case CACHE_IFLUSH:
-		flush_icache_range((unsigned long)addr,
-				   (unsigned long)addr + len);
-		ret = 0;
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-out:
-	return ret;
-}
-
-void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
-		unsigned long vaddr, void *dst, const void *src,
-		unsigned long len)
-{
-	memcpy(dst, src, len);
-	if (vma->vm_flags & VM_EXEC)
-		flush_icache_range((unsigned long)dst,
-				(unsigned long)dst + len);
-}
diff --git a/arch/avr32/mm/clear_page.S b/arch/avr32/mm/clear_page.S
deleted file mode 100644
index 5d70dca00699..000000000000
--- a/arch/avr32/mm/clear_page.S
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/page.h>
-
-/*
- * clear_page
- * r12: P1 address (to)
- */
-	.text
-	.global clear_page
-clear_page:
-	sub	r9, r12, -PAGE_SIZE
-	mov     r10, 0
-	mov	r11, 0
-0:      st.d    r12++, r10
-	cp      r12, r9
-	brne	0b
-	mov     pc, lr
diff --git a/arch/avr32/mm/copy_page.S b/arch/avr32/mm/copy_page.S
deleted file mode 100644
index c2b3752946b8..000000000000
--- a/arch/avr32/mm/copy_page.S
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/page.h>
-
-/*
- * copy_page
- *
- * r12		to (P1 address)
- * r11		from (P1 address)
- * r8-r10	scratch
- */
-	.text
-	.global copy_page
-copy_page:
-	sub	r10, r11, -(1 << PAGE_SHIFT)
-	/* pref	r11[0] */
-1:	/* pref	r11[8] */
-	ld.d	r8, r11++
-	st.d	r12++, r8
-	cp	r11, r10
-	brlo	1b
-	mov	pc, lr
diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c
deleted file mode 100644
index 555222d4f414..000000000000
--- a/arch/avr32/mm/dma-coherent.c
+++ /dev/null
@@ -1,202 +0,0 @@
-/*
- *  Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/gfp.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/device.h>
-#include <linux/scatterlist.h>
-
-#include <asm/processor.h>
-#include <asm/cacheflush.h>
-#include <asm/io.h>
-#include <asm/addrspace.h>
-
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size, int direction)
-{
-	/*
-	 * No need to sync an uncached area
-	 */
-	if (PXSEG(vaddr) == P2SEG)
-		return;
-
-	switch (direction) {
-	case DMA_FROM_DEVICE:		/* invalidate only */
-		invalidate_dcache_region(vaddr, size);
-		break;
-	case DMA_TO_DEVICE:		/* writeback only */
-		clean_dcache_region(vaddr, size);
-		break;
-	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
-		flush_dcache_region(vaddr, size);
-		break;
-	default:
-		BUG();
-	}
-}
-EXPORT_SYMBOL(dma_cache_sync);
-
-static struct page *__dma_alloc(struct device *dev, size_t size,
-				dma_addr_t *handle, gfp_t gfp)
-{
-	struct page *page, *free, *end;
-	int order;
-
-	/* Following is a work-around (a.k.a. hack) to prevent pages
-	 * with __GFP_COMP being passed to split_page() which cannot
-	 * handle them.  The real problem is that this flag probably
-	 * should be 0 on AVR32 as it is not supported on this
-	 * platform--see CONFIG_HUGETLB_PAGE. */
-	gfp &= ~(__GFP_COMP);
-
-	size = PAGE_ALIGN(size);
-	order = get_order(size);
-
-	page = alloc_pages(gfp, order);
-	if (!page)
-		return NULL;
-	split_page(page, order);
-
-	/*
-	 * When accessing physical memory with valid cache data, we
-	 * get a cache hit even if the virtual memory region is marked
-	 * as uncached.
-	 *
-	 * Since the memory is newly allocated, there is no point in
-	 * doing a writeback. If the previous owner cares, he should
-	 * have flushed the cache before releasing the memory.
-	 */
-	invalidate_dcache_region(phys_to_virt(page_to_phys(page)), size);
-
-	*handle = page_to_bus(page);
-	free = page + (size >> PAGE_SHIFT);
-	end = page + (1 << order);
-
-	/*
-	 * Free any unused pages
-	 */
-	while (free < end) {
-		__free_page(free);
-		free++;
-	}
-
-	return page;
-}
-
-static void __dma_free(struct device *dev, size_t size,
-		       struct page *page, dma_addr_t handle)
-{
-	struct page *end = page + (PAGE_ALIGN(size) >> PAGE_SHIFT);
-
-	while (page < end)
-		__free_page(page++);
-}
-
-static void *avr32_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	struct page *page;
-	dma_addr_t phys;
-
-	page = __dma_alloc(dev, size, handle, gfp);
-	if (!page)
-		return NULL;
-	phys = page_to_phys(page);
-
-	if (attrs & DMA_ATTR_WRITE_COMBINE) {
-		/* Now, map the page into P3 with write-combining turned on */
-		*handle = phys;
-		return __ioremap(phys, size, _PAGE_BUFFER);
-	} else {
-		return phys_to_uncached(phys);
-	}
-}
-
-static void avr32_dma_free(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t handle, unsigned long attrs)
-{
-	struct page *page;
-
-	if (attrs & DMA_ATTR_WRITE_COMBINE) {
-		iounmap(cpu_addr);
-
-		page = phys_to_page(handle);
-	} else {
-		void *addr = phys_to_cached(uncached_to_phys(cpu_addr));
-
-		pr_debug("avr32_dma_free addr %p (phys %08lx) size %u\n",
-			 cpu_addr, (unsigned long)handle, (unsigned)size);
-
-		BUG_ON(!virt_addr_valid(addr));
-		page = virt_to_page(addr);
-	}
-
-	__dma_free(dev, size, page, handle);
-}
-
-static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction direction, unsigned long attrs)
-{
-	void *cpu_addr = page_address(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_cache_sync(dev, cpu_addr, size, direction);
-	return virt_to_bus(cpu_addr);
-}
-
-static int avr32_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		char *virt;
-
-		sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset;
-		virt = sg_virt(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		dma_cache_sync(dev, virt, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static void avr32_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	dma_cache_sync(dev, bus_to_virt(dma_handle), size, direction);
-}
-
-static void avr32_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sglist, int nents,
-		enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i)
-		dma_cache_sync(dev, sg_virt(sg), sg->length, direction);
-}
-
-const struct dma_map_ops avr32_dma_ops = {
-	.alloc			= avr32_dma_alloc,
-	.free			= avr32_dma_free,
-	.map_page		= avr32_dma_map_page,
-	.map_sg			= avr32_dma_map_sg,
-	.sync_single_for_device	= avr32_dma_sync_single_for_device,
-	.sync_sg_for_device	= avr32_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(avr32_dma_ops);
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
deleted file mode 100644
index b3977e9208a3..000000000000
--- a/arch/avr32/mm/fault.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/arch/sh/mm/fault.c:
- *   Copyright (C) 1999  Niibe Yutaka
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/mm.h>
-#include <linux/extable.h>
-#include <linux/pagemap.h>
-#include <linux/kdebug.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-
-#include <asm/mmu_context.h>
-#include <asm/sysreg.h>
-#include <asm/tlb.h>
-
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	int ret = 0;
-
-	if (!user_mode(regs)) {
-		if (kprobe_running() && kprobe_fault_handler(regs, trap))
-			ret = 1;
-	}
-
-	return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	return 0;
-}
-#endif
-
-int exception_trace = 1;
-
-/*
- * This routine handles page faults. It determines the address and the
- * problem, and then passes it off to one of the appropriate routines.
- *
- * ecr is the Exception Cause Register. Possible values are:
- *   6:  Protection fault (instruction access)
- *   15: Protection fault (read access)
- *   16: Protection fault (write access)
- *   20: Page not found (instruction access)
- *   24: Page not found (read access)
- *   28: Page not found (write access)
- */
-asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
-{
-	struct task_struct *tsk;
-	struct mm_struct *mm;
-	struct vm_area_struct *vma;
-	const struct exception_table_entry *fixup;
-	unsigned long address;
-	unsigned long page;
-	long signr;
-	int code;
-	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-
-	if (notify_page_fault(regs, ecr))
-		return;
-
-	address = sysreg_read(TLBEAR);
-
-	tsk = current;
-	mm = tsk->mm;
-
-	signr = SIGSEGV;
-	code = SEGV_MAPERR;
-
-	/*
-	 * If we're in an interrupt or have no user context, we must
-	 * not take the fault...
-	 */
-	if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
-		goto no_context;
-
-	local_irq_enable();
-
-	if (user_mode(regs))
-		flags |= FAULT_FLAG_USER;
-retry:
-	down_read(&mm->mmap_sem);
-
-	vma = find_vma(mm, address);
-	if (!vma)
-		goto bad_area;
-	if (vma->vm_start <= address)
-		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
-	if (expand_stack(vma, address))
-		goto bad_area;
-
-	/*
-	 * Ok, we have a good vm_area for this memory access, so we
-	 * can handle it...
-	 */
-good_area:
-	code = SEGV_ACCERR;
-
-	switch (ecr) {
-	case ECR_PROTECTION_X:
-	case ECR_TLB_MISS_X:
-		if (!(vma->vm_flags & VM_EXEC))
-			goto bad_area;
-		break;
-	case ECR_PROTECTION_R:
-	case ECR_TLB_MISS_R:
-		if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
-			goto bad_area;
-		break;
-	case ECR_PROTECTION_W:
-	case ECR_TLB_MISS_W:
-		if (!(vma->vm_flags & VM_WRITE))
-			goto bad_area;
-		flags |= FAULT_FLAG_WRITE;
-		break;
-	default:
-		panic("Unhandled case %lu in do_page_fault!", ecr);
-	}
-
-	/*
-	 * If for any reason at all we couldn't handle the fault, make
-	 * sure we exit gracefully rather than endlessly redo the
-	 * fault.
-	 */
-	fault = handle_mm_fault(vma, address, flags);
-
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
-		return;
-
-	if (unlikely(fault & VM_FAULT_ERROR)) {
-		if (fault & VM_FAULT_OOM)
-			goto out_of_memory;
-		else if (fault & VM_FAULT_SIGSEGV)
-			goto bad_area;
-		else if (fault & VM_FAULT_SIGBUS)
-			goto do_sigbus;
-		BUG();
-	}
-
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
-		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			flags |= FAULT_FLAG_TRIED;
-
-			/*
-			 * No need to up_read(&mm->mmap_sem) as we would have
-			 * already released it in __lock_page_or_retry() in
-			 * mm/filemap.c.
-			 */
-			goto retry;
-		}
-	}
-
-	up_read(&mm->mmap_sem);
-	return;
-
-	/*
-	 * Something tried to access memory that isn't in our memory
-	 * map. Fix it, but check if it's kernel or user first...
-	 */
-bad_area:
-	up_read(&mm->mmap_sem);
-
-	if (user_mode(regs)) {
-		if (exception_trace && printk_ratelimit())
-			printk("%s%s[%d]: segfault at %08lx pc %08lx "
-			       "sp %08lx ecr %lu\n",
-			       is_global_init(tsk) ? KERN_EMERG : KERN_INFO,
-			       tsk->comm, tsk->pid, address, regs->pc,
-			       regs->sp, ecr);
-		_exception(SIGSEGV, regs, code, address);
-		return;
-	}
-
-no_context:
-	/* Are we prepared to handle this kernel fault? */
-	fixup = search_exception_tables(regs->pc);
-	if (fixup) {
-		regs->pc = fixup->fixup;
-		return;
-	}
-
-	/*
-	 * Oops. The kernel tried to access some bad page. We'll have
-	 * to terminate things with extreme prejudice.
-	 */
-	if (address < PAGE_SIZE)
-		printk(KERN_ALERT
-		       "Unable to handle kernel NULL pointer dereference");
-	else
-		printk(KERN_ALERT
-		       "Unable to handle kernel paging request");
-	printk(" at virtual address %08lx\n", address);
-
-	page = sysreg_read(PTBR);
-	printk(KERN_ALERT "ptbr = %08lx", page);
-	if (address >= TASK_SIZE)
-		page = (unsigned long)swapper_pg_dir;
-	if (page) {
-		page = ((unsigned long *)page)[address >> 22];
-		printk(" pgd = %08lx", page);
-		if (page & _PAGE_PRESENT) {
-			page &= PAGE_MASK;
-			address &= 0x003ff000;
-			page = ((unsigned long *)__va(page))[address >> PAGE_SHIFT];
-			printk(" pte = %08lx", page);
-		}
-	}
-	printk("\n");
-	die("Kernel access of bad area", regs, signr);
-	return;
-
-	/*
-	 * We ran out of memory, or some other thing happened to us
-	 * that made us unable to handle the page fault gracefully.
-	 */
-out_of_memory:
-	up_read(&mm->mmap_sem);
-	if (!user_mode(regs))
-		goto no_context;
-	pagefault_out_of_memory();
-	return;
-
-do_sigbus:
-	up_read(&mm->mmap_sem);
-
-	/* Kernel mode? Handle exceptions or die */
-	signr = SIGBUS;
-	code = BUS_ADRERR;
-	if (!user_mode(regs))
-		goto no_context;
-
-	if (exception_trace)
-		printk("%s%s[%d]: bus error at %08lx pc %08lx "
-		       "sp %08lx ecr %lu\n",
-		       is_global_init(tsk) ? KERN_EMERG : KERN_INFO,
-		       tsk->comm, tsk->pid, address, regs->pc,
-		       regs->sp, ecr);
-
-	_exception(SIGBUS, regs, BUS_ADRERR, address);
-}
-
-asmlinkage void do_bus_error(unsigned long addr, int write_access,
-			     struct pt_regs *regs)
-{
-	printk(KERN_ALERT
-	       "Bus error at physical address 0x%08lx (%s access)\n",
-	       addr, write_access ? "write" : "read");
-	printk(KERN_INFO "DTLB dump:\n");
-	dump_dtlb();
-	die("Bus Error", regs, SIGKILL);
-}
diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c
deleted file mode 100644
index def5391d927a..000000000000
--- a/arch/avr32/mm/init.c
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/gfp.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/init.h>
-#include <linux/mmzone.h>
-#include <linux/module.h>
-#include <linux/bootmem.h>
-#include <linux/pagemap.h>
-#include <linux/nodemask.h>
-
-#include <asm/page.h>
-#include <asm/mmu_context.h>
-#include <asm/tlb.h>
-#include <asm/io.h>
-#include <asm/dma.h>
-#include <asm/setup.h>
-#include <asm/sections.h>
-
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_data;
-
-struct page *empty_zero_page;
-EXPORT_SYMBOL(empty_zero_page);
-
-/*
- * Cache of MMU context last used.
- */
-unsigned long mmu_context_cache = NO_CONTEXT;
-
-/*
- * paging_init() sets up the page tables
- *
- * This routine also unmaps the page at virtual kernel address 0, so
- * that we can trap those pesky NULL-reference errors in the kernel.
- */
-void __init paging_init(void)
-{
-	extern unsigned long _evba;
-	void *zero_page;
-	int nid;
-
-	/*
-	 * Make sure we can handle exceptions before enabling
-	 * paging. Not that we should ever _get_ any exceptions this
-	 * early, but you never know...
-	 */
-	printk("Exception vectors start at %p\n", &_evba);
-	sysreg_write(EVBA, (unsigned long)&_evba);
-
-	/*
-	 * Since we are ready to handle exceptions now, we should let
-	 * the CPU generate them...
-	 */
-	__asm__ __volatile__ ("csrf %0" : : "i"(SR_EM_BIT));
-
-	/*
-	 * Allocate the zero page. The allocator will panic if it
-	 * can't satisfy the request, so no need to check.
-	 */
-	zero_page = alloc_bootmem_low_pages_node(NODE_DATA(0),
-						 PAGE_SIZE);
-
-	sysreg_write(PTBR, (unsigned long)swapper_pg_dir);
-	enable_mmu();
-	printk ("CPU: Paging enabled\n");
-
-	for_each_online_node(nid) {
-		pg_data_t *pgdat = NODE_DATA(nid);
-		unsigned long zones_size[MAX_NR_ZONES];
-		unsigned long low, start_pfn;
-
-		start_pfn = pgdat->bdata->node_min_pfn;
-		low = pgdat->bdata->node_low_pfn;
-
-		memset(zones_size, 0, sizeof(zones_size));
-		zones_size[ZONE_NORMAL] = low - start_pfn;
-
-		printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n",
-		       nid, start_pfn, low);
-
-		free_area_init_node(nid, zones_size, start_pfn, NULL);
-
-		printk("Node %u: mem_map starts at %p\n",
-		       pgdat->node_id, pgdat->node_mem_map);
-	}
-
-	mem_map = NODE_DATA(0)->node_mem_map;
-
-	empty_zero_page = virt_to_page(zero_page);
-	flush_dcache_page(empty_zero_page);
-}
-
-void __init mem_init(void)
-{
-	pg_data_t *pgdat;
-
-	high_memory = NULL;
-	for_each_online_pgdat(pgdat)
-		high_memory = max_t(void *, high_memory,
-				    __va(pgdat_end_pfn(pgdat) << PAGE_SHIFT));
-
-	set_max_mapnr(MAP_NR(high_memory));
-	free_all_bootmem();
-	mem_init_print_info(NULL);
-}
-
-void free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
diff --git a/arch/avr32/mm/ioremap.c b/arch/avr32/mm/ioremap.c
deleted file mode 100644
index 7def0d84cec6..000000000000
--- a/arch/avr32/mm/ioremap.c
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-
-#include <asm/pgtable.h>
-#include <asm/addrspace.h>
-
-/*
- * Re-map an arbitrary physical address space into the kernel virtual
- * address space. Needed when the kernel wants to access physical
- * memory directly.
- */
-void __iomem *__ioremap(unsigned long phys_addr, size_t size,
-			unsigned long flags)
-{
-	unsigned long addr;
-	struct vm_struct *area;
-	unsigned long offset, last_addr;
-	pgprot_t prot;
-
-	/*
-	 * Check if we can simply use the P4 segment. This area is
-	 * uncacheable, so if caching/buffering is requested, we can't
-	 * use it.
-	 */
-	if ((phys_addr >= P4SEG) && (flags == 0))
-		return (void __iomem *)phys_addr;
-
-	/* Don't allow wraparound or zero size */
-	last_addr = phys_addr + size - 1;
-	if (!size || last_addr < phys_addr)
-		return NULL;
-
-	/*
-	 * XXX: When mapping regular RAM, we'd better make damn sure
-	 * it's never used for anything else.  But this is really the
-	 * caller's responsibility...
-	 */
-	if (PHYSADDR(P2SEGADDR(phys_addr)) == phys_addr)
-		return (void __iomem *)P2SEGADDR(phys_addr);
-
-	/* Mappings have to be page-aligned */
-	offset = phys_addr & ~PAGE_MASK;
-	phys_addr &= PAGE_MASK;
-	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
-
-	prot = __pgprot(_PAGE_PRESENT | _PAGE_GLOBAL | _PAGE_RW | _PAGE_DIRTY
-			| _PAGE_ACCESSED | _PAGE_TYPE_SMALL | flags);
-
-	/*
-	 * Ok, go for it..
-	 */
-	area = get_vm_area(size, VM_IOREMAP);
-	if (!area)
-		return NULL;
-	area->phys_addr = phys_addr;
-	addr = (unsigned long )area->addr;
-	if (ioremap_page_range(addr, addr + size, phys_addr, prot)) {
-		vunmap((void *)addr);
-		return NULL;
-	}
-
-	return (void __iomem *)(offset + (char *)addr);
-}
-EXPORT_SYMBOL(__ioremap);
-
-void __iounmap(void __iomem *addr)
-{
-	struct vm_struct *p;
-
-	if ((unsigned long)addr >= P4SEG)
-		return;
-	if (PXSEG(addr) == P2SEG)
-		return;
-
-	p = remove_vm_area((void *)(PAGE_MASK & (unsigned long __force)addr));
-	if (unlikely(!p)) {
-		printk (KERN_ERR "iounmap: bad address %p\n", addr);
-		return;
-	}
-
-	kfree (p);
-}
-EXPORT_SYMBOL(__iounmap);
diff --git a/arch/avr32/mm/tlb.c b/arch/avr32/mm/tlb.c
deleted file mode 100644
index 0da23109f817..000000000000
--- a/arch/avr32/mm/tlb.c
+++ /dev/null
@@ -1,375 +0,0 @@
-/*
- * AVR32 TLB operations
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/mm.h>
-
-#include <asm/mmu_context.h>
-
-/* TODO: Get the correct number from the CONFIG1 system register */
-#define NR_TLB_ENTRIES 32
-
-static void show_dtlb_entry(unsigned int index)
-{
-	u32 tlbehi, tlbehi_save, tlbelo, mmucr, mmucr_save;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	mmucr_save = sysreg_read(MMUCR);
-	tlbehi_save = sysreg_read(TLBEHI);
-	mmucr = SYSREG_BFINS(DRP, index, mmucr_save);
-	sysreg_write(MMUCR, mmucr);
-
-	__builtin_tlbr();
-	cpu_sync_pipeline();
-
-	tlbehi = sysreg_read(TLBEHI);
-	tlbelo = sysreg_read(TLBELO);
-
-	printk("%2u: %c %c %02x   %05x %05x %o  %o  %c %c %c %c\n",
-	       index,
-	       SYSREG_BFEXT(TLBEHI_V, tlbehi) ? '1' : '0',
-	       SYSREG_BFEXT(G, tlbelo) ? '1' : '0',
-	       SYSREG_BFEXT(ASID, tlbehi),
-	       SYSREG_BFEXT(VPN, tlbehi) >> 2,
-	       SYSREG_BFEXT(PFN, tlbelo) >> 2,
-	       SYSREG_BFEXT(AP, tlbelo),
-	       SYSREG_BFEXT(SZ, tlbelo),
-	       SYSREG_BFEXT(TLBELO_C, tlbelo) ? 'C' : ' ',
-	       SYSREG_BFEXT(B, tlbelo) ? 'B' : ' ',
-	       SYSREG_BFEXT(W, tlbelo) ? 'W' : ' ',
-	       SYSREG_BFEXT(TLBELO_D, tlbelo) ? 'D' : ' ');
-
-	sysreg_write(MMUCR, mmucr_save);
-	sysreg_write(TLBEHI, tlbehi_save);
-	cpu_sync_pipeline();
-	local_irq_restore(flags);
-}
-
-void dump_dtlb(void)
-{
-	unsigned int i;
-
-	printk("ID  V G ASID VPN   PFN   AP SZ C B W D\n");
-	for (i = 0; i < NR_TLB_ENTRIES; i++)
-		show_dtlb_entry(i);
-}
-
-static void update_dtlb(unsigned long address, pte_t pte)
-{
-	u32 tlbehi;
-	u32 mmucr;
-
-	/*
-	 * We're not changing the ASID here, so no need to flush the
-	 * pipeline.
-	 */
-	tlbehi = sysreg_read(TLBEHI);
-	tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
-	tlbehi |= address & MMU_VPN_MASK;
-	tlbehi |= SYSREG_BIT(TLBEHI_V);
-	sysreg_write(TLBEHI, tlbehi);
-
-	/* Does this mapping already exist? */
-	__builtin_tlbs();
-	mmucr = sysreg_read(MMUCR);
-
-	if (mmucr & SYSREG_BIT(MMUCR_N)) {
-		/* Not found -- pick a not-recently-accessed entry */
-		unsigned int rp;
-		u32 tlbar = sysreg_read(TLBARLO);
-
-		rp = 32 - fls(tlbar);
-		if (rp == 32) {
-			rp = 0;
-			sysreg_write(TLBARLO, -1L);
-		}
-
-		mmucr = SYSREG_BFINS(DRP, rp, mmucr);
-		sysreg_write(MMUCR, mmucr);
-	}
-
-	sysreg_write(TLBELO, pte_val(pte) & _PAGE_FLAGS_HARDWARE_MASK);
-
-	/* Let's go */
-	__builtin_tlbw();
-}
-
-void update_mmu_cache(struct vm_area_struct *vma,
-		      unsigned long address, pte_t *ptep)
-{
-	unsigned long flags;
-
-	/* ptrace may call this routine */
-	if (vma && current->active_mm != vma->vm_mm)
-		return;
-
-	local_irq_save(flags);
-	update_dtlb(address, *ptep);
-	local_irq_restore(flags);
-}
-
-static void __flush_tlb_page(unsigned long asid, unsigned long page)
-{
-	u32 mmucr, tlbehi;
-
-	/*
-	 * Caller is responsible for masking out non-PFN bits in page
-	 * and changing the current ASID if necessary. This means that
-	 * we don't need to flush the pipeline after writing TLBEHI.
-	 */
-	tlbehi = page | asid;
-	sysreg_write(TLBEHI, tlbehi);
-
-	__builtin_tlbs();
-	mmucr = sysreg_read(MMUCR);
-
-	if (!(mmucr & SYSREG_BIT(MMUCR_N))) {
-		unsigned int entry;
-		u32 tlbarlo;
-
-		/* Clear the "valid" bit */
-		sysreg_write(TLBEHI, tlbehi);
-
-		/* mark the entry as "not accessed" */
-		entry = SYSREG_BFEXT(DRP, mmucr);
-		tlbarlo = sysreg_read(TLBARLO);
-		tlbarlo |= (0x80000000UL >> entry);
-		sysreg_write(TLBARLO, tlbarlo);
-
-		/* update the entry with valid bit clear */
-		__builtin_tlbw();
-	}
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
-{
-	if (vma->vm_mm && vma->vm_mm->context != NO_CONTEXT) {
-		unsigned long flags, asid;
-		unsigned long saved_asid = MMU_NO_ASID;
-
-		asid = vma->vm_mm->context & MMU_CONTEXT_ASID_MASK;
-		page &= PAGE_MASK;
-
-		local_irq_save(flags);
-		if (vma->vm_mm != current->mm) {
-			saved_asid = get_asid();
-			set_asid(asid);
-		}
-
-		__flush_tlb_page(asid, page);
-
-		if (saved_asid != MMU_NO_ASID)
-			set_asid(saved_asid);
-		local_irq_restore(flags);
-	}
-}
-
-void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
-		     unsigned long end)
-{
-	struct mm_struct *mm = vma->vm_mm;
-
-	if (mm->context != NO_CONTEXT) {
-		unsigned long flags;
-		int size;
-
-		local_irq_save(flags);
-		size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-
-		if (size > (MMU_DTLB_ENTRIES / 4)) { /* Too many entries to flush */
-			mm->context = NO_CONTEXT;
-			if (mm == current->mm)
-				activate_context(mm);
-		} else {
-			unsigned long asid;
-			unsigned long saved_asid;
-
-			asid = mm->context & MMU_CONTEXT_ASID_MASK;
-			saved_asid = MMU_NO_ASID;
-
-			start &= PAGE_MASK;
-			end += (PAGE_SIZE - 1);
-			end &= PAGE_MASK;
-
-			if (mm != current->mm) {
-				saved_asid = get_asid();
-				set_asid(asid);
-			}
-
-			while (start < end) {
-				__flush_tlb_page(asid, start);
-				start += PAGE_SIZE;
-			}
-			if (saved_asid != MMU_NO_ASID)
-				set_asid(saved_asid);
-		}
-		local_irq_restore(flags);
-	}
-}
-
-/*
- * This function depends on the pages to be flushed having the G
- * (global) bit set in their pte. This is true for all
- * PAGE_KERNEL(_RO) pages.
- */
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	unsigned long flags;
-	int size;
-
-	size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-	if (size > (MMU_DTLB_ENTRIES / 4)) { /* Too many entries to flush */
-		flush_tlb_all();
-	} else {
-		unsigned long asid;
-
-		local_irq_save(flags);
-		asid = get_asid();
-
-		start &= PAGE_MASK;
-		end += (PAGE_SIZE - 1);
-		end &= PAGE_MASK;
-
-		while (start < end) {
-			__flush_tlb_page(asid, start);
-			start += PAGE_SIZE;
-		}
-		local_irq_restore(flags);
-	}
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
-	/* Invalidate all TLB entries of this process by getting a new ASID */
-	if (mm->context != NO_CONTEXT) {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		mm->context = NO_CONTEXT;
-		if (mm == current->mm)
-			activate_context(mm);
-		local_irq_restore(flags);
-	}
-}
-
-void flush_tlb_all(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	sysreg_write(MMUCR, sysreg_read(MMUCR) | SYSREG_BIT(MMUCR_I));
-	local_irq_restore(flags);
-}
-
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
-#include <linux/init.h>
-
-static void *tlb_start(struct seq_file *tlb, loff_t *pos)
-{
-	static unsigned long tlb_index;
-
-	if (*pos >= NR_TLB_ENTRIES)
-		return NULL;
-
-	tlb_index = 0;
-	return &tlb_index;
-}
-
-static void *tlb_next(struct seq_file *tlb, void *v, loff_t *pos)
-{
-	unsigned long *index = v;
-
-	if (*index >= NR_TLB_ENTRIES - 1)
-		return NULL;
-
-	++*pos;
-	++*index;
-	return index;
-}
-
-static void tlb_stop(struct seq_file *tlb, void *v)
-{
-
-}
-
-static int tlb_show(struct seq_file *tlb, void *v)
-{
-	unsigned int tlbehi, tlbehi_save, tlbelo, mmucr, mmucr_save;
-	unsigned long flags;
-	unsigned long *index = v;
-
-	if (*index == 0)
-		seq_puts(tlb, "ID  V G ASID VPN   PFN   AP SZ C B W D\n");
-
-	BUG_ON(*index >= NR_TLB_ENTRIES);
-
-	local_irq_save(flags);
-	mmucr_save = sysreg_read(MMUCR);
-	tlbehi_save = sysreg_read(TLBEHI);
-	mmucr = SYSREG_BFINS(DRP, *index, mmucr_save);
-	sysreg_write(MMUCR, mmucr);
-
-	/* TLBR might change the ASID */
-	__builtin_tlbr();
-	cpu_sync_pipeline();
-
-	tlbehi = sysreg_read(TLBEHI);
-	tlbelo = sysreg_read(TLBELO);
-
-	sysreg_write(MMUCR, mmucr_save);
-	sysreg_write(TLBEHI, tlbehi_save);
-	cpu_sync_pipeline();
-	local_irq_restore(flags);
-
-	seq_printf(tlb, "%2lu: %c %c %02x   %05x %05x %o  %o  %c %c %c %c\n",
-		   *index,
-		   SYSREG_BFEXT(TLBEHI_V, tlbehi) ? '1' : '0',
-		   SYSREG_BFEXT(G, tlbelo) ? '1' : '0',
-		   SYSREG_BFEXT(ASID, tlbehi),
-		   SYSREG_BFEXT(VPN, tlbehi) >> 2,
-		   SYSREG_BFEXT(PFN, tlbelo) >> 2,
-		   SYSREG_BFEXT(AP, tlbelo),
-		   SYSREG_BFEXT(SZ, tlbelo),
-		   SYSREG_BFEXT(TLBELO_C, tlbelo) ? '1' : '0',
-		   SYSREG_BFEXT(B, tlbelo) ? '1' : '0',
-		   SYSREG_BFEXT(W, tlbelo) ? '1' : '0',
-		   SYSREG_BFEXT(TLBELO_D, tlbelo) ? '1' : '0');
-
-	return 0;
-}
-
-static const struct seq_operations tlb_ops = {
-	.start		= tlb_start,
-	.next		= tlb_next,
-	.stop		= tlb_stop,
-	.show		= tlb_show,
-};
-
-static int tlb_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &tlb_ops);
-}
-
-static const struct file_operations proc_tlb_operations = {
-	.open		= tlb_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int __init proctlb_init(void)
-{
-	proc_create("tlb", 0, NULL, &proc_tlb_operations);
-	return 0;
-}
-late_initcall(proctlb_init);
-#endif /* CONFIG_PROC_FS */
diff --git a/arch/avr32/oprofile/Makefile b/arch/avr32/oprofile/Makefile
deleted file mode 100644
index e0eb520e0287..000000000000
--- a/arch/avr32/oprofile/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-obj-$(CONFIG_OPROFILE) += oprofile.o
-
-oprofile-y		:= $(addprefix ../../../drivers/oprofile/,	\
-				oprof.o cpu_buffer.o buffer_sync.o	\
-				event_buffer.o oprofile_files.o		\
-				oprofilefs.o oprofile_stats.o		\
-				timer_int.o)
-oprofile-y		+= op_model_avr32.o backtrace.o
diff --git a/arch/avr32/oprofile/backtrace.c b/arch/avr32/oprofile/backtrace.c
deleted file mode 100644
index 75d9ad6f99cf..000000000000
--- a/arch/avr32/oprofile/backtrace.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * AVR32 specific backtracing code for oprofile
- *
- * Copyright 2008 Weinmann GmbH
- *
- * Author: Nikolaus Voss <n.voss@weinmann.de>
- *
- * Based on i386 oprofile backtrace code by John Levon and David Smith
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/oprofile.h>
-#include <linux/sched.h>
-#include <linux/uaccess.h>
-
-/* The first two words of each frame on the stack look like this if we have
- * frame pointers */
-struct frame_head {
-	unsigned long lr;
-	struct frame_head *fp;
-};
-
-/* copied from arch/avr32/kernel/process.c */
-static inline int valid_stack_ptr(struct thread_info *tinfo, unsigned long p)
-{
-	return (p > (unsigned long)tinfo)
-		&& (p < (unsigned long)tinfo + THREAD_SIZE - 3);
-}
-
-/* copied from arch/x86/oprofile/backtrace.c */
-static struct frame_head *dump_user_backtrace(struct frame_head *head)
-{
-	struct frame_head bufhead[2];
-
-	/* Also check accessibility of one struct frame_head beyond */
-	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
-		return NULL;
-	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
-		return NULL;
-
-	oprofile_add_trace(bufhead[0].lr);
-
-	/* frame pointers should strictly progress back up the stack
-	 * (towards higher addresses) */
-	if (bufhead[0].fp <= head)
-		return NULL;
-
-	return bufhead[0].fp;
-}
-
-void avr32_backtrace(struct pt_regs * const regs, unsigned int depth)
-{
-	/* Get first frame pointer */
-	struct frame_head *head = (struct frame_head *)(regs->r7);
-
-	if (!user_mode(regs)) {
-#ifdef CONFIG_FRAME_POINTER
-		/*
-		 * Traverse the kernel stack from frame to frame up to
-		 * "depth" steps.
-		 */
-		while (depth-- && valid_stack_ptr(task_thread_info(current),
-						  (unsigned long)head)) {
-			oprofile_add_trace(head->lr);
-			if (head->fp <= head)
-				break;
-			head = head->fp;
-		}
-#endif
-	} else {
-		/* Assume we have frame pointers in user mode process */
-		while (depth-- && head)
-			head = dump_user_backtrace(head);
-	}
-}
-
-
diff --git a/arch/avr32/oprofile/op_model_avr32.c b/arch/avr32/oprofile/op_model_avr32.c
deleted file mode 100644
index 08308be2c02c..000000000000
--- a/arch/avr32/oprofile/op_model_avr32.c
+++ /dev/null
@@ -1,236 +0,0 @@
-/*
- * AVR32 Performance Counter Driver
- *
- * Copyright (C) 2005-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Author: Ronny Pedersen
- */
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/oprofile.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-
-#include <asm/sysreg.h>
-
-#define AVR32_PERFCTR_IRQ_GROUP	0
-#define AVR32_PERFCTR_IRQ_LINE	1
-
-void avr32_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-enum { PCCNT, PCNT0, PCNT1, NR_counter };
-
-struct avr32_perf_counter {
-	unsigned long	enabled;
-	unsigned long	event;
-	unsigned long	count;
-	unsigned long	unit_mask;
-	unsigned long	kernel;
-	unsigned long	user;
-
-	u32		ie_mask;
-	u32		flag_mask;
-};
-
-static struct avr32_perf_counter counter[NR_counter] = {
-	{
-		.ie_mask	= SYSREG_BIT(IEC),
-		.flag_mask	= SYSREG_BIT(FC),
-	}, {
-		.ie_mask	= SYSREG_BIT(IE0),
-		.flag_mask	= SYSREG_BIT(F0),
-	}, {
-		.ie_mask	= SYSREG_BIT(IE1),
-		.flag_mask	= SYSREG_BIT(F1),
-	},
-};
-
-static void avr32_perf_counter_reset(void)
-{
-	/* Reset all counter and disable/clear all interrupts */
-	sysreg_write(PCCR, (SYSREG_BIT(PCCR_R)
-				| SYSREG_BIT(PCCR_C)
-				| SYSREG_BIT(FC)
-				| SYSREG_BIT(F0)
-				| SYSREG_BIT(F1)));
-}
-
-static irqreturn_t avr32_perf_counter_interrupt(int irq, void *dev_id)
-{
-	struct avr32_perf_counter *ctr = dev_id;
-	struct pt_regs *regs;
-	u32 pccr;
-
-	if (likely(!(intc_get_pending(AVR32_PERFCTR_IRQ_GROUP)
-					& (1 << AVR32_PERFCTR_IRQ_LINE))))
-		return IRQ_NONE;
-
-	regs = get_irq_regs();
-	pccr = sysreg_read(PCCR);
-
-	/* Clear the interrupt flags we're about to handle */
-	sysreg_write(PCCR, pccr);
-
-	/* PCCNT */
-	if (ctr->enabled && (pccr & ctr->flag_mask)) {
-		sysreg_write(PCCNT, -ctr->count);
-		oprofile_add_sample(regs, PCCNT);
-	}
-	ctr++;
-	/* PCNT0 */
-	if (ctr->enabled && (pccr & ctr->flag_mask)) {
-		sysreg_write(PCNT0, -ctr->count);
-		oprofile_add_sample(regs, PCNT0);
-	}
-	ctr++;
-	/* PCNT1 */
-	if (ctr->enabled && (pccr & ctr->flag_mask)) {
-		sysreg_write(PCNT1, -ctr->count);
-		oprofile_add_sample(regs, PCNT1);
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int avr32_perf_counter_create_files(struct dentry *root)
-{
-	struct dentry *dir;
-	unsigned int i;
-	char filename[4];
-
-	for (i = 0; i < NR_counter; i++) {
-		snprintf(filename, sizeof(filename), "%u", i);
-		dir = oprofilefs_mkdir(root, filename);
-
-		oprofilefs_create_ulong(dir, "enabled",
-				&counter[i].enabled);
-		oprofilefs_create_ulong(dir, "event",
-				&counter[i].event);
-		oprofilefs_create_ulong(dir, "count",
-				&counter[i].count);
-
-		/* Dummy entries */
-		oprofilefs_create_ulong(dir, "kernel",
-				&counter[i].kernel);
-		oprofilefs_create_ulong(dir, "user",
-				&counter[i].user);
-		oprofilefs_create_ulong(dir, "unit_mask",
-				&counter[i].unit_mask);
-	}
-
-	return 0;
-}
-
-static int avr32_perf_counter_setup(void)
-{
-	struct avr32_perf_counter *ctr;
-	u32 pccr;
-	int ret;
-	int i;
-
-	pr_debug("avr32_perf_counter_setup\n");
-
-	if (sysreg_read(PCCR) & SYSREG_BIT(PCCR_E)) {
-		printk(KERN_ERR
-			"oprofile: setup: perf counter already enabled\n");
-		return -EBUSY;
-	}
-
-	ret = request_irq(AVR32_PERFCTR_IRQ_GROUP,
-			avr32_perf_counter_interrupt, IRQF_SHARED,
-			"oprofile", counter);
-	if (ret)
-		return ret;
-
-	avr32_perf_counter_reset();
-
-	pccr = 0;
-	for (i = PCCNT; i < NR_counter; i++) {
-		ctr = &counter[i];
-		if (!ctr->enabled)
-			continue;
-
-		pr_debug("enabling counter %d...\n", i);
-
-		pccr |= ctr->ie_mask;
-
-		switch (i) {
-		case PCCNT:
-			/* PCCNT always counts cycles, so no events */
-			sysreg_write(PCCNT, -ctr->count);
-			break;
-		case PCNT0:
-			pccr |= SYSREG_BF(CONF0, ctr->event);
-			sysreg_write(PCNT0, -ctr->count);
-			break;
-		case PCNT1:
-			pccr |= SYSREG_BF(CONF1, ctr->event);
-			sysreg_write(PCNT1, -ctr->count);
-			break;
-		}
-	}
-
-	pr_debug("oprofile: writing 0x%x to PCCR...\n", pccr);
-
-	sysreg_write(PCCR, pccr);
-
-	return 0;
-}
-
-static void avr32_perf_counter_shutdown(void)
-{
-	pr_debug("avr32_perf_counter_shutdown\n");
-
-	avr32_perf_counter_reset();
-	free_irq(AVR32_PERFCTR_IRQ_GROUP, counter);
-}
-
-static int avr32_perf_counter_start(void)
-{
-	pr_debug("avr32_perf_counter_start\n");
-
-	sysreg_write(PCCR, sysreg_read(PCCR) | SYSREG_BIT(PCCR_E));
-
-	return 0;
-}
-
-static void avr32_perf_counter_stop(void)
-{
-	pr_debug("avr32_perf_counter_stop\n");
-
-	sysreg_write(PCCR, sysreg_read(PCCR) & ~SYSREG_BIT(PCCR_E));
-}
-
-static struct oprofile_operations avr32_perf_counter_ops __initdata = {
-	.create_files	= avr32_perf_counter_create_files,
-	.setup		= avr32_perf_counter_setup,
-	.shutdown	= avr32_perf_counter_shutdown,
-	.start		= avr32_perf_counter_start,
-	.stop		= avr32_perf_counter_stop,
-	.cpu_type	= "avr32",
-};
-
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
-	if (!(current_cpu_data.features & AVR32_FEATURE_PCTR))
-		return -ENODEV;
-
-	memcpy(ops, &avr32_perf_counter_ops,
-			sizeof(struct oprofile_operations));
-
-	ops->backtrace = avr32_backtrace;
-
-	printk(KERN_INFO "oprofile: using AVR32 performance monitoring.\n");
-
-	return 0;
-}
-
-void oprofile_arch_exit(void)
-{
-
-}
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 625db8ac815e..dc4ef9ac1e83 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += futex.h
 generic-y += hw_irq.h
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 0eff88aa6d6a..f54a34f31cea 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -12,7 +12,6 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/string.h>
 
@@ -29,9 +28,6 @@ static inline void set_fs(mm_segment_t fs)
 
 #define segment_eq(a, b) ((a) == (b))
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define access_ok(type, addr, size) _access_ok((unsigned long)(addr), (size))
 
 /*
@@ -46,22 +42,7 @@ static inline int _access_ok(unsigned long addr, unsigned long size) { return 1;
 extern int _access_ok(unsigned long addr, unsigned long size);
 #endif
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
+#include <asm/extable.h>
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -163,41 +144,23 @@ static inline int bad_user_access_length(void)
 		: "a" (__ptr(ptr)));		\
 })
 
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
 static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	memcpy(to, (const void __force *)from, n);
 	return 0;
 }
 
 static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	memcpy((void __force *)to, from, n);
 	SSYNC();
 	return 0;
 }
 
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		return __copy_from_user(to, from, n);
-	memset(to, 0, n);
-	return n;
-}
-
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_WRITE, to, n)))
-		return __copy_to_user(to, from, n);
-	return n;
-}
-
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 /*
  * Copy a null terminated string from userspace.
  */
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 89d5162d4ca6..89814850b08b 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -370,7 +370,7 @@ int _access_ok(unsigned long addr, unsigned long size)
 	/* Check that things do not wrap around */
 	if (addr > ULONG_MAX - size)
 		return 0;
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (uaccess_kernel())
 		return 1;
 #ifdef CONFIG_MTD_UCLINUX
 	if (1)
diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c
index 0e9fcf841d67..01350557fbd7 100644
--- a/arch/blackfin/kernel/time-ts.c
+++ b/arch/blackfin/kernel/time-ts.c
@@ -230,7 +230,9 @@ static void __init bfin_gptmr0_clockevent_init(struct clock_event_device *evt)
 	clock_tick = get_sclk();
 	evt->mult = div_sc(clock_tick, NSEC_PER_SEC, evt->shift);
 	evt->max_delta_ns = clockevent_delta2ns(-1, evt);
+	evt->max_delta_ticks = (unsigned long)-1;
 	evt->min_delta_ns = clockevent_delta2ns(100, evt);
+	evt->min_delta_ticks = 100;
 
 	evt->cpumask = cpumask_of(0);
 
@@ -344,7 +346,9 @@ void bfin_coretmr_clockevent_init(void)
 	clock_tick = get_cclk() / TIME_SCALE;
 	evt->mult = div_sc(clock_tick, NSEC_PER_SEC, evt->shift);
 	evt->max_delta_ns = clockevent_delta2ns(-1, evt);
+	evt->max_delta_ticks = (unsigned long)-1;
 	evt->min_delta_ns = clockevent_delta2ns(100, evt);
+	evt->min_delta_ticks = 100;
 
 	evt->cpumask = cpumask_of(cpu);
 
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 68069a120055..334ef8139b35 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -115,6 +115,8 @@ SECTIONS
 	__data_lma = LOADADDR(.data);
 	__data_len = SIZEOF(.data);
 
+	BUG_TABLE
+
 	/* The init section should be last, so when we free it, it goes into
 	 * the general memory pool, and (hopefully) will decrease fragmentation
 	 * a tiny bit. The init section has a _requirement_ that it be
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 82619c32d25b..f0eaf0475e7e 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += futex.h
diff --git a/arch/c6x/include/asm/uaccess.h b/arch/c6x/include/asm/uaccess.h
index 453dd263bee3..ba6756879f00 100644
--- a/arch/c6x/include/asm/uaccess.h
+++ b/arch/c6x/include/asm/uaccess.h
@@ -13,17 +13,11 @@
 #include <linux/compiler.h>
 #include <linux/string.h>
 
-#ifdef CONFIG_ACCESS_CHECK
-#define __access_ok _access_ok
-#endif
-
 /*
- * __copy_from_user/copy_to_user are based on ones in asm-generic/uaccess.h
- *
  * C6X supports unaligned 32 and 64 bit loads and stores.
  */
-static inline __must_check long __copy_from_user(void *to,
-		const void __user *from, unsigned long n)
+static inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	u32 tmp32;
 	u64 tmp64;
@@ -58,8 +52,8 @@ static inline __must_check long __copy_from_user(void *to,
 	return 0;
 }
 
-static inline __must_check long __copy_to_user(void __user *to,
-		const void *from, unsigned long n)
+static inline __must_check unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	u32 tmp32;
 	u64 tmp64;
@@ -93,9 +87,8 @@ static inline __must_check long __copy_to_user(void __user *to,
 	memcpy((void __force *)to, from, n);
 	return 0;
 }
-
-#define __copy_to_user   __copy_to_user
-#define __copy_from_user __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 extern int _access_ok(unsigned long addr, unsigned long size);
 #ifdef CONFIG_ACCESS_CHECK
diff --git a/arch/c6x/kernel/ptrace.c b/arch/c6x/kernel/ptrace.c
index a27e1f02ce18..8801dc98fd44 100644
--- a/arch/c6x/kernel/ptrace.c
+++ b/arch/c6x/kernel/ptrace.c
@@ -70,46 +70,6 @@ static int gpr_get(struct task_struct *target,
 				   0, sizeof(*regs));
 }
 
-static int gpr_set(struct task_struct *target,
-		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-	struct pt_regs *regs = task_pt_regs(target);
-
-	/* Don't copyin TSR or CSR */
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &regs,
-				 0, PT_TSR * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					PT_TSR * sizeof(long),
-					(PT_TSR + 1) * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &regs,
-				 (PT_TSR + 1) * sizeof(long),
-				 PT_CSR * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					PT_CSR * sizeof(long),
-					(PT_CSR + 1) * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &regs,
-				 (PT_CSR + 1) * sizeof(long), -1);
-	return ret;
-}
-
 enum c6x_regset {
 	REGSET_GPR,
 };
@@ -121,7 +81,6 @@ static const struct user_regset c6x_regsets[] = {
 		.size = sizeof(u32),
 		.align = sizeof(u32),
 		.get = gpr_get,
-		.set = gpr_set
 	},
 };
 
diff --git a/arch/c6x/kernel/sys_c6x.c b/arch/c6x/kernel/sys_c6x.c
index 3e9bdfbee8ad..a742ae259239 100644
--- a/arch/c6x/kernel/sys_c6x.c
+++ b/arch/c6x/kernel/sys_c6x.c
@@ -23,7 +23,7 @@ int _access_ok(unsigned long addr, unsigned long size)
 	if (!addr || addr > (0xffffffffUL - (size - 1)))
 		goto _bad_access;
 
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (uaccess_kernel())
 		return 1;
 
 	if (memory_start <= addr && (addr + size - 1) < memory_end)
diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S
index a1a5c166bc9b..29ebea49ddd5 100644
--- a/arch/c6x/kernel/vmlinux.lds.S
+++ b/arch/c6x/kernel/vmlinux.lds.S
@@ -128,6 +128,8 @@ SECTIONS
 		. = ALIGN(8);
 	}
 
+	BUG_TABLE
+
 	_edata = .;
 
 	__bss_start = .;
diff --git a/arch/c6x/platforms/timer64.c b/arch/c6x/platforms/timer64.c
index c19901e5f055..0bd0452ded80 100644
--- a/arch/c6x/platforms/timer64.c
+++ b/arch/c6x/platforms/timer64.c
@@ -234,7 +234,9 @@ void __init timer64_init(void)
 	clockevents_calc_mult_shift(cd, c6x_core_freq / TIMER_DIVISOR, 5);
 
 	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
+	cd->max_delta_ticks	= 0x7fffffff;
 	cd->min_delta_ns	= clockevent_delta2ns(250, cd);
+	cd->min_delta_ticks	= 250;
 
 	cd->cpumask		= cpumask_of(smp_processor_id());
 
diff --git a/arch/cris/arch-v10/lib/usercopy.c b/arch/cris/arch-v10/lib/usercopy.c
index 1ba7cc000dfc..48fa37fe0f9b 100644
--- a/arch/cris/arch-v10/lib/usercopy.c
+++ b/arch/cris/arch-v10/lib/usercopy.c
@@ -188,11 +188,10 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, unsigned long pn)
 }
 EXPORT_SYMBOL(__copy_user);
 
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
-   userland.  The return-value is the number of bytes that were
+/* Copy from user to kernel.  The return-value is the number of bytes that were
    inaccessible.  */
 
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
+unsigned long __copy_user_in(void *pdst, const void __user *psrc,
 				  unsigned long pn)
 {
   /* We want the parameters put in special registers.
@@ -217,19 +216,17 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
     {
       __asm_copy_from_user_1 (dst, src, retn);
       n--;
+      if (retn)
+         goto exception;
     }
 
     if (((unsigned long) src & 2) && n >= 2)
     {
       __asm_copy_from_user_2 (dst, src, retn);
       n -= 2;
+      if (retn)
+         goto exception;
     }
-
-    /* We only need one check after the unalignment-adjustments, because
-       if both adjustments were done, either both or neither reference
-       had an exception.  */
-    if (retn != 0)
-      goto copy_exception_bytes;
   }
 
   /* Decide which copying method to use. */
@@ -328,7 +325,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
     n -= 4;
 
     if (retn)
-      goto copy_exception_bytes;
+      goto exception;
   }
 
   /* If we get here, there were no memory read faults.  */
@@ -356,20 +353,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
      bytes.  */
   return retn;
 
-copy_exception_bytes:
-  /* We already have "retn" bytes cleared, and need to clear the
-     remaining "n" bytes.  A non-optimized simple byte-for-byte in-line
-     memset is preferred here, since this isn't speed-critical code and
-     we'd rather have this a leaf-function than calling memset.  */
-  {
-    char *endp;
-    for (endp = dst + n; dst < endp; dst++)
-      *dst = 0;
-  }
-
+exception:
   return retn + n;
 }
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(__copy_user_in);
 
 /* Zero userspace.  */
 unsigned long __do_clear_user(void __user *pto, unsigned long pn)
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index ae6903d7fdbe..14970f11bbf2 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void)
 		dma_in_cfg.en = regk_dma_no;
 		REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg);
 
-		/* Disble the cryptocop. */
+		/* Disable the cryptocop. */
 		rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg);
 		rw_cfg.en = 0;
 		REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg);
diff --git a/arch/cris/arch-v32/lib/usercopy.c b/arch/cris/arch-v32/lib/usercopy.c
index 05e58dab800d..20b608026913 100644
--- a/arch/cris/arch-v32/lib/usercopy.c
+++ b/arch/cris/arch-v32/lib/usercopy.c
@@ -156,10 +156,9 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, unsigned long pn)
 }
 EXPORT_SYMBOL(__copy_user);
 
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
-   userland.  The return-value is the number of bytes that were
+/* Copy from user to kernel.  The return-value is the number of bytes that were
    inaccessible.  */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
+unsigned long __copy_user_in(void *pdst, const void __user *psrc,
 				  unsigned long pn)
 {
   /* We want the parameters put in special registers.
@@ -184,19 +183,18 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
     {
       __asm_copy_from_user_1 (dst, src, retn);
       n--;
+      if (retn != 0)
+        goto exception;
     }
 
     if (((unsigned long) src & 2) && n >= 2)
     {
       __asm_copy_from_user_2 (dst, src, retn);
       n -= 2;
+      if (retn != 0)
+        goto exception;
     }
 
-    /* We only need one check after the unalignment-adjustments, because
-       if both adjustments were done, either both or neither reference
-       had an exception.  */
-    if (retn != 0)
-      goto copy_exception_bytes;
   }
 
   /* Movem is dirt cheap.  The overheap is low enough to always use the
@@ -279,7 +277,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
     n -= 4;
 
     if (retn)
-      goto copy_exception_bytes;
+      goto exception;
   }
 
   /* If we get here, there were no memory read faults.  */
@@ -307,20 +305,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
      bytes.  */
   return retn;
 
-copy_exception_bytes:
-  /* We already have "retn" bytes cleared, and need to clear the
-     remaining "n" bytes.  A non-optimized simple byte-for-byte in-line
-     memset is preferred here, since this isn't speed-critical code and
-     we'd rather have this a leaf-function than calling memset.  */
-  {
-    char *endp;
-    for (endp = dst + n; dst < endp; dst++)
-      *dst = 0;
-  }
-
+exception:
   return retn + n;
 }
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(__copy_user_in);
 
 /* Zero userspace.  */
 unsigned long __do_clear_user(void __user *pto, unsigned long pn)
diff --git a/arch/cris/include/arch-v10/arch/uaccess.h b/arch/cris/include/arch-v10/arch/uaccess.h
index 65b02d9b605a..5477c98c2281 100644
--- a/arch/cris/include/arch-v10/arch/uaccess.h
+++ b/arch/cris/include/arch-v10/arch/uaccess.h
@@ -172,16 +172,14 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_user_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"	\
 		"2:	move.b $r9,[%0+]\n",	\
-		"3:	addq 1,%2\n"		\
-		"	clear.b [%0+]\n",	\
+		"3:	addq 1,%2\n",		\
 		"	.dword 2b,3b\n")
 
 #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	move.w [%1+],$r9\n"		\
 		"2:	move.w $r9,[%0+]\n" COPY,	\
-		"3:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n" FIXUP,		\
+		"3:	addq 2,%2\n" FIXUP,		\
 		"	.dword 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_2(to, from, ret) \
@@ -191,16 +189,14 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_2x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"4:	move.b $r9,[%0+]\n",		\
-		"5:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"5:	addq 1,%2\n",			\
 		"	.dword 4b,5b\n")
 
 #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	move.d [%1+],$r9\n"		\
 		"2:	move.d $r9,[%0+]\n" COPY,	\
-		"3:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n" FIXUP,		\
+		"3:	addq 4,%2\n" FIXUP,		\
 		"	.dword 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_4(to, from, ret) \
@@ -210,8 +206,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_4x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"4:	move.b $r9,[%0+]\n",		\
-		"5:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"5:	addq 1,%2\n",			\
 		"	.dword 4b,5b\n")
 
 #define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -219,7 +214,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.w [%1+],$r9\n"		\
 		"4:	move.w $r9,[%0+]\n" COPY,	\
 		"5:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 4b,5b\n" TENTRY)
 
 #define __asm_copy_from_user_6(to, from, ret) \
@@ -229,8 +224,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_6x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"6:	move.b $r9,[%0+]\n",		\
-		"7:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"7:	addq 1,%2\n",			\
 		"	.dword 6b,7b\n")
 
 #define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -238,7 +232,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.d [%1+],$r9\n"		\
 		"4:	move.d $r9,[%0+]\n" COPY,	\
 		"5:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 4b,5b\n" TENTRY)
 
 #define __asm_copy_from_user_8(to, from, ret) \
@@ -248,8 +242,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_8x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"6:	move.b $r9,[%0+]\n",		\
-		"7:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"7:	addq 1,%2\n",			\
 		"	.dword 6b,7b\n")
 
 #define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -257,7 +250,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.w [%1+],$r9\n"		\
 		"6:	move.w $r9,[%0+]\n" COPY,	\
 		"7:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 6b,7b\n" TENTRY)
 
 #define __asm_copy_from_user_10(to, from, ret) \
@@ -267,8 +260,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_10x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"8:	move.b $r9,[%0+]\n",		\
-		"9:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"9:	addq 1,%2\n",			\
 		"	.dword 8b,9b\n")
 
 #define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -276,7 +268,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.d [%1+],$r9\n"		\
 		"6:	move.d $r9,[%0+]\n" COPY,	\
 		"7:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 6b,7b\n" TENTRY)
 
 #define __asm_copy_from_user_12(to, from, ret) \
@@ -286,8 +278,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_12x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"8:	move.b $r9,[%0+]\n",		\
-		"9:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"9:	addq 1,%2\n",			\
 		"	.dword 8b,9b\n")
 
 #define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -295,7 +286,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.w [%1+],$r9\n"		\
 		"8:	move.w $r9,[%0+]\n" COPY,	\
 		"9:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 8b,9b\n" TENTRY)
 
 #define __asm_copy_from_user_14(to, from, ret) \
@@ -305,8 +296,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_14x_cont(to, from, ret,	\
 		"	move.b [%1+],$r9\n"		\
 		"10:	move.b $r9,[%0+]\n",		\
-		"11:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"11:	addq 1,%2\n",			\
 		"	.dword 10b,11b\n")
 
 #define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -314,7 +304,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.d [%1+],$r9\n"		\
 		"8:	move.d $r9,[%0+]\n" COPY,	\
 		"9:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 8b,9b\n" TENTRY)
 
 #define __asm_copy_from_user_16(to, from, ret) \
@@ -325,7 +315,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.d [%1+],$r9\n"		\
 		"10:	move.d $r9,[%0+]\n" COPY,	\
 		"11:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 10b,11b\n" TENTRY)
 
 #define __asm_copy_from_user_20(to, from, ret) \
@@ -336,7 +326,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.d [%1+],$r9\n"		\
 		"12:	move.d $r9,[%0+]\n" COPY,	\
 		"13:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n" FIXUP,		\
+			FIXUP,				\
 		"	.dword 12b,13b\n" TENTRY)
 
 #define __asm_copy_from_user_24(to, from, ret) \
diff --git a/arch/cris/include/arch-v32/arch/uaccess.h b/arch/cris/include/arch-v32/arch/uaccess.h
index 3196019706cb..dc2ce090f624 100644
--- a/arch/cris/include/arch-v32/arch/uaccess.h
+++ b/arch/cris/include/arch-v32/arch/uaccess.h
@@ -178,8 +178,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"2:	move.b [%1+],$acr\n"	\
 		"	move.b $acr,[%0+]\n",	\
 		"3:	addq 1,%2\n"		\
-		"	jump 1b\n"		\
-		"	clear.b [%0+]\n",	\
+		"	jump 1b\n",		\
 		"	.dword 2b,3b\n")
 
 #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -189,8 +188,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.w $acr,[%0+]\n",		\
 			FIXUP				\
 		"3:	addq 2,%2\n"			\
-		"	jump 1b\n"			\
-		"	clear.w [%0+]\n",		\
+		"	jump 1b\n",			\
 			TENTRY				\
 		"	.dword 2b,3b\n")
 
@@ -201,8 +199,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_2x_cont(to, from, ret,	\
 		"4:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"5:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"5:	addq 1,%2\n",			\
 		"	.dword 4b,5b\n")
 
 #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -212,8 +209,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"	move.d $acr,[%0+]\n",		\
 			FIXUP				\
 		"3:	addq 4,%2\n"			\
-		"	jump 1b\n"			\
-		"	clear.d [%0+]\n",		\
+		"	jump 1b\n",			\
 			TENTRY				\
 		"	.dword 2b,3b\n")
 
@@ -224,8 +220,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_4x_cont(to, from, ret,	\
 		"4:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"5:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"5:	addq 1,%2\n",			\
 		"	.dword 4b,5b\n")
 
 #define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -234,8 +229,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"4:	move.w [%1+],$acr\n"		\
 		"	move.w $acr,[%0+]\n",		\
 			FIXUP				\
-		"5:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n",		\
+		"5:	addq 2,%2\n",			\
 			TENTRY				\
 		"	.dword 4b,5b\n")
 
@@ -246,8 +240,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_6x_cont(to, from, ret,	\
 		"6:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"7:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"7:	addq 1,%2\n",			\
 		"	.dword 6b,7b\n")
 
 #define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -256,8 +249,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"4:	move.d [%1+],$acr\n"		\
 		"	move.d $acr,[%0+]\n",		\
 			FIXUP				\
-		"5:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n",		\
+		"5:	addq 4,%2\n",			\
 			TENTRY				\
 		"	.dword 4b,5b\n")
 
@@ -268,8 +260,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_8x_cont(to, from, ret,	\
 		"6:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"7:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"7:	addq 1,%2\n",			\
 		"	.dword 6b,7b\n")
 
 #define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -278,8 +269,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"6:	move.w [%1+],$acr\n"		\
 		"	move.w $acr,[%0+]\n",		\
 			FIXUP				\
-		"7:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n",		\
+		"7:	addq 2,%2\n",			\
 			TENTRY				\
 		"	.dword 6b,7b\n")
 
@@ -290,8 +280,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_10x_cont(to, from, ret,	\
 		"8:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"9:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"9:	addq 1,%2\n",			\
 		"	.dword 8b,9b\n")
 
 #define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -300,8 +289,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"6:	move.d [%1+],$acr\n"		\
 		"	move.d $acr,[%0+]\n",		\
 			FIXUP				\
-		"7:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n",		\
+		"7:	addq 4,%2\n",			\
 			TENTRY				\
 		"	.dword 6b,7b\n")
 
@@ -312,8 +300,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_12x_cont(to, from, ret,	\
 		"8:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"9:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"9:	addq 1,%2\n",			\
 		"	.dword 8b,9b\n")
 
 #define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -322,8 +309,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"8:	move.w [%1+],$acr\n"		\
 		"	move.w $acr,[%0+]\n",		\
 			FIXUP				\
-		"9:	addq 2,%2\n"			\
-		"	clear.w [%0+]\n",		\
+		"9:	addq 2,%2\n",			\
 			TENTRY				\
 		"	.dword 8b,9b\n")
 
@@ -334,8 +320,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 	__asm_copy_from_user_14x_cont(to, from, ret,	\
 		"10:	move.b [%1+],$acr\n"		\
 		"	move.b $acr,[%0+]\n",		\
-		"11:	addq 1,%2\n"			\
-		"	clear.b [%0+]\n",		\
+		"11:	addq 1,%2\n",			\
 		"	.dword 10b,11b\n")
 
 #define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
@@ -344,8 +329,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"8:	move.d [%1+],$acr\n"		\
 		"	move.d $acr,[%0+]\n",		\
 			FIXUP				\
-		"9:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n",		\
+		"9:	addq 4,%2\n",			\
 			TENTRY				\
 		"	.dword 8b,9b\n")
 
@@ -358,8 +342,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"10:	move.d [%1+],$acr\n"		\
 		"	move.d $acr,[%0+]\n",		\
 			FIXUP				\
-		"11:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n",		\
+		"11:	addq 4,%2\n",			\
 			TENTRY				\
 		"	.dword 10b,11b\n")
 
@@ -372,8 +355,7 @@ __do_strncpy_from_user(char *dst, const char *src, long count)
 		"12:	move.d [%1+],$acr\n"		\
 		"	move.d $acr,[%0+]\n",		\
 			FIXUP				\
-		"13:	addq 4,%2\n"			\
-		"	clear.d [%0+]\n",		\
+		"13:	addq 4,%2\n",			\
 			TENTRY				\
 		"	.dword 12b,13b\n")
 
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 0f5132b08896..2890099992a9 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += device.h
 generic-y += div64.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += emergency-restart.h
 generic-y += fcntl.h
 generic-y += futex.h
diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h
index 2a3210ba4c72..fa3a73004cc5 100644
--- a/arch/cris/include/asm/pgtable.h
+++ b/arch/cris/include/asm/pgtable.h
@@ -6,6 +6,7 @@
 #define _CRIS_PGTABLE_H
 
 #include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/cris/include/asm/uaccess.h b/arch/cris/include/asm/uaccess.h
index 56c7d5750abd..0d473aec3066 100644
--- a/arch/cris/include/asm/uaccess.h
+++ b/arch/cris/include/asm/uaccess.h
@@ -15,15 +15,9 @@
 #ifndef _CRIS_UACCESS_H
 #define _CRIS_UACCESS_H
 
-#ifndef __ASSEMBLY__
-#include <linux/sched.h>
-#include <linux/errno.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 /*
  * The fs value determines whether argument validity checking should be
  * performed or not.  If get_fs() == USER_DS, checking is performed, with
@@ -49,30 +43,14 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
 #define __user_ok(addr, size) \
 	(((size) <= TASK_SIZE) && ((addr) <= TASK_SIZE-(size)))
 #define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr), (size))
 
 #include <arch/uaccess.h>
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
+#include <asm/extable.h>
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -191,7 +169,7 @@ extern long __get_user_bad(void);
    live in lib/usercopy.c  */
 
 extern unsigned long __copy_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
+extern unsigned long __copy_user_in(void *to, const void __user *from, unsigned long n);
 extern unsigned long __do_clear_user(void __user *to, unsigned long n);
 
 static inline long
@@ -258,7 +236,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_from_user_24(to, from, ret);
 	else
-		ret = __copy_user_zeroing(to, from, n);
+		ret = __copy_user_in(to, from, n);
 
 	return ret;
 }
@@ -358,64 +336,33 @@ static inline size_t clear_user(void __user *to, size_t n)
 		return __do_clear_user(to, n);
 }
 
-static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (unlikely(!access_ok(VERIFY_READ, from, n))) {
-		memset(to, 0, n);
-		return n;
-	}
 	if (__builtin_constant_p(n))
 		return __constant_copy_from_user(to, from, n);
 	else
-		return __copy_user_zeroing(to, from, n);
+		return __copy_user_in(to, from, n);
 }
 
-static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
-		return n;
 	if (__builtin_constant_p(n))
 		return __constant_copy_to_user(to, from, n);
 	else
 		return __copy_user(to, from, n);
 }
 
-/* We let the __ versions of copy_from/to_user inline, because they're often
- * used in fast paths and have only a small space overhead.
- */
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 static inline unsigned long
-__generic_copy_from_user_nocheck(void *to, const void __user *from,
-				 unsigned long n)
-{
-	return __copy_user_zeroing(to, from, n);
-}
-
-static inline unsigned long
-__generic_copy_to_user_nocheck(void __user *to, const void *from,
-			       unsigned long n)
-{
-	return __copy_user(to, from, n);
-}
-
-static inline unsigned long
-__generic_clear_user_nocheck(void __user *to, unsigned long n)
+__clear_user(void __user *to, unsigned long n)
 {
 	return __do_clear_user(to, n);
 }
 
-/* without checking */
-
-#define __copy_to_user(to, from, n) \
-	__generic_copy_to_user_nocheck((to), (from), (n))
-#define __copy_from_user(to, from, n) \
-	__generic_copy_from_user_nocheck((to), (from), (n))
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-#define __clear_user(to, n) __generic_clear_user_nocheck((to), (n))
-
 #define strlen_user(str)	strnlen_user((str), 0x7ffffffe)
 
-#endif  /* __ASSEMBLY__ */
-
 #endif	/* _CRIS_UACCESS_H */
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 979586261520..867f237d7c5c 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -68,6 +68,8 @@ SECTIONS
 	__edata = . ;			/* End of data section. */
 	_edata = . ;
 
+	BUG_TABLE
+
 	INIT_TASK_DATA_SECTION(PAGE_SIZE)
 
 	. = ALIGN(PAGE_SIZE);		/* Init code and data. */
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index c33b46715f65..cce3bc3603ea 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,6 +1,7 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h
index a0513d463a1f..ab6e7e961b54 100644
--- a/arch/frv/include/asm/pgtable.h
+++ b/arch/frv/include/asm/pgtable.h
@@ -16,6 +16,7 @@
 #ifndef _ASM_PGTABLE_H
 #define _ASM_PGTABLE_H
 
+#include <asm-generic/5level-fixup.h>
 #include <asm/mem-layout.h>
 #include <asm/setup.h>
 #include <asm/processor.h>
diff --git a/arch/frv/include/asm/uaccess.h b/arch/frv/include/asm/uaccess.h
index c0f4057eab60..e4e33b4cd3ae 100644
--- a/arch/frv/include/asm/uaccess.h
+++ b/arch/frv/include/asm/uaccess.h
@@ -15,16 +15,13 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/segment.h>
 #include <asm/sections.h>
+#include <asm/extable.h>
 
 #define __ptr(x) ((unsigned long __force *)(x))
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 /*
  * check that a range of addresses falls within the current address limit
  */
@@ -63,26 +60,6 @@ static inline int ___range_ok(unsigned long addr, unsigned long size)
 #define access_ok(type,addr,size) (__range_ok((void __user *)(addr), (size)) == 0)
 #define __access_ok(addr,size) (__range_ok((addr), (size)) == 0)
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise.  */
-extern unsigned long search_exception_table(unsigned long);
-
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -256,61 +233,50 @@ do {							\
 /*
  *
  */
+
 #define ____force(x) (__force void *)(void __user *)(x)
 #ifdef CONFIG_MMU
 extern long __memset_user(void *dst, unsigned long count);
 extern long __memcpy_user(void *dst, const void *src, unsigned long count);
 
 #define __clear_user(dst,count)			__memset_user(____force(dst), (count))
-#define __copy_from_user_inatomic(to, from, n)	__memcpy_user((to), ____force(from), (n))
-#define __copy_to_user_inatomic(to, from, n)	__memcpy_user(____force(to), (from), (n))
 
 #else
 
 #define __clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
-#define __copy_from_user_inatomic(to, from, n)	(memcpy((to), ____force(from), (n)), 0)
-#define __copy_to_user_inatomic(to, from, n)	(memcpy(____force(to), (from), (n)), 0)
 
 #endif
 
-static inline unsigned long __must_check
-clear_user(void __user *to, unsigned long n)
-{
-	if (likely(__access_ok(to, n)))
-		n = __clear_user(to, n);
-	return n;
-}
-
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-       might_fault();
-       return __copy_to_user_inatomic(to, from, n);
-}
-
 static inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-       might_fault();
-       return __copy_from_user_inatomic(to, from, n);
+#ifdef CONFIG_MMU
+	return __memcpy_user(to, (__force const void *)from, n);
+#else
+	memcpy(to, (__force const void *)from, n);
+	return 0;
+#endif
 }
 
-static inline long copy_from_user(void *to, const void __user *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret = n;
-
-	if (likely(__access_ok(from, n)))
-		ret = __copy_from_user(to, from, n);
-
-	if (unlikely(ret != 0))
-		memset(to + (n - ret), 0, ret);
-
-	return ret;
+#ifdef CONFIG_MMU
+	return __memcpy_user((__force void *)to, from, n);
+#else
+	memcpy((__force void *)to, from, n);
+	return 0;
+#endif
 }
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
 
-static inline long copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
 {
-	return likely(__access_ok(to, n)) ? __copy_to_user(to, from, n) : n;
+	if (likely(__access_ok(to, n)))
+		n = __clear_user(to, n);
+	return n;
 }
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
@@ -318,6 +284,4 @@ extern long strnlen_user(const char __user *src, long count);
 
 #define strlen_user(str) strnlen_user(str, 32767)
 
-extern unsigned long search_exception_table(unsigned long addr);
-
 #endif /* _ASM_UACCESS_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 81e03530ed39..1ccf45657472 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -92,5 +92,11 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c
index ce29991e4219..fb08ebe0dab4 100644
--- a/arch/frv/kernel/traps.c
+++ b/arch/frv/kernel/traps.c
@@ -360,13 +360,8 @@ asmlinkage void memory_access_exception(unsigned long esr0,
 	siginfo_t info;
 
 #ifdef CONFIG_MMU
-	unsigned long fixup;
-
-	fixup = search_exception_table(__frame->pc);
-	if (fixup) {
-		__frame->pc = fixup;
+	if (fixup_exception(__frame))
 		return;
-	}
 #endif
 
 	die_if_kernel("-- Memory Access Exception --\n"
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index aa6e573d57da..3f44dcbbad4d 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/arch/frv/kernel/vmlinux.lds.S
@@ -102,6 +102,8 @@ SECTIONS
 
   _edata = .;			/* End of data section */
 
+  BUG_TABLE
+
   /* GP section */
   . = ALIGN(L1_CACHE_BYTES);
   _gp = . + 2048;
diff --git a/arch/frv/mm/extable.c b/arch/frv/mm/extable.c
index a0e8b3e03e4c..9198ddd16092 100644
--- a/arch/frv/mm/extable.c
+++ b/arch/frv/mm/extable.c
@@ -10,40 +10,39 @@ extern const void __memset_end, __memset_user_error_lr, __memset_user_error_hand
 extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
 extern spinlock_t modlist_lock;
 
-
-/*****************************************************************************/
-/*
- * see if there's a fixup handler available to deal with a kernel fault
- */
-unsigned long search_exception_table(unsigned long pc)
+int fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *extab;
+	unsigned long pc = regs->pc;
 
 	/* determine if the fault lay during a memcpy_user or a memset_user */
-	if (__frame->lr == (unsigned long) &__memset_user_error_lr &&
+	if (regs->lr == (unsigned long) &__memset_user_error_lr &&
 	    (unsigned long) &memset <= pc && pc < (unsigned long) &__memset_end
 	    ) {
 		/* the fault occurred in a protected memset
 		 * - we search for the return address (in LR) instead of the program counter
 		 * - it was probably during a clear_user()
 		 */
-		return (unsigned long) &__memset_user_error_handler;
+		regs->pc = (unsigned long) &__memset_user_error_handler;
+		return 1;
 	}
 
-	if (__frame->lr == (unsigned long) &__memcpy_user_error_lr &&
+	if (regs->lr == (unsigned long) &__memcpy_user_error_lr &&
 	    (unsigned long) &memcpy <= pc && pc < (unsigned long) &__memcpy_end
 	    ) {
 		/* the fault occurred in a protected memset
 		 * - we search for the return address (in LR) instead of the program counter
 		 * - it was probably during a copy_to/from_user()
 		 */
-		return (unsigned long) &__memcpy_user_error_handler;
+		regs->pc = (unsigned long) &__memcpy_user_error_handler;
+		return 1;
 	}
 
 	extab = search_exception_tables(pc);
-	if (extab)
-		return extab->fixup;
+	if (extab) {
+		regs->pc = extab->fixup;
+		return 1;
+	}
 
 	return 0;
-
-} /* end search_exception_table() */
+}
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 614a46c413d2..179e79e220e5 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -33,7 +33,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
-	unsigned long _pme, lrai, lrad, fixup;
+	unsigned long _pme, lrai, lrad;
 	unsigned long flags = 0;
 	siginfo_t info;
 	pgd_t *pge;
@@ -201,10 +201,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 
  no_context:
 	/* are we prepared to handle this kernel fault? */
-	if ((fixup = search_exception_table(__frame->pc)) != 0) {
-		__frame->pc = fixup;
+	if (fixup_exception(__frame))
 		return;
-	}
 
 /*
  * Oops. The kernel tried to access some bad page. We'll have to
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 341740c3581c..757cdeb24e6e 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
@@ -68,7 +69,6 @@ generic-y += tlbflush.h
 generic-y += trace_clock.h
 generic-y += topology.h
 generic-y += types.h
-generic-y += uaccess.h
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += vga.h
diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h
index 8341db67821d..7d265d28ba5e 100644
--- a/arch/h8300/include/asm/pgtable.h
+++ b/arch/h8300/include/asm/pgtable.h
@@ -1,5 +1,6 @@
 #ifndef _H8300_PGTABLE_H
 #define _H8300_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm-generic/pgtable.h>
 #define pgtable_cache_init()   do { } while (0)
diff --git a/arch/h8300/include/asm/uaccess.h b/arch/h8300/include/asm/uaccess.h
new file mode 100644
index 000000000000..6f6144a240ce
--- /dev/null
+++ b/arch/h8300/include/asm/uaccess.h
@@ -0,0 +1,54 @@
+#ifndef _ASM_UACCESS_H
+#define _ASM_UACCESS_H
+
+#include <linux/string.h>
+
+static inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user * from, unsigned long n)
+{
+	if (__builtin_constant_p(n)) {
+		switch(n) {
+		case 1:
+			*(u8 *)to = *(u8 __force *)from;
+			return 0;
+		case 2:
+			*(u16 *)to = *(u16 __force *)from;
+			return 0;
+		case 4:
+			*(u32 *)to = *(u32 __force *)from;
+			return 0;
+		}
+	}
+
+	memcpy(to, (const void __force *)from, n);
+	return 0;
+}
+
+static inline __must_check unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (__builtin_constant_p(n)) {
+		switch(n) {
+		case 1:
+			*(u8 __force *)to = *(u8 *)from;
+			return 0;
+		case 2:
+			*(u16 __force *)to = *(u16 *)from;
+			return 0;
+		case 4:
+			*(u32 __force *)to = *(u32 *)from;
+			return 0;
+		default:
+			break;
+		}
+	}
+
+	memcpy((void __force *)to, from, n);
+	return 0;
+}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
+
+#include <asm-generic/uaccess.h>
+
+#endif
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
index 92075544a19a..0dc1c8f622bc 100644
--- a/arch/h8300/kernel/ptrace.c
+++ b/arch/h8300/kernel/ptrace.c
@@ -95,7 +95,8 @@ static int regs_get(struct task_struct *target,
 	long *reg = (long *)&regs;
 
 	/* build user regs in buffer */
-	for (r = 0; r < ARRAY_SIZE(register_offset); r++)
+	BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0);
+	for (r = 0; r < sizeof(regs) / sizeof(long); r++)
 		*reg++ = h8300_get_reg(target, r);
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
@@ -113,7 +114,8 @@ static int regs_set(struct task_struct *target,
 	long *reg;
 
 	/* build user regs in buffer */
-	for (reg = (long *)&regs, r = 0; r < ARRAY_SIZE(register_offset); r++)
+	BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0);
+	for (reg = (long *)&regs, r = 0; r < sizeof(regs) / sizeof(long); r++)
 		*reg++ = h8300_get_reg(target, r);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
@@ -122,7 +124,7 @@ static int regs_set(struct task_struct *target,
 		return ret;
 
 	/* write back to pt_regs */
-	for (reg = (long *)&regs, r = 0; r < ARRAY_SIZE(register_offset); r++)
+	for (reg = (long *)&regs, r = 0; r < sizeof(regs) / sizeof(long); r++)
 		h8300_put_reg(target, r, *reg++);
 	return 0;
 }
diff --git a/arch/h8300/kernel/ptrace_h.c b/arch/h8300/kernel/ptrace_h.c
index fe3b5673baba..f5ff3b794c85 100644
--- a/arch/h8300/kernel/ptrace_h.c
+++ b/arch/h8300/kernel/ptrace_h.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <asm/ptrace.h>
 
 #define BREAKINST 0x5730 /* trapa #3 */
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 797b64a4b80b..a2036bfda8af 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -11,6 +11,7 @@ generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h
index 49eab8136ec3..24a9177fb897 100644
--- a/arch/hexagon/include/asm/pgtable.h
+++ b/arch/hexagon/include/asm/pgtable.h
@@ -26,6 +26,7 @@
  */
 #include <linux/swap.h>
 #include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* A handy thing to have if one has the RAM. Declared in head.S */
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index f61cfb28e9f2..458b69886b34 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -23,7 +23,6 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/segment.h>
 #include <asm/sections.h>
@@ -50,8 +49,6 @@
  * reasonably simple and not *too* slow.  After all, we've got the
  * MMU for backup.
  */
-#define VERIFY_READ     0
-#define VERIFY_WRITE    1
 
 #define __access_ok(addr, size) \
 	((get_fs().seg == KERNEL_DS.seg) || \
@@ -68,19 +65,12 @@
  */
 
 /*  Assembly somewhat optimized copy routines  */
-unsigned long __copy_from_user_hexagon(void *to, const void __user *from,
+unsigned long raw_copy_from_user(void *to, const void __user *from,
 				     unsigned long n);
-unsigned long __copy_to_user_hexagon(void __user *to, const void *from,
+unsigned long raw_copy_to_user(void __user *to, const void *from,
 				   unsigned long n);
-
-#define __copy_from_user(to, from, n) __copy_from_user_hexagon(to, from, n)
-#define __copy_to_user(to, from, n) __copy_to_user_hexagon(to, from, n)
-
-/*
- * XXX todo: some additonal performance gain is possible by
- * implementing __copy_to/from_user_inatomic, which is much
- * like __copy_to/from_user, but performs slightly less checking.
- */
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 __kernel_size_t __clear_user_hexagon(void __user *dest, unsigned long count);
 #define __clear_user(a, s) __clear_user_hexagon((a), (s))
@@ -107,10 +97,14 @@ static inline long hexagon_strncpy_from_user(char *dst, const char __user *src,
 		return -EFAULT;
 
 	if (res > n) {
-		copy_from_user(dst, src, n);
+		long left = raw_copy_from_user(dst, src, n);
+		if (unlikely(left))
+			memset(dst + (n - left), 0, left);
 		return n;
 	} else {
-		copy_from_user(dst, src, res);
+		long left = raw_copy_from_user(dst, src, res);
+		if (unlikely(left))
+			memset(dst + (res - left), 0, left);
 		return res-1;
 	}
 }
diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c
index af9dec4c28eb..00bcad9cbd8f 100644
--- a/arch/hexagon/kernel/hexagon_ksyms.c
+++ b/arch/hexagon/kernel/hexagon_ksyms.c
@@ -25,8 +25,8 @@
 
 /* Additional functions */
 EXPORT_SYMBOL(__clear_user_hexagon);
-EXPORT_SYMBOL(__copy_from_user_hexagon);
-EXPORT_SYMBOL(__copy_to_user_hexagon);
+EXPORT_SYMBOL(raw_copy_from_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__strnlen_user);
 EXPORT_SYMBOL(__vmgetie);
diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c
index ff4e9bf995e9..29b1f57116c8 100644
--- a/arch/hexagon/kernel/time.c
+++ b/arch/hexagon/kernel/time.c
@@ -199,7 +199,9 @@ void __init time_init_deferred(void)
 	clockevents_calc_mult_shift(ce_dev, sleep_clk_freq, 4);
 
 	ce_dev->max_delta_ns = clockevent_delta2ns(0x7fffffff, ce_dev);
+	ce_dev->max_delta_ticks = 0x7fffffff;
 	ce_dev->min_delta_ns = clockevent_delta2ns(0xf, ce_dev);
+	ce_dev->min_delta_ticks = 0xf;
 
 #ifdef CONFIG_SMP
 	setup_percpu_clockdev();
diff --git a/arch/hexagon/mm/copy_from_user.S b/arch/hexagon/mm/copy_from_user.S
index 7fc94f3e6642..7da066fbd16f 100644
--- a/arch/hexagon/mm/copy_from_user.S
+++ b/arch/hexagon/mm/copy_from_user.S
@@ -44,7 +44,7 @@
 #define bytes r2
 #define loopcount r5
 
-#define FUNCNAME __copy_from_user_hexagon
+#define FUNCNAME raw_copy_from_user
 #include "copy_user_template.S"
 
 	/* LOAD FAULTS from COPY_FROM_USER */
diff --git a/arch/hexagon/mm/copy_to_user.S b/arch/hexagon/mm/copy_to_user.S
index 0cfbcc09d1d9..a7b7f8db21df 100644
--- a/arch/hexagon/mm/copy_to_user.S
+++ b/arch/hexagon/mm/copy_to_user.S
@@ -43,7 +43,7 @@
 #define bytes r2
 #define loopcount r5
 
-#define FUNCNAME __copy_to_user_hexagon
+#define FUNCNAME raw_copy_to_user
 #include "copy_user_template.S"
 
 	/* STORE FAULTS from COPY_TO_USER */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 18ca6a9ce566..6a15083cc366 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -52,7 +52,6 @@ config IA64
 	select MODULES_USE_ELF_RELA
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_ARCH_HARDENED_USERCOPY
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/ia64/include/asm/asm-prototypes.h b/arch/ia64/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..a2c139808cfe
--- /dev/null
+++ b/arch/ia64/include/asm/asm-prototypes.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_IA64_ASM_PROTOTYPES_H
+#define _ASM_IA64_ASM_PROTOTYPES_H
+
+#include <asm/cacheflush.h>
+#include <asm/checksum.h>
+#include <asm/esi.h>
+#include <asm/ftrace.h>
+#include <asm/page.h>
+#include <asm/pal.h>
+#include <asm/string.h>
+#include <asm/uaccess.h>
+#include <asm/unwind.h>
+#include <asm/xor.h>
+
+extern const char ia64_ivt[];
+
+signed int __divsi3(signed int, unsigned int);
+signed int __modsi3(signed int, unsigned int);
+
+signed long long __divdi3(signed long long, unsigned long long);
+signed long long __moddi3(signed long long, unsigned long long);
+
+unsigned int __udivsi3(unsigned int, unsigned int);
+unsigned int __umodsi3(unsigned int, unsigned int);
+
+unsigned long long __udivdi3(unsigned long long, unsigned long long);
+unsigned long long __umoddi3(unsigned long long, unsigned long long);
+
+#endif /* _ASM_IA64_ASM_PROTOTYPES_H */
diff --git a/arch/ia64/include/asm/extable.h b/arch/ia64/include/asm/extable.h
new file mode 100644
index 000000000000..20376e71eab4
--- /dev/null
+++ b/arch/ia64/include/asm/extable.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_IA64_EXTABLE_H
+#define _ASM_IA64_EXTABLE_H
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+struct exception_table_entry {
+	int insn;	/* location-relative address of insn this fixup is for */
+	int fixup;	/* location-relative continuation addr.; if bit 2 is set, r9 is set to 0 */
+};
+
+#endif
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 384794e665fc..6cc22c8d8923 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -587,8 +587,10 @@ extern struct page *zero_page_memmap_ptr;
 
 
 #if CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #endif
+#include <asm-generic/5level-fixup.h>
 #include <asm-generic/pgtable.h>
 
 #endif /* _ASM_IA64_PGTABLE_H */
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 471044be2a3b..82a7646c4416 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -33,14 +33,13 @@
  */
 
 #include <linux/compiler.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/page-flags.h>
 #include <linux/mm.h>
 
 #include <asm/intrinsics.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
+#include <asm/extable.h>
 
 /*
  * For historical reasons, the following macros are grossly misnamed:
@@ -48,9 +47,6 @@
 #define KERNEL_DS	((mm_segment_t) { ~0UL })		/* cf. access_ok() */
 #define USER_DS		((mm_segment_t) { TASK_SIZE-1 })	/* cf. access_ok() */
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define get_ds()  (KERNEL_DS)
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
@@ -63,14 +59,14 @@
  * address TASK_SIZE is never valid.  We also need to make sure that the address doesn't
  * point inside the virtually mapped linear page table.
  */
-#define __access_ok(addr, size, segment)						\
-({											\
-	__chk_user_ptr(addr);								\
-	(likely((unsigned long) (addr) <= (segment).seg)				\
-	 && ((segment).seg == KERNEL_DS.seg						\
-	     || likely(REGION_OFFSET((unsigned long) (addr)) < RGN_MAP_LIMIT)));	\
-})
-#define access_ok(type, addr, size)	__access_ok((addr), (size), get_fs())
+static inline int __access_ok(const void __user *p, unsigned long size)
+{
+	unsigned long addr = (unsigned long)p;
+	unsigned long seg = get_fs().seg;
+	return likely(addr <= seg) &&
+	 (seg == KERNEL_DS.seg || likely(REGION_OFFSET(addr) < RGN_MAP_LIMIT));
+}
+#define access_ok(type, addr, size)	__access_ok((addr), (size))
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -80,8 +76,8 @@
  * (a) re-use the arguments for side effects (sizeof/typeof is ok)
  * (b) require any knowledge of processes at this stage
  */
-#define put_user(x, ptr)	__put_user_check((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr)), get_fs())
-#define get_user(x, ptr)	__get_user_check((x), (ptr), sizeof(*(ptr)), get_fs())
+#define put_user(x, ptr)	__put_user_check((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr)))
+#define get_user(x, ptr)	__get_user_check((x), (ptr), sizeof(*(ptr)))
 
 /*
  * The "__xxx" versions do not do address space checking, useful when
@@ -184,13 +180,13 @@ extern void __get_user_unknown (void);
  * could clobber r8 and r9 (among others).  Thus, be careful not to evaluate it while
  * using r8/r9.
  */
-#define __do_get_user(check, x, ptr, size, segment)					\
+#define __do_get_user(check, x, ptr, size)						\
 ({											\
 	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);				\
 	__typeof__ (size) __gu_size = (size);						\
 	long __gu_err = -EFAULT;							\
 	unsigned long __gu_val = 0;							\
-	if (!check || __access_ok(__gu_ptr, size, segment))				\
+	if (!check || __access_ok(__gu_ptr, size))					\
 		switch (__gu_size) {							\
 		      case 1: __get_user_size(__gu_val, __gu_ptr, 1, __gu_err); break;	\
 		      case 2: __get_user_size(__gu_val, __gu_ptr, 2, __gu_err); break;	\
@@ -202,8 +198,8 @@ extern void __get_user_unknown (void);
 	__gu_err;									\
 })
 
-#define __get_user_nocheck(x, ptr, size)	__do_get_user(0, x, ptr, size, KERNEL_DS)
-#define __get_user_check(x, ptr, size, segment)	__do_get_user(1, x, ptr, size, segment)
+#define __get_user_nocheck(x, ptr, size)	__do_get_user(0, x, ptr, size)
+#define __get_user_check(x, ptr, size)	__do_get_user(1, x, ptr, size)
 
 extern void __put_user_unknown (void);
 
@@ -211,14 +207,14 @@ extern void __put_user_unknown (void);
  * Evaluating arguments X, PTR, SIZE, and SEGMENT may involve subroutine-calls, which
  * could clobber r8 (among others).  Thus, be careful not to evaluate them while using r8.
  */
-#define __do_put_user(check, x, ptr, size, segment)					\
+#define __do_put_user(check, x, ptr, size)						\
 ({											\
 	__typeof__ (x) __pu_x = (x);							\
 	__typeof__ (*(ptr)) __user *__pu_ptr = (ptr);					\
 	__typeof__ (size) __pu_size = (size);						\
 	long __pu_err = -EFAULT;							\
 											\
-	if (!check || __access_ok(__pu_ptr, __pu_size, segment))			\
+	if (!check || __access_ok(__pu_ptr, __pu_size))					\
 		switch (__pu_size) {							\
 		      case 1: __put_user_size(__pu_x, __pu_ptr, 1, __pu_err); break;	\
 		      case 2: __put_user_size(__pu_x, __pu_ptr, 2, __pu_err); break;	\
@@ -229,8 +225,8 @@ extern void __put_user_unknown (void);
 	__pu_err;									\
 })
 
-#define __put_user_nocheck(x, ptr, size)	__do_put_user(0, x, ptr, size, KERNEL_DS)
-#define __put_user_check(x, ptr, size, segment)	__do_put_user(1, x, ptr, size, segment)
+#define __put_user_nocheck(x, ptr, size)	__do_put_user(0, x, ptr, size)
+#define __put_user_check(x, ptr, size)	__do_put_user(1, x, ptr, size)
 
 /*
  * Complex access routines
@@ -239,56 +235,19 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use
 					       unsigned long count);
 
 static inline unsigned long
-__copy_to_user (void __user *to, const void *from, unsigned long count)
+raw_copy_to_user(void __user *to, const void *from, unsigned long count)
 {
-	check_object_size(from, count, true);
-
 	return __copy_user(to, (__force void __user *) from, count);
 }
 
 static inline unsigned long
-__copy_from_user (void *to, const void __user *from, unsigned long count)
+raw_copy_from_user(void *to, const void __user *from, unsigned long count)
 {
-	check_object_size(to, count, false);
-
 	return __copy_user((__force void __user *) to, from, count);
 }
 
-#define __copy_to_user_inatomic		__copy_to_user
-#define __copy_from_user_inatomic	__copy_from_user
-#define copy_to_user(to, from, n)							\
-({											\
-	void __user *__cu_to = (to);							\
-	const void *__cu_from = (from);							\
-	long __cu_len = (n);								\
-											\
-	if (__access_ok(__cu_to, __cu_len, get_fs())) {					\
-		check_object_size(__cu_from, __cu_len, true);			\
-		__cu_len = __copy_user(__cu_to, (__force void __user *)  __cu_from, __cu_len);	\
-	}										\
-	__cu_len;									\
-})
-
-static inline unsigned long
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	check_object_size(to, n, false);
-	if (likely(__access_ok(from, n, get_fs())))
-		n = __copy_user((__force void __user *) to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-
-#define __copy_in_user(to, from, size)	__copy_user((to), (from), (size))
-
-static inline unsigned long
-copy_in_user (void __user *to, const void __user *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_READ, from, n) && access_ok(VERIFY_WRITE, to, n)))
-		n = __copy_user(to, from, n);
-	return n;
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 extern unsigned long __do_clear_user (void __user *, unsigned long);
 
@@ -297,7 +256,7 @@ extern unsigned long __do_clear_user (void __user *, unsigned long);
 #define clear_user(to, n)					\
 ({								\
 	unsigned long __cu_len = (n);				\
-	if (__access_ok(to, __cu_len, get_fs()))		\
+	if (__access_ok(to, __cu_len))				\
 		__cu_len = __do_clear_user(to, __cu_len);	\
 	__cu_len;						\
 })
@@ -313,7 +272,7 @@ extern long __must_check __strncpy_from_user (char *to, const char __user *from,
 ({									\
 	const char __user * __sfu_from = (from);			\
 	long __sfu_ret = -EFAULT;					\
-	if (__access_ok(__sfu_from, 0, get_fs()))			\
+	if (__access_ok(__sfu_from, 0))					\
 		__sfu_ret = __strncpy_from_user((to), __sfu_from, (n));	\
 	__sfu_ret;							\
 })
@@ -325,7 +284,7 @@ extern unsigned long __strlen_user (const char __user *);
 ({							\
 	const char __user *__su_str = (str);		\
 	unsigned long __su_ret = 0;			\
-	if (__access_ok(__su_str, 0, get_fs()))		\
+	if (__access_ok(__su_str, 0))			\
 		__su_ret = __strlen_user(__su_str);	\
 	__su_ret;					\
 })
@@ -341,18 +300,11 @@ extern unsigned long __strnlen_user (const char __user *, long);
 ({								\
 	const char __user *__su_str = (str);			\
 	unsigned long __su_ret = 0;				\
-	if (__access_ok(__su_str, 0, get_fs()))			\
+	if (__access_ok(__su_str, 0))				\
 		__su_ret = __strnlen_user(__su_str, len);	\
 	__su_ret;						\
 })
 
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-struct exception_table_entry {
-	int insn;	/* location-relative address of insn this fixup is for */
-	int fixup;	/* location-relative continuation addr.; if bit 2 is set, r9 is set to 0 */
-};
-
 #define ARCH_HAS_TRANSLATE_MEM_PTR	1
 static __inline__ void *
 xlate_dev_mem_ptr(phys_addr_t p)
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 57feb0c1f7d7..2c3f4b48042a 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -101,4 +101,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 6ab0ae7d6535..d1d945c6bd05 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -153,7 +153,7 @@ slot (const struct insn *insn)
 static int
 apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
 {
-	if (slot(insn) != 2) {
+	if (slot(insn) != 1 && slot(insn) != 2) {
 		printk(KERN_ERR "%s: invalid slot number %d for IMM64\n",
 		       mod->name, slot(insn));
 		return 0;
@@ -165,7 +165,7 @@ apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
 static int
 apply_imm60 (struct module *mod, struct insn *insn, uint64_t val)
 {
-	if (slot(insn) != 2) {
+	if (slot(insn) != 1 && slot(insn) != 2) {
 		printk(KERN_ERR "%s: invalid slot number %d for IMM60\n",
 		       mod->name, slot(insn));
 		return 0;
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index d194d5c83d32..63dc9cdc95c5 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -179,14 +179,14 @@ struct salinfo_platform_oemdata_parms {
 	const u8 *efi_guid;
 	u8 **oemdata;
 	u64 *oemdata_size;
-	int ret;
 };
 
-static void
+static long
 salinfo_platform_oemdata_cpu(void *context)
 {
 	struct salinfo_platform_oemdata_parms *parms = context;
-	parms->ret = salinfo_platform_oemdata(parms->efi_guid, parms->oemdata, parms->oemdata_size);
+
+	return salinfo_platform_oemdata(parms->efi_guid, parms->oemdata, parms->oemdata_size);
 }
 
 static void
@@ -380,16 +380,7 @@ salinfo_log_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static void
-call_on_cpu(int cpu, void (*fn)(void *), void *arg)
-{
-	cpumask_t save_cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-	(*fn)(arg);
-	set_cpus_allowed_ptr(current, &save_cpus_allowed);
-}
-
-static void
+static long
 salinfo_log_read_cpu(void *context)
 {
 	struct salinfo_data *data = context;
@@ -399,6 +390,7 @@ salinfo_log_read_cpu(void *context)
 	/* Clear corrected errors as they are read from SAL */
 	if (rh->severity == sal_log_severity_corrected)
 		ia64_sal_clear_state_info(data->type);
+	return 0;
 }
 
 static void
@@ -430,7 +422,7 @@ retry:
 	spin_unlock_irqrestore(&data_saved_lock, flags);
 
 	if (!data->saved_num)
-		call_on_cpu(cpu, salinfo_log_read_cpu, data);
+		work_on_cpu_safe(cpu, salinfo_log_read_cpu, data);
 	if (!data->log_size) {
 		data->state = STATE_NO_DATA;
 		cpumask_clear_cpu(cpu, &data->cpu_event);
@@ -459,11 +451,13 @@ salinfo_log_read(struct file *file, char __user *buffer, size_t count, loff_t *p
 	return simple_read_from_buffer(buffer, count, ppos, buf, bufsize);
 }
 
-static void
+static long
 salinfo_log_clear_cpu(void *context)
 {
 	struct salinfo_data *data = context;
+
 	ia64_sal_clear_state_info(data->type);
+	return 0;
 }
 
 static int
@@ -486,7 +480,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu)
 	rh = (sal_log_record_header_t *)(data->log_buffer);
 	/* Corrected errors have already been cleared from SAL */
 	if (rh->severity != sal_log_severity_corrected)
-		call_on_cpu(cpu, salinfo_log_clear_cpu, data);
+		work_on_cpu_safe(cpu, salinfo_log_clear_cpu, data);
 	/* clearing a record may make a new record visible */
 	salinfo_log_new_read(cpu, data);
 	if (data->state == STATE_LOG_RECORD) {
@@ -531,9 +525,8 @@ salinfo_log_write(struct file *file, const char __user *buffer, size_t count, lo
 				.oemdata = &data->oemdata,
 				.oemdata_size = &data->oemdata_size
 			};
-			call_on_cpu(cpu, salinfo_platform_oemdata_cpu, &parms);
-			if (parms.ret)
-				count = parms.ret;
+			count = work_on_cpu_safe(cpu, salinfo_platform_oemdata_cpu,
+						 &parms);
 		} else
 			data->oemdata_size = 0;
 	} else
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 1a68f012a6dc..d76529cbff20 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -355,18 +355,12 @@ static int cache_add_dev(unsigned int cpu)
 	unsigned long i, j;
 	struct cache_info *this_object;
 	int retval = 0;
-	cpumask_t oldmask;
 
 	if (all_cpu_cache_info[cpu].kobj.parent)
 		return 0;
 
-	oldmask = current->cpus_allowed;
-	retval = set_cpus_allowed_ptr(current, cpumask_of(cpu));
-	if (unlikely(retval))
-		return retval;
 
 	retval = cpu_cache_sysfs_init(cpu);
-	set_cpus_allowed_ptr(current, &oldmask);
 	if (unlikely(retval < 0))
 		return retval;
 
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index f89d20c97412..798026dde52e 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -192,6 +192,8 @@ SECTIONS {
 		CONSTRUCTORS
 	}
 
+	BUG_TABLE
+
 	. = ALIGN(16);	/* gp must be 16-byte aligned for exc. table */
 	.got : AT(ADDR(.got) - LOAD_OFFSET) {
 		*(.got.plt)
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile
index 1f3d3877618f..0a40b14407b1 100644
--- a/arch/ia64/lib/Makefile
+++ b/arch/ia64/lib/Makefile
@@ -24,25 +24,25 @@ AFLAGS___modsi3.o	=	     -DMODULO
 AFLAGS___umodsi3.o	= -DUNSIGNED -DMODULO
 
 $(obj)/__divdi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__udivdi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__moddi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__umoddi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__divsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__udivsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__modsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__umodsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
diff --git a/arch/ia64/lib/memcpy_mck.S b/arch/ia64/lib/memcpy_mck.S
index b264b6a7967b..bbbadc478f5b 100644
--- a/arch/ia64/lib/memcpy_mck.S
+++ b/arch/ia64/lib/memcpy_mck.S
@@ -556,9 +556,6 @@ EK(.ex_handler,  (p17)	st8	[dst1]=r39,8);						\
 #define D	r22
 #define F	r28
 
-#define memset_arg0	r32
-#define memset_arg2	r33
-
 #define saved_retval	loc0
 #define saved_rtlink	loc1
 #define saved_pfs_stack	loc2
@@ -622,7 +619,7 @@ EK(.ex_handler,  (p17)	st8	[dst1]=r39,8);						\
  * 	(faulting_addr - orig_dst)	-> len to faulting st address
  * B =	(cur_dst - orig_dst)		-> len copied so far
  * C =	A - B				-> len need to be copied
- * D =	orig_len - A			-> len need to be zeroed
+ * D =	orig_len - A			-> len need to be left along
  */
 (p6)	sub	A = F, saved_in0
 (p7)	sub	A = F, saved_in1
@@ -638,9 +635,6 @@ EK(.ex_handler,  (p17)	st8	[dst1]=r39,8);						\
 	sub	D = saved_in2, A
 	;;
 	cmp.gt	p8,p0=C,r0		// more than 1 byte?
-	add	memset_arg0=saved_in0, A
-(p6)	mov	memset_arg2=0		// copy_to_user should not call memset
-(p7)	mov	memset_arg2=D		// copy_from_user need to have kbuf zeroed
 	mov	r8=0
 	mov	saved_retval = D
 	mov	saved_rtlink = b0
@@ -652,11 +646,6 @@ EK(.ex_handler,  (p17)	st8	[dst1]=r39,8);						\
 	;;
 
 	add	saved_retval=saved_retval,r8	// above might return non-zero value
-	cmp.gt	p8,p0=memset_arg2,r0	// more than 1 byte?
-	mov	out0=memset_arg0	// *s
-	mov	out1=r0			// c
-	mov	out2=memset_arg2	// n
-(p8)	br.call.sptk.few b0=memset
 	;;
 
 	mov	retval=saved_retval
diff --git a/arch/ia64/mm/extable.c b/arch/ia64/mm/extable.c
index 4edb816aba9a..10dd4a66e167 100644
--- a/arch/ia64/mm/extable.c
+++ b/arch/ia64/mm/extable.c
@@ -5,7 +5,10 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-#include <linux/uaccess.h>
+#include <asm/ptrace.h>
+#include <asm/extable.h>
+#include <asm/errno.h>
+#include <asm/processor.h>
 
 void
 ia64_handle_exception (struct pt_regs *regs, const struct exception_table_entry *e)
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 52704f199dd6..55febd65911a 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -598,12 +598,17 @@ static void sn_hwperf_call_sal(void *info)
 	op_info->ret = r;
 }
 
+static long sn_hwperf_call_sal_work(void *info)
+{
+	sn_hwperf_call_sal(info);
+	return 0;
+}
+
 static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
 {
 	u32 cpu;
 	u32 use_ipi;
 	int r = 0;
-	cpumask_t save_allowed;
 	
 	cpu = (op_info->a->arg & SN_HWPERF_ARG_CPU_MASK) >> 32;
 	use_ipi = op_info->a->arg & SN_HWPERF_ARG_USE_IPI_MASK;
@@ -629,13 +634,9 @@ static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
 			/* use an interprocessor interrupt to call SAL */
 			smp_call_function_single(cpu, sn_hwperf_call_sal,
 				op_info, 1);
-		}
-		else {
-			/* migrate the task before calling SAL */ 
-			save_allowed = current->cpus_allowed;
-			set_cpus_allowed_ptr(current, cpumask_of(cpu));
-			sn_hwperf_call_sal(op_info);
-			set_cpus_allowed_ptr(current, &save_allowed);
+		} else {
+			/* Call on the target CPU */
+			work_on_cpu_safe(cpu, sn_hwperf_call_sal_work, op_info);
 		}
 	}
 	r = op_info->ret;
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index deb298777df2..c000ffac8586 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -2,6 +2,7 @@
 generic-y += clkdev.h
 generic-y += current.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index 6f8982157a75..07be349c00ad 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -11,13 +11,9 @@
 /*
  * User space memory access functions
  */
-#include <linux/errno.h>
-#include <linux/thread_info.h>
 #include <asm/page.h>
 #include <asm/setup.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <linux/prefetch.h>
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -114,25 +110,7 @@ static inline int access_ok(int type, const void *addr, unsigned long size)
 }
 #endif /* CONFIG_MMU */
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -483,174 +461,25 @@ do {									\
 		: "r14", "memory");					\
 } while (0)
 
-#define __copy_user_zeroing(to, from, size)				\
-do {									\
-	unsigned long __dst, __src, __c;				\
-	__asm__ __volatile__ (						\
-		"	mv	r14, %0\n"				\
-		"	or	r14, %1\n"				\
-		"	beq	%0, %1, 9f\n"				\
-		"	beqz	%2, 9f\n"				\
-		"	and3	r14, r14, #3\n"				\
-		"	bnez	r14, 2f\n"				\
-		"	and3	%2, %2, #3\n"				\
-		"	beqz	%3, 2f\n"				\
-		"	addi	%0, #-4		; word_copy \n"		\
-		"	.fillinsn\n"					\
-		"0:	ld	r14, @%1+\n"				\
-		"	addi	%3, #-1\n"				\
-		"	.fillinsn\n"					\
-		"1:	st	r14, @+%0\n"				\
-		"	bnez	%3, 0b\n"				\
-		"	beqz	%2, 9f\n"				\
-		"	addi	%0, #4\n"				\
-		"	.fillinsn\n"					\
-		"2:	ldb	r14, @%1	; byte_copy \n"		\
-		"	.fillinsn\n"					\
-		"3:	stb	r14, @%0\n"				\
-		"	addi	%1, #1\n"				\
-		"	addi	%2, #-1\n"				\
-		"	addi	%0, #1\n"				\
-		"	bnez	%2, 2b\n"				\
-		"	.fillinsn\n"					\
-		"9:\n"							\
-		".section .fixup,\"ax\"\n"				\
-		"	.balign 4\n"					\
-		"5:	addi	%3, #1\n"				\
-		"	addi	%1, #-4\n"				\
-		"	.fillinsn\n"					\
-		"6:	slli	%3, #2\n"				\
-		"	add	%2, %3\n"				\
-		"	addi	%0, #4\n"				\
-		"	.fillinsn\n"					\
-		"7:	ldi	r14, #0		; store zero \n"	\
-		"	.fillinsn\n"					\
-		"8:	addi	%2, #-1\n"				\
-		"	stb	r14, @%0	; ACE? \n"		\
-		"	addi	%0, #1\n"				\
-		"	bnez	%2, 8b\n"				\
-		"	seth	r14, #high(9b)\n"			\
-		"	or3	r14, r14, #low(9b)\n"			\
-		"	jmp	r14\n"					\
-		".previous\n"						\
-		".section __ex_table,\"a\"\n"				\
-		"	.balign 4\n"					\
-		"	.long 0b,6b\n"					\
-		"	.long 1b,5b\n"					\
-		"	.long 2b,7b\n"					\
-		"	.long 3b,7b\n"					\
-		".previous\n"						\
-		: "=&r" (__dst), "=&r" (__src), "=&r" (size),		\
-		  "=&r" (__c)						\
-		: "0" (to), "1" (from), "2" (size), "3" (size / 4)	\
-		: "r14", "memory");					\
-} while (0)
-
-
 /* We let the __ versions of copy_from/to_user inline, because they're often
  * used in fast paths and have only a small space overhead.
  */
-static inline unsigned long __generic_copy_from_user_nocheck(void *to,
-	const void __user *from, unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	__copy_user_zeroing(to, from, n);
+	prefetchw(to);
+	__copy_user(to, from, n);
 	return n;
 }
 
-static inline unsigned long __generic_copy_to_user_nocheck(void __user *to,
-	const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+	prefetch(from);
 	__copy_user(to, from, n);
 	return n;
 }
 
-unsigned long __generic_copy_to_user(void __user *, const void *, unsigned long);
-unsigned long __generic_copy_from_user(void *, const void __user *, unsigned long);
-
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define __copy_to_user(to, from, n)			\
-	__generic_copy_to_user_nocheck((to), (from), (n))
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define copy_to_user(to, from, n)			\
-({							\
-	might_fault();					\
-	__generic_copy_to_user((to), (from), (n));	\
-})
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking. * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define __copy_from_user(to, from, n)			\
-	__generic_copy_from_user_nocheck((to), (from), (n))
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define copy_from_user(to, from, n)			\
-({							\
-	might_fault();					\
-	__generic_copy_from_user((to), (from), (n));	\
-})
-
 long __must_check strncpy_from_user(char *dst, const char __user *src,
 				long count);
 long __must_check __strncpy_from_user(char *dst,
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 5853f8e92c20..ae6548d29a18 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -92,4 +92,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c
index d763f0bd2106..a4d43b5cc102 100644
--- a/arch/m32r/kernel/m32r_ksyms.c
+++ b/arch/m32r/kernel/m32r_ksyms.c
@@ -26,8 +26,6 @@ EXPORT_SYMBOL(strncpy_from_user);
 EXPORT_SYMBOL(__strncpy_from_user);
 EXPORT_SYMBOL(clear_user);
 EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__generic_copy_from_user);
-EXPORT_SYMBOL(__generic_copy_to_user);
 EXPORT_SYMBOL(strnlen_user);
 
 #ifdef CONFIG_SMP
diff --git a/arch/m32r/lib/usercopy.c b/arch/m32r/lib/usercopy.c
index fd03f2731f20..b3ef2c899f96 100644
--- a/arch/m32r/lib/usercopy.c
+++ b/arch/m32r/lib/usercopy.c
@@ -11,27 +11,6 @@
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
 
-unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	prefetch(from);
-	if (access_ok(VERIFY_WRITE, to, n))
-		__copy_user(to,from,n);
-	return n;
-}
-
-unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	prefetchw(to);
-	if (access_ok(VERIFY_READ, from, n))
-		__copy_user_zeroing(to,from,n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-
-
 /*
  * Copy a null terminated string from userspace.
  */
diff --git a/arch/m68k/coldfire/pit.c b/arch/m68k/coldfire/pit.c
index 175553d5b8ed..6c0878018b44 100644
--- a/arch/m68k/coldfire/pit.c
+++ b/arch/m68k/coldfire/pit.c
@@ -149,8 +149,10 @@ void hw_timer_init(irq_handler_t handler)
 	cf_pit_clockevent.mult = div_sc(FREQ, NSEC_PER_SEC, 32);
 	cf_pit_clockevent.max_delta_ns =
 		clockevent_delta2ns(0xFFFF, &cf_pit_clockevent);
+	cf_pit_clockevent.max_delta_ticks = 0xFFFF;
 	cf_pit_clockevent.min_delta_ns =
 		clockevent_delta2ns(0x3f, &cf_pit_clockevent);
+	cf_pit_clockevent.min_delta_ticks = 0x3f;
 	clockevents_register_device(&cf_pit_clockevent);
 
 	setup_irq(MCF_IRQ_PIT1, &pit_irq);
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 048bf076f7df..531cb9eb3319 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -25,6 +25,7 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
@@ -60,6 +61,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -71,6 +73,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -101,6 +104,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -298,6 +302,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -371,6 +377,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -383,6 +390,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_A2065=y
 CONFIG_ARIADNE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -404,7 +412,6 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -564,6 +571,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -594,6 +603,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -605,6 +615,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -629,4 +640,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index d4de24963f5f..ca91d39555da 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -26,6 +26,7 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
@@ -58,6 +59,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -69,6 +71,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -99,6 +102,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -296,6 +300,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -353,6 +359,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -362,6 +369,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -378,7 +386,6 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -523,6 +530,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -553,6 +562,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -564,6 +574,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -588,4 +599,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index fc0fd3f871f3..23a3d8a691e2 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -25,6 +25,7 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
@@ -58,6 +59,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -69,6 +71,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -99,6 +102,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -296,6 +300,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -362,6 +368,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -372,6 +379,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_ATARILANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -389,7 +397,6 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -544,6 +551,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -574,6 +583,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -585,6 +595,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -609,4 +620,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 52e984a0aa69..95deb95140fe 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -25,6 +25,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
@@ -56,6 +57,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -67,6 +69,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -97,6 +100,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -294,6 +298,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -352,6 +358,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -361,6 +368,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -377,7 +385,6 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -515,6 +522,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -545,6 +554,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -556,6 +566,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -580,4 +591,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index aaeed4422cc9..afae6958db2d 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -26,6 +26,7 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
@@ -58,6 +59,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -69,6 +71,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -99,6 +102,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -296,6 +300,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -353,6 +359,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -363,6 +370,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_HPLANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -379,7 +387,6 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -525,6 +532,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -555,6 +564,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -566,6 +576,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -590,4 +601,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 3bbc9b2f0dac..b010734729a7 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -25,6 +25,7 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
@@ -57,6 +58,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -68,6 +70,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -98,6 +101,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -298,6 +302,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -369,6 +375,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -379,6 +386,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_MACMACE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -398,7 +406,6 @@ CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -547,6 +554,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -577,6 +586,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -588,6 +598,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -612,4 +623,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 8f2c0decb2f8..0e414549b235 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -21,6 +21,7 @@ CONFIG_SOLARIS_X86_PARTITION=y
 CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
@@ -67,6 +68,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -78,6 +80,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -108,6 +111,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -308,6 +312,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -402,6 +408,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -419,6 +426,7 @@ CONFIG_HPLANCE=y
 CONFIG_MVME147_NET=y
 CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -444,7 +452,6 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PLIP=m
@@ -627,6 +634,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -657,6 +666,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -668,6 +678,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -692,4 +703,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index c743dd22e96f..b2e687a0ec3d 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -25,6 +25,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68030=y
@@ -55,6 +56,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -66,6 +68,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -96,6 +99,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -293,6 +297,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -351,6 +357,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -361,6 +368,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_MVME147_NET=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -377,7 +385,6 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -515,6 +522,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -545,6 +554,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -556,6 +566,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -580,4 +591,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 2ccaca858f05..cbd8ee24d1bc 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -25,6 +25,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
@@ -56,6 +57,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -67,6 +69,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -97,6 +100,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -294,6 +298,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -352,6 +358,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -361,6 +368,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -377,7 +385,6 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -515,6 +522,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -545,6 +554,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -556,6 +566,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -580,4 +591,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 5599f3fd5fcd..1e82cc944339 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -26,6 +26,7 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
@@ -56,6 +57,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -67,6 +69,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -97,6 +100,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -294,6 +298,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -358,6 +364,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -369,6 +376,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -388,7 +396,6 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PLIP=m
@@ -538,6 +545,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -568,6 +577,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -579,6 +589,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -603,4 +614,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 313bf0a562ad..f9e77f57a972 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -25,6 +25,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_SUN3=y
@@ -53,6 +54,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -64,6 +66,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -94,6 +97,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -291,6 +295,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -349,6 +355,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -359,6 +366,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_SUN3LANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -375,7 +383,6 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SUN is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -517,6 +524,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -546,6 +555,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -557,6 +567,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -581,4 +592,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 38b61365f769..3c394fcfb368 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -25,6 +25,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
 CONFIG_KEXEC=y
 CONFIG_BOOTINFO_PROC=y
 CONFIG_SUN3X=y
@@ -53,6 +54,7 @@ CONFIG_NET_IPVTI=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -64,6 +66,7 @@ CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_ILA=m
 CONFIG_IPV6_VTI=m
@@ -94,6 +97,7 @@ CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
 CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -291,6 +295,8 @@ CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
 CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -349,6 +355,7 @@ CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
 CONFIG_GTP=m
@@ -359,6 +366,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_SUN3LANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -375,7 +383,6 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
@@ -517,6 +524,8 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
@@ -547,6 +556,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -558,6 +568,7 @@ CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -582,4 +593,5 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index d4f9ccbfa85c..82005d2ff717 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += futex.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index b4a9b0d5928d..dda58cfe8c22 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -148,7 +148,7 @@ static inline void bfchg_mem_change_bit(int nr, volatile unsigned long *vaddr)
 #define __change_bit(nr, vaddr)	change_bit(nr, vaddr)
 
 
-static inline int test_bit(int nr, const unsigned long *vaddr)
+static inline int test_bit(int nr, const volatile unsigned long *vaddr)
 {
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index f5f790c31bf8..77239e81379b 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -122,16 +122,6 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc,
 	wrusp(usp);
 }
 
-#ifdef CONFIG_MMU
-extern int handle_kernel_fault(struct pt_regs *regs);
-#else
-static inline  int handle_kernel_fault(struct pt_regs *regs)
-{
-	/* Any fault in kernel is fatal on non-mmu */
-	return 0;
-}
-#endif
-
 /* Forward declaration, a strange C thing */
 struct task_struct;
 
diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h
index 3fadc4a93d97..67b3481d6020 100644
--- a/arch/m68k/include/asm/uaccess.h
+++ b/arch/m68k/include/asm/uaccess.h
@@ -4,6 +4,7 @@
 #include <asm/uaccess_mm.h>
 #endif
 
+#include <asm/extable.h>
 #ifdef CONFIG_CPU_HAS_NO_UNALIGNED
 #include <asm-generic/uaccess-unaligned.h>
 #else
diff --git a/arch/m68k/include/asm/uaccess_mm.h b/arch/m68k/include/asm/uaccess_mm.h
index d228601b3afc..ef856ffeffdf 100644
--- a/arch/m68k/include/asm/uaccess_mm.h
+++ b/arch/m68k/include/asm/uaccess_mm.h
@@ -5,14 +5,9 @@
  * User space memory access functions
  */
 #include <linux/compiler.h>
-#include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/sched.h>
 #include <asm/segment.h>
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 /* We let the MMU do all checking */
 static inline int access_ok(int type, const void __user *addr,
 			    unsigned long size)
@@ -36,24 +31,6 @@ static inline int access_ok(int type, const void __user *addr,
 #define	MOVES	"move"
 #endif
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
 extern int __put_user_bad(void);
 extern int __get_user_bad(void);
 
@@ -202,39 +179,55 @@ asm volatile ("\n"					\
 unsigned long __generic_copy_from_user(void *to, const void __user *from, unsigned long n);
 unsigned long __generic_copy_to_user(void __user *to, const void *from, unsigned long n);
 
-#define __constant_copy_from_user_asm(res, to, from, tmp, n, s1, s2, s3)\
+#define __suffix0
+#define __suffix1 b
+#define __suffix2 w
+#define __suffix4 l
+
+#define ____constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, s1, s2, s3)\
 	asm volatile ("\n"						\
 		"1:	"MOVES"."#s1"	(%2)+,%3\n"			\
 		"	move."#s1"	%3,(%1)+\n"			\
+		"	.ifnc	\""#s2"\",\"\"\n"			\
 		"2:	"MOVES"."#s2"	(%2)+,%3\n"			\
 		"	move."#s2"	%3,(%1)+\n"			\
 		"	.ifnc	\""#s3"\",\"\"\n"			\
 		"3:	"MOVES"."#s3"	(%2)+,%3\n"			\
 		"	move."#s3"	%3,(%1)+\n"			\
 		"	.endif\n"					\
+		"	.endif\n"					\
 		"4:\n"							\
 		"	.section __ex_table,\"a\"\n"			\
 		"	.align	4\n"					\
 		"	.long	1b,10f\n"				\
+		"	.ifnc	\""#s2"\",\"\"\n"			\
 		"	.long	2b,20f\n"				\
 		"	.ifnc	\""#s3"\",\"\"\n"			\
 		"	.long	3b,30f\n"				\
 		"	.endif\n"					\
+		"	.endif\n"					\
 		"	.previous\n"					\
 		"\n"							\
 		"	.section .fixup,\"ax\"\n"			\
 		"	.even\n"					\
-		"10:	clr."#s1"	(%1)+\n"			\
-		"20:	clr."#s2"	(%1)+\n"			\
+		"10:	addq.l #"#n1",%0\n"				\
+		"	.ifnc	\""#s2"\",\"\"\n"			\
+		"20:	addq.l #"#n2",%0\n"				\
 		"	.ifnc	\""#s3"\",\"\"\n"			\
-		"30:	clr."#s3"	(%1)+\n"			\
+		"30:	addq.l #"#n3",%0\n"				\
+		"	.endif\n"					\
 		"	.endif\n"					\
-		"	moveq.l	#"#n",%0\n"				\
 		"	jra	4b\n"					\
 		"	.previous\n"					\
 		: "+d" (res), "+&a" (to), "+a" (from), "=&d" (tmp)	\
 		: : "memory")
 
+#define ___constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, s1, s2, s3)\
+	____constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, s1, s2, s3)
+#define __constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3)	\
+	___constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3,  \
+					__suffix##n1, __suffix##n2, __suffix##n3)
+
 static __always_inline unsigned long
 __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
@@ -242,37 +235,37 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
 
 	switch (n) {
 	case 1:
-		__get_user_asm(res, *(u8 *)to, (u8 __user *)from, u8, b, d, 1);
+		__constant_copy_from_user_asm(res, to, from, tmp, 1, 0, 0);
 		break;
 	case 2:
-		__get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, r, 2);
+		__constant_copy_from_user_asm(res, to, from, tmp, 2, 0, 0);
 		break;
 	case 3:
-		__constant_copy_from_user_asm(res, to, from, tmp, 3, w, b,);
+		__constant_copy_from_user_asm(res, to, from, tmp, 2, 1, 0);
 		break;
 	case 4:
-		__get_user_asm(res, *(u32 *)to, (u32 __user *)from, u32, l, r, 4);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 0, 0);
 		break;
 	case 5:
-		__constant_copy_from_user_asm(res, to, from, tmp, 5, l, b,);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 1, 0);
 		break;
 	case 6:
-		__constant_copy_from_user_asm(res, to, from, tmp, 6, l, w,);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 2, 0);
 		break;
 	case 7:
-		__constant_copy_from_user_asm(res, to, from, tmp, 7, l, w, b);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 2, 1);
 		break;
 	case 8:
-		__constant_copy_from_user_asm(res, to, from, tmp, 8, l, l,);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 0);
 		break;
 	case 9:
-		__constant_copy_from_user_asm(res, to, from, tmp, 9, l, l, b);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 1);
 		break;
 	case 10:
-		__constant_copy_from_user_asm(res, to, from, tmp, 10, l, l, w);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 2);
 		break;
 	case 12:
-		__constant_copy_from_user_asm(res, to, from, tmp, 12, l, l, l);
+		__constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 4);
 		break;
 	default:
 		/* we limit the inlined version to 3 moves */
@@ -363,24 +356,26 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
 	return res;
 }
 
-#define __copy_from_user(to, from, n)		\
-(__builtin_constant_p(n) ?			\
- __constant_copy_from_user(to, from, n) :	\
- __generic_copy_from_user(to, from, n))
-
-#define __copy_to_user(to, from, n)		\
-(__builtin_constant_p(n) ?			\
- __constant_copy_to_user(to, from, n) :		\
- __generic_copy_to_user(to, from, n))
-
-#define __copy_to_user_inatomic		__copy_to_user
-#define __copy_from_user_inatomic	__copy_from_user
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (__builtin_constant_p(n))
+		return __constant_copy_from_user(to, from, n);
+	return __generic_copy_from_user(to, from, n);
+}
 
-#define copy_from_user(to, from, n)	__copy_from_user(to, from, n)
-#define copy_to_user(to, from, n)	__copy_to_user(to, from, n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (__builtin_constant_p(n))
+		return __constant_copy_to_user(to, from, n);
+	return __generic_copy_to_user(to, from, n);
+}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+	(uaccess_kernel() ? ~0UL : TASK_SIZE)
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
diff --git a/arch/m68k/include/asm/uaccess_no.h b/arch/m68k/include/asm/uaccess_no.h
index 36deeb36503b..e482c3899ff1 100644
--- a/arch/m68k/include/asm/uaccess_no.h
+++ b/arch/m68k/include/asm/uaccess_no.h
@@ -4,15 +4,11 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/string.h>
 
 #include <asm/segment.h>
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define access_ok(type,addr,size)	_access_ok((unsigned long)(addr),(size))
 
 /*
@@ -27,25 +23,6 @@ static inline int _access_ok(unsigned long addr, unsigned long size)
 }
 
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-
-/*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.
  */
@@ -124,13 +101,21 @@ extern int __get_user_bad(void);
 		 : "=d" (x)					\
 		 : "m" (*__ptr(ptr)))
 
-#define copy_from_user(to, from, n)		(memcpy(to, from, n), 0)
-#define copy_to_user(to, from, n)		(memcpy(to, from, n), 0)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	memcpy(to, (__force const void *)from, n);
+	return 0;
+}
 
-#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
-#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	memcpy((__force void *)to, from, n);
+	return 0;
+}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 /*
  * Copy a null terminated string from userspace.
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index a857d82ec509..aab1edd0d4ba 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		379
+#define NR_syscalls		380
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 9fe674bf911f..25589f5b8669 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -384,5 +384,6 @@
 #define __NR_copy_file_range	376
 #define __NR_preadv2		377
 #define __NR_pwritev2		378
+#define __NR_statx		379
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 093b7c42fb85..6f945bb5ffbd 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -88,7 +88,7 @@ static inline int frame_extra_sizes(int f)
 	return frame_size_change[f];
 }
 
-int handle_kernel_fault(struct pt_regs *regs)
+int fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
 	struct pt_regs *tregs;
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index d6fd6d9ced24..8c9fcfafe0dd 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -399,3 +399,4 @@ ENTRY(sys_call_table)
 	.long sys_copy_file_range
 	.long sys_preadv2
 	.long sys_pwritev2
+	.long sys_statx
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index a926d2c88898..c1cc4e99aa94 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -1016,8 +1016,13 @@ asmlinkage void trap_c(struct frame *fp)
 			/* traced a trapping instruction on a 68020/30,
 			 * real exception will be executed afterwards.
 			 */
-		} else if (!handle_kernel_fault(&fp->ptregs))
-			bad_super_trap(fp);
+			return;
+		}
+#ifdef CONFIG_MMU
+		if (fixup_exception(&fp->ptregs))
+			return;
+#endif
+		bad_super_trap(fp);
 		return;
 	}
 
diff --git a/arch/m68k/lib/uaccess.c b/arch/m68k/lib/uaccess.c
index a76b73abaf64..7646e461aa62 100644
--- a/arch/m68k/lib/uaccess.c
+++ b/arch/m68k/lib/uaccess.c
@@ -30,19 +30,13 @@ unsigned long __generic_copy_from_user(void *to, const void __user *from,
 		"6:\n"
 		"	.section .fixup,\"ax\"\n"
 		"	.even\n"
-		"10:	move.l	%0,%3\n"
-		"7:	clr.l	(%2)+\n"
-		"	subq.l	#1,%3\n"
-		"	jne	7b\n"
-		"	lsl.l	#2,%0\n"
+		"10:	lsl.l	#2,%0\n"
 		"	btst	#1,%5\n"
 		"	jeq	8f\n"
-		"30:	clr.w	(%2)+\n"
-		"	addq.l	#2,%0\n"
+		"30:	addq.l	#2,%0\n"
 		"8:	btst	#0,%5\n"
 		"	jeq	6b\n"
-		"50:	clr.b	(%2)+\n"
-		"	addq.l	#1,%0\n"
+		"50:	addq.l	#1,%0\n"
 		"	jra	6b\n"
 		"	.previous\n"
 		"\n"
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 9dc65a4c28d2..22123f7e8f75 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -150,7 +150,7 @@ static void mac_cache_card_flush(int writeback)
 void __init config_mac(void)
 {
 	if (!MACH_IS_MAC)
-		printk(KERN_ERR "ERROR: no Mac, but config_mac() called!!\n");
+		pr_err("ERROR: no Mac, but config_mac() called!!\n");
 
 	mach_sched_init = mac_sched_init;
 	mach_init_IRQ = mac_init_IRQ;
@@ -837,8 +837,7 @@ static void __init mac_identify(void)
 		/* no bootinfo model id -> NetBSD booter was used! */
 		/* XXX FIXME: breaks for model > 31 */
 		model = (mac_bi_data.cpuid >> 2) & 63;
-		printk(KERN_WARNING "No bootinfo model ID, using cpuid instead "
-		       "(obsolete bootloader?)\n");
+		pr_warn("No bootinfo model ID, using cpuid instead (obsolete bootloader?)\n");
 	}
 
 	macintosh_config = mac_data_table;
@@ -880,14 +879,13 @@ static void __init mac_identify(void)
 	 */
 	iop_preinit();
 
-	printk(KERN_INFO "Detected Macintosh model: %d\n", model);
+	pr_info("Detected Macintosh model: %d\n", model);
 
 	/*
 	 * Report booter data:
 	 */
 	printk(KERN_DEBUG " Penguin bootinfo data:\n");
-	printk(KERN_DEBUG " Video: addr 0x%lx "
-		"row 0x%lx depth %lx dimensions %ld x %ld\n",
+	printk(KERN_DEBUG " Video: addr 0x%lx row 0x%lx depth %lx dimensions %ld x %ld\n",
 		mac_bi_data.videoaddr, mac_bi_data.videorow,
 		mac_bi_data.videodepth, mac_bi_data.dimensions & 0xFFFF,
 		mac_bi_data.dimensions >> 16);
@@ -912,7 +910,7 @@ static void __init mac_identify(void)
 
 static void __init mac_report_hardware(void)
 {
-	printk(KERN_INFO "Apple Macintosh %s\n", macintosh_config->name);
+	pr_info("Apple Macintosh %s\n", macintosh_config->name);
 }
 
 static void mac_get_model(char *str)
@@ -921,15 +919,6 @@ static void mac_get_model(char *str)
 	strcat(str, macintosh_config->name);
 }
 
-static struct resource swim_rsrc = { .flags = IORESOURCE_MEM };
-
-static struct platform_device swim_pdev = {
-	.name		= "swim",
-	.id		= -1,
-	.num_resources	= 1,
-	.resource	= &swim_rsrc,
-};
-
 static const struct resource mac_scsi_iifx_rsrc[] __initconst = {
 	{
 		.flags = IORESOURCE_IRQ,
@@ -994,26 +983,6 @@ static const struct resource mac_scsi_ccl_rsrc[] __initconst = {
 	},
 };
 
-static struct platform_device esp_0_pdev = {
-	.name		= "mac_esp",
-	.id		= 0,
-};
-
-static struct platform_device esp_1_pdev = {
-	.name		= "mac_esp",
-	.id		= 1,
-};
-
-static struct platform_device sonic_pdev = {
-	.name		= "macsonic",
-	.id		= -1,
-};
-
-static struct platform_device mace_pdev = {
-	.name		= "macmace",
-	.id		= -1,
-};
-
 int __init mac_platform_init(void)
 {
 	u8 *swim_base;
@@ -1045,9 +1014,13 @@ int __init mac_platform_init(void)
 	}
 
 	if (swim_base) {
-		swim_rsrc.start = (resource_size_t) swim_base,
-		swim_rsrc.end   = (resource_size_t) swim_base + 0x2000,
-		platform_device_register(&swim_pdev);
+		struct resource swim_rsrc = {
+			.flags = IORESOURCE_MEM,
+			.start = (resource_size_t)swim_base,
+			.end   = (resource_size_t)swim_base + 0x2000,
+		};
+
+		platform_device_register_simple("swim", -1, &swim_rsrc, 1);
 	}
 
 	/*
@@ -1057,13 +1030,13 @@ int __init mac_platform_init(void)
 	switch (macintosh_config->scsi_type) {
 	case MAC_SCSI_QUADRA:
 	case MAC_SCSI_QUADRA3:
-		platform_device_register(&esp_0_pdev);
+		platform_device_register_simple("mac_esp", 0, NULL, 0);
 		break;
 	case MAC_SCSI_QUADRA2:
-		platform_device_register(&esp_0_pdev);
+		platform_device_register_simple("mac_esp", 0, NULL, 0);
 		if ((macintosh_config->ident == MAC_MODEL_Q900) ||
 		    (macintosh_config->ident == MAC_MODEL_Q950))
-			platform_device_register(&esp_1_pdev);
+			platform_device_register_simple("mac_esp", 1, NULL, 0);
 		break;
 	case MAC_SCSI_IIFX:
 		/* Addresses from The Guide to Mac Family Hardware.
@@ -1129,10 +1102,10 @@ int __init mac_platform_init(void)
 
 	switch (macintosh_config->ether_type) {
 	case MAC_ETHER_SONIC:
-		platform_device_register(&sonic_pdev);
+		platform_device_register_simple("macsonic", -1, NULL, 0);
 		break;
 	case MAC_ETHER_MACE:
-		platform_device_register(&mace_pdev);
+		platform_device_register_simple("macmace", -1, NULL, 0);
 		break;
 	}
 
diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index 7990b6f50105..4c1e606e7d03 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -115,7 +115,17 @@
 #include <asm/macints.h>
 #include <asm/mac_iop.h>
 
-/*#define DEBUG_IOP*/
+#ifdef DEBUG
+#define iop_pr_debug(fmt, ...) \
+	printk(KERN_DEBUG "%s: " fmt, __func__, ##__VA_ARGS__)
+#define iop_pr_cont(fmt, ...) \
+	printk(KERN_CONT fmt, ##__VA_ARGS__)
+#else
+#define iop_pr_debug(fmt, ...) \
+	no_printk(KERN_DEBUG "%s: " fmt, __func__, ##__VA_ARGS__)
+#define iop_pr_cont(fmt, ...) \
+	no_printk(KERN_CONT fmt, ##__VA_ARGS__)
+#endif
 
 /* Non-zero if the IOPs are present */
 
@@ -200,7 +210,7 @@ static int iop_alive(volatile struct mac_iop *iop)
 	return retval;
 }
 
-static struct iop_msg *iop_alloc_msg(void)
+static struct iop_msg *iop_get_unused_msg(void)
 {
 	int i;
 	unsigned long flags;
@@ -219,11 +229,6 @@ static struct iop_msg *iop_alloc_msg(void)
 	return NULL;
 }
 
-static void iop_free_msg(struct iop_msg *msg)
-{
-	msg->status = IOP_MSGSTATUS_UNUSED;
-}
-
 /*
  * This is called by the startup code before anything else. Its purpose
  * is to find and initialize the IOPs early in the boot sequence, so that
@@ -268,10 +273,10 @@ void __init iop_init(void)
 	int i;
 
 	if (iop_scc_present) {
-		printk("IOP: detected SCC IOP at %p\n", iop_base[IOP_NUM_SCC]);
+		pr_info("IOP: detected SCC IOP at %p\n", iop_base[IOP_NUM_SCC]);
 	}
 	if (iop_ism_present) {
-		printk("IOP: detected ISM IOP at %p\n", iop_base[IOP_NUM_ISM]);
+		pr_info("IOP: detected ISM IOP at %p\n", iop_base[IOP_NUM_ISM]);
 		iop_start(iop_base[IOP_NUM_ISM]);
 		iop_alive(iop_base[IOP_NUM_ISM]); /* clears the alive flag */
 	}
@@ -310,9 +315,9 @@ void __init iop_register_interrupts(void)
 				pr_err("Couldn't register ISM IOP interrupt\n");
 		}
 		if (!iop_alive(iop_base[IOP_NUM_ISM])) {
-			printk("IOP: oh my god, they killed the ISM IOP!\n");
+			pr_warn("IOP: oh my god, they killed the ISM IOP!\n");
 		} else {
-			printk("IOP: the ISM IOP seems to be alive.\n");
+			pr_warn("IOP: the ISM IOP seems to be alive.\n");
 		}
 	}
 }
@@ -349,9 +354,8 @@ void iop_complete_message(struct iop_msg *msg)
 	int chan = msg->channel;
 	int i,offset;
 
-#ifdef DEBUG_IOP
-	printk("iop_complete(%p): iop %d chan %d\n", msg, msg->iop_num, msg->channel);
-#endif
+	iop_pr_debug("msg %p iop_num %d channel %d\n", msg, msg->iop_num,
+	             msg->channel);
 
 	offset = IOP_ADDR_RECV_MSG + (msg->channel * IOP_MSG_LEN);
 
@@ -363,7 +367,7 @@ void iop_complete_message(struct iop_msg *msg)
 		   IOP_ADDR_RECV_STATE + chan, IOP_MSG_COMPLETE);
 	iop_interrupt(iop_base[msg->iop_num]);
 
-	iop_free_msg(msg);
+	msg->status = IOP_MSGSTATUS_UNUSED;
 }
 
 /*
@@ -394,12 +398,10 @@ static void iop_do_send(struct iop_msg *msg)
 static void iop_handle_send(uint iop_num, uint chan)
 {
 	volatile struct mac_iop *iop = iop_base[iop_num];
-	struct iop_msg *msg,*msg2;
+	struct iop_msg *msg;
 	int i,offset;
 
-#ifdef DEBUG_IOP
-	printk("iop_handle_send: iop %d channel %d\n", iop_num, chan);
-#endif
+	iop_pr_debug("iop_num %d chan %d\n", iop_num, chan);
 
 	iop_writeb(iop, IOP_ADDR_SEND_STATE + chan, IOP_MSG_IDLE);
 
@@ -411,10 +413,8 @@ static void iop_handle_send(uint iop_num, uint chan)
 		msg->reply[i] = iop_readb(iop, offset);
 	}
 	if (msg->handler) (*msg->handler)(msg);
-	msg2 = msg;
+	msg->status = IOP_MSGSTATUS_UNUSED;
 	msg = msg->next;
-	iop_free_msg(msg2);
-
 	iop_send_queue[iop_num][chan] = msg;
 	if (msg) iop_do_send(msg);
 }
@@ -430,11 +430,9 @@ static void iop_handle_recv(uint iop_num, uint chan)
 	int i,offset;
 	struct iop_msg *msg;
 
-#ifdef DEBUG_IOP
-	printk("iop_handle_recv: iop %d channel %d\n", iop_num, chan);
-#endif
+	iop_pr_debug("iop_num %d chan %d\n", iop_num, chan);
 
-	msg = iop_alloc_msg();
+	msg = iop_get_unused_msg();
 	msg->iop_num = iop_num;
 	msg->channel = chan;
 	msg->status = IOP_MSGSTATUS_UNSOL;
@@ -454,14 +452,9 @@ static void iop_handle_recv(uint iop_num, uint chan)
 	if (msg->handler) {
 		(*msg->handler)(msg);
 	} else {
-#ifdef DEBUG_IOP
-		printk("iop_handle_recv: unclaimed message on iop %d channel %d\n", iop_num, chan);
-		printk("iop_handle_recv:");
-		for (i = 0 ; i < IOP_MSG_LEN ; i++) {
-			printk(" %02X", (uint) msg->message[i]);
-		}
-		printk("\n");
-#endif
+		iop_pr_debug("unclaimed message on iop_num %d chan %d\n",
+		             iop_num, chan);
+		iop_pr_debug("%*ph\n", IOP_MSG_LEN, msg->message);
 		iop_complete_message(msg);
 	}
 }
@@ -484,7 +477,7 @@ int iop_send_message(uint iop_num, uint chan, void *privdata,
 	if (chan >= NUM_IOP_CHAN) return -EINVAL;
 	if (msg_len > IOP_MSG_LEN) return -EINVAL;
 
-	msg = iop_alloc_msg();
+	msg = iop_get_unused_msg();
 	if (!msg) return -ENOMEM;
 
 	msg->next = NULL;
@@ -574,50 +567,34 @@ irqreturn_t iop_ism_irq(int irq, void *dev_id)
 	volatile struct mac_iop *iop = iop_base[iop_num];
 	int i,state;
 
-#ifdef DEBUG_IOP
-	printk("iop_ism_irq: status = %02X\n", (uint) iop->status_ctrl);
-#endif
+	iop_pr_debug("status %02X\n", iop->status_ctrl);
 
 	/* INT0 indicates a state change on an outgoing message channel */
 
 	if (iop->status_ctrl & IOP_INT0) {
 		iop->status_ctrl = IOP_INT0 | IOP_RUN | IOP_AUTOINC;
-#ifdef DEBUG_IOP
-		printk("iop_ism_irq: new status = %02X, send states",
-			(uint) iop->status_ctrl);
-#endif
+		iop_pr_debug("new status %02X, send states", iop->status_ctrl);
 		for (i = 0 ; i < NUM_IOP_CHAN  ; i++) {
 			state = iop_readb(iop, IOP_ADDR_SEND_STATE + i);
-#ifdef DEBUG_IOP
-			printk(" %02X", state);
-#endif
+			iop_pr_cont(" %02X", state);
 			if (state == IOP_MSG_COMPLETE) {
 				iop_handle_send(iop_num, i);
 			}
 		}
-#ifdef DEBUG_IOP
-		printk("\n");
-#endif
+		iop_pr_cont("\n");
 	}
 
 	if (iop->status_ctrl & IOP_INT1) {	/* INT1 for incoming msgs */
 		iop->status_ctrl = IOP_INT1 | IOP_RUN | IOP_AUTOINC;
-#ifdef DEBUG_IOP
-		printk("iop_ism_irq: new status = %02X, recv states",
-			(uint) iop->status_ctrl);
-#endif
+		iop_pr_debug("new status %02X, recv states", iop->status_ctrl);
 		for (i = 0 ; i < NUM_IOP_CHAN ; i++) {
 			state = iop_readb(iop, IOP_ADDR_RECV_STATE + i);
-#ifdef DEBUG_IOP
-			printk(" %02X", state);
-#endif
+			iop_pr_cont(" %02X", state);
 			if (state == IOP_MSG_NEW) {
 				iop_handle_recv(iop_num, i);
 			}
 		}
-#ifdef DEBUG_IOP
-		printk("\n");
-#endif
+		iop_pr_cont("\n");
 	}
 	return IRQ_HANDLED;
 }
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 5b01704c85eb..8aa8792e3174 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -281,8 +281,7 @@ static long via_read_time(void)
 		last_result.idata = result.idata;
 	}
 
-	pr_err("via_read_time: failed to read a stable value; "
-	       "got 0x%08lx then 0x%08lx\n",
+	pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n",
 	       last_result.idata, result.idata);
 
 	return 0;
@@ -465,7 +464,7 @@ void mac_poweroff(void)
 #endif
 	}
 	local_irq_enable();
-	printk("It is now safe to turn off your Macintosh.\n");
+	pr_crit("It is now safe to turn off your Macintosh.\n");
 	while(1);
 }
 
@@ -556,7 +555,7 @@ void mac_reset(void)
 
 	/* should never get here */
 	local_irq_enable();
-	printk ("Restart failed.  Please restart manually.\n");
+	pr_crit("Restart failed. Please restart manually.\n");
 	while(1);
 }
 
@@ -661,17 +660,13 @@ int mac_hwclk(int op, struct rtc_time *t)
 		unmktime(now, 0,
 			 &t->tm_year, &t->tm_mon, &t->tm_mday,
 			 &t->tm_hour, &t->tm_min, &t->tm_sec);
-#if 0
-		printk("mac_hwclk: read %04d-%02d-%-2d %02d:%02d:%02d\n",
-			t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
-			t->tm_hour, t->tm_min, t->tm_sec);
-#endif
+		pr_debug("%s: read %04d-%02d-%-2d %02d:%02d:%02d\n",
+		         __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+		         t->tm_hour, t->tm_min, t->tm_sec);
 	} else { /* write */
-#if 0
-		printk("mac_hwclk: tried to write %04d-%02d-%-2d %02d:%02d:%02d\n",
-			t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
-			t->tm_hour, t->tm_min, t->tm_sec);
-#endif
+		pr_debug("%s: tried to write %04d-%02d-%-2d %02d:%02d:%02d\n",
+		         __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+		         t->tm_hour, t->tm_min, t->tm_sec);
 
 		now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
 			     t->tm_hour, t->tm_min, t->tm_sec);
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index bd66a0b20c6b..2795e4ca09d7 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -32,7 +32,7 @@ int send_fault_sig(struct pt_regs *regs)
 		force_sig_info(siginfo.si_signo,
 			       &siginfo, current);
 	} else {
-		if (handle_kernel_fault(regs))
+		if (fixup_exception(regs))
 			return -1;
 
 		//if (siginfo.si_signo == SIGBUS)
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index f9b9df5d6de9..8f940553a579 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += futex.h
diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h
index ffa3a3a2ecad..0c151e5af079 100644
--- a/arch/metag/include/asm/pgtable.h
+++ b/arch/metag/include/asm/pgtable.h
@@ -6,6 +6,7 @@
 #define _METAG_PGTABLE_H
 
 #include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 273e61225c27..5ebc2850690e 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -4,10 +4,6 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
-
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -28,7 +24,7 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
 /*
  * Explicitly allow NULL pointers here. Parts of the kernel such
  * as readv/writev use access_ok to validate pointers, but want
@@ -51,28 +47,7 @@ static inline int __access_ok(unsigned long addr, unsigned long size)
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr),	\
 						(unsigned long)(size))
 
-static inline int verify_area(int type, const void *addr, unsigned long size)
-{
-	return access_ok(type, addr, size) ? 0 : -EFAULT;
-}
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -197,36 +172,10 @@ extern long __must_check strnlen_user(const char __user *src, long count);
 
 #define strlen_user(str) strnlen_user(str, 32767)
 
-extern unsigned long __must_check __copy_user_zeroing(void *to,
-						      const void __user *from,
-						      unsigned long n);
-
-static inline unsigned long
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		return __copy_user_zeroing(to, from, n);
-	memset(to, 0, n);
-	return n;
-}
-
-#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
-#define __copy_from_user_inatomic __copy_from_user
-
-extern unsigned long __must_check __copy_user(void __user *to,
-					      const void *from,
-					      unsigned long n);
-
-static inline unsigned long copy_to_user(void __user *to, const void *from,
-					 unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_user(to, from, n);
-	return n;
-}
-
-#define __copy_to_user(to, from, n) __copy_user(to, from, n)
-#define __copy_to_user_inatomic __copy_to_user
+extern unsigned long raw_copy_from_user(void *to, const void __user *from,
+					unsigned long n);
+extern unsigned long raw_copy_to_user(void __user *to, const void *from,
+				      unsigned long n);
 
 /*
  * Zero Userspace
diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c
index 5fd16ee5280c..e615603a4b0a 100644
--- a/arch/metag/kernel/ptrace.c
+++ b/arch/metag/kernel/ptrace.c
@@ -26,6 +26,16 @@
  * user_regset definitions.
  */
 
+static unsigned long user_txstatus(const struct pt_regs *regs)
+{
+	unsigned long data = (unsigned long)regs->ctx.Flags;
+
+	if (regs->ctx.SaveMask & TBICTX_CBUF_BIT)
+		data |= USER_GP_REGS_STATUS_CATCH_BIT;
+
+	return data;
+}
+
 int metag_gp_regs_copyout(const struct pt_regs *regs,
 			  unsigned int pos, unsigned int count,
 			  void *kbuf, void __user *ubuf)
@@ -64,9 +74,7 @@ int metag_gp_regs_copyout(const struct pt_regs *regs,
 	if (ret)
 		goto out;
 	/* TXSTATUS */
-	data = (unsigned long)regs->ctx.Flags;
-	if (regs->ctx.SaveMask & TBICTX_CBUF_BIT)
-		data |= USER_GP_REGS_STATUS_CATCH_BIT;
+	data = user_txstatus(regs);
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				  &data, 4*25, 4*26);
 	if (ret)
@@ -121,6 +129,7 @@ int metag_gp_regs_copyin(struct pt_regs *regs,
 	if (ret)
 		goto out;
 	/* TXSTATUS */
+	data = user_txstatus(regs);
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &data, 4*25, 4*26);
 	if (ret)
@@ -246,6 +255,8 @@ int metag_rp_state_copyin(struct pt_regs *regs,
 	unsigned long long *ptr;
 	int ret, i;
 
+	if (count < 4*13)
+		return -EINVAL;
 	/* Read the entire pipeline before making any changes */
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &rp, 0, 4*13);
@@ -305,7 +316,7 @@ static int metag_tls_set(struct task_struct *target,
 			const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	void __user *tls;
+	void __user *tls = target->thread.tls_ptr;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
diff --git a/arch/metag/kernel/stacktrace.c b/arch/metag/kernel/stacktrace.c
index 91ffc4b75c33..09d67b7f51ca 100644
--- a/arch/metag/kernel/stacktrace.c
+++ b/arch/metag/kernel/stacktrace.c
@@ -31,8 +31,6 @@ static void tbi_boing_init(void)
 }
 #endif
 
-#define ALIGN_DOWN(addr, size)  ((addr)&(~((size)-1)))
-
 /*
  * Unwind the current stack frame and store the new register values in the
  * structure passed as argument. Unwinding is equivalent to a function return,
diff --git a/arch/metag/lib/usercopy.c b/arch/metag/lib/usercopy.c
index b3ebfe9c8e88..e8a4ea83cabb 100644
--- a/arch/metag/lib/usercopy.c
+++ b/arch/metag/lib/usercopy.c
@@ -29,7 +29,6 @@
 		COPY						 \
 		"1:\n"						 \
 		"	.section .fixup,\"ax\"\n"		 \
-		"	MOV D1Ar1,#0\n"				 \
 		FIXUP						 \
 		"	MOVT    D1Ar1,#HI(1b)\n"		 \
 		"	JUMP    D1Ar1,#LO(1b)\n"		 \
@@ -260,27 +259,31 @@
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"22:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
-		"SUB	%3, %3, #32\n"					\
 		"23:\n"							\
-		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"SUB	%3, %3, #32\n"					\
 		"24:\n"							\
+		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"25:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"26:\n"							\
 		"SUB	%3, %3, #32\n"					\
 		"DCACHE	[%1+#-64], D0Ar6\n"				\
 		"BR	$Lloop"id"\n"					\
 									\
 		"MOV	RAPF, %1\n"					\
-		"25:\n"							\
+		"27:\n"							\
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"26:\n"							\
+		"28:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"29:\n"							\
 		"SUB	%3, %3, #32\n"					\
-		"27:\n"							\
+		"30:\n"							\
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"28:\n"							\
+		"31:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"32:\n"							\
 		"SUB	%0, %0, #8\n"					\
-		"29:\n"							\
+		"33:\n"							\
 		"SETL	[%0++], D0.7, D1.7\n"				\
 		"SUB	%3, %3, #32\n"					\
 		"1:"							\
@@ -312,11 +315,15 @@
 		"	.long 26b,3b\n"					\
 		"	.long 27b,3b\n"					\
 		"	.long 28b,3b\n"					\
-		"	.long 29b,4b\n"					\
+		"	.long 29b,3b\n"					\
+		"	.long 30b,3b\n"					\
+		"	.long 31b,3b\n"					\
+		"	.long 32b,3b\n"					\
+		"	.long 33b,4b\n"					\
 		"	.previous\n"					\
 		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
 		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
-		: "D1Ar1", "D0Ar2", "memory")
+		: "D1Ar1", "D0Ar2", "cc", "memory")
 
 /*	rewind 'to' and 'from'  pointers when a fault occurs
  *
@@ -342,7 +349,7 @@
 #define __asm_copy_to_user_64bit_rapf_loop(to,	from, ret, n, id)\
 	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
 		"LSR	D0Ar2, D0Ar2, #8\n"				\
-		"AND	D0Ar2, D0Ar2, #0x7\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
 		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
 		"SUB	D0Ar2, D0Ar2, #1\n"				\
 		"MOV	D1Ar1, #4\n"					\
@@ -403,47 +410,55 @@
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"22:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
-		"SUB	%3, %3, #16\n"					\
 		"23:\n"							\
-		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"24:\n"							\
-		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
 		"SUB	%3, %3, #16\n"					\
-		"25:\n"							\
+		"24:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"26:\n"							\
+		"25:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"26:\n"							\
 		"SUB	%3, %3, #16\n"					\
 		"27:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"28:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"29:\n"							\
+		"SUB	%3, %3, #16\n"					\
+		"30:\n"							\
+		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"31:\n"							\
+		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"32:\n"							\
 		"SUB	%3, %3, #16\n"					\
 		"DCACHE	[%1+#-64], D0Ar6\n"				\
 		"BR	$Lloop"id"\n"					\
 									\
 		"MOV	RAPF, %1\n"					\
-		"29:\n"							\
+		"33:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"30:\n"							\
+		"34:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"35:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"31:\n"							\
+		"36:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"32:\n"							\
+		"37:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"38:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"33:\n"							\
+		"39:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"34:\n"							\
+		"40:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"41:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"35:\n"							\
+		"42:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"36:\n"							\
+		"43:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"44:\n"							\
 		"SUB	%0, %0, #4\n"					\
-		"37:\n"							\
+		"45:\n"							\
 		"SETD	[%0++], D0.7\n"					\
 		"SUB	%3, %3, #16\n"					\
 		"1:"							\
@@ -483,11 +498,19 @@
 		"	.long 34b,3b\n"					\
 		"	.long 35b,3b\n"					\
 		"	.long 36b,3b\n"					\
-		"	.long 37b,4b\n"					\
+		"	.long 37b,3b\n"					\
+		"	.long 38b,3b\n"					\
+		"	.long 39b,3b\n"					\
+		"	.long 40b,3b\n"					\
+		"	.long 41b,3b\n"					\
+		"	.long 42b,3b\n"					\
+		"	.long 43b,3b\n"					\
+		"	.long 44b,3b\n"					\
+		"	.long 45b,4b\n"					\
 		"	.previous\n"					\
 		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
 		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
-		: "D1Ar1", "D0Ar2", "memory")
+		: "D1Ar1", "D0Ar2", "cc", "memory")
 
 /*	rewind 'to' and 'from'  pointers when a fault occurs
  *
@@ -513,7 +536,7 @@
 #define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
 	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
 		"LSR	D0Ar2, D0Ar2, #8\n"				\
-		"AND	D0Ar2, D0Ar2, #0x7\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
 		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
 		"SUB	D0Ar2, D0Ar2, #1\n"				\
 		"MOV	D1Ar1, #4\n"					\
@@ -525,8 +548,8 @@
 		"SUB	%1,	%1,	D0Ar2\n"			\
 		"SUB	%3, %3, D1Ar1\n")
 
-unsigned long __copy_user(void __user *pdst, const void *psrc,
-			  unsigned long n)
+unsigned long raw_copy_to_user(void __user *pdst, const void *psrc,
+			       unsigned long n)
 {
 	register char __user *dst asm ("A0.2") = pdst;
 	register const char *src asm ("A1.2") = psrc;
@@ -538,23 +561,31 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 	if ((unsigned long) src & 1) {
 		__asm_copy_to_user_1(dst, src, retn);
 		n--;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 1) {
 		/* Worst case - byte copy */
 		while (n > 0) {
 			__asm_copy_to_user_1(dst, src, retn);
 			n--;
+			if (retn)
+				return retn + n;
 		}
 	}
 	if (((unsigned long) src & 2) && n >= 2) {
 		__asm_copy_to_user_2(dst, src, retn);
 		n -= 2;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 2) {
 		/* Second worst case - word copy */
 		while (n >= 2) {
 			__asm_copy_to_user_2(dst, src, retn);
 			n -= 2;
+			if (retn)
+				return retn + n;
 		}
 	}
 
@@ -569,6 +600,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		while (n >= 8) {
 			__asm_copy_to_user_8x64(dst, src, retn);
 			n -= 8;
+			if (retn)
+				return retn + n;
 		}
 	}
 	if (n >= RAPF_MIN_BUF_SIZE) {
@@ -581,6 +614,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		while (n >= 8) {
 			__asm_copy_to_user_8x64(dst, src, retn);
 			n -= 8;
+			if (retn)
+				return retn + n;
 		}
 	}
 #endif
@@ -588,11 +623,15 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 	while (n >= 16) {
 		__asm_copy_to_user_16(dst, src, retn);
 		n -= 16;
+		if (retn)
+			return retn + n;
 	}
 
 	while (n >= 4) {
 		__asm_copy_to_user_4(dst, src, retn);
 		n -= 4;
+		if (retn)
+			return retn + n;
 	}
 
 	switch (n) {
@@ -609,24 +648,26 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		break;
 	}
 
+	/*
+	 * If we get here, retn correctly reflects the number of failing
+	 * bytes.
+	 */
 	return retn;
 }
-EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 
 #define __asm_copy_from_user_1(to, from, ret) \
 	__asm_copy_user_cont(to, from, ret,	\
 		"	GETB D1Ar1,[%1++]\n"	\
 		"2:	SETB [%0++],D1Ar1\n",	\
-		"3:	ADD  %2,%2,#1\n"	\
-		"	SETB [%0++],D1Ar1\n",	\
+		"3:	ADD  %2,%2,#1\n",	\
 		"	.long 2b,3b\n")
 
 #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	GETW D1Ar1,[%1++]\n"		\
 		"2:	SETW [%0++],D1Ar1\n" COPY,	\
-		"3:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
+		"3:	ADD  %2,%2,#2\n" FIXUP,		\
 		"	.long 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_2(to, from, ret) \
@@ -636,145 +677,26 @@ EXPORT_SYMBOL(__copy_user);
 	__asm_copy_from_user_2x_cont(to, from, ret,	\
 		"	GETB D1Ar1,[%1++]\n"		\
 		"4:	SETB [%0++],D1Ar1\n",		\
-		"5:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
+		"5:	ADD  %2,%2,#1\n",		\
 		"	.long 4b,5b\n")
 
 #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	GETD D1Ar1,[%1++]\n"		\
 		"2:	SETD [%0++],D1Ar1\n" COPY,	\
-		"3:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
+		"3:	ADD  %2,%2,#4\n" FIXUP,		\
 		"	.long 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_4(to, from, ret) \
 	__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")
 
-#define __asm_copy_from_user_5(to, from, ret) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"4:	SETB [%0++],D1Ar1\n",		\
-		"5:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 4b,5b\n")
-
-#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"4:	SETW [%0++],D1Ar1\n" COPY,	\
-		"5:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_6(to, from, ret) \
-	__asm_copy_from_user_6x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_7(to, from, ret) \
-	__asm_copy_from_user_6x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"6:	SETB [%0++],D1Ar1\n",		\
-		"7:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 6b,7b\n")
-
-#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"4:	SETD [%0++],D1Ar1\n" COPY,	\
-		"5:	ADD  %2,%2,#4\n"			\
-		"	SETD [%0++],D1Ar1\n" FIXUP,		\
-		"	.long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_8(to, from, ret) \
-	__asm_copy_from_user_8x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_9(to, from, ret) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"6:	SETB [%0++],D1Ar1\n",		\
-		"7:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 6b,7b\n")
-
-#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"6:	SETW [%0++],D1Ar1\n" COPY,	\
-		"7:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_10(to, from, ret) \
-	__asm_copy_from_user_10x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_11(to, from, ret)		\
-	__asm_copy_from_user_10x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"8:	SETB [%0++],D1Ar1\n",		\
-		"9:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 8b,9b\n")
-
-#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"6:	SETD [%0++],D1Ar1\n" COPY,	\
-		"7:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_12(to, from, ret) \
-	__asm_copy_from_user_12x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_13(to, from, ret) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"8:	SETB [%0++],D1Ar1\n",		\
-		"9:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 8b,9b\n")
-
-#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"8:	SETW [%0++],D1Ar1\n" COPY,	\
-		"9:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_14(to, from, ret) \
-	__asm_copy_from_user_14x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_15(to, from, ret) \
-	__asm_copy_from_user_14x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"10:	SETB [%0++],D1Ar1\n",		\
-		"11:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 10b,11b\n")
-
-#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"8:	SETD [%0++],D1Ar1\n" COPY,	\
-		"9:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_16(to, from, ret) \
-	__asm_copy_from_user_16x_cont(to, from, ret, "", "", "")
-
 #define __asm_copy_from_user_8x64(to, from, ret) \
 	asm volatile (				\
 		"	GETL D0Ar2,D1Ar1,[%1++]\n"	\
 		"2:	SETL [%0++],D0Ar2,D1Ar1\n"	\
 		"1:\n"					\
 		"	.section .fixup,\"ax\"\n"	\
-		"	MOV D1Ar1,#0\n"			\
-		"	MOV D0Ar2,#0\n"			\
 		"3:	ADD  %2,%2,#8\n"		\
-		"	SETL [%0++],D0Ar2,D1Ar1\n"	\
 		"	MOVT    D0Ar2,#HI(1b)\n"	\
 		"	JUMP    D0Ar2,#LO(1b)\n"	\
 		"	.previous\n"			\
@@ -789,36 +711,57 @@ EXPORT_SYMBOL(__copy_user);
  *
  *	Rationale:
  *		A fault occurs while reading from user buffer, which is the
- *		source. Since the fault is at a single address, we only
- *		need to rewind by 8 bytes.
+ *		source.
  *		Since we don't write to kernel buffer until we read first,
  *		the kernel buffer is at the right state and needn't be
- *		corrected.
+ *		corrected, but the source must be rewound to the beginning of
+ *		the block, which is LSM_STEP*8 bytes.
+ *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ *		and stored in D0Ar2
+ *
+ *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ *			a fault happens at the 4th write, LSM_STEP will be 0
+ *			instead of 4. The code copes with that.
  */
 #define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id)	\
 	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
-		"SUB	%1, %1, #8\n")
+		"LSR	D0Ar2, D0Ar2, #5\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x38\n"				\
+		"ADDZ	D0Ar2, D0Ar2, #32\n"				\
+		"SUB	%1, %1, D0Ar2\n")
 
 /*	rewind 'from' pointer when a fault occurs
  *
  *	Rationale:
  *		A fault occurs while reading from user buffer, which is the
- *		source. Since the fault is at a single address, we only
- *		need to rewind by 4 bytes.
+ *		source.
  *		Since we don't write to kernel buffer until we read first,
  *		the kernel buffer is at the right state and needn't be
- *		corrected.
+ *		corrected, but the source must be rewound to the beginning of
+ *		the block, which is LSM_STEP*4 bytes.
+ *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ *		and stored in D0Ar2
+ *
+ *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ *			a fault happens at the 4th write, LSM_STEP will be 0
+ *			instead of 4. The code copes with that.
  */
 #define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id)	\
 	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
-		"SUB	%1, %1, #4\n")
+		"LSR	D0Ar2, D0Ar2, #6\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x1c\n"				\
+		"ADDZ	D0Ar2, D0Ar2, #16\n"				\
+		"SUB	%1, %1, D0Ar2\n")
 
 
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
-   userland.  The return-value is the number of bytes that were
-   inaccessible.  */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
-				  unsigned long n)
+/*
+ * Copy from user to kernel. The return-value is the number of bytes that were
+ * inaccessible.
+ */
+unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
+				 unsigned long n)
 {
 	register char *dst asm ("A0.2") = pdst;
 	register const char __user *src asm ("A1.2") = psrc;
@@ -830,6 +773,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 	if ((unsigned long) src & 1) {
 		__asm_copy_from_user_1(dst, src, retn);
 		n--;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 1) {
 		/* Worst case - byte copy */
@@ -837,12 +782,14 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_1(dst, src, retn);
 			n--;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 	if (((unsigned long) src & 2) && n >= 2) {
 		__asm_copy_from_user_2(dst, src, retn);
 		n -= 2;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 2) {
 		/* Second worst case - word copy */
@@ -850,16 +797,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_2(dst, src, retn);
 			n -= 2;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 
-	/* We only need one check after the unalignment-adjustments,
-	   because if both adjustments were done, either both or
-	   neither reference had an exception.  */
-	if (retn != 0)
-		goto copy_exception_bytes;
-
 #ifdef USE_RAPF
 	/* 64 bit copy loop */
 	if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
@@ -872,7 +813,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_8x64(dst, src, retn);
 			n -= 8;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 
@@ -888,7 +829,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_8x64(dst, src, retn);
 			n -= 8;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 #endif
@@ -898,7 +839,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 		n -= 4;
 
 		if (retn)
-			goto copy_exception_bytes;
+			return retn + n;
 	}
 
 	/* If we get here, there were no memory read faults.  */
@@ -924,21 +865,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 	/* If we get here, retn correctly reflects the number of failing
 	   bytes.  */
 	return retn;
-
- copy_exception_bytes:
-	/* We already have "retn" bytes cleared, and need to clear the
-	   remaining "n" bytes.  A non-optimized simple byte-for-byte in-line
-	   memset is preferred here, since this isn't speed-critical code and
-	   we'd rather have this a leaf-function than calling memset.  */
-	{
-		char *endp;
-		for (endp = dst + n; dst < endp; dst++)
-			*dst = 0;
-	}
-
-	return retn + n;
 }
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(raw_copy_from_user);
 
 #define __asm_clear_8x64(to, ret) \
 	asm volatile (					\
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 1732ec13b211..56830ff65333 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += device.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index fd850879854d..d506bb0893f9 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -95,7 +95,8 @@ typedef struct { unsigned long pgd; } pgd_t;
 #   else /* CONFIG_MMU */
 typedef struct { unsigned long	ste[64]; }	pmd_t;
 typedef struct { pmd_t		pue[1]; }	pud_t;
-typedef struct { pud_t		pge[1]; }	pgd_t;
+typedef struct { pud_t		p4e[1]; }	p4d_t;
+typedef struct { p4d_t		pge[1]; }	pgd_t;
 #   endif /* CONFIG_MMU */
 
 # define pte_val(x)	((x).pte)
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 253a67e275ad..38f2c9ccef10 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -11,22 +11,15 @@
 #ifndef _ASM_MICROBLAZE_UACCESS_H
 #define _ASM_MICROBLAZE_UACCESS_H
 
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
 #include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/sched.h> /* RLIMIT_FSIZE */
 #include <linux/mm.h>
 
 #include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/extable.h>
 #include <linux/string.h>
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 /*
  * On Microblaze the fs value is actually the top of the corresponding
  * address space.
@@ -55,22 +48,6 @@
 
 # define segment_eq(a, b)	((a).seg == (b).seg)
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
 #ifndef CONFIG_MMU
 
 /* Check against bounds of physical memory */
@@ -359,39 +336,19 @@ extern long __user_bad(void);
 	__gu_err;							\
 })
 
-
-/* copy_to_from_user */
-#define __copy_from_user(to, from, n)	\
-	__copy_tofrom_user((__force void __user *)(to), \
-				(void __user *)(from), (n))
-#define __copy_from_user_inatomic(to, from, n) \
-		__copy_from_user((to), (from), (n))
-
-static inline long copy_from_user(void *to,
-		const void __user *from, unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	unsigned long res = n;
-	might_fault();
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		res = __copy_from_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
+	return __copy_tofrom_user((__force void __user *)to, from, n);
 }
 
-#define __copy_to_user(to, from, n)	\
-		__copy_tofrom_user((void __user *)(to), \
-			(__force const void __user *)(from), (n))
-#define __copy_to_user_inatomic(to, from, n) __copy_to_user((to), (from), (n))
-
-static inline long copy_to_user(void __user *to,
-		const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	might_fault();
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_to_user(to, from, n);
-	return n;
+	return __copy_tofrom_user(to, (__force const void __user *)from, n);
 }
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 /*
  * Copy a null terminated string from userspace.
@@ -422,7 +379,4 @@ static inline long strnlen_user(const char __user *src, long n)
 	return __strnlen_user(src, n);
 }
 
-#endif  /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
 #endif /* _ASM_MICROBLAZE_UACCESS_H */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a008a9f03072..d6d545a45118 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -68,7 +68,6 @@ config MIPS
 	select HANDLE_DOMAIN_IRQ
 	select HAVE_EXIT_THREAD
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_ARCH_HARDENED_USERCOPY
 
 menu "Machine selection"
 
@@ -1531,7 +1530,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
-	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+	select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
 	select HAVE_KVM
 	help
 	  Choose this option to build a kernel for release 6 or later of the
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 8ef9c02747fa..02a1787c888c 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -489,7 +489,7 @@ $(generic_defconfigs):
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
 		-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/generic_defconfig $^ \
 		$(foreach board,$(BOARDS),$(generic_config_dir)/board-$(board).config)
-	$(Q)$(MAKE) olddefconfig
+	$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 
 #
 # Prevent generic merge_config rules attempting to merge single fragments
@@ -503,8 +503,8 @@ $(generic_config_dir)/%.config: ;
 #
 .PHONY: sead3_defconfig
 sead3_defconfig:
-	$(Q)$(MAKE) 32r2el_defconfig BOARDS=sead-3
+	$(Q)$(MAKE) -f $(srctree)/Makefile 32r2el_defconfig BOARDS=sead-3
 
 .PHONY: sead3micro_defconfig
 sead3micro_defconfig:
-	$(Q)$(MAKE) micro32r2el_defconfig BOARDS=sead-3
+	$(Q)$(MAKE) -f $(srctree)/Makefile micro32r2el_defconfig BOARDS=sead-3
diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c
index e1bec5a77c39..32d1333bb243 100644
--- a/arch/mips/alchemy/common/time.c
+++ b/arch/mips/alchemy/common/time.c
@@ -138,7 +138,9 @@ static int __init alchemy_time_init(unsigned int m2int)
 	cd->shift = 32;
 	cd->mult = div_sc(32768, NSEC_PER_SEC, cd->shift);
 	cd->max_delta_ns = clockevent_delta2ns(0xffffffff, cd);
-	cd->min_delta_ns = clockevent_delta2ns(9, cd);	/* ~0.28ms */
+	cd->max_delta_ticks = 0xffffffff;
+	cd->min_delta_ns = clockevent_delta2ns(9, cd);
+	cd->min_delta_ticks = 9;	/* ~0.28ms */
 	clockevents_register_device(cd);
 	setup_irq(m2int, &au1x_rtcmatch2_irqaction);
 
diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c
index a5b427909b5c..036d56cc4591 100644
--- a/arch/mips/cavium-octeon/cpu.c
+++ b/arch/mips/cavium-octeon/cpu.c
@@ -10,7 +10,9 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.c b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
index 4d22365844af..cfb4a146cf17 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-crypto.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
@@ -9,6 +9,7 @@
 #include <asm/cop2.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
+#include <linux/sched/task_stack.h>
 
 #include "octeon-crypto.h"
 
diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S
index cfd97f6448bb..0a7c9834b81c 100644
--- a/arch/mips/cavium-octeon/octeon-memcpy.S
+++ b/arch/mips/cavium-octeon/octeon-memcpy.S
@@ -140,15 +140,6 @@
 	.set	noat
 
 /*
- * t7 is used as a flag to note inatomic mode.
- */
-LEAF(__copy_user_inatomic)
-EXPORT_SYMBOL(__copy_user_inatomic)
-	b	__copy_user_common
-	 li	t7, 1
-	END(__copy_user_inatomic)
-
-/*
  * A combined memcpy/__copy_user
  * __copy_user sets len to 0 for success; else to an upper bound of
  * the number of uncopied bytes.
@@ -161,8 +152,6 @@ EXPORT_SYMBOL(memcpy)
 __memcpy:
 FEXPORT(__copy_user)
 EXPORT_SYMBOL(__copy_user)
-	li	t7, 0				/* not inatomic */
-__copy_user_common:
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
 	 * Temps
@@ -414,25 +403,7 @@ l_exc:
 	LOAD	t0, TI_TASK($28)
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
 	SUB	len, AT, t0		# len number of uncopied bytes
-	bnez	t7, 2f		/* Skip the zeroing out part if inatomic */
-	/*
-	 * Here's where we rely on src and dst being incremented in tandem,
-	 *   See (3) above.
-	 * dst += (fault addr - src) to put dst at first byte to clear
-	 */
-	ADD	dst, t0			# compute start address in a1
-	SUB	dst, src
-	/*
-	 * Clear len bytes starting at dst.  Can't call __bzero because it
-	 * might modify len.  An inefficient loop for these rare times...
-	 */
-	beqz	len, done
-	 SUB	src, len, 1
-1:	sb	zero, 0(dst)
-	ADD	dst, dst, 1
-	bnez	src, 1b
-	 SUB	src, src, 1
-2:	jr	ra
+	jr	ra
 	 nop
 
 
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 4b94b7fbafa3..3de786545ded 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -12,6 +12,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/init.h>
 #include <linux/export.h>
 
diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig
index 31e3c4d9adb0..d4fda41f00ba 100644
--- a/arch/mips/configs/cavium_octeon_defconfig
+++ b/arch/mips/configs/cavium_octeon_defconfig
@@ -127,6 +127,11 @@ CONFIG_USB_EHCI_HCD=m
 CONFIG_USB_EHCI_HCD_PLATFORM=m
 CONFIG_USB_OHCI_HCD=m
 CONFIG_USB_OHCI_HCD_PLATFORM=m
+CONFIG_MMC=y
+# CONFIG_PWRSEQ_EMMC is not set
+# CONFIG_PWRSEQ_SIMPLE is not set
+# CONFIG_MMC_BLOCK_BOUNCE is not set
+CONFIG_MMC_CAVIUM_OCTEON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_STAGING=y
diff --git a/arch/mips/include/asm/asm-prototypes.h b/arch/mips/include/asm/asm-prototypes.h
index a160cf69bb92..6e28971fe73a 100644
--- a/arch/mips/include/asm/asm-prototypes.h
+++ b/arch/mips/include/asm/asm-prototypes.h
@@ -3,3 +3,4 @@
 #include <asm/fpu.h>
 #include <asm-generic/asm-prototypes.h>
 #include <asm/uaccess.h>
+#include <asm/ftrace.h>
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index c8b574f7e0cc..77cad232a1c6 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -50,7 +50,7 @@ __wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len,
 				   __wsum sum, int *err_ptr)
 {
 	might_fault();
-	if (segment_eq(get_fs(), get_ds()))
+	if (uaccess_kernel())
 		return __csum_partial_copy_kernel((__force void *)src, dst,
 						  len, sum, err_ptr);
 	else
@@ -82,7 +82,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
 {
 	might_fault();
 	if (access_ok(VERIFY_WRITE, dst, len)) {
-		if (segment_eq(get_fs(), get_ds()))
+		if (uaccess_kernel())
 			return __csum_partial_copy_kernel(src,
 							  (__force void *)dst,
 							  len, sum, err_ptr);
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 321752bcbab6..a2813fe381cf 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/ptrace.h>
 #include <linux/thread_info.h>
 #include <linux/bitops.h>
 
@@ -20,6 +21,7 @@
 #include <asm/cpu-features.h>
 #include <asm/fpu_emulator.h>
 #include <asm/hazards.h>
+#include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/current.h>
 #include <asm/msa.h>
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 956db6e201d1..ddd1c918103b 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -18,9 +18,24 @@
 #include <irq.h>
 
 #define IRQ_STACK_SIZE			THREAD_SIZE
+#define IRQ_STACK_START			(IRQ_STACK_SIZE - sizeof(unsigned long))
 
 extern void *irq_stack[NR_CPUS];
 
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ *   top ------------
+ *       | task sp  | <- irq_stack[cpu] + IRQ_STACK_START
+ *       ------------
+ *       |          | <- First frame of IRQ context
+ *       ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
 static inline bool on_irq_stack(int cpu, unsigned long sp)
 {
 	unsigned long low = (unsigned long)irq_stack[cpu];
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index d21f3da7bdb6..6f94bed571c4 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -16,6 +16,7 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 extern int temp_tlb_entry;
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 514cbc0a6a67..130a2a6c1531 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -17,6 +17,7 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
+#define __ARCH_USE_5LEVEL_HACK
 #if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48)
 #include <asm-generic/pgtable-nopmd.h>
 #else
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 55fd94e6cd0b..7f12d7e27c94 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -20,7 +20,7 @@
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/mipsmtregs.h>
-#include <linux/uaccess.h> /* for segment_eq() */
+#include <linux/uaccess.h> /* for uaccess_kernel() */
 
 extern void (*r4k_blast_dcache)(void);
 extern void (*r4k_blast_icache)(void);
@@ -714,7 +714,7 @@ static inline void protected_blast_##pfx##cache##_range(unsigned long start,\
 									\
 	__##pfx##flush_prologue						\
 									\
-	if (segment_eq(get_fs(), USER_DS)) {				\
+	if (!uaccess_kernel()) {					\
 		while (1) {						\
 			protected_cachee_op(hitop, addr);		\
 			if (addr == aend)				\
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index f485afe51514..a8df44d60607 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -127,7 +127,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	bne	%[ticket], %[my_ticket], 4f		\n"
 		"	 subu	%[ticket], %[my_ticket], %[ticket]	\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"4:	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	sll	%[ticket], 5				\n"
@@ -202,7 +202,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	sc	%[ticket], %[ticket_ptr]		\n"
 		"	beqz	%[ticket], 1b				\n"
 		"	 li	%[ticket], 1				\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"3:	b	2b					\n"
 		"	 li	%[ticket], 0				\n"
@@ -382,7 +382,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		"	.set	reorder					\n"
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
 		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
@@ -422,7 +422,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 			"	lui	%1, 0x8000			\n"
 			"	sc	%1, %0				\n"
 			"	li	%2, 1				\n"
-			"2:						\n"
+			"2:	.insn					\n"
 			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
 			  "=&r" (ret)
 			: GCC_OFF_SMALL_ASM() (rw->lock)
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 5347cfe15af2..99e629a590a5 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -12,8 +12,6 @@
 #define _ASM_UACCESS_H
 
 #include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/thread_info.h>
 #include <linux/string.h>
 #include <asm/asm-eva.h>
 #include <asm/extable.h>
@@ -71,9 +69,6 @@ extern u64 __ua_limit;
 #define USER_DS		((mm_segment_t) { __UA_LIMIT })
 #endif
 
-#define VERIFY_READ    0
-#define VERIFY_WRITE   1
-
 #define get_ds()	(KERNEL_DS)
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
@@ -93,7 +88,7 @@ static inline bool eva_kernel_access(void)
 	if (!IS_ENABLED(CONFIG_EVA))
 		return false;
 
-	return segment_eq(get_fs(), get_ds());
+	return uaccess_kernel();
 }
 
 /*
@@ -133,23 +128,14 @@ static inline bool eva_kernel_access(void)
  * this function, memory access functions may still return -EFAULT.
  */
 
-#define __access_mask get_fs().seg
-
-#define __access_ok(addr, size, mask)					\
-({									\
-	unsigned long __addr = (unsigned long) (addr);			\
-	unsigned long __size = size;					\
-	unsigned long __mask = mask;					\
-	unsigned long __ok;						\
-									\
-	__chk_user_ptr(addr);						\
-	__ok = (signed long)(__mask & (__addr | (__addr + __size) |	\
-		__ua_size(__size)));					\
-	__ok == 0;							\
-})
+static inline int __access_ok(const void __user *p, unsigned long size)
+{
+	unsigned long addr = (unsigned long)p;
+	return (get_fs().seg & (addr | (addr + size) | __ua_size(size))) == 0;
+}
 
 #define access_ok(type, addr, size)					\
-	likely(__access_ok((addr), (size), __access_mask))
+	likely(__access_ok((addr), (size)))
 
 /*
  * put_user: - Write a simple value into user space.
@@ -811,157 +797,7 @@ extern void __put_user_unaligned_unknown(void);
 
 extern size_t __copy_user(void *__to, const void *__from, size_t __n);
 
-#ifndef CONFIG_EVA
-#define __invoke_copy_to_user(to, from, n)				\
-({									\
-	register void __user *__cu_to_r __asm__("$4");			\
-	register const void *__cu_from_r __asm__("$5");			\
-	register long __cu_len_r __asm__("$6");				\
-									\
-	__cu_to_r = (to);						\
-	__cu_from_r = (from);						\
-	__cu_len_r = (n);						\
-	__asm__ __volatile__(						\
-	__MODULE_JAL(__copy_user)					\
-	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
-	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
-	  DADDI_SCRATCH, "memory");					\
-	__cu_len_r;							\
-})
-
-#define __invoke_copy_to_kernel(to, from, n)				\
-	__invoke_copy_to_user(to, from, n)
-
-#endif
-
-/*
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:	  Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:	  Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define __copy_to_user(to, from, n)					\
-({									\
-	void __user *__cu_to;						\
-	const void *__cu_from;						\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-									\
-	check_object_size(__cu_from, __cu_len, true);			\
-	might_fault();							\
-									\
-	if (eva_kernel_access())					\
-		__cu_len = __invoke_copy_to_kernel(__cu_to, __cu_from,	\
-						   __cu_len);		\
-	else								\
-		__cu_len = __invoke_copy_to_user(__cu_to, __cu_from,	\
-						 __cu_len);		\
-	__cu_len;							\
-})
-
-extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
-
-#define __copy_to_user_inatomic(to, from, n)				\
-({									\
-	void __user *__cu_to;						\
-	const void *__cu_from;						\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-									\
-	check_object_size(__cu_from, __cu_len, true);			\
-									\
-	if (eva_kernel_access())					\
-		__cu_len = __invoke_copy_to_kernel(__cu_to, __cu_from,	\
-						   __cu_len);		\
-	else								\
-		__cu_len = __invoke_copy_to_user(__cu_to, __cu_from,	\
-						 __cu_len);		\
-	__cu_len;							\
-})
-
-#define __copy_from_user_inatomic(to, from, n)				\
-({									\
-	void *__cu_to;							\
-	const void __user *__cu_from;					\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-									\
-	check_object_size(__cu_to, __cu_len, false);			\
-									\
-	if (eva_kernel_access())					\
-		__cu_len = __invoke_copy_from_kernel_inatomic(__cu_to,	\
-							      __cu_from,\
-							      __cu_len);\
-	else								\
-		__cu_len = __invoke_copy_from_user_inatomic(__cu_to,	\
-							    __cu_from,	\
-							    __cu_len);	\
-	__cu_len;							\
-})
-
-/*
- * copy_to_user: - Copy a block of data into user space.
- * @to:	  Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:	  Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define copy_to_user(to, from, n)					\
-({									\
-	void __user *__cu_to;						\
-	const void *__cu_from;						\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-									\
-	check_object_size(__cu_from, __cu_len, true);			\
-									\
-	if (eva_kernel_access()) {					\
-		__cu_len = __invoke_copy_to_kernel(__cu_to,		\
-						   __cu_from,		\
-						   __cu_len);		\
-	} else {							\
-		if (access_ok(VERIFY_WRITE, __cu_to, __cu_len)) {       \
-			might_fault();                                  \
-			__cu_len = __invoke_copy_to_user(__cu_to,	\
-							 __cu_from,	\
-							 __cu_len);     \
-		}							\
-	}								\
-	__cu_len;							\
-})
-
-#ifndef CONFIG_EVA
-
-#define __invoke_copy_from_user(to, from, n)				\
+#define __invoke_copy_from(func, to, from, n)				\
 ({									\
 	register void *__cu_to_r __asm__("$4");				\
 	register const void __user *__cu_from_r __asm__("$5");		\
@@ -972,7 +808,7 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	__cu_len_r = (n);						\
 	__asm__ __volatile__(						\
 	".set\tnoreorder\n\t"						\
-	__MODULE_JAL(__copy_user)					\
+	__MODULE_JAL(func)						\
 	".set\tnoat\n\t"						\
 	__UA_ADDU "\t$1, %1, %2\n\t"					\
 	".set\tat\n\t"							\
@@ -984,33 +820,17 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	__cu_len_r;							\
 })
 
-#define __invoke_copy_from_kernel(to, from, n)				\
-	__invoke_copy_from_user(to, from, n)
-
-/* For userland <-> userland operations */
-#define ___invoke_copy_in_user(to, from, n)				\
-	__invoke_copy_from_user(to, from, n)
-
-/* For kernel <-> kernel operations */
-#define ___invoke_copy_in_kernel(to, from, n)				\
-	__invoke_copy_from_user(to, from, n)
-
-#define __invoke_copy_from_user_inatomic(to, from, n)			\
+#define __invoke_copy_to(func, to, from, n)				\
 ({									\
-	register void *__cu_to_r __asm__("$4");				\
-	register const void __user *__cu_from_r __asm__("$5");		\
+	register void __user *__cu_to_r __asm__("$4");			\
+	register const void *__cu_from_r __asm__("$5");			\
 	register long __cu_len_r __asm__("$6");				\
 									\
 	__cu_to_r = (to);						\
 	__cu_from_r = (from);						\
 	__cu_len_r = (n);						\
 	__asm__ __volatile__(						\
-	".set\tnoreorder\n\t"						\
-	__MODULE_JAL(__copy_user_inatomic)				\
-	".set\tnoat\n\t"						\
-	__UA_ADDU "\t$1, %1, %2\n\t"					\
-	".set\tat\n\t"							\
-	".set\treorder"							\
+	__MODULE_JAL(func)						\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
 	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
@@ -1018,228 +838,79 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	__cu_len_r;							\
 })
 
-#define __invoke_copy_from_kernel_inatomic(to, from, n)			\
-	__invoke_copy_from_user_inatomic(to, from, n)			\
+#define __invoke_copy_from_kernel(to, from, n)				\
+	__invoke_copy_from(__copy_user, to, from, n)
+
+#define __invoke_copy_to_kernel(to, from, n)				\
+	__invoke_copy_to(__copy_user, to, from, n)
+
+#define ___invoke_copy_in_kernel(to, from, n)				\
+	__invoke_copy_from(__copy_user, to, from, n)
+
+#ifndef CONFIG_EVA
+#define __invoke_copy_from_user(to, from, n)				\
+	__invoke_copy_from(__copy_user, to, from, n)
+
+#define __invoke_copy_to_user(to, from, n)				\
+	__invoke_copy_to(__copy_user, to, from, n)
+
+#define ___invoke_copy_in_user(to, from, n)				\
+	__invoke_copy_from(__copy_user, to, from, n)
 
 #else
 
 /* EVA specific functions */
 
-extern size_t __copy_user_inatomic_eva(void *__to, const void *__from,
-				       size_t __n);
 extern size_t __copy_from_user_eva(void *__to, const void *__from,
 				   size_t __n);
 extern size_t __copy_to_user_eva(void *__to, const void *__from,
 				 size_t __n);
 extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
 
-#define __invoke_copy_from_user_eva_generic(to, from, n, func_ptr)	\
-({									\
-	register void *__cu_to_r __asm__("$4");				\
-	register const void __user *__cu_from_r __asm__("$5");		\
-	register long __cu_len_r __asm__("$6");				\
-									\
-	__cu_to_r = (to);						\
-	__cu_from_r = (from);						\
-	__cu_len_r = (n);						\
-	__asm__ __volatile__(						\
-	".set\tnoreorder\n\t"						\
-	__MODULE_JAL(func_ptr)						\
-	".set\tnoat\n\t"						\
-	__UA_ADDU "\t$1, %1, %2\n\t"					\
-	".set\tat\n\t"							\
-	".set\treorder"							\
-	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
-	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
-	  DADDI_SCRATCH, "memory");					\
-	__cu_len_r;							\
-})
-
-#define __invoke_copy_to_user_eva_generic(to, from, n, func_ptr)	\
-({									\
-	register void *__cu_to_r __asm__("$4");				\
-	register const void __user *__cu_from_r __asm__("$5");		\
-	register long __cu_len_r __asm__("$6");				\
-									\
-	__cu_to_r = (to);						\
-	__cu_from_r = (from);						\
-	__cu_len_r = (n);						\
-	__asm__ __volatile__(						\
-	__MODULE_JAL(func_ptr)						\
-	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
-	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
-	  DADDI_SCRATCH, "memory");					\
-	__cu_len_r;							\
-})
-
 /*
  * Source or destination address is in userland. We need to go through
  * the TLB
  */
 #define __invoke_copy_from_user(to, from, n)				\
-	__invoke_copy_from_user_eva_generic(to, from, n, __copy_from_user_eva)
-
-#define __invoke_copy_from_user_inatomic(to, from, n)			\
-	__invoke_copy_from_user_eva_generic(to, from, n,		\
-					    __copy_user_inatomic_eva)
+	__invoke_copy_from(__copy_from_user_eva, to, from, n)
 
 #define __invoke_copy_to_user(to, from, n)				\
-	__invoke_copy_to_user_eva_generic(to, from, n, __copy_to_user_eva)
+	__invoke_copy_to(__copy_to_user_eva, to, from, n)
 
 #define ___invoke_copy_in_user(to, from, n)				\
-	__invoke_copy_from_user_eva_generic(to, from, n, __copy_in_user_eva)
-
-/*
- * Source or destination address in the kernel. We are not going through
- * the TLB
- */
-#define __invoke_copy_from_kernel(to, from, n)				\
-	__invoke_copy_from_user_eva_generic(to, from, n, __copy_user)
-
-#define __invoke_copy_from_kernel_inatomic(to, from, n)			\
-	__invoke_copy_from_user_eva_generic(to, from, n, __copy_user_inatomic)
-
-#define __invoke_copy_to_kernel(to, from, n)				\
-	__invoke_copy_to_user_eva_generic(to, from, n, __copy_user)
-
-#define ___invoke_copy_in_kernel(to, from, n)				\
-	__invoke_copy_from_user_eva_generic(to, from, n, __copy_user)
+	__invoke_copy_from(__copy_in_user_eva, to, from, n)
 
 #endif /* CONFIG_EVA */
 
-/*
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to:	  Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:	  Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define __copy_from_user(to, from, n)					\
-({									\
-	void *__cu_to;							\
-	const void __user *__cu_from;					\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-									\
-	check_object_size(__cu_to, __cu_len, false);			\
-									\
-	if (eva_kernel_access()) {					\
-		__cu_len = __invoke_copy_from_kernel(__cu_to,		\
-						     __cu_from,		\
-						     __cu_len);		\
-	} else {							\
-		might_fault();						\
-		__cu_len = __invoke_copy_from_user(__cu_to, __cu_from,	\
-						   __cu_len);		\
-	}								\
-	__cu_len;							\
-})
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (eva_kernel_access())
+		return __invoke_copy_to_kernel(to, from, n);
+	else
+		return __invoke_copy_to_user(to, from, n);
+}
 
-/*
- * copy_from_user: - Copy a block of data from user space.
- * @to:	  Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:	  Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define copy_from_user(to, from, n)					\
-({									\
-	void *__cu_to;							\
-	const void __user *__cu_from;					\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-									\
-	check_object_size(__cu_to, __cu_len, false);			\
-									\
-	if (eva_kernel_access()) {					\
-		__cu_len = __invoke_copy_from_kernel(__cu_to,		\
-						     __cu_from,		\
-						     __cu_len);		\
-	} else {							\
-		if (access_ok(VERIFY_READ, __cu_from, __cu_len)) {	\
-			might_fault();                                  \
-			__cu_len = __invoke_copy_from_user(__cu_to,	\
-							   __cu_from,	\
-							   __cu_len);   \
-		} else {						\
-			memset(__cu_to, 0, __cu_len);			\
-		}							\
-	}								\
-	__cu_len;							\
-})
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (eva_kernel_access())
+		return __invoke_copy_from_kernel(to, from, n);
+	else
+		return __invoke_copy_from_user(to, from, n);
+}
 
-#define __copy_in_user(to, from, n)					\
-({									\
-	void __user *__cu_to;						\
-	const void __user *__cu_from;					\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-	if (eva_kernel_access()) {					\
-		__cu_len = ___invoke_copy_in_kernel(__cu_to, __cu_from,	\
-						    __cu_len);		\
-	} else {							\
-		might_fault();						\
-		__cu_len = ___invoke_copy_in_user(__cu_to, __cu_from,	\
-						  __cu_len);		\
-	}								\
-	__cu_len;							\
-})
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
-#define copy_in_user(to, from, n)					\
-({									\
-	void __user *__cu_to;						\
-	const void __user *__cu_from;					\
-	long __cu_len;							\
-									\
-	__cu_to = (to);							\
-	__cu_from = (from);						\
-	__cu_len = (n);							\
-	if (eva_kernel_access()) {					\
-		__cu_len = ___invoke_copy_in_kernel(__cu_to,__cu_from,	\
-						    __cu_len);		\
-	} else {							\
-		if (likely(access_ok(VERIFY_READ, __cu_from, __cu_len) &&\
-			   access_ok(VERIFY_WRITE, __cu_to, __cu_len))) {\
-			might_fault();					\
-			__cu_len = ___invoke_copy_in_user(__cu_to,	\
-							  __cu_from,	\
-							  __cu_len);	\
-		}							\
-	}								\
-	__cu_len;							\
-})
+static inline unsigned long
+raw_copy_in_user(void __user*to, const void __user *from, unsigned long n)
+{
+	if (eva_kernel_access())
+		return ___invoke_copy_in_kernel(to, from, n);
+	else
+		return ___invoke_copy_in_user(to, from,	n);
+}
 
 extern __kernel_size_t __bzero_kernel(void __user *addr, __kernel_size_t size);
 extern __kernel_size_t __bzero(void __user *addr, __kernel_size_t size);
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 566ecdcb5b4b..3418ec9c1c50 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -110,4 +110,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 3e940dbe0262..78faf4292e90 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -386,17 +386,18 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 363)
 #define __NR_pkey_alloc			(__NR_Linux + 364)
 #define __NR_pkey_free			(__NR_Linux + 365)
+#define __NR_statx			(__NR_Linux + 366)
 
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		365
+#define __NR_Linux_syscalls		366
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		365
+#define __NR_O32_Linux_syscalls		366
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -730,16 +731,17 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 323)
 #define __NR_pkey_alloc			(__NR_Linux + 324)
 #define __NR_pkey_free			(__NR_Linux + 325)
+#define __NR_statx			(__NR_Linux + 326)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		325
+#define __NR_Linux_syscalls		326
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		325
+#define __NR_64_Linux_syscalls		326
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1077,15 +1079,16 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 327)
 #define __NR_pkey_alloc			(__NR_Linux + 328)
 #define __NR_pkey_free			(__NR_Linux + 329)
+#define __NR_statx			(__NR_Linux + 330)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		329
+#define __NR_Linux_syscalls		330
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		329
+#define __NR_N32_Linux_syscalls		330
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/jz4740/time.c b/arch/mips/jz4740/time.c
index bcf8f8c62737..bb1ad5119da4 100644
--- a/arch/mips/jz4740/time.c
+++ b/arch/mips/jz4740/time.c
@@ -145,7 +145,9 @@ void __init plat_time_init(void)
 
 	clockevent_set_clock(&jz4740_clockevent, clk_rate);
 	jz4740_clockevent.min_delta_ns = clockevent_delta2ns(100, &jz4740_clockevent);
+	jz4740_clockevent.min_delta_ticks = 100;
 	jz4740_clockevent.max_delta_ns = clockevent_delta2ns(0xffff, &jz4740_clockevent);
+	jz4740_clockevent.max_delta_ticks = 0xffff;
 	jz4740_clockevent.cpumask = cpumask_of(0);
 
 	clockevents_register_device(&jz4740_clockevent);
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index bb5c5d34ba81..a670c0c11875 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -102,6 +102,7 @@ void output_thread_info_defines(void)
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
 	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+	DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
 	BLANK();
 }
 
diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c
index 940ac00e9129..8f9f2daf06a3 100644
--- a/arch/mips/kernel/cevt-bcm1480.c
+++ b/arch/mips/kernel/cevt-bcm1480.c
@@ -123,7 +123,9 @@ void sb1480_clockevent_init(void)
 				  CLOCK_EVT_FEAT_ONESHOT;
 	clockevent_set_clock(cd, V_SCD_TIMER_FREQ);
 	cd->max_delta_ns	= clockevent_delta2ns(0x7fffff, cd);
+	cd->max_delta_ticks	= 0x7fffff;
 	cd->min_delta_ns	= clockevent_delta2ns(2, cd);
+	cd->min_delta_ticks	= 2;
 	cd->rating		= 200;
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
index 77a5ddf53f57..61ad9079fa16 100644
--- a/arch/mips/kernel/cevt-ds1287.c
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -128,7 +128,9 @@ int __init ds1287_clockevent_init(int irq)
 	cd->irq = irq;
 	clockevent_set_clock(cd, 32768);
 	cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+	cd->max_delta_ticks = 0x7fffffff;
 	cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+	cd->min_delta_ticks = 0x300;
 	cd->cpumask = cpumask_of(0);
 
 	clockevents_register_device(&ds1287_clockevent);
diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c
index 66040051151d..fd90c82dc17d 100644
--- a/arch/mips/kernel/cevt-gt641xx.c
+++ b/arch/mips/kernel/cevt-gt641xx.c
@@ -152,7 +152,9 @@ static int __init gt641xx_timer0_clockevent_init(void)
 	cd->rating = 200 + gt641xx_base_clock / 10000000;
 	clockevent_set_clock(cd, gt641xx_base_clock);
 	cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+	cd->max_delta_ticks = 0x7fffffff;
 	cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+	cd->min_delta_ticks = 0x300;
 	cd->cpumask = cpumask_of(0);
 
 	clockevents_register_device(&gt641xx_timer0_clockevent);
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 804d2a2a19fe..dd6a18bc10ab 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -80,7 +80,7 @@ static unsigned int calculate_min_delta(void)
 		}
 
 		/* Sorted insert of 75th percentile into buf2 */
-		for (k = 0; k < i; ++k) {
+		for (k = 0; k < i && k < ARRAY_SIZE(buf2); ++k) {
 			if (buf1[ARRAY_SIZE(buf1) - 1] < buf2[k]) {
 				l = min_t(unsigned int,
 					  i, ARRAY_SIZE(buf2) - 1);
diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c
index 3d860efd63b9..9d1edb5938b8 100644
--- a/arch/mips/kernel/cevt-sb1250.c
+++ b/arch/mips/kernel/cevt-sb1250.c
@@ -123,7 +123,9 @@ void sb1250_clockevent_init(void)
 				  CLOCK_EVT_FEAT_ONESHOT;
 	clockevent_set_clock(cd, V_SCD_TIMER_FREQ);
 	cd->max_delta_ns	= clockevent_delta2ns(0x7fffff, cd);
+	cd->max_delta_ticks	= 0x7fffff;
 	cd->min_delta_ns	= clockevent_delta2ns(2, cd);
+	cd->min_delta_ticks	= 2;
 	cd->rating		= 200;
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index aaca60d6ffc3..7b17c8f5009d 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -196,7 +196,9 @@ void __init txx9_clockevent_init(unsigned long baseaddr, int irq,
 	clockevent_set_clock(cd, TIMER_CLK(imbusclk));
 	cd->max_delta_ns =
 		clockevent_delta2ns(0xffffffff >> (32 - TXX9_TIMER_BITS), cd);
+	cd->max_delta_ticks = 0xffffffff >> (32 - TXX9_TIMER_BITS);
 	cd->min_delta_ns = clockevent_delta2ns(0xf, cd);
+	cd->min_delta_ticks = 0xf;
 	cd->irq = irq;
 	cd->cpumask = cpumask_of(0),
 	clockevents_register_device(cd);
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 59476a607add..a00e87b0256d 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -361,7 +361,7 @@ LEAF(mips_cps_get_bootcfg)
 	END(mips_cps_get_bootcfg)
 
 LEAF(mips_cps_boot_vpes)
-	PTR_L	ta2, COREBOOTCFG_VPEMASK(a0)
+	lw	ta2, COREBOOTCFG_VPEMASK(a0)
 	PTR_L	ta3, COREBOOTCFG_VPECONFIG(a0)
 
 #if defined(CONFIG_CPU_MIPSR6)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 07718bb5fc9d..12422fd4af23 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1824,7 +1824,7 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		}
 
 		decode_configs(c);
-		c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+		c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
 		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		break;
 	default:
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index 6430bff21fff..5c429d70e17f 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -257,7 +257,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr,
 	else if ((prog_req.fr1 && prog_req.frdefault) ||
 		 (prog_req.single && !prog_req.frdefault))
 		/* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */
-		state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
+		state->overall_fp_mode = ((raw_current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
 					  cpu_has_mips_r2_r6) ?
 					  FP_FR1 : FP_FR0;
 	else if (prog_req.fr1)
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 7ec9612cb007..ae810da4d499 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -215,9 +215,11 @@ NESTED(handle_int, PT_SIZE, sp)
 	beq	t0, t1, 2f
 
 	/* Switch to IRQ stack */
-	li	t1, _IRQ_STACK_SIZE
+	li	t1, _IRQ_STACK_START
 	PTR_ADD sp, t0, t1
 
+	/* Save task's sp on IRQ stack so that unwinding can follow it */
+	LONG_S	s1, 0(sp)
 2:
 	jal	plat_irq_dispatch
 
@@ -325,9 +327,11 @@ NESTED(except_vec_vi_handler, 0, sp)
 	beq	t0, t1, 2f
 
 	/* Switch to IRQ stack */
-	li	t1, _IRQ_STACK_SIZE
+	li	t1, _IRQ_STACK_START
 	PTR_ADD sp, t0, t1
 
+	/* Save task's sp on IRQ stack so that unwinding can follow it */
+	LONG_S	s1, 0(sp)
 2:
 	jalr	v0
 
@@ -519,7 +523,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	BUILD_HANDLER reserved reserved sti verbose	/* others */
 
 	.align	5
-	LEAF(handle_ri_rdhwr_vivt)
+	LEAF(handle_ri_rdhwr_tlbp)
 	.set	push
 	.set	noat
 	.set	noreorder
@@ -538,7 +542,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	pop
 	bltz	k1, handle_ri	/* slow path */
 	/* fall thru */
-	END(handle_ri_rdhwr_vivt)
+	END(handle_ri_rdhwr_tlbp)
 
 	LEAF(handle_ri_rdhwr)
 	.set	push
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index 1f4bd222ba76..eb6c0d582626 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -244,9 +244,6 @@ static int compute_signal(int tt)
 void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
 	int reg;
-	struct thread_info *ti = task_thread_info(p);
-	unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32;
-	struct pt_regs *regs = (struct pt_regs *)ksp - 1;
 #if (KGDB_GDB_REG_SIZE == 32)
 	u32 *ptr = (u32 *)gdb_regs;
 #else
@@ -254,25 +251,46 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 #endif
 
 	for (reg = 0; reg < 16; reg++)
-		*(ptr++) = regs->regs[reg];
+		*(ptr++) = 0;
 
 	/* S0 - S7 */
-	for (reg = 16; reg < 24; reg++)
-		*(ptr++) = regs->regs[reg];
+	*(ptr++) = p->thread.reg16;
+	*(ptr++) = p->thread.reg17;
+	*(ptr++) = p->thread.reg18;
+	*(ptr++) = p->thread.reg19;
+	*(ptr++) = p->thread.reg20;
+	*(ptr++) = p->thread.reg21;
+	*(ptr++) = p->thread.reg22;
+	*(ptr++) = p->thread.reg23;
 
 	for (reg = 24; reg < 28; reg++)
 		*(ptr++) = 0;
 
 	/* GP, SP, FP, RA */
-	for (reg = 28; reg < 32; reg++)
-		*(ptr++) = regs->regs[reg];
-
-	*(ptr++) = regs->cp0_status;
-	*(ptr++) = regs->lo;
-	*(ptr++) = regs->hi;
-	*(ptr++) = regs->cp0_badvaddr;
-	*(ptr++) = regs->cp0_cause;
-	*(ptr++) = regs->cp0_epc;
+	*(ptr++) = (long)p;
+	*(ptr++) = p->thread.reg29;
+	*(ptr++) = p->thread.reg30;
+	*(ptr++) = p->thread.reg31;
+
+	*(ptr++) = p->thread.cp0_status;
+
+	/* lo, hi */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * BadVAddr, Cause
+	 * Ideally these would come from the last exception frame up the stack
+	 * but that requires unwinding, otherwise we can't know much for sure.
+	 */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * PC
+	 * use return address (RA), i.e. the moment after return from resume()
+	 */
+	*(ptr++) = p->thread.reg31;
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index d8f1cf1ec370..550e7d03090a 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -1200,7 +1200,7 @@ fpu_emul:
 	case lwl_op:
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+		if (!access_ok(VERIFY_READ, (void __user *)vaddr, 4)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1273,7 +1273,7 @@ fpu_emul:
 	case lwr_op:
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+		if (!access_ok(VERIFY_READ, (void __user *)vaddr, 4)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1347,7 +1347,7 @@ fpu_emul:
 	case swl_op:
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+		if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 4)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1417,7 +1417,7 @@ fpu_emul:
 	case swr_op:
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+		if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 4)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1492,7 +1492,7 @@ fpu_emul:
 
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+		if (!access_ok(VERIFY_READ, (void __user *)vaddr, 8)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1611,7 +1611,7 @@ fpu_emul:
 
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+		if (!access_ok(VERIFY_READ, (void __user *)vaddr, 8)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1730,7 +1730,7 @@ fpu_emul:
 
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+		if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 8)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1848,7 +1848,7 @@ fpu_emul:
 
 		rt = regs->regs[MIPSInst_RT(inst)];
 		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
-		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+		if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 8)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGSEGV;
 			break;
@@ -1965,7 +1965,7 @@ fpu_emul:
 			err = SIGBUS;
 			break;
 		}
-		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+		if (!access_ok(VERIFY_READ, (void __user *)vaddr, 4)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGBUS;
 			break;
@@ -2021,7 +2021,7 @@ fpu_emul:
 			err = SIGBUS;
 			break;
 		}
-		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+		if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 4)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGBUS;
 			break;
@@ -2084,7 +2084,7 @@ fpu_emul:
 			err = SIGBUS;
 			break;
 		}
-		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+		if (!access_ok(VERIFY_READ, (void __user *)vaddr, 8)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGBUS;
 			break;
@@ -2145,7 +2145,7 @@ fpu_emul:
 			err = SIGBUS;
 			break;
 		}
-		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+		if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 8)) {
 			current->thread.cp0_baduaddr = vaddr;
 			err = SIGBUS;
 			break;
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 8c35b3152e1e..9452b02ce079 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1446,6 +1446,11 @@ static int mipsxx_pmu_handle_shared_irq(void)
 	HANDLE_COUNTER(0)
 	}
 
+#ifdef CONFIG_MIPS_PERF_SHARED_TC_COUNTERS
+	read_unlock(&pmuint_rwlock);
+#endif
+	resume_local_counters();
+
 	/*
 	 * Do all the work for the pending perf events. We can do this
 	 * in here because the performance counter interrupt is a regular
@@ -1454,10 +1459,6 @@ static int mipsxx_pmu_handle_shared_irq(void)
 	if (handled == IRQ_HANDLED)
 		irq_work_run();
 
-#ifdef CONFIG_MIPS_PERF_SHARED_TC_COUNTERS
-	read_unlock(&pmuint_rwlock);
-#endif
-	resume_local_counters();
 	return handled;
 }
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index fb6b6b650719..b68e10fc453d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -488,31 +488,52 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 					      unsigned long pc,
 					      unsigned long *ra)
 {
+	unsigned long low, high, irq_stack_high;
 	struct mips_frame_info info;
 	unsigned long size, ofs;
+	struct pt_regs *regs;
 	int leaf;
-	extern void ret_from_irq(void);
-	extern void ret_from_exception(void);
 
 	if (!stack_page)
 		return 0;
 
 	/*
-	 * If we reached the bottom of interrupt context,
-	 * return saved pc in pt_regs.
+	 * IRQ stacks start at IRQ_STACK_START
+	 * task stacks at THREAD_SIZE - 32
 	 */
-	if (pc == (unsigned long)ret_from_irq ||
-	    pc == (unsigned long)ret_from_exception) {
-		struct pt_regs *regs;
-		if (*sp >= stack_page &&
-		    *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
-			regs = (struct pt_regs *)*sp;
-			pc = regs->cp0_epc;
-			if (!user_mode(regs) && __kernel_text_address(pc)) {
-				*sp = regs->regs[29];
-				*ra = regs->regs[31];
-				return pc;
-			}
+	low = stack_page;
+	if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+		high = stack_page + IRQ_STACK_START;
+		irq_stack_high = high;
+	} else {
+		high = stack_page + THREAD_SIZE - 32;
+		irq_stack_high = 0;
+	}
+
+	/*
+	 * If we reached the top of the interrupt stack, start unwinding
+	 * the interrupted task stack.
+	 */
+	if (unlikely(*sp == irq_stack_high)) {
+		unsigned long task_sp = *(unsigned long *)*sp;
+
+		/*
+		 * Check that the pointer saved in the IRQ stack head points to
+		 * something within the stack of the current task
+		 */
+		if (!object_is_on_stack((void *)task_sp))
+			return 0;
+
+		/*
+		 * Follow pointer to tasks kernel stack frame where interrupted
+		 * state was saved.
+		 */
+		regs = (struct pt_regs *)task_sp;
+		pc = regs->cp0_epc;
+		if (!user_mode(regs) && __kernel_text_address(pc)) {
+			*sp = regs->regs[29];
+			*ra = regs->regs[31];
+			return pc;
 		}
 		return 0;
 	}
@@ -533,8 +554,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 	if (leaf < 0)
 		return 0;
 
-	if (*sp < stack_page ||
-	    *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+	if (*sp < low || *sp + info.frame_size > high)
 		return 0;
 
 	if (leaf)
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 339601267265..6931fe722a0b 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -456,7 +456,8 @@ static int fpr_set(struct task_struct *target,
 					  &target->thread.fpu,
 					  0, sizeof(elf_fpregset_t));
 
-	for (i = 0; i < NUM_FPU_REGS; i++) {
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) {
 		err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					 &fpr_val, i * sizeof(elf_fpreg_t),
 					 (i + 1) * sizeof(elf_fpreg_t));
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 9103bebc9a8e..2d1a0c438771 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/libfdt.h>
 #include <linux/of_fdt.h>
-#include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/start_kernel.h>
 #include <linux/string.h>
 #include <linux/printk.h>
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index c29d397eee86..80ed68b2c95e 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -600,3 +600,4 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
+	PTR	sys_statx
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 0687f96ee912..49765b44aa9b 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -438,4 +438,5 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 5325 */
+	PTR	sys_statx
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 0331ba39a065..90bad2d1b2d3 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -433,4 +433,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free
+	PTR	sys_statx			/* 6330 */
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 5a47042dd25f..2dd70bd104e1 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -588,4 +588,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
+	PTR	sys_statx
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 3daa2cae50b0..1b070a76fcdd 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 6d45f05538c8..795b4aaf8927 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -422,13 +422,12 @@ void play_dead(void)
 	local_irq_disable();
 	idle_task_exit();
 	cpu = smp_processor_id();
+	core = cpu_data[cpu].core;
 	cpu_death = CPU_DEATH_POWER;
 
 	pr_debug("CPU%d going offline\n", cpu);
 
 	if (cpu_has_mipsmt || cpu_has_vp) {
-		core = cpu_data[cpu].core;
-
 		/* Look for another online VPE within the core */
 		for_each_online_cpu(cpu_death_sibling) {
 			if (cpu_data[cpu_death_sibling].core != core)
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index e077ea3e11fb..e398cbc3d776 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/mips-gic.h>
 #include <linux/compiler.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 
 #include <linux/atomic.h>
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index f1d17ece4181..1dfa7f5796c7 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -98,7 +98,7 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 	if (unlikely(addr & 3))
 		return -EINVAL;
 
-	if (unlikely(!access_ok(VERIFY_WRITE, addr, 4)))
+	if (unlikely(!access_ok(VERIFY_WRITE, (const void __user *)addr, 4)))
 		return -EINVAL;
 
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index c7d17cfb32f6..b49e7bf9f950 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -83,7 +83,7 @@ extern asmlinkage void handle_dbe(void);
 extern asmlinkage void handle_sys(void);
 extern asmlinkage void handle_bp(void);
 extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_ri_rdhwr_vivt(void);
+extern asmlinkage void handle_ri_rdhwr_tlbp(void);
 extern asmlinkage void handle_ri_rdhwr(void);
 extern asmlinkage void handle_cpu(void);
 extern asmlinkage void handle_ov(void);
@@ -2408,9 +2408,18 @@ void __init trap_init(void)
 
 	set_except_vector(EXCCODE_SYS, handle_sys);
 	set_except_vector(EXCCODE_BP, handle_bp);
-	set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri :
-			  (cpu_has_vtag_icache ?
-			   handle_ri_rdhwr_vivt : handle_ri_rdhwr));
+
+	if (rdhwr_noopt)
+		set_except_vector(EXCCODE_RI, handle_ri);
+	else {
+		if (cpu_has_vtag_icache)
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+		else if (current_cpu_type() == CPU_LOONGSON3)
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+		else
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
+	}
+
 	set_except_vector(EXCCODE_CPU, handle_cpu);
 	set_except_vector(EXCCODE_OV, handle_ov);
 	set_except_vector(EXCCODE_TR, handle_tr);
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 7ed98354fe9d..f806ee56e639 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -1026,7 +1026,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			goto sigbus;
 
 		if (IS_ENABLED(CONFIG_EVA)) {
-			if (segment_eq(get_fs(), get_ds()))
+			if (uaccess_kernel())
 				LoadHW(addr, value, res);
 			else
 				LoadHWE(addr, value, res);
@@ -1045,7 +1045,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			goto sigbus;
 
 		if (IS_ENABLED(CONFIG_EVA)) {
-			if (segment_eq(get_fs(), get_ds()))
+			if (uaccess_kernel())
 				LoadW(addr, value, res);
 			else
 				LoadWE(addr, value, res);
@@ -1064,7 +1064,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			goto sigbus;
 
 		if (IS_ENABLED(CONFIG_EVA)) {
-			if (segment_eq(get_fs(), get_ds()))
+			if (uaccess_kernel())
 				LoadHWU(addr, value, res);
 			else
 				LoadHWUE(addr, value, res);
@@ -1132,7 +1132,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		value = regs->regs[insn.i_format.rt];
 
 		if (IS_ENABLED(CONFIG_EVA)) {
-			if (segment_eq(get_fs(), get_ds()))
+			if (uaccess_kernel())
 				StoreHW(addr, value, res);
 			else
 				StoreHWE(addr, value, res);
@@ -1152,7 +1152,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		value = regs->regs[insn.i_format.rt];
 
 		if (IS_ENABLED(CONFIG_EVA)) {
-			if (segment_eq(get_fs(), get_ds()))
+			if (uaccess_kernel())
 				StoreW(addr, value, res);
 			else
 				StoreWE(addr, value, res);
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index f0a0e6d62be3..8ca2371aa684 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -97,6 +97,7 @@ SECTIONS
 		DATA_DATA
 		CONSTRUCTORS
 	}
+	BUG_TABLE
 	_gp = . + 0x8000;
 	.lit8 : {
 		*(.lit8)
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 3c3aa05891dd..95bec460b651 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -467,7 +467,7 @@ void __init ltq_soc_init(void)
 
 		if (!np_xbar)
 			panic("Failed to load xbar nodes from devicetree");
-		if (of_address_to_resource(np_pmu, 0, &res_xbar))
+		if (of_address_to_resource(np_xbar, 0, &res_xbar))
 			panic("Failed to get xbar resources");
 		if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
 			res_xbar.name))
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index c3031f18c572..3114a2ed1f4e 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -562,39 +562,9 @@
 	LOADK	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
 	 nop
 	SUB	len, AT, t0		# len number of uncopied bytes
-	bnez	t6, .Ldone\@	/* Skip the zeroing part if inatomic */
-	/*
-	 * Here's where we rely on src and dst being incremented in tandem,
-	 *   See (3) above.
-	 * dst += (fault addr - src) to put dst at first byte to clear
-	 */
-	ADD	dst, t0			# compute start address in a1
-	SUB	dst, src
-	/*
-	 * Clear len bytes starting at dst.  Can't call __bzero because it
-	 * might modify len.  An inefficient loop for these rare times...
-	 */
-	.set	reorder				/* DADDI_WAR */
-	SUB	src, len, 1
-	beqz	len, .Ldone\@
-	.set	noreorder
-1:	sb	zero, 0(dst)
-	ADD	dst, dst, 1
-#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
-	bnez	src, 1b
-	 SUB	src, src, 1
-#else
-	.set	push
-	.set	noat
-	li	v1, 1
-	bnez	src, 1b
-	 SUB	src, src, v1
-	.set	pop
-#endif
 	jr	ra
 	 nop
 
-
 #define SEXC(n)							\
 	.set	reorder;			/* DADDI_WAR */ \
 .Ls_exc_p ## n ## u\@:						\
@@ -673,15 +643,6 @@ LEAF(__rmemcpy)					/* a0=dst a1=src a2=len */
 	END(__rmemcpy)
 
 /*
- * t6 is used as a flag to note inatomic mode.
- */
-LEAF(__copy_user_inatomic)
-EXPORT_SYMBOL(__copy_user_inatomic)
-	b	__copy_user_common
-	li	t6, 1
-	END(__copy_user_inatomic)
-
-/*
  * A combined memcpy/__copy_user
  * __copy_user sets len to 0 for success; else to an upper bound of
  * the number of uncopied bytes.
@@ -694,8 +655,6 @@ EXPORT_SYMBOL(memcpy)
 .L__memcpy:
 FEXPORT(__copy_user)
 EXPORT_SYMBOL(__copy_user)
-	li	t6, 0	/* not inatomic */
-__copy_user_common:
 	/* Legacy Mode, user <-> user */
 	__BUILD_COPY_USER LEGACY_MODE USEROP USEROP
 
@@ -708,20 +667,12 @@ __copy_user_common:
  * space
  */
 
-LEAF(__copy_user_inatomic_eva)
-EXPORT_SYMBOL(__copy_user_inatomic_eva)
-	b       __copy_from_user_common
-	li	t6, 1
-	END(__copy_user_inatomic_eva)
-
 /*
  * __copy_from_user (EVA)
  */
 
 LEAF(__copy_from_user_eva)
 EXPORT_SYMBOL(__copy_from_user_eva)
-	li	t6, 0	/* not inatomic */
-__copy_from_user_common:
 	__BUILD_COPY_USER EVA_MODE USEROP KERNELOP
 END(__copy_from_user_eva)
 
diff --git a/arch/mips/loongson32/common/time.c b/arch/mips/loongson32/common/time.c
index e6f972d35252..1c4332a26cf1 100644
--- a/arch/mips/loongson32/common/time.c
+++ b/arch/mips/loongson32/common/time.c
@@ -199,7 +199,9 @@ static void __init ls1x_time_init(void)
 
 	clockevent_set_clock(cd, mips_hpt_frequency);
 	cd->max_delta_ns = clockevent_delta2ns(0xffffff, cd);
+	cd->max_delta_ticks = 0xffffff;
 	cd->min_delta_ns = clockevent_delta2ns(0x000300, cd);
+	cd->min_delta_ticks = 0x000300;
 	cd->cpumask = cpumask_of(smp_processor_id());
 	clockevents_register_device(cd);
 
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
index b817d6d3a060..a6adcc4f8960 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
@@ -123,7 +123,9 @@ void __init setup_mfgpt0_timer(void)
 	cd->cpumask = cpumask_of(cpu);
 	clockevent_set_clock(cd, MFGPT_TICK_RATE);
 	cd->max_delta_ns = clockevent_delta2ns(0xffff, cd);
+	cd->max_delta_ticks = 0xffff;
 	cd->min_delta_ns = clockevent_delta2ns(0xf, cd);
+	cd->min_delta_ticks = 0xf;
 
 	/* Enable MFGPT0 Comparator 2 Output to the Interrupt Mapper */
 	_wrmsr(DIVIL_MSR_REG(MFGPT_IRQ), 0, 0x100);
diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/loongson-3/cop2-ex.c
index ea13764d0a03..621d6af5f6eb 100644
--- a/arch/mips/loongson64/loongson-3/cop2-ex.c
+++ b/arch/mips/loongson64/loongson-3/cop2-ex.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
+#include <linux/ptrace.h>
 
 #include <asm/fpu.h>
 #include <asm/cop2.h>
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index 24afe364637b..4df9d4b7356a 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -241,7 +241,9 @@ void __init setup_hpet_timer(void)
 	cd->cpumask = cpumask_of(cpu);
 	clockevent_set_clock(cd, HPET_FREQ);
 	cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+	cd->max_delta_ticks = 0x7fffffff;
 	cd->min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, cd);
+	cd->min_delta_ticks = HPET_MIN_PROG_DELTA;
 
 	clockevents_register_device(cd);
 	setup_irq(HPET_T0_IRQ, &hpet_irq);
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index e7f798d55fbc..3fe99cb271a9 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1562,6 +1562,7 @@ static void probe_vcache(void)
 	vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz;
 
 	c->vcache.waybit = 0;
+	c->vcache.waysize = vcache_size / c->vcache.ways;
 
 	pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
 		vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
@@ -1664,6 +1665,7 @@ static void __init loongson3_sc_init(void)
 	/* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */
 	scache_size *= 4;
 	c->scache.waybit = 0;
+	c->scache.waysize = scache_size / c->scache.ways;
 	pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
 	       scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
 	if (scache_size)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 9bfee8988eaf..4f642e07c2b1 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -760,7 +760,8 @@ static void build_huge_update_entries(u32 **p, unsigned int pte,
 static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 				    struct uasm_label **l,
 				    unsigned int pte,
-				    unsigned int ptr)
+				    unsigned int ptr,
+				    unsigned int flush)
 {
 #ifdef CONFIG_SMP
 	UASM_i_SC(p, pte, 0, ptr);
@@ -769,6 +770,22 @@ static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 #else
 	UASM_i_SW(p, pte, 0, ptr);
 #endif
+	if (cpu_has_ftlb && flush) {
+		BUG_ON(!cpu_has_tlbinv);
+
+		UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+		uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_tlb_write_entry(p, l, r, tlb_indexed);
+
+		uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_huge_update_entries(p, pte, ptr);
+		build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+		return;
+	}
+
 	build_huge_update_entries(p, pte, ptr);
 	build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
 }
@@ -2199,7 +2216,7 @@ static void build_r4000_tlb_load_handler(void)
 		uasm_l_tlbl_goaround2(&l, p);
 	}
 	uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbl(&l, p);
@@ -2254,7 +2271,7 @@ static void build_r4000_tlb_store_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbs(&l, p);
@@ -2310,7 +2327,7 @@ static void build_r4000_tlb_modify_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
 #endif
 
 	uasm_l_nopage_tlbm(&l, p);
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index cb675ec6f283..54f56d5a96c4 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -232,6 +232,17 @@ void __init arch_init_irq(void)
 {
 	int corehi_irq;
 
+	/*
+	 * Preallocate the i8259's expected virq's here. Since irqchip_init()
+	 * will probe the irqchips in hierarchial order, i8259 is probed last.
+	 * If anything allocates a virq before the i8259 is probed, it will
+	 * be given one of the i8259's expected range and consequently setup
+	 * of the i8259 will fail.
+	 */
+	WARN(irq_alloc_descs(I8259A_IRQ_BASE, I8259A_IRQ_BASE,
+			    16, numa_node_id()) < 0,
+		"Cannot reserve i8259 virqs at IRQ%d\n", I8259A_IRQ_BASE);
+
 	i8259_set_poll(mips_pcibios_iack);
 	irqchip_init();
 
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 1829a9031eec..289edcfadd7c 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -21,6 +21,7 @@
 #include <linux/i8253.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
+#include <linux/libfdt.h>
 #include <linux/math64.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
@@ -207,6 +208,33 @@ static void __init init_rtc(void)
 		CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
 }
 
+#ifdef CONFIG_CLKSRC_MIPS_GIC
+static u32 gic_frequency_dt;
+
+static struct property gic_frequency_prop = {
+	.name = "clock-frequency",
+	.length = sizeof(u32),
+	.value = &gic_frequency_dt,
+};
+
+static void update_gic_frequency_dt(void)
+{
+	struct device_node *node;
+
+	gic_frequency_dt = cpu_to_be32(gic_frequency);
+
+	node = of_find_compatible_node(NULL, NULL, "mti,gic-timer");
+	if (!node) {
+		pr_err("mti,gic-timer device node not found\n");
+		return;
+	}
+
+	if (of_update_property(node, &gic_frequency_prop) < 0)
+		pr_err("error updating gic frequency property\n");
+}
+
+#endif
+
 void __init plat_time_init(void)
 {
 	unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
@@ -236,7 +264,8 @@ void __init plat_time_init(void)
 		printk("GIC frequency %d.%02d MHz\n", freq/1000000,
 		       (freq%1000000)*100/1000000);
 #ifdef CONFIG_CLKSRC_MIPS_GIC
-		gic_clocksource_init(gic_frequency);
+		update_gic_frequency_dt();
+		clocksource_probe();
 #endif
 	}
 #endif
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 10d86d54880a..bddf1ef553a4 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
 
diff --git a/arch/mips/netlogic/xlp/cop2-ex.c b/arch/mips/netlogic/xlp/cop2-ex.c
index 52bc5de42005..21e439b3db70 100644
--- a/arch/mips/netlogic/xlp/cop2-ex.c
+++ b/arch/mips/netlogic/xlp/cop2-ex.c
@@ -9,11 +9,14 @@
  * Copyright (C) 2009 Wind River Systems,
  *   written by Ralf Baechle <ralf@linux-mips.org>
  */
+#include <linux/capability.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>
diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c
index 5e645c9a3162..16ace558cd9d 100644
--- a/arch/mips/oprofile/backtrace.c
+++ b/arch/mips/oprofile/backtrace.c
@@ -18,7 +18,7 @@ struct stackframe {
 static inline int get_mem(unsigned long addr, unsigned long *result)
 {
 	unsigned long *address = (unsigned long *) addr;
-	if (!access_ok(VERIFY_READ, addr, sizeof(unsigned long)))
+	if (!access_ok(VERIFY_READ, address, sizeof(unsigned long)))
 		return -1;
 	if (__copy_from_user_inatomic(result, address, sizeof(unsigned long)))
 		return -3;
diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c
index 014649be158d..3a84f6c0c840 100644
--- a/arch/mips/pci/pci-legacy.c
+++ b/arch/mips/pci/pci-legacy.c
@@ -190,7 +190,7 @@ void register_pci_controller(struct pci_controller *hose)
 	}
 
 	INIT_LIST_HEAD(&hose->list);
-	list_add(&hose->list, &controllers);
+	list_add_tail(&hose->list, &controllers);
 
 	/*
 	 * Do not panic here but later - this might happen before console init.
diff --git a/arch/mips/ralink/cevt-rt3352.c b/arch/mips/ralink/cevt-rt3352.c
index f24eee04e16a..b8a1376165b0 100644
--- a/arch/mips/ralink/cevt-rt3352.c
+++ b/arch/mips/ralink/cevt-rt3352.c
@@ -129,7 +129,9 @@ static int __init ralink_systick_init(struct device_node *np)
 	systick.dev.name = np->name;
 	clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60);
 	systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev);
+	systick.dev.max_delta_ticks = 0x7fff;
 	systick.dev.min_delta_ns = clockevent_delta2ns(0x3, &systick.dev);
+	systick.dev.min_delta_ticks = 0x3;
 	systick.dev.irq = irq_of_parse_and_map(np, 0);
 	if (!systick.dev.irq) {
 		pr_err("%s: request_irq failed", np->name);
diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c
index c4ffd43d3996..48ce701557a4 100644
--- a/arch/mips/ralink/rt3883.c
+++ b/arch/mips/ralink/rt3883.c
@@ -35,7 +35,7 @@ static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
 static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
 static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
 static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
 static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-dev", 0, 40, 32),
 	FUNC("pci-host2", 1, 40, 32),
@@ -43,7 +43,7 @@ static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-fnc", 3, 40, 32)
 };
 static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
 
 static struct rt2880_pmx_group rt3883_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 1f2a5bc4779e..75460e1e106b 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <linux/seq_file.h>
 
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index d12879eb2b1f..83efe03d5c60 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -12,7 +12,9 @@
 #include <linux/signal.h>	/* for SIGBUS */
 #include <linux/sched.h>	/* schow_regs(), force_sig() */
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 
+#include <asm/ptrace.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/sn0/hub.h>
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index f5ed45e8f442..4cd47d23d81a 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -8,10 +8,13 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/topology.h>
 #include <linux/nodemask.h>
+
 #include <asm/page.h>
 #include <asm/processor.h>
+#include <asm/ptrace.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
 #include <asm/sn/intr.h>
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index 695c51bdd7dc..a53f0c8c901e 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -113,7 +113,9 @@ void hub_rt_clock_event_init(void)
 	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
 	clockevent_set_clock(cd, CYCLES_PER_SEC);
 	cd->max_delta_ns	= clockevent_delta2ns(0xfffffffffffff, cd);
+	cd->max_delta_ticks	= 0xfffffffffffff;
 	cd->min_delta_ns	= clockevent_delta2ns(0x300, cd);
+	cd->min_delta_ticks	= 0x300;
 	cd->rating		= 200;
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index 57d8c7486fe6..c1f12a9cf305 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 8bd415c8729f..b3b442def423 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/notifier.h>
 #include <linux/delay.h>
 #include <linux/rtc/ds1685.h>
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 97f64c723a0c..ed810e7206e8 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -2,6 +2,7 @@
 generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
diff --git a/arch/mn10300/include/asm/page.h b/arch/mn10300/include/asm/page.h
index 3810a6f740fd..dfe730a5ede0 100644
--- a/arch/mn10300/include/asm/page.h
+++ b/arch/mn10300/include/asm/page.h
@@ -57,6 +57,7 @@ typedef struct page *pgtable_t;
 #define __pgd(x)	((pgd_t) { (x) })
 #define __pgprot(x)	((pgprot_t) { (x) })
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 2eedf6f46a57..c6966474827f 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -14,13 +14,8 @@
 /*
  * User space memory access functions
  */
-#include <linux/thread_info.h>
 #include <linux/kernel.h>
 #include <asm/page.h>
-#include <asm/errno.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -71,26 +66,7 @@ static inline int ___range_ok(unsigned long addr, unsigned int size)
 #define access_ok(type, addr, size) (__range_ok((addr), (size)) == 0)
 #define __access_ok(addr, size)     (__range_ok((addr), (size)) == 0)
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise.  */
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 #define put_user(x, ptr) __put_user_check((x), (ptr), sizeof(*(ptr)))
 #define get_user(x, ptr) __get_user_check((x), (ptr), sizeof(*(ptr)))
@@ -299,170 +275,19 @@ do {									\
 	}								\
 } while (0)
 
-#define __copy_user_zeroing(to, from, size)				\
-do {									\
-	if (size) {							\
-		void *__to = to;					\
-		const void *__from = from;				\
-		int w;							\
-		asm volatile(						\
-			"0:     movbu	(%0),%3;\n"			\
-			"1:     movbu	%3,(%1);\n"			\
-			"	inc	%0;\n"				\
-			"	inc	%1;\n"				\
-			"       add	-1,%2;\n"			\
-			"       bne	0b;\n"				\
-			"2:\n"						\
-			"	.section .fixup,\"ax\"\n"		\
-			"3:\n"						\
-			"	mov	%2,%0\n"			\
-			"	clr	%3\n"				\
-			"4:     movbu	%3,(%1);\n"			\
-			"	inc	%1;\n"				\
-			"       add	-1,%2;\n"			\
-			"       bne	4b;\n"				\
-			"	mov	%0,%2\n"			\
-			"	jmp	2b\n"				\
-			"	.previous\n"				\
-			"	.section __ex_table,\"a\"\n"		\
-			"       .balign	4\n"				\
-			"       .long	0b,3b\n"			\
-			"       .long	1b,3b\n"			\
-			"	.previous\n"				\
-			: "=a"(__from), "=a"(__to), "=r"(size), "=&r"(w)\
-			: "0"(__from), "1"(__to), "2"(size)		\
-			: "cc", "memory");				\
-	}								\
-} while (0)
-
-/* We let the __ versions of copy_from/to_user inline, because they're often
- * used in fast paths and have only a small space overhead.
- */
-static inline
-unsigned long __generic_copy_from_user_nocheck(void *to, const void *from,
-					       unsigned long n)
-{
-	__copy_user_zeroing(to, from, n);
-	return n;
-}
-
-static inline
-unsigned long __generic_copy_to_user_nocheck(void *to, const void *from,
-					     unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	__copy_user(to, from, n);
 	return n;
 }
 
-
-#if 0
-#error "don't use - these macros don't increment to & from pointers"
-/* Optimize just a little bit when we know the size of the move. */
-#define __constant_copy_user(to, from, size)	\
-do {						\
-	asm volatile(				\
-		"       mov %0,a0;\n"		\
-		"0:     movbu (%1),d3;\n"	\
-		"1:     movbu d3,(%2);\n"	\
-		"       add -1,a0;\n"		\
-		"       bne 0b;\n"		\
-		"2:;"				\
-		".section .fixup,\"ax\"\n"	\
-		"3:	jmp 2b\n"		\
-		".previous\n"			\
-		".section __ex_table,\"a\"\n"	\
-		"       .balign 4\n"		\
-		"       .long 0b,3b\n"		\
-		"       .long 1b,3b\n"		\
-		".previous"			\
-		:				\
-		: "d"(size), "d"(to), "d"(from)	\
-		: "d3", "a0");			\
-} while (0)
-
-/* Optimize just a little bit when we know the size of the move. */
-#define __constant_copy_user_zeroing(to, from, size)	\
-do {							\
-	asm volatile(					\
-		"       mov %0,a0;\n"			\
-		"0:     movbu (%1),d3;\n"		\
-		"1:     movbu d3,(%2);\n"		\
-		"       add -1,a0;\n"			\
-		"       bne 0b;\n"			\
-		"2:;"					\
-		".section .fixup,\"ax\"\n"		\
-		"3:	jmp 2b\n"			\
-		".previous\n"				\
-		".section __ex_table,\"a\"\n"		\
-		"       .balign 4\n"			\
-		"       .long 0b,3b\n"			\
-		"       .long 1b,3b\n"			\
-		".previous"				\
-		:					\
-		: "d"(size), "d"(to), "d"(from)		\
-		: "d3", "a0");				\
-} while (0)
-
-static inline
-unsigned long __constant_copy_to_user(void *to, const void *from,
-				      unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		__constant_copy_user(to, from, n);
-	return n;
-}
-
-static inline
-unsigned long __constant_copy_from_user(void *to, const void *from,
-					unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
-		__constant_copy_user_zeroing(to, from, n);
-	return n;
-}
-
-static inline
-unsigned long __constant_copy_to_user_nocheck(void *to, const void *from,
-					      unsigned long n)
-{
-	__constant_copy_user(to, from, n);
-	return n;
-}
-
-static inline
-unsigned long __constant_copy_from_user_nocheck(void *to, const void *from,
-						unsigned long n)
-{
-	__constant_copy_user_zeroing(to, from, n);
+	__copy_user(to, from, n);
 	return n;
 }
-#endif
-
-extern unsigned long __generic_copy_to_user(void __user *, const void *,
-					    unsigned long);
-extern unsigned long __generic_copy_from_user(void *, const void __user *,
-					      unsigned long);
-
-#define __copy_to_user_inatomic(to, from, n) \
-	__generic_copy_to_user_nocheck((to), (from), (n))
-#define __copy_from_user_inatomic(to, from, n) \
-	__generic_copy_from_user_nocheck((to), (from), (n))
-
-#define __copy_to_user(to, from, n)			\
-({							\
-	might_fault();					\
-	__copy_to_user_inatomic((to), (from), (n));	\
-})
-
-#define __copy_from_user(to, from, n)			\
-({							\
-	might_fault();					\
-	__copy_from_user_inatomic((to), (from), (n));	\
-})
-
-
-#define copy_to_user(to, from, n)   __generic_copy_to_user((to), (from), (n))
-#define copy_from_user(to, from, n) __generic_copy_from_user((to), (from), (n))
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern long __strncpy_from_user(char *dst, const char __user *src, long count);
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 0e12527c4b0e..4526e92301a6 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -92,4 +92,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/mn10300/kernel/cevt-mn10300.c b/arch/mn10300/kernel/cevt-mn10300.c
index d9b34dd44f04..2b21bbc9efa4 100644
--- a/arch/mn10300/kernel/cevt-mn10300.c
+++ b/arch/mn10300/kernel/cevt-mn10300.c
@@ -98,7 +98,9 @@ int __init init_clockevents(void)
 
 	/* Calculate the min / max delta */
 	cd->max_delta_ns	= clockevent_delta2ns(TMJCBR_MAX, cd);
+	cd->max_delta_ticks	= TMJCBR_MAX;
 	cd->min_delta_ns	= clockevent_delta2ns(100, cd);
+	cd->min_delta_ticks	= 100;
 
 	cd->rating		= 200;
 	cd->cpumask		= cpumask_of(smp_processor_id());
diff --git a/arch/mn10300/kernel/mn10300_ksyms.c b/arch/mn10300/kernel/mn10300_ksyms.c
index ec6c4f8f93a6..5e9f919635f0 100644
--- a/arch/mn10300/kernel/mn10300_ksyms.c
+++ b/arch/mn10300/kernel/mn10300_ksyms.c
@@ -26,8 +26,6 @@ EXPORT_SYMBOL(strncpy_from_user);
 EXPORT_SYMBOL(__strncpy_from_user);
 EXPORT_SYMBOL(clear_user);
 EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__generic_copy_from_user);
-EXPORT_SYMBOL(__generic_copy_to_user);
 EXPORT_SYMBOL(strnlen_user);
 
 extern u64 __ashrdi3(u64, unsigned);
diff --git a/arch/mn10300/lib/usercopy.c b/arch/mn10300/lib/usercopy.c
index ce8899e5e171..cece1799cc32 100644
--- a/arch/mn10300/lib/usercopy.c
+++ b/arch/mn10300/lib/usercopy.c
@@ -11,24 +11,6 @@
  */
 #include <linux/uaccess.h>
 
-unsigned long
-__generic_copy_to_user(void *to, const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		__copy_user(to, from, n);
-	return n;
-}
-
-unsigned long
-__generic_copy_from_user(void *to, const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		__copy_user_zeroing(to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-
 /*
  * Copy a null terminated string from userspace.
  */
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index aaa3c218b56c..87e70f2b463f 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h
index 298393c3cb42..db4f7d179220 100644
--- a/arch/nios2/include/asm/pgtable.h
+++ b/arch/nios2/include/asm/pgtable.h
@@ -22,6 +22,7 @@
 #include <asm/tlbflush.h>
 
 #include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #define FIRST_USER_ADDRESS	0UL
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index 0ab82324c817..727bd9504899 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -13,33 +13,11 @@
 #ifndef _ASM_NIOS2_UACCESS_H
 #define _ASM_NIOS2_UACCESS_H
 
-#include <linux/errno.h>
-#include <linux/thread_info.h>
 #include <linux/string.h>
 
 #include <asm/page.h>
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
-	unsigned long insn;
-	unsigned long fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 /*
  * Segment stuff
@@ -95,36 +73,17 @@ static inline unsigned long __must_check clear_user(void __user *to,
 	return __clear_user(to, n);
 }
 
-extern long __copy_from_user(void *to, const void __user *from,
-				unsigned long n);
-extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
-
-static inline long copy_from_user(void *to, const void __user *from,
-				unsigned long n)
-{
-	unsigned long res = n;
-	if (access_ok(VERIFY_READ, from, n))
-		res = __copy_from_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
-}
-
-static inline long copy_to_user(void __user *to, const void *from,
-				unsigned long n)
-{
-	if (!access_ok(VERIFY_WRITE, to, n))
-		return n;
-	return __copy_to_user(to, from, n);
-}
+extern unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+extern unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 extern long strncpy_from_user(char *__to, const char __user *__from,
 				long __len);
 extern long strnlen_user(const char __user *s, long n);
 
-#define __copy_from_user_inatomic	__copy_from_user
-#define __copy_to_user_inatomic		__copy_to_user
-
 /* Optimized macros */
 #define __get_user_asm(val, insn, addr, err)				\
 {									\
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 367c5426157b..3901b80d4420 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -48,6 +48,13 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return alloc_bootmem_align(size, align);
 }
 
+int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+					     bool nomap)
+{
+	reserve_bootmem(base, size, BOOTMEM_DEFAULT);
+	return 0;
+}
+
 void __init early_init_devtree(void *params)
 {
 	__be32 *dtb = (u32 *)__dtb_start;
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index 6e57ffa5db27..6044d9be28b4 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -201,6 +201,9 @@ void __init setup_arch(char **cmdline_p)
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
 	unflatten_and_copy_device_tree();
 
 	setup_cpuinfo();
diff --git a/arch/nios2/mm/uaccess.c b/arch/nios2/mm/uaccess.c
index 7663e156ff4f..804983317766 100644
--- a/arch/nios2/mm/uaccess.c
+++ b/arch/nios2/mm/uaccess.c
@@ -10,9 +10,9 @@
 #include <linux/export.h>
 #include <linux/uaccess.h>
 
-asm(".global	__copy_from_user\n"
-	"   .type __copy_from_user, @function\n"
-	"__copy_from_user:\n"
+asm(".global	raw_copy_from_user\n"
+	"   .type raw_copy_from_user, @function\n"
+	"raw_copy_from_user:\n"
 	"   movi  r2,7\n"
 	"   mov   r3,r4\n"
 	"   bge   r2,r6,1f\n"
@@ -65,12 +65,12 @@ asm(".global	__copy_from_user\n"
 	".word 7b,13b\n"
 	".previous\n"
 	);
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
 
 asm(
-	"   .global __copy_to_user\n"
-	"   .type __copy_to_user, @function\n"
-	"__copy_to_user:\n"
+	"   .global raw_copy_to_user\n"
+	"   .type raw_copy_to_user, @function\n"
+	"raw_copy_to_user:\n"
 	"   movi  r2,7\n"
 	"   mov   r3,r4\n"
 	"   bge   r2,r6,1f\n"
@@ -127,7 +127,7 @@ asm(
 	".word 11b,13b\n"
 	".word 12b,13b\n"
 	".previous\n");
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 
 long strncpy_from_user(char *__to, const char __user *__from, long __len)
 {
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index fb01873a5aad..df8e2f7bc7dd 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index 5fcb9ac72693..f0a5d8b844d6 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -77,7 +77,11 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
 	return val;
 }
 
-#define xchg(ptr, with) \
-	((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), sizeof(*(ptr))))
+#define xchg(ptr, with) 						\
+	({								\
+		(__typeof__(*(ptr))) __xchg((unsigned long)(with),	\
+					    (ptr),			\
+					    sizeof(*(ptr)));		\
+	})
 
 #endif /* __ASM_OPENRISC_CMPXCHG_H */
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 3567aa7be555..ff97374ca069 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -25,6 +25,7 @@
 #ifndef __ASM_OPENRISC_PGTABLE_H
 #define __ASM_OPENRISC_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index 140faa16685a..a557a7cd0232 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -22,14 +22,10 @@
 /*
  * User space memory access functions
  */
-#include <linux/errno.h>
-#include <linux/thread_info.h>
 #include <linux/prefetch.h>
 #include <linux/string.h>
 #include <asm/page.h>
-
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
+#include <asm/extable.h>
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -66,23 +62,6 @@
 	__range_ok((unsigned long)addr, (unsigned long)size)
 
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-/*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.
  *
@@ -211,7 +190,7 @@ do {									\
 	case 1: __get_user_asm(x, ptr, retval, "l.lbz"); break;		\
 	case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break;		\
 	case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break;		\
-	case 8: __get_user_asm2(x, ptr, retval);			\
+	case 8: __get_user_asm2(x, ptr, retval); break;			\
 	default: (x) = __get_user_bad();				\
 	}								\
 } while (0)
@@ -257,34 +236,18 @@ do {									\
 
 extern unsigned long __must_check
 __copy_tofrom_user(void *to, const void *from, unsigned long size);
-
-#define __copy_from_user(to, from, size) \
-	__copy_tofrom_user(to, from, size)
-#define __copy_to_user(to, from, size) \
-	__copy_tofrom_user(to, from, size)
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
 static inline unsigned long
-copy_from_user(void *to, const void *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long size)
 {
-	unsigned long res = n;
-
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		res = __copy_tofrom_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
+	return __copy_tofrom_user(to, (__force const void *)from, size);
 }
-
 static inline unsigned long
-copy_to_user(void *to, const void *from, unsigned long n)
+raw_copy_to_user(void *to, const void __user *from, unsigned long size)
 {
-	if (likely(access_ok(VERIFY_WRITE, to, n)))
-		n = __copy_tofrom_user(to, from, n);
-	return n;
+	return __copy_tofrom_user((__force void *)to, from, size);
 }
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 extern unsigned long __clear_user(void *addr, unsigned long size);
 
@@ -297,7 +260,7 @@ clear_user(void *addr, unsigned long size)
 }
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+	(uaccess_kernel() ? ~0UL : TASK_SIZE)
 
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c
index 5c4695d13542..ee3e604959e1 100644
--- a/arch/openrisc/kernel/or32_ksyms.c
+++ b/arch/openrisc/kernel/or32_ksyms.c
@@ -30,6 +30,7 @@
 #include <asm/hardirq.h>
 #include <asm/delay.h>
 #include <asm/pgalloc.h>
+#include <asm/pgtable.h>
 
 #define DECLARE_EXPORT(name) extern void name(void); EXPORT_SYMBOL(name)
 
@@ -42,6 +43,9 @@ DECLARE_EXPORT(__muldi3);
 DECLARE_EXPORT(__ashrdi3);
 DECLARE_EXPORT(__ashldi3);
 DECLARE_EXPORT(__lshrdi3);
+DECLARE_EXPORT(__ucmpdi2);
 
+EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(__copy_tofrom_user);
+EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(memset);
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 828a29110459..f8da545854f9 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -90,6 +90,7 @@ void arch_cpu_idle(void)
 }
 
 void (*pm_power_off) (void) = machine_power_off;
+EXPORT_SYMBOL(pm_power_off);
 
 /*
  * When a process does an "exec", machine state like FPU and debug
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index ad294b3fb90b..531da9eb8f43 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -26,7 +26,6 @@ config PARISC
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_MOD_ARCH_SPECIFIC
-	select HAVE_ARCH_HARDENED_USERCOPY
 	select VIRT_TO_BUS
 	select MODULES_USE_ELF_RELA
 	select CLONE_BACKWARDS
diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h
index 62a33338549c..d2742273a685 100644
--- a/arch/parisc/include/asm/bug.h
+++ b/arch/parisc/include/asm/bug.h
@@ -46,7 +46,7 @@
 #endif
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-#define __WARN_TAINT(taint)						\
+#define __WARN_FLAGS(flags)						\
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
@@ -56,11 +56,11 @@
 			     "\t.org 2b+%c3\n"				\
 			     "\t.popsection"				\
 			     : : "i" (__FILE__), "i" (__LINE__),	\
-			     "i" (BUGFLAG_TAINT(taint)), 		\
+			     "i" (BUGFLAG_WARNING|(flags)),		\
 			     "i" (sizeof(struct bug_entry)) );		\
 	} while(0)
 #else
-#define __WARN_TAINT(taint)						\
+#define __WARN_FLAGS(flags)						\
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
@@ -69,7 +69,7 @@
 			     "\t.short %c0\n"				\
 			     "\t.org 2b+%c1\n"				\
 			     "\t.popsection"				\
-			     : : "i" (BUGFLAG_TAINT(taint)),		\
+			     : : "i" (BUGFLAG_WARNING|(flags)),		\
 			     "i" (sizeof(struct bug_entry)) );		\
 	} while(0)
 #endif
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 19c9c3c5f267..c7e15cc5c668 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -43,28 +43,9 @@ static inline void flush_kernel_dcache_page(struct page *page)
 
 #define flush_kernel_dcache_range(start,size) \
 	flush_kernel_dcache_range_asm((start), (start)+(size));
-/* vmap range flushes and invalidates.  Architecturally, we don't need
- * the invalidate, because the CPU should refuse to speculate once an
- * area has been flushed, so invalidate is left empty */
-static inline void flush_kernel_vmap_range(void *vaddr, int size)
-{
-	unsigned long start = (unsigned long)vaddr;
-
-	flush_kernel_dcache_range_asm(start, start + size);
-}
-static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
-{
-	unsigned long start = (unsigned long)vaddr;
-	void *cursor = vaddr;
 
-	for ( ; cursor < vaddr + size; cursor += PAGE_SIZE) {
-		struct page *page = vmalloc_to_page(cursor);
-
-		if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
-			flush_kernel_dcache_page(page);
-	}
-	flush_kernel_dcache_range_asm(start, start + size);
-}
+void flush_kernel_vmap_range(void *vaddr, int size);
+void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
 #define flush_cache_vunmap(start, end)		flush_cache_all()
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index ac8bd586ace8..0ba14300cd8e 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -109,7 +109,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
 	 */
-	if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
+	if (uaccess_kernel() && !uaddr)
 		return -EFAULT;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index fb4382c28259..6b113f39f30c 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -6,15 +6,10 @@
  */
 #include <asm/page.h>
 #include <asm/cache.h>
-#include <asm/errno.h>
 #include <asm-generic/uaccess-unaligned.h>
 
 #include <linux/bug.h>
 #include <linux/string.h>
-#include <linux/thread_info.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
 
 #define KERNEL_DS	((mm_segment_t){0})
 #define USER_DS 	((mm_segment_t){1})
@@ -32,16 +27,17 @@
  * that put_user is the same as __put_user, etc.
  */
 
-#define access_ok(type, uaddr, size) (1)
+#define access_ok(type, uaddr, size)	\
+	( (uaddr) == (uaddr) )
 
 #define put_user __put_user
 #define get_user __get_user
 
 #if !defined(CONFIG_64BIT)
-#define LDD_USER(ptr)		__get_user_asm64(ptr)
+#define LDD_USER(val, ptr)	__get_user_asm64(val, ptr)
 #define STD_USER(x, ptr)	__put_user_asm64(x, ptr)
 #else
-#define LDD_USER(ptr)		__get_user_asm("ldd", ptr)
+#define LDD_USER(val, ptr)	__get_user_asm(val, "ldd", ptr)
 #define STD_USER(x, ptr)	__put_user_asm("std", x, ptr)
 #endif
 
@@ -64,6 +60,15 @@ struct exception_table_entry {
 	".previous\n"
 
 /*
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
+ * (with lowest bit set) for which the fault handler in fixup_exception() will
+ * load -EFAULT into %r8 for a read or write fault, and zeroes the target
+ * register in case of a read fault in get_user().
+ */
+#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
+	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
+
+/*
  * The page fault handler stores, in a per-cpu area, the following information
  * if a fixup routine is available.
  */
@@ -87,92 +92,116 @@ struct exception_data {
 		" mtsp %0,%%sr2\n\t"		\
 		: : "r"(get_fs()) : )
 
-#define __get_user(x, ptr)                               \
-({                                                       \
-	register long __gu_err __asm__ ("r8") = 0;       \
-	register long __gu_val __asm__ ("r9") = 0;       \
-							 \
-	load_sr2();					 \
-	switch (sizeof(*(ptr))) {			 \
-	    case 1: __get_user_asm("ldb", ptr); break;   \
-	    case 2: __get_user_asm("ldh", ptr); break;   \
-	    case 4: __get_user_asm("ldw", ptr); break;   \
-	    case 8: LDD_USER(ptr);  break;		 \
-	    default: BUILD_BUG(); break;		 \
-	}                                                \
-							 \
-	(x) = (__force __typeof__(*(ptr))) __gu_val;	 \
-	__gu_err;                                        \
+#define __get_user_internal(val, ptr)			\
+({							\
+	register long __gu_err __asm__ ("r8") = 0;	\
+							\
+	switch (sizeof(*(ptr))) {			\
+	case 1: __get_user_asm(val, "ldb", ptr); break;	\
+	case 2: __get_user_asm(val, "ldh", ptr); break; \
+	case 4: __get_user_asm(val, "ldw", ptr); break; \
+	case 8: LDD_USER(val, ptr); break;		\
+	default: BUILD_BUG();				\
+	}						\
+							\
+	__gu_err;					\
+})
+
+#define __get_user(val, ptr)				\
+({							\
+	load_sr2();					\
+	__get_user_internal(val, ptr);			\
 })
 
-#define __get_user_asm(ldx, ptr)                        \
-	__asm__("\n1:\t" ldx "\t0(%%sr2,%2),%0\n\t"	\
-		ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_1)\
+#define __get_user_asm(val, ldx, ptr)			\
+{							\
+	register long __gu_val;				\
+							\
+	__asm__("1: " ldx " 0(%%sr2,%2),%0\n"		\
+		"9:\n"					\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
 		: "=r"(__gu_val), "=r"(__gu_err)        \
-		: "r"(ptr), "1"(__gu_err)		\
-		: "r1");
+		: "r"(ptr), "1"(__gu_err));		\
+							\
+	(val) = (__force __typeof__(*(ptr))) __gu_val;	\
+}
 
 #if !defined(CONFIG_64BIT)
 
-#define __get_user_asm64(ptr) 				\
-	__asm__("\n1:\tldw 0(%%sr2,%2),%0"		\
-		"\n2:\tldw 4(%%sr2,%2),%R0\n\t"		\
-		ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_2)\
-		ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_get_user_skip_1)\
-		: "=r"(__gu_val), "=r"(__gu_err)	\
-		: "r"(ptr), "1"(__gu_err)		\
-		: "r1");
+#define __get_user_asm64(val, ptr)			\
+{							\
+	union {						\
+		unsigned long long	l;		\
+		__typeof__(*(ptr))	t;		\
+	} __gu_tmp;					\
+							\
+	__asm__("   copy %%r0,%R0\n"			\
+		"1: ldw 0(%%sr2,%2),%0\n"		\
+		"2: ldw 4(%%sr2,%2),%R0\n"		\
+		"9:\n"					\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
+		: "=&r"(__gu_tmp.l), "=r"(__gu_err)	\
+		: "r"(ptr), "1"(__gu_err));		\
+							\
+	(val) = __gu_tmp.t;				\
+}
 
 #endif /* !defined(CONFIG_64BIT) */
 
 
-#define __put_user(x, ptr)                                      \
+#define __put_user_internal(x, ptr)				\
 ({								\
 	register long __pu_err __asm__ ("r8") = 0;      	\
         __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x);	\
 								\
-	load_sr2();						\
 	switch (sizeof(*(ptr))) {				\
-	    case 1: __put_user_asm("stb", __x, ptr); break;     \
-	    case 2: __put_user_asm("sth", __x, ptr); break;     \
-	    case 4: __put_user_asm("stw", __x, ptr); break;     \
-	    case 8: STD_USER(__x, ptr); break;			\
-	    default: BUILD_BUG(); break;			\
-	}                                                       \
+	case 1: __put_user_asm("stb", __x, ptr); break;		\
+	case 2: __put_user_asm("sth", __x, ptr); break;		\
+	case 4: __put_user_asm("stw", __x, ptr); break;		\
+	case 8: STD_USER(__x, ptr); break;			\
+	default: BUILD_BUG();					\
+	}							\
 								\
 	__pu_err;						\
 })
 
+#define __put_user(x, ptr)					\
+({								\
+	load_sr2();						\
+	__put_user_internal(x, ptr);				\
+})
+
+
 /*
  * The "__put_user/kernel_asm()" macros tell gcc they read from memory
  * instead of writing. This is because they do not write to any memory
  * gcc knows about, so there are no aliasing issues. These macros must
- * also be aware that "fixup_put_user_skip_[12]" are executed in the
- * context of the fault, and any registers used there must be listed
- * as clobbers. In this case only "r1" is used by the current routines.
- * r8/r9 are already listed as err/val.
+ * also be aware that fixups are executed in the context of the fault,
+ * and any registers used there must be listed as clobbers.
+ * r8 is already listed as err.
  */
 
 #define __put_user_asm(stx, x, ptr)                         \
 	__asm__ __volatile__ (                              \
-		"\n1:\t" stx "\t%2,0(%%sr2,%1)\n\t"	    \
-		ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_1)\
+		"1: " stx " %2,0(%%sr2,%1)\n"		    \
+		"9:\n"					    \
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	    \
 		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(x), "0"(__pu_err)	    \
-		: "r1")
+		: "r"(ptr), "r"(x), "0"(__pu_err))
 
 
 #if !defined(CONFIG_64BIT)
 
 #define __put_user_asm64(__val, ptr) do {	    	    \
 	__asm__ __volatile__ (				    \
-		"\n1:\tstw %2,0(%%sr2,%1)"		    \
-		"\n2:\tstw %R2,4(%%sr2,%1)\n\t"		    \
-		ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_2)\
-		ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_put_user_skip_1)\
+		"1: stw %2,0(%%sr2,%1)\n"		    \
+		"2: stw %R2,4(%%sr2,%1)\n"		    \
+		"9:\n"					    \
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	    \
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	    \
 		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(__val), "0"(__pu_err) \
-		: "r1");				    \
+		: "r"(ptr), "r"(__val), "0"(__pu_err));	    \
 } while (0)
 
 #endif /* !defined(CONFIG_64BIT) */
@@ -182,9 +211,6 @@ struct exception_data {
  * Complex access routines -- external declarations
  */
 
-extern unsigned long lcopy_to_user(void __user *, const void *, unsigned long);
-extern unsigned long lcopy_from_user(void *, const void __user *, unsigned long);
-extern unsigned long lcopy_in_user(void __user *, const void __user *, unsigned long);
 extern long strncpy_from_user(char *, const char __user *, long);
 extern unsigned lclear_user(void __user *, unsigned long);
 extern long lstrnlen_user(const char __user *, long);
@@ -198,59 +224,14 @@ extern long lstrnlen_user(const char __user *, long);
 #define clear_user lclear_user
 #define __clear_user lclear_user
 
-unsigned long __must_check __copy_to_user(void __user *dst, const void *src,
-					  unsigned long len);
-unsigned long __must_check __copy_from_user(void *dst, const void __user *src,
-					  unsigned long len);
-unsigned long copy_in_user(void __user *dst, const void __user *src,
-			   unsigned long len);
-#define __copy_in_user copy_in_user
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
-	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static __always_inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	int sz = __compiletime_object_size(to);
-	unsigned long ret = n;
-
-	if (likely(sz < 0 || sz >= n)) {
-		check_object_size(to, n, false);
-		ret = __copy_from_user(to, from, n);
-	} else if (!__builtin_constant_p(n))
-		copy_user_overflow(sz, n);
-	else
-		__bad_copy_user();
-
-	if (unlikely(ret))
-		memset(to + (n - ret), 0, ret);
-
-	return ret;
-}
-
-static __always_inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	int sz = __compiletime_object_size(from);
-
-	if (likely(sz < 0 || sz >= n)) {
-		check_object_size(from, n, true);
-		n = __copy_to_user(to, from, n);
-	} else if (!__builtin_constant_p(n))
-		copy_user_overflow(sz, n);
-	else
-		__bad_copy_user();
-
-	return n;
-}
+unsigned long __must_check raw_copy_to_user(void __user *dst, const void *src,
+					    unsigned long len);
+unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
+					    unsigned long len);
+unsigned long __must_check raw_copy_in_user(void __user *dst, const void __user *src,
+					    unsigned long len);
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
 
 struct pt_regs;
 int fixup_exception(struct pt_regs *regs);
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 7a109b73ddf7..514701840bd9 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -91,4 +91,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	0x402F
 
+#define SO_MEMINFO		0x4030
+
+#define SO_INCOMING_NAPI_ID	0x4031
+
+#define SO_COOKIE		0x4032
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 6b0741e7a7ed..667c99421003 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -362,8 +362,9 @@
 #define __NR_copy_file_range	(__NR_Linux + 346)
 #define __NR_preadv2		(__NR_Linux + 347)
 #define __NR_pwritev2		(__NR_Linux + 348)
+#define __NR_statx		(__NR_Linux + 349)
 
-#define __NR_Linux_syscalls	(__NR_pwritev2 + 1)
+#define __NR_Linux_syscalls	(__NR_statx + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 0dc72d5de861..c32a09095216 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -616,3 +616,25 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
+
+void flush_kernel_vmap_range(void *vaddr, int size)
+{
+	unsigned long start = (unsigned long)vaddr;
+
+	if ((unsigned long)size > parisc_cache_flush_threshold)
+		flush_data_cache();
+	else
+		flush_kernel_dcache_range_asm(start, start + size);
+}
+EXPORT_SYMBOL(flush_kernel_vmap_range);
+
+void invalidate_kernel_vmap_range(void *vaddr, int size)
+{
+	unsigned long start = (unsigned long)vaddr;
+
+	if ((unsigned long)size > parisc_cache_flush_threshold)
+		flush_data_cache();
+	else
+		flush_kernel_dcache_range_asm(start, start + size);
+}
+EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index a0ecdb4abcc8..c66c943d9322 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -620,6 +620,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
 			 */
 			*loc = fsel(val, addend); 
 			break;
+		case R_PARISC_SECREL32:
+			/* 32-bit section relative address. */
+			*loc = fsel(val, addend);
+			break;
 		case R_PARISC_DPREL21L:
 			/* left 21 bit of relative address */
 			val = lrsel(val - dp, addend);
@@ -807,6 +811,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
 			 */
 			*loc = fsel(val, addend); 
 			break;
+		case R_PARISC_SECREL32:
+			/* 32-bit section relative address. */
+			*loc = fsel(val, addend);
+			break;
 		case R_PARISC_FPTR64:
 			/* 64-bit function address */
 			if(in_local(me, (void *)(val + addend))) {
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 7484b3d11e0d..c6d6272a934f 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -47,16 +47,6 @@ EXPORT_SYMBOL(__cmpxchg_u64);
 EXPORT_SYMBOL(lclear_user);
 EXPORT_SYMBOL(lstrnlen_user);
 
-/* Global fixups - defined as int to avoid creation of function pointers */
-extern int fixup_get_user_skip_1;
-extern int fixup_get_user_skip_2;
-extern int fixup_put_user_skip_1;
-extern int fixup_put_user_skip_2;
-EXPORT_SYMBOL(fixup_get_user_skip_1);
-EXPORT_SYMBOL(fixup_get_user_skip_2);
-EXPORT_SYMBOL(fixup_put_user_skip_1);
-EXPORT_SYMBOL(fixup_put_user_skip_2);
-
 #ifndef CONFIG_64BIT
 /* Needed so insmod can set dp value */
 extern int $global$;
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index e282a5131d77..6017a5af2e6e 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -39,7 +39,7 @@
  *  the PDC INTRIGUE calls.  This is done to eliminate bugs introduced
  *  in various PDC revisions.  The code is much more maintainable
  *  and reliable this way vs having to debug on every version of PDC
- *  on every box. 
+ *  on every box.
  */
 
 #include <linux/capability.h>
@@ -195,8 +195,8 @@ static int perf_config(uint32_t *image_ptr);
 static int perf_release(struct inode *inode, struct file *file);
 static int perf_open(struct inode *inode, struct file *file);
 static ssize_t perf_read(struct file *file, char __user *buf, size_t cnt, loff_t *ppos);
-static ssize_t perf_write(struct file *file, const char __user *buf, size_t count, 
-	loff_t *ppos);
+static ssize_t perf_write(struct file *file, const char __user *buf,
+	size_t count, loff_t *ppos);
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 static void perf_start_counters(void);
 static int perf_stop_counters(uint32_t *raddr);
@@ -222,7 +222,7 @@ extern void perf_intrigue_disable_perf_counters (void);
 /*
  * configure:
  *
- * Configure the cpu with a given data image.  First turn off the counters, 
+ * Configure the cpu with a given data image.  First turn off the counters,
  * then download the image, then turn the counters back on.
  */
 static int perf_config(uint32_t *image_ptr)
@@ -234,7 +234,7 @@ static int perf_config(uint32_t *image_ptr)
 	error = perf_stop_counters(raddr);
 	if (error != 0) {
 		printk("perf_config: perf_stop_counters = %ld\n", error);
-		return -EINVAL; 
+		return -EINVAL;
 	}
 
 printk("Preparing to write image\n");
@@ -242,7 +242,7 @@ printk("Preparing to write image\n");
 	error = perf_write_image((uint64_t *)image_ptr);
 	if (error != 0) {
 		printk("perf_config: DOWNLOAD = %ld\n", error);
-		return -EINVAL; 
+		return -EINVAL;
 	}
 
 printk("Preparing to start counters\n");
@@ -254,7 +254,7 @@ printk("Preparing to start counters\n");
 }
 
 /*
- * Open the device and initialize all of its memory.  The device is only 
+ * Open the device and initialize all of its memory.  The device is only
  * opened once, but can be "queried" by multiple processes that know its
  * file descriptor.
  */
@@ -298,19 +298,19 @@ static ssize_t perf_read(struct file *file, char __user *buf, size_t cnt, loff_t
  * called on the processor that the download should happen
  * on.
  */
-static ssize_t perf_write(struct file *file, const char __user *buf, size_t count, 
-	loff_t *ppos)
+static ssize_t perf_write(struct file *file, const char __user *buf,
+	size_t count, loff_t *ppos)
 {
 	size_t image_size;
 	uint32_t image_type;
 	uint32_t interface_type;
 	uint32_t test;
 
-	if (perf_processor_interface == ONYX_INTF) 
+	if (perf_processor_interface == ONYX_INTF)
 		image_size = PCXU_IMAGE_SIZE;
-	else if (perf_processor_interface == CUDA_INTF) 
+	else if (perf_processor_interface == CUDA_INTF)
 		image_size = PCXW_IMAGE_SIZE;
-	else 
+	else
 		return -EFAULT;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -330,22 +330,22 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun
 
 	/* First check the machine type is correct for
 	   the requested image */
-        if (((perf_processor_interface == CUDA_INTF) &&
-		       (interface_type != CUDA_INTF)) ||
-	    ((perf_processor_interface == ONYX_INTF) &&
-	               (interface_type != ONYX_INTF))) 
+	if (((perf_processor_interface == CUDA_INTF) &&
+			(interface_type != CUDA_INTF)) ||
+		((perf_processor_interface == ONYX_INTF) &&
+			(interface_type != ONYX_INTF)))
 		return -EINVAL;
 
 	/* Next check to make sure the requested image
 	   is valid */
-	if (((interface_type == CUDA_INTF) && 
+	if (((interface_type == CUDA_INTF) &&
 		       (test >= MAX_CUDA_IMAGES)) ||
-	    ((interface_type == ONYX_INTF) && 
-		       (test >= MAX_ONYX_IMAGES))) 
+	    ((interface_type == ONYX_INTF) &&
+		       (test >= MAX_ONYX_IMAGES)))
 		return -EINVAL;
 
 	/* Copy the image into the processor */
-	if (interface_type == CUDA_INTF) 
+	if (interface_type == CUDA_INTF)
 		return perf_config(cuda_images[test]);
 	else
 		return perf_config(onyx_images[test]);
@@ -359,7 +359,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun
 static void perf_patch_images(void)
 {
 #if 0 /* FIXME!! */
-/* 
+/*
  * NOTE:  this routine is VERY specific to the current TLB image.
  * If the image is changed, this routine might also need to be changed.
  */
@@ -367,9 +367,9 @@ static void perf_patch_images(void)
 	extern void $i_dtlb_miss_2_0();
 	extern void PA2_0_iva();
 
-	/* 
+	/*
 	 * We can only use the lower 32-bits, the upper 32-bits should be 0
-	 * anyway given this is in the kernel 
+	 * anyway given this is in the kernel
 	 */
 	uint32_t itlb_addr  = (uint32_t)&($i_itlb_miss_2_0);
 	uint32_t dtlb_addr  = (uint32_t)&($i_dtlb_miss_2_0);
@@ -377,21 +377,21 @@ static void perf_patch_images(void)
 
 	if (perf_processor_interface == ONYX_INTF) {
 		/* clear last 2 bytes */
-		onyx_images[TLBMISS][15] &= 0xffffff00;  
+		onyx_images[TLBMISS][15] &= 0xffffff00;
 		/* set 2 bytes */
 		onyx_images[TLBMISS][15] |= (0x000000ff&((dtlb_addr) >> 24));
 		onyx_images[TLBMISS][16] = (dtlb_addr << 8)&0xffffff00;
 		onyx_images[TLBMISS][17] = itlb_addr;
 
 		/* clear last 2 bytes */
-		onyx_images[TLBHANDMISS][15] &= 0xffffff00;  
+		onyx_images[TLBHANDMISS][15] &= 0xffffff00;
 		/* set 2 bytes */
 		onyx_images[TLBHANDMISS][15] |= (0x000000ff&((dtlb_addr) >> 24));
 		onyx_images[TLBHANDMISS][16] = (dtlb_addr << 8)&0xffffff00;
 		onyx_images[TLBHANDMISS][17] = itlb_addr;
 
 		/* clear last 2 bytes */
-		onyx_images[BIG_CPI][15] &= 0xffffff00;  
+		onyx_images[BIG_CPI][15] &= 0xffffff00;
 		/* set 2 bytes */
 		onyx_images[BIG_CPI][15] |= (0x000000ff&((dtlb_addr) >> 24));
 		onyx_images[BIG_CPI][16] = (dtlb_addr << 8)&0xffffff00;
@@ -404,24 +404,24 @@ static void perf_patch_images(void)
 
 	} else if (perf_processor_interface == CUDA_INTF) {
 		/* Cuda interface */
-		cuda_images[TLBMISS][16] =  
+		cuda_images[TLBMISS][16] =
 			(cuda_images[TLBMISS][16]&0xffff0000) |
 			((dtlb_addr >> 8)&0x0000ffff);
-		cuda_images[TLBMISS][17] = 
+		cuda_images[TLBMISS][17] =
 			((dtlb_addr << 24)&0xff000000) | ((itlb_addr >> 16)&0x000000ff);
 		cuda_images[TLBMISS][18] = (itlb_addr << 16)&0xffff0000;
 
-		cuda_images[TLBHANDMISS][16] = 
+		cuda_images[TLBHANDMISS][16] =
 			(cuda_images[TLBHANDMISS][16]&0xffff0000) |
 			((dtlb_addr >> 8)&0x0000ffff);
-		cuda_images[TLBHANDMISS][17] = 
+		cuda_images[TLBHANDMISS][17] =
 			((dtlb_addr << 24)&0xff000000) | ((itlb_addr >> 16)&0x000000ff);
 		cuda_images[TLBHANDMISS][18] = (itlb_addr << 16)&0xffff0000;
 
-		cuda_images[BIG_CPI][16] = 
+		cuda_images[BIG_CPI][16] =
 			(cuda_images[BIG_CPI][16]&0xffff0000) |
 			((dtlb_addr >> 8)&0x0000ffff);
-		cuda_images[BIG_CPI][17] = 
+		cuda_images[BIG_CPI][17] =
 			((dtlb_addr << 24)&0xff000000) | ((itlb_addr >> 16)&0x000000ff);
 		cuda_images[BIG_CPI][18] = (itlb_addr << 16)&0xffff0000;
 	} else {
@@ -433,7 +433,7 @@ static void perf_patch_images(void)
 
 /*
  * ioctl routine
- * All routines effect the processor that they are executed on.  Thus you 
+ * All routines effect the processor that they are executed on.  Thus you
  * must be running on the processor that you wish to change.
  */
 
@@ -459,7 +459,7 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			}
 
 			/* copy out the Counters */
-			if (copy_to_user((void __user *)arg, raddr, 
+			if (copy_to_user((void __user *)arg, raddr,
 					sizeof (raddr)) != 0) {
 				error =  -EFAULT;
 				break;
@@ -487,7 +487,7 @@ static const struct file_operations perf_fops = {
 	.open = perf_open,
 	.release = perf_release
 };
-	
+
 static struct miscdevice perf_dev = {
 	MISC_DYNAMIC_MINOR,
 	PA_PERF_DEV,
@@ -595,7 +595,7 @@ static int perf_stop_counters(uint32_t *raddr)
 		/* OR sticky2 (bit 1496) to counter2 bit 32 */
 		tmp64 |= (userbuf[23] >> 8) & 0x0000000080000000;
 		raddr[2] = (uint32_t)tmp64;
-		
+
 		/* Counter3 is bits 1497 to 1528 */
 		tmp64 =  (userbuf[23] >> 7) & 0x00000000ffffffff;
 		/* OR sticky3 (bit 1529) to counter3 bit 32 */
@@ -617,7 +617,7 @@ static int perf_stop_counters(uint32_t *raddr)
 		userbuf[22] = 0;
 		userbuf[23] = 0;
 
-		/* 
+		/*
 		 * Write back the zeroed bytes + the image given
 		 * the read was destructive.
 		 */
@@ -625,13 +625,13 @@ static int perf_stop_counters(uint32_t *raddr)
 	} else {
 
 		/*
-		 * Read RDR-15 which contains the counters and sticky bits 
+		 * Read RDR-15 which contains the counters and sticky bits
 		 */
 		if (!perf_rdr_read_ubuf(15, userbuf)) {
 			return -13;
 		}
 
-		/* 
+		/*
 		 * Clear out the counters
 		 */
 		perf_rdr_clear(15);
@@ -644,7 +644,7 @@ static int perf_stop_counters(uint32_t *raddr)
 		raddr[2] = (uint32_t)((userbuf[1] >> 32) & 0x00000000ffffffffUL);
 		raddr[3] = (uint32_t)(userbuf[1] & 0x00000000ffffffffUL);
 	}
- 
+
 	return 0;
 }
 
@@ -682,7 +682,7 @@ static int perf_rdr_read_ubuf(uint32_t	rdr_num, uint64_t *buffer)
 	i = tentry->num_words;
 	while (i--) {
 		buffer[i] = 0;
-	}	
+	}
 
 	/* Check for bits an even number of 64 */
 	if ((xbits = width & 0x03f) != 0) {
@@ -808,18 +808,22 @@ static int perf_write_image(uint64_t *memaddr)
 	}
 
 	runway = ioremap_nocache(cpu_device->hpa.start, 4096);
+	if (!runway) {
+		pr_err("perf_write_image: ioremap failed!\n");
+		return -ENOMEM;
+	}
 
 	/* Merge intrigue bits into Runway STATUS 0 */
 	tmp64 = __raw_readq(runway + RUNWAY_STATUS) & 0xffecfffffffffffful;
-	__raw_writeq(tmp64 | (*memaddr++ & 0x0013000000000000ul), 
+	__raw_writeq(tmp64 | (*memaddr++ & 0x0013000000000000ul),
 		     runway + RUNWAY_STATUS);
-	
+
 	/* Write RUNWAY DEBUG registers */
 	for (i = 0; i < 8; i++) {
 		__raw_writeq(*memaddr++, runway + RUNWAY_DEBUG);
 	}
 
-	return 0; 
+	return 0;
 }
 
 /*
@@ -843,7 +847,7 @@ printk("perf_rdr_write\n");
 			perf_rdr_shift_out_U(rdr_num, buffer[i]);
 		} else {
 			perf_rdr_shift_out_W(rdr_num, buffer[i]);
-		}	
+		}
 	}
 printk("perf_rdr_write done\n");
 }
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 06f7ca7fe70b..4516a5b53f38 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -142,6 +142,10 @@ void machine_power_off(void)
 
 	printk(KERN_EMERG "System shut down completed.\n"
 	       "Please power this system off now.");
+
+	/* prevent soft lockup/stalled CPU messages for endless loop. */
+	rcu_sysrq_start();
+	for (;;);
 }
 
 void (*pm_power_off)(void) = machine_power_off;
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 3cfef1de8061..44aeaa9c039f 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -444,6 +444,7 @@
 	ENTRY_SAME(copy_file_range)
 	ENTRY_COMP(preadv2)
 	ENTRY_COMP(pwritev2)
+	ENTRY_SAME(statx)
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile
index 8fa92b8d839a..f2dac4d73b1b 100644
--- a/arch/parisc/lib/Makefile
+++ b/arch/parisc/lib/Makefile
@@ -2,7 +2,7 @@
 # Makefile for parisc-specific library files
 #
 
-lib-y	:= lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o \
+lib-y	:= lusercopy.o bitops.o checksum.o io.o memset.o memcpy.o \
 	   ucmpdi2.o delay.o
 
 obj-y	:= iomap.o
diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S
deleted file mode 100644
index a5b72f22c7a6..000000000000
--- a/arch/parisc/lib/fixup.S
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Linux/PA-RISC Project (http://www.parisc-linux.org/)
- *
- *  Copyright (C) 2004  Randolph Chung <tausq@debian.org>
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2, or (at your option)
- *    any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *    GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- * 
- * Fixup routines for kernel exception handling.
- */
-#include <asm/asm-offsets.h>
-#include <asm/assembly.h>
-#include <asm/errno.h>
-#include <linux/linkage.h>
-
-#ifdef CONFIG_SMP
-	.macro  get_fault_ip t1 t2
-	loadgp
-	addil LT%__per_cpu_offset,%r27
-	LDREG RT%__per_cpu_offset(%r1),\t1
-	/* t2 = smp_processor_id() */
-	mfctl 30,\t2
-	ldw TI_CPU(\t2),\t2
-#ifdef CONFIG_64BIT
-	extrd,u \t2,63,32,\t2
-#endif
-	/* t2 = &__per_cpu_offset[smp_processor_id()]; */
-	LDREGX \t2(\t1),\t2 
-	addil LT%exception_data,%r27
-	LDREG RT%exception_data(%r1),\t1
-	/* t1 = this_cpu_ptr(&exception_data) */
-	add,l \t1,\t2,\t1
-	/* %r27 = t1->fault_gp - restore gp */
-	LDREG EXCDATA_GP(\t1), %r27
-	/* t1 = t1->fault_ip */
-	LDREG EXCDATA_IP(\t1), \t1
-	.endm
-#else
-	.macro  get_fault_ip t1 t2
-	loadgp
-	/* t1 = this_cpu_ptr(&exception_data) */
-	addil LT%exception_data,%r27
-	LDREG RT%exception_data(%r1),\t2
-	/* %r27 = t2->fault_gp - restore gp */
-	LDREG EXCDATA_GP(\t2), %r27
-	/* t1 = t2->fault_ip */
-	LDREG EXCDATA_IP(\t2), \t1
-	.endm
-#endif
-
-	.level LEVEL
-
-	.text
-	.section .fixup, "ax"
-
-	/* get_user() fixups, store -EFAULT in r8, and 0 in r9 */
-ENTRY_CFI(fixup_get_user_skip_1)
-	get_fault_ip %r1,%r8
-	ldo 4(%r1), %r1
-	ldi -EFAULT, %r8
-	bv %r0(%r1)
-	copy %r0, %r9
-ENDPROC_CFI(fixup_get_user_skip_1)
-
-ENTRY_CFI(fixup_get_user_skip_2)
-	get_fault_ip %r1,%r8
-	ldo 8(%r1), %r1
-	ldi -EFAULT, %r8
-	bv %r0(%r1)
-	copy %r0, %r9
-ENDPROC_CFI(fixup_get_user_skip_2)
-
-	/* put_user() fixups, store -EFAULT in r8 */
-ENTRY_CFI(fixup_put_user_skip_1)
-	get_fault_ip %r1,%r8
-	ldo 4(%r1), %r1
-	bv %r0(%r1)
-	ldi -EFAULT, %r8
-ENDPROC_CFI(fixup_put_user_skip_1)
-
-ENTRY_CFI(fixup_put_user_skip_2)
-	get_fault_ip %r1,%r8
-	ldo 8(%r1), %r1
-	bv %r0(%r1)
-	ldi -EFAULT, %r8
-ENDPROC_CFI(fixup_put_user_skip_2)
-
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index 56845de6b5df..85c28bb80fb7 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -5,6 +5,8 @@
  *    Copyright (C) 2000 Richard Hirst <rhirst with parisc-linux.org>
  *    Copyright (C) 2001 Matthieu Delahaye <delahaym at esiee.fr>
  *    Copyright (C) 2003 Randolph Chung <tausq with parisc-linux.org>
+ *    Copyright (C) 2017 Helge Deller <deller@gmx.de>
+ *    Copyright (C) 2017 John David Anglin <dave.anglin@bell.net>
  *
  *
  *    This program is free software; you can redistribute it and/or modify
@@ -132,4 +134,321 @@ ENDPROC_CFI(lstrnlen_user)
 
 	.procend
 
+
+
+/*
+ * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
+ *
+ * Inputs:
+ * - sr1 already contains space of source region
+ * - sr2 already contains space of destination region
+ *
+ * Returns:
+ * - number of bytes that could not be copied.
+ *   On success, this will be zero.
+ *
+ * This code is based on a C-implementation of a copy routine written by
+ * Randolph Chung, which in turn was derived from the glibc.
+ *
+ * Several strategies are tried to try to get the best performance for various
+ * conditions. In the optimal case, we copy by loops that copy 32- or 16-bytes
+ * at a time using general registers.  Unaligned copies are handled either by
+ * aligning the destination and then using shift-and-write method, or in a few
+ * cases by falling back to a byte-at-a-time copy.
+ *
+ * Testing with various alignments and buffer sizes shows that this code is
+ * often >10x faster than a simple byte-at-a-time copy, even for strangely
+ * aligned operands. It is interesting to note that the glibc version of memcpy
+ * (written in C) is actually quite fast already. This routine is able to beat
+ * it by 30-40% for aligned copies because of the loop unrolling, but in some
+ * cases the glibc version is still slightly faster. This lends more
+ * credibility that gcc can generate very good code as long as we are careful.
+ *
+ * Possible optimizations:
+ * - add cache prefetching
+ * - try not to use the post-increment address modifiers; they may create
+ *   additional interlocks. Assumption is that those were only efficient on old
+ *   machines (pre PA8000 processors)
+ */
+
+	dst = arg0
+	src = arg1
+	len = arg2
+	end = arg3
+	t1  = r19
+	t2  = r20
+	t3  = r21
+	t4  = r22
+	srcspc = sr1
+	dstspc = sr2
+
+	t0 = r1
+	a1 = t1
+	a2 = t2
+	a3 = t3
+	a0 = t4
+
+	save_src = ret0
+	save_dst = ret1
+	save_len = r31
+
+ENTRY_CFI(pa_memcpy)
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	/* Last destination address */
+	add	dst,len,end
+
+	/* short copy with less than 16 bytes? */
+	cmpib,COND(>>=),n 15,len,.Lbyte_loop
+
+	/* same alignment? */
+	xor	src,dst,t0
+	extru	t0,31,2,t1
+	cmpib,<>,n  0,t1,.Lunaligned_copy
+
+#ifdef CONFIG_64BIT
+	/* only do 64-bit copies if we can get aligned. */
+	extru	t0,31,3,t1
+	cmpib,<>,n  0,t1,.Lalign_loop32
+
+	/* loop until we are 64-bit aligned */
+.Lalign_loop64:
+	extru	dst,31,3,t1
+	cmpib,=,n	0,t1,.Lcopy_loop_16_start
+20:	ldb,ma	1(srcspc,src),t1
+21:	stb,ma	t1,1(dstspc,dst)
+	b	.Lalign_loop64
+	ldo	-1(len),len
+
+	ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+.Lcopy_loop_16_start:
+	ldi	31,t0
+.Lcopy_loop_16:
+	cmpb,COND(>>=),n t0,len,.Lword_loop
+
+10:	ldd	0(srcspc,src),t1
+11:	ldd	8(srcspc,src),t2
+	ldo	16(src),src
+12:	std,ma	t1,8(dstspc,dst)
+13:	std,ma	t2,8(dstspc,dst)
+14:	ldd	0(srcspc,src),t1
+15:	ldd	8(srcspc,src),t2
+	ldo	16(src),src
+16:	std,ma	t1,8(dstspc,dst)
+17:	std,ma	t2,8(dstspc,dst)
+
+	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(11b,.Lcopy16_fault)
+	ASM_EXCEPTIONTABLE_ENTRY(12b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(13b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(14b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(15b,.Lcopy16_fault)
+	ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done)
+
+	b	.Lcopy_loop_16
+	ldo	-32(len),len
+
+.Lword_loop:
+	cmpib,COND(>>=),n 3,len,.Lbyte_loop
+20:	ldw,ma	4(srcspc,src),t1
+21:	stw,ma	t1,4(dstspc,dst)
+	b	.Lword_loop
+	ldo	-4(len),len
+
+	ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+#endif /* CONFIG_64BIT */
+
+	/* loop until we are 32-bit aligned */
+.Lalign_loop32:
+	extru	dst,31,2,t1
+	cmpib,=,n	0,t1,.Lcopy_loop_8
+20:	ldb,ma	1(srcspc,src),t1
+21:	stb,ma	t1,1(dstspc,dst)
+	b	.Lalign_loop32
+	ldo	-1(len),len
+
+	ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+
+.Lcopy_loop_8:
+	cmpib,COND(>>=),n 15,len,.Lbyte_loop
+
+10:	ldw	0(srcspc,src),t1
+11:	ldw	4(srcspc,src),t2
+12:	stw,ma	t1,4(dstspc,dst)
+13:	stw,ma	t2,4(dstspc,dst)
+14:	ldw	8(srcspc,src),t1
+15:	ldw	12(srcspc,src),t2
+	ldo	16(src),src
+16:	stw,ma	t1,4(dstspc,dst)
+17:	stw,ma	t2,4(dstspc,dst)
+
+	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(11b,.Lcopy8_fault)
+	ASM_EXCEPTIONTABLE_ENTRY(12b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(13b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(14b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(15b,.Lcopy8_fault)
+	ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done)
+
+	b	.Lcopy_loop_8
+	ldo	-16(len),len
+
+.Lbyte_loop:
+	cmpclr,COND(<>) len,%r0,%r0
+	b,n	.Lcopy_done
+20:	ldb	0(srcspc,src),t1
+	ldo	1(src),src
+21:	stb,ma	t1,1(dstspc,dst)
+	b	.Lbyte_loop
+	ldo	-1(len),len
+
+	ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+.Lcopy_done:
+	bv	%r0(%r2)
+	sub	end,dst,ret0
+
+
+	/* src and dst are not aligned the same way. */
+	/* need to go the hard way */
+.Lunaligned_copy:
+	/* align until dst is 32bit-word-aligned */
+	extru	dst,31,2,t1
+	cmpib,=,n	0,t1,.Lcopy_dstaligned
+20:	ldb	0(srcspc,src),t1
+	ldo	1(src),src
+21:	stb,ma	t1,1(dstspc,dst)
+	b	.Lunaligned_copy
+	ldo	-1(len),len
+
+	ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+.Lcopy_dstaligned:
+
+	/* store src, dst and len in safe place */
+	copy	src,save_src
+	copy	dst,save_dst
+	copy	len,save_len
+
+	/* len now needs give number of words to copy */
+	SHRREG	len,2,len
+
+	/*
+	 * Copy from a not-aligned src to an aligned dst using shifts.
+	 * Handles 4 words per loop.
+	 */
+
+	depw,z src,28,2,t0
+	subi 32,t0,t0
+	mtsar t0
+	extru len,31,2,t0
+	cmpib,= 2,t0,.Lcase2
+	/* Make src aligned by rounding it down.  */
+	depi 0,31,2,src
+
+	cmpiclr,<> 3,t0,%r0
+	b,n .Lcase3
+	cmpiclr,<> 1,t0,%r0
+	b,n .Lcase1
+.Lcase0:
+	cmpb,COND(=) %r0,len,.Lcda_finish
+	nop
+
+1:	ldw,ma 4(srcspc,src), a3
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1:	ldw,ma 4(srcspc,src), a0
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	b,n .Ldo3
+.Lcase1:
+1:	ldw,ma 4(srcspc,src), a2
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1:	ldw,ma 4(srcspc,src), a3
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	ldo -1(len),len
+	cmpb,COND(=),n %r0,len,.Ldo0
+.Ldo4:
+1:	ldw,ma 4(srcspc,src), a0
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	shrpw a2, a3, %sar, t0
+1:	stw,ma t0, 4(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+.Ldo3:
+1:	ldw,ma 4(srcspc,src), a1
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	shrpw a3, a0, %sar, t0
+1:	stw,ma t0, 4(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+.Ldo2:
+1:	ldw,ma 4(srcspc,src), a2
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	shrpw a0, a1, %sar, t0
+1:	stw,ma t0, 4(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+.Ldo1:
+1:	ldw,ma 4(srcspc,src), a3
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	shrpw a1, a2, %sar, t0
+1:	stw,ma t0, 4(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+	ldo -4(len),len
+	cmpb,COND(<>) %r0,len,.Ldo4
+	nop
+.Ldo0:
+	shrpw a2, a3, %sar, t0
+1:	stw,ma t0, 4(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+
+.Lcda_rdfault:
+.Lcda_finish:
+	/* calculate new src, dst and len and jump to byte-copy loop */
+	sub	dst,save_dst,t0
+	add	save_src,t0,src
+	b	.Lbyte_loop
+	sub	save_len,t0,len
+
+.Lcase3:
+1:	ldw,ma 4(srcspc,src), a0
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1:	ldw,ma 4(srcspc,src), a1
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	b .Ldo2
+	ldo 1(len),len
+.Lcase2:
+1:	ldw,ma 4(srcspc,src), a1
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1:	ldw,ma 4(srcspc,src), a2
+	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+	b .Ldo1
+	ldo 2(len),len
+
+
+	/* fault exception fixup handlers: */
+#ifdef CONFIG_64BIT
+.Lcopy16_fault:
+	b	.Lcopy_done
+10:	std,ma	t1,8(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+#endif
+
+.Lcopy8_fault:
+	b	.Lcopy_done
+10:	stw,ma	t1,4(dstspc,dst)
+	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+
+	.exit
+ENDPROC_CFI(pa_memcpy)
+	.procend
+
 	.end
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index f82ff10ed974..99115cd9e790 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -2,7 +2,7 @@
  *    Optimized memory copy routines.
  *
  *    Copyright (C) 2004 Randolph Chung <tausq@debian.org>
- *    Copyright (C) 2013 Helge Deller <deller@gmx.de>
+ *    Copyright (C) 2013-2017 Helge Deller <deller@gmx.de>
  *
  *    This program is free software; you can redistribute it and/or modify
  *    it under the terms of the GNU General Public License as published by
@@ -21,493 +21,40 @@
  *    Portions derived from the GNU C Library
  *    Copyright (C) 1991, 1997, 2003 Free Software Foundation, Inc.
  *
- * Several strategies are tried to try to get the best performance for various
- * conditions. In the optimal case, we copy 64-bytes in an unrolled loop using 
- * fp regs. This is followed by loops that copy 32- or 16-bytes at a time using
- * general registers.  Unaligned copies are handled either by aligning the 
- * destination and then using shift-and-write method, or in a few cases by 
- * falling back to a byte-at-a-time copy.
- *
- * I chose to implement this in C because it is easier to maintain and debug,
- * and in my experiments it appears that the C code generated by gcc (3.3/3.4
- * at the time of writing) is fairly optimal. Unfortunately some of the 
- * semantics of the copy routine (exception handling) is difficult to express
- * in C, so we have to play some tricks to get it to work.
- *
- * All the loads and stores are done via explicit asm() code in order to use
- * the right space registers. 
- * 
- * Testing with various alignments and buffer sizes shows that this code is 
- * often >10x faster than a simple byte-at-a-time copy, even for strangely
- * aligned operands. It is interesting to note that the glibc version
- * of memcpy (written in C) is actually quite fast already. This routine is 
- * able to beat it by 30-40% for aligned copies because of the loop unrolling, 
- * but in some cases the glibc version is still slightly faster. This lends 
- * more credibility that gcc can generate very good code as long as we are 
- * careful.
- *
- * TODO:
- * - cache prefetching needs more experimentation to get optimal settings
- * - try not to use the post-increment address modifiers; they create additional
- *   interlocks
- * - replace byte-copy loops with stybs sequences
  */
 
-#ifdef __KERNEL__
 #include <linux/module.h>
 #include <linux/compiler.h>
 #include <linux/uaccess.h>
-#define s_space "%%sr1"
-#define d_space "%%sr2"
-#else
-#include "memcpy.h"
-#define s_space "%%sr0"
-#define d_space "%%sr0"
-#define pa_memcpy new2_copy
-#endif
 
 DECLARE_PER_CPU(struct exception_data, exception_data);
 
-#define preserve_branch(label)	do {					\
-	volatile int dummy = 0;						\
-	/* The following branch is never taken, it's just here to  */	\
-	/* prevent gcc from optimizing away our exception code. */ 	\
-	if (unlikely(dummy != dummy))					\
-		goto label;						\
-} while (0)
-
-#define get_user_space() (segment_eq(get_fs(), KERNEL_DS) ? 0 : mfsp(3))
+#define get_user_space() (uaccess_kernel() ? 0 : mfsp(3))
 #define get_kernel_space() (0)
 
-#define MERGE(w0, sh_1, w1, sh_2)  ({					\
-	unsigned int _r;						\
-	asm volatile (							\
-	"mtsar %3\n"							\
-	"shrpw %1, %2, %%sar, %0\n"					\
-	: "=r"(_r)							\
-	: "r"(w0), "r"(w1), "r"(sh_2)					\
-	);								\
-	_r;								\
-})
-#define THRESHOLD	16
-
-#ifdef DEBUG_MEMCPY
-#define DPRINTF(fmt, args...) do { printk(KERN_DEBUG "%s:%d:%s ", __FILE__, __LINE__, __func__ ); printk(KERN_DEBUG fmt, ##args ); } while (0)
-#else
-#define DPRINTF(fmt, args...)
-#endif
-
-#define def_load_ai_insn(_insn,_sz,_tt,_s,_a,_t,_e)	\
-	__asm__ __volatile__ (				\
-	"1:\t" #_insn ",ma " #_sz "(" _s ",%1), %0\n\t"	\
-	ASM_EXCEPTIONTABLE_ENTRY(1b,_e)			\
-	: _tt(_t), "+r"(_a)				\
-	: 						\
-	: "r8")
-
-#define def_store_ai_insn(_insn,_sz,_tt,_s,_a,_t,_e) 	\
-	__asm__ __volatile__ (				\
-	"1:\t" #_insn ",ma %1, " #_sz "(" _s ",%0)\n\t"	\
-	ASM_EXCEPTIONTABLE_ENTRY(1b,_e)			\
-	: "+r"(_a) 					\
-	: _tt(_t)					\
-	: "r8")
-
-#define ldbma(_s, _a, _t, _e) def_load_ai_insn(ldbs,1,"=r",_s,_a,_t,_e)
-#define stbma(_s, _t, _a, _e) def_store_ai_insn(stbs,1,"r",_s,_a,_t,_e)
-#define ldwma(_s, _a, _t, _e) def_load_ai_insn(ldw,4,"=r",_s,_a,_t,_e)
-#define stwma(_s, _t, _a, _e) def_store_ai_insn(stw,4,"r",_s,_a,_t,_e)
-#define flddma(_s, _a, _t, _e) def_load_ai_insn(fldd,8,"=f",_s,_a,_t,_e)
-#define fstdma(_s, _t, _a, _e) def_store_ai_insn(fstd,8,"f",_s,_a,_t,_e)
-
-#define def_load_insn(_insn,_tt,_s,_o,_a,_t,_e) 	\
-	__asm__ __volatile__ (				\
-	"1:\t" #_insn " " #_o "(" _s ",%1), %0\n\t"	\
-	ASM_EXCEPTIONTABLE_ENTRY(1b,_e)			\
-	: _tt(_t) 					\
-	: "r"(_a)					\
-	: "r8")
-
-#define def_store_insn(_insn,_tt,_s,_t,_o,_a,_e) 	\
-	__asm__ __volatile__ (				\
-	"1:\t" #_insn " %0, " #_o "(" _s ",%1)\n\t" 	\
-	ASM_EXCEPTIONTABLE_ENTRY(1b,_e)			\
-	: 						\
-	: _tt(_t), "r"(_a)				\
-	: "r8")
-
-#define ldw(_s,_o,_a,_t,_e)	def_load_insn(ldw,"=r",_s,_o,_a,_t,_e)
-#define stw(_s,_t,_o,_a,_e) 	def_store_insn(stw,"r",_s,_t,_o,_a,_e)
-
-#ifdef  CONFIG_PREFETCH
-static inline void prefetch_src(const void *addr)
-{
-	__asm__("ldw 0(" s_space ",%0), %%r0" : : "r" (addr));
-}
-
-static inline void prefetch_dst(const void *addr)
-{
-	__asm__("ldd 0(" d_space ",%0), %%r0" : : "r" (addr));
-}
-#else
-#define prefetch_src(addr) do { } while(0)
-#define prefetch_dst(addr) do { } while(0)
-#endif
-
-#define PA_MEMCPY_OK		0
-#define PA_MEMCPY_LOAD_ERROR	1
-#define PA_MEMCPY_STORE_ERROR	2
-
-/* Copy from a not-aligned src to an aligned dst, using shifts. Handles 4 words
- * per loop.  This code is derived from glibc. 
- */
-static noinline unsigned long copy_dstaligned(unsigned long dst,
-					unsigned long src, unsigned long len)
-{
-	/* gcc complains that a2 and a3 may be uninitialized, but actually
-	 * they cannot be.  Initialize a2/a3 to shut gcc up.
-	 */
-	register unsigned int a0, a1, a2 = 0, a3 = 0;
-	int sh_1, sh_2;
-
-	/* prefetch_src((const void *)src); */
-
-	/* Calculate how to shift a word read at the memory operation
-	   aligned srcp to make it aligned for copy.  */
-	sh_1 = 8 * (src % sizeof(unsigned int));
-	sh_2 = 8 * sizeof(unsigned int) - sh_1;
-
-	/* Make src aligned by rounding it down.  */
-	src &= -sizeof(unsigned int);
-
-	switch (len % 4)
-	{
-		case 2:
-			/* a1 = ((unsigned int *) src)[0];
-			   a2 = ((unsigned int *) src)[1]; */
-			ldw(s_space, 0, src, a1, cda_ldw_exc);
-			ldw(s_space, 4, src, a2, cda_ldw_exc);
-			src -= 1 * sizeof(unsigned int);
-			dst -= 3 * sizeof(unsigned int);
-			len += 2;
-			goto do1;
-		case 3:
-			/* a0 = ((unsigned int *) src)[0];
-			   a1 = ((unsigned int *) src)[1]; */
-			ldw(s_space, 0, src, a0, cda_ldw_exc);
-			ldw(s_space, 4, src, a1, cda_ldw_exc);
-			src -= 0 * sizeof(unsigned int);
-			dst -= 2 * sizeof(unsigned int);
-			len += 1;
-			goto do2;
-		case 0:
-			if (len == 0)
-				return PA_MEMCPY_OK;
-			/* a3 = ((unsigned int *) src)[0];
-			   a0 = ((unsigned int *) src)[1]; */
-			ldw(s_space, 0, src, a3, cda_ldw_exc);
-			ldw(s_space, 4, src, a0, cda_ldw_exc);
-			src -=-1 * sizeof(unsigned int);
-			dst -= 1 * sizeof(unsigned int);
-			len += 0;
-			goto do3;
-		case 1:
-			/* a2 = ((unsigned int *) src)[0];
-			   a3 = ((unsigned int *) src)[1]; */
-			ldw(s_space, 0, src, a2, cda_ldw_exc);
-			ldw(s_space, 4, src, a3, cda_ldw_exc);
-			src -=-2 * sizeof(unsigned int);
-			dst -= 0 * sizeof(unsigned int);
-			len -= 1;
-			if (len == 0)
-				goto do0;
-			goto do4;			/* No-op.  */
-	}
-
-	do
-	{
-		/* prefetch_src((const void *)(src + 4 * sizeof(unsigned int))); */
-do4:
-		/* a0 = ((unsigned int *) src)[0]; */
-		ldw(s_space, 0, src, a0, cda_ldw_exc);
-		/* ((unsigned int *) dst)[0] = MERGE (a2, sh_1, a3, sh_2); */
-		stw(d_space, MERGE (a2, sh_1, a3, sh_2), 0, dst, cda_stw_exc);
-do3:
-		/* a1 = ((unsigned int *) src)[1]; */
-		ldw(s_space, 4, src, a1, cda_ldw_exc);
-		/* ((unsigned int *) dst)[1] = MERGE (a3, sh_1, a0, sh_2); */
-		stw(d_space, MERGE (a3, sh_1, a0, sh_2), 4, dst, cda_stw_exc);
-do2:
-		/* a2 = ((unsigned int *) src)[2]; */
-		ldw(s_space, 8, src, a2, cda_ldw_exc);
-		/* ((unsigned int *) dst)[2] = MERGE (a0, sh_1, a1, sh_2); */
-		stw(d_space, MERGE (a0, sh_1, a1, sh_2), 8, dst, cda_stw_exc);
-do1:
-		/* a3 = ((unsigned int *) src)[3]; */
-		ldw(s_space, 12, src, a3, cda_ldw_exc);
-		/* ((unsigned int *) dst)[3] = MERGE (a1, sh_1, a2, sh_2); */
-		stw(d_space, MERGE (a1, sh_1, a2, sh_2), 12, dst, cda_stw_exc);
-
-		src += 4 * sizeof(unsigned int);
-		dst += 4 * sizeof(unsigned int);
-		len -= 4;
-	}
-	while (len != 0);
-
-do0:
-	/* ((unsigned int *) dst)[0] = MERGE (a2, sh_1, a3, sh_2); */
-	stw(d_space, MERGE (a2, sh_1, a3, sh_2), 0, dst, cda_stw_exc);
-
-	preserve_branch(handle_load_error);
-	preserve_branch(handle_store_error);
-
-	return PA_MEMCPY_OK;
-
-handle_load_error:
-	__asm__ __volatile__ ("cda_ldw_exc:\n");
-	return PA_MEMCPY_LOAD_ERROR;
-
-handle_store_error:
-	__asm__ __volatile__ ("cda_stw_exc:\n");
-	return PA_MEMCPY_STORE_ERROR;
-}
-
-
-/* Returns PA_MEMCPY_OK, PA_MEMCPY_LOAD_ERROR or PA_MEMCPY_STORE_ERROR.
- * In case of an access fault the faulty address can be read from the per_cpu
- * exception data struct. */
-static noinline unsigned long pa_memcpy_internal(void *dstp, const void *srcp,
-					unsigned long len)
-{
-	register unsigned long src, dst, t1, t2, t3;
-	register unsigned char *pcs, *pcd;
-	register unsigned int *pws, *pwd;
-	register double *pds, *pdd;
-	unsigned long ret;
-
-	src = (unsigned long)srcp;
-	dst = (unsigned long)dstp;
-	pcs = (unsigned char *)srcp;
-	pcd = (unsigned char *)dstp;
-
-	/* prefetch_src((const void *)srcp); */
-
-	if (len < THRESHOLD)
-		goto byte_copy;
-
-	/* Check alignment */
-	t1 = (src ^ dst);
-	if (unlikely(t1 & (sizeof(double)-1)))
-		goto unaligned_copy;
-
-	/* src and dst have same alignment. */
-
-	/* Copy bytes till we are double-aligned. */
-	t2 = src & (sizeof(double) - 1);
-	if (unlikely(t2 != 0)) {
-		t2 = sizeof(double) - t2;
-		while (t2 && len) {
-			/* *pcd++ = *pcs++; */
-			ldbma(s_space, pcs, t3, pmc_load_exc);
-			len--;
-			stbma(d_space, t3, pcd, pmc_store_exc);
-			t2--;
-		}
-	}
-
-	pds = (double *)pcs;
-	pdd = (double *)pcd;
-
-#if 0
-	/* Copy 8 doubles at a time */
-	while (len >= 8*sizeof(double)) {
-		register double r1, r2, r3, r4, r5, r6, r7, r8;
-		/* prefetch_src((char *)pds + L1_CACHE_BYTES); */
-		flddma(s_space, pds, r1, pmc_load_exc);
-		flddma(s_space, pds, r2, pmc_load_exc);
-		flddma(s_space, pds, r3, pmc_load_exc);
-		flddma(s_space, pds, r4, pmc_load_exc);
-		fstdma(d_space, r1, pdd, pmc_store_exc);
-		fstdma(d_space, r2, pdd, pmc_store_exc);
-		fstdma(d_space, r3, pdd, pmc_store_exc);
-		fstdma(d_space, r4, pdd, pmc_store_exc);
-
-#if 0
-		if (L1_CACHE_BYTES <= 32)
-			prefetch_src((char *)pds + L1_CACHE_BYTES);
-#endif
-		flddma(s_space, pds, r5, pmc_load_exc);
-		flddma(s_space, pds, r6, pmc_load_exc);
-		flddma(s_space, pds, r7, pmc_load_exc);
-		flddma(s_space, pds, r8, pmc_load_exc);
-		fstdma(d_space, r5, pdd, pmc_store_exc);
-		fstdma(d_space, r6, pdd, pmc_store_exc);
-		fstdma(d_space, r7, pdd, pmc_store_exc);
-		fstdma(d_space, r8, pdd, pmc_store_exc);
-		len -= 8*sizeof(double);
-	}
-#endif
-
-	pws = (unsigned int *)pds;
-	pwd = (unsigned int *)pdd;
-
-word_copy:
-	while (len >= 8*sizeof(unsigned int)) {
-		register unsigned int r1,r2,r3,r4,r5,r6,r7,r8;
-		/* prefetch_src((char *)pws + L1_CACHE_BYTES); */
-		ldwma(s_space, pws, r1, pmc_load_exc);
-		ldwma(s_space, pws, r2, pmc_load_exc);
-		ldwma(s_space, pws, r3, pmc_load_exc);
-		ldwma(s_space, pws, r4, pmc_load_exc);
-		stwma(d_space, r1, pwd, pmc_store_exc);
-		stwma(d_space, r2, pwd, pmc_store_exc);
-		stwma(d_space, r3, pwd, pmc_store_exc);
-		stwma(d_space, r4, pwd, pmc_store_exc);
-
-		ldwma(s_space, pws, r5, pmc_load_exc);
-		ldwma(s_space, pws, r6, pmc_load_exc);
-		ldwma(s_space, pws, r7, pmc_load_exc);
-		ldwma(s_space, pws, r8, pmc_load_exc);
-		stwma(d_space, r5, pwd, pmc_store_exc);
-		stwma(d_space, r6, pwd, pmc_store_exc);
-		stwma(d_space, r7, pwd, pmc_store_exc);
-		stwma(d_space, r8, pwd, pmc_store_exc);
-		len -= 8*sizeof(unsigned int);
-	}
-
-	while (len >= 4*sizeof(unsigned int)) {
-		register unsigned int r1,r2,r3,r4;
-		ldwma(s_space, pws, r1, pmc_load_exc);
-		ldwma(s_space, pws, r2, pmc_load_exc);
-		ldwma(s_space, pws, r3, pmc_load_exc);
-		ldwma(s_space, pws, r4, pmc_load_exc);
-		stwma(d_space, r1, pwd, pmc_store_exc);
-		stwma(d_space, r2, pwd, pmc_store_exc);
-		stwma(d_space, r3, pwd, pmc_store_exc);
-		stwma(d_space, r4, pwd, pmc_store_exc);
-		len -= 4*sizeof(unsigned int);
-	}
-
-	pcs = (unsigned char *)pws;
-	pcd = (unsigned char *)pwd;
-
-byte_copy:
-	while (len) {
-		/* *pcd++ = *pcs++; */
-		ldbma(s_space, pcs, t3, pmc_load_exc);
-		stbma(d_space, t3, pcd, pmc_store_exc);
-		len--;
-	}
-
-	return PA_MEMCPY_OK;
-
-unaligned_copy:
-	/* possibly we are aligned on a word, but not on a double... */
-	if (likely((t1 & (sizeof(unsigned int)-1)) == 0)) {
-		t2 = src & (sizeof(unsigned int) - 1);
-
-		if (unlikely(t2 != 0)) {
-			t2 = sizeof(unsigned int) - t2;
-			while (t2) {
-				/* *pcd++ = *pcs++; */
-				ldbma(s_space, pcs, t3, pmc_load_exc);
-				stbma(d_space, t3, pcd, pmc_store_exc);
-				len--;
-				t2--;
-			}
-		}
-
-		pws = (unsigned int *)pcs;
-		pwd = (unsigned int *)pcd;
-		goto word_copy;
-	}
-
-	/* Align the destination.  */
-	if (unlikely((dst & (sizeof(unsigned int) - 1)) != 0)) {
-		t2 = sizeof(unsigned int) - (dst & (sizeof(unsigned int) - 1));
-		while (t2) {
-			/* *pcd++ = *pcs++; */
-			ldbma(s_space, pcs, t3, pmc_load_exc);
-			stbma(d_space, t3, pcd, pmc_store_exc);
-			len--;
-			t2--;
-		}
-		dst = (unsigned long)pcd;
-		src = (unsigned long)pcs;
-	}
-
-	ret = copy_dstaligned(dst, src, len / sizeof(unsigned int));
-	if (ret)
-		return ret;
-
-	pcs += (len & -sizeof(unsigned int));
-	pcd += (len & -sizeof(unsigned int));
-	len %= sizeof(unsigned int);
-
-	preserve_branch(handle_load_error);
-	preserve_branch(handle_store_error);
-
-	goto byte_copy;
-
-handle_load_error:
-	__asm__ __volatile__ ("pmc_load_exc:\n");
-	return PA_MEMCPY_LOAD_ERROR;
-
-handle_store_error:
-	__asm__ __volatile__ ("pmc_store_exc:\n");
-	return PA_MEMCPY_STORE_ERROR;
-}
-
-
 /* Returns 0 for success, otherwise, returns number of bytes not transferred. */
-static unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
-{
-	unsigned long ret, fault_addr, reference;
-	struct exception_data *d;
-
-	ret = pa_memcpy_internal(dstp, srcp, len);
-	if (likely(ret == PA_MEMCPY_OK))
-		return 0;
-
-	/* if a load or store fault occured we can get the faulty addr */
-	d = this_cpu_ptr(&exception_data);
-	fault_addr = d->fault_addr;
-
-	/* error in load or store? */
-	if (ret == PA_MEMCPY_LOAD_ERROR)
-		reference = (unsigned long) srcp;
-	else
-		reference = (unsigned long) dstp;
-
-	DPRINTF("pa_memcpy: fault type = %lu, len=%lu fault_addr=%lu ref=%lu\n",
-		ret, len, fault_addr, reference);
+extern unsigned long pa_memcpy(void *dst, const void *src,
+				unsigned long len);
 
-	if (fault_addr >= reference)
-		return len - (fault_addr - reference);
-	else
-		return len;
-}
-
-#ifdef __KERNEL__
-unsigned long __copy_to_user(void __user *dst, const void *src,
-			     unsigned long len)
+unsigned long raw_copy_to_user(void __user *dst, const void *src,
+			       unsigned long len)
 {
 	mtsp(get_kernel_space(), 1);
 	mtsp(get_user_space(), 2);
 	return pa_memcpy((void __force *)dst, src, len);
 }
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 
-unsigned long __copy_from_user(void *dst, const void __user *src,
+unsigned long raw_copy_from_user(void *dst, const void __user *src,
 			       unsigned long len)
 {
 	mtsp(get_user_space(), 1);
 	mtsp(get_kernel_space(), 2);
 	return pa_memcpy(dst, (void __force *)src, len);
 }
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
 
-unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned long len)
+unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long len)
 {
 	mtsp(get_user_space(), 1);
 	mtsp(get_user_space(), 2);
@@ -523,7 +70,7 @@ void * memcpy(void * dst,const void *src, size_t count)
 	return dst;
 }
 
-EXPORT_SYMBOL(copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
 EXPORT_SYMBOL(memcpy);
 
 long probe_kernel_read(void *dst, const void *src, size_t size)
@@ -537,5 +84,3 @@ long probe_kernel_read(void *dst, const void *src, size_t size)
 
 	return __probe_kernel_read(dst, src, size);
 }
-
-#endif
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index deab89a8915a..32ec22146141 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -150,6 +150,23 @@ int fixup_exception(struct pt_regs *regs)
 		d->fault_space = regs->isr;
 		d->fault_addr = regs->ior;
 
+		/*
+		 * Fix up get_user() and put_user().
+		 * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant
+		 * bit in the relative address of the fixup routine to indicate
+		 * that %r8 should be loaded with -EFAULT to report a userspace
+		 * access error.
+		 */
+		if (fix->fixup & 1) {
+			regs->gr[8] = -EFAULT;
+
+			/* zero target register for get_user() */
+			if (parisc_acctyp(0, regs->iir) == VM_READ) {
+				int treg = regs->iir & 0x1f;
+				regs->gr[treg] = 0;
+			}
+		}
+
 		regs->iaoq[0] = (unsigned long)&fix->fixup + fix->fixup;
 		regs->iaoq[0] &= ~3;
 		/*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 494091762bd7..053382616533 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -80,93 +80,98 @@ config ARCH_HAS_DMA_SET_COHERENT_MASK
 config PPC
 	bool
 	default y
-	select BUILDTIME_EXTABLE_SORT
+	#
+	# Please keep this list sorted alphabetically.
+	#
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
+	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select BINFMT_ELF
-	select ARCH_HAS_ELF_RANDOMIZE
-	select OF
-	select OF_EARLY_FLATTREE
-	select OF_RESERVED_MEM
-	select HAVE_FTRACE_MCOUNT_RECORD
+	select BUILDTIME_EXTABLE_SORT
+	select CLONE_BACKWARDS
+	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
+	select EDAC_ATOMIC_SCRUB
+	select EDAC_SUPPORT
+	select GENERIC_ATOMIC64			if PPC32
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
+	select GENERIC_CMOS_UPDATE
+	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_TIME_VSYSCALL_OLD
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_CBPF_JIT			if !PPC64
+	select HAVE_CONTEXT_TRACKING		if PPC64
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
-	select HAVE_FUNCTION_TRACER
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL
+	select HAVE_EBPF_JIT			if PPC64
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS	if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
-	select SYSCTL_EXCEPTION_TRACE
-	select VIRT_TO_BUS if !PPC64
+	select HAVE_GENERIC_RCU_GUP
+	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
-	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_KERNEL_GZIP
 	select HAVE_KPROBES
-	select HAVE_OPTPROBES if PPC64
-	select HAVE_ARCH_KGDB
 	select HAVE_KRETPROBES
-	select HAVE_ARCH_TRACEHOOK
+	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_API_DEBUG
+	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_NMI				if PERF_EVENTS
 	select HAVE_OPROFILE
-	select HAVE_DEBUG_KMEMLEAK
-	select ARCH_HAS_SG_CHAIN
-	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE		if SMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select SPARSE_IRQ
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_VIRT_CPU_ACCOUNTING
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_SHOW_LEVEL
 	select IRQ_FORCED_THREADING
-	select HAVE_RCU_TABLE_FREE if SMP
-	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT if !PPC64
-	select HAVE_EBPF_JIT if PPC64
-	select HAVE_ARCH_JUMP_LABEL
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select ARCH_HAS_GCOV_PROFILE_ALL
-	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_CMOS_UPDATE
-	select GENERIC_TIME_VSYSCALL_OLD
-	select GENERIC_CLOCKEVENTS
-	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
-	select ARCH_USE_BUILTIN_BSWAP
-	select OLD_SIGSUSPEND
-	select OLD_SIGACTION if PPC32
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_IRQ_EXIT_ON_IRQ_STACK
-	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
-	select HAVE_ARCH_AUDITSYSCALL
-	select ARCH_SUPPORTS_ATOMIC_RMW
-	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
 	select NO_BOOTMEM
-	select HAVE_GENERIC_RCU_GUP
-	select HAVE_PERF_EVENTS_NMI if PPC64
-	select HAVE_NMI if PERF_EVENTS
-	select EDAC_SUPPORT
-	select EDAC_ATOMIC_SCRUB
-	select ARCH_HAS_DMA_SET_COHERENT_MASK
-	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select HAVE_ARCH_SECCOMP_FILTER
-	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
-	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select GENERIC_CPU_AUTOPROBE
-	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
-	select HAVE_ARCH_HARDENED_USERCOPY
-	select HAVE_KERNEL_GZIP
-	select HAVE_CONTEXT_TRACKING if PPC64
+	select OF
+	select OF_EARLY_FLATTREE
+	select OF_RESERVED_MEM
+	select OLD_SIGACTION			if PPC32
+	select OLD_SIGSUSPEND
+	select SPARSE_IRQ
+	select SYSCTL_EXCEPTION_TRACE
+	select VIRT_TO_BUS			if !PPC64
+	#
+	# Please keep this list sorted alphabetically.
+	#
 
 config GENERIC_CSUM
 	def_bool n
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 31286fa7873c..19b0d1a81959 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -72,8 +72,15 @@ GNUTARGET	:= powerpc
 MULTIPLEWORD	:= -mmultiple
 endif
 
-cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
+ifdef CONFIG_PPC64
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mcall-aixdesc)
+aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mabi=elfv2
+endif
+
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
 ifneq ($(cc-name),clang)
   cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
 endif
@@ -113,7 +120,9 @@ ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
 else
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 861e72109df2..f080abfc2f83 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -68,6 +68,7 @@ SECTIONS
   }
 
 #ifdef CONFIG_PPC64_BOOT_WRAPPER
+  . = ALIGN(256);
   .got :
   {
     __toc_start = .;
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index 528ff0e714e6..c03d0fb16665 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -16,9 +16,8 @@ CONFIG_DAVICOM_PHY=y
 CONFIG_DMADEVICES=y
 CONFIG_E1000E=y
 CONFIG_E1000=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_EDAC_MPC85XX=y
 CONFIG_EDAC=y
+CONFIG_EDAC_MPC85XX=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_LEGACY=y
 CONFIG_FB_FSL_DIU=y
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index c79283be5680..a917f7afb4f9 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -155,7 +155,6 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
 CONFIG_USB_STORAGE=y
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_MPC85XX=y
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_INTF_PROC is not set
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index dbd961de251e..72900b84d3e0 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -116,7 +116,6 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_CMOS=y
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 2d7fcbe047ac..aa564599e368 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -179,7 +179,6 @@ CONFIG_INFINIBAND_MTHCA=m
 CONFIG_INFINIBAND_IPOIB=m
 CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_CELL=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 5553c5ce4274..fe43ff47bd2f 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -142,7 +142,6 @@ CONFIG_USB_UHCI_HCD=y
 CONFIG_USB_SL811_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_PASEMI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 4f1288b04303..f2e03f032041 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -262,7 +262,6 @@ CONFIG_INFINIBAND_IPOIB_CM=y
 CONFIG_INFINIBAND_SRP=m
 CONFIG_INFINIBAND_ISER=m
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_PASEMI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 11a3473f9e2e..6340e6c53c54 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -173,7 +173,6 @@ CONFIG_INFINIBAND_MTHCA=m
 CONFIG_INFINIBAND_IPOIB=m
 CONFIG_INFINIBAND_ISER=m
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_FS_DAX=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 1d2d69dd6409..18d0d60dadbf 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -988,8 +988,7 @@ CONFIG_LEDS_TRIGGER_BACKLIGHT=m
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
 CONFIG_ACCESSIBILITY=y
 CONFIG_A11Y_BRAILLE_CONSOLE=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=m
+CONFIG_EDAC=m
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_RTC_DRV_DS1307=m
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 87f40454bad3..67eca3af9fc7 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -10,6 +10,8 @@ obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
 obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
 obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
+obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
 
 aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
 md5-ppc-y := md5-asm.o md5-glue.o
@@ -17,3 +19,4 @@ sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
 sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
 crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
+crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
new file mode 100644
index 000000000000..0153a9c6f4af
--- /dev/null
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -0,0 +1,137 @@
+/*
+ * CRC vpmsum tester
+ * Copyright 2017 Daniel Axtens, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+static unsigned long iterations = 10000;
+
+#define MAX_CRC_LENGTH 65535
+
+
+static int __init crc_test_init(void)
+{
+	u16 crc16 = 0, verify16 = 0;
+	u32 crc32 = 0, verify32 = 0;
+	__le32 verify32le = 0;
+	unsigned char *data;
+	unsigned long i;
+	int ret;
+
+	struct crypto_shash *crct10dif_tfm;
+	struct crypto_shash *crc32c_tfm;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
+
+	if (IS_ERR(crct10dif_tfm)) {
+		pr_err("Error allocating crc-t10dif\n");
+		goto free_buf;
+	}
+
+	crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0);
+
+	if (IS_ERR(crc32c_tfm)) {
+		pr_err("Error allocating crc32c\n");
+		goto free_16;
+	}
+
+	do {
+		SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm);
+		SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm);
+
+		crct10dif_shash->tfm = crct10dif_tfm;
+		ret = crypto_shash_init(crct10dif_shash);
+
+		if (ret) {
+			pr_err("Error initing crc-t10dif\n");
+			goto free_32;
+		}
+
+
+		crc32c_shash->tfm = crc32c_tfm;
+		ret = crypto_shash_init(crc32c_shash);
+
+		if (ret) {
+			pr_err("Error initing crc32c\n");
+			goto free_32;
+		}
+
+		pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
+		for (i=0; i<iterations; i++) {
+			size_t len, offset;
+
+			get_random_bytes(data, MAX_CRC_LENGTH);
+			get_random_bytes(&len, sizeof(len));
+			get_random_bytes(&offset, sizeof(offset));
+
+			len %= MAX_CRC_LENGTH;
+			offset &= 15;
+			if (len <= offset)
+				continue;
+			len -= offset;
+
+			crypto_shash_update(crct10dif_shash, data+offset, len);
+			crypto_shash_final(crct10dif_shash, (u8 *)(&crc16));
+			verify16 = crc_t10dif_generic(verify16, data+offset, len);
+
+
+			if (crc16 != verify16) {
+				pr_err("FAILURE in CRC16: got 0x%04x expected 0x%04x (len %lu)\n",
+				       crc16, verify16, len);
+				break;
+			}
+
+			crypto_shash_update(crc32c_shash, data+offset, len);
+			crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
+			verify32 = le32_to_cpu(verify32le);
+		        verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
+			if (crc32 != (u32)verify32le) {
+				pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
+				       crc32, verify32, len);
+				break;
+			}
+		}
+		pr_info("crc-vpmsum_test done, completed %lu iterations\n", i);
+	} while (0);
+
+free_32:
+	crypto_free_shash(crc32c_tfm);
+
+free_16:
+	crypto_free_shash(crct10dif_tfm);
+
+free_buf:
+	kfree(data);
+
+	return 0;
+}
+
+static void __exit crc_test_exit(void) {}
+
+module_init(crc_test_init);
+module_exit(crc_test_exit);
+module_param(iterations, long, 0400);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
new file mode 100644
index 000000000000..aadb59c96a27
--- /dev/null
+++ b/arch/powerpc/crypto/crc32-vpmsum_core.S
@@ -0,0 +1,755 @@
+/*
+ * Core of the accelerated CRC algorithm.
+ * In your file, define the constants and CRC_FUNCTION_NAME
+ * Then include this file.
+ *
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * We then use fixed point Barrett reduction to compute a mod n over GF(2)
+ * for n = CRC using POWER8 instructions. We use x = 32.
+ *
+ * http://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+*/
+
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+#define MAX_SIZE	32768
+
+	.text
+
+#if defined(__BIG_ENDIAN__) && defined(REFLECT)
+#define BYTESWAP_DATA
+#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT)
+#define BYTESWAP_DATA
+#else
+#undef BYTESWAP_DATA
+#endif
+
+#define off16		r25
+#define off32		r26
+#define off48		r27
+#define off64		r28
+#define off80		r29
+#define off96		r30
+#define off112		r31
+
+#define const1		v24
+#define const2		v25
+
+#define byteswap	v26
+#define	mask_32bit	v27
+#define	mask_64bit	v28
+#define zeroes		v29
+
+#ifdef BYTESWAP_DATA
+#define VPERM(A, B, C, D) vperm	A, B, C, D
+#else
+#define VPERM(A, B, C, D)
+#endif
+
+/* unsigned int CRC_FUNCTION_NAME(unsigned int crc, void *p, unsigned long len) */
+FUNC_START(CRC_FUNCTION_NAME)
+	std	r31,-8(r1)
+	std	r30,-16(r1)
+	std	r29,-24(r1)
+	std	r28,-32(r1)
+	std	r27,-40(r1)
+	std	r26,-48(r1)
+	std	r25,-56(r1)
+
+	li	off16,16
+	li	off32,32
+	li	off48,48
+	li	off64,64
+	li	off80,80
+	li	off96,96
+	li	off112,112
+	li	r0,0
+
+	/* Enough room for saving 10 non volatile VMX registers */
+	subi	r6,r1,56+10*16
+	subi	r7,r1,56+2*16
+
+	stvx	v20,0,r6
+	stvx	v21,off16,r6
+	stvx	v22,off32,r6
+	stvx	v23,off48,r6
+	stvx	v24,off64,r6
+	stvx	v25,off80,r6
+	stvx	v26,off96,r6
+	stvx	v27,off112,r6
+	stvx	v28,0,r7
+	stvx	v29,off16,r7
+
+	mr	r10,r3
+
+	vxor	zeroes,zeroes,zeroes
+	vspltisw v0,-1
+
+	vsldoi	mask_32bit,zeroes,v0,4
+	vsldoi	mask_64bit,zeroes,v0,8
+
+	/* Get the initial value into v8 */
+	vxor	v8,v8,v8
+	MTVRD(v8, R3)
+#ifdef REFLECT
+	vsldoi	v8,zeroes,v8,8	/* shift into bottom 32 bits */
+#else
+	vsldoi	v8,v8,zeroes,4	/* shift into top 32 bits */
+#endif
+
+#ifdef BYTESWAP_DATA
+	addis	r3,r2,.byteswap_constant@toc@ha
+	addi	r3,r3,.byteswap_constant@toc@l
+
+	lvx	byteswap,0,r3
+	addi	r3,r3,16
+#endif
+
+	cmpdi	r5,256
+	blt	.Lshort
+
+	rldicr	r6,r5,0,56
+
+	/* Checksum in blocks of MAX_SIZE */
+1:	lis	r7,MAX_SIZE@h
+	ori	r7,r7,MAX_SIZE@l
+	mr	r9,r7
+	cmpd	r6,r7
+	bgt	2f
+	mr	r7,r6
+2:	subf	r6,r7,r6
+
+	/* our main loop does 128 bytes at a time */
+	srdi	r7,r7,7
+
+	/*
+	 * Work out the offset into the constants table to start at. Each
+	 * constant is 16 bytes, and it is used against 128 bytes of input
+	 * data - 128 / 16 = 8
+	 */
+	sldi	r8,r7,4
+	srdi	r9,r9,3
+	subf	r8,r8,r9
+
+	/* We reduce our final 128 bytes in a separate step */
+	addi	r7,r7,-1
+	mtctr	r7
+
+	addis	r3,r2,.constants@toc@ha
+	addi	r3,r3,.constants@toc@l
+
+	/* Find the start of our constants */
+	add	r3,r3,r8
+
+	/* zero v0-v7 which will contain our checksums */
+	vxor	v0,v0,v0
+	vxor	v1,v1,v1
+	vxor	v2,v2,v2
+	vxor	v3,v3,v3
+	vxor	v4,v4,v4
+	vxor	v5,v5,v5
+	vxor	v6,v6,v6
+	vxor	v7,v7,v7
+
+	lvx	const1,0,r3
+
+	/*
+	 * If we are looping back to consume more data we use the values
+	 * already in v16-v23.
+	 */
+	cmpdi	r0,1
+	beq	2f
+
+	/* First warm up pass */
+	lvx	v16,0,r4
+	lvx	v17,off16,r4
+	VPERM(v16,v16,v16,byteswap)
+	VPERM(v17,v17,v17,byteswap)
+	lvx	v18,off32,r4
+	lvx	v19,off48,r4
+	VPERM(v18,v18,v18,byteswap)
+	VPERM(v19,v19,v19,byteswap)
+	lvx	v20,off64,r4
+	lvx	v21,off80,r4
+	VPERM(v20,v20,v20,byteswap)
+	VPERM(v21,v21,v21,byteswap)
+	lvx	v22,off96,r4
+	lvx	v23,off112,r4
+	VPERM(v22,v22,v22,byteswap)
+	VPERM(v23,v23,v23,byteswap)
+	addi	r4,r4,8*16
+
+	/* xor in initial value */
+	vxor	v16,v16,v8
+
+2:	bdz	.Lfirst_warm_up_done
+
+	addi	r3,r3,16
+	lvx	const2,0,r3
+
+	/* Second warm up pass */
+	VPMSUMD(v8,v16,const1)
+	lvx	v16,0,r4
+	VPERM(v16,v16,v16,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v9,v17,const1)
+	lvx	v17,off16,r4
+	VPERM(v17,v17,v17,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v10,v18,const1)
+	lvx	v18,off32,r4
+	VPERM(v18,v18,v18,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v11,v19,const1)
+	lvx	v19,off48,r4
+	VPERM(v19,v19,v19,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v12,v20,const1)
+	lvx	v20,off64,r4
+	VPERM(v20,v20,v20,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v13,v21,const1)
+	lvx	v21,off80,r4
+	VPERM(v21,v21,v21,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v14,v22,const1)
+	lvx	v22,off96,r4
+	VPERM(v22,v22,v22,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v15,v23,const1)
+	lvx	v23,off112,r4
+	VPERM(v23,v23,v23,byteswap)
+
+	addi	r4,r4,8*16
+
+	bdz	.Lfirst_cool_down
+
+	/*
+	 * main loop. We modulo schedule it such that it takes three iterations
+	 * to complete - first iteration load, second iteration vpmsum, third
+	 * iteration xor.
+	 */
+	.balign	16
+4:	lvx	const1,0,r3
+	addi	r3,r3,16
+	ori	r2,r2,0
+
+	vxor	v0,v0,v8
+	VPMSUMD(v8,v16,const2)
+	lvx	v16,0,r4
+	VPERM(v16,v16,v16,byteswap)
+	ori	r2,r2,0
+
+	vxor	v1,v1,v9
+	VPMSUMD(v9,v17,const2)
+	lvx	v17,off16,r4
+	VPERM(v17,v17,v17,byteswap)
+	ori	r2,r2,0
+
+	vxor	v2,v2,v10
+	VPMSUMD(v10,v18,const2)
+	lvx	v18,off32,r4
+	VPERM(v18,v18,v18,byteswap)
+	ori	r2,r2,0
+
+	vxor	v3,v3,v11
+	VPMSUMD(v11,v19,const2)
+	lvx	v19,off48,r4
+	VPERM(v19,v19,v19,byteswap)
+	lvx	const2,0,r3
+	ori	r2,r2,0
+
+	vxor	v4,v4,v12
+	VPMSUMD(v12,v20,const1)
+	lvx	v20,off64,r4
+	VPERM(v20,v20,v20,byteswap)
+	ori	r2,r2,0
+
+	vxor	v5,v5,v13
+	VPMSUMD(v13,v21,const1)
+	lvx	v21,off80,r4
+	VPERM(v21,v21,v21,byteswap)
+	ori	r2,r2,0
+
+	vxor	v6,v6,v14
+	VPMSUMD(v14,v22,const1)
+	lvx	v22,off96,r4
+	VPERM(v22,v22,v22,byteswap)
+	ori	r2,r2,0
+
+	vxor	v7,v7,v15
+	VPMSUMD(v15,v23,const1)
+	lvx	v23,off112,r4
+	VPERM(v23,v23,v23,byteswap)
+
+	addi	r4,r4,8*16
+
+	bdnz	4b
+
+.Lfirst_cool_down:
+	/* First cool down pass */
+	lvx	const1,0,r3
+	addi	r3,r3,16
+
+	vxor	v0,v0,v8
+	VPMSUMD(v8,v16,const1)
+	ori	r2,r2,0
+
+	vxor	v1,v1,v9
+	VPMSUMD(v9,v17,const1)
+	ori	r2,r2,0
+
+	vxor	v2,v2,v10
+	VPMSUMD(v10,v18,const1)
+	ori	r2,r2,0
+
+	vxor	v3,v3,v11
+	VPMSUMD(v11,v19,const1)
+	ori	r2,r2,0
+
+	vxor	v4,v4,v12
+	VPMSUMD(v12,v20,const1)
+	ori	r2,r2,0
+
+	vxor	v5,v5,v13
+	VPMSUMD(v13,v21,const1)
+	ori	r2,r2,0
+
+	vxor	v6,v6,v14
+	VPMSUMD(v14,v22,const1)
+	ori	r2,r2,0
+
+	vxor	v7,v7,v15
+	VPMSUMD(v15,v23,const1)
+	ori	r2,r2,0
+
+.Lsecond_cool_down:
+	/* Second cool down pass */
+	vxor	v0,v0,v8
+	vxor	v1,v1,v9
+	vxor	v2,v2,v10
+	vxor	v3,v3,v11
+	vxor	v4,v4,v12
+	vxor	v5,v5,v13
+	vxor	v6,v6,v14
+	vxor	v7,v7,v15
+
+#ifdef REFLECT
+	/*
+	 * vpmsumd produces a 96 bit result in the least significant bits
+	 * of the register. Since we are bit reflected we have to shift it
+	 * left 32 bits so it occupies the least significant bits in the
+	 * bit reflected domain.
+	 */
+	vsldoi	v0,v0,zeroes,4
+	vsldoi	v1,v1,zeroes,4
+	vsldoi	v2,v2,zeroes,4
+	vsldoi	v3,v3,zeroes,4
+	vsldoi	v4,v4,zeroes,4
+	vsldoi	v5,v5,zeroes,4
+	vsldoi	v6,v6,zeroes,4
+	vsldoi	v7,v7,zeroes,4
+#endif
+
+	/* xor with last 1024 bits */
+	lvx	v8,0,r4
+	lvx	v9,off16,r4
+	VPERM(v8,v8,v8,byteswap)
+	VPERM(v9,v9,v9,byteswap)
+	lvx	v10,off32,r4
+	lvx	v11,off48,r4
+	VPERM(v10,v10,v10,byteswap)
+	VPERM(v11,v11,v11,byteswap)
+	lvx	v12,off64,r4
+	lvx	v13,off80,r4
+	VPERM(v12,v12,v12,byteswap)
+	VPERM(v13,v13,v13,byteswap)
+	lvx	v14,off96,r4
+	lvx	v15,off112,r4
+	VPERM(v14,v14,v14,byteswap)
+	VPERM(v15,v15,v15,byteswap)
+
+	addi	r4,r4,8*16
+
+	vxor	v16,v0,v8
+	vxor	v17,v1,v9
+	vxor	v18,v2,v10
+	vxor	v19,v3,v11
+	vxor	v20,v4,v12
+	vxor	v21,v5,v13
+	vxor	v22,v6,v14
+	vxor	v23,v7,v15
+
+	li	r0,1
+	cmpdi	r6,0
+	addi	r6,r6,128
+	bne	1b
+
+	/* Work out how many bytes we have left */
+	andi.	r5,r5,127
+
+	/* Calculate where in the constant table we need to start */
+	subfic	r6,r5,128
+	add	r3,r3,r6
+
+	/* How many 16 byte chunks are in the tail */
+	srdi	r7,r5,4
+	mtctr	r7
+
+	/*
+	 * Reduce the previously calculated 1024 bits to 64 bits, shifting
+	 * 32 bits to include the trailing 32 bits of zeros
+	 */
+	lvx	v0,0,r3
+	lvx	v1,off16,r3
+	lvx	v2,off32,r3
+	lvx	v3,off48,r3
+	lvx	v4,off64,r3
+	lvx	v5,off80,r3
+	lvx	v6,off96,r3
+	lvx	v7,off112,r3
+	addi	r3,r3,8*16
+
+	VPMSUMW(v0,v16,v0)
+	VPMSUMW(v1,v17,v1)
+	VPMSUMW(v2,v18,v2)
+	VPMSUMW(v3,v19,v3)
+	VPMSUMW(v4,v20,v4)
+	VPMSUMW(v5,v21,v5)
+	VPMSUMW(v6,v22,v6)
+	VPMSUMW(v7,v23,v7)
+
+	/* Now reduce the tail (0 - 112 bytes) */
+	cmpdi	r7,0
+	beq	1f
+
+	lvx	v16,0,r4
+	lvx	v17,0,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off32,r4
+	lvx	v17,off32,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off64,r4
+	lvx	v17,off64,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off96,r4
+	lvx	v17,off96,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+
+	/* Now xor all the parallel chunks together */
+1:	vxor	v0,v0,v1
+	vxor	v2,v2,v3
+	vxor	v4,v4,v5
+	vxor	v6,v6,v7
+
+	vxor	v0,v0,v2
+	vxor	v4,v4,v6
+
+	vxor	v0,v0,v4
+
+.Lbarrett_reduction:
+	/* Barrett constants */
+	addis	r3,r2,.barrett_constants@toc@ha
+	addi	r3,r3,.barrett_constants@toc@l
+
+	lvx	const1,0,r3
+	lvx	const2,off16,r3
+
+	vsldoi	v1,v0,v0,8
+	vxor	v0,v0,v1		/* xor two 64 bit results together */
+
+#ifdef REFLECT
+	/* shift left one bit */
+	vspltisb v1,1
+	vsl	v0,v0,v1
+#endif
+
+	vand	v0,v0,mask_64bit
+#ifndef REFLECT
+	/*
+	 * Now for the Barrett reduction algorithm. The idea is to calculate q,
+	 * the multiple of our polynomial that we need to subtract. By
+	 * doing the computation 2x bits higher (ie 64 bits) and shifting the
+	 * result back down 2x bits, we round down to the nearest multiple.
+	 */
+	VPMSUMD(v1,v0,const1)	/* ma */
+	vsldoi	v1,zeroes,v1,8	/* q = floor(ma/(2^64)) */
+	VPMSUMD(v1,v1,const2)	/* qn */
+	vxor	v0,v0,v1	/* a - qn, subtraction is xor in GF(2) */
+
+	/*
+	 * Get the result into r3. We need to shift it left 8 bytes:
+	 * V0 [ 0 1 2 X ]
+	 * V0 [ 0 X 2 3 ]
+	 */
+	vsldoi	v0,v0,zeroes,8	/* shift result into top 64 bits */
+#else
+	/*
+	 * The reflected version of Barrett reduction. Instead of bit
+	 * reflecting our data (which is expensive to do), we bit reflect our
+	 * constants and our algorithm, which means the intermediate data in
+	 * our vector registers goes from 0-63 instead of 63-0. We can reflect
+	 * the algorithm because we don't carry in mod 2 arithmetic.
+	 */
+	vand	v1,v0,mask_32bit	/* bottom 32 bits of a */
+	VPMSUMD(v1,v1,const1)		/* ma */
+	vand	v1,v1,mask_32bit	/* bottom 32bits of ma */
+	VPMSUMD(v1,v1,const2)		/* qn */
+	vxor	v0,v0,v1		/* a - qn, subtraction is xor in GF(2) */
+
+	/*
+	 * Since we are bit reflected, the result (ie the low 32 bits) is in
+	 * the high 32 bits. We just need to shift it left 4 bytes
+	 * V0 [ 0 1 X 3 ]
+	 * V0 [ 0 X 2 3 ]
+	 */
+	vsldoi	v0,v0,zeroes,4		/* shift result into top 64 bits of */
+#endif
+
+	/* Get it into r3 */
+	MFVRD(R3, v0)
+
+.Lout:
+	subi	r6,r1,56+10*16
+	subi	r7,r1,56+2*16
+
+	lvx	v20,0,r6
+	lvx	v21,off16,r6
+	lvx	v22,off32,r6
+	lvx	v23,off48,r6
+	lvx	v24,off64,r6
+	lvx	v25,off80,r6
+	lvx	v26,off96,r6
+	lvx	v27,off112,r6
+	lvx	v28,0,r7
+	lvx	v29,off16,r7
+
+	ld	r31,-8(r1)
+	ld	r30,-16(r1)
+	ld	r29,-24(r1)
+	ld	r28,-32(r1)
+	ld	r27,-40(r1)
+	ld	r26,-48(r1)
+	ld	r25,-56(r1)
+
+	blr
+
+.Lfirst_warm_up_done:
+	lvx	const1,0,r3
+	addi	r3,r3,16
+
+	VPMSUMD(v8,v16,const1)
+	VPMSUMD(v9,v17,const1)
+	VPMSUMD(v10,v18,const1)
+	VPMSUMD(v11,v19,const1)
+	VPMSUMD(v12,v20,const1)
+	VPMSUMD(v13,v21,const1)
+	VPMSUMD(v14,v22,const1)
+	VPMSUMD(v15,v23,const1)
+
+	b	.Lsecond_cool_down
+
+.Lshort:
+	cmpdi	r5,0
+	beq	.Lzero
+
+	addis	r3,r2,.short_constants@toc@ha
+	addi	r3,r3,.short_constants@toc@l
+
+	/* Calculate where in the constant table we need to start */
+	subfic	r6,r5,256
+	add	r3,r3,r6
+
+	/* How many 16 byte chunks? */
+	srdi	r7,r5,4
+	mtctr	r7
+
+	vxor	v19,v19,v19
+	vxor	v20,v20,v20
+
+	lvx	v0,0,r4
+	lvx	v16,0,r3
+	VPERM(v0,v0,v16,byteswap)
+	vxor	v0,v0,v8	/* xor in initial value */
+	VPMSUMW(v0,v0,v16)
+	bdz	.Lv0
+
+	lvx	v1,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v1,v1,v17,byteswap)
+	VPMSUMW(v1,v1,v17)
+	bdz	.Lv1
+
+	lvx	v2,off32,r4
+	lvx	v16,off32,r3
+	VPERM(v2,v2,v16,byteswap)
+	VPMSUMW(v2,v2,v16)
+	bdz	.Lv2
+
+	lvx	v3,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v3,v3,v17,byteswap)
+	VPMSUMW(v3,v3,v17)
+	bdz	.Lv3
+
+	lvx	v4,off64,r4
+	lvx	v16,off64,r3
+	VPERM(v4,v4,v16,byteswap)
+	VPMSUMW(v4,v4,v16)
+	bdz	.Lv4
+
+	lvx	v5,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v5,v5,v17,byteswap)
+	VPMSUMW(v5,v5,v17)
+	bdz	.Lv5
+
+	lvx	v6,off96,r4
+	lvx	v16,off96,r3
+	VPERM(v6,v6,v16,byteswap)
+	VPMSUMW(v6,v6,v16)
+	bdz	.Lv6
+
+	lvx	v7,off112,r4
+	lvx	v17,off112,r3
+	VPERM(v7,v7,v17,byteswap)
+	VPMSUMW(v7,v7,v17)
+	bdz	.Lv7
+
+	addi	r3,r3,128
+	addi	r4,r4,128
+
+	lvx	v8,0,r4
+	lvx	v16,0,r3
+	VPERM(v8,v8,v16,byteswap)
+	VPMSUMW(v8,v8,v16)
+	bdz	.Lv8
+
+	lvx	v9,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v9,v9,v17,byteswap)
+	VPMSUMW(v9,v9,v17)
+	bdz	.Lv9
+
+	lvx	v10,off32,r4
+	lvx	v16,off32,r3
+	VPERM(v10,v10,v16,byteswap)
+	VPMSUMW(v10,v10,v16)
+	bdz	.Lv10
+
+	lvx	v11,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v11,v11,v17,byteswap)
+	VPMSUMW(v11,v11,v17)
+	bdz	.Lv11
+
+	lvx	v12,off64,r4
+	lvx	v16,off64,r3
+	VPERM(v12,v12,v16,byteswap)
+	VPMSUMW(v12,v12,v16)
+	bdz	.Lv12
+
+	lvx	v13,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v13,v13,v17,byteswap)
+	VPMSUMW(v13,v13,v17)
+	bdz	.Lv13
+
+	lvx	v14,off96,r4
+	lvx	v16,off96,r3
+	VPERM(v14,v14,v16,byteswap)
+	VPMSUMW(v14,v14,v16)
+	bdz	.Lv14
+
+	lvx	v15,off112,r4
+	lvx	v17,off112,r3
+	VPERM(v15,v15,v17,byteswap)
+	VPMSUMW(v15,v15,v17)
+
+.Lv15:	vxor	v19,v19,v15
+.Lv14:	vxor	v20,v20,v14
+.Lv13:	vxor	v19,v19,v13
+.Lv12:	vxor	v20,v20,v12
+.Lv11:	vxor	v19,v19,v11
+.Lv10:	vxor	v20,v20,v10
+.Lv9:	vxor	v19,v19,v9
+.Lv8:	vxor	v20,v20,v8
+.Lv7:	vxor	v19,v19,v7
+.Lv6:	vxor	v20,v20,v6
+.Lv5:	vxor	v19,v19,v5
+.Lv4:	vxor	v20,v20,v4
+.Lv3:	vxor	v19,v19,v3
+.Lv2:	vxor	v20,v20,v2
+.Lv1:	vxor	v19,v19,v1
+.Lv0:	vxor	v20,v20,v0
+
+	vxor	v0,v19,v20
+
+	b	.Lbarrett_reduction
+
+.Lzero:
+	mr	r3,r10
+	b	.Lout
+
+FUNC_END(CRC_FUNCTION_NAME)
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
index dc640b212299..d2bea48051a0 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_asm.S
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -1,20 +1,5 @@
 /*
- * Calculate the checksum of data that is 16 byte aligned and a multiple of
- * 16 bytes.
- *
- * The first step is to reduce it to 1024 bits. We do this in 8 parallel
- * chunks in order to mask the latency of the vpmsum instructions. If we
- * have more than 32 kB of data to checksum we repeat this step multiple
- * times, passing in the previous 1024 bits.
- *
- * The next step is to reduce the 1024 bits to 64 bits. This step adds
- * 32 bits of 0s to the end - this matches what a CRC does. We just
- * calculate constants that land the data in this 32 bits.
- *
- * We then use fixed point Barrett reduction to compute a mod n over GF(2)
- * for n = CRC using POWER8 instructions. We use x = 32.
- *
- * http://en.wikipedia.org/wiki/Barrett_reduction
+ * Calculate a crc32c with vpmsum acceleration
  *
  * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
  *
@@ -23,9 +8,6 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
-#include <asm/ppc_asm.h>
-#include <asm/ppc-opcode.h>
-
 	.section	.rodata
 .balign 16
 
@@ -33,7 +15,6 @@
 	/* byte reverse permute constant */
 	.octa 0x0F0E0D0C0B0A09080706050403020100
 
-#define MAX_SIZE	32768
 .constants:
 
 	/* Reduce 262144 kbits to 1024 bits */
@@ -860,694 +841,6 @@
 	/* 33 bit reflected Barrett constant n */
 	.octa 0x00000000000000000000000105ec76f1
 
-	.text
-
-#if defined(__BIG_ENDIAN__)
-#define BYTESWAP_DATA
-#else
-#undef BYTESWAP_DATA
-#endif
-
-#define off16		r25
-#define off32		r26
-#define off48		r27
-#define off64		r28
-#define off80		r29
-#define off96		r30
-#define off112		r31
-
-#define const1		v24
-#define const2		v25
-
-#define byteswap	v26
-#define	mask_32bit	v27
-#define	mask_64bit	v28
-#define zeroes		v29
-
-#ifdef BYTESWAP_DATA
-#define VPERM(A, B, C, D) vperm	A, B, C, D
-#else
-#define VPERM(A, B, C, D)
-#endif
-
-/* unsigned int __crc32c_vpmsum(unsigned int crc, void *p, unsigned long len) */
-FUNC_START(__crc32c_vpmsum)
-	std	r31,-8(r1)
-	std	r30,-16(r1)
-	std	r29,-24(r1)
-	std	r28,-32(r1)
-	std	r27,-40(r1)
-	std	r26,-48(r1)
-	std	r25,-56(r1)
-
-	li	off16,16
-	li	off32,32
-	li	off48,48
-	li	off64,64
-	li	off80,80
-	li	off96,96
-	li	off112,112
-	li	r0,0
-
-	/* Enough room for saving 10 non volatile VMX registers */
-	subi	r6,r1,56+10*16
-	subi	r7,r1,56+2*16
-
-	stvx	v20,0,r6
-	stvx	v21,off16,r6
-	stvx	v22,off32,r6
-	stvx	v23,off48,r6
-	stvx	v24,off64,r6
-	stvx	v25,off80,r6
-	stvx	v26,off96,r6
-	stvx	v27,off112,r6
-	stvx	v28,0,r7
-	stvx	v29,off16,r7
-
-	mr	r10,r3
-
-	vxor	zeroes,zeroes,zeroes
-	vspltisw v0,-1
-
-	vsldoi	mask_32bit,zeroes,v0,4
-	vsldoi	mask_64bit,zeroes,v0,8
-
-	/* Get the initial value into v8 */
-	vxor	v8,v8,v8
-	MTVRD(v8, R3)
-	vsldoi	v8,zeroes,v8,8	/* shift into bottom 32 bits */
-
-#ifdef BYTESWAP_DATA
-	addis	r3,r2,.byteswap_constant@toc@ha
-	addi	r3,r3,.byteswap_constant@toc@l
-
-	lvx	byteswap,0,r3
-	addi	r3,r3,16
-#endif
-
-	cmpdi	r5,256
-	blt	.Lshort
-
-	rldicr	r6,r5,0,56
-
-	/* Checksum in blocks of MAX_SIZE */
-1:	lis	r7,MAX_SIZE@h
-	ori	r7,r7,MAX_SIZE@l
-	mr	r9,r7
-	cmpd	r6,r7
-	bgt	2f
-	mr	r7,r6
-2:	subf	r6,r7,r6
-
-	/* our main loop does 128 bytes at a time */
-	srdi	r7,r7,7
-
-	/*
-	 * Work out the offset into the constants table to start at. Each
-	 * constant is 16 bytes, and it is used against 128 bytes of input
-	 * data - 128 / 16 = 8
-	 */
-	sldi	r8,r7,4
-	srdi	r9,r9,3
-	subf	r8,r8,r9
-
-	/* We reduce our final 128 bytes in a separate step */
-	addi	r7,r7,-1
-	mtctr	r7
-
-	addis	r3,r2,.constants@toc@ha
-	addi	r3,r3,.constants@toc@l
-
-	/* Find the start of our constants */
-	add	r3,r3,r8
-
-	/* zero v0-v7 which will contain our checksums */
-	vxor	v0,v0,v0
-	vxor	v1,v1,v1
-	vxor	v2,v2,v2
-	vxor	v3,v3,v3
-	vxor	v4,v4,v4
-	vxor	v5,v5,v5
-	vxor	v6,v6,v6
-	vxor	v7,v7,v7
-
-	lvx	const1,0,r3
-
-	/*
-	 * If we are looping back to consume more data we use the values
-	 * already in v16-v23.
-	 */
-	cmpdi	r0,1
-	beq	2f
-
-	/* First warm up pass */
-	lvx	v16,0,r4
-	lvx	v17,off16,r4
-	VPERM(v16,v16,v16,byteswap)
-	VPERM(v17,v17,v17,byteswap)
-	lvx	v18,off32,r4
-	lvx	v19,off48,r4
-	VPERM(v18,v18,v18,byteswap)
-	VPERM(v19,v19,v19,byteswap)
-	lvx	v20,off64,r4
-	lvx	v21,off80,r4
-	VPERM(v20,v20,v20,byteswap)
-	VPERM(v21,v21,v21,byteswap)
-	lvx	v22,off96,r4
-	lvx	v23,off112,r4
-	VPERM(v22,v22,v22,byteswap)
-	VPERM(v23,v23,v23,byteswap)
-	addi	r4,r4,8*16
-
-	/* xor in initial value */
-	vxor	v16,v16,v8
-
-2:	bdz	.Lfirst_warm_up_done
-
-	addi	r3,r3,16
-	lvx	const2,0,r3
-
-	/* Second warm up pass */
-	VPMSUMD(v8,v16,const1)
-	lvx	v16,0,r4
-	VPERM(v16,v16,v16,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v9,v17,const1)
-	lvx	v17,off16,r4
-	VPERM(v17,v17,v17,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v10,v18,const1)
-	lvx	v18,off32,r4
-	VPERM(v18,v18,v18,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v11,v19,const1)
-	lvx	v19,off48,r4
-	VPERM(v19,v19,v19,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v12,v20,const1)
-	lvx	v20,off64,r4
-	VPERM(v20,v20,v20,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v13,v21,const1)
-	lvx	v21,off80,r4
-	VPERM(v21,v21,v21,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v14,v22,const1)
-	lvx	v22,off96,r4
-	VPERM(v22,v22,v22,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v15,v23,const1)
-	lvx	v23,off112,r4
-	VPERM(v23,v23,v23,byteswap)
-
-	addi	r4,r4,8*16
-
-	bdz	.Lfirst_cool_down
-
-	/*
-	 * main loop. We modulo schedule it such that it takes three iterations
-	 * to complete - first iteration load, second iteration vpmsum, third
-	 * iteration xor.
-	 */
-	.balign	16
-4:	lvx	const1,0,r3
-	addi	r3,r3,16
-	ori	r2,r2,0
-
-	vxor	v0,v0,v8
-	VPMSUMD(v8,v16,const2)
-	lvx	v16,0,r4
-	VPERM(v16,v16,v16,byteswap)
-	ori	r2,r2,0
-
-	vxor	v1,v1,v9
-	VPMSUMD(v9,v17,const2)
-	lvx	v17,off16,r4
-	VPERM(v17,v17,v17,byteswap)
-	ori	r2,r2,0
-
-	vxor	v2,v2,v10
-	VPMSUMD(v10,v18,const2)
-	lvx	v18,off32,r4
-	VPERM(v18,v18,v18,byteswap)
-	ori	r2,r2,0
-
-	vxor	v3,v3,v11
-	VPMSUMD(v11,v19,const2)
-	lvx	v19,off48,r4
-	VPERM(v19,v19,v19,byteswap)
-	lvx	const2,0,r3
-	ori	r2,r2,0
-
-	vxor	v4,v4,v12
-	VPMSUMD(v12,v20,const1)
-	lvx	v20,off64,r4
-	VPERM(v20,v20,v20,byteswap)
-	ori	r2,r2,0
-
-	vxor	v5,v5,v13
-	VPMSUMD(v13,v21,const1)
-	lvx	v21,off80,r4
-	VPERM(v21,v21,v21,byteswap)
-	ori	r2,r2,0
-
-	vxor	v6,v6,v14
-	VPMSUMD(v14,v22,const1)
-	lvx	v22,off96,r4
-	VPERM(v22,v22,v22,byteswap)
-	ori	r2,r2,0
-
-	vxor	v7,v7,v15
-	VPMSUMD(v15,v23,const1)
-	lvx	v23,off112,r4
-	VPERM(v23,v23,v23,byteswap)
-
-	addi	r4,r4,8*16
-
-	bdnz	4b
-
-.Lfirst_cool_down:
-	/* First cool down pass */
-	lvx	const1,0,r3
-	addi	r3,r3,16
-
-	vxor	v0,v0,v8
-	VPMSUMD(v8,v16,const1)
-	ori	r2,r2,0
-
-	vxor	v1,v1,v9
-	VPMSUMD(v9,v17,const1)
-	ori	r2,r2,0
-
-	vxor	v2,v2,v10
-	VPMSUMD(v10,v18,const1)
-	ori	r2,r2,0
-
-	vxor	v3,v3,v11
-	VPMSUMD(v11,v19,const1)
-	ori	r2,r2,0
-
-	vxor	v4,v4,v12
-	VPMSUMD(v12,v20,const1)
-	ori	r2,r2,0
-
-	vxor	v5,v5,v13
-	VPMSUMD(v13,v21,const1)
-	ori	r2,r2,0
-
-	vxor	v6,v6,v14
-	VPMSUMD(v14,v22,const1)
-	ori	r2,r2,0
-
-	vxor	v7,v7,v15
-	VPMSUMD(v15,v23,const1)
-	ori	r2,r2,0
-
-.Lsecond_cool_down:
-	/* Second cool down pass */
-	vxor	v0,v0,v8
-	vxor	v1,v1,v9
-	vxor	v2,v2,v10
-	vxor	v3,v3,v11
-	vxor	v4,v4,v12
-	vxor	v5,v5,v13
-	vxor	v6,v6,v14
-	vxor	v7,v7,v15
-
-	/*
-	 * vpmsumd produces a 96 bit result in the least significant bits
-	 * of the register. Since we are bit reflected we have to shift it
-	 * left 32 bits so it occupies the least significant bits in the
-	 * bit reflected domain.
-	 */
-	vsldoi	v0,v0,zeroes,4
-	vsldoi	v1,v1,zeroes,4
-	vsldoi	v2,v2,zeroes,4
-	vsldoi	v3,v3,zeroes,4
-	vsldoi	v4,v4,zeroes,4
-	vsldoi	v5,v5,zeroes,4
-	vsldoi	v6,v6,zeroes,4
-	vsldoi	v7,v7,zeroes,4
-
-	/* xor with last 1024 bits */
-	lvx	v8,0,r4
-	lvx	v9,off16,r4
-	VPERM(v8,v8,v8,byteswap)
-	VPERM(v9,v9,v9,byteswap)
-	lvx	v10,off32,r4
-	lvx	v11,off48,r4
-	VPERM(v10,v10,v10,byteswap)
-	VPERM(v11,v11,v11,byteswap)
-	lvx	v12,off64,r4
-	lvx	v13,off80,r4
-	VPERM(v12,v12,v12,byteswap)
-	VPERM(v13,v13,v13,byteswap)
-	lvx	v14,off96,r4
-	lvx	v15,off112,r4
-	VPERM(v14,v14,v14,byteswap)
-	VPERM(v15,v15,v15,byteswap)
-
-	addi	r4,r4,8*16
-
-	vxor	v16,v0,v8
-	vxor	v17,v1,v9
-	vxor	v18,v2,v10
-	vxor	v19,v3,v11
-	vxor	v20,v4,v12
-	vxor	v21,v5,v13
-	vxor	v22,v6,v14
-	vxor	v23,v7,v15
-
-	li	r0,1
-	cmpdi	r6,0
-	addi	r6,r6,128
-	bne	1b
-
-	/* Work out how many bytes we have left */
-	andi.	r5,r5,127
-
-	/* Calculate where in the constant table we need to start */
-	subfic	r6,r5,128
-	add	r3,r3,r6
-
-	/* How many 16 byte chunks are in the tail */
-	srdi	r7,r5,4
-	mtctr	r7
-
-	/*
-	 * Reduce the previously calculated 1024 bits to 64 bits, shifting
-	 * 32 bits to include the trailing 32 bits of zeros
-	 */
-	lvx	v0,0,r3
-	lvx	v1,off16,r3
-	lvx	v2,off32,r3
-	lvx	v3,off48,r3
-	lvx	v4,off64,r3
-	lvx	v5,off80,r3
-	lvx	v6,off96,r3
-	lvx	v7,off112,r3
-	addi	r3,r3,8*16
-
-	VPMSUMW(v0,v16,v0)
-	VPMSUMW(v1,v17,v1)
-	VPMSUMW(v2,v18,v2)
-	VPMSUMW(v3,v19,v3)
-	VPMSUMW(v4,v20,v4)
-	VPMSUMW(v5,v21,v5)
-	VPMSUMW(v6,v22,v6)
-	VPMSUMW(v7,v23,v7)
-
-	/* Now reduce the tail (0 - 112 bytes) */
-	cmpdi	r7,0
-	beq	1f
-
-	lvx	v16,0,r4
-	lvx	v17,0,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off16,r4
-	lvx	v17,off16,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off32,r4
-	lvx	v17,off32,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off48,r4
-	lvx	v17,off48,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off64,r4
-	lvx	v17,off64,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off80,r4
-	lvx	v17,off80,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off96,r4
-	lvx	v17,off96,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-
-	/* Now xor all the parallel chunks together */
-1:	vxor	v0,v0,v1
-	vxor	v2,v2,v3
-	vxor	v4,v4,v5
-	vxor	v6,v6,v7
-
-	vxor	v0,v0,v2
-	vxor	v4,v4,v6
-
-	vxor	v0,v0,v4
-
-.Lbarrett_reduction:
-	/* Barrett constants */
-	addis	r3,r2,.barrett_constants@toc@ha
-	addi	r3,r3,.barrett_constants@toc@l
-
-	lvx	const1,0,r3
-	lvx	const2,off16,r3
-
-	vsldoi	v1,v0,v0,8
-	vxor	v0,v0,v1		/* xor two 64 bit results together */
-
-	/* shift left one bit */
-	vspltisb v1,1
-	vsl	v0,v0,v1
-
-	vand	v0,v0,mask_64bit
-
-	/*
-	 * The reflected version of Barrett reduction. Instead of bit
-	 * reflecting our data (which is expensive to do), we bit reflect our
-	 * constants and our algorithm, which means the intermediate data in
-	 * our vector registers goes from 0-63 instead of 63-0. We can reflect
-	 * the algorithm because we don't carry in mod 2 arithmetic.
-	 */
-	vand	v1,v0,mask_32bit	/* bottom 32 bits of a */
-	VPMSUMD(v1,v1,const1)		/* ma */
-	vand	v1,v1,mask_32bit	/* bottom 32bits of ma */
-	VPMSUMD(v1,v1,const2)		/* qn */
-	vxor	v0,v0,v1		/* a - qn, subtraction is xor in GF(2) */
-
-	/*
-	 * Since we are bit reflected, the result (ie the low 32 bits) is in
-	 * the high 32 bits. We just need to shift it left 4 bytes
-	 * V0 [ 0 1 X 3 ]
-	 * V0 [ 0 X 2 3 ]
-	 */
-	vsldoi	v0,v0,zeroes,4		/* shift result into top 64 bits of */
-
-	/* Get it into r3 */
-	MFVRD(R3, v0)
-
-.Lout:
-	subi	r6,r1,56+10*16
-	subi	r7,r1,56+2*16
-
-	lvx	v20,0,r6
-	lvx	v21,off16,r6
-	lvx	v22,off32,r6
-	lvx	v23,off48,r6
-	lvx	v24,off64,r6
-	lvx	v25,off80,r6
-	lvx	v26,off96,r6
-	lvx	v27,off112,r6
-	lvx	v28,0,r7
-	lvx	v29,off16,r7
-
-	ld	r31,-8(r1)
-	ld	r30,-16(r1)
-	ld	r29,-24(r1)
-	ld	r28,-32(r1)
-	ld	r27,-40(r1)
-	ld	r26,-48(r1)
-	ld	r25,-56(r1)
-
-	blr
-
-.Lfirst_warm_up_done:
-	lvx	const1,0,r3
-	addi	r3,r3,16
-
-	VPMSUMD(v8,v16,const1)
-	VPMSUMD(v9,v17,const1)
-	VPMSUMD(v10,v18,const1)
-	VPMSUMD(v11,v19,const1)
-	VPMSUMD(v12,v20,const1)
-	VPMSUMD(v13,v21,const1)
-	VPMSUMD(v14,v22,const1)
-	VPMSUMD(v15,v23,const1)
-
-	b	.Lsecond_cool_down
-
-.Lshort:
-	cmpdi	r5,0
-	beq	.Lzero
-
-	addis	r3,r2,.short_constants@toc@ha
-	addi	r3,r3,.short_constants@toc@l
-
-	/* Calculate where in the constant table we need to start */
-	subfic	r6,r5,256
-	add	r3,r3,r6
-
-	/* How many 16 byte chunks? */
-	srdi	r7,r5,4
-	mtctr	r7
-
-	vxor	v19,v19,v19
-	vxor	v20,v20,v20
-
-	lvx	v0,0,r4
-	lvx	v16,0,r3
-	VPERM(v0,v0,v16,byteswap)
-	vxor	v0,v0,v8	/* xor in initial value */
-	VPMSUMW(v0,v0,v16)
-	bdz	.Lv0
-
-	lvx	v1,off16,r4
-	lvx	v17,off16,r3
-	VPERM(v1,v1,v17,byteswap)
-	VPMSUMW(v1,v1,v17)
-	bdz	.Lv1
-
-	lvx	v2,off32,r4
-	lvx	v16,off32,r3
-	VPERM(v2,v2,v16,byteswap)
-	VPMSUMW(v2,v2,v16)
-	bdz	.Lv2
-
-	lvx	v3,off48,r4
-	lvx	v17,off48,r3
-	VPERM(v3,v3,v17,byteswap)
-	VPMSUMW(v3,v3,v17)
-	bdz	.Lv3
-
-	lvx	v4,off64,r4
-	lvx	v16,off64,r3
-	VPERM(v4,v4,v16,byteswap)
-	VPMSUMW(v4,v4,v16)
-	bdz	.Lv4
-
-	lvx	v5,off80,r4
-	lvx	v17,off80,r3
-	VPERM(v5,v5,v17,byteswap)
-	VPMSUMW(v5,v5,v17)
-	bdz	.Lv5
-
-	lvx	v6,off96,r4
-	lvx	v16,off96,r3
-	VPERM(v6,v6,v16,byteswap)
-	VPMSUMW(v6,v6,v16)
-	bdz	.Lv6
-
-	lvx	v7,off112,r4
-	lvx	v17,off112,r3
-	VPERM(v7,v7,v17,byteswap)
-	VPMSUMW(v7,v7,v17)
-	bdz	.Lv7
-
-	addi	r3,r3,128
-	addi	r4,r4,128
-
-	lvx	v8,0,r4
-	lvx	v16,0,r3
-	VPERM(v8,v8,v16,byteswap)
-	VPMSUMW(v8,v8,v16)
-	bdz	.Lv8
-
-	lvx	v9,off16,r4
-	lvx	v17,off16,r3
-	VPERM(v9,v9,v17,byteswap)
-	VPMSUMW(v9,v9,v17)
-	bdz	.Lv9
-
-	lvx	v10,off32,r4
-	lvx	v16,off32,r3
-	VPERM(v10,v10,v16,byteswap)
-	VPMSUMW(v10,v10,v16)
-	bdz	.Lv10
-
-	lvx	v11,off48,r4
-	lvx	v17,off48,r3
-	VPERM(v11,v11,v17,byteswap)
-	VPMSUMW(v11,v11,v17)
-	bdz	.Lv11
-
-	lvx	v12,off64,r4
-	lvx	v16,off64,r3
-	VPERM(v12,v12,v16,byteswap)
-	VPMSUMW(v12,v12,v16)
-	bdz	.Lv12
-
-	lvx	v13,off80,r4
-	lvx	v17,off80,r3
-	VPERM(v13,v13,v17,byteswap)
-	VPMSUMW(v13,v13,v17)
-	bdz	.Lv13
-
-	lvx	v14,off96,r4
-	lvx	v16,off96,r3
-	VPERM(v14,v14,v16,byteswap)
-	VPMSUMW(v14,v14,v16)
-	bdz	.Lv14
-
-	lvx	v15,off112,r4
-	lvx	v17,off112,r3
-	VPERM(v15,v15,v17,byteswap)
-	VPMSUMW(v15,v15,v17)
-
-.Lv15:	vxor	v19,v19,v15
-.Lv14:	vxor	v20,v20,v14
-.Lv13:	vxor	v19,v19,v13
-.Lv12:	vxor	v20,v20,v12
-.Lv11:	vxor	v19,v19,v11
-.Lv10:	vxor	v20,v20,v10
-.Lv9:	vxor	v19,v19,v9
-.Lv8:	vxor	v20,v20,v8
-.Lv7:	vxor	v19,v19,v7
-.Lv6:	vxor	v20,v20,v6
-.Lv5:	vxor	v19,v19,v5
-.Lv4:	vxor	v20,v20,v4
-.Lv3:	vxor	v19,v19,v3
-.Lv2:	vxor	v20,v20,v2
-.Lv1:	vxor	v19,v19,v1
-.Lv0:	vxor	v20,v20,v0
-
-	vxor	v0,v19,v20
-
-	b	.Lbarrett_reduction
-
-.Lzero:
-	mr	r3,r10
-	b	.Lout
-
-FUNC_END(__crc32_vpmsum)
+#define CRC_FUNCTION_NAME __crc32c_vpmsum
+#define REFLECT
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index 9fa046d56eba..f058e0c3e4d4 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -33,10 +33,13 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
 	}
 
 	if (len & ~VMX_ALIGN_MASK) {
+		preempt_disable();
 		pagefault_disable();
 		enable_kernel_altivec();
 		crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+		disable_kernel_altivec();
 		pagefault_enable();
+		preempt_enable();
 	}
 
 	tail = len & VMX_ALIGN_MASK;
@@ -52,7 +55,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
 {
 	u32 *key = crypto_tfm_ctx(tfm);
 
-	*key = 0;
+	*key = ~0;
 
 	return 0;
 }
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
new file mode 100644
index 000000000000..5e3d81a0af1b
--- /dev/null
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
@@ -0,0 +1,850 @@
+/*
+ * Calculate a CRC T10DIF  with vpmsum acceleration
+ *
+ * Constants generated by crc32-vpmsum, available at
+ * https://github.com/antonblanchard/crc32-vpmsum
+ *
+ * crc32-vpmsum is
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ * and is available under the GPL v2 or later.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+	.section	.rodata
+.balign 16
+
+.byteswap_constant:
+	/* byte reverse permute constant */
+	.octa 0x0F0E0D0C0B0A09080706050403020100
+
+.constants:
+
+	/* Reduce 262144 kbits to 1024 bits */
+	/* x^261184 mod p(x), x^261120 mod p(x) */
+	.octa 0x0000000056d300000000000052550000
+
+	/* x^260160 mod p(x), x^260096 mod p(x) */
+	.octa 0x00000000ee67000000000000a1e40000
+
+	/* x^259136 mod p(x), x^259072 mod p(x) */
+	.octa 0x0000000060830000000000004ad10000
+
+	/* x^258112 mod p(x), x^258048 mod p(x) */
+	.octa 0x000000008cfe0000000000009ab40000
+
+	/* x^257088 mod p(x), x^257024 mod p(x) */
+	.octa 0x000000003e93000000000000fdb50000
+
+	/* x^256064 mod p(x), x^256000 mod p(x) */
+	.octa 0x000000003c2000000000000045480000
+
+	/* x^255040 mod p(x), x^254976 mod p(x) */
+	.octa 0x00000000b1fc0000000000008d690000
+
+	/* x^254016 mod p(x), x^253952 mod p(x) */
+	.octa 0x00000000f82b00000000000024ad0000
+
+	/* x^252992 mod p(x), x^252928 mod p(x) */
+	.octa 0x0000000044420000000000009f1a0000
+
+	/* x^251968 mod p(x), x^251904 mod p(x) */
+	.octa 0x00000000e88c00000000000066ec0000
+
+	/* x^250944 mod p(x), x^250880 mod p(x) */
+	.octa 0x00000000385c000000000000c87d0000
+
+	/* x^249920 mod p(x), x^249856 mod p(x) */
+	.octa 0x000000003227000000000000c8ff0000
+
+	/* x^248896 mod p(x), x^248832 mod p(x) */
+	.octa 0x00000000a9a900000000000033440000
+
+	/* x^247872 mod p(x), x^247808 mod p(x) */
+	.octa 0x00000000abaa00000000000066eb0000
+
+	/* x^246848 mod p(x), x^246784 mod p(x) */
+	.octa 0x000000001ac3000000000000c4ef0000
+
+	/* x^245824 mod p(x), x^245760 mod p(x) */
+	.octa 0x0000000063f000000000000056f30000
+
+	/* x^244800 mod p(x), x^244736 mod p(x) */
+	.octa 0x0000000032cc00000000000002050000
+
+	/* x^243776 mod p(x), x^243712 mod p(x) */
+	.octa 0x00000000f8b5000000000000568e0000
+
+	/* x^242752 mod p(x), x^242688 mod p(x) */
+	.octa 0x000000008db100000000000064290000
+
+	/* x^241728 mod p(x), x^241664 mod p(x) */
+	.octa 0x0000000059ca0000000000006b660000
+
+	/* x^240704 mod p(x), x^240640 mod p(x) */
+	.octa 0x000000005f5c00000000000018f80000
+
+	/* x^239680 mod p(x), x^239616 mod p(x) */
+	.octa 0x0000000061af000000000000b6090000
+
+	/* x^238656 mod p(x), x^238592 mod p(x) */
+	.octa 0x00000000e29e000000000000099a0000
+
+	/* x^237632 mod p(x), x^237568 mod p(x) */
+	.octa 0x000000000975000000000000a8360000
+
+	/* x^236608 mod p(x), x^236544 mod p(x) */
+	.octa 0x0000000043900000000000004f570000
+
+	/* x^235584 mod p(x), x^235520 mod p(x) */
+	.octa 0x00000000f9cd000000000000134c0000
+
+	/* x^234560 mod p(x), x^234496 mod p(x) */
+	.octa 0x000000007c29000000000000ec380000
+
+	/* x^233536 mod p(x), x^233472 mod p(x) */
+	.octa 0x000000004c6a000000000000b0d10000
+
+	/* x^232512 mod p(x), x^232448 mod p(x) */
+	.octa 0x00000000e7290000000000007d3e0000
+
+	/* x^231488 mod p(x), x^231424 mod p(x) */
+	.octa 0x00000000f1ab000000000000f0b20000
+
+	/* x^230464 mod p(x), x^230400 mod p(x) */
+	.octa 0x0000000039db0000000000009c270000
+
+	/* x^229440 mod p(x), x^229376 mod p(x) */
+	.octa 0x000000005e2800000000000092890000
+
+	/* x^228416 mod p(x), x^228352 mod p(x) */
+	.octa 0x00000000d44e000000000000d5ee0000
+
+	/* x^227392 mod p(x), x^227328 mod p(x) */
+	.octa 0x00000000cd0a00000000000041f50000
+
+	/* x^226368 mod p(x), x^226304 mod p(x) */
+	.octa 0x00000000c5b400000000000010520000
+
+	/* x^225344 mod p(x), x^225280 mod p(x) */
+	.octa 0x00000000fd2100000000000042170000
+
+	/* x^224320 mod p(x), x^224256 mod p(x) */
+	.octa 0x000000002f2500000000000095c20000
+
+	/* x^223296 mod p(x), x^223232 mod p(x) */
+	.octa 0x000000001b0100000000000001ce0000
+
+	/* x^222272 mod p(x), x^222208 mod p(x) */
+	.octa 0x000000000d430000000000002aca0000
+
+	/* x^221248 mod p(x), x^221184 mod p(x) */
+	.octa 0x0000000030a6000000000000385e0000
+
+	/* x^220224 mod p(x), x^220160 mod p(x) */
+	.octa 0x00000000e37b0000000000006f7a0000
+
+	/* x^219200 mod p(x), x^219136 mod p(x) */
+	.octa 0x00000000873600000000000024320000
+
+	/* x^218176 mod p(x), x^218112 mod p(x) */
+	.octa 0x00000000e9fb000000000000bd9c0000
+
+	/* x^217152 mod p(x), x^217088 mod p(x) */
+	.octa 0x000000003b9500000000000054bc0000
+
+	/* x^216128 mod p(x), x^216064 mod p(x) */
+	.octa 0x00000000133e000000000000a4660000
+
+	/* x^215104 mod p(x), x^215040 mod p(x) */
+	.octa 0x00000000784500000000000079930000
+
+	/* x^214080 mod p(x), x^214016 mod p(x) */
+	.octa 0x00000000b9800000000000001bb80000
+
+	/* x^213056 mod p(x), x^212992 mod p(x) */
+	.octa 0x00000000687600000000000024400000
+
+	/* x^212032 mod p(x), x^211968 mod p(x) */
+	.octa 0x00000000aff300000000000029e10000
+
+	/* x^211008 mod p(x), x^210944 mod p(x) */
+	.octa 0x0000000024b50000000000005ded0000
+
+	/* x^209984 mod p(x), x^209920 mod p(x) */
+	.octa 0x0000000017e8000000000000b12e0000
+
+	/* x^208960 mod p(x), x^208896 mod p(x) */
+	.octa 0x00000000128400000000000026d20000
+
+	/* x^207936 mod p(x), x^207872 mod p(x) */
+	.octa 0x000000002115000000000000a32a0000
+
+	/* x^206912 mod p(x), x^206848 mod p(x) */
+	.octa 0x000000009595000000000000a1210000
+
+	/* x^205888 mod p(x), x^205824 mod p(x) */
+	.octa 0x00000000281e000000000000ee8b0000
+
+	/* x^204864 mod p(x), x^204800 mod p(x) */
+	.octa 0x0000000006010000000000003d0d0000
+
+	/* x^203840 mod p(x), x^203776 mod p(x) */
+	.octa 0x00000000e2b600000000000034e90000
+
+	/* x^202816 mod p(x), x^202752 mod p(x) */
+	.octa 0x000000001bd40000000000004cdb0000
+
+	/* x^201792 mod p(x), x^201728 mod p(x) */
+	.octa 0x00000000df2800000000000030e90000
+
+	/* x^200768 mod p(x), x^200704 mod p(x) */
+	.octa 0x0000000049c200000000000042590000
+
+	/* x^199744 mod p(x), x^199680 mod p(x) */
+	.octa 0x000000009b97000000000000df950000
+
+	/* x^198720 mod p(x), x^198656 mod p(x) */
+	.octa 0x000000006184000000000000da7b0000
+
+	/* x^197696 mod p(x), x^197632 mod p(x) */
+	.octa 0x00000000461700000000000012510000
+
+	/* x^196672 mod p(x), x^196608 mod p(x) */
+	.octa 0x000000009b40000000000000f37e0000
+
+	/* x^195648 mod p(x), x^195584 mod p(x) */
+	.octa 0x00000000eeb2000000000000ecf10000
+
+	/* x^194624 mod p(x), x^194560 mod p(x) */
+	.octa 0x00000000b2e800000000000050f20000
+
+	/* x^193600 mod p(x), x^193536 mod p(x) */
+	.octa 0x00000000f59a000000000000e0b30000
+
+	/* x^192576 mod p(x), x^192512 mod p(x) */
+	.octa 0x00000000467f0000000000004d5a0000
+
+	/* x^191552 mod p(x), x^191488 mod p(x) */
+	.octa 0x00000000da92000000000000bb010000
+
+	/* x^190528 mod p(x), x^190464 mod p(x) */
+	.octa 0x000000001e1000000000000022a40000
+
+	/* x^189504 mod p(x), x^189440 mod p(x) */
+	.octa 0x0000000058fe000000000000836f0000
+
+	/* x^188480 mod p(x), x^188416 mod p(x) */
+	.octa 0x00000000b9ce000000000000d78d0000
+
+	/* x^187456 mod p(x), x^187392 mod p(x) */
+	.octa 0x0000000022210000000000004f8d0000
+
+	/* x^186432 mod p(x), x^186368 mod p(x) */
+	.octa 0x00000000744600000000000033760000
+
+	/* x^185408 mod p(x), x^185344 mod p(x) */
+	.octa 0x000000001c2e000000000000a1e50000
+
+	/* x^184384 mod p(x), x^184320 mod p(x) */
+	.octa 0x00000000dcc8000000000000a1a40000
+
+	/* x^183360 mod p(x), x^183296 mod p(x) */
+	.octa 0x00000000910f00000000000019a20000
+
+	/* x^182336 mod p(x), x^182272 mod p(x) */
+	.octa 0x0000000055d5000000000000f6ae0000
+
+	/* x^181312 mod p(x), x^181248 mod p(x) */
+	.octa 0x00000000c8ba000000000000a7ac0000
+
+	/* x^180288 mod p(x), x^180224 mod p(x) */
+	.octa 0x0000000031f8000000000000eea20000
+
+	/* x^179264 mod p(x), x^179200 mod p(x) */
+	.octa 0x000000001966000000000000c4d90000
+
+	/* x^178240 mod p(x), x^178176 mod p(x) */
+	.octa 0x00000000b9810000000000002b470000
+
+	/* x^177216 mod p(x), x^177152 mod p(x) */
+	.octa 0x000000008303000000000000f7cf0000
+
+	/* x^176192 mod p(x), x^176128 mod p(x) */
+	.octa 0x000000002ce500000000000035b30000
+
+	/* x^175168 mod p(x), x^175104 mod p(x) */
+	.octa 0x000000002fae0000000000000c7c0000
+
+	/* x^174144 mod p(x), x^174080 mod p(x) */
+	.octa 0x00000000f50c0000000000009edf0000
+
+	/* x^173120 mod p(x), x^173056 mod p(x) */
+	.octa 0x00000000714f00000000000004cd0000
+
+	/* x^172096 mod p(x), x^172032 mod p(x) */
+	.octa 0x00000000c161000000000000541b0000
+
+	/* x^171072 mod p(x), x^171008 mod p(x) */
+	.octa 0x0000000021c8000000000000e2700000
+
+	/* x^170048 mod p(x), x^169984 mod p(x) */
+	.octa 0x00000000b93d00000000000009a60000
+
+	/* x^169024 mod p(x), x^168960 mod p(x) */
+	.octa 0x00000000fbcf000000000000761c0000
+
+	/* x^168000 mod p(x), x^167936 mod p(x) */
+	.octa 0x0000000026350000000000009db30000
+
+	/* x^166976 mod p(x), x^166912 mod p(x) */
+	.octa 0x00000000b64f0000000000003e9f0000
+
+	/* x^165952 mod p(x), x^165888 mod p(x) */
+	.octa 0x00000000bd0e00000000000078590000
+
+	/* x^164928 mod p(x), x^164864 mod p(x) */
+	.octa 0x00000000d9360000000000008bc80000
+
+	/* x^163904 mod p(x), x^163840 mod p(x) */
+	.octa 0x000000002f140000000000008c9f0000
+
+	/* x^162880 mod p(x), x^162816 mod p(x) */
+	.octa 0x000000006a270000000000006af70000
+
+	/* x^161856 mod p(x), x^161792 mod p(x) */
+	.octa 0x000000006685000000000000e5210000
+
+	/* x^160832 mod p(x), x^160768 mod p(x) */
+	.octa 0x0000000062da00000000000008290000
+
+	/* x^159808 mod p(x), x^159744 mod p(x) */
+	.octa 0x00000000bb4b000000000000e4d00000
+
+	/* x^158784 mod p(x), x^158720 mod p(x) */
+	.octa 0x00000000d2490000000000004ae10000
+
+	/* x^157760 mod p(x), x^157696 mod p(x) */
+	.octa 0x00000000c85b00000000000000e70000
+
+	/* x^156736 mod p(x), x^156672 mod p(x) */
+	.octa 0x00000000c37a00000000000015650000
+
+	/* x^155712 mod p(x), x^155648 mod p(x) */
+	.octa 0x0000000018530000000000001c2f0000
+
+	/* x^154688 mod p(x), x^154624 mod p(x) */
+	.octa 0x00000000b46600000000000037bd0000
+
+	/* x^153664 mod p(x), x^153600 mod p(x) */
+	.octa 0x00000000439b00000000000012190000
+
+	/* x^152640 mod p(x), x^152576 mod p(x) */
+	.octa 0x00000000b1260000000000005ece0000
+
+	/* x^151616 mod p(x), x^151552 mod p(x) */
+	.octa 0x00000000d8110000000000002a5e0000
+
+	/* x^150592 mod p(x), x^150528 mod p(x) */
+	.octa 0x00000000099f00000000000052330000
+
+	/* x^149568 mod p(x), x^149504 mod p(x) */
+	.octa 0x00000000f9f9000000000000f9120000
+
+	/* x^148544 mod p(x), x^148480 mod p(x) */
+	.octa 0x000000005cc00000000000000ddc0000
+
+	/* x^147520 mod p(x), x^147456 mod p(x) */
+	.octa 0x00000000343b00000000000012200000
+
+	/* x^146496 mod p(x), x^146432 mod p(x) */
+	.octa 0x000000009222000000000000d12b0000
+
+	/* x^145472 mod p(x), x^145408 mod p(x) */
+	.octa 0x00000000d781000000000000eb2d0000
+
+	/* x^144448 mod p(x), x^144384 mod p(x) */
+	.octa 0x000000000bf400000000000058970000
+
+	/* x^143424 mod p(x), x^143360 mod p(x) */
+	.octa 0x00000000094200000000000013690000
+
+	/* x^142400 mod p(x), x^142336 mod p(x) */
+	.octa 0x00000000d55100000000000051950000
+
+	/* x^141376 mod p(x), x^141312 mod p(x) */
+	.octa 0x000000008f11000000000000954b0000
+
+	/* x^140352 mod p(x), x^140288 mod p(x) */
+	.octa 0x00000000140f000000000000b29e0000
+
+	/* x^139328 mod p(x), x^139264 mod p(x) */
+	.octa 0x00000000c6db000000000000db5d0000
+
+	/* x^138304 mod p(x), x^138240 mod p(x) */
+	.octa 0x00000000715b000000000000dfaf0000
+
+	/* x^137280 mod p(x), x^137216 mod p(x) */
+	.octa 0x000000000dea000000000000e3b60000
+
+	/* x^136256 mod p(x), x^136192 mod p(x) */
+	.octa 0x000000006f94000000000000ddaf0000
+
+	/* x^135232 mod p(x), x^135168 mod p(x) */
+	.octa 0x0000000024e1000000000000e4f70000
+
+	/* x^134208 mod p(x), x^134144 mod p(x) */
+	.octa 0x000000008810000000000000aa110000
+
+	/* x^133184 mod p(x), x^133120 mod p(x) */
+	.octa 0x0000000030c2000000000000a8e60000
+
+	/* x^132160 mod p(x), x^132096 mod p(x) */
+	.octa 0x00000000e6d0000000000000ccf30000
+
+	/* x^131136 mod p(x), x^131072 mod p(x) */
+	.octa 0x000000004da000000000000079bf0000
+
+	/* x^130112 mod p(x), x^130048 mod p(x) */
+	.octa 0x000000007759000000000000b3a30000
+
+	/* x^129088 mod p(x), x^129024 mod p(x) */
+	.octa 0x00000000597400000000000028790000
+
+	/* x^128064 mod p(x), x^128000 mod p(x) */
+	.octa 0x000000007acd000000000000b5820000
+
+	/* x^127040 mod p(x), x^126976 mod p(x) */
+	.octa 0x00000000e6e400000000000026ad0000
+
+	/* x^126016 mod p(x), x^125952 mod p(x) */
+	.octa 0x000000006d49000000000000985b0000
+
+	/* x^124992 mod p(x), x^124928 mod p(x) */
+	.octa 0x000000000f0800000000000011520000
+
+	/* x^123968 mod p(x), x^123904 mod p(x) */
+	.octa 0x000000002c7f000000000000846c0000
+
+	/* x^122944 mod p(x), x^122880 mod p(x) */
+	.octa 0x000000005ce7000000000000ae1d0000
+
+	/* x^121920 mod p(x), x^121856 mod p(x) */
+	.octa 0x00000000d4cb000000000000e21d0000
+
+	/* x^120896 mod p(x), x^120832 mod p(x) */
+	.octa 0x000000003a2300000000000019bb0000
+
+	/* x^119872 mod p(x), x^119808 mod p(x) */
+	.octa 0x000000000e1700000000000095290000
+
+	/* x^118848 mod p(x), x^118784 mod p(x) */
+	.octa 0x000000006e6400000000000050d20000
+
+	/* x^117824 mod p(x), x^117760 mod p(x) */
+	.octa 0x000000008d5c0000000000000cd10000
+
+	/* x^116800 mod p(x), x^116736 mod p(x) */
+	.octa 0x00000000ef310000000000007b570000
+
+	/* x^115776 mod p(x), x^115712 mod p(x) */
+	.octa 0x00000000645d00000000000053d60000
+
+	/* x^114752 mod p(x), x^114688 mod p(x) */
+	.octa 0x0000000018fc00000000000077510000
+
+	/* x^113728 mod p(x), x^113664 mod p(x) */
+	.octa 0x000000000cb3000000000000a7b70000
+
+	/* x^112704 mod p(x), x^112640 mod p(x) */
+	.octa 0x00000000991b000000000000d0780000
+
+	/* x^111680 mod p(x), x^111616 mod p(x) */
+	.octa 0x00000000845a000000000000be3c0000
+
+	/* x^110656 mod p(x), x^110592 mod p(x) */
+	.octa 0x00000000d3a9000000000000df020000
+
+	/* x^109632 mod p(x), x^109568 mod p(x) */
+	.octa 0x0000000017d7000000000000063e0000
+
+	/* x^108608 mod p(x), x^108544 mod p(x) */
+	.octa 0x000000007a860000000000008ab40000
+
+	/* x^107584 mod p(x), x^107520 mod p(x) */
+	.octa 0x00000000fd7c000000000000c7bd0000
+
+	/* x^106560 mod p(x), x^106496 mod p(x) */
+	.octa 0x00000000a56b000000000000efd60000
+
+	/* x^105536 mod p(x), x^105472 mod p(x) */
+	.octa 0x0000000010e400000000000071380000
+
+	/* x^104512 mod p(x), x^104448 mod p(x) */
+	.octa 0x00000000994500000000000004d30000
+
+	/* x^103488 mod p(x), x^103424 mod p(x) */
+	.octa 0x00000000b83c0000000000003b0e0000
+
+	/* x^102464 mod p(x), x^102400 mod p(x) */
+	.octa 0x00000000d6c10000000000008b020000
+
+	/* x^101440 mod p(x), x^101376 mod p(x) */
+	.octa 0x000000009efc000000000000da940000
+
+	/* x^100416 mod p(x), x^100352 mod p(x) */
+	.octa 0x000000005e87000000000000f9f70000
+
+	/* x^99392 mod p(x), x^99328 mod p(x) */
+	.octa 0x000000006c9b00000000000045e40000
+
+	/* x^98368 mod p(x), x^98304 mod p(x) */
+	.octa 0x00000000178a00000000000083940000
+
+	/* x^97344 mod p(x), x^97280 mod p(x) */
+	.octa 0x00000000f0c8000000000000f0a00000
+
+	/* x^96320 mod p(x), x^96256 mod p(x) */
+	.octa 0x00000000f699000000000000b74b0000
+
+	/* x^95296 mod p(x), x^95232 mod p(x) */
+	.octa 0x00000000316d000000000000c1cf0000
+
+	/* x^94272 mod p(x), x^94208 mod p(x) */
+	.octa 0x00000000987e00000000000072680000
+
+	/* x^93248 mod p(x), x^93184 mod p(x) */
+	.octa 0x00000000acff000000000000e0ab0000
+
+	/* x^92224 mod p(x), x^92160 mod p(x) */
+	.octa 0x00000000a1f6000000000000c5a80000
+
+	/* x^91200 mod p(x), x^91136 mod p(x) */
+	.octa 0x0000000061bd000000000000cf690000
+
+	/* x^90176 mod p(x), x^90112 mod p(x) */
+	.octa 0x00000000c9f2000000000000cbcc0000
+
+	/* x^89152 mod p(x), x^89088 mod p(x) */
+	.octa 0x000000005a33000000000000de050000
+
+	/* x^88128 mod p(x), x^88064 mod p(x) */
+	.octa 0x00000000e416000000000000ccd70000
+
+	/* x^87104 mod p(x), x^87040 mod p(x) */
+	.octa 0x0000000058930000000000002f670000
+
+	/* x^86080 mod p(x), x^86016 mod p(x) */
+	.octa 0x00000000a9d3000000000000152f0000
+
+	/* x^85056 mod p(x), x^84992 mod p(x) */
+	.octa 0x00000000c114000000000000ecc20000
+
+	/* x^84032 mod p(x), x^83968 mod p(x) */
+	.octa 0x00000000b9270000000000007c890000
+
+	/* x^83008 mod p(x), x^82944 mod p(x) */
+	.octa 0x000000002e6000000000000006ee0000
+
+	/* x^81984 mod p(x), x^81920 mod p(x) */
+	.octa 0x00000000dfc600000000000009100000
+
+	/* x^80960 mod p(x), x^80896 mod p(x) */
+	.octa 0x000000004911000000000000ad4e0000
+
+	/* x^79936 mod p(x), x^79872 mod p(x) */
+	.octa 0x00000000ae1b000000000000b04d0000
+
+	/* x^78912 mod p(x), x^78848 mod p(x) */
+	.octa 0x0000000005fa000000000000e9900000
+
+	/* x^77888 mod p(x), x^77824 mod p(x) */
+	.octa 0x0000000004a1000000000000cc6f0000
+
+	/* x^76864 mod p(x), x^76800 mod p(x) */
+	.octa 0x00000000af73000000000000ed110000
+
+	/* x^75840 mod p(x), x^75776 mod p(x) */
+	.octa 0x0000000082530000000000008f7e0000
+
+	/* x^74816 mod p(x), x^74752 mod p(x) */
+	.octa 0x00000000cfdc000000000000594f0000
+
+	/* x^73792 mod p(x), x^73728 mod p(x) */
+	.octa 0x00000000a6b6000000000000a8750000
+
+	/* x^72768 mod p(x), x^72704 mod p(x) */
+	.octa 0x00000000fd76000000000000aa0c0000
+
+	/* x^71744 mod p(x), x^71680 mod p(x) */
+	.octa 0x0000000006f500000000000071db0000
+
+	/* x^70720 mod p(x), x^70656 mod p(x) */
+	.octa 0x0000000037ca000000000000ab0c0000
+
+	/* x^69696 mod p(x), x^69632 mod p(x) */
+	.octa 0x00000000d7ab000000000000b7a00000
+
+	/* x^68672 mod p(x), x^68608 mod p(x) */
+	.octa 0x00000000440800000000000090d30000
+
+	/* x^67648 mod p(x), x^67584 mod p(x) */
+	.octa 0x00000000186100000000000054730000
+
+	/* x^66624 mod p(x), x^66560 mod p(x) */
+	.octa 0x000000007368000000000000a3a20000
+
+	/* x^65600 mod p(x), x^65536 mod p(x) */
+	.octa 0x0000000026d0000000000000f9040000
+
+	/* x^64576 mod p(x), x^64512 mod p(x) */
+	.octa 0x00000000fe770000000000009c0a0000
+
+	/* x^63552 mod p(x), x^63488 mod p(x) */
+	.octa 0x000000002cba000000000000d1e70000
+
+	/* x^62528 mod p(x), x^62464 mod p(x) */
+	.octa 0x00000000f8bd0000000000005ac10000
+
+	/* x^61504 mod p(x), x^61440 mod p(x) */
+	.octa 0x000000007372000000000000d68d0000
+
+	/* x^60480 mod p(x), x^60416 mod p(x) */
+	.octa 0x00000000f37f00000000000089f60000
+
+	/* x^59456 mod p(x), x^59392 mod p(x) */
+	.octa 0x00000000078400000000000008a90000
+
+	/* x^58432 mod p(x), x^58368 mod p(x) */
+	.octa 0x00000000d3e400000000000042360000
+
+	/* x^57408 mod p(x), x^57344 mod p(x) */
+	.octa 0x00000000eba800000000000092d50000
+
+	/* x^56384 mod p(x), x^56320 mod p(x) */
+	.octa 0x00000000afbe000000000000b4d50000
+
+	/* x^55360 mod p(x), x^55296 mod p(x) */
+	.octa 0x00000000d8ca000000000000c9060000
+
+	/* x^54336 mod p(x), x^54272 mod p(x) */
+	.octa 0x00000000c2d00000000000008f4f0000
+
+	/* x^53312 mod p(x), x^53248 mod p(x) */
+	.octa 0x00000000373200000000000028690000
+
+	/* x^52288 mod p(x), x^52224 mod p(x) */
+	.octa 0x0000000046ae000000000000c3b30000
+
+	/* x^51264 mod p(x), x^51200 mod p(x) */
+	.octa 0x00000000b243000000000000f8700000
+
+	/* x^50240 mod p(x), x^50176 mod p(x) */
+	.octa 0x00000000f7f500000000000029eb0000
+
+	/* x^49216 mod p(x), x^49152 mod p(x) */
+	.octa 0x000000000c7e000000000000fe730000
+
+	/* x^48192 mod p(x), x^48128 mod p(x) */
+	.octa 0x00000000c38200000000000096000000
+
+	/* x^47168 mod p(x), x^47104 mod p(x) */
+	.octa 0x000000008956000000000000683c0000
+
+	/* x^46144 mod p(x), x^46080 mod p(x) */
+	.octa 0x00000000422d0000000000005f1e0000
+
+	/* x^45120 mod p(x), x^45056 mod p(x) */
+	.octa 0x00000000ac0f0000000000006f810000
+
+	/* x^44096 mod p(x), x^44032 mod p(x) */
+	.octa 0x00000000ce30000000000000031f0000
+
+	/* x^43072 mod p(x), x^43008 mod p(x) */
+	.octa 0x000000003d43000000000000455a0000
+
+	/* x^42048 mod p(x), x^41984 mod p(x) */
+	.octa 0x000000007ebe000000000000a6050000
+
+	/* x^41024 mod p(x), x^40960 mod p(x) */
+	.octa 0x00000000976e00000000000077eb0000
+
+	/* x^40000 mod p(x), x^39936 mod p(x) */
+	.octa 0x000000000872000000000000389c0000
+
+	/* x^38976 mod p(x), x^38912 mod p(x) */
+	.octa 0x000000008979000000000000c7b20000
+
+	/* x^37952 mod p(x), x^37888 mod p(x) */
+	.octa 0x000000005c1e0000000000001d870000
+
+	/* x^36928 mod p(x), x^36864 mod p(x) */
+	.octa 0x00000000aebb00000000000045810000
+
+	/* x^35904 mod p(x), x^35840 mod p(x) */
+	.octa 0x000000004f7e0000000000006d4a0000
+
+	/* x^34880 mod p(x), x^34816 mod p(x) */
+	.octa 0x00000000ea98000000000000b9200000
+
+	/* x^33856 mod p(x), x^33792 mod p(x) */
+	.octa 0x00000000f39600000000000022f20000
+
+	/* x^32832 mod p(x), x^32768 mod p(x) */
+	.octa 0x000000000bc500000000000041ca0000
+
+	/* x^31808 mod p(x), x^31744 mod p(x) */
+	.octa 0x00000000786400000000000078500000
+
+	/* x^30784 mod p(x), x^30720 mod p(x) */
+	.octa 0x00000000be970000000000009e7e0000
+
+	/* x^29760 mod p(x), x^29696 mod p(x) */
+	.octa 0x00000000dd6d000000000000a53c0000
+
+	/* x^28736 mod p(x), x^28672 mod p(x) */
+	.octa 0x000000004c3f00000000000039340000
+
+	/* x^27712 mod p(x), x^27648 mod p(x) */
+	.octa 0x0000000093a4000000000000b58e0000
+
+	/* x^26688 mod p(x), x^26624 mod p(x) */
+	.octa 0x0000000050fb00000000000062d40000
+
+	/* x^25664 mod p(x), x^25600 mod p(x) */
+	.octa 0x00000000f505000000000000a26f0000
+
+	/* x^24640 mod p(x), x^24576 mod p(x) */
+	.octa 0x0000000064f900000000000065e60000
+
+	/* x^23616 mod p(x), x^23552 mod p(x) */
+	.octa 0x00000000e8c2000000000000aad90000
+
+	/* x^22592 mod p(x), x^22528 mod p(x) */
+	.octa 0x00000000720b000000000000a3b00000
+
+	/* x^21568 mod p(x), x^21504 mod p(x) */
+	.octa 0x00000000e992000000000000d2680000
+
+	/* x^20544 mod p(x), x^20480 mod p(x) */
+	.octa 0x000000009132000000000000cf4c0000
+
+	/* x^19520 mod p(x), x^19456 mod p(x) */
+	.octa 0x00000000608a00000000000076610000
+
+	/* x^18496 mod p(x), x^18432 mod p(x) */
+	.octa 0x000000009948000000000000fb9f0000
+
+	/* x^17472 mod p(x), x^17408 mod p(x) */
+	.octa 0x00000000173000000000000003770000
+
+	/* x^16448 mod p(x), x^16384 mod p(x) */
+	.octa 0x000000006fe300000000000004880000
+
+	/* x^15424 mod p(x), x^15360 mod p(x) */
+	.octa 0x00000000e15300000000000056a70000
+
+	/* x^14400 mod p(x), x^14336 mod p(x) */
+	.octa 0x0000000092d60000000000009dfd0000
+
+	/* x^13376 mod p(x), x^13312 mod p(x) */
+	.octa 0x0000000002fd00000000000074c80000
+
+	/* x^12352 mod p(x), x^12288 mod p(x) */
+	.octa 0x00000000c78b000000000000a3ec0000
+
+	/* x^11328 mod p(x), x^11264 mod p(x) */
+	.octa 0x000000009262000000000000b3530000
+
+	/* x^10304 mod p(x), x^10240 mod p(x) */
+	.octa 0x0000000084f200000000000047bf0000
+
+	/* x^9280 mod p(x), x^9216 mod p(x) */
+	.octa 0x0000000067ee000000000000e97c0000
+
+	/* x^8256 mod p(x), x^8192 mod p(x) */
+	.octa 0x00000000535b00000000000091e10000
+
+	/* x^7232 mod p(x), x^7168 mod p(x) */
+	.octa 0x000000007ebb00000000000055060000
+
+	/* x^6208 mod p(x), x^6144 mod p(x) */
+	.octa 0x00000000c6a1000000000000fd360000
+
+	/* x^5184 mod p(x), x^5120 mod p(x) */
+	.octa 0x000000001be500000000000055860000
+
+	/* x^4160 mod p(x), x^4096 mod p(x) */
+	.octa 0x00000000ae0e0000000000005bd00000
+
+	/* x^3136 mod p(x), x^3072 mod p(x) */
+	.octa 0x0000000022040000000000008db20000
+
+	/* x^2112 mod p(x), x^2048 mod p(x) */
+	.octa 0x00000000c9eb000000000000efe20000
+
+	/* x^1088 mod p(x), x^1024 mod p(x) */
+	.octa 0x0000000039b400000000000051d10000
+
+.short_constants:
+
+	/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+	/* x^2048 mod p(x), x^2016 mod p(x), x^1984 mod p(x), x^1952 mod p(x) */
+	.octa 0xefe20000dccf00009440000033590000
+
+	/* x^1920 mod p(x), x^1888 mod p(x), x^1856 mod p(x), x^1824 mod p(x) */
+	.octa 0xee6300002f3f000062180000e0ed0000
+
+	/* x^1792 mod p(x), x^1760 mod p(x), x^1728 mod p(x), x^1696 mod p(x) */
+	.octa 0xcf5f000017ef0000ccbe000023d30000
+
+	/* x^1664 mod p(x), x^1632 mod p(x), x^1600 mod p(x), x^1568 mod p(x) */
+	.octa 0x6d0c0000a30e00000920000042630000
+
+	/* x^1536 mod p(x), x^1504 mod p(x), x^1472 mod p(x), x^1440 mod p(x) */
+	.octa 0x21d30000932b0000a7a00000efcc0000
+
+	/* x^1408 mod p(x), x^1376 mod p(x), x^1344 mod p(x), x^1312 mod p(x) */
+	.octa 0x10be00000b310000666f00000d1c0000
+
+	/* x^1280 mod p(x), x^1248 mod p(x), x^1216 mod p(x), x^1184 mod p(x) */
+	.octa 0x1f240000ce9e0000caad0000589e0000
+
+	/* x^1152 mod p(x), x^1120 mod p(x), x^1088 mod p(x), x^1056 mod p(x) */
+	.octa 0x29610000d02b000039b400007cf50000
+
+	/* x^1024 mod p(x), x^992 mod p(x), x^960 mod p(x), x^928 mod p(x) */
+	.octa 0x51d100009d9d00003c0e0000bfd60000
+
+	/* x^896 mod p(x), x^864 mod p(x), x^832 mod p(x), x^800 mod p(x) */
+	.octa 0xda390000ceae000013830000713c0000
+
+	/* x^768 mod p(x), x^736 mod p(x), x^704 mod p(x), x^672 mod p(x) */
+	.octa 0xb67800001e16000085c0000080a60000
+
+	/* x^640 mod p(x), x^608 mod p(x), x^576 mod p(x), x^544 mod p(x) */
+	.octa 0x0db40000f7f90000371d0000e6580000
+
+	/* x^512 mod p(x), x^480 mod p(x), x^448 mod p(x), x^416 mod p(x) */
+	.octa 0x87e70000044c0000aadb0000a4970000
+
+	/* x^384 mod p(x), x^352 mod p(x), x^320 mod p(x), x^288 mod p(x) */
+	.octa 0x1f990000ad180000d8b30000e7b50000
+
+	/* x^256 mod p(x), x^224 mod p(x), x^192 mod p(x), x^160 mod p(x) */
+	.octa 0xbe6c00006ee300004c1a000006df0000
+
+	/* x^128 mod p(x), x^96 mod p(x), x^64 mod p(x), x^32 mod p(x) */
+	.octa 0xfb0b00002d560000136800008bb70000
+
+
+.barrett_constants:
+	/* Barrett constant m - (4^32)/n */
+	.octa 0x000000000000000000000001f65a57f8	/* x^64 div p(x) */
+	/* Barrett constant n */
+	.octa 0x0000000000000000000000018bb70000
+
+#define CRC_FUNCTION_NAME __crct10dif_vpmsum
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
new file mode 100644
index 000000000000..02ea277863d1
--- /dev/null
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
@@ -0,0 +1,128 @@
+/*
+ * Calculate a CRC T10-DIF with vpmsum acceleration
+ *
+ * Copyright 2017, Daniel Axtens, IBM Corporation.
+ * [based on crc32c-vpmsum_glue.c]
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ */
+
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN		16
+#define VMX_ALIGN_MASK		(VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT	64
+
+u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
+
+static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
+{
+	unsigned int prealign;
+	unsigned int tail;
+	u32 crc = crci;
+
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+		return crc_t10dif_generic(crc, p, len);
+
+	if ((unsigned long)p & VMX_ALIGN_MASK) {
+		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+		crc = crc_t10dif_generic(crc, p, prealign);
+		len -= prealign;
+		p += prealign;
+	}
+
+	if (len & ~VMX_ALIGN_MASK) {
+		crc <<= 16;
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+		crc = __crct10dif_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+		disable_kernel_altivec();
+		pagefault_enable();
+		preempt_enable();
+		crc >>= 16;
+	}
+
+	tail = len & VMX_ALIGN_MASK;
+	if (tail) {
+		p += len & ~VMX_ALIGN_MASK;
+		crc = crc_t10dif_generic(crc, p, tail);
+	}
+
+	return crc & 0xffff;
+}
+
+static int crct10dif_vpmsum_init(struct shash_desc *desc)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	*crc = 0;
+	return 0;
+}
+
+static int crct10dif_vpmsum_update(struct shash_desc *desc, const u8 *data,
+			    unsigned int length)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	*crc = crct10dif_vpmsum(*crc, data, length);
+
+	return 0;
+}
+
+
+static int crct10dif_vpmsum_final(struct shash_desc *desc, u8 *out)
+{
+	u16 *crcp = shash_desc_ctx(desc);
+
+	*(u16 *)out = *crcp;
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.init		= crct10dif_vpmsum_init,
+	.update		= crct10dif_vpmsum_update,
+	.final		= crct10dif_vpmsum_final,
+	.descsize	= CRC_T10DIF_DIGEST_SIZE,
+	.digestsize	= CRC_T10DIF_DIGEST_SIZE,
+	.base		= {
+		.cra_name		= "crct10dif",
+		.cra_driver_name	= "crct10dif-vpmsum",
+		.cra_priority		= 200,
+		.cra_blocksize		= CRC_T10DIF_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init crct10dif_vpmsum_mod_init(void)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crct10dif_vpmsum_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crct10dif_vpmsum_mod_init);
+module_exit(crct10dif_vpmsum_mod_fini);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-vpmsum");
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 73eb794d6163..bc5fdfd22788 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -51,6 +51,10 @@
 #define PPC_BIT(bit)		(1UL << PPC_BITLSHIFT(bit))
 #define PPC_BITMASK(bs, be)	((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
 
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit)			\
+	((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
 #include <asm/barrier.h>
 
 /* Macro for generating the ***_bits() functions */
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 012223638815..26ed228d4dc6 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
 #define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #include <asm/book3s/32/hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 1eeeb72c7015..8f4d41936e5a 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1,9 +1,12 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 
+#include <asm-generic/5level-fixup.h>
+
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
 #endif
+
 /*
  * Common bits between hash and Radix page table
  */
@@ -347,23 +350,58 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 	__r;							\
 })
 
+static inline int __pte_write(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+	/*
+	 * Saved write ptes are prot none ptes that doesn't have
+	 * privileged bit sit. We mark prot none as one which has
+	 * present and pviliged bit set and RWX cleared. To mark
+	 * protnone which used to have _PAGE_WRITE set we clear
+	 * the privileged bit.
+	 */
+	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+}
+#else
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+	return false;
+}
+#endif
+
+static inline int pte_write(pte_t pte)
+{
+	return __pte_write(pte) || pte_savedwrite(pte);
+}
+
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+	if (__pte_write(*ptep))
+		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+	else if (unlikely(pte_savedwrite(*ptep)))
+		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+	/*
+	 * We should not find protnone for hugetlb, but this complete the
+	 * interface.
+	 */
+	if (__pte_write(*ptep))
+		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+	else if (unlikely(pte_savedwrite(*ptep)))
+		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
 }
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -397,11 +435,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
 
-static inline int pte_write(pte_t pte)
-{
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
 static inline int pte_dirty(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@@ -465,19 +498,12 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
 	VM_BUG_ON(!pte_protnone(pte));
 	return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
 }
-
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
+#else
+#define pte_clear_savedwrite pte_clear_savedwrite
+static inline pte_t pte_clear_savedwrite(pte_t pte)
 {
-	/*
-	 * Saved write ptes are prot none ptes that doesn't have
-	 * privileged bit sit. We mark prot none as one which has
-	 * present and pviliged bit set and RWX cleared. To mark
-	 * protnone which used to have _PAGE_WRITE set we clear
-	 * the privileged bit.
-	 */
-	VM_BUG_ON(!pte_protnone(pte));
-	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+	VM_WARN_ON(1);
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
@@ -506,6 +532,8 @@ static inline unsigned long pte_pfn(pte_t pte)
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
+	if (unlikely(pte_savedwrite(pte)))
+		return pte_clear_savedwrite(pte);
 	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 
@@ -926,6 +954,7 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+#define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
 #define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -982,11 +1011,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
-
-	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+	if (__pmd_write((*pmdp)))
+		pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+	else if (unlikely(pmd_savedwrite(*pmdp)))
+		pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
 }
 
 static inline int pmd_trans_huge(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 3a39283333c3..f2c562a0a427 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -85,12 +85,12 @@
 	}							\
 } while (0)
 
-#define __WARN_TAINT(taint) do {				\
+#define __WARN_FLAGS(flags) do {				\
 	__asm__ __volatile__(					\
 		"1:	twi 31,0,0\n"				\
 		_EMIT_BUG_ENTRY					\
 		: : "i" (__FILE__), "i" (__LINE__),		\
-		  "i" (BUGFLAG_TAINT(taint)),			\
+		  "i" (BUGFLAG_WARNING|(flags)),		\
 		  "i" (sizeof(struct bug_entry)));		\
 } while (0)
 
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 4e63787dc3be..842124b199b5 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 
 #ifdef __powerpc64__
 	res += (__force u64)addend;
-	return (__force __wsum)((u32)res + (res >> 32));
+	return (__force __wsum) from64to32(res);
 #else
 	asm("addc %0,%0,%1;"
 	    "addze %0,%0;"
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index fd321eb423cb..155731557c9b 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -70,8 +70,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err)
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmpd	cr0,r0,r0;					\
-	bne	1b;						\
+236:	cmpd	cr0,r0,r0;					\
+	bne	236b;						\
 	IDLE_INST;						\
 
 #define	IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 93b9b84568e8..09bde6e34f5d 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define ARCH_DLINFO_CACHE_GEOMETRY					\
 	NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size);		\
 	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i));	\
-	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size);		\
-	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size);		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d));	\
 	NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size);		\
 	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2));	\
 	NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size);		\
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 14752eee3d0c..ed3beadd2cc5 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -236,9 +236,9 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtctr	reg;							\
 	bctr
 
-#define BRANCH_LINK_TO_FAR(reg, label)					\
-	__LOAD_FAR_HANDLER(reg, label);					\
-	mtctr	reg;							\
+#define BRANCH_LINK_TO_FAR(label)					\
+	__LOAD_FAR_HANDLER(r12, label);					\
+	mtctr	r12;							\
 	bctrl
 
 /*
@@ -265,7 +265,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define BRANCH_TO_COMMON(reg, label)					\
 	b	label
 
-#define BRANCH_LINK_TO_FAR(reg, label)					\
+#define BRANCH_LINK_TO_FAR(label)					\
 	bl	label
 
 #define BRANCH_TO_KVM(reg, label)					\
diff --git a/arch/powerpc/include/asm/extable.h b/arch/powerpc/include/asm/extable.h
new file mode 100644
index 000000000000..07cc45cd86d9
--- /dev/null
+++ b/arch/powerpc/include/asm/extable.h
@@ -0,0 +1,29 @@
+#ifndef _ARCH_POWERPC_EXTABLE_H
+#define _ARCH_POWERPC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative addresses: the first is
+ * the address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out what
+ * to do.
+ *
+ * All the routines below use bits of fixup code that are out of line with the
+ * main instruction path.  This means when everything is well, we don't even
+ * have to jump over them.  Further, they do not intrude on our cache or tlb
+ * entries.
+ */
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+struct exception_table_entry {
+	int insn;
+	int fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->fixup + x->fixup;
+}
+
+#endif
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index f97d8cb6bdf6..ed62efe01e49 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -66,6 +66,55 @@
 
 #define P8_DSISR_MC_SLB_ERRORS		(P7_DSISR_MC_SLB_ERRORS | \
 					 P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
+/*
+ * Machine Check bits on power9
+ */
+#define P9_SRR1_MC_LOADSTORE(srr1)	(((srr1) >> PPC_BITLSHIFT(42)) & 1)
+
+#define P9_SRR1_MC_IFETCH(srr1)	(	\
+	PPC_BITEXTRACT(srr1, 45, 0) |	\
+	PPC_BITEXTRACT(srr1, 44, 1) |	\
+	PPC_BITEXTRACT(srr1, 43, 2) |	\
+	PPC_BITEXTRACT(srr1, 36, 3) )
+
+/* 0 is reserved */
+#define P9_SRR1_MC_IFETCH_UE				1
+#define P9_SRR1_MC_IFETCH_SLB_PARITY			2
+#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT			3
+#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT			4
+#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT			5
+#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD			6
+/* 7 is reserved */
+#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT			8
+#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT	9
+/* 10 ? */
+#define P9_SRR1_MC_IFETCH_RA			11
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK		12
+#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE		13
+#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT	14
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN	15
+
+/* DSISR bits for machine check (On Power9) */
+#define P9_DSISR_MC_UE					(PPC_BIT(48))
+#define P9_DSISR_MC_UE_TABLEWALK			(PPC_BIT(49))
+#define P9_DSISR_MC_LINK_LOAD_TIMEOUT			(PPC_BIT(50))
+#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT		(PPC_BIT(51))
+#define P9_DSISR_MC_ERAT_MULTIHIT			(PPC_BIT(52))
+#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB			(PPC_BIT(53))
+#define P9_DSISR_MC_USER_TLBIE				(PPC_BIT(54))
+#define P9_DSISR_MC_SLB_PARITY_MFSLB			(PPC_BIT(55))
+#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB			(PPC_BIT(56))
+#define P9_DSISR_MC_RA_LOAD				(PPC_BIT(57))
+#define P9_DSISR_MC_RA_TABLEWALK			(PPC_BIT(58))
+#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN		(PPC_BIT(59))
+#define P9_DSISR_MC_RA_FOREIGN				(PPC_BIT(60))
+
+/* SLB error bits */
+#define P9_DSISR_MC_SLB_ERRORS		(P9_DSISR_MC_ERAT_MULTIHIT | \
+					 P9_DSISR_MC_SLB_PARITY_MFSLB | \
+					 P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+
 enum MCE_Version {
 	MCE_V1 = 1,
 };
@@ -93,6 +142,9 @@ enum MCE_ErrorType {
 	MCE_ERROR_TYPE_SLB = 2,
 	MCE_ERROR_TYPE_ERAT = 3,
 	MCE_ERROR_TYPE_TLB = 4,
+	MCE_ERROR_TYPE_USER = 5,
+	MCE_ERROR_TYPE_RA = 6,
+	MCE_ERROR_TYPE_LINK = 7,
 };
 
 enum MCE_UeErrorType {
@@ -121,6 +173,32 @@ enum MCE_TlbErrorType {
 	MCE_TLB_ERROR_MULTIHIT = 2,
 };
 
+enum MCE_UserErrorType {
+	MCE_USER_ERROR_INDETERMINATE = 0,
+	MCE_USER_ERROR_TLBIE = 1,
+};
+
+enum MCE_RaErrorType {
+	MCE_RA_ERROR_INDETERMINATE = 0,
+	MCE_RA_ERROR_IFETCH = 1,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
+	MCE_RA_ERROR_LOAD = 4,
+	MCE_RA_ERROR_STORE = 5,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
+	MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+};
+
+enum MCE_LinkErrorType {
+	MCE_LINK_ERROR_INDETERMINATE = 0,
+	MCE_LINK_ERROR_IFETCH_TIMEOUT = 1,
+	MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2,
+	MCE_LINK_ERROR_LOAD_TIMEOUT = 3,
+	MCE_LINK_ERROR_STORE_TIMEOUT = 4,
+	MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5,
+};
+
 struct machine_check_event {
 	enum MCE_Version	version:8;	/* 0x00 */
 	uint8_t			in_use;		/* 0x01 */
@@ -166,6 +244,30 @@ struct machine_check_event {
 			uint64_t	effective_address;
 			uint8_t		reserved_2[16];
 		} tlb_error;
+
+		struct {
+			enum MCE_UserErrorType user_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} user_error;
+
+		struct {
+			enum MCE_RaErrorType ra_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} ra_error;
+
+		struct {
+			enum MCE_LinkErrorType link_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} link_error;
 	} u;
 };
 
@@ -176,8 +278,12 @@ struct mce_error_info {
 		enum MCE_SlbErrorType slb_error_type:8;
 		enum MCE_EratErrorType erat_error_type:8;
 		enum MCE_TlbErrorType tlb_error_type:8;
+		enum MCE_UserErrorType user_error_type:8;
+		enum MCE_RaErrorType ra_error_type:8;
+		enum MCE_LinkErrorType link_error_type:8;
 	} u;
-	uint8_t		reserved[2];
+	enum MCE_Severity	severity:8;
+	enum MCE_Initiator	initiator:8;
 };
 
 #define MAX_MC_EVT	100
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b9e3f0aca261..ecf9885ab660 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -163,11 +163,5 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	/* by default, allow everything */
 	return true;
 }
-
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
-	/* by default, allow everything */
-	return true;
-}
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ba9921bf202e..5134ade2e850 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H
 #define _ASM_POWERPC_NOHASH_32_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index d0db98793dd8..9f4de0a1035e 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -1,5 +1,8 @@
 #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
 #define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
+
+#include <asm-generic/5level-fixup.h>
+
 /*
  * Entries per page directory level.  The PTE level must use a 64b record
  * for each page table entry.  The PMD and PGD level use a 32b record for
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
index 55b28ef3409a..1facb584dd29 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 #define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 0cd8a3852763..e5805ad78e12 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd)
 	return ((hpd_val(hpd) & 0x4) != 0);
 #else
 	/* We clear the top bit to indicate hugepd */
-	return ((hpd_val(hpd) & PD_HUGE) ==  0);
+	return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d99bd442aacb..e7d6d86563ee 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -284,6 +284,13 @@
 #define PPC_INST_BRANCH_COND		0x40800000
 #define PPC_INST_LBZCIX			0x7c0006aa
 #define PPC_INST_STBCIX			0x7c0007aa
+#define PPC_INST_LWZX			0x7c00002e
+#define PPC_INST_LFSX			0x7c00042e
+#define PPC_INST_STFSX			0x7c00052e
+#define PPC_INST_LFDX			0x7c0004ae
+#define PPC_INST_STFDX			0x7c0005ae
+#define PPC_INST_LVX			0x7c0000ce
+#define PPC_INST_STVX			0x7c0001ce
 
 /* macros to insert fields into opcodes */
 #define ___PPC_RA(a)	(((a) & 0x1f) << 16)
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 4a90634e8322..35c00d7a0cf8 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -160,12 +160,18 @@ struct of_drconf_cell {
 #define OV5_PFO_HW_ENCR		0x1120	/* PFO Encryption Accelerator */
 #define OV5_SUB_PROCESSORS	0x1501	/* 1,2,or 4 Sub-Processors supported */
 #define OV5_XIVE_EXPLOIT	0x1701	/* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300	0x1880	/* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300	0x1840	/* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX	0x1820	/* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL	0x1810	/* hcall selects SLB or proc table */
-#define OV5_MMU_SLB		0x1800	/* always use SLB */
-#define OV5_MMU_GTSE		0x1808	/* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT		0x18C0	/* MMU Mode Support Mask */
+#define OV5_MMU_HASH		0x1800	/* Hash MMU Only */
+#define OV5_MMU_RADIX		0x1840	/* Radix MMU Only */
+#define OV5_MMU_EITHER		0x1880	/* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC		0x18C0	/* Hash or Radix Can Switch Later */
+#define OV5_NMMU		0x1820	/* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL	0x1980	/* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE		0x1940	/* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE		0x1A40	/* Guest Translation Shoot Down Avail */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 4b369d83fe9c..1c9470881c4a 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -387,3 +387,4 @@ SYSCALL(copy_file_range)
 COMPAT_SYS_SPU(preadv2)
 COMPAT_SYS_SPU(pwritev2)
 SYSCALL(kexec_file_load)
+SYSCALL(statx)
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 0e6add3187bc..5c0d8a8cdae5 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -1,18 +1,11 @@
 #ifndef _ARCH_POWERPC_UACCESS_H
 #define _ARCH_POWERPC_UACCESS_H
 
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/errno.h>
 #include <asm/asm-compat.h>
 #include <asm/ppc_asm.h>
 #include <asm/processor.h>
 #include <asm/page.h>
-
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
+#include <asm/extable.h>
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -64,31 +57,6 @@
 	 __access_ok((__force unsigned long)(addr), (size), get_fs()))
 
 /*
- * The exception table consists of pairs of relative addresses: the first is
- * the address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out what
- * to do.
- *
- * All the routines below use bits of fixup code that are out of line with the
- * main instruction path.  This means when everything is well, we don't even
- * have to jump over them.  Further, they do not intrude on our cache or tlb
- * entries.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-struct exception_table_entry {
-	int insn;
-	int fixup;
-};
-
-static inline unsigned long extable_fixup(const struct exception_table_entry *x)
-{
-	return (unsigned long)&x->fixup + x->fixup;
-}
-
-/*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.
  *
@@ -301,42 +269,19 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 
 #ifndef __powerpc64__
 
-static inline unsigned long copy_from_user(void *to,
-		const void __user *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_READ, from, n))) {
-		check_object_size(to, n, false);
-		return __copy_tofrom_user((__force void __user *)to, from, n);
-	}
-	memset(to, 0, n);
-	return n;
-}
-
-static inline unsigned long copy_to_user(void __user *to,
-		const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n)) {
-		check_object_size(from, n, true);
-		return __copy_tofrom_user(to, (__force void __user *)from, n);
-	}
-	return n;
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 #else /* __powerpc64__ */
 
-#define __copy_in_user(to, from, size) \
-	__copy_tofrom_user((to), (from), (size))
-
-extern unsigned long copy_from_user(void *to, const void __user *from,
-				    unsigned long n);
-extern unsigned long copy_to_user(void __user *to, const void *from,
-				  unsigned long n);
-extern unsigned long copy_in_user(void __user *to, const void __user *from,
-				  unsigned long n);
-
+static inline unsigned long
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+	return __copy_tofrom_user(to, from, n);
+}
 #endif /* __powerpc64__ */
 
-static inline unsigned long __copy_from_user_inatomic(void *to,
+static inline unsigned long raw_copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
 	if (__builtin_constant_p(n) && (n <= 8)) {
@@ -360,12 +305,10 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
 			return 0;
 	}
 
-	check_object_size(to, n, false);
-
 	return __copy_tofrom_user((__force void __user *)to, from, n);
 }
 
-static inline unsigned long __copy_to_user_inatomic(void __user *to,
+static inline unsigned long raw_copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
 	if (__builtin_constant_p(n) && (n <= 8)) {
@@ -389,25 +332,9 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to,
 			return 0;
 	}
 
-	check_object_size(from, n, true);
-
 	return __copy_tofrom_user(to, (__force const void __user *)from, n);
 }
 
-static inline unsigned long __copy_from_user(void *to,
-		const void __user *from, unsigned long size)
-{
-	might_fault();
-	return __copy_from_user_inatomic(to, from, size);
-}
-
-static inline unsigned long __copy_to_user(void __user *to,
-		const void *from, unsigned long size)
-{
-	might_fault();
-	return __copy_to_user_inatomic(to, from, size);
-}
-
 extern unsigned long __clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
@@ -422,7 +349,4 @@ extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-#endif  /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
 #endif	/* _ARCH_POWERPC_UACCESS_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index eb1acee91a20..9ba11dbcaca9 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		383
+#define NR_syscalls		384
 
 #define __NR__exit __NR_exit
 
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 44583a52f882..58e2ec0310fc 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -99,4 +99,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 2f26335a3c42..b85f14228857 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -393,5 +393,6 @@
 #define __NR_preadv2		380
 #define __NR_pwritev2		381
 #define __NR_kexec_file_load	382
+#define __NR_statx		383
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index cbc7c42cdb74..ec7a8b099dd9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -807,14 +807,25 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
-	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
-	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
-		nb = 8;
-		flags = LD+SW;
-	} else if (IS_XFORM(instruction) &&
-		   ((instruction >> 1) & 0x3ff) == 660) {
-		nb = 8;
-		flags = ST+SW;
+	/*
+	 * Handle some cases which give overlaps in the DSISR values.
+	 */
+	if (IS_XFORM(instruction)) {
+		switch (get_xop(instruction)) {
+		case 532:	/* ldbrx */
+			nb = 8;
+			flags = LD+SW;
+			break;
+		case 660:	/* stdbrx */
+			nb = 8;
+			flags = ST+SW;
+			break;
+		case 20:	/* lwarx */
+		case 84:	/* ldarx */
+		case 116:	/* lharx */
+		case 276:	/* lqarx */
+			return 0;	/* not emulated ever */
+		}
 	}
 
 	/* Byteswap little endian loads and stores */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index bb7a1890aeb7..e79b9daa873c 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -77,6 +77,7 @@ extern void __flush_tlb_power8(unsigned int action);
 extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_E500)
 extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -540,6 +541,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
 		.flush_tlb		= __flush_tlb_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
 	{	/* Power9 */
@@ -559,6 +561,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
 		.flush_tlb		= __flush_tlb_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
 	{	/* Cell Broadband Engine */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6432d4bf08c8..767ef6d68c9e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -689,7 +689,7 @@ resume_kernel:
 
 	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
 
-	lwz	r3,GPR1(r1)
+	ld	r3,GPR1(r1)
 	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
 	mr	r4,r1			/* src:  current exception frame */
 	mr	r1,r3			/* Reroute the trampoline frame to r1 */
@@ -703,8 +703,8 @@ resume_kernel:
 	addi	r6,r6,8
 	bdnz	2b
 
-	/* Do real store operation to complete stwu */
-	lwz	r5,GPR1(r1)
+	/* Do real store operation to complete stdu */
+	ld	r5,GPR1(r1)
 	std	r8,0(r5)
 
 	/* Clear _TIF_EMULATE_STACK_STORE flag */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 857bf7c5b946..6353019966e6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -982,7 +982,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early)
 	EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN)
 	EXCEPTION_PROLOG_COMMON_3(0xe60)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode)
+	BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */
 	/* Windup the stack. */
 	/* Move original HSRR0 and HSRR1 into the respective regs */
 	ld	r9,_MSR(r1)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 5f61cc0349c0..6fd08219248d 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -276,19 +276,21 @@ power_enter_stop:
  */
 	andis.   r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
 	clrldi   r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
-	bne	 1f
+	bne	 .Lhandle_esl_ec_set
 	IDLE_STATE_ENTER_SEQ(PPC_STOP)
 	li	r3,0  /* Since we didn't lose state, return 0 */
 	b 	pnv_wakeup_noloss
+
+.Lhandle_esl_ec_set:
 /*
  * Check if the requested state is a deep idle state.
  */
-1:	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
 	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
 	cmpd	r3,r4
-	bge	2f
+	bge	.Lhandle_deep_stop
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
-2:
+.Lhandle_deep_stop:
 /*
  * Entering deep idle state.
  * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
@@ -447,9 +449,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 _GLOBAL(pnv_wakeup_tb_loss)
 	ld	r1,PACAR1(r13)
 	/*
-	 * Before entering any idle state, the NVGPRs are saved in the stack
-	 * and they are restored before switching to the process context. Hence
-	 * until they are restored, they are free to be used.
+	 * Before entering any idle state, the NVGPRs are saved in the stack.
+	 * If there was a state loss, or PACA_NAPSTATELOST was set, then the
+	 * NVGPRs are restored. If we are here, it is likely that state is lost,
+	 * but not guaranteed -- neither ISA207 nor ISA300 tests to reach
+	 * here are the same as the test to restore NVGPRS:
+	 * PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
+	 * and SRR1 test for restoring NVGPRs.
+	 *
+	 * We are about to clobber NVGPRs now, so set NAPSTATELOST to
+	 * guarantee they will always be restored. This might be tightened
+	 * with careful reading of specs (particularly for ISA300) but this
+	 * is already a slow wakeup path and it's simpler to be safe.
+	 */
+	li	r0,1
+	stb	r0,PACA_NAPSTATELOST(r13)
+
+	/*
 	 *
 	 * Save SRR1 and LR in NVGPRs as they might be clobbered in
 	 * opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index c6923ff45131..a1475e6aef3a 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -58,6 +58,15 @@ static void mce_set_error_info(struct machine_check_event *mce,
 	case MCE_ERROR_TYPE_TLB:
 		mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
 		break;
+	case MCE_ERROR_TYPE_USER:
+		mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+		break;
+	case MCE_ERROR_TYPE_RA:
+		mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+		break;
 	case MCE_ERROR_TYPE_UNKNOWN:
 	default:
 		break;
@@ -90,13 +99,14 @@ void save_mce_event(struct pt_regs *regs, long handled,
 	mce->gpr3 = regs->gpr[3];
 	mce->in_use = 1;
 
-	mce->initiator = MCE_INITIATOR_CPU;
 	/* Mark it recovered if we have handled it and MSR(RI=1). */
 	if (handled && (regs->msr & MSR_RI))
 		mce->disposition = MCE_DISPOSITION_RECOVERED;
 	else
 		mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
-	mce->severity = MCE_SEV_ERROR_SYNC;
+
+	mce->initiator = mce_err->initiator;
+	mce->severity = mce_err->severity;
 
 	/*
 	 * Populate the mce error_type and type-specific error_type.
@@ -115,6 +125,15 @@ void save_mce_event(struct pt_regs *regs, long handled,
 	} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
 		mce->u.erat_error.effective_address_provided = true;
 		mce->u.erat_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+		mce->u.user_error.effective_address_provided = true;
+		mce->u.user_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+		mce->u.ra_error.effective_address_provided = true;
+		mce->u.ra_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+		mce->u.link_error.effective_address_provided = true;
+		mce->u.link_error.effective_address = addr;
 	} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
 		mce->u.ue_error.effective_address_provided = true;
 		mce->u.ue_error.effective_address = addr;
@@ -239,6 +258,29 @@ void machine_check_print_event_info(struct machine_check_event *evt)
 		"Parity",
 		"Multihit",
 	};
+	static const char *mc_user_types[] = {
+		"Indeterminate",
+		"tlbie(l) invalid",
+	};
+	static const char *mc_ra_types[] = {
+		"Indeterminate",
+		"Instruction fetch (bad)",
+		"Page table walk ifetch (bad)",
+		"Page table walk ifetch (foreign)",
+		"Load (bad)",
+		"Store (bad)",
+		"Page table walk Load/Store (bad)",
+		"Page table walk Load/Store (foreign)",
+		"Load/Store (foreign)",
+	};
+	static const char *mc_link_types[] = {
+		"Indeterminate",
+		"Instruction fetch (timeout)",
+		"Page table walk ifetch (timeout)",
+		"Load (timeout)",
+		"Store (timeout)",
+		"Page table walk Load/Store (timeout)",
+	};
 
 	/* Print things out */
 	if (evt->version != MCE_V1) {
@@ -315,6 +357,36 @@ void machine_check_print_event_info(struct machine_check_event *evt)
 			printk("%s    Effective address: %016llx\n",
 			       level, evt->u.tlb_error.effective_address);
 		break;
+	case MCE_ERROR_TYPE_USER:
+		subtype = evt->u.user_error.user_error_type <
+			ARRAY_SIZE(mc_user_types) ?
+			mc_user_types[evt->u.user_error.user_error_type]
+			: "Unknown";
+		printk("%s  Error type: User [%s]\n", level, subtype);
+		if (evt->u.user_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.user_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_RA:
+		subtype = evt->u.ra_error.ra_error_type <
+			ARRAY_SIZE(mc_ra_types) ?
+			mc_ra_types[evt->u.ra_error.ra_error_type]
+			: "Unknown";
+		printk("%s  Error type: Real address [%s]\n", level, subtype);
+		if (evt->u.ra_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.ra_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		subtype = evt->u.link_error.link_error_type <
+			ARRAY_SIZE(mc_link_types) ?
+			mc_link_types[evt->u.link_error.link_error_type]
+			: "Unknown";
+		printk("%s  Error type: Link [%s]\n", level, subtype);
+		if (evt->u.link_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.link_error.effective_address);
+		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:
 		printk("%s  Error type: Unknown\n", level);
@@ -341,6 +413,18 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt)
 		if (evt->u.tlb_error.effective_address_provided)
 			return evt->u.tlb_error.effective_address;
 		break;
+	case MCE_ERROR_TYPE_USER:
+		if (evt->u.user_error.effective_address_provided)
+			return evt->u.user_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_RA:
+		if (evt->u.ra_error.effective_address_provided)
+			return evt->u.ra_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		if (evt->u.link_error.effective_address_provided)
+			return evt->u.link_error.effective_address;
+		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:
 		break;
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 7353991c4ece..763d6f58caa8 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -116,6 +116,51 @@ static void flush_and_reload_slb(void)
 }
 #endif
 
+static void flush_erat(void)
+{
+	asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+}
+
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
+#ifdef CONFIG_PPC_STD_MMU_64
+	if (what == MCE_FLUSH_SLB) {
+		flush_and_reload_slb();
+		return 1;
+	}
+#endif
+	if (what == MCE_FLUSH_ERAT) {
+		flush_erat();
+		return 1;
+	}
+	if (what == MCE_FLUSH_TLB) {
+		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat)
+{
+	if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB))
+		dsisr &= ~slb;
+	if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT))
+		dsisr &= ~erat;
+	if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB))
+		dsisr &= ~tlb;
+	/* Any other errors we don't understand? */
+	if (dsisr)
+		return 0;
+	return 1;
+}
+
 static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 {
 	long handled = 1;
@@ -281,6 +326,9 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
+	mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+	mce_error_info.initiator = MCE_INITIATOR_CPU;
+
 	srr1 = regs->msr;
 	nip = regs->nip;
 
@@ -352,6 +400,9 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
+	mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+	mce_error_info.initiator = MCE_INITIATOR_CPU;
+
 	srr1 = regs->msr;
 	nip = regs->nip;
 
@@ -372,3 +423,189 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
 	save_mce_event(regs, handled, &mce_error_info, nip, addr);
 	return handled;
 }
+
+static int mce_handle_derror_p9(struct pt_regs *regs)
+{
+	uint64_t dsisr = regs->dsisr;
+
+	return mce_handle_flush_derrors(dsisr,
+			P9_DSISR_MC_SLB_PARITY_MFSLB |
+			P9_DSISR_MC_SLB_MULTIHIT_MFSLB,
+
+			P9_DSISR_MC_TLB_MULTIHIT_MFTLB,
+
+			P9_DSISR_MC_ERAT_MULTIHIT);
+}
+
+static int mce_handle_ierror_p9(struct pt_regs *regs)
+{
+	uint64_t srr1 = regs->msr;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_SLB_PARITY:
+	case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		return mce_flush(MCE_FLUSH_SLB);
+	case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		return mce_flush(MCE_FLUSH_TLB);
+	case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+		return mce_flush(MCE_FLUSH_ERAT);
+	default:
+		return 0;
+	}
+}
+
+static void mce_get_derror_p9(struct pt_regs *regs,
+		struct mce_error_info *mce_err, uint64_t *addr)
+{
+	uint64_t dsisr = regs->dsisr;
+
+	mce_err->severity = MCE_SEV_ERROR_SYNC;
+	mce_err->initiator = MCE_INITIATOR_CPU;
+
+	if (dsisr & P9_DSISR_MC_USER_TLBIE)
+		*addr = regs->nip;
+	else
+		*addr = regs->dar;
+
+	if (dsisr & P9_DSISR_MC_UE) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) {
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT;
+	} else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) {
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT;
+	} else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) {
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_USER_TLBIE) {
+		mce_err->error_type = MCE_ERROR_TYPE_USER;
+		mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE;
+	} else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+	} else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_RA_LOAD) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD;
+	} else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN;
+	} else if (dsisr & P9_DSISR_MC_RA_FOREIGN) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN;
+	}
+}
+
+static void mce_get_ierror_p9(struct pt_regs *regs,
+		struct mce_error_info *mce_err, uint64_t *addr)
+{
+	uint64_t srr1 = regs->msr;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+	case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+		mce_err->severity = MCE_SEV_FATAL;
+		break;
+	default:
+		mce_err->severity = MCE_SEV_ERROR_SYNC;
+		break;
+	}
+
+	mce_err->initiator = MCE_INITIATOR_CPU;
+
+	*addr = regs->nip;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_UE:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_SLB_PARITY:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+		break;
+	case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_RA:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_TABLEWALK:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_STORE;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN;
+		break;
+	default:
+		break;
+	}
+}
+
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
+{
+	uint64_t nip, addr;
+	long handled;
+	struct mce_error_info mce_error_info = { 0 };
+
+	nip = regs->nip;
+
+	if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
+		handled = mce_handle_derror_p9(regs);
+		mce_get_derror_p9(regs, &mce_error_info, &addr);
+	} else {
+		handled = mce_handle_ierror_p9(regs);
+		mce_get_ierror_p9(regs, &mce_error_info, &addr);
+	}
+
+	/* Handle UE error. */
+	if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+		handled = mce_handle_ue_error(regs);
+
+	save_mce_event(regs, handled, &mce_error_info, nip, addr);
+	return handled;
+}
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ae179cb1bb3c..c119044cad0d 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -67,7 +67,7 @@ PPC64_CACHES:
  *   flush all bytes from start through stop-1 inclusive
  */
 
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
 BEGIN_FTR_SECTION
 	PURGE_PREFETCHED_INS
 	blr
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(flush_icache_range)
  *
  *    flush all bytes from start to stop-1 inclusive
  */
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
 
 /*
  * Flush the data cache to memory 
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index d5e2b8309939..eae61b044e9e 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -389,51 +389,40 @@ static int nvram_pstore_open(struct pstore_info *psi)
 
 /**
  * nvram_pstore_write - pstore write callback for nvram
- * @type:               Type of message logged
- * @reason:             reason behind dump (oops/panic)
- * @id:                 identifier to indicate the write performed
- * @part:               pstore writes data to registered buffer in parts,
- *                      part number will indicate the same.
- * @count:              Indicates oops count
- * @compressed:         Flag to indicate the log is compressed
- * @size:               number of bytes written to the registered buffer
- * @psi:                registered pstore_info structure
+ * @record:             pstore record to write, with @id to be set
  *
  * Called by pstore_dump() when an oops or panic report is logged in the
  * printk buffer.
  * Returns 0 on successful write.
  */
-static int nvram_pstore_write(enum pstore_type_id type,
-				enum kmsg_dump_reason reason,
-				u64 *id, unsigned int part, int count,
-				bool compressed, size_t size,
-				struct pstore_info *psi)
+static int nvram_pstore_write(struct pstore_record *record)
 {
 	int rc;
 	unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
 	struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
 
 	/* part 1 has the recent messages from printk buffer */
-	if (part > 1 || (type != PSTORE_TYPE_DMESG))
+	if (record->part > 1 || (record->type != PSTORE_TYPE_DMESG))
 		return -1;
 
 	if (clobbering_unread_rtas_event())
 		return -1;
 
 	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
-	oops_hdr->report_length = cpu_to_be16(size);
+	oops_hdr->report_length = cpu_to_be16(record->size);
 	oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
 
-	if (compressed)
+	if (record->compressed)
 		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
 
 	rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) (sizeof(*oops_hdr) + size), err_type, count);
+		(int) (sizeof(*oops_hdr) + record->size), err_type,
+		record->count);
 
 	if (rc != 0)
 		return rc;
 
-	*id = part;
+	record->id = record->part;
 	return 0;
 }
 
@@ -442,10 +431,7 @@ static int nvram_pstore_write(enum pstore_type_id type,
  * Returns the length of the data we read from each partition.
  * Returns 0 if we've been called before.
  */
-static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
-				int *count, struct timespec *time, char **buf,
-				bool *compressed, ssize_t *ecc_notice_size,
-				struct pstore_info *psi)
+static ssize_t nvram_pstore_read(struct pstore_record *record)
 {
 	struct oops_log_info *oops_hdr;
 	unsigned int err_type, id_no, size = 0;
@@ -459,40 +445,40 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 	switch (nvram_type_ids[read_type]) {
 	case PSTORE_TYPE_DMESG:
 		part = &oops_log_partition;
-		*type = PSTORE_TYPE_DMESG;
+		record->type = PSTORE_TYPE_DMESG;
 		break;
 	case PSTORE_TYPE_PPC_COMMON:
 		sig = NVRAM_SIG_SYS;
 		part = &common_partition;
-		*type = PSTORE_TYPE_PPC_COMMON;
-		*id = PSTORE_TYPE_PPC_COMMON;
-		time->tv_sec = 0;
-		time->tv_nsec = 0;
+		record->type = PSTORE_TYPE_PPC_COMMON;
+		record->id = PSTORE_TYPE_PPC_COMMON;
+		record->time.tv_sec = 0;
+		record->time.tv_nsec = 0;
 		break;
 #ifdef CONFIG_PPC_PSERIES
 	case PSTORE_TYPE_PPC_RTAS:
 		part = &rtas_log_partition;
-		*type = PSTORE_TYPE_PPC_RTAS;
-		time->tv_sec = last_rtas_event;
-		time->tv_nsec = 0;
+		record->type = PSTORE_TYPE_PPC_RTAS;
+		record->time.tv_sec = last_rtas_event;
+		record->time.tv_nsec = 0;
 		break;
 	case PSTORE_TYPE_PPC_OF:
 		sig = NVRAM_SIG_OF;
 		part = &of_config_partition;
-		*type = PSTORE_TYPE_PPC_OF;
-		*id = PSTORE_TYPE_PPC_OF;
-		time->tv_sec = 0;
-		time->tv_nsec = 0;
+		record->type = PSTORE_TYPE_PPC_OF;
+		record->id = PSTORE_TYPE_PPC_OF;
+		record->time.tv_sec = 0;
+		record->time.tv_nsec = 0;
 		break;
 #endif
 #ifdef CONFIG_PPC_POWERNV
 	case PSTORE_TYPE_PPC_OPAL:
 		sig = NVRAM_SIG_FW;
 		part = &skiboot_partition;
-		*type = PSTORE_TYPE_PPC_OPAL;
-		*id = PSTORE_TYPE_PPC_OPAL;
-		time->tv_sec = 0;
-		time->tv_nsec = 0;
+		record->type = PSTORE_TYPE_PPC_OPAL;
+		record->id = PSTORE_TYPE_PPC_OPAL;
+		record->time.tv_sec = 0;
+		record->time.tv_nsec = 0;
 		break;
 #endif
 	default:
@@ -520,10 +506,10 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		return 0;
 	}
 
-	*count = 0;
+	record->count = 0;
 
 	if (part->os_partition)
-		*id = id_no;
+		record->id = id_no;
 
 	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
 		size_t length, hdr_size;
@@ -533,34 +519,35 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 			/* Old format oops header had 2-byte record size */
 			hdr_size = sizeof(u16);
 			length = be16_to_cpu(oops_hdr->version);
-			time->tv_sec = 0;
-			time->tv_nsec = 0;
+			record->time.tv_sec = 0;
+			record->time.tv_nsec = 0;
 		} else {
 			hdr_size = sizeof(*oops_hdr);
 			length = be16_to_cpu(oops_hdr->report_length);
-			time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
-			time->tv_nsec = 0;
+			record->time.tv_sec = be64_to_cpu(oops_hdr->timestamp);
+			record->time.tv_nsec = 0;
 		}
-		*buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
+		record->buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
 		kfree(buff);
-		if (*buf == NULL)
+		if (record->buf == NULL)
 			return -ENOMEM;
 
-		*ecc_notice_size = 0;
+		record->ecc_notice_size = 0;
 		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
-			*compressed = true;
+			record->compressed = true;
 		else
-			*compressed = false;
+			record->compressed = false;
 		return length;
 	}
 
-	*buf = buff;
+	record->buf = buff;
 	return part->size;
 }
 
 static struct pstore_info nvram_pstore_info = {
 	.owner = THIS_MODULE,
 	.name = "nvram",
+	.flags = PSTORE_FLAGS_DMESG,
 	.open = nvram_pstore_open,
 	.read = nvram_pstore_read,
 	.write = nvram_pstore_write,
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a3944540fe0d..1c1b44ec7642 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
 
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+	bool hash_mmu;
+	bool radix_mmu;
+	bool radix_gtse;
+};
+
 /* Platforms codes are now obsolete in the kernel. Now only used within this
  * file and ultimately gone too. Feel free to change them if you need, they
  * are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
 		prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
 #endif
 	}
+
+	opt = strstr(prom_cmd_line, "disable_radix");
+	if (opt) {
+		prom_debug("Radix disabled from cmdline\n");
+		prom_radix_disable = true;
+	}
 }
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
 	u8 byte22;
 	u8 intarch;
 	u8 mmu;
+	u8 hash_ext;
+	u8 radix_ext;
 } __packed;
 
 struct option_vector6 {
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.reserved3 = 0,
 		.subprocessors = 1,
 		.intarch = 0,
-		.mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
-			OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+		.mmu = 0,
+		.hash_ext = 0,
+		.radix_ext = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
 
 }
 
+static void __init prom_parse_mmu_model(u8 val,
+					struct platform_support *support)
+{
+	switch (val) {
+	case OV5_FEAT(OV5_MMU_DYNAMIC):
+	case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+		prom_debug("MMU - either supported\n");
+		support->radix_mmu = !prom_radix_disable;
+		support->hash_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+		prom_debug("MMU - radix only\n");
+		if (prom_radix_disable) {
+			/*
+			 * If we __have__ to do radix, we're better off ignoring
+			 * the command line rather than not booting.
+			 */
+			prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		support->radix_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_HASH):
+		prom_debug("MMU - hash only\n");
+		support->hash_mmu = true;
+		break;
+	default:
+		prom_debug("Unknown mmu support option: 0x%x\n", val);
+		break;
+	}
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+					       struct platform_support *support)
+{
+	switch (index) {
+	case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+		prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+		break;
+	case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+		if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+			prom_debug("Radix - GTSE supported\n");
+			support->radix_gtse = true;
+		}
+		break;
+	}
+}
+
+static void __init prom_check_platform_support(void)
+{
+	struct platform_support supported = {
+		.hash_mmu = false,
+		.radix_mmu = false,
+		.radix_gtse = false
+	};
+	int prop_len = prom_getproplen(prom.chosen,
+				       "ibm,arch-vec-5-platform-support");
+	if (prop_len > 1) {
+		int i;
+		u8 vec[prop_len];
+		prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+			   prop_len);
+		prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+			     &vec, sizeof(vec));
+		for (i = 0; i < prop_len; i += 2) {
+			prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+								  , vec[i]
+								  , vec[i + 1]);
+			prom_parse_platform_support(vec[i], vec[i + 1],
+						    &supported);
+		}
+	}
+
+	if (supported.radix_mmu && supported.radix_gtse) {
+		/* Radix preferred - but we require GTSE for now */
+		prom_debug("Asking for radix with GTSE\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+		ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+	} else if (supported.hash_mmu) {
+		/* Default to hash mmu (if we can) */
+		prom_debug("Asking for hash\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+	} else {
+		/* We're probably on a legacy hypervisor */
+		prom_debug("Assuming legacy hash support\n");
+	}
+}
 
 static void __init prom_send_capabilities(void)
 {
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
 	prom_arg_t ret;
 	u32 cores;
 
+	/* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+	prom_check_platform_support();
+
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
 		/* We need to tell the FW about the number of cores we support.
@@ -2993,6 +3099,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	prom_check_initrd(r3, r4);
 
+	/*
+	 * Do early parsing of command line
+	 */
+	early_cmdline_parse();
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 	/*
 	 * On pSeries, inform the firmware about our capabilities
@@ -3009,11 +3120,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 		copy_and_flush(0, kbase, 0x100, 0);
 
 	/*
-	 * Do early parsing of command line
-	 */
-	early_cmdline_parse();
-
-	/*
 	 * Initialize memory management within prom_init
 	 */
 	prom_init_mem();
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index adf2084f214b..f997154dfc41 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -236,6 +236,15 @@ static void cpu_ready_for_interrupts(void)
 		mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
 	}
 
+	/*
+	 * Fixup HFSCR:TM based on CPU features. The bit is set by our
+	 * early asm init because at that point we haven't updated our
+	 * CPU features from firmware and device-tree. Here we have,
+	 * so let's do it.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+		mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
 	/* Set IR and DR in PACA MSR */
 	get_paca()->kernel_msr = MSR_KERNEL;
 }
@@ -408,7 +417,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
 	info->line_size = lsize;
 	info->block_size = bsize;
 	info->log_block_size = __ilog2(bsize);
-	info->blocks_per_page = PAGE_SIZE / bsize;
+	if (bsize)
+		info->blocks_per_page = PAGE_SIZE / bsize;
+	else
+		info->blocks_per_page = 0;
 
 	if (sets == 0)
 		info->assoc = 0xffff;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 46f89e66a273..d68ed1f004a3 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -787,24 +787,21 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 	{ NULL, },
 };
 
-void __init smp_cpus_done(unsigned int max_cpus)
+static __init long smp_setup_cpu_workfn(void *data __always_unused)
 {
-	cpumask_var_t old_mask;
+	smp_ops->setup_cpu(boot_cpuid);
+	return 0;
+}
 
-	/* We want the setup_cpu() here to be called from CPU 0, but our
-	 * init thread may have been "borrowed" by another CPU in the meantime
-	 * se we pin us down to CPU 0 for a short while
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+	/*
+	 * We want the setup_cpu() here to be called on the boot CPU, but
+	 * init might run on any CPU, so make sure it's invoked on the boot
+	 * CPU.
 	 */
-	alloc_cpumask_var(&old_mask, GFP_NOWAIT);
-	cpumask_copy(old_mask, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
-	
 	if (smp_ops && smp_ops->setup_cpu)
-		smp_ops->setup_cpu(boot_cpuid);
-
-	set_cpus_allowed_ptr(current, old_mask);
-
-	free_cpumask_var(old_mask);
+		work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
 
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();
@@ -812,7 +809,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	dump_numa_cpu_topology();
 
 	set_sched_topology(powerpc_topology);
-
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 07b90725855e..2b33cfaac7b8 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -995,8 +995,10 @@ static void __init init_decrementer_clockevent(void)
 
 	decrementer_clockevent.max_delta_ns =
 		clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
+	decrementer_clockevent.max_delta_ticks = decrementer_max;
 	decrementer_clockevent.min_delta_ns =
 		clockevent_delta2ns(2, &decrementer_clockevent);
+	decrementer_clockevent.min_delta_ticks = 2;
 
 	register_decrementer_clockevent(cpu);
 }
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 7394b770ae1f..1c24c894c908 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -312,6 +312,8 @@ SECTIONS
 		NOSAVE_DATA
 	}
 
+	BUG_TABLE
+
 	. = ALIGN(PAGE_SIZE);
 	_edata  =  .;
 	PROVIDE32 (edata = .);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3158fb16de3..710e491206ed 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 							 hva, NULL, NULL);
 			if (ptep) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
-				if (pte_write(pte))
+				if (__pte_write(pte))
 					write_ok = 1;
 			}
 			local_irq_restore(flags);
@@ -1487,6 +1487,10 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 	/* start new resize */
 
 	resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+	if (!resize) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	resize->order = shift;
 	resize->kvm = kvm;
 	INIT_WORK(&resize->work, resize_hpt_prepare_work);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6fca970373ee..ce6f2121fffe 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		}
 		pte = kvmppc_read_update_linux_pte(ptep, writing);
 		if (pte_present(pte) && !pte_protnone(pte)) {
-			if (writing && !pte_write(pte))
+			if (writing && !__pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);
 			is_ci = pte_ci(pte);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 0e649d72fe8d..ed7dfce331e0 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -14,12 +14,13 @@ obj-y += string.o alloc.o crtsavres.o code-patching.o \
 
 obj-$(CONFIG_PPC32)	+= div64.o copy_32.o
 
-obj64-y	+= copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
+obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
 	   copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
 	   memcpy_64.o memcmp_64.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o
 
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index ff0d894d7ff9..8aedbb5f4b86 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -477,18 +477,6 @@ _GLOBAL(__copy_tofrom_user)
 	bdnz	130b
 /* then clear out the destination: r3 bytes starting at 4(r6) */
 132:	mfctr	r3
-	srwi.	r0,r3,2
-	li	r9,0
-	mtctr	r0
-	beq	113f
-112:	stwu	r9,4(r6)
-	bdnz	112b
-113:	andi.	r0,r3,3
-	mtctr	r0
-	beq	120f
-114:	stb	r9,4(r6)
-	addi	r6,r6,1
-	bdnz	114b
 120:	blr
 
 	EX_TABLE(30b,108b)
@@ -497,7 +485,5 @@ _GLOBAL(__copy_tofrom_user)
 	EX_TABLE(41b,111b)
 	EX_TABLE(130b,132b)
 	EX_TABLE(131b,120b)
-	EX_TABLE(112b,120b)
-	EX_TABLE(114b,120b)
 
 EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index aee6e24e81ab..08da06e1bd72 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -319,32 +319,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	blr
 
 /*
- * here we have trapped again, need to clear ctr bytes starting at r3
+ * here we have trapped again, amount remaining is in ctr.
  */
-143:	mfctr	r5
-	li	r0,0
-	mr	r4,r3
-	mr	r3,r5		/* return the number of bytes not copied */
-1:	andi.	r9,r4,7
-	beq	3f
-90:	stb	r0,0(r4)
-	addic.	r5,r5,-1
-	addi	r4,r4,1
-	bne	1b
-	blr
-3:	cmpldi	cr1,r5,8
-	srdi	r9,r5,3
-	andi.	r5,r5,7
-	blt	cr1,93f
-	mtctr	r9
-91:	std	r0,0(r4)
-	addi	r4,r4,8
-	bdnz	91b
-93:	beqlr
-	mtctr	r5	
-92:	stb	r0,0(r4)
-	addi	r4,r4,1
-	bdnz	92b
+143:	mfctr	r3
 	blr
 
 /*
@@ -389,10 +366,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	ld	r5,-8(r1)
 	add	r6,r6,r5
 	subf	r3,r3,r6	/* #bytes not copied */
-190:
-191:
-192:
-	blr			/* #bytes not copied in r3 */
+	blr
 
 	EX_TABLE(20b,120b)
 	EX_TABLE(220b,320b)
@@ -451,9 +425,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	EX_TABLE(88b,188b)
 	EX_TABLE(43b,143b)
 	EX_TABLE(89b,189b)
-	EX_TABLE(90b,190b)
-	EX_TABLE(91b,191b)
-	EX_TABLE(92b,192b)
 
 /*
  * Routine to copy a whole page of data, optimized for POWER4.
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 846dba2c6360..9c542ec70c5b 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1799,8 +1799,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case LARX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1823,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case STCX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1849,8 +1845,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case LOAD:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
 		if (!err) {
 			if (op.type & SIGNEXT)
@@ -1862,8 +1856,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
 		else
@@ -1872,15 +1864,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case LOAD_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
@@ -1903,8 +1891,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case STORE:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if ((op.type & UPDATE) && size == sizeof(long) &&
 		    op.reg == 1 && op.update_reg == 1 &&
 		    !(regs->msr & MSR_PR) &&
@@ -1917,8 +1903,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
 		else
@@ -1927,15 +1911,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case STORE_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
new file mode 100644
index 000000000000..2534c1447554
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -0,0 +1,434 @@
+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i)		((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i)	(PPC_INST_LD | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i)	(PPC_INST_LWZ | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b)	(PPC_INST_LWZX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i)	(PPC_INST_STD | ___PPC_RS(r) |		\
+					___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh)	(PPC_INST_LDARX | ___PPC_RT(t) |	\
+					___PPC_RA(a) | ___PPC_RB(b) |	\
+					__PPC_EH(eh))
+#define TEST_STDCX(s, a, b)	(PPC_INST_STDCX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b)	(PPC_INST_LFSX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b)	(PPC_INST_STFSX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b)	(PPC_INST_LFDX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b)	(PPC_INST_STFDX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b)	(PPC_INST_LVX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b)	(PPC_INST_STVX | ___PPC_RS(s) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+	static unsigned long msr;
+	static bool msr_cached;
+
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	if (likely(msr_cached)) {
+		regs->msr = msr;
+		return;
+	}
+
+	asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+	regs->msr |= MSR_FP;
+	regs->msr |= MSR_VEC;
+	regs->msr |= MSR_VSX;
+
+	msr = regs->msr;
+	msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+	pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x23;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* ld r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("ld", "PASS");
+	else
+		show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+	struct pt_regs regs;
+	unsigned int a = 0x4545;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* lwz r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("lwz", "PASS");
+	else
+		show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+	struct pt_regs regs;
+	unsigned int a[3] = {0x0, 0x0, 0x1234};
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) a;
+	regs.gpr[4] = 8;
+	regs.gpr[5] = 0x8765;
+
+	/* lwzx r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+	if (stepped == 1 && regs.gpr[5] == a[2])
+		show_result("lwzx", "PASS");
+	else
+		show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[5] = 0x5678;
+
+	/* std r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+	if (stepped == 1 || regs.gpr[5] == a)
+		show_result("std", "PASS");
+	else
+		show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+	unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+	init_pt_regs(&regs);
+	asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+	/*** ldarx ***/
+
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[4] = 0;
+	regs.gpr[5] = 0x5678;
+
+	/* ldarx r5, r3, r4, 0 */
+	stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+
+	/*
+	 * Don't touch 'a' here. Touching 'a' can do Load/store
+	 * of 'a' which result in failure of subsequent stdcx.
+	 * Instead, use hardcoded value for comparison.
+	 */
+	if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+		show_result("ldarx / stdcx.", "FAIL (ldarx)");
+		return;
+	}
+
+
+	/*** stdcx. ***/
+
+	regs.gpr[5] = 0x9ABC;
+
+	/* stdcx. r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+
+	/*
+	 * Two possible scenarios that indicates successful emulation
+	 * of stdcx. :
+	 *  1. Reservation is active and store is performed. In this
+	 *     case cr0.eq bit will be set to 1.
+	 *  2. Reservation is not active and store is not performed.
+	 *     In this case cr0.eq bit will be set to 0.
+	 */
+	if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+			|| (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+		show_result("ldarx / stdcx.", "PASS");
+	else
+		show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+	struct pt_regs regs;
+	union {
+		float a;
+		int b;
+	} c;
+	int cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfsx ***/
+
+	c.a = 123.45;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfsx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfsx", "PASS");
+	else
+		show_result("lfsx", "FAIL");
+
+
+	/*** stfsx ***/
+
+	c.a = 678.91;
+
+	/* stfsx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfsx", "PASS");
+	else
+		show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	struct pt_regs regs;
+	union {
+		double a;
+		long b;
+	} c;
+	long cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfdx ***/
+
+	c.a = 123456.78;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfdx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfdx", "PASS");
+	else
+		show_result("lfdx", "FAIL");
+
+
+	/*** stfdx ***/
+
+	c.a = 987654.32;
+
+	/* stfdx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfdx", "PASS");
+	else
+		show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+	show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lvx ***/
+
+	cached_b[0] = c.b[0] = 923745;
+	cached_b[1] = c.b[1] = 2139478;
+	cached_b[2] = c.b[2] = 9012;
+	cached_b[3] = c.b[3] = 982134;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lvx vrt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lvx", "PASS");
+	else
+		show_result("lvx", "FAIL");
+
+
+	/*** stvx ***/
+
+	c.b[0] = 4987513;
+	c.b[1] = 84313948;
+	c.b[2] = 71;
+	c.b[3] = 498532;
+
+	/* stvx vrs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STVX(10, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stvx", "PASS");
+	else
+		show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+	show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+	show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lxvd2x ***/
+
+	cached_b[0] = c.b[0] = 18233;
+	cached_b[1] = c.b[1] = 34863571;
+	cached_b[2] = c.b[2] = 834;
+	cached_b[3] = c.b[3] = 6138911;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+
+	if (stepped == 1)
+		show_result("lxvd2x", "PASS");
+	else
+		show_result("lxvd2x", "FAIL");
+
+
+	/*** stxvd2x ***/
+
+	c.b[0] = 21379463;
+	c.b[1] = 87;
+	c.b[2] = 374234;
+	c.b[3] = 4;
+
+	/* stxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stxvd2x", "PASS");
+	else
+		show_result("stxvd2x", "FAIL");
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+	show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+	test_ld();
+	test_lwz();
+	test_lwzx();
+	test_std();
+	test_ldarx_stdcx();
+	test_lfsx_stfsx();
+	test_lfdx_stfdx();
+	test_lvx_stvx();
+	test_lxvd2x_stxvd2x();
+
+	return 0;
+}
+late_initcall(test_emulate_step);
diff --git a/arch/powerpc/lib/usercopy_64.c b/arch/powerpc/lib/usercopy_64.c
deleted file mode 100644
index 9bd3a3dad78d..000000000000
--- a/arch/powerpc/lib/usercopy_64.c
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Functions which are too large to be inlined.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/module.h>
-#include <linux/uaccess.h>
-
-unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		n = __copy_from_user(to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-
-unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (likely(access_ok(VERIFY_WRITE, to, n)))
-		n = __copy_to_user(to, from, n);
-	return n;
-}
-
-unsigned long copy_in_user(void __user *to, const void __user *from,
-			   unsigned long n)
-{
-	might_sleep();
-	if (likely(access_ok(VERIFY_READ, from, n) &&
-	    access_ok(VERIFY_WRITE, to, n)))
-		n =__copy_tofrom_user(to, from, n);
-	return n;
-}
-
-EXPORT_SYMBOL(copy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(copy_in_user);
-
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index cc332608e656..65bb8f33b399 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -638,6 +638,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 	unsigned long psize = batch->psize;
 	int ssize = batch->ssize;
 	int i;
+	unsigned int use_local;
+
+	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+		mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
 
 	local_irq_save(flags);
 
@@ -667,8 +671,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
-	    mmu_psize_defs[psize].tlbiel && local) {
+	if (use_local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
 			vpn = batch->vpn[i];
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6aa3b76aa0d6..c22f207aa656 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -356,25 +356,48 @@ static void early_check_vec5(void)
 	unsigned long root, chosen;
 	int size;
 	const u8 *vec5;
+	u8 mmu_supported;
 
 	root = of_get_flat_dt_root();
 	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
-	if (chosen == -FDT_ERR_NOTFOUND)
+	if (chosen == -FDT_ERR_NOTFOUND) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 		return;
+	}
 	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
-	if (!vec5)
+	if (!vec5) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 		return;
-	if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
-	    !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
-		/* Hypervisor doesn't support radix */
+	}
+	if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
 		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+		return;
+	}
+
+	/* Check for supported configuration */
+	mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+			OV5_FEAT(OV5_MMU_SUPPORT);
+	if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+		/* Hypervisor only supports radix - check enabled && GTSE */
+		if (!early_radix_enabled()) {
+			pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+						OV5_FEAT(OV5_RADIX_GTSE))) {
+			pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+		}
+		/* Do radix anyway - the hypervisor said we had to */
+		cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	} else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
+		/* Hypervisor only supports hash - disable radix */
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+	}
 }
 
 void __init mmu_early_init_devtree(void)
 {
 	/* Disable radix mode based on kernel command line. */
-	/* We don't yet have the machinery to do radix as a guest. */
-	if (disable_radix || !(mfmsr() & MSR_HV))
+	if (disable_radix)
 		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 
 	/*
@@ -383,7 +406,7 @@ void __init mmu_early_init_devtree(void)
 	 * even though the ibm,architecture-vec-5 property created by
 	 * skiboot doesn't have the necessary bits set.
 	 */
-	if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
 	if (early_radix_enabled())
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 2a590a98e652..c28165d8970b 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void)
 	 */
 	register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
 	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
+	asm volatile("ptesync" : : : "memory");
+	asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 
 static void __init radix_init_partition_table(void)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 595dd718ea87..2ff13249f87a 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -188,6 +188,8 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 			sdsync = POWER7P_MMCRA_SDAR_VALID;
 		else if (ppmu->flags & PPMU_ALT_SIPR)
 			sdsync = POWER6_MMCRA_SDSYNC;
+		else if (ppmu->flags & PPMU_NO_SIAR)
+			sdsync = MMCRA_SAMPLE_ENABLE;
 		else
 			sdsync = MMCRA_SDSYNC;
 
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index e79fb5fb817d..cd951fd231c4 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -65,12 +65,41 @@ static bool is_event_valid(u64 event)
 	return !(event & ~valid_mask);
 }
 
-static u64 mmcra_sdar_mode(u64 event)
+static inline bool is_event_marked(u64 event)
 {
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+	if (event & EVENT_IS_MARKED)
+		return true;
+
+	return false;
+}
 
-	return MMCRA_SDAR_MODE_TLB;
+static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
+{
+	/*
+	 * MMCRA[SDAR_MODE] specifices how the SDAR should be updated in
+	 * continous sampling mode.
+	 *
+	 * Incase of Power8:
+	 * MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling
+	 * mode and will be un-changed when setting MMCRA[63] (Marked events).
+	 *
+	 * Incase of Power9:
+	 * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
+	 *               or if group already have any marked events.
+	 * Non-Marked events (for DD1):
+	 *	MMCRA[SDAR_MODE] will be set to 0b01
+	 * For rest
+	 *	MMCRA[SDAR_MODE] will be set from event code.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
+			*mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
+		else if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+			*mmcra |=  p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+		else if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			*mmcra |= MMCRA_SDAR_MODE_TLB;
+	} else
+		*mmcra |= MMCRA_SDAR_MODE_TLB;
 }
 
 static u64 thresh_cmp_val(u64 value)
@@ -180,7 +209,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
 		value |= CNST_L1_QUAL_VAL(cache);
 	}
 
-	if (event & EVENT_IS_MARKED) {
+	if (is_event_marked(event)) {
 		mask  |= CNST_SAMPLE_MASK;
 		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
 	}
@@ -276,7 +305,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
 		}
 
 		/* In continuous sampling mode, update SDAR on TLB miss */
-		mmcra |= mmcra_sdar_mode(event[i]);
+		mmcra_sdar_mode(event[i], &mmcra);
 
 		if (event[i] & EVENT_IS_L1) {
 			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
@@ -285,7 +314,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
 			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
 		}
 
-		if (event[i] & EVENT_IS_MARKED) {
+		if (is_event_marked(event[i])) {
 			mmcra |= MMCRA_SAMPLE_ENABLE;
 
 			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index cf9bd8990159..899210f14ee4 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -246,6 +246,7 @@
 #define MMCRA_THR_CMP_SHIFT		32
 #define MMCRA_SDAR_MODE_SHIFT		42
 #define MMCRA_SDAR_MODE_TLB		(1ull << MMCRA_SDAR_MODE_SHIFT)
+#define MMCRA_SDAR_MODE_NO_UPDATES	~(0x3ull << MMCRA_SDAR_MODE_SHIFT)
 #define MMCRA_IFM_SHIFT			30
 
 /* MMCR1 Threshold Compare bit constant for power9 */
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6693f75e93d1..da8a0f7a035c 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -39,8 +39,8 @@ opal_tracepoint_refcount:
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r12,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r12,0;						\
+	ld	r11,opal_tracepoint_refcount@toc(r2);		\
+	cmpdi	r11,0;						\
 	bne-	LABEL;						\
 1:
 
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 86d9fde93c17..e0f856bfbfe8 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs,
 					struct machine_check_event *evt)
 {
 	int recovered = 0;
-	uint64_t ea = get_mce_fault_addr(evt);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
@@ -404,26 +403,18 @@ static int opal_recover_mce(struct pt_regs *regs,
 	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */
 		recovered = 1;
-	} else if (ea && !is_kernel_addr(ea)) {
+	} else if (evt->severity == MCE_SEV_FATAL) {
+		/* Fatal machine check */
+		pr_err("Machine check interrupt is fatal\n");
+		recovered = 0;
+	} else if ((evt->severity == MCE_SEV_ERROR_SYNC) &&
+			(user_mode(regs) && !is_global_init(current))) {
 		/*
-		 * Faulting address is not in kernel text. We should be fine.
-		 * We need to find which process uses this address.
 		 * For now, kill the task if we have received exception when
 		 * in userspace.
 		 *
 		 * TODO: Queue up this address for hwpoisioning later.
 		 */
-		if (user_mode(regs) && !is_global_init(current)) {
-			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
-			recovered = 1;
-		} else
-			recovered = 0;
-	} else if (user_mode(regs) && !is_global_init(current) &&
-		evt->severity == MCE_SEV_ERROR_SYNC) {
-		/*
-		 * If we have received a synchronous error when in userspace
-		 * kill the task.
-		 */
 		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
 		recovered = 1;
 	}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 6901a06da2f9..e36738291c32 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1775,17 +1775,20 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
-				   struct pci_bus *bus)
+				   struct pci_bus *bus,
+				   bool add_to_group)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
 		set_dma_offset(&dev->dev, pe->tce_bypass_base);
-		iommu_add_device(&dev->dev);
+		if (add_to_group)
+			iommu_add_device(&dev->dev);
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
+					add_to_group);
 	}
 }
 
@@ -2191,7 +2194,7 @@ found:
 		set_iommu_table_base(&pe->pdev->dev, tbl);
 		iommu_add_device(&pe->pdev->dev);
 	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 
 	return;
  fail:
@@ -2426,6 +2429,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 
 	pnv_pci_ioda2_set_bypass(pe, false);
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+	if (pe->pbus)
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 	pnv_ioda2_table_free(tbl);
 }
 
@@ -2435,6 +2440,8 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
 						table_group);
 
 	pnv_pci_ioda2_setup_default_config(pe);
+	if (pe->pbus)
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 }
 
 static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
@@ -2624,6 +2631,9 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 	level_shift = entries_shift + 3;
 	level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
 
+	if ((level_shift - 3) * levels + page_shift >= 60)
+		return -EINVAL;
+
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
 			levels, tce_table_size, &offset, &total_allocated);
@@ -2728,7 +2738,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	if (pe->flags & PNV_IODA_PE_DEV)
 		iommu_add_device(&pe->pdev->dev);
 	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 }
 
 #ifdef CONFIG_PCI_MSI
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 251060cf1713..8b1fe895daa3 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -751,7 +751,9 @@ void __init hpte_init_pseries(void)
 	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
 	mmu_hash_ops.hpte_clear_all      = pseries_hpte_clear_all;
 	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
-	mmu_hash_ops.resize_hpt		 = pseries_lpar_resize_hpt;
+
+	if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
+		mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
 }
 
 void radix_init_pseries(void)
diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S
index f9760ccf4032..3696ea6c4826 100644
--- a/arch/powerpc/purgatory/trampoline.S
+++ b/arch/powerpc/purgatory/trampoline.S
@@ -116,13 +116,13 @@ dt_offset:
 
 	.data
 	.balign 8
-.globl sha256_digest
-sha256_digest:
+.globl purgatory_sha256_digest
+purgatory_sha256_digest:
 	.skip	32
-	.size sha256_digest, . - sha256_digest
+	.size purgatory_sha256_digest, . - purgatory_sha256_digest
 
 	.balign 8
-.globl sha_regions
-sha_regions:
+.globl purgatory_sha_regions
+purgatory_sha_regions:
 	.skip	8 * 2 * 16
-	.size sha_regions, . - sha_regions
+	.size purgatory_sha_regions, . - purgatory_sha_regions
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ada29eaed6e2..f523ac883150 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -274,7 +274,9 @@ failed:
 			if (bank->disk->major > 0)
 				unregister_blkdev(bank->disk->major,
 						bank->disk->disk_name);
-			del_gendisk(bank->disk);
+			if (bank->disk->flags & GENHD_FL_UP)
+				del_gendisk(bank->disk);
+			put_disk(bank->disk);
 		}
 		device->dev.platform_data = NULL;
 		if (bank->io_addr != 0)
@@ -299,6 +301,7 @@ axon_ram_remove(struct platform_device *device)
 	device_remove_file(&device->dev, &dev_attr_ecc);
 	free_irq(bank->irq_id, device);
 	del_gendisk(bank->disk);
+	put_disk(bank->disk);
 	iounmap((void __iomem *) bank->io_addr);
 	kfree(bank);
 
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index f9670eabfcfa..b53f80f0b4d8 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void)
 
 static void icp_opal_set_cpu_priority(unsigned char cppr)
 {
+	/*
+	 * Here be dragons. The caller has asked to allow only IPI's and not
+	 * external interrupts. But OPAL XIVE doesn't support that. So instead
+	 * of allowing no interrupts allow all. That's still not right, but
+	 * currently the only caller who does this is xics_migrate_irqs_away()
+	 * and it works in that case.
+	 */
+	if (cppr >= DEFAULT_PRIORITY)
+		cppr = LOWEST_PRIORITY;
+
 	xics_set_base_cppr(cppr);
 	opal_int_set_cppr(cppr);
 	iosync();
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 69d858e51ac7..23efe4e42172 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/delay.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void)
 	/* Remove ourselves from the global interrupt queue */
 	xics_set_cpu_giq(xics_default_distrib_server, 0);
 
-	/* Allow IPIs again... */
-	icp_ops->set_priority(DEFAULT_PRIORITY);
-
 	for_each_irq_desc(virq, desc) {
 		struct irq_chip *chip;
 		long server;
@@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void)
 unlock:
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
+
+	/* Allow "sufficient" time to drop any inflight IRQ's */
+	mdelay(5);
+
+	/*
+	 * Allow IPIs again. This is done at the very end, after migrating all
+	 * interrupts, the expectation is that we'll only get woken up by an IPI
+	 * interrupt beyond this point, but leave externals masked just to be
+	 * safe. If we're using icp-opal this may actually allow all
+	 * interrupts anyway, but that should be OK.
+	 */
+	icp_ops->set_priority(DEFAULT_PRIORITY);
+
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index e256592eb66e..eae2c64cf69d 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -1,7 +1,7 @@
 obj-y				+= kernel/
 obj-y				+= mm/
 obj-$(CONFIG_KVM)		+= kvm/
-obj-$(CONFIG_CRYPTO_HW)		+= crypto/
+obj-y				+= crypto/
 obj-$(CONFIG_S390_HYPFS_FS)	+= hypfs/
 obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
 obj-y				+= net/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a2dcef0aacc7..e161fafb495b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -105,6 +105,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
@@ -123,8 +124,6 @@ config S390
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_ARCH_EARLY_PFN_TO_NID
-	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_JUMP_LABEL
 	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER
@@ -507,6 +506,21 @@ source kernel/Kconfig.preempt
 
 source kernel/Kconfig.hz
 
+config ARCH_RANDOM
+	def_bool y
+	prompt "s390 architectural random number generation API"
+	help
+	  Enable the s390 architectural random number generation API
+	  to provide random data for all consumers within the Linux
+	  kernel.
+
+	  When enabled the arch_random_* functions declared in linux/random.h
+	  are implemented. The implementation is based on the s390 CPACF
+	  instruction subfunction TRNG which provides a real true random
+	  number generator.
+
+	  If unsure, say Y.
+
 endmenu
 
 menu "Memory setup"
@@ -537,6 +551,16 @@ config FORCE_MAX_ZONEORDER
 
 source "mm/Kconfig"
 
+config MAX_PHYSMEM_BITS
+	int "Maximum size of supported physical memory in bits (42-53)"
+	range 42 53
+	default "46"
+	help
+	  This option specifies the maximum supported size of physical memory
+	  in bits. Supported is any size between 2^42 (4TB) and 2^53 (8PB).
+	  Increasing the number of bits also increases the kernel image size.
+	  By default 46 bits (64TB) are supported.
+
 config PACK_STACK
 	def_bool y
 	prompt "Pack kernel stack"
@@ -614,7 +638,7 @@ if PCI
 config PCI_NR_FUNCTIONS
 	int "Maximum number of PCI functions (1-4096)"
 	range 1 4096
-	default "64"
+	default "128"
 	help
 	  This allows you to specify the maximum number of PCI functions which
 	  this kernel will support.
@@ -672,6 +696,16 @@ config EADM_SCH
 	  To compile this driver as a module, choose M here: the
 	  module will be called eadm_sch.
 
+config VFIO_CCW
+	def_tristate n
+	prompt "Support for VFIO-CCW subchannels"
+	depends on S390_CCW_IOMMU && VFIO_MDEV
+	help
+	  This driver allows usage of I/O subchannels via VFIO-CCW.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called vfio_ccw.
+
 endmenu
 
 menu "Dump support"
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index fa95041fa9f6..33ca29333e18 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -141,31 +141,34 @@ static void check_ipl_parmblock(void *start, unsigned long size)
 
 unsigned long decompress_kernel(void)
 {
-	unsigned long output_addr;
-	unsigned char *output;
+	void *output, *kernel_end;
 
-	output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
-	check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start);
-	memset(&_bss, 0, &_ebss - &_bss);
-	free_mem_ptr = (unsigned long)&_end;
-	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
-	output = (unsigned char *) output_addr;
+	output = (void *) ALIGN((unsigned long) &_end + HEAP_SIZE, PAGE_SIZE);
+	kernel_end = output + SZ__bss_start;
+	check_ipl_parmblock((void *) 0, (unsigned long) kernel_end);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/*
 	 * Move the initrd right behind the end of the decompressed
-	 * kernel image.
+	 * kernel image. This also prevents initrd corruption caused by
+	 * bss clearing since kernel_end will always be located behind the
+	 * current bss section..
 	 */
-	if (INITRD_START && INITRD_SIZE &&
-	    INITRD_START < (unsigned long) output + SZ__bss_start) {
-		check_ipl_parmblock(output + SZ__bss_start,
-				    INITRD_START + INITRD_SIZE);
-		memmove(output + SZ__bss_start,
-			(void *) INITRD_START, INITRD_SIZE);
-		INITRD_START = (unsigned long) output + SZ__bss_start;
+	if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) {
+		check_ipl_parmblock(kernel_end, INITRD_SIZE);
+		memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE);
+		INITRD_START = (unsigned long) kernel_end;
 	}
 #endif
 
+	/*
+	 * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be
+	 * initialized afterwards since they reside in bss.
+	 */
+	memset(&_bss, 0, &_ebss - &_bss);
+	free_mem_ptr = (unsigned long) &_end;
+	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+
 	puts("Uncompressing Linux... ");
 	__decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);
 	puts("Ok, booting the kernel.\n");
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 143b1e00b818..a5039fa89314 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -73,6 +73,7 @@ CONFIG_ZSWAP=y
 CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
+CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_PCI=y
 CONFIG_PCI_DEBUG=y
@@ -609,7 +610,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index f05d2d6e1087..83970b5afb2b 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -72,6 +72,7 @@ CONFIG_ZSWAP=y
 CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
+CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_PCI=y
 CONFIG_HOTPLUG_PCI=y
@@ -560,7 +561,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 2358bf33c5ef..fbc6542aaf59 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -70,6 +70,7 @@ CONFIG_ZSWAP=y
 CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
+CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_PCI=y
 CONFIG_HOTPLUG_PCI=y
@@ -558,7 +559,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 4366a3e3e754..e23d97c13735 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -35,7 +35,6 @@ CONFIG_SCSI_ENCLOSURE=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_SRP_ATTRS=y
 CONFIG_ZFCP=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile
index 402c530c6da5..678d9863e3f0 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -10,5 +10,6 @@ obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o paes_s390.o
 obj-$(CONFIG_S390_PRNG) += prng.o
 obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o
 obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o
+obj-$(CONFIG_ARCH_RANDOM) += arch_random.o
 
 crc32-vx_s390-y := crc32-vx.o crc32le-vx.o crc32be-vx.o
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
new file mode 100644
index 000000000000..9317b3e645e2
--- /dev/null
+++ b/arch/s390/crypto/arch_random.c
@@ -0,0 +1,31 @@
+/*
+ * s390 arch random implementation.
+ *
+ * Copyright IBM Corp. 2017
+ * Author(s): Harald Freudenberger <freude@de.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+#include <linux/static_key.h>
+#include <asm/cpacf.h>
+
+DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
+
+atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0);
+EXPORT_SYMBOL(s390_arch_random_counter);
+
+static int __init s390_arch_random_init(void)
+{
+	/* check if subfunction CPACF_PRNO_TRNG is available */
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		static_branch_enable(&s390_arch_random_available);
+
+	return 0;
+}
+arch_initcall(s390_arch_random_init);
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index d69ea495c4d7..a4e903ed7e21 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -474,8 +474,11 @@ static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 			ret = blkcipher_walk_done(desc, walk, nbytes - n);
 		}
 		if (k < n) {
-			if (__ctr_paes_set_key(ctx) != 0)
+			if (__ctr_paes_set_key(ctx) != 0) {
+				if (locked)
+					spin_unlock(&ctrblk_lock);
 				return blkcipher_walk_done(desc, walk, -EIO);
+			}
 		}
 	}
 	if (locked)
@@ -613,7 +616,7 @@ out_err:
 module_init(paes_s390_init);
 module_exit(paes_s390_fini);
 
-MODULE_ALIAS_CRYPTO("aes-all");
+MODULE_ALIAS_CRYPTO("paes");
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm with protected keys");
 MODULE_LICENSE("GPL");
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 5a3ec04a7082..3e47c4a0f18b 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -81,7 +81,7 @@ struct prng_ws_s {
 	u64 byte_counter;
 };
 
-struct ppno_ws_s {
+struct prno_ws_s {
 	u32 res;
 	u32 reseed_counter;
 	u64 stream_bytes;
@@ -93,7 +93,7 @@ struct prng_data_s {
 	struct mutex mutex;
 	union {
 		struct prng_ws_s prngws;
-		struct ppno_ws_s ppnows;
+		struct prno_ws_s prnows;
 	};
 	u8 *buf;
 	u32 rest;
@@ -306,12 +306,12 @@ static int __init prng_sha512_selftest(void)
 		0x36, 0x8c, 0x5a, 0x9f, 0x7a, 0x4b, 0x3e, 0xe2 };
 
 	u8 buf[sizeof(random)];
-	struct ppno_ws_s ws;
+	struct prno_ws_s ws;
 
 	memset(&ws, 0, sizeof(ws));
 
 	/* initial seed */
-	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED,
+	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
 		   &ws, NULL, 0, seed, sizeof(seed));
 
 	/* check working states V and C */
@@ -324,9 +324,9 @@ static int __init prng_sha512_selftest(void)
 	}
 
 	/* generate random bytes */
-	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN,
+	cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
 		   &ws, buf, sizeof(buf), NULL, 0);
-	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN,
+	cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
 		   &ws, buf, sizeof(buf), NULL, 0);
 
 	/* check against expected data */
@@ -374,16 +374,16 @@ static int __init prng_sha512_instantiate(void)
 	/* followed by 16 bytes of unique nonce */
 	get_tod_clock_ext(seed + 64 + 32);
 
-	/* initial seed of the ppno drng */
-	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED,
-		   &prng_data->ppnows, NULL, 0, seed, sizeof(seed));
+	/* initial seed of the prno drng */
+	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
+		   &prng_data->prnows, NULL, 0, seed, sizeof(seed));
 
 	/* if fips mode is enabled, generate a first block of random
 	   bytes for the FIPS 140-2 Conditional Self Test */
 	if (fips_enabled) {
 		prng_data->prev = prng_data->buf + prng_chunk_size;
-		cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN,
-			   &prng_data->ppnows,
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
+			   &prng_data->prnows,
 			   prng_data->prev, prng_chunk_size, NULL, 0);
 	}
 
@@ -412,9 +412,9 @@ static int prng_sha512_reseed(void)
 	if (ret != sizeof(seed))
 		return ret;
 
-	/* do a reseed of the ppno drng with this bytestring */
-	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED,
-		   &prng_data->ppnows, NULL, 0, seed, sizeof(seed));
+	/* do a reseed of the prno drng with this bytestring */
+	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
+		   &prng_data->prnows, NULL, 0, seed, sizeof(seed));
 
 	return 0;
 }
@@ -425,15 +425,15 @@ static int prng_sha512_generate(u8 *buf, size_t nbytes)
 	int ret;
 
 	/* reseed needed ? */
-	if (prng_data->ppnows.reseed_counter > prng_reseed_limit) {
+	if (prng_data->prnows.reseed_counter > prng_reseed_limit) {
 		ret = prng_sha512_reseed();
 		if (ret)
 			return ret;
 	}
 
-	/* PPNO generate */
-	cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN,
-		   &prng_data->ppnows, buf, nbytes, NULL, 0);
+	/* PRNO generate */
+	cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
+		   &prng_data->prnows, buf, nbytes, NULL, 0);
 
 	/* FIPS 140-2 Conditional Self Test */
 	if (fips_enabled) {
@@ -653,7 +653,7 @@ static ssize_t prng_counter_show(struct device *dev,
 	if (mutex_lock_interruptible(&prng_data->mutex))
 		return -ERESTARTSYS;
 	if (prng_mode == PRNG_MODE_SHA512)
-		counter = prng_data->ppnows.stream_bytes;
+		counter = prng_data->prnows.stream_bytes;
 	else
 		counter = prng_data->prngws.byte_counter;
 	mutex_unlock(&prng_data->mutex);
@@ -774,8 +774,8 @@ static int __init prng_init(void)
 
 	/* choose prng mode */
 	if (prng_mode != PRNG_MODE_TDES) {
-		/* check for MSA5 support for PPNO operations */
-		if (!cpacf_query_func(CPACF_PPNO, CPACF_PPNO_SHA512_DRNG_GEN)) {
+		/* check for MSA5 support for PRNO operations */
+		if (!cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) {
 			if (prng_mode == PRNG_MODE_SHA512) {
 				pr_err("The prng module cannot "
 				       "start in SHA-512 mode\n");
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 68bfd09f1b02..97189dbaf34b 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -179,7 +179,7 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_KPROBES_SANITY_TEST=y
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 8aea32fe8bd2..7e3481eb2174 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,8 +1,14 @@
 generic-y += asm-offsets.h
 generic-y += clkdev.h
 generic-y += dma-contiguous.h
+generic-y += div64.h
+generic-y += emergency-restart.h
 generic-y += export.h
+generic-y += irq_regs.h
 generic-y += irq_work.h
+generic-y += kmap_types.h
+generic-y += local.h
+generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += preempt.h
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
new file mode 100644
index 000000000000..6033901a40b2
--- /dev/null
+++ b/arch/s390/include/asm/archrandom.h
@@ -0,0 +1,69 @@
+/*
+ * Kernel interface for the s390 arch_random_* functions
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author: Harald Freudenberger <freude@de.ibm.com>
+ *
+ */
+
+#ifndef _ASM_S390_ARCHRANDOM_H
+#define _ASM_S390_ARCHRANDOM_H
+
+#ifdef CONFIG_ARCH_RANDOM
+
+#include <linux/static_key.h>
+#include <linux/atomic.h>
+#include <asm/cpacf.h>
+
+DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
+extern atomic64_t s390_arch_random_counter;
+
+static void s390_arch_random_generate(u8 *buf, unsigned int nbytes)
+{
+	cpacf_trng(NULL, 0, buf, nbytes);
+	atomic64_add(nbytes, &s390_arch_random_counter);
+}
+
+static inline bool arch_has_random(void)
+{
+	if (static_branch_likely(&s390_arch_random_available))
+		return true;
+	return false;
+}
+
+static inline bool arch_has_random_seed(void)
+{
+	return arch_has_random();
+}
+
+static inline bool arch_get_random_long(unsigned long *v)
+{
+	if (static_branch_likely(&s390_arch_random_available)) {
+		s390_arch_random_generate((u8 *)v, sizeof(*v));
+		return true;
+	}
+	return false;
+}
+
+static inline bool arch_get_random_int(unsigned int *v)
+{
+	if (static_branch_likely(&s390_arch_random_available)) {
+		s390_arch_random_generate((u8 *)v, sizeof(*v));
+		return true;
+	}
+	return false;
+}
+
+static inline bool arch_get_random_seed_long(unsigned long *v)
+{
+	return arch_get_random_long(v);
+}
+
+static inline bool arch_get_random_seed_int(unsigned int *v)
+{
+	return arch_get_random_int(v);
+}
+
+#endif /* CONFIG_ARCH_RANDOM */
+#endif /* _ASM_S390_ARCHRANDOM_H */
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index ac9e2b939d04..ba6d29412344 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -111,20 +111,22 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr")
 
 static inline int __atomic_cmpxchg(int *ptr, int old, int new)
 {
-	asm volatile(
-		"	cs	%[old],%[new],%[ptr]"
-		: [old] "+d" (old), [ptr] "+Q" (*ptr)
-		: [new] "d" (new) : "cc", "memory");
-	return old;
+	return __sync_val_compare_and_swap(ptr, old, new);
+}
+
+static inline int __atomic_cmpxchg_bool(int *ptr, int old, int new)
+{
+	return __sync_bool_compare_and_swap(ptr, old, new);
 }
 
 static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
 {
-	asm volatile(
-		"	csg	%[old],%[new],%[ptr]"
-		: [old] "+d" (old), [ptr] "+Q" (*ptr)
-		: [new] "d" (new) : "cc", "memory");
-	return old;
+	return __sync_val_compare_and_swap(ptr, old, new);
+}
+
+static inline long __atomic64_cmpxchg_bool(long *ptr, long old, long new)
+{
+	return __sync_bool_compare_and_swap(ptr, old, new);
 }
 
 #endif /* __ARCH_S390_ATOMIC_OPS__  */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index d92047da5ccb..99902b7b9f0c 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -15,14 +15,6 @@
  * end up numbered:
  *   |63..............0|127............64|191...........128|255...........192|
  *
- * There are a few little-endian macros used mostly for filesystem
- * bitmaps, these work on similar bit array layouts, but byte-oriented:
- *   |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
- *
- * The main difference is that bit 3-5 in the bit number field needs to be
- * reversed compared to the big-endian bit fields. This can be achieved by
- * XOR with 0x38.
- *
  * We also have special functions which work with an MSB0 encoding.
  * The bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
@@ -253,6 +245,11 @@ unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size);
 unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size,
 				unsigned long offset);
 
+#define for_each_set_bit_inv(bit, addr, size)				\
+	for ((bit) = find_first_bit_inv((addr), (size));		\
+	     (bit) < (size);						\
+	     (bit) = find_next_bit_inv((addr), (size), (bit) + 1))
+
 static inline void set_bit_inv(unsigned long nr, volatile unsigned long *ptr)
 {
 	return set_bit(nr ^ (BITS_PER_LONG - 1), ptr);
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index bf90d1fd97a5..1bbd9dbfe4e0 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -46,8 +46,8 @@
 	unreachable();					\
 } while (0)
 
-#define __WARN_TAINT(taint) do {			\
-	__EMIT_BUG(BUGFLAG_TAINT(taint));		\
+#define __WARN_FLAGS(flags) do {			\
+	__EMIT_BUG(BUGFLAG_WARNING|(flags));		\
 } while (0)
 
 #define WARN_ON(x) ({					\
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index f7ed88cc066e..7a38ca85190b 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -33,6 +33,24 @@ struct ccw1 {
 	__u32 cda;
 } __attribute__ ((packed,aligned(8)));
 
+/**
+ * struct ccw0 - channel command word
+ * @cmd_code: command code
+ * @cda: data address
+ * @flags: flags, like IDA addressing, etc.
+ * @reserved: will be ignored
+ * @count: byte count
+ *
+ * The format-0 ccw structure.
+ */
+struct ccw0 {
+	__u8 cmd_code;
+	__u32 cda : 24;
+	__u8  flags;
+	__u8  reserved;
+	__u16 count;
+} __packed __aligned(8);
+
 #define CCW_FLAG_DC		0x80
 #define CCW_FLAG_CC		0x40
 #define CCW_FLAG_SLI		0x20
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index e2dfbf280d12..e06f2556b316 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -25,7 +25,8 @@
 #define CPACF_KMO		0xb92b		/* MSA4 */
 #define CPACF_PCC		0xb92c		/* MSA4 */
 #define CPACF_KMCTR		0xb92d		/* MSA4 */
-#define CPACF_PPNO		0xb93c		/* MSA5 */
+#define CPACF_PRNO		0xb93c		/* MSA5 */
+#define CPACF_KMA		0xb929		/* MSA8 */
 
 /*
  * En/decryption modifier bits
@@ -123,12 +124,14 @@
 #define CPACF_PCKMO_ENC_AES_256_KEY	0x14
 
 /*
- * Function codes for the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION)
+ * Function codes for the PRNO (PERFORM RANDOM NUMBER OPERATION)
  * instruction
  */
-#define CPACF_PPNO_QUERY		0x00
-#define CPACF_PPNO_SHA512_DRNG_GEN	0x03
-#define CPACF_PPNO_SHA512_DRNG_SEED	0x83
+#define CPACF_PRNO_QUERY		0x00
+#define CPACF_PRNO_SHA512_DRNG_GEN	0x03
+#define CPACF_PRNO_SHA512_DRNG_SEED	0x83
+#define CPACF_PRNO_TRNG_Q_R2C_RATIO	0x70
+#define CPACF_PRNO_TRNG			0x72
 
 typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
 
@@ -149,8 +152,8 @@ static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
 
 	asm volatile(
 		"	spm 0\n" /* pckmo doesn't change the cc */
-		/* Parameter registers are ignored, but may not be 0 */
-		"0:	.insn	rrf,%[opc] << 16,2,2,2,0\n"
+		/* Parameter regs are ignored, but must be nonzero and unique */
+		"0:	.insn	rrf,%[opc] << 16,2,4,6,0\n"
 		"	brc	1,0b\n"	/* handle partial completion */
 		: "=m" (*mask)
 		: [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (opcode)
@@ -173,7 +176,7 @@ static inline int __cpacf_check_opcode(unsigned int opcode)
 	case CPACF_PCC:
 	case CPACF_KMCTR:
 		return test_facility(77);	/* check for MSA4 */
-	case CPACF_PPNO:
+	case CPACF_PRNO:
 		return test_facility(57);	/* check for MSA5 */
 	default:
 		BUG();
@@ -373,18 +376,18 @@ static inline int cpacf_kmctr(unsigned long func, void *param, u8 *dest,
 }
 
 /**
- * cpacf_ppno() - executes the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION)
+ * cpacf_prno() - executes the PRNO (PERFORM RANDOM NUMBER OPERATION)
  *		  instruction
- * @func: the function code passed to PPNO; see CPACF_PPNO_xxx defines
+ * @func: the function code passed to PRNO; see CPACF_PRNO_xxx defines
  * @param: address of parameter block; see POP for details on each func
  * @dest: address of destination memory area
  * @dest_len: size of destination memory area in bytes
  * @seed: address of seed data
  * @seed_len: size of seed data in bytes
  */
-static inline void cpacf_ppno(unsigned long func, void *param,
-			      u8 *dest, long dest_len,
-			      const u8 *seed, long seed_len)
+static inline void cpacf_prno(unsigned long func, void *param,
+			      u8 *dest, unsigned long dest_len,
+			      const u8 *seed, unsigned long seed_len)
 {
 	register unsigned long r0 asm("0") = (unsigned long) func;
 	register unsigned long r1 asm("1") = (unsigned long) param;
@@ -398,7 +401,32 @@ static inline void cpacf_ppno(unsigned long func, void *param,
 		"	brc	1,0b\n"	  /* handle partial completion */
 		: [dst] "+a" (r2), [dlen] "+d" (r3)
 		: [fc] "d" (r0), [pba] "a" (r1),
-		  [seed] "a" (r4), [slen] "d" (r5), [opc] "i" (CPACF_PPNO)
+		  [seed] "a" (r4), [slen] "d" (r5), [opc] "i" (CPACF_PRNO)
+		: "cc", "memory");
+}
+
+/**
+ * cpacf_trng() - executes the TRNG subfunction of the PRNO instruction
+ * @ucbuf: buffer for unconditioned data
+ * @ucbuf_len: amount of unconditioned data to fetch in bytes
+ * @cbuf: buffer for conditioned data
+ * @cbuf_len: amount of conditioned data to fetch in bytes
+ */
+static inline void cpacf_trng(u8 *ucbuf, unsigned long ucbuf_len,
+			      u8 *cbuf, unsigned long cbuf_len)
+{
+	register unsigned long r0 asm("0") = (unsigned long) CPACF_PRNO_TRNG;
+	register unsigned long r2 asm("2") = (unsigned long) ucbuf;
+	register unsigned long r3 asm("3") = (unsigned long) ucbuf_len;
+	register unsigned long r4 asm("4") = (unsigned long) cbuf;
+	register unsigned long r5 asm("5") = (unsigned long) cbuf_len;
+
+	asm volatile (
+		"0:	.insn	rre,%[opc] << 16,%[ucbuf],%[cbuf]\n"
+		"	brc	1,0b\n"	  /* handle partial completion */
+		: [ucbuf] "+a" (r2), [ucbuflen] "+d" (r3),
+		  [cbuf] "+a" (r4), [cbuflen] "+d" (r5)
+		: [fc] "d" (r0), [opc] "i" (CPACF_PRNO)
 		: "cc", "memory");
 }
 
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index d1e0707310fd..05480e4cc5ca 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -20,9 +20,11 @@
 #define CPU_MF_INT_SF_PRA	(1 << 29)	/* program request alert */
 #define CPU_MF_INT_SF_SACA	(1 << 23)	/* sampler auth. change alert */
 #define CPU_MF_INT_SF_LSDA	(1 << 22)	/* loss of sample data alert */
+#define CPU_MF_INT_CF_MTDA	(1 << 15)	/* loss of MT ctr. data alert */
 #define CPU_MF_INT_CF_CACA	(1 <<  7)	/* counter auth. change alert */
 #define CPU_MF_INT_CF_LCDA	(1 <<  6)	/* loss of counter data alert */
-#define CPU_MF_INT_CF_MASK	(CPU_MF_INT_CF_CACA|CPU_MF_INT_CF_LCDA)
+#define CPU_MF_INT_CF_MASK	(CPU_MF_INT_CF_MTDA|CPU_MF_INT_CF_CACA| \
+				 CPU_MF_INT_CF_LCDA)
 #define CPU_MF_INT_SF_MASK	(CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE|	\
 				 CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA|	\
 				 CPU_MF_INT_SF_LSDA)
@@ -172,7 +174,7 @@ static inline int lcctl(u64 ctl)
 /* Extract CPU counter */
 static inline int __ecctr(u64 ctr, u64 *content)
 {
-	register u64 _content asm("4") = 0;
+	u64 _content;
 	int cc;
 
 	asm volatile (
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index d1c407ddf703..9072bf63a846 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -8,31 +8,27 @@
 #define _S390_CPUTIME_H
 
 #include <linux/types.h>
-#include <asm/div64.h>
+#include <asm/timex.h>
 
 #define CPUTIME_PER_USEC 4096ULL
 #define CPUTIME_PER_SEC (CPUTIME_PER_USEC * USEC_PER_SEC)
 
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 
-typedef unsigned long long __nocast cputime_t;
-typedef unsigned long long __nocast cputime64_t;
-
 #define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
 
-static inline unsigned long __div(unsigned long long n, unsigned long base)
-{
-	return n / base;
-}
-
 /*
- * Convert cputime to microseconds and back.
+ * Convert cputime to microseconds.
  */
-static inline unsigned int cputime_to_usecs(const cputime_t cputime)
+static inline u64 cputime_to_usecs(const u64 cputime)
 {
-	return (__force unsigned long long) cputime >> 12;
+	return cputime >> 12;
 }
 
+/*
+ * Convert cputime to nanoseconds.
+ */
+#define cputime_to_nsecs(cputime) tod_to_ns(cputime)
 
 u64 arch_cpu_idle_time(int cpu);
 
diff --git a/arch/s390/include/asm/div64.h b/arch/s390/include/asm/div64.h
deleted file mode 100644
index 6cd978cefb28..000000000000
--- a/arch/s390/include/asm/div64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/div64.h>
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 1d48880b3cc1..e8f623041769 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -105,6 +105,7 @@
 #define HWCAP_S390_VXRS		2048
 #define HWCAP_S390_VXRS_BCD	4096
 #define HWCAP_S390_VXRS_EXT	8192
+#define HWCAP_S390_GS		16384
 
 /* Internal bits, not exposed via elf */
 #define HWCAP_INT_SIE		1UL
diff --git a/arch/s390/include/asm/emergency-restart.h b/arch/s390/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/arch/s390/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h
new file mode 100644
index 000000000000..16cfe2d62eeb
--- /dev/null
+++ b/arch/s390/include/asm/extable.h
@@ -0,0 +1,28 @@
+#ifndef __S390_EXTABLE_H
+#define __S390_EXTABLE_H
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	int insn, fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->fixup + x->fixup;
+}
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#endif
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 09b406db7529..cb60d5c5755d 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -8,14 +8,11 @@
 #define __ASM_FACILITY_H
 
 #include <generated/facilities.h>
-
-#ifndef __ASSEMBLY__
-
 #include <linux/string.h>
 #include <linux/preempt.h>
 #include <asm/lowcore.h>
 
-#define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
+#define MAX_FACILITY_BIT (sizeof(((struct lowcore *)0)->stfle_fac_list) * 8)
 
 static inline int __test_facility(unsigned long nr, void *facilities)
 {
@@ -72,5 +69,4 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	preempt_enable();
 }
 
-#endif /* __ASSEMBLY__ */
 #endif /* __ASM_FACILITY_H */
diff --git a/arch/s390/include/asm/irq_regs.h b/arch/s390/include/asm/irq_regs.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/arch/s390/include/asm/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/s390/include/asm/isc.h b/arch/s390/include/asm/isc.h
index 68d7d68300f2..8a0b721a9b8d 100644
--- a/arch/s390/include/asm/isc.h
+++ b/arch/s390/include/asm/isc.h
@@ -16,6 +16,7 @@
 #define CONSOLE_ISC 1			/* console I/O subchannel */
 #define EADM_SCH_ISC 4			/* EADM subchannels */
 #define CHSC_SCH_ISC 7			/* CHSC subchannels */
+#define VFIO_CCW_ISC IO_SCH_ISC		/* VFIO-CCW I/O subchannels */
 /* Adapter interrupts. */
 #define QDIO_AIRQ_ISC IO_SCH_ISC	/* I/O subchannel in qdio mode */
 #define PCI_ISC 2			/* PCI I/O subchannels */
diff --git a/arch/s390/include/asm/kmap_types.h b/arch/s390/include/asm/kmap_types.h
deleted file mode 100644
index 0a88622339ee..000000000000
--- a/arch/s390/include/asm/kmap_types.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-#include <asm-generic/kmap_types.h>
-
-#endif
diff --git a/arch/s390/include/asm/local.h b/arch/s390/include/asm/local.h
deleted file mode 100644
index c11c530f74d0..000000000000
--- a/arch/s390/include/asm/local.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local.h>
diff --git a/arch/s390/include/asm/local64.h b/arch/s390/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/s390/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 61261e0e95c0..8a5b082797f8 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -157,8 +157,8 @@ struct lowcore {
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
 	__u8	pad_0x1000[0x11b0-0x1000];	/* 0x1000 */
 
-	/* Pointer to vector register save area */
-	__u64	vector_save_area_addr;		/* 0x11b0 */
+	/* Pointer to the machine check extended save area */
+	__u64	mcesad;				/* 0x11b0 */
 
 	/* 64 bit extparam used for pfault/diag 250: defined by architecture */
 	__u64	ext_params2;			/* 0x11B8 */
@@ -182,10 +182,7 @@ struct lowcore {
 
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
-	__u8	pad_0x1900[0x1c00-0x1900];	/* 0x1900 */
-
-	/* Software defined save area for vector registers */
-	__u8	vector_save_area[1024];		/* 0x1c00 */
+	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
 } __packed;
 
 #define S390_lowcore (*((struct lowcore *) 0))
diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h
index b55a59e1d134..b79813d9cf68 100644
--- a/arch/s390/include/asm/mman.h
+++ b/arch/s390/include/asm/mman.h
@@ -8,8 +8,4 @@
 
 #include <uapi/asm/mman.h>
 
-#ifndef __ASSEMBLY__
-int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags);
-#define arch_mmap_check(addr, len, flags) s390_mmap_check(addr, len, flags)
-#endif
 #endif /* __S390_MMAN_H__ */
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index bea785d7f853..bd6f30304518 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -22,6 +22,8 @@ typedef struct {
 	unsigned int has_pgste:1;
 	/* The mmu context uses storage keys. */
 	unsigned int use_skey:1;
+	/* The mmu context uses CMMA. */
+	unsigned int use_cmma:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 6e31d87fb669..8712e11bead4 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -28,6 +28,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.alloc_pgste = page_table_allocate_pgste;
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
+	mm->context.use_cmma = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case 1UL << 42:
@@ -156,10 +157,4 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	/* by default, allow everything */
 	return true;
 }
-
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
-	/* by default, allow everything */
-	return true;
-}
 #endif /* __S390_MMU_CONTEXT_H */
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
index b75fd910386a..e3e8895f5d3e 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -58,7 +58,9 @@ union mci {
 		u64 ie :  1; /* 32 indirect storage error */
 		u64 ar :  1; /* 33 access register validity */
 		u64 da :  1; /* 34 delayed access exception */
-		u64    :  7; /* 35-41 */
+		u64    :  1; /* 35 */
+		u64 gs :  1; /* 36 guarded storage registers */
+		u64    :  5; /* 37-41 */
 		u64 pr :  1; /* 42 tod programmable register validity */
 		u64 fc :  1; /* 43 fp control register validity */
 		u64 ap :  1; /* 44 ancillary report */
@@ -69,6 +71,14 @@ union mci {
 	};
 };
 
+#define MCESA_ORIGIN_MASK	(~0x3ffUL)
+#define MCESA_LC_MASK		(0xfUL)
+
+struct mcesa {
+	u8 vector_save_area[1024];
+	u8 guarded_storage_save_area[32];
+};
+
 struct pt_regs;
 
 extern void s390_handle_mcck(void);
diff --git a/arch/s390/include/asm/page-states.h b/arch/s390/include/asm/page-states.h
new file mode 100644
index 000000000000..42267a2fe29e
--- /dev/null
+++ b/arch/s390/include/asm/page-states.h
@@ -0,0 +1,19 @@
+/*
+ *    Copyright IBM Corp. 2017
+ *    Author(s): Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
+ */
+
+#ifndef PAGE_STATES_H
+#define PAGE_STATES_H
+
+#define ESSA_GET_STATE			0
+#define ESSA_SET_STABLE			1
+#define ESSA_SET_UNUSED			2
+#define ESSA_SET_VOLATILE		3
+#define ESSA_SET_POT_VOLATILE		4
+#define ESSA_SET_STABLE_RESIDENT	5
+#define ESSA_SET_STABLE_IF_RESIDENT	6
+
+#define ESSA_MAX	ESSA_SET_STABLE_IF_RESIDENT
+
+#endif
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index c64c0befd3f3..dd32beb9d30c 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -1,7 +1,7 @@
 /*
  * Performance event support - s390 specific definitions.
  *
- * Copyright IBM Corp. 2009, 2013
+ * Copyright IBM Corp. 2009, 2017
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
@@ -47,7 +47,7 @@ struct perf_sf_sde_regs {
 };
 
 /* Perf PMU definitions for the counter facility */
-#define PERF_CPUM_CF_MAX_CTR		256
+#define PERF_CPUM_CF_MAX_CTR		0xffffUL  /* Max ctr for ECCTR */
 
 /* Perf PMU definitions for the sampling facility */
 #define PERF_CPUM_SF_MAX_CTR		2
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 7ed1972b1920..e6e3b887bee3 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -24,6 +24,7 @@
  * the S390 page table tree.
  */
 #ifndef __ASSEMBLY__
+#include <asm-generic/5level-fixup.h>
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
@@ -371,10 +372,12 @@ static inline int is_module_addr(void *addr)
 #define PGSTE_VSIE_BIT	0x0000200000000000UL	/* ref'd in a shadow table */
 
 /* Guest Page State used for virtualization */
-#define _PGSTE_GPS_ZERO		0x0000000080000000UL
-#define _PGSTE_GPS_USAGE_MASK	0x0000000003000000UL
-#define _PGSTE_GPS_USAGE_STABLE 0x0000000000000000UL
-#define _PGSTE_GPS_USAGE_UNUSED 0x0000000001000000UL
+#define _PGSTE_GPS_ZERO			0x0000000080000000UL
+#define _PGSTE_GPS_USAGE_MASK		0x0000000003000000UL
+#define _PGSTE_GPS_USAGE_STABLE		0x0000000000000000UL
+#define _PGSTE_GPS_USAGE_UNUSED		0x0000000001000000UL
+#define _PGSTE_GPS_USAGE_POT_VOLATILE	0x0000000002000000UL
+#define _PGSTE_GPS_USAGE_VOLATILE	_PGSTE_GPS_USAGE_MASK
 
 /*
  * A user page table pointer has the space-switch-event bit, the
@@ -1040,6 +1043,12 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr);
 int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char *key);
 
+int set_pgste_bits(struct mm_struct *mm, unsigned long addr,
+				unsigned long bits, unsigned long value);
+int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep);
+int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
+			unsigned long *oldpte, unsigned long *oldpgste);
+
 /*
  * Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
@@ -1050,6 +1059,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 {
 	if (!MACHINE_HAS_NX)
 		pte_val(entry) &= ~_PAGE_NOEXEC;
+	if (pte_present(entry))
+		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm))
 		ptep_set_pte_at(mm, addr, ptep, entry);
 	else
diff --git a/arch/s390/include/asm/pkey.h b/arch/s390/include/asm/pkey.h
index b48aef4188f6..4c484590d858 100644
--- a/arch/s390/include/asm/pkey.h
+++ b/arch/s390/include/asm/pkey.h
@@ -87,4 +87,25 @@ int pkey_findcard(const struct pkey_seckey *seckey,
 int pkey_skey2pkey(const struct pkey_seckey *seckey,
 		   struct pkey_protkey *protkey);
 
+/*
+ * Verify the given secure key for being able to be useable with
+ * the pkey module. Check for correct key type and check for having at
+ * least one crypto card being able to handle this key (master key
+ * or old master key verification pattern matches).
+ * Return some info about the key: keysize in bits, keytype (currently
+ * only AES), flag if key is wrapped with an old MKVP.
+ * @param seckey pointer to buffer with the input secure key
+ * @param pcardnr pointer to cardnr, receives the card number on success
+ * @param pdomain pointer to domain, receives the domain number on success
+ * @param pkeysize pointer to keysize, receives the bitsize of the key
+ * @param pattributes pointer to attributes, receives additional info
+ *	  PKEY_VERIFY_ATTR_AES if the key is an AES key
+ *	  PKEY_VERIFY_ATTR_OLD_MKVP if key has old mkvp stored in
+ * @return 0 on success, negative errno value on failure. If no card could
+ *	   be found which is able to handle this key, -ENODEV is returned.
+ */
+int pkey_verifykey(const struct pkey_seckey *seckey,
+		   u16 *pcardnr, u16 *pdomain,
+		   u16 *pkeysize, u32 *pattributes);
+
 #endif /* _KAPI_PKEY_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index e4988710aa86..60d395fdc864 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -91,14 +91,15 @@ extern void execve_tail(void);
  * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.
  */
 
-#define TASK_SIZE_OF(tsk)	((tsk)->mm ? \
-				 (tsk)->mm->context.asce_limit : TASK_MAX_SIZE)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_31BIT) ? \
+					(1UL << 31) : (1UL << 53))
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_31BIT) ? \
 					(1UL << 30) : (1UL << 41))
 #define TASK_SIZE		TASK_SIZE_OF(current)
-#define TASK_MAX_SIZE		(1UL << 53)
+#define TASK_SIZE_MAX		(1UL << 53)
 
-#define STACK_TOP		(1UL << (test_thread_flag(TIF_31BIT) ? 31:42))
+#define STACK_TOP		(test_thread_flag(TIF_31BIT) ? \
+					(1UL << 31) : (1UL << 42))
 #define STACK_TOP_MAX		(1UL << 42)
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
@@ -135,6 +136,8 @@ struct thread_struct {
 	struct list_head list;
 	/* cpu runtime instrumentation */
 	struct runtime_instr_cb *ri_cb;
+	struct gs_cb *gs_cb;		/* Current guarded storage cb */
+	struct gs_cb *gs_bc_cb;		/* Broadcast guarded storage cb */
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
 	/*
 	 * Warning: 'fpu' is dynamically-sized. It *MUST* be at
@@ -215,6 +218,9 @@ void show_cacheinfo(struct seq_file *m);
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
+/* Free guarded storage control block for current */
+void exit_thread_gs(void);
+
 /*
  * Return saved PC of a blocked thread.
  */
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 5ce29fe100ba..fbd9116eb17b 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -4,6 +4,5 @@
 #include <asm-generic/sections.h>
 
 extern char _eshared[], _ehead[];
-extern char __start_ro_after_init[], __end_ro_after_init[];
 
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 30bdb5a027f3..cd78155b1829 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -29,8 +29,8 @@
 #define MACHINE_FLAG_TE		_BITUL(11)
 #define MACHINE_FLAG_TLB_LC	_BITUL(12)
 #define MACHINE_FLAG_VX		_BITUL(13)
-#define MACHINE_FLAG_CAD	_BITUL(14)
-#define MACHINE_FLAG_NX		_BITUL(15)
+#define MACHINE_FLAG_NX		_BITUL(14)
+#define MACHINE_FLAG_GS		_BITUL(15)
 
 #define LPP_MAGIC		_BITUL(31)
 #define LPP_PFAULT_PID_MASK	_AC(0xffffffff, UL)
@@ -68,8 +68,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
 #define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
-#define MACHINE_HAS_CAD		(S390_lowcore.machine_flags & MACHINE_FLAG_CAD)
 #define MACHINE_HAS_NX		(S390_lowcore.machine_flags & MACHINE_FLAG_NX)
+#define MACHINE_HAS_GS		(S390_lowcore.machine_flags & MACHINE_FLAG_GS)
 
 /*
  * Console mode. Override with conmode=
diff --git a/arch/s390/include/asm/sparsemem.h b/arch/s390/include/asm/sparsemem.h
index 487428b6d099..334e279f1bce 100644
--- a/arch/s390/include/asm/sparsemem.h
+++ b/arch/s390/include/asm/sparsemem.h
@@ -2,6 +2,6 @@
 #define _ASM_S390_SPARSEMEM_H
 
 #define SECTION_SIZE_BITS	28
-#define MAX_PHYSMEM_BITS	46
+#define MAX_PHYSMEM_BITS	CONFIG_MAX_PHYSMEM_BITS
 
 #endif /* _ASM_S390_SPARSEMEM_H */
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index ffc45048ea7d..f7838ecd83c6 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -10,6 +10,7 @@
 #define __ASM_SPINLOCK_H
 
 #include <linux/smp.h>
+#include <asm/atomic_ops.h>
 #include <asm/barrier.h>
 #include <asm/processor.h>
 
@@ -17,12 +18,6 @@
 
 extern int spin_retry;
 
-static inline int
-_raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new)
-{
-	return __sync_bool_compare_and_swap(lock, old, new);
-}
-
 #ifndef CONFIG_SMP
 static inline bool arch_vcpu_is_preempted(int cpu) { return false; }
 #else
@@ -40,7 +35,7 @@ bool arch_vcpu_is_preempted(int cpu);
  * (the type definitions are in asm/spinlock_types.h)
  */
 
-void arch_lock_relax(unsigned int cpu);
+void arch_lock_relax(int cpu);
 
 void arch_spin_lock_wait(arch_spinlock_t *);
 int arch_spin_trylock_retry(arch_spinlock_t *);
@@ -70,7 +65,7 @@ static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
 {
 	barrier();
 	return likely(arch_spin_value_unlocked(*lp) &&
-		      _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
+		      __atomic_cmpxchg_bool(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
 static inline void arch_spin_lock(arch_spinlock_t *lp)
@@ -95,7 +90,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
-	typecheck(unsigned int, lp->lock);
+	typecheck(int, lp->lock);
 	asm volatile(
 		"st	%1,%0\n"
 		: "+Q" (lp->lock)
@@ -141,16 +136,16 @@ extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
 static inline int arch_read_trylock_once(arch_rwlock_t *rw)
 {
-	unsigned int old = ACCESS_ONCE(rw->lock);
-	return likely((int) old >= 0 &&
-		      _raw_compare_and_swap(&rw->lock, old, old + 1));
+	int old = ACCESS_ONCE(rw->lock);
+	return likely(old >= 0 &&
+		      __atomic_cmpxchg_bool(&rw->lock, old, old + 1));
 }
 
 static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 {
-	unsigned int old = ACCESS_ONCE(rw->lock);
+	int old = ACCESS_ONCE(rw->lock);
 	return likely(old == 0 &&
-		      _raw_compare_and_swap(&rw->lock, 0, 0x80000000));
+		      __atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000));
 }
 
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
@@ -161,9 +156,9 @@ static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 
 #define __RAW_LOCK(ptr, op_val, op_string)		\
 ({							\
-	unsigned int old_val;				\
+	int old_val;					\
 							\
-	typecheck(unsigned int *, ptr);			\
+	typecheck(int *, ptr);				\
 	asm volatile(					\
 		op_string "	%0,%2,%1\n"		\
 		"bcr	14,0\n"				\
@@ -175,9 +170,9 @@ static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 
 #define __RAW_UNLOCK(ptr, op_val, op_string)		\
 ({							\
-	unsigned int old_val;				\
+	int old_val;					\
 							\
-	typecheck(unsigned int *, ptr);			\
+	typecheck(int *, ptr);				\
 	asm volatile(					\
 		op_string "	%0,%2,%1\n"		\
 		: "=d" (old_val), "+Q" (*ptr)		\
@@ -187,14 +182,14 @@ static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 })
 
 extern void _raw_read_lock_wait(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait(arch_rwlock_t *lp, unsigned int prev);
+extern void _raw_write_lock_wait(arch_rwlock_t *lp, int prev);
 
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	int old;
 
 	old = __RAW_LOCK(&rw->lock, 1, __RAW_OP_ADD);
-	if ((int) old < 0)
+	if (old < 0)
 		_raw_read_lock_wait(rw);
 }
 
@@ -205,7 +200,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline void arch_write_lock(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	int old;
 
 	old = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
 	if (old != 0)
@@ -232,11 +227,11 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	int old;
 
 	do {
 		old = ACCESS_ONCE(rw->lock);
-	} while (!_raw_compare_and_swap(&rw->lock, old, old - 1));
+	} while (!__atomic_cmpxchg_bool(&rw->lock, old, old - 1));
 }
 
 static inline void arch_write_lock(arch_rwlock_t *rw)
@@ -248,7 +243,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
-	typecheck(unsigned int, rw->lock);
+	typecheck(int, rw->lock);
 
 	rw->owner = 0;
 	asm volatile(
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index d84b6939237c..fe755eec275f 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -6,14 +6,14 @@
 #endif
 
 typedef struct {
-	unsigned int lock;
+	int lock;
 } __attribute__ ((aligned (4))) arch_spinlock_t;
 
 #define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0, }
 
 typedef struct {
-	unsigned int lock;
-	unsigned int owner;
+	int lock;
+	int owner;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 12d45f0cfdd9..f6c2b5814ab0 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -10,6 +10,7 @@
 #include <linux/thread_info.h>
 #include <asm/fpu/api.h>
 #include <asm/ptrace.h>
+#include <asm/guarded_storage.h>
 
 extern struct task_struct *__switch_to(void *, void *);
 extern void update_cr_regs(struct task_struct *task);
@@ -33,12 +34,14 @@ static inline void restore_access_regs(unsigned int *acrs)
 		save_fpu_regs();					\
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
+		save_gs_cb(prev->thread.gs_cb);				\
 	}								\
 	if (next->mm) {							\
 		update_cr_regs(next);					\
 		set_cpu_flag(CIF_FPU);					\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
+		restore_gs_cb(next->thread.gs_cb);			\
 	}								\
 	prev = __switch_to(prev,next);					\
 } while (0)
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 229326c942c7..73bff45ced55 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -142,7 +142,15 @@ struct sysinfo_3_2_2 {
 
 extern int topology_max_mnest;
 
-#define TOPOLOGY_CORE_BITS	64
+/*
+ * Returns the maximum nesting level supported by the cpu topology code.
+ * The current maximum level is 4 which is the drawer level.
+ */
+static inline int topology_mnest_limit(void)
+{
+	return min(topology_max_mnest, 4);
+}
+
 #define TOPOLOGY_NR_MAG		6
 
 struct topology_core {
@@ -152,7 +160,7 @@ struct topology_core {
 	unsigned char pp:2;
 	unsigned char reserved1;
 	unsigned short origin;
-	unsigned long mask[TOPOLOGY_CORE_BITS / BITS_PER_LONG];
+	unsigned long mask;
 };
 
 struct topology_container {
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 646845edf148..0b3ee083a665 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -56,7 +56,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
 #define TIF_UPROBE		3	/* breakpointed or single-stepping */
-#define TIF_PATCH_PENDING	4	/* pending live patching update */
+#define TIF_GUARDED_STORAGE	4	/* load guarded storage control block */
+#define TIF_PATCH_PENDING	5	/* pending live patching update */
 
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
@@ -75,6 +76,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define _TIF_SIGPENDING		_BITUL(TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	_BITUL(TIF_NEED_RESCHED)
 #define _TIF_UPROBE		_BITUL(TIF_UPROBE)
+#define _TIF_GUARDED_STORAGE	_BITUL(TIF_GUARDED_STORAGE)
 #define _TIF_PATCH_PENDING	_BITUL(TIF_PATCH_PENDING)
 
 #define _TIF_31BIT		_BITUL(TIF_31BIT)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 354344dcc198..118535123f34 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -206,20 +206,16 @@ static inline unsigned long long get_tod_clock_monotonic(void)
  *    ns = (todval * 125) >> 9;
  *
  * In order to avoid an overflow with the multiplication we can rewrite this.
- * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits)
+ * With a split todval == 2^9 * th + tl (th upper 55 bits, tl lower 9 bits)
  * we end up with
  *
- *    ns = ((2^32 * th + tl) * 125 ) >> 9;
- * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9);
+ *    ns = ((2^9 * th + tl) * 125 ) >> 9;
+ * -> ns = (th * 125) + ((tl * 125) >> 9);
  *
  */
 static inline unsigned long long tod_to_ns(unsigned long long todval)
 {
-	unsigned long long ns;
-
-	ns = ((todval >> 32) << 23) * 125;
-	ns += ((todval & 0xffffffff) * 125) >> 9;
-	return ns;
+	return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
 }
 
 #endif
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 136932ff4250..78f3f093d143 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -12,13 +12,9 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
-#include <linux/errno.h>
 #include <asm/processor.h>
 #include <asm/ctl_reg.h>
-
-#define VERIFY_READ     0
-#define VERIFY_WRITE    1
+#include <asm/extable.h>
 
 
 /*
@@ -42,7 +38,7 @@
 static inline void set_fs(mm_segment_t fs)
 {
 	current->thread.mm_segment = fs;
-	if (segment_eq(fs, KERNEL_DS)) {
+	if (uaccess_kernel()) {
 		set_cpu_flag(CIF_ASCE_SECONDARY);
 		__ctl_load(S390_lowcore.kernel_asce, 7, 7);
 	} else {
@@ -64,72 +60,14 @@ static inline int __range_ok(unsigned long addr, unsigned long size)
 
 #define access_ok(type, addr, size) __access_ok(addr, size)
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	int insn, fixup;
-};
-
-static inline unsigned long extable_fixup(const struct exception_table_entry *x)
-{
-	return (unsigned long)&x->fixup + x->fixup;
-}
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:	  Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-unsigned long __must_check __copy_from_user(void *to, const void __user *from,
-					    unsigned long n);
+unsigned long __must_check
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
 
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:	  Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-unsigned long __must_check __copy_to_user(void __user *to, const void *from,
-					  unsigned long n);
+unsigned long __must_check
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 
@@ -147,7 +85,7 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from,
 		"	jg	2b\n"				\
 		".popsection\n"					\
 		EX_TABLE(0b,3b) EX_TABLE(1b,3b)			\
-		: "=d" (__rc), "=Q" (*(to))			\
+		: "=d" (__rc), "+Q" (*(to))			\
 		: "d" (size), "Q" (*(from)),			\
 		  "d" (__reg0), "K" (-EFAULT)			\
 		: "cc");					\
@@ -218,13 +156,13 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s
 
 static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
-	size = __copy_to_user(ptr, x, size);
+	size = raw_copy_to_user(ptr, x, size);
 	return size ? -EFAULT : 0;
 }
 
 static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
 {
-	size = __copy_from_user(x, ptr, size);
+	size = raw_copy_from_user(x, ptr, size);
 	return size ? -EFAULT : 0;
 }
 
@@ -314,77 +252,8 @@ int __get_user_bad(void) __attribute__((noreturn));
 #define __put_user_unaligned __put_user
 #define __get_user_unaligned __get_user
 
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
-	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	might_fault();
-	return __copy_to_user(to, from, n);
-}
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	unsigned int sz = __compiletime_object_size(to);
-
-	might_fault();
-	if (unlikely(sz != -1 && sz < n)) {
-		if (!__builtin_constant_p(n))
-			copy_user_overflow(sz, n);
-		else
-			__bad_copy_user();
-		return n;
-	}
-	return __copy_from_user(to, from, n);
-}
-
 unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n);
-
-static inline unsigned long __must_check
-copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-	might_fault();
-	return __copy_in_user(to, from, n);
-}
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
 
 /*
  * Copy a null terminated string from userspace.
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index 6848ba5c1454..addb09cee0f5 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -1,6 +1,16 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += errno.h
+generic-y += fcntl.h
+generic-y += ioctl.h
+generic-y += mman.h
+generic-y += param.h
+generic-y += poll.h
+generic-y += resource.h
+generic-y += sockios.h
+generic-y += termbits.h
+
 header-y += auxvec.h
 header-y += bitsperlong.h
 header-y += byteorder.h
@@ -11,25 +21,20 @@ header-y += cmb.h
 header-y += dasd.h
 header-y += debug.h
 header-y += errno.h
-header-y += fcntl.h
+header-y += guarded_storage.h
 header-y += hypfs.h
-header-y += ioctl.h
 header-y += ioctls.h
 header-y += ipcbuf.h
 header-y += kvm.h
 header-y += kvm_para.h
 header-y += kvm_perf.h
 header-y += kvm_virtio.h
-header-y += mman.h
 header-y += monwriter.h
 header-y += msgbuf.h
-header-y += param.h
 header-y += pkey.h
-header-y += poll.h
 header-y += posix_types.h
 header-y += ptrace.h
 header-y += qeth.h
-header-y += resource.h
 header-y += schid.h
 header-y += sclp_ctl.h
 header-y += sembuf.h
@@ -40,12 +45,10 @@ header-y += sigcontext.h
 header-y += siginfo.h
 header-y += signal.h
 header-y += socket.h
-header-y += sockios.h
 header-y += stat.h
 header-y += statfs.h
 header-y += swab.h
 header-y += tape390.h
-header-y += termbits.h
 header-y += termios.h
 header-y += types.h
 header-y += ucontext.h
diff --git a/arch/s390/include/uapi/asm/errno.h b/arch/s390/include/uapi/asm/errno.h
deleted file mode 100644
index 395e97d8005e..000000000000
--- a/arch/s390/include/uapi/asm/errno.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/*
- *  S390 version
- *
- */
-
-#ifndef _S390_ERRNO_H
-#define _S390_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif
diff --git a/arch/s390/include/uapi/asm/fcntl.h b/arch/s390/include/uapi/asm/fcntl.h
deleted file mode 100644
index 46ab12db5739..000000000000
--- a/arch/s390/include/uapi/asm/fcntl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/fcntl.h>
diff --git a/arch/s390/include/uapi/asm/guarded_storage.h b/arch/s390/include/uapi/asm/guarded_storage.h
new file mode 100644
index 000000000000..852850e8e17e
--- /dev/null
+++ b/arch/s390/include/uapi/asm/guarded_storage.h
@@ -0,0 +1,77 @@
+#ifndef _GUARDED_STORAGE_H
+#define _GUARDED_STORAGE_H
+
+#include <linux/types.h>
+
+struct gs_cb {
+	__u64 reserved;
+	__u64 gsd;
+	__u64 gssm;
+	__u64 gs_epl_a;
+};
+
+struct gs_epl {
+	__u8 pad1;
+	union {
+		__u8 gs_eam;
+		struct {
+			__u8	: 6;
+			__u8 e	: 1;
+			__u8 b	: 1;
+		};
+	};
+	union {
+		__u8 gs_eci;
+		struct {
+			__u8 tx	: 1;
+			__u8 cx	: 1;
+			__u8	: 5;
+			__u8 in	: 1;
+		};
+	};
+	union {
+		__u8 gs_eai;
+		struct {
+			__u8	: 1;
+			__u8 t	: 1;
+			__u8 as	: 2;
+			__u8 ar	: 4;
+		};
+	};
+	__u32 pad2;
+	__u64 gs_eha;
+	__u64 gs_eia;
+	__u64 gs_eoa;
+	__u64 gs_eir;
+	__u64 gs_era;
+};
+
+#define GS_ENABLE	0
+#define	GS_DISABLE	1
+#define GS_SET_BC_CB	2
+#define GS_CLEAR_BC_CB	3
+#define GS_BROADCAST	4
+
+static inline void load_gs_cb(struct gs_cb *gs_cb)
+{
+	asm volatile(".insn rxy,0xe3000000004d,0,%0" : : "Q" (*gs_cb));
+}
+
+static inline void store_gs_cb(struct gs_cb *gs_cb)
+{
+	asm volatile(".insn rxy,0xe30000000049,0,%0" : : "Q" (*gs_cb));
+}
+
+static inline void save_gs_cb(struct gs_cb *gs_cb)
+{
+	if (gs_cb)
+		store_gs_cb(gs_cb);
+}
+
+static inline void restore_gs_cb(struct gs_cb *gs_cb)
+{
+	if (gs_cb)
+		load_gs_cb(gs_cb);
+}
+
+#endif /* _GUARDED_STORAGE_H */
diff --git a/arch/s390/include/uapi/asm/ioctl.h b/arch/s390/include/uapi/asm/ioctl.h
deleted file mode 100644
index b279fe06dfe5..000000000000
--- a/arch/s390/include/uapi/asm/ioctl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ioctl.h>
diff --git a/arch/s390/include/uapi/asm/mman.h b/arch/s390/include/uapi/asm/mman.h
deleted file mode 100644
index de23da1f41b2..000000000000
--- a/arch/s390/include/uapi/asm/mman.h
+++ /dev/null
@@ -1,6 +0,0 @@
-/*
- *  S390 version
- *
- *  Derived from "include/asm-i386/mman.h"
- */
-#include <asm-generic/mman.h>
diff --git a/arch/s390/include/uapi/asm/param.h b/arch/s390/include/uapi/asm/param.h
deleted file mode 100644
index c616821bf2ac..000000000000
--- a/arch/s390/include/uapi/asm/param.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASMS390_PARAM_H
-#define _ASMS390_PARAM_H
-
-#include <asm-generic/param.h>
-
-#endif /* _ASMS390_PARAM_H */
diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h
index ed7f19c27ce5..e6c04faf8a6c 100644
--- a/arch/s390/include/uapi/asm/pkey.h
+++ b/arch/s390/include/uapi/asm/pkey.h
@@ -109,4 +109,23 @@ struct pkey_skey2pkey {
 };
 #define PKEY_SKEY2PKEY _IOWR(PKEY_IOCTL_MAGIC, 0x06, struct pkey_skey2pkey)
 
+/*
+ * Verify the given secure key for being able to be useable with
+ * the pkey module. Check for correct key type and check for having at
+ * least one crypto card being able to handle this key (master key
+ * or old master key verification pattern matches).
+ * Return some info about the key: keysize in bits, keytype (currently
+ * only AES), flag if key is wrapped with an old MKVP.
+ */
+struct pkey_verifykey {
+	struct pkey_seckey seckey;	       /* in: the secure key blob */
+	__u16  cardnr;			       /* out: card number	  */
+	__u16  domain;			       /* out: domain number	  */
+	__u16  keysize;			       /* out: key size in bits   */
+	__u32  attributes;		       /* out: attribute bits	  */
+};
+#define PKEY_VERIFYKEY _IOWR(PKEY_IOCTL_MAGIC, 0x07, struct pkey_verifykey)
+#define PKEY_VERIFY_ATTR_AES	   0x00000001  /* key is an AES key */
+#define PKEY_VERIFY_ATTR_OLD_MKVP  0x00000100  /* key has old MKVP value */
+
 #endif /* _UAPI_PKEY_H */
diff --git a/arch/s390/include/uapi/asm/poll.h b/arch/s390/include/uapi/asm/poll.h
deleted file mode 100644
index c98509d3149e..000000000000
--- a/arch/s390/include/uapi/asm/poll.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/poll.h>
diff --git a/arch/s390/include/uapi/asm/resource.h b/arch/s390/include/uapi/asm/resource.h
deleted file mode 100644
index ec23d1c73c92..000000000000
--- a/arch/s390/include/uapi/asm/resource.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- *  S390 version
- *
- *  Derived from "include/asm-i386/resources.h"
- */
-
-#ifndef _S390_RESOURCE_H
-#define _S390_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif
-
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index b24a64cbfeb1..e8e5ecf673fd 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -98,4 +98,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define	SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/sockios.h b/arch/s390/include/uapi/asm/sockios.h
deleted file mode 100644
index 6f60eee73242..000000000000
--- a/arch/s390/include/uapi/asm/sockios.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_S390_SOCKIOS_H
-#define _ASM_S390_SOCKIOS_H
-
-#include <asm-generic/sockios.h>
-
-#endif
diff --git a/arch/s390/include/uapi/asm/termbits.h b/arch/s390/include/uapi/asm/termbits.h
deleted file mode 100644
index 71bf6ac6a2b9..000000000000
--- a/arch/s390/include/uapi/asm/termbits.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_S390_TERMBITS_H
-#define _ASM_S390_TERMBITS_H
-
-#include <asm-generic/termbits.h>
-
-#endif
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 4384bc797a54..ea42290e7d51 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -313,7 +313,9 @@
 #define __NR_copy_file_range	375
 #define __NR_preadv2		376
 #define __NR_pwritev2		377
-#define NR_syscalls 378
+#define __NR_s390_guarded_storage	378
+#define __NR_statx		379
+#define NR_syscalls 380
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 060ce548fe8b..adb3fe2e3d42 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -51,14 +51,12 @@ CFLAGS_dumpstack.o	+= -fno-optimize-sibling-calls
 #
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
-CFLAGS_sysinfo.o	+= -w
-
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
-obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o
-obj-y	+= entry.o reipl.o relocate_kernel.o
+obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o
+obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o
 
 extra-y				+= head.o head64.o vmlinux.lds
 
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index c4b3570ded5b..6bb29633e1f1 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -175,7 +175,7 @@ int main(void)
 	/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
 	OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
 	/* hardware defined lowcore locations 0x1000 - 0x18ff */
-	OFFSET(__LC_VX_SAVE_AREA_ADDR, lowcore, vector_save_area_addr);
+	OFFSET(__LC_MCESAD, lowcore, mcesad);
 	OFFSET(__LC_EXT_PARAMS2, lowcore, ext_params2);
 	OFFSET(__LC_FPREGS_SAVE_AREA, lowcore, floating_pt_save_area);
 	OFFSET(__LC_GPREGS_SAVE_AREA, lowcore, gpregs_save_area);
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index ae2cda5eee5a..986642a3543b 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -178,3 +178,5 @@ COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
 COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
 COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
 COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
+COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index dd1d5c62c374..d628afc26708 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -429,6 +429,20 @@ static void *nt_vmcoreinfo(void *ptr)
 }
 
 /*
+ * Initialize final note (needed for /proc/vmcore code)
+ */
+static void *nt_final(void *ptr)
+{
+	Elf64_Nhdr *note;
+
+	note = (Elf64_Nhdr *) ptr;
+	note->n_namesz = 0;
+	note->n_descsz = 0;
+	note->n_type = 0;
+	return PTR_ADD(ptr, sizeof(Elf64_Nhdr));
+}
+
+/*
  * Initialize ELF header (new kernel)
  */
 static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
@@ -515,6 +529,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 		if (sa->prefix != 0)
 			ptr = fill_cpu_elf_notes(ptr, cpu++, sa);
 	ptr = nt_vmcoreinfo(ptr);
+	ptr = nt_final(ptr);
 	memset(phdr, 0, sizeof(*phdr));
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = notes_offset;
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 4e65c79cc5f2..5d20182ee8ae 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -231,9 +231,29 @@ static noinline __init void detect_machine_type(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
 }
 
+/* Remove leading, trailing and double whitespace. */
+static inline void strim_all(char *str)
+{
+	char *s;
+
+	s = strim(str);
+	if (s != str)
+		memmove(str, s, strlen(s));
+	while (*str) {
+		if (!isspace(*str++))
+			continue;
+		if (isspace(*str)) {
+			s = skip_spaces(str);
+			memmove(str, s, strlen(s) + 1);
+		}
+	}
+}
+
 static noinline __init void setup_arch_string(void)
 {
 	struct sysinfo_1_1_1 *mach = (struct sysinfo_1_1_1 *)&sysinfo_page;
+	struct sysinfo_3_2_2 *vm = (struct sysinfo_3_2_2 *)&sysinfo_page;
+	char mstr[80], hvstr[17];
 
 	if (stsi(mach, 1, 1, 1))
 		return;
@@ -241,14 +261,21 @@ static noinline __init void setup_arch_string(void)
 	EBCASC(mach->type, sizeof(mach->type));
 	EBCASC(mach->model, sizeof(mach->model));
 	EBCASC(mach->model_capacity, sizeof(mach->model_capacity));
-	dump_stack_set_arch_desc("%-16.16s %-4.4s %-16.16s %-16.16s (%s)",
-				 mach->manufacturer,
-				 mach->type,
-				 mach->model,
-				 mach->model_capacity,
-				 MACHINE_IS_LPAR ? "LPAR" :
-				 MACHINE_IS_VM ? "z/VM" :
-				 MACHINE_IS_KVM ? "KVM" : "unknown");
+	sprintf(mstr, "%-16.16s %-4.4s %-16.16s %-16.16s",
+		mach->manufacturer, mach->type,
+		mach->model, mach->model_capacity);
+	strim_all(mstr);
+	if (stsi(vm, 3, 2, 2) == 0 && vm->count) {
+		EBCASC(vm->vm[0].cpi, sizeof(vm->vm[0].cpi));
+		sprintf(hvstr, "%-16.16s", vm->vm[0].cpi);
+		strim_all(hvstr);
+	} else {
+		sprintf(hvstr, "%s",
+			MACHINE_IS_LPAR ? "LPAR" :
+			MACHINE_IS_VM ? "z/VM" :
+			MACHINE_IS_KVM ? "KVM" : "unknown");
+	}
+	dump_stack_set_arch_desc("%s (%s)", mstr, hvstr);
 }
 
 static __init void setup_topology(void)
@@ -358,6 +385,8 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
 		__ctl_set_bit(0, 20);
 	}
+	if (test_facility(133))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_GS;
 }
 
 static inline void save_vector_registers(void)
@@ -375,7 +404,7 @@ static int __init topology_setup(char *str)
 
 	rc = kstrtobool(str, &enabled);
 	if (!rc && !enabled)
-		S390_lowcore.machine_flags &= ~MACHINE_HAS_TOPOLOGY;
+		S390_lowcore.machine_flags &= ~MACHINE_FLAG_TOPOLOGY;
 	return rc;
 }
 early_param("topology", topology_setup);
@@ -405,23 +434,16 @@ early_param("noexec", noexec_setup);
 
 static int __init cad_setup(char *str)
 {
-	int val;
-
-	get_option(&str, &val);
-	if (val && test_facility(128))
-		S390_lowcore.machine_flags |= MACHINE_FLAG_CAD;
-	return 0;
-}
-early_param("cad", cad_setup);
+	bool enabled;
+	int rc;
 
-static int __init cad_init(void)
-{
-	if (MACHINE_HAS_CAD)
+	rc = kstrtobool(str, &enabled);
+	if (!rc && enabled && test_facility(128))
 		/* Enable problem state CAD. */
 		__ctl_set_bit(2, 3);
-	return 0;
+	return rc;
 }
-early_initcall(cad_init);
+early_param("cad", cad_setup);
 
 static __init void memmove_early(void *dst, const void *src, size_t n)
 {
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a08b5eea5567..a5f5d3bb3dbc 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -47,7 +47,7 @@ STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
 _TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		   _TIF_UPROBE | _TIF_PATCH_PENDING)
+		   _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
 _CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \
@@ -189,8 +189,6 @@ ENTRY(__switch_to)
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
-	/* c4 is used in guest detection: arch/s390/kernel/perf_cpum_sf.c */
-	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
@@ -332,6 +330,8 @@ ENTRY(system_call)
 	TSTMSK	__TI_flags(%r12),_TIF_UPROBE
 	jo	.Lsysc_uprobe_notify
 #endif
+	TSTMSK	__TI_flags(%r12),_TIF_GUARDED_STORAGE
+	jo	.Lsysc_guarded_storage
 	TSTMSK	__PT_FLAGS(%r11),_PIF_PER_TRAP
 	jo	.Lsysc_singlestep
 #ifdef CONFIG_LIVEPATCH
@@ -414,6 +414,13 @@ ENTRY(system_call)
 #endif
 
 #
+# _TIF_GUARDED_STORAGE is set, call guarded_storage_load
+#
+.Lsysc_guarded_storage:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,.Lsysc_return
+	jg	gs_load_bc_cb
+#
 # _TIF_PATCH_PENDING is set, call klp_update_patch_state
 #
 #ifdef CONFIG_LIVEPATCH
@@ -505,7 +512,7 @@ ENTRY(pgm_check_handler)
 	jnz	.Lpgm_svcper		# -> single stepped svc
 1:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	j	3f
+	j	4f
 2:	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
 	lg	%r15,__LC_KERNEL_STACK
 	lgr	%r14,%r12
@@ -514,8 +521,8 @@ ENTRY(pgm_check_handler)
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
 	jz	3f
 	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
-3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
-	stg	%r10,__THREAD_last_break(%r14)
+3:	stg	%r10,__THREAD_last_break(%r14)
+4:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
@@ -524,14 +531,14 @@ ENTRY(pgm_check_handler)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	stg	%r10,__PT_ARGS(%r11)
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
-	jz	4f
+	jz	5f
 	tmhh	%r8,0x0001		# kernel per event ?
 	jz	.Lpgm_kprobe
 	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
 	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
 	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
-4:	REENABLE_IRQS
+5:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
@@ -682,6 +689,8 @@ ENTRY(io_int_handler)
 	jo	.Lio_sigpending
 	TSTMSK	__TI_flags(%r12),_TIF_NOTIFY_RESUME
 	jo	.Lio_notify_resume
+	TSTMSK	__TI_flags(%r12),_TIF_GUARDED_STORAGE
+	jo	.Lio_guarded_storage
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lio_vxrs
 	TSTMSK	__LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
@@ -716,6 +725,18 @@ ENTRY(io_int_handler)
 	jg	load_fpu_regs
 
 #
+# _TIF_GUARDED_STORAGE is set, call guarded_storage_load
+#
+.Lio_guarded_storage:
+	# TRACE_IRQS_ON already done at .Lio_return
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,gs_load_bc_cb
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
+	j	.Lio_return
+
+#
 # _TIF_NEED_RESCHED is set, call schedule
 #
 .Lio_reschedule:
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 33f901865326..dbf5f7e18246 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -74,12 +74,14 @@ long sys_sigreturn(void);
 
 long sys_s390_personality(unsigned int personality);
 long sys_s390_runtime_instr(int command, int signum);
+long sys_s390_guarded_storage(int command, struct gs_cb __user *);
 long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
 long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
 void verify_facilities(void);
+void gs_load_bc_cb(struct pt_regs *regs);
 void set_fs_fixup(void);
 
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/guarded_storage.c b/arch/s390/kernel/guarded_storage.c
new file mode 100644
index 000000000000..6f064745c3b1
--- /dev/null
+++ b/arch/s390/kernel/guarded_storage.c
@@ -0,0 +1,128 @@
+/*
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/signal.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/guarded_storage.h>
+#include "entry.h"
+
+void exit_thread_gs(void)
+{
+	kfree(current->thread.gs_cb);
+	kfree(current->thread.gs_bc_cb);
+	current->thread.gs_cb = current->thread.gs_bc_cb = NULL;
+}
+
+static int gs_enable(void)
+{
+	struct gs_cb *gs_cb;
+
+	if (!current->thread.gs_cb) {
+		gs_cb = kzalloc(sizeof(*gs_cb), GFP_KERNEL);
+		if (!gs_cb)
+			return -ENOMEM;
+		gs_cb->gsd = 25;
+		preempt_disable();
+		__ctl_set_bit(2, 4);
+		load_gs_cb(gs_cb);
+		current->thread.gs_cb = gs_cb;
+		preempt_enable();
+	}
+	return 0;
+}
+
+static int gs_disable(void)
+{
+	if (current->thread.gs_cb) {
+		preempt_disable();
+		kfree(current->thread.gs_cb);
+		current->thread.gs_cb = NULL;
+		__ctl_clear_bit(2, 4);
+		preempt_enable();
+	}
+	return 0;
+}
+
+static int gs_set_bc_cb(struct gs_cb __user *u_gs_cb)
+{
+	struct gs_cb *gs_cb;
+
+	gs_cb = current->thread.gs_bc_cb;
+	if (!gs_cb) {
+		gs_cb = kzalloc(sizeof(*gs_cb), GFP_KERNEL);
+		if (!gs_cb)
+			return -ENOMEM;
+		current->thread.gs_bc_cb = gs_cb;
+	}
+	if (copy_from_user(gs_cb, u_gs_cb, sizeof(*gs_cb)))
+		return -EFAULT;
+	return 0;
+}
+
+static int gs_clear_bc_cb(void)
+{
+	struct gs_cb *gs_cb;
+
+	gs_cb = current->thread.gs_bc_cb;
+	current->thread.gs_bc_cb = NULL;
+	kfree(gs_cb);
+	return 0;
+}
+
+void gs_load_bc_cb(struct pt_regs *regs)
+{
+	struct gs_cb *gs_cb;
+
+	preempt_disable();
+	clear_thread_flag(TIF_GUARDED_STORAGE);
+	gs_cb = current->thread.gs_bc_cb;
+	if (gs_cb) {
+		kfree(current->thread.gs_cb);
+		current->thread.gs_bc_cb = NULL;
+		__ctl_set_bit(2, 4);
+		load_gs_cb(gs_cb);
+		current->thread.gs_cb = gs_cb;
+	}
+	preempt_enable();
+}
+
+static int gs_broadcast(void)
+{
+	struct task_struct *sibling;
+
+	read_lock(&tasklist_lock);
+	for_each_thread(current, sibling) {
+		if (!sibling->thread.gs_bc_cb)
+			continue;
+		if (test_and_set_tsk_thread_flag(sibling, TIF_GUARDED_STORAGE))
+			kick_process(sibling);
+	}
+	read_unlock(&tasklist_lock);
+	return 0;
+}
+
+SYSCALL_DEFINE2(s390_guarded_storage, int, command,
+		struct gs_cb __user *, gs_cb)
+{
+	if (!MACHINE_HAS_GS)
+		return -EOPNOTSUPP;
+	switch (command) {
+	case GS_ENABLE:
+		return gs_enable();
+	case GS_DISABLE:
+		return gs_disable();
+	case GS_SET_BC_CB:
+		return gs_set_bc_cb(gs_cb);
+	case GS_CLEAR_BC_CB:
+		return gs_clear_bc_cb();
+	case GS_BROADCAST:
+		return gs_broadcast();
+	default:
+		return -EINVAL;
+	}
+}
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 0b5ebf8a3d30..eff5b31671d4 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -25,7 +25,6 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
-#include <asm/facility.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 482d3526e32b..31c91f24e562 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -52,7 +52,7 @@ ENTRY(startup_continue)
 	.quad	0			# cr1: primary space segment table
 	.quad	.Lduct			# cr2: dispatchable unit control table
 	.quad	0			# cr3: instruction authorization
-	.quad	0			# cr4: instruction authorization
+	.quad	0xffff			# cr4: instruction authorization
 	.quad	.Lduct			# cr5: primary-aste origin
 	.quad	0			# cr6:	I/O interrupts
 	.quad	0			# cr7:	secondary space segment table
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index b67dafb7b7cf..e545ffe5155a 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -564,6 +564,8 @@ static struct kset *ipl_kset;
 
 static void __ipl_run(void *unused)
 {
+	if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW)
+		diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
 	diag308(DIAG308_LOAD_CLEAR, NULL);
 	if (MACHINE_IS_VM)
 		__cpcmd("IPL", NULL, 0, NULL);
diff --git a/arch/s390/kernel/kdebugfs.c b/arch/s390/kernel/kdebugfs.c
new file mode 100644
index 000000000000..ee85e17dd79d
--- /dev/null
+++ b/arch/s390/kernel/kdebugfs.c
@@ -0,0 +1,15 @@
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/init.h>
+
+struct dentry *arch_debugfs_dir;
+EXPORT_SYMBOL(arch_debugfs_dir);
+
+static int __init arch_kdebugfs_init(void)
+{
+	arch_debugfs_dir = debugfs_create_dir("s390", NULL);
+	if (IS_ERR(arch_debugfs_dir))
+		arch_debugfs_dir = NULL;
+	return 0;
+}
+postcore_initcall(arch_kdebugfs_init);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 3074c1d83829..db5658daf994 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/os_info.h>
 #include <asm/switch_to.h>
+#include <asm/nmi.h>
 
 typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long);
 
@@ -102,6 +103,8 @@ static void __do_machine_kdump(void *image)
  */
 static noinline void __machine_kdump(void *image)
 {
+	struct mcesa *mcesa;
+	unsigned long cr2_old, cr2_new;
 	int this_cpu, cpu;
 
 	lgr_info_log();
@@ -114,8 +117,16 @@ static noinline void __machine_kdump(void *image)
 			continue;
 	}
 	/* Store status of the boot CPU */
+	mcesa = (struct mcesa *)(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
 	if (MACHINE_HAS_VX)
-		save_vx_regs((void *) &S390_lowcore.vector_save_area);
+		save_vx_regs((__vector128 *) mcesa->vector_save_area);
+	if (MACHINE_HAS_GS) {
+		__ctl_store(cr2_old, 2, 2);
+		cr2_new = cr2_old | (1UL << 4);
+		__ctl_load(cr2_new, 2, 2);
+		save_gs_cb((struct gs_cb *) mcesa->guarded_storage_save_area);
+		__ctl_load(cr2_old, 2, 2);
+	}
 	/*
 	 * To create a good backchain for this CPU in the dump store_status
 	 * is passed the address of a function. The address is saved into
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 9bf8327154ee..985589523970 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -106,6 +106,7 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 	int kill_task;
 	u64 zero;
 	void *fpt_save_area;
+	struct mcesa *mcesa;
 
 	kill_task = 0;
 	zero = 0;
@@ -165,6 +166,7 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 			     : : "Q" (S390_lowcore.fpt_creg_save_area));
 	}
 
+	mcesa = (struct mcesa *)(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
 	if (!MACHINE_HAS_VX) {
 		/* Validate floating point registers */
 		asm volatile(
@@ -209,8 +211,8 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 			"	la	1,%0\n"
 			"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
 			"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
-			: : "Q" (*(struct vx_array *)
-				 &S390_lowcore.vector_save_area) : "1");
+			: : "Q" (*(struct vx_array *) mcesa->vector_save_area)
+			: "1");
 		__ctl_load(S390_lowcore.cregs_save_area[0], 0, 0);
 	}
 	/* Validate access registers */
@@ -224,6 +226,19 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 		 */
 		kill_task = 1;
 	}
+	/* Validate guarded storage registers */
+	if (MACHINE_HAS_GS && (S390_lowcore.cregs_save_area[2] & (1UL << 4))) {
+		if (!mci.gs)
+			/*
+			 * Guarded storage register can't be restored and
+			 * the current processes uses guarded storage.
+			 * It has to be terminated.
+			 */
+			kill_task = 1;
+		else
+			load_gs_cb((struct gs_cb *)
+				   mcesa->guarded_storage_save_area);
+	}
 	/*
 	 * We don't even try to validate the TOD register, since we simply
 	 * can't write something sensible into that register.
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 1aba10e90906..746d03423333 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -1,7 +1,7 @@
 /*
  * Performance event support for s390x - CPU-measurement Counter Facility
  *
- *  Copyright IBM Corp. 2012
+ *  Copyright IBM Corp. 2012, 2017
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -22,19 +22,12 @@
 #include <asm/irq.h>
 #include <asm/cpu_mf.h>
 
-/* CPU-measurement counter facility supports these CPU counter sets:
- * For CPU counter sets:
- *    Basic counter set:	     0-31
- *    Problem-state counter set:    32-63
- *    Crypto-activity counter set:  64-127
- *    Extented counter set:	   128-159
- */
 enum cpumf_ctr_set {
-	/* CPU counter sets */
-	CPUMF_CTR_SET_BASIC   = 0,
-	CPUMF_CTR_SET_USER    = 1,
-	CPUMF_CTR_SET_CRYPTO  = 2,
-	CPUMF_CTR_SET_EXT     = 3,
+	CPUMF_CTR_SET_BASIC   = 0,    /* Basic Counter Set */
+	CPUMF_CTR_SET_USER    = 1,    /* Problem-State Counter Set */
+	CPUMF_CTR_SET_CRYPTO  = 2,    /* Crypto-Activity Counter Set */
+	CPUMF_CTR_SET_EXT     = 3,    /* Extended Counter Set */
+	CPUMF_CTR_SET_MT_DIAG = 4,    /* MT-diagnostic Counter Set */
 
 	/* Maximum number of counter sets */
 	CPUMF_CTR_SET_MAX,
@@ -47,6 +40,7 @@ static const u64 cpumf_state_ctl[CPUMF_CTR_SET_MAX] = {
 	[CPUMF_CTR_SET_USER]	= 0x04,
 	[CPUMF_CTR_SET_CRYPTO]	= 0x08,
 	[CPUMF_CTR_SET_EXT]	= 0x01,
+	[CPUMF_CTR_SET_MT_DIAG] = 0x20,
 };
 
 static void ctr_set_enable(u64 *state, int ctr_set)
@@ -76,19 +70,20 @@ struct cpu_hw_events {
 };
 static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.ctr_set = {
-		[CPUMF_CTR_SET_BASIC]  = ATOMIC_INIT(0),
-		[CPUMF_CTR_SET_USER]   = ATOMIC_INIT(0),
-		[CPUMF_CTR_SET_CRYPTO] = ATOMIC_INIT(0),
-		[CPUMF_CTR_SET_EXT]    = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_BASIC]	= ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_USER]	= ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_CRYPTO]	= ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_EXT]	= ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_MT_DIAG] = ATOMIC_INIT(0),
 	},
 	.state = 0,
 	.flags = 0,
 	.txn_flags = 0,
 };
 
-static int get_counter_set(u64 event)
+static enum cpumf_ctr_set get_counter_set(u64 event)
 {
-	int set = -1;
+	int set = CPUMF_CTR_SET_MAX;
 
 	if (event < 32)
 		set = CPUMF_CTR_SET_BASIC;
@@ -98,34 +93,17 @@ static int get_counter_set(u64 event)
 		set = CPUMF_CTR_SET_CRYPTO;
 	else if (event < 256)
 		set = CPUMF_CTR_SET_EXT;
+	else if (event >= 448 && event < 496)
+		set = CPUMF_CTR_SET_MT_DIAG;
 
 	return set;
 }
 
-static int validate_event(const struct hw_perf_event *hwc)
-{
-	switch (hwc->config_base) {
-	case CPUMF_CTR_SET_BASIC:
-	case CPUMF_CTR_SET_USER:
-	case CPUMF_CTR_SET_CRYPTO:
-	case CPUMF_CTR_SET_EXT:
-		/* check for reserved counters */
-		if ((hwc->config >=  6 && hwc->config <=  31) ||
-		    (hwc->config >= 38 && hwc->config <=  63) ||
-		    (hwc->config >= 80 && hwc->config <= 127))
-			return -EOPNOTSUPP;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int validate_ctr_version(const struct hw_perf_event *hwc)
 {
 	struct cpu_hw_events *cpuhw;
 	int err = 0;
+	u16 mtdiag_ctl;
 
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
@@ -145,6 +123,27 @@ static int validate_ctr_version(const struct hw_perf_event *hwc)
 		    (cpuhw->info.csvn  > 2 && hwc->config > 255))
 			err = -EOPNOTSUPP;
 		break;
+	case CPUMF_CTR_SET_MT_DIAG:
+		if (cpuhw->info.csvn <= 3)
+			err = -EOPNOTSUPP;
+		/*
+		 * MT-diagnostic counters are read-only.  The counter set
+		 * is automatically enabled and activated on all CPUs with
+		 * multithreading (SMT).  Deactivation of multithreading
+		 * also disables the counter set.  State changes are ignored
+		 * by lcctl().	Because Linux controls SMT enablement through
+		 * a kernel parameter only, the counter set is either disabled
+		 * or enabled and active.
+		 *
+		 * Thus, the counters can only be used if SMT is on and the
+		 * counter set is enabled and active.
+		 */
+		mtdiag_ctl = cpumf_state_ctl[CPUMF_CTR_SET_MT_DIAG];
+		if (!((cpuhw->info.auth_ctl & mtdiag_ctl) &&
+		      (cpuhw->info.enable_ctl & mtdiag_ctl) &&
+		      (cpuhw->info.act_ctl & mtdiag_ctl)))
+			err = -EOPNOTSUPP;
+		break;
 	}
 
 	put_cpu_var(cpu_hw_events);
@@ -250,6 +249,11 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 	/* loss of counter data alert */
 	if (alert & CPU_MF_INT_CF_LCDA)
 		pr_err("CPU[%i] Counter data was lost\n", smp_processor_id());
+
+	/* loss of MT counter data alert */
+	if (alert & CPU_MF_INT_CF_MTDA)
+		pr_warn("CPU[%i] MT counter data was lost\n",
+			smp_processor_id());
 }
 
 #define PMC_INIT      0
@@ -330,6 +334,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
+	enum cpumf_ctr_set set;
 	int err;
 	u64 ev;
 
@@ -370,25 +375,30 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if (ev == -1)
 		return -ENOENT;
 
-	if (ev >= PERF_CPUM_CF_MAX_CTR)
+	if (ev > PERF_CPUM_CF_MAX_CTR)
 		return -EINVAL;
 
-	/* Use the hardware perf event structure to store the counter number
-	 * in 'config' member and the counter set to which the counter belongs
-	 * in the 'config_base'.  The counter set (config_base) is then used
-	 * to enable/disable the counters.
-	 */
-	hwc->config = ev;
-	hwc->config_base = get_counter_set(ev);
-
-	/* Validate the counter that is assigned to this event.
-	 * Because the counter facility can use numerous counters at the
-	 * same time without constraints, it is not necessary to explicitly
-	 * validate event groups (event->group_leader != event).
-	 */
-	err = validate_event(hwc);
-	if (err)
-		return err;
+	/* Obtain the counter set to which the specified counter belongs */
+	set = get_counter_set(ev);
+	switch (set) {
+	case CPUMF_CTR_SET_BASIC:
+	case CPUMF_CTR_SET_USER:
+	case CPUMF_CTR_SET_CRYPTO:
+	case CPUMF_CTR_SET_EXT:
+	case CPUMF_CTR_SET_MT_DIAG:
+		/*
+		 * Use the hardware perf event structure to store the
+		 * counter number in the 'config' member and the counter
+		 * set number in the 'config_base'.  The counter set number
+		 * is then later used to enable/disable the counter(s).
+		 */
+		hwc->config = ev;
+		hwc->config_base = set;
+		break;
+	case CPUMF_CTR_SET_MAX:
+		/* The counter could not be associated to a counter set */
+		return -EINVAL;
+	};
 
 	/* Initialize for using the CPU-measurement counter facility */
 	if (!atomic_inc_not_zero(&num_events)) {
@@ -452,7 +462,7 @@ static int hw_perf_event_reset(struct perf_event *event)
 	return err;
 }
 
-static int hw_perf_event_update(struct perf_event *event)
+static void hw_perf_event_update(struct perf_event *event)
 {
 	u64 prev, new, delta;
 	int err;
@@ -461,14 +471,12 @@ static int hw_perf_event_update(struct perf_event *event)
 		prev = local64_read(&event->hw.prev_count);
 		err = ecctr(event->hw.config, &new);
 		if (err)
-			goto out;
+			return;
 	} while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
 
 	delta = (prev <= new) ? new - prev
 			      : (-1ULL - prev) + new + 1;	 /* overflow */
 	local64_add(delta, &event->count);
-out:
-	return err;
 }
 
 static void cpumf_pmu_read(struct perf_event *event)
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index c343ac2cf6c5..d3133285b7d1 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -114,8 +114,64 @@ CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1);
 CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
 CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
 CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
+CPUMF_EVENT_ATTR(cf_z13, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z13, DTLB1_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z13, DTLB1_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z13, DTLB1_HPAGE_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z13, DTLB1_GPAGE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z13, L1D_L2D_SOURCED_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_z13, ITLB1_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z13, ITLB1_MISSES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z13, L1I_L2I_SOURCED_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z13, TLB2_PTE_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z13, TLB2_CRSTE_HPAGE_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z13, TLB2_CRSTE_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z13, TX_C_TEND, 0x008c);
+CPUMF_EVENT_ATTR(cf_z13, TX_NC_TEND, 0x008d);
+CPUMF_EVENT_ATTR(cf_z13, L1C_TLB1_MISSES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONCHIP_L3_SOURCED_WRITES_IV, 0x0091);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONNODE_L4_SOURCED_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONNODE_L3_SOURCED_WRITES_IV, 0x0093);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONNODE_L3_SOURCED_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONDRAWER_L4_SOURCED_WRITES, 0x0095);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONDRAWER_L3_SOURCED_WRITES_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONDRAWER_L3_SOURCED_WRITES, 0x0097);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES, 0x0098);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV, 0x0099);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES, 0x009a);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV, 0x009c);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES, 0x009d);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONNODE_MEM_SOURCED_WRITES, 0x009e);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONDRAWER_MEM_SOURCED_WRITES, 0x009f);
+CPUMF_EVENT_ATTR(cf_z13, L1D_OFFDRAWER_MEM_SOURCED_WRITES, 0x00a0);
+CPUMF_EVENT_ATTR(cf_z13, L1D_ONCHIP_MEM_SOURCED_WRITES, 0x00a1);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONCHIP_L3_SOURCED_WRITES, 0x00a2);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONCHIP_L3_SOURCED_WRITES_IV, 0x00a3);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONNODE_L4_SOURCED_WRITES, 0x00a4);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONNODE_L3_SOURCED_WRITES_IV, 0x00a5);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONNODE_L3_SOURCED_WRITES, 0x00a6);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONDRAWER_L4_SOURCED_WRITES, 0x00a7);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONDRAWER_L3_SOURCED_WRITES_IV, 0x00a8);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONDRAWER_L3_SOURCED_WRITES, 0x00a9);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES, 0x00aa);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV, 0x00ab);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES, 0x00ac);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES, 0x00ad);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV, 0x00ae);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES, 0x00af);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONNODE_MEM_SOURCED_WRITES, 0x00b0);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONDRAWER_MEM_SOURCED_WRITES, 0x00b1);
+CPUMF_EVENT_ATTR(cf_z13, L1I_OFFDRAWER_MEM_SOURCED_WRITES, 0x00b2);
+CPUMF_EVENT_ATTR(cf_z13, L1I_ONCHIP_MEM_SOURCED_WRITES, 0x00b3);
+CPUMF_EVENT_ATTR(cf_z13, TX_NC_TABORT, 0x00da);
+CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_NO_SPECIAL, 0x00db);
+CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_SPECIAL, 0x00dc);
+CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
+CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 
-static struct attribute *cpumcf_pmu_event_attr[] = {
+static struct attribute *cpumcf_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf, CPU_CYCLES),
 	CPUMF_EVENT_PTR(cf, INSTRUCTIONS),
 	CPUMF_EVENT_PTR(cf, L1I_DIR_WRITES),
@@ -236,28 +292,87 @@ static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
+static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z13, L1D_WRITES_RO_EXCL),
+	CPUMF_EVENT_PTR(cf_z13, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z13, DTLB1_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, DTLB1_GPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_L2D_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_L2I_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, TX_C_TEND),
+	CPUMF_EVENT_PTR(cf_z13, TX_NC_TEND),
+	CPUMF_EVENT_PTR(cf_z13, L1C_TLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONNODE_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONNODE_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONNODE_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONDRAWER_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONDRAWER_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONDRAWER_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONNODE_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONDRAWER_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_OFFDRAWER_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1D_ONCHIP_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONNODE_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONNODE_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONNODE_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONDRAWER_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONDRAWER_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONDRAWER_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONNODE_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONDRAWER_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_OFFDRAWER_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, L1I_ONCHIP_MEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z13, TX_NC_TABORT),
+	CPUMF_EVENT_PTR(cf_z13, TX_C_TABORT_NO_SPECIAL),
+	CPUMF_EVENT_PTR(cf_z13, TX_C_TABORT_SPECIAL),
+	CPUMF_EVENT_PTR(cf_z13, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
+	CPUMF_EVENT_PTR(cf_z13, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
+	NULL,
+};
+
 /* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
 
-static struct attribute_group cpumsf_pmu_events_group = {
+static struct attribute_group cpumcf_pmu_events_group = {
 	.name = "events",
-	.attrs = cpumcf_pmu_event_attr,
 };
 
 PMU_FORMAT_ATTR(event, "config:0-63");
 
-static struct attribute *cpumsf_pmu_format_attr[] = {
+static struct attribute *cpumcf_pmu_format_attr[] = {
 	&format_attr_event.attr,
 	NULL,
 };
 
-static struct attribute_group cpumsf_pmu_format_group = {
+static struct attribute_group cpumcf_pmu_format_group = {
 	.name = "format",
-	.attrs = cpumsf_pmu_format_attr,
+	.attrs = cpumcf_pmu_format_attr,
 };
 
-static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
-	&cpumsf_pmu_events_group,
-	&cpumsf_pmu_format_group,
+static const struct attribute_group *cpumcf_pmu_attr_groups[] = {
+	&cpumcf_pmu_events_group,
+	&cpumcf_pmu_format_group,
 	NULL,
 };
 
@@ -290,6 +405,7 @@ static __init struct attribute **merge_attr(struct attribute **a,
 __init const struct attribute_group **cpumf_cf_event_group(void)
 {
 	struct attribute **combined, **model;
+	struct attribute *none[] = { NULL };
 	struct cpuid cpu_id;
 
 	get_cpu_id(&cpu_id);
@@ -306,17 +422,17 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	case 0x2828:
 		model = cpumcf_zec12_pmu_event_attr;
 		break;
+	case 0x2964:
+	case 0x2965:
+		model = cpumcf_z13_pmu_event_attr;
+		break;
 	default:
-		model = NULL;
+		model = none;
 		break;
 	}
 
-	if (!model)
-		goto out;
-
 	combined = merge_attr(cpumcf_pmu_event_attr, model);
 	if (combined)
-		cpumsf_pmu_events_group.attrs = combined;
-out:
-	return cpumsf_pmu_attr_groups;
+		cpumcf_pmu_events_group.attrs = combined;
+	return cpumcf_pmu_attr_groups;
 }
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 1c0b58545c04..9a4f279d25ca 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1009,8 +1009,8 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 	 * sample. Some early samples or samples from guests without
 	 * lpp usage would be misaccounted to the host. We use the asn
 	 * value as an addon heuristic to detect most of these guest samples.
-	 * If the value differs from the host hpp value, we assume to be a
-	 * KVM guest.
+	 * If the value differs from 0xffff (the host value), we assume to
+	 * be a KVM guest.
 	 */
 	switch (sfr->basic.CL) {
 	case 1: /* logical partition */
@@ -1020,8 +1020,7 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 		sde_regs->in_guest = 1;
 		break;
 	default: /* old machine, use heuristics */
-		if (sfr->basic.gpp ||
-		    sfr->basic.prim_asn != (u16)sfr->basic.hpp)
+		if (sfr->basic.gpp || sfr->basic.prim_asn != 0xffff)
 			sde_regs->in_guest = 1;
 		break;
 	}
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 20cd339e11ae..999d7154bbdc 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -73,8 +73,10 @@ extern void kernel_thread_starter(void);
  */
 void exit_thread(struct task_struct *tsk)
 {
-	if (tsk == current)
+	if (tsk == current) {
 		exit_thread_runtime_instr();
+		exit_thread_gs();
+	}
 }
 
 void flush_thread(void)
@@ -124,7 +126,10 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
 	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
 	/* Initialize per thread user and system timer values */
 	p->thread.user_timer = 0;
+	p->thread.guest_timer = 0;
 	p->thread.system_timer = 0;
+	p->thread.hardirq_timer = 0;
+	p->thread.softirq_timer = 0;
 
 	frame->sf.back_chain = 0;
 	/* new return point is ret_from_fork */
@@ -156,6 +161,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
 	/* Don't copy runtime instrumentation info */
 	p->thread.ri_cb = NULL;
 	frame->childregs.psw.mask &= ~PSW_MASK_RI;
+	/* Don't copy guarded storage control block */
+	p->thread.gs_cb = NULL;
+	p->thread.gs_bc_cb = NULL;
 
 	/* Set a new TLS ?  */
 	if (clone_flags & CLONE_SETTLS) {
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 928b929a6261..778cd6536175 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -7,6 +7,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/cpufeature.h>
+#include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/sched/mm.h>
 #include <linux/init.h>
@@ -91,11 +92,23 @@ int cpu_have_feature(unsigned int num)
 }
 EXPORT_SYMBOL(cpu_have_feature);
 
+static void show_facilities(struct seq_file *m)
+{
+	unsigned int bit;
+	long *facilities;
+
+	facilities = (long *)&S390_lowcore.stfle_fac_list;
+	seq_puts(m, "facilities      :");
+	for_each_set_bit_inv(bit, facilities, MAX_FACILITY_BIT)
+		seq_printf(m, " %d", bit);
+	seq_putc(m, '\n');
+}
+
 static void show_cpu_summary(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe"
+		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs"
 	};
 	static const char * const int_hwcap_str[] = {
 		"sie"
@@ -116,6 +129,7 @@ static void show_cpu_summary(struct seq_file *m, void *v)
 		if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
 			seq_printf(m, "%s ", int_hwcap_str[i]);
 	seq_puts(m, "\n");
+	show_facilities(m);
 	show_cacheinfo(m);
 	for_each_online_cpu(cpu) {
 		struct cpuid *id = &per_cpu(cpu_info.cpu_id, cpu);
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index c14df0a1ec3c..488c5bb8dc77 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -44,30 +44,42 @@ void update_cr_regs(struct task_struct *task)
 	struct pt_regs *regs = task_pt_regs(task);
 	struct thread_struct *thread = &task->thread;
 	struct per_regs old, new;
-
+	unsigned long cr0_old, cr0_new;
+	unsigned long cr2_old, cr2_new;
+	int cr0_changed, cr2_changed;
+
+	__ctl_store(cr0_old, 0, 0);
+	__ctl_store(cr2_old, 2, 2);
+	cr0_new = cr0_old;
+	cr2_new = cr2_old;
 	/* Take care of the enable/disable of transactional execution. */
 	if (MACHINE_HAS_TE) {
-		unsigned long cr, cr_new;
-
-		__ctl_store(cr, 0, 0);
 		/* Set or clear transaction execution TXC bit 8. */
-		cr_new = cr | (1UL << 55);
+		cr0_new |= (1UL << 55);
 		if (task->thread.per_flags & PER_FLAG_NO_TE)
-			cr_new &= ~(1UL << 55);
-		if (cr_new != cr)
-			__ctl_load(cr_new, 0, 0);
+			cr0_new &= ~(1UL << 55);
 		/* Set or clear transaction execution TDC bits 62 and 63. */
-		__ctl_store(cr, 2, 2);
-		cr_new = cr & ~3UL;
+		cr2_new &= ~3UL;
 		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
 			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
-				cr_new |= 1UL;
+				cr2_new |= 1UL;
 			else
-				cr_new |= 2UL;
+				cr2_new |= 2UL;
 		}
-		if (cr_new != cr)
-			__ctl_load(cr_new, 2, 2);
 	}
+	/* Take care of enable/disable of guarded storage. */
+	if (MACHINE_HAS_GS) {
+		cr2_new &= ~(1UL << 4);
+		if (task->thread.gs_cb)
+			cr2_new |= (1UL << 4);
+	}
+	/* Load control register 0/2 iff changed */
+	cr0_changed = cr0_new != cr0_old;
+	cr2_changed = cr2_new != cr2_old;
+	if (cr0_changed)
+		__ctl_load(cr0_new, 0, 0);
+	if (cr2_changed)
+		__ctl_load(cr2_new, 2, 2);
 	/* Copy user specified PER registers */
 	new.control = thread->per_user.control;
 	new.start = thread->per_user.start;
@@ -1137,6 +1149,74 @@ static int s390_system_call_set(struct task_struct *target,
 				  data, 0, sizeof(unsigned int));
 }
 
+static int s390_gs_cb_get(struct task_struct *target,
+			  const struct user_regset *regset,
+			  unsigned int pos, unsigned int count,
+			  void *kbuf, void __user *ubuf)
+{
+	struct gs_cb *data = target->thread.gs_cb;
+
+	if (!MACHINE_HAS_GS)
+		return -ENODEV;
+	if (!data)
+		return -ENODATA;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   data, 0, sizeof(struct gs_cb));
+}
+
+static int s390_gs_cb_set(struct task_struct *target,
+			  const struct user_regset *regset,
+			  unsigned int pos, unsigned int count,
+			  const void *kbuf, const void __user *ubuf)
+{
+	struct gs_cb *data = target->thread.gs_cb;
+
+	if (!MACHINE_HAS_GS)
+		return -ENODEV;
+	if (!data) {
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+		target->thread.gs_cb = data;
+	}
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  data, 0, sizeof(struct gs_cb));
+}
+
+static int s390_gs_bc_get(struct task_struct *target,
+			  const struct user_regset *regset,
+			  unsigned int pos, unsigned int count,
+			  void *kbuf, void __user *ubuf)
+{
+	struct gs_cb *data = target->thread.gs_bc_cb;
+
+	if (!MACHINE_HAS_GS)
+		return -ENODEV;
+	if (!data)
+		return -ENODATA;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   data, 0, sizeof(struct gs_cb));
+}
+
+static int s390_gs_bc_set(struct task_struct *target,
+			  const struct user_regset *regset,
+			  unsigned int pos, unsigned int count,
+			  const void *kbuf, const void __user *ubuf)
+{
+	struct gs_cb *data = target->thread.gs_bc_cb;
+
+	if (!MACHINE_HAS_GS)
+		return -ENODEV;
+	if (!data) {
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+		target->thread.gs_bc_cb = data;
+	}
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  data, 0, sizeof(struct gs_cb));
+}
+
 static const struct user_regset s390_regsets[] = {
 	{
 		.core_note_type = NT_PRSTATUS,
@@ -1194,6 +1274,22 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_vxrs_high_get,
 		.set = s390_vxrs_high_set,
 	},
+	{
+		.core_note_type = NT_S390_GS_CB,
+		.n = sizeof(struct gs_cb) / sizeof(__u64),
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.get = s390_gs_cb_get,
+		.set = s390_gs_cb_set,
+	},
+	{
+		.core_note_type = NT_S390_GS_BC,
+		.n = sizeof(struct gs_cb) / sizeof(__u64),
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.get = s390_gs_bc_get,
+		.set = s390_gs_bc_set,
+	},
 };
 
 static const struct user_regset_view user_s390_view = {
@@ -1422,6 +1518,14 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_regs_high_get,
 		.set = s390_compat_regs_high_set,
 	},
+	{
+		.core_note_type = NT_S390_GS_CB,
+		.n = sizeof(struct gs_cb) / sizeof(__u64),
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.get = s390_gs_cb_get,
+		.set = s390_gs_cb_set,
+	},
 };
 
 static const struct user_regset_view user_s390_compat_view = {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 911dc0b49be0..3ae756c0db3d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -339,9 +339,15 @@ static void __init setup_lowcore(void)
 	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
 	       MAX_FACILITY_BIT/8);
-	if (MACHINE_HAS_VX)
-		lc->vector_save_area_addr =
-			(unsigned long) &lc->vector_save_area;
+	if (MACHINE_HAS_VX || MACHINE_HAS_GS) {
+		unsigned long bits, size;
+
+		bits = MACHINE_HAS_GS ? 11 : 10;
+		size = 1UL << bits;
+		lc->mcesad = (__u64) memblock_virt_alloc(size, size);
+		if (MACHINE_HAS_GS)
+			lc->mcesad |= bits;
+	}
 	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
 	lc->async_enter_timer = S390_lowcore.async_enter_timer;
@@ -779,6 +785,12 @@ static int __init setup_hwcaps(void)
 			elf_hwcap |= HWCAP_S390_VXRS_BCD;
 	}
 
+	/*
+	 * Guarded storage support HWCAP_S390_GS is bit 12.
+	 */
+	if (MACHINE_HAS_GS)
+		elf_hwcap |= HWCAP_S390_GS;
+
 	get_cpu_id(&cpu_id);
 	add_device_randomness(&cpu_id, sizeof(cpu_id));
 	switch (cpu_id.machine) {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 47a973b5b4f1..363000a77ffc 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -51,6 +51,7 @@
 #include <asm/os_info.h>
 #include <asm/sigp.h>
 #include <asm/idle.h>
+#include <asm/nmi.h>
 #include "entry.h"
 
 enum {
@@ -78,6 +79,8 @@ struct pcpu {
 static u8 boot_core_type;
 static struct pcpu pcpu_devices[NR_CPUS];
 
+static struct kmem_cache *pcpu_mcesa_cache;
+
 unsigned int smp_cpu_mt_shift;
 EXPORT_SYMBOL(smp_cpu_mt_shift);
 
@@ -188,8 +191,10 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
 static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 {
 	unsigned long async_stack, panic_stack;
+	unsigned long mcesa_origin, mcesa_bits;
 	struct lowcore *lc;
 
+	mcesa_origin = mcesa_bits = 0;
 	if (pcpu != &pcpu_devices[0]) {
 		pcpu->lowcore =	(struct lowcore *)
 			__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
@@ -197,20 +202,27 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 		panic_stack = __get_free_page(GFP_KERNEL);
 		if (!pcpu->lowcore || !panic_stack || !async_stack)
 			goto out;
+		if (MACHINE_HAS_VX || MACHINE_HAS_GS) {
+			mcesa_origin = (unsigned long)
+				kmem_cache_alloc(pcpu_mcesa_cache, GFP_KERNEL);
+			if (!mcesa_origin)
+				goto out;
+			mcesa_bits = MACHINE_HAS_GS ? 11 : 0;
+		}
 	} else {
 		async_stack = pcpu->lowcore->async_stack - ASYNC_FRAME_OFFSET;
 		panic_stack = pcpu->lowcore->panic_stack - PANIC_FRAME_OFFSET;
+		mcesa_origin = pcpu->lowcore->mcesad & MCESA_ORIGIN_MASK;
+		mcesa_bits = pcpu->lowcore->mcesad & MCESA_LC_MASK;
 	}
 	lc = pcpu->lowcore;
 	memcpy(lc, &S390_lowcore, 512);
 	memset((char *) lc + 512, 0, sizeof(*lc) - 512);
 	lc->async_stack = async_stack + ASYNC_FRAME_OFFSET;
 	lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET;
+	lc->mcesad = mcesa_origin | mcesa_bits;
 	lc->cpu_nr = cpu;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
-	if (MACHINE_HAS_VX)
-		lc->vector_save_area_addr =
-			(unsigned long) &lc->vector_save_area;
 	if (vdso_alloc_per_cpu(lc))
 		goto out;
 	lowcore_ptr[cpu] = lc;
@@ -218,6 +230,9 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	return 0;
 out:
 	if (pcpu != &pcpu_devices[0]) {
+		if (mcesa_origin)
+			kmem_cache_free(pcpu_mcesa_cache,
+					(void *) mcesa_origin);
 		free_page(panic_stack);
 		free_pages(async_stack, ASYNC_ORDER);
 		free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
@@ -229,11 +244,17 @@ out:
 
 static void pcpu_free_lowcore(struct pcpu *pcpu)
 {
+	unsigned long mcesa_origin;
+
 	pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0);
 	lowcore_ptr[pcpu - pcpu_devices] = NULL;
 	vdso_free_per_cpu(pcpu->lowcore);
 	if (pcpu == &pcpu_devices[0])
 		return;
+	if (MACHINE_HAS_VX || MACHINE_HAS_GS) {
+		mcesa_origin = pcpu->lowcore->mcesad & MCESA_ORIGIN_MASK;
+		kmem_cache_free(pcpu_mcesa_cache, (void *) mcesa_origin);
+	}
 	free_page(pcpu->lowcore->panic_stack-PANIC_FRAME_OFFSET);
 	free_pages(pcpu->lowcore->async_stack-ASYNC_FRAME_OFFSET, ASYNC_ORDER);
 	free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
@@ -550,9 +571,11 @@ int smp_store_status(int cpu)
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
 			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
-	if (!MACHINE_HAS_VX)
+	if (!MACHINE_HAS_VX && !MACHINE_HAS_GS)
 		return 0;
-	pa = __pa(pcpu->lowcore->vector_save_area_addr);
+	pa = __pa(pcpu->lowcore->mcesad & MCESA_ORIGIN_MASK);
+	if (MACHINE_HAS_GS)
+		pa |= pcpu->lowcore->mcesad & MCESA_LC_MASK;
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
 			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
@@ -897,25 +920,33 @@ void __init smp_fill_possible_mask(void)
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
+	unsigned long size;
+
 	/* request the 0x1201 emergency signal external interrupt */
 	if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt))
 		panic("Couldn't request external interrupt 0x1201");
 	/* request the 0x1202 external call external interrupt */
 	if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt))
 		panic("Couldn't request external interrupt 0x1202");
+	/* create slab cache for the machine-check-extended-save-areas */
+	if (MACHINE_HAS_VX || MACHINE_HAS_GS) {
+		size = 1UL << (MACHINE_HAS_GS ? 11 : 10);
+		pcpu_mcesa_cache = kmem_cache_create("nmi_save_areas",
+						     size, size, 0, NULL);
+		if (!pcpu_mcesa_cache)
+			panic("Couldn't create nmi save area cache");
+	}
 }
 
 void __init smp_prepare_boot_cpu(void)
 {
 	struct pcpu *pcpu = pcpu_devices;
 
+	WARN_ON(!cpu_present(0) || !cpu_online(0));
 	pcpu->state = CPU_STATE_CONFIGURED;
-	pcpu->address = stap();
 	pcpu->lowcore = (struct lowcore *)(unsigned long) store_prefix();
 	S390_lowcore.percpu_offset = __per_cpu_offset[0];
 	smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
-	set_cpu_present(0, true);
-	set_cpu_online(0, true);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -924,6 +955,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_setup_processor_id(void)
 {
+	pcpu_devices[0].address = stap();
 	S390_lowcore.cpu_nr = 0;
 	S390_lowcore.spinlock_lockval = arch_spin_lockval(0);
 }
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 9b59e6212d8f..54fce7b065de 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -386,3 +386,5 @@ SYSCALL(sys_mlock2,compat_sys_mlock2)
 SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */
 SYSCALL(sys_preadv2,compat_sys_preadv2)
 SYSCALL(sys_pwritev2,compat_sys_pwritev2)
+SYSCALL(sys_s390_guarded_storage,compat_sys_s390_guarded_storage) /* 378 */
+SYSCALL(sys_statx,compat_sys_statx)
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 12b6b138e354..eefcb54872a5 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -4,6 +4,7 @@
  *	       Martin Schwidefsky <schwidefsky@de.ibm.com>,
  */
 
+#include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/proc_fs.h>
@@ -13,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <asm/ebcdic.h>
+#include <asm/debug.h>
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/topology.h>
@@ -485,3 +487,99 @@ void calibrate_delay(void)
 	       "%lu.%02lu BogoMIPS preset\n", loops_per_jiffy/(500000/HZ),
 	       (loops_per_jiffy/(5000/HZ)) % 100);
 }
+
+#ifdef CONFIG_DEBUG_FS
+
+#define STSI_FILE(fc, s1, s2)						       \
+static int stsi_open_##fc##_##s1##_##s2(struct inode *inode, struct file *file)\
+{									       \
+	file->private_data = (void *) get_zeroed_page(GFP_KERNEL);	       \
+	if (!file->private_data)					       \
+		return -ENOMEM;						       \
+	if (stsi(file->private_data, fc, s1, s2)) {			       \
+		free_page((unsigned long)file->private_data);		       \
+		file->private_data = NULL;				       \
+		return -EACCES;						       \
+	}								       \
+	return nonseekable_open(inode, file);				       \
+}									       \
+									       \
+static const struct file_operations stsi_##fc##_##s1##_##s2##_fs_ops = {       \
+	.open		= stsi_open_##fc##_##s1##_##s2,			       \
+	.release	= stsi_release,					       \
+	.read		= stsi_read,					       \
+	.llseek		= no_llseek,					       \
+};
+
+static int stsi_release(struct inode *inode, struct file *file)
+{
+	free_page((unsigned long)file->private_data);
+	return 0;
+}
+
+static ssize_t stsi_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, size, ppos, file->private_data, PAGE_SIZE);
+}
+
+STSI_FILE( 1, 1, 1);
+STSI_FILE( 1, 2, 1);
+STSI_FILE( 1, 2, 2);
+STSI_FILE( 2, 2, 1);
+STSI_FILE( 2, 2, 2);
+STSI_FILE( 3, 2, 2);
+STSI_FILE(15, 1, 2);
+STSI_FILE(15, 1, 3);
+STSI_FILE(15, 1, 4);
+STSI_FILE(15, 1, 5);
+STSI_FILE(15, 1, 6);
+
+struct stsi_file {
+	const struct file_operations *fops;
+	char *name;
+};
+
+static struct stsi_file stsi_file[] __initdata = {
+	{.fops = &stsi_1_1_1_fs_ops,  .name =  "1_1_1"},
+	{.fops = &stsi_1_2_1_fs_ops,  .name =  "1_2_1"},
+	{.fops = &stsi_1_2_2_fs_ops,  .name =  "1_2_2"},
+	{.fops = &stsi_2_2_1_fs_ops,  .name =  "2_2_1"},
+	{.fops = &stsi_2_2_2_fs_ops,  .name =  "2_2_2"},
+	{.fops = &stsi_3_2_2_fs_ops,  .name =  "3_2_2"},
+	{.fops = &stsi_15_1_2_fs_ops, .name = "15_1_2"},
+	{.fops = &stsi_15_1_3_fs_ops, .name = "15_1_3"},
+	{.fops = &stsi_15_1_4_fs_ops, .name = "15_1_4"},
+	{.fops = &stsi_15_1_5_fs_ops, .name = "15_1_5"},
+	{.fops = &stsi_15_1_6_fs_ops, .name = "15_1_6"},
+};
+
+static u8 stsi_0_0_0;
+
+static __init int stsi_init_debugfs(void)
+{
+	struct dentry *stsi_root;
+	struct stsi_file *sf;
+	int lvl, i;
+
+	stsi_root = debugfs_create_dir("stsi", arch_debugfs_dir);
+	if (IS_ERR_OR_NULL(stsi_root))
+		return 0;
+	lvl = stsi(NULL, 0, 0, 0);
+	if (lvl > 0)
+		stsi_0_0_0 = lvl;
+	debugfs_create_u8("0_0_0", 0400, stsi_root, &stsi_0_0_0);
+	for (i = 0; i < ARRAY_SIZE(stsi_file); i++) {
+		sf = &stsi_file[i];
+		debugfs_create_file(sf->name, 0400, stsi_root, NULL, sf->fops);
+	}
+	if (IS_ENABLED(CONFIG_SCHED_TOPOLOGY) && MACHINE_HAS_TOPOLOGY) {
+		char link_to[10];
+
+		sprintf(link_to, "15_1_%d", topology_mnest_limit());
+		debugfs_create_symlink("topology", stsi_root, link_to);
+	}
+	return 0;
+}
+device_initcall(stsi_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index c31da46bc037..c3a52f9a69a0 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -158,7 +158,9 @@ void init_cpu_timer(void)
 	cd->mult		= 16777;
 	cd->shift		= 12;
 	cd->min_delta_ns	= 1;
+	cd->min_delta_ticks	= 1;
 	cd->max_delta_ns	= LONG_MAX;
+	cd->max_delta_ticks	= ULONG_MAX;
 	cd->rating		= 400;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= s390_next_event;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 17660e800e74..bb47c92476f0 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -83,6 +83,8 @@ static cpumask_t cpu_thread_map(unsigned int cpu)
 	return mask;
 }
 
+#define TOPOLOGY_CORE_BITS	64
+
 static void add_cpus_to_mask(struct topology_core *tl_core,
 			     struct mask_info *drawer,
 			     struct mask_info *book,
@@ -91,7 +93,7 @@ static void add_cpus_to_mask(struct topology_core *tl_core,
 	struct cpu_topology_s390 *topo;
 	unsigned int core;
 
-	for_each_set_bit(core, &tl_core->mask[0], TOPOLOGY_CORE_BITS) {
+	for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) {
 		unsigned int rcore;
 		int lcpu, i;
 
@@ -244,7 +246,7 @@ static void update_cpu_masks(void)
 
 void store_topology(struct sysinfo_15_1_x *info)
 {
-	stsi(info, 15, 1, min(topology_max_mnest, 4));
+	stsi(info, 15, 1, topology_mnest_limit());
 }
 
 static int __arch_update_cpu_topology(void)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 5ccf95396251..72307f108c40 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -63,11 +63,9 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	__start_ro_after_init = .;
-	__start_data_ro_after_init = .;
 	.data..ro_after_init : {
 		 *(.data..ro_after_init)
 	}
-	__end_data_ro_after_init = .;
 	EXCEPTION_TABLE(16)
 	. = ALIGN(PAGE_SIZE);
 	__end_ro_after_init = .;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c14fc9029912..072d84ba42a3 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -111,7 +111,7 @@ static inline u64 scale_vtime(u64 vtime)
 }
 
 static void account_system_index_scaled(struct task_struct *p,
-					cputime_t cputime, cputime_t scaled,
+					u64 cputime, u64 scaled,
 					enum cpu_usage_stat index)
 {
 	p->stimescaled += cputime_to_nsecs(scaled);
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index d55c829a5944..ddbffb715b40 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -168,8 +168,7 @@ union page_table_entry {
 		unsigned long z  : 1; /* Zero Bit */
 		unsigned long i  : 1; /* Page-Invalid Bit */
 		unsigned long p  : 1; /* DAT-Protection Bit */
-		unsigned long co : 1; /* Change-Recording Override */
-		unsigned long	 : 8;
+		unsigned long	 : 9;
 	};
 };
 
@@ -745,8 +744,6 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 		return PGM_PAGE_TRANSLATION;
 	if (pte.z)
 		return PGM_TRANSLATION_SPEC;
-	if (pte.co && !edat1)
-		return PGM_TRANSLATION_SPEC;
 	dat_protection |= pte.p;
 	raddr.pfra = pte.pfra;
 real_address:
@@ -1182,7 +1179,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 		rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
 	if (!rc && pte.i)
 		rc = PGM_PAGE_TRANSLATION;
-	if (!rc && (pte.z || (pte.co && sg->edat_level < 1)))
+	if (!rc && pte.z)
 		rc = PGM_TRANSLATION_SPEC;
 shadow_page:
 	pte.p |= dat_protection;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 0f8f14199734..169558dc7daf 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -420,8 +420,8 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	/* Extended save area */
-	rc = read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, &ext_sa_addr,
-			    sizeof(unsigned long));
+	rc = read_guest_lc(vcpu, __LC_MCESAD, &ext_sa_addr,
+			   sizeof(unsigned long));
 	/* Only bits 0-53 are used for address formation */
 	ext_sa_addr &= ~0x3ffUL;
 	if (!rc && mci.vr && ext_sa_addr && test_kvm_facility(vcpu->kvm, 129)) {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index fd6cd05bb6a7..d5c5c911821a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -273,7 +273,7 @@ static void kvm_s390_cpu_feat_init(void)
 			      kvm_s390_available_subfunc.pcc);
 	}
 	if (test_facility(57)) /* MSA5 */
-		__cpacf_query(CPACF_PPNO, (cpacf_mask_t *)
+		__cpacf_query(CPACF_PRNO, (cpacf_mask_t *)
 			      kvm_s390_available_subfunc.ppno);
 
 	if (MACHINE_HAS_ESOP)
@@ -1512,9 +1512,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
 	} else {
 		if (sclp.hamax == U64_MAX)
-			kvm->arch.mem_limit = TASK_MAX_SIZE;
+			kvm->arch.mem_limit = TASK_SIZE_MAX;
 		else
-			kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+			kvm->arch.mem_limit = min_t(unsigned long, TASK_SIZE_MAX,
 						    sclp.hamax + 1);
 		kvm->arch.gmap = gmap_create(current->mm, kvm->arch.mem_limit - 1);
 		if (!kvm->arch.gmap)
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index ba427eb6f14c..ffb15bd4c593 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -17,7 +17,7 @@ int spin_retry = -1;
 static int __init spin_retry_init(void)
 {
 	if (spin_retry < 0)
-		spin_retry = MACHINE_HAS_CAD ? 10 : 1000;
+		spin_retry = 1000;
 	return 0;
 }
 early_initcall(spin_retry_init);
@@ -32,23 +32,17 @@ static int __init spin_retry_setup(char *str)
 }
 __setup("spin_retry=", spin_retry_setup);
 
-static inline void _raw_compare_and_delay(unsigned int *lock, unsigned int old)
-{
-	asm(".insn rsy,0xeb0000000022,%0,0,%1" : : "d" (old), "Q" (*lock));
-}
-
 void arch_spin_lock_wait(arch_spinlock_t *lp)
 {
-	unsigned int cpu = SPINLOCK_LOCKVAL;
-	unsigned int owner;
-	int count, first_diag;
+	int cpu = SPINLOCK_LOCKVAL;
+	int owner, count, first_diag;
 
 	first_diag = 1;
 	while (1) {
 		owner = ACCESS_ONCE(lp->lock);
 		/* Try to get the lock if it is free. */
 		if (!owner) {
-			if (_raw_compare_and_swap(&lp->lock, 0, cpu))
+			if (__atomic_cmpxchg_bool(&lp->lock, 0, cpu))
 				return;
 			continue;
 		}
@@ -61,8 +55,6 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 		/* Loop for a while on the lock value. */
 		count = spin_retry;
 		do {
-			if (MACHINE_HAS_CAD)
-				_raw_compare_and_delay(&lp->lock, owner);
 			owner = ACCESS_ONCE(lp->lock);
 		} while (owner && count-- > 0);
 		if (!owner)
@@ -82,9 +74,8 @@ EXPORT_SYMBOL(arch_spin_lock_wait);
 
 void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 {
-	unsigned int cpu = SPINLOCK_LOCKVAL;
-	unsigned int owner;
-	int count, first_diag;
+	int cpu = SPINLOCK_LOCKVAL;
+	int owner, count, first_diag;
 
 	local_irq_restore(flags);
 	first_diag = 1;
@@ -93,7 +84,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 		/* Try to get the lock if it is free. */
 		if (!owner) {
 			local_irq_disable();
-			if (_raw_compare_and_swap(&lp->lock, 0, cpu))
+			if (__atomic_cmpxchg_bool(&lp->lock, 0, cpu))
 				return;
 			local_irq_restore(flags);
 			continue;
@@ -107,8 +98,6 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 		/* Loop for a while on the lock value. */
 		count = spin_retry;
 		do {
-			if (MACHINE_HAS_CAD)
-				_raw_compare_and_delay(&lp->lock, owner);
 			owner = ACCESS_ONCE(lp->lock);
 		} while (owner && count-- > 0);
 		if (!owner)
@@ -128,18 +117,16 @@ EXPORT_SYMBOL(arch_spin_lock_wait_flags);
 
 int arch_spin_trylock_retry(arch_spinlock_t *lp)
 {
-	unsigned int cpu = SPINLOCK_LOCKVAL;
-	unsigned int owner;
-	int count;
+	int cpu = SPINLOCK_LOCKVAL;
+	int owner, count;
 
 	for (count = spin_retry; count > 0; count--) {
 		owner = READ_ONCE(lp->lock);
 		/* Try to get the lock if it is free. */
 		if (!owner) {
-			if (_raw_compare_and_swap(&lp->lock, 0, cpu))
+			if (__atomic_cmpxchg_bool(&lp->lock, 0, cpu))
 				return 1;
-		} else if (MACHINE_HAS_CAD)
-			_raw_compare_and_delay(&lp->lock, owner);
+		}
 	}
 	return 0;
 }
@@ -147,8 +134,8 @@ EXPORT_SYMBOL(arch_spin_trylock_retry);
 
 void _raw_read_lock_wait(arch_rwlock_t *rw)
 {
-	unsigned int owner, old;
 	int count = spin_retry;
+	int owner, old;
 
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 	__RAW_LOCK(&rw->lock, -1, __RAW_OP_ADD);
@@ -162,12 +149,9 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 		}
 		old = ACCESS_ONCE(rw->lock);
 		owner = ACCESS_ONCE(rw->owner);
-		if ((int) old < 0) {
-			if (MACHINE_HAS_CAD)
-				_raw_compare_and_delay(&rw->lock, old);
+		if (old < 0)
 			continue;
-		}
-		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
+		if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1))
 			return;
 	}
 }
@@ -175,17 +159,14 @@ EXPORT_SYMBOL(_raw_read_lock_wait);
 
 int _raw_read_trylock_retry(arch_rwlock_t *rw)
 {
-	unsigned int old;
 	int count = spin_retry;
+	int old;
 
 	while (count-- > 0) {
 		old = ACCESS_ONCE(rw->lock);
-		if ((int) old < 0) {
-			if (MACHINE_HAS_CAD)
-				_raw_compare_and_delay(&rw->lock, old);
+		if (old < 0)
 			continue;
-		}
-		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
+		if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1))
 			return 1;
 	}
 	return 0;
@@ -194,10 +175,10 @@ EXPORT_SYMBOL(_raw_read_trylock_retry);
 
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 
-void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev)
+void _raw_write_lock_wait(arch_rwlock_t *rw, int prev)
 {
-	unsigned int owner, old;
 	int count = spin_retry;
+	int owner, old;
 
 	owner = 0;
 	while (1) {
@@ -209,14 +190,12 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev)
 		old = ACCESS_ONCE(rw->lock);
 		owner = ACCESS_ONCE(rw->owner);
 		smp_mb();
-		if ((int) old >= 0) {
+		if (old >= 0) {
 			prev = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
 			old = prev;
 		}
-		if ((old & 0x7fffffff) == 0 && (int) prev >= 0)
+		if ((old & 0x7fffffff) == 0 && prev >= 0)
 			break;
-		if (MACHINE_HAS_CAD)
-			_raw_compare_and_delay(&rw->lock, old);
 	}
 }
 EXPORT_SYMBOL(_raw_write_lock_wait);
@@ -225,8 +204,8 @@ EXPORT_SYMBOL(_raw_write_lock_wait);
 
 void _raw_write_lock_wait(arch_rwlock_t *rw)
 {
-	unsigned int owner, old, prev;
 	int count = spin_retry;
+	int owner, old, prev;
 
 	prev = 0x80000000;
 	owner = 0;
@@ -238,15 +217,13 @@ void _raw_write_lock_wait(arch_rwlock_t *rw)
 		}
 		old = ACCESS_ONCE(rw->lock);
 		owner = ACCESS_ONCE(rw->owner);
-		if ((int) old >= 0 &&
-		    _raw_compare_and_swap(&rw->lock, old, old | 0x80000000))
+		if (old >= 0 &&
+		    __atomic_cmpxchg_bool(&rw->lock, old, old | 0x80000000))
 			prev = old;
 		else
 			smp_mb();
-		if ((old & 0x7fffffff) == 0 && (int) prev >= 0)
+		if ((old & 0x7fffffff) == 0 && prev >= 0)
 			break;
-		if (MACHINE_HAS_CAD)
-			_raw_compare_and_delay(&rw->lock, old);
 	}
 }
 EXPORT_SYMBOL(_raw_write_lock_wait);
@@ -255,24 +232,21 @@ EXPORT_SYMBOL(_raw_write_lock_wait);
 
 int _raw_write_trylock_retry(arch_rwlock_t *rw)
 {
-	unsigned int old;
 	int count = spin_retry;
+	int old;
 
 	while (count-- > 0) {
 		old = ACCESS_ONCE(rw->lock);
-		if (old) {
-			if (MACHINE_HAS_CAD)
-				_raw_compare_and_delay(&rw->lock, old);
+		if (old)
 			continue;
-		}
-		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
+		if (__atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000))
 			return 1;
 	}
 	return 0;
 }
 EXPORT_SYMBOL(_raw_write_trylock_retry);
 
-void arch_lock_relax(unsigned int cpu)
+void arch_lock_relax(int cpu)
 {
 	if (!cpu)
 		return;
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index f481fcde067b..1e5bb2b86c42 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -26,7 +26,7 @@ static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr
 	tmp1 = -4096UL;
 	asm volatile(
 		"0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n"
-		"9: jz    7f\n"
+		"6: jz    4f\n"
 		"1: algr  %0,%3\n"
 		"   slgr  %1,%3\n"
 		"   slgr  %2,%3\n"
@@ -35,23 +35,13 @@ static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr
 		"   nr    %4,%3\n"	/* %4 = (ptr + 4095) & -4096 */
 		"   slgr  %4,%1\n"
 		"   clgr  %0,%4\n"	/* copy crosses next page boundary? */
-		"   jnh   4f\n"
+		"   jnh   5f\n"
 		"3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n"
-		"10:slgr  %0,%4\n"
-		"   algr  %2,%4\n"
-		"4: lghi  %4,-1\n"
-		"   algr  %4,%0\n"	/* copy remaining size, subtract 1 */
-		"   bras  %3,6f\n"	/* memset loop */
-		"   xc    0(1,%2),0(%2)\n"
-		"5: xc    0(256,%2),0(%2)\n"
-		"   la    %2,256(%2)\n"
-		"6: aghi  %4,-256\n"
-		"   jnm   5b\n"
-		"   ex    %4,0(%3)\n"
-		"   j     8f\n"
-		"7: slgr  %0,%0\n"
-		"8:\n"
-		EX_TABLE(0b,2b) EX_TABLE(3b,4b) EX_TABLE(9b,2b) EX_TABLE(10b,4b)
+		"7: slgr  %0,%4\n"
+		"   j     5f\n"
+		"4: slgr  %0,%0\n"
+		"5:\n"
+		EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b)
 		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
 		: "d" (reg0) : "cc", "memory");
 	return size;
@@ -67,49 +57,38 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
 	asm volatile(
 		"   sacf  0\n"
 		"0: mvcp  0(%0,%2),0(%1),%3\n"
-		"10:jz    8f\n"
+		"7: jz    5f\n"
 		"1: algr  %0,%3\n"
 		"   la    %1,256(%1)\n"
 		"   la    %2,256(%2)\n"
 		"2: mvcp  0(%0,%2),0(%1),%3\n"
-		"11:jnz   1b\n"
-		"   j     8f\n"
+		"8: jnz   1b\n"
+		"   j     5f\n"
 		"3: la    %4,255(%1)\n"	/* %4 = ptr + 255 */
 		"   lghi  %3,-4096\n"
 		"   nr    %4,%3\n"	/* %4 = (ptr + 255) & -4096 */
 		"   slgr  %4,%1\n"
 		"   clgr  %0,%4\n"	/* copy crosses next page boundary? */
-		"   jnh   5f\n"
+		"   jnh   6f\n"
 		"4: mvcp  0(%4,%2),0(%1),%3\n"
-		"12:slgr  %0,%4\n"
-		"   algr  %2,%4\n"
-		"5: lghi  %4,-1\n"
-		"   algr  %4,%0\n"	/* copy remaining size, subtract 1 */
-		"   bras  %3,7f\n"	/* memset loop */
-		"   xc    0(1,%2),0(%2)\n"
-		"6: xc    0(256,%2),0(%2)\n"
-		"   la    %2,256(%2)\n"
-		"7: aghi  %4,-256\n"
-		"   jnm   6b\n"
-		"   ex    %4,0(%3)\n"
-		"   j     9f\n"
-		"8: slgr  %0,%0\n"
-		"9: sacf  768\n"
-		EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,5b)
-		EX_TABLE(10b,3b) EX_TABLE(11b,3b) EX_TABLE(12b,5b)
+		"9: slgr  %0,%4\n"
+		"   j     6f\n"
+		"5: slgr  %0,%0\n"
+		"6: sacf  768\n"
+		EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,6b)
+		EX_TABLE(7b,3b) EX_TABLE(8b,3b) EX_TABLE(9b,6b)
 		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
 		: : "cc", "memory");
 	return size;
 }
 
-unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	check_object_size(to, n, false);
 	if (static_branch_likely(&have_mvcos))
 		return copy_from_user_mvcos(to, from, n);
 	return copy_from_user_mvcp(to, from, n);
 }
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
 
 static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
 					       unsigned long size)
@@ -176,14 +155,13 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x,
 	return size;
 }
 
-unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	check_object_size(from, n, true);
 	if (static_branch_likely(&have_mvcos))
 		return copy_to_user_mvcos(to, from, n);
 	return copy_to_user_mvcs(to, from, n);
 }
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 
 static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from,
 					       unsigned long size)
@@ -240,13 +218,13 @@ static inline unsigned long copy_in_user_mvc(void __user *to, const void __user
 	return size;
 }
 
-unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n)
+unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
 	if (static_branch_likely(&have_mvcos))
 		return copy_in_user_mvcos(to, from, n);
 	return copy_in_user_mvc(to, from, n);
 }
-EXPORT_SYMBOL(__copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
 
 static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
 {
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index a07b1ec1391d..7f6db1e6c048 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -431,7 +431,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || from + len < from || to + len < to ||
-	    from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
+	    from + len - 1 > TASK_SIZE_MAX || to + len - 1 > gmap->asce_end)
 		return -EINVAL;
 
 	flush = 0;
@@ -2004,20 +2004,12 @@ EXPORT_SYMBOL_GPL(gmap_shadow_page);
  * Called with sg->parent->shadow_lock.
  */
 static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
-			       unsigned long offset, pte_t *pte)
+			       unsigned long gaddr, pte_t *pte)
 {
 	struct gmap_rmap *rmap, *rnext, *head;
-	unsigned long gaddr, start, end, bits, raddr;
-	unsigned long *table;
+	unsigned long start, end, bits, raddr;
 
 	BUG_ON(!gmap_is_shadow(sg));
-	spin_lock(&sg->parent->guest_table_lock);
-	table = radix_tree_lookup(&sg->parent->host_to_guest,
-				  vmaddr >> PMD_SHIFT);
-	gaddr = table ? __gmap_segment_gaddr(table) + offset : 0;
-	spin_unlock(&sg->parent->guest_table_lock);
-	if (!table)
-		return;
 
 	spin_lock(&sg->guest_table_lock);
 	if (sg->removed) {
@@ -2076,7 +2068,7 @@ static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
 void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 		 pte_t *pte, unsigned long bits)
 {
-	unsigned long offset, gaddr;
+	unsigned long offset, gaddr = 0;
 	unsigned long *table;
 	struct gmap *gmap, *sg, *next;
 
@@ -2084,22 +2076,23 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 	offset = offset * (4096 / sizeof(pte_t));
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
-		if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
-			spin_lock(&gmap->shadow_lock);
-			list_for_each_entry_safe(sg, next,
-						 &gmap->children, list)
-				gmap_shadow_notify(sg, vmaddr, offset, pte);
-			spin_unlock(&gmap->shadow_lock);
-		}
-		if (!(bits & PGSTE_IN_BIT))
-			continue;
 		spin_lock(&gmap->guest_table_lock);
 		table = radix_tree_lookup(&gmap->host_to_guest,
 					  vmaddr >> PMD_SHIFT);
 		if (table)
 			gaddr = __gmap_segment_gaddr(table) + offset;
 		spin_unlock(&gmap->guest_table_lock);
-		if (table)
+		if (!table)
+			continue;
+
+		if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
+			spin_lock(&gmap->shadow_lock);
+			list_for_each_entry_safe(sg, next,
+						 &gmap->children, list)
+				gmap_shadow_notify(sg, vmaddr, gaddr, pte);
+			spin_unlock(&gmap->shadow_lock);
+		}
+		if (bits & PGSTE_IN_BIT)
 			gmap_call_notifier(gmap, gaddr, gaddr + PAGE_SIZE - 1);
 	}
 	rcu_read_unlock();
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 18d4107e10ee..b7b779c40a5b 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -211,7 +211,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	addr = start;
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 	end = start + len;
-	if ((end <= start) || (end > TASK_SIZE))
+	if ((end <= start) || (end > mm->context.asce_limit))
 		return 0;
 	/*
 	 * local_irq_save() doesn't prevent pagetable teardown, but does
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 50618614881f..b017daed6887 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -89,19 +89,20 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	struct vm_unmapped_area_info info;
+	int rc;
 
 	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
-		return addr;
+		goto check_asce_limit;
 
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 		    (!vma || addr + len <= vma->vm_start))
-			return addr;
+			goto check_asce_limit;
 	}
 
 	info.flags = 0;
@@ -113,7 +114,18 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	else
 		info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
-	return vm_unmapped_area(&info);
+	addr = vm_unmapped_area(&info);
+	if (addr & ~PAGE_MASK)
+		return addr;
+
+check_asce_limit:
+	if (addr + len > current->mm->context.asce_limit) {
+		rc = crst_table_upgrade(mm);
+		if (rc)
+			return (unsigned long) rc;
+	}
+
+	return addr;
 }
 
 unsigned long
@@ -125,13 +137,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
+	int rc;
 
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
-		return addr;
+		goto check_asce_limit;
 
 	/* requesting a specific address */
 	if (addr) {
@@ -139,7 +152,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 				(!vma || addr + len <= vma->vm_start))
-			return addr;
+			goto check_asce_limit;
 	}
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
@@ -165,65 +178,20 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		info.low_limit = TASK_UNMAPPED_BASE;
 		info.high_limit = TASK_SIZE;
 		addr = vm_unmapped_area(&info);
+		if (addr & ~PAGE_MASK)
+			return addr;
 	}
 
-	return addr;
-}
-
-int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
-{
-	if (is_compat_task() || TASK_SIZE >= TASK_MAX_SIZE)
-		return 0;
-	if (!(flags & MAP_FIXED))
-		addr = 0;
-	if ((addr + len) >= TASK_SIZE)
-		return crst_table_upgrade(current->mm);
-	return 0;
-}
-
-static unsigned long
-s390_get_unmapped_area(struct file *filp, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long area;
-	int rc;
-
-	area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
-	if (!(area & ~PAGE_MASK))
-		return area;
-	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
-		/* Upgrade the page table to 4 levels and retry. */
+check_asce_limit:
+	if (addr + len > current->mm->context.asce_limit) {
 		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
-		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
 	}
-	return area;
-}
-
-static unsigned long
-s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
-			  const unsigned long len, const unsigned long pgoff,
-			  const unsigned long flags)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long area;
-	int rc;
 
-	area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags);
-	if (!(area & ~PAGE_MASK))
-		return area;
-	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
-		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm);
-		if (rc)
-			return (unsigned long) rc;
-		area = arch_get_unmapped_area_topdown(filp, addr, len,
-						      pgoff, flags);
-	}
-	return area;
+	return addr;
 }
+
 /*
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
@@ -241,9 +209,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	 */
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mmap_base_legacy(random_factor);
-		mm->get_unmapped_area = s390_get_unmapped_area;
+		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
 		mm->mmap_base = mmap_base(random_factor);
-		mm->get_unmapped_area = s390_get_unmapped_area_topdown;
+		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index 3330ea124eec..69a7b01ae746 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -13,8 +13,7 @@
 #include <linux/gfp.h>
 #include <linux/init.h>
 
-#define ESSA_SET_STABLE		1
-#define ESSA_SET_UNUSED		2
+#include <asm/page-states.h>
 
 static int cmma_flag = 1;
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index fc5dc33bb141..fc321c5ec30e 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -94,7 +94,7 @@ static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			new = pte_wrprotect(new);
 		else if (flags & SET_MEMORY_RW)
 			new = pte_mkwrite(pte_mkdirty(new));
-		if ((flags & SET_MEMORY_NX) && MACHINE_HAS_NX)
+		if (flags & SET_MEMORY_NX)
 			pte_val(new) |= _PAGE_NOEXEC;
 		else if (flags & SET_MEMORY_X)
 			pte_val(new) &= ~_PAGE_NOEXEC;
@@ -144,7 +144,7 @@ static void modify_pmd_page(pmd_t *pmdp, unsigned long addr,
 		new = pmd_wrprotect(new);
 	else if (flags & SET_MEMORY_RW)
 		new = pmd_mkwrite(pmd_mkdirty(new));
-	if ((flags & SET_MEMORY_NX) && MACHINE_HAS_NX)
+	if (flags & SET_MEMORY_NX)
 		pmd_val(new) |= _SEGMENT_ENTRY_NOEXEC;
 	else if (flags & SET_MEMORY_X)
 		pmd_val(new) &= ~_SEGMENT_ENTRY_NOEXEC;
@@ -221,7 +221,7 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr,
 		new = pud_wrprotect(new);
 	else if (flags & SET_MEMORY_RW)
 		new = pud_mkwrite(pud_mkdirty(new));
-	if ((flags & SET_MEMORY_NX) && MACHINE_HAS_NX)
+	if (flags & SET_MEMORY_NX)
 		pud_val(new) |= _REGION_ENTRY_NOEXEC;
 	else if (flags & SET_MEMORY_X)
 		pud_val(new) &= ~_REGION_ENTRY_NOEXEC;
@@ -288,6 +288,10 @@ static int change_page_attr(unsigned long addr, unsigned long end,
 
 int __set_memory(unsigned long addr, int numpages, unsigned long flags)
 {
+	if (!MACHINE_HAS_NX)
+		flags &= ~(SET_MEMORY_NX | SET_MEMORY_X);
+	if (!flags)
+		return 0;
 	addr &= PAGE_MASK;
 	return change_page_attr(addr, addr + numpages * PAGE_SIZE, flags);
 }
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 995f78532cc2..f502cbe657af 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -95,7 +95,6 @@ int crst_table_upgrade(struct mm_struct *mm)
 	mm->context.asce_limit = 1UL << 53;
 	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 			   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
-	mm->task_size = mm->context.asce_limit;
 	spin_unlock_bh(&mm->page_table_lock);
 
 	on_each_cpu(__crst_table_upgrade, mm, 0);
@@ -119,7 +118,6 @@ void crst_table_downgrade(struct mm_struct *mm)
 	mm->context.asce_limit = 1UL << 31;
 	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 			   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
-	mm->task_size = mm->context.asce_limit;
 	crst_table_free(mm, (unsigned long *) pgd);
 
 	if (current->active_mm == mm)
@@ -144,7 +142,7 @@ struct page *page_table_alloc_pgste(struct mm_struct *mm)
 	struct page *page;
 	unsigned long *table;
 
-	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	page = alloc_page(GFP_KERNEL);
 	if (page) {
 		table = (unsigned long *) page_to_phys(page);
 		clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b48dc5f1900b..947b66a5cdba 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -23,6 +23,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/page-states.h>
 
 static inline pte_t ptep_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pte_t *ptep)
@@ -608,12 +609,29 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 {
 	spinlock_t *ptl;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
 	pgste_t pgste;
 	pte_t *ptep;
 	pte_t pte;
 	bool dirty;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return false;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return false;
+	/* We can't run guests backed by huge pages, but userspace can
+	 * still set them up and then try to migrate them without any
+	 * migration support.
+	 */
+	if (pmd_large(*pmd))
+		return true;
+
+	ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (unlikely(!ptep))
 		return false;
 
@@ -770,4 +788,156 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	return 0;
 }
 EXPORT_SYMBOL(get_guest_storage_key);
+
+/**
+ * pgste_perform_essa - perform ESSA actions on the PGSTE.
+ * @mm: the memory context. It must have PGSTEs, no check is performed here!
+ * @hva: the host virtual address of the page whose PGSTE is to be processed
+ * @orc: the specific action to perform, see the ESSA_SET_* macros.
+ * @oldpte: the PTE will be saved there if the pointer is not NULL.
+ * @oldpgste: the old PGSTE will be saved there if the pointer is not NULL.
+ *
+ * Return: 1 if the page is to be added to the CBRL, otherwise 0,
+ *	   or < 0 in case of error. -EINVAL is returned for invalid values
+ *	   of orc, -EFAULT for invalid addresses.
+ */
+int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
+			unsigned long *oldpte, unsigned long *oldpgste)
+{
+	unsigned long pgstev;
+	spinlock_t *ptl;
+	pgste_t pgste;
+	pte_t *ptep;
+	int res = 0;
+
+	WARN_ON_ONCE(orc > ESSA_MAX);
+	if (unlikely(orc > ESSA_MAX))
+		return -EINVAL;
+	ptep = get_locked_pte(mm, hva, &ptl);
+	if (unlikely(!ptep))
+		return -EFAULT;
+	pgste = pgste_get_lock(ptep);
+	pgstev = pgste_val(pgste);
+	if (oldpte)
+		*oldpte = pte_val(*ptep);
+	if (oldpgste)
+		*oldpgste = pgstev;
+
+	switch (orc) {
+	case ESSA_GET_STATE:
+		break;
+	case ESSA_SET_STABLE:
+		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		pgstev |= _PGSTE_GPS_USAGE_STABLE;
+		break;
+	case ESSA_SET_UNUSED:
+		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		pgstev |= _PGSTE_GPS_USAGE_UNUSED;
+		if (pte_val(*ptep) & _PAGE_INVALID)
+			res = 1;
+		break;
+	case ESSA_SET_VOLATILE:
+		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		pgstev |= _PGSTE_GPS_USAGE_VOLATILE;
+		if (pte_val(*ptep) & _PAGE_INVALID)
+			res = 1;
+		break;
+	case ESSA_SET_POT_VOLATILE:
+		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+			pgstev |= _PGSTE_GPS_USAGE_POT_VOLATILE;
+			break;
+		}
+		if (pgstev & _PGSTE_GPS_ZERO) {
+			pgstev |= _PGSTE_GPS_USAGE_VOLATILE;
+			break;
+		}
+		if (!(pgstev & PGSTE_GC_BIT)) {
+			pgstev |= _PGSTE_GPS_USAGE_VOLATILE;
+			res = 1;
+			break;
+		}
+		break;
+	case ESSA_SET_STABLE_RESIDENT:
+		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		pgstev |= _PGSTE_GPS_USAGE_STABLE;
+		/*
+		 * Since the resident state can go away any time after this
+		 * call, we will not make this page resident. We can revisit
+		 * this decision if a guest will ever start using this.
+		 */
+		break;
+	case ESSA_SET_STABLE_IF_RESIDENT:
+		if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+			pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+			pgstev |= _PGSTE_GPS_USAGE_STABLE;
+		}
+		break;
+	default:
+		/* we should never get here! */
+		break;
+	}
+	/* If we are discarding a page, set it to logical zero */
+	if (res)
+		pgstev |= _PGSTE_GPS_ZERO;
+
+	pgste_val(pgste) = pgstev;
+	pgste_set_unlock(ptep, pgste);
+	pte_unmap_unlock(ptep, ptl);
+	return res;
+}
+EXPORT_SYMBOL(pgste_perform_essa);
+
+/**
+ * set_pgste_bits - set specific PGSTE bits.
+ * @mm: the memory context. It must have PGSTEs, no check is performed here!
+ * @hva: the host virtual address of the page whose PGSTE is to be processed
+ * @bits: a bitmask representing the bits that will be touched
+ * @value: the values of the bits to be written. Only the bits in the mask
+ *	   will be written.
+ *
+ * Return: 0 on success, < 0 in case of error.
+ */
+int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
+			unsigned long bits, unsigned long value)
+{
+	spinlock_t *ptl;
+	pgste_t new;
+	pte_t *ptep;
+
+	ptep = get_locked_pte(mm, hva, &ptl);
+	if (unlikely(!ptep))
+		return -EFAULT;
+	new = pgste_get_lock(ptep);
+
+	pgste_val(new) &= ~bits;
+	pgste_val(new) |= value & bits;
+
+	pgste_set_unlock(ptep, new);
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+EXPORT_SYMBOL(set_pgste_bits);
+
+/**
+ * get_pgste - get the current PGSTE for the given address.
+ * @mm: the memory context. It must have PGSTEs, no check is performed here!
+ * @hva: the host virtual address of the page whose PGSTE is to be processed
+ * @pgstep: will be written with the current PGSTE for the given address.
+ *
+ * Return: 0 on success, < 0 in case of error.
+ */
+int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	ptep = get_locked_pte(mm, hva, &ptl);
+	if (unlikely(!ptep))
+		return -EFAULT;
+	*pgstep = pgste_val(pgste_get(ptep));
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+EXPORT_SYMBOL(get_pgste);
 #endif
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 364b9d824be3..8051df109db3 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -60,16 +60,8 @@ static DEFINE_SPINLOCK(zpci_domain_lock);
 static struct airq_iv *zpci_aisb_iv;
 static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
 
-/* Adapter interrupt definitions */
-static void zpci_irq_handler(struct airq_struct *airq);
-
-static struct airq_struct zpci_airq = {
-	.handler = zpci_irq_handler,
-	.isc = PCI_ISC,
-};
-
 #define ZPCI_IOMAP_ENTRIES						\
-	min(((unsigned long) CONFIG_PCI_NR_FUNCTIONS * PCI_BAR_COUNT),	\
+	min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2),	\
 	    ZPCI_IOMAP_MAX_ENTRIES)
 
 static DEFINE_SPINLOCK(zpci_iomap_lock);
@@ -214,8 +206,6 @@ int zpci_fmb_disable_device(struct zpci_dev *zdev)
 	return rc;
 }
 
-#define ZPCI_PCIAS_CFGSPC	15
-
 static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
 {
 	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
@@ -507,6 +497,11 @@ static void zpci_unmap_resources(struct pci_dev *pdev)
 	}
 }
 
+static struct airq_struct zpci_airq = {
+	.handler = zpci_irq_handler,
+	.isc = PCI_ISC,
+};
+
 static int __init zpci_irq_init(void)
 {
 	int rc;
@@ -871,11 +866,6 @@ int zpci_report_error(struct pci_dev *pdev,
 }
 EXPORT_SYMBOL(zpci_report_error);
 
-static inline int barsize(u8 size)
-{
-	return (size) ? (1 << size) >> 10 : 0;
-}
-
 static int zpci_mem_init(void)
 {
 	BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) ||
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 926943a49ea5..e3a8d0f96652 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -4,6 +4,7 @@ header-y +=
 generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += current.h
+generic-y += extable.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
diff --git a/arch/score/include/asm/extable.h b/arch/score/include/asm/extable.h
deleted file mode 100644
index c4423ccf830d..000000000000
--- a/arch/score/include/asm/extable.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_SCORE_EXTABLE_H
-#define _ASM_SCORE_EXTABLE_H
-
-struct exception_table_entry {
-	unsigned long insn;
-	unsigned long fixup;
-};
-
-struct pt_regs;
-extern int fixup_exception(struct pt_regs *regs);
-#endif
diff --git a/arch/score/include/asm/pgtable.h b/arch/score/include/asm/pgtable.h
index 0553e5cd5985..46ff8fd678a7 100644
--- a/arch/score/include/asm/pgtable.h
+++ b/arch/score/include/asm/pgtable.h
@@ -2,6 +2,7 @@
 #define _ASM_SCORE_PGTABLE_H
 
 #include <linux/const.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #include <asm/fixmap.h>
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index db58ab98ec4b..916e5dbf0bfd 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -2,13 +2,8 @@
 #define __SCORE_UACCESS_H
 
 #include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/thread_info.h>
 #include <asm/extable.h>
 
-#define VERIFY_READ		0
-#define VERIFY_WRITE		1
-
 #define get_ds()		(KERNEL_DS)
 #define get_fs()		(current_thread_info()->addr_limit)
 #define segment_eq(a, b)	((a).seg == (b).seg)
@@ -300,61 +295,19 @@ extern void __put_user_unknown(void);
 extern int __copy_tofrom_user(void *to, const void *from, unsigned long len);
 
 static inline unsigned long
-copy_from_user(void *to, const void *from, unsigned long len)
-{
-	unsigned long res = len;
-
-	if (likely(access_ok(VERIFY_READ, from, len)))
-		res = __copy_tofrom_user(to, from, len);
-
-	if (unlikely(res))
-		memset(to + (len - res), 0, res);
-
-	return res;
-}
-
-static inline unsigned long
-copy_to_user(void *to, const void *from, unsigned long len)
-{
-	if (likely(access_ok(VERIFY_WRITE, to, len)))
-		len = __copy_tofrom_user(to, from, len);
-
-	return len;
-}
-
-static inline unsigned long
-__copy_from_user(void *to, const void *from, unsigned long len)
+raw_copy_from_user(void *to, const void __user *from, unsigned long len)
 {
-	unsigned long left = __copy_tofrom_user(to, from, len);
-	if (unlikely(left))
-		memset(to + (len - left), 0, left);
-	return left;
+	return __copy_tofrom_user(to, (__force const void *)from, len);
 }
 
-#define __copy_to_user(to, from, len)		\
-		__copy_tofrom_user((to), (from), (len))
-
 static inline unsigned long
-__copy_to_user_inatomic(void *to, const void *from, unsigned long len)
+raw_copy_to_user(void __user *to, const void *from, unsigned long len)
 {
-	return __copy_to_user(to, from, len);
+	return __copy_tofrom_user((__force void *)to, from, len);
 }
 
-static inline unsigned long
-__copy_from_user_inatomic(void *to, const void *from, unsigned long len)
-{
-	return __copy_tofrom_user(to, from, len);
-}
-
-#define __copy_in_user(to, from, len)	__copy_tofrom_user(to, from, len)
-
-static inline unsigned long
-copy_in_user(void *to, const void *from, unsigned long len)
-{
-	if (access_ok(VERIFY_READ, from, len) &&
-		      access_ok(VERFITY_WRITE, to, len))
-		return __copy_tofrom_user(to, from, len);
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 /*
  * __clear_user: - Zero a block of memory in user space, with less checking.
diff --git a/arch/score/kernel/time.c b/arch/score/kernel/time.c
index 679b8d7b0350..29aafc741f69 100644
--- a/arch/score/kernel/time.c
+++ b/arch/score/kernel/time.c
@@ -81,8 +81,10 @@ void __init time_init(void)
 					score_clockevent.shift);
 	score_clockevent.max_delta_ns = clockevent_delta2ns((u32)~0,
 					&score_clockevent);
+	score_clockevent.max_delta_ticks = (u32)~0;
 	score_clockevent.min_delta_ns = clockevent_delta2ns(50,
 						&score_clockevent) + 1;
+	score_clockevent.min_delta_ticks = 50;
 	score_clockevent.cpumask = cpumask_of(0);
 	clockevents_register_device(&score_clockevent);
 }
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index e359ec675869..12daf45369b4 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -24,6 +24,7 @@
  */
 
 #include <linux/extable.h>
+#include <linux/ptrace.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
diff --git a/arch/score/mm/extable.c b/arch/score/mm/extable.c
index ec871355fc2d..6736a3ad6286 100644
--- a/arch/score/mm/extable.c
+++ b/arch/score/mm/extable.c
@@ -24,6 +24,8 @@
  */
 
 #include <linux/extable.h>
+#include <linux/ptrace.h>
+#include <asm/extable.h>
 
 int fixup_exception(struct pt_regs *regs)
 {
diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c
index 340fd40b381d..9c292c27e0d7 100644
--- a/arch/sh/boards/mach-cayman/setup.c
+++ b/arch/sh/boards/mach-cayman/setup.c
@@ -128,7 +128,6 @@ static int __init smsc_superio_setup(void)
 	SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX);
 	SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX);
 
-#ifdef CONFIG_IDE
 	/*
 	 * Only IDE1 exists on the Cayman
 	 */
@@ -158,7 +157,6 @@ static int __init smsc_superio_setup(void)
 	SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */
 	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */
 	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */
-#endif
 
 	/* Exit the configuration state */
 	outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);
diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h
index dcf278075429..1b77f068be2b 100644
--- a/arch/sh/include/asm/bug.h
+++ b/arch/sh/include/asm/bug.h
@@ -50,7 +50,7 @@ do {							\
 		   "i" (sizeof(struct bug_entry)));	\
 } while (0)
 
-#define __WARN_TAINT(taint)				\
+#define __WARN_FLAGS(flags)				\
 do {							\
 	__asm__ __volatile__ (				\
 		"1:\t.short %O0\n"			\
@@ -59,7 +59,7 @@ do {							\
 		 : "n" (TRAPA_BUG_OPCODE),		\
 		   "i" (__FILE__),			\
 		   "i" (__LINE__),			\
-		   "i" (BUGFLAG_TAINT(taint)),		\
+		   "i" (BUGFLAG_WARNING|(flags)),	\
 		   "i" (sizeof(struct bug_entry)));	\
 } while (0)
 
diff --git a/arch/sh/include/asm/extable.h b/arch/sh/include/asm/extable.h
new file mode 100644
index 000000000000..df2ee2fcb8d3
--- /dev/null
+++ b/arch/sh/include/asm/extable.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_SH_EXTABLE_H
+#define __ASM_SH_EXTABLE_H
+
+#include <asm-generic/extable.h>
+
+#if defined(CONFIG_SUPERH64) && defined(CONFIG_MMU)
+#define ARCH_HAS_SEARCH_EXTABLE
+#endif
+
+#endif
diff --git a/arch/sh/include/asm/pgtable-2level.h b/arch/sh/include/asm/pgtable-2level.h
index 19bd89db17e7..f75cf4387257 100644
--- a/arch/sh/include/asm/pgtable-2level.h
+++ b/arch/sh/include/asm/pgtable-2level.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SH_PGTABLE_2LEVEL_H
 #define __ASM_SH_PGTABLE_2LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /*
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
index 249a985d9648..9b1e776eca31 100644
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SH_PGTABLE_3LEVEL_H
 #define __ASM_SH_PGTABLE_3LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /*
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index c4f0fee812c3..2722b61b2283 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -1,12 +1,8 @@
 #ifndef __ASM_SH_UACCESS_H
 #define __ASM_SH_UACCESS_H
 
-#include <linux/errno.h>
-#include <linux/sched.h>
 #include <asm/segment.h>
-
-#define VERIFY_READ    0
-#define VERIFY_WRITE   1
+#include <asm/extable.h>
 
 #define __addr_ok(addr) \
 	((unsigned long __force)(addr) < current_thread_info()->addr_limit.seg)
@@ -112,19 +108,18 @@ extern __must_check long strnlen_user(const char __user *str, long n);
 __kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n);
 
 static __always_inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	return __copy_user(to, (__force void *)from, n);
 }
 
 static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	return __copy_user((__force void *)to, from, n);
 }
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 /*
  * Clear the area and return remaining number of bytes
@@ -144,55 +139,6 @@ __kernel_size_t __clear_user(void *addr, __kernel_size_t size);
 	__cl_size;							\
 })
 
-static inline unsigned long
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	unsigned long __copy_from = (unsigned long) from;
-	__kernel_size_t __copy_size = (__kernel_size_t) n;
-
-	if (__copy_size && __access_ok(__copy_from, __copy_size))
-		__copy_size = __copy_user(to, from, __copy_size);
-
-	if (unlikely(__copy_size))
-		memset(to + (n - __copy_size), 0, __copy_size);
-
-	return __copy_size;
-}
-
-static inline unsigned long
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	unsigned long __copy_to = (unsigned long) to;
-	__kernel_size_t __copy_size = (__kernel_size_t) n;
-
-	if (__copy_size && __access_ok(__copy_to, __copy_size))
-		return __copy_user(to, from, __copy_size);
-
-	return __copy_size;
-}
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-#if defined(CONFIG_SUPERH64) && defined(CONFIG_MMU)
-#define ARCH_HAS_SEARCH_EXTABLE
-#endif
-
-int fixup_exception(struct pt_regs *regs);
-
 extern void *set_exception_table_vec(unsigned int vec, void *handler);
 
 static inline void *set_exception_table_evt(unsigned int evt, void *handler)
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 68ac5c7cd982..58243b0d21c0 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -31,7 +31,8 @@ config SPARC
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_PCI_IOMAP
 	select HAVE_NMI_WATCHDOG if SPARC64
-	select HAVE_CBPF_JIT
+	select HAVE_CBPF_JIT if SPARC32
+	select HAVE_EBPF_JIT if SPARC64
 	select HAVE_DEBUG_BUGVERBOSE
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CLOCKEVENTS
@@ -42,8 +43,7 @@ config SPARC
 	select OLD_SIGSUSPEND
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
-	select HAVE_ARCH_HARDENED_USERCOPY
-	select PROVE_LOCKING_SMALL if PROVE_LOCKING
+	select LOCKDEP_SMALL if LOCKDEP
 	select ARCH_WANT_RELAX_ORDER
 
 config SPARC32
@@ -82,6 +82,7 @@ config SPARC64
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select HAVE_NMI
+	select HAVE_REGS_AND_STACK_ACCESS_API
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index f294dd42fc7d..5961b2d8398a 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -17,6 +17,7 @@
 
 #define HPAGE_SHIFT		23
 #define REAL_HPAGE_SHIFT	22
+#define HPAGE_2GB_SHIFT		31
 #define HPAGE_256MB_SHIFT	28
 #define HPAGE_64K_SHIFT		16
 #define REAL_HPAGE_SIZE		(_AC(1,UL) << REAL_HPAGE_SHIFT)
@@ -27,7 +28,7 @@
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #define REAL_HPAGE_PER_HPAGE	(_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE		3
+#define HUGE_MAX_HSTATE		4
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 56e49c8f770d..6fbd931f0570 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -12,6 +12,7 @@
  * the SpitFire page tables.
  */
 
+#include <asm-generic/5level-fixup.h>
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <asm/types.h>
@@ -678,26 +679,27 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return pte_pfn(pte);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_dirty(pte);
+	return pte_write(pte);
 }
 
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_dirty(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 365d4cb267b4..dd27159819eb 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -18,12 +18,6 @@
 #include <asm/signal.h>
 #include <asm/page.h>
 
-/*
- * The sparc has no problems with write protection
- */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
 /* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too...
  * That one page is used to protect kernel from intruders, so that
  * we can make our access_ok test faster
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 6448cfc8292f..b58ee9018433 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -18,10 +18,6 @@
 #include <asm/ptrace.h>
 #include <asm/page.h>
 
-/* The sparc has no problems with write protection */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
 /*
  * User lives in his very own context, and cannot reference us. Note
  * that TASK_SIZE is a misnomer, it really gives maximum user virtual
diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h
index ca57f08bd3db..d73428e4333c 100644
--- a/arch/sparc/include/asm/ptrace.h
+++ b/arch/sparc/include/asm/ptrace.h
@@ -83,7 +83,8 @@ unsigned long profile_pc(struct pt_regs *);
 
 #define MAX_REG_OFFSET (offsetof(struct pt_regs, magic))
 
-extern int regs_query_register_offset(const char *name);
+int regs_query_register_offset(const char *name);
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
 
 /**
  * regs_get_register() - get register value from its offset
diff --git a/arch/sparc/include/asm/uaccess.h b/arch/sparc/include/asm/uaccess.h
index bd56c28fff9f..9e068bf9060a 100644
--- a/arch/sparc/include/asm/uaccess.h
+++ b/arch/sparc/include/asm/uaccess.h
@@ -7,7 +7,7 @@
 #endif
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+	(uaccess_kernel() ? ~0UL : TASK_SIZE)
 
 long strncpy_from_user(char *dest, const char __user *src, long count);
 
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index ea55f86d7ccd..12ebee2d97c7 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -7,14 +7,8 @@
 #ifndef _ASM_UACCESS_H
 #define _ASM_UACCESS_H
 
-#ifdef __KERNEL__
 #include <linux/compiler.h>
-#include <linux/sched.h>
 #include <linux/string.h>
-#include <linux/errno.h>
-#endif
-
-#ifndef __ASSEMBLY__
 
 #include <asm/processor.h>
 
@@ -30,9 +24,6 @@
 #define KERNEL_DS   ((mm_segment_t) { 0 })
 #define USER_DS     ((mm_segment_t) { -1 })
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define get_ds()	(KERNEL_DS)
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	((current->thread.current_ds) = (val))
@@ -45,7 +36,7 @@
  * large size and address near to PAGE_OFFSET - a fault will break his intentions.
  */
 #define __user_ok(addr, size) ({ (void)(size); (addr) < STACK_TOP; })
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
 #define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size)))
 #define access_ok(type, addr, size) \
 	({ (void)(type); __access_ok((unsigned long)(addr), size); })
@@ -80,8 +71,6 @@ struct exception_table_entry
 /* Returns 0 if exception not found and fixup otherwise.  */
 unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
 
-void __ret_efault(void);
-
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
  * pointer type..
@@ -246,39 +235,18 @@ int __get_user_bad(void);
 
 unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
 
-static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (n && __access_ok((unsigned long) to, n)) {
-		check_object_size(from, n, true);
-		return __copy_user(to, (__force void __user *) from, n);
-	} else
-		return n;
-}
-
-static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	check_object_size(from, n, true);
 	return __copy_user(to, (__force void __user *) from, n);
 }
 
-static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (n && __access_ok((unsigned long) from, n)) {
-		check_object_size(to, n, false);
-		return __copy_user((__force void __user *) to, from, n);
-	} else {
-		memset(to, 0, n);
-		return n;
-	}
-}
-
-static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	return __copy_user((__force void __user *) to, from, n);
 }
 
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 static inline unsigned long __clear_user(void __user *addr, unsigned long size)
 {
@@ -312,6 +280,4 @@ static inline unsigned long clear_user(void __user *addr, unsigned long n)
 __must_check long strlen_user(const char __user *str);
 __must_check long strnlen_user(const char __user *str, long n);
 
-#endif  /* __ASSEMBLY__ */
-
 #endif /* _ASM_UACCESS_H */
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 5373136c412b..6096d671aa63 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -5,18 +5,12 @@
  * User space memory access functions
  */
 
-#ifdef __KERNEL__
-#include <linux/errno.h>
 #include <linux/compiler.h>
 #include <linux/string.h>
-#include <linux/thread_info.h>
 #include <asm/asi.h>
 #include <asm/spitfire.h>
 #include <asm-generic/uaccess-unaligned.h>
 #include <asm/extable_64.h>
-#endif
-
-#ifndef __ASSEMBLY__
 
 #include <asm/processor.h>
 
@@ -36,9 +30,6 @@
 #define KERNEL_DS   ((mm_segment_t) { ASI_P })
 #define USER_DS     ((mm_segment_t) { ASI_AIUS })	/* har har har */
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)})
 #define get_ds() (KERNEL_DS)
 
@@ -185,39 +176,19 @@ __asm__ __volatile__(							\
 
 int __get_user_bad(void);
 
-unsigned long __must_check ___copy_from_user(void *to,
+unsigned long __must_check raw_copy_from_user(void *to,
 					     const void __user *from,
 					     unsigned long size);
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long size)
-{
-	check_object_size(to, size, false);
 
-	return ___copy_from_user(to, from, size);
-}
-#define __copy_from_user copy_from_user
-
-unsigned long __must_check ___copy_to_user(void __user *to,
+unsigned long __must_check raw_copy_to_user(void __user *to,
 					   const void *from,
 					   unsigned long size);
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long size)
-{
-	check_object_size(from, size, true);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
-	return ___copy_to_user(to, from, size);
-}
-#define __copy_to_user copy_to_user
-
-unsigned long __must_check ___copy_in_user(void __user *to,
+unsigned long __must_check raw_copy_in_user(void __user *to,
 					   const void __user *from,
 					   unsigned long size);
-static inline unsigned long __must_check
-copy_in_user(void __user *to, void __user *from, unsigned long size)
-{
-	return ___copy_in_user(to, from, size);
-}
-#define __copy_in_user copy_in_user
 
 unsigned long __must_check __clear_user(void __user *, unsigned long);
 
@@ -226,14 +197,9 @@ unsigned long __must_check __clear_user(void __user *, unsigned long);
 __must_check long strlen_user(const char __user *str);
 __must_check long strnlen_user(const char __user *str, long n);
 
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
 struct pt_regs;
 unsigned long compute_effective_address(struct pt_regs *,
 					unsigned int insn,
 					unsigned int rd);
 
-#endif  /* __ASSEMBLY__ */
-
 #endif /* _ASM_UACCESS_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index a25dc32f5d6a..3f4ad19d9ec7 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -88,6 +88,12 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	0x0038
 
+#define SO_MEMINFO		0x0039
+
+#define SO_INCOMING_NAPI_ID	0x003a
+
+#define SO_COOKIE		0x003b
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index 36eee8132c22..ae77df75bffa 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -425,8 +425,9 @@
 #define __NR_copy_file_range	357
 #define __NR_preadv2		358
 #define __NR_pwritev2		359
+#define __NR_statx		360
 
-#define NR_syscalls		360
+#define NR_syscalls		361
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
@@ -442,4 +443,9 @@
 #define __IGNORE_getresgid
 #endif
 
+/* Sparc doesn't have protection keys. */
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
+
 #endif /* _UAPI_SPARC_UNISTD_H */
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index 7bb317b87dde..7274e43ff9be 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -809,10 +809,3 @@ lvl14_save:
 	.word	0
 	.word	0
 	.word	t_irq14
-
-        .section        ".fixup",#alloc,#execinstr
-        .globl  __ret_efault
-__ret_efault:
-        ret
-         restore %g0, -EFAULT, %o0
-EXPORT_SYMBOL(__ret_efault)
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 6aa3da152c20..44101196d02b 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -96,6 +96,7 @@ sparc64_boot:
 	andn	%g1, PSTATE_AM, %g1
 	wrpr	%g1, 0x0, %pstate
 	ba,a,pt	%xcc, 1f
+	 nop
 
 	.globl	prom_finddev_name, prom_chosen_path, prom_root_node
 	.globl	prom_getprop_name, prom_mmu_name, prom_peer_name
@@ -613,6 +614,7 @@ niagara_tlb_fixup:
 	 nop
 
 	ba,a,pt	%xcc, 80f
+	 nop
 niagara4_patch:
 	call	niagara4_patch_copyops
 	 nop
@@ -622,6 +624,7 @@ niagara4_patch:
 	 nop
 
 	ba,a,pt	%xcc, 80f
+	 nop
 
 niagara2_patch:
 	call	niagara2_patch_copyops
@@ -632,6 +635,7 @@ niagara2_patch:
 	 nop
 
 	ba,a,pt	%xcc, 80f
+	 nop
 
 niagara_patch:
 	call	niagara_patch_copyops
diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 34b4933900bf..9276d2f0dd86 100644
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@@ -82,6 +82,7 @@ do_stdfmna:
 	call		handle_stdfmna
 	 add		%sp, PTREGS_OFF, %o0
 	ba,a,pt		%xcc, rtrap
+	 nop
 	.size		do_stdfmna,.-do_stdfmna
 
 	.type		breakpoint_trap,#function
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index df9e731a76f5..e1d965e90e16 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -351,7 +351,7 @@ static int genregs64_set(struct task_struct *target,
 	}
 
 	if (!ret) {
-		unsigned long y;
+		unsigned long y = regs->y;
 
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					 &y,
@@ -1162,3 +1162,39 @@ int regs_query_register_offset(const char *name)
 			return roff->offset;
 	return -EINVAL;
 }
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @addr:	address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static inline int regs_within_kernel_stack(struct pt_regs *regs,
+					   unsigned long addr)
+{
+	unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS;
+	return ((addr & ~(THREAD_SIZE - 1))  ==
+		(ksp & ~(THREAD_SIZE - 1)));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS;
+	unsigned long *addr = (unsigned long *)ksp;
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 216948ca4382..709a82ebd294 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -237,6 +237,7 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		bne,pt			%xcc, user_rtt_fill_32bit
 		 wrpr			%g1, %cwp
 		ba,a,pt			%xcc, user_rtt_fill_64bit
+		 nop
 
 user_rtt_fill_fixup_dax:
 		ba,pt	%xcc, user_rtt_fill_fixup_common
diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index 4a73009f66a5..d7e540842809 100644
--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -86,6 +86,7 @@ __spitfire_cee_trap_continue:
 	 rd		%pc, %g7
 
 	ba,a,pt		%xcc, 2f
+	 nop
 
 1:	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index 6179e19bc9b9..c19f352f46c7 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -352,6 +352,7 @@ sun4v_mna:
 	call	sun4v_do_mna
 	 add	%sp, PTREGS_OFF, %o0
 	ba,a,pt	%xcc, rtrap
+	 nop
 
 	/* Privileged Action.  */
 sun4v_privact:
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index d63fc613e7a9..5fd352b759af 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -98,27 +98,7 @@ static struct attribute_group mmu_stat_group = {
 	.name = "mmu_stats",
 };
 
-/* XXX convert to rusty's on_one_cpu */
-static unsigned long run_on_cpu(unsigned long cpu,
-			        unsigned long (*func)(unsigned long),
-				unsigned long arg)
-{
-	cpumask_t old_affinity;
-	unsigned long ret;
-
-	cpumask_copy(&old_affinity, &current->cpus_allowed);
-	/* should return -EINVAL to userspace */
-	if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
-		return 0;
-
-	ret = func(arg);
-
-	set_cpus_allowed_ptr(current, &old_affinity);
-
-	return ret;
-}
-
-static unsigned long read_mmustat_enable(unsigned long junk)
+static long read_mmustat_enable(void *data __maybe_unused)
 {
 	unsigned long ra = 0;
 
@@ -127,11 +107,11 @@ static unsigned long read_mmustat_enable(unsigned long junk)
 	return ra != 0;
 }
 
-static unsigned long write_mmustat_enable(unsigned long val)
+static long write_mmustat_enable(void *data)
 {
-	unsigned long ra, orig_ra;
+	unsigned long ra, orig_ra, *val = data;
 
-	if (val)
+	if (*val)
 		ra = __pa(&per_cpu(mmu_stats, smp_processor_id()));
 	else
 		ra = 0UL;
@@ -142,7 +122,8 @@ static unsigned long write_mmustat_enable(unsigned long val)
 static ssize_t show_mmustat_enable(struct device *s,
 				struct device_attribute *attr, char *buf)
 {
-	unsigned long val = run_on_cpu(s->id, read_mmustat_enable, 0);
+	long val = work_on_cpu(s->id, read_mmustat_enable, NULL);
+
 	return sprintf(buf, "%lx\n", val);
 }
 
@@ -150,13 +131,15 @@ static ssize_t store_mmustat_enable(struct device *s,
 			struct device_attribute *attr, const char *buf,
 			size_t count)
 {
-	unsigned long val, err;
-	int ret = sscanf(buf, "%lu", &val);
+	unsigned long val;
+	long err;
+	int ret;
 
+	ret = sscanf(buf, "%lu", &val);
 	if (ret != 1)
 		return -EINVAL;
 
-	err = run_on_cpu(s->id, write_mmustat_enable, val);
+	err = work_on_cpu(s->id, write_mmustat_enable, &val);
 	if (err)
 		return -EIO;
 
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index eac7f0db5c8c..5253e895b81b 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -89,3 +89,4 @@ sys_call_table:
 /*345*/	.long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
 /*355*/	.long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2
+/*360*/	.long sys_statx
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index b0f17ff2ddba..82339f6be0b2 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -90,6 +90,7 @@ sys_call_table32:
 	.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
 	.word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2
+/*360*/	.word sys_statx
 
 #endif /* CONFIG_COMPAT */
 
@@ -171,3 +172,4 @@ sys_call_table:
 	.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
 	.word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2
+/*360*/	.word sys_statx
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 244062bdaa56..9f575dfc2e41 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -228,7 +228,9 @@ void register_percpu_ce(int cpu)
 	ce->mult           = div_sc(sparc_config.clock_rate, NSEC_PER_SEC,
 	                            ce->shift);
 	ce->max_delta_ns   = clockevent_delta2ns(sparc_config.clock_rate, ce);
+	ce->max_delta_ticks = (unsigned long)sparc_config.clock_rate;
 	ce->min_delta_ns   = clockevent_delta2ns(100, ce);
+	ce->min_delta_ticks = 100;
 
 	clockevents_register_device(ce);
 }
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 12a6d3555cb8..98d05de8da66 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -796,8 +796,10 @@ void __init time_init(void)
 
 	sparc64_clockevent.max_delta_ns =
 		clockevent_delta2ns(0x7fffffffffffffffUL, &sparc64_clockevent);
+	sparc64_clockevent.max_delta_ticks = 0x7fffffffffffffffUL;
 	sparc64_clockevent.min_delta_ns =
 		clockevent_delta2ns(0xF, &sparc64_clockevent);
+	sparc64_clockevent.min_delta_ticks = 0xF;
 
 	printk("clockevent: mult[%x] shift[%d]\n",
 	       sparc64_clockevent.mult, sparc64_clockevent.shift);
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
index 5604a2b051d4..364af3250646 100644
--- a/arch/sparc/kernel/urtt_fill.S
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -92,6 +92,7 @@ user_rtt_fill_fixup_common:
 		call	sun4v_data_access_exception
 		 nop
 		ba,a,pt	%xcc, rtrap
+		 nop
 
 1:		call	spitfire_data_access_exception
 		 nop
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index 855019a8590e..1ee173cc3c39 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -152,6 +152,8 @@ fill_fixup_dax:
 	call	sun4v_data_access_exception
 	 nop
 	ba,a,pt	%xcc, rtrap
+	 nop
 1:	call	spitfire_data_access_exception
 	 nop
 	ba,a,pt	%xcc, rtrap
+	 nop
diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S
index 69a439fa2fc1..8aa16ef113f2 100644
--- a/arch/sparc/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
@@ -23,7 +23,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S
index 9947427ce354..311c8fa5e98e 100644
--- a/arch/sparc/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
@@ -27,7 +27,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/GENpatch.S b/arch/sparc/lib/GENpatch.S
index fab9e89f16bd..95e2f1f9e477 100644
--- a/arch/sparc/lib/GENpatch.S
+++ b/arch/sparc/lib/GENpatch.S
@@ -26,8 +26,8 @@
 	.type	generic_patch_copyops,#function
 generic_patch_copyops:
 	GEN_DO_PATCH(memcpy, GENmemcpy)
-	GEN_DO_PATCH(___copy_from_user, GENcopy_from_user)
-	GEN_DO_PATCH(___copy_to_user, GENcopy_to_user)
+	GEN_DO_PATCH(raw_copy_from_user, GENcopy_from_user)
+	GEN_DO_PATCH(raw_copy_to_user, GENcopy_to_user)
 	retl
 	 nop
 	.size	generic_patch_copyops,.-generic_patch_copyops
diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index b79a6998d87c..0d8a018118c2 100644
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -36,7 +36,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index dcec55f254ab..a7a0ea0d8a0b 100644
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -45,7 +45,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index c629dbd121b6..64dcd6cdb606 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -326,11 +326,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	blu		170f
 	 nop
 	ba,a,pt		%xcc, 180f
+	 nop
 
 4:	/* 32 <= low bits < 48 */
 	blu		150f
 	 nop
 	ba,a,pt		%xcc, 160f
+	 nop
 5:	/* 0 < low bits < 32 */
 	blu,a		6f
 	 cmp		%g2, 8
@@ -338,6 +340,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	blu		130f
 	 nop
 	ba,a,pt		%xcc, 140f
+	 nop
 6:	/* 0 < low bits < 16 */
 	bgeu		120f
 	 nop
@@ -475,6 +478,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	brz,pt		%o2, 85f
 	 sub		%o0, %o1, GLOBAL_SPARE
 	ba,a,pt		%XCC, 90f
+	 nop
 
 	.align		64
 75: /* 16 < len <= 64 */
diff --git a/arch/sparc/lib/NG2patch.S b/arch/sparc/lib/NG2patch.S
index 28c36f06a6d1..56ccc19adde8 100644
--- a/arch/sparc/lib/NG2patch.S
+++ b/arch/sparc/lib/NG2patch.S
@@ -26,8 +26,8 @@
 	.type	niagara2_patch_copyops,#function
 niagara2_patch_copyops:
 	NG_DO_PATCH(memcpy, NG2memcpy)
-	NG_DO_PATCH(___copy_from_user, NG2copy_from_user)
-	NG_DO_PATCH(___copy_to_user, NG2copy_to_user)
+	NG_DO_PATCH(raw_copy_from_user, NG2copy_from_user)
+	NG_DO_PATCH(raw_copy_to_user, NG2copy_to_user)
 	retl
 	 nop
 	.size	niagara2_patch_copyops,.-niagara2_patch_copyops
diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S
index 16a286c1a528..5bb506bd61fa 100644
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -31,7 +31,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S
index 6b0276ffc858..a82d4d45fc1c 100644
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -40,7 +40,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 75bb93b1437f..78ea962edcbe 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -530,4 +530,5 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	bne,pt		%icc, 1b
 	 EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
 	ba,a,pt		%icc, .Lexit
+	 nop
 	.size		FUNC_NAME, .-FUNC_NAME
diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index 41da4bdd95cb..7c0c81f18837 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -102,4 +102,5 @@ NG4bzero:
 	bne,pt		%icc, 1b
 	 add		%o0, 0x30, %o0
 	ba,a,pt		%icc, .Lpostloop
+	 nop
 	.size		NG4bzero,.-NG4bzero
diff --git a/arch/sparc/lib/NG4patch.S b/arch/sparc/lib/NG4patch.S
index a114cbcf2a48..3cc0f8cc95df 100644
--- a/arch/sparc/lib/NG4patch.S
+++ b/arch/sparc/lib/NG4patch.S
@@ -26,8 +26,8 @@
 	.type	niagara4_patch_copyops,#function
 niagara4_patch_copyops:
 	NG_DO_PATCH(memcpy, NG4memcpy)
-	NG_DO_PATCH(___copy_from_user, NG4copy_from_user)
-	NG_DO_PATCH(___copy_to_user, NG4copy_to_user)
+	NG_DO_PATCH(raw_copy_from_user, NG4copy_from_user)
+	NG_DO_PATCH(raw_copy_to_user, NG4copy_to_user)
 	retl
 	 nop
 	.size	niagara4_patch_copyops,.-niagara4_patch_copyops
diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S
index 9cd42fcbc781..2333b6f3e824 100644
--- a/arch/sparc/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
@@ -25,7 +25,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S
index 5c358afd464e..07ba20bc4ea4 100644
--- a/arch/sparc/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
@@ -28,7 +28,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop
 #endif
 
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index d88c4ed50a00..cd654a719b27 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -394,6 +394,7 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	brz,pt		%i2, 85f
 	 sub		%o0, %i1, %i3
 	ba,a,pt		%XCC, 90f
+	 nop
 
 	.align		64
 70: /* 16 < len <= 64 */
diff --git a/arch/sparc/lib/NGpatch.S b/arch/sparc/lib/NGpatch.S
index 3b0674fc3366..62ccda7e7b38 100644
--- a/arch/sparc/lib/NGpatch.S
+++ b/arch/sparc/lib/NGpatch.S
@@ -26,8 +26,8 @@
 	.type	niagara_patch_copyops,#function
 niagara_patch_copyops:
 	NG_DO_PATCH(memcpy, NGmemcpy)
-	NG_DO_PATCH(___copy_from_user, NGcopy_from_user)
-	NG_DO_PATCH(___copy_to_user, NGcopy_to_user)
+	NG_DO_PATCH(raw_copy_from_user, NGcopy_from_user)
+	NG_DO_PATCH(raw_copy_to_user, NGcopy_to_user)
 	retl
 	 nop
 	.size	niagara_patch_copyops,.-niagara_patch_copyops
diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index bb6ff73229e3..9a6e68a9bf4a 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -19,7 +19,7 @@
 	.text;			\
 	.align 4;
 
-#define FUNC_NAME		___copy_from_user
+#define FUNC_NAME		raw_copy_from_user
 #define LOAD(type,addr,dest)	type##a [addr] %asi, dest
 #define LOAD_BLK(addr,dest)	ldda [addr] ASI_BLK_AIUS, dest
 #define EX_RETVAL(x)		0
@@ -31,7 +31,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop;						\
 
 #include "U1memcpy.S"
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index ed92ce739558..d7b28491eddf 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -19,7 +19,7 @@
 	.text;			\
 	.align 4;
 
-#define FUNC_NAME		___copy_to_user
+#define FUNC_NAME		raw_copy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] ASI_AIUS
 #define STORE_BLK(src,addr)	stda src, [addr] ASI_BLK_AIUS
 #define EX_RETVAL(x)		0
@@ -31,7 +31,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop;						\
 
 #include "U1memcpy.S"
diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index c4ee858e352a..f48fb87fe9f2 100644
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -31,7 +31,7 @@
 #define PREAMBLE					\
 	rd		%asi, %g1;			\
 	cmp		%g1, ASI_AIUS;			\
-	bne,pn		%icc, ___copy_in_user;		\
+	bne,pn		%icc, raw_copy_in_user;		\
 	 nop;						\
 
 #include "U3memcpy.S"
diff --git a/arch/sparc/lib/U3patch.S b/arch/sparc/lib/U3patch.S
index ecc302619a6e..91cd6539b6e1 100644
--- a/arch/sparc/lib/U3patch.S
+++ b/arch/sparc/lib/U3patch.S
@@ -26,8 +26,8 @@
 	.type	cheetah_patch_copyops,#function
 cheetah_patch_copyops:
 	ULTRA3_DO_PATCH(memcpy, U3memcpy)
-	ULTRA3_DO_PATCH(___copy_from_user, U3copy_from_user)
-	ULTRA3_DO_PATCH(___copy_to_user, U3copy_to_user)
+	ULTRA3_DO_PATCH(raw_copy_from_user, U3copy_from_user)
+	ULTRA3_DO_PATCH(raw_copy_to_user, U3copy_to_user)
 	retl
 	 nop
 	.size	cheetah_patch_copyops,.-cheetah_patch_copyops
diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S
index 0252b218de45..1b73bb80aeb0 100644
--- a/arch/sparc/lib/copy_in_user.S
+++ b/arch/sparc/lib/copy_in_user.S
@@ -44,7 +44,7 @@ __retl_o2_plus_1:
 	 * to copy register windows around during thread cloning.
 	 */
 
-ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
+ENTRY(raw_copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 	cmp		%o2, 0
 	be,pn		%XCC, 85f
 	 or		%o0, %o1, %o3
@@ -105,5 +105,5 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 	 add		%o0, 1, %o0
 	retl
 	 clr		%o0
-ENDPROC(___copy_in_user)
-EXPORT_SYMBOL(___copy_in_user)
+ENDPROC(raw_copy_in_user)
+EXPORT_SYMBOL(raw_copy_in_user)
diff --git a/arch/sparc/lib/copy_user.S b/arch/sparc/lib/copy_user.S
index cea644dc67a6..bc243ee807cc 100644
--- a/arch/sparc/lib/copy_user.S
+++ b/arch/sparc/lib/copy_user.S
@@ -364,21 +364,7 @@ short_aligned_end:
 97:
 	mov	%o2, %g3
 fixupretl:
-	sethi   %hi(PAGE_OFFSET), %g1
-	cmp	%o0, %g1
-	blu	1f
-	 cmp	%o1, %g1
-	bgeu	1f
-	 ld	[%g6 + TI_PREEMPT], %g1
-	cmp	%g1, 0
-	bne	1f
-	 nop
-	save	%sp, -64, %sp
-	mov	%i0, %o0
-	call	__bzero
-	 mov	%g3, %o1
-	restore
-1:	retl
+	retl
 	 mov	%g3, %o0
 
 /* exception routine sets %g2 to (broken_insn - first_insn)>>2 */
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 323bc6b6e3ad..7c29d38e6b99 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -143,6 +143,10 @@ static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
 
 	switch (shift) {
+	case HPAGE_2GB_SHIFT:
+		hugepage_size = _PAGE_SZ2GB_4V;
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
 	case HPAGE_256MB_SHIFT:
 		hugepage_size = _PAGE_SZ256MB_4V;
 		pte_val(entry) |= _PAGE_PMD_HUGE;
@@ -183,6 +187,9 @@ static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
 	unsigned int shift;
 
 	switch (tte_szbits) {
+	case _PAGE_SZ2GB_4V:
+		shift = HPAGE_2GB_SHIFT;
+		break;
 	case _PAGE_SZ256MB_4V:
 		shift = HPAGE_256MB_SHIFT;
 		break;
@@ -261,7 +268,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		if (!pmd)
 			return NULL;
 
-		if (sz == PMD_SHIFT)
+		if (sz >= PMD_SIZE)
 			pte = (pte_t *)pmd;
 		else
 			pte = pte_alloc_map(mm, pmd, addr);
@@ -454,6 +461,22 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	pgd_t *pgd;
 	unsigned long next;
 
+	addr &= PMD_MASK;
+	if (addr < floor) {
+		addr += PMD_SIZE;
+		if (!addr)
+			return;
+	}
+	if (ceiling) {
+		ceiling &= PMD_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		end -= PMD_SIZE;
+	if (addr > end - 1)
+		return;
+
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index ccd455328989..0cda653ae007 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -337,6 +337,10 @@ static int __init setup_hugepagesz(char *string)
 	hugepage_shift = ilog2(hugepage_size);
 
 	switch (hugepage_shift) {
+	case HPAGE_2GB_SHIFT:
+		hv_pgsz_mask = HV_PGSZ_MASK_2GB;
+		hv_pgsz_idx = HV_PGSZ_IDX_2GB;
+		break;
 	case HPAGE_256MB_SHIFT:
 		hv_pgsz_mask = HV_PGSZ_MASK_256MB;
 		hv_pgsz_idx = HV_PGSZ_IDX_256MB;
@@ -1563,7 +1567,7 @@ bool kern_addr_valid(unsigned long addr)
 	if ((long)addr < 0L) {
 		unsigned long pa = __pa(addr);
 
-		if ((addr >> max_phys_bits) != 0UL)
+		if ((pa >> max_phys_bits) != 0UL)
 			return false;
 
 		return pfn_valid(pa >> PAGE_SHIFT);
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index def82f6d626f..8e76ebba2986 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -54,6 +54,7 @@
 enum mbus_module srmmu_modtype;
 static unsigned int hwbug_bitmask;
 int vac_cache_size;
+EXPORT_SYMBOL(vac_cache_size);
 int vac_line_size;
 
 extern struct resource sparc_iomap;
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index afda3bbf7854..ee8066c3d96c 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -154,7 +154,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 		if (pte_val(*pte) & _PAGE_VALID) {
 			bool exec = pte_exec(*pte);
 
-			tlb_batch_add_one(mm, vaddr, exec, false);
+			tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT);
 		}
 		pte++;
 		vaddr += PAGE_SIZE;
@@ -209,9 +209,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			pte_t orig_pte = __pte(pmd_val(orig));
 			bool exec = pte_exec(orig_pte);
 
-			tlb_batch_add_one(mm, addr, exec, true);
+			tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
 			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
-					true);
+					  REAL_HPAGE_SHIFT);
 		} else {
 			tlb_batch_pmd_scan(mm, addr, orig);
 		}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 0a04811f06b7..bedf08b22a47 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -122,7 +122,7 @@ void flush_tsb_user(struct tlb_batch *tb)
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	if (tb->hugepage_shift < HPAGE_SHIFT) {
+	if (tb->hugepage_shift < REAL_HPAGE_SHIFT) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
@@ -155,7 +155,7 @@ void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr,
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	if (hugepage_shift < HPAGE_SHIFT) {
+	if (hugepage_shift < REAL_HPAGE_SHIFT) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
diff --git a/arch/sparc/net/Makefile b/arch/sparc/net/Makefile
index 1306a58ac541..76fa8e95b721 100644
--- a/arch/sparc/net/Makefile
+++ b/arch/sparc/net/Makefile
@@ -1,4 +1,4 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o
diff --git a/arch/sparc/net/bpf_jit.h b/arch/sparc/net/bpf_jit_32.h
index 33d6b375ff12..d5c069bff5f9 100644
--- a/arch/sparc/net/bpf_jit.h
+++ b/arch/sparc/net/bpf_jit_32.h
@@ -39,7 +39,7 @@
 #define r_TMP2		G2
 #define r_OFF		G3
 
-/* assembly code in arch/sparc/net/bpf_jit_asm.S */
+/* assembly code in arch/sparc/net/bpf_jit_asm_32.S */
 extern u32 bpf_jit_load_word[];
 extern u32 bpf_jit_load_half[];
 extern u32 bpf_jit_load_byte[];
diff --git a/arch/sparc/net/bpf_jit_64.h b/arch/sparc/net/bpf_jit_64.h
new file mode 100644
index 000000000000..74abd45796ea
--- /dev/null
+++ b/arch/sparc/net/bpf_jit_64.h
@@ -0,0 +1,66 @@
+#ifndef _BPF_JIT_H
+#define _BPF_JIT_H
+
+#ifndef __ASSEMBLER__
+#define G0		0x00
+#define G1		0x01
+#define G2		0x02
+#define G3		0x03
+#define G6		0x06
+#define G7		0x07
+#define O0		0x08
+#define O1		0x09
+#define O2		0x0a
+#define O3		0x0b
+#define O4		0x0c
+#define O5		0x0d
+#define SP		0x0e
+#define O7		0x0f
+#define L0		0x10
+#define L1		0x11
+#define L2		0x12
+#define L3		0x13
+#define L4		0x14
+#define L5		0x15
+#define L6		0x16
+#define L7		0x17
+#define I0		0x18
+#define I1		0x19
+#define I2		0x1a
+#define I3		0x1b
+#define I4		0x1c
+#define I5		0x1d
+#define FP		0x1e
+#define I7		0x1f
+
+#define r_SKB		L0
+#define r_HEADLEN	L4
+#define r_SKB_DATA	L5
+#define r_TMP		G1
+#define r_TMP2		G3
+
+/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */
+extern u32 bpf_jit_load_word[];
+extern u32 bpf_jit_load_half[];
+extern u32 bpf_jit_load_byte[];
+extern u32 bpf_jit_load_byte_msh[];
+extern u32 bpf_jit_load_word_positive_offset[];
+extern u32 bpf_jit_load_half_positive_offset[];
+extern u32 bpf_jit_load_byte_positive_offset[];
+extern u32 bpf_jit_load_byte_msh_positive_offset[];
+extern u32 bpf_jit_load_word_negative_offset[];
+extern u32 bpf_jit_load_half_negative_offset[];
+extern u32 bpf_jit_load_byte_negative_offset[];
+extern u32 bpf_jit_load_byte_msh_negative_offset[];
+
+#else
+#define r_RESULT	%o0
+#define r_SKB		%o0
+#define r_OFF		%o1
+#define r_HEADLEN	%l4
+#define r_SKB_DATA	%l5
+#define r_TMP		%g1
+#define r_TMP2		%g3
+#endif
+
+#endif /* _BPF_JIT_H */
diff --git a/arch/sparc/net/bpf_jit_asm.S b/arch/sparc/net/bpf_jit_asm_32.S
index 8c83f4b8eb15..dcc402f5738a 100644
--- a/arch/sparc/net/bpf_jit_asm.S
+++ b/arch/sparc/net/bpf_jit_asm_32.S
@@ -1,18 +1,11 @@
 #include <asm/ptrace.h>
 
-#include "bpf_jit.h"
+#include "bpf_jit_32.h"
 
-#ifdef CONFIG_SPARC64
-#define SAVE_SZ		176
-#define SCRATCH_OFF	STACK_BIAS + 128
-#define BE_PTR(label)	be,pn %xcc, label
-#define SIGN_EXTEND(reg)	sra reg, 0, reg
-#else
 #define SAVE_SZ		96
 #define SCRATCH_OFF	72
 #define BE_PTR(label)	be label
 #define SIGN_EXTEND(reg)
-#endif
 
 #define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
 
diff --git a/arch/sparc/net/bpf_jit_asm_64.S b/arch/sparc/net/bpf_jit_asm_64.S
new file mode 100644
index 000000000000..3b3f14655f81
--- /dev/null
+++ b/arch/sparc/net/bpf_jit_asm_64.S
@@ -0,0 +1,161 @@
+#include <asm/ptrace.h>
+
+#include "bpf_jit_64.h"
+
+#define SAVE_SZ		176
+#define SCRATCH_OFF	STACK_BIAS + 128
+#define BE_PTR(label)	be,pn %xcc, label
+#define SIGN_EXTEND(reg)	sra reg, 0, reg
+
+#define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
+
+	.text
+	.globl	bpf_jit_load_word
+bpf_jit_load_word:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_word_neg
+	 nop
+	.globl	bpf_jit_load_word_positive_offset
+bpf_jit_load_word_positive_offset:
+	sub	r_HEADLEN, r_OFF, r_TMP
+	cmp	r_TMP, 3
+	ble	bpf_slow_path_word
+	 add	r_SKB_DATA, r_OFF, r_TMP
+	andcc	r_TMP, 3, %g0
+	bne	load_word_unaligned
+	 nop
+	retl
+	 ld	[r_TMP], r_RESULT
+load_word_unaligned:
+	ldub	[r_TMP + 0x0], r_OFF
+	ldub	[r_TMP + 0x1], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	or	r_OFF, r_TMP2, r_OFF
+	ldub	[r_TMP + 0x2], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	or	r_OFF, r_TMP2, r_OFF
+	ldub	[r_TMP + 0x3], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	retl
+	 or	r_OFF, r_TMP2, r_RESULT
+
+	.globl	bpf_jit_load_half
+bpf_jit_load_half:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_half_neg
+	 nop
+	.globl	bpf_jit_load_half_positive_offset
+bpf_jit_load_half_positive_offset:
+	sub	r_HEADLEN, r_OFF, r_TMP
+	cmp	r_TMP, 1
+	ble	bpf_slow_path_half
+	 add	r_SKB_DATA, r_OFF, r_TMP
+	andcc	r_TMP, 1, %g0
+	bne	load_half_unaligned
+	 nop
+	retl
+	 lduh	[r_TMP], r_RESULT
+load_half_unaligned:
+	ldub	[r_TMP + 0x0], r_OFF
+	ldub	[r_TMP + 0x1], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	retl
+	 or	r_OFF, r_TMP2, r_RESULT
+
+	.globl	bpf_jit_load_byte
+bpf_jit_load_byte:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_byte_neg
+	 nop
+	.globl	bpf_jit_load_byte_positive_offset
+bpf_jit_load_byte_positive_offset:
+	cmp	r_OFF, r_HEADLEN
+	bge	bpf_slow_path_byte
+	 nop
+	retl
+	 ldub	[r_SKB_DATA + r_OFF], r_RESULT
+
+#define bpf_slow_path_common(LEN)	\
+	save	%sp, -SAVE_SZ, %sp;	\
+	mov	%i0, %o0;		\
+	mov	%i1, %o1;		\
+	add	%fp, SCRATCH_OFF, %o2;	\
+	call	skb_copy_bits;		\
+	 mov	(LEN), %o3;		\
+	cmp	%o0, 0;			\
+	restore;
+
+bpf_slow_path_word:
+	bpf_slow_path_common(4)
+	bl	bpf_error
+	 ld	[%sp + SCRATCH_OFF], r_RESULT
+	retl
+	 nop
+bpf_slow_path_half:
+	bpf_slow_path_common(2)
+	bl	bpf_error
+	 lduh	[%sp + SCRATCH_OFF], r_RESULT
+	retl
+	 nop
+bpf_slow_path_byte:
+	bpf_slow_path_common(1)
+	bl	bpf_error
+	 ldub	[%sp + SCRATCH_OFF], r_RESULT
+	retl
+	 nop
+
+#define bpf_negative_common(LEN)			\
+	save	%sp, -SAVE_SZ, %sp;			\
+	mov	%i0, %o0;				\
+	mov	%i1, %o1;				\
+	SIGN_EXTEND(%o1);				\
+	call	bpf_internal_load_pointer_neg_helper;	\
+	 mov	(LEN), %o2;				\
+	mov	%o0, r_TMP;				\
+	cmp	%o0, 0;					\
+	BE_PTR(bpf_error);				\
+	 restore;
+
+bpf_slow_path_word_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_word_negative_offset
+bpf_jit_load_word_negative_offset:
+	bpf_negative_common(4)
+	andcc	r_TMP, 3, %g0
+	bne	load_word_unaligned
+	 nop
+	retl
+	 ld	[r_TMP], r_RESULT
+
+bpf_slow_path_half_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_half_negative_offset
+bpf_jit_load_half_negative_offset:
+	bpf_negative_common(2)
+	andcc	r_TMP, 1, %g0
+	bne	load_half_unaligned
+	 nop
+	retl
+	 lduh	[r_TMP], r_RESULT
+
+bpf_slow_path_byte_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_byte_negative_offset
+bpf_jit_load_byte_negative_offset:
+	bpf_negative_common(1)
+	retl
+	 ldub	[r_TMP], r_RESULT
+
+bpf_error:
+	/* Make the JIT program itself return zero. */
+	ret
+	restore	%g0, %g0, %o0
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp_32.c
index a6d9204a6a0b..d193748548e2 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -8,7 +8,7 @@
 #include <asm/cacheflush.h>
 #include <asm/ptrace.h>
 
-#include "bpf_jit.h"
+#include "bpf_jit_32.h"
 
 int bpf_jit_enable __read_mostly;
 
@@ -17,24 +17,6 @@ static inline bool is_simm13(unsigned int value)
 	return value + 0x1000 < 0x2000;
 }
 
-static void bpf_flush_icache(void *start_, void *end_)
-{
-#ifdef CONFIG_SPARC64
-	/* Cheetah's I-cache is fully coherent.  */
-	if (tlb_type == spitfire) {
-		unsigned long start = (unsigned long) start_;
-		unsigned long end = (unsigned long) end_;
-
-		start &= ~7UL;
-		end = (end + 7UL) & ~7UL;
-		while (start < end) {
-			flushi(start);
-			start += 32;
-		}
-	}
-#endif
-}
-
 #define SEEN_DATAREF 1 /* might call external helpers */
 #define SEEN_XREG    2 /* ebx is used */
 #define SEEN_MEM     4 /* use mem[] for temporary storage */
@@ -82,11 +64,7 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define BE		(F2(0, 2) | CONDE)
 #define BNE		(F2(0, 2) | CONDNE)
 
-#ifdef CONFIG_SPARC64
-#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
-#else
 #define BE_PTR		BE
-#endif
 
 #define SETHI(K, REG)	\
 	(F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff))
@@ -116,13 +94,8 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define LD64		F3(3, 0x0b)
 #define ST32		F3(3, 0x04)
 
-#ifdef CONFIG_SPARC64
-#define LDPTR		LD64
-#define BASE_STACKFRAME	176
-#else
 #define LDPTR		LD32
 #define BASE_STACKFRAME	96
-#endif
 
 #define LD32I		(LD32 | IMMED)
 #define LD8I		(LD8 | IMMED)
@@ -234,11 +207,7 @@ do {	BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u8));	\
 	__emit_load8(BASE, STRUCT, FIELD, DEST);			\
 } while (0)
 
-#ifdef CONFIG_SPARC64
-#define BIAS (STACK_BIAS - 4)
-#else
 #define BIAS (-4)
-#endif
 
 #define emit_ldmem(OFF, DEST)						\
 do {	*prog++ = LD32I | RS1(SP) | S13(BIAS - (OFF)) | RD(DEST);	\
@@ -249,13 +218,8 @@ do {	*prog++ = ST32I | RS1(SP) | S13(BIAS - (OFF)) | RD(SRC);	\
 } while (0)
 
 #ifdef CONFIG_SMP
-#ifdef CONFIG_SPARC64
-#define emit_load_cpu(REG)						\
-	emit_load16(G6, struct thread_info, cpu, REG)
-#else
 #define emit_load_cpu(REG)						\
 	emit_load32(G6, struct thread_info, cpu, REG)
-#endif
 #else
 #define emit_load_cpu(REG)	emit_clear(REG)
 #endif
@@ -486,7 +450,6 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				if (K == 1)
 					break;
 				emit_write_y(G0);
-#ifdef CONFIG_SPARC32
 				/* The Sparc v8 architecture requires
 				 * three instructions between a %y
 				 * register write and the first use.
@@ -494,31 +457,21 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				emit_nop();
 				emit_nop();
 				emit_nop();
-#endif
 				emit_alu_K(DIV, K);
 				break;
 			case BPF_ALU | BPF_DIV | BPF_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
 				if (pc_ret0 > 0) {
 					t_offset = addrs[pc_ret0 - 1];
-#ifdef CONFIG_SPARC32
 					emit_branch(BE, t_offset + 20);
-#else
-					emit_branch(BE, t_offset + 8);
-#endif
 					emit_nop(); /* delay slot */
 				} else {
 					emit_branch_off(BNE, 16);
 					emit_nop();
-#ifdef CONFIG_SPARC32
 					emit_jump(cleanup_addr + 20);
-#else
-					emit_jump(cleanup_addr + 8);
-#endif
 					emit_clear(r_A);
 				}
 				emit_write_y(G0);
-#ifdef CONFIG_SPARC32
 				/* The Sparc v8 architecture requires
 				 * three instructions between a %y
 				 * register write and the first use.
@@ -526,7 +479,6 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				emit_nop();
 				emit_nop();
 				emit_nop();
-#endif
 				emit_alu_X(DIV);
 				break;
 			case BPF_ALU | BPF_NEG:
@@ -797,7 +749,6 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 		bpf_jit_dump(flen, proglen, pass + 1, image);
 
 	if (image) {
-		bpf_flush_icache(image, image + proglen);
 		fp->bpf_func = (void *)image;
 		fp->jited = 1;
 	}
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
new file mode 100644
index 000000000000..21de77419f48
--- /dev/null
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -0,0 +1,1566 @@
+#include <linux/moduleloader.h>
+#include <linux/workqueue.h>
+#include <linux/netdevice.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/cache.h>
+#include <linux/if_vlan.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ptrace.h>
+
+#include "bpf_jit_64.h"
+
+int bpf_jit_enable __read_mostly;
+
+static inline bool is_simm13(unsigned int value)
+{
+	return value + 0x1000 < 0x2000;
+}
+
+static inline bool is_simm10(unsigned int value)
+{
+	return value + 0x200 < 0x400;
+}
+
+static inline bool is_simm5(unsigned int value)
+{
+	return value + 0x10 < 0x20;
+}
+
+static inline bool is_sethi(unsigned int value)
+{
+	return (value & ~0x3fffff) == 0;
+}
+
+static void bpf_flush_icache(void *start_, void *end_)
+{
+	/* Cheetah's I-cache is fully coherent.  */
+	if (tlb_type == spitfire) {
+		unsigned long start = (unsigned long) start_;
+		unsigned long end = (unsigned long) end_;
+
+		start &= ~7UL;
+		end = (end + 7UL) & ~7UL;
+		while (start < end) {
+			flushi(start);
+			start += 32;
+		}
+	}
+}
+
+#define SEEN_DATAREF 1 /* might call external helpers */
+#define SEEN_XREG    2 /* ebx is used */
+#define SEEN_MEM     4 /* use mem[] for temporary storage */
+
+#define S13(X)		((X) & 0x1fff)
+#define S5(X)		((X) & 0x1f)
+#define IMMED		0x00002000
+#define RD(X)		((X) << 25)
+#define RS1(X)		((X) << 14)
+#define RS2(X)		((X))
+#define OP(X)		((X) << 30)
+#define OP2(X)		((X) << 22)
+#define OP3(X)		((X) << 19)
+#define COND(X)		(((X) & 0xf) << 25)
+#define CBCOND(X)	(((X) & 0x1f) << 25)
+#define F1(X)		OP(X)
+#define F2(X, Y)	(OP(X) | OP2(Y))
+#define F3(X, Y)	(OP(X) | OP3(Y))
+#define ASI(X)		(((X) & 0xff) << 5)
+
+#define CONDN		COND(0x0)
+#define CONDE		COND(0x1)
+#define CONDLE		COND(0x2)
+#define CONDL		COND(0x3)
+#define CONDLEU		COND(0x4)
+#define CONDCS		COND(0x5)
+#define CONDNEG		COND(0x6)
+#define CONDVC		COND(0x7)
+#define CONDA		COND(0x8)
+#define CONDNE		COND(0x9)
+#define CONDG		COND(0xa)
+#define CONDGE		COND(0xb)
+#define CONDGU		COND(0xc)
+#define CONDCC		COND(0xd)
+#define CONDPOS		COND(0xe)
+#define CONDVS		COND(0xf)
+
+#define CONDGEU		CONDCC
+#define CONDLU		CONDCS
+
+#define WDISP22(X)	(((X) >> 2) & 0x3fffff)
+#define WDISP19(X)	(((X) >> 2) & 0x7ffff)
+
+/* The 10-bit branch displacement for CBCOND is split into two fields */
+static u32 WDISP10(u32 off)
+{
+	u32 ret = ((off >> 2) & 0xff) << 5;
+
+	ret |= ((off >> (2 + 8)) & 0x03) << 19;
+
+	return ret;
+}
+
+#define CBCONDE		CBCOND(0x09)
+#define CBCONDLE	CBCOND(0x0a)
+#define CBCONDL		CBCOND(0x0b)
+#define CBCONDLEU	CBCOND(0x0c)
+#define CBCONDCS	CBCOND(0x0d)
+#define CBCONDN		CBCOND(0x0e)
+#define CBCONDVS	CBCOND(0x0f)
+#define CBCONDNE	CBCOND(0x19)
+#define CBCONDG		CBCOND(0x1a)
+#define CBCONDGE	CBCOND(0x1b)
+#define CBCONDGU	CBCOND(0x1c)
+#define CBCONDCC	CBCOND(0x1d)
+#define CBCONDPOS	CBCOND(0x1e)
+#define CBCONDVC	CBCOND(0x1f)
+
+#define CBCONDGEU	CBCONDCC
+#define CBCONDLU	CBCONDCS
+
+#define ANNUL		(1 << 29)
+#define XCC		(1 << 21)
+
+#define BRANCH		(F2(0, 1) | XCC)
+#define CBCOND_OP	(F2(0, 3) | XCC)
+
+#define BA		(BRANCH | CONDA)
+#define BG		(BRANCH | CONDG)
+#define BGU		(BRANCH | CONDGU)
+#define BLEU		(BRANCH | CONDLEU)
+#define BGE		(BRANCH | CONDGE)
+#define BGEU		(BRANCH | CONDGEU)
+#define BLU		(BRANCH | CONDLU)
+#define BE		(BRANCH | CONDE)
+#define BNE		(BRANCH | CONDNE)
+
+#define SETHI(K, REG)	\
+	(F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff))
+#define OR_LO(K, REG)	\
+	(F3(2, 0x02) | IMMED | RS1(REG) | ((K) & 0x3ff) | RD(REG))
+
+#define ADD		F3(2, 0x00)
+#define AND		F3(2, 0x01)
+#define ANDCC		F3(2, 0x11)
+#define OR		F3(2, 0x02)
+#define XOR		F3(2, 0x03)
+#define SUB		F3(2, 0x04)
+#define SUBCC		F3(2, 0x14)
+#define MUL		F3(2, 0x0a)
+#define MULX		F3(2, 0x09)
+#define UDIVX		F3(2, 0x0d)
+#define DIV		F3(2, 0x0e)
+#define SLL		F3(2, 0x25)
+#define SLLX		(F3(2, 0x25)|(1<<12))
+#define SRA		F3(2, 0x27)
+#define SRAX		(F3(2, 0x27)|(1<<12))
+#define SRL		F3(2, 0x26)
+#define SRLX		(F3(2, 0x26)|(1<<12))
+#define JMPL		F3(2, 0x38)
+#define SAVE		F3(2, 0x3c)
+#define RESTORE		F3(2, 0x3d)
+#define CALL		F1(1)
+#define BR		F2(0, 0x01)
+#define RD_Y		F3(2, 0x28)
+#define WR_Y		F3(2, 0x30)
+
+#define LD32		F3(3, 0x00)
+#define LD8		F3(3, 0x01)
+#define LD16		F3(3, 0x02)
+#define LD64		F3(3, 0x0b)
+#define LD64A		F3(3, 0x1b)
+#define ST8		F3(3, 0x05)
+#define ST16		F3(3, 0x06)
+#define ST32		F3(3, 0x04)
+#define ST64		F3(3, 0x0e)
+
+#define CAS		F3(3, 0x3c)
+#define CASX		F3(3, 0x3e)
+
+#define LDPTR		LD64
+#define BASE_STACKFRAME	176
+
+#define LD32I		(LD32 | IMMED)
+#define LD8I		(LD8 | IMMED)
+#define LD16I		(LD16 | IMMED)
+#define LD64I		(LD64 | IMMED)
+#define LDPTRI		(LDPTR | IMMED)
+#define ST32I		(ST32 | IMMED)
+
+struct jit_ctx {
+	struct bpf_prog		*prog;
+	unsigned int		*offset;
+	int			idx;
+	int			epilogue_offset;
+	bool 			tmp_1_used;
+	bool 			tmp_2_used;
+	bool 			tmp_3_used;
+	bool			saw_ld_abs_ind;
+	bool			saw_frame_pointer;
+	bool			saw_call;
+	bool			saw_tail_call;
+	u32			*image;
+};
+
+#define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
+#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 2)
+#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 3)
+#define TMP_REG_3	(MAX_BPF_JIT_REG + 4)
+
+/* Map BPF registers to SPARC registers */
+static const int bpf2sparc[] = {
+	/* return value from in-kernel function, and exit value from eBPF */
+	[BPF_REG_0] = O5,
+
+	/* arguments from eBPF program to in-kernel function */
+	[BPF_REG_1] = O0,
+	[BPF_REG_2] = O1,
+	[BPF_REG_3] = O2,
+	[BPF_REG_4] = O3,
+	[BPF_REG_5] = O4,
+
+	/* callee saved registers that in-kernel function will preserve */
+	[BPF_REG_6] = L0,
+	[BPF_REG_7] = L1,
+	[BPF_REG_8] = L2,
+	[BPF_REG_9] = L3,
+
+	/* read-only frame pointer to access stack */
+	[BPF_REG_FP] = L6,
+
+	[BPF_REG_AX] = G7,
+
+	/* temporary register for internal BPF JIT */
+	[TMP_REG_1] = G1,
+	[TMP_REG_2] = G2,
+	[TMP_REG_3] = G3,
+
+	[SKB_HLEN_REG] = L4,
+	[SKB_DATA_REG] = L5,
+};
+
+static void emit(const u32 insn, struct jit_ctx *ctx)
+{
+	if (ctx->image != NULL)
+		ctx->image[ctx->idx] = insn;
+
+	ctx->idx++;
+}
+
+static void emit_call(u32 *func, struct jit_ctx *ctx)
+{
+	if (ctx->image != NULL) {
+		void *here = &ctx->image[ctx->idx];
+		unsigned int off;
+
+		off = (void *)func - here;
+		ctx->image[ctx->idx] = CALL | ((off >> 2) & 0x3fffffff);
+	}
+	ctx->idx++;
+}
+
+static void emit_nop(struct jit_ctx *ctx)
+{
+	emit(SETHI(0, G0), ctx);
+}
+
+static void emit_reg_move(u32 from, u32 to, struct jit_ctx *ctx)
+{
+	emit(OR | RS1(G0) | RS2(from) | RD(to), ctx);
+}
+
+/* Emit 32-bit constant, zero extended. */
+static void emit_set_const(s32 K, u32 reg, struct jit_ctx *ctx)
+{
+	emit(SETHI(K, reg), ctx);
+	emit(OR_LO(K, reg), ctx);
+}
+
+/* Emit 32-bit constant, sign extended. */
+static void emit_set_const_sext(s32 K, u32 reg, struct jit_ctx *ctx)
+{
+	if (K >= 0) {
+		emit(SETHI(K, reg), ctx);
+		emit(OR_LO(K, reg), ctx);
+	} else {
+		u32 hbits = ~(u32) K;
+		u32 lbits = -0x400 | (u32) K;
+
+		emit(SETHI(hbits, reg), ctx);
+		emit(XOR | IMMED | RS1(reg) | S13(lbits) | RD(reg), ctx);
+	}
+}
+
+static void emit_alu(u32 opcode, u32 src, u32 dst, struct jit_ctx *ctx)
+{
+	emit(opcode | RS1(dst) | RS2(src) | RD(dst), ctx);
+}
+
+static void emit_alu3(u32 opcode, u32 a, u32 b, u32 c, struct jit_ctx *ctx)
+{
+	emit(opcode | RS1(a) | RS2(b) | RD(c), ctx);
+}
+
+static void emit_alu_K(unsigned int opcode, unsigned int dst, unsigned int imm,
+		       struct jit_ctx *ctx)
+{
+	bool small_immed = is_simm13(imm);
+	unsigned int insn = opcode;
+
+	insn |= RS1(dst) | RD(dst);
+	if (small_immed) {
+		emit(insn | IMMED | S13(imm), ctx);
+	} else {
+		unsigned int tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_set_const_sext(imm, tmp, ctx);
+		emit(insn | RS2(tmp), ctx);
+	}
+}
+
+static void emit_alu3_K(unsigned int opcode, unsigned int src, unsigned int imm,
+			unsigned int dst, struct jit_ctx *ctx)
+{
+	bool small_immed = is_simm13(imm);
+	unsigned int insn = opcode;
+
+	insn |= RS1(src) | RD(dst);
+	if (small_immed) {
+		emit(insn | IMMED | S13(imm), ctx);
+	} else {
+		unsigned int tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_set_const_sext(imm, tmp, ctx);
+		emit(insn | RS2(tmp), ctx);
+	}
+}
+
+static void emit_loadimm32(s32 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	if (K >= 0 && is_simm13(K)) {
+		/* or %g0, K, DEST */
+		emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx);
+	} else {
+		emit_set_const(K, dest, ctx);
+	}
+}
+
+static void emit_loadimm(s32 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	if (is_simm13(K)) {
+		/* or %g0, K, DEST */
+		emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx);
+	} else {
+		emit_set_const(K, dest, ctx);
+	}
+}
+
+static void emit_loadimm_sext(s32 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	if (is_simm13(K)) {
+		/* or %g0, K, DEST */
+		emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx);
+	} else {
+		emit_set_const_sext(K, dest, ctx);
+	}
+}
+
+static void analyze_64bit_constant(u32 high_bits, u32 low_bits,
+				   int *hbsp, int *lbsp, int *abbasp)
+{
+	int lowest_bit_set, highest_bit_set, all_bits_between_are_set;
+	int i;
+
+	lowest_bit_set = highest_bit_set = -1;
+	i = 0;
+	do {
+		if ((lowest_bit_set == -1) && ((low_bits >> i) & 1))
+			lowest_bit_set = i;
+		if ((highest_bit_set == -1) && ((high_bits >> (32 - i - 1)) & 1))
+			highest_bit_set = (64 - i - 1);
+	}  while (++i < 32 && (highest_bit_set == -1 ||
+			       lowest_bit_set == -1));
+	if (i == 32) {
+		i = 0;
+		do {
+			if (lowest_bit_set == -1 && ((high_bits >> i) & 1))
+				lowest_bit_set = i + 32;
+			if (highest_bit_set == -1 &&
+			    ((low_bits >> (32 - i - 1)) & 1))
+				highest_bit_set = 32 - i - 1;
+		} while (++i < 32 && (highest_bit_set == -1 ||
+				      lowest_bit_set == -1));
+	}
+
+	all_bits_between_are_set = 1;
+	for (i = lowest_bit_set; i <= highest_bit_set; i++) {
+		if (i < 32) {
+			if ((low_bits & (1 << i)) != 0)
+				continue;
+		} else {
+			if ((high_bits & (1 << (i - 32))) != 0)
+				continue;
+		}
+		all_bits_between_are_set = 0;
+		break;
+	}
+	*hbsp = highest_bit_set;
+	*lbsp = lowest_bit_set;
+	*abbasp = all_bits_between_are_set;
+}
+
+static unsigned long create_simple_focus_bits(unsigned long high_bits,
+					      unsigned long low_bits,
+					      int lowest_bit_set, int shift)
+{
+	long hi, lo;
+
+	if (lowest_bit_set < 32) {
+		lo = (low_bits >> lowest_bit_set) << shift;
+		hi = ((high_bits << (32 - lowest_bit_set)) << shift);
+	} else {
+		lo = 0;
+		hi = ((high_bits >> (lowest_bit_set - 32)) << shift);
+	}
+	return hi | lo;
+}
+
+static bool const64_is_2insns(unsigned long high_bits,
+			      unsigned long low_bits)
+{
+	int highest_bit_set, lowest_bit_set, all_bits_between_are_set;
+
+	if (high_bits == 0 || high_bits == 0xffffffff)
+		return true;
+
+	analyze_64bit_constant(high_bits, low_bits,
+			       &highest_bit_set, &lowest_bit_set,
+			       &all_bits_between_are_set);
+
+	if ((highest_bit_set == 63 || lowest_bit_set == 0) &&
+	    all_bits_between_are_set != 0)
+		return true;
+
+	if (highest_bit_set - lowest_bit_set < 21)
+		return true;
+
+	return false;
+}
+
+static void sparc_emit_set_const64_quick2(unsigned long high_bits,
+					  unsigned long low_imm,
+					  unsigned int dest,
+					  int shift_count, struct jit_ctx *ctx)
+{
+	emit_loadimm32(high_bits, dest, ctx);
+
+	/* Now shift it up into place.  */
+	emit_alu_K(SLLX, dest, shift_count, ctx);
+
+	/* If there is a low immediate part piece, finish up by
+	 * putting that in as well.
+	 */
+	if (low_imm != 0)
+		emit(OR | IMMED | RS1(dest) | S13(low_imm) | RD(dest), ctx);
+}
+
+static void emit_loadimm64(u64 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	int all_bits_between_are_set, lowest_bit_set, highest_bit_set;
+	unsigned int tmp = bpf2sparc[TMP_REG_1];
+	u32 low_bits = (K & 0xffffffff);
+	u32 high_bits = (K >> 32);
+
+	/* These two tests also take care of all of the one
+	 * instruction cases.
+	 */
+	if (high_bits == 0xffffffff && (low_bits & 0x80000000))
+		return emit_loadimm_sext(K, dest, ctx);
+	if (high_bits == 0x00000000)
+		return emit_loadimm32(K, dest, ctx);
+
+	analyze_64bit_constant(high_bits, low_bits, &highest_bit_set,
+			       &lowest_bit_set, &all_bits_between_are_set);
+
+	/* 1) mov	-1, %reg
+	 *    sllx	%reg, shift, %reg
+	 * 2) mov	-1, %reg
+	 *    srlx	%reg, shift, %reg
+	 * 3) mov	some_small_const, %reg
+	 *    sllx	%reg, shift, %reg
+	 */
+	if (((highest_bit_set == 63 || lowest_bit_set == 0) &&
+	     all_bits_between_are_set != 0) ||
+	    ((highest_bit_set - lowest_bit_set) < 12)) {
+		int shift = lowest_bit_set;
+		long the_const = -1;
+
+		if ((highest_bit_set != 63 && lowest_bit_set != 0) ||
+		    all_bits_between_are_set == 0) {
+			the_const =
+				create_simple_focus_bits(high_bits, low_bits,
+							 lowest_bit_set, 0);
+		} else if (lowest_bit_set == 0)
+			shift = -(63 - highest_bit_set);
+
+		emit(OR | IMMED | RS1(G0) | S13(the_const) | RD(dest), ctx);
+		if (shift > 0)
+			emit_alu_K(SLLX, dest, shift, ctx);
+		else if (shift < 0)
+			emit_alu_K(SRLX, dest, -shift, ctx);
+
+		return;
+	}
+
+	/* Now a range of 22 or less bits set somewhere.
+	 * 1) sethi	%hi(focus_bits), %reg
+	 *    sllx	%reg, shift, %reg
+	 * 2) sethi	%hi(focus_bits), %reg
+	 *    srlx	%reg, shift, %reg
+	 */
+	if ((highest_bit_set - lowest_bit_set) < 21) {
+		unsigned long focus_bits =
+			create_simple_focus_bits(high_bits, low_bits,
+						 lowest_bit_set, 10);
+
+		emit(SETHI(focus_bits, dest), ctx);
+
+		/* If lowest_bit_set == 10 then a sethi alone could
+		 * have done it.
+		 */
+		if (lowest_bit_set < 10)
+			emit_alu_K(SRLX, dest, 10 - lowest_bit_set, ctx);
+		else if (lowest_bit_set > 10)
+			emit_alu_K(SLLX, dest, lowest_bit_set - 10, ctx);
+		return;
+	}
+
+	/* Ok, now 3 instruction sequences.  */
+	if (low_bits == 0) {
+		emit_loadimm32(high_bits, dest, ctx);
+		emit_alu_K(SLLX, dest, 32, ctx);
+		return;
+	}
+
+	/* We may be able to do something quick
+	 * when the constant is negated, so try that.
+	 */
+	if (const64_is_2insns((~high_bits) & 0xffffffff,
+			      (~low_bits) & 0xfffffc00)) {
+		/* NOTE: The trailing bits get XOR'd so we need the
+		 * non-negated bits, not the negated ones.
+		 */
+		unsigned long trailing_bits = low_bits & 0x3ff;
+
+		if ((((~high_bits) & 0xffffffff) == 0 &&
+		     ((~low_bits) & 0x80000000) == 0) ||
+		    (((~high_bits) & 0xffffffff) == 0xffffffff &&
+		     ((~low_bits) & 0x80000000) != 0)) {
+			unsigned long fast_int = (~low_bits & 0xffffffff);
+
+			if ((is_sethi(fast_int) &&
+			     (~high_bits & 0xffffffff) == 0)) {
+				emit(SETHI(fast_int, dest), ctx);
+			} else if (is_simm13(fast_int)) {
+				emit(OR | IMMED | RS1(G0) | S13(fast_int) | RD(dest), ctx);
+			} else {
+				emit_loadimm64(fast_int, dest, ctx);
+			}
+		} else {
+			u64 n = ((~low_bits) & 0xfffffc00) |
+				(((unsigned long)((~high_bits) & 0xffffffff))<<32);
+			emit_loadimm64(n, dest, ctx);
+		}
+
+		low_bits = -0x400 | trailing_bits;
+
+		emit(XOR | IMMED | RS1(dest) | S13(low_bits) | RD(dest), ctx);
+		return;
+	}
+
+	/* 1) sethi	%hi(xxx), %reg
+	 *    or	%reg, %lo(xxx), %reg
+	 *    sllx	%reg, yyy, %reg
+	 */
+	if ((highest_bit_set - lowest_bit_set) < 32) {
+		unsigned long focus_bits =
+			create_simple_focus_bits(high_bits, low_bits,
+						 lowest_bit_set, 0);
+
+		/* So what we know is that the set bits straddle the
+		 * middle of the 64-bit word.
+		 */
+		sparc_emit_set_const64_quick2(focus_bits, 0, dest,
+					      lowest_bit_set, ctx);
+		return;
+	}
+
+	/* 1) sethi	%hi(high_bits), %reg
+	 *    or	%reg, %lo(high_bits), %reg
+	 *    sllx	%reg, 32, %reg
+	 *    or	%reg, low_bits, %reg
+	 */
+	if (is_simm13(low_bits) && ((int)low_bits > 0)) {
+		sparc_emit_set_const64_quick2(high_bits, low_bits,
+					      dest, 32, ctx);
+		return;
+	}
+
+	/* Oh well, we tried... Do a full 64-bit decomposition.  */
+	ctx->tmp_1_used = true;
+
+	emit_loadimm32(high_bits, tmp, ctx);
+	emit_loadimm32(low_bits, dest, ctx);
+	emit_alu_K(SLLX, tmp, 32, ctx);
+	emit(OR | RS1(dest) | RS2(tmp) | RD(dest), ctx);
+}
+
+static void emit_branch(unsigned int br_opc, unsigned int from_idx, unsigned int to_idx,
+			struct jit_ctx *ctx)
+{
+	unsigned int off = to_idx - from_idx;
+
+	if (br_opc & XCC)
+		emit(br_opc | WDISP19(off << 2), ctx);
+	else
+		emit(br_opc | WDISP22(off << 2), ctx);
+}
+
+static void emit_cbcond(unsigned int cb_opc, unsigned int from_idx, unsigned int to_idx,
+			const u8 dst, const u8 src, struct jit_ctx *ctx)
+{
+	unsigned int off = to_idx - from_idx;
+
+	emit(cb_opc | WDISP10(off << 2) | RS1(dst) | RS2(src), ctx);
+}
+
+static void emit_cbcondi(unsigned int cb_opc, unsigned int from_idx, unsigned int to_idx,
+			 const u8 dst, s32 imm, struct jit_ctx *ctx)
+{
+	unsigned int off = to_idx - from_idx;
+
+	emit(cb_opc | IMMED | WDISP10(off << 2) | RS1(dst) | S5(imm), ctx);
+}
+
+#define emit_read_y(REG, CTX)	emit(RD_Y | RD(REG), CTX)
+#define emit_write_y(REG, CTX)	emit(WR_Y | IMMED | RS1(REG) | S13(0), CTX)
+
+#define emit_cmp(R1, R2, CTX)				\
+	emit(SUBCC | RS1(R1) | RS2(R2) | RD(G0), CTX)
+
+#define emit_cmpi(R1, IMM, CTX)				\
+	emit(SUBCC | IMMED | RS1(R1) | S13(IMM) | RD(G0), CTX)
+
+#define emit_btst(R1, R2, CTX)				\
+	emit(ANDCC | RS1(R1) | RS2(R2) | RD(G0), CTX)
+
+#define emit_btsti(R1, IMM, CTX)			\
+	emit(ANDCC | IMMED | RS1(R1) | S13(IMM) | RD(G0), CTX)
+
+static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
+				   const s32 imm, bool is_imm, int branch_dst,
+				   struct jit_ctx *ctx)
+{
+	bool use_cbcond = (sparc64_elf_hwcap & AV_SPARC_CBCOND) != 0;
+	const u8 tmp = bpf2sparc[TMP_REG_1];
+
+	branch_dst = ctx->offset[branch_dst];
+
+	if (!is_simm10(branch_dst - ctx->idx) ||
+	    BPF_OP(code) == BPF_JSET)
+		use_cbcond = false;
+
+	if (is_imm) {
+		bool fits = true;
+
+		if (use_cbcond) {
+			if (!is_simm5(imm))
+				fits = false;
+		} else if (!is_simm13(imm)) {
+			fits = false;
+		}
+		if (!fits) {
+			ctx->tmp_1_used = true;
+			emit_loadimm_sext(imm, tmp, ctx);
+			src = tmp;
+			is_imm = false;
+		}
+	}
+
+	if (!use_cbcond) {
+		u32 br_opcode;
+
+		if (BPF_OP(code) == BPF_JSET) {
+			if (is_imm)
+				emit_btsti(dst, imm, ctx);
+			else
+				emit_btst(dst, src, ctx);
+		} else {
+			if (is_imm)
+				emit_cmpi(dst, imm, ctx);
+			else
+				emit_cmp(dst, src, ctx);
+		}
+		switch (BPF_OP(code)) {
+		case BPF_JEQ:
+			br_opcode = BE;
+			break;
+		case BPF_JGT:
+			br_opcode = BGU;
+			break;
+		case BPF_JGE:
+			br_opcode = BGEU;
+			break;
+		case BPF_JSET:
+		case BPF_JNE:
+			br_opcode = BNE;
+			break;
+		case BPF_JSGT:
+			br_opcode = BG;
+			break;
+		case BPF_JSGE:
+			br_opcode = BGE;
+			break;
+		default:
+			/* Make sure we dont leak kernel information to the
+			 * user.
+			 */
+			return -EFAULT;
+		}
+		emit_branch(br_opcode, ctx->idx, branch_dst, ctx);
+		emit_nop(ctx);
+	} else {
+		u32 cbcond_opcode;
+
+		switch (BPF_OP(code)) {
+		case BPF_JEQ:
+			cbcond_opcode = CBCONDE;
+			break;
+		case BPF_JGT:
+			cbcond_opcode = CBCONDGU;
+			break;
+		case BPF_JGE:
+			cbcond_opcode = CBCONDGEU;
+			break;
+		case BPF_JNE:
+			cbcond_opcode = CBCONDNE;
+			break;
+		case BPF_JSGT:
+			cbcond_opcode = CBCONDG;
+			break;
+		case BPF_JSGE:
+			cbcond_opcode = CBCONDGE;
+			break;
+		default:
+			/* Make sure we dont leak kernel information to the
+			 * user.
+			 */
+			return -EFAULT;
+		}
+		cbcond_opcode |= CBCOND_OP;
+		if (is_imm)
+			emit_cbcondi(cbcond_opcode, ctx->idx, branch_dst,
+				     dst, imm, ctx);
+		else
+			emit_cbcond(cbcond_opcode, ctx->idx, branch_dst,
+				    dst, src, ctx);
+	}
+	return 0;
+}
+
+static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb)
+{
+	const u8 r_headlen = bpf2sparc[SKB_HLEN_REG];
+	const u8 r_data = bpf2sparc[SKB_DATA_REG];
+	const u8 r_tmp = bpf2sparc[TMP_REG_1];
+	unsigned int off;
+
+	off = offsetof(struct sk_buff, len);
+	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx);
+
+	off = offsetof(struct sk_buff, data_len);
+	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx);
+
+	emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx);
+
+	off = offsetof(struct sk_buff, data);
+	emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx);
+}
+
+/* Just skip the save instruction and the ctx register move.  */
+#define BPF_TAILCALL_PROLOGUE_SKIP	16
+#define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	s32 stack_needed = BASE_STACKFRAME;
+
+	if (ctx->saw_frame_pointer || ctx->saw_tail_call)
+		stack_needed += MAX_BPF_STACK;
+
+	if (ctx->saw_tail_call)
+		stack_needed += 8;
+
+	/* save %sp, -176, %sp */
+	emit(SAVE | IMMED | RS1(SP) | S13(-stack_needed) | RD(SP), ctx);
+
+	/* tail_call_cnt = 0 */
+	if (ctx->saw_tail_call) {
+		u32 off = BPF_TAILCALL_CNT_SP_OFF;
+
+		emit(ST32 | IMMED | RS1(SP) | S13(off) | RD(G0), ctx);
+	} else {
+		emit_nop(ctx);
+	}
+	if (ctx->saw_frame_pointer) {
+		const u8 vfp = bpf2sparc[BPF_REG_FP];
+
+		emit(ADD | IMMED | RS1(FP) | S13(STACK_BIAS) | RD(vfp), ctx);
+	}
+
+	emit_reg_move(I0, O0, ctx);
+	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
+
+	if (ctx->saw_ld_abs_ind)
+		load_skb_regs(ctx, bpf2sparc[BPF_REG_1]);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	ctx->epilogue_offset = ctx->idx;
+
+	/* ret (jmpl %i7 + 8, %g0) */
+	emit(JMPL | IMMED | RS1(I7) | S13(8) | RD(G0), ctx);
+
+	/* restore %i5, %g0, %o0 */
+	emit(RESTORE | RS1(bpf2sparc[BPF_REG_0]) | RS2(G0) | RD(O0), ctx);
+}
+
+static void emit_tail_call(struct jit_ctx *ctx)
+{
+	const u8 bpf_array = bpf2sparc[BPF_REG_2];
+	const u8 bpf_index = bpf2sparc[BPF_REG_3];
+	const u8 tmp = bpf2sparc[TMP_REG_1];
+	u32 off;
+
+	ctx->saw_tail_call = true;
+
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit(LD32 | IMMED | RS1(bpf_array) | S13(off) | RD(tmp), ctx);
+	emit_cmp(bpf_index, tmp, ctx);
+#define OFFSET1 17
+	emit_branch(BGEU, ctx->idx, ctx->idx + OFFSET1, ctx);
+	emit_nop(ctx);
+
+	off = BPF_TAILCALL_CNT_SP_OFF;
+	emit(LD32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx);
+	emit_cmpi(tmp, MAX_TAIL_CALL_CNT, ctx);
+#define OFFSET2 13
+	emit_branch(BGU, ctx->idx, ctx->idx + OFFSET2, ctx);
+	emit_nop(ctx);
+
+	emit_alu_K(ADD, tmp, 1, ctx);
+	off = BPF_TAILCALL_CNT_SP_OFF;
+	emit(ST32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx);
+
+	emit_alu3_K(SLL, bpf_index, 3, tmp, ctx);
+	emit_alu(ADD, bpf_array, tmp, ctx);
+	off = offsetof(struct bpf_array, ptrs);
+	emit(LD64 | IMMED | RS1(tmp) | S13(off) | RD(tmp), ctx);
+
+	emit_cmpi(tmp, 0, ctx);
+#define OFFSET3 5
+	emit_branch(BE, ctx->idx, ctx->idx + OFFSET3, ctx);
+	emit_nop(ctx);
+
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit(LD64 | IMMED | RS1(tmp) | S13(off) | RD(tmp), ctx);
+
+	off = BPF_TAILCALL_PROLOGUE_SKIP;
+	emit(JMPL | IMMED | RS1(tmp) | S13(off) | RD(G0), ctx);
+	emit_nop(ctx);
+}
+
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const u8 code = insn->code;
+	const u8 dst = bpf2sparc[insn->dst_reg];
+	const u8 src = bpf2sparc[insn->src_reg];
+	const int i = insn - ctx->prog->insnsi;
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	u32 *func;
+
+	if (insn->src_reg == BPF_REG_FP)
+		ctx->saw_frame_pointer = true;
+
+	switch (code) {
+	/* dst = src */
+	case BPF_ALU | BPF_MOV | BPF_X:
+		emit_alu3_K(SRL, src, 0, dst, ctx);
+		break;
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		emit_reg_move(src, dst, ctx);
+		break;
+	/* dst = dst OP src */
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		emit_alu(ADD, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		emit_alu(SUB, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		emit_alu(AND, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		emit_alu(OR, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_XOR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		emit_alu(XOR, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_MUL | BPF_X:
+		emit_alu(MUL, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		emit_alu(MULX, src, dst, ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_X:
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_write_y(G0, ctx);
+		emit_alu(DIV, src, dst, ctx);
+		break;
+
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_alu(UDIVX, src, dst, ctx);
+		break;
+
+	case BPF_ALU | BPF_MOD | BPF_X: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_write_y(G0, ctx);
+		emit_alu3(DIV, dst, src, tmp, ctx);
+		emit_alu3(MULX, tmp, src, tmp, ctx);
+		emit_alu3(SUB, dst, tmp, dst, ctx);
+		goto do_alu32_trunc;
+	}
+	case BPF_ALU64 | BPF_MOD | BPF_X: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_alu3(UDIVX, dst, src, tmp, ctx);
+		emit_alu3(MULX, tmp, src, tmp, ctx);
+		emit_alu3(SUB, dst, tmp, dst, ctx);
+		break;
+	}
+	case BPF_ALU | BPF_LSH | BPF_X:
+		emit_alu(SLL, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+		emit_alu(SLLX, src, dst, ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_X:
+		emit_alu(SRL, src, dst, ctx);
+		break;
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+		emit_alu(SRLX, src, dst, ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_X:
+		emit_alu(SRA, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		emit_alu(SRAX, src, dst, ctx);
+		break;
+
+	/* dst = -dst */
+	case BPF_ALU | BPF_NEG:
+	case BPF_ALU64 | BPF_NEG:
+		emit(SUB | RS1(0) | RS2(dst) | RD(dst), ctx);
+		goto do_alu32_trunc;
+
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+		switch (imm) {
+		case 16:
+			emit_alu_K(SLL, dst, 16, ctx);
+			emit_alu_K(SRL, dst, 16, ctx);
+			break;
+		case 32:
+			emit_alu_K(SRL, dst, 0, ctx);
+			break;
+		case 64:
+			/* nop */
+			break;
+
+		}
+		break;
+
+	/* dst = BSWAP##imm(dst) */
+	case BPF_ALU | BPF_END | BPF_FROM_LE: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+
+		ctx->tmp_1_used = true;
+		switch (imm) {
+		case 16:
+			emit_alu3_K(AND, dst, 0xff, tmp, ctx);
+			emit_alu3_K(SRL, dst, 8, dst, ctx);
+			emit_alu3_K(AND, dst, 0xff, dst, ctx);
+			emit_alu3_K(SLL, tmp, 8, tmp, ctx);
+			emit_alu(OR, tmp, dst, ctx);
+			break;
+
+		case 32:
+			ctx->tmp_2_used = true;
+			emit_alu3_K(SRL, dst, 24, tmp, ctx);	/* tmp  = dst >> 24 */
+			emit_alu3_K(SRL, dst, 16, tmp2, ctx);	/* tmp2 = dst >> 16 */
+			emit_alu3_K(AND, tmp2, 0xff, tmp2, ctx);/* tmp2 = tmp2 & 0xff */
+			emit_alu3_K(SLL, tmp2, 8, tmp2, ctx);	/* tmp2 = tmp2 << 8 */
+			emit_alu(OR, tmp2, tmp, ctx);		/* tmp  = tmp | tmp2 */
+			emit_alu3_K(SRL, dst, 8, tmp2, ctx);	/* tmp2 = dst >> 8 */
+			emit_alu3_K(AND, tmp2, 0xff, tmp2, ctx);/* tmp2 = tmp2 & 0xff */
+			emit_alu3_K(SLL, tmp2, 16, tmp2, ctx);	/* tmp2 = tmp2 << 16 */
+			emit_alu(OR, tmp2, tmp, ctx);		/* tmp  = tmp | tmp2 */
+			emit_alu3_K(AND, dst, 0xff, dst, ctx);	/* dst	= dst & 0xff */
+			emit_alu3_K(SLL, dst, 24, dst, ctx);	/* dst  = dst << 24 */
+			emit_alu(OR, tmp, dst, ctx);		/* dst  = dst | tmp */
+			break;
+
+		case 64:
+			emit_alu3_K(ADD, SP, STACK_BIAS + 128, tmp, ctx);
+			emit(ST64 | RS1(tmp) | RS2(G0) | RD(dst), ctx);
+			emit(LD64A | ASI(ASI_PL) | RS1(tmp) | RS2(G0) | RD(dst), ctx);
+			break;
+		}
+		break;
+	}
+	/* dst = imm */
+	case BPF_ALU | BPF_MOV | BPF_K:
+		emit_loadimm32(imm, dst, ctx);
+		break;
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		emit_loadimm_sext(imm, dst, ctx);
+		break;
+	/* dst = dst OP imm */
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		emit_alu_K(ADD, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		emit_alu_K(SUB, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		emit_alu_K(AND, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		emit_alu_K(OR, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		emit_alu_K(XOR, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_MUL | BPF_K:
+		emit_alu_K(MUL, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		emit_alu_K(MULX, dst, imm, ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_K:
+		if (imm == 0)
+			return -EINVAL;
+
+		emit_write_y(G0, ctx);
+		emit_alu_K(DIV, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+		if (imm == 0)
+			return -EINVAL;
+
+		emit_alu_K(UDIVX, dst, imm, ctx);
+		break;
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+	case BPF_ALU | BPF_MOD | BPF_K: {
+		const u8 tmp = bpf2sparc[TMP_REG_2];
+		unsigned int div;
+
+		if (imm == 0)
+			return -EINVAL;
+
+		div = (BPF_CLASS(code) == BPF_ALU64) ? UDIVX : DIV;
+
+		ctx->tmp_2_used = true;
+
+		if (BPF_CLASS(code) != BPF_ALU64)
+			emit_write_y(G0, ctx);
+		if (is_simm13(imm)) {
+			emit(div | IMMED | RS1(dst) | S13(imm) | RD(tmp), ctx);
+			emit(MULX | IMMED | RS1(tmp) | S13(imm) | RD(tmp), ctx);
+			emit(SUB | RS1(dst) | RS2(tmp) | RD(dst), ctx);
+		} else {
+			const u8 tmp1 = bpf2sparc[TMP_REG_1];
+
+			ctx->tmp_1_used = true;
+
+			emit_set_const_sext(imm, tmp1, ctx);
+			emit(div | RS1(dst) | RS2(tmp1) | RD(tmp), ctx);
+			emit(MULX | RS1(tmp) | RS2(tmp1) | RD(tmp), ctx);
+			emit(SUB | RS1(dst) | RS2(tmp) | RD(dst), ctx);
+		}
+		goto do_alu32_trunc;
+	}
+	case BPF_ALU | BPF_LSH | BPF_K:
+		emit_alu_K(SLL, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		emit_alu_K(SLLX, dst, imm, ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_K:
+		emit_alu_K(SRL, dst, imm, ctx);
+		break;
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		emit_alu_K(SRLX, dst, imm, ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_K:
+		emit_alu_K(SRA, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		emit_alu_K(SRAX, dst, imm, ctx);
+		break;
+
+	do_alu32_trunc:
+		if (BPF_CLASS(code) == BPF_ALU)
+			emit_alu_K(SRL, dst, 0, ctx);
+		break;
+
+	/* JUMP off */
+	case BPF_JMP | BPF_JA:
+		emit_branch(BA, ctx->idx, ctx->offset[i + off], ctx);
+		emit_nop(ctx);
+		break;
+	/* IF (dst COND src) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JSET | BPF_X: {
+		int err;
+
+		err = emit_compare_and_branch(code, dst, src, 0, false, i + off, ctx);
+		if (err)
+			return err;
+		break;
+	}
+	/* IF (dst COND imm) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP | BPF_JSET | BPF_K: {
+		int err;
+
+		err = emit_compare_and_branch(code, dst, 0, imm, true, i + off, ctx);
+		if (err)
+			return err;
+		break;
+	}
+
+	/* function call */
+	case BPF_JMP | BPF_CALL:
+	{
+		u8 *func = ((u8 *)__bpf_call_base) + imm;
+
+		ctx->saw_call = true;
+
+		emit_call((u32 *)func, ctx);
+		emit_nop(ctx);
+
+		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
+
+		if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind)
+			load_skb_regs(ctx, bpf2sparc[BPF_REG_6]);
+		break;
+	}
+
+	/* tail call */
+	case BPF_JMP | BPF_CALL |BPF_X:
+		emit_tail_call(ctx);
+		break;
+
+	/* function return */
+	case BPF_JMP | BPF_EXIT:
+		/* Optimization: when last instruction is EXIT,
+		   simply fallthrough to epilogue. */
+		if (i == ctx->prog->len - 1)
+			break;
+		emit_branch(BA, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_nop(ctx);
+		break;
+
+	/* dst = imm64 */
+	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		const struct bpf_insn insn1 = insn[1];
+		u64 imm64;
+
+		imm64 = (u64)insn1.imm << 32 | (u32)imm;
+		emit_loadimm64(imm64, dst, ctx);
+
+		return 1;
+	}
+
+	/* LDX: dst = *(size *)(src + off) */
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		u32 opcode = 0, rs2;
+
+		ctx->tmp_1_used = true;
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			opcode = LD32;
+			break;
+		case BPF_H:
+			opcode = LD16;
+			break;
+		case BPF_B:
+			opcode = LD8;
+			break;
+		case BPF_DW:
+			opcode = LD64;
+			break;
+		}
+
+		if (is_simm13(off)) {
+			opcode |= IMMED;
+			rs2 = S13(off);
+		} else {
+			emit_loadimm(off, tmp, ctx);
+			rs2 = RS2(tmp);
+		}
+		emit(opcode | RS1(src) | rs2 | RD(dst), ctx);
+		break;
+	}
+	/* ST: *(size *)(dst + off) = imm */
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_B:
+	case BPF_ST | BPF_MEM | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+		u32 opcode = 0, rs2;
+
+		ctx->tmp_2_used = true;
+		emit_loadimm(imm, tmp2, ctx);
+
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			opcode = ST32;
+			break;
+		case BPF_H:
+			opcode = ST16;
+			break;
+		case BPF_B:
+			opcode = ST8;
+			break;
+		case BPF_DW:
+			opcode = ST64;
+			break;
+		}
+
+		if (is_simm13(off)) {
+			opcode |= IMMED;
+			rs2 = S13(off);
+		} else {
+			ctx->tmp_1_used = true;
+			emit_loadimm(off, tmp, ctx);
+			rs2 = RS2(tmp);
+		}
+		emit(opcode | RS1(dst) | rs2 | RD(tmp2), ctx);
+		break;
+	}
+
+	/* STX: *(size *)(dst + off) = src */
+	case BPF_STX | BPF_MEM | BPF_W:
+	case BPF_STX | BPF_MEM | BPF_H:
+	case BPF_STX | BPF_MEM | BPF_B:
+	case BPF_STX | BPF_MEM | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		u32 opcode = 0, rs2;
+
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			opcode = ST32;
+			break;
+		case BPF_H:
+			opcode = ST16;
+			break;
+		case BPF_B:
+			opcode = ST8;
+			break;
+		case BPF_DW:
+			opcode = ST64;
+			break;
+		}
+		if (is_simm13(off)) {
+			opcode |= IMMED;
+			rs2 = S13(off);
+		} else {
+			ctx->tmp_1_used = true;
+			emit_loadimm(off, tmp, ctx);
+			rs2 = RS2(tmp);
+		}
+		emit(opcode | RS1(dst) | rs2 | RD(src), ctx);
+		break;
+	}
+
+	/* STX XADD: lock *(u32 *)(dst + off) += src */
+	case BPF_STX | BPF_XADD | BPF_W: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+		const u8 tmp3 = bpf2sparc[TMP_REG_3];
+
+		ctx->tmp_1_used = true;
+		ctx->tmp_2_used = true;
+		ctx->tmp_3_used = true;
+		emit_loadimm(off, tmp, ctx);
+		emit_alu3(ADD, dst, tmp, tmp, ctx);
+
+		emit(LD32 | RS1(tmp) | RS2(G0) | RD(tmp2), ctx);
+		emit_alu3(ADD, tmp2, src, tmp3, ctx);
+		emit(CAS | ASI(ASI_P) | RS1(tmp) | RS2(tmp2) | RD(tmp3), ctx);
+		emit_cmp(tmp2, tmp3, ctx);
+		emit_branch(BNE, 4, 0, ctx);
+		emit_nop(ctx);
+		break;
+	}
+	/* STX XADD: lock *(u64 *)(dst + off) += src */
+	case BPF_STX | BPF_XADD | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+		const u8 tmp3 = bpf2sparc[TMP_REG_3];
+
+		ctx->tmp_1_used = true;
+		ctx->tmp_2_used = true;
+		ctx->tmp_3_used = true;
+		emit_loadimm(off, tmp, ctx);
+		emit_alu3(ADD, dst, tmp, tmp, ctx);
+
+		emit(LD64 | RS1(tmp) | RS2(G0) | RD(tmp2), ctx);
+		emit_alu3(ADD, tmp2, src, tmp3, ctx);
+		emit(CASX | ASI(ASI_P) | RS1(tmp) | RS2(tmp2) | RD(tmp3), ctx);
+		emit_cmp(tmp2, tmp3, ctx);
+		emit_branch(BNE, 4, 0, ctx);
+		emit_nop(ctx);
+		break;
+	}
+#define CHOOSE_LOAD_FUNC(K, func) \
+		((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
+
+	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
+	case BPF_LD | BPF_ABS | BPF_W:
+		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word);
+		goto common_load;
+	case BPF_LD | BPF_ABS | BPF_H:
+		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half);
+		goto common_load;
+	case BPF_LD | BPF_ABS | BPF_B:
+		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte);
+		goto common_load;
+	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
+	case BPF_LD | BPF_IND | BPF_W:
+		func = bpf_jit_load_word;
+		goto common_load;
+	case BPF_LD | BPF_IND | BPF_H:
+		func = bpf_jit_load_half;
+		goto common_load;
+
+	case BPF_LD | BPF_IND | BPF_B:
+		func = bpf_jit_load_byte;
+	common_load:
+		ctx->saw_ld_abs_ind = true;
+
+		emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx);
+		emit_loadimm(imm, O1, ctx);
+
+		if (BPF_MODE(code) == BPF_IND)
+			emit_alu(ADD, src, O1, ctx);
+
+		emit_call(func, ctx);
+		emit_alu_K(SRA, O1, 0, ctx);
+
+		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
+		break;
+
+	default:
+		pr_err_once("unknown opcode %02x\n", code);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	const struct bpf_prog *prog = ctx->prog;
+	int i;
+
+	for (i = 0; i < prog->len; i++) {
+		const struct bpf_insn *insn = &prog->insnsi[i];
+		int ret;
+
+		ret = build_insn(insn, ctx);
+
+		if (ret > 0) {
+			i++;
+			ctx->offset[i] = ctx->idx;
+			continue;
+		}
+		ctx->offset[i] = ctx->idx;
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	u32 *ptr;
+	/* We are guaranteed to have aligned memory. */
+	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
+		*ptr++ = 0x91d02005; /* ta 5 */
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	struct bpf_prog *tmp, *orig_prog = prog;
+	struct bpf_binary_header *header;
+	bool tmp_blinded = false;
+	struct jit_ctx ctx;
+	u32 image_size;
+	u8 *image_ptr;
+	int pass;
+
+	if (!bpf_jit_enable)
+		return orig_prog;
+
+	tmp = bpf_jit_blind_constants(prog);
+	/* If blinding was requested and we failed during blinding,
+	 * we must fall back to the interpreter.
+	 */
+	if (IS_ERR(tmp))
+		return orig_prog;
+	if (tmp != prog) {
+		tmp_blinded = true;
+		prog = tmp;
+	}
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.prog = prog;
+
+	ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL);
+	if (ctx.offset == NULL) {
+		prog = orig_prog;
+		goto out;
+	}
+
+	/* Fake pass to detect features used, and get an accurate assessment
+	 * of what the final image size will be.
+	 */
+	if (build_body(&ctx)) {
+		prog = orig_prog;
+		goto out_off;
+	}
+	build_prologue(&ctx);
+	build_epilogue(&ctx);
+
+	/* Now we know the actual image size. */
+	image_size = sizeof(u32) * ctx.idx;
+	header = bpf_jit_binary_alloc(image_size, &image_ptr,
+				      sizeof(u32), jit_fill_hole);
+	if (header == NULL) {
+		prog = orig_prog;
+		goto out_off;
+	}
+
+	ctx.image = (u32 *)image_ptr;
+
+	for (pass = 1; pass < 3; pass++) {
+		ctx.idx = 0;
+
+		build_prologue(&ctx);
+
+		if (build_body(&ctx)) {
+			bpf_jit_binary_free(header);
+			prog = orig_prog;
+			goto out_off;
+		}
+
+		build_epilogue(&ctx);
+
+		if (bpf_jit_enable > 1)
+			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass,
+				image_size - (ctx.idx * 4),
+				ctx.tmp_1_used ? '1' : ' ',
+				ctx.tmp_2_used ? '2' : ' ',
+				ctx.tmp_3_used ? '3' : ' ',
+				ctx.saw_ld_abs_ind ? 'L' : ' ',
+				ctx.saw_frame_pointer ? 'F' : ' ',
+				ctx.saw_call ? 'C' : ' ',
+				ctx.saw_tail_call ? 'T' : ' ');
+	}
+
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(prog->len, image_size, pass, ctx.image);
+
+	bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE));
+
+	bpf_jit_binary_lock_ro(header);
+
+	prog->bpf_func = (void *)ctx.image;
+	prog->jited = 1;
+
+out_off:
+	kfree(ctx.offset);
+out:
+	if (tmp_blinded)
+		bpf_jit_prog_release_other(prog, prog == orig_prog ?
+					   tmp : orig_prog);
+	return prog;
+}
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index fd122ef45b00..0d925fa0f0c1 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -249,7 +249,6 @@ CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_TILE=y
 CONFIG_EXT2_FS=y
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index eb6a55944191..149d8e8eacb8 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -358,7 +358,6 @@ CONFIG_WATCHDOG_NOWAYOUT=y
 # CONFIG_VGA_ARB is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_TILE=y
 CONFIG_EXT2_FS=y
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index aa48b6eaff2d..24c44e93804d 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += clkdev.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += hw_irq.h
diff --git a/arch/tile/include/asm/pgtable_32.h b/arch/tile/include/asm/pgtable_32.h
index d26a42279036..5f8c615cb5e9 100644
--- a/arch/tile/include/asm/pgtable_32.h
+++ b/arch/tile/include/asm/pgtable_32.h
@@ -74,6 +74,7 @@ extern unsigned long VMALLOC_RESERVE /* = CONFIG_VMALLOC_RESERVE */;
 #define MAXMEM		(_VMALLOC_START - PAGE_OFFSET)
 
 /* We have no pmd or pud since we are strictly a two-level page table */
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline int pud_huge_page(pud_t pud)	{ return 0; }
diff --git a/arch/tile/include/asm/pgtable_64.h b/arch/tile/include/asm/pgtable_64.h
index e96cec52f6d8..96fe58b45118 100644
--- a/arch/tile/include/asm/pgtable_64.h
+++ b/arch/tile/include/asm/pgtable_64.h
@@ -59,6 +59,7 @@
 #ifndef __ASSEMBLY__
 
 /* We have no pud since we are a three-level page table. */
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /*
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index a77369e91e54..a803f6bb4d92 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -18,15 +18,11 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm-generic/uaccess-unaligned.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 /*
  * The fs value determines whether argument validity checking should be
  * performed or not.  If get_fs() == USER_DS, checking is performed, with
@@ -102,24 +98,7 @@ int __range_ok(unsigned long addr, unsigned long size);
 	likely(__range_ok((unsigned long)(addr), (size)) == 0);	\
 })
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
 
 /*
  * This is a type: either unsigned long, if the argument fits into
@@ -334,145 +313,16 @@ extern int __put_user_bad(void)
 		((x) = 0, -EFAULT);					\
 })
 
-/**
- * __copy_to_user() - copy data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * An alternate version - __copy_to_user_inatomic() - is designed
- * to be called from atomic context, typically bracketed by calls
- * to pagefault_disable() and pagefault_enable().
- */
-extern unsigned long __must_check __copy_to_user_inatomic(
-	void __user *to, const void *from, unsigned long n);
-
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	might_fault();
-	return __copy_to_user_inatomic(to, from, n);
-}
-
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		n = __copy_to_user(to, from, n);
-	return n;
-}
-
-/**
- * __copy_from_user() - copy data from user space, with less checking.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - is designed
- * to be called from atomic context, typically bracketed by calls
- * to pagefault_disable() and pagefault_enable().  This version
- * does *NOT* pad with zeros.
- */
-extern unsigned long __must_check __copy_from_user_inatomic(
-	void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_from_user_zeroing(
-	void *to, const void __user *from, unsigned long n);
-
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-       might_fault();
-       return __copy_from_user_zeroing(to, from, n);
-}
-
-static inline unsigned long __must_check
-_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		n = __copy_from_user(to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
-	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static inline unsigned long __must_check copy_from_user(void *to,
-					  const void __user *from,
-					  unsigned long n)
-{
-	int sz = __compiletime_object_size(to);
-
-	if (likely(sz == -1 || sz >= n))
-		n = _copy_from_user(to, from, n);
-	else if (!__builtin_constant_p(n))
-		copy_user_overflow(sz, n);
-	else
-		__bad_copy_user();
-
-	return n;
-}
+extern unsigned long __must_check
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 #ifdef __tilegx__
-/**
- * __copy_in_user() - copy data within user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to user space.  Caller must check
- * the specified blocks with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-extern unsigned long __copy_in_user_inatomic(
+extern unsigned long raw_copy_in_user(
 	void __user *to, const void __user *from, unsigned long n);
-
-static inline unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-	might_fault();
-	return __copy_in_user_inatomic(to, from, n);
-}
-
-static inline unsigned long __must_check
-copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n))
-		n = __copy_in_user(to, from, n);
-	return n;
-}
 #endif
 
 
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 5bd4e88c7c60..6643ffbc0615 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -155,6 +155,8 @@ static DEFINE_PER_CPU(struct clock_event_device, tile_timer) = {
 	.name = "tile timer",
 	.features = CLOCK_EVT_FEAT_ONESHOT,
 	.min_delta_ns = 1000,
+	.min_delta_ticks = 1,
+	.max_delta_ticks = MAX_TICK,
 	.rating = 100,
 	.irq = -1,
 	.set_next_event = tile_timer_set_next_event,
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index c5369fe643c7..ecce8e177e3f 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -38,11 +38,10 @@ EXPORT_SYMBOL(__mcount);
 
 /* arch/tile/lib/, various memcpy files */
 EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(__copy_to_user_inatomic);
-EXPORT_SYMBOL(__copy_from_user_inatomic);
-EXPORT_SYMBOL(__copy_from_user_zeroing);
+EXPORT_SYMBOL(raw_copy_to_user);
+EXPORT_SYMBOL(raw_copy_from_user);
 #ifdef __tilegx__
-EXPORT_SYMBOL(__copy_in_user_inatomic);
+EXPORT_SYMBOL(raw_copy_in_user);
 #endif
 
 /* hypervisor glue */
diff --git a/arch/tile/lib/memcpy_32.S b/arch/tile/lib/memcpy_32.S
index a2771ae5da53..270f1267cd18 100644
--- a/arch/tile/lib/memcpy_32.S
+++ b/arch/tile/lib/memcpy_32.S
@@ -24,7 +24,6 @@
 
 #define IS_MEMCPY	  0
 #define IS_COPY_FROM_USER  1
-#define IS_COPY_FROM_USER_ZEROING  2
 #define IS_COPY_TO_USER   -1
 
 	.section .text.memcpy_common, "ax"
@@ -42,40 +41,31 @@
 	9
 
 
-/* __copy_from_user_inatomic takes the kernel target address in r0,
+/* raw_copy_from_user takes the kernel target address in r0,
  * the user source in r1, and the bytes to copy in r2.
  * It returns the number of uncopiable bytes (hopefully zero) in r0.
  */
-ENTRY(__copy_from_user_inatomic)
-.type __copy_from_user_inatomic, @function
-	FEEDBACK_ENTER_EXPLICIT(__copy_from_user_inatomic, \
+ENTRY(raw_copy_from_user)
+.type raw_copy_from_user, @function
+	FEEDBACK_ENTER_EXPLICIT(raw_copy_from_user, \
 	  .text.memcpy_common, \
-	  .Lend_memcpy_common - __copy_from_user_inatomic)
+	  .Lend_memcpy_common - raw_copy_from_user)
 	{ movei r29, IS_COPY_FROM_USER; j memcpy_common }
-	.size __copy_from_user_inatomic, . - __copy_from_user_inatomic
+	.size raw_copy_from_user, . - raw_copy_from_user
 
-/* __copy_from_user_zeroing is like __copy_from_user_inatomic, but
- * any uncopiable bytes are zeroed in the target.
- */
-ENTRY(__copy_from_user_zeroing)
-.type __copy_from_user_zeroing, @function
-	FEEDBACK_REENTER(__copy_from_user_inatomic)
-	{ movei r29, IS_COPY_FROM_USER_ZEROING; j memcpy_common }
-	.size __copy_from_user_zeroing, . - __copy_from_user_zeroing
-
-/* __copy_to_user_inatomic takes the user target address in r0,
+/* raw_copy_to_user takes the user target address in r0,
  * the kernel source in r1, and the bytes to copy in r2.
  * It returns the number of uncopiable bytes (hopefully zero) in r0.
  */
-ENTRY(__copy_to_user_inatomic)
-.type __copy_to_user_inatomic, @function
-	FEEDBACK_REENTER(__copy_from_user_inatomic)
+ENTRY(raw_copy_to_user)
+.type raw_copy_to_user, @function
+	FEEDBACK_REENTER(raw_copy_from_user)
 	{ movei r29, IS_COPY_TO_USER; j memcpy_common }
-	.size __copy_to_user_inatomic, . - __copy_to_user_inatomic
+	.size raw_copy_to_user, . - raw_copy_to_user
 
 ENTRY(memcpy)
 .type memcpy, @function
-	FEEDBACK_REENTER(__copy_from_user_inatomic)
+	FEEDBACK_REENTER(raw_copy_from_user)
 	{ movei r29, IS_MEMCPY }
 	.size memcpy, . - memcpy
 	/* Fall through */
@@ -520,12 +510,7 @@ copy_from_user_fixup_loop:
 	{ bnzt r2, copy_from_user_fixup_loop }
 
 .Lcopy_from_user_fixup_zero_remainder:
-	{ bbs r29, 2f }  /* low bit set means IS_COPY_FROM_USER */
-	/* byte-at-a-time loop faulted, so zero the rest. */
-	{ move r3, r2; bz r2, 2f /* should be impossible, but handle it. */ }
-1:      { sb r0, zero; addi r0, r0, 1; addi r3, r3, -1 }
-	{ bnzt r3, 1b }
-2:	move lr, r27
+	move lr, r27
 	{ move r0, r2; jrp lr }
 
 copy_to_user_fixup_loop:
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
index 97bbb6060b25..a3fea9fd973e 100644
--- a/arch/tile/lib/memcpy_user_64.c
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -51,7 +51,7 @@
 		__v;						\
 	})
 
-#define USERCOPY_FUNC __copy_to_user_inatomic
+#define USERCOPY_FUNC raw_copy_to_user
 #define ST1(p, v) _ST((p), st1, (v))
 #define ST2(p, v) _ST((p), st2, (v))
 #define ST4(p, v) _ST((p), st4, (v))
@@ -62,7 +62,7 @@
 #define LD8 LD
 #include "memcpy_64.c"
 
-#define USERCOPY_FUNC __copy_from_user_inatomic
+#define USERCOPY_FUNC raw_copy_from_user
 #define ST1 ST
 #define ST2 ST
 #define ST4 ST
@@ -73,7 +73,7 @@
 #define LD8(p) _LD((p), ld)
 #include "memcpy_64.c"
 
-#define USERCOPY_FUNC __copy_in_user_inatomic
+#define USERCOPY_FUNC raw_copy_in_user
 #define ST1(p, v) _ST((p), st1, (v))
 #define ST2(p, v) _ST((p), st2, (v))
 #define ST4(p, v) _ST((p), st4, (v))
@@ -83,12 +83,3 @@
 #define LD4(p) _LD((p), ld4u)
 #define LD8(p) _LD((p), ld)
 #include "memcpy_64.c"
-
-unsigned long __copy_from_user_zeroing(void *to, const void __user *from,
-				       unsigned long n)
-{
-	unsigned long rc = __copy_from_user_inatomic(to, from, n);
-	if (unlikely(rc))
-		memset(to + n - rc, 0, rc);
-	return rc;
-}
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index fd443852103c..ed9c5b5ff028 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -50,11 +50,6 @@ config GENERIC_CALIBRATE_DELAY
 	bool
 	default y
 
-config GENERIC_BUG
-	bool
-	default y
-	depends on BUG
-
 config HZ
 	int
 	default 100
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index e9d42aab76dc..50a32c33d729 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += delay.h
 generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 94ac2739918c..b668e351fd6c 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -37,12 +37,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	return true;
 }
 
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
-	/* by default, allow everything */
-	return true;
-}
-
 /*
  * end asm-generic/mm_hooks.h functions
  */
diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h
index cfbe59752469..179c0ea87a0c 100644
--- a/arch/um/include/asm/pgtable-2level.h
+++ b/arch/um/include/asm/pgtable-2level.h
@@ -8,6 +8,7 @@
 #ifndef __UM_PGTABLE_2LEVEL_H
 #define __UM_PGTABLE_2LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* PGDIR_SHIFT determines what a third-level page table entry can map */
diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h
index bae8523a162f..c4d876dfb9ac 100644
--- a/arch/um/include/asm/pgtable-3level.h
+++ b/arch/um/include/asm/pgtable-3level.h
@@ -7,6 +7,7 @@
 #ifndef __UM_PGTABLE_3LEVEL_H
 #define __UM_PGTABLE_3LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /* PGDIR_SHIFT determines what a third-level page table entry can map */
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index 3705620ca298..cc00fc50768f 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -7,7 +7,6 @@
 #ifndef __UM_UACCESS_H
 #define __UM_UACCESS_H
 
-#include <asm/thread_info.h>
 #include <asm/elf.h>
 
 #define __under_task_size(addr, size) \
@@ -22,8 +21,8 @@
 #define __addr_range_nowrap(addr, size) \
 	((unsigned long) (addr) <= ((unsigned long) (addr) + (size)))
 
-extern long __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+extern unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 extern long __strncpy_from_user(char *dst, const char __user *src, long count);
 extern long __strnlen_user(const void __user *str, long len);
 extern unsigned long __clear_user(void __user *mem, unsigned long len);
@@ -32,12 +31,10 @@ static inline int __access_ok(unsigned long addr, unsigned long size);
 /* Teach asm-generic/uaccess.h that we have C functions for these. */
 #define __access_ok __access_ok
 #define __clear_user __clear_user
-#define __copy_to_user __copy_to_user
-#define __copy_from_user __copy_from_user
 #define __strnlen_user __strnlen_user
 #define __strncpy_from_user __strncpy_from_user
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 #include <asm-generic/uaccess.h>
 
@@ -46,7 +43,7 @@ static inline int __access_ok(unsigned long addr, unsigned long size)
 	return __addr_range_nowrap(addr, size) &&
 		(__under_task_size(addr, size) ||
 		__access_ok_vsyscall(addr, size) ||
-		segment_eq(get_fs(), KERNEL_DS));
+		uaccess_kernel());
 }
 
 #endif
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index de5d572225f3..cd1fa97776c3 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -302,8 +302,8 @@ extern int ignore_sigio_fd(int fd);
 extern void maybe_sigio_broken(int fd, int read);
 extern void sigio_broken(int fd, int read);
 
-/* sys-x86_64/prctl.c */
-extern int os_arch_prctl(int pid, int code, unsigned long *addr);
+/* prctl.c */
+extern int os_arch_prctl(int pid, int option, unsigned long *arg2);
 
 /* tty.c */
 extern int get_pty(void);
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index 85ac8adb069b..d450797a3a7c 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -139,16 +139,16 @@ static int copy_chunk_from_user(unsigned long from, int len, void *arg)
 	return 0;
 }
 
-long __copy_from_user(void *to, const void __user *from, unsigned long n)
+unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (uaccess_kernel()) {
 		memcpy(to, (__force void*)from, n);
 		return 0;
 	}
 
 	return buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to);
 }
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
 
 static int copy_chunk_to_user(unsigned long to, int len, void *arg)
 {
@@ -159,16 +159,16 @@ static int copy_chunk_to_user(unsigned long to, int len, void *arg)
 	return 0;
 }
 
-long __copy_to_user(void __user *to, const void *from, unsigned long n)
+unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (uaccess_kernel()) {
 		memcpy((__force void *) to, from, n);
 		return 0;
 	}
 
 	return buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from);
 }
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 
 static int strncpy_chunk_from_user(unsigned long from, int len, void *arg)
 {
@@ -189,7 +189,7 @@ long __strncpy_from_user(char *dst, const char __user *src, long count)
 	long n;
 	char *ptr = dst;
 
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (uaccess_kernel()) {
 		strncpy(dst, (__force void *) src, count);
 		return strnlen(dst, count);
 	}
@@ -210,7 +210,7 @@ static int clear_chunk(unsigned long addr, int len, void *unused)
 
 unsigned long __clear_user(void __user *mem, unsigned long len)
 {
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (uaccess_kernel()) {
 		memset((__force void*)mem, 0, len);
 		return 0;
 	}
@@ -235,7 +235,7 @@ long __strnlen_user(const void __user *str, long len)
 {
 	int count = 0, n;
 
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (uaccess_kernel())
 		return strnlen((__force char*)str, len) + 1;
 
 	n = buffer_op((unsigned long) str, len, 0, strnlen_chunk, &count);
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index ba87a27d6715..0b034ebbda2a 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -65,7 +65,9 @@ static struct clock_event_device timer_clockevent = {
 	.set_next_event		= itimer_next_event,
 	.shift			= 0,
 	.max_delta_ns		= 0xffffffff,
-	.min_delta_ns		= TIMER_MIN_DELTA, //microsecond resolution should be enough for anyone, same as 640K RAM
+	.max_delta_ticks	= 0xffffffff,
+	.min_delta_ns		= TIMER_MIN_DELTA,
+	.min_delta_ticks	= TIMER_MIN_DELTA, // microsecond resolution should be enough for anyone, same as 640K RAM
 	.irq			= 0,
 	.mult			= 1,
 };
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 84205fe1cd79..e9ad511c1043 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 62dfc644c908..59b06b48f27d 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -103,10 +103,4 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	/* by default, allow everything */
 	return true;
 }
-
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
-	/* by default, allow everything */
-	return true;
-}
 #endif
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
index 818d0f5598e3..a4f2bef37e70 100644
--- a/arch/unicore32/include/asm/pgtable.h
+++ b/arch/unicore32/include/asm/pgtable.h
@@ -12,6 +12,7 @@
 #ifndef __UNICORE_PGTABLE_H__
 #define __UNICORE_PGTABLE_H__
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/cpu-single.h>
 
diff --git a/arch/unicore32/include/asm/uaccess.h b/arch/unicore32/include/asm/uaccess.h
index 897e11ad8124..1d55f2f83759 100644
--- a/arch/unicore32/include/asm/uaccess.h
+++ b/arch/unicore32/include/asm/uaccess.h
@@ -12,35 +12,30 @@
 #ifndef __UNICORE_UACCESS_H__
 #define __UNICORE_UACCESS_H__
 
-#include <linux/thread_info.h>
-#include <linux/errno.h>
-
 #include <asm/memory.h>
 
-#define __copy_from_user	__copy_from_user
-#define __copy_to_user		__copy_to_user
 #define __strncpy_from_user	__strncpy_from_user
 #define __strnlen_user		__strnlen_user
 #define __clear_user		__clear_user
 
-#define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok		(uaccess_kernel())
 #define __user_ok(addr, size)	(((size) <= TASK_SIZE)			\
 				&& ((addr) <= TASK_SIZE - (size)))
 #define __access_ok(addr, size)	(__kernel_ok || __user_ok((addr), (size)))
 
 extern unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n);
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
 extern unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n);
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 extern unsigned long __must_check
 __clear_user(void __user *addr, unsigned long n);
 extern unsigned long __must_check
 __strncpy_from_user(char *to, const char __user *from, unsigned long count);
 extern unsigned long
 __strnlen_user(const char __user *s, long n);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 #include <asm-generic/uaccess.h>
 
-extern int fixup_exception(struct pt_regs *regs);
-
 #endif /* __UNICORE_UACCESS_H__ */
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index 0323528a80fd..dcc72ee1fcdb 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -46,8 +46,8 @@ EXPORT_SYMBOL(__strncpy_from_user);
 
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_from_user);
+EXPORT_SYMBOL(raw_copy_to_user);
 EXPORT_SYMBOL(__clear_user);
 
 EXPORT_SYMBOL(__ashldi3);
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index d22c1dc7e39e..ddaf78ae6854 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -178,7 +178,7 @@ void __show_regs(struct pt_regs *regs)
 		buf, interrupts_enabled(regs) ? "n" : "ff",
 		fast_interrupts_enabled(regs) ? "n" : "ff",
 		processor_modes[processor_mode(regs)],
-		segment_eq(get_fs(), get_ds()) ? "kernel" : "user");
+		uaccess_kernel() ? "kernel" : "user");
 	{
 		unsigned int ctrl;
 
diff --git a/arch/unicore32/kernel/time.c b/arch/unicore32/kernel/time.c
index fceaa673f861..c6b3fa3ee0b6 100644
--- a/arch/unicore32/kernel/time.c
+++ b/arch/unicore32/kernel/time.c
@@ -91,8 +91,10 @@ void __init time_init(void)
 
 	ckevt_puv3_osmr0.max_delta_ns =
 		clockevent_delta2ns(0x7fffffff, &ckevt_puv3_osmr0);
+	ckevt_puv3_osmr0.max_delta_ticks = 0x7fffffff;
 	ckevt_puv3_osmr0.min_delta_ns =
 		clockevent_delta2ns(MIN_OSCR_DELTA * 2, &ckevt_puv3_osmr0) + 1;
+	ckevt_puv3_osmr0.min_delta_ticks = MIN_OSCR_DELTA * 2;
 	ckevt_puv3_osmr0.cpumask = cpumask_of(0);
 
 	setup_irq(IRQ_TIMER0, &puv3_timer_irq);
diff --git a/arch/unicore32/lib/copy_from_user.S b/arch/unicore32/lib/copy_from_user.S
index ab0767ea5dbd..5f80fcbe8631 100644
--- a/arch/unicore32/lib/copy_from_user.S
+++ b/arch/unicore32/lib/copy_from_user.S
@@ -16,7 +16,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_from_user(void *to, const void *from, size_t n)
+ *	size_t raw_copy_from_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -87,22 +87,18 @@
 
 	.text
 
-ENTRY(__copy_from_user)
+ENTRY(raw_copy_from_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_from_user)
+ENDPROC(raw_copy_from_user)
 
 	.pushsection .fixup,"ax"
 	.align 0
 	copy_abort_preamble
-	ldm.w	(r1, r2), [sp]+
-	sub	r3, r0, r1
-	rsub	r2, r3, r2
-	stw	r2, [sp]
-	mov	r1, #0
-	b.l	memset
-	ldw.w	r0, [sp]+, #4
+	ldm.w	(r1, r2, r3), [sp]+
+	sub	r0, r0, r1
+	rsub	r0, r0, r2
 	copy_abort_end
 	.popsection
 
diff --git a/arch/unicore32/lib/copy_to_user.S b/arch/unicore32/lib/copy_to_user.S
index 6e22151c840d..857c6816ffe7 100644
--- a/arch/unicore32/lib/copy_to_user.S
+++ b/arch/unicore32/lib/copy_to_user.S
@@ -16,7 +16,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_to_user(void *to, const void *from, size_t n)
+ *	size_t raw_copy_to_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -79,11 +79,11 @@
 
 	.text
 
-WEAK(__copy_to_user)
+WEAK(raw_copy_to_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_to_user)
+ENDPROC(raw_copy_to_user)
 
 	.pushsection .fixup,"ax"
 	.align 0
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2a26852c11b6..cd18994a9555 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -98,7 +98,6 @@ config X86
 	select HAVE_ACPI_APEI_NMI		if ACPI
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if X86_64 && SPARSEMEM_VMEMMAP
@@ -106,6 +105,7 @@ config X86
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT
+	select HAVE_ARCH_COMPAT_MMAP_BASES	if MMU && COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
@@ -127,7 +127,7 @@ config X86
 	select HAVE_EBPF_JIT			if X86_64
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_EXIT_THREAD
-	select HAVE_FENTRY			if X86_64
+	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
@@ -291,6 +291,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
+	default 0xdff8000000000000 if X86_5LEVEL
 	default 0xdffffc0000000000
 
 config HAVE_INTEL_TXT
@@ -1044,6 +1045,14 @@ config X86_MCE
 	  The action the kernel takes depends on the severity of the problem,
 	  ranging from warning messages to halting the machine.
 
+config X86_MCELOG_LEGACY
+	bool "Support for deprecated /dev/mcelog character device"
+	depends on X86_MCE
+	---help---
+	  Enable support for /dev/mcelog which is needed by the old mcelog
+	  userspace logging daemon. Consider switching to the new generation
+	  rasdaemon solution.
+
 config X86_MCE_INTEL
 	def_bool y
 	prompt "Intel MCE features"
@@ -1073,7 +1082,7 @@ config X86_MCE_THRESHOLD
 	def_bool y
 
 config X86_MCE_INJECT
-	depends on X86_MCE && X86_LOCAL_APIC
+	depends on X86_MCE && X86_LOCAL_APIC && X86_MCELOG_LEGACY
 	tristate "Machine check injector support"
 	---help---
 	  Provide support for injecting machine checks for testing purposes.
@@ -1967,7 +1976,7 @@ config RELOCATABLE
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image (KASLR)"
 	depends on RELOCATABLE
-	default n
+	default y
 	---help---
 	  In support of Kernel Address Space Layout Randomization (KASLR),
 	  this randomizes the physical address at which the kernel image
@@ -1997,7 +2006,7 @@ config RANDOMIZE_BASE
 	  theoretically possible, but the implementations are further
 	  limited due to memory layouts.
 
-	  If unsure, say N.
+	  If unsure, say Y.
 
 # Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
@@ -2046,7 +2055,7 @@ config RANDOMIZE_MEMORY
 	   configuration have in average 30,000 different possible virtual
 	   addresses for each memory section.
 
-	   If unsure, say N.
+	   If unsure, say Y.
 
 config RANDOMIZE_MEMORY_PHYSICAL_PADDING
 	hex "Physical memory mapping padding" if EXPERT
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 63c1d13aaf9f..fcb7604172ce 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -5,6 +5,9 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
+config EARLY_PRINTK_USB
+	bool
+
 config X86_VERBOSE_BOOTUP
 	bool "Enable verbose x86 bootup info messages"
 	default y
@@ -23,19 +26,20 @@ config EARLY_PRINTK
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized. For normal operation
 	  it is not recommended because it looks ugly and doesn't cooperate
-	  with klogd/syslogd or the X server. You should normally N here,
+	  with klogd/syslogd or the X server. You should normally say N here,
 	  unless you want to debug such a crash.
 
 config EARLY_PRINTK_DBGP
 	bool "Early printk via EHCI debug port"
 	depends on EARLY_PRINTK && PCI
+	select EARLY_PRINTK_USB
 	---help---
 	  Write kernel log output directly into the EHCI debug port.
 
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized. For normal operation
 	  it is not recommended because it looks ugly and doesn't cooperate
-	  with klogd/syslogd or the X server. You should normally N here,
+	  with klogd/syslogd or the X server. You should normally say N here,
 	  unless you want to debug such a crash. You need usb debug device.
 
 config EARLY_PRINTK_EFI
@@ -48,6 +52,25 @@ config EARLY_PRINTK_EFI
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized.
 
+config EARLY_PRINTK_USB_XDBC
+	bool "Early printk via the xHCI debug port"
+	depends on EARLY_PRINTK && PCI
+	select EARLY_PRINTK_USB
+	---help---
+	  Write kernel log output directly into the xHCI debug port.
+
+	  One use for this feature is kernel debugging, for example when your
+	  machine crashes very early before the regular console code is
+	  initialized. Other uses include simpler, lockless logging instead of
+	  a full-blown printk console driver + klogd.
+
+	  For normal production environments this is normally not recommended,
+	  because it doesn't feed events into klogd/syslogd and doesn't try to
+	  print anything on the screen.
+
+	  You should normally say N here, unless you want to debug early
+	  crashes or need a very simple printk logging facility.
+
 config X86_PTDUMP_CORE
 	def_bool n
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d449337a360..4430dd489620 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -88,10 +88,10 @@ else
         KBUILD_CFLAGS += -m64
 
         # Align jump targets to 1 byte, not the default 16 bytes:
-        KBUILD_CFLAGS += -falign-jumps=1
+        KBUILD_CFLAGS += $(call cc-option,-falign-jumps=1)
 
         # Pack loops tightly as well:
-        KBUILD_CFLAGS += -falign-loops=1
+        KBUILD_CFLAGS += $(call cc-option,-falign-loops=1)
 
         # Don't autogenerate traditional x87 instructions
         KBUILD_CFLAGS += $(call cc-option,-mno-80387)
@@ -120,10 +120,6 @@ else
         # -funit-at-a-time shrinks the kernel .text considerably
         # unfortunately it makes reading oopses harder.
         KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
-        # this works around some issues with generating unwind tables in older gccs
-        # newer gccs do it by default
-        KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
 endif
 
 ifdef CONFIG_X86_X32
@@ -147,6 +143,45 @@ ifeq ($(CONFIG_KMEMCHECK),y)
 	KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
 endif
 
+#
+# If the function graph tracer is used with mcount instead of fentry,
+# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109)
+#
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
+  ifndef CONFIG_HAVE_FENTRY
+	ACCUMULATE_OUTGOING_ARGS := 1
+  else
+    ifeq ($(call cc-option-yn, -mfentry), n)
+	ACCUMULATE_OUTGOING_ARGS := 1
+
+	# GCC ignores '-maccumulate-outgoing-args' when used with '-Os'.
+	# If '-Os' is enabled, disable it and print a warning.
+        ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
+          undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
+	  $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE.  Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
+        endif
+
+    endif
+  endif
+endif
+
+#
+# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
+# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226).  There's no way
+# to test for this bug at compile-time because the test case needs to execute,
+# which is a no-go for cross compilers.  So check the GCC version instead.
+#
+ifdef CONFIG_JUMP_LABEL
+  ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+	ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
+  endif
+endif
+
+ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+	KBUILD_CFLAGS += -maccumulate-outgoing-args
+endif
+
 # Stackpointer is addressed different for 32 bit and 64 bit x86
 sp-$(CONFIG_X86_32) := esp
 sp-$(CONFIG_X86_64) := rsp
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 6647ed49c66c..a45eb15b7cf2 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -45,24 +45,6 @@ cflags-$(CONFIG_MGEODE_LX)	+= $(call cc-option,-march=geode,-march=pentium-mmx)
 # cpu entries
 cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 
-# Work around the pentium-mmx code generator madness of gcc4.4.x which
-# does stack alignment by generating horrible code _before_ the mcount
-# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
-# tracer assumptions. For i686, generic, core2 this is set by the
-# compiler anyway
-ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-# Work around to a bug with asm goto with first implementations of it
-# in gcc causing gcc to mess up the push and pop of the stack in some
-# uses of asm goto.
-ifeq ($(CONFIG_JUMP_LABEL), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
-
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.
 ifneq ($(CONFIG_X86_P6_NOP),y)
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 9b42b6d1e902..ef5a9cc66fb8 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -16,7 +16,7 @@
 #ifndef BOOT_BOOT_H
 #define BOOT_BOOT_H
 
-#define STACK_SIZE	512	/* Minimum number of bytes for stack */
+#define STACK_SIZE	1024	/* Minimum number of bytes for stack */
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 801c7a158e55..cbf4b87f55b9 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -9,7 +9,9 @@
 
 #include <linux/efi.h>
 #include <linux/pci.h>
+
 #include <asm/efi.h>
+#include <asm/e820/types.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
 
@@ -729,7 +731,7 @@ static void add_e820ext(struct boot_params *params,
 	unsigned long size;
 
 	e820ext->type = SETUP_E820_EXT;
-	e820ext->len = nr_entries * sizeof(struct e820entry);
+	e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
 	e820ext->next = 0;
 
 	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
@@ -746,9 +748,9 @@ static void add_e820ext(struct boot_params *params,
 static efi_status_t setup_e820(struct boot_params *params,
 			       struct setup_data *e820ext, u32 e820ext_size)
 {
-	struct e820entry *e820_map = &params->e820_map[0];
+	struct boot_e820_entry *entry = params->e820_table;
 	struct efi_info *efi = &params->efi_info;
-	struct e820entry *prev = NULL;
+	struct boot_e820_entry *prev = NULL;
 	u32 nr_entries;
 	u32 nr_desc;
 	int i;
@@ -773,15 +775,15 @@ static efi_status_t setup_e820(struct boot_params *params,
 		case EFI_MEMORY_MAPPED_IO:
 		case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
 		case EFI_PAL_CODE:
-			e820_type = E820_RESERVED;
+			e820_type = E820_TYPE_RESERVED;
 			break;
 
 		case EFI_UNUSABLE_MEMORY:
-			e820_type = E820_UNUSABLE;
+			e820_type = E820_TYPE_UNUSABLE;
 			break;
 
 		case EFI_ACPI_RECLAIM_MEMORY:
-			e820_type = E820_ACPI;
+			e820_type = E820_TYPE_ACPI;
 			break;
 
 		case EFI_LOADER_CODE:
@@ -789,15 +791,15 @@ static efi_status_t setup_e820(struct boot_params *params,
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			e820_type = E820_RAM;
+			e820_type = E820_TYPE_RAM;
 			break;
 
 		case EFI_ACPI_MEMORY_NVS:
-			e820_type = E820_NVS;
+			e820_type = E820_TYPE_NVS;
 			break;
 
 		case EFI_PERSISTENT_MEMORY:
-			e820_type = E820_PMEM;
+			e820_type = E820_TYPE_PMEM;
 			break;
 
 		default:
@@ -811,26 +813,26 @@ static efi_status_t setup_e820(struct boot_params *params,
 			continue;
 		}
 
-		if (nr_entries == ARRAY_SIZE(params->e820_map)) {
-			u32 need = (nr_desc - i) * sizeof(struct e820entry) +
+		if (nr_entries == ARRAY_SIZE(params->e820_table)) {
+			u32 need = (nr_desc - i) * sizeof(struct e820_entry) +
 				   sizeof(struct setup_data);
 
 			if (!e820ext || e820ext_size < need)
 				return EFI_BUFFER_TOO_SMALL;
 
 			/* boot_params map full, switch to e820 extended */
-			e820_map = (struct e820entry *)e820ext->data;
+			entry = (struct boot_e820_entry *)e820ext->data;
 		}
 
-		e820_map->addr = d->phys_addr;
-		e820_map->size = d->num_pages << PAGE_SHIFT;
-		e820_map->type = e820_type;
-		prev = e820_map++;
+		entry->addr = d->phys_addr;
+		entry->size = d->num_pages << PAGE_SHIFT;
+		entry->type = e820_type;
+		prev = entry++;
 		nr_entries++;
 	}
 
-	if (nr_entries > ARRAY_SIZE(params->e820_map)) {
-		u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map);
+	if (nr_entries > ARRAY_SIZE(params->e820_table)) {
+		u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_table);
 
 		add_e820ext(params, e820ext, nr_e820ext);
 		nr_entries -= nr_e820ext;
@@ -848,7 +850,7 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 	unsigned long size;
 
 	size = sizeof(struct setup_data) +
-		sizeof(struct e820entry) * nr_desc;
+		sizeof(struct e820_entry) * nr_desc;
 
 	if (*e820ext) {
 		efi_call_early(free_pool, *e820ext);
@@ -884,9 +886,9 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 
 	if (first) {
 		nr_desc = *map->buff_size / *map->desc_size;
-		if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+		if (nr_desc > ARRAY_SIZE(p->boot_params->e820_table)) {
 			u32 nr_e820ext = nr_desc -
-					ARRAY_SIZE(p->boot_params->e820_map);
+					ARRAY_SIZE(p->boot_params->e820_table);
 
 			status = alloc_e820ext(nr_e820ext, &p->e820ext,
 					       &p->e820ext_size);
diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c
index 6248740b68b5..31922023de49 100644
--- a/arch/x86/boot/compressed/error.c
+++ b/arch/x86/boot/compressed/error.c
@@ -4,6 +4,7 @@
  * memcpy() and memmove() are defined for the compressed boot environment.
  */
 #include "misc.h"
+#include "error.h"
 
 void warn(char *m)
 {
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 8b7c9e75edcb..54c24f0a43d3 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -426,7 +426,7 @@ static unsigned long slots_fetch_random(void)
 	return 0;
 }
 
-static void process_e820_entry(struct e820entry *entry,
+static void process_e820_entry(struct boot_e820_entry *entry,
 			       unsigned long minimum,
 			       unsigned long image_size)
 {
@@ -435,7 +435,7 @@ static void process_e820_entry(struct e820entry *entry,
 	unsigned long start_orig;
 
 	/* Skip non-RAM entries. */
-	if (entry->type != E820_RAM)
+	if (entry->type != E820_TYPE_RAM)
 		return;
 
 	/* On 32-bit, ignore entries entirely above our maximum. */
@@ -518,7 +518,7 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
 
 	/* Verify potential e820 positions, appending to slots list. */
 	for (i = 0; i < boot_params->e820_entries; i++) {
-		process_e820_entry(&boot_params->e820_map[i], minimum,
+		process_e820_entry(&boot_params->e820_table[i], minimum,
 				   image_size);
 		if (slot_area_index == MAX_SLOT_AREA) {
 			debug_putstr("Aborted e820 scan (slot_areas full)!\n");
@@ -597,10 +597,17 @@ void choose_random_location(unsigned long input,
 			add_identity_map(random_addr, output_size);
 			*output = random_addr;
 		}
+
+		/*
+		 * This loads the identity mapping page table.
+		 * This should only be done if a new physical address
+		 * is found for the kernel, otherwise we should keep
+		 * the old page table to make it be like the "nokaslr"
+		 * case.
+		 */
+		finalize_identity_maps();
 	}
 
-	/* This actually loads the identity pagetable on x86_64. */
-	finalize_identity_maps();
 
 	/* Pick random virtual address starting from LOAD_PHYSICAL_ADDR. */
 	if (IS_ENABLED(CONFIG_X86_64))
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 4ad7d70e8739..8f0c4c9fc904 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -44,6 +44,15 @@ static const u32 req_flags[NCAPINTS] =
 	0, /* REQUIRED_MASK5 not implemented in this file */
 	REQUIRED_MASK6,
 	0, /* REQUIRED_MASK7 not implemented in this file */
+	0, /* REQUIRED_MASK8 not implemented in this file */
+	0, /* REQUIRED_MASK9 not implemented in this file */
+	0, /* REQUIRED_MASK10 not implemented in this file */
+	0, /* REQUIRED_MASK11 not implemented in this file */
+	0, /* REQUIRED_MASK12 not implemented in this file */
+	0, /* REQUIRED_MASK13 not implemented in this file */
+	0, /* REQUIRED_MASK14 not implemented in this file */
+	0, /* REQUIRED_MASK15 not implemented in this file */
+	REQUIRED_MASK16,
 };
 
 #define A32(a, b, c, d) (((d) << 24)+((c) << 16)+((b) << 8)+(a))
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index 6687ab953257..9e77c23c2422 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -70,16 +70,19 @@ int has_eflag(unsigned long mask)
 # define EBX_REG "=b"
 #endif
 
-static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
+static inline void cpuid_count(u32 id, u32 count,
+		u32 *a, u32 *b, u32 *c, u32 *d)
 {
 	asm volatile(".ifnc %%ebx,%3 ; movl  %%ebx,%3 ; .endif	\n\t"
 		     "cpuid					\n\t"
 		     ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif	\n\t"
 		    : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b)
-		    : "a" (id)
+		    : "a" (id), "c" (count)
 	);
 }
 
+#define cpuid(id, a, b, c, d) cpuid_count(id, 0, a, b, c, d)
+
 void get_cpuflags(void)
 {
 	u32 max_intel_level, max_amd_level;
@@ -108,6 +111,11 @@ void get_cpuflags(void)
 				cpu.model += ((tfms >> 16) & 0xf) << 4;
 		}
 
+		if (max_intel_level >= 0x00000007) {
+			cpuid_count(0x00000007, 0, &ignored, &ignored,
+					&cpu.flags[16], &ignored);
+		}
+
 		cpuid(0x80000000, &max_amd_level, &ignored, &ignored,
 		      &ignored);
 
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 3dd5be33aaa7..2ed8f0c25def 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -18,7 +18,6 @@
 #include <asm/segment.h>
 #include <generated/utsrelease.h>
 #include <asm/boot.h>
-#include <asm/e820.h>
 #include <asm/page_types.h>
 #include <asm/setup.h>
 #include <asm/bootparam.h>
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index db75d07c3645..d9c28c87e477 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -21,8 +21,8 @@ static int detect_memory_e820(void)
 {
 	int count = 0;
 	struct biosregs ireg, oreg;
-	struct e820entry *desc = boot_params.e820_map;
-	static struct e820entry buf; /* static so it is zeroed */
+	struct boot_e820_entry *desc = boot_params.e820_table;
+	static struct boot_e820_entry buf; /* static so it is zeroed */
 
 	initregs(&ireg);
 	ireg.ax  = 0xe820;
@@ -66,7 +66,7 @@ static int detect_memory_e820(void)
 
 		*desc++ = buf;
 		count++;
-	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
+	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_table));
 
 	return boot_params.e820_entries = count;
 }
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 5fa6ee2c2dde..6cf79e1a6830 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -57,6 +57,8 @@ CONFIG_EFI=y
 CONFIG_HZ_1000=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_RANDOMIZE_MEMORY=y
 # CONFIG_COMPAT_VDSO is not set
 CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 7ef4a099defc..de45f57b410d 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -55,6 +55,8 @@ CONFIG_EFI=y
 CONFIG_HZ_1000=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_RANDOMIZE_MEMORY=y
 # CONFIG_COMPAT_VDSO is not set
 CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
@@ -176,6 +178,7 @@ CONFIG_E1000E=y
 CONFIG_SKY2=y
 CONFIG_FORCEDETH=y
 CONFIG_8139TOO=y
+CONFIG_R8169=y
 CONFIG_FDDI=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index a916c4a61165..5f6a5af9c489 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -65,7 +65,6 @@
 #include <linux/linkage.h>
 #include <asm/inst.h>
 
-#define CONCAT(a,b)	a##b
 #define VMOVDQ		vmovdqu
 
 #define xdata0		%xmm0
@@ -92,8 +91,6 @@
 #define num_bytes	%r8
 
 #define tmp		%r10
-#define	DDQ(i)		CONCAT(ddq_add_,i)
-#define	XMM(i)		CONCAT(%xmm, i)
 #define	DDQ_DATA	0
 #define	XDATA		1
 #define KEY_128		1
@@ -131,12 +128,12 @@ ddq_add_8:
 /* generate a unique variable for ddq_add_x */
 
 .macro setddq n
-	var_ddq_add = DDQ(\n)
+	var_ddq_add = ddq_add_\n
 .endm
 
 /* generate a unique variable for xmm register */
 .macro setxdata n
-	var_xdata = XMM(\n)
+	var_xdata = %xmm\n
 .endm
 
 /* club the numeric 'id' to the symbol 'name' */
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index aa76cad9d262..af4840ab2a3d 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1522,7 +1522,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
 	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[2 * 4];
+	le128 buf[2 * 4];
 	struct xts_crypt_req req = {
 		.tbuf = buf,
 		.tbuflen = sizeof(buf),
@@ -1540,7 +1540,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
 	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[2 * 4];
+	le128 buf[2 * 4];
 	struct xts_crypt_req req = {
 		.tbuf = buf,
 		.tbuflen = sizeof(buf),
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index 260a060d7275..24ac9fad832d 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -27,6 +27,7 @@
 
 #include <linux/module.h>
 #include <crypto/b128ops.h>
+#include <crypto/gf128mul.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
@@ -457,7 +458,7 @@ void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src, le128 *iv,
 	le128 ivblk = *iv;
 
 	/* generate next IV */
-	le128_gf128mul_x_ble(iv, &ivblk);
+	gf128mul_x_ble(iv, &ivblk);
 
 	/* CC <- T xor C */
 	u128_xor(dst, src, (u128 *)&ivblk);
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 644f97ab8cac..ac0e831943f5 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -328,7 +328,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
 	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_PARALLEL_BLOCKS];
+	le128 buf[SERPENT_PARALLEL_BLOCKS];
 	struct crypt_priv crypt_ctx = {
 		.ctx = &ctx->crypt_ctx,
 		.fpu_enabled = false,
@@ -355,7 +355,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
 	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_PARALLEL_BLOCKS];
+	le128 buf[SERPENT_PARALLEL_BLOCKS];
 	struct crypt_priv crypt_ctx = {
 		.ctx = &ctx->crypt_ctx,
 		.fpu_enabled = false,
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 2ebb5e9789f3..243e90a4b5d9 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -296,7 +296,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
 	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[3];
+	le128 buf[3];
 	struct xts_crypt_req req = {
 		.tbuf = buf,
 		.tbuflen = sizeof(buf),
@@ -314,7 +314,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
 	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[3];
+	le128 buf[3];
 	struct xts_crypt_req req = {
 		.tbuf = buf,
 		.tbuflen = sizeof(buf),
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 57f7ec35216e..50bc26949e9e 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -35,16 +35,13 @@
 #include <asm/errno.h>
 #include <asm/segment.h>
 #include <asm/smp.h>
-#include <asm/page_types.h>
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
-#include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
-#include <asm/export.h>
 #include <asm/frame.h>
 
 	.section .entry.text, "ax"
@@ -585,7 +582,7 @@ ENTRY(iret_exc	)
 	 * will soon execute iret and the tracer was already set to
 	 * the irqstate after the IRET:
 	 */
-	DISABLE_INTERRUPTS(CLBR_EAX)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	lss	(%esp), %esp			/* switch to espfix segment */
 	jmp	.Lrestore_nocheck
 #endif
@@ -886,172 +883,6 @@ BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
 
 #endif /* CONFIG_HYPERV */
 
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
-	ret
-END(mcount)
-
-ENTRY(ftrace_caller)
-	pushl	%eax
-	pushl	%ecx
-	pushl	%edx
-	pushl	$0				/* Pass NULL as regs pointer */
-	movl	4*4(%esp), %eax
-	movl	0x4(%ebp), %edx
-	movl	function_trace_op, %ecx
-	subl	$MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
-	call	ftrace_stub
-
-	addl	$4, %esp			/* skip NULL pointer */
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-.Lftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
-	jmp	ftrace_stub
-#endif
-
-/* This is weak to keep gas from relaxing the jumps */
-WEAK(ftrace_stub)
-	ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
-	pushf	/* push flags before compare (in cs location) */
-
-	/*
-	 * i386 does not save SS and ESP when coming from kernel.
-	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
-	 * Unfortunately, that means eflags must be at the same location
-	 * as the current return ip is. We move the return ip into the
-	 * ip location, and move flags into the return ip location.
-	 */
-	pushl	4(%esp)				/* save return ip into ip slot */
-
-	pushl	$0				/* Load 0 into orig_ax */
-	pushl	%gs
-	pushl	%fs
-	pushl	%es
-	pushl	%ds
-	pushl	%eax
-	pushl	%ebp
-	pushl	%edi
-	pushl	%esi
-	pushl	%edx
-	pushl	%ecx
-	pushl	%ebx
-
-	movl	13*4(%esp), %eax		/* Get the saved flags */
-	movl	%eax, 14*4(%esp)		/* Move saved flags into regs->flags location */
-						/* clobbering return ip */
-	movl	$__KERNEL_CS, 13*4(%esp)
-
-	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
-	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
-	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
-	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
-	pushl	%esp				/* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
-	call	ftrace_stub
-
-	addl	$4, %esp			/* Skip pt_regs */
-	movl	14*4(%esp), %eax		/* Move flags back into cs */
-	movl	%eax, 13*4(%esp)		/* Needed to keep addl	from modifying flags */
-	movl	12*4(%esp), %eax		/* Get return ip from regs->ip */
-	movl	%eax, 14*4(%esp)		/* Put return ip back for ret */
-
-	popl	%ebx
-	popl	%ecx
-	popl	%edx
-	popl	%esi
-	popl	%edi
-	popl	%ebp
-	popl	%eax
-	popl	%ds
-	popl	%es
-	popl	%fs
-	popl	%gs
-	addl	$8, %esp			/* Skip orig_ax and ip */
-	popf					/* Pop flags at end (no addl to corrupt flags) */
-	jmp	.Lftrace_ret
-
-	popf
-	jmp	ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
-	cmpl	$__PAGE_OFFSET, %esp
-	jb	ftrace_stub			/* Paging not enabled yet? */
-
-	cmpl	$ftrace_stub, ftrace_trace_function
-	jnz	.Ltrace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpl	$ftrace_stub, ftrace_graph_return
-	jnz	ftrace_graph_caller
-
-	cmpl	$ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz	ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
-	ret
-
-	/* taken from glibc */
-.Ltrace:
-	pushl	%eax
-	pushl	%ecx
-	pushl	%edx
-	movl	0xc(%esp), %eax
-	movl	0x4(%ebp), %edx
-	subl	$MCOUNT_INSN_SIZE, %eax
-
-	call	*ftrace_trace_function
-
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-	jmp	ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-EXPORT_SYMBOL(mcount)
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
-	pushl	%eax
-	pushl	%ecx
-	pushl	%edx
-	movl	0xc(%esp), %eax
-	lea	0x4(%ebp), %edx
-	movl	(%ebp), %ecx
-	subl	$MCOUNT_INSN_SIZE, %eax
-	call	prepare_ftrace_return
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-	ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
-	pushl	%eax
-	pushl	%edx
-	movl	%ebp, %eax
-	call	ftrace_return_to_handler
-	movl	%eax, %ecx
-	popl	%edx
-	popl	%eax
-	jmp	*%ecx
-#endif
-
 #ifdef CONFIG_TRACING
 ENTRY(trace_page_fault)
 	ASM_CLAC
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 044d18ebc43c..607d72c4a485 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -212,7 +212,7 @@ entry_SYSCALL_64_fastpath:
 	 * If we see that no exit work is required (which we are required
 	 * to check with IRQs off), then we can go straight to SYSRET64.
 	 */
-	DISABLE_INTERRUPTS(CLBR_NONE)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	movq	PER_CPU_VAR(current_task), %r11
 	testl	$_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
@@ -233,7 +233,7 @@ entry_SYSCALL_64_fastpath:
 	 * raise(3) will trigger this, for example.  IRQs are off.
 	 */
 	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
+	ENABLE_INTERRUPTS(CLBR_ANY)
 	SAVE_EXTRA_REGS
 	movq	%rsp, %rdi
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
@@ -265,12 +265,9 @@ return_from_SYSCALL_64:
 	 *
 	 * If width of "canonical tail" ever becomes variable, this will need
 	 * to be updated to remain correct on both old and new CPUs.
+	 *
+	 * Change top 16 bits to be the sign-extension of 47th bit
 	 */
-	.ifne __VIRTUAL_MASK_SHIFT - 47
-	.error "virtual address width changed -- SYSRET checks need update"
-	.endif
-
-	/* Change top 16 bits to be the sign-extension of 47th bit */
 	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
 	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
 
@@ -343,7 +340,7 @@ ENTRY(stub_ptregs_64)
 	 * Called from fast path -- disable IRQs again, pop return address
 	 * and jump to slow path
 	 */
-	DISABLE_INTERRUPTS(CLBR_NONE)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	popq	%rax
 	jmp	entry_SYSCALL64_slow_path
@@ -518,7 +515,7 @@ common_interrupt:
 	interrupt do_IRQ
 	/* 0(%rsp): old RSP */
 ret_from_intr:
-	DISABLE_INTERRUPTS(CLBR_NONE)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	decl	PER_CPU_VAR(irq_count)
 
@@ -1051,7 +1048,7 @@ END(paranoid_entry)
  * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
  */
 ENTRY(paranoid_exit)
-	DISABLE_INTERRUPTS(CLBR_NONE)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF_DEBUG
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	paranoid_exit_no_swapgs
@@ -1156,10 +1153,9 @@ END(error_entry)
  *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
  */
 ENTRY(error_exit)
-	movl	%ebx, %eax
-	DISABLE_INTERRUPTS(CLBR_NONE)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
-	testl	%eax, %eax
+	testl	%ebx, %ebx
 	jnz	retint_kernel
 	jmp	retint_user
 END(error_exit)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9ba050fe47f3..448ac2161112 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -226,7 +226,7 @@
 217	i386	pivot_root		sys_pivot_root
 218	i386	mincore			sys_mincore
 219	i386	madvise			sys_madvise
-220	i386	getdents64		sys_getdents64			compat_sys_getdents64
+220	i386	getdents64		sys_getdents64
 221	i386	fcntl64			sys_fcntl64			compat_sys_fcntl64
 # 222 is unused
 # 223 is unused
@@ -390,3 +390,4 @@
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
+384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9d4d6e138311..fa8dbfcf7ed3 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -17,6 +17,7 @@
 #include <asm/unistd.h>
 #include <asm/msr.h>
 #include <asm/pvclock.h>
+#include <asm/mshyperv.h>
 #include <linux/math64.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
@@ -32,6 +33,11 @@ extern u8 pvclock_page
 	__attribute__((visibility("hidden")));
 #endif
 
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern u8 hvclock_page
+	__attribute__((visibility("hidden")));
+#endif
+
 #ifndef BUILD_VDSO32
 
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
@@ -141,6 +147,20 @@ static notrace u64 vread_pvclock(int *mode)
 	return last;
 }
 #endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+static notrace u64 vread_hvclock(int *mode)
+{
+	const struct ms_hyperv_tsc_page *tsc_pg =
+		(const struct ms_hyperv_tsc_page *)&hvclock_page;
+	u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+	if (current_tick != U64_MAX)
+		return current_tick;
+
+	*mode = VCLOCK_NONE;
+	return 0;
+}
+#endif
 
 notrace static u64 vread_tsc(void)
 {
@@ -173,6 +193,10 @@ notrace static inline u64 vgetsns(int *mode)
 	else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
 		cycles = vread_pvclock(mode);
 #endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+	else if (gtod->vclock_mode == VCLOCK_HVCLOCK)
+		cycles = vread_hvclock(mode);
+#endif
 	else
 		return 0;
 	v = (cycles - gtod->cycle_last) & gtod->mask;
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index a708aa90b507..8ebb4b6454fe 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - 2 * PAGE_SIZE;
+	vvar_start = . - 3 * PAGE_SIZE;
 	vvar_page = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@ SECTIONS
 #undef EMIT_VVAR
 
 	pvclock_page = vvar_start + PAGE_SIZE;
+	hvclock_page = vvar_start + 2 * PAGE_SIZE;
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 491020b2826d..0780a443a53b 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -74,6 +74,7 @@ enum {
 	sym_vvar_page,
 	sym_hpet_page,
 	sym_pvclock_page,
+	sym_hvclock_page,
 	sym_VDSO_FAKE_SECTION_TABLE_START,
 	sym_VDSO_FAKE_SECTION_TABLE_END,
 };
@@ -82,6 +83,7 @@ const int special_pages[] = {
 	sym_vvar_page,
 	sym_hpet_page,
 	sym_pvclock_page,
+	sym_hvclock_page,
 };
 
 struct vdso_sym {
@@ -94,6 +96,7 @@ struct vdso_sym required_syms[] = {
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_hpet_page] = {"hpet_page", true},
 	[sym_pvclock_page] = {"pvclock_page", true},
+	[sym_hvclock_page] = {"hvclock_page", true},
 	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
 		"VDSO_FAKE_SECTION_TABLE_START", false
 	},
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 7853b53959cd..3f9d1a83891a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -30,8 +30,10 @@ static int __init vdso32_setup(char *s)
 {
 	vdso32_enabled = simple_strtoul(s, NULL, 0);
 
-	if (vdso32_enabled > 1)
+	if (vdso32_enabled > 1) {
 		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+		vdso32_enabled = 0;
+	}
 
 	return 1;
 }
@@ -62,13 +64,18 @@ subsys_initcall(sysenter_setup);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
+static const int zero;
+static const int one = 1;
+
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
 		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (int *)&zero,
+		.extra2		= (int *)&one,
 	},
 	{}
 };
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 226ca70dc6bd..139ad7726e10 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -22,6 +22,7 @@
 #include <asm/page.h>
 #include <asm/desc.h>
 #include <asm/cpufeature.h>
+#include <asm/mshyperv.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
@@ -121,6 +122,12 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 				vmf->address,
 				__pa(pvti) >> PAGE_SHIFT);
 		}
+	} else if (sym_offset == image->sym_hvclock_page) {
+		struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();
+
+		if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
+			ret = vm_insert_pfn(vma, vmf->address,
+					    vmalloc_to_pfn(tsc_pg));
 	}
 
 	if (ret == 0 || ret == -EBUSY)
@@ -354,7 +361,7 @@ static void vgetcpu_cpu_init(void *arg)
 	d.p = 1;		/* Present */
 	d.d = 1;		/* 32-bit */
 
-	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
 }
 
 static int vgetcpu_online(unsigned int cpu)
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index afb222b63cae..c84584bb9402 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 			return &amd_f15_PMC20;
 		}
 	case AMD_EVENT_NB:
-		/* moved to perf_event_amd_uncore.c */
+		/* moved to uncore.c */
 		return &emptyconstraint;
 	default:
 		return &emptyconstraint;
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index b28200dea715..3641e24fdac5 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -11,6 +11,8 @@
  * published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt)	"perf/amd_iommu: " fmt
+
 #include <linux/perf_event.h>
 #include <linux/init.h>
 #include <linux/cpumask.h>
@@ -21,44 +23,42 @@
 
 #define COUNTER_SHIFT		16
 
-#define _GET_BANK(ev)       ((u8)(ev->hw.extra_reg.reg >> 8))
-#define _GET_CNTR(ev)       ((u8)(ev->hw.extra_reg.reg))
+/* iommu pmu conf masks */
+#define GET_CSOURCE(x)     ((x)->conf & 0xFFULL)
+#define GET_DEVID(x)       (((x)->conf >> 8)  & 0xFFFFULL)
+#define GET_DOMID(x)       (((x)->conf >> 24) & 0xFFFFULL)
+#define GET_PASID(x)       (((x)->conf >> 40) & 0xFFFFFULL)
 
-/* iommu pmu config masks */
-#define _GET_CSOURCE(ev)    ((ev->hw.config & 0xFFULL))
-#define _GET_DEVID(ev)      ((ev->hw.config >> 8)  & 0xFFFFULL)
-#define _GET_PASID(ev)      ((ev->hw.config >> 24) & 0xFFFFULL)
-#define _GET_DOMID(ev)      ((ev->hw.config >> 40) & 0xFFFFULL)
-#define _GET_DEVID_MASK(ev) ((ev->hw.extra_reg.config)  & 0xFFFFULL)
-#define _GET_PASID_MASK(ev) ((ev->hw.extra_reg.config >> 16) & 0xFFFFULL)
-#define _GET_DOMID_MASK(ev) ((ev->hw.extra_reg.config >> 32) & 0xFFFFULL)
+/* iommu pmu conf1 masks */
+#define GET_DEVID_MASK(x)  ((x)->conf1  & 0xFFFFULL)
+#define GET_DOMID_MASK(x)  (((x)->conf1 >> 16) & 0xFFFFULL)
+#define GET_PASID_MASK(x)  (((x)->conf1 >> 32) & 0xFFFFFULL)
 
-static struct perf_amd_iommu __perf_iommu;
+#define IOMMU_NAME_SIZE 16
 
 struct perf_amd_iommu {
+	struct list_head list;
 	struct pmu pmu;
+	struct amd_iommu *iommu;
+	char name[IOMMU_NAME_SIZE];
 	u8 max_banks;
 	u8 max_counters;
 	u64 cntr_assign_mask;
 	raw_spinlock_t lock;
-	const struct attribute_group *attr_groups[4];
 };
 
-#define format_group	attr_groups[0]
-#define cpumask_group	attr_groups[1]
-#define events_group	attr_groups[2]
-#define null_group	attr_groups[3]
+static LIST_HEAD(perf_amd_iommu_list);
 
 /*---------------------------------------------
  * sysfs format attributes
  *---------------------------------------------*/
 PMU_FORMAT_ATTR(csource,    "config:0-7");
 PMU_FORMAT_ATTR(devid,      "config:8-23");
-PMU_FORMAT_ATTR(pasid,      "config:24-39");
-PMU_FORMAT_ATTR(domid,      "config:40-55");
+PMU_FORMAT_ATTR(domid,      "config:24-39");
+PMU_FORMAT_ATTR(pasid,      "config:40-59");
 PMU_FORMAT_ATTR(devid_mask, "config1:0-15");
-PMU_FORMAT_ATTR(pasid_mask, "config1:16-31");
-PMU_FORMAT_ATTR(domid_mask, "config1:32-47");
+PMU_FORMAT_ATTR(domid_mask, "config1:16-31");
+PMU_FORMAT_ATTR(pasid_mask, "config1:32-51");
 
 static struct attribute *iommu_format_attrs[] = {
 	&format_attr_csource.attr,
@@ -79,6 +79,10 @@ static struct attribute_group amd_iommu_format_group = {
 /*---------------------------------------------
  * sysfs events attributes
  *---------------------------------------------*/
+static struct attribute_group amd_iommu_events_group = {
+	.name = "events",
+};
+
 struct amd_iommu_event_desc {
 	struct kobj_attribute attr;
 	const char *event;
@@ -150,30 +154,34 @@ static struct attribute_group amd_iommu_cpumask_group = {
 
 /*---------------------------------------------*/
 
-static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu)
+static int get_next_avail_iommu_bnk_cntr(struct perf_event *event)
 {
+	struct perf_amd_iommu *piommu = container_of(event->pmu, struct perf_amd_iommu, pmu);
+	int max_cntrs = piommu->max_counters;
+	int max_banks = piommu->max_banks;
+	u32 shift, bank, cntr;
 	unsigned long flags;
-	int shift, bank, cntr, retval;
-	int max_banks = perf_iommu->max_banks;
-	int max_cntrs = perf_iommu->max_counters;
+	int retval;
 
-	raw_spin_lock_irqsave(&perf_iommu->lock, flags);
+	raw_spin_lock_irqsave(&piommu->lock, flags);
 
 	for (bank = 0, shift = 0; bank < max_banks; bank++) {
 		for (cntr = 0; cntr < max_cntrs; cntr++) {
 			shift = bank + (bank*3) + cntr;
-			if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) {
+			if (piommu->cntr_assign_mask & BIT_ULL(shift)) {
 				continue;
 			} else {
-				perf_iommu->cntr_assign_mask |= (1ULL<<shift);
-				retval = ((u16)((u16)bank<<8) | (u8)(cntr));
+				piommu->cntr_assign_mask |= BIT_ULL(shift);
+				event->hw.iommu_bank = bank;
+				event->hw.iommu_cntr = cntr;
+				retval = 0;
 				goto out;
 			}
 		}
 	}
 	retval = -ENOSPC;
 out:
-	raw_spin_unlock_irqrestore(&perf_iommu->lock, flags);
+	raw_spin_unlock_irqrestore(&piommu->lock, flags);
 	return retval;
 }
 
@@ -202,8 +210,6 @@ static int clear_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu,
 static int perf_iommu_event_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct perf_amd_iommu *perf_iommu;
-	u64 config, config1;
 
 	/* test the event attr type check for PMU enumeration */
 	if (event->attr.type != event->pmu->type)
@@ -225,80 +231,62 @@ static int perf_iommu_event_init(struct perf_event *event)
 	if (event->cpu < 0)
 		return -EINVAL;
 
-	perf_iommu = &__perf_iommu;
-
-	if (event->pmu != &perf_iommu->pmu)
-		return -ENOENT;
-
-	if (perf_iommu) {
-		config = event->attr.config;
-		config1 = event->attr.config1;
-	} else {
-		return -EINVAL;
-	}
-
-	/* integrate with iommu base devid (0000), assume one iommu */
-	perf_iommu->max_banks =
-		amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID);
-	perf_iommu->max_counters =
-		amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID);
-	if ((perf_iommu->max_banks == 0) || (perf_iommu->max_counters == 0))
-		return -EINVAL;
-
 	/* update the hw_perf_event struct with the iommu config data */
-	hwc->config = config;
-	hwc->extra_reg.config = config1;
+	hwc->conf  = event->attr.config;
+	hwc->conf1 = event->attr.config1;
 
 	return 0;
 }
 
+static inline struct amd_iommu *perf_event_2_iommu(struct perf_event *ev)
+{
+	return (container_of(ev->pmu, struct perf_amd_iommu, pmu))->iommu;
+}
+
 static void perf_iommu_enable_event(struct perf_event *ev)
 {
-	u8 csource = _GET_CSOURCE(ev);
-	u16 devid = _GET_DEVID(ev);
+	struct amd_iommu *iommu = perf_event_2_iommu(ev);
+	struct hw_perf_event *hwc = &ev->hw;
+	u8 bank = hwc->iommu_bank;
+	u8 cntr = hwc->iommu_cntr;
 	u64 reg = 0ULL;
 
-	reg = csource;
-	amd_iommu_pc_get_set_reg_val(devid,
-			_GET_BANK(ev), _GET_CNTR(ev) ,
-			 IOMMU_PC_COUNTER_SRC_REG, &reg, true);
+	reg = GET_CSOURCE(hwc);
+	amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_COUNTER_SRC_REG, &reg);
 
-	reg = 0ULL | devid | (_GET_DEVID_MASK(ev) << 32);
+	reg = GET_DEVID_MASK(hwc);
+	reg = GET_DEVID(hwc) | (reg << 32);
 	if (reg)
-		reg |= (1UL << 31);
-	amd_iommu_pc_get_set_reg_val(devid,
-			_GET_BANK(ev), _GET_CNTR(ev) ,
-			 IOMMU_PC_DEVID_MATCH_REG, &reg, true);
+		reg |= BIT(31);
+	amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_DEVID_MATCH_REG, &reg);
 
-	reg = 0ULL | _GET_PASID(ev) | (_GET_PASID_MASK(ev) << 32);
+	reg = GET_PASID_MASK(hwc);
+	reg = GET_PASID(hwc) | (reg << 32);
 	if (reg)
-		reg |= (1UL << 31);
-	amd_iommu_pc_get_set_reg_val(devid,
-			_GET_BANK(ev), _GET_CNTR(ev) ,
-			 IOMMU_PC_PASID_MATCH_REG, &reg, true);
+		reg |= BIT(31);
+	amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_PASID_MATCH_REG, &reg);
 
-	reg = 0ULL | _GET_DOMID(ev) | (_GET_DOMID_MASK(ev) << 32);
+	reg = GET_DOMID_MASK(hwc);
+	reg = GET_DOMID(hwc) | (reg << 32);
 	if (reg)
-		reg |= (1UL << 31);
-	amd_iommu_pc_get_set_reg_val(devid,
-			_GET_BANK(ev), _GET_CNTR(ev) ,
-			 IOMMU_PC_DOMID_MATCH_REG, &reg, true);
+		reg |= BIT(31);
+	amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_DOMID_MATCH_REG, &reg);
 }
 
 static void perf_iommu_disable_event(struct perf_event *event)
 {
+	struct amd_iommu *iommu = perf_event_2_iommu(event);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 reg = 0ULL;
 
-	amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
-			_GET_BANK(event), _GET_CNTR(event),
-			IOMMU_PC_COUNTER_SRC_REG, &reg, true);
+	amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
+			     IOMMU_PC_COUNTER_SRC_REG, &reg);
 }
 
 static void perf_iommu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	pr_debug("perf: amd_iommu:perf_iommu_start\n");
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
 		return;
 
@@ -306,10 +294,11 @@ static void perf_iommu_start(struct perf_event *event, int flags)
 	hwc->state = 0;
 
 	if (flags & PERF_EF_RELOAD) {
-		u64 prev_raw_count =  local64_read(&hwc->prev_count);
-		amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
-				_GET_BANK(event), _GET_CNTR(event),
-				IOMMU_PC_COUNTER_REG, &prev_raw_count, true);
+		u64 prev_raw_count = local64_read(&hwc->prev_count);
+		struct amd_iommu *iommu = perf_event_2_iommu(event);
+
+		amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
+				     IOMMU_PC_COUNTER_REG, &prev_raw_count);
 	}
 
 	perf_iommu_enable_event(event);
@@ -319,37 +308,30 @@ static void perf_iommu_start(struct perf_event *event, int flags)
 
 static void perf_iommu_read(struct perf_event *event)
 {
-	u64 count = 0ULL;
-	u64 prev_raw_count = 0ULL;
-	u64 delta = 0ULL;
+	u64 count, prev, delta;
 	struct hw_perf_event *hwc = &event->hw;
-	pr_debug("perf: amd_iommu:perf_iommu_read\n");
+	struct amd_iommu *iommu = perf_event_2_iommu(event);
 
-	amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
-				_GET_BANK(event), _GET_CNTR(event),
-				IOMMU_PC_COUNTER_REG, &count, false);
+	if (amd_iommu_pc_get_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
+				 IOMMU_PC_COUNTER_REG, &count))
+		return;
 
 	/* IOMMU pc counter register is only 48 bits */
-	count &= 0xFFFFFFFFFFFFULL;
+	count &= GENMASK_ULL(47, 0);
 
-	prev_raw_count =  local64_read(&hwc->prev_count);
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-					count) != prev_raw_count)
+	prev = local64_read(&hwc->prev_count);
+	if (local64_cmpxchg(&hwc->prev_count, prev, count) != prev)
 		return;
 
-	/* Handling 48-bit counter overflowing */
-	delta = (count << COUNTER_SHIFT) - (prev_raw_count << COUNTER_SHIFT);
+	/* Handle 48-bit counter overflow */
+	delta = (count << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
 	delta >>= COUNTER_SHIFT;
 	local64_add(delta, &event->count);
-
 }
 
 static void perf_iommu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	u64 config;
-
-	pr_debug("perf: amd_iommu:perf_iommu_stop\n");
 
 	if (hwc->state & PERF_HES_UPTODATE)
 		return;
@@ -361,7 +343,6 @@ static void perf_iommu_stop(struct perf_event *event, int flags)
 	if (hwc->state & PERF_HES_UPTODATE)
 		return;
 
-	config = hwc->config;
 	perf_iommu_read(event);
 	hwc->state |= PERF_HES_UPTODATE;
 }
@@ -369,17 +350,12 @@ static void perf_iommu_stop(struct perf_event *event, int flags)
 static int perf_iommu_add(struct perf_event *event, int flags)
 {
 	int retval;
-	struct perf_amd_iommu *perf_iommu =
-			container_of(event->pmu, struct perf_amd_iommu, pmu);
 
-	pr_debug("perf: amd_iommu:perf_iommu_add\n");
 	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
 	/* request an iommu bank/counter */
-	retval = get_next_avail_iommu_bnk_cntr(perf_iommu);
-	if (retval != -ENOSPC)
-		event->hw.extra_reg.reg = (u16)retval;
-	else
+	retval = get_next_avail_iommu_bnk_cntr(event);
+	if (retval)
 		return retval;
 
 	if (flags & PERF_EF_START)
@@ -390,115 +366,124 @@ static int perf_iommu_add(struct perf_event *event, int flags)
 
 static void perf_iommu_del(struct perf_event *event, int flags)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	struct perf_amd_iommu *perf_iommu =
 			container_of(event->pmu, struct perf_amd_iommu, pmu);
 
-	pr_debug("perf: amd_iommu:perf_iommu_del\n");
 	perf_iommu_stop(event, PERF_EF_UPDATE);
 
 	/* clear the assigned iommu bank/counter */
 	clear_avail_iommu_bnk_cntr(perf_iommu,
-				     _GET_BANK(event),
-				     _GET_CNTR(event));
+				   hwc->iommu_bank, hwc->iommu_cntr);
 
 	perf_event_update_userpage(event);
 }
 
-static __init int _init_events_attrs(struct perf_amd_iommu *perf_iommu)
+static __init int _init_events_attrs(void)
 {
-	struct attribute **attrs;
-	struct attribute_group *attr_group;
 	int i = 0, j;
+	struct attribute **attrs;
 
 	while (amd_iommu_v2_event_descs[i].attr.attr.name)
 		i++;
 
-	attr_group = kzalloc(sizeof(struct attribute *)
-		* (i + 1) + sizeof(*attr_group), GFP_KERNEL);
-	if (!attr_group)
+	attrs = kzalloc(sizeof(struct attribute **) * (i + 1), GFP_KERNEL);
+	if (!attrs)
 		return -ENOMEM;
 
-	attrs = (struct attribute **)(attr_group + 1);
 	for (j = 0; j < i; j++)
 		attrs[j] = &amd_iommu_v2_event_descs[j].attr.attr;
 
-	attr_group->name = "events";
-	attr_group->attrs = attrs;
-	perf_iommu->events_group = attr_group;
-
+	amd_iommu_events_group.attrs = attrs;
 	return 0;
 }
 
-static __init void amd_iommu_pc_exit(void)
-{
-	if (__perf_iommu.events_group != NULL) {
-		kfree(__perf_iommu.events_group);
-		__perf_iommu.events_group = NULL;
-	}
-}
+const struct attribute_group *amd_iommu_attr_groups[] = {
+	&amd_iommu_format_group,
+	&amd_iommu_cpumask_group,
+	&amd_iommu_events_group,
+	NULL,
+};
+
+static struct pmu iommu_pmu = {
+	.event_init	= perf_iommu_event_init,
+	.add		= perf_iommu_add,
+	.del		= perf_iommu_del,
+	.start		= perf_iommu_start,
+	.stop		= perf_iommu_stop,
+	.read		= perf_iommu_read,
+	.task_ctx_nr	= perf_invalid_context,
+	.attr_groups	= amd_iommu_attr_groups,
+};
 
-static __init int _init_perf_amd_iommu(
-	struct perf_amd_iommu *perf_iommu, char *name)
+static __init int init_one_iommu(unsigned int idx)
 {
+	struct perf_amd_iommu *perf_iommu;
 	int ret;
 
+	perf_iommu = kzalloc(sizeof(struct perf_amd_iommu), GFP_KERNEL);
+	if (!perf_iommu)
+		return -ENOMEM;
+
 	raw_spin_lock_init(&perf_iommu->lock);
 
-	/* Init format attributes */
-	perf_iommu->format_group = &amd_iommu_format_group;
+	perf_iommu->pmu          = iommu_pmu;
+	perf_iommu->iommu        = get_amd_iommu(idx);
+	perf_iommu->max_banks    = amd_iommu_pc_get_max_banks(idx);
+	perf_iommu->max_counters = amd_iommu_pc_get_max_counters(idx);
 
-	/* Init cpumask attributes to only core 0 */
-	cpumask_set_cpu(0, &iommu_cpumask);
-	perf_iommu->cpumask_group = &amd_iommu_cpumask_group;
-
-	/* Init events attributes */
-	if (_init_events_attrs(perf_iommu) != 0)
-		pr_err("perf: amd_iommu: Only support raw events.\n");
+	if (!perf_iommu->iommu ||
+	    !perf_iommu->max_banks ||
+	    !perf_iommu->max_counters) {
+		kfree(perf_iommu);
+		return -EINVAL;
+	}
 
-	/* Init null attributes */
-	perf_iommu->null_group = NULL;
-	perf_iommu->pmu.attr_groups = perf_iommu->attr_groups;
+	snprintf(perf_iommu->name, IOMMU_NAME_SIZE, "amd_iommu_%u", idx);
 
-	ret = perf_pmu_register(&perf_iommu->pmu, name, -1);
-	if (ret) {
-		pr_err("perf: amd_iommu: Failed to initialized.\n");
-		amd_iommu_pc_exit();
+	ret = perf_pmu_register(&perf_iommu->pmu, perf_iommu->name, -1);
+	if (!ret) {
+		pr_info("Detected AMD IOMMU #%d (%d banks, %d counters/bank).\n",
+			idx, perf_iommu->max_banks, perf_iommu->max_counters);
+		list_add_tail(&perf_iommu->list, &perf_amd_iommu_list);
 	} else {
-		pr_info("perf: amd_iommu: Detected. (%d banks, %d counters/bank)\n",
-			amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID),
-			amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID));
+		pr_warn("Error initializing IOMMU %d.\n", idx);
+		kfree(perf_iommu);
 	}
-
 	return ret;
 }
 
-static struct perf_amd_iommu __perf_iommu = {
-	.pmu = {
-		.task_ctx_nr    = perf_invalid_context,
-		.event_init	= perf_iommu_event_init,
-		.add		= perf_iommu_add,
-		.del		= perf_iommu_del,
-		.start		= perf_iommu_start,
-		.stop		= perf_iommu_stop,
-		.read		= perf_iommu_read,
-	},
-	.max_banks		= 0x00,
-	.max_counters		= 0x00,
-	.cntr_assign_mask	= 0ULL,
-	.format_group		= NULL,
-	.cpumask_group		= NULL,
-	.events_group		= NULL,
-	.null_group		= NULL,
-};
-
 static __init int amd_iommu_pc_init(void)
 {
+	unsigned int i, cnt = 0;
+	int ret;
+
 	/* Make sure the IOMMU PC resource is available */
 	if (!amd_iommu_pc_supported())
 		return -ENODEV;
 
-	_init_perf_amd_iommu(&__perf_iommu, "amd_iommu");
+	ret = _init_events_attrs();
+	if (ret)
+		return ret;
+
+	/*
+	 * An IOMMU PMU is specific to an IOMMU, and can function independently.
+	 * So we go through all IOMMUs and ignore the one that fails init
+	 * unless all IOMMU are failing.
+	 */
+	for (i = 0; i < amd_iommu_get_num_iommus(); i++) {
+		ret = init_one_iommu(i);
+		if (!ret)
+			cnt++;
+	}
+
+	if (!cnt) {
+		kfree(amd_iommu_events_group.attrs);
+		return -ENODEV;
+	}
 
+	/* Init cpumask attributes to only core 0 */
+	cpumask_set_cpu(0, &iommu_cpumask);
 	return 0;
 }
 
diff --git a/arch/x86/events/amd/iommu.h b/arch/x86/events/amd/iommu.h
index 845d173278e3..62e0702c4374 100644
--- a/arch/x86/events/amd/iommu.h
+++ b/arch/x86/events/amd/iommu.h
@@ -24,17 +24,23 @@
 #define PC_MAX_SPEC_BNKS			64
 #define PC_MAX_SPEC_CNTRS			16
 
-/* iommu pc reg masks*/
-#define IOMMU_BASE_DEVID			0x0000
+struct amd_iommu;
 
 /* amd_iommu_init.c external support functions */
+extern int amd_iommu_get_num_iommus(void);
+
 extern bool amd_iommu_pc_supported(void);
 
-extern u8 amd_iommu_pc_get_max_banks(u16 devid);
+extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+
+extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+
+extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
 
-extern u8 amd_iommu_pc_get_max_counters(u16 devid);
+extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
 
-extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr,
-			u8 fxn, u64 *value, bool is_write);
+extern struct amd_iommu *get_amd_iommu(int idx);
 
 #endif /*_PERF_EVENT_AMD_IOMMU_H_*/
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4d1f7f2d9aff..ad44af0dd667 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -30,6 +30,9 @@
 
 #define COUNTER_SHIFT		16
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"amd_uncore: " fmt
+
 static int num_counters_llc;
 static int num_counters_nb;
 
@@ -509,51 +512,34 @@ static int __init amd_uncore_init(void)
 	int ret = -ENODEV;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
-		goto fail_nodev;
-
-	switch(boot_cpu_data.x86) {
-		case 23:
-			/* Family 17h: */
-			num_counters_nb = NUM_COUNTERS_NB;
-			num_counters_llc = NUM_COUNTERS_L3;
-			/*
-			 * For Family17h, the NorthBridge counters are
-			 * re-purposed as Data Fabric counters. Also, support is
-			 * added for L3 counters. The pmus are exported based on
-			 * family as either L2 or L3 and NB or DF.
-			 */
-			amd_nb_pmu.name = "amd_df";
-			amd_llc_pmu.name = "amd_l3";
-			format_attr_event_df.show = &event_show_df;
-			format_attr_event_l3.show = &event_show_l3;
-			break;
-		case 22:
-			/* Family 16h - may change: */
-			num_counters_nb = NUM_COUNTERS_NB;
-			num_counters_llc = NUM_COUNTERS_L2;
-			amd_nb_pmu.name = "amd_nb";
-			amd_llc_pmu.name = "amd_l2";
-			format_attr_event_df = format_attr_event;
-			format_attr_event_l3 = format_attr_event;
-			break;
-		default:
-			/*
-			 * All prior families have the same number of
-			 * NorthBridge and Last Level Cache counters
-			 */
-			num_counters_nb = NUM_COUNTERS_NB;
-			num_counters_llc = NUM_COUNTERS_L2;
-			amd_nb_pmu.name = "amd_nb";
-			amd_llc_pmu.name = "amd_l2";
-			format_attr_event_df = format_attr_event;
-			format_attr_event_l3 = format_attr_event;
-			break;
-	}
-	amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
-	amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
+		return -ENODEV;
 
 	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
-		goto fail_nodev;
+		return -ENODEV;
+
+	if (boot_cpu_data.x86 == 0x17) {
+		/*
+		 * For F17h, the Northbridge counters are repurposed as Data
+		 * Fabric counters. Also, L3 counters are supported too. The PMUs
+		 * are exported based on  family as either L2 or L3 and NB or DF.
+		 */
+		num_counters_nb		  = NUM_COUNTERS_NB;
+		num_counters_llc	  = NUM_COUNTERS_L3;
+		amd_nb_pmu.name		  = "amd_df";
+		amd_llc_pmu.name	  = "amd_l3";
+		format_attr_event_df.show = &event_show_df;
+		format_attr_event_l3.show = &event_show_l3;
+	} else {
+		num_counters_nb		  = NUM_COUNTERS_NB;
+		num_counters_llc	  = NUM_COUNTERS_L2;
+		amd_nb_pmu.name		  = "amd_nb";
+		amd_llc_pmu.name	  = "amd_l2";
+		format_attr_event_df	  = format_attr_event;
+		format_attr_event_l3	  = format_attr_event;
+	}
+
+	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;
+	amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
 
 	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
@@ -565,7 +551,7 @@ static int __init amd_uncore_init(void)
 		if (ret)
 			goto fail_nb;
 
-		pr_info("perf: AMD NB counters detected\n");
+		pr_info("AMD NB counters detected\n");
 		ret = 0;
 	}
 
@@ -579,7 +565,7 @@ static int __init amd_uncore_init(void)
 		if (ret)
 			goto fail_llc;
 
-		pr_info("perf: AMD LLC counters detected\n");
+		pr_info("AMD LLC counters detected\n");
 		ret = 0;
 	}
 
@@ -615,7 +601,6 @@ fail_nb:
 	if (amd_uncore_nb)
 		free_percpu(amd_uncore_nb);
 
-fail_nodev:
 	return ret;
 }
 device_initcall(amd_uncore_init);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 349d4d17aa7f..580b60f5ac83 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2101,8 +2101,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	if (current->mm)
-		load_mm_cr4(current->mm);
+	if (current->active_mm)
+		load_mm_cr4(current->active_mm);
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event)
@@ -2110,6 +2110,18 @@ static void x86_pmu_event_mapped(struct perf_event *event)
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 
+	/*
+	 * This function relies on not being called concurrently in two
+	 * tasks in the same mm.  Otherwise one task could observe
+	 * perf_rdpmc_allowed > 1 and return all the way back to
+	 * userspace with CR4.PCE clear while another task is still
+	 * doing on_each_cpu_mask() to propagate CR4.PCE.
+	 *
+	 * For now, this can't happen because all callers hold mmap_sem
+	 * for write.  If this changes, we'll need a different solution.
+	 */
+	lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+
 	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
 		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
 }
@@ -2244,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
 	struct cyc2ns_data *data;
+	u64 offset;
 
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
@@ -2251,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event,
 		!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!sched_clock_stable())
+	if (!using_native_sched_clock() || !sched_clock_stable())
 		return;
 
 	data = cyc2ns_read_begin();
 
+	offset = data->cyc2ns_offset + __sched_clock_offset;
+
 	/*
 	 * Internal timekeeping for enabled/running/stopped times
 	 * is always in the local_clock domain.
@@ -2263,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 1;
 	userpg->time_mult = data->cyc2ns_mul;
 	userpg->time_shift = data->cyc2ns_shift;
-	userpg->time_offset = data->cyc2ns_offset - now;
+	userpg->time_offset = offset - now;
 
 	/*
 	 * cap_user_time_zero doesn't make sense when we're using a different
@@ -2271,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 */
 	if (!event->attr.use_clockid) {
 		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = data->cyc2ns_offset;
+		userpg->time_zero = offset;
 	}
 
 	cyc2ns_read_end(data);
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 982c9e31daca..8ae8c5ce3a1f 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -63,7 +63,6 @@ struct bts_buffer {
 	unsigned int	cur_buf;
 	bool		snapshot;
 	local_t		data_size;
-	local_t		lost;
 	local_t		head;
 	unsigned long	end;
 	void		**data_pages;
@@ -199,7 +198,8 @@ static void bts_update(struct bts_ctx *bts)
 			return;
 
 		if (ds->bts_index >= ds->bts_absolute_maximum)
-			local_inc(&buf->lost);
+			perf_aux_output_flag(&bts->handle,
+			                     PERF_AUX_FLAG_TRUNCATED);
 
 		/*
 		 * old and head are always in the same physical buffer, so we
@@ -276,7 +276,7 @@ static void bts_event_start(struct perf_event *event, int flags)
 	return;
 
 fail_end_stop:
-	perf_aux_output_end(&bts->handle, 0, false);
+	perf_aux_output_end(&bts->handle, 0);
 
 fail_stop:
 	event->hw.state = PERF_HES_STOPPED;
@@ -319,9 +319,8 @@ static void bts_event_stop(struct perf_event *event, int flags)
 				bts->handle.head =
 					local_xchg(&buf->data_size,
 						   buf->nr_pages << PAGE_SHIFT);
-
-			perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
-					    !!local_xchg(&buf->lost, 0));
+			perf_aux_output_end(&bts->handle,
+			                    local_xchg(&buf->data_size, 0));
 		}
 
 		cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
@@ -484,8 +483,7 @@ int intel_bts_interrupt(void)
 	if (old_head == local_read(&buf->head))
 		return handled;
 
-	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
-			    !!local_xchg(&buf->lost, 0));
+	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0));
 
 	buf = perf_aux_output_begin(&bts->handle, event);
 	if (buf)
@@ -500,7 +498,7 @@ int intel_bts_interrupt(void)
 			 * cleared handle::event
 			 */
 			barrier();
-			perf_aux_output_end(&bts->handle, 0, false);
+			perf_aux_output_end(&bts->handle, 0);
 		}
 	}
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index eb1484c86bb4..a6d91d4e37a1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1553,6 +1553,27 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
+EVENT_ATTR_STR(topdown-total-slots, td_total_slots_glm, "event=0x3c");
+EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_glm, "3");
+/* UOPS_NOT_DELIVERED.ANY */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_glm, "event=0x9c");
+/* ISSUE_SLOTS_NOT_CONSUMED.RECOVERY */
+EVENT_ATTR_STR(topdown-recovery-bubbles, td_recovery_bubbles_glm, "event=0xca,umask=0x02");
+/* UOPS_RETIRED.ANY */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_glm, "event=0xc2");
+/* UOPS_ISSUED.ANY */
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_glm, "event=0x0e");
+
+static struct attribute *glm_events_attrs[] = {
+	EVENT_PTR(td_total_slots_glm),
+	EVENT_PTR(td_total_slots_scale_glm),
+	EVENT_PTR(td_fetch_bubbles_glm),
+	EVENT_PTR(td_recovery_bubbles_glm),
+	EVENT_PTR(td_slots_issued_glm),
+	EVENT_PTR(td_slots_retired_glm),
+	NULL
+};
+
 static struct extra_reg intel_glm_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0),
@@ -2130,7 +2151,7 @@ again:
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	status &= ~cpuc->pebs_enabled;
+	status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -3750,6 +3771,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.cpu_events = glm_events_attrs;
 		pr_cont("Goldmont events, ");
 		break;
 
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index aff4b5b69d40..238ae3248ba5 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -1,5 +1,5 @@
 /*
- * perf_event_intel_cstate.c: support cstate residency counters
+ * Support cstate residency counters
  *
  * Copyright (C) 2015, Intel Corp.
  * Author: Kan Liang (kan.liang@intel.com)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 9dfeeeca0ea8..c6d23ffe422d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1222,7 +1222,7 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 
 			/* clear non-PEBS bit and re-check */
 			pebs_status = p->status & cpuc->pebs_enabled;
-			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			pebs_status &= PEBS_COUNTER_MASK;
 			if (pebs_status == (1 << bit))
 				return at;
 		}
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 81b321ace8e0..f924629836a8 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -507,6 +507,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
 		cpuc->lbr_entries[i].mispred	= 0;
 		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].in_tx	= 0;
+		cpuc->lbr_entries[i].abort	= 0;
+		cpuc->lbr_entries[i].cycles	= 0;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 5900471ee508..ae8324d65e61 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -28,6 +28,7 @@
 #include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/intel_pt.h>
+#include <asm/intel-family.h>
 
 #include "../perf_event.h"
 #include "pt.h"
@@ -98,6 +99,7 @@ static struct attribute_group pt_cap_group = {
 	.name	= "caps",
 };
 
+PMU_FORMAT_ATTR(pt,		"config:0"	);
 PMU_FORMAT_ATTR(cyc,		"config:1"	);
 PMU_FORMAT_ATTR(pwr_evt,	"config:4"	);
 PMU_FORMAT_ATTR(fup_on_ptw,	"config:5"	);
@@ -105,11 +107,13 @@ PMU_FORMAT_ATTR(mtc,		"config:9"	);
 PMU_FORMAT_ATTR(tsc,		"config:10"	);
 PMU_FORMAT_ATTR(noretcomp,	"config:11"	);
 PMU_FORMAT_ATTR(ptw,		"config:12"	);
+PMU_FORMAT_ATTR(branch,		"config:13"	);
 PMU_FORMAT_ATTR(mtc_period,	"config:14-17"	);
 PMU_FORMAT_ATTR(cyc_thresh,	"config:19-22"	);
 PMU_FORMAT_ATTR(psb_period,	"config:24-27"	);
 
 static struct attribute *pt_formats_attr[] = {
+	&format_attr_pt.attr,
 	&format_attr_cyc.attr,
 	&format_attr_pwr_evt.attr,
 	&format_attr_fup_on_ptw.attr,
@@ -117,6 +121,7 @@ static struct attribute *pt_formats_attr[] = {
 	&format_attr_tsc.attr,
 	&format_attr_noretcomp.attr,
 	&format_attr_ptw.attr,
+	&format_attr_branch.attr,
 	&format_attr_mtc_period.attr,
 	&format_attr_cyc_thresh.attr,
 	&format_attr_psb_period.attr,
@@ -197,6 +202,19 @@ static int __init pt_pmu_hw_init(void)
 		pt_pmu.tsc_art_den = eax;
 	}
 
+	/* model-specific quirks */
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_XEON_D:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_X:
+		/* not setting BRANCH_EN will #GP, erratum BDM106 */
+		pt_pmu.branch_en_always_on = true;
+		break;
+	default:
+		break;
+	}
+
 	if (boot_cpu_has(X86_FEATURE_VMX)) {
 		/*
 		 * Intel SDM, 36.5 "Tracing post-VMXON" says that
@@ -263,8 +281,20 @@ fail:
 #define RTIT_CTL_PTW	(RTIT_CTL_PTW_EN	| \
 			 RTIT_CTL_FUP_ON_PTW)
 
-#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN		| \
+/*
+ * Bit 0 (TraceEn) in the attr.config is meaningless as the
+ * corresponding bit in the RTIT_CTL can only be controlled
+ * by the driver; therefore, repurpose it to mean: pass
+ * through the bit that was previously assumed to be always
+ * on for PT, thereby allowing the user to *not* set it if
+ * they so wish. See also pt_event_valid() and pt_config().
+ */
+#define RTIT_CTL_PASSTHROUGH RTIT_CTL_TRACEEN
+
+#define PT_CONFIG_MASK (RTIT_CTL_TRACEEN	| \
+			RTIT_CTL_TSC_EN		| \
 			RTIT_CTL_DISRETC	| \
+			RTIT_CTL_BRANCH_EN	| \
 			RTIT_CTL_CYC_PSB	| \
 			RTIT_CTL_MTC		| \
 			RTIT_CTL_PWR_EVT_EN	| \
@@ -332,6 +362,33 @@ static bool pt_event_valid(struct perf_event *event)
 			return false;
 	}
 
+	/*
+	 * Setting bit 0 (TraceEn in RTIT_CTL MSR) in the attr.config
+	 * clears the assomption that BranchEn must always be enabled,
+	 * as was the case with the first implementation of PT.
+	 * If this bit is not set, the legacy behavior is preserved
+	 * for compatibility with the older userspace.
+	 *
+	 * Re-using bit 0 for this purpose is fine because it is never
+	 * directly set by the user; previous attempts at setting it in
+	 * the attr.config resulted in -EINVAL.
+	 */
+	if (config & RTIT_CTL_PASSTHROUGH) {
+		/*
+		 * Disallow not setting BRANCH_EN where BRANCH_EN is
+		 * always required.
+		 */
+		if (pt_pmu.branch_en_always_on &&
+		    !(config & RTIT_CTL_BRANCH_EN))
+			return false;
+	} else {
+		/*
+		 * Disallow BRANCH_EN without the PASSTHROUGH.
+		 */
+		if (config & RTIT_CTL_BRANCH_EN)
+			return false;
+	}
+
 	return true;
 }
 
@@ -411,6 +468,7 @@ static u64 pt_config_filters(struct perf_event *event)
 
 static void pt_config(struct perf_event *event)
 {
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	u64 reg;
 
 	if (!event->hw.itrace_started) {
@@ -419,7 +477,20 @@ static void pt_config(struct perf_event *event)
 	}
 
 	reg = pt_config_filters(event);
-	reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
+	reg |= RTIT_CTL_TOPA | RTIT_CTL_TRACEEN;
+
+	/*
+	 * Previously, we had BRANCH_EN on by default, but now that PT has
+	 * grown features outside of branch tracing, it is useful to allow
+	 * the user to disable it. Setting bit 0 in the event's attr.config
+	 * allows BRANCH_EN to pass through instead of being always on. See
+	 * also the comment in pt_event_valid().
+	 */
+	if (event->attr.config & BIT(0)) {
+		reg |= event->attr.config & RTIT_CTL_BRANCH_EN;
+	} else {
+		reg |= RTIT_CTL_BRANCH_EN;
+	}
 
 	if (!event->attr.exclude_kernel)
 		reg |= RTIT_CTL_OS;
@@ -429,11 +500,15 @@ static void pt_config(struct perf_event *event)
 	reg |= (event->attr.config & PT_CONFIG_MASK);
 
 	event->hw.config = reg;
-	wrmsrl(MSR_IA32_RTIT_CTL, reg);
+	if (READ_ONCE(pt->vmx_on))
+		perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
+	else
+		wrmsrl(MSR_IA32_RTIT_CTL, reg);
 }
 
 static void pt_config_stop(struct perf_event *event)
 {
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	u64 ctl = READ_ONCE(event->hw.config);
 
 	/* may be already stopped by a PMI */
@@ -441,7 +516,8 @@ static void pt_config_stop(struct perf_event *event)
 		return;
 
 	ctl &= ~RTIT_CTL_TRACEEN;
-	wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+	if (!READ_ONCE(pt->vmx_on))
+		wrmsrl(MSR_IA32_RTIT_CTL, ctl);
 
 	WRITE_ONCE(event->hw.config, ctl);
 
@@ -753,7 +829,8 @@ static void pt_handle_status(struct pt *pt)
 		 */
 		if (!pt_cap_get(PT_CAP_topa_multiple_entries) ||
 		    buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
-			local_inc(&buf->lost);
+			perf_aux_output_flag(&pt->handle,
+			                     PERF_AUX_FLAG_TRUNCATED);
 			advance++;
 		}
 	}
@@ -846,8 +923,10 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 
 	/* can't stop in the middle of an output region */
 	if (buf->output_off + handle->size + 1 <
-	    sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size))
+	    sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 		return -EINVAL;
+	}
 
 
 	/* single entry ToPA is handled by marking all regions STOP=1 INT=1 */
@@ -1171,12 +1250,6 @@ void intel_pt_interrupt(void)
 	if (!READ_ONCE(pt->handle_nmi))
 		return;
 
-	/*
-	 * If VMX is on and PT does not support it, don't touch anything.
-	 */
-	if (READ_ONCE(pt->vmx_on))
-		return;
-
 	if (!event)
 		return;
 
@@ -1192,8 +1265,7 @@ void intel_pt_interrupt(void)
 
 	pt_update_head(pt);
 
-	perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
-			    local_xchg(&buf->lost, 0));
+	perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0));
 
 	if (!event->hw.state) {
 		int ret;
@@ -1208,7 +1280,7 @@ void intel_pt_interrupt(void)
 		/* snapshot counters don't use PMI, so it's safe */
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
 		if (ret) {
-			perf_aux_output_end(&pt->handle, 0, true);
+			perf_aux_output_end(&pt->handle, 0);
 			return;
 		}
 
@@ -1237,12 +1309,19 @@ void intel_pt_handle_vmx(int on)
 	local_irq_save(flags);
 	WRITE_ONCE(pt->vmx_on, on);
 
-	if (on) {
-		/* prevent pt_config_stop() from writing RTIT_CTL */
-		event = pt->handle.event;
-		if (event)
-			event->hw.config = 0;
-	}
+	/*
+	 * If an AUX transaction is in progress, it will contain
+	 * gap(s), so flag it PARTIAL to inform the user.
+	 */
+	event = pt->handle.event;
+	if (event)
+		perf_aux_output_flag(&pt->handle,
+		                     PERF_AUX_FLAG_PARTIAL);
+
+	/* Turn PTs back on */
+	if (!on && event)
+		wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config);
+
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);
@@ -1257,9 +1336,6 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf;
 
-	if (READ_ONCE(pt->vmx_on))
-		return;
-
 	buf = perf_aux_output_begin(&pt->handle, event);
 	if (!buf)
 		goto fail_stop;
@@ -1280,7 +1356,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 	return;
 
 fail_end_stop:
-	perf_aux_output_end(&pt->handle, 0, true);
+	perf_aux_output_end(&pt->handle, 0);
 fail_stop:
 	hwc->state = PERF_HES_STOPPED;
 }
@@ -1321,8 +1397,7 @@ static void pt_event_stop(struct perf_event *event, int mode)
 			pt->handle.head =
 				local_xchg(&buf->data_size,
 					   buf->nr_pages << PAGE_SHIFT);
-		perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
-				    local_xchg(&buf->lost, 0));
+		perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0));
 	}
 }
 
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 53473c21b554..0eb41d07b79a 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -110,6 +110,7 @@ struct pt_pmu {
 	struct pmu		pmu;
 	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
 	bool			vmx;
+	bool			branch_en_always_on;
 	unsigned long		max_nonturbo_ratio;
 	unsigned int		tsc_art_num;
 	unsigned int		tsc_art_den;
@@ -143,7 +144,6 @@ struct pt_buffer {
 	size_t			output_off;
 	unsigned long		nr_pages;
 	local_t			data_size;
-	local_t			lost;
 	local64_t		head;
 	bool			snapshot;
 	unsigned long		stop_pos, intr_pos;
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 22054ca49026..9d05c7e67f60 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -1,5 +1,5 @@
 /*
- * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Support Intel RAPL energy consumption counters
  * Copyright (C) 2013 Google, Inc., Stephane Eranian
  *
  * Intel RAPL interface is specified in the IA-32 Manual Vol3b
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index ad986c1e29bc..df5989f27b1b 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head;
 extern struct pci_extra_dev *uncore_extra_pci_dev;
 extern struct event_constraint uncore_constraint_empty;
 
-/* perf_event_intel_uncore_snb.c */
+/* uncore_snb.c */
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
@@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void);
 void skl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
-/* perf_event_intel_uncore_snbep.c */
+/* uncore_snbep.c */
 int snbep_uncore_pci_init(void);
 void snbep_uncore_cpu_init(void);
 int ivbep_uncore_pci_init(void);
@@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void);
 int skx_uncore_pci_init(void);
 void skx_uncore_cpu_init(void);
 
-/* perf_event_intel_uncore_nhmex.c */
+/* uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index bcbb1d2ae10b..be3d36254040 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -79,6 +79,7 @@ struct amd_nb {
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
+#define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
 
 /*
  * Flags PEBS can handle without an PMI.
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index db64baf0e500..2b01421f7d0f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -27,45 +27,22 @@
 #include <linux/clockchips.h>
 
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_HYPERV_TSCPAGE
 
 static struct ms_hyperv_tsc_page *tsc_pg;
 
+struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+	return tsc_pg;
+}
+
 static u64 read_hv_clock_tsc(struct clocksource *arg)
 {
-	u64 current_tick;
+	u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+	if (current_tick == U64_MAX)
+		rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
 
-	if (tsc_pg->tsc_sequence != 0) {
-		/*
-		 * Use the tsc page to compute the value.
-		 */
-
-		while (1) {
-			u64 tmp;
-			u32 sequence = tsc_pg->tsc_sequence;
-			u64 cur_tsc;
-			u64 scale = tsc_pg->tsc_scale;
-			s64 offset = tsc_pg->tsc_offset;
-
-			rdtscll(cur_tsc);
-			/* current_tick = ((cur_tsc *scale) >> 64) + offset */
-			asm("mulq %3"
-				: "=d" (current_tick), "=a" (tmp)
-				: "a" (cur_tsc), "r" (scale));
-
-			current_tick += offset;
-			if (tsc_pg->tsc_sequence == sequence)
-				return current_tick;
-
-			if (tsc_pg->tsc_sequence != 0)
-				continue;
-			/*
-			 * Fallback using MSR method.
-			 */
-			break;
-		}
-	}
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
 	return current_tick;
 }
 
@@ -139,7 +116,7 @@ void hyperv_init(void)
 	/*
 	 * Register Hyper-V specific clocksource.
 	 */
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_HYPERV_TSCPAGE
 	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
 		union hv_x64_msr_hypercall_contents tsc_msr;
 
@@ -155,16 +132,19 @@ void hyperv_init(void)
 		tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);
 
 		wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+
+		hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK;
+
 		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 		return;
 	}
+register_msr_cs:
 #endif
 	/*
 	 * For 32 bit guests just use the MSR based mechanism for reading
 	 * the partition counter.
 	 */
 
-register_msr_cs:
 	hyperv_cs = &hyperv_cs_msr;
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 395b69551fce..2efc768e4362 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -52,6 +52,8 @@ extern u8 acpi_sci_flags;
 extern int acpi_sci_override_gsi;
 void acpi_pic_sci_set_trigger(unsigned int, u16);
 
+struct device;
+
 extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
 				  int trigger, int polarity);
 extern void (*__acpi_unregister_gsi)(u32 gsi);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 730ef65e8393..bdffcd9eab2b 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -252,12 +252,6 @@ static inline int x2apic_enabled(void) { return 0; }
 #define	x2apic_supported()	(0)
 #endif /* !CONFIG_X86_X2APIC */
 
-#ifdef CONFIG_X86_64
-#define	SET_APIC_ID(x)		(apic->set_apic_id(x))
-#else
-
-#endif
-
 /*
  * Copyright 2004 James Cleverdon, IBM.
  * Subject to the GNU Public License, v.2
@@ -299,6 +293,7 @@ struct apic {
 	int (*phys_pkg_id)(int cpuid_apic, int index_msb);
 
 	unsigned int (*get_apic_id)(unsigned long x);
+	/* Can't be NULL on 64-bit */
 	unsigned long (*set_apic_id)(unsigned int id);
 
 	int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 14635c5ea025..caa5798c92f4 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -186,6 +186,12 @@ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return cmpxchg(&v->counter, old, new);
 }
 
+#define atomic_try_cmpxchg atomic_try_cmpxchg
+static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+{
+	return try_cmpxchg(&v->counter, old, new);
+}
+
 static inline int atomic_xchg(atomic_t *v, int new)
 {
 	return xchg(&v->counter, new);
@@ -201,16 +207,12 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 }
 
 #define ATOMIC_FETCH_OP(op, c_op)					\
-static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 {									\
-	int old, val = atomic_read(v);					\
-	for (;;) {							\
-		old = atomic_cmpxchg(v, val, val c_op i);		\
-		if (old == val)						\
-			break;						\
-		val = old;						\
-	}								\
-	return old;							\
+	int val = atomic_read(v);					\
+	do {								\
+	} while (!atomic_try_cmpxchg(v, &val, val c_op i));		\
+	return val;							\
 }
 
 #define ATOMIC_OPS(op, c_op)						\
@@ -236,16 +238,11 @@ ATOMIC_OPS(xor, ^)
  */
 static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
+	int c = atomic_read(v);
+	do {
+		if (unlikely(c == u))
 			break;
-		c = old;
-	}
+	} while (!atomic_try_cmpxchg(v, &c, c + a));
 	return c;
 }
 
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 89ed2f6ae2f7..6189a433c9a9 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -176,6 +176,12 @@ static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
 	return cmpxchg(&v->counter, old, new);
 }
 
+#define atomic64_try_cmpxchg atomic64_try_cmpxchg
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new)
+{
+	return try_cmpxchg(&v->counter, old, new);
+}
+
 static inline long atomic64_xchg(atomic64_t *v, long new)
 {
 	return xchg(&v->counter, new);
@@ -192,17 +198,12 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  */
 static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
 {
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
+	long c = atomic64_read(v);
+	do {
+		if (unlikely(c == u))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+	return true;
 }
 
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
@@ -216,17 +217,12 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
  */
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
+	long dec, c = atomic64_read(v);
+	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
+	} while (!atomic64_try_cmpxchg(v, &c, dec));
 	return dec;
 }
 
@@ -242,14 +238,10 @@ static inline void atomic64_##op(long i, atomic64_t *v)			\
 #define ATOMIC64_FETCH_OP(op, c_op)					\
 static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
 {									\
-	long old, val = atomic64_read(v);				\
-	for (;;) {							\
-		old = atomic64_cmpxchg(v, val, val c_op i);		\
-		if (old == val)						\
-			break;						\
-		val = old;						\
-	}								\
-	return old;							\
+	long val = atomic64_read(v);					\
+	do {								\
+	} while (!atomic64_try_cmpxchg(v, &val, val c_op i));		\
+	return val;							\
 }
 
 #define ATOMIC64_OPS(op, c_op)						\
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index ba38ebbaced3..39e702d90cdb 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -1,36 +1,82 @@
 #ifndef _ASM_X86_BUG_H
 #define _ASM_X86_BUG_H
 
-#define HAVE_ARCH_BUG
+#include <linux/stringify.h>
 
-#ifdef CONFIG_DEBUG_BUGVERBOSE
+/*
+ * Since some emulators terminate on UD2, we cannot use it for WARN.
+ * Since various instruction decoders disagree on the length of UD1,
+ * we cannot use it either. So use UD0 for WARN.
+ *
+ * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas
+ *  our kernel decoder thinks it takes a ModRM byte, which seems consistent
+ *  with various things like the Intel SDM instruction encoding rules)
+ */
+
+#define ASM_UD0		".byte 0x0f, 0xff"
+#define ASM_UD1		".byte 0x0f, 0xb9" /* + ModRM */
+#define ASM_UD2		".byte 0x0f, 0x0b"
+
+#define INSN_UD0	0xff0f
+#define INSN_UD2	0x0b0f
+
+#define LEN_UD0		2
+
+#ifdef CONFIG_GENERIC_BUG
 
 #ifdef CONFIG_X86_32
-# define __BUG_C0	"2:\t.long 1b, %c0\n"
+# define __BUG_REL(val)	".long " __stringify(val)
 #else
-# define __BUG_C0	"2:\t.long 1b - 2b, %c0 - 2b\n"
+# define __BUG_REL(val)	".long " __stringify(val) " - 2b"
 #endif
 
-#define BUG()							\
-do {								\
-	asm volatile("1:\tud2\n"				\
-		     ".pushsection __bug_table,\"a\"\n"		\
-		     __BUG_C0					\
-		     "\t.word %c1, 0\n"				\
-		     "\t.org 2b+%c2\n"				\
-		     ".popsection"				\
-		     : : "i" (__FILE__), "i" (__LINE__),	\
-		     "i" (sizeof(struct bug_entry)));		\
-	unreachable();						\
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+#define _BUG_FLAGS(ins, flags)						\
+do {									\
+	asm volatile("1:\t" ins "\n"					\
+		     ".pushsection __bug_table,\"a\"\n"			\
+		     "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n"	\
+		     "\t"  __BUG_REL(%c0) "\t# bug_entry::file\n"	\
+		     "\t.word %c1"        "\t# bug_entry::line\n"	\
+		     "\t.word %c2"        "\t# bug_entry::flags\n"	\
+		     "\t.org 2b+%c3\n"					\
+		     ".popsection"					\
+		     : : "i" (__FILE__), "i" (__LINE__),		\
+			 "i" (flags),					\
+			 "i" (sizeof(struct bug_entry)));		\
 } while (0)
 
+#else /* !CONFIG_DEBUG_BUGVERBOSE */
+
+#define _BUG_FLAGS(ins, flags)						\
+do {									\
+	asm volatile("1:\t" ins "\n"					\
+		     ".pushsection __bug_table,\"a\"\n"			\
+		     "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n"	\
+		     "\t.word %c0"        "\t# bug_entry::flags\n"	\
+		     "\t.org 2b+%c1\n"					\
+		     ".popsection"					\
+		     : : "i" (flags),					\
+			 "i" (sizeof(struct bug_entry)));		\
+} while (0)
+
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
 #else
+
+#define _BUG_FLAGS(ins, flags)  asm volatile(ins)
+
+#endif /* CONFIG_GENERIC_BUG */
+
+#define HAVE_ARCH_BUG
 #define BUG()							\
 do {								\
-	asm volatile("ud2");					\
+	_BUG_FLAGS(ASM_UD2, 0);					\
 	unreachable();						\
 } while (0)
-#endif
+
+#define __WARN_FLAGS(flags)	_BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags))
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index eae33c7170c8..47bea8cadbd0 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -6,7 +6,8 @@
 #define VCLOCK_NONE	0	/* No vDSO clock available.		*/
 #define VCLOCK_TSC	1	/* vDSO should use vread_tsc.		*/
 #define VCLOCK_PVCLOCK	2	/* vDSO should use vread_pvclock.	*/
-#define VCLOCK_MAX	2
+#define VCLOCK_HVCLOCK	3	/* vDSO should use vread_hvclock.	*/
+#define VCLOCK_MAX	3
 
 struct arch_clocksource_data {
 	int vclock_mode;
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 97848cdfcb1a..d90296d061e8 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -153,6 +153,76 @@ extern void __add_wrong_size(void)
 #define cmpxchg_local(ptr, old, new)					\
 	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 
+
+#define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock)		\
+({									\
+	bool success;							\
+	__typeof__(_ptr) _old = (_pold);				\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	switch (size) {							\
+	case __X86_CASE_B:						\
+	{								\
+		volatile u8 *__ptr = (volatile u8 *)(_ptr);		\
+		asm volatile(lock "cmpxchgb %[new], %[ptr]"		\
+			     CC_SET(z)					\
+			     : CC_OUT(z) (success),			\
+			       [ptr] "+m" (*__ptr),			\
+			       [old] "+a" (__old)			\
+			     : [new] "q" (__new)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_W:						\
+	{								\
+		volatile u16 *__ptr = (volatile u16 *)(_ptr);		\
+		asm volatile(lock "cmpxchgw %[new], %[ptr]"		\
+			     CC_SET(z)					\
+			     : CC_OUT(z) (success),			\
+			       [ptr] "+m" (*__ptr),			\
+			       [old] "+a" (__old)			\
+			     : [new] "r" (__new)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_L:						\
+	{								\
+		volatile u32 *__ptr = (volatile u32 *)(_ptr);		\
+		asm volatile(lock "cmpxchgl %[new], %[ptr]"		\
+			     CC_SET(z)					\
+			     : CC_OUT(z) (success),			\
+			       [ptr] "+m" (*__ptr),			\
+			       [old] "+a" (__old)			\
+			     : [new] "r" (__new)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_Q:						\
+	{								\
+		volatile u64 *__ptr = (volatile u64 *)(_ptr);		\
+		asm volatile(lock "cmpxchgq %[new], %[ptr]"		\
+			     CC_SET(z)					\
+			     : CC_OUT(z) (success),			\
+			       [ptr] "+m" (*__ptr),			\
+			       [old] "+a" (__old)			\
+			     : [new] "r" (__new)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	default:							\
+		__cmpxchg_wrong_size();					\
+	}								\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);						\
+})
+
+#define __try_cmpxchg(ptr, pold, new, size)				\
+	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+
+#define try_cmpxchg(ptr, pold, new)					\
+	__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+
 /*
  * xadd() adds "inc" to "*ptr" and atomically returns the previous
  * value of "*ptr".
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4e7772387c6e..2701e5f8145b 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -187,6 +187,7 @@
  * Reuse free bits when adding new feature flags!
  */
 #define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
 #define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -201,6 +202,8 @@
 #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
+#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
@@ -289,7 +292,8 @@
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
 #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
+#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 29e53ea7d764..ed8b66de541f 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -125,16 +125,6 @@ static inline void le128_inc(le128 *i)
 	i->b = cpu_to_le64(b);
 }
 
-static inline void le128_gf128mul_x_ble(le128 *dst, const le128 *src)
-{
-	u64 a = le64_to_cpu(src->a);
-	u64 b = le64_to_cpu(src->b);
-	u64 _tt = ((s64)a >> 63) & 0x87;
-
-	dst->a = cpu_to_le64((a << 1) ^ (b >> 63));
-	dst->b = cpu_to_le64((b << 1) ^ _tt);
-}
-
 extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
 				 struct blkcipher_desc *desc,
 				 struct scatterlist *dst,
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 1548ca92ad3f..d0a21b12dd58 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -4,6 +4,7 @@
 #include <asm/desc_defs.h>
 #include <asm/ldt.h>
 #include <asm/mmu.h>
+#include <asm/fixmap.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
@@ -45,11 +46,43 @@ struct gdt_page {
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
-static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
+/* Provide the original GDT */
+static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
 {
 	return per_cpu(gdt_page, cpu).gdt;
 }
 
+/* Provide the current original GDT */
+static inline struct desc_struct *get_current_gdt_rw(void)
+{
+	return this_cpu_ptr(&gdt_page)->gdt;
+}
+
+/* Get the fixmap index for a specific processor */
+static inline unsigned int get_cpu_gdt_ro_index(int cpu)
+{
+	return FIX_GDT_REMAP_BEGIN + cpu;
+}
+
+/* Provide the fixmap address of the remapped GDT */
+static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
+{
+	unsigned int idx = get_cpu_gdt_ro_index(cpu);
+	return (struct desc_struct *)__fix_to_virt(idx);
+}
+
+/* Provide the current read-only GDT */
+static inline struct desc_struct *get_current_gdt_ro(void)
+{
+	return get_cpu_gdt_ro(smp_processor_id());
+}
+
+/* Provide the physical address of the GDT page. */
+static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu)
+{
+	return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu));
+}
+
 #ifdef CONFIG_X86_64
 
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
@@ -174,7 +207,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned t
 
 static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
 {
-	struct desc_struct *d = get_cpu_gdt_table(cpu);
+	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 
 	set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS,
@@ -194,22 +227,90 @@ static inline void native_set_ldt(const void *addr, unsigned int entries)
 
 		set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
 				      entries * LDT_ENTRY_SIZE - 1);
-		write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
+		write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT,
 				&ldt, DESC_LDT);
 		asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
 	}
 }
 
+static inline void native_load_gdt(const struct desc_ptr *dtr)
+{
+	asm volatile("lgdt %0"::"m" (*dtr));
+}
+
+static inline void native_load_idt(const struct desc_ptr *dtr)
+{
+	asm volatile("lidt %0"::"m" (*dtr));
+}
+
+static inline void native_store_gdt(struct desc_ptr *dtr)
+{
+	asm volatile("sgdt %0":"=m" (*dtr));
+}
+
+static inline void native_store_idt(struct desc_ptr *dtr)
+{
+	asm volatile("sidt %0":"=m" (*dtr));
+}
+
+/*
+ * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is
+ * a read-only remapping. To prevent a page fault, the GDT is switched to the
+ * original writeable version when needed.
+ */
+#ifdef CONFIG_X86_64
+static inline void native_load_tr_desc(void)
+{
+	struct desc_ptr gdt;
+	int cpu = raw_smp_processor_id();
+	bool restore = 0;
+	struct desc_struct *fixmap_gdt;
+
+	native_store_gdt(&gdt);
+	fixmap_gdt = get_cpu_gdt_ro(cpu);
+
+	/*
+	 * If the current GDT is the read-only fixmap, swap to the original
+	 * writeable version. Swap back at the end.
+	 */
+	if (gdt.address == (unsigned long)fixmap_gdt) {
+		load_direct_gdt(cpu);
+		restore = 1;
+	}
+	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
+	if (restore)
+		load_fixmap_gdt(cpu);
+}
+#else
 static inline void native_load_tr_desc(void)
 {
 	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
 }
+#endif
+
+static inline unsigned long native_store_tr(void)
+{
+	unsigned long tr;
+
+	asm volatile("str %0":"=r" (tr));
+
+	return tr;
+}
+
+static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+	struct desc_struct *gdt = get_cpu_gdt_rw(cpu);
+	unsigned int i;
+
+	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
+}
 
 DECLARE_PER_CPU(bool, __tss_limit_invalid);
 
 static inline void force_reload_TR(void)
 {
-	struct desc_struct *d = get_cpu_gdt_table(smp_processor_id());
+	struct desc_struct *d = get_current_gdt_rw();
 	tss_desc tss;
 
 	memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc));
@@ -257,44 +358,6 @@ static inline void invalidate_tss_limit(void)
 		this_cpu_write(__tss_limit_invalid, true);
 }
 
-static inline void native_load_gdt(const struct desc_ptr *dtr)
-{
-	asm volatile("lgdt %0"::"m" (*dtr));
-}
-
-static inline void native_load_idt(const struct desc_ptr *dtr)
-{
-	asm volatile("lidt %0"::"m" (*dtr));
-}
-
-static inline void native_store_gdt(struct desc_ptr *dtr)
-{
-	asm volatile("sgdt %0":"=m" (*dtr));
-}
-
-static inline void native_store_idt(struct desc_ptr *dtr)
-{
-	asm volatile("sidt %0":"=m" (*dtr));
-}
-
-static inline unsigned long native_store_tr(void)
-{
-	unsigned long tr;
-
-	asm volatile("str %0":"=r" (tr));
-
-	return tr;
-}
-
-static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
-	unsigned int i;
-
-	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
-		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
-}
-
 /* This intentionally ignores lm, since 32-bit apps don't have that field. */
 #define LDT_empty(info)					\
 	((info)->base_addr		== 0	&&	\
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 85599ad4d024..5dff775af7cd 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -36,6 +36,12 @@
 # define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
 #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
 
+#ifdef CONFIG_X86_5LEVEL
+# define DISABLE_LA57	0
+#else
+# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -55,7 +61,7 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
deleted file mode 100644
index 67313f3a9874..000000000000
--- a/arch/x86/include/asm/e820.h
+++ /dev/null
@@ -1,73 +0,0 @@
-#ifndef _ASM_X86_E820_H
-#define _ASM_X86_E820_H
-
-/*
- * E820_X_MAX is the maximum size of the extended E820 table.  The extended
- * table may contain up to 3 extra E820 entries per possible NUMA node, so we
- * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128.
- * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h.
- */
-#include <linux/numa.h>
-#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
-
-#include <uapi/asm/e820.h>
-
-#ifndef __ASSEMBLY__
-/* see comment in arch/x86/kernel/e820.c */
-extern struct e820map *e820;
-extern struct e820map *e820_saved;
-
-extern unsigned long pci_mem_start;
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern int e820_all_mapped(u64 start, u64 end, unsigned type);
-extern void e820_add_region(u64 start, u64 size, int type);
-extern void e820_print_map(char *who);
-extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
-extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
-			       unsigned new_type);
-extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
-			     int checktype);
-extern void update_e820(void);
-extern void e820_setup_gap(void);
-struct setup_data;
-extern void parse_e820_ext(u64 phys_addr, u32 data_len);
-
-#if defined(CONFIG_X86_64) || \
-	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-extern void e820_mark_nosave_regions(unsigned long limit_pfn);
-#else
-static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
-{
-}
-#endif
-
-extern unsigned long e820_end_of_ram_pfn(void);
-extern unsigned long e820_end_of_low_ram_pfn(void);
-extern u64 early_reserve_e820(u64 sizet, u64 align);
-
-void memblock_x86_fill(void);
-void memblock_find_dma_reserve(void);
-
-extern void finish_e820_parsing(void);
-extern void e820_reserve_resources(void);
-extern void e820_reserve_resources_late(void);
-extern void setup_memory_map(void);
-extern char *default_machine_specific_memory_setup(void);
-
-extern void e820_reallocate_tables(void);
-
-/*
- * Returns true iff the specified range [s,e) is completely contained inside
- * the ISA region.
- */
-static inline bool is_ISA_range(u64 s, u64 e)
-{
-	return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
-}
-
-#endif /* __ASSEMBLY__ */
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY	(1024*1024)
-#endif /* _ASM_X86_E820_H */
diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
new file mode 100644
index 000000000000..8e0f8b85b209
--- /dev/null
+++ b/arch/x86/include/asm/e820/api.h
@@ -0,0 +1,50 @@
+#ifndef _ASM_E820_API_H
+#define _ASM_E820_API_H
+
+#include <asm/e820/types.h>
+
+extern struct e820_table *e820_table;
+extern struct e820_table *e820_table_firmware;
+
+extern unsigned long pci_mem_start;
+
+extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type);
+extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
+
+extern void e820__range_add   (u64 start, u64 size, enum e820_type type);
+extern u64  e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
+extern u64  e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+
+extern void e820__print_table(char *who);
+extern int  e820__update_table(struct e820_table *table);
+extern void e820__update_table_print(void);
+
+extern unsigned long e820__end_of_ram_pfn(void);
+extern unsigned long e820__end_of_low_ram_pfn(void);
+
+extern u64  e820__memblock_alloc_reserved(u64 size, u64 align);
+extern void e820__memblock_setup(void);
+
+extern void e820__reserve_setup_data(void);
+extern void e820__finish_early_params(void);
+extern void e820__reserve_resources(void);
+extern void e820__reserve_resources_late(void);
+
+extern void e820__memory_setup(void);
+extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len);
+extern char *e820__memory_setup_default(void);
+extern void e820__setup_pci_gap(void);
+
+extern void e820__reallocate_tables(void);
+extern void e820__register_nosave_regions(unsigned long limit_pfn);
+
+/*
+ * Returns true iff the specified range [start,end) is completely contained inside
+ * the ISA region.
+ */
+static inline bool is_ISA_range(u64 start, u64 end)
+{
+	return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS;
+}
+
+#endif /* _ASM_E820_API_H */
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
new file mode 100644
index 000000000000..4adeed03a9a1
--- /dev/null
+++ b/arch/x86/include/asm/e820/types.h
@@ -0,0 +1,104 @@
+#ifndef _ASM_E820_TYPES_H
+#define _ASM_E820_TYPES_H
+
+#include <uapi/asm/bootparam.h>
+
+/*
+ * These are the E820 types known to the kernel:
+ */
+enum e820_type {
+	E820_TYPE_RAM		= 1,
+	E820_TYPE_RESERVED	= 2,
+	E820_TYPE_ACPI		= 3,
+	E820_TYPE_NVS		= 4,
+	E820_TYPE_UNUSABLE	= 5,
+	E820_TYPE_PMEM		= 7,
+
+	/*
+	 * This is a non-standardized way to represent ADR or
+	 * NVDIMM regions that persist over a reboot.
+	 *
+	 * The kernel will ignore their special capabilities
+	 * unless the CONFIG_X86_PMEM_LEGACY=y option is set.
+	 *
+	 * ( Note that older platforms also used 6 for the same
+	 *   type of memory, but newer versions switched to 12 as
+	 *   6 was assigned differently. Some time they will learn... )
+	 */
+	E820_TYPE_PRAM		= 12,
+
+	/*
+	 * Reserved RAM used by the kernel itself if
+	 * CONFIG_INTEL_TXT=y is enabled, memory of this type
+	 * will be included in the S3 integrity calculation
+	 * and so should not include any memory that the BIOS
+	 * might alter over the S3 transition:
+	 */
+	E820_TYPE_RESERVED_KERN	= 128,
+};
+
+/*
+ * A single E820 map entry, describing a memory range of [addr...addr+size-1],
+ * of 'type' memory type:
+ *
+ * (We pack it because there can be thousands of them on large systems.)
+ */
+struct e820_entry {
+	u64			addr;
+	u64			size;
+	enum e820_type		type;
+} __attribute__((packed));
+
+/*
+ * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes
+ * due to the constrained space in the zeropage.
+ *
+ * On large systems we can easily have thousands of nodes with RAM,
+ * which cannot be fit into so few entries - so we have a mechanism
+ * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES
+ * define below.
+ *
+ * ( Those extra entries are enumerated via the EFI memory map, not
+ *   via the legacy zeropage mechanism. )
+ *
+ * Size our internal memory map tables to have room for these additional
+ * entries, based on a heuristic calculation: up to three entries per
+ * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space.
+ *
+ * This allows for bootstrap/firmware quirks such as possible duplicate
+ * E820 entries that might need room in the same arrays, prior to the
+ * call to e820__update_table() to remove duplicates.  The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries.  Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+#include <linux/numa.h>
+
+#define E820_MAX_ENTRIES	(E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES)
+
+/*
+ * The whole array of E820 entries:
+ */
+struct e820_table {
+	__u32 nr_entries;
+	struct e820_entry entries[E820_MAX_ENTRIES];
+};
+
+/*
+ * Various well-known legacy memory ranges in physical memory:
+ */
+#define ISA_START_ADDRESS	0x000a0000
+#define ISA_END_ADDRESS		0x00100000
+
+#define BIOS_BEGIN		0x000a0000
+#define BIOS_END		0x00100000
+
+#define HIGH_MEMORY		0x00100000
+
+#define BIOS_ROM_BASE		0xffe00000
+#define BIOS_ROM_END		0xffffffff
+
+#endif /* _ASM_E820_TYPES_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9d49c18b5ea9..e8ab9a46bc68 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -287,14 +287,29 @@ struct task_struct;
 
 #define	ARCH_DLINFO_IA32						\
 do {									\
-	if (vdso32_enabled) {						\
+	if (VDSO_CURRENT_BASE) {					\
 		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
 	}								\
 } while (0)
 
+/*
+ * True on X86_32 or when emulating IA32 on X86_64
+ */
+static inline int mmap_is_ia32(void)
+{
+	return IS_ENABLED(CONFIG_X86_32) ||
+	       (IS_ENABLED(CONFIG_COMPAT) &&
+		test_thread_flag(TIF_ADDR32));
+}
+
+extern unsigned long tasksize_32bit(void);
+extern unsigned long tasksize_64bit(void);
+extern unsigned long get_mmap_base(int is_legacy);
+
 #ifdef CONFIG_X86_32
 
+#define __STACK_RND_MASK(is32bit) (0x7ff)
 #define STACK_RND_MASK (0x7ff)
 
 #define ARCH_DLINFO		ARCH_DLINFO_IA32
@@ -304,7 +319,8 @@ do {									\
 #else /* CONFIG_X86_32 */
 
 /* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
+#define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32())
 
 #define ARCH_DLINFO							\
 do {									\
@@ -348,16 +364,6 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 					      int uses_interp);
 #define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
 
-/*
- * True on X86_32 or when emulating IA32 on X86_64
- */
-static inline int mmap_is_ia32(void)
-{
-	return IS_ENABLED(CONFIG_X86_32) ||
-	       (IS_ENABLED(CONFIG_COMPAT) &&
-		test_thread_flag(TIF_ADDR32));
-}
-
 /* Do not change the values. See get_align_mask() */
 enum align_flags {
 	ALIGN_VA_32	= BIT(0),
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 8554f960e21b..b65155cc3760 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -100,6 +100,10 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
+	/* Fixmap entries to remap the GDTs, one per processor. */
+	FIX_GDT_REMAP_BEGIN,
+	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
+
 	__end_of_permanent_fixed_addresses,
 
 	/*
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 156cd5d18d2a..1d268098ac2e 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_GART_H
 #define _ASM_X86_GART_H
 
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 
 extern void set_up_gart_resume(u32, u32);
 
@@ -97,7 +97,7 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 		printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
 		return 0;
 	}
-	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+	if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) {
 		printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
 		return 0;
 	}
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 9814db42b790..75b748a1deb8 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -12,6 +12,7 @@
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
+
 #define INTEL_FAM6_CORE2_MEROM		0x0F
 #define INTEL_FAM6_CORE2_MEROM_L	0x16
 #define INTEL_FAM6_CORE2_PENRYN		0x17
@@ -21,6 +22,7 @@
 #define INTEL_FAM6_NEHALEM_G		0x1F /* Auburndale / Havendale */
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
+
 #define INTEL_FAM6_WESTMERE		0x25
 #define INTEL_FAM6_WESTMERE_EP		0x2C
 #define INTEL_FAM6_WESTMERE_EX		0x2F
@@ -36,9 +38,9 @@
 #define INTEL_FAM6_HASWELL_GT3E		0x46
 
 #define INTEL_FAM6_BROADWELL_CORE	0x3D
-#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 #define INTEL_FAM6_BROADWELL_GT3E	0x47
 #define INTEL_FAM6_BROADWELL_X		0x4F
+#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 
 #define INTEL_FAM6_SKYLAKE_MOBILE	0x4E
 #define INTEL_FAM6_SKYLAKE_DESKTOP	0x5E
@@ -59,8 +61,8 @@
 #define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
 #define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
-#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
+#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
 
 /* Xeon Phi */
 
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 0d64397cee58..597dc4995678 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -12,6 +12,7 @@
 #define IA32_L3_QOS_CFG		0xc81
 #define IA32_L3_CBM_BASE	0xc90
 #define IA32_L2_CBM_BASE	0xd10
+#define IA32_MBA_THRTL_BASE	0xd50
 
 #define L3_QOS_CDP_ENABLE	0x01ULL
 
@@ -37,23 +38,30 @@ struct rdtgroup {
 /* rdtgroup.flags */
 #define	RDT_DELETED		1
 
+/* rftype.flags */
+#define RFTYPE_FLAGS_CPUS_LIST	1
+
 /* List of all resource groups */
 extern struct list_head rdt_all_groups;
 
+extern int max_name_width, max_data_width;
+
 int __init rdtgroup_init(void);
 
 /**
  * struct rftype - describe each file in the resctrl file system
- * @name: file name
- * @mode: access mode
- * @kf_ops: operations
- * @seq_show: show content of the file
- * @write: write to the file
+ * @name:	File name
+ * @mode:	Access mode
+ * @kf_ops:	File operations
+ * @flags:	File specific RFTYPE_FLAGS_* flags
+ * @seq_show:	Show content of the file
+ * @write:	Write to the file
  */
 struct rftype {
 	char			*name;
 	umode_t			mode;
 	struct kernfs_ops	*kf_ops;
+	unsigned long		flags;
 
 	int (*seq_show)(struct kernfs_open_file *of,
 			struct seq_file *sf, void *v);
@@ -67,54 +75,21 @@ struct rftype {
 };
 
 /**
- * struct rdt_resource - attributes of an RDT resource
- * @enabled:			Is this feature enabled on this machine
- * @capable:			Is this feature available on this machine
- * @name:			Name to use in "schemata" file
- * @num_closid:			Number of CLOSIDs available
- * @max_cbm:			Largest Cache Bit Mask allowed
- * @min_cbm_bits:		Minimum number of consecutive bits to be set
- *				in a cache bit mask
- * @domains:			All domains for this resource
- * @num_domains:		Number of domains active
- * @msr_base:			Base MSR address for CBMs
- * @tmp_cbms:			Scratch space when updating schemata
- * @num_tmp_cbms:		Number of CBMs in tmp_cbms
- * @cache_level:		Which cache level defines scope of this domain
- * @cbm_idx_multi:		Multiplier of CBM index
- * @cbm_idx_offset:		Offset of CBM index. CBM index is computed by:
- *				closid * cbm_idx_multi + cbm_idx_offset
- */
-struct rdt_resource {
-	bool			enabled;
-	bool			capable;
-	char			*name;
-	int			num_closid;
-	int			cbm_len;
-	int			min_cbm_bits;
-	u32			max_cbm;
-	struct list_head	domains;
-	int			num_domains;
-	int			msr_base;
-	u32			*tmp_cbms;
-	int			num_tmp_cbms;
-	int			cache_level;
-	int			cbm_idx_multi;
-	int			cbm_idx_offset;
-};
-
-/**
  * struct rdt_domain - group of cpus sharing an RDT resource
  * @list:	all instances of this resource
  * @id:		unique id for this instance
  * @cpu_mask:	which cpus share this resource
- * @cbm:	array of cache bit masks (indexed by CLOSID)
+ * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
+ * @new_ctrl:	new ctrl value to be loaded
+ * @have_new_ctrl: did user provide new_ctrl for this domain
  */
 struct rdt_domain {
 	struct list_head	list;
 	int			id;
 	struct cpumask		cpu_mask;
-	u32			*cbm;
+	u32			*ctrl_val;
+	u32			new_ctrl;
+	bool			have_new_ctrl;
 };
 
 /**
@@ -129,6 +104,83 @@ struct msr_param {
 	int			high;
 };
 
+/**
+ * struct rdt_cache - Cache allocation related data
+ * @cbm_len:		Length of the cache bit mask
+ * @min_cbm_bits:	Minimum number of consecutive bits to be set
+ * @cbm_idx_mult:	Multiplier of CBM index
+ * @cbm_idx_offset:	Offset of CBM index. CBM index is computed by:
+ *			closid * cbm_idx_multi + cbm_idx_offset
+ *			in a cache bit mask
+ */
+struct rdt_cache {
+	unsigned int	cbm_len;
+	unsigned int	min_cbm_bits;
+	unsigned int	cbm_idx_mult;
+	unsigned int	cbm_idx_offset;
+};
+
+/**
+ * struct rdt_membw - Memory bandwidth allocation related data
+ * @max_delay:		Max throttle delay. Delay is the hardware
+ *			representation for memory bandwidth.
+ * @min_bw:		Minimum memory bandwidth percentage user can request
+ * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @delay_linear:	True if memory B/W delay is in linear scale
+ * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
+ */
+struct rdt_membw {
+	u32		max_delay;
+	u32		min_bw;
+	u32		bw_gran;
+	u32		delay_linear;
+	u32		*mb_map;
+};
+
+/**
+ * struct rdt_resource - attributes of an RDT resource
+ * @enabled:		Is this feature enabled on this machine
+ * @capable:		Is this feature available on this machine
+ * @name:		Name to use in "schemata" file
+ * @num_closid:		Number of CLOSIDs available
+ * @cache_level:	Which cache level defines scope of this resource
+ * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
+ * @msr_base:		Base MSR address for CBMs
+ * @msr_update:		Function pointer to update QOS MSRs
+ * @data_width:		Character width of data when displaying
+ * @domains:		All domains for this resource
+ * @cache:		Cache allocation related data
+ * @info_files:		resctrl info files for the resource
+ * @nr_info_files:	Number of info files
+ * @format_str:		Per resource format string to show domain value
+ * @parse_ctrlval:	Per resource function pointer to parse control values
+ */
+struct rdt_resource {
+	bool			enabled;
+	bool			capable;
+	char			*name;
+	int			num_closid;
+	int			cache_level;
+	u32			default_ctrl;
+	unsigned int		msr_base;
+	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
+				 struct rdt_resource *r);
+	int			data_width;
+	struct list_head	domains;
+	struct rdt_cache	cache;
+	struct rdt_membw	membw;
+	struct rftype		*info_files;
+	int			nr_info_files;
+	const char		*format_str;
+	int (*parse_ctrlval)	(char *buf, struct rdt_resource *r,
+				 struct rdt_domain *d);
+};
+
+void rdt_get_cache_infofile(struct rdt_resource *r);
+void rdt_get_mba_infofile(struct rdt_resource *r);
+int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(char *buf, struct rdt_resource *r,  struct rdt_domain *d);
+
 extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_resource rdt_resources_all[];
@@ -142,6 +194,7 @@ enum {
 	RDT_RESOURCE_L3DATA,
 	RDT_RESOURCE_L3CODE,
 	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
 
 	/* Must be the last */
 	RDT_NUM_RESOURCES,
@@ -149,7 +202,7 @@ enum {
 
 #define for_each_capable_rdt_resource(r)				      \
 	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
-	     r++) 							      \
+	     r++)							      \
 		if (r->capable)
 
 #define for_each_enabled_rdt_resource(r)				      \
@@ -165,8 +218,16 @@ union cpuid_0x10_1_eax {
 	unsigned int full;
 };
 
-/* CPUID.(EAX=10H, ECX=ResID=1).EDX */
-union cpuid_0x10_1_edx {
+/* CPUID.(EAX=10H, ECX=ResID=3).EAX */
+union cpuid_0x10_3_eax {
+	struct {
+		unsigned int max_delay:12;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID).EDX */
+union cpuid_0x10_x_edx {
 	struct {
 		unsigned int cos_max:16;
 	} split;
@@ -175,7 +236,7 @@ union cpuid_0x10_1_edx {
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid);
 
-void rdt_cbm_update(void *arg);
+void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 1410b567ecde..f527b02a0ee3 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -11,9 +11,12 @@
  * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT
  */
 #define KASAN_SHADOW_START      (KASAN_SHADOW_OFFSET + \
-					(0xffff800000000000ULL >> 3))
-/* 47 bits for kernel address -> (47 - 3) bits for shadow */
-#define KASAN_SHADOW_END        (KASAN_SHADOW_START + (1ULL << (47 - 3)))
+					((-1UL << __VIRTUAL_MASK_SHIFT) >> 3))
+/*
+ * 47 bits for kernel address -> (47 - 3) bits for shadow
+ * 56 bits for kernel address -> (56 - 3) bits for shadow
+ */
+#define KASAN_SHADOW_END        (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3)))
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 282630e4c6ea..70ef205489f0 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -164,6 +164,7 @@ struct kimage_arch {
 };
 #else
 struct kimage_arch {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 200581691c6e..34b984c60790 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -72,14 +72,13 @@ struct arch_specific_insn {
 	/* copy of the original instruction */
 	kprobe_opcode_t *insn;
 	/*
-	 * boostable = -1: This instruction type is not boostable.
-	 * boostable = 0: This instruction type is boostable.
-	 * boostable = 1: This instruction has been boosted: we have
+	 * boostable = false: This instruction type is not boostable.
+	 * boostable = true: This instruction has been boosted: we have
 	 * added a relative jump after the instruction copy in insn,
 	 * so no single-step and fixup are needed (unless there's
 	 * a post_handler or break_handler).
 	 */
-	int boostable;
+	bool boostable;
 	bool if_modifier;
 };
 
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b031ec..c4eda791f877 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
 };
 
 void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
 				 struct kvm_memory_slot *dont);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index e63873683d4a..4fd5195deed0 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -128,7 +128,7 @@
  * debugging tools.  Each entry is only valid when its finished flag
  * is set.
  */
-struct mce_log {
+struct mce_log_buffer {
 	char signature[12]; /* "MACHINECHECK" */
 	unsigned len;	    /* = MCE_LOG_LEN */
 	unsigned next;
@@ -191,10 +191,12 @@ extern struct mca_config mca_cfg;
 extern struct mca_msr_regs msr_ops;
 
 enum mce_notifier_prios {
-	MCE_PRIO_SRAO		= INT_MAX,
-	MCE_PRIO_EXTLOG		= INT_MAX - 1,
-	MCE_PRIO_NFIT		= INT_MAX - 2,
-	MCE_PRIO_EDAC		= INT_MAX - 3,
+	MCE_PRIO_FIRST		= INT_MAX,
+	MCE_PRIO_SRAO		= INT_MAX - 1,
+	MCE_PRIO_EXTLOG		= INT_MAX - 2,
+	MCE_PRIO_NFIT		= INT_MAX - 3,
+	MCE_PRIO_EDAC		= INT_MAX - 4,
+	MCE_PRIO_MCELOG		= 1,
 	MCE_PRIO_LOWEST		= 0,
 };
 
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 306c7e12af55..68b329d77b3a 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -268,8 +268,4 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	return __pkru_allows_pkey(vma_pkey(vma), write);
 }
 
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
-	return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write);
-}
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 32007041ef8c..831eb7895535 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -64,7 +64,7 @@ static inline void find_smp_config(void)
 }
 
 #ifdef CONFIG_X86_MPPARSE
-extern void early_reserve_e820_mpc_new(void);
+extern void e820__memblock_alloc_reserved_mpc_new(void);
 extern int enable_update_mptable;
 extern int default_mpc_apic_id(struct mpc_cpu *m);
 extern void default_smp_read_mpc_oem(struct mpc_table *mpc);
@@ -76,7 +76,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
 extern void default_find_smp_config(void);
 extern void default_get_smp_config(unsigned int early);
 #else
-static inline void early_reserve_e820_mpc_new(void) { }
+static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
 #define enable_update_mptable 0
 #define default_mpc_apic_id NULL
 #define default_smp_read_mpc_oem NULL
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 7c9c895432a9..fba100713924 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -176,4 +176,58 @@ void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);
 void hyperv_cleanup(void);
 #endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+	u64 scale, offset, cur_tsc;
+	u32 sequence;
+
+	/*
+	 * The protocol for reading Hyper-V TSC page is specified in Hypervisor
+	 * Top-Level Functional Specification ver. 3.0 and above. To get the
+	 * reference time we must do the following:
+	 * - READ ReferenceTscSequence
+	 *   A special '0' value indicates the time source is unreliable and we
+	 *   need to use something else. The currently published specification
+	 *   versions (up to 4.0b) contain a mistake and wrongly claim '-1'
+	 *   instead of '0' as the special value, see commit c35b82ef0294.
+	 * - ReferenceTime =
+	 *        ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset
+	 * - READ ReferenceTscSequence again. In case its value has changed
+	 *   since our first reading we need to discard ReferenceTime and repeat
+	 *   the whole sequence as the hypervisor was updating the page in
+	 *   between.
+	 */
+	do {
+		sequence = READ_ONCE(tsc_pg->tsc_sequence);
+		if (!sequence)
+			return U64_MAX;
+		/*
+		 * Make sure we read sequence before we read other values from
+		 * TSC page.
+		 */
+		smp_rmb();
+
+		scale = READ_ONCE(tsc_pg->tsc_scale);
+		offset = READ_ONCE(tsc_pg->tsc_offset);
+		cur_tsc = rdtsc_ordered();
+
+		/*
+		 * Make sure we read sequence after we read all other values
+		 * from TSC page.
+		 */
+		smp_rmb();
+
+	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
+
+	return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+}
+
+#else
+static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+	return NULL;
+}
+#endif
 #endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d8b5f8ab8ef9..673f9ac50f6d 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -45,6 +45,8 @@
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
 #define MSR_PLATFORM_INFO		0x000000ce
+#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
+#define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
 
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
@@ -127,6 +129,7 @@
 
 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_TR			(1UL <<  6)
 #define DEBUGCTLMSR_BTS			(1UL <<  7)
@@ -552,10 +555,12 @@
 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
 
-/* MISC_FEATURE_ENABLES non-architectural features */
-#define MSR_MISC_FEATURE_ENABLES	0x00000140
+/* MISC_FEATURES_ENABLES non-architectural features */
+#define MSR_MISC_FEATURES_ENABLES	0x00000140
 
-#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT		1
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT	0
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT		BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
+#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT	1
 
 #define MSR_IA32_TSC_DEADLINE		0x000006E0
 
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index b3bebf9e5746..b4a0d43248cf 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -4,6 +4,7 @@
 #include <asm/page_64_types.h>
 
 #ifndef __ASSEMBLY__
+#include <asm/alternative.h>
 
 /* duplicated to the one in bootmem.h */
 extern unsigned long max_pfn;
@@ -34,7 +35,20 @@ extern unsigned long __phys_addr_symbol(unsigned long);
 #define pfn_valid(pfn)          ((pfn) < max_pfn)
 #endif
 
-void clear_page(void *page);
+void clear_page_orig(void *page);
+void clear_page_rep(void *page);
+void clear_page_erms(void *page);
+
+static inline void clear_page(void *page)
+{
+	alternative_call_2(clear_page_orig,
+			   clear_page_rep, X86_FEATURE_REP_GOOD,
+			   clear_page_erms, X86_FEATURE_ERMS,
+			   "=D" (page),
+			   "0" (page)
+			   : "memory", "rax", "rcx");
+}
+
 void copy_page(void *to, void *from);
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 9215e0527647..3f5f08b010d0 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -36,7 +36,12 @@
  * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
  * what Xen requires.
  */
+#ifdef CONFIG_X86_5LEVEL
+#define __PAGE_OFFSET_BASE      _AC(0xff10000000000000, UL)
+#else
 #define __PAGE_OFFSET_BASE      _AC(0xffff880000000000, UL)
+#endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
 #define __PAGE_OFFSET           page_offset_base
 #else
@@ -46,8 +51,13 @@
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
+#ifdef CONFIG_X86_5LEVEL
+#define __PHYSICAL_MASK_SHIFT	52
+#define __VIRTUAL_MASK_SHIFT	56
+#else
 #define __PHYSICAL_MASK_SHIFT	46
 #define __VIRTUAL_MASK_SHIFT	47
+#endif
 
 /*
  * Kernel image size is limited to 1GiB due to the fixmap living in the
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 0489884fdc44..55fa56fe4e45 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -357,6 +357,16 @@ static inline void paravirt_release_pud(unsigned long pfn)
 	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
 }
 
+static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)
+{
+	PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn);
+}
+
+static inline void paravirt_release_p4d(unsigned long pfn)
+{
+	PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn);
+}
+
 static inline void pte_update(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
@@ -536,7 +546,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 		PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
 			    val);
 }
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
@@ -565,26 +575,54 @@ static inline pudval_t pud_val(pud_t pud)
 	return ret;
 }
 
-static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+static inline void pud_clear(pud_t *pudp)
 {
-	pgdval_t val = native_pgd_val(pgd);
+	set_pud(pudp, __pud(0));
+}
 
-	if (sizeof(pgdval_t) > sizeof(long))
-		PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp,
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	p4dval_t val = native_p4d_val(p4d);
+
+	if (sizeof(p4dval_t) > sizeof(long))
+		PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp,
 			    val, (u64)val >> 32);
 	else
-		PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp,
+		PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp,
 			    val);
 }
 
+#if CONFIG_PGTABLE_LEVELS >= 5
+
+static inline p4d_t __p4d(p4dval_t val)
+{
+	p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val);
+
+	return (p4d_t) { ret };
+}
+
+static inline p4dval_t p4d_val(p4d_t p4d)
+{
+	return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d);
+}
+
+static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	pgdval_t val = native_pgd_val(pgd);
+
+	PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val);
+}
+
 static inline void pgd_clear(pgd_t *pgdp)
 {
 	set_pgd(pgdp, __pgd(0));
 }
 
-static inline void pud_clear(pud_t *pudp)
+#endif  /* CONFIG_PGTABLE_LEVELS == 5 */
+
+static inline void p4d_clear(p4d_t *p4dp)
 {
-	set_pud(pudp, __pud(0));
+	set_p4d(p4dp, __p4d(0));
 }
 
 #endif	/* CONFIG_PGTABLE_LEVELS == 4 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index b060f962d581..7465d6fe336f 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -238,9 +238,11 @@ struct pv_mmu_ops {
 	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
 	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
 	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
+	void (*alloc_p4d)(struct mm_struct *mm, unsigned long pfn);
 	void (*release_pte)(unsigned long pfn);
 	void (*release_pmd)(unsigned long pfn);
 	void (*release_pud)(unsigned long pfn);
+	void (*release_p4d)(unsigned long pfn);
 
 	/* Pagetable manipulation functions */
 	void (*set_pte)(pte_t *ptep, pte_t pteval);
@@ -279,12 +281,21 @@ struct pv_mmu_ops {
 	struct paravirt_callee_save pmd_val;
 	struct paravirt_callee_save make_pmd;
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	struct paravirt_callee_save pud_val;
 	struct paravirt_callee_save make_pud;
 
-	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+	void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval);
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+	struct paravirt_callee_save p4d_val;
+	struct paravirt_callee_save make_p4d;
+
+	void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval);
+#endif	/* CONFIG_PGTABLE_LEVELS >= 5 */
+
+#endif	/* CONFIG_PGTABLE_LEVELS >= 4 */
+
 #endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	struct pv_lazy_ops lazy_mode;
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index d08eacd298c2..9f1b21f372fe 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -4,6 +4,8 @@
  *	(c) 1999 Martin Mares <mj@ucw.cz>
  */
 
+#include <linux/ioport.h>
+
 #undef DEBUG
 
 #ifdef DEBUG
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index b6d425999f99..b2d0cd8288aa 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -17,9 +17,11 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{
 static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
 					    unsigned long start, unsigned long count) {}
 static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)	{}
 static inline void paravirt_release_pte(unsigned long pfn) {}
 static inline void paravirt_release_pmd(unsigned long pfn) {}
 static inline void paravirt_release_pud(unsigned long pfn) {}
+static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
 /*
@@ -121,10 +123,10 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 #endif	/* CONFIG_X86_PAE */
 
 #if CONFIG_PGTABLE_LEVELS > 3
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
 {
 	paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
-	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
+	set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud)));
 }
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -150,6 +152,37 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 	___pud_free_tlb(tlb, pud);
 }
 
+#if CONFIG_PGTABLE_LEVELS > 4
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
+{
+	paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
+	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
+}
+
+static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_KERNEL_ACCOUNT;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
+	return (p4d_t *)get_zeroed_page(gfp);
+}
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+	free_page((unsigned long)p4d);
+}
+
+extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
+
+static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
+				  unsigned long address)
+{
+	___p4d_free_tlb(tlb, p4d);
+}
+
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 392576433e77..373ab1de909f 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -7,6 +7,7 @@
 typedef unsigned long	pteval_t;
 typedef unsigned long	pmdval_t;
 typedef unsigned long	pudval_t;
+typedef unsigned long	p4dval_t;
 typedef unsigned long	pgdval_t;
 typedef unsigned long	pgprotval_t;
 
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 72277b1028a5..50d35e3185f5 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd)
 	*(tmp + 1) = 0;
 }
 
-#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \
-		defined(CONFIG_PARAVIRT))
 static inline void native_pud_clear(pud_t *pudp)
 {
 }
-#endif
 
 static inline void pud_clear(pud_t *pudp)
 {
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index bcc89625ebe5..b8a4341faafa 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -7,6 +7,7 @@
 typedef u64	pteval_t;
 typedef u64	pmdval_t;
 typedef u64	pudval_t;
+typedef u64	p4dval_t;
 typedef u64	pgdval_t;
 typedef u64	pgprotval_t;
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1cfb36b8c024..f5af95a0c6b8 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -2,8 +2,6 @@
 #define _ASM_X86_PGTABLE_H
 
 #include <asm/page.h>
-#include <asm/e820.h>
-
 #include <asm/pgtable_types.h>
 
 /*
@@ -53,16 +51,24 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 
 #define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)
 
-#ifndef __PAGETABLE_PUD_FOLDED
+#ifndef __PAGETABLE_P4D_FOLDED
 #define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
 #define pgd_clear(pgd)			native_pgd_clear(pgd)
 #endif
 
+#ifndef set_p4d
+# define set_p4d(p4dp, p4d)		native_set_p4d(p4dp, p4d)
+#endif
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define p4d_clear(p4d)			native_p4d_clear(p4d)
+#endif
+
 #ifndef set_pud
 # define set_pud(pudp, pud)		native_set_pud(pudp, pud)
 #endif
 
-#ifndef __PAGETABLE_PMD_FOLDED
+#ifndef __PAGETABLE_PUD_FOLDED
 #define pud_clear(pud)			native_pud_clear(pud)
 #endif
 
@@ -74,6 +80,11 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 #define pgd_val(x)	native_pgd_val(x)
 #define __pgd(x)	native_make_pgd(x)
 
+#ifndef __PAGETABLE_P4D_FOLDED
+#define p4d_val(x)	native_p4d_val(x)
+#define __p4d(x)	native_make_p4d(x)
+#endif
+
 #ifndef __PAGETABLE_PUD_FOLDED
 #define pud_val(x)	native_pud_val(x)
 #define __pud(x)	native_make_pud(x)
@@ -179,6 +190,17 @@ static inline unsigned long pud_pfn(pud_t pud)
 	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
+static inline unsigned long p4d_pfn(p4d_t p4d)
+{
+	return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT;
+}
+
+static inline int p4d_large(p4d_t p4d)
+{
+	/* No 512 GiB pages yet */
+	return 0;
+}
+
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 static inline int pmd_large(pmd_t pte)
@@ -538,6 +560,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define pte_pgprot(x) __pgprot(pte_flags(x))
 #define pmd_pgprot(x) __pgprot(pmd_flags(x))
 #define pud_pgprot(x) __pgprot(pud_flags(x))
+#define p4d_pgprot(x) __pgprot(p4d_flags(x))
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
@@ -587,6 +610,7 @@ pte_t *populate_extra_pte(unsigned long vaddr);
 #include <linux/mm_types.h>
 #include <linux/mmdebug.h>
 #include <linux/log2.h>
+#include <asm/fixmap.h>
 
 static inline int pte_none(pte_t pte)
 {
@@ -770,7 +794,52 @@ static inline int pud_large(pud_t pud)
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
+static inline unsigned long pud_index(unsigned long address)
+{
+	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
 #if CONFIG_PGTABLE_LEVELS > 3
+static inline int p4d_none(p4d_t p4d)
+{
+	return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+	return p4d_flags(p4d) & _PAGE_PRESENT;
+}
+
+static inline unsigned long p4d_page_vaddr(p4d_t p4d)
+{
+	return (unsigned long)__va(p4d_val(p4d) & p4d_pfn_mask(p4d));
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define p4d_page(p4d)		\
+	pfn_to_page((p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT)
+
+/* Find an entry in the third-level page table.. */
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address);
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+	return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+#endif  /* CONFIG_PGTABLE_LEVELS > 3 */
+
+static inline unsigned long p4d_index(unsigned long address)
+{
+	return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1);
+}
+
+#if CONFIG_PGTABLE_LEVELS > 4
 static inline int pgd_present(pgd_t pgd)
 {
 	return pgd_flags(pgd) & _PAGE_PRESENT;
@@ -788,14 +857,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 #define pgd_page(pgd)		pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
 
 /* to find an entry in a page-table-directory. */
-static inline unsigned long pud_index(unsigned long address)
-{
-	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
-}
-
-static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
+	return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
 }
 
 static inline int pgd_bad(pgd_t pgd)
@@ -813,7 +877,7 @@ static inline int pgd_none(pgd_t pgd)
 	 */
 	return !native_pgd_val(pgd);
 }
-#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 
 #endif	/* __ASSEMBLY__ */
 
@@ -845,6 +909,7 @@ static inline int pgd_none(pgd_t pgd)
 extern int direct_gbpages;
 void init_mem_mapping(void);
 void early_alloc_pgt_buf(void);
+extern void memblock_find_dma_reserve(void);
 
 #ifdef CONFIG_X86_64
 /* Realmode trampoline initialization. */
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index fbc73360aea0..bfab55675c16 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -14,7 +14,6 @@
  */
 #ifndef __ASSEMBLY__
 #include <asm/processor.h>
-#include <asm/fixmap.h>
 #include <linux/threads.h>
 #include <asm/paravirt.h>
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 73c7ccc38912..9991224f6238 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -35,15 +35,22 @@ extern void paging_init(void);
 #define pud_ERROR(e)					\
 	pr_err("%s:%d: bad pud %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pud_val(e))
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+#define p4d_ERROR(e)					\
+	pr_err("%s:%d: bad p4d %p(%016lx)\n",		\
+	       __FILE__, __LINE__, &(e), p4d_val(e))
+#endif
+
 #define pgd_ERROR(e)					\
 	pr_err("%s:%d: bad pgd %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
 struct mm_struct;
 
+void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte);
 void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
 
-
 static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)
 {
@@ -121,6 +128,20 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	*p4dp = p4d;
+}
+
+static inline void native_p4d_clear(p4d_t *p4d)
+{
+#ifdef CONFIG_X86_5LEVEL
+	native_set_p4d(p4d, native_make_p4d(0));
+#else
+	native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)});
+#endif
+}
+
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	*pgdp = pgd;
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 3a264200c62f..06470da156ba 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -13,6 +13,7 @@
 typedef unsigned long	pteval_t;
 typedef unsigned long	pmdval_t;
 typedef unsigned long	pudval_t;
+typedef unsigned long	p4dval_t;
 typedef unsigned long	pgdval_t;
 typedef unsigned long	pgprotval_t;
 
@@ -22,12 +23,32 @@ typedef struct { pteval_t pte; } pte_t;
 
 #define SHARED_KERNEL_PMD	0
 
+#ifdef CONFIG_X86_5LEVEL
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT	48
+#define PTRS_PER_PGD	512
+
+/*
+ * 4th level page in 5-level paging case
+ */
+#define P4D_SHIFT	39
+#define PTRS_PER_P4D	512
+#define P4D_SIZE	(_AC(1, UL) << P4D_SHIFT)
+#define P4D_MASK	(~(P4D_SIZE - 1))
+
+#else /* CONFIG_X86_5LEVEL */
+
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */
 #define PGDIR_SHIFT	39
 #define PTRS_PER_PGD	512
 
+#endif /* CONFIG_X86_5LEVEL */
+
 /*
  * 3rd level page
  */
@@ -55,9 +76,15 @@ typedef struct { pteval_t pte; } pte_t;
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#ifdef CONFIG_X86_5LEVEL
+#define VMALLOC_SIZE_TB _AC(16384, UL)
+#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
+#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+#else
 #define VMALLOC_SIZE_TB	_AC(32, UL)
 #define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
 #define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+#endif
 #ifdef CONFIG_RANDOMIZE_MEMORY
 #define VMALLOC_START	vmalloc_base
 #define VMEMMAP_START	vmemmap_base
@@ -67,10 +94,11 @@ typedef struct { pteval_t pte; } pte_t;
 #endif /* CONFIG_RANDOMIZE_MEMORY */
 #define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
-#define MODULES_END      _AC(0xffffffffff000000, UL)
+/* The module sections ends with the start of the fixmap */
+#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 #define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
 #define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
 #define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 8b4de22d6429..bf9638e1ee42 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -272,6 +272,27 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
 	return native_pgd_val(pgd) & PTE_FLAGS_MASK;
 }
 
+#if CONFIG_PGTABLE_LEVELS > 4
+typedef struct { p4dval_t p4d; } p4d_t;
+
+static inline p4d_t native_make_p4d(pudval_t val)
+{
+	return (p4d_t) { val };
+}
+
+static inline p4dval_t native_p4d_val(p4d_t p4d)
+{
+	return p4d.p4d;
+}
+#else
+#include <asm-generic/pgtable-nop4d.h>
+
+static inline p4dval_t native_p4d_val(p4d_t p4d)
+{
+	return native_pgd_val(p4d.pgd);
+}
+#endif
+
 #if CONFIG_PGTABLE_LEVELS > 3
 typedef struct { pudval_t pud; } pud_t;
 
@@ -289,7 +310,7 @@ static inline pudval_t native_pud_val(pud_t pud)
 
 static inline pudval_t native_pud_val(pud_t pud)
 {
-	return native_pgd_val(pud.pgd);
+	return native_pgd_val(pud.p4d.pgd);
 }
 #endif
 
@@ -310,10 +331,26 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 
 static inline pmdval_t native_pmd_val(pmd_t pmd)
 {
-	return native_pgd_val(pmd.pud.pgd);
+	return native_pgd_val(pmd.pud.p4d.pgd);
 }
 #endif
 
+static inline p4dval_t p4d_pfn_mask(p4d_t p4d)
+{
+	/* No 512 GiB huge pages yet */
+	return PTE_PFN_MASK;
+}
+
+static inline p4dval_t p4d_flags_mask(p4d_t p4d)
+{
+	return ~p4d_pfn_mask(p4d);
+}
+
+static inline p4dval_t p4d_flags(p4d_t p4d)
+{
+	return native_p4d_val(p4d) & p4d_flags_mask(p4d);
+}
+
 static inline pudval_t pud_pfn_mask(pud_t pud)
 {
 	if (native_pud_val(pud) & _PAGE_PSE)
@@ -457,6 +494,7 @@ enum pg_level {
 	PG_LEVEL_4K,
 	PG_LEVEL_2M,
 	PG_LEVEL_1G,
+	PG_LEVEL_512G,
 	PG_LEVEL_NUM
 };
 
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 34684adb6899..b3b09b98896d 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 static inline
 bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
 {
+	/*
+	 * "Allocated" pkeys are those that have been returned
+	 * from pkey_alloc().  pkey 0 is special, and never
+	 * returned from pkey_alloc().
+	 */
+	if (pkey <= 0)
+		return false;
+	if (pkey >= arch_max_pkey())
+		return false;
 	return mm_pkey_allocation_map(mm) & (1U << pkey);
 }
 
@@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm)
 static inline
 int mm_pkey_free(struct mm_struct *mm, int pkey)
 {
-	/*
-	 * pkey 0 is special, always allocated and can never
-	 * be freed.
-	 */
-	if (!pkey)
-		return -EINVAL;
 	if (!mm_pkey_is_allocated(mm, pkey))
 		return -EINVAL;
 
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 2c1ebeb4d737..529bb4a6487a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
@@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(addr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				arch_wb_cache_pmem(addr, 1);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
 		arch_wb_cache_pmem(addr, bytes);
 
 	return len;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f385eca5407a..3cada998a402 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -80,7 +80,7 @@ extern u16 __read_mostly tlb_lld_1g[NR_INFO];
 
 /*
  *  CPU type and hardware bug flags. Kept separately for each CPU.
- *  Members of this structure are referenced in head.S, so think twice
+ *  Members of this structure are referenced in head_32.S, so think twice
  *  before touching them. [mj]
  */
 
@@ -89,14 +89,7 @@ struct cpuinfo_x86 {
 	__u8			x86_vendor;	/* CPU vendor */
 	__u8			x86_model;
 	__u8			x86_mask;
-#ifdef CONFIG_X86_32
-	char			wp_works_ok;	/* It doesn't on 386's */
-
-	/* Problems on some 486Dx4's and old 386's: */
-	char			rfu;
-	char			pad0;
-	char			pad1;
-#else
+#ifdef CONFIG_X86_64
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
 	int			x86_tlbsize;
 #endif
@@ -716,6 +709,8 @@ extern struct desc_ptr		early_gdt_descr;
 
 extern void cpu_set_gdt(int);
 extern void switch_to_new_gdt(int);
+extern void load_direct_gdt(int);
+extern void load_fixmap_gdt(int);
 extern void load_percpu_segment(int);
 extern void cpu_init(void);
 
@@ -797,6 +792,7 @@ static inline void spin_lock_prefetch(const void *x)
 /*
  * User space process size: 3GB (default).
  */
+#define IA32_PAGE_OFFSET	PAGE_OFFSET
 #define TASK_SIZE		PAGE_OFFSET
 #define TASK_SIZE_MAX		TASK_SIZE
 #define STACK_TOP		TASK_SIZE
@@ -873,7 +869,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
  * This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
+#define __TASK_UNMAPPED_BASE(task_size)	(PAGE_ALIGN(task_size / 3))
+#define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE)
 
 #define KSTK_EIP(task)		(task_pt_regs(task)->ip)
 
@@ -884,6 +881,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
+DECLARE_PER_CPU(u64, msr_misc_features_shadow);
+
 /* Register/unregister a process' MPX related resource */
 #define MPX_ENABLE_MANAGEMENT()	mpx_enable_management()
 #define MPX_DISABLE_MANAGEMENT()	mpx_disable_management()
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 9b9b30b19441..8d3964fc5f91 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -9,6 +9,7 @@ void syscall_init(void);
 
 #ifdef CONFIG_X86_64
 void entry_SYSCALL_64(void);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
 #ifdef CONFIG_X86_32
@@ -30,6 +31,7 @@ void x86_report_nx(void);
 
 extern int reboot_force;
 
-long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
+long do_arch_prctl_common(struct task_struct *task, int option,
+			  unsigned long cpuid_enabled);
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
new file mode 100644
index 000000000000..d7da2729903d
--- /dev/null
+++ b/arch/x86/include/asm/purgatory.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_PURGATORY_H
+#define _ASM_X86_PURGATORY_H
+
+#ifndef __ASSEMBLY__
+#include <linux/purgatory.h>
+
+extern void purgatory(void);
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ *    lookup in kexec works
+ */
+extern unsigned long purgatory_backup_dest;
+extern unsigned long purgatory_backup_src;
+extern unsigned long purgatory_backup_sz;
+#endif	/* __ASSEMBLY__ */
+
+#endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 2cb1cc253d51..fc62ba8dce93 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -15,6 +15,7 @@ struct machine_ops {
 };
 
 extern struct machine_ops machine_ops;
+extern int crashing_cpu;
 
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index fac9a5c0abe9..d91ba04dd007 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -53,6 +53,12 @@
 # define NEED_MOVBE	0
 #endif
 
+#ifdef CONFIG_X86_5LEVEL
+# define NEED_LA57	(1<<(X86_FEATURE_LA57 & 31))
+#else
+# define NEED_LA57	0
+#endif
+
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT
 /* Paravirtualized systems may not have PSE or PGE available */
@@ -98,7 +104,7 @@
 #define REQUIRED_MASK13	0
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
+#define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 026ea82ecc60..47103eca3775 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -149,6 +149,19 @@ void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 #define cpu_acpi_id(cpu)	per_cpu(x86_cpu_to_acpiid, cpu)
 
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+#define raw_smp_processor_id() (this_cpu_read(cpu_number))
+
+#ifdef CONFIG_X86_32
+extern int safe_smp_processor_id(void);
+#else
+# define safe_smp_processor_id()	smp_processor_id()
+#endif
+
 #else /* !CONFIG_SMP */
 #define wbinvd_on_cpu(cpu)     wbinvd()
 static inline int wbinvd_on_all_cpus(void)
@@ -161,22 +174,6 @@ static inline int wbinvd_on_all_cpus(void)
 
 extern unsigned disabled_cpus;
 
-#ifdef CONFIG_X86_32_SMP
-/*
- * This function is needed by all SMP systems. It must _always_ be valid
- * from the initial startup. We map APIC_BASE very early in page_setup(),
- * so this is correct in the x86 case.
- */
-#define raw_smp_processor_id() (this_cpu_read(cpu_number))
-extern int safe_smp_processor_id(void);
-
-#elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id() (this_cpu_read(cpu_number))
-
-#define safe_smp_processor_id()		smp_processor_id()
-
-#endif
-
 #ifdef CONFIG_X86_LOCAL_APIC
 
 #ifndef CONFIG_X86_64
@@ -191,11 +188,7 @@ static inline int logical_smp_processor_id(void)
 extern int hard_smp_processor_id(void);
 
 #else /* CONFIG_X86_LOCAL_APIC */
-
-# ifndef CONFIG_SMP
-#  define hard_smp_processor_id()	0
-# endif
-
+#define hard_smp_processor_id()	0
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4517d6b93188..1f5bee2c202f 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -26,8 +26,13 @@
 # endif
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS	44
-# define MAX_PHYSMEM_BITS	46
+# ifdef CONFIG_X86_5LEVEL
+#  define MAX_PHYSADDR_BITS	52
+#  define MAX_PHYSMEM_BITS	52
+# else
+#  define MAX_PHYSADDR_BITS	44
+#  define MAX_PHYSMEM_BITS	46
+# endif
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 58505f01962f..dcbd9bcce714 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -87,7 +87,7 @@ static inline void setup_stack_canary_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
 	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
-	struct desc_struct *gdt_table = get_cpu_gdt_table(cpu);
+	struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
 	struct desc_struct desc;
 
 	desc = gdt_table[GDT_ENTRY_STACK_CANARY];
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 83372dc43943..e00e1bd6e7b3 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -85,6 +85,7 @@ struct thread_info {
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_PATCH_PENDING	13	/* pending live patching update */
+#define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_NOHZ		19	/* in adaptive nohz mode */
@@ -109,6 +110,7 @@ struct thread_info {
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
+#define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
@@ -139,7 +141,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
+	(_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
@@ -169,9 +171,9 @@ static inline unsigned long current_stack_pointer(void)
  * entirely contained by a single stack frame.
  *
  * Returns:
- *		 1 if within a frame
- *		-1 if placed across a frame boundary (or outside stack)
- *		 0 unable to determine (no frame pointers, etc)
+ *	GOOD_FRAME	if within a frame
+ *	BAD_STACK	if placed across a frame boundary (or outside stack)
+ *	NOT_STACK	unable to determine (no frame pointers, etc)
  */
 static inline int arch_within_stack_frames(const void * const stack,
 					   const void * const stackend,
@@ -198,13 +200,14 @@ static inline int arch_within_stack_frames(const void * const stack,
 		 * the copy as invalid.
 		 */
 		if (obj + len <= frame)
-			return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1;
+			return obj >= oldframe + 2 * sizeof(void *) ?
+				GOOD_FRAME : BAD_STACK;
 		oldframe = frame;
 		frame = *(const void * const *)frame;
 	}
-	return -1;
+	return BAD_STACK;
 #else
-	return 0;
+	return NOT_STACK;
 #endif
 }
 
@@ -240,6 +243,8 @@ static inline int arch_within_stack_frames(const void * const stack,
 extern void arch_task_cache_init(void);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 extern void arch_release_task_struct(struct task_struct *tsk);
+extern void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index a04eabd43d06..27e9f9d769b8 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
+extern bool using_native_sched_clock(void);
+
 /*
  * We use the full linear equation: f(x) = a + b*x, in order to allow
  * a continuous function in the face of dynamic freq changes.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa85944af83..6ed9ea469b48 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsigned long mask)
 	}
 }
 
+static inline void cr4_toggle_bits(unsigned long mask)
+{
+	unsigned long cr4;
+
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	cr4 ^= mask;
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+	__write_cr4(cr4);
+}
+
 /* Read the CR4 shadow. */
 static inline unsigned long cr4_read_shadow(void)
 {
@@ -188,7 +198,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
 
 static inline void __flush_tlb_all(void)
 {
-	if (static_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		__flush_tlb_global();
 	else
 		__flush_tlb();
@@ -205,7 +215,6 @@ static inline void __flush_tlb_one(unsigned long addr)
 /*
  * TLB flushing:
  *
- *  - flush_tlb() flushes the current mm struct TLBs
  *  - flush_tlb_all() flushes all processes TLBs
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
@@ -237,11 +246,6 @@ static inline void flush_tlb_all(void)
 	__flush_tlb_all();
 }
 
-static inline void flush_tlb(void)
-{
-	__flush_tlb_up();
-}
-
 static inline void local_flush_tlb(void)
 {
 	__flush_tlb_up();
@@ -303,14 +307,11 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
 
 extern void flush_tlb_all(void);
-extern void flush_tlb_current_task(void);
 extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
-#define flush_tlb()	flush_tlb_current_task()
-
 void native_flush_tlb_others(const struct cpumask *cpumask,
 				struct mm_struct *mm,
 				unsigned long start, unsigned long end);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ea148313570f..68766b276d9e 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -3,19 +3,14 @@
 /*
  * User space memory access functions
  */
-#include <linux/errno.h>
 #include <linux/compiler.h>
 #include <linux/kasan-checks.h>
-#include <linux/thread_info.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/smap.h>
 #include <asm/extable.h>
 
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
 /*
  * The fs value determines whether argument validity checking should be
  * performed or not.  If get_fs() == USER_DS, checking is performed, with
@@ -384,6 +379,18 @@ do {									\
 		     : "=r" (err), ltype(x)				\
 		     : "m" (__m(addr)), "i" (errret), "0" (err))
 
+#define __get_user_asm_nozero(x, addr, err, itype, rtype, ltype, errret)	\
+	asm volatile("\n"						\
+		     "1:	mov"itype" %2,%"rtype"1\n"		\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:	mov %3,%0\n"				\
+		     "	jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : "=r" (err), ltype(x)				\
+		     : "m" (__m(addr)), "i" (errret), "0" (err))
+
 /*
  * This doesn't do __uaccess_begin/end - the exception handling
  * around it must do that.
@@ -675,59 +682,6 @@ extern struct movsl_mask {
 # include <asm/uaccess_64.h>
 #endif
 
-unsigned long __must_check _copy_from_user(void *to, const void __user *from,
-					   unsigned n);
-unsigned long __must_check _copy_to_user(void __user *to, const void *from,
-					 unsigned n);
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
-	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static __always_inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	int sz = __compiletime_object_size(to);
-
-	might_fault();
-
-	kasan_check_write(to, n);
-
-	if (likely(sz < 0 || sz >= n)) {
-		check_object_size(to, n, false);
-		n = _copy_from_user(to, from, n);
-	} else if (!__builtin_constant_p(n))
-		copy_user_overflow(sz, n);
-	else
-		__bad_copy_user();
-
-	return n;
-}
-
-static __always_inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	int sz = __compiletime_object_size(from);
-
-	kasan_check_read(from, n);
-
-	might_fault();
-
-	if (likely(sz < 0 || sz >= n)) {
-		check_object_size(from, n, true);
-		n = _copy_to_user(to, from, n);
-	} else if (!__builtin_constant_p(n))
-		copy_user_overflow(sz, n);
-	else
-		__bad_copy_user();
-
-	return n;
-}
-
 /*
  * We rely on the nested NMI work to allow atomic faults from the NMI path; the
  * nested NMI paths are careful to preserve CR2.
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 7d3bdd1ed697..aeda9bb8af50 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -4,149 +4,52 @@
 /*
  * User space memory access functions
  */
-#include <linux/errno.h>
-#include <linux/thread_info.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
 
-unsigned long __must_check __copy_to_user_ll
-		(void __user *to, const void *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll
-		(void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nozero
-		(void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nocache
-		(void *to, const void __user *from, unsigned long n);
+unsigned long __must_check __copy_user_ll
+		(void *to, const void *from, unsigned long n);
 unsigned long __must_check __copy_from_user_ll_nocache_nozero
 		(void *to, const void __user *from, unsigned long n);
 
-/**
- * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- * The caller should also make sure he pins the user space address
- * so that we don't result in page fault and sleep.
- */
-static __always_inline unsigned long __must_check
-__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
-{
-	check_object_size(from, n, true);
-	return __copy_to_user_ll(to, from, n);
-}
-
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
 static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	might_fault();
-	return __copy_to_user_inatomic(to, from, n);
+	return __copy_user_ll((__force void *)to, from, n);
 }
 
 static __always_inline unsigned long
-__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
-{
-	return __copy_from_user_ll_nozero(to, from, n);
-}
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - may be called from
- * atomic context and will fail rather than sleep.  In this case the
- * uncopied bytes will *NOT* be padded with zeros.  See fs/filemap.h
- * for explanation of why this is needed.
- */
-static __always_inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	might_fault();
-	check_object_size(to, n, false);
-	if (__builtin_constant_p(n)) {
-		unsigned long ret;
-
-		switch (n) {
-		case 1:
-			__uaccess_begin();
-			__get_user_size(*(u8 *)to, from, 1, ret, 1);
-			__uaccess_end();
-			return ret;
-		case 2:
-			__uaccess_begin();
-			__get_user_size(*(u16 *)to, from, 2, ret, 2);
-			__uaccess_end();
-			return ret;
-		case 4:
-			__uaccess_begin();
-			__get_user_size(*(u32 *)to, from, 4, ret, 4);
-			__uaccess_end();
-			return ret;
-		}
-	}
-	return __copy_from_user_ll(to, from, n);
-}
-
-static __always_inline unsigned long __copy_from_user_nocache(void *to,
-				const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
 		switch (n) {
 		case 1:
+			ret = 0;
 			__uaccess_begin();
-			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__get_user_asm_nozero(*(u8 *)to, from, ret,
+					      "b", "b", "=q", 1);
 			__uaccess_end();
 			return ret;
 		case 2:
+			ret = 0;
 			__uaccess_begin();
-			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__get_user_asm_nozero(*(u16 *)to, from, ret,
+					      "w", "w", "=r", 2);
 			__uaccess_end();
 			return ret;
 		case 4:
+			ret = 0;
 			__uaccess_begin();
-			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__get_user_asm_nozero(*(u32 *)to, from, ret,
+					      "l", "k", "=r", 4);
 			__uaccess_end();
 			return ret;
 		}
 	}
-	return __copy_from_user_ll_nocache(to, from, n);
+	return __copy_user_ll(to, (__force const void *)from, n);
 }
 
 static __always_inline unsigned long
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 673059a109fe..c5504b9a472e 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -5,7 +5,6 @@
  * User space memory access functions
  */
 #include <linux/compiler.h>
-#include <linux/errno.h>
 #include <linux/lockdep.h>
 #include <linux/kasan-checks.h>
 #include <asm/alternative.h>
@@ -46,58 +45,54 @@ copy_user_generic(void *to, const void *from, unsigned len)
 	return ret;
 }
 
-__must_check unsigned long
-copy_in_user(void __user *to, const void __user *from, unsigned len);
-
-static __always_inline __must_check
-int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
+static __always_inline __must_check unsigned long
+raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 {
 	int ret = 0;
 
-	check_object_size(dst, size, false);
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
 	case 1:
 		__uaccess_begin();
-		__get_user_asm(*(u8 *)dst, (u8 __user *)src,
+		__get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
 		__uaccess_end();
 		return ret;
 	case 2:
 		__uaccess_begin();
-		__get_user_asm(*(u16 *)dst, (u16 __user *)src,
+		__get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 4:
 		__uaccess_begin();
-		__get_user_asm(*(u32 *)dst, (u32 __user *)src,
+		__get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
 	case 8:
 		__uaccess_begin();
-		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
 		__uaccess_end();
 		return ret;
 	case 10:
 		__uaccess_begin();
-		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
 		if (likely(!ret))
-			__get_user_asm(*(u16 *)(8 + (char *)dst),
+			__get_user_asm_nozero(*(u16 *)(8 + (char *)dst),
 				       (u16 __user *)(8 + (char __user *)src),
 				       ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 16:
 		__uaccess_begin();
-		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
 		if (likely(!ret))
-			__get_user_asm(*(u64 *)(8 + (char *)dst),
+			__get_user_asm_nozero(*(u64 *)(8 + (char *)dst),
 				       (u64 __user *)(8 + (char __user *)src),
 				       ret, "q", "", "=r", 8);
 		__uaccess_end();
@@ -107,20 +102,11 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
 	}
 }
 
-static __always_inline __must_check
-int __copy_from_user(void *dst, const void __user *src, unsigned size)
-{
-	might_fault();
-	kasan_check_write(dst, size);
-	return __copy_from_user_nocheck(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
+static __always_inline __must_check unsigned long
+raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
 {
 	int ret = 0;
 
-	check_object_size(src, size, true);
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
@@ -176,100 +162,16 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
 }
 
 static __always_inline __must_check
-int __copy_to_user(void __user *dst, const void *src, unsigned size)
-{
-	might_fault();
-	kasan_check_read(src, size);
-	return __copy_to_user_nocheck(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
-{
-	int ret = 0;
-
-	might_fault();
-	if (!__builtin_constant_p(size))
-		return copy_user_generic((__force void *)dst,
-					 (__force void *)src, size);
-	switch (size) {
-	case 1: {
-		u8 tmp;
-		__uaccess_begin();
-		__get_user_asm(tmp, (u8 __user *)src,
-			       ret, "b", "b", "=q", 1);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u8 __user *)dst,
-				       ret, "b", "b", "iq", 1);
-		__uaccess_end();
-		return ret;
-	}
-	case 2: {
-		u16 tmp;
-		__uaccess_begin();
-		__get_user_asm(tmp, (u16 __user *)src,
-			       ret, "w", "w", "=r", 2);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u16 __user *)dst,
-				       ret, "w", "w", "ir", 2);
-		__uaccess_end();
-		return ret;
-	}
-
-	case 4: {
-		u32 tmp;
-		__uaccess_begin();
-		__get_user_asm(tmp, (u32 __user *)src,
-			       ret, "l", "k", "=r", 4);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u32 __user *)dst,
-				       ret, "l", "k", "ir", 4);
-		__uaccess_end();
-		return ret;
-	}
-	case 8: {
-		u64 tmp;
-		__uaccess_begin();
-		__get_user_asm(tmp, (u64 __user *)src,
-			       ret, "q", "", "=r", 8);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u64 __user *)dst,
-				       ret, "q", "", "er", 8);
-		__uaccess_end();
-		return ret;
-	}
-	default:
-		return copy_user_generic((__force void *)dst,
-					 (__force void *)src, size);
-	}
-}
-
-static __must_check __always_inline int
-__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
-{
-	kasan_check_write(dst, size);
-	return __copy_from_user_nocheck(dst, src, size);
-}
-
-static __must_check __always_inline int
-__copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
+unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size)
 {
-	kasan_check_read(src, size);
-	return __copy_to_user_nocheck(dst, src, size);
+	return copy_user_generic((__force void *)dst,
+				 (__force void *)src, size);
 }
 
 extern long __copy_user_nocache(void *dst, const void __user *src,
 				unsigned size, int zerorest);
 
 static inline int
-__copy_from_user_nocache(void *dst, const void __user *src, unsigned size)
-{
-	might_fault();
-	kasan_check_write(dst, size);
-	return __copy_user_nocache(dst, src, size, 1);
-}
-
-static inline int
 __copy_from_user_inatomic_nocache(void *dst, const void __user *src,
 				  unsigned size)
 {
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 32712a925f26..1ba1536f627e 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -23,7 +23,6 @@
 #  include <asm/unistd_64.h>
 #  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
-#  define __ARCH_WANT_COMPAT_SYS_GETDENTS64
 #  define __ARCH_WANT_COMPAT_SYS_PREADV64
 #  define __ARCH_WANT_COMPAT_SYS_PWRITEV64
 #  define __ARCH_WANT_COMPAT_SYS_PREADV64V2
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 137e9cce2ab4..e6676495b125 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -13,8 +13,10 @@ struct unwind_state {
 	int graph_idx;
 	bool error;
 #ifdef CONFIG_FRAME_POINTER
+	bool got_irq;
 	unsigned long *bp, *orig_sp;
 	struct pt_regs *regs;
+	unsigned long ip;
 #else
 	unsigned long *sp;
 #endif
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 57ab86d94d64..7cac79802ad2 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -185,6 +185,15 @@
 #define MSG_REGULAR			1
 #define MSG_RETRY			2
 
+#define BAU_DESC_QUALIFIER		0x534749
+
+enum uv_bau_version {
+	UV_BAU_V1 = 1,
+	UV_BAU_V2,
+	UV_BAU_V3,
+	UV_BAU_V4,
+};
+
 /*
  * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
  * If the 'multilevel' flag in the header portion of the descriptor
@@ -222,20 +231,32 @@ struct bau_local_cpumask {
  *   the s/w ack bit vector  ]
  */
 
-/*
- * The payload is software-defined for INTD transactions
+/**
+ * struct uv1_2_3_bau_msg_payload - defines payload for INTD transactions
+ * @address:		Signifies a page or all TLB's of the cpu
+ * @sending_cpu:	CPU from which the message originates
+ * @acknowledge_count:	CPUs on the destination Hub that received the interrupt
  */
-struct bau_msg_payload {
-	unsigned long	address;		/* signifies a page or all
-						   TLB's of the cpu */
-	/* 64 bits */
-	unsigned short	sending_cpu;		/* filled in by sender */
-	/* 16 bits */
-	unsigned short	acknowledge_count;	/* filled in by destination */
-	/* 16 bits */
-	unsigned int	reserved1:32;		/* not usable */
+struct uv1_2_3_bau_msg_payload {
+	u64 address;
+	u16 sending_cpu;
+	u16 acknowledge_count;
 };
 
+/**
+ * struct uv4_bau_msg_payload - defines payload for INTD transactions
+ * @address:		Signifies a page or all TLB's of the cpu
+ * @sending_cpu:	CPU from which the message originates
+ * @acknowledge_count:	CPUs on the destination Hub that received the interrupt
+ * @qualifier:		Set by source to verify origin of INTD broadcast
+ */
+struct uv4_bau_msg_payload {
+	u64 address;
+	u16 sending_cpu;
+	u16 acknowledge_count;
+	u32 reserved:8;
+	u32 qualifier:24;
+};
 
 /*
  * UV1 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
@@ -385,17 +406,6 @@ struct uv2_3_bau_msg_header {
 	/* bits 127:120 */
 };
 
-/* Abstracted BAU functions */
-struct bau_operations {
-	unsigned long (*read_l_sw_ack)(void);
-	unsigned long (*read_g_sw_ack)(int pnode);
-	unsigned long (*bau_gpa_to_offset)(unsigned long vaddr);
-	void (*write_l_sw_ack)(unsigned long mmr);
-	void (*write_g_sw_ack)(int pnode, unsigned long mmr);
-	void (*write_payload_first)(int pnode, unsigned long mmr);
-	void (*write_payload_last)(int pnode, unsigned long mmr);
-};
-
 /*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
@@ -411,7 +421,10 @@ struct bau_desc {
 		struct uv2_3_bau_msg_header	uv2_3_hdr;
 	} header;
 
-	struct bau_msg_payload			payload;
+	union bau_payload_header {
+		struct uv1_2_3_bau_msg_payload	uv1_2_3;
+		struct uv4_bau_msg_payload	uv4;
+	} payload;
 };
 /* UV1:
  *   -payload--    ---------header------
@@ -588,8 +601,12 @@ struct uvhub_desc {
 	struct socket_desc	socket[2];
 };
 
-/*
- * one per-cpu; to locate the software tables
+/**
+ * struct bau_control
+ * @status_mmr: location of status mmr, determined by uvhub_cpu
+ * @status_index: index of ERR|BUSY bits in status mmr, determined by uvhub_cpu
+ *
+ * Per-cpu control struct containing CPU topology information and BAU tuneables.
  */
 struct bau_control {
 	struct bau_desc		*descriptor_base;
@@ -607,6 +624,8 @@ struct bau_control {
 	int			timeout_tries;
 	int			ipi_attempts;
 	int			conseccompletes;
+	u64			status_mmr;
+	int			status_index;
 	bool			nobau;
 	short			baudisabled;
 	short			cpu;
@@ -644,6 +663,19 @@ struct bau_control {
 	struct hub_and_pnode	*thp;
 };
 
+/* Abstracted BAU functions */
+struct bau_operations {
+	unsigned long	(*read_l_sw_ack)(void);
+	unsigned long	(*read_g_sw_ack)(int pnode);
+	unsigned long	(*bau_gpa_to_offset)(unsigned long vaddr);
+	void		(*write_l_sw_ack)(unsigned long mmr);
+	void		(*write_g_sw_ack)(int pnode, unsigned long mmr);
+	void		(*write_payload_first)(int pnode, unsigned long mmr);
+	void		(*write_payload_last)(int pnode, unsigned long mmr);
+	int		(*wait_completion)(struct bau_desc*,
+				struct bau_control*, long try);
+};
+
 static inline void write_mmr_data_broadcast(int pnode, unsigned long mmr_image)
 {
 	write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image);
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 72e8300b1e8a..9cffb44a3cf5 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 
 	if (paddr < uv_hub_info->lowmem_remap_top)
 		paddr |= uv_hub_info->lowmem_remap_base;
-	paddr |= uv_hub_info->gnode_upper;
-	if (m_val)
+
+	if (m_val) {
+		paddr |= uv_hub_info->gnode_upper;
 		paddr = ((paddr << uv_hub_info->m_shift)
 						>> uv_hub_info->m_shift) |
 			((paddr >> uv_hub_info->m_val)
 						<< uv_hub_info->n_lshift);
-	else
+	} else {
 		paddr |= uv_soc_phys_ram_to_nasid(paddr)
 						<< uv_hub_info->gpa_shift;
+	}
 	return paddr;
 }
 
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 2444189cbe28..bccdf4938ddf 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -20,6 +20,7 @@ struct vdso_image {
 	long sym_vvar_page;
 	long sym_hpet_page;
 	long sym_pvclock_page;
+	long sym_hvclock_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 33cbd3db97b9..8a5a02b1dfba 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
+#include <linux/device.h>
 
 #include <linux/uaccess.h>
 #include <asm/page.h>
@@ -279,13 +280,17 @@ static inline pte_t __pte_ma(pteval_t x)
 
 #define pmd_val_ma(v) ((v).pmd)
 #ifdef __PAGETABLE_PUD_FOLDED
-#define pud_val_ma(v) ((v).pgd.pgd)
+#define pud_val_ma(v) ((v).p4d.pgd.pgd)
 #else
 #define pud_val_ma(v) ((v).pud)
 #endif
 #define __pmd_ma(x)	((pmd_t) { (x) } )
 
-#define pgd_val_ma(x)	((x).pgd)
+#ifdef __PAGETABLE_P4D_FOLDED
+#define p4d_val_ma(x)	((x).pgd.pgd)
+#else
+#define p4d_val_ma(x)	((x).p4d)
+#endif
 
 void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
 
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 5138dacf8bb8..ddef37b16af2 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -34,7 +34,6 @@
 #include <linux/screen_info.h>
 #include <linux/apm_bios.h>
 #include <linux/edd.h>
-#include <asm/e820.h>
 #include <asm/ist.h>
 #include <video/edid.h>
 
@@ -58,7 +57,7 @@ struct setup_header {
 	__u32	header;
 	__u16	version;
 	__u32	realmode_swtch;
-	__u16	start_sys;
+	__u16	start_sys_seg;
 	__u16	kernel_version;
 	__u8	type_of_loader;
 	__u8	loadflags;
@@ -111,6 +110,21 @@ struct efi_info {
 	__u32 efi_memmap_hi;
 };
 
+/*
+ * This is the maximum number of entries in struct boot_params::e820_table
+ * (the zeropage), which is part of the x86 boot protocol ABI:
+ */
+#define E820_MAX_ENTRIES_ZEROPAGE 128
+
+/*
+ * The E820 memory region entry of the boot protocol ABI:
+ */
+struct boot_e820_entry {
+	__u64 addr;
+	__u64 size;
+	__u32 type;
+} __attribute__((packed));
+
 /* The so-called "zeropage" */
 struct boot_params {
 	struct screen_info screen_info;			/* 0x000 */
@@ -153,7 +167,7 @@ struct boot_params {
 	struct setup_header hdr;    /* setup header */	/* 0x1f1 */
 	__u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
 	__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];	/* 0x290 */
-	struct e820entry e820_map[E820MAX];		/* 0x2d0 */
+	struct boot_e820_entry e820_table[E820_MAX_ENTRIES_ZEROPAGE]; /* 0x2d0 */
 	__u8  _pad8[48];				/* 0xcd0 */
 	struct edd_info eddbuf[EDDMAXNR];		/* 0xd00 */
 	__u8  _pad9[276];				/* 0xeec */
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 835aa51c7f6e..c45765517092 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -1,10 +1,13 @@
 #ifndef _ASM_X86_PRCTL_H
 #define _ASM_X86_PRCTL_H
 
-#define ARCH_SET_GS 0x1001
-#define ARCH_SET_FS 0x1002
-#define ARCH_GET_FS 0x1003
-#define ARCH_GET_GS 0x1004
+#define ARCH_SET_GS		0x1001
+#define ARCH_SET_FS		0x1002
+#define ARCH_GET_FS		0x1003
+#define ARCH_GET_GS		0x1004
+
+#define ARCH_GET_CPUID		0x1011
+#define ARCH_SET_CPUID		0x1012
 
 #define ARCH_MAP_VDSO_X32	0x2001
 #define ARCH_MAP_VDSO_32	0x2002
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 84c00592d359..4b994232cb57 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -27,7 +27,7 @@ KASAN_SANITIZE_stacktrace.o := n
 
 OBJECT_FILES_NON_STANDARD_head_$(BITS).o		:= y
 OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y
-OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y
 OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
 
 # If instrumentation of this dir is enabled, boot hangs during first second.
@@ -46,7 +46,7 @@ obj-$(CONFIG_MODIFY_LDT_SYSCALL)	+= ldt.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
-obj-$(CONFIG_X86_64)	+= sys_x86_64.o mcount_64.o
+obj-$(CONFIG_X86_64)	+= sys_x86_64.o
 obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
@@ -82,6 +82,7 @@ obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_LIVEPATCH)	+= livepatch.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace_$(BITS).o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ae32838cac5f..6bb680671088 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -37,6 +37,7 @@
 #include <linux/pci.h>
 #include <linux/efi-bgrt.h>
 
+#include <asm/e820/api.h>
 #include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
 #include <asm/pgtable.h>
@@ -179,10 +180,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 		return -EINVAL;
 	}
 
+	if (!enabled) {
+		++disabled_cpus;
+		return -EINVAL;
+	}
+
 	if (boot_cpu_physical_apicid != -1U)
 		ver = boot_cpu_apic_version;
 
-	cpu = __generic_processor_info(id, ver, enabled);
+	cpu = generic_processor_info(id, ver);
 	if (cpu >= 0)
 		early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
 
@@ -710,7 +716,7 @@ static void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
@@ -1559,12 +1565,6 @@ int __init early_acpi_boot_init(void)
 	return 0;
 }
 
-static int __init acpi_parse_bgrt(struct acpi_table_header *table)
-{
-	efi_bgrt_init(table);
-	return 0;
-}
-
 int __init acpi_boot_init(void)
 {
 	/* those are executed after early-quirks are executed */
@@ -1724,6 +1724,6 @@ int __acpi_release_global_lock(unsigned int *lock)
 
 void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
 {
-	e820_add_region(addr, size, E820_ACPI);
-	update_e820();
+	e820__range_add(addr, size, E820_TYPE_ACPI);
+	e820__update_table_print();
 }
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 48587335ede8..ed014814ea35 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,7 +101,7 @@ int x86_acpi_suspend_lowlevel(void)
 #ifdef CONFIG_SMP
 	initial_stack = (unsigned long)temp_stack + sizeof(temp_stack);
 	early_gdt_descr.address =
-			(unsigned long)get_cpu_gdt_table(smp_processor_id());
+			(unsigned long)get_cpu_gdt_rw(smp_processor_id());
 	initial_gs = per_cpu_offset(smp_processor_id());
 #endif
 	initial_code = (unsigned long)wakeup_long64;
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 0a2bb1f62e72..ef2859f9fcce 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -21,7 +21,7 @@
 #include <linux/pci.h>
 #include <linux/bitops.h>
 #include <linux/suspend.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
@@ -306,13 +306,13 @@ void __init early_gart_iommu_check(void)
 		fix = 1;
 
 	if (gart_fix_e820 && !fix && aper_enabled) {
-		if (e820_any_mapped(aper_base, aper_base + aper_size,
-				    E820_RAM)) {
+		if (e820__mapped_any(aper_base, aper_base + aper_size,
+				    E820_TYPE_RAM)) {
 			/* reserve it, so we can reuse it in second kernel */
 			pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n",
 				aper_base, aper_base + aper_size - 1);
-			e820_add_region(aper_base, aper_size, E820_RESERVED);
-			update_e820();
+			e820__range_add(aper_base, aper_size, E820_TYPE_RESERVED);
+			e820__update_table_print();
 		}
 	}
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4261b3282ad9..2d75faf743f2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -731,8 +731,10 @@ static int __init calibrate_APIC_clock(void)
 					TICK_NSEC, lapic_clockevent.shift);
 		lapic_clockevent.max_delta_ns =
 			clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+		lapic_clockevent.max_delta_ticks = 0x7FFFFF;
 		lapic_clockevent.min_delta_ns =
 			clockevent_delta2ns(0xF, &lapic_clockevent);
+		lapic_clockevent.min_delta_ticks = 0xF;
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 		return 0;
 	}
@@ -778,8 +780,10 @@ static int __init calibrate_APIC_clock(void)
 				       lapic_clockevent.shift);
 	lapic_clockevent.max_delta_ns =
 		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
+	lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
 	lapic_clockevent.min_delta_ns =
 		clockevent_delta2ns(0xF, &lapic_clockevent);
+	lapic_clockevent.min_delta_ticks = 0xF;
 
 	lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
 
@@ -1610,24 +1614,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { }
 static inline void __x2apic_enable(void) { }
 #endif /* !CONFIG_X86_X2APIC */
 
-static int __init try_to_enable_IR(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	if (!x2apic_enabled() && skip_ioapic_setup) {
-		pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
-		return -1;
-	}
-#endif
-	return irq_remapping_enable();
-}
-
 void __init enable_IR_x2apic(void)
 {
 	unsigned long flags;
 	int ret, ir_stat;
 
-	if (skip_ioapic_setup)
+	if (skip_ioapic_setup) {
+		pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
 		return;
+	}
 
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
@@ -1645,7 +1640,7 @@ void __init enable_IR_x2apic(void)
 
 	/* If irq_remapping_prepare() succeeded, try to enable it */
 	if (ir_stat >= 0)
-		ir_stat = try_to_enable_IR();
+		ir_stat = irq_remapping_enable();
 	/* ir_stat contains the remap mode or an error code */
 	try_to_enable_x2apic(ir_stat);
 
@@ -1798,8 +1793,8 @@ void __init init_apic_mappings(void)
 		apic_phys = mp_lapic_addr;
 
 		/*
-		 * acpi lapic path already maps that address in
-		 * acpi_register_lapic_address()
+		 * If the system has ACPI MADT tables or MP info, the LAPIC
+		 * address is already registered.
 		 */
 		if (!acpi_lapic && !smp_found_config)
 			register_lapic_address(apic_phys);
@@ -2062,17 +2057,17 @@ static int allocate_logical_cpuid(int apicid)
 
 	/* Allocate a new cpuid. */
 	if (nr_logical_cpuids >= nr_cpu_ids) {
-		WARN_ONCE(1, "Only %d processors supported."
+		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. "
 			     "Processor %d/0x%x and the rest are ignored.\n",
-			     nr_cpu_ids - 1, nr_logical_cpuids, apicid);
-		return -1;
+			     nr_cpu_ids, nr_logical_cpuids, apicid);
+		return -EINVAL;
 	}
 
 	cpuid_to_apicid[nr_logical_cpuids] = apicid;
 	return nr_logical_cpuids++;
 }
 
-int __generic_processor_info(int apicid, int version, bool enabled)
+int generic_processor_info(int apicid, int version)
 {
 	int cpu, max = nr_cpu_ids;
 	bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2130,11 +2125,9 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 	if (num_processors >= nr_cpu_ids) {
 		int thiscpu = max + disabled_cpus;
 
-		if (enabled) {
-			pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
-				   "reached. Processor %d/0x%x ignored.\n",
-				   max, thiscpu, apicid);
-		}
+		pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
+			   "reached. Processor %d/0x%x ignored.\n",
+			   max, thiscpu, apicid);
 
 		disabled_cpus++;
 		return -EINVAL;
@@ -2186,23 +2179,13 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 		apic->x86_32_early_logical_apicid(cpu);
 #endif
 	set_cpu_possible(cpu, true);
-
-	if (enabled) {
-		num_processors++;
-		physid_set(apicid, phys_cpu_present_map);
-		set_cpu_present(cpu, true);
-	} else {
-		disabled_cpus++;
-	}
+	physid_set(apicid, phys_cpu_present_map);
+	set_cpu_present(cpu, true);
+	num_processors++;
 
 	return cpu;
 }
 
-int generic_processor_info(int apicid, int version)
-{
-	return __generic_processor_info(apicid, version, true);
-}
-
 int hard_smp_processor_id(void)
 {
 	return read_apic_id();
@@ -2258,7 +2241,7 @@ void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v))
 static void __init apic_bsp_up_setup(void)
 {
 #ifdef CONFIG_X86_64
-	apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid));
+	apic_write(APIC_ID, apic->set_apic_id(boot_cpu_physical_apicid));
 #else
 	/*
 	 * Hack: In case of kdump, after a crash, kernel might be booting
@@ -2648,7 +2631,7 @@ static int __init lapic_insert_resource(void)
 }
 
 /*
- * need call insert after e820_reserve_resources()
+ * need call insert after e820__reserve_resources()
  * that is using request_resource
  */
 late_initcall(lapic_insert_resource);
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index b109e4389c92..2262eb6df796 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -26,7 +26,7 @@
 
 #include <linux/interrupt.h>
 #include <asm/acpi.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 
 static void noop_init_apic_ldr(void) { }
 static void noop_send_IPI(int cpu, int vector) { }
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index c48264e202fd..2e8f7f048f4f 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -25,7 +25,7 @@
 
 #include <linux/interrupt.h>
 #include <asm/acpi.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
 #define DEFAULT_SEND_IPI	(1)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e9f8f8cdd570..b487b3a01615 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -34,6 +34,7 @@
 #include <asm/uv/bios.h>
 #include <asm/uv/uv.h>
 #include <asm/apic.h>
+#include <asm/e820/api.h>
 #include <asm/ipi.h>
 #include <asm/smp.h>
 #include <asm/x86_init.h>
@@ -1105,7 +1106,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi)
 	node_id.v		= uv_read_local_mmr(UVH_NODE_ID);
 	uv_cpuid.gnode_shift	= max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val);
 	hi->gnode_extra		= (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1;
-	hi->gnode_upper		= (unsigned long)hi->gnode_extra << mn.m_val;
+	if (mn.m_val)
+		hi->gnode_upper	= (u64)hi->gnode_extra << mn.m_val;
 
 	if (uv_gp_table) {
 		hi->global_mmr_base	= uv_gp_table->mmr_base;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5a414545e8a3..446b0d3d4932 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -609,7 +609,7 @@ static long __apm_bios_call(void *_call)
 
 	cpu = get_cpu();
 	BUG_ON(cpu != 0);
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
@@ -685,7 +685,7 @@ static long __apm_bios_call_simple(void *_call)
 
 	cpu = get_cpu();
 	BUG_ON(cpu != 0);
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
@@ -2352,7 +2352,7 @@ static int __init apm_init(void)
 	 * Note we only set APM segments on CPU zero, since we pin the APM
 	 * code to that CPU.
 	 */
-	gdt = get_cpu_gdt_table(0);
+	gdt = get_cpu_gdt_rw(0);
 	set_desc_base(&gdt[APM_CS >> 3],
 		 (unsigned long)__va((unsigned long)apm_info.bios.cseg << 4));
 	set_desc_base(&gdt[APM_CS_16 >> 3],
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 35a5d5dca2fa..c36140d788fe 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (check_tsc_unstable())
-			clear_sched_clock_stable();
-	} else {
-		clear_sched_clock_stable();
 	}
 
 	/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index adc0ebd8bed0..44207b71fee1 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -3,7 +3,7 @@
 #include <linux/sched/clock.h>
 
 #include <asm/cpufeature.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 
@@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #endif
-
-	clear_sched_clock_stable();
 }
 
 static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b11b38c3b0bd..8ee32119144d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c)
 			strcpy(c->x86_model_id, "386");
 	}
 #endif
-	clear_sched_clock_stable();
 }
 
 static const struct cpu_dev default_cpu = {
@@ -449,19 +448,60 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
+/* Setup the fixmap mapping only once per-processor */
+static inline void setup_fixmap_gdt(int cpu)
+{
+#ifdef CONFIG_X86_64
+	/* On 64-bit systems, we use a read-only fixmap GDT. */
+	pgprot_t prot = PAGE_KERNEL_RO;
+#else
+	/*
+	 * On native 32-bit systems, the GDT cannot be read-only because
+	 * our double fault handler uses a task gate, and entering through
+	 * a task gate needs to change an available TSS to busy.  If the GDT
+	 * is read-only, that will triple fault.
+	 *
+	 * On Xen PV, the GDT must be read-only because the hypervisor requires
+	 * it.
+	 */
+	pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
+		PAGE_KERNEL_RO : PAGE_KERNEL;
+#endif
+
+	__set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
+}
+
+/* Load the original GDT from the per-cpu structure */
+void load_direct_gdt(int cpu)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_rw(cpu);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+EXPORT_SYMBOL_GPL(load_direct_gdt);
+
+/* Load a fixmap remapping of the per-cpu GDT */
+void load_fixmap_gdt(int cpu)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_ro(cpu);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+EXPORT_SYMBOL_GPL(load_fixmap_gdt);
+
 /*
  * Current gdt points %fs at the "master" per-cpu area: after this,
  * it's on the real one.
  */
 void switch_to_new_gdt(int cpu)
 {
-	struct desc_ptr gdt_descr;
-
-	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
-	gdt_descr.size = GDT_SIZE - 1;
-	load_gdt(&gdt_descr);
+	/* Load the original GDT */
+	load_direct_gdt(cpu);
 	/* Reload the per-cpu base */
-
 	load_percpu_segment(cpu);
 }
 
@@ -1077,8 +1117,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (this_cpu->c_init)
 		this_cpu->c_init(c);
-	else
-		clear_sched_clock_stable();
 
 	/* Disable the PN if appropriate */
 	squash_the_stupid_serial_number(c);
@@ -1529,6 +1567,9 @@ void cpu_init(void)
 
 	if (is_uv_system())
 		uv_cpu_init();
+
+	setup_fixmap_gdt(cpu);
+	load_fixmap_gdt(cpu);
 }
 
 #else
@@ -1584,6 +1625,9 @@ void cpu_init(void)
 	dbg_restore_debug_regs();
 
 	fpu__init_cpu();
+
+	setup_fixmap_gdt(cpu);
+	load_fixmap_gdt(cpu);
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 0a3bc19de017..a70fd61095f8 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
 		break;
 	}
-	clear_sched_clock_stable();
 }
 
 static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fe0a615a051b..dfa90a3a5145 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -90,16 +90,12 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
 		return;
 	}
 
-	if (ring3mwait_disabled) {
-		msr_clear_bit(MSR_MISC_FEATURE_ENABLES,
-			      MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+	if (ring3mwait_disabled)
 		return;
-	}
-
-	msr_set_bit(MSR_MISC_FEATURE_ENABLES,
-		    MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
 
 	set_cpu_cap(c, X86_FEATURE_RING3MWAIT);
+	this_cpu_or(msr_misc_features_shadow,
+		    1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT);
 
 	if (c == &boot_cpu_data)
 		ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
@@ -162,10 +158,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (check_tsc_unstable())
-			clear_sched_clock_stable();
-	} else {
-		clear_sched_clock_stable();
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
@@ -492,6 +484,34 @@ static void intel_bsp_resume(struct cpuinfo_x86 *c)
 	init_intel_energy_perf(c);
 }
 
+static void init_cpuid_fault(struct cpuinfo_x86 *c)
+{
+	u64 msr;
+
+	if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) {
+		if (msr & MSR_PLATFORM_INFO_CPUID_FAULT)
+			set_cpu_cap(c, X86_FEATURE_CPUID_FAULT);
+	}
+}
+
+static void init_intel_misc_features(struct cpuinfo_x86 *c)
+{
+	u64 msr;
+
+	if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr))
+		return;
+
+	/* Clear all MISC features */
+	this_cpu_write(msr_misc_features_shadow, 0);
+
+	/* Check features and update capabilities and shadow control bits */
+	init_cpuid_fault(c);
+	probe_xeon_phi_r3mwait(c);
+
+	msr = this_cpu_read(msr_misc_features_shadow);
+	wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
+}
+
 static void init_intel(struct cpuinfo_x86 *c)
 {
 	unsigned int l2 = 0;
@@ -606,7 +626,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_intel_energy_perf(c);
 
-	probe_xeon_phi_r3mwait(c);
+	init_intel_misc_features(c);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 5a533fefefa0..5b366462f579 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -32,55 +32,98 @@
 #include <asm/intel-family.h>
 #include <asm/intel_rdt.h>
 
+#define MAX_MBA_BW	100u
+#define MBA_IS_LINEAR	0x4
+
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
 DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
 
+/*
+ * Used to store the max resource name width and max resource data width
+ * to display the schemata in a tabular format
+ */
+int max_name_width, max_data_width;
+
+static void
+mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+static void
+cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
 struct rdt_resource rdt_resources_all[] = {
 	{
-		.name		= "L3",
-		.domains	= domain_init(RDT_RESOURCE_L3),
-		.msr_base	= IA32_L3_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 3,
-		.cbm_idx_multi	= 1,
-		.cbm_idx_offset	= 0
+		.name			= "L3",
+		.domains		= domain_init(RDT_RESOURCE_L3),
+		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 3,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 1,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
+	},
+	{
+		.name			= "L3DATA",
+		.domains		= domain_init(RDT_RESOURCE_L3DATA),
+		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 3,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 2,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
 	},
 	{
-		.name		= "L3DATA",
-		.domains	= domain_init(RDT_RESOURCE_L3DATA),
-		.msr_base	= IA32_L3_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 3,
-		.cbm_idx_multi	= 2,
-		.cbm_idx_offset	= 0
+		.name			= "L3CODE",
+		.domains		= domain_init(RDT_RESOURCE_L3CODE),
+		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 3,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 2,
+			.cbm_idx_offset	= 1,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
 	},
 	{
-		.name		= "L3CODE",
-		.domains	= domain_init(RDT_RESOURCE_L3CODE),
-		.msr_base	= IA32_L3_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 3,
-		.cbm_idx_multi	= 2,
-		.cbm_idx_offset	= 1
+		.name			= "L2",
+		.domains		= domain_init(RDT_RESOURCE_L2),
+		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 2,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 1,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
 	},
 	{
-		.name		= "L2",
-		.domains	= domain_init(RDT_RESOURCE_L2),
-		.msr_base	= IA32_L2_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 2,
-		.cbm_idx_multi	= 1,
-		.cbm_idx_offset	= 0
+		.name			= "MB",
+		.domains		= domain_init(RDT_RESOURCE_MBA),
+		.msr_base		= IA32_MBA_THRTL_BASE,
+		.msr_update		= mba_wrmsr,
+		.cache_level		= 3,
+		.parse_ctrlval		= parse_bw,
+		.format_str		= "%d=%*d",
 	},
 };
 
-static int cbm_idx(struct rdt_resource *r, int closid)
+static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
 {
-	return closid * r->cbm_idx_multi + r->cbm_idx_offset;
+	return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset;
 }
 
 /*
@@ -118,9 +161,9 @@ static inline bool cache_alloc_hsw_probe(void)
 			return false;
 
 		r->num_closid = 4;
-		r->cbm_len = 20;
-		r->max_cbm = max_cbm;
-		r->min_cbm_bits = 2;
+		r->default_ctrl = max_cbm;
+		r->cache.cbm_len = 20;
+		r->cache.min_cbm_bits = 2;
 		r->capable = true;
 		r->enabled = true;
 
@@ -130,16 +173,66 @@ static inline bool cache_alloc_hsw_probe(void)
 	return false;
 }
 
-static void rdt_get_config(int idx, struct rdt_resource *r)
+/*
+ * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
+ * exposed to user interface and the h/w understandable delay values.
+ *
+ * The non-linear delay values have the granularity of power of two
+ * and also the h/w does not guarantee a curve for configured delay
+ * values vs. actual b/w enforced.
+ * Hence we need a mapping that is pre calibrated so the user can
+ * express the memory b/w as a percentage value.
+ */
+static inline bool rdt_get_mb_table(struct rdt_resource *r)
+{
+	/*
+	 * There are no Intel SKUs as of now to support non-linear delay.
+	 */
+	pr_info("MBA b/w map not implemented for cpu:%d, model:%d",
+		boot_cpu_data.x86, boot_cpu_data.x86_model);
+
+	return false;
+}
+
+static bool rdt_get_mem_config(struct rdt_resource *r)
+{
+	union cpuid_0x10_3_eax eax;
+	union cpuid_0x10_x_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->membw.max_delay = eax.split.max_delay + 1;
+	r->default_ctrl = MAX_MBA_BW;
+	if (ecx & MBA_IS_LINEAR) {
+		r->membw.delay_linear = true;
+		r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
+		r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
+	} else {
+		if (!rdt_get_mb_table(r))
+			return false;
+	}
+	r->data_width = 3;
+	rdt_get_mba_infofile(r);
+
+	r->capable = true;
+	r->enabled = true;
+
+	return true;
+}
+
+static void rdt_get_cache_config(int idx, struct rdt_resource *r)
 {
 	union cpuid_0x10_1_eax eax;
-	union cpuid_0x10_1_edx edx;
+	union cpuid_0x10_x_edx edx;
 	u32 ebx, ecx;
 
 	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
 	r->num_closid = edx.split.cos_max + 1;
-	r->cbm_len = eax.split.cbm_len + 1;
-	r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->cache.cbm_len = eax.split.cbm_len + 1;
+	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->data_width = (r->cache.cbm_len + 3) / 4;
+	rdt_get_cache_infofile(r);
 	r->capable = true;
 	r->enabled = true;
 }
@@ -150,8 +243,9 @@ static void rdt_get_cdp_l3_config(int type)
 	struct rdt_resource *r = &rdt_resources_all[type];
 
 	r->num_closid = r_l3->num_closid / 2;
-	r->cbm_len = r_l3->cbm_len;
-	r->max_cbm = r_l3->max_cbm;
+	r->cache.cbm_len = r_l3->cache.cbm_len;
+	r->default_ctrl = r_l3->default_ctrl;
+	r->data_width = (r->cache.cbm_len + 3) / 4;
 	r->capable = true;
 	/*
 	 * By default, CDP is disabled. CDP can be enabled by mount parameter
@@ -160,33 +254,6 @@ static void rdt_get_cdp_l3_config(int type)
 	r->enabled = false;
 }
 
-static inline bool get_rdt_resources(void)
-{
-	bool ret = false;
-
-	if (cache_alloc_hsw_probe())
-		return true;
-
-	if (!boot_cpu_has(X86_FEATURE_RDT_A))
-		return false;
-
-	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
-		rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
-		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
-			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
-			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
-		}
-		ret = true;
-	}
-	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
-		/* CPUID 0x10.2 fields are same format at 0x10.1 */
-		rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
-		ret = true;
-	}
-
-	return ret;
-}
-
 static int get_cache_id(int cpu, int level)
 {
 	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
@@ -200,29 +267,55 @@ static int get_cache_id(int cpu, int level)
 	return -1;
 }
 
-void rdt_cbm_update(void *arg)
+/*
+ * Map the memory b/w percentage value to delay values
+ * that can be written to QOS_MSRs.
+ * There are currently no SKUs which support non linear delay values.
+ */
+static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 {
-	struct msr_param *m = (struct msr_param *)arg;
+	if (r->membw.delay_linear)
+		return MAX_MBA_BW - bw;
+
+	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
+	return r->default_ctrl;
+}
+
+static void
+mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	/*  Write the delay values for mba. */
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r));
+}
+
+static void
+cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]);
+}
+
+void rdt_ctrl_update(void *arg)
+{
+	struct msr_param *m = arg;
 	struct rdt_resource *r = m->res;
-	int i, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
 	struct rdt_domain *d;
 
 	list_for_each_entry(d, &r->domains, list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
-			goto found;
+		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+			r->msr_update(d, m, r);
+			return;
+		}
 	}
-	pr_info_once("cpu %d not found in any domain for resource %s\n",
+	pr_warn_once("cpu %d not found in any domain for resource %s\n",
 		     cpu, r->name);
-
-	return;
-
-found:
-	for (i = m->low; i < m->high; i++) {
-		int idx = cbm_idx(r, i);
-
-		wrmsrl(r->msr_base + idx, d->cbm[i]);
-	}
 }
 
 /*
@@ -258,6 +351,32 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	return NULL;
 }
 
+static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
+{
+	struct msr_param m;
+	u32 *dc;
+	int i;
+
+	dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
+	if (!dc)
+		return -ENOMEM;
+
+	d->ctrl_val = dc;
+
+	/*
+	 * Initialize the Control MSRs to having no control.
+	 * For Cache Allocation: Set all bits in cbm
+	 * For Memory Allocation: Set b/w requested to 100
+	 */
+	for (i = 0; i < r->num_closid; i++, dc++)
+		*dc = r->default_ctrl;
+
+	m.low = 0;
+	m.high = r->num_closid;
+	r->msr_update(d, &m, r);
+	return 0;
+}
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -273,7 +392,7 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int i, id = get_cache_id(cpu, r->cache_level);
+	int id = get_cache_id(cpu, r->cache_level);
 	struct list_head *add_pos = NULL;
 	struct rdt_domain *d;
 
@@ -294,22 +413,13 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d->id = id;
 
-	d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL);
-	if (!d->cbm) {
+	if (domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
 	}
 
-	for (i = 0; i < r->num_closid; i++) {
-		int idx = cbm_idx(r, i);
-
-		d->cbm[i] = r->max_cbm;
-		wrmsrl(r->msr_base + idx, d->cbm[i]);
-	}
-
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 	list_add_tail(&d->list, add_pos);
-	r->num_domains++;
 }
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
@@ -325,8 +435,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 	cpumask_clear_cpu(cpu, &d->cpu_mask);
 	if (cpumask_empty(&d->cpu_mask)) {
-		r->num_domains--;
-		kfree(d->cbm);
+		kfree(d->ctrl_val);
 		list_del(&d->list);
 		kfree(d);
 	}
@@ -374,6 +483,57 @@ static int intel_rdt_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * Choose a width for the resource name and resource data based on the
+ * resource that has widest name and cbm.
+ */
+static __init void rdt_init_padding(void)
+{
+	struct rdt_resource *r;
+	int cl;
+
+	for_each_capable_rdt_resource(r) {
+		cl = strlen(r->name);
+		if (cl > max_name_width)
+			max_name_width = cl;
+
+		if (r->data_width > max_data_width)
+			max_data_width = r->data_width;
+	}
+}
+
+static __init bool get_rdt_resources(void)
+{
+	bool ret = false;
+
+	if (cache_alloc_hsw_probe())
+		return true;
+
+	if (!boot_cpu_has(X86_FEATURE_RDT_A))
+		return false;
+
+	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
+		rdt_get_cache_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
+		}
+		ret = true;
+	}
+	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+		/* CPUID 0x10.2 fields are same format at 0x10.1 */
+		rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		ret = true;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_MBA)) {
+		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
+			ret = true;
+	}
+
+	return ret;
+}
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
@@ -382,6 +542,8 @@ static int __init intel_rdt_late_init(void)
 	if (!get_rdt_resources())
 		return -ENODEV;
 
+	rdt_init_padding();
+
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/rdt/cat:online:",
 				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 0bbe0f3a039f..f5af0cc7eb0d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -28,7 +28,6 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/slab.h>
-#include <linux/cpu.h>
 #include <linux/task_work.h>
 
 #include <uapi/linux/magic.h>
@@ -175,6 +174,13 @@ static struct kernfs_ops rdtgroup_kf_single_ops = {
 	.seq_show		= rdtgroup_seqfile_show,
 };
 
+static bool is_cpu_list(struct kernfs_open_file *of)
+{
+	struct rftype *rft = of->kn->priv;
+
+	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
+}
+
 static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 			      struct seq_file *s, void *v)
 {
@@ -183,10 +189,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
-	if (rdtgrp)
-		seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask));
-	else
+	if (rdtgrp) {
+		seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+			   cpumask_pr_args(&rdtgrp->cpu_mask));
+	} else {
 		ret = -ENOENT;
+	}
 	rdtgroup_kn_unlock(of->kn);
 
 	return ret;
@@ -253,7 +261,11 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
-	ret = cpumask_parse(buf, newmask);
+	if (is_cpu_list(of))
+		ret = cpulist_parse(buf, newmask);
+	else
+		ret = cpumask_parse(buf, newmask);
+
 	if (ret)
 		goto unlock;
 
@@ -474,6 +486,14 @@ static struct rftype rdtgroup_base_files[] = {
 		.seq_show	= rdtgroup_cpus_show,
 	},
 	{
+		.name		= "cpus_list",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+		.flags		= RFTYPE_FLAGS_CPUS_LIST,
+	},
+	{
 		.name		= "tasks",
 		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -495,32 +515,56 @@ static int rdt_num_closids_show(struct kernfs_open_file *of,
 	struct rdt_resource *r = of->kn->parent->priv;
 
 	seq_printf(seq, "%d\n", r->num_closid);
+	return 0;
+}
 
+static int rdt_default_ctrl_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%x\n", r->default_ctrl);
 	return 0;
 }
 
-static int rdt_cbm_mask_show(struct kernfs_open_file *of,
+static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
 
-	seq_printf(seq, "%x\n", r->max_cbm);
+	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
+	return 0;
+}
+
+static int rdt_min_bw_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
 
+	seq_printf(seq, "%u\n", r->membw.min_bw);
 	return 0;
 }
 
-static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
+static int rdt_bw_gran_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
 
-	seq_printf(seq, "%d\n", r->min_cbm_bits);
+	seq_printf(seq, "%u\n", r->membw.bw_gran);
+	return 0;
+}
 
+static int rdt_delay_linear_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%u\n", r->membw.delay_linear);
 	return 0;
 }
 
 /* rdtgroup information files for one cache resource. */
-static struct rftype res_info_files[] = {
+static struct rftype res_cache_info_files[] = {
 	{
 		.name		= "num_closids",
 		.mode		= 0444,
@@ -531,7 +575,7 @@ static struct rftype res_info_files[] = {
 		.name		= "cbm_mask",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_cbm_mask_show,
+		.seq_show	= rdt_default_ctrl_show,
 	},
 	{
 		.name		= "min_cbm_bits",
@@ -541,11 +585,52 @@ static struct rftype res_info_files[] = {
 	},
 };
 
+/* rdtgroup information files for memory bandwidth. */
+static struct rftype res_mba_info_files[] = {
+	{
+		.name		= "num_closids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_closids_show,
+	},
+	{
+		.name		= "min_bandwidth",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_bw_show,
+	},
+	{
+		.name		= "bandwidth_gran",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bw_gran_show,
+	},
+	{
+		.name		= "delay_linear",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_delay_linear_show,
+	},
+};
+
+void rdt_get_mba_infofile(struct rdt_resource *r)
+{
+	r->info_files = res_mba_info_files;
+	r->nr_info_files = ARRAY_SIZE(res_mba_info_files);
+}
+
+void rdt_get_cache_infofile(struct rdt_resource *r)
+{
+	r->info_files = res_cache_info_files;
+	r->nr_info_files = ARRAY_SIZE(res_cache_info_files);
+}
+
 static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 {
 	struct kernfs_node *kn_subdir;
+	struct rftype *res_info_files;
 	struct rdt_resource *r;
-	int ret;
+	int ret, len;
 
 	/* create the directory */
 	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
@@ -564,8 +649,11 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 		ret = rdtgroup_kn_set_ugid(kn_subdir);
 		if (ret)
 			goto out_destroy;
-		ret = rdtgroup_add_files(kn_subdir, res_info_files,
-					 ARRAY_SIZE(res_info_files));
+
+		res_info_files = r->info_files;
+		len = r->nr_info_files;
+
+		ret = rdtgroup_add_files(kn_subdir, res_info_files, len);
 		if (ret)
 			goto out_destroy;
 		kernfs_activate(kn_subdir);
@@ -728,7 +816,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
 		kernfs_unbreak_active_protection(kn);
-		kernfs_put(kn);
+		kernfs_put(rdtgrp->kn);
 		kfree(rdtgrp);
 	} else {
 		kernfs_unbreak_active_protection(kn);
@@ -781,7 +869,7 @@ out:
 	return dentry;
 }
 
-static int reset_all_cbms(struct rdt_resource *r)
+static int reset_all_ctrls(struct rdt_resource *r)
 {
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
@@ -804,14 +892,14 @@ static int reset_all_cbms(struct rdt_resource *r)
 		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 
 		for (i = 0; i < r->num_closid; i++)
-			d->cbm[i] = r->max_cbm;
+			d->ctrl_val[i] = r->default_ctrl;
 	}
 	cpu = get_cpu();
 	/* Update CBM on this cpu if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_cbm_update(&msr_param);
+		rdt_ctrl_update(&msr_param);
 	/* Update CBM on all other cpus in cpu_mask. */
-	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	put_cpu();
 
 	free_cpumask_var(cpu_mask);
@@ -897,7 +985,7 @@ static void rdt_kill_sb(struct super_block *sb)
 
 	/*Put everything back to default values. */
 	for_each_enabled_rdt_resource(r)
-		reset_all_cbms(r);
+		reset_all_ctrls(r);
 	cdp_disable();
 	rmdir_all_sub();
 	static_branch_disable(&rdt_enable_key);
diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c
index f369cb8db0d5..406d7a6532f9 100644
--- a/arch/x86/kernel/cpu/intel_rdt_schemata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c
@@ -29,26 +29,77 @@
 #include <asm/intel_rdt.h>
 
 /*
+ * Check whether MBA bandwidth percentage value is correct. The value is
+ * checked against the minimum and max bandwidth values specified by the
+ * hardware. The allocated bandwidth percentage is rounded to the next
+ * control step available on the hardware.
+ */
+static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+{
+	unsigned long bw;
+	int ret;
+
+	/*
+	 * Only linear delay values is supported for current Intel SKUs.
+	 */
+	if (!r->membw.delay_linear)
+		return false;
+
+	ret = kstrtoul(buf, 10, &bw);
+	if (ret)
+		return false;
+
+	if (bw < r->membw.min_bw || bw > r->default_ctrl)
+		return false;
+
+	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
+	return true;
+}
+
+int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+{
+	unsigned long data;
+
+	if (d->have_new_ctrl)
+		return -EINVAL;
+
+	if (!bw_validate(buf, &data, r))
+		return -EINVAL;
+	d->new_ctrl = data;
+	d->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
  * Check whether a cache bit mask is valid. The SDM says:
  *	Please note that all (and only) contiguous '1' combinations
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(unsigned long var, struct rdt_resource *r)
+static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 {
-	unsigned long first_bit, zero_bit;
+	unsigned long first_bit, zero_bit, val;
+	unsigned int cbm_len = r->cache.cbm_len;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return false;
 
-	if (var == 0 || var > r->max_cbm)
+	if (val == 0 || val > r->default_ctrl)
 		return false;
 
-	first_bit = find_first_bit(&var, r->cbm_len);
-	zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit);
+	first_bit = find_first_bit(&val, cbm_len);
+	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
-	if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len)
+	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)
 		return false;
 
-	if ((zero_bit - first_bit) < r->min_cbm_bits)
+	if ((zero_bit - first_bit) < r->cache.min_cbm_bits)
 		return false;
+
+	*data = val;
 	return true;
 }
 
@@ -56,17 +107,17 @@ static bool cbm_validate(unsigned long var, struct rdt_resource *r)
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-static int parse_cbm(char *buf, struct rdt_resource *r)
+int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
-	int ret;
 
-	ret = kstrtoul(buf, 16, &data);
-	if (ret)
-		return ret;
-	if (!cbm_validate(data, r))
+	if (d->have_new_ctrl)
 		return -EINVAL;
-	r->tmp_cbms[r->num_tmp_cbms++] = data;
+
+	if(!cbm_validate(buf, &data, r))
+		return -EINVAL;
+	d->new_ctrl = data;
+	d->have_new_ctrl = true;
 
 	return 0;
 }
@@ -74,8 +125,8 @@ static int parse_cbm(char *buf, struct rdt_resource *r)
 /*
  * For each domain in this resource we expect to find a series of:
  *	id=mask
- * separated by ";". The "id" is in decimal, and must appear in the
- * right order.
+ * separated by ";". The "id" is in decimal, and must match one of
+ * the "id"s for this resource.
  */
 static int parse_line(char *line, struct rdt_resource *r)
 {
@@ -83,21 +134,22 @@ static int parse_line(char *line, struct rdt_resource *r)
 	struct rdt_domain *d;
 	unsigned long dom_id;
 
+next:
+	if (!line || line[0] == '\0')
+		return 0;
+	dom = strsep(&line, ";");
+	id = strsep(&dom, "=");
+	if (!dom || kstrtoul(id, 10, &dom_id))
+		return -EINVAL;
+	dom = strim(dom);
 	list_for_each_entry(d, &r->domains, list) {
-		dom = strsep(&line, ";");
-		if (!dom)
-			return -EINVAL;
-		id = strsep(&dom, "=");
-		if (kstrtoul(id, 10, &dom_id) || dom_id != d->id)
-			return -EINVAL;
-		if (parse_cbm(dom, r))
-			return -EINVAL;
+		if (d->id == dom_id) {
+			if (r->parse_ctrlval(dom, r, d))
+				return -EINVAL;
+			goto next;
+		}
 	}
-
-	/* Any garbage at the end of the line? */
-	if (line && line[0])
-		return -EINVAL;
-	return 0;
+	return -EINVAL;
 }
 
 static int update_domains(struct rdt_resource *r, int closid)
@@ -105,7 +157,7 @@ static int update_domains(struct rdt_resource *r, int closid)
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
-	int cpu, idx = 0;
+	int cpu;
 
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
@@ -115,30 +167,46 @@ static int update_domains(struct rdt_resource *r, int closid)
 	msr_param.res = r;
 
 	list_for_each_entry(d, &r->domains, list) {
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
-		d->cbm[msr_param.low] = r->tmp_cbms[idx++];
+		if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) {
+			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+			d->ctrl_val[closid] = d->new_ctrl;
+		}
 	}
+	if (cpumask_empty(cpu_mask))
+		goto done;
 	cpu = get_cpu();
 	/* Update CBM on this cpu if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_cbm_update(&msr_param);
+		rdt_ctrl_update(&msr_param);
 	/* Update CBM on other cpus. */
-	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	put_cpu();
 
+done:
 	free_cpumask_var(cpu_mask);
 
 	return 0;
 }
 
+static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
+{
+	struct rdt_resource *r;
+
+	for_each_enabled_rdt_resource(r) {
+		if (!strcmp(resname, r->name) && closid < r->num_closid)
+			return parse_line(tok, r);
+	}
+	return -EINVAL;
+}
+
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct rdtgroup *rdtgrp;
+	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
 	int closid, ret = 0;
-	u32 *l3_cbms = NULL;
 
 	/* Valid input requires a trailing newline */
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
@@ -153,44 +221,20 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 
 	closid = rdtgrp->closid;
 
-	/* get scratch space to save all the masks while we validate input */
 	for_each_enabled_rdt_resource(r) {
-		r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms),
-				      GFP_KERNEL);
-		if (!r->tmp_cbms) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		r->num_tmp_cbms = 0;
+		list_for_each_entry(dom, &r->domains, list)
+			dom->have_new_ctrl = false;
 	}
 
 	while ((tok = strsep(&buf, "\n")) != NULL) {
-		resname = strsep(&tok, ":");
+		resname = strim(strsep(&tok, ":"));
 		if (!tok) {
 			ret = -EINVAL;
 			goto out;
 		}
-		for_each_enabled_rdt_resource(r) {
-			if (!strcmp(resname, r->name) &&
-			    closid < r->num_closid) {
-				ret = parse_line(tok, r);
-				if (ret)
-					goto out;
-				break;
-			}
-		}
-		if (!r->name) {
-			ret = -EINVAL;
-			goto out;
-		}
-	}
-
-	/* Did the parser find all the masks we need? */
-	for_each_enabled_rdt_resource(r) {
-		if (r->num_tmp_cbms != r->num_domains) {
-			ret = -EINVAL;
+		ret = rdtgroup_parse_resource(resname, tok, closid);
+		if (ret)
 			goto out;
-		}
 	}
 
 	for_each_enabled_rdt_resource(r) {
@@ -201,10 +245,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 
 out:
 	rdtgroup_kn_unlock(of->kn);
-	for_each_enabled_rdt_resource(r) {
-		kfree(r->tmp_cbms);
-		r->tmp_cbms = NULL;
-	}
 	return ret ?: nbytes;
 }
 
@@ -213,11 +253,12 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
 	struct rdt_domain *dom;
 	bool sep = false;
 
-	seq_printf(s, "%s:", r->name);
+	seq_printf(s, "%*s:", max_name_width, r->name);
 	list_for_each_entry(dom, &r->domains, list) {
 		if (sep)
 			seq_puts(s, ";");
-		seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]);
+		seq_printf(s, r->format_str, dom->id, max_data_width,
+			   dom->ctrl_val[closid]);
 		sep = true;
 	}
 	seq_puts(s, "\n");
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index a3311c886194..43051f0777d4 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -9,3 +9,5 @@ obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
 
 obj-$(CONFIG_ACPI_APEI)		+= mce-apei.o
+
+obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
new file mode 100644
index 000000000000..9c632cb88546
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -0,0 +1,397 @@
+/*
+ * /dev/mcelog driver
+ *
+ * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs.
+ * Rest from unknown author(s).
+ * 2004 Andi Kleen. Rewrote most of it.
+ * Copyright 2008 Intel Corporation
+ * Author: Andi Kleen
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/poll.h>
+
+#include "mce-internal.h"
+
+static DEFINE_MUTEX(mce_chrdev_read_mutex);
+
+static char mce_helper[128];
+static char *mce_helper_argv[2] = { mce_helper, NULL };
+
+#define mce_log_get_idx_check(p) \
+({ \
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
+			 !lockdep_is_held(&mce_chrdev_read_mutex), \
+			 "suspicious mce_log_get_idx_check() usage"); \
+	smp_load_acquire(&(p)); \
+})
+
+/*
+ * Lockless MCE logging infrastructure.
+ * This avoids deadlocks on printk locks without having to break locks. Also
+ * separate MCEs from kernel messages to avoid bogus bug reports.
+ */
+
+static struct mce_log_buffer mcelog = {
+	.signature	= MCE_LOG_SIGNATURE,
+	.len		= MCE_LOG_LEN,
+	.recordlen	= sizeof(struct mce),
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
+
+/* User mode helper program triggered by machine check event */
+extern char			mce_helper[128];
+
+static int dev_mce_log(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	unsigned int next, entry;
+
+	wmb();
+	for (;;) {
+		entry = mce_log_get_idx_check(mcelog.next);
+		for (;;) {
+
+			/*
+			 * When the buffer fills up discard new entries.
+			 * Assume that the earlier errors are the more
+			 * interesting ones:
+			 */
+			if (entry >= MCE_LOG_LEN) {
+				set_bit(MCE_OVERFLOW,
+					(unsigned long *)&mcelog.flags);
+				return NOTIFY_OK;
+			}
+			/* Old left over entry. Skip: */
+			if (mcelog.entry[entry].finished) {
+				entry++;
+				continue;
+			}
+			break;
+		}
+		smp_rmb();
+		next = entry + 1;
+		if (cmpxchg(&mcelog.next, entry, next) == entry)
+			break;
+	}
+	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
+	wmb();
+	mcelog.entry[entry].finished = 1;
+	wmb();
+
+	/* wake processes polling /dev/mcelog */
+	wake_up_interruptible(&mce_chrdev_wait);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dev_mcelog_nb = {
+	.notifier_call	= dev_mce_log,
+	.priority	= MCE_PRIO_MCELOG,
+};
+
+static void mce_do_trigger(struct work_struct *work)
+{
+	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
+}
+
+static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
+
+
+void mce_work_trigger(void)
+{
+	if (mce_helper[0])
+		schedule_work(&mce_trigger_work);
+}
+
+static ssize_t
+show_trigger(struct device *s, struct device_attribute *attr, char *buf)
+{
+	strcpy(buf, mce_helper);
+	strcat(buf, "\n");
+	return strlen(mce_helper) + 1;
+}
+
+static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
+				const char *buf, size_t siz)
+{
+	char *p;
+
+	strncpy(mce_helper, buf, sizeof(mce_helper));
+	mce_helper[sizeof(mce_helper)-1] = 0;
+	p = strchr(mce_helper, '\n');
+
+	if (p)
+		*p = 0;
+
+	return strlen(mce_helper) + !!p;
+}
+
+DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
+
+/*
+ * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
+ */
+
+static DEFINE_SPINLOCK(mce_chrdev_state_lock);
+static int mce_chrdev_open_count;	/* #times opened */
+static int mce_chrdev_open_exclu;	/* already open exclusive? */
+
+static int mce_chrdev_open(struct inode *inode, struct file *file)
+{
+	spin_lock(&mce_chrdev_state_lock);
+
+	if (mce_chrdev_open_exclu ||
+	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
+		spin_unlock(&mce_chrdev_state_lock);
+
+		return -EBUSY;
+	}
+
+	if (file->f_flags & O_EXCL)
+		mce_chrdev_open_exclu = 1;
+	mce_chrdev_open_count++;
+
+	spin_unlock(&mce_chrdev_state_lock);
+
+	return nonseekable_open(inode, file);
+}
+
+static int mce_chrdev_release(struct inode *inode, struct file *file)
+{
+	spin_lock(&mce_chrdev_state_lock);
+
+	mce_chrdev_open_count--;
+	mce_chrdev_open_exclu = 0;
+
+	spin_unlock(&mce_chrdev_state_lock);
+
+	return 0;
+}
+
+static void collect_tscs(void *data)
+{
+	unsigned long *cpu_tsc = (unsigned long *)data;
+
+	cpu_tsc[smp_processor_id()] = rdtsc();
+}
+
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+	int rc;
+	u64 record_id;
+	struct mce m;
+
+	if (usize < sizeof(struct mce))
+		return -EINVAL;
+
+	rc = apei_read_mce(&m, &record_id);
+	/* Error or no more MCE record */
+	if (rc <= 0) {
+		mce_apei_read_done = 1;
+		/*
+		 * When ERST is disabled, mce_chrdev_read() should return
+		 * "no record" instead of "no device."
+		 */
+		if (rc == -ENODEV)
+			return 0;
+		return rc;
+	}
+	rc = -EFAULT;
+	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+		return rc;
+	/*
+	 * In fact, we should have cleared the record after that has
+	 * been flushed to the disk or sent to network in
+	 * /sbin/mcelog, but we have no interface to support that now,
+	 * so just clear it to avoid duplication.
+	 */
+	rc = apei_clear_mce(record_id);
+	if (rc) {
+		mce_apei_read_done = 1;
+		return rc;
+	}
+	*ubuf += sizeof(struct mce);
+
+	return 0;
+}
+
+static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	char __user *buf = ubuf;
+	unsigned long *cpu_tsc;
+	unsigned prev, next;
+	int i, err;
+
+	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
+	if (!cpu_tsc)
+		return -ENOMEM;
+
+	mutex_lock(&mce_chrdev_read_mutex);
+
+	if (!mce_apei_read_done) {
+		err = __mce_read_apei(&buf, usize);
+		if (err || buf != ubuf)
+			goto out;
+	}
+
+	next = mce_log_get_idx_check(mcelog.next);
+
+	/* Only supports full reads right now */
+	err = -EINVAL;
+	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+		goto out;
+
+	err = 0;
+	prev = 0;
+	do {
+		for (i = prev; i < next; i++) {
+			unsigned long start = jiffies;
+			struct mce *m = &mcelog.entry[i];
+
+			while (!m->finished) {
+				if (time_after_eq(jiffies, start + 2)) {
+					memset(m, 0, sizeof(*m));
+					goto timeout;
+				}
+				cpu_relax();
+			}
+			smp_rmb();
+			err |= copy_to_user(buf, m, sizeof(*m));
+			buf += sizeof(*m);
+timeout:
+			;
+		}
+
+		memset(mcelog.entry + prev, 0,
+		       (next - prev) * sizeof(struct mce));
+		prev = next;
+		next = cmpxchg(&mcelog.next, prev, 0);
+	} while (next != prev);
+
+	synchronize_sched();
+
+	/*
+	 * Collect entries that were still getting written before the
+	 * synchronize.
+	 */
+	on_each_cpu(collect_tscs, cpu_tsc, 1);
+
+	for (i = next; i < MCE_LOG_LEN; i++) {
+		struct mce *m = &mcelog.entry[i];
+
+		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
+			err |= copy_to_user(buf, m, sizeof(*m));
+			smp_rmb();
+			buf += sizeof(*m);
+			memset(m, 0, sizeof(*m));
+		}
+	}
+
+	if (err)
+		err = -EFAULT;
+
+out:
+	mutex_unlock(&mce_chrdev_read_mutex);
+	kfree(cpu_tsc);
+
+	return err ? err : buf - ubuf;
+}
+
+static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &mce_chrdev_wait, wait);
+	if (READ_ONCE(mcelog.next))
+		return POLLIN | POLLRDNORM;
+	if (!mce_apei_read_done && apei_check_mce())
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
+static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
+				unsigned long arg)
+{
+	int __user *p = (int __user *)arg;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (cmd) {
+	case MCE_GET_RECORD_LEN:
+		return put_user(sizeof(struct mce), p);
+	case MCE_GET_LOG_LEN:
+		return put_user(MCE_LOG_LEN, p);
+	case MCE_GETCLEAR_FLAGS: {
+		unsigned flags;
+
+		do {
+			flags = mcelog.flags;
+		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);
+
+		return put_user(flags, p);
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+			    size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+			     const char __user *ubuf,
+			     size_t usize, loff_t *off))
+{
+	mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	if (mce_write)
+		return mce_write(filp, ubuf, usize, off);
+	else
+		return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
+	.open			= mce_chrdev_open,
+	.release		= mce_chrdev_release,
+	.read			= mce_chrdev_read,
+	.write			= mce_chrdev_write,
+	.poll			= mce_chrdev_poll,
+	.unlocked_ioctl		= mce_chrdev_ioctl,
+	.llseek			= no_llseek,
+};
+
+static struct miscdevice mce_chrdev_device = {
+	MISC_MCELOG_MINOR,
+	"mcelog",
+	&mce_chrdev_ops,
+};
+
+static __init int dev_mcelog_init_device(void)
+{
+	int err;
+
+	/* register character device /dev/mcelog */
+	err = misc_register(&mce_chrdev_device);
+	if (err) {
+		pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+		return err;
+	}
+	mce_register_decode_chain(&dev_mcelog_nb);
+	return 0;
+}
+device_initcall_sync(dev_mcelog_init_device);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 1e5a50c11d3c..217cd4449bc9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused)
 	head = llist_reverse_order(head);
 	llist_for_each_entry_safe(node, tmp, head, llnode) {
 		mce = &node->mce;
-		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+		blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
 		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
 	}
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 903043e6a62b..654ad0668d72 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -13,7 +13,7 @@ enum severity_level {
 	MCE_PANIC_SEVERITY,
 };
 
-extern struct atomic_notifier_head x86_mce_decoder_chain;
+extern struct blocking_notifier_head x86_mce_decoder_chain;
 
 #define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
@@ -96,3 +96,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2)
 		m1->addr != m2->addr ||
 		m1->misc != m2->misc;
 }
+
+extern struct device_attribute dev_attr_trigger;
+
+#ifdef CONFIG_X86_MCELOG_LEGACY
+extern void mce_work_trigger(void);
+#else
+static inline void mce_work_trigger(void)	{ }
+#endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8e9725c607ea..5abd4bf73d6e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -35,6 +35,7 @@
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/cpu.h>
+#include <linux/ras.h>
 #include <linux/smp.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -49,18 +50,11 @@
 #include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/reboot.h>
 
 #include "mce-internal.h"
 
-static DEFINE_MUTEX(mce_chrdev_read_mutex);
-
-#define mce_log_get_idx_check(p) \
-({ \
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
-			 !lockdep_is_held(&mce_chrdev_read_mutex), \
-			 "suspicious mce_log_get_idx_check() usage"); \
-	smp_load_acquire(&(p)); \
-})
+static DEFINE_MUTEX(mce_log_mutex);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -85,15 +79,9 @@ struct mca_config mca_cfg __read_mostly = {
 	.monarch_timeout = -1
 };
 
-/* User mode helper program triggered by machine check event */
-static unsigned long		mce_need_notify;
-static char			mce_helper[128];
-static char			*mce_helper_argv[2] = { mce_helper, NULL };
-
-static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
-
 static DEFINE_PER_CPU(struct mce, mces_seen);
-static int			cpu_missing;
+static unsigned long mce_need_notify;
+static int cpu_missing;
 
 /*
  * MCA banks polled by the period polling timer for corrected events.
@@ -121,7 +109,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
  */
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
@@ -143,82 +131,38 @@ void mce_setup(struct mce *m)
 DEFINE_PER_CPU(struct mce, injectm);
 EXPORT_PER_CPU_SYMBOL_GPL(injectm);
 
-/*
- * Lockless MCE logging infrastructure.
- * This avoids deadlocks on printk locks without having to break locks. Also
- * separate MCEs from kernel messages to avoid bogus bug reports.
- */
-
-static struct mce_log mcelog = {
-	.signature	= MCE_LOG_SIGNATURE,
-	.len		= MCE_LOG_LEN,
-	.recordlen	= sizeof(struct mce),
-};
-
-void mce_log(struct mce *mce)
+void mce_log(struct mce *m)
 {
-	unsigned next, entry;
-
-	/* Emit the trace record: */
-	trace_mce_record(mce);
-
-	if (!mce_gen_pool_add(mce))
+	if (!mce_gen_pool_add(m))
 		irq_work_queue(&mce_irq_work);
-
-	wmb();
-	for (;;) {
-		entry = mce_log_get_idx_check(mcelog.next);
-		for (;;) {
-
-			/*
-			 * When the buffer fills up discard new entries.
-			 * Assume that the earlier errors are the more
-			 * interesting ones:
-			 */
-			if (entry >= MCE_LOG_LEN) {
-				set_bit(MCE_OVERFLOW,
-					(unsigned long *)&mcelog.flags);
-				return;
-			}
-			/* Old left over entry. Skip: */
-			if (mcelog.entry[entry].finished) {
-				entry++;
-				continue;
-			}
-			break;
-		}
-		smp_rmb();
-		next = entry + 1;
-		if (cmpxchg(&mcelog.next, entry, next) == entry)
-			break;
-	}
-	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
-	wmb();
-	mcelog.entry[entry].finished = 1;
-	wmb();
-
-	set_bit(0, &mce_need_notify);
 }
 
 void mce_inject_log(struct mce *m)
 {
-	mutex_lock(&mce_chrdev_read_mutex);
+	mutex_lock(&mce_log_mutex);
 	mce_log(m);
-	mutex_unlock(&mce_chrdev_read_mutex);
+	mutex_unlock(&mce_log_mutex);
 }
 EXPORT_SYMBOL_GPL(mce_inject_log);
 
 static struct notifier_block mce_srao_nb;
 
+/*
+ * We run the default notifier if we have only the SRAO, the first and the
+ * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
+ * notifiers registered on the chain.
+ */
+#define NUM_DEFAULT_NOTIFIERS	3
 static atomic_t num_notifiers;
 
 void mce_register_decode_chain(struct notifier_block *nb)
 {
-	atomic_inc(&num_notifiers);
+	if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
+		return;
 
-	WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
+	atomic_inc(&num_notifiers);
 
-	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_register_decode_chain);
 
@@ -226,7 +170,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb)
 {
 	atomic_dec(&num_notifiers);
 
-	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+	blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
 
@@ -319,18 +263,7 @@ static void __print_mce(struct mce *m)
 
 static void print_mce(struct mce *m)
 {
-	int ret = 0;
-
 	__print_mce(m);
-
-	/*
-	 * Print out human-readable details about the MCE error,
-	 * (if the CPU has an implementation for that)
-	 */
-	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
-	if (ret == NOTIFY_STOP)
-		return;
-
 	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }
 
@@ -519,7 +452,6 @@ static void mce_schedule_work(void)
 
 static void mce_irq_work_cb(struct irq_work *entry)
 {
-	mce_notify_irq();
 	mce_schedule_work();
 }
 
@@ -548,20 +480,97 @@ static void mce_report_event(struct pt_regs *regs)
  */
 static int mce_usable_address(struct mce *m)
 {
-	if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
+	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
 	/* Checks after this one are Intel-specific: */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 1;
 
+	if (!(m->status & MCI_STATUS_MISCV))
+		return 0;
+
 	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
 		return 0;
+
 	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
 		return 0;
+
 	return 1;
 }
 
+static bool memory_error(struct mce *m)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		/* ErrCodeExt[20:16] */
+		u8 xec = (m->status >> 16) & 0x1f;
+
+		return (xec == 0x0 || xec == 0x8);
+	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
+		/*
+		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
+		 *
+		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
+		 * indicating a memory error. Bit 8 is used for indicating a
+		 * cache hierarchy error. The combination of bit 2 and bit 3
+		 * is used for indicating a `generic' cache hierarchy error
+		 * But we can't just blindly check the above bits, because if
+		 * bit 11 is set, then it is a bus/interconnect error - and
+		 * either way the above bits just gives more detail on what
+		 * bus/interconnect error happened. Note that bit 12 can be
+		 * ignored, as it's the "filter" bit.
+		 */
+		return (m->status & 0xef80) == BIT(7) ||
+		       (m->status & 0xef00) == BIT(8) ||
+		       (m->status & 0xeffc) == 0xc;
+	}
+
+	return false;
+}
+
+static bool cec_add_mce(struct mce *m)
+{
+	if (!m)
+		return false;
+
+	/* We eat only correctable DRAM errors with usable addresses. */
+	if (memory_error(m) &&
+	    !(m->status & MCI_STATUS_UC) &&
+	    mce_usable_address(m))
+		if (!cec_add_elem(m->addr >> PAGE_SHIFT))
+			return true;
+
+	return false;
+}
+
+static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
+			      void *data)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (!m)
+		return NOTIFY_DONE;
+
+	if (cec_add_mce(m))
+		return NOTIFY_STOP;
+
+	/* Emit the trace record: */
+	trace_mce_record(m);
+
+	set_bit(0, &mce_need_notify);
+
+	mce_notify_irq();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block first_nb = {
+	.notifier_call	= mce_first_notifier,
+	.priority	= MCE_PRIO_FIRST,
+};
+
 static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
@@ -591,11 +600,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 	if (!m)
 		return NOTIFY_DONE;
 
-	/*
-	 * Run the default notifier if we have only the SRAO
-	 * notifier and us registered.
-	 */
-	if (atomic_read(&num_notifiers) > 2)
+	if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
 		return NOTIFY_DONE;
 
 	__print_mce(m);
@@ -648,37 +653,6 @@ static void mce_read_aux(struct mce *m, int i)
 	}
 }
 
-static bool memory_error(struct mce *m)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* ErrCodeExt[20:16] */
-		u8 xec = (m->status >> 16) & 0x1f;
-
-		return (xec == 0x0 || xec == 0x8);
-	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
-		/*
-		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
-		 *
-		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
-		 * indicating a memory error. Bit 8 is used for indicating a
-		 * cache hierarchy error. The combination of bit 2 and bit 3
-		 * is used for indicating a `generic' cache hierarchy error
-		 * But we can't just blindly check the above bits, because if
-		 * bit 11 is set, then it is a bus/interconnect error - and
-		 * either way the above bits just gives more detail on what
-		 * bus/interconnect error happened. Note that bit 12 can be
-		 * ignored, as it's the "filter" bit.
-		 */
-		return (m->status & 0xef80) == BIT(7) ||
-		       (m->status & 0xef00) == BIT(8) ||
-		       (m->status & 0xeffc) == 0xc;
-	}
-
-	return false;
-}
-
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
@@ -1127,9 +1101,22 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * on Intel.
 	 */
 	int lmce = 1;
+	int cpu = smp_processor_id();
 
-	/* If this CPU is offline, just bail out. */
-	if (cpu_is_offline(smp_processor_id())) {
+	/*
+	 * Cases where we avoid rendezvous handler timeout:
+	 * 1) If this CPU is offline.
+	 *
+	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+	 *  skip those CPUs which remain looping in the 1st kernel - see
+	 *  crash_nmi_callback().
+	 *
+	 * Note: there still is a small window between kexec-ing and the new,
+	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
+	 * might not get handled properly.
+	 */
+	if (cpu_is_offline(cpu) ||
+	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
@@ -1399,13 +1386,6 @@ static void mce_timer_delete_all(void)
 		del_timer_sync(&per_cpu(mce_timer, cpu));
 }
 
-static void mce_do_trigger(struct work_struct *work)
-{
-	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
-}
-
-static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
-
 /*
  * Notify the user(s) about new machine check events.
  * Can be called from interrupt context, but not from machine check/NMI
@@ -1417,11 +1397,7 @@ int mce_notify_irq(void)
 	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
 
 	if (test_and_clear_bit(0, &mce_need_notify)) {
-		/* wake processes polling /dev/mcelog */
-		wake_up_interruptible(&mce_chrdev_wait);
-
-		if (mce_helper[0])
-			schedule_work(&mce_trigger_work);
+		mce_work_trigger();
 
 		if (__ratelimit(&ratelimit))
 			pr_info(HW_ERR "Machine check events logged\n");
@@ -1688,30 +1664,35 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 	return 0;
 }
 
-static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+/*
+ * Init basic CPU features needed for early decoding of MCEs.
+ */
+static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 {
-	switch (c->x86_vendor) {
-	case X86_VENDOR_INTEL:
-		mce_intel_feature_init(c);
-		mce_adjust_timer = cmci_intel_adjust_timer;
-		break;
-
-	case X86_VENDOR_AMD: {
+	if (c->x86_vendor == X86_VENDOR_AMD) {
 		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
 		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
 		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);
 
-		/*
-		 * Install proper ops for Scalable MCA enabled processors
-		 */
 		if (mce_flags.smca) {
 			msr_ops.ctl	= smca_ctl_reg;
 			msr_ops.status	= smca_status_reg;
 			msr_ops.addr	= smca_addr_reg;
 			msr_ops.misc	= smca_misc_reg;
 		}
-		mce_amd_feature_init(c);
+	}
+}
+
+static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_vendor) {
+	case X86_VENDOR_INTEL:
+		mce_intel_feature_init(c);
+		mce_adjust_timer = cmci_intel_adjust_timer;
+		break;
 
+	case X86_VENDOR_AMD: {
+		mce_amd_feature_init(c);
 		break;
 		}
 
@@ -1798,6 +1779,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	machine_check_vector = do_machine_check;
 
+	__mcheck_cpu_init_early(c);
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
@@ -1823,252 +1805,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c)
 
 }
 
-/*
- * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
- */
-
-static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_count;	/* #times opened */
-static int mce_chrdev_open_exclu;	/* already open exclusive? */
-
-static int mce_chrdev_open(struct inode *inode, struct file *file)
-{
-	spin_lock(&mce_chrdev_state_lock);
-
-	if (mce_chrdev_open_exclu ||
-	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
-		spin_unlock(&mce_chrdev_state_lock);
-
-		return -EBUSY;
-	}
-
-	if (file->f_flags & O_EXCL)
-		mce_chrdev_open_exclu = 1;
-	mce_chrdev_open_count++;
-
-	spin_unlock(&mce_chrdev_state_lock);
-
-	return nonseekable_open(inode, file);
-}
-
-static int mce_chrdev_release(struct inode *inode, struct file *file)
-{
-	spin_lock(&mce_chrdev_state_lock);
-
-	mce_chrdev_open_count--;
-	mce_chrdev_open_exclu = 0;
-
-	spin_unlock(&mce_chrdev_state_lock);
-
-	return 0;
-}
-
-static void collect_tscs(void *data)
-{
-	unsigned long *cpu_tsc = (unsigned long *)data;
-
-	cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
-static int mce_apei_read_done;
-
-/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
-static int __mce_read_apei(char __user **ubuf, size_t usize)
-{
-	int rc;
-	u64 record_id;
-	struct mce m;
-
-	if (usize < sizeof(struct mce))
-		return -EINVAL;
-
-	rc = apei_read_mce(&m, &record_id);
-	/* Error or no more MCE record */
-	if (rc <= 0) {
-		mce_apei_read_done = 1;
-		/*
-		 * When ERST is disabled, mce_chrdev_read() should return
-		 * "no record" instead of "no device."
-		 */
-		if (rc == -ENODEV)
-			return 0;
-		return rc;
-	}
-	rc = -EFAULT;
-	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
-		return rc;
-	/*
-	 * In fact, we should have cleared the record after that has
-	 * been flushed to the disk or sent to network in
-	 * /sbin/mcelog, but we have no interface to support that now,
-	 * so just clear it to avoid duplication.
-	 */
-	rc = apei_clear_mce(record_id);
-	if (rc) {
-		mce_apei_read_done = 1;
-		return rc;
-	}
-	*ubuf += sizeof(struct mce);
-
-	return 0;
-}
-
-static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
-				size_t usize, loff_t *off)
-{
-	char __user *buf = ubuf;
-	unsigned long *cpu_tsc;
-	unsigned prev, next;
-	int i, err;
-
-	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
-	if (!cpu_tsc)
-		return -ENOMEM;
-
-	mutex_lock(&mce_chrdev_read_mutex);
-
-	if (!mce_apei_read_done) {
-		err = __mce_read_apei(&buf, usize);
-		if (err || buf != ubuf)
-			goto out;
-	}
-
-	next = mce_log_get_idx_check(mcelog.next);
-
-	/* Only supports full reads right now */
-	err = -EINVAL;
-	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
-		goto out;
-
-	err = 0;
-	prev = 0;
-	do {
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			struct mce *m = &mcelog.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2)) {
-					memset(m, 0, sizeof(*m));
-					goto timeout;
-				}
-				cpu_relax();
-			}
-			smp_rmb();
-			err |= copy_to_user(buf, m, sizeof(*m));
-			buf += sizeof(*m);
-timeout:
-			;
-		}
-
-		memset(mcelog.entry + prev, 0,
-		       (next - prev) * sizeof(struct mce));
-		prev = next;
-		next = cmpxchg(&mcelog.next, prev, 0);
-	} while (next != prev);
-
-	synchronize_sched();
-
-	/*
-	 * Collect entries that were still getting written before the
-	 * synchronize.
-	 */
-	on_each_cpu(collect_tscs, cpu_tsc, 1);
-
-	for (i = next; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog.entry[i];
-
-		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
-			err |= copy_to_user(buf, m, sizeof(*m));
-			smp_rmb();
-			buf += sizeof(*m);
-			memset(m, 0, sizeof(*m));
-		}
-	}
-
-	if (err)
-		err = -EFAULT;
-
-out:
-	mutex_unlock(&mce_chrdev_read_mutex);
-	kfree(cpu_tsc);
-
-	return err ? err : buf - ubuf;
-}
-
-static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
-{
-	poll_wait(file, &mce_chrdev_wait, wait);
-	if (READ_ONCE(mcelog.next))
-		return POLLIN | POLLRDNORM;
-	if (!mce_apei_read_done && apei_check_mce())
-		return POLLIN | POLLRDNORM;
-	return 0;
-}
-
-static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
-				unsigned long arg)
-{
-	int __user *p = (int __user *)arg;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	switch (cmd) {
-	case MCE_GET_RECORD_LEN:
-		return put_user(sizeof(struct mce), p);
-	case MCE_GET_LOG_LEN:
-		return put_user(MCE_LOG_LEN, p);
-	case MCE_GETCLEAR_FLAGS: {
-		unsigned flags;
-
-		do {
-			flags = mcelog.flags;
-		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);
-
-		return put_user(flags, p);
-	}
-	default:
-		return -ENOTTY;
-	}
-}
-
-static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
-			    size_t usize, loff_t *off);
-
-void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
-			     const char __user *ubuf,
-			     size_t usize, loff_t *off))
-{
-	mce_write = fn;
-}
-EXPORT_SYMBOL_GPL(register_mce_write_callback);
-
-static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-				size_t usize, loff_t *off)
-{
-	if (mce_write)
-		return mce_write(filp, ubuf, usize, off);
-	else
-		return -EINVAL;
-}
-
-static const struct file_operations mce_chrdev_ops = {
-	.open			= mce_chrdev_open,
-	.release		= mce_chrdev_release,
-	.read			= mce_chrdev_read,
-	.write			= mce_chrdev_write,
-	.poll			= mce_chrdev_poll,
-	.unlocked_ioctl		= mce_chrdev_ioctl,
-	.llseek			= no_llseek,
-};
-
-static struct miscdevice mce_chrdev_device = {
-	MISC_MCELOG_MINOR,
-	"mcelog",
-	&mce_chrdev_ops,
-};
-
 static void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
@@ -2142,6 +1878,7 @@ __setup("mce", mcheck_enable);
 int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
+	mce_register_decode_chain(&first_nb);
 	mce_register_decode_chain(&mce_srao_nb);
 	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
@@ -2286,29 +2023,6 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 	return size;
 }
 
-static ssize_t
-show_trigger(struct device *s, struct device_attribute *attr, char *buf)
-{
-	strcpy(buf, mce_helper);
-	strcat(buf, "\n");
-	return strlen(mce_helper) + 1;
-}
-
-static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
-				const char *buf, size_t siz)
-{
-	char *p;
-
-	strncpy(mce_helper, buf, sizeof(mce_helper));
-	mce_helper[sizeof(mce_helper)-1] = 0;
-	p = strchr(mce_helper, '\n');
-
-	if (p)
-		*p = 0;
-
-	return strlen(mce_helper) + !!p;
-}
-
 static ssize_t set_ignore_ce(struct device *s,
 			     struct device_attribute *attr,
 			     const char *buf, size_t size)
@@ -2365,7 +2079,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	return ret;
 }
 
-static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
 static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
 static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
 static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
@@ -2388,7 +2101,9 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = {
 static struct device_attribute *mce_device_attrs[] = {
 	&dev_attr_tolerant.attr,
 	&dev_attr_check_interval.attr,
+#ifdef CONFIG_X86_MCELOG_LEGACY
 	&dev_attr_trigger,
+#endif
 	&dev_attr_monarch_timeout.attr,
 	&dev_attr_dont_log_ce.attr,
 	&dev_attr_ignore_ce.attr,
@@ -2562,7 +2277,6 @@ static __init void mce_init_banks(void)
 
 static __init int mcheck_init_device(void)
 {
-	enum cpuhp_state hp_online;
 	int err;
 
 	if (!mce_available(&boot_cpu_data)) {
@@ -2590,21 +2304,11 @@ static __init int mcheck_init_device(void)
 				mce_cpu_online, mce_cpu_pre_down);
 	if (err < 0)
 		goto err_out_online;
-	hp_online = err;
 
 	register_syscore_ops(&mce_syscore_ops);
 
-	/* register character device /dev/mcelog */
-	err = misc_register(&mce_chrdev_device);
-	if (err)
-		goto err_register;
-
 	return 0;
 
-err_register:
-	unregister_syscore_ops(&mce_syscore_ops);
-	cpuhp_remove_state(hp_online);
-
 err_out_online:
 	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);
 
@@ -2612,7 +2316,7 @@ err_out_mem:
 	free_cpumask_var(mce_device_initialized);
 
 err_out:
-	pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+	pr_err("Unable to init MCE device (rc: %d)\n", err);
 
 	return err;
 }
@@ -2691,6 +2395,7 @@ static int __init mcheck_late_init(void)
 		static_branch_inc(&mcsafe_key);
 
 	mcheck_debugfs_init();
+	cec_init();
 
 	/*
 	 * Flush out everything that has been logged during early boot, now that
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 524cc5780a77..6e4a047e4b68 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -60,7 +60,7 @@ static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
 	"combined_unit",
-	"",
+	"decode_unit",
 	"northbridge",
 	"execution_unit",
 };
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 190b3e6cef4d..e84db79ef272 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -481,6 +481,9 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_XEON_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
+
 		if (rdmsrl_safe(MSR_PPIN_CTL, &val))
 			return;
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 3b442b64c72d..765afd599039 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -27,7 +27,7 @@
 #include <linux/range.h>
 
 #include <asm/processor.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 
@@ -860,7 +860,7 @@ real_trim_memory(unsigned long start_pfn, unsigned long limit_pfn)
 	trim_size <<= PAGE_SHIFT;
 	trim_size -= trim_start;
 
-	return e820_update_range(trim_start, trim_size, E820_RAM, E820_RESERVED);
+	return e820__range_update(trim_start, trim_size, E820_TYPE_RAM, E820_TYPE_RESERVED);
 }
 
 /**
@@ -978,7 +978,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 			WARN_ON(1);
 
 		pr_info("update e820 for mtrr\n");
-		update_e820();
+		e820__update_table_print();
 
 		return 1;
 	}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 24e87e74990d..2bce84d91c2b 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -48,7 +48,7 @@
 #include <linux/syscore_ops.h>
 
 #include <asm/cpufeature.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 #include <asm/pat.h>
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 18ca99f2798b..6df621ae62a7 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -31,14 +31,13 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
 		   "fpu\t\t: %s\n"
 		   "fpu_exception\t: %s\n"
 		   "cpuid level\t: %d\n"
-		   "wp\t\t: %s\n",
+		   "wp\t\t: yes\n",
 		   static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
 		   static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
 		   static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
 		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
 		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
-		   c->cpuid_level,
-		   c->wp_works_ok ? "yes" : "no");
+		   c->cpuid_level);
 }
 #else
 static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index d9794060fe22..23c23508c012 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
 	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
 	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
+	{ X86_FEATURE_MBA,		CPUID_EBX,  3, 0x00000010, 0 },
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 8457b4978668..d77d07ab310b 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
 		if (xlvl >= 0x80860001)
 			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
-
-	clear_sched_clock_stable();
 }
 
 static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 891f4dad7b2c..22403a28caf5 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,7 +30,6 @@
 #include <asm/hypervisor.h>
 #include <asm/timer.h>
 #include <asm/apic.h>
-#include <asm/timer.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"vmware: " fmt
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 3741461c63a0..22217ece26c8 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -29,6 +29,7 @@
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
+#include <asm/e820/types.h>
 #include <asm/io_apic.h>
 #include <asm/hpet.h>
 #include <linux/kdebug.h>
@@ -503,16 +504,16 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 	return ret;
 }
 
-static int add_e820_entry(struct boot_params *params, struct e820entry *entry)
+static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
 {
 	unsigned int nr_e820_entries;
 
 	nr_e820_entries = params->e820_entries;
-	if (nr_e820_entries >= E820MAX)
+	if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE)
 		return 1;
 
-	memcpy(&params->e820_map[nr_e820_entries], entry,
-			sizeof(struct e820entry));
+	memcpy(&params->e820_table[nr_e820_entries], entry,
+			sizeof(struct e820_entry));
 	params->e820_entries++;
 	return 0;
 }
@@ -521,7 +522,7 @@ static int memmap_entry_callback(u64 start, u64 end, void *arg)
 {
 	struct crash_memmap_data *cmd = arg;
 	struct boot_params *params = cmd->params;
-	struct e820entry ei;
+	struct e820_entry ei;
 
 	ei.addr = start;
 	ei.size = end - start + 1;
@@ -560,7 +561,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 {
 	int i, ret = 0;
 	unsigned long flags;
-	struct e820entry ei;
+	struct e820_entry ei;
 	struct crash_memmap_data cmd;
 	struct crash_mem *cmem;
 
@@ -574,17 +575,17 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	/* Add first 640K segment */
 	ei.addr = image->arch.backup_src_start;
 	ei.size = image->arch.backup_src_sz;
-	ei.type = E820_RAM;
+	ei.type = E820_TYPE_RAM;
 	add_e820_entry(params, &ei);
 
 	/* Add ACPI tables */
-	cmd.type = E820_ACPI;
+	cmd.type = E820_TYPE_ACPI;
 	flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
 		       memmap_entry_callback);
 
 	/* Add ACPI Non-volatile Storage */
-	cmd.type = E820_NVS;
+	cmd.type = E820_TYPE_NVS;
 	walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
 			memmap_entry_callback);
 
@@ -592,7 +593,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	if (crashk_low_res.end) {
 		ei.addr = crashk_low_res.start;
 		ei.size = crashk_low_res.end - crashk_low_res.start + 1;
-		ei.type = E820_RAM;
+		ei.type = E820_TYPE_RAM;
 		add_e820_entry(params, &ei);
 	}
 
@@ -609,7 +610,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 		if (ei.size < PAGE_SIZE)
 			continue;
 		ei.addr = cmem->ranges[i].start;
-		ei.type = E820_RAM;
+		ei.type = E820_TYPE_RAM;
 		add_e820_entry(params, &ei);
 	}
 
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 09d4ac0d2661..dbce3cca94cb 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -77,7 +77,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - softirq stack
 	 * - hardirq stack
 	 */
-	for (regs = NULL; stack; stack = stack_info.next_sp) {
+	for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		const char *stack_name;
 
 		/*
@@ -289,9 +289,6 @@ void die(const char *str, struct pt_regs *regs, long err)
 	unsigned long flags = oops_begin();
 	int sig = SIGSEGV;
 
-	if (!user_mode(regs))
-		report_bug(regs->ip, regs);
-
 	if (__die(str, regs, err))
 		sig = 0;
 	oops_end(flags, regs, sig);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index b0b3a3df7c20..e5f0b40e66d2 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -162,15 +162,3 @@ void show_regs(struct pt_regs *regs)
 	}
 	pr_cont("\n");
 }
-
-int is_valid_bugaddr(unsigned long ip)
-{
-	unsigned short ud2;
-
-	if (ip < PAGE_OFFSET)
-		return 0;
-	if (probe_kernel_address((unsigned short *)ip, ud2))
-		return 0;
-
-	return ud2 == 0x0b0f;
-}
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index a8b117e93b46..3e1471d57487 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -178,13 +178,3 @@ void show_regs(struct pt_regs *regs)
 	}
 	pr_cont("\n");
 }
-
-int is_valid_bugaddr(unsigned long ip)
-{
-	unsigned short ud2;
-
-	if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2)))
-		return 0;
-
-	return ud2 == 0x0b0f;
-}
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index b2bbad6ebe4d..d78a586ba8dc 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1,49 +1,55 @@
 /*
- * Handle the memory map.
- * The functions here do the job until bootmem takes over.
+ * Low level x86 E820 memory map handling functions.
  *
- *  Getting sanitize_e820_map() in sync with i386 version by applying change:
- *  -  Provisions for empty E820 memory regions (reported by certain BIOSes).
- *     Alex Achenbach <xela@slit.de>, December 2002.
- *  Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ * The firmware and bootloader passes us the "E820 table", which is the primary
+ * physical memory layout description available about x86 systems.
  *
+ * The kernel takes the E820 memory layout and optionally modifies it with
+ * quirks and other tweaks, and feeds that into the generic Linux memory
+ * allocation code routines via a platform independent interface (memblock, etc.).
  */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
 #include <linux/crash_dump.h>
-#include <linux/export.h>
 #include <linux/bootmem.h>
-#include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <linux/firmware-map.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
 
-#include <asm/e820.h>
-#include <asm/proto.h>
+#include <asm/e820/api.h>
 #include <asm/setup.h>
-#include <asm/cpufeature.h>
 
 /*
- * The e820 map is the map that gets modified e.g. with command line parameters
- * and that is also registered with modifications in the kernel resource tree
- * with the iomem_resource as parent.
+ * We organize the E820 table into two main data structures:
  *
- * The e820_saved is directly saved after the BIOS-provided memory map is
- * copied. It doesn't get modified afterwards. It's registered for the
- * /sys/firmware/memmap interface.
+ * - 'e820_table_firmware': the original firmware version passed to us by the
+ *   bootloader - not modified by the kernel. We use this to:
  *
- * That memory map is not modified and is used as base for kexec. The kexec'd
- * kernel should get the same memory map as the firmware provides. Then the
- * user can e.g. boot the original kernel with mem=1G while still booting the
- * next kernel with full memory.
+ *       - inform the user about the firmware's notion of memory layout
+ *         via /sys/firmware/memmap
+ *
+ *       - the hibernation code uses it to generate a kernel-independent MD5
+ *         fingerprint of the physical memory layout of a system.
+ *
+ *       - kexec, which is a bootloader in disguise, uses the original E820
+ *         layout to pass to the kexec-ed kernel. This way the original kernel
+ *         can have a restricted E820 map while the kexec()-ed kexec-kernel
+ *         can have access to full memory - etc.
+ *
+ * - 'e820_table': this is the main E820 table that is massaged by the
+ *   low level x86 platform code, or modified by boot parameters, before
+ *   passed on to higher level MM layers.
+ *
+ * Once the E820 map has been converted to the standard Linux memory layout
+ * information its role stops - modifying it has no effect and does not get
+ * re-propagated. So itsmain role is a temporary bootstrap storage of firmware
+ * specific memory layout data during early bootup.
  */
-static struct e820map initial_e820  __initdata;
-static struct e820map initial_e820_saved  __initdata;
-struct e820map *e820 __refdata = &initial_e820;
-struct e820map *e820_saved __refdata = &initial_e820_saved;
+static struct e820_table e820_table_init		__initdata;
+static struct e820_table e820_table_firmware_init	__initdata;
+
+struct e820_table *e820_table __refdata			= &e820_table_init;
+struct e820_table *e820_table_firmware __refdata	= &e820_table_firmware_init;
 
 /* For PCI or other memory-mapped resources */
 unsigned long pci_mem_start = 0xaeedbabe;
@@ -55,51 +61,53 @@ EXPORT_SYMBOL(pci_mem_start);
  * This function checks if any part of the range <start,end> is mapped
  * with type.
  */
-int
-e820_any_mapped(u64 start, u64 end, unsigned type)
+bool e820__mapped_any(u64 start, u64 end, enum e820_type type)
 {
 	int i;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 
-		if (type && ei->type != type)
+		if (type && entry->type != type)
 			continue;
-		if (ei->addr >= end || ei->addr + ei->size <= start)
+		if (entry->addr >= end || entry->addr + entry->size <= start)
 			continue;
 		return 1;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(e820_any_mapped);
+EXPORT_SYMBOL_GPL(e820__mapped_any);
 
 /*
- * This function checks if the entire range <start,end> is mapped with type.
+ * This function checks if the entire <start,end> range is mapped with 'type'.
  *
- * Note: this function only works correct if the e820 table is sorted and
- * not-overlapping, which is the case
+ * Note: this function only works correctly once the E820 table is sorted and
+ * not-overlapping (at least for the range specified), which is the case normally.
  */
-int __init e820_all_mapped(u64 start, u64 end, unsigned type)
+bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type)
 {
 	int i;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 
-		if (type && ei->type != type)
+		if (type && entry->type != type)
 			continue;
-		/* is the region (part) in overlap with the current region ?*/
-		if (ei->addr >= end || ei->addr + ei->size <= start)
+
+		/* Is the region (part) in overlap with the current region? */
+		if (entry->addr >= end || entry->addr + entry->size <= start)
 			continue;
 
-		/* if the region is at the beginning of <start,end> we move
-		 * start to the end of the region since it's ok until there
+		/*
+		 * If the region is at the beginning of <start,end> we move
+		 * 'start' to the end of the region since it's ok until there
 		 */
-		if (ei->addr <= start)
-			start = ei->addr + ei->size;
+		if (entry->addr <= start)
+			start = entry->addr + entry->size;
+
 		/*
-		 * if start is now at or beyond end, we're done, full
-		 * coverage
+		 * If 'start' is now at or beyond 'end', we're done, full
+		 * coverage of the desired range exists:
 		 */
 		if (start >= end)
 			return 1;
@@ -108,94 +116,77 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type)
 }
 
 /*
- * Add a memory region to the kernel e820 map.
+ * Add a memory region to the kernel E820 map.
  */
-static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
-					 int type)
+static void __init __e820__range_add(struct e820_table *table, u64 start, u64 size, enum e820_type type)
 {
-	int x = e820x->nr_map;
+	int x = table->nr_entries;
 
-	if (x >= ARRAY_SIZE(e820x->map)) {
-		printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n",
-		       (unsigned long long) start,
-		       (unsigned long long) (start + size - 1));
+	if (x >= ARRAY_SIZE(table->entries)) {
+		pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1);
 		return;
 	}
 
-	e820x->map[x].addr = start;
-	e820x->map[x].size = size;
-	e820x->map[x].type = type;
-	e820x->nr_map++;
+	table->entries[x].addr = start;
+	table->entries[x].size = size;
+	table->entries[x].type = type;
+	table->nr_entries++;
 }
 
-void __init e820_add_region(u64 start, u64 size, int type)
+void __init e820__range_add(u64 start, u64 size, enum e820_type type)
 {
-	__e820_add_region(e820, start, size, type);
+	__e820__range_add(e820_table, start, size, type);
 }
 
-static void __init e820_print_type(u32 type)
+static void __init e820_print_type(enum e820_type type)
 {
 	switch (type) {
-	case E820_RAM:
-	case E820_RESERVED_KERN:
-		printk(KERN_CONT "usable");
-		break;
-	case E820_RESERVED:
-		printk(KERN_CONT "reserved");
-		break;
-	case E820_ACPI:
-		printk(KERN_CONT "ACPI data");
-		break;
-	case E820_NVS:
-		printk(KERN_CONT "ACPI NVS");
-		break;
-	case E820_UNUSABLE:
-		printk(KERN_CONT "unusable");
-		break;
-	case E820_PMEM:
-	case E820_PRAM:
-		printk(KERN_CONT "persistent (type %u)", type);
-		break;
-	default:
-		printk(KERN_CONT "type %u", type);
-		break;
+	case E820_TYPE_RAM:		/* Fall through: */
+	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
+	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
+	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
+	case E820_TYPE_NVS:		pr_cont("ACPI NVS");			break;
+	case E820_TYPE_UNUSABLE:	pr_cont("unusable");			break;
+	case E820_TYPE_PMEM:		/* Fall through: */
+	case E820_TYPE_PRAM:		pr_cont("persistent (type %u)", type);	break;
+	default:			pr_cont("type %u", type);		break;
 	}
 }
 
-void __init e820_print_map(char *who)
+void __init e820__print_table(char *who)
 {
 	int i;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who,
-		       (unsigned long long) e820->map[i].addr,
-		       (unsigned long long)
-		       (e820->map[i].addr + e820->map[i].size - 1));
-		e820_print_type(e820->map[i].type);
-		printk(KERN_CONT "\n");
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		pr_info("%s: [mem %#018Lx-%#018Lx] ", who,
+		       e820_table->entries[i].addr,
+		       e820_table->entries[i].addr + e820_table->entries[i].size - 1);
+
+		e820_print_type(e820_table->entries[i].type);
+		pr_cont("\n");
 	}
 }
 
 /*
- * Sanitize the BIOS e820 map.
+ * Sanitize an E820 map.
  *
- * Some e820 responses include overlapping entries. The following
- * replaces the original e820 map with a new one, removing overlaps,
+ * Some E820 layouts include overlapping entries. The following
+ * replaces the original E820 map with a new one, removing overlaps,
  * and resolving conflicting memory types in favor of highest
  * numbered type.
  *
- * The input parameter biosmap points to an array of 'struct
- * e820entry' which on entry has elements in the range [0, *pnr_map)
- * valid, and which has space for up to max_nr_map entries.
- * On return, the resulting sanitized e820 map entries will be in
- * overwritten in the same location, starting at biosmap.
+ * The input parameter 'entries' points to an array of 'struct
+ * e820_entry' which on entry has elements in the range [0, *nr_entries)
+ * valid, and which has space for up to max_nr_entries entries.
+ * On return, the resulting sanitized E820 map entries will be in
+ * overwritten in the same location, starting at 'entries'.
  *
- * The integer pointed to by pnr_map must be valid on entry (the
- * current number of valid entries located at biosmap). If the
- * sanitizing succeeds the *pnr_map will be updated with the new
- * number of valid entries (something no more than max_nr_map).
+ * The integer pointed to by nr_entries must be valid on entry (the
+ * current number of valid entries located at 'entries'). If the
+ * sanitizing succeeds the *nr_entries will be updated with the new
+ * number of valid entries (something no more than max_nr_entries).
  *
- * The return value from sanitize_e820_map() is zero if it
+ * The return value from e820__update_table() is zero if it
  * successfully 'sanitized' the map entries passed in, and is -1
  * if it did nothing, which can happen if either of (1) it was
  * only passed one map entry, or (2) any of the input map entries
@@ -238,10 +229,17 @@ void __init e820_print_map(char *who)
  *	   ______________________4_
  */
 struct change_member {
-	struct e820entry *pbios; /* pointer to original bios entry */
-	unsigned long long addr; /* address for this change point */
+	/* Pointer to the original entry: */
+	struct e820_entry	*entry;
+	/* Address for this change point: */
+	unsigned long long	addr;
 };
 
+static struct change_member	change_point_list[2*E820_MAX_ENTRIES]	__initdata;
+static struct change_member	*change_point[2*E820_MAX_ENTRIES]	__initdata;
+static struct e820_entry	*overlap_list[E820_MAX_ENTRIES]		__initdata;
+static struct e820_entry	new_entries[E820_MAX_ENTRIES]		__initdata;
+
 static int __init cpcompare(const void *a, const void *b)
 {
 	struct change_member * const *app = a, * const *bpp = b;
@@ -249,164 +247,140 @@ static int __init cpcompare(const void *a, const void *b)
 
 	/*
 	 * Inputs are pointers to two elements of change_point[].  If their
-	 * addresses are unequal, their difference dominates.  If the addresses
+	 * addresses are not equal, their difference dominates.  If the addresses
 	 * are equal, then consider one that represents the end of its region
 	 * to be greater than one that does not.
 	 */
 	if (ap->addr != bp->addr)
 		return ap->addr > bp->addr ? 1 : -1;
 
-	return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr);
+	return (ap->addr != ap->entry->addr) - (bp->addr != bp->entry->addr);
 }
 
-int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
-			     u32 *pnr_map)
+int __init e820__update_table(struct e820_table *table)
 {
-	static struct change_member change_point_list[2*E820_X_MAX] __initdata;
-	static struct change_member *change_point[2*E820_X_MAX] __initdata;
-	static struct e820entry *overlap_list[E820_X_MAX] __initdata;
-	static struct e820entry new_bios[E820_X_MAX] __initdata;
-	unsigned long current_type, last_type;
+	struct e820_entry *entries = table->entries;
+	u32 max_nr_entries = ARRAY_SIZE(table->entries);
+	enum e820_type current_type, last_type;
 	unsigned long long last_addr;
-	int chgidx;
-	int overlap_entries;
-	int new_bios_entry;
-	int old_nr, new_nr, chg_nr;
-	int i;
+	u32 new_nr_entries, overlap_entries;
+	u32 i, chg_idx, chg_nr;
 
-	/* if there's only one memory region, don't bother */
-	if (*pnr_map < 2)
+	/* If there's only one memory region, don't bother: */
+	if (table->nr_entries < 2)
 		return -1;
 
-	old_nr = *pnr_map;
-	BUG_ON(old_nr > max_nr_map);
+	BUG_ON(table->nr_entries > max_nr_entries);
 
-	/* bail out if we find any unreasonable addresses in bios map */
-	for (i = 0; i < old_nr; i++)
-		if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
+	/* Bail out if we find any unreasonable addresses in the map: */
+	for (i = 0; i < table->nr_entries; i++) {
+		if (entries[i].addr + entries[i].size < entries[i].addr)
 			return -1;
+	}
 
-	/* create pointers for initial change-point information (for sorting) */
-	for (i = 0; i < 2 * old_nr; i++)
+	/* Create pointers for initial change-point information (for sorting): */
+	for (i = 0; i < 2 * table->nr_entries; i++)
 		change_point[i] = &change_point_list[i];
 
-	/* record all known change-points (starting and ending addresses),
-	   omitting those that are for empty memory regions */
-	chgidx = 0;
-	for (i = 0; i < old_nr; i++)	{
-		if (biosmap[i].size != 0) {
-			change_point[chgidx]->addr = biosmap[i].addr;
-			change_point[chgidx++]->pbios = &biosmap[i];
-			change_point[chgidx]->addr = biosmap[i].addr +
-				biosmap[i].size;
-			change_point[chgidx++]->pbios = &biosmap[i];
+	/*
+	 * Record all known change-points (starting and ending addresses),
+	 * omitting empty memory regions:
+	 */
+	chg_idx = 0;
+	for (i = 0; i < table->nr_entries; i++)	{
+		if (entries[i].size != 0) {
+			change_point[chg_idx]->addr	= entries[i].addr;
+			change_point[chg_idx++]->entry	= &entries[i];
+			change_point[chg_idx]->addr	= entries[i].addr + entries[i].size;
+			change_point[chg_idx++]->entry	= &entries[i];
 		}
 	}
-	chg_nr = chgidx;
-
-	/* sort change-point list by memory addresses (low -> high) */
-	sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL);
-
-	/* create a new bios memory map, removing overlaps */
-	overlap_entries = 0;	 /* number of entries in the overlap table */
-	new_bios_entry = 0;	 /* index for creating new bios map entries */
-	last_type = 0;		 /* start with undefined memory type */
-	last_addr = 0;		 /* start with 0 as last starting address */
-
-	/* loop through change-points, determining affect on the new bios map */
-	for (chgidx = 0; chgidx < chg_nr; chgidx++) {
-		/* keep track of all overlapping bios entries */
-		if (change_point[chgidx]->addr ==
-		    change_point[chgidx]->pbios->addr) {
-			/*
-			 * add map entry to overlap list (> 1 entry
-			 * implies an overlap)
-			 */
-			overlap_list[overlap_entries++] =
-				change_point[chgidx]->pbios;
+	chg_nr = chg_idx;
+
+	/* Sort change-point list by memory addresses (low -> high): */
+	sort(change_point, chg_nr, sizeof(*change_point), cpcompare, NULL);
+
+	/* Create a new memory map, removing overlaps: */
+	overlap_entries = 0;	 /* Number of entries in the overlap table */
+	new_nr_entries = 0;	 /* Index for creating new map entries */
+	last_type = 0;		 /* Start with undefined memory type */
+	last_addr = 0;		 /* Start with 0 as last starting address */
+
+	/* Loop through change-points, determining effect on the new map: */
+	for (chg_idx = 0; chg_idx < chg_nr; chg_idx++) {
+		/* Keep track of all overlapping entries */
+		if (change_point[chg_idx]->addr == change_point[chg_idx]->entry->addr) {
+			/* Add map entry to overlap list (> 1 entry implies an overlap) */
+			overlap_list[overlap_entries++] = change_point[chg_idx]->entry;
 		} else {
-			/*
-			 * remove entry from list (order independent,
-			 * so swap with last)
-			 */
+			/* Remove entry from list (order independent, so swap with last): */
 			for (i = 0; i < overlap_entries; i++) {
-				if (overlap_list[i] ==
-				    change_point[chgidx]->pbios)
-					overlap_list[i] =
-						overlap_list[overlap_entries-1];
+				if (overlap_list[i] == change_point[chg_idx]->entry)
+					overlap_list[i] = overlap_list[overlap_entries-1];
 			}
 			overlap_entries--;
 		}
 		/*
-		 * if there are overlapping entries, decide which
+		 * If there are overlapping entries, decide which
 		 * "type" to use (larger value takes precedence --
 		 * 1=usable, 2,3,4,4+=unusable)
 		 */
 		current_type = 0;
-		for (i = 0; i < overlap_entries; i++)
+		for (i = 0; i < overlap_entries; i++) {
 			if (overlap_list[i]->type > current_type)
 				current_type = overlap_list[i]->type;
-		/*
-		 * continue building up new bios map based on this
-		 * information
-		 */
-		if (current_type != last_type || current_type == E820_PRAM) {
+		}
+
+		/* Continue building up new map based on this information: */
+		if (current_type != last_type || current_type == E820_TYPE_PRAM) {
 			if (last_type != 0)	 {
-				new_bios[new_bios_entry].size =
-					change_point[chgidx]->addr - last_addr;
-				/*
-				 * move forward only if the new size
-				 * was non-zero
-				 */
-				if (new_bios[new_bios_entry].size != 0)
-					/*
-					 * no more space left for new
-					 * bios entries ?
-					 */
-					if (++new_bios_entry >= max_nr_map)
+				new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr;
+				/* Move forward only if the new size was non-zero: */
+				if (new_entries[new_nr_entries].size != 0)
+					/* No more space left for new entries? */
+					if (++new_nr_entries >= max_nr_entries)
 						break;
 			}
 			if (current_type != 0)	{
-				new_bios[new_bios_entry].addr =
-					change_point[chgidx]->addr;
-				new_bios[new_bios_entry].type = current_type;
-				last_addr = change_point[chgidx]->addr;
+				new_entries[new_nr_entries].addr = change_point[chg_idx]->addr;
+				new_entries[new_nr_entries].type = current_type;
+				last_addr = change_point[chg_idx]->addr;
 			}
 			last_type = current_type;
 		}
 	}
-	/* retain count for new bios entries */
-	new_nr = new_bios_entry;
 
-	/* copy new bios mapping into original location */
-	memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry));
-	*pnr_map = new_nr;
+	/* Copy the new entries into the original location: */
+	memcpy(entries, new_entries, new_nr_entries*sizeof(*entries));
+	table->nr_entries = new_nr_entries;
 
 	return 0;
 }
 
-static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
+static int __init __append_e820_table(struct boot_e820_entry *entries, u32 nr_entries)
 {
-	while (nr_map) {
-		u64 start = biosmap->addr;
-		u64 size = biosmap->size;
+	struct boot_e820_entry *entry = entries;
+
+	while (nr_entries) {
+		u64 start = entry->addr;
+		u64 size = entry->size;
 		u64 end = start + size - 1;
-		u32 type = biosmap->type;
+		u32 type = entry->type;
 
-		/* Overflow in 64 bits? Ignore the memory map. */
+		/* Ignore the entry on 64-bit overflow: */
 		if (start > end && likely(size))
 			return -1;
 
-		e820_add_region(start, size, type);
+		e820__range_add(start, size, type);
 
-		biosmap++;
-		nr_map--;
+		entry++;
+		nr_entries--;
 	}
 	return 0;
 }
 
 /*
- * Copy the BIOS e820 map into a safe place.
+ * Copy the BIOS E820 map into a safe place.
  *
  * Sanity-check it while we're at it..
  *
@@ -414,18 +388,17 @@ static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
  * will have given us a memory map that we can use to properly
  * set up memory.  If we aren't, we'll fake a memory map.
  */
-static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
+static int __init append_e820_table(struct boot_e820_entry *entries, u32 nr_entries)
 {
 	/* Only one memory region (or negative)? Ignore it */
-	if (nr_map < 2)
+	if (nr_entries < 2)
 		return -1;
 
-	return __append_e820_map(biosmap, nr_map);
+	return __append_e820_table(entries, nr_entries);
 }
 
-static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
-					u64 size, unsigned old_type,
-					unsigned new_type)
+static u64 __init
+__e820__range_update(struct e820_table *table, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
 {
 	u64 end;
 	unsigned int i;
@@ -437,77 +410,73 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
 		size = ULLONG_MAX - start;
 
 	end = start + size;
-	printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ",
-	       (unsigned long long) start, (unsigned long long) (end - 1));
+	printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", start, end - 1);
 	e820_print_type(old_type);
-	printk(KERN_CONT " ==> ");
+	pr_cont(" ==> ");
 	e820_print_type(new_type);
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 
-	for (i = 0; i < e820x->nr_map; i++) {
-		struct e820entry *ei = &e820x->map[i];
+	for (i = 0; i < table->nr_entries; i++) {
+		struct e820_entry *entry = &table->entries[i];
 		u64 final_start, final_end;
-		u64 ei_end;
+		u64 entry_end;
 
-		if (ei->type != old_type)
+		if (entry->type != old_type)
 			continue;
 
-		ei_end = ei->addr + ei->size;
-		/* totally covered by new range? */
-		if (ei->addr >= start && ei_end <= end) {
-			ei->type = new_type;
-			real_updated_size += ei->size;
+		entry_end = entry->addr + entry->size;
+
+		/* Completely covered by new range? */
+		if (entry->addr >= start && entry_end <= end) {
+			entry->type = new_type;
+			real_updated_size += entry->size;
 			continue;
 		}
 
-		/* new range is totally covered? */
-		if (ei->addr < start && ei_end > end) {
-			__e820_add_region(e820x, start, size, new_type);
-			__e820_add_region(e820x, end, ei_end - end, ei->type);
-			ei->size = start - ei->addr;
+		/* New range is completely covered? */
+		if (entry->addr < start && entry_end > end) {
+			__e820__range_add(table, start, size, new_type);
+			__e820__range_add(table, end, entry_end - end, entry->type);
+			entry->size = start - entry->addr;
 			real_updated_size += size;
 			continue;
 		}
 
-		/* partially covered */
-		final_start = max(start, ei->addr);
-		final_end = min(end, ei_end);
+		/* Partially covered: */
+		final_start = max(start, entry->addr);
+		final_end = min(end, entry_end);
 		if (final_start >= final_end)
 			continue;
 
-		__e820_add_region(e820x, final_start, final_end - final_start,
-				  new_type);
+		__e820__range_add(table, final_start, final_end - final_start, new_type);
 
 		real_updated_size += final_end - final_start;
 
 		/*
-		 * left range could be head or tail, so need to update
-		 * size at first.
+		 * Left range could be head or tail, so need to update
+		 * its size first:
 		 */
-		ei->size -= final_end - final_start;
-		if (ei->addr < final_start)
+		entry->size -= final_end - final_start;
+		if (entry->addr < final_start)
 			continue;
-		ei->addr = final_end;
+
+		entry->addr = final_end;
 	}
 	return real_updated_size;
 }
 
-u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
-			     unsigned new_type)
+u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
 {
-	return __e820_update_range(e820, start, size, old_type, new_type);
+	return __e820__range_update(e820_table, start, size, old_type, new_type);
 }
 
-static u64 __init e820_update_range_saved(u64 start, u64 size,
-					  unsigned old_type, unsigned new_type)
+static u64 __init e820__range_update_firmware(u64 start, u64 size, enum e820_type old_type, enum e820_type  new_type)
 {
-	return __e820_update_range(e820_saved, start, size, old_type,
-				     new_type);
+	return __e820__range_update(e820_table_firmware, start, size, old_type, new_type);
 }
 
-/* make e820 not cover the range */
-u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
-			     int checktype)
+/* Remove a range of memory from the E820 table: */
+u64 __init e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type)
 {
 	int i;
 	u64 end;
@@ -517,85 +486,89 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
 		size = ULLONG_MAX - start;
 
 	end = start + size;
-	printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ",
-	       (unsigned long long) start, (unsigned long long) (end - 1));
-	if (checktype)
+	printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", start, end - 1);
+	if (check_type)
 		e820_print_type(old_type);
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 		u64 final_start, final_end;
-		u64 ei_end;
+		u64 entry_end;
 
-		if (checktype && ei->type != old_type)
+		if (check_type && entry->type != old_type)
 			continue;
 
-		ei_end = ei->addr + ei->size;
-		/* totally covered? */
-		if (ei->addr >= start && ei_end <= end) {
-			real_removed_size += ei->size;
-			memset(ei, 0, sizeof(struct e820entry));
+		entry_end = entry->addr + entry->size;
+
+		/* Completely covered? */
+		if (entry->addr >= start && entry_end <= end) {
+			real_removed_size += entry->size;
+			memset(entry, 0, sizeof(*entry));
 			continue;
 		}
 
-		/* new range is totally covered? */
-		if (ei->addr < start && ei_end > end) {
-			e820_add_region(end, ei_end - end, ei->type);
-			ei->size = start - ei->addr;
+		/* Is the new range completely covered? */
+		if (entry->addr < start && entry_end > end) {
+			e820__range_add(end, entry_end - end, entry->type);
+			entry->size = start - entry->addr;
 			real_removed_size += size;
 			continue;
 		}
 
-		/* partially covered */
-		final_start = max(start, ei->addr);
-		final_end = min(end, ei_end);
+		/* Partially covered: */
+		final_start = max(start, entry->addr);
+		final_end = min(end, entry_end);
 		if (final_start >= final_end)
 			continue;
+
 		real_removed_size += final_end - final_start;
 
 		/*
-		 * left range could be head or tail, so need to update
-		 * size at first.
+		 * Left range could be head or tail, so need to update
+		 * the size first:
 		 */
-		ei->size -= final_end - final_start;
-		if (ei->addr < final_start)
+		entry->size -= final_end - final_start;
+		if (entry->addr < final_start)
 			continue;
-		ei->addr = final_end;
+
+		entry->addr = final_end;
 	}
 	return real_removed_size;
 }
 
-void __init update_e820(void)
+void __init e820__update_table_print(void)
 {
-	if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map))
+	if (e820__update_table(e820_table))
 		return;
-	printk(KERN_INFO "e820: modified physical RAM map:\n");
-	e820_print_map("modified");
+
+	pr_info("e820: modified physical RAM map:\n");
+	e820__print_table("modified");
 }
-static void __init update_e820_saved(void)
+
+static void __init e820__update_table_firmware(void)
 {
-	sanitize_e820_map(e820_saved->map, ARRAY_SIZE(e820_saved->map),
-				&e820_saved->nr_map);
+	e820__update_table(e820_table_firmware);
 }
+
 #define MAX_GAP_END 0x100000000ull
+
 /*
- * Search for a gap in the e820 memory space from 0 to MAX_GAP_END.
+ * Search for a gap in the E820 memory space from 0 to MAX_GAP_END (4GB).
  */
-static int __init e820_search_gap(unsigned long *gapstart,
-		unsigned long *gapsize)
+static int __init e820_search_gap(unsigned long *gapstart, unsigned long *gapsize)
 {
 	unsigned long long last = MAX_GAP_END;
-	int i = e820->nr_map;
+	int i = e820_table->nr_entries;
 	int found = 0;
 
 	while (--i >= 0) {
-		unsigned long long start = e820->map[i].addr;
-		unsigned long long end = start + e820->map[i].size;
+		unsigned long long start = e820_table->entries[i].addr;
+		unsigned long long end = start + e820_table->entries[i].size;
 
 		/*
 		 * Since "last" is at most 4GB, we know we'll
-		 * fit in 32 bits if this condition is true
+		 * fit in 32 bits if this condition is true:
 		 */
 		if (last > end) {
 			unsigned long gap = last - end;
@@ -613,12 +586,14 @@ static int __init e820_search_gap(unsigned long *gapstart,
 }
 
 /*
- * Search for the biggest gap in the low 32 bits of the e820
- * memory space.  We pass this space to PCI to assign MMIO resources
- * for hotplug or unconfigured devices in.
+ * Search for the biggest gap in the low 32 bits of the E820
+ * memory space. We pass this space to the PCI subsystem, so
+ * that it can assign MMIO resources for hotplug or
+ * unconfigured devices in.
+ *
  * Hopefully the BIOS let enough space left.
  */
-__init void e820_setup_gap(void)
+__init void e820__setup_pci_gap(void)
 {
 	unsigned long gapstart, gapsize;
 	int found;
@@ -629,138 +604,143 @@ __init void e820_setup_gap(void)
 	if (!found) {
 #ifdef CONFIG_X86_64
 		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
-		printk(KERN_ERR
-	"e820: cannot find a gap in the 32bit address range\n"
-	"e820: PCI devices with unassigned 32bit BARs may break!\n");
+		pr_err(
+			"e820: Cannot find an available gap in the 32-bit address range\n"
+			"e820: PCI devices with unassigned 32-bit BARs may not work!\n");
 #else
 		gapstart = 0x10000000;
 #endif
 	}
 
 	/*
-	 * e820_reserve_resources_late protect stolen RAM already
+	 * e820__reserve_resources_late() protects stolen RAM already:
 	 */
 	pci_mem_start = gapstart;
 
-	printk(KERN_INFO
-	       "e820: [mem %#010lx-%#010lx] available for PCI devices\n",
-	       gapstart, gapstart + gapsize - 1);
+	pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1);
 }
 
 /*
  * Called late during init, in free_initmem().
  *
- * Initial e820 and e820_saved are largish __initdata arrays.
- * Copy them to (usually much smaller) dynamically allocated area.
- * This is done after all tweaks we ever do to them:
- * all functions which modify them are __init functions,
- * they won't exist after this point.
+ * Initial e820_table and e820_table_firmware are largish __initdata arrays.
+ *
+ * Copy them to a (usually much smaller) dynamically allocated area that is
+ * sized precisely after the number of e820 entries.
+ *
+ * This is done after we've performed all the fixes and tweaks to the tables.
+ * All functions which modify them are __init functions, which won't exist
+ * after free_initmem().
  */
-__init void e820_reallocate_tables(void)
+__init void e820__reallocate_tables(void)
 {
-	struct e820map *n;
+	struct e820_table *n;
 	int size;
 
-	size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820->nr_map;
+	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries;
 	n = kmalloc(size, GFP_KERNEL);
 	BUG_ON(!n);
-	memcpy(n, e820, size);
-	e820 = n;
+	memcpy(n, e820_table, size);
+	e820_table = n;
 
-	size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820_saved->nr_map;
+	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries;
 	n = kmalloc(size, GFP_KERNEL);
 	BUG_ON(!n);
-	memcpy(n, e820_saved, size);
-	e820_saved = n;
+	memcpy(n, e820_table_firmware, size);
+	e820_table_firmware = n;
 }
 
-/**
- * Because of the size limitation of struct boot_params, only first
- * 128 E820 memory entries are passed to kernel via
- * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
- * linked list of struct setup_data, which is parsed here.
+/*
+ * Because of the small fixed size of struct boot_params, only the first
+ * 128 E820 memory entries are passed to the kernel via boot_params.e820_table,
+ * the remaining (if any) entries are passed via the SETUP_E820_EXT node of
+ * struct setup_data, which is parsed here.
  */
-void __init parse_e820_ext(u64 phys_addr, u32 data_len)
+void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
 {
 	int entries;
-	struct e820entry *extmap;
+	struct boot_e820_entry *extmap;
 	struct setup_data *sdata;
 
 	sdata = early_memremap(phys_addr, data_len);
-	entries = sdata->len / sizeof(struct e820entry);
-	extmap = (struct e820entry *)(sdata->data);
-	__append_e820_map(extmap, entries);
-	sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+	entries = sdata->len / sizeof(*extmap);
+	extmap = (struct boot_e820_entry *)(sdata->data);
+
+	__append_e820_table(extmap, entries);
+	e820__update_table(e820_table);
+
 	early_memunmap(sdata, data_len);
-	printk(KERN_INFO "e820: extended physical RAM map:\n");
-	e820_print_map("extended");
+	pr_info("e820: extended physical RAM map:\n");
+	e820__print_table("extended");
 }
 
-#if defined(CONFIG_X86_64) || \
-	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-/**
+/*
  * Find the ranges of physical addresses that do not correspond to
- * e820 RAM areas and mark the corresponding pages as nosave for
- * hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
+ * E820 RAM areas and register the corresponding pages as 'nosave' for
+ * hibernation (32-bit) or software suspend and suspend to RAM (64-bit).
  *
- * This function requires the e820 map to be sorted and without any
+ * This function requires the E820 map to be sorted and without any
  * overlapping entries.
  */
-void __init e820_mark_nosave_regions(unsigned long limit_pfn)
+void __init e820__register_nosave_regions(unsigned long limit_pfn)
 {
 	int i;
 	unsigned long pfn = 0;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 
-		if (pfn < PFN_UP(ei->addr))
-			register_nosave_region(pfn, PFN_UP(ei->addr));
+		if (pfn < PFN_UP(entry->addr))
+			register_nosave_region(pfn, PFN_UP(entry->addr));
 
-		pfn = PFN_DOWN(ei->addr + ei->size);
+		pfn = PFN_DOWN(entry->addr + entry->size);
 
-		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
-			register_nosave_region(PFN_UP(ei->addr), pfn);
+		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
+			register_nosave_region(PFN_UP(entry->addr), pfn);
 
 		if (pfn >= limit_pfn)
 			break;
 	}
 }
-#endif
 
 #ifdef CONFIG_ACPI
-/**
- * Mark ACPI NVS memory region, so that we can save/restore it during
- * hibernation and the subsequent resume.
+/*
+ * Register ACPI NVS memory regions, so that we can save/restore them during
+ * hibernation and the subsequent resume:
  */
-static int __init e820_mark_nvs_memory(void)
+static int __init e820__register_nvs_regions(void)
 {
 	int i;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 
-		if (ei->type == E820_NVS)
-			acpi_nvs_register(ei->addr, ei->size);
+		if (entry->type == E820_TYPE_NVS)
+			acpi_nvs_register(entry->addr, entry->size);
 	}
 
 	return 0;
 }
-core_initcall(e820_mark_nvs_memory);
+core_initcall(e820__register_nvs_regions);
 #endif
 
 /*
- * pre allocated 4k and reserved it in memblock and e820_saved
+ * Allocate the requested number of bytes with the requsted alignment
+ * and return (the physical address) to the caller. Also register this
+ * range in the 'firmware' E820 table as a reserved range.
+ *
+ * This allows kexec to fake a new mptable, as if it came from the real
+ * system.
  */
-u64 __init early_reserve_e820(u64 size, u64 align)
+u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
 {
 	u64 addr;
 
 	addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 	if (addr) {
-		e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
-		printk(KERN_INFO "e820: update e820_saved for early_reserve_e820\n");
-		update_e820_saved();
+		e820__range_update_firmware(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		pr_info("e820: update e820_table_firmware for e820__memblock_alloc_reserved()\n");
+		e820__update_table_firmware();
 	}
 
 	return addr;
@@ -779,22 +759,22 @@ u64 __init early_reserve_e820(u64 size, u64 align)
 /*
  * Find the highest page frame number we have available
  */
-static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type)
 {
 	int i;
 	unsigned long last_pfn = 0;
 	unsigned long max_arch_pfn = MAX_ARCH_PFN;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 		unsigned long start_pfn;
 		unsigned long end_pfn;
 
-		if (ei->type != type)
+		if (entry->type != type)
 			continue;
 
-		start_pfn = ei->addr >> PAGE_SHIFT;
-		end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
+		start_pfn = entry->addr >> PAGE_SHIFT;
+		end_pfn = (entry->addr + entry->size) >> PAGE_SHIFT;
 
 		if (start_pfn >= limit_pfn)
 			continue;
@@ -809,18 +789,19 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 	if (last_pfn > max_arch_pfn)
 		last_pfn = max_arch_pfn;
 
-	printk(KERN_INFO "e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
+	pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
 			 last_pfn, max_arch_pfn);
 	return last_pfn;
 }
-unsigned long __init e820_end_of_ram_pfn(void)
+
+unsigned long __init e820__end_of_ram_pfn(void)
 {
-	return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
+	return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM);
 }
 
-unsigned long __init e820_end_of_low_ram_pfn(void)
+unsigned long __init e820__end_of_low_ram_pfn(void)
 {
-	return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM);
+	return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM);
 }
 
 static void __init early_panic(char *msg)
@@ -831,7 +812,7 @@ static void __init early_panic(char *msg)
 
 static int userdef __initdata;
 
-/* "mem=nopentium" disables the 4MB page tables. */
+/* The "mem=nopentium" boot option disables 4MB page tables on 32-bit kernels: */
 static int __init parse_memopt(char *p)
 {
 	u64 mem_size;
@@ -844,17 +825,19 @@ static int __init parse_memopt(char *p)
 		setup_clear_cpu_cap(X86_FEATURE_PSE);
 		return 0;
 #else
-		printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
+		pr_warn("mem=nopentium ignored! (only supported on x86_32)\n");
 		return -EINVAL;
 #endif
 	}
 
 	userdef = 1;
 	mem_size = memparse(p, &p);
-	/* don't remove all of memory when handling "mem={invalid}" param */
+
+	/* Don't remove all memory when getting "mem={invalid}" parameter: */
 	if (mem_size == 0)
 		return -EINVAL;
-	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+
+	e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
 
 	return 0;
 }
@@ -872,12 +855,12 @@ static int __init parse_memmap_one(char *p)
 #ifdef CONFIG_CRASH_DUMP
 		/*
 		 * If we are doing a crash dump, we still need to know
-		 * the real mem size before original memory map is
+		 * the real memory size before the original memory map is
 		 * reset.
 		 */
-		saved_max_pfn = e820_end_of_ram_pfn();
+		saved_max_pfn = e820__end_of_ram_pfn();
 #endif
-		e820->nr_map = 0;
+		e820_table->nr_entries = 0;
 		userdef = 1;
 		return 0;
 	}
@@ -890,21 +873,23 @@ static int __init parse_memmap_one(char *p)
 	userdef = 1;
 	if (*p == '@') {
 		start_at = memparse(p+1, &p);
-		e820_add_region(start_at, mem_size, E820_RAM);
+		e820__range_add(start_at, mem_size, E820_TYPE_RAM);
 	} else if (*p == '#') {
 		start_at = memparse(p+1, &p);
-		e820_add_region(start_at, mem_size, E820_ACPI);
+		e820__range_add(start_at, mem_size, E820_TYPE_ACPI);
 	} else if (*p == '$') {
 		start_at = memparse(p+1, &p);
-		e820_add_region(start_at, mem_size, E820_RESERVED);
+		e820__range_add(start_at, mem_size, E820_TYPE_RESERVED);
 	} else if (*p == '!') {
 		start_at = memparse(p+1, &p);
-		e820_add_region(start_at, mem_size, E820_PRAM);
-	} else
-		e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+		e820__range_add(start_at, mem_size, E820_TYPE_PRAM);
+	} else {
+		e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
+	}
 
 	return *p == '\0' ? 0 : -EINVAL;
 }
+
 static int __init parse_memmap_opt(char *str)
 {
 	while (str) {
@@ -921,68 +906,97 @@ static int __init parse_memmap_opt(char *str)
 }
 early_param("memmap", parse_memmap_opt);
 
-void __init finish_e820_parsing(void)
+/*
+ * Reserve all entries from the bootloader's extensible data nodes list,
+ * because if present we are going to use it later on to fetch e820
+ * entries from it:
+ */
+void __init e820__reserve_setup_data(void)
+{
+	struct setup_data *data;
+	u64 pa_data;
+
+	pa_data = boot_params.hdr.setup_data;
+	if (!pa_data)
+		return;
+
+	while (pa_data) {
+		data = early_memremap(pa_data, sizeof(*data));
+		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+		pa_data = data->next;
+		early_memunmap(data, sizeof(*data));
+	}
+
+	e820__update_table(e820_table);
+
+	memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
+
+	pr_info("extended physical RAM map:\n");
+	e820__print_table("reserve setup_data");
+}
+
+/*
+ * Called after parse_early_param(), after early parameters (such as mem=)
+ * have been processed, in which case we already have an E820 table filled in
+ * via the parameter callback function(s), but it's not sorted and printed yet:
+ */
+void __init e820__finish_early_params(void)
 {
 	if (userdef) {
-		if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map),
-					&e820->nr_map) < 0)
+		if (e820__update_table(e820_table) < 0)
 			early_panic("Invalid user supplied memory map");
 
-		printk(KERN_INFO "e820: user-defined physical RAM map:\n");
-		e820_print_map("user");
+		pr_info("e820: user-defined physical RAM map:\n");
+		e820__print_table("user");
 	}
 }
 
-static const char *__init e820_type_to_string(int e820_type)
+static const char *__init e820_type_to_string(struct e820_entry *entry)
 {
-	switch (e820_type) {
-	case E820_RESERVED_KERN:
-	case E820_RAM:	return "System RAM";
-	case E820_ACPI:	return "ACPI Tables";
-	case E820_NVS:	return "ACPI Non-volatile Storage";
-	case E820_UNUSABLE:	return "Unusable memory";
-	case E820_PRAM: return "Persistent Memory (legacy)";
-	case E820_PMEM: return "Persistent Memory";
-	default:	return "reserved";
+	switch (entry->type) {
+	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
+	case E820_TYPE_RAM:		return "System RAM";
+	case E820_TYPE_ACPI:		return "ACPI Tables";
+	case E820_TYPE_NVS:		return "ACPI Non-volatile Storage";
+	case E820_TYPE_UNUSABLE:	return "Unusable memory";
+	case E820_TYPE_PRAM:		return "Persistent Memory (legacy)";
+	case E820_TYPE_PMEM:		return "Persistent Memory";
+	case E820_TYPE_RESERVED:	return "Reserved";
+	default:			return "Unknown E820 type";
 	}
 }
 
-static unsigned long __init e820_type_to_iomem_type(int e820_type)
+static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
 {
-	switch (e820_type) {
-	case E820_RESERVED_KERN:
-	case E820_RAM:
-		return IORESOURCE_SYSTEM_RAM;
-	case E820_ACPI:
-	case E820_NVS:
-	case E820_UNUSABLE:
-	case E820_PRAM:
-	case E820_PMEM:
-	default:
-		return IORESOURCE_MEM;
+	switch (entry->type) {
+	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
+	case E820_TYPE_RAM:		return IORESOURCE_SYSTEM_RAM;
+	case E820_TYPE_ACPI:		/* Fall-through: */
+	case E820_TYPE_NVS:		/* Fall-through: */
+	case E820_TYPE_UNUSABLE:	/* Fall-through: */
+	case E820_TYPE_PRAM:		/* Fall-through: */
+	case E820_TYPE_PMEM:		/* Fall-through: */
+	case E820_TYPE_RESERVED:	/* Fall-through: */
+	default:			return IORESOURCE_MEM;
 	}
 }
 
-static unsigned long __init e820_type_to_iores_desc(int e820_type)
+static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 {
-	switch (e820_type) {
-	case E820_ACPI:
-		return IORES_DESC_ACPI_TABLES;
-	case E820_NVS:
-		return IORES_DESC_ACPI_NV_STORAGE;
-	case E820_PMEM:
-		return IORES_DESC_PERSISTENT_MEMORY;
-	case E820_PRAM:
-		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
-	case E820_RESERVED_KERN:
-	case E820_RAM:
-	case E820_UNUSABLE:
-	default:
-		return IORES_DESC_NONE;
+	switch (entry->type) {
+	case E820_TYPE_ACPI:		return IORES_DESC_ACPI_TABLES;
+	case E820_TYPE_NVS:		return IORES_DESC_ACPI_NV_STORAGE;
+	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
+	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
+	case E820_TYPE_RAM:		/* Fall-through: */
+	case E820_TYPE_UNUSABLE:	/* Fall-through: */
+	case E820_TYPE_RESERVED:	/* Fall-through: */
+	default:			return IORES_DESC_NONE;
 	}
 }
 
-static bool __init do_mark_busy(u32 type, struct resource *res)
+static bool __init do_mark_busy(enum e820_type type, struct resource *res)
 {
 	/* this is the legacy bios/dos rom-shadow + mmio region */
 	if (res->start < (1ULL<<20))
@@ -993,61 +1007,71 @@ static bool __init do_mark_busy(u32 type, struct resource *res)
 	 * for exclusive use of a driver
 	 */
 	switch (type) {
-	case E820_RESERVED:
-	case E820_PRAM:
-	case E820_PMEM:
+	case E820_TYPE_RESERVED:
+	case E820_TYPE_PRAM:
+	case E820_TYPE_PMEM:
 		return false;
+	case E820_TYPE_RESERVED_KERN:
+	case E820_TYPE_RAM:
+	case E820_TYPE_ACPI:
+	case E820_TYPE_NVS:
+	case E820_TYPE_UNUSABLE:
 	default:
 		return true;
 	}
 }
 
 /*
- * Mark e820 reserved areas as busy for the resource manager.
+ * Mark E820 reserved areas as busy for the resource manager:
  */
+
 static struct resource __initdata *e820_res;
-void __init e820_reserve_resources(void)
+
+void __init e820__reserve_resources(void)
 {
 	int i;
 	struct resource *res;
 	u64 end;
 
-	res = alloc_bootmem(sizeof(struct resource) * e820->nr_map);
+	res = alloc_bootmem(sizeof(*res) * e820_table->nr_entries);
 	e820_res = res;
-	for (i = 0; i < e820->nr_map; i++) {
-		end = e820->map[i].addr + e820->map[i].size - 1;
+
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = e820_table->entries + i;
+
+		end = entry->addr + entry->size - 1;
 		if (end != (resource_size_t)end) {
 			res++;
 			continue;
 		}
-		res->name = e820_type_to_string(e820->map[i].type);
-		res->start = e820->map[i].addr;
-		res->end = end;
-
-		res->flags = e820_type_to_iomem_type(e820->map[i].type);
-		res->desc = e820_type_to_iores_desc(e820->map[i].type);
+		res->start = entry->addr;
+		res->end   = end;
+		res->name  = e820_type_to_string(entry);
+		res->flags = e820_type_to_iomem_type(entry);
+		res->desc  = e820_type_to_iores_desc(entry);
 
 		/*
-		 * don't register the region that could be conflicted with
-		 * pci device BAR resource and insert them later in
-		 * pcibios_resource_survey()
+		 * Don't register the region that could be conflicted with
+		 * PCI device BAR resources and insert them later in
+		 * pcibios_resource_survey():
 		 */
-		if (do_mark_busy(e820->map[i].type, res)) {
+		if (do_mark_busy(entry->type, res)) {
 			res->flags |= IORESOURCE_BUSY;
 			insert_resource(&iomem_resource, res);
 		}
 		res++;
 	}
 
-	for (i = 0; i < e820_saved->nr_map; i++) {
-		struct e820entry *entry = &e820_saved->map[i];
-		firmware_map_add_early(entry->addr,
-			entry->addr + entry->size,
-			e820_type_to_string(entry->type));
+	for (i = 0; i < e820_table_firmware->nr_entries; i++) {
+		struct e820_entry *entry = e820_table_firmware->entries + i;
+
+		firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry));
 	}
 }
 
-/* How much should we pad RAM ending depending on where it is? */
+/*
+ * How much should we pad the end of RAM, depending on where it is?
+ */
 static unsigned long __init ram_alignment(resource_size_t pos)
 {
 	unsigned long mb = pos >> 20;
@@ -1066,64 +1090,59 @@ static unsigned long __init ram_alignment(resource_size_t pos)
 
 #define MAX_RESOURCE_SIZE ((resource_size_t)-1)
 
-void __init e820_reserve_resources_late(void)
+void __init e820__reserve_resources_late(void)
 {
 	int i;
 	struct resource *res;
 
 	res = e820_res;
-	for (i = 0; i < e820->nr_map; i++) {
+	for (i = 0; i < e820_table->nr_entries; i++) {
 		if (!res->parent && res->end)
 			insert_resource_expand_to_fit(&iomem_resource, res);
 		res++;
 	}
 
 	/*
-	 * Try to bump up RAM regions to reasonable boundaries to
+	 * Try to bump up RAM regions to reasonable boundaries, to
 	 * avoid stolen RAM:
 	 */
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *entry = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 		u64 start, end;
 
-		if (entry->type != E820_RAM)
+		if (entry->type != E820_TYPE_RAM)
 			continue;
+
 		start = entry->addr + entry->size;
 		end = round_up(start, ram_alignment(start)) - 1;
 		if (end > MAX_RESOURCE_SIZE)
 			end = MAX_RESOURCE_SIZE;
 		if (start >= end)
 			continue;
-		printk(KERN_DEBUG
-		       "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n",
-		       start, end);
-		reserve_region_with_split(&iomem_resource, start, end,
-					  "RAM buffer");
+
+		printk(KERN_DEBUG "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", start, end);
+		reserve_region_with_split(&iomem_resource, start, end, "RAM buffer");
 	}
 }
 
-char *__init default_machine_specific_memory_setup(void)
+/*
+ * Pass the firmware (bootloader) E820 map to the kernel and process it:
+ */
+char *__init e820__memory_setup_default(void)
 {
 	char *who = "BIOS-e820";
-	u32 new_nr;
+
 	/*
 	 * Try to copy the BIOS-supplied E820-map.
 	 *
 	 * Otherwise fake a memory map; one section from 0k->640k,
 	 * the next section from 1mb->appropriate_mem_k
 	 */
-	new_nr = boot_params.e820_entries;
-	sanitize_e820_map(boot_params.e820_map,
-			ARRAY_SIZE(boot_params.e820_map),
-			&new_nr);
-	boot_params.e820_entries = new_nr;
-	if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
-	  < 0) {
+	if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) {
 		u64 mem_size;
 
-		/* compare results from other methods and take the greater */
-		if (boot_params.alt_mem_k
-		    < boot_params.screen_info.ext_mem_k) {
+		/* Compare results from other methods and take the one that gives more RAM: */
+		if (boot_params.alt_mem_k < boot_params.screen_info.ext_mem_k) {
 			mem_size = boot_params.screen_info.ext_mem_k;
 			who = "BIOS-88";
 		} else {
@@ -1131,84 +1150,68 @@ char *__init default_machine_specific_memory_setup(void)
 			who = "BIOS-e801";
 		}
 
-		e820->nr_map = 0;
-		e820_add_region(0, LOWMEMSIZE(), E820_RAM);
-		e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
+		e820_table->nr_entries = 0;
+		e820__range_add(0, LOWMEMSIZE(), E820_TYPE_RAM);
+		e820__range_add(HIGH_MEMORY, mem_size << 10, E820_TYPE_RAM);
 	}
 
-	/* In case someone cares... */
+	/* We just appended a lot of ranges, sanitize the table: */
+	e820__update_table(e820_table);
+
 	return who;
 }
 
-void __init setup_memory_map(void)
+/*
+ * Calls e820__memory_setup_default() in essence to pick up the firmware/bootloader
+ * E820 map - with an optional platform quirk available for virtual platforms
+ * to override this method of boot environment processing:
+ */
+void __init e820__memory_setup(void)
 {
 	char *who;
 
+	/* This is a firmware interface ABI - make sure we don't break it: */
+	BUILD_BUG_ON(sizeof(struct boot_e820_entry) != 20);
+
 	who = x86_init.resources.memory_setup();
-	memcpy(e820_saved, e820, sizeof(struct e820map));
-	printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n");
-	e820_print_map(who);
+
+	memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
+
+	pr_info("e820: BIOS-provided physical RAM map:\n");
+	e820__print_table(who);
 }
 
-void __init memblock_x86_fill(void)
+void __init e820__memblock_setup(void)
 {
 	int i;
 	u64 end;
 
 	/*
-	 * EFI may have more than 128 entries
-	 * We are safe to enable resizing, beause memblock_x86_fill()
-	 * is rather later for x86
+	 * The bootstrap memblock region count maximum is 128 entries
+	 * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries
+	 * than that - so allow memblock resizing.
+	 *
+	 * This is safe, because this call happens pretty late during x86 setup,
+	 * so we know about reserved memory regions already. (This is important
+	 * so that memblock resizing does no stomp over reserved areas.)
 	 */
 	memblock_allow_resize();
 
-	for (i = 0; i < e820->nr_map; i++) {
-		struct e820entry *ei = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		struct e820_entry *entry = &e820_table->entries[i];
 
-		end = ei->addr + ei->size;
+		end = entry->addr + entry->size;
 		if (end != (resource_size_t)end)
 			continue;
 
-		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
 			continue;
 
-		memblock_add(ei->addr, ei->size);
+		memblock_add(entry->addr, entry->size);
 	}
 
-	/* throw away partial pages */
+	/* Throw away partial pages: */
 	memblock_trim_memory(PAGE_SIZE);
 
 	memblock_dump_all();
 }
-
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
-	u64 nr_pages = 0, nr_free_pages = 0;
-	unsigned long start_pfn, end_pfn;
-	phys_addr_t start, end;
-	int i;
-	u64 u;
-
-	/*
-	 * need to find out used area below MAX_DMA_PFN
-	 * need to use memblock to get free size in [0, MAX_DMA_PFN]
-	 * at first, and assume boot_mem will not take below MAX_DMA_PFN
-	 */
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-		start_pfn = min(start_pfn, MAX_DMA_PFN);
-		end_pfn = min(end_pfn, MAX_DMA_PFN);
-		nr_pages += end_pfn - start_pfn;
-	}
-
-	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
-				NULL) {
-		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
-		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
-		if (start_pfn < end_pfn)
-			nr_free_pages += end_pfn - start_pfn;
-	}
-
-	set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6a08e25a48d8..ff7e4b3988ed 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -546,8 +546,8 @@ intel_graphics_stolen(int num, int slot, int func,
 	       &base, &end);
 
 	/* Mark this space as reserved */
-	e820_add_region(base, size, E820_RESERVED);
-	sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+	e820__range_add(base, size, E820_TYPE_RESERVED);
+	e820__update_table(e820_table);
 }
 
 static void __init intel_graphics_quirks(int num, int slot, int func)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 8a121991e5ba..0f0840304452 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -17,6 +17,7 @@
 #include <asm/intel-mid.h>
 #include <asm/pgtable.h>
 #include <linux/usb/ehci_def.h>
+#include <linux/usb/xhci-dbgp.h>
 #include <linux/efi.h>
 #include <asm/efi.h>
 #include <asm/pci_x86.h>
@@ -381,6 +382,10 @@ static int __init setup_early_printk(char *buf)
 		if (!strncmp(buf, "efi", 3))
 			early_console_register(&early_efi_console, keep);
 #endif
+#ifdef CONFIG_EARLY_PRINTK_USB_XDBC
+		if (!strncmp(buf, "xdbc", 4))
+			early_xdbc_parse_parameter(buf + 4);
+#endif
 
 		buf++;
 	}
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 04f89caef9c4..8e598a1ad986 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -50,11 +50,11 @@
 #define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
 
 /* There is address space for how many espfix pages? */
-#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+#define ESPFIX_PAGE_SPACE	(1UL << (P4D_SHIFT-PAGE_SHIFT-16))
 
 #define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
 #if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
-# error "Need more than one PGD for the ESPFIX hack"
+# error "Need more virtual address space for the ESPFIX hack"
 #endif
 
 #define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
@@ -121,11 +121,13 @@ static void init_espfix_random(void)
 
 void __init init_espfix_bsp(void)
 {
-	pgd_t *pgd_p;
+	pgd_t *pgd;
+	p4d_t *p4d;
 
 	/* Install the espfix pud into the kernel page directory */
-	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
-	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+	pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR);
+	p4d_populate(&init_mm, p4d, espfix_pud_page);
 
 	/* Randomize the locations */
 	init_espfix_random();
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8639bb2ae058..5b7153540727 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -535,7 +535,7 @@ static void run_sync(void)
 {
 	int enable_irqs = irqs_disabled();
 
-	/* We may be called with interrupts disbled (on bootup). */
+	/* We may be called with interrupts disabled (on bootup). */
 	if (enable_irqs)
 		local_irq_enable();
 	on_each_cpu(do_sync_core, NULL, 1);
@@ -983,6 +983,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
+	/*
+	 * When resuming from suspend-to-ram, this function can be indirectly
+	 * called from early CPU startup code while the CPU is in real mode,
+	 * which would fail miserably.  Make sure the stack pointer is a
+	 * virtual address.
+	 *
+	 * This check isn't as accurate as virt_addr_valid(), but it should be
+	 * good enough for this purpose, and it's fast.
+	 */
+	if (unlikely((long)__builtin_frame_address(0) >= 0))
+		return;
+
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
new file mode 100644
index 000000000000..722a145b4139
--- /dev/null
+++ b/arch/x86/kernel/ftrace_32.S
@@ -0,0 +1,244 @@
+/*
+ *  Copyright (C) 2017  Steven Rostedt, VMware Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+#include <asm/segment.h>
+#include <asm/export.h>
+#include <asm/ftrace.h>
+
+#ifdef CC_USING_FENTRY
+# define function_hook	__fentry__
+EXPORT_SYMBOL(__fentry__)
+#else
+# define function_hook	mcount
+EXPORT_SYMBOL(mcount)
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* mcount uses a frame pointer even if CONFIG_FRAME_POINTER is not set */
+#if !defined(CC_USING_FENTRY) || defined(CONFIG_FRAME_POINTER)
+# define USING_FRAME_POINTER
+#endif
+
+#ifdef USING_FRAME_POINTER
+# define MCOUNT_FRAME			1	/* using frame = true  */
+#else
+# define MCOUNT_FRAME			0	/* using frame = false */
+#endif
+
+ENTRY(function_hook)
+	ret
+END(function_hook)
+
+ENTRY(ftrace_caller)
+
+#ifdef USING_FRAME_POINTER
+# ifdef CC_USING_FENTRY
+	/*
+	 * Frame pointers are of ip followed by bp.
+	 * Since fentry is an immediate jump, we are left with
+	 * parent-ip, function-ip. We need to add a frame with
+	 * parent-ip followed by ebp.
+	 */
+	pushl	4(%esp)				/* parent ip */
+	pushl	%ebp
+	movl	%esp, %ebp
+	pushl	2*4(%esp)			/* function ip */
+# endif
+	/* For mcount, the function ip is directly above */
+	pushl	%ebp
+	movl	%esp, %ebp
+#endif
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	pushl	$0				/* Pass NULL as regs pointer */
+
+#ifdef USING_FRAME_POINTER
+	/* Load parent ebp into edx */
+	movl	4*4(%esp), %edx
+#else
+	/* There's no frame pointer, load the appropriate stack addr instead */
+	lea	4*4(%esp), %edx
+#endif
+
+	movl	(MCOUNT_FRAME+4)*4(%esp), %eax	/* load the rip */
+	/* Get the parent ip */
+	movl	4(%edx), %edx			/* edx has ebp */
+
+	movl	function_trace_op, %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+	call	ftrace_stub
+
+	addl	$4, %esp			/* skip NULL pointer */
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+#ifdef USING_FRAME_POINTER
+	popl	%ebp
+# ifdef CC_USING_FENTRY
+	addl	$4,%esp				/* skip function ip */
+	popl	%ebp				/* this is the orig bp */
+	addl	$4, %esp			/* skip parent ip */
+# endif
+#endif
+.Lftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	jmp	ftrace_stub
+#endif
+
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
+	ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+	/*
+	 * i386 does not save SS and ESP when coming from kernel.
+	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
+	 * Unfortunately, that means eflags must be at the same location
+	 * as the current return ip is. We move the return ip into the
+	 * regs->ip location, and move flags into the return ip location.
+	 */
+	pushl	$__KERNEL_CS
+	pushl	4(%esp)				/* Save the return ip */
+	pushl	$0				/* Load 0 into orig_ax */
+	pushl	%gs
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+
+	/* Get flags and place them into the return ip slot */
+	pushf
+	popl	%eax
+	movl	%eax, 8*4(%esp)
+
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+
+	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
+	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
+#ifdef CC_USING_FENTRY
+	movl	15*4(%esp), %edx		/* Load parent ip (2nd parameter) */
+#else
+	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
+#endif
+	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
+	pushl	%esp				/* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+	call	ftrace_stub
+
+	addl	$4, %esp			/* Skip pt_regs */
+
+	/* restore flags */
+	push	14*4(%esp)
+	popf
+
+	/* Move return ip back to its original location */
+	movl	12*4(%esp), %eax
+	movl	%eax, 14*4(%esp)
+
+	popl	%ebx
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	popl	%edi
+	popl	%ebp
+	popl	%eax
+	popl	%ds
+	popl	%es
+	popl	%fs
+	popl	%gs
+
+	/* use lea to not affect flags */
+	lea	3*4(%esp), %esp			/* Skip orig_ax, ip and cs */
+
+	jmp	.Lftrace_ret
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(function_hook)
+	cmpl	$__PAGE_OFFSET, %esp
+	jb	ftrace_stub			/* Paging not enabled yet? */
+
+	cmpl	$ftrace_stub, ftrace_trace_function
+	jnz	.Ltrace
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	cmpl	$ftrace_stub, ftrace_graph_return
+	jnz	ftrace_graph_caller
+
+	cmpl	$ftrace_graph_entry_stub, ftrace_graph_entry
+	jnz	ftrace_graph_caller
+#endif
+.globl ftrace_stub
+ftrace_stub:
+	ret
+
+	/* taken from glibc */
+.Ltrace:
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	0xc(%esp), %eax
+	movl	0x4(%ebp), %edx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+	call	*ftrace_trace_function
+
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	jmp	ftrace_stub
+END(function_hook)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	3*4(%esp), %eax
+	/* Even with frame pointers, fentry doesn't have one here */
+#ifdef CC_USING_FENTRY
+	lea	4*4(%esp), %edx
+	movl	$0, %ecx
+#else
+	lea	0x4(%ebp), %edx
+	movl	(%ebp), %ecx
+#endif
+	subl	$MCOUNT_INSN_SIZE, %eax
+	call	prepare_ftrace_return
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+	pushl	%eax
+	pushl	%edx
+#ifdef CC_USING_FENTRY
+	movl	$0, %eax
+#else
+	movl	%ebp, %eax
+#endif
+	call	ftrace_return_to_handler
+	movl	%eax, %ecx
+	popl	%edx
+	popl	%eax
+	jmp	*%ecx
+#endif
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/ftrace_64.S
index 7b0d3da52fb4..1dfac634bbf7 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/x86_64/mcount_64.S
- *
  *  Copyright (C) 2014  Steven Rostedt, Red Hat Inc
  */
 
@@ -13,9 +11,6 @@
 	.code64
 	.section .entry.text, "ax"
 
-
-#ifdef CONFIG_FUNCTION_TRACER
-
 #ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
 EXPORT_SYMBOL(__fentry__)
@@ -297,7 +292,6 @@ trace:
 	jmp fgraph_trace
 END(function_hook)
 #endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 ENTRY(ftrace_graph_caller)
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index e5fb436a6548..538ec012b371 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -12,7 +12,7 @@
 
 #include <asm/setup.h>
 #include <asm/sections.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/page.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 54a2372f5dbb..43b7002f44fb 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -23,7 +24,7 @@
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/kdebug.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/bios_ebda.h>
 #include <asm/bootparam_utils.h>
 #include <asm/microcode.h>
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b467b14b03eb..ac9d327d2e42 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -269,10 +269,8 @@ ENTRY(secondary_startup_64)
 	/* rsi is pointer to real mode structure with interesting info.
 	   pass it to C */
 	movq	%rsi, %rdi
-	jmp	start_cpu
-ENDPROC(secondary_startup_64)
 
-ENTRY(start_cpu)
+.Ljump_to_C_code:
 	/*
 	 * Jump to run C code and to be on a real kernel address.
 	 * Since we are running on identity-mapped space we have to jump
@@ -305,7 +303,7 @@ ENTRY(start_cpu)
 	pushq	%rax		# target address in negative space
 	lretq
 .Lafter_lret:
-ENDPROC(start_cpu)
+ENDPROC(secondary_startup_64)
 
 #include "verify_cpu.S"
 
@@ -313,11 +311,11 @@ ENDPROC(start_cpu)
 /*
  * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
  * up already except stack. We just set up stack here. Then call
- * start_secondary() via start_cpu().
+ * start_secondary() via .Ljump_to_C_code.
  */
 ENTRY(start_cpu0)
 	movq	initial_stack(%rip), %rsp
-	jmp	start_cpu
+	jmp	.Ljump_to_C_code
 ENDPROC(start_cpu0)
 #endif
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dc6ba5bda9fc..89ff7af2de50 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 
 		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_irq(hdev->irq);
+		disable_hardirq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 		enable_irq(hdev->irq);
 	}
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4d8183b5f113..f34fe7444836 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -394,6 +394,9 @@ int check_irq_vectors_for_cpu_disable(void)
 		    !cpumask_subset(&affinity_new, &online_new))
 			this_count++;
 	}
+	/* No need to check any further. */
+	if (!this_count)
+		return 0;
 
 	count = 0;
 	for_each_online_cpu(cpu) {
@@ -411,8 +414,10 @@ int check_irq_vectors_for_cpu_disable(void)
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
 			if (!test_bit(vector, used_vectors) &&
-			    IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
-			    count++;
+			    IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) {
+				if (++count == this_count)
+					return 0;
+			}
 		}
 	}
 
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 1423ab1b0312..7468c6987547 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -195,7 +195,5 @@ void __init native_init_IRQ(void)
 	if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
 		setup_irq(2, &irq2);
 
-#ifdef CONFIG_X86_32
 	irq_ctx_init(smp_processor_id());
-#endif
 }
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index bdb83e431d89..38b64587b31b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void)
 	struct dentry *dbp, *version, *data;
 	int error = -ENOMEM;
 
-	dbp = debugfs_create_dir("boot_params", NULL);
+	dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
 	if (!dbp)
 		return -ENOMEM;
 
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index d0a814a9d96a..9d7fd5e6689a 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -25,6 +25,7 @@
 #include <asm/setup.h>
 #include <asm/crash.h>
 #include <asm/efi.h>
+#include <asm/e820/api.h>
 #include <asm/kexec-bzimage64.h>
 
 #define MAX_ELFCOREHDR_STR_LEN	30	/* elfcorehdr=0x<64bit-value> */
@@ -99,15 +100,14 @@ static int setup_e820_entries(struct boot_params *params)
 {
 	unsigned int nr_e820_entries;
 
-	nr_e820_entries = e820_saved->nr_map;
+	nr_e820_entries = e820_table_firmware->nr_entries;
 
-	/* TODO: Pass entries more than E820MAX in bootparams setup data */
-	if (nr_e820_entries > E820MAX)
-		nr_e820_entries = E820MAX;
+	/* TODO: Pass entries more than E820_MAX_ENTRIES_ZEROPAGE in bootparams setup data */
+	if (nr_e820_entries > E820_MAX_ENTRIES_ZEROPAGE)
+		nr_e820_entries = E820_MAX_ENTRIES_ZEROPAGE;
 
 	params->e820_entries = nr_e820_entries;
-	memcpy(&params->e820_map, &e820_saved->map,
-	       nr_e820_entries * sizeof(struct e820entry));
+	memcpy(&params->e820_table, &e820_table_firmware->entries, nr_e820_entries*sizeof(struct e820_entry));
 
 	return 0;
 }
@@ -232,10 +232,10 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	nr_e820_entries = params->e820_entries;
 
 	for (i = 0; i < nr_e820_entries; i++) {
-		if (params->e820_map[i].type != E820_RAM)
+		if (params->e820_table[i].type != E820_TYPE_RAM)
 			continue;
-		start = params->e820_map[i].addr;
-		end = params->e820_map[i].addr + params->e820_map[i].size - 1;
+		start = params->e820_table[i].addr;
+		end = params->e820_table[i].addr + params->e820_table[i].size - 1;
 
 		if ((start <= 0x100000) && end > 0x100000) {
 			mem_k = (end >> 10) - (0x100000 >> 10);
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f927ab..db2182d63ed0 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(struct insn *insn, void *orig_addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);
@@ -75,7 +75,7 @@ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
  * Copy an instruction and adjust the displacement if the instruction
  * uses the %rip-relative addressing mode.
  */
-extern int __copy_instruction(u8 *dest, u8 *src);
+extern int __copy_instruction(u8 *dest, u8 *src, struct insn *insn);
 
 /* Generate a relative-jump/call instruction */
 extern void synthesize_reljump(void *from, void *to);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6384eb754a58..19e1f2a6d7b0 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -164,42 +164,38 @@ static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn)
 NOKPROBE_SYMBOL(skip_prefixes);
 
 /*
- * Returns non-zero if opcode is boostable.
+ * Returns non-zero if INSN is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(struct insn *insn, void *addr)
 {
 	kprobe_opcode_t opcode;
-	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
-retry:
-	if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
-		return 0;
-	opcode = *(opcodes++);
-
 	/* 2nd-byte opcode */
-	if (opcode == 0x0f) {
-		if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
-			return 0;
-		return test_bit(*opcodes,
+	if (insn->opcode.nbytes == 2)
+		return test_bit(insn->opcode.bytes[1],
 				(unsigned long *)twobyte_is_boostable);
-	}
+
+	if (insn->opcode.nbytes != 1)
+		return 0;
+
+	/* Can't boost Address-size override prefix */
+	if (unlikely(inat_is_address_size_prefix(insn->attr)))
+		return 0;
+
+	opcode = insn->opcode.bytes[0];
 
 	switch (opcode & 0xf0) {
-#ifdef CONFIG_X86_64
-	case 0x40:
-		goto retry; /* REX prefix is boostable */
-#endif
 	case 0x60:
-		if (0x63 < opcode && opcode < 0x67)
-			goto retry; /* prefixes */
-		/* can't boost Address-size override and bound */
-		return (opcode != 0x62 && opcode != 0x67);
+		/* can't boost "bound" */
+		return (opcode != 0x62);
 	case 0x70:
 		return 0; /* can't boost conditional jump */
+	case 0x90:
+		return opcode != 0x9a;	/* can't boost call far */
 	case 0xc0:
 		/* can't boost software-interruptions */
 		return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
@@ -210,14 +206,9 @@ retry:
 		/* can boost in/out and absolute jmps */
 		return ((opcode & 0x04) || opcode == 0xea);
 	case 0xf0:
-		if ((opcode & 0x0c) == 0 && opcode != 0xf1)
-			goto retry; /* lock/rep(ne) prefix */
 		/* clear and set flags are boostable */
 		return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
 	default:
-		/* segment override prefixes are boostable */
-		if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e)
-			goto retry; /* prefixes */
 		/* CS override prefix and call are not boostable */
 		return (opcode != 0x2e && opcode != 0x9a);
 	}
@@ -264,7 +255,10 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	 * Fortunately, we know that the original code is the ideal 5-byte
 	 * long NOP.
 	 */
-	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (probe_kernel_read(buf, (void *)addr,
+		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
+		return 0UL;
+
 	if (faddr)
 		memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
 	else
@@ -276,7 +270,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
  * Recover the probed instruction at addr for further analysis.
  * Caller must lock kprobes by kprobe_mutex, or disable preemption
  * for preventing to release referencing kprobes.
- * Returns zero if the instruction can not get recovered.
+ * Returns zero if the instruction can not get recovered (or access failed).
  */
 unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 {
@@ -348,37 +342,36 @@ static int is_IF_modifier(kprobe_opcode_t *insn)
 }
 
 /*
- * Copy an instruction and adjust the displacement if the instruction
- * uses the %rip-relative addressing mode.
- * If it does, Return the address of the 32-bit displacement word.
- * If not, return null.
- * Only applicable to 64-bit x86.
+ * Copy an instruction with recovering modified instruction by kprobes
+ * and adjust the displacement if the instruction uses the %rip-relative
+ * addressing mode.
+ * This returns the length of copied instruction, or 0 if it has an error.
  */
-int __copy_instruction(u8 *dest, u8 *src)
+int __copy_instruction(u8 *dest, u8 *src, struct insn *insn)
 {
-	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
-	int length;
 	unsigned long recovered_insn =
 		recover_probed_instruction(buf, (unsigned long)src);
 
-	if (!recovered_insn)
+	if (!recovered_insn || !insn)
+		return 0;
+
+	/* This can access kernel text if given address is not recovered */
+	if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE))
 		return 0;
-	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
-	insn_get_length(&insn);
-	length = insn.length;
+
+	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
+	insn_get_length(insn);
 
 	/* Another subsystem puts a breakpoint, failed to recover */
-	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+	if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
-	memcpy(dest, insn.kaddr, length);
 
 #ifdef CONFIG_X86_64
-	if (insn_rip_relative(&insn)) {
+	/* Only x86_64 has RIP relative instructions */
+	if (insn_rip_relative(insn)) {
 		s64 newdisp;
 		u8 *disp;
-		kernel_insn_init(&insn, dest, length);
-		insn_get_displacement(&insn);
 		/*
 		 * The copied instruction uses the %rip-relative addressing
 		 * mode.  Adjust the displacement for the difference between
@@ -391,36 +384,57 @@ int __copy_instruction(u8 *dest, u8 *src)
 		 * extension of the original signed 32-bit displacement would
 		 * have given.
 		 */
-		newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
+		newdisp = (u8 *) src + (s64) insn->displacement.value
+			  - (u8 *) dest;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
-			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value);
+			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
+				src, dest, insn->displacement.value);
 			return 0;
 		}
-		disp = (u8 *) dest + insn_offset_displacement(&insn);
+		disp = (u8 *) dest + insn_offset_displacement(insn);
 		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
-	return length;
+	return insn->length;
+}
+
+/* Prepare reljump right after instruction to boost */
+static void prepare_boost(struct kprobe *p, struct insn *insn)
+{
+	if (can_boost(insn, p->addr) &&
+	    MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) {
+		/*
+		 * These instructions can be executed directly if it
+		 * jumps back to correct address.
+		 */
+		synthesize_reljump(p->ainsn.insn + insn->length,
+				   p->addr + insn->length);
+		p->ainsn.boostable = true;
+	} else {
+		p->ainsn.boostable = false;
+	}
 }
 
 static int arch_copy_kprobe(struct kprobe *p)
 {
-	int ret;
+	struct insn insn;
+	int len;
+
+	set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
 
 	/* Copy an instruction with recovering if other optprobe modifies it.*/
-	ret = __copy_instruction(p->ainsn.insn, p->addr);
-	if (!ret)
+	len = __copy_instruction(p->ainsn.insn, p->addr, &insn);
+	if (!len)
 		return -EINVAL;
 
 	/*
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
-		p->ainsn.boostable = 0;
-	else
-		p->ainsn.boostable = -1;
+	prepare_boost(p, &insn);
+
+	set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
 
 	/* Check whether the instruction modifies Interrupt Flag or not */
 	p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
@@ -459,7 +473,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
-		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
+		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
 		p->ainsn.insn = NULL;
 	}
 }
@@ -531,7 +545,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 		return;
 
 #if !defined(CONFIG_PREEMPT)
-	if (p->ainsn.boostable == 1 && !p->post_handler) {
+	if (p->ainsn.boostable && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		if (!reenter)
 			reset_current_kprobe();
@@ -851,7 +865,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs,
 	case 0xcf:
 	case 0xea:	/* jmp absolute -- ip is correct */
 		/* ip is already adjusted, no more changes required */
-		p->ainsn.boostable = 1;
+		p->ainsn.boostable = true;
 		goto no_change;
 	case 0xe8:	/* call relative - Fix return addr */
 		*tos = orig_ip + (*tos - copy_ip);
@@ -876,28 +890,13 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs,
 			 * jmp near and far, absolute indirect
 			 * ip is correct. And this is boostable
 			 */
-			p->ainsn.boostable = 1;
+			p->ainsn.boostable = true;
 			goto no_change;
 		}
 	default:
 		break;
 	}
 
-	if (p->ainsn.boostable == 0) {
-		if ((regs->ip > copy_ip) &&
-		    (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) {
-			/*
-			 * These instructions can be executed directly if it
-			 * jumps back to correct address.
-			 */
-			synthesize_reljump((void *)regs->ip,
-				(void *)orig_ip + (regs->ip - copy_ip));
-			p->ainsn.boostable = 1;
-		} else {
-			p->ainsn.boostable = -1;
-		}
-	}
-
 	regs->ip += orig_ip - copy_ip;
 
 no_change:
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 5f8f0b3cc674..041f7b6dfa0f 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -94,6 +94,6 @@ NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 int arch_prepare_kprobe_ftrace(struct kprobe *p)
 {
 	p->ainsn.insn = NULL;
-	p->ainsn.boostable = -1;
+	p->ainsn.boostable = false;
 	return 0;
 }
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3d1bee9d6a72..9aadff3d0902 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -65,7 +65,10 @@ found:
 	 * overwritten by jump destination address. In this case, original
 	 * bytes must be recovered from op->optinsn.copied_insn buffer.
 	 */
-	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (probe_kernel_read(buf, (void *)addr,
+		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
+		return 0UL;
+
 	if (addr == (unsigned long)kp->addr) {
 		buf[0] = kp->opcode;
 		memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
@@ -174,11 +177,12 @@ NOKPROBE_SYMBOL(optimized_callback);
 
 static int copy_optimized_instructions(u8 *dest, u8 *src)
 {
+	struct insn insn;
 	int len = 0, ret;
 
 	while (len < RELATIVEJUMP_SIZE) {
-		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		ret = __copy_instruction(dest + len, src + len, &insn);
+		if (!ret || !can_boost(&insn, src + len))
 			return -EINVAL;
 		len += ret;
 	}
@@ -350,6 +354,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 	}
 
 	buf = (u8 *)op->optinsn.insn;
+	set_memory_rw((unsigned long)buf & PAGE_MASK, 1);
 
 	/* Copy instructions into the out-of-line buffer */
 	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
@@ -372,6 +377,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 
+	set_memory_ro((unsigned long)buf & PAGE_MASK, 1);
+
 	flush_icache_range((unsigned long) buf,
 			   (unsigned long) buf + TMPL_END_IDX +
 			   op->optinsn.size + RELATIVEJUMP_SIZE);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 469b23d6acc2..5f43cec296c5 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -103,6 +103,7 @@ static void machine_kexec_page_table_set_one(
 	pgd_t *pgd, pmd_t *pmd, pte_t *pte,
 	unsigned long vaddr, unsigned long paddr)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 
 	pgd += pgd_index(vaddr);
@@ -110,7 +111,8 @@ static void machine_kexec_page_table_set_one(
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT))
 		set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT));
 #endif
-	pud = pud_offset(pgd, vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	pmd = pmd_offset(pud, vaddr);
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT))
 		set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 307b1f4543de..085c3b300d32 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -36,6 +36,7 @@ static struct kexec_file_ops *kexec_file_loaders[] = {
 
 static void free_transition_pgtable(struct kimage *image)
 {
+	free_page((unsigned long)image->arch.p4d);
 	free_page((unsigned long)image->arch.pud);
 	free_page((unsigned long)image->arch.pmd);
 	free_page((unsigned long)image->arch.pte);
@@ -43,6 +44,7 @@ static void free_transition_pgtable(struct kimage *image)
 
 static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -53,13 +55,21 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
 	pgd += pgd_index(vaddr);
 	if (!pgd_present(*pgd)) {
+		p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL);
+		if (!p4d)
+			goto err;
+		image->arch.p4d = p4d;
+		set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+	}
+	p4d = p4d_offset(pgd, vaddr);
+	if (!p4d_present(*p4d)) {
 		pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
 		if (!pud)
 			goto err;
 		image->arch.pud = pud;
-		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
 	}
-	pud = pud_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	if (!pud_present(*pud)) {
 		pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 		if (!pmd)
@@ -194,19 +204,22 @@ static int arch_update_purgatory(struct kimage *image)
 
 	/* Setup copying of backup region */
 	if (image->type == KEXEC_TYPE_CRASH) {
-		ret = kexec_purgatory_get_set_symbol(image, "backup_dest",
+		ret = kexec_purgatory_get_set_symbol(image,
+				"purgatory_backup_dest",
 				&image->arch.backup_load_addr,
 				sizeof(image->arch.backup_load_addr), 0);
 		if (ret)
 			return ret;
 
-		ret = kexec_purgatory_get_set_symbol(image, "backup_src",
+		ret = kexec_purgatory_get_set_symbol(image,
+				"purgatory_backup_src",
 				&image->arch.backup_src_start,
 				sizeof(image->arch.backup_src_start), 0);
 		if (ret)
 			return ret;
 
-		ret = kexec_purgatory_get_set_symbol(image, "backup_sz",
+		ret = kexec_purgatory_get_set_symbol(image,
+				"purgatory_backup_sz",
 				&image->arch.backup_src_sz,
 				sizeof(image->arch.backup_src_sz), 0);
 		if (ret)
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 0f8d20497383..0d904d759ff1 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -26,7 +26,7 @@
 #include <asm/io_apic.h>
 #include <asm/proto.h>
 #include <asm/bios_ebda.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/setup.h>
 #include <asm/smp.h>
 
@@ -826,10 +826,10 @@ static int __init parse_alloc_mptable_opt(char *p)
 }
 early_param("alloc_mptable", parse_alloc_mptable_opt);
 
-void __init early_reserve_e820_mpc_new(void)
+void __init e820__memblock_alloc_reserved_mpc_new(void)
 {
 	if (enable_update_mptable && alloc_mptable)
-		mpc_new_phys = early_reserve_e820(mpc_new_length, 4);
+		mpc_new_phys = e820__memblock_alloc_reserved(mpc_new_length, 4);
 }
 
 static int __init update_mp_table(void)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f088ea4c66e7..446c8aa09b9b 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/*
-	 * most handlers of type NMI_UNKNOWN never return because
-	 * they just assume the NMI is theirs.  Just a sanity check
-	 * to manage expectations
+	 * Indicate if there are multiple registrations on the
+	 * internal NMI handler call chains (SERR and IO_CHECK).
 	 */
-	WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
 
@@ -224,17 +222,6 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
 	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
 		 reason, smp_processor_id());
 
-	/*
-	 * On some machines, PCI SERR line is used to report memory
-	 * errors. EDAC makes use of it.
-	 */
-#if defined(CONFIG_EDAC)
-	if (edac_handler_set()) {
-		edac_atomic_assert_error();
-		return;
-	}
-#endif
-
 	if (panic_on_unrecovered_nmi)
 		nmi_panic(regs, "NMI: Not continuing");
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 4797e87b0fb6..3586996fc50d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -405,9 +405,11 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 	.alloc_pte = paravirt_nop,
 	.alloc_pmd = paravirt_nop,
 	.alloc_pud = paravirt_nop,
+	.alloc_p4d = paravirt_nop,
 	.release_pte = paravirt_nop,
 	.release_pmd = paravirt_nop,
 	.release_pud = paravirt_nop,
+	.release_p4d = paravirt_nop,
 
 	.set_pte = native_set_pte,
 	.set_pte_at = native_set_pte_at,
@@ -430,12 +432,19 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 	.pmd_val = PTE_IDENT,
 	.make_pmd = PTE_IDENT,
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	.pud_val = PTE_IDENT,
 	.make_pud = PTE_IDENT,
 
+	.set_p4d = native_set_p4d,
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+	.p4d_val = PTE_IDENT,
+	.make_p4d = PTE_IDENT,
+
 	.set_pgd = native_set_pgd,
-#endif
+#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
+#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
 #endif /* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	.pte_val = PTE_IDENT,
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 0c150c06fa5a..fda7867046d0 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1007,9 +1007,8 @@ static void __init calgary_enable_translation(struct pci_dev *dev)
 	writel(cpu_to_be32(val32), target);
 	readl(target); /* flush */
 
-	init_timer(&tbl->watchdog_timer);
-	tbl->watchdog_timer.function = &calgary_watchdog;
-	tbl->watchdog_timer.data = (unsigned long)dev;
+	setup_timer(&tbl->watchdog_timer, &calgary_watchdog,
+		    (unsigned long)dev);
 	mod_timer(&tbl->watchdog_timer, jiffies);
 }
 
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index d5f15c3f7b25..963e3fb56437 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -14,7 +14,7 @@
 
 #include <asm/probe_roms.h>
 #include <asm/pci-direct.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mmzone.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f67591561711..0bb88428cbf2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -37,6 +37,7 @@
 #include <asm/vm86.h>
 #include <asm/switch_to.h>
 #include <asm/desc.h>
+#include <asm/prctl.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -124,11 +125,6 @@ void flush_thread(void)
 	fpu__clear(&tsk->thread.fpu);
 }
 
-static void hard_disable_TSC(void)
-{
-	cr4_set_bits(X86_CR4_TSD);
-}
-
 void disable_TSC(void)
 {
 	preempt_disable();
@@ -137,15 +133,10 @@ void disable_TSC(void)
 		 * Must flip the CPU state synchronously with
 		 * TIF_NOTSC in the current running context.
 		 */
-		hard_disable_TSC();
+		cr4_set_bits(X86_CR4_TSD);
 	preempt_enable();
 }
 
-static void hard_enable_TSC(void)
-{
-	cr4_clear_bits(X86_CR4_TSD);
-}
-
 static void enable_TSC(void)
 {
 	preempt_disable();
@@ -154,7 +145,7 @@ static void enable_TSC(void)
 		 * Must flip the CPU state synchronously with
 		 * TIF_NOTSC in the current running context.
 		 */
-		hard_enable_TSC();
+		cr4_clear_bits(X86_CR4_TSD);
 	preempt_enable();
 }
 
@@ -182,54 +173,129 @@ int set_tsc_mode(unsigned int val)
 	return 0;
 }
 
-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
-		      struct tss_struct *tss)
-{
-	struct thread_struct *prev, *next;
-
-	prev = &prev_p->thread;
-	next = &next_p->thread;
+DEFINE_PER_CPU(u64, msr_misc_features_shadow);
 
-	if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
-	    test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
-		unsigned long debugctl = get_debugctlmsr();
+static void set_cpuid_faulting(bool on)
+{
+	u64 msrval;
 
-		debugctl &= ~DEBUGCTLMSR_BTF;
-		if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
-			debugctl |= DEBUGCTLMSR_BTF;
+	msrval = this_cpu_read(msr_misc_features_shadow);
+	msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT;
+	msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT);
+	this_cpu_write(msr_misc_features_shadow, msrval);
+	wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval);
+}
 
-		update_debugctlmsr(debugctl);
+static void disable_cpuid(void)
+{
+	preempt_disable();
+	if (!test_and_set_thread_flag(TIF_NOCPUID)) {
+		/*
+		 * Must flip the CPU state synchronously with
+		 * TIF_NOCPUID in the current running context.
+		 */
+		set_cpuid_faulting(true);
 	}
+	preempt_enable();
+}
 
-	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
-	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
-		/* prev and next are different */
-		if (test_tsk_thread_flag(next_p, TIF_NOTSC))
-			hard_disable_TSC();
-		else
-			hard_enable_TSC();
+static void enable_cpuid(void)
+{
+	preempt_disable();
+	if (test_and_clear_thread_flag(TIF_NOCPUID)) {
+		/*
+		 * Must flip the CPU state synchronously with
+		 * TIF_NOCPUID in the current running context.
+		 */
+		set_cpuid_faulting(false);
 	}
+	preempt_enable();
+}
+
+static int get_cpuid_mode(void)
+{
+	return !test_thread_flag(TIF_NOCPUID);
+}
+
+static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
+{
+	if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+		return -ENODEV;
+
+	if (cpuid_enabled)
+		enable_cpuid();
+	else
+		disable_cpuid();
+
+	return 0;
+}
+
+/*
+ * Called immediately after a successful exec.
+ */
+void arch_setup_new_exec(void)
+{
+	/* If cpuid was previously disabled for this task, re-enable it. */
+	if (test_thread_flag(TIF_NOCPUID))
+		enable_cpuid();
+}
 
-	if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
+static inline void switch_to_bitmap(struct tss_struct *tss,
+				    struct thread_struct *prev,
+				    struct thread_struct *next,
+				    unsigned long tifp, unsigned long tifn)
+{
+	if (tifn & _TIF_IO_BITMAP) {
 		/*
 		 * Copy the relevant range of the IO bitmap.
 		 * Normally this is 128 bytes or less:
 		 */
 		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
 		       max(prev->io_bitmap_max, next->io_bitmap_max));
-
 		/*
 		 * Make sure that the TSS limit is correct for the CPU
 		 * to notice the IO bitmap.
 		 */
 		refresh_tss_limit();
-	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
+	} else if (tifp & _TIF_IO_BITMAP) {
 		/*
 		 * Clear any possible leftover bits:
 		 */
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
+}
+
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+		      struct tss_struct *tss)
+{
+	struct thread_struct *prev, *next;
+	unsigned long tifp, tifn;
+
+	prev = &prev_p->thread;
+	next = &next_p->thread;
+
+	tifn = READ_ONCE(task_thread_info(next_p)->flags);
+	tifp = READ_ONCE(task_thread_info(prev_p)->flags);
+	switch_to_bitmap(tss, prev, next, tifp, tifn);
+
 	propagate_user_return_notify(prev_p, next_p);
+
+	if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) &&
+	    arch_has_block_step()) {
+		unsigned long debugctl, msk;
+
+		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		msk = tifn & _TIF_BLOCKSTEP;
+		debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT;
+		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	}
+
+	if ((tifp ^ tifn) & _TIF_NOTSC)
+		cr4_toggle_bits(X86_CR4_TSD);
+
+	if ((tifp ^ tifn) & _TIF_NOCPUID)
+		set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
 }
 
 /*
@@ -550,3 +616,16 @@ out:
 	put_task_stack(p);
 	return ret;
 }
+
+long do_arch_prctl_common(struct task_struct *task, int option,
+			  unsigned long cpuid_enabled)
+{
+	switch (option) {
+	case ARCH_GET_CPUID:
+		return get_cpuid_mode();
+	case ARCH_SET_CPUID:
+		return set_cpuid_mode(task, cpuid_enabled);
+	}
+
+	return -EINVAL;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4c818f8bc135..ff40e74c9181 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/kdebug.h>
+#include <linux/syscalls.h>
 
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
@@ -56,6 +57,7 @@
 #include <asm/switch_to.h>
 #include <asm/vm86.h>
 #include <asm/intel_rdt.h>
+#include <asm/proto.h>
 
 void __show_regs(struct pt_regs *regs, int all)
 {
@@ -304,3 +306,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	return prev_p;
 }
+
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
+{
+	return do_arch_prctl_common(current, option, arg2);
+}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index d6b784a5520d..825a1e47cf3e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/ftrace.h>
+#include <linux/syscalls.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -52,6 +53,11 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/vdso.h>
 #include <asm/intel_rdt.h>
+#include <asm/unistd.h>
+#ifdef CONFIG_IA32_EMULATION
+/* Not included via unistd.h */
+#include <asm/unistd_32_ia32.h>
+#endif
 
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
@@ -204,7 +210,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 				(struct user_desc __user *)tls, 0);
 		else
 #endif
-			err = do_arch_prctl(p, ARCH_SET_FS, tls);
+			err = do_arch_prctl_64(p, ARCH_SET_FS, tls);
 		if (err)
 			goto out;
 	}
@@ -493,6 +499,8 @@ void set_personality_64bit(void)
 	clear_thread_flag(TIF_IA32);
 	clear_thread_flag(TIF_ADDR32);
 	clear_thread_flag(TIF_X32);
+	/* Pretend that this comes from a 64bit execve */
+	task_pt_regs(current)->orig_ax = __NR_execve;
 
 	/* Ensure the corresponding mm is not marked. */
 	if (current->mm)
@@ -505,32 +513,50 @@ void set_personality_64bit(void)
 	current->personality &= ~READ_IMPLIES_EXEC;
 }
 
-void set_personality_ia32(bool x32)
+static void __set_personality_x32(void)
 {
-	/* inherit personality from parent */
+#ifdef CONFIG_X86_X32
+	clear_thread_flag(TIF_IA32);
+	set_thread_flag(TIF_X32);
+	if (current->mm)
+		current->mm->context.ia32_compat = TIF_X32;
+	current->personality &= ~READ_IMPLIES_EXEC;
+	/*
+	 * in_compat_syscall() uses the presence of the x32 syscall bit
+	 * flag to determine compat status.  The x86 mmap() code relies on
+	 * the syscall bitness so set x32 syscall bit right here to make
+	 * in_compat_syscall() work during exec().
+	 *
+	 * Pretend to come from a x32 execve.
+	 */
+	task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT;
+	current->thread.status &= ~TS_COMPAT;
+#endif
+}
+
+static void __set_personality_ia32(void)
+{
+#ifdef CONFIG_IA32_EMULATION
+	set_thread_flag(TIF_IA32);
+	clear_thread_flag(TIF_X32);
+	if (current->mm)
+		current->mm->context.ia32_compat = TIF_IA32;
+	current->personality |= force_personality32;
+	/* Prepare the first "return" to user space */
+	task_pt_regs(current)->orig_ax = __NR_ia32_execve;
+	current->thread.status |= TS_COMPAT;
+#endif
+}
 
+void set_personality_ia32(bool x32)
+{
 	/* Make sure to be in 32bit mode */
 	set_thread_flag(TIF_ADDR32);
 
-	/* Mark the associated mm as containing 32-bit tasks. */
-	if (x32) {
-		clear_thread_flag(TIF_IA32);
-		set_thread_flag(TIF_X32);
-		if (current->mm)
-			current->mm->context.ia32_compat = TIF_X32;
-		current->personality &= ~READ_IMPLIES_EXEC;
-		/* in_compat_syscall() uses the presence of the x32
-		   syscall bit flag to determine compat status */
-		current->thread.status &= ~TS_COMPAT;
-	} else {
-		set_thread_flag(TIF_IA32);
-		clear_thread_flag(TIF_X32);
-		if (current->mm)
-			current->mm->context.ia32_compat = TIF_IA32;
-		current->personality |= force_personality32;
-		/* Prepare the first "return" to user space */
-		current->thread.status |= TS_COMPAT;
-	}
+	if (x32)
+		__set_personality_x32();
+	else
+		__set_personality_ia32();
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
 
@@ -547,70 +573,72 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 }
 #endif
 
-long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 {
 	int ret = 0;
 	int doit = task == current;
 	int cpu;
 
-	switch (code) {
+	switch (option) {
 	case ARCH_SET_GS:
-		if (addr >= TASK_SIZE_MAX)
+		if (arg2 >= TASK_SIZE_MAX)
 			return -EPERM;
 		cpu = get_cpu();
 		task->thread.gsindex = 0;
-		task->thread.gsbase = addr;
+		task->thread.gsbase = arg2;
 		if (doit) {
 			load_gs_index(0);
-			ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
+			ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2);
 		}
 		put_cpu();
 		break;
 	case ARCH_SET_FS:
 		/* Not strictly needed for fs, but do it for symmetry
 		   with gs */
-		if (addr >= TASK_SIZE_MAX)
+		if (arg2 >= TASK_SIZE_MAX)
 			return -EPERM;
 		cpu = get_cpu();
 		task->thread.fsindex = 0;
-		task->thread.fsbase = addr;
+		task->thread.fsbase = arg2;
 		if (doit) {
 			/* set the selector to 0 to not confuse __switch_to */
 			loadsegment(fs, 0);
-			ret = wrmsrl_safe(MSR_FS_BASE, addr);
+			ret = wrmsrl_safe(MSR_FS_BASE, arg2);
 		}
 		put_cpu();
 		break;
 	case ARCH_GET_FS: {
 		unsigned long base;
+
 		if (doit)
 			rdmsrl(MSR_FS_BASE, base);
 		else
 			base = task->thread.fsbase;
-		ret = put_user(base, (unsigned long __user *)addr);
+		ret = put_user(base, (unsigned long __user *)arg2);
 		break;
 	}
 	case ARCH_GET_GS: {
 		unsigned long base;
+
 		if (doit)
 			rdmsrl(MSR_KERNEL_GS_BASE, base);
 		else
 			base = task->thread.gsbase;
-		ret = put_user(base, (unsigned long __user *)addr);
+		ret = put_user(base, (unsigned long __user *)arg2);
 		break;
 	}
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
 # ifdef CONFIG_X86_X32_ABI
 	case ARCH_MAP_VDSO_X32:
-		return prctl_map_vdso(&vdso_image_x32, addr);
+		return prctl_map_vdso(&vdso_image_x32, arg2);
 # endif
 # if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 	case ARCH_MAP_VDSO_32:
-		return prctl_map_vdso(&vdso_image_32, addr);
+		return prctl_map_vdso(&vdso_image_32, arg2);
 # endif
 	case ARCH_MAP_VDSO_64:
-		return prctl_map_vdso(&vdso_image_64, addr);
+		return prctl_map_vdso(&vdso_image_64, arg2);
 #endif
 
 	default:
@@ -621,10 +649,23 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 	return ret;
 }
 
-long sys_arch_prctl(int code, unsigned long addr)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
-	return do_arch_prctl(current, code, addr);
+	long ret;
+
+	ret = do_arch_prctl_64(current, option, arg2);
+	if (ret == -EINVAL)
+		ret = do_arch_prctl_common(current, option, arg2);
+
+	return ret;
+}
+
+#ifdef CONFIG_IA32_EMULATION
+COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
+{
+	return do_arch_prctl_common(current, option, arg2);
 }
+#endif
 
 unsigned long KSTK_ESP(struct task_struct *task)
 {
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 2364b23ea3e5..f37d18124648 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -396,12 +396,12 @@ static int putreg(struct task_struct *child,
 		if (value >= TASK_SIZE_MAX)
 			return -EIO;
 		/*
-		 * When changing the segment base, use do_arch_prctl
+		 * When changing the segment base, use do_arch_prctl_64
 		 * to set either thread.fs or thread.fsindex and the
 		 * corresponding GDT slot.
 		 */
 		if (child->thread.fsbase != value)
-			return do_arch_prctl(child, ARCH_SET_FS, value);
+			return do_arch_prctl_64(child, ARCH_SET_FS, value);
 		return 0;
 	case offsetof(struct user_regs_struct,gs_base):
 		/*
@@ -410,7 +410,7 @@ static int putreg(struct task_struct *child,
 		if (value >= TASK_SIZE_MAX)
 			return -EIO;
 		if (child->thread.gsbase != value)
-			return do_arch_prctl(child, ARCH_SET_GS, value);
+			return do_arch_prctl_64(child, ARCH_SET_GS, value);
 		return 0;
 #endif
 	}
@@ -869,7 +869,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		   Works just like arch_prctl, except that the arguments
 		   are reversed. */
 	case PTRACE_ARCH_PRCTL:
-		ret = do_arch_prctl(child, data, addr);
+		ret = do_arch_prctl_64(child, data, addr);
 		break;
 #endif
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e244c19a2451..2544700a2a87 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
 		},
 	},
+	{	/* Handle problems with rebooting on ASUS EeeBook X205TA */
+		.callback = set_acpi_reboot,
+		.ident = "ASUS EeeBook X205TA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"),
+		},
+	},
+	{	/* Handle problems with rebooting on ASUS EeeBook X205TAW */
+		.callback = set_acpi_reboot,
+		.ident = "ASUS EeeBook X205TAW",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+		},
+	},
 
 	/* Certec */
 	{       /* Handle problems with rebooting on Certec BPC600 */
@@ -749,10 +765,11 @@ void machine_crash_shutdown(struct pt_regs *regs)
 #endif
 
 
+/* This is the CPU performing the emergency shutdown work. */
+int crashing_cpu = -1;
+
 #if defined(CONFIG_SMP)
 
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
 static nmi_shootdown_cb shootdown_callback;
 
 static atomic_t waiting_for_crash_ipi;
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2408c1603438..5ab3895516ac 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -1,5 +1,5 @@
 #include <linux/ioport.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 
 static void resource_clip(struct resource *res, resource_size_t start,
 			  resource_size_t end)
@@ -25,10 +25,10 @@ static void resource_clip(struct resource *res, resource_size_t start,
 static void remove_e820_regions(struct resource *avail)
 {
 	int i;
-	struct e820entry *entry;
+	struct e820_entry *entry;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		entry = &e820->map[i];
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		entry = &e820_table->entries[i];
 
 		resource_clip(avail, entry->addr,
 			      entry->addr + entry->size - 1);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4bf0c8926a1c..603a1669a2ec 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -70,12 +70,13 @@
 #include <linux/tboot.h>
 #include <linux/jiffies.h>
 
+#include <linux/usb/xhci-dbgp.h>
 #include <video/edid.h>
 
 #include <asm/mtrr.h>
 #include <asm/apic.h>
 #include <asm/realmode.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/efi.h>
@@ -119,7 +120,7 @@
  * max_low_pfn_mapped: highest direct mapped pfn under 4GB
  * max_pfn_mapped:     highest direct mapped pfn over 4GB
  *
- * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are
  * represented by pfn_mapped
  */
 unsigned long max_low_pfn_mapped;
@@ -173,14 +174,11 @@ static struct resource bss_resource = {
 
 
 #ifdef CONFIG_X86_32
-/* cpu data as detected by the assembly code in head.S */
-struct cpuinfo_x86 new_cpu_data = {
-	.wp_works_ok = -1,
-};
+/* cpu data as detected by the assembly code in head_32.S */
+struct cpuinfo_x86 new_cpu_data;
+
 /* common cpu data for all cpus */
-struct cpuinfo_x86 boot_cpu_data __read_mostly = {
-	.wp_works_ok = -1,
-};
+struct cpuinfo_x86 boot_cpu_data __read_mostly;
 EXPORT_SYMBOL(boot_cpu_data);
 
 unsigned int def_to_bigsmp;
@@ -426,7 +424,7 @@ static void __init parse_setup_data(void)
 
 		switch (data_type) {
 		case SETUP_E820_EXT:
-			parse_e820_ext(pa_data, data_len);
+			e820__memory_setup_extended(pa_data, data_len);
 			break;
 		case SETUP_DTB:
 			add_dtb(pa_data);
@@ -441,29 +439,6 @@ static void __init parse_setup_data(void)
 	}
 }
 
-static void __init e820_reserve_setup_data(void)
-{
-	struct setup_data *data;
-	u64 pa_data;
-
-	pa_data = boot_params.hdr.setup_data;
-	if (!pa_data)
-		return;
-
-	while (pa_data) {
-		data = early_memremap(pa_data, sizeof(*data));
-		e820_update_range(pa_data, sizeof(*data)+data->len,
-			 E820_RAM, E820_RESERVED_KERN);
-		pa_data = data->next;
-		early_memunmap(data, sizeof(*data));
-	}
-
-	sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
-	memcpy(e820_saved, e820, sizeof(struct e820map));
-	printk(KERN_INFO "extended physical RAM map:\n");
-	e820_print_map("reserve setup_data");
-}
-
 static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_data *data;
@@ -756,16 +731,16 @@ static void __init trim_bios_range(void)
 	 * since some BIOSes are known to corrupt low memory.  See the
 	 * Kconfig help text for X86_RESERVE_LOW.
 	 */
-	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+	e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 
 	/*
 	 * special case: Some BIOSen report the PC BIOS
 	 * area (640->1Mb) as ram even though it is not.
 	 * take them out.
 	 */
-	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+	e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1);
 
-	sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+	e820__update_table(e820_table);
 }
 
 /* called before trim_bios_range() to spare extra sanitize */
@@ -775,18 +750,18 @@ static void __init e820_add_kernel_range(void)
 	u64 size = __pa_symbol(_end) - start;
 
 	/*
-	 * Complain if .text .data and .bss are not marked as E820_RAM and
+	 * Complain if .text .data and .bss are not marked as E820_TYPE_RAM and
 	 * attempt to fix it by adding the range. We may have a confused BIOS,
 	 * or the user may have used memmap=exactmap or memmap=xxM$yyM to
 	 * exclude kernel range. If we really are running on top non-RAM,
 	 * we will crash later anyways.
 	 */
-	if (e820_all_mapped(start, start + size, E820_RAM))
+	if (e820__mapped_all(start, start + size, E820_TYPE_RAM))
 		return;
 
-	pr_warn(".text .data .bss are not marked as E820_RAM!\n");
-	e820_remove_range(start, size, E820_RAM, 0);
-	e820_add_region(start, size, E820_RAM);
+	pr_warn(".text .data .bss are not marked as E820_TYPE_RAM!\n");
+	e820__range_remove(start, size, E820_TYPE_RAM, 0);
+	e820__range_add(start, size, E820_TYPE_RAM);
 }
 
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
@@ -837,6 +812,26 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 	return 0;
 }
 
+static void __init simple_udelay_calibration(void)
+{
+	unsigned int tsc_khz, cpu_khz;
+	unsigned long lpj;
+
+	if (!boot_cpu_has(X86_FEATURE_TSC))
+		return;
+
+	cpu_khz = x86_platform.calibrate_cpu();
+	tsc_khz = x86_platform.calibrate_tsc();
+
+	tsc_khz = tsc_khz ? : cpu_khz;
+	if (!tsc_khz)
+		return;
+
+	lpj = tsc_khz * 1000;
+	do_div(lpj, HZ);
+	loops_per_jiffy = lpj;
+}
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -939,7 +934,7 @@ void __init setup_arch(char **cmdline_p)
 	x86_init.oem.arch_setup();
 
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
-	setup_memory_map();
+	e820__memory_setup();
 	parse_setup_data();
 
 	copy_edd();
@@ -985,6 +980,8 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	x86_configure_nx();
 
+	simple_udelay_calibration();
+
 	parse_early_param();
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -1028,9 +1025,8 @@ void __init setup_arch(char **cmdline_p)
 		early_dump_pci_devices();
 #endif
 
-	/* update the e820_saved too */
-	e820_reserve_setup_data();
-	finish_e820_parsing();
+	e820__reserve_setup_data();
+	e820__finish_early_params();
 
 	if (efi_enabled(EFI_BOOT))
 		efi_init();
@@ -1056,11 +1052,11 @@ void __init setup_arch(char **cmdline_p)
 	trim_bios_range();
 #ifdef CONFIG_X86_32
 	if (ppro_with_ram_bug()) {
-		e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
-				  E820_RESERVED);
-		sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+		e820__range_update(0x70000000ULL, 0x40000ULL, E820_TYPE_RAM,
+				  E820_TYPE_RESERVED);
+		e820__update_table(e820_table);
 		printk(KERN_INFO "fixed physical RAM map:\n");
-		e820_print_map("bad_ppro");
+		e820__print_table("bad_ppro");
 	}
 #else
 	early_gart_iommu_check();
@@ -1070,12 +1066,12 @@ void __init setup_arch(char **cmdline_p)
 	 * partially used pages are not usable - thus
 	 * we are rounding upwards:
 	 */
-	max_pfn = e820_end_of_ram_pfn();
+	max_pfn = e820__end_of_ram_pfn();
 
 	/* update e820 for memory not covered by WB MTRRs */
 	mtrr_bp_init();
 	if (mtrr_trim_uncached_memory(max_pfn))
-		max_pfn = e820_end_of_ram_pfn();
+		max_pfn = e820__end_of_ram_pfn();
 
 	max_possible_pfn = max_pfn;
 
@@ -1094,7 +1090,7 @@ void __init setup_arch(char **cmdline_p)
 	/* How many end-of-memory variables you have, grandma! */
 	/* need this before calling reserve_initrd */
 	if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
-		max_low_pfn = e820_end_of_low_ram_pfn();
+		max_low_pfn = e820__end_of_low_ram_pfn();
 	else
 		max_low_pfn = max_pfn;
 
@@ -1111,7 +1107,7 @@ void __init setup_arch(char **cmdline_p)
 	early_alloc_pgt_buf();
 
 	/*
-	 * Need to conclude brk, before memblock_x86_fill()
+	 * Need to conclude brk, before e820__memblock_setup()
 	 *  it could use memblock_find_in_range, could overlap with
 	 *  brk area.
 	 */
@@ -1120,7 +1116,10 @@ void __init setup_arch(char **cmdline_p)
 	cleanup_highmap();
 
 	memblock_set_current_limit(ISA_END_ADDRESS);
-	memblock_x86_fill();
+	e820__memblock_setup();
+
+	if (!early_xdbc_setup_hardware())
+		early_xdbc_register_console();
 
 	reserve_bios_regions();
 
@@ -1137,7 +1136,7 @@ void __init setup_arch(char **cmdline_p)
 	}
 
 	/* preallocate 4k for mptable mpc */
-	early_reserve_e820_mpc_new();
+	e820__memblock_alloc_reserved_mpc_new();
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 	setup_bios_corruption_check();
@@ -1226,21 +1225,6 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-#ifdef CONFIG_X86_32
-	/* sync back kernel address range */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
-	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
-	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
-
 	tboot_probe();
 
 	map_vsyscall();
@@ -1275,12 +1259,12 @@ void __init setup_arch(char **cmdline_p)
 
 	kvm_guest_init();
 
-	e820_reserve_resources();
-	e820_mark_nosave_regions(max_low_pfn);
+	e820__reserve_resources();
+	e820__register_nosave_regions(max_low_pfn);
 
 	x86_init.resources.reserve_resources();
 
-	e820_setup_gap();
+	e820__setup_pci_gap();
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 9820d6d977c6..bb1e8cc0bc84 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -160,7 +160,7 @@ static inline void setup_percpu_segment(int cpu)
 	pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF,
 			0x2 | DESCTYPE_S, 0x8);
 	gdt.s = 1;
-	write_gdt_entry(get_cpu_gdt_table(cpu),
+	write_gdt_entry(get_cpu_gdt_rw(cpu),
 			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
 #endif
 }
@@ -288,4 +288,25 @@ void __init setup_per_cpu_areas(void)
 
 	/* Setup cpu initialized, callin, callout masks */
 	setup_cpu_local_masks();
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Sync back kernel address range.  We want to make sure that
+	 * all kernel mappings, including percpu mappings, are available
+	 * in the smpboot asm.  We can't reliably pick up percpu
+	 * mappings using vmalloc_fault(), because exception dispatch
+	 * needs percpu data.
+	 */
+	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			KERNEL_PGD_PTRS);
+
+	/*
+	 * sync back low identity map too.  It is used for example
+	 * in the 32-bit EFI stub.
+	 */
+	clone_pgd_range(initial_page_table,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+#endif
 }
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 396c042e9d0e..cc30a74e4adb 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -846,7 +846,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 		       task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
 		       me->comm, me->pid, where, frame,
 		       regs->ip, regs->sp, regs->orig_ax);
-		print_vma_addr(" in ", regs->ip);
+		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
 
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ec1f756f9dc9..71beb28600d4 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
 
 				if (from->si_signo == SIGSEGV) {
 					if (from->si_code == SEGV_BNDERR) {
-						compat_uptr_t lower = (unsigned long)&to->si_lower;
-						compat_uptr_t upper = (unsigned long)&to->si_upper;
+						compat_uptr_t lower = (unsigned long)from->si_lower;
+						compat_uptr_t upper = (unsigned long)from->si_upper;
 						put_user_ex(lower, &to->si_lower);
 						put_user_ex(upper, &to->si_upper);
 					}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d3c66a15bbde..d798c0da451c 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -33,6 +33,7 @@
 #include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 #include <asm/kexec.h>
+#include <asm/virtext.h>
 
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
@@ -124,7 +125,7 @@ static bool smp_no_nmi_ipi = false;
 static void native_smp_send_reschedule(int cpu)
 {
 	if (unlikely(cpu_is_offline(cpu))) {
-		WARN_ON(1);
+		WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
 		return;
 	}
 	apic->send_IPI(cpu, RESCHEDULE_VECTOR);
@@ -162,6 +163,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
 		return NMI_HANDLED;
 
+	cpu_emergency_vmxoff();
 	stop_this_cpu(NULL);
 
 	return NMI_HANDLED;
@@ -174,6 +176,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 asmlinkage __visible void smp_reboot_interrupt(void)
 {
 	ipi_entering_ack_irq();
+	cpu_emergency_vmxoff();
 	stop_this_cpu(NULL);
 	irq_exit();
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bd1f1ad35284..f04479a8f74f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -983,7 +983,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	unsigned long timeout;
 
 	idle->thread.sp = (unsigned long)task_pt_regs(idle);
-	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
+	early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
 	initial_code = (unsigned long)start_secondary;
 	initial_stack  = idle->thread.sp;
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 50215a4b9347..207b8f2582c7 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -17,6 +17,8 @@
 #include <linux/uaccess.h>
 #include <linux/elf.h>
 
+#include <asm/elf.h>
+#include <asm/compat.h>
 #include <asm/ia32.h>
 #include <asm/syscalls.h>
 
@@ -101,7 +103,7 @@ out:
 static void find_start_end(unsigned long flags, unsigned long *begin,
 			   unsigned long *end)
 {
-	if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
+	if (!in_compat_syscall() && (flags & MAP_32BIT)) {
 		/* This is usually used needed to map code in small
 		   model, so it needs to be in the first 31bit. Limit
 		   it to that.  This means we need to move the
@@ -114,10 +116,11 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
 		if (current->flags & PF_RANDOMIZE) {
 			*begin = randomize_page(*begin, 0x02000000);
 		}
-	} else {
-		*begin = current->mm->mmap_legacy_base;
-		*end = TASK_SIZE;
+		return;
 	}
+
+	*begin	= get_mmap_base(1);
+	*end	= in_compat_syscall() ? tasksize_32bit() : tasksize_64bit();
 }
 
 unsigned long
@@ -176,7 +179,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		return addr;
 
 	/* for MAP_32BIT mappings we force the legacy mmap base */
-	if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
+	if (!in_compat_syscall() && (flags & MAP_32BIT))
 		goto bottomup;
 
 	/* requesting a specific address */
@@ -191,7 +194,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
-	info.high_limit = mm->mmap_base;
+	info.high_limit = get_mmap_base(0);
 	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 	if (filp) {
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index b868fa1b812b..d4c8011a2293 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -42,7 +42,7 @@
 #include <asm/fixmap.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/io.h>
 
 #include "../realmode/rm/wakeup.h"
@@ -68,9 +68,9 @@ void __init tboot_probe(void)
 	 * also verify that it is mapped as we expect it before calling
 	 * set_fixmap(), to reduce chance of garbage value causing crash
 	 */
-	if (!e820_any_mapped(boot_params.tboot_addr,
-			     boot_params.tboot_addr, E820_RESERVED)) {
-		pr_warning("non-0 tboot_addr but it is not of type E820_RESERVED\n");
+	if (!e820__mapped_any(boot_params.tboot_addr,
+			     boot_params.tboot_addr, E820_TYPE_RESERVED)) {
+		pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n");
 		return;
 	}
 
@@ -118,12 +118,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
 			  pgprot_t prot)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
 	pgd = pgd_offset(&tboot_mm, vaddr);
-	pud = pud_alloc(&tboot_mm, pgd, vaddr);
+	p4d = p4d_alloc(&tboot_mm, pgd, vaddr);
+	if (!p4d)
+		return -1;
+	pud = pud_alloc(&tboot_mm, p4d, vaddr);
 	if (!pud)
 		return -1;
 	pmd = pmd_alloc(&tboot_mm, pud, vaddr);
@@ -188,12 +192,12 @@ static int tboot_setup_sleep(void)
 
 	tboot->num_mac_regions = 0;
 
-	for (i = 0; i < e820->nr_map; i++) {
-		if ((e820->map[i].type != E820_RAM)
-		 && (e820->map[i].type != E820_RESERVED_KERN))
+	for (i = 0; i < e820_table->nr_entries; i++) {
+		if ((e820_table->entries[i].type != E820_TYPE_RAM)
+		 && (e820_table->entries[i].type != E820_TYPE_RESERVED_KERN))
 			continue;
 
-		add_mac_region(e820->map[i].addr, e820->map[i].size);
+		add_mac_region(e820_table->entries[i].addr, e820_table->entries[i].size);
 	}
 
 	tboot->acpi_sinfo.kernel_s3_resume_vector =
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6c8934406dc9..dcd699baea1b 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -92,10 +92,17 @@ static void set_tls_desc(struct task_struct *p, int idx,
 	cpu = get_cpu();
 
 	while (n-- > 0) {
-		if (LDT_empty(info) || LDT_zero(info))
+		if (LDT_empty(info) || LDT_zero(info)) {
 			desc->a = desc->b = 0;
-		else
+		} else {
 			fill_ldt(desc, info);
+
+			/*
+			 * Always set the accessed bit so that the CPU
+			 * doesn't try to write to the (read-only) GDT.
+			 */
+			desc->type |= 1;
+		}
 		++info;
 		++desc;
 	}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 948443e115c1..3995d3a777d4 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -169,6 +169,37 @@ void ist_end_non_atomic(void)
 	preempt_disable();
 }
 
+int is_valid_bugaddr(unsigned long addr)
+{
+	unsigned short ud;
+
+	if (addr < TASK_SIZE_MAX)
+		return 0;
+
+	if (probe_kernel_address((unsigned short *)addr, ud))
+		return 0;
+
+	return ud == INSN_UD0 || ud == INSN_UD2;
+}
+
+static int fixup_bug(struct pt_regs *regs, int trapnr)
+{
+	if (trapnr != X86_TRAP_UD)
+		return 0;
+
+	switch (report_bug(regs->ip, regs)) {
+	case BUG_TRAP_TYPE_NONE:
+	case BUG_TRAP_TYPE_BUG:
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		regs->ip += LEN_UD0;
+		return 1;
+	}
+
+	return 0;
+}
+
 static nokprobe_inline int
 do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 		  struct pt_regs *regs,	long error_code)
@@ -187,12 +218,15 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	}
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs, trapnr)) {
-			tsk->thread.error_code = error_code;
-			tsk->thread.trap_nr = trapnr;
-			die(str, regs, error_code);
-		}
-		return 0;
+		if (fixup_exception(regs, trapnr))
+			return 0;
+
+		if (fixup_bug(regs, trapnr))
+			return 0;
+
+		tsk->thread.error_code = error_code;
+		tsk->thread.trap_nr = trapnr;
+		die(str, regs, error_code);
 	}
 
 	return -1;
@@ -255,7 +289,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 		pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
 			tsk->comm, tsk->pid, str,
 			regs->ip, regs->sp, error_code);
-		print_vma_addr(" in ", regs->ip);
+		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
 
@@ -519,7 +553,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 		pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
 			tsk->comm, task_pid_nr(tsk),
 			regs->ip, regs->sp, error_code);
-		print_vma_addr(" in ", regs->ip);
+		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 46bcda4cb1c2..714dfba6a1e7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -327,9 +327,16 @@ unsigned long long sched_clock(void)
 {
 	return paravirt_sched_clock();
 }
+
+bool using_native_sched_clock(void)
+{
+	return pv_time_ops.sched_clock == native_sched_clock;
+}
 #else
 unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
+
+bool using_native_sched_clock(void) { return true; }
 #endif
 
 int check_tsc_unstable(void)
@@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
 {
 	if (tsc_unstable)
 		return;
+
 	tsc_unstable = 1;
-	clear_sched_clock_stable();
+	if (using_native_sched_clock())
+		clear_sched_clock_stable();
 	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to clocksource watchdog\n");
 }
@@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = {
 
 void mark_tsc_unstable(char *reason)
 {
-	if (!tsc_unstable) {
-		tsc_unstable = 1;
+	if (tsc_unstable)
+		return;
+
+	tsc_unstable = 1;
+	if (using_native_sched_clock())
 		clear_sched_clock_stable();
-		disable_sched_clock_irqtime();
-		pr_info("Marking TSC unstable due to %s\n", reason);
-		/* Change only the rating, when not registered */
-		if (clocksource_tsc.mult)
-			clocksource_mark_unstable(&clocksource_tsc);
-		else {
-			clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
-			clocksource_tsc.rating = 0;
-		}
+	disable_sched_clock_irqtime();
+	pr_info("Marking TSC unstable due to %s\n", reason);
+	/* Change only the rating, when not registered */
+	if (clocksource_tsc.mult) {
+		clocksource_mark_unstable(&clocksource_tsc);
+	} else {
+		clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
+		clocksource_tsc.rating = 0;
 	}
 }
 
@@ -1322,6 +1333,8 @@ static int __init init_tsc_clocksource(void)
 	 * the refined calibration and directly register it as a clocksource.
 	 */
 	if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+		if (boot_cpu_has(X86_FEATURE_ART))
+			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
 		return 0;
 	}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 5ed43910e04b..82c6d7f1fd73 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -1,6 +1,8 @@
 #include <linux/sched.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/interrupt.h>
+#include <asm/sections.h>
 #include <asm/ptrace.h>
 #include <asm/bitops.h>
 #include <asm/stacktrace.h>
@@ -23,53 +25,53 @@
 	val;						\
 })
 
-static void unwind_dump(struct unwind_state *state, unsigned long *sp)
+static void unwind_dump(struct unwind_state *state)
 {
 	static bool dumped_before = false;
 	bool prev_zero, zero = false;
-	unsigned long word;
+	unsigned long word, *sp;
+	struct stack_info stack_info = {0};
+	unsigned long visit_mask = 0;
 
 	if (dumped_before)
 		return;
 
 	dumped_before = true;
 
-	printk_deferred("unwind stack type:%d next_sp:%p mask:%lx graph_idx:%d\n",
+	printk_deferred("unwind stack type:%d next_sp:%p mask:0x%lx graph_idx:%d\n",
 			state->stack_info.type, state->stack_info.next_sp,
 			state->stack_mask, state->graph_idx);
 
-	for (sp = state->orig_sp; sp < state->stack_info.end; sp++) {
-		word = READ_ONCE_NOCHECK(*sp);
+	for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+		if (get_stack_info(sp, state->task, &stack_info, &visit_mask))
+			break;
 
-		prev_zero = zero;
-		zero = word == 0;
+		for (; sp < stack_info.end; sp++) {
 
-		if (zero) {
-			if (!prev_zero)
-				printk_deferred("%p: %016x ...\n", sp, 0);
-			continue;
-		}
+			word = READ_ONCE_NOCHECK(*sp);
+
+			prev_zero = zero;
+			zero = word == 0;
+
+			if (zero) {
+				if (!prev_zero)
+					printk_deferred("%p: %0*x ...\n",
+							sp, BITS_PER_LONG/4, 0);
+				continue;
+			}
 
-		printk_deferred("%p: %016lx (%pB)\n", sp, word, (void *)word);
+			printk_deferred("%p: %0*lx (%pB)\n",
+					sp, BITS_PER_LONG/4, word, (void *)word);
+		}
 	}
 }
 
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {
-	unsigned long addr;
-	unsigned long *addr_p = unwind_get_return_address_ptr(state);
-
 	if (unwind_done(state))
 		return 0;
 
-	if (state->regs && user_mode(state->regs))
-		return 0;
-
-	addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
-	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr,
-				     addr_p);
-
-	return __kernel_text_address(addr) ? addr : 0;
+	return __kernel_text_address(state->ip) ? state->ip : 0;
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
@@ -82,19 +84,68 @@ static size_t regs_size(struct pt_regs *regs)
 	return sizeof(*regs);
 }
 
+static bool in_entry_code(unsigned long ip)
+{
+	char *addr = (char *)ip;
+
+	if (addr >= __entry_text_start && addr < __entry_text_end)
+		return true;
+
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+	if (addr >= __irqentry_text_start && addr < __irqentry_text_end)
+		return true;
+#endif
+
+	return false;
+}
+
+static inline unsigned long *last_frame(struct unwind_state *state)
+{
+	return (unsigned long *)task_pt_regs(state->task) - 2;
+}
+
+#ifdef CONFIG_X86_32
+#define GCC_REALIGN_WORDS 3
+#else
+#define GCC_REALIGN_WORDS 1
+#endif
+
+static inline unsigned long *last_aligned_frame(struct unwind_state *state)
+{
+	return last_frame(state) - GCC_REALIGN_WORDS;
+}
+
 static bool is_last_task_frame(struct unwind_state *state)
 {
-	unsigned long bp = (unsigned long)state->bp;
-	unsigned long regs = (unsigned long)task_pt_regs(state->task);
+	unsigned long *last_bp = last_frame(state);
+	unsigned long *aligned_bp = last_aligned_frame(state);
 
 	/*
 	 * We have to check for the last task frame at two different locations
 	 * because gcc can occasionally decide to realign the stack pointer and
-	 * change the offset of the stack frame by a word in the prologue of a
-	 * function called by head/entry code.
+	 * change the offset of the stack frame in the prologue of a function
+	 * called by head/entry code.  Examples:
+	 *
+	 * <start_secondary>:
+	 *      push   %edi
+	 *      lea    0x8(%esp),%edi
+	 *      and    $0xfffffff8,%esp
+	 *      pushl  -0x4(%edi)
+	 *      push   %ebp
+	 *      mov    %esp,%ebp
+	 *
+	 * <x86_64_start_kernel>:
+	 *      lea    0x8(%rsp),%r10
+	 *      and    $0xfffffffffffffff0,%rsp
+	 *      pushq  -0x8(%r10)
+	 *      push   %rbp
+	 *      mov    %rsp,%rbp
+	 *
+	 * Note that after aligning the stack, it pushes a duplicate copy of
+	 * the return address before pushing the frame pointer.
 	 */
-	return bp == regs - FRAME_HEADER_SIZE ||
-	       bp == regs - FRAME_HEADER_SIZE - sizeof(long);
+	return (state->bp == last_bp ||
+		(state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
 }
 
 /*
@@ -111,26 +162,70 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp)
 	return (struct pt_regs *)(regs & ~0x1);
 }
 
-static bool update_stack_state(struct unwind_state *state, void *addr,
-			       size_t len)
+static bool update_stack_state(struct unwind_state *state,
+			       unsigned long *next_bp)
 {
 	struct stack_info *info = &state->stack_info;
-	enum stack_type orig_type = info->type;
+	enum stack_type prev_type = info->type;
+	struct pt_regs *regs;
+	unsigned long *frame, *prev_frame_end, *addr_p, addr;
+	size_t len;
+
+	if (state->regs)
+		prev_frame_end = (void *)state->regs + regs_size(state->regs);
+	else
+		prev_frame_end = (void *)state->bp + FRAME_HEADER_SIZE;
+
+	/* Is the next frame pointer an encoded pointer to pt_regs? */
+	regs = decode_frame_pointer(next_bp);
+	if (regs) {
+		frame = (unsigned long *)regs;
+		len = regs_size(regs);
+		state->got_irq = true;
+	} else {
+		frame = next_bp;
+		len = FRAME_HEADER_SIZE;
+	}
 
 	/*
-	 * If addr isn't on the current stack, switch to the next one.
+	 * If the next bp isn't on the current stack, switch to the next one.
 	 *
 	 * We may have to traverse multiple stacks to deal with the possibility
-	 * that 'info->next_sp' could point to an empty stack and 'addr' could
-	 * be on a subsequent stack.
+	 * that info->next_sp could point to an empty stack and the next bp
+	 * could be on a subsequent stack.
 	 */
-	while (!on_stack(info, addr, len))
+	while (!on_stack(info, frame, len))
 		if (get_stack_info(info->next_sp, state->task, info,
 				   &state->stack_mask))
 			return false;
 
-	if (!state->orig_sp || info->type != orig_type)
-		state->orig_sp = addr;
+	/* Make sure it only unwinds up and doesn't overlap the prev frame: */
+	if (state->orig_sp && state->stack_info.type == prev_type &&
+	    frame < prev_frame_end)
+		return false;
+
+	/* Move state to the next frame: */
+	if (regs) {
+		state->regs = regs;
+		state->bp = NULL;
+	} else {
+		state->bp = next_bp;
+		state->regs = NULL;
+	}
+
+	/* Save the return address: */
+	if (state->regs && user_mode(state->regs))
+		state->ip = 0;
+	else {
+		addr_p = unwind_get_return_address_ptr(state);
+		addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
+		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+						  addr, addr_p);
+	}
+
+	/* Save the original stack pointer for unwind_dump(): */
+	if (!state->orig_sp)
+		state->orig_sp = frame;
 
 	return true;
 }
@@ -138,14 +233,12 @@ static bool update_stack_state(struct unwind_state *state, void *addr,
 bool unwind_next_frame(struct unwind_state *state)
 {
 	struct pt_regs *regs;
-	unsigned long *next_bp, *next_frame;
-	size_t next_len;
-	enum stack_type prev_type = state->stack_info.type;
+	unsigned long *next_bp;
 
 	if (unwind_done(state))
 		return false;
 
-	/* have we reached the end? */
+	/* Have we reached the end? */
 	if (state->regs && user_mode(state->regs))
 		goto the_end;
 
@@ -173,54 +266,19 @@ bool unwind_next_frame(struct unwind_state *state)
 		 */
 		state->regs = regs;
 		state->bp = NULL;
+		state->ip = 0;
 		return true;
 	}
 
-	/* get the next frame pointer */
+	/* Get the next frame pointer: */
 	if (state->regs)
 		next_bp = (unsigned long *)state->regs->bp;
 	else
-		next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp);
-
-	/* is the next frame pointer an encoded pointer to pt_regs? */
-	regs = decode_frame_pointer(next_bp);
-	if (regs) {
-		next_frame = (unsigned long *)regs;
-		next_len = sizeof(*regs);
-	} else {
-		next_frame = next_bp;
-		next_len = FRAME_HEADER_SIZE;
-	}
-
-	/* make sure the next frame's data is accessible */
-	if (!update_stack_state(state, next_frame, next_len)) {
-		/*
-		 * Don't warn on bad regs->bp.  An interrupt in entry code
-		 * might cause a false positive warning.
-		 */
-		if (state->regs)
-			goto the_end;
+		next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task, *state->bp);
 
+	/* Move to the next frame if it's safe: */
+	if (!update_stack_state(state, next_bp))
 		goto bad_address;
-	}
-
-	/* Make sure it only unwinds up and doesn't overlap the last frame: */
-	if (state->stack_info.type == prev_type) {
-		if (state->regs && (void *)next_frame < (void *)state->regs + regs_size(state->regs))
-			goto bad_address;
-
-		if (state->bp && (void *)next_frame < (void *)state->bp + FRAME_HEADER_SIZE)
-			goto bad_address;
-	}
-
-	/* move to the next frame */
-	if (regs) {
-		state->regs = regs;
-		state->bp = NULL;
-	} else {
-		state->bp = next_bp;
-		state->regs = NULL;
-	}
 
 	return true;
 
@@ -237,18 +295,29 @@ bad_address:
 	if (state->task != current)
 		goto the_end;
 
+	/*
+	 * Don't warn if the unwinder got lost due to an interrupt in entry
+	 * code or in the C handler before the first frame pointer got set up:
+	 */
+	if (state->got_irq && in_entry_code(state->ip))
+		goto the_end;
+	if (state->regs &&
+	    state->regs->sp >= (unsigned long)last_aligned_frame(state) &&
+	    state->regs->sp < (unsigned long)task_pt_regs(state->task))
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
 			state->regs, state->task->comm,
-			state->task->pid, next_frame);
-		unwind_dump(state, (unsigned long *)state->regs);
+			state->task->pid, next_bp);
+		unwind_dump(state);
 	} else {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n",
 			state->bp, state->task->comm,
-			state->task->pid, next_frame);
-		unwind_dump(state, state->bp);
+			state->task->pid, next_bp);
+		unwind_dump(state);
 	}
 the_end:
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
@@ -259,35 +328,24 @@ EXPORT_SYMBOL_GPL(unwind_next_frame);
 void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		    struct pt_regs *regs, unsigned long *first_frame)
 {
-	unsigned long *bp, *frame;
-	size_t len;
+	unsigned long *bp;
 
 	memset(state, 0, sizeof(*state));
 	state->task = task;
+	state->got_irq = (regs);
 
-	/* don't even attempt to start from user mode regs */
+	/* Don't even attempt to start from user mode regs: */
 	if (regs && user_mode(regs)) {
 		state->stack_info.type = STACK_TYPE_UNKNOWN;
 		return;
 	}
 
-	/* set up the starting stack frame */
 	bp = get_frame_pointer(task, regs);
-	regs = decode_frame_pointer(bp);
-	if (regs) {
-		state->regs = regs;
-		frame = (unsigned long *)regs;
-		len = sizeof(*regs);
-	} else {
-		state->bp = bp;
-		frame = bp;
-		len = FRAME_HEADER_SIZE;
-	}
 
-	/* initialize stack info and make sure the frame data is accessible */
-	get_stack_info(frame, state->task, &state->stack_info,
+	/* Initialize stack info and make sure the frame data is accessible: */
+	get_stack_info(bp, state->task, &state->stack_info,
 		       &state->stack_mask);
-	update_stack_state(state, frame, len);
+	update_stack_state(state, bp);
 
 	/*
 	 * The caller can provide the address of the first frame directly
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 22881ddcbb9f..039f36738e49 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -34,7 +34,7 @@ bool unwind_next_frame(struct unwind_state *state)
 				return true;
 		}
 
-		state->sp = info->next_sp;
+		state->sp = PTR_ALIGN(info->next_sp, sizeof(long));
 
 	} while (!get_stack_info(state->sp, state->task, info,
 				 &state->stack_mask));
@@ -49,7 +49,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	memset(state, 0, sizeof(*state));
 
 	state->task = task;
-	state->sp   = first_frame;
+	state->sp   = PTR_ALIGN(first_frame, sizeof(long));
 
 	get_stack_info(first_frame, state->task, &state->stack_info,
 		       &state->stack_mask);
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 23ee89ce59a9..7924a5356c8a 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -164,6 +164,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -173,7 +174,10 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	pgd = pgd_offset(mm, 0xA0000);
 	if (pgd_none_or_clear_bad(pgd))
 		goto out;
-	pud = pud_offset(pgd, 0xA0000);
+	p4d = p4d_offset(pgd, 0xA0000);
+	if (p4d_none_or_clear_bad(p4d))
+		goto out;
+	pud = pud_offset(p4d, 0xA0000);
 	if (pud_none_or_clear_bad(pud))
 		goto out;
 	pmd = pmd_offset(pud, 0xA0000);
@@ -193,7 +197,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	pte_unmap_unlock(pte, ptl);
 out:
 	up_write(&mm->mmap_sem);
-	flush_tlb();
+	flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL);
 }
 
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index c74ae9ce8dc4..c8a3b61be0aa 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -146,6 +146,7 @@ SECTIONS
 		_edata = .;
 	} :data
 
+	BUG_TABLE
 
 	. = ALIGN(PAGE_SIZE);
 	__vvar_page = .;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 11a93f005268..a088b2c47f73 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -14,7 +14,7 @@
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/time.h>
 #include <asm/irq.h>
 #include <asm/io_apic.h>
@@ -38,7 +38,7 @@ struct x86_init_ops x86_init __initdata = {
 	.resources = {
 		.probe_roms		= probe_roms,
 		.reserve_resources	= reserve_standard_io_resources,
-		.memory_setup		= default_machine_specific_memory_setup,
+		.memory_setup		= e820__memory_setup_default,
 	},
 
 	.mpparse = {
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 73ea24d4f119..047b17a26269 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm)
 {
 	struct kvm_pic *vpic = kvm->arch.vpic;
 
+	if (!vpic)
+		return;
+
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 6e219e5c07d2..289270a6aecb 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
+	if (!ioapic)
+		return;
+
 	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
 	kvm->arch.vioapic = NULL;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 37942e419c32..60168cdd0546 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
 }
 
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+	cleanup_srcu_struct(&head->track_srcu);
+}
+
 void kvm_page_track_init(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d1efe2c62b3f..5f48f62b8dc2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -741,7 +741,6 @@ static int svm_hardware_enable(void)
 
 	struct svm_cpu_data *sd;
 	uint64_t efer;
-	struct desc_ptr gdt_descr;
 	struct desc_struct *gdt;
 	int me = raw_smp_processor_id();
 
@@ -763,8 +762,7 @@ static int svm_hardware_enable(void)
 	sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
 	sd->next_asid = sd->max_asid + 1;
 
-	native_store_gdt(&gdt_descr);
-	gdt = (struct desc_struct *)gdt_descr.address;
+	gdt = get_current_gdt_rw();
 	sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
 	wrmsrl(MSR_EFER, efer | EFER_SVME);
@@ -1379,6 +1377,9 @@ static void avic_vm_destroy(struct kvm *kvm)
 	unsigned long flags;
 	struct kvm_arch *vm_data = &kvm->arch;
 
+	if (!avic)
+		return;
+
 	avic_free_vm_id(vm_data->avic_vm_id);
 
 	if (vm_data->avic_logical_id_table_page)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 283aa8601833..1a471e5f963f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -935,7 +935,6 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
  * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it.
  */
 static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
-static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
 
 /*
  * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
@@ -1239,6 +1238,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
 	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
 }
 
+static inline bool cpu_has_vmx_invvpid(void)
+{
+	return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
 static inline bool cpu_has_vmx_ept(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -2052,14 +2056,13 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
  */
 static unsigned long segment_base(u16 selector)
 {
-	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *table;
 	unsigned long v;
 
 	if (!(selector & ~SEGMENT_RPL_MASK))
 		return 0;
 
-	table = (struct desc_struct *)gdt->address;
+	table = get_current_gdt_ro();
 
 	if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) {
 		u16 ldt_selector = kvm_read_ldt();
@@ -2164,7 +2167,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #endif
 	if (vmx->host_state.msr_host_bndcfgs)
 		wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
-	load_gdt(this_cpu_ptr(&host_gdt));
+	load_fixmap_gdt(raw_smp_processor_id());
 }
 
 static void vmx_load_host_state(struct vcpu_vmx *vmx)
@@ -2266,7 +2269,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	if (!already_loaded) {
-		struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
+		void *gdt = get_current_gdt_ro();
 		unsigned long sysenter_esp;
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
@@ -2277,7 +2280,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 */
 		vmcs_writel(HOST_TR_BASE,
 			    (unsigned long)this_cpu_ptr(&cpu_tss));
-		vmcs_writel(HOST_GDTR_BASE, gdt->address);
+		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
 
 		/*
 		 * VM exits change the host TR limit to 0x67 after a VM
@@ -2753,7 +2756,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_RDTSCP |
 		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-		SECONDARY_EXEC_ENABLE_VPID |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING |
@@ -2781,10 +2783,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 * though it is treated as global context.  The alternative is
 	 * not failing the single-context invvpid, and it is worse.
 	 */
-	if (enable_vpid)
+	if (enable_vpid) {
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_ENABLE_VPID;
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
 			VMX_VPID_EXTENT_SUPPORTED_MASK;
-	else
+	} else
 		vmx->nested.nested_vmx_vpid_caps = 0;
 
 	if (enable_unrestricted_guest)
@@ -3465,8 +3469,6 @@ static int hardware_enable(void)
 		ept_sync_global();
 	}
 
-	native_store_gdt(this_cpu_ptr(&host_gdt));
-
 	return 0;
 }
 
@@ -4024,6 +4026,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
 }
 
+static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
+{
+	if (enable_ept)
+		vmx_flush_tlb(vcpu);
+}
+
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -6517,8 +6525,10 @@ static __init int hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
-	if (!cpu_has_vmx_vpid())
+	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
+
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
 	if (enable_shadow_vmcs)
@@ -7258,9 +7268,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 zero = 0;
 	gpa_t vmptr;
-	struct vmcs12 *vmcs12;
-	struct page *page;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -7271,22 +7280,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (vmptr == vmx->nested.current_vmptr)
 		nested_release_vmcs12(vmx);
 
-	page = nested_get_page(vcpu, vmptr);
-	if (page == NULL) {
-		/*
-		 * For accurate processor emulation, VMCLEAR beyond available
-		 * physical memory should do nothing at all. However, it is
-		 * possible that a nested vmx bug, not a guest hypervisor bug,
-		 * resulted in this case, so let's shut down before doing any
-		 * more damage:
-		 */
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return 1;
-	}
-	vmcs12 = kmap(page);
-	vmcs12->launch_state = 0;
-	kunmap(page);
-	nested_release_page(page);
+	kvm_vcpu_write_guest(vcpu,
+			vmptr + offsetof(struct vmcs12, launch_state),
+			&zero, sizeof(zero));
 
 	nested_free_vmcs02(vmx, vmptr);
 
@@ -8198,6 +8194,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return false;
+	case EXIT_REASON_PML_FULL:
+		/* We don't expose PML support to L1. */
+		return false;
 	default:
 		return true;
 	}
@@ -8515,7 +8514,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	    && kvm_vmx_exit_handlers[exit_reason])
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
 	else {
-		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+				exit_reason);
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}
@@ -8561,6 +8561,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -8586,8 +8587,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	 */
 	if (!is_guest_mode(vcpu) ||
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
-			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
+		vmx_flush_tlb_ept_only(vcpu);
+	}
 }
 
 static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
@@ -9694,10 +9697,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		return false;
 
 	page = nested_get_page(vcpu, vmcs12->msr_bitmap);
-	if (!page) {
-		WARN_ON(1);
+	if (!page)
 		return false;
-	}
 	msr_bitmap_l1 = (unsigned long *)kmap(page);
 
 	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
@@ -9990,7 +9991,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
-	bool nested_ept_enabled = false;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10137,8 +10137,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				vmcs12->guest_intr_status);
 		}
 
-		nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
-
 		/*
 		 * Write an illegal value to APIC_ACCESS_ADDR. Later,
 		 * nested_get_vmcs12_pages will either fix it up or
@@ -10268,9 +10266,24 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	}
 
+	if (enable_pml) {
+		/*
+		 * Conceptually we want to copy the PML address and index from
+		 * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+		 * since we always flush the log on each vmexit, this happens
+		 * to be equivalent to simply resetting the fields in vmcs02.
+		 */
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	if (nested_cpu_has_ept(vmcs12)) {
 		kvm_mmu_unload(vcpu);
 		nested_ept_init_mmu_context(vcpu);
+	} else if (nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 
 	/*
@@ -10298,12 +10311,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmx_set_efer(vcpu, vcpu->arch.efer);
 
 	/* Shadow page tables on either EPT or shadow page tables. */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
 				entry_failure_code))
 		return 1;
 
-	kvm_mmu_reset_context(vcpu);
-
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
@@ -11072,6 +11083,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
 		vmx_set_virtual_x2apic_mode(vcpu,
 				vcpu->arch.apic_base & X2APIC_ENABLE);
+	} else if (!nested_cpu_has_ept(vmcs12) &&
+		   nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -11121,8 +11136,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
  */
 static void vmx_leave_nested(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu))
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.nested_run_pending = 0;
 		nested_vmx_vmexit(vcpu, -1, 0, 0);
+	}
 	free_nested(to_vmx(vcpu));
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1faf620a6fdc..ccbd45ecd41a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	if (kvm_x86_ops->vm_destroy)
 		kvm_x86_ops->vm_destroy(kvm);
 	kvm_iommu_unmap_guest(kvm);
-	kfree(kvm->arch.vpic);
-	kfree(kvm->arch.vioapic);
+	kvm_pic_destroy(kvm);
+	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kvm_mmu_uninit_vm(kvm);
+	kvm_page_track_cleanup(kvm);
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 
 	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
 	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index d3289d7e78fa..99472698c931 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -67,7 +67,7 @@
 #include <asm/pgtable.h>
 #include <asm/desc.h>
 #include <asm/setup.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mce.h>
 #include <asm/io.h>
 #include <asm/fpu/api.h>
@@ -994,7 +994,9 @@ static struct clock_event_device lguest_clockevent = {
 	.mult                   = 1,
 	.shift                  = 0,
 	.min_delta_ns           = LG_CLOCK_MIN_DELTA,
+	.min_delta_ticks        = LG_CLOCK_MIN_DELTA,
 	.max_delta_ns           = LG_CLOCK_MAX_DELTA,
+	.max_delta_ticks        = LG_CLOCK_MAX_DELTA,
 };
 
 /*
@@ -1178,9 +1180,9 @@ static __init char *lguest_memory_setup(void)
 	 * The Linux bootloader header contains an "e820" memory map: the
 	 * Launcher populated the first entry with our memory limit.
 	 */
-	e820_add_region(boot_params.e820_map[0].addr,
-			  boot_params.e820_map[0].size,
-			  boot_params.e820_map[0].type);
+	e820__range_add(boot_params.e820_table[0].addr,
+			  boot_params.e820_table[0].size,
+			  boot_params.e820_table[0].type);
 
 	/* This string is for the boot messages. */
 	return "LGUEST";
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 5e2af3a88cf5..81b1635d67de 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -14,20 +14,15 @@
  * Zero a page.
  * %rdi	- page
  */
-ENTRY(clear_page)
-
-	ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
-		      "jmp clear_page_c_e", X86_FEATURE_ERMS
-
+ENTRY(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
 	ret
-ENDPROC(clear_page)
-EXPORT_SYMBOL(clear_page)
+ENDPROC(clear_page_rep)
+EXPORT_SYMBOL_GPL(clear_page_rep)
 
 ENTRY(clear_page_orig)
-
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
 	.p2align 4
@@ -47,10 +42,12 @@ ENTRY(clear_page_orig)
 	nop
 	ret
 ENDPROC(clear_page_orig)
+EXPORT_SYMBOL_GPL(clear_page_orig)
 
-ENTRY(clear_page_c_e)
+ENTRY(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
 	ret
-ENDPROC(clear_page_c_e)
+ENDPROC(clear_page_erms)
+EXPORT_SYMBOL_GPL(clear_page_erms)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index a8e91ae89fb3..29df077cb089 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -93,6 +93,13 @@ static void delay_mwaitx(unsigned long __loops)
 {
 	u64 start, end, delay, loops = __loops;
 
+	/*
+	 * Timer value of 0 causes MWAITX to wait indefinitely, unless there
+	 * is a store on the memory monitored by MONITORX.
+	 */
+	if (loops == 0)
+		return;
+
 	start = rdtsc_ordered();
 
 	for (;;) {
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 121f59c6ee54..5761a4f19455 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -8,7 +8,7 @@
 #include <asm/kaslr.h>
 #include <asm/msr.h>
 #include <asm/archrandom.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/io.h>
 
 /*
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 779782f58324..9a53a06e5a3e 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -290,7 +290,7 @@ EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
 	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index c074799bddae..c8c6ad0d58b8 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -4,12 +4,9 @@
  *  For licencing details see kernel-base/COPYING
  */
 
-#include <linux/highmem.h>
+#include <linux/uaccess.h>
 #include <linux/export.h>
 
-#include <asm/word-at-a-time.h>
-#include <linux/sched.h>
-
 /*
  * We rely on the nested NMI work to allow atomic faults from the NMI path; the
  * nested NMI paths are careful to preserve CR2.
@@ -34,52 +31,3 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-unsigned long _copy_to_user(void __user *to, const void *from, unsigned n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		n = __copy_to_user(to, from, n);
-	return n;
-}
-EXPORT_SYMBOL(_copy_to_user);
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-unsigned long _copy_from_user(void *to, const void __user *from, unsigned n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		n = __copy_from_user(to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-EXPORT_SYMBOL(_copy_from_user);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 1f65ff6540f0..bd057a4ffe6e 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -5,12 +5,7 @@
  * Copyright 1997 Andi Kleen <ak@muc.de>
  * Copyright 1997 Linus Torvalds
  */
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/blkdev.h>
 #include <linux/export.h>
-#include <linux/backing-dev.h>
-#include <linux/interrupt.h>
 #include <linux/uaccess.h>
 #include <asm/mmx.h>
 #include <asm/asm.h>
@@ -201,197 +196,6 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
 	return size;
 }
 
-static unsigned long
-__copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size)
-{
-	int d0, d1;
-	__asm__ __volatile__(
-		       "        .align 2,0x90\n"
-		       "0:      movl 32(%4), %%eax\n"
-		       "        cmpl $67, %0\n"
-		       "        jbe 2f\n"
-		       "1:      movl 64(%4), %%eax\n"
-		       "        .align 2,0x90\n"
-		       "2:      movl 0(%4), %%eax\n"
-		       "21:     movl 4(%4), %%edx\n"
-		       "        movl %%eax, 0(%3)\n"
-		       "        movl %%edx, 4(%3)\n"
-		       "3:      movl 8(%4), %%eax\n"
-		       "31:     movl 12(%4),%%edx\n"
-		       "        movl %%eax, 8(%3)\n"
-		       "        movl %%edx, 12(%3)\n"
-		       "4:      movl 16(%4), %%eax\n"
-		       "41:     movl 20(%4), %%edx\n"
-		       "        movl %%eax, 16(%3)\n"
-		       "        movl %%edx, 20(%3)\n"
-		       "10:     movl 24(%4), %%eax\n"
-		       "51:     movl 28(%4), %%edx\n"
-		       "        movl %%eax, 24(%3)\n"
-		       "        movl %%edx, 28(%3)\n"
-		       "11:     movl 32(%4), %%eax\n"
-		       "61:     movl 36(%4), %%edx\n"
-		       "        movl %%eax, 32(%3)\n"
-		       "        movl %%edx, 36(%3)\n"
-		       "12:     movl 40(%4), %%eax\n"
-		       "71:     movl 44(%4), %%edx\n"
-		       "        movl %%eax, 40(%3)\n"
-		       "        movl %%edx, 44(%3)\n"
-		       "13:     movl 48(%4), %%eax\n"
-		       "81:     movl 52(%4), %%edx\n"
-		       "        movl %%eax, 48(%3)\n"
-		       "        movl %%edx, 52(%3)\n"
-		       "14:     movl 56(%4), %%eax\n"
-		       "91:     movl 60(%4), %%edx\n"
-		       "        movl %%eax, 56(%3)\n"
-		       "        movl %%edx, 60(%3)\n"
-		       "        addl $-64, %0\n"
-		       "        addl $64, %4\n"
-		       "        addl $64, %3\n"
-		       "        cmpl $63, %0\n"
-		       "        ja  0b\n"
-		       "5:      movl  %0, %%eax\n"
-		       "        shrl  $2, %0\n"
-		       "        andl $3, %%eax\n"
-		       "        cld\n"
-		       "6:      rep; movsl\n"
-		       "        movl %%eax,%0\n"
-		       "7:      rep; movsb\n"
-		       "8:\n"
-		       ".section .fixup,\"ax\"\n"
-		       "9:      lea 0(%%eax,%0,4),%0\n"
-		       "16:     pushl %0\n"
-		       "        pushl %%eax\n"
-		       "        xorl %%eax,%%eax\n"
-		       "        rep; stosb\n"
-		       "        popl %%eax\n"
-		       "        popl %0\n"
-		       "        jmp 8b\n"
-		       ".previous\n"
-		       _ASM_EXTABLE(0b,16b)
-		       _ASM_EXTABLE(1b,16b)
-		       _ASM_EXTABLE(2b,16b)
-		       _ASM_EXTABLE(21b,16b)
-		       _ASM_EXTABLE(3b,16b)
-		       _ASM_EXTABLE(31b,16b)
-		       _ASM_EXTABLE(4b,16b)
-		       _ASM_EXTABLE(41b,16b)
-		       _ASM_EXTABLE(10b,16b)
-		       _ASM_EXTABLE(51b,16b)
-		       _ASM_EXTABLE(11b,16b)
-		       _ASM_EXTABLE(61b,16b)
-		       _ASM_EXTABLE(12b,16b)
-		       _ASM_EXTABLE(71b,16b)
-		       _ASM_EXTABLE(13b,16b)
-		       _ASM_EXTABLE(81b,16b)
-		       _ASM_EXTABLE(14b,16b)
-		       _ASM_EXTABLE(91b,16b)
-		       _ASM_EXTABLE(6b,9b)
-		       _ASM_EXTABLE(7b,16b)
-		       : "=&c"(size), "=&D" (d0), "=&S" (d1)
-		       :  "1"(to), "2"(from), "0"(size)
-		       : "eax", "edx", "memory");
-	return size;
-}
-
-/*
- * Non Temporal Hint version of __copy_user_zeroing_intel.  It is cache aware.
- * hyoshiok@miraclelinux.com
- */
-
-static unsigned long __copy_user_zeroing_intel_nocache(void *to,
-				const void __user *from, unsigned long size)
-{
-	int d0, d1;
-
-	__asm__ __volatile__(
-	       "        .align 2,0x90\n"
-	       "0:      movl 32(%4), %%eax\n"
-	       "        cmpl $67, %0\n"
-	       "        jbe 2f\n"
-	       "1:      movl 64(%4), %%eax\n"
-	       "        .align 2,0x90\n"
-	       "2:      movl 0(%4), %%eax\n"
-	       "21:     movl 4(%4), %%edx\n"
-	       "        movnti %%eax, 0(%3)\n"
-	       "        movnti %%edx, 4(%3)\n"
-	       "3:      movl 8(%4), %%eax\n"
-	       "31:     movl 12(%4),%%edx\n"
-	       "        movnti %%eax, 8(%3)\n"
-	       "        movnti %%edx, 12(%3)\n"
-	       "4:      movl 16(%4), %%eax\n"
-	       "41:     movl 20(%4), %%edx\n"
-	       "        movnti %%eax, 16(%3)\n"
-	       "        movnti %%edx, 20(%3)\n"
-	       "10:     movl 24(%4), %%eax\n"
-	       "51:     movl 28(%4), %%edx\n"
-	       "        movnti %%eax, 24(%3)\n"
-	       "        movnti %%edx, 28(%3)\n"
-	       "11:     movl 32(%4), %%eax\n"
-	       "61:     movl 36(%4), %%edx\n"
-	       "        movnti %%eax, 32(%3)\n"
-	       "        movnti %%edx, 36(%3)\n"
-	       "12:     movl 40(%4), %%eax\n"
-	       "71:     movl 44(%4), %%edx\n"
-	       "        movnti %%eax, 40(%3)\n"
-	       "        movnti %%edx, 44(%3)\n"
-	       "13:     movl 48(%4), %%eax\n"
-	       "81:     movl 52(%4), %%edx\n"
-	       "        movnti %%eax, 48(%3)\n"
-	       "        movnti %%edx, 52(%3)\n"
-	       "14:     movl 56(%4), %%eax\n"
-	       "91:     movl 60(%4), %%edx\n"
-	       "        movnti %%eax, 56(%3)\n"
-	       "        movnti %%edx, 60(%3)\n"
-	       "        addl $-64, %0\n"
-	       "        addl $64, %4\n"
-	       "        addl $64, %3\n"
-	       "        cmpl $63, %0\n"
-	       "        ja  0b\n"
-	       "        sfence \n"
-	       "5:      movl  %0, %%eax\n"
-	       "        shrl  $2, %0\n"
-	       "        andl $3, %%eax\n"
-	       "        cld\n"
-	       "6:      rep; movsl\n"
-	       "        movl %%eax,%0\n"
-	       "7:      rep; movsb\n"
-	       "8:\n"
-	       ".section .fixup,\"ax\"\n"
-	       "9:      lea 0(%%eax,%0,4),%0\n"
-	       "16:     pushl %0\n"
-	       "        pushl %%eax\n"
-	       "        xorl %%eax,%%eax\n"
-	       "        rep; stosb\n"
-	       "        popl %%eax\n"
-	       "        popl %0\n"
-	       "        jmp 8b\n"
-	       ".previous\n"
-	       _ASM_EXTABLE(0b,16b)
-	       _ASM_EXTABLE(1b,16b)
-	       _ASM_EXTABLE(2b,16b)
-	       _ASM_EXTABLE(21b,16b)
-	       _ASM_EXTABLE(3b,16b)
-	       _ASM_EXTABLE(31b,16b)
-	       _ASM_EXTABLE(4b,16b)
-	       _ASM_EXTABLE(41b,16b)
-	       _ASM_EXTABLE(10b,16b)
-	       _ASM_EXTABLE(51b,16b)
-	       _ASM_EXTABLE(11b,16b)
-	       _ASM_EXTABLE(61b,16b)
-	       _ASM_EXTABLE(12b,16b)
-	       _ASM_EXTABLE(71b,16b)
-	       _ASM_EXTABLE(13b,16b)
-	       _ASM_EXTABLE(81b,16b)
-	       _ASM_EXTABLE(14b,16b)
-	       _ASM_EXTABLE(91b,16b)
-	       _ASM_EXTABLE(6b,9b)
-	       _ASM_EXTABLE(7b,16b)
-	       : "=&c"(size), "=&D" (d0), "=&S" (d1)
-	       :  "1"(to), "2"(from), "0"(size)
-	       : "eax", "edx", "memory");
-	return size;
-}
-
 static unsigned long __copy_user_intel_nocache(void *to,
 				const void __user *from, unsigned long size)
 {
@@ -486,12 +290,8 @@ static unsigned long __copy_user_intel_nocache(void *to,
  * Leave these declared but undefined.  They should not be any references to
  * them
  */
-unsigned long __copy_user_zeroing_intel(void *to, const void __user *from,
-					unsigned long size);
 unsigned long __copy_user_intel(void __user *to, const void *from,
 					unsigned long size);
-unsigned long __copy_user_zeroing_intel_nocache(void *to,
-				const void __user *from, unsigned long size);
 #endif /* CONFIG_X86_INTEL_USERCOPY */
 
 /* Generic arbitrary sized copy.  */
@@ -528,47 +328,7 @@ do {									\
 		: "memory");						\
 } while (0)
 
-#define __copy_user_zeroing(to, from, size)				\
-do {									\
-	int __d0, __d1, __d2;						\
-	__asm__ __volatile__(						\
-		"	cmp  $7,%0\n"					\
-		"	jbe  1f\n"					\
-		"	movl %1,%0\n"					\
-		"	negl %0\n"					\
-		"	andl $7,%0\n"					\
-		"	subl %0,%3\n"					\
-		"4:	rep; movsb\n"					\
-		"	movl %3,%0\n"					\
-		"	shrl $2,%0\n"					\
-		"	andl $3,%3\n"					\
-		"	.align 2,0x90\n"				\
-		"0:	rep; movsl\n"					\
-		"	movl %3,%0\n"					\
-		"1:	rep; movsb\n"					\
-		"2:\n"							\
-		".section .fixup,\"ax\"\n"				\
-		"5:	addl %3,%0\n"					\
-		"	jmp 6f\n"					\
-		"3:	lea 0(%3,%0,4),%0\n"				\
-		"6:	pushl %0\n"					\
-		"	pushl %%eax\n"					\
-		"	xorl %%eax,%%eax\n"				\
-		"	rep; stosb\n"					\
-		"	popl %%eax\n"					\
-		"	popl %0\n"					\
-		"	jmp 2b\n"					\
-		".previous\n"						\
-		_ASM_EXTABLE(4b,5b)					\
-		_ASM_EXTABLE(0b,3b)					\
-		_ASM_EXTABLE(1b,6b)					\
-		: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2)	\
-		: "3"(size), "0"(size), "1"(to), "2"(from)		\
-		: "memory");						\
-} while (0)
-
-unsigned long __copy_to_user_ll(void __user *to, const void *from,
-				unsigned long n)
+unsigned long __copy_user_ll(void *to, const void *from, unsigned long n)
 {
 	stac();
 	if (movsl_is_ok(to, from, n))
@@ -578,51 +338,7 @@ unsigned long __copy_to_user_ll(void __user *to, const void *from,
 	clac();
 	return n;
 }
-EXPORT_SYMBOL(__copy_to_user_ll);
-
-unsigned long __copy_from_user_ll(void *to, const void __user *from,
-					unsigned long n)
-{
-	stac();
-	if (movsl_is_ok(to, from, n))
-		__copy_user_zeroing(to, from, n);
-	else
-		n = __copy_user_zeroing_intel(to, from, n);
-	clac();
-	return n;
-}
-EXPORT_SYMBOL(__copy_from_user_ll);
-
-unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
-					 unsigned long n)
-{
-	stac();
-	if (movsl_is_ok(to, from, n))
-		__copy_user(to, from, n);
-	else
-		n = __copy_user_intel((void __user *)to,
-				      (const void *)from, n);
-	clac();
-	return n;
-}
-EXPORT_SYMBOL(__copy_from_user_ll_nozero);
-
-unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
-					unsigned long n)
-{
-	stac();
-#ifdef CONFIG_X86_INTEL_USERCOPY
-	if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
-		n = __copy_user_zeroing_intel_nocache(to, from, n);
-	else
-		__copy_user_zeroing(to, from, n);
-#else
-	__copy_user_zeroing(to, from, n);
-#endif
-	clac();
-	return n;
-}
-EXPORT_SYMBOL(__copy_from_user_ll_nocache);
+EXPORT_SYMBOL(__copy_user_ll);
 
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 69873589c0ba..3b7c40a2e3e1 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -54,15 +54,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 }
 EXPORT_SYMBOL(clear_user);
 
-unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len)
-{
-	if (access_ok(VERIFY_WRITE, to, len) && access_ok(VERIFY_READ, from, len)) { 
-		return copy_user_generic((__force void *)to, (__force void *)from, len);
-	} 
-	return len;		
-}
-EXPORT_SYMBOL(copy_in_user);
-
 /*
  * Try to copy last bytes and clear the rest if needed.
  * Since protection fault in copy_from/to_user is not a normal situation,
@@ -80,9 +71,5 @@ copy_user_handle_tail(char *to, char *from, unsigned len)
 			break;
 	}
 	clac();
-
-	/* If the destination is a kernel buffer, we always clear the end */
-	if (!__addr_ok(to))
-		memset(to, 0, len);
 	return len;
 }
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index d1c7de095808..91f501b2da3b 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -19,7 +19,7 @@
 #include <asm/types.h>
 #include <asm/mmzone.h>
 #include <asm/proto.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/pci-direct.h>
 #include <asm/numa.h>
 #include <asm/mpspec.h>
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 58b5bee7ea27..bce6990b1d81 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -110,7 +110,8 @@ static struct addr_marker address_markers[] = {
 #define PTE_LEVEL_MULT (PAGE_SIZE)
 #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
 #define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT)
-#define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
+#define P4D_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
+#define PGD_LEVEL_MULT (PTRS_PER_P4D * P4D_LEVEL_MULT)
 
 #define pt_dump_seq_printf(m, to_dmesg, fmt, args...)		\
 ({								\
@@ -286,14 +287,13 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 	}
 }
 
-static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
-							unsigned long P)
+static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, unsigned long P)
 {
 	int i;
 	pte_t *start;
 	pgprotval_t prot;
 
-	start = (pte_t *) pmd_page_vaddr(addr);
+	start = (pte_t *)pmd_page_vaddr(addr);
 	for (i = 0; i < PTRS_PER_PTE; i++) {
 		prot = pte_flags(*start);
 		st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
@@ -304,14 +304,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
 
 #if PTRS_PER_PMD > 1
 
-static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
-							unsigned long P)
+static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P)
 {
 	int i;
 	pmd_t *start;
 	pgprotval_t prot;
 
-	start = (pmd_t *) pud_page_vaddr(addr);
+	start = (pmd_t *)pud_page_vaddr(addr);
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
 		if (!pmd_none(*start)) {
@@ -347,15 +346,14 @@ static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx)
 	return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud));
 }
 
-static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
-							unsigned long P)
+static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P)
 {
 	int i;
 	pud_t *start;
 	pgprotval_t prot;
 	pud_t *prev_pud = NULL;
 
-	start = (pud_t *) pgd_page_vaddr(addr);
+	start = (pud_t *)p4d_page_vaddr(addr);
 
 	for (i = 0; i < PTRS_PER_PUD; i++) {
 		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
@@ -377,9 +375,42 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 }
 
 #else
-#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(pgd_val(a)),p)
-#define pgd_large(a) pud_large(__pud(pgd_val(a)))
-#define pgd_none(a)  pud_none(__pud(pgd_val(a)))
+#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(p4d_val(a)),p)
+#define p4d_large(a) pud_large(__pud(p4d_val(a)))
+#define p4d_none(a)  pud_none(__pud(p4d_val(a)))
+#endif
+
+#if PTRS_PER_P4D > 1
+
+static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P)
+{
+	int i;
+	p4d_t *start;
+	pgprotval_t prot;
+
+	start = (p4d_t *)pgd_page_vaddr(addr);
+
+	for (i = 0; i < PTRS_PER_P4D; i++) {
+		st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT);
+		if (!p4d_none(*start)) {
+			if (p4d_large(*start) || !p4d_present(*start)) {
+				prot = p4d_flags(*start);
+				note_page(m, st, __pgprot(prot), 2);
+			} else {
+				walk_pud_level(m, st, *start,
+					       P + i * P4D_LEVEL_MULT);
+			}
+		} else
+			note_page(m, st, __pgprot(0), 2);
+
+		start++;
+	}
+}
+
+#else
+#define walk_p4d_level(m,s,a,p) walk_pud_level(m,s,__p4d(pgd_val(a)),p)
+#define pgd_large(a) p4d_large(__p4d(pgd_val(a)))
+#define pgd_none(a)  p4d_none(__p4d(pgd_val(a)))
 #endif
 
 static inline bool is_hypervisor_range(int idx)
@@ -424,7 +455,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				prot = pgd_flags(*start);
 				note_page(m, &st, __pgprot(prot), 1);
 			} else {
-				walk_pud_level(m, &st, *start,
+				walk_p4d_level(m, &st, *start,
 					       i * PGD_LEVEL_MULT);
 			}
 		} else
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 428e31763cb9..8ad91a01cbc8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -253,6 +253,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 {
 	unsigned index = pgd_index(address);
 	pgd_t *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
@@ -265,10 +266,15 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	/*
 	 * set_pgd(pgd, *pgd_k); here would be useless on PAE
 	 * and redundant with the set_pmd() on non-PAE. As would
-	 * set_pud.
+	 * set_p4d/set_pud.
 	 */
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (!p4d_present(*p4d_k))
+		return NULL;
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
 	if (!pud_present(*pud_k))
 		return NULL;
 
@@ -384,6 +390,8 @@ static void dump_pagetable(unsigned long address)
 {
 	pgd_t *base = __va(read_cr3());
 	pgd_t *pgd = &base[pgd_index(address)];
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
@@ -392,7 +400,9 @@ static void dump_pagetable(unsigned long address)
 	if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd))
 		goto out;
 #endif
-	pmd = pmd_offset(pud_offset(pgd, address), address);
+	p4d = p4d_offset(pgd, address);
+	pud = pud_offset(p4d, address);
+	pmd = pmd_offset(pud, address);
 	printk(KERN_CONT "*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd));
 
 	/*
@@ -425,6 +435,7 @@ void vmalloc_sync_all(void)
 static noinline int vmalloc_fault(unsigned long address)
 {
 	pgd_t *pgd, *pgd_ref;
+	p4d_t *p4d, *p4d_ref;
 	pud_t *pud, *pud_ref;
 	pmd_t *pmd, *pmd_ref;
 	pte_t *pte, *pte_ref;
@@ -448,17 +459,37 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd)) {
 		set_pgd(pgd, *pgd_ref);
 		arch_flush_lazy_mmu_mode();
-	} else {
+	} else if (CONFIG_PGTABLE_LEVELS > 4) {
+		/*
+		 * With folded p4d, pgd_none() is always false, so the pgd may
+		 * point to an empty page table entry and pgd_page_vaddr()
+		 * will return garbage.
+		 *
+		 * We will do the correct sanity check on the p4d level.
+		 */
 		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
 	}
 
+	/* With 4-level paging, copying happens on the p4d level. */
+	p4d = p4d_offset(pgd, address);
+	p4d_ref = p4d_offset(pgd_ref, address);
+	if (p4d_none(*p4d_ref))
+		return -1;
+
+	if (p4d_none(*p4d)) {
+		set_p4d(p4d, *p4d_ref);
+		arch_flush_lazy_mmu_mode();
+	} else {
+		BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_ref));
+	}
+
 	/*
 	 * Below here mismatches are bugs because these lower tables
 	 * are shared:
 	 */
 
-	pud = pud_offset(pgd, address);
-	pud_ref = pud_offset(pgd_ref, address);
+	pud = pud_offset(p4d, address);
+	pud_ref = pud_offset(p4d_ref, address);
 	if (pud_none(*pud_ref))
 		return -1;
 
@@ -526,6 +557,7 @@ static void dump_pagetable(unsigned long address)
 {
 	pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK);
 	pgd_t *pgd = base + pgd_index(address);
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -538,7 +570,15 @@ static void dump_pagetable(unsigned long address)
 	if (!pgd_present(*pgd))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (bad_address(p4d))
+		goto bad;
+
+	printk("P4D %lx ", p4d_val(*p4d));
+	if (!p4d_present(*p4d) || p4d_large(*p4d))
+		goto out;
+
+	pud = pud_offset(p4d, address);
 	if (bad_address(pud))
 		goto bad;
 
@@ -1082,6 +1122,7 @@ static noinline int
 spurious_fault(unsigned long error_code, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -1104,7 +1145,14 @@ spurious_fault(unsigned long error_code, unsigned long address)
 	if (!pgd_present(*pgd))
 		return 0;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		return 0;
+
+	if (p4d_large(*p4d))
+		return spurious_fault_check(error_code, (pte_t *) p4d);
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		return 0;
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 99c7805a9693..456dfdfd2249 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -76,9 +76,9 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
 }
 
 /*
- * 'pteval' can come from a pte, pmd or pud.  We only check
+ * 'pteval' can come from a pte, pmd, pud or p4d.  We only check
  * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the
- * same value on all 3 types.
+ * same value on all 4 types.
  */
 static inline int pte_allows_gup(unsigned long pteval, int write)
 {
@@ -106,32 +106,35 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	struct dev_pagemap *pgmap = NULL;
-	int nr_start = *nr;
-	pte_t *ptep;
+	int nr_start = *nr, ret = 0;
+	pte_t *ptep, *ptem;
 
-	ptep = pte_offset_map(&pmd, addr);
+	/*
+	 * Keep the original mapped PTE value (ptem) around since we
+	 * might increment ptep off the end of the page when finishing
+	 * our loop iteration.
+	 */
+	ptem = ptep = pte_offset_map(&pmd, addr);
 	do {
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
 		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_protnone(pte)) {
-			pte_unmap(ptep);
-			return 0;
-		}
+		if (pte_protnone(pte))
+			break;
+
+		if (!pte_allows_gup(pte_val(pte), write))
+			break;
 
 		if (pte_devmap(pte)) {
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
 				undo_dev_pagemap(nr, nr_start, pages);
-				pte_unmap(ptep);
-				return 0;
+				break;
 			}
-		} else if (!pte_allows_gup(pte_val(pte), write) ||
-			   pte_special(pte)) {
-			pte_unmap(ptep);
-			return 0;
-		}
+		} else if (pte_special(pte))
+			break;
+
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 		get_page(page);
@@ -141,9 +144,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		(*nr)++;
 
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(ptep - 1);
+	if (addr == end)
+		ret = 1;
+	pte_unmap(ptem);
 
-	return 1;
+	return ret;
 }
 
 static inline void get_head_page_multiple(struct page *page, int nr)
@@ -290,13 +295,13 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 			int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(&pgd, addr);
+	pudp = pud_offset(&p4d, addr);
 	do {
 		pud_t pud = *pudp;
 
@@ -315,6 +320,27 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	p4d_t *p4dp;
+
+	p4dp = p4d_offset(&pgd, addr);
+	do {
+		p4d_t p4d = *p4dp;
+
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(p4d))
+			return 0;
+		BUILD_BUG_ON(p4d_large(p4d));
+		if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+			return 0;
+	} while (p4dp++, addr = next, addr != end);
+
+	return 1;
+}
+
 /*
  * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
  * back to the regular GUP.
@@ -363,7 +389,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			break;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);
@@ -435,7 +461,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			goto slow;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
 			goto slow;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_enable();
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index c5066a260803..302f43fd9c28 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -12,10 +12,12 @@
 #include <linux/pagemap.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
+#include <linux/compat.h>
 #include <asm/mman.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
+#include <asm/elf.h>
 
 #if 0	/* This is just for testing */
 struct page *
@@ -82,8 +84,9 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = current->mm->mmap_legacy_base;
-	info.high_limit = TASK_SIZE;
+	info.low_limit = get_mmap_base(1);
+	info.high_limit = in_compat_syscall() ?
+		tasksize_32bit() : tasksize_64bit();
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	return vm_unmapped_area(&info);
@@ -100,7 +103,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
-	info.high_limit = current->mm->mmap_base;
+	info.high_limit = get_mmap_base(0);
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 4473cb4f8b90..04210a29dd60 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -45,6 +45,34 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	return 0;
 }
 
+static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		p4d_t *p4d = p4d_page + p4d_index(addr);
+		pud_t *pud;
+
+		next = (addr & P4D_MASK) + P4D_SIZE;
+		if (next > end)
+			next = end;
+
+		if (p4d_present(*p4d)) {
+			pud = pud_offset(p4d, 0);
+			ident_pud_init(info, pud, addr, next);
+			continue;
+		}
+		pud = (pud_t *)info->alloc_pgt_page(info->context);
+		if (!pud)
+			return -ENOMEM;
+		ident_pud_init(info, pud, addr, next);
+		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 			      unsigned long pstart, unsigned long pend)
 {
@@ -55,27 +83,36 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 
 	for (; addr < end; addr = next) {
 		pgd_t *pgd = pgd_page + pgd_index(addr);
-		pud_t *pud;
+		p4d_t *p4d;
 
 		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
 		if (next > end)
 			next = end;
 
 		if (pgd_present(*pgd)) {
-			pud = pud_offset(pgd, 0);
-			result = ident_pud_init(info, pud, addr, next);
+			p4d = p4d_offset(pgd, 0);
+			result = ident_p4d_init(info, p4d, addr, next);
 			if (result)
 				return result;
 			continue;
 		}
 
-		pud = (pud_t *)info->alloc_pgt_page(info->context);
-		if (!pud)
+		p4d = (p4d_t *)info->alloc_pgt_page(info->context);
+		if (!p4d)
 			return -ENOMEM;
-		result = ident_pud_init(info, pud, addr, next);
+		result = ident_p4d_init(info, p4d, addr, next);
 		if (result)
 			return result;
-		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+		if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+			set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+		} else {
+			/*
+			 * With p4d folded, pgd is equal to p4d.
+			 * The pgd entry has to point to the pud page table in this case.
+			 */
+			pud_t *pud = pud_offset(p4d, 0);
+			set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+		}
 	}
 
 	return 0;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 22af912d66d2..138bad2fb6bc 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -6,7 +6,7 @@
 #include <linux/bootmem.h>	/* for max_low_pfn */
 
 #include <asm/cacheflush.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/init.h>
 #include <asm/page.h>
 #include <asm/page_types.h>
@@ -373,14 +373,14 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 	return nr_range;
 }
 
-struct range pfn_mapped[E820_X_MAX];
+struct range pfn_mapped[E820_MAX_ENTRIES];
 int nr_pfn_mapped;
 
 static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
 {
-	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX,
+	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES,
 					     nr_pfn_mapped, start_pfn, end_pfn);
-	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX);
+	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES);
 
 	max_pfn_mapped = max(max_pfn_mapped, end_pfn);
 
@@ -430,7 +430,7 @@ unsigned long __ref init_memory_mapping(unsigned long start,
 
 /*
  * We need to iterate through the E820 memory map and create direct mappings
- * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply
  * create direct mappings for all pfns from [0 to max_low_pfn) and
  * [4GB to max_pfn) because of possible memory holes in high addresses
  * that cannot be marked as UC by fixed/variable range MTRRs.
@@ -643,21 +643,40 @@ void __init init_mem_mapping(void)
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.
  *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
  */
 int devmem_is_allowed(unsigned long pagenr)
 {
-	if (pagenr < 256)
-		return 1;
-	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+	if (page_is_ram(pagenr)) {
+		/*
+		 * For disallowed memory regions in the low 1MB range,
+		 * request that the page be shown as all zeros.
+		 */
+		if (pagenr < 256)
+			return 2;
+
 		return 0;
-	if (!page_is_ram(pagenr))
-		return 1;
-	return 0;
+	}
+
+	/*
+	 * This must follow RAM test, since System RAM is considered a
+	 * restricted resource under CONFIG_STRICT_IOMEM.
+	 */
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+		/* Low 1MB bypasses iomem restrictions. */
+		if (pagenr < 256)
+			return 1;
+
+		return 0;
+	}
+
+	return 1;
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
@@ -701,7 +720,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 
 void __ref free_initmem(void)
 {
-	e820_reallocate_tables();
+	e820__reallocate_tables();
 
 	free_init_pages("unused kernel",
 			(unsigned long)(&__init_begin),
@@ -724,6 +743,53 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
+/*
+ * Calculate the precise size of the DMA zone (first 16 MB of RAM),
+ * and pass it to the MM layer - to help it set zone watermarks more
+ * accurately.
+ *
+ * Done on 64-bit systems only for the time being, although 32-bit systems
+ * might benefit from this as well.
+ */
+void __init memblock_find_dma_reserve(void)
+{
+#ifdef CONFIG_X86_64
+	u64 nr_pages = 0, nr_free_pages = 0;
+	unsigned long start_pfn, end_pfn;
+	phys_addr_t start_addr, end_addr;
+	int i;
+	u64 u;
+
+	/*
+	 * Iterate over all memory ranges (free and reserved ones alike),
+	 * to calculate the total number of pages in the first 16 MB of RAM:
+	 */
+	nr_pages = 0;
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+		start_pfn = min(start_pfn, MAX_DMA_PFN);
+		end_pfn   = min(end_pfn,   MAX_DMA_PFN);
+
+		nr_pages += end_pfn - start_pfn;
+	}
+
+	/*
+	 * Iterate over free memory ranges to calculate the number of free
+	 * pages in the DMA zone, while not counting potential partial
+	 * pages at the beginning or the end of the range:
+	 */
+	nr_free_pages = 0;
+	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
+		start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
+		end_pfn   = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
+
+		if (start_pfn < end_pfn)
+			nr_free_pages += end_pfn - start_pfn;
+	}
+
+	set_dma_reserve(nr_pages - nr_free_pages);
+#endif
+}
+
 void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2b4b53e6793f..f34d275ee201 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -38,7 +38,7 @@
 #include <asm/pgtable.h>
 #include <asm/dma.h>
 #include <asm/fixmap.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/apic.h>
 #include <asm/bugs.h>
 #include <asm/tlb.h>
@@ -56,8 +56,6 @@
 
 unsigned long highstart_pfn, highend_pfn;
 
-static noinline int do_test_wp_bit(void);
-
 bool __read_mostly __vmalloc_start_set = false;
 
 /*
@@ -67,6 +65,7 @@ bool __read_mostly __vmalloc_start_set = false;
  */
 static pmd_t * __init one_md_table_init(pgd_t *pgd)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd_table;
 
@@ -75,13 +74,15 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 		pmd_table = (pmd_t *)alloc_low_page();
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
-		pud = pud_offset(pgd, 0);
+		p4d = p4d_offset(pgd, 0);
+		pud = pud_offset(p4d, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
 
 		return pmd_table;
 	}
 #endif
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
 	pmd_table = pmd_offset(pud, 0);
 
 	return pmd_table;
@@ -390,8 +391,11 @@ pte_t *kmap_pte;
 
 static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
 {
-	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
-			vaddr), vaddr), vaddr);
+	pgd_t *pgd = pgd_offset_k(vaddr);
+	p4d_t *p4d = p4d_offset(pgd, vaddr);
+	pud_t *pud = pud_offset(p4d, vaddr);
+	pmd_t *pmd = pmd_offset(pud, vaddr);
+	return pte_offset_kernel(pmd, vaddr);
 }
 
 static void __init kmap_init(void)
@@ -410,6 +414,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
 	unsigned long vaddr;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -418,7 +423,8 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 	page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);
 
 	pgd = swapper_pg_dir + pgd_index(vaddr);
-	pud = pud_offset(pgd, vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	pmd = pmd_offset(pud, vaddr);
 	pte = pte_offset_kernel(pmd, vaddr);
 	pkmap_page_table = pte;
@@ -450,6 +456,7 @@ void __init native_pagetable_init(void)
 {
 	unsigned long pfn, va;
 	pgd_t *pgd, *base = swapper_pg_dir;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -469,7 +476,8 @@ void __init native_pagetable_init(void)
 		if (!pgd_present(*pgd))
 			break;
 
-		pud = pud_offset(pgd, va);
+		p4d = p4d_offset(pgd, va);
+		pud = pud_offset(p4d, va);
 		pmd = pmd_offset(pud, va);
 		if (!pmd_present(*pmd))
 			break;
@@ -716,20 +724,20 @@ void __init paging_init(void)
  */
 static void __init test_wp_bit(void)
 {
-	printk(KERN_INFO
-  "Checking if this processor honours the WP bit even in supervisor mode...");
+	char z = 0;
+
+	printk(KERN_INFO "Checking if this processor honours the WP bit even in supervisor mode...");
 
-	/* Any page-aligned address will do, the test is non-destructive */
-	__set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_KERNEL_RO);
-	boot_cpu_data.wp_works_ok = do_test_wp_bit();
-	clear_fixmap(FIX_WP_TEST);
+	__set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO);
 
-	if (!boot_cpu_data.wp_works_ok) {
-		printk(KERN_CONT "No.\n");
-		panic("Linux doesn't support CPUs with broken WP.");
-	} else {
+	if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
+		clear_fixmap(FIX_WP_TEST);
 		printk(KERN_CONT "Ok.\n");
+		return;
 	}
+
+	printk(KERN_CONT "No.\n");
+	panic("Linux doesn't support CPUs with broken WP.");
 }
 
 void __init mem_init(void)
@@ -811,8 +819,7 @@ void __init mem_init(void)
 	BUG_ON(VMALLOC_START				>= VMALLOC_END);
 	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
 
-	if (boot_cpu_data.wp_works_ok < 0)
-		test_wp_bit();
+	test_wp_bit();
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -840,30 +847,6 @@ int arch_remove_memory(u64 start, u64 size)
 #endif
 #endif
 
-/*
- * This function cannot be __init, since exceptions don't work in that
- * section.  Put this after the callers, so that it cannot be inlined.
- */
-static noinline int do_test_wp_bit(void)
-{
-	char tmp_reg;
-	int flag;
-
-	__asm__ __volatile__(
-		"	movb %0, %1	\n"
-		"1:	movb %1, %0	\n"
-		"	xorl %2, %2	\n"
-		"2:			\n"
-		_ASM_EXTABLE(1b,2b)
-		:"=m" (*(char *)fix_to_virt(FIX_WP_TEST)),
-		 "=q" (tmp_reg),
-		 "=r" (flag)
-		:"2" (1)
-		:"memory");
-
-	return flag;
-}
-
 int kernel_set_to_readonly __read_mostly;
 
 void set_kernel_text_rw(void)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 15173d37f399..745e5e183169 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -41,7 +41,7 @@
 #include <asm/pgalloc.h>
 #include <asm/dma.h>
 #include <asm/fixmap.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/apic.h>
 #include <asm/tlb.h>
 #include <asm/mmu_context.h>
@@ -97,28 +97,38 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 	unsigned long address;
 
 	for (address = start; address <= end; address += PGDIR_SIZE) {
-		const pgd_t *pgd_ref = pgd_offset_k(address);
+		pgd_t *pgd_ref = pgd_offset_k(address);
+		const p4d_t *p4d_ref;
 		struct page *page;
 
-		if (pgd_none(*pgd_ref))
+		/*
+		 * With folded p4d, pgd_none() is always false, we need to
+		 * handle synchonization on p4d level.
+		 */
+		BUILD_BUG_ON(pgd_none(*pgd_ref));
+		p4d_ref = p4d_offset(pgd_ref, address);
+
+		if (p4d_none(*p4d_ref))
 			continue;
 
 		spin_lock(&pgd_lock);
 		list_for_each_entry(page, &pgd_list, lru) {
 			pgd_t *pgd;
+			p4d_t *p4d;
 			spinlock_t *pgt_lock;
 
 			pgd = (pgd_t *)page_address(page) + pgd_index(address);
+			p4d = p4d_offset(pgd, address);
 			/* the pgt_lock only for Xen */
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 			spin_lock(pgt_lock);
 
-			if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
-				BUG_ON(pgd_page_vaddr(*pgd)
-				       != pgd_page_vaddr(*pgd_ref));
+			if (!p4d_none(*p4d_ref) && !p4d_none(*p4d))
+				BUG_ON(p4d_page_vaddr(*p4d)
+				       != p4d_page_vaddr(*p4d_ref));
 
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
+			if (p4d_none(*p4d))
+				set_p4d(p4d, *p4d_ref);
 
 			spin_unlock(pgt_lock);
 		}
@@ -149,16 +159,28 @@ static __ref void *spp_getpage(void)
 	return ptr;
 }
 
-static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr)
+static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr)
 {
 	if (pgd_none(*pgd)) {
-		pud_t *pud = (pud_t *)spp_getpage();
-		pgd_populate(&init_mm, pgd, pud);
-		if (pud != pud_offset(pgd, 0))
+		p4d_t *p4d = (p4d_t *)spp_getpage();
+		pgd_populate(&init_mm, pgd, p4d);
+		if (p4d != p4d_offset(pgd, 0))
 			printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
-			       pud, pud_offset(pgd, 0));
+			       p4d, p4d_offset(pgd, 0));
+	}
+	return p4d_offset(pgd, vaddr);
+}
+
+static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr)
+{
+	if (p4d_none(*p4d)) {
+		pud_t *pud = (pud_t *)spp_getpage();
+		p4d_populate(&init_mm, p4d, pud);
+		if (pud != pud_offset(p4d, 0))
+			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
+			       pud, pud_offset(p4d, 0));
 	}
-	return pud_offset(pgd, vaddr);
+	return pud_offset(p4d, vaddr);
 }
 
 static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
@@ -167,7 +189,7 @@ static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
 		pmd_t *pmd = (pmd_t *) spp_getpage();
 		pud_populate(&init_mm, pud, pmd);
 		if (pmd != pmd_offset(pud, 0))
-			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
+			printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n",
 			       pmd, pmd_offset(pud, 0));
 	}
 	return pmd_offset(pud, vaddr);
@@ -179,20 +201,15 @@ static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
 		pte_t *pte = (pte_t *) spp_getpage();
 		pmd_populate_kernel(&init_mm, pmd, pte);
 		if (pte != pte_offset_kernel(pmd, 0))
-			printk(KERN_ERR "PAGETABLE BUG #02!\n");
+			printk(KERN_ERR "PAGETABLE BUG #03!\n");
 	}
 	return pte_offset_kernel(pmd, vaddr);
 }
 
-void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
+static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte)
 {
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	pud = pud_page + pud_index(vaddr);
-	pmd = fill_pmd(pud, vaddr);
-	pte = fill_pte(pmd, vaddr);
+	pmd_t *pmd = fill_pmd(pud, vaddr);
+	pte_t *pte = fill_pte(pmd, vaddr);
 
 	set_pte(pte, new_pte);
 
@@ -203,10 +220,25 @@ void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 	__flush_tlb_one(vaddr);
 }
 
+void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte)
+{
+	p4d_t *p4d = p4d_page + p4d_index(vaddr);
+	pud_t *pud = fill_pud(p4d, vaddr);
+
+	__set_pte_vaddr(pud, vaddr, new_pte);
+}
+
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
+{
+	pud_t *pud = pud_page + pud_index(vaddr);
+
+	__set_pte_vaddr(pud, vaddr, new_pte);
+}
+
 void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 {
 	pgd_t *pgd;
-	pud_t *pud_page;
+	p4d_t *p4d_page;
 
 	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));
 
@@ -216,17 +248,20 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
 		return;
 	}
-	pud_page = (pud_t*)pgd_page_vaddr(*pgd);
-	set_pte_vaddr_pud(pud_page, vaddr, pteval);
+
+	p4d_page = p4d_offset(pgd, 0);
+	set_pte_vaddr_p4d(p4d_page, vaddr, pteval);
 }
 
 pmd_t * __init populate_extra_pmd(unsigned long vaddr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 
 	pgd = pgd_offset_k(vaddr);
-	pud = fill_pud(pgd, vaddr);
+	p4d = fill_p4d(pgd, vaddr);
+	pud = fill_pud(p4d, vaddr);
 	return fill_pmd(pud, vaddr);
 }
 
@@ -245,6 +280,7 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
 					enum page_cache_mode cache)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pgprot_t prot;
@@ -255,11 +291,17 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
 	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
 		pgd = pgd_offset_k((unsigned long)__va(phys));
 		if (pgd_none(*pgd)) {
+			p4d = (p4d_t *) spp_getpage();
+			set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE |
+						_PAGE_USER));
+		}
+		p4d = p4d_offset(pgd, (unsigned long)__va(phys));
+		if (p4d_none(*p4d)) {
 			pud = (pud_t *) spp_getpage();
-			set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE |
+			set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE |
 						_PAGE_USER));
 		}
-		pud = pud_offset(pgd, (unsigned long)__va(phys));
+		pud = pud_offset(p4d, (unsigned long)__va(phys));
 		if (pud_none(*pud)) {
 			pmd = (pmd_t *) spp_getpage();
 			set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
@@ -337,10 +379,10 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 		paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE;
 		if (paddr >= paddr_end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(paddr & PAGE_MASK, paddr_next,
-					     E820_RAM) &&
-			    !e820_any_mapped(paddr & PAGE_MASK, paddr_next,
-					     E820_RESERVED_KERN))
+			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+					     E820_TYPE_RESERVED_KERN))
 				set_pte(pte, __pte(0));
 			continue;
 		}
@@ -392,10 +434,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 		paddr_next = (paddr & PMD_MASK) + PMD_SIZE;
 		if (paddr >= paddr_end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(paddr & PMD_MASK, paddr_next,
-					     E820_RAM) &&
-			    !e820_any_mapped(paddr & PMD_MASK, paddr_next,
-					     E820_RESERVED_KERN))
+			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+					     E820_TYPE_RESERVED_KERN))
 				set_pmd(pmd, __pmd(0));
 			continue;
 		}
@@ -478,10 +520,10 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 
 		if (paddr >= paddr_end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(paddr & PUD_MASK, paddr_next,
-					     E820_RAM) &&
-			    !e820_any_mapped(paddr & PUD_MASK, paddr_next,
-					     E820_RESERVED_KERN))
+			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+					     E820_TYPE_RESERVED_KERN))
 				set_pud(pud, __pud(0));
 			continue;
 		}
@@ -563,12 +605,15 @@ kernel_physical_mapping_init(unsigned long paddr_start,
 
 	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
 		pgd_t *pgd = pgd_offset_k(vaddr);
+		p4d_t *p4d;
 		pud_t *pud;
 
 		vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE;
 
-		if (pgd_val(*pgd)) {
-			pud = (pud_t *)pgd_page_vaddr(*pgd);
+		BUILD_BUG_ON(pgd_none(*pgd));
+		p4d = p4d_offset(pgd, vaddr);
+		if (p4d_val(*p4d)) {
+			pud = (pud_t *)p4d_page_vaddr(*p4d);
 			paddr_last = phys_pud_init(pud, __pa(vaddr),
 						   __pa(vaddr_end),
 						   page_size_mask);
@@ -580,7 +625,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
 					   page_size_mask);
 
 		spin_lock(&init_mm.page_table_lock);
-		pgd_populate(&init_mm, pgd, pud);
+		p4d_populate(&init_mm, p4d, pud);
 		spin_unlock(&init_mm.page_table_lock);
 		pgd_changed = true;
 	}
@@ -726,6 +771,24 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 	spin_unlock(&init_mm.page_table_lock);
 }
 
+static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
+{
+	pud_t *pud;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		pud = pud_start + i;
+		if (!pud_none(*pud))
+			return;
+	}
+
+	/* free a pud talbe */
+	free_pagetable(p4d_page(*p4d), 0);
+	spin_lock(&init_mm.page_table_lock);
+	p4d_clear(p4d);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
 static void __meminit
 remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 		 bool direct)
@@ -899,7 +962,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		pmd_base = (pmd_t *)pud_page_vaddr(*pud);
+		pmd_base = pmd_offset(pud, 0);
 		remove_pmd_table(pmd_base, addr, next, direct);
 		free_pmd_table(pmd_base, pud);
 	}
@@ -908,6 +971,32 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 		update_page_count(PG_LEVEL_1G, -pages);
 }
 
+static void __meminit
+remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
+		 bool direct)
+{
+	unsigned long next, pages = 0;
+	pud_t *pud_base;
+	p4d_t *p4d;
+
+	p4d = p4d_start + p4d_index(addr);
+	for (; addr < end; addr = next, p4d++) {
+		next = p4d_addr_end(addr, end);
+
+		if (!p4d_present(*p4d))
+			continue;
+
+		BUILD_BUG_ON(p4d_large(*p4d));
+
+		pud_base = pud_offset(p4d, 0);
+		remove_pud_table(pud_base, addr, next, direct);
+		free_pud_table(pud_base, p4d);
+	}
+
+	if (direct)
+		update_page_count(PG_LEVEL_512G, -pages);
+}
+
 /* start and end are both virtual address. */
 static void __meminit
 remove_pagetable(unsigned long start, unsigned long end, bool direct)
@@ -915,7 +1004,7 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 	unsigned long next;
 	unsigned long addr;
 	pgd_t *pgd;
-	pud_t *pud;
+	p4d_t *p4d;
 
 	for (addr = start; addr < end; addr = next) {
 		next = pgd_addr_end(addr, end);
@@ -924,8 +1013,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 		if (!pgd_present(*pgd))
 			continue;
 
-		pud = (pud_t *)pgd_page_vaddr(*pgd);
-		remove_pud_table(pud, addr, next, direct);
+		p4d = p4d_offset(pgd, 0);
+		remove_p4d_table(p4d, addr, next, direct);
 	}
 
 	flush_tlb_all();
@@ -1090,6 +1179,7 @@ int kern_addr_valid(unsigned long addr)
 {
 	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -1101,7 +1191,11 @@ int kern_addr_valid(unsigned long addr)
 	if (pgd_none(*pgd))
 		return 0;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return 0;
+
+	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud))
 		return 0;
 
@@ -1158,6 +1252,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 	unsigned long addr;
 	unsigned long next;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -1168,7 +1263,11 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 		if (!pgd)
 			return -ENOMEM;
 
-		pud = vmemmap_pud_populate(pgd, addr, node);
+		p4d = vmemmap_p4d_populate(pgd, addr, node);
+		if (!p4d)
+			return -ENOMEM;
+
+		pud = vmemmap_pud_populate(p4d, addr, node);
 		if (!pud)
 			return -ENOMEM;
 
@@ -1236,6 +1335,7 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 	unsigned long end = (unsigned long)(start_page + size);
 	unsigned long next;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	unsigned int nr_pages;
@@ -1251,7 +1351,14 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO);
 
-		pud = pud_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (p4d_none(*p4d)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, p4d_page(*p4d), MIX_SECTION_INFO);
+
+		pud = pud_offset(p4d, addr);
 		if (pud_none(*pud)) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
 			continue;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 7aaa2635862d..e4f7b25df18e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -9,12 +9,13 @@
 #include <linux/bootmem.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/ioport.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mmiotrace.h>
 
 #include <asm/cacheflush.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/fixmap.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -425,7 +426,8 @@ static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
 	/* Don't assume we're using swapper_pg_dir at this point */
 	pgd_t *base = __va(read_cr3());
 	pgd_t *pgd = &base[pgd_index(addr)];
-	pud_t *pud = pud_offset(pgd, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	pmd_t *pmd = pmd_offset(pud, addr);
 
 	return pmd;
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 8d63d7a104c3..0c7d8129bed6 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
@@ -7,11 +8,12 @@
 #include <linux/sched/task.h>
 #include <linux/vmalloc.h>
 
+#include <asm/e820/types.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
-extern struct range pfn_mapped[E820_X_MAX];
+extern struct range pfn_mapped[E820_MAX_ENTRIES];
 
 static int __init map_range(struct range *range)
 {
@@ -32,8 +34,19 @@ static int __init map_range(struct range *range)
 static void __init clear_pgds(unsigned long start,
 			unsigned long end)
 {
-	for (; start < end; start += PGDIR_SIZE)
-		pgd_clear(pgd_offset_k(start));
+	pgd_t *pgd;
+
+	for (; start < end; start += PGDIR_SIZE) {
+		pgd = pgd_offset_k(start);
+		/*
+		 * With folded p4d, pgd_clear() is nop, use p4d_clear()
+		 * instead.
+		 */
+		if (CONFIG_PGTABLE_LEVELS < 5)
+			p4d_clear(p4d_offset(pgd, start));
+		else
+			pgd_clear(pgd);
+	}
 }
 
 static void __init kasan_map_early_shadow(pgd_t *pgd)
@@ -43,8 +56,18 @@ static void __init kasan_map_early_shadow(pgd_t *pgd)
 	unsigned long end = KASAN_SHADOW_END;
 
 	for (i = pgd_index(start); start < end; i++) {
-		pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud)
-				| _KERNPG_TABLE);
+		switch (CONFIG_PGTABLE_LEVELS) {
+		case 4:
+			pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) |
+					_KERNPG_TABLE);
+			break;
+		case 5:
+			pgd[i] = __pgd(__pa_nodebug(kasan_zero_p4d) |
+					_KERNPG_TABLE);
+			break;
+		default:
+			BUILD_BUG();
+		}
 		start += PGDIR_SIZE;
 	}
 }
@@ -72,6 +95,7 @@ void __init kasan_early_init(void)
 	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
 	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
 	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+	p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE;
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		kasan_zero_pte[i] = __pte(pte_val);
@@ -82,6 +106,9 @@ void __init kasan_early_init(void)
 	for (i = 0; i < PTRS_PER_PUD; i++)
 		kasan_zero_pud[i] = __pud(pud_val);
 
+	for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++)
+		kasan_zero_p4d[i] = __p4d(p4d_val);
+
 	kasan_map_early_shadow(early_level4_pgt);
 	kasan_map_early_shadow(init_level4_pgt);
 }
@@ -103,7 +130,7 @@ void __init kasan_init(void)
 	kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
 			kasan_mem_to_shadow((void *)PAGE_OFFSET));
 
-	for (i = 0; i < E820_X_MAX; i++) {
+	for (i = 0; i < E820_MAX_ENTRIES; i++) {
 		if (pfn_mapped[i].end == 0)
 			break;
 
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 887e57182716..aed206475aa7 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
 #if defined(CONFIG_X86_ESPFIX64)
 static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
 #elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_START;
+static const unsigned long vaddr_end = EFI_VA_END;
 #else
 static const unsigned long vaddr_end = __START_KERNEL_map;
 #endif
@@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void)
 	 */
 	BUILD_BUG_ON(vaddr_start >= vaddr_end);
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
-		     vaddr_end >= EFI_VA_START);
+		     vaddr_end >= EFI_VA_END);
 	BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
 		      IS_ENABLED(CONFIG_EFI)) &&
 		     vaddr_end >= __START_KERNEL_map);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 7940166c799b..19ad095b41df 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -30,30 +30,44 @@
 #include <linux/limits.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/compat.h>
 #include <asm/elf.h>
 
 struct va_alignment __read_mostly va_align = {
 	.flags = -1,
 };
 
-static unsigned long stack_maxrandom_size(void)
+unsigned long tasksize_32bit(void)
+{
+	return IA32_PAGE_OFFSET;
+}
+
+unsigned long tasksize_64bit(void)
+{
+	return TASK_SIZE_MAX;
+}
+
+static unsigned long stack_maxrandom_size(unsigned long task_size)
 {
 	unsigned long max = 0;
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
+		max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit());
+		max <<= PAGE_SHIFT;
 	}
 
 	return max;
 }
 
-/*
- * Top of mmap area (just below the process stack).
- *
- * Leave an at least ~128 MB hole with possible stack randomization.
- */
-#define MIN_GAP (128*1024*1024UL + stack_maxrandom_size())
-#define MAX_GAP (TASK_SIZE/6*5)
+#ifdef CONFIG_COMPAT
+# define mmap32_rnd_bits  mmap_rnd_compat_bits
+# define mmap64_rnd_bits  mmap_rnd_bits
+#else
+# define mmap32_rnd_bits  mmap_rnd_bits
+# define mmap64_rnd_bits  mmap_rnd_bits
+#endif
+
+#define SIZE_128M    (128 * 1024 * 1024UL)
 
 static int mmap_is_legacy(void)
 {
@@ -66,54 +80,91 @@ static int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-unsigned long arch_mmap_rnd(void)
+static unsigned long arch_rnd(unsigned int rndbits)
 {
-	unsigned long rnd;
-
-	if (mmap_is_ia32())
-#ifdef CONFIG_COMPAT
-		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
-#else
-		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-#endif
-	else
-		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
+	return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT;
+}
 
-	return rnd << PAGE_SHIFT;
+unsigned long arch_mmap_rnd(void)
+{
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
+	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 
-static unsigned long mmap_base(unsigned long rnd)
+static unsigned long mmap_base(unsigned long rnd, unsigned long task_size)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap_min, gap_max;
+
+	/*
+	 * Top of mmap area (just below the process stack).
+	 * Leave an at least ~128 MB hole with possible stack randomization.
+	 */
+	gap_min = SIZE_128M + stack_maxrandom_size(task_size);
+	gap_max = (task_size / 6) * 5;
 
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
+	if (gap < gap_min)
+		gap = gap_min;
+	else if (gap > gap_max)
+		gap = gap_max;
+
+	return PAGE_ALIGN(task_size - gap - rnd);
+}
 
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+static unsigned long mmap_legacy_base(unsigned long rnd,
+				      unsigned long task_size)
+{
+	return __TASK_UNMAPPED_BASE(task_size) + rnd;
 }
 
 /*
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
  */
+static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
+		unsigned long random_factor, unsigned long task_size)
+{
+	*legacy_base = mmap_legacy_base(random_factor, task_size);
+	if (mmap_is_legacy())
+		*base = *legacy_base;
+	else
+		*base = mmap_base(random_factor, task_size);
+}
+
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
-	unsigned long random_factor = 0UL;
+	if (mmap_is_legacy())
+		mm->get_unmapped_area = arch_get_unmapped_area;
+	else
+		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 
-	if (current->flags & PF_RANDOMIZE)
-		random_factor = arch_mmap_rnd();
+	arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
+			arch_rnd(mmap64_rnd_bits), tasksize_64bit());
+
+#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
+	/*
+	 * The mmap syscall mapping base decision depends solely on the
+	 * syscall type (64-bit or compat). This applies for 64bit
+	 * applications and 32bit applications. The 64bit syscall uses
+	 * mmap_base, the compat syscall uses mmap_compat_base.
+	 */
+	arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base,
+			arch_rnd(mmap32_rnd_bits), tasksize_32bit());
+#endif
+}
 
-	mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
+unsigned long get_mmap_base(int is_legacy)
+{
+	struct mm_struct *mm = current->mm;
 
-	if (mmap_is_legacy()) {
-		mm->mmap_base = mm->mmap_legacy_base;
-		mm->get_unmapped_area = arch_get_unmapped_area;
-	} else {
-		mm->mmap_base = mmap_base(random_factor);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
+	if (in_compat_syscall()) {
+		return is_legacy ? mm->mmap_compat_legacy_base
+				 : mm->mmap_compat_base;
 	}
+#endif
+	return is_legacy ? mm->mmap_legacy_base : mm->mmap_base;
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index bef36622e408..4d434ddb75db 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -32,7 +32,7 @@
 #include <linux/kallsyms.h>
 #include <asm/pgtable.h>
 #include <linux/mmiotrace.h>
-#include <asm/e820.h> /* for ISA_START_ADDRESS */
+#include <asm/e820/api.h> /* for ISA_START_ADDRESS */
 #include <linux/atomic.h>
 #include <linux/percpu.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 5126dfd52b18..1c34b767c84c 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -526,15 +526,7 @@ int mpx_handle_bd_fault(void)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault()) {
-		force_sig(SIGSEGV, current);
-		/*
-		 * The force_sig() is essentially "handling" this
-		 * exception, so we do not pass up the error
-		 * from do_mpx_bt_fault().
-		 */
-	}
-	return 0;
+	return do_mpx_bt_fault();
 }
 
 /*
@@ -590,7 +582,7 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
  * we might run off the end of the bounds table if we are on
  * a 64-bit kernel and try to get 8 bytes.
  */
-int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
 		long __user *bd_entry_ptr)
 {
 	u32 bd_entry_32;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 12dcad7297a5..25504d5aa816 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -12,7 +12,7 @@
 #include <linux/sched.h>
 #include <linux/topology.h>
 
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
@@ -201,7 +201,7 @@ static void __init alloc_node_data(int nid)
 		nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
 					      MEMBLOCK_ALLOC_ACCESSIBLE);
 		if (!nd_pa) {
-			pr_err("Cannot find %zu bytes in node %d\n",
+			pr_err("Cannot find %zu bytes in any node (initial node: %d)\n",
 			       nd_size, nid);
 			return;
 		}
@@ -225,7 +225,7 @@ static void __init alloc_node_data(int nid)
  * numa_cleanup_meminfo - Cleanup a numa_meminfo
  * @mi: numa_meminfo to clean up
  *
- * Sanitize @mi by merging and removing unncessary memblks.  Also check for
+ * Sanitize @mi by merging and removing unnecessary memblks.  Also check for
  * conflicts and clear unused memblks.
  *
  * RETURNS:
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 28d42130243c..56b22fa504df 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -15,7 +15,7 @@
 #include <linux/pci.h>
 #include <linux/vmalloc.h>
 
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
@@ -346,6 +346,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 			     unsigned int *level)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -354,7 +355,15 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (pgd_none(*pgd))
 		return NULL;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d))
+		return NULL;
+
+	*level = PG_LEVEL_512G;
+	if (p4d_large(*p4d) || !p4d_present(*p4d))
+		return (pte_t *)p4d;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud))
 		return NULL;
 
@@ -406,13 +415,18 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
 pmd_t *lookup_pmd_address(unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 
 	pgd = pgd_offset_k(address);
 	if (pgd_none(*pgd))
 		return NULL;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d) || p4d_large(*p4d) || !p4d_present(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud))
 		return NULL;
 
@@ -477,11 +491,13 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
 
 		list_for_each_entry(page, &pgd_list, lru) {
 			pgd_t *pgd;
+			p4d_t *p4d;
 			pud_t *pud;
 			pmd_t *pmd;
 
 			pgd = (pgd_t *)page_address(page) + pgd_index(address);
-			pud = pud_offset(pgd, address);
+			p4d = p4d_offset(pgd, address);
+			pud = pud_offset(p4d, address);
 			pmd = pmd_offset(pud, address);
 			set_pte_atomic((pte_t *)pmd, pte);
 		}
@@ -836,9 +852,9 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
 			pud_clear(pud);
 }
 
-static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
 {
-	pud_t *pud = pud_offset(pgd, start);
+	pud_t *pud = pud_offset(p4d, start);
 
 	/*
 	 * Not on a GB page boundary?
@@ -1004,8 +1020,8 @@ static long populate_pmd(struct cpa_data *cpa,
 	return num_pages;
 }
 
-static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
-			 pgprot_t pgprot)
+static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d,
+			pgprot_t pgprot)
 {
 	pud_t *pud;
 	unsigned long end;
@@ -1026,7 +1042,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 		cur_pages = (pre_end - start) >> PAGE_SHIFT;
 		cur_pages = min_t(int, (int)cpa->numpages, cur_pages);
 
-		pud = pud_offset(pgd, start);
+		pud = pud_offset(p4d, start);
 
 		/*
 		 * Need a PMD page?
@@ -1047,7 +1063,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	if (cpa->numpages == cur_pages)
 		return cur_pages;
 
-	pud = pud_offset(pgd, start);
+	pud = pud_offset(p4d, start);
 	pud_pgprot = pgprot_4k_2_large(pgprot);
 
 	/*
@@ -1067,7 +1083,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	if (start < end) {
 		long tmp;
 
-		pud = pud_offset(pgd, start);
+		pud = pud_offset(p4d, start);
 		if (pud_none(*pud))
 			if (alloc_pmd_page(pud))
 				return -1;
@@ -1090,33 +1106,43 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 {
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
 	pud_t *pud = NULL;	/* shut up gcc */
+	p4d_t *p4d;
 	pgd_t *pgd_entry;
 	long ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
 
+	if (pgd_none(*pgd_entry)) {
+		p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+		if (!p4d)
+			return -1;
+
+		set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE));
+	}
+
 	/*
 	 * Allocate a PUD page and hand it down for mapping.
 	 */
-	if (pgd_none(*pgd_entry)) {
+	p4d = p4d_offset(pgd_entry, addr);
+	if (p4d_none(*p4d)) {
 		pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
 		if (!pud)
 			return -1;
 
-		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
+		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
 	}
 
 	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
 	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);
 
-	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
+	ret = populate_pud(cpa, addr, p4d, pgprot);
 	if (ret < 0) {
 		/*
 		 * Leave the PUD page in place in case some other CPU or thread
 		 * already found it, but remove any useless entries we just
 		 * added to it.
 		 */
-		unmap_pud_range(pgd_entry, addr,
+		unmap_pud_range(p4d, addr,
 				addr + (cpa->numpages << PAGE_SHIFT));
 		return ret;
 	}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index efc32bc6862b..9b78685b66e6 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -10,6 +10,7 @@
 #include <linux/seq_file.h>
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
+#include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
@@ -23,7 +24,7 @@
 #include <asm/x86_init.h>
 #include <asm/pgtable.h>
 #include <asm/fcntl.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/page.h>
 #include <asm/msr.h>
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 6cbdff26bb96..508a708eb9a6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -81,6 +81,14 @@ void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
 	tlb_remove_page(tlb, virt_to_page(pud));
 }
+
+#if CONFIG_PGTABLE_LEVELS > 4
+void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
+{
+	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
+	tlb_remove_page(tlb, virt_to_page(p4d));
+}
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
@@ -120,7 +128,7 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 	   references from swapper_pg_dir. */
 	if (CONFIG_PGTABLE_LEVELS == 2 ||
 	    (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
-	    CONFIG_PGTABLE_LEVELS == 4) {
+	    CONFIG_PGTABLE_LEVELS >= 4) {
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
@@ -261,13 +269,15 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 
 static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	int i;
 
 	if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
 		return;
 
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
 
 	for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) {
 		pmd_t *pmd = pmds[i];
@@ -580,6 +590,28 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
 }
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+#ifdef CONFIG_X86_5LEVEL
+/**
+ * p4d_set_huge - setup kernel P4D mapping
+ *
+ * No 512GB pages yet -- always return 0
+ */
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+
+/**
+ * p4d_clear_huge - clear kernel P4D mapping when it is set
+ *
+ * No 512GB pages yet -- always return 0
+ */
+int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
+#endif
+
 /**
  * pud_set_huge - setup kernel PUD mapping
  *
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 9adce776852b..b9bd5b8b14fa 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -12,7 +12,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/io.h>
@@ -26,6 +26,7 @@ unsigned int __VMALLOC_RESERVE = 128 << 20;
 void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -35,7 +36,12 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 		BUG();
 		return;
 	}
-	pud = pud_offset(pgd, vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	if (p4d_none(*p4d)) {
+		BUG();
+		return;
+	}
+	pud = pud_offset(p4d, vaddr);
 	if (pud_none(*pud)) {
 		BUG();
 		return;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 35fe69529bc1..3ea20d61b523 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -18,7 +18,7 @@
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a7655f6caf7d..6e7bedf69af7 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -263,8 +263,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 {
 	struct flush_tlb_info info;
 
-	if (end == 0)
-		end = start + PAGE_SIZE;
 	info.flush_mm = mm;
 	info.flush_start = start;
 	info.flush_end = end;
@@ -289,23 +287,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
 }
 
-void flush_tlb_current_task(void)
-{
-	struct mm_struct *mm = current->mm;
-
-	preempt_disable();
-
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-
-	/* This is an implicit full barrier that synchronizes with switch_mm. */
-	local_flush_tlb();
-
-	trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
-	preempt_enable();
-}
-
 /*
  * See Documentation/x86/tlb.txt for details.  We choose 33
  * because it is large enough to cover the vast majority (at
@@ -326,6 +307,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	unsigned long base_pages_to_flush = TLB_FLUSH_ALL;
 
 	preempt_disable();
+
+	if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
+		base_pages_to_flush = (end - start) >> PAGE_SHIFT;
+	if (base_pages_to_flush > tlb_single_page_flush_ceiling)
+		base_pages_to_flush = TLB_FLUSH_ALL;
+
 	if (current->active_mm != mm) {
 		/* Synchronize with switch_mm. */
 		smp_mb();
@@ -342,15 +329,11 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		goto out;
 	}
 
-	if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
-		base_pages_to_flush = (end - start) >> PAGE_SHIFT;
-
 	/*
 	 * Both branches below are implicit full barriers (MOV to CR or
 	 * INVLPG) that synchronize with switch_mm.
 	 */
-	if (base_pages_to_flush > tlb_single_page_flush_ceiling) {
-		base_pages_to_flush = TLB_FLUSH_ALL;
+	if (base_pages_to_flush == TLB_FLUSH_ALL) {
 		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
@@ -393,7 +376,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
+		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
 
 	preempt_enable();
 }
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 32322ce9b405..14f840df1d95 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -490,13 +490,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_LD | BPF_IMM | BPF_DW:
-			if (insn[1].code != 0 || insn[1].src_reg != 0 ||
-			    insn[1].dst_reg != 0 || insn[1].off != 0) {
-				/* verifier must catch invalid insns */
-				pr_err("invalid BPF_LD_IMM64 insn\n");
-				return -EINVAL;
-			}
-
 			/* optimization: if imm64 is zero, use 'xor <dst>,<dst>'
 			 * to save 7 bytes.
 			 */
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 0cb52ae0a8f0..190e718694b1 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pcibios_release_device(struct pci_dev *dev)
+{
+	if (atomic_dec_return(&dev->enable_cnt) >= 0)
+		pcibios_disable_device(dev);
+
+}
+#endif
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 0a9f2caf358f..6fa84d531f4f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -34,7 +34,7 @@
 #include <linux/bootmem.h>
 
 #include <asm/pat.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 #include <asm/io_apic.h>
 
@@ -398,7 +398,7 @@ void __init pcibios_resource_survey(void)
 	list_for_each_entry(bus, &pci_root_buses, node)
 		pcibios_allocate_resources(bus, 1);
 
-	e820_reserve_resources_late();
+	e820__reserve_resources_late();
 	/*
 	 * Insert the IO APIC resources after PCI initialization has
 	 * occurred to handle IO APICS that are mapped in on a BAR in
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index dd30b7e08bc2..d1b47d5bc9c3 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/rculist.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
 
@@ -423,7 +423,7 @@ static acpi_status find_mboard_resource(acpi_handle handle, u32 lvl,
 	return AE_OK;
 }
 
-static int is_acpi_reserved(u64 start, u64 end, unsigned not_used)
+static bool is_acpi_reserved(u64 start, u64 end, unsigned not_used)
 {
 	struct resource mcfg_res;
 
@@ -440,11 +440,11 @@ static int is_acpi_reserved(u64 start, u64 end, unsigned not_used)
 	return mcfg_res.flags;
 }
 
-typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type);
+typedef bool (*check_reserved_t)(u64 start, u64 end, unsigned type);
 
-static int __ref is_mmconf_reserved(check_reserved_t is_reserved,
-				    struct pci_mmcfg_region *cfg,
-				    struct device *dev, int with_e820)
+static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
+				     struct pci_mmcfg_region *cfg,
+				     struct device *dev, int with_e820)
 {
 	u64 addr = cfg->res.start;
 	u64 size = resource_size(&cfg->res);
@@ -452,7 +452,7 @@ static int __ref is_mmconf_reserved(check_reserved_t is_reserved,
 	int num_buses;
 	char *method = with_e820 ? "E820" : "ACPI motherboard resources";
 
-	while (!is_reserved(addr, addr + size, E820_RESERVED)) {
+	while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
 		size >>= 1;
 		if (size < (16UL<<20))
 			break;
@@ -494,8 +494,8 @@ static int __ref is_mmconf_reserved(check_reserved_t is_reserved,
 	return 1;
 }
 
-static int __ref pci_mmcfg_check_reserved(struct device *dev,
-		  struct pci_mmcfg_region *cfg, int early)
+static bool __ref
+pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
 {
 	if (!early && !acpi_disabled) {
 		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
@@ -514,7 +514,7 @@ static int __ref pci_mmcfg_check_reserved(struct device *dev,
 	}
 
 	/*
-	 * e820_all_mapped() is marked as __init.
+	 * e820__mapped_all() is marked as __init.
 	 * All entries from ACPI MCFG table have been checked at boot time.
 	 * For MCFG information constructed from hotpluggable host bridge's
 	 * _CBA method, just assume it's reserved.
@@ -525,7 +525,7 @@ static int __ref pci_mmcfg_check_reserved(struct device *dev,
 	/* Don't try to do this check unless configuration
 	   type 1 is available. how about type 2 ?*/
 	if (raw_pci_ops)
-		return is_mmconf_reserved(e820_all_mapped, cfg, dev, 1);
+		return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
 
 	return 0;
 }
diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
index 43984bc1665a..3e9e166f6408 100644
--- a/arch/x86/pci/mmconfig_32.c
+++ b/arch/x86/pci/mmconfig_32.c
@@ -12,7 +12,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/rcupdate.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 
 /* Assume systems with more busses have correct MCFG */
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index bea52496aea6..f1c1aa0430ae 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -10,7 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
 #include <linux/rcupdate.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 
 #define PREFIX "PCI: "
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 1d97cea3b3a4..29e9ba6ace9d 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -7,7 +7,9 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+
 #include <asm/pci_x86.h>
+#include <asm/e820/types.h>
 #include <asm/pci-functions.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e1fb269c87af..292ab0364a89 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return 1;
 
 	for_each_pci_msi_entry(msidesc, dev) {
-		__pci_read_msi_msg(msidesc, &msg);
-		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
-			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
-		if (msg.data != XEN_PIRQ_MSI_DATA ||
-		    xen_irq_from_pirq(pirq) < 0) {
-			pirq = xen_allocate_pirq_msi(dev, msidesc);
-			if (pirq < 0) {
-				irq = -ENODEV;
-				goto error;
-			}
-			xen_msi_compose_msg(dev, pirq, &msg);
-			__pci_write_msi_msg(msidesc, &msg);
-			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
-		} else {
-			dev_dbg(&dev->dev,
-				"xen: msi already bound to pirq=%d\n", pirq);
+		pirq = xen_allocate_pirq_msi(dev, msidesc);
+		if (pirq < 0) {
+			irq = -ENODEV;
+			goto error;
 		}
+		xen_msi_compose_msg(dev, pirq, &msg);
+		__pci_write_msi_msg(msidesc, &msg);
+		dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index 066619b0700c..f1d83b34c329 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1,6 +1,5 @@
 OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y
 
 obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
-obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
 obj-$(CONFIG_EARLY_PRINTK_EFI)	+= early_printk.o
 obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 565dff3c9a12..a15cf815ac4e 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -47,6 +47,7 @@
 
 #include <asm/setup.h>
 #include <asm/efi.h>
+#include <asm/e820/api.h>
 #include <asm/time.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
@@ -139,21 +140,21 @@ static void __init do_add_efi_memmap(void)
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
 			if (md->attribute & EFI_MEMORY_WB)
-				e820_type = E820_RAM;
+				e820_type = E820_TYPE_RAM;
 			else
-				e820_type = E820_RESERVED;
+				e820_type = E820_TYPE_RESERVED;
 			break;
 		case EFI_ACPI_RECLAIM_MEMORY:
-			e820_type = E820_ACPI;
+			e820_type = E820_TYPE_ACPI;
 			break;
 		case EFI_ACPI_MEMORY_NVS:
-			e820_type = E820_NVS;
+			e820_type = E820_TYPE_NVS;
 			break;
 		case EFI_UNUSABLE_MEMORY:
-			e820_type = E820_UNUSABLE;
+			e820_type = E820_TYPE_UNUSABLE;
 			break;
 		case EFI_PERSISTENT_MEMORY:
-			e820_type = E820_PMEM;
+			e820_type = E820_TYPE_PMEM;
 			break;
 		default:
 			/*
@@ -161,12 +162,12 @@ static void __init do_add_efi_memmap(void)
 			 * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
 			 * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
 			 */
-			e820_type = E820_RESERVED;
+			e820_type = E820_TYPE_RESERVED;
 			break;
 		}
-		e820_add_region(start, size, e820_type);
+		e820__range_add(start, size, e820_type);
 	}
-	sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+	e820__update_table(e820_table);
 }
 
 int __init efi_memblock_x86_reserve_range(void)
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index cef39b097649..3481268da3d0 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -68,7 +68,7 @@ pgd_t * __init efi_call_phys_prolog(void)
 	load_cr3(initial_page_table);
 	__flush_tlb_all();
 
-	gdt_descr.address = __pa(get_cpu_gdt_table(0));
+	gdt_descr.address = get_cpu_gdt_paddr(0);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 
@@ -79,7 +79,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 {
 	struct desc_ptr gdt_descr;
 
-	gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
+	gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index a4695da42d77..c488625c9712 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -35,7 +35,7 @@
 
 #include <asm/setup.h>
 #include <asm/page.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/proto.h>
@@ -47,7 +47,7 @@
 #include <asm/pgalloc.h>
 
 /*
- * We allocate runtime services regions bottom-up, starting from -4G, i.e.
+ * We allocate runtime services regions top-down, starting from -4G, i.e.
  * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
  */
 static u64 efi_va = EFI_VA_START;
@@ -135,6 +135,7 @@ static pgd_t *efi_pgd;
 int __init efi_alloc_page_tables(void)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	gfp_t gfp_mask;
 
@@ -147,15 +148,20 @@ int __init efi_alloc_page_tables(void)
 		return -ENOMEM;
 
 	pgd = efi_pgd + pgd_index(EFI_VA_END);
+	p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
+	if (!p4d) {
+		free_page((unsigned long)efi_pgd);
+		return -ENOMEM;
+	}
 
-	pud = pud_alloc_one(NULL, 0);
+	pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
 	if (!pud) {
+		if (CONFIG_PGTABLE_LEVELS > 4)
+			free_page((unsigned long) pgd_page_vaddr(*pgd));
 		free_page((unsigned long)efi_pgd);
 		return -ENOMEM;
 	}
 
-	pgd_populate(NULL, pgd, pud);
-
 	return 0;
 }
 
@@ -166,6 +172,7 @@ void efi_sync_low_kernel_mappings(void)
 {
 	unsigned num_entries;
 	pgd_t *pgd_k, *pgd_efi;
+	p4d_t *p4d_k, *p4d_efi;
 	pud_t *pud_k, *pud_efi;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
@@ -190,23 +197,37 @@ void efi_sync_low_kernel_mappings(void)
 	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
 
 	/*
+	 * As with PGDs, we share all P4D entries apart from the one entry
+	 * that covers the EFI runtime mapping space.
+	 */
+	BUILD_BUG_ON(p4d_index(EFI_VA_END) != p4d_index(MODULES_END));
+	BUILD_BUG_ON((EFI_VA_START & P4D_MASK) != (EFI_VA_END & P4D_MASK));
+
+	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
+	pgd_k = pgd_offset_k(EFI_VA_END);
+	p4d_efi = p4d_offset(pgd_efi, 0);
+	p4d_k = p4d_offset(pgd_k, 0);
+
+	num_entries = p4d_index(EFI_VA_END);
+	memcpy(p4d_efi, p4d_k, sizeof(p4d_t) * num_entries);
+
+	/*
 	 * We share all the PUD entries apart from those that map the
 	 * EFI regions. Copy around them.
 	 */
 	BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0);
 	BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0);
 
-	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
-	pud_efi = pud_offset(pgd_efi, 0);
-
-	pgd_k = pgd_offset_k(EFI_VA_END);
-	pud_k = pud_offset(pgd_k, 0);
+	p4d_efi = p4d_offset(pgd_efi, EFI_VA_END);
+	p4d_k = p4d_offset(pgd_k, EFI_VA_END);
+	pud_efi = pud_offset(p4d_efi, 0);
+	pud_k = pud_offset(p4d_k, 0);
 
 	num_entries = pud_index(EFI_VA_END);
 	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
 
-	pud_efi = pud_offset(pgd_efi, EFI_VA_START);
-	pud_k = pud_offset(pgd_k, EFI_VA_START);
+	pud_efi = pud_offset(p4d_efi, EFI_VA_START);
+	pud_k = pud_offset(p4d_k, EFI_VA_START);
 
 	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);
 	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 30031d5293c4..26615991d69c 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -11,6 +11,8 @@
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
+
+#include <asm/e820/api.h>
 #include <asm/efi.h>
 #include <asm/uv/uv.h>
 
@@ -201,6 +203,10 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 		return;
 	}
 
+	/* No need to reserve regions that will never be freed. */
+	if (md.attribute & EFI_MEMORY_RUNTIME)
+		return;
+
 	size += addr % EFI_PAGE_SIZE;
 	size = round_up(size, EFI_PAGE_SIZE);
 	addr = round_down(addr, EFI_PAGE_SIZE);
@@ -240,14 +246,14 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
  * else. We must only reserve (and then free) regions:
  *
  * - Not within any part of the kernel
- * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc)
+ * - Not the BIOS reserved area (E820_TYPE_RESERVED, E820_TYPE_NVS, etc)
  */
 static bool can_free_region(u64 start, u64 size)
 {
 	if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end))
 		return false;
 
-	if (!e820_all_mapped(start, start+size, E820_RAM))
+	if (!e820__mapped_all(start, start+size, E820_TYPE_RAM))
 		return false;
 
 	return true;
@@ -280,7 +286,7 @@ void __init efi_reserve_boot_services(void)
 		 * A good example of a critical region that must not be
 		 * freed is page zero (first 4Kb of memory), which may
 		 * contain boot services code/data but is marked
-		 * E820_RESERVED by trim_bios_range().
+		 * E820_TYPE_RESERVED by trim_bios_range().
 		 */
 		if (!already_reserved) {
 			memblock_reserve(start, size);
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index a7dbec4dce27..53e0235e308f 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -2,8 +2,9 @@
 obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o
 # SDHCI Devices
 obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o
-# WiFi
+# WiFi + BT
 obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o
+obj-$(subst m,y,$(CONFIG_BT_HCIUART_BCM)) += platform_bt.o
 # IPC Devices
 obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o
 obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o
@@ -26,5 +27,6 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
 obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o
 obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
 obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
new file mode 100644
index 000000000000..5a0483e7bf66
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -0,0 +1,108 @@
+/*
+ * Bluetooth platform data initialization file
+ *
+ * (C) Copyright 2017 Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/gpio/machine.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/intel-mid.h>
+
+struct bt_sfi_data {
+	struct device *dev;
+	const char *name;
+	int (*setup)(struct bt_sfi_data *ddata);
+};
+
+static struct gpiod_lookup_table tng_bt_sfi_gpio_table = {
+	.dev_id	= "hci_bcm",
+	.table	= {
+		GPIO_LOOKUP("0000:00:0c.0", -1, "device-wakeup", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("0000:00:0c.0", -1, "shutdown",      GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("0000:00:0c.0", -1, "host-wakeup",   GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
+#define TNG_BT_SFI_GPIO_DEVICE_WAKEUP	"bt_wakeup"
+#define TNG_BT_SFI_GPIO_SHUTDOWN	"BT-reset"
+#define TNG_BT_SFI_GPIO_HOST_WAKEUP	"bt_uart_enable"
+
+static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata)
+{
+	struct gpiod_lookup_table *table = &tng_bt_sfi_gpio_table;
+	struct gpiod_lookup *lookup = table->table;
+	struct pci_dev *pdev;
+
+	/* Connected to /dev/ttyS0 */
+	pdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(4, 1));
+	if (!pdev)
+		return -ENODEV;
+
+	ddata->dev = &pdev->dev;
+	ddata->name = table->dev_id;
+
+	lookup[0].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_DEVICE_WAKEUP);
+	lookup[1].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_SHUTDOWN);
+	lookup[2].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_HOST_WAKEUP);
+
+	gpiod_add_lookup_table(table);
+	return 0;
+}
+
+static struct bt_sfi_data tng_bt_sfi_data __initdata = {
+	.setup	= tng_bt_sfi_setup,
+};
+
+#define ICPU(model, ddata)	\
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
+
+static const struct x86_cpu_id bt_sfi_cpu_ids[] = {
+	ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data),
+	{}
+};
+
+static int __init bt_sfi_init(void)
+{
+	struct platform_device_info info;
+	struct platform_device *pdev;
+	const struct x86_cpu_id *id;
+	struct bt_sfi_data *ddata;
+	int ret;
+
+	id = x86_match_cpu(bt_sfi_cpu_ids);
+	if (!id)
+		return -ENODEV;
+
+	ddata = (struct bt_sfi_data *)id->driver_data;
+	if (!ddata)
+		return -ENODEV;
+
+	ret = ddata->setup(ddata);
+	if (ret)
+		return ret;
+
+	memset(&info, 0, sizeof(info));
+	info.fwnode	= ddata->dev->fwnode;
+	info.parent	= ddata->dev;
+	info.name	= ddata->name,
+	info.id		= PLATFORM_DEVID_NONE,
+
+	pdev = platform_device_register_full(&info);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	dev_info(ddata->dev, "Registered Bluetooth device: %s\n", ddata->name);
+	return 0;
+}
+device_initcall(bt_sfi_init);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
new file mode 100644
index 000000000000..a6c3705a28ad
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
@@ -0,0 +1,82 @@
+/*
+ * Intel Merrifield power button support
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/sfi.h>
+
+#include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
+
+static struct resource mrfld_power_btn_resources[] = {
+	{
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mrfld_power_btn_dev = {
+	.name		= "msic_power_btn",
+	.id		= PLATFORM_DEVID_NONE,
+	.num_resources	= ARRAY_SIZE(mrfld_power_btn_resources),
+	.resource	= mrfld_power_btn_resources,
+};
+
+static int mrfld_power_btn_scu_status_change(struct notifier_block *nb,
+					     unsigned long code, void *data)
+{
+	if (code == SCU_DOWN) {
+		platform_device_unregister(&mrfld_power_btn_dev);
+		return 0;
+	}
+
+	return platform_device_register(&mrfld_power_btn_dev);
+}
+
+static struct notifier_block mrfld_power_btn_scu_notifier = {
+	.notifier_call	= mrfld_power_btn_scu_status_change,
+};
+
+static int __init register_mrfld_power_btn(void)
+{
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return -ENODEV;
+
+	/*
+	 * We need to be sure that the SCU IPC is ready before
+	 * PMIC power button device can be registered:
+	 */
+	intel_scu_notifier_add(&mrfld_power_btn_scu_notifier);
+
+	return 0;
+}
+arch_initcall(register_mrfld_power_btn);
+
+static void __init *mrfld_power_btn_platform_data(void *info)
+{
+	struct resource *res = mrfld_power_btn_resources;
+	struct sfi_device_table_entry *pentry = info;
+
+	res->start = res->end = pentry->irq;
+	return NULL;
+}
+
+static const struct devs_id mrfld_power_btn_dev_id __initconst = {
+	.name			= "bcove_power_btn",
+	.type			= SFI_DEV_TYPE_IPC,
+	.delay			= 1,
+	.msic			= 1,
+	.get_platform_data	= &mrfld_power_btn_platform_data,
+};
+
+sfi_device(mrfld_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 86edd1e941eb..9e304e2ea4f5 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -19,7 +19,7 @@
 #include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
 
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
 
 static struct platform_device wdt_dev = {
 	.name = "intel_mid_wdt",
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index e793fe509971..e42978d4deaf 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -17,16 +17,6 @@
 
 #include "intel_mid_weak_decls.h"
 
-static void penwell_arch_setup(void);
-/* penwell arch ops */
-static struct intel_mid_ops penwell_ops = {
-	.arch_setup = penwell_arch_setup,
-};
-
-static void mfld_power_off(void)
-{
-}
-
 static unsigned long __init mfld_calibrate_tsc(void)
 {
 	unsigned long fast_calibrate;
@@ -63,9 +53,12 @@ static unsigned long __init mfld_calibrate_tsc(void)
 static void __init penwell_arch_setup(void)
 {
 	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
-	pm_power_off = mfld_power_off;
 }
 
+static struct intel_mid_ops penwell_ops = {
+	.arch_setup = penwell_arch_setup,
+};
+
 void *get_penwell_ops(void)
 {
 	return &penwell_ops;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 766d4d3529a1..42e65fee5673 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -23,28 +23,7 @@
 #include <asm/irq_vectors.h>
 #include <asm/timer.h>
 
-static struct bau_operations ops;
-
-static struct bau_operations uv123_bau_ops = {
-	.bau_gpa_to_offset       = uv_gpa_to_offset,
-	.read_l_sw_ack           = read_mmr_sw_ack,
-	.read_g_sw_ack           = read_gmmr_sw_ack,
-	.write_l_sw_ack          = write_mmr_sw_ack,
-	.write_g_sw_ack          = write_gmmr_sw_ack,
-	.write_payload_first     = write_mmr_payload_first,
-	.write_payload_last      = write_mmr_payload_last,
-};
-
-static struct bau_operations uv4_bau_ops = {
-	.bau_gpa_to_offset       = uv_gpa_to_soc_phys_ram,
-	.read_l_sw_ack           = read_mmr_proc_sw_ack,
-	.read_g_sw_ack           = read_gmmr_proc_sw_ack,
-	.write_l_sw_ack          = write_mmr_proc_sw_ack,
-	.write_g_sw_ack          = write_gmmr_proc_sw_ack,
-	.write_payload_first     = write_mmr_proc_payload_first,
-	.write_payload_last      = write_mmr_proc_payload_last,
-};
-
+static struct bau_operations ops __ro_after_init;
 
 /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */
 static int timeout_base_ns[] = {
@@ -548,11 +527,12 @@ static unsigned long uv1_read_status(unsigned long mmr_offset, int right_shift)
  * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP
  */
 static int uv1_wait_completion(struct bau_desc *bau_desc,
-				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_status;
 	cycles_t ttm;
+	u64 mmr_offset = bcp->status_mmr;
+	int right_shift = bcp->status_index;
 	struct ptc_stats *stat = bcp->statp;
 
 	descriptor_status = uv1_read_status(mmr_offset, right_shift);
@@ -640,11 +620,12 @@ int handle_uv2_busy(struct bau_control *bcp)
 }
 
 static int uv2_3_wait_completion(struct bau_desc *bau_desc,
-				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_stat;
 	cycles_t ttm;
+	u64 mmr_offset = bcp->status_mmr;
+	int right_shift = bcp->status_index;
 	int desc = bcp->uvhub_cpu;
 	long busy_reps = 0;
 	struct ptc_stats *stat = bcp->statp;
@@ -706,28 +687,59 @@ static int uv2_3_wait_completion(struct bau_desc *bau_desc,
 }
 
 /*
- * There are 2 status registers; each and array[32] of 2 bits. Set up for
- * which register to read and position in that register based on cpu in
- * current hub.
+ * Returns the status of current BAU message for cpu desc as a bit field
+ * [Error][Busy][Aux]
  */
-static int wait_completion(struct bau_desc *bau_desc, struct bau_control *bcp, long try)
+static u64 read_status(u64 status_mmr, int index, int desc)
 {
-	int right_shift;
-	unsigned long mmr_offset;
+	u64 stat;
+
+	stat = ((read_lmmr(status_mmr) >> index) & UV_ACT_STATUS_MASK) << 1;
+	stat |= (read_lmmr(UVH_LB_BAU_SB_ACTIVATION_STATUS_2) >> desc) & 0x1;
+
+	return stat;
+}
+
+static int uv4_wait_completion(struct bau_desc *bau_desc,
+				struct bau_control *bcp, long try)
+{
+	struct ptc_stats *stat = bcp->statp;
+	u64 descriptor_stat;
+	u64 mmr = bcp->status_mmr;
+	int index = bcp->status_index;
 	int desc = bcp->uvhub_cpu;
 
-	if (desc < UV_CPUS_PER_AS) {
-		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-		right_shift = desc * UV_ACT_STATUS_SIZE;
-	} else {
-		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-		right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
-	}
+	descriptor_stat = read_status(mmr, index, desc);
 
-	if (bcp->uvhub_version == 1)
-		return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try);
-	else
-		return uv2_3_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try);
+	/* spin on the status MMR, waiting for it to go idle */
+	while (descriptor_stat != UV2H_DESC_IDLE) {
+		switch (descriptor_stat) {
+		case UV2H_DESC_SOURCE_TIMEOUT:
+			stat->s_stimeout++;
+			return FLUSH_GIVEUP;
+
+		case UV2H_DESC_DEST_TIMEOUT:
+			stat->s_dtimeout++;
+			bcp->conseccompletes = 0;
+			return FLUSH_RETRY_TIMEOUT;
+
+		case UV2H_DESC_DEST_STRONG_NACK:
+			stat->s_plugged++;
+			bcp->conseccompletes = 0;
+			return FLUSH_RETRY_PLUGGED;
+
+		case UV2H_DESC_DEST_PUT_ERR:
+			bcp->conseccompletes = 0;
+			return FLUSH_GIVEUP;
+
+		default:
+			/* descriptor_stat is still BUSY */
+			cpu_relax();
+		}
+		descriptor_stat = read_status(mmr, index, desc);
+	}
+	bcp->conseccompletes++;
+	return FLUSH_COMPLETE;
 }
 
 /*
@@ -918,7 +930,7 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp,
 	struct uv1_bau_msg_header *uv1_hdr = NULL;
 	struct uv2_3_bau_msg_header *uv2_3_hdr = NULL;
 
-	if (bcp->uvhub_version == 1) {
+	if (bcp->uvhub_version == UV_BAU_V1) {
 		uv1 = 1;
 		uv1_throttle(hmaster, stat);
 	}
@@ -958,7 +970,7 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp,
 		write_mmr_activation(index);
 
 		try++;
-		completion_stat = wait_completion(bau_desc, bcp, try);
+		completion_stat = ops.wait_completion(bau_desc, bcp, try);
 
 		handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
 
@@ -1114,15 +1126,12 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 						unsigned long end,
 						unsigned int cpu)
 {
-	int locals = 0;
-	int remotes = 0;
-	int hubs = 0;
+	int locals = 0, remotes = 0, hubs = 0;
 	struct bau_desc *bau_desc;
 	struct cpumask *flush_mask;
 	struct ptc_stats *stat;
 	struct bau_control *bcp;
-	unsigned long descriptor_status;
-	unsigned long status;
+	unsigned long descriptor_status, status, address;
 
 	bcp = &per_cpu(bau_control, cpu);
 
@@ -1171,10 +1180,24 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
 	if (!end || (end - start) <= PAGE_SIZE)
-		bau_desc->payload.address = start;
+		address = start;
 	else
-		bau_desc->payload.address = TLB_FLUSH_ALL;
-	bau_desc->payload.sending_cpu = cpu;
+		address = TLB_FLUSH_ALL;
+
+	switch (bcp->uvhub_version) {
+	case UV_BAU_V1:
+	case UV_BAU_V2:
+	case UV_BAU_V3:
+		bau_desc->payload.uv1_2_3.address = address;
+		bau_desc->payload.uv1_2_3.sending_cpu = cpu;
+		break;
+	case UV_BAU_V4:
+		bau_desc->payload.uv4.address = address;
+		bau_desc->payload.uv4.sending_cpu = cpu;
+		bau_desc->payload.uv4.qualifier = BAU_DESC_QUALIFIER;
+		break;
+	}
+
 	/*
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
 	 * or 1 if it gave up and the original cpumask should be returned.
@@ -1296,7 +1319,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 
 		msgdesc.msg_slot = msg - msgdesc.queue_first;
 		msgdesc.msg = msg;
-		if (bcp->uvhub_version == 2)
+		if (bcp->uvhub_version == UV_BAU_V2)
 			process_uv2_message(&msgdesc, bcp);
 		else
 			/* no error workaround for uv1 or uv3 */
@@ -1838,7 +1861,7 @@ static void pq_init(int node, int pnode)
 	 * and the payload queue tail must be maintained by the kernel.
 	 */
 	bcp = &per_cpu(bau_control, smp_processor_id());
-	if (bcp->uvhub_version <= 3) {
+	if (bcp->uvhub_version <= UV_BAU_V3) {
 		tail = first;
 		gnode = uv_gpa_to_gnode(uv_gpa(pqp));
 		first = (gnode << UV_PAYLOADQ_GNODE_SHIFT) | tail;
@@ -1847,7 +1870,6 @@ static void pq_init(int node, int pnode)
 
 	ops.write_payload_first(pnode, first);
 	ops.write_payload_last(pnode, last);
-	ops.write_g_sw_ack(pnode, 0xffffUL);
 
 	/* in effect, all msg_type's are set to MSG_NOOP */
 	memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
@@ -2035,8 +2057,7 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 			struct bau_control **smasterp,
 			struct bau_control **hmasterp)
 {
-	int i;
-	int cpu;
+	int i, cpu, uvhub_cpu;
 	struct bau_control *bcp;
 
 	for (i = 0; i < sdp->num_cpus; i++) {
@@ -2053,19 +2074,33 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 		bcp->socket_master = *smasterp;
 		bcp->uvhub = bdp->uvhub;
 		if (is_uv1_hub())
-			bcp->uvhub_version = 1;
+			bcp->uvhub_version = UV_BAU_V1;
 		else if (is_uv2_hub())
-			bcp->uvhub_version = 2;
+			bcp->uvhub_version = UV_BAU_V2;
 		else if (is_uv3_hub())
-			bcp->uvhub_version = 3;
+			bcp->uvhub_version = UV_BAU_V3;
 		else if (is_uv4_hub())
-			bcp->uvhub_version = 4;
+			bcp->uvhub_version = UV_BAU_V4;
 		else {
 			pr_emerg("uvhub version not 1, 2, 3, or 4\n");
 			return 1;
 		}
 		bcp->uvhub_master = *hmasterp;
-		bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu);
+		uvhub_cpu = uv_cpu_blade_processor_id(cpu);
+		bcp->uvhub_cpu = uvhub_cpu;
+
+		/*
+		 * The ERROR and BUSY status registers are located pairwise over
+		 * the STATUS_0 and STATUS_1 mmrs; each an array[32] of 2 bits.
+		 */
+		if (uvhub_cpu < UV_CPUS_PER_AS) {
+			bcp->status_mmr = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+			bcp->status_index = uvhub_cpu * UV_ACT_STATUS_SIZE;
+		} else {
+			bcp->status_mmr = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+			bcp->status_index = (uvhub_cpu - UV_CPUS_PER_AS)
+						* UV_ACT_STATUS_SIZE;
+		}
 
 		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
 			pr_emerg("%d cpus per uvhub invalid\n",
@@ -2148,6 +2183,39 @@ fail:
 	return 1;
 }
 
+static const struct bau_operations uv1_bau_ops __initconst = {
+	.bau_gpa_to_offset       = uv_gpa_to_offset,
+	.read_l_sw_ack           = read_mmr_sw_ack,
+	.read_g_sw_ack           = read_gmmr_sw_ack,
+	.write_l_sw_ack          = write_mmr_sw_ack,
+	.write_g_sw_ack          = write_gmmr_sw_ack,
+	.write_payload_first     = write_mmr_payload_first,
+	.write_payload_last      = write_mmr_payload_last,
+	.wait_completion	 = uv1_wait_completion,
+};
+
+static const struct bau_operations uv2_3_bau_ops __initconst = {
+	.bau_gpa_to_offset       = uv_gpa_to_offset,
+	.read_l_sw_ack           = read_mmr_sw_ack,
+	.read_g_sw_ack           = read_gmmr_sw_ack,
+	.write_l_sw_ack          = write_mmr_sw_ack,
+	.write_g_sw_ack          = write_gmmr_sw_ack,
+	.write_payload_first     = write_mmr_payload_first,
+	.write_payload_last      = write_mmr_payload_last,
+	.wait_completion	 = uv2_3_wait_completion,
+};
+
+static const struct bau_operations uv4_bau_ops __initconst = {
+	.bau_gpa_to_offset       = uv_gpa_to_soc_phys_ram,
+	.read_l_sw_ack           = read_mmr_proc_sw_ack,
+	.read_g_sw_ack           = read_gmmr_proc_sw_ack,
+	.write_l_sw_ack          = write_mmr_proc_sw_ack,
+	.write_g_sw_ack          = write_gmmr_proc_sw_ack,
+	.write_payload_first     = write_mmr_proc_payload_first,
+	.write_payload_last      = write_mmr_proc_payload_last,
+	.wait_completion         = uv4_wait_completion,
+};
+
 /*
  * Initialization of BAU-related structures
  */
@@ -2167,11 +2235,11 @@ static int __init uv_bau_init(void)
 	if (is_uv4_hub())
 		ops = uv4_bau_ops;
 	else if (is_uv3_hub())
-		ops = uv123_bau_ops;
+		ops = uv2_3_bau_ops;
 	else if (is_uv2_hub())
-		ops = uv123_bau_ops;
+		ops = uv2_3_bau_ops;
 	else if (is_uv1_hub())
-		ops = uv123_bau_ops;
+		ops = uv1_bau_ops;
 
 	for_each_possible_cpu(cur_cpu) {
 		mask = &per_cpu(uv_flush_tlb_mask, cur_cpu);
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 2ee7632d4916..b082d71b08ee 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -390,9 +390,11 @@ static __init int uv_rtc_setup_clock(void)
 
 	clock_event_device_uv.min_delta_ns = NSEC_PER_SEC /
 						sn_rtc_cycles_per_second;
+	clock_event_device_uv.min_delta_ticks = 1;
 
 	clock_event_device_uv.max_delta_ns = clocksource_uv.mask *
 				(NSEC_PER_SEC / sn_rtc_cycles_per_second);
+	clock_event_device_uv.max_delta_ticks = clocksource_uv.mask;
 
 	rc = schedule_on_each_cpu(uv_rtc_register_clockevents);
 	if (rc) {
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 66ade16c7693..6b05a9219ea2 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -95,7 +95,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 	 * 'pmode_gdt' in wakeup_start.
 	 */
 	ctxt->gdt_desc.size = GDT_SIZE - 1;
-	ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_table(smp_processor_id());
+	ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id());
 
 	store_tr(ctxt->tr);
 
@@ -162,7 +162,7 @@ static void fix_processor_context(void)
 	int cpu = smp_processor_id();
 	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
 #ifdef CONFIG_X86_64
-	struct desc_struct *desc = get_cpu_gdt_table(cpu);
+	struct desc_struct *desc = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 #endif
 	set_tss_desc(cpu, t);	/*
@@ -183,6 +183,9 @@ static void fix_processor_context(void)
 	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
+
+	/* The processor is back on the direct GDT, load back the fixmap */
+	load_fixmap_gdt(cpu);
 }
 
 /**
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 9f14bd34581d..c35fdb585c68 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -32,6 +32,7 @@ pgd_t *resume_pg_dir;
  */
 static pmd_t *resume_one_md_table_init(pgd_t *pgd)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd_table;
 
@@ -41,11 +42,13 @@ static pmd_t *resume_one_md_table_init(pgd_t *pgd)
 		return NULL;
 
 	set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
 
 	BUG_ON(pmd_table != pmd_offset(pud, 0));
 #else
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
 	pmd_table = pmd_offset(pud, 0);
 #endif
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index ded2e8272382..6a61194ffd58 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -16,6 +16,7 @@
 
 #include <crypto/hash.h>
 
+#include <asm/e820/api.h>
 #include <asm/init.h>
 #include <asm/proto.h>
 #include <asm/page.h>
@@ -49,6 +50,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 {
 	pmd_t *pmd;
 	pud_t *pud;
+	p4d_t *p4d;
 
 	/*
 	 * The new mapping only has to cover the page containing the image
@@ -63,6 +65,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 	 * the virtual address space after switching over to the original page
 	 * tables used by the image kernel.
 	 */
+
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		p4d = (p4d_t *)get_safe_page(GFP_ATOMIC);
+		if (!p4d)
+			return -ENOMEM;
+	}
+
 	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
 	if (!pud)
 		return -ENOMEM;
@@ -75,8 +84,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
 	set_pud(pud + pud_index(restore_jump_address),
 		__pud(__pa(pmd) | _KERNPG_TABLE));
-	set_pgd(pgd + pgd_index(restore_jump_address),
-		__pgd(__pa(pud) | _KERNPG_TABLE));
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		set_p4d(p4d + p4d_index(restore_jump_address), __p4d(__pa(pud) | _KERNPG_TABLE));
+		set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(p4d) | _KERNPG_TABLE));
+	} else {
+		/* No p4d for 4-level paging: point the pgd to the pud page table */
+		set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
 
 	return 0;
 }
@@ -124,7 +138,10 @@ static int set_up_temporary_mappings(void)
 static int relocate_restore_code(void)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
 
 	relocated_restore_code = get_safe_page(GFP_ATOMIC);
 	if (!relocated_restore_code)
@@ -134,22 +151,25 @@ static int relocate_restore_code(void)
 
 	/* Make the page containing the relocated code executable */
 	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
-	pud = pud_offset(pgd, relocated_restore_code);
+	p4d = p4d_offset(pgd, relocated_restore_code);
+	if (p4d_large(*p4d)) {
+		set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
+		goto out;
+	}
+	pud = pud_offset(p4d, relocated_restore_code);
 	if (pud_large(*pud)) {
 		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
-	} else {
-		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
-
-		if (pmd_large(*pmd)) {
-			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
-		} else {
-			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
-
-			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
-		}
+		goto out;
+	}
+	pmd = pmd_offset(pud, relocated_restore_code);
+	if (pmd_large(*pmd)) {
+		set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		goto out;
 	}
+	pte = pte_offset_kernel(pmd, relocated_restore_code);
+	set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+out:
 	__flush_tlb_all();
-
 	return 0;
 }
 
@@ -195,12 +215,12 @@ struct restore_data_record {
 
 #if IS_BUILTIN(CONFIG_CRYPTO_MD5)
 /**
- * get_e820_md5 - calculate md5 according to given e820 map
+ * get_e820_md5 - calculate md5 according to given e820 table
  *
- * @map: the e820 map to be calculated
+ * @table: the e820 table to be calculated
  * @buf: the md5 result to be stored to
  */
-static int get_e820_md5(struct e820map *map, void *buf)
+static int get_e820_md5(struct e820_table *table, void *buf)
 {
 	struct scatterlist sg;
 	struct crypto_ahash *tfm;
@@ -213,10 +233,9 @@ static int get_e820_md5(struct e820map *map, void *buf)
 
 	{
 		AHASH_REQUEST_ON_STACK(req, tfm);
-		size = offsetof(struct e820map, map)
-			+ sizeof(struct e820entry) * map->nr_map;
+		size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries;
 		ahash_request_set_tfm(req, tfm);
-		sg_init_one(&sg, (u8 *)map, size);
+		sg_init_one(&sg, (u8 *)table, size);
 		ahash_request_set_callback(req, 0, NULL, NULL);
 		ahash_request_set_crypt(req, &sg, buf, size);
 
@@ -231,7 +250,7 @@ static int get_e820_md5(struct e820map *map, void *buf)
 
 static void hibernation_e820_save(void *buf)
 {
-	get_e820_md5(e820_saved, buf);
+	get_e820_md5(e820_table_firmware, buf);
 }
 
 static bool hibernation_e820_mismatch(void *buf)
@@ -244,7 +263,7 @@ static bool hibernation_e820_mismatch(void *buf)
 	if (!memcmp(result, buf, MD5_DIGEST_SIZE))
 		return false;
 
-	ret = get_e820_md5(e820_saved, result);
+	ret = get_e820_md5(e820_table_firmware, result);
 	if (ret)
 		return true;
 
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 555b9fa0ad43..7dbdb780264d 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -8,6 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
 targets += purgatory.ro
 
+KASAN_SANITIZE	:= n
 KCOV_INSTRUMENT := n
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 25e068ba3382..470edad96bb9 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -10,21 +10,19 @@
  * Version 2.  See the file COPYING for more details.
  */
 
+#include <linux/bug.h>
+#include <asm/purgatory.h>
+
 #include "sha256.h"
 #include "../boot/string.h"
 
-struct sha_region {
-	unsigned long start;
-	unsigned long len;
-};
-
-unsigned long backup_dest = 0;
-unsigned long backup_src = 0;
-unsigned long backup_sz = 0;
+unsigned long purgatory_backup_dest __section(.kexec-purgatory);
+unsigned long purgatory_backup_src __section(.kexec-purgatory);
+unsigned long purgatory_backup_sz __section(.kexec-purgatory);
 
-u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
 
-struct sha_region sha_regions[16] = {};
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
 
 /*
  * On x86, second kernel requries first 640K of memory to boot. Copy
@@ -33,26 +31,28 @@ struct sha_region sha_regions[16] = {};
  */
 static int copy_backup_region(void)
 {
-	if (backup_dest)
-		memcpy((void *)backup_dest, (void *)backup_src, backup_sz);
-
+	if (purgatory_backup_dest) {
+		memcpy((void *)purgatory_backup_dest,
+		       (void *)purgatory_backup_src, purgatory_backup_sz);
+	}
 	return 0;
 }
 
-int verify_sha256_digest(void)
+static int verify_sha256_digest(void)
 {
-	struct sha_region *ptr, *end;
+	struct kexec_sha_region *ptr, *end;
 	u8 digest[SHA256_DIGEST_SIZE];
 	struct sha256_state sctx;
 
 	sha256_init(&sctx);
-	end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])];
-	for (ptr = sha_regions; ptr < end; ptr++)
+	end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+
+	for (ptr = purgatory_sha_regions; ptr < end; ptr++)
 		sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
 
 	sha256_final(&sctx, digest);
 
-	if (memcmp(digest, sha256_digest, sizeof(digest)))
+	if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)))
 		return 1;
 
 	return 0;
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index fe3c91ba1bd0..dfae9b9e60b5 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -9,6 +9,7 @@
  * This source code is licensed under the GNU General Public License,
  * Version 2.  See the file COPYING for more details.
  */
+#include <asm/purgatory.h>
 
 	.text
 	.globl purgatory_start
diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h
index bd15a4127735..2867d9825a57 100644
--- a/arch/x86/purgatory/sha256.h
+++ b/arch/x86/purgatory/sha256.h
@@ -10,7 +10,6 @@
 #ifndef SHA256_H
 #define SHA256_H
 
-
 #include <linux/types.h>
 #include <crypto/sha.h>
 
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index 0bc60a308730..2a2d89d39af6 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -7,3 +7,17 @@ config MCE_AMD_INJ
 	  aspects of the MCE handling code.
 
 	  WARNING: Do not even assume this interface is staying stable!
+
+config RAS_CEC
+	bool "Correctable Errors Collector"
+	depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS
+	---help---
+	  This is a small cache which collects correctable memory errors per 4K
+	  page PFN and counts their repeated occurrence. Once the counter for a
+	  PFN overflows, we try to soft-offline that page as we take it to mean
+	  that it has reached a relatively high error count and would probably
+	  be best if we don't use it anymore.
+
+	  Bear in mind that this is absolutely useless if your platform doesn't
+	  have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS.
+
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index e7e7055a8658..46cbbfe03285 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -8,7 +8,7 @@ else
 	BITS := 64
 endif
 
-obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \
+obj-y = bugs_$(BITS).o delay.o fault.o ldt.o \
 	ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \
 	stub_$(BITS).o stub_segv.o \
 	sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \
@@ -16,7 +16,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \
 
 ifeq ($(CONFIG_X86_32),y)
 
-obj-y += checksum_32.o
+obj-y += checksum_32.o syscalls_32.o
 obj-$(CONFIG_ELF_CORE) += elfcore.o
 
 subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index e59eef20647b..b291ca5cf66b 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -78,7 +78,7 @@ static inline int ptrace_set_thread_area(struct task_struct *child, int idx,
         return -ENOSYS;
 }
 
-extern long arch_prctl(struct task_struct *task, int code,
+extern long arch_prctl(struct task_struct *task, int option,
 		       unsigned long __user *addr);
 
 #endif
diff --git a/arch/x86/um/bug.c b/arch/x86/um/bug.c
deleted file mode 100644
index e8034e363d83..000000000000
--- a/arch/x86/um/bug.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL V2
- */
-
-#include <linux/uaccess.h>
-
-/*
- * Mostly copied from i386/x86_86 - eliminated the eip < PAGE_OFFSET because
- * that's not relevant in skas mode.
- */
-
-int is_valid_bugaddr(unsigned long eip)
-{
-	unsigned short ud2;
-
-	if (probe_kernel_address((unsigned short __user *)eip, ud2))
-		return 0;
-
-	return ud2 == 0x0b0f;
-}
diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c
index 96eb2bd28832..8431e87ac333 100644
--- a/arch/x86/um/os-Linux/prctl.c
+++ b/arch/x86/um/os-Linux/prctl.c
@@ -6,7 +6,7 @@
 #include <sys/ptrace.h>
 #include <asm/ptrace.h>
 
-int os_arch_prctl(int pid, int code, unsigned long *addr)
+int os_arch_prctl(int pid, int option, unsigned long *arg2)
 {
-        return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) addr, code);
+	return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option);
 }
diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c
new file mode 100644
index 000000000000..627d68836b16
--- /dev/null
+++ b/arch/x86/um/syscalls_32.c
@@ -0,0 +1,7 @@
+#include <linux/syscalls.h>
+#include <os.h>
+
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
+{
+	return -EINVAL;
+}
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index 10d907098c26..58f51667e2e4 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -7,13 +7,15 @@
 
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <asm/prctl.h> /* XXX This should get the constants from libc */
 #include <os.h>
 
-long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
+long arch_prctl(struct task_struct *task, int option,
+		unsigned long __user *arg2)
 {
-	unsigned long *ptr = addr, tmp;
+	unsigned long *ptr = arg2, tmp;
 	long ret;
 	int pid = task->mm->context.id.u.pid;
 
@@ -30,7 +32,7 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
 	 * arch_prctl is run on the host, then the registers are read
 	 * back.
 	 */
-	switch (code) {
+	switch (option) {
 	case ARCH_SET_FS:
 	case ARCH_SET_GS:
 		ret = restore_registers(pid, &current->thread.regs.regs);
@@ -50,11 +52,11 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
 		ptr = &tmp;
 	}
 
-	ret = os_arch_prctl(pid, code, ptr);
+	ret = os_arch_prctl(pid, option, ptr);
 	if (ret)
 		return ret;
 
-	switch (code) {
+	switch (option) {
 	case ARCH_SET_FS:
 		current->thread.arch.fs = (unsigned long) ptr;
 		ret = save_registers(pid, &current->thread.regs.regs);
@@ -63,19 +65,19 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
 		ret = save_registers(pid, &current->thread.regs.regs);
 		break;
 	case ARCH_GET_FS:
-		ret = put_user(tmp, addr);
+		ret = put_user(tmp, arg2);
 		break;
 	case ARCH_GET_GS:
-		ret = put_user(tmp, addr);
+		ret = put_user(tmp, arg2);
 		break;
 	}
 
 	return ret;
 }
 
-long sys_arch_prctl(int code, unsigned long addr)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
-	return arch_prctl(current, code, (unsigned long __user *) addr);
+	return arch_prctl(current, option, (unsigned long __user *) arg2);
 }
 
 void arch_switch_to(struct task_struct *to)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ec1d5c46e58f..30822e8e64ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -76,6 +76,7 @@
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/cpu.h>
+#include <asm/e820/api.h> 
 
 #ifdef CONFIG_ACPI
 #include <linux/acpi.h>
@@ -710,7 +711,7 @@ static void load_TLS_descriptor(struct thread_struct *t,
 
 	*shadow = t->tls_array[i];
 
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 	maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
 	mc = __xen_mc_entry(0);
 
@@ -1595,7 +1596,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* set up basic CPUID stuff */
 	cpu_detect(&new_cpu_data);
 	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
-	new_cpu_data.wp_works_ok = 1;
 	new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
 #endif
 
@@ -1690,34 +1690,32 @@ static void __init init_pvh_bootparams(void)
 
 	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
 
-	memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map);
-	set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map);
+	memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table);
+	set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table);
 	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
 	if (rc) {
 		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
 		BUG();
 	}
 
-	if (memmap.nr_entries < E820MAX - 1) {
-		pvh_bootparams.e820_map[memmap.nr_entries].addr =
+	if (memmap.nr_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) {
+		pvh_bootparams.e820_table[memmap.nr_entries].addr =
 			ISA_START_ADDRESS;
-		pvh_bootparams.e820_map[memmap.nr_entries].size =
+		pvh_bootparams.e820_table[memmap.nr_entries].size =
 			ISA_END_ADDRESS - ISA_START_ADDRESS;
-		pvh_bootparams.e820_map[memmap.nr_entries].type =
-			E820_RESERVED;
+		pvh_bootparams.e820_table[memmap.nr_entries].type =
+			E820_TYPE_RESERVED;
 		memmap.nr_entries++;
 	} else
 		xen_raw_printk("Warning: Can fit ISA range into e820\n");
 
-	sanitize_e820_map(pvh_bootparams.e820_map,
-			  ARRAY_SIZE(pvh_bootparams.e820_map),
-			  &memmap.nr_entries);
-
 	pvh_bootparams.e820_entries = memmap.nr_entries;
 	for (i = 0; i < pvh_bootparams.e820_entries; i++)
-		e820_add_region(pvh_bootparams.e820_map[i].addr,
-				pvh_bootparams.e820_map[i].size,
-				pvh_bootparams.e820_map[i].type);
+		e820__range_add(pvh_bootparams.e820_table[i].addr,
+				pvh_bootparams.e820_table[i].size,
+				pvh_bootparams.e820_table[i].type);
+
+	e820__update_table(e820_table);
 
 	pvh_bootparams.hdr.cmd_line_ptr =
 		pvh_start_info.cmdline_paddr;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 37cb5aad71de..f226038a39ca 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -58,7 +58,7 @@
 #include <asm/mmu_context.h>
 #include <asm/setup.h>
 #include <asm/paravirt.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/linkage.h>
 #include <asm/page.h>
 #include <asm/init.h>
@@ -535,40 +535,41 @@ static pgd_t *xen_get_user_pgd(pgd_t *pgd)
 	return user_ptr;
 }
 
-static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+static void __xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 {
 	struct mmu_update u;
 
 	u.ptr = virt_to_machine(ptr).maddr;
-	u.val = pgd_val_ma(val);
+	u.val = p4d_val_ma(val);
 	xen_extend_mmu_update(&u);
 }
 
 /*
- * Raw hypercall-based set_pgd, intended for in early boot before
+ * Raw hypercall-based set_p4d, intended for in early boot before
  * there's a page structure.  This implies:
  *  1. The only existing pagetable is the kernel's
  *  2. It is always pinned
  *  3. It has no user pagetable attached to it
  */
-static void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 {
 	preempt_disable();
 
 	xen_mc_batch();
 
-	__xen_set_pgd_hyper(ptr, val);
+	__xen_set_p4d_hyper(ptr, val);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 
 	preempt_enable();
 }
 
-static void xen_set_pgd(pgd_t *ptr, pgd_t val)
+static void xen_set_p4d(p4d_t *ptr, p4d_t val)
 {
-	pgd_t *user_ptr = xen_get_user_pgd(ptr);
+	pgd_t *user_ptr = xen_get_user_pgd((pgd_t *)ptr);
+	pgd_t pgd_val;
 
-	trace_xen_mmu_set_pgd(ptr, user_ptr, val);
+	trace_xen_mmu_set_p4d(ptr, (p4d_t *)user_ptr, val);
 
 	/* If page is not pinned, we can just update the entry
 	   directly */
@@ -576,7 +577,8 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 		*ptr = val;
 		if (user_ptr) {
 			WARN_ON(xen_page_pinned(user_ptr));
-			*user_ptr = val;
+			pgd_val.pgd = p4d_val_ma(val);
+			*user_ptr = pgd_val;
 		}
 		return;
 	}
@@ -585,14 +587,72 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 	   user updates together. */
 	xen_mc_batch();
 
-	__xen_set_pgd_hyper(ptr, val);
+	__xen_set_p4d_hyper(ptr, val);
 	if (user_ptr)
-		__xen_set_pgd_hyper(user_ptr, val);
+		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 #endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
+static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
+		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
+		bool last, unsigned long limit)
+{
+	int i, nr, flush = 0;
+
+	nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD;
+	for (i = 0; i < nr; i++) {
+		if (!pmd_none(pmd[i]))
+			flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE);
+	}
+	return flush;
+}
+
+static int xen_pud_walk(struct mm_struct *mm, pud_t *pud,
+		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
+		bool last, unsigned long limit)
+{
+	int i, nr, flush = 0;
+
+	nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD;
+	for (i = 0; i < nr; i++) {
+		pmd_t *pmd;
+
+		if (pud_none(pud[i]))
+			continue;
+
+		pmd = pmd_offset(&pud[i], 0);
+		if (PTRS_PER_PMD > 1)
+			flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
+		flush |= xen_pmd_walk(mm, pmd, func,
+				last && i == nr - 1, limit);
+	}
+	return flush;
+}
+
+static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
+		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
+		bool last, unsigned long limit)
+{
+	int i, nr, flush = 0;
+
+	nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D;
+	for (i = 0; i < nr; i++) {
+		pud_t *pud;
+
+		if (p4d_none(p4d[i]))
+			continue;
+
+		pud = pud_offset(&p4d[i], 0);
+		if (PTRS_PER_PUD > 1)
+			flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
+		flush |= xen_pud_walk(mm, pud, func,
+				last && i == nr - 1, limit);
+	}
+	return flush;
+}
+
 /*
  * (Yet another) pagetable walker.  This one is intended for pinning a
  * pagetable.  This means that it walks a pagetable and calls the
@@ -613,10 +673,8 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
 				      enum pt_level),
 			  unsigned long limit)
 {
-	int flush = 0;
+	int i, nr, flush = 0;
 	unsigned hole_low, hole_high;
-	unsigned pgdidx_limit, pudidx_limit, pmdidx_limit;
-	unsigned pgdidx, pudidx, pmdidx;
 
 	/* The limit is the last byte to be touched */
 	limit--;
@@ -633,65 +691,22 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
 	hole_low = pgd_index(USER_LIMIT);
 	hole_high = pgd_index(PAGE_OFFSET);
 
-	pgdidx_limit = pgd_index(limit);
-#if PTRS_PER_PUD > 1
-	pudidx_limit = pud_index(limit);
-#else
-	pudidx_limit = 0;
-#endif
-#if PTRS_PER_PMD > 1
-	pmdidx_limit = pmd_index(limit);
-#else
-	pmdidx_limit = 0;
-#endif
-
-	for (pgdidx = 0; pgdidx <= pgdidx_limit; pgdidx++) {
-		pud_t *pud;
+	nr = pgd_index(limit) + 1;
+	for (i = 0; i < nr; i++) {
+		p4d_t *p4d;
 
-		if (pgdidx >= hole_low && pgdidx < hole_high)
+		if (i >= hole_low && i < hole_high)
 			continue;
 
-		if (!pgd_val(pgd[pgdidx]))
+		if (pgd_none(pgd[i]))
 			continue;
 
-		pud = pud_offset(&pgd[pgdidx], 0);
-
-		if (PTRS_PER_PUD > 1) /* not folded */
-			flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
-
-		for (pudidx = 0; pudidx < PTRS_PER_PUD; pudidx++) {
-			pmd_t *pmd;
-
-			if (pgdidx == pgdidx_limit &&
-			    pudidx > pudidx_limit)
-				goto out;
-
-			if (pud_none(pud[pudidx]))
-				continue;
-
-			pmd = pmd_offset(&pud[pudidx], 0);
-
-			if (PTRS_PER_PMD > 1) /* not folded */
-				flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
-
-			for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) {
-				struct page *pte;
-
-				if (pgdidx == pgdidx_limit &&
-				    pudidx == pudidx_limit &&
-				    pmdidx > pmdidx_limit)
-					goto out;
-
-				if (pmd_none(pmd[pmdidx]))
-					continue;
-
-				pte = pmd_page(pmd[pmdidx]);
-				flush |= (*func)(mm, pte, PT_PTE);
-			}
-		}
+		p4d = p4d_offset(&pgd[i], 0);
+		if (PTRS_PER_P4D > 1)
+			flush |= (*func)(mm, virt_to_page(p4d), PT_P4D);
+		flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
 	}
 
-out:
 	/* Do the top level last, so that the callbacks can use it as
 	   a cue to do final things like tlb flushes. */
 	flush |= (*func)(mm, virt_to_page(pgd), PT_PGD);
@@ -1150,57 +1165,97 @@ static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
 	xen_free_ro_pages(pa, PAGE_SIZE);
 }
 
+static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin)
+{
+	unsigned long pa;
+	pte_t *pte_tbl;
+	int i;
+
+	if (pmd_large(*pmd)) {
+		pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
+		xen_free_ro_pages(pa, PMD_SIZE);
+		return;
+	}
+
+	pte_tbl = pte_offset_kernel(pmd, 0);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		if (pte_none(pte_tbl[i]))
+			continue;
+		pa = pte_pfn(pte_tbl[i]) << PAGE_SHIFT;
+		xen_free_ro_pages(pa, PAGE_SIZE);
+	}
+	set_pmd(pmd, __pmd(0));
+	xen_cleanmfnmap_free_pgtbl(pte_tbl, unpin);
+}
+
+static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin)
+{
+	unsigned long pa;
+	pmd_t *pmd_tbl;
+	int i;
+
+	if (pud_large(*pud)) {
+		pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
+		xen_free_ro_pages(pa, PUD_SIZE);
+		return;
+	}
+
+	pmd_tbl = pmd_offset(pud, 0);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (pmd_none(pmd_tbl[i]))
+			continue;
+		xen_cleanmfnmap_pmd(pmd_tbl + i, unpin);
+	}
+	set_pud(pud, __pud(0));
+	xen_cleanmfnmap_free_pgtbl(pmd_tbl, unpin);
+}
+
+static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin)
+{
+	unsigned long pa;
+	pud_t *pud_tbl;
+	int i;
+
+	if (p4d_large(*p4d)) {
+		pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK;
+		xen_free_ro_pages(pa, P4D_SIZE);
+		return;
+	}
+
+	pud_tbl = pud_offset(p4d, 0);
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (pud_none(pud_tbl[i]))
+			continue;
+		xen_cleanmfnmap_pud(pud_tbl + i, unpin);
+	}
+	set_p4d(p4d, __p4d(0));
+	xen_cleanmfnmap_free_pgtbl(pud_tbl, unpin);
+}
+
 /*
  * Since it is well isolated we can (and since it is perhaps large we should)
  * also free the page tables mapping the initial P->M table.
  */
 static void __init xen_cleanmfnmap(unsigned long vaddr)
 {
-	unsigned long va = vaddr & PMD_MASK;
-	unsigned long pa;
-	pgd_t *pgd = pgd_offset_k(va);
-	pud_t *pud_page = pud_offset(pgd, 0);
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgd;
+	p4d_t *p4d;
 	unsigned int i;
 	bool unpin;
 
 	unpin = (vaddr == 2 * PGDIR_SIZE);
-	set_pgd(pgd, __pgd(0));
-	do {
-		pud = pud_page + pud_index(va);
-		if (pud_none(*pud)) {
-			va += PUD_SIZE;
-		} else if (pud_large(*pud)) {
-			pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
-			xen_free_ro_pages(pa, PUD_SIZE);
-			va += PUD_SIZE;
-		} else {
-			pmd = pmd_offset(pud, va);
-			if (pmd_large(*pmd)) {
-				pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
-				xen_free_ro_pages(pa, PMD_SIZE);
-			} else if (!pmd_none(*pmd)) {
-				pte = pte_offset_kernel(pmd, va);
-				set_pmd(pmd, __pmd(0));
-				for (i = 0; i < PTRS_PER_PTE; ++i) {
-					if (pte_none(pte[i]))
-						break;
-					pa = pte_pfn(pte[i]) << PAGE_SHIFT;
-					xen_free_ro_pages(pa, PAGE_SIZE);
-				}
-				xen_cleanmfnmap_free_pgtbl(pte, unpin);
-			}
-			va += PMD_SIZE;
-			if (pmd_index(va))
-				continue;
-			set_pud(pud, __pud(0));
-			xen_cleanmfnmap_free_pgtbl(pmd, unpin);
-		}
-
-	} while (pud_index(va) || pmd_index(va));
-	xen_cleanmfnmap_free_pgtbl(pud_page, unpin);
+	vaddr &= PMD_MASK;
+	pgd = pgd_offset_k(vaddr);
+	p4d = p4d_offset(pgd, 0);
+	for (i = 0; i < PTRS_PER_P4D; i++) {
+		if (p4d_none(p4d[i]))
+			continue;
+		xen_cleanmfnmap_p4d(p4d + i, unpin);
+	}
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		set_pgd(pgd, __pgd(0));
+		xen_cleanmfnmap_free_pgtbl(p4d, unpin);
+	}
 }
 
 static void __init xen_pagetable_p2m_free(void)
@@ -1538,7 +1593,6 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
 	}
 #endif
-
 	return ret;
 }
 
@@ -1730,7 +1784,7 @@ static void xen_release_pmd(unsigned long pfn)
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
@@ -2071,21 +2125,27 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
  */
 void __init xen_relocate_p2m(void)
 {
-	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys;
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys;
 	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
-	int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
+	int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d;
 	pte_t *pt;
 	pmd_t *pmd;
 	pud_t *pud;
+	p4d_t *p4d = NULL;
 	pgd_t *pgd;
 	unsigned long *new_p2m;
+	int save_pud;
 
 	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
 	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
 	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
 	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
-	n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
-	n_frames = n_pte + n_pt + n_pmd + n_pud;
+	n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT;
+	if (PTRS_PER_P4D > 1)
+		n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
+	else
+		n_p4d = 0;
+	n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d;
 
 	new_area = xen_find_free_area(PFN_PHYS(n_frames));
 	if (!new_area) {
@@ -2101,55 +2161,76 @@ void __init xen_relocate_p2m(void)
 	 * To avoid any possible virtual address collision, just use
 	 * 2 * PUD_SIZE for the new area.
 	 */
-	pud_phys = new_area;
+	p4d_phys = new_area;
+	pud_phys = p4d_phys + PFN_PHYS(n_p4d);
 	pmd_phys = pud_phys + PFN_PHYS(n_pud);
 	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
 	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
 
 	pgd = __va(read_cr3());
 	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
-	for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
-		pud = early_memremap(pud_phys, PAGE_SIZE);
-		clear_page(pud);
-		for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
-		     idx_pmd++) {
-			pmd = early_memremap(pmd_phys, PAGE_SIZE);
-			clear_page(pmd);
-			for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
-			     idx_pt++) {
-				pt = early_memremap(pt_phys, PAGE_SIZE);
-				clear_page(pt);
-				for (idx_pte = 0;
-				     idx_pte < min(n_pte, PTRS_PER_PTE);
-				     idx_pte++) {
-					set_pte(pt + idx_pte,
-						pfn_pte(p2m_pfn, PAGE_KERNEL));
-					p2m_pfn++;
+	idx_p4d = 0;
+	save_pud = n_pud;
+	do {
+		if (n_p4d > 0) {
+			p4d = early_memremap(p4d_phys, PAGE_SIZE);
+			clear_page(p4d);
+			n_pud = min(save_pud, PTRS_PER_P4D);
+		}
+		for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
+			pud = early_memremap(pud_phys, PAGE_SIZE);
+			clear_page(pud);
+			for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
+				 idx_pmd++) {
+				pmd = early_memremap(pmd_phys, PAGE_SIZE);
+				clear_page(pmd);
+				for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
+					 idx_pt++) {
+					pt = early_memremap(pt_phys, PAGE_SIZE);
+					clear_page(pt);
+					for (idx_pte = 0;
+						 idx_pte < min(n_pte, PTRS_PER_PTE);
+						 idx_pte++) {
+						set_pte(pt + idx_pte,
+								pfn_pte(p2m_pfn, PAGE_KERNEL));
+						p2m_pfn++;
+					}
+					n_pte -= PTRS_PER_PTE;
+					early_memunmap(pt, PAGE_SIZE);
+					make_lowmem_page_readonly(__va(pt_phys));
+					pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
+							PFN_DOWN(pt_phys));
+					set_pmd(pmd + idx_pt,
+							__pmd(_PAGE_TABLE | pt_phys));
+					pt_phys += PAGE_SIZE;
 				}
-				n_pte -= PTRS_PER_PTE;
-				early_memunmap(pt, PAGE_SIZE);
-				make_lowmem_page_readonly(__va(pt_phys));
-				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
-						  PFN_DOWN(pt_phys));
-				set_pmd(pmd + idx_pt,
-					__pmd(_PAGE_TABLE | pt_phys));
-				pt_phys += PAGE_SIZE;
+				n_pt -= PTRS_PER_PMD;
+				early_memunmap(pmd, PAGE_SIZE);
+				make_lowmem_page_readonly(__va(pmd_phys));
+				pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
+						PFN_DOWN(pmd_phys));
+				set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+				pmd_phys += PAGE_SIZE;
 			}
-			n_pt -= PTRS_PER_PMD;
-			early_memunmap(pmd, PAGE_SIZE);
-			make_lowmem_page_readonly(__va(pmd_phys));
-			pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
-					  PFN_DOWN(pmd_phys));
-			set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
-			pmd_phys += PAGE_SIZE;
+			n_pmd -= PTRS_PER_PUD;
+			early_memunmap(pud, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(pud_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+			if (n_p4d > 0)
+				set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys));
+			else
+				set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
+			pud_phys += PAGE_SIZE;
 		}
-		n_pmd -= PTRS_PER_PUD;
-		early_memunmap(pud, PAGE_SIZE);
-		make_lowmem_page_readonly(__va(pud_phys));
-		pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
-		set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
-		pud_phys += PAGE_SIZE;
-	}
+		if (n_p4d > 0) {
+			save_pud -= PTRS_PER_P4D;
+			early_memunmap(p4d, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(p4d_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys));
+			set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys));
+			p4d_phys += PAGE_SIZE;
+		}
+	} while (++idx_p4d < n_p4d);
 
 	/* Now copy the old p2m info to the new area. */
 	memcpy(new_p2m, xen_p2m_addr, size);
@@ -2326,6 +2407,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
+	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
@@ -2378,8 +2460,8 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
-#if CONFIG_PGTABLE_LEVELS == 4
-	pv_mmu_ops.set_pgd = xen_set_pgd;
+#if CONFIG_PGTABLE_LEVELS >= 4
+	pv_mmu_ops.set_p4d = xen_set_p4d;
 #endif
 
 	/* This will work as long as patching hasn't happened yet
@@ -2388,7 +2470,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
 	pv_mmu_ops.release_pte = xen_release_pte;
 	pv_mmu_ops.release_pmd = xen_release_pmd;
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
@@ -2454,10 +2536,10 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
 	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
 	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
-	.set_pgd = xen_set_pgd_hyper,
+	.set_p4d = xen_set_p4d_hyper,
 
 	.alloc_pud = xen_alloc_pmd_init,
 	.release_pud = xen_release_pmd_init,
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index 73809bb951b4..3fe2b3292915 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -5,6 +5,7 @@
 
 enum pt_level {
 	PT_PGD,
+	PT_P4D,
 	PT_PUD,
 	PT_PMD,
 	PT_PTE
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a8c306cf8868..a5bf7c451435 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -14,7 +14,7 @@
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/setup.h>
 #include <asm/acpi.h>
 #include <asm/numa.h>
@@ -41,8 +41,7 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 unsigned long xen_released_pages;
 
 /* E820 map used during setting up memory. */
-static struct e820entry xen_e820_map[E820_X_MAX] __initdata;
-static u32 xen_e820_map_entries __initdata;
+static struct e820_table xen_e820_table __initdata;
 
 /*
  * Buffer used to remap identity mapped pages. We only need the virtual space.
@@ -198,15 +197,15 @@ void __init xen_inv_extra_mem(void)
  */
 static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn)
 {
-	const struct e820entry *entry = xen_e820_map;
+	const struct e820_entry *entry = xen_e820_table.entries;
 	unsigned int i;
 	unsigned long done = 0;
 
-	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
+	for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) {
 		unsigned long s_pfn;
 		unsigned long e_pfn;
 
-		if (entry->type != E820_RAM)
+		if (entry->type != E820_TYPE_RAM)
 			continue;
 
 		e_pfn = PFN_DOWN(entry->addr + entry->size);
@@ -457,7 +456,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
 {
 	phys_addr_t start = 0;
 	unsigned long ret_val = 0;
-	const struct e820entry *entry = xen_e820_map;
+	const struct e820_entry *entry = xen_e820_table.entries;
 	int i;
 
 	/*
@@ -471,13 +470,13 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
 	 * example) the DMI tables in a reserved region that begins on
 	 * a non-page boundary.
 	 */
-	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
+	for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) {
 		phys_addr_t end = entry->addr + entry->size;
-		if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) {
+		if (entry->type == E820_TYPE_RAM || i == xen_e820_table.nr_entries - 1) {
 			unsigned long start_pfn = PFN_DOWN(start);
 			unsigned long end_pfn = PFN_UP(end);
 
-			if (entry->type == E820_RAM)
+			if (entry->type == E820_TYPE_RAM)
 				end_pfn = PFN_UP(entry->addr);
 
 			if (start_pfn < end_pfn)
@@ -591,28 +590,28 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start,
 	phys_addr_t end = start + size;
 
 	/* Align RAM regions to page boundaries. */
-	if (type == E820_RAM) {
+	if (type == E820_TYPE_RAM) {
 		start = PAGE_ALIGN(start);
 		end &= ~((phys_addr_t)PAGE_SIZE - 1);
 	}
 
-	e820_add_region(start, end - start, type);
+	e820__range_add(start, end - start, type);
 }
 
 static void __init xen_ignore_unusable(void)
 {
-	struct e820entry *entry = xen_e820_map;
+	struct e820_entry *entry = xen_e820_table.entries;
 	unsigned int i;
 
-	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
-		if (entry->type == E820_UNUSABLE)
-			entry->type = E820_RAM;
+	for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) {
+		if (entry->type == E820_TYPE_UNUSABLE)
+			entry->type = E820_TYPE_RAM;
 	}
 }
 
 bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
 {
-	struct e820entry *entry;
+	struct e820_entry *entry;
 	unsigned mapcnt;
 	phys_addr_t end;
 
@@ -620,10 +619,10 @@ bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
 		return false;
 
 	end = start + size;
-	entry = xen_e820_map;
+	entry = xen_e820_table.entries;
 
-	for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) {
-		if (entry->type == E820_RAM && entry->addr <= start &&
+	for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) {
+		if (entry->type == E820_TYPE_RAM && entry->addr <= start &&
 		    (entry->addr + entry->size) >= end)
 			return false;
 
@@ -645,10 +644,10 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size)
 {
 	unsigned mapcnt;
 	phys_addr_t addr, start;
-	struct e820entry *entry = xen_e820_map;
+	struct e820_entry *entry = xen_e820_table.entries;
 
-	for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) {
-		if (entry->type != E820_RAM || entry->size < size)
+	for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++, entry++) {
+		if (entry->type != E820_TYPE_RAM || entry->size < size)
 			continue;
 		start = entry->addr;
 		for (addr = start; addr < start + size; addr += PAGE_SIZE) {
@@ -750,8 +749,8 @@ char * __init xen_memory_setup(void)
 	max_pfn = min(max_pfn, xen_start_info->nr_pages);
 	mem_end = PFN_PHYS(max_pfn);
 
-	memmap.nr_entries = ARRAY_SIZE(xen_e820_map);
-	set_xen_guest_handle(memmap.buffer, xen_e820_map);
+	memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
+	set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
 
 	op = xen_initial_domain() ?
 		XENMEM_machine_memory_map :
@@ -760,16 +759,16 @@ char * __init xen_memory_setup(void)
 	if (rc == -ENOSYS) {
 		BUG_ON(xen_initial_domain());
 		memmap.nr_entries = 1;
-		xen_e820_map[0].addr = 0ULL;
-		xen_e820_map[0].size = mem_end;
+		xen_e820_table.entries[0].addr = 0ULL;
+		xen_e820_table.entries[0].size = mem_end;
 		/* 8MB slack (to balance backend allocations). */
-		xen_e820_map[0].size += 8ULL << 20;
-		xen_e820_map[0].type = E820_RAM;
+		xen_e820_table.entries[0].size += 8ULL << 20;
+		xen_e820_table.entries[0].type = E820_TYPE_RAM;
 		rc = 0;
 	}
 	BUG_ON(rc);
 	BUG_ON(memmap.nr_entries == 0);
-	xen_e820_map_entries = memmap.nr_entries;
+	xen_e820_table.nr_entries = memmap.nr_entries;
 
 	/*
 	 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
@@ -783,8 +782,7 @@ char * __init xen_memory_setup(void)
 		xen_ignore_unusable();
 
 	/* Make sure the Xen-supplied memory map is well-ordered. */
-	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
-			  &xen_e820_map_entries);
+	e820__update_table(&xen_e820_table);
 
 	max_pages = xen_get_max_pages();
 
@@ -811,15 +809,15 @@ char * __init xen_memory_setup(void)
 	extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
 			   extra_pages, max_pages - max_pfn);
 	i = 0;
-	addr = xen_e820_map[0].addr;
-	size = xen_e820_map[0].size;
-	while (i < xen_e820_map_entries) {
+	addr = xen_e820_table.entries[0].addr;
+	size = xen_e820_table.entries[0].size;
+	while (i < xen_e820_table.nr_entries) {
 		bool discard = false;
 
 		chunk_size = size;
-		type = xen_e820_map[i].type;
+		type = xen_e820_table.entries[i].type;
 
-		if (type == E820_RAM) {
+		if (type == E820_TYPE_RAM) {
 			if (addr < mem_end) {
 				chunk_size = min(size, mem_end - addr);
 			} else if (extra_pages) {
@@ -840,9 +838,9 @@ char * __init xen_memory_setup(void)
 		size -= chunk_size;
 		if (size == 0) {
 			i++;
-			if (i < xen_e820_map_entries) {
-				addr = xen_e820_map[i].addr;
-				size = xen_e820_map[i].size;
+			if (i < xen_e820_table.nr_entries) {
+				addr = xen_e820_table.entries[i].addr;
+				size = xen_e820_table.entries[i].size;
 			}
 		}
 	}
@@ -858,10 +856,9 @@ char * __init xen_memory_setup(void)
 	 * reserve ISA memory anyway because too many things poke
 	 * about in there.
 	 */
-	e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
-			E820_RESERVED);
+	e820__range_add(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_TYPE_RESERVED);
 
-	sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+	e820__update_table(e820_table);
 
 	/*
 	 * Check whether the kernel itself conflicts with the target E820 map.
@@ -915,6 +912,37 @@ char * __init xen_memory_setup(void)
 }
 
 /*
+ * Machine specific memory setup for auto-translated guests.
+ */
+char * __init xen_auto_xlated_memory_setup(void)
+{
+	struct xen_memory_map memmap;
+	int i;
+	int rc;
+
+	memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
+	set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
+
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc < 0)
+		panic("No memory map (%d)\n", rc);
+
+	xen_e820_table.nr_entries = memmap.nr_entries;
+
+	e820__update_table(&xen_e820_table);
+
+	for (i = 0; i < xen_e820_table.nr_entries; i++)
+		e820__range_add(xen_e820_table.entries[i].addr, xen_e820_table.entries[i].size, xen_e820_table.entries[i].type);
+
+	/* Remove p2m info, it is not needed. */
+	xen_start_info->mfn_list = 0;
+	xen_start_info->first_p2m_pfn = 0;
+	xen_start_info->nr_p2m_frames = 0;
+
+	return "Xen";
+}
+
+/*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
  * can have un-truncated segments, so wrapping around is allowed.
@@ -999,8 +1027,8 @@ void __init xen_pvmmu_arch_setup(void)
 void __init xen_arch_setup(void)
 {
 	xen_panic_handler_init();
-
-	xen_pvmmu_arch_setup();
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		xen_pvmmu_arch_setup();
 
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7ff2f1bfb7ec..eaa36162ed4a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -392,7 +392,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	if (ctxt == NULL)
 		return -ENOMEM;
 
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 
 #ifdef CONFIG_X86_32
 	ctxt->user_regs.fs = __KERNEL_PERCPU;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 1e69956d7852..7a3089285c59 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -209,7 +209,9 @@ static const struct clock_event_device xen_timerop_clockevent = {
 	.features		= CLOCK_EVT_FEAT_ONESHOT,
 
 	.max_delta_ns		= 0xffffffff,
+	.max_delta_ticks	= 0xffffffff,
 	.min_delta_ns		= TIMER_SLOP,
+	.min_delta_ticks	= TIMER_SLOP,
 
 	.mult			= 1,
 	.shift			= 0,
@@ -268,7 +270,9 @@ static const struct clock_event_device xen_vcpuop_clockevent = {
 	.features = CLOCK_EVT_FEAT_ONESHOT,
 
 	.max_delta_ns = 0xffffffff,
+	.max_delta_ticks = 0xffffffff,
 	.min_delta_ns = TIMER_SLOP,
+	.min_delta_ticks = TIMER_SLOP,
 
 	.mult = 1,
 	.shift = 0,
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index f41408c53fe1..cc23e9ecc6bb 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += extable.h
 generic-y += fcntl.h
 generic-y += hardirq.h
 generic-y += ioctl.h
diff --git a/arch/xtensa/include/asm/asm-uaccess.h b/arch/xtensa/include/asm/asm-uaccess.h
index a7a110039786..dfdf9fae1f84 100644
--- a/arch/xtensa/include/asm/asm-uaccess.h
+++ b/arch/xtensa/include/asm/asm-uaccess.h
@@ -19,9 +19,6 @@
 #include <linux/errno.h>
 #include <asm/types.h>
 
-#define VERIFY_READ    0
-#define VERIFY_WRITE   1
-
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor.h>
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index 976b1d70edbc..4ddbfd57a7c8 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -164,8 +164,21 @@ void copy_user_highpage(struct page *to, struct page *from,
 
 #define ARCH_PFN_OFFSET		(PHYS_OFFSET >> PAGE_SHIFT)
 
+#ifdef CONFIG_MMU
+static inline unsigned long ___pa(unsigned long va)
+{
+	unsigned long off = va - PAGE_OFFSET;
+
+	if (off >= XCHAL_KSEG_SIZE)
+		off -= XCHAL_KSEG_SIZE;
+
+	return off + PHYS_OFFSET;
+}
+#define __pa(x)	___pa((unsigned long)(x))
+#else
 #define __pa(x)	\
 	((unsigned long) (x) - PAGE_OFFSET + PHYS_OFFSET)
+#endif
 #define __va(x)	\
 	((void *)((unsigned long) (x) - PHYS_OFFSET + PAGE_OFFSET))
 #define pfn_valid(pfn) \
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 8aa0e0d9cbb2..30dd5b2e4ad5 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -11,6 +11,7 @@
 #ifndef _XTENSA_PGTABLE_H
 #define _XTENSA_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/page.h>
 #include <asm/kmem_layout.h>
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index 848a3d736bcb..2e7bac0d4b2c 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -16,14 +16,9 @@
 #ifndef _XTENSA_UACCESS_H
 #define _XTENSA_UACCESS_H
 
-#include <linux/errno.h>
 #include <linux/prefetch.h>
 #include <asm/types.h>
-
-#define VERIFY_READ    0
-#define VERIFY_WRITE   1
-
-#include <linux/sched.h>
+#include <asm/extable.h>
 
 /*
  * The fs value determines whether argument validity checking should
@@ -43,7 +38,7 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
 #define __user_ok(addr, size) \
 		(((size) <= TASK_SIZE)&&((addr) <= TASK_SIZE-(size)))
 #define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
@@ -239,60 +234,22 @@ __asm__ __volatile__(			\
  * Copy to/from user space
  */
 
-/*
- * We use a generic, arbitrary-sized copy subroutine.  The Xtensa
- * architecture would cause heavy code bloat if we tried to inline
- * these functions and provide __constant_copy_* equivalents like the
- * i386 versions.  __xtensa_copy_user is quite efficient.  See the
- * .fixup section of __xtensa_copy_user for a discussion on the
- * X_zeroing equivalents for Xtensa.
- */
-
 extern unsigned __xtensa_copy_user(void *to, const void *from, unsigned n);
-#define __copy_user(to, from, size) __xtensa_copy_user(to, from, size)
-
 
 static inline unsigned long
-__generic_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	return __copy_user(to, from, n);
-}
-
-static inline unsigned long
-__generic_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
-{
-	return __copy_user(to, from, n);
+	prefetchw(to);
+	return __xtensa_copy_user(to, (__force const void *)from, n);
 }
-
 static inline unsigned long
-__generic_copy_to_user(void *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	prefetch(from);
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_user(to, from, n);
-	return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void *from, unsigned long n)
-{
-	prefetchw(to);
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_user(to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
+	return __xtensa_copy_user((__force void *)to, from, n);
 }
-
-#define copy_to_user(to, from, n) __generic_copy_to_user((to), (from), (n))
-#define copy_from_user(to, from, n) __generic_copy_from_user((to), (from), (n))
-#define __copy_to_user(to, from, n) \
-	__generic_copy_to_user_nocheck((to), (from), (n))
-#define __copy_from_user(to, from, n) \
-	__generic_copy_from_user_nocheck((to), (from), (n))
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
 /*
  * We need to return the number of bytes not cleared.  Our memset()
@@ -348,10 +305,4 @@ static inline long strnlen_user(const char *str, long len)
 	return __strnlen_user(str, len);
 }
 
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
 #endif	/* _XTENSA_UACCESS_H */
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 9fdbe1fe0473..1eb6d2fe70d3 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -103,4 +103,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index cd400af4a6b2..6be7eb27fd29 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -774,7 +774,10 @@ __SYSCALL(349, sys_pkey_alloc, 2)
 #define __NR_pkey_free				350
 __SYSCALL(350, sys_pkey_free, 1)
 
-#define __NR_syscall_count			351
+#define __NR_statx				351
+__SYSCALL(351, sys_statx, 5)
+
+#define __NR_syscall_count			352
 
 /*
  * sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index c82c43bff296..bae697a06a98 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -483,10 +483,8 @@ void show_regs(struct pt_regs * regs)
 
 static int show_trace_cb(struct stackframe *frame, void *data)
 {
-	if (kernel_text_address(frame->pc)) {
-		pr_cont(" [<%08lx>]", frame->pc);
-		print_symbol(" %s\n", frame->pc);
-	}
+	if (kernel_text_address(frame->pc))
+		pr_cont(" [<%08lx>] %pB\n", frame->pc, (void *)frame->pc);
 	return 0;
 }
 
diff --git a/arch/xtensa/lib/usercopy.S b/arch/xtensa/lib/usercopy.S
index 7ea4dd68893e..d9cd766bde3e 100644
--- a/arch/xtensa/lib/usercopy.S
+++ b/arch/xtensa/lib/usercopy.S
@@ -102,9 +102,9 @@ __xtensa_copy_user:
 	bltui	a4, 7, .Lbytecopy	# do short copies byte by byte
 
 	# copy 1 byte
-	EX(l8ui, a6, a3, 0, l_fixup)
+	EX(l8ui, a6, a3, 0, fixup)
 	addi	a3, a3,  1
-	EX(s8i, a6, a5,  0, s_fixup)
+	EX(s8i, a6, a5,  0, fixup)
 	addi	a5, a5,  1
 	addi	a4, a4, -1
 	bbci.l	a5, 1, .Ldstaligned	# if dst is now aligned, then
@@ -112,11 +112,11 @@ __xtensa_copy_user:
 .Ldst2mod4:	# dst 16-bit aligned
 	# copy 2 bytes
 	bltui	a4, 6, .Lbytecopy	# do short copies byte by byte
-	EX(l8ui, a6, a3, 0, l_fixup)
-	EX(l8ui, a7, a3, 1, l_fixup)
+	EX(l8ui, a6, a3, 0, fixup)
+	EX(l8ui, a7, a3, 1, fixup)
 	addi	a3, a3,  2
-	EX(s8i, a6, a5,  0, s_fixup)
-	EX(s8i, a7, a5,  1, s_fixup)
+	EX(s8i, a6, a5,  0, fixup)
+	EX(s8i, a7, a5,  1, fixup)
 	addi	a5, a5,  2
 	addi	a4, a4, -2
 	j	.Ldstaligned	# dst is now aligned, return to main algorithm
@@ -135,9 +135,9 @@ __xtensa_copy_user:
 	add	a7, a3, a4	# a7 = end address for source
 #endif /* !XCHAL_HAVE_LOOPS */
 .Lnextbyte:
-	EX(l8ui, a6, a3, 0, l_fixup)
+	EX(l8ui, a6, a3, 0, fixup)
 	addi	a3, a3, 1
-	EX(s8i, a6, a5, 0, s_fixup)
+	EX(s8i, a6, a5, 0, fixup)
 	addi	a5, a5, 1
 #if !XCHAL_HAVE_LOOPS
 	blt	a3, a7, .Lnextbyte
@@ -161,15 +161,15 @@ __xtensa_copy_user:
 	add	a8, a8, a3	# a8 = end of last 16B source chunk
 #endif /* !XCHAL_HAVE_LOOPS */
 .Loop1:
-	EX(l32i, a6, a3,  0, l_fixup)
-	EX(l32i, a7, a3,  4, l_fixup)
-	EX(s32i, a6, a5,  0, s_fixup)
-	EX(l32i, a6, a3,  8, l_fixup)
-	EX(s32i, a7, a5,  4, s_fixup)
-	EX(l32i, a7, a3, 12, l_fixup)
-	EX(s32i, a6, a5,  8, s_fixup)
+	EX(l32i, a6, a3,  0, fixup)
+	EX(l32i, a7, a3,  4, fixup)
+	EX(s32i, a6, a5,  0, fixup)
+	EX(l32i, a6, a3,  8, fixup)
+	EX(s32i, a7, a5,  4, fixup)
+	EX(l32i, a7, a3, 12, fixup)
+	EX(s32i, a6, a5,  8, fixup)
 	addi	a3, a3, 16
-	EX(s32i, a7, a5, 12, s_fixup)
+	EX(s32i, a7, a5, 12, fixup)
 	addi	a5, a5, 16
 #if !XCHAL_HAVE_LOOPS
 	blt	a3, a8, .Loop1
@@ -177,31 +177,31 @@ __xtensa_copy_user:
 .Loop1done:
 	bbci.l	a4, 3, .L2
 	# copy 8 bytes
-	EX(l32i, a6, a3,  0, l_fixup)
-	EX(l32i, a7, a3,  4, l_fixup)
+	EX(l32i, a6, a3,  0, fixup)
+	EX(l32i, a7, a3,  4, fixup)
 	addi	a3, a3,  8
-	EX(s32i, a6, a5,  0, s_fixup)
-	EX(s32i, a7, a5,  4, s_fixup)
+	EX(s32i, a6, a5,  0, fixup)
+	EX(s32i, a7, a5,  4, fixup)
 	addi	a5, a5,  8
 .L2:
 	bbci.l	a4, 2, .L3
 	# copy 4 bytes
-	EX(l32i, a6, a3,  0, l_fixup)
+	EX(l32i, a6, a3,  0, fixup)
 	addi	a3, a3,  4
-	EX(s32i, a6, a5,  0, s_fixup)
+	EX(s32i, a6, a5,  0, fixup)
 	addi	a5, a5,  4
 .L3:
 	bbci.l	a4, 1, .L4
 	# copy 2 bytes
-	EX(l16ui, a6, a3,  0, l_fixup)
+	EX(l16ui, a6, a3,  0, fixup)
 	addi	a3, a3,  2
-	EX(s16i,  a6, a5,  0, s_fixup)
+	EX(s16i,  a6, a5,  0, fixup)
 	addi	a5, a5,  2
 .L4:
 	bbci.l	a4, 0, .L5
 	# copy 1 byte
-	EX(l8ui, a6, a3,  0, l_fixup)
-	EX(s8i,  a6, a5,  0, s_fixup)
+	EX(l8ui, a6, a3,  0, fixup)
+	EX(s8i,  a6, a5,  0, fixup)
 .L5:
 	movi	a2, 0		# return success for len bytes copied
 	retw
@@ -217,7 +217,7 @@ __xtensa_copy_user:
 	# copy 16 bytes per iteration for word-aligned dst and unaligned src
 	and	a10, a3, a8	# save unalignment offset for below
 	sub	a3, a3, a10	# align a3 (to avoid sim warnings only; not needed for hardware)
-	EX(l32i, a6, a3, 0, l_fixup)	# load first word
+	EX(l32i, a6, a3, 0, fixup)	# load first word
 #if XCHAL_HAVE_LOOPS
 	loopnez	a7, .Loop2done
 #else /* !XCHAL_HAVE_LOOPS */
@@ -226,19 +226,19 @@ __xtensa_copy_user:
 	add	a12, a12, a3	# a12 = end of last 16B source chunk
 #endif /* !XCHAL_HAVE_LOOPS */
 .Loop2:
-	EX(l32i, a7, a3,  4, l_fixup)
-	EX(l32i, a8, a3,  8, l_fixup)
+	EX(l32i, a7, a3,  4, fixup)
+	EX(l32i, a8, a3,  8, fixup)
 	ALIGN(	a6, a6, a7)
-	EX(s32i, a6, a5,  0, s_fixup)
-	EX(l32i, a9, a3, 12, l_fixup)
+	EX(s32i, a6, a5,  0, fixup)
+	EX(l32i, a9, a3, 12, fixup)
 	ALIGN(	a7, a7, a8)
-	EX(s32i, a7, a5,  4, s_fixup)
-	EX(l32i, a6, a3, 16, l_fixup)
+	EX(s32i, a7, a5,  4, fixup)
+	EX(l32i, a6, a3, 16, fixup)
 	ALIGN(	a8, a8, a9)
-	EX(s32i, a8, a5,  8, s_fixup)
+	EX(s32i, a8, a5,  8, fixup)
 	addi	a3, a3, 16
 	ALIGN(	a9, a9, a6)
-	EX(s32i, a9, a5, 12, s_fixup)
+	EX(s32i, a9, a5, 12, fixup)
 	addi	a5, a5, 16
 #if !XCHAL_HAVE_LOOPS
 	blt	a3, a12, .Loop2
@@ -246,39 +246,39 @@ __xtensa_copy_user:
 .Loop2done:
 	bbci.l	a4, 3, .L12
 	# copy 8 bytes
-	EX(l32i, a7, a3,  4, l_fixup)
-	EX(l32i, a8, a3,  8, l_fixup)
+	EX(l32i, a7, a3,  4, fixup)
+	EX(l32i, a8, a3,  8, fixup)
 	ALIGN(	a6, a6, a7)
-	EX(s32i, a6, a5,  0, s_fixup)
+	EX(s32i, a6, a5,  0, fixup)
 	addi	a3, a3,  8
 	ALIGN(	a7, a7, a8)
-	EX(s32i, a7, a5,  4, s_fixup)
+	EX(s32i, a7, a5,  4, fixup)
 	addi	a5, a5,  8
 	mov	a6, a8
 .L12:
 	bbci.l	a4, 2, .L13
 	# copy 4 bytes
-	EX(l32i, a7, a3,  4, l_fixup)
+	EX(l32i, a7, a3,  4, fixup)
 	addi	a3, a3,  4
 	ALIGN(	a6, a6, a7)
-	EX(s32i, a6, a5,  0, s_fixup)
+	EX(s32i, a6, a5,  0, fixup)
 	addi	a5, a5,  4
 	mov	a6, a7
 .L13:
 	add	a3, a3, a10	# readjust a3 with correct misalignment
 	bbci.l	a4, 1, .L14
 	# copy 2 bytes
-	EX(l8ui, a6, a3,  0, l_fixup)
-	EX(l8ui, a7, a3,  1, l_fixup)
+	EX(l8ui, a6, a3,  0, fixup)
+	EX(l8ui, a7, a3,  1, fixup)
 	addi	a3, a3,  2
-	EX(s8i, a6, a5,  0, s_fixup)
-	EX(s8i, a7, a5,  1, s_fixup)
+	EX(s8i, a6, a5,  0, fixup)
+	EX(s8i, a7, a5,  1, fixup)
 	addi	a5, a5,  2
 .L14:
 	bbci.l	a4, 0, .L15
 	# copy 1 byte
-	EX(l8ui, a6, a3,  0, l_fixup)
-	EX(s8i,  a6, a5,  0, s_fixup)
+	EX(l8ui, a6, a3,  0, fixup)
+	EX(s8i,  a6, a5,  0, fixup)
 .L15:
 	movi	a2, 0		# return success for len bytes copied
 	retw
@@ -291,30 +291,10 @@ __xtensa_copy_user:
  * bytes_copied = a5 - a2
  * retval = bytes_not_copied = original len - bytes_copied
  * retval = a11 - (a5 - a2)
- *
- * Clearing the remaining pieces of kernel memory plugs security
- * holes.  This functionality is the equivalent of the *_zeroing
- * functions that some architectures provide.
  */
 
-.Lmemset:
-	.word	memset
 
-s_fixup:
+fixup:
 	sub	a2, a5, a2	/* a2 <-- bytes copied */
 	sub	a2, a11, a2	/* a2 <-- bytes not copied */
 	retw
-
-l_fixup:
-	sub	a2, a5, a2	/* a2 <-- bytes copied */
-	sub	a2, a11, a2	/* a2 <-- bytes not copied == return value */
-
-	/* void *memset(void *s, int c, size_t n); */
-	mov	a6, a5		/* s */
-	movi	a7, 0		/* c */
-	mov	a8, a2		/* n */
-	l32r	a4, .Lmemset
-	callx4	a4
-	/* Ignore memset return value in a6. */
-	/* a2 still contains bytes not copied. */
-	retw
diff --git a/block/Kconfig b/block/Kconfig
index e9f780f815f5..89cd28f8d051 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -115,6 +115,18 @@ config BLK_DEV_THROTTLING
 
 	See Documentation/cgroups/blkio-controller.txt for more information.
 
+config BLK_DEV_THROTTLING_LOW
+	bool "Block throttling .low limit interface support (EXPERIMENTAL)"
+	depends on BLK_DEV_THROTTLING
+	default n
+	---help---
+	Add .low limit interface for block throttling. The low limit is a best
+	effort limit to prioritize cgroups. Depending on the setting, the limit
+	can be used to protect cgroups in terms of bandwidth/iops and better
+	utilize disk resource.
+
+	Note, this is an experimental interface and could be changed someday.
+
 config BLK_CMDLINE_PARSER
 	bool "Block device command line partition parser"
 	default n
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 58fc8684788d..fd2cefa47d35 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -40,6 +40,7 @@ config CFQ_GROUP_IOSCHED
 	  Enable group IO scheduling in CFQ.
 
 choice
+
 	prompt "Default I/O scheduler"
 	default DEFAULT_CFQ
 	help
@@ -69,6 +70,35 @@ config MQ_IOSCHED_DEADLINE
 	---help---
 	  MQ version of the deadline IO scheduler.
 
+config MQ_IOSCHED_KYBER
+	tristate "Kyber I/O scheduler"
+	default y
+	---help---
+	  The Kyber I/O scheduler is a low-overhead scheduler suitable for
+	  multiqueue and other fast devices. Given target latencies for reads and
+	  synchronous writes, it will self-tune queue depths to achieve that
+	  goal.
+
+config IOSCHED_BFQ
+	tristate "BFQ I/O scheduler"
+	default n
+	---help---
+	BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
+	of the device among all processes according to their weights,
+	regardless of the device parameters and with any workload. It
+	also guarantees a low latency to interactive and soft
+	real-time applications.  Details in
+	Documentation/block/bfq-iosched.txt
+
+config BFQ_GROUP_IOSCHED
+       bool "BFQ hierarchical scheduling support"
+       depends on IOSCHED_BFQ && BLK_CGROUP
+       default n
+       ---help---
+
+       Enable hierarchical scheduling in BFQ, using the blkio
+       (cgroups-v1) or io (cgroups-v2) controller.
+
 endmenu
 
 endif
diff --git a/block/Makefile b/block/Makefile
index 081bb680789b..2b281cf258a0 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -20,6 +20,9 @@ obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
+obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
+bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
+obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
new file mode 100644
index 000000000000..c8a32fb345cf
--- /dev/null
+++ b/block/bfq-cgroup.c
@@ -0,0 +1,1139 @@
+/*
+ * cgroups support for the BFQ I/O scheduler.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "bfq-iosched.h"
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/* bfqg stats flags */
+enum bfqg_stats_flags {
+	BFQG_stats_waiting = 0,
+	BFQG_stats_idling,
+	BFQG_stats_empty,
+};
+
+#define BFQG_FLAG_FNS(name)						\
+static void bfqg_stats_mark_##name(struct bfqg_stats *stats)	\
+{									\
+	stats->flags |= (1 << BFQG_stats_##name);			\
+}									\
+static void bfqg_stats_clear_##name(struct bfqg_stats *stats)	\
+{									\
+	stats->flags &= ~(1 << BFQG_stats_##name);			\
+}									\
+static int bfqg_stats_##name(struct bfqg_stats *stats)		\
+{									\
+	return (stats->flags & (1 << BFQG_stats_##name)) != 0;		\
+}									\
+
+BFQG_FLAG_FNS(waiting)
+BFQG_FLAG_FNS(idling)
+BFQG_FLAG_FNS(empty)
+#undef BFQG_FLAG_FNS
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
+{
+	unsigned long long now;
+
+	if (!bfqg_stats_waiting(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_group_wait_time))
+		blkg_stat_add(&stats->group_wait_time,
+			      now - stats->start_group_wait_time);
+	bfqg_stats_clear_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
+						 struct bfq_group *curr_bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	if (bfqg_stats_waiting(stats))
+		return;
+	if (bfqg == curr_bfqg)
+		return;
+	stats->start_group_wait_time = sched_clock();
+	bfqg_stats_mark_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
+{
+	unsigned long long now;
+
+	if (!bfqg_stats_empty(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_empty_time))
+		blkg_stat_add(&stats->empty_time,
+			      now - stats->start_empty_time);
+	bfqg_stats_clear_empty(stats);
+}
+
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
+{
+	blkg_stat_add(&bfqg->stats.dequeue, 1);
+}
+
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	if (blkg_rwstat_total(&stats->queued))
+		return;
+
+	/*
+	 * group is already marked empty. This can happen if bfqq got new
+	 * request in parent group and moved to this group while being added
+	 * to service tree. Just ignore the event and move on.
+	 */
+	if (bfqg_stats_empty(stats))
+		return;
+
+	stats->start_empty_time = sched_clock();
+	bfqg_stats_mark_empty(stats);
+}
+
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	if (bfqg_stats_idling(stats)) {
+		unsigned long long now = sched_clock();
+
+		if (time_after64(now, stats->start_idle_time))
+			blkg_stat_add(&stats->idle_time,
+				      now - stats->start_idle_time);
+		bfqg_stats_clear_idling(stats);
+	}
+}
+
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	stats->start_idle_time = sched_clock();
+	bfqg_stats_mark_idling(stats);
+}
+
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	blkg_stat_add(&stats->avg_queue_size_sum,
+		      blkg_rwstat_total(&stats->queued));
+	blkg_stat_add(&stats->avg_queue_size_samples, 1);
+	bfqg_stats_update_group_wait_time(stats);
+}
+
+/*
+ * blk-cgroup policy-related handlers
+ * The following functions help in converting between blk-cgroup
+ * internal structures and BFQ-specific structures.
+ */
+
+static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct bfq_group, pd) : NULL;
+}
+
+struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
+{
+	return pd_to_blkg(&bfqg->pd);
+}
+
+static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
+{
+	return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
+}
+
+/*
+ * bfq_group handlers
+ * The following functions help in navigating the bfq_group hierarchy
+ * by allowing to find the parent of a bfq_group or the bfq_group
+ * associated to a bfq_queue.
+ */
+
+static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
+{
+	struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;
+
+	return pblkg ? blkg_to_bfqg(pblkg) : NULL;
+}
+
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *group_entity = bfqq->entity.parent;
+
+	return group_entity ? container_of(group_entity, struct bfq_group,
+					   entity) :
+			      bfqq->bfqd->root_group;
+}
+
+/*
+ * The following two functions handle get and put of a bfq_group by
+ * wrapping the related blk-cgroup hooks.
+ */
+
+static void bfqg_get(struct bfq_group *bfqg)
+{
+	return blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_put(struct bfq_group *bfqg)
+{
+	return blkg_put(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+	bfqg_stats_end_empty_time(&bfqg->stats);
+	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
+		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
+}
+
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+}
+
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+}
+
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+	unsigned long long now = sched_clock();
+
+	if (time_after64(now, io_start_time))
+		blkg_rwstat_add(&stats->service_time, op,
+				now - io_start_time);
+	if (time_after64(io_start_time, start_time))
+		blkg_rwstat_add(&stats->wait_time, op,
+				io_start_time - start_time);
+}
+
+/* @stats = 0 */
+static void bfqg_stats_reset(struct bfqg_stats *stats)
+{
+	/* queued stats shouldn't be cleared */
+	blkg_rwstat_reset(&stats->merged);
+	blkg_rwstat_reset(&stats->service_time);
+	blkg_rwstat_reset(&stats->wait_time);
+	blkg_stat_reset(&stats->time);
+	blkg_stat_reset(&stats->avg_queue_size_sum);
+	blkg_stat_reset(&stats->avg_queue_size_samples);
+	blkg_stat_reset(&stats->dequeue);
+	blkg_stat_reset(&stats->group_wait_time);
+	blkg_stat_reset(&stats->idle_time);
+	blkg_stat_reset(&stats->empty_time);
+}
+
+/* @to += @from */
+static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
+{
+	if (!to || !from)
+		return;
+
+	/* queued stats shouldn't be cleared */
+	blkg_rwstat_add_aux(&to->merged, &from->merged);
+	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
+	blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
+	blkg_stat_add_aux(&from->time, &from->time);
+	blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
+	blkg_stat_add_aux(&to->avg_queue_size_samples,
+			  &from->avg_queue_size_samples);
+	blkg_stat_add_aux(&to->dequeue, &from->dequeue);
+	blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
+	blkg_stat_add_aux(&to->idle_time, &from->idle_time);
+	blkg_stat_add_aux(&to->empty_time, &from->empty_time);
+}
+
+/*
+ * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
+ * recursive stats can still account for the amount used by this bfqg after
+ * it's gone.
+ */
+static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
+{
+	struct bfq_group *parent;
+
+	if (!bfqg) /* root_group */
+		return;
+
+	parent = bfqg_parent(bfqg);
+
+	lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
+
+	if (unlikely(!parent))
+		return;
+
+	bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
+	bfqg_stats_reset(&bfqg->stats);
+}
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->weight = entity->new_weight;
+	entity->orig_weight = entity->new_weight;
+	if (bfqq) {
+		bfqq->ioprio = bfqq->new_ioprio;
+		bfqq->ioprio_class = bfqq->new_ioprio_class;
+		bfqg_get(bfqg);
+	}
+	entity->parent = bfqg->my_entity; /* NULL for root group */
+	entity->sched_data = &bfqg->sched_data;
+}
+
+static void bfqg_stats_exit(struct bfqg_stats *stats)
+{
+	blkg_rwstat_exit(&stats->merged);
+	blkg_rwstat_exit(&stats->service_time);
+	blkg_rwstat_exit(&stats->wait_time);
+	blkg_rwstat_exit(&stats->queued);
+	blkg_stat_exit(&stats->time);
+	blkg_stat_exit(&stats->avg_queue_size_sum);
+	blkg_stat_exit(&stats->avg_queue_size_samples);
+	blkg_stat_exit(&stats->dequeue);
+	blkg_stat_exit(&stats->group_wait_time);
+	blkg_stat_exit(&stats->idle_time);
+	blkg_stat_exit(&stats->empty_time);
+}
+
+static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
+{
+	if (blkg_rwstat_init(&stats->merged, gfp) ||
+	    blkg_rwstat_init(&stats->service_time, gfp) ||
+	    blkg_rwstat_init(&stats->wait_time, gfp) ||
+	    blkg_rwstat_init(&stats->queued, gfp) ||
+	    blkg_stat_init(&stats->time, gfp) ||
+	    blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
+	    blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
+	    blkg_stat_init(&stats->dequeue, gfp) ||
+	    blkg_stat_init(&stats->group_wait_time, gfp) ||
+	    blkg_stat_init(&stats->idle_time, gfp) ||
+	    blkg_stat_init(&stats->empty_time, gfp)) {
+		bfqg_stats_exit(stats);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
+{
+	return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
+}
+
+static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
+{
+	return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
+}
+
+struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
+{
+	struct bfq_group_data *bgd;
+
+	bgd = kzalloc(sizeof(*bgd), gfp);
+	if (!bgd)
+		return NULL;
+	return &bgd->pd;
+}
+
+void bfq_cpd_init(struct blkcg_policy_data *cpd)
+{
+	struct bfq_group_data *d = cpd_to_bfqgd(cpd);
+
+	d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
+		CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
+}
+
+void bfq_cpd_free(struct blkcg_policy_data *cpd)
+{
+	kfree(cpd_to_bfqgd(cpd));
+}
+
+struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+{
+	struct bfq_group *bfqg;
+
+	bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+	if (!bfqg)
+		return NULL;
+
+	if (bfqg_stats_init(&bfqg->stats, gfp)) {
+		kfree(bfqg);
+		return NULL;
+	}
+
+	return &bfqg->pd;
+}
+
+void bfq_pd_init(struct blkg_policy_data *pd)
+{
+	struct blkcg_gq *blkg = pd_to_blkg(pd);
+	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+	struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
+	struct bfq_entity *entity = &bfqg->entity;
+	struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
+
+	entity->orig_weight = entity->weight = entity->new_weight = d->weight;
+	entity->my_sched_data = &bfqg->sched_data;
+	bfqg->my_entity = entity; /*
+				   * the root_group's will be set to NULL
+				   * in bfq_init_queue()
+				   */
+	bfqg->bfqd = bfqd;
+	bfqg->active_entities = 0;
+	bfqg->rq_pos_tree = RB_ROOT;
+}
+
+void bfq_pd_free(struct blkg_policy_data *pd)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+	bfqg_stats_exit(&bfqg->stats);
+	return kfree(bfqg);
+}
+
+void bfq_pd_reset_stats(struct blkg_policy_data *pd)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+	bfqg_stats_reset(&bfqg->stats);
+}
+
+static void bfq_group_set_parent(struct bfq_group *bfqg,
+					struct bfq_group *parent)
+{
+	struct bfq_entity *entity;
+
+	entity = &bfqg->entity;
+	entity->parent = parent->my_entity;
+	entity->sched_data = &parent->sched_data;
+}
+
+static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
+					 struct blkcg *blkcg)
+{
+	struct blkcg_gq *blkg;
+
+	blkg = blkg_lookup(blkcg, bfqd->queue);
+	if (likely(blkg))
+		return blkg_to_bfqg(blkg);
+	return NULL;
+}
+
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+				     struct blkcg *blkcg)
+{
+	struct bfq_group *bfqg, *parent;
+	struct bfq_entity *entity;
+
+	bfqg = bfq_lookup_bfqg(bfqd, blkcg);
+
+	if (unlikely(!bfqg))
+		return NULL;
+
+	/*
+	 * Update chain of bfq_groups as we might be handling a leaf group
+	 * which, along with some of its relatives, has not been hooked yet
+	 * to the private hierarchy of BFQ.
+	 */
+	entity = &bfqg->entity;
+	for_each_entity(entity) {
+		bfqg = container_of(entity, struct bfq_group, entity);
+		if (bfqg != bfqd->root_group) {
+			parent = bfqg_parent(bfqg);
+			if (!parent)
+				parent = bfqd->root_group;
+			bfq_group_set_parent(bfqg, parent);
+		}
+	}
+
+	return bfqg;
+}
+
+/**
+ * bfq_bfqq_move - migrate @bfqq to @bfqg.
+ * @bfqd: queue descriptor.
+ * @bfqq: the queue to move.
+ * @bfqg: the group to move to.
+ *
+ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
+ * it on the new one.  Avoid putting the entity on the old group idle tree.
+ *
+ * Must be called under the queue lock; the cgroup owning @bfqg must
+ * not disappear (by now this just means that we are called under
+ * rcu_read_lock()).
+ */
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		   struct bfq_group *bfqg)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	/* If bfqq is empty, then bfq_bfqq_expire also invokes
+	 * bfq_del_bfqq_busy, thereby removing bfqq and its entity
+	 * from data structures related to current group. Otherwise we
+	 * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
+	 * we do below.
+	 */
+	if (bfqq == bfqd->in_service_queue)
+		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+				false, BFQQE_PREEMPTED);
+
+	if (bfq_bfqq_busy(bfqq))
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+	else if (entity->on_st)
+		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
+	bfqg_put(bfqq_group(bfqq));
+
+	/*
+	 * Here we use a reference to bfqg.  We don't need a refcounter
+	 * as the cgroup reference will not be dropped, so that its
+	 * destroy() callback will not be invoked.
+	 */
+	entity->parent = bfqg->my_entity;
+	entity->sched_data = &bfqg->sched_data;
+	bfqg_get(bfqg);
+
+	if (bfq_bfqq_busy(bfqq)) {
+		bfq_pos_tree_add_move(bfqd, bfqq);
+		bfq_activate_bfqq(bfqd, bfqq);
+	}
+
+	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+}
+
+/**
+ * __bfq_bic_change_cgroup - move @bic to @cgroup.
+ * @bfqd: the queue descriptor.
+ * @bic: the bic to move.
+ * @blkcg: the blk-cgroup to move to.
+ *
+ * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
+ * has to make sure that the reference to cgroup is valid across the call.
+ *
+ * NOTE: an alternative approach might have been to store the current
+ * cgroup in bfqq and getting a reference to it, reducing the lookup
+ * time here, at the price of slightly more complex code.
+ */
+static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
+						struct bfq_io_cq *bic,
+						struct blkcg *blkcg)
+{
+	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
+	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
+	struct bfq_group *bfqg;
+	struct bfq_entity *entity;
+
+	bfqg = bfq_find_set_group(bfqd, blkcg);
+
+	if (unlikely(!bfqg))
+		bfqg = bfqd->root_group;
+
+	if (async_bfqq) {
+		entity = &async_bfqq->entity;
+
+		if (entity->sched_data != &bfqg->sched_data) {
+			bic_set_bfqq(bic, NULL, 0);
+			bfq_log_bfqq(bfqd, async_bfqq,
+				     "bic_change_group: %p %d",
+				     async_bfqq, async_bfqq->ref);
+			bfq_put_queue(async_bfqq);
+		}
+	}
+
+	if (sync_bfqq) {
+		entity = &sync_bfqq->entity;
+		if (entity->sched_data != &bfqg->sched_data)
+			bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+	}
+
+	return bfqg;
+}
+
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
+{
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	struct bfq_group *bfqg = NULL;
+	uint64_t serial_nr;
+
+	rcu_read_lock();
+	serial_nr = bio_blkcg(bio)->css.serial_nr;
+
+	/*
+	 * Check whether blkcg has changed.  The condition may trigger
+	 * spuriously on a newly created cic but there's no harm.
+	 */
+	if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
+		goto out;
+
+	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+	bic->blkcg_serial_nr = serial_nr;
+out:
+	rcu_read_unlock();
+}
+
+/**
+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
+ * @st: the service tree being flushed.
+ */
+static void bfq_flush_idle_tree(struct bfq_service_tree *st)
+{
+	struct bfq_entity *entity = st->first_idle;
+
+	for (; entity ; entity = st->first_idle)
+		__bfq_deactivate_entity(entity, false);
+}
+
+/**
+ * bfq_reparent_leaf_entity - move leaf entity to the root_group.
+ * @bfqd: the device data structure with the root group.
+ * @entity: the entity to move.
+ */
+static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
+				     struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+}
+
+/**
+ * bfq_reparent_active_entities - move to the root group all active
+ *                                entities.
+ * @bfqd: the device data structure with the root group.
+ * @bfqg: the group to move from.
+ * @st: the service tree with the entities.
+ *
+ * Needs queue_lock to be taken and reference to be valid over the call.
+ */
+static void bfq_reparent_active_entities(struct bfq_data *bfqd,
+					 struct bfq_group *bfqg,
+					 struct bfq_service_tree *st)
+{
+	struct rb_root *active = &st->active;
+	struct bfq_entity *entity = NULL;
+
+	if (!RB_EMPTY_ROOT(&st->active))
+		entity = bfq_entity_of(rb_first(active));
+
+	for (; entity ; entity = bfq_entity_of(rb_first(active)))
+		bfq_reparent_leaf_entity(bfqd, entity);
+
+	if (bfqg->sched_data.in_service_entity)
+		bfq_reparent_leaf_entity(bfqd,
+			bfqg->sched_data.in_service_entity);
+}
+
+/**
+ * bfq_pd_offline - deactivate the entity associated with @pd,
+ *		    and reparent its children entities.
+ * @pd: descriptor of the policy going offline.
+ *
+ * blkio already grabs the queue_lock for us, so no need to use
+ * RCU-based magic
+ */
+void bfq_pd_offline(struct blkg_policy_data *pd)
+{
+	struct bfq_service_tree *st;
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+	struct bfq_data *bfqd = bfqg->bfqd;
+	struct bfq_entity *entity = bfqg->my_entity;
+	unsigned long flags;
+	int i;
+
+	if (!entity) /* root group */
+		return;
+
+	spin_lock_irqsave(&bfqd->lock, flags);
+	/*
+	 * Empty all service_trees belonging to this group before
+	 * deactivating the group itself.
+	 */
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
+		st = bfqg->sched_data.service_tree + i;
+
+		/*
+		 * The idle tree may still contain bfq_queues belonging
+		 * to exited task because they never migrated to a different
+		 * cgroup from the one being destroyed now.  No one else
+		 * can access them so it's safe to act without any lock.
+		 */
+		bfq_flush_idle_tree(st);
+
+		/*
+		 * It may happen that some queues are still active
+		 * (busy) upon group destruction (if the corresponding
+		 * processes have been forced to terminate). We move
+		 * all the leaf entities corresponding to these queues
+		 * to the root_group.
+		 * Also, it may happen that the group has an entity
+		 * in service, which is disconnected from the active
+		 * tree: it must be moved, too.
+		 * There is no need to put the sync queues, as the
+		 * scheduler has taken no reference.
+		 */
+		bfq_reparent_active_entities(bfqd, bfqg, st);
+	}
+
+	__bfq_deactivate_entity(entity, false);
+	bfq_put_async_queues(bfqd, bfqg);
+
+	spin_unlock_irqrestore(&bfqd->lock, flags);
+	/*
+	 * @blkg is going offline and will be ignored by
+	 * blkg_[rw]stat_recursive_sum().  Transfer stats to the parent so
+	 * that they don't get lost.  If IOs complete after this point, the
+	 * stats for them will be lost.  Oh well...
+	 */
+	bfqg_stats_xfer_dead(bfqg);
+}
+
+void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	struct blkcg_gq *blkg;
+
+	list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
+		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+		bfq_end_wr_async_queues(bfqd, bfqg);
+	}
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+static int bfq_io_show_weight(struct seq_file *sf, void *v)
+{
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+	unsigned int val = 0;
+
+	if (bfqgd)
+		val = bfqgd->weight;
+
+	seq_printf(sf, "%u\n", val);
+
+	return 0;
+}
+
+static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
+				    struct cftype *cftype,
+				    u64 val)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+	struct blkcg_gq *blkg;
+	int ret = -ERANGE;
+
+	if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
+		return ret;
+
+	ret = 0;
+	spin_lock_irq(&blkcg->lock);
+	bfqgd->weight = (unsigned short)val;
+	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+		if (!bfqg)
+			continue;
+		/*
+		 * Setting the prio_changed flag of the entity
+		 * to 1 with new_weight == weight would re-set
+		 * the value of the weight to its ioprio mapping.
+		 * Set the flag only if necessary.
+		 */
+		if ((unsigned short)val != bfqg->entity.new_weight) {
+			bfqg->entity.new_weight = (unsigned short)val;
+			/*
+			 * Make sure that the above new value has been
+			 * stored in bfqg->entity.new_weight before
+			 * setting the prio_changed flag. In fact,
+			 * this flag may be read asynchronously (in
+			 * critical sections protected by a different
+			 * lock than that held here), and finding this
+			 * flag set may cause the execution of the code
+			 * for updating parameters whose value may
+			 * depend also on bfqg->entity.new_weight (in
+			 * __bfq_entity_update_weight_prio).
+			 * This barrier makes sure that the new value
+			 * of bfqg->entity.new_weight is correctly
+			 * seen in that code.
+			 */
+			smp_wmb();
+			bfqg->entity.prio_changed = 1;
+		}
+	}
+	spin_unlock_irq(&blkcg->lock);
+
+	return ret;
+}
+
+static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
+				 char *buf, size_t nbytes,
+				 loff_t off)
+{
+	u64 weight;
+	/* First unsigned long found in the file is used */
+	int ret = kstrtoull(strim(buf), 0, &weight);
+
+	if (ret)
+		return ret;
+
+	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+}
+
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
+	return 0;
+}
+
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
+				      struct blkg_policy_data *pd, int off)
+{
+	u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
+					  &blkcg_policy_bfq, off);
+	return __blkg_prfill_u64(sf, pd, sum);
+}
+
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+					struct blkg_policy_data *pd, int off)
+{
+	struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
+							   &blkcg_policy_bfq,
+							   off);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_stat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, false);
+	return 0;
+}
+
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
+			       int off)
+{
+	u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+
+	return __blkg_prfill_u64(sf, pd, sum >> 9);
+}
+
+static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
+	return 0;
+}
+
+static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
+					 struct blkg_policy_data *pd, int off)
+{
+	struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
+					offsetof(struct blkcg_gq, stat_bytes));
+	u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
+		atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);
+
+	return __blkg_prfill_u64(sf, pd, sum >> 9);
+}
+
+static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
+			  false);
+	return 0;
+}
+
+static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
+				      struct blkg_policy_data *pd, int off)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+	u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples);
+	u64 v = 0;
+
+	if (samples) {
+		v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
+		v = div64_u64(v, samples);
+	}
+	__blkg_prfill_u64(sf, pd, v);
+	return 0;
+}
+
+/* print avg_queue_size */
+static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
+			  0, false);
+	return 0;
+}
+
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+{
+	int ret;
+
+	ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
+	if (ret)
+		return NULL;
+
+	return blkg_to_bfqg(bfqd->queue->root_blkg);
+}
+
+struct blkcg_policy blkcg_policy_bfq = {
+	.dfl_cftypes		= bfq_blkg_files,
+	.legacy_cftypes		= bfq_blkcg_legacy_files,
+
+	.cpd_alloc_fn		= bfq_cpd_alloc,
+	.cpd_init_fn		= bfq_cpd_init,
+	.cpd_bind_fn	        = bfq_cpd_init,
+	.cpd_free_fn		= bfq_cpd_free,
+
+	.pd_alloc_fn		= bfq_pd_alloc,
+	.pd_init_fn		= bfq_pd_init,
+	.pd_offline_fn		= bfq_pd_offline,
+	.pd_free_fn		= bfq_pd_free,
+	.pd_reset_stats_fn	= bfq_pd_reset_stats,
+};
+
+struct cftype bfq_blkcg_legacy_files[] = {
+	{
+		.name = "bfq.weight",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = bfq_io_show_weight,
+		.write_u64 = bfq_io_set_weight_legacy,
+	},
+
+	/* statistics, covers only the tasks in the bfqg */
+	{
+		.name = "bfq.time",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.sectors",
+		.seq_show = bfqg_print_stat_sectors,
+	},
+	{
+		.name = "bfq.io_service_bytes",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_bytes,
+	},
+	{
+		.name = "bfq.io_serviced",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_ios,
+	},
+	{
+		.name = "bfq.io_service_time",
+		.private = offsetof(struct bfq_group, stats.service_time),
+		.seq_show = bfqg_print_rwstat,
+	},
+	{
+		.name = "bfq.io_wait_time",
+		.private = offsetof(struct bfq_group, stats.wait_time),
+		.seq_show = bfqg_print_rwstat,
+	},
+	{
+		.name = "bfq.io_merged",
+		.private = offsetof(struct bfq_group, stats.merged),
+		.seq_show = bfqg_print_rwstat,
+	},
+	{
+		.name = "bfq.io_queued",
+		.private = offsetof(struct bfq_group, stats.queued),
+		.seq_show = bfqg_print_rwstat,
+	},
+
+	/* the same statictics which cover the bfqg and its descendants */
+	{
+		.name = "bfq.time_recursive",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat_recursive,
+	},
+	{
+		.name = "bfq.sectors_recursive",
+		.seq_show = bfqg_print_stat_sectors_recursive,
+	},
+	{
+		.name = "bfq.io_service_bytes_recursive",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_bytes_recursive,
+	},
+	{
+		.name = "bfq.io_serviced_recursive",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_ios_recursive,
+	},
+	{
+		.name = "bfq.io_service_time_recursive",
+		.private = offsetof(struct bfq_group, stats.service_time),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.io_wait_time_recursive",
+		.private = offsetof(struct bfq_group, stats.wait_time),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.io_merged_recursive",
+		.private = offsetof(struct bfq_group, stats.merged),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.io_queued_recursive",
+		.private = offsetof(struct bfq_group, stats.queued),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.avg_queue_size",
+		.seq_show = bfqg_print_avg_queue_size,
+	},
+	{
+		.name = "bfq.group_wait_time",
+		.private = offsetof(struct bfq_group, stats.group_wait_time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.idle_time",
+		.private = offsetof(struct bfq_group, stats.idle_time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.empty_time",
+		.private = offsetof(struct bfq_group, stats.empty_time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.dequeue",
+		.private = offsetof(struct bfq_group, stats.dequeue),
+		.seq_show = bfqg_print_stat,
+	},
+	{ }	/* terminate */
+};
+
+struct cftype bfq_blkg_files[] = {
+	{
+		.name = "bfq.weight",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = bfq_io_show_weight,
+		.write = bfq_io_set_weight,
+	},
+	{} /* terminate */
+};
+
+#else	/* CONFIG_BFQ_GROUP_IOSCHED */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op) { }
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
+
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		   struct bfq_group *bfqg) {}
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->weight = entity->new_weight;
+	entity->orig_weight = entity->new_weight;
+	if (bfqq) {
+		bfqq->ioprio = bfqq->new_ioprio;
+		bfqq->ioprio_class = bfqq->new_ioprio_class;
+	}
+	entity->sched_data = &bfqg->sched_data;
+}
+
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}
+
+void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg)
+{
+	return bfqd->root_group;
+}
+
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+	return bfqq->bfqd->root_group;
+}
+
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+{
+	struct bfq_group *bfqg;
+	int i;
+
+	bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
+	if (!bfqg)
+		return NULL;
+
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+	return bfqg;
+}
+#endif	/* CONFIG_BFQ_GROUP_IOSCHED */
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
new file mode 100644
index 000000000000..bd8499ef157c
--- /dev/null
+++ b/block/bfq-iosched.c
@@ -0,0 +1,5047 @@
+/*
+ * Budget Fair Queueing (BFQ) I/O scheduler.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ *                    Arianna Avanzini <avanzini@google.com>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ * BFQ is a proportional-share I/O scheduler, with some extra
+ * low-latency capabilities. BFQ also supports full hierarchical
+ * scheduling through cgroups. Next paragraphs provide an introduction
+ * on BFQ inner workings. Details on BFQ benefits, usage and
+ * limitations can be found in Documentation/block/bfq-iosched.txt.
+ *
+ * BFQ is a proportional-share storage-I/O scheduling algorithm based
+ * on the slice-by-slice service scheme of CFQ. But BFQ assigns
+ * budgets, measured in number of sectors, to processes instead of
+ * time slices. The device is not granted to the in-service process
+ * for a given time slice, but until it has exhausted its assigned
+ * budget. This change from the time to the service domain enables BFQ
+ * to distribute the device throughput among processes as desired,
+ * without any distortion due to throughput fluctuations, or to device
+ * internal queueing. BFQ uses an ad hoc internal scheduler, called
+ * B-WF2Q+, to schedule processes according to their budgets. More
+ * precisely, BFQ schedules queues associated with processes. Each
+ * process/queue is assigned a user-configurable weight, and B-WF2Q+
+ * guarantees that each queue receives a fraction of the throughput
+ * proportional to its weight. Thanks to the accurate policy of
+ * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
+ * processes issuing sequential requests (to boost the throughput),
+ * and yet guarantee a low latency to interactive and soft real-time
+ * applications.
+ *
+ * In particular, to provide these low-latency guarantees, BFQ
+ * explicitly privileges the I/O of two classes of time-sensitive
+ * applications: interactive and soft real-time. This feature enables
+ * BFQ to provide applications in these classes with a very low
+ * latency. Finally, BFQ also features additional heuristics for
+ * preserving both a low latency and a high throughput on NCQ-capable,
+ * rotational or flash-based devices, and to get the job done quickly
+ * for applications consisting in many I/O-bound processes.
+ *
+ * BFQ is described in [1], where also a reference to the initial, more
+ * theoretical paper on BFQ can be found. The interested reader can find
+ * in the latter paper full details on the main algorithm, as well as
+ * formulas of the guarantees and formal proofs of all the properties.
+ * With respect to the version of BFQ presented in these papers, this
+ * implementation adds a few more heuristics, such as the one that
+ * guarantees a low latency to soft real-time applications, and a
+ * hierarchical extension based on H-WF2Q+.
+ *
+ * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
+ * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
+ * with O(log N) complexity derives from the one introduced with EEVDF
+ * in [3].
+ *
+ * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+ *     Scheduler", Proceedings of the First Workshop on Mobile System
+ *     Technologies (MST-2015), May 2015.
+ *     http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+ *
+ * [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
+ *     Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
+ *     Oct 1997.
+ *
+ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
+ *
+ * [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
+ *     First: A Flexible and Accurate Mechanism for Proportional Share
+ *     Resource Allocation", technical report.
+ *
+ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+#include "bfq-iosched.h"
+
+#define BFQ_BFQQ_FNS(name)						\
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)			\
+{									\
+	__set_bit(BFQQF_##name, &(bfqq)->flags);			\
+}									\
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)			\
+{									\
+	__clear_bit(BFQQF_##name, &(bfqq)->flags);		\
+}									\
+int bfq_bfqq_##name(const struct bfq_queue *bfqq)			\
+{									\
+	return test_bit(BFQQF_##name, &(bfqq)->flags);		\
+}
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS						\
+
+/* Expiration time of sync (0) and async (1) requests, in ns. */
+static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
+
+/* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
+static const int bfq_back_max = 16 * 1024;
+
+/* Penalty of a backwards seek, in number of sectors. */
+static const int bfq_back_penalty = 2;
+
+/* Idling period duration, in ns. */
+static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
+
+/* Minimum number of assigned budgets for which stats are safe to compute. */
+static const int bfq_stats_min_budgets = 194;
+
+/* Default maximum budget values, in sectors and number of requests. */
+static const int bfq_default_max_budget = 16 * 1024;
+
+/*
+ * Async to sync throughput distribution is controlled as follows:
+ * when an async request is served, the entity is charged the number
+ * of sectors of the request, multiplied by the factor below
+ */
+static const int bfq_async_charge_factor = 10;
+
+/* Default timeout values, in jiffies, approximating CFQ defaults. */
+const int bfq_timeout = HZ / 8;
+
+static struct kmem_cache *bfq_pool;
+
+/* Below this threshold (in ns), we consider thinktime immediate. */
+#define BFQ_MIN_TT		(2 * NSEC_PER_MSEC)
+
+/* hw_tag detection: parallel requests threshold and min samples needed. */
+#define BFQ_HW_QUEUE_THRESHOLD	4
+#define BFQ_HW_QUEUE_SAMPLES	32
+
+#define BFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define BFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
+#define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 32/8)
+
+/* Min number of samples required to perform peak-rate update */
+#define BFQ_RATE_MIN_SAMPLES	32
+/* Min observation time interval required to perform a peak-rate update (ns) */
+#define BFQ_RATE_MIN_INTERVAL	(300*NSEC_PER_MSEC)
+/* Target observation time interval for a peak-rate update (ns) */
+#define BFQ_RATE_REF_INTERVAL	NSEC_PER_SEC
+
+/* Shift used for peak rate fixed precision calculations. */
+#define BFQ_RATE_SHIFT		16
+
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ *   SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and
+ * T_slow[0]/T_fast[0] are the reference values for a slow/fast
+ * rotational device, whereas R_slow[1]/R_fast[1] and
+ * T_slow[1]/T_fast[1] are the reference values for a slow/fast
+ * non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes. The reference
+ * rates are not the actual peak rates of the devices used as a
+ * reference, but slightly lower values. The reason for using these
+ * slightly lower values is that the peak-rate estimator tends to
+ * yield slightly lower values than the actual peak rate (it can yield
+ * the actual peak rate only if there is only one process doing I/O,
+ * and the process does sequential I/O).
+ *
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1000, 10700};
+static int R_fast[2] = {14000, 33000};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
+#define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
+#define RQ_BFQQ(rq)		((rq)->elv.priv[1])
+
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+	return bic->bfqq[is_sync];
+}
+
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
+{
+	bic->bfqq[is_sync] = bfqq;
+}
+
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
+{
+	return bic->icq.q->elevator->elevator_data;
+}
+
+/**
+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
+ * @icq: the iocontext queue.
+ */
+static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
+{
+	/* bic->icq is the first member, %NULL will convert to %NULL */
+	return container_of(icq, struct bfq_io_cq, icq);
+}
+
+/**
+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
+ * @bfqd: the lookup key.
+ * @ioc: the io_context of the process doing I/O.
+ * @q: the request queue.
+ */
+static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+					struct io_context *ioc,
+					struct request_queue *q)
+{
+	if (ioc) {
+		unsigned long flags;
+		struct bfq_io_cq *icq;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
+		spin_unlock_irqrestore(q->queue_lock, flags);
+
+		return icq;
+	}
+
+	return NULL;
+}
+
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+void bfq_schedule_dispatch(struct bfq_data *bfqd)
+{
+	if (bfqd->queued != 0) {
+		bfq_log(bfqd, "schedule dispatch");
+		blk_mq_run_hw_queues(bfqd->queue, true);
+	}
+}
+
+#define bfq_class_idle(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
+#define bfq_class_rt(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
+
+#define bfq_sample_valid(samples)	((samples) > 80)
+
+/*
+ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
+ * We choose the request that is closesr to the head right now.  Distance
+ * behind the head is penalized and only allowed to a certain extent.
+ */
+static struct request *bfq_choose_req(struct bfq_data *bfqd,
+				      struct request *rq1,
+				      struct request *rq2,
+				      sector_t last)
+{
+	sector_t s1, s2, d1 = 0, d2 = 0;
+	unsigned long back_max;
+#define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
+#define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
+	unsigned int wrap = 0; /* bit mask: requests behind the disk head? */
+
+	if (!rq1 || rq1 == rq2)
+		return rq2;
+	if (!rq2)
+		return rq1;
+
+	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
+		return rq1;
+	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
+		return rq2;
+	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
+		return rq1;
+	else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
+		return rq2;
+
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
+
+	/*
+	 * By definition, 1KiB is 2 sectors.
+	 */
+	back_max = bfqd->bfq_back_max * 2;
+
+	/*
+	 * Strict one way elevator _except_ in the case where we allow
+	 * short backward seeks which are biased as twice the cost of a
+	 * similar forward seek.
+	 */
+	if (s1 >= last)
+		d1 = s1 - last;
+	else if (s1 + back_max >= last)
+		d1 = (last - s1) * bfqd->bfq_back_penalty;
+	else
+		wrap |= BFQ_RQ1_WRAP;
+
+	if (s2 >= last)
+		d2 = s2 - last;
+	else if (s2 + back_max >= last)
+		d2 = (last - s2) * bfqd->bfq_back_penalty;
+	else
+		wrap |= BFQ_RQ2_WRAP;
+
+	/* Found required data */
+
+	/*
+	 * By doing switch() on the bit mask "wrap" we avoid having to
+	 * check two variables for all permutations: --> faster!
+	 */
+	switch (wrap) {
+	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
+		if (d1 < d2)
+			return rq1;
+		else if (d2 < d1)
+			return rq2;
+
+		if (s1 >= s2)
+			return rq1;
+		else
+			return rq2;
+
+	case BFQ_RQ2_WRAP:
+		return rq1;
+	case BFQ_RQ1_WRAP:
+		return rq2;
+	case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP: /* both rqs wrapped */
+	default:
+		/*
+		 * Since both rqs are wrapped,
+		 * start with the one that's further behind head
+		 * (--> only *one* back seek required),
+		 * since back seek takes more time than forward.
+		 */
+		if (s1 <= s2)
+			return rq1;
+		else
+			return rq2;
+	}
+}
+
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *bfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+		/*
+		 * Sort strictly based on sector. Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		bfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+
+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+		(unsigned long long)sector,
+		bfqq ? bfqq->pid : 0);
+
+	return bfqq;
+}
+
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *__bfqq;
+
+	if (bfqq->pos_root) {
+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
+		bfqq->pos_root = NULL;
+	}
+
+	if (bfq_class_idle(bfqq))
+		return;
+	if (!bfqq->next_rq)
+		return;
+
+	bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+			blk_rq_pos(bfqq->next_rq), &parent, &p);
+	if (!__bfqq) {
+		rb_link_node(&bfqq->pos_node, parent, p);
+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+	} else
+		bfqq->pos_root = NULL;
+}
+
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+	/*
+	 * For weights to differ, at least one of the trees must contain
+	 * at least two nodes.
+	 */
+	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+		(bfqd->queue_weights_tree.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	       ) ||
+	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+		(bfqd->group_weights_tree.rb_node->rb_left ||
+		 bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+	       );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ *    weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ *    number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+	return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+			  struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/*
+	 * Do not insert if the entity is already associated with a
+	 * counter, which happens if:
+	 *   1) the entity is associated with a queue,
+	 *   2) a request arrival has caused the queue to become both
+	 *      non-weight-raised, and hence change its weight, and
+	 *      backlogged; in this respect, each of the two events
+	 *      causes an invocation of this function,
+	 *   3) this is the invocation of this function caused by the
+	 *      second event. This second invocation is actually useless,
+	 *      and we handle this fact by exiting immediately. More
+	 *      efficient or clearer solutions might possibly be adopted.
+	 */
+	if (entity->weight_counter)
+		return;
+
+	while (*new) {
+		struct bfq_weight_counter *__counter = container_of(*new,
+						struct bfq_weight_counter,
+						weights_node);
+		parent = *new;
+
+		if (entity->weight == __counter->weight) {
+			entity->weight_counter = __counter;
+			goto inc_counter;
+		}
+		if (entity->weight < __counter->weight)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+					 GFP_ATOMIC);
+
+	/*
+	 * In the unlucky event of an allocation failure, we just
+	 * exit. This will cause the weight of entity to not be
+	 * considered in bfq_differentiated_weights, which, in its
+	 * turn, causes the scenario to be deemed wrongly symmetric in
+	 * case entity's weight would have been the only weight making
+	 * the scenario asymmetric. On the bright side, no unbalance
+	 * will however occur when entity becomes inactive again (the
+	 * invocation of this function is triggered by an activation
+	 * of entity). In fact, bfq_weights_tree_remove does nothing
+	 * if !entity->weight_counter.
+	 */
+	if (unlikely(!entity->weight_counter))
+		return;
+
+	entity->weight_counter->weight = entity->weight;
+	rb_link_node(&entity->weight_counter->weights_node, parent, new);
+	rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+	entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+			     struct rb_root *root)
+{
+	if (!entity->weight_counter)
+		return;
+
+	entity->weight_counter->num_active--;
+	if (entity->weight_counter->num_active > 0)
+		goto reset_entity_pointer;
+
+	rb_erase(&entity->weight_counter->weights_node, root);
+	kfree(entity->weight_counter);
+
+reset_entity_pointer:
+	entity->weight_counter = NULL;
+}
+
+/*
+ * Return expired entry, or NULL to just start from scratch in rbtree.
+ */
+static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
+				      struct request *last)
+{
+	struct request *rq;
+
+	if (bfq_bfqq_fifo_expire(bfqq))
+		return NULL;
+
+	bfq_mark_bfqq_fifo_expire(bfqq);
+
+	rq = rq_entry_fifo(bfqq->fifo.next);
+
+	if (rq == last || ktime_get_ns() < rq->fifo_time)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
+	return rq;
+}
+
+static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq,
+					struct request *last)
+{
+	struct rb_node *rbnext = rb_next(&last->rb_node);
+	struct rb_node *rbprev = rb_prev(&last->rb_node);
+	struct request *next, *prev = NULL;
+
+	/* Follow expired path, else get first next available. */
+	next = bfq_check_fifo(bfqq, last);
+	if (next)
+		return next;
+
+	if (rbprev)
+		prev = rb_entry_rq(rbprev);
+
+	if (rbnext)
+		next = rb_entry_rq(rbnext);
+	else {
+		rbnext = rb_first(&bfqq->sort_list);
+		if (rbnext && rbnext != &last->rb_node)
+			next = rb_entry_rq(rbnext);
+	}
+
+	return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
+}
+
+/* see the definition of bfq_async_charge_factor for details */
+static unsigned long bfq_serv_to_charge(struct request *rq,
+					struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
+		return blk_rq_sectors(rq);
+
+	/*
+	 * If there are no weight-raised queues, then amplify service
+	 * by just the async charge factor; otherwise amplify service
+	 * by twice the async charge factor, to further reduce latency
+	 * for weight-raised queues.
+	 */
+	if (bfqq->bfqd->wr_busy_queues == 0)
+		return blk_rq_sectors(rq) * bfq_async_charge_factor;
+
+	return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
+}
+
+/**
+ * bfq_updated_next_req - update the queue after a new next_rq selection.
+ * @bfqd: the device data the queue belongs to.
+ * @bfqq: the queue to update.
+ *
+ * If the first request of a queue changes we make sure that the queue
+ * has enough budget to serve at least its first request (if the
+ * request has grown).  We do this because if the queue has not enough
+ * budget for its first request, it has to go through two dispatch
+ * rounds to actually get it dispatched.
+ */
+static void bfq_updated_next_req(struct bfq_data *bfqd,
+				 struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	struct request *next_rq = bfqq->next_rq;
+	unsigned long new_budget;
+
+	if (!next_rq)
+		return;
+
+	if (bfqq == bfqd->in_service_queue)
+		/*
+		 * In order not to break guarantees, budgets cannot be
+		 * changed after an entity has been selected.
+		 */
+		return;
+
+	new_budget = max_t(unsigned long, bfqq->max_budget,
+			   bfq_serv_to_charge(next_rq, bfqq));
+	if (entity->budget != new_budget) {
+		entity->budget = new_budget;
+		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
+					 new_budget);
+		bfq_requeue_bfqq(bfqd, bfqq);
+	}
+}
+
+static void
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+	if (bic->saved_idle_window)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+
+	if (bic->saved_IO_bound)
+		bfq_mark_bfqq_IO_bound(bfqq);
+	else
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	bfqq->ttime = bic->saved_ttime;
+	bfqq->wr_coeff = bic->saved_wr_coeff;
+	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
+	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
+	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+
+	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
+	    time_is_before_jiffies(bfqq->last_wr_start_finish +
+				   bfqq->wr_cur_max_time))) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+		    "resume state: switching off wr");
+
+		bfqq->wr_coeff = 1;
+	}
+
+	/* make sure weight will be updated, however we got here */
+	bfqq->entity.prio_changed = 1;
+}
+
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+	return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
+}
+
+/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_queue *item;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+		hlist_del_init(&item->burst_list_node);
+	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+	bfqd->burst_size = 1;
+	bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/* Increment burst size to take into account also bfqq */
+	bfqd->burst_size++;
+
+	if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+		struct bfq_queue *pos, *bfqq_item;
+		struct hlist_node *n;
+
+		/*
+		 * Enough queues have been activated shortly after each
+		 * other to consider this burst as large.
+		 */
+		bfqd->large_burst = true;
+
+		/*
+		 * We can now mark all queues in the burst list as
+		 * belonging to a large burst.
+		 */
+		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+				     burst_list_node)
+			bfq_mark_bfqq_in_large_burst(bfqq_item);
+		bfq_mark_bfqq_in_large_burst(bfqq);
+
+		/*
+		 * From now on, and until the current burst finishes, any
+		 * new queue being activated shortly after the last queue
+		 * was inserted in the burst can be immediately marked as
+		 * belonging to a large burst. So the burst list is not
+		 * needed any more. Remove it.
+		 */
+		hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+					  burst_list_node)
+			hlist_del_init(&pos->burst_list_node);
+	} else /*
+		* Burst not yet large: add bfqq to the burst list. Do
+		* not increment the ref counter for bfqq, because bfqq
+		* is removed from the burst list before freeing bfqq
+		* in put_queue.
+		*/
+		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ *   list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ *   not yet belong to the burst is activated shortly after the last time
+ *   at which a new queue entered the burst list, then the function appends
+ *   Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ *   the large-burst threshold, then
+ *
+ *     . all the queues in the burst list are marked as belonging to a
+ *       large burst
+ *
+ *     . the burst list is deleted; in fact, the burst list already served
+ *       its purpose (keeping temporarily track of the queues in a burst,
+ *       so as to be able to mark them as belonging to a large burst in the
+ *       previous sub-step), and now is not needed any more
+ *
+ *     . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ *   the device is in large-burst mode and shortly after the last time
+ *   at which a queue either entered the burst list or was marked as
+ *   belonging to the current large burst, then Q is immediately marked
+ *   as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ *   later, i.e., not shortly after, than the last time at which a queue
+ *   either entered the burst list or was marked as belonging to the
+ *   current large burst, then the current burst is deemed as finished and:
+ *
+ *        . the large-burst mode is reset if set
+ *
+ *        . the burst list is emptied
+ *
+ *        . Q is inserted in the burst list, as Q may be the first queue
+ *          in a possible new burst (then the burst list contains just Q
+ *          after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq is already in the burst list or is part of a large
+	 * burst, or finally has just been split, then there is
+	 * nothing else to do.
+	 */
+	if (!hlist_unhashed(&bfqq->burst_list_node) ||
+	    bfq_bfqq_in_large_burst(bfqq) ||
+	    time_is_after_eq_jiffies(bfqq->split_time +
+				     msecs_to_jiffies(10)))
+		return;
+
+	/*
+	 * If bfqq's creation happens late enough, or bfqq belongs to
+	 * a different group than the burst group, then the current
+	 * burst is finished, and related data structures must be
+	 * reset.
+	 *
+	 * In this respect, consider the special case where bfqq is
+	 * the very first queue created after BFQ is selected for this
+	 * device. In this case, last_ins_in_burst and
+	 * burst_parent_entity are not yet significant when we get
+	 * here. But it is easy to verify that, whether or not the
+	 * following condition is true, bfqq will end up being
+	 * inserted into the burst list. In particular the list will
+	 * happen to contain only bfqq. And this is exactly what has
+	 * to happen, as bfqq may be the first queue of the first
+	 * burst.
+	 */
+	if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+	    bfqd->bfq_burst_interval) ||
+	    bfqq->entity.parent != bfqd->burst_parent_entity) {
+		bfqd->large_burst = false;
+		bfq_reset_burst_list(bfqd, bfqq);
+		goto end;
+	}
+
+	/*
+	 * If we get here, then bfqq is being activated shortly after the
+	 * last queue. So, if the current burst is also large, we can mark
+	 * bfqq as belonging to this large burst immediately.
+	 */
+	if (bfqd->large_burst) {
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		goto end;
+	}
+
+	/*
+	 * If we get here, then a large-burst state has not yet been
+	 * reached, but bfqq is being activated shortly after the last
+	 * queue. Then we add bfqq to the burst.
+	 */
+	bfq_add_to_burst(bfqd, bfqq);
+end:
+	/*
+	 * At this point, bfqq either has been added to the current
+	 * burst or has caused the current burst to terminate and a
+	 * possible new burst to start. In particular, in the second
+	 * case, bfqq has become the first queue in the possible new
+	 * burst.  In both cases last_ins_in_burst needs to be moved
+	 * forward.
+	 */
+	bfqd->last_ins_in_burst = jiffies;
+}
+
+static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	return entity->budget - entity->service;
+}
+
+/*
+ * If enough samples have been computed, return the current max budget
+ * stored in bfqd, which is dynamically updated according to the
+ * estimated disk peak rate; otherwise return the default max budget
+ */
+static int bfq_max_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+		return bfq_default_max_budget;
+	else
+		return bfqd->bfq_max_budget;
+}
+
+/*
+ * Return min budget, which is a fraction of the current or default
+ * max budget (trying with 1/32)
+ */
+static int bfq_min_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+		return bfq_default_max_budget / 32;
+	else
+		return bfqd->bfq_max_budget / 32;
+}
+
+/*
+ * The next function, invoked after the input queue bfqq switches from
+ * idle to busy, updates the budget of bfqq. The function also tells
+ * whether the in-service queue should be expired, by returning
+ * true. The purpose of expiring the in-service queue is to give bfqq
+ * the chance to possibly preempt the in-service queue, and the reason
+ * for preempting the in-service queue is to achieve one of the two
+ * goals below.
+ *
+ * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
+ * expired because it has remained idle. In particular, bfqq may have
+ * expired for one of the following two reasons:
+ *
+ * - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
+ *   and did not make it to issue a new request before its last
+ *   request was served;
+ *
+ * - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
+ *   a new request before the expiration of the idling-time.
+ *
+ * Even if bfqq has expired for one of the above reasons, the process
+ * associated with the queue may be however issuing requests greedily,
+ * and thus be sensitive to the bandwidth it receives (bfqq may have
+ * remained idle for other reasons: CPU high load, bfqq not enjoying
+ * idling, I/O throttling somewhere in the path from the process to
+ * the I/O scheduler, ...). But if, after every expiration for one of
+ * the above two reasons, bfqq has to wait for the service of at least
+ * one full budget of another queue before being served again, then
+ * bfqq is likely to get a much lower bandwidth or resource time than
+ * its reserved ones. To address this issue, two countermeasures need
+ * to be taken.
+ *
+ * First, the budget and the timestamps of bfqq need to be updated in
+ * a special way on bfqq reactivation: they need to be updated as if
+ * bfqq did not remain idle and did not expire. In fact, if they are
+ * computed as if bfqq expired and remained idle until reactivation,
+ * then the process associated with bfqq is treated as if, instead of
+ * being greedy, it stopped issuing requests when bfqq remained idle,
+ * and restarts issuing requests only on this reactivation. In other
+ * words, the scheduler does not help the process recover the "service
+ * hole" between bfqq expiration and reactivation. As a consequence,
+ * the process receives a lower bandwidth than its reserved one. In
+ * contrast, to recover this hole, the budget must be updated as if
+ * bfqq was not expired at all before this reactivation, i.e., it must
+ * be set to the value of the remaining budget when bfqq was
+ * expired. Along the same line, timestamps need to be assigned the
+ * value they had the last time bfqq was selected for service, i.e.,
+ * before last expiration. Thus timestamps need to be back-shifted
+ * with respect to their normal computation (see [1] for more details
+ * on this tricky aspect).
+ *
+ * Secondly, to allow the process to recover the hole, the in-service
+ * queue must be expired too, to give bfqq the chance to preempt it
+ * immediately. In fact, if bfqq has to wait for a full budget of the
+ * in-service queue to be completed, then it may become impossible to
+ * let the process recover the hole, even if the back-shifted
+ * timestamps of bfqq are lower than those of the in-service queue. If
+ * this happens for most or all of the holes, then the process may not
+ * receive its reserved bandwidth. In this respect, it is worth noting
+ * that, being the service of outstanding requests unpreemptible, a
+ * little fraction of the holes may however be unrecoverable, thereby
+ * causing a little loss of bandwidth.
+ *
+ * The last important point is detecting whether bfqq does need this
+ * bandwidth recovery. In this respect, the next function deems the
+ * process associated with bfqq greedy, and thus allows it to recover
+ * the hole, if: 1) the process is waiting for the arrival of a new
+ * request (which implies that bfqq expired for one of the above two
+ * reasons), and 2) such a request has arrived soon. The first
+ * condition is controlled through the flag non_blocking_wait_rq,
+ * while the second through the flag arrived_in_time. If both
+ * conditions hold, then the function computes the budget in the
+ * above-described special way, and signals that the in-service queue
+ * should be expired. Timestamp back-shifting is done later in
+ * __bfq_activate_entity.
+ *
+ * 2. Reduce latency. Even if timestamps are not backshifted to let
+ * the process associated with bfqq recover a service hole, bfqq may
+ * however happen to have, after being (re)activated, a lower finish
+ * timestamp than the in-service queue.	 That is, the next budget of
+ * bfqq may have to be completed before the one of the in-service
+ * queue. If this is the case, then preempting the in-service queue
+ * allows this goal to be achieved, apart from the unpreemptible,
+ * outstanding requests mentioned above.
+ *
+ * Unfortunately, regardless of which of the above two goals one wants
+ * to achieve, service trees need first to be updated to know whether
+ * the in-service queue must be preempted. To have service trees
+ * correctly updated, the in-service queue must be expired and
+ * rescheduled, and bfqq must be scheduled too. This is one of the
+ * most costly operations (in future versions, the scheduling
+ * mechanism may be re-designed in such a way to make it possible to
+ * know whether preemption is needed without needing to update service
+ * trees). In addition, queue preemptions almost always cause random
+ * I/O, and thus loss of throughput. Because of these facts, the next
+ * function adopts the following simple scheme to avoid both costly
+ * operations and too frequent preemptions: it requests the expiration
+ * of the in-service queue (unconditionally) only for queues that need
+ * to recover a hole, or that either are weight-raised or deserve to
+ * be weight-raised.
+ */
+static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq,
+						bool arrived_in_time,
+						bool wr_or_deserves_wr)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
+		/*
+		 * We do not clear the flag non_blocking_wait_rq here, as
+		 * the latter is used in bfq_activate_bfqq to signal
+		 * that timestamps need to be back-shifted (and is
+		 * cleared right after).
+		 */
+
+		/*
+		 * In next assignment we rely on that either
+		 * entity->service or entity->budget are not updated
+		 * on expiration if bfqq is empty (see
+		 * __bfq_bfqq_recalc_budget). Thus both quantities
+		 * remain unchanged after such an expiration, and the
+		 * following statement therefore assigns to
+		 * entity->budget the remaining budget on such an
+		 * expiration. For clarity, entity->service is not
+		 * updated on expiration in any case, and, in normal
+		 * operation, is reset only when bfqq is selected for
+		 * service (see bfq_get_next_queue).
+		 */
+		entity->budget = min_t(unsigned long,
+				       bfq_bfqq_budget_left(bfqq),
+				       bfqq->max_budget);
+
+		return true;
+	}
+
+	entity->budget = max_t(unsigned long, bfqq->max_budget,
+			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
+	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+	return wr_or_deserves_wr;
+}
+
+static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+	u64 dur;
+
+	if (bfqd->bfq_wr_max_time > 0)
+		return bfqd->bfq_wr_max_time;
+
+	dur = bfqd->RT_prod;
+	do_div(dur, bfqd->peak_rate);
+
+	/*
+	 * Limit duration between 3 and 13 seconds. Tests show that
+	 * higher values than 13 seconds often yield the opposite of
+	 * the desired result, i.e., worsen responsiveness by letting
+	 * non-interactive and non-soft-real-time applications
+	 * preserve weight raising for a too long time interval.
+	 *
+	 * On the other end, lower values than 3 seconds make it
+	 * difficult for most interactive tasks to complete their jobs
+	 * before weight-raising finishes.
+	 */
+	if (dur > msecs_to_jiffies(13000))
+		dur = msecs_to_jiffies(13000);
+	else if (dur < msecs_to_jiffies(3000))
+		dur = msecs_to_jiffies(3000);
+
+	return dur;
+}
+
+static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     unsigned int old_wr_coeff,
+					     bool wr_or_deserves_wr,
+					     bool interactive,
+					     bool in_burst,
+					     bool soft_rt)
+{
+	if (old_wr_coeff == 1 && wr_or_deserves_wr) {
+		/* start a weight-raising period */
+		if (interactive) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else {
+			bfqq->wr_start_at_switch_to_srt = jiffies;
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+				BFQ_SOFTRT_WEIGHT_FACTOR;
+			bfqq->wr_cur_max_time =
+				bfqd->bfq_wr_rt_max_time;
+		}
+
+		/*
+		 * If needed, further reduce budget to make sure it is
+		 * close to bfqq's backlog, so as to reduce the
+		 * scheduling-error component due to a too large
+		 * budget. Do not care about throughput consequences,
+		 * but only about latency. Finally, do not assign a
+		 * too small budget either, to avoid increasing
+		 * latency by causing too frequent expirations.
+		 */
+		bfqq->entity.budget = min_t(unsigned long,
+					    bfqq->entity.budget,
+					    2 * bfq_min_budget(bfqd));
+	} else if (old_wr_coeff > 1) {
+		if (interactive) { /* update wr coeff and duration */
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else if (in_burst)
+			bfqq->wr_coeff = 1;
+		else if (soft_rt) {
+			/*
+			 * The application is now or still meeting the
+			 * requirements for being deemed soft rt.  We
+			 * can then correctly and safely (re)charge
+			 * the weight-raising duration for the
+			 * application with the weight-raising
+			 * duration for soft rt applications.
+			 *
+			 * In particular, doing this recharge now, i.e.,
+			 * before the weight-raising period for the
+			 * application finishes, reduces the probability
+			 * of the following negative scenario:
+			 * 1) the weight of a soft rt application is
+			 *    raised at startup (as for any newly
+			 *    created application),
+			 * 2) since the application is not interactive,
+			 *    at a certain time weight-raising is
+			 *    stopped for the application,
+			 * 3) at that time the application happens to
+			 *    still have pending requests, and hence
+			 *    is destined to not have a chance to be
+			 *    deemed soft rt before these requests are
+			 *    completed (see the comments to the
+			 *    function bfq_bfqq_softrt_next_start()
+			 *    for details on soft rt detection),
+			 * 4) these pending requests experience a high
+			 *    latency because the application is not
+			 *    weight-raised while they are pending.
+			 */
+			if (bfqq->wr_cur_max_time !=
+				bfqd->bfq_wr_rt_max_time) {
+				bfqq->wr_start_at_switch_to_srt =
+					bfqq->last_wr_start_finish;
+
+				bfqq->wr_cur_max_time =
+					bfqd->bfq_wr_rt_max_time;
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+					BFQ_SOFTRT_WEIGHT_FACTOR;
+			}
+			bfqq->last_wr_start_finish = jiffies;
+		}
+	}
+}
+
+static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq)
+{
+	return bfqq->dispatched == 0 &&
+		time_is_before_jiffies(
+			bfqq->budget_timeout +
+			bfqd->bfq_wr_min_idle_time);
+}
+
+static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     int old_wr_coeff,
+					     struct request *rq,
+					     bool *interactive)
+{
+	bool soft_rt, in_burst,	wr_or_deserves_wr,
+		bfqq_wants_to_preempt,
+		idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
+		/*
+		 * See the comments on
+		 * bfq_bfqq_update_budg_for_activation for
+		 * details on the usage of the next variable.
+		 */
+		arrived_in_time =  ktime_get_ns() <=
+			bfqq->ttime.last_end_request +
+			bfqd->bfq_slice_idle * 3;
+
+	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
+
+	/*
+	 * bfqq deserves to be weight-raised if:
+	 * - it is sync,
+	 * - it does not belong to a large burst,
+	 * - it has been idle for enough time or is soft real-time,
+	 * - is linked to a bfq_io_cq (it is not shared in any sense).
+	 */
+	in_burst = bfq_bfqq_in_large_burst(bfqq);
+	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+		!in_burst &&
+		time_is_before_jiffies(bfqq->soft_rt_next_start);
+	*interactive = !in_burst && idle_for_long_time;
+	wr_or_deserves_wr = bfqd->low_latency &&
+		(bfqq->wr_coeff > 1 ||
+		 (bfq_bfqq_sync(bfqq) &&
+		  bfqq->bic && (*interactive || soft_rt)));
+
+	/*
+	 * Using the last flag, update budget and check whether bfqq
+	 * may want to preempt the in-service queue.
+	 */
+	bfqq_wants_to_preempt =
+		bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
+						    arrived_in_time,
+						    wr_or_deserves_wr);
+
+	/*
+	 * If bfqq happened to be activated in a burst, but has been
+	 * idle for much more than an interactive queue, then we
+	 * assume that, in the overall I/O initiated in the burst, the
+	 * I/O associated with bfqq is finished. So bfqq does not need
+	 * to be treated as a queue belonging to a burst
+	 * anymore. Accordingly, we reset bfqq's in_large_burst flag
+	 * if set, and remove bfqq from the burst list if it's
+	 * there. We do not decrement burst_size, because the fact
+	 * that bfqq does not need to belong to the burst list any
+	 * more does not invalidate the fact that bfqq was created in
+	 * a burst.
+	 */
+	if (likely(!bfq_bfqq_just_created(bfqq)) &&
+	    idle_for_long_time &&
+	    time_is_before_jiffies(
+		    bfqq->budget_timeout +
+		    msecs_to_jiffies(10000))) {
+		hlist_del_init(&bfqq->burst_list_node);
+		bfq_clear_bfqq_in_large_burst(bfqq);
+	}
+
+	bfq_clear_bfqq_just_created(bfqq);
+
+
+	if (!bfq_bfqq_IO_bound(bfqq)) {
+		if (arrived_in_time) {
+			bfqq->requests_within_timer++;
+			if (bfqq->requests_within_timer >=
+			    bfqd->bfq_requests_within_timer)
+				bfq_mark_bfqq_IO_bound(bfqq);
+		} else
+			bfqq->requests_within_timer = 0;
+	}
+
+	if (bfqd->low_latency) {
+		if (unlikely(time_is_after_jiffies(bfqq->split_time)))
+			/* wraparound */
+			bfqq->split_time =
+				jiffies - bfqd->bfq_wr_min_idle_time - 1;
+
+		if (time_is_before_jiffies(bfqq->split_time +
+					   bfqd->bfq_wr_min_idle_time)) {
+			bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+							 old_wr_coeff,
+							 wr_or_deserves_wr,
+							 *interactive,
+							 in_burst,
+							 soft_rt);
+
+			if (old_wr_coeff != bfqq->wr_coeff)
+				bfqq->entity.prio_changed = 1;
+		}
+	}
+
+	bfqq->last_idle_bklogged = jiffies;
+	bfqq->service_from_backlogged = 0;
+	bfq_clear_bfqq_softrt_update(bfqq);
+
+	bfq_add_bfqq_busy(bfqd, bfqq);
+
+	/*
+	 * Expire in-service queue only if preemption may be needed
+	 * for guarantees. In this respect, the function
+	 * next_queue_may_preempt just checks a simple, necessary
+	 * condition, and not a sufficient condition based on
+	 * timestamps. In fact, for the latter condition to be
+	 * evaluated, timestamps would need first to be updated, and
+	 * this operation is quite costly (see the comments on the
+	 * function bfq_bfqq_update_budg_for_activation).
+	 */
+	if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
+	    bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
+	    next_queue_may_preempt(bfqd))
+		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+				false, BFQQE_PREEMPTED);
+}
+
+static void bfq_add_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	struct request *next_rq, *prev;
+	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	bool interactive = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
+	bfqq->queued[rq_is_sync(rq)]++;
+	bfqd->queued++;
+
+	elv_rb_add(&bfqq->sort_list, rq);
+
+	/*
+	 * Check if this request is a better next-serve candidate.
+	 */
+	prev = bfqq->next_rq;
+	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
+	bfqq->next_rq = next_rq;
+
+	/*
+	 * Adjust priority tree position, if next_rq changes.
+	 */
+	if (prev != bfqq->next_rq)
+		bfq_pos_tree_add_move(bfqd, bfqq);
+
+	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
+		bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
+						 rq, &interactive);
+	else {
+		if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+		    time_is_before_jiffies(
+				bfqq->last_wr_start_finish +
+				bfqd->bfq_wr_min_inter_arr_async)) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+			bfqd->wr_busy_queues++;
+			bfqq->entity.prio_changed = 1;
+		}
+		if (prev != bfqq->next_rq)
+			bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	/*
+	 * Assign jiffies to last_wr_start_finish in the following
+	 * cases:
+	 *
+	 * . if bfqq is not going to be weight-raised, because, for
+	 *   non weight-raised queues, last_wr_start_finish stores the
+	 *   arrival time of the last request; as of now, this piece
+	 *   of information is used only for deciding whether to
+	 *   weight-raise async queues
+	 *
+	 * . if bfqq is not weight-raised, because, if bfqq is now
+	 *   switching to weight-raised, then last_wr_start_finish
+	 *   stores the time when weight-raising starts
+	 *
+	 * . if bfqq is interactive, because, regardless of whether
+	 *   bfqq is currently weight-raised, the weight-raising
+	 *   period must start or restart (this case is considered
+	 *   separately because it is not detected by the above
+	 *   conditions, if bfqq is already weight-raised)
+	 *
+	 * last_wr_start_finish has to be updated also if bfqq is soft
+	 * real-time, because the weight-raising period is constantly
+	 * restarted on idle-to-busy transitions for these queues, but
+	 * this is already done in bfq_bfqq_handle_idle_busy_switch if
+	 * needed.
+	 */
+	if (bfqd->low_latency &&
+		(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+		bfqq->last_wr_start_finish = jiffies;
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+					  struct bio *bio,
+					  struct request_queue *q)
+{
+	struct bfq_queue *bfqq = bfqd->bio_bfqq;
+
+
+	if (bfqq)
+		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+	return NULL;
+}
+
+static sector_t get_sdist(sector_t last_pos, struct request *rq)
+{
+	if (last_pos)
+		return abs(blk_rq_pos(rq) - last_pos);
+
+	return 0;
+}
+
+#if 0 /* Still not clear if we can do without next two functions */
+static void bfq_activate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	bfqd->rq_in_driver++;
+}
+
+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	bfqd->rq_in_driver--;
+}
+#endif
+
+static void bfq_remove_request(struct request_queue *q,
+			       struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	const int sync = rq_is_sync(rq);
+
+	if (bfqq->next_rq == rq) {
+		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
+		bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	if (rq->queuelist.prev != &rq->queuelist)
+		list_del_init(&rq->queuelist);
+	bfqq->queued[sync]--;
+	bfqd->queued--;
+	elv_rb_del(&bfqq->sort_list, rq);
+
+	elv_rqhash_del(q, rq);
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		bfqq->next_rq = NULL;
+
+		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
+			bfq_del_bfqq_busy(bfqd, bfqq, false);
+			/*
+			 * bfqq emptied. In normal operation, when
+			 * bfqq is empty, bfqq->entity.service and
+			 * bfqq->entity.budget must contain,
+			 * respectively, the service received and the
+			 * budget used last time bfqq emptied. These
+			 * facts do not hold in this case, as at least
+			 * this last removal occurred while bfqq is
+			 * not in service. To avoid inconsistencies,
+			 * reset both bfqq->entity.service and
+			 * bfqq->entity.budget, if bfqq has still a
+			 * process that may issue I/O requests to it.
+			 */
+			bfqq->entity.budget = bfqq->entity.service = 0;
+		}
+
+		/*
+		 * Remove queue from request-position tree as it is empty.
+		 */
+		if (bfqq->pos_root) {
+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
+			bfqq->pos_root = NULL;
+		}
+	}
+
+	if (rq->cmd_flags & REQ_META)
+		bfqq->meta_pending--;
+
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+}
+
+static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+	struct request_queue *q = hctx->queue;
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct request *free = NULL;
+	/*
+	 * bfq_bic_lookup grabs the queue_lock: invoke it now and
+	 * store its return value for later use, to avoid nesting
+	 * queue_lock inside the bfqd->lock. We assume that the bic
+	 * returned by bfq_bic_lookup does not go away before
+	 * bfqd->lock is taken.
+	 */
+	struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
+	bool ret;
+
+	spin_lock_irq(&bfqd->lock);
+
+	if (bic)
+		bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+	else
+		bfqd->bio_bfqq = NULL;
+	bfqd->bio_bic = bic;
+
+	ret = blk_mq_sched_try_merge(q, bio, &free);
+
+	if (free)
+		blk_mq_free_request(free);
+	spin_unlock_irq(&bfqd->lock);
+
+	return ret;
+}
+
+static int bfq_request_merge(struct request_queue *q, struct request **req,
+			     struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct request *__rq;
+
+	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_request_merged(struct request_queue *q, struct request *req,
+			       enum elv_merge type)
+{
+	if (type == ELEVATOR_FRONT_MERGE &&
+	    rb_prev(&req->rb_node) &&
+	    blk_rq_pos(req) <
+	    blk_rq_pos(container_of(rb_prev(&req->rb_node),
+				    struct request, rb_node))) {
+		struct bfq_queue *bfqq = RQ_BFQQ(req);
+		struct bfq_data *bfqd = bfqq->bfqd;
+		struct request *prev, *next_rq;
+
+		/* Reposition request in its sort_list */
+		elv_rb_del(&bfqq->sort_list, req);
+		elv_rb_add(&bfqq->sort_list, req);
+
+		/* Choose next request to be served for bfqq */
+		prev = bfqq->next_rq;
+		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
+					 bfqd->last_position);
+		bfqq->next_rq = next_rq;
+		/*
+		 * If next_rq changes, update both the queue's budget to
+		 * fit the new request and the queue's position in its
+		 * rq_pos_tree.
+		 */
+		if (prev != bfqq->next_rq) {
+			bfq_updated_next_req(bfqd, bfqq);
+			bfq_pos_tree_add_move(bfqd, bfqq);
+		}
+	}
+}
+
+static void bfq_requests_merged(struct request_queue *q, struct request *rq,
+				struct request *next)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+	if (!RB_EMPTY_NODE(&rq->rb_node))
+		goto end;
+	spin_lock_irq(&bfqq->bfqd->lock);
+
+	/*
+	 * If next and rq belong to the same bfq_queue and next is older
+	 * than rq, then reposition rq in the fifo (by substituting next
+	 * with rq). Otherwise, if next and rq belong to different
+	 * bfq_queues, never reposition rq: in fact, we would have to
+	 * reposition it with respect to next's position in its own fifo,
+	 * which would most certainly be too expensive with respect to
+	 * the benefits.
+	 */
+	if (bfqq == next_bfqq &&
+	    !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+	    next->fifo_time < rq->fifo_time) {
+		list_del_init(&rq->queuelist);
+		list_replace_init(&next->queuelist, &rq->queuelist);
+		rq->fifo_time = next->fifo_time;
+	}
+
+	if (bfqq->next_rq == next)
+		bfqq->next_rq = rq;
+
+	bfq_remove_request(q, next);
+
+	spin_unlock_irq(&bfqq->bfqd->lock);
+end:
+	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+}
+
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_busy(bfqq))
+		bfqq->bfqd->wr_busy_queues--;
+	bfqq->wr_coeff = 1;
+	bfqq->wr_cur_max_time = 0;
+	bfqq->last_wr_start_finish = jiffies;
+	/*
+	 * Trigger a weight change on the next invocation of
+	 * __bfq_entity_update_weight_prio.
+	 */
+	bfqq->entity.prio_changed = 1;
+}
+
+void bfq_end_wr_async_queues(struct bfq_data *bfqd,
+			     struct bfq_group *bfqg)
+{
+	int i, j;
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < IOPRIO_BE_NR; j++)
+			if (bfqg->async_bfqq[i][j])
+				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+	if (bfqg->async_idle_bfqq)
+		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+
+	spin_lock_irq(&bfqd->lock);
+
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	bfq_end_wr_async(bfqd);
+
+	spin_unlock_irq(&bfqd->lock);
+}
+
+static sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+	if (request)
+		return blk_rq_pos(io_struct);
+	else
+		return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static int bfq_rq_close_to_sector(void *io_struct, bool request,
+				  sector_t sector)
+{
+	return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
+	       BFQQ_CLOSE_THR;
+}
+
+static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
+					 struct bfq_queue *bfqq,
+					 sector_t sector)
+{
+	struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	struct rb_node *parent, *node;
+	struct bfq_queue *__bfqq;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+	if (__bfqq)
+		return __bfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector (rq_pos_tree sorted by
+	 * next_request position).
+	 */
+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	if (blk_rq_pos(__bfqq->next_rq) < sector)
+		node = rb_next(&__bfqq->pos_node);
+	else
+		node = rb_prev(&__bfqq->pos_node);
+	if (!node)
+		return NULL;
+
+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	return NULL;
+}
+
+static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
+						   struct bfq_queue *cur_bfqq,
+						   sector_t sector)
+{
+	struct bfq_queue *bfqq;
+
+	/*
+	 * We shall notice if some of the queues are cooperating,
+	 * e.g., working closely on the same area of the device. In
+	 * that case, we can group them together and: 1) don't waste
+	 * time idling, and 2) serve the union of their requests in
+	 * the best possible order for throughput.
+	 */
+	bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
+	if (!bfqq || bfqq == cur_bfqq)
+		return NULL;
+
+	return bfqq;
+}
+
+static struct bfq_queue *
+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	int process_refs, new_process_refs;
+	struct bfq_queue *__bfqq;
+
+	/*
+	 * If there are no process references on the new_bfqq, then it is
+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+	 * may have dropped their last reference (not just their last process
+	 * reference).
+	 */
+	if (!bfqq_process_refs(new_bfqq))
+		return NULL;
+
+	/* Avoid a circular list and skip interim queue merges. */
+	while ((__bfqq = new_bfqq->new_bfqq)) {
+		if (__bfqq == bfqq)
+			return NULL;
+		new_bfqq = __bfqq;
+	}
+
+	process_refs = bfqq_process_refs(bfqq);
+	new_process_refs = bfqq_process_refs(new_bfqq);
+	/*
+	 * If the process for the bfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0 || new_process_refs == 0)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+		new_bfqq->pid);
+
+	/*
+	 * Merging is just a redirection: the requests of the process
+	 * owning one of the two queues are redirected to the other queue.
+	 * The latter queue, in its turn, is set as shared if this is the
+	 * first time that the requests of some process are redirected to
+	 * it.
+	 *
+	 * We redirect bfqq to new_bfqq and not the opposite, because
+	 * we are in the context of the process owning bfqq, thus we
+	 * have the io_cq of this process. So we can immediately
+	 * configure this io_cq to redirect the requests of the
+	 * process to new_bfqq. In contrast, the io_cq of new_bfqq is
+	 * not available any more (new_bfqq->bic == NULL).
+	 *
+	 * Anyway, even in case new_bfqq coincides with the in-service
+	 * queue, redirecting requests the in-service queue is the
+	 * best option, as we feed the in-service queue with new
+	 * requests close to the last request served and, by doing so,
+	 * are likely to increase the throughput.
+	 */
+	bfqq->new_bfqq = new_bfqq;
+	new_bfqq->ref += process_refs;
+	return new_bfqq;
+}
+
+static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
+					struct bfq_queue *new_bfqq)
+{
+	if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
+	    (bfqq->ioprio_class != new_bfqq->ioprio_class))
+		return false;
+
+	/*
+	 * If either of the queues has already been detected as seeky,
+	 * then merging it with the other queue is unlikely to lead to
+	 * sequential I/O.
+	 */
+	if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
+		return false;
+
+	/*
+	 * Interleaved I/O is known to be done by (some) applications
+	 * only for reads, so it does not make sense to merge async
+	 * queues.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
+		return false;
+
+	return true;
+}
+
+/*
+ * If this function returns true, then bfqq cannot be merged. The idea
+ * is that true cooperation happens very early after processes start
+ * to do I/O. Usually, late cooperations are just accidental false
+ * positives. In case bfqq is weight-raised, such false positives
+ * would evidently degrade latency guarantees for bfqq.
+ */
+static bool wr_from_too_long(struct bfq_queue *bfqq)
+{
+	return bfqq->wr_coeff > 1 &&
+		time_is_before_jiffies(bfqq->last_wr_start_finish +
+				       msecs_to_jiffies(100));
+}
+
+/*
+ * Attempt to schedule a merge of bfqq with the currently in-service
+ * queue or with a close queue among the scheduled queues.  Return
+ * NULL if no merge was scheduled, a pointer to the shared bfq_queue
+ * structure otherwise.
+ *
+ * The OOM queue is not allowed to participate to cooperation: in fact, since
+ * the requests temporarily redirected to the OOM queue could be redirected
+ * again to dedicated queues at any time, the state needed to correctly
+ * handle merging with the OOM queue would be quite complex and expensive
+ * to maintain. Besides, in such a critical condition as an out of memory,
+ * the benefits of queue merging may be little relevant, or even negligible.
+ *
+ * Weight-raised queues can be merged only if their weight-raising
+ * period has just started. In fact cooperating processes are usually
+ * started together. Thus, with this filter we avoid false positives
+ * that would jeopardize low-latency guarantees.
+ *
+ * WARNING: queue merging may impair fairness among non-weight raised
+ * queues, for at least two reasons: 1) the original weight of a
+ * merged queue may change during the merged state, 2) even being the
+ * weight the same, a merged queue may be bloated with many more
+ * requests than the ones produced by its originally-associated
+ * process.
+ */
+static struct bfq_queue *
+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     void *io_struct, bool request)
+{
+	struct bfq_queue *in_service_bfqq, *new_bfqq;
+
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
+	if (!io_struct ||
+	    wr_from_too_long(bfqq) ||
+	    unlikely(bfqq == &bfqd->oom_bfqq))
+		return NULL;
+
+	/* If there is only one backlogged queue, don't search. */
+	if (bfqd->busy_queues == 1)
+		return NULL;
+
+	in_service_bfqq = bfqd->in_service_queue;
+
+	if (!in_service_bfqq || in_service_bfqq == bfqq
+	    || wr_from_too_long(in_service_bfqq) ||
+	    unlikely(in_service_bfqq == &bfqd->oom_bfqq))
+		goto check_scheduled;
+
+	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+	    bfqq->entity.parent == in_service_bfqq->entity.parent &&
+	    bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
+		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+		if (new_bfqq)
+			return new_bfqq;
+	}
+	/*
+	 * Check whether there is a cooperator among currently scheduled
+	 * queues. The only thing we need is that the bio/request is not
+	 * NULL, as we need it to establish whether a cooperator exists.
+	 */
+check_scheduled:
+	new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
+			bfq_io_struct_pos(io_struct, request));
+
+	if (new_bfqq && !wr_from_too_long(new_bfqq) &&
+	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
+		return bfq_setup_merge(bfqq, new_bfqq);
+
+	return NULL;
+}
+
+static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+	struct bfq_io_cq *bic = bfqq->bic;
+
+	/*
+	 * If !bfqq->bic, the queue is already shared or its requests
+	 * have already been redirected to a shared queue; both idle window
+	 * and weight raising state have already been saved. Do nothing.
+	 */
+	if (!bic)
+		return;
+
+	bic->saved_ttime = bfqq->ttime;
+	bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
+	bic->saved_wr_coeff = bfqq->wr_coeff;
+	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
+	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+}
+
+static void
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+		(unsigned long)new_bfqq->pid);
+	/* Save weight raising and idle window of the merged queues */
+	bfq_bfqq_save_state(bfqq);
+	bfq_bfqq_save_state(new_bfqq);
+	if (bfq_bfqq_IO_bound(bfqq))
+		bfq_mark_bfqq_IO_bound(new_bfqq);
+	bfq_clear_bfqq_IO_bound(bfqq);
+
+	/*
+	 * If bfqq is weight-raised, then let new_bfqq inherit
+	 * weight-raising. To reduce false positives, neglect the case
+	 * where bfqq has just been created, but has not yet made it
+	 * to be weight-raised (which may happen because EQM may merge
+	 * bfqq even before bfq_add_request is executed for the first
+	 * time for bfqq). Handling this case would however be very
+	 * easy, thanks to the flag just_created.
+	 */
+	if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
+		new_bfqq->wr_coeff = bfqq->wr_coeff;
+		new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
+		new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
+		new_bfqq->wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		if (bfq_bfqq_busy(new_bfqq))
+			bfqd->wr_busy_queues++;
+		new_bfqq->entity.prio_changed = 1;
+	}
+
+	if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
+		bfqq->wr_coeff = 1;
+		bfqq->entity.prio_changed = 1;
+		if (bfq_bfqq_busy(bfqq))
+			bfqd->wr_busy_queues--;
+	}
+
+	bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
+		     bfqd->wr_busy_queues);
+
+	/*
+	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
+	 */
+	bic_set_bfqq(bic, new_bfqq, 1);
+	bfq_mark_bfqq_coop(new_bfqq);
+	/*
+	 * new_bfqq now belongs to at least two bics (it is a shared queue):
+	 * set new_bfqq->bic to NULL. bfqq either:
+	 * - does not belong to any bic any more, and hence bfqq->bic must
+	 *   be set to NULL, or
+	 * - is a queue whose owning bics have already been redirected to a
+	 *   different queue, hence the queue is destined to not belong to
+	 *   any bic soon and bfqq->bic is already NULL (therefore the next
+	 *   assignment causes no harm).
+	 */
+	new_bfqq->bic = NULL;
+	bfqq->bic = NULL;
+	/* release process reference to bfqq */
+	bfq_put_queue(bfqq);
+}
+
+static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+				struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	bool is_sync = op_is_sync(bio->bi_opf);
+	struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
+
+	/*
+	 * Disallow merge of a sync bio into an async request.
+	 */
+	if (is_sync && !rq_is_sync(rq))
+		return false;
+
+	/*
+	 * Lookup the bfqq that this bio will be queued with. Allow
+	 * merge only if rq is queued there.
+	 */
+	if (!bfqq)
+		return false;
+
+	/*
+	 * We take advantage of this function to perform an early merge
+	 * of the queues of possible cooperating processes.
+	 */
+	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+	if (new_bfqq) {
+		/*
+		 * bic still points to bfqq, then it has not yet been
+		 * redirected to some other bfq_queue, and a queue
+		 * merge beween bfqq and new_bfqq can be safely
+		 * fulfillled, i.e., bic can be redirected to new_bfqq
+		 * and bfqq can be put.
+		 */
+		bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
+				new_bfqq);
+		/*
+		 * If we get here, bio will be queued into new_queue,
+		 * so use new_bfqq to decide whether bio and rq can be
+		 * merged.
+		 */
+		bfqq = new_bfqq;
+
+		/*
+		 * Change also bqfd->bio_bfqq, as
+		 * bfqd->bio_bic now points to new_bfqq, and
+		 * this function may be invoked again (and then may
+		 * use again bqfd->bio_bfqq).
+		 */
+		bfqd->bio_bfqq = bfqq;
+	}
+
+	return bfqq == RQ_BFQQ(rq);
+}
+
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the throughput.
+ * In practice, a time-slice service scheme is used with seeky
+ * processes.
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq)
+{
+	unsigned int timeout_coeff;
+
+	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+		timeout_coeff = 1;
+	else
+		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
+	bfqd->last_budget_start = ktime_get();
+
+	bfqq->budget_timeout = jiffies +
+		bfqd->bfq_timeout * timeout_coeff;
+}
+
+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq)
+{
+	if (bfqq) {
+		bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
+		bfq_clear_bfqq_fifo_expire(bfqq);
+
+		bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;
+
+		if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
+		    bfqq->wr_coeff > 1 &&
+		    bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    time_is_before_jiffies(bfqq->budget_timeout)) {
+			/*
+			 * For soft real-time queues, move the start
+			 * of the weight-raising period forward by the
+			 * time the queue has not received any
+			 * service. Otherwise, a relatively long
+			 * service delay is likely to cause the
+			 * weight-raising period of the queue to end,
+			 * because of the short duration of the
+			 * weight-raising period of a soft real-time
+			 * queue.  It is worth noting that this move
+			 * is not so dangerous for the other queues,
+			 * because soft real-time queues are not
+			 * greedy.
+			 *
+			 * To not add a further variable, we use the
+			 * overloaded field budget_timeout to
+			 * determine for how long the queue has not
+			 * received service, i.e., how much time has
+			 * elapsed since the queue expired. However,
+			 * this is a little imprecise, because
+			 * budget_timeout is set to jiffies if bfqq
+			 * not only expires, but also remains with no
+			 * request.
+			 */
+			if (time_after(bfqq->budget_timeout,
+				       bfqq->last_wr_start_finish))
+				bfqq->last_wr_start_finish +=
+					jiffies - bfqq->budget_timeout;
+			else
+				bfqq->last_wr_start_finish = jiffies;
+		}
+
+		bfq_set_budget_timeout(bfqd, bfqq);
+		bfq_log_bfqq(bfqd, bfqq,
+			     "set_in_service_queue, cur-budget = %d",
+			     bfqq->entity.budget);
+	}
+
+	bfqd->in_service_queue = bfqq;
+}
+
+/*
+ * Get and set a new queue for service.
+ */
+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);
+
+	__bfq_set_in_service_queue(bfqd, bfqq);
+	return bfqq;
+}
+
+static void bfq_arm_slice_timer(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq = bfqd->in_service_queue;
+	u32 sl;
+
+	bfq_mark_bfqq_wait_request(bfqq);
+
+	/*
+	 * We don't want to idle for seeks, but we do want to allow
+	 * fair distribution of slice time for a process doing back-to-back
+	 * seeks. So allow a little bit of time for him to submit a new rq.
+	 */
+	sl = bfqd->bfq_slice_idle;
+	/*
+	 * Unless the queue is being weight-raised or the scenario is
+	 * asymmetric, grant only minimum idle time if the queue
+	 * is seeky. A long idling is preserved for a weight-raised
+	 * queue, or, more in general, in an asymmetric scenario,
+	 * because a long idling is needed for guaranteeing to a queue
+	 * its reserved share of the throughput (in particular, it is
+	 * needed if the queue has a higher weight than some other
+	 * queue).
+	 */
+	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+	    bfq_symmetric_scenario(bfqd))
+		sl = min_t(u64, sl, BFQ_MIN_TT);
+
+	bfqd->last_idling_start = ktime_get();
+	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
+		      HRTIMER_MODE_REL);
+	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
+}
+
+/*
+ * In autotuning mode, max_budget is dynamically recomputed as the
+ * amount of sectors transferred in timeout at the estimated peak
+ * rate. This enables BFQ to utilize a full timeslice with a full
+ * budget, even if the in-service queue is served at peak rate. And
+ * this maximises throughput with sequential workloads.
+ */
+static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
+{
+	return (u64)bfqd->peak_rate * USEC_PER_MSEC *
+		jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
+}
+
+/*
+ * Update parameters related to throughput and responsiveness, as a
+ * function of the estimated peak rate. See comments on
+ * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ */
+static void update_thr_responsiveness_params(struct bfq_data *bfqd)
+{
+	int dev_type = blk_queue_nonrot(bfqd->queue);
+
+	if (bfqd->bfq_user_max_budget == 0)
+		bfqd->bfq_max_budget =
+			bfq_calc_max_budget(bfqd);
+
+	if (bfqd->device_speed == BFQ_BFQD_FAST &&
+	    bfqd->peak_rate < device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_SLOW;
+		bfqd->RT_prod = R_slow[dev_type] *
+			T_slow[dev_type];
+	} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+		   bfqd->peak_rate > device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_FAST;
+		bfqd->RT_prod = R_fast[dev_type] *
+			T_fast[dev_type];
+	}
+
+	bfq_log(bfqd,
+"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
+		dev_type == 0 ? "ROT" : "NONROT",
+		bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
+		bfqd->device_speed == BFQ_BFQD_FAST ?
+		(USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
+		(USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
+		(USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
+		BFQ_RATE_SHIFT);
+}
+
+static void bfq_reset_rate_computation(struct bfq_data *bfqd,
+				       struct request *rq)
+{
+	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
+		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+		bfqd->peak_rate_samples = 1;
+		bfqd->sequential_samples = 0;
+		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
+			blk_rq_sectors(rq);
+	} else /* no new rq dispatched, just reset the number of samples */
+		bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
+
+	bfq_log(bfqd,
+		"reset_rate_computation at end, sample %u/%u tot_sects %llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		bfqd->tot_sectors_dispatched);
+}
+
+static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
+{
+	u32 rate, weight, divisor;
+
+	/*
+	 * For the convergence property to hold (see comments on
+	 * bfq_update_peak_rate()) and for the assessment to be
+	 * reliable, a minimum number of samples must be present, and
+	 * a minimum amount of time must have elapsed. If not so, do
+	 * not compute new rate. Just reset parameters, to get ready
+	 * for a new evaluation attempt.
+	 */
+	if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
+	    bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL)
+		goto reset_computation;
+
+	/*
+	 * If a new request completion has occurred after last
+	 * dispatch, then, to approximate the rate at which requests
+	 * have been served by the device, it is more precise to
+	 * extend the observation interval to the last completion.
+	 */
+	bfqd->delta_from_first =
+		max_t(u64, bfqd->delta_from_first,
+		      bfqd->last_completion - bfqd->first_dispatch);
+
+	/*
+	 * Rate computed in sects/usec, and not sects/nsec, for
+	 * precision issues.
+	 */
+	rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
+			div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
+
+	/*
+	 * Peak rate not updated if:
+	 * - the percentage of sequential dispatches is below 3/4 of the
+	 *   total, and rate is below the current estimated peak rate
+	 * - rate is unreasonably high (> 20M sectors/sec)
+	 */
+	if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
+	     rate <= bfqd->peak_rate) ||
+		rate > 20<<BFQ_RATE_SHIFT)
+		goto reset_computation;
+
+	/*
+	 * We have to update the peak rate, at last! To this purpose,
+	 * we use a low-pass filter. We compute the smoothing constant
+	 * of the filter as a function of the 'weight' of the new
+	 * measured rate.
+	 *
+	 * As can be seen in next formulas, we define this weight as a
+	 * quantity proportional to how sequential the workload is,
+	 * and to how long the observation time interval is.
+	 *
+	 * The weight runs from 0 to 8. The maximum value of the
+	 * weight, 8, yields the minimum value for the smoothing
+	 * constant. At this minimum value for the smoothing constant,
+	 * the measured rate contributes for half of the next value of
+	 * the estimated peak rate.
+	 *
+	 * So, the first step is to compute the weight as a function
+	 * of how sequential the workload is. Note that the weight
+	 * cannot reach 9, because bfqd->sequential_samples cannot
+	 * become equal to bfqd->peak_rate_samples, which, in its
+	 * turn, holds true because bfqd->sequential_samples is not
+	 * incremented for the first sample.
+	 */
+	weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
+
+	/*
+	 * Second step: further refine the weight as a function of the
+	 * duration of the observation interval.
+	 */
+	weight = min_t(u32, 8,
+		       div_u64(weight * bfqd->delta_from_first,
+			       BFQ_RATE_REF_INTERVAL));
+
+	/*
+	 * Divisor ranging from 10, for minimum weight, to 2, for
+	 * maximum weight.
+	 */
+	divisor = 10 - weight;
+
+	/*
+	 * Finally, update peak rate:
+	 *
+	 * peak_rate = peak_rate * (divisor-1) / divisor  +  rate / divisor
+	 */
+	bfqd->peak_rate *= divisor-1;
+	bfqd->peak_rate /= divisor;
+	rate /= divisor; /* smoothing constant alpha = 1/divisor */
+
+	bfqd->peak_rate += rate;
+	update_thr_responsiveness_params(bfqd);
+
+reset_computation:
+	bfq_reset_rate_computation(bfqd, rq);
+}
+
+/*
+ * Update the read/write peak rate (the main quantity used for
+ * auto-tuning, see update_thr_responsiveness_params()).
+ *
+ * It is not trivial to estimate the peak rate (correctly): because of
+ * the presence of sw and hw queues between the scheduler and the
+ * device components that finally serve I/O requests, it is hard to
+ * say exactly when a given dispatched request is served inside the
+ * device, and for how long. As a consequence, it is hard to know
+ * precisely at what rate a given set of requests is actually served
+ * by the device.
+ *
+ * On the opposite end, the dispatch time of any request is trivially
+ * available, and, from this piece of information, the "dispatch rate"
+ * of requests can be immediately computed. So, the idea in the next
+ * function is to use what is known, namely request dispatch times
+ * (plus, when useful, request completion times), to estimate what is
+ * unknown, namely in-device request service rate.
+ *
+ * The main issue is that, because of the above facts, the rate at
+ * which a certain set of requests is dispatched over a certain time
+ * interval can vary greatly with respect to the rate at which the
+ * same requests are then served. But, since the size of any
+ * intermediate queue is limited, and the service scheme is lossless
+ * (no request is silently dropped), the following obvious convergence
+ * property holds: the number of requests dispatched MUST become
+ * closer and closer to the number of requests completed as the
+ * observation interval grows. This is the key property used in
+ * the next function to estimate the peak service rate as a function
+ * of the observed dispatch rate. The function assumes to be invoked
+ * on every request dispatch.
+ */
+static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
+{
+	u64 now_ns = ktime_get_ns();
+
+	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
+		bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
+			bfqd->peak_rate_samples);
+		bfq_reset_rate_computation(bfqd, rq);
+		goto update_last_values; /* will add one sample */
+	}
+
+	/*
+	 * Device idle for very long: the observation interval lasting
+	 * up to this dispatch cannot be a valid observation interval
+	 * for computing a new peak rate (similarly to the late-
+	 * completion event in bfq_completed_request()). Go to
+	 * update_rate_and_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - start a new observation interval with this dispatch
+	 */
+	if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
+	    bfqd->rq_in_driver == 0)
+		goto update_rate_and_reset;
+
+	/* Update sampling information */
+	bfqd->peak_rate_samples++;
+
+	if ((bfqd->rq_in_driver > 0 ||
+		now_ns - bfqd->last_completion < BFQ_MIN_TT)
+	     && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
+		bfqd->sequential_samples++;
+
+	bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
+
+	/* Reset max observed rq size every 32 dispatches */
+	if (likely(bfqd->peak_rate_samples % 32))
+		bfqd->last_rq_max_size =
+			max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
+	else
+		bfqd->last_rq_max_size = blk_rq_sectors(rq);
+
+	bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
+
+	/* Target observation interval not yet reached, go on sampling */
+	if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
+		goto update_last_values;
+
+update_rate_and_reset:
+	bfq_update_rate_reset(bfqd, rq);
+update_last_values:
+	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+	bfqd->last_dispatch = now_ns;
+}
+
+/*
+ * Remove request from internal lists.
+ */
+static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	/*
+	 * For consistency, the next instruction should have been
+	 * executed after removing the request from the queue and
+	 * dispatching it.  We execute instead this instruction before
+	 * bfq_remove_request() (and hence introduce a temporary
+	 * inconsistency), for efficiency.  In fact, should this
+	 * dispatch occur for a non in-service bfqq, this anticipated
+	 * increment prevents two counters related to bfqq->dispatched
+	 * from risking to be, first, uselessly decremented, and then
+	 * incremented again when the (new) value of bfqq->dispatched
+	 * happens to be taken into account.
+	 */
+	bfqq->dispatched++;
+	bfq_update_peak_rate(q->elevator->elevator_data, rq);
+
+	bfq_remove_request(q, rq);
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * If this bfqq is shared between multiple processes, check
+	 * to make sure that those processes are still issuing I/Os
+	 * within the mean seek distance. If not, it may be time to
+	 * break the queues apart again.
+	 */
+	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+		bfq_mark_bfqq_split_coop(bfqq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		if (bfqq->dispatched == 0)
+			/*
+			 * Overloading budget_timeout field to store
+			 * the time at which the queue remains with no
+			 * backlog and no outstanding request; used by
+			 * the weight-raising mechanism.
+			 */
+			bfqq->budget_timeout = jiffies;
+
+		bfq_del_bfqq_busy(bfqd, bfqq, true);
+	} else {
+		bfq_requeue_bfqq(bfqd, bfqq);
+		/*
+		 * Resort priority tree of potential close cooperators.
+		 */
+		bfq_pos_tree_add_move(bfqd, bfqq);
+	}
+
+	/*
+	 * All in-service entities must have been properly deactivated
+	 * or requeued before executing the next function, which
+	 * resets all in-service entites as no more in service.
+	 */
+	__bfq_bfqd_reset_in_service(bfqd);
+}
+
+/**
+ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
+ * @bfqd: device data.
+ * @bfqq: queue to update.
+ * @reason: reason for expiration.
+ *
+ * Handle the feedback on @bfqq budget at queue expiration.
+ * See the body for detailed comments.
+ */
+static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
+				     struct bfq_queue *bfqq,
+				     enum bfqq_expiration reason)
+{
+	struct request *next_rq;
+	int budget, min_budget;
+
+	min_budget = bfq_min_budget(bfqd);
+
+	if (bfqq->wr_coeff == 1)
+		budget = bfqq->max_budget;
+	else /*
+	      * Use a constant, low budget for weight-raised queues,
+	      * to help achieve a low latency. Keep it slightly higher
+	      * than the minimum possible budget, to cause a little
+	      * bit fewer expirations.
+	      */
+		budget = 2 * min_budget;
+
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
+		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
+		budget, bfq_min_budget(bfqd));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
+		bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
+
+	if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) {
+		switch (reason) {
+		/*
+		 * Caveat: in all the following cases we trade latency
+		 * for throughput.
+		 */
+		case BFQQE_TOO_IDLE:
+			/*
+			 * This is the only case where we may reduce
+			 * the budget: if there is no request of the
+			 * process still waiting for completion, then
+			 * we assume (tentatively) that the timer has
+			 * expired because the batch of requests of
+			 * the process could have been served with a
+			 * smaller budget.  Hence, betting that
+			 * process will behave in the same way when it
+			 * becomes backlogged again, we reduce its
+			 * next budget.  As long as we guess right,
+			 * this budget cut reduces the latency
+			 * experienced by the process.
+			 *
+			 * However, if there are still outstanding
+			 * requests, then the process may have not yet
+			 * issued its next request just because it is
+			 * still waiting for the completion of some of
+			 * the still outstanding ones.  So in this
+			 * subcase we do not reduce its budget, on the
+			 * contrary we increase it to possibly boost
+			 * the throughput, as discussed in the
+			 * comments to the BUDGET_TIMEOUT case.
+			 */
+			if (bfqq->dispatched > 0) /* still outstanding reqs */
+				budget = min(budget * 2, bfqd->bfq_max_budget);
+			else {
+				if (budget > 5 * min_budget)
+					budget -= 4 * min_budget;
+				else
+					budget = min_budget;
+			}
+			break;
+		case BFQQE_BUDGET_TIMEOUT:
+			/*
+			 * We double the budget here because it gives
+			 * the chance to boost the throughput if this
+			 * is not a seeky process (and has bumped into
+			 * this timeout because of, e.g., ZBR).
+			 */
+			budget = min(budget * 2, bfqd->bfq_max_budget);
+			break;
+		case BFQQE_BUDGET_EXHAUSTED:
+			/*
+			 * The process still has backlog, and did not
+			 * let either the budget timeout or the disk
+			 * idling timeout expire. Hence it is not
+			 * seeky, has a short thinktime and may be
+			 * happy with a higher budget too. So
+			 * definitely increase the budget of this good
+			 * candidate to boost the disk throughput.
+			 */
+			budget = min(budget * 4, bfqd->bfq_max_budget);
+			break;
+		case BFQQE_NO_MORE_REQUESTS:
+			/*
+			 * For queues that expire for this reason, it
+			 * is particularly important to keep the
+			 * budget close to the actual service they
+			 * need. Doing so reduces the timestamp
+			 * misalignment problem described in the
+			 * comments in the body of
+			 * __bfq_activate_entity. In fact, suppose
+			 * that a queue systematically expires for
+			 * BFQQE_NO_MORE_REQUESTS and presents a
+			 * new request in time to enjoy timestamp
+			 * back-shifting. The larger the budget of the
+			 * queue is with respect to the service the
+			 * queue actually requests in each service
+			 * slot, the more times the queue can be
+			 * reactivated with the same virtual finish
+			 * time. It follows that, even if this finish
+			 * time is pushed to the system virtual time
+			 * to reduce the consequent timestamp
+			 * misalignment, the queue unjustly enjoys for
+			 * many re-activations a lower finish time
+			 * than all newly activated queues.
+			 *
+			 * The service needed by bfqq is measured
+			 * quite precisely by bfqq->entity.service.
+			 * Since bfqq does not enjoy device idling,
+			 * bfqq->entity.service is equal to the number
+			 * of sectors that the process associated with
+			 * bfqq requested to read/write before waiting
+			 * for request completions, or blocking for
+			 * other reasons.
+			 */
+			budget = max_t(int, bfqq->entity.service, min_budget);
+			break;
+		default:
+			return;
+		}
+	} else if (!bfq_bfqq_sync(bfqq)) {
+		/*
+		 * Async queues get always the maximum possible
+		 * budget, as for them we do not care about latency
+		 * (in addition, their ability to dispatch is limited
+		 * by the charging factor).
+		 */
+		budget = bfqd->bfq_max_budget;
+	}
+
+	bfqq->max_budget = budget;
+
+	if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
+	    !bfqd->bfq_user_max_budget)
+		bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);
+
+	/*
+	 * If there is still backlog, then assign a new budget, making
+	 * sure that it is large enough for the next request.  Since
+	 * the finish time of bfqq must be kept in sync with the
+	 * budget, be sure to call __bfq_bfqq_expire() *after* this
+	 * update.
+	 *
+	 * If there is no backlog, then no need to update the budget;
+	 * it will be updated on the arrival of a new request.
+	 */
+	next_rq = bfqq->next_rq;
+	if (next_rq)
+		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+					    bfq_serv_to_charge(next_rq, bfqq));
+
+	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
+			next_rq ? blk_rq_sectors(next_rq) : 0,
+			bfqq->entity.budget);
+}
+
+/*
+ * Return true if the process associated with bfqq is "slow". The slow
+ * flag is used, in addition to the budget timeout, to reduce the
+ * amount of service provided to seeky processes, and thus reduce
+ * their chances to lower the throughput. More details in the comments
+ * on the function bfq_bfqq_expire().
+ *
+ * An important observation is in order: as discussed in the comments
+ * on the function bfq_update_peak_rate(), with devices with internal
+ * queues, it is hard if ever possible to know when and for how long
+ * an I/O request is processed by the device (apart from the trivial
+ * I/O pattern where a new request is dispatched only after the
+ * previous one has been completed). This makes it hard to evaluate
+ * the real rate at which the I/O requests of each bfq_queue are
+ * served.  In fact, for an I/O scheduler like BFQ, serving a
+ * bfq_queue means just dispatching its requests during its service
+ * slot (i.e., until the budget of the queue is exhausted, or the
+ * queue remains idle, or, finally, a timeout fires). But, during the
+ * service slot of a bfq_queue, around 100 ms at most, the device may
+ * be even still processing requests of bfq_queues served in previous
+ * service slots. On the opposite end, the requests of the in-service
+ * bfq_queue may be completed after the service slot of the queue
+ * finishes.
+ *
+ * Anyway, unless more sophisticated solutions are used
+ * (where possible), the sum of the sizes of the requests dispatched
+ * during the service slot of a bfq_queue is probably the only
+ * approximation available for the service received by the bfq_queue
+ * during its service slot. And this sum is the quantity used in this
+ * function to evaluate the I/O speed of a process.
+ */
+static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				 bool compensate, enum bfqq_expiration reason,
+				 unsigned long *delta_ms)
+{
+	ktime_t delta_ktime;
+	u32 delta_usecs;
+	bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
+
+	if (!bfq_bfqq_sync(bfqq))
+		return false;
+
+	if (compensate)
+		delta_ktime = bfqd->last_idling_start;
+	else
+		delta_ktime = ktime_get();
+	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
+	delta_usecs = ktime_to_us(delta_ktime);
+
+	/* don't use too short time intervals */
+	if (delta_usecs < 1000) {
+		if (blk_queue_nonrot(bfqd->queue))
+			 /*
+			  * give same worst-case guarantees as idling
+			  * for seeky
+			  */
+			*delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
+		else /* charge at least one seek */
+			*delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
+
+		return slow;
+	}
+
+	*delta_ms = delta_usecs / USEC_PER_MSEC;
+
+	/*
+	 * Use only long (> 20ms) intervals to filter out excessive
+	 * spikes in service rate estimation.
+	 */
+	if (delta_usecs > 20000) {
+		/*
+		 * Caveat for rotational devices: processes doing I/O
+		 * in the slower disk zones tend to be slow(er) even
+		 * if not seeky. In this respect, the estimated peak
+		 * rate is likely to be an average over the disk
+		 * surface. Accordingly, to not be too harsh with
+		 * unlucky processes, a process is deemed slow only if
+		 * its rate has been lower than half of the estimated
+		 * peak rate.
+		 */
+		slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
+
+	return slow;
+}
+
+/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, the application must not require an average
+ * bandwidth higher than the approximate bandwidth required to playback or
+ * record a compressed high-definition video.
+ * The next function is invoked on the completion of the last request of a
+ * batch, to compute the next-start time instant, soft_rt_next_start, such
+ * that, if the next request of the application does not arrive before
+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
+ *
+ * The second requirement is that the request pattern of the application is
+ * isochronous, i.e., that, after issuing a request or a batch of requests,
+ * the application stops issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue a new batch,
+ * and so on.
+ * For this reason the next function is invoked to compute
+ * soft_rt_next_start only for applications that meet this requirement,
+ * whereas soft_rt_next_start is set to infinity for applications that do
+ * not.
+ *
+ * Unfortunately, even a greedy application may happen to behave in an
+ * isochronous way if the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop again for a while, and so on. In addition, if
+ * the disk achieves a low enough throughput with the request pattern
+ * issued by the application (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement too. To prevent such a greedy application to be
+ * deemed as soft real-time, a further rule is used in the computation of
+ * soft_rt_next_start: soft_rt_next_start must be higher than the current
+ * time plus the maximum time for which the arrival of a request is waited
+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
+ * This filters out greedy applications, as the latter issue instead their
+ * next request as soon as possible after the last one has been completed
+ * (in contrast, when a batch of requests is completed, a soft real-time
+ * application spends some time processing data).
+ *
+ * Unfortunately, the last filter may easily generate false positives if
+ * only bfqd->bfq_slice_idle is used as a reference time interval and one
+ * or both the following cases occur:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
+ *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
+ *    HZ=100.
+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
+ *    for a while, then suddenly 'jump' by several units to recover the lost
+ *    increments. This seems to happen, e.g., inside virtual machines.
+ * To address this issue, we do not use as a reference time interval just
+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
+ * particular we add the minimum number of jiffies for which the filter
+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual
+ * machines.
+ */
+static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq)
+{
+	return max(bfqq->last_idle_bklogged +
+		   HZ * bfqq->service_from_backlogged /
+		   bfqd->bfq_wr_max_softrt_rate,
+		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+}
+
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+	return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+	return jiffies - MAX_JIFFY_OFFSET;
+}
+
+/**
+ * bfq_bfqq_expire - expire a queue.
+ * @bfqd: device owning the queue.
+ * @bfqq: the queue to expire.
+ * @compensate: if true, compensate for the time spent idling.
+ * @reason: the reason causing the expiration.
+ *
+ * If the process associated with bfqq does slow I/O (e.g., because it
+ * issues random requests), we charge bfqq with the time it has been
+ * in service instead of the service it has received (see
+ * bfq_bfqq_charge_time for details on how this goal is achieved). As
+ * a consequence, bfqq will typically get higher timestamps upon
+ * reactivation, and hence it will be rescheduled as if it had
+ * received more service than what it has actually received. In the
+ * end, bfqq receives less service in proportion to how slowly its
+ * associated process consumes its budgets (and hence how seriously it
+ * tends to lower the throughput). In addition, this time-charging
+ * strategy guarantees time fairness among slow processes. In
+ * contrast, if the process associated with bfqq is not slow, we
+ * charge bfqq exactly with the service it has received.
+ *
+ * Charging time to the first type of queues and the exact service to
+ * the other has the effect of using the WF2Q+ policy to schedule the
+ * former on a timeslice basis, without violating service domain
+ * guarantees among the latter.
+ */
+void bfq_bfqq_expire(struct bfq_data *bfqd,
+		     struct bfq_queue *bfqq,
+		     bool compensate,
+		     enum bfqq_expiration reason)
+{
+	bool slow;
+	unsigned long delta = 0;
+	struct bfq_entity *entity = &bfqq->entity;
+	int ref;
+
+	/*
+	 * Check whether the process is slow (see bfq_bfqq_is_slow).
+	 */
+	slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
+
+	/*
+	 * Increase service_from_backlogged before next statement,
+	 * because the possible next invocation of
+	 * bfq_bfqq_charge_time would likely inflate
+	 * entity->service. In contrast, service_from_backlogged must
+	 * contain real service, to enable the soft real-time
+	 * heuristic to correctly compute the bandwidth consumed by
+	 * bfqq.
+	 */
+	bfqq->service_from_backlogged += entity->service;
+
+	/*
+	 * As above explained, charge slow (typically seeky) and
+	 * timed-out queues with the time and not the service
+	 * received, to favor sequential workloads.
+	 *
+	 * Processes doing I/O in the slower disk zones will tend to
+	 * be slow(er) even if not seeky. Therefore, since the
+	 * estimated peak rate is actually an average over the disk
+	 * surface, these processes may timeout just for bad luck. To
+	 * avoid punishing them, do not charge time to processes that
+	 * succeeded in consuming at least 2/3 of their budget. This
+	 * allows BFQ to preserve enough elasticity to still perform
+	 * bandwidth, and not time, distribution with little unlucky
+	 * or quasi-sequential processes.
+	 */
+	if (bfqq->wr_coeff == 1 &&
+	    (slow ||
+	     (reason == BFQQE_BUDGET_TIMEOUT &&
+	      bfq_bfqq_budget_left(bfqq) >=  entity->budget / 3)))
+		bfq_bfqq_charge_time(bfqd, bfqq, delta);
+
+	if (reason == BFQQE_TOO_IDLE &&
+	    entity->service <= 2 * entity->budget / 10)
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (bfqd->low_latency && bfqq->wr_coeff == 1)
+		bfqq->last_wr_start_finish = jiffies;
+
+	if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		/*
+		 * If we get here, and there are no outstanding
+		 * requests, then the request pattern is isochronous
+		 * (see the comments on the function
+		 * bfq_bfqq_softrt_next_start()). Thus we can compute
+		 * soft_rt_next_start. If, instead, the queue still
+		 * has outstanding requests, then we have to wait for
+		 * the completion of all the outstanding requests to
+		 * discover whether the request pattern is actually
+		 * isochronous.
+		 */
+		if (bfqq->dispatched == 0)
+			bfqq->soft_rt_next_start =
+				bfq_bfqq_softrt_next_start(bfqd, bfqq);
+		else {
+			/*
+			 * The application is still waiting for the
+			 * completion of one or more requests:
+			 * prevent it from possibly being incorrectly
+			 * deemed as soft real-time by setting its
+			 * soft_rt_next_start to infinity. In fact,
+			 * without this assignment, the application
+			 * would be incorrectly deemed as soft
+			 * real-time if:
+			 * 1) it issued a new request before the
+			 *    completion of all its in-flight
+			 *    requests, and
+			 * 2) at that time, its soft_rt_next_start
+			 *    happened to be in the past.
+			 */
+			bfqq->soft_rt_next_start =
+				bfq_greatest_from_now();
+			/*
+			 * Schedule an update of soft_rt_next_start to when
+			 * the task may be discovered to be isochronous.
+			 */
+			bfq_mark_bfqq_softrt_update(bfqq);
+		}
+	}
+
+	bfq_log_bfqq(bfqd, bfqq,
+		"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
+		slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
+
+	/*
+	 * Increase, decrease or leave budget unchanged according to
+	 * reason.
+	 */
+	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
+	ref = bfqq->ref;
+	__bfq_bfqq_expire(bfqd, bfqq);
+
+	/* mark bfqq as waiting a request only if a bic still points to it */
+	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	    reason != BFQQE_BUDGET_TIMEOUT &&
+	    reason != BFQQE_BUDGET_EXHAUSTED)
+		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+/*
+ * Budget timeout is not implemented through a dedicated timer, but
+ * just checked on request arrivals and completions, as well as on
+ * idle timer expirations.
+ */
+static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
+{
+	return time_is_before_eq_jiffies(bfqq->budget_timeout);
+}
+
+/*
+ * If we expire a queue that is actively waiting (i.e., with the
+ * device idled) for the arrival of a new request, then we may incur
+ * the timestamp misalignment problem described in the body of the
+ * function __bfq_activate_entity. Hence we return true only if this
+ * condition does not hold, or if the queue is slow enough to deserve
+ * only to be kicked off for preserving a high throughput.
+ */
+static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		"may_budget_timeout: wait_request %d left %d timeout %d",
+		bfq_bfqq_wait_request(bfqq),
+			bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3,
+		bfq_bfqq_budget_timeout(bfqq));
+
+	return (!bfq_bfqq_wait_request(bfqq) ||
+		bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3)
+		&&
+		bfq_bfqq_budget_timeout(bfqq);
+}
+
+/*
+ * For a queue that becomes empty, device idling is allowed only if
+ * this function returns true for the queue. As a consequence, since
+ * device idling plays a critical role in both throughput boosting and
+ * service guarantees, the return value of this function plays a
+ * critical role in both these aspects as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * In more detail, the return value of this function is obtained by,
+ * first, computing a number of boolean variables that take into
+ * account throughput and service-guarantee issues, and, then,
+ * combining these variables in a logical expression. Most of the
+ * issues taken into account are not trivial. We discuss these issues
+ * individually while introducing the variables.
+ */
+static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+	bool idling_boosts_thr, idling_boosts_thr_without_issues,
+		idling_needed_for_service_guarantees,
+		asymmetric_scenario;
+
+	if (bfqd->strict_guarantees)
+		return true;
+
+	/*
+	 * The next variable takes into account the cases where idling
+	 * boosts the throughput.
+	 *
+	 * The value of the variable is computed considering, first, that
+	 * idling is virtually always beneficial for the throughput if:
+	 * (a) the device is not NCQ-capable, or
+	 * (b) regardless of the presence of NCQ, the device is rotational
+	 *     and the request pattern for bfqq is I/O-bound and sequential.
+	 *
+	 * Secondly, and in contrast to the above item (b), idling an
+	 * NCQ-capable flash-based device would not boost the
+	 * throughput even with sequential I/O; rather it would lower
+	 * the throughput in proportion to how fast the device
+	 * is. Accordingly, the next variable is true if any of the
+	 * above conditions (a) and (b) is true, and, in particular,
+	 * happens to be false if bfqd is an NCQ-capable flash-based
+	 * device.
+	 */
+	idling_boosts_thr = !bfqd->hw_tag ||
+		(!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
+		 bfq_bfqq_idle_window(bfqq));
+
+	/*
+	 * The value of the next variable,
+	 * idling_boosts_thr_without_issues, is equal to that of
+	 * idling_boosts_thr, unless a special case holds. In this
+	 * special case, described below, idling may cause problems to
+	 * weight-raised queues.
+	 *
+	 * When the request pool is saturated (e.g., in the presence
+	 * of write hogs), if the processes associated with
+	 * non-weight-raised queues ask for requests at a lower rate,
+	 * then processes associated with weight-raised queues have a
+	 * higher probability to get a request from the pool
+	 * immediately (or at least soon) when they need one. Thus
+	 * they have a higher probability to actually get a fraction
+	 * of the device throughput proportional to their high
+	 * weight. This is especially true with NCQ-capable drives,
+	 * which enqueue several requests in advance, and further
+	 * reorder internally-queued requests.
+	 *
+	 * For this reason, we force to false the value of
+	 * idling_boosts_thr_without_issues if there are weight-raised
+	 * busy queues. In this case, and if bfqq is not weight-raised,
+	 * this guarantees that the device is not idled for bfqq (if,
+	 * instead, bfqq is weight-raised, then idling will be
+	 * guaranteed by another variable, see below). Combined with
+	 * the timestamping rules of BFQ (see [1] for details), this
+	 * behavior causes bfqq, and hence any sync non-weight-raised
+	 * queue, to get a lower number of requests served, and thus
+	 * to ask for a lower number of requests from the request
+	 * pool, before the busy weight-raised queues get served
+	 * again. This often mitigates starvation problems in the
+	 * presence of heavy write workloads and NCQ, thereby
+	 * guaranteeing a higher application and system responsiveness
+	 * in these hostile scenarios.
+	 */
+	idling_boosts_thr_without_issues = idling_boosts_thr &&
+		bfqd->wr_busy_queues == 0;
+
+	/*
+	 * There is then a case where idling must be performed not
+	 * for throughput concerns, but to preserve service
+	 * guarantees.
+	 *
+	 * To introduce this case, we can note that allowing the drive
+	 * to enqueue more than one request at a time, and hence
+	 * delegating de facto final scheduling decisions to the
+	 * drive's internal scheduler, entails loss of control on the
+	 * actual request service order. In particular, the critical
+	 * situation is when requests from different processes happen
+	 * to be present, at the same time, in the internal queue(s)
+	 * of the drive. In such a situation, the drive, by deciding
+	 * the service order of the internally-queued requests, does
+	 * determine also the actual throughput distribution among
+	 * these processes. But the drive typically has no notion or
+	 * concern about per-process throughput distribution, and
+	 * makes its decisions only on a per-request basis. Therefore,
+	 * the service distribution enforced by the drive's internal
+	 * scheduler is likely to coincide with the desired
+	 * device-throughput distribution only in a completely
+	 * symmetric scenario where:
+	 * (i)  each of these processes must get the same throughput as
+	 *      the others;
+	 * (ii) all these processes have the same I/O pattern
+		(either sequential or random).
+	 * In fact, in such a scenario, the drive will tend to treat
+	 * the requests of each of these processes in about the same
+	 * way as the requests of the others, and thus to provide
+	 * each of these processes with about the same throughput
+	 * (which is exactly the desired throughput distribution). In
+	 * contrast, in any asymmetric scenario, device idling is
+	 * certainly needed to guarantee that bfqq receives its
+	 * assigned fraction of the device throughput (see [1] for
+	 * details).
+	 *
+	 * We address this issue by controlling, actually, only the
+	 * symmetry sub-condition (i), i.e., provided that
+	 * sub-condition (i) holds, idling is not performed,
+	 * regardless of whether sub-condition (ii) holds. In other
+	 * words, only if sub-condition (i) holds, then idling is
+	 * allowed, and the device tends to be prevented from queueing
+	 * many requests, possibly of several processes. The reason
+	 * for not controlling also sub-condition (ii) is that we
+	 * exploit preemption to preserve guarantees in case of
+	 * symmetric scenarios, even if (ii) does not hold, as
+	 * explained in the next two paragraphs.
+	 *
+	 * Even if a queue, say Q, is expired when it remains idle, Q
+	 * can still preempt the new in-service queue if the next
+	 * request of Q arrives soon (see the comments on
+	 * bfq_bfqq_update_budg_for_activation). If all queues and
+	 * groups have the same weight, this form of preemption,
+	 * combined with the hole-recovery heuristic described in the
+	 * comments on function bfq_bfqq_update_budg_for_activation,
+	 * are enough to preserve a correct bandwidth distribution in
+	 * the mid term, even without idling. In fact, even if not
+	 * idling allows the internal queues of the device to contain
+	 * many requests, and thus to reorder requests, we can rather
+	 * safely assume that the internal scheduler still preserves a
+	 * minimum of mid-term fairness. The motivation for using
+	 * preemption instead of idling is that, by not idling,
+	 * service guarantees are preserved without minimally
+	 * sacrificing throughput. In other words, both a high
+	 * throughput and its desired distribution are obtained.
+	 *
+	 * More precisely, this preemption-based, idleless approach
+	 * provides fairness in terms of IOPS, and not sectors per
+	 * second. This can be seen with a simple example. Suppose
+	 * that there are two queues with the same weight, but that
+	 * the first queue receives requests of 8 sectors, while the
+	 * second queue receives requests of 1024 sectors. In
+	 * addition, suppose that each of the two queues contains at
+	 * most one request at a time, which implies that each queue
+	 * always remains idle after it is served. Finally, after
+	 * remaining idle, each queue receives very quickly a new
+	 * request. It follows that the two queues are served
+	 * alternatively, preempting each other if needed. This
+	 * implies that, although both queues have the same weight,
+	 * the queue with large requests receives a service that is
+	 * 1024/8 times as high as the service received by the other
+	 * queue.
+	 *
+	 * On the other hand, device idling is performed, and thus
+	 * pure sector-domain guarantees are provided, for the
+	 * following queues, which are likely to need stronger
+	 * throughput guarantees: weight-raised queues, and queues
+	 * with a higher weight than other queues. When such queues
+	 * are active, sub-condition (i) is false, which triggers
+	 * device idling.
+	 *
+	 * According to the above considerations, the next variable is
+	 * true (only) if sub-condition (i) holds. To compute the
+	 * value of this variable, we not only use the return value of
+	 * the function bfq_symmetric_scenario(), but also check
+	 * whether bfqq is being weight-raised, because
+	 * bfq_symmetric_scenario() does not take into account also
+	 * weight-raised queues (see comments on
+	 * bfq_weights_tree_add()).
+	 *
+	 * As a side note, it is worth considering that the above
+	 * device-idling countermeasures may however fail in the
+	 * following unlucky scenario: if idling is (correctly)
+	 * disabled in a time period during which all symmetry
+	 * sub-conditions hold, and hence the device is allowed to
+	 * enqueue many requests, but at some later point in time some
+	 * sub-condition stops to hold, then it may become impossible
+	 * to let requests be served in the desired order until all
+	 * the requests already queued in the device have been served.
+	 */
+	asymmetric_scenario = bfqq->wr_coeff > 1 ||
+		!bfq_symmetric_scenario(bfqd);
+
+	/*
+	 * Finally, there is a case where maximizing throughput is the
+	 * best choice even if it may cause unfairness toward
+	 * bfqq. Such a case is when bfqq became active in a burst of
+	 * queue activations. Queues that became active during a large
+	 * burst benefit only from throughput, as discussed in the
+	 * comments on bfq_handle_burst. Thus, if bfqq became active
+	 * in a burst and not idling the device maximizes throughput,
+	 * then the device must no be idled, because not idling the
+	 * device provides bfqq and all other queues in the burst with
+	 * maximum benefit. Combining this and the above case, we can
+	 * now establish when idling is actually needed to preserve
+	 * service guarantees.
+	 */
+	idling_needed_for_service_guarantees =
+		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+
+	/*
+	 * We have now all the components we need to compute the return
+	 * value of the function, which is true only if both the following
+	 * conditions hold:
+	 * 1) bfqq is sync, because idling make sense only for sync queues;
+	 * 2) idling either boosts the throughput (without issues), or
+	 *    is necessary to preserve service guarantees.
+	 */
+	return bfq_bfqq_sync(bfqq) &&
+		(idling_boosts_thr_without_issues ||
+		 idling_needed_for_service_guarantees);
+}
+
+/*
+ * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * returns true, then:
+ * 1) the queue must remain in service and cannot be expired, and
+ * 2) the device must be idled to wait for the possible arrival of a new
+ *    request for the queue.
+ * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * why performing device idling is the best choice to boost the throughput
+ * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * returns true.
+ */
+static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
+	       bfq_bfqq_may_idle(bfqq);
+}
+
+/*
+ * Select a queue for service.  If we have a current queue in service,
+ * check whether to continue servicing it, or retrieve and set a new one.
+ */
+static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+	struct request *next_rq;
+	enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT;
+
+	bfqq = bfqd->in_service_queue;
+	if (!bfqq)
+		goto new_queue;
+
+	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
+
+	if (bfq_may_expire_for_budg_timeout(bfqq) &&
+	    !bfq_bfqq_wait_request(bfqq) &&
+	    !bfq_bfqq_must_idle(bfqq))
+		goto expire;
+
+check_queue:
+	/*
+	 * This loop is rarely executed more than once. Even when it
+	 * happens, it is much more convenient to re-execute this loop
+	 * than to return NULL and trigger a new dispatch to get a
+	 * request served.
+	 */
+	next_rq = bfqq->next_rq;
+	/*
+	 * If bfqq has requests queued and it has enough budget left to
+	 * serve them, keep the queue, otherwise expire it.
+	 */
+	if (next_rq) {
+		if (bfq_serv_to_charge(next_rq, bfqq) >
+			bfq_bfqq_budget_left(bfqq)) {
+			/*
+			 * Expire the queue for budget exhaustion,
+			 * which makes sure that the next budget is
+			 * enough to serve the next request, even if
+			 * it comes from the fifo expired path.
+			 */
+			reason = BFQQE_BUDGET_EXHAUSTED;
+			goto expire;
+		} else {
+			/*
+			 * The idle timer may be pending because we may
+			 * not disable disk idling even when a new request
+			 * arrives.
+			 */
+			if (bfq_bfqq_wait_request(bfqq)) {
+				/*
+				 * If we get here: 1) at least a new request
+				 * has arrived but we have not disabled the
+				 * timer because the request was too small,
+				 * 2) then the block layer has unplugged
+				 * the device, causing the dispatch to be
+				 * invoked.
+				 *
+				 * Since the device is unplugged, now the
+				 * requests are probably large enough to
+				 * provide a reasonable throughput.
+				 * So we disable idling.
+				 */
+				bfq_clear_bfqq_wait_request(bfqq);
+				hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+				bfqg_stats_update_idle_time(bfqq_group(bfqq));
+			}
+			goto keep_queue;
+		}
+	}
+
+	/*
+	 * No requests pending. However, if the in-service queue is idling
+	 * for a new request, or has requests waiting for a completion and
+	 * may idle after their completion, then keep it anyway.
+	 */
+	if (bfq_bfqq_wait_request(bfqq) ||
+	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+		bfqq = NULL;
+		goto keep_queue;
+	}
+
+	reason = BFQQE_NO_MORE_REQUESTS;
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, false, reason);
+new_queue:
+	bfqq = bfq_set_in_service_queue(bfqd);
+	if (bfqq) {
+		bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
+		goto check_queue;
+	}
+keep_queue:
+	if (bfqq)
+		bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
+	else
+		bfq_log(bfqd, "select_queue: no queue returned");
+
+	return bfqq;
+}
+
+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+		if (entity->prio_changed)
+			bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+
+		/*
+		 * If the queue was activated in a burst, or too much
+		 * time has elapsed from the beginning of this
+		 * weight-raising period, then end weight raising.
+		 */
+		if (bfq_bfqq_in_large_burst(bfqq))
+			bfq_bfqq_end_wr(bfqq);
+		else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+						bfqq->wr_cur_max_time)) {
+			if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
+			time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+					       bfq_wr_duration(bfqd)))
+				bfq_bfqq_end_wr(bfqq);
+			else {
+				/* switch back to interactive wr */
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+				bfqq->last_wr_start_finish =
+					bfqq->wr_start_at_switch_to_srt;
+				bfqq->entity.prio_changed = 1;
+			}
+		}
+	}
+	/* Update weight both if it must be raised and if it must be lowered */
+	if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
+		__bfq_entity_update_weight_prio(
+			bfq_entity_service_tree(entity),
+			entity);
+}
+
+/*
+ * Dispatch next request from bfqq.
+ */
+static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
+						 struct bfq_queue *bfqq)
+{
+	struct request *rq = bfqq->next_rq;
+	unsigned long service_to_charge;
+
+	service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+	bfq_bfqq_served(bfqq, service_to_charge);
+
+	bfq_dispatch_remove(bfqd->queue, rq);
+
+	/*
+	 * If weight raising has to terminate for bfqq, then next
+	 * function causes an immediate update of bfqq's weight,
+	 * without waiting for next activation. As a consequence, on
+	 * expiration, bfqq will be timestamped as if has never been
+	 * weight-raised during this service slot, even if it has
+	 * received part or even most of the service as a
+	 * weight-raised queue. This inflates bfqq's timestamps, which
+	 * is beneficial, as bfqq is then more willing to leave the
+	 * device immediately to possible other weight-raised queues.
+	 */
+	bfq_update_wr_data(bfqd, bfqq);
+
+	/*
+	 * Expire bfqq, pretending that its budget expired, if bfqq
+	 * belongs to CLASS_IDLE and other queues are waiting for
+	 * service.
+	 */
+	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
+		goto expire;
+
+	return rq;
+
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
+	return rq;
+}
+
+static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+
+	/*
+	 * Avoiding lock: a race on bfqd->busy_queues should cause at
+	 * most a call to dispatch for nothing
+	 */
+	return !list_empty_careful(&bfqd->dispatch) ||
+		bfqd->busy_queues > 0;
+}
+
+static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct request *rq = NULL;
+	struct bfq_queue *bfqq = NULL;
+
+	if (!list_empty(&bfqd->dispatch)) {
+		rq = list_first_entry(&bfqd->dispatch, struct request,
+				      queuelist);
+		list_del_init(&rq->queuelist);
+
+		bfqq = RQ_BFQQ(rq);
+
+		if (bfqq) {
+			/*
+			 * Increment counters here, because this
+			 * dispatch does not follow the standard
+			 * dispatch flow (where counters are
+			 * incremented)
+			 */
+			bfqq->dispatched++;
+
+			goto inc_in_driver_start_rq;
+		}
+
+		/*
+		 * We exploit the put_rq_private hook to decrement
+		 * rq_in_driver, but put_rq_private will not be
+		 * invoked on this request. So, to avoid unbalance,
+		 * just start this request, without incrementing
+		 * rq_in_driver. As a negative consequence,
+		 * rq_in_driver is deceptively lower than it should be
+		 * while this request is in service. This may cause
+		 * bfq_schedule_dispatch to be invoked uselessly.
+		 *
+		 * As for implementing an exact solution, the
+		 * put_request hook, if defined, is probably invoked
+		 * also on this request. So, by exploiting this hook,
+		 * we could 1) increment rq_in_driver here, and 2)
+		 * decrement it in put_request. Such a solution would
+		 * let the value of the counter be always accurate,
+		 * but it would entail using an extra interface
+		 * function. This cost seems higher than the benefit,
+		 * being the frequency of non-elevator-private
+		 * requests very low.
+		 */
+		goto start_rq;
+	}
+
+	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+
+	if (bfqd->busy_queues == 0)
+		goto exit;
+
+	/*
+	 * Force device to serve one request at a time if
+	 * strict_guarantees is true. Forcing this service scheme is
+	 * currently the ONLY way to guarantee that the request
+	 * service order enforced by the scheduler is respected by a
+	 * queueing device. Otherwise the device is free even to make
+	 * some unlucky request wait for as long as the device
+	 * wishes.
+	 *
+	 * Of course, serving one request at at time may cause loss of
+	 * throughput.
+	 */
+	if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
+		goto exit;
+
+	bfqq = bfq_select_queue(bfqd);
+	if (!bfqq)
+		goto exit;
+
+	rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
+
+	if (rq) {
+inc_in_driver_start_rq:
+		bfqd->rq_in_driver++;
+start_rq:
+		rq->rq_flags |= RQF_STARTED;
+	}
+exit:
+	return rq;
+}
+
+static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+
+	spin_lock_irq(&bfqd->lock);
+
+	rq = __bfq_dispatch_request(hctx);
+	spin_unlock_irq(&bfqd->lock);
+
+	return rq;
+}
+
+/*
+ * Task holds one reference to the queue, dropped when task exits.  Each rq
+ * in-flight on this queue also holds a reference, dropped when rq is freed.
+ *
+ * Scheduler lock must be held here. Recall not to use bfqq after calling
+ * this function on it.
+ */
+void bfq_put_queue(struct bfq_queue *bfqq)
+{
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	struct bfq_group *bfqg = bfqq_group(bfqq);
+#endif
+
+	if (bfqq->bfqd)
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
+			     bfqq, bfqq->ref);
+
+	bfqq->ref--;
+	if (bfqq->ref)
+		return;
+
+	if (bfq_bfqq_sync(bfqq))
+		/*
+		 * The fact that this queue is being destroyed does not
+		 * invalidate the fact that this queue may have been
+		 * activated during the current burst. As a consequence,
+		 * although the queue does not exist anymore, and hence
+		 * needs to be removed from the burst list if there,
+		 * the burst size has not to be decremented.
+		 */
+		hlist_del_init(&bfqq->burst_list_node);
+
+	kmem_cache_free(bfq_pool, bfqq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	bfqg_put(bfqg);
+#endif
+}
+
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+	struct bfq_queue *__bfqq, *next;
+
+	/*
+	 * If this queue was scheduled to merge with another queue, be
+	 * sure to drop the reference taken on that queue (and others in
+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+	 */
+	__bfqq = bfqq->new_bfqq;
+	while (__bfqq) {
+		if (__bfqq == bfqq)
+			break;
+		next = __bfqq->new_bfqq;
+		bfq_put_queue(__bfqq);
+		__bfqq = next;
+	}
+}
+
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	if (bfqq == bfqd->in_service_queue) {
+		__bfq_bfqq_expire(bfqd, bfqq);
+		bfq_schedule_dispatch(bfqd);
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq); /* release process reference */
+}
+
+static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+	struct bfq_data *bfqd;
+
+	if (bfqq)
+		bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
+
+	if (bfqq && bfqd) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&bfqd->lock, flags);
+		bfq_exit_bfqq(bfqd, bfqq);
+		bic_set_bfqq(bic, NULL, is_sync);
+		spin_unlock_irqrestore(&bfqd->lock, flags);
+	}
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+
+	bfq_exit_icq_bfqq(bic, true);
+	bfq_exit_icq_bfqq(bic, false);
+}
+
+/*
+ * Update the entity prio values; note that the new values will not
+ * be used until the next (re)activation.
+ */
+static void
+bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+	struct task_struct *tsk = current;
+	int ioprio_class;
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	if (!bfqd)
+		return;
+
+	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+	switch (ioprio_class) {
+	default:
+		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
+			"bfq: bad prio class %d\n", ioprio_class);
+	case IOPRIO_CLASS_NONE:
+		/*
+		 * No prio set, inherit CPU scheduling settings.
+		 */
+		bfqq->new_ioprio = task_nice_ioprio(tsk);
+		bfqq->new_ioprio_class = task_nice_ioclass(tsk);
+		break;
+	case IOPRIO_CLASS_RT:
+		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+		bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
+		break;
+	case IOPRIO_CLASS_BE:
+		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+		bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
+		break;
+	case IOPRIO_CLASS_IDLE:
+		bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
+		bfqq->new_ioprio = 7;
+		bfq_clear_bfqq_idle_window(bfqq);
+		break;
+	}
+
+	if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
+		pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
+			bfqq->new_ioprio);
+		bfqq->new_ioprio = IOPRIO_BE_NR;
+	}
+
+	bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+	bfqq->entity.prio_changed = 1;
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+				       struct bio *bio, bool is_sync,
+				       struct bfq_io_cq *bic);
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
+{
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	struct bfq_queue *bfqq;
+	int ioprio = bic->icq.ioc->ioprio;
+
+	/*
+	 * This condition may trigger on a newly created bic, be sure to
+	 * drop the lock before returning.
+	 */
+	if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
+		return;
+
+	bic->ioprio = ioprio;
+
+	bfqq = bic_to_bfqq(bic, false);
+	if (bfqq) {
+		/* release process reference on this queue */
+		bfq_put_queue(bfqq);
+		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
+		bic_set_bfqq(bic, bfqq, false);
+	}
+
+	bfqq = bic_to_bfqq(bic, true);
+	if (bfqq)
+		bfq_set_next_ioprio_data(bfqq, bic);
+}
+
+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  struct bfq_io_cq *bic, pid_t pid, int is_sync)
+{
+	RB_CLEAR_NODE(&bfqq->entity.rb_node);
+	INIT_LIST_HEAD(&bfqq->fifo);
+	INIT_HLIST_NODE(&bfqq->burst_list_node);
+
+	bfqq->ref = 0;
+	bfqq->bfqd = bfqd;
+
+	if (bic)
+		bfq_set_next_ioprio_data(bfqq, bic);
+
+	if (is_sync) {
+		if (!bfq_class_idle(bfqq))
+			bfq_mark_bfqq_idle_window(bfqq);
+		bfq_mark_bfqq_sync(bfqq);
+		bfq_mark_bfqq_just_created(bfqq);
+	} else
+		bfq_clear_bfqq_sync(bfqq);
+
+	/* set end request to minus infinity from now */
+	bfqq->ttime.last_end_request = ktime_get_ns() + 1;
+
+	bfq_mark_bfqq_IO_bound(bfqq);
+
+	bfqq->pid = pid;
+
+	/* Tentative initial value to trade off between thr and lat */
+	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
+	bfqq->budget_timeout = bfq_smallest_from_now();
+
+	bfqq->wr_coeff = 1;
+	bfqq->last_wr_start_finish = jiffies;
+	bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+	bfqq->split_time = bfq_smallest_from_now();
+
+	/*
+	 * Set to the value for which bfqq will not be deemed as
+	 * soft rt when it becomes backlogged.
+	 */
+	bfqq->soft_rt_next_start = bfq_greatest_from_now();
+
+	/* first request is almost certainly seeky */
+	bfqq->seek_history = 1;
+}
+
+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
+					       struct bfq_group *bfqg,
+					       int ioprio_class, int ioprio)
+{
+	switch (ioprio_class) {
+	case IOPRIO_CLASS_RT:
+		return &bfqg->async_bfqq[0][ioprio];
+	case IOPRIO_CLASS_NONE:
+		ioprio = IOPRIO_NORM;
+		/* fall through */
+	case IOPRIO_CLASS_BE:
+		return &bfqg->async_bfqq[1][ioprio];
+	case IOPRIO_CLASS_IDLE:
+		return &bfqg->async_idle_bfqq;
+	default:
+		return NULL;
+	}
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+				       struct bio *bio, bool is_sync,
+				       struct bfq_io_cq *bic)
+{
+	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+	struct bfq_queue **async_bfqq = NULL;
+	struct bfq_queue *bfqq;
+	struct bfq_group *bfqg;
+
+	rcu_read_lock();
+
+	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
+	if (!bfqg) {
+		bfqq = &bfqd->oom_bfqq;
+		goto out;
+	}
+
+	if (!is_sync) {
+		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
+						  ioprio);
+		bfqq = *async_bfqq;
+		if (bfqq)
+			goto out;
+	}
+
+	bfqq = kmem_cache_alloc_node(bfq_pool,
+				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
+				     bfqd->queue->node);
+
+	if (bfqq) {
+		bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
+			      is_sync);
+		bfq_init_entity(&bfqq->entity, bfqg);
+		bfq_log_bfqq(bfqd, bfqq, "allocated");
+	} else {
+		bfqq = &bfqd->oom_bfqq;
+		bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
+		goto out;
+	}
+
+	/*
+	 * Pin the queue now that it's allocated, scheduler exit will
+	 * prune it.
+	 */
+	if (async_bfqq) {
+		bfqq->ref++; /*
+			      * Extra group reference, w.r.t. sync
+			      * queue. This extra reference is removed
+			      * only if bfqq->bfqg disappears, to
+			      * guarantee that this queue is not freed
+			      * until its group goes away.
+			      */
+		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
+			     bfqq, bfqq->ref);
+		*async_bfqq = bfqq;
+	}
+
+out:
+	bfqq->ref++; /* get a process reference to this queue */
+	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
+	rcu_read_unlock();
+	return bfqq;
+}
+
+static void bfq_update_io_thinktime(struct bfq_data *bfqd,
+				    struct bfq_queue *bfqq)
+{
+	struct bfq_ttime *ttime = &bfqq->ttime;
+	u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+
+	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
+
+	ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
+	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
+	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+				     ttime->ttime_samples);
+}
+
+static void
+bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       struct request *rq)
+{
+	bfqq->seek_history <<= 1;
+	bfqq->seek_history |=
+		get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR &&
+		(!blk_queue_nonrot(bfqd->queue) ||
+		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
+}
+
+/*
+ * Disable idle window if the process thinks too long or seeks so much that
+ * it doesn't matter.
+ */
+static void bfq_update_idle_window(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq,
+				   struct bfq_io_cq *bic)
+{
+	int enable_idle;
+
+	/* Don't idle for async or idle io prio class. */
+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+		return;
+
+	/* Idle window just restored, statistics are meaningless. */
+	if (time_is_after_eq_jiffies(bfqq->split_time +
+				     bfqd->bfq_wr_min_idle_time))
+		return;
+
+	enable_idle = bfq_bfqq_idle_window(bfqq);
+
+	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
+	    bfqd->bfq_slice_idle == 0 ||
+		(bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
+			bfqq->wr_coeff == 1))
+		enable_idle = 0;
+	else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
+		if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle &&
+			bfqq->wr_coeff == 1)
+			enable_idle = 0;
+		else
+			enable_idle = 1;
+	}
+	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
+		enable_idle);
+
+	if (enable_idle)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+}
+
+/*
+ * Called when a new fs request (rq) is added to bfqq.  Check if there's
+ * something we should do about it.
+ */
+static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			    struct request *rq)
+{
+	struct bfq_io_cq *bic = RQ_BIC(rq);
+
+	if (rq->cmd_flags & REQ_META)
+		bfqq->meta_pending++;
+
+	bfq_update_io_thinktime(bfqd, bfqq);
+	bfq_update_io_seektime(bfqd, bfqq, rq);
+	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
+	    !BFQQ_SEEKY(bfqq))
+		bfq_update_idle_window(bfqd, bfqq, bic);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "rq_enqueued: idle_window=%d (seeky %d)",
+		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));
+
+	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+
+	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
+		bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
+				 blk_rq_sectors(rq) < 32;
+		bool budget_timeout = bfq_bfqq_budget_timeout(bfqq);
+
+		/*
+		 * There is just this request queued: if the request
+		 * is small and the queue is not to be expired, then
+		 * just exit.
+		 *
+		 * In this way, if the device is being idled to wait
+		 * for a new request from the in-service queue, we
+		 * avoid unplugging the device and committing the
+		 * device to serve just a small request. On the
+		 * contrary, we wait for the block layer to decide
+		 * when to unplug the device: hopefully, new requests
+		 * will be merged to this one quickly, then the device
+		 * will be unplugged and larger requests will be
+		 * dispatched.
+		 */
+		if (small_req && !budget_timeout)
+			return;
+
+		/*
+		 * A large enough request arrived, or the queue is to
+		 * be expired: in both cases disk idling is to be
+		 * stopped, so clear wait_request flag and reset
+		 * timer.
+		 */
+		bfq_clear_bfqq_wait_request(bfqq);
+		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+		bfqg_stats_update_idle_time(bfqq_group(bfqq));
+
+		/*
+		 * The queue is not empty, because a new request just
+		 * arrived. Hence we can safely expire the queue, in
+		 * case of budget timeout, without risking that the
+		 * timestamps of the queue are not updated correctly.
+		 * See [1] for more details.
+		 */
+		if (budget_timeout)
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQQE_BUDGET_TIMEOUT);
+	}
+}
+
+static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq),
+		*new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+
+	if (new_bfqq) {
+		if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
+			new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
+		/*
+		 * Release the request's reference to the old bfqq
+		 * and make sure one is taken to the shared queue.
+		 */
+		new_bfqq->allocated++;
+		bfqq->allocated--;
+		new_bfqq->ref++;
+		bfq_clear_bfqq_just_created(bfqq);
+		/*
+		 * If the bic associated with the process
+		 * issuing this request still points to bfqq
+		 * (and thus has not been already redirected
+		 * to new_bfqq or even some other bfq_queue),
+		 * then complete the merge and redirect it to
+		 * new_bfqq.
+		 */
+		if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
+			bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+					bfqq, new_bfqq);
+		/*
+		 * rq is about to be enqueued into new_bfqq,
+		 * release rq reference on bfqq
+		 */
+		bfq_put_queue(bfqq);
+		rq->elv.priv[1] = new_bfqq;
+		bfqq = new_bfqq;
+	}
+
+	bfq_add_request(rq);
+
+	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	list_add_tail(&rq->queuelist, &bfqq->fifo);
+
+	bfq_rq_enqueued(bfqd, bfqq, rq);
+}
+
+static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			       bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	spin_lock_irq(&bfqd->lock);
+	if (blk_mq_sched_try_insert_merge(q, rq)) {
+		spin_unlock_irq(&bfqd->lock);
+		return;
+	}
+
+	spin_unlock_irq(&bfqd->lock);
+
+	blk_mq_sched_request_inserted(rq);
+
+	spin_lock_irq(&bfqd->lock);
+	if (at_head || blk_rq_is_passthrough(rq)) {
+		if (at_head)
+			list_add(&rq->queuelist, &bfqd->dispatch);
+		else
+			list_add_tail(&rq->queuelist, &bfqd->dispatch);
+	} else {
+		__bfq_insert_request(bfqd, rq);
+
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				q->last_merge = rq;
+		}
+	}
+
+	spin_unlock_irq(&bfqd->lock);
+}
+
+static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
+				struct list_head *list, bool at_head)
+{
+	while (!list_empty(list)) {
+		struct request *rq;
+
+		rq = list_first_entry(list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		bfq_insert_request(hctx, rq, at_head);
+	}
+}
+
+static void bfq_update_hw_tag(struct bfq_data *bfqd)
+{
+	bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver,
+				       bfqd->rq_in_driver);
+
+	if (bfqd->hw_tag == 1)
+		return;
+
+	/*
+	 * This sample is valid if the number of outstanding requests
+	 * is large enough to allow a queueing behavior.  Note that the
+	 * sum is not exact, as it's not taking into account deactivated
+	 * requests.
+	 */
+	if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
+		return;
+
+	if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
+		return;
+
+	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
+	bfqd->max_rq_in_driver = 0;
+	bfqd->hw_tag_samples = 0;
+}
+
+static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
+{
+	u64 now_ns;
+	u32 delta_us;
+
+	bfq_update_hw_tag(bfqd);
+
+	bfqd->rq_in_driver--;
+	bfqq->dispatched--;
+
+	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+		/*
+		 * Set budget_timeout (which we overload to store the
+		 * time at which the queue remains with no backlog and
+		 * no outstanding request; used by the weight-raising
+		 * mechanism).
+		 */
+		bfqq->budget_timeout = jiffies;
+
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+	}
+
+	now_ns = ktime_get_ns();
+
+	bfqq->ttime.last_end_request = now_ns;
+
+	/*
+	 * Using us instead of ns, to get a reasonable precision in
+	 * computing rate in next check.
+	 */
+	delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
+
+	/*
+	 * If the request took rather long to complete, and, according
+	 * to the maximum request size recorded, this completion latency
+	 * implies that the request was certainly served at a very low
+	 * rate (less than 1M sectors/sec), then the whole observation
+	 * interval that lasts up to this time instant cannot be a
+	 * valid time interval for computing a new peak rate.  Invoke
+	 * bfq_update_rate_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - reset to zero samples, which will trigger a proper
+	 *   re-initialization of the observation interval on next
+	 *   dispatch
+	 */
+	if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
+	   (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
+			1UL<<(BFQ_RATE_SHIFT - 10))
+		bfq_update_rate_reset(bfqd, NULL);
+	bfqd->last_completion = now_ns;
+
+	/*
+	 * If we are waiting to discover whether the request pattern
+	 * of the task associated with the queue is actually
+	 * isochronous, and both requisites for this condition to hold
+	 * are now satisfied, then compute soft_rt_next_start (see the
+	 * comments on the function bfq_bfqq_softrt_next_start()). We
+	 * schedule this delayed check when bfqq expires, if it still
+	 * has in-flight requests.
+	 */
+	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list))
+		bfqq->soft_rt_next_start =
+			bfq_bfqq_softrt_next_start(bfqd, bfqq);
+
+	/*
+	 * If this is the in-service queue, check if it needs to be expired,
+	 * or if we want to idle in case it has no pending requests.
+	 */
+	if (bfqd->in_service_queue == bfqq) {
+		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
+			bfq_arm_slice_timer(bfqd);
+			return;
+		} else if (bfq_may_expire_for_budg_timeout(bfqq))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQQE_BUDGET_TIMEOUT);
+		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+			 (bfqq->dispatched == 0 ||
+			  !bfq_bfqq_may_idle(bfqq)))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQQE_NO_MORE_REQUESTS);
+	}
+}
+
+static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
+{
+	bfqq->allocated--;
+
+	bfq_put_queue(bfqq);
+}
+
+static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	if (rq->rq_flags & RQF_STARTED)
+		bfqg_stats_update_completion(bfqq_group(bfqq),
+					     rq_start_time_ns(rq),
+					     rq_io_start_time_ns(rq),
+					     rq->cmd_flags);
+
+	if (likely(rq->rq_flags & RQF_STARTED)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&bfqd->lock, flags);
+
+		bfq_completed_request(bfqq, bfqd);
+		bfq_put_rq_priv_body(bfqq);
+
+		spin_unlock_irqrestore(&bfqd->lock, flags);
+	} else {
+		/*
+		 * Request rq may be still/already in the scheduler,
+		 * in which case we need to remove it. And we cannot
+		 * defer such a check and removal, to avoid
+		 * inconsistencies in the time interval from the end
+		 * of this function to the start of the deferred work.
+		 * This situation seems to occur only in process
+		 * context, as a consequence of a merge. In the
+		 * current version of the code, this implies that the
+		 * lock is held.
+		 */
+
+		if (!RB_EMPTY_NODE(&rq->rb_node))
+			bfq_remove_request(q, rq);
+		bfq_put_rq_priv_body(bfqq);
+	}
+
+	rq->elv.priv[0] = NULL;
+	rq->elv.priv[1] = NULL;
+}
+
+/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to that bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->pid = current->pid;
+		bfq_clear_bfqq_coop(bfqq);
+		bfq_clear_bfqq_split_coop(bfqq);
+		return bfqq;
+	}
+
+	bic_set_bfqq(bic, NULL, 1);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+	return NULL;
+}
+
+static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
+						   struct bfq_io_cq *bic,
+						   struct bio *bio,
+						   bool split, bool is_sync,
+						   bool *new_queue)
+{
+	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+
+	if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
+		return bfqq;
+
+	if (new_queue)
+		*new_queue = true;
+
+	if (bfqq)
+		bfq_put_queue(bfqq);
+	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+
+	bic_set_bfqq(bic, bfqq, is_sync);
+	if (split && is_sync) {
+		if ((bic->was_in_burst_list && bfqd->large_burst) ||
+		    bic->saved_in_large_burst)
+			bfq_mark_bfqq_in_large_burst(bfqq);
+		else {
+			bfq_clear_bfqq_in_large_burst(bfqq);
+			if (bic->was_in_burst_list)
+				hlist_add_head(&bfqq->burst_list_node,
+					       &bfqd->burst_list);
+		}
+		bfqq->split_time = jiffies;
+	}
+
+	return bfqq;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
+			      struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+	const int is_sync = rq_is_sync(rq);
+	struct bfq_queue *bfqq;
+	bool new_queue = false;
+	bool split = false;
+
+	spin_lock_irq(&bfqd->lock);
+
+	if (!bic)
+		goto queue_fail;
+
+	bfq_check_ioprio_change(bic, bio);
+
+	bfq_bic_update_cgroup(bic, bio);
+
+	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
+					 &new_queue);
+
+	if (likely(!new_queue)) {
+		/* If the queue was seeky for too long, break it apart. */
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+
+			/* Update bic before losing reference to bfqq */
+			if (bfq_bfqq_in_large_burst(bfqq))
+				bic->saved_in_large_burst = true;
+
+			bfqq = bfq_split_bfqq(bic, bfqq);
+			split = true;
+
+			if (!bfqq)
+				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
+								 true, is_sync,
+								 NULL);
+		}
+	}
+
+	bfqq->allocated++;
+	bfqq->ref++;
+	bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
+		     rq, bfqq, bfqq->ref);
+
+	rq->elv.priv[0] = bic;
+	rq->elv.priv[1] = bfqq;
+
+	/*
+	 * If a bfq_queue has only one process reference, it is owned
+	 * by only this bic: we can then set bfqq->bic = bic. in
+	 * addition, if the queue has also just been split, we have to
+	 * resume its state.
+	 */
+	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
+		bfqq->bic = bic;
+		if (split) {
+			/*
+			 * The queue has just been split from a shared
+			 * queue: restore the idle window and the
+			 * possible weight raising period.
+			 */
+			bfq_bfqq_resume_state(bfqq, bic);
+		}
+	}
+
+	if (unlikely(bfq_bfqq_just_created(bfqq)))
+		bfq_handle_burst(bfqd, bfqq);
+
+	spin_unlock_irq(&bfqd->lock);
+
+	return 0;
+
+queue_fail:
+	spin_unlock_irq(&bfqd->lock);
+
+	return 1;
+}
+
+static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+	enum bfqq_expiration reason;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bfqd->lock, flags);
+	bfq_clear_bfqq_wait_request(bfqq);
+
+	if (bfqq != bfqd->in_service_queue) {
+		spin_unlock_irqrestore(&bfqd->lock, flags);
+		return;
+	}
+
+	if (bfq_bfqq_budget_timeout(bfqq))
+		/*
+		 * Also here the queue can be safely expired
+		 * for budget timeout without wasting
+		 * guarantees
+		 */
+		reason = BFQQE_BUDGET_TIMEOUT;
+	else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
+		/*
+		 * The queue may not be empty upon timer expiration,
+		 * because we may not disable the timer when the
+		 * first request of the in-service queue arrives
+		 * during disk idling.
+		 */
+		reason = BFQQE_TOO_IDLE;
+	else
+		goto schedule_dispatch;
+
+	bfq_bfqq_expire(bfqd, bfqq, true, reason);
+
+schedule_dispatch:
+	spin_unlock_irqrestore(&bfqd->lock, flags);
+	bfq_schedule_dispatch(bfqd);
+}
+
+/*
+ * Handler of the expiration of the timer running if the in-service queue
+ * is idling inside its time slice.
+ */
+static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
+{
+	struct bfq_data *bfqd = container_of(timer, struct bfq_data,
+					     idle_slice_timer);
+	struct bfq_queue *bfqq = bfqd->in_service_queue;
+
+	/*
+	 * Theoretical race here: the in-service queue can be NULL or
+	 * different from the queue that was idling if a new request
+	 * arrives for the current queue and there is a full dispatch
+	 * cycle that changes the in-service queue.  This can hardly
+	 * happen, but in the worst case we just expire a queue too
+	 * early.
+	 */
+	if (bfqq)
+		bfq_idle_slice_timer_body(bfqq);
+
+	return HRTIMER_NORESTART;
+}
+
+static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+				 struct bfq_queue **bfqq_ptr)
+{
+	struct bfq_queue *bfqq = *bfqq_ptr;
+
+	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+	if (bfqq) {
+		bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+
+		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
+			     bfqq, bfqq->ref);
+		bfq_put_queue(bfqq);
+		*bfqq_ptr = NULL;
+	}
+}
+
+/*
+ * Release all the bfqg references to its async queues.  If we are
+ * deallocating the group these queues may still contain requests, so
+ * we reparent them to the root cgroup (i.e., the only one that will
+ * exist for sure until all the requests on a device are gone).
+ */
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
+{
+	int i, j;
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < IOPRIO_BE_NR; j++)
+			__bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
+
+	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
+}
+
+static void bfq_exit_queue(struct elevator_queue *e)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	struct bfq_queue *bfqq, *n;
+
+	hrtimer_cancel(&bfqd->idle_slice_timer);
+
+	spin_lock_irq(&bfqd->lock);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+	spin_unlock_irq(&bfqd->lock);
+
+	hrtimer_cancel(&bfqd->idle_slice_timer);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
+#else
+	spin_lock_irq(&bfqd->lock);
+	bfq_put_async_queues(bfqd, bfqd->root_group);
+	kfree(bfqd->root_group);
+	spin_unlock_irq(&bfqd->lock);
+#endif
+
+	kfree(bfqd);
+}
+
+static void bfq_init_root_group(struct bfq_group *root_group,
+				struct bfq_data *bfqd)
+{
+	int i;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	root_group->entity.parent = NULL;
+	root_group->my_entity = NULL;
+	root_group->bfqd = bfqd;
+#endif
+	root_group->rq_pos_tree = RB_ROOT;
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+		root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+	root_group->sched_data.bfq_class_idle_last_service = jiffies;
+}
+
+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+	struct bfq_data *bfqd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
+	if (!bfqd) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+	eq->elevator_data = bfqd;
+
+	spin_lock_irq(q->queue_lock);
+	q->elevator = eq;
+	spin_unlock_irq(q->queue_lock);
+
+	/*
+	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
+	 * Grab a permanent reference to it, so that the normal code flow
+	 * will not attempt to free it.
+	 */
+	bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0);
+	bfqd->oom_bfqq.ref++;
+	bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
+	bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
+	bfqd->oom_bfqq.entity.new_weight =
+		bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
+
+	/* oom_bfqq does not participate to bursts */
+	bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+
+	/*
+	 * Trigger weight initialization, according to ioprio, at the
+	 * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
+	 * class won't be changed any more.
+	 */
+	bfqd->oom_bfqq.entity.prio_changed = 1;
+
+	bfqd->queue = q;
+
+	INIT_LIST_HEAD(&bfqd->dispatch);
+
+	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+
+	bfqd->queue_weights_tree = RB_ROOT;
+	bfqd->group_weights_tree = RB_ROOT;
+
+	INIT_LIST_HEAD(&bfqd->active_list);
+	INIT_LIST_HEAD(&bfqd->idle_list);
+	INIT_HLIST_HEAD(&bfqd->burst_list);
+
+	bfqd->hw_tag = -1;
+
+	bfqd->bfq_max_budget = bfq_default_max_budget;
+
+	bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
+	bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
+	bfqd->bfq_back_max = bfq_back_max;
+	bfqd->bfq_back_penalty = bfq_back_penalty;
+	bfqd->bfq_slice_idle = bfq_slice_idle;
+	bfqd->bfq_timeout = bfq_timeout;
+
+	bfqd->bfq_requests_within_timer = 120;
+
+	bfqd->bfq_large_burst_thresh = 8;
+	bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
+	bfqd->low_latency = true;
+
+	/*
+	 * Trade-off between responsiveness and fairness.
+	 */
+	bfqd->bfq_wr_coeff = 30;
+	bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
+	bfqd->bfq_wr_max_time = 0;
+	bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+	bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+	bfqd->bfq_wr_max_softrt_rate = 7000; /*
+					      * Approximate rate required
+					      * to playback or record a
+					      * high-definition compressed
+					      * video.
+					      */
+	bfqd->wr_busy_queues = 0;
+
+	/*
+	 * Begin by assuming, optimistically, that the device is a
+	 * high-speed one, and that its peak rate is equal to 2/3 of
+	 * the highest reference rate.
+	 */
+	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+			T_fast[blk_queue_nonrot(bfqd->queue)];
+	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+	bfqd->device_speed = BFQ_BFQD_FAST;
+
+	spin_lock_init(&bfqd->lock);
+
+	/*
+	 * The invocation of the next bfq_create_group_hierarchy
+	 * function is the head of a chain of function calls
+	 * (bfq_create_group_hierarchy->blkcg_activate_policy->
+	 * blk_mq_freeze_queue) that may lead to the invocation of the
+	 * has_work hook function. For this reason,
+	 * bfq_create_group_hierarchy is invoked only after all
+	 * scheduler data has been initialized, apart from the fields
+	 * that can be initialized only after invoking
+	 * bfq_create_group_hierarchy. This, in particular, enables
+	 * has_work to correctly return false. Of course, to avoid
+	 * other inconsistencies, the blk-mq stack must then refrain
+	 * from invoking further scheduler hooks before this init
+	 * function is finished.
+	 */
+	bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
+	if (!bfqd->root_group)
+		goto out_free;
+	bfq_init_root_group(bfqd->root_group, bfqd);
+	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
+
+
+	return 0;
+
+out_free:
+	kfree(bfqd);
+	kobject_put(&eq->kobj);
+	return -ENOMEM;
+}
+
+static void bfq_slab_kill(void)
+{
+	kmem_cache_destroy(bfq_pool);
+}
+
+static int __init bfq_slab_setup(void)
+{
+	bfq_pool = KMEM_CACHE(bfq_queue, 0);
+	if (!bfq_pool)
+		return -ENOMEM;
+	return 0;
+}
+
+static ssize_t bfq_var_show(unsigned int var, char *page)
+{
+	return sprintf(page, "%u\n", var);
+}
+
+static ssize_t bfq_var_store(unsigned long *var, const char *page,
+			     size_t count)
+{
+	unsigned long new_val;
+	int ret = kstrtoul(page, 10, &new_val);
+
+	if (ret == 0)
+		*var = new_val;
+
+	return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	if (__CONV == 1)						\
+		__data = jiffies_to_msecs(__data);			\
+	else if (__CONV == 2)						\
+		__data = div_u64(__data, NSEC_PER_MSEC);		\
+	return bfq_var_show(__data, (page));				\
+}
+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
+SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
+SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
+SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+#undef SHOW_FUNCTION
+
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	__data = div_u64(__data, NSEC_PER_USEC);			\
+	return bfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
+#undef USEC_SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t								\
+__FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned long uninitialized_var(__data);			\
+	int ret = bfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV == 1)						\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else if (__CONV == 2)						\
+		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
+		INT_MAX, 2);
+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
+		INT_MAX, 2);
+STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
+STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
+		INT_MAX, 0);
+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
+#undef STORE_FUNCTION
+
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned long uninitialized_var(__data);			\
+	int ret = bfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
+		    UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
+static ssize_t bfq_max_budget_store(struct elevator_queue *e,
+				    const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data == 0)
+		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
+	else {
+		if (__data > INT_MAX)
+			__data = INT_MAX;
+		bfqd->bfq_max_budget = __data;
+	}
+
+	bfqd->bfq_user_max_budget = __data;
+
+	return ret;
+}
+
+/*
+ * Leaving this name to preserve name compatibility with cfq
+ * parameters, but this timeout is used for both sync and async.
+ */
+static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
+				      const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data < 1)
+		__data = 1;
+	else if (__data > INT_MAX)
+		__data = INT_MAX;
+
+	bfqd->bfq_timeout = msecs_to_jiffies(__data);
+	if (bfqd->bfq_user_max_budget == 0)
+		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
+
+	return ret;
+}
+
+static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
+				     const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data > 1)
+		__data = 1;
+	if (!bfqd->strict_guarantees && __data == 1
+	    && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
+		bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;
+
+	bfqd->strict_guarantees = __data;
+
+	return ret;
+}
+
+static ssize_t bfq_low_latency_store(struct elevator_queue *e,
+				     const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data > 1)
+		__data = 1;
+	if (__data == 0 && bfqd->low_latency != 0)
+		bfq_end_wr(bfqd);
+	bfqd->low_latency = __data;
+
+	return ret;
+}
+
+#define BFQ_ATTR(name) \
+	__ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)
+
+static struct elv_fs_entry bfq_attrs[] = {
+	BFQ_ATTR(fifo_expire_sync),
+	BFQ_ATTR(fifo_expire_async),
+	BFQ_ATTR(back_seek_max),
+	BFQ_ATTR(back_seek_penalty),
+	BFQ_ATTR(slice_idle),
+	BFQ_ATTR(slice_idle_us),
+	BFQ_ATTR(max_budget),
+	BFQ_ATTR(timeout_sync),
+	BFQ_ATTR(strict_guarantees),
+	BFQ_ATTR(low_latency),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq_mq = {
+	.ops.mq = {
+		.get_rq_priv		= bfq_get_rq_private,
+		.put_rq_priv		= bfq_put_rq_private,
+		.exit_icq		= bfq_exit_icq,
+		.insert_requests	= bfq_insert_requests,
+		.dispatch_request	= bfq_dispatch_request,
+		.next_request		= elv_rb_latter_request,
+		.former_request		= elv_rb_former_request,
+		.allow_merge		= bfq_allow_bio_merge,
+		.bio_merge		= bfq_bio_merge,
+		.request_merge		= bfq_request_merge,
+		.requests_merged	= bfq_requests_merged,
+		.request_merged		= bfq_request_merged,
+		.has_work		= bfq_has_work,
+		.init_sched		= bfq_init_queue,
+		.exit_sched		= bfq_exit_queue,
+	},
+
+	.uses_mq =		true,
+	.icq_size =		sizeof(struct bfq_io_cq),
+	.icq_align =		__alignof__(struct bfq_io_cq),
+	.elevator_attrs =	bfq_attrs,
+	.elevator_name =	"bfq",
+	.elevator_owner =	THIS_MODULE,
+};
+
+static int __init bfq_init(void)
+{
+	int ret;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	ret = blkcg_policy_register(&blkcg_policy_bfq);
+	if (ret)
+		return ret;
+#endif
+
+	ret = -ENOMEM;
+	if (bfq_slab_setup())
+		goto err_pol_unreg;
+
+	/*
+	 * Times to load large popular applications for the typical
+	 * systems installed on the reference devices (see the
+	 * comments before the definitions of the next two
+	 * arrays). Actually, we use slightly slower values, as the
+	 * estimated peak rate tends to be smaller than the actual
+	 * peak rate.  The reason for this last fact is that estimates
+	 * are computed over much shorter time intervals than the long
+	 * intervals typically used for benchmarking. Why? First, to
+	 * adapt more quickly to variations. Second, because an I/O
+	 * scheduler cannot rely on a peak-rate-evaluation workload to
+	 * be run for a long time.
+	 */
+	T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
+	T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
+	T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+	T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
+
+	/*
+	 * Thresholds that determine the switch between speed classes
+	 * (see the comments before the definition of the array
+	 * device_speed_thresh). These thresholds are biased towards
+	 * transitions to the fast class. This is safer than the
+	 * opposite bias. In fact, a wrong transition to the slow
+	 * class results in short weight-raising periods, because the
+	 * speed of the device then tends to be higher that the
+	 * reference peak rate. On the opposite end, a wrong
+	 * transition to the fast class tends to increase
+	 * weight-raising periods, because of the opposite reason.
+	 */
+	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
+	device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+
+	ret = elv_register(&iosched_bfq_mq);
+	if (ret)
+		goto err_pol_unreg;
+
+	return 0;
+
+err_pol_unreg:
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	return ret;
+}
+
+static void __exit bfq_exit(void)
+{
+	elv_unregister(&iosched_bfq_mq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Paolo Valente");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
new file mode 100644
index 000000000000..ae783c06dfd9
--- /dev/null
+++ b/block/bfq-iosched.h
@@ -0,0 +1,941 @@
+/*
+ * Header file for the BFQ I/O scheduler: data structures and
+ * prototypes of interface functions among BFQ components.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#ifndef _BFQ_H
+#define _BFQ_H
+
+#include <linux/blktrace_api.h>
+#include <linux/hrtimer.h>
+#include <linux/blk-cgroup.h>
+
+#define BFQ_IOPRIO_CLASSES	3
+#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
+
+#define BFQ_MIN_WEIGHT			1
+#define BFQ_MAX_WEIGHT			1000
+#define BFQ_WEIGHT_CONVERSION_COEFF	10
+
+#define BFQ_DEFAULT_QUEUE_IOPRIO	4
+
+#define BFQ_WEIGHT_LEGACY_DFL	100
+#define BFQ_DEFAULT_GRP_IOPRIO	0
+#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
+
+/*
+ * Soft real-time applications are extremely more latency sensitive
+ * than interactive ones. Over-raise the weight of the former to
+ * privilege them against the latter.
+ */
+#define BFQ_SOFTRT_WEIGHT_FACTOR	100
+
+struct bfq_entity;
+
+/**
+ * struct bfq_service_tree - per ioprio_class service tree.
+ *
+ * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
+ * ioprio_class has its own independent scheduler, and so its own
+ * bfq_service_tree.  All the fields are protected by the queue lock
+ * of the containing bfqd.
+ */
+struct bfq_service_tree {
+	/* tree for active entities (i.e., those backlogged) */
+	struct rb_root active;
+	/* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
+	struct rb_root idle;
+
+	/* idle entity with minimum F_i */
+	struct bfq_entity *first_idle;
+	/* idle entity with maximum F_i */
+	struct bfq_entity *last_idle;
+
+	/* scheduler virtual time */
+	u64 vtime;
+	/* scheduler weight sum; active and idle entities contribute to it */
+	unsigned long wsum;
+};
+
+/**
+ * struct bfq_sched_data - multi-class scheduler.
+ *
+ * bfq_sched_data is the basic scheduler queue.  It supports three
+ * ioprio_classes, and can be used either as a toplevel queue or as an
+ * intermediate queue on a hierarchical setup.  @next_in_service
+ * points to the active entity of the sched_data service trees that
+ * will be scheduled next. It is used to reduce the number of steps
+ * needed for each hierarchical-schedule update.
+ *
+ * The supported ioprio_classes are the same as in CFQ, in descending
+ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
+ * Requests from higher priority queues are served before all the
+ * requests from lower priority queues; among requests of the same
+ * queue requests are served according to B-WF2Q+.
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_sched_data {
+	/* entity in service */
+	struct bfq_entity *in_service_entity;
+	/* head-of-line entity (see comments above) */
+	struct bfq_entity *next_in_service;
+	/* array of service trees, one per ioprio_class */
+	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
+	/* last time CLASS_IDLE was served */
+	unsigned long bfq_class_idle_last_service;
+
+};
+
+/**
+ * struct bfq_weight_counter - counter of the number of all active entities
+ *                             with a given weight.
+ */
+struct bfq_weight_counter {
+	unsigned int weight; /* weight of the entities this counter refers to */
+	unsigned int num_active; /* nr of active entities with this weight */
+	/*
+	 * Weights tree member (see bfq_data's @queue_weights_tree and
+	 * @group_weights_tree)
+	 */
+	struct rb_node weights_node;
+};
+
+/**
+ * struct bfq_entity - schedulable entity.
+ *
+ * A bfq_entity is used to represent either a bfq_queue (leaf node in the
+ * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
+ * entity belongs to the sched_data of the parent group in the cgroup
+ * hierarchy.  Non-leaf entities have also their own sched_data, stored
+ * in @my_sched_data.
+ *
+ * Each entity stores independently its priority values; this would
+ * allow different weights on different devices, but this
+ * functionality is not exported to userspace by now.  Priorities and
+ * weights are updated lazily, first storing the new values into the
+ * new_* fields, then setting the @prio_changed flag.  As soon as
+ * there is a transition in the entity state that allows the priority
+ * update to take place the effective and the requested priority
+ * values are synchronized.
+ *
+ * Unless cgroups are used, the weight value is calculated from the
+ * ioprio to export the same interface as CFQ.  When dealing with
+ * ``well-behaved'' queues (i.e., queues that do not spend too much
+ * time to consume their budget and have true sequential behavior, and
+ * when there are no external factors breaking anticipation) the
+ * relative weights at each level of the cgroups hierarchy should be
+ * guaranteed.  All the fields are protected by the queue lock of the
+ * containing bfqd.
+ */
+struct bfq_entity {
+	/* service_tree member */
+	struct rb_node rb_node;
+	/* pointer to the weight counter associated with this entity */
+	struct bfq_weight_counter *weight_counter;
+
+	/*
+	 * Flag, true if the entity is on a tree (either the active or
+	 * the idle one of its service_tree) or is in service.
+	 */
+	bool on_st;
+
+	/* B-WF2Q+ start and finish timestamps [sectors/weight] */
+	u64 start, finish;
+
+	/* tree the entity is enqueued into; %NULL if not on a tree */
+	struct rb_root *tree;
+
+	/*
+	 * minimum start time of the (active) subtree rooted at this
+	 * entity; used for O(log N) lookups into active trees
+	 */
+	u64 min_start;
+
+	/* amount of service received during the last service slot */
+	int service;
+
+	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
+	int budget;
+
+	/* weight of the queue */
+	int weight;
+	/* next weight if a change is in progress */
+	int new_weight;
+
+	/* original weight, used to implement weight boosting */
+	int orig_weight;
+
+	/* parent entity, for hierarchical scheduling */
+	struct bfq_entity *parent;
+
+	/*
+	 * For non-leaf nodes in the hierarchy, the associated
+	 * scheduler queue, %NULL on leaf nodes.
+	 */
+	struct bfq_sched_data *my_sched_data;
+	/* the scheduler queue this entity belongs to */
+	struct bfq_sched_data *sched_data;
+
+	/* flag, set to request a weight, ioprio or ioprio_class change  */
+	int prio_changed;
+};
+
+struct bfq_group;
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+	/* completion time of the last request */
+	u64 last_end_request;
+
+	/* total process thinktime */
+	u64 ttime_total;
+	/* number of thinktime samples */
+	unsigned long ttime_samples;
+	/* average process thinktime */
+	u64 ttime_mean;
+};
+
+/**
+ * struct bfq_queue - leaf schedulable entity.
+ *
+ * A bfq_queue is a leaf request queue; it can be associated with an
+ * io_context or more, if it  is  async or shared  between  cooperating
+ * processes. @cgroup holds a reference to the cgroup, to be sure that it
+ * does not disappear while a bfqq still references it (mostly to avoid
+ * races between request issuing and task migration followed by cgroup
+ * destruction).
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_queue {
+	/* reference counter */
+	int ref;
+	/* parent bfq_data */
+	struct bfq_data *bfqd;
+
+	/* current ioprio and ioprio class */
+	unsigned short ioprio, ioprio_class;
+	/* next ioprio and ioprio class if a change is in progress */
+	unsigned short new_ioprio, new_ioprio_class;
+
+	/*
+	 * Shared bfq_queue if queue is cooperating with one or more
+	 * other queues.
+	 */
+	struct bfq_queue *new_bfqq;
+	/* request-position tree member (see bfq_group's @rq_pos_tree) */
+	struct rb_node pos_node;
+	/* request-position tree root (see bfq_group's @rq_pos_tree) */
+	struct rb_root *pos_root;
+
+	/* sorted list of pending requests */
+	struct rb_root sort_list;
+	/* if fifo isn't expired, next request to serve */
+	struct request *next_rq;
+	/* number of sync and async requests queued */
+	int queued[2];
+	/* number of requests currently allocated */
+	int allocated;
+	/* number of pending metadata requests */
+	int meta_pending;
+	/* fifo list of requests in sort_list */
+	struct list_head fifo;
+
+	/* entity representing this queue in the scheduler */
+	struct bfq_entity entity;
+
+	/* maximum budget allowed from the feedback mechanism */
+	int max_budget;
+	/* budget expiration (in jiffies) */
+	unsigned long budget_timeout;
+
+	/* number of requests on the dispatch list or inside driver */
+	int dispatched;
+
+	/* status flags */
+	unsigned long flags;
+
+	/* node for active/idle bfqq list inside parent bfqd */
+	struct list_head bfqq_list;
+
+	/* associated @bfq_ttime struct */
+	struct bfq_ttime ttime;
+
+	/* bit vector: a 1 for each seeky requests in history */
+	u32 seek_history;
+
+	/* node for the device's burst list */
+	struct hlist_node burst_list_node;
+
+	/* position of the last request enqueued */
+	sector_t last_request_pos;
+
+	/* Number of consecutive pairs of request completion and
+	 * arrival, such that the queue becomes idle after the
+	 * completion, but the next request arrives within an idle
+	 * time slice; used only if the queue's IO_bound flag has been
+	 * cleared.
+	 */
+	unsigned int requests_within_timer;
+
+	/* pid of the process owning the queue, used for logging purposes */
+	pid_t pid;
+
+	/*
+	 * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
+	 * if the queue is shared.
+	 */
+	struct bfq_io_cq *bic;
+
+	/* current maximum weight-raising time for this queue */
+	unsigned long wr_cur_max_time;
+	/*
+	 * Minimum time instant such that, only if a new request is
+	 * enqueued after this time instant in an idle @bfq_queue with
+	 * no outstanding requests, then the task associated with the
+	 * queue it is deemed as soft real-time (see the comments on
+	 * the function bfq_bfqq_softrt_next_start())
+	 */
+	unsigned long soft_rt_next_start;
+	/*
+	 * Start time of the current weight-raising period if
+	 * the @bfq-queue is being weight-raised, otherwise
+	 * finish time of the last weight-raising period.
+	 */
+	unsigned long last_wr_start_finish;
+	/* factor by which the weight of this queue is multiplied */
+	unsigned int wr_coeff;
+	/*
+	 * Time of the last transition of the @bfq_queue from idle to
+	 * backlogged.
+	 */
+	unsigned long last_idle_bklogged;
+	/*
+	 * Cumulative service received from the @bfq_queue since the
+	 * last transition from idle to backlogged.
+	 */
+	unsigned long service_from_backlogged;
+
+	/*
+	 * Value of wr start time when switching to soft rt
+	 */
+	unsigned long wr_start_at_switch_to_srt;
+
+	unsigned long split_time; /* time of last split */
+};
+
+/**
+ * struct bfq_io_cq - per (request_queue, io_context) structure.
+ */
+struct bfq_io_cq {
+	/* associated io_cq structure */
+	struct io_cq icq; /* must be the first member */
+	/* array of two process queues, the sync and the async */
+	struct bfq_queue *bfqq[2];
+	/* per (request_queue, blkcg) ioprio */
+	int ioprio;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
+	/*
+	 * Snapshot of the idle window before merging; taken to
+	 * remember this value while the queue is merged, so as to be
+	 * able to restore it in case of split.
+	 */
+	bool saved_idle_window;
+	/*
+	 * Same purpose as the previous two fields for the I/O bound
+	 * classification of a queue.
+	 */
+	bool saved_IO_bound;
+
+	/*
+	 * Same purpose as the previous fields for the value of the
+	 * field keeping the queue's belonging to a large burst
+	 */
+	bool saved_in_large_burst;
+	/*
+	 * True if the queue belonged to a burst list before its merge
+	 * with another cooperating queue.
+	 */
+	bool was_in_burst_list;
+
+	/*
+	 * Similar to previous fields: save wr information.
+	 */
+	unsigned long saved_wr_coeff;
+	unsigned long saved_last_wr_start_finish;
+	unsigned long saved_wr_start_at_switch_to_srt;
+	unsigned int saved_wr_cur_max_time;
+	struct bfq_ttime saved_ttime;
+};
+
+enum bfq_device_speed {
+	BFQ_BFQD_FAST,
+	BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per-device data structure.
+ *
+ * All the fields are protected by @lock.
+ */
+struct bfq_data {
+	/* device request queue */
+	struct request_queue *queue;
+	/* dispatch queue */
+	struct list_head dispatch;
+
+	/* root bfq_group for the device */
+	struct bfq_group *root_group;
+
+	/*
+	 * rbtree of weight counters of @bfq_queues, sorted by
+	 * weight. Used to keep track of whether all @bfq_queues have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active and not
+	 * weight-raised @bfq_queue (see the comments to the functions
+	 * bfq_weights_tree_[add|remove] for further details).
+	 */
+	struct rb_root queue_weights_tree;
+	/*
+	 * rbtree of non-queue @bfq_entity weight counters, sorted by
+	 * weight. Used to keep track of whether all @bfq_groups have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active @bfq_group (see
+	 * the comments to the functions bfq_weights_tree_[add|remove]
+	 * for further details).
+	 */
+	struct rb_root group_weights_tree;
+
+	/*
+	 * Number of bfq_queues containing requests (including the
+	 * queue in service, even if it is idling).
+	 */
+	int busy_queues;
+	/* number of weight-raised busy @bfq_queues */
+	int wr_busy_queues;
+	/* number of queued requests */
+	int queued;
+	/* number of requests dispatched and waiting for completion */
+	int rq_in_driver;
+
+	/*
+	 * Maximum number of requests in driver in the last
+	 * @hw_tag_samples completed requests.
+	 */
+	int max_rq_in_driver;
+	/* number of samples used to calculate hw_tag */
+	int hw_tag_samples;
+	/* flag set to one if the driver is showing a queueing behavior */
+	int hw_tag;
+
+	/* number of budgets assigned */
+	int budgets_assigned;
+
+	/*
+	 * Timer set when idling (waiting) for the next request from
+	 * the queue in service.
+	 */
+	struct hrtimer idle_slice_timer;
+
+	/* bfq_queue in service */
+	struct bfq_queue *in_service_queue;
+
+	/* on-disk position of the last served request */
+	sector_t last_position;
+
+	/* time of last request completion (ns) */
+	u64 last_completion;
+
+	/* time of first rq dispatch in current observation interval (ns) */
+	u64 first_dispatch;
+	/* time of last rq dispatch in current observation interval (ns) */
+	u64 last_dispatch;
+
+	/* beginning of the last budget */
+	ktime_t last_budget_start;
+	/* beginning of the last idle slice */
+	ktime_t last_idling_start;
+
+	/* number of samples in current observation interval */
+	int peak_rate_samples;
+	/* num of samples of seq dispatches in current observation interval */
+	u32 sequential_samples;
+	/* total num of sectors transferred in current observation interval */
+	u64 tot_sectors_dispatched;
+	/* max rq size seen during current observation interval (sectors) */
+	u32 last_rq_max_size;
+	/* time elapsed from first dispatch in current observ. interval (us) */
+	u64 delta_from_first;
+	/*
+	 * Current estimate of the device peak rate, measured in
+	 * [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
+	 * BFQ_RATE_SHIFT is performed to increase precision in
+	 * fixed-point calculations.
+	 */
+	u32 peak_rate;
+
+	/* maximum budget allotted to a bfq_queue before rescheduling */
+	int bfq_max_budget;
+
+	/* list of all the bfq_queues active on the device */
+	struct list_head active_list;
+	/* list of all the bfq_queues idle on the device */
+	struct list_head idle_list;
+
+	/*
+	 * Timeout for async/sync requests; when it fires, requests
+	 * are served in fifo order.
+	 */
+	u64 bfq_fifo_expire[2];
+	/* weight of backward seeks wrt forward ones */
+	unsigned int bfq_back_penalty;
+	/* maximum allowed backward seek */
+	unsigned int bfq_back_max;
+	/* maximum idling time */
+	u32 bfq_slice_idle;
+
+	/* user-configured max budget value (0 for auto-tuning) */
+	int bfq_user_max_budget;
+	/*
+	 * Timeout for bfq_queues to consume their budget; used to
+	 * prevent seeky queues from imposing long latencies to
+	 * sequential or quasi-sequential ones (this also implies that
+	 * seeky queues cannot receive guarantees in the service
+	 * domain; after a timeout they are charged for the time they
+	 * have been in service, to preserve fairness among them, but
+	 * without service-domain guarantees).
+	 */
+	unsigned int bfq_timeout;
+
+	/*
+	 * Number of consecutive requests that must be issued within
+	 * the idle time slice to set again idling to a queue which
+	 * was marked as non-I/O-bound (see the definition of the
+	 * IO_bound flag for further details).
+	 */
+	unsigned int bfq_requests_within_timer;
+
+	/*
+	 * Force device idling whenever needed to provide accurate
+	 * service guarantees, without caring about throughput
+	 * issues. CAVEAT: this may even increase latencies, in case
+	 * of useless idling for processes that did stop doing I/O.
+	 */
+	bool strict_guarantees;
+
+	/*
+	 * Last time at which a queue entered the current burst of
+	 * queues being activated shortly after each other; for more
+	 * details about this and the following parameters related to
+	 * a burst of activations, see the comments on the function
+	 * bfq_handle_burst.
+	 */
+	unsigned long last_ins_in_burst;
+	/*
+	 * Reference time interval used to decide whether a queue has
+	 * been activated shortly after @last_ins_in_burst.
+	 */
+	unsigned long bfq_burst_interval;
+	/* number of queues in the current burst of queue activations */
+	int burst_size;
+
+	/* common parent entity for the queues in the burst */
+	struct bfq_entity *burst_parent_entity;
+	/* Maximum burst size above which the current queue-activation
+	 * burst is deemed as 'large'.
+	 */
+	unsigned long bfq_large_burst_thresh;
+	/* true if a large queue-activation burst is in progress */
+	bool large_burst;
+	/*
+	 * Head of the burst list (as for the above fields, more
+	 * details in the comments on the function bfq_handle_burst).
+	 */
+	struct hlist_head burst_list;
+
+	/* if set to true, low-latency heuristics are enabled */
+	bool low_latency;
+	/*
+	 * Maximum factor by which the weight of a weight-raised queue
+	 * is multiplied.
+	 */
+	unsigned int bfq_wr_coeff;
+	/* maximum duration of a weight-raising period (jiffies) */
+	unsigned int bfq_wr_max_time;
+
+	/* Maximum weight-raising duration for soft real-time processes */
+	unsigned int bfq_wr_rt_max_time;
+	/*
+	 * Minimum idle period after which weight-raising may be
+	 * reactivated for a queue (in jiffies).
+	 */
+	unsigned int bfq_wr_min_idle_time;
+	/*
+	 * Minimum period between request arrivals after which
+	 * weight-raising may be reactivated for an already busy async
+	 * queue (in jiffies).
+	 */
+	unsigned long bfq_wr_min_inter_arr_async;
+
+	/* Max service-rate for a soft real-time queue, in sectors/sec */
+	unsigned int bfq_wr_max_softrt_rate;
+	/*
+	 * Cached value of the product R*T, used for computing the
+	 * maximum duration of weight raising automatically.
+	 */
+	u64 RT_prod;
+	/* device-speed class for the low-latency heuristic */
+	enum bfq_device_speed device_speed;
+
+	/* fallback dummy bfqq for extreme OOM conditions */
+	struct bfq_queue oom_bfqq;
+
+	spinlock_t lock;
+
+	/*
+	 * bic associated with the task issuing current bio for
+	 * merging. This and the next field are used as a support to
+	 * be able to perform the bic lookup, needed by bio-merge
+	 * functions, before the scheduler lock is taken, and thus
+	 * avoid taking the request-queue lock while the scheduler
+	 * lock is being held.
+	 */
+	struct bfq_io_cq *bio_bic;
+	/* bfqq associated with the task issuing current bio for merging */
+	struct bfq_queue *bio_bfqq;
+};
+
+enum bfqq_state_flags {
+	BFQQF_just_created = 0,	/* queue just allocated */
+	BFQQF_busy,		/* has requests or is in service */
+	BFQQF_wait_request,	/* waiting for a request */
+	BFQQF_non_blocking_wait_rq, /*
+				     * waiting for a request
+				     * without idling the device
+				     */
+	BFQQF_fifo_expire,	/* FIFO checked in this slice */
+	BFQQF_idle_window,	/* slice idling enabled */
+	BFQQF_sync,		/* synchronous queue */
+	BFQQF_IO_bound,		/*
+				 * bfqq has timed-out at least once
+				 * having consumed at most 2/10 of
+				 * its budget
+				 */
+	BFQQF_in_large_burst,	/*
+				 * bfqq activated in a large burst,
+				 * see comments to bfq_handle_burst.
+				 */
+	BFQQF_softrt_update,	/*
+				 * may need softrt-next-start
+				 * update
+				 */
+	BFQQF_coop,		/* bfqq is shared */
+	BFQQF_split_coop	/* shared bfqq will be split */
+};
+
+#define BFQ_BFQQ_FNS(name)						\
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq);			\
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq);			\
+int bfq_bfqq_##name(const struct bfq_queue *bfqq);
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS
+
+/* Expiration reasons. */
+enum bfqq_expiration {
+	BFQQE_TOO_IDLE = 0,		/*
+					 * queue has been idling for
+					 * too long
+					 */
+	BFQQE_BUDGET_TIMEOUT,	/* budget took too long to be used */
+	BFQQE_BUDGET_EXHAUSTED,	/* budget consumed */
+	BFQQE_NO_MORE_REQUESTS,	/* the queue has no more requests */
+	BFQQE_PREEMPTED		/* preemption in progress */
+};
+
+struct bfqg_stats {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	/* number of ios merged */
+	struct blkg_rwstat		merged;
+	/* total time spent on device in ns, may not be accurate w/ queueing */
+	struct blkg_rwstat		service_time;
+	/* total time spent waiting in scheduler queue in ns */
+	struct blkg_rwstat		wait_time;
+	/* number of IOs queued up */
+	struct blkg_rwstat		queued;
+	/* total disk time and nr sectors dispatched by this group */
+	struct blkg_stat		time;
+	/* sum of number of ios queued across all samples */
+	struct blkg_stat		avg_queue_size_sum;
+	/* count of samples taken for average */
+	struct blkg_stat		avg_queue_size_samples;
+	/* how many times this group has been removed from service tree */
+	struct blkg_stat		dequeue;
+	/* total time spent waiting for it to be assigned a timeslice. */
+	struct blkg_stat		group_wait_time;
+	/* time spent idling for this blkcg_gq */
+	struct blkg_stat		idle_time;
+	/* total time with empty current active q with other requests queued */
+	struct blkg_stat		empty_time;
+	/* fields after this shouldn't be cleared on stat reset */
+	uint64_t			start_group_wait_time;
+	uint64_t			start_idle_time;
+	uint64_t			start_empty_time;
+	uint16_t			flags;
+#endif	/* CONFIG_BFQ_GROUP_IOSCHED */
+};
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/*
+ * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
+ *
+ * @ps: @blkcg_policy_storage that this structure inherits
+ * @weight: weight of the bfq_group
+ */
+struct bfq_group_data {
+	/* must be the first member */
+	struct blkcg_policy_data pd;
+
+	unsigned int weight;
+};
+
+/**
+ * struct bfq_group - per (device, cgroup) data structure.
+ * @entity: schedulable entity to insert into the parent group sched_data.
+ * @sched_data: own sched_data, to contain child entities (they may be
+ *              both bfq_queues and bfq_groups).
+ * @bfqd: the bfq_data for the device this group acts upon.
+ * @async_bfqq: array of async queues for all the tasks belonging to
+ *              the group, one queue per ioprio value per ioprio_class,
+ *              except for the idle class that has only one queue.
+ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
+ * @my_entity: pointer to @entity, %NULL for the toplevel group; used
+ *             to avoid too many special cases during group creation/
+ *             migration.
+ * @stats: stats for this bfqg.
+ * @active_entities: number of active entities belonging to the group;
+ *                   unused for the root group. Used to know whether there
+ *                   are groups with more than one active @bfq_entity
+ *                   (see the comments to the function
+ *                   bfq_bfqq_may_idle()).
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ *               determining if two or more queues have interleaving
+ *               requests (see bfq_find_close_cooperator()).
+ *
+ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
+ * there is a set of bfq_groups, each one collecting the lower-level
+ * entities belonging to the group that are acting on the same device.
+ *
+ * Locking works as follows:
+ *    o @bfqd is protected by the queue lock, RCU is used to access it
+ *      from the readers.
+ *    o All the other fields are protected by the @bfqd queue lock.
+ */
+struct bfq_group {
+	/* must be the first member */
+	struct blkg_policy_data pd;
+
+	struct bfq_entity entity;
+	struct bfq_sched_data sched_data;
+
+	void *bfqd;
+
+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+	struct bfq_queue *async_idle_bfqq;
+
+	struct bfq_entity *my_entity;
+
+	int active_entities;
+
+	struct rb_root rq_pos_tree;
+
+	struct bfqg_stats stats;
+};
+
+#else
+struct bfq_group {
+	struct bfq_sched_data sched_data;
+
+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+	struct bfq_queue *async_idle_bfqq;
+
+	struct rb_root rq_pos_tree;
+};
+#endif
+
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+
+/* --------------- main algorithm interface ----------------- */
+
+#define BFQ_SERVICE_TREE_INIT	((struct bfq_service_tree)		\
+				{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
+
+extern const int bfq_timeout;
+
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+			  struct rb_root *root);
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+			     struct rb_root *root);
+void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     bool compensate, enum bfqq_expiration reason);
+void bfq_put_queue(struct bfq_queue *bfqq);
+void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+void bfq_schedule_dispatch(struct bfq_data *bfqd);
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+
+/* ------------ end of main algorithm interface -------------- */
+
+/* ---------------- cgroups-support interface ---------------- */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op);
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op);
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		   struct bfq_group *bfqg);
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
+void bfq_end_wr_async(struct bfq_data *bfqd);
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+				     struct blkcg *blkcg);
+struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
+void bfqg_put(struct bfq_group *bfqg);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+extern struct cftype bfq_blkcg_legacy_files[];
+extern struct cftype bfq_blkg_files[];
+extern struct blkcg_policy blkcg_policy_bfq;
+#endif
+
+/* ------------- end of cgroups-support interface ------------- */
+
+/* - interface of the internal hierarchical B-WF2Q+ scheduler - */
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+/* both next loops stop at one of the child entities of the root group */
+#define for_each_entity(entity)	\
+	for (; entity ; entity = entity->parent)
+
+/*
+ * For each iteration, compute parent in advance, so as to be safe if
+ * entity is deallocated during the iteration. Such a deallocation may
+ * happen as a consequence of a bfq_put_queue that frees the bfq_queue
+ * containing entity.
+ */
+#define for_each_entity_safe(entity, parent) \
+	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+/*
+ * Next two macros are fake loops when cgroups support is not
+ * enabled. I fact, in such a case, there is only one level to go up
+ * (to reach the root group).
+ */
+#define for_each_entity(entity)	\
+	for (; entity ; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+	for (parent = NULL; entity ; entity = parent)
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
+struct bfq_entity *bfq_entity_of(struct rb_node *node);
+unsigned short bfq_ioprio_to_weight(int ioprio);
+void bfq_put_idle_entity(struct bfq_service_tree *st,
+			 struct bfq_entity *entity);
+struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+				struct bfq_entity *entity);
+void bfq_bfqq_served(struct bfq_queue *bfqq, int served);
+void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  unsigned long time_ms);
+bool __bfq_deactivate_entity(struct bfq_entity *entity,
+			     bool ins_into_idle_tree);
+bool next_queue_may_preempt(struct bfq_data *bfqd);
+struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
+void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			 bool ins_into_idle_tree, bool expiration);
+void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       bool expiration);
+void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+/* --------------- end of interface of B-WF2Q+ ---------------- */
+
+/* Logging facilities. */
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
+	char __pbuf[128];						\
+									\
+	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
+	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
+			  __pbuf, ##args);				\
+} while (0)
+
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
+	char __pbuf[128];						\
+									\
+	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
+	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
+} while (0)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	\
+	blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid,	\
+			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
+				##args)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log(bfqd, fmt, args...) \
+	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+
+#endif /* _BFQ_H */
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
new file mode 100644
index 000000000000..b4fc3e4260b7
--- /dev/null
+++ b/block/bfq-wf2q.c
@@ -0,0 +1,1616 @@
+/*
+ * Hierarchical Budget Worst-case Fair Weighted Fair Queueing
+ * (B-WF2Q+): hierarchical scheduling algorithm by which the BFQ I/O
+ * scheduler schedules generic entities. The latter can represent
+ * either single bfq queues (associated with processes) or groups of
+ * bfq queues (associated with cgroups).
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#include "bfq-iosched.h"
+
+/**
+ * bfq_gt - compare two timestamps.
+ * @a: first ts.
+ * @b: second ts.
+ *
+ * Return @a > @b, dealing with wrapping correctly.
+ */
+static int bfq_gt(u64 a, u64 b)
+{
+	return (s64)(a - b) > 0;
+}
+
+static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
+{
+	struct rb_node *node = tree->rb_node;
+
+	return rb_entry(node, struct bfq_entity, rb_node);
+}
+
+static unsigned int bfq_class_idx(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	return bfqq ? bfqq->ioprio_class - 1 :
+		BFQ_DEFAULT_GRP_CLASS - 1;
+}
+
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
+
+/**
+ * bfq_update_next_in_service - update sd->next_in_service
+ * @sd: sched_data for which to perform the update.
+ * @new_entity: if not NULL, pointer to the entity whose activation,
+ *		requeueing or repositionig triggered the invocation of
+ *		this function.
+ *
+ * This function is called to update sd->next_in_service, which, in
+ * its turn, may change as a consequence of the insertion or
+ * extraction of an entity into/from one of the active trees of
+ * sd. These insertions/extractions occur as a consequence of
+ * activations/deactivations of entities, with some activations being
+ * 'true' activations, and other activations being requeueings (i.e.,
+ * implementing the second, requeueing phase of the mechanism used to
+ * reposition an entity in its active tree; see comments on
+ * __bfq_activate_entity and __bfq_requeue_entity for details). In
+ * both the last two activation sub-cases, new_entity points to the
+ * just activated or requeued entity.
+ *
+ * Returns true if sd->next_in_service changes in such a way that
+ * entity->parent may become the next_in_service for its parent
+ * entity.
+ */
+static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
+				       struct bfq_entity *new_entity)
+{
+	struct bfq_entity *next_in_service = sd->next_in_service;
+	bool parent_sched_may_change = false;
+
+	/*
+	 * If this update is triggered by the activation, requeueing
+	 * or repositiong of an entity that does not coincide with
+	 * sd->next_in_service, then a full lookup in the active tree
+	 * can be avoided. In fact, it is enough to check whether the
+	 * just-modified entity has a higher priority than
+	 * sd->next_in_service, or, even if it has the same priority
+	 * as sd->next_in_service, is eligible and has a lower virtual
+	 * finish time than sd->next_in_service. If this compound
+	 * condition holds, then the new entity becomes the new
+	 * next_in_service. Otherwise no change is needed.
+	 */
+	if (new_entity && new_entity != sd->next_in_service) {
+		/*
+		 * Flag used to decide whether to replace
+		 * sd->next_in_service with new_entity. Tentatively
+		 * set to true, and left as true if
+		 * sd->next_in_service is NULL.
+		 */
+		bool replace_next = true;
+
+		/*
+		 * If there is already a next_in_service candidate
+		 * entity, then compare class priorities or timestamps
+		 * to decide whether to replace sd->service_tree with
+		 * new_entity.
+		 */
+		if (next_in_service) {
+			unsigned int new_entity_class_idx =
+				bfq_class_idx(new_entity);
+			struct bfq_service_tree *st =
+				sd->service_tree + new_entity_class_idx;
+
+			/*
+			 * For efficiency, evaluate the most likely
+			 * sub-condition first.
+			 */
+			replace_next =
+				(new_entity_class_idx ==
+				 bfq_class_idx(next_in_service)
+				 &&
+				 !bfq_gt(new_entity->start, st->vtime)
+				 &&
+				 bfq_gt(next_in_service->finish,
+					new_entity->finish))
+				||
+				new_entity_class_idx <
+				bfq_class_idx(next_in_service);
+		}
+
+		if (replace_next)
+			next_in_service = new_entity;
+	} else /* invoked because of a deactivation: lookup needed */
+		next_in_service = bfq_lookup_next_entity(sd);
+
+	if (next_in_service) {
+		parent_sched_may_change = !sd->next_in_service ||
+			bfq_update_parent_budget(next_in_service);
+	}
+
+	sd->next_in_service = next_in_service;
+
+	if (!next_in_service)
+		return parent_sched_may_change;
+
+	return parent_sched_may_change;
+}
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *group_entity = bfqq->entity.parent;
+
+	if (!group_entity)
+		group_entity = &bfqq->bfqd->root_group->entity;
+
+	return container_of(group_entity, struct bfq_group, entity);
+}
+
+/*
+ * Returns true if this budget changes may let next_in_service->parent
+ * become the next_in_service entity for its parent entity.
+ */
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
+{
+	struct bfq_entity *bfqg_entity;
+	struct bfq_group *bfqg;
+	struct bfq_sched_data *group_sd;
+	bool ret = false;
+
+	group_sd = next_in_service->sched_data;
+
+	bfqg = container_of(group_sd, struct bfq_group, sched_data);
+	/*
+	 * bfq_group's my_entity field is not NULL only if the group
+	 * is not the root group. We must not touch the root entity
+	 * as it must never become an in-service entity.
+	 */
+	bfqg_entity = bfqg->my_entity;
+	if (bfqg_entity) {
+		if (bfqg_entity->budget > next_in_service->budget)
+			ret = true;
+		bfqg_entity->budget = next_in_service->budget;
+	}
+
+	return ret;
+}
+
+/*
+ * This function tells whether entity stops being a candidate for next
+ * service, according to the following logic.
+ *
+ * This function is invoked for an entity that is about to be set in
+ * service. If such an entity is a queue, then the entity is no longer
+ * a candidate for next service (i.e, a candidate entity to serve
+ * after the in-service entity is expired). The function then returns
+ * true.
+ *
+ * In contrast, the entity could stil be a candidate for next service
+ * if it is not a queue, and has more than one child. In fact, even if
+ * one of its children is about to be set in service, other children
+ * may still be the next to serve. As a consequence, a non-queue
+ * entity is not a candidate for next-service only if it has only one
+ * child. And only if this condition holds, then the function returns
+ * true for a non-queue entity.
+ */
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+	struct bfq_group *bfqg;
+
+	if (bfq_entity_to_bfqq(entity))
+		return true;
+
+	bfqg = container_of(entity, struct bfq_group, entity);
+
+	if (bfqg->active_entities == 1)
+		return true;
+
+	return false;
+}
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	return bfqq->bfqd->root_group;
+}
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
+{
+	return false;
+}
+
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+	return true;
+}
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+/*
+ * Shift for timestamp calculations.  This actually limits the maximum
+ * service allowed in one timestamp delta (small shift values increase it),
+ * the maximum total weight that can be used for the queues in the system
+ * (big shift values increase it), and the period of virtual time
+ * wraparounds.
+ */
+#define WFQ_SERVICE_SHIFT	22
+
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = NULL;
+
+	if (!entity->my_sched_data)
+		bfqq = container_of(entity, struct bfq_queue, entity);
+
+	return bfqq;
+}
+
+
+/**
+ * bfq_delta - map service into the virtual time domain.
+ * @service: amount of service.
+ * @weight: scale factor (weight of an entity or weight sum).
+ */
+static u64 bfq_delta(unsigned long service, unsigned long weight)
+{
+	u64 d = (u64)service << WFQ_SERVICE_SHIFT;
+
+	do_div(d, weight);
+	return d;
+}
+
+/**
+ * bfq_calc_finish - assign the finish time to an entity.
+ * @entity: the entity to act upon.
+ * @service: the service to be charged to the entity.
+ */
+static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->finish = entity->start +
+		bfq_delta(service, entity->weight);
+
+	if (bfqq) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"calc_finish: serv %lu, w %d",
+			service, entity->weight);
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"calc_finish: start %llu, finish %llu, delta %llu",
+			entity->start, entity->finish,
+			bfq_delta(service, entity->weight));
+	}
+}
+
+/**
+ * bfq_entity_of - get an entity from a node.
+ * @node: the node field of the entity.
+ *
+ * Convert a node pointer to the relative entity.  This is used only
+ * to simplify the logic of some functions and not as the generic
+ * conversion mechanism because, e.g., in the tree walking functions,
+ * the check for a %NULL value would be redundant.
+ */
+struct bfq_entity *bfq_entity_of(struct rb_node *node)
+{
+	struct bfq_entity *entity = NULL;
+
+	if (node)
+		entity = rb_entry(node, struct bfq_entity, rb_node);
+
+	return entity;
+}
+
+/**
+ * bfq_extract - remove an entity from a tree.
+ * @root: the tree root.
+ * @entity: the entity to remove.
+ */
+static void bfq_extract(struct rb_root *root, struct bfq_entity *entity)
+{
+	entity->tree = NULL;
+	rb_erase(&entity->rb_node, root);
+}
+
+/**
+ * bfq_idle_extract - extract an entity from the idle tree.
+ * @st: the service tree of the owning @entity.
+ * @entity: the entity being removed.
+ */
+static void bfq_idle_extract(struct bfq_service_tree *st,
+			     struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *next;
+
+	if (entity == st->first_idle) {
+		next = rb_next(&entity->rb_node);
+		st->first_idle = bfq_entity_of(next);
+	}
+
+	if (entity == st->last_idle) {
+		next = rb_prev(&entity->rb_node);
+		st->last_idle = bfq_entity_of(next);
+	}
+
+	bfq_extract(&st->idle, entity);
+
+	if (bfqq)
+		list_del(&bfqq->bfqq_list);
+}
+
+/**
+ * bfq_insert - generic tree insertion.
+ * @root: tree root.
+ * @entity: entity to insert.
+ *
+ * This is used for the idle and the active tree, since they are both
+ * ordered by finish time.
+ */
+static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
+{
+	struct bfq_entity *entry;
+	struct rb_node **node = &root->rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*node) {
+		parent = *node;
+		entry = rb_entry(parent, struct bfq_entity, rb_node);
+
+		if (bfq_gt(entry->finish, entity->finish))
+			node = &parent->rb_left;
+		else
+			node = &parent->rb_right;
+	}
+
+	rb_link_node(&entity->rb_node, parent, node);
+	rb_insert_color(&entity->rb_node, root);
+
+	entity->tree = root;
+}
+
+/**
+ * bfq_update_min - update the min_start field of a entity.
+ * @entity: the entity to update.
+ * @node: one of its children.
+ *
+ * This function is called when @entity may store an invalid value for
+ * min_start due to updates to the active tree.  The function  assumes
+ * that the subtree rooted at @node (which may be its left or its right
+ * child) has a valid min_start value.
+ */
+static void bfq_update_min(struct bfq_entity *entity, struct rb_node *node)
+{
+	struct bfq_entity *child;
+
+	if (node) {
+		child = rb_entry(node, struct bfq_entity, rb_node);
+		if (bfq_gt(entity->min_start, child->min_start))
+			entity->min_start = child->min_start;
+	}
+}
+
+/**
+ * bfq_update_active_node - recalculate min_start.
+ * @node: the node to update.
+ *
+ * @node may have changed position or one of its children may have moved,
+ * this function updates its min_start value.  The left and right subtrees
+ * are assumed to hold a correct min_start value.
+ */
+static void bfq_update_active_node(struct rb_node *node)
+{
+	struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
+
+	entity->min_start = entity->start;
+	bfq_update_min(entity, node->rb_right);
+	bfq_update_min(entity, node->rb_left);
+}
+
+/**
+ * bfq_update_active_tree - update min_start for the whole active tree.
+ * @node: the starting node.
+ *
+ * @node must be the deepest modified node after an update.  This function
+ * updates its min_start using the values held by its children, assuming
+ * that they did not change, and then updates all the nodes that may have
+ * changed in the path to the root.  The only nodes that may have changed
+ * are the ones in the path or their siblings.
+ */
+static void bfq_update_active_tree(struct rb_node *node)
+{
+	struct rb_node *parent;
+
+up:
+	bfq_update_active_node(node);
+
+	parent = rb_parent(node);
+	if (!parent)
+		return;
+
+	if (node == parent->rb_left && parent->rb_right)
+		bfq_update_active_node(parent->rb_right);
+	else if (parent->rb_left)
+		bfq_update_active_node(parent->rb_left);
+
+	node = parent;
+	goto up;
+}
+
+/**
+ * bfq_active_insert - insert an entity in the active tree of its
+ *                     group/device.
+ * @st: the service tree of the entity.
+ * @entity: the entity being inserted.
+ *
+ * The active tree is ordered by finish time, but an extra key is kept
+ * per each node, containing the minimum value for the start times of
+ * its children (and the node itself), so it's possible to search for
+ * the eligible node with the lowest finish time in logarithmic time.
+ */
+static void bfq_active_insert(struct bfq_service_tree *st,
+			      struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *node = &entity->rb_node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	struct bfq_sched_data *sd = NULL;
+	struct bfq_group *bfqg = NULL;
+	struct bfq_data *bfqd = NULL;
+#endif
+
+	bfq_insert(&st->active, entity);
+
+	if (node->rb_left)
+		node = node->rb_left;
+	else if (node->rb_right)
+		node = node->rb_right;
+
+	bfq_update_active_tree(node);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	else /* bfq_group */
+		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
+
+	if (bfqg != bfqd->root_group)
+		bfqg->active_entities++;
+#endif
+}
+
+/**
+ * bfq_ioprio_to_weight - calc a weight from an ioprio.
+ * @ioprio: the ioprio value to convert.
+ */
+unsigned short bfq_ioprio_to_weight(int ioprio)
+{
+	return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
+}
+
+/**
+ * bfq_weight_to_ioprio - calc an ioprio from a weight.
+ * @weight: the weight value to convert.
+ *
+ * To preserve as much as possible the old only-ioprio user interface,
+ * 0 is used as an escape ioprio value for weights (numerically) equal or
+ * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF.
+ */
+static unsigned short bfq_weight_to_ioprio(int weight)
+{
+	return max_t(int, 0,
+		     IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight);
+}
+
+static void bfq_get_entity(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	if (bfqq) {
+		bfqq->ref++;
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
+			     bfqq, bfqq->ref);
+	}
+}
+
+/**
+ * bfq_find_deepest - find the deepest node that an extraction can modify.
+ * @node: the node being removed.
+ *
+ * Do the first step of an extraction in an rb tree, looking for the
+ * node that will replace @node, and returning the deepest node that
+ * the following modifications to the tree can touch.  If @node is the
+ * last node in the tree return %NULL.
+ */
+static struct rb_node *bfq_find_deepest(struct rb_node *node)
+{
+	struct rb_node *deepest;
+
+	if (!node->rb_right && !node->rb_left)
+		deepest = rb_parent(node);
+	else if (!node->rb_right)
+		deepest = node->rb_left;
+	else if (!node->rb_left)
+		deepest = node->rb_right;
+	else {
+		deepest = rb_next(node);
+		if (deepest->rb_right)
+			deepest = deepest->rb_right;
+		else if (rb_parent(deepest) != node)
+			deepest = rb_parent(deepest);
+	}
+
+	return deepest;
+}
+
+/**
+ * bfq_active_extract - remove an entity from the active tree.
+ * @st: the service_tree containing the tree.
+ * @entity: the entity being removed.
+ */
+static void bfq_active_extract(struct bfq_service_tree *st,
+			       struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	struct bfq_sched_data *sd = NULL;
+	struct bfq_group *bfqg = NULL;
+	struct bfq_data *bfqd = NULL;
+#endif
+
+	node = bfq_find_deepest(&entity->rb_node);
+	bfq_extract(&st->active, entity);
+
+	if (node)
+		bfq_update_active_tree(node);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq)
+		list_del(&bfqq->bfqq_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	else /* bfq_group */
+		bfq_weights_tree_remove(bfqd, entity,
+					&bfqd->group_weights_tree);
+
+	if (bfqg != bfqd->root_group)
+		bfqg->active_entities--;
+#endif
+}
+
+/**
+ * bfq_idle_insert - insert an entity into the idle tree.
+ * @st: the service tree containing the tree.
+ * @entity: the entity to insert.
+ */
+static void bfq_idle_insert(struct bfq_service_tree *st,
+			    struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_entity *first_idle = st->first_idle;
+	struct bfq_entity *last_idle = st->last_idle;
+
+	if (!first_idle || bfq_gt(first_idle->finish, entity->finish))
+		st->first_idle = entity;
+	if (!last_idle || bfq_gt(entity->finish, last_idle->finish))
+		st->last_idle = entity;
+
+	bfq_insert(&st->idle, entity);
+
+	if (bfqq)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
+}
+
+/**
+ * bfq_forget_entity - do not consider entity any longer for scheduling
+ * @st: the service tree.
+ * @entity: the entity being removed.
+ * @is_in_service: true if entity is currently the in-service entity.
+ *
+ * Forget everything about @entity. In addition, if entity represents
+ * a queue, and the latter is not in service, then release the service
+ * reference to the queue (the one taken through bfq_get_entity). In
+ * fact, in this case, there is really no more service reference to
+ * the queue, as the latter is also outside any service tree. If,
+ * instead, the queue is in service, then __bfq_bfqd_reset_in_service
+ * will take care of putting the reference when the queue finally
+ * stops being served.
+ */
+static void bfq_forget_entity(struct bfq_service_tree *st,
+			      struct bfq_entity *entity,
+			      bool is_in_service)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->on_st = false;
+	st->wsum -= entity->weight;
+	if (bfqq && !is_in_service)
+		bfq_put_queue(bfqq);
+}
+
+/**
+ * bfq_put_idle_entity - release the idle tree ref of an entity.
+ * @st: service tree for the entity.
+ * @entity: the entity being released.
+ */
+void bfq_put_idle_entity(struct bfq_service_tree *st, struct bfq_entity *entity)
+{
+	bfq_idle_extract(st, entity);
+	bfq_forget_entity(st, entity,
+			  entity == entity->sched_data->in_service_entity);
+}
+
+/**
+ * bfq_forget_idle - update the idle tree if necessary.
+ * @st: the service tree to act upon.
+ *
+ * To preserve the global O(log N) complexity we only remove one entry here;
+ * as the idle tree will not grow indefinitely this can be done safely.
+ */
+static void bfq_forget_idle(struct bfq_service_tree *st)
+{
+	struct bfq_entity *first_idle = st->first_idle;
+	struct bfq_entity *last_idle = st->last_idle;
+
+	if (RB_EMPTY_ROOT(&st->active) && last_idle &&
+	    !bfq_gt(last_idle->finish, st->vtime)) {
+		/*
+		 * Forget the whole idle tree, increasing the vtime past
+		 * the last finish time of idle entities.
+		 */
+		st->vtime = last_idle->finish;
+	}
+
+	if (first_idle && !bfq_gt(first_idle->finish, st->vtime))
+		bfq_put_idle_entity(st, first_idle);
+}
+
+struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sched_data = entity->sched_data;
+	unsigned int idx = bfq_class_idx(entity);
+
+	return sched_data->service_tree + idx;
+}
+
+
+struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+				struct bfq_entity *entity)
+{
+	struct bfq_service_tree *new_st = old_st;
+
+	if (entity->prio_changed) {
+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+		unsigned int prev_weight, new_weight;
+		struct bfq_data *bfqd = NULL;
+		struct rb_root *root;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		struct bfq_sched_data *sd;
+		struct bfq_group *bfqg;
+#endif
+
+		if (bfqq)
+			bfqd = bfqq->bfqd;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		else {
+			sd = entity->my_sched_data;
+			bfqg = container_of(sd, struct bfq_group, sched_data);
+			bfqd = (struct bfq_data *)bfqg->bfqd;
+		}
+#endif
+
+		old_st->wsum -= entity->weight;
+
+		if (entity->new_weight != entity->orig_weight) {
+			if (entity->new_weight < BFQ_MIN_WEIGHT ||
+			    entity->new_weight > BFQ_MAX_WEIGHT) {
+				pr_crit("update_weight_prio: new_weight %d\n",
+					entity->new_weight);
+				if (entity->new_weight < BFQ_MIN_WEIGHT)
+					entity->new_weight = BFQ_MIN_WEIGHT;
+				else
+					entity->new_weight = BFQ_MAX_WEIGHT;
+			}
+			entity->orig_weight = entity->new_weight;
+			if (bfqq)
+				bfqq->ioprio =
+				  bfq_weight_to_ioprio(entity->orig_weight);
+		}
+
+		if (bfqq)
+			bfqq->ioprio_class = bfqq->new_ioprio_class;
+		entity->prio_changed = 0;
+
+		/*
+		 * NOTE: here we may be changing the weight too early,
+		 * this will cause unfairness.  The correct approach
+		 * would have required additional complexity to defer
+		 * weight changes to the proper time instants (i.e.,
+		 * when entity->finish <= old_st->vtime).
+		 */
+		new_st = bfq_entity_service_tree(entity);
+
+		prev_weight = entity->weight;
+		new_weight = entity->orig_weight *
+			     (bfqq ? bfqq->wr_coeff : 1);
+		/*
+		 * If the weight of the entity changes, remove the entity
+		 * from its old weight counter (if there is a counter
+		 * associated with the entity), and add it to the counter
+		 * associated with its new weight.
+		 */
+		if (prev_weight != new_weight) {
+			root = bfqq ? &bfqd->queue_weights_tree :
+				      &bfqd->group_weights_tree;
+			bfq_weights_tree_remove(bfqd, entity, root);
+		}
+		entity->weight = new_weight;
+		/*
+		 * Add the entity to its weights tree only if it is
+		 * not associated with a weight-raised queue.
+		 */
+		if (prev_weight != new_weight &&
+		    (bfqq ? bfqq->wr_coeff == 1 : 1))
+			/* If we get here, root has been initialized. */
+			bfq_weights_tree_add(bfqd, entity, root);
+
+		new_st->wsum += entity->weight;
+
+		if (new_st != old_st)
+			entity->start = new_st->vtime;
+	}
+
+	return new_st;
+}
+
+/**
+ * bfq_bfqq_served - update the scheduler status after selection for
+ *                   service.
+ * @bfqq: the queue being served.
+ * @served: bytes to transfer.
+ *
+ * NOTE: this can be optimized, as the timestamps of upper level entities
+ * are synchronized every time a new bfqq is selected for service.  By now,
+ * we keep it to better check consistency.
+ */
+void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	struct bfq_service_tree *st;
+
+	for_each_entity(entity) {
+		st = bfq_entity_service_tree(entity);
+
+		entity->service += served;
+
+		st->vtime += bfq_delta(served, st->wsum);
+		bfq_forget_idle(st);
+	}
+	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
+}
+
+/**
+ * bfq_bfqq_charge_time - charge an amount of service equivalent to the length
+ *			  of the time interval during which bfqq has been in
+ *			  service.
+ * @bfqd: the device
+ * @bfqq: the queue that needs a service update.
+ * @time_ms: the amount of time during which the queue has received service
+ *
+ * If a queue does not consume its budget fast enough, then providing
+ * the queue with service fairness may impair throughput, more or less
+ * severely. For this reason, queues that consume their budget slowly
+ * are provided with time fairness instead of service fairness. This
+ * goal is achieved through the BFQ scheduling engine, even if such an
+ * engine works in the service, and not in the time domain. The trick
+ * is charging these queues with an inflated amount of service, equal
+ * to the amount of service that they would have received during their
+ * service slot if they had been fast, i.e., if their requests had
+ * been dispatched at a rate equal to the estimated peak rate.
+ *
+ * It is worth noting that time fairness can cause important
+ * distortions in terms of bandwidth distribution, on devices with
+ * internal queueing. The reason is that I/O requests dispatched
+ * during the service slot of a queue may be served after that service
+ * slot is finished, and may have a total processing time loosely
+ * correlated with the duration of the service slot. This is
+ * especially true for short service slots.
+ */
+void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  unsigned long time_ms)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	int tot_serv_to_charge = entity->service;
+	unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
+
+	if (time_ms > 0 && time_ms < timeout_ms)
+		tot_serv_to_charge =
+			(bfqd->bfq_max_budget * time_ms) / timeout_ms;
+
+	if (tot_serv_to_charge < entity->service)
+		tot_serv_to_charge = entity->service;
+
+	/* Increase budget to avoid inconsistencies */
+	if (tot_serv_to_charge > entity->budget)
+		entity->budget = tot_serv_to_charge;
+
+	bfq_bfqq_served(bfqq,
+			max_t(int, 0, tot_serv_to_charge - entity->service));
+}
+
+static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
+					struct bfq_service_tree *st,
+					bool backshifted)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	st = __bfq_entity_update_weight_prio(st, entity);
+	bfq_calc_finish(entity, entity->budget);
+
+	/*
+	 * If some queues enjoy backshifting for a while, then their
+	 * (virtual) finish timestamps may happen to become lower and
+	 * lower than the system virtual time.	In particular, if
+	 * these queues often happen to be idle for short time
+	 * periods, and during such time periods other queues with
+	 * higher timestamps happen to be busy, then the backshifted
+	 * timestamps of the former queues can become much lower than
+	 * the system virtual time. In fact, to serve the queues with
+	 * higher timestamps while the ones with lower timestamps are
+	 * idle, the system virtual time may be pushed-up to much
+	 * higher values than the finish timestamps of the idle
+	 * queues. As a consequence, the finish timestamps of all new
+	 * or newly activated queues may end up being much larger than
+	 * those of lucky queues with backshifted timestamps. The
+	 * latter queues may then monopolize the device for a lot of
+	 * time. This would simply break service guarantees.
+	 *
+	 * To reduce this problem, push up a little bit the
+	 * backshifted timestamps of the queue associated with this
+	 * entity (only a queue can happen to have the backshifted
+	 * flag set): just enough to let the finish timestamp of the
+	 * queue be equal to the current value of the system virtual
+	 * time. This may introduce a little unfairness among queues
+	 * with backshifted timestamps, but it does not break
+	 * worst-case fairness guarantees.
+	 *
+	 * As a special case, if bfqq is weight-raised, push up
+	 * timestamps much less, to keep very low the probability that
+	 * this push up causes the backshifted finish timestamps of
+	 * weight-raised queues to become higher than the backshifted
+	 * finish timestamps of non weight-raised queues.
+	 */
+	if (backshifted && bfq_gt(st->vtime, entity->finish)) {
+		unsigned long delta = st->vtime - entity->finish;
+
+		if (bfqq)
+			delta /= bfqq->wr_coeff;
+
+		entity->start += delta;
+		entity->finish += delta;
+	}
+
+	bfq_active_insert(st, entity);
+}
+
+/**
+ * __bfq_activate_entity - handle activation of entity.
+ * @entity: the entity being activated.
+ * @non_blocking_wait_rq: true if entity was waiting for a request
+ *
+ * Called for a 'true' activation, i.e., if entity is not active and
+ * one of its children receives a new request.
+ *
+ * Basically, this function updates the timestamps of entity and
+ * inserts entity into its active tree, ater possible extracting it
+ * from its idle tree.
+ */
+static void __bfq_activate_entity(struct bfq_entity *entity,
+				  bool non_blocking_wait_rq)
+{
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	bool backshifted = false;
+	unsigned long long min_vstart;
+
+	/* See comments on bfq_fqq_update_budg_for_activation */
+	if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
+		backshifted = true;
+		min_vstart = entity->finish;
+	} else
+		min_vstart = st->vtime;
+
+	if (entity->tree == &st->idle) {
+		/*
+		 * Must be on the idle tree, bfq_idle_extract() will
+		 * check for that.
+		 */
+		bfq_idle_extract(st, entity);
+		entity->start = bfq_gt(min_vstart, entity->finish) ?
+			min_vstart : entity->finish;
+	} else {
+		/*
+		 * The finish time of the entity may be invalid, and
+		 * it is in the past for sure, otherwise the queue
+		 * would have been on the idle tree.
+		 */
+		entity->start = min_vstart;
+		st->wsum += entity->weight;
+		/*
+		 * entity is about to be inserted into a service tree,
+		 * and then set in service: get a reference to make
+		 * sure entity does not disappear until it is no
+		 * longer in service or scheduled for service.
+		 */
+		bfq_get_entity(entity);
+
+		entity->on_st = true;
+	}
+
+	bfq_update_fin_time_enqueue(entity, st, backshifted);
+}
+
+/**
+ * __bfq_requeue_entity - handle requeueing or repositioning of an entity.
+ * @entity: the entity being requeued or repositioned.
+ *
+ * Requeueing is needed if this entity stops being served, which
+ * happens if a leaf descendant entity has expired. On the other hand,
+ * repositioning is needed if the next_inservice_entity for the child
+ * entity has changed. See the comments inside the function for
+ * details.
+ *
+ * Basically, this function: 1) removes entity from its active tree if
+ * present there, 2) updates the timestamps of entity and 3) inserts
+ * entity back into its active tree (in the new, right position for
+ * the new values of the timestamps).
+ */
+static void __bfq_requeue_entity(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+	if (entity == sd->in_service_entity) {
+		/*
+		 * We are requeueing the current in-service entity,
+		 * which may have to be done for one of the following
+		 * reasons:
+		 * - entity represents the in-service queue, and the
+		 *   in-service queue is being requeued after an
+		 *   expiration;
+		 * - entity represents a group, and its budget has
+		 *   changed because one of its child entities has
+		 *   just been either activated or requeued for some
+		 *   reason; the timestamps of the entity need then to
+		 *   be updated, and the entity needs to be enqueued
+		 *   or repositioned accordingly.
+		 *
+		 * In particular, before requeueing, the start time of
+		 * the entity must be moved forward to account for the
+		 * service that the entity has received while in
+		 * service. This is done by the next instructions. The
+		 * finish time will then be updated according to this
+		 * new value of the start time, and to the budget of
+		 * the entity.
+		 */
+		bfq_calc_finish(entity, entity->service);
+		entity->start = entity->finish;
+		/*
+		 * In addition, if the entity had more than one child
+		 * when set in service, then was not extracted from
+		 * the active tree. This implies that the position of
+		 * the entity in the active tree may need to be
+		 * changed now, because we have just updated the start
+		 * time of the entity, and we will update its finish
+		 * time in a moment (the requeueing is then, more
+		 * precisely, a repositioning in this case). To
+		 * implement this repositioning, we: 1) dequeue the
+		 * entity here, 2) update the finish time and
+		 * requeue the entity according to the new
+		 * timestamps below.
+		 */
+		if (entity->tree)
+			bfq_active_extract(st, entity);
+	} else { /* The entity is already active, and not in service */
+		/*
+		 * In this case, this function gets called only if the
+		 * next_in_service entity below this entity has
+		 * changed, and this change has caused the budget of
+		 * this entity to change, which, finally implies that
+		 * the finish time of this entity must be
+		 * updated. Such an update may cause the scheduling,
+		 * i.e., the position in the active tree, of this
+		 * entity to change. We handle this change by: 1)
+		 * dequeueing the entity here, 2) updating the finish
+		 * time and requeueing the entity according to the new
+		 * timestamps below. This is the same approach as the
+		 * non-extracted-entity sub-case above.
+		 */
+		bfq_active_extract(st, entity);
+	}
+
+	bfq_update_fin_time_enqueue(entity, st, false);
+}
+
+static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
+					  struct bfq_sched_data *sd,
+					  bool non_blocking_wait_rq)
+{
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+	if (sd->in_service_entity == entity || entity->tree == &st->active)
+		 /*
+		  * in service or already queued on the active tree,
+		  * requeue or reposition
+		  */
+		__bfq_requeue_entity(entity);
+	else
+		/*
+		 * Not in service and not queued on its active tree:
+		 * the activity is idle and this is a true activation.
+		 */
+		__bfq_activate_entity(entity, non_blocking_wait_rq);
+}
+
+
+/**
+ * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
+ *			 and activate, requeue or reposition all ancestors
+ *			 for which such an update becomes necessary.
+ * @entity: the entity to activate.
+ * @non_blocking_wait_rq: true if this entity was waiting for a request
+ * @requeue: true if this is a requeue, which implies that bfqq is
+ *	     being expired; thus ALL its ancestors stop being served and must
+ *	     therefore be requeued
+ */
+static void bfq_activate_requeue_entity(struct bfq_entity *entity,
+					bool non_blocking_wait_rq,
+					bool requeue)
+{
+	struct bfq_sched_data *sd;
+
+	for_each_entity(entity) {
+		sd = entity->sched_data;
+		__bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
+
+		if (!bfq_update_next_in_service(sd, entity) && !requeue)
+			break;
+	}
+}
+
+/**
+ * __bfq_deactivate_entity - deactivate an entity from its service tree.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: if false, the entity will not be put into the
+ *			idle tree.
+ *
+ * Deactivates an entity, independently from its previous state.  Must
+ * be invoked only if entity is on a service tree. Extracts the entity
+ * from that tree, and if necessary and allowed, puts it on the idle
+ * tree.
+ */
+bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	int is_in_service = entity == sd->in_service_entity;
+
+	if (!entity->on_st) /* entity never activated, or already inactive */
+		return false;
+
+	if (is_in_service)
+		bfq_calc_finish(entity, entity->service);
+
+	if (entity->tree == &st->active)
+		bfq_active_extract(st, entity);
+	else if (!is_in_service && entity->tree == &st->idle)
+		bfq_idle_extract(st, entity);
+
+	if (!ins_into_idle_tree || !bfq_gt(entity->finish, st->vtime))
+		bfq_forget_entity(st, entity, is_in_service);
+	else
+		bfq_idle_insert(st, entity);
+
+	return true;
+}
+
+/**
+ * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: true if the entity can be put on the idle tree
+ */
+static void bfq_deactivate_entity(struct bfq_entity *entity,
+				  bool ins_into_idle_tree,
+				  bool expiration)
+{
+	struct bfq_sched_data *sd;
+	struct bfq_entity *parent = NULL;
+
+	for_each_entity_safe(entity, parent) {
+		sd = entity->sched_data;
+
+		if (!__bfq_deactivate_entity(entity, ins_into_idle_tree)) {
+			/*
+			 * entity is not in any tree any more, so
+			 * this deactivation is a no-op, and there is
+			 * nothing to change for upper-level entities
+			 * (in case of expiration, this can never
+			 * happen).
+			 */
+			return;
+		}
+
+		if (sd->next_in_service == entity)
+			/*
+			 * entity was the next_in_service entity,
+			 * then, since entity has just been
+			 * deactivated, a new one must be found.
+			 */
+			bfq_update_next_in_service(sd, NULL);
+
+		if (sd->next_in_service)
+			/*
+			 * The parent entity is still backlogged,
+			 * because next_in_service is not NULL. So, no
+			 * further upwards deactivation must be
+			 * performed.  Yet, next_in_service has
+			 * changed.  Then the schedule does need to be
+			 * updated upwards.
+			 */
+			break;
+
+		/*
+		 * If we get here, then the parent is no more
+		 * backlogged and we need to propagate the
+		 * deactivation upwards. Thus let the loop go on.
+		 */
+
+		/*
+		 * Also let parent be queued into the idle tree on
+		 * deactivation, to preserve service guarantees, and
+		 * assuming that who invoked this function does not
+		 * need parent entities too to be removed completely.
+		 */
+		ins_into_idle_tree = true;
+	}
+
+	/*
+	 * If the deactivation loop is fully executed, then there are
+	 * no more entities to touch and next loop is not executed at
+	 * all. Otherwise, requeue remaining entities if they are
+	 * about to stop receiving service, or reposition them if this
+	 * is not the case.
+	 */
+	entity = parent;
+	for_each_entity(entity) {
+		/*
+		 * Invoke __bfq_requeue_entity on entity, even if
+		 * already active, to requeue/reposition it in the
+		 * active tree (because sd->next_in_service has
+		 * changed)
+		 */
+		__bfq_requeue_entity(entity);
+
+		sd = entity->sched_data;
+		if (!bfq_update_next_in_service(sd, entity) &&
+		    !expiration)
+			/*
+			 * next_in_service unchanged or not causing
+			 * any change in entity->parent->sd, and no
+			 * requeueing needed for expiration: stop
+			 * here.
+			 */
+			break;
+	}
+}
+
+/**
+ * bfq_calc_vtime_jump - compute the value to which the vtime should jump,
+ *                       if needed, to have at least one entity eligible.
+ * @st: the service tree to act upon.
+ *
+ * Assumes that st is not empty.
+ */
+static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
+{
+	struct bfq_entity *root_entity = bfq_root_active_entity(&st->active);
+
+	if (bfq_gt(root_entity->min_start, st->vtime))
+		return root_entity->min_start;
+
+	return st->vtime;
+}
+
+static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value)
+{
+	if (new_value > st->vtime) {
+		st->vtime = new_value;
+		bfq_forget_idle(st);
+	}
+}
+
+/**
+ * bfq_first_active_entity - find the eligible entity with
+ *                           the smallest finish time
+ * @st: the service tree to select from.
+ * @vtime: the system virtual to use as a reference for eligibility
+ *
+ * This function searches the first schedulable entity, starting from the
+ * root of the tree and going on the left every time on this side there is
+ * a subtree with at least one eligible (start >= vtime) entity. The path on
+ * the right is followed only if a) the left subtree contains no eligible
+ * entities and b) no eligible entity has been found yet.
+ */
+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
+						  u64 vtime)
+{
+	struct bfq_entity *entry, *first = NULL;
+	struct rb_node *node = st->active.rb_node;
+
+	while (node) {
+		entry = rb_entry(node, struct bfq_entity, rb_node);
+left:
+		if (!bfq_gt(entry->start, vtime))
+			first = entry;
+
+		if (node->rb_left) {
+			entry = rb_entry(node->rb_left,
+					 struct bfq_entity, rb_node);
+			if (!bfq_gt(entry->min_start, vtime)) {
+				node = node->rb_left;
+				goto left;
+			}
+		}
+		if (first)
+			break;
+		node = node->rb_right;
+	}
+
+	return first;
+}
+
+/**
+ * __bfq_lookup_next_entity - return the first eligible entity in @st.
+ * @st: the service tree.
+ *
+ * If there is no in-service entity for the sched_data st belongs to,
+ * then return the entity that will be set in service if:
+ * 1) the parent entity this st belongs to is set in service;
+ * 2) no entity belonging to such parent entity undergoes a state change
+ * that would influence the timestamps of the entity (e.g., becomes idle,
+ * becomes backlogged, changes its budget, ...).
+ *
+ * In this first case, update the virtual time in @st too (see the
+ * comments on this update inside the function).
+ *
+ * In constrast, if there is an in-service entity, then return the
+ * entity that would be set in service if not only the above
+ * conditions, but also the next one held true: the currently
+ * in-service entity, on expiration,
+ * 1) gets a finish time equal to the current one, or
+ * 2) is not eligible any more, or
+ * 3) is idle.
+ */
+static struct bfq_entity *
+__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
+{
+	struct bfq_entity *entity;
+	u64 new_vtime;
+
+	if (RB_EMPTY_ROOT(&st->active))
+		return NULL;
+
+	/*
+	 * Get the value of the system virtual time for which at
+	 * least one entity is eligible.
+	 */
+	new_vtime = bfq_calc_vtime_jump(st);
+
+	/*
+	 * If there is no in-service entity for the sched_data this
+	 * active tree belongs to, then push the system virtual time
+	 * up to the value that guarantees that at least one entity is
+	 * eligible. If, instead, there is an in-service entity, then
+	 * do not make any such update, because there is already an
+	 * eligible entity, namely the in-service one (even if the
+	 * entity is not on st, because it was extracted when set in
+	 * service).
+	 */
+	if (!in_service)
+		bfq_update_vtime(st, new_vtime);
+
+	entity = bfq_first_active_entity(st, new_vtime);
+
+	return entity;
+}
+
+/**
+ * bfq_lookup_next_entity - return the first eligible entity in @sd.
+ * @sd: the sched_data.
+ *
+ * This function is invoked when there has been a change in the trees
+ * for sd, and we need know what is the new next entity after this
+ * change.
+ */
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
+{
+	struct bfq_service_tree *st = sd->service_tree;
+	struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
+	struct bfq_entity *entity = NULL;
+	int class_idx = 0;
+
+	/*
+	 * Choose from idle class, if needed to guarantee a minimum
+	 * bandwidth to this class (and if there is some active entity
+	 * in idle class). This should also mitigate
+	 * priority-inversion problems in case a low priority task is
+	 * holding file system resources.
+	 */
+	if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
+				   BFQ_CL_IDLE_TIMEOUT)) {
+		if (!RB_EMPTY_ROOT(&idle_class_st->active))
+			class_idx = BFQ_IOPRIO_CLASSES - 1;
+		/* About to be served if backlogged, or not yet backlogged */
+		sd->bfq_class_idle_last_service = jiffies;
+	}
+
+	/*
+	 * Find the next entity to serve for the highest-priority
+	 * class, unless the idle class needs to be served.
+	 */
+	for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
+		entity = __bfq_lookup_next_entity(st + class_idx,
+						  sd->in_service_entity);
+
+		if (entity)
+			break;
+	}
+
+	if (!entity)
+		return NULL;
+
+	return entity;
+}
+
+bool next_queue_may_preempt(struct bfq_data *bfqd)
+{
+	struct bfq_sched_data *sd = &bfqd->root_group->sched_data;
+
+	return sd->next_in_service != sd->in_service_entity;
+}
+
+/*
+ * Get next queue for service.
+ */
+struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
+{
+	struct bfq_entity *entity = NULL;
+	struct bfq_sched_data *sd;
+	struct bfq_queue *bfqq;
+
+	if (bfqd->busy_queues == 0)
+		return NULL;
+
+	/*
+	 * Traverse the path from the root to the leaf entity to
+	 * serve. Set in service all the entities visited along the
+	 * way.
+	 */
+	sd = &bfqd->root_group->sched_data;
+	for (; sd ; sd = entity->my_sched_data) {
+		/*
+		 * WARNING. We are about to set the in-service entity
+		 * to sd->next_in_service, i.e., to the (cached) value
+		 * returned by bfq_lookup_next_entity(sd) the last
+		 * time it was invoked, i.e., the last time when the
+		 * service order in sd changed as a consequence of the
+		 * activation or deactivation of an entity. In this
+		 * respect, if we execute bfq_lookup_next_entity(sd)
+		 * in this very moment, it may, although with low
+		 * probability, yield a different entity than that
+		 * pointed to by sd->next_in_service. This rare event
+		 * happens in case there was no CLASS_IDLE entity to
+		 * serve for sd when bfq_lookup_next_entity(sd) was
+		 * invoked for the last time, while there is now one
+		 * such entity.
+		 *
+		 * If the above event happens, then the scheduling of
+		 * such entity in CLASS_IDLE is postponed until the
+		 * service of the sd->next_in_service entity
+		 * finishes. In fact, when the latter is expired,
+		 * bfq_lookup_next_entity(sd) gets called again,
+		 * exactly to update sd->next_in_service.
+		 */
+
+		/* Make next_in_service entity become in_service_entity */
+		entity = sd->next_in_service;
+		sd->in_service_entity = entity;
+
+		/*
+		 * Reset the accumulator of the amount of service that
+		 * the entity is about to receive.
+		 */
+		entity->service = 0;
+
+		/*
+		 * If entity is no longer a candidate for next
+		 * service, then we extract it from its active tree,
+		 * for the following reason. To further boost the
+		 * throughput in some special case, BFQ needs to know
+		 * which is the next candidate entity to serve, while
+		 * there is already an entity in service. In this
+		 * respect, to make it easy to compute/update the next
+		 * candidate entity to serve after the current
+		 * candidate has been set in service, there is a case
+		 * where it is necessary to extract the current
+		 * candidate from its service tree. Such a case is
+		 * when the entity just set in service cannot be also
+		 * a candidate for next service. Details about when
+		 * this conditions holds are reported in the comments
+		 * on the function bfq_no_longer_next_in_service()
+		 * invoked below.
+		 */
+		if (bfq_no_longer_next_in_service(entity))
+			bfq_active_extract(bfq_entity_service_tree(entity),
+					   entity);
+
+		/*
+		 * For the same reason why we may have just extracted
+		 * entity from its active tree, we may need to update
+		 * next_in_service for the sched_data of entity too,
+		 * regardless of whether entity has been extracted.
+		 * In fact, even if entity has not been extracted, a
+		 * descendant entity may get extracted. Such an event
+		 * would cause a change in next_in_service for the
+		 * level of the descendant entity, and thus possibly
+		 * back to upper levels.
+		 *
+		 * We cannot perform the resulting needed update
+		 * before the end of this loop, because, to know which
+		 * is the correct next-to-serve candidate entity for
+		 * each level, we need first to find the leaf entity
+		 * to set in service. In fact, only after we know
+		 * which is the next-to-serve leaf entity, we can
+		 * discover whether the parent entity of the leaf
+		 * entity becomes the next-to-serve, and so on.
+		 */
+
+	}
+
+	bfqq = bfq_entity_to_bfqq(entity);
+
+	/*
+	 * We can finally update all next-to-serve entities along the
+	 * path from the leaf entity just set in service to the root.
+	 */
+	for_each_entity(entity) {
+		struct bfq_sched_data *sd = entity->sched_data;
+
+		if (!bfq_update_next_in_service(sd, NULL))
+			break;
+	}
+
+	return bfqq;
+}
+
+void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+{
+	struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
+	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
+	struct bfq_entity *entity = in_serv_entity;
+
+	bfq_clear_bfqq_wait_request(in_serv_bfqq);
+	hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+	bfqd->in_service_queue = NULL;
+
+	/*
+	 * When this function is called, all in-service entities have
+	 * been properly deactivated or requeued, so we can safely
+	 * execute the final step: reset in_service_entity along the
+	 * path from entity to the root.
+	 */
+	for_each_entity(entity)
+		entity->sched_data->in_service_entity = NULL;
+
+	/*
+	 * in_serv_entity is no longer in service, so, if it is in no
+	 * service tree either, then release the service reference to
+	 * the queue it represents (taken with bfq_get_entity).
+	 */
+	if (!in_serv_entity->on_st)
+		bfq_put_queue(in_serv_bfqq);
+}
+
+void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			 bool ins_into_idle_tree, bool expiration)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_deactivate_entity(entity, ins_into_idle_tree, expiration);
+}
+
+void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
+				    false);
+	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_activate_requeue_entity(entity, false,
+				    bfqq == bfqd->in_service_queue);
+}
+
+/*
+ * Called when the bfqq no longer has requests pending, remove it from
+ * the service tree. As a special case, it can be invoked during an
+ * expiration.
+ */
+void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       bool expiration)
+{
+	bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+	bfq_clear_bfqq_busy(bfqq);
+
+	bfqd->busy_queues--;
+
+	if (!bfqq->dispatched)
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+
+	if (bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues--;
+
+	bfqg_stats_update_dequeue(bfqq_group(bfqq));
+
+	bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
+}
+
+/*
+ * Called when an inactive queue receives a new request.
+ */
+void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+	bfq_activate_bfqq(bfqd, bfqq);
+
+	bfq_mark_bfqq_busy(bfqq);
+	bfqd->busy_queues++;
+
+	if (!bfqq->dispatched)
+		if (bfqq->wr_coeff == 1)
+			bfq_weights_tree_add(bfqd, &bfqq->entity,
+					     &bfqd->queue_weights_tree);
+
+	if (bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues++;
+}
diff --git a/block/bio.c b/block/bio.c
index 5eec5e08417f..f4d207180266 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -30,6 +30,7 @@
 #include <linux/cgroup.h>
 
 #include <trace/events/block.h>
+#include "blk.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -376,10 +377,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	bio_list_init(&punt);
 	bio_list_init(&nopunt);
 
-	while ((bio = bio_list_pop(current->bio_list)))
+	while ((bio = bio_list_pop(&current->bio_list[0])))
 		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[0] = nopunt;
 
-	*current->bio_list = nopunt;
+	bio_list_init(&nopunt);
+	while ((bio = bio_list_pop(&current->bio_list[1])))
+		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[1] = nopunt;
 
 	spin_lock(&bs->rescue_lock);
 	bio_list_merge(&bs->rescue_list, &punt);
@@ -423,7 +428,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  *   RETURNS:
  *   Pointer to new bio on success, NULL on failure.
  */
-struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
+struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
+			     struct bio_set *bs)
 {
 	gfp_t saved_gfp = gfp_mask;
 	unsigned front_pad;
@@ -466,7 +472,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		 * we retry with the original gfp_flags.
 		 */
 
-		if (current->bio_list && !bio_list_empty(current->bio_list))
+		if (current->bio_list &&
+		    (!bio_list_empty(&current->bio_list[0]) ||
+		     !bio_list_empty(&current->bio_list[1])))
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -1818,6 +1826,11 @@ static inline bool bio_remaining_done(struct bio *bio)
  *   bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
  *   way to end I/O on a bio. No one should call bi_end_io() directly on a
  *   bio unless they own it and thus know that it has an end_io function.
+ *
+ *   bio_endio() can be called several times on a bio that has been chained
+ *   using bio_chain().  The ->bi_end_io() function will only be called the
+ *   last time.  At this point the BLK_TA_COMPLETE tracing event will be
+ *   generated if BIO_TRACE_COMPLETION is set.
  **/
 void bio_endio(struct bio *bio)
 {
@@ -1838,6 +1851,13 @@ again:
 		goto again;
 	}
 
+	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
+					 bio, bio->bi_error);
+		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
+	}
+
+	blk_throtl_bio_endio(bio);
 	if (bio->bi_end_io)
 		bio->bi_end_io(bio);
 }
@@ -1876,6 +1896,9 @@ struct bio *bio_split(struct bio *bio, int sectors,
 
 	bio_advance(bio, split->bi_iter.bi_size);
 
+	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
+		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+
 	return split;
 }
 EXPORT_SYMBOL(bio_split);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bbe7ee00bd3d..7c2947128f58 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -772,6 +772,27 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
 
+/* Performs queue bypass and policy enabled checks then looks up blkg. */
+static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
+					  const struct blkcg_policy *pol,
+					  struct request_queue *q)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	lockdep_assert_held(q->queue_lock);
+
+	if (!blkcg_policy_enabled(q, pol))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/*
+	 * This could be the first entry point of blkcg implementation and
+	 * we shouldn't allow anything to go through for a bypassing queue.
+	 */
+	if (unlikely(blk_queue_bypass(q)))
+		return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
+
+	return __blkg_lookup(blkcg, q, true /* update_hint */);
+}
+
 /**
  * blkg_conf_prep - parse and prepare for per-blkg config update
  * @blkcg: target block cgroup
@@ -789,6 +810,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	__acquires(rcu) __acquires(disk->queue->queue_lock)
 {
 	struct gendisk *disk;
+	struct request_queue *q;
 	struct blkcg_gq *blkg;
 	struct module *owner;
 	unsigned int major, minor;
@@ -807,44 +829,95 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
-		owner = disk->fops->owner;
-		put_disk(disk);
-		module_put(owner);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto fail;
 	}
 
-	rcu_read_lock();
-	spin_lock_irq(disk->queue->queue_lock);
+	q = disk->queue;
 
-	if (blkcg_policy_enabled(disk->queue, pol))
-		blkg = blkg_lookup_create(blkcg, disk->queue);
-	else
-		blkg = ERR_PTR(-EOPNOTSUPP);
+	rcu_read_lock();
+	spin_lock_irq(q->queue_lock);
 
+	blkg = blkg_lookup_check(blkcg, pol, q);
 	if (IS_ERR(blkg)) {
 		ret = PTR_ERR(blkg);
+		goto fail_unlock;
+	}
+
+	if (blkg)
+		goto success;
+
+	/*
+	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
+	 * non-root blkgs have access to their parents.
+	 */
+	while (true) {
+		struct blkcg *pos = blkcg;
+		struct blkcg *parent;
+		struct blkcg_gq *new_blkg;
+
+		parent = blkcg_parent(blkcg);
+		while (parent && !__blkg_lookup(parent, q, false)) {
+			pos = parent;
+			parent = blkcg_parent(parent);
+		}
+
+		/* Drop locks to do new blkg allocation with GFP_KERNEL. */
+		spin_unlock_irq(q->queue_lock);
 		rcu_read_unlock();
-		spin_unlock_irq(disk->queue->queue_lock);
-		owner = disk->fops->owner;
-		put_disk(disk);
-		module_put(owner);
-		/*
-		 * If queue was bypassing, we should retry.  Do so after a
-		 * short msleep().  It isn't strictly necessary but queue
-		 * can be bypassing for some time and it's always nice to
-		 * avoid busy looping.
-		 */
-		if (ret == -EBUSY) {
-			msleep(10);
-			ret = restart_syscall();
+
+		new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
+		if (unlikely(!new_blkg)) {
+			ret = -ENOMEM;
+			goto fail;
 		}
-		return ret;
-	}
 
+		rcu_read_lock();
+		spin_lock_irq(q->queue_lock);
+
+		blkg = blkg_lookup_check(pos, pol, q);
+		if (IS_ERR(blkg)) {
+			ret = PTR_ERR(blkg);
+			goto fail_unlock;
+		}
+
+		if (blkg) {
+			blkg_free(new_blkg);
+		} else {
+			blkg = blkg_create(pos, q, new_blkg);
+			if (unlikely(IS_ERR(blkg))) {
+				ret = PTR_ERR(blkg);
+				goto fail_unlock;
+			}
+		}
+
+		if (pos == blkcg)
+			goto success;
+	}
+success:
 	ctx->disk = disk;
 	ctx->blkg = blkg;
 	ctx->body = body;
 	return 0;
+
+fail_unlock:
+	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
+fail:
+	owner = disk->fops->owner;
+	put_disk(disk);
+	module_put(owner);
+	/*
+	 * If queue was bypassing, we should retry.  Do so after a
+	 * short msleep().  It isn't strictly necessary but queue
+	 * can be bypassing for some time and it's always nice to
+	 * avoid busy looping.
+	 */
+	if (ret == -EBUSY) {
+		msleep(10);
+		ret = restart_syscall();
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(blkg_conf_prep);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 1086dac8724c..24886b69690f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -268,10 +268,8 @@ void blk_sync_queue(struct request_queue *q)
 		struct blk_mq_hw_ctx *hctx;
 		int i;
 
-		queue_for_each_hw_ctx(q, hctx, i) {
-			cancel_work_sync(&hctx->run_work);
-			cancel_delayed_work_sync(&hctx->delay_work);
-		}
+		queue_for_each_hw_ctx(q, hctx, i)
+			cancel_delayed_work_sync(&hctx->run_work);
 	} else {
 		cancel_delayed_work_sync(&q->delay_work);
 	}
@@ -500,6 +498,13 @@ void blk_set_queue_dying(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_DYING, q);
 	spin_unlock_irq(q->queue_lock);
 
+	/*
+	 * When queue DYING flag is set, we need to block new req
+	 * entering queue, so we call blk_freeze_queue_start() to
+	 * prevent I/O from crossing blk_queue_enter().
+	 */
+	blk_freeze_queue_start(q);
+
 	if (q->mq_ops)
 		blk_mq_wake_waiters(q);
 	else {
@@ -556,9 +561,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
 	blk_freeze_queue(q);
-	spin_lock_irq(lock);
-	if (!q->mq_ops)
+	if (!q->mq_ops) {
+		spin_lock_irq(lock);
 		__blk_drain_queue(q, true);
+	} else {
+		blk_mq_debugfs_unregister_mq(q);
+		spin_lock_irq(lock);
+	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
@@ -578,8 +587,6 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	put_disk_devt(q->disk_devt);
-
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }
@@ -671,6 +678,15 @@ int blk_queue_enter(struct request_queue *q, bool nowait)
 		if (nowait)
 			return -EBUSY;
 
+		/*
+		 * read pair of barrier in blk_freeze_queue_start(),
+		 * we need to order reading __PERCPU_REF_DEAD flag of
+		 * .q_usage_counter and reading .mq_freeze_depth or
+		 * queue dying flag, otherwise the following wait may
+		 * never return if the two reads are reordered.
+		 */
+		smp_rmb();
+
 		ret = wait_event_interruptible(q->mq_freeze_wq,
 				!atomic_read(&q->mq_freeze_depth) ||
 				blk_queue_dying(q));
@@ -722,6 +738,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q->backing_dev_info)
 		goto fail_split;
 
+	q->stats = blk_alloc_queue_stats();
+	if (!q->stats)
+		goto fail_stats;
+
 	q->backing_dev_info->ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
@@ -778,6 +798,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 fail_ref:
 	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
+	blk_free_queue_stats(q->stats);
+fail_stats:
 	bdi_put(q->backing_dev_info);
 fail_split:
 	bioset_free(q->bio_split);
@@ -891,7 +913,6 @@ out_exit_flush_rq:
 		q->exit_rq_fn(q, q->fq->flush_rq);
 out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
-	wbt_exit(q);
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1130,7 +1151,6 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	blk_rq_set_prio(rq, ioc);
 	rq->cmd_flags = op;
 	rq->rq_flags = rq_flags;
 
@@ -1610,17 +1630,23 @@ out:
 	return ret;
 }
 
-void init_request_from_bio(struct request *req, struct bio *bio)
+void blk_init_request_from_bio(struct request *req, struct bio *bio)
 {
+	struct io_context *ioc = rq_ioc(bio);
+
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
-	req->errors = 0;
 	req->__sector = bio->bi_iter.bi_sector;
 	if (ioprio_valid(bio_prio(bio)))
 		req->ioprio = bio_prio(bio);
+	else if (ioc)
+		req->ioprio = ioc->ioprio;
+	else
+		req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
 	blk_rq_bio_prep(req->q, req, bio);
 }
+EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
@@ -1711,7 +1737,7 @@ get_rq:
 	 * We don't worry about that case for efficiency. It won't happen
 	 * often, and the elevators are able to handle it.
 	 */
-	init_request_from_bio(req, bio);
+	blk_init_request_from_bio(req, bio);
 
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
 		req->cpu = raw_smp_processor_id();
@@ -1938,7 +1964,13 @@ generic_make_request_checks(struct bio *bio)
 	if (!blkcg_bio_issue_check(q, bio))
 		return false;
 
-	trace_block_bio_queue(q, bio);
+	if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+		trace_block_bio_queue(q, bio);
+		/* Now that enqueuing has been traced, we need to trace
+		 * completion as well.
+		 */
+		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+	}
 	return true;
 
 not_supported:
@@ -1975,7 +2007,14 @@ end_io:
  */
 blk_qc_t generic_make_request(struct bio *bio)
 {
-	struct bio_list bio_list_on_stack;
+	/*
+	 * bio_list_on_stack[0] contains bios submitted by the current
+	 * make_request_fn.
+	 * bio_list_on_stack[1] contains bios that were submitted before
+	 * the current make_request_fn, but that haven't been processed
+	 * yet.
+	 */
+	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (!generic_make_request_checks(bio))
@@ -1992,7 +2031,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * should be added at the tail
 	 */
 	if (current->bio_list) {
-		bio_list_add(current->bio_list, bio);
+		bio_list_add(&current->bio_list[0], bio);
 		goto out;
 	}
 
@@ -2011,23 +2050,39 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * bio_list, and call into ->make_request() again.
 	 */
 	BUG_ON(bio->bi_next);
-	bio_list_init(&bio_list_on_stack);
-	current->bio_list = &bio_list_on_stack;
+	bio_list_init(&bio_list_on_stack[0]);
+	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 		if (likely(blk_queue_enter(q, false) == 0)) {
+			struct bio_list lower, same;
+
+			/* Create a fresh bio_list for all subordinate requests */
+			bio_list_on_stack[1] = bio_list_on_stack[0];
+			bio_list_init(&bio_list_on_stack[0]);
 			ret = q->make_request_fn(q, bio);
 
 			blk_queue_exit(q);
 
-			bio = bio_list_pop(current->bio_list);
+			/* sort new bios into those for a lower level
+			 * and those for the same level
+			 */
+			bio_list_init(&lower);
+			bio_list_init(&same);
+			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
+				if (q == bdev_get_queue(bio->bi_bdev))
+					bio_list_add(&same, bio);
+				else
+					bio_list_add(&lower, bio);
+			/* now assemble so we handle the lowest level first */
+			bio_list_merge(&bio_list_on_stack[0], &lower);
+			bio_list_merge(&bio_list_on_stack[0], &same);
+			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
-			struct bio *bio_next = bio_list_pop(current->bio_list);
-
 			bio_io_error(bio);
-			bio = bio_next;
 		}
+		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 
@@ -2457,7 +2512,7 @@ void blk_start_request(struct request *req)
 	blk_dequeue_request(req);
 
 	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
-		blk_stat_set_issue_time(&req->issue_stat);
+		blk_stat_set_issue(&req->issue_stat, blk_rq_sectors(req));
 		req->rq_flags |= RQF_STATS;
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
@@ -2519,22 +2574,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
 	int total_bytes;
 
-	trace_block_rq_complete(req->q, req, nr_bytes);
+	trace_block_rq_complete(req, error, nr_bytes);
 
 	if (!req->bio)
 		return false;
 
-	/*
-	 * For fs requests, rq is just carrier of independent bio's
-	 * and each partial completion should be handled separately.
-	 * Reset per-request error on each partial completion.
-	 *
-	 * TODO: tj: This is too subtle.  It would be better to let
-	 * low level drivers do what they see fit.
-	 */
-	if (!blk_rq_is_passthrough(req))
-		req->errors = 0;
-
 	if (error && !blk_rq_is_passthrough(req) &&
 	    !(req->rq_flags & RQF_QUIET)) {
 		char *error_type;
@@ -2580,6 +2624,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
 
+		/* Completion has already been traced */
+		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 		req_bio_endio(req, bio, bio_bytes, error);
 
 		total_bytes += bio_bytes;
@@ -2678,7 +2724,7 @@ void blk_finish_request(struct request *req, int error)
 	struct request_queue *q = req->q;
 
 	if (req->rq_flags & RQF_STATS)
-		blk_stat_add(&q->rq_stats[rq_data_dir(req)], req);
+		blk_stat_add(req);
 
 	if (req->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, req);
@@ -2755,7 +2801,7 @@ static bool blk_end_bidi_request(struct request *rq, int error,
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-bool __blk_end_bidi_request(struct request *rq, int error,
+static bool __blk_end_bidi_request(struct request *rq, int error,
 				   unsigned int nr_bytes, unsigned int bidi_bytes)
 {
 	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
@@ -2808,43 +2854,6 @@ void blk_end_request_all(struct request *rq, int error)
 EXPORT_SYMBOL(blk_end_request_all);
 
 /**
- * blk_end_request_cur - Helper function to finish the current request chunk.
- * @rq: the request to finish the current chunk for
- * @error: %0 for success, < %0 for error
- *
- * Description:
- *     Complete the current consecutively mapped chunk from @rq.
- *
- * Return:
- *     %false - we are done with this request
- *     %true  - still buffers pending for this request
- */
-bool blk_end_request_cur(struct request *rq, int error)
-{
-	return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
-}
-EXPORT_SYMBOL(blk_end_request_cur);
-
-/**
- * blk_end_request_err - Finish a request till the next failure boundary.
- * @rq: the request to finish till the next failure boundary for
- * @error: must be negative errno
- *
- * Description:
- *     Complete @rq till the next failure boundary.
- *
- * Return:
- *     %false - we are done with this request
- *     %true  - still buffers pending for this request
- */
-bool blk_end_request_err(struct request *rq, int error)
-{
-	WARN_ON(error >= 0);
-	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
-}
-EXPORT_SYMBOL_GPL(blk_end_request_err);
-
-/**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
  * @error:    %0 for success, < %0 for error
@@ -2903,26 +2912,6 @@ bool __blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_end_request_cur);
 
-/**
- * __blk_end_request_err - Finish a request till the next failure boundary.
- * @rq: the request to finish till the next failure boundary for
- * @error: must be negative errno
- *
- * Description:
- *     Complete @rq till the next failure boundary.  Must be called
- *     with queue lock held.
- *
- * Return:
- *     %false - we are done with this request
- *     %true  - still buffers pending for this request
- */
-bool __blk_end_request_err(struct request *rq, int error)
-{
-	WARN_ON(error >= 0);
-	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
-}
-EXPORT_SYMBOL_GPL(__blk_end_request_err);
-
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
@@ -3085,6 +3074,13 @@ int kblockd_schedule_work_on(int cpu, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work_on);
 
+int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
+				unsigned long delay)
+{
+	return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
+
 int kblockd_schedule_delayed_work(struct delayed_work *dwork,
 				  unsigned long delay)
 {
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 8cd0e9bc8dc8..a9451e3b8587 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -69,8 +69,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
-		rq->errors = -ENXIO;
-		__blk_end_request_all(rq, rq->errors);
+		__blk_end_request_all(rq, -ENXIO);
 		spin_unlock_irq(q->queue_lock);
 		return;
 	}
@@ -92,11 +91,10 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
  *    Insert a fully prepared request at the back of the I/O scheduler queue
  *    for execution and wait for completion.
  */
-int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
+void blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		   struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	int err = 0;
 	unsigned long hang_check;
 
 	rq->end_io_data = &wait;
@@ -108,10 +106,5 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
 	else
 		wait_for_completion_io(&wait);
-
-	if (rq->errors)
-		err = -EIO;
-
-	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 0d5a9c1da1fc..c4e0880b54bb 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -447,7 +447,7 @@ void blk_insert_flush(struct request *rq)
 		if (q->mq_ops)
 			blk_mq_end_request(rq, 0);
 		else
-			__blk_end_bidi_request(rq, 0, 0, 0);
+			__blk_end_request(rq, 0, 0);
 		return;
 	}
 
@@ -497,8 +497,7 @@ void blk_insert_flush(struct request *rq)
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to. If WAIT flag is not passed then caller may check only what
- *    request was pushed in some internal queue for later handling.
+ *    wish to.
  */
 int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 		sector_t *error_sector)
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 9f0ff5ba4f84..0f891a9aff4d 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -389,7 +389,7 @@ static int blk_integrity_nop_fn(struct blk_integrity_iter *iter)
 	return 0;
 }
 
-static struct blk_integrity_profile nop_profile = {
+static const struct blk_integrity_profile nop_profile = {
 	.name = "nop",
 	.generate_fn = blk_integrity_nop_fn,
 	.verify_fn = blk_integrity_nop_fn,
@@ -412,12 +412,13 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 
 	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
 		template->flags;
-	bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
+	bi->interval_exp = template->interval_exp ? :
+		ilog2(queue_logical_block_size(disk->queue));
 	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
 }
 EXPORT_SYMBOL(blk_integrity_register);
 
@@ -430,26 +431,11 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 
-void blk_integrity_revalidate(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!(disk->flags & GENHD_FL_UP))
-		return;
-
-	if (bi->profile)
-		disk->queue->backing_dev_info->capabilities |=
-			BDI_CAP_STABLE_WRITES;
-	else
-		disk->queue->backing_dev_info->capabilities &=
-			~BDI_CAP_STABLE_WRITES;
-}
-
 void blk_integrity_add(struct gendisk *disk)
 {
 	if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
diff --git a/block/blk-lib.c b/block/blk-lib.c
index ed1e78e24db0..e8caecd71688 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -37,17 +37,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -ENXIO;
 
 	if (flags & BLKDEV_DISCARD_SECURE) {
-		if (flags & BLKDEV_DISCARD_ZERO)
-			return -EOPNOTSUPP;
 		if (!blk_queue_secure_erase(q))
 			return -EOPNOTSUPP;
 		op = REQ_OP_SECURE_ERASE;
 	} else {
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
-		if ((flags & BLKDEV_DISCARD_ZERO) &&
-		    !q->limits.discard_zeroes_data)
-			return -EOPNOTSUPP;
 		op = REQ_OP_DISCARD;
 	}
 
@@ -109,7 +104,7 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
  * @sector:	start sector
  * @nr_sects:	number of sectors to discard
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_IFL_* flags to control behaviour
+ * @flags:	BLKDEV_DISCARD_* flags to control behaviour
  *
  * Description:
  *    Issue a discard request for the sectors in question.
@@ -126,7 +121,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			&bio);
 	if (!ret && bio) {
 		ret = submit_bio_wait(bio);
-		if (ret == -EOPNOTSUPP && !(flags & BLKDEV_DISCARD_ZERO))
+		if (ret == -EOPNOTSUPP)
 			ret = 0;
 		bio_put(bio);
 	}
@@ -226,20 +221,9 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
 
-/**
- * __blkdev_issue_write_zeroes - generate number of bios with WRITE ZEROES
- * @bdev:	blockdev to issue
- * @sector:	start sector
- * @nr_sects:	number of sectors to write
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @biop:	pointer to anchor bio
- *
- * Description:
- *  Generate and issue number of bios(REQ_OP_WRITE_ZEROES) with zerofiled pages.
- */
 static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
-		struct bio **biop)
+		struct bio **biop, unsigned flags)
 {
 	struct bio *bio = *biop;
 	unsigned int max_write_zeroes_sectors;
@@ -258,7 +242,9 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		bio = next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
-		bio_set_op_attrs(bio, REQ_OP_WRITE_ZEROES, 0);
+		bio->bi_opf = REQ_OP_WRITE_ZEROES;
+		if (flags & BLKDEV_ZERO_NOUNMAP)
+			bio->bi_opf |= REQ_NOUNMAP;
 
 		if (nr_sects > max_write_zeroes_sectors) {
 			bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
@@ -282,14 +268,27 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
  * @biop:	pointer to anchor bio
- * @discard:	discard flag
+ * @flags:	controls detailed behavior
  *
  * Description:
- *  Generate and issue number of bios with zerofiled pages.
+ *  Zero-fill a block range, either using hardware offload or by explicitly
+ *  writing zeroes to the device.
+ *
+ *  Note that this function may fail with -EOPNOTSUPP if the driver signals
+ *  zeroing offload support, but the device fails to process the command (for
+ *  some devices there is no non-destructive way to verify whether this
+ *  operation is actually supported).  In this case the caller should call
+ *  retry the call to blkdev_issue_zeroout() and the fallback path will be used.
+ *
+ *  If a device is using logical block provisioning, the underlying space will
+ *  not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
+ *
+ *  If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return
+ *  -EOPNOTSUPP if no explicit hardware offload for zeroing is provided.
  */
 int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
-		bool discard)
+		unsigned flags)
 {
 	int ret;
 	int bi_size = 0;
@@ -302,8 +301,8 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		return -EINVAL;
 
 	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
-			biop);
-	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
+			biop, flags);
+	if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
 		goto out;
 
 	ret = 0;
@@ -337,40 +336,23 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout);
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @discard:	whether to discard the block range
+ * @flags:	controls detailed behavior
  *
  * Description:
- *  Zero-fill a block range.  If the discard flag is set and the block
- *  device guarantees that subsequent READ operations to the block range
- *  in question will return zeroes, the blocks will be discarded. Should
- *  the discard request fail, if the discard flag is not set, or if
- *  discard_zeroes_data is not supported, this function will resort to
- *  zeroing the blocks manually, thus provisioning (allocating,
- *  anchoring) them. If the block device supports WRITE ZEROES or WRITE SAME
- *  command(s), blkdev_issue_zeroout() will use it to optimize the process of
- *  clearing the block range. Otherwise the zeroing will be performed
- *  using regular WRITE calls.
+ *  Zero-fill a block range, either using hardware offload or by explicitly
+ *  writing zeroes to the device.  See __blkdev_issue_zeroout() for the
+ *  valid values for %flags.
  */
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
+		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
 {
 	int ret;
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 
-	if (discard) {
-		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
-				BLKDEV_DISCARD_ZERO))
-			return 0;
-	}
-
-	if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-			ZERO_PAGE(0)))
-		return 0;
-
 	blk_start_plug(&plug);
 	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
-			&bio, discard);
+			&bio, flags);
 	if (ret == 0 && bio) {
 		ret = submit_bio_wait(bio);
 		bio_put(bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 2afa262425d1..3990ae406341 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -54,6 +54,20 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 	return bio_split(bio, split_sectors, GFP_NOIO, bs);
 }
 
+static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
+		struct bio *bio, struct bio_set *bs, unsigned *nsegs)
+{
+	*nsegs = 1;
+
+	if (!q->limits.max_write_zeroes_sectors)
+		return NULL;
+
+	if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
+		return NULL;
+
+	return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+}
+
 static struct bio *blk_bio_write_same_split(struct request_queue *q,
 					    struct bio *bio,
 					    struct bio_set *bs,
@@ -200,8 +214,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
 		break;
 	case REQ_OP_WRITE_ZEROES:
-		split = NULL;
-		nsegs = (*bio)->bi_phys_segments;
+		split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs);
 		break;
 	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index f6d917977b33..bcd2a7d4a3a5 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -43,11 +43,157 @@ static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
+static int blk_flags_show(struct seq_file *m, const unsigned long flags,
+			  const char *const *flag_name, int flag_name_count)
+{
+	bool sep = false;
+	int i;
+
+	for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) {
+		if (!(flags & BIT(i)))
+			continue;
+		if (sep)
+			seq_puts(m, " ");
+		sep = true;
+		if (i < flag_name_count && flag_name[i])
+			seq_puts(m, flag_name[i]);
+		else
+			seq_printf(m, "%d", i);
+	}
+	return 0;
+}
+
+static const char *const blk_queue_flag_name[] = {
+	[QUEUE_FLAG_QUEUED]	 = "QUEUED",
+	[QUEUE_FLAG_STOPPED]	 = "STOPPED",
+	[QUEUE_FLAG_SYNCFULL]	 = "SYNCFULL",
+	[QUEUE_FLAG_ASYNCFULL]	 = "ASYNCFULL",
+	[QUEUE_FLAG_DYING]	 = "DYING",
+	[QUEUE_FLAG_BYPASS]	 = "BYPASS",
+	[QUEUE_FLAG_BIDI]	 = "BIDI",
+	[QUEUE_FLAG_NOMERGES]	 = "NOMERGES",
+	[QUEUE_FLAG_SAME_COMP]	 = "SAME_COMP",
+	[QUEUE_FLAG_FAIL_IO]	 = "FAIL_IO",
+	[QUEUE_FLAG_STACKABLE]	 = "STACKABLE",
+	[QUEUE_FLAG_NONROT]	 = "NONROT",
+	[QUEUE_FLAG_IO_STAT]	 = "IO_STAT",
+	[QUEUE_FLAG_DISCARD]	 = "DISCARD",
+	[QUEUE_FLAG_NOXMERGES]	 = "NOXMERGES",
+	[QUEUE_FLAG_ADD_RANDOM]	 = "ADD_RANDOM",
+	[QUEUE_FLAG_SECERASE]	 = "SECERASE",
+	[QUEUE_FLAG_SAME_FORCE]	 = "SAME_FORCE",
+	[QUEUE_FLAG_DEAD]	 = "DEAD",
+	[QUEUE_FLAG_INIT_DONE]	 = "INIT_DONE",
+	[QUEUE_FLAG_NO_SG_MERGE] = "NO_SG_MERGE",
+	[QUEUE_FLAG_POLL]	 = "POLL",
+	[QUEUE_FLAG_WC]		 = "WC",
+	[QUEUE_FLAG_FUA]	 = "FUA",
+	[QUEUE_FLAG_FLUSH_NQ]	 = "FLUSH_NQ",
+	[QUEUE_FLAG_DAX]	 = "DAX",
+	[QUEUE_FLAG_STATS]	 = "STATS",
+	[QUEUE_FLAG_POLL_STATS]	 = "POLL_STATS",
+	[QUEUE_FLAG_REGISTERED]	 = "REGISTERED",
+};
+
+static int blk_queue_flags_show(struct seq_file *m, void *v)
+{
+	struct request_queue *q = m->private;
+
+	blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
+		       ARRAY_SIZE(blk_queue_flag_name));
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static ssize_t blk_queue_flags_store(struct file *file, const char __user *ubuf,
+				     size_t len, loff_t *offp)
+{
+	struct request_queue *q = file_inode(file)->i_private;
+	char op[16] = { }, *s;
+
+	len = min(len, sizeof(op) - 1);
+	if (copy_from_user(op, ubuf, len))
+		return -EFAULT;
+	s = op;
+	strsep(&s, " \t\n"); /* strip trailing whitespace */
+	if (strcmp(op, "run") == 0) {
+		blk_mq_run_hw_queues(q, true);
+	} else if (strcmp(op, "start") == 0) {
+		blk_mq_start_stopped_hw_queues(q, true);
+	} else {
+		pr_err("%s: unsupported operation %s. Use either 'run' or 'start'\n",
+		       __func__, op);
+		return -EINVAL;
+	}
+	return len;
+}
+
+static int blk_queue_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, blk_queue_flags_show, inode->i_private);
+}
+
+static const struct file_operations blk_queue_flags_fops = {
+	.open		= blk_queue_flags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= blk_queue_flags_store,
+};
+
+static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
+{
+	if (stat->nr_samples) {
+		seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
+			   stat->nr_samples, stat->mean, stat->min, stat->max);
+	} else {
+		seq_puts(m, "samples=0");
+	}
+}
+
+static int queue_poll_stat_show(struct seq_file *m, void *v)
+{
+	struct request_queue *q = m->private;
+	int bucket;
+
+	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS/2; bucket++) {
+		seq_printf(m, "read  (%d Bytes): ", 1 << (9+bucket));
+		print_stat(m, &q->poll_stat[2*bucket]);
+		seq_puts(m, "\n");
+
+		seq_printf(m, "write (%d Bytes): ",  1 << (9+bucket));
+		print_stat(m, &q->poll_stat[2*bucket+1]);
+		seq_puts(m, "\n");
+	}
+	return 0;
+}
+
+static int queue_poll_stat_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, queue_poll_stat_show, inode->i_private);
+}
+
+static const struct file_operations queue_poll_stat_fops = {
+	.open		= queue_poll_stat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const char *const hctx_state_name[] = {
+	[BLK_MQ_S_STOPPED]	 = "STOPPED",
+	[BLK_MQ_S_TAG_ACTIVE]	 = "TAG_ACTIVE",
+	[BLK_MQ_S_SCHED_RESTART] = "SCHED_RESTART",
+	[BLK_MQ_S_TAG_WAITING]	 = "TAG_WAITING",
+
+};
 static int hctx_state_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 
-	seq_printf(m, "0x%lx\n", hctx->state);
+	blk_flags_show(m, hctx->state, hctx_state_name,
+		       ARRAY_SIZE(hctx_state_name));
+	seq_puts(m, "\n");
 	return 0;
 }
 
@@ -63,11 +209,35 @@ static const struct file_operations hctx_state_fops = {
 	.release	= single_release,
 };
 
+static const char *const alloc_policy_name[] = {
+	[BLK_TAG_ALLOC_FIFO]	= "fifo",
+	[BLK_TAG_ALLOC_RR]	= "rr",
+};
+
+static const char *const hctx_flag_name[] = {
+	[ilog2(BLK_MQ_F_SHOULD_MERGE)]	= "SHOULD_MERGE",
+	[ilog2(BLK_MQ_F_TAG_SHARED)]	= "TAG_SHARED",
+	[ilog2(BLK_MQ_F_SG_MERGE)]	= "SG_MERGE",
+	[ilog2(BLK_MQ_F_BLOCKING)]	= "BLOCKING",
+	[ilog2(BLK_MQ_F_NO_SCHED)]	= "NO_SCHED",
+};
+
 static int hctx_flags_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
-
-	seq_printf(m, "0x%lx\n", hctx->flags);
+	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
+
+	seq_puts(m, "alloc_policy=");
+	if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
+	    alloc_policy_name[alloc_policy])
+		seq_puts(m, alloc_policy_name[alloc_policy]);
+	else
+		seq_printf(m, "%d", alloc_policy);
+	seq_puts(m, " ");
+	blk_flags_show(m,
+		       hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy),
+		       hctx_flag_name, ARRAY_SIZE(hctx_flag_name));
+	seq_puts(m, "\n");
 	return 0;
 }
 
@@ -83,13 +253,83 @@ static const struct file_operations hctx_flags_fops = {
 	.release	= single_release,
 };
 
+static const char *const op_name[] = {
+	[REQ_OP_READ]		= "READ",
+	[REQ_OP_WRITE]		= "WRITE",
+	[REQ_OP_FLUSH]		= "FLUSH",
+	[REQ_OP_DISCARD]	= "DISCARD",
+	[REQ_OP_ZONE_REPORT]	= "ZONE_REPORT",
+	[REQ_OP_SECURE_ERASE]	= "SECURE_ERASE",
+	[REQ_OP_ZONE_RESET]	= "ZONE_RESET",
+	[REQ_OP_WRITE_SAME]	= "WRITE_SAME",
+	[REQ_OP_WRITE_ZEROES]	= "WRITE_ZEROES",
+	[REQ_OP_SCSI_IN]	= "SCSI_IN",
+	[REQ_OP_SCSI_OUT]	= "SCSI_OUT",
+	[REQ_OP_DRV_IN]		= "DRV_IN",
+	[REQ_OP_DRV_OUT]	= "DRV_OUT",
+};
+
+static const char *const cmd_flag_name[] = {
+	[__REQ_FAILFAST_DEV]		= "FAILFAST_DEV",
+	[__REQ_FAILFAST_TRANSPORT]	= "FAILFAST_TRANSPORT",
+	[__REQ_FAILFAST_DRIVER]		= "FAILFAST_DRIVER",
+	[__REQ_SYNC]			= "SYNC",
+	[__REQ_META]			= "META",
+	[__REQ_PRIO]			= "PRIO",
+	[__REQ_NOMERGE]			= "NOMERGE",
+	[__REQ_IDLE]			= "IDLE",
+	[__REQ_INTEGRITY]		= "INTEGRITY",
+	[__REQ_FUA]			= "FUA",
+	[__REQ_PREFLUSH]		= "PREFLUSH",
+	[__REQ_RAHEAD]			= "RAHEAD",
+	[__REQ_BACKGROUND]		= "BACKGROUND",
+	[__REQ_NR_BITS]			= "NR_BITS",
+};
+
+static const char *const rqf_name[] = {
+	[ilog2((__force u32)RQF_SORTED)]		= "SORTED",
+	[ilog2((__force u32)RQF_STARTED)]		= "STARTED",
+	[ilog2((__force u32)RQF_QUEUED)]		= "QUEUED",
+	[ilog2((__force u32)RQF_SOFTBARRIER)]		= "SOFTBARRIER",
+	[ilog2((__force u32)RQF_FLUSH_SEQ)]		= "FLUSH_SEQ",
+	[ilog2((__force u32)RQF_MIXED_MERGE)]		= "MIXED_MERGE",
+	[ilog2((__force u32)RQF_MQ_INFLIGHT)]		= "MQ_INFLIGHT",
+	[ilog2((__force u32)RQF_DONTPREP)]		= "DONTPREP",
+	[ilog2((__force u32)RQF_PREEMPT)]		= "PREEMPT",
+	[ilog2((__force u32)RQF_COPY_USER)]		= "COPY_USER",
+	[ilog2((__force u32)RQF_FAILED)]		= "FAILED",
+	[ilog2((__force u32)RQF_QUIET)]			= "QUIET",
+	[ilog2((__force u32)RQF_ELVPRIV)]		= "ELVPRIV",
+	[ilog2((__force u32)RQF_IO_STAT)]		= "IO_STAT",
+	[ilog2((__force u32)RQF_ALLOCED)]		= "ALLOCED",
+	[ilog2((__force u32)RQF_PM)]			= "PM",
+	[ilog2((__force u32)RQF_HASHED)]		= "HASHED",
+	[ilog2((__force u32)RQF_STATS)]			= "STATS",
+	[ilog2((__force u32)RQF_SPECIAL_PAYLOAD)]	= "SPECIAL_PAYLOAD",
+};
+
 static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 {
 	struct request *rq = list_entry_rq(v);
-
-	seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
-		   rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags,
-		   rq->tag, rq->internal_tag);
+	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
+	const unsigned int op = rq->cmd_flags & REQ_OP_MASK;
+
+	seq_printf(m, "%p {.op=", rq);
+	if (op < ARRAY_SIZE(op_name) && op_name[op])
+		seq_printf(m, "%s", op_name[op]);
+	else
+		seq_printf(m, "%d", op);
+	seq_puts(m, ", .cmd_flags=");
+	blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name,
+		       ARRAY_SIZE(cmd_flag_name));
+	seq_puts(m, ", .rq_flags=");
+	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
+		       ARRAY_SIZE(rqf_name));
+	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
+		   rq->internal_tag);
+	if (mq_ops->show_rq)
+		mq_ops->show_rq(m, rq);
+	seq_puts(m, "}\n");
 	return 0;
 }
 
@@ -322,60 +562,6 @@ static const struct file_operations hctx_io_poll_fops = {
 	.release	= single_release,
 };
 
-static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
-{
-	seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
-		   stat->nr_samples, stat->mean, stat->min, stat->max);
-}
-
-static int hctx_stats_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
-	struct blk_rq_stat stat[2];
-
-	blk_stat_init(&stat[BLK_STAT_READ]);
-	blk_stat_init(&stat[BLK_STAT_WRITE]);
-
-	blk_hctx_stat_get(hctx, stat);
-
-	seq_puts(m, "read: ");
-	print_stat(m, &stat[BLK_STAT_READ]);
-	seq_puts(m, "\n");
-
-	seq_puts(m, "write: ");
-	print_stat(m, &stat[BLK_STAT_WRITE]);
-	seq_puts(m, "\n");
-	return 0;
-}
-
-static int hctx_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_stats_show, inode->i_private);
-}
-
-static ssize_t hctx_stats_write(struct file *file, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	struct seq_file *m = file->private_data;
-	struct blk_mq_hw_ctx *hctx = m->private;
-	struct blk_mq_ctx *ctx;
-	int i;
-
-	hctx_for_each_ctx(hctx, ctx, i) {
-		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
-		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
-	}
-	return count;
-}
-
-static const struct file_operations hctx_stats_fops = {
-	.open		= hctx_stats_open,
-	.read		= seq_read,
-	.write		= hctx_stats_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int hctx_dispatched_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
@@ -636,6 +822,12 @@ static const struct file_operations ctx_completed_fops = {
 	.release	= single_release,
 };
 
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
+	{"poll_stat", 0400, &queue_poll_stat_fops},
+	{"state", 0600, &blk_queue_flags_fops},
+	{},
+};
+
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"state", 0400, &hctx_state_fops},
 	{"flags", 0400, &hctx_flags_fops},
@@ -646,7 +838,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"sched_tags", 0400, &hctx_sched_tags_fops},
 	{"sched_tags_bitmap", 0400, &hctx_sched_tags_bitmap_fops},
 	{"io_poll", 0600, &hctx_io_poll_fops},
-	{"stats", 0600, &hctx_stats_fops},
 	{"dispatched", 0600, &hctx_dispatched_fops},
 	{"queued", 0600, &hctx_queued_fops},
 	{"run", 0600, &hctx_run_fops},
@@ -662,16 +853,17 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
 	{},
 };
 
-int blk_mq_debugfs_register(struct request_queue *q, const char *name)
+int blk_mq_debugfs_register(struct request_queue *q)
 {
 	if (!blk_debugfs_root)
 		return -ENOENT;
 
-	q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
+	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
+					    blk_debugfs_root);
 	if (!q->debugfs_dir)
 		goto err;
 
-	if (blk_mq_debugfs_register_hctxs(q))
+	if (blk_mq_debugfs_register_mq(q))
 		goto err;
 
 	return 0;
@@ -741,7 +933,7 @@ static int blk_mq_debugfs_register_hctx(struct request_queue *q,
 	return 0;
 }
 
-int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+int blk_mq_debugfs_register_mq(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
@@ -753,6 +945,9 @@ int blk_mq_debugfs_register_hctxs(struct request_queue *q)
 	if (!q->mq_debugfs_dir)
 		goto err;
 
+	if (!debugfs_create_files(q->mq_debugfs_dir, q, blk_mq_debugfs_queue_attrs))
+		goto err;
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_debugfs_register_hctx(q, hctx))
 			goto err;
@@ -761,11 +956,11 @@ int blk_mq_debugfs_register_hctxs(struct request_queue *q)
 	return 0;
 
 err:
-	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_debugfs_unregister_mq(q);
 	return -ENOMEM;
 }
 
-void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+void blk_mq_debugfs_unregister_mq(struct request_queue *q)
 {
 	debugfs_remove_recursive(q->mq_debugfs_dir);
 	q->mq_debugfs_dir = NULL;
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index 966c2169762e..0c3354cf3552 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -23,7 +23,7 @@
  * @pdev:	PCI device associated with @set.
  *
  * This function assumes the PCI device @pdev has at least as many available
- * interrupt vetors as @set has queues.  It will then queuery the vector
+ * interrupt vectors as @set has queues.  It will then query the vector
  * corresponding to each queue for it's affinity mask and built queue mapping
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 09af8ff18719..8b361e192e8a 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -30,43 +30,6 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
 
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
-				int (*init)(struct blk_mq_hw_ctx *),
-				void (*exit)(struct blk_mq_hw_ctx *))
-{
-	struct blk_mq_hw_ctx *hctx;
-	int ret;
-	int i;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
-		if (!hctx->sched_data) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (init) {
-			ret = init(hctx);
-			if (ret) {
-				/*
-				 * We don't want to give exit() a partially
-				 * initialized sched_data. init() must clean up
-				 * if it fails.
-				 */
-				kfree(hctx->sched_data);
-				hctx->sched_data = NULL;
-				goto error;
-			}
-		}
-	}
-
-	return 0;
-error:
-	blk_mq_sched_free_hctx_data(q, exit);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
-
 static void __blk_mq_sched_assign_ioc(struct request_queue *q,
 				      struct request *rq,
 				      struct bio *bio,
@@ -119,7 +82,11 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 
-	if (e) {
+	/*
+	 * For a reserved tag, allocate a normal request since we might
+	 * have driver dependencies on the value of the internal tag.
+	 */
+	if (e && !(data->flags & BLK_MQ_REQ_RESERVED)) {
 		data->flags |= BLK_MQ_REQ_INTERNAL;
 
 		/*
@@ -171,7 +138,8 @@ void blk_mq_sched_put_request(struct request *rq)
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
-	struct elevator_queue *e = hctx->queue->elevator;
+	struct request_queue *q = hctx->queue;
+	struct elevator_queue *e = q->elevator;
 	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
 	bool did_work = false;
 	LIST_HEAD(rq_list);
@@ -203,10 +171,10 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
-		did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
+		did_work = blk_mq_dispatch_rq_list(q, &rq_list);
 	} else if (!has_sched_dispatch) {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
-		blk_mq_dispatch_rq_list(hctx, &rq_list);
+		blk_mq_dispatch_rq_list(q, &rq_list);
 	}
 
 	/*
@@ -222,26 +190,10 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 			if (!rq)
 				break;
 			list_add(&rq->queuelist, &rq_list);
-		} while (blk_mq_dispatch_rq_list(hctx, &rq_list));
+		} while (blk_mq_dispatch_rq_list(q, &rq_list));
 	}
 }
 
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
-				   struct list_head *rq_list,
-				   struct request *(*get_rq)(struct blk_mq_hw_ctx *))
-{
-	do {
-		struct request *rq;
-
-		rq = get_rq(hctx);
-		if (!rq)
-			break;
-
-		list_add_tail(&rq->queuelist, rq_list);
-	} while (1);
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
-
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 			    struct request **merged_request)
 {
@@ -317,25 +269,68 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 	return true;
 }
 
-static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 {
 	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
 		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
-		if (blk_mq_hctx_has_pending(hctx))
+		if (blk_mq_hctx_has_pending(hctx)) {
 			blk_mq_run_hw_queue(hctx, true);
+			return true;
+		}
 	}
+	return false;
 }
 
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
-{
-	struct request_queue *q = hctx->queue;
-	unsigned int i;
+/**
+ * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
+ * @pos:    loop cursor.
+ * @skip:   the list element that will not be examined. Iteration starts at
+ *          @skip->next.
+ * @head:   head of the list to examine. This list must have at least one
+ *          element, namely @skip.
+ * @member: name of the list_head structure within typeof(*pos).
+ */
+#define list_for_each_entry_rcu_rr(pos, skip, head, member)		\
+	for ((pos) = (skip);						\
+	     (pos = (pos)->member.next != (head) ? list_entry_rcu(	\
+			(pos)->member.next, typeof(*pos), member) :	\
+	      list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
+	     (pos) != (skip); )
 
-	if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
-		if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
-			queue_for_each_hw_ctx(q, hctx, i)
-				blk_mq_sched_restart_hctx(hctx);
+/*
+ * Called after a driver tag has been freed to check whether a hctx needs to
+ * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
+ * queues in a round-robin fashion if the tag set of @hctx is shared with other
+ * hardware queues.
+ */
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
+{
+	struct blk_mq_tags *const tags = hctx->tags;
+	struct blk_mq_tag_set *const set = hctx->queue->tag_set;
+	struct request_queue *const queue = hctx->queue, *q;
+	struct blk_mq_hw_ctx *hctx2;
+	unsigned int i, j;
+
+	if (set->flags & BLK_MQ_F_TAG_SHARED) {
+		rcu_read_lock();
+		list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
+					   tag_set_list) {
+			queue_for_each_hw_ctx(q, hctx2, i)
+				if (hctx2->tags == tags &&
+				    blk_mq_sched_restart_hctx(hctx2))
+					goto done;
 		}
+		j = hctx->queue_num + 1;
+		for (i = 0; i < queue->nr_hw_queues; i++, j++) {
+			if (j == queue->nr_hw_queues)
+				j = 0;
+			hctx2 = queue->queue_hw_ctx[j];
+			if (hctx2->tags == tags &&
+			    blk_mq_sched_restart_hctx(hctx2))
+				break;
+		}
+done:
+		rcu_read_unlock();
 	} else {
 		blk_mq_sched_restart_hctx(hctx);
 	}
@@ -431,11 +426,86 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
 	}
 }
 
-int blk_mq_sched_setup(struct request_queue *q)
+static int blk_mq_sched_alloc_tags(struct request_queue *q,
+				   struct blk_mq_hw_ctx *hctx,
+				   unsigned int hctx_idx)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
+	int ret;
+
+	hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
+					       set->reserved_tags);
+	if (!hctx->sched_tags)
+		return -ENOMEM;
+
+	ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
+	if (ret)
+		blk_mq_sched_free_tags(set, hctx, hctx_idx);
+
+	return ret;
+}
+
+static void blk_mq_sched_tags_teardown(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_sched_free_tags(set, hctx, i);
+}
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+			   unsigned int hctx_idx)
+{
+	struct elevator_queue *e = q->elevator;
+	int ret;
+
+	if (!e)
+		return 0;
+
+	ret = blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+	if (ret)
+		return ret;
+
+	if (e->type->ops.mq.init_hctx) {
+		ret = e->type->ops.mq.init_hctx(hctx, hctx_idx);
+		if (ret) {
+			blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+			    unsigned int hctx_idx)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (!e)
+		return;
+
+	if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
+		e->type->ops.mq.exit_hctx(hctx, hctx_idx);
+		hctx->sched_data = NULL;
+	}
+
+	blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+}
+
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
+{
 	struct blk_mq_hw_ctx *hctx;
-	int ret, i;
+	struct elevator_queue *eq;
+	unsigned int i;
+	int ret;
+
+	if (!e) {
+		q->elevator = NULL;
+		return 0;
+	}
 
 	/*
 	 * Default to 256, since we don't split into sync/async like the
@@ -443,49 +513,53 @@ int blk_mq_sched_setup(struct request_queue *q)
 	 */
 	q->nr_requests = 2 * BLKDEV_MAX_RQ;
 
-	/*
-	 * We're switching to using an IO scheduler, so setup the hctx
-	 * scheduler tags and switch the request map from the regular
-	 * tags to scheduler tags. First allocate what we need, so we
-	 * can safely fail and fallback, if needed.
-	 */
-	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
-		hctx->sched_tags = blk_mq_alloc_rq_map(set, i,
-				q->nr_requests, set->reserved_tags);
-		if (!hctx->sched_tags) {
-			ret = -ENOMEM;
-			break;
-		}
-		ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
+		ret = blk_mq_sched_alloc_tags(q, hctx, i);
 		if (ret)
-			break;
+			goto err;
 	}
 
-	/*
-	 * If we failed, free what we did allocate
-	 */
-	if (ret) {
+	ret = e->ops.mq.init_sched(q, e);
+	if (ret)
+		goto err;
+
+	if (e->ops.mq.init_hctx) {
 		queue_for_each_hw_ctx(q, hctx, i) {
-			if (!hctx->sched_tags)
-				continue;
-			blk_mq_sched_free_tags(set, hctx, i);
+			ret = e->ops.mq.init_hctx(hctx, i);
+			if (ret) {
+				eq = q->elevator;
+				blk_mq_exit_sched(q, eq);
+				kobject_put(&eq->kobj);
+				return ret;
+			}
 		}
-
-		return ret;
 	}
 
 	return 0;
+
+err:
+	blk_mq_sched_tags_teardown(q);
+	q->elevator = NULL;
+	return ret;
 }
 
-void blk_mq_sched_teardown(struct request_queue *q)
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 {
-	struct blk_mq_tag_set *set = q->tag_set;
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned int i;
 
-	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_sched_free_tags(set, hctx, i);
+	if (e->type->ops.mq.exit_hctx) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			if (hctx->sched_data) {
+				e->type->ops.mq.exit_hctx(hctx, i);
+				hctx->sched_data = NULL;
+			}
+		}
+	}
+	if (e->type->ops.mq.exit_sched)
+		e->type->ops.mq.exit_sched(e);
+	blk_mq_sched_tags_teardown(q);
+	q->elevator = NULL;
 }
 
 int blk_mq_sched_init(struct request_queue *q)
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index a75b16b123f7..edafb5383b7b 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -4,10 +4,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
-				int (*init)(struct blk_mq_hw_ctx *),
-				void (*exit)(struct blk_mq_hw_ctx *));
-
 void blk_mq_sched_free_hctx_data(struct request_queue *q,
 				 void (*exit)(struct blk_mq_hw_ctx *));
 
@@ -19,7 +15,7 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 				struct request **merged_request);
 bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
 bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 				 bool run_queue, bool async, bool can_block);
@@ -28,12 +24,14 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 				  struct list_head *list, bool run_queue_async);
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
-			struct list_head *rq_list,
-			struct request *(*get_rq)(struct blk_mq_hw_ctx *));
 
-int blk_mq_sched_setup(struct request_queue *q);
-void blk_mq_sched_teardown(struct request_queue *q);
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+			   unsigned int hctx_idx);
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+			    unsigned int hctx_idx);
 
 int blk_mq_sched_init(struct request_queue *q);
 
@@ -81,17 +79,12 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 	return true;
 }
 
-static inline void
-blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static inline void blk_mq_sched_completed_request(struct request *rq)
 {
-	struct elevator_queue *e = hctx->queue->elevator;
+	struct elevator_queue *e = rq->q->elevator;
 
 	if (e && e->type->ops.mq.completed_request)
-		e->type->ops.mq.completed_request(hctx, rq);
-
-	BUG_ON(rq->internal_tag == -1);
-
-	blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
+		e->type->ops.mq.completed_request(rq);
 }
 
 static inline void blk_mq_sched_started_request(struct request *rq)
@@ -131,20 +124,6 @@ static inline void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
 		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 }
 
-/*
- * Mark a hardware queue and the request queue it belongs to as needing a
- * restart.
- */
-static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
-{
-	struct request_queue *q = hctx->queue;
-
-	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
-	if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
-		set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-}
-
 static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
 {
 	return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 295e69670c39..ec0afdf765e3 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -17,6 +17,15 @@ static void blk_mq_sysfs_release(struct kobject *kobj)
 {
 }
 
+static void blk_mq_hw_sysfs_release(struct kobject *kobj)
+{
+	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
+						  kobj);
+	free_cpumask_var(hctx->cpumask);
+	kfree(hctx->ctxs);
+	kfree(hctx);
+}
+
 struct blk_mq_ctx_sysfs_entry {
 	struct attribute attr;
 	ssize_t (*show)(struct blk_mq_ctx *, char *);
@@ -200,7 +209,7 @@ static struct kobj_type blk_mq_ctx_ktype = {
 static struct kobj_type blk_mq_hw_ktype = {
 	.sysfs_ops	= &blk_mq_hw_sysfs_ops,
 	.default_attrs	= default_hw_ctx_attrs,
-	.release	= blk_mq_sysfs_release,
+	.release	= blk_mq_hw_sysfs_release,
 };
 
 static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
@@ -242,24 +251,17 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	int i, j;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		blk_mq_unregister_hctx(hctx);
+	int i;
 
-		hctx_for_each_ctx(hctx, ctx, j)
-			kobject_put(&ctx->kobj);
+	lockdep_assert_held(&q->sysfs_lock);
 
-		kobject_put(&hctx->kobj);
-	}
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_unregister_hctx(hctx);
 
-	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_debugfs_unregister_mq(q);
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
-	kobject_put(&q->mq_kobj);
-
 	kobject_put(&dev->kobj);
 
 	q->mq_sysfs_init_done = false;
@@ -267,9 +269,9 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 
 void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
-	blk_mq_disable_hotplug();
+	mutex_lock(&q->sysfs_lock);
 	__blk_mq_unregister_dev(dev, q);
-	blk_mq_enable_hotplug();
+	mutex_unlock(&q->sysfs_lock);
 }
 
 void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
@@ -277,7 +279,19 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
 }
 
-static void blk_mq_sysfs_init(struct request_queue *q)
+void blk_mq_sysfs_deinit(struct request_queue *q)
+{
+	struct blk_mq_ctx *ctx;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		ctx = per_cpu_ptr(q->queue_ctx, cpu);
+		kobject_put(&ctx->kobj);
+	}
+	kobject_put(&q->mq_kobj);
+}
+
+void blk_mq_sysfs_init(struct request_queue *q)
 {
 	struct blk_mq_ctx *ctx;
 	int cpu;
@@ -290,14 +304,13 @@ static void blk_mq_sysfs_init(struct request_queue *q)
 	}
 }
 
-int blk_mq_register_dev(struct device *dev, struct request_queue *q)
+int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int ret, i;
 
-	blk_mq_disable_hotplug();
-
-	blk_mq_sysfs_init(q);
+	WARN_ON_ONCE(!q->kobj.parent);
+	lockdep_assert_held(&q->sysfs_lock);
 
 	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
 	if (ret < 0)
@@ -305,20 +318,38 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
 
 	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
 
-	blk_mq_debugfs_register(q, kobject_name(&dev->kobj));
+	blk_mq_debugfs_register(q);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
-			break;
+			goto unreg;
 	}
 
-	if (ret)
-		__blk_mq_unregister_dev(dev, q);
-	else
-		q->mq_sysfs_init_done = true;
+	q->mq_sysfs_init_done = true;
+
 out:
-	blk_mq_enable_hotplug();
+	return ret;
+
+unreg:
+	while (--i >= 0)
+		blk_mq_unregister_hctx(q->queue_hw_ctx[i]);
+
+	blk_mq_debugfs_unregister_mq(q);
+
+	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
+	kobject_del(&q->mq_kobj);
+	kobject_put(&dev->kobj);
+	return ret;
+}
+
+int blk_mq_register_dev(struct device *dev, struct request_queue *q)
+{
+	int ret;
+
+	mutex_lock(&q->sysfs_lock);
+	ret = __blk_mq_register_dev(dev, q);
+	mutex_unlock(&q->sysfs_lock);
 
 	return ret;
 }
@@ -329,13 +360,17 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	mutex_lock(&q->sysfs_lock);
 	if (!q->mq_sysfs_init_done)
-		return;
+		goto unlock;
 
-	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_debugfs_unregister_mq(q);
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
+
+unlock:
+	mutex_unlock(&q->sysfs_lock);
 }
 
 int blk_mq_sysfs_register(struct request_queue *q)
@@ -343,10 +378,11 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i, ret = 0;
 
+	mutex_lock(&q->sysfs_lock);
 	if (!q->mq_sysfs_init_done)
-		return ret;
+		goto unlock;
 
-	blk_mq_debugfs_register_hctxs(q);
+	blk_mq_debugfs_register_mq(q);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
@@ -354,5 +390,8 @@ int blk_mq_sysfs_register(struct request_queue *q)
 			break;
 	}
 
+unlock:
+	mutex_unlock(&q->sysfs_lock);
+
 	return ret;
 }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index e48bc2c72615..d0be72ccb091 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -96,7 +96,10 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
 	if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
 	    !hctx_may_queue(data->hctx, bt))
 		return -1;
-	return __sbitmap_queue_get(bt);
+	if (data->shallow_depth)
+		return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
+	else
+		return __sbitmap_queue_get(bt);
 }
 
 unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
@@ -295,6 +298,9 @@ int blk_mq_reinit_tagset(struct blk_mq_tag_set *set)
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		struct blk_mq_tags *tags = set->tags[i];
 
+		if (!tags)
+			continue;
+
 		for (j = 0; j < tags->nr_tags; j++) {
 			if (!tags->static_rqs[j])
 				continue;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b2fd175e84d7..bf90684a007a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -39,6 +39,26 @@
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
 
+static void blk_mq_poll_stats_start(struct request_queue *q);
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
+
+static int blk_mq_poll_stats_bkt(const struct request *rq)
+{
+	int ddir, bytes, bucket;
+
+	ddir = rq_data_dir(rq);
+	bytes = blk_rq_bytes(rq);
+
+	bucket = ddir + 2*(ilog2(bytes) - 9);
+
+	if (bucket < 0)
+		return -1;
+	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
+		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
+
+	return bucket;
+}
+
 /*
  * Check if any of the ctx's have pending work in this hardware queue
  */
@@ -65,7 +85,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
 }
 
-void blk_mq_freeze_queue_start(struct request_queue *q)
+void blk_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
 
@@ -75,7 +95,7 @@ void blk_mq_freeze_queue_start(struct request_queue *q)
 		blk_mq_run_hw_queues(q, false);
 	}
 }
-EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
+EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
 
 void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
@@ -105,7 +125,7 @@ void blk_freeze_queue(struct request_queue *q)
 	 * no blk_unfreeze_queue(), and blk_freeze_queue() is not
 	 * exported to drivers as the only user for unfreeze is blk_mq.
 	 */
-	blk_mq_freeze_queue_start(q);
+	blk_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
 
@@ -210,7 +230,6 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 #endif
 	rq->special = NULL;
 	/* tag was already set */
-	rq->errors = 0;
 	rq->extra_len = 0;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
@@ -321,7 +340,6 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 
 	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
 
-	blk_mq_put_ctx(alloc_data.ctx);
 	blk_queue_exit(q);
 
 	if (!rq)
@@ -348,8 +366,8 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	if (rq->tag != -1)
 		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
 	if (sched_tag != -1)
-		blk_mq_sched_completed_request(hctx, rq);
-	blk_mq_sched_restart_queues(hctx);
+		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
 }
 
@@ -366,6 +384,7 @@ void blk_mq_finish_request(struct request *rq)
 {
 	blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
 }
+EXPORT_SYMBOL_GPL(blk_mq_finish_request);
 
 void blk_mq_free_request(struct request *rq)
 {
@@ -403,12 +422,19 @@ static void __blk_mq_complete_request_remote(void *data)
 	rq->q->softirq_done_fn(rq);
 }
 
-static void blk_mq_ipi_complete_request(struct request *rq)
+static void __blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	bool shared = false;
 	int cpu;
 
+	if (rq->internal_tag != -1)
+		blk_mq_sched_completed_request(rq);
+	if (rq->rq_flags & RQF_STATS) {
+		blk_mq_poll_stats_start(rq->q);
+		blk_stat_add(rq);
+	}
+
 	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
 		rq->q->softirq_done_fn(rq);
 		return;
@@ -429,33 +455,6 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 	put_cpu();
 }
 
-static void blk_mq_stat_add(struct request *rq)
-{
-	if (rq->rq_flags & RQF_STATS) {
-		/*
-		 * We could rq->mq_ctx here, but there's less of a risk
-		 * of races if we have the completion event add the stats
-		 * to the local software queue.
-		 */
-		struct blk_mq_ctx *ctx;
-
-		ctx = __blk_mq_get_ctx(rq->q, raw_smp_processor_id());
-		blk_stat_add(&ctx->stat[rq_data_dir(rq)], rq);
-	}
-}
-
-static void __blk_mq_complete_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-
-	blk_mq_stat_add(rq);
-
-	if (!q->softirq_done_fn)
-		blk_mq_end_request(rq, rq->errors);
-	else
-		blk_mq_ipi_complete_request(rq);
-}
-
 /**
  * blk_mq_complete_request - end I/O on a request
  * @rq:		the request being processed
@@ -464,16 +463,14 @@ static void __blk_mq_complete_request(struct request *rq)
  *	Ends all I/O on a request. It does not handle partial completions.
  *	The actual completion happens out-of-order, through a IPI handler.
  **/
-void blk_mq_complete_request(struct request *rq, int error)
+void blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
 	if (unlikely(blk_should_fake_timeout(q)))
 		return;
-	if (!blk_mark_rq_complete(rq)) {
-		rq->errors = error;
+	if (!blk_mark_rq_complete(rq))
 		__blk_mq_complete_request(rq);
-	}
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
@@ -492,7 +489,7 @@ void blk_mq_start_request(struct request *rq)
 	trace_block_rq_issue(q, rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
-		blk_stat_set_issue_time(&rq->issue_stat);
+		blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
 		rq->rq_flags |= RQF_STATS;
 		wbt_issue(q->rq_wb, &rq->issue_stat);
 	}
@@ -527,6 +524,15 @@ void blk_mq_start_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_start_request);
 
+/*
+ * When we reach here because queue is busy, REQ_ATOM_COMPLETE
+ * flag isn't set yet, so there may be race with timeout handler,
+ * but given rq->deadline is just set in .queue_rq() under
+ * this situation, the race won't be possible in reality because
+ * rq->timeout should be set as big enough to cover the window
+ * between blk_mq_start_request() called from .queue_rq() and
+ * clearing REQ_ATOM_STARTED here.
+ */
 static void __blk_mq_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -634,8 +640,7 @@ void blk_mq_abort_requeue_list(struct request_queue *q)
 
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		rq->errors = -EIO;
-		blk_mq_end_request(rq, rq->errors);
+		blk_mq_end_request(rq, -EIO);
 	}
 }
 EXPORT_SYMBOL(blk_mq_abort_requeue_list);
@@ -667,7 +672,7 @@ void blk_mq_rq_timed_out(struct request *req, bool reserved)
 	 * just be ignored. This can happen due to the bitflag ordering.
 	 * Timeout first checks if STARTED is set, and if it is, assumes
 	 * the request is active. But if we race with completion, then
-	 * we both flags will get cleared. So check here again, and ignore
+	 * both flags will get cleared. So check here again, and ignore
 	 * a timeout event with a request that isn't active.
 	 */
 	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
@@ -697,18 +702,22 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 {
 	struct blk_mq_timeout_data *data = priv;
 
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
-		/*
-		 * If a request wasn't started before the queue was
-		 * marked dying, kill it here or it'll go unnoticed.
-		 */
-		if (unlikely(blk_queue_dying(rq->q))) {
-			rq->errors = -EIO;
-			blk_mq_end_request(rq, rq->errors);
-		}
+	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
 		return;
-	}
 
+	/*
+	 * The rq being checked may have been freed and reallocated
+	 * out already here, we avoid this race by checking rq->deadline
+	 * and REQ_ATOM_COMPLETE flag together:
+	 *
+	 * - if rq->deadline is observed as new value because of
+	 *   reusing, the rq won't be timed out because of timing.
+	 * - if rq->deadline is observed as previous value,
+	 *   REQ_ATOM_COMPLETE flag won't be cleared in reuse path
+	 *   because we put a barrier between setting rq->deadline
+	 *   and clearing the flag in blk_mq_start_request(), so
+	 *   this rq won't be timed out too.
+	 */
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))
 			blk_mq_rq_timed_out(rq, reserved);
@@ -737,7 +746,7 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	 * percpu_ref_tryget directly, because we need to be able to
 	 * obtain a reference even in the short window between the queue
 	 * starting to freeze, by dropping the first reference in
-	 * blk_mq_freeze_queue_start, and the moment the last request is
+	 * blk_freeze_queue_start, and the moment the last request is
 	 * consumed, marked by the instant q_usage_counter reaches
 	 * zero.
 	 */
@@ -855,12 +864,10 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
 	};
 
-	if (rq->tag != -1) {
-done:
-		if (hctx)
-			*hctx = data.hctx;
-		return true;
-	}
+	might_sleep_if(wait);
+
+	if (rq->tag != -1)
+		goto done;
 
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
@@ -872,10 +879,12 @@ done:
 			atomic_inc(&data.hctx->nr_active);
 		}
 		data.hctx->tags->rqs[rq->tag] = rq;
-		goto done;
 	}
 
-	return false;
+done:
+	if (hctx)
+		*hctx = data.hctx;
+	return rq->tag != -1;
 }
 
 static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
@@ -972,25 +981,20 @@ static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
 	return true;
 }
 
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 {
-	struct request_queue *q = hctx->queue;
+	struct blk_mq_hw_ctx *hctx;
 	struct request *rq;
-	LIST_HEAD(driver_list);
-	struct list_head *dptr;
-	int queued, ret = BLK_MQ_RQ_QUEUE_OK;
+	int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
 
-	/*
-	 * Start off with dptr being NULL, so we start the first request
-	 * immediately, even if we have more pending.
-	 */
-	dptr = NULL;
+	if (list_empty(list))
+		return false;
 
 	/*
 	 * Now process all the entries, sending them to the driver.
 	 */
-	queued = 0;
-	while (!list_empty(list)) {
+	errors = queued = 0;
+	do {
 		struct blk_mq_queue_data bd;
 
 		rq = list_first_entry(list, struct request, queuelist);
@@ -1002,23 +1006,21 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed.
 			 */
-			if (blk_mq_dispatch_wait_add(hctx)) {
-				/*
-				 * It's possible that a tag was freed in the
-				 * window between the allocation failure and
-				 * adding the hardware queue to the wait queue.
-				 */
-				if (!blk_mq_get_driver_tag(rq, &hctx, false))
-					break;
-			} else {
+			if (!blk_mq_dispatch_wait_add(hctx))
+				break;
+
+			/*
+			 * It's possible that a tag was freed in the window
+			 * between the allocation failure and adding the
+			 * hardware queue to the wait queue.
+			 */
+			if (!blk_mq_get_driver_tag(rq, &hctx, false))
 				break;
-			}
 		}
 
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
-		bd.list = dptr;
 
 		/*
 		 * Flag last if we have no more requests, or if we have more
@@ -1046,21 +1048,14 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 		default:
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
 		case BLK_MQ_RQ_QUEUE_ERROR:
-			rq->errors = -EIO;
-			blk_mq_end_request(rq, rq->errors);
+			errors++;
+			blk_mq_end_request(rq, -EIO);
 			break;
 		}
 
 		if (ret == BLK_MQ_RQ_QUEUE_BUSY)
 			break;
-
-		/*
-		 * We've done the first request. If we have more than 1
-		 * left in the list, set dptr to defer issue.
-		 */
-		if (!dptr && list->next != list->prev)
-			dptr = &driver_list;
-	}
+	} while (!list_empty(list));
 
 	hctx->dispatched[queued_to_index(queued)]++;
 
@@ -1070,8 +1065,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	 */
 	if (!list_empty(list)) {
 		/*
-		 * If we got a driver tag for the next request already,
-		 * free it again.
+		 * If an I/O scheduler has been configured and we got a driver
+		 * tag for the next request already, free it again.
 		 */
 		rq = list_first_entry(list, struct request, queuelist);
 		blk_mq_put_driver_tag(rq);
@@ -1081,23 +1076,31 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 		spin_unlock(&hctx->lock);
 
 		/*
-		 * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
-		 * it's possible the queue is stopped and restarted again
-		 * before this. Queue restart will dispatch requests. And since
-		 * requests in rq_list aren't added into hctx->dispatch yet,
-		 * the requests in rq_list might get lost.
+		 * If SCHED_RESTART was set by the caller of this function and
+		 * it is no longer set that means that it was cleared by another
+		 * thread and hence that a queue rerun is needed.
 		 *
-		 * blk_mq_run_hw_queue() already checks the STOPPED bit
+		 * If TAG_WAITING is set that means that an I/O scheduler has
+		 * been configured and another thread is waiting for a driver
+		 * tag. To guarantee fairness, do not rerun this hardware queue
+		 * but let the other thread grab the driver tag.
 		 *
-		 * If RESTART or TAG_WAITING is set, then let completion restart
-		 * the queue instead of potentially looping here.
+		 * If no I/O scheduler has been configured it is possible that
+		 * the hardware queue got stopped and restarted before requests
+		 * were pushed back onto the dispatch list. Rerun the queue to
+		 * avoid starvation. Notes:
+		 * - blk_mq_run_hw_queue() checks whether or not a queue has
+		 *   been stopped before rerunning a queue.
+		 * - Some but not all block drivers stop a queue before
+		 *   returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq
+		 *   and dm-rq.
 		 */
 		if (!blk_mq_sched_needs_restart(hctx) &&
 		    !test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))
 			blk_mq_run_hw_queue(hctx, true);
 	}
 
-	return queued != 0;
+	return (queued + errors) != 0;
 }
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
@@ -1112,6 +1115,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		blk_mq_sched_dispatch_requests(hctx);
 		rcu_read_unlock();
 	} else {
+		might_sleep();
+
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
 		blk_mq_sched_dispatch_requests(hctx);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
@@ -1143,7 +1148,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 	return hctx->next_cpu;
 }
 
-void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
+					unsigned long msecs)
 {
 	if (unlikely(blk_mq_hctx_stopped(hctx) ||
 		     !blk_mq_hw_queue_mapped(hctx)))
@@ -1160,8 +1166,22 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		put_cpu();
 	}
 
-	kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work);
+	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+					 &hctx->run_work,
+					 msecs_to_jiffies(msecs));
+}
+
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
+{
+	__blk_mq_delay_run_hw_queue(hctx, true, msecs);
 }
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+	__blk_mq_delay_run_hw_queue(hctx, async, 0);
+}
+EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
 void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
@@ -1200,8 +1220,7 @@ EXPORT_SYMBOL(blk_mq_queue_stopped);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
-	cancel_work(&hctx->run_work);
-	cancel_delayed_work(&hctx->delay_work);
+	cancel_delayed_work_sync(&hctx->run_work);
 	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queue);
@@ -1258,29 +1277,40 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 {
 	struct blk_mq_hw_ctx *hctx;
 
-	hctx = container_of(work, struct blk_mq_hw_ctx, run_work);
-
-	__blk_mq_run_hw_queue(hctx);
-}
+	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
 
-static void blk_mq_delay_work_fn(struct work_struct *work)
-{
-	struct blk_mq_hw_ctx *hctx;
+	/*
+	 * If we are stopped, don't run the queue. The exception is if
+	 * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
+	 * the STOPPED bit and run it.
+	 */
+	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
+		if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
+			return;
 
-	hctx = container_of(work, struct blk_mq_hw_ctx, delay_work.work);
+		clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	}
 
-	if (test_and_clear_bit(BLK_MQ_S_STOPPED, &hctx->state))
-		__blk_mq_run_hw_queue(hctx);
+	__blk_mq_run_hw_queue(hctx);
 }
 
+
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
 	if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
 		return;
 
+	/*
+	 * Stop the hw queue, then modify currently delayed work.
+	 * This should prevent us from running the queue prematurely.
+	 * Mark the queue as auto-clearing STOPPED when it runs.
+	 */
 	blk_mq_stop_hw_queue(hctx);
-	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-			&hctx->delay_work, msecs_to_jiffies(msecs));
+	set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+					&hctx->run_work,
+					msecs_to_jiffies(msecs));
 }
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
@@ -1389,7 +1419,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 {
-	init_request_from_bio(rq, bio);
+	blk_init_request_from_bio(rq, bio);
 
 	blk_account_io_start(rq, true);
 }
@@ -1434,13 +1464,13 @@ static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
-static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
+static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
+				      bool may_sleep)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
-		.list = NULL,
-		.last = 1
+		.last = true,
 	};
 	struct blk_mq_hw_ctx *hctx;
 	blk_qc_t new_cookie;
@@ -1465,31 +1495,42 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 		return;
 	}
 
-	__blk_mq_requeue_request(rq);
-
 	if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
 		*cookie = BLK_QC_T_NONE;
-		rq->errors = -EIO;
-		blk_mq_end_request(rq, rq->errors);
+		blk_mq_end_request(rq, -EIO);
 		return;
 	}
 
+	__blk_mq_requeue_request(rq);
 insert:
-	blk_mq_sched_insert_request(rq, false, true, true, false);
+	blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
+}
+
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, blk_qc_t *cookie)
+{
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		rcu_read_lock();
+		__blk_mq_try_issue_directly(rq, cookie, false);
+		rcu_read_unlock();
+	} else {
+		unsigned int srcu_idx;
+
+		might_sleep();
+
+		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+		__blk_mq_try_issue_directly(rq, cookie, true);
+		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+	}
 }
 
-/*
- * Multiple hardware queue variant. This will not use per-process plugs,
- * but will attempt to bypass the hctx queueing if we can go straight to
- * hardware for SYNC IO.
- */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = op_is_flush(bio->bi_opf);
 	struct blk_mq_alloc_data data = { .flags = 0 };
 	struct request *rq;
-	unsigned int request_count = 0, srcu_idx;
+	unsigned int request_count = 0;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
@@ -1525,147 +1566,21 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	cookie = request_to_qc_t(data.hctx, rq);
 
-	if (unlikely(is_flush_fua)) {
-		if (q->elevator)
-			goto elv_insert;
-		blk_mq_bio_to_request(rq, bio);
-		blk_insert_flush(rq);
-		goto run_queue;
-	}
-
 	plug = current->plug;
-	/*
-	 * If the driver supports defer issued based on 'last', then
-	 * queue it up like normal since we can potentially save some
-	 * CPU this way.
-	 */
-	if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
-	    !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
-		struct request *old_rq = NULL;
-
-		blk_mq_bio_to_request(rq, bio);
-
-		/*
-		 * We do limited plugging. If the bio can be merged, do that.
-		 * Otherwise the existing request in the plug list will be
-		 * issued. So the plug list will have one request at most
-		 */
-		if (plug) {
-			/*
-			 * The plug list might get flushed before this. If that
-			 * happens, same_queue_rq is invalid and plug list is
-			 * empty
-			 */
-			if (same_queue_rq && !list_empty(&plug->mq_list)) {
-				old_rq = same_queue_rq;
-				list_del_init(&old_rq->queuelist);
-			}
-			list_add_tail(&rq->queuelist, &plug->mq_list);
-		} else /* is_sync */
-			old_rq = rq;
+	if (unlikely(is_flush_fua)) {
 		blk_mq_put_ctx(data.ctx);
-		if (!old_rq)
-			goto done;
-
-		if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
-			rcu_read_lock();
-			blk_mq_try_issue_directly(old_rq, &cookie);
-			rcu_read_unlock();
+		blk_mq_bio_to_request(rq, bio);
+		if (q->elevator) {
+			blk_mq_sched_insert_request(rq, false, true, true,
+					true);
 		} else {
-			srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
-			blk_mq_try_issue_directly(old_rq, &cookie);
-			srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
+			blk_insert_flush(rq);
+			blk_mq_run_hw_queue(data.hctx, true);
 		}
-		goto done;
-	}
-
-	if (q->elevator) {
-elv_insert:
-		blk_mq_put_ctx(data.ctx);
-		blk_mq_bio_to_request(rq, bio);
-		blk_mq_sched_insert_request(rq, false, true,
-						!is_sync || is_flush_fua, true);
-		goto done;
-	}
-	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
-		/*
-		 * For a SYNC request, send it to the hardware immediately. For
-		 * an ASYNC request, just ensure that we run it later on. The
-		 * latter allows for merging opportunities and more efficient
-		 * dispatching.
-		 */
-run_queue:
-		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
-	}
-	blk_mq_put_ctx(data.ctx);
-done:
-	return cookie;
-}
-
-/*
- * Single hardware queue variant. This will attempt to use any per-process
- * plug for merging and IO deferral.
- */
-static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
-{
-	const int is_sync = op_is_sync(bio->bi_opf);
-	const int is_flush_fua = op_is_flush(bio->bi_opf);
-	struct blk_plug *plug;
-	unsigned int request_count = 0;
-	struct blk_mq_alloc_data data = { .flags = 0 };
-	struct request *rq;
-	blk_qc_t cookie;
-	unsigned int wb_acct;
-
-	blk_queue_bounce(q, &bio);
-
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_io_error(bio);
-		return BLK_QC_T_NONE;
-	}
-
-	blk_queue_split(q, &bio, q->bio_split);
-
-	if (!is_flush_fua && !blk_queue_nomerges(q)) {
-		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
-			return BLK_QC_T_NONE;
-	} else
-		request_count = blk_plug_queued_count(q);
-
-	if (blk_mq_sched_bio_merge(q, bio))
-		return BLK_QC_T_NONE;
-
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
-
-	trace_block_getrq(q, bio, bio->bi_opf);
-
-	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
-	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
-		return BLK_QC_T_NONE;
-	}
-
-	wbt_track(&rq->issue_stat, wb_acct);
-
-	cookie = request_to_qc_t(data.hctx, rq);
-
-	if (unlikely(is_flush_fua)) {
-		if (q->elevator)
-			goto elv_insert;
-		blk_mq_bio_to_request(rq, bio);
-		blk_insert_flush(rq);
-		goto run_queue;
-	}
-
-	/*
-	 * A task plug currently exists. Since this is completely lockless,
-	 * utilize that to temporarily store requests until the task is
-	 * either done or scheduled away.
-	 */
-	plug = current->plug;
-	if (plug) {
+	} else if (plug && q->nr_hw_queues == 1) {
 		struct request *last = NULL;
 
+		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
@@ -1674,13 +1589,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		 */
 		if (list_empty(&plug->mq_list))
 			request_count = 0;
+		else if (blk_queue_nomerges(q))
+			request_count = blk_plug_queued_count(q);
+
 		if (!request_count)
 			trace_block_plug(q);
 		else
 			last = list_entry_rq(plug->mq_list.prev);
 
-		blk_mq_put_ctx(data.ctx);
-
 		if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
 		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
 			blk_flush_plug_list(plug, false);
@@ -1688,30 +1604,41 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		list_add_tail(&rq->queuelist, &plug->mq_list);
-		return cookie;
-	}
-
-	if (q->elevator) {
-elv_insert:
-		blk_mq_put_ctx(data.ctx);
+	} else if (plug && !blk_queue_nomerges(q)) {
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_sched_insert_request(rq, false, true,
-						!is_sync || is_flush_fua, true);
-		goto done;
-	}
-	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+
 		/*
-		 * For a SYNC request, send it to the hardware immediately. For
-		 * an ASYNC request, just ensure that we run it later on. The
-		 * latter allows for merging opportunities and more efficient
-		 * dispatching.
+		 * We do limited plugging. If the bio can be merged, do that.
+		 * Otherwise the existing request in the plug list will be
+		 * issued. So the plug list will have one request at most
+		 * The plug list might get flushed before this. If that happens,
+		 * the plug list is empty, and same_queue_rq is invalid.
 		 */
-run_queue:
-		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
-	}
+		if (list_empty(&plug->mq_list))
+			same_queue_rq = NULL;
+		if (same_queue_rq)
+			list_del_init(&same_queue_rq->queuelist);
+		list_add_tail(&rq->queuelist, &plug->mq_list);
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (same_queue_rq)
+			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
+					&cookie);
+	} else if (q->nr_hw_queues > 1 && is_sync) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+	} else if (q->elevator) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true, true, true);
+	} else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_run_hw_queue(data.hctx, true);
+	} else
+		blk_mq_put_ctx(data.ctx);
 
-	blk_mq_put_ctx(data.ctx);
-done:
 	return cookie;
 }
 
@@ -1931,6 +1858,8 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 				       hctx->fq->flush_rq, hctx_idx,
 				       flush_start_tag + hctx_idx);
 
+	blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
+
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
@@ -1955,16 +1884,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
-static void blk_mq_free_hw_queues(struct request_queue *q,
-		struct blk_mq_tag_set *set)
-{
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
-
-	queue_for_each_hw_ctx(q, hctx, i)
-		free_cpumask_var(hctx->cpumask);
-}
-
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
@@ -1976,8 +1895,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	if (node == NUMA_NO_NODE)
 		node = hctx->numa_node = set->numa_node;
 
-	INIT_WORK(&hctx->run_work, blk_mq_run_work_fn);
-	INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
+	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
@@ -2007,9 +1925,12 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
 		goto free_bitmap;
 
+	if (blk_mq_sched_init_hctx(q, hctx, hctx_idx))
+		goto exit_hctx;
+
 	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
 	if (!hctx->fq)
-		goto exit_hctx;
+		goto sched_exit_hctx;
 
 	if (set->ops->init_request &&
 	    set->ops->init_request(set->driver_data,
@@ -2024,6 +1945,8 @@ static int blk_mq_init_hctx(struct request_queue *q,
 
  free_fq:
 	kfree(hctx->fq);
+ sched_exit_hctx:
+	blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
@@ -2045,13 +1968,10 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
 		struct blk_mq_hw_ctx *hctx;
 
-		memset(__ctx, 0, sizeof(*__ctx));
 		__ctx->cpu = i;
 		spin_lock_init(&__ctx->lock);
 		INIT_LIST_HEAD(&__ctx->rq_list);
 		__ctx->queue = q;
-		blk_stat_init(&__ctx->stat[BLK_STAT_READ]);
-		blk_stat_init(&__ctx->stat[BLK_STAT_WRITE]);
 
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpu_online(i))
@@ -2198,6 +2118,8 @@ static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared)
 {
 	struct request_queue *q;
 
+	lockdep_assert_held(&set->tag_list_lock);
+
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_freeze_queue(q);
 		queue_set_hctx_shared(q, shared);
@@ -2210,7 +2132,8 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	struct blk_mq_tag_set *set = q->tag_set;
 
 	mutex_lock(&set->tag_list_lock);
-	list_del_init(&q->tag_set_list);
+	list_del_rcu(&q->tag_set_list);
+	INIT_LIST_HEAD(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
 		set->flags &= ~BLK_MQ_F_TAG_SHARED;
@@ -2218,6 +2141,8 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
+
+	synchronize_rcu();
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
@@ -2235,7 +2160,7 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	}
 	if (set->flags & BLK_MQ_F_TAG_SHARED)
 		queue_set_hctx_shared(q, true);
-	list_add_tail(&q->tag_set_list, &set->tag_list);
+	list_add_tail_rcu(&q->tag_set_list, &set->tag_list);
 
 	mutex_unlock(&set->tag_list_lock);
 }
@@ -2251,21 +2176,23 @@ void blk_mq_release(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int i;
 
-	blk_mq_sched_teardown(q);
-
 	/* hctx kobj stays in hctx */
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx)
 			continue;
-		kfree(hctx->ctxs);
-		kfree(hctx);
+		kobject_put(&hctx->kobj);
 	}
 
 	q->mq_map = NULL;
 
 	kfree(q->queue_hw_ctx);
 
-	/* ctx kobj stays in queue_ctx */
+	/*
+	 * release .mq_kobj and sw queue's kobject now because
+	 * both share lifetime with request queue.
+	 */
+	blk_mq_sysfs_deinit(q);
+
 	free_percpu(q->queue_ctx);
 }
 
@@ -2330,10 +2257,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			if (hctx->tags)
 				blk_mq_free_map_and_requests(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
-			free_cpumask_var(hctx->cpumask);
 			kobject_put(&hctx->kobj);
-			kfree(hctx->ctxs);
-			kfree(hctx);
 			hctxs[j] = NULL;
 
 		}
@@ -2348,10 +2272,19 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
+	q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
+					     blk_mq_poll_stats_bkt,
+					     BLK_MQ_POLL_STATS_BKTS, q);
+	if (!q->poll_cb)
+		goto err_exit;
+
 	q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
 	if (!q->queue_ctx)
 		goto err_exit;
 
+	/* init q->mq_kobj and sw queues' kobjects */
+	blk_mq_sysfs_init(q);
+
 	q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)),
 						GFP_KERNEL, set->numa_node);
 	if (!q->queue_hw_ctx)
@@ -2379,10 +2312,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&q->requeue_list);
 	spin_lock_init(&q->requeue_lock);
 
-	if (q->nr_hw_queues > 1)
-		blk_queue_make_request(q, blk_mq_make_request);
-	else
-		blk_queue_make_request(q, blk_sq_make_request);
+	blk_queue_make_request(q, blk_mq_make_request);
 
 	/*
 	 * Do this after blk_queue_make_request() overrides it...
@@ -2437,12 +2367,9 @@ void blk_mq_free_queue(struct request_queue *q)
 	list_del_init(&q->all_q_node);
 	mutex_unlock(&all_q_mutex);
 
-	wbt_exit(q);
-
 	blk_mq_del_queue_tag_set(q);
 
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
-	blk_mq_free_hw_queues(q, set);
 }
 
 /* Basically redo blk_mq_init_queue with queue frozen */
@@ -2484,7 +2411,7 @@ static void blk_mq_queue_reinit_work(void)
 	 * take place in parallel.
 	 */
 	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_freeze_queue_start(q);
+		blk_freeze_queue_start(q);
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_freeze_queue_wait(q);
 
@@ -2580,6 +2507,14 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 	return 0;
 }
 
+static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
+{
+	if (set->ops->map_queues)
+		return set->ops->map_queues(set);
+	else
+		return blk_mq_map_queues(set);
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -2634,10 +2569,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (!set->mq_map)
 		goto out_free_tags;
 
-	if (set->ops->map_queues)
-		ret = set->ops->map_queues(set);
-	else
-		ret = blk_mq_map_queues(set);
+	ret = blk_mq_update_queue_map(set);
 	if (ret)
 		goto out_free_mq_map;
 
@@ -2720,6 +2652,8 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 {
 	struct request_queue *q;
 
+	lockdep_assert_held(&set->tag_list_lock);
+
 	if (nr_hw_queues > nr_cpu_ids)
 		nr_hw_queues = nr_cpu_ids;
 	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
@@ -2729,18 +2663,9 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 		blk_mq_freeze_queue(q);
 
 	set->nr_hw_queues = nr_hw_queues;
+	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
-
-		/*
-		 * Manually set the make_request_fn as blk_queue_make_request
-		 * resets a lot of the queue settings.
-		 */
-		if (q->nr_hw_queues > 1)
-			q->make_request_fn = blk_mq_make_request;
-		else
-			q->make_request_fn = blk_sq_make_request;
-
 		blk_mq_queue_reinit(q, cpu_online_mask);
 	}
 
@@ -2749,39 +2674,69 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
+/* Enable polling stats and return whether they were already enabled. */
+static bool blk_poll_stats_enable(struct request_queue *q)
+{
+	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+	    test_and_set_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+		return true;
+	blk_stat_add_callback(q, q->poll_cb);
+	return false;
+}
+
+static void blk_mq_poll_stats_start(struct request_queue *q)
+{
+	/*
+	 * We don't arm the callback if polling stats are not enabled or the
+	 * callback is already active.
+	 */
+	if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+	    blk_stat_is_active(q->poll_cb))
+		return;
+
+	blk_stat_activate_msecs(q->poll_cb, 100);
+}
+
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
+{
+	struct request_queue *q = cb->data;
+	int bucket;
+
+	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) {
+		if (cb->stat[bucket].nr_samples)
+			q->poll_stat[bucket] = cb->stat[bucket];
+	}
+}
+
 static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
 				       struct blk_mq_hw_ctx *hctx,
 				       struct request *rq)
 {
-	struct blk_rq_stat stat[2];
 	unsigned long ret = 0;
+	int bucket;
 
 	/*
 	 * If stats collection isn't on, don't sleep but turn it on for
 	 * future users
 	 */
-	if (!blk_stat_enable(q))
+	if (!blk_poll_stats_enable(q))
 		return 0;
 
 	/*
-	 * We don't have to do this once per IO, should optimize this
-	 * to just use the current window of stats until it changes
-	 */
-	memset(&stat, 0, sizeof(stat));
-	blk_hctx_stat_get(hctx, stat);
-
-	/*
 	 * As an optimistic guess, use half of the mean service time
 	 * for this type of request. We can (and should) make this smarter.
 	 * For instance, if the completion latencies are tight, we can
 	 * get closer than just half the mean. This is especially
 	 * important on devices where the completion latencies are longer
-	 * than ~10 usec.
+	 * than ~10 usec. We do use the stats for the relevant IO size
+	 * if available which does lead to better estimates.
 	 */
-	if (req_op(rq) == REQ_OP_READ && stat[BLK_STAT_READ].nr_samples)
-		ret = (stat[BLK_STAT_READ].mean + 1) / 2;
-	else if (req_op(rq) == REQ_OP_WRITE && stat[BLK_STAT_WRITE].nr_samples)
-		ret = (stat[BLK_STAT_WRITE].mean + 1) / 2;
+	bucket = blk_mq_poll_stats_bkt(rq);
+	if (bucket < 0)
+		return ret;
+
+	if (q->poll_stat[bucket].nr_samples)
+		ret = (q->poll_stat[bucket].mean + 1) / 2;
 
 	return ret;
 }
@@ -2904,8 +2859,17 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
 	if (!blk_qc_t_is_internal(cookie))
 		rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
-	else
+	else {
 		rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
+		/*
+		 * With scheduling, if the request has completed, we'll
+		 * get a NULL return here, as we clear the sched tag when
+		 * that happens. The request still remains valid, like always,
+		 * so we should be safe with just the NULL check.
+		 */
+		if (!rq)
+			return false;
+	}
 
 	return __blk_mq_poll(hctx, rq);
 }
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 088ced003c13..2814a14e529c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -20,7 +20,6 @@ struct blk_mq_ctx {
 
 	/* incremented at completion time */
 	unsigned long		____cacheline_aligned_in_smp rq_completed[2];
-	struct blk_rq_stat	stat[2];
 
 	struct request_queue	*queue;
 	struct kobject		kobj;
@@ -31,7 +30,7 @@ void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
 bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
@@ -77,6 +76,9 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 /*
  * sysfs helpers
  */
+extern void blk_mq_sysfs_init(struct request_queue *q);
+extern void blk_mq_sysfs_deinit(struct request_queue *q);
+extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
 extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
@@ -85,13 +87,12 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
  * debugfs helpers
  */
 #ifdef CONFIG_BLK_DEBUG_FS
-int blk_mq_debugfs_register(struct request_queue *q, const char *name);
+int blk_mq_debugfs_register(struct request_queue *q);
 void blk_mq_debugfs_unregister(struct request_queue *q);
-int blk_mq_debugfs_register_hctxs(struct request_queue *q);
-void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
+int blk_mq_debugfs_register_mq(struct request_queue *q);
+void blk_mq_debugfs_unregister_mq(struct request_queue *q);
 #else
-static inline int blk_mq_debugfs_register(struct request_queue *q,
-					  const char *name)
+static inline int blk_mq_debugfs_register(struct request_queue *q)
 {
 	return 0;
 }
@@ -100,12 +101,12 @@ static inline void blk_mq_debugfs_unregister(struct request_queue *q)
 {
 }
 
-static inline int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+static inline int blk_mq_debugfs_register_mq(struct request_queue *q)
 {
 	return 0;
 }
 
-static inline void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+static inline void blk_mq_debugfs_unregister_mq(struct request_queue *q)
 {
 }
 #endif
@@ -140,6 +141,7 @@ struct blk_mq_alloc_data {
 	/* input parameter */
 	struct request_queue *q;
 	unsigned int flags;
+	unsigned int shallow_depth;
 
 	/* input & output parameter */
 	struct blk_mq_ctx *ctx;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 1e7174ffc9d4..4fa81ed383ca 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -103,7 +103,6 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
-	lim->discard_zeroes_data = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
 	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
 	lim->alignment_offset = 0;
@@ -127,7 +126,6 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	blk_set_default_limits(lim);
 
 	/* Inherit limits from component devices */
-	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
 	lim->max_discard_segments = 1;
 	lim->max_hw_sectors = UINT_MAX;
@@ -609,7 +607,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
 
 	t->cluster &= b->cluster;
-	t->discard_zeroes_data &= b->discard_zeroes_data;
 
 	/* Physical block size a multiple of the logical block size? */
 	if (t->physical_block_size & (t->logical_block_size - 1)) {
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 9b43efb8933f..6c2f40940439 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -4,10 +4,27 @@
  * Copyright (C) 2016 Jens Axboe
  */
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 #include <linux/blk-mq.h>
 
 #include "blk-stat.h"
 #include "blk-mq.h"
+#include "blk.h"
+
+#define BLK_RQ_STAT_BATCH	64
+
+struct blk_queue_stats {
+	struct list_head callbacks;
+	spinlock_t lock;
+	bool enable_accounting;
+};
+
+static void blk_stat_init(struct blk_rq_stat *stat)
+{
+	stat->min = -1ULL;
+	stat->max = stat->nr_samples = stat->mean = 0;
+	stat->batch = stat->nr_batch = 0;
+}
 
 static void blk_stat_flush_batch(struct blk_rq_stat *stat)
 {
@@ -30,11 +47,11 @@ static void blk_stat_flush_batch(struct blk_rq_stat *stat)
 
 static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
+	blk_stat_flush_batch(src);
+
 	if (!src->nr_samples)
 		return;
 
-	blk_stat_flush_batch(src);
-
 	dst->min = min(dst->min, src->min);
 	dst->max = max(dst->max, src->max);
 
@@ -48,209 +65,185 @@ static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 	dst->nr_samples += src->nr_samples;
 }
 
-static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
 {
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	uint64_t latest = 0;
-	int i, j, nr;
-
-	blk_stat_init(&dst[BLK_STAT_READ]);
-	blk_stat_init(&dst[BLK_STAT_WRITE]);
-
-	nr = 0;
-	do {
-		uint64_t newest = 0;
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			hctx_for_each_ctx(hctx, ctx, j) {
-				blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
-				blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
-
-				if (!ctx->stat[BLK_STAT_READ].nr_samples &&
-				    !ctx->stat[BLK_STAT_WRITE].nr_samples)
-					continue;
-				if (ctx->stat[BLK_STAT_READ].time > newest)
-					newest = ctx->stat[BLK_STAT_READ].time;
-				if (ctx->stat[BLK_STAT_WRITE].time > newest)
-					newest = ctx->stat[BLK_STAT_WRITE].time;
-			}
-		}
+	stat->min = min(stat->min, value);
+	stat->max = max(stat->max, value);
 
-		/*
-		 * No samples
-		 */
-		if (!newest)
-			break;
-
-		if (newest > latest)
-			latest = newest;
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			hctx_for_each_ctx(hctx, ctx, j) {
-				if (ctx->stat[BLK_STAT_READ].time == newest) {
-					blk_stat_sum(&dst[BLK_STAT_READ],
-						     &ctx->stat[BLK_STAT_READ]);
-					nr++;
-				}
-				if (ctx->stat[BLK_STAT_WRITE].time == newest) {
-					blk_stat_sum(&dst[BLK_STAT_WRITE],
-						     &ctx->stat[BLK_STAT_WRITE]);
-					nr++;
-				}
-			}
-		}
-		/*
-		 * If we race on finding an entry, just loop back again.
-		 * Should be very rare.
-		 */
-	} while (!nr);
+	if (stat->batch + value < stat->batch ||
+	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
+		blk_stat_flush_batch(stat);
 
-	dst[BLK_STAT_READ].time = dst[BLK_STAT_WRITE].time = latest;
+	stat->batch += value;
+	stat->nr_batch++;
 }
 
-void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+void blk_stat_add(struct request *rq)
 {
-	if (q->mq_ops)
-		blk_mq_stat_get(q, dst);
-	else {
-		blk_stat_flush_batch(&q->rq_stats[BLK_STAT_READ]);
-		blk_stat_flush_batch(&q->rq_stats[BLK_STAT_WRITE]);
-		memcpy(&dst[BLK_STAT_READ], &q->rq_stats[BLK_STAT_READ],
-				sizeof(struct blk_rq_stat));
-		memcpy(&dst[BLK_STAT_WRITE], &q->rq_stats[BLK_STAT_WRITE],
-				sizeof(struct blk_rq_stat));
+	struct request_queue *q = rq->q;
+	struct blk_stat_callback *cb;
+	struct blk_rq_stat *stat;
+	int bucket;
+	s64 now, value;
+
+	now = __blk_stat_time(ktime_to_ns(ktime_get()));
+	if (now < blk_stat_time(&rq->issue_stat))
+		return;
+
+	value = now - blk_stat_time(&rq->issue_stat);
+
+	blk_throtl_stat_add(rq, value);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
+		if (blk_stat_is_active(cb)) {
+			bucket = cb->bucket_fn(rq);
+			if (bucket < 0)
+				continue;
+			stat = &this_cpu_ptr(cb->cpu_stat)[bucket];
+			__blk_stat_add(stat, value);
+		}
 	}
+	rcu_read_unlock();
 }
 
-void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst)
+static void blk_stat_timer_fn(unsigned long data)
 {
-	struct blk_mq_ctx *ctx;
-	unsigned int i, nr;
+	struct blk_stat_callback *cb = (void *)data;
+	unsigned int bucket;
+	int cpu;
 
-	nr = 0;
-	do {
-		uint64_t newest = 0;
+	for (bucket = 0; bucket < cb->buckets; bucket++)
+		blk_stat_init(&cb->stat[bucket]);
 
-		hctx_for_each_ctx(hctx, ctx, i) {
-			blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
-			blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
+	for_each_online_cpu(cpu) {
+		struct blk_rq_stat *cpu_stat;
 
-			if (!ctx->stat[BLK_STAT_READ].nr_samples &&
-			    !ctx->stat[BLK_STAT_WRITE].nr_samples)
-				continue;
-
-			if (ctx->stat[BLK_STAT_READ].time > newest)
-				newest = ctx->stat[BLK_STAT_READ].time;
-			if (ctx->stat[BLK_STAT_WRITE].time > newest)
-				newest = ctx->stat[BLK_STAT_WRITE].time;
+		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
+		for (bucket = 0; bucket < cb->buckets; bucket++) {
+			blk_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
+			blk_stat_init(&cpu_stat[bucket]);
 		}
+	}
 
-		if (!newest)
-			break;
-
-		hctx_for_each_ctx(hctx, ctx, i) {
-			if (ctx->stat[BLK_STAT_READ].time == newest) {
-				blk_stat_sum(&dst[BLK_STAT_READ],
-						&ctx->stat[BLK_STAT_READ]);
-				nr++;
-			}
-			if (ctx->stat[BLK_STAT_WRITE].time == newest) {
-				blk_stat_sum(&dst[BLK_STAT_WRITE],
-						&ctx->stat[BLK_STAT_WRITE]);
-				nr++;
-			}
-		}
-		/*
-		 * If we race on finding an entry, just loop back again.
-		 * Should be very rare, as the window is only updated
-		 * occasionally
-		 */
-	} while (!nr);
+	cb->timer_fn(cb);
 }
 
-static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
+struct blk_stat_callback *
+blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
+			int (*bucket_fn)(const struct request *),
+			unsigned int buckets, void *data)
 {
-	stat->min = -1ULL;
-	stat->max = stat->nr_samples = stat->mean = 0;
-	stat->batch = stat->nr_batch = 0;
-	stat->time = time_now & BLK_STAT_NSEC_MASK;
-}
+	struct blk_stat_callback *cb;
 
-void blk_stat_init(struct blk_rq_stat *stat)
-{
-	__blk_stat_init(stat, ktime_to_ns(ktime_get()));
-}
+	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
+	if (!cb)
+		return NULL;
 
-static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now)
-{
-	return (now & BLK_STAT_NSEC_MASK) == (stat->time & BLK_STAT_NSEC_MASK);
+	cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat),
+				 GFP_KERNEL);
+	if (!cb->stat) {
+		kfree(cb);
+		return NULL;
+	}
+	cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat),
+				      __alignof__(struct blk_rq_stat));
+	if (!cb->cpu_stat) {
+		kfree(cb->stat);
+		kfree(cb);
+		return NULL;
+	}
+
+	cb->timer_fn = timer_fn;
+	cb->bucket_fn = bucket_fn;
+	cb->data = data;
+	cb->buckets = buckets;
+	setup_timer(&cb->timer, blk_stat_timer_fn, (unsigned long)cb);
+
+	return cb;
 }
+EXPORT_SYMBOL_GPL(blk_stat_alloc_callback);
 
-bool blk_stat_is_current(struct blk_rq_stat *stat)
+void blk_stat_add_callback(struct request_queue *q,
+			   struct blk_stat_callback *cb)
 {
-	return __blk_stat_is_current(stat, ktime_to_ns(ktime_get()));
+	unsigned int bucket;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blk_rq_stat *cpu_stat;
+
+		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
+		for (bucket = 0; bucket < cb->buckets; bucket++)
+			blk_stat_init(&cpu_stat[bucket]);
+	}
+
+	spin_lock(&q->stats->lock);
+	list_add_tail_rcu(&cb->list, &q->stats->callbacks);
+	set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+	spin_unlock(&q->stats->lock);
 }
+EXPORT_SYMBOL_GPL(blk_stat_add_callback);
 
-void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
+void blk_stat_remove_callback(struct request_queue *q,
+			      struct blk_stat_callback *cb)
 {
-	s64 now, value;
+	spin_lock(&q->stats->lock);
+	list_del_rcu(&cb->list);
+	if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
+		clear_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+	spin_unlock(&q->stats->lock);
 
-	now = __blk_stat_time(ktime_to_ns(ktime_get()));
-	if (now < blk_stat_time(&rq->issue_stat))
-		return;
-
-	if (!__blk_stat_is_current(stat, now))
-		__blk_stat_init(stat, now);
+	del_timer_sync(&cb->timer);
+}
+EXPORT_SYMBOL_GPL(blk_stat_remove_callback);
 
-	value = now - blk_stat_time(&rq->issue_stat);
-	if (value > stat->max)
-		stat->max = value;
-	if (value < stat->min)
-		stat->min = value;
+static void blk_stat_free_callback_rcu(struct rcu_head *head)
+{
+	struct blk_stat_callback *cb;
 
-	if (stat->batch + value < stat->batch ||
-	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
-		blk_stat_flush_batch(stat);
+	cb = container_of(head, struct blk_stat_callback, rcu);
+	free_percpu(cb->cpu_stat);
+	kfree(cb->stat);
+	kfree(cb);
+}
 
-	stat->batch += value;
-	stat->nr_batch++;
+void blk_stat_free_callback(struct blk_stat_callback *cb)
+{
+	if (cb)
+		call_rcu(&cb->rcu, blk_stat_free_callback_rcu);
 }
+EXPORT_SYMBOL_GPL(blk_stat_free_callback);
 
-void blk_stat_clear(struct request_queue *q)
+void blk_stat_enable_accounting(struct request_queue *q)
 {
-	if (q->mq_ops) {
-		struct blk_mq_hw_ctx *hctx;
-		struct blk_mq_ctx *ctx;
-		int i, j;
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			hctx_for_each_ctx(hctx, ctx, j) {
-				blk_stat_init(&ctx->stat[BLK_STAT_READ]);
-				blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
-			}
-		}
-	} else {
-		blk_stat_init(&q->rq_stats[BLK_STAT_READ]);
-		blk_stat_init(&q->rq_stats[BLK_STAT_WRITE]);
-	}
+	spin_lock(&q->stats->lock);
+	q->stats->enable_accounting = true;
+	set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+	spin_unlock(&q->stats->lock);
 }
 
-void blk_stat_set_issue_time(struct blk_issue_stat *stat)
+struct blk_queue_stats *blk_alloc_queue_stats(void)
 {
-	stat->time = (stat->time & BLK_STAT_MASK) |
-			(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK);
+	struct blk_queue_stats *stats;
+
+	stats = kmalloc(sizeof(*stats), GFP_KERNEL);
+	if (!stats)
+		return NULL;
+
+	INIT_LIST_HEAD(&stats->callbacks);
+	spin_lock_init(&stats->lock);
+	stats->enable_accounting = false;
+
+	return stats;
 }
 
-/*
- * Enable stat tracking, return whether it was enabled
- */
-bool blk_stat_enable(struct request_queue *q)
+void blk_free_queue_stats(struct blk_queue_stats *stats)
 {
-	if (!test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
-		set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
-		return false;
-	}
+	if (!stats)
+		return;
+
+	WARN_ON(!list_empty(&stats->callbacks));
 
-	return true;
+	kfree(stats);
 }
diff --git a/block/blk-stat.h b/block/blk-stat.h
index a2050a0a5314..2fb20d1a341a 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -1,33 +1,85 @@
 #ifndef BLK_STAT_H
 #define BLK_STAT_H
 
-/*
- * ~0.13s window as a power-of-2 (2^27 nsecs)
- */
-#define BLK_STAT_NSEC		134217728ULL
-#define BLK_STAT_NSEC_MASK	~(BLK_STAT_NSEC - 1)
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/ktime.h>
+#include <linux/rcupdate.h>
+#include <linux/timer.h>
 
 /*
- * Upper 3 bits can be used elsewhere
+ * from upper:
+ * 3 bits: reserved for other usage
+ * 12 bits: size
+ * 49 bits: time
  */
 #define BLK_STAT_RES_BITS	3
-#define BLK_STAT_SHIFT		(64 - BLK_STAT_RES_BITS)
-#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SHIFT) - 1)
-#define BLK_STAT_MASK		~BLK_STAT_TIME_MASK
+#define BLK_STAT_SIZE_BITS	12
+#define BLK_STAT_RES_SHIFT	(64 - BLK_STAT_RES_BITS)
+#define BLK_STAT_SIZE_SHIFT	(BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS)
+#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SIZE_SHIFT) - 1)
+#define BLK_STAT_SIZE_MASK	\
+	(((1ULL << BLK_STAT_SIZE_BITS) - 1) << BLK_STAT_SIZE_SHIFT)
+#define BLK_STAT_RES_MASK	(~((1ULL << BLK_STAT_RES_SHIFT) - 1))
+
+/**
+ * struct blk_stat_callback - Block statistics callback.
+ *
+ * A &struct blk_stat_callback is associated with a &struct request_queue. While
+ * @timer is active, that queue's request completion latencies are sorted into
+ * buckets by @bucket_fn and added to a per-cpu buffer, @cpu_stat. When the
+ * timer fires, @cpu_stat is flushed to @stat and @timer_fn is invoked.
+ */
+struct blk_stat_callback {
+	/*
+	 * @list: RCU list of callbacks for a &struct request_queue.
+	 */
+	struct list_head list;
+
+	/**
+	 * @timer: Timer for the next callback invocation.
+	 */
+	struct timer_list timer;
+
+	/**
+	 * @cpu_stat: Per-cpu statistics buckets.
+	 */
+	struct blk_rq_stat __percpu *cpu_stat;
+
+	/**
+	 * @bucket_fn: Given a request, returns which statistics bucket it
+	 * should be accounted under. Return -1 for no bucket for this
+	 * request.
+	 */
+	int (*bucket_fn)(const struct request *);
+
+	/**
+	 * @buckets: Number of statistics buckets.
+	 */
+	unsigned int buckets;
+
+	/**
+	 * @stat: Array of statistics buckets.
+	 */
+	struct blk_rq_stat *stat;
+
+	/**
+	 * @fn: Callback function.
+	 */
+	void (*timer_fn)(struct blk_stat_callback *);
+
+	/**
+	 * @data: Private pointer for the user.
+	 */
+	void *data;
 
-enum {
-	BLK_STAT_READ	= 0,
-	BLK_STAT_WRITE,
+	struct rcu_head rcu;
 };
 
-void blk_stat_add(struct blk_rq_stat *, struct request *);
-void blk_hctx_stat_get(struct blk_mq_hw_ctx *, struct blk_rq_stat *);
-void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *);
-void blk_stat_clear(struct request_queue *);
-void blk_stat_init(struct blk_rq_stat *);
-bool blk_stat_is_current(struct blk_rq_stat *);
-void blk_stat_set_issue_time(struct blk_issue_stat *);
-bool blk_stat_enable(struct request_queue *);
+struct blk_queue_stats *blk_alloc_queue_stats(void);
+void blk_free_queue_stats(struct blk_queue_stats *);
+
+void blk_stat_add(struct request *);
 
 static inline u64 __blk_stat_time(u64 time)
 {
@@ -36,7 +88,117 @@ static inline u64 __blk_stat_time(u64 time)
 
 static inline u64 blk_stat_time(struct blk_issue_stat *stat)
 {
-	return __blk_stat_time(stat->time);
+	return __blk_stat_time(stat->stat);
+}
+
+static inline sector_t blk_capped_size(sector_t size)
+{
+	return size & ((1ULL << BLK_STAT_SIZE_BITS) - 1);
+}
+
+static inline sector_t blk_stat_size(struct blk_issue_stat *stat)
+{
+	return (stat->stat & BLK_STAT_SIZE_MASK) >> BLK_STAT_SIZE_SHIFT;
+}
+
+static inline void blk_stat_set_issue(struct blk_issue_stat *stat,
+	sector_t size)
+{
+	stat->stat = (stat->stat & BLK_STAT_RES_MASK) |
+		(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK) |
+		(((u64)blk_capped_size(size)) << BLK_STAT_SIZE_SHIFT);
+}
+
+/* record time/size info in request but not add a callback */
+void blk_stat_enable_accounting(struct request_queue *q);
+
+/**
+ * blk_stat_alloc_callback() - Allocate a block statistics callback.
+ * @timer_fn: Timer callback function.
+ * @bucket_fn: Bucket callback function.
+ * @buckets: Number of statistics buckets.
+ * @data: Value for the @data field of the &struct blk_stat_callback.
+ *
+ * See &struct blk_stat_callback for details on the callback functions.
+ *
+ * Return: &struct blk_stat_callback on success or NULL on ENOMEM.
+ */
+struct blk_stat_callback *
+blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
+			int (*bucket_fn)(const struct request *),
+			unsigned int buckets, void *data);
+
+/**
+ * blk_stat_add_callback() - Add a block statistics callback to be run on a
+ * request queue.
+ * @q: The request queue.
+ * @cb: The callback.
+ *
+ * Note that a single &struct blk_stat_callback can only be added to a single
+ * &struct request_queue.
+ */
+void blk_stat_add_callback(struct request_queue *q,
+			   struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_remove_callback() - Remove a block statistics callback from a
+ * request queue.
+ * @q: The request queue.
+ * @cb: The callback.
+ *
+ * When this returns, the callback is not running on any CPUs and will not be
+ * called again unless readded.
+ */
+void blk_stat_remove_callback(struct request_queue *q,
+			      struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_free_callback() - Free a block statistics callback.
+ * @cb: The callback.
+ *
+ * @cb may be NULL, in which case this does nothing. If it is not NULL, @cb must
+ * not be associated with a request queue. I.e., if it was previously added with
+ * blk_stat_add_callback(), it must also have been removed since then with
+ * blk_stat_remove_callback().
+ */
+void blk_stat_free_callback(struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_is_active() - Check if a block statistics callback is currently
+ * gathering statistics.
+ * @cb: The callback.
+ */
+static inline bool blk_stat_is_active(struct blk_stat_callback *cb)
+{
+	return timer_pending(&cb->timer);
+}
+
+/**
+ * blk_stat_activate_nsecs() - Gather block statistics during a time window in
+ * nanoseconds.
+ * @cb: The callback.
+ * @nsecs: Number of nanoseconds to gather statistics for.
+ *
+ * The timer callback will be called when the window expires.
+ */
+static inline void blk_stat_activate_nsecs(struct blk_stat_callback *cb,
+					   u64 nsecs)
+{
+	mod_timer(&cb->timer, jiffies + nsecs_to_jiffies(nsecs));
+}
+
+/**
+ * blk_stat_activate_msecs() - Gather block statistics during a time window in
+ * milliseconds.
+ * @cb: The callback.
+ * @msecs: Number of milliseconds to gather statistics for.
+ *
+ * The timer callback will be called when the window expires.
+ */
+static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb,
+					   unsigned int msecs)
+{
+	mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs));
 }
 
 #endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index c44b321335f3..3f37813ccbaf 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -208,7 +208,7 @@ static ssize_t queue_discard_max_store(struct request_queue *q,
 
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(queue_discard_zeroes_data(q), page);
+	return queue_var_show(0, page);
 }
 
 static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
@@ -503,26 +503,6 @@ static ssize_t queue_dax_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
-static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
-{
-	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
-			pre, (long long) stat->nr_samples,
-			(long long) stat->mean, (long long) stat->min,
-			(long long) stat->max);
-}
-
-static ssize_t queue_stats_show(struct request_queue *q, char *page)
-{
-	struct blk_rq_stat stat[2];
-	ssize_t ret;
-
-	blk_queue_stat_get(q, stat);
-
-	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
-	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
-	return ret;
-}
-
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -691,17 +671,20 @@ static struct queue_sysfs_entry queue_dax_entry = {
 	.show = queue_dax_show,
 };
 
-static struct queue_sysfs_entry queue_stats_entry = {
-	.attr = {.name = "stats", .mode = S_IRUGO },
-	.show = queue_stats_show,
-};
-
 static struct queue_sysfs_entry queue_wb_lat_entry = {
 	.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_wb_lat_show,
 	.store = queue_wb_lat_store,
 };
 
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static struct queue_sysfs_entry throtl_sample_time_entry = {
+	.attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR },
+	.show = blk_throtl_sample_time_show,
+	.store = blk_throtl_sample_time_store,
+};
+#endif
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -733,9 +716,11 @@ static struct attribute *default_attrs[] = {
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
-	&queue_stats_entry.attr,
 	&queue_wb_lat_entry.attr,
 	&queue_poll_delay_entry.attr,
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	&throtl_sample_time_entry.attr,
+#endif
 	NULL,
 };
 
@@ -810,15 +795,19 @@ static void blk_release_queue(struct kobject *kobj)
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
 
-	wbt_exit(q);
+	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+		blk_stat_remove_callback(q, q->poll_cb);
+	blk_stat_free_callback(q->poll_cb);
 	bdi_put(q->backing_dev_info);
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
 		ioc_clear_queue(q);
-		elevator_exit(q->elevator);
+		elevator_exit(q, q->elevator);
 	}
 
+	blk_free_queue_stats(q->stats);
+
 	blk_exit_rl(&q->root_rl);
 
 	if (q->queue_tags)
@@ -855,23 +844,6 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
-static void blk_wb_init(struct request_queue *q)
-{
-#ifndef CONFIG_BLK_WBT_MQ
-	if (q->mq_ops)
-		return;
-#endif
-#ifndef CONFIG_BLK_WBT_SQ
-	if (q->request_fn)
-		return;
-#endif
-
-	/*
-	 * If this fails, we don't get throttling
-	 */
-	wbt_init(q);
-}
-
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
@@ -881,6 +853,11 @@ int blk_register_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return -ENXIO;
 
+	WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags),
+		  "%s is registering an already registered queue\n",
+		  kobject_name(&dev->kobj));
+	queue_flag_set_unlocked(QUEUE_FLAG_REGISTERED, q);
+
 	/*
 	 * SCSI probing may synchronously create and destroy a lot of
 	 * request_queues for non-existent devices.  Shutting down a fully
@@ -900,9 +877,6 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
-	if (q->mq_ops)
-		blk_mq_register_dev(dev, q);
-
 	/* Prevent changes through sysfs until registration is completed. */
 	mutex_lock(&q->sysfs_lock);
 
@@ -912,9 +886,14 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	if (q->mq_ops)
+		__blk_mq_register_dev(dev, q);
+
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
-	blk_wb_init(q);
+	wbt_enable_default(q);
+
+	blk_throtl_register_queue(q);
 
 	if (q->request_fn || (q->mq_ops && q->elevator)) {
 		ret = elv_register_queue(q);
@@ -939,6 +918,11 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return;
 
+	queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q);
+
+	wbt_exit(q);
+
+
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 8fab716e4059..b78db2e5fdff 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -18,8 +18,17 @@ static int throtl_grp_quantum = 8;
 /* Total max dispatch from all groups in one round */
 static int throtl_quantum = 32;
 
-/* Throttling is performed over 100ms slice and after that slice is renewed */
-static unsigned long throtl_slice = HZ/10;	/* 100 ms */
+/* Throttling is performed over a slice and after that slice is renewed */
+#define DFL_THROTL_SLICE_HD (HZ / 10)
+#define DFL_THROTL_SLICE_SSD (HZ / 50)
+#define MAX_THROTL_SLICE (HZ)
+#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
+#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
+#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
+/* default latency target is 0, eg, guarantee IO latency by default */
+#define DFL_LATENCY_TARGET (0)
+
+#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
 
 static struct blkcg_policy blkcg_policy_throtl;
 
@@ -83,6 +92,12 @@ enum tg_state_flags {
 
 #define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
 
+enum {
+	LIMIT_LOW,
+	LIMIT_MAX,
+	LIMIT_CNT,
+};
+
 struct throtl_grp {
 	/* must be the first member */
 	struct blkg_policy_data pd;
@@ -119,20 +134,54 @@ struct throtl_grp {
 	/* are there any throtl rules between this group and td? */
 	bool has_rules[2];
 
-	/* bytes per second rate limits */
-	uint64_t bps[2];
+	/* internally used bytes per second rate limits */
+	uint64_t bps[2][LIMIT_CNT];
+	/* user configured bps limits */
+	uint64_t bps_conf[2][LIMIT_CNT];
 
-	/* IOPS limits */
-	unsigned int iops[2];
+	/* internally used IOPS limits */
+	unsigned int iops[2][LIMIT_CNT];
+	/* user configured IOPS limits */
+	unsigned int iops_conf[2][LIMIT_CNT];
 
 	/* Number of bytes disptached in current slice */
 	uint64_t bytes_disp[2];
 	/* Number of bio's dispatched in current slice */
 	unsigned int io_disp[2];
 
+	unsigned long last_low_overflow_time[2];
+
+	uint64_t last_bytes_disp[2];
+	unsigned int last_io_disp[2];
+
+	unsigned long last_check_time;
+
+	unsigned long latency_target; /* us */
 	/* When did we start a new slice */
 	unsigned long slice_start[2];
 	unsigned long slice_end[2];
+
+	unsigned long last_finish_time; /* ns / 1024 */
+	unsigned long checked_last_finish_time; /* ns / 1024 */
+	unsigned long avg_idletime; /* ns / 1024 */
+	unsigned long idletime_threshold; /* us */
+
+	unsigned int bio_cnt; /* total bios */
+	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
+	unsigned long bio_cnt_reset_time;
+};
+
+/* We measure latency for request size from <= 4k to >= 1M */
+#define LATENCY_BUCKET_SIZE 9
+
+struct latency_bucket {
+	unsigned long total_latency; /* ns / 1024 */
+	int samples;
+};
+
+struct avg_latency_bucket {
+	unsigned long latency; /* ns / 1024 */
+	bool valid;
 };
 
 struct throtl_data
@@ -145,8 +194,26 @@ struct throtl_data
 	/* Total Number of queued bios on READ and WRITE lists */
 	unsigned int nr_queued[2];
 
+	unsigned int throtl_slice;
+
 	/* Work for dispatching throttled bios */
 	struct work_struct dispatch_work;
+	unsigned int limit_index;
+	bool limit_valid[LIMIT_CNT];
+
+	unsigned long dft_idletime_threshold; /* us */
+
+	unsigned long low_upgrade_time;
+	unsigned long low_downgrade_time;
+
+	unsigned int scale;
+
+	struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
+	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
+	struct latency_bucket __percpu *latency_buckets;
+	unsigned long last_calculate_time;
+
+	bool track_bio_latency;
 };
 
 static void throtl_pending_timer_fn(unsigned long arg);
@@ -198,6 +265,76 @@ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
 		return container_of(sq, struct throtl_data, service_queue);
 }
 
+/*
+ * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to
+ * make the IO dispatch more smooth.
+ * Scale up: linearly scale up according to lapsed time since upgrade. For
+ *           every throtl_slice, the limit scales up 1/2 .low limit till the
+ *           limit hits .max limit
+ * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit
+ */
+static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td)
+{
+	/* arbitrary value to avoid too big scale */
+	if (td->scale < 4096 && time_after_eq(jiffies,
+	    td->low_upgrade_time + td->scale * td->throtl_slice))
+		td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice;
+
+	return low + (low >> 1) * td->scale;
+}
+
+static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
+{
+	struct blkcg_gq *blkg = tg_to_blkg(tg);
+	struct throtl_data *td;
+	uint64_t ret;
+
+	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
+		return U64_MAX;
+
+	td = tg->td;
+	ret = tg->bps[rw][td->limit_index];
+	if (ret == 0 && td->limit_index == LIMIT_LOW)
+		return tg->bps[rw][LIMIT_MAX];
+
+	if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
+	    tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
+		uint64_t adjusted;
+
+		adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td);
+		ret = min(tg->bps[rw][LIMIT_MAX], adjusted);
+	}
+	return ret;
+}
+
+static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
+{
+	struct blkcg_gq *blkg = tg_to_blkg(tg);
+	struct throtl_data *td;
+	unsigned int ret;
+
+	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
+		return UINT_MAX;
+	td = tg->td;
+	ret = tg->iops[rw][td->limit_index];
+	if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
+		return tg->iops[rw][LIMIT_MAX];
+
+	if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
+	    tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
+		uint64_t adjusted;
+
+		adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td);
+		if (adjusted > UINT_MAX)
+			adjusted = UINT_MAX;
+		ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted);
+	}
+	return ret;
+}
+
+#define request_bucket_index(sectors) \
+	clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1)
+
 /**
  * throtl_log - log debug message via blktrace
  * @sq: the service_queue being reported
@@ -334,10 +471,17 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
 	}
 
 	RB_CLEAR_NODE(&tg->rb_node);
-	tg->bps[READ] = -1;
-	tg->bps[WRITE] = -1;
-	tg->iops[READ] = -1;
-	tg->iops[WRITE] = -1;
+	tg->bps[READ][LIMIT_MAX] = U64_MAX;
+	tg->bps[WRITE][LIMIT_MAX] = U64_MAX;
+	tg->iops[READ][LIMIT_MAX] = UINT_MAX;
+	tg->iops[WRITE][LIMIT_MAX] = UINT_MAX;
+	tg->bps_conf[READ][LIMIT_MAX] = U64_MAX;
+	tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX;
+	tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX;
+	tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX;
+	/* LIMIT_LOW will have default value 0 */
+
+	tg->latency_target = DFL_LATENCY_TARGET;
 
 	return &tg->pd;
 }
@@ -366,6 +510,8 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
 		sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
 	tg->td = td;
+
+	tg->idletime_threshold = td->dft_idletime_threshold;
 }
 
 /*
@@ -376,20 +522,59 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 static void tg_update_has_rules(struct throtl_grp *tg)
 {
 	struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
+	struct throtl_data *td = tg->td;
 	int rw;
 
 	for (rw = READ; rw <= WRITE; rw++)
 		tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
-				    (tg->bps[rw] != -1 || tg->iops[rw] != -1);
+			(td->limit_valid[td->limit_index] &&
+			 (tg_bps_limit(tg, rw) != U64_MAX ||
+			  tg_iops_limit(tg, rw) != UINT_MAX));
 }
 
 static void throtl_pd_online(struct blkg_policy_data *pd)
 {
+	struct throtl_grp *tg = pd_to_tg(pd);
 	/*
 	 * We don't want new groups to escape the limits of its ancestors.
 	 * Update has_rules[] after a new group is brought online.
 	 */
-	tg_update_has_rules(pd_to_tg(pd));
+	tg_update_has_rules(tg);
+}
+
+static void blk_throtl_update_limit_valid(struct throtl_data *td)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+	bool low_valid = false;
+
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
+		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+			low_valid = true;
+	}
+	rcu_read_unlock();
+
+	td->limit_valid[LIMIT_LOW] = low_valid;
+}
+
+static void throtl_upgrade_state(struct throtl_data *td);
+static void throtl_pd_offline(struct blkg_policy_data *pd)
+{
+	struct throtl_grp *tg = pd_to_tg(pd);
+
+	tg->bps[READ][LIMIT_LOW] = 0;
+	tg->bps[WRITE][LIMIT_LOW] = 0;
+	tg->iops[READ][LIMIT_LOW] = 0;
+	tg->iops[WRITE][LIMIT_LOW] = 0;
+
+	blk_throtl_update_limit_valid(tg->td);
+
+	if (!tg->td->limit_valid[tg->td->limit_index])
+		throtl_upgrade_state(tg->td);
 }
 
 static void throtl_pd_free(struct blkg_policy_data *pd)
@@ -499,6 +684,17 @@ static void throtl_dequeue_tg(struct throtl_grp *tg)
 static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
 					  unsigned long expires)
 {
+	unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+
+	/*
+	 * Since we are adjusting the throttle limit dynamically, the sleep
+	 * time calculated according to previous limit might be invalid. It's
+	 * possible the cgroup sleep time is very long and no other cgroups
+	 * have IO running so notify the limit changes. Make sure the cgroup
+	 * doesn't sleep too long to avoid the missed notification.
+	 */
+	if (time_after(expires, max_expire))
+		expires = max_expire;
 	mod_timer(&sq->pending_timer, expires);
 	throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu",
 		   expires - jiffies, jiffies);
@@ -556,7 +752,7 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
 	if (time_after_eq(start, tg->slice_start[rw]))
 		tg->slice_start[rw] = start;
 
-	tg->slice_end[rw] = jiffies + throtl_slice;
+	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -568,7 +764,7 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 	tg->bytes_disp[rw] = 0;
 	tg->io_disp[rw] = 0;
 	tg->slice_start[rw] = jiffies;
-	tg->slice_end[rw] = jiffies + throtl_slice;
+	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -578,13 +774,13 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw,
 					unsigned long jiffy_end)
 {
-	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+	tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
 }
 
 static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw,
 				       unsigned long jiffy_end)
 {
-	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+	tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
 	throtl_log(&tg->service_queue,
 		   "[%c] extend slice start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -624,19 +820,20 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	 * is bad because it does not allow new slice to start.
 	 */
 
-	throtl_set_slice_end(tg, rw, jiffies + throtl_slice);
+	throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
 
 	time_elapsed = jiffies - tg->slice_start[rw];
 
-	nr_slices = time_elapsed / throtl_slice;
+	nr_slices = time_elapsed / tg->td->throtl_slice;
 
 	if (!nr_slices)
 		return;
-	tmp = tg->bps[rw] * throtl_slice * nr_slices;
+	tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
 	do_div(tmp, HZ);
 	bytes_trim = tmp;
 
-	io_trim = (tg->iops[rw] * throtl_slice * nr_slices)/HZ;
+	io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
+		HZ;
 
 	if (!bytes_trim && !io_trim)
 		return;
@@ -651,7 +848,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	else
 		tg->io_disp[rw] = 0;
 
-	tg->slice_start[rw] += nr_slices * throtl_slice;
+	tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
 
 	throtl_log(&tg->service_queue,
 		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
@@ -671,9 +868,9 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Slice has just started. Consider one slice interval */
 	if (!jiffy_elapsed)
-		jiffy_elapsed_rnd = throtl_slice;
+		jiffy_elapsed_rnd = tg->td->throtl_slice;
 
-	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 
 	/*
 	 * jiffy_elapsed_rnd should not be a big value as minimum iops can be
@@ -682,7 +879,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	 * have been trimmed.
 	 */
 
-	tmp = (u64)tg->iops[rw] * jiffy_elapsed_rnd;
+	tmp = (u64)tg_iops_limit(tg, rw) * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 
 	if (tmp > UINT_MAX)
@@ -697,7 +894,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	}
 
 	/* Calc approx time to dispatch */
-	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ)/tg->iops[rw] + 1;
+	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
 
 	if (jiffy_wait > jiffy_elapsed)
 		jiffy_wait = jiffy_wait - jiffy_elapsed;
@@ -720,11 +917,11 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Slice has just started. Consider one slice interval */
 	if (!jiffy_elapsed)
-		jiffy_elapsed_rnd = throtl_slice;
+		jiffy_elapsed_rnd = tg->td->throtl_slice;
 
-	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 
-	tmp = tg->bps[rw] * jiffy_elapsed_rnd;
+	tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
@@ -736,7 +933,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Calc approx time to dispatch */
 	extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
-	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+	jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
 
 	if (!jiffy_wait)
 		jiffy_wait = 1;
@@ -771,7 +968,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
 
 	/* If tg->bps = -1, then BW is unlimited */
-	if (tg->bps[rw] == -1 && tg->iops[rw] == -1) {
+	if (tg_bps_limit(tg, rw) == U64_MAX &&
+	    tg_iops_limit(tg, rw) == UINT_MAX) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -787,8 +985,10 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
 		throtl_start_new_slice(tg, rw);
 	else {
-		if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
-			throtl_extend_slice(tg, rw, jiffies + throtl_slice);
+		if (time_before(tg->slice_end[rw],
+		    jiffies + tg->td->throtl_slice))
+			throtl_extend_slice(tg, rw,
+				jiffies + tg->td->throtl_slice);
 	}
 
 	if (tg_with_in_bps_limit(tg, bio, &bps_wait) &&
@@ -816,6 +1016,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	/* Charge the bio to the group */
 	tg->bytes_disp[rw] += bio->bi_iter.bi_size;
 	tg->io_disp[rw]++;
+	tg->last_bytes_disp[rw] += bio->bi_iter.bi_size;
+	tg->last_io_disp[rw]++;
 
 	/*
 	 * BIO_THROTTLED is used to prevent the same bio to be throttled
@@ -999,6 +1201,8 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
 	return nr_disp;
 }
 
+static bool throtl_can_upgrade(struct throtl_data *td,
+	struct throtl_grp *this_tg);
 /**
  * throtl_pending_timer_fn - timer function for service_queue->pending_timer
  * @arg: the throtl_service_queue being serviced
@@ -1025,6 +1229,9 @@ static void throtl_pending_timer_fn(unsigned long arg)
 	int ret;
 
 	spin_lock_irq(q->queue_lock);
+	if (throtl_can_upgrade(td, NULL))
+		throtl_upgrade_state(td);
+
 again:
 	parent_sq = sq->parent_sq;
 	dispatched = false;
@@ -1112,7 +1319,7 @@ static u64 tg_prfill_conf_u64(struct seq_file *sf, struct blkg_policy_data *pd,
 	struct throtl_grp *tg = pd_to_tg(pd);
 	u64 v = *(u64 *)((void *)tg + off);
 
-	if (v == -1)
+	if (v == U64_MAX)
 		return 0;
 	return __blkg_prfill_u64(sf, pd, v);
 }
@@ -1123,7 +1330,7 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
 	struct throtl_grp *tg = pd_to_tg(pd);
 	unsigned int v = *(unsigned int *)((void *)tg + off);
 
-	if (v == -1)
+	if (v == UINT_MAX)
 		return 0;
 	return __blkg_prfill_u64(sf, pd, v);
 }
@@ -1150,8 +1357,8 @@ static void tg_conf_updated(struct throtl_grp *tg)
 
 	throtl_log(&tg->service_queue,
 		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",
-		   tg->bps[READ], tg->bps[WRITE],
-		   tg->iops[READ], tg->iops[WRITE]);
+		   tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
+		   tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));
 
 	/*
 	 * Update has_rules[] flags for the updated tg's subtree.  A tg is
@@ -1197,7 +1404,7 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of,
 	if (sscanf(ctx.body, "%llu", &v) != 1)
 		goto out_finish;
 	if (!v)
-		v = -1;
+		v = U64_MAX;
 
 	tg = blkg_to_tg(ctx.blkg);
 
@@ -1228,25 +1435,25 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
 static struct cftype throtl_legacy_files[] = {
 	{
 		.name = "throttle.read_bps_device",
-		.private = offsetof(struct throtl_grp, bps[READ]),
+		.private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]),
 		.seq_show = tg_print_conf_u64,
 		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.write_bps_device",
-		.private = offsetof(struct throtl_grp, bps[WRITE]),
+		.private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]),
 		.seq_show = tg_print_conf_u64,
 		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.read_iops_device",
-		.private = offsetof(struct throtl_grp, iops[READ]),
+		.private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]),
 		.seq_show = tg_print_conf_uint,
 		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.write_iops_device",
-		.private = offsetof(struct throtl_grp, iops[WRITE]),
+		.private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]),
 		.seq_show = tg_print_conf_uint,
 		.write = tg_set_conf_uint,
 	},
@@ -1263,48 +1470,87 @@ static struct cftype throtl_legacy_files[] = {
 	{ }	/* terminate */
 };
 
-static u64 tg_prfill_max(struct seq_file *sf, struct blkg_policy_data *pd,
+static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
 			 int off)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
 	const char *dname = blkg_dev_name(pd->blkg);
 	char bufs[4][21] = { "max", "max", "max", "max" };
+	u64 bps_dft;
+	unsigned int iops_dft;
+	char idle_time[26] = "";
+	char latency_time[26] = "";
 
 	if (!dname)
 		return 0;
-	if (tg->bps[READ] == -1 && tg->bps[WRITE] == -1 &&
-	    tg->iops[READ] == -1 && tg->iops[WRITE] == -1)
+
+	if (off == LIMIT_LOW) {
+		bps_dft = 0;
+		iops_dft = 0;
+	} else {
+		bps_dft = U64_MAX;
+		iops_dft = UINT_MAX;
+	}
+
+	if (tg->bps_conf[READ][off] == bps_dft &&
+	    tg->bps_conf[WRITE][off] == bps_dft &&
+	    tg->iops_conf[READ][off] == iops_dft &&
+	    tg->iops_conf[WRITE][off] == iops_dft &&
+	    (off != LIMIT_LOW ||
+	     (tg->idletime_threshold == tg->td->dft_idletime_threshold &&
+	      tg->latency_target == DFL_LATENCY_TARGET)))
 		return 0;
 
-	if (tg->bps[READ] != -1)
-		snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps[READ]);
-	if (tg->bps[WRITE] != -1)
-		snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps[WRITE]);
-	if (tg->iops[READ] != -1)
-		snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops[READ]);
-	if (tg->iops[WRITE] != -1)
-		snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops[WRITE]);
-
-	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s\n",
-		   dname, bufs[0], bufs[1], bufs[2], bufs[3]);
+	if (tg->bps_conf[READ][off] != bps_dft)
+		snprintf(bufs[0], sizeof(bufs[0]), "%llu",
+			tg->bps_conf[READ][off]);
+	if (tg->bps_conf[WRITE][off] != bps_dft)
+		snprintf(bufs[1], sizeof(bufs[1]), "%llu",
+			tg->bps_conf[WRITE][off]);
+	if (tg->iops_conf[READ][off] != iops_dft)
+		snprintf(bufs[2], sizeof(bufs[2]), "%u",
+			tg->iops_conf[READ][off]);
+	if (tg->iops_conf[WRITE][off] != iops_dft)
+		snprintf(bufs[3], sizeof(bufs[3]), "%u",
+			tg->iops_conf[WRITE][off]);
+	if (off == LIMIT_LOW) {
+		if (tg->idletime_threshold == ULONG_MAX)
+			strcpy(idle_time, " idle=max");
+		else
+			snprintf(idle_time, sizeof(idle_time), " idle=%lu",
+				tg->idletime_threshold);
+
+		if (tg->latency_target == ULONG_MAX)
+			strcpy(latency_time, " latency=max");
+		else
+			snprintf(latency_time, sizeof(latency_time),
+				" latency=%lu", tg->latency_target);
+	}
+
+	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
+		   dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time,
+		   latency_time);
 	return 0;
 }
 
-static int tg_print_max(struct seq_file *sf, void *v)
+static int tg_print_limit(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_max,
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit,
 			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static ssize_t tg_set_max(struct kernfs_open_file *of,
+static ssize_t tg_set_limit(struct kernfs_open_file *of,
 			  char *buf, size_t nbytes, loff_t off)
 {
 	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct throtl_grp *tg;
 	u64 v[4];
+	unsigned long idle_time;
+	unsigned long latency_time;
 	int ret;
+	int index = of_cft(of)->private;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
 	if (ret)
@@ -1312,15 +1558,17 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 
 	tg = blkg_to_tg(ctx.blkg);
 
-	v[0] = tg->bps[READ];
-	v[1] = tg->bps[WRITE];
-	v[2] = tg->iops[READ];
-	v[3] = tg->iops[WRITE];
+	v[0] = tg->bps_conf[READ][index];
+	v[1] = tg->bps_conf[WRITE][index];
+	v[2] = tg->iops_conf[READ][index];
+	v[3] = tg->iops_conf[WRITE][index];
 
+	idle_time = tg->idletime_threshold;
+	latency_time = tg->latency_target;
 	while (true) {
 		char tok[27];	/* wiops=18446744073709551616 */
 		char *p;
-		u64 val = -1;
+		u64 val = U64_MAX;
 		int len;
 
 		if (sscanf(ctx.body, "%26s%n", tok, &len) != 1)
@@ -1348,15 +1596,43 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 			v[2] = min_t(u64, val, UINT_MAX);
 		else if (!strcmp(tok, "wiops"))
 			v[3] = min_t(u64, val, UINT_MAX);
+		else if (off == LIMIT_LOW && !strcmp(tok, "idle"))
+			idle_time = val;
+		else if (off == LIMIT_LOW && !strcmp(tok, "latency"))
+			latency_time = val;
 		else
 			goto out_finish;
 	}
 
-	tg->bps[READ] = v[0];
-	tg->bps[WRITE] = v[1];
-	tg->iops[READ] = v[2];
-	tg->iops[WRITE] = v[3];
+	tg->bps_conf[READ][index] = v[0];
+	tg->bps_conf[WRITE][index] = v[1];
+	tg->iops_conf[READ][index] = v[2];
+	tg->iops_conf[WRITE][index] = v[3];
 
+	if (index == LIMIT_MAX) {
+		tg->bps[READ][index] = v[0];
+		tg->bps[WRITE][index] = v[1];
+		tg->iops[READ][index] = v[2];
+		tg->iops[WRITE][index] = v[3];
+	}
+	tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW],
+		tg->bps_conf[READ][LIMIT_MAX]);
+	tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW],
+		tg->bps_conf[WRITE][LIMIT_MAX]);
+	tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW],
+		tg->iops_conf[READ][LIMIT_MAX]);
+	tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
+		tg->iops_conf[WRITE][LIMIT_MAX]);
+
+	if (index == LIMIT_LOW) {
+		blk_throtl_update_limit_valid(tg->td);
+		if (tg->td->limit_valid[LIMIT_LOW])
+			tg->td->limit_index = LIMIT_LOW;
+		tg->idletime_threshold = (idle_time == ULONG_MAX) ?
+			ULONG_MAX : idle_time;
+		tg->latency_target = (latency_time == ULONG_MAX) ?
+			ULONG_MAX : latency_time;
+	}
 	tg_conf_updated(tg);
 	ret = 0;
 out_finish:
@@ -1365,11 +1641,21 @@ out_finish:
 }
 
 static struct cftype throtl_files[] = {
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	{
+		.name = "low",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = tg_print_limit,
+		.write = tg_set_limit,
+		.private = LIMIT_LOW,
+	},
+#endif
 	{
 		.name = "max",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.seq_show = tg_print_max,
-		.write = tg_set_max,
+		.seq_show = tg_print_limit,
+		.write = tg_set_limit,
+		.private = LIMIT_MAX,
 	},
 	{ }	/* terminate */
 };
@@ -1388,9 +1674,376 @@ static struct blkcg_policy blkcg_policy_throtl = {
 	.pd_alloc_fn		= throtl_pd_alloc,
 	.pd_init_fn		= throtl_pd_init,
 	.pd_online_fn		= throtl_pd_online,
+	.pd_offline_fn		= throtl_pd_offline,
 	.pd_free_fn		= throtl_pd_free,
 };
 
+static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+	unsigned long rtime = jiffies, wtime = jiffies;
+
+	if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW])
+		rtime = tg->last_low_overflow_time[READ];
+	if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+		wtime = tg->last_low_overflow_time[WRITE];
+	return min(rtime, wtime);
+}
+
+/* tg should not be an intermediate node */
+static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+	struct throtl_service_queue *parent_sq;
+	struct throtl_grp *parent = tg;
+	unsigned long ret = __tg_last_low_overflow_time(tg);
+
+	while (true) {
+		parent_sq = parent->service_queue.parent_sq;
+		parent = sq_to_tg(parent_sq);
+		if (!parent)
+			break;
+
+		/*
+		 * The parent doesn't have low limit, it always reaches low
+		 * limit. Its overflow time is useless for children
+		 */
+		if (!parent->bps[READ][LIMIT_LOW] &&
+		    !parent->iops[READ][LIMIT_LOW] &&
+		    !parent->bps[WRITE][LIMIT_LOW] &&
+		    !parent->iops[WRITE][LIMIT_LOW])
+			continue;
+		if (time_after(__tg_last_low_overflow_time(parent), ret))
+			ret = __tg_last_low_overflow_time(parent);
+	}
+	return ret;
+}
+
+static bool throtl_tg_is_idle(struct throtl_grp *tg)
+{
+	/*
+	 * cgroup is idle if:
+	 * - single idle is too long, longer than a fixed value (in case user
+	 *   configure a too big threshold) or 4 times of slice
+	 * - average think time is more than threshold
+	 * - IO latency is largely below threshold
+	 */
+	unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
+
+	time = min_t(unsigned long, MAX_IDLE_TIME, time);
+	return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+	       tg->avg_idletime > tg->idletime_threshold ||
+	       (tg->latency_target && tg->bio_cnt &&
+		tg->bad_bio_cnt * 5 < tg->bio_cnt);
+}
+
+static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
+{
+	struct throtl_service_queue *sq = &tg->service_queue;
+	bool read_limit, write_limit;
+
+	/*
+	 * if cgroup reaches low limit (if low limit is 0, the cgroup always
+	 * reaches), it's ok to upgrade to next limit
+	 */
+	read_limit = tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW];
+	write_limit = tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW];
+	if (!read_limit && !write_limit)
+		return true;
+	if (read_limit && sq->nr_queued[READ] &&
+	    (!write_limit || sq->nr_queued[WRITE]))
+		return true;
+	if (write_limit && sq->nr_queued[WRITE] &&
+	    (!read_limit || sq->nr_queued[READ]))
+		return true;
+
+	if (time_after_eq(jiffies,
+		tg_last_low_overflow_time(tg) + tg->td->throtl_slice) &&
+	    throtl_tg_is_idle(tg))
+		return true;
+	return false;
+}
+
+static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
+{
+	while (true) {
+		if (throtl_tg_can_upgrade(tg))
+			return true;
+		tg = sq_to_tg(tg->service_queue.parent_sq);
+		if (!tg || !tg_to_blkg(tg)->parent)
+			return false;
+	}
+	return false;
+}
+
+static bool throtl_can_upgrade(struct throtl_data *td,
+	struct throtl_grp *this_tg)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	if (td->limit_index != LIMIT_LOW)
+		return false;
+
+	if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice))
+		return false;
+
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		if (tg == this_tg)
+			continue;
+		if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+			continue;
+		if (!throtl_hierarchy_can_upgrade(tg)) {
+			rcu_read_unlock();
+			return false;
+		}
+	}
+	rcu_read_unlock();
+	return true;
+}
+
+static void throtl_upgrade_check(struct throtl_grp *tg)
+{
+	unsigned long now = jiffies;
+
+	if (tg->td->limit_index != LIMIT_LOW)
+		return;
+
+	if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
+		return;
+
+	tg->last_check_time = now;
+
+	if (!time_after_eq(now,
+	     __tg_last_low_overflow_time(tg) + tg->td->throtl_slice))
+		return;
+
+	if (throtl_can_upgrade(tg->td, NULL))
+		throtl_upgrade_state(tg->td);
+}
+
+static void throtl_upgrade_state(struct throtl_data *td)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	td->limit_index = LIMIT_MAX;
+	td->low_upgrade_time = jiffies;
+	td->scale = 0;
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+		struct throtl_service_queue *sq = &tg->service_queue;
+
+		tg->disptime = jiffies - 1;
+		throtl_select_dispatch(sq);
+		throtl_schedule_next_dispatch(sq, false);
+	}
+	rcu_read_unlock();
+	throtl_select_dispatch(&td->service_queue);
+	throtl_schedule_next_dispatch(&td->service_queue, false);
+	queue_work(kthrotld_workqueue, &td->dispatch_work);
+}
+
+static void throtl_downgrade_state(struct throtl_data *td, int new)
+{
+	td->scale /= 2;
+
+	if (td->scale) {
+		td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
+		return;
+	}
+
+	td->limit_index = new;
+	td->low_downgrade_time = jiffies;
+}
+
+static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
+{
+	struct throtl_data *td = tg->td;
+	unsigned long now = jiffies;
+
+	/*
+	 * If cgroup is below low limit, consider downgrade and throttle other
+	 * cgroups
+	 */
+	if (time_after_eq(now, td->low_upgrade_time + td->throtl_slice) &&
+	    time_after_eq(now, tg_last_low_overflow_time(tg) +
+					td->throtl_slice) &&
+	    (!throtl_tg_is_idle(tg) ||
+	     !list_empty(&tg_to_blkg(tg)->blkcg->css.children)))
+		return true;
+	return false;
+}
+
+static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg)
+{
+	while (true) {
+		if (!throtl_tg_can_downgrade(tg))
+			return false;
+		tg = sq_to_tg(tg->service_queue.parent_sq);
+		if (!tg || !tg_to_blkg(tg)->parent)
+			break;
+	}
+	return true;
+}
+
+static void throtl_downgrade_check(struct throtl_grp *tg)
+{
+	uint64_t bps;
+	unsigned int iops;
+	unsigned long elapsed_time;
+	unsigned long now = jiffies;
+
+	if (tg->td->limit_index != LIMIT_MAX ||
+	    !tg->td->limit_valid[LIMIT_LOW])
+		return;
+	if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+		return;
+	if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
+		return;
+
+	elapsed_time = now - tg->last_check_time;
+	tg->last_check_time = now;
+
+	if (time_before(now, tg_last_low_overflow_time(tg) +
+			tg->td->throtl_slice))
+		return;
+
+	if (tg->bps[READ][LIMIT_LOW]) {
+		bps = tg->last_bytes_disp[READ] * HZ;
+		do_div(bps, elapsed_time);
+		if (bps >= tg->bps[READ][LIMIT_LOW])
+			tg->last_low_overflow_time[READ] = now;
+	}
+
+	if (tg->bps[WRITE][LIMIT_LOW]) {
+		bps = tg->last_bytes_disp[WRITE] * HZ;
+		do_div(bps, elapsed_time);
+		if (bps >= tg->bps[WRITE][LIMIT_LOW])
+			tg->last_low_overflow_time[WRITE] = now;
+	}
+
+	if (tg->iops[READ][LIMIT_LOW]) {
+		iops = tg->last_io_disp[READ] * HZ / elapsed_time;
+		if (iops >= tg->iops[READ][LIMIT_LOW])
+			tg->last_low_overflow_time[READ] = now;
+	}
+
+	if (tg->iops[WRITE][LIMIT_LOW]) {
+		iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
+		if (iops >= tg->iops[WRITE][LIMIT_LOW])
+			tg->last_low_overflow_time[WRITE] = now;
+	}
+
+	/*
+	 * If cgroup is below low limit, consider downgrade and throttle other
+	 * cgroups
+	 */
+	if (throtl_hierarchy_can_downgrade(tg))
+		throtl_downgrade_state(tg->td, LIMIT_LOW);
+
+	tg->last_bytes_disp[READ] = 0;
+	tg->last_bytes_disp[WRITE] = 0;
+	tg->last_io_disp[READ] = 0;
+	tg->last_io_disp[WRITE] = 0;
+}
+
+static void blk_throtl_update_idletime(struct throtl_grp *tg)
+{
+	unsigned long now = ktime_get_ns() >> 10;
+	unsigned long last_finish_time = tg->last_finish_time;
+
+	if (now <= last_finish_time || last_finish_time == 0 ||
+	    last_finish_time == tg->checked_last_finish_time)
+		return;
+
+	tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3;
+	tg->checked_last_finish_time = last_finish_time;
+}
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static void throtl_update_latency_buckets(struct throtl_data *td)
+{
+	struct avg_latency_bucket avg_latency[LATENCY_BUCKET_SIZE];
+	int i, cpu;
+	unsigned long last_latency = 0;
+	unsigned long latency;
+
+	if (!blk_queue_nonrot(td->queue))
+		return;
+	if (time_before(jiffies, td->last_calculate_time + HZ))
+		return;
+	td->last_calculate_time = jiffies;
+
+	memset(avg_latency, 0, sizeof(avg_latency));
+	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+		struct latency_bucket *tmp = &td->tmp_buckets[i];
+
+		for_each_possible_cpu(cpu) {
+			struct latency_bucket *bucket;
+
+			/* this isn't race free, but ok in practice */
+			bucket = per_cpu_ptr(td->latency_buckets, cpu);
+			tmp->total_latency += bucket[i].total_latency;
+			tmp->samples += bucket[i].samples;
+			bucket[i].total_latency = 0;
+			bucket[i].samples = 0;
+		}
+
+		if (tmp->samples >= 32) {
+			int samples = tmp->samples;
+
+			latency = tmp->total_latency;
+
+			tmp->total_latency = 0;
+			tmp->samples = 0;
+			latency /= samples;
+			if (latency == 0)
+				continue;
+			avg_latency[i].latency = latency;
+		}
+	}
+
+	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+		if (!avg_latency[i].latency) {
+			if (td->avg_buckets[i].latency < last_latency)
+				td->avg_buckets[i].latency = last_latency;
+			continue;
+		}
+
+		if (!td->avg_buckets[i].valid)
+			latency = avg_latency[i].latency;
+		else
+			latency = (td->avg_buckets[i].latency * 7 +
+				avg_latency[i].latency) >> 3;
+
+		td->avg_buckets[i].latency = max(latency, last_latency);
+		td->avg_buckets[i].valid = true;
+		last_latency = td->avg_buckets[i].latency;
+	}
+}
+#else
+static inline void throtl_update_latency_buckets(struct throtl_data *td)
+{
+}
+#endif
+
+static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
+{
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	int ret;
+
+	ret = bio_associate_current(bio);
+	if (ret == 0 || ret == -EBUSY)
+		bio->bi_cg_private = tg;
+	blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio));
+#else
+	bio_associate_current(bio);
+#endif
+}
+
 bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 		    struct bio *bio)
 {
@@ -1399,6 +2052,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	struct throtl_service_queue *sq;
 	bool rw = bio_data_dir(bio);
 	bool throttled = false;
+	struct throtl_data *td = tg->td;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
@@ -1408,19 +2062,35 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 
 	spin_lock_irq(q->queue_lock);
 
+	throtl_update_latency_buckets(td);
+
 	if (unlikely(blk_queue_bypass(q)))
 		goto out_unlock;
 
+	blk_throtl_assoc_bio(tg, bio);
+	blk_throtl_update_idletime(tg);
+
 	sq = &tg->service_queue;
 
+again:
 	while (true) {
+		if (tg->last_low_overflow_time[rw] == 0)
+			tg->last_low_overflow_time[rw] = jiffies;
+		throtl_downgrade_check(tg);
+		throtl_upgrade_check(tg);
 		/* throtl is FIFO - if bios are already queued, should queue */
 		if (sq->nr_queued[rw])
 			break;
 
 		/* if above limits, break to queue */
-		if (!tg_may_dispatch(tg, bio, NULL))
+		if (!tg_may_dispatch(tg, bio, NULL)) {
+			tg->last_low_overflow_time[rw] = jiffies;
+			if (throtl_can_upgrade(td, tg)) {
+				throtl_upgrade_state(td);
+				goto again;
+			}
 			break;
+		}
 
 		/* within limits, let's charge and dispatch directly */
 		throtl_charge_bio(tg, bio);
@@ -1453,12 +2123,14 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	/* out-of-limit, queue to @tg */
 	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
 		   rw == READ ? 'R' : 'W',
-		   tg->bytes_disp[rw], bio->bi_iter.bi_size, tg->bps[rw],
-		   tg->io_disp[rw], tg->iops[rw],
+		   tg->bytes_disp[rw], bio->bi_iter.bi_size,
+		   tg_bps_limit(tg, rw),
+		   tg->io_disp[rw], tg_iops_limit(tg, rw),
 		   sq->nr_queued[READ], sq->nr_queued[WRITE]);
 
-	bio_associate_current(bio);
-	tg->td->nr_queued[rw]++;
+	tg->last_low_overflow_time[rw] = jiffies;
+
+	td->nr_queued[rw]++;
 	throtl_add_bio_tg(bio, qn, tg);
 	throttled = true;
 
@@ -1483,9 +2155,94 @@ out:
 	 */
 	if (!throttled)
 		bio_clear_flag(bio, BIO_THROTTLED);
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	if (throttled || !td->track_bio_latency)
+		bio->bi_issue_stat.stat |= SKIP_LATENCY;
+#endif
 	return throttled;
 }
 
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static void throtl_track_latency(struct throtl_data *td, sector_t size,
+	int op, unsigned long time)
+{
+	struct latency_bucket *latency;
+	int index;
+
+	if (!td || td->limit_index != LIMIT_LOW || op != REQ_OP_READ ||
+	    !blk_queue_nonrot(td->queue))
+		return;
+
+	index = request_bucket_index(size);
+
+	latency = get_cpu_ptr(td->latency_buckets);
+	latency[index].total_latency += time;
+	latency[index].samples++;
+	put_cpu_ptr(td->latency_buckets);
+}
+
+void blk_throtl_stat_add(struct request *rq, u64 time_ns)
+{
+	struct request_queue *q = rq->q;
+	struct throtl_data *td = q->td;
+
+	throtl_track_latency(td, blk_stat_size(&rq->issue_stat),
+		req_op(rq), time_ns >> 10);
+}
+
+void blk_throtl_bio_endio(struct bio *bio)
+{
+	struct throtl_grp *tg;
+	u64 finish_time_ns;
+	unsigned long finish_time;
+	unsigned long start_time;
+	unsigned long lat;
+
+	tg = bio->bi_cg_private;
+	if (!tg)
+		return;
+	bio->bi_cg_private = NULL;
+
+	finish_time_ns = ktime_get_ns();
+	tg->last_finish_time = finish_time_ns >> 10;
+
+	start_time = blk_stat_time(&bio->bi_issue_stat) >> 10;
+	finish_time = __blk_stat_time(finish_time_ns) >> 10;
+	if (!start_time || finish_time <= start_time)
+		return;
+
+	lat = finish_time - start_time;
+	/* this is only for bio based driver */
+	if (!(bio->bi_issue_stat.stat & SKIP_LATENCY))
+		throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
+			bio_op(bio), lat);
+
+	if (tg->latency_target) {
+		int bucket;
+		unsigned int threshold;
+
+		bucket = request_bucket_index(
+			blk_stat_size(&bio->bi_issue_stat));
+		threshold = tg->td->avg_buckets[bucket].latency +
+			tg->latency_target;
+		if (lat > threshold)
+			tg->bad_bio_cnt++;
+		/*
+		 * Not race free, could get wrong count, which means cgroups
+		 * will be throttled
+		 */
+		tg->bio_cnt++;
+	}
+
+	if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) {
+		tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies;
+		tg->bio_cnt /= 2;
+		tg->bad_bio_cnt /= 2;
+	}
+}
+#endif
+
 /*
  * Dispatch all bios from all children tg's queued on @parent_sq.  On
  * return, @parent_sq is guaranteed to not have any active children tg's
@@ -1558,6 +2315,12 @@ int blk_throtl_init(struct request_queue *q)
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
 	if (!td)
 		return -ENOMEM;
+	td->latency_buckets = __alloc_percpu(sizeof(struct latency_bucket) *
+		LATENCY_BUCKET_SIZE, __alignof__(u64));
+	if (!td->latency_buckets) {
+		kfree(td);
+		return -ENOMEM;
+	}
 
 	INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
 	throtl_service_queue_init(&td->service_queue);
@@ -1565,10 +2328,17 @@ int blk_throtl_init(struct request_queue *q)
 	q->td = td;
 	td->queue = q;
 
+	td->limit_valid[LIMIT_MAX] = true;
+	td->limit_index = LIMIT_MAX;
+	td->low_upgrade_time = jiffies;
+	td->low_downgrade_time = jiffies;
+
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
-	if (ret)
+	if (ret) {
+		free_percpu(td->latency_buckets);
 		kfree(td);
+	}
 	return ret;
 }
 
@@ -1577,9 +2347,74 @@ void blk_throtl_exit(struct request_queue *q)
 	BUG_ON(!q->td);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
+	free_percpu(q->td->latency_buckets);
 	kfree(q->td);
 }
 
+void blk_throtl_register_queue(struct request_queue *q)
+{
+	struct throtl_data *td;
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	td = q->td;
+	BUG_ON(!td);
+
+	if (blk_queue_nonrot(q)) {
+		td->throtl_slice = DFL_THROTL_SLICE_SSD;
+		td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_SSD;
+	} else {
+		td->throtl_slice = DFL_THROTL_SLICE_HD;
+		td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_HD;
+	}
+#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
+	/* if no low limit, use previous default */
+	td->throtl_slice = DFL_THROTL_SLICE_HD;
+#endif
+
+	td->track_bio_latency = !q->mq_ops && !q->request_fn;
+	if (!td->track_bio_latency)
+		blk_stat_enable_accounting(q);
+
+	/*
+	 * some tg are created before queue is fully initialized, eg, nonrot
+	 * isn't initialized yet
+	 */
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		tg->idletime_threshold = td->dft_idletime_threshold;
+	}
+	rcu_read_unlock();
+}
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page)
+{
+	if (!q->td)
+		return -EINVAL;
+	return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice));
+}
+
+ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+	const char *page, size_t count)
+{
+	unsigned long v;
+	unsigned long t;
+
+	if (!q->td)
+		return -EINVAL;
+	if (kstrtoul(page, 10, &v))
+		return -EINVAL;
+	t = msecs_to_jiffies(v);
+	if (t == 0 || t > MAX_THROTL_SLICE)
+		return -EINVAL;
+	q->td->throtl_slice = t;
+	return count;
+}
+#endif
+
 static int __init throtl_init(void)
 {
 	kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index a30441a200c0..cbff183f3d9f 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -89,7 +89,6 @@ static void blk_rq_timed_out(struct request *req)
 		ret = q->rq_timed_out_fn(req);
 	switch (ret) {
 	case BLK_EH_HANDLED:
-		/* Can we use req->errors here? */
 		__blk_complete_request(req);
 		break;
 	case BLK_EH_RESET_TIMER:
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 1aedb1f7ee0c..17676f4d7fd1 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -255,8 +255,8 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 	 * that it's writes impacting us, and not just some sole read on
 	 * a device that is in a lower power state.
 	 */
-	return stat[BLK_STAT_READ].nr_samples >= 1 &&
-		stat[BLK_STAT_WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES;
+	return (stat[READ].nr_samples >= 1 &&
+		stat[WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES);
 }
 
 static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
@@ -277,7 +277,7 @@ enum {
 	LAT_EXCEEDED,
 };
 
-static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
+static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
 	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 	u64 thislat;
@@ -293,7 +293,7 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 	 */
 	thislat = rwb_sync_issue_lat(rwb);
 	if (thislat > rwb->cur_win_nsec ||
-	    (thislat > rwb->min_lat_nsec && !stat[BLK_STAT_READ].nr_samples)) {
+	    (thislat > rwb->min_lat_nsec && !stat[READ].nr_samples)) {
 		trace_wbt_lat(bdi, thislat);
 		return LAT_EXCEEDED;
 	}
@@ -308,8 +308,8 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 		 * waited or still has writes in flights, consider us doing
 		 * just writes as well.
 		 */
-		if ((stat[BLK_STAT_WRITE].nr_samples && blk_stat_is_current(stat)) ||
-		    wb_recent_wait(rwb) || wbt_inflight(rwb))
+		if (stat[WRITE].nr_samples || wb_recent_wait(rwb) ||
+		    wbt_inflight(rwb))
 			return LAT_UNKNOWN_WRITES;
 		return LAT_UNKNOWN;
 	}
@@ -317,8 +317,8 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 	/*
 	 * If the 'min' latency exceeds our target, step down.
 	 */
-	if (stat[BLK_STAT_READ].min > rwb->min_lat_nsec) {
-		trace_wbt_lat(bdi, stat[BLK_STAT_READ].min);
+	if (stat[READ].min > rwb->min_lat_nsec) {
+		trace_wbt_lat(bdi, stat[READ].min);
 		trace_wbt_stat(bdi, stat);
 		return LAT_EXCEEDED;
 	}
@@ -329,14 +329,6 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 	return LAT_OK;
 }
 
-static int latency_exceeded(struct rq_wb *rwb)
-{
-	struct blk_rq_stat stat[2];
-
-	blk_queue_stat_get(rwb->queue, stat);
-	return __latency_exceeded(rwb, stat);
-}
-
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
 	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
@@ -355,7 +347,6 @@ static void scale_up(struct rq_wb *rwb)
 
 	rwb->scale_step--;
 	rwb->unknown_cnt = 0;
-	blk_stat_clear(rwb->queue);
 
 	rwb->scaled_max = calc_wb_limits(rwb);
 
@@ -385,15 +376,12 @@ static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 
 	rwb->scaled_max = false;
 	rwb->unknown_cnt = 0;
-	blk_stat_clear(rwb->queue);
 	calc_wb_limits(rwb);
 	rwb_trace_step(rwb, "step down");
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
 {
-	unsigned long expires;
-
 	if (rwb->scale_step > 0) {
 		/*
 		 * We should speed this up, using some variant of a fast
@@ -411,17 +399,16 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 		rwb->cur_win_nsec = rwb->win_nsec;
 	}
 
-	expires = jiffies + nsecs_to_jiffies(rwb->cur_win_nsec);
-	mod_timer(&rwb->window_timer, expires);
+	blk_stat_activate_nsecs(rwb->cb, rwb->cur_win_nsec);
 }
 
-static void wb_timer_fn(unsigned long data)
+static void wb_timer_fn(struct blk_stat_callback *cb)
 {
-	struct rq_wb *rwb = (struct rq_wb *) data;
+	struct rq_wb *rwb = cb->data;
 	unsigned int inflight = wbt_inflight(rwb);
 	int status;
 
-	status = latency_exceeded(rwb);
+	status = latency_exceeded(rwb, cb->stat);
 
 	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
 			inflight);
@@ -614,7 +601,7 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 
 	__wbt_wait(rwb, bio->bi_opf, lock);
 
-	if (!timer_pending(&rwb->window_timer))
+	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
 
 	if (current_is_kswapd())
@@ -666,22 +653,37 @@ void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
 		rwb->wc = write_cache_on;
 }
 
- /*
- * Disable wbt, if enabled by default. Only called from CFQ, if we have
- * cgroups enabled
+/*
+ * Disable wbt, if enabled by default. Only called from CFQ.
  */
 void wbt_disable_default(struct request_queue *q)
 {
 	struct rq_wb *rwb = q->rq_wb;
 
-	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT) {
-		del_timer_sync(&rwb->window_timer);
-		rwb->win_nsec = rwb->min_lat_nsec = 0;
-		wbt_update_limits(rwb);
-	}
+	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		wbt_exit(q);
 }
 EXPORT_SYMBOL_GPL(wbt_disable_default);
 
+/*
+ * Enable wbt if defaults are configured that way
+ */
+void wbt_enable_default(struct request_queue *q)
+{
+	/* Throttling already enabled? */
+	if (q->rq_wb)
+		return;
+
+	/* Queue not registered? Maybe shutting down... */
+	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+		return;
+
+	if ((q->mq_ops && IS_ENABLED(CONFIG_BLK_WBT_MQ)) ||
+	    (q->request_fn && IS_ENABLED(CONFIG_BLK_WBT_SQ)))
+		wbt_init(q);
+}
+EXPORT_SYMBOL_GPL(wbt_enable_default);
+
 u64 wbt_default_latency_nsec(struct request_queue *q)
 {
 	/*
@@ -694,29 +696,33 @@ u64 wbt_default_latency_nsec(struct request_queue *q)
 		return 75000000ULL;
 }
 
+static int wbt_data_dir(const struct request *rq)
+{
+	return rq_data_dir(rq);
+}
+
 int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
 	int i;
 
-	/*
-	 * For now, we depend on the stats window being larger than
-	 * our monitoring window. Ensure that this isn't inadvertently
-	 * violated.
-	 */
-	BUILD_BUG_ON(RWB_WINDOW_NSEC > BLK_STAT_NSEC);
 	BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
 
 	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
 	if (!rwb)
 		return -ENOMEM;
 
+	rwb->cb = blk_stat_alloc_callback(wb_timer_fn, wbt_data_dir, 2, rwb);
+	if (!rwb->cb) {
+		kfree(rwb);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < WBT_NUM_RWQ; i++) {
 		atomic_set(&rwb->rq_wait[i].inflight, 0);
 		init_waitqueue_head(&rwb->rq_wait[i].wait);
 	}
 
-	setup_timer(&rwb->window_timer, wb_timer_fn, (unsigned long) rwb);
 	rwb->wc = 1;
 	rwb->queue_depth = RWB_DEF_DEPTH;
 	rwb->last_comp = rwb->last_issue = jiffies;
@@ -726,10 +732,10 @@ int wbt_init(struct request_queue *q)
 	wbt_update_limits(rwb);
 
 	/*
-	 * Assign rwb, and turn on stats tracking for this queue
+	 * Assign rwb and add the stats callback.
 	 */
 	q->rq_wb = rwb;
-	blk_stat_enable(q);
+	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 
@@ -744,7 +750,8 @@ void wbt_exit(struct request_queue *q)
 	struct rq_wb *rwb = q->rq_wb;
 
 	if (rwb) {
-		del_timer_sync(&rwb->window_timer);
+		blk_stat_remove_callback(q, rwb->cb);
+		blk_stat_free_callback(rwb->cb);
 		q->rq_wb = NULL;
 		kfree(rwb);
 	}
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 65f1de519f67..df6de50c5d59 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -32,27 +32,27 @@ enum {
 
 static inline void wbt_clear_state(struct blk_issue_stat *stat)
 {
-	stat->time &= BLK_STAT_TIME_MASK;
+	stat->stat &= ~BLK_STAT_RES_MASK;
 }
 
 static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
 {
-	return (stat->time & BLK_STAT_MASK) >> BLK_STAT_SHIFT;
+	return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT;
 }
 
 static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
 {
-	stat->time |= ((u64) wb_acct) << BLK_STAT_SHIFT;
+	stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT;
 }
 
 static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
 {
-	return (stat->time >> BLK_STAT_SHIFT) & WBT_TRACKED;
+	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED;
 }
 
 static inline bool wbt_is_read(struct blk_issue_stat *stat)
 {
-	return (stat->time >> BLK_STAT_SHIFT) & WBT_READ;
+	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ;
 }
 
 struct rq_wait {
@@ -81,7 +81,7 @@ struct rq_wb {
 	u64 win_nsec;				/* default window size */
 	u64 cur_win_nsec;			/* current window size */
 
-	struct timer_list window_timer;
+	struct blk_stat_callback *cb;
 
 	s64 sync_issue;
 	void *sync_cookie;
@@ -117,6 +117,7 @@ void wbt_update_limits(struct rq_wb *);
 void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
 void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
 void wbt_disable_default(struct request_queue *);
+void wbt_enable_default(struct request_queue *);
 
 void wbt_set_queue_depth(struct rq_wb *, unsigned int);
 void wbt_set_write_cache(struct rq_wb *, bool);
@@ -155,6 +156,9 @@ static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
 static inline void wbt_disable_default(struct request_queue *q)
 {
 }
+static inline void wbt_enable_default(struct request_queue *q)
+{
+}
 static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
 {
 }
diff --git a/block/blk.h b/block/blk.h
index d1ea4bd9b9a3..2ed70228e44f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -60,15 +60,12 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
 void blk_exit_rl(struct request_list *rl);
-void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
 void blk_queue_bypass_end(struct request_queue *q);
 void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
-bool __blk_end_bidi_request(struct request *rq, int error,
-			    unsigned int nr_bytes, unsigned int bidi_bytes);
 void blk_freeze_queue(struct request_queue *q);
 
 static inline void blk_queue_enter_live(struct request_queue *q)
@@ -319,10 +316,22 @@ static inline struct io_context *create_io_context(gfp_t gfp_mask, int node)
 extern void blk_throtl_drain(struct request_queue *q);
 extern int blk_throtl_init(struct request_queue *q);
 extern void blk_throtl_exit(struct request_queue *q);
+extern void blk_throtl_register_queue(struct request_queue *q);
 #else /* CONFIG_BLK_DEV_THROTTLING */
 static inline void blk_throtl_drain(struct request_queue *q) { }
 static inline int blk_throtl_init(struct request_queue *q) { return 0; }
 static inline void blk_throtl_exit(struct request_queue *q) { }
+static inline void blk_throtl_register_queue(struct request_queue *q) { }
 #endif /* CONFIG_BLK_DEV_THROTTLING */
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
+extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+	const char *page, size_t count);
+extern void blk_throtl_bio_endio(struct bio *bio);
+extern void blk_throtl_stat_add(struct request *rq, u64 time);
+#else
+static inline void blk_throtl_bio_endio(struct bio *bio) { }
+static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
+#endif
 
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index cd15f9dbb147..0a23dbba2d30 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -37,7 +37,7 @@ static void bsg_destroy_job(struct kref *kref)
 	struct bsg_job *job = container_of(kref, struct bsg_job, kref);
 	struct request *rq = job->req;
 
-	blk_end_request_all(rq, rq->errors);
+	blk_end_request_all(rq, scsi_req(rq)->result);
 
 	put_device(job->dev);	/* release reference for the request */
 
@@ -74,7 +74,7 @@ void bsg_job_done(struct bsg_job *job, int result,
 	struct scsi_request *rq = scsi_req(req);
 	int err;
 
-	err = job->req->errors = result;
+	err = scsi_req(job->req)->result = result;
 	if (err < 0)
 		/* we're only returning the result field in the reply */
 		rq->sense_len = sizeof(u32);
@@ -177,7 +177,7 @@ failjob_rls_job:
  * @q: request queue to manage
  *
  * On error the create_bsg_job function should return a -Exyz error value
- * that will be set to the req->errors.
+ * that will be set to ->result.
  *
  * Drivers/subsys should pass this to the queue init function.
  */
@@ -201,7 +201,7 @@ static void bsg_request_fn(struct request_queue *q)
 
 		ret = bsg_create_job(dev, req);
 		if (ret) {
-			req->errors = ret;
+			scsi_req(req)->result = ret;
 			blk_end_request_all(req, ret);
 			spin_lock_irq(q->queue_lock);
 			continue;
diff --git a/block/bsg.c b/block/bsg.c
index 74835dbf0c47..6fd08544d77e 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -391,13 +391,13 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
-	dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
+	dprintk("rq %p bio %p 0x%x\n", rq, bio, req->result);
 	/*
 	 * fill in all the output members
 	 */
-	hdr->device_status = rq->errors & 0xff;
-	hdr->transport_status = host_byte(rq->errors);
-	hdr->driver_status = driver_byte(rq->errors);
+	hdr->device_status = req->result & 0xff;
+	hdr->transport_status = host_byte(req->result);
+	hdr->driver_status = driver_byte(req->result);
 	hdr->info = 0;
 	if (hdr->device_status || hdr->transport_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
@@ -431,8 +431,8 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	 * just a protocol response (i.e. non negative), that gets
 	 * processed above.
 	 */
-	if (!ret && rq->errors < 0)
-		ret = rq->errors;
+	if (!ret && req->result < 0)
+		ret = req->result;
 
 	blk_rq_unmap_user(bio);
 	scsi_req_free_cmd(req);
@@ -650,7 +650,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 
 	dprintk("%s: write %zd bytes\n", bd->name, count);
 
-	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+	if (unlikely(uaccess_kernel()))
 		return -EINVAL;
 
 	bsg_set_block(bd, file);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 440b95ee593c..da69b079725f 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3761,16 +3761,14 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
 	uint64_t serial_nr;
-	bool nonroot_cg;
 
 	rcu_read_lock();
 	serial_nr = bio_blkcg(bio)->css.serial_nr;
-	nonroot_cg = bio_blkcg(bio) != &blkcg_root;
 	rcu_read_unlock();
 
 	/*
@@ -3778,7 +3776,7 @@ static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	 * spuriously on a newly created cic but there's no harm.
 	 */
 	if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
-		return nonroot_cg;
+		return;
 
 	/*
 	 * Drop reference to queues.  New queues will be assigned in new
@@ -3799,12 +3797,10 @@ static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	}
 
 	cic->blkcg_serial_nr = serial_nr;
-	return nonroot_cg;
 }
 #else
-static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
-	return false;
 }
 #endif  /* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -4449,12 +4445,11 @@ cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio,
 	const int rw = rq_data_dir(rq);
 	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
-	bool disable_wbt;
 
 	spin_lock_irq(q->queue_lock);
 
 	check_ioprio_changed(cic, bio);
-	disable_wbt = check_blkcg_changed(cic, bio);
+	check_blkcg_changed(cic, bio);
 new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
 	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
@@ -4491,9 +4486,6 @@ new_queue:
 	rq->elv.priv[1] = cfqq->cfqg;
 	spin_unlock_irq(q->queue_lock);
 
-	if (disable_wbt)
-		wbt_disable_default(q);
-
 	return 0;
 }
 
@@ -4706,6 +4698,7 @@ static void cfq_registered_queue(struct request_queue *q)
 	 */
 	if (blk_queue_nonrot(q))
 		cfqd->cfq_slice_idle = 0;
+	wbt_disable_default(q);
 }
 
 /*
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 570021a0dc1c..04325b81c2b4 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -685,7 +685,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKALIGNOFF:
 		return compat_put_int(arg, bdev_alignment_offset(bdev));
 	case BLKDISCARDZEROES:
-		return compat_put_uint(arg, bdev_discard_zeroes_data(bdev));
+		return compat_put_uint(arg, 0);
 	case BLKFLSBUF:
 	case BLKROSET:
 	case BLKDISCARD:
diff --git a/block/elevator.c b/block/elevator.c
index 01139f549b5b..bf11e70f008b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -41,6 +41,7 @@
 
 #include "blk.h"
 #include "blk-mq-sched.h"
+#include "blk-wbt.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -242,26 +243,21 @@ int elevator_init(struct request_queue *q, char *name)
 		}
 	}
 
-	if (e->uses_mq) {
-		err = blk_mq_sched_setup(q);
-		if (!err)
-			err = e->ops.mq.init_sched(q, e);
-	} else
+	if (e->uses_mq)
+		err = blk_mq_init_sched(q, e);
+	else
 		err = e->ops.sq.elevator_init_fn(q, e);
-	if (err) {
-		if (e->uses_mq)
-			blk_mq_sched_teardown(q);
+	if (err)
 		elevator_put(e);
-	}
 	return err;
 }
 EXPORT_SYMBOL(elevator_init);
 
-void elevator_exit(struct elevator_queue *e)
+void elevator_exit(struct request_queue *q, struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
 	if (e->uses_mq && e->type->ops.mq.exit_sched)
-		e->type->ops.mq.exit_sched(e);
+		blk_mq_exit_sched(q, e);
 	else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
 		e->type->ops.sq.elevator_exit_fn(e);
 	mutex_unlock(&e->sysfs_lock);
@@ -882,6 +878,8 @@ void elv_unregister_queue(struct request_queue *q)
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
 		kobject_del(&e->kobj);
 		e->registered = 0;
+		/* Re-enable throttling in case elevator disabled it */
+		wbt_enable_default(q);
 	}
 }
 EXPORT_SYMBOL(elv_unregister_queue);
@@ -946,6 +944,45 @@ void elv_unregister(struct elevator_type *e)
 }
 EXPORT_SYMBOL_GPL(elv_unregister);
 
+static int elevator_switch_mq(struct request_queue *q,
+			      struct elevator_type *new_e)
+{
+	int ret;
+
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
+
+	if (q->elevator) {
+		if (q->elevator->registered)
+			elv_unregister_queue(q);
+		ioc_clear_queue(q);
+		elevator_exit(q, q->elevator);
+	}
+
+	ret = blk_mq_init_sched(q, new_e);
+	if (ret)
+		goto out;
+
+	if (new_e) {
+		ret = elv_register_queue(q);
+		if (ret) {
+			elevator_exit(q, q->elevator);
+			goto out;
+		}
+	}
+
+	if (new_e)
+		blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	else
+		blk_add_trace_msg(q, "elv switch: none");
+
+out:
+	blk_mq_unfreeze_queue(q);
+	blk_mq_start_stopped_hw_queues(q, true);
+	return ret;
+
+}
+
 /*
  * switch to new_e io scheduler. be careful not to introduce deadlocks -
  * we don't free the old io scheduler, before we have allocated what we
@@ -958,10 +995,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	bool old_registered = false;
 	int err;
 
-	if (q->mq_ops) {
-		blk_mq_freeze_queue(q);
-		blk_mq_quiesce_queue(q);
-	}
+	if (q->mq_ops)
+		return elevator_switch_mq(q, new_e);
 
 	/*
 	 * Turn on BYPASS and drain all requests w/ elevator private data.
@@ -973,11 +1008,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	if (old) {
 		old_registered = old->registered;
 
-		if (old->uses_mq)
-			blk_mq_sched_teardown(q);
-
-		if (!q->mq_ops)
-			blk_queue_bypass_start(q);
+		blk_queue_bypass_start(q);
 
 		/* unregister and clear all auxiliary data of the old elevator */
 		if (old_registered)
@@ -987,56 +1018,32 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	}
 
 	/* allocate, init and register new elevator */
-	if (new_e) {
-		if (new_e->uses_mq) {
-			err = blk_mq_sched_setup(q);
-			if (!err)
-				err = new_e->ops.mq.init_sched(q, new_e);
-		} else
-			err = new_e->ops.sq.elevator_init_fn(q, new_e);
-		if (err)
-			goto fail_init;
+	err = new_e->ops.sq.elevator_init_fn(q, new_e);
+	if (err)
+		goto fail_init;
 
-		err = elv_register_queue(q);
-		if (err)
-			goto fail_register;
-	} else
-		q->elevator = NULL;
+	err = elv_register_queue(q);
+	if (err)
+		goto fail_register;
 
 	/* done, kill the old one and finish */
 	if (old) {
-		elevator_exit(old);
-		if (!q->mq_ops)
-			blk_queue_bypass_end(q);
+		elevator_exit(q, old);
+		blk_queue_bypass_end(q);
 	}
 
-	if (q->mq_ops) {
-		blk_mq_unfreeze_queue(q);
-		blk_mq_start_stopped_hw_queues(q, true);
-	}
-
-	if (new_e)
-		blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
-	else
-		blk_add_trace_msg(q, "elv switch: none");
+	blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
 
 	return 0;
 
 fail_register:
-	if (q->mq_ops)
-		blk_mq_sched_teardown(q);
-	elevator_exit(q->elevator);
+	elevator_exit(q, q->elevator);
 fail_init:
 	/* switch failed, restore and re-register old elevator */
 	if (old) {
 		q->elevator = old;
 		elv_register_queue(q);
-		if (!q->mq_ops)
-			blk_queue_bypass_end(q);
-	}
-	if (q->mq_ops) {
-		blk_mq_unfreeze_queue(q);
-		blk_mq_start_stopped_hw_queues(q, true);
+		blk_queue_bypass_end(q);
 	}
 
 	return err;
@@ -1094,12 +1101,20 @@ int elevator_change(struct request_queue *q, const char *name)
 }
 EXPORT_SYMBOL(elevator_change);
 
+static inline bool elv_support_iosched(struct request_queue *q)
+{
+	if (q->mq_ops && q->tag_set && (q->tag_set->flags &
+				BLK_MQ_F_NO_SCHED))
+		return false;
+	return true;
+}
+
 ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 			  size_t count)
 {
 	int ret;
 
-	if (!(q->mq_ops || q->request_fn))
+	if (!(q->mq_ops || q->request_fn) || !elv_support_iosched(q))
 		return count;
 
 	ret = __elevator_change(q, name);
@@ -1131,7 +1146,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name)
 			len += sprintf(name+len, "[%s] ", elv->elevator_name);
 			continue;
 		}
-		if (__e->uses_mq && q->mq_ops)
+		if (__e->uses_mq && q->mq_ops && elv_support_iosched(q))
 			len += sprintf(name+len, "%s ", __e->elevator_name);
 		else if (!__e->uses_mq && !q->mq_ops)
 			len += sprintf(name+len, "%s ", __e->elevator_name);
diff --git a/block/genhd.c b/block/genhd.c
index b26a5ea115d0..d252d29fe837 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -271,16 +271,17 @@ void blkdev_show(struct seq_file *seqf, off_t offset)
 /**
  * register_blkdev - register a new block device
  *
- * @major: the requested major device number [1..255]. If @major=0, try to
+ * @major: the requested major device number [1..255]. If @major = 0, try to
  *         allocate any unused major number.
  * @name: the name of the new block device as a zero terminated string
  *
  * The @name must be unique within the system.
  *
- * The return value depends on the @major input parameter.
+ * The return value depends on the @major input parameter:
+ *
  *  - if a major device number was requested in range [1..255] then the
  *    function returns zero on success, or a negative error code
- *  - if any unused major number was requested with @major=0 parameter
+ *  - if any unused major number was requested with @major = 0 parameter
  *    then the return value is the allocated major number in range
  *    [1..255] or a negative error code otherwise
  */
@@ -572,20 +573,6 @@ exit:
 	disk_part_iter_exit(&piter);
 }
 
-void put_disk_devt(struct disk_devt *disk_devt)
-{
-	if (disk_devt && atomic_dec_and_test(&disk_devt->count))
-		disk_devt->release(disk_devt);
-}
-EXPORT_SYMBOL(put_disk_devt);
-
-void get_disk_devt(struct disk_devt *disk_devt)
-{
-	if (disk_devt)
-		atomic_inc(&disk_devt->count);
-}
-EXPORT_SYMBOL(get_disk_devt);
-
 /**
  * device_add_disk - add partitioning information to kernel list
  * @parent: parent device for the disk
@@ -626,13 +613,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 
 	disk_alloc_events(disk);
 
-	/*
-	 * Take a reference on the devt and assign it to queue since it
-	 * must not be reallocated while the bdi is registered
-	 */
-	disk->queue->disk_devt = disk->disk_devt;
-	get_disk_devt(disk->disk_devt);
-
 	/* Register BDI before referencing it from bdev */
 	bdi = disk->queue->backing_dev_info;
 	bdi_register_owner(bdi, disk_to_dev(disk));
@@ -681,12 +661,16 @@ void del_gendisk(struct gendisk *disk)
 	disk->flags &= ~GENHD_FL_UP;
 
 	sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
-	/*
-	 * Unregister bdi before releasing device numbers (as they can get
-	 * reused and we'd get clashes in sysfs).
-	 */
-	bdi_unregister(disk->queue->backing_dev_info);
-	blk_unregister_queue(disk);
+	if (disk->queue) {
+		/*
+		 * Unregister bdi before releasing device numbers (as they can
+		 * get reused and we'd get clashes in sysfs).
+		 */
+		bdi_unregister(disk->queue->backing_dev_info);
+		blk_unregister_queue(disk);
+	} else {
+		WARN_ON(1);
+	}
 	blk_unregister_region(disk_devt(disk), disk->minors);
 
 	part_stat_set_all(&disk->part0, 0);
@@ -1077,8 +1061,19 @@ static struct attribute *disk_attrs[] = {
 	NULL
 };
 
+static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (a == &dev_attr_badblocks.attr && !disk->bb)
+		return 0;
+	return a->mode;
+}
+
 static struct attribute_group disk_attr_group = {
 	.attrs = disk_attrs,
+	.is_visible = disk_visible,
 };
 
 static const struct attribute_group *disk_attr_groups[] = {
@@ -1369,7 +1364,7 @@ struct kobject *get_disk(struct gendisk *disk)
 	owner = disk->fops->owner;
 	if (owner && !try_module_get(owner))
 		return NULL;
-	kobj = kobject_get(&disk_to_dev(disk)->kobj);
+	kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj);
 	if (kobj == NULL) {
 		module_put(owner);
 		return NULL;
diff --git a/block/ioctl.c b/block/ioctl.c
index 7b88820b93d9..0de02ee67eed 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -255,7 +255,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 	truncate_inode_pages_range(mapping, start, end);
 
 	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
-				    false);
+			BLKDEV_ZERO_NOUNMAP);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)
@@ -547,7 +547,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKALIGNOFF:
 		return put_int(arg, bdev_alignment_offset(bdev));
 	case BLKDISCARDZEROES:
-		return put_uint(arg, bdev_discard_zeroes_data(bdev));
+		return put_uint(arg, 0);
 	case BLKSECTGET:
 		max_sectors = min_t(unsigned int, USHRT_MAX,
 				    queue_max_sectors(bdev_get_queue(bdev)));
diff --git a/block/ioprio.c b/block/ioprio.c
index 0c47a00f92a8..4b120c9cf7e8 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -163,22 +163,12 @@ out:
 
 int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
-	unsigned short aclass;
-	unsigned short bclass;
-
 	if (!ioprio_valid(aprio))
 		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 	if (!ioprio_valid(bprio))
 		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 
-	aclass = IOPRIO_PRIO_CLASS(aprio);
-	bclass = IOPRIO_PRIO_CLASS(bprio);
-	if (aclass == bclass)
-		return min(aprio, bprio);
-	if (aclass > bclass)
-		return bprio;
-	else
-		return aprio;
+	return min(aprio, bprio);
 }
 
 SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
new file mode 100644
index 000000000000..3b0090bc5dd1
--- /dev/null
+++ b/block/kyber-iosched.c
@@ -0,0 +1,719 @@
+/*
+ * The Kyber I/O scheduler. Controls latency by throttling queue depths using
+ * scalable techniques.
+ *
+ * Copyright (C) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/elevator.h>
+#include <linux/module.h>
+#include <linux/sbitmap.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-sched.h"
+#include "blk-mq-tag.h"
+#include "blk-stat.h"
+
+/* Scheduling domains. */
+enum {
+	KYBER_READ,
+	KYBER_SYNC_WRITE,
+	KYBER_OTHER, /* Async writes, discard, etc. */
+	KYBER_NUM_DOMAINS,
+};
+
+enum {
+	KYBER_MIN_DEPTH = 256,
+
+	/*
+	 * In order to prevent starvation of synchronous requests by a flood of
+	 * asynchronous requests, we reserve 25% of requests for synchronous
+	 * operations.
+	 */
+	KYBER_ASYNC_PERCENT = 75,
+};
+
+/*
+ * Initial device-wide depths for each scheduling domain.
+ *
+ * Even for fast devices with lots of tags like NVMe, you can saturate
+ * the device with only a fraction of the maximum possible queue depth.
+ * So, we cap these to a reasonable value.
+ */
+static const unsigned int kyber_depth[] = {
+	[KYBER_READ] = 256,
+	[KYBER_SYNC_WRITE] = 128,
+	[KYBER_OTHER] = 64,
+};
+
+/*
+ * Scheduling domain batch sizes. We favor reads.
+ */
+static const unsigned int kyber_batch_size[] = {
+	[KYBER_READ] = 16,
+	[KYBER_SYNC_WRITE] = 8,
+	[KYBER_OTHER] = 8,
+};
+
+struct kyber_queue_data {
+	struct request_queue *q;
+
+	struct blk_stat_callback *cb;
+
+	/*
+	 * The device is divided into multiple scheduling domains based on the
+	 * request type. Each domain has a fixed number of in-flight requests of
+	 * that type device-wide, limited by these tokens.
+	 */
+	struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS];
+
+	/*
+	 * Async request percentage, converted to per-word depth for
+	 * sbitmap_get_shallow().
+	 */
+	unsigned int async_depth;
+
+	/* Target latencies in nanoseconds. */
+	u64 read_lat_nsec, write_lat_nsec;
+};
+
+struct kyber_hctx_data {
+	spinlock_t lock;
+	struct list_head rqs[KYBER_NUM_DOMAINS];
+	unsigned int cur_domain;
+	unsigned int batching;
+	wait_queue_t domain_wait[KYBER_NUM_DOMAINS];
+	atomic_t wait_index[KYBER_NUM_DOMAINS];
+};
+
+static int rq_sched_domain(const struct request *rq)
+{
+	unsigned int op = rq->cmd_flags;
+
+	if ((op & REQ_OP_MASK) == REQ_OP_READ)
+		return KYBER_READ;
+	else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op))
+		return KYBER_SYNC_WRITE;
+	else
+		return KYBER_OTHER;
+}
+
+enum {
+	NONE = 0,
+	GOOD = 1,
+	GREAT = 2,
+	BAD = -1,
+	AWFUL = -2,
+};
+
+#define IS_GOOD(status) ((status) > 0)
+#define IS_BAD(status) ((status) < 0)
+
+static int kyber_lat_status(struct blk_stat_callback *cb,
+			    unsigned int sched_domain, u64 target)
+{
+	u64 latency;
+
+	if (!cb->stat[sched_domain].nr_samples)
+		return NONE;
+
+	latency = cb->stat[sched_domain].mean;
+	if (latency >= 2 * target)
+		return AWFUL;
+	else if (latency > target)
+		return BAD;
+	else if (latency <= target / 2)
+		return GREAT;
+	else /* (latency <= target) */
+		return GOOD;
+}
+
+/*
+ * Adjust the read or synchronous write depth given the status of reads and
+ * writes. The goal is that the latencies of the two domains are fair (i.e., if
+ * one is good, then the other is good).
+ */
+static void kyber_adjust_rw_depth(struct kyber_queue_data *kqd,
+				  unsigned int sched_domain, int this_status,
+				  int other_status)
+{
+	unsigned int orig_depth, depth;
+
+	/*
+	 * If this domain had no samples, or reads and writes are both good or
+	 * both bad, don't adjust the depth.
+	 */
+	if (this_status == NONE ||
+	    (IS_GOOD(this_status) && IS_GOOD(other_status)) ||
+	    (IS_BAD(this_status) && IS_BAD(other_status)))
+		return;
+
+	orig_depth = depth = kqd->domain_tokens[sched_domain].sb.depth;
+
+	if (other_status == NONE) {
+		depth++;
+	} else {
+		switch (this_status) {
+		case GOOD:
+			if (other_status == AWFUL)
+				depth -= max(depth / 4, 1U);
+			else
+				depth -= max(depth / 8, 1U);
+			break;
+		case GREAT:
+			if (other_status == AWFUL)
+				depth /= 2;
+			else
+				depth -= max(depth / 4, 1U);
+			break;
+		case BAD:
+			depth++;
+			break;
+		case AWFUL:
+			if (other_status == GREAT)
+				depth += 2;
+			else
+				depth++;
+			break;
+		}
+	}
+
+	depth = clamp(depth, 1U, kyber_depth[sched_domain]);
+	if (depth != orig_depth)
+		sbitmap_queue_resize(&kqd->domain_tokens[sched_domain], depth);
+}
+
+/*
+ * Adjust the depth of other requests given the status of reads and synchronous
+ * writes. As long as either domain is doing fine, we don't throttle, but if
+ * both domains are doing badly, we throttle heavily.
+ */
+static void kyber_adjust_other_depth(struct kyber_queue_data *kqd,
+				     int read_status, int write_status,
+				     bool have_samples)
+{
+	unsigned int orig_depth, depth;
+	int status;
+
+	orig_depth = depth = kqd->domain_tokens[KYBER_OTHER].sb.depth;
+
+	if (read_status == NONE && write_status == NONE) {
+		depth += 2;
+	} else if (have_samples) {
+		if (read_status == NONE)
+			status = write_status;
+		else if (write_status == NONE)
+			status = read_status;
+		else
+			status = max(read_status, write_status);
+		switch (status) {
+		case GREAT:
+			depth += 2;
+			break;
+		case GOOD:
+			depth++;
+			break;
+		case BAD:
+			depth -= max(depth / 4, 1U);
+			break;
+		case AWFUL:
+			depth /= 2;
+			break;
+		}
+	}
+
+	depth = clamp(depth, 1U, kyber_depth[KYBER_OTHER]);
+	if (depth != orig_depth)
+		sbitmap_queue_resize(&kqd->domain_tokens[KYBER_OTHER], depth);
+}
+
+/*
+ * Apply heuristics for limiting queue depths based on gathered latency
+ * statistics.
+ */
+static void kyber_stat_timer_fn(struct blk_stat_callback *cb)
+{
+	struct kyber_queue_data *kqd = cb->data;
+	int read_status, write_status;
+
+	read_status = kyber_lat_status(cb, KYBER_READ, kqd->read_lat_nsec);
+	write_status = kyber_lat_status(cb, KYBER_SYNC_WRITE, kqd->write_lat_nsec);
+
+	kyber_adjust_rw_depth(kqd, KYBER_READ, read_status, write_status);
+	kyber_adjust_rw_depth(kqd, KYBER_SYNC_WRITE, write_status, read_status);
+	kyber_adjust_other_depth(kqd, read_status, write_status,
+				 cb->stat[KYBER_OTHER].nr_samples != 0);
+
+	/*
+	 * Continue monitoring latencies if we aren't hitting the targets or
+	 * we're still throttling other requests.
+	 */
+	if (!blk_stat_is_active(kqd->cb) &&
+	    ((IS_BAD(read_status) || IS_BAD(write_status) ||
+	      kqd->domain_tokens[KYBER_OTHER].sb.depth < kyber_depth[KYBER_OTHER])))
+		blk_stat_activate_msecs(kqd->cb, 100);
+}
+
+static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd)
+{
+	/*
+	 * All of the hardware queues have the same depth, so we can just grab
+	 * the shift of the first one.
+	 */
+	return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
+}
+
+static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
+{
+	struct kyber_queue_data *kqd;
+	unsigned int max_tokens;
+	unsigned int shift;
+	int ret = -ENOMEM;
+	int i;
+
+	kqd = kmalloc_node(sizeof(*kqd), GFP_KERNEL, q->node);
+	if (!kqd)
+		goto err;
+	kqd->q = q;
+
+	kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain,
+					  KYBER_NUM_DOMAINS, kqd);
+	if (!kqd->cb)
+		goto err_kqd;
+
+	/*
+	 * The maximum number of tokens for any scheduling domain is at least
+	 * the queue depth of a single hardware queue. If the hardware doesn't
+	 * have many tags, still provide a reasonable number.
+	 */
+	max_tokens = max_t(unsigned int, q->tag_set->queue_depth,
+			   KYBER_MIN_DEPTH);
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		WARN_ON(!kyber_depth[i]);
+		WARN_ON(!kyber_batch_size[i]);
+		ret = sbitmap_queue_init_node(&kqd->domain_tokens[i],
+					      max_tokens, -1, false, GFP_KERNEL,
+					      q->node);
+		if (ret) {
+			while (--i >= 0)
+				sbitmap_queue_free(&kqd->domain_tokens[i]);
+			goto err_cb;
+		}
+		sbitmap_queue_resize(&kqd->domain_tokens[i], kyber_depth[i]);
+	}
+
+	shift = kyber_sched_tags_shift(kqd);
+	kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U;
+
+	kqd->read_lat_nsec = 2000000ULL;
+	kqd->write_lat_nsec = 10000000ULL;
+
+	return kqd;
+
+err_cb:
+	blk_stat_free_callback(kqd->cb);
+err_kqd:
+	kfree(kqd);
+err:
+	return ERR_PTR(ret);
+}
+
+static int kyber_init_sched(struct request_queue *q, struct elevator_type *e)
+{
+	struct kyber_queue_data *kqd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	kqd = kyber_queue_data_alloc(q);
+	if (IS_ERR(kqd)) {
+		kobject_put(&eq->kobj);
+		return PTR_ERR(kqd);
+	}
+
+	eq->elevator_data = kqd;
+	q->elevator = eq;
+
+	blk_stat_add_callback(q, kqd->cb);
+
+	return 0;
+}
+
+static void kyber_exit_sched(struct elevator_queue *e)
+{
+	struct kyber_queue_data *kqd = e->elevator_data;
+	struct request_queue *q = kqd->q;
+	int i;
+
+	blk_stat_remove_callback(q, kqd->cb);
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+		sbitmap_queue_free(&kqd->domain_tokens[i]);
+	blk_stat_free_callback(kqd->cb);
+	kfree(kqd);
+}
+
+static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	struct kyber_hctx_data *khd;
+	int i;
+
+	khd = kmalloc_node(sizeof(*khd), GFP_KERNEL, hctx->numa_node);
+	if (!khd)
+		return -ENOMEM;
+
+	spin_lock_init(&khd->lock);
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		INIT_LIST_HEAD(&khd->rqs[i]);
+		INIT_LIST_HEAD(&khd->domain_wait[i].task_list);
+		atomic_set(&khd->wait_index[i], 0);
+	}
+
+	khd->cur_domain = 0;
+	khd->batching = 0;
+
+	hctx->sched_data = khd;
+
+	return 0;
+}
+
+static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	kfree(hctx->sched_data);
+}
+
+static int rq_get_domain_token(struct request *rq)
+{
+	return (long)rq->elv.priv[0];
+}
+
+static void rq_set_domain_token(struct request *rq, int token)
+{
+	rq->elv.priv[0] = (void *)(long)token;
+}
+
+static void rq_clear_domain_token(struct kyber_queue_data *kqd,
+				  struct request *rq)
+{
+	unsigned int sched_domain;
+	int nr;
+
+	nr = rq_get_domain_token(rq);
+	if (nr != -1) {
+		sched_domain = rq_sched_domain(rq);
+		sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr,
+				    rq->mq_ctx->cpu);
+	}
+}
+
+static struct request *kyber_get_request(struct request_queue *q,
+					 unsigned int op,
+					 struct blk_mq_alloc_data *data)
+{
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+	struct request *rq;
+
+	/*
+	 * We use the scheduler tags as per-hardware queue queueing tokens.
+	 * Async requests can be limited at this stage.
+	 */
+	if (!op_is_sync(op))
+		data->shallow_depth = kqd->async_depth;
+
+	rq = __blk_mq_alloc_request(data, op);
+	if (rq)
+		rq_set_domain_token(rq, -1);
+	return rq;
+}
+
+static void kyber_put_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+
+	rq_clear_domain_token(kqd, rq);
+	blk_mq_finish_request(rq);
+}
+
+static void kyber_completed_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+	unsigned int sched_domain;
+	u64 now, latency, target;
+
+	/*
+	 * Check if this request met our latency goal. If not, quickly gather
+	 * some statistics and start throttling.
+	 */
+	sched_domain = rq_sched_domain(rq);
+	switch (sched_domain) {
+	case KYBER_READ:
+		target = kqd->read_lat_nsec;
+		break;
+	case KYBER_SYNC_WRITE:
+		target = kqd->write_lat_nsec;
+		break;
+	default:
+		return;
+	}
+
+	/* If we are already monitoring latencies, don't check again. */
+	if (blk_stat_is_active(kqd->cb))
+		return;
+
+	now = __blk_stat_time(ktime_to_ns(ktime_get()));
+	if (now < blk_stat_time(&rq->issue_stat))
+		return;
+
+	latency = now - blk_stat_time(&rq->issue_stat);
+
+	if (latency > target)
+		blk_stat_activate_msecs(kqd->cb, 10);
+}
+
+static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
+				  struct blk_mq_hw_ctx *hctx)
+{
+	LIST_HEAD(rq_list);
+	struct request *rq, *next;
+
+	blk_mq_flush_busy_ctxs(hctx, &rq_list);
+	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
+		unsigned int sched_domain;
+
+		sched_domain = rq_sched_domain(rq);
+		list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]);
+	}
+}
+
+static int kyber_domain_wake(wait_queue_t *wait, unsigned mode, int flags,
+			     void *key)
+{
+	struct blk_mq_hw_ctx *hctx = READ_ONCE(wait->private);
+
+	list_del_init(&wait->task_list);
+	blk_mq_run_hw_queue(hctx, true);
+	return 1;
+}
+
+static int kyber_get_domain_token(struct kyber_queue_data *kqd,
+				  struct kyber_hctx_data *khd,
+				  struct blk_mq_hw_ctx *hctx)
+{
+	unsigned int sched_domain = khd->cur_domain;
+	struct sbitmap_queue *domain_tokens = &kqd->domain_tokens[sched_domain];
+	wait_queue_t *wait = &khd->domain_wait[sched_domain];
+	struct sbq_wait_state *ws;
+	int nr;
+
+	nr = __sbitmap_queue_get(domain_tokens);
+	if (nr >= 0)
+		return nr;
+
+	/*
+	 * If we failed to get a domain token, make sure the hardware queue is
+	 * run when one becomes available. Note that this is serialized on
+	 * khd->lock, but we still need to be careful about the waker.
+	 */
+	if (list_empty_careful(&wait->task_list)) {
+		init_waitqueue_func_entry(wait, kyber_domain_wake);
+		wait->private = hctx;
+		ws = sbq_wait_ptr(domain_tokens,
+				  &khd->wait_index[sched_domain]);
+		add_wait_queue(&ws->wait, wait);
+
+		/*
+		 * Try again in case a token was freed before we got on the wait
+		 * queue.
+		 */
+		nr = __sbitmap_queue_get(domain_tokens);
+	}
+	return nr;
+}
+
+static struct request *
+kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
+			  struct kyber_hctx_data *khd,
+			  struct blk_mq_hw_ctx *hctx,
+			  bool *flushed)
+{
+	struct list_head *rqs;
+	struct request *rq;
+	int nr;
+
+	rqs = &khd->rqs[khd->cur_domain];
+	rq = list_first_entry_or_null(rqs, struct request, queuelist);
+
+	/*
+	 * If there wasn't already a pending request and we haven't flushed the
+	 * software queues yet, flush the software queues and check again.
+	 */
+	if (!rq && !*flushed) {
+		kyber_flush_busy_ctxs(khd, hctx);
+		*flushed = true;
+		rq = list_first_entry_or_null(rqs, struct request, queuelist);
+	}
+
+	if (rq) {
+		nr = kyber_get_domain_token(kqd, khd, hctx);
+		if (nr >= 0) {
+			khd->batching++;
+			rq_set_domain_token(rq, nr);
+			list_del_init(&rq->queuelist);
+			return rq;
+		}
+	}
+
+	/* There were either no pending requests or no tokens. */
+	return NULL;
+}
+
+static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	bool flushed = false;
+	struct request *rq;
+	int i;
+
+	spin_lock(&khd->lock);
+
+	/*
+	 * First, if we are still entitled to batch, try to dispatch a request
+	 * from the batch.
+	 */
+	if (khd->batching < kyber_batch_size[khd->cur_domain]) {
+		rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+		if (rq)
+			goto out;
+	}
+
+	/*
+	 * Either,
+	 * 1. We were no longer entitled to a batch.
+	 * 2. The domain we were batching didn't have any requests.
+	 * 3. The domain we were batching was out of tokens.
+	 *
+	 * Start another batch. Note that this wraps back around to the original
+	 * domain if no other domains have requests or tokens.
+	 */
+	khd->batching = 0;
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		if (khd->cur_domain == KYBER_NUM_DOMAINS - 1)
+			khd->cur_domain = 0;
+		else
+			khd->cur_domain++;
+
+		rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+		if (rq)
+			goto out;
+	}
+
+	rq = NULL;
+out:
+	spin_unlock(&khd->lock);
+	return rq;
+}
+
+static bool kyber_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	int i;
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		if (!list_empty_careful(&khd->rqs[i]))
+			return true;
+	}
+	return false;
+}
+
+#define KYBER_LAT_SHOW_STORE(op)					\
+static ssize_t kyber_##op##_lat_show(struct elevator_queue *e,		\
+				     char *page)			\
+{									\
+	struct kyber_queue_data *kqd = e->elevator_data;		\
+									\
+	return sprintf(page, "%llu\n", kqd->op##_lat_nsec);		\
+}									\
+									\
+static ssize_t kyber_##op##_lat_store(struct elevator_queue *e,		\
+				      const char *page, size_t count)	\
+{									\
+	struct kyber_queue_data *kqd = e->elevator_data;		\
+	unsigned long long nsec;					\
+	int ret;							\
+									\
+	ret = kstrtoull(page, 10, &nsec);				\
+	if (ret)							\
+		return ret;						\
+									\
+	kqd->op##_lat_nsec = nsec;					\
+									\
+	return count;							\
+}
+KYBER_LAT_SHOW_STORE(read);
+KYBER_LAT_SHOW_STORE(write);
+#undef KYBER_LAT_SHOW_STORE
+
+#define KYBER_LAT_ATTR(op) __ATTR(op##_lat_nsec, 0644, kyber_##op##_lat_show, kyber_##op##_lat_store)
+static struct elv_fs_entry kyber_sched_attrs[] = {
+	KYBER_LAT_ATTR(read),
+	KYBER_LAT_ATTR(write),
+	__ATTR_NULL
+};
+#undef KYBER_LAT_ATTR
+
+static struct elevator_type kyber_sched = {
+	.ops.mq = {
+		.init_sched = kyber_init_sched,
+		.exit_sched = kyber_exit_sched,
+		.init_hctx = kyber_init_hctx,
+		.exit_hctx = kyber_exit_hctx,
+		.get_request = kyber_get_request,
+		.put_request = kyber_put_request,
+		.completed_request = kyber_completed_request,
+		.dispatch_request = kyber_dispatch_request,
+		.has_work = kyber_has_work,
+	},
+	.uses_mq = true,
+	.elevator_attrs = kyber_sched_attrs,
+	.elevator_name = "kyber",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init kyber_init(void)
+{
+	return elv_register(&kyber_sched);
+}
+
+static void __exit kyber_exit(void)
+{
+	elv_unregister(&kyber_sched);
+}
+
+module_init(kyber_init);
+module_exit(kyber_exit);
+
+MODULE_AUTHOR("Omar Sandoval");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Kyber I/O scheduler");
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 7afb9907821f..0171a2faad68 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -497,7 +497,6 @@ rescan:
 
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	check_disk_size_change(disk, bdev);
 	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 2a2fc768b27a..4a294a5f7fab 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -262,11 +262,11 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	/*
 	 * fill in all the output members
 	 */
-	hdr->status = rq->errors & 0xff;
-	hdr->masked_status = status_byte(rq->errors);
-	hdr->msg_status = msg_byte(rq->errors);
-	hdr->host_status = host_byte(rq->errors);
-	hdr->driver_status = driver_byte(rq->errors);
+	hdr->status = req->result & 0xff;
+	hdr->masked_status = status_byte(req->result);
+	hdr->msg_status = msg_byte(req->result);
+	hdr->host_status = host_byte(req->result);
+	hdr->driver_status = driver_byte(req->result);
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
@@ -362,7 +362,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		goto out_free_cdb;
 
 	bio = rq->bio;
-	rq->retries = 0;
+	req->retries = 0;
 
 	start_time = jiffies;
 
@@ -476,13 +476,13 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		goto error;
 
 	/* default.  possible overriden later */
-	rq->retries = 5;
+	req->retries = 5;
 
 	switch (opcode) {
 	case SEND_DIAGNOSTIC:
 	case FORMAT_UNIT:
 		rq->timeout = FORMAT_UNIT_TIMEOUT;
-		rq->retries = 1;
+		req->retries = 1;
 		break;
 	case START_STOP:
 		rq->timeout = START_STOP_TIMEOUT;
@@ -495,7 +495,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		break;
 	case READ_DEFECT_DATA:
 		rq->timeout = READ_DEFECT_DATA_TIMEOUT;
-		rq->retries = 1;
+		req->retries = 1;
 		break;
 	default:
 		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
@@ -509,7 +509,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	blk_execute_rq(q, disk, rq, 0);
 
-	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
+	err = req->result & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
 		if (req->sense_len && req->sense) {
 			bytes = (OMAX_SB_LEN > req->sense_len) ?
@@ -547,7 +547,8 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	scsi_req(rq)->cmd[0] = cmd;
 	scsi_req(rq)->cmd[4] = data;
 	scsi_req(rq)->cmd_len = 6;
-	err = blk_execute_rq(q, bd_disk, rq, 0);
+	blk_execute_rq(q, bd_disk, rq, 0);
+	err = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 
 	return err;
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 1e18dca360fc..9b30ae5ab843 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -275,8 +275,8 @@ static bool check_tper(const void *data)
 	u8 flags = tper->supported_features;
 
 	if (!(flags & TPER_SYNC_SUPPORTED)) {
-		pr_err("TPer sync not supported. flags = %d\n",
-		       tper->supported_features);
+		pr_debug("TPer sync not supported. flags = %d\n",
+			 tper->supported_features);
 		return false;
 	}
 
@@ -289,7 +289,7 @@ static bool check_sum(const void *data)
 	u32 nlo = be32_to_cpu(sum->num_locking_objects);
 
 	if (nlo == 0) {
-		pr_err("Need at least one locking object.\n");
+		pr_debug("Need at least one locking object.\n");
 		return false;
 	}
 
@@ -385,9 +385,9 @@ static int next(struct opal_dev *dev)
 
 		error = step->fn(dev, step->data);
 		if (error) {
-			pr_err("Error on step function: %d with error %d: %s\n",
-			       state, error,
-			       opal_error_to_human(error));
+			pr_debug("Error on step function: %d with error %d: %s\n",
+				 state, error,
+				 opal_error_to_human(error));
 
 			/* For each OPAL command we do a discovery0 then we
 			 * start some sort of session.
@@ -419,8 +419,8 @@ static int opal_discovery0_end(struct opal_dev *dev)
 	print_buffer(dev->resp, hlen);
 
 	if (hlen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
-		pr_warn("Discovery length overflows buffer (%zu+%u)/%u\n",
-			sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
+		pr_debug("Discovery length overflows buffer (%zu+%u)/%u\n",
+			 sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
 		return -EFAULT;
 	}
 
@@ -503,7 +503,7 @@ static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
 	if (*err)
 		return;
 	if (cmd->pos >= IO_BUFFER_LENGTH - 1) {
-		pr_err("Error adding u8: end of buffer.\n");
+		pr_debug("Error adding u8: end of buffer.\n");
 		*err = -ERANGE;
 		return;
 	}
@@ -553,7 +553,7 @@ static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
 	len = DIV_ROUND_UP(msb, 4);
 
 	if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) {
-		pr_err("Error adding u64: end of buffer.\n");
+		pr_debug("Error adding u64: end of buffer.\n");
 		*err = -ERANGE;
 		return;
 	}
@@ -579,7 +579,7 @@ static void add_token_bytestring(int *err, struct opal_dev *cmd,
 	}
 
 	if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) {
-		pr_err("Error adding bytestring: end of buffer.\n");
+		pr_debug("Error adding bytestring: end of buffer.\n");
 		*err = -ERANGE;
 		return;
 	}
@@ -597,7 +597,7 @@ static void add_token_bytestring(int *err, struct opal_dev *cmd,
 static int build_locking_range(u8 *buffer, size_t length, u8 lr)
 {
 	if (length > OPAL_UID_LENGTH) {
-		pr_err("Can't build locking range. Length OOB\n");
+		pr_debug("Can't build locking range. Length OOB\n");
 		return -ERANGE;
 	}
 
@@ -614,7 +614,7 @@ static int build_locking_range(u8 *buffer, size_t length, u8 lr)
 static int build_locking_user(u8 *buffer, size_t length, u8 lr)
 {
 	if (length > OPAL_UID_LENGTH) {
-		pr_err("Can't build locking range user, Length OOB\n");
+		pr_debug("Can't build locking range user, Length OOB\n");
 		return -ERANGE;
 	}
 
@@ -648,7 +648,7 @@ static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
 	add_token_u8(&err, cmd, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error finalizing command.\n");
+		pr_debug("Error finalizing command.\n");
 		return -EFAULT;
 	}
 
@@ -660,7 +660,7 @@ static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
 	hdr->subpkt.length = cpu_to_be32(cmd->pos - sizeof(*hdr));
 	while (cmd->pos % 4) {
 		if (cmd->pos >= IO_BUFFER_LENGTH) {
-			pr_err("Error: Buffer overrun\n");
+			pr_debug("Error: Buffer overrun\n");
 			return -ERANGE;
 		}
 		cmd->cmd[cmd->pos++] = 0;
@@ -679,14 +679,14 @@ static const struct opal_resp_tok *response_get_token(
 	const struct opal_resp_tok *tok;
 
 	if (n >= resp->num) {
-		pr_err("Token number doesn't exist: %d, resp: %d\n",
-		       n, resp->num);
+		pr_debug("Token number doesn't exist: %d, resp: %d\n",
+			 n, resp->num);
 		return ERR_PTR(-EINVAL);
 	}
 
 	tok = &resp->toks[n];
 	if (tok->len == 0) {
-		pr_err("Token length must be non-zero\n");
+		pr_debug("Token length must be non-zero\n");
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -727,7 +727,7 @@ static ssize_t response_parse_short(struct opal_resp_tok *tok,
 
 		tok->type = OPAL_DTA_TOKENID_UINT;
 		if (tok->len > 9) {
-			pr_warn("uint64 with more than 8 bytes\n");
+			pr_debug("uint64 with more than 8 bytes\n");
 			return -EINVAL;
 		}
 		for (i = tok->len - 1; i > 0; i--) {
@@ -814,8 +814,8 @@ static int response_parse(const u8 *buf, size_t length,
 
 	if (clen == 0 || plen == 0 || slen == 0 ||
 	    slen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
-		pr_err("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
-		       clen, plen, slen);
+		pr_debug("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
+			 clen, plen, slen);
 		print_buffer(pos, sizeof(*hdr));
 		return -EINVAL;
 	}
@@ -848,7 +848,7 @@ static int response_parse(const u8 *buf, size_t length,
 	}
 
 	if (num_entries == 0) {
-		pr_err("Couldn't parse response.\n");
+		pr_debug("Couldn't parse response.\n");
 		return -EINVAL;
 	}
 	resp->num = num_entries;
@@ -861,18 +861,18 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 {
 	*store = NULL;
 	if (!resp) {
-		pr_err("Response is NULL\n");
+		pr_debug("Response is NULL\n");
 		return 0;
 	}
 
 	if (n > resp->num) {
-		pr_err("Response has %d tokens. Can't access %d\n",
-		       resp->num, n);
+		pr_debug("Response has %d tokens. Can't access %d\n",
+			 resp->num, n);
 		return 0;
 	}
 
 	if (resp->toks[n].type != OPAL_DTA_TOKENID_BYTESTRING) {
-		pr_err("Token is not a byte string!\n");
+		pr_debug("Token is not a byte string!\n");
 		return 0;
 	}
 
@@ -883,26 +883,26 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 static u64 response_get_u64(const struct parsed_resp *resp, int n)
 {
 	if (!resp) {
-		pr_err("Response is NULL\n");
+		pr_debug("Response is NULL\n");
 		return 0;
 	}
 
 	if (n > resp->num) {
-		pr_err("Response has %d tokens. Can't access %d\n",
-		       resp->num, n);
+		pr_debug("Response has %d tokens. Can't access %d\n",
+			 resp->num, n);
 		return 0;
 	}
 
 	if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) {
-		pr_err("Token is not unsigned it: %d\n",
-		       resp->toks[n].type);
+		pr_debug("Token is not unsigned it: %d\n",
+			 resp->toks[n].type);
 		return 0;
 	}
 
 	if (!(resp->toks[n].width == OPAL_WIDTH_TINY ||
 	      resp->toks[n].width == OPAL_WIDTH_SHORT)) {
-		pr_err("Atom is not short or tiny: %d\n",
-		       resp->toks[n].width);
+		pr_debug("Atom is not short or tiny: %d\n",
+			 resp->toks[n].width);
 		return 0;
 	}
 
@@ -949,7 +949,7 @@ static int parse_and_check_status(struct opal_dev *dev)
 
 	error = response_parse(dev->resp, IO_BUFFER_LENGTH, &dev->parsed);
 	if (error) {
-		pr_err("Couldn't parse response.\n");
+		pr_debug("Couldn't parse response.\n");
 		return error;
 	}
 
@@ -975,7 +975,7 @@ static int start_opal_session_cont(struct opal_dev *dev)
 	tsn = response_get_u64(&dev->parsed, 5);
 
 	if (hsn == 0 && tsn == 0) {
-		pr_err("Couldn't authenticate session\n");
+		pr_debug("Couldn't authenticate session\n");
 		return -EPERM;
 	}
 
@@ -1012,7 +1012,7 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
 
 	ret = cmd_finalize(dev, dev->hsn, dev->tsn);
 	if (ret) {
-		pr_err("Error finalizing command buffer: %d\n", ret);
+		pr_debug("Error finalizing command buffer: %d\n", ret);
 		return ret;
 	}
 
@@ -1023,7 +1023,6 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
 
 static int gen_key(struct opal_dev *dev, void *data)
 {
-	const u8 *method;
 	u8 uid[OPAL_UID_LENGTH];
 	int err = 0;
 
@@ -1031,7 +1030,6 @@ static int gen_key(struct opal_dev *dev, void *data)
 	set_comid(dev, dev->comid);
 
 	memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
-	method = opalmethod[OPAL_GENKEY];
 	kfree(dev->prev_data);
 	dev->prev_data = NULL;
 
@@ -1043,7 +1041,7 @@ static int gen_key(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building gen key command\n");
+		pr_debug("Error building gen key command\n");
 		return err;
 
 	}
@@ -1061,8 +1059,8 @@ static int get_active_key_cont(struct opal_dev *dev)
 		return error;
 	keylen = response_get_string(&dev->parsed, 4, &activekey);
 	if (!activekey) {
-		pr_err("%s: Couldn't extract the Activekey from the response\n",
-		       __func__);
+		pr_debug("%s: Couldn't extract the Activekey from the response\n",
+			 __func__);
 		return OPAL_INVAL_PARAM;
 	}
 	dev->prev_data = kmemdup(activekey, keylen, GFP_KERNEL);
@@ -1105,7 +1103,7 @@ static int get_active_key(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	if (err) {
-		pr_err("Error building get active key command\n");
+		pr_debug("Error building get active key command\n");
 		return err;
 	}
 
@@ -1161,7 +1159,7 @@ static inline int enable_global_lr(struct opal_dev *dev, u8 *uid,
 	err = generic_lr_enable_disable(dev, uid, !!setup->RLE, !!setup->WLE,
 					0, 0);
 	if (err)
-		pr_err("Failed to create enable global lr command\n");
+		pr_debug("Failed to create enable global lr command\n");
 	return err;
 }
 
@@ -1219,7 +1217,7 @@ static int setup_locking_range(struct opal_dev *dev, void *data)
 
 	}
 	if (err) {
-		pr_err("Error building Setup Locking range command.\n");
+		pr_debug("Error building Setup Locking range command.\n");
 		return err;
 
 	}
@@ -1236,11 +1234,8 @@ static int start_generic_opal_session(struct opal_dev *dev,
 	u32 hsn;
 	int err = 0;
 
-	if (key == NULL && auth != OPAL_ANYBODY_UID) {
-		pr_err("%s: Attempted to open ADMIN_SP Session without a Host" \
-		       "Challenge, and not as the Anybody UID\n", __func__);
+	if (key == NULL && auth != OPAL_ANYBODY_UID)
 		return OPAL_INVAL_PARAM;
-	}
 
 	clear_opal_cmd(dev);
 
@@ -1275,12 +1270,12 @@ static int start_generic_opal_session(struct opal_dev *dev,
 		add_token_u8(&err, dev, OPAL_ENDLIST);
 		break;
 	default:
-		pr_err("Cannot start Admin SP session with auth %d\n", auth);
+		pr_debug("Cannot start Admin SP session with auth %d\n", auth);
 		return OPAL_INVAL_PARAM;
 	}
 
 	if (err) {
-		pr_err("Error building start adminsp session command.\n");
+		pr_debug("Error building start adminsp session command.\n");
 		return err;
 	}
 
@@ -1371,7 +1366,7 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building STARTSESSION command.\n");
+		pr_debug("Error building STARTSESSION command.\n");
 		return err;
 	}
 
@@ -1393,7 +1388,7 @@ static int revert_tper(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	if (err) {
-		pr_err("Error building REVERT TPER command.\n");
+		pr_debug("Error building REVERT TPER command.\n");
 		return err;
 	}
 
@@ -1428,7 +1423,7 @@ static int internal_activate_user(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building Activate UserN command.\n");
+		pr_debug("Error building Activate UserN command.\n");
 		return err;
 	}
 
@@ -1455,7 +1450,7 @@ static int erase_locking_range(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building Erase Locking Range Command.\n");
+		pr_debug("Error building Erase Locking Range Command.\n");
 		return err;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1486,7 +1481,7 @@ static int set_mbr_done(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error Building set MBR Done command\n");
+		pr_debug("Error Building set MBR Done command\n");
 		return err;
 	}
 
@@ -1518,7 +1513,7 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error Building set MBR done command\n");
+		pr_debug("Error Building set MBR done command\n");
 		return err;
 	}
 
@@ -1569,7 +1564,7 @@ static int set_new_pw(struct opal_dev *dev, void *data)
 
 	if (generic_pw_cmd(usr->opal_key.key, usr->opal_key.key_len,
 			   cpin_uid, dev)) {
-		pr_err("Error building set password command.\n");
+		pr_debug("Error building set password command.\n");
 		return -ERANGE;
 	}
 
@@ -1584,7 +1579,7 @@ static int set_sid_cpin_pin(struct opal_dev *dev, void *data)
 	memcpy(cpin_uid, opaluid[OPAL_C_PIN_SID], OPAL_UID_LENGTH);
 
 	if (generic_pw_cmd(key->key, key->key_len, cpin_uid, dev)) {
-		pr_err("Error building Set SID cpin\n");
+		pr_debug("Error building Set SID cpin\n");
 		return -ERANGE;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1659,7 +1654,7 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building add user to locking range command.\n");
+		pr_debug("Error building add user to locking range command.\n");
 		return err;
 	}
 
@@ -1669,7 +1664,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 {
 	u8 lr_buffer[OPAL_UID_LENGTH];
-	const u8 *method;
 	struct opal_lock_unlock *lkul = data;
 	u8 read_locked = 1, write_locked = 1;
 	int err = 0;
@@ -1677,7 +1671,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	clear_opal_cmd(dev);
 	set_comid(dev, dev->comid);
 
-	method = opalmethod[OPAL_SET];
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
 		return -ERANGE;
@@ -1695,7 +1688,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 		/* vars are initalized to locked */
 		break;
 	default:
-		pr_err("Tried to set an invalid locking state... returning to uland\n");
+		pr_debug("Tried to set an invalid locking state... returning to uland\n");
 		return OPAL_INVAL_PARAM;
 	}
 
@@ -1722,7 +1715,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building SET command.\n");
+		pr_debug("Error building SET command.\n");
 		return err;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1733,14 +1726,12 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
 {
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	u8 read_locked = 1, write_locked = 1;
-	const u8 *method;
 	struct opal_lock_unlock *lkul = data;
 	int ret;
 
 	clear_opal_cmd(dev);
 	set_comid(dev, dev->comid);
 
-	method = opalmethod[OPAL_SET];
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
 		return -ERANGE;
@@ -1758,14 +1749,14 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
 		/* vars are initalized to locked */
 		break;
 	default:
-		pr_err("Tried to set an invalid locking state.\n");
+		pr_debug("Tried to set an invalid locking state.\n");
 		return OPAL_INVAL_PARAM;
 	}
 	ret = generic_lr_enable_disable(dev, lr_buffer, 1, 1,
 					read_locked, write_locked);
 
 	if (ret < 0) {
-		pr_err("Error building SET command.\n");
+		pr_debug("Error building SET command.\n");
 		return ret;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1817,7 +1808,7 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 	}
 
 	if (err) {
-		pr_err("Error building Activate LockingSP command.\n");
+		pr_debug("Error building Activate LockingSP command.\n");
 		return err;
 	}
 
@@ -1837,7 +1828,7 @@ static int get_lsp_lifecycle_cont(struct opal_dev *dev)
 	/* 0x08 is Manufacured Inactive */
 	/* 0x09 is Manufactured */
 	if (lc_status != OPAL_MANUFACTURED_INACTIVE) {
-		pr_err("Couldn't determine the status of the Lifcycle state\n");
+		pr_debug("Couldn't determine the status of the Lifecycle state\n");
 		return -ENODEV;
 	}
 
@@ -1874,7 +1865,7 @@ static int get_lsp_lifecycle(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error Building GET Lifecycle Status command\n");
+		pr_debug("Error Building GET Lifecycle Status command\n");
 		return err;
 	}
 
@@ -1893,7 +1884,7 @@ static int get_msid_cpin_pin_cont(struct opal_dev *dev)
 
 	strlen = response_get_string(&dev->parsed, 4, &msid_pin);
 	if (!msid_pin) {
-		pr_err("%s: Couldn't extract PIN from response\n", __func__);
+		pr_debug("%s: Couldn't extract PIN from response\n", __func__);
 		return OPAL_INVAL_PARAM;
 	}
 
@@ -1935,7 +1926,7 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building Get MSID CPIN PIN command.\n");
+		pr_debug("Error building Get MSID CPIN PIN command.\n");
 		return err;
 	}
 
@@ -2130,18 +2121,18 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 
 	if (lk_unlk->l_state != OPAL_RO &&
 	    lk_unlk->l_state != OPAL_RW) {
-		pr_err("Locking state was not RO or RW\n");
+		pr_debug("Locking state was not RO or RW\n");
 		return -EINVAL;
 	}
-	if (lk_unlk->session.who < OPAL_USER1 &&
+	if (lk_unlk->session.who < OPAL_USER1 ||
 	    lk_unlk->session.who > OPAL_USER9) {
-		pr_err("Authority was not within the range of users: %d\n",
-		       lk_unlk->session.who);
+		pr_debug("Authority was not within the range of users: %d\n",
+			 lk_unlk->session.who);
 		return -EINVAL;
 	}
 	if (lk_unlk->session.sum) {
-		pr_err("%s not supported in sum. Use setup locking range\n",
-		       __func__);
+		pr_debug("%s not supported in sum. Use setup locking range\n",
+			 __func__);
 		return -EINVAL;
 	}
 
@@ -2316,9 +2307,9 @@ static int opal_activate_user(struct opal_dev *dev,
 	int ret;
 
 	/* We can't activate Admin1 it's active as manufactured */
-	if (opal_session->who < OPAL_USER1 &&
+	if (opal_session->who < OPAL_USER1 ||
 	    opal_session->who > OPAL_USER9) {
-		pr_err("Who was not a valid user: %d\n", opal_session->who);
+		pr_debug("Who was not a valid user: %d\n", opal_session->who);
 		return -EINVAL;
 	}
 
@@ -2349,9 +2340,9 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 
 		ret = __opal_lock_unlock(dev, &suspend->unlk);
 		if (ret) {
-			pr_warn("Failed to unlock LR %hhu with sum %d\n",
-				suspend->unlk.session.opal_key.lr,
-				suspend->unlk.session.sum);
+			pr_debug("Failed to unlock LR %hhu with sum %d\n",
+				 suspend->unlk.session.opal_key.lr,
+				 suspend->unlk.session.sum);
 			was_failure = true;
 		}
 	}
@@ -2369,10 +2360,8 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 		return -EACCES;
 	if (!dev)
 		return -ENOTSUPP;
-	if (!dev->supported) {
-		pr_err("Not supported\n");
+	if (!dev->supported)
 		return -ENOTSUPP;
-	}
 
 	p = memdup_user(arg, _IOC_SIZE(cmd));
 	if (IS_ERR(p))
@@ -2416,7 +2405,7 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 		ret = opal_secure_erase_locking_range(dev, p);
 		break;
 	default:
-		pr_warn("No such Opal Ioctl %u\n", cmd);
+		break;
 	}
 
 	kfree(p);
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 2c97912335a9..680c6d636298 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -160,28 +160,28 @@ static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
 }
 
-struct blk_integrity_profile t10_pi_type1_crc = {
+const struct blk_integrity_profile t10_pi_type1_crc = {
 	.name			= "T10-DIF-TYPE1-CRC",
 	.generate_fn		= t10_pi_type1_generate_crc,
 	.verify_fn		= t10_pi_type1_verify_crc,
 };
 EXPORT_SYMBOL(t10_pi_type1_crc);
 
-struct blk_integrity_profile t10_pi_type1_ip = {
+const struct blk_integrity_profile t10_pi_type1_ip = {
 	.name			= "T10-DIF-TYPE1-IP",
 	.generate_fn		= t10_pi_type1_generate_ip,
 	.verify_fn		= t10_pi_type1_verify_ip,
 };
 EXPORT_SYMBOL(t10_pi_type1_ip);
 
-struct blk_integrity_profile t10_pi_type3_crc = {
+const struct blk_integrity_profile t10_pi_type3_crc = {
 	.name			= "T10-DIF-TYPE3-CRC",
 	.generate_fn		= t10_pi_type3_generate_crc,
 	.verify_fn		= t10_pi_type3_verify_crc,
 };
 EXPORT_SYMBOL(t10_pi_type3_crc);
 
-struct blk_integrity_profile t10_pi_type3_ip = {
+const struct blk_integrity_profile t10_pi_type3_ip = {
 	.name			= "T10-DIF-TYPE3-IP",
 	.generate_fn		= t10_pi_type3_generate_ip,
 	.verify_fn		= t10_pi_type3_verify_ip,
diff --git a/crypto/Kconfig b/crypto/Kconfig
index f37e9cca50e1..aac4bc90a138 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -374,7 +374,6 @@ config CRYPTO_XTS
 	tristate "XTS support"
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
-	select CRYPTO_GF128MUL
 	select CRYPTO_ECB
 	help
 	  XTS: IEEE1619/D16 narrow block cipher use with aes-xts-plain,
@@ -513,6 +512,23 @@ config CRYPTO_CRCT10DIF_PCLMUL
 	  'crct10dif-plcmul' module, which is faster when computing the
 	  crct10dif checksum as compared with the generic table implementation.
 
+config CRYPTO_CRCT10DIF_VPMSUM
+	tristate "CRC32T10DIF powerpc64 hardware acceleration"
+	depends on PPC64 && ALTIVEC && CRC_T10DIF
+	select CRYPTO_HASH
+	help
+	  CRC10T10DIF algorithm implemented using vector polynomial
+	  multiply-sum (vpmsum) instructions, introduced in POWER8. Enable on
+	  POWER8 and newer processors for improved performance.
+
+config CRYPTO_VPMSUM_TESTER
+	tristate "Powerpc64 vpmsum hardware acceleration tester"
+	depends on CRYPTO_CRCT10DIF_VPMSUM && CRYPTO_CRC32C_VPMSUM
+	help
+	  Stress test for CRC32c and CRC-T10DIF algorithms implemented with
+	  POWER8 vpmsum instructions.
+	  Unless you are testing these algorithms, you don't need this.
+
 config CRYPTO_GHASH
 	tristate "GHASH digest algorithm"
 	select CRYPTO_GF128MUL
diff --git a/crypto/acompress.c b/crypto/acompress.c
index 47d11627cd20..1544b7c057fb 100644
--- a/crypto/acompress.c
+++ b/crypto/acompress.c
@@ -166,5 +166,34 @@ int crypto_unregister_acomp(struct acomp_alg *alg)
 }
 EXPORT_SYMBOL_GPL(crypto_unregister_acomp);
 
+int crypto_register_acomps(struct acomp_alg *algs, int count)
+{
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_acomp(&algs[i]);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (--i; i >= 0; --i)
+		crypto_unregister_acomp(&algs[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_register_acomps);
+
+void crypto_unregister_acomps(struct acomp_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_acomp(&algs[i]);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_acomps);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Asynchronous compression type");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index f5e18c2a4852..3556d8eb54a7 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -160,11 +160,11 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (sock->state == SS_CONNECTED)
 		return -EINVAL;
 
-	if (addr_len != sizeof(*sa))
+	if (addr_len < sizeof(*sa))
 		return -EINVAL;
 
 	sa->salg_type[sizeof(sa->salg_type) - 1] = 0;
-	sa->salg_name[sizeof(sa->salg_name) - 1] = 0;
+	sa->salg_name[sizeof(sa->salg_name) + addr_len - sizeof(*sa) - 1] = 0;
 
 	type = alg_get_type(sa->salg_type);
 	if (IS_ERR(type) && PTR_ERR(type) == -ENOENT) {
@@ -266,7 +266,7 @@ unlock:
 	return err;
 }
 
-int af_alg_accept(struct sock *sk, struct socket *newsock)
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 {
 	struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_type *type;
@@ -281,7 +281,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 	if (!type)
 		goto unlock;
 
-	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0);
+	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern);
 	err = -ENOMEM;
 	if (!sk2)
 		goto unlock;
@@ -323,9 +323,10 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(af_alg_accept);
 
-static int alg_accept(struct socket *sock, struct socket *newsock, int flags)
+static int alg_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
-	return af_alg_accept(sock->sk, newsock);
+	return af_alg_accept(sock->sk, newsock, kern);
 }
 
 static const struct proto_ops alg_proto_ops = {
diff --git a/crypto/ahash.c b/crypto/ahash.c
index e58c4970c22b..826cd7ab4d4a 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -32,6 +32,7 @@ struct ahash_request_priv {
 	crypto_completion_t complete;
 	void *data;
 	u8 *result;
+	u32 flags;
 	void *ubuf[] CRYPTO_MINALIGN_ATTR;
 };
 
@@ -253,6 +254,8 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt)
 	priv->result = req->result;
 	priv->complete = req->base.complete;
 	priv->data = req->base.data;
+	priv->flags = req->base.flags;
+
 	/*
 	 * WARNING: We do not backup req->priv here! The req->priv
 	 *          is for internal use of the Crypto API and the
@@ -267,38 +270,44 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt)
 	return 0;
 }
 
-static void ahash_restore_req(struct ahash_request *req)
+static void ahash_restore_req(struct ahash_request *req, int err)
 {
 	struct ahash_request_priv *priv = req->priv;
 
+	if (!err)
+		memcpy(priv->result, req->result,
+		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
+
 	/* Restore the original crypto request. */
 	req->result = priv->result;
-	req->base.complete = priv->complete;
-	req->base.data = priv->data;
+
+	ahash_request_set_callback(req, priv->flags,
+				   priv->complete, priv->data);
 	req->priv = NULL;
 
 	/* Free the req->priv.priv from the ADJUSTED request. */
 	kzfree(priv);
 }
 
-static void ahash_op_unaligned_finish(struct ahash_request *req, int err)
+static void ahash_notify_einprogress(struct ahash_request *req)
 {
 	struct ahash_request_priv *priv = req->priv;
+	struct crypto_async_request oreq;
 
-	if (err == -EINPROGRESS)
-		return;
-
-	if (!err)
-		memcpy(priv->result, req->result,
-		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
+	oreq.data = priv->data;
 
-	ahash_restore_req(req);
+	priv->complete(&oreq, -EINPROGRESS);
 }
 
 static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
 
+	if (err == -EINPROGRESS) {
+		ahash_notify_einprogress(areq);
+		return;
+	}
+
 	/*
 	 * Restore the original request, see ahash_op_unaligned() for what
 	 * goes where.
@@ -309,7 +318,7 @@ static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
 	 */
 
 	/* First copy req->result into req->priv.result */
-	ahash_op_unaligned_finish(areq, err);
+	ahash_restore_req(areq, err);
 
 	/* Complete the ORIGINAL request. */
 	areq->base.complete(&areq->base, err);
@@ -325,7 +334,12 @@ static int ahash_op_unaligned(struct ahash_request *req,
 		return err;
 
 	err = op(req);
-	ahash_op_unaligned_finish(req, err);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && (ahash_request_flags(req) &
+			       CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return err;
+
+	ahash_restore_req(req, err);
 
 	return err;
 }
@@ -360,25 +374,14 @@ int crypto_ahash_digest(struct ahash_request *req)
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_digest);
 
-static void ahash_def_finup_finish2(struct ahash_request *req, int err)
+static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
 {
-	struct ahash_request_priv *priv = req->priv;
+	struct ahash_request *areq = req->data;
 
 	if (err == -EINPROGRESS)
 		return;
 
-	if (!err)
-		memcpy(priv->result, req->result,
-		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
-
-	ahash_restore_req(req);
-}
-
-static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
-{
-	struct ahash_request *areq = req->data;
-
-	ahash_def_finup_finish2(areq, err);
+	ahash_restore_req(areq, err);
 
 	areq->base.complete(&areq->base, err);
 }
@@ -389,11 +392,15 @@ static int ahash_def_finup_finish1(struct ahash_request *req, int err)
 		goto out;
 
 	req->base.complete = ahash_def_finup_done2;
-	req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
 	err = crypto_ahash_reqtfm(req)->final(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && (ahash_request_flags(req) &
+			       CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return err;
 
 out:
-	ahash_def_finup_finish2(req, err);
+	ahash_restore_req(req, err);
 	return err;
 }
 
@@ -401,7 +408,16 @@ static void ahash_def_finup_done1(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
 
+	if (err == -EINPROGRESS) {
+		ahash_notify_einprogress(areq);
+		return;
+	}
+
+	areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
 	err = ahash_def_finup_finish1(areq, err);
+	if (areq->priv)
+		return;
 
 	areq->base.complete(&areq->base, err);
 }
@@ -416,6 +432,11 @@ static int ahash_def_finup(struct ahash_request *req)
 		return err;
 
 	err = tfm->update(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && (ahash_request_flags(req) &
+			       CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return err;
+
 	return ahash_def_finup_finish1(req, err);
 }
 
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 6b52e8f0b95f..9eed4ef9c971 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -963,11 +963,11 @@ void crypto_inc(u8 *a, unsigned int size)
 	u32 c;
 
 	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
-	    !((unsigned long)b & (__alignof__(*b) - 1)))
+	    IS_ALIGNED((unsigned long)b, __alignof__(*b)))
 		for (; size >= 4; size -= 4) {
 			c = be32_to_cpu(*--b) + 1;
 			*b = cpu_to_be32(c);
-			if (c)
+			if (likely(c))
 				return;
 		}
 
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 5a8053758657..8af664f7d27c 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -40,10 +40,16 @@ struct aead_async_req {
 	struct aead_async_rsgl first_rsgl;
 	struct list_head list;
 	struct kiocb *iocb;
+	struct sock *sk;
 	unsigned int tsgls;
 	char iv[];
 };
 
+struct aead_tfm {
+	struct crypto_aead *aead;
+	bool has_key;
+};
+
 struct aead_ctx {
 	struct aead_sg_list tsgl;
 	struct aead_async_rsgl first_rsgl;
@@ -379,12 +385,10 @@ unlock:
 
 static void aead_async_cb(struct crypto_async_request *_req, int err)
 {
-	struct sock *sk = _req->data;
-	struct alg_sock *ask = alg_sk(sk);
-	struct aead_ctx *ctx = ask->private;
-	struct crypto_aead *tfm = crypto_aead_reqtfm(&ctx->aead_req);
-	struct aead_request *req = aead_request_cast(_req);
+	struct aead_request *req = _req->data;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aead_async_req *areq = GET_ASYM_REQ(req, tfm);
+	struct sock *sk = areq->sk;
 	struct scatterlist *sg = areq->tsgl;
 	struct aead_async_rsgl *rsgl;
 	struct kiocb *iocb = areq->iocb;
@@ -447,11 +451,12 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg,
 	memset(&areq->first_rsgl, '\0', sizeof(areq->first_rsgl));
 	INIT_LIST_HEAD(&areq->list);
 	areq->iocb = msg->msg_iocb;
+	areq->sk = sk;
 	memcpy(areq->iv, ctx->iv, crypto_aead_ivsize(tfm));
 	aead_request_set_tfm(req, tfm);
 	aead_request_set_ad(req, ctx->aead_assoclen);
 	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				  aead_async_cb, sk);
+				  aead_async_cb, req);
 	used -= ctx->aead_assoclen;
 
 	/* take over all tx sgls from ctx */
@@ -723,24 +728,146 @@ static struct proto_ops algif_aead_ops = {
 	.poll		=	aead_poll,
 };
 
+static int aead_check_key(struct socket *sock)
+{
+	int err = 0;
+	struct sock *psk;
+	struct alg_sock *pask;
+	struct aead_tfm *tfm;
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+
+	lock_sock(sk);
+	if (ask->refcnt)
+		goto unlock_child;
+
+	psk = ask->parent;
+	pask = alg_sk(ask->parent);
+	tfm = pask->private;
+
+	err = -ENOKEY;
+	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
+	if (!tfm->has_key)
+		goto unlock;
+
+	if (!pask->refcnt++)
+		sock_hold(psk);
+
+	ask->refcnt = 1;
+	sock_put(psk);
+
+	err = 0;
+
+unlock:
+	release_sock(psk);
+unlock_child:
+	release_sock(sk);
+
+	return err;
+}
+
+static int aead_sendmsg_nokey(struct socket *sock, struct msghdr *msg,
+				  size_t size)
+{
+	int err;
+
+	err = aead_check_key(sock);
+	if (err)
+		return err;
+
+	return aead_sendmsg(sock, msg, size);
+}
+
+static ssize_t aead_sendpage_nokey(struct socket *sock, struct page *page,
+				       int offset, size_t size, int flags)
+{
+	int err;
+
+	err = aead_check_key(sock);
+	if (err)
+		return err;
+
+	return aead_sendpage(sock, page, offset, size, flags);
+}
+
+static int aead_recvmsg_nokey(struct socket *sock, struct msghdr *msg,
+				  size_t ignored, int flags)
+{
+	int err;
+
+	err = aead_check_key(sock);
+	if (err)
+		return err;
+
+	return aead_recvmsg(sock, msg, ignored, flags);
+}
+
+static struct proto_ops algif_aead_ops_nokey = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.accept		=	sock_no_accept,
+	.setsockopt	=	sock_no_setsockopt,
+
+	.release	=	af_alg_release,
+	.sendmsg	=	aead_sendmsg_nokey,
+	.sendpage	=	aead_sendpage_nokey,
+	.recvmsg	=	aead_recvmsg_nokey,
+	.poll		=	aead_poll,
+};
+
 static void *aead_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_aead(name, type, mask);
+	struct aead_tfm *tfm;
+	struct crypto_aead *aead;
+
+	tfm = kzalloc(sizeof(*tfm), GFP_KERNEL);
+	if (!tfm)
+		return ERR_PTR(-ENOMEM);
+
+	aead = crypto_alloc_aead(name, type, mask);
+	if (IS_ERR(aead)) {
+		kfree(tfm);
+		return ERR_CAST(aead);
+	}
+
+	tfm->aead = aead;
+
+	return tfm;
 }
 
 static void aead_release(void *private)
 {
-	crypto_free_aead(private);
+	struct aead_tfm *tfm = private;
+
+	crypto_free_aead(tfm->aead);
+	kfree(tfm);
 }
 
 static int aead_setauthsize(void *private, unsigned int authsize)
 {
-	return crypto_aead_setauthsize(private, authsize);
+	struct aead_tfm *tfm = private;
+
+	return crypto_aead_setauthsize(tfm->aead, authsize);
 }
 
 static int aead_setkey(void *private, const u8 *key, unsigned int keylen)
 {
-	return crypto_aead_setkey(private, key, keylen);
+	struct aead_tfm *tfm = private;
+	int err;
+
+	err = crypto_aead_setkey(tfm->aead, key, keylen);
+	tfm->has_key = !err;
+
+	return err;
 }
 
 static void aead_sock_destruct(struct sock *sk)
@@ -757,12 +884,14 @@ static void aead_sock_destruct(struct sock *sk)
 	af_alg_release_parent(sk);
 }
 
-static int aead_accept_parent(void *private, struct sock *sk)
+static int aead_accept_parent_nokey(void *private, struct sock *sk)
 {
 	struct aead_ctx *ctx;
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned int len = sizeof(*ctx) + crypto_aead_reqsize(private);
-	unsigned int ivlen = crypto_aead_ivsize(private);
+	struct aead_tfm *tfm = private;
+	struct crypto_aead *aead = tfm->aead;
+	unsigned int len = sizeof(*ctx) + crypto_aead_reqsize(aead);
+	unsigned int ivlen = crypto_aead_ivsize(aead);
 
 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
@@ -789,7 +918,7 @@ static int aead_accept_parent(void *private, struct sock *sk)
 
 	ask->private = ctx;
 
-	aead_request_set_tfm(&ctx->aead_req, private);
+	aead_request_set_tfm(&ctx->aead_req, aead);
 	aead_request_set_callback(&ctx->aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  af_alg_complete, &ctx->completion);
 
@@ -798,13 +927,25 @@ static int aead_accept_parent(void *private, struct sock *sk)
 	return 0;
 }
 
+static int aead_accept_parent(void *private, struct sock *sk)
+{
+	struct aead_tfm *tfm = private;
+
+	if (!tfm->has_key)
+		return -ENOKEY;
+
+	return aead_accept_parent_nokey(private, sk);
+}
+
 static const struct af_alg_type algif_type_aead = {
 	.bind		=	aead_bind,
 	.release	=	aead_release,
 	.setkey		=	aead_setkey,
 	.setauthsize	=	aead_setauthsize,
 	.accept		=	aead_accept_parent,
+	.accept_nokey	=	aead_accept_parent_nokey,
 	.ops		=	&algif_aead_ops,
+	.ops_nokey	=	&algif_aead_ops_nokey,
 	.name		=	"aead",
 	.owner		=	THIS_MODULE
 };
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 54fc90e8339c..5e92bd275ef3 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -239,7 +239,8 @@ unlock:
 	return err ?: len;
 }
 
-static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
+static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
@@ -260,7 +261,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
 	if (err)
 		return err;
 
-	err = af_alg_accept(ask->parent, newsock);
+	err = af_alg_accept(ask->parent, newsock, kern);
 	if (err)
 		return err;
 
@@ -378,7 +379,7 @@ static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg,
 }
 
 static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
-			     int flags)
+			     int flags, bool kern)
 {
 	int err;
 
@@ -386,7 +387,7 @@ static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
 	if (err)
 		return err;
 
-	return hash_accept(sock, newsock, flags);
+	return hash_accept(sock, newsock, flags, kern);
 }
 
 static struct proto_ops algif_hash_ops_nokey = {
diff --git a/crypto/cbc.c b/crypto/cbc.c
index bc160a3186dc..b761b1f9c6ca 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -10,6 +10,7 @@
  *
  */
 
+#include <crypto/algapi.h>
 #include <crypto/cbc.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
@@ -108,8 +109,10 @@ static void crypto_cbc_free(struct skcipher_instance *inst)
 static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct skcipher_instance *inst;
+	struct crypto_attr_type *algt;
 	struct crypto_spawn *spawn;
 	struct crypto_alg *alg;
+	u32 mask;
 	int err;
 
 	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER);
@@ -120,8 +123,16 @@ static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (!inst)
 		return -ENOMEM;
 
-	alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_CIPHER,
-				  CRYPTO_ALG_TYPE_MASK);
+	algt = crypto_get_attr_type(tb);
+	err = PTR_ERR(algt);
+	if (IS_ERR(algt))
+		goto err_free_inst;
+
+	mask = CRYPTO_ALG_TYPE_MASK |
+		crypto_requires_off(algt->type, algt->mask,
+				    CRYPTO_ALG_NEED_FALLBACK);
+
+	alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_CIPHER, mask);
 	err = PTR_ERR(alg);
 	if (IS_ERR(alg))
 		goto err_free_inst;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index a90404a0c5ff..0dbe2be7f783 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -83,7 +83,7 @@ static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_cipher rcipher;
 
-	strncpy(rcipher.type, "cipher", sizeof(rcipher.type));
+	strlcpy(rcipher.type, "cipher", sizeof(rcipher.type));
 
 	rcipher.blocksize = alg->cra_blocksize;
 	rcipher.min_keysize = alg->cra_cipher.cia_min_keysize;
@@ -102,7 +102,7 @@ static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_comp rcomp;
 
-	strncpy(rcomp.type, "compression", sizeof(rcomp.type));
+	strlcpy(rcomp.type, "compression", sizeof(rcomp.type));
 	if (nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS,
 		    sizeof(struct crypto_report_comp), &rcomp))
 		goto nla_put_failure;
@@ -116,7 +116,7 @@ static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_acomp racomp;
 
-	strncpy(racomp.type, "acomp", sizeof(racomp.type));
+	strlcpy(racomp.type, "acomp", sizeof(racomp.type));
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP,
 		    sizeof(struct crypto_report_acomp), &racomp))
@@ -131,7 +131,7 @@ static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_akcipher rakcipher;
 
-	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+	strlcpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
 		    sizeof(struct crypto_report_akcipher), &rakcipher))
@@ -146,7 +146,7 @@ static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_kpp rkpp;
 
-	strncpy(rkpp.type, "kpp", sizeof(rkpp.type));
+	strlcpy(rkpp.type, "kpp", sizeof(rkpp.type));
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_KPP,
 		    sizeof(struct crypto_report_kpp), &rkpp))
@@ -160,10 +160,10 @@ nla_put_failure:
 static int crypto_report_one(struct crypto_alg *alg,
 			     struct crypto_user_alg *ualg, struct sk_buff *skb)
 {
-	strncpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name));
-	strncpy(ualg->cru_driver_name, alg->cra_driver_name,
+	strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name));
+	strlcpy(ualg->cru_driver_name, alg->cra_driver_name,
 		sizeof(ualg->cru_driver_name));
-	strncpy(ualg->cru_module_name, module_name(alg->cra_module),
+	strlcpy(ualg->cru_module_name, module_name(alg->cra_module),
 		sizeof(ualg->cru_module_name));
 
 	ualg->cru_type = 0;
@@ -176,7 +176,7 @@ static int crypto_report_one(struct crypto_alg *alg,
 	if (alg->cra_flags & CRYPTO_ALG_LARVAL) {
 		struct crypto_report_larval rl;
 
-		strncpy(rl.type, "larval", sizeof(rl.type));
+		strlcpy(rl.type, "larval", sizeof(rl.type));
 		if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL,
 			    sizeof(struct crypto_report_larval), &rl))
 			goto nla_put_failure;
@@ -483,7 +483,8 @@ static const struct crypto_link {
 	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = { .doit = crypto_del_rng },
 };
 
-static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct nlattr *attrs[CRYPTOCFGA_MAX+1];
 	const struct crypto_link *link;
@@ -522,7 +523,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 
 	err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX,
-			  crypto_policy);
+			  crypto_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/crypto/ctr.c b/crypto/ctr.c
index a4f4a8983169..477d9226ccaa 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -181,15 +181,24 @@ static void crypto_ctr_exit_tfm(struct crypto_tfm *tfm)
 static struct crypto_instance *crypto_ctr_alloc(struct rtattr **tb)
 {
 	struct crypto_instance *inst;
+	struct crypto_attr_type *algt;
 	struct crypto_alg *alg;
+	u32 mask;
 	int err;
 
 	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
 	if (err)
 		return ERR_PTR(err);
 
-	alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_CIPHER,
-				  CRYPTO_ALG_TYPE_MASK);
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return ERR_CAST(algt);
+
+	mask = CRYPTO_ALG_TYPE_MASK |
+		crypto_requires_off(algt->type, algt->mask,
+				    CRYPTO_ALG_NEED_FALLBACK);
+
+	alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_CIPHER, mask);
 	if (IS_ERR(alg))
 		return ERR_CAST(alg);
 
@@ -350,6 +359,8 @@ static int crypto_rfc3686_create(struct crypto_template *tmpl,
 	struct skcipher_alg *alg;
 	struct crypto_skcipher_spawn *spawn;
 	const char *cipher_name;
+	u32 mask;
+
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -367,12 +378,14 @@ static int crypto_rfc3686_create(struct crypto_template *tmpl,
 	if (!inst)
 		return -ENOMEM;
 
+	mask = crypto_requires_sync(algt->type, algt->mask) |
+		crypto_requires_off(algt->type, algt->mask,
+				    CRYPTO_ALG_NEED_FALLBACK);
+
 	spawn = skcipher_instance_ctx(inst);
 
 	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(spawn, cipher_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(spawn, cipher_name, 0, mask);
 	if (err)
 		goto err_free_inst;
 
diff --git a/crypto/deflate.c b/crypto/deflate.c
index f942cb391890..94ec3b36a8e8 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -43,20 +43,24 @@ struct deflate_ctx {
 	struct z_stream_s decomp_stream;
 };
 
-static int deflate_comp_init(struct deflate_ctx *ctx)
+static int deflate_comp_init(struct deflate_ctx *ctx, int format)
 {
 	int ret = 0;
 	struct z_stream_s *stream = &ctx->comp_stream;
 
 	stream->workspace = vzalloc(zlib_deflate_workspacesize(
-				-DEFLATE_DEF_WINBITS, DEFLATE_DEF_MEMLEVEL));
+				    MAX_WBITS, MAX_MEM_LEVEL));
 	if (!stream->workspace) {
 		ret = -ENOMEM;
 		goto out;
 	}
-	ret = zlib_deflateInit2(stream, DEFLATE_DEF_LEVEL, Z_DEFLATED,
-	                        -DEFLATE_DEF_WINBITS, DEFLATE_DEF_MEMLEVEL,
-	                        Z_DEFAULT_STRATEGY);
+	if (format)
+		ret = zlib_deflateInit(stream, 3);
+	else
+		ret = zlib_deflateInit2(stream, DEFLATE_DEF_LEVEL, Z_DEFLATED,
+					-DEFLATE_DEF_WINBITS,
+					DEFLATE_DEF_MEMLEVEL,
+					Z_DEFAULT_STRATEGY);
 	if (ret != Z_OK) {
 		ret = -EINVAL;
 		goto out_free;
@@ -68,7 +72,7 @@ out_free:
 	goto out;
 }
 
-static int deflate_decomp_init(struct deflate_ctx *ctx)
+static int deflate_decomp_init(struct deflate_ctx *ctx, int format)
 {
 	int ret = 0;
 	struct z_stream_s *stream = &ctx->decomp_stream;
@@ -78,7 +82,10 @@ static int deflate_decomp_init(struct deflate_ctx *ctx)
 		ret = -ENOMEM;
 		goto out;
 	}
-	ret = zlib_inflateInit2(stream, -DEFLATE_DEF_WINBITS);
+	if (format)
+		ret = zlib_inflateInit(stream);
+	else
+		ret = zlib_inflateInit2(stream, -DEFLATE_DEF_WINBITS);
 	if (ret != Z_OK) {
 		ret = -EINVAL;
 		goto out_free;
@@ -102,21 +109,21 @@ static void deflate_decomp_exit(struct deflate_ctx *ctx)
 	vfree(ctx->decomp_stream.workspace);
 }
 
-static int __deflate_init(void *ctx)
+static int __deflate_init(void *ctx, int format)
 {
 	int ret;
 
-	ret = deflate_comp_init(ctx);
+	ret = deflate_comp_init(ctx, format);
 	if (ret)
 		goto out;
-	ret = deflate_decomp_init(ctx);
+	ret = deflate_decomp_init(ctx, format);
 	if (ret)
 		deflate_comp_exit(ctx);
 out:
 	return ret;
 }
 
-static void *deflate_alloc_ctx(struct crypto_scomp *tfm)
+static void *gen_deflate_alloc_ctx(struct crypto_scomp *tfm, int format)
 {
 	struct deflate_ctx *ctx;
 	int ret;
@@ -125,7 +132,7 @@ static void *deflate_alloc_ctx(struct crypto_scomp *tfm)
 	if (!ctx)
 		return ERR_PTR(-ENOMEM);
 
-	ret = __deflate_init(ctx);
+	ret = __deflate_init(ctx, format);
 	if (ret) {
 		kfree(ctx);
 		return ERR_PTR(ret);
@@ -134,11 +141,21 @@ static void *deflate_alloc_ctx(struct crypto_scomp *tfm)
 	return ctx;
 }
 
+static void *deflate_alloc_ctx(struct crypto_scomp *tfm)
+{
+	return gen_deflate_alloc_ctx(tfm, 0);
+}
+
+static void *zlib_deflate_alloc_ctx(struct crypto_scomp *tfm)
+{
+	return gen_deflate_alloc_ctx(tfm, 1);
+}
+
 static int deflate_init(struct crypto_tfm *tfm)
 {
 	struct deflate_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	return __deflate_init(ctx);
+	return __deflate_init(ctx, 0);
 }
 
 static void __deflate_exit(void *ctx)
@@ -272,7 +289,7 @@ static struct crypto_alg alg = {
 	.coa_decompress  	= deflate_decompress } }
 };
 
-static struct scomp_alg scomp = {
+static struct scomp_alg scomp[] = { {
 	.alloc_ctx		= deflate_alloc_ctx,
 	.free_ctx		= deflate_free_ctx,
 	.compress		= deflate_scompress,
@@ -282,7 +299,17 @@ static struct scomp_alg scomp = {
 		.cra_driver_name = "deflate-scomp",
 		.cra_module	 = THIS_MODULE,
 	}
-};
+}, {
+	.alloc_ctx		= zlib_deflate_alloc_ctx,
+	.free_ctx		= deflate_free_ctx,
+	.compress		= deflate_scompress,
+	.decompress		= deflate_sdecompress,
+	.base			= {
+		.cra_name	= "zlib-deflate",
+		.cra_driver_name = "zlib-deflate-scomp",
+		.cra_module	 = THIS_MODULE,
+	}
+} };
 
 static int __init deflate_mod_init(void)
 {
@@ -292,7 +319,7 @@ static int __init deflate_mod_init(void)
 	if (ret)
 		return ret;
 
-	ret = crypto_register_scomp(&scomp);
+	ret = crypto_register_scomps(scomp, ARRAY_SIZE(scomp));
 	if (ret) {
 		crypto_unregister_alg(&alg);
 		return ret;
@@ -304,7 +331,7 @@ static int __init deflate_mod_init(void)
 static void __exit deflate_mod_fini(void)
 {
 	crypto_unregister_alg(&alg);
-	crypto_unregister_scomp(&scomp);
+	crypto_unregister_scomps(scomp, ARRAY_SIZE(scomp));
 }
 
 module_init(deflate_mod_init);
diff --git a/crypto/dh.c b/crypto/dh.c
index ddcb528ab2cc..87e3542cf1b8 100644
--- a/crypto/dh.c
+++ b/crypto/dh.c
@@ -79,7 +79,8 @@ static int dh_set_params(struct dh_ctx *ctx, struct dh *params)
 	return 0;
 }
 
-static int dh_set_secret(struct crypto_kpp *tfm, void *buf, unsigned int len)
+static int dh_set_secret(struct crypto_kpp *tfm, const void *buf,
+			 unsigned int len)
 {
 	struct dh_ctx *ctx = dh_get_ctx(tfm);
 	struct dh params;
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 8a4d98b4adba..fa749f470135 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1749,17 +1749,16 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 			      u8 *inbuf, u32 inlen,
 			      u8 *outbuf, u32 outlen)
 {
-	struct scatterlist sg_in;
+	struct scatterlist sg_in, sg_out;
 	int ret;
 
 	sg_init_one(&sg_in, inbuf, inlen);
+	sg_init_one(&sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN);
 
 	while (outlen) {
 		u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN);
-		struct scatterlist sg_out;
 
 		/* Output buffer may not be valid for SGL, use scratchpad */
-		sg_init_one(&sg_out, drbg->outscratchpad, cryptlen);
 		skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out,
 					   cryptlen, drbg->V);
 		ret = crypto_skcipher_encrypt(drbg->ctr_req);
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
index 3de289806d67..63ca33771e4e 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -38,7 +38,8 @@ static unsigned int ecdh_supported_curve(unsigned int curve_id)
 	}
 }
 
-static int ecdh_set_secret(struct crypto_kpp *tfm, void *buf, unsigned int len)
+static int ecdh_set_secret(struct crypto_kpp *tfm, const void *buf,
+			   unsigned int len)
 {
 	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
 	struct ecdh params;
diff --git a/crypto/gf128mul.c b/crypto/gf128mul.c
index 72015fee533d..dc012129c063 100644
--- a/crypto/gf128mul.c
+++ b/crypto/gf128mul.c
@@ -44,7 +44,7 @@
  ---------------------------------------------------------------------------
  Issue 31/01/2006
 
- This file provides fast multiplication in GF(128) as required by several
+ This file provides fast multiplication in GF(2^128) as required by several
  cryptographic authentication modes
 */
 
@@ -88,76 +88,59 @@
 	q(0xf8), q(0xf9), q(0xfa), q(0xfb), q(0xfc), q(0xfd), q(0xfe), q(0xff) \
 }
 
-/*	Given the value i in 0..255 as the byte overflow when a field element
-    in GHASH is multiplied by x^8, this function will return the values that
-    are generated in the lo 16-bit word of the field value by applying the
-    modular polynomial. The values lo_byte and hi_byte are returned via the
-    macro xp_fun(lo_byte, hi_byte) so that the values can be assembled into
-    memory as required by a suitable definition of this macro operating on
-    the table above
-*/
-
-#define xx(p, q)	0x##p##q
+/*
+ * Given a value i in 0..255 as the byte overflow when a field element
+ * in GF(2^128) is multiplied by x^8, the following macro returns the
+ * 16-bit value that must be XOR-ed into the low-degree end of the
+ * product to reduce it modulo the polynomial x^128 + x^7 + x^2 + x + 1.
+ *
+ * There are two versions of the macro, and hence two tables: one for
+ * the "be" convention where the highest-order bit is the coefficient of
+ * the highest-degree polynomial term, and one for the "le" convention
+ * where the highest-order bit is the coefficient of the lowest-degree
+ * polynomial term.  In both cases the values are stored in CPU byte
+ * endianness such that the coefficients are ordered consistently across
+ * bytes, i.e. in the "be" table bits 15..0 of the stored value
+ * correspond to the coefficients of x^15..x^0, and in the "le" table
+ * bits 15..0 correspond to the coefficients of x^0..x^15.
+ *
+ * Therefore, provided that the appropriate byte endianness conversions
+ * are done by the multiplication functions (and these must be in place
+ * anyway to support both little endian and big endian CPUs), the "be"
+ * table can be used for multiplications of both "bbe" and "ble"
+ * elements, and the "le" table can be used for multiplications of both
+ * "lle" and "lbe" elements.
+ */
 
-#define xda_bbe(i) ( \
-	(i & 0x80 ? xx(43, 80) : 0) ^ (i & 0x40 ? xx(21, c0) : 0) ^ \
-	(i & 0x20 ? xx(10, e0) : 0) ^ (i & 0x10 ? xx(08, 70) : 0) ^ \
-	(i & 0x08 ? xx(04, 38) : 0) ^ (i & 0x04 ? xx(02, 1c) : 0) ^ \
-	(i & 0x02 ? xx(01, 0e) : 0) ^ (i & 0x01 ? xx(00, 87) : 0) \
+#define xda_be(i) ( \
+	(i & 0x80 ? 0x4380 : 0) ^ (i & 0x40 ? 0x21c0 : 0) ^ \
+	(i & 0x20 ? 0x10e0 : 0) ^ (i & 0x10 ? 0x0870 : 0) ^ \
+	(i & 0x08 ? 0x0438 : 0) ^ (i & 0x04 ? 0x021c : 0) ^ \
+	(i & 0x02 ? 0x010e : 0) ^ (i & 0x01 ? 0x0087 : 0) \
 )
 
-#define xda_lle(i) ( \
-	(i & 0x80 ? xx(e1, 00) : 0) ^ (i & 0x40 ? xx(70, 80) : 0) ^ \
-	(i & 0x20 ? xx(38, 40) : 0) ^ (i & 0x10 ? xx(1c, 20) : 0) ^ \
-	(i & 0x08 ? xx(0e, 10) : 0) ^ (i & 0x04 ? xx(07, 08) : 0) ^ \
-	(i & 0x02 ? xx(03, 84) : 0) ^ (i & 0x01 ? xx(01, c2) : 0) \
+#define xda_le(i) ( \
+	(i & 0x80 ? 0xe100 : 0) ^ (i & 0x40 ? 0x7080 : 0) ^ \
+	(i & 0x20 ? 0x3840 : 0) ^ (i & 0x10 ? 0x1c20 : 0) ^ \
+	(i & 0x08 ? 0x0e10 : 0) ^ (i & 0x04 ? 0x0708 : 0) ^ \
+	(i & 0x02 ? 0x0384 : 0) ^ (i & 0x01 ? 0x01c2 : 0) \
 )
 
-static const u16 gf128mul_table_lle[256] = gf128mul_dat(xda_lle);
-static const u16 gf128mul_table_bbe[256] = gf128mul_dat(xda_bbe);
+static const u16 gf128mul_table_le[256] = gf128mul_dat(xda_le);
+static const u16 gf128mul_table_be[256] = gf128mul_dat(xda_be);
 
-/* These functions multiply a field element by x, by x^4 and by x^8
- * in the polynomial field representation. It uses 32-bit word operations
- * to gain speed but compensates for machine endianess and hence works
+/*
+ * The following functions multiply a field element by x^8 in
+ * the polynomial field representation.  They use 64-bit word operations
+ * to gain speed but compensate for machine endianness and hence work
  * correctly on both styles of machine.
  */
 
-static void gf128mul_x_lle(be128 *r, const be128 *x)
-{
-	u64 a = be64_to_cpu(x->a);
-	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_lle[(b << 7) & 0xff];
-
-	r->b = cpu_to_be64((b >> 1) | (a << 63));
-	r->a = cpu_to_be64((a >> 1) ^ (_tt << 48));
-}
-
-static void gf128mul_x_bbe(be128 *r, const be128 *x)
-{
-	u64 a = be64_to_cpu(x->a);
-	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_bbe[a >> 63];
-
-	r->a = cpu_to_be64((a << 1) | (b >> 63));
-	r->b = cpu_to_be64((b << 1) ^ _tt);
-}
-
-void gf128mul_x_ble(be128 *r, const be128 *x)
-{
-	u64 a = le64_to_cpu(x->a);
-	u64 b = le64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_bbe[b >> 63];
-
-	r->a = cpu_to_le64((a << 1) ^ _tt);
-	r->b = cpu_to_le64((b << 1) | (a >> 63));
-}
-EXPORT_SYMBOL(gf128mul_x_ble);
-
 static void gf128mul_x8_lle(be128 *x)
 {
 	u64 a = be64_to_cpu(x->a);
 	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_lle[b & 0xff];
+	u64 _tt = gf128mul_table_le[b & 0xff];
 
 	x->b = cpu_to_be64((b >> 8) | (a << 56));
 	x->a = cpu_to_be64((a >> 8) ^ (_tt << 48));
@@ -167,7 +150,7 @@ static void gf128mul_x8_bbe(be128 *x)
 {
 	u64 a = be64_to_cpu(x->a);
 	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_bbe[a >> 56];
+	u64 _tt = gf128mul_table_be[a >> 56];
 
 	x->a = cpu_to_be64((a << 8) | (b >> 56));
 	x->b = cpu_to_be64((b << 8) ^ _tt);
@@ -251,7 +234,7 @@ EXPORT_SYMBOL(gf128mul_bbe);
 
 /*      This version uses 64k bytes of table space.
     A 16 byte buffer has to be multiplied by a 16 byte key
-    value in GF(128).  If we consider a GF(128) value in
+    value in GF(2^128).  If we consider a GF(2^128) value in
     the buffer's lowest byte, we can construct a table of
     the 256 16 byte values that result from the 256 values
     of this byte.  This requires 4096 bytes. But we also
@@ -315,7 +298,7 @@ void gf128mul_free_64k(struct gf128mul_64k *t)
 }
 EXPORT_SYMBOL(gf128mul_free_64k);
 
-void gf128mul_64k_bbe(be128 *a, struct gf128mul_64k *t)
+void gf128mul_64k_bbe(be128 *a, const struct gf128mul_64k *t)
 {
 	u8 *ap = (u8 *)a;
 	be128 r[1];
@@ -330,7 +313,7 @@ EXPORT_SYMBOL(gf128mul_64k_bbe);
 
 /*      This version uses 4k bytes of table space.
     A 16 byte buffer has to be multiplied by a 16 byte key
-    value in GF(128).  If we consider a GF(128) value in a
+    value in GF(2^128).  If we consider a GF(2^128) value in a
     single byte, we can construct a table of the 256 16 byte
     values that result from the 256 values of this byte.
     This requires 4096 bytes. If we take the highest byte in
@@ -388,7 +371,7 @@ out:
 }
 EXPORT_SYMBOL(gf128mul_init_4k_bbe);
 
-void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t)
+void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t)
 {
 	u8 *ap = (u8 *)a;
 	be128 r[1];
@@ -403,7 +386,7 @@ void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t)
 }
 EXPORT_SYMBOL(gf128mul_4k_lle);
 
-void gf128mul_4k_bbe(be128 *a, struct gf128mul_4k *t)
+void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t)
 {
 	u8 *ap = (u8 *)a;
 	be128 r[1];
diff --git a/crypto/lrw.c b/crypto/lrw.c
index ecd8474018e3..a8bfae4451bf 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -286,8 +286,11 @@ static int init_crypt(struct skcipher_request *req, crypto_completion_t done)
 
 	subreq->cryptlen = LRW_BUFFER_SIZE;
 	if (req->cryptlen > LRW_BUFFER_SIZE) {
-		subreq->cryptlen = min(req->cryptlen, (unsigned)PAGE_SIZE);
-		rctx->ext = kmalloc(subreq->cryptlen, gfp);
+		unsigned int n = min(req->cryptlen, (unsigned int)PAGE_SIZE);
+
+		rctx->ext = kmalloc(n, gfp);
+		if (rctx->ext)
+			subreq->cryptlen = n;
 	}
 
 	rctx->src = req->src;
@@ -342,6 +345,13 @@ static void encrypt_done(struct crypto_async_request *areq, int err)
 	struct rctx *rctx;
 
 	rctx = skcipher_request_ctx(req);
+
+	if (err == -EINPROGRESS) {
+		if (rctx->left != req->cryptlen)
+			return;
+		goto out;
+	}
+
 	subreq = &rctx->subreq;
 	subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
 
@@ -349,6 +359,7 @@ static void encrypt_done(struct crypto_async_request *areq, int err)
 	if (rctx->left)
 		return;
 
+out:
 	skcipher_request_complete(req, err);
 }
 
@@ -386,6 +397,13 @@ static void decrypt_done(struct crypto_async_request *areq, int err)
 	struct rctx *rctx;
 
 	rctx = skcipher_request_ctx(req);
+
+	if (err == -EINPROGRESS) {
+		if (rctx->left != req->cryptlen)
+			return;
+		goto out;
+	}
+
 	subreq = &rctx->subreq;
 	subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
 
@@ -393,6 +411,7 @@ static void decrypt_done(struct crypto_async_request *areq, int err)
 	if (rctx->left)
 		return;
 
+out:
 	skcipher_request_complete(req, err);
 }
 
diff --git a/crypto/lz4.c b/crypto/lz4.c
index 71eff9b01b12..2ce2660d3519 100644
--- a/crypto/lz4.c
+++ b/crypto/lz4.c
@@ -97,7 +97,7 @@ static int __lz4_decompress_crypto(const u8 *src, unsigned int slen,
 	int out_len = LZ4_decompress_safe(src, dst, slen, *dlen);
 
 	if (out_len < 0)
-		return out_len;
+		return -EINVAL;
 
 	*dlen = out_len;
 	return 0;
diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c
index 03a34a8109c0..2be14f054daf 100644
--- a/crypto/lz4hc.c
+++ b/crypto/lz4hc.c
@@ -98,7 +98,7 @@ static int __lz4hc_decompress_crypto(const u8 *src, unsigned int slen,
 	int out_len = LZ4_decompress_safe(src, dst, slen, *dlen);
 
 	if (out_len < 0)
-		return out_len;
+		return -EINVAL;
 
 	*dlen = out_len;
 	return 0;
diff --git a/crypto/md5.c b/crypto/md5.c
index 2355a7c25c45..f7ae1a48225b 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -21,9 +21,11 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/cryptohash.h>
 #include <asm/byteorder.h>
 
+#define MD5_DIGEST_WORDS 4
+#define MD5_MESSAGE_BYTES 64
+
 const u8 md5_zero_message_hash[MD5_DIGEST_SIZE] = {
 	0xd4, 0x1d, 0x8c, 0xd9, 0x8f, 0x00, 0xb2, 0x04,
 	0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
@@ -47,6 +49,97 @@ static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
 	}
 }
 
+#define F1(x, y, z)	(z ^ (x & (y ^ z)))
+#define F2(x, y, z)	F1(z, x, y)
+#define F3(x, y, z)	(x ^ y ^ z)
+#define F4(x, y, z)	(y ^ (x | ~z))
+
+#define MD5STEP(f, w, x, y, z, in, s) \
+	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
+
+static void md5_transform(__u32 *hash, __u32 const *in)
+{
+	u32 a, b, c, d;
+
+	a = hash[0];
+	b = hash[1];
+	c = hash[2];
+	d = hash[3];
+
+	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
+	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
+	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
+	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
+	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
+	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
+	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
+	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
+	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
+	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
+	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
+	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
+	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
+	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
+	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
+	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
+
+	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
+	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
+	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
+	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
+	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
+	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
+	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
+	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
+	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
+	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
+	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
+	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
+	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
+	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
+	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
+	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
+
+	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
+	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
+	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
+	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
+	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
+	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
+	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
+	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
+	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
+	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
+	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
+	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
+	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
+	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
+	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
+	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
+
+	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
+	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
+	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
+	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
+	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
+	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
+	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
+	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
+	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
+	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
+	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
+	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
+	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
+	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
+	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
+	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
+
+	hash[0] += a;
+	hash[1] += b;
+	hash[2] += c;
+	hash[3] += d;
+}
+
 static inline void md5_transform_helper(struct md5_state *ctx)
 {
 	le32_to_cpu_array(ctx->block, sizeof(ctx->block) / sizeof(u32));
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 6b048b36312d..ae1d3cf209e4 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -353,5 +353,34 @@ int crypto_unregister_scomp(struct scomp_alg *alg)
 }
 EXPORT_SYMBOL_GPL(crypto_unregister_scomp);
 
+int crypto_register_scomps(struct scomp_alg *algs, int count)
+{
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_scomp(&algs[i]);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (--i; i >= 0; --i)
+		crypto_unregister_scomp(&algs[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_register_scomps);
+
+void crypto_unregister_scomps(struct scomp_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_scomp(&algs[i]);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_scomps);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Synchronous compression type");
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f9c378af3907..6f5f3ed8376c 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -83,47 +83,47 @@ struct tcrypt_result {
 
 struct aead_test_suite {
 	struct {
-		struct aead_testvec *vecs;
+		const struct aead_testvec *vecs;
 		unsigned int count;
 	} enc, dec;
 };
 
 struct cipher_test_suite {
 	struct {
-		struct cipher_testvec *vecs;
+		const struct cipher_testvec *vecs;
 		unsigned int count;
 	} enc, dec;
 };
 
 struct comp_test_suite {
 	struct {
-		struct comp_testvec *vecs;
+		const struct comp_testvec *vecs;
 		unsigned int count;
 	} comp, decomp;
 };
 
 struct hash_test_suite {
-	struct hash_testvec *vecs;
+	const struct hash_testvec *vecs;
 	unsigned int count;
 };
 
 struct cprng_test_suite {
-	struct cprng_testvec *vecs;
+	const struct cprng_testvec *vecs;
 	unsigned int count;
 };
 
 struct drbg_test_suite {
-	struct drbg_testvec *vecs;
+	const struct drbg_testvec *vecs;
 	unsigned int count;
 };
 
 struct akcipher_test_suite {
-	struct akcipher_testvec *vecs;
+	const struct akcipher_testvec *vecs;
 	unsigned int count;
 };
 
 struct kpp_test_suite {
-	struct kpp_testvec *vecs;
+	const struct kpp_testvec *vecs;
 	unsigned int count;
 };
 
@@ -145,7 +145,8 @@ struct alg_test_desc {
 	} suite;
 };
 
-static unsigned int IDX[8] = { IDX1, IDX2, IDX3, IDX4, IDX5, IDX6, IDX7, IDX8 };
+static const unsigned int IDX[8] = {
+	IDX1, IDX2, IDX3, IDX4, IDX5, IDX6, IDX7, IDX8 };
 
 static void hexdump(unsigned char *buf, unsigned int len)
 {
@@ -203,7 +204,7 @@ static int wait_async_op(struct tcrypt_result *tr, int ret)
 }
 
 static int ahash_partial_update(struct ahash_request **preq,
-	struct crypto_ahash *tfm, struct hash_testvec *template,
+	struct crypto_ahash *tfm, const struct hash_testvec *template,
 	void *hash_buff, int k, int temp, struct scatterlist *sg,
 	const char *algo, char *result, struct tcrypt_result *tresult)
 {
@@ -260,9 +261,9 @@ out_nostate:
 	return ret;
 }
 
-static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
-		       unsigned int tcount, bool use_digest,
-		       const int align_offset)
+static int __test_hash(struct crypto_ahash *tfm,
+		       const struct hash_testvec *template, unsigned int tcount,
+		       bool use_digest, const int align_offset)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm));
 	size_t digest_size = crypto_ahash_digestsize(tfm);
@@ -538,7 +539,8 @@ out_nobuf:
 	return ret;
 }
 
-static int test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
+static int test_hash(struct crypto_ahash *tfm,
+		     const struct hash_testvec *template,
 		     unsigned int tcount, bool use_digest)
 {
 	unsigned int alignmask;
@@ -566,7 +568,7 @@ static int test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 }
 
 static int __test_aead(struct crypto_aead *tfm, int enc,
-		       struct aead_testvec *template, unsigned int tcount,
+		       const struct aead_testvec *template, unsigned int tcount,
 		       const bool diff_dst, const int align_offset)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_aead_tfm(tfm));
@@ -957,7 +959,7 @@ out_noxbuf:
 }
 
 static int test_aead(struct crypto_aead *tfm, int enc,
-		     struct aead_testvec *template, unsigned int tcount)
+		     const struct aead_testvec *template, unsigned int tcount)
 {
 	unsigned int alignmask;
 	int ret;
@@ -990,7 +992,8 @@ static int test_aead(struct crypto_aead *tfm, int enc,
 }
 
 static int test_cipher(struct crypto_cipher *tfm, int enc,
-		       struct cipher_testvec *template, unsigned int tcount)
+		       const struct cipher_testvec *template,
+		       unsigned int tcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_cipher_tfm(tfm));
 	unsigned int i, j, k;
@@ -1068,7 +1071,8 @@ out_nobuf:
 }
 
 static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
-			   struct cipher_testvec *template, unsigned int tcount,
+			   const struct cipher_testvec *template,
+			   unsigned int tcount,
 			   const bool diff_dst, const int align_offset)
 {
 	const char *algo =
@@ -1332,7 +1336,8 @@ out_nobuf:
 }
 
 static int test_skcipher(struct crypto_skcipher *tfm, int enc,
-			 struct cipher_testvec *template, unsigned int tcount)
+			 const struct cipher_testvec *template,
+			 unsigned int tcount)
 {
 	unsigned int alignmask;
 	int ret;
@@ -1364,8 +1369,10 @@ static int test_skcipher(struct crypto_skcipher *tfm, int enc,
 	return 0;
 }
 
-static int test_comp(struct crypto_comp *tfm, struct comp_testvec *ctemplate,
-		     struct comp_testvec *dtemplate, int ctcount, int dtcount)
+static int test_comp(struct crypto_comp *tfm,
+		     const struct comp_testvec *ctemplate,
+		     const struct comp_testvec *dtemplate,
+		     int ctcount, int dtcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_comp_tfm(tfm));
 	unsigned int i;
@@ -1444,12 +1451,14 @@ out:
 	return ret;
 }
 
-static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
-		      struct comp_testvec *dtemplate, int ctcount, int dtcount)
+static int test_acomp(struct crypto_acomp *tfm,
+		      const struct comp_testvec *ctemplate,
+		      const struct comp_testvec *dtemplate,
+		      int ctcount, int dtcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm));
 	unsigned int i;
-	char *output;
+	char *output, *decomp_out;
 	int ret;
 	struct scatterlist src, dst;
 	struct acomp_req *req;
@@ -1459,6 +1468,12 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 	if (!output)
 		return -ENOMEM;
 
+	decomp_out = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!decomp_out) {
+		kfree(output);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
@@ -1497,7 +1512,23 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			goto out;
 		}
 
-		if (req->dlen != ctemplate[i].outlen) {
+		ilen = req->dlen;
+		dlen = COMP_BUF_SIZE;
+		sg_init_one(&src, output, ilen);
+		sg_init_one(&dst, decomp_out, dlen);
+		init_completion(&result.completion);
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
+
+		ret = wait_async_op(&result, crypto_acomp_decompress(req));
+		if (ret) {
+			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
+			       i + 1, algo, -ret);
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
+		}
+
+		if (req->dlen != ctemplate[i].inlen) {
 			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
@@ -1506,7 +1537,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			goto out;
 		}
 
-		if (memcmp(output, ctemplate[i].output, req->dlen)) {
+		if (memcmp(input_vec, decomp_out, req->dlen)) {
 			pr_err("alg: acomp: Compression test %d failed for %s\n",
 			       i + 1, algo);
 			hexdump(output, req->dlen);
@@ -1584,11 +1615,13 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 	ret = 0;
 
 out:
+	kfree(decomp_out);
 	kfree(output);
 	return ret;
 }
 
-static int test_cprng(struct crypto_rng *tfm, struct cprng_testvec *template,
+static int test_cprng(struct crypto_rng *tfm,
+		      const struct cprng_testvec *template,
 		      unsigned int tcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_rng_tfm(tfm));
@@ -1865,7 +1898,7 @@ static int alg_test_cprng(const struct alg_test_desc *desc, const char *driver,
 }
 
 
-static int drbg_cavs_test(struct drbg_testvec *test, int pr,
+static int drbg_cavs_test(const struct drbg_testvec *test, int pr,
 			  const char *driver, u32 type, u32 mask)
 {
 	int ret = -EAGAIN;
@@ -1939,7 +1972,7 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
 	int err = 0;
 	int pr = 0;
 	int i = 0;
-	struct drbg_testvec *template = desc->suite.drbg.vecs;
+	const struct drbg_testvec *template = desc->suite.drbg.vecs;
 	unsigned int tcount = desc->suite.drbg.count;
 
 	if (0 == memcmp(driver, "drbg_pr_", 8))
@@ -1958,7 +1991,7 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
 
 }
 
-static int do_test_kpp(struct crypto_kpp *tfm, struct kpp_testvec *vec,
+static int do_test_kpp(struct crypto_kpp *tfm, const struct kpp_testvec *vec,
 		       const char *alg)
 {
 	struct kpp_request *req;
@@ -2050,7 +2083,7 @@ free_req:
 }
 
 static int test_kpp(struct crypto_kpp *tfm, const char *alg,
-		    struct kpp_testvec *vecs, unsigned int tcount)
+		    const struct kpp_testvec *vecs, unsigned int tcount)
 {
 	int ret, i;
 
@@ -2086,7 +2119,7 @@ static int alg_test_kpp(const struct alg_test_desc *desc, const char *driver,
 }
 
 static int test_akcipher_one(struct crypto_akcipher *tfm,
-			     struct akcipher_testvec *vecs)
+			     const struct akcipher_testvec *vecs)
 {
 	char *xbuf[XBUFSIZE];
 	struct akcipher_request *req;
@@ -2206,7 +2239,8 @@ free_xbuf:
 }
 
 static int test_akcipher(struct crypto_akcipher *tfm, const char *alg,
-			 struct akcipher_testvec *vecs, unsigned int tcount)
+			 const struct akcipher_testvec *vecs,
+			 unsigned int tcount)
 {
 	const char *algo =
 		crypto_tfm_alg_driver_name(crypto_akcipher_tfm(tfm));
@@ -2634,6 +2668,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "ctr(des3_ede)",
 		.test = alg_test_skcipher,
+		.fips_allowed = 1,
 		.suite = {
 			.cipher = {
 				.enc = __VECS(des3_ede_ctr_enc_tv_template),
@@ -2875,6 +2910,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "ecb(cipher_null)",
 		.test = alg_test_null,
+		.fips_allowed = 1,
 	}, {
 		.alg = "ecb(des)",
 		.test = alg_test_skcipher,
@@ -3477,6 +3513,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 				.dec = __VECS(tf_xts_dec_tv_template)
 			}
 		}
+	}, {
+		.alg = "zlib-deflate",
+		.test = alg_test_comp,
+		.fips_allowed = 1,
+		.suite = {
+			.comp = {
+				.comp = __VECS(zlib_deflate_comp_tv_template),
+				.decomp = __VECS(zlib_deflate_decomp_tv_template)
+			}
+		}
 	}
 };
 
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 03f473116f78..429357339dcc 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -34,9 +34,9 @@
 
 struct hash_testvec {
 	/* only used with keyed hash algorithms */
-	char *key;
-	char *plaintext;
-	char *digest;
+	const char *key;
+	const char *plaintext;
+	const char *digest;
 	unsigned char tap[MAX_TAP];
 	unsigned short psize;
 	unsigned char np;
@@ -63,11 +63,11 @@ struct hash_testvec {
  */
 
 struct cipher_testvec {
-	char *key;
-	char *iv;
-	char *iv_out;
-	char *input;
-	char *result;
+	const char *key;
+	const char *iv;
+	const char *iv_out;
+	const char *input;
+	const char *result;
 	unsigned short tap[MAX_TAP];
 	int np;
 	unsigned char also_non_np;
@@ -80,11 +80,11 @@ struct cipher_testvec {
 };
 
 struct aead_testvec {
-	char *key;
-	char *iv;
-	char *input;
-	char *assoc;
-	char *result;
+	const char *key;
+	const char *iv;
+	const char *input;
+	const char *assoc;
+	const char *result;
 	unsigned char tap[MAX_TAP];
 	unsigned char atap[MAX_TAP];
 	int np;
@@ -99,10 +99,10 @@ struct aead_testvec {
 };
 
 struct cprng_testvec {
-	char *key;
-	char *dt;
-	char *v;
-	char *result;
+	const char *key;
+	const char *dt;
+	const char *v;
+	const char *result;
 	unsigned char klen;
 	unsigned short dtlen;
 	unsigned short vlen;
@@ -111,24 +111,24 @@ struct cprng_testvec {
 };
 
 struct drbg_testvec {
-	unsigned char *entropy;
+	const unsigned char *entropy;
 	size_t entropylen;
-	unsigned char *entpra;
-	unsigned char *entprb;
+	const unsigned char *entpra;
+	const unsigned char *entprb;
 	size_t entprlen;
-	unsigned char *addtla;
-	unsigned char *addtlb;
+	const unsigned char *addtla;
+	const unsigned char *addtlb;
 	size_t addtllen;
-	unsigned char *pers;
+	const unsigned char *pers;
 	size_t perslen;
-	unsigned char *expected;
+	const unsigned char *expected;
 	size_t expectedlen;
 };
 
 struct akcipher_testvec {
-	unsigned char *key;
-	unsigned char *m;
-	unsigned char *c;
+	const unsigned char *key;
+	const unsigned char *m;
+	const unsigned char *c;
 	unsigned int key_len;
 	unsigned int m_size;
 	unsigned int c_size;
@@ -136,22 +136,22 @@ struct akcipher_testvec {
 };
 
 struct kpp_testvec {
-	unsigned char *secret;
-	unsigned char *b_public;
-	unsigned char *expected_a_public;
-	unsigned char *expected_ss;
+	const unsigned char *secret;
+	const unsigned char *b_public;
+	const unsigned char *expected_a_public;
+	const unsigned char *expected_ss;
 	unsigned short secret_size;
 	unsigned short b_public_size;
 	unsigned short expected_a_public_size;
 	unsigned short expected_ss_size;
 };
 
-static char zeroed_string[48];
+static const char zeroed_string[48];
 
 /*
  * RSA test vectors. Borrowed from openSSL.
  */
-static struct akcipher_testvec rsa_tv_template[] = {
+static const struct akcipher_testvec rsa_tv_template[] = {
 	{
 #ifndef CONFIG_CRYPTO_FIPS
 	.key =
@@ -538,7 +538,7 @@ static struct akcipher_testvec rsa_tv_template[] = {
 	}
 };
 
-struct kpp_testvec dh_tv_template[] = {
+static const struct kpp_testvec dh_tv_template[] = {
 	{
 	.secret =
 #ifdef __LITTLE_ENDIAN
@@ -755,7 +755,7 @@ struct kpp_testvec dh_tv_template[] = {
 	}
 };
 
-struct kpp_testvec ecdh_tv_template[] = {
+static const struct kpp_testvec ecdh_tv_template[] = {
 	{
 #ifndef CONFIG_CRYPTO_FIPS
 	.secret =
@@ -846,7 +846,7 @@ struct kpp_testvec ecdh_tv_template[] = {
 /*
  * MD4 test vectors from RFC1320
  */
-static struct hash_testvec md4_tv_template [] = {
+static const struct hash_testvec md4_tv_template[] = {
 	{
 		.plaintext = "",
 		.digest	= "\x31\xd6\xcf\xe0\xd1\x6a\xe9\x31"
@@ -887,7 +887,7 @@ static struct hash_testvec md4_tv_template [] = {
 	},
 };
 
-static struct hash_testvec sha3_224_tv_template[] = {
+static const struct hash_testvec sha3_224_tv_template[] = {
 	{
 		.plaintext = "",
 		.digest	= "\x6b\x4e\x03\x42\x36\x67\xdb\xb7"
@@ -912,7 +912,7 @@ static struct hash_testvec sha3_224_tv_template[] = {
 	},
 };
 
-static struct hash_testvec sha3_256_tv_template[] = {
+static const struct hash_testvec sha3_256_tv_template[] = {
 	{
 		.plaintext = "",
 		.digest	= "\xa7\xff\xc6\xf8\xbf\x1e\xd7\x66"
@@ -938,7 +938,7 @@ static struct hash_testvec sha3_256_tv_template[] = {
 };
 
 
-static struct hash_testvec sha3_384_tv_template[] = {
+static const struct hash_testvec sha3_384_tv_template[] = {
 	{
 		.plaintext = "",
 		.digest	= "\x0c\x63\xa7\x5b\x84\x5e\x4f\x7d"
@@ -970,7 +970,7 @@ static struct hash_testvec sha3_384_tv_template[] = {
 };
 
 
-static struct hash_testvec sha3_512_tv_template[] = {
+static const struct hash_testvec sha3_512_tv_template[] = {
 	{
 		.plaintext = "",
 		.digest	= "\xa6\x9f\x73\xcc\xa2\x3a\x9a\xc5"
@@ -1011,7 +1011,7 @@ static struct hash_testvec sha3_512_tv_template[] = {
 /*
  * MD5 test vectors from RFC1321
  */
-static struct hash_testvec md5_tv_template[] = {
+static const struct hash_testvec md5_tv_template[] = {
 	{
 		.digest	= "\xd4\x1d\x8c\xd9\x8f\x00\xb2\x04"
 			  "\xe9\x80\x09\x98\xec\xf8\x42\x7e",
@@ -1055,7 +1055,7 @@ static struct hash_testvec md5_tv_template[] = {
 /*
  * RIPEMD-128 test vectors from ISO/IEC 10118-3:2004(E)
  */
-static struct hash_testvec rmd128_tv_template[] = {
+static const struct hash_testvec rmd128_tv_template[] = {
 	{
 		.digest	= "\xcd\xf2\x62\x13\xa1\x50\xdc\x3e"
 			  "\xcb\x61\x0f\x18\xf6\xb3\x8b\x46",
@@ -1117,7 +1117,7 @@ static struct hash_testvec rmd128_tv_template[] = {
 /*
  * RIPEMD-160 test vectors from ISO/IEC 10118-3:2004(E)
  */
-static struct hash_testvec rmd160_tv_template[] = {
+static const struct hash_testvec rmd160_tv_template[] = {
 	{
 		.digest	= "\x9c\x11\x85\xa5\xc5\xe9\xfc\x54\x61\x28"
 			  "\x08\x97\x7e\xe8\xf5\x48\xb2\x25\x8d\x31",
@@ -1179,7 +1179,7 @@ static struct hash_testvec rmd160_tv_template[] = {
 /*
  * RIPEMD-256 test vectors
  */
-static struct hash_testvec rmd256_tv_template[] = {
+static const struct hash_testvec rmd256_tv_template[] = {
 	{
 		.digest	= "\x02\xba\x4c\x4e\x5f\x8e\xcd\x18"
 			  "\x77\xfc\x52\xd6\x4d\x30\xe3\x7a"
@@ -1245,7 +1245,7 @@ static struct hash_testvec rmd256_tv_template[] = {
 /*
  * RIPEMD-320 test vectors
  */
-static struct hash_testvec rmd320_tv_template[] = {
+static const struct hash_testvec rmd320_tv_template[] = {
 	{
 		.digest	= "\x22\xd6\x5d\x56\x61\x53\x6c\xdc\x75\xc1"
 			  "\xfd\xf5\xc6\xde\x7b\x41\xb9\xf2\x73\x25"
@@ -1308,7 +1308,7 @@ static struct hash_testvec rmd320_tv_template[] = {
 	}
 };
 
-static struct hash_testvec crct10dif_tv_template[] = {
+static const struct hash_testvec crct10dif_tv_template[] = {
 	{
 		.plaintext	= "abc",
 		.psize		= 3,
@@ -1358,7 +1358,7 @@ static struct hash_testvec crct10dif_tv_template[] = {
  * SHA1 test vectors  from from FIPS PUB 180-1
  * Long vector from CAVS 5.0
  */
-static struct hash_testvec sha1_tv_template[] = {
+static const struct hash_testvec sha1_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -1548,7 +1548,7 @@ static struct hash_testvec sha1_tv_template[] = {
 /*
  * SHA224 test vectors from from FIPS PUB 180-2
  */
-static struct hash_testvec sha224_tv_template[] = {
+static const struct hash_testvec sha224_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -1720,7 +1720,7 @@ static struct hash_testvec sha224_tv_template[] = {
 /*
  * SHA256 test vectors from from NIST
  */
-static struct hash_testvec sha256_tv_template[] = {
+static const struct hash_testvec sha256_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -1891,7 +1891,7 @@ static struct hash_testvec sha256_tv_template[] = {
 /*
  * SHA384 test vectors from from NIST and kerneli
  */
-static struct hash_testvec sha384_tv_template[] = {
+static const struct hash_testvec sha384_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2083,7 +2083,7 @@ static struct hash_testvec sha384_tv_template[] = {
 /*
  * SHA512 test vectors from from NIST and kerneli
  */
-static struct hash_testvec sha512_tv_template[] = {
+static const struct hash_testvec sha512_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2290,7 +2290,7 @@ static struct hash_testvec sha512_tv_template[] = {
  * by Vincent Rijmen and Paulo S. L. M. Barreto as part of the NESSIE
  * submission
  */
-static struct hash_testvec wp512_tv_template[] = {
+static const struct hash_testvec wp512_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2386,7 +2386,7 @@ static struct hash_testvec wp512_tv_template[] = {
 	},
 };
 
-static struct hash_testvec wp384_tv_template[] = {
+static const struct hash_testvec wp384_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2466,7 +2466,7 @@ static struct hash_testvec wp384_tv_template[] = {
 	},
 };
 
-static struct hash_testvec wp256_tv_template[] = {
+static const struct hash_testvec wp256_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2533,7 +2533,7 @@ static struct hash_testvec wp256_tv_template[] = {
 /*
  * TIGER test vectors from Tiger website
  */
-static struct hash_testvec tgr192_tv_template[] = {
+static const struct hash_testvec tgr192_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2576,7 +2576,7 @@ static struct hash_testvec tgr192_tv_template[] = {
 	},
 };
 
-static struct hash_testvec tgr160_tv_template[] = {
+static const struct hash_testvec tgr160_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2619,7 +2619,7 @@ static struct hash_testvec tgr160_tv_template[] = {
 	},
 };
 
-static struct hash_testvec tgr128_tv_template[] = {
+static const struct hash_testvec tgr128_tv_template[] = {
 	{
 		.plaintext = "",
 		.psize	= 0,
@@ -2656,7 +2656,7 @@ static struct hash_testvec tgr128_tv_template[] = {
 	},
 };
 
-static struct hash_testvec ghash_tv_template[] =
+static const struct hash_testvec ghash_tv_template[] =
 {
 	{
 		.key	= "\xdf\xa6\xbf\x4d\xed\x81\xdb\x03"
@@ -2771,7 +2771,7 @@ static struct hash_testvec ghash_tv_template[] =
  * HMAC-MD5 test vectors from RFC2202
  * (These need to be fixed to not use strlen).
  */
-static struct hash_testvec hmac_md5_tv_template[] =
+static const struct hash_testvec hmac_md5_tv_template[] =
 {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b",
@@ -2851,7 +2851,7 @@ static struct hash_testvec hmac_md5_tv_template[] =
 /*
  * HMAC-RIPEMD128 test vectors from RFC2286
  */
-static struct hash_testvec hmac_rmd128_tv_template[] = {
+static const struct hash_testvec hmac_rmd128_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b",
 		.ksize	= 16,
@@ -2930,7 +2930,7 @@ static struct hash_testvec hmac_rmd128_tv_template[] = {
 /*
  * HMAC-RIPEMD160 test vectors from RFC2286
  */
-static struct hash_testvec hmac_rmd160_tv_template[] = {
+static const struct hash_testvec hmac_rmd160_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b",
 		.ksize	= 20,
@@ -3009,7 +3009,7 @@ static struct hash_testvec hmac_rmd160_tv_template[] = {
 /*
  * HMAC-SHA1 test vectors from RFC2202
  */
-static struct hash_testvec hmac_sha1_tv_template[] = {
+static const struct hash_testvec hmac_sha1_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b",
 		.ksize	= 20,
@@ -3090,7 +3090,7 @@ static struct hash_testvec hmac_sha1_tv_template[] = {
 /*
  * SHA224 HMAC test vectors from RFC4231
  */
-static struct hash_testvec hmac_sha224_tv_template[] = {
+static const struct hash_testvec hmac_sha224_tv_template[] = {
 	{
 		.key    = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			"\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -3203,7 +3203,7 @@ static struct hash_testvec hmac_sha224_tv_template[] = {
  * HMAC-SHA256 test vectors from
  * draft-ietf-ipsec-ciph-sha-256-01.txt
  */
-static struct hash_testvec hmac_sha256_tv_template[] = {
+static const struct hash_testvec hmac_sha256_tv_template[] = {
 	{
 		.key	= "\x01\x02\x03\x04\x05\x06\x07\x08"
 			  "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
@@ -3338,7 +3338,7 @@ static struct hash_testvec hmac_sha256_tv_template[] = {
 	},
 };
 
-static struct hash_testvec aes_cmac128_tv_template[] = {
+static const struct hash_testvec aes_cmac128_tv_template[] = {
 	{ /* From NIST Special Publication 800-38B, AES-128 */
 		.key		= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
 				  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
@@ -3413,7 +3413,7 @@ static struct hash_testvec aes_cmac128_tv_template[] = {
 	}
 };
 
-static struct hash_testvec aes_cbcmac_tv_template[] = {
+static const struct hash_testvec aes_cbcmac_tv_template[] = {
 	{
 		.key		= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
 				  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
@@ -3473,7 +3473,7 @@ static struct hash_testvec aes_cbcmac_tv_template[] = {
 	}
 };
 
-static struct hash_testvec des3_ede_cmac64_tv_template[] = {
+static const struct hash_testvec des3_ede_cmac64_tv_template[] = {
 /*
  * From NIST Special Publication 800-38B, Three Key TDEA
  * Corrected test vectors from:
@@ -3519,7 +3519,7 @@ static struct hash_testvec des3_ede_cmac64_tv_template[] = {
 	}
 };
 
-static struct hash_testvec aes_xcbc128_tv_template[] = {
+static const struct hash_testvec aes_xcbc128_tv_template[] = {
 	{
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
@@ -3585,35 +3585,35 @@ static struct hash_testvec aes_xcbc128_tv_template[] = {
 	}
 };
 
-static char vmac_string1[128] = {'\x01', '\x01', '\x01', '\x01',
-				'\x02', '\x03', '\x02', '\x02',
-				'\x02', '\x04', '\x01', '\x07',
-				'\x04', '\x01', '\x04', '\x03',};
-static char vmac_string2[128] = {'a', 'b', 'c',};
-static char vmac_string3[128] = {'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				'a', 'b', 'c', 'a', 'b', 'c',
-				};
+static const char vmac_string1[128] = {'\x01', '\x01', '\x01', '\x01',
+				       '\x02', '\x03', '\x02', '\x02',
+				       '\x02', '\x04', '\x01', '\x07',
+				       '\x04', '\x01', '\x04', '\x03',};
+static const char vmac_string2[128] = {'a', 'b', 'c',};
+static const char vmac_string3[128] = {'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				       'a', 'b', 'c', 'a', 'b', 'c',
+				      };
 
-static char vmac_string4[17] = {'b', 'c', 'e', 'f',
-				'i', 'j', 'l', 'm',
-				'o', 'p', 'r', 's',
-				't', 'u', 'w', 'x', 'z'};
+static const char vmac_string4[17] = {'b', 'c', 'e', 'f',
+				      'i', 'j', 'l', 'm',
+				      'o', 'p', 'r', 's',
+				      't', 'u', 'w', 'x', 'z'};
 
-static char vmac_string5[127] = {'r', 'm', 'b', 't', 'c',
-				 'o', 'l', 'k', ']', '%',
-				 '9', '2', '7', '!', 'A'};
+static const char vmac_string5[127] = {'r', 'm', 'b', 't', 'c',
+				       'o', 'l', 'k', ']', '%',
+				       '9', '2', '7', '!', 'A'};
 
-static char vmac_string6[129] = {'p', 't', '*', '7', 'l',
-				 'i', '!', '#', 'w', '0',
-				 'z', '/', '4', 'A', 'n'};
+static const char vmac_string6[129] = {'p', 't', '*', '7', 'l',
+				       'i', '!', '#', 'w', '0',
+				       'z', '/', '4', 'A', 'n'};
 
-static struct hash_testvec aes_vmac128_tv_template[] = {
+static const struct hash_testvec aes_vmac128_tv_template[] = {
 	{
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
@@ -3691,7 +3691,7 @@ static struct hash_testvec aes_vmac128_tv_template[] = {
  * SHA384 HMAC test vectors from RFC4231
  */
 
-static struct hash_testvec hmac_sha384_tv_template[] = {
+static const struct hash_testvec hmac_sha384_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -3789,7 +3789,7 @@ static struct hash_testvec hmac_sha384_tv_template[] = {
  * SHA512 HMAC test vectors from RFC4231
  */
 
-static struct hash_testvec hmac_sha512_tv_template[] = {
+static const struct hash_testvec hmac_sha512_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -3894,7 +3894,7 @@ static struct hash_testvec hmac_sha512_tv_template[] = {
 	},
 };
 
-static struct hash_testvec hmac_sha3_224_tv_template[] = {
+static const struct hash_testvec hmac_sha3_224_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -3983,7 +3983,7 @@ static struct hash_testvec hmac_sha3_224_tv_template[] = {
 	},
 };
 
-static struct hash_testvec hmac_sha3_256_tv_template[] = {
+static const struct hash_testvec hmac_sha3_256_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -4072,7 +4072,7 @@ static struct hash_testvec hmac_sha3_256_tv_template[] = {
 	},
 };
 
-static struct hash_testvec hmac_sha3_384_tv_template[] = {
+static const struct hash_testvec hmac_sha3_384_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -4169,7 +4169,7 @@ static struct hash_testvec hmac_sha3_384_tv_template[] = {
 	},
 };
 
-static struct hash_testvec hmac_sha3_512_tv_template[] = {
+static const struct hash_testvec hmac_sha3_512_tv_template[] = {
 	{
 		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
 			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
@@ -4278,7 +4278,7 @@ static struct hash_testvec hmac_sha3_512_tv_template[] = {
  * Poly1305 test vectors from RFC7539 A.3.
  */
 
-static struct hash_testvec poly1305_tv_template[] = {
+static const struct hash_testvec poly1305_tv_template[] = {
 	{ /* Test Vector #1 */
 		.plaintext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 				  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -4523,7 +4523,7 @@ static struct hash_testvec poly1305_tv_template[] = {
 /*
  * DES test vectors.
  */
-static struct cipher_testvec des_enc_tv_template[] = {
+static const struct cipher_testvec des_enc_tv_template[] = {
 	{ /* From Applied Cryptography */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
@@ -4697,7 +4697,7 @@ static struct cipher_testvec des_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des_dec_tv_template[] = {
+static const struct cipher_testvec des_dec_tv_template[] = {
 	{ /* From Applied Cryptography */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
@@ -4807,7 +4807,7 @@ static struct cipher_testvec des_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des_cbc_enc_tv_template[] = {
+static const struct cipher_testvec des_cbc_enc_tv_template[] = {
 	{ /* From OpenSSL */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
@@ -4933,7 +4933,7 @@ static struct cipher_testvec des_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des_cbc_dec_tv_template[] = {
+static const struct cipher_testvec des_cbc_dec_tv_template[] = {
 	{ /* FIPS Pub 81 */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
@@ -5042,7 +5042,7 @@ static struct cipher_testvec des_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des_ctr_enc_tv_template[] = {
+static const struct cipher_testvec des_ctr_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
@@ -5188,7 +5188,7 @@ static struct cipher_testvec des_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des_ctr_dec_tv_template[] = {
+static const struct cipher_testvec des_ctr_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
@@ -5334,7 +5334,7 @@ static struct cipher_testvec des_ctr_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des3_ede_enc_tv_template[] = {
+static const struct cipher_testvec des3_ede_enc_tv_template[] = {
 	{ /* These are from openssl */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\x55\x55\x55\x55\x55\x55\x55\x55"
@@ -5499,7 +5499,7 @@ static struct cipher_testvec des3_ede_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des3_ede_dec_tv_template[] = {
+static const struct cipher_testvec des3_ede_dec_tv_template[] = {
 	{ /* These are from openssl */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\x55\x55\x55\x55\x55\x55\x55\x55"
@@ -5664,7 +5664,7 @@ static struct cipher_testvec des3_ede_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
+static const struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 	{ /* Generated from openssl */
 		.key	= "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24"
 			  "\x44\x4D\x99\x5A\x12\xD6\x40\xC0"
@@ -5844,7 +5844,7 @@ static struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des3_ede_cbc_dec_tv_template[] = {
+static const struct cipher_testvec des3_ede_cbc_dec_tv_template[] = {
 	{ /* Generated from openssl */
 		.key	= "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24"
 			  "\x44\x4D\x99\x5A\x12\xD6\x40\xC0"
@@ -6024,7 +6024,7 @@ static struct cipher_testvec des3_ede_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
+static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
 			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
@@ -6302,7 +6302,7 @@ static struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
+static const struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
 			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
@@ -6583,7 +6583,7 @@ static struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
 /*
  * Blowfish test vectors.
  */
-static struct cipher_testvec bf_enc_tv_template[] = {
+static const struct cipher_testvec bf_enc_tv_template[] = {
 	{ /* DES test vectors from OpenSSL */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
@@ -6775,7 +6775,7 @@ static struct cipher_testvec bf_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec bf_dec_tv_template[] = {
+static const struct cipher_testvec bf_dec_tv_template[] = {
 	{ /* DES test vectors from OpenSSL */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
@@ -6967,7 +6967,7 @@ static struct cipher_testvec bf_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec bf_cbc_enc_tv_template[] = {
+static const struct cipher_testvec bf_cbc_enc_tv_template[] = {
 	{ /* From OpenSSL */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
@@ -7124,7 +7124,7 @@ static struct cipher_testvec bf_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec bf_cbc_dec_tv_template[] = {
+static const struct cipher_testvec bf_cbc_dec_tv_template[] = {
 	{ /* From OpenSSL */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
@@ -7281,7 +7281,7 @@ static struct cipher_testvec bf_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec bf_ctr_enc_tv_template[] = {
+static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -7693,7 +7693,7 @@ static struct cipher_testvec bf_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec bf_ctr_dec_tv_template[] = {
+static const struct cipher_testvec bf_ctr_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -8108,7 +8108,7 @@ static struct cipher_testvec bf_ctr_dec_tv_template[] = {
 /*
  * Twofish test vectors.
  */
-static struct cipher_testvec tf_enc_tv_template[] = {
+static const struct cipher_testvec tf_enc_tv_template[] = {
 	{
 		.key	= zeroed_string,
 		.klen	= 16,
@@ -8276,7 +8276,7 @@ static struct cipher_testvec tf_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_dec_tv_template[] = {
+static const struct cipher_testvec tf_dec_tv_template[] = {
 	{
 		.key	= zeroed_string,
 		.klen	= 16,
@@ -8444,7 +8444,7 @@ static struct cipher_testvec tf_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_cbc_enc_tv_template[] = {
+static const struct cipher_testvec tf_cbc_enc_tv_template[] = {
 	{ /* Generated with Nettle */
 		.key	= zeroed_string,
 		.klen	= 16,
@@ -8627,7 +8627,7 @@ static struct cipher_testvec tf_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_cbc_dec_tv_template[] = {
+static const struct cipher_testvec tf_cbc_dec_tv_template[] = {
 	{ /* Reverse of the first four above */
 		.key	= zeroed_string,
 		.klen	= 16,
@@ -8810,7 +8810,7 @@ static struct cipher_testvec tf_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_ctr_enc_tv_template[] = {
+static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -9221,7 +9221,7 @@ static struct cipher_testvec tf_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_ctr_dec_tv_template[] = {
+static const struct cipher_testvec tf_ctr_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -9632,7 +9632,7 @@ static struct cipher_testvec tf_ctr_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_lrw_enc_tv_template[] = {
+static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	{
 		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -9884,7 +9884,7 @@ static struct cipher_testvec tf_lrw_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_lrw_dec_tv_template[] = {
+static const struct cipher_testvec tf_lrw_dec_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	/* same as enc vectors with input and result reversed */
 	{
@@ -10137,7 +10137,7 @@ static struct cipher_testvec tf_lrw_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_xts_enc_tv_template[] = {
+static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 {
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -10479,7 +10479,7 @@ static struct cipher_testvec tf_xts_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tf_xts_dec_tv_template[] = {
+static const struct cipher_testvec tf_xts_dec_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	/* same as enc vectors with input and result reversed */
 	{
@@ -10826,7 +10826,7 @@ static struct cipher_testvec tf_xts_dec_tv_template[] = {
  * Serpent test vectors.  These are backwards because Serpent writes
  * octet sequences in right-to-left mode.
  */
-static struct cipher_testvec serpent_enc_tv_template[] = {
+static const struct cipher_testvec serpent_enc_tv_template[] = {
 	{
 		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
@@ -11002,7 +11002,7 @@ static struct cipher_testvec serpent_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tnepres_enc_tv_template[] = {
+static const struct cipher_testvec tnepres_enc_tv_template[] = {
 	{ /* KeySize=128, PT=0, I=1 */
 		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
@@ -11052,7 +11052,7 @@ static struct cipher_testvec tnepres_enc_tv_template[] = {
 };
 
 
-static struct cipher_testvec serpent_dec_tv_template[] = {
+static const struct cipher_testvec serpent_dec_tv_template[] = {
 	{
 		.input	= "\x12\x07\xfc\xce\x9b\xd0\xd6\x47"
 			  "\x6a\xe9\x8f\xbe\xd1\x43\xa0\xe2",
@@ -11228,7 +11228,7 @@ static struct cipher_testvec serpent_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec tnepres_dec_tv_template[] = {
+static const struct cipher_testvec tnepres_dec_tv_template[] = {
 	{
 		.input	= "\x41\xcc\x6b\x31\x59\x31\x45\x97"
 			  "\x6d\x6f\xbb\x38\x4b\x37\x21\x28",
@@ -11269,7 +11269,7 @@ static struct cipher_testvec tnepres_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_cbc_enc_tv_template[] = {
+static const struct cipher_testvec serpent_cbc_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -11410,7 +11410,7 @@ static struct cipher_testvec serpent_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_cbc_dec_tv_template[] = {
+static const struct cipher_testvec serpent_cbc_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -11551,7 +11551,7 @@ static struct cipher_testvec serpent_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_ctr_enc_tv_template[] = {
+static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -11962,7 +11962,7 @@ static struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_ctr_dec_tv_template[] = {
+static const struct cipher_testvec serpent_ctr_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -12373,7 +12373,7 @@ static struct cipher_testvec serpent_ctr_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_lrw_enc_tv_template[] = {
+static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	{
 		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -12625,7 +12625,7 @@ static struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_lrw_dec_tv_template[] = {
+static const struct cipher_testvec serpent_lrw_dec_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	/* same as enc vectors with input and result reversed */
 	{
@@ -12878,7 +12878,7 @@ static struct cipher_testvec serpent_lrw_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_xts_enc_tv_template[] = {
+static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	{
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -13220,7 +13220,7 @@ static struct cipher_testvec serpent_xts_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec serpent_xts_dec_tv_template[] = {
+static const struct cipher_testvec serpent_xts_dec_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	/* same as enc vectors with input and result reversed */
 	{
@@ -13564,7 +13564,7 @@ static struct cipher_testvec serpent_xts_dec_tv_template[] = {
 };
 
 /* Cast6 test vectors from RFC 2612 */
-static struct cipher_testvec cast6_enc_tv_template[] = {
+static const struct cipher_testvec cast6_enc_tv_template[] = {
 	{
 		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
 			  "\x0a\xf7\x56\x47\xf2\x9f\x61\x5d",
@@ -13735,7 +13735,7 @@ static struct cipher_testvec cast6_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_dec_tv_template[] = {
+static const struct cipher_testvec cast6_dec_tv_template[] = {
 	{
 		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
 			  "\x0a\xf7\x56\x47\xf2\x9f\x61\x5d",
@@ -13906,7 +13906,7 @@ static struct cipher_testvec cast6_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_cbc_enc_tv_template[] = {
+static const struct cipher_testvec cast6_cbc_enc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -14047,7 +14047,7 @@ static struct cipher_testvec cast6_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_cbc_dec_tv_template[] = {
+static const struct cipher_testvec cast6_cbc_dec_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -14188,7 +14188,7 @@ static struct cipher_testvec cast6_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_ctr_enc_tv_template[] = {
+static const struct cipher_testvec cast6_ctr_enc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -14345,7 +14345,7 @@ static struct cipher_testvec cast6_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_ctr_dec_tv_template[] = {
+static const struct cipher_testvec cast6_ctr_dec_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -14502,7 +14502,7 @@ static struct cipher_testvec cast6_ctr_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_lrw_enc_tv_template[] = {
+static const struct cipher_testvec cast6_lrw_enc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -14649,7 +14649,7 @@ static struct cipher_testvec cast6_lrw_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_lrw_dec_tv_template[] = {
+static const struct cipher_testvec cast6_lrw_dec_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -14796,7 +14796,7 @@ static struct cipher_testvec cast6_lrw_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_xts_enc_tv_template[] = {
+static const struct cipher_testvec cast6_xts_enc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -14945,7 +14945,7 @@ static struct cipher_testvec cast6_xts_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast6_xts_dec_tv_template[] = {
+static const struct cipher_testvec cast6_xts_dec_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -15098,7 +15098,7 @@ static struct cipher_testvec cast6_xts_dec_tv_template[] = {
 /*
  * AES test vectors.
  */
-static struct cipher_testvec aes_enc_tv_template[] = {
+static const struct cipher_testvec aes_enc_tv_template[] = {
 	{ /* From FIPS-197 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
@@ -15270,7 +15270,7 @@ static struct cipher_testvec aes_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_dec_tv_template[] = {
+static const struct cipher_testvec aes_dec_tv_template[] = {
 	{ /* From FIPS-197 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
@@ -15442,7 +15442,7 @@ static struct cipher_testvec aes_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_cbc_enc_tv_template[] = {
+static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 	{ /* From RFC 3602 */
 		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
 			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
@@ -15664,7 +15664,7 @@ static struct cipher_testvec aes_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_cbc_dec_tv_template[] = {
+static const struct cipher_testvec aes_cbc_dec_tv_template[] = {
 	{ /* From RFC 3602 */
 		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
 			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
@@ -15886,7 +15886,7 @@ static struct cipher_testvec aes_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct aead_testvec hmac_md5_ecb_cipher_null_enc_tv_template[] = {
+static const struct aead_testvec hmac_md5_ecb_cipher_null_enc_tv_template[] = {
 	{ /* Input data from RFC 2410 Case 1 */
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -15928,7 +15928,7 @@ static struct aead_testvec hmac_md5_ecb_cipher_null_enc_tv_template[] = {
 	},
 };
 
-static struct aead_testvec hmac_md5_ecb_cipher_null_dec_tv_template[] = {
+static const struct aead_testvec hmac_md5_ecb_cipher_null_dec_tv_template[] = {
 	{
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -15970,7 +15970,7 @@ static struct aead_testvec hmac_md5_ecb_cipher_null_dec_tv_template[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 	{ /* RFC 3602 Case 1 */
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -16239,7 +16239,7 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha1_ecb_cipher_null_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha1_ecb_cipher_null_enc_tv_temp[] = {
 	{ /* Input data from RFC 2410 Case 1 */
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -16285,7 +16285,7 @@ static struct aead_testvec hmac_sha1_ecb_cipher_null_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha1_ecb_cipher_null_dec_tv_temp[] = {
+static const struct aead_testvec hmac_sha1_ecb_cipher_null_dec_tv_temp[] = {
 	{
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -16331,7 +16331,7 @@ static struct aead_testvec hmac_sha1_ecb_cipher_null_dec_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 	{ /* RFC 3602 Case 1 */
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -16614,7 +16614,7 @@ static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 	{ /* RFC 3602 Case 1 */
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -16953,7 +16953,7 @@ static struct aead_testvec hmac_sha512_aes_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha1_des_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha1_des_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17012,7 +17012,7 @@ static struct aead_testvec hmac_sha1_des_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha224_des_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha224_des_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17071,7 +17071,7 @@ static struct aead_testvec hmac_sha224_des_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha256_des_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha256_des_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17132,7 +17132,7 @@ static struct aead_testvec hmac_sha256_des_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha384_des_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha384_des_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17197,7 +17197,7 @@ static struct aead_testvec hmac_sha384_des_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha512_des_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha512_des_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17266,7 +17266,7 @@ static struct aead_testvec hmac_sha512_des_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha1_des3_ede_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha1_des3_ede_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17327,7 +17327,7 @@ static struct aead_testvec hmac_sha1_des3_ede_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha224_des3_ede_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha224_des3_ede_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17388,7 +17388,7 @@ static struct aead_testvec hmac_sha224_des3_ede_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha256_des3_ede_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha256_des3_ede_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17451,7 +17451,7 @@ static struct aead_testvec hmac_sha256_des3_ede_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha384_des3_ede_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha384_des3_ede_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17518,7 +17518,7 @@ static struct aead_testvec hmac_sha384_des3_ede_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct aead_testvec hmac_sha512_des3_ede_cbc_enc_tv_temp[] = {
+static const struct aead_testvec hmac_sha512_des3_ede_cbc_enc_tv_temp[] = {
 	{ /*Generated with cryptopp*/
 #ifdef __LITTLE_ENDIAN
 		.key    = "\x08\x00"		/* rta length */
@@ -17589,7 +17589,7 @@ static struct aead_testvec hmac_sha512_des3_ede_cbc_enc_tv_temp[] = {
 	},
 };
 
-static struct cipher_testvec aes_lrw_enc_tv_template[] = {
+static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 	/* from http://grouper.ieee.org/groups/1619/email/pdf00017.pdf */
 	{ /* LRW-32-AES 1 */
 		.key    = "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -17842,7 +17842,7 @@ static struct cipher_testvec aes_lrw_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec aes_lrw_dec_tv_template[] = {
+static const struct cipher_testvec aes_lrw_dec_tv_template[] = {
 	/* from http://grouper.ieee.org/groups/1619/email/pdf00017.pdf */
 	/* same as enc vectors with input and result reversed */
 	{ /* LRW-32-AES 1 */
@@ -18096,7 +18096,7 @@ static struct cipher_testvec aes_lrw_dec_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec aes_xts_enc_tv_template[] = {
+static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 	/* http://grouper.ieee.org/groups/1619/email/pdf00086.pdf */
 	{ /* XTS-AES 1 */
 		.key    = "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -18439,7 +18439,7 @@ static struct cipher_testvec aes_xts_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec aes_xts_dec_tv_template[] = {
+static const struct cipher_testvec aes_xts_dec_tv_template[] = {
 	/* http://grouper.ieee.org/groups/1619/email/pdf00086.pdf */
 	{ /* XTS-AES 1 */
 		.key    = "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -18783,7 +18783,7 @@ static struct cipher_testvec aes_xts_dec_tv_template[] = {
 };
 
 
-static struct cipher_testvec aes_ctr_enc_tv_template[] = {
+static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 	{ /* From NIST Special Publication 800-38A, Appendix F.5 */
 		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
 			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
@@ -19138,7 +19138,7 @@ static struct cipher_testvec aes_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_ctr_dec_tv_template[] = {
+static const struct cipher_testvec aes_ctr_dec_tv_template[] = {
 	{ /* From NIST Special Publication 800-38A, Appendix F.5 */
 		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
 			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
@@ -19493,7 +19493,7 @@ static struct cipher_testvec aes_ctr_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
+static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 	{ /* From RFC 3686 */
 		.key	= "\xae\x68\x52\xf8\x12\x10\x67\xcc"
 			  "\x4b\xf7\xa5\x76\x55\x77\xf3\x9e"
@@ -20625,7 +20625,7 @@ static struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_ctr_rfc3686_dec_tv_template[] = {
+static const struct cipher_testvec aes_ctr_rfc3686_dec_tv_template[] = {
 	{ /* From RFC 3686 */
 		.key	= "\xae\x68\x52\xf8\x12\x10\x67\xcc"
 			  "\x4b\xf7\xa5\x76\x55\x77\xf3\x9e"
@@ -20716,7 +20716,7 @@ static struct cipher_testvec aes_ctr_rfc3686_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_ofb_enc_tv_template[] = {
+static const struct cipher_testvec aes_ofb_enc_tv_template[] = {
 	 /* From NIST Special Publication 800-38A, Appendix F.5 */
 	{
 		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
@@ -20745,7 +20745,7 @@ static struct cipher_testvec aes_ofb_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec aes_ofb_dec_tv_template[] = {
+static const struct cipher_testvec aes_ofb_dec_tv_template[] = {
 	 /* From NIST Special Publication 800-38A, Appendix F.5 */
 	{
 		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
@@ -20774,7 +20774,7 @@ static struct cipher_testvec aes_ofb_dec_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_gcm_enc_tv_template[] = {
+static const struct aead_testvec aes_gcm_enc_tv_template[] = {
 	{ /* From McGrew & Viega - http://citeseer.ist.psu.edu/656989.html */
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -20934,7 +20934,7 @@ static struct aead_testvec aes_gcm_enc_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_gcm_dec_tv_template[] = {
+static const struct aead_testvec aes_gcm_dec_tv_template[] = {
 	{ /* From McGrew & Viega - http://citeseer.ist.psu.edu/656989.html */
 		.key    = zeroed_string,
 		.klen	= 32,
@@ -21136,7 +21136,7 @@ static struct aead_testvec aes_gcm_dec_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
+static const struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 	{ /* Generated using Crypto++ */
 		.key    = zeroed_string,
 		.klen	= 20,
@@ -21749,7 +21749,7 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
+static const struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 	{ /* Generated using Crypto++ */
 		.key    = zeroed_string,
 		.klen	= 20,
@@ -22363,7 +22363,7 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_gcm_rfc4543_enc_tv_template[] = {
+static const struct aead_testvec aes_gcm_rfc4543_enc_tv_template[] = {
 	{ /* From draft-mcgrew-gcm-test-01 */
 		.key	= "\x4c\x80\xcd\xef\xbb\x5d\x10\xda"
 			  "\x90\x6a\xc7\x3c\x36\x13\xa6\x34"
@@ -22394,7 +22394,7 @@ static struct aead_testvec aes_gcm_rfc4543_enc_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
+static const struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
 	{ /* From draft-mcgrew-gcm-test-01 */
 		.key	= "\x4c\x80\xcd\xef\xbb\x5d\x10\xda"
 			  "\x90\x6a\xc7\x3c\x36\x13\xa6\x34"
@@ -22453,7 +22453,7 @@ static struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
 	},
 };
 
-static struct aead_testvec aes_ccm_enc_tv_template[] = {
+static const struct aead_testvec aes_ccm_enc_tv_template[] = {
 	{ /* From RFC 3610 */
 		.key	= "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
 			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf",
@@ -22737,7 +22737,7 @@ static struct aead_testvec aes_ccm_enc_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_ccm_dec_tv_template[] = {
+static const struct aead_testvec aes_ccm_dec_tv_template[] = {
 	{ /* From RFC 3610 */
 		.key	= "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
 			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf",
@@ -23069,7 +23069,7 @@ static struct aead_testvec aes_ccm_dec_tv_template[] = {
  * These vectors are copied/generated from the ones for rfc4106 with
  * the key truncated by one byte..
  */
-static struct aead_testvec aes_ccm_rfc4309_enc_tv_template[] = {
+static const struct aead_testvec aes_ccm_rfc4309_enc_tv_template[] = {
 	{ /* Generated using Crypto++ */
 		.key	= zeroed_string,
 		.klen	= 19,
@@ -23682,7 +23682,7 @@ static struct aead_testvec aes_ccm_rfc4309_enc_tv_template[] = {
 	}
 };
 
-static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[]	= {
+static const struct aead_testvec aes_ccm_rfc4309_dec_tv_template[]	= {
 	{ /* Generated using Crypto++ */
 		.key	= zeroed_string,
 		.klen	= 19,
@@ -24298,7 +24298,7 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[]	= {
 /*
  * ChaCha20-Poly1305 AEAD test vectors from RFC7539 2.8.2./A.5.
  */
-static struct aead_testvec rfc7539_enc_tv_template[] = {
+static const struct aead_testvec rfc7539_enc_tv_template[] = {
 	{
 		.key	= "\x80\x81\x82\x83\x84\x85\x86\x87"
 			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
@@ -24430,7 +24430,7 @@ static struct aead_testvec rfc7539_enc_tv_template[] = {
 	},
 };
 
-static struct aead_testvec rfc7539_dec_tv_template[] = {
+static const struct aead_testvec rfc7539_dec_tv_template[] = {
 	{
 		.key	= "\x80\x81\x82\x83\x84\x85\x86\x87"
 			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
@@ -24565,7 +24565,7 @@ static struct aead_testvec rfc7539_dec_tv_template[] = {
 /*
  * draft-irtf-cfrg-chacha20-poly1305
  */
-static struct aead_testvec rfc7539esp_enc_tv_template[] = {
+static const struct aead_testvec rfc7539esp_enc_tv_template[] = {
 	{
 		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
 			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
@@ -24653,7 +24653,7 @@ static struct aead_testvec rfc7539esp_enc_tv_template[] = {
 	},
 };
 
-static struct aead_testvec rfc7539esp_dec_tv_template[] = {
+static const struct aead_testvec rfc7539esp_dec_tv_template[] = {
 	{
 		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
 			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
@@ -24749,7 +24749,7 @@ static struct aead_testvec rfc7539esp_dec_tv_template[] = {
  * semiblock of the ciphertext from the test vector. For decryption, iv is
  * the first semiblock of the ciphertext.
  */
-static struct cipher_testvec aes_kw_enc_tv_template[] = {
+static const struct cipher_testvec aes_kw_enc_tv_template[] = {
 	{
 		.key	= "\x75\x75\xda\x3a\x93\x60\x7c\xc2"
 			  "\xbf\xd8\xce\xc7\xaa\xdf\xd9\xa6",
@@ -24764,7 +24764,7 @@ static struct cipher_testvec aes_kw_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec aes_kw_dec_tv_template[] = {
+static const struct cipher_testvec aes_kw_dec_tv_template[] = {
 	{
 		.key	= "\x80\xaa\x99\x73\x27\xa4\x80\x6b"
 			  "\x6a\x7a\x41\xa5\x2b\x86\xc3\x71"
@@ -24787,7 +24787,7 @@ static struct cipher_testvec aes_kw_dec_tv_template[] = {
  *     http://csrc.nist.gov/groups/STM/cavp/documents/rng/RNGVS.pdf
  * Only AES-128 is supported at this time.
  */
-static struct cprng_testvec ansi_cprng_aes_tv_template[] = {
+static const struct cprng_testvec ansi_cprng_aes_tv_template[] = {
 	{
 		.key	= "\xf3\xb1\x66\x6d\x13\x60\x72\x42"
 			  "\xed\x06\x1c\xab\xb8\xd4\x62\x02",
@@ -24883,7 +24883,7 @@ static struct cprng_testvec ansi_cprng_aes_tv_template[] = {
  * (Hash, HMAC, CTR) are tested with all permutations of use cases (w/ and
  * w/o personalization string, w/ and w/o additional input string).
  */
-static struct drbg_testvec drbg_pr_sha256_tv_template[] = {
+static const struct drbg_testvec drbg_pr_sha256_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\x72\x88\x4c\xcd\x6c\x85\x57\x70\xf7\x0b\x8b\x86"
@@ -25041,7 +25041,7 @@ static struct drbg_testvec drbg_pr_sha256_tv_template[] = {
 	},
 };
 
-static struct drbg_testvec drbg_pr_hmac_sha256_tv_template[] = {
+static const struct drbg_testvec drbg_pr_hmac_sha256_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\x99\x69\xe5\x4b\x47\x03\xff\x31\x78\x5b\x87\x9a"
@@ -25199,7 +25199,7 @@ static struct drbg_testvec drbg_pr_hmac_sha256_tv_template[] = {
 	},
 };
 
-static struct drbg_testvec drbg_pr_ctr_aes128_tv_template[] = {
+static const struct drbg_testvec drbg_pr_ctr_aes128_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\xd1\x44\xc6\x61\x81\x6d\xca\x9d\x15\x28\x8a\x42"
@@ -25323,7 +25323,7 @@ static struct drbg_testvec drbg_pr_ctr_aes128_tv_template[] = {
  * (Hash, HMAC, CTR) are tested with all permutations of use cases (w/ and
  * w/o personalization string, w/ and w/o additional input string).
  */
-static struct drbg_testvec drbg_nopr_sha256_tv_template[] = {
+static const struct drbg_testvec drbg_nopr_sha256_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\xa6\x5a\xd0\xf3\x45\xdb\x4e\x0e\xff\xe8\x75\xc3"
@@ -25445,7 +25445,7 @@ static struct drbg_testvec drbg_nopr_sha256_tv_template[] = {
 	},
 };
 
-static struct drbg_testvec drbg_nopr_hmac_sha256_tv_template[] = {
+static const struct drbg_testvec drbg_nopr_hmac_sha256_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\xca\x85\x19\x11\x34\x93\x84\xbf\xfe\x89\xde\x1c"
@@ -25567,7 +25567,7 @@ static struct drbg_testvec drbg_nopr_hmac_sha256_tv_template[] = {
 	},
 };
 
-static struct drbg_testvec drbg_nopr_ctr_aes192_tv_template[] = {
+static const struct drbg_testvec drbg_nopr_ctr_aes192_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\xc3\x5c\x2f\xa2\xa8\x9d\x52\xa1\x1f\xa3\x2a\xa9"
@@ -25591,7 +25591,7 @@ static struct drbg_testvec drbg_nopr_ctr_aes192_tv_template[] = {
 	},
 };
 
-static struct drbg_testvec drbg_nopr_ctr_aes256_tv_template[] = {
+static const struct drbg_testvec drbg_nopr_ctr_aes256_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\x36\x40\x19\x40\xfa\x8b\x1f\xba\x91\xa1\x66\x1f"
@@ -25615,7 +25615,7 @@ static struct drbg_testvec drbg_nopr_ctr_aes256_tv_template[] = {
 	},
 };
 
-static struct drbg_testvec drbg_nopr_ctr_aes128_tv_template[] = {
+static const struct drbg_testvec drbg_nopr_ctr_aes128_tv_template[] = {
 	{
 		.entropy = (unsigned char *)
 			"\x87\xe1\xc5\x32\x99\x7f\x57\xa3\x5c\x28\x6d\xe8"
@@ -25704,7 +25704,7 @@ static struct drbg_testvec drbg_nopr_ctr_aes128_tv_template[] = {
 };
 
 /* Cast5 test vectors from RFC 2144 */
-static struct cipher_testvec cast5_enc_tv_template[] = {
+static const struct cipher_testvec cast5_enc_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x12\x34\x56\x78"
 			  "\x23\x45\x67\x89\x34\x56\x78\x9a",
@@ -25865,7 +25865,7 @@ static struct cipher_testvec cast5_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast5_dec_tv_template[] = {
+static const struct cipher_testvec cast5_dec_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x12\x34\x56\x78"
 			  "\x23\x45\x67\x89\x34\x56\x78\x9a",
@@ -26026,7 +26026,7 @@ static struct cipher_testvec cast5_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast5_cbc_enc_tv_template[] = {
+static const struct cipher_testvec cast5_cbc_enc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
@@ -26164,7 +26164,7 @@ static struct cipher_testvec cast5_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast5_cbc_dec_tv_template[] = {
+static const struct cipher_testvec cast5_cbc_dec_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
@@ -26302,7 +26302,7 @@ static struct cipher_testvec cast5_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast5_ctr_enc_tv_template[] = {
+static const struct cipher_testvec cast5_ctr_enc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
@@ -26453,7 +26453,7 @@ static struct cipher_testvec cast5_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec cast5_ctr_dec_tv_template[] = {
+static const struct cipher_testvec cast5_ctr_dec_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
@@ -26607,7 +26607,7 @@ static struct cipher_testvec cast5_ctr_dec_tv_template[] = {
 /*
  * ARC4 test vectors from OpenSSL
  */
-static struct cipher_testvec arc4_enc_tv_template[] = {
+static const struct cipher_testvec arc4_enc_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
@@ -26673,7 +26673,7 @@ static struct cipher_testvec arc4_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec arc4_dec_tv_template[] = {
+static const struct cipher_testvec arc4_dec_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
@@ -26742,7 +26742,7 @@ static struct cipher_testvec arc4_dec_tv_template[] = {
 /*
  * TEA test vectors
  */
-static struct cipher_testvec tea_enc_tv_template[] = {
+static const struct cipher_testvec tea_enc_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -26785,7 +26785,7 @@ static struct cipher_testvec tea_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec tea_dec_tv_template[] = {
+static const struct cipher_testvec tea_dec_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -26831,7 +26831,7 @@ static struct cipher_testvec tea_dec_tv_template[] = {
 /*
  * XTEA test vectors
  */
-static struct cipher_testvec xtea_enc_tv_template[] = {
+static const struct cipher_testvec xtea_enc_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -26874,7 +26874,7 @@ static struct cipher_testvec xtea_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec xtea_dec_tv_template[] = {
+static const struct cipher_testvec xtea_dec_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -26920,7 +26920,7 @@ static struct cipher_testvec xtea_dec_tv_template[] = {
 /*
  * KHAZAD test vectors.
  */
-static struct cipher_testvec khazad_enc_tv_template[] = {
+static const struct cipher_testvec khazad_enc_tv_template[] = {
 	{
 		.key	= "\x80\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
@@ -26966,7 +26966,7 @@ static struct cipher_testvec khazad_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec khazad_dec_tv_template[] = {
+static const struct cipher_testvec khazad_dec_tv_template[] = {
 	{
 		.key	= "\x80\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
@@ -27016,7 +27016,7 @@ static struct cipher_testvec khazad_dec_tv_template[] = {
  * Anubis test vectors.
  */
 
-static struct cipher_testvec anubis_enc_tv_template[] = {
+static const struct cipher_testvec anubis_enc_tv_template[] = {
 	{
 		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
@@ -27079,7 +27079,7 @@ static struct cipher_testvec anubis_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec anubis_dec_tv_template[] = {
+static const struct cipher_testvec anubis_dec_tv_template[] = {
 	{
 		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
@@ -27142,7 +27142,7 @@ static struct cipher_testvec anubis_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec anubis_cbc_enc_tv_template[] = {
+static const struct cipher_testvec anubis_cbc_enc_tv_template[] = {
 	{
 		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
@@ -27177,7 +27177,7 @@ static struct cipher_testvec anubis_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec anubis_cbc_dec_tv_template[] = {
+static const struct cipher_testvec anubis_cbc_dec_tv_template[] = {
 	{
 		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
@@ -27215,7 +27215,7 @@ static struct cipher_testvec anubis_cbc_dec_tv_template[] = {
 /*
  * XETA test vectors
  */
-static struct cipher_testvec xeta_enc_tv_template[] = {
+static const struct cipher_testvec xeta_enc_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -27258,7 +27258,7 @@ static struct cipher_testvec xeta_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec xeta_dec_tv_template[] = {
+static const struct cipher_testvec xeta_dec_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -27304,7 +27304,7 @@ static struct cipher_testvec xeta_dec_tv_template[] = {
 /*
  * FCrypt test vectors
  */
-static struct cipher_testvec fcrypt_pcbc_enc_tv_template[] = {
+static const struct cipher_testvec fcrypt_pcbc_enc_tv_template[] = {
 	{ /* http://www.openafs.org/pipermail/openafs-devel/2000-December/005320.html */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
@@ -27365,7 +27365,7 @@ static struct cipher_testvec fcrypt_pcbc_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec fcrypt_pcbc_dec_tv_template[] = {
+static const struct cipher_testvec fcrypt_pcbc_dec_tv_template[] = {
 	{ /* http://www.openafs.org/pipermail/openafs-devel/2000-December/005320.html */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
@@ -27429,7 +27429,7 @@ static struct cipher_testvec fcrypt_pcbc_dec_tv_template[] = {
 /*
  * CAMELLIA test vectors.
  */
-static struct cipher_testvec camellia_enc_tv_template[] = {
+static const struct cipher_testvec camellia_enc_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
@@ -27729,7 +27729,7 @@ static struct cipher_testvec camellia_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_dec_tv_template[] = {
+static const struct cipher_testvec camellia_dec_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
@@ -28029,7 +28029,7 @@ static struct cipher_testvec camellia_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_cbc_enc_tv_template[] = {
+static const struct cipher_testvec camellia_cbc_enc_tv_template[] = {
 	{
 		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
 			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
@@ -28325,7 +28325,7 @@ static struct cipher_testvec camellia_cbc_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_cbc_dec_tv_template[] = {
+static const struct cipher_testvec camellia_cbc_dec_tv_template[] = {
 	{
 		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
 			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
@@ -28621,7 +28621,7 @@ static struct cipher_testvec camellia_cbc_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_ctr_enc_tv_template[] = {
+static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -29288,7 +29288,7 @@ static struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_ctr_dec_tv_template[] = {
+static const struct cipher_testvec camellia_ctr_dec_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -29955,7 +29955,7 @@ static struct cipher_testvec camellia_ctr_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_lrw_enc_tv_template[] = {
+static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	{
 		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -30207,7 +30207,7 @@ static struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_lrw_dec_tv_template[] = {
+static const struct cipher_testvec camellia_lrw_dec_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	/* same as enc vectors with input and result reversed */
 	{
@@ -30460,7 +30460,7 @@ static struct cipher_testvec camellia_lrw_dec_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_xts_enc_tv_template[] = {
+static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	{
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -30802,7 +30802,7 @@ static struct cipher_testvec camellia_xts_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec camellia_xts_dec_tv_template[] = {
+static const struct cipher_testvec camellia_xts_dec_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	/* same as enc vectors with input and result reversed */
 	{
@@ -31148,7 +31148,7 @@ static struct cipher_testvec camellia_xts_dec_tv_template[] = {
 /*
  * SEED test vectors
  */
-static struct cipher_testvec seed_enc_tv_template[] = {
+static const struct cipher_testvec seed_enc_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -31190,7 +31190,7 @@ static struct cipher_testvec seed_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec seed_dec_tv_template[] = {
+static const struct cipher_testvec seed_dec_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
@@ -31232,7 +31232,7 @@ static struct cipher_testvec seed_dec_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec salsa20_stream_enc_tv_template[] = {
+static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 	/*
 	* Testvectors from verified.test-vectors submitted to ECRYPT.
 	* They are truncated to size 39, 64, 111, 129 to test a variety
@@ -32401,7 +32401,7 @@ static struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 	},
 };
 
-static struct cipher_testvec chacha20_enc_tv_template[] = {
+static const struct cipher_testvec chacha20_enc_tv_template[] = {
 	{ /* RFC7539 A.2. Test Vector #1 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -32912,7 +32912,7 @@ static struct cipher_testvec chacha20_enc_tv_template[] = {
 /*
  * CTS (Cipher Text Stealing) mode tests
  */
-static struct cipher_testvec cts_mode_enc_tv_template[] = {
+static const struct cipher_testvec cts_mode_enc_tv_template[] = {
 	{ /* from rfc3962 */
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
@@ -33014,7 +33014,7 @@ static struct cipher_testvec cts_mode_enc_tv_template[] = {
 	}
 };
 
-static struct cipher_testvec cts_mode_dec_tv_template[] = {
+static const struct cipher_testvec cts_mode_dec_tv_template[] = {
 	{ /* from rfc3962 */
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
@@ -33132,7 +33132,7 @@ struct comp_testvec {
  * Params: winbits=-11, Z_DEFAULT_COMPRESSION, MAX_MEM_LEVEL.
  */
 
-static struct comp_testvec deflate_comp_tv_template[] = {
+static const struct comp_testvec deflate_comp_tv_template[] = {
 	{
 		.inlen	= 70,
 		.outlen	= 38,
@@ -33168,7 +33168,7 @@ static struct comp_testvec deflate_comp_tv_template[] = {
 	},
 };
 
-static struct comp_testvec deflate_decomp_tv_template[] = {
+static const struct comp_testvec deflate_decomp_tv_template[] = {
 	{
 		.inlen	= 122,
 		.outlen	= 191,
@@ -33204,10 +33204,85 @@ static struct comp_testvec deflate_decomp_tv_template[] = {
 	},
 };
 
+static const struct comp_testvec zlib_deflate_comp_tv_template[] = {
+	{
+		.inlen	= 70,
+		.outlen	= 44,
+		.input	= "Join us now and share the software "
+			"Join us now and share the software ",
+		.output	= "\x78\x5e\xf3\xca\xcf\xcc\x53\x28"
+			  "\x2d\x56\xc8\xcb\x2f\x57\x48\xcc"
+			  "\x4b\x51\x28\xce\x48\x2c\x4a\x55"
+			  "\x28\xc9\x48\x55\x28\xce\x4f\x2b"
+			  "\x29\x07\x71\xbc\x08\x2b\x01\x00"
+			  "\x7c\x65\x19\x3d",
+	}, {
+		.inlen	= 191,
+		.outlen	= 129,
+		.input	= "This document describes a compression method based on the DEFLATE"
+			"compression algorithm.  This document defines the application of "
+			"the DEFLATE algorithm to the IP Payload Compression Protocol.",
+		.output	= "\x78\x5e\x5d\xce\x41\x0a\xc3\x30"
+			  "\x0c\x04\xc0\xaf\xec\x0b\xf2\x87"
+			  "\xd2\xa6\x50\xe8\xc1\x07\x7f\x40"
+			  "\xb1\x95\x5a\x60\x5b\xc6\x56\x0f"
+			  "\xfd\x7d\x93\x1e\x42\xe8\x51\xec"
+			  "\xee\x20\x9f\x64\x20\x6a\x78\x17"
+			  "\xae\x86\xc8\x23\x74\x59\x78\x80"
+			  "\x10\xb4\xb4\xce\x63\x88\x56\x14"
+			  "\xb6\xa4\x11\x0b\x0d\x8e\xd8\x6e"
+			  "\x4b\x8c\xdb\x7c\x7f\x5e\xfc\x7c"
+			  "\xae\x51\x7e\x69\x17\x4b\x65\x02"
+			  "\xfc\x1f\xbc\x4a\xdd\xd8\x7d\x48"
+			  "\xad\x65\x09\x64\x3b\xac\xeb\xd9"
+			  "\xc2\x01\xc0\xf4\x17\x3c\x1c\x1c"
+			  "\x7d\xb2\x52\xc4\xf5\xf4\x8f\xeb"
+			  "\x6a\x1a\x34\x4f\x5f\x2e\x32\x45"
+			  "\x4e",
+	},
+};
+
+static const struct comp_testvec zlib_deflate_decomp_tv_template[] = {
+	{
+		.inlen	= 128,
+		.outlen	= 191,
+		.input	= "\x78\x9c\x5d\x8d\x31\x0e\xc2\x30"
+			  "\x10\x04\xbf\xb2\x2f\xc8\x1f\x10"
+			  "\x04\x09\x89\xc2\x85\x3f\x70\xb1"
+			  "\x2f\xf8\x24\xdb\x67\xd9\x47\xc1"
+			  "\xef\x49\x68\x12\x51\xae\x76\x67"
+			  "\xd6\x27\x19\x88\x1a\xde\x85\xab"
+			  "\x21\xf2\x08\x5d\x16\x1e\x20\x04"
+			  "\x2d\xad\xf3\x18\xa2\x15\x85\x2d"
+			  "\x69\xc4\x42\x83\x23\xb6\x6c\x89"
+			  "\x71\x9b\xef\xcf\x8b\x9f\xcf\x33"
+			  "\xca\x2f\xed\x62\xa9\x4c\x80\xff"
+			  "\x13\xaf\x52\x37\xed\x0e\x52\x6b"
+			  "\x59\x02\xd9\x4e\xe8\x7a\x76\x1d"
+			  "\x02\x98\xfe\x8a\x87\x83\xa3\x4f"
+			  "\x56\x8a\xb8\x9e\x8e\x5c\x57\xd3"
+			  "\xa0\x79\xfa\x02\x2e\x32\x45\x4e",
+		.output	= "This document describes a compression method based on the DEFLATE"
+			"compression algorithm.  This document defines the application of "
+			"the DEFLATE algorithm to the IP Payload Compression Protocol.",
+	}, {
+		.inlen	= 44,
+		.outlen	= 70,
+		.input	= "\x78\x9c\xf3\xca\xcf\xcc\x53\x28"
+			  "\x2d\x56\xc8\xcb\x2f\x57\x48\xcc"
+			  "\x4b\x51\x28\xce\x48\x2c\x4a\x55"
+			  "\x28\xc9\x48\x55\x28\xce\x4f\x2b"
+			  "\x29\x07\x71\xbc\x08\x2b\x01\x00"
+			  "\x7c\x65\x19\x3d",
+		.output	= "Join us now and share the software "
+			"Join us now and share the software ",
+	},
+};
+
 /*
  * LZO test vectors (null-terminated strings).
  */
-static struct comp_testvec lzo_comp_tv_template[] = {
+static const struct comp_testvec lzo_comp_tv_template[] = {
 	{
 		.inlen	= 70,
 		.outlen	= 57,
@@ -33247,7 +33322,7 @@ static struct comp_testvec lzo_comp_tv_template[] = {
 	},
 };
 
-static struct comp_testvec lzo_decomp_tv_template[] = {
+static const struct comp_testvec lzo_decomp_tv_template[] = {
 	{
 		.inlen	= 133,
 		.outlen	= 159,
@@ -33290,7 +33365,7 @@ static struct comp_testvec lzo_decomp_tv_template[] = {
  */
 #define MICHAEL_MIC_TEST_VECTORS 6
 
-static struct hash_testvec michael_mic_tv_template[] = {
+static const struct hash_testvec michael_mic_tv_template[] = {
 	{
 		.key = "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.ksize = 8,
@@ -33338,7 +33413,7 @@ static struct hash_testvec michael_mic_tv_template[] = {
 /*
  * CRC32 test vectors
  */
-static struct hash_testvec crc32_tv_template[] = {
+static const struct hash_testvec crc32_tv_template[] = {
 	{
 		.key = "\x87\xa9\xcb\xed",
 		.ksize = 4,
@@ -33770,7 +33845,7 @@ static struct hash_testvec crc32_tv_template[] = {
 /*
  * CRC32C test vectors
  */
-static struct hash_testvec crc32c_tv_template[] = {
+static const struct hash_testvec crc32c_tv_template[] = {
 	{
 		.psize = 0,
 		.digest = "\x00\x00\x00\x00",
@@ -34206,7 +34281,7 @@ static struct hash_testvec crc32c_tv_template[] = {
 /*
  * Blakcifn CRC test vectors
  */
-static struct hash_testvec bfin_crc_tv_template[] = {
+static const struct hash_testvec bfin_crc_tv_template[] = {
 	{
 		.psize = 0,
 		.digest = "\x00\x00\x00\x00",
@@ -34291,7 +34366,7 @@ static struct hash_testvec bfin_crc_tv_template[] = {
 
 };
 
-static struct comp_testvec lz4_comp_tv_template[] = {
+static const struct comp_testvec lz4_comp_tv_template[] = {
 	{
 		.inlen	= 255,
 		.outlen	= 218,
@@ -34322,7 +34397,7 @@ static struct comp_testvec lz4_comp_tv_template[] = {
 	},
 };
 
-static struct comp_testvec lz4_decomp_tv_template[] = {
+static const struct comp_testvec lz4_decomp_tv_template[] = {
 	{
 		.inlen	= 218,
 		.outlen	= 255,
@@ -34352,7 +34427,7 @@ static struct comp_testvec lz4_decomp_tv_template[] = {
 	},
 };
 
-static struct comp_testvec lz4hc_comp_tv_template[] = {
+static const struct comp_testvec lz4hc_comp_tv_template[] = {
 	{
 		.inlen	= 255,
 		.outlen	= 216,
@@ -34383,7 +34458,7 @@ static struct comp_testvec lz4hc_comp_tv_template[] = {
 	},
 };
 
-static struct comp_testvec lz4hc_decomp_tv_template[] = {
+static const struct comp_testvec lz4hc_decomp_tv_template[] = {
 	{
 		.inlen	= 216,
 		.outlen	= 255,
diff --git a/crypto/xts.c b/crypto/xts.c
index baeb34dd8582..d86c11a8c882 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -39,11 +39,11 @@ struct xts_instance_ctx {
 };
 
 struct rctx {
-	be128 buf[XTS_BUFFER_SIZE / sizeof(be128)];
+	le128 buf[XTS_BUFFER_SIZE / sizeof(le128)];
 
-	be128 t;
+	le128 t;
 
-	be128 *ext;
+	le128 *ext;
 
 	struct scatterlist srcbuf[2];
 	struct scatterlist dstbuf[2];
@@ -99,7 +99,7 @@ static int setkey(struct crypto_skcipher *parent, const u8 *key,
 static int post_crypt(struct skcipher_request *req)
 {
 	struct rctx *rctx = skcipher_request_ctx(req);
-	be128 *buf = rctx->ext ?: rctx->buf;
+	le128 *buf = rctx->ext ?: rctx->buf;
 	struct skcipher_request *subreq;
 	const int bs = XTS_BLOCK_SIZE;
 	struct skcipher_walk w;
@@ -112,12 +112,12 @@ static int post_crypt(struct skcipher_request *req)
 
 	while (w.nbytes) {
 		unsigned int avail = w.nbytes;
-		be128 *wdst;
+		le128 *wdst;
 
 		wdst = w.dst.virt.addr;
 
 		do {
-			be128_xor(wdst, buf++, wdst);
+			le128_xor(wdst, buf++, wdst);
 			wdst++;
 		} while ((avail -= bs) >= bs);
 
@@ -150,7 +150,7 @@ out:
 static int pre_crypt(struct skcipher_request *req)
 {
 	struct rctx *rctx = skcipher_request_ctx(req);
-	be128 *buf = rctx->ext ?: rctx->buf;
+	le128 *buf = rctx->ext ?: rctx->buf;
 	struct skcipher_request *subreq;
 	const int bs = XTS_BLOCK_SIZE;
 	struct skcipher_walk w;
@@ -174,15 +174,15 @@ static int pre_crypt(struct skcipher_request *req)
 
 	while (w.nbytes) {
 		unsigned int avail = w.nbytes;
-		be128 *wsrc;
-		be128 *wdst;
+		le128 *wsrc;
+		le128 *wdst;
 
 		wsrc = w.src.virt.addr;
 		wdst = w.dst.virt.addr;
 
 		do {
 			*buf++ = rctx->t;
-			be128_xor(wdst++, &rctx->t, wsrc++);
+			le128_xor(wdst++, &rctx->t, wsrc++);
 			gf128mul_x_ble(&rctx->t, &rctx->t);
 		} while ((avail -= bs) >= bs);
 
@@ -230,8 +230,11 @@ static int init_crypt(struct skcipher_request *req, crypto_completion_t done)
 
 	subreq->cryptlen = XTS_BUFFER_SIZE;
 	if (req->cryptlen > XTS_BUFFER_SIZE) {
-		subreq->cryptlen = min(req->cryptlen, (unsigned)PAGE_SIZE);
-		rctx->ext = kmalloc(subreq->cryptlen, gfp);
+		unsigned int n = min(req->cryptlen, (unsigned int)PAGE_SIZE);
+
+		rctx->ext = kmalloc(n, gfp);
+		if (rctx->ext)
+			subreq->cryptlen = n;
 	}
 
 	rctx->src = req->src;
@@ -283,6 +286,13 @@ static void encrypt_done(struct crypto_async_request *areq, int err)
 	struct rctx *rctx;
 
 	rctx = skcipher_request_ctx(req);
+
+	if (err == -EINPROGRESS) {
+		if (rctx->left != req->cryptlen)
+			return;
+		goto out;
+	}
+
 	subreq = &rctx->subreq;
 	subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
 
@@ -290,6 +300,7 @@ static void encrypt_done(struct crypto_async_request *areq, int err)
 	if (rctx->left)
 		return;
 
+out:
 	skcipher_request_complete(req, err);
 }
 
@@ -327,6 +338,13 @@ static void decrypt_done(struct crypto_async_request *areq, int err)
 	struct rctx *rctx;
 
 	rctx = skcipher_request_ctx(req);
+
+	if (err == -EINPROGRESS) {
+		if (rctx->left != req->cryptlen)
+			return;
+		goto out;
+	}
+
 	subreq = &rctx->subreq;
 	subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
 
@@ -334,6 +352,7 @@ static void decrypt_done(struct crypto_async_request *areq, int err)
 	if (rctx->left)
 		return;
 
+out:
 	skcipher_request_complete(req, err);
 }
 
@@ -350,8 +369,8 @@ int xts_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
 	const unsigned int max_blks = req->tbuflen / bsize;
 	struct blkcipher_walk walk;
 	unsigned int nblocks;
-	be128 *src, *dst, *t;
-	be128 *t_buf = req->tbuf;
+	le128 *src, *dst, *t;
+	le128 *t_buf = req->tbuf;
 	int err, i;
 
 	BUG_ON(max_blks < 1);
@@ -364,8 +383,8 @@ int xts_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
 		return err;
 
 	nblocks = min(nbytes / bsize, max_blks);
-	src = (be128 *)walk.src.virt.addr;
-	dst = (be128 *)walk.dst.virt.addr;
+	src = (le128 *)walk.src.virt.addr;
+	dst = (le128 *)walk.dst.virt.addr;
 
 	/* calculate first value of T */
 	req->tweak_fn(req->tweak_ctx, (u8 *)&t_buf[0], walk.iv);
@@ -381,7 +400,7 @@ first:
 				t = &t_buf[i];
 
 				/* PP <- T xor P */
-				be128_xor(dst + i, t, src + i);
+				le128_xor(dst + i, t, src + i);
 			}
 
 			/* CC <- E(Key2,PP) */
@@ -390,7 +409,7 @@ first:
 
 			/* C <- T xor CC */
 			for (i = 0; i < nblocks; i++)
-				be128_xor(dst + i, dst + i, &t_buf[i]);
+				le128_xor(dst + i, dst + i, &t_buf[i]);
 
 			src += nblocks;
 			dst += nblocks;
@@ -398,7 +417,7 @@ first:
 			nblocks = min(nbytes / bsize, max_blks);
 		} while (nblocks > 0);
 
-		*(be128 *)walk.iv = *t;
+		*(le128 *)walk.iv = *t;
 
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 		nbytes = walk.nbytes;
@@ -406,8 +425,8 @@ first:
 			break;
 
 		nblocks = min(nbytes / bsize, max_blks);
-		src = (be128 *)walk.src.virt.addr;
-		dst = (be128 *)walk.dst.virt.addr;
+		src = (le128 *)walk.src.virt.addr;
+		dst = (le128 *)walk.dst.virt.addr;
 	}
 
 	return err;
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 83e5f7e1a20d..18f3036fcb82 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -256,7 +256,7 @@ config ACPI_PROCESSOR
 
 config ACPI_IPMI
 	tristate "IPMI"
-	depends on IPMI_SI
+	depends on IPMI_HANDLER
 	default n
 	help
 	  This driver enables the ACPI to access the BMC controller. And it
@@ -440,7 +440,7 @@ config ACPI_CUSTOM_METHOD
 
 config ACPI_BGRT
 	bool "Boottime Graphics Resource Table support"
-	depends on EFI && X86
+	depends on EFI && (X86 || ARM64)
         help
 	  This driver adds support for exposing the ACPI Boottime Graphics
 	  Resource Table, which allows the operating system to obtain
@@ -469,9 +469,8 @@ config ACPI_WATCHDOG
 
 config ACPI_EXTLOG
 	tristate "Extended Error Log support"
-	depends on X86_MCE && X86_LOCAL_APIC
+	depends on X86_MCE && X86_LOCAL_APIC && EDAC
 	select UEFI_CPER
-	select RAS
 	default n
 	help
 	  Certain usages such as Predictive Failure Analysis (PFA) require
@@ -506,7 +505,7 @@ config CRC_PMIC_OPREGION
 
 config XPOWER_PMIC_OPREGION
 	bool "ACPI operation region support for XPower AXP288 PMIC"
-	depends on AXP288_ADC = y
+	depends on MFD_AXP20X_I2C
 	help
 	  This config adds ACPI operation region support for XPower AXP288 PMIC.
 
@@ -516,6 +515,12 @@ config BXT_WC_PMIC_OPREGION
 	help
 	  This config adds ACPI operation region support for BXT WhiskeyCove PMIC.
 
+config CHT_WC_PMIC_OPREGION
+	bool "ACPI operation region support for CHT Whiskey Cove PMIC"
+	depends on INTEL_SOC_PMIC_CHTWC
+	help
+	  This config adds ACPI operation region support for CHT Whiskey Cove PMIC.
+
 endif
 
 config ACPI_CONFIGFS
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index a391bbc48105..d78065cc9324 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -2,7 +2,6 @@
 # Makefile for the Linux ACPI interpreter
 #
 
-ccflags-y			:= -Os
 ccflags-$(CONFIG_ACPI_DEBUG)	+= -DACPI_DEBUG_OUTPUT
 
 #
@@ -102,6 +101,7 @@ obj-$(CONFIG_PMIC_OPREGION)	+= pmic/intel_pmic.o
 obj-$(CONFIG_CRC_PMIC_OPREGION) += pmic/intel_pmic_crc.o
 obj-$(CONFIG_XPOWER_PMIC_OPREGION) += pmic/intel_pmic_xpower.o
 obj-$(CONFIG_BXT_WC_PMIC_OPREGION) += pmic/intel_pmic_bxtwc.o
+obj-$(CONFIG_CHT_WC_PMIC_OPREGION) += pmic/intel_pmic_chtwc.o
 
 obj-$(CONFIG_ACPI_CONFIGFS)	+= acpi_configfs.o
 
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index f71b756b05c4..8f52483219ba 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -57,12 +57,23 @@ static int acpi_ac_add(struct acpi_device *device);
 static int acpi_ac_remove(struct acpi_device *device);
 static void acpi_ac_notify(struct acpi_device *device, u32 event);
 
+struct acpi_ac_bl {
+	const char *hid;
+	int hrv;
+};
+
 static const struct acpi_device_id ac_device_ids[] = {
 	{"ACPI0003", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, ac_device_ids);
 
+/* Lists of PMIC ACPI HIDs with an (often better) native charger driver */
+static const struct acpi_ac_bl acpi_ac_blacklist[] = {
+	{ "INT33F4", -1 }, /* X-Powers AXP288 PMIC */
+	{ "INT34D3",  3 }, /* Intel Cherrytrail Whiskey Cove PMIC */
+};
+
 #ifdef CONFIG_PM_SLEEP
 static int acpi_ac_resume(struct device *dev);
 #endif
@@ -424,11 +435,20 @@ static int acpi_ac_remove(struct acpi_device *device)
 
 static int __init acpi_ac_init(void)
 {
+	unsigned int i;
 	int result;
 
 	if (acpi_disabled)
 		return -ENODEV;
 
+	for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++)
+		if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1",
+				     acpi_ac_blacklist[i].hrv)) {
+			pr_info(PREFIX "AC: found native %s PMIC, not loading\n",
+				acpi_ac_blacklist[i].hid);
+			return -ENODEV;
+		}
+
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_ac_dir = acpi_lock_ac_dir();
 	if (!acpi_ac_dir)
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index a15270a806fc..502ea4dc2080 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -229,7 +229,7 @@ static int __init extlog_init(void)
 	if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr())
 		return -ENODEV;
 
-	if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
+	if (edac_get_report_status() == EDAC_REPORTING_FORCE) {
 		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
 		return -EPERM;
 	}
@@ -285,8 +285,8 @@ static int __init extlog_init(void)
 	 * eMCA event report method has higher priority than EDAC method,
 	 * unless EDAC event report method is mandatory.
 	 */
-	old_edac_report_status = get_edac_report_status();
-	set_edac_report_status(EDAC_REPORTING_DISABLED);
+	old_edac_report_status = edac_get_report_status();
+	edac_set_report_status(EDAC_REPORTING_DISABLED);
 	mce_register_decode_chain(&extlog_mce_dec);
 	/* enable OS to be involved to take over management from BIOS */
 	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
@@ -308,7 +308,7 @@ err:
 
 static void __exit extlog_exit(void)
 {
-	set_edac_report_status(old_edac_report_status);
+	edac_set_report_status(old_edac_report_status);
 	mce_unregister_decode_chain(&extlog_mce_dec);
 	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 	if (extlog_l1_addr)
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index 747c2ba98534..1b64419e2fec 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -429,8 +429,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 	if (msg->recv_type == IPMI_RESPONSE_RECV_TYPE &&
 	    msg->msg.data_len == 1) {
 		if (msg->msg.data[0] == IPMI_TIMEOUT_COMPLETION_CODE) {
-			dev_WARN_ONCE(dev, true,
-				      "Unexpected response (timeout).\n");
+			dev_dbg_once(dev, "Unexpected response (timeout).\n");
 			tx_msg->msg_done = ACPI_IPMI_TIMEOUT;
 		}
 		goto out_comp;
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index b4c1a6a51da4..88cd949003f3 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -25,9 +25,11 @@
 ACPI_MODULE_NAME("platform");
 
 static const struct acpi_device_id forbidden_id_list[] = {
-	{"PNP0000", 0},	/* PIC */
-	{"PNP0100", 0},	/* Timer */
-	{"PNP0200", 0},	/* AT DMA Controller */
+	{"PNP0000",  0},	/* PIC */
+	{"PNP0100",  0},	/* Timer */
+	{"PNP0200",  0},	/* AT DMA Controller */
+	{"ACPI0009", 0},	/* IOxAPIC */
+	{"ACPI000A", 0},	/* IOAPIC */
 	{"", 0},
 };
 
@@ -119,11 +121,14 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 	if (IS_ERR(pdev))
 		dev_err(&adev->dev, "platform device creation failed: %ld\n",
 			PTR_ERR(pdev));
-	else
+	else {
+		set_dev_node(&pdev->dev, acpi_get_node(adev->handle));
 		dev_dbg(&adev->dev, "created platform device %s\n",
 			dev_name(&pdev->dev));
+	}
 
 	kfree(resources);
+
 	return pdev;
 }
 EXPORT_SYMBOL_GPL(acpi_create_platform_device);
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 4467a8089ab8..f098e25b6b41 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -182,11 +182,6 @@ int __weak arch_register_cpu(int cpu)
 
 void __weak arch_unregister_cpu(int cpu) {}
 
-int __weak acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
-{
-	return -ENODEV;
-}
-
 static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 {
 	unsigned long long sta;
@@ -285,6 +280,13 @@ static int acpi_processor_get_info(struct acpi_device *device)
 		pr->acpi_id = value;
 	}
 
+	if (acpi_duplicate_processor_id(pr->acpi_id)) {
+		dev_err(&device->dev,
+			"Failed to get unique processor _UID (0x%x)\n",
+			pr->acpi_id);
+		return -ENODEV;
+	}
+
 	pr->phys_id = acpi_get_phys_id(pr->handle, device_declaration,
 					pr->acpi_id);
 	if (invalid_phys_cpuid(pr->phys_id))
@@ -386,11 +388,6 @@ static int acpi_processor_add(struct acpi_device *device,
 	if (result) /* Processor is not physically present or unavailable */
 		return 0;
 
-#ifdef CONFIG_SMP
-	if (pr->id >= setup_max_cpus && pr->id != 0)
-		return 0;
-#endif
-
 	BUG_ON(pr->id >= nr_cpu_ids);
 
 	/*
@@ -585,7 +582,7 @@ static struct acpi_scan_handler processor_container_handler = {
 static int nr_unique_ids __initdata;
 
 /* The number of the duplicate processor IDs */
-static int nr_duplicate_ids __initdata;
+static int nr_duplicate_ids;
 
 /* Used to store the unique processor IDs */
 static int unique_processor_ids[] __initdata = {
@@ -593,7 +590,7 @@ static int unique_processor_ids[] __initdata = {
 };
 
 /* Used to store the duplicate processor IDs */
-static int duplicate_processor_ids[] __initdata = {
+static int duplicate_processor_ids[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
@@ -638,28 +635,53 @@ static acpi_status __init acpi_processor_ids_walk(acpi_handle handle,
 						  void **rv)
 {
 	acpi_status status;
+	acpi_object_type acpi_type;
+	unsigned long long uid;
 	union acpi_object object = { 0 };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 
-	status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
+	status = acpi_get_type(handle, &acpi_type);
 	if (ACPI_FAILURE(status))
-		acpi_handle_info(handle, "Not get the processor object\n");
-	else
-		processor_validated_ids_update(object.processor.proc_id);
+		return false;
+
+	switch (acpi_type) {
+	case ACPI_TYPE_PROCESSOR:
+		status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
+		if (ACPI_FAILURE(status))
+			goto err;
+		uid = object.processor.proc_id;
+		break;
+
+	case ACPI_TYPE_DEVICE:
+		status = acpi_evaluate_integer(handle, "_UID", NULL, &uid);
+		if (ACPI_FAILURE(status))
+			goto err;
+		break;
+	default:
+		goto err;
+	}
+
+	processor_validated_ids_update(uid);
+	return true;
+
+err:
+	acpi_handle_info(handle, "Invalid processor object\n");
+	return false;
 
-	return AE_OK;
 }
 
-static void __init acpi_processor_check_duplicates(void)
+void __init acpi_processor_check_duplicates(void)
 {
-	/* Search all processor nodes in ACPI namespace */
+	/* check the correctness for all processors in ACPI namespace */
 	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
 						ACPI_UINT32_MAX,
 						acpi_processor_ids_walk,
 						NULL, NULL, NULL);
+	acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, acpi_processor_ids_walk,
+						NULL, NULL);
 }
 
-bool __init acpi_processor_validate_proc_id(int proc_id)
+bool acpi_duplicate_processor_id(int proc_id)
 {
 	int i;
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index d00bc0ef87a6..e88fe3632dd6 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -73,6 +73,10 @@ module_param(report_key_events, int, 0644);
 MODULE_PARM_DESC(report_key_events,
 	"0: none, 1: output changes, 2: brightness changes, 3: all");
 
+/*
+ * Whether the struct acpi_video_device_attrib::device_id_scheme bit should be
+ * assumed even if not actually set.
+ */
 static bool device_id_scheme = false;
 module_param(device_id_scheme, bool, 0444);
 
@@ -88,6 +92,18 @@ static int acpi_video_bus_remove(struct acpi_device *device);
 static void acpi_video_bus_notify(struct acpi_device *device, u32 event);
 void acpi_video_detect_exit(void);
 
+/*
+ * Indices in the _BCL method response: the first two items are special,
+ * the rest are all supported levels.
+ *
+ * See page 575 of the ACPI spec 3.0
+ */
+enum acpi_video_level_idx {
+	ACPI_VIDEO_AC_LEVEL,		/* level when machine has full power */
+	ACPI_VIDEO_BATTERY_LEVEL,	/* level when machine is on batteries */
+	ACPI_VIDEO_FIRST_LEVEL,		/* actual supported levels begin here */
+};
+
 static const struct acpi_device_id video_device_ids[] = {
 	{ACPI_VIDEO_HID, 0},
 	{"", 0},
@@ -132,7 +148,15 @@ struct acpi_video_device_attrib {
 				   the VGA device. */
 	u32 pipe_id:3;		/* For VGA multiple-head devices. */
 	u32 reserved:10;	/* Must be 0 */
-	u32 device_id_scheme:1;	/* Device ID Scheme */
+
+	/*
+	 * The device ID might not actually follow the scheme described by this
+	 * struct acpi_video_device_attrib. If it does, then this bit
+	 * device_id_scheme is set; otherwise, other fields should be ignored.
+	 *
+	 * (but also see the global flag device_id_scheme)
+	 */
+	u32 device_id_scheme:1;
 };
 
 struct acpi_video_enumerated_device {
@@ -217,20 +241,16 @@ static int acpi_video_get_brightness(struct backlight_device *bd)
 
 	if (acpi_video_device_lcd_get_level_current(vd, &cur_level, false))
 		return -EINVAL;
-	for (i = 2; i < vd->brightness->count; i++) {
+	for (i = ACPI_VIDEO_FIRST_LEVEL; i < vd->brightness->count; i++) {
 		if (vd->brightness->levels[i] == cur_level)
-			/*
-			 * The first two entries are special - see page 575
-			 * of the ACPI spec 3.0
-			 */
-			return i - 2;
+			return i - ACPI_VIDEO_FIRST_LEVEL;
 	}
 	return 0;
 }
 
 static int acpi_video_set_brightness(struct backlight_device *bd)
 {
-	int request_level = bd->props.brightness + 2;
+	int request_level = bd->props.brightness + ACPI_VIDEO_FIRST_LEVEL;
 	struct acpi_video_device *vd = bl_get_data(bd);
 
 	cancel_delayed_work(&vd->switch_brightness_work);
@@ -244,18 +264,18 @@ static const struct backlight_ops acpi_backlight_ops = {
 };
 
 /* thermal cooling device callbacks */
-static int video_get_max_state(struct thermal_cooling_device *cooling_dev, unsigned
-			       long *state)
+static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
+			       unsigned long *state)
 {
 	struct acpi_device *device = cooling_dev->devdata;
 	struct acpi_video_device *video = acpi_driver_data(device);
 
-	*state = video->brightness->count - 3;
+	*state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
 	return 0;
 }
 
-static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, unsigned
-			       long *state)
+static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
+			       unsigned long *state)
 {
 	struct acpi_device *device = cooling_dev->devdata;
 	struct acpi_video_device *video = acpi_driver_data(device);
@@ -264,7 +284,8 @@ static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, unsig
 
 	if (acpi_video_device_lcd_get_level_current(video, &level, false))
 		return -EINVAL;
-	for (offset = 2; offset < video->brightness->count; offset++)
+	for (offset = ACPI_VIDEO_FIRST_LEVEL; offset < video->brightness->count;
+	     offset++)
 		if (level == video->brightness->levels[offset]) {
 			*state = video->brightness->count - offset - 1;
 			return 0;
@@ -280,7 +301,7 @@ video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long st
 	struct acpi_video_device *video = acpi_driver_data(device);
 	int level;
 
-	if (state >= video->brightness->count - 2)
+	if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL)
 		return -EINVAL;
 
 	state = video->brightness->count - state;
@@ -345,10 +366,12 @@ acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level)
 	}
 
 	device->brightness->curr = level;
-	for (state = 2; state < device->brightness->count; state++)
+	for (state = ACPI_VIDEO_FIRST_LEVEL; state < device->brightness->count;
+	     state++)
 		if (level == device->brightness->levels[state]) {
 			if (device->backlight)
-				device->backlight->props.brightness = state - 2;
+				device->backlight->props.brightness =
+					state - ACPI_VIDEO_FIRST_LEVEL;
 			return 0;
 		}
 
@@ -530,14 +553,16 @@ acpi_video_bqc_value_to_level(struct acpi_video_device *device,
 
 	if (device->brightness->flags._BQC_use_index) {
 		/*
-		 * _BQC returns an index that doesn't account for
-		 * the first 2 items with special meaning, so we need
-		 * to compensate for that by offsetting ourselves
+		 * _BQC returns an index that doesn't account for the first 2
+		 * items with special meaning (see enum acpi_video_level_idx),
+		 * so we need to compensate for that by offsetting ourselves
 		 */
 		if (device->brightness->flags._BCL_reversed)
-			bqc_value = device->brightness->count - 3 - bqc_value;
+			bqc_value = device->brightness->count -
+				ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value;
 
-		level = device->brightness->levels[bqc_value + 2];
+		level = device->brightness->levels[bqc_value +
+		                                   ACPI_VIDEO_FIRST_LEVEL];
 	} else {
 		level = bqc_value;
 	}
@@ -571,7 +596,8 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device,
 
 			*level = acpi_video_bqc_value_to_level(device, *level);
 
-			for (i = 2; i < device->brightness->count; i++)
+			for (i = ACPI_VIDEO_FIRST_LEVEL;
+			     i < device->brightness->count; i++)
 				if (device->brightness->levels[i] == *level) {
 					device->brightness->curr = *level;
 					return 0;
@@ -714,9 +740,37 @@ static int acpi_video_bqc_quirk(struct acpi_video_device *device,
 
 	/*
 	 * Some systems always report current brightness level as maximum
-	 * through _BQC, we need to test another value for them.
+	 * through _BQC, we need to test another value for them. However,
+	 * there is a subtlety:
+	 *
+	 * If the _BCL package ordering is descending, the first level
+	 * (br->levels[2]) is likely to be 0, and if the number of levels
+	 * matches the number of steps, we might confuse a returned level to
+	 * mean the index.
+	 *
+	 * For example:
+	 *
+	 *     current_level = max_level = 100
+	 *     test_level = 0
+	 *     returned level = 100
+	 *
+	 * In this case 100 means the level, not the index, and _BCM failed.
+	 * Still, if the _BCL package ordering is descending, the index of
+	 * level 0 is also 100, so we assume _BQC is indexed, when it's not.
+	 *
+	 * This causes all _BQC calls to return bogus values causing weird
+	 * behavior from the user's perspective.  For example:
+	 *
+	 * xbacklight -set 10; xbacklight -set 20;
+	 *
+	 * would flash to 90% and then slowly down to the desired level (20).
+	 *
+	 * The solution is simple; test anything other than the first level
+	 * (e.g. 1).
 	 */
-	test_level = current_level == max_level ? br->levels[3] : max_level;
+	test_level = current_level == max_level
+		? br->levels[ACPI_VIDEO_FIRST_LEVEL + 1]
+		: max_level;
 
 	result = acpi_video_device_lcd_set_level(device, test_level);
 	if (result)
@@ -730,8 +784,8 @@ static int acpi_video_bqc_quirk(struct acpi_video_device *device,
 		/* buggy _BQC found, need to find out if it uses index */
 		if (level < br->count) {
 			if (br->flags._BCL_reversed)
-				level = br->count - 3 - level;
-			if (br->levels[level + 2] == test_level)
+				level = br->count - ACPI_VIDEO_FIRST_LEVEL - 1 - level;
+			if (br->levels[level + ACPI_VIDEO_FIRST_LEVEL] == test_level)
 				br->flags._BQC_use_index = 1;
 		}
 
@@ -761,7 +815,7 @@ int acpi_video_get_levels(struct acpi_device *device,
 		goto out;
 	}
 
-	if (obj->package.count < 2) {
+	if (obj->package.count < ACPI_VIDEO_FIRST_LEVEL) {
 		result = -EINVAL;
 		goto out;
 	}
@@ -773,8 +827,13 @@ int acpi_video_get_levels(struct acpi_device *device,
 		goto out;
 	}
 
-	br->levels = kmalloc((obj->package.count + 2) * sizeof *(br->levels),
-				GFP_KERNEL);
+	/*
+	 * Note that we have to reserve 2 extra items (ACPI_VIDEO_FIRST_LEVEL),
+	 * in order to account for buggy BIOS which don't export the first two
+	 * special levels (see below)
+	 */
+	br->levels = kmalloc((obj->package.count + ACPI_VIDEO_FIRST_LEVEL) *
+	                     sizeof(*br->levels), GFP_KERNEL);
 	if (!br->levels) {
 		result = -ENOMEM;
 		goto out_free;
@@ -788,7 +847,8 @@ int acpi_video_get_levels(struct acpi_device *device,
 		}
 		value = (u32) o->integer.value;
 		/* Skip duplicate entries */
-		if (count > 2 && br->levels[count - 1] == value)
+		if (count > ACPI_VIDEO_FIRST_LEVEL
+		    && br->levels[count - 1] == value)
 			continue;
 
 		br->levels[count] = value;
@@ -804,27 +864,30 @@ int acpi_video_get_levels(struct acpi_device *device,
 	 * In this case, the first two elements in _BCL packages
 	 * are also supported brightness levels that OS should take care of.
 	 */
-	for (i = 2; i < count; i++) {
-		if (br->levels[i] == br->levels[0])
+	for (i = ACPI_VIDEO_FIRST_LEVEL; i < count; i++) {
+		if (br->levels[i] == br->levels[ACPI_VIDEO_AC_LEVEL])
 			level_ac_battery++;
-		if (br->levels[i] == br->levels[1])
+		if (br->levels[i] == br->levels[ACPI_VIDEO_BATTERY_LEVEL])
 			level_ac_battery++;
 	}
 
-	if (level_ac_battery < 2) {
-		level_ac_battery = 2 - level_ac_battery;
+	if (level_ac_battery < ACPI_VIDEO_FIRST_LEVEL) {
+		level_ac_battery = ACPI_VIDEO_FIRST_LEVEL - level_ac_battery;
 		br->flags._BCL_no_ac_battery_levels = 1;
-		for (i = (count - 1 + level_ac_battery); i >= 2; i--)
+		for (i = (count - 1 + level_ac_battery);
+		     i >= ACPI_VIDEO_FIRST_LEVEL; i--)
 			br->levels[i] = br->levels[i - level_ac_battery];
 		count += level_ac_battery;
-	} else if (level_ac_battery > 2)
+	} else if (level_ac_battery > ACPI_VIDEO_FIRST_LEVEL)
 		ACPI_ERROR((AE_INFO, "Too many duplicates in _BCL package"));
 
 	/* Check if the _BCL package is in a reversed order */
-	if (max_level == br->levels[2]) {
+	if (max_level == br->levels[ACPI_VIDEO_FIRST_LEVEL]) {
 		br->flags._BCL_reversed = 1;
-		sort(&br->levels[2], count - 2, sizeof(br->levels[2]),
-			acpi_video_cmp_level, NULL);
+		sort(&br->levels[ACPI_VIDEO_FIRST_LEVEL],
+		     count - ACPI_VIDEO_FIRST_LEVEL,
+		     sizeof(br->levels[ACPI_VIDEO_FIRST_LEVEL]),
+		     acpi_video_cmp_level, NULL);
 	} else if (max_level != br->levels[count - 1])
 		ACPI_ERROR((AE_INFO,
 			    "Found unordered _BCL package"));
@@ -894,7 +957,7 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 	 * level_old is invalid (no matter whether it's a level
 	 * or an index). Set the backlight to max_level in this case.
 	 */
-	for (i = 2; i < br->count; i++)
+	for (i = ACPI_VIDEO_FIRST_LEVEL; i < br->count; i++)
 		if (level == br->levels[i])
 			break;
 	if (i == br->count || !level)
@@ -906,7 +969,8 @@ set_level:
 		goto out_free_levels;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-			  "found %d brightness levels\n", br->count - 2));
+	                  "found %d brightness levels\n",
+	                  br->count - ACPI_VIDEO_FIRST_LEVEL));
 	return 0;
 
 out_free_levels:
@@ -1297,7 +1361,7 @@ acpi_video_get_next_level(struct acpi_video_device *device,
 	max = max_below = 0;
 	min = min_above = 255;
 	/* Find closest level to level_current */
-	for (i = 2; i < device->brightness->count; i++) {
+	for (i = ACPI_VIDEO_FIRST_LEVEL; i < device->brightness->count; i++) {
 		l = device->brightness->levels[i];
 		if (abs(l - level_current) < abs(delta)) {
 			delta = l - level_current;
@@ -1307,7 +1371,7 @@ acpi_video_get_next_level(struct acpi_video_device *device,
 	}
 	/* Ajust level_current to closest available level */
 	level_current += delta;
-	for (i = 2; i < device->brightness->count; i++) {
+	for (i = ACPI_VIDEO_FIRST_LEVEL; i < device->brightness->count; i++) {
 		l = device->brightness->levels[i];
 		if (l < min)
 			min = l;
@@ -1680,7 +1744,8 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 
 	memset(&props, 0, sizeof(struct backlight_properties));
 	props.type = BACKLIGHT_FIRMWARE;
-	props.max_brightness = device->brightness->count - 3;
+	props.max_brightness =
+		device->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
 	device->backlight = backlight_device_register(name,
 						      parent,
 						      device,
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index c86bae7b1d0f..ff096d9755b9 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -421,10 +421,8 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state,
 
 	ACPI_FUNCTION_TRACE(ut_walk_aml_resources);
 
-	/*
-	 * The absolute minimum resource template is one end_tag descriptor.
-	 * However, we will treat a lone end_tag as just a simple buffer.
-	 */
+	/* The absolute minimum resource template is one end_tag descriptor */
+
 	if (aml_length < sizeof(struct aml_resource_end_tag)) {
 		return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
 	}
@@ -456,8 +454,9 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state,
 		/* Invoke the user function */
 
 		if (user_function) {
-			status = user_function(aml, length, offset,
-					       resource_index, context);
+			status =
+			    user_function(aml, length, offset, resource_index,
+					  context);
 			if (ACPI_FAILURE(status)) {
 				return_ACPI_STATUS(status);
 			}
@@ -481,12 +480,6 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state,
 				*context = aml;
 			}
 
-			/* Check if buffer is defined to be longer than the resource length */
-
-			if (aml_length > (offset + length)) {
-				return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
-			}
-
 			/* Normal exit */
 
 			return_ACPI_STATUS(AE_OK);
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index ec4f507b524f..7207e5fc9d3d 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -925,15 +925,9 @@ static int erst_check_table(struct acpi_table_erst *erst_tab)
 
 static int erst_open_pstore(struct pstore_info *psi);
 static int erst_close_pstore(struct pstore_info *psi);
-static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
-			   struct timespec *time, char **buf,
-			   bool *compressed, ssize_t *ecc_notice_size,
-			   struct pstore_info *psi);
-static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count, bool compressed,
-		       size_t size, struct pstore_info *psi);
-static int erst_clearer(enum pstore_type_id type, u64 id, int count,
-			struct timespec time, struct pstore_info *psi);
+static ssize_t erst_reader(struct pstore_record *record);
+static int erst_writer(struct pstore_record *record);
+static int erst_clearer(struct pstore_record *record);
 
 static struct pstore_info erst_info = {
 	.owner		= THIS_MODULE,
@@ -986,10 +980,7 @@ static int erst_close_pstore(struct pstore_info *psi)
 	return 0;
 }
 
-static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
-			   struct timespec *time, char **buf,
-			   bool *compressed, ssize_t *ecc_notice_size,
-			   struct pstore_info *psi)
+static ssize_t erst_reader(struct pstore_record *record)
 {
 	int rc;
 	ssize_t len = 0;
@@ -1027,42 +1018,40 @@ skip:
 	if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0)
 		goto skip;
 
-	*buf = kmalloc(len, GFP_KERNEL);
-	if (*buf == NULL) {
+	record->buf = kmalloc(len, GFP_KERNEL);
+	if (record->buf == NULL) {
 		rc = -ENOMEM;
 		goto out;
 	}
-	memcpy(*buf, rcd->data, len - sizeof(*rcd));
-	*id = record_id;
-	*compressed = false;
-	*ecc_notice_size = 0;
+	memcpy(record->buf, rcd->data, len - sizeof(*rcd));
+	record->id = record_id;
+	record->compressed = false;
+	record->ecc_notice_size = 0;
 	if (uuid_le_cmp(rcd->sec_hdr.section_type,
 			CPER_SECTION_TYPE_DMESG_Z) == 0) {
-		*type = PSTORE_TYPE_DMESG;
-		*compressed = true;
+		record->type = PSTORE_TYPE_DMESG;
+		record->compressed = true;
 	} else if (uuid_le_cmp(rcd->sec_hdr.section_type,
 			CPER_SECTION_TYPE_DMESG) == 0)
-		*type = PSTORE_TYPE_DMESG;
+		record->type = PSTORE_TYPE_DMESG;
 	else if (uuid_le_cmp(rcd->sec_hdr.section_type,
 			     CPER_SECTION_TYPE_MCE) == 0)
-		*type = PSTORE_TYPE_MCE;
+		record->type = PSTORE_TYPE_MCE;
 	else
-		*type = PSTORE_TYPE_UNKNOWN;
+		record->type = PSTORE_TYPE_UNKNOWN;
 
 	if (rcd->hdr.validation_bits & CPER_VALID_TIMESTAMP)
-		time->tv_sec = rcd->hdr.timestamp;
+		record->time.tv_sec = rcd->hdr.timestamp;
 	else
-		time->tv_sec = 0;
-	time->tv_nsec = 0;
+		record->time.tv_sec = 0;
+	record->time.tv_nsec = 0;
 
 out:
 	kfree(rcd);
 	return (rc < 0) ? rc : (len - sizeof(*rcd));
 }
 
-static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count, bool compressed,
-		       size_t size, struct pstore_info *psi)
+static int erst_writer(struct pstore_record *record)
 {
 	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
 					(erst_info.buf - sizeof(*rcd));
@@ -1077,21 +1066,21 @@ static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 	/* timestamp valid. platform_id, partition_id are invalid */
 	rcd->hdr.validation_bits = CPER_VALID_TIMESTAMP;
 	rcd->hdr.timestamp = get_seconds();
-	rcd->hdr.record_length = sizeof(*rcd) + size;
+	rcd->hdr.record_length = sizeof(*rcd) + record->size;
 	rcd->hdr.creator_id = CPER_CREATOR_PSTORE;
 	rcd->hdr.notification_type = CPER_NOTIFY_MCE;
 	rcd->hdr.record_id = cper_next_record_id();
 	rcd->hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR;
 
 	rcd->sec_hdr.section_offset = sizeof(*rcd);
-	rcd->sec_hdr.section_length = size;
+	rcd->sec_hdr.section_length = record->size;
 	rcd->sec_hdr.revision = CPER_SEC_REV;
 	/* fru_id and fru_text is invalid */
 	rcd->sec_hdr.validation_bits = 0;
 	rcd->sec_hdr.flags = CPER_SEC_PRIMARY;
-	switch (type) {
+	switch (record->type) {
 	case PSTORE_TYPE_DMESG:
-		if (compressed)
+		if (record->compressed)
 			rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG_Z;
 		else
 			rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG;
@@ -1105,15 +1094,14 @@ static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 	rcd->sec_hdr.section_severity = CPER_SEV_FATAL;
 
 	ret = erst_write(&rcd->hdr);
-	*id = rcd->hdr.record_id;
+	record->id = rcd->hdr.record_id;
 
 	return ret;
 }
 
-static int erst_clearer(enum pstore_type_id type, u64 id, int count,
-			struct timespec time, struct pstore_info *psi)
+static int erst_clearer(struct pstore_record *record)
 {
-	return erst_clear(id);
+	return erst_clear(record->id);
 }
 
 static int __init erst_init(void)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index b192b42a8351..d0855c09f32f 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1005,9 +1005,8 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	switch (generic->notify.type) {
 	case ACPI_HEST_NOTIFY_POLLED:
-		ghes->timer.function = ghes_poll_func;
-		ghes->timer.data = (unsigned long)ghes;
-		init_timer_deferrable(&ghes->timer);
+		setup_deferrable_timer(&ghes->timer, ghes_poll_func,
+				       (unsigned long)ghes);
 		ghes_add_timer(ghes);
 		break;
 	case ACPI_HEST_NOTIFY_EXTERNAL:
@@ -1073,6 +1072,7 @@ static int ghes_remove(struct platform_device *ghes_dev)
 		if (list_empty(&ghes_sci))
 			unregister_acpi_hed_notifier(&ghes_notifier_sci);
 		mutex_unlock(&ghes_list_mutex);
+		synchronize_rcu();
 		break;
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_remove(ghes);
diff --git a/drivers/acpi/arm64/Kconfig b/drivers/acpi/arm64/Kconfig
index 4616da4c15be..5a6f80fce0d6 100644
--- a/drivers/acpi/arm64/Kconfig
+++ b/drivers/acpi/arm64/Kconfig
@@ -4,3 +4,6 @@
 
 config ACPI_IORT
 	bool
+
+config ACPI_GTDT
+	bool
diff --git a/drivers/acpi/arm64/Makefile b/drivers/acpi/arm64/Makefile
index 72331f2ce0e9..1017def2ea12 100644
--- a/drivers/acpi/arm64/Makefile
+++ b/drivers/acpi/arm64/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_ACPI_IORT) 	+= iort.o
+obj-$(CONFIG_ACPI_GTDT) 	+= gtdt.o
diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c
new file mode 100644
index 000000000000..597a737d538f
--- /dev/null
+++ b/drivers/acpi/arm64/gtdt.c
@@ -0,0 +1,417 @@
+/*
+ * ARM Specific GTDT table Support
+ *
+ * Copyright (C) 2016, Linaro Ltd.
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *         Fu Wei <fu.wei@linaro.org>
+ *         Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "ACPI GTDT: " fmt
+
+/**
+ * struct acpi_gtdt_descriptor - Store the key info of GTDT for all functions
+ * @gtdt:	The pointer to the struct acpi_table_gtdt of GTDT table.
+ * @gtdt_end:	The pointer to the end of GTDT table.
+ * @platform_timer:	The pointer to the start of Platform Timer Structure
+ *
+ * The struct store the key info of GTDT table, it should be initialized by
+ * acpi_gtdt_init.
+ */
+struct acpi_gtdt_descriptor {
+	struct acpi_table_gtdt *gtdt;
+	void *gtdt_end;
+	void *platform_timer;
+};
+
+static struct acpi_gtdt_descriptor acpi_gtdt_desc __initdata;
+
+static inline void *next_platform_timer(void *platform_timer)
+{
+	struct acpi_gtdt_header *gh = platform_timer;
+
+	platform_timer += gh->length;
+	if (platform_timer < acpi_gtdt_desc.gtdt_end)
+		return platform_timer;
+
+	return NULL;
+}
+
+#define for_each_platform_timer(_g)				\
+	for (_g = acpi_gtdt_desc.platform_timer; _g;	\
+	     _g = next_platform_timer(_g))
+
+static inline bool is_timer_block(void *platform_timer)
+{
+	struct acpi_gtdt_header *gh = platform_timer;
+
+	return gh->type == ACPI_GTDT_TYPE_TIMER_BLOCK;
+}
+
+static inline bool is_non_secure_watchdog(void *platform_timer)
+{
+	struct acpi_gtdt_header *gh = platform_timer;
+	struct acpi_gtdt_watchdog *wd = platform_timer;
+
+	if (gh->type != ACPI_GTDT_TYPE_WATCHDOG)
+		return false;
+
+	return !(wd->timer_flags & ACPI_GTDT_WATCHDOG_SECURE);
+}
+
+static int __init map_gt_gsi(u32 interrupt, u32 flags)
+{
+	int trigger, polarity;
+
+	trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE
+			: ACPI_LEVEL_SENSITIVE;
+
+	polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW
+			: ACPI_ACTIVE_HIGH;
+
+	return acpi_register_gsi(NULL, interrupt, trigger, polarity);
+}
+
+/**
+ * acpi_gtdt_map_ppi() - Map the PPIs of per-cpu arch_timer.
+ * @type:	the type of PPI.
+ *
+ * Note: Secure state is not managed by the kernel on ARM64 systems.
+ * So we only handle the non-secure timer PPIs,
+ * ARCH_TIMER_PHYS_SECURE_PPI is treated as invalid type.
+ *
+ * Return: the mapped PPI value, 0 if error.
+ */
+int __init acpi_gtdt_map_ppi(int type)
+{
+	struct acpi_table_gtdt *gtdt = acpi_gtdt_desc.gtdt;
+
+	switch (type) {
+	case ARCH_TIMER_PHYS_NONSECURE_PPI:
+		return map_gt_gsi(gtdt->non_secure_el1_interrupt,
+				  gtdt->non_secure_el1_flags);
+	case ARCH_TIMER_VIRT_PPI:
+		return map_gt_gsi(gtdt->virtual_timer_interrupt,
+				  gtdt->virtual_timer_flags);
+
+	case ARCH_TIMER_HYP_PPI:
+		return map_gt_gsi(gtdt->non_secure_el2_interrupt,
+				  gtdt->non_secure_el2_flags);
+	default:
+		pr_err("Failed to map timer interrupt: invalid type.\n");
+	}
+
+	return 0;
+}
+
+/**
+ * acpi_gtdt_c3stop() - Got c3stop info from GTDT according to the type of PPI.
+ * @type:	the type of PPI.
+ *
+ * Return: true if the timer HW state is lost when a CPU enters an idle state,
+ * false otherwise
+ */
+bool __init acpi_gtdt_c3stop(int type)
+{
+	struct acpi_table_gtdt *gtdt = acpi_gtdt_desc.gtdt;
+
+	switch (type) {
+	case ARCH_TIMER_PHYS_NONSECURE_PPI:
+		return !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON);
+
+	case ARCH_TIMER_VIRT_PPI:
+		return !(gtdt->virtual_timer_flags & ACPI_GTDT_ALWAYS_ON);
+
+	case ARCH_TIMER_HYP_PPI:
+		return !(gtdt->non_secure_el2_flags & ACPI_GTDT_ALWAYS_ON);
+
+	default:
+		pr_err("Failed to get c3stop info: invalid type.\n");
+	}
+
+	return false;
+}
+
+/**
+ * acpi_gtdt_init() - Get the info of GTDT table to prepare for further init.
+ * @table:			The pointer to GTDT table.
+ * @platform_timer_count:	It points to a integer variable which is used
+ *				for storing the number of platform timers.
+ *				This pointer could be NULL, if the caller
+ *				doesn't need this info.
+ *
+ * Return: 0 if success, -EINVAL if error.
+ */
+int __init acpi_gtdt_init(struct acpi_table_header *table,
+			  int *platform_timer_count)
+{
+	void *platform_timer;
+	struct acpi_table_gtdt *gtdt;
+
+	gtdt = container_of(table, struct acpi_table_gtdt, header);
+	acpi_gtdt_desc.gtdt = gtdt;
+	acpi_gtdt_desc.gtdt_end = (void *)table + table->length;
+	acpi_gtdt_desc.platform_timer = NULL;
+	if (platform_timer_count)
+		*platform_timer_count = 0;
+
+	if (table->revision < 2) {
+		pr_warn("Revision:%d doesn't support Platform Timers.\n",
+			table->revision);
+		return 0;
+	}
+
+	if (!gtdt->platform_timer_count) {
+		pr_debug("No Platform Timer.\n");
+		return 0;
+	}
+
+	platform_timer = (void *)gtdt + gtdt->platform_timer_offset;
+	if (platform_timer < (void *)table + sizeof(struct acpi_table_gtdt)) {
+		pr_err(FW_BUG "invalid timer data.\n");
+		return -EINVAL;
+	}
+	acpi_gtdt_desc.platform_timer = platform_timer;
+	if (platform_timer_count)
+		*platform_timer_count = gtdt->platform_timer_count;
+
+	return 0;
+}
+
+static int __init gtdt_parse_timer_block(struct acpi_gtdt_timer_block *block,
+					 struct arch_timer_mem *timer_mem)
+{
+	int i;
+	struct arch_timer_mem_frame *frame;
+	struct acpi_gtdt_timer_entry *gtdt_frame;
+
+	if (!block->timer_count) {
+		pr_err(FW_BUG "GT block present, but frame count is zero.");
+		return -ENODEV;
+	}
+
+	if (block->timer_count > ARCH_TIMER_MEM_MAX_FRAMES) {
+		pr_err(FW_BUG "GT block lists %d frames, ACPI spec only allows 8\n",
+		       block->timer_count);
+		return -EINVAL;
+	}
+
+	timer_mem->cntctlbase = (phys_addr_t)block->block_address;
+	/*
+	 * The CNTCTLBase frame is 4KB (register offsets 0x000 - 0xFFC).
+	 * See ARM DDI 0487A.k_iss10775, page I1-5129, Table I1-3
+	 * "CNTCTLBase memory map".
+	 */
+	timer_mem->size = SZ_4K;
+
+	gtdt_frame = (void *)block + block->timer_offset;
+	if (gtdt_frame + block->timer_count != (void *)block + block->header.length)
+		return -EINVAL;
+
+	/*
+	 * Get the GT timer Frame data for every GT Block Timer
+	 */
+	for (i = 0; i < block->timer_count; i++, gtdt_frame++) {
+		if (gtdt_frame->common_flags & ACPI_GTDT_GT_IS_SECURE_TIMER)
+			continue;
+		if (gtdt_frame->frame_number >= ARCH_TIMER_MEM_MAX_FRAMES ||
+		    !gtdt_frame->base_address || !gtdt_frame->timer_interrupt)
+			goto error;
+
+		frame = &timer_mem->frame[gtdt_frame->frame_number];
+
+		/* duplicate frame */
+		if (frame->valid)
+			goto error;
+
+		frame->phys_irq = map_gt_gsi(gtdt_frame->timer_interrupt,
+					     gtdt_frame->timer_flags);
+		if (frame->phys_irq <= 0) {
+			pr_warn("failed to map physical timer irq in frame %d.\n",
+				gtdt_frame->frame_number);
+			goto error;
+		}
+
+		if (gtdt_frame->virtual_timer_interrupt) {
+			frame->virt_irq =
+				map_gt_gsi(gtdt_frame->virtual_timer_interrupt,
+					   gtdt_frame->virtual_timer_flags);
+			if (frame->virt_irq <= 0) {
+				pr_warn("failed to map virtual timer irq in frame %d.\n",
+					gtdt_frame->frame_number);
+				goto error;
+			}
+		} else {
+			pr_debug("virtual timer in frame %d not implemented.\n",
+				 gtdt_frame->frame_number);
+		}
+
+		frame->cntbase = gtdt_frame->base_address;
+		/*
+		 * The CNTBaseN frame is 4KB (register offsets 0x000 - 0xFFC).
+		 * See ARM DDI 0487A.k_iss10775, page I1-5130, Table I1-4
+		 * "CNTBaseN memory map".
+		 */
+		frame->size = SZ_4K;
+		frame->valid = true;
+	}
+
+	return 0;
+
+error:
+	do {
+		if (gtdt_frame->common_flags & ACPI_GTDT_GT_IS_SECURE_TIMER ||
+		    gtdt_frame->frame_number >= ARCH_TIMER_MEM_MAX_FRAMES)
+			continue;
+
+		frame = &timer_mem->frame[gtdt_frame->frame_number];
+
+		if (frame->phys_irq > 0)
+			acpi_unregister_gsi(gtdt_frame->timer_interrupt);
+		frame->phys_irq = 0;
+
+		if (frame->virt_irq > 0)
+			acpi_unregister_gsi(gtdt_frame->virtual_timer_interrupt);
+		frame->virt_irq = 0;
+	} while (i-- >= 0 && gtdt_frame--);
+
+	return -EINVAL;
+}
+
+/**
+ * acpi_arch_timer_mem_init() - Get the info of all GT blocks in GTDT table.
+ * @timer_mem:	The pointer to the array of struct arch_timer_mem for returning
+ *		the result of parsing. The element number of this array should
+ *		be platform_timer_count(the total number of platform timers).
+ * @timer_count: It points to a integer variable which is used for storing the
+ *		number of GT blocks we have parsed.
+ *
+ * Return: 0 if success, -EINVAL/-ENODEV if error.
+ */
+int __init acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem,
+				    int *timer_count)
+{
+	int ret;
+	void *platform_timer;
+
+	*timer_count = 0;
+	for_each_platform_timer(platform_timer) {
+		if (is_timer_block(platform_timer)) {
+			ret = gtdt_parse_timer_block(platform_timer, timer_mem);
+			if (ret)
+				return ret;
+			timer_mem++;
+			(*timer_count)++;
+		}
+	}
+
+	if (*timer_count)
+		pr_info("found %d memory-mapped timer block(s).\n",
+			*timer_count);
+
+	return 0;
+}
+
+/*
+ * Initialize a SBSA generic Watchdog platform device info from GTDT
+ */
+static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
+					int index)
+{
+	struct platform_device *pdev;
+	int irq = map_gt_gsi(wd->timer_interrupt, wd->timer_flags);
+
+	/*
+	 * According to SBSA specification the size of refresh and control
+	 * frames of SBSA Generic Watchdog is SZ_4K(Offset 0x000 – 0xFFF).
+	 */
+	struct resource res[] = {
+		DEFINE_RES_MEM(wd->control_frame_address, SZ_4K),
+		DEFINE_RES_MEM(wd->refresh_frame_address, SZ_4K),
+		DEFINE_RES_IRQ(irq),
+	};
+	int nr_res = ARRAY_SIZE(res);
+
+	pr_debug("found a Watchdog (0x%llx/0x%llx gsi:%u flags:0x%x).\n",
+		 wd->refresh_frame_address, wd->control_frame_address,
+		 wd->timer_interrupt, wd->timer_flags);
+
+	if (!(wd->refresh_frame_address && wd->control_frame_address)) {
+		pr_err(FW_BUG "failed to get the Watchdog base address.\n");
+		acpi_unregister_gsi(wd->timer_interrupt);
+		return -EINVAL;
+	}
+
+	if (irq <= 0) {
+		pr_warn("failed to map the Watchdog interrupt.\n");
+		nr_res--;
+	}
+
+	/*
+	 * Add a platform device named "sbsa-gwdt" to match the platform driver.
+	 * "sbsa-gwdt": SBSA(Server Base System Architecture) Generic Watchdog
+	 * The platform driver can get device info below by matching this name.
+	 */
+	pdev = platform_device_register_simple("sbsa-gwdt", index, res, nr_res);
+	if (IS_ERR(pdev)) {
+		acpi_unregister_gsi(wd->timer_interrupt);
+		return PTR_ERR(pdev);
+	}
+
+	return 0;
+}
+
+static int __init gtdt_sbsa_gwdt_init(void)
+{
+	void *platform_timer;
+	struct acpi_table_header *table;
+	int ret, timer_count, gwdt_count = 0;
+
+	if (acpi_disabled)
+		return 0;
+
+	if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_GTDT, 0, &table)))
+		return -EINVAL;
+
+	/*
+	 * Note: Even though the global variable acpi_gtdt_desc has been
+	 * initialized by acpi_gtdt_init() while initializing the arch timers,
+	 * when we call this function to get SBSA watchdogs info from GTDT, the
+	 * pointers stashed in it are stale (since they are early temporary
+	 * mappings carried out before acpi_permanent_mmap is set) and we need
+	 * to re-initialize them with permanent mapped pointer values to let the
+	 * GTDT parsing possible.
+	 */
+	ret = acpi_gtdt_init(table, &timer_count);
+	if (ret || !timer_count)
+		return ret;
+
+	for_each_platform_timer(platform_timer) {
+		if (is_non_secure_watchdog(platform_timer)) {
+			ret = gtdt_import_sbsa_gwdt(platform_timer, gwdt_count);
+			if (ret)
+				break;
+			gwdt_count++;
+		}
+	}
+
+	if (gwdt_count)
+		pr_info("found %d SBSA generic Watchdog(s).\n", gwdt_count);
+
+	return ret;
+}
+
+device_initcall(gtdt_sbsa_gwdt_init);
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 4ef1e4624b2b..d42eeef9d928 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -67,6 +67,7 @@ MODULE_DESCRIPTION("ACPI Battery Driver");
 MODULE_LICENSE("GPL");
 
 static async_cookie_t async_cookie;
+static bool battery_driver_registered;
 static int battery_bix_broken_package;
 static int battery_notification_delay_ms;
 static unsigned int cache_time = 1000;
@@ -93,6 +94,11 @@ static const struct acpi_device_id battery_device_ids[] = {
 
 MODULE_DEVICE_TABLE(acpi, battery_device_ids);
 
+/* Lists of PMIC ACPI HIDs with an (often better) native battery driver */
+static const char * const acpi_battery_blacklist[] = {
+	"INT33F4", /* X-Powers AXP288 PMIC */
+};
+
 enum {
 	ACPI_BATTERY_ALARM_PRESENT,
 	ACPI_BATTERY_XINFO_PRESENT,
@@ -1315,8 +1321,17 @@ static struct acpi_driver acpi_battery_driver = {
 
 static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 {
+	unsigned int i;
 	int result;
 
+	for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++)
+		if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) {
+			pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME
+				": found native %s PMIC, not loading\n",
+				acpi_battery_blacklist[i]);
+			return;
+		}
+
 	dmi_check_system(bat_dmi_table);
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
@@ -1329,6 +1344,7 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 	if (result < 0)
 		acpi_unlock_battery_dir(acpi_battery_dir);
 #endif
+	battery_driver_registered = (result == 0);
 }
 
 static int __init acpi_battery_init(void)
@@ -1343,9 +1359,11 @@ static int __init acpi_battery_init(void)
 static void __exit acpi_battery_exit(void)
 {
 	async_synchronize_cookie(async_cookie + 1);
-	acpi_bus_unregister_driver(&acpi_battery_driver);
+	if (battery_driver_registered)
+		acpi_bus_unregister_driver(&acpi_battery_driver);
 #ifdef CONFIG_ACPI_PROCFS_POWER
-	acpi_unlock_battery_dir(acpi_battery_dir);
+	if (acpi_battery_dir)
+		acpi_unlock_battery_dir(acpi_battery_dir);
 #endif
 }
 
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index ca28aa572aa9..df1c629205e7 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -81,6 +81,12 @@ static struct attribute_group bgrt_attribute_group = {
 	.bin_attrs = bgrt_bin_attributes,
 };
 
+int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+	efi_bgrt_init(table);
+	return 0;
+}
+
 static int __init bgrt_init(void)
 {
 	int ret;
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 4421f7c9981c..bb542acc0574 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -188,6 +188,14 @@ static struct dmi_system_id acpi_rev_dmi_table[] __initdata = {
 		      DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3350"),
 		},
 	},
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Inspiron 7537",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7537"),
+		},
+	},
 #endif
 	{}
 };
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 80cb5eb75b63..34fbe027e73a 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1249,7 +1249,6 @@ static int __init acpi_init(void)
 	acpi_wakeup_device_init();
 	acpi_debugger_init();
 	acpi_setup_sb_notify_handler();
-	acpi_set_processor_mapping();
 	return 0;
 }
 
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 3ca0729f7e0e..6cbe6036da99 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -132,49 +132,54 @@ __ATTR(_name, 0444, show_##_name, NULL)
 
 #define to_cpc_desc(a) container_of(a, struct cpc_desc, kobj)
 
+#define show_cppc_data(access_fn, struct_name, member_name)		\
+	static ssize_t show_##member_name(struct kobject *kobj,		\
+					struct attribute *attr,	char *buf) \
+	{								\
+		struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);		\
+		struct struct_name st_name = {0};			\
+		int ret;						\
+									\
+		ret = access_fn(cpc_ptr->cpu_id, &st_name);		\
+		if (ret)						\
+			return ret;					\
+									\
+		return scnprintf(buf, PAGE_SIZE, "%llu\n",		\
+				(u64)st_name.member_name);		\
+	}								\
+	define_one_cppc_ro(member_name)
+
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, highest_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_nonlinear_perf);
+show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf);
+show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);
+
 static ssize_t show_feedback_ctrs(struct kobject *kobj,
 		struct attribute *attr, char *buf)
 {
 	struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
 	struct cppc_perf_fb_ctrs fb_ctrs = {0};
+	int ret;
 
-	cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
+	ret = cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
+	if (ret)
+		return ret;
 
 	return scnprintf(buf, PAGE_SIZE, "ref:%llu del:%llu\n",
 			fb_ctrs.reference, fb_ctrs.delivered);
 }
 define_one_cppc_ro(feedback_ctrs);
 
-static ssize_t show_reference_perf(struct kobject *kobj,
-		struct attribute *attr, char *buf)
-{
-	struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
-
-	cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
-
-	return scnprintf(buf, PAGE_SIZE, "%llu\n",
-			fb_ctrs.reference_perf);
-}
-define_one_cppc_ro(reference_perf);
-
-static ssize_t show_wraparound_time(struct kobject *kobj,
-				struct attribute *attr, char *buf)
-{
-	struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
-
-	cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
-
-	return scnprintf(buf, PAGE_SIZE, "%llu\n", fb_ctrs.ctr_wrap_time);
-
-}
-define_one_cppc_ro(wraparound_time);
-
 static struct attribute *cppc_attrs[] = {
 	&feedback_ctrs.attr,
 	&reference_perf.attr,
 	&wraparound_time.attr,
+	&highest_perf.attr,
+	&lowest_perf.attr,
+	&lowest_nonlinear_perf.attr,
+	&nominal_perf.attr,
 	NULL
 };
 
@@ -972,9 +977,9 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 {
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
-	struct cpc_register_resource *highest_reg, *lowest_reg, *ref_perf,
-								 *nom_perf;
-	u64 high, low, nom;
+	struct cpc_register_resource *highest_reg, *lowest_reg,
+		*lowest_non_linear_reg, *nominal_reg;
+	u64 high, low, nom, min_nonlinear;
 	int ret = 0, regs_in_pcc = 0;
 
 	if (!cpc_desc) {
@@ -984,12 +989,12 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 
 	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
 	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
-	ref_perf = &cpc_desc->cpc_regs[REFERENCE_PERF];
-	nom_perf = &cpc_desc->cpc_regs[NOMINAL_PERF];
+	lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
+	nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
 
 	/* Are any of the regs PCC ?*/
 	if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) ||
-		CPC_IN_PCC(ref_perf) || CPC_IN_PCC(nom_perf)) {
+		CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg)) {
 		regs_in_pcc = 1;
 		down_write(&pcc_data.pcc_lock);
 		/* Ring doorbell once to update PCC subspace */
@@ -1005,10 +1010,13 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 	cpc_read(cpunum, lowest_reg, &low);
 	perf_caps->lowest_perf = low;
 
-	cpc_read(cpunum, nom_perf, &nom);
+	cpc_read(cpunum, nominal_reg, &nom);
 	perf_caps->nominal_perf = nom;
 
-	if (!high || !low || !nom)
+	cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear);
+	perf_caps->lowest_nonlinear_perf = min_nonlinear;
+
+	if (!high || !low || !nom || !min_nonlinear)
 		ret = -EFAULT;
 
 out_err:
@@ -1083,7 +1091,7 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	perf_fb_ctrs->delivered = delivered;
 	perf_fb_ctrs->reference = reference;
 	perf_fb_ctrs->reference_perf = ref_perf;
-	perf_fb_ctrs->ctr_wrap_time = ctr_wrap_time;
+	perf_fb_ctrs->wraparound_time = ctr_wrap_time;
 out_err:
 	if (regs_in_pcc)
 		up_write(&pcc_data.pcc_lock);
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index fb19e1cdb641..edc8663b5db3 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -99,13 +99,13 @@ static int find_child_checks(struct acpi_device *adev, bool check_children)
 		return -ENODEV;
 
 	/*
-	 * If the device has a _HID (or _CID) returning a valid ACPI/PNP
-	 * device ID, it is better to make it look less attractive here, so that
-	 * the other device with the same _ADR value (that may not have a valid
-	 * device ID) can be matched going forward.  [This means a second spec
-	 * violation in a row, so whatever we do here is best effort anyway.]
+	 * If the device has a _HID returning a valid ACPI/PNP device ID, it is
+	 * better to make it look less attractive here, so that the other device
+	 * with the same _ADR value (that may not have a valid device ID) can be
+	 * matched going forward.  [This means a second spec violation in a row,
+	 * so whatever we do here is best effort anyway.]
 	 */
-	return sta_present && list_empty(&adev->pnp.ids) ?
+	return sta_present && !adev->pnp.type.platform_id ?
 			FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
 }
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 219b90bc0922..66229ffa909b 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -41,8 +41,10 @@ void acpi_gpe_apply_masked_gpes(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
 #ifdef	CONFIG_ACPI_HOTPLUG_IOAPIC
+void pci_ioapic_remove(struct acpi_pci_root *root);
 int acpi_ioapic_remove(struct acpi_pci_root *root);
 #else
+static inline void pci_ioapic_remove(struct acpi_pci_root *root) { return; }
 static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; }
 #endif
 #ifdef CONFIG_ACPI_DOCK
@@ -63,8 +65,6 @@ static inline void acpi_cmos_rtc_init(void) {}
 #endif
 int acpi_rev_override_setup(char *str);
 
-extern bool acpi_force_hot_remove;
-
 void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
 				    const char *name);
 int acpi_scan_add_handler_with_hotplug(struct acpi_scan_handler *handler,
diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c
index 6d7ce6e12aaa..7e4fbf9a53a3 100644
--- a/drivers/acpi/ioapic.c
+++ b/drivers/acpi/ioapic.c
@@ -45,6 +45,12 @@ static acpi_status setup_res(struct acpi_resource *acpi_res, void *data)
 	struct resource *res = data;
 	struct resource_win win;
 
+	/*
+	 * We might assign this to 'res' later, make sure all pointers are
+	 * cleared before the resource is added to the global list
+	 */
+	memset(&win, 0, sizeof(win));
+
 	res->flags = 0;
 	if (acpi_dev_filter_resource_type(acpi_res, IORESOURCE_MEM))
 		return AE_OK;
@@ -206,24 +212,34 @@ int acpi_ioapic_add(acpi_handle root_handle)
 	return ACPI_SUCCESS(status) && ACPI_SUCCESS(retval) ? 0 : -ENODEV;
 }
 
-int acpi_ioapic_remove(struct acpi_pci_root *root)
+void pci_ioapic_remove(struct acpi_pci_root *root)
 {
-	int retval = 0;
 	struct acpi_pci_ioapic *ioapic, *tmp;
 
 	mutex_lock(&ioapic_list_lock);
 	list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
 		if (root->device->handle != ioapic->root_handle)
 			continue;
-
-		if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base))
-			retval = -EBUSY;
-
 		if (ioapic->pdev) {
 			pci_release_region(ioapic->pdev, 0);
 			pci_disable_device(ioapic->pdev);
 			pci_dev_put(ioapic->pdev);
 		}
+	}
+	mutex_unlock(&ioapic_list_lock);
+}
+
+int acpi_ioapic_remove(struct acpi_pci_root *root)
+{
+	int retval = 0;
+	struct acpi_pci_ioapic *ioapic, *tmp;
+
+	mutex_lock(&ioapic_list_lock);
+	list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
+		if (root->device->handle != ioapic->root_handle)
+			continue;
+		if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base))
+			retval = -EBUSY;
 		if (ioapic->res.flags && ioapic->res.parent)
 			release_resource(&ioapic->res);
 		list_del(&ioapic->list);
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 662036bdc65e..c8ea9d698cd0 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1617,7 +1617,11 @@ static int cmp_map(const void *m0, const void *m1)
 	const struct nfit_set_info_map *map0 = m0;
 	const struct nfit_set_info_map *map1 = m1;
 
-	return map0->region_offset - map1->region_offset;
+	if (map0->region_offset < map1->region_offset)
+		return -1;
+	else if (map0->region_offset > map1->region_offset)
+		return 1;
+	return 0;
 }
 
 /* Retrieve the nth entry referencing this spa */
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index bf601d4df8cf..919be0aa2578 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -648,12 +648,12 @@ static void acpi_pci_root_remove(struct acpi_device *device)
 
 	pci_stop_root_bus(root->bus);
 
-	WARN_ON(acpi_ioapic_remove(root));
-
+	pci_ioapic_remove(root);
 	device_set_run_wake(root->bus->bridge, false);
 	pci_acpi_remove_bus_pm_notifier(device);
 
 	pci_remove_root_bus(root->bus);
+	WARN_ON(acpi_ioapic_remove(root));
 
 	dmar_device_remove(device->handle);
 
diff --git a/drivers/acpi/pmic/intel_pmic_chtwc.c b/drivers/acpi/pmic/intel_pmic_chtwc.c
new file mode 100644
index 000000000000..85636d7a9d39
--- /dev/null
+++ b/drivers/acpi/pmic/intel_pmic_chtwc.c
@@ -0,0 +1,280 @@
+/*
+ * Intel CHT Whiskey Cove PMIC operation region driver
+ * Copyright (C) 2017 Hans de Goede <hdegoede@redhat.com>
+ *
+ * Based on various non upstream patches to support the CHT Whiskey Cove PMIC:
+ * Copyright (C) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/mfd/intel_soc_pmic.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include "intel_pmic.h"
+
+#define CHT_WC_V1P05A_CTRL		0x6e3b
+#define CHT_WC_V1P15_CTRL		0x6e3c
+#define CHT_WC_V1P05A_VSEL		0x6e3d
+#define CHT_WC_V1P15_VSEL		0x6e3e
+#define CHT_WC_V1P8A_CTRL		0x6e56
+#define CHT_WC_V1P8SX_CTRL		0x6e57
+#define CHT_WC_VDDQ_CTRL		0x6e58
+#define CHT_WC_V1P2A_CTRL		0x6e59
+#define CHT_WC_V1P2SX_CTRL		0x6e5a
+#define CHT_WC_V1P8A_VSEL		0x6e5b
+#define CHT_WC_VDDQ_VSEL		0x6e5c
+#define CHT_WC_V2P8SX_CTRL		0x6e5d
+#define CHT_WC_V3P3A_CTRL		0x6e5e
+#define CHT_WC_V3P3SD_CTRL		0x6e5f
+#define CHT_WC_VSDIO_CTRL		0x6e67
+#define CHT_WC_V3P3A_VSEL		0x6e68
+#define CHT_WC_VPROG1A_CTRL		0x6e90
+#define CHT_WC_VPROG1B_CTRL		0x6e91
+#define CHT_WC_VPROG1F_CTRL		0x6e95
+#define CHT_WC_VPROG2D_CTRL		0x6e99
+#define CHT_WC_VPROG3A_CTRL		0x6e9a
+#define CHT_WC_VPROG3B_CTRL		0x6e9b
+#define CHT_WC_VPROG4A_CTRL		0x6e9c
+#define CHT_WC_VPROG4B_CTRL		0x6e9d
+#define CHT_WC_VPROG4C_CTRL		0x6e9e
+#define CHT_WC_VPROG4D_CTRL		0x6e9f
+#define CHT_WC_VPROG5A_CTRL		0x6ea0
+#define CHT_WC_VPROG5B_CTRL		0x6ea1
+#define CHT_WC_VPROG6A_CTRL		0x6ea2
+#define CHT_WC_VPROG6B_CTRL		0x6ea3
+#define CHT_WC_VPROG1A_VSEL		0x6ec0
+#define CHT_WC_VPROG1B_VSEL		0x6ec1
+#define CHT_WC_V1P8SX_VSEL		0x6ec2
+#define CHT_WC_V1P2SX_VSEL		0x6ec3
+#define CHT_WC_V1P2A_VSEL		0x6ec4
+#define CHT_WC_VPROG1F_VSEL		0x6ec5
+#define CHT_WC_VSDIO_VSEL		0x6ec6
+#define CHT_WC_V2P8SX_VSEL		0x6ec7
+#define CHT_WC_V3P3SD_VSEL		0x6ec8
+#define CHT_WC_VPROG2D_VSEL		0x6ec9
+#define CHT_WC_VPROG3A_VSEL		0x6eca
+#define CHT_WC_VPROG3B_VSEL		0x6ecb
+#define CHT_WC_VPROG4A_VSEL		0x6ecc
+#define CHT_WC_VPROG4B_VSEL		0x6ecd
+#define CHT_WC_VPROG4C_VSEL		0x6ece
+#define CHT_WC_VPROG4D_VSEL		0x6ecf
+#define CHT_WC_VPROG5A_VSEL		0x6ed0
+#define CHT_WC_VPROG5B_VSEL		0x6ed1
+#define CHT_WC_VPROG6A_VSEL		0x6ed2
+#define CHT_WC_VPROG6B_VSEL		0x6ed3
+
+/*
+ * Regulator support is based on the non upstream patch:
+ * "regulator: whiskey_cove: implements Whiskey Cove pmic VRF support"
+ * https://github.com/intel-aero/meta-intel-aero/blob/master/recipes-kernel/linux/linux-yocto/0019-regulator-whiskey_cove-implements-WhiskeyCove-pmic-V.patch
+ */
+static struct pmic_table power_table[] = {
+	{
+		.address = 0x0,
+		.reg = CHT_WC_V1P8A_CTRL,
+		.bit = 0x01,
+	}, /* V18A */
+	{
+		.address = 0x04,
+		.reg = CHT_WC_V1P8SX_CTRL,
+		.bit = 0x07,
+	}, /* V18X */
+	{
+		.address = 0x08,
+		.reg = CHT_WC_VDDQ_CTRL,
+		.bit = 0x01,
+	}, /* VDDQ */
+	{
+		.address = 0x0c,
+		.reg = CHT_WC_V1P2A_CTRL,
+		.bit = 0x07,
+	}, /* V12A */
+	{
+		.address = 0x10,
+		.reg = CHT_WC_V1P2SX_CTRL,
+		.bit = 0x07,
+	}, /* V12X */
+	{
+		.address = 0x14,
+		.reg = CHT_WC_V2P8SX_CTRL,
+		.bit = 0x07,
+	}, /* V28X */
+	{
+		.address = 0x18,
+		.reg = CHT_WC_V3P3A_CTRL,
+		.bit = 0x01,
+	}, /* V33A */
+	{
+		.address = 0x1c,
+		.reg = CHT_WC_V3P3SD_CTRL,
+		.bit = 0x07,
+	}, /* V3SD */
+	{
+		.address = 0x20,
+		.reg = CHT_WC_VSDIO_CTRL,
+		.bit = 0x07,
+	}, /* VSD */
+/*	{
+		.address = 0x24,
+		.reg = ??,
+		.bit = ??,
+	}, ** VSW2 */
+/*	{
+		.address = 0x28,
+		.reg = ??,
+		.bit = ??,
+	}, ** VSW1 */
+/*	{
+		.address = 0x2c,
+		.reg = ??,
+		.bit = ??,
+	}, ** VUPY */
+/*	{
+		.address = 0x30,
+		.reg = ??,
+		.bit = ??,
+	}, ** VRSO */
+	{
+		.address = 0x34,
+		.reg = CHT_WC_VPROG1A_CTRL,
+		.bit = 0x07,
+	}, /* VP1A */
+	{
+		.address = 0x38,
+		.reg = CHT_WC_VPROG1B_CTRL,
+		.bit = 0x07,
+	}, /* VP1B */
+	{
+		.address = 0x3c,
+		.reg = CHT_WC_VPROG1F_CTRL,
+		.bit = 0x07,
+	}, /* VP1F */
+	{
+		.address = 0x40,
+		.reg = CHT_WC_VPROG2D_CTRL,
+		.bit = 0x07,
+	}, /* VP2D */
+	{
+		.address = 0x44,
+		.reg = CHT_WC_VPROG3A_CTRL,
+		.bit = 0x07,
+	}, /* VP3A */
+	{
+		.address = 0x48,
+		.reg = CHT_WC_VPROG3B_CTRL,
+		.bit = 0x07,
+	}, /* VP3B */
+	{
+		.address = 0x4c,
+		.reg = CHT_WC_VPROG4A_CTRL,
+		.bit = 0x07,
+	}, /* VP4A */
+	{
+		.address = 0x50,
+		.reg = CHT_WC_VPROG4B_CTRL,
+		.bit = 0x07,
+	}, /* VP4B */
+	{
+		.address = 0x54,
+		.reg = CHT_WC_VPROG4C_CTRL,
+		.bit = 0x07,
+	}, /* VP4C */
+	{
+		.address = 0x58,
+		.reg = CHT_WC_VPROG4D_CTRL,
+		.bit = 0x07,
+	}, /* VP4D */
+	{
+		.address = 0x5c,
+		.reg = CHT_WC_VPROG5A_CTRL,
+		.bit = 0x07,
+	}, /* VP5A */
+	{
+		.address = 0x60,
+		.reg = CHT_WC_VPROG5B_CTRL,
+		.bit = 0x07,
+	}, /* VP5B */
+	{
+		.address = 0x64,
+		.reg = CHT_WC_VPROG6A_CTRL,
+		.bit = 0x07,
+	}, /* VP6A */
+	{
+		.address = 0x68,
+		.reg = CHT_WC_VPROG6B_CTRL,
+		.bit = 0x07,
+	}, /* VP6B */
+/*	{
+		.address = 0x6c,
+		.reg = ??,
+		.bit = ??,
+	}  ** VP7A */
+};
+
+static int intel_cht_wc_pmic_get_power(struct regmap *regmap, int reg,
+		int bit, u64 *value)
+{
+	int data;
+
+	if (regmap_read(regmap, reg, &data))
+		return -EIO;
+
+	*value = (data & bit) ? 1 : 0;
+	return 0;
+}
+
+static int intel_cht_wc_pmic_update_power(struct regmap *regmap, int reg,
+		int bitmask, bool on)
+{
+	return regmap_update_bits(regmap, reg, bitmask, on ? 1 : 0);
+}
+
+/*
+ * The thermal table and ops are empty, we do not support the Thermal opregion
+ * (DPTF) due to lacking documentation.
+ */
+static struct intel_pmic_opregion_data intel_cht_wc_pmic_opregion_data = {
+	.get_power		= intel_cht_wc_pmic_get_power,
+	.update_power		= intel_cht_wc_pmic_update_power,
+	.power_table		= power_table,
+	.power_table_count	= ARRAY_SIZE(power_table),
+};
+
+static int intel_cht_wc_pmic_opregion_probe(struct platform_device *pdev)
+{
+	struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
+
+	return intel_pmic_install_opregion_handler(&pdev->dev,
+			ACPI_HANDLE(pdev->dev.parent),
+			pmic->regmap,
+			&intel_cht_wc_pmic_opregion_data);
+}
+
+static struct platform_device_id cht_wc_opregion_id_table[] = {
+	{ .name = "cht_wcove_region" },
+	{},
+};
+MODULE_DEVICE_TABLE(platform, cht_wc_opregion_id_table);
+
+static struct platform_driver intel_cht_wc_pmic_opregion_driver = {
+	.probe = intel_cht_wc_pmic_opregion_probe,
+	.driver = {
+		.name = "cht_whiskey_cove_pmic",
+	},
+	.id_table = cht_wc_opregion_id_table,
+};
+module_platform_driver(intel_cht_wc_pmic_opregion_driver);
+
+MODULE_DESCRIPTION("Intel CHT Whiskey Cove PMIC operation region driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/pmic/intel_pmic_xpower.c b/drivers/acpi/pmic/intel_pmic_xpower.c
index e6e991ac20f3..55f51115f016 100644
--- a/drivers/acpi/pmic/intel_pmic_xpower.c
+++ b/drivers/acpi/pmic/intel_pmic_xpower.c
@@ -18,7 +18,6 @@
 #include <linux/mfd/axp20x.h>
 #include <linux/regmap.h>
 #include <linux/platform_device.h>
-#include <linux/iio/consumer.h>
 #include "intel_pmic.h"
 
 #define XPOWER_GPADC_LOW	0x5b
@@ -186,28 +185,16 @@ static int intel_xpower_pmic_update_power(struct regmap *regmap, int reg,
  * @regmap: regmap of the PMIC device
  * @reg: register to get the reading
  *
- * We could get the sensor value by manipulating the HW regs here, but since
- * the axp288 IIO driver may also access the same regs at the same time, the
- * APIs provided by IIO subsystem are used here instead to avoid problems. As
- * a result, the two passed in params are of no actual use.
- *
  * Return a positive value on success, errno on failure.
  */
 static int intel_xpower_pmic_get_raw_temp(struct regmap *regmap, int reg)
 {
-	struct iio_channel *gpadc_chan;
-	int ret, val;
-
-	gpadc_chan = iio_channel_get(NULL, "axp288-system-temp");
-	if (IS_ERR_OR_NULL(gpadc_chan))
-		return -EACCES;
+	u8 buf[2];
 
-	ret = iio_read_channel_raw(gpadc_chan, &val);
-	if (ret < 0)
-		val = ret;
+	if (regmap_bulk_read(regmap, AXP288_GP_ADC_H, buf, 2))
+		return -EIO;
 
-	iio_channel_release(gpadc_chan);
-	return val;
+	return (buf[0] << 4) + ((buf[1] >> 4) & 0x0F);
 }
 
 static struct intel_pmic_opregion_data intel_xpower_pmic_opregion_data = {
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index fcd4ce6f78d5..1c2b846c5776 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state)
 		return -EINVAL;
 
 	/* The state of the list is 'on' IFF all resources are 'on'. */
+	cur_state = 0;
 	list_for_each_entry(entry, list, node) {
 		struct acpi_power_resource *resource = entry->resource;
 		acpi_handle handle = resource->device.handle;
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 611a5585a902..b933061b6b60 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -32,12 +32,12 @@ static struct acpi_table_madt *get_madt_table(void)
 }
 
 static int map_lapic_id(struct acpi_subtable_header *entry,
-		 u32 acpi_id, phys_cpuid_t *apic_id, bool ignore_disabled)
+		 u32 acpi_id, phys_cpuid_t *apic_id)
 {
 	struct acpi_madt_local_apic *lapic =
 		container_of(entry, struct acpi_madt_local_apic, header);
 
-	if (ignore_disabled && !(lapic->lapic_flags & ACPI_MADT_ENABLED))
+	if (!(lapic->lapic_flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
 
 	if (lapic->processor_id != acpi_id)
@@ -48,13 +48,12 @@ static int map_lapic_id(struct acpi_subtable_header *entry,
 }
 
 static int map_x2apic_id(struct acpi_subtable_header *entry,
-		int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id,
-		bool ignore_disabled)
+		int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id)
 {
 	struct acpi_madt_local_x2apic *apic =
 		container_of(entry, struct acpi_madt_local_x2apic, header);
 
-	if (ignore_disabled && !(apic->lapic_flags & ACPI_MADT_ENABLED))
+	if (!(apic->lapic_flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
 
 	if (device_declaration && (apic->uid == acpi_id)) {
@@ -66,13 +65,12 @@ static int map_x2apic_id(struct acpi_subtable_header *entry,
 }
 
 static int map_lsapic_id(struct acpi_subtable_header *entry,
-		int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id,
-		bool ignore_disabled)
+		int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id)
 {
 	struct acpi_madt_local_sapic *lsapic =
 		container_of(entry, struct acpi_madt_local_sapic, header);
 
-	if (ignore_disabled && !(lsapic->lapic_flags & ACPI_MADT_ENABLED))
+	if (!(lsapic->lapic_flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
 
 	if (device_declaration) {
@@ -89,13 +87,12 @@ static int map_lsapic_id(struct acpi_subtable_header *entry,
  * Retrieve the ARM CPU physical identifier (MPIDR)
  */
 static int map_gicc_mpidr(struct acpi_subtable_header *entry,
-		int device_declaration, u32 acpi_id, phys_cpuid_t *mpidr,
-		bool ignore_disabled)
+		int device_declaration, u32 acpi_id, phys_cpuid_t *mpidr)
 {
 	struct acpi_madt_generic_interrupt *gicc =
 	    container_of(entry, struct acpi_madt_generic_interrupt, header);
 
-	if (ignore_disabled && !(gicc->flags & ACPI_MADT_ENABLED))
+	if (!(gicc->flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
 
 	/* device_declaration means Device object in DSDT, in the
@@ -112,7 +109,7 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry,
 }
 
 static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt,
-				   int type, u32 acpi_id, bool ignore_disabled)
+				   int type, u32 acpi_id)
 {
 	unsigned long madt_end, entry;
 	phys_cpuid_t phys_id = PHYS_CPUID_INVALID;	/* CPU hardware ID */
@@ -130,20 +127,16 @@ static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt,
 		struct acpi_subtable_header *header =
 			(struct acpi_subtable_header *)entry;
 		if (header->type == ACPI_MADT_TYPE_LOCAL_APIC) {
-			if (!map_lapic_id(header, acpi_id, &phys_id,
-					  ignore_disabled))
+			if (!map_lapic_id(header, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC) {
-			if (!map_x2apic_id(header, type, acpi_id, &phys_id,
-					   ignore_disabled))
+			if (!map_x2apic_id(header, type, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC) {
-			if (!map_lsapic_id(header, type, acpi_id, &phys_id,
-					   ignore_disabled))
+			if (!map_lsapic_id(header, type, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) {
-			if (!map_gicc_mpidr(header, type, acpi_id, &phys_id,
-					    ignore_disabled))
+			if (!map_gicc_mpidr(header, type, acpi_id, &phys_id))
 				break;
 		}
 		entry += header->length;
@@ -161,15 +154,14 @@ phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id)
 	if (!madt)
 		return PHYS_CPUID_INVALID;
 
-	rv = map_madt_entry(madt, 1, acpi_id, true);
+	rv = map_madt_entry(madt, 1, acpi_id);
 
 	acpi_put_table((struct acpi_table_header *)madt);
 
 	return rv;
 }
 
-static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id,
-				  bool ignore_disabled)
+static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *obj;
@@ -190,38 +182,30 @@ static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id,
 
 	header = (struct acpi_subtable_header *)obj->buffer.pointer;
 	if (header->type == ACPI_MADT_TYPE_LOCAL_APIC)
-		map_lapic_id(header, acpi_id, &phys_id, ignore_disabled);
+		map_lapic_id(header, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC)
-		map_lsapic_id(header, type, acpi_id, &phys_id, ignore_disabled);
+		map_lsapic_id(header, type, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC)
-		map_x2apic_id(header, type, acpi_id, &phys_id, ignore_disabled);
+		map_x2apic_id(header, type, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT)
-		map_gicc_mpidr(header, type, acpi_id, &phys_id,
-			       ignore_disabled);
+		map_gicc_mpidr(header, type, acpi_id, &phys_id);
 
 exit:
 	kfree(buffer.pointer);
 	return phys_id;
 }
 
-static phys_cpuid_t __acpi_get_phys_id(acpi_handle handle, int type,
-				       u32 acpi_id, bool ignore_disabled)
+phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
 {
 	phys_cpuid_t phys_id;
 
-	phys_id = map_mat_entry(handle, type, acpi_id, ignore_disabled);
+	phys_id = map_mat_entry(handle, type, acpi_id);
 	if (invalid_phys_cpuid(phys_id))
-		phys_id = map_madt_entry(get_madt_table(), type, acpi_id,
-					   ignore_disabled);
+		phys_id = map_madt_entry(get_madt_table(), type, acpi_id);
 
 	return phys_id;
 }
 
-phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
-{
-	return __acpi_get_phys_id(handle, type, acpi_id, true);
-}
-
 int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id)
 {
 #ifdef CONFIG_SMP
@@ -278,79 +262,6 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
 
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
-static bool __init
-map_processor(acpi_handle handle, phys_cpuid_t *phys_id, int *cpuid)
-{
-	int type, id;
-	u32 acpi_id;
-	acpi_status status;
-	acpi_object_type acpi_type;
-	unsigned long long tmp;
-	union acpi_object object = { 0 };
-	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
-
-	status = acpi_get_type(handle, &acpi_type);
-	if (ACPI_FAILURE(status))
-		return false;
-
-	switch (acpi_type) {
-	case ACPI_TYPE_PROCESSOR:
-		status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
-		if (ACPI_FAILURE(status))
-			return false;
-		acpi_id = object.processor.proc_id;
-
-		/* validate the acpi_id */
-		if(acpi_processor_validate_proc_id(acpi_id))
-			return false;
-		break;
-	case ACPI_TYPE_DEVICE:
-		status = acpi_evaluate_integer(handle, "_UID", NULL, &tmp);
-		if (ACPI_FAILURE(status))
-			return false;
-		acpi_id = tmp;
-		break;
-	default:
-		return false;
-	}
-
-	type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0;
-
-	*phys_id = __acpi_get_phys_id(handle, type, acpi_id, false);
-	id = acpi_map_cpuid(*phys_id, acpi_id);
-
-	if (id < 0)
-		return false;
-	*cpuid = id;
-	return true;
-}
-
-static acpi_status __init
-set_processor_node_mapping(acpi_handle handle, u32 lvl, void *context,
-			   void **rv)
-{
-	phys_cpuid_t phys_id;
-	int cpu_id;
-
-	if (!map_processor(handle, &phys_id, &cpu_id))
-		return AE_ERROR;
-
-	acpi_map_cpu2node(handle, cpu_id, phys_id);
-	return AE_OK;
-}
-
-void __init acpi_set_processor_mapping(void)
-{
-	/* Set persistent cpu <-> node mapping for all processors. */
-	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
-			    ACPI_UINT32_MAX, set_processor_node_mapping,
-			    NULL, NULL, NULL);
-}
-#else
-void __init acpi_set_processor_mapping(void) {}
-#endif /* CONFIG_ACPI_HOTPLUG_CPU */
-
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
 static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base,
 			 u64 *phys_addr, int *ioapic_id)
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 9d5f0c7ed3f7..8697a82bd465 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -251,6 +251,9 @@ static int __acpi_processor_start(struct acpi_device *device)
 	if (ACPI_SUCCESS(status))
 		return 0;
 
+	result = -ENODEV;
+	acpi_pss_perf_exit(pr, device);
+
 err_power_exit:
 	acpi_processor_power_exit(pr);
 	return result;
@@ -259,11 +262,16 @@ err_power_exit:
 static int acpi_processor_start(struct device *dev)
 {
 	struct acpi_device *device = ACPI_COMPANION(dev);
+	int ret;
 
 	if (!device)
 		return -ENODEV;
 
-	return __acpi_processor_start(device);
+	/* Protect against concurrent CPU hotplug operations */
+	get_online_cpus();
+	ret = __acpi_processor_start(device);
+	put_online_cpus();
+	return ret;
 }
 
 static int acpi_processor_stop(struct device *dev)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index a12f96cc93ff..3de34633f7f9 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -62,8 +62,8 @@ struct acpi_processor_throttling_arg {
 #define THROTTLING_POSTCHANGE      (2)
 
 static int acpi_processor_get_throttling(struct acpi_processor *pr);
-int acpi_processor_set_throttling(struct acpi_processor *pr,
-						int state, bool force);
+static int __acpi_processor_set_throttling(struct acpi_processor *pr,
+					   int state, bool force, bool direct);
 
 static int acpi_processor_update_tsd_coord(void)
 {
@@ -891,7 +891,8 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr)
 			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				"Invalid throttling state, reset\n"));
 			state = 0;
-			ret = acpi_processor_set_throttling(pr, state, true);
+			ret = __acpi_processor_set_throttling(pr, state, true,
+							      true);
 			if (ret)
 				return ret;
 		}
@@ -901,36 +902,31 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr)
 	return 0;
 }
 
-static int acpi_processor_get_throttling(struct acpi_processor *pr)
+static long __acpi_processor_get_throttling(void *data)
 {
-	cpumask_var_t saved_mask;
-	int ret;
+	struct acpi_processor *pr = data;
+
+	return pr->throttling.acpi_processor_get_throttling(pr);
+}
 
+static int acpi_processor_get_throttling(struct acpi_processor *pr)
+{
 	if (!pr)
 		return -EINVAL;
 
 	if (!pr->flags.throttling)
 		return -ENODEV;
 
-	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	/*
-	 * Migrate task to the cpu pointed by pr.
+	 * This is either called from the CPU hotplug callback of
+	 * processor_driver or via the ACPI probe function. In the latter
+	 * case the CPU is not guaranteed to be online. Both call sites are
+	 * protected against CPU hotplug.
 	 */
-	cpumask_copy(saved_mask, &current->cpus_allowed);
-	/* FIXME: use work_on_cpu() */
-	if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
-		/* Can't migrate to the target pr->id CPU. Exit */
-		free_cpumask_var(saved_mask);
+	if (!cpu_online(pr->id))
 		return -ENODEV;
-	}
-	ret = pr->throttling.acpi_processor_get_throttling(pr);
-	/* restore the previous state */
-	set_cpus_allowed_ptr(current, saved_mask);
-	free_cpumask_var(saved_mask);
 
-	return ret;
+	return work_on_cpu(pr->id, __acpi_processor_get_throttling, pr);
 }
 
 static int acpi_processor_get_fadt_info(struct acpi_processor *pr)
@@ -1080,8 +1076,15 @@ static long acpi_processor_throttling_fn(void *data)
 			arg->target_state, arg->force);
 }
 
-int acpi_processor_set_throttling(struct acpi_processor *pr,
-						int state, bool force)
+static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
+{
+	if (direct)
+		return fn(arg);
+	return work_on_cpu(cpu, fn, arg);
+}
+
+static int __acpi_processor_set_throttling(struct acpi_processor *pr,
+					   int state, bool force, bool direct)
 {
 	int ret = 0;
 	unsigned int i;
@@ -1130,7 +1133,8 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 		arg.pr = pr;
 		arg.target_state = state;
 		arg.force = force;
-		ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
+		ret = call_on_cpu(pr->id, acpi_processor_throttling_fn, &arg,
+				  direct);
 	} else {
 		/*
 		 * When the T-state coordination is SW_ALL or HW_ALL,
@@ -1163,8 +1167,8 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 			arg.pr = match_pr;
 			arg.target_state = state;
 			arg.force = force;
-			ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
-				&arg);
+			ret = call_on_cpu(pr->id, acpi_processor_throttling_fn,
+					  &arg, direct);
 		}
 	}
 	/*
@@ -1182,6 +1186,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr,
 	return ret;
 }
 
+int acpi_processor_set_throttling(struct acpi_processor *pr, int state,
+				  bool force)
+{
+	return __acpi_processor_set_throttling(pr, state, force, false);
+}
+
 int acpi_processor_get_throttling_info(struct acpi_processor *pr)
 {
 	int result = 0;
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 3afddcd834ef..9364398204e9 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -37,14 +37,16 @@ static const u8 ads_uuid[16] = {
 
 static bool acpi_enumerate_nondev_subnodes(acpi_handle scope,
 					   const union acpi_object *desc,
-					   struct acpi_device_data *data);
+					   struct acpi_device_data *data,
+					   struct fwnode_handle *parent);
 static bool acpi_extract_properties(const union acpi_object *desc,
 				    struct acpi_device_data *data);
 
 static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
 					acpi_handle handle,
 					const union acpi_object *link,
-					struct list_head *list)
+					struct list_head *list,
+					struct fwnode_handle *parent)
 {
 	struct acpi_data_node *dn;
 	bool result;
@@ -55,6 +57,7 @@ static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
 
 	dn->name = link->package.elements[0].string.pointer;
 	dn->fwnode.type = FWNODE_ACPI_DATA;
+	dn->parent = parent;
 	INIT_LIST_HEAD(&dn->data.subnodes);
 
 	result = acpi_extract_properties(desc, &dn->data);
@@ -71,9 +74,11 @@ static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
 		 */
 		status = acpi_get_parent(handle, &scope);
 		if (ACPI_SUCCESS(status)
-		    && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data))
+		    && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data,
+						      &dn->fwnode))
 			result = true;
-	} else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data)) {
+	} else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data,
+						  &dn->fwnode)) {
 		result = true;
 	}
 
@@ -91,7 +96,8 @@ static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
 
 static bool acpi_nondev_subnode_data_ok(acpi_handle handle,
 					const union acpi_object *link,
-					struct list_head *list)
+					struct list_head *list,
+					struct fwnode_handle *parent)
 {
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
 	acpi_status status;
@@ -101,7 +107,8 @@ static bool acpi_nondev_subnode_data_ok(acpi_handle handle,
 	if (ACPI_FAILURE(status))
 		return false;
 
-	if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list))
+	if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list,
+					parent))
 		return true;
 
 	ACPI_FREE(buf.pointer);
@@ -110,7 +117,8 @@ static bool acpi_nondev_subnode_data_ok(acpi_handle handle,
 
 static bool acpi_nondev_subnode_ok(acpi_handle scope,
 				   const union acpi_object *link,
-				   struct list_head *list)
+				   struct list_head *list,
+				   struct fwnode_handle *parent)
 {
 	acpi_handle handle;
 	acpi_status status;
@@ -123,12 +131,13 @@ static bool acpi_nondev_subnode_ok(acpi_handle scope,
 	if (ACPI_FAILURE(status))
 		return false;
 
-	return acpi_nondev_subnode_data_ok(handle, link, list);
+	return acpi_nondev_subnode_data_ok(handle, link, list, parent);
 }
 
 static int acpi_add_nondev_subnodes(acpi_handle scope,
 				    const union acpi_object *links,
-				    struct list_head *list)
+				    struct list_head *list,
+				    struct fwnode_handle *parent)
 {
 	bool ret = false;
 	int i;
@@ -150,15 +159,18 @@ static int acpi_add_nondev_subnodes(acpi_handle scope,
 		/* The second one may be a string, a reference or a package. */
 		switch (link->package.elements[1].type) {
 		case ACPI_TYPE_STRING:
-			result = acpi_nondev_subnode_ok(scope, link, list);
+			result = acpi_nondev_subnode_ok(scope, link, list,
+							 parent);
 			break;
 		case ACPI_TYPE_LOCAL_REFERENCE:
 			handle = link->package.elements[1].reference.handle;
-			result = acpi_nondev_subnode_data_ok(handle, link, list);
+			result = acpi_nondev_subnode_data_ok(handle, link, list,
+							     parent);
 			break;
 		case ACPI_TYPE_PACKAGE:
 			desc = &link->package.elements[1];
-			result = acpi_nondev_subnode_extract(desc, NULL, link, list);
+			result = acpi_nondev_subnode_extract(desc, NULL, link,
+							     list, parent);
 			break;
 		default:
 			result = false;
@@ -172,7 +184,8 @@ static int acpi_add_nondev_subnodes(acpi_handle scope,
 
 static bool acpi_enumerate_nondev_subnodes(acpi_handle scope,
 					   const union acpi_object *desc,
-					   struct acpi_device_data *data)
+					   struct acpi_device_data *data,
+					   struct fwnode_handle *parent)
 {
 	int i;
 
@@ -194,7 +207,8 @@ static bool acpi_enumerate_nondev_subnodes(acpi_handle scope,
 		if (memcmp(uuid->buffer.pointer, ads_uuid, sizeof(ads_uuid)))
 			continue;
 
-		return acpi_add_nondev_subnodes(scope, links, &data->subnodes);
+		return acpi_add_nondev_subnodes(scope, links, &data->subnodes,
+						parent);
 	}
 
 	return false;
@@ -345,7 +359,8 @@ void acpi_init_properties(struct acpi_device *adev)
 		if (acpi_of)
 			acpi_init_of_compatible(adev);
 	}
-	if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer, &adev->data))
+	if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer,
+					&adev->data, acpi_fwnode_handle(adev)))
 		adev->data.pointer = buf.pointer;
 
 	if (!adev->data.pointer) {
@@ -699,6 +714,8 @@ static int acpi_data_prop_read_single(struct acpi_device_data *data,
 			return ret;
 
 		*(char **)val = obj->string.pointer;
+
+		return 1;
 	} else {
 		ret = -EINVAL;
 	}
@@ -708,7 +725,15 @@ static int acpi_data_prop_read_single(struct acpi_device_data *data,
 int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
 			      enum dev_prop_type proptype, void *val)
 {
-	return adev ? acpi_data_prop_read_single(&adev->data, propname, proptype, val) : -EINVAL;
+	int ret;
+
+	if (!adev)
+		return -EINVAL;
+
+	ret = acpi_data_prop_read_single(&adev->data, propname, proptype, val);
+	if (ret < 0 || proptype != ACPI_TYPE_STRING)
+		return ret;
+	return 0;
 }
 
 static int acpi_copy_property_array_u8(const union acpi_object *items, u8 *val,
@@ -784,7 +809,7 @@ static int acpi_copy_property_array_string(const union acpi_object *items,
 
 		val[i] = items[i].string.pointer;
 	}
-	return 0;
+	return nval;
 }
 
 static int acpi_data_prop_read(struct acpi_device_data *data,
@@ -798,7 +823,7 @@ static int acpi_data_prop_read(struct acpi_device_data *data,
 
 	if (val && nval == 1) {
 		ret = acpi_data_prop_read_single(data, propname, proptype, val);
-		if (!ret)
+		if (ret >= 0)
 			return ret;
 	}
 
@@ -809,7 +834,7 @@ static int acpi_data_prop_read(struct acpi_device_data *data,
 	if (!val)
 		return obj->package.count;
 
-	if (nval > obj->package.count)
+	if (proptype != DEV_PROP_STRING && nval > obj->package.count)
 		return -EOVERFLOW;
 	else if (nval <= 0)
 		return -EINVAL;
@@ -830,7 +855,9 @@ static int acpi_data_prop_read(struct acpi_device_data *data,
 		ret = acpi_copy_property_array_u64(items, (u64 *)val, nval);
 		break;
 	case DEV_PROP_STRING:
-		ret = acpi_copy_property_array_string(items, (char **)val, nval);
+		ret = acpi_copy_property_array_string(
+			items, (char **)val,
+			min_t(u32, nval, obj->package.count));
 		break;
 	default:
 		ret = -EINVAL;
@@ -865,21 +892,22 @@ int acpi_node_prop_read(struct fwnode_handle *fwnode,  const char *propname,
 }
 
 /**
- * acpi_get_next_subnode - Return the next child node handle for a device.
- * @dev: Device to find the next child node for.
+ * acpi_get_next_subnode - Return the next child node handle for a fwnode
+ * @fwnode: Firmware node to find the next child node for.
  * @child: Handle to one of the device's child nodes or a null handle.
  */
-struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
+struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode,
 					    struct fwnode_handle *child)
 {
-	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct acpi_device *adev = to_acpi_device_node(fwnode);
 	struct list_head *head, *next;
 
-	if (!adev)
-		return NULL;
-
 	if (!child || child->type == FWNODE_ACPI) {
-		head = &adev->children;
+		if (adev)
+			head = &adev->children;
+		else
+			goto nondev;
+
 		if (list_empty(head))
 			goto nondev;
 
@@ -888,7 +916,6 @@ struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
 			next = adev->node.next;
 			if (next == head) {
 				child = NULL;
-				adev = ACPI_COMPANION(dev);
 				goto nondev;
 			}
 			adev = list_entry(next, struct acpi_device, node);
@@ -900,9 +927,16 @@ struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
 
  nondev:
 	if (!child || child->type == FWNODE_ACPI_DATA) {
+		struct acpi_data_node *data = to_acpi_data_node(fwnode);
 		struct acpi_data_node *dn;
 
-		head = &adev->data.subnodes;
+		if (adev)
+			head = &adev->data.subnodes;
+		else if (data)
+			head = &data->data.subnodes;
+		else
+			return NULL;
+
 		if (list_empty(head))
 			return NULL;
 
@@ -920,3 +954,168 @@ struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
 	}
 	return NULL;
 }
+
+/**
+ * acpi_node_get_parent - Return parent fwnode of this fwnode
+ * @fwnode: Firmware node whose parent to get
+ *
+ * Returns parent node of an ACPI device or data firmware node or %NULL if
+ * not available.
+ */
+struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode)
+{
+	if (is_acpi_data_node(fwnode)) {
+		/* All data nodes have parent pointer so just return that */
+		return to_acpi_data_node(fwnode)->parent;
+	} else if (is_acpi_device_node(fwnode)) {
+		acpi_handle handle, parent_handle;
+
+		handle = to_acpi_device_node(fwnode)->handle;
+		if (ACPI_SUCCESS(acpi_get_parent(handle, &parent_handle))) {
+			struct acpi_device *adev;
+
+			if (!acpi_bus_get_device(parent_handle, &adev))
+				return acpi_fwnode_handle(adev);
+		}
+	}
+
+	return NULL;
+}
+
+/**
+ * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node
+ * @fwnode: Pointer to the parent firmware node
+ * @prev: Previous endpoint node or %NULL to get the first
+ *
+ * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns
+ * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case
+ * of success the next endpoint is returned.
+ */
+struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+						   struct fwnode_handle *prev)
+{
+	struct fwnode_handle *port = NULL;
+	struct fwnode_handle *endpoint;
+
+	if (!prev) {
+		do {
+			port = fwnode_get_next_child_node(fwnode, port);
+			/* Ports must have port property */
+			if (fwnode_property_present(port, "port"))
+				break;
+		} while (port);
+	} else {
+		port = fwnode_get_parent(prev);
+	}
+
+	if (!port)
+		return NULL;
+
+	endpoint = fwnode_get_next_child_node(port, prev);
+	while (!endpoint) {
+		port = fwnode_get_next_child_node(fwnode, port);
+		if (!port)
+			break;
+		if (fwnode_property_present(port, "port"))
+			endpoint = fwnode_get_next_child_node(port, NULL);
+	}
+
+	if (endpoint) {
+		/* Endpoints must have "endpoint" property */
+		if (!fwnode_property_present(endpoint, "endpoint"))
+			return ERR_PTR(-EPROTO);
+	}
+
+	return endpoint;
+}
+
+/**
+ * acpi_graph_get_child_prop_value - Return a child with a given property value
+ * @fwnode: device fwnode
+ * @prop_name: The name of the property to look for
+ * @val: the desired property value
+ *
+ * Return the port node corresponding to a given port number. Returns
+ * the child node on success, NULL otherwise.
+ */
+static struct fwnode_handle *acpi_graph_get_child_prop_value(
+	struct fwnode_handle *fwnode, const char *prop_name, unsigned int val)
+{
+	struct fwnode_handle *child;
+
+	fwnode_for_each_child_node(fwnode, child) {
+		u32 nr;
+
+		if (!fwnode_property_read_u32(fwnode, prop_name, &nr))
+			continue;
+
+		if (val == nr)
+			return child;
+	}
+
+	return NULL;
+}
+
+
+/**
+ * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint
+ * @fwnode: Endpoint firmware node pointing to a remote device
+ * @parent: Firmware node of remote port parent is filled here if not %NULL
+ * @port: Firmware node of remote port is filled here if not %NULL
+ * @endpoint: Firmware node of remote endpoint is filled here if not %NULL
+ *
+ * Function parses remote end of ACPI firmware remote endpoint and fills in
+ * fields requested by the caller. Returns %0 in case of success and
+ * negative errno otherwise.
+ */
+int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
+				   struct fwnode_handle **parent,
+				   struct fwnode_handle **port,
+				   struct fwnode_handle **endpoint)
+{
+	unsigned int port_nr, endpoint_nr;
+	struct acpi_reference_args args;
+	int ret;
+
+	memset(&args, 0, sizeof(args));
+	ret = acpi_node_get_property_reference(fwnode, "remote-endpoint", 0,
+					       &args);
+	if (ret)
+		return ret;
+
+	/*
+	 * Always require two arguments with the reference: port and
+	 * endpoint indices.
+	 */
+	if (args.nargs != 2)
+		return -EPROTO;
+
+	fwnode = acpi_fwnode_handle(args.adev);
+	port_nr = args.args[0];
+	endpoint_nr = args.args[1];
+
+	if (parent)
+		*parent = fwnode;
+
+	if (!port && !endpoint)
+		return 0;
+
+	fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr);
+	if (!fwnode)
+		return -EPROTO;
+
+	if (port)
+		*port = fwnode;
+
+	if (!endpoint)
+		return 0;
+
+	fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint",
+						 endpoint_nr);
+	if (!fwnode)
+		return -EPROTO;
+
+	*endpoint = fwnode;
+
+	return 0;
+}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 192691880d55..c26931067415 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -30,12 +30,6 @@ extern struct acpi_device *acpi_root;
 
 #define INVALID_ACPI_HANDLE	((acpi_handle)empty_zero_page)
 
-/*
- * If set, devices will be hot-removed even if they cannot be put offline
- * gracefully (from the kernel's standpoint).
- */
-bool acpi_force_hot_remove;
-
 static const char *dummy_hid = "device";
 
 static LIST_HEAD(acpi_dep_list);
@@ -170,9 +164,6 @@ static acpi_status acpi_bus_offline(acpi_handle handle, u32 lvl, void *data,
 			pn->put_online = false;
 		}
 		ret = device_offline(pn->dev);
-		if (acpi_force_hot_remove)
-			continue;
-
 		if (ret >= 0) {
 			pn->put_online = !ret;
 		} else {
@@ -241,11 +232,11 @@ static int acpi_scan_try_to_offline(struct acpi_device *device)
 		acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
 				    NULL, acpi_bus_offline, (void *)true,
 				    (void **)&errdev);
-		if (!errdev || acpi_force_hot_remove)
+		if (!errdev)
 			acpi_bus_offline(handle, 0, (void *)true,
 					 (void **)&errdev);
 
-		if (errdev && !acpi_force_hot_remove) {
+		if (errdev) {
 			dev_warn(errdev, "Offline failed.\n");
 			acpi_bus_online(handle, 0, NULL, NULL);
 			acpi_walk_namespace(ACPI_TYPE_ANY, handle,
@@ -263,8 +254,7 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 	unsigned long long sta;
 	acpi_status status;
 
-	if (device->handler && device->handler->hotplug.demand_offline
-	    && !acpi_force_hot_remove) {
+	if (device->handler && device->handler->hotplug.demand_offline) {
 		if (!acpi_scan_is_offline(device, true))
 			return -EBUSY;
 	} else {
@@ -1850,6 +1840,8 @@ static void acpi_bus_attach(struct acpi_device *device)
 			device->flags.power_manageable = 0;
 
 		device->flags.initialized = true;
+	} else if (device->flags.visited) {
+		goto ok;
 	}
 
 	ret = acpi_scan_attach_handler(device);
@@ -1857,15 +1849,20 @@ static void acpi_bus_attach(struct acpi_device *device)
 		return;
 
 	device->flags.match_driver = true;
-	if (!ret) {
-		ret = device_attach(&device->dev);
-		if (ret < 0)
-			return;
-
-		if (!ret && device->pnp.type.platform_id)
-			acpi_default_enumeration(device);
+	if (ret > 0) {
+		acpi_device_set_enumerated(device);
+		goto ok;
 	}
 
+	ret = device_attach(&device->dev);
+	if (ret < 0)
+		return;
+
+	if (device->pnp.type.platform_id)
+		acpi_default_enumeration(device);
+	else
+		acpi_device_set_enumerated(device);
+
  ok:
 	list_for_each_entry(child, &device->children, node)
 		acpi_bus_attach(child);
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index 01c94669a2b0..3afa8c1fa127 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -30,7 +30,7 @@ static bool qdf2400_erratum_44_present(struct acpi_table_header *h)
 		return true;
 
 	if (!memcmp(h->oem_table_id, "QDF2400 ", ACPI_OEM_TABLE_ID_SIZE) &&
-			h->oem_revision == 0)
+			h->oem_revision == 1)
 		return true;
 
 	return false;
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index cf05ae973381..1b5ee1e0e5a3 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -921,7 +921,7 @@ void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
 static ssize_t force_remove_show(struct kobject *kobj,
 				 struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", !!acpi_force_hot_remove);
+	return sprintf(buf, "%d\n", 0);
 }
 
 static ssize_t force_remove_store(struct kobject *kobj,
@@ -935,9 +935,10 @@ static ssize_t force_remove_store(struct kobject *kobj,
 	if (ret < 0)
 		return ret;
 
-	lock_device_hotplug();
-	acpi_force_hot_remove = val;
-	unlock_device_hotplug();
+	if (val) {
+		pr_err("Enabling force_remove is not supported anymore. Please report to linux-acpi@vger.kernel.org if you depend on this functionality\n");
+		return -EINVAL;
+	}
 	return size;
 }
 
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 2604189d6cd1..ff425390bfa8 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -311,22 +311,6 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 }
 
 int __init
-acpi_parse_entries(char *id,
-			unsigned long table_size,
-			acpi_tbl_entry_handler handler,
-			struct acpi_table_header *table_header,
-			int entry_id, unsigned int max_entries)
-{
-	struct acpi_subtable_proc proc = {
-		.id		= entry_id,
-		.handler	= handler,
-	};
-
-	return acpi_parse_entries_array(id, table_size, table_header,
-			&proc, 1, max_entries);
-}
-
-int __init
 acpi_table_parse_entries_array(char *id,
 			 unsigned long table_size,
 			 struct acpi_subtable_proc *proc, int proc_num,
@@ -556,7 +540,7 @@ void __init acpi_table_upgrade(void)
 	 * But it's not enough on X86 because ioremap will
 	 * complain later (used by acpi_os_map_memory) that the pages
 	 * that should get mapped are not marked "reserved".
-	 * Both memblock_reserve and e820_add_region (via arch_reserve_mem_area)
+	 * Both memblock_reserve and e820__range_add (via arch_reserve_mem_area)
 	 * works fine.
 	 */
 	memblock_reserve(acpi_tables_addr, all_tables_size);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 22c09952e177..27d0dcfcf47d 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -736,6 +736,72 @@ bool acpi_dev_found(const char *hid)
 }
 EXPORT_SYMBOL(acpi_dev_found);
 
+struct acpi_dev_present_info {
+	struct acpi_device_id hid[2];
+	const char *uid;
+	s64 hrv;
+};
+
+static int acpi_dev_present_cb(struct device *dev, void *data)
+{
+	struct acpi_device *adev = to_acpi_device(dev);
+	struct acpi_dev_present_info *match = data;
+	unsigned long long hrv;
+	acpi_status status;
+
+	if (acpi_match_device_ids(adev, match->hid))
+		return 0;
+
+	if (match->uid && (!adev->pnp.unique_id ||
+	    strcmp(adev->pnp.unique_id, match->uid)))
+		return 0;
+
+	if (match->hrv == -1)
+		return 1;
+
+	status = acpi_evaluate_integer(adev->handle, "_HRV", NULL, &hrv);
+	if (ACPI_FAILURE(status))
+		return 0;
+
+	return hrv == match->hrv;
+}
+
+/**
+ * acpi_dev_present - Detect that a given ACPI device is present
+ * @hid: Hardware ID of the device.
+ * @uid: Unique ID of the device, pass NULL to not check _UID
+ * @hrv: Hardware Revision of the device, pass -1 to not check _HRV
+ *
+ * Return %true if a matching device was present at the moment of invocation.
+ * Note that if the device is pluggable, it may since have disappeared.
+ *
+ * Note that unlike acpi_dev_found() this function checks the status
+ * of the device. So for devices which are present in the dsdt, but
+ * which are disabled (their _STA callback returns 0) this function
+ * will return false.
+ *
+ * For this function to work, acpi_bus_scan() must have been executed
+ * which happens in the subsys_initcall() subsection. Hence, do not
+ * call from a subsys_initcall() or earlier (use acpi_get_devices()
+ * instead). Calling from module_init() is fine (which is synonymous
+ * with device_initcall()).
+ */
+bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
+{
+	struct acpi_dev_present_info match = {};
+	struct device *dev;
+
+	strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
+	match.uid = uid;
+	match.hrv = hrv;
+
+	dev = bus_find_device(&acpi_bus_type, NULL, &match,
+			      acpi_dev_present_cb);
+
+	return !!dev;
+}
+EXPORT_SYMBOL(acpi_dev_present);
+
 /*
  * acpi_backlight= handling, this is done here rather then in video_detect.c
  * because __setup cannot be used in modules.
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 70b57d2229d6..ff6cb9e4c381 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -14,7 +14,6 @@ menuconfig ATA
 	tristate "Serial ATA and Parallel ATA drivers (libata)"
 	depends on HAS_IOMEM
 	depends on BLOCK
-	depends on !(M32R || S390) || BROKEN
 	select SCSI
 	select GLOB
 	---help---
@@ -118,6 +117,15 @@ config AHCI_DA850
 
 	  If unsure, say N.
 
+config AHCI_DM816
+	tristate "DaVinci DM816 AHCI SATA support"
+	depends on ARCH_OMAP2PLUS
+	help
+	  This option enables support for the DaVinci DM816 SoC's
+	  onboard AHCI SATA controller.
+
+	  If unsure, say N.
+
 config AHCI_ST
 	tristate "ST AHCI SATA support"
 	depends on ARCH_STI
@@ -885,14 +893,6 @@ config PATA_AT32
 
 	  If unsure, say N.
 
-config PATA_AT91
-	tristate "PATA support for AT91SAM9260"
-	depends on ARM && SOC_AT91SAM9
-	help
-	  This option enables support for IDE devices on the Atmel AT91SAM9260 SoC.
-
-	  If unsure, say N.
-
 config PATA_CMD640_PCI
 	tristate "CMD640 PCI PATA support (Experimental)"
 	depends on PCI
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 89a0a1915d36..3048cc100a46 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_SATA_HIGHBANK)	+= sata_highbank.o libahci.o
 obj-$(CONFIG_AHCI_BRCM)		+= ahci_brcm.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_CEVA)		+= ahci_ceva.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_DA850)	+= ahci_da850.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_DM816)	+= ahci_dm816.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_IMX)		+= ahci_imx.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_MVEBU)	+= ahci_mvebu.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_OCTEON)	+= ahci_octeon.o
@@ -91,7 +92,6 @@ obj-$(CONFIG_PATA_WINBOND)	+= pata_sl82c105.o
 
 # SFF PIO only
 obj-$(CONFIG_PATA_AT32)		+= pata_at32.o
-obj-$(CONFIG_PATA_AT91)		+= pata_at91.o
 obj-$(CONFIG_PATA_CMD640_PCI)	+= pata_cmd640.o
 obj-$(CONFIG_PATA_FALCON)	+= pata_falcon.o
 obj-$(CONFIG_PATA_ISAPNP)	+= pata_isapnp.o
diff --git a/drivers/ata/ahci_dm816.c b/drivers/ata/ahci_dm816.c
new file mode 100644
index 000000000000..fbd827c3a75c
--- /dev/null
+++ b/drivers/ata/ahci_dm816.c
@@ -0,0 +1,200 @@
+/*
+ * DaVinci DM816 AHCI SATA platform driver
+ *
+ * Copyright (C) 2017 BayLibre SAS
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/pm.h>
+#include <linux/platform_device.h>
+#include <linux/libata.h>
+#include <linux/ahci_platform.h>
+
+#include "ahci.h"
+
+#define AHCI_DM816_DRV_NAME		"ahci-dm816"
+
+#define AHCI_DM816_PHY_ENPLL(x)		((x) << 0)
+#define AHCI_DM816_PHY_MPY(x)		((x) << 1)
+#define AHCI_DM816_PHY_LOS(x)		((x) << 12)
+#define AHCI_DM816_PHY_RXCDR(x)		((x) << 13)
+#define AHCI_DM816_PHY_RXEQ(x)		((x) << 16)
+#define AHCI_DM816_PHY_TXSWING(x)	((x) << 23)
+
+#define AHCI_DM816_P0PHYCR_REG		0x178
+#define AHCI_DM816_P1PHYCR_REG		0x1f8
+
+#define AHCI_DM816_PLL_OUT		1500000000LU
+
+static const unsigned long pll_mpy_table[] = {
+	  400,  500,  600,  800,  825, 1000, 1200,
+	 1250, 1500, 1600, 1650, 2000, 2200, 2500
+};
+
+static int ahci_dm816_get_mpy_bits(unsigned long refclk_rate)
+{
+	unsigned long pll_multiplier;
+	int i;
+
+	/*
+	 * We need to determine the value of the multiplier (MPY) bits.
+	 * In order to include the 8.25 multiplier we need to first divide
+	 * the refclk rate by 100.
+	 */
+	pll_multiplier = AHCI_DM816_PLL_OUT / (refclk_rate / 100);
+
+	for (i = 0; i < ARRAY_SIZE(pll_mpy_table); i++) {
+		if (pll_mpy_table[i] == pll_multiplier)
+			return i;
+	}
+
+	/*
+	 * We should have divided evenly - if not, return an invalid
+	 * value.
+	 */
+	return -1;
+}
+
+static int ahci_dm816_phy_init(struct ahci_host_priv *hpriv, struct device *dev)
+{
+	unsigned long refclk_rate;
+	int mpy;
+	u32 val;
+
+	/*
+	 * We should have been supplied two clocks: the functional and
+	 * keep-alive clock and the external reference clock. We need the
+	 * rate of the latter to calculate the correct value of MPY bits.
+	 */
+	if (!hpriv->clks[1]) {
+		dev_err(dev, "reference clock not supplied\n");
+		return -EINVAL;
+	}
+
+	refclk_rate = clk_get_rate(hpriv->clks[1]);
+	if ((refclk_rate % 100) != 0) {
+		dev_err(dev, "reference clock rate must be divisible by 100\n");
+		return -EINVAL;
+	}
+
+	mpy = ahci_dm816_get_mpy_bits(refclk_rate);
+	if (mpy < 0) {
+		dev_err(dev, "can't calculate the MPY bits value\n");
+		return -EINVAL;
+	}
+
+	/* Enable the PHY and configure the first HBA port. */
+	val = AHCI_DM816_PHY_MPY(mpy) | AHCI_DM816_PHY_LOS(1) |
+	      AHCI_DM816_PHY_RXCDR(4) | AHCI_DM816_PHY_RXEQ(1) |
+	      AHCI_DM816_PHY_TXSWING(3) | AHCI_DM816_PHY_ENPLL(1);
+	writel(val, hpriv->mmio + AHCI_DM816_P0PHYCR_REG);
+
+	/* Configure the second HBA port. */
+	val = AHCI_DM816_PHY_LOS(1) | AHCI_DM816_PHY_RXCDR(4) |
+	      AHCI_DM816_PHY_RXEQ(1) | AHCI_DM816_PHY_TXSWING(3);
+	writel(val, hpriv->mmio + AHCI_DM816_P1PHYCR_REG);
+
+	return 0;
+}
+
+static int ahci_dm816_softreset(struct ata_link *link,
+				unsigned int *class, unsigned long deadline)
+{
+	int pmp, ret;
+
+	pmp = sata_srst_pmp(link);
+
+	/*
+	 * There's an issue with the SATA controller on DM816 SoC: if we
+	 * enable Port Multiplier support, but the drive is connected directly
+	 * to the board, it can't be detected. As a workaround: if PMP is
+	 * enabled, we first call ahci_do_softreset() and pass it the result of
+	 * sata_srst_pmp(). If this call fails, we retry with pmp = 0.
+	 */
+	ret = ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
+	if (pmp && ret == -EBUSY)
+		return ahci_do_softreset(link, class, 0,
+					 deadline, ahci_check_ready);
+
+	return ret;
+}
+
+static struct ata_port_operations ahci_dm816_port_ops = {
+	.inherits = &ahci_platform_ops,
+	.softreset = ahci_dm816_softreset,
+};
+
+static const struct ata_port_info ahci_dm816_port_info = {
+	.flags		= AHCI_FLAG_COMMON,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_dm816_port_ops,
+};
+
+static struct scsi_host_template ahci_dm816_platform_sht = {
+	AHCI_SHT(AHCI_DM816_DRV_NAME),
+};
+
+static int ahci_dm816_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ahci_host_priv *hpriv;
+	int rc;
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
+
+	rc = ahci_dm816_phy_init(hpriv, dev);
+	if (rc)
+		goto disable_resources;
+
+	rc = ahci_platform_init_host(pdev, hpriv,
+				     &ahci_dm816_port_info,
+				     &ahci_dm816_platform_sht);
+	if (rc)
+		goto disable_resources;
+
+	return 0;
+
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+
+	return rc;
+}
+
+static SIMPLE_DEV_PM_OPS(ahci_dm816_pm_ops,
+			 ahci_platform_suspend,
+			 ahci_platform_resume);
+
+static const struct of_device_id ahci_dm816_of_match[] = {
+	{ .compatible = "ti,dm816-ahci", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ahci_dm816_of_match);
+
+static struct platform_driver ahci_dm816_driver = {
+	.probe = ahci_dm816_probe,
+	.remove = ata_platform_remove_one,
+	.driver = {
+		.name = AHCI_DM816_DRV_NAME,
+		.of_match_table = ahci_dm816_of_match,
+		.pm = &ahci_dm816_pm_ops,
+	},
+};
+module_platform_driver(ahci_dm816_driver);
+
+MODULE_DESCRIPTION("DaVinci DM816 AHCI SATA platform driver");
+MODULE_AUTHOR("Bartosz Golaszewski <bgolaszewski@baylibre.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/ata/ahci_octeon.c b/drivers/ata/ahci_octeon.c
index ea865fe953e1..5a44e089c6bb 100644
--- a/drivers/ata/ahci_octeon.c
+++ b/drivers/ata/ahci_octeon.c
@@ -38,11 +38,6 @@ static int ahci_octeon_probe(struct platform_device *pdev)
 	int ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Platform resource[0] is missing\n");
-		return -ENODEV;
-	}
-
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 85d833289f28..4c96f3ac4976 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -177,7 +177,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 	case AHCI_LS1043A:
 		if (!qpriv->ecc_addr)
 			return -EINVAL;
-		writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr);
+		writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
+				qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
@@ -194,7 +195,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 	case AHCI_LS1046A:
 		if (!qpriv->ecc_addr)
 			return -EINVAL;
-		writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr);
+		writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
+				qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ca75823697dd..2d83b8c75965 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4910,7 +4910,7 @@ void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_sg_clean(struct ata_queued_cmd *qc)
+static void ata_sg_clean(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct scatterlist *sg = qc->sg;
@@ -5902,9 +5902,9 @@ struct ata_port *ata_port_alloc(struct ata_host *host)
 	INIT_LIST_HEAD(&ap->eh_done_q);
 	init_waitqueue_head(&ap->eh_wait_q);
 	init_completion(&ap->park_req_pending);
-	init_timer_deferrable(&ap->fastdrain_timer);
-	ap->fastdrain_timer.function = ata_eh_fastdrain_timerfn;
-	ap->fastdrain_timer.data = (unsigned long)ap;
+	setup_deferrable_timer(&ap->fastdrain_timer,
+			       ata_eh_fastdrain_timerfn,
+			       (unsigned long)ap);
 
 	ap->cbl = ATA_CBL_NONE;
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 1ac70744ae7b..49ba9834c715 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3393,46 +3393,6 @@ static size_t ata_format_dsm_trim_descr(struct scsi_cmnd *cmd, u32 trmax,
 }
 
 /**
- * ata_format_dsm_trim_descr() - SATL Write Same to ATA SCT Write Same
- * @cmd: SCSI command being translated
- * @lba: Starting sector
- * @num: Number of sectors to be zero'd.
- *
- * Rewrite the WRITE SAME payload to be an SCT Write Same formatted
- * descriptor.
- * NOTE: Writes a pattern (0's) in the foreground.
- *
- * Return: Number of bytes copied into sglist.
- */
-static size_t ata_format_sct_write_same(struct scsi_cmnd *cmd, u64 lba, u64 num)
-{
-	struct scsi_device *sdp = cmd->device;
-	size_t len = sdp->sector_size;
-	size_t r;
-	u16 *buf;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ata_scsi_rbuf_lock, flags);
-	buf = ((void *)ata_scsi_rbuf);
-
-	put_unaligned_le16(0x0002,  &buf[0]); /* SCT_ACT_WRITE_SAME */
-	put_unaligned_le16(0x0101,  &buf[1]); /* WRITE PTRN FG */
-	put_unaligned_le64(lba,     &buf[2]);
-	put_unaligned_le64(num,     &buf[6]);
-	put_unaligned_le32(0u,      &buf[10]); /* pattern */
-
-	WARN_ON(len > ATA_SCSI_RBUF_SIZE);
-
-	if (len > ATA_SCSI_RBUF_SIZE)
-		len = ATA_SCSI_RBUF_SIZE;
-
-	r = sg_copy_from_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, len);
-	spin_unlock_irqrestore(&ata_scsi_rbuf_lock, flags);
-
-	return r;
-}
-
-/**
  * ata_scsi_write_same_xlat() - SATL Write Same to ATA SCT Write Same
  * @qc: Command to be translated
  *
@@ -3462,32 +3422,31 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
 	if (unlikely(!dev->dma_mode))
 		goto invalid_opcode;
 
+	/*
+	 * We only allow sending this command through the block layer,
+	 * as it modifies the DATA OUT buffer, which would corrupt user
+	 * memory for SG_IO commands.
+	 */
+	if (unlikely(blk_rq_is_passthrough(scmd->request)))
+		goto invalid_opcode;
+
 	if (unlikely(scmd->cmd_len < 16)) {
 		fp = 15;
 		goto invalid_fld;
 	}
 	scsi_16_lba_len(cdb, &block, &n_block);
 
-	if (unmap) {
-		/* If trim is not enabled the cmd is invalid. */
-		if ((dev->horkage & ATA_HORKAGE_NOTRIM) ||
-		    !ata_id_has_trim(dev->id)) {
-			fp = 1;
-			bp = 3;
-			goto invalid_fld;
-		}
-		/* If the request is too large the cmd is invalid */
-		if (n_block > 0xffff * trmax) {
-			fp = 2;
-			goto invalid_fld;
-		}
-	} else {
-		/* If write same is not available the cmd is invalid */
-		if (!ata_id_sct_write_same(dev->id)) {
-			fp = 1;
-			bp = 3;
-			goto invalid_fld;
-		}
+	if (!unmap ||
+	    (dev->horkage & ATA_HORKAGE_NOTRIM) ||
+	    !ata_id_has_trim(dev->id)) {
+		fp = 1;
+		bp = 3;
+		goto invalid_fld;
+	}
+	/* If the request is too large the cmd is invalid */
+	if (n_block > 0xffff * trmax) {
+		fp = 2;
+		goto invalid_fld;
 	}
 
 	/*
@@ -3502,49 +3461,28 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
 	 * For DATA SET MANAGEMENT TRIM in ACS-2 nsect (aka count)
 	 * is defined as number of 512 byte blocks to be transferred.
 	 */
-	if (unmap) {
-		size = ata_format_dsm_trim_descr(scmd, trmax, block, n_block);
-		if (size != len)
-			goto invalid_param_len;
 
-		if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
-			/* Newer devices support queued TRIM commands */
-			tf->protocol = ATA_PROT_NCQ;
-			tf->command = ATA_CMD_FPDMA_SEND;
-			tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
-			tf->nsect = qc->tag << 3;
-			tf->hob_feature = (size / 512) >> 8;
-			tf->feature = size / 512;
+	size = ata_format_dsm_trim_descr(scmd, trmax, block, n_block);
+	if (size != len)
+		goto invalid_param_len;
 
-			tf->auxiliary = 1;
-		} else {
-			tf->protocol = ATA_PROT_DMA;
-			tf->hob_feature = 0;
-			tf->feature = ATA_DSM_TRIM;
-			tf->hob_nsect = (size / 512) >> 8;
-			tf->nsect = size / 512;
-			tf->command = ATA_CMD_DSM;
-		}
-	} else {
-		size = ata_format_sct_write_same(scmd, block, n_block);
-		if (size != len)
-			goto invalid_param_len;
+	if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
+		/* Newer devices support queued TRIM commands */
+		tf->protocol = ATA_PROT_NCQ;
+		tf->command = ATA_CMD_FPDMA_SEND;
+		tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
+		tf->nsect = qc->tag << 3;
+		tf->hob_feature = (size / 512) >> 8;
+		tf->feature = size / 512;
 
-		tf->hob_feature = 0;
-		tf->feature = 0;
-		tf->hob_nsect = 0;
-		tf->nsect = 1;
-		tf->lbah = 0;
-		tf->lbam = 0;
-		tf->lbal = ATA_CMD_STANDBYNOW1;
-		tf->hob_lbah = 0;
-		tf->hob_lbam = 0;
-		tf->hob_lbal = 0;
-		tf->device = ATA_CMD_STANDBYNOW1;
+		tf->auxiliary = 1;
+	} else {
 		tf->protocol = ATA_PROT_DMA;
-		tf->command = ATA_CMD_WRITE_LOG_DMA_EXT;
-		if (unlikely(dev->flags & ATA_DFLAG_PIO))
-			tf->command = ATA_CMD_WRITE_LOG_EXT;
+		tf->hob_feature = 0;
+		tf->feature = ATA_DSM_TRIM;
+		tf->hob_nsect = (size / 512) >> 8;
+		tf->nsect = size / 512;
+		tf->command = ATA_CMD_DSM;
 	}
 
 	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48 |
@@ -3619,10 +3557,6 @@ static unsigned int ata_scsiop_maint_in(struct ata_scsi_args *args, u8 *rbuf)
 	case START_STOP:
 		supported = 3;
 		break;
-	case WRITE_SAME_16:
-		if (!ata_id_sct_write_same(dev->id))
-			break;
-		/* fallthrough: if SCT ... only enable for ZBC */
 	case ZBC_IN:
 	case ZBC_OUT:
 		if (ata_id_zoned_cap(dev->id) ||
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 2bd92dca3e62..274d6d7193d7 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -1482,7 +1482,6 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc)
 		break;
 
 	default:
-		WARN_ON_ONCE(1);
 		return AC_ERR_SYSTEM;
 	}
 
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index 46698232e6bf..19e6e539a061 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -224,7 +224,6 @@ static DECLARE_TRANSPORT_CLASS(ata_port_class,
 
 static void ata_tport_release(struct device *dev)
 {
-	put_device(dev->parent);
 }
 
 /**
@@ -284,7 +283,7 @@ int ata_tport_add(struct device *parent,
 	device_initialize(dev);
 	dev->type = &ata_port_type;
 
-	dev->parent = get_device(parent);
+	dev->parent = parent;
 	dev->release = ata_tport_release;
 	dev_set_name(dev, "ata%d", ap->print_id);
 	transport_setup_device(dev);
@@ -348,7 +347,6 @@ static DECLARE_TRANSPORT_CLASS(ata_link_class,
 
 static void ata_tlink_release(struct device *dev)
 {
-	put_device(dev->parent);
 }
 
 /**
@@ -410,7 +408,7 @@ int ata_tlink_add(struct ata_link *link)
 	int error;
 
 	device_initialize(dev);
-	dev->parent = get_device(&ap->tdev);
+	dev->parent = &ap->tdev;
 	dev->release = ata_tlink_release;
 	if (ata_is_host_link(link))
 		dev_set_name(dev, "link%d", ap->print_id);
@@ -589,7 +587,6 @@ static DECLARE_TRANSPORT_CLASS(ata_dev_class,
 
 static void ata_tdev_release(struct device *dev)
 {
-	put_device(dev->parent);
 }
 
 /**
@@ -662,7 +659,7 @@ static int ata_tdev_add(struct ata_device *ata_dev)
 	int error;
 
 	device_initialize(dev);
-	dev->parent = get_device(&link->tdev);
+	dev->parent = &link->tdev;
 	dev->release = ata_tdev_release;
 	if (ata_is_host_link(link))
 		dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno);
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
deleted file mode 100644
index fd5b34f0d007..000000000000
--- a/drivers/ata/pata_at91.c
+++ /dev/null
@@ -1,503 +0,0 @@
-/*
- * PATA driver for AT91SAM9260 Static Memory Controller
- * with CompactFlash interface in True IDE mode
- *
- * Copyright (C) 2009 Matyukevich Sergey
- *               2011 Igor Plyatov
- *
- * Based on:
- *      * generic platform driver by Paul Mundt: drivers/ata/pata_platform.c
- *      * pata_at32 driver by Kristoffer Nyborg Gregertsen
- *      * at91_ide driver by Stanislaw Gruszka
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/blkdev.h>
-#include <linux/gfp.h>
-#include <scsi/scsi_host.h>
-#include <linux/ata.h>
-#include <linux/clk.h>
-#include <linux/libata.h>
-#include <linux/mfd/syscon.h>
-#include <linux/mfd/syscon/atmel-smc.h>
-#include <linux/platform_device.h>
-#include <linux/ata_platform.h>
-#include <linux/platform_data/atmel.h>
-#include <linux/regmap.h>
-#include <linux/gpio.h>
-
-#define DRV_NAME		"pata_at91"
-#define DRV_VERSION		"0.3"
-
-#define CF_IDE_OFFSET		0x00c00000
-#define CF_ALT_IDE_OFFSET	0x00e00000
-#define CF_IDE_RES_SIZE		0x08
-#define CS_PULSE_MAXIMUM	319
-#define ER_SMC_CALC		1
-#define ER_SMC_RECALC		2
-
-struct at91_ide_info {
-	unsigned long mode;
-	unsigned int cs;
-	struct clk *mck;
-	void __iomem *ide_addr;
-	void __iomem *alt_addr;
-};
-
-/**
- * struct smc_range - range of valid values for SMC register.
- */
-struct smc_range {
-	int min;
-	int max;
-};
-
-struct regmap *smc;
-
-struct at91sam9_smc_generic_fields {
-	struct regmap_field *setup;
-	struct regmap_field *pulse;
-	struct regmap_field *cycle;
-	struct regmap_field *mode;
-} fields;
-
-/**
- * adjust_smc_value - adjust value for one of SMC registers.
- * @value: adjusted value
- * @range: array of SMC ranges with valid values
- * @size: SMC ranges array size
- *
- * This returns the difference between input and output value or negative
- * in case of invalid input value.
- * If negative returned, then output value = maximal possible from ranges.
- */
-static int adjust_smc_value(int *value, struct smc_range *range, int size)
-{
-	int maximum = (range + size - 1)->max;
-	int remainder;
-
-	do {
-		if (*value < range->min) {
-			remainder = range->min - *value;
-			*value = range->min; /* nearest valid value */
-			return remainder;
-		} else if ((range->min <= *value) && (*value <= range->max))
-			return 0;
-
-		range++;
-	} while (--size);
-	*value = maximum;
-
-	return -1; /* invalid value */
-}
-
-/**
- * calc_smc_vals - calculate SMC register values
- * @dev: ATA device
- * @setup: SMC_SETUP register value
- * @pulse: SMC_PULSE register value
- * @cycle: SMC_CYCLE register value
- *
- * This returns negative in case of invalid values for SMC registers:
- * -ER_SMC_RECALC - recalculation required for SMC values,
- * -ER_SMC_CALC - calculation failed (invalid input values).
- *
- * SMC use special coding scheme, see "Coding and Range of Timing
- * Parameters" table from AT91SAM9 datasheets.
- *
- *	SMC_SETUP = 128*setup[5] + setup[4:0]
- *	SMC_PULSE = 256*pulse[6] + pulse[5:0]
- *	SMC_CYCLE = 256*cycle[8:7] + cycle[6:0]
- */
-static int calc_smc_vals(struct device *dev,
-		int *setup, int *pulse, int *cycle, int *cs_pulse)
-{
-	int ret_val;
-	int err = 0;
-	struct smc_range range_setup[] = {	/* SMC_SETUP valid values */
-		{.min = 0,	.max = 31},	/* first  range */
-		{.min = 128,	.max = 159}	/* second range */
-	};
-	struct smc_range range_pulse[] = {	/* SMC_PULSE valid values */
-		{.min = 0,	.max = 63},	/* first  range */
-		{.min = 256,	.max = 319}	/* second range */
-	};
-	struct smc_range range_cycle[] = {	/* SMC_CYCLE valid values */
-		{.min = 0,	.max = 127},	/* first  range */
-		{.min = 256,	.max = 383},	/* second range */
-		{.min = 512,	.max = 639},	/* third  range */
-		{.min = 768,	.max = 895}	/* fourth range */
-	};
-
-	ret_val = adjust_smc_value(setup, range_setup, ARRAY_SIZE(range_setup));
-	if (ret_val < 0)
-		dev_warn(dev, "maximal SMC Setup value\n");
-	else
-		*cycle += ret_val;
-
-	ret_val = adjust_smc_value(pulse, range_pulse, ARRAY_SIZE(range_pulse));
-	if (ret_val < 0)
-		dev_warn(dev, "maximal SMC Pulse value\n");
-	else
-		*cycle += ret_val;
-
-	ret_val = adjust_smc_value(cycle, range_cycle, ARRAY_SIZE(range_cycle));
-	if (ret_val < 0)
-		dev_warn(dev, "maximal SMC Cycle value\n");
-
-	*cs_pulse = *cycle;
-	if (*cs_pulse > CS_PULSE_MAXIMUM) {
-		dev_err(dev, "unable to calculate valid SMC settings\n");
-		return -ER_SMC_CALC;
-	}
-
-	ret_val = adjust_smc_value(cs_pulse, range_pulse,
-					ARRAY_SIZE(range_pulse));
-	if (ret_val < 0) {
-		dev_warn(dev, "maximal SMC CS Pulse value\n");
-	} else if (ret_val != 0) {
-		*cycle = *cs_pulse;
-		dev_warn(dev, "SMC Cycle extended\n");
-		err = -ER_SMC_RECALC;
-	}
-
-	return err;
-}
-
-/**
- * to_smc_format - convert values into SMC format
- * @setup: SETUP value of SMC Setup Register
- * @pulse: PULSE value of SMC Pulse Register
- * @cycle: CYCLE value of SMC Cycle Register
- * @cs_pulse: NCS_PULSE value of SMC Pulse Register
- */
-static void to_smc_format(int *setup, int *pulse, int *cycle, int *cs_pulse)
-{
-	*setup = (*setup & 0x1f) | ((*setup & 0x80) >> 2);
-	*pulse = (*pulse & 0x3f) | ((*pulse & 0x100) >> 2);
-	*cycle = (*cycle & 0x7f) | ((*cycle & 0x300) >> 1);
-	*cs_pulse = (*cs_pulse & 0x3f) | ((*cs_pulse & 0x100) >> 2);
-}
-
-static unsigned long calc_mck_cycles(unsigned long ns, unsigned long mck_hz)
-{
-	unsigned long mul;
-
-	/*
-	* cycles = x [nsec] * f [Hz] / 10^9 [ns in sec] =
-	*     x * (f / 1_000_000_000) =
-	*     x * ((f * 65536) / 1_000_000_000) / 65536 =
-	*     x * (((f / 10_000) * 65536) / 100_000) / 65536 =
-	*/
-
-	mul = (mck_hz / 10000) << 16;
-	mul /= 100000;
-
-	return (ns * mul + 65536) >> 16;    /* rounding */
-}
-
-/**
- * set_smc_timing - SMC timings setup.
- * @dev: device
- * @info: AT91 IDE info
- * @ata: ATA timings
- *
- * Its assumed that write timings are same as read timings,
- * cs_setup = 0 and cs_pulse = cycle.
- */
-static void set_smc_timing(struct device *dev, struct ata_device *adev,
-		struct at91_ide_info *info, const struct ata_timing *ata)
-{
-	int ret = 0;
-	int use_iordy;
-	unsigned int t6z;         /* data tristate time in ns */
-	unsigned int cycle;       /* SMC Cycle width in MCK ticks */
-	unsigned int setup;       /* SMC Setup width in MCK ticks */
-	unsigned int pulse;       /* CFIOR and CFIOW pulse width in MCK ticks */
-	unsigned int cs_pulse;    /* CS4 or CS5 pulse width in MCK ticks*/
-	unsigned int tdf_cycles;  /* SMC TDF MCK ticks */
-	unsigned long mck_hz;     /* MCK frequency in Hz */
-
-	t6z = (ata->mode < XFER_PIO_5) ? 30 : 20;
-	mck_hz = clk_get_rate(info->mck);
-	cycle = calc_mck_cycles(ata->cyc8b, mck_hz);
-	setup = calc_mck_cycles(ata->setup, mck_hz);
-	pulse = calc_mck_cycles(ata->act8b, mck_hz);
-	tdf_cycles = calc_mck_cycles(t6z, mck_hz);
-
-	do {
-		ret = calc_smc_vals(dev, &setup, &pulse, &cycle, &cs_pulse);
-	} while (ret == -ER_SMC_RECALC);
-
-	if (ret == -ER_SMC_CALC)
-		dev_err(dev, "Interface may not operate correctly\n");
-
-	dev_dbg(dev, "SMC Setup=%u, Pulse=%u, Cycle=%u, CS Pulse=%u\n",
-		setup, pulse, cycle, cs_pulse);
-	to_smc_format(&setup, &pulse, &cycle, &cs_pulse);
-	/* disable or enable waiting for IORDY signal */
-	use_iordy = ata_pio_need_iordy(adev);
-	if (use_iordy)
-		info->mode |= AT91_SMC_EXNWMODE_READY;
-
-	if (tdf_cycles > 15) {
-		tdf_cycles = 15;
-		dev_warn(dev, "maximal SMC TDF Cycles value\n");
-	}
-
-	dev_dbg(dev, "Use IORDY=%u, TDF Cycles=%u\n", use_iordy, tdf_cycles);
-
-	regmap_fields_write(fields.setup, info->cs,
-			    AT91SAM9_SMC_NRDSETUP(setup) |
-			    AT91SAM9_SMC_NWESETUP(setup) |
-			    AT91SAM9_SMC_NCS_NRDSETUP(0) |
-			    AT91SAM9_SMC_NCS_WRSETUP(0));
-	regmap_fields_write(fields.pulse, info->cs,
-			    AT91SAM9_SMC_NRDPULSE(pulse) |
-			    AT91SAM9_SMC_NWEPULSE(pulse) |
-			    AT91SAM9_SMC_NCS_NRDPULSE(cs_pulse) |
-			    AT91SAM9_SMC_NCS_WRPULSE(cs_pulse));
-	regmap_fields_write(fields.cycle, info->cs,
-			    AT91SAM9_SMC_NRDCYCLE(cycle) |
-			    AT91SAM9_SMC_NWECYCLE(cycle));
-	regmap_fields_write(fields.mode, info->cs, info->mode |
-			    AT91_SMC_TDF_(tdf_cycles));
-}
-
-static void pata_at91_set_piomode(struct ata_port *ap, struct ata_device *adev)
-{
-	struct at91_ide_info *info = ap->host->private_data;
-	struct ata_timing timing;
-	int ret;
-
-	/* Compute ATA timing and set it to SMC */
-	ret = ata_timing_compute(adev, adev->pio_mode, &timing, 1000, 0);
-	if (ret) {
-		dev_warn(ap->dev, "Failed to compute ATA timing %d, "
-			 "set PIO_0 timing\n", ret);
-		timing = *ata_timing_find_mode(XFER_PIO_0);
-	}
-	set_smc_timing(ap->dev, adev, info, &timing);
-}
-
-static unsigned int pata_at91_data_xfer_noirq(struct ata_queued_cmd *qc,
-		unsigned char *buf, unsigned int buflen, int rw)
-{
-	struct at91_ide_info *info = qc->dev->link->ap->host->private_data;
-	unsigned int consumed;
-	unsigned int mode;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	regmap_fields_read(fields.mode, info->cs, &mode);
-
-	/* set 16bit mode before writing data */
-	regmap_fields_write(fields.mode, info->cs, (mode & ~AT91_SMC_DBW) |
-			    AT91_SMC_DBW_16);
-
-	consumed = ata_sff_data_xfer(qc, buf, buflen, rw);
-
-	/* restore 8bit mode after data is written */
-	regmap_fields_write(fields.mode, info->cs, (mode & ~AT91_SMC_DBW) |
-			    AT91_SMC_DBW_8);
-
-	local_irq_restore(flags);
-	return consumed;
-}
-
-static struct scsi_host_template pata_at91_sht = {
-	ATA_PIO_SHT(DRV_NAME),
-};
-
-static struct ata_port_operations pata_at91_port_ops = {
-	.inherits	= &ata_sff_port_ops,
-
-	.sff_data_xfer	= pata_at91_data_xfer_noirq,
-	.set_piomode	= pata_at91_set_piomode,
-	.cable_detect	= ata_cable_40wire,
-};
-
-static int at91sam9_smc_fields_init(struct device *dev)
-{
-	struct reg_field field = REG_FIELD(0, 0, 31);
-
-	field.id_size = 8;
-	field.id_offset = AT91SAM9_SMC_GENERIC_BLK_SZ;
-
-	field.reg = AT91SAM9_SMC_SETUP(AT91SAM9_SMC_GENERIC);
-	fields.setup = devm_regmap_field_alloc(dev, smc, field);
-	if (IS_ERR(fields.setup))
-		return PTR_ERR(fields.setup);
-
-	field.reg = AT91SAM9_SMC_PULSE(AT91SAM9_SMC_GENERIC);
-	fields.pulse = devm_regmap_field_alloc(dev, smc, field);
-	if (IS_ERR(fields.pulse))
-		return PTR_ERR(fields.pulse);
-
-	field.reg = AT91SAM9_SMC_CYCLE(AT91SAM9_SMC_GENERIC);
-	fields.cycle = devm_regmap_field_alloc(dev, smc, field);
-	if (IS_ERR(fields.cycle))
-		return PTR_ERR(fields.cycle);
-
-	field.reg = AT91SAM9_SMC_MODE(AT91SAM9_SMC_GENERIC);
-	fields.mode = devm_regmap_field_alloc(dev, smc, field);
-
-	return PTR_ERR_OR_ZERO(fields.mode);
-}
-
-static int pata_at91_probe(struct platform_device *pdev)
-{
-	struct at91_cf_data *board = dev_get_platdata(&pdev->dev);
-	struct device *dev = &pdev->dev;
-	struct at91_ide_info *info;
-	struct resource *mem_res;
-	struct ata_host *host;
-	struct ata_port *ap;
-
-	int irq_flags = 0;
-	int irq = 0;
-	int ret;
-
-	/*  get platform resources: IO/CTL memories and irq/rst pins */
-
-	if (pdev->num_resources != 1) {
-		dev_err(&pdev->dev, "invalid number of resources\n");
-		return -EINVAL;
-	}
-
-	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	if (!mem_res) {
-		dev_err(dev, "failed to get mem resource\n");
-		return -EINVAL;
-	}
-
-	irq = board->irq_pin;
-
-	smc = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "atmel,smc");
-	if (IS_ERR(smc))
-		return PTR_ERR(smc);
-
-	ret = at91sam9_smc_fields_init(dev);
-	if (ret < 0)
-		return ret;
-
-	/* init ata host */
-
-	host = ata_host_alloc(dev, 1);
-
-	if (!host)
-		return -ENOMEM;
-
-	ap = host->ports[0];
-	ap->ops = &pata_at91_port_ops;
-	ap->flags |= ATA_FLAG_SLAVE_POSS;
-	ap->pio_mask = ATA_PIO4;
-
-	if (!gpio_is_valid(irq)) {
-		ap->flags |= ATA_FLAG_PIO_POLLING;
-		ata_port_desc(ap, "no IRQ, using PIO polling");
-	}
-
-	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
-
-	if (!info) {
-		dev_err(dev, "failed to allocate memory for private data\n");
-		return -ENOMEM;
-	}
-
-	info->mck = clk_get(NULL, "mck");
-
-	if (IS_ERR(info->mck)) {
-		dev_err(dev, "failed to get access to mck clock\n");
-		return -ENODEV;
-	}
-
-	info->cs    = board->chipselect;
-	info->mode  = AT91_SMC_READMODE | AT91_SMC_WRITEMODE |
-		AT91_SMC_EXNWMODE_READY | AT91_SMC_BAT_SELECT |
-		AT91_SMC_DBW_8 | AT91_SMC_TDF_(0);
-
-	info->ide_addr = devm_ioremap(dev,
-			mem_res->start + CF_IDE_OFFSET, CF_IDE_RES_SIZE);
-
-	if (!info->ide_addr) {
-		dev_err(dev, "failed to map IO base\n");
-		ret = -ENOMEM;
-		goto err_put;
-	}
-
-	info->alt_addr = devm_ioremap(dev,
-			mem_res->start + CF_ALT_IDE_OFFSET, CF_IDE_RES_SIZE);
-
-	if (!info->alt_addr) {
-		dev_err(dev, "failed to map CTL base\n");
-		ret = -ENOMEM;
-		goto err_put;
-	}
-
-	ap->ioaddr.cmd_addr = info->ide_addr;
-	ap->ioaddr.ctl_addr = info->alt_addr + 0x06;
-	ap->ioaddr.altstatus_addr = ap->ioaddr.ctl_addr;
-
-	ata_sff_std_ports(&ap->ioaddr);
-
-	ata_port_desc(ap, "mmio cmd 0x%llx ctl 0x%llx",
-			(unsigned long long)mem_res->start + CF_IDE_OFFSET,
-			(unsigned long long)mem_res->start + CF_ALT_IDE_OFFSET);
-
-	host->private_data = info;
-
-	ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
-				gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
-				irq_flags, &pata_at91_sht);
-	if (ret)
-		goto err_put;
-
-	return 0;
-
-err_put:
-	clk_put(info->mck);
-	return ret;
-}
-
-static int pata_at91_remove(struct platform_device *pdev)
-{
-	struct ata_host *host = platform_get_drvdata(pdev);
-	struct at91_ide_info *info;
-
-	if (!host)
-		return 0;
-	info = host->private_data;
-
-	ata_host_detach(host);
-
-	if (!info)
-		return 0;
-
-	clk_put(info->mck);
-
-	return 0;
-}
-
-static struct platform_driver pata_at91_driver = {
-	.probe		= pata_at91_probe,
-	.remove		= pata_at91_remove,
-	.driver		= {
-		.name		= DRV_NAME,
-	},
-};
-
-module_platform_driver(pata_at91_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Driver for CF in True IDE mode on AT91SAM9260 SoC");
-MODULE_AUTHOR("Matyukevich Sergey");
-MODULE_VERSION(DRV_VERSION);
-
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 6c9aa95a9a05..49d705c9f0f7 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -278,11 +278,6 @@ static int atiixp_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	const struct ata_port_info *ppi[] = { &info, &info };
 
-	/* SB600/700 don't have secondary port wired */
-	if ((pdev->device == PCI_DEVICE_ID_ATI_IXP600_IDE) ||
-		(pdev->device == PCI_DEVICE_ID_ATI_IXP700_IDE))
-		ppi[1] = &ata_dummy_port_info;
-
 	return ata_pci_bmdma_init_one(pdev, ppi, &atiixp_sht, NULL,
 				      ATA_HOST_PARALLEL_SCAN);
 }
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index e347e7acd8ed..0adcb40d2794 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -1328,7 +1328,7 @@ static int pata_macio_pci_resume(struct pci_dev *pdev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-static struct of_device_id pata_macio_match[] =
+static const struct of_device_id pata_macio_match[] =
 {
 	{
 	.name 		= "IDE",
diff --git a/drivers/ata/pata_mpc52xx.c b/drivers/ata/pata_mpc52xx.c
index 252ba27fa63b..9730125530f6 100644
--- a/drivers/ata/pata_mpc52xx.c
+++ b/drivers/ata/pata_mpc52xx.c
@@ -847,7 +847,7 @@ mpc52xx_ata_resume(struct platform_device *op)
 }
 #endif
 
-static struct of_device_id mpc52xx_ata_of_match[] = {
+static const struct of_device_id mpc52xx_ata_of_match[] = {
 	{ .compatible = "fsl,mpc5200-ata", },
 	{ .compatible = "mpc5200-ata", },
 	{},
diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c
index 201a32d0627f..01161c1aef4d 100644
--- a/drivers/ata/pata_of_platform.c
+++ b/drivers/ata/pata_of_platform.c
@@ -67,7 +67,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
 				     reg_shift, pio_mask, &pata_platform_sht);
 }
 
-static struct of_device_id pata_of_platform_match[] = {
+static const struct of_device_id pata_of_platform_match[] = {
 	{ .compatible = "ata-generic", },
 	{ },
 };
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index a723ae929783..01734d54c69c 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1612,7 +1612,7 @@ static int sata_fsl_resume(struct platform_device *op)
 }
 #endif
 
-static struct of_device_id fsl_sata_match[] = {
+static const struct of_device_id fsl_sata_match[] = {
 	{
 		.compatible = "fsl,pq-sata",
 	},
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 00ce26d0c047..b66bcda88320 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4286,7 +4286,7 @@ static int mv_platform_resume(struct platform_device *pdev)
 #endif
 
 #ifdef CONFIG_OF
-static struct of_device_id mv_sata_dt_ids[] = {
+static const struct of_device_id mv_sata_dt_ids[] = {
 	{ .compatible = "marvell,armada-370-sata", },
 	{ .compatible = "marvell,orion-sata", },
 	{},
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index 0636d84fbefe..f3f538eec7b3 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -644,14 +644,16 @@ static void svia_configure(struct pci_dev *pdev, int board_id,
 		pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8);
 	}
 
-	/* enable IRQ on hotplug */
-	pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
-	if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
-		dev_dbg(&pdev->dev,
-			"enabling SATA hotplug (0x%x)\n",
-			(int) tmp8);
-		tmp8 |= SATA_HOTPLUG;
-		pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+	if (board_id == vt6421) {
+		/* enable IRQ on hotplug */
+		pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
+		if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
+			dev_dbg(&pdev->dev,
+				"enabling SATA hotplug (0x%x)\n",
+				(int) tmp8);
+			tmp8 |= SATA_HOTPLUG;
+			pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+		}
 	}
 
 	/*
diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c
index 4a610795b585..906705e5f776 100644
--- a/drivers/atm/ambassador.c
+++ b/drivers/atm/ambassador.c
@@ -2267,9 +2267,8 @@ static int amb_probe(struct pci_dev *pci_dev,
 	dev->atm_dev->ci_range.vpi_bits = NUM_VPI_BITS;
 	dev->atm_dev->ci_range.vci_bits = NUM_VCI_BITS;
 
-	init_timer(&dev->housekeeping);
-	dev->housekeeping.function = do_housekeeping;
-	dev->housekeeping.data = (unsigned long) dev;
+	setup_timer(&dev->housekeeping, do_housekeeping,
+		    (unsigned long)dev);
 	mod_timer(&dev->housekeeping, jiffies);
 
 	// enable host interrupts
diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c
index bf43b5d2aafc..83f1439e57fd 100644
--- a/drivers/auxdisplay/img-ascii-lcd.c
+++ b/drivers/auxdisplay/img-ascii-lcd.c
@@ -218,6 +218,7 @@ static const struct of_device_id img_ascii_lcd_matches[] = {
 	{ .compatible = "img,boston-lcd", .data = &boston_config },
 	{ .compatible = "mti,malta-lcd", .data = &malta_config },
 	{ .compatible = "mti,sead3-lcd", .data = &sead3_config },
+	{ /* sentinel */ }
 };
 
 /**
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 684bda4d14a1..6bb60fb6a30b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -639,11 +639,6 @@ int lock_device_hotplug_sysfs(void)
 	return restart_syscall();
 }
 
-void assert_held_device_hotplug(void)
-{
-	lockdep_assert_held(&device_hotplug_lock);
-}
-
 #ifdef CONFIG_BLOCK
 static inline int device_is_not_partition(struct device *dev)
 {
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index 0fc7c4da7756..d35e9a20caf7 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -345,8 +345,7 @@ platform_msi_create_device_domain(struct device *dev,
 
 	data->host_data = host_data;
 	domain = irq_domain_create_hierarchy(dev->msi_domain, 0, nvec,
-					     of_node_to_fwnode(dev->of_node),
-					     ops, data);
+					     dev->fwnode, ops, data);
 	if (!domain)
 		goto free_priv;
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e697dec9d25b..ad196427b4f2 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -121,7 +121,9 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
 #define genpd_unlock(p)			p->lock_ops->unlock(p)
 
+#define genpd_status_on(genpd)		(genpd->status == GPD_STATE_ACTIVE)
 #define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
+#define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 
 static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 		struct generic_pm_domain *genpd)
@@ -130,8 +132,12 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 
 	ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
 
-	/* Warn once if IRQ safe dev in no sleep domain */
-	if (ret)
+	/*
+	 * Warn once if an IRQ safe device is attached to a no sleep domain, as
+	 * to indicate a suboptimal configuration for PM. For an always on
+	 * domain this isn't case, thus don't warn.
+	 */
+	if (ret && !genpd_is_always_on(genpd))
 		dev_warn_once(dev, "PM domain %s will not be powered off\n",
 				genpd->name);
 
@@ -296,11 +302,15 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 	 * (1) The domain is already in the "power off" state.
 	 * (2) System suspend is in progress.
 	 */
-	if (genpd->status == GPD_STATE_POWER_OFF
-	    || genpd->prepared_count > 0)
+	if (!genpd_status_on(genpd) || genpd->prepared_count > 0)
 		return 0;
 
-	if (atomic_read(&genpd->sd_count) > 0)
+	/*
+	 * Abort power off for the PM domain in the following situations:
+	 * (1) The domain is configured as always on.
+	 * (2) When the domain has a subdomain being powered on.
+	 */
+	if (genpd_is_always_on(genpd) || atomic_read(&genpd->sd_count) > 0)
 		return -EBUSY;
 
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
@@ -373,7 +383,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 	struct gpd_link *link;
 	int ret = 0;
 
-	if (genpd->status == GPD_STATE_ACTIVE)
+	if (genpd_status_on(genpd))
 		return 0;
 
 	/*
@@ -752,7 +762,7 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
 {
 	struct gpd_link *link;
 
-	if (genpd->status == GPD_STATE_POWER_OFF)
+	if (!genpd_status_on(genpd) || genpd_is_always_on(genpd))
 		return;
 
 	if (genpd->suspended_count != genpd->device_count
@@ -761,7 +771,8 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
 
 	/* Choose the deepest state when suspending */
 	genpd->state_idx = genpd->state_count - 1;
-	_genpd_power_off(genpd, false);
+	if (_genpd_power_off(genpd, false))
+		return;
 
 	genpd->status = GPD_STATE_POWER_OFF;
 
@@ -793,7 +804,7 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 {
 	struct gpd_link *link;
 
-	if (genpd->status == GPD_STATE_ACTIVE)
+	if (genpd_status_on(genpd))
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
@@ -1329,8 +1340,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 	genpd_lock(subdomain);
 	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
-	if (genpd->status == GPD_STATE_POWER_OFF
-	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
+	if (!genpd_status_on(genpd) && genpd_status_on(subdomain)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1346,7 +1356,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 	list_add_tail(&link->master_node, &genpd->master_links);
 	link->slave = subdomain;
 	list_add_tail(&link->slave_node, &subdomain->slave_links);
-	if (subdomain->status != GPD_STATE_POWER_OFF)
+	if (genpd_status_on(subdomain))
 		genpd_sd_counter_inc(genpd);
 
  out:
@@ -1406,7 +1416,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 		list_del(&link->master_node);
 		list_del(&link->slave_node);
 		kfree(link);
-		if (subdomain->status != GPD_STATE_POWER_OFF)
+		if (genpd_status_on(subdomain))
 			genpd_sd_counter_dec(genpd);
 
 		ret = 0;
@@ -1492,6 +1502,10 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 		genpd->dev_ops.start = pm_clk_resume;
 	}
 
+	/* Always-on domains must be powered on at initialization. */
+	if (genpd_is_always_on(genpd) && !genpd_status_on(genpd))
+		return -EINVAL;
+
 	/* Use only one "off" state if there were no states declared */
 	if (genpd->state_count == 0) {
 		ret = genpd_set_default_power_state(genpd);
@@ -1700,12 +1714,12 @@ int of_genpd_add_provider_simple(struct device_node *np,
 
 	mutex_lock(&gpd_list_lock);
 
-	if (pm_genpd_present(genpd))
+	if (pm_genpd_present(genpd)) {
 		ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
-
-	if (!ret) {
-		genpd->provider = &np->fwnode;
-		genpd->has_provider = true;
+		if (!ret) {
+			genpd->provider = &np->fwnode;
+			genpd->has_provider = true;
+		}
 	}
 
 	mutex_unlock(&gpd_list_lock);
@@ -2079,11 +2093,6 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state,
 	int err;
 	u32 residency;
 	u32 entry_latency, exit_latency;
-	const struct of_device_id *match_id;
-
-	match_id = of_match_node(idle_state_match, state_node);
-	if (!match_id)
-		return -EINVAL;
 
 	err = of_property_read_u32(state_node, "entry-latency-us",
 						&entry_latency);
@@ -2132,6 +2141,7 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 	int err, ret;
 	int count;
 	struct of_phandle_iterator it;
+	const struct of_device_id *match_id;
 
 	count = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
 	if (count <= 0)
@@ -2144,6 +2154,9 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 	/* Loop over the phandles until all the requested entry is found */
 	of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) {
 		np = it.node;
+		match_id = of_match_node(idle_state_match, np);
+		if (!match_id)
+			continue;
 		ret = genpd_parse_state(&st[i++], np);
 		if (ret) {
 			pr_err
@@ -2155,8 +2168,11 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 		}
 	}
 
-	*n = count;
-	*states = st;
+	*n = i;
+	if (!i)
+		kfree(st);
+	else
+		*states = st;
 
 	return 0;
 }
@@ -2221,7 +2237,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
-	if (genpd->status == GPD_STATE_POWER_OFF)
+	if (!genpd_status_on(genpd))
 		snprintf(state, sizeof(state), "%s-%u",
 			 status_lookup[genpd->status], genpd->state_idx);
 	else
diff --git a/drivers/base/property.c b/drivers/base/property.c
index c458c63e353f..149de311a10e 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_graph.h>
 #include <linux/property.h>
 #include <linux/etherdevice.h>
 #include <linux/phy.h>
@@ -146,47 +147,45 @@ static int pset_prop_read_string_array(struct property_set *pset,
 				       const char *propname,
 				       const char **strings, size_t nval)
 {
+	const struct property_entry *prop;
 	const void *pointer;
-	size_t length = nval * sizeof(*strings);
+	size_t array_len, length;
+
+	/* Find out the array length. */
+	prop = pset_prop_get(pset, propname);
+	if (!prop)
+		return -EINVAL;
+
+	if (!prop->is_array)
+		/* The array length for a non-array string property is 1. */
+		array_len = 1;
+	else
+		/* Find the length of an array. */
+		array_len = pset_prop_count_elems_of_size(pset, propname,
+							  sizeof(const char *));
+
+	/* Return how many there are if strings is NULL. */
+	if (!strings)
+		return array_len;
+
+	array_len = min(nval, array_len);
+	length = array_len * sizeof(*strings);
 
 	pointer = pset_prop_find(pset, propname, length);
 	if (IS_ERR(pointer))
 		return PTR_ERR(pointer);
 
 	memcpy(strings, pointer, length);
-	return 0;
-}
 
-static int pset_prop_read_string(struct property_set *pset,
-				 const char *propname, const char **strings)
-{
-	const struct property_entry *prop;
-	const char * const *pointer;
-
-	prop = pset_prop_get(pset, propname);
-	if (!prop)
-		return -EINVAL;
-	if (!prop->is_string)
-		return -EILSEQ;
-	if (prop->is_array) {
-		pointer = prop->pointer.str;
-		if (!pointer)
-			return -ENODATA;
-	} else {
-		pointer = &prop->value.str;
-		if (*pointer && strnlen(*pointer, prop->length) >= prop->length)
-			return -EILSEQ;
-	}
-
-	*strings = *pointer;
-	return 0;
+	return array_len;
 }
 
-static inline struct fwnode_handle *dev_fwnode(struct device *dev)
+struct fwnode_handle *dev_fwnode(struct device *dev)
 {
 	return IS_ENABLED(CONFIG_OF) && dev->of_node ?
 		&dev->of_node->fwnode : dev->fwnode;
 }
+EXPORT_SYMBOL_GPL(dev_fwnode);
 
 /**
  * device_property_present - check if a property of a device is present
@@ -340,8 +339,8 @@ EXPORT_SYMBOL_GPL(device_property_read_u64_array);
  * Function reads an array of string properties with @propname from the device
  * firmware description and stores them to @val if found.
  *
- * Return: number of values if @val was %NULL,
- *         %0 if the property was found (success),
+ * Return: number of values read on success if @val is non-NULL,
+ *	   number of values available on success if @val is NULL,
  *	   %-EINVAL if given arguments are not valid,
  *	   %-ENODATA if the property does not have a value,
  *	   %-EPROTO or %-EILSEQ if the property is not an array of strings,
@@ -553,25 +552,8 @@ static int __fwnode_property_read_string_array(struct fwnode_handle *fwnode,
 		return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING,
 					   val, nval);
 	else if (is_pset_node(fwnode))
-		return val ?
-			pset_prop_read_string_array(to_pset_node(fwnode),
-						    propname, val, nval) :
-			pset_prop_count_elems_of_size(to_pset_node(fwnode),
-						      propname,
-						      sizeof(const char *));
-	return -ENXIO;
-}
-
-static int __fwnode_property_read_string(struct fwnode_handle *fwnode,
-					 const char *propname, const char **val)
-{
-	if (is_of_node(fwnode))
-		return of_property_read_string(to_of_node(fwnode), propname, val);
-	else if (is_acpi_node(fwnode))
-		return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING,
-					   val, 1);
-	else if (is_pset_node(fwnode))
-		return pset_prop_read_string(to_pset_node(fwnode), propname, val);
+		return pset_prop_read_string_array(to_pset_node(fwnode),
+						   propname, val, nval);
 	return -ENXIO;
 }
 
@@ -585,11 +567,11 @@ static int __fwnode_property_read_string(struct fwnode_handle *fwnode,
  * Read an string list property @propname from the given firmware node and store
  * them to @val if found.
  *
- * Return: number of values if @val was %NULL,
- *         %0 if the property was found (success),
+ * Return: number of values read on success if @val is non-NULL,
+ *	   number of values available on success if @val is NULL,
  *	   %-EINVAL if given arguments are not valid,
  *	   %-ENODATA if the property does not have a value,
- *	   %-EPROTO if the property is not an array of strings,
+ *	   %-EPROTO or %-EILSEQ if the property is not an array of strings,
  *	   %-EOVERFLOW if the size of the property is not as expected,
  *	   %-ENXIO if no suitable firmware interface is present.
  */
@@ -626,14 +608,9 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_string_array);
 int fwnode_property_read_string(struct fwnode_handle *fwnode,
 				const char *propname, const char **val)
 {
-	int ret;
+	int ret = fwnode_property_read_string_array(fwnode, propname, val, 1);
 
-	ret = __fwnode_property_read_string(fwnode, propname, val);
-	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
-	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = __fwnode_property_read_string(fwnode->secondary,
-						    propname, val);
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_string);
 
@@ -932,41 +909,109 @@ int device_add_properties(struct device *dev,
 EXPORT_SYMBOL_GPL(device_add_properties);
 
 /**
- * device_get_next_child_node - Return the next child node handle for a device
- * @dev: Device to find the next child node for.
- * @child: Handle to one of the device's child nodes or a null handle.
+ * fwnode_get_next_parent - Iterate to the node's parent
+ * @fwnode: Firmware whose parent is retrieved
+ *
+ * This is like fwnode_get_parent() except that it drops the refcount
+ * on the passed node, making it suitable for iterating through a
+ * node's parents.
+ *
+ * Returns a node pointer with refcount incremented, use
+ * fwnode_handle_node() on it when done.
  */
-struct fwnode_handle *device_get_next_child_node(struct device *dev,
+struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *parent = fwnode_get_parent(fwnode);
+
+	fwnode_handle_put(fwnode);
+
+	return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_next_parent);
+
+/**
+ * fwnode_get_parent - Return parent firwmare node
+ * @fwnode: Firmware whose parent is retrieved
+ *
+ * Return parent firmware node of the given node if possible or %NULL if no
+ * parent was available.
+ */
+struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *parent = NULL;
+
+	if (is_of_node(fwnode)) {
+		struct device_node *node;
+
+		node = of_get_parent(to_of_node(fwnode));
+		if (node)
+			parent = &node->fwnode;
+	} else if (is_acpi_node(fwnode)) {
+		parent = acpi_node_get_parent(fwnode);
+	}
+
+	return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_parent);
+
+/**
+ * fwnode_get_next_child_node - Return the next child node handle for a node
+ * @fwnode: Firmware node to find the next child node for.
+ * @child: Handle to one of the node's child nodes or a %NULL handle.
+ */
+struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode,
 						 struct fwnode_handle *child)
 {
-	if (IS_ENABLED(CONFIG_OF) && dev->of_node) {
+	if (is_of_node(fwnode)) {
 		struct device_node *node;
 
-		node = of_get_next_available_child(dev->of_node, to_of_node(child));
+		node = of_get_next_available_child(to_of_node(fwnode),
+						   to_of_node(child));
 		if (node)
 			return &node->fwnode;
-	} else if (IS_ENABLED(CONFIG_ACPI)) {
-		return acpi_get_next_subnode(dev, child);
+	} else if (is_acpi_node(fwnode)) {
+		return acpi_get_next_subnode(fwnode, child);
 	}
+
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(fwnode_get_next_child_node);
+
+/**
+ * device_get_next_child_node - Return the next child node handle for a device
+ * @dev: Device to find the next child node for.
+ * @child: Handle to one of the device's child nodes or a null handle.
+ */
+struct fwnode_handle *device_get_next_child_node(struct device *dev,
+						 struct fwnode_handle *child)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct fwnode_handle *fwnode = NULL;
+
+	if (dev->of_node)
+		fwnode = &dev->of_node->fwnode;
+	else if (adev)
+		fwnode = acpi_fwnode_handle(adev);
+
+	return fwnode_get_next_child_node(fwnode, child);
+}
 EXPORT_SYMBOL_GPL(device_get_next_child_node);
 
 /**
- * device_get_named_child_node - Return first matching named child node handle
- * @dev: Device to find the named child node for.
+ * fwnode_get_named_child_node - Return first matching named child node handle
+ * @fwnode: Firmware node to find the named child node for.
  * @childname: String to match child node name against.
  */
-struct fwnode_handle *device_get_named_child_node(struct device *dev,
+struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode,
 						  const char *childname)
 {
 	struct fwnode_handle *child;
 
 	/*
-	 * Find first matching named child node of this device.
+	 * Find first matching named child node of this fwnode.
 	 * For ACPI this will be a data only sub-node.
 	 */
-	device_for_each_child_node(dev, child) {
+	fwnode_for_each_child_node(fwnode, child) {
 		if (is_of_node(child)) {
 			if (!of_node_cmp(to_of_node(child)->name, childname))
 				return child;
@@ -978,9 +1023,32 @@ struct fwnode_handle *device_get_named_child_node(struct device *dev,
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(fwnode_get_named_child_node);
+
+/**
+ * device_get_named_child_node - Return first matching named child node handle
+ * @dev: Device to find the named child node for.
+ * @childname: String to match child node name against.
+ */
+struct fwnode_handle *device_get_named_child_node(struct device *dev,
+						  const char *childname)
+{
+	return fwnode_get_named_child_node(dev_fwnode(dev), childname);
+}
 EXPORT_SYMBOL_GPL(device_get_named_child_node);
 
 /**
+ * fwnode_handle_get - Obtain a reference to a device node
+ * @fwnode: Pointer to the device node to obtain the reference to.
+ */
+void fwnode_handle_get(struct fwnode_handle *fwnode)
+{
+	if (is_of_node(fwnode))
+		of_node_get(to_of_node(fwnode));
+}
+EXPORT_SYMBOL_GPL(fwnode_handle_get);
+
+/**
  * fwnode_handle_put - Drop reference to a device node
  * @fwnode: Pointer to the device node to drop the reference to.
  *
@@ -1117,3 +1185,157 @@ void *device_get_mac_address(struct device *dev, char *addr, int alen)
 	return device_get_mac_addr(dev, "address", addr, alen);
 }
 EXPORT_SYMBOL(device_get_mac_address);
+
+/**
+ * device_graph_get_next_endpoint - Get next endpoint firmware node
+ * @fwnode: Pointer to the parent firmware node
+ * @prev: Previous endpoint node or %NULL to get the first
+ *
+ * Returns an endpoint firmware node pointer or %NULL if no more endpoints
+ * are available.
+ */
+struct fwnode_handle *
+fwnode_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+			       struct fwnode_handle *prev)
+{
+	struct fwnode_handle *endpoint = NULL;
+
+	if (is_of_node(fwnode)) {
+		struct device_node *node;
+
+		node = of_graph_get_next_endpoint(to_of_node(fwnode),
+						  to_of_node(prev));
+
+		if (node)
+			endpoint = &node->fwnode;
+	} else if (is_acpi_node(fwnode)) {
+		endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
+		if (IS_ERR(endpoint))
+			endpoint = NULL;
+	}
+
+	return endpoint;
+
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
+
+/**
+ * fwnode_graph_get_remote_port_parent - Return fwnode of a remote device
+ * @fwnode: Endpoint firmware node pointing to the remote endpoint
+ *
+ * Extracts firmware node of a remote device the @fwnode points to.
+ */
+struct fwnode_handle *
+fwnode_graph_get_remote_port_parent(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *parent = NULL;
+
+	if (is_of_node(fwnode)) {
+		struct device_node *node;
+
+		node = of_graph_get_remote_port_parent(to_of_node(fwnode));
+		if (node)
+			parent = &node->fwnode;
+	} else if (is_acpi_node(fwnode)) {
+		int ret;
+
+		ret = acpi_graph_get_remote_endpoint(fwnode, &parent, NULL,
+						     NULL);
+		if (ret)
+			return NULL;
+	}
+
+	return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port_parent);
+
+/**
+ * fwnode_graph_get_remote_port - Return fwnode of a remote port
+ * @fwnode: Endpoint firmware node pointing to the remote endpoint
+ *
+ * Extracts firmware node of a remote port the @fwnode points to.
+ */
+struct fwnode_handle *fwnode_graph_get_remote_port(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *port = NULL;
+
+	if (is_of_node(fwnode)) {
+		struct device_node *node;
+
+		node = of_graph_get_remote_port(to_of_node(fwnode));
+		if (node)
+			port = &node->fwnode;
+	} else if (is_acpi_node(fwnode)) {
+		int ret;
+
+		ret = acpi_graph_get_remote_endpoint(fwnode, NULL, &port, NULL);
+		if (ret)
+			return NULL;
+	}
+
+	return port;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port);
+
+/**
+ * fwnode_graph_get_remote_endpoint - Return fwnode of a remote endpoint
+ * @fwnode: Endpoint firmware node pointing to the remote endpoint
+ *
+ * Extracts firmware node of a remote endpoint the @fwnode points to.
+ */
+struct fwnode_handle *
+fwnode_graph_get_remote_endpoint(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *endpoint = NULL;
+
+	if (is_of_node(fwnode)) {
+		struct device_node *node;
+
+		node = of_parse_phandle(to_of_node(fwnode), "remote-endpoint",
+					0);
+		if (node)
+			endpoint = &node->fwnode;
+	} else if (is_acpi_node(fwnode)) {
+		int ret;
+
+		ret = acpi_graph_get_remote_endpoint(fwnode, NULL, NULL,
+						     &endpoint);
+		if (ret)
+			return NULL;
+	}
+
+	return endpoint;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint);
+
+/**
+ * fwnode_graph_parse_endpoint - parse common endpoint node properties
+ * @fwnode: pointer to endpoint fwnode_handle
+ * @endpoint: pointer to the fwnode endpoint data structure
+ *
+ * Parse @fwnode representing a graph endpoint node and store the
+ * information in @endpoint. The caller must hold a reference to
+ * @fwnode.
+ */
+int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
+				struct fwnode_endpoint *endpoint)
+{
+	struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode);
+
+	memset(endpoint, 0, sizeof(*endpoint));
+
+	endpoint->local_fwnode = fwnode;
+
+	if (is_acpi_node(port_fwnode)) {
+		fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
+		fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
+	} else {
+		fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port);
+		fwnode_property_read_u32(fwnode, "reg", &endpoint->id);
+	}
+
+	fwnode_handle_put(port_fwnode);
+
+	return 0;
+}
+EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 771a2a253440..7bde8d7a2816 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -185,8 +185,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 	chip->owner		= THIS_MODULE;
 	chip->parent		= bcma_bus_get_host_dev(bus);
 #if IS_BUILTIN(CONFIG_OF)
-	if (cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC)
-		chip->of_node	= cc->core->dev.of_node;
+	chip->of_node		= cc->core->dev.of_node;
 #endif
 	switch (bus->chipinfo.id) {
 	case BCMA_CHIP_ID_BCM4707:
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 12da68ec48ba..e6986c7608f1 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -201,9 +201,6 @@ static void bcma_of_fill_device(struct device *parent,
 {
 	struct device_node *node;
 
-	if (!IS_ENABLED(CONFIG_OF_IRQ))
-		return;
-
 	node = bcma_of_find_child_device(parent, core);
 	if (node)
 		core->dev.of_node = node;
@@ -242,19 +239,18 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core)
 	core->dev.release = bcma_release_core_dev;
 	core->dev.bus = &bcma_bus_type;
 	dev_set_name(&core->dev, "bcma%d:%d", bus->num, core->core_index);
+	core->dev.parent = bcma_bus_get_host_dev(bus);
+	if (core->dev.parent)
+		bcma_of_fill_device(core->dev.parent, core);
 
 	switch (bus->hosttype) {
 	case BCMA_HOSTTYPE_PCI:
-		core->dev.parent = &bus->host_pci->dev;
 		core->dma_dev = &bus->host_pci->dev;
 		core->irq = bus->host_pci->irq;
 		break;
 	case BCMA_HOSTTYPE_SOC:
 		if (IS_ENABLED(CONFIG_OF) && bus->host_pdev) {
 			core->dma_dev = &bus->host_pdev->dev;
-			core->dev.parent = &bus->host_pdev->dev;
-			if (core->dev.parent)
-				bcma_of_fill_device(core->dev.parent, core);
 		} else {
 			core->dev.dma_mask = &core->dev.coherent_dma_mask;
 			core->dma_dev = &core->dev;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index f744de7a0f9b..19df4918e37e 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -312,22 +312,6 @@ config BLK_DEV_SKD
 
 	Use device /dev/skd$N amd /dev/skd$Np$M.
 
-config BLK_DEV_OSD
-	tristate "OSD object-as-blkdev support"
-	depends on SCSI_OSD_ULD
-	---help---
-	  Saying Y or M here will allow the exporting of a single SCSI
-	  OSD (object-based storage) object as a Linux block device.
-
-	  For example, if you create a 2G object on an OSD device,
-	  you can then use this module to present that 2G object as
-	  a Linux block device.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called osdblk.
-
-	  If unsure, say N.
-
 config BLK_DEV_SX8
 	tristate "Promise SATA SX8 support"
 	depends on PCI
@@ -434,23 +418,6 @@ config ATA_OVER_ETH
 	This driver provides Support for ATA over Ethernet block
 	devices like the Coraid EtherDrive (R) Storage Blade.
 
-config MG_DISK
-	tristate "mGine mflash, gflash support"
-	depends on ARM && GPIOLIB
-	help
-	  mGine mFlash(gFlash) block device driver
-
-config MG_DISK_RES
-	int "Size of reserved area before MBR"
-	depends on MG_DISK
-	default 0
-	help
-	  Define size of reserved area that usually used for boot. Unit is KB.
-	  All of the block device operation will be taken this value as start
-	  offset
-	  Examples:
-			1024 => 1 MB
-
 config SUNVDC
 	tristate "Sun Virtual Disk Client support"
 	depends on SUN_LDOMS
@@ -512,19 +479,7 @@ config VIRTIO_BLK_SCSI
 	  Enable support for SCSI passthrough (e.g. the SG_IO ioctl) on
 	  virtio-blk devices.  This is only supported for the legacy
 	  virtio protocol and not enabled by default by any hypervisor.
-	  Your probably want to virtio-scsi instead.
-
-config BLK_DEV_HD
-	bool "Very old hard disk (MFM/RLL/IDE) driver"
-	depends on HAVE_IDE
-	depends on !ARM || ARCH_RPC || BROKEN
-	help
-	  This is a very old hard disk driver that lacks the enhanced
-	  functionality of the newer ones.
-
-	  It is required for systems with ancient MFM/RLL/ESDI drives.
-
-	  If unsure, say N.
+	  You probably want to use virtio-scsi instead.
 
 config BLK_DEV_RBD
 	tristate "Rados block device (RBD)"
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 1e9661e26f29..ec8c36897b75 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -19,10 +19,8 @@ obj-$(CONFIG_BLK_CPQ_CISS_DA)  += cciss.o
 obj-$(CONFIG_BLK_DEV_DAC960)	+= DAC960.o
 obj-$(CONFIG_XILINX_SYSACE)	+= xsysace.o
 obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
-obj-$(CONFIG_MG_DISK)		+= mg_disk.o
 obj-$(CONFIG_SUNVDC)		+= sunvdc.o
 obj-$(CONFIG_BLK_DEV_SKD)	+= skd.o
-obj-$(CONFIG_BLK_DEV_OSD)	+= osdblk.o
 
 obj-$(CONFIG_BLK_DEV_UMEM)	+= umem.o
 obj-$(CONFIG_BLK_DEV_NBD)	+= nbd.o
@@ -30,7 +28,6 @@ obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o
 obj-$(CONFIG_VIRTIO_BLK)	+= virtio_blk.o
 
 obj-$(CONFIG_BLK_DEV_SX8)	+= sx8.o
-obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
 obj-$(CONFIG_XEN_BLKDEV_BACKEND)	+= xen-blkback/
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 2104b1b4ccda..fa69ecd52cb5 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -617,12 +617,12 @@ static void fd_error( void )
 	if (!fd_request)
 		return;
 
-	fd_request->errors++;
-	if (fd_request->errors >= MAX_ERRORS) {
+	fd_request->error_count++;
+	if (fd_request->error_count >= MAX_ERRORS) {
 		printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
 		fd_end_request_cur(-EIO);
 	}
-	else if (fd_request->errors == RECALIBRATE_ERRORS) {
+	else if (fd_request->error_count == RECALIBRATE_ERRORS) {
 		printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
 		if (SelectedDrive != -1)
 			SUD.track = -1;
@@ -1386,7 +1386,7 @@ static void setup_req_params( int drive )
 	ReqData = ReqBuffer + 512 * ReqCnt;
 
 	if (UseTrackbuffer)
-		read_track = (ReqCmd == READ && fd_request->errors == 0);
+		read_track = (ReqCmd == READ && fd_request->error_count == 0);
 	else
 		read_track = 0;
 
@@ -1409,8 +1409,10 @@ static struct request *set_next_request(void)
 			fdc_queue = 0;
 		if (q) {
 			rq = blk_fetch_request(q);
-			if (rq)
+			if (rq) {
+				rq->error_count = 0;
 				break;
+			}
 		}
 	} while (fdc_queue != old_pos);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 3adc32a3153b..4ec84d504780 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -134,28 +134,6 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
 	return page;
 }
 
-static void brd_free_page(struct brd_device *brd, sector_t sector)
-{
-	struct page *page;
-	pgoff_t idx;
-
-	spin_lock(&brd->brd_lock);
-	idx = sector >> PAGE_SECTORS_SHIFT;
-	page = radix_tree_delete(&brd->brd_pages, idx);
-	spin_unlock(&brd->brd_lock);
-	if (page)
-		__free_page(page);
-}
-
-static void brd_zero_page(struct brd_device *brd, sector_t sector)
-{
-	struct page *page;
-
-	page = brd_lookup_page(brd, sector);
-	if (page)
-		clear_highpage(page);
-}
-
 /*
  * Free all backing store pages and radix tree. This must only be called when
  * there are no other users of the device.
@@ -212,24 +190,6 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
 	return 0;
 }
 
-static void discard_from_brd(struct brd_device *brd,
-			sector_t sector, size_t n)
-{
-	while (n >= PAGE_SIZE) {
-		/*
-		 * Don't want to actually discard pages here because
-		 * re-allocating the pages can result in writeback
-		 * deadlocks under heavy load.
-		 */
-		if (0)
-			brd_free_page(brd, sector);
-		else
-			brd_zero_page(brd, sector);
-		sector += PAGE_SIZE >> SECTOR_SHIFT;
-		n -= PAGE_SIZE;
-	}
-}
-
 /*
  * Copy n bytes from src to the brd starting at sector. Does not sleep.
  */
@@ -338,14 +298,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
 		goto io_error;
 
-	if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
-		if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) ||
-		    bio->bi_iter.bi_size & ~PAGE_MASK)
-			goto io_error;
-		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
-		goto out;
-	}
-
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
@@ -357,7 +309,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		sector += len >> SECTOR_SHIFT;
 	}
 
-out:
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
 io_error:
@@ -464,11 +415,6 @@ static struct brd_device *brd_alloc(int i)
 	 *  is harmless)
 	 */
 	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
-
-	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
-	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
-	brd->brd_queue->limits.discard_zeroes_data = 1;
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 	queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
 #endif
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 8e1a4554951c..cd375503f7b0 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1864,8 +1864,7 @@ static void cciss_softirq_done(struct request *rq)
 	/* set the residual count for pc requests */
 	if (blk_rq_is_passthrough(rq))
 		scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
-
-	blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
+	blk_end_request_all(rq, scsi_req(rq)->result ? -EIO : 0);
 
 	spin_lock_irqsave(&h->lock, flags);
 	cmd_free(h, c);
@@ -3140,18 +3139,19 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 {
 	int retry_cmd = 0;
 	struct request *rq = cmd->rq;
+	struct scsi_request *sreq = scsi_req(rq);
 
-	rq->errors = 0;
+	sreq->result = 0;
 
 	if (timeout)
-		rq->errors = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
+		sreq->result = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
 
 	if (cmd->err_info->CommandStatus == 0)	/* no error has occurred */
 		goto after_error_processing;
 
 	switch (cmd->err_info->CommandStatus) {
 	case CMD_TARGET_STATUS:
-		rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
+		sreq->result = evaluate_target_status(h, cmd, &retry_cmd);
 		break;
 	case CMD_DATA_UNDERRUN:
 		if (!blk_rq_is_passthrough(cmd->rq)) {
@@ -3169,7 +3169,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_INVALID:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p is "
 		       "reported invalid\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3177,7 +3177,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_PROTOCOL_ERR:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p has "
 		       "protocol error\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3185,7 +3185,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_HARDWARE_ERR:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p had "
 		       " hardware error\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3193,7 +3193,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_CONNECTION_LOST:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p had "
 		       "connection lost\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3201,7 +3201,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_ABORTED:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p was "
 		       "aborted\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
@@ -3209,7 +3209,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_ABORT_FAILED:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p reports "
 		       "abort failed\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3224,21 +3224,21 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		} else
 			dev_warn(&h->pdev->dev,
 				"%p retried too many times\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
 		break;
 	case CMD_TIMEOUT:
 		dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_UNABORTABLE:
 		dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3247,7 +3247,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		dev_warn(&h->pdev->dev, "cmd %p returned "
 		       "unknown status %x\n", cmd,
 		       cmd->err_info->CommandStatus);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3380,9 +3380,9 @@ static void do_cciss_request(struct request_queue *q)
 		if (dma_mapping_error(&h->pdev->dev, temp64.val)) {
 			dev_warn(&h->pdev->dev,
 				"%s: error mapping page for DMA\n", __func__);
-			creq->errors = make_status_bytes(SAM_STAT_GOOD,
-							0, DRIVER_OK,
-							DID_SOFT_ERROR);
+			scsi_req(creq)->result =
+				make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+						  DID_SOFT_ERROR);
 			cmd_free(h, c);
 			return;
 		}
@@ -3395,9 +3395,9 @@ static void do_cciss_request(struct request_queue *q)
 		if (cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
 			(seg - (h->max_cmd_sgentries - 1)) *
 				sizeof(SGDescriptor_struct))) {
-			creq->errors = make_status_bytes(SAM_STAT_GOOD,
-							0, DRIVER_OK,
-							DID_SOFT_ERROR);
+			scsi_req(creq)->result =
+				make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+						  DID_SOFT_ERROR);
 			cmd_free(h, c);
 			return;
 		}
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index de5c3ee8a790..494837e59f23 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -236,9 +236,6 @@ static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_re
 	seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL");
 	seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
 	seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
-
-	if (f & EE_IS_TRIM)
-		__seq_print_rq_state_bit(m, f & EE_IS_TRIM_USE_ZEROOUT, &sep, "zero-out", "trim");
 	seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same");
 	seq_putc(m, '\n');
 }
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 724d1c50fc52..d5da45bb03a6 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -437,9 +437,6 @@ enum {
 
 	/* is this a TRIM aka REQ_DISCARD? */
 	__EE_IS_TRIM,
-	/* our lower level cannot handle trim,
-	 * and we want to fall back to zeroout instead */
-	__EE_IS_TRIM_USE_ZEROOUT,
 
 	/* In case a barrier failed,
 	 * we need to resubmit without the barrier flag. */
@@ -482,7 +479,6 @@ enum {
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
 #define EE_IS_TRIM             (1<<__EE_IS_TRIM)
-#define EE_IS_TRIM_USE_ZEROOUT (1<<__EE_IS_TRIM_USE_ZEROOUT)
 #define EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
 #define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)
@@ -1561,8 +1557,6 @@ extern void start_resync_timer_fn(unsigned long data);
 extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
 
 /* drbd_receiver.c */
-extern int drbd_issue_discard_or_zero_out(struct drbd_device *device,
-		sector_t start, unsigned int nr_sectors, bool discard);
 extern int drbd_receiver(struct drbd_thread *thi);
 extern int drbd_ack_receiver(struct drbd_thread *thi);
 extern void drbd_send_ping_wf(struct work_struct *ws);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 92c60cbd04ee..84455c365f57 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -931,7 +931,6 @@ void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct r
 		p->qlim->io_min = cpu_to_be32(queue_io_min(q));
 		p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
 		p->qlim->discard_enabled = blk_queue_discard(q);
-		p->qlim->discard_zeroes_data = queue_discard_zeroes_data(q);
 		p->qlim->write_same_capable = !!q->limits.max_write_same_sectors;
 	} else {
 		q = device->rq_queue;
@@ -941,7 +940,6 @@ void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct r
 		p->qlim->io_min = cpu_to_be32(queue_io_min(q));
 		p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
 		p->qlim->discard_enabled = 0;
-		p->qlim->discard_zeroes_data = 0;
 		p->qlim->write_same_capable = 0;
 	}
 }
@@ -1668,7 +1666,8 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection,
 			(bio->bi_opf & REQ_FUA ? DP_FUA : 0) |
 			(bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) |
 			(bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) |
-			(bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0);
+			(bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0) |
+			(bio_op(bio) == REQ_OP_WRITE_ZEROES ? DP_DISCARD : 0);
 	else
 		return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0;
 }
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 908c704e20aa..02255a0d68b9 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1199,10 +1199,6 @@ static void decide_on_discard_support(struct drbd_device *device,
 	struct drbd_connection *connection = first_peer_device(device)->connection;
 	bool can_do = b ? blk_queue_discard(b) : true;
 
-	if (can_do && b && !b->limits.discard_zeroes_data && !discard_zeroes_if_aligned) {
-		can_do = false;
-		drbd_info(device, "discard_zeroes_data=0 and discard_zeroes_if_aligned=no: disabling discards\n");
-	}
 	if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) {
 		can_do = false;
 		drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n");
@@ -1217,10 +1213,12 @@ static void decide_on_discard_support(struct drbd_device *device,
 		blk_queue_discard_granularity(q, 512);
 		q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+		q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection);
 	} else {
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		blk_queue_discard_granularity(q, 0);
 		q->limits.max_discard_sectors = 0;
+		q->limits.max_write_zeroes_sectors = 0;
 	}
 }
 
@@ -1482,8 +1480,7 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 	if (disk_conf->al_extents > drbd_al_extents_max(nbc))
 		disk_conf->al_extents = drbd_al_extents_max(nbc);
 
-	if (!blk_queue_discard(q)
-	    || (!q->limits.discard_zeroes_data && !disk_conf->discard_zeroes_if_aligned)) {
+	if (!blk_queue_discard(q)) {
 		if (disk_conf->rs_discard_granularity) {
 			disk_conf->rs_discard_granularity = 0; /* disable feature */
 			drbd_info(device, "rs_discard_granularity feature disabled\n");
diff --git a/drivers/block/drbd/drbd_nla.c b/drivers/block/drbd/drbd_nla.c
index b2d4791498a6..6bf806df60dc 100644
--- a/drivers/block/drbd/drbd_nla.c
+++ b/drivers/block/drbd/drbd_nla.c
@@ -34,7 +34,7 @@ int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 
 	err = drbd_nla_check_mandatory(maxtype, nla);
 	if (!err)
-		err = nla_parse_nested(tb, maxtype, nla, policy);
+		err = nla_parse_nested(tb, maxtype, nla, policy, NULL);
 
 	return err;
 }
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index aa6bf9692eff..1b0a2be24f39 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1448,105 +1448,14 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 		drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]);
 }
 
-/*
- * We *may* ignore the discard-zeroes-data setting, if so configured.
- *
- * Assumption is that it "discard_zeroes_data=0" is only because the backend
- * may ignore partial unaligned discards.
- *
- * LVM/DM thin as of at least
- *   LVM version:     2.02.115(2)-RHEL7 (2015-01-28)
- *   Library version: 1.02.93-RHEL7 (2015-01-28)
- *   Driver version:  4.29.0
- * still behaves this way.
- *
- * For unaligned (wrt. alignment and granularity) or too small discards,
- * we zero-out the initial (and/or) trailing unaligned partial chunks,
- * but discard all the aligned full chunks.
- *
- * At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1".
- */
-int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, bool discard)
-{
-	struct block_device *bdev = device->ldev->backing_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t tmp, nr;
-	unsigned int max_discard_sectors, granularity;
-	int alignment;
-	int err = 0;
-
-	if (!discard)
-		goto zero_out;
-
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
-	max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22));
-	max_discard_sectors -= max_discard_sectors % granularity;
-	if (unlikely(!max_discard_sectors))
-		goto zero_out;
-
-	if (nr_sectors < granularity)
-		goto zero_out;
-
-	tmp = start;
-	if (sector_div(tmp, granularity) != alignment) {
-		if (nr_sectors < 2*granularity)
-			goto zero_out;
-		/* start + gran - (start + gran - align) % gran */
-		tmp = start + granularity - alignment;
-		tmp = start + granularity - sector_div(tmp, granularity);
-
-		nr = tmp - start;
-		err |= blkdev_issue_zeroout(bdev, start, nr, GFP_NOIO, 0);
-		nr_sectors -= nr;
-		start = tmp;
-	}
-	while (nr_sectors >= granularity) {
-		nr = min_t(sector_t, nr_sectors, max_discard_sectors);
-		err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
-		nr_sectors -= nr;
-		start += nr;
-	}
- zero_out:
-	if (nr_sectors) {
-		err |= blkdev_issue_zeroout(bdev, start, nr_sectors, GFP_NOIO, 0);
-	}
-	return err != 0;
-}
-
-static bool can_do_reliable_discards(struct drbd_device *device)
-{
-	struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
-	struct disk_conf *dc;
-	bool can_do;
-
-	if (!blk_queue_discard(q))
-		return false;
-
-	if (q->limits.discard_zeroes_data)
-		return true;
-
-	rcu_read_lock();
-	dc = rcu_dereference(device->ldev->disk_conf);
-	can_do = dc->discard_zeroes_if_aligned;
-	rcu_read_unlock();
-	return can_do;
-}
-
 static void drbd_issue_peer_discard(struct drbd_device *device, struct drbd_peer_request *peer_req)
 {
-	/* If the backend cannot discard, or does not guarantee
-	 * read-back zeroes in discarded ranges, we fall back to
-	 * zero-out.  Unless configuration specifically requested
-	 * otherwise. */
-	if (!can_do_reliable_discards(device))
-		peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
+	struct block_device *bdev = device->ldev->backing_bdev;
 
-	if (drbd_issue_discard_or_zero_out(device, peer_req->i.sector,
-	    peer_req->i.size >> 9, !(peer_req->flags & EE_IS_TRIM_USE_ZEROOUT)))
+	if (blkdev_issue_zeroout(bdev, peer_req->i.sector, peer_req->i.size >> 9,
+			GFP_NOIO, 0))
 		peer_req->flags |= EE_WAS_ERROR;
+
 	drbd_endio_write_sec_final(peer_req);
 }
 
@@ -2376,7 +2285,7 @@ static unsigned long wire_flags_to_bio_flags(u32 dpf)
 static unsigned long wire_flags_to_bio_op(u32 dpf)
 {
 	if (dpf & DP_DISCARD)
-		return REQ_OP_DISCARD;
+		return REQ_OP_WRITE_ZEROES;
 	else
 		return REQ_OP_WRITE;
 }
@@ -2567,7 +2476,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 	op_flags = wire_flags_to_bio_flags(dp_flags);
 	if (pi->cmd == P_TRIM) {
 		D_ASSERT(peer_device, peer_req->i.size > 0);
-		D_ASSERT(peer_device, op == REQ_OP_DISCARD);
+		D_ASSERT(peer_device, op == REQ_OP_WRITE_ZEROES);
 		D_ASSERT(peer_device, peer_req->pages == NULL);
 	} else if (peer_req->pages == NULL) {
 		D_ASSERT(device, peer_req->i.size == 0);
@@ -4880,7 +4789,7 @@ static int receive_rs_deallocated(struct drbd_connection *connection, struct pac
 
 	if (get_ldev(device)) {
 		struct drbd_peer_request *peer_req;
-		const int op = REQ_OP_DISCARD;
+		const int op = REQ_OP_WRITE_ZEROES;
 
 		peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER, sector,
 					       size, 0, GFP_NOIO);
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 652114ae1a8a..b5730e17b455 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -59,6 +59,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
 	drbd_req_make_private_bio(req, bio_src);
 	req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
 		      | (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
+		      | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_UNMAP : 0)
 		      | (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
 	req->device = device;
 	req->master_bio = bio_src;
@@ -1148,10 +1149,10 @@ static int drbd_process_write_request(struct drbd_request *req)
 
 static void drbd_process_discard_req(struct drbd_request *req)
 {
-	int err = drbd_issue_discard_or_zero_out(req->device,
-				req->i.sector, req->i.size >> 9, true);
+	struct block_device *bdev = req->device->ldev->backing_bdev;
 
-	if (err)
+	if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
+			GFP_NOIO, 0))
 		req->private_bio->bi_error = -EIO;
 	bio_endio(req->private_bio);
 }
@@ -1180,7 +1181,8 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 	if (get_ldev(device)) {
 		if (drbd_insert_fault(device, type))
 			bio_io_error(bio);
-		else if (bio_op(bio) == REQ_OP_DISCARD)
+		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+			 bio_op(bio) == REQ_OP_DISCARD)
 			drbd_process_discard_req(req);
 		else
 			generic_make_request(bio);
@@ -1234,7 +1236,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 	_drbd_start_io_acct(device, req);
 
 	/* process discards always from our submitter thread */
-	if (bio_op(bio) & REQ_OP_DISCARD)
+	if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
+	    (bio_op(bio) & REQ_OP_DISCARD))
 		goto queue_for_submitter_thread;
 
 	if (rw == WRITE && req->private_bio && req->i.size
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 3bff33f21435..1afcb4e02d8d 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -174,7 +174,8 @@ void drbd_peer_request_endio(struct bio *bio)
 	struct drbd_peer_request *peer_req = bio->bi_private;
 	struct drbd_device *device = peer_req->peer_device->device;
 	bool is_write = bio_data_dir(bio) == WRITE;
-	bool is_discard = !!(bio_op(bio) == REQ_OP_DISCARD);
+	bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+			  bio_op(bio) == REQ_OP_DISCARD;
 
 	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
@@ -249,6 +250,7 @@ void drbd_request_endio(struct bio *bio)
 	/* to avoid recursion in __req_mod */
 	if (unlikely(bio->bi_error)) {
 		switch (bio_op(bio)) {
+		case REQ_OP_WRITE_ZEROES:
 		case REQ_OP_DISCARD:
 			if (bio->bi_error == -EOPNOTSUPP)
 				what = DISCARD_COMPLETED_NOTSUPP;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 45b4384f650c..60d4c7653178 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2805,8 +2805,10 @@ static int set_next_request(void)
 			fdc_queue = 0;
 		if (q) {
 			current_req = blk_fetch_request(q);
-			if (current_req)
+			if (current_req) {
+				current_req->error_count = 0;
 				break;
+			}
 		}
 	} while (fdc_queue != old_pos);
 
@@ -2866,7 +2868,7 @@ do_request:
 		_floppy = floppy_type + DP->autodetect[DRS->probed_format];
 	} else
 		probing = 0;
-	errors = &(current_req->errors);
+	errors = &(current_req->error_count);
 	tmp = make_raw_rw_request();
 	if (tmp < 2) {
 		request_done(tmp);
@@ -4207,9 +4209,7 @@ static int __init do_floppy_init(void)
 		disks[drive]->fops = &floppy_fops;
 		sprintf(disks[drive]->disk_name, "fd%d", drive);
 
-		init_timer(&motor_off_timer[drive]);
-		motor_off_timer[drive].data = drive;
-		motor_off_timer[drive].function = motor_off_callback;
+		setup_timer(&motor_off_timer[drive], motor_off_callback, drive);
 	}
 
 	err = register_blkdev(FLOPPY_MAJOR, "fd");
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
deleted file mode 100644
index 6043648da1e8..000000000000
--- a/drivers/block/hd.c
+++ /dev/null
@@ -1,803 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *
- * This is the low-level hd interrupt support. It traverses the
- * request-list, using interrupts to jump between functions. As
- * all the functions are called within interrupts, we may not
- * sleep. Special care is recommended.
- *
- *  modified by Drew Eckhardt to check nr of hd's from the CMOS.
- *
- *  Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug
- *  in the early extended-partition checks and added DM partitions
- *
- *  IRQ-unmask, drive-id, multiple-mode, support for ">16 heads",
- *  and general streamlining by Mark Lord.
- *
- *  Removed 99% of above. Use Mark's ide driver for those options.
- *  This is now a lightweight ST-506 driver. (Paul Gortmaker)
- *
- *  Modified 1995 Russell King for ARM processor.
- *
- *  Bugfix: max_sectors must be <= 255 or the wheels tend to come
- *  off in a hurry once you queue things up - Paul G. 02/2001
- */
-
-/* Uncomment the following if you want verbose error reports. */
-/* #define VERBOSE_ERRORS */
-
-#include <linux/blkdev.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/interrupt.h>
-#include <linux/timer.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/genhd.h>
-#include <linux/string.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/blkpg.h>
-#include <linux/ata.h>
-#include <linux/hdreg.h>
-
-#define HD_IRQ 14
-
-#define REALLY_SLOW_IO
-#include <asm/io.h>
-#include <linux/uaccess.h>
-
-#ifdef __arm__
-#undef  HD_IRQ
-#endif
-#include <asm/irq.h>
-#ifdef __arm__
-#define HD_IRQ IRQ_HARDDISK
-#endif
-
-/* Hd controller regster ports */
-
-#define HD_DATA		0x1f0		/* _CTL when writing */
-#define HD_ERROR	0x1f1		/* see err-bits */
-#define HD_NSECTOR	0x1f2		/* nr of sectors to read/write */
-#define HD_SECTOR	0x1f3		/* starting sector */
-#define HD_LCYL		0x1f4		/* starting cylinder */
-#define HD_HCYL		0x1f5		/* high byte of starting cyl */
-#define HD_CURRENT	0x1f6		/* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS	0x1f7		/* see status-bits */
-#define HD_FEATURE	HD_ERROR	/* same io address, read=error, write=feature */
-#define HD_PRECOMP	HD_FEATURE	/* obsolete use of this port - predates IDE */
-#define HD_COMMAND	HD_STATUS	/* same io address, read=status, write=cmd */
-
-#define HD_CMD		0x3f6		/* used for resets */
-#define HD_ALTSTATUS	0x3f6		/* same as HD_STATUS but doesn't clear irq */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT		0x01
-#define INDEX_STAT		0x02
-#define ECC_STAT		0x04	/* Corrected error */
-#define DRQ_STAT		0x08
-#define SEEK_STAT		0x10
-#define SERVICE_STAT		SEEK_STAT
-#define WRERR_STAT		0x20
-#define READY_STAT		0x40
-#define BUSY_STAT		0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR		0x01	/* Bad address mark */
-#define TRK0_ERR		0x02	/* couldn't find track 0 */
-#define ABRT_ERR		0x04	/* Command aborted */
-#define MCR_ERR			0x08	/* media change request */
-#define ID_ERR			0x10	/* ID field not found */
-#define MC_ERR			0x20	/* media changed */
-#define ECC_ERR			0x40	/* Uncorrectable ECC error */
-#define BBD_ERR			0x80	/* pre-EIDE meaning:  block marked bad */
-#define ICRC_ERR		0x80	/* new meaning:  CRC error during transfer */
-
-static DEFINE_SPINLOCK(hd_lock);
-static struct request_queue *hd_queue;
-static struct request *hd_req;
-
-#define TIMEOUT_VALUE	(6*HZ)
-#define	HD_DELAY	0
-
-#define MAX_ERRORS     16	/* Max read/write errors/sector */
-#define RESET_FREQ      8	/* Reset controller every 8th retry */
-#define RECAL_FREQ      4	/* Recalibrate every 4th retry */
-#define MAX_HD		2
-
-#define STAT_OK		(READY_STAT|SEEK_STAT)
-#define OK_STATUS(s)	(((s)&(STAT_OK|(BUSY_STAT|WRERR_STAT|ERR_STAT)))==STAT_OK)
-
-static void recal_intr(void);
-static void bad_rw_intr(void);
-
-static int reset;
-static int hd_error;
-
-/*
- *  This struct defines the HD's and their types.
- */
-struct hd_i_struct {
-	unsigned int head, sect, cyl, wpcom, lzone, ctl;
-	int unit;
-	int recalibrate;
-	int special_op;
-};
-
-#ifdef HD_TYPE
-static struct hd_i_struct hd_info[] = { HD_TYPE };
-static int NR_HD = ARRAY_SIZE(hd_info);
-#else
-static struct hd_i_struct hd_info[MAX_HD];
-static int NR_HD;
-#endif
-
-static struct gendisk *hd_gendisk[MAX_HD];
-
-static struct timer_list device_timer;
-
-#define TIMEOUT_VALUE (6*HZ)
-
-#define SET_TIMER							\
-	do {								\
-		mod_timer(&device_timer, jiffies + TIMEOUT_VALUE);	\
-	} while (0)
-
-static void (*do_hd)(void) = NULL;
-#define SET_HANDLER(x) \
-if ((do_hd = (x)) != NULL) \
-	SET_TIMER; \
-else \
-	del_timer(&device_timer);
-
-
-#if (HD_DELAY > 0)
-
-#include <linux/i8253.h>
-
-unsigned long last_req;
-
-unsigned long read_timer(void)
-{
-	unsigned long t, flags;
-	int i;
-
-	raw_spin_lock_irqsave(&i8253_lock, flags);
-	t = jiffies * 11932;
-	outb_p(0, 0x43);
-	i = inb_p(0x40);
-	i |= inb(0x40) << 8;
-	raw_spin_unlock_irqrestore(&i8253_lock, flags);
-	return(t - i);
-}
-#endif
-
-static void __init hd_setup(char *str, int *ints)
-{
-	int hdind = 0;
-
-	if (ints[0] != 3)
-		return;
-	if (hd_info[0].head != 0)
-		hdind = 1;
-	hd_info[hdind].head = ints[2];
-	hd_info[hdind].sect = ints[3];
-	hd_info[hdind].cyl = ints[1];
-	hd_info[hdind].wpcom = 0;
-	hd_info[hdind].lzone = ints[1];
-	hd_info[hdind].ctl = (ints[2] > 8 ? 8 : 0);
-	NR_HD = hdind+1;
-}
-
-static bool hd_end_request(int err, unsigned int bytes)
-{
-	if (__blk_end_request(hd_req, err, bytes))
-		return true;
-	hd_req = NULL;
-	return false;
-}
-
-static bool hd_end_request_cur(int err)
-{
-	return hd_end_request(err, blk_rq_cur_bytes(hd_req));
-}
-
-static void dump_status(const char *msg, unsigned int stat)
-{
-	char *name = "hd?";
-	if (hd_req)
-		name = hd_req->rq_disk->disk_name;
-
-#ifdef VERBOSE_ERRORS
-	printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
-	if (stat & BUSY_STAT)	printk("Busy ");
-	if (stat & READY_STAT)	printk("DriveReady ");
-	if (stat & WRERR_STAT)	printk("WriteFault ");
-	if (stat & SEEK_STAT)	printk("SeekComplete ");
-	if (stat & DRQ_STAT)	printk("DataRequest ");
-	if (stat & ECC_STAT)	printk("CorrectedError ");
-	if (stat & INDEX_STAT)	printk("Index ");
-	if (stat & ERR_STAT)	printk("Error ");
-	printk("}\n");
-	if ((stat & ERR_STAT) == 0) {
-		hd_error = 0;
-	} else {
-		hd_error = inb(HD_ERROR);
-		printk("%s: %s: error=0x%02x { ", name, msg, hd_error & 0xff);
-		if (hd_error & BBD_ERR)		printk("BadSector ");
-		if (hd_error & ECC_ERR)		printk("UncorrectableError ");
-		if (hd_error & ID_ERR)		printk("SectorIdNotFound ");
-		if (hd_error & ABRT_ERR)	printk("DriveStatusError ");
-		if (hd_error & TRK0_ERR)	printk("TrackZeroNotFound ");
-		if (hd_error & MARK_ERR)	printk("AddrMarkNotFound ");
-		printk("}");
-		if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
-			printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
-				inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
-			if (hd_req)
-				printk(", sector=%ld", blk_rq_pos(hd_req));
-		}
-		printk("\n");
-	}
-#else
-	printk("%s: %s: status=0x%02x.\n", name, msg, stat & 0xff);
-	if ((stat & ERR_STAT) == 0) {
-		hd_error = 0;
-	} else {
-		hd_error = inb(HD_ERROR);
-		printk("%s: %s: error=0x%02x.\n", name, msg, hd_error & 0xff);
-	}
-#endif
-}
-
-static void check_status(void)
-{
-	int i = inb_p(HD_STATUS);
-
-	if (!OK_STATUS(i)) {
-		dump_status("check_status", i);
-		bad_rw_intr();
-	}
-}
-
-static int controller_busy(void)
-{
-	int retries = 100000;
-	unsigned char status;
-
-	do {
-		status = inb_p(HD_STATUS);
-	} while ((status & BUSY_STAT) && --retries);
-	return status;
-}
-
-static int status_ok(void)
-{
-	unsigned char status = inb_p(HD_STATUS);
-
-	if (status & BUSY_STAT)
-		return 1;	/* Ancient, but does it make sense??? */
-	if (status & WRERR_STAT)
-		return 0;
-	if (!(status & READY_STAT))
-		return 0;
-	if (!(status & SEEK_STAT))
-		return 0;
-	return 1;
-}
-
-static int controller_ready(unsigned int drive, unsigned int head)
-{
-	int retry = 100;
-
-	do {
-		if (controller_busy() & BUSY_STAT)
-			return 0;
-		outb_p(0xA0 | (drive<<4) | head, HD_CURRENT);
-		if (status_ok())
-			return 1;
-	} while (--retry);
-	return 0;
-}
-
-static void hd_out(struct hd_i_struct *disk,
-		   unsigned int nsect,
-		   unsigned int sect,
-		   unsigned int head,
-		   unsigned int cyl,
-		   unsigned int cmd,
-		   void (*intr_addr)(void))
-{
-	unsigned short port;
-
-#if (HD_DELAY > 0)
-	while (read_timer() - last_req < HD_DELAY)
-		/* nothing */;
-#endif
-	if (reset)
-		return;
-	if (!controller_ready(disk->unit, head)) {
-		reset = 1;
-		return;
-	}
-	SET_HANDLER(intr_addr);
-	outb_p(disk->ctl, HD_CMD);
-	port = HD_DATA;
-	outb_p(disk->wpcom >> 2, ++port);
-	outb_p(nsect, ++port);
-	outb_p(sect, ++port);
-	outb_p(cyl, ++port);
-	outb_p(cyl >> 8, ++port);
-	outb_p(0xA0 | (disk->unit << 4) | head, ++port);
-	outb_p(cmd, ++port);
-}
-
-static void hd_request (void);
-
-static int drive_busy(void)
-{
-	unsigned int i;
-	unsigned char c;
-
-	for (i = 0; i < 500000 ; i++) {
-		c = inb_p(HD_STATUS);
-		if ((c & (BUSY_STAT | READY_STAT | SEEK_STAT)) == STAT_OK)
-			return 0;
-	}
-	dump_status("reset timed out", c);
-	return 1;
-}
-
-static void reset_controller(void)
-{
-	int	i;
-
-	outb_p(4, HD_CMD);
-	for (i = 0; i < 1000; i++) barrier();
-	outb_p(hd_info[0].ctl & 0x0f, HD_CMD);
-	for (i = 0; i < 1000; i++) barrier();
-	if (drive_busy())
-		printk("hd: controller still busy\n");
-	else if ((hd_error = inb(HD_ERROR)) != 1)
-		printk("hd: controller reset failed: %02x\n", hd_error);
-}
-
-static void reset_hd(void)
-{
-	static int i;
-
-repeat:
-	if (reset) {
-		reset = 0;
-		i = -1;
-		reset_controller();
-	} else {
-		check_status();
-		if (reset)
-			goto repeat;
-	}
-	if (++i < NR_HD) {
-		struct hd_i_struct *disk = &hd_info[i];
-		disk->special_op = disk->recalibrate = 1;
-		hd_out(disk, disk->sect, disk->sect, disk->head-1,
-			disk->cyl, ATA_CMD_INIT_DEV_PARAMS, &reset_hd);
-		if (reset)
-			goto repeat;
-	} else
-		hd_request();
-}
-
-/*
- * Ok, don't know what to do with the unexpected interrupts: on some machines
- * doing a reset and a retry seems to result in an eternal loop. Right now I
- * ignore it, and just set the timeout.
- *
- * On laptops (and "green" PCs), an unexpected interrupt occurs whenever the
- * drive enters "idle", "standby", or "sleep" mode, so if the status looks
- * "good", we just ignore the interrupt completely.
- */
-static void unexpected_hd_interrupt(void)
-{
-	unsigned int stat = inb_p(HD_STATUS);
-
-	if (stat & (BUSY_STAT|DRQ_STAT|ECC_STAT|ERR_STAT)) {
-		dump_status("unexpected interrupt", stat);
-		SET_TIMER;
-	}
-}
-
-/*
- * bad_rw_intr() now tries to be a bit smarter and does things
- * according to the error returned by the controller.
- * -Mika Liljeberg (liljeber@cs.Helsinki.FI)
- */
-static void bad_rw_intr(void)
-{
-	struct request *req = hd_req;
-
-	if (req != NULL) {
-		struct hd_i_struct *disk = req->rq_disk->private_data;
-		if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
-			hd_end_request_cur(-EIO);
-			disk->special_op = disk->recalibrate = 1;
-		} else if (req->errors % RESET_FREQ == 0)
-			reset = 1;
-		else if ((hd_error & TRK0_ERR) || req->errors % RECAL_FREQ == 0)
-			disk->special_op = disk->recalibrate = 1;
-		/* Otherwise just retry */
-	}
-}
-
-static inline int wait_DRQ(void)
-{
-	int retries;
-	int stat;
-
-	for (retries = 0; retries < 100000; retries++) {
-		stat = inb_p(HD_STATUS);
-		if (stat & DRQ_STAT)
-			return 0;
-	}
-	dump_status("wait_DRQ", stat);
-	return -1;
-}
-
-static void read_intr(void)
-{
-	struct request *req;
-	int i, retries = 100000;
-
-	do {
-		i = (unsigned) inb_p(HD_STATUS);
-		if (i & BUSY_STAT)
-			continue;
-		if (!OK_STATUS(i))
-			break;
-		if (i & DRQ_STAT)
-			goto ok_to_read;
-	} while (--retries > 0);
-	dump_status("read_intr", i);
-	bad_rw_intr();
-	hd_request();
-	return;
-
-ok_to_read:
-	req = hd_req;
-	insw(HD_DATA, bio_data(req->bio), 256);
-#ifdef DEBUG
-	printk("%s: read: sector %ld, remaining = %u, buffer=%p\n",
-	       req->rq_disk->disk_name, blk_rq_pos(req) + 1,
-	       blk_rq_sectors(req) - 1, bio_data(req->bio)+512);
-#endif
-	if (hd_end_request(0, 512)) {
-		SET_HANDLER(&read_intr);
-		return;
-	}
-
-	(void) inb_p(HD_STATUS);
-#if (HD_DELAY > 0)
-	last_req = read_timer();
-#endif
-	hd_request();
-}
-
-static void write_intr(void)
-{
-	struct request *req = hd_req;
-	int i;
-	int retries = 100000;
-
-	do {
-		i = (unsigned) inb_p(HD_STATUS);
-		if (i & BUSY_STAT)
-			continue;
-		if (!OK_STATUS(i))
-			break;
-		if ((blk_rq_sectors(req) <= 1) || (i & DRQ_STAT))
-			goto ok_to_write;
-	} while (--retries > 0);
-	dump_status("write_intr", i);
-	bad_rw_intr();
-	hd_request();
-	return;
-
-ok_to_write:
-	if (hd_end_request(0, 512)) {
-		SET_HANDLER(&write_intr);
-		outsw(HD_DATA, bio_data(req->bio), 256);
-		return;
-	}
-
-#if (HD_DELAY > 0)
-	last_req = read_timer();
-#endif
-	hd_request();
-}
-
-static void recal_intr(void)
-{
-	check_status();
-#if (HD_DELAY > 0)
-	last_req = read_timer();
-#endif
-	hd_request();
-}
-
-/*
- * This is another of the error-routines I don't know what to do with. The
- * best idea seems to just set reset, and start all over again.
- */
-static void hd_times_out(unsigned long dummy)
-{
-	char *name;
-
-	do_hd = NULL;
-
-	if (!hd_req)
-		return;
-
-	spin_lock_irq(hd_queue->queue_lock);
-	reset = 1;
-	name = hd_req->rq_disk->disk_name;
-	printk("%s: timeout\n", name);
-	if (++hd_req->errors >= MAX_ERRORS) {
-#ifdef DEBUG
-		printk("%s: too many errors\n", name);
-#endif
-		hd_end_request_cur(-EIO);
-	}
-	hd_request();
-	spin_unlock_irq(hd_queue->queue_lock);
-}
-
-static int do_special_op(struct hd_i_struct *disk, struct request *req)
-{
-	if (disk->recalibrate) {
-		disk->recalibrate = 0;
-		hd_out(disk, disk->sect, 0, 0, 0, ATA_CMD_RESTORE, &recal_intr);
-		return reset;
-	}
-	if (disk->head > 16) {
-		printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
-		hd_end_request_cur(-EIO);
-	}
-	disk->special_op = 0;
-	return 1;
-}
-
-/*
- * The driver enables interrupts as much as possible.  In order to do this,
- * (a) the device-interrupt is disabled before entering hd_request(),
- * and (b) the timeout-interrupt is disabled before the sti().
- *
- * Interrupts are still masked (by default) whenever we are exchanging
- * data/cmds with a drive, because some drives seem to have very poor
- * tolerance for latency during I/O. The IDE driver has support to unmask
- * interrupts for non-broken hardware, so use that driver if required.
- */
-static void hd_request(void)
-{
-	unsigned int block, nsect, sec, track, head, cyl;
-	struct hd_i_struct *disk;
-	struct request *req;
-
-	if (do_hd)
-		return;
-repeat:
-	del_timer(&device_timer);
-
-	if (!hd_req) {
-		hd_req = blk_fetch_request(hd_queue);
-		if (!hd_req) {
-			do_hd = NULL;
-			return;
-		}
-	}
-	req = hd_req;
-
-	if (reset) {
-		reset_hd();
-		return;
-	}
-	disk = req->rq_disk->private_data;
-	block = blk_rq_pos(req);
-	nsect = blk_rq_sectors(req);
-	if (block >= get_capacity(req->rq_disk) ||
-	    ((block+nsect) > get_capacity(req->rq_disk))) {
-		printk("%s: bad access: block=%d, count=%d\n",
-			req->rq_disk->disk_name, block, nsect);
-		hd_end_request_cur(-EIO);
-		goto repeat;
-	}
-
-	if (disk->special_op) {
-		if (do_special_op(disk, req))
-			goto repeat;
-		return;
-	}
-	sec   = block % disk->sect + 1;
-	track = block / disk->sect;
-	head  = track % disk->head;
-	cyl   = track / disk->head;
-#ifdef DEBUG
-	printk("%s: %sing: CHS=%d/%d/%d, sectors=%d, buffer=%p\n",
-		req->rq_disk->disk_name,
-		req_data_dir(req) == READ ? "read" : "writ",
-		cyl, head, sec, nsect, bio_data(req->bio));
-#endif
-
-	switch (req_op(req)) {
-	case REQ_OP_READ:
-		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
-			&read_intr);
-		if (reset)
-			goto repeat;
-		break;
-	case REQ_OP_WRITE:
-		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
-			&write_intr);
-		if (reset)
-			goto repeat;
-		if (wait_DRQ()) {
-			bad_rw_intr();
-			goto repeat;
-		}
-		outsw(HD_DATA, bio_data(req->bio), 256);
-		break;
-	default:
-		printk("unknown hd-command\n");
-		hd_end_request_cur(-EIO);
-		break;
-	}
-}
-
-static void do_hd_request(struct request_queue *q)
-{
-	hd_request();
-}
-
-static int hd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
-	struct hd_i_struct *disk = bdev->bd_disk->private_data;
-
-	geo->heads = disk->head;
-	geo->sectors = disk->sect;
-	geo->cylinders = disk->cyl;
-	return 0;
-}
-
-/*
- * Releasing a block device means we sync() it, so that it can safely
- * be forgotten about...
- */
-
-static irqreturn_t hd_interrupt(int irq, void *dev_id)
-{
-	void (*handler)(void) = do_hd;
-
-	spin_lock(hd_queue->queue_lock);
-
-	do_hd = NULL;
-	del_timer(&device_timer);
-	if (!handler)
-		handler = unexpected_hd_interrupt;
-	handler();
-
-	spin_unlock(hd_queue->queue_lock);
-
-	return IRQ_HANDLED;
-}
-
-static const struct block_device_operations hd_fops = {
-	.getgeo =	hd_getgeo,
-};
-
-static int __init hd_init(void)
-{
-	int drive;
-
-	if (register_blkdev(HD_MAJOR, "hd"))
-		return -1;
-
-	hd_queue = blk_init_queue(do_hd_request, &hd_lock);
-	if (!hd_queue) {
-		unregister_blkdev(HD_MAJOR, "hd");
-		return -ENOMEM;
-	}
-
-	blk_queue_max_hw_sectors(hd_queue, 255);
-	init_timer(&device_timer);
-	device_timer.function = hd_times_out;
-	blk_queue_logical_block_size(hd_queue, 512);
-
-	if (!NR_HD) {
-		/*
-		 * We don't know anything about the drive.  This means
-		 * that you *MUST* specify the drive parameters to the
-		 * kernel yourself.
-		 *
-		 * If we were on an i386, we used to read this info from
-		 * the BIOS or CMOS.  This doesn't work all that well,
-		 * since this assumes that this is a primary or secondary
-		 * drive, and if we're using this legacy driver, it's
-		 * probably an auxiliary controller added to recover
-		 * legacy data off an ST-506 drive.  Either way, it's
-		 * definitely safest to have the user explicitly specify
-		 * the information.
-		 */
-		printk("hd: no drives specified - use hd=cyl,head,sectors"
-			" on kernel command line\n");
-		goto out;
-	}
-
-	for (drive = 0 ; drive < NR_HD ; drive++) {
-		struct gendisk *disk = alloc_disk(64);
-		struct hd_i_struct *p = &hd_info[drive];
-		if (!disk)
-			goto Enomem;
-		disk->major = HD_MAJOR;
-		disk->first_minor = drive << 6;
-		disk->fops = &hd_fops;
-		sprintf(disk->disk_name, "hd%c", 'a'+drive);
-		disk->private_data = p;
-		set_capacity(disk, p->head * p->sect * p->cyl);
-		disk->queue = hd_queue;
-		p->unit = drive;
-		hd_gendisk[drive] = disk;
-		printk("%s: %luMB, CHS=%d/%d/%d\n",
-			disk->disk_name, (unsigned long)get_capacity(disk)/2048,
-			p->cyl, p->head, p->sect);
-	}
-
-	if (request_irq(HD_IRQ, hd_interrupt, 0, "hd", NULL)) {
-		printk("hd: unable to get IRQ%d for the hard disk driver\n",
-			HD_IRQ);
-		goto out1;
-	}
-	if (!request_region(HD_DATA, 8, "hd")) {
-		printk(KERN_WARNING "hd: port 0x%x busy\n", HD_DATA);
-		goto out2;
-	}
-	if (!request_region(HD_CMD, 1, "hd(cmd)")) {
-		printk(KERN_WARNING "hd: port 0x%x busy\n", HD_CMD);
-		goto out3;
-	}
-
-	/* Let them fly */
-	for (drive = 0; drive < NR_HD; drive++)
-		add_disk(hd_gendisk[drive]);
-
-	return 0;
-
-out3:
-	release_region(HD_DATA, 8);
-out2:
-	free_irq(HD_IRQ, NULL);
-out1:
-	for (drive = 0; drive < NR_HD; drive++)
-		put_disk(hd_gendisk[drive]);
-	NR_HD = 0;
-out:
-	del_timer(&device_timer);
-	unregister_blkdev(HD_MAJOR, "hd");
-	blk_cleanup_queue(hd_queue);
-	return -1;
-Enomem:
-	while (drive--)
-		put_disk(hd_gendisk[drive]);
-	goto out;
-}
-
-static int __init parse_hd_setup(char *line)
-{
-	int ints[6];
-
-	(void) get_options(line, ARRAY_SIZE(ints), ints);
-	hd_setup(NULL, ints);
-
-	return 1;
-}
-__setup("hd=", parse_hd_setup);
-
-late_initcall(hd_init);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 0ecb6461ed81..994403efee19 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -445,32 +445,27 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
 	return ret;
 }
 
-static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
+static void lo_complete_rq(struct request *rq)
 {
-	if (bytes < 0 || op_is_write(req_op(cmd->rq)))
-		return;
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+	if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
+		     cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
 		struct bio *bio = cmd->rq->bio;
 
-		bio_advance(bio, bytes);
+		bio_advance(bio, cmd->ret);
 		zero_fill_bio(bio);
 	}
+
+	blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
 {
 	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
-	struct request *rq = cmd->rq;
-
-	handle_partial_read(cmd, ret);
 
-	if (ret > 0)
-		ret = 0;
-	else if (ret < 0)
-		ret = -EIO;
-
-	blk_mq_complete_request(rq, ret);
+	cmd->ret = ret;
+	blk_mq_complete_request(cmd->rq);
 }
 
 static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
@@ -528,6 +523,7 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
 	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 		return lo_discard(lo, rq, pos);
 	case REQ_OP_WRITE:
 		if (lo->transfer)
@@ -826,7 +822,7 @@ static void loop_config_discard(struct loop_device *lo)
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(q, 0);
-		q->limits.discard_zeroes_data = 0;
+		blk_queue_max_write_zeroes_sectors(q, 0);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		return;
 	}
@@ -834,7 +830,7 @@ static void loop_config_discard(struct loop_device *lo)
 	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
 	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	q->limits.discard_zeroes_data = 1;
+	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
@@ -1660,6 +1656,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	switch (req_op(cmd->rq)) {
 	case REQ_OP_FLUSH:
 	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 		cmd->use_aio = false;
 		break;
 	default:
@@ -1686,8 +1683,10 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	ret = do_req_filebacked(lo, cmd->rq);
  failed:
 	/* complete non-aio request */
-	if (!cmd->use_aio || ret)
-		blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
+	if (!cmd->use_aio || ret) {
+		cmd->ret = ret ? -EIO : 0;
+		blk_mq_complete_request(cmd->rq);
+	}
 }
 
 static void loop_queue_work(struct kthread_work *work)
@@ -1710,9 +1709,10 @@ static int loop_init_request(void *data, struct request *rq,
 	return 0;
 }
 
-static struct blk_mq_ops loop_mq_ops = {
+static const struct blk_mq_ops loop_mq_ops = {
 	.queue_rq       = loop_queue_rq,
 	.init_request	= loop_init_request,
+	.complete	= lo_complete_rq,
 };
 
 static int loop_add(struct loop_device **l, int i)
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index fb2237c73e61..fecd3f97ef8c 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -70,6 +70,7 @@ struct loop_cmd {
 	struct request *rq;
 	struct list_head list;
 	bool use_aio;           /* use AIO interface to handle I/O */
+	long ret;
 	struct kiocb iocb;
 };
 
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
deleted file mode 100644
index 286f276f586e..000000000000
--- a/drivers/block/mg_disk.c
+++ /dev/null
@@ -1,1112 +0,0 @@
-/*
- *  drivers/block/mg_disk.c
- *
- *  Support for the mGine m[g]flash IO mode.
- *  Based on legacy hd.c
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/blkdev.h>
-#include <linux/hdreg.h>
-#include <linux/ata.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-#include <linux/mg_disk.h>
-#include <linux/slab.h>
-
-#define MG_RES_SEC (CONFIG_MG_DISK_RES << 1)
-
-/* name for block device */
-#define MG_DISK_NAME "mgd"
-
-#define MG_DISK_MAJ 0
-#define MG_DISK_MAX_PART 16
-#define MG_SECTOR_SIZE 512
-#define MG_MAX_SECTS 256
-
-/* Register offsets */
-#define MG_BUFF_OFFSET			0x8000
-#define MG_REG_OFFSET			0xC000
-#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
-#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
-#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
-#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
-#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
-#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
-#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
-#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
-#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
-#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
-#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
-
-/* handy status */
-#define MG_STAT_READY	(ATA_DRDY | ATA_DSC)
-#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | (ATA_BUSY | ATA_DF | \
-				 ATA_ERR))) == MG_STAT_READY)
-
-/* error code for others */
-#define MG_ERR_NONE		0
-#define MG_ERR_TIMEOUT		0x100
-#define MG_ERR_INIT_STAT	0x101
-#define MG_ERR_TRANSLATION	0x102
-#define MG_ERR_CTRL_RST		0x103
-#define MG_ERR_INV_STAT		0x104
-#define MG_ERR_RSTOUT		0x105
-
-#define MG_MAX_ERRORS	6	/* Max read/write errors */
-
-/* command */
-#define MG_CMD_RD 0x20
-#define MG_CMD_WR 0x30
-#define MG_CMD_SLEEP 0x99
-#define MG_CMD_WAKEUP 0xC3
-#define MG_CMD_ID 0xEC
-#define MG_CMD_WR_CONF 0x3C
-#define MG_CMD_RD_CONF 0x40
-
-/* operation mode */
-#define MG_OP_CASCADE (1 << 0)
-#define MG_OP_CASCADE_SYNC_RD (1 << 1)
-#define MG_OP_CASCADE_SYNC_WR (1 << 2)
-#define MG_OP_INTERLEAVE (1 << 3)
-
-/* synchronous */
-#define MG_BURST_LAT_4 (3 << 4)
-#define MG_BURST_LAT_5 (4 << 4)
-#define MG_BURST_LAT_6 (5 << 4)
-#define MG_BURST_LAT_7 (6 << 4)
-#define MG_BURST_LAT_8 (7 << 4)
-#define MG_BURST_LEN_4 (1 << 1)
-#define MG_BURST_LEN_8 (2 << 1)
-#define MG_BURST_LEN_16 (3 << 1)
-#define MG_BURST_LEN_32 (4 << 1)
-#define MG_BURST_LEN_CONT (0 << 1)
-
-/* timeout value (unit: ms) */
-#define MG_TMAX_CONF_TO_CMD	1
-#define MG_TMAX_WAIT_RD_DRQ	10
-#define MG_TMAX_WAIT_WR_DRQ	500
-#define MG_TMAX_RST_TO_BUSY	10
-#define MG_TMAX_HDRST_TO_RDY	500
-#define MG_TMAX_SWRST_TO_RDY	500
-#define MG_TMAX_RSTOUT		3000
-
-#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
-
-/* main structure for mflash driver */
-struct mg_host {
-	struct device *dev;
-
-	struct request_queue *breq;
-	struct request *req;
-	spinlock_t lock;
-	struct gendisk *gd;
-
-	struct timer_list timer;
-	void (*mg_do_intr) (struct mg_host *);
-
-	u16 id[ATA_ID_WORDS];
-
-	u16 cyls;
-	u16 heads;
-	u16 sectors;
-	u32 n_sectors;
-	u32 nres_sectors;
-
-	void __iomem *dev_base;
-	unsigned int irq;
-	unsigned int rst;
-	unsigned int rstout;
-
-	u32 major;
-	u32 error;
-};
-
-/*
- * Debugging macro and defines
- */
-#undef DO_MG_DEBUG
-#ifdef DO_MG_DEBUG
-#  define MG_DBG(fmt, args...) \
-	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
-#else /* CONFIG_MG_DEBUG */
-#  define MG_DBG(fmt, args...) do { } while (0)
-#endif /* CONFIG_MG_DEBUG */
-
-static void mg_request(struct request_queue *);
-
-static bool mg_end_request(struct mg_host *host, int err, unsigned int nr_bytes)
-{
-	if (__blk_end_request(host->req, err, nr_bytes))
-		return true;
-
-	host->req = NULL;
-	return false;
-}
-
-static bool mg_end_request_cur(struct mg_host *host, int err)
-{
-	return mg_end_request(host, err, blk_rq_cur_bytes(host->req));
-}
-
-static void mg_dump_status(const char *msg, unsigned int stat,
-		struct mg_host *host)
-{
-	char *name = MG_DISK_NAME;
-
-	if (host->req)
-		name = host->req->rq_disk->disk_name;
-
-	printk(KERN_ERR "%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
-	if (stat & ATA_BUSY)
-		printk("Busy ");
-	if (stat & ATA_DRDY)
-		printk("DriveReady ");
-	if (stat & ATA_DF)
-		printk("WriteFault ");
-	if (stat & ATA_DSC)
-		printk("SeekComplete ");
-	if (stat & ATA_DRQ)
-		printk("DataRequest ");
-	if (stat & ATA_CORR)
-		printk("CorrectedError ");
-	if (stat & ATA_ERR)
-		printk("Error ");
-	printk("}\n");
-	if ((stat & ATA_ERR) == 0) {
-		host->error = 0;
-	} else {
-		host->error = inb((unsigned long)host->dev_base + MG_REG_ERROR);
-		printk(KERN_ERR "%s: %s: error=0x%02x { ", name, msg,
-				host->error & 0xff);
-		if (host->error & ATA_BBK)
-			printk("BadSector ");
-		if (host->error & ATA_UNC)
-			printk("UncorrectableError ");
-		if (host->error & ATA_IDNF)
-			printk("SectorIdNotFound ");
-		if (host->error & ATA_ABORTED)
-			printk("DriveStatusError ");
-		if (host->error & ATA_AMNF)
-			printk("AddrMarkNotFound ");
-		printk("}");
-		if (host->error & (ATA_BBK | ATA_UNC | ATA_IDNF | ATA_AMNF)) {
-			if (host->req)
-				printk(", sector=%u",
-				       (unsigned int)blk_rq_pos(host->req));
-		}
-		printk("\n");
-	}
-}
-
-static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
-{
-	u8 status;
-	unsigned long expire, cur_jiffies;
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-
-	host->error = MG_ERR_NONE;
-	expire = jiffies + msecs_to_jiffies(msec);
-
-	/* These 2 times dummy status read prevents reading invalid
-	 * status. A very little time (3 times of mflash operating clk)
-	 * is required for busy bit is set. Use dummy read instead of
-	 * busy wait, because mflash's PLL is machine dependent.
-	 */
-	if (prv_data->use_polling) {
-		status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-	}
-
-	status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
-	do {
-		cur_jiffies = jiffies;
-		if (status & ATA_BUSY) {
-			if (expect == ATA_BUSY)
-				break;
-		} else {
-			/* Check the error condition! */
-			if (status & ATA_ERR) {
-				mg_dump_status("mg_wait", status, host);
-				break;
-			}
-
-			if (expect == MG_STAT_READY)
-				if (MG_READY_OK(status))
-					break;
-
-			if (expect == ATA_DRQ)
-				if (status & ATA_DRQ)
-					break;
-		}
-		if (!msec) {
-			mg_dump_status("not ready", status, host);
-			return MG_ERR_INV_STAT;
-		}
-
-		status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-	} while (time_before(cur_jiffies, expire));
-
-	if (time_after_eq(cur_jiffies, expire) && msec)
-		host->error = MG_ERR_TIMEOUT;
-
-	return host->error;
-}
-
-static unsigned int mg_wait_rstout(u32 rstout, u32 msec)
-{
-	unsigned long expire;
-
-	expire = jiffies + msecs_to_jiffies(msec);
-	while (time_before(jiffies, expire)) {
-		if (gpio_get_value(rstout) == 1)
-			return MG_ERR_NONE;
-		msleep(10);
-	}
-
-	return MG_ERR_RSTOUT;
-}
-
-static void mg_unexpected_intr(struct mg_host *host)
-{
-	u32 status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
-	mg_dump_status("mg_unexpected_intr", status, host);
-}
-
-static irqreturn_t mg_irq(int irq, void *dev_id)
-{
-	struct mg_host *host = dev_id;
-	void (*handler)(struct mg_host *) = host->mg_do_intr;
-
-	spin_lock(&host->lock);
-
-	host->mg_do_intr = NULL;
-	del_timer(&host->timer);
-	if (!handler)
-		handler = mg_unexpected_intr;
-	handler(host);
-
-	spin_unlock(&host->lock);
-
-	return IRQ_HANDLED;
-}
-
-/* local copy of ata_id_string() */
-static void mg_id_string(const u16 *id, unsigned char *s,
-			 unsigned int ofs, unsigned int len)
-{
-	unsigned int c;
-
-	BUG_ON(len & 1);
-
-	while (len > 0) {
-		c = id[ofs] >> 8;
-		*s = c;
-		s++;
-
-		c = id[ofs] & 0xff;
-		*s = c;
-		s++;
-
-		ofs++;
-		len -= 2;
-	}
-}
-
-/* local copy of ata_id_c_string() */
-static void mg_id_c_string(const u16 *id, unsigned char *s,
-			   unsigned int ofs, unsigned int len)
-{
-	unsigned char *p;
-
-	mg_id_string(id, s, ofs, len - 1);
-
-	p = s + strnlen(s, len - 1);
-	while (p > s && p[-1] == ' ')
-		p--;
-	*p = '\0';
-}
-
-static int mg_get_disk_id(struct mg_host *host)
-{
-	u32 i;
-	s32 err;
-	const u16 *id = host->id;
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-	char fwrev[ATA_ID_FW_REV_LEN + 1];
-	char model[ATA_ID_PROD_LEN + 1];
-	char serial[ATA_ID_SERNO_LEN + 1];
-
-	if (!prv_data->use_polling)
-		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	outb(MG_CMD_ID, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	err = mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_RD_DRQ);
-	if (err)
-		return err;
-
-	for (i = 0; i < (MG_SECTOR_SIZE >> 1); i++)
-		host->id[i] = le16_to_cpu(inw((unsigned long)host->dev_base +
-					MG_BUFF_OFFSET + i * 2));
-
-	outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	err = mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD);
-	if (err)
-		return err;
-
-	if ((id[ATA_ID_FIELD_VALID] & 1) == 0)
-		return MG_ERR_TRANSLATION;
-
-	host->n_sectors = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
-	host->cyls = id[ATA_ID_CYLS];
-	host->heads = id[ATA_ID_HEADS];
-	host->sectors = id[ATA_ID_SECTORS];
-
-	if (MG_RES_SEC && host->heads && host->sectors) {
-		/* modify cyls, n_sectors */
-		host->cyls = (host->n_sectors - MG_RES_SEC) /
-			host->heads / host->sectors;
-		host->nres_sectors = host->n_sectors - host->cyls *
-			host->heads * host->sectors;
-		host->n_sectors -= host->nres_sectors;
-	}
-
-	mg_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
-	mg_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
-	mg_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
-	printk(KERN_INFO "mg_disk: model: %s\n", model);
-	printk(KERN_INFO "mg_disk: firm: %.8s\n", fwrev);
-	printk(KERN_INFO "mg_disk: serial: %s\n", serial);
-	printk(KERN_INFO "mg_disk: %d + reserved %d sectors\n",
-			host->n_sectors, host->nres_sectors);
-
-	if (!prv_data->use_polling)
-		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	return err;
-}
-
-
-static int mg_disk_init(struct mg_host *host)
-{
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-	s32 err;
-	u8 init_status;
-
-	/* hdd rst low */
-	gpio_set_value(host->rst, 0);
-	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
-	if (err)
-		return err;
-
-	/* hdd rst high */
-	gpio_set_value(host->rst, 1);
-	err = mg_wait(host, MG_STAT_READY, MG_TMAX_HDRST_TO_RDY);
-	if (err)
-		return err;
-
-	/* soft reset on */
-	outb(ATA_SRST | (prv_data->use_polling ? ATA_NIEN : 0),
-			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
-	if (err)
-		return err;
-
-	/* soft reset off */
-	outb(prv_data->use_polling ? ATA_NIEN : 0,
-			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-	err = mg_wait(host, MG_STAT_READY, MG_TMAX_SWRST_TO_RDY);
-	if (err)
-		return err;
-
-	init_status = inb((unsigned long)host->dev_base + MG_REG_STATUS) & 0xf;
-
-	if (init_status == 0xf)
-		return MG_ERR_INIT_STAT;
-
-	return err;
-}
-
-static void mg_bad_rw_intr(struct mg_host *host)
-{
-	if (host->req)
-		if (++host->req->errors >= MG_MAX_ERRORS ||
-		    host->error == MG_ERR_TIMEOUT)
-			mg_end_request_cur(host, -EIO);
-}
-
-static unsigned int mg_out(struct mg_host *host,
-		unsigned int sect_num,
-		unsigned int sect_cnt,
-		unsigned int cmd,
-		void (*intr_addr)(struct mg_host *))
-{
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return host->error;
-
-	if (!prv_data->use_polling) {
-		host->mg_do_intr = intr_addr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	}
-	if (MG_RES_SEC)
-		sect_num += MG_RES_SEC;
-	outb((u8)sect_cnt, (unsigned long)host->dev_base + MG_REG_SECT_CNT);
-	outb((u8)sect_num, (unsigned long)host->dev_base + MG_REG_SECT_NUM);
-	outb((u8)(sect_num >> 8), (unsigned long)host->dev_base +
-			MG_REG_CYL_LOW);
-	outb((u8)(sect_num >> 16), (unsigned long)host->dev_base +
-			MG_REG_CYL_HIGH);
-	outb((u8)((sect_num >> 24) | ATA_LBA | ATA_DEVICE_OBS),
-			(unsigned long)host->dev_base + MG_REG_DRV_HEAD);
-	outb(cmd, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	return MG_ERR_NONE;
-}
-
-static void mg_read_one(struct mg_host *host, struct request *req)
-{
-	u16 *buff = (u16 *)bio_data(req->bio);
-	u32 i;
-
-	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
-		*buff++ = inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
-			      (i << 1));
-}
-
-static void mg_read(struct request *req)
-{
-	struct mg_host *host = req->rq_disk->private_data;
-
-	if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
-		   MG_CMD_RD, NULL) != MG_ERR_NONE)
-		mg_bad_rw_intr(host);
-
-	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-	       blk_rq_sectors(req), blk_rq_pos(req), bio_data(req->bio));
-
-	do {
-		if (mg_wait(host, ATA_DRQ,
-			    MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return;
-		}
-
-		mg_read_one(host, req);
-
-		outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base +
-				MG_REG_COMMAND);
-	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_write_one(struct mg_host *host, struct request *req)
-{
-	u16 *buff = (u16 *)bio_data(req->bio);
-	u32 i;
-
-	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
-		outw(*buff++, (unsigned long)host->dev_base + MG_BUFF_OFFSET +
-		     (i << 1));
-}
-
-static void mg_write(struct request *req)
-{
-	struct mg_host *host = req->rq_disk->private_data;
-	unsigned int rem = blk_rq_sectors(req);
-
-	if (mg_out(host, blk_rq_pos(req), rem,
-		   MG_CMD_WR, NULL) != MG_ERR_NONE) {
-		mg_bad_rw_intr(host);
-		return;
-	}
-
-	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-	       rem, blk_rq_pos(req), bio_data(req->bio));
-
-	if (mg_wait(host, ATA_DRQ,
-		    MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
-		mg_bad_rw_intr(host);
-		return;
-	}
-
-	do {
-		mg_write_one(host, req);
-
-		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
-				MG_REG_COMMAND);
-
-		rem--;
-		if (rem > 1 && mg_wait(host, ATA_DRQ,
-					MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return;
-		} else if (mg_wait(host, MG_STAT_READY,
-					MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return;
-		}
-	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_read_intr(struct mg_host *host)
-{
-	struct request *req = host->req;
-	u32 i;
-
-	/* check status */
-	do {
-		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & ATA_BUSY)
-			break;
-		if (!MG_READY_OK(i))
-			break;
-		if (i & ATA_DRQ)
-			goto ok_to_read;
-	} while (0);
-	mg_dump_status("mg_read_intr", i, host);
-	mg_bad_rw_intr(host);
-	mg_request(host->breq);
-	return;
-
-ok_to_read:
-	mg_read_one(host, req);
-
-	MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-	       blk_rq_pos(req), blk_rq_sectors(req) - 1, bio_data(req->bio));
-
-	/* send read confirm */
-	outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
-	if (mg_end_request(host, 0, MG_SECTOR_SIZE)) {
-		/* set handler if read remains */
-		host->mg_do_intr = mg_read_intr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	} else /* goto next request */
-		mg_request(host->breq);
-}
-
-static void mg_write_intr(struct mg_host *host)
-{
-	struct request *req = host->req;
-	u32 i;
-	bool rem;
-
-	/* check status */
-	do {
-		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & ATA_BUSY)
-			break;
-		if (!MG_READY_OK(i))
-			break;
-		if ((blk_rq_sectors(req) <= 1) || (i & ATA_DRQ))
-			goto ok_to_write;
-	} while (0);
-	mg_dump_status("mg_write_intr", i, host);
-	mg_bad_rw_intr(host);
-	mg_request(host->breq);
-	return;
-
-ok_to_write:
-	if ((rem = mg_end_request(host, 0, MG_SECTOR_SIZE))) {
-		/* write 1 sector and set handler if remains */
-		mg_write_one(host, req);
-		MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-		       blk_rq_pos(req), blk_rq_sectors(req), bio_data(req->bio));
-		host->mg_do_intr = mg_write_intr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	}
-
-	/* send write confirm */
-	outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
-	if (!rem)
-		mg_request(host->breq);
-}
-
-static void mg_times_out(unsigned long data)
-{
-	struct mg_host *host = (struct mg_host *)data;
-	char *name;
-
-	spin_lock_irq(&host->lock);
-
-	if (!host->req)
-		goto out_unlock;
-
-	host->mg_do_intr = NULL;
-
-	name = host->req->rq_disk->disk_name;
-	printk(KERN_DEBUG "%s: timeout\n", name);
-
-	host->error = MG_ERR_TIMEOUT;
-	mg_bad_rw_intr(host);
-
-out_unlock:
-	mg_request(host->breq);
-	spin_unlock_irq(&host->lock);
-}
-
-static void mg_request_poll(struct request_queue *q)
-{
-	struct mg_host *host = q->queuedata;
-
-	while (1) {
-		if (!host->req) {
-			host->req = blk_fetch_request(q);
-			if (!host->req)
-				break;
-		}
-
-		switch (req_op(host->req)) {
-		case REQ_OP_READ:
-			mg_read(host->req);
-			break;
-		case REQ_OP_WRITE:
-			mg_write(host->req);
-			break;
-		default:
-			mg_end_request_cur(host, -EIO);
-			break;
-		}
-	}
-}
-
-static unsigned int mg_issue_req(struct request *req,
-		struct mg_host *host,
-		unsigned int sect_num,
-		unsigned int sect_cnt)
-{
-	switch (req_op(host->req)) {
-	case REQ_OP_READ:
-		if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
-				!= MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return host->error;
-		}
-		break;
-	case REQ_OP_WRITE:
-		/* TODO : handler */
-		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
-				!= MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return host->error;
-		}
-		del_timer(&host->timer);
-		mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ);
-		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-		if (host->error) {
-			mg_bad_rw_intr(host);
-			return host->error;
-		}
-		mg_write_one(host, req);
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
-				MG_REG_COMMAND);
-		break;
-	default:
-		mg_end_request_cur(host, -EIO);
-		break;
-	}
-	return MG_ERR_NONE;
-}
-
-/* This function also called from IRQ context */
-static void mg_request(struct request_queue *q)
-{
-	struct mg_host *host = q->queuedata;
-	struct request *req;
-	u32 sect_num, sect_cnt;
-
-	while (1) {
-		if (!host->req) {
-			host->req = blk_fetch_request(q);
-			if (!host->req)
-				break;
-		}
-		req = host->req;
-
-		/* check unwanted request call */
-		if (host->mg_do_intr)
-			return;
-
-		del_timer(&host->timer);
-
-		sect_num = blk_rq_pos(req);
-		/* deal whole segments */
-		sect_cnt = blk_rq_sectors(req);
-
-		/* sanity check */
-		if (sect_num >= get_capacity(req->rq_disk) ||
-				((sect_num + sect_cnt) >
-				 get_capacity(req->rq_disk))) {
-			printk(KERN_WARNING
-					"%s: bad access: sector=%d, count=%d\n",
-					req->rq_disk->disk_name,
-					sect_num, sect_cnt);
-			mg_end_request_cur(host, -EIO);
-			continue;
-		}
-
-		if (!mg_issue_req(req, host, sect_num, sect_cnt))
-			return;
-	}
-}
-
-static int mg_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
-	struct mg_host *host = bdev->bd_disk->private_data;
-
-	geo->cylinders = (unsigned short)host->cyls;
-	geo->heads = (unsigned char)host->heads;
-	geo->sectors = (unsigned char)host->sectors;
-	return 0;
-}
-
-static const struct block_device_operations mg_disk_ops = {
-	.getgeo = mg_getgeo
-};
-
-#ifdef CONFIG_PM_SLEEP
-static int mg_suspend(struct device *dev)
-{
-	struct mg_drv_data *prv_data = dev->platform_data;
-	struct mg_host *host = prv_data->host;
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return -EIO;
-
-	if (!prv_data->use_polling)
-		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	outb(MG_CMD_SLEEP, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	/* wait until mflash deep sleep */
-	msleep(1);
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) {
-		if (!prv_data->use_polling)
-			outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static int mg_resume(struct device *dev)
-{
-	struct mg_drv_data *prv_data = dev->platform_data;
-	struct mg_host *host = prv_data->host;
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return -EIO;
-
-	outb(MG_CMD_WAKEUP, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	/* wait until mflash wakeup */
-	msleep(1);
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return -EIO;
-
-	if (!prv_data->use_polling)
-		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(mg_pm, mg_suspend, mg_resume);
-
-static int mg_probe(struct platform_device *plat_dev)
-{
-	struct mg_host *host;
-	struct resource *rsc;
-	struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
-	int err = 0;
-
-	if (!prv_data) {
-		printk(KERN_ERR	"%s:%d fail (no driver_data)\n",
-				__func__, __LINE__);
-		err = -EINVAL;
-		goto probe_err;
-	}
-
-	/* alloc mg_host */
-	host = kzalloc(sizeof(struct mg_host), GFP_KERNEL);
-	if (!host) {
-		printk(KERN_ERR "%s:%d fail (no memory for mg_host)\n",
-				__func__, __LINE__);
-		err = -ENOMEM;
-		goto probe_err;
-	}
-	host->major = MG_DISK_MAJ;
-
-	/* link each other */
-	prv_data->host = host;
-	host->dev = &plat_dev->dev;
-
-	/* io remap */
-	rsc = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
-	if (!rsc) {
-		printk(KERN_ERR "%s:%d platform_get_resource fail\n",
-				__func__, __LINE__);
-		err = -EINVAL;
-		goto probe_err_2;
-	}
-	host->dev_base = ioremap(rsc->start, resource_size(rsc));
-	if (!host->dev_base) {
-		printk(KERN_ERR "%s:%d ioremap fail\n",
-				__func__, __LINE__);
-		err = -EIO;
-		goto probe_err_2;
-	}
-	MG_DBG("dev_base = 0x%x\n", (u32)host->dev_base);
-
-	/* get reset pin */
-	rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
-			MG_RST_PIN);
-	if (!rsc) {
-		printk(KERN_ERR "%s:%d get reset pin fail\n",
-				__func__, __LINE__);
-		err = -EIO;
-		goto probe_err_3;
-	}
-	host->rst = rsc->start;
-
-	/* init rst pin */
-	err = gpio_request(host->rst, MG_RST_PIN);
-	if (err)
-		goto probe_err_3;
-	gpio_direction_output(host->rst, 1);
-
-	/* reset out pin */
-	if (!(prv_data->dev_attr & MG_DEV_MASK)) {
-		err = -EINVAL;
-		goto probe_err_3a;
-	}
-
-	if (prv_data->dev_attr != MG_BOOT_DEV) {
-		rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
-				MG_RSTOUT_PIN);
-		if (!rsc) {
-			printk(KERN_ERR "%s:%d get reset-out pin fail\n",
-					__func__, __LINE__);
-			err = -EIO;
-			goto probe_err_3a;
-		}
-		host->rstout = rsc->start;
-		err = gpio_request(host->rstout, MG_RSTOUT_PIN);
-		if (err)
-			goto probe_err_3a;
-		gpio_direction_input(host->rstout);
-	}
-
-	/* disk reset */
-	if (prv_data->dev_attr == MG_STORAGE_DEV) {
-		/* If POR seq. not yet finished, wait */
-		err = mg_wait_rstout(host->rstout, MG_TMAX_RSTOUT);
-		if (err)
-			goto probe_err_3b;
-		err = mg_disk_init(host);
-		if (err) {
-			printk(KERN_ERR "%s:%d fail (err code : %d)\n",
-					__func__, __LINE__, err);
-			err = -EIO;
-			goto probe_err_3b;
-		}
-	}
-
-	/* get irq resource */
-	if (!prv_data->use_polling) {
-		host->irq = platform_get_irq(plat_dev, 0);
-		if (host->irq == -ENXIO) {
-			err = host->irq;
-			goto probe_err_3b;
-		}
-		err = request_irq(host->irq, mg_irq,
-				IRQF_TRIGGER_RISING,
-				MG_DEV_NAME, host);
-		if (err) {
-			printk(KERN_ERR "%s:%d fail (request_irq err=%d)\n",
-					__func__, __LINE__, err);
-			goto probe_err_3b;
-		}
-
-	}
-
-	/* get disk id */
-	err = mg_get_disk_id(host);
-	if (err) {
-		printk(KERN_ERR "%s:%d fail (err code : %d)\n",
-				__func__, __LINE__, err);
-		err = -EIO;
-		goto probe_err_4;
-	}
-
-	err = register_blkdev(host->major, MG_DISK_NAME);
-	if (err < 0) {
-		printk(KERN_ERR "%s:%d register_blkdev fail (err code : %d)\n",
-				__func__, __LINE__, err);
-		goto probe_err_4;
-	}
-	if (!host->major)
-		host->major = err;
-
-	spin_lock_init(&host->lock);
-
-	if (prv_data->use_polling)
-		host->breq = blk_init_queue(mg_request_poll, &host->lock);
-	else
-		host->breq = blk_init_queue(mg_request, &host->lock);
-
-	if (!host->breq) {
-		err = -ENOMEM;
-		printk(KERN_ERR "%s:%d (blk_init_queue) fail\n",
-				__func__, __LINE__);
-		goto probe_err_5;
-	}
-	host->breq->queuedata = host;
-
-	/* mflash is random device, thanx for the noop */
-	err = elevator_change(host->breq, "noop");
-	if (err) {
-		printk(KERN_ERR "%s:%d (elevator_init) fail\n",
-				__func__, __LINE__);
-		goto probe_err_6;
-	}
-	blk_queue_max_hw_sectors(host->breq, MG_MAX_SECTS);
-	blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
-
-	init_timer(&host->timer);
-	host->timer.function = mg_times_out;
-	host->timer.data = (unsigned long)host;
-
-	host->gd = alloc_disk(MG_DISK_MAX_PART);
-	if (!host->gd) {
-		printk(KERN_ERR "%s:%d (alloc_disk) fail\n",
-				__func__, __LINE__);
-		err = -ENOMEM;
-		goto probe_err_7;
-	}
-	host->gd->major = host->major;
-	host->gd->first_minor = 0;
-	host->gd->fops = &mg_disk_ops;
-	host->gd->queue = host->breq;
-	host->gd->private_data = host;
-	sprintf(host->gd->disk_name, MG_DISK_NAME"a");
-
-	set_capacity(host->gd, host->n_sectors);
-
-	add_disk(host->gd);
-
-	return err;
-
-probe_err_7:
-	del_timer_sync(&host->timer);
-probe_err_6:
-	blk_cleanup_queue(host->breq);
-probe_err_5:
-	unregister_blkdev(host->major, MG_DISK_NAME);
-probe_err_4:
-	if (!prv_data->use_polling)
-		free_irq(host->irq, host);
-probe_err_3b:
-	gpio_free(host->rstout);
-probe_err_3a:
-	gpio_free(host->rst);
-probe_err_3:
-	iounmap(host->dev_base);
-probe_err_2:
-	kfree(host);
-probe_err:
-	return err;
-}
-
-static int mg_remove(struct platform_device *plat_dev)
-{
-	struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
-	struct mg_host *host = prv_data->host;
-	int err = 0;
-
-	/* delete timer */
-	del_timer_sync(&host->timer);
-
-	/* remove disk */
-	if (host->gd) {
-		del_gendisk(host->gd);
-		put_disk(host->gd);
-	}
-	/* remove queue */
-	if (host->breq)
-		blk_cleanup_queue(host->breq);
-
-	/* unregister blk device */
-	unregister_blkdev(host->major, MG_DISK_NAME);
-
-	/* free irq */
-	if (!prv_data->use_polling)
-		free_irq(host->irq, host);
-
-	/* free reset-out pin */
-	if (prv_data->dev_attr != MG_BOOT_DEV)
-		gpio_free(host->rstout);
-
-	/* free rst pin */
-	if (host->rst)
-		gpio_free(host->rst);
-
-	/* unmap io */
-	if (host->dev_base)
-		iounmap(host->dev_base);
-
-	/* free mg_host */
-	kfree(host);
-
-	return err;
-}
-
-static struct platform_driver mg_disk_driver = {
-	.probe = mg_probe,
-	.remove = mg_remove,
-	.driver = {
-		.name = MG_DEV_NAME,
-		.pm = &mg_pm,
-	}
-};
-
-/****************************************************************************
- *
- * Module stuff
- *
- ****************************************************************************/
-
-static int __init mg_init(void)
-{
-	printk(KERN_INFO "mGine mflash driver, (c) 2008 mGine Co.\n");
-	return platform_driver_register(&mg_disk_driver);
-}
-
-static void __exit mg_exit(void)
-{
-	printk(KERN_INFO "mflash driver : bye bye\n");
-	platform_driver_unregister(&mg_disk_driver);
-}
-
-module_init(mg_init);
-module_exit(mg_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("unsik Kim <donari75@gmail.com>");
-MODULE_DESCRIPTION("mGine m[g]flash device driver");
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index f96ab717534c..02804cc79d82 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -169,6 +169,25 @@ static bool mtip_check_surprise_removal(struct pci_dev *pdev)
 	return false; /* device present */
 }
 
+/* we have to use runtime tag to setup command header */
+static void mtip_init_cmd_header(struct request *rq)
+{
+	struct driver_data *dd = rq->q->queuedata;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
+
+	/* Point the command headers at the command tables. */
+	cmd->command_header = dd->port->command_list +
+				(sizeof(struct mtip_cmd_hdr) * rq->tag);
+	cmd->command_header_dma = dd->port->command_list_dma +
+				(sizeof(struct mtip_cmd_hdr) * rq->tag);
+
+	if (host_cap_64)
+		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
+
+	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
+}
+
 static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 {
 	struct request *rq;
@@ -180,6 +199,9 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 	if (IS_ERR(rq))
 		return NULL;
 
+	/* Internal cmd isn't submitted via .queue_rq */
+	mtip_init_cmd_header(rq);
+
 	return blk_mq_rq_to_pdu(rq);
 }
 
@@ -241,7 +263,8 @@ static void mtip_async_complete(struct mtip_port *port,
 
 	rq = mtip_rq_from_tag(dd, tag);
 
-	blk_mq_complete_request(rq, status);
+	cmd->status = status;
+	blk_mq_complete_request(rq);
 }
 
 /*
@@ -2910,18 +2933,19 @@ static void mtip_softirq_done_fn(struct request *rq)
 	if (unlikely(cmd->unaligned))
 		up(&dd->port->cmd_slot_unal);
 
-	blk_mq_end_request(rq, rq->errors);
+	blk_mq_end_request(rq, cmd->status);
 }
 
 static void mtip_abort_cmd(struct request *req, void *data,
 							bool reserved)
 {
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct driver_data *dd = data;
 
 	dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
 
 	clear_bit(req->tag, dd->port->cmds_to_issue);
-	req->errors = -EIO;
+	cmd->status = -EIO;
 	mtip_softirq_done_fn(req);
 }
 
@@ -3807,6 +3831,8 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *rq = bd->rq;
 	int ret;
 
+	mtip_init_cmd_header(rq);
+
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
@@ -3816,7 +3842,6 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
 
-	rq->errors = ret;
 	return BLK_MQ_RQ_QUEUE_ERROR;
 }
 
@@ -3838,7 +3863,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 {
 	struct driver_data *dd = data;
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
-	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
 
 	/*
 	 * For flush requests, request_idx starts at the end of the
@@ -3855,17 +3879,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 
 	memset(cmd->command, 0, CMD_DMA_ALLOC_SZ);
 
-	/* Point the command headers at the command tables. */
-	cmd->command_header = dd->port->command_list +
-				(sizeof(struct mtip_cmd_hdr) * request_idx);
-	cmd->command_header_dma = dd->port->command_list_dma +
-				(sizeof(struct mtip_cmd_hdr) * request_idx);
-
-	if (host_cap_64)
-		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
-
-	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
-
 	sg_init_table(cmd->sg, MTIP_MAX_SG);
 	return 0;
 }
@@ -3889,7 +3902,7 @@ exit_handler:
 	return BLK_EH_RESET_TIMER;
 }
 
-static struct blk_mq_ops mtip_mq_ops = {
+static const struct blk_mq_ops mtip_mq_ops = {
 	.queue_rq	= mtip_queue_rq,
 	.init_request	= mtip_init_cmd,
 	.exit_request	= mtip_free_cmd,
@@ -3969,7 +3982,7 @@ static int mtip_block_initialize(struct driver_data *dd)
 	dd->tags.reserved_tags = 1;
 	dd->tags.cmd_size = sizeof(struct mtip_cmd);
 	dd->tags.numa_node = dd->numa_node;
-	dd->tags.flags = BLK_MQ_F_SHOULD_MERGE;
+	dd->tags.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_SCHED;
 	dd->tags.driver_data = dd;
 	dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS;
 
@@ -4025,7 +4038,6 @@ skip_create_disk:
 		dd->queue->limits.discard_granularity = 4096;
 		blk_queue_max_discard_sectors(dd->queue,
 			MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES);
-		dd->queue->limits.discard_zeroes_data = 0;
 	}
 
 	/* Set the capacity of the device in 512 byte sectors. */
@@ -4107,9 +4119,11 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
 	struct driver_data *dd = (struct driver_data *)data;
 	struct mtip_cmd *cmd;
 
-	if (likely(!reserv))
-		blk_mq_complete_request(rq, -ENODEV);
-	else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
+	if (likely(!reserv)) {
+		cmd = blk_mq_rq_to_pdu(rq);
+		cmd->status = -ENODEV;
+		blk_mq_complete_request(rq);
+	} else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
 
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		if (cmd->comp_func)
@@ -4162,7 +4176,7 @@ static int mtip_block_remove(struct driver_data *dd)
 		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
 						dd->disk->disk_name);
 
-	blk_mq_freeze_queue_start(dd->queue);
+	blk_freeze_queue_start(dd->queue);
 	blk_mq_stop_hw_queues(dd->queue);
 	blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
 
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 7617888f7944..57b41528a824 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -352,6 +352,7 @@ struct mtip_cmd {
 	int retries; /* The number of retries left for this command. */
 
 	int direction; /* Data transfer direction */
+	int status;
 };
 
 /* Structure used to describe a port. */
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 7e4287bc19e5..9b482baa869e 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -40,47 +40,82 @@
 #include <asm/types.h>
 
 #include <linux/nbd.h>
+#include <linux/nbd-netlink.h>
+#include <net/genetlink.h>
 
 static DEFINE_IDR(nbd_index_idr);
 static DEFINE_MUTEX(nbd_index_mutex);
+static int nbd_total_devices = 0;
 
 struct nbd_sock {
 	struct socket *sock;
 	struct mutex tx_lock;
+	struct request *pending;
+	int sent;
+	bool dead;
+	int fallback_index;
+	int cookie;
+};
+
+struct recv_thread_args {
+	struct work_struct work;
+	struct nbd_device *nbd;
+	int index;
+};
+
+struct link_dead_args {
+	struct work_struct work;
+	int index;
 };
 
 #define NBD_TIMEDOUT			0
 #define NBD_DISCONNECT_REQUESTED	1
 #define NBD_DISCONNECTED		2
-#define NBD_RUNNING			3
+#define NBD_HAS_PID_FILE		3
+#define NBD_HAS_CONFIG_REF		4
+#define NBD_BOUND			5
+#define NBD_DESTROY_ON_DISCONNECT	6
 
-struct nbd_device {
+struct nbd_config {
 	u32 flags;
 	unsigned long runtime_flags;
-	struct nbd_sock **socks;
-	int magic;
+	u64 dead_conn_timeout;
 
-	struct blk_mq_tag_set tag_set;
-
-	struct mutex config_lock;
-	struct gendisk *disk;
+	struct nbd_sock **socks;
 	int num_connections;
+	atomic_t live_connections;
+	wait_queue_head_t conn_wait;
+
 	atomic_t recv_threads;
 	wait_queue_head_t recv_wq;
 	loff_t blksize;
 	loff_t bytesize;
-
-	struct task_struct *task_recv;
-	struct task_struct *task_setup;
-
 #if IS_ENABLED(CONFIG_DEBUG_FS)
 	struct dentry *dbg_dir;
 #endif
 };
 
+struct nbd_device {
+	struct blk_mq_tag_set tag_set;
+
+	int index;
+	refcount_t config_refs;
+	refcount_t refs;
+	struct nbd_config *config;
+	struct mutex config_lock;
+	struct gendisk *disk;
+
+	struct list_head list;
+	struct task_struct *task_recv;
+	struct task_struct *task_setup;
+};
+
 struct nbd_cmd {
 	struct nbd_device *nbd;
+	int index;
+	int cookie;
 	struct completion send_complete;
+	int status;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -98,18 +133,16 @@ static int part_shift;
 
 static int nbd_dev_dbg_init(struct nbd_device *nbd);
 static void nbd_dev_dbg_close(struct nbd_device *nbd);
-
+static void nbd_config_put(struct nbd_device *nbd);
+static void nbd_connect_reply(struct genl_info *info, int index);
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
+static void nbd_dead_link_work(struct work_struct *work);
 
 static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 {
 	return disk_to_dev(nbd->disk);
 }
 
-static bool nbd_is_connected(struct nbd_device *nbd)
-{
-	return !!nbd->task_recv;
-}
-
 static const char *nbdcmd_to_ascii(int cmd)
 {
 	switch (cmd) {
@@ -122,43 +155,104 @@ static const char *nbdcmd_to_ascii(int cmd)
 	return "invalid";
 }
 
-static int nbd_size_clear(struct nbd_device *nbd, struct block_device *bdev)
+static ssize_t pid_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
 {
-	bd_set_size(bdev, 0);
-	set_capacity(nbd->disk, 0);
-	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
 
-	return 0;
+	return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
+}
+
+static struct device_attribute pid_attr = {
+	.attr = { .name = "pid", .mode = S_IRUGO},
+	.show = pid_show,
+};
+
+static void nbd_dev_remove(struct nbd_device *nbd)
+{
+	struct gendisk *disk = nbd->disk;
+	if (disk) {
+		del_gendisk(disk);
+		blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&nbd->tag_set);
+		disk->private_data = NULL;
+		put_disk(disk);
+	}
+	kfree(nbd);
+}
+
+static void nbd_put(struct nbd_device *nbd)
+{
+	if (refcount_dec_and_mutex_lock(&nbd->refs,
+					&nbd_index_mutex)) {
+		idr_remove(&nbd_index_idr, nbd->index);
+		mutex_unlock(&nbd_index_mutex);
+		nbd_dev_remove(nbd);
+	}
+}
+
+static int nbd_disconnected(struct nbd_config *config)
+{
+	return test_bit(NBD_DISCONNECTED, &config->runtime_flags) ||
+		test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+}
+
+static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
+				int notify)
+{
+	if (!nsock->dead && notify && !nbd_disconnected(nbd->config)) {
+		struct link_dead_args *args;
+		args = kmalloc(sizeof(struct link_dead_args), GFP_NOIO);
+		if (args) {
+			INIT_WORK(&args->work, nbd_dead_link_work);
+			args->index = nbd->index;
+			queue_work(system_wq, &args->work);
+		}
+	}
+	if (!nsock->dead) {
+		kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+		atomic_dec(&nbd->config->live_connections);
+	}
+	nsock->dead = true;
+	nsock->pending = NULL;
+	nsock->sent = 0;
 }
 
-static void nbd_size_update(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_size_clear(struct nbd_device *nbd)
 {
-	blk_queue_logical_block_size(nbd->disk->queue, nbd->blksize);
-	blk_queue_physical_block_size(nbd->disk->queue, nbd->blksize);
-	bd_set_size(bdev, nbd->bytesize);
-	set_capacity(nbd->disk, nbd->bytesize >> 9);
+	if (nbd->config->bytesize) {
+		set_capacity(nbd->disk, 0);
+		kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+	}
+}
+
+static void nbd_size_update(struct nbd_device *nbd)
+{
+	struct nbd_config *config = nbd->config;
+	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
+	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
+	set_capacity(nbd->disk, config->bytesize >> 9);
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
 }
 
-static void nbd_size_set(struct nbd_device *nbd, struct block_device *bdev,
-			loff_t blocksize, loff_t nr_blocks)
+static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
+			 loff_t nr_blocks)
 {
-	nbd->blksize = blocksize;
-	nbd->bytesize = blocksize * nr_blocks;
-	if (nbd_is_connected(nbd))
-		nbd_size_update(nbd, bdev);
+	struct nbd_config *config = nbd->config;
+	config->blksize = blocksize;
+	config->bytesize = blocksize * nr_blocks;
+	nbd_size_update(nbd);
 }
 
-static void nbd_end_request(struct nbd_cmd *cmd)
+static void nbd_complete_rq(struct request *req)
 {
-	struct nbd_device *nbd = cmd->nbd;
-	struct request *req = blk_mq_rq_from_pdu(cmd);
-	int error = req->errors ? -EIO : 0;
+	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
-	dev_dbg(nbd_to_dev(nbd), "request %p: %s\n", cmd,
-		error ? "failed" : "done");
+	dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd,
+		cmd->status ? "failed" : "done");
 
-	blk_mq_complete_request(req, error);
+	blk_mq_end_request(req, cmd->status);
 }
 
 /*
@@ -166,17 +260,18 @@ static void nbd_end_request(struct nbd_cmd *cmd)
  */
 static void sock_shutdown(struct nbd_device *nbd)
 {
+	struct nbd_config *config = nbd->config;
 	int i;
 
-	if (nbd->num_connections == 0)
+	if (config->num_connections == 0)
 		return;
-	if (test_and_set_bit(NBD_DISCONNECTED, &nbd->runtime_flags))
+	if (test_and_set_bit(NBD_DISCONNECTED, &config->runtime_flags))
 		return;
 
-	for (i = 0; i < nbd->num_connections; i++) {
-		struct nbd_sock *nsock = nbd->socks[i];
+	for (i = 0; i < config->num_connections; i++) {
+		struct nbd_sock *nsock = config->socks[i];
 		mutex_lock(&nsock->tx_lock);
-		kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+		nbd_mark_nsock_dead(nbd, nsock, 0);
 		mutex_unlock(&nsock->tx_lock);
 	}
 	dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n");
@@ -187,14 +282,58 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct nbd_device *nbd = cmd->nbd;
+	struct nbd_config *config;
 
-	dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n");
-	set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
-	req->errors++;
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		cmd->status = -EIO;
+		return BLK_EH_HANDLED;
+	}
 
-	mutex_lock(&nbd->config_lock);
+	/* If we are waiting on our dead timer then we could get timeout
+	 * callbacks for our request.  For this we just want to reset the timer
+	 * and let the queue side take care of everything.
+	 */
+	if (!completion_done(&cmd->send_complete)) {
+		nbd_config_put(nbd);
+		return BLK_EH_RESET_TIMER;
+	}
+	config = nbd->config;
+
+	if (config->num_connections > 1) {
+		dev_err_ratelimited(nbd_to_dev(nbd),
+				    "Connection timed out, retrying\n");
+		/*
+		 * Hooray we have more connections, requeue this IO, the submit
+		 * path will put it on a real connection.
+		 */
+		if (config->socks && config->num_connections > 1) {
+			if (cmd->index < config->num_connections) {
+				struct nbd_sock *nsock =
+					config->socks[cmd->index];
+				mutex_lock(&nsock->tx_lock);
+				/* We can have multiple outstanding requests, so
+				 * we don't want to mark the nsock dead if we've
+				 * already reconnected with a new socket, so
+				 * only mark it dead if its the same socket we
+				 * were sent out on.
+				 */
+				if (cmd->cookie == nsock->cookie)
+					nbd_mark_nsock_dead(nbd, nsock, 1);
+				mutex_unlock(&nsock->tx_lock);
+			}
+			blk_mq_requeue_request(req, true);
+			nbd_config_put(nbd);
+			return BLK_EH_NOT_HANDLED;
+		}
+	} else {
+		dev_err_ratelimited(nbd_to_dev(nbd),
+				    "Connection timed out\n");
+	}
+	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
+	cmd->status = -EIO;
 	sock_shutdown(nbd);
-	mutex_unlock(&nbd->config_lock);
+	nbd_config_put(nbd);
+
 	return BLK_EH_HANDLED;
 }
 
@@ -202,9 +341,10 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
  *  Send or receive packet.
  */
 static int sock_xmit(struct nbd_device *nbd, int index, int send,
-		     struct iov_iter *iter, int msg_flags)
+		     struct iov_iter *iter, int msg_flags, int *sent)
 {
-	struct socket *sock = nbd->socks[index]->sock;
+	struct nbd_config *config = nbd->config;
+	struct socket *sock = config->socks[index]->sock;
 	int result;
 	struct msghdr msg;
 	unsigned long pflags = current->flags;
@@ -237,9 +377,11 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 				result = -EPIPE; /* short read */
 			break;
 		}
+		if (sent)
+			*sent += result;
 	} while (msg_data_left(&msg));
 
-	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+	current_restore_flags(pflags, PF_MEMALLOC);
 
 	return result;
 }
@@ -248,6 +390,8 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
+	struct nbd_config *config = nbd->config;
+	struct nbd_sock *nsock = config->socks[index];
 	int result;
 	struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
 	struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
@@ -256,6 +400,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	struct bio *bio;
 	u32 type;
 	u32 tag = blk_mq_unique_tag(req);
+	int sent = nsock->sent, skip = 0;
 
 	iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
 
@@ -277,12 +422,25 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	}
 
 	if (rq_data_dir(req) == WRITE &&
-	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
+	    (config->flags & NBD_FLAG_READ_ONLY)) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Write on read-only\n");
 		return -EIO;
 	}
 
+	/* We did a partial send previously, and we at least sent the whole
+	 * request struct, so just go and send the rest of the pages in the
+	 * request.
+	 */
+	if (sent) {
+		if (sent >= sizeof(request)) {
+			skip = sent - sizeof(request);
+			goto send_pages;
+		}
+		iov_iter_advance(&from, sent);
+	}
+	cmd->index = index;
+	cmd->cookie = nsock->cookie;
 	request.type = htonl(type);
 	if (type != NBD_CMD_FLUSH) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
@@ -294,15 +452,27 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		cmd, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, index, 1, &from,
-			(type == NBD_CMD_WRITE) ? MSG_MORE : 0);
+			(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
 	if (result <= 0) {
+		if (result == -ERESTARTSYS) {
+			/* If we havne't sent anything we can just return BUSY,
+			 * however if we have sent something we need to make
+			 * sure we only allow this req to be sent until we are
+			 * completely done.
+			 */
+			if (sent) {
+				nsock->pending = req;
+				nsock->sent = sent;
+			}
+			return BLK_MQ_RQ_QUEUE_BUSY;
+		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
-		return -EIO;
+		return -EAGAIN;
 	}
-
+send_pages:
 	if (type != NBD_CMD_WRITE)
-		return 0;
+		goto out;
 
 	bio = req->bio;
 	while (bio) {
@@ -318,12 +488,29 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				cmd, bvec.bv_len);
 			iov_iter_bvec(&from, ITER_BVEC | WRITE,
 				      &bvec, 1, bvec.bv_len);
-			result = sock_xmit(nbd, index, 1, &from, flags);
+			if (skip) {
+				if (skip >= iov_iter_count(&from)) {
+					skip -= iov_iter_count(&from);
+					continue;
+				}
+				iov_iter_advance(&from, skip);
+				skip = 0;
+			}
+			result = sock_xmit(nbd, index, 1, &from, flags, &sent);
 			if (result <= 0) {
+				if (result == -ERESTARTSYS) {
+					/* We've already sent the header, we
+					 * have no choice but to set pending and
+					 * return BUSY.
+					 */
+					nsock->pending = req;
+					nsock->sent = sent;
+					return BLK_MQ_RQ_QUEUE_BUSY;
+				}
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
 					result);
-				return -EIO;
+				return -EAGAIN;
 			}
 			/*
 			 * The completion might already have come in,
@@ -336,12 +523,16 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		}
 		bio = next;
 	}
+out:
+	nsock->pending = NULL;
+	nsock->sent = 0;
 	return 0;
 }
 
 /* NULL returned = something went wrong, inform userspace */
 static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 {
+	struct nbd_config *config = nbd->config;
 	int result;
 	struct nbd_reply reply;
 	struct nbd_cmd *cmd;
@@ -353,10 +544,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 
 	reply.magic = 0;
 	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
-	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL);
+	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
 	if (result <= 0) {
-		if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) &&
-		    !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
+		if (!nbd_disconnected(config))
 			dev_err(disk_to_dev(nbd->disk),
 				"Receive control failed (result %d)\n", result);
 		return ERR_PTR(result);
@@ -383,7 +573,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	if (ntohl(reply.error)) {
 		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
-		req->errors++;
+		cmd->status = -EIO;
 		return cmd;
 	}
 
@@ -395,12 +585,23 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		rq_for_each_segment(bvec, req, iter) {
 			iov_iter_bvec(&to, ITER_BVEC | READ,
 				      &bvec, 1, bvec.bv_len);
-			result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL);
+			result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
 					result);
-				req->errors++;
-				return cmd;
+				/*
+				 * If we've disconnected or we only have 1
+				 * connection then we need to make sure we
+				 * complete this request, otherwise error out
+				 * and let the timeout stuff handle resubmitting
+				 * this request onto another connection.
+				 */
+				if (nbd_disconnected(config) ||
+				    config->num_connections <= 1) {
+					cmd->status = -EIO;
+					return cmd;
+				}
+				return ERR_PTR(-EIO);
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
 				cmd, bvec.bv_len);
@@ -412,54 +613,34 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	return cmd;
 }
 
-static ssize_t pid_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct gendisk *disk = dev_to_disk(dev);
-	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
-
-	return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
-}
-
-static struct device_attribute pid_attr = {
-	.attr = { .name = "pid", .mode = S_IRUGO},
-	.show = pid_show,
-};
-
-struct recv_thread_args {
-	struct work_struct work;
-	struct nbd_device *nbd;
-	int index;
-};
-
 static void recv_work(struct work_struct *work)
 {
 	struct recv_thread_args *args = container_of(work,
 						     struct recv_thread_args,
 						     work);
 	struct nbd_device *nbd = args->nbd;
+	struct nbd_config *config = nbd->config;
 	struct nbd_cmd *cmd;
 	int ret = 0;
 
-	BUG_ON(nbd->magic != NBD_MAGIC);
 	while (1) {
 		cmd = nbd_read_stat(nbd, args->index);
 		if (IS_ERR(cmd)) {
+			struct nbd_sock *nsock = config->socks[args->index];
+
+			mutex_lock(&nsock->tx_lock);
+			nbd_mark_nsock_dead(nbd, nsock, 1);
+			mutex_unlock(&nsock->tx_lock);
 			ret = PTR_ERR(cmd);
 			break;
 		}
 
-		nbd_end_request(cmd);
+		blk_mq_complete_request(blk_mq_rq_from_pdu(cmd));
 	}
-
-	/*
-	 * We got an error, shut everybody down if this wasn't the result of a
-	 * disconnect request.
-	 */
-	if (ret && !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
-		sock_shutdown(nbd);
-	atomic_dec(&nbd->recv_threads);
-	wake_up(&nbd->recv_wq);
+	atomic_dec(&config->recv_threads);
+	wake_up(&config->recv_wq);
+	nbd_config_put(nbd);
+	kfree(args);
 }
 
 static void nbd_clear_req(struct request *req, void *data, bool reserved)
@@ -469,68 +650,154 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved)
 	if (!blk_mq_request_started(req))
 		return;
 	cmd = blk_mq_rq_to_pdu(req);
-	req->errors++;
-	nbd_end_request(cmd);
+	cmd->status = -EIO;
+	blk_mq_complete_request(req);
 }
 
 static void nbd_clear_que(struct nbd_device *nbd)
 {
-	BUG_ON(nbd->magic != NBD_MAGIC);
-
+	blk_mq_stop_hw_queues(nbd->disk->queue);
 	blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL);
+	blk_mq_start_hw_queues(nbd->disk->queue);
 	dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n");
 }
 
+static int find_fallback(struct nbd_device *nbd, int index)
+{
+	struct nbd_config *config = nbd->config;
+	int new_index = -1;
+	struct nbd_sock *nsock = config->socks[index];
+	int fallback = nsock->fallback_index;
+
+	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+		return new_index;
 
-static void nbd_handle_cmd(struct nbd_cmd *cmd, int index)
+	if (config->num_connections <= 1) {
+		dev_err_ratelimited(disk_to_dev(nbd->disk),
+				    "Attempted send on invalid socket\n");
+		return new_index;
+	}
+
+	if (fallback >= 0 && fallback < config->num_connections &&
+	    !config->socks[fallback]->dead)
+		return fallback;
+
+	if (nsock->fallback_index < 0 ||
+	    nsock->fallback_index >= config->num_connections ||
+	    config->socks[nsock->fallback_index]->dead) {
+		int i;
+		for (i = 0; i < config->num_connections; i++) {
+			if (i == index)
+				continue;
+			if (!config->socks[i]->dead) {
+				new_index = i;
+				break;
+			}
+		}
+		nsock->fallback_index = new_index;
+		if (new_index < 0) {
+			dev_err_ratelimited(disk_to_dev(nbd->disk),
+					    "Dead connection, failed to find a fallback\n");
+			return new_index;
+		}
+	}
+	new_index = nsock->fallback_index;
+	return new_index;
+}
+
+static int wait_for_reconnect(struct nbd_device *nbd)
+{
+	struct nbd_config *config = nbd->config;
+	if (!config->dead_conn_timeout)
+		return 0;
+	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+		return 0;
+	wait_event_interruptible_timeout(config->conn_wait,
+					 atomic_read(&config->live_connections),
+					 config->dead_conn_timeout);
+	return atomic_read(&config->live_connections);
+}
+
+static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 	struct nbd_device *nbd = cmd->nbd;
+	struct nbd_config *config;
 	struct nbd_sock *nsock;
+	int ret;
 
-	if (index >= nbd->num_connections) {
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Attempted send on invalid socket\n");
-		goto error_out;
+				    "Socks array is empty\n");
+		return -EINVAL;
 	}
+	config = nbd->config;
 
-	if (test_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) {
+	if (index >= config->num_connections) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Attempted send on closed socket\n");
-		goto error_out;
+				    "Attempted send on invalid socket\n");
+		nbd_config_put(nbd);
+		return -EINVAL;
 	}
-
-	req->errors = 0;
-
-	nsock = nbd->socks[index];
+	cmd->status = 0;
+again:
+	nsock = config->socks[index];
 	mutex_lock(&nsock->tx_lock);
-	if (unlikely(!nsock->sock)) {
+	if (nsock->dead) {
+		int old_index = index;
+		index = find_fallback(nbd, index);
 		mutex_unlock(&nsock->tx_lock);
-		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Attempted send on closed socket\n");
-		goto error_out;
+		if (index < 0) {
+			if (wait_for_reconnect(nbd)) {
+				index = old_index;
+				goto again;
+			}
+			/* All the sockets should already be down at this point,
+			 * we just want to make sure that DISCONNECTED is set so
+			 * any requests that come in that were queue'ed waiting
+			 * for the reconnect timer don't trigger the timer again
+			 * and instead just error out.
+			 */
+			sock_shutdown(nbd);
+			nbd_config_put(nbd);
+			return -EIO;
+		}
+		goto again;
 	}
 
-	if (nbd_send_cmd(nbd, cmd, index) != 0) {
+	/* Handle the case that we have a pending request that was partially
+	 * transmitted that _has_ to be serviced first.  We need to call requeue
+	 * here so that it gets put _after_ the request that is already on the
+	 * dispatch list.
+	 */
+	if (unlikely(nsock->pending && nsock->pending != req)) {
+		blk_mq_requeue_request(req, true);
+		ret = 0;
+		goto out;
+	}
+	/*
+	 * Some failures are related to the link going down, so anything that
+	 * returns EAGAIN can be retried on a different socket.
+	 */
+	ret = nbd_send_cmd(nbd, cmd, index);
+	if (ret == -EAGAIN) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Request send failed\n");
-		req->errors++;
-		nbd_end_request(cmd);
+				    "Request send failed trying another connection\n");
+		nbd_mark_nsock_dead(nbd, nsock, 1);
+		mutex_unlock(&nsock->tx_lock);
+		goto again;
 	}
-
+out:
 	mutex_unlock(&nsock->tx_lock);
-
-	return;
-
-error_out:
-	req->errors++;
-	nbd_end_request(cmd);
+	nbd_config_put(nbd);
+	return ret;
 }
 
 static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 			const struct blk_mq_queue_data *bd)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+	int ret;
 
 	/*
 	 * Since we look at the bio's to send the request over the network we
@@ -543,15 +810,26 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 */
 	init_completion(&cmd->send_complete);
 	blk_mq_start_request(bd->rq);
-	nbd_handle_cmd(cmd, hctx->queue_num);
+
+	/* We can be called directly from the user space process, which means we
+	 * could possibly have signals pending so our sendmsg will fail.  In
+	 * this case we need to return that we are busy, otherwise error out as
+	 * appropriate.
+	 */
+	ret = nbd_handle_cmd(cmd, hctx->queue_num);
+	if (ret < 0)
+		ret = BLK_MQ_RQ_QUEUE_ERROR;
+	if (!ret)
+		ret = BLK_MQ_RQ_QUEUE_OK;
 	complete(&cmd->send_complete);
 
-	return BLK_MQ_RQ_QUEUE_OK;
+	return ret;
 }
 
-static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
-			  unsigned long arg)
+static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
+			  bool netlink)
 {
+	struct nbd_config *config = nbd->config;
 	struct socket *sock;
 	struct nbd_sock **socks;
 	struct nbd_sock *nsock;
@@ -561,62 +839,132 @@ static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
 	if (!sock)
 		return err;
 
-	if (!nbd->task_setup)
+	if (!netlink && !nbd->task_setup &&
+	    !test_bit(NBD_BOUND, &config->runtime_flags))
 		nbd->task_setup = current;
-	if (nbd->task_setup != current) {
+
+	if (!netlink &&
+	    (nbd->task_setup != current ||
+	     test_bit(NBD_BOUND, &config->runtime_flags))) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Device being setup by another task");
-		return -EINVAL;
+		sockfd_put(sock);
+		return -EBUSY;
 	}
 
-	socks = krealloc(nbd->socks, (nbd->num_connections + 1) *
+	socks = krealloc(config->socks, (config->num_connections + 1) *
 			 sizeof(struct nbd_sock *), GFP_KERNEL);
-	if (!socks)
+	if (!socks) {
+		sockfd_put(sock);
 		return -ENOMEM;
+	}
 	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
-	if (!nsock)
+	if (!nsock) {
+		sockfd_put(sock);
 		return -ENOMEM;
+	}
 
-	nbd->socks = socks;
+	config->socks = socks;
 
+	nsock->fallback_index = -1;
+	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
 	nsock->sock = sock;
-	socks[nbd->num_connections++] = nsock;
+	nsock->pending = NULL;
+	nsock->sent = 0;
+	nsock->cookie = 0;
+	socks[config->num_connections++] = nsock;
+	atomic_inc(&config->live_connections);
 
-	if (max_part)
-		bdev->bd_invalidated = 1;
 	return 0;
 }
 
+static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
+{
+	struct nbd_config *config = nbd->config;
+	struct socket *sock, *old;
+	struct recv_thread_args *args;
+	int i;
+	int err;
+
+	sock = sockfd_lookup(arg, &err);
+	if (!sock)
+		return err;
+
+	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	if (!args) {
+		sockfd_put(sock);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < config->num_connections; i++) {
+		struct nbd_sock *nsock = config->socks[i];
+
+		if (!nsock->dead)
+			continue;
+
+		mutex_lock(&nsock->tx_lock);
+		if (!nsock->dead) {
+			mutex_unlock(&nsock->tx_lock);
+			continue;
+		}
+		sk_set_memalloc(sock->sk);
+		atomic_inc(&config->recv_threads);
+		refcount_inc(&nbd->config_refs);
+		old = nsock->sock;
+		nsock->fallback_index = -1;
+		nsock->sock = sock;
+		nsock->dead = false;
+		INIT_WORK(&args->work, recv_work);
+		args->index = i;
+		args->nbd = nbd;
+		nsock->cookie++;
+		mutex_unlock(&nsock->tx_lock);
+		sockfd_put(old);
+
+		/* We take the tx_mutex in an error path in the recv_work, so we
+		 * need to queue_work outside of the tx_mutex.
+		 */
+		queue_work(recv_workqueue, &args->work);
+
+		atomic_inc(&config->live_connections);
+		wake_up(&config->conn_wait);
+		return 0;
+	}
+	sockfd_put(sock);
+	kfree(args);
+	return -ENOSPC;
+}
+
 /* Reset all properties of an NBD device */
 static void nbd_reset(struct nbd_device *nbd)
 {
-	nbd->runtime_flags = 0;
-	nbd->blksize = 1024;
-	nbd->bytesize = 0;
-	set_capacity(nbd->disk, 0);
-	nbd->flags = 0;
+	nbd->config = NULL;
 	nbd->tag_set.timeout = 0;
 	queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 }
 
 static void nbd_bdev_reset(struct block_device *bdev)
 {
-	set_device_ro(bdev, false);
-	bdev->bd_inode->i_size = 0;
+	if (bdev->bd_openers > 1)
+		return;
+	bd_set_size(bdev, 0);
 	if (max_part > 0) {
 		blkdev_reread_part(bdev);
 		bdev->bd_invalidated = 1;
 	}
 }
 
-static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_parse_flags(struct nbd_device *nbd)
 {
-	if (nbd->flags & NBD_FLAG_READ_ONLY)
-		set_device_ro(bdev, true);
-	if (nbd->flags & NBD_FLAG_SEND_TRIM)
+	struct nbd_config *config = nbd->config;
+	if (config->flags & NBD_FLAG_READ_ONLY)
+		set_disk_ro(nbd->disk, true);
+	else
+		set_disk_ro(nbd->disk, false);
+	if (config->flags & NBD_FLAG_SEND_TRIM)
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
-	if (nbd->flags & NBD_FLAG_SEND_FLUSH)
+	if (config->flags & NBD_FLAG_SEND_FLUSH)
 		blk_queue_write_cache(nbd->disk->queue, true, false);
 	else
 		blk_queue_write_cache(nbd->disk->queue, false, false);
@@ -624,6 +972,7 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
 
 static void send_disconnects(struct nbd_device *nbd)
 {
+	struct nbd_config *config = nbd->config;
 	struct nbd_request request = {
 		.magic = htonl(NBD_REQUEST_MAGIC),
 		.type = htonl(NBD_CMD_DISC),
@@ -632,163 +981,184 @@ static void send_disconnects(struct nbd_device *nbd)
 	struct iov_iter from;
 	int i, ret;
 
-	for (i = 0; i < nbd->num_connections; i++) {
+	for (i = 0; i < config->num_connections; i++) {
 		iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
-		ret = sock_xmit(nbd, i, 1, &from, 0);
+		ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
 		if (ret <= 0)
 			dev_err(disk_to_dev(nbd->disk),
 				"Send disconnect failed %d\n", ret);
 	}
 }
 
-static int nbd_disconnect(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_disconnect(struct nbd_device *nbd)
 {
-	dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
-	if (!nbd->socks)
-		return -EINVAL;
-
-	mutex_unlock(&nbd->config_lock);
-	fsync_bdev(bdev);
-	mutex_lock(&nbd->config_lock);
-
-	/* Check again after getting mutex back.  */
-	if (!nbd->socks)
-		return -EINVAL;
+	struct nbd_config *config = nbd->config;
 
+	dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
 	if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED,
-			      &nbd->runtime_flags))
+			      &config->runtime_flags))
 		send_disconnects(nbd);
 	return 0;
 }
 
-static int nbd_clear_sock(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_clear_sock(struct nbd_device *nbd)
 {
 	sock_shutdown(nbd);
 	nbd_clear_que(nbd);
-	kill_bdev(bdev);
-	nbd_bdev_reset(bdev);
-	/*
-	 * We want to give the run thread a chance to wait for everybody
-	 * to clean up and then do it's own cleanup.
-	 */
-	if (!test_bit(NBD_RUNNING, &nbd->runtime_flags) &&
-	    nbd->num_connections) {
-		int i;
+	nbd->task_setup = NULL;
+}
 
-		for (i = 0; i < nbd->num_connections; i++) {
-			sockfd_put(nbd->socks[i]->sock);
-			kfree(nbd->socks[i]);
+static void nbd_config_put(struct nbd_device *nbd)
+{
+	if (refcount_dec_and_mutex_lock(&nbd->config_refs,
+					&nbd->config_lock)) {
+		struct nbd_config *config = nbd->config;
+		nbd_dev_dbg_close(nbd);
+		nbd_size_clear(nbd);
+		if (test_and_clear_bit(NBD_HAS_PID_FILE,
+				       &config->runtime_flags))
+			device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+		nbd->task_recv = NULL;
+		nbd_clear_sock(nbd);
+		if (config->num_connections) {
+			int i;
+			for (i = 0; i < config->num_connections; i++) {
+				sockfd_put(config->socks[i]->sock);
+				kfree(config->socks[i]);
+			}
+			kfree(config->socks);
 		}
-		kfree(nbd->socks);
-		nbd->socks = NULL;
-		nbd->num_connections = 0;
-	}
-	nbd->task_setup = NULL;
+		nbd_reset(nbd);
 
-	return 0;
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		module_put(THIS_MODULE);
+	}
 }
 
-static int nbd_start_device(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_start_device(struct nbd_device *nbd)
 {
-	struct recv_thread_args *args;
-	int num_connections = nbd->num_connections;
+	struct nbd_config *config = nbd->config;
+	int num_connections = config->num_connections;
 	int error = 0, i;
 
 	if (nbd->task_recv)
 		return -EBUSY;
-	if (!nbd->socks)
+	if (!config->socks)
 		return -EINVAL;
 	if (num_connections > 1 &&
-	    !(nbd->flags & NBD_FLAG_CAN_MULTI_CONN)) {
+	    !(config->flags & NBD_FLAG_CAN_MULTI_CONN)) {
 		dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n");
-		error = -EINVAL;
-		goto out_err;
+		return -EINVAL;
 	}
 
-	set_bit(NBD_RUNNING, &nbd->runtime_flags);
-	blk_mq_update_nr_hw_queues(&nbd->tag_set, nbd->num_connections);
-	args = kcalloc(num_connections, sizeof(*args), GFP_KERNEL);
-	if (!args) {
-		error = -ENOMEM;
-		goto out_err;
-	}
+	blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
 	nbd->task_recv = current;
-	mutex_unlock(&nbd->config_lock);
 
-	nbd_parse_flags(nbd, bdev);
+	nbd_parse_flags(nbd);
 
 	error = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (error) {
 		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
-		goto out_recv;
+		return error;
 	}
-
-	nbd_size_update(nbd, bdev);
+	set_bit(NBD_HAS_PID_FILE, &config->runtime_flags);
 
 	nbd_dev_dbg_init(nbd);
 	for (i = 0; i < num_connections; i++) {
-		sk_set_memalloc(nbd->socks[i]->sock->sk);
-		atomic_inc(&nbd->recv_threads);
-		INIT_WORK(&args[i].work, recv_work);
-		args[i].nbd = nbd;
-		args[i].index = i;
-		queue_work(recv_workqueue, &args[i].work);
-	}
-	wait_event_interruptible(nbd->recv_wq,
-				 atomic_read(&nbd->recv_threads) == 0);
-	for (i = 0; i < num_connections; i++)
-		flush_work(&args[i].work);
-	nbd_dev_dbg_close(nbd);
-	nbd_size_clear(nbd, bdev);
-	device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
-out_recv:
-	mutex_lock(&nbd->config_lock);
-	nbd->task_recv = NULL;
-out_err:
-	clear_bit(NBD_RUNNING, &nbd->runtime_flags);
-	nbd_clear_sock(nbd, bdev);
+		struct recv_thread_args *args;
 
+		args = kzalloc(sizeof(*args), GFP_KERNEL);
+		if (!args) {
+			sock_shutdown(nbd);
+			return -ENOMEM;
+		}
+		sk_set_memalloc(config->socks[i]->sock->sk);
+		atomic_inc(&config->recv_threads);
+		refcount_inc(&nbd->config_refs);
+		INIT_WORK(&args->work, recv_work);
+		args->nbd = nbd;
+		args->index = i;
+		queue_work(recv_workqueue, &args->work);
+	}
+	return error;
+}
+
+static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev)
+{
+	struct nbd_config *config = nbd->config;
+	int ret;
+
+	ret = nbd_start_device(nbd);
+	if (ret)
+		return ret;
+
+	bd_set_size(bdev, config->bytesize);
+	if (max_part)
+		bdev->bd_invalidated = 1;
+	mutex_unlock(&nbd->config_lock);
+	ret = wait_event_interruptible(config->recv_wq,
+					 atomic_read(&config->recv_threads) == 0);
+	if (ret)
+		sock_shutdown(nbd);
+	mutex_lock(&nbd->config_lock);
+	bd_set_size(bdev, 0);
 	/* user requested, ignore socket errors */
-	if (test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
-		error = 0;
-	if (test_bit(NBD_TIMEDOUT, &nbd->runtime_flags))
-		error = -ETIMEDOUT;
+	if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
+		ret = 0;
+	if (test_bit(NBD_TIMEDOUT, &config->runtime_flags))
+		ret = -ETIMEDOUT;
+	return ret;
+}
 
-	nbd_reset(nbd);
-	return error;
+static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
+				 struct block_device *bdev)
+{
+	sock_shutdown(nbd);
+	kill_bdev(bdev);
+	nbd_bdev_reset(bdev);
+	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+			       &nbd->config->runtime_flags))
+		nbd_config_put(nbd);
 }
 
 /* Must be called with config_lock held */
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
 {
+	struct nbd_config *config = nbd->config;
+
 	switch (cmd) {
 	case NBD_DISCONNECT:
-		return nbd_disconnect(nbd, bdev);
+		return nbd_disconnect(nbd);
 	case NBD_CLEAR_SOCK:
-		return nbd_clear_sock(nbd, bdev);
+		nbd_clear_sock_ioctl(nbd, bdev);
+		return 0;
 	case NBD_SET_SOCK:
-		return nbd_add_socket(nbd, bdev, arg);
+		return nbd_add_socket(nbd, arg, false);
 	case NBD_SET_BLKSIZE:
-		nbd_size_set(nbd, bdev, arg,
-			     div_s64(nbd->bytesize, arg));
+		nbd_size_set(nbd, arg,
+			     div_s64(config->bytesize, arg));
 		return 0;
 	case NBD_SET_SIZE:
-		nbd_size_set(nbd, bdev, nbd->blksize,
-			     div_s64(arg, nbd->blksize));
+		nbd_size_set(nbd, config->blksize,
+			     div_s64(arg, config->blksize));
 		return 0;
 	case NBD_SET_SIZE_BLOCKS:
-		nbd_size_set(nbd, bdev, nbd->blksize, arg);
+		nbd_size_set(nbd, config->blksize, arg);
 		return 0;
 	case NBD_SET_TIMEOUT:
-		nbd->tag_set.timeout = arg * HZ;
+		if (arg) {
+			nbd->tag_set.timeout = arg * HZ;
+			blk_queue_rq_timeout(nbd->disk->queue, arg * HZ);
+		}
 		return 0;
 
 	case NBD_SET_FLAGS:
-		nbd->flags = arg;
+		config->flags = arg;
 		return 0;
 	case NBD_DO_IT:
-		return nbd_start_device(nbd, bdev);
+		return nbd_start_device_ioctl(nbd, bdev);
 	case NBD_CLEAR_QUE:
 		/*
 		 * This is for compatibility only.  The queue is always cleared
@@ -809,23 +1179,92 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct nbd_device *nbd = bdev->bd_disk->private_data;
-	int error;
+	struct nbd_config *config = nbd->config;
+	int error = -EINVAL;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	BUG_ON(nbd->magic != NBD_MAGIC);
-
 	mutex_lock(&nbd->config_lock);
-	error = __nbd_ioctl(bdev, nbd, cmd, arg);
-	mutex_unlock(&nbd->config_lock);
 
+	/* Don't allow ioctl operations on a nbd device that was created with
+	 * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine.
+	 */
+	if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+	    (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK))
+		error = __nbd_ioctl(bdev, nbd, cmd, arg);
+	else
+		dev_err(nbd_to_dev(nbd), "Cannot use ioctl interface on a netlink controlled device.\n");
+	mutex_unlock(&nbd->config_lock);
 	return error;
 }
 
+static struct nbd_config *nbd_alloc_config(void)
+{
+	struct nbd_config *config;
+
+	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
+	if (!config)
+		return NULL;
+	atomic_set(&config->recv_threads, 0);
+	init_waitqueue_head(&config->recv_wq);
+	init_waitqueue_head(&config->conn_wait);
+	config->blksize = 1024;
+	atomic_set(&config->live_connections, 0);
+	try_module_get(THIS_MODULE);
+	return config;
+}
+
+static int nbd_open(struct block_device *bdev, fmode_t mode)
+{
+	struct nbd_device *nbd;
+	int ret = 0;
+
+	mutex_lock(&nbd_index_mutex);
+	nbd = bdev->bd_disk->private_data;
+	if (!nbd) {
+		ret = -ENXIO;
+		goto out;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		ret = -ENXIO;
+		goto out;
+	}
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		struct nbd_config *config;
+
+		mutex_lock(&nbd->config_lock);
+		if (refcount_inc_not_zero(&nbd->config_refs)) {
+			mutex_unlock(&nbd->config_lock);
+			goto out;
+		}
+		config = nbd->config = nbd_alloc_config();
+		if (!config) {
+			ret = -ENOMEM;
+			mutex_unlock(&nbd->config_lock);
+			goto out;
+		}
+		refcount_set(&nbd->config_refs, 1);
+		refcount_inc(&nbd->refs);
+		mutex_unlock(&nbd->config_lock);
+	}
+out:
+	mutex_unlock(&nbd_index_mutex);
+	return ret;
+}
+
+static void nbd_release(struct gendisk *disk, fmode_t mode)
+{
+	struct nbd_device *nbd = disk->private_data;
+	nbd_config_put(nbd);
+	nbd_put(nbd);
+}
+
 static const struct block_device_operations nbd_fops =
 {
 	.owner =	THIS_MODULE,
+	.open =		nbd_open,
+	.release =	nbd_release,
 	.ioctl =	nbd_ioctl,
 	.compat_ioctl =	nbd_ioctl,
 };
@@ -857,7 +1296,7 @@ static const struct file_operations nbd_dbg_tasks_ops = {
 static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
 {
 	struct nbd_device *nbd = s->private;
-	u32 flags = nbd->flags;
+	u32 flags = nbd->config->flags;
 
 	seq_printf(s, "Hex: 0x%08x\n\n", flags);
 
@@ -890,6 +1329,7 @@ static const struct file_operations nbd_dbg_flags_ops = {
 static int nbd_dev_dbg_init(struct nbd_device *nbd)
 {
 	struct dentry *dir;
+	struct nbd_config *config = nbd->config;
 
 	if (!nbd_dbg_dir)
 		return -EIO;
@@ -900,12 +1340,12 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 			nbd_name(nbd));
 		return -EIO;
 	}
-	nbd->dbg_dir = dir;
+	config->dbg_dir = dir;
 
 	debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_ops);
-	debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
+	debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize);
 	debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout);
-	debugfs_create_u64("blocksize", 0444, dir, &nbd->blksize);
+	debugfs_create_u64("blocksize", 0444, dir, &config->blksize);
 	debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
 
 	return 0;
@@ -913,7 +1353,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 
 static void nbd_dev_dbg_close(struct nbd_device *nbd)
 {
-	debugfs_remove_recursive(nbd->dbg_dir);
+	debugfs_remove_recursive(nbd->config->dbg_dir);
 }
 
 static int nbd_dbg_init(void)
@@ -965,25 +1405,13 @@ static int nbd_init_request(void *data, struct request *rq,
 	return 0;
 }
 
-static struct blk_mq_ops nbd_mq_ops = {
+static const struct blk_mq_ops nbd_mq_ops = {
 	.queue_rq	= nbd_queue_rq,
+	.complete	= nbd_complete_rq,
 	.init_request	= nbd_init_request,
 	.timeout	= nbd_xmit_timeout,
 };
 
-static void nbd_dev_remove(struct nbd_device *nbd)
-{
-	struct gendisk *disk = nbd->disk;
-	nbd->magic = 0;
-	if (disk) {
-		del_gendisk(disk);
-		blk_cleanup_queue(disk->queue);
-		blk_mq_free_tag_set(&nbd->tag_set);
-		put_disk(disk);
-	}
-	kfree(nbd);
-}
-
 static int nbd_dev_add(int index)
 {
 	struct nbd_device *nbd;
@@ -1012,6 +1440,7 @@ static int nbd_dev_add(int index)
 	if (err < 0)
 		goto out_free_disk;
 
+	nbd->index = index;
 	nbd->disk = disk;
 	nbd->tag_set.ops = &nbd_mq_ops;
 	nbd->tag_set.nr_hw_queues = 1;
@@ -1040,20 +1469,23 @@ static int nbd_dev_add(int index)
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	disk->queue->limits.discard_granularity = 512;
 	blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
-	disk->queue->limits.discard_zeroes_data = 0;
+	blk_queue_max_segment_size(disk->queue, UINT_MAX);
+	blk_queue_max_segments(disk->queue, USHRT_MAX);
 	blk_queue_max_hw_sectors(disk->queue, 65536);
 	disk->queue->limits.max_sectors = 256;
 
-	nbd->magic = NBD_MAGIC;
 	mutex_init(&nbd->config_lock);
+	refcount_set(&nbd->config_refs, 0);
+	refcount_set(&nbd->refs, 1);
+	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
 	disk->first_minor = index << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
 	sprintf(disk->disk_name, "nbd%d", index);
-	init_waitqueue_head(&nbd->recv_wq);
 	nbd_reset(nbd);
 	add_disk(disk);
+	nbd_total_devices++;
 	return index;
 
 out_free_tags:
@@ -1068,10 +1500,535 @@ out:
 	return err;
 }
 
-/*
- * And here should be modules and kernel interface 
- *  (Just smiley confuses emacs :-)
+static int find_free_cb(int id, void *ptr, void *data)
+{
+	struct nbd_device *nbd = ptr;
+	struct nbd_device **found = data;
+
+	if (!refcount_read(&nbd->config_refs)) {
+		*found = nbd;
+		return 1;
+	}
+	return 0;
+}
+
+/* Netlink interface. */
+static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
+	[NBD_ATTR_INDEX]		=	{ .type = NLA_U32 },
+	[NBD_ATTR_SIZE_BYTES]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_BLOCK_SIZE_BYTES]	=	{ .type = NLA_U64 },
+	[NBD_ATTR_TIMEOUT]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_SERVER_FLAGS]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_CLIENT_FLAGS]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_SOCKETS]		=	{ .type = NLA_NESTED},
+	[NBD_ATTR_DEAD_CONN_TIMEOUT]	=	{ .type = NLA_U64 },
+	[NBD_ATTR_DEVICE_LIST]		=	{ .type = NLA_NESTED},
+};
+
+static struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
+	[NBD_SOCK_FD]			=	{ .type = NLA_U32 },
+};
+
+/* We don't use this right now since we don't parse the incoming list, but we
+ * still want it here so userspace knows what to expect.
  */
+static struct nla_policy __attribute__((unused))
+nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
+	[NBD_DEVICE_INDEX]		=	{ .type = NLA_U32 },
+	[NBD_DEVICE_CONNECTED]		=	{ .type = NLA_U8 },
+};
+
+static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nbd_device *nbd = NULL;
+	struct nbd_config *config;
+	int index = -1;
+	int ret;
+	bool put_dev = false;
+
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (info->attrs[NBD_ATTR_INDEX])
+		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+	if (!info->attrs[NBD_ATTR_SOCKETS]) {
+		printk(KERN_ERR "nbd: must specify at least one socket\n");
+		return -EINVAL;
+	}
+	if (!info->attrs[NBD_ATTR_SIZE_BYTES]) {
+		printk(KERN_ERR "nbd: must specify a size in bytes for the device\n");
+		return -EINVAL;
+	}
+again:
+	mutex_lock(&nbd_index_mutex);
+	if (index == -1) {
+		ret = idr_for_each(&nbd_index_idr, &find_free_cb, &nbd);
+		if (ret == 0) {
+			int new_index;
+			new_index = nbd_dev_add(-1);
+			if (new_index < 0) {
+				mutex_unlock(&nbd_index_mutex);
+				printk(KERN_ERR "nbd: failed to add new device\n");
+				return ret;
+			}
+			nbd = idr_find(&nbd_index_idr, new_index);
+		}
+	} else {
+		nbd = idr_find(&nbd_index_idr, index);
+	}
+	if (!nbd) {
+		printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+		       index);
+		mutex_unlock(&nbd_index_mutex);
+		return -EINVAL;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		mutex_unlock(&nbd_index_mutex);
+		if (index == -1)
+			goto again;
+		printk(KERN_ERR "nbd: device at index %d is going down\n",
+		       index);
+		return -EINVAL;
+	}
+	mutex_unlock(&nbd_index_mutex);
+
+	mutex_lock(&nbd->config_lock);
+	if (refcount_read(&nbd->config_refs)) {
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		if (index == -1)
+			goto again;
+		printk(KERN_ERR "nbd: nbd%d already in use\n", index);
+		return -EBUSY;
+	}
+	if (WARN_ON(nbd->config)) {
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		return -EINVAL;
+	}
+	config = nbd->config = nbd_alloc_config();
+	if (!nbd->config) {
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		printk(KERN_ERR "nbd: couldn't allocate config\n");
+		return -ENOMEM;
+	}
+	refcount_set(&nbd->config_refs, 1);
+	set_bit(NBD_BOUND, &config->runtime_flags);
+
+	if (info->attrs[NBD_ATTR_SIZE_BYTES]) {
+		u64 bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]);
+		nbd_size_set(nbd, config->blksize,
+			     div64_u64(bytes, config->blksize));
+	}
+	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
+		u64 bsize =
+			nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+		nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
+	}
+	if (info->attrs[NBD_ATTR_TIMEOUT]) {
+		u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+		nbd->tag_set.timeout = timeout * HZ;
+		blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+	}
+	if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+		config->dead_conn_timeout =
+			nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+		config->dead_conn_timeout *= HZ;
+	}
+	if (info->attrs[NBD_ATTR_SERVER_FLAGS])
+		config->flags =
+			nla_get_u64(info->attrs[NBD_ATTR_SERVER_FLAGS]);
+	if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+		u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+		if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+			set_bit(NBD_DESTROY_ON_DISCONNECT,
+				&config->runtime_flags);
+			put_dev = true;
+		}
+	}
+
+	if (info->attrs[NBD_ATTR_SOCKETS]) {
+		struct nlattr *attr;
+		int rem, fd;
+
+		nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+				    rem) {
+			struct nlattr *socks[NBD_SOCK_MAX+1];
+
+			if (nla_type(attr) != NBD_SOCK_ITEM) {
+				printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+					       nbd_sock_policy, info->extack);
+			if (ret != 0) {
+				printk(KERN_ERR "nbd: error processing sock list\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!socks[NBD_SOCK_FD])
+				continue;
+			fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+			ret = nbd_add_socket(nbd, fd, true);
+			if (ret)
+				goto out;
+		}
+	}
+	ret = nbd_start_device(nbd);
+out:
+	mutex_unlock(&nbd->config_lock);
+	if (!ret) {
+		set_bit(NBD_HAS_CONFIG_REF, &config->runtime_flags);
+		refcount_inc(&nbd->config_refs);
+		nbd_connect_reply(info, nbd->index);
+	}
+	nbd_config_put(nbd);
+	if (put_dev)
+		nbd_put(nbd);
+	return ret;
+}
+
+static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nbd_device *nbd;
+	int index;
+
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!info->attrs[NBD_ATTR_INDEX]) {
+		printk(KERN_ERR "nbd: must specify an index to disconnect\n");
+		return -EINVAL;
+	}
+	index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+	mutex_lock(&nbd_index_mutex);
+	nbd = idr_find(&nbd_index_idr, index);
+	if (!nbd) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+		       index);
+		return -EINVAL;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: device at index %d is going down\n",
+		       index);
+		return -EINVAL;
+	}
+	mutex_unlock(&nbd_index_mutex);
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		nbd_put(nbd);
+		return 0;
+	}
+	mutex_lock(&nbd->config_lock);
+	nbd_disconnect(nbd);
+	mutex_unlock(&nbd->config_lock);
+	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+			       &nbd->config->runtime_flags))
+		nbd_config_put(nbd);
+	nbd_config_put(nbd);
+	nbd_put(nbd);
+	return 0;
+}
+
+static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nbd_device *nbd = NULL;
+	struct nbd_config *config;
+	int index;
+	int ret = -EINVAL;
+	bool put_dev = false;
+
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!info->attrs[NBD_ATTR_INDEX]) {
+		printk(KERN_ERR "nbd: must specify a device to reconfigure\n");
+		return -EINVAL;
+	}
+	index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+	mutex_lock(&nbd_index_mutex);
+	nbd = idr_find(&nbd_index_idr, index);
+	if (!nbd) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: couldn't find a device at index %d\n",
+		       index);
+		return -EINVAL;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: device at index %d is going down\n",
+		       index);
+		return -EINVAL;
+	}
+	mutex_unlock(&nbd_index_mutex);
+
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		dev_err(nbd_to_dev(nbd),
+			"not configured, cannot reconfigure\n");
+		nbd_put(nbd);
+		return -EINVAL;
+	}
+
+	mutex_lock(&nbd->config_lock);
+	config = nbd->config;
+	if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+	    !nbd->task_recv) {
+		dev_err(nbd_to_dev(nbd),
+			"not configured, cannot reconfigure\n");
+		goto out;
+	}
+
+	if (info->attrs[NBD_ATTR_TIMEOUT]) {
+		u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+		nbd->tag_set.timeout = timeout * HZ;
+		blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+	}
+	if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+		config->dead_conn_timeout =
+			nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+		config->dead_conn_timeout *= HZ;
+	}
+	if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+		u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+		if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+			if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT,
+					      &config->runtime_flags))
+				put_dev = true;
+		} else {
+			if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT,
+					       &config->runtime_flags))
+				refcount_inc(&nbd->refs);
+		}
+	}
+
+	if (info->attrs[NBD_ATTR_SOCKETS]) {
+		struct nlattr *attr;
+		int rem, fd;
+
+		nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+				    rem) {
+			struct nlattr *socks[NBD_SOCK_MAX+1];
+
+			if (nla_type(attr) != NBD_SOCK_ITEM) {
+				printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+					       nbd_sock_policy, info->extack);
+			if (ret != 0) {
+				printk(KERN_ERR "nbd: error processing sock list\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!socks[NBD_SOCK_FD])
+				continue;
+			fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+			ret = nbd_reconnect_socket(nbd, fd);
+			if (ret) {
+				if (ret == -ENOSPC)
+					ret = 0;
+				goto out;
+			}
+			dev_info(nbd_to_dev(nbd), "reconnected socket\n");
+		}
+	}
+out:
+	mutex_unlock(&nbd->config_lock);
+	nbd_config_put(nbd);
+	nbd_put(nbd);
+	if (put_dev)
+		nbd_put(nbd);
+	return ret;
+}
+
+static const struct genl_ops nbd_connect_genl_ops[] = {
+	{
+		.cmd	= NBD_CMD_CONNECT,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_connect,
+	},
+	{
+		.cmd	= NBD_CMD_DISCONNECT,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_disconnect,
+	},
+	{
+		.cmd	= NBD_CMD_RECONFIGURE,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_reconfigure,
+	},
+	{
+		.cmd	= NBD_CMD_STATUS,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_status,
+	},
+};
+
+static const struct genl_multicast_group nbd_mcast_grps[] = {
+	{ .name = NBD_GENL_MCAST_GROUP_NAME, },
+};
+
+static struct genl_family nbd_genl_family __ro_after_init = {
+	.hdrsize	= 0,
+	.name		= NBD_GENL_FAMILY_NAME,
+	.version	= NBD_GENL_VERSION,
+	.module		= THIS_MODULE,
+	.ops		= nbd_connect_genl_ops,
+	.n_ops		= ARRAY_SIZE(nbd_connect_genl_ops),
+	.maxattr	= NBD_ATTR_MAX,
+	.mcgrps		= nbd_mcast_grps,
+	.n_mcgrps	= ARRAY_SIZE(nbd_mcast_grps),
+};
+
+static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply)
+{
+	struct nlattr *dev_opt;
+	u8 connected = 0;
+	int ret;
+
+	/* This is a little racey, but for status it's ok.  The
+	 * reason we don't take a ref here is because we can't
+	 * take a ref in the index == -1 case as we would need
+	 * to put under the nbd_index_mutex, which could
+	 * deadlock if we are configured to remove ourselves
+	 * once we're disconnected.
+	 */
+	if (refcount_read(&nbd->config_refs))
+		connected = 1;
+	dev_opt = nla_nest_start(reply, NBD_DEVICE_ITEM);
+	if (!dev_opt)
+		return -EMSGSIZE;
+	ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index);
+	if (ret)
+		return -EMSGSIZE;
+	ret = nla_put_u8(reply, NBD_DEVICE_CONNECTED,
+			 connected);
+	if (ret)
+		return -EMSGSIZE;
+	nla_nest_end(reply, dev_opt);
+	return 0;
+}
+
+static int status_cb(int id, void *ptr, void *data)
+{
+	struct nbd_device *nbd = ptr;
+	return populate_nbd_status(nbd, (struct sk_buff *)data);
+}
+
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *dev_list;
+	struct sk_buff *reply;
+	void *reply_head;
+	size_t msg_size;
+	int index = -1;
+	int ret = -ENOMEM;
+
+	if (info->attrs[NBD_ATTR_INDEX])
+		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+	mutex_lock(&nbd_index_mutex);
+
+	msg_size = nla_total_size(nla_attr_size(sizeof(u32)) +
+				  nla_attr_size(sizeof(u8)));
+	msg_size *= (index == -1) ? nbd_total_devices : 1;
+
+	reply = genlmsg_new(msg_size, GFP_KERNEL);
+	if (!reply)
+		goto out;
+	reply_head = genlmsg_put_reply(reply, info, &nbd_genl_family, 0,
+				       NBD_CMD_STATUS);
+	if (!reply_head) {
+		nlmsg_free(reply);
+		goto out;
+	}
+
+	dev_list = nla_nest_start(reply, NBD_ATTR_DEVICE_LIST);
+	if (index == -1) {
+		ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
+		if (ret) {
+			nlmsg_free(reply);
+			goto out;
+		}
+	} else {
+		struct nbd_device *nbd;
+		nbd = idr_find(&nbd_index_idr, index);
+		if (nbd) {
+			ret = populate_nbd_status(nbd, reply);
+			if (ret) {
+				nlmsg_free(reply);
+				goto out;
+			}
+		}
+	}
+	nla_nest_end(reply, dev_list);
+	genlmsg_end(reply, reply_head);
+	genlmsg_reply(reply, info);
+	ret = 0;
+out:
+	mutex_unlock(&nbd_index_mutex);
+	return ret;
+}
+
+static void nbd_connect_reply(struct genl_info *info, int index)
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	int ret;
+
+	skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+	if (!skb)
+		return;
+	msg_head = genlmsg_put_reply(skb, info, &nbd_genl_family, 0,
+				     NBD_CMD_CONNECT);
+	if (!msg_head) {
+		nlmsg_free(skb);
+		return;
+	}
+	ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+	if (ret) {
+		nlmsg_free(skb);
+		return;
+	}
+	genlmsg_end(skb, msg_head);
+	genlmsg_reply(skb, info);
+}
+
+static void nbd_mcast_index(int index)
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	int ret;
+
+	skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+	if (!skb)
+		return;
+	msg_head = genlmsg_put(skb, 0, 0, &nbd_genl_family, 0,
+				     NBD_CMD_LINK_DEAD);
+	if (!msg_head) {
+		nlmsg_free(skb);
+		return;
+	}
+	ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+	if (ret) {
+		nlmsg_free(skb);
+		return;
+	}
+	genlmsg_end(skb, msg_head);
+	genlmsg_multicast(&nbd_genl_family, skb, 0, 0, GFP_KERNEL);
+}
+
+static void nbd_dead_link_work(struct work_struct *work)
+{
+	struct link_dead_args *args = container_of(work, struct link_dead_args,
+						   work);
+	nbd_mcast_index(args->index);
+	kfree(args);
+}
 
 static int __init nbd_init(void)
 {
@@ -1114,6 +2071,11 @@ static int __init nbd_init(void)
 		return -EIO;
 	}
 
+	if (genl_register_family(&nbd_genl_family)) {
+		unregister_blkdev(NBD_MAJOR, "nbd");
+		destroy_workqueue(recv_workqueue);
+		return -EINVAL;
+	}
 	nbd_dbg_init();
 
 	mutex_lock(&nbd_index_mutex);
@@ -1125,17 +2087,34 @@ static int __init nbd_init(void)
 
 static int nbd_exit_cb(int id, void *ptr, void *data)
 {
+	struct list_head *list = (struct list_head *)data;
 	struct nbd_device *nbd = ptr;
-	nbd_dev_remove(nbd);
+
+	list_add_tail(&nbd->list, list);
 	return 0;
 }
 
 static void __exit nbd_cleanup(void)
 {
+	struct nbd_device *nbd;
+	LIST_HEAD(del_list);
+
 	nbd_dbg_close();
 
-	idr_for_each(&nbd_index_idr, &nbd_exit_cb, NULL);
+	mutex_lock(&nbd_index_mutex);
+	idr_for_each(&nbd_index_idr, &nbd_exit_cb, &del_list);
+	mutex_unlock(&nbd_index_mutex);
+
+	while (!list_empty(&del_list)) {
+		nbd = list_first_entry(&del_list, struct nbd_device, list);
+		list_del_init(&nbd->list);
+		if (refcount_read(&nbd->refs) != 1)
+			printk(KERN_ERR "nbd: possibly leaking a device\n");
+		nbd_put(nbd);
+	}
+
 	idr_destroy(&nbd_index_idr);
+	genl_unregister_family(&nbd_genl_family);
 	destroy_workqueue(recv_workqueue);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6f2e565bccc5..d946e1eeac8e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -117,6 +117,10 @@ static bool use_lightnvm;
 module_param(use_lightnvm, bool, S_IRUGO);
 MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
 
+static bool blocking;
+module_param(blocking, bool, S_IRUGO);
+MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -277,7 +281,7 @@ static inline void null_handle_cmd(struct nullb_cmd *cmd)
 	case NULL_IRQ_SOFTIRQ:
 		switch (queue_mode)  {
 		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq, cmd->rq->errors);
+			blk_mq_complete_request(cmd->rq);
 			break;
 		case NULL_Q_RQ:
 			blk_complete_request(cmd->rq);
@@ -357,6 +361,8 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
 
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
 	if (irqmode == NULL_IRQ_TIMER) {
 		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		cmd->timer.function = null_cmd_timer_expired;
@@ -392,7 +398,7 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 	return 0;
 }
 
-static struct blk_mq_ops null_mq_ops = {
+static const struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
 	.init_hctx	= null_init_hctx,
 	.complete	= null_softirq_done_fn,
@@ -437,14 +443,7 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
-	rq->__sector = bio->bi_iter.bi_sector;
-	rq->ioprio = bio_prio(bio);
-
-	if (bio_has_data(bio))
-		rq->nr_phys_segments = bio_phys_segments(q, bio);
-
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
+	blk_init_request_from_bio(rq, bio);
 
 	rq->end_io_data = rqd;
 
@@ -724,6 +723,9 @@ static int null_add_dev(void)
 		nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 		nullb->tag_set.driver_data = nullb;
 
+		if (blocking)
+			nullb->tag_set.flags |= BLK_MQ_F_BLOCKING;
+
 		rv = blk_mq_alloc_tag_set(&nullb->tag_set);
 		if (rv)
 			goto out_cleanup_queues;
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
deleted file mode 100644
index 8127b8201a01..000000000000
--- a/drivers/block/osdblk.c
+++ /dev/null
@@ -1,693 +0,0 @@
-
-/*
-   osdblk.c -- Export a single SCSI OSD object as a Linux block device
-
-
-   Copyright 2009 Red Hat, Inc.
-
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License
-   along with this program; see the file COPYING.  If not, write to
-   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
-
-
-   Instructions for use
-   --------------------
-
-   1) Map a Linux block device to an existing OSD object.
-
-      In this example, we will use partition id 1234, object id 5678,
-      OSD device /dev/osd1.
-
-      $ echo "1234 5678 /dev/osd1" > /sys/class/osdblk/add
-
-
-   2) List all active blkdev<->object mappings.
-
-      In this example, we have performed step #1 twice, creating two blkdevs,
-      mapped to two separate OSD objects.
-
-      $ cat /sys/class/osdblk/list
-      0 174 1234 5678 /dev/osd1
-      1 179 1994 897123 /dev/osd0
-
-      The columns, in order, are:
-      - blkdev unique id
-      - blkdev assigned major
-      - OSD object partition id
-      - OSD object id
-      - OSD device
-
-
-   3) Remove an active blkdev<->object mapping.
-
-      In this example, we remove the mapping with blkdev unique id 1.
-
-      $ echo 1 > /sys/class/osdblk/remove
-
-
-   NOTE:  The actual creation and deletion of OSD objects is outside the scope
-   of this driver.
-
- */
-
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_attributes.h>
-#include <scsi/osd_sec.h>
-#include <scsi/scsi_device.h>
-
-#define DRV_NAME "osdblk"
-#define PFX DRV_NAME ": "
-
-/* #define _OSDBLK_DEBUG */
-#ifdef _OSDBLK_DEBUG
-#define OSDBLK_DEBUG(fmt, a...) \
-	printk(KERN_NOTICE "osdblk @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define OSDBLK_DEBUG(fmt, a...) \
-	do { if (0) printk(fmt, ##a); } while (0)
-#endif
-
-MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
-MODULE_DESCRIPTION("block device inside an OSD object osdblk.ko");
-MODULE_LICENSE("GPL");
-
-struct osdblk_device;
-
-enum {
-	OSDBLK_MINORS_PER_MAJOR	= 256,		/* max minors per blkdev */
-	OSDBLK_MAX_REQ		= 32,		/* max parallel requests */
-	OSDBLK_OP_TIMEOUT	= 4 * 60,	/* sync OSD req timeout */
-};
-
-struct osdblk_request {
-	struct request		*rq;		/* blk layer request */
-	struct bio		*bio;		/* cloned bio */
-	struct osdblk_device	*osdev;		/* associated blkdev */
-};
-
-struct osdblk_device {
-	int			id;		/* blkdev unique id */
-
-	int			major;		/* blkdev assigned major */
-	struct gendisk		*disk;		/* blkdev's gendisk and rq */
-	struct request_queue	*q;
-
-	struct osd_dev		*osd;		/* associated OSD */
-
-	char			name[32];	/* blkdev name, e.g. osdblk34 */
-
-	spinlock_t		lock;		/* queue lock */
-
-	struct osd_obj_id	obj;		/* OSD partition, obj id */
-	uint8_t			obj_cred[OSD_CAP_LEN]; /* OSD cred */
-
-	struct osdblk_request	req[OSDBLK_MAX_REQ]; /* request table */
-
-	struct list_head	node;
-
-	char			osd_path[0];	/* OSD device path */
-};
-
-static struct class *class_osdblk;		/* /sys/class/osdblk */
-static DEFINE_MUTEX(ctl_mutex);	/* Serialize open/close/setup/teardown */
-static LIST_HEAD(osdblkdev_list);
-
-static const struct block_device_operations osdblk_bd_ops = {
-	.owner		= THIS_MODULE,
-};
-
-static const struct osd_attr g_attr_logical_length = ATTR_DEF(
-	OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
-
-static void osdblk_make_credential(u8 cred_a[OSD_CAP_LEN],
-				   const struct osd_obj_id *obj)
-{
-	osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
-}
-
-/* copied from exofs; move to libosd? */
-/*
- * Perform a synchronous OSD operation.  copied from exofs; move to libosd?
- */
-static int osd_sync_op(struct osd_request *or, int timeout, uint8_t *credential)
-{
-	int ret;
-
-	or->timeout = timeout;
-	ret = osd_finalize_request(or, 0, credential, NULL);
-	if (ret)
-		return ret;
-
-	ret = osd_execute_request(or);
-
-	/* osd_req_decode_sense(or, ret); */
-	return ret;
-}
-
-/*
- * Perform an asynchronous OSD operation.  copied from exofs; move to libosd?
- */
-static int osd_async_op(struct osd_request *or, osd_req_done_fn *async_done,
-		   void *caller_context, u8 *cred)
-{
-	int ret;
-
-	ret = osd_finalize_request(or, 0, cred, NULL);
-	if (ret)
-		return ret;
-
-	ret = osd_execute_request_async(or, async_done, caller_context);
-
-	return ret;
-}
-
-/* copied from exofs; move to libosd? */
-static int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
-{
-	struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
-	void *iter = NULL;
-	int nelem;
-
-	do {
-		nelem = 1;
-		osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter);
-		if ((cur_attr.attr_page == attr->attr_page) &&
-		    (cur_attr.attr_id == attr->attr_id)) {
-			attr->len = cur_attr.len;
-			attr->val_ptr = cur_attr.val_ptr;
-			return 0;
-		}
-	} while (iter);
-
-	return -EIO;
-}
-
-static int osdblk_get_obj_size(struct osdblk_device *osdev, u64 *size_out)
-{
-	struct osd_request *or;
-	struct osd_attr attr;
-	int ret;
-
-	/* start request */
-	or = osd_start_request(osdev->osd, GFP_KERNEL);
-	if (!or)
-		return -ENOMEM;
-
-	/* create a get-attributes(length) request */
-	osd_req_get_attributes(or, &osdev->obj);
-
-	osd_req_add_get_attr_list(or, &g_attr_logical_length, 1);
-
-	/* execute op synchronously */
-	ret = osd_sync_op(or, OSDBLK_OP_TIMEOUT, osdev->obj_cred);
-	if (ret)
-		goto out;
-
-	/* extract length from returned attribute info */
-	attr = g_attr_logical_length;
-	ret = extract_attr_from_req(or, &attr);
-	if (ret)
-		goto out;
-
-	*size_out = get_unaligned_be64(attr.val_ptr);
-
-out:
-	osd_end_request(or);
-	return ret;
-
-}
-
-static void osdblk_osd_complete(struct osd_request *or, void *private)
-{
-	struct osdblk_request *orq = private;
-	struct osd_sense_info osi;
-	int ret = osd_req_decode_sense(or, &osi);
-
-	if (ret) {
-		ret = -EIO;
-		OSDBLK_DEBUG("osdblk_osd_complete with err=%d\n", ret);
-	}
-
-	/* complete OSD request */
-	osd_end_request(or);
-
-	/* complete request passed to osdblk by block layer */
-	__blk_end_request_all(orq->rq, ret);
-}
-
-static void bio_chain_put(struct bio *chain)
-{
-	struct bio *tmp;
-
-	while (chain) {
-		tmp = chain;
-		chain = chain->bi_next;
-
-		bio_put(tmp);
-	}
-}
-
-static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
-{
-	struct bio *tmp, *new_chain = NULL, *tail = NULL;
-
-	while (old_chain) {
-		tmp = bio_clone_kmalloc(old_chain, gfpmask);
-		if (!tmp)
-			goto err_out;
-
-		tmp->bi_bdev = NULL;
-		gfpmask &= ~__GFP_DIRECT_RECLAIM;
-		tmp->bi_next = NULL;
-
-		if (!new_chain)
-			new_chain = tail = tmp;
-		else {
-			tail->bi_next = tmp;
-			tail = tmp;
-		}
-
-		old_chain = old_chain->bi_next;
-	}
-
-	return new_chain;
-
-err_out:
-	OSDBLK_DEBUG("bio_chain_clone with err\n");
-	bio_chain_put(new_chain);
-	return NULL;
-}
-
-static void osdblk_rq_fn(struct request_queue *q)
-{
-	struct osdblk_device *osdev = q->queuedata;
-
-	while (1) {
-		struct request *rq;
-		struct osdblk_request *orq;
-		struct osd_request *or;
-		struct bio *bio;
-		bool do_write, do_flush;
-
-		/* peek at request from block layer */
-		rq = blk_fetch_request(q);
-		if (!rq)
-			break;
-
-		/* deduce our operation (read, write, flush) */
-		/* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
-		 * into a clearly defined set of RPC commands:
-		 * read, write, flush, scsi command, power mgmt req,
-		 * driver-specific, etc.
-		 */
-
-		do_flush = (req_op(rq) == REQ_OP_FLUSH);
-		do_write = (rq_data_dir(rq) == WRITE);
-
-		if (!do_flush) { /* osd_flush does not use a bio */
-			/* a bio clone to be passed down to OSD request */
-			bio = bio_chain_clone(rq->bio, GFP_ATOMIC);
-			if (!bio)
-				break;
-		} else
-			bio = NULL;
-
-		/* alloc internal OSD request, for OSD command execution */
-		or = osd_start_request(osdev->osd, GFP_ATOMIC);
-		if (!or) {
-			bio_chain_put(bio);
-			OSDBLK_DEBUG("osd_start_request with err\n");
-			break;
-		}
-
-		orq = &osdev->req[rq->tag];
-		orq->rq = rq;
-		orq->bio = bio;
-		orq->osdev = osdev;
-
-		/* init OSD command: flush, write or read */
-		if (do_flush)
-			osd_req_flush_object(or, &osdev->obj,
-					     OSD_CDB_FLUSH_ALL, 0, 0);
-		else if (do_write)
-			osd_req_write(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
-				      bio, blk_rq_bytes(rq));
-		else
-			osd_req_read(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
-				     bio, blk_rq_bytes(rq));
-
-		OSDBLK_DEBUG("%s 0x%x bytes at 0x%llx\n",
-			do_flush ? "flush" : do_write ?
-				"write" : "read", blk_rq_bytes(rq),
-			blk_rq_pos(rq) * 512ULL);
-
-		/* begin OSD command execution */
-		if (osd_async_op(or, osdblk_osd_complete, orq,
-				 osdev->obj_cred)) {
-			osd_end_request(or);
-			blk_requeue_request(q, rq);
-			bio_chain_put(bio);
-			OSDBLK_DEBUG("osd_execute_request_async with err\n");
-			break;
-		}
-
-		/* remove the special 'flush' marker, now that the command
-		 * is executing
-		 */
-		rq->special = NULL;
-	}
-}
-
-static void osdblk_free_disk(struct osdblk_device *osdev)
-{
-	struct gendisk *disk = osdev->disk;
-
-	if (!disk)
-		return;
-
-	if (disk->flags & GENHD_FL_UP)
-		del_gendisk(disk);
-	if (disk->queue)
-		blk_cleanup_queue(disk->queue);
-	put_disk(disk);
-}
-
-static int osdblk_init_disk(struct osdblk_device *osdev)
-{
-	struct gendisk *disk;
-	struct request_queue *q;
-	int rc;
-	u64 obj_size = 0;
-
-	/* contact OSD, request size info about the object being mapped */
-	rc = osdblk_get_obj_size(osdev, &obj_size);
-	if (rc)
-		return rc;
-
-	/* create gendisk info */
-	disk = alloc_disk(OSDBLK_MINORS_PER_MAJOR);
-	if (!disk)
-		return -ENOMEM;
-
-	sprintf(disk->disk_name, DRV_NAME "%d", osdev->id);
-	disk->major = osdev->major;
-	disk->first_minor = 0;
-	disk->fops = &osdblk_bd_ops;
-	disk->private_data = osdev;
-
-	/* init rq */
-	q = blk_init_queue(osdblk_rq_fn, &osdev->lock);
-	if (!q) {
-		put_disk(disk);
-		return -ENOMEM;
-	}
-
-	/* switch queue to TCQ mode; allocate tag map */
-	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
-	if (rc) {
-		blk_cleanup_queue(q);
-		put_disk(disk);
-		return rc;
-	}
-
-	/* Set our limits to the lower device limits, because osdblk cannot
-	 * sleep when allocating a lower-request and therefore cannot be
-	 * bouncing.
-	 */
-	blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
-
-	blk_queue_prep_rq(q, blk_queue_start_tag);
-	blk_queue_write_cache(q, true, false);
-
-	disk->queue = q;
-
-	q->queuedata = osdev;
-
-	osdev->disk = disk;
-	osdev->q = q;
-
-	/* finally, announce the disk to the world */
-	set_capacity(disk, obj_size / 512ULL);
-	add_disk(disk);
-
-	printk(KERN_INFO "%s: Added of size 0x%llx\n",
-		disk->disk_name, (unsigned long long)obj_size);
-
-	return 0;
-}
-
-/********************************************************************
- * /sys/class/osdblk/
- *                   add	map OSD object to blkdev
- *                   remove	unmap OSD object
- *                   list	show mappings
- *******************************************************************/
-
-static void class_osdblk_release(struct class *cls)
-{
-	kfree(cls);
-}
-
-static ssize_t class_osdblk_list(struct class *c,
-				struct class_attribute *attr,
-				char *data)
-{
-	int n = 0;
-	struct list_head *tmp;
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &osdblkdev_list) {
-		struct osdblk_device *osdev;
-
-		osdev = list_entry(tmp, struct osdblk_device, node);
-
-		n += sprintf(data+n, "%d %d %llu %llu %s\n",
-			osdev->id,
-			osdev->major,
-			osdev->obj.partition,
-			osdev->obj.id,
-			osdev->osd_path);
-	}
-
-	mutex_unlock(&ctl_mutex);
-	return n;
-}
-
-static ssize_t class_osdblk_add(struct class *c,
-				struct class_attribute *attr,
-				const char *buf, size_t count)
-{
-	struct osdblk_device *osdev;
-	ssize_t rc;
-	int irc, new_id = 0;
-	struct list_head *tmp;
-
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
-
-	/* new osdblk_device object */
-	osdev = kzalloc(sizeof(*osdev) + strlen(buf) + 1, GFP_KERNEL);
-	if (!osdev) {
-		rc = -ENOMEM;
-		goto err_out_mod;
-	}
-
-	/* static osdblk_device initialization */
-	spin_lock_init(&osdev->lock);
-	INIT_LIST_HEAD(&osdev->node);
-
-	/* generate unique id: find highest unique id, add one */
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &osdblkdev_list) {
-		struct osdblk_device *osdev;
-
-		osdev = list_entry(tmp, struct osdblk_device, node);
-		if (osdev->id > new_id)
-			new_id = osdev->id + 1;
-	}
-
-	osdev->id = new_id;
-
-	/* add to global list */
-	list_add_tail(&osdev->node, &osdblkdev_list);
-
-	mutex_unlock(&ctl_mutex);
-
-	/* parse add command */
-	if (sscanf(buf, "%llu %llu %s", &osdev->obj.partition, &osdev->obj.id,
-		   osdev->osd_path) != 3) {
-		rc = -EINVAL;
-		goto err_out_slot;
-	}
-
-	/* initialize rest of new object */
-	sprintf(osdev->name, DRV_NAME "%d", osdev->id);
-
-	/* contact requested OSD */
-	osdev->osd = osduld_path_lookup(osdev->osd_path);
-	if (IS_ERR(osdev->osd)) {
-		rc = PTR_ERR(osdev->osd);
-		goto err_out_slot;
-	}
-
-	/* build OSD credential */
-	osdblk_make_credential(osdev->obj_cred, &osdev->obj);
-
-	/* register our block device */
-	irc = register_blkdev(0, osdev->name);
-	if (irc < 0) {
-		rc = irc;
-		goto err_out_osd;
-	}
-
-	osdev->major = irc;
-
-	/* set up and announce blkdev mapping */
-	rc = osdblk_init_disk(osdev);
-	if (rc)
-		goto err_out_blkdev;
-
-	return count;
-
-err_out_blkdev:
-	unregister_blkdev(osdev->major, osdev->name);
-err_out_osd:
-	osduld_put_device(osdev->osd);
-err_out_slot:
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-	list_del_init(&osdev->node);
-	mutex_unlock(&ctl_mutex);
-
-	kfree(osdev);
-err_out_mod:
-	OSDBLK_DEBUG("Error adding device %s\n", buf);
-	module_put(THIS_MODULE);
-	return rc;
-}
-
-static ssize_t class_osdblk_remove(struct class *c,
-					struct class_attribute *attr,
-					const char *buf,
-					size_t count)
-{
-	struct osdblk_device *osdev = NULL;
-	int target_id, rc;
-	unsigned long ul;
-	struct list_head *tmp;
-
-	rc = kstrtoul(buf, 10, &ul);
-	if (rc)
-		return rc;
-
-	/* convert to int; abort if we lost anything in the conversion */
-	target_id = (int) ul;
-	if (target_id != ul)
-		return -EINVAL;
-
-	/* remove object from list immediately */
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &osdblkdev_list) {
-		osdev = list_entry(tmp, struct osdblk_device, node);
-		if (osdev->id == target_id) {
-			list_del_init(&osdev->node);
-			break;
-		}
-		osdev = NULL;
-	}
-
-	mutex_unlock(&ctl_mutex);
-
-	if (!osdev)
-		return -ENOENT;
-
-	/* clean up and free blkdev and associated OSD connection */
-	osdblk_free_disk(osdev);
-	unregister_blkdev(osdev->major, osdev->name);
-	osduld_put_device(osdev->osd);
-	kfree(osdev);
-
-	/* release module ref */
-	module_put(THIS_MODULE);
-
-	return count;
-}
-
-static struct class_attribute class_osdblk_attrs[] = {
-	__ATTR(add,	0200, NULL, class_osdblk_add),
-	__ATTR(remove,	0200, NULL, class_osdblk_remove),
-	__ATTR(list,	0444, class_osdblk_list, NULL),
-	__ATTR_NULL
-};
-
-static int osdblk_sysfs_init(void)
-{
-	int ret = 0;
-
-	/*
-	 * create control files in sysfs
-	 * /sys/class/osdblk/...
-	 */
-	class_osdblk = kzalloc(sizeof(*class_osdblk), GFP_KERNEL);
-	if (!class_osdblk)
-		return -ENOMEM;
-
-	class_osdblk->name = DRV_NAME;
-	class_osdblk->owner = THIS_MODULE;
-	class_osdblk->class_release = class_osdblk_release;
-	class_osdblk->class_attrs = class_osdblk_attrs;
-
-	ret = class_register(class_osdblk);
-	if (ret) {
-		kfree(class_osdblk);
-		class_osdblk = NULL;
-		printk(PFX "failed to create class osdblk\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static void osdblk_sysfs_cleanup(void)
-{
-	if (class_osdblk)
-		class_destroy(class_osdblk);
-	class_osdblk = NULL;
-}
-
-static int __init osdblk_init(void)
-{
-	int rc;
-
-	rc = osdblk_sysfs_init();
-	if (rc)
-		return rc;
-
-	return 0;
-}
-
-static void __exit osdblk_exit(void)
-{
-	osdblk_sysfs_cleanup();
-}
-
-module_init(osdblk_init);
-module_exit(osdblk_exit);
-
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 10aed84244f5..b1267ef34d5a 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -50,7 +50,7 @@
                         the slower the port i/o.  In some cases, setting
                         this to zero will speed up the device. (default -1)
                         
-            major       You may use this parameter to overide the
+            major       You may use this parameter to override the
                         default major number (46) that this driver
                         will use.  Be sure to change the device
                         name as well.
@@ -300,6 +300,11 @@ static void pcd_init_units(void)
 		struct gendisk *disk = alloc_disk(1);
 		if (!disk)
 			continue;
+		disk->queue = blk_init_queue(do_pcd_request, &pcd_lock);
+		if (!disk->queue) {
+			put_disk(disk);
+			continue;
+		}
 		cd->disk = disk;
 		cd->pi = &cd->pia;
 		cd->present = 0;
@@ -735,18 +740,36 @@ static int pcd_detect(void)
 }
 
 /* I/O request processing */
-static struct request_queue *pcd_queue;
+static int pcd_queue;
+
+static int set_next_request(void)
+{
+	struct pcd_unit *cd;
+	struct request_queue *q;
+	int old_pos = pcd_queue;
+
+	do {
+		cd = &pcd[pcd_queue];
+		q = cd->present ? cd->disk->queue : NULL;
+		if (++pcd_queue == PCD_UNITS)
+			pcd_queue = 0;
+		if (q) {
+			pcd_req = blk_fetch_request(q);
+			if (pcd_req)
+				break;
+		}
+	} while (pcd_queue != old_pos);
+
+	return pcd_req != NULL;
+}
 
-static void do_pcd_request(struct request_queue * q)
+static void pcd_request(void)
 {
 	if (pcd_busy)
 		return;
 	while (1) {
-		if (!pcd_req) {
-			pcd_req = blk_fetch_request(q);
-			if (!pcd_req)
-				return;
-		}
+		if (!pcd_req && !set_next_request())
+			return;
 
 		if (rq_data_dir(pcd_req) == READ) {
 			struct pcd_unit *cd = pcd_req->rq_disk->private_data;
@@ -766,6 +789,11 @@ static void do_pcd_request(struct request_queue * q)
 	}
 }
 
+static void do_pcd_request(struct request_queue *q)
+{
+	pcd_request();
+}
+
 static inline void next_request(int err)
 {
 	unsigned long saved_flags;
@@ -774,7 +802,7 @@ static inline void next_request(int err)
 	if (!__blk_end_request_cur(pcd_req, err))
 		pcd_req = NULL;
 	pcd_busy = 0;
-	do_pcd_request(pcd_queue);
+	pcd_request();
 	spin_unlock_irqrestore(&pcd_lock, saved_flags);
 }
 
@@ -849,7 +877,7 @@ static void do_pcd_read_drq(void)
 
 	do_pcd_read();
 	spin_lock_irqsave(&pcd_lock, saved_flags);
-	do_pcd_request(pcd_queue);
+	pcd_request();
 	spin_unlock_irqrestore(&pcd_lock, saved_flags);
 }
 
@@ -957,19 +985,10 @@ static int __init pcd_init(void)
 		return -EBUSY;
 	}
 
-	pcd_queue = blk_init_queue(do_pcd_request, &pcd_lock);
-	if (!pcd_queue) {
-		unregister_blkdev(major, name);
-		for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
-			put_disk(cd->disk);
-		return -ENOMEM;
-	}
-
 	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
 		if (cd->present) {
 			register_cdrom(&cd->info);
 			cd->disk->private_data = cd;
-			cd->disk->queue = pcd_queue;
 			add_disk(cd->disk);
 		}
 	}
@@ -988,9 +1007,9 @@ static void __exit pcd_exit(void)
 			pi_release(cd->pi);
 			unregister_cdrom(&cd->info);
 		}
+		blk_cleanup_queue(cd->disk->queue);
 		put_disk(cd->disk);
 	}
-	blk_cleanup_queue(pcd_queue);
 	unregister_blkdev(major, name);
 	pi_unregister_driver(par_drv);
 }
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 644ba0888bd4..7d2402f90978 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -61,7 +61,7 @@
                         first drive found.
 			
 
-            major       You may use this parameter to overide the
+            major       You may use this parameter to override the
                         default major number (45) that this driver
                         will use.  Be sure to change the device
                         name as well.
@@ -381,12 +381,33 @@ static enum action do_pd_write_start(void);
 static enum action do_pd_read_drq(void);
 static enum action do_pd_write_done(void);
 
-static struct request_queue *pd_queue;
+static int pd_queue;
 static int pd_claimed;
 
 static struct pd_unit *pd_current; /* current request's drive */
 static PIA *pi_current; /* current request's PIA */
 
+static int set_next_request(void)
+{
+	struct gendisk *disk;
+	struct request_queue *q;
+	int old_pos = pd_queue;
+
+	do {
+		disk = pd[pd_queue].gd;
+		q = disk ? disk->queue : NULL;
+		if (++pd_queue == PD_UNITS)
+			pd_queue = 0;
+		if (q) {
+			pd_req = blk_fetch_request(q);
+			if (pd_req)
+				break;
+		}
+	} while (pd_queue != old_pos);
+
+	return pd_req != NULL;
+}
+
 static void run_fsm(void)
 {
 	while (1) {
@@ -418,8 +439,7 @@ static void run_fsm(void)
 				spin_lock_irqsave(&pd_lock, saved_flags);
 				if (!__blk_end_request_cur(pd_req,
 						res == Ok ? 0 : -EIO)) {
-					pd_req = blk_fetch_request(pd_queue);
-					if (!pd_req)
+					if (!set_next_request())
 						stop = 1;
 				}
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
@@ -719,18 +739,15 @@ static int pd_special_command(struct pd_unit *disk,
 		      enum action (*func)(struct pd_unit *disk))
 {
 	struct request *rq;
-	int err = 0;
 
 	rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
 	rq->special = func;
-
-	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
-
+	blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
 	blk_put_request(rq);
-	return err;
+	return 0;
 }
 
 /* kernel glue structures */
@@ -839,7 +856,13 @@ static void pd_probe_drive(struct pd_unit *disk)
 	p->first_minor = (disk - pd) << PD_BITS;
 	disk->gd = p;
 	p->private_data = disk;
-	p->queue = pd_queue;
+	p->queue = blk_init_queue(do_pd_request, &pd_lock);
+	if (!p->queue) {
+		disk->gd = NULL;
+		put_disk(p);
+		return;
+	}
+	blk_queue_max_hw_sectors(p->queue, cluster);
 
 	if (disk->drive == -1) {
 		for (disk->drive = 0; disk->drive <= 1; disk->drive++)
@@ -919,26 +942,18 @@ static int __init pd_init(void)
 	if (disable)
 		goto out1;
 
-	pd_queue = blk_init_queue(do_pd_request, &pd_lock);
-	if (!pd_queue)
-		goto out1;
-
-	blk_queue_max_hw_sectors(pd_queue, cluster);
-
 	if (register_blkdev(major, name))
-		goto out2;
+		goto out1;
 
 	printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
 	       name, name, PD_VERSION, major, cluster, nice);
 	if (!pd_detect())
-		goto out3;
+		goto out2;
 
 	return 0;
 
-out3:
-	unregister_blkdev(major, name);
 out2:
-	blk_cleanup_queue(pd_queue);
+	unregister_blkdev(major, name);
 out1:
 	return -ENODEV;
 }
@@ -953,11 +968,11 @@ static void __exit pd_exit(void)
 		if (p) {
 			disk->gd = NULL;
 			del_gendisk(p);
+			blk_cleanup_queue(p->queue);
 			put_disk(p);
 			pi_release(disk->pi);
 		}
 	}
-	blk_cleanup_queue(pd_queue);
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index ed93e8badf56..f24ca7315ddc 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -59,7 +59,7 @@
                         the slower the port i/o.  In some cases, setting
                         this to zero will speed up the device. (default -1)
 
-	    major	You may use this parameter to overide the
+	    major	You may use this parameter to override the
 			default major number (47) that this driver
 			will use.  Be sure to change the device
 			name as well.
@@ -287,6 +287,12 @@ static void __init pf_init_units(void)
 		struct gendisk *disk = alloc_disk(1);
 		if (!disk)
 			continue;
+		disk->queue = blk_init_queue(do_pf_request, &pf_spin_lock);
+		if (!disk->queue) {
+			put_disk(disk);
+			return;
+		}
+		blk_queue_max_segments(disk->queue, cluster);
 		pf->disk = disk;
 		pf->pi = &pf->pia;
 		pf->media_status = PF_NM;
@@ -772,7 +778,28 @@ static int pf_ready(void)
 	return (((status_reg(pf_current) & (STAT_BUSY | pf_mask)) == pf_mask));
 }
 
-static struct request_queue *pf_queue;
+static int pf_queue;
+
+static int set_next_request(void)
+{
+	struct pf_unit *pf;
+	struct request_queue *q;
+	int old_pos = pf_queue;
+
+	do {
+		pf = &units[pf_queue];
+		q = pf->present ? pf->disk->queue : NULL;
+		if (++pf_queue == PF_UNITS)
+			pf_queue = 0;
+		if (q) {
+			pf_req = blk_fetch_request(q);
+			if (pf_req)
+				break;
+		}
+	} while (pf_queue != old_pos);
+
+	return pf_req != NULL;
+}
 
 static void pf_end_request(int err)
 {
@@ -780,16 +807,13 @@ static void pf_end_request(int err)
 		pf_req = NULL;
 }
 
-static void do_pf_request(struct request_queue * q)
+static void pf_request(void)
 {
 	if (pf_busy)
 		return;
 repeat:
-	if (!pf_req) {
-		pf_req = blk_fetch_request(q);
-		if (!pf_req)
-			return;
-	}
+	if (!pf_req && !set_next_request())
+		return;
 
 	pf_current = pf_req->rq_disk->private_data;
 	pf_block = blk_rq_pos(pf_req);
@@ -817,6 +841,11 @@ repeat:
 	}
 }
 
+static void do_pf_request(struct request_queue *q)
+{
+	pf_request();
+}
+
 static int pf_next_buf(void)
 {
 	unsigned long saved_flags;
@@ -846,7 +875,7 @@ static inline void next_request(int err)
 	spin_lock_irqsave(&pf_spin_lock, saved_flags);
 	pf_end_request(err);
 	pf_busy = 0;
-	do_pf_request(pf_queue);
+	pf_request();
 	spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
 }
 
@@ -972,15 +1001,6 @@ static int __init pf_init(void)
 			put_disk(pf->disk);
 		return -EBUSY;
 	}
-	pf_queue = blk_init_queue(do_pf_request, &pf_spin_lock);
-	if (!pf_queue) {
-		unregister_blkdev(major, name);
-		for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
-			put_disk(pf->disk);
-		return -ENOMEM;
-	}
-
-	blk_queue_max_segments(pf_queue, cluster);
 
 	for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
 		struct gendisk *disk = pf->disk;
@@ -988,7 +1008,6 @@ static int __init pf_init(void)
 		if (!pf->present)
 			continue;
 		disk->private_data = pf;
-		disk->queue = pf_queue;
 		add_disk(disk);
 	}
 	return 0;
@@ -1003,10 +1022,10 @@ static void __exit pf_exit(void)
 		if (!pf->present)
 			continue;
 		del_gendisk(pf->disk);
+		blk_cleanup_queue(pf->disk->queue);
 		put_disk(pf->disk);
 		pi_release(pf->pi);
 	}
-	blk_cleanup_queue(pf_queue);
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index 5db955fe3a94..3b5882bfb736 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -84,7 +84,7 @@
 			the slower the port i/o.  In some cases, setting
 			this to zero will speed up the device. (default -1)
 
-	    major	You may use this parameter to overide the
+	    major	You may use this parameter to override the
 			default major number (97) that this driver
 			will use.  Be sure to change the device
 			name as well.
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 61fc6824299a..e815312a00ad 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -61,7 +61,7 @@
                         the slower the port i/o.  In some cases, setting
                         this to zero will speed up the device. (default -1)
 
-	    major	You may use this parameter to overide the
+	    major	You may use this parameter to override the
 			default major number (96) that this driver
 			will use.  Be sure to change the device
 			name as well.
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 66d846ba85a9..205b865ebeb9 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -724,7 +724,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 		rq->rq_flags |= RQF_QUIET;
 
 	blk_execute_rq(rq->q, pd->bdev->bd_disk, rq, 0);
-	if (rq->errors)
+	if (scsi_req(rq)->result)
 		ret = -EIO;
 out:
 	blk_put_request(rq);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4d6807723798..089ac4179919 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -120,10 +120,11 @@ static int atomic_dec_return_safe(atomic_t *v)
 
 /* Feature bits */
 
-#define RBD_FEATURE_LAYERING	(1<<0)
-#define RBD_FEATURE_STRIPINGV2	(1<<1)
-#define RBD_FEATURE_EXCLUSIVE_LOCK (1<<2)
-#define RBD_FEATURE_DATA_POOL (1<<7)
+#define RBD_FEATURE_LAYERING		(1ULL<<0)
+#define RBD_FEATURE_STRIPINGV2		(1ULL<<1)
+#define RBD_FEATURE_EXCLUSIVE_LOCK	(1ULL<<2)
+#define RBD_FEATURE_DATA_POOL		(1ULL<<7)
+
 #define RBD_FEATURES_ALL	(RBD_FEATURE_LAYERING |		\
 				 RBD_FEATURE_STRIPINGV2 |	\
 				 RBD_FEATURE_EXCLUSIVE_LOCK |	\
@@ -499,16 +500,23 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
 	return is_lock_owner;
 }
 
+static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
+{
+	return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
+}
+
 static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
 static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
 static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
 static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
 
 static struct attribute *rbd_bus_attrs[] = {
 	&bus_attr_add.attr,
 	&bus_attr_remove.attr,
 	&bus_attr_add_single_major.attr,
 	&bus_attr_remove_single_major.attr,
+	&bus_attr_supported_features.attr,
 	NULL,
 };
 
@@ -4309,7 +4317,7 @@ static int rbd_init_request(void *data, struct request *rq,
 	return 0;
 }
 
-static struct blk_mq_ops rbd_mq_ops = {
+static const struct blk_mq_ops rbd_mq_ops = {
 	.queue_rq	= rbd_queue_rq,
 	.init_request	= rbd_init_request,
 };
@@ -4372,7 +4380,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	q->limits.discard_granularity = segment_size;
 	q->limits.discard_alignment = segment_size;
 	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
-	q->limits.discard_zeroes_data = 1;
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
 		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index f81d70b39d10..9c566364ac9c 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -300,7 +300,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 						RSXX_HW_BLK_SIZE >> 9);
 		card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE;
 		card->queue->limits.discard_alignment   = RSXX_HW_BLK_SIZE;
-		card->queue->limits.discard_zeroes_data = 1;
 	}
 
 	card->queue->queuedata = card;
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index b5afd495d482..3064be6cf375 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -211,7 +211,7 @@ enum head {
 struct swim_priv {
 	struct swim __iomem *base;
 	spinlock_t lock;
-	struct request_queue *queue;
+	int fdc_queue;
 	int floppy_count;
 	struct floppy_state unit[FD_MAX_UNIT];
 };
@@ -525,12 +525,33 @@ static int floppy_read_sectors(struct floppy_state *fs,
 	return 0;
 }
 
-static void redo_fd_request(struct request_queue *q)
+static struct request *swim_next_request(struct swim_priv *swd)
 {
+	struct request_queue *q;
+	struct request *rq;
+	int old_pos = swd->fdc_queue;
+
+	do {
+		q = swd->unit[swd->fdc_queue].disk->queue;
+		if (++swd->fdc_queue == swd->floppy_count)
+			swd->fdc_queue = 0;
+		if (q) {
+			rq = blk_fetch_request(q);
+			if (rq)
+				return rq;
+		}
+	} while (swd->fdc_queue != old_pos);
+
+	return NULL;
+}
+
+static void do_fd_request(struct request_queue *q)
+{
+	struct swim_priv *swd = q->queuedata;
 	struct request *req;
 	struct floppy_state *fs;
 
-	req = blk_fetch_request(q);
+	req = swim_next_request(swd);
 	while (req) {
 		int err = -EIO;
 
@@ -554,15 +575,10 @@ static void redo_fd_request(struct request_queue *q)
 		}
 	done:
 		if (!__blk_end_request_cur(req, err))
-			req = blk_fetch_request(q);
+			req = swim_next_request(swd);
 	}
 }
 
-static void do_fd_request(struct request_queue *q)
-{
-	redo_fd_request(q);
-}
-
 static struct floppy_struct floppy_type[4] = {
 	{    0,  0, 0,  0, 0, 0x00, 0x00, 0x00, 0x00, NULL }, /* no testing   */
 	{  720,  9, 1, 80, 0, 0x2A, 0x02, 0xDF, 0x50, NULL }, /* 360KB SS 3.5"*/
@@ -833,22 +849,25 @@ static int swim_floppy_init(struct swim_priv *swd)
 		return -EBUSY;
 	}
 
+	spin_lock_init(&swd->lock);
+
 	for (drive = 0; drive < swd->floppy_count; drive++) {
 		swd->unit[drive].disk = alloc_disk(1);
 		if (swd->unit[drive].disk == NULL) {
 			err = -ENOMEM;
 			goto exit_put_disks;
 		}
+		swd->unit[drive].disk->queue = blk_init_queue(do_fd_request,
+							      &swd->lock);
+		if (!swd->unit[drive].disk->queue) {
+			err = -ENOMEM;
+			put_disk(swd->unit[drive].disk);
+			goto exit_put_disks;
+		}
+		swd->unit[drive].disk->queue->queuedata = swd;
 		swd->unit[drive].swd = swd;
 	}
 
-	spin_lock_init(&swd->lock);
-	swd->queue = blk_init_queue(do_fd_request, &swd->lock);
-	if (!swd->queue) {
-		err = -ENOMEM;
-		goto exit_put_disks;
-	}
-
 	for (drive = 0; drive < swd->floppy_count; drive++) {
 		swd->unit[drive].disk->flags = GENHD_FL_REMOVABLE;
 		swd->unit[drive].disk->major = FLOPPY_MAJOR;
@@ -856,7 +875,6 @@ static int swim_floppy_init(struct swim_priv *swd)
 		sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
 		swd->unit[drive].disk->fops = &floppy_fops;
 		swd->unit[drive].disk->private_data = &swd->unit[drive];
-		swd->unit[drive].disk->queue = swd->queue;
 		set_capacity(swd->unit[drive].disk, 2880);
 		add_disk(swd->unit[drive].disk);
 	}
@@ -943,13 +961,12 @@ static int swim_remove(struct platform_device *dev)
 
 	for (drive = 0; drive < swd->floppy_count; drive++) {
 		del_gendisk(swd->unit[drive].disk);
+		blk_cleanup_queue(swd->unit[drive].disk->queue);
 		put_disk(swd->unit[drive].disk);
 	}
 
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 
-	blk_cleanup_queue(swd->queue);
-
 	/* eject floppies */
 
 	for (drive = 0; drive < swd->floppy_count; drive++)
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 61b3ffa4f458..ba4809c9bdba 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -343,8 +343,8 @@ static void start_request(struct floppy_state *fs)
 			  req->rq_disk->disk_name, req->cmd,
 			  (long)blk_rq_pos(req), blk_rq_sectors(req),
 			  bio_data(req->bio));
-		swim3_dbg("           errors=%d current_nr_sectors=%u\n",
-			  req->errors, blk_rq_cur_sectors(req));
+		swim3_dbg("           current_nr_sectors=%u\n",
+			  blk_rq_cur_sectors(req));
 #endif
 
 		if (blk_rq_pos(req) >= fs->total_secs) {
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 1d4c9f8bc1e1..f94614257462 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -111,7 +111,7 @@ static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	struct virtio_blk *vblk = req->q->queuedata;
@@ -119,7 +119,7 @@ static inline void virtblk_scsi_reques_done(struct request *req)
 
 	sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
 	sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
-	req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+	sreq->result = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
 }
 
 static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
@@ -144,7 +144,7 @@ static inline int virtblk_add_req_scsi(struct virtqueue *vq,
 {
 	return -EIO;
 }
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
 {
 }
 #define virtblk_ioctl	NULL
@@ -175,19 +175,15 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
-	int error = virtblk_result(vbr);
 
 	switch (req_op(req)) {
 	case REQ_OP_SCSI_IN:
 	case REQ_OP_SCSI_OUT:
-		virtblk_scsi_reques_done(req);
-		break;
-	case REQ_OP_DRV_IN:
-		req->errors = (error != 0);
+		virtblk_scsi_request_done(req);
 		break;
 	}
 
-	blk_mq_end_request(req, error);
+	blk_mq_end_request(req, virtblk_result(vbr));
 }
 
 static void virtblk_done(struct virtqueue *vq)
@@ -205,7 +201,7 @@ static void virtblk_done(struct virtqueue *vq)
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
 			struct request *req = blk_mq_rq_from_pdu(vbr);
 
-			blk_mq_complete_request(req, req->errors);
+			blk_mq_complete_request(req);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -310,7 +306,8 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	if (err)
 		goto out;
 
-	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+	blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+	err = virtblk_result(blk_mq_rq_to_pdu(req));
 out:
 	blk_put_request(req);
 	return err;
@@ -597,7 +594,7 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set)
 	return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
 }
 
-static struct blk_mq_ops virtio_mq_ops = {
+static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 5067a0a952cb..39459631667c 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -115,6 +115,15 @@ struct split_bio {
 	atomic_t pending;
 };
 
+struct blkif_req {
+	int	error;
+};
+
+static inline struct blkif_req *blkif_req(struct request *rq)
+{
+	return blk_mq_rq_to_pdu(rq);
+}
+
 static DEFINE_MUTEX(blkfront_mutex);
 static const struct block_device_operations xlvbd_block_fops;
 
@@ -907,8 +916,14 @@ out_busy:
 	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
-static struct blk_mq_ops blkfront_mq_ops = {
+static void blkif_complete_rq(struct request *rq)
+{
+	blk_mq_end_request(rq, blkif_req(rq)->error);
+}
+
+static const struct blk_mq_ops blkfront_mq_ops = {
 	.queue_rq = blkif_queue_rq,
+	.complete = blkif_complete_rq,
 };
 
 static void blkif_set_queue_limits(struct blkfront_info *info)
@@ -969,7 +984,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 		info->tag_set.queue_depth = BLK_RING_SIZE(info);
 	info->tag_set.numa_node = NUMA_NO_NODE;
 	info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
-	info->tag_set.cmd_size = 0;
+	info->tag_set.cmd_size = sizeof(struct blkif_req);
 	info->tag_set.driver_data = info;
 
 	if (blk_mq_alloc_tag_set(&info->tag_set))
@@ -1543,7 +1558,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 	unsigned long flags;
 	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
 	struct blkfront_info *info = rinfo->dev_info;
-	int error;
 
 	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
 		return IRQ_HANDLED;
@@ -1587,37 +1601,36 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			continue;
 		}
 
-		error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+		blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
 		switch (bret->operation) {
 		case BLKIF_OP_DISCARD:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 					   info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				blkif_req(req)->error = -EOPNOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
 				queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
 			}
-			blk_mq_complete_request(req, error);
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				blkif_req(req)->error = -EOPNOTSUPP;
 			}
 			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
 				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				blkif_req(req)->error = -EOPNOTSUPP;
 			}
-			if (unlikely(error)) {
-				if (error == -EOPNOTSUPP)
-					error = 0;
+			if (unlikely(blkif_req(req)->error)) {
+				if (blkif_req(req)->error == -EOPNOTSUPP)
+					blkif_req(req)->error = 0;
 				info->feature_fua = 0;
 				info->feature_flush = 0;
 				xlvbd_flush(info);
@@ -1629,11 +1642,12 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
 					"request: %x\n", bret->status);
 
-			blk_mq_complete_request(req, error);
 			break;
 		default:
 			BUG();
 		}
+
+		blk_mq_complete_request(req);
 	}
 
 	rinfo->ring.rsp_cons = i;
@@ -2345,6 +2359,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	unsigned long sector_size;
 	unsigned int physical_sector_size;
 	unsigned int binfo;
+	char *envp[] = { "RESIZE=1", NULL };
 	int err, i;
 
 	switch (info->connected) {
@@ -2361,6 +2376,8 @@ static void blkfront_connect(struct blkfront_info *info)
 		       sectors);
 		set_capacity(info->gd, sectors);
 		revalidate_disk(info->gd);
+		kobject_uevent_env(&disk_to_dev(info->gd)->kobj,
+				   KOBJ_CHANGE, envp);
 
 		return;
 	case BLKIF_STATE_SUSPENDED:
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e27d89a36c34..6fac5fedd610 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -523,7 +523,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE) {
-		copy_page(mem, cmem);
+		memcpy(mem, cmem, PAGE_SIZE);
 	} else {
 		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
 
@@ -717,7 +717,7 @@ compress_again:
 
 	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
 		src = kmap_atomic(page);
-		copy_page(cmem, src);
+		memcpy(cmem, src, PAGE_SIZE);
 		kunmap_atomic(src);
 	} else {
 		memcpy(cmem, src, clen);
@@ -829,10 +829,14 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 	offset = (bio->bi_iter.bi_sector &
 		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
-	if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 		zram_bio_discard(zram, index, offset, bio);
 		bio_endio(bio);
 		return;
+	default:
+		break;
 	}
 
 	bio_for_each_segment(bvec, bio, iter) {
@@ -928,7 +932,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	}
 
 	index = sector >> SECTORS_PER_PAGE_SHIFT;
-	offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+	offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
 	bv.bv_page = page;
 	bv.bv_len = PAGE_SIZE;
@@ -1189,7 +1193,11 @@ static int zram_add(void)
 	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
 	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
+	zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
+	zram->disk->queue->limits.chunk_sectors = 0;
 	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+
 	/*
 	 * zram_bio_discard() will clear all logical blocks if logical block
 	 * size is identical with physical block size(PAGE_SIZE). But if it is
@@ -1199,10 +1207,7 @@ static int zram_add(void)
 	 * zeroed.
 	 */
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
-		zram->disk->queue->limits.discard_zeroes_data = 1;
-	else
-		zram->disk->queue->limits.discard_zeroes_data = 0;
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
 	add_disk(zram->disk);
 
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index c2c14a12713b..737d93ef27c5 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -76,6 +76,12 @@ config BT_HCIUART
 	  Say Y here to compile support for Bluetooth UART devices into the
 	  kernel or say M to compile it as module (hci_uart).
 
+config BT_HCIUART_SERDEV
+	bool
+	depends on SERIAL_DEV_BUS && BT_HCIUART
+	depends on SERIAL_DEV_BUS=y || SERIAL_DEV_BUS=BT_HCIUART
+	default y
+
 config BT_HCIUART_H4
 	bool "UART (H4) protocol support"
 	depends on BT_HCIUART
@@ -86,6 +92,18 @@ config BT_HCIUART_H4
 
 	  Say Y here to compile support for HCI UART (H4) protocol.
 
+config BT_HCIUART_NOKIA
+	tristate "UART Nokia H4+ protocol support"
+	depends on BT_HCIUART
+	depends on BT_HCIUART_SERDEV
+	depends on PM
+	help
+	  Nokia H4+ is serial protocol for communication between Bluetooth
+	  device and host. This protocol is required for Bluetooth devices
+	  with UART interface in Nokia devices.
+
+	  Say Y here to compile support for Nokia's H4+ protocol.
+
 config BT_HCIUART_BCSP
 	bool "BCSP protocol support"
 	depends on BT_HCIUART
@@ -344,7 +362,8 @@ config BT_WILINK
 
 config BT_QCOMSMD
 	tristate "Qualcomm SMD based HCI support"
-	depends on (QCOM_SMD && QCOM_WCNSS_CTRL) || COMPILE_TEST
+	depends on RPMSG || (COMPILE_TEST && RPMSG=n)
+	depends on QCOM_WCNSS_CTRL || (COMPILE_TEST && QCOM_WCNSS_CTRL=n)
 	select BT_QCA
 	help
 	  Qualcomm SMD based HCI driver.
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index 80627187c8b6..e693ca6eeed9 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -25,10 +25,13 @@ obj-$(CONFIG_BT_BCM)		+= btbcm.o
 obj-$(CONFIG_BT_RTL)		+= btrtl.o
 obj-$(CONFIG_BT_QCA)		+= btqca.o
 
+obj-$(CONFIG_BT_HCIUART_NOKIA)	+= hci_nokia.o
+
 btmrvl-y			:= btmrvl_main.o
 btmrvl-$(CONFIG_DEBUG_FS)	+= btmrvl_debugfs.o
 
 hci_uart-y				:= hci_ldisc.o
+hci_uart-$(CONFIG_BT_HCIUART_SERDEV)	+= hci_serdev.o
 hci_uart-$(CONFIG_BT_HCIUART_H4)	+= hci_h4.o
 hci_uart-$(CONFIG_BT_HCIUART_BCSP)	+= hci_bcsp.o
 hci_uart-$(CONFIG_BT_HCIUART_LL)	+= hci_ll.o
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index c0b3b5576992..007c0a45f31b 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -695,9 +695,8 @@ static int bluecard_open(struct bluecard_info *info)
 
 	spin_lock_init(&(info->lock));
 
-	init_timer(&(info->timer));
-	info->timer.function = &bluecard_activity_led_timeout;
-	info->timer.data = (u_long)info;
+	setup_timer(&(info->timer), &bluecard_activity_led_timeout,
+		    (u_long)info);
 
 	skb_queue_head_init(&(info->txq));
 
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 08e01f002bad..eb794f08b238 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -20,6 +20,7 @@
 
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/suspend.h>
 
 #include <linux/mmc/sdio_ids.h>
 #include <linux/mmc/sdio_func.h>
@@ -60,13 +61,15 @@ static const struct of_device_id btmrvl_sdio_of_match_table[] = {
 
 static irqreturn_t btmrvl_wake_irq_bt(int irq, void *priv)
 {
-	struct btmrvl_plt_wake_cfg *cfg = priv;
+	struct btmrvl_sdio_card *card = priv;
+	struct btmrvl_plt_wake_cfg *cfg = card->plt_wake_cfg;
 
-	if (cfg->irq_bt >= 0) {
-		pr_info("%s: wake by bt", __func__);
-		cfg->wake_by_bt = true;
-		disable_irq_nosync(irq);
-	}
+	pr_info("%s: wake by bt", __func__);
+	cfg->wake_by_bt = true;
+	disable_irq_nosync(irq);
+
+	pm_wakeup_event(&card->func->dev, 0);
+	pm_system_wakeup();
 
 	return IRQ_HANDLED;
 }
@@ -101,7 +104,7 @@ static int btmrvl_sdio_probe_of(struct device *dev,
 		} else {
 			ret = devm_request_irq(dev, cfg->irq_bt,
 					       btmrvl_wake_irq_bt,
-					       0, "bt_wake", cfg);
+					       0, "bt_wake", card);
 			if (ret) {
 				dev_err(dev,
 					"Failed to request irq_bt %d (%d)\n",
@@ -1574,7 +1577,7 @@ static void btmrvl_sdio_remove(struct sdio_func *func)
 							MODULE_SHUTDOWN_REQ);
 				btmrvl_sdio_disable_host_int(card);
 			}
-			BT_DBG("unregester dev");
+			BT_DBG("unregister dev");
 			card->priv->surprise_removed = true;
 			btmrvl_sdio_unregister_dev(card);
 			btmrvl_remove_card(card->priv);
@@ -1625,6 +1628,13 @@ static int btmrvl_sdio_suspend(struct device *dev)
 	if (priv->adapter->hs_state != HS_ACTIVATED) {
 		if (btmrvl_enable_hs(priv)) {
 			BT_ERR("HS not activated, suspend failed!");
+			/* Disable platform specific wakeup interrupt */
+			if (card->plt_wake_cfg &&
+			    card->plt_wake_cfg->irq_bt >= 0) {
+				disable_irq_wake(card->plt_wake_cfg->irq_bt);
+				disable_irq(card->plt_wake_cfg->irq_bt);
+			}
+
 			priv->adapter->is_suspending = false;
 			return -EBUSY;
 		}
@@ -1637,10 +1647,10 @@ static int btmrvl_sdio_suspend(struct device *dev)
 	if (priv->adapter->hs_state == HS_ACTIVATED) {
 		BT_DBG("suspend with MMC_PM_KEEP_POWER");
 		return sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
-	} else {
-		BT_DBG("suspend without MMC_PM_KEEP_POWER");
-		return 0;
 	}
+
+	BT_DBG("suspend without MMC_PM_KEEP_POWER");
+	return 0;
 }
 
 static int btmrvl_sdio_resume(struct device *dev)
diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c
index 8d4868af9bbd..ef730c173d4b 100644
--- a/drivers/bluetooth/btqcomsmd.c
+++ b/drivers/bluetooth/btqcomsmd.c
@@ -14,7 +14,7 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
 #include <linux/platform_device.h>
 
@@ -26,8 +26,8 @@
 struct btqcomsmd {
 	struct hci_dev *hdev;
 
-	struct qcom_smd_channel *acl_channel;
-	struct qcom_smd_channel *cmd_channel;
+	struct rpmsg_endpoint *acl_channel;
+	struct rpmsg_endpoint *cmd_channel;
 };
 
 static int btqcomsmd_recv(struct hci_dev *hdev, unsigned int type,
@@ -48,19 +48,19 @@ static int btqcomsmd_recv(struct hci_dev *hdev, unsigned int type,
 	return hci_recv_frame(hdev, skb);
 }
 
-static int btqcomsmd_acl_callback(struct qcom_smd_channel *channel,
-				  const void *data, size_t count)
+static int btqcomsmd_acl_callback(struct rpmsg_device *rpdev, void *data,
+				  int count, void *priv, u32 addr)
 {
-	struct btqcomsmd *btq = qcom_smd_get_drvdata(channel);
+	struct btqcomsmd *btq = priv;
 
 	btq->hdev->stat.byte_rx += count;
 	return btqcomsmd_recv(btq->hdev, HCI_ACLDATA_PKT, data, count);
 }
 
-static int btqcomsmd_cmd_callback(struct qcom_smd_channel *channel,
-				  const void *data, size_t count)
+static int btqcomsmd_cmd_callback(struct rpmsg_device *rpdev, void *data,
+				  int count, void *priv, u32 addr)
 {
-	struct btqcomsmd *btq = qcom_smd_get_drvdata(channel);
+	struct btqcomsmd *btq = priv;
 
 	return btqcomsmd_recv(btq->hdev, HCI_EVENT_PKT, data, count);
 }
@@ -72,12 +72,12 @@ static int btqcomsmd_send(struct hci_dev *hdev, struct sk_buff *skb)
 
 	switch (hci_skb_pkt_type(skb)) {
 	case HCI_ACLDATA_PKT:
-		ret = qcom_smd_send(btq->acl_channel, skb->data, skb->len);
+		ret = rpmsg_send(btq->acl_channel, skb->data, skb->len);
 		hdev->stat.acl_tx++;
 		hdev->stat.byte_tx += skb->len;
 		break;
 	case HCI_COMMAND_PKT:
-		ret = qcom_smd_send(btq->cmd_channel, skb->data, skb->len);
+		ret = rpmsg_send(btq->cmd_channel, skb->data, skb->len);
 		hdev->stat.cmd_tx++;
 		break;
 	default:
@@ -114,18 +114,15 @@ static int btqcomsmd_probe(struct platform_device *pdev)
 	wcnss = dev_get_drvdata(pdev->dev.parent);
 
 	btq->acl_channel = qcom_wcnss_open_channel(wcnss, "APPS_RIVA_BT_ACL",
-						   btqcomsmd_acl_callback);
+						   btqcomsmd_acl_callback, btq);
 	if (IS_ERR(btq->acl_channel))
 		return PTR_ERR(btq->acl_channel);
 
 	btq->cmd_channel = qcom_wcnss_open_channel(wcnss, "APPS_RIVA_BT_CMD",
-						   btqcomsmd_cmd_callback);
+						   btqcomsmd_cmd_callback, btq);
 	if (IS_ERR(btq->cmd_channel))
 		return PTR_ERR(btq->cmd_channel);
 
-	qcom_smd_set_drvdata(btq->acl_channel, btq);
-	qcom_smd_set_drvdata(btq->cmd_channel, btq);
-
 	hdev = hci_alloc_dev();
 	if (!hdev)
 		return -ENOMEM;
@@ -158,6 +155,9 @@ static int btqcomsmd_remove(struct platform_device *pdev)
 	hci_unregister_dev(btq->hdev);
 	hci_free_dev(btq->hdev);
 
+	rpmsg_destroy_ept(btq->cmd_channel);
+	rpmsg_destroy_ept(btq->acl_channel);
+
 	return 0;
 }
 
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index fc9b25703c67..8279094dd713 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -275,11 +275,8 @@ static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff)
 
 	BT_INFO("%s: rtl: loading %s", hdev->name, name);
 	ret = request_firmware(&fw, name, &hdev->dev);
-	if (ret < 0) {
-		BT_ERR("%s: Failed to load %s", hdev->name, name);
+	if (ret < 0)
 		return ret;
-	}
-
 	ret = fw->size;
 	*buff = kmemdup(fw->data, ret, GFP_KERNEL);
 
@@ -331,6 +328,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
 	u8 *cfg_buff = NULL;
 	u8 *tbuff;
 	char *cfg_name = NULL;
+	bool config_needed = false;
 
 	switch (lmp_subver) {
 	case RTL_ROM_LMP_8723B:
@@ -344,6 +342,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
 		break;
 	case RTL_ROM_LMP_8822B:
 		cfg_name = "rtl_bt/rtl8822b_config.bin";
+		config_needed = true;
 		break;
 	default:
 		BT_ERR("%s: rtl: no config according to lmp_subver %04x",
@@ -353,8 +352,12 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
 
 	if (cfg_name) {
 		cfg_sz = rtl_load_config(hdev, cfg_name, &cfg_buff);
-		if (cfg_sz < 0)
+		if (cfg_sz < 0) {
 			cfg_sz = 0;
+			if (config_needed)
+				BT_ERR("Necessary config file %s not found\n",
+				       cfg_name);
+		}
 	} else
 		cfg_sz = 0;
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 1c8094ef3f22..7fa373b428f8 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -26,6 +26,7 @@
 #include <linux/firmware.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
+#include <linux/suspend.h>
 #include <asm/unaligned.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -262,6 +263,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME },
+	{ USB_DEVICE(0x0cf3, 0xe301), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0489, 0xe092), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME },
@@ -328,6 +330,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x1286, 0x204e), .driver_info = BTUSB_MARVELL },
 
 	/* Intel Bluetooth devices */
+	{ USB_DEVICE(0x8087, 0x0025), .driver_info = BTUSB_INTEL_NEW },
 	{ USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR },
 	{ USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL },
 	{ USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL },
@@ -2024,13 +2027,18 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return -EINVAL;
 	}
 
-	/* At the moment the iBT 3.0 hardware variants 0x0b (LnP/SfP)
-	 * and 0x0c (WsP) are supported by this firmware loading method.
+	/* Check for supported iBT hardware variants of this firmware
+	 * loading method.
 	 *
 	 * This check has been put in place to ensure correct forward
 	 * compatibility options when newer hardware variants come along.
 	 */
-	if (ver.hw_variant != 0x0b && ver.hw_variant != 0x0c) {
+	switch (ver.hw_variant) {
+	case 0x0b:	/* SfP */
+	case 0x0c:	/* WsP */
+	case 0x12:	/* ThP */
+		break;
+	default:
 		BT_ERR("%s: Unsupported Intel hardware variant (%u)",
 		       hdev->name, ver.hw_variant);
 		return -EINVAL;
@@ -2792,6 +2800,7 @@ static irqreturn_t btusb_oob_wake_handler(int irq, void *priv)
 	struct btusb_data *data = priv;
 
 	pm_wakeup_event(&data->udev->dev, 0);
+	pm_system_wakeup();
 
 	/* Disable only if not already disabled (keep it balanced) */
 	if (test_and_clear_bit(BTUSB_OOB_WAKE_ENABLED, &data->flags)) {
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 5262a2077d7a..f87bfdfee4ff 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -146,13 +146,13 @@ static bool bcm_device_exists(struct bcm_device *device)
 static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 {
 	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled)
-		clk_enable(dev->clk);
+		clk_prepare_enable(dev->clk);
 
 	gpiod_set_value(dev->shutdown, powered);
 	gpiod_set_value(dev->device_wakeup, powered);
 
 	if (!powered && !IS_ERR(dev->clk) && dev->clk_enabled)
-		clk_disable(dev->clk);
+		clk_disable_unprepare(dev->clk);
 
 	dev->clk_enabled = powered;
 
@@ -287,6 +287,9 @@ static int bcm_open(struct hci_uart *hu)
 
 	hu->priv = bcm;
 
+	if (!hu->tty->dev)
+		goto out;
+
 	mutex_lock(&bcm_device_lock);
 	list_for_each(p, &bcm_device_list) {
 		struct bcm_device *dev = list_entry(p, struct bcm_device, list);
@@ -307,7 +310,7 @@ static int bcm_open(struct hci_uart *hu)
 	}
 
 	mutex_unlock(&bcm_device_lock);
-
+out:
 	return 0;
 }
 
@@ -697,28 +700,14 @@ static int bcm_resource(struct acpi_resource *ares, void *data)
 	/* Always tell the ACPI core to skip this resource */
 	return 1;
 }
+#endif /* CONFIG_ACPI */
 
-static int bcm_acpi_probe(struct bcm_device *dev)
+static int bcm_platform_probe(struct bcm_device *dev)
 {
 	struct platform_device *pdev = dev->pdev;
-	LIST_HEAD(resources);
-	const struct dmi_system_id *dmi_id;
-	const struct acpi_gpio_mapping *gpio_mapping = acpi_bcm_int_last_gpios;
-	const struct acpi_device_id *id;
-	int ret;
 
 	dev->name = dev_name(&pdev->dev);
 
-	/* Retrieve GPIO data */
-	id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev);
-	if (id)
-		gpio_mapping = (const struct acpi_gpio_mapping *) id->driver_data;
-
-	ret = acpi_dev_add_driver_gpios(ACPI_COMPANION(&pdev->dev),
-					gpio_mapping);
-	if (ret)
-		return ret;
-
 	dev->clk = devm_clk_get(&pdev->dev, NULL);
 
 	dev->device_wakeup = devm_gpiod_get_optional(&pdev->dev,
@@ -755,6 +744,33 @@ static int bcm_acpi_probe(struct bcm_device *dev)
 		return -EINVAL;
 	}
 
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+static int bcm_acpi_probe(struct bcm_device *dev)
+{
+	struct platform_device *pdev = dev->pdev;
+	LIST_HEAD(resources);
+	const struct dmi_system_id *dmi_id;
+	const struct acpi_gpio_mapping *gpio_mapping = acpi_bcm_int_last_gpios;
+	const struct acpi_device_id *id;
+	int ret;
+
+	/* Retrieve GPIO data */
+	id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev);
+	if (id)
+		gpio_mapping = (const struct acpi_gpio_mapping *) id->driver_data;
+
+	ret = acpi_dev_add_driver_gpios(ACPI_COMPANION(&pdev->dev),
+					gpio_mapping);
+	if (ret)
+		return ret;
+
+	ret = bcm_platform_probe(dev);
+	if (ret)
+		return ret;
+
 	/* Retrieve UART ACPI info */
 	ret = acpi_dev_get_resources(ACPI_COMPANION(&dev->pdev->dev),
 				     &resources, bcm_resource, dev);
@@ -789,7 +805,10 @@ static int bcm_probe(struct platform_device *pdev)
 
 	dev->pdev = pdev;
 
-	ret = bcm_acpi_probe(dev);
+	if (has_acpi_companion(&pdev->dev))
+		ret = bcm_acpi_probe(dev);
+	else
+		ret = bcm_platform_probe(dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
index 635597b6e168..82e5a32b87a4 100644
--- a/drivers/bluetooth/hci_h4.c
+++ b/drivers/bluetooth/hci_h4.c
@@ -171,9 +171,20 @@ struct sk_buff *h4_recv_buf(struct hci_dev *hdev, struct sk_buff *skb,
 			    const unsigned char *buffer, int count,
 			    const struct h4_recv_pkt *pkts, int pkts_count)
 {
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	u8 alignment = hu->alignment;
+
 	while (count) {
 		int i, len;
 
+		/* remove padding bytes from buffer */
+		for (; hu->padding && count > 0; hu->padding--) {
+			count--;
+			buffer++;
+		}
+		if (!count)
+			break;
+
 		if (!skb) {
 			for (i = 0; i < pkts_count; i++) {
 				if (buffer[0] != (&pkts[i])->type)
@@ -253,11 +264,17 @@ struct sk_buff *h4_recv_buf(struct hci_dev *hdev, struct sk_buff *skb,
 			}
 
 			if (!dlen) {
+				hu->padding = (skb->len - 1) % alignment;
+				hu->padding = (alignment - hu->padding) % alignment;
+
 				/* No more data, complete frame */
 				(&pkts[i])->recv(hdev, skb);
 				skb = NULL;
 			}
 		} else {
+			hu->padding = (skb->len - 1) % alignment;
+			hu->padding = (alignment - hu->padding) % alignment;
+
 			/* Complete frame */
 			(&pkts[i])->recv(hdev, skb);
 			skb = NULL;
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 9e271286c5e5..fa5099986f1b 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -307,6 +307,9 @@ static int intel_set_power(struct hci_uart *hu, bool powered)
 	struct list_head *p;
 	int err = -ENODEV;
 
+	if (!hu->tty->dev)
+		return err;
+
 	mutex_lock(&intel_device_list_lock);
 
 	list_for_each(p, &intel_device_list) {
@@ -379,6 +382,9 @@ static void intel_busy_work(struct work_struct *work)
 	struct intel_data *intel = container_of(work, struct intel_data,
 						busy_work);
 
+	if (!intel->hu->tty->dev)
+		return;
+
 	/* Link is busy, delay the suspend */
 	mutex_lock(&intel_device_list_lock);
 	list_for_each(p, &intel_device_list) {
@@ -601,12 +607,18 @@ static int intel_setup(struct hci_uart *hu)
 		return -EINVAL;
 	}
 
-	/* At the moment only the hardware variant iBT 3.0 (LnP/SfP) is
-	 * supported by this firmware loading method. This check has been
-	 * put in place to ensure correct forward compatibility options
-	 * when newer hardware variants come along.
-	 */
-	if (ver.hw_variant != 0x0b) {
+        /* Check for supported iBT hardware variants of this firmware
+         * loading method.
+         *
+         * This check has been put in place to ensure correct forward
+         * compatibility options when newer hardware variants come along.
+         */
+	switch (ver.hw_variant) {
+	case 0x0b:	/* LnP */
+	case 0x0c:	/* WsP */
+	case 0x12:	/* ThP */
+		break;
+	default:
 		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
 			   ver.hw_variant);
 		return -EINVAL;
@@ -699,11 +711,14 @@ static int intel_setup(struct hci_uart *hu)
 	/* With this Intel bootloader only the hardware variant and device
 	 * revision information are used to select the right firmware.
 	 *
-	 * Currently this bootloader support is limited to hardware variant
-	 * iBT 3.0 (LnP/SfP) which is identified by the value 11 (0x0b).
+	 * The firmware filename is ibt-<hw_variant>-<dev_revid>.sfi.
+	 *
+	 * Currently the supported hardware variants are:
+	 *   11 (0x0b) for iBT 3.0 (LnP/SfP)
 	 */
-	snprintf(fwname, sizeof(fwname), "intel/ibt-11-%u.sfi",
-		 le16_to_cpu(params->dev_revid));
+	snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
+		le16_to_cpu(ver.hw_variant),
+		le16_to_cpu(params->dev_revid));
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err < 0) {
@@ -716,8 +731,9 @@ static int intel_setup(struct hci_uart *hu)
 	bt_dev_info(hdev, "Found device firmware: %s", fwname);
 
 	/* Save the DDC file name for later */
-	snprintf(fwname, sizeof(fwname), "intel/ibt-11-%u.ddc",
-		 le16_to_cpu(params->dev_revid));
+	snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
+		le16_to_cpu(ver.hw_variant),
+		le16_to_cpu(params->dev_revid));
 
 	kfree_skb(skb);
 
@@ -889,6 +905,8 @@ done:
 	list_for_each(p, &intel_device_list) {
 		struct intel_device *dev = list_entry(p, struct intel_device,
 						      list);
+		if (!hu->tty->dev)
+			break;
 		if (hu->tty->dev->parent == dev->pdev->dev.parent) {
 			if (device_may_wakeup(&dev->pdev->dev)) {
 				set_bit(STATE_LPM_ENABLED, &intel->flags);
@@ -1056,6 +1074,9 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 
 	BT_DBG("hu %p skb %p", hu, skb);
 
+	if (!hu->tty->dev)
+		goto out_enqueue;
+
 	/* Be sure our controller is resumed and potential LPM transaction
 	 * completed before enqueuing any packet.
 	 */
@@ -1072,7 +1093,7 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 		}
 	}
 	mutex_unlock(&intel_device_list_lock);
-
+out_enqueue:
 	skb_queue_tail(&intel->txq, skb);
 
 	return 0;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 9497c469efd2..2edd30556956 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -113,16 +113,21 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 {
 	struct sk_buff *skb = hu->tx_skb;
 
-	if (!skb)
-		skb = hu->proto->dequeue(hu);
-	else
+	if (!skb) {
+		if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+			skb = hu->proto->dequeue(hu);
+	} else {
 		hu->tx_skb = NULL;
+	}
 
 	return skb;
 }
 
 int hci_uart_tx_wakeup(struct hci_uart *hu)
 {
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		return 0;
+
 	if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) {
 		set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 		return 0;
@@ -134,6 +139,7 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hci_uart_tx_wakeup);
 
 static void hci_uart_write_work(struct work_struct *work)
 {
@@ -176,6 +182,7 @@ static void hci_uart_init_work(struct work_struct *work)
 {
 	struct hci_uart *hu = container_of(work, struct hci_uart, init_ready);
 	int err;
+	struct hci_dev *hdev;
 
 	if (!test_and_clear_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags))
 		return;
@@ -183,9 +190,12 @@ static void hci_uart_init_work(struct work_struct *work)
 	err = hci_register_dev(hu->hdev);
 	if (err < 0) {
 		BT_ERR("Can't register HCI device");
-		hci_free_dev(hu->hdev);
+		hdev = hu->hdev;
 		hu->hdev = NULL;
+		hci_free_dev(hdev);
+		clear_bit(HCI_UART_PROTO_READY, &hu->flags);
 		hu->proto->close(hu);
+		return;
 	}
 
 	set_bit(HCI_UART_REGISTERED, &hu->flags);
@@ -251,6 +261,9 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	BT_DBG("%s: type %d len %d", hdev->name, hci_skb_pkt_type(skb),
 	       skb->len);
 
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		return -EUNATCH;
+
 	hu->proto->enqueue(hu, skb);
 
 	hci_uart_tx_wakeup(hu);
@@ -318,25 +331,6 @@ void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed,
 	hu->oper_speed = oper_speed;
 }
 
-void hci_uart_init_tty(struct hci_uart *hu)
-{
-	struct tty_struct *tty = hu->tty;
-	struct ktermios ktermios;
-
-	/* Bring the UART into a known 8 bits no parity hw fc state */
-	ktermios = tty->termios;
-	ktermios.c_iflag &= ~(IGNBRK | BRKINT | PARMRK | ISTRIP |
-			      INLCR | IGNCR | ICRNL | IXON);
-	ktermios.c_oflag &= ~OPOST;
-	ktermios.c_lflag &= ~(ECHO | ECHONL | ICANON | ISIG | IEXTEN);
-	ktermios.c_cflag &= ~(CSIZE | PARENB);
-	ktermios.c_cflag |= CS8;
-	ktermios.c_cflag |= CRTSCTS;
-
-	/* tty_set_termios() return not checked as it is always 0 */
-	tty_set_termios(tty, &ktermios);
-}
-
 void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed)
 {
 	struct tty_struct *tty = hu->tty;
@@ -459,6 +453,10 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	hu->tty = tty;
 	tty->receive_room = 65536;
 
+	/* disable alignment support by default */
+	hu->alignment = 1;
+	hu->padding = 0;
+
 	INIT_WORK(&hu->init_ready, hci_uart_init_work);
 	INIT_WORK(&hu->write_work, hci_uart_write_work);
 
@@ -616,6 +614,7 @@ static int hci_uart_register_dev(struct hci_uart *hu)
 
 	if (hci_register_dev(hdev) < 0) {
 		BT_ERR("Can't register HCI device");
+		hu->hdev = NULL;
 		hci_free_dev(hdev);
 		return -ENODEV;
 	}
diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c
index 02692fe30279..adc444f309a3 100644
--- a/drivers/bluetooth/hci_ll.c
+++ b/drivers/bluetooth/hci_ll.c
@@ -34,20 +34,24 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
+#include <linux/firmware.h>
 #include <linux/interrupt.h>
 #include <linux/ptrace.h>
 #include <linux/poll.h>
 
 #include <linux/slab.h>
-#include <linux/tty.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/signal.h>
 #include <linux/ioctl.h>
+#include <linux/of.h>
+#include <linux/serdev.h>
 #include <linux/skbuff.h>
+#include <linux/ti_wilink_st.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <linux/gpio/consumer.h>
 
 #include "hci_uart.h"
 
@@ -76,6 +80,12 @@ struct hcill_cmd {
 	u8 cmd;
 } __packed;
 
+struct ll_device {
+	struct hci_uart hu;
+	struct serdev_device *serdev;
+	struct gpio_desc *enable_gpio;
+};
+
 struct ll_struct {
 	unsigned long rx_state;
 	unsigned long rx_count;
@@ -136,6 +146,9 @@ static int ll_open(struct hci_uart *hu)
 
 	hu->priv = ll;
 
+	if (hu->serdev)
+		serdev_device_open(hu->serdev);
+
 	return 0;
 }
 
@@ -164,6 +177,13 @@ static int ll_close(struct hci_uart *hu)
 
 	kfree_skb(ll->rx_skb);
 
+	if (hu->serdev) {
+		struct ll_device *lldev = serdev_device_get_drvdata(hu->serdev);
+		gpiod_set_value_cansleep(lldev->enable_gpio, 0);
+
+		serdev_device_close(hu->serdev);
+	}
+
 	hu->priv = NULL;
 
 	kfree(ll);
@@ -505,9 +525,244 @@ static struct sk_buff *ll_dequeue(struct hci_uart *hu)
 	return skb_dequeue(&ll->txq);
 }
 
+#if IS_ENABLED(CONFIG_SERIAL_DEV_BUS)
+static int read_local_version(struct hci_dev *hdev)
+{
+	int err = 0;
+	unsigned short version = 0;
+	struct sk_buff *skb;
+	struct hci_rp_read_local_version *ver;
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		bt_dev_err(hdev, "Reading TI version information failed (%ld)",
+			   PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+	if (skb->len != sizeof(*ver)) {
+		err = -EILSEQ;
+		goto out;
+	}
+
+	ver = (struct hci_rp_read_local_version *)skb->data;
+	if (le16_to_cpu(ver->manufacturer) != 13) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	version = le16_to_cpu(ver->lmp_subver);
+
+out:
+	if (err) bt_dev_err(hdev, "Failed to read TI version info: %d", err);
+	kfree_skb(skb);
+	return err ? err : version;
+}
+
+/**
+ * download_firmware -
+ *	internal function which parses through the .bts firmware
+ *	script file intreprets SEND, DELAY actions only as of now
+ */
+static int download_firmware(struct ll_device *lldev)
+{
+	unsigned short chip, min_ver, maj_ver;
+	int version, err, len;
+	unsigned char *ptr, *action_ptr;
+	unsigned char bts_scr_name[40];	/* 40 char long bts scr name? */
+	const struct firmware *fw;
+	struct sk_buff *skb;
+	struct hci_command *cmd;
+
+	version = read_local_version(lldev->hu.hdev);
+	if (version < 0)
+		return version;
+
+	chip = (version & 0x7C00) >> 10;
+	min_ver = (version & 0x007F);
+	maj_ver = (version & 0x0380) >> 7;
+	if (version & 0x8000)
+		maj_ver |= 0x0008;
+
+	snprintf(bts_scr_name, sizeof(bts_scr_name),
+		 "ti-connectivity/TIInit_%d.%d.%d.bts",
+		 chip, maj_ver, min_ver);
+
+	err = request_firmware(&fw, bts_scr_name, &lldev->serdev->dev);
+	if (err || !fw->data || !fw->size) {
+		bt_dev_err(lldev->hu.hdev, "request_firmware failed(errno %d) for %s",
+			   err, bts_scr_name);
+		return -EINVAL;
+	}
+	ptr = (void *)fw->data;
+	len = fw->size;
+	/* bts_header to remove out magic number and
+	 * version
+	 */
+	ptr += sizeof(struct bts_header);
+	len -= sizeof(struct bts_header);
+
+	while (len > 0 && ptr) {
+		bt_dev_dbg(lldev->hu.hdev, " action size %d, type %d ",
+			   ((struct bts_action *)ptr)->size,
+			   ((struct bts_action *)ptr)->type);
+
+		action_ptr = &(((struct bts_action *)ptr)->data[0]);
+
+		switch (((struct bts_action *)ptr)->type) {
+		case ACTION_SEND_COMMAND:	/* action send */
+			bt_dev_dbg(lldev->hu.hdev, "S");
+			cmd = (struct hci_command *)action_ptr;
+			if (cmd->opcode == 0xff36) {
+				/* ignore remote change
+				 * baud rate HCI VS command */
+				bt_dev_warn(lldev->hu.hdev, "change remote baud rate command in firmware");
+				break;
+			}
+			if (cmd->prefix != 1)
+				bt_dev_dbg(lldev->hu.hdev, "command type %d\n", cmd->prefix);
+
+			skb = __hci_cmd_sync(lldev->hu.hdev, cmd->opcode, cmd->plen, &cmd->speed, HCI_INIT_TIMEOUT);
+			if (IS_ERR(skb)) {
+				bt_dev_err(lldev->hu.hdev, "send command failed\n");
+				goto out_rel_fw;
+			}
+			kfree_skb(skb);
+			break;
+		case ACTION_WAIT_EVENT:  /* wait */
+			/* no need to wait as command was synchronous */
+			bt_dev_dbg(lldev->hu.hdev, "W");
+			break;
+		case ACTION_DELAY:	/* sleep */
+			bt_dev_info(lldev->hu.hdev, "sleep command in scr");
+			mdelay(((struct bts_action_delay *)action_ptr)->msec);
+			break;
+		}
+		len -= (sizeof(struct bts_action) +
+			((struct bts_action *)ptr)->size);
+		ptr += sizeof(struct bts_action) +
+			((struct bts_action *)ptr)->size;
+	}
+
+out_rel_fw:
+	/* fw download complete */
+	release_firmware(fw);
+	return err;
+}
+
+static int ll_setup(struct hci_uart *hu)
+{
+	int err, retry = 3;
+	struct ll_device *lldev;
+	struct serdev_device *serdev = hu->serdev;
+	u32 speed;
+
+	if (!serdev)
+		return 0;
+
+	lldev = serdev_device_get_drvdata(serdev);
+
+	serdev_device_set_flow_control(serdev, true);
+
+	do {
+		/* Configure BT_EN to HIGH state */
+		gpiod_set_value_cansleep(lldev->enable_gpio, 0);
+		msleep(5);
+		gpiod_set_value_cansleep(lldev->enable_gpio, 1);
+		msleep(100);
+
+		err = download_firmware(lldev);
+		if (!err)
+			break;
+
+		/* Toggle BT_EN and retry */
+		bt_dev_err(hu->hdev, "download firmware failed, retrying...");
+	} while (retry--);
+
+	if (err)
+		return err;
+
+	/* Operational speed if any */
+	if (hu->oper_speed)
+		speed = hu->oper_speed;
+	else if (hu->proto->oper_speed)
+		speed = hu->proto->oper_speed;
+	else
+		speed = 0;
+
+	if (speed) {
+		struct sk_buff *skb = __hci_cmd_sync(hu->hdev, 0xff36, sizeof(speed), &speed, HCI_INIT_TIMEOUT);
+		if (!IS_ERR(skb)) {
+			kfree_skb(skb);
+			serdev_device_set_baudrate(serdev, speed);
+		}
+	}
+
+	return 0;
+}
+
+static const struct hci_uart_proto llp;
+
+static int hci_ti_probe(struct serdev_device *serdev)
+{
+	struct hci_uart *hu;
+	struct ll_device *lldev;
+	u32 max_speed = 3000000;
+
+	lldev = devm_kzalloc(&serdev->dev, sizeof(struct ll_device), GFP_KERNEL);
+	if (!lldev)
+		return -ENOMEM;
+	hu = &lldev->hu;
+
+	serdev_device_set_drvdata(serdev, lldev);
+	lldev->serdev = hu->serdev = serdev;
+
+	lldev->enable_gpio = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(lldev->enable_gpio))
+		return PTR_ERR(lldev->enable_gpio);
+
+	of_property_read_u32(serdev->dev.of_node, "max-speed", &max_speed);
+	hci_uart_set_speeds(hu, 115200, max_speed);
+
+	return hci_uart_register_device(hu, &llp);
+}
+
+static void hci_ti_remove(struct serdev_device *serdev)
+{
+	struct ll_device *lldev = serdev_device_get_drvdata(serdev);
+	struct hci_uart *hu = &lldev->hu;
+	struct hci_dev *hdev = hu->hdev;
+
+	cancel_work_sync(&hu->write_work);
+
+	hci_unregister_dev(hdev);
+	hci_free_dev(hdev);
+	hu->proto->close(hu);
+}
+
+static const struct of_device_id hci_ti_of_match[] = {
+	{ .compatible = "ti,wl1831-st" },
+	{ .compatible = "ti,wl1835-st" },
+	{ .compatible = "ti,wl1837-st" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, hci_ti_of_match);
+
+static struct serdev_device_driver hci_ti_drv = {
+	.driver		= {
+		.name	= "hci-ti",
+		.of_match_table = of_match_ptr(hci_ti_of_match),
+	},
+	.probe	= hci_ti_probe,
+	.remove	= hci_ti_remove,
+};
+#else
+#define ll_setup NULL
+#endif
+
 static const struct hci_uart_proto llp = {
 	.id		= HCI_UART_LL,
 	.name		= "LL",
+	.setup		= ll_setup,
 	.open		= ll_open,
 	.close		= ll_close,
 	.recv		= ll_recv,
@@ -518,10 +773,14 @@ static const struct hci_uart_proto llp = {
 
 int __init ll_init(void)
 {
+	serdev_device_driver_register(&hci_ti_drv);
+
 	return hci_uart_register_proto(&llp);
 }
 
 int __exit ll_deinit(void)
 {
+	serdev_device_driver_unregister(&hci_ti_drv);
+
 	return hci_uart_unregister_proto(&llp);
 }
diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c
new file mode 100644
index 000000000000..a7d687d8d456
--- /dev/null
+++ b/drivers/bluetooth/hci_nokia.c
@@ -0,0 +1,827 @@
+/*
+ *  Bluetooth HCI UART H4 driver with Nokia Extensions AKA Nokia H4+
+ *
+ *  Copyright (C) 2015 Marcel Holtmann <marcel@holtmann.org>
+ *  Copyright (C) 2015-2017 Sebastian Reichel <sre@kernel.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/errno.h>
+#include <linux/firmware.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/serdev.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/unaligned/le_struct.h>
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "hci_uart.h"
+#include "btbcm.h"
+
+#define VERSION "0.1"
+
+#define NOKIA_ID_BCM2048	0x04
+#define NOKIA_ID_TI1271		0x31
+
+#define FIRMWARE_BCM2048	"nokia/bcmfw.bin"
+#define FIRMWARE_TI1271		"nokia/ti1273.bin"
+
+#define HCI_NOKIA_NEG_PKT	0x06
+#define HCI_NOKIA_ALIVE_PKT	0x07
+#define HCI_NOKIA_RADIO_PKT	0x08
+
+#define HCI_NOKIA_NEG_HDR_SIZE		1
+#define HCI_NOKIA_MAX_NEG_SIZE		255
+#define HCI_NOKIA_ALIVE_HDR_SIZE	1
+#define HCI_NOKIA_MAX_ALIVE_SIZE	255
+#define HCI_NOKIA_RADIO_HDR_SIZE	2
+#define HCI_NOKIA_MAX_RADIO_SIZE	255
+
+#define NOKIA_PROTO_PKT		0x44
+#define NOKIA_PROTO_BYTE	0x4c
+
+#define NOKIA_NEG_REQ		0x00
+#define NOKIA_NEG_ACK		0x20
+#define NOKIA_NEG_NAK		0x40
+
+#define H4_TYPE_SIZE		1
+
+#define NOKIA_RECV_ALIVE \
+	.type = HCI_NOKIA_ALIVE_PKT, \
+	.hlen = HCI_NOKIA_ALIVE_HDR_SIZE, \
+	.loff = 0, \
+	.lsize = 1, \
+	.maxlen = HCI_NOKIA_MAX_ALIVE_SIZE \
+
+#define NOKIA_RECV_NEG \
+	.type = HCI_NOKIA_NEG_PKT, \
+	.hlen = HCI_NOKIA_NEG_HDR_SIZE, \
+	.loff = 0, \
+	.lsize = 1, \
+	.maxlen = HCI_NOKIA_MAX_NEG_SIZE \
+
+#define NOKIA_RECV_RADIO \
+	.type = HCI_NOKIA_RADIO_PKT, \
+	.hlen = HCI_NOKIA_RADIO_HDR_SIZE, \
+	.loff = 1, \
+	.lsize = 1, \
+	.maxlen = HCI_NOKIA_MAX_RADIO_SIZE \
+
+struct hci_nokia_neg_hdr {
+	u8	dlen;
+} __packed;
+
+struct hci_nokia_neg_cmd {
+	u8	ack;
+	u16	baud;
+	u16	unused1;
+	u8	proto;
+	u16	sys_clk;
+	u16	unused2;
+} __packed;
+
+#define NOKIA_ALIVE_REQ   0x55
+#define NOKIA_ALIVE_RESP  0xcc
+
+struct hci_nokia_alive_hdr {
+	u8	dlen;
+} __packed;
+
+struct hci_nokia_alive_pkt {
+	u8	mid;
+	u8	unused;
+} __packed;
+
+struct hci_nokia_neg_evt {
+	u8	ack;
+	u16	baud;
+	u16	unused1;
+	u8	proto;
+	u16	sys_clk;
+	u16	unused2;
+	u8	man_id;
+	u8	ver_id;
+} __packed;
+
+#define MAX_BAUD_RATE		3692300
+#define SETUP_BAUD_RATE		921600
+#define INIT_BAUD_RATE		120000
+
+struct hci_nokia_radio_hdr {
+	u8	evt;
+	u8	dlen;
+} __packed;
+
+struct nokia_bt_dev {
+	struct hci_uart hu;
+	struct serdev_device *serdev;
+
+	struct gpio_desc *reset;
+	struct gpio_desc *wakeup_host;
+	struct gpio_desc *wakeup_bt;
+	unsigned long sysclk_speed;
+
+	int wake_irq;
+	struct sk_buff *rx_skb;
+	struct sk_buff_head txq;
+	bdaddr_t bdaddr;
+
+	int init_error;
+	struct completion init_completion;
+
+	u8 man_id;
+	u8 ver_id;
+
+	bool initialized;
+	bool tx_enabled;
+	bool rx_enabled;
+};
+
+static int nokia_enqueue(struct hci_uart *hu, struct sk_buff *skb);
+
+static void nokia_flow_control(struct serdev_device *serdev, bool enable)
+{
+	if (enable) {
+		serdev_device_set_rts(serdev, true);
+		serdev_device_set_flow_control(serdev, true);
+	} else {
+		serdev_device_set_flow_control(serdev, false);
+		serdev_device_set_rts(serdev, false);
+	}
+}
+
+static irqreturn_t wakeup_handler(int irq, void *data)
+{
+	struct nokia_bt_dev *btdev = data;
+	struct device *dev = &btdev->serdev->dev;
+	int wake_state = gpiod_get_value(btdev->wakeup_host);
+
+	if (btdev->rx_enabled == wake_state)
+		return IRQ_HANDLED;
+
+	if (wake_state)
+		pm_runtime_get(dev);
+	else
+		pm_runtime_put(dev);
+
+	btdev->rx_enabled = wake_state;
+
+	return IRQ_HANDLED;
+}
+
+static int nokia_reset(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	int err;
+
+	/* reset routine */
+	gpiod_set_value_cansleep(btdev->reset, 1);
+	gpiod_set_value_cansleep(btdev->wakeup_bt, 1);
+
+	msleep(100);
+
+	/* safety check */
+	err = gpiod_get_value_cansleep(btdev->wakeup_host);
+	if (err == 1) {
+		dev_err(dev, "reset: host wakeup not low!");
+		return -EPROTO;
+	}
+
+	/* flush queue */
+	serdev_device_write_flush(btdev->serdev);
+
+	/* init uart */
+	nokia_flow_control(btdev->serdev, false);
+	serdev_device_set_baudrate(btdev->serdev, INIT_BAUD_RATE);
+
+	gpiod_set_value_cansleep(btdev->reset, 0);
+
+	/* wait for cts */
+	err = serdev_device_wait_for_cts(btdev->serdev, true, 200);
+	if (err < 0) {
+		dev_err(dev, "CTS not received: %d", err);
+		return err;
+	}
+
+	nokia_flow_control(btdev->serdev, true);
+
+	return 0;
+}
+
+static int nokia_send_alive_packet(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	struct hci_nokia_alive_hdr *hdr;
+	struct hci_nokia_alive_pkt *pkt;
+	struct sk_buff *skb;
+	int len;
+
+	init_completion(&btdev->init_completion);
+
+	len = H4_TYPE_SIZE + sizeof(*hdr) + sizeof(*pkt);
+	skb = bt_skb_alloc(len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hci_skb_pkt_type(skb) = HCI_NOKIA_ALIVE_PKT;
+	memset(skb->data, 0x00, len);
+
+	hdr = (struct hci_nokia_alive_hdr *)skb_put(skb, sizeof(*hdr));
+	hdr->dlen = sizeof(*pkt);
+	pkt = (struct hci_nokia_alive_pkt *)skb_put(skb, sizeof(*pkt));
+	pkt->mid = NOKIA_ALIVE_REQ;
+
+	nokia_enqueue(hu, skb);
+	hci_uart_tx_wakeup(hu);
+
+	dev_dbg(dev, "Alive sent");
+
+	if (!wait_for_completion_interruptible_timeout(&btdev->init_completion,
+		msecs_to_jiffies(1000))) {
+		return -ETIMEDOUT;
+	}
+
+	if (btdev->init_error < 0)
+		return btdev->init_error;
+
+	return 0;
+}
+
+static int nokia_send_negotiation(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	struct hci_nokia_neg_cmd *neg_cmd;
+	struct hci_nokia_neg_hdr *neg_hdr;
+	struct sk_buff *skb;
+	int len, err;
+	u16 baud = DIV_ROUND_CLOSEST(btdev->sysclk_speed * 10, SETUP_BAUD_RATE);
+	int sysclk = btdev->sysclk_speed / 1000;
+
+	len = H4_TYPE_SIZE + sizeof(*neg_hdr) + sizeof(*neg_cmd);
+	skb = bt_skb_alloc(len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hci_skb_pkt_type(skb) = HCI_NOKIA_NEG_PKT;
+
+	neg_hdr = (struct hci_nokia_neg_hdr *)skb_put(skb, sizeof(*neg_hdr));
+	neg_hdr->dlen = sizeof(*neg_cmd);
+
+	neg_cmd = (struct hci_nokia_neg_cmd *)skb_put(skb, sizeof(*neg_cmd));
+	neg_cmd->ack = NOKIA_NEG_REQ;
+	neg_cmd->baud = cpu_to_le16(baud);
+	neg_cmd->unused1 = 0x0000;
+	neg_cmd->proto = NOKIA_PROTO_BYTE;
+	neg_cmd->sys_clk = cpu_to_le16(sysclk);
+	neg_cmd->unused2 = 0x0000;
+
+	btdev->init_error = 0;
+	init_completion(&btdev->init_completion);
+
+	nokia_enqueue(hu, skb);
+	hci_uart_tx_wakeup(hu);
+
+	dev_dbg(dev, "Negotiation sent");
+
+	if (!wait_for_completion_interruptible_timeout(&btdev->init_completion,
+		msecs_to_jiffies(10000))) {
+		return -ETIMEDOUT;
+	}
+
+	if (btdev->init_error < 0)
+		return btdev->init_error;
+
+	/* Change to previously negotiated speed. Flow Control
+	 * is disabled until bluetooth adapter is ready to avoid
+	 * broken bytes being received.
+	 */
+	nokia_flow_control(btdev->serdev, false);
+	serdev_device_set_baudrate(btdev->serdev, SETUP_BAUD_RATE);
+	err = serdev_device_wait_for_cts(btdev->serdev, true, 200);
+	if (err < 0) {
+		dev_err(dev, "CTS not received: %d", err);
+		return err;
+	}
+	nokia_flow_control(btdev->serdev, true);
+
+	dev_dbg(dev, "Negotiation successful");
+
+	return 0;
+}
+
+static int nokia_setup_fw(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	const char *fwname;
+	const struct firmware *fw;
+	const u8 *fw_ptr;
+	size_t fw_size;
+	int err;
+
+	dev_dbg(dev, "setup firmware");
+
+	if (btdev->man_id == NOKIA_ID_BCM2048) {
+		fwname = FIRMWARE_BCM2048;
+	} else if (btdev->man_id == NOKIA_ID_TI1271) {
+		fwname = FIRMWARE_TI1271;
+	} else {
+		dev_err(dev, "Unsupported bluetooth device!");
+		return -ENODEV;
+	}
+
+	err = request_firmware(&fw, fwname, dev);
+	if (err < 0) {
+		dev_err(dev, "%s: Failed to load Nokia firmware file (%d)",
+			hu->hdev->name, err);
+		return err;
+	}
+
+	fw_ptr = fw->data;
+	fw_size = fw->size;
+
+	while (fw_size >= 4) {
+		u16 pkt_size = get_unaligned_le16(fw_ptr);
+		u8 pkt_type = fw_ptr[2];
+		const struct hci_command_hdr *cmd;
+		u16 opcode;
+		struct sk_buff *skb;
+
+		switch (pkt_type) {
+		case HCI_COMMAND_PKT:
+			cmd = (struct hci_command_hdr *)(fw_ptr + 3);
+			opcode = le16_to_cpu(cmd->opcode);
+
+			skb = __hci_cmd_sync(hu->hdev, opcode, cmd->plen,
+					     fw_ptr + 3 + HCI_COMMAND_HDR_SIZE,
+					     HCI_INIT_TIMEOUT);
+			if (IS_ERR(skb)) {
+				err = PTR_ERR(skb);
+				dev_err(dev, "%s: FW command %04x failed (%d)",
+				       hu->hdev->name, opcode, err);
+				goto done;
+			}
+			kfree_skb(skb);
+			break;
+		case HCI_NOKIA_RADIO_PKT:
+		case HCI_NOKIA_NEG_PKT:
+		case HCI_NOKIA_ALIVE_PKT:
+			break;
+		}
+
+		fw_ptr += pkt_size + 2;
+		fw_size -= pkt_size + 2;
+	}
+
+done:
+	release_firmware(fw);
+	return err;
+}
+
+static int nokia_setup(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	int err;
+
+	btdev->initialized = false;
+
+	nokia_flow_control(btdev->serdev, false);
+
+	pm_runtime_get_sync(dev);
+
+	if (btdev->tx_enabled) {
+		gpiod_set_value_cansleep(btdev->wakeup_bt, 0);
+		pm_runtime_put(&btdev->serdev->dev);
+		btdev->tx_enabled = false;
+	}
+
+	dev_dbg(dev, "protocol setup");
+
+	/* 0. reset connection */
+	err = nokia_reset(hu);
+	if (err < 0) {
+		dev_err(dev, "Reset failed: %d", err);
+		goto out;
+	}
+
+	/* 1. negotiate speed etc */
+	err = nokia_send_negotiation(hu);
+	if (err < 0) {
+		dev_err(dev, "Negotiation failed: %d", err);
+		goto out;
+	}
+
+	/* 2. verify correct setup using alive packet */
+	err = nokia_send_alive_packet(hu);
+	if (err < 0) {
+		dev_err(dev, "Alive check failed: %d", err);
+		goto out;
+	}
+
+	/* 3. send firmware */
+	err = nokia_setup_fw(hu);
+	if (err < 0) {
+		dev_err(dev, "Could not setup FW: %d", err);
+		goto out;
+	}
+
+	nokia_flow_control(btdev->serdev, false);
+	serdev_device_set_baudrate(btdev->serdev, MAX_BAUD_RATE);
+	nokia_flow_control(btdev->serdev, true);
+
+	if (btdev->man_id == NOKIA_ID_BCM2048) {
+		hu->hdev->set_bdaddr = btbcm_set_bdaddr;
+		set_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks);
+		dev_dbg(dev, "bcm2048 has invalid bluetooth address!");
+	}
+
+	dev_dbg(dev, "protocol setup done!");
+
+	gpiod_set_value_cansleep(btdev->wakeup_bt, 0);
+	pm_runtime_put(dev);
+	btdev->tx_enabled = false;
+	btdev->initialized = true;
+
+	return 0;
+out:
+	pm_runtime_put(dev);
+
+	return err;
+}
+
+static int nokia_open(struct hci_uart *hu)
+{
+	struct device *dev = &hu->serdev->dev;
+
+	dev_dbg(dev, "protocol open");
+
+	serdev_device_open(hu->serdev);
+
+	pm_runtime_enable(dev);
+
+	return 0;
+}
+
+static int nokia_flush(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+
+	dev_dbg(&btdev->serdev->dev, "flush device");
+
+	skb_queue_purge(&btdev->txq);
+
+	return 0;
+}
+
+static int nokia_close(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+
+	dev_dbg(dev, "close device");
+
+	btdev->initialized = false;
+
+	skb_queue_purge(&btdev->txq);
+
+	kfree_skb(btdev->rx_skb);
+
+	/* disable module */
+	gpiod_set_value(btdev->reset, 1);
+	gpiod_set_value(btdev->wakeup_bt, 0);
+
+	pm_runtime_disable(&btdev->serdev->dev);
+	serdev_device_close(btdev->serdev);
+
+	return 0;
+}
+
+/* Enqueue frame for transmittion (padding, crc, etc) */
+static int nokia_enqueue(struct hci_uart *hu, struct sk_buff *skb)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	int err;
+
+	/* Prepend skb with frame type */
+	memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1);
+
+	/* Packets must be word aligned */
+	if (skb->len % 2) {
+		err = skb_pad(skb, 1);
+		if (err)
+			return err;
+		*skb_put(skb, 1) = 0x00;
+	}
+
+	skb_queue_tail(&btdev->txq, skb);
+
+	return 0;
+}
+
+static int nokia_recv_negotiation_packet(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	struct hci_nokia_neg_hdr *hdr;
+	struct hci_nokia_neg_evt *evt;
+	int ret = 0;
+
+	hdr = (struct hci_nokia_neg_hdr *)skb->data;
+	if (hdr->dlen != sizeof(*evt)) {
+		btdev->init_error = -EIO;
+		ret = -EIO;
+		goto finish_neg;
+	}
+
+	evt = (struct hci_nokia_neg_evt *)skb_pull(skb, sizeof(*hdr));
+
+	if (evt->ack != NOKIA_NEG_ACK) {
+		dev_err(dev, "Negotiation received: wrong reply");
+		btdev->init_error = -EINVAL;
+		ret = -EINVAL;
+		goto finish_neg;
+	}
+
+	btdev->man_id = evt->man_id;
+	btdev->ver_id = evt->ver_id;
+
+	dev_dbg(dev, "Negotiation received: baud=%u:clk=%u:manu=%u:vers=%u",
+		evt->baud, evt->sys_clk, evt->man_id, evt->ver_id);
+
+finish_neg:
+	complete(&btdev->init_completion);
+	kfree_skb(skb);
+	return ret;
+}
+
+static int nokia_recv_alive_packet(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	struct hci_nokia_alive_hdr *hdr;
+	struct hci_nokia_alive_pkt *pkt;
+	int ret = 0;
+
+	hdr = (struct hci_nokia_alive_hdr *)skb->data;
+	if (hdr->dlen != sizeof(*pkt)) {
+		dev_err(dev, "Corrupted alive message");
+		btdev->init_error = -EIO;
+		ret = -EIO;
+		goto finish_alive;
+	}
+
+	pkt = (struct hci_nokia_alive_pkt *)skb_pull(skb, sizeof(*hdr));
+
+	if (pkt->mid != NOKIA_ALIVE_RESP) {
+		dev_err(dev, "Alive received: invalid response: 0x%02x!",
+			pkt->mid);
+		btdev->init_error = -EINVAL;
+		ret = -EINVAL;
+		goto finish_alive;
+	}
+
+	dev_dbg(dev, "Alive received");
+
+finish_alive:
+	complete(&btdev->init_completion);
+	kfree_skb(skb);
+	return ret;
+}
+
+static int nokia_recv_radio(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	/* Packets received on the dedicated radio channel are
+	 * HCI events and so feed them back into the core.
+	 */
+	hci_skb_pkt_type(skb) = HCI_EVENT_PKT;
+	return hci_recv_frame(hdev, skb);
+}
+
+/* Recv data */
+static const struct h4_recv_pkt nokia_recv_pkts[] = {
+	{ H4_RECV_ACL,		.recv = hci_recv_frame },
+	{ H4_RECV_SCO,		.recv = hci_recv_frame },
+	{ H4_RECV_EVENT,	.recv = hci_recv_frame },
+	{ NOKIA_RECV_ALIVE,	.recv = nokia_recv_alive_packet },
+	{ NOKIA_RECV_NEG,	.recv = nokia_recv_negotiation_packet },
+	{ NOKIA_RECV_RADIO,	.recv = nokia_recv_radio },
+};
+
+static int nokia_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	int err;
+
+	if (!test_bit(HCI_UART_REGISTERED, &hu->flags))
+		return -EUNATCH;
+
+	btdev->rx_skb = h4_recv_buf(hu->hdev, btdev->rx_skb, data, count,
+				  nokia_recv_pkts, ARRAY_SIZE(nokia_recv_pkts));
+	if (IS_ERR(btdev->rx_skb)) {
+		err = PTR_ERR(btdev->rx_skb);
+		dev_err(dev, "Frame reassembly failed (%d)", err);
+		btdev->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
+static struct sk_buff *nokia_dequeue(struct hci_uart *hu)
+{
+	struct nokia_bt_dev *btdev = hu->priv;
+	struct device *dev = &btdev->serdev->dev;
+	struct sk_buff *result = skb_dequeue(&btdev->txq);
+
+	if (!btdev->initialized)
+		return result;
+
+	if (btdev->tx_enabled == !!result)
+		return result;
+
+	if (result) {
+		pm_runtime_get_sync(dev);
+		gpiod_set_value_cansleep(btdev->wakeup_bt, 1);
+	} else {
+		serdev_device_wait_until_sent(btdev->serdev, 0);
+		gpiod_set_value_cansleep(btdev->wakeup_bt, 0);
+		pm_runtime_put(dev);
+	}
+
+	btdev->tx_enabled = !!result;
+
+	return result;
+}
+
+static const struct hci_uart_proto nokia_proto = {
+	.id		= HCI_UART_NOKIA,
+	.name		= "Nokia",
+	.open		= nokia_open,
+	.close		= nokia_close,
+	.recv		= nokia_recv,
+	.enqueue	= nokia_enqueue,
+	.dequeue	= nokia_dequeue,
+	.flush		= nokia_flush,
+	.setup		= nokia_setup,
+	.manufacturer	= 1,
+};
+
+static int nokia_bluetooth_serdev_probe(struct serdev_device *serdev)
+{
+	struct device *dev = &serdev->dev;
+	struct nokia_bt_dev *btdev;
+	struct clk *sysclk;
+	int err = 0;
+
+	btdev = devm_kzalloc(dev, sizeof(*btdev), GFP_KERNEL);
+	if (!btdev)
+		return -ENOMEM;
+
+	btdev->hu.serdev = btdev->serdev = serdev;
+	serdev_device_set_drvdata(serdev, btdev);
+
+	btdev->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(btdev->reset)) {
+		err = PTR_ERR(btdev->reset);
+		dev_err(dev, "could not get reset gpio: %d", err);
+		return err;
+	}
+
+	btdev->wakeup_host = devm_gpiod_get(dev, "host-wakeup", GPIOD_IN);
+	if (IS_ERR(btdev->wakeup_host)) {
+		err = PTR_ERR(btdev->wakeup_host);
+		dev_err(dev, "could not get host wakeup gpio: %d", err);
+		return err;
+	}
+
+	btdev->wake_irq = gpiod_to_irq(btdev->wakeup_host);
+
+	err = devm_request_threaded_irq(dev, btdev->wake_irq, NULL,
+		wakeup_handler,
+		IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+		"wakeup", btdev);
+	if (err) {
+		dev_err(dev, "could request wakeup irq: %d", err);
+		return err;
+	}
+
+	btdev->wakeup_bt = devm_gpiod_get(dev, "bluetooth-wakeup",
+					   GPIOD_OUT_LOW);
+	if (IS_ERR(btdev->wakeup_bt)) {
+		err = PTR_ERR(btdev->wakeup_bt);
+		dev_err(dev, "could not get BT wakeup gpio: %d", err);
+		return err;
+	}
+
+	sysclk = devm_clk_get(dev, "sysclk");
+	if (IS_ERR(sysclk)) {
+		err = PTR_ERR(sysclk);
+		dev_err(dev, "could not get sysclk: %d", err);
+		return err;
+	}
+
+	clk_prepare_enable(sysclk);
+	btdev->sysclk_speed = clk_get_rate(sysclk);
+	clk_disable_unprepare(sysclk);
+
+	skb_queue_head_init(&btdev->txq);
+
+	btdev->hu.priv = btdev;
+	btdev->hu.alignment = 2; /* Nokia H4+ is word aligned */
+
+	err = hci_uart_register_device(&btdev->hu, &nokia_proto);
+	if (err) {
+		dev_err(dev, "could not register bluetooth uart: %d", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void nokia_bluetooth_serdev_remove(struct serdev_device *serdev)
+{
+	struct nokia_bt_dev *btdev = serdev_device_get_drvdata(serdev);
+	struct hci_uart *hu = &btdev->hu;
+	struct hci_dev *hdev = hu->hdev;
+
+	cancel_work_sync(&hu->write_work);
+
+	hci_unregister_dev(hdev);
+	hci_free_dev(hdev);
+	hu->proto->close(hu);
+
+	pm_runtime_disable(&btdev->serdev->dev);
+}
+
+static int nokia_bluetooth_runtime_suspend(struct device *dev)
+{
+	struct serdev_device *serdev = to_serdev_device(dev);
+
+	nokia_flow_control(serdev, false);
+	return 0;
+}
+
+static int nokia_bluetooth_runtime_resume(struct device *dev)
+{
+	struct serdev_device *serdev = to_serdev_device(dev);
+
+	nokia_flow_control(serdev, true);
+	return 0;
+}
+
+static const struct dev_pm_ops nokia_bluetooth_pm_ops = {
+	SET_RUNTIME_PM_OPS(nokia_bluetooth_runtime_suspend,
+			   nokia_bluetooth_runtime_resume,
+			   NULL)
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id nokia_bluetooth_of_match[] = {
+	{ .compatible = "nokia,h4p-bluetooth", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, nokia_bluetooth_of_match);
+#endif
+
+static struct serdev_device_driver nokia_bluetooth_serdev_driver = {
+	.probe = nokia_bluetooth_serdev_probe,
+	.remove = nokia_bluetooth_serdev_remove,
+	.driver = {
+		.name = "nokia-bluetooth",
+		.pm = &nokia_bluetooth_pm_ops,
+		.of_match_table = of_match_ptr(nokia_bluetooth_of_match),
+	},
+};
+
+module_serdev_device_driver(nokia_bluetooth_serdev_driver);
+
+MODULE_AUTHOR("Sebastian Reichel <sre@kernel.org>");
+MODULE_DESCRIPTION("Bluetooth HCI UART Nokia H4+ driver ver " VERSION);
+MODULE_VERSION(VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
new file mode 100644
index 000000000000..7de0edc0ff8c
--- /dev/null
+++ b/drivers/bluetooth/hci_serdev.c
@@ -0,0 +1,356 @@
+/*
+ *  Bluetooth HCI serdev driver lib
+ *
+ *  Copyright (C) 2017  Linaro, Ltd., Rob Herring <robh@kernel.org>
+ *
+ *  Based on hci_ldisc.c:
+ *
+ *  Copyright (C) 2000-2001  Qualcomm Incorporated
+ *  Copyright (C) 2002-2003  Maxim Krasnyansky <maxk@qualcomm.com>
+ *  Copyright (C) 2004-2005  Marcel Holtmann <marcel@holtmann.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/serdev.h>
+#include <linux/skbuff.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "hci_uart.h"
+
+struct serdev_device_ops hci_serdev_client_ops;
+
+static inline void hci_uart_tx_complete(struct hci_uart *hu, int pkt_type)
+{
+	struct hci_dev *hdev = hu->hdev;
+
+	/* Update HCI stat counters */
+	switch (pkt_type) {
+	case HCI_COMMAND_PKT:
+		hdev->stat.cmd_tx++;
+		break;
+
+	case HCI_ACLDATA_PKT:
+		hdev->stat.acl_tx++;
+		break;
+
+	case HCI_SCODATA_PKT:
+		hdev->stat.sco_tx++;
+		break;
+	}
+}
+
+static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
+{
+	struct sk_buff *skb = hu->tx_skb;
+
+	if (!skb)
+		skb = hu->proto->dequeue(hu);
+	else
+		hu->tx_skb = NULL;
+
+	return skb;
+}
+
+static void hci_uart_write_work(struct work_struct *work)
+{
+	struct hci_uart *hu = container_of(work, struct hci_uart, write_work);
+	struct serdev_device *serdev = hu->serdev;
+	struct hci_dev *hdev = hu->hdev;
+	struct sk_buff *skb;
+
+	/* REVISIT:
+	 * should we cope with bad skbs or ->write() returning an error value?
+	 */
+	do {
+		clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
+
+		while ((skb = hci_uart_dequeue(hu))) {
+			int len;
+
+			len = serdev_device_write_buf(serdev,
+						      skb->data, skb->len);
+			hdev->stat.byte_tx += len;
+
+			skb_pull(skb, len);
+			if (skb->len) {
+				hu->tx_skb = skb;
+				break;
+			}
+
+			hci_uart_tx_complete(hu, hci_skb_pkt_type(skb));
+			kfree_skb(skb);
+		}
+	} while(test_bit(HCI_UART_TX_WAKEUP, &hu->tx_state));
+
+	clear_bit(HCI_UART_SENDING, &hu->tx_state);
+}
+
+/* ------- Interface to HCI layer ------ */
+
+/* Initialize device */
+static int hci_uart_open(struct hci_dev *hdev)
+{
+	BT_DBG("%s %p", hdev->name, hdev);
+
+	return 0;
+}
+
+/* Reset device */
+static int hci_uart_flush(struct hci_dev *hdev)
+{
+	struct hci_uart *hu  = hci_get_drvdata(hdev);
+
+	BT_DBG("hdev %p serdev %p", hdev, hu->serdev);
+
+	if (hu->tx_skb) {
+		kfree_skb(hu->tx_skb); hu->tx_skb = NULL;
+	}
+
+	/* Flush any pending characters in the driver and discipline. */
+	serdev_device_write_flush(hu->serdev);
+
+	if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		hu->proto->flush(hu);
+
+	return 0;
+}
+
+/* Close device */
+static int hci_uart_close(struct hci_dev *hdev)
+{
+	BT_DBG("hdev %p", hdev);
+
+	hci_uart_flush(hdev);
+	hdev->flush = NULL;
+
+	return 0;
+}
+
+/* Send frames from HCI layer */
+static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
+	BT_DBG("%s: type %d len %d", hdev->name, hci_skb_pkt_type(skb),
+	       skb->len);
+
+	hu->proto->enqueue(hu, skb);
+
+	hci_uart_tx_wakeup(hu);
+
+	return 0;
+}
+
+static int hci_uart_setup(struct hci_dev *hdev)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct hci_rp_read_local_version *ver;
+	struct sk_buff *skb;
+	unsigned int speed;
+	int err;
+
+	/* Init speed if any */
+	if (hu->init_speed)
+		speed = hu->init_speed;
+	else if (hu->proto->init_speed)
+		speed = hu->proto->init_speed;
+	else
+		speed = 0;
+
+	if (speed)
+		serdev_device_set_baudrate(hu->serdev, speed);
+
+	/* Operational speed if any */
+	if (hu->oper_speed)
+		speed = hu->oper_speed;
+	else if (hu->proto->oper_speed)
+		speed = hu->proto->oper_speed;
+	else
+		speed = 0;
+
+	if (hu->proto->set_baudrate && speed) {
+		err = hu->proto->set_baudrate(hu, speed);
+		if (err)
+			BT_ERR("%s: failed to set baudrate", hdev->name);
+		else
+			serdev_device_set_baudrate(hu->serdev, speed);
+	}
+
+	if (hu->proto->setup)
+		return hu->proto->setup(hu);
+
+	if (!test_bit(HCI_UART_VND_DETECT, &hu->hdev_flags))
+		return 0;
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Reading local version information failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return 0;
+	}
+
+	if (skb->len != sizeof(*ver)) {
+		BT_ERR("%s: Event length mismatch for version information",
+		       hdev->name);
+	}
+
+	kfree_skb(skb);
+	return 0;
+}
+
+/** hci_uart_write_wakeup - transmit buffer wakeup
+ * @serdev: serial device
+ *
+ * This function is called by the serdev framework when it accepts
+ * more data being sent.
+ */
+static void hci_uart_write_wakeup(struct serdev_device *serdev)
+{
+	struct hci_uart *hu = serdev_device_get_drvdata(serdev);
+
+	BT_DBG("");
+
+	if (!hu || serdev != hu->serdev) {
+		WARN_ON(1);
+		return;
+	}
+
+	if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		hci_uart_tx_wakeup(hu);
+}
+
+/** hci_uart_receive_buf - receive buffer wakeup
+ * @serdev: serial device
+ * @data:   pointer to received data
+ * @count:  count of received data in bytes
+ *
+ * This function is called by the serdev framework when it received data
+ * in the RX buffer.
+ *
+ * Return: number of processed bytes
+ */
+static int hci_uart_receive_buf(struct serdev_device *serdev, const u8 *data,
+				   size_t count)
+{
+	struct hci_uart *hu = serdev_device_get_drvdata(serdev);
+
+	if (!hu || serdev != hu->serdev) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		return 0;
+
+	/* It does not need a lock here as it is already protected by a mutex in
+	 * tty caller
+	 */
+	hu->proto->recv(hu, data, count);
+
+	if (hu->hdev)
+		hu->hdev->stat.byte_rx += count;
+
+	return count;
+}
+
+struct serdev_device_ops hci_serdev_client_ops = {
+	.receive_buf = hci_uart_receive_buf,
+	.write_wakeup = hci_uart_write_wakeup,
+};
+
+int hci_uart_register_device(struct hci_uart *hu,
+			     const struct hci_uart_proto *p)
+{
+	int err;
+	struct hci_dev *hdev;
+
+	BT_DBG("");
+
+	serdev_device_set_client_ops(hu->serdev, &hci_serdev_client_ops);
+
+	err = p->open(hu);
+	if (err)
+		return err;
+
+	hu->proto = p;
+	set_bit(HCI_UART_PROTO_READY, &hu->flags);
+
+	/* Initialize and register HCI device */
+	hdev = hci_alloc_dev();
+	if (!hdev) {
+		BT_ERR("Can't allocate HCI device");
+		err = -ENOMEM;
+		goto err_alloc;
+	}
+
+	hu->hdev = hdev;
+
+	hdev->bus = HCI_UART;
+	hci_set_drvdata(hdev, hu);
+
+	INIT_WORK(&hu->write_work, hci_uart_write_work);
+
+	/* Only when vendor specific setup callback is provided, consider
+	 * the manufacturer information valid. This avoids filling in the
+	 * value for Ericsson when nothing is specified.
+	 */
+	if (hu->proto->setup)
+		hdev->manufacturer = hu->proto->manufacturer;
+
+	hdev->open  = hci_uart_open;
+	hdev->close = hci_uart_close;
+	hdev->flush = hci_uart_flush;
+	hdev->send  = hci_uart_send_frame;
+	hdev->setup = hci_uart_setup;
+	SET_HCIDEV_DEV(hdev, &hu->serdev->dev);
+
+	if (test_bit(HCI_UART_RAW_DEVICE, &hu->hdev_flags))
+		set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);
+
+	if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags))
+		set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks);
+
+	if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags))
+		set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks);
+
+	if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags))
+		hdev->dev_type = HCI_AMP;
+	else
+		hdev->dev_type = HCI_PRIMARY;
+
+	if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags))
+		return 0;
+
+	if (hci_register_dev(hdev) < 0) {
+		BT_ERR("Can't register HCI device");
+		err = -ENODEV;
+		goto err_register;
+	}
+
+	set_bit(HCI_UART_REGISTERED, &hu->flags);
+
+	return 0;
+
+err_register:
+	hci_free_dev(hdev);
+err_alloc:
+	clear_bit(HCI_UART_PROTO_READY, &hu->flags);
+	p->close(hu);
+	return err;
+}
+EXPORT_SYMBOL_GPL(hci_uart_register_device);
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index 070139513e65..2b05e557fad0 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -58,6 +58,7 @@
 #define HCI_UART_VND_DETECT	5
 
 struct hci_uart;
+struct serdev_device;
 
 struct hci_uart_proto {
 	unsigned int id;
@@ -77,6 +78,7 @@ struct hci_uart_proto {
 
 struct hci_uart {
 	struct tty_struct	*tty;
+	struct serdev_device	*serdev;
 	struct hci_dev		*hdev;
 	unsigned long		flags;
 	unsigned long		hdev_flags;
@@ -92,6 +94,9 @@ struct hci_uart {
 
 	unsigned int init_speed;
 	unsigned int oper_speed;
+
+	u8			alignment;
+	u8			padding;
 };
 
 /* HCI_UART proto flag bits */
@@ -105,9 +110,10 @@ struct hci_uart {
 
 int hci_uart_register_proto(const struct hci_uart_proto *p);
 int hci_uart_unregister_proto(const struct hci_uart_proto *p);
+int hci_uart_register_device(struct hci_uart *hu, const struct hci_uart_proto *p);
+
 int hci_uart_tx_wakeup(struct hci_uart *hu);
 int hci_uart_init_ready(struct hci_uart *hu);
-void hci_uart_init_tty(struct hci_uart *hu);
 void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed);
 void hci_uart_set_flow_control(struct hci_uart *hu, bool enable);
 void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed,
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 87739649eac2..76c952fd9ab9 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2218,7 +2218,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		rq->timeout = 60 * HZ;
 		bio = rq->bio;
 
-		if (blk_execute_rq(q, cdi->disk, rq, 0)) {
+		blk_execute_rq(q, cdi->disk, rq, 0);
+		if (scsi_req(rq)->result) {
 			struct request_sense *s = req->sense;
 			ret = -EIO;
 			cdi->last_sense = s->sense_key;
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 0ef350010766..c99cd19d9147 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -14,7 +14,7 @@
 #include <linux/agp_backend.h>
 #include <linux/mmzone.h>
 #include <asm/page.h>		/* PAGE_SIZE */
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/amd_nb.h>
 #include <asm/gart.h>
 #include "agp.h"
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 0cafe08919c9..1b223c32a8ae 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -294,20 +294,6 @@ config HW_RANDOM_POWERNV
 
 	  If unsure, say Y.
 
-config HW_RANDOM_EXYNOS
-	tristate "EXYNOS HW random number generator support"
-	depends on ARCH_EXYNOS || COMPILE_TEST
-	depends on HAS_IOMEM
-	default HW_RANDOM
-	---help---
-	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on EXYNOS SOCs.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called exynos-rng.
-
-	  If unsure, say Y.
-
 config HW_RANDOM_TPM
 	tristate "TPM HW Random Number Generator support"
 	depends on TCG_TPM
@@ -423,6 +409,34 @@ config HW_RANDOM_CAVIUM
 
          If unsure, say Y.
 
+config HW_RANDOM_MTK
+	tristate "Mediatek Random Number Generator support"
+	depends on HW_RANDOM
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	default y
+	---help---
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on Mediatek SoCs.
+
+	  To compile this driver as a module, choose M here. the
+	  module will be called mtk-rng.
+
+	  If unsure, say Y.
+
+config HW_RANDOM_S390
+	tristate "S390 True Random Number Generator support"
+	depends on S390
+	default HW_RANDOM
+	---help---
+	  This driver provides kernel-side support for the True
+	  Random Number Generator available as CPACF extension
+	  on modern s390 hardware platforms.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called s390-trng.
+
+	  If unsure, say Y.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 5f52b1e4e7be..b085975ec1d2 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -24,7 +24,6 @@ obj-$(CONFIG_HW_RANDOM_OCTEON) += octeon-rng.o
 obj-$(CONFIG_HW_RANDOM_NOMADIK) += nomadik-rng.o
 obj-$(CONFIG_HW_RANDOM_PSERIES) += pseries-rng.o
 obj-$(CONFIG_HW_RANDOM_POWERNV) += powernv-rng.o
-obj-$(CONFIG_HW_RANDOM_EXYNOS)	+= exynos-rng.o
 obj-$(CONFIG_HW_RANDOM_HISI)	+= hisi-rng.o
 obj-$(CONFIG_HW_RANDOM_TPM) += tpm-rng.o
 obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o
@@ -36,3 +35,5 @@ obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
 obj-$(CONFIG_HW_RANDOM_PIC32) += pic32-rng.o
 obj-$(CONFIG_HW_RANDOM_MESON) += meson-rng.o
 obj-$(CONFIG_HW_RANDOM_CAVIUM) += cavium-rng.o cavium-rng-vf.o
+obj-$(CONFIG_HW_RANDOM_MTK)	+= mtk-rng.o
+obj-$(CONFIG_HW_RANDOM_S390) += s390-trng.o
diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c
index 4a99ac756f08..9959c762da2f 100644
--- a/drivers/char/hw_random/amd-rng.c
+++ b/drivers/char/hw_random/amd-rng.c
@@ -55,6 +55,7 @@ MODULE_DEVICE_TABLE(pci, pci_tbl);
 struct amd768_priv {
 	void __iomem *iobase;
 	struct pci_dev *pcidev;
+	u32 pmbase;
 };
 
 static int amd_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
@@ -148,33 +149,58 @@ found:
 	if (pmbase == 0)
 		return -EIO;
 
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
-	if (!devm_request_region(&pdev->dev, pmbase + PMBASE_OFFSET,
-				PMBASE_SIZE, DRV_NAME)) {
+	if (!request_region(pmbase + PMBASE_OFFSET, PMBASE_SIZE, DRV_NAME)) {
 		dev_err(&pdev->dev, DRV_NAME " region 0x%x already in use!\n",
 			pmbase + 0xF0);
-		return -EBUSY;
+		err = -EBUSY;
+		goto out;
 	}
 
-	priv->iobase = devm_ioport_map(&pdev->dev, pmbase + PMBASE_OFFSET,
-			PMBASE_SIZE);
+	priv->iobase = ioport_map(pmbase + PMBASE_OFFSET, PMBASE_SIZE);
 	if (!priv->iobase) {
 		pr_err(DRV_NAME "Cannot map ioport\n");
-		return -ENOMEM;
+		err = -EINVAL;
+		goto err_iomap;
 	}
 
 	amd_rng.priv = (unsigned long)priv;
+	priv->pmbase = pmbase;
 	priv->pcidev = pdev;
 
 	pr_info(DRV_NAME " detected\n");
-	return devm_hwrng_register(&pdev->dev, &amd_rng);
+	err = hwrng_register(&amd_rng);
+	if (err) {
+		pr_err(DRV_NAME " registering failed (%d)\n", err);
+		goto err_hwrng;
+	}
+	return 0;
+
+err_hwrng:
+	ioport_unmap(priv->iobase);
+err_iomap:
+	release_region(pmbase + PMBASE_OFFSET, PMBASE_SIZE);
+out:
+	kfree(priv);
+	return err;
 }
 
 static void __exit mod_exit(void)
 {
+	struct amd768_priv *priv;
+
+	priv = (struct amd768_priv *)amd_rng.priv;
+
+	hwrng_unregister(&amd_rng);
+
+	ioport_unmap(priv->iobase);
+
+	release_region(priv->pmbase + PMBASE_OFFSET, PMBASE_SIZE);
+
+	kfree(priv);
 }
 
 module_init(mod_init);
diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c
deleted file mode 100644
index 23d358553b21..000000000000
--- a/drivers/char/hw_random/exynos-rng.c
+++ /dev/null
@@ -1,231 +0,0 @@
-/*
- * exynos-rng.c - Random Number Generator driver for the exynos
- *
- * Copyright (C) 2012 Samsung Electronics
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation;
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/hw_random.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-#include <linux/pm_runtime.h>
-#include <linux/err.h>
-
-#define EXYNOS_PRNG_STATUS_OFFSET	0x10
-#define EXYNOS_PRNG_SEED_OFFSET		0x140
-#define EXYNOS_PRNG_OUT1_OFFSET		0x160
-#define SEED_SETTING_DONE		BIT(1)
-#define PRNG_START			0x18
-#define PRNG_DONE			BIT(5)
-#define EXYNOS_AUTOSUSPEND_DELAY	100
-
-struct exynos_rng {
-	struct device *dev;
-	struct hwrng rng;
-	void __iomem *mem;
-	struct clk *clk;
-};
-
-static u32 exynos_rng_readl(struct exynos_rng *rng, u32 offset)
-{
-	return	readl_relaxed(rng->mem + offset);
-}
-
-static void exynos_rng_writel(struct exynos_rng *rng, u32 val, u32 offset)
-{
-	writel_relaxed(val, rng->mem + offset);
-}
-
-static int exynos_rng_configure(struct exynos_rng *exynos_rng)
-{
-	int i;
-	int ret = 0;
-
-	for (i = 0 ; i < 5 ; i++)
-		exynos_rng_writel(exynos_rng, jiffies,
-				EXYNOS_PRNG_SEED_OFFSET + 4*i);
-
-	if (!(exynos_rng_readl(exynos_rng, EXYNOS_PRNG_STATUS_OFFSET)
-						 & SEED_SETTING_DONE))
-		ret = -EIO;
-
-	return ret;
-}
-
-static int exynos_init(struct hwrng *rng)
-{
-	struct exynos_rng *exynos_rng = container_of(rng,
-						struct exynos_rng, rng);
-	int ret = 0;
-
-	pm_runtime_get_sync(exynos_rng->dev);
-	ret = exynos_rng_configure(exynos_rng);
-	pm_runtime_mark_last_busy(exynos_rng->dev);
-	pm_runtime_put_autosuspend(exynos_rng->dev);
-
-	return ret;
-}
-
-static int exynos_read(struct hwrng *rng, void *buf,
-					size_t max, bool wait)
-{
-	struct exynos_rng *exynos_rng = container_of(rng,
-						struct exynos_rng, rng);
-	u32 *data = buf;
-	int retry = 100;
-	int ret = 4;
-
-	pm_runtime_get_sync(exynos_rng->dev);
-
-	exynos_rng_writel(exynos_rng, PRNG_START, 0);
-
-	while (!(exynos_rng_readl(exynos_rng,
-			EXYNOS_PRNG_STATUS_OFFSET) & PRNG_DONE) && --retry)
-		cpu_relax();
-	if (!retry) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
-
-	exynos_rng_writel(exynos_rng, PRNG_DONE, EXYNOS_PRNG_STATUS_OFFSET);
-
-	*data = exynos_rng_readl(exynos_rng, EXYNOS_PRNG_OUT1_OFFSET);
-
-out:
-	pm_runtime_mark_last_busy(exynos_rng->dev);
-	pm_runtime_put_sync_autosuspend(exynos_rng->dev);
-
-	return ret;
-}
-
-static int exynos_rng_probe(struct platform_device *pdev)
-{
-	struct exynos_rng *exynos_rng;
-	struct resource *res;
-	int ret;
-
-	exynos_rng = devm_kzalloc(&pdev->dev, sizeof(struct exynos_rng),
-					GFP_KERNEL);
-	if (!exynos_rng)
-		return -ENOMEM;
-
-	exynos_rng->dev = &pdev->dev;
-	exynos_rng->rng.name = "exynos";
-	exynos_rng->rng.init =	exynos_init;
-	exynos_rng->rng.read = exynos_read;
-	exynos_rng->clk = devm_clk_get(&pdev->dev, "secss");
-	if (IS_ERR(exynos_rng->clk)) {
-		dev_err(&pdev->dev, "Couldn't get clock.\n");
-		return -ENOENT;
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	exynos_rng->mem = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(exynos_rng->mem))
-		return PTR_ERR(exynos_rng->mem);
-
-	platform_set_drvdata(pdev, exynos_rng);
-
-	pm_runtime_set_autosuspend_delay(&pdev->dev, EXYNOS_AUTOSUSPEND_DELAY);
-	pm_runtime_use_autosuspend(&pdev->dev);
-	pm_runtime_enable(&pdev->dev);
-
-	ret = devm_hwrng_register(&pdev->dev, &exynos_rng->rng);
-	if (ret) {
-		pm_runtime_dont_use_autosuspend(&pdev->dev);
-		pm_runtime_disable(&pdev->dev);
-	}
-
-	return ret;
-}
-
-static int exynos_rng_remove(struct platform_device *pdev)
-{
-	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
-
-	return 0;
-}
-
-static int __maybe_unused exynos_rng_runtime_suspend(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct exynos_rng *exynos_rng = platform_get_drvdata(pdev);
-
-	clk_disable_unprepare(exynos_rng->clk);
-
-	return 0;
-}
-
-static int __maybe_unused exynos_rng_runtime_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct exynos_rng *exynos_rng = platform_get_drvdata(pdev);
-
-	return clk_prepare_enable(exynos_rng->clk);
-}
-
-static int __maybe_unused exynos_rng_suspend(struct device *dev)
-{
-	return pm_runtime_force_suspend(dev);
-}
-
-static int __maybe_unused exynos_rng_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct exynos_rng *exynos_rng = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = pm_runtime_force_resume(dev);
-	if (ret)
-		return ret;
-
-	return exynos_rng_configure(exynos_rng);
-}
-
-static const struct dev_pm_ops exynos_rng_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(exynos_rng_suspend, exynos_rng_resume)
-	SET_RUNTIME_PM_OPS(exynos_rng_runtime_suspend,
-			   exynos_rng_runtime_resume, NULL)
-};
-
-static const struct of_device_id exynos_rng_dt_match[] = {
-	{
-		.compatible = "samsung,exynos4-rng",
-	},
-	{ },
-};
-MODULE_DEVICE_TABLE(of, exynos_rng_dt_match);
-
-static struct platform_driver exynos_rng_driver = {
-	.driver		= {
-		.name	= "exynos-rng",
-		.pm	= &exynos_rng_pm_ops,
-		.of_match_table = exynos_rng_dt_match,
-	},
-	.probe		= exynos_rng_probe,
-	.remove		= exynos_rng_remove,
-};
-
-module_platform_driver(exynos_rng_driver);
-
-MODULE_DESCRIPTION("EXYNOS 4 H/W Random Number Generator driver");
-MODULE_AUTHOR("Jonghwa Lee <jonghwa3.lee@samsung.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/char/hw_random/geode-rng.c b/drivers/char/hw_random/geode-rng.c
index e7a245942029..e1d421a36a13 100644
--- a/drivers/char/hw_random/geode-rng.c
+++ b/drivers/char/hw_random/geode-rng.c
@@ -31,6 +31,9 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
+
+#define PFX	KBUILD_MODNAME ": "
+
 #define GEODE_RNG_DATA_REG   0x50
 #define GEODE_RNG_STATUS_REG 0x54
 
@@ -82,6 +85,7 @@ static struct hwrng geode_rng = {
 
 static int __init mod_init(void)
 {
+	int err = -ENODEV;
 	struct pci_dev *pdev = NULL;
 	const struct pci_device_id *ent;
 	void __iomem *mem;
@@ -89,27 +93,43 @@ static int __init mod_init(void)
 
 	for_each_pci_dev(pdev) {
 		ent = pci_match_id(pci_tbl, pdev);
-		if (ent) {
-			rng_base = pci_resource_start(pdev, 0);
-			if (rng_base == 0)
-				return -ENODEV;
-
-			mem = devm_ioremap(&pdev->dev, rng_base, 0x58);
-			if (!mem)
-				return -ENOMEM;
-			geode_rng.priv = (unsigned long)mem;
-
-			pr_info("AMD Geode RNG detected\n");
-			return devm_hwrng_register(&pdev->dev, &geode_rng);
-		}
+		if (ent)
+			goto found;
 	}
-
 	/* Device not found. */
-	return -ENODEV;
+	goto out;
+
+found:
+	rng_base = pci_resource_start(pdev, 0);
+	if (rng_base == 0)
+		goto out;
+	err = -ENOMEM;
+	mem = ioremap(rng_base, 0x58);
+	if (!mem)
+		goto out;
+	geode_rng.priv = (unsigned long)mem;
+
+	pr_info("AMD Geode RNG detected\n");
+	err = hwrng_register(&geode_rng);
+	if (err) {
+		pr_err(PFX "RNG registering failed (%d)\n",
+		       err);
+		goto err_unmap;
+	}
+out:
+	return err;
+
+err_unmap:
+	iounmap(mem);
+	goto out;
 }
 
 static void __exit mod_exit(void)
 {
+	void __iomem *mem = (void __iomem *)geode_rng.priv;
+
+	hwrng_unregister(&geode_rng);
+	iounmap(mem);
 }
 
 module_init(mod_init);
diff --git a/drivers/char/hw_random/meson-rng.c b/drivers/char/hw_random/meson-rng.c
index 119d698439ae..2e23be802a62 100644
--- a/drivers/char/hw_random/meson-rng.c
+++ b/drivers/char/hw_random/meson-rng.c
@@ -62,6 +62,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/of.h>
+#include <linux/clk.h>
 
 #define RNG_DATA 0x00
 
@@ -69,6 +70,7 @@ struct meson_rng_data {
 	void __iomem *base;
 	struct platform_device *pdev;
 	struct hwrng rng;
+	struct clk *core_clk;
 };
 
 static int meson_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
@@ -81,11 +83,17 @@ static int meson_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
 	return sizeof(u32);
 }
 
+static void meson_rng_clk_disable(void *data)
+{
+	clk_disable_unprepare(data);
+}
+
 static int meson_rng_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct meson_rng_data *data;
 	struct resource *res;
+	int ret;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -98,6 +106,20 @@ static int meson_rng_probe(struct platform_device *pdev)
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
 
+	data->core_clk = devm_clk_get(dev, "core");
+	if (IS_ERR(data->core_clk))
+		data->core_clk = NULL;
+
+	if (data->core_clk) {
+		ret = clk_prepare_enable(data->core_clk);
+		if (ret)
+			return ret;
+		ret = devm_add_action_or_reset(dev, meson_rng_clk_disable,
+					       data->core_clk);
+		if (ret)
+			return ret;
+	}
+
 	data->rng.name = pdev->name;
 	data->rng.read = meson_rng_read;
 
diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c
new file mode 100644
index 000000000000..df8eb54fd5a3
--- /dev/null
+++ b/drivers/char/hw_random/mtk-rng.c
@@ -0,0 +1,168 @@
+/*
+ * Driver for Mediatek Hardware Random Number Generator
+ *
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#define MTK_RNG_DEV KBUILD_MODNAME
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#define USEC_POLL			2
+#define TIMEOUT_POLL			20
+
+#define RNG_CTRL			0x00
+#define RNG_EN				BIT(0)
+#define RNG_READY			BIT(31)
+
+#define RNG_DATA			0x08
+
+#define to_mtk_rng(p)	container_of(p, struct mtk_rng, rng)
+
+struct mtk_rng {
+	void __iomem *base;
+	struct clk *clk;
+	struct hwrng rng;
+};
+
+static int mtk_rng_init(struct hwrng *rng)
+{
+	struct mtk_rng *priv = to_mtk_rng(rng);
+	u32 val;
+	int err;
+
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		return err;
+
+	val = readl(priv->base + RNG_CTRL);
+	val |= RNG_EN;
+	writel(val, priv->base + RNG_CTRL);
+
+	return 0;
+}
+
+static void mtk_rng_cleanup(struct hwrng *rng)
+{
+	struct mtk_rng *priv = to_mtk_rng(rng);
+	u32 val;
+
+	val = readl(priv->base + RNG_CTRL);
+	val &= ~RNG_EN;
+	writel(val, priv->base + RNG_CTRL);
+
+	clk_disable_unprepare(priv->clk);
+}
+
+static bool mtk_rng_wait_ready(struct hwrng *rng, bool wait)
+{
+	struct mtk_rng *priv = to_mtk_rng(rng);
+	int ready;
+
+	ready = readl(priv->base + RNG_CTRL) & RNG_READY;
+	if (!ready && wait)
+		readl_poll_timeout_atomic(priv->base + RNG_CTRL, ready,
+					  ready & RNG_READY, USEC_POLL,
+					  TIMEOUT_POLL);
+	return !!ready;
+}
+
+static int mtk_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct mtk_rng *priv = to_mtk_rng(rng);
+	int retval = 0;
+
+	while (max >= sizeof(u32)) {
+		if (!mtk_rng_wait_ready(rng, wait))
+			break;
+
+		*(u32 *)buf = readl(priv->base + RNG_DATA);
+		retval += sizeof(u32);
+		buf += sizeof(u32);
+		max -= sizeof(u32);
+	}
+
+	return retval || !wait ? retval : -EIO;
+}
+
+static int mtk_rng_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	int ret;
+	struct mtk_rng *priv;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "no iomem resource\n");
+		return -ENXIO;
+	}
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->rng.name = pdev->name;
+	priv->rng.init = mtk_rng_init;
+	priv->rng.cleanup = mtk_rng_cleanup;
+	priv->rng.read = mtk_rng_read;
+
+	priv->clk = devm_clk_get(&pdev->dev, "rng");
+	if (IS_ERR(priv->clk)) {
+		ret = PTR_ERR(priv->clk);
+		dev_err(&pdev->dev, "no clock for device: %d\n", ret);
+		return ret;
+	}
+
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	ret = devm_hwrng_register(&pdev->dev, &priv->rng);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register rng device: %d\n",
+			ret);
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "registered RNG driver\n");
+
+	return 0;
+}
+
+static const struct of_device_id mtk_rng_match[] = {
+	{ .compatible = "mediatek,mt7623-rng" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtk_rng_match);
+
+static struct platform_driver mtk_rng_driver = {
+	.probe          = mtk_rng_probe,
+	.driver = {
+		.name = MTK_RNG_DEV,
+		.of_match_table = mtk_rng_match,
+	},
+};
+
+module_platform_driver(mtk_rng_driver);
+
+MODULE_DESCRIPTION("Mediatek Random Number Generator Driver");
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/char/hw_random/n2-drv.c b/drivers/char/hw_random/n2-drv.c
index 31cbdbbaebfc..92dd4e925315 100644
--- a/drivers/char/hw_random/n2-drv.c
+++ b/drivers/char/hw_random/n2-drv.c
@@ -748,9 +748,7 @@ static int n2rng_probe(struct platform_device *op)
 
 	dev_info(&op->dev, "Registered RNG HVAPI major %lu minor %lu\n",
 		 np->hvapi_major, np->hvapi_minor);
-
-	np->units = devm_kzalloc(&op->dev,
-				 sizeof(struct n2rng_unit) * np->num_units,
+	np->units = devm_kcalloc(&op->dev, np->num_units, sizeof(*np->units),
 				 GFP_KERNEL);
 	err = -ENOMEM;
 	if (!np->units)
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 3ad86fdf954e..74d11ae6abe9 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -397,17 +397,19 @@ static int of_get_omap_rng_device_details(struct omap_rng_dev *priv,
 				irq, err);
 			return err;
 		}
-		omap_rng_write(priv, RNG_INTMASK_REG, RNG_SHUTDOWN_OFLO_MASK);
-
-		priv->clk = of_clk_get(pdev->dev.of_node, 0);
-		if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-		if (!IS_ERR(priv->clk)) {
-			err = clk_prepare_enable(priv->clk);
-			if (err)
-				dev_err(&pdev->dev, "unable to enable the clk, "
-						    "err = %d\n", err);
-		}
+
+		/*
+		 * On OMAP4, enabling the shutdown_oflo interrupt is
+		 * done in the interrupt mask register. There is no
+		 * such register on EIP76, and it's enabled by the
+		 * same bit in the control register
+		 */
+		if (priv->pdata->regs[RNG_INTMASK_REG])
+			omap_rng_write(priv, RNG_INTMASK_REG,
+				       RNG_SHUTDOWN_OFLO_MASK);
+		else
+			omap_rng_write(priv, RNG_CONTROL_REG,
+				       RNG_SHUTDOWN_OFLO_MASK);
 	}
 	return 0;
 }
@@ -466,6 +468,18 @@ static int omap_rng_probe(struct platform_device *pdev)
 		goto err_ioremap;
 	}
 
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+	if (!IS_ERR(priv->clk)) {
+		ret = clk_prepare_enable(priv->clk);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Unable to enable the clk: %d\n", ret);
+			goto err_register;
+		}
+	}
+
 	ret = (dev->of_node) ? of_get_omap_rng_device_details(priv, pdev) :
 				get_omap_rng_device_details(priv);
 	if (ret)
diff --git a/drivers/char/hw_random/s390-trng.c b/drivers/char/hw_random/s390-trng.c
new file mode 100644
index 000000000000..aca48e893fca
--- /dev/null
+++ b/drivers/char/hw_random/s390-trng.c
@@ -0,0 +1,268 @@
+/*
+ * s390 TRNG device driver
+ *
+ * Driver for the TRNG (true random number generation) command
+ * available via CPACF extension MSA 7 on the s390 arch.
+
+ * Copyright IBM Corp. 2017
+ * Author(s): Harald Freudenberger <freude@de.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ */
+
+#define KMSG_COMPONENT "trng"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/hw_random.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/miscdevice.h>
+#include <linux/debugfs.h>
+#include <linux/atomic.h>
+#include <linux/random.h>
+#include <linux/sched/signal.h>
+#include <asm/debug.h>
+#include <asm/cpacf.h>
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("IBM Corporation");
+MODULE_DESCRIPTION("s390 CPACF TRNG device driver");
+
+
+/* trng related debug feature things */
+
+static debug_info_t *debug_info;
+
+#define DEBUG_DBG(...)	debug_sprintf_event(debug_info, 6, ##__VA_ARGS__)
+#define DEBUG_INFO(...) debug_sprintf_event(debug_info, 5, ##__VA_ARGS__)
+#define DEBUG_WARN(...) debug_sprintf_event(debug_info, 4, ##__VA_ARGS__)
+#define DEBUG_ERR(...)	debug_sprintf_event(debug_info, 3, ##__VA_ARGS__)
+
+
+/* trng helpers */
+
+static atomic64_t trng_dev_counter = ATOMIC64_INIT(0);
+static atomic64_t trng_hwrng_counter = ATOMIC64_INIT(0);
+
+
+/* file io functions */
+
+static int trng_open(struct inode *inode, struct file *file)
+{
+	return nonseekable_open(inode, file);
+}
+
+static ssize_t trng_read(struct file *file, char __user *ubuf,
+			 size_t nbytes, loff_t *ppos)
+{
+	u8 buf[32];
+	u8 *p = buf;
+	unsigned int n;
+	ssize_t ret = 0;
+
+	/*
+	 * use buf for requests <= sizeof(buf),
+	 * otherwise allocate one page and fetch
+	 * pagewise.
+	 */
+
+	if (nbytes > sizeof(buf)) {
+		p = (u8 *) __get_free_page(GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+	}
+
+	while (nbytes) {
+		if (need_resched()) {
+			if (signal_pending(current)) {
+				if (ret == 0)
+					ret = -ERESTARTSYS;
+				break;
+			}
+			schedule();
+		}
+		n = nbytes > PAGE_SIZE ? PAGE_SIZE : nbytes;
+		cpacf_trng(NULL, 0, p, n);
+		atomic64_add(n, &trng_dev_counter);
+		if (copy_to_user(ubuf, p, n)) {
+			ret = -EFAULT;
+			break;
+		}
+		nbytes -= n;
+		ubuf += n;
+		ret += n;
+	}
+
+	if (p != buf)
+		free_page((unsigned long) p);
+
+	DEBUG_DBG("trng_read()=%zd\n", ret);
+	return ret;
+}
+
+
+/* sysfs */
+
+static ssize_t trng_counter_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	u64 dev_counter = atomic64_read(&trng_dev_counter);
+	u64 hwrng_counter = atomic64_read(&trng_hwrng_counter);
+#if IS_ENABLED(CONFIG_ARCH_RANDOM)
+	u64 arch_counter = atomic64_read(&s390_arch_random_counter);
+
+	return snprintf(buf, PAGE_SIZE,
+			"trng:  %llu\n"
+			"hwrng: %llu\n"
+			"arch:  %llu\n"
+			"total: %llu\n",
+			dev_counter, hwrng_counter, arch_counter,
+			dev_counter + hwrng_counter + arch_counter);
+#else
+	return snprintf(buf, PAGE_SIZE,
+			"trng:  %llu\n"
+			"hwrng: %llu\n"
+			"total: %llu\n",
+			dev_counter, hwrng_counter,
+			dev_counter + hwrng_counter);
+#endif
+}
+static DEVICE_ATTR(byte_counter, 0444, trng_counter_show, NULL);
+
+static struct attribute *trng_dev_attrs[] = {
+	&dev_attr_byte_counter.attr,
+	NULL
+};
+
+static const struct attribute_group trng_dev_attr_group = {
+	.attrs = trng_dev_attrs
+};
+
+static const struct attribute_group *trng_dev_attr_groups[] = {
+	&trng_dev_attr_group,
+	NULL
+};
+
+static const struct file_operations trng_fops = {
+	.owner		= THIS_MODULE,
+	.open		= &trng_open,
+	.release	= NULL,
+	.read		= &trng_read,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice trng_dev = {
+	.name	= "trng",
+	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0444,
+	.fops	= &trng_fops,
+	.groups = trng_dev_attr_groups,
+};
+
+
+/* hwrng_register */
+
+static inline void _trng_hwrng_read(u8 *buf, size_t len)
+{
+	cpacf_trng(NULL, 0, buf, len);
+	atomic64_add(len, &trng_hwrng_counter);
+}
+
+static int trng_hwrng_data_read(struct hwrng *rng, u32 *data)
+{
+	size_t len = sizeof(*data);
+
+	_trng_hwrng_read((u8 *) data, len);
+
+	DEBUG_DBG("trng_hwrng_data_read()=%zu\n", len);
+
+	return len;
+}
+
+static int trng_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	size_t len = max <= PAGE_SIZE ? max : PAGE_SIZE;
+
+	_trng_hwrng_read((u8 *) data, len);
+
+	DEBUG_DBG("trng_hwrng_read()=%zu\n", len);
+
+	return len;
+}
+
+/*
+ * hwrng register struct
+ * The trng is suppost to have 100% entropy, and thus
+ * we register with a very high quality value.
+ */
+static struct hwrng trng_hwrng_dev = {
+	.name		= "s390-trng",
+	.data_read	= trng_hwrng_data_read,
+	.read		= trng_hwrng_read,
+	.quality	= 999,
+};
+
+
+/* init and exit */
+
+static void __init trng_debug_init(void)
+{
+	debug_info = debug_register("trng", 1, 1, 4 * sizeof(long));
+	debug_register_view(debug_info, &debug_sprintf_view);
+	debug_set_level(debug_info, 3);
+}
+
+static void trng_debug_exit(void)
+{
+	debug_unregister(debug_info);
+}
+
+static int __init trng_init(void)
+{
+	int ret;
+
+	trng_debug_init();
+
+	/* check if subfunction CPACF_PRNO_TRNG is available */
+	if (!cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG)) {
+		DEBUG_INFO("trng_init CPACF_PRNO_TRNG not available\n");
+		ret = -ENODEV;
+		goto out_dbg;
+	}
+
+	ret = misc_register(&trng_dev);
+	if (ret) {
+		DEBUG_WARN("trng_init misc_register() failed rc=%d\n", ret);
+		goto out_dbg;
+	}
+
+	ret = hwrng_register(&trng_hwrng_dev);
+	if (ret) {
+		DEBUG_WARN("trng_init hwrng_register() failed rc=%d\n", ret);
+		goto out_misc;
+	}
+
+	DEBUG_DBG("trng_init successful\n");
+
+	return 0;
+
+out_misc:
+	misc_deregister(&trng_dev);
+out_dbg:
+	trng_debug_exit();
+	return ret;
+}
+
+static void __exit trng_exit(void)
+{
+	hwrng_unregister(&trng_hwrng_dev);
+	misc_deregister(&trng_dev);
+	trng_debug_exit();
+}
+
+module_cpu_feature_match(MSA, trng_init);
+module_exit(trng_exit);
diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c
index cf37db263ecd..a0faa5f05deb 100644
--- a/drivers/char/hw_random/timeriomem-rng.c
+++ b/drivers/char/hw_random/timeriomem-rng.c
@@ -20,84 +20,100 @@
  * TODO: add support for reading sizes other than 32bits and masking
  */
 
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/hrtimer.h>
 #include <linux/hw_random.h>
 #include <linux/io.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/time.h>
 #include <linux/timeriomem-rng.h>
-#include <linux/jiffies.h>
-#include <linux/sched.h>
-#include <linux/timer.h>
-#include <linux/completion.h>
 
-struct timeriomem_rng_private_data {
+struct timeriomem_rng_private {
 	void __iomem		*io_base;
-	unsigned int		expires;
-	unsigned int		period;
+	ktime_t			period;
 	unsigned int		present:1;
 
-	struct timer_list	timer;
+	struct hrtimer		timer;
 	struct completion	completion;
 
-	struct hwrng		timeriomem_rng_ops;
+	struct hwrng		rng_ops;
 };
 
-#define to_rng_priv(rng) \
-		((struct timeriomem_rng_private_data *)rng->priv)
-
-/*
- * have data return 1, however return 0 if we have nothing
- */
-static int timeriomem_rng_data_present(struct hwrng *rng, int wait)
+static int timeriomem_rng_read(struct hwrng *hwrng, void *data,
+				size_t max, bool wait)
 {
-	struct timeriomem_rng_private_data *priv = to_rng_priv(rng);
-
-	if (!wait || priv->present)
-		return priv->present;
+	struct timeriomem_rng_private *priv =
+		container_of(hwrng, struct timeriomem_rng_private, rng_ops);
+	int retval = 0;
+	int period_us = ktime_to_us(priv->period);
+
+	/*
+	 * The RNG provides 32-bits per read.  Ensure there is enough space for
+	 * at minimum one read.
+	 */
+	if (max < sizeof(u32))
+		return 0;
+
+	/*
+	 * There may not have been enough time for new data to be generated
+	 * since the last request.  If the caller doesn't want to wait, let them
+	 * bail out.  Otherwise, wait for the completion.  If the new data has
+	 * already been generated, the completion should already be available.
+	 */
+	if (!wait && !priv->present)
+		return 0;
 
 	wait_for_completion(&priv->completion);
 
-	return 1;
-}
-
-static int timeriomem_rng_data_read(struct hwrng *rng, u32 *data)
-{
-	struct timeriomem_rng_private_data *priv = to_rng_priv(rng);
-	unsigned long cur;
-	s32 delay;
-
-	*data = readl(priv->io_base);
-
-	cur = jiffies;
-
-	delay = cur - priv->expires;
-	delay = priv->period - (delay % priv->period);
-
-	priv->expires = cur + delay;
+	do {
+		/*
+		 * After the first read, all additional reads will need to wait
+		 * for the RNG to generate new data.  Since the period can have
+		 * a wide range of values (1us to 1s have been observed), allow
+		 * for 1% tolerance in the sleep time rather than a fixed value.
+		 */
+		if (retval > 0)
+			usleep_range(period_us,
+					period_us + min(1, period_us / 100));
+
+		*(u32 *)data = readl(priv->io_base);
+		retval += sizeof(u32);
+		data += sizeof(u32);
+		max -= sizeof(u32);
+	} while (wait && max > sizeof(u32));
+
+	/*
+	 * Block any new callers until the RNG has had time to generate new
+	 * data.
+	 */
 	priv->present = 0;
-
 	reinit_completion(&priv->completion);
-	mod_timer(&priv->timer, priv->expires);
+	hrtimer_forward_now(&priv->timer, priv->period);
+	hrtimer_restart(&priv->timer);
 
-	return 4;
+	return retval;
 }
 
-static void timeriomem_rng_trigger(unsigned long data)
+static enum hrtimer_restart timeriomem_rng_trigger(struct hrtimer *timer)
 {
-	struct timeriomem_rng_private_data *priv
-			= (struct timeriomem_rng_private_data *)data;
+	struct timeriomem_rng_private *priv
+		= container_of(timer, struct timeriomem_rng_private, timer);
 
 	priv->present = 1;
 	complete(&priv->completion);
+
+	return HRTIMER_NORESTART;
 }
 
 static int timeriomem_rng_probe(struct platform_device *pdev)
 {
 	struct timeriomem_rng_data *pdata = pdev->dev.platform_data;
-	struct timeriomem_rng_private_data *priv;
+	struct timeriomem_rng_private *priv;
 	struct resource *res;
 	int err = 0;
 	int period;
@@ -119,7 +135,7 @@ static int timeriomem_rng_probe(struct platform_device *pdev)
 
 	/* Allocate memory for the device structure (and zero it) */
 	priv = devm_kzalloc(&pdev->dev,
-			sizeof(struct timeriomem_rng_private_data), GFP_KERNEL);
+			sizeof(struct timeriomem_rng_private), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
@@ -139,54 +155,41 @@ static int timeriomem_rng_probe(struct platform_device *pdev)
 		period = pdata->period;
 	}
 
-	priv->period = usecs_to_jiffies(period);
-	if (priv->period < 1) {
-		dev_err(&pdev->dev, "period is less than one jiffy\n");
-		return -EINVAL;
-	}
-
-	priv->expires	= jiffies;
-	priv->present	= 1;
-
+	priv->period = ns_to_ktime(period * NSEC_PER_USEC);
 	init_completion(&priv->completion);
-	complete(&priv->completion);
+	hrtimer_init(&priv->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	priv->timer.function = timeriomem_rng_trigger;
 
-	setup_timer(&priv->timer, timeriomem_rng_trigger, (unsigned long)priv);
-
-	priv->timeriomem_rng_ops.name		= dev_name(&pdev->dev);
-	priv->timeriomem_rng_ops.data_present	= timeriomem_rng_data_present;
-	priv->timeriomem_rng_ops.data_read	= timeriomem_rng_data_read;
-	priv->timeriomem_rng_ops.priv		= (unsigned long)priv;
+	priv->rng_ops.name = dev_name(&pdev->dev);
+	priv->rng_ops.read = timeriomem_rng_read;
 
 	priv->io_base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(priv->io_base)) {
-		err = PTR_ERR(priv->io_base);
-		goto out_timer;
+		return PTR_ERR(priv->io_base);
 	}
 
-	err = hwrng_register(&priv->timeriomem_rng_ops);
+	/* Assume random data is already available. */
+	priv->present = 1;
+	complete(&priv->completion);
+
+	err = hwrng_register(&priv->rng_ops);
 	if (err) {
 		dev_err(&pdev->dev, "problem registering\n");
-		goto out_timer;
+		return err;
 	}
 
 	dev_info(&pdev->dev, "32bits from 0x%p @ %dus\n",
 			priv->io_base, period);
 
 	return 0;
-
-out_timer:
-	del_timer_sync(&priv->timer);
-	return err;
 }
 
 static int timeriomem_rng_remove(struct platform_device *pdev)
 {
-	struct timeriomem_rng_private_data *priv = platform_get_drvdata(pdev);
-
-	hwrng_unregister(&priv->timeriomem_rng_ops);
+	struct timeriomem_rng_private *priv = platform_get_drvdata(pdev);
 
-	del_timer_sync(&priv->timer);
+	hwrng_unregister(&priv->rng_ops);
+	hrtimer_cancel(&priv->timer);
 
 	return 0;
 }
diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c
index d6f5d9eb102d..70d434bc1cbf 100644
--- a/drivers/char/ipmi/bt-bmc.c
+++ b/drivers/char/ipmi/bt-bmc.c
@@ -523,6 +523,7 @@ static int bt_bmc_remove(struct platform_device *pdev)
 
 static const struct of_device_id bt_bmc_match[] = {
 	{ .compatible = "aspeed,ast2400-ibt-bmc" },
+	{ .compatible = "aspeed,ast2500-ibt-bmc" },
 	{ },
 };
 
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 2a7c425ddfa7..b2b618f066e0 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1954,7 +1954,9 @@ static int hotmod_handler(const char *val, struct kernel_param *kp)
 				kfree(info);
 				goto out;
 			}
+			mutex_lock(&smi_infos_lock);
 			rv = try_smi_init(info);
+			mutex_unlock(&smi_infos_lock);
 			if (rv) {
 				cleanup_one_si(info);
 				goto out;
@@ -2042,8 +2044,10 @@ static int hardcode_find_bmc(void)
 		info->slave_addr = slave_addrs[i];
 
 		if (!add_smi(info)) {
+			mutex_lock(&smi_infos_lock);
 			if (try_smi_init(info))
 				cleanup_one_si(info);
+			mutex_unlock(&smi_infos_lock);
 			ret = 0;
 		} else {
 			kfree(info);
@@ -3492,6 +3496,11 @@ out_err:
 	return rv;
 }
 
+/*
+ * Try to start up an interface.  Must be called with smi_infos_lock
+ * held, primarily to keep smi_num consistent, we only one to do these
+ * one at a time.
+ */
 static int try_smi_init(struct smi_info *new_smi)
 {
 	int rv = 0;
@@ -3524,9 +3533,12 @@ static int try_smi_init(struct smi_info *new_smi)
 		goto out_err;
 	}
 
+	new_smi->intf_num = smi_num;
+
 	/* Do this early so it's available for logs. */
 	if (!new_smi->dev) {
-		init_name = kasprintf(GFP_KERNEL, "ipmi_si.%d", 0);
+		init_name = kasprintf(GFP_KERNEL, "ipmi_si.%d",
+				      new_smi->intf_num);
 
 		/*
 		 * If we don't already have a device from something
@@ -3593,8 +3605,6 @@ static int try_smi_init(struct smi_info *new_smi)
 
 	new_smi->interrupt_disabled = true;
 	atomic_set(&new_smi->need_watch, 0);
-	new_smi->intf_num = smi_num;
-	smi_num++;
 
 	rv = try_enable_event_buffer(new_smi);
 	if (rv == 0)
@@ -3661,6 +3671,9 @@ static int try_smi_init(struct smi_info *new_smi)
 		goto out_err_stop_timer;
 	}
 
+	/* Don't increment till we know we have succeeded. */
+	smi_num++;
+
 	dev_info(new_smi->dev, "IPMI %s interface initialized\n",
 		 si_to_str[new_smi->si_type]);
 
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index cca6e5bc1cea..0b22a9be5029 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -891,6 +891,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 		 * for details on the intricacies of this.
 		 */
 		int left;
+		unsigned char *data_to_send;
 
 		ssif_inc_stat(ssif_info, sent_messages_parts);
 
@@ -899,6 +900,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 			left = 32;
 		/* Length byte. */
 		ssif_info->multi_data[ssif_info->multi_pos] = left;
+		data_to_send = ssif_info->multi_data + ssif_info->multi_pos;
 		ssif_info->multi_pos += left;
 		if (left < 32)
 			/*
@@ -912,7 +914,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 		rv = ssif_i2c_send(ssif_info, msg_written_handler,
 				  I2C_SMBUS_WRITE,
 				  SSIF_IPMI_MULTI_PART_REQUEST_MIDDLE,
-				  ssif_info->multi_data + ssif_info->multi_pos,
+				  data_to_send,
 				  I2C_SMBUS_BLOCK_DATA);
 		if (rv < 0) {
 			/* request failed, just return the error. */
@@ -1642,9 +1644,8 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 	spin_lock_init(&ssif_info->lock);
 	ssif_info->ssif_state = SSIF_NORMAL;
-	init_timer(&ssif_info->retry_timer);
-	ssif_info->retry_timer.data = (unsigned long) ssif_info;
-	ssif_info->retry_timer.function = retry_timeout;
+	setup_timer(&ssif_info->retry_timer, retry_timeout,
+		    (unsigned long)ssif_info);
 
 	for (i = 0; i < SSIF_NUM_STATS; i++)
 		atomic_set(&ssif_info->stats[i], 0);
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 5ca24d9b101b..d165af8abe36 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -516,7 +516,7 @@ static void panic_halt_ipmi_heartbeat(void)
 	msg.cmd = IPMI_WDOG_RESET_TIMER;
 	msg.data = NULL;
 	msg.data_len = 0;
-	atomic_add(2, &panic_done_count);
+	atomic_add(1, &panic_done_count);
 	rv = ipmi_request_supply_msgs(watchdog_user,
 				      (struct ipmi_addr *) &addr,
 				      0,
@@ -526,7 +526,7 @@ static void panic_halt_ipmi_heartbeat(void)
 				      &panic_halt_heartbeat_recv_msg,
 				      1);
 	if (rv)
-		atomic_sub(2, &panic_done_count);
+		atomic_sub(1, &panic_done_count);
 }
 
 static struct ipmi_smi_msg panic_halt_smi_msg = {
@@ -550,12 +550,12 @@ static void panic_halt_ipmi_set_timeout(void)
 	/* Wait for the messages to be free. */
 	while (atomic_read(&panic_done_count) != 0)
 		ipmi_poll_interface(watchdog_user);
-	atomic_add(2, &panic_done_count);
+	atomic_add(1, &panic_done_count);
 	rv = i_ipmi_set_timeout(&panic_halt_smi_msg,
 				&panic_halt_recv_msg,
 				&send_heartbeat_now);
 	if (rv) {
-		atomic_sub(2, &panic_done_count);
+		atomic_sub(1, &panic_done_count);
 		printk(KERN_WARNING PFX
 		       "Unable to extend the watchdog timeout.");
 	} else {
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 6d9cc2d39d22..7e4a9d1296bb 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -60,6 +60,10 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 #endif
 
 #ifdef CONFIG_STRICT_DEVMEM
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return devmem_is_allowed(pfn);
+}
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
 	u64 from = ((u64)pfn) << PAGE_SHIFT;
@@ -75,6 +79,10 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	return 1;
 }
 #else
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return 1;
+}
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
 	return 1;
@@ -122,23 +130,31 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 
 	while (count > 0) {
 		unsigned long remaining;
+		int allowed;
 
 		sz = size_inside_page(p, count);
 
-		if (!range_is_allowed(p >> PAGE_SHIFT, count))
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
 			return -EPERM;
+		if (allowed == 2) {
+			/* Show zeros for restricted memory. */
+			remaining = clear_user(buf, sz);
+		} else {
+			/*
+			 * On ia64 if a page has been mapped somewhere as
+			 * uncached, then it must also be accessed uncached
+			 * by the kernel or data corruption may occur.
+			 */
+			ptr = xlate_dev_mem_ptr(p);
+			if (!ptr)
+				return -EFAULT;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_mem_ptr(p);
-		if (!ptr)
-			return -EFAULT;
+			remaining = copy_to_user(buf, ptr, sz);
+
+			unxlate_dev_mem_ptr(p, ptr);
+		}
 
-		remaining = copy_to_user(buf, ptr, sz);
-		unxlate_dev_mem_ptr(p, ptr);
 		if (remaining)
 			return -EFAULT;
 
@@ -181,30 +197,36 @@ static ssize_t write_mem(struct file *file, const char __user *buf,
 #endif
 
 	while (count > 0) {
+		int allowed;
+
 		sz = size_inside_page(p, count);
 
-		if (!range_is_allowed(p >> PAGE_SHIFT, sz))
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
 			return -EPERM;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_mem_ptr(p);
-		if (!ptr) {
-			if (written)
-				break;
-			return -EFAULT;
-		}
+		/* Skip actual writing when a page is marked as restricted. */
+		if (allowed == 1) {
+			/*
+			 * On ia64 if a page has been mapped somewhere as
+			 * uncached, then it must also be accessed uncached
+			 * by the kernel or data corruption may occur.
+			 */
+			ptr = xlate_dev_mem_ptr(p);
+			if (!ptr) {
+				if (written)
+					break;
+				return -EFAULT;
+			}
 
-		copied = copy_from_user(ptr, buf, sz);
-		unxlate_dev_mem_ptr(p, ptr);
-		if (copied) {
-			written += sz - copied;
-			if (written)
-				break;
-			return -EFAULT;
+			copied = copy_from_user(ptr, buf, sz);
+			unxlate_dev_mem_ptr(p, ptr);
+			if (copied) {
+				written += sz - copied;
+				if (written)
+					break;
+				return -EFAULT;
+			}
 		}
 
 		buf += sz;
diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index b708c85dc9c1..0e7fcb04f01e 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -478,18 +478,18 @@ static int sgi_clock_period;
 static struct timespec sgi_clock_offset;
 static int sgi_clock_period;
 
-static int sgi_clock_get(clockid_t clockid, struct timespec *tp)
+static int sgi_clock_get(clockid_t clockid, struct timespec64 *tp)
 {
 	u64 nsec;
 
 	nsec = rtc_time() * sgi_clock_period
 			+ sgi_clock_offset.tv_nsec;
-	*tp = ns_to_timespec(nsec);
+	*tp = ns_to_timespec64(nsec);
 	tp->tv_sec += sgi_clock_offset.tv_sec;
 	return 0;
 };
 
-static int sgi_clock_set(const clockid_t clockid, const struct timespec *tp)
+static int sgi_clock_set(const clockid_t clockid, const struct timespec64 *tp)
 {
 
 	u64 nsec;
@@ -657,7 +657,7 @@ static int sgi_timer_del(struct k_itimer *timr)
 }
 
 /* Assumption: it_lock is already held with irq's disabled */
-static void sgi_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
+static void sgi_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 {
 
 	if (timr->it.mmtimer.clock == TIMER_OFF) {
@@ -668,14 +668,14 @@ static void sgi_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 		return;
 	}
 
-	cur_setting->it_interval = ns_to_timespec(timr->it.mmtimer.incr * sgi_clock_period);
-	cur_setting->it_value = ns_to_timespec((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period);
+	cur_setting->it_interval = ns_to_timespec64(timr->it.mmtimer.incr * sgi_clock_period);
+	cur_setting->it_value = ns_to_timespec64((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period);
 }
 
 
 static int sgi_timer_set(struct k_itimer *timr, int flags,
-	struct itimerspec * new_setting,
-	struct itimerspec * old_setting)
+	struct itimerspec64 *new_setting,
+	struct itimerspec64 *old_setting)
 {
 	unsigned long when, period, irqflags;
 	int err = 0;
@@ -687,8 +687,8 @@ static int sgi_timer_set(struct k_itimer *timr, int flags,
 		sgi_timer_get(timr, old_setting);
 
 	sgi_timer_del(timr);
-	when = timespec_to_ns(&new_setting->it_value);
-	period = timespec_to_ns(&new_setting->it_interval);
+	when = timespec64_to_ns(&new_setting->it_value);
+	period = timespec64_to_ns(&new_setting->it_interval);
 
 	if (when == 0)
 		/* Clear timer */
@@ -699,11 +699,11 @@ static int sgi_timer_set(struct k_itimer *timr, int flags,
 		return -ENOMEM;
 
 	if (flags & TIMER_ABSTIME) {
-		struct timespec n;
+		struct timespec64 n;
 		unsigned long now;
 
-		getnstimeofday(&n);
-		now = timespec_to_ns(&n);
+		getnstimeofday64(&n);
+		now = timespec64_to_ns(&n);
 		if (when > now)
 			when -= now;
 		else
@@ -765,7 +765,7 @@ static int sgi_timer_set(struct k_itimer *timr, int flags,
 	return err;
 }
 
-static int sgi_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int sgi_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
 {
 	tp->tv_sec = 0;
 	tp->tv_nsec = sgi_clock_period;
diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c
index a5b1eb276c0b..e6d0d271c58c 100644
--- a/drivers/char/nwbutton.c
+++ b/drivers/char/nwbutton.c
@@ -6,7 +6,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/timer.h>
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 2a558c706581..3e73bcdf9e65 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -84,11 +84,14 @@ struct pp_struct {
 	struct ieee1284_info state;
 	struct ieee1284_info saved_state;
 	long default_inactivity;
+	int index;
 };
 
 /* should we use PARDEVICE_MAX here? */
 static struct device *devices[PARPORT_MAX];
 
+static DEFINE_IDA(ida_index);
+
 /* pp_struct.flags bitfields */
 #define PP_CLAIMED    (1<<0)
 #define PP_EXCL       (1<<1)
@@ -290,7 +293,7 @@ static int register_device(int minor, struct pp_struct *pp)
 	struct pardevice *pdev = NULL;
 	char *name;
 	struct pardev_cb ppdev_cb;
-	int rc = 0;
+	int rc = 0, index;
 
 	name = kasprintf(GFP_KERNEL, CHRDEV "%x", minor);
 	if (name == NULL)
@@ -303,20 +306,23 @@ static int register_device(int minor, struct pp_struct *pp)
 		goto err;
 	}
 
+	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
 	memset(&ppdev_cb, 0, sizeof(ppdev_cb));
 	ppdev_cb.irq_func = pp_irq;
 	ppdev_cb.flags = (pp->flags & PP_EXCL) ? PARPORT_FLAG_EXCL : 0;
 	ppdev_cb.private = pp;
-	pdev = parport_register_dev_model(port, name, &ppdev_cb, minor);
+	pdev = parport_register_dev_model(port, name, &ppdev_cb, index);
 	parport_put_port(port);
 
 	if (!pdev) {
 		pr_warn("%s: failed to register device!\n", name);
 		rc = -ENXIO;
+		ida_simple_remove(&ida_index, index);
 		goto err;
 	}
 
 	pp->pdev = pdev;
+	pp->index = index;
 	dev_dbg(&pdev->dev, "registered pardevice\n");
 err:
 	kfree(name);
@@ -755,6 +761,7 @@ static int pp_release(struct inode *inode, struct file *file)
 
 	if (pp->pdev) {
 		parport_unregister_device(pp->pdev);
+		ida_simple_remove(&ida_index, pp->index);
 		pp->pdev = NULL;
 		pr_debug(CHRDEV "%x: unregistered pardevice\n", minor);
 	}
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 1ef26403bcc8..0ab024918907 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -313,13 +313,6 @@ static int random_read_wakeup_bits = 64;
 static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
 
 /*
- * The minimum number of seconds between urandom pool reseeding.  We
- * do this to limit the amount of entropy that can be drained from the
- * input pool even if there are heavy demands on /dev/urandom.
- */
-static int random_min_urandom_seed = 60;
-
-/*
  * Originally, we used a primitive polynomial of degree .poolwords
  * over GF(2).  The taps for various sizes are defined below.  They
  * were chosen to be evenly spaced except for the last tap, which is 1
@@ -409,7 +402,6 @@ static struct poolinfo {
  */
 static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
 static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
-static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait);
 static struct fasync_struct *fasync;
 
 static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -467,7 +459,6 @@ struct entropy_store {
 	int entropy_count;
 	int entropy_total;
 	unsigned int initialized:1;
-	unsigned int limit:1;
 	unsigned int last_data_init:1;
 	__u8 last_data[EXTRACT_SIZE];
 };
@@ -485,7 +476,6 @@ static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy;
 static struct entropy_store input_pool = {
 	.poolinfo = &poolinfo_table[0],
 	.name = "input",
-	.limit = 1,
 	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
 	.pool = input_pool_data
 };
@@ -493,7 +483,6 @@ static struct entropy_store input_pool = {
 static struct entropy_store blocking_pool = {
 	.poolinfo = &poolinfo_table[1],
 	.name = "blocking",
-	.limit = 1,
 	.pull = &input_pool,
 	.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
 	.pool = blocking_pool_data,
@@ -855,13 +844,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	spin_unlock_irqrestore(&primary_crng.lock, flags);
 }
 
-static inline void maybe_reseed_primary_crng(void)
-{
-	if (crng_init > 2 &&
-	    time_after(jiffies, primary_crng.init_time + CRNG_RESEED_INTERVAL))
-		crng_reseed(&primary_crng, &input_pool);
-}
-
 static inline void crng_wait_ready(void)
 {
 	wait_event_interruptible(crng_init_wait, crng_ready());
@@ -1220,15 +1202,6 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 	    r->entropy_count > r->poolinfo->poolfracbits)
 		return;
 
-	if (r->limit == 0 && random_min_urandom_seed) {
-		unsigned long now = jiffies;
-
-		if (time_before(now,
-				r->last_pulled + random_min_urandom_seed * HZ))
-			return;
-		r->last_pulled = now;
-	}
-
 	_xfer_secondary_pool(r, nbytes);
 }
 
@@ -1236,8 +1209,6 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
 	__u32	tmp[OUTPUT_POOL_WORDS];
 
-	/* For /dev/random's pool, always leave two wakeups' worth */
-	int rsvd_bytes = r->limit ? 0 : random_read_wakeup_bits / 4;
 	int bytes = nbytes;
 
 	/* pull at least as much as a wakeup */
@@ -1248,7 +1219,7 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 	trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8,
 				  ENTROPY_BITS(r), ENTROPY_BITS(r->pull));
 	bytes = extract_entropy(r->pull, tmp, bytes,
-				random_read_wakeup_bits / 8, rsvd_bytes);
+				random_read_wakeup_bits / 8, 0);
 	mix_pool_bytes(r, tmp, bytes);
 	credit_entropy_bits(r, bytes*8);
 }
@@ -1276,7 +1247,7 @@ static void push_to_pool(struct work_struct *work)
 static size_t account(struct entropy_store *r, size_t nbytes, int min,
 		      int reserved)
 {
-	int entropy_count, orig;
+	int entropy_count, orig, have_bytes;
 	size_t ibytes, nfrac;
 
 	BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
@@ -1285,14 +1256,12 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	ibytes = nbytes;
-	/* If limited, never pull more than available */
-	if (r->limit) {
-		int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
+	/* never pull more than available */
+	have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
 
-		if ((have_bytes -= reserved) < 0)
-			have_bytes = 0;
-		ibytes = min_t(size_t, ibytes, have_bytes);
-	}
+	if ((have_bytes -= reserved) < 0)
+		have_bytes = 0;
+	ibytes = min_t(size_t, ibytes, have_bytes);
 	if (ibytes < min)
 		ibytes = 0;
 
@@ -1912,6 +1881,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 static int min_read_thresh = 8, min_write_thresh;
 static int max_read_thresh = OUTPUT_POOL_WORDS * 32;
 static int max_write_thresh = INPUT_POOL_WORDS * 32;
+static int random_min_urandom_seed = 60;
 static char sysctl_bootid[16];
 
 /*
@@ -2042,63 +2012,64 @@ struct ctl_table random_table[] = {
 };
 #endif 	/* CONFIG_SYSCTL */
 
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
-
-int random_int_secret_init(void)
-{
-	get_random_bytes(random_int_secret, sizeof(random_int_secret));
-	return 0;
-}
-
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
-		__aligned(sizeof(unsigned long));
+struct batched_entropy {
+	union {
+		u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)];
+		u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)];
+	};
+	unsigned int position;
+};
 
 /*
- * Get a random word for internal kernel use only. Similar to urandom but
- * with the goal of minimal entropy pool depletion. As a result, the random
- * value is not cryptographically secure but for several uses the cost of
- * depleting entropy is too high
+ * Get a random word for internal kernel use only. The quality of the random
+ * number is either as good as RDRAND or as good as /dev/urandom, with the
+ * goal of being quite fast and not depleting entropy.
  */
-unsigned int get_random_int(void)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64);
+u64 get_random_u64(void)
 {
-	__u32 *hash;
-	unsigned int ret;
+	u64 ret;
+	struct batched_entropy *batch;
 
-	if (arch_get_random_int(&ret))
+#if BITS_PER_LONG == 64
+	if (arch_get_random_long((unsigned long *)&ret))
 		return ret;
+#else
+	if (arch_get_random_long((unsigned long *)&ret) &&
+	    arch_get_random_long((unsigned long *)&ret + 1))
+	    return ret;
+#endif
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = hash[0];
-	put_cpu_var(get_random_int_hash);
-
+	batch = &get_cpu_var(batched_entropy_u64);
+	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
+		extract_crng((u8 *)batch->entropy_u64);
+		batch->position = 0;
+	}
+	ret = batch->entropy_u64[batch->position++];
+	put_cpu_var(batched_entropy_u64);
 	return ret;
 }
-EXPORT_SYMBOL(get_random_int);
+EXPORT_SYMBOL(get_random_u64);
 
-/*
- * Same as get_random_int(), but returns unsigned long.
- */
-unsigned long get_random_long(void)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32);
+u32 get_random_u32(void)
 {
-	__u32 *hash;
-	unsigned long ret;
+	u32 ret;
+	struct batched_entropy *batch;
 
-	if (arch_get_random_long(&ret))
+	if (arch_get_random_int(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = *(unsigned long *)hash;
-	put_cpu_var(get_random_int_hash);
-
+	batch = &get_cpu_var(batched_entropy_u32);
+	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
+		extract_crng((u8 *)batch->entropy_u32);
+		batch->position = 0;
+	}
+	ret = batch->entropy_u32[batch->position++];
+	put_cpu_var(batched_entropy_u32);
 	return ret;
 }
-EXPORT_SYMBOL(get_random_long);
+EXPORT_SYMBOL(get_random_u32);
 
 /**
  * randomize_page - Generate a random, page aligned address
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index e9b7e0b3cabe..87fe111d0be6 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -2202,14 +2202,16 @@ static int virtcons_freeze(struct virtio_device *vdev)
 
 	vdev->config->reset(vdev);
 
-	virtqueue_disable_cb(portdev->c_ivq);
+	if (use_multiport(portdev))
+		virtqueue_disable_cb(portdev->c_ivq);
 	cancel_work_sync(&portdev->control_work);
 	cancel_work_sync(&portdev->config_work);
 	/*
 	 * Once more: if control_work_handler() was running, it would
 	 * enable the cb as the last step.
 	 */
-	virtqueue_disable_cb(portdev->c_ivq);
+	if (use_multiport(portdev))
+		virtqueue_disable_cb(portdev->c_ivq);
 	remove_controlq_data(portdev);
 
 	list_for_each_entry(port, &portdev->ports, list) {
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index ab609a76706f..cf9449b3dbd9 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -429,6 +429,13 @@ static const struct clk_div_table pll_divp_table[] = {
 	{ 0, 2 }, { 1, 4 }, { 2, 6 }, { 3, 8 }, { 0 }
 };
 
+static const struct clk_div_table pll_divq_table[] = {
+	{ 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 },
+	{ 8, 8 }, { 9, 9 }, { 10, 10 }, { 11, 11 }, { 12, 12 }, { 13, 13 },
+	{ 14, 14 }, { 15, 15 },
+	{ 0 }
+};
+
 static const struct clk_div_table pll_divr_table[] = {
 	{ 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, { 0 }
 };
@@ -496,9 +503,9 @@ struct stm32f4_div_data {
 
 #define MAX_PLL_DIV 3
 static const struct stm32f4_div_data  div_data[MAX_PLL_DIV] = {
-	{ 16, 2, 0,			pll_divp_table	},
-	{ 24, 4, CLK_DIVIDER_ONE_BASED, NULL		},
-	{ 28, 3, 0,			pll_divr_table	},
+	{ 16, 2, 0, pll_divp_table },
+	{ 24, 4, 0, pll_divq_table },
+	{ 28, 3, 0, pll_divr_table },
 };
 
 struct stm32f4_pll_data {
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 0fb39fe217d1..67201f67a14a 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2502,7 +2502,7 @@ struct clk *__clk_create_clk(struct clk_hw *hw, const char *dev_id,
 
 	clk->core = hw->core;
 	clk->dev_id = dev_id;
-	clk->con_id = con_id;
+	clk->con_id = kstrdup_const(con_id, GFP_KERNEL);
 	clk->max_rate = ULONG_MAX;
 
 	clk_prepare_lock();
@@ -2518,6 +2518,7 @@ void __clk_free_clk(struct clk *clk)
 	hlist_del(&clk->clks_node);
 	clk_prepare_unlock();
 
+	kfree_const(clk->con_id);
 	kfree(clk);
 }
 
diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index 8ee2022ce5d5..cbd62e46bb5b 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -193,7 +193,7 @@
 /* CLKID_I2C */
 /* #define CLKID_SAR_ADC */
 #define CLKID_SMART_CARD	  24
-#define CLKID_RNG0		  25
+/* CLKID_RNG0 */
 #define CLKID_UART0		  26
 #define CLKID_SDHC		  27
 #define CLKID_STREAM		  28
diff --git a/drivers/clk/mvebu/ap806-system-controller.c b/drivers/clk/mvebu/ap806-system-controller.c
index f17702107ac5..8155baccc98e 100644
--- a/drivers/clk/mvebu/ap806-system-controller.c
+++ b/drivers/clk/mvebu/ap806-system-controller.c
@@ -23,7 +23,7 @@
 #define AP806_SAR_REG			0x400
 #define AP806_SAR_CLKFREQ_MODE_MASK	0x1f
 
-#define AP806_CLK_NUM			4
+#define AP806_CLK_NUM			5
 
 static struct clk *ap806_clks[AP806_CLK_NUM];
 
@@ -135,6 +135,23 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev)
 		goto fail3;
 	}
 
+	/* eMMC Clock is fixed clock divided by 3 */
+	if (of_property_read_string_index(np, "clock-output-names",
+					  4, &name)) {
+		ap806_clk_data.clk_num--;
+		dev_warn(&pdev->dev,
+			 "eMMC clock missing: update the device tree!\n");
+	} else {
+		ap806_clks[4] = clk_register_fixed_factor(NULL, name,
+							  fixedclk_name,
+							  0, 1, 3);
+		if (IS_ERR(ap806_clks[4])) {
+			ret = PTR_ERR(ap806_clks[4]);
+			goto fail4;
+		}
+	}
+
+	of_clk_add_provider(np, of_clk_src_onecell_get, &ap806_clk_data);
 	ret = of_clk_add_provider(np, of_clk_src_onecell_get, &ap806_clk_data);
 	if (ret)
 		goto fail_clk_add;
@@ -142,6 +159,8 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev)
 	return 0;
 
 fail_clk_add:
+	clk_unregister_fixed_factor(ap806_clks[4]);
+fail4:
 	clk_unregister_fixed_factor(ap806_clks[3]);
 fail3:
 	clk_unregister_fixed_rate(ap806_clks[2]);
diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index 924f560dcf80..00d4150e33c3 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -127,7 +127,7 @@ PNAME(mux_ddrphy_p)		= { "dpll_ddr", "gpll_ddr" };
 PNAME(mux_pll_src_3plls_p)	= { "apll", "dpll", "gpll" };
 PNAME(mux_timer_p)		= { "xin24m", "pclk_peri_src" };
 
-PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p)	= { "apll", "dpll", "gpll" "usb480m" };
+PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p)	= { "apll", "dpll", "gpll", "usb480m" };
 
 PNAME(mux_mmc_src_p)	= { "apll", "dpll", "gpll", "xin24m" };
 PNAME(mux_i2s_pre_p)	= { "i2s_src", "i2s_frac", "ext_i2s", "xin12m" };
@@ -450,6 +450,13 @@ static void __init rk3036_clk_init(struct device_node *np)
 		return;
 	}
 
+	/*
+	 * Make uart_pll_clk a child of the gpll, as all other sources are
+	 * not that usable / stable.
+	 */
+	writel_relaxed(HIWORD_UPDATE(0x2, 0x3, 10),
+		       reg_base + RK2928_CLKSEL_CON(13));
+
 	ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
 	if (IS_ERR(ctx)) {
 		pr_err("%s: rockchip clk init failed\n", __func__);
diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig
index 695bbf9ef428..a077ab6edffa 100644
--- a/drivers/clk/sunxi-ng/Kconfig
+++ b/drivers/clk/sunxi-ng/Kconfig
@@ -1,6 +1,7 @@
 config SUNXI_CCU
 	bool "Clock support for Allwinner SoCs"
 	depends on ARCH_SUNXI || COMPILE_TEST
+	select RESET_CONTROLLER
 	default ARCH_SUNXI
 
 if SUNXI_CCU
@@ -15,7 +16,7 @@ config SUNXI_CCU_FRAC
 	bool
 
 config SUNXI_CCU_GATE
-	bool
+	def_bool y
 
 config SUNXI_CCU_MUX
 	bool
@@ -80,6 +81,7 @@ config SUN6I_A31_CCU
 	select SUNXI_CCU_DIV
 	select SUNXI_CCU_NK
 	select SUNXI_CCU_NKM
+	select SUNXI_CCU_NKMP
 	select SUNXI_CCU_NM
 	select SUNXI_CCU_MP
 	select SUNXI_CCU_PHASE
@@ -134,6 +136,7 @@ config SUN8I_V3S_CCU
 config SUN9I_A80_CCU
 	bool "Support for the Allwinner A80 CCU"
 	select SUNXI_CCU_DIV
+	select SUNXI_CCU_MULT
 	select SUNXI_CCU_GATE
 	select SUNXI_CCU_NKMP
 	select SUNXI_CCU_NM
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index e3c084cc6da5..f54114c607df 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -566,7 +566,7 @@ static SUNXI_CCU_M_WITH_GATE(gpu_clk, "gpu", "pll-gpu",
 			     0x1a0, 0, 3, BIT(31), CLK_SET_RATE_PARENT);
 
 /* Fixed Factor clocks */
-static CLK_FIXED_FACTOR(osc12M_clk, "osc12M", "osc24M", 1, 2, 0);
+static CLK_FIXED_FACTOR(osc12M_clk, "osc12M", "osc24M", 2, 1, 0);
 
 /* We hardcode the divider to 4 for now */
 static CLK_FIXED_FACTOR(pll_audio_clk, "pll-audio",
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
index 4c9a920ff4ab..89e68d29bf45 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
@@ -608,7 +608,7 @@ static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", lcd_ch1_parents,
 				 0x150, 0, 4, 24, 2, BIT(31),
 				 CLK_SET_RATE_PARENT);
 
-static SUNXI_CCU_GATE(hdmi_ddc_clk, "hdmi-ddc", "osc24M", 0x150, BIT(31), 0);
+static SUNXI_CCU_GATE(hdmi_ddc_clk, "hdmi-ddc", "osc24M", 0x150, BIT(30), 0);
 
 static SUNXI_CCU_GATE(ps_clk, "ps", "lcd1-ch1", 0x140, BIT(31), 0);
 
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c
index a7b3c08ed0e2..2c69b631967a 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c
@@ -752,6 +752,13 @@ static const struct sunxi_ccu_desc sun8i_a33_ccu_desc = {
 	.num_resets	= ARRAY_SIZE(sun8i_a33_ccu_resets),
 };
 
+static struct ccu_pll_nb sun8i_a33_pll_cpu_nb = {
+	.common	= &pll_cpux_clk.common,
+	/* copy from pll_cpux_clk */
+	.enable	= BIT(31),
+	.lock	= BIT(28),
+};
+
 static struct ccu_mux_nb sun8i_a33_cpu_nb = {
 	.common		= &cpux_clk.common,
 	.cm		= &cpux_clk.mux,
@@ -783,6 +790,10 @@ static void __init sun8i_a33_ccu_setup(struct device_node *node)
 
 	sunxi_ccu_probe(node, reg, &sun8i_a33_ccu_desc);
 
+	/* Gate then ungate PLL CPU after any rate changes */
+	ccu_pll_notifier_register(&sun8i_a33_pll_cpu_nb);
+
+	/* Reparent CPU during PLL CPU rate changes */
 	ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
 				  &sun8i_a33_cpu_nb);
 }
diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c
index 8a47bafd7890..9d8724715a43 100644
--- a/drivers/clk/sunxi-ng/ccu_common.c
+++ b/drivers/clk/sunxi-ng/ccu_common.c
@@ -14,11 +14,13 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/iopoll.h>
 #include <linux/slab.h>
 
 #include "ccu_common.h"
+#include "ccu_gate.h"
 #include "ccu_reset.h"
 
 static DEFINE_SPINLOCK(ccu_lock);
@@ -39,6 +41,53 @@ void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock)
 	WARN_ON(readl_relaxed_poll_timeout(addr, reg, reg & lock, 100, 70000));
 }
 
+/*
+ * This clock notifier is called when the frequency of a PLL clock is
+ * changed. In common PLL designs, changes to the dividers take effect
+ * almost immediately, while changes to the multipliers (implemented
+ * as dividers in the feedback loop) take a few cycles to work into
+ * the feedback loop for the PLL to stablize.
+ *
+ * Sometimes when the PLL clock rate is changed, the decrease in the
+ * divider is too much for the decrease in the multiplier to catch up.
+ * The PLL clock rate will spike, and in some cases, might lock up
+ * completely.
+ *
+ * This notifier callback will gate and then ungate the clock,
+ * effectively resetting it, so it proceeds to work. Care must be
+ * taken to reparent consumers to other temporary clocks during the
+ * rate change, and that this notifier callback must be the first
+ * to be registered.
+ */
+static int ccu_pll_notifier_cb(struct notifier_block *nb,
+			       unsigned long event, void *data)
+{
+	struct ccu_pll_nb *pll = to_ccu_pll_nb(nb);
+	int ret = 0;
+
+	if (event != POST_RATE_CHANGE)
+		goto out;
+
+	ccu_gate_helper_disable(pll->common, pll->enable);
+
+	ret = ccu_gate_helper_enable(pll->common, pll->enable);
+	if (ret)
+		goto out;
+
+	ccu_helper_wait_for_lock(pll->common, pll->lock);
+
+out:
+	return notifier_from_errno(ret);
+}
+
+int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb)
+{
+	pll_nb->clk_nb.notifier_call = ccu_pll_notifier_cb;
+
+	return clk_notifier_register(pll_nb->common->hw.clk,
+				     &pll_nb->clk_nb);
+}
+
 int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
 		    const struct sunxi_ccu_desc *desc)
 {
diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h
index 73d81dc58fc5..d6fdd7a789aa 100644
--- a/drivers/clk/sunxi-ng/ccu_common.h
+++ b/drivers/clk/sunxi-ng/ccu_common.h
@@ -83,6 +83,18 @@ struct sunxi_ccu_desc {
 
 void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock);
 
+struct ccu_pll_nb {
+	struct notifier_block	clk_nb;
+	struct ccu_common	*common;
+
+	u32	enable;
+	u32	lock;
+};
+
+#define to_ccu_pll_nb(_nb) container_of(_nb, struct ccu_pll_nb, clk_nb)
+
+int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb);
+
 int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
 		    const struct sunxi_ccu_desc *desc);
 
diff --git a/drivers/clk/sunxi-ng/ccu_mp.c b/drivers/clk/sunxi-ng/ccu_mp.c
index 22c2ca7a2a22..b583f186a804 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.c
+++ b/drivers/clk/sunxi-ng/ccu_mp.c
@@ -85,6 +85,10 @@ static unsigned long ccu_mp_recalc_rate(struct clk_hw *hw,
 	unsigned int m, p;
 	u32 reg;
 
+	/* Adjust parent_rate according to pre-dividers */
+	ccu_mux_helper_adjust_parent_for_prediv(&cmp->common, &cmp->mux,
+						-1, &parent_rate);
+
 	reg = readl(cmp->common.base + cmp->common.reg);
 
 	m = reg >> cmp->m.shift;
@@ -117,6 +121,10 @@ static int ccu_mp_set_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned int m, p;
 	u32 reg;
 
+	/* Adjust parent_rate according to pre-dividers */
+	ccu_mux_helper_adjust_parent_for_prediv(&cmp->common, &cmp->mux,
+						-1, &parent_rate);
+
 	max_m = cmp->m.max ?: 1 << cmp->m.width;
 	max_p = cmp->p.max ?: 1 << ((1 << cmp->p.width) - 1);
 
diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.c b/drivers/clk/sunxi-ng/ccu_nkmp.c
index a2b40a000157..488055ed944f 100644
--- a/drivers/clk/sunxi-ng/ccu_nkmp.c
+++ b/drivers/clk/sunxi-ng/ccu_nkmp.c
@@ -107,7 +107,7 @@ static unsigned long ccu_nkmp_recalc_rate(struct clk_hw *hw,
 	p = reg >> nkmp->p.shift;
 	p &= (1 << nkmp->p.width) - 1;
 
-	return parent_rate * n * k >> p / m;
+	return (parent_rate * n * k >> p) / m;
 }
 
 static long ccu_nkmp_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 3356ab821624..545d541ae20e 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -67,20 +67,22 @@ config DW_APB_TIMER_OF
 	select DW_APB_TIMER
 	select CLKSRC_OF
 
-config GEMINI_TIMER
-	bool "Cortina Gemini timer driver" if COMPILE_TEST
+config FTTMR010_TIMER
+	bool "Faraday Technology timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
 	depends on HAS_IOMEM
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	select MFD_SYSCON
 	help
-	  Enables support for the Gemini timer
+	  Enables support for the Faraday Technology timer block
+	  FTTMR010.
 
 config ROCKCHIP_TIMER
 	bool "Rockchip timer driver" if COMPILE_TEST
 	depends on ARM || ARM64
 	select CLKSRC_OF
+	select CLKSRC_MMIO
 	help
 	  Enables the support for the rockchip timer driver.
 
@@ -366,6 +368,17 @@ config HISILICON_ERRATUM_161010101
 	  161010101. The workaround will be active if the hisilicon,erratum-161010101
 	  property is found in the timer node.
 
+config ARM64_ERRATUM_858921
+	bool "Workaround for Cortex-A73 erratum 858921"
+	default y
+	select ARM_ARCH_TIMER_OOL_WORKAROUND
+	depends on ARM_ARCH_TIMER && ARM64
+	help
+	  This option enables a workaround applicable to Cortex-A73
+	  (all versions), whose counter may return incorrect values.
+	  The workaround will be dynamically enabled when an affected
+	  core is detected.
+
 config ARM_GLOBAL_TIMER
 	bool "Support for the ARM global timer" if COMPILE_TEST
 	select CLKSRC_OF if OF
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index d227d1314f14..2b5b56a6f00f 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -17,7 +17,7 @@ obj-$(CONFIG_CLKSRC_MMIO)	+= mmio.o
 obj-$(CONFIG_DIGICOLOR_TIMER)	+= timer-digicolor.o
 obj-$(CONFIG_DW_APB_TIMER)	+= dw_apb_timer.o
 obj-$(CONFIG_DW_APB_TIMER_OF)	+= dw_apb_timer_of.o
-obj-$(CONFIG_GEMINI_TIMER)	+= timer-gemini.o
+obj-$(CONFIG_FTTMR010_TIMER)	+= timer-fttmr010.o
 obj-$(CONFIG_ROCKCHIP_TIMER)      += rockchip_timer.o
 obj-$(CONFIG_CLKSRC_NOMADIK_MTU)	+= nomadik-mtu.o
 obj-$(CONFIG_CLKSRC_DBX500_PRCMU)	+= clksrc-dbx500-prcmu.o
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index 7517f959cba7..21649733827d 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -37,7 +37,7 @@ static int noinline arc_get_timer_clk(struct device_node *node)
 
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk)) {
-		pr_err("timer missing clk");
+		pr_err("timer missing clk\n");
 		return PTR_ERR(clk);
 	}
 
@@ -89,7 +89,7 @@ static int __init arc_cs_setup_gfrc(struct device_node *node)
 
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 	if (!mp.gfrc) {
-		pr_warn("Global-64-bit-Ctr clocksource not detected");
+		pr_warn("Global-64-bit-Ctr clocksource not detected\n");
 		return -ENXIO;
 	}
 
@@ -140,13 +140,13 @@ static int __init arc_cs_setup_rtc(struct device_node *node)
 
 	READ_BCR(ARC_REG_TIMERS_BCR, timer);
 	if (!timer.rtc) {
-		pr_warn("Local-64-bit-Ctr clocksource not detected");
+		pr_warn("Local-64-bit-Ctr clocksource not detected\n");
 		return -ENXIO;
 	}
 
 	/* Local to CPU hence not usable in SMP */
 	if (IS_ENABLED(CONFIG_SMP)) {
-		pr_warn("Local-64-bit-Ctr not usable in SMP");
+		pr_warn("Local-64-bit-Ctr not usable in SMP\n");
 		return -EINVAL;
 	}
 
@@ -290,13 +290,13 @@ static int __init arc_clockevent_setup(struct device_node *node)
 
 	arc_timer_irq = irq_of_parse_and_map(node, 0);
 	if (arc_timer_irq <= 0) {
-		pr_err("clockevent: missing irq");
+		pr_err("clockevent: missing irq\n");
 		return -EINVAL;
 	}
 
 	ret = arc_get_timer_clk(node);
 	if (ret) {
-		pr_err("clockevent: missing clk");
+		pr_err("clockevent: missing clk\n");
 		return ret;
 	}
 
@@ -313,7 +313,7 @@ static int __init arc_clockevent_setup(struct device_node *node)
 				arc_timer_starting_cpu,
 				arc_timer_dying_cpu);
 	if (ret) {
-		pr_err("Failed to setup hotplug state");
+		pr_err("Failed to setup hotplug state\n");
 		return ret;
 	}
 	return 0;
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 7a8a4117f123..a1fb918b8021 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -33,6 +33,9 @@
 
 #include <clocksource/arm_arch_timer.h>
 
+#undef pr_fmt
+#define pr_fmt(fmt) "arch_timer: " fmt
+
 #define CNTTIDR		0x08
 #define CNTTIDR_VIRT(n)	(BIT(1) << ((n) * 4))
 
@@ -52,8 +55,6 @@
 #define CNTV_TVAL	0x38
 #define CNTV_CTL	0x3c
 
-#define ARCH_CP15_TIMER	BIT(0)
-#define ARCH_MEM_TIMER	BIT(1)
 static unsigned arch_timers_present __initdata;
 
 static void __iomem *arch_counter_base;
@@ -66,23 +67,15 @@ struct arch_timer {
 #define to_arch_timer(e) container_of(e, struct arch_timer, evt)
 
 static u32 arch_timer_rate;
-
-enum ppi_nr {
-	PHYS_SECURE_PPI,
-	PHYS_NONSECURE_PPI,
-	VIRT_PPI,
-	HYP_PPI,
-	MAX_TIMER_PPI
-};
-
-static int arch_timer_ppi[MAX_TIMER_PPI];
+static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI];
 
 static struct clock_event_device __percpu *arch_timer_evt;
 
-static enum ppi_nr arch_timer_uses_ppi = VIRT_PPI;
+static enum arch_timer_ppi_nr arch_timer_uses_ppi = ARCH_TIMER_VIRT_PPI;
 static bool arch_timer_c3stop;
 static bool arch_timer_mem_use_virtual;
 static bool arch_counter_suspend_stop;
+static bool vdso_default = true;
 
 static bool evtstrm_enable = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
 
@@ -96,6 +89,105 @@ early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg);
  * Architected system timer support.
  */
 
+static __always_inline
+void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
+			  struct clock_event_device *clk)
+{
+	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			writel_relaxed(val, timer->base + CNTP_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			writel_relaxed(val, timer->base + CNTP_TVAL);
+			break;
+		}
+	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			writel_relaxed(val, timer->base + CNTV_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			writel_relaxed(val, timer->base + CNTV_TVAL);
+			break;
+		}
+	} else {
+		arch_timer_reg_write_cp15(access, reg, val);
+	}
+}
+
+static __always_inline
+u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
+			struct clock_event_device *clk)
+{
+	u32 val;
+
+	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			val = readl_relaxed(timer->base + CNTP_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			val = readl_relaxed(timer->base + CNTP_TVAL);
+			break;
+		}
+	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			val = readl_relaxed(timer->base + CNTV_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			val = readl_relaxed(timer->base + CNTV_TVAL);
+			break;
+		}
+	} else {
+		val = arch_timer_reg_read_cp15(access, reg);
+	}
+
+	return val;
+}
+
+/*
+ * Default to cp15 based access because arm64 uses this function for
+ * sched_clock() before DT is probed and the cp15 method is guaranteed
+ * to exist on arm64. arm doesn't use this before DT is probed so even
+ * if we don't have the cp15 accessors we won't have a problem.
+ */
+u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
+
+static u64 arch_counter_read(struct clocksource *cs)
+{
+	return arch_timer_read_counter();
+}
+
+static u64 arch_counter_read_cc(const struct cyclecounter *cc)
+{
+	return arch_timer_read_counter();
+}
+
+static struct clocksource clocksource_counter = {
+	.name	= "arch_sys_counter",
+	.rating	= 400,
+	.read	= arch_counter_read,
+	.mask	= CLOCKSOURCE_MASK(56),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static struct cyclecounter cyclecounter __ro_after_init = {
+	.read	= arch_counter_read_cc,
+	.mask	= CLOCKSOURCE_MASK(56),
+};
+
+struct ate_acpi_oem_info {
+	char oem_id[ACPI_OEM_ID_SIZE + 1];
+	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
+	u32 oem_revision;
+};
+
 #ifdef CONFIG_FSL_ERRATUM_A008585
 /*
  * The number of retries is an arbitrary value well beyond the highest number
@@ -170,97 +262,289 @@ static u64 notrace hisi_161010101_read_cntvct_el0(void)
 {
 	return __hisi_161010101_read_reg(cntvct_el0);
 }
+
+static struct ate_acpi_oem_info hisi_161010101_oem_info[] = {
+	/*
+	 * Note that trailing spaces are required to properly match
+	 * the OEM table information.
+	 */
+	{
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP05   ",
+		.oem_revision	= 0,
+	},
+	{
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP06   ",
+		.oem_revision	= 0,
+	},
+	{
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP07   ",
+		.oem_revision	= 0,
+	},
+	{ /* Sentinel indicating the end of the OEM array */ },
+};
+#endif
+
+#ifdef CONFIG_ARM64_ERRATUM_858921
+static u64 notrace arm64_858921_read_cntvct_el0(void)
+{
+	u64 old, new;
+
+	old = read_sysreg(cntvct_el0);
+	new = read_sysreg(cntvct_el0);
+	return (((old ^ new) >> 32) & 1) ? old : new;
+}
 #endif
 
 #ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround = NULL;
+DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *,
+	       timer_unstable_counter_workaround);
 EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
 
 DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
 EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
 
+static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
+						struct clock_event_device *clk)
+{
+	unsigned long ctrl;
+	u64 cval = evt + arch_counter_get_cntvct();
+
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+	ctrl |= ARCH_TIMER_CTRL_ENABLE;
+	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS)
+		write_sysreg(cval, cntp_cval_el0);
+	else
+		write_sysreg(cval, cntv_cval_el0);
+
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+}
+
+static __maybe_unused int erratum_set_next_event_tval_virt(unsigned long evt,
+					    struct clock_event_device *clk)
+{
+	erratum_set_next_event_tval_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+	return 0;
+}
+
+static __maybe_unused int erratum_set_next_event_tval_phys(unsigned long evt,
+					    struct clock_event_device *clk)
+{
+	erratum_set_next_event_tval_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+	return 0;
+}
+
 static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 #ifdef CONFIG_FSL_ERRATUM_A008585
 	{
+		.match_type = ate_match_dt,
 		.id = "fsl,erratum-a008585",
+		.desc = "Freescale erratum a005858",
 		.read_cntp_tval_el0 = fsl_a008585_read_cntp_tval_el0,
 		.read_cntv_tval_el0 = fsl_a008585_read_cntv_tval_el0,
 		.read_cntvct_el0 = fsl_a008585_read_cntvct_el0,
+		.set_next_event_phys = erratum_set_next_event_tval_phys,
+		.set_next_event_virt = erratum_set_next_event_tval_virt,
 	},
 #endif
 #ifdef CONFIG_HISILICON_ERRATUM_161010101
 	{
+		.match_type = ate_match_dt,
 		.id = "hisilicon,erratum-161010101",
+		.desc = "HiSilicon erratum 161010101",
 		.read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
 		.read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
 		.read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
+		.set_next_event_phys = erratum_set_next_event_tval_phys,
+		.set_next_event_virt = erratum_set_next_event_tval_virt,
+	},
+	{
+		.match_type = ate_match_acpi_oem_info,
+		.id = hisi_161010101_oem_info,
+		.desc = "HiSilicon erratum 161010101",
+		.read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
+		.read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
+		.read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
+		.set_next_event_phys = erratum_set_next_event_tval_phys,
+		.set_next_event_virt = erratum_set_next_event_tval_virt,
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_858921
+	{
+		.match_type = ate_match_local_cap_id,
+		.id = (void *)ARM64_WORKAROUND_858921,
+		.desc = "ARM erratum 858921",
+		.read_cntvct_el0 = arm64_858921_read_cntvct_el0,
 	},
 #endif
 };
-#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
 
-static __always_inline
-void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
-			  struct clock_event_device *clk)
+typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *,
+			       const void *);
+
+static
+bool arch_timer_check_dt_erratum(const struct arch_timer_erratum_workaround *wa,
+				 const void *arg)
 {
-	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
-		struct arch_timer *timer = to_arch_timer(clk);
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			writel_relaxed(val, timer->base + CNTP_CTL);
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			writel_relaxed(val, timer->base + CNTP_TVAL);
-			break;
-		}
-	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
-		struct arch_timer *timer = to_arch_timer(clk);
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			writel_relaxed(val, timer->base + CNTV_CTL);
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			writel_relaxed(val, timer->base + CNTV_TVAL);
-			break;
-		}
-	} else {
-		arch_timer_reg_write_cp15(access, reg, val);
+	const struct device_node *np = arg;
+
+	return of_property_read_bool(np, wa->id);
+}
+
+static
+bool arch_timer_check_local_cap_erratum(const struct arch_timer_erratum_workaround *wa,
+					const void *arg)
+{
+	return this_cpu_has_cap((uintptr_t)wa->id);
+}
+
+
+static
+bool arch_timer_check_acpi_oem_erratum(const struct arch_timer_erratum_workaround *wa,
+				       const void *arg)
+{
+	static const struct ate_acpi_oem_info empty_oem_info = {};
+	const struct ate_acpi_oem_info *info = wa->id;
+	const struct acpi_table_header *table = arg;
+
+	/* Iterate over the ACPI OEM info array, looking for a match */
+	while (memcmp(info, &empty_oem_info, sizeof(*info))) {
+		if (!memcmp(info->oem_id, table->oem_id, ACPI_OEM_ID_SIZE) &&
+		    !memcmp(info->oem_table_id, table->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
+		    info->oem_revision == table->oem_revision)
+			return true;
+
+		info++;
 	}
+
+	return false;
 }
 
-static __always_inline
-u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
-			struct clock_event_device *clk)
+static const struct arch_timer_erratum_workaround *
+arch_timer_iterate_errata(enum arch_timer_erratum_match_type type,
+			  ate_match_fn_t match_fn,
+			  void *arg)
 {
-	u32 val;
+	int i;
 
-	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
-		struct arch_timer *timer = to_arch_timer(clk);
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			val = readl_relaxed(timer->base + CNTP_CTL);
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			val = readl_relaxed(timer->base + CNTP_TVAL);
-			break;
-		}
-	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
-		struct arch_timer *timer = to_arch_timer(clk);
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			val = readl_relaxed(timer->base + CNTV_CTL);
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			val = readl_relaxed(timer->base + CNTV_TVAL);
-			break;
-		}
+	for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) {
+		if (ool_workarounds[i].match_type != type)
+			continue;
+
+		if (match_fn(&ool_workarounds[i], arg))
+			return &ool_workarounds[i];
+	}
+
+	return NULL;
+}
+
+static
+void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa,
+				  bool local)
+{
+	int i;
+
+	if (local) {
+		__this_cpu_write(timer_unstable_counter_workaround, wa);
 	} else {
-		val = arch_timer_reg_read_cp15(access, reg);
+		for_each_possible_cpu(i)
+			per_cpu(timer_unstable_counter_workaround, i) = wa;
 	}
 
-	return val;
+	static_branch_enable(&arch_timer_read_ool_enabled);
+
+	/*
+	 * Don't use the vdso fastpath if errata require using the
+	 * out-of-line counter accessor. We may change our mind pretty
+	 * late in the game (with a per-CPU erratum, for example), so
+	 * change both the default value and the vdso itself.
+	 */
+	if (wa->read_cntvct_el0) {
+		clocksource_counter.archdata.vdso_direct = false;
+		vdso_default = false;
+	}
+}
+
+static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type,
+					    void *arg)
+{
+	const struct arch_timer_erratum_workaround *wa;
+	ate_match_fn_t match_fn = NULL;
+	bool local = false;
+
+	switch (type) {
+	case ate_match_dt:
+		match_fn = arch_timer_check_dt_erratum;
+		break;
+	case ate_match_local_cap_id:
+		match_fn = arch_timer_check_local_cap_erratum;
+		local = true;
+		break;
+	case ate_match_acpi_oem_info:
+		match_fn = arch_timer_check_acpi_oem_erratum;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	wa = arch_timer_iterate_errata(type, match_fn, arg);
+	if (!wa)
+		return;
+
+	if (needs_unstable_timer_counter_workaround()) {
+		const struct arch_timer_erratum_workaround *__wa;
+		__wa = __this_cpu_read(timer_unstable_counter_workaround);
+		if (__wa && wa != __wa)
+			pr_warn("Can't enable workaround for %s (clashes with %s\n)",
+				wa->desc, __wa->desc);
+
+		if (__wa)
+			return;
+	}
+
+	arch_timer_enable_workaround(wa, local);
+	pr_info("Enabling %s workaround for %s\n",
+		local ? "local" : "global", wa->desc);
 }
 
+#define erratum_handler(fn, r, ...)					\
+({									\
+	bool __val;							\
+	if (needs_unstable_timer_counter_workaround()) {		\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		if (__wa && __wa->fn) {					\
+			r = __wa->fn(__VA_ARGS__);			\
+			__val = true;					\
+		} else {						\
+			__val = false;					\
+		}							\
+	} else {							\
+		__val = false;						\
+	}								\
+	__val;								\
+})
+
+static bool arch_timer_this_cpu_has_cntvct_wa(void)
+{
+	const struct arch_timer_erratum_workaround *wa;
+
+	wa = __this_cpu_read(timer_unstable_counter_workaround);
+	return wa && wa->read_cntvct_el0;
+}
+#else
+#define arch_timer_check_ool_workaround(t,a)		do { } while(0)
+#define erratum_set_next_event_tval_virt(...)		({BUG(); 0;})
+#define erratum_set_next_event_tval_phys(...)		({BUG(); 0;})
+#define erratum_handler(fn, r, ...)			({false;})
+#define arch_timer_this_cpu_has_cntvct_wa()		({false;})
+#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
+
 static __always_inline irqreturn_t timer_handler(const int access,
 					struct clock_event_device *evt)
 {
@@ -348,43 +632,14 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-static __always_inline void erratum_set_next_event_generic(const int access,
-		unsigned long evt, struct clock_event_device *clk)
-{
-	unsigned long ctrl;
-	u64 cval = evt + arch_counter_get_cntvct();
-
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
-	ctrl |= ARCH_TIMER_CTRL_ENABLE;
-	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
-
-	if (access == ARCH_TIMER_PHYS_ACCESS)
-		write_sysreg(cval, cntp_cval_el0);
-	else if (access == ARCH_TIMER_VIRT_ACCESS)
-		write_sysreg(cval, cntv_cval_el0);
-
-	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
-}
-
-static int erratum_set_next_event_virt(unsigned long evt,
-					   struct clock_event_device *clk)
-{
-	erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
-	return 0;
-}
-
-static int erratum_set_next_event_phys(unsigned long evt,
-					   struct clock_event_device *clk)
-{
-	erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
-	return 0;
-}
-#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
-
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
 {
+	int ret;
+
+	if (erratum_handler(set_next_event_virt, ret, evt, clk))
+		return ret;
+
 	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
@@ -392,6 +647,11 @@ static int arch_timer_set_next_event_virt(unsigned long evt,
 static int arch_timer_set_next_event_phys(unsigned long evt,
 					  struct clock_event_device *clk)
 {
+	int ret;
+
+	if (erratum_handler(set_next_event_phys, ret, evt, clk))
+		return ret;
+
 	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
@@ -410,25 +670,12 @@ static int arch_timer_set_next_event_phys_mem(unsigned long evt,
 	return 0;
 }
 
-static void erratum_workaround_set_sne(struct clock_event_device *clk)
-{
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-	if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
-		return;
-
-	if (arch_timer_uses_ppi == VIRT_PPI)
-		clk->set_next_event = erratum_set_next_event_virt;
-	else
-		clk->set_next_event = erratum_set_next_event_phys;
-#endif
-}
-
 static void __arch_timer_setup(unsigned type,
 			       struct clock_event_device *clk)
 {
 	clk->features = CLOCK_EVT_FEAT_ONESHOT;
 
-	if (type == ARCH_CP15_TIMER) {
+	if (type == ARCH_TIMER_TYPE_CP15) {
 		if (arch_timer_c3stop)
 			clk->features |= CLOCK_EVT_FEAT_C3STOP;
 		clk->name = "arch_sys_timer";
@@ -436,14 +683,14 @@ static void __arch_timer_setup(unsigned type,
 		clk->cpumask = cpumask_of(smp_processor_id());
 		clk->irq = arch_timer_ppi[arch_timer_uses_ppi];
 		switch (arch_timer_uses_ppi) {
-		case VIRT_PPI:
+		case ARCH_TIMER_VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
 			clk->set_next_event = arch_timer_set_next_event_virt;
 			break;
-		case PHYS_SECURE_PPI:
-		case PHYS_NONSECURE_PPI:
-		case HYP_PPI:
+		case ARCH_TIMER_PHYS_SECURE_PPI:
+		case ARCH_TIMER_PHYS_NONSECURE_PPI:
+		case ARCH_TIMER_HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
 			clk->set_next_event = arch_timer_set_next_event_phys;
@@ -452,7 +699,7 @@ static void __arch_timer_setup(unsigned type,
 			BUG();
 		}
 
-		erratum_workaround_set_sne(clk);
+		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -508,23 +755,31 @@ static void arch_counter_set_user_access(void)
 {
 	u32 cntkctl = arch_timer_get_cntkctl();
 
-	/* Disable user access to the timers and the physical counter */
+	/* Disable user access to the timers and both counters */
 	/* Also disable virtual event stream */
 	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
 			| ARCH_TIMER_USR_VT_ACCESS_EN
+		        | ARCH_TIMER_USR_VCT_ACCESS_EN
 			| ARCH_TIMER_VIRT_EVT_EN
 			| ARCH_TIMER_USR_PCT_ACCESS_EN);
 
-	/* Enable user access to the virtual counter */
-	cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+	/*
+	 * Enable user access to the virtual counter if it doesn't
+	 * need to be workaround. The vdso may have been already
+	 * disabled though.
+	 */
+	if (arch_timer_this_cpu_has_cntvct_wa())
+		pr_info("CPU%d: Trapping CNTVCT access\n", smp_processor_id());
+	else
+		cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
 
 	arch_timer_set_cntkctl(cntkctl);
 }
 
 static bool arch_timer_has_nonsecure_ppi(void)
 {
-	return (arch_timer_uses_ppi == PHYS_SECURE_PPI &&
-		arch_timer_ppi[PHYS_NONSECURE_PPI]);
+	return (arch_timer_uses_ppi == ARCH_TIMER_PHYS_SECURE_PPI &&
+		arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]);
 }
 
 static u32 check_ppi_trigger(int irq)
@@ -545,14 +800,15 @@ static int arch_timer_starting_cpu(unsigned int cpu)
 	struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
 	u32 flags;
 
-	__arch_timer_setup(ARCH_CP15_TIMER, clk);
+	__arch_timer_setup(ARCH_TIMER_TYPE_CP15, clk);
 
 	flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]);
 	enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags);
 
 	if (arch_timer_has_nonsecure_ppi()) {
-		flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]);
-		enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags);
+		flags = check_ppi_trigger(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]);
+		enable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI],
+				  flags);
 	}
 
 	arch_counter_set_user_access();
@@ -562,43 +818,39 @@ static int arch_timer_starting_cpu(unsigned int cpu)
 	return 0;
 }
 
-static void
-arch_timer_detect_rate(void __iomem *cntbase, struct device_node *np)
+/*
+ * For historical reasons, when probing with DT we use whichever (non-zero)
+ * rate was probed first, and don't verify that others match. If the first node
+ * probed has a clock-frequency property, this overrides the HW register.
+ */
+static void arch_timer_of_configure_rate(u32 rate, struct device_node *np)
 {
 	/* Who has more than one independent system counter? */
 	if (arch_timer_rate)
 		return;
 
-	/*
-	 * Try to determine the frequency from the device tree or CNTFRQ,
-	 * if ACPI is enabled, get the frequency from CNTFRQ ONLY.
-	 */
-	if (!acpi_disabled ||
-	    of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) {
-		if (cntbase)
-			arch_timer_rate = readl_relaxed(cntbase + CNTFRQ);
-		else
-			arch_timer_rate = arch_timer_get_cntfrq();
-	}
+	if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate))
+		arch_timer_rate = rate;
 
 	/* Check the timer frequency. */
 	if (arch_timer_rate == 0)
-		pr_warn("Architected timer frequency not available\n");
+		pr_warn("frequency not available\n");
 }
 
 static void arch_timer_banner(unsigned type)
 {
-	pr_info("Architected %s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
-		     type & ARCH_CP15_TIMER ? "cp15" : "",
-		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  " and " : "",
-		     type & ARCH_MEM_TIMER ? "mmio" : "",
-		     (unsigned long)arch_timer_rate / 1000000,
-		     (unsigned long)(arch_timer_rate / 10000) % 100,
-		     type & ARCH_CP15_TIMER ?
-		     (arch_timer_uses_ppi == VIRT_PPI) ? "virt" : "phys" :
+	pr_info("%s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
+		type & ARCH_TIMER_TYPE_CP15 ? "cp15" : "",
+		type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ?
+			" and " : "",
+		type & ARCH_TIMER_TYPE_MEM ? "mmio" : "",
+		(unsigned long)arch_timer_rate / 1000000,
+		(unsigned long)(arch_timer_rate / 10000) % 100,
+		type & ARCH_TIMER_TYPE_CP15 ?
+			(arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) ? "virt" : "phys" :
 			"",
-		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  "/" : "",
-		     type & ARCH_MEM_TIMER ?
+		type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ? "/" : "",
+		type & ARCH_TIMER_TYPE_MEM ?
 			arch_timer_mem_use_virtual ? "virt" : "phys" :
 			"");
 }
@@ -621,37 +873,6 @@ static u64 arch_counter_get_cntvct_mem(void)
 	return ((u64) vct_hi << 32) | vct_lo;
 }
 
-/*
- * Default to cp15 based access because arm64 uses this function for
- * sched_clock() before DT is probed and the cp15 method is guaranteed
- * to exist on arm64. arm doesn't use this before DT is probed so even
- * if we don't have the cp15 accessors we won't have a problem.
- */
-u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
-
-static u64 arch_counter_read(struct clocksource *cs)
-{
-	return arch_timer_read_counter();
-}
-
-static u64 arch_counter_read_cc(const struct cyclecounter *cc)
-{
-	return arch_timer_read_counter();
-}
-
-static struct clocksource clocksource_counter = {
-	.name	= "arch_sys_counter",
-	.rating	= 400,
-	.read	= arch_counter_read,
-	.mask	= CLOCKSOURCE_MASK(56),
-	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static struct cyclecounter cyclecounter __ro_after_init = {
-	.read	= arch_counter_read_cc,
-	.mask	= CLOCKSOURCE_MASK(56),
-};
-
 static struct arch_timer_kvm_info arch_timer_kvm_info;
 
 struct arch_timer_kvm_info *arch_timer_get_kvm_info(void)
@@ -664,22 +885,14 @@ static void __init arch_counter_register(unsigned type)
 	u64 start_count;
 
 	/* Register the CP15 based counter if we have one */
-	if (type & ARCH_CP15_TIMER) {
-		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_uses_ppi == VIRT_PPI)
+	if (type & ARCH_TIMER_TYPE_CP15) {
+		if (IS_ENABLED(CONFIG_ARM64) ||
+		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
 
-		clocksource_counter.archdata.vdso_direct = true;
-
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-		/*
-		 * Don't use the vdso fastpath if errata require using
-		 * the out-of-line counter accessor.
-		 */
-		if (static_branch_unlikely(&arch_timer_read_ool_enabled))
-			clocksource_counter.archdata.vdso_direct = false;
-#endif
+		clocksource_counter.archdata.vdso_direct = vdso_default;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 	}
@@ -699,12 +912,11 @@ static void __init arch_counter_register(unsigned type)
 
 static void arch_timer_stop(struct clock_event_device *clk)
 {
-	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
-		 clk->irq, smp_processor_id());
+	pr_debug("disable IRQ%d cpu #%d\n", clk->irq, smp_processor_id());
 
 	disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]);
 	if (arch_timer_has_nonsecure_ppi())
-		disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
+		disable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]);
 
 	clk->set_state_shutdown(clk);
 }
@@ -718,14 +930,14 @@ static int arch_timer_dying_cpu(unsigned int cpu)
 }
 
 #ifdef CONFIG_CPU_PM
-static unsigned int saved_cntkctl;
+static DEFINE_PER_CPU(unsigned long, saved_cntkctl);
 static int arch_timer_cpu_pm_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
 	if (action == CPU_PM_ENTER)
-		saved_cntkctl = arch_timer_get_cntkctl();
+		__this_cpu_write(saved_cntkctl, arch_timer_get_cntkctl());
 	else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT)
-		arch_timer_set_cntkctl(saved_cntkctl);
+		arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
 	return NOTIFY_OK;
 }
 
@@ -767,24 +979,24 @@ static int __init arch_timer_register(void)
 
 	ppi = arch_timer_ppi[arch_timer_uses_ppi];
 	switch (arch_timer_uses_ppi) {
-	case VIRT_PPI:
+	case ARCH_TIMER_VIRT_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_virt,
 					 "arch_timer", arch_timer_evt);
 		break;
-	case PHYS_SECURE_PPI:
-	case PHYS_NONSECURE_PPI:
+	case ARCH_TIMER_PHYS_SECURE_PPI:
+	case ARCH_TIMER_PHYS_NONSECURE_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_phys,
 					 "arch_timer", arch_timer_evt);
-		if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
-			ppi = arch_timer_ppi[PHYS_NONSECURE_PPI];
+		if (!err && arch_timer_has_nonsecure_ppi()) {
+			ppi = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI];
 			err = request_percpu_irq(ppi, arch_timer_handler_phys,
 						 "arch_timer", arch_timer_evt);
 			if (err)
-				free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+				free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_SECURE_PPI],
 						arch_timer_evt);
 		}
 		break;
-	case HYP_PPI:
+	case ARCH_TIMER_HYP_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_phys,
 					 "arch_timer", arch_timer_evt);
 		break;
@@ -793,8 +1005,7 @@ static int __init arch_timer_register(void)
 	}
 
 	if (err) {
-		pr_err("arch_timer: can't register interrupt %d (%d)\n",
-		       ppi, err);
+		pr_err("can't register interrupt %d (%d)\n", ppi, err);
 		goto out_free;
 	}
 
@@ -817,7 +1028,7 @@ out_unreg_cpupm:
 out_unreg_notify:
 	free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt);
 	if (arch_timer_has_nonsecure_ppi())
-		free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
+		free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI],
 				arch_timer_evt);
 
 out_free:
@@ -838,7 +1049,7 @@ static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq)
 
 	t->base = base;
 	t->evt.irq = irq;
-	__arch_timer_setup(ARCH_MEM_TIMER, &t->evt);
+	__arch_timer_setup(ARCH_TIMER_TYPE_MEM, &t->evt);
 
 	if (arch_timer_mem_use_virtual)
 		func = arch_timer_handler_virt_mem;
@@ -847,7 +1058,7 @@ static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq)
 
 	ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &t->evt);
 	if (ret) {
-		pr_err("arch_timer: Failed to request mem timer irq\n");
+		pr_err("Failed to request mem timer irq\n");
 		kfree(t);
 	}
 
@@ -865,15 +1076,28 @@ static const struct of_device_id arch_timer_mem_of_match[] __initconst = {
 	{},
 };
 
-static bool __init
-arch_timer_needs_probing(int type, const struct of_device_id *matches)
+static bool __init arch_timer_needs_of_probing(void)
 {
 	struct device_node *dn;
 	bool needs_probing = false;
+	unsigned int mask = ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM;
+
+	/* We have two timers, and both device-tree nodes are probed. */
+	if ((arch_timers_present & mask) == mask)
+		return false;
 
-	dn = of_find_matching_node(NULL, matches);
-	if (dn && of_device_is_available(dn) && !(arch_timers_present & type))
+	/*
+	 * Only one type of timer is probed,
+	 * check if we have another type of timer node in device-tree.
+	 */
+	if (arch_timers_present & ARCH_TIMER_TYPE_CP15)
+		dn = of_find_matching_node(NULL, arch_timer_mem_of_match);
+	else
+		dn = of_find_matching_node(NULL, arch_timer_of_match);
+
+	if (dn && of_device_is_available(dn))
 		needs_probing = true;
+
 	of_node_put(dn);
 
 	return needs_probing;
@@ -881,96 +1105,66 @@ arch_timer_needs_probing(int type, const struct of_device_id *matches)
 
 static int __init arch_timer_common_init(void)
 {
-	unsigned mask = ARCH_CP15_TIMER | ARCH_MEM_TIMER;
-
-	/* Wait until both nodes are probed if we have two timers */
-	if ((arch_timers_present & mask) != mask) {
-		if (arch_timer_needs_probing(ARCH_MEM_TIMER, arch_timer_mem_of_match))
-			return 0;
-		if (arch_timer_needs_probing(ARCH_CP15_TIMER, arch_timer_of_match))
-			return 0;
-	}
-
 	arch_timer_banner(arch_timers_present);
 	arch_counter_register(arch_timers_present);
 	return arch_timer_arch_init();
 }
 
-static int __init arch_timer_init(void)
+/**
+ * arch_timer_select_ppi() - Select suitable PPI for the current system.
+ *
+ * If HYP mode is available, we know that the physical timer
+ * has been configured to be accessible from PL1. Use it, so
+ * that a guest can use the virtual timer instead.
+ *
+ * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
+ * accesses to CNTP_*_EL1 registers are silently redirected to
+ * their CNTHP_*_EL2 counterparts, and use a different PPI
+ * number.
+ *
+ * If no interrupt provided for virtual timer, we'll have to
+ * stick to the physical timer. It'd better be accessible...
+ * For arm64 we never use the secure interrupt.
+ *
+ * Return: a suitable PPI type for the current system.
+ */
+static enum arch_timer_ppi_nr __init arch_timer_select_ppi(void)
 {
-	int ret;
-	/*
-	 * If HYP mode is available, we know that the physical timer
-	 * has been configured to be accessible from PL1. Use it, so
-	 * that a guest can use the virtual timer instead.
-	 *
-	 * If no interrupt provided for virtual timer, we'll have to
-	 * stick to the physical timer. It'd better be accessible...
-	 *
-	 * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
-	 * accesses to CNTP_*_EL1 registers are silently redirected to
-	 * their CNTHP_*_EL2 counterparts, and use a different PPI
-	 * number.
-	 */
-	if (is_hyp_mode_available() || !arch_timer_ppi[VIRT_PPI]) {
-		bool has_ppi;
-
-		if (is_kernel_in_hyp_mode()) {
-			arch_timer_uses_ppi = HYP_PPI;
-			has_ppi = !!arch_timer_ppi[HYP_PPI];
-		} else {
-			arch_timer_uses_ppi = PHYS_SECURE_PPI;
-			has_ppi = (!!arch_timer_ppi[PHYS_SECURE_PPI] ||
-				   !!arch_timer_ppi[PHYS_NONSECURE_PPI]);
-		}
-
-		if (!has_ppi) {
-			pr_warn("arch_timer: No interrupt available, giving up\n");
-			return -EINVAL;
-		}
-	}
+	if (is_kernel_in_hyp_mode())
+		return ARCH_TIMER_HYP_PPI;
 
-	ret = arch_timer_register();
-	if (ret)
-		return ret;
+	if (!is_hyp_mode_available() && arch_timer_ppi[ARCH_TIMER_VIRT_PPI])
+		return ARCH_TIMER_VIRT_PPI;
 
-	ret = arch_timer_common_init();
-	if (ret)
-		return ret;
+	if (IS_ENABLED(CONFIG_ARM64))
+		return ARCH_TIMER_PHYS_NONSECURE_PPI;
 
-	arch_timer_kvm_info.virtual_irq = arch_timer_ppi[VIRT_PPI];
-	
-	return 0;
+	return ARCH_TIMER_PHYS_SECURE_PPI;
 }
 
 static int __init arch_timer_of_init(struct device_node *np)
 {
-	int i;
+	int i, ret;
+	u32 rate;
 
-	if (arch_timers_present & ARCH_CP15_TIMER) {
-		pr_warn("arch_timer: multiple nodes in dt, skipping\n");
+	if (arch_timers_present & ARCH_TIMER_TYPE_CP15) {
+		pr_warn("multiple nodes in dt, skipping\n");
 		return 0;
 	}
 
-	arch_timers_present |= ARCH_CP15_TIMER;
-	for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
+	arch_timers_present |= ARCH_TIMER_TYPE_CP15;
+	for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++)
 		arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
 
-	arch_timer_detect_rate(NULL, np);
+	arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI];
+
+	rate = arch_timer_get_cntfrq();
+	arch_timer_of_configure_rate(rate, np);
 
 	arch_timer_c3stop = !of_property_read_bool(np, "always-on");
 
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-	for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) {
-		if (of_property_read_bool(np, ool_workarounds[i].id)) {
-			timer_unstable_counter_workaround = &ool_workarounds[i];
-			static_branch_enable(&arch_timer_read_ool_enabled);
-			pr_info("arch_timer: Enabling workaround for %s\n",
-				timer_unstable_counter_workaround->id);
-			break;
-		}
-	}
-#endif
+	/* Check for globally applicable workarounds */
+	arch_timer_check_ool_workaround(ate_match_dt, np);
 
 	/*
 	 * If we cannot rely on firmware initializing the timer registers then
@@ -978,29 +1172,63 @@ static int __init arch_timer_of_init(struct device_node *np)
 	 */
 	if (IS_ENABLED(CONFIG_ARM) &&
 	    of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
-		arch_timer_uses_ppi = PHYS_SECURE_PPI;
+		arch_timer_uses_ppi = ARCH_TIMER_PHYS_SECURE_PPI;
+	else
+		arch_timer_uses_ppi = arch_timer_select_ppi();
+
+	if (!arch_timer_ppi[arch_timer_uses_ppi]) {
+		pr_err("No interrupt available, giving up\n");
+		return -EINVAL;
+	}
 
 	/* On some systems, the counter stops ticking when in suspend. */
 	arch_counter_suspend_stop = of_property_read_bool(np,
 							 "arm,no-tick-in-suspend");
 
-	return arch_timer_init();
+	ret = arch_timer_register();
+	if (ret)
+		return ret;
+
+	if (arch_timer_needs_of_probing())
+		return 0;
+
+	return arch_timer_common_init();
 }
 CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init);
 CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init);
 
-static int __init arch_timer_mem_init(struct device_node *np)
+static u32 __init
+arch_timer_mem_frame_get_cntfrq(struct arch_timer_mem_frame *frame)
 {
-	struct device_node *frame, *best_frame = NULL;
-	void __iomem *cntctlbase, *base;
-	unsigned int irq, ret = -EINVAL;
+	void __iomem *base;
+	u32 rate;
+
+	base = ioremap(frame->cntbase, frame->size);
+	if (!base) {
+		pr_err("Unable to map frame @ %pa\n", &frame->cntbase);
+		return 0;
+	}
+
+	rate = readl_relaxed(frame + CNTFRQ);
+
+	iounmap(frame);
+
+	return rate;
+}
+
+static struct arch_timer_mem_frame * __init
+arch_timer_mem_find_best_frame(struct arch_timer_mem *timer_mem)
+{
+	struct arch_timer_mem_frame *frame, *best_frame = NULL;
+	void __iomem *cntctlbase;
 	u32 cnttidr;
+	int i;
 
-	arch_timers_present |= ARCH_MEM_TIMER;
-	cntctlbase = of_iomap(np, 0);
+	cntctlbase = ioremap(timer_mem->cntctlbase, timer_mem->size);
 	if (!cntctlbase) {
-		pr_err("arch_timer: Can't find CNTCTLBase\n");
-		return -ENXIO;
+		pr_err("Can't map CNTCTLBase @ %pa\n",
+			&timer_mem->cntctlbase);
+		return NULL;
 	}
 
 	cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
@@ -1009,25 +1237,20 @@ static int __init arch_timer_mem_init(struct device_node *np)
 	 * Try to find a virtual capable frame. Otherwise fall back to a
 	 * physical capable frame.
 	 */
-	for_each_available_child_of_node(np, frame) {
-		int n;
-		u32 cntacr;
+	for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) {
+		u32 cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
+			     CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
 
-		if (of_property_read_u32(frame, "frame-number", &n)) {
-			pr_err("arch_timer: Missing frame-number\n");
-			of_node_put(frame);
-			goto out;
-		}
+		frame = &timer_mem->frame[i];
+		if (!frame->valid)
+			continue;
 
 		/* Try enabling everything, and see what sticks */
-		cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
-			 CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
-		writel_relaxed(cntacr, cntctlbase + CNTACR(n));
-		cntacr = readl_relaxed(cntctlbase + CNTACR(n));
+		writel_relaxed(cntacr, cntctlbase + CNTACR(i));
+		cntacr = readl_relaxed(cntctlbase + CNTACR(i));
 
-		if ((cnttidr & CNTTIDR_VIRT(n)) &&
+		if ((cnttidr & CNTTIDR_VIRT(i)) &&
 		    !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) {
-			of_node_put(best_frame);
 			best_frame = frame;
 			arch_timer_mem_use_virtual = true;
 			break;
@@ -1036,99 +1259,262 @@ static int __init arch_timer_mem_init(struct device_node *np)
 		if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT))
 			continue;
 
-		of_node_put(best_frame);
-		best_frame = of_node_get(frame);
+		best_frame = frame;
 	}
 
-	ret= -ENXIO;
-	base = arch_counter_base = of_io_request_and_map(best_frame, 0,
-							 "arch_mem_timer");
-	if (IS_ERR(base)) {
-		pr_err("arch_timer: Can't map frame's registers\n");
-		goto out;
-	}
+	iounmap(cntctlbase);
+
+	if (!best_frame)
+		pr_err("Unable to find a suitable frame in timer @ %pa\n",
+			&timer_mem->cntctlbase);
+
+	return frame;
+}
+
+static int __init
+arch_timer_mem_frame_register(struct arch_timer_mem_frame *frame)
+{
+	void __iomem *base;
+	int ret, irq = 0;
 
 	if (arch_timer_mem_use_virtual)
-		irq = irq_of_parse_and_map(best_frame, 1);
+		irq = frame->virt_irq;
 	else
-		irq = irq_of_parse_and_map(best_frame, 0);
+		irq = frame->phys_irq;
 
-	ret = -EINVAL;
 	if (!irq) {
-		pr_err("arch_timer: Frame missing %s irq",
+		pr_err("Frame missing %s irq.\n",
 		       arch_timer_mem_use_virtual ? "virt" : "phys");
-		goto out;
+		return -EINVAL;
+	}
+
+	if (!request_mem_region(frame->cntbase, frame->size,
+				"arch_mem_timer"))
+		return -EBUSY;
+
+	base = ioremap(frame->cntbase, frame->size);
+	if (!base) {
+		pr_err("Can't map frame's registers\n");
+		return -ENXIO;
 	}
 
-	arch_timer_detect_rate(base, np);
 	ret = arch_timer_mem_register(base, irq);
-	if (ret)
+	if (ret) {
+		iounmap(base);
+		return ret;
+	}
+
+	arch_counter_base = base;
+	arch_timers_present |= ARCH_TIMER_TYPE_MEM;
+
+	return 0;
+}
+
+static int __init arch_timer_mem_of_init(struct device_node *np)
+{
+	struct arch_timer_mem *timer_mem;
+	struct arch_timer_mem_frame *frame;
+	struct device_node *frame_node;
+	struct resource res;
+	int ret = -EINVAL;
+	u32 rate;
+
+	timer_mem = kzalloc(sizeof(*timer_mem), GFP_KERNEL);
+	if (!timer_mem)
+		return -ENOMEM;
+
+	if (of_address_to_resource(np, 0, &res))
 		goto out;
+	timer_mem->cntctlbase = res.start;
+	timer_mem->size = resource_size(&res);
 
-	return arch_timer_common_init();
+	for_each_available_child_of_node(np, frame_node) {
+		u32 n;
+		struct arch_timer_mem_frame *frame;
+
+		if (of_property_read_u32(frame_node, "frame-number", &n)) {
+			pr_err(FW_BUG "Missing frame-number.\n");
+			of_node_put(frame_node);
+			goto out;
+		}
+		if (n >= ARCH_TIMER_MEM_MAX_FRAMES) {
+			pr_err(FW_BUG "Wrong frame-number, only 0-%u are permitted.\n",
+			       ARCH_TIMER_MEM_MAX_FRAMES - 1);
+			of_node_put(frame_node);
+			goto out;
+		}
+		frame = &timer_mem->frame[n];
+
+		if (frame->valid) {
+			pr_err(FW_BUG "Duplicated frame-number.\n");
+			of_node_put(frame_node);
+			goto out;
+		}
+
+		if (of_address_to_resource(frame_node, 0, &res)) {
+			of_node_put(frame_node);
+			goto out;
+		}
+		frame->cntbase = res.start;
+		frame->size = resource_size(&res);
+
+		frame->virt_irq = irq_of_parse_and_map(frame_node,
+						       ARCH_TIMER_VIRT_SPI);
+		frame->phys_irq = irq_of_parse_and_map(frame_node,
+						       ARCH_TIMER_PHYS_SPI);
+
+		frame->valid = true;
+	}
+
+	frame = arch_timer_mem_find_best_frame(timer_mem);
+	if (!frame) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	rate = arch_timer_mem_frame_get_cntfrq(frame);
+	arch_timer_of_configure_rate(rate, np);
+
+	ret = arch_timer_mem_frame_register(frame);
+	if (!ret && !arch_timer_needs_of_probing())
+		ret = arch_timer_common_init();
 out:
-	iounmap(cntctlbase);
-	of_node_put(best_frame);
+	kfree(timer_mem);
 	return ret;
 }
 CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
-		       arch_timer_mem_init);
+		       arch_timer_mem_of_init);
 
-#ifdef CONFIG_ACPI
-static int __init map_generic_timer_interrupt(u32 interrupt, u32 flags)
+#ifdef CONFIG_ACPI_GTDT
+static int __init
+arch_timer_mem_verify_cntfrq(struct arch_timer_mem *timer_mem)
 {
-	int trigger, polarity;
+	struct arch_timer_mem_frame *frame;
+	u32 rate;
+	int i;
 
-	if (!interrupt)
-		return 0;
+	for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) {
+		frame = &timer_mem->frame[i];
 
-	trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE
-			: ACPI_LEVEL_SENSITIVE;
+		if (!frame->valid)
+			continue;
+
+		rate = arch_timer_mem_frame_get_cntfrq(frame);
+		if (rate == arch_timer_rate)
+			continue;
+
+		pr_err(FW_BUG "CNTFRQ mismatch: frame @ %pa: (0x%08lx), CPU: (0x%08lx)\n",
+			&frame->cntbase,
+			(unsigned long)rate, (unsigned long)arch_timer_rate);
 
-	polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW
-			: ACPI_ACTIVE_HIGH;
+		return -EINVAL;
+	}
 
-	return acpi_register_gsi(NULL, interrupt, trigger, polarity);
+	return 0;
 }
 
-/* Initialize per-processor generic timer */
+static int __init arch_timer_mem_acpi_init(int platform_timer_count)
+{
+	struct arch_timer_mem *timers, *timer;
+	struct arch_timer_mem_frame *frame;
+	int timer_count, i, ret = 0;
+
+	timers = kcalloc(platform_timer_count, sizeof(*timers),
+			    GFP_KERNEL);
+	if (!timers)
+		return -ENOMEM;
+
+	ret = acpi_arch_timer_mem_init(timers, &timer_count);
+	if (ret || !timer_count)
+		goto out;
+
+	for (i = 0; i < timer_count; i++) {
+		ret = arch_timer_mem_verify_cntfrq(&timers[i]);
+		if (ret) {
+			pr_err("Disabling MMIO timers due to CNTFRQ mismatch\n");
+			goto out;
+		}
+	}
+
+	/*
+	 * While unlikely, it's theoretically possible that none of the frames
+	 * in a timer expose the combination of feature we want.
+	 */
+	for (i = i; i < timer_count; i++) {
+		timer = &timers[i];
+
+		frame = arch_timer_mem_find_best_frame(timer);
+		if (frame)
+			break;
+	}
+
+	if (frame)
+		ret = arch_timer_mem_frame_register(frame);
+out:
+	kfree(timers);
+	return ret;
+}
+
+/* Initialize per-processor generic timer and memory-mapped timer(if present) */
 static int __init arch_timer_acpi_init(struct acpi_table_header *table)
 {
-	struct acpi_table_gtdt *gtdt;
+	int ret, platform_timer_count;
 
-	if (arch_timers_present & ARCH_CP15_TIMER) {
-		pr_warn("arch_timer: already initialized, skipping\n");
+	if (arch_timers_present & ARCH_TIMER_TYPE_CP15) {
+		pr_warn("already initialized, skipping\n");
 		return -EINVAL;
 	}
 
-	gtdt = container_of(table, struct acpi_table_gtdt, header);
+	arch_timers_present |= ARCH_TIMER_TYPE_CP15;
+
+	ret = acpi_gtdt_init(table, &platform_timer_count);
+	if (ret) {
+		pr_err("Failed to init GTDT table.\n");
+		return ret;
+	}
 
-	arch_timers_present |= ARCH_CP15_TIMER;
+	arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI] =
+		acpi_gtdt_map_ppi(ARCH_TIMER_PHYS_NONSECURE_PPI);
 
-	arch_timer_ppi[PHYS_SECURE_PPI] =
-		map_generic_timer_interrupt(gtdt->secure_el1_interrupt,
-		gtdt->secure_el1_flags);
+	arch_timer_ppi[ARCH_TIMER_VIRT_PPI] =
+		acpi_gtdt_map_ppi(ARCH_TIMER_VIRT_PPI);
 
-	arch_timer_ppi[PHYS_NONSECURE_PPI] =
-		map_generic_timer_interrupt(gtdt->non_secure_el1_interrupt,
-		gtdt->non_secure_el1_flags);
+	arch_timer_ppi[ARCH_TIMER_HYP_PPI] =
+		acpi_gtdt_map_ppi(ARCH_TIMER_HYP_PPI);
 
-	arch_timer_ppi[VIRT_PPI] =
-		map_generic_timer_interrupt(gtdt->virtual_timer_interrupt,
-		gtdt->virtual_timer_flags);
+	arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI];
 
-	arch_timer_ppi[HYP_PPI] =
-		map_generic_timer_interrupt(gtdt->non_secure_el2_interrupt,
-		gtdt->non_secure_el2_flags);
+	/*
+	 * When probing via ACPI, we have no mechanism to override the sysreg
+	 * CNTFRQ value. This *must* be correct.
+	 */
+	arch_timer_rate = arch_timer_get_cntfrq();
+	if (!arch_timer_rate) {
+		pr_err(FW_BUG "frequency not available.\n");
+		return -EINVAL;
+	}
 
-	/* Get the frequency from CNTFRQ */
-	arch_timer_detect_rate(NULL, NULL);
+	arch_timer_uses_ppi = arch_timer_select_ppi();
+	if (!arch_timer_ppi[arch_timer_uses_ppi]) {
+		pr_err("No interrupt available, giving up\n");
+		return -EINVAL;
+	}
 
 	/* Always-on capability */
-	arch_timer_c3stop = !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON);
+	arch_timer_c3stop = acpi_gtdt_c3stop(arch_timer_uses_ppi);
 
-	arch_timer_init();
-	return 0;
+	/* Check for globally applicable workarounds */
+	arch_timer_check_ool_workaround(ate_match_acpi_oem_info, table);
+
+	ret = arch_timer_register();
+	if (ret)
+		return ret;
+
+	if (platform_timer_count &&
+	    arch_timer_mem_acpi_init(platform_timer_count))
+		pr_err("Failed to initialize memory-mapped timer.\n");
+
+	return arch_timer_common_init();
 }
 CLOCKSOURCE_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init);
 #endif
diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c
index 1ba871b7fe11..c6780830b8ac 100644
--- a/drivers/clocksource/asm9260_timer.c
+++ b/drivers/clocksource/asm9260_timer.c
@@ -193,7 +193,7 @@ static int __init asm9260_timer_init(struct device_node *np)
 
 	priv.base = of_io_request_and_map(np, 0, np->name);
 	if (IS_ERR(priv.base)) {
-		pr_err("%s: unable to map resource", np->name);
+		pr_err("%s: unable to map resource\n", np->name);
 		return PTR_ERR(priv.base);
 	}
 
diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index f2f29d2be1cf..dce44307469e 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/drivers/clocksource/bcm2835_timer.c
@@ -89,13 +89,13 @@ static int __init bcm2835_timer_init(struct device_node *node)
 
 	base = of_iomap(node, 0);
 	if (!base) {
-		pr_err("Can't remap registers");
+		pr_err("Can't remap registers\n");
 		return -ENXIO;
 	}
 
 	ret = of_property_read_u32(node, "clock-frequency", &freq);
 	if (ret) {
-		pr_err("Can't read clock-frequency");
+		pr_err("Can't read clock-frequency\n");
 		goto err_iounmap;
 	}
 
@@ -107,7 +107,7 @@ static int __init bcm2835_timer_init(struct device_node *node)
 
 	irq = irq_of_parse_and_map(node, DEFAULT_TIMER);
 	if (irq <= 0) {
-		pr_err("Can't parse IRQ");
+		pr_err("Can't parse IRQ\n");
 		ret = -EINVAL;
 		goto err_iounmap;
 	}
diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c
index 92f6e4deee74..fda5e1476638 100644
--- a/drivers/clocksource/bcm_kona_timer.c
+++ b/drivers/clocksource/bcm_kona_timer.c
@@ -179,7 +179,7 @@ static int __init kona_timer_init(struct device_node *node)
 	} else if (!of_property_read_u32(node, "clock-frequency", &freq)) {
 		arch_timer_rate = freq;
 	} else {
-		pr_err("Kona Timer v1 unable to determine clock-frequency");
+		pr_err("Kona Timer v1 unable to determine clock-frequency\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/clocksource/clkevt-probe.c b/drivers/clocksource/clkevt-probe.c
index 8c30fec86094..eb89b502acbd 100644
--- a/drivers/clocksource/clkevt-probe.c
+++ b/drivers/clocksource/clkevt-probe.c
@@ -17,7 +17,7 @@
 
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/clockchip.h>
+#include <linux/clockchips.h>
 
 extern struct of_device_id __clkevt_of_table[];
 
diff --git a/drivers/clocksource/clksrc-probe.c b/drivers/clocksource/clksrc-probe.c
index bc62be97f0a8..ac701ffb8d59 100644
--- a/drivers/clocksource/clksrc-probe.c
+++ b/drivers/clocksource/clksrc-probe.c
@@ -40,7 +40,7 @@ void __init clocksource_probe(void)
 
 		ret = init_func_ret(np);
 		if (ret) {
-			pr_err("Failed to initialize '%s': %d",
+			pr_err("Failed to initialize '%s': %d\n",
 			       of_node_full_name(np), ret);
 			continue;
 		}
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index 63e4f5519577..1f5f734e4919 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -101,7 +101,7 @@ static irqreturn_t dw_apb_clockevent_irq(int irq, void *data)
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
 
 	if (!evt->event_handler) {
-		pr_info("Spurious APBT timer interrupt %d", irq);
+		pr_info("Spurious APBT timer interrupt %d\n", irq);
 		return IRQ_NONE;
 	}
 
@@ -257,7 +257,9 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating,
 	clockevents_calc_mult_shift(&dw_ced->ced, freq, APBT_MIN_PERIOD);
 	dw_ced->ced.max_delta_ns = clockevent_delta2ns(0x7fffffff,
 						       &dw_ced->ced);
+	dw_ced->ced.max_delta_ticks = 0x7fffffff;
 	dw_ced->ced.min_delta_ns = clockevent_delta2ns(5000, &dw_ced->ced);
+	dw_ced->ced.min_delta_ticks = 5000;
 	dw_ced->ced.cpumask = cpumask_of(cpu);
 	dw_ced->ced.features = CLOCK_EVT_FEAT_PERIODIC |
 				CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_DYNIRQ;
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index aff87df07449..bc48cbf6a795 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -78,15 +78,12 @@ static int em_sti_enable(struct em_sti_priv *p)
 	int ret;
 
 	/* enable clock */
-	ret = clk_prepare_enable(p->clk);
+	ret = clk_enable(p->clk);
 	if (ret) {
 		dev_err(&p->pdev->dev, "cannot enable clock\n");
 		return ret;
 	}
 
-	/* configure channel, periodic mode and maximum timeout */
-	p->rate = clk_get_rate(p->clk);
-
 	/* reset the counter */
 	em_sti_write(p, STI_SET_H, 0x40000000);
 	em_sti_write(p, STI_SET_L, 0x00000000);
@@ -107,7 +104,7 @@ static void em_sti_disable(struct em_sti_priv *p)
 	em_sti_write(p, STI_INTENCLR, 3);
 
 	/* stop clock */
-	clk_disable_unprepare(p->clk);
+	clk_disable(p->clk);
 }
 
 static u64 em_sti_count(struct em_sti_priv *p)
@@ -205,13 +202,9 @@ static u64 em_sti_clocksource_read(struct clocksource *cs)
 
 static int em_sti_clocksource_enable(struct clocksource *cs)
 {
-	int ret;
 	struct em_sti_priv *p = cs_to_em_sti(cs);
 
-	ret = em_sti_start(p, USER_CLOCKSOURCE);
-	if (!ret)
-		__clocksource_update_freq_hz(cs, p->rate);
-	return ret;
+	return em_sti_start(p, USER_CLOCKSOURCE);
 }
 
 static void em_sti_clocksource_disable(struct clocksource *cs)
@@ -240,8 +233,7 @@ static int em_sti_register_clocksource(struct em_sti_priv *p)
 
 	dev_info(&p->pdev->dev, "used as clock source\n");
 
-	/* Register with dummy 1 Hz value, gets updated in ->enable() */
-	clocksource_register_hz(cs, 1);
+	clocksource_register_hz(cs, p->rate);
 	return 0;
 }
 
@@ -263,7 +255,6 @@ static int em_sti_clock_event_set_oneshot(struct clock_event_device *ced)
 
 	dev_info(&p->pdev->dev, "used for oneshot clock events\n");
 	em_sti_start(p, USER_CLOCKEVENT);
-	clockevents_config(&p->ced, p->rate);
 	return 0;
 }
 
@@ -294,8 +285,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
 
 	dev_info(&p->pdev->dev, "used for clock events\n");
 
-	/* Register with dummy 1 Hz value, gets updated in ->set_state_oneshot() */
-	clockevents_config_and_register(ced, 1, 2, 0xffffffff);
+	clockevents_config_and_register(ced, p->rate, 2, 0xffffffff);
 }
 
 static int em_sti_probe(struct platform_device *pdev)
@@ -303,6 +293,7 @@ static int em_sti_probe(struct platform_device *pdev)
 	struct em_sti_priv *p;
 	struct resource *res;
 	int irq;
+	int ret;
 
 	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
 	if (p == NULL)
@@ -323,6 +314,13 @@ static int em_sti_probe(struct platform_device *pdev)
 	if (IS_ERR(p->base))
 		return PTR_ERR(p->base);
 
+	if (devm_request_irq(&pdev->dev, irq, em_sti_interrupt,
+			     IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
+			     dev_name(&pdev->dev), p)) {
+		dev_err(&pdev->dev, "failed to request low IRQ\n");
+		return -ENOENT;
+	}
+
 	/* get hold of clock */
 	p->clk = devm_clk_get(&pdev->dev, "sclk");
 	if (IS_ERR(p->clk)) {
@@ -330,12 +328,20 @@ static int em_sti_probe(struct platform_device *pdev)
 		return PTR_ERR(p->clk);
 	}
 
-	if (devm_request_irq(&pdev->dev, irq, em_sti_interrupt,
-			     IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
-			     dev_name(&pdev->dev), p)) {
-		dev_err(&pdev->dev, "failed to request low IRQ\n");
-		return -ENOENT;
+	ret = clk_prepare(p->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "cannot prepare clock\n");
+		return ret;
+	}
+
+	ret = clk_enable(p->clk);
+	if (ret < 0) {
+		dev_err(&p->pdev->dev, "cannot enable clock\n");
+		clk_unprepare(p->clk);
+		return ret;
 	}
+	p->rate = clk_get_rate(p->clk);
+	clk_disable(p->clk);
 
 	raw_spin_lock_init(&p->lock);
 	em_sti_register_clockevent(p);
diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c
index 546bb180f5a4..804c489531d6 100644
--- a/drivers/clocksource/h8300_timer8.c
+++ b/drivers/clocksource/h8300_timer8.c
@@ -101,15 +101,7 @@ static inline struct timer8_priv *ced_to_priv(struct clock_event_device *ced)
 
 static void timer8_clock_event_start(struct timer8_priv *p, unsigned long delta)
 {
-	struct clock_event_device *ced = &p->ced;
-
 	timer8_start(p);
-
-	ced->shift = 32;
-	ced->mult = div_sc(p->rate, NSEC_PER_SEC, ced->shift);
-	ced->max_delta_ns = clockevent_delta2ns(0xffff, ced);
-	ced->min_delta_ns = clockevent_delta2ns(0x0001, ced);
-
 	timer8_set_next(p, delta);
 }
 
diff --git a/drivers/clocksource/meson6_timer.c b/drivers/clocksource/meson6_timer.c
index 52af591a9fc7..39d21f693a33 100644
--- a/drivers/clocksource/meson6_timer.c
+++ b/drivers/clocksource/meson6_timer.c
@@ -133,13 +133,13 @@ static int __init meson6_timer_init(struct device_node *node)
 
 	timer_base = of_io_request_and_map(node, 0, "meson6-timer");
 	if (IS_ERR(timer_base)) {
-		pr_err("Can't map registers");
+		pr_err("Can't map registers\n");
 		return -ENXIO;
 	}
 
 	irq = irq_of_parse_and_map(node, 0);
 	if (irq <= 0) {
-		pr_err("Can't parse IRQ");
+		pr_err("Can't parse IRQ\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index 6fcf96540631..3e5fa2f62d5f 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -114,7 +114,9 @@ static int arch_timer_starting_cpu(unsigned int cpu)
 
 	clk->mult = div_sc(hwtimer_freq, NSEC_PER_SEC, clk->shift);
 	clk->max_delta_ns = clockevent_delta2ns(0x7fffffff, clk);
+	clk->max_delta_ticks = 0x7fffffff;
 	clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
+	clk->min_delta_ticks = 0xf;
 	clk->cpumask = cpumask_of(cpu);
 
 	clockevents_register_device(clk);
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index d9ef7a61e093..3f52ee219923 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -154,19 +154,6 @@ static int __init __gic_clocksource_init(void)
 	return ret;
 }
 
-void __init gic_clocksource_init(unsigned int frequency)
-{
-	gic_frequency = frequency;
-	gic_timer_irq = MIPS_GIC_IRQ_BASE +
-		GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_COMPARE);
-
-	__gic_clocksource_init();
-	gic_clockevent_init();
-
-	/* And finally start the counter */
-	gic_start_count();
-}
-
 static int __init gic_clocksource_of_init(struct device_node *node)
 {
 	struct clk *clk;
@@ -174,7 +161,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
 
 	if (!gic_present || !node->parent ||
 	    !of_device_is_compatible(node->parent, "mti,gic")) {
-		pr_warn("No DT definition for the mips gic driver");
+		pr_warn("No DT definition for the mips gic driver\n");
 		return -ENXIO;
 	}
 
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
index 3c124d1ca600..7d44de304f37 100644
--- a/drivers/clocksource/nomadik-mtu.c
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -260,25 +260,25 @@ static int __init nmdk_timer_of_init(struct device_node *node)
 
 	base = of_iomap(node, 0);
 	if (!base) {
-		pr_err("Can't remap registers");
+		pr_err("Can't remap registers\n");
 		return -ENXIO;
 	}
 
 	pclk = of_clk_get_by_name(node, "apb_pclk");
 	if (IS_ERR(pclk)) {
-		pr_err("could not get apb_pclk");
+		pr_err("could not get apb_pclk\n");
 		return PTR_ERR(pclk);
 	}
 
 	clk = of_clk_get_by_name(node, "timclk");
 	if (IS_ERR(clk)) {
-		pr_err("could not get timclk");
+		pr_err("could not get timclk\n");
 		return PTR_ERR(clk);
 	}
 
 	irq = irq_of_parse_and_map(node, 0);
 	if (irq <= 0) {
-		pr_err("Can't parse IRQ");
+		pr_err("Can't parse IRQ\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c
index 4e0f11fd2617..6a20dc8b253f 100644
--- a/drivers/clocksource/numachip.c
+++ b/drivers/clocksource/numachip.c
@@ -51,7 +51,9 @@ static struct clock_event_device numachip2_clockevent = {
 	.mult            = 1,
 	.shift           = 0,
 	.min_delta_ns    = 1250,
+	.min_delta_ticks = 1250,
 	.max_delta_ns    = LONG_MAX,
+	.max_delta_ticks = LONG_MAX,
 };
 
 static void numachip_timer_interrupt(void)
diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c
index 1c24de215c14..a10fa667325f 100644
--- a/drivers/clocksource/pxa_timer.c
+++ b/drivers/clocksource/pxa_timer.c
@@ -166,14 +166,14 @@ static int __init pxa_timer_common_init(int irq, unsigned long clock_tick_rate)
 
 	ret = setup_irq(irq, &pxa_ost0_irq);
 	if (ret) {
-		pr_err("Failed to setup irq");
+		pr_err("Failed to setup irq\n");
 		return ret;
 	}
 
 	ret = clocksource_mmio_init(timer_base + OSCR, "oscr0", clock_tick_rate, 200,
 				    32, clocksource_mmio_readl_up);
 	if (ret) {
-		pr_err("Failed to init clocksource");
+		pr_err("Failed to init clocksource\n");
 		return ret;
 	}
 
@@ -203,7 +203,7 @@ static int __init pxa_timer_dt_init(struct device_node *np)
 
 	ret = clk_prepare_enable(clk);
 	if (ret) {
-		pr_crit("Failed to prepare clock");
+		pr_crit("Failed to prepare clock\n");
 		return ret;
 	}
 
diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c
index 23e267acba25..49c02be50eca 100644
--- a/drivers/clocksource/rockchip_timer.c
+++ b/drivers/clocksource/rockchip_timer.c
@@ -11,6 +11,8 @@
 #include <linux/clockchips.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -19,6 +21,8 @@
 
 #define TIMER_LOAD_COUNT0	0x00
 #define TIMER_LOAD_COUNT1	0x04
+#define TIMER_CURRENT_VALUE0	0x08
+#define TIMER_CURRENT_VALUE1	0x0C
 #define TIMER_CONTROL_REG3288	0x10
 #define TIMER_CONTROL_REG3399	0x1c
 #define TIMER_INT_STATUS	0x18
@@ -29,103 +33,118 @@
 #define TIMER_MODE_USER_DEFINED_COUNT		(1 << 1)
 #define TIMER_INT_UNMASK			(1 << 2)
 
-struct bc_timer {
-	struct clock_event_device ce;
+struct rk_timer {
 	void __iomem *base;
 	void __iomem *ctrl;
+	struct clk *clk;
+	struct clk *pclk;
 	u32 freq;
+	int irq;
 };
 
-static struct bc_timer bc_timer;
-
-static inline struct bc_timer *rk_timer(struct clock_event_device *ce)
-{
-	return container_of(ce, struct bc_timer, ce);
-}
+struct rk_clkevt {
+	struct clock_event_device ce;
+	struct rk_timer timer;
+};
 
-static inline void __iomem *rk_base(struct clock_event_device *ce)
-{
-	return rk_timer(ce)->base;
-}
+static struct rk_clkevt *rk_clkevt;
+static struct rk_timer *rk_clksrc;
 
-static inline void __iomem *rk_ctrl(struct clock_event_device *ce)
+static inline struct rk_timer *rk_timer(struct clock_event_device *ce)
 {
-	return rk_timer(ce)->ctrl;
+	return &container_of(ce, struct rk_clkevt, ce)->timer;
 }
 
-static inline void rk_timer_disable(struct clock_event_device *ce)
+static inline void rk_timer_disable(struct rk_timer *timer)
 {
-	writel_relaxed(TIMER_DISABLE, rk_ctrl(ce));
+	writel_relaxed(TIMER_DISABLE, timer->ctrl);
 }
 
-static inline void rk_timer_enable(struct clock_event_device *ce, u32 flags)
+static inline void rk_timer_enable(struct rk_timer *timer, u32 flags)
 {
-	writel_relaxed(TIMER_ENABLE | TIMER_INT_UNMASK | flags,
-		       rk_ctrl(ce));
+	writel_relaxed(TIMER_ENABLE | flags, timer->ctrl);
 }
 
 static void rk_timer_update_counter(unsigned long cycles,
-				    struct clock_event_device *ce)
+				    struct rk_timer *timer)
 {
-	writel_relaxed(cycles, rk_base(ce) + TIMER_LOAD_COUNT0);
-	writel_relaxed(0, rk_base(ce) + TIMER_LOAD_COUNT1);
+	writel_relaxed(cycles, timer->base + TIMER_LOAD_COUNT0);
+	writel_relaxed(0, timer->base + TIMER_LOAD_COUNT1);
 }
 
-static void rk_timer_interrupt_clear(struct clock_event_device *ce)
+static void rk_timer_interrupt_clear(struct rk_timer *timer)
 {
-	writel_relaxed(1, rk_base(ce) + TIMER_INT_STATUS);
+	writel_relaxed(1, timer->base + TIMER_INT_STATUS);
 }
 
 static inline int rk_timer_set_next_event(unsigned long cycles,
 					  struct clock_event_device *ce)
 {
-	rk_timer_disable(ce);
-	rk_timer_update_counter(cycles, ce);
-	rk_timer_enable(ce, TIMER_MODE_USER_DEFINED_COUNT);
+	struct rk_timer *timer = rk_timer(ce);
+
+	rk_timer_disable(timer);
+	rk_timer_update_counter(cycles, timer);
+	rk_timer_enable(timer, TIMER_MODE_USER_DEFINED_COUNT |
+			       TIMER_INT_UNMASK);
 	return 0;
 }
 
 static int rk_timer_shutdown(struct clock_event_device *ce)
 {
-	rk_timer_disable(ce);
+	struct rk_timer *timer = rk_timer(ce);
+
+	rk_timer_disable(timer);
 	return 0;
 }
 
 static int rk_timer_set_periodic(struct clock_event_device *ce)
 {
-	rk_timer_disable(ce);
-	rk_timer_update_counter(rk_timer(ce)->freq / HZ - 1, ce);
-	rk_timer_enable(ce, TIMER_MODE_FREE_RUNNING);
+	struct rk_timer *timer = rk_timer(ce);
+
+	rk_timer_disable(timer);
+	rk_timer_update_counter(timer->freq / HZ - 1, timer);
+	rk_timer_enable(timer, TIMER_MODE_FREE_RUNNING | TIMER_INT_UNMASK);
 	return 0;
 }
 
 static irqreturn_t rk_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *ce = dev_id;
+	struct rk_timer *timer = rk_timer(ce);
 
-	rk_timer_interrupt_clear(ce);
+	rk_timer_interrupt_clear(timer);
 
 	if (clockevent_state_oneshot(ce))
-		rk_timer_disable(ce);
+		rk_timer_disable(timer);
 
 	ce->event_handler(ce);
 
 	return IRQ_HANDLED;
 }
 
-static int __init rk_timer_init(struct device_node *np, u32 ctrl_reg)
+static u64 notrace rk_timer_sched_read(void)
+{
+	return ~readl_relaxed(rk_clksrc->base + TIMER_CURRENT_VALUE0);
+}
+
+static int __init
+rk_timer_probe(struct rk_timer *timer, struct device_node *np)
 {
-	struct clock_event_device *ce = &bc_timer.ce;
 	struct clk *timer_clk;
 	struct clk *pclk;
 	int ret = -EINVAL, irq;
+	u32 ctrl_reg = TIMER_CONTROL_REG3288;
 
-	bc_timer.base = of_iomap(np, 0);
-	if (!bc_timer.base) {
+	timer->base = of_iomap(np, 0);
+	if (!timer->base) {
 		pr_err("Failed to get base address for '%s'\n", TIMER_NAME);
 		return -ENXIO;
 	}
-	bc_timer.ctrl = bc_timer.base + ctrl_reg;
+
+	if (of_device_is_compatible(np, "rockchip,rk3399-timer"))
+		ctrl_reg = TIMER_CONTROL_REG3399;
+
+	timer->ctrl = timer->base + ctrl_reg;
 
 	pclk = of_clk_get_by_name(np, "pclk");
 	if (IS_ERR(pclk)) {
@@ -139,6 +158,7 @@ static int __init rk_timer_init(struct device_node *np, u32 ctrl_reg)
 		pr_err("Failed to enable pclk for '%s'\n", TIMER_NAME);
 		goto out_unmap;
 	}
+	timer->pclk = pclk;
 
 	timer_clk = of_clk_get_by_name(np, "timer");
 	if (IS_ERR(timer_clk)) {
@@ -152,8 +172,9 @@ static int __init rk_timer_init(struct device_node *np, u32 ctrl_reg)
 		pr_err("Failed to enable timer clock\n");
 		goto out_timer_clk;
 	}
+	timer->clk = timer_clk;
 
-	bc_timer.freq = clk_get_rate(timer_clk);
+	timer->freq = clk_get_rate(timer_clk);
 
 	irq = irq_of_parse_and_map(np, 0);
 	if (!irq) {
@@ -161,51 +182,126 @@ static int __init rk_timer_init(struct device_node *np, u32 ctrl_reg)
 		pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME);
 		goto out_irq;
 	}
+	timer->irq = irq;
+
+	rk_timer_interrupt_clear(timer);
+	rk_timer_disable(timer);
+	return 0;
+
+out_irq:
+	clk_disable_unprepare(timer_clk);
+out_timer_clk:
+	clk_disable_unprepare(pclk);
+out_unmap:
+	iounmap(timer->base);
+
+	return ret;
+}
+
+static void __init rk_timer_cleanup(struct rk_timer *timer)
+{
+	clk_disable_unprepare(timer->clk);
+	clk_disable_unprepare(timer->pclk);
+	iounmap(timer->base);
+}
+
+static int __init rk_clkevt_init(struct device_node *np)
+{
+	struct clock_event_device *ce;
+	int ret = -EINVAL;
+
+	rk_clkevt = kzalloc(sizeof(struct rk_clkevt), GFP_KERNEL);
+	if (!rk_clkevt) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
+	ret = rk_timer_probe(&rk_clkevt->timer, np);
+	if (ret)
+		goto out_probe;
+
+	ce = &rk_clkevt->ce;
 	ce->name = TIMER_NAME;
 	ce->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
 		       CLOCK_EVT_FEAT_DYNIRQ;
 	ce->set_next_event = rk_timer_set_next_event;
 	ce->set_state_shutdown = rk_timer_shutdown;
 	ce->set_state_periodic = rk_timer_set_periodic;
-	ce->irq = irq;
+	ce->irq = rk_clkevt->timer.irq;
 	ce->cpumask = cpu_possible_mask;
 	ce->rating = 250;
 
-	rk_timer_interrupt_clear(ce);
-	rk_timer_disable(ce);
-
-	ret = request_irq(irq, rk_timer_interrupt, IRQF_TIMER, TIMER_NAME, ce);
+	ret = request_irq(rk_clkevt->timer.irq, rk_timer_interrupt, IRQF_TIMER,
+			  TIMER_NAME, ce);
 	if (ret) {
-		pr_err("Failed to initialize '%s': %d\n", TIMER_NAME, ret);
+		pr_err("Failed to initialize '%s': %d\n",
+			TIMER_NAME, ret);
 		goto out_irq;
 	}
 
-	clockevents_config_and_register(ce, bc_timer.freq, 1, UINT_MAX);
-
+	clockevents_config_and_register(&rk_clkevt->ce,
+					rk_clkevt->timer.freq, 1, UINT_MAX);
 	return 0;
 
 out_irq:
-	clk_disable_unprepare(timer_clk);
-out_timer_clk:
-	clk_disable_unprepare(pclk);
-out_unmap:
-	iounmap(bc_timer.base);
-
+	rk_timer_cleanup(&rk_clkevt->timer);
+out_probe:
+	kfree(rk_clkevt);
+out:
+	/* Leave rk_clkevt not NULL to prevent future init */
+	rk_clkevt = ERR_PTR(ret);
 	return ret;
 }
 
-static int __init rk3288_timer_init(struct device_node *np)
+static int __init rk_clksrc_init(struct device_node *np)
 {
-	return rk_timer_init(np, TIMER_CONTROL_REG3288);
+	int ret = -EINVAL;
+
+	rk_clksrc = kzalloc(sizeof(struct rk_timer), GFP_KERNEL);
+	if (!rk_clksrc) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = rk_timer_probe(rk_clksrc, np);
+	if (ret)
+		goto out_probe;
+
+	rk_timer_update_counter(UINT_MAX, rk_clksrc);
+	rk_timer_enable(rk_clksrc, 0);
+
+	ret = clocksource_mmio_init(rk_clksrc->base + TIMER_CURRENT_VALUE0,
+		TIMER_NAME, rk_clksrc->freq, 250, 32,
+		clocksource_mmio_readl_down);
+	if (ret) {
+		pr_err("Failed to register clocksource");
+		goto out_clocksource;
+	}
+
+	sched_clock_register(rk_timer_sched_read, 32, rk_clksrc->freq);
+	return 0;
+
+out_clocksource:
+	rk_timer_cleanup(rk_clksrc);
+out_probe:
+	kfree(rk_clksrc);
+out:
+	/* Leave rk_clksrc not NULL to prevent future init */
+	rk_clksrc = ERR_PTR(ret);
+	return ret;
 }
 
-static int __init rk3399_timer_init(struct device_node *np)
+static int __init rk_timer_init(struct device_node *np)
 {
-	return rk_timer_init(np, TIMER_CONTROL_REG3399);
+	if (!rk_clkevt)
+		return rk_clkevt_init(np);
+
+	if (!rk_clksrc)
+		return rk_clksrc_init(np);
+
+	pr_err("Too many timer definitions for '%s'\n", TIMER_NAME);
+	return -EINVAL;
 }
 
-CLOCKSOURCE_OF_DECLARE(rk3288_timer, "rockchip,rk3288-timer",
-		       rk3288_timer_init);
-CLOCKSOURCE_OF_DECLARE(rk3399_timer, "rockchip,rk3399-timer",
-		       rk3399_timer_init);
+CLOCKSOURCE_OF_DECLARE(rk3288_timer, "rockchip,rk3288-timer", rk_timer_init);
+CLOCKSOURCE_OF_DECLARE(rk3399_timer, "rockchip,rk3399-timer", rk_timer_init);
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 0093ece661fe..a68e6538c809 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -385,7 +385,7 @@ static int __init _samsung_pwm_clocksource_init(void)
 	mask = ~pwm.variant.output_mask & ((1 << SAMSUNG_PWM_NUM) - 1);
 	channel = fls(mask) - 1;
 	if (channel < 0) {
-		pr_crit("failed to find PWM channel for clocksource");
+		pr_crit("failed to find PWM channel for clocksource\n");
 		return -EINVAL;
 	}
 	pwm.source_id = channel;
@@ -393,7 +393,7 @@ static int __init _samsung_pwm_clocksource_init(void)
 	mask &= ~(1 << channel);
 	channel = fls(mask) - 1;
 	if (channel < 0) {
-		pr_crit("failed to find PWM channel for clock event");
+		pr_crit("failed to find PWM channel for clock event\n");
 		return -EINVAL;
 	}
 	pwm.event_id = channel;
@@ -448,7 +448,7 @@ static int __init samsung_pwm_alloc(struct device_node *np,
 
 	pwm.timerclk = of_clk_get_by_name(np, "timers");
 	if (IS_ERR(pwm.timerclk)) {
-		pr_crit("failed to get timers clock for timer");
+		pr_crit("failed to get timers clock for timer\n");
 		return PTR_ERR(pwm.timerclk);
 	}
 
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 28757edf6aca..e09e8bf0bb9b 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -103,7 +103,6 @@ struct sh_cmt_channel {
 	unsigned long match_value;
 	unsigned long next_match_value;
 	unsigned long max_match_value;
-	unsigned long rate;
 	raw_spinlock_t lock;
 	struct clock_event_device ced;
 	struct clocksource cs;
@@ -118,6 +117,7 @@ struct sh_cmt_device {
 
 	void __iomem *mapbase;
 	struct clk *clk;
+	unsigned long rate;
 
 	raw_spinlock_t lock; /* Protect the shared start/stop register */
 
@@ -320,7 +320,7 @@ static void sh_cmt_start_stop_ch(struct sh_cmt_channel *ch, int start)
 	raw_spin_unlock_irqrestore(&ch->cmt->lock, flags);
 }
 
-static int sh_cmt_enable(struct sh_cmt_channel *ch, unsigned long *rate)
+static int sh_cmt_enable(struct sh_cmt_channel *ch)
 {
 	int k, ret;
 
@@ -340,11 +340,9 @@ static int sh_cmt_enable(struct sh_cmt_channel *ch, unsigned long *rate)
 
 	/* configure channel, periodic mode and maximum timeout */
 	if (ch->cmt->info->width == 16) {
-		*rate = clk_get_rate(ch->cmt->clk) / 512;
 		sh_cmt_write_cmcsr(ch, SH_CMT16_CMCSR_CMIE |
 				   SH_CMT16_CMCSR_CKS512);
 	} else {
-		*rate = clk_get_rate(ch->cmt->clk) / 8;
 		sh_cmt_write_cmcsr(ch, SH_CMT32_CMCSR_CMM |
 				   SH_CMT32_CMCSR_CMTOUT_IE |
 				   SH_CMT32_CMCSR_CMR_IRQ |
@@ -572,7 +570,7 @@ static int sh_cmt_start(struct sh_cmt_channel *ch, unsigned long flag)
 	raw_spin_lock_irqsave(&ch->lock, flags);
 
 	if (!(ch->flags & (FLAG_CLOCKEVENT | FLAG_CLOCKSOURCE)))
-		ret = sh_cmt_enable(ch, &ch->rate);
+		ret = sh_cmt_enable(ch);
 
 	if (ret)
 		goto out;
@@ -640,10 +638,9 @@ static int sh_cmt_clocksource_enable(struct clocksource *cs)
 	ch->total_cycles = 0;
 
 	ret = sh_cmt_start(ch, FLAG_CLOCKSOURCE);
-	if (!ret) {
-		__clocksource_update_freq_hz(cs, ch->rate);
+	if (!ret)
 		ch->cs_enabled = true;
-	}
+
 	return ret;
 }
 
@@ -697,8 +694,7 @@ static int sh_cmt_register_clocksource(struct sh_cmt_channel *ch,
 	dev_info(&ch->cmt->pdev->dev, "ch%u: used as clock source\n",
 		 ch->index);
 
-	/* Register with dummy 1 Hz value, gets updated in ->enable() */
-	clocksource_register_hz(cs, 1);
+	clocksource_register_hz(cs, ch->cmt->rate);
 	return 0;
 }
 
@@ -709,19 +705,10 @@ static struct sh_cmt_channel *ced_to_sh_cmt(struct clock_event_device *ced)
 
 static void sh_cmt_clock_event_start(struct sh_cmt_channel *ch, int periodic)
 {
-	struct clock_event_device *ced = &ch->ced;
-
 	sh_cmt_start(ch, FLAG_CLOCKEVENT);
 
-	/* TODO: calculate good shift from rate and counter bit width */
-
-	ced->shift = 32;
-	ced->mult = div_sc(ch->rate, NSEC_PER_SEC, ced->shift);
-	ced->max_delta_ns = clockevent_delta2ns(ch->max_match_value, ced);
-	ced->min_delta_ns = clockevent_delta2ns(0x1f, ced);
-
 	if (periodic)
-		sh_cmt_set_next(ch, ((ch->rate + HZ/2) / HZ) - 1);
+		sh_cmt_set_next(ch, ((ch->cmt->rate + HZ/2) / HZ) - 1);
 	else
 		sh_cmt_set_next(ch, ch->max_match_value);
 }
@@ -824,6 +811,14 @@ static int sh_cmt_register_clockevent(struct sh_cmt_channel *ch,
 	ced->suspend = sh_cmt_clock_event_suspend;
 	ced->resume = sh_cmt_clock_event_resume;
 
+	/* TODO: calculate good shift from rate and counter bit width */
+	ced->shift = 32;
+	ced->mult = div_sc(ch->cmt->rate, NSEC_PER_SEC, ced->shift);
+	ced->max_delta_ns = clockevent_delta2ns(ch->max_match_value, ced);
+	ced->max_delta_ticks = ch->max_match_value;
+	ced->min_delta_ns = clockevent_delta2ns(0x1f, ced);
+	ced->min_delta_ticks = 0x1f;
+
 	dev_info(&ch->cmt->pdev->dev, "ch%u: used for clock events\n",
 		 ch->index);
 	clockevents_register_device(ced);
@@ -996,6 +991,18 @@ static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev)
 	if (ret < 0)
 		goto err_clk_put;
 
+	/* Determine clock rate. */
+	ret = clk_enable(cmt->clk);
+	if (ret < 0)
+		goto err_clk_unprepare;
+
+	if (cmt->info->width == 16)
+		cmt->rate = clk_get_rate(cmt->clk) / 512;
+	else
+		cmt->rate = clk_get_rate(cmt->clk) / 8;
+
+	clk_disable(cmt->clk);
+
 	/* Map the memory resource(s). */
 	ret = sh_cmt_map_memory(cmt);
 	if (ret < 0)
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 1fbf2aadcfd4..31d881621e41 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -46,7 +46,6 @@ struct sh_tmu_channel {
 	void __iomem *base;
 	int irq;
 
-	unsigned long rate;
 	unsigned long periodic;
 	struct clock_event_device ced;
 	struct clocksource cs;
@@ -59,6 +58,7 @@ struct sh_tmu_device {
 
 	void __iomem *mapbase;
 	struct clk *clk;
+	unsigned long rate;
 
 	enum sh_tmu_model model;
 
@@ -165,7 +165,6 @@ static int __sh_tmu_enable(struct sh_tmu_channel *ch)
 	sh_tmu_write(ch, TCNT, 0xffffffff);
 
 	/* configure channel to parent clock / 4, irq off */
-	ch->rate = clk_get_rate(ch->tmu->clk) / 4;
 	sh_tmu_write(ch, TCR, TCR_TPSC_CLK4);
 
 	/* enable channel */
@@ -271,10 +270,8 @@ static int sh_tmu_clocksource_enable(struct clocksource *cs)
 		return 0;
 
 	ret = sh_tmu_enable(ch);
-	if (!ret) {
-		__clocksource_update_freq_hz(cs, ch->rate);
+	if (!ret)
 		ch->cs_enabled = true;
-	}
 
 	return ret;
 }
@@ -334,8 +331,7 @@ static int sh_tmu_register_clocksource(struct sh_tmu_channel *ch,
 	dev_info(&ch->tmu->pdev->dev, "ch%u: used as clock source\n",
 		 ch->index);
 
-	/* Register with dummy 1 Hz value, gets updated in ->enable() */
-	clocksource_register_hz(cs, 1);
+	clocksource_register_hz(cs, ch->tmu->rate);
 	return 0;
 }
 
@@ -346,14 +342,10 @@ static struct sh_tmu_channel *ced_to_sh_tmu(struct clock_event_device *ced)
 
 static void sh_tmu_clock_event_start(struct sh_tmu_channel *ch, int periodic)
 {
-	struct clock_event_device *ced = &ch->ced;
-
 	sh_tmu_enable(ch);
 
-	clockevents_config(ced, ch->rate);
-
 	if (periodic) {
-		ch->periodic = (ch->rate + HZ/2) / HZ;
+		ch->periodic = (ch->tmu->rate + HZ/2) / HZ;
 		sh_tmu_set_next(ch, ch->periodic, 1);
 	}
 }
@@ -435,7 +427,7 @@ static void sh_tmu_register_clockevent(struct sh_tmu_channel *ch,
 	dev_info(&ch->tmu->pdev->dev, "ch%u: used for clock events\n",
 		 ch->index);
 
-	clockevents_config_and_register(ced, 1, 0x300, 0xffffffff);
+	clockevents_config_and_register(ced, ch->tmu->rate, 0x300, 0xffffffff);
 
 	ret = request_irq(ch->irq, sh_tmu_interrupt,
 			  IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
@@ -561,6 +553,14 @@ static int sh_tmu_setup(struct sh_tmu_device *tmu, struct platform_device *pdev)
 	if (ret < 0)
 		goto err_clk_put;
 
+	/* Determine clock rate. */
+	ret = clk_enable(tmu->clk);
+	if (ret < 0)
+		goto err_clk_unprepare;
+
+	tmu->rate = clk_get_rate(tmu->clk) / 4;
+	clk_disable(tmu->clk);
+
 	/* Map the memory resource. */
 	ret = sh_tmu_map_memory(tmu);
 	if (ret < 0) {
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index c83452cacb41..4452d5c8f304 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -159,25 +159,25 @@ static int __init sun4i_timer_init(struct device_node *node)
 
 	timer_base = of_iomap(node, 0);
 	if (!timer_base) {
-		pr_crit("Can't map registers");
+		pr_crit("Can't map registers\n");
 		return -ENXIO;
 	}
 
 	irq = irq_of_parse_and_map(node, 0);
 	if (irq <= 0) {
-		pr_crit("Can't parse IRQ");
+		pr_crit("Can't parse IRQ\n");
 		return -EINVAL;
 	}
 
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk)) {
-		pr_crit("Can't get timer clock");
+		pr_crit("Can't get timer clock\n");
 		return PTR_ERR(clk);
 	}
 
 	ret = clk_prepare_enable(clk);
 	if (ret) {
-		pr_err("Failed to prepare clock");
+		pr_err("Failed to prepare clock\n");
 		return ret;
 	}
 
@@ -200,7 +200,7 @@ static int __init sun4i_timer_init(struct device_node *node)
 	ret = clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name,
 				    rate, 350, 32, clocksource_mmio_readl_down);
 	if (ret) {
-		pr_err("Failed to register clocksource");
+		pr_err("Failed to register clocksource\n");
 		return ret;
 	}
 
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 745844ee973e..d4ca9962a759 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -10,7 +10,6 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/atmel_tc.h>
-#include <linux/sched_clock.h>
 
 
 /*
@@ -57,14 +56,9 @@ static u64 tc_get_cycles(struct clocksource *cs)
 	return (upper << 16) | lower;
 }
 
-static u32 tc_get_cv32(void)
-{
-	return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
-}
-
 static u64 tc_get_cycles32(struct clocksource *cs)
 {
-	return tc_get_cv32();
+	return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
 }
 
 static struct clocksource clksrc = {
@@ -75,11 +69,6 @@ static struct clocksource clksrc = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace tc_read_sched_clock(void)
-{
-	return tc_get_cv32();
-}
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 struct tc_clkevt_device {
@@ -350,9 +339,6 @@ static int __init tcb_clksrc_init(void)
 		clksrc.read = tc_get_cycles32;
 		/* setup ony channel 0 */
 		tcb_setup_single_chan(tc, best_divisor_idx);
-
-		/* register sched_clock on chips with single 32 bit counter */
-		sched_clock_register(tc_read_sched_clock, 32, divided_rate);
 	} else {
 		/* tclib will give us three clocks no matter what the
 		 * underlying platform supports.
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index f960891aa04e..b9990b9c98c5 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -245,7 +245,7 @@ static int __init tegra20_init_rtc(struct device_node *np)
 
 	rtc_base = of_iomap(np, 0);
 	if (!rtc_base) {
-		pr_err("Can't map RTC registers");
+		pr_err("Can't map RTC registers\n");
 		return -ENXIO;
 	}
 
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 4440aefc59cd..aea4380129ea 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -247,13 +247,13 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 
 	timer_base = of_iomap(np, 0);
 	if (!timer_base) {
-		pr_err("Failed to iomap");
+		pr_err("Failed to iomap\n");
 		return -ENXIO;
 	}
 
 	local_base = of_iomap(np, 1);
 	if (!local_base) {
-		pr_err("Failed to iomap");
+		pr_err("Failed to iomap\n");
 		return -ENXIO;
 	}
 
@@ -298,7 +298,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 				    "armada_370_xp_clocksource",
 				    timer_clk, 300, 32, clocksource_mmio_readl_down);
 	if (res) {
-		pr_err("Failed to initialize clocksource mmio");
+		pr_err("Failed to initialize clocksource mmio\n");
 		return res;
 	}
 
@@ -315,7 +315,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 				armada_370_xp_evt);
 	/* Immediately configure the timer on the boot CPU */
 	if (res) {
-		pr_err("Failed to request percpu irq");
+		pr_err("Failed to request percpu irq\n");
 		return res;
 	}
 
@@ -324,7 +324,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 				armada_370_xp_timer_starting_cpu,
 				armada_370_xp_timer_dying_cpu);
 	if (res) {
-		pr_err("Failed to setup hotplug state and timer");
+		pr_err("Failed to setup hotplug state and timer\n");
 		return res;
 	}
 
@@ -339,7 +339,7 @@ static int __init armada_xp_timer_init(struct device_node *np)
 	int ret;
 
 	if (IS_ERR(clk)) {
-		pr_err("Failed to get clock");
+		pr_err("Failed to get clock\n");
 		return PTR_ERR(clk);
 	}
 
@@ -375,7 +375,7 @@ static int __init armada_375_timer_init(struct device_node *np)
 
 		/* Must have at least a clock */
 		if (IS_ERR(clk)) {
-			pr_err("Failed to get clock");
+			pr_err("Failed to get clock\n");
 			return PTR_ERR(clk);
 		}
 
@@ -399,7 +399,7 @@ static int __init armada_370_timer_init(struct device_node *np)
 
 	clk = of_clk_get(np, 0);
 	if (IS_ERR(clk)) {
-		pr_err("Failed to get clock");
+		pr_err("Failed to get clock\n");
 		return PTR_ERR(clk);
 	}
 
diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c
index 5ac344b383e1..ce0f97b4e5db 100644
--- a/drivers/clocksource/time-efm32.c
+++ b/drivers/clocksource/time-efm32.c
@@ -235,7 +235,7 @@ static int __init efm32_clockevent_init(struct device_node *np)
 
 	ret = setup_irq(irq, &efm32_clock_event_irq);
 	if (ret) {
-		pr_err("Failed setup irq");
+		pr_err("Failed setup irq\n");
 		goto err_setup_irq;
 	}
 
diff --git a/drivers/clocksource/time-orion.c b/drivers/clocksource/time-orion.c
index a28f496e97cf..b9b97f630c4d 100644
--- a/drivers/clocksource/time-orion.c
+++ b/drivers/clocksource/time-orion.c
@@ -15,6 +15,7 @@
 #include <linux/bitops.h>
 #include <linux/clk.h>
 #include <linux/clockchips.h>
+#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -36,6 +37,21 @@
 
 static void __iomem *timer_base;
 
+static unsigned long notrace orion_read_timer(void)
+{
+	return ~readl(timer_base + TIMER0_VAL);
+}
+
+static struct delay_timer orion_delay_timer = {
+	.read_current_timer = orion_read_timer,
+};
+
+static void orion_delay_timer_init(unsigned long rate)
+{
+	orion_delay_timer.freq = rate;
+	register_current_timer_delay(&orion_delay_timer);
+}
+
 /*
  * Free-running clocksource handling.
  */
@@ -106,6 +122,7 @@ static struct irqaction orion_clkevt_irq = {
 
 static int __init orion_timer_init(struct device_node *np)
 {
+	unsigned long rate;
 	struct clk *clk;
 	int irq, ret;
 
@@ -124,7 +141,7 @@ static int __init orion_timer_init(struct device_node *np)
 
 	ret = clk_prepare_enable(clk);
 	if (ret) {
-		pr_err("Failed to prepare clock");
+		pr_err("Failed to prepare clock\n");
 		return ret;
 	}
 
@@ -135,6 +152,8 @@ static int __init orion_timer_init(struct device_node *np)
 		return -EINVAL;
 	}
 
+	rate = clk_get_rate(clk);
+
 	/* setup timer0 as free-running clocksource */
 	writel(~0, timer_base + TIMER0_VAL);
 	writel(~0, timer_base + TIMER0_RELOAD);
@@ -142,15 +161,15 @@ static int __init orion_timer_init(struct device_node *np)
 		TIMER0_RELOAD_EN | TIMER0_EN,
 		TIMER0_RELOAD_EN | TIMER0_EN);
 
-	ret = clocksource_mmio_init(timer_base + TIMER0_VAL, "orion_clocksource",
-				    clk_get_rate(clk), 300, 32,
+	ret = clocksource_mmio_init(timer_base + TIMER0_VAL,
+				    "orion_clocksource", rate, 300, 32,
 				    clocksource_mmio_readl_down);
 	if (ret) {
-		pr_err("Failed to initialize mmio timer");
+		pr_err("Failed to initialize mmio timer\n");
 		return ret;
 	}
 
-	sched_clock_register(orion_read_sched_clock, 32, clk_get_rate(clk));
+	sched_clock_register(orion_read_sched_clock, 32, rate);
 
 	/* setup timer1 as clockevent timer */
 	ret = setup_irq(irq, &orion_clkevt_irq);
@@ -162,9 +181,12 @@ static int __init orion_timer_init(struct device_node *np)
 	ticks_per_jiffy = (clk_get_rate(clk) + HZ/2) / HZ;
 	orion_clkevt.cpumask = cpumask_of(0);
 	orion_clkevt.irq = irq;
-	clockevents_config_and_register(&orion_clkevt, clk_get_rate(clk),
+	clockevents_config_and_register(&orion_clkevt, rate,
 					ORION_ONESHOT_MIN, ORION_ONESHOT_MAX);
 
+
+	orion_delay_timer_init(rate);
+
 	return 0;
 }
 CLOCKSOURCE_OF_DECLARE(orion_timer, "marvell,orion-timer", orion_timer_init);
diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c
index 3d8a181f0252..50300eec4a39 100644
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -192,7 +192,9 @@ static int sirfsoc_local_timer_starting_cpu(unsigned int cpu)
 	ce->set_next_event = sirfsoc_timer_set_next_event;
 	clockevents_calc_mult_shift(ce, atlas7_timer_rate, 60);
 	ce->max_delta_ns = clockevent_delta2ns(-2, ce);
+	ce->max_delta_ticks = (unsigned long)-2;
 	ce->min_delta_ns = clockevent_delta2ns(2, ce);
+	ce->min_delta_ticks = 2;
 	ce->cpumask = cpumask_of(cpu);
 
 	action->dev_id = ce;
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index c0b5df3167a0..cc112351dc70 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/drivers/clocksource/timer-atmel-pit.c
@@ -226,7 +226,7 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
 	
 	ret = clocksource_register_hz(&data->clksrc, pit_rate);
 	if (ret) {
-		pr_err("Failed to register clocksource");
+		pr_err("Failed to register clocksource\n");
 		return ret;
 	}
 
diff --git a/drivers/clocksource/timer-digicolor.c b/drivers/clocksource/timer-digicolor.c
index e9f50d289362..94a161eb9cce 100644
--- a/drivers/clocksource/timer-digicolor.c
+++ b/drivers/clocksource/timer-digicolor.c
@@ -161,19 +161,19 @@ static int __init digicolor_timer_init(struct device_node *node)
 	 */
 	dc_timer_dev.base = of_iomap(node, 0);
 	if (!dc_timer_dev.base) {
-		pr_err("Can't map registers");
+		pr_err("Can't map registers\n");
 		return -ENXIO;
 	}
 
 	irq = irq_of_parse_and_map(node, dc_timer_dev.timer_id);
 	if (irq <= 0) {
-		pr_err("Can't parse IRQ");
+		pr_err("Can't parse IRQ\n");
 		return -EINVAL;
 	}
 
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock");
+		pr_err("Can't get timer clock\n");
 		return PTR_ERR(clk);
 	}
 	clk_prepare_enable(clk);
diff --git a/drivers/clocksource/timer-gemini.c b/drivers/clocksource/timer-fttmr010.c
index dda27b7bf1a1..b4a6f1e4bc54 100644
--- a/drivers/clocksource/timer-gemini.c
+++ b/drivers/clocksource/timer-fttmr010.c
@@ -1,5 +1,5 @@
 /*
- * Gemini timer driver
+ * Faraday Technology FTTMR010 timer driver
  * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
  *
  * Based on a rewrite of arch/arm/mach-gemini/timer.c:
@@ -16,17 +16,7 @@
 #include <linux/clockchips.h>
 #include <linux/clocksource.h>
 #include <linux/sched_clock.h>
-
-/*
- * Relevant registers in the global syscon
- */
-#define GLOBAL_STATUS		0x04
-#define CPU_AHB_RATIO_MASK	(0x3 << 18)
-#define CPU_AHB_1_1		(0x0 << 18)
-#define CPU_AHB_3_2		(0x1 << 18)
-#define CPU_AHB_24_13		(0x2 << 18)
-#define CPU_AHB_2_1		(0x3 << 18)
-#define REG_TO_AHB_SPEED(reg)	((((reg) >> 15) & 0x7) * 10 + 130)
+#include <linux/clk.h>
 
 /*
  * Register definitions for the timers
@@ -77,12 +67,12 @@
 static unsigned int tick_rate;
 static void __iomem *base;
 
-static u64 notrace gemini_read_sched_clock(void)
+static u64 notrace fttmr010_read_sched_clock(void)
 {
 	return readl(base + TIMER3_COUNT);
 }
 
-static int gemini_timer_set_next_event(unsigned long cycles,
+static int fttmr010_timer_set_next_event(unsigned long cycles,
 				       struct clock_event_device *evt)
 {
 	u32 cr;
@@ -96,7 +86,7 @@ static int gemini_timer_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static int gemini_timer_shutdown(struct clock_event_device *evt)
+static int fttmr010_timer_shutdown(struct clock_event_device *evt)
 {
 	u32 cr;
 
@@ -127,7 +117,7 @@ static int gemini_timer_shutdown(struct clock_event_device *evt)
 	return 0;
 }
 
-static int gemini_timer_set_periodic(struct clock_event_device *evt)
+static int fttmr010_timer_set_periodic(struct clock_event_device *evt)
 {
 	u32 period = DIV_ROUND_CLOSEST(tick_rate, HZ);
 	u32 cr;
@@ -158,54 +148,40 @@ static int gemini_timer_set_periodic(struct clock_event_device *evt)
 }
 
 /* Use TIMER1 as clock event */
-static struct clock_event_device gemini_clockevent = {
+static struct clock_event_device fttmr010_clockevent = {
 	.name			= "TIMER1",
 	/* Reasonably fast and accurate clock event */
 	.rating			= 300,
 	.shift                  = 32,
 	.features		= CLOCK_EVT_FEAT_PERIODIC |
 				  CLOCK_EVT_FEAT_ONESHOT,
-	.set_next_event		= gemini_timer_set_next_event,
-	.set_state_shutdown	= gemini_timer_shutdown,
-	.set_state_periodic	= gemini_timer_set_periodic,
-	.set_state_oneshot	= gemini_timer_shutdown,
-	.tick_resume		= gemini_timer_shutdown,
+	.set_next_event		= fttmr010_timer_set_next_event,
+	.set_state_shutdown	= fttmr010_timer_shutdown,
+	.set_state_periodic	= fttmr010_timer_set_periodic,
+	.set_state_oneshot	= fttmr010_timer_shutdown,
+	.tick_resume		= fttmr010_timer_shutdown,
 };
 
 /*
  * IRQ handler for the timer
  */
-static irqreturn_t gemini_timer_interrupt(int irq, void *dev_id)
+static irqreturn_t fttmr010_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = &gemini_clockevent;
+	struct clock_event_device *evt = &fttmr010_clockevent;
 
 	evt->event_handler(evt);
 	return IRQ_HANDLED;
 }
 
-static struct irqaction gemini_timer_irq = {
-	.name		= "Gemini Timer Tick",
+static struct irqaction fttmr010_timer_irq = {
+	.name		= "Faraday FTTMR010 Timer Tick",
 	.flags		= IRQF_TIMER,
-	.handler	= gemini_timer_interrupt,
+	.handler	= fttmr010_timer_interrupt,
 };
 
-static int __init gemini_timer_of_init(struct device_node *np)
+static int __init fttmr010_timer_common_init(struct device_node *np)
 {
-	static struct regmap *map;
 	int irq;
-	int ret;
-	u32 val;
-
-	map = syscon_regmap_lookup_by_phandle(np, "syscon");
-	if (IS_ERR(map)) {
-		pr_err("Can't get regmap for syscon handle");
-		return -ENODEV;
-	}
-	ret = regmap_read(map, GLOBAL_STATUS, &val);
-	if (ret) {
-		pr_err("Can't read syscon status register");
-		return -ENXIO;
-	}
 
 	base = of_iomap(np, 0);
 	if (!base) {
@@ -219,26 +195,6 @@ static int __init gemini_timer_of_init(struct device_node *np)
 		return -EINVAL;
 	}
 
-	tick_rate = REG_TO_AHB_SPEED(val) * 1000000;
-	printk(KERN_INFO "Bus: %dMHz", tick_rate / 1000000);
-
-	tick_rate /= 6;		/* APB bus run AHB*(1/6) */
-
-	switch (val & CPU_AHB_RATIO_MASK) {
-	case CPU_AHB_1_1:
-		printk(KERN_CONT "(1/1)\n");
-		break;
-	case CPU_AHB_3_2:
-		printk(KERN_CONT "(3/2)\n");
-		break;
-	case CPU_AHB_24_13:
-		printk(KERN_CONT "(24/13)\n");
-		break;
-	case CPU_AHB_2_1:
-		printk(KERN_CONT "(2/1)\n");
-		break;
-	}
-
 	/*
 	 * Reset the interrupt mask and status
 	 */
@@ -255,9 +211,9 @@ static int __init gemini_timer_of_init(struct device_node *np)
 	writel(0, base + TIMER3_MATCH1);
 	writel(0, base + TIMER3_MATCH2);
 	clocksource_mmio_init(base + TIMER3_COUNT,
-			      "gemini_clocksource", tick_rate,
+			      "fttmr010_clocksource", tick_rate,
 			      300, 32, clocksource_mmio_readl_up);
-	sched_clock_register(gemini_read_sched_clock, 32, tick_rate);
+	sched_clock_register(fttmr010_read_sched_clock, 32, tick_rate);
 
 	/*
 	 * Setup clockevent timer (interrupt-driven.)
@@ -266,12 +222,82 @@ static int __init gemini_timer_of_init(struct device_node *np)
 	writel(0, base + TIMER1_LOAD);
 	writel(0, base + TIMER1_MATCH1);
 	writel(0, base + TIMER1_MATCH2);
-	setup_irq(irq, &gemini_timer_irq);
-	gemini_clockevent.cpumask = cpumask_of(0);
-	clockevents_config_and_register(&gemini_clockevent, tick_rate,
+	setup_irq(irq, &fttmr010_timer_irq);
+	fttmr010_clockevent.cpumask = cpumask_of(0);
+	clockevents_config_and_register(&fttmr010_clockevent, tick_rate,
 					1, 0xffffffff);
 
 	return 0;
 }
-CLOCKSOURCE_OF_DECLARE(nomadik_mtu, "cortina,gemini-timer",
-		       gemini_timer_of_init);
+
+static int __init fttmr010_timer_of_init(struct device_node *np)
+{
+	/*
+	 * These implementations require a clock reference.
+	 * FIXME: we currently only support clocking using PCLK
+	 * and using EXTCLK is not supported in the driver.
+	 */
+	struct clk *clk;
+
+	clk = of_clk_get_by_name(np, "PCLK");
+	if (IS_ERR(clk)) {
+		pr_err("could not get PCLK");
+		return PTR_ERR(clk);
+	}
+	tick_rate = clk_get_rate(clk);
+
+	return fttmr010_timer_common_init(np);
+}
+CLOCKSOURCE_OF_DECLARE(fttmr010, "faraday,fttmr010", fttmr010_timer_of_init);
+
+/*
+ * Gemini-specific: relevant registers in the global syscon
+ */
+#define GLOBAL_STATUS		0x04
+#define CPU_AHB_RATIO_MASK	(0x3 << 18)
+#define CPU_AHB_1_1		(0x0 << 18)
+#define CPU_AHB_3_2		(0x1 << 18)
+#define CPU_AHB_24_13		(0x2 << 18)
+#define CPU_AHB_2_1		(0x3 << 18)
+#define REG_TO_AHB_SPEED(reg)	((((reg) >> 15) & 0x7) * 10 + 130)
+
+static int __init gemini_timer_of_init(struct device_node *np)
+{
+	static struct regmap *map;
+	int ret;
+	u32 val;
+
+	map = syscon_regmap_lookup_by_phandle(np, "syscon");
+	if (IS_ERR(map)) {
+		pr_err("Can't get regmap for syscon handle\n");
+		return -ENODEV;
+	}
+	ret = regmap_read(map, GLOBAL_STATUS, &val);
+	if (ret) {
+		pr_err("Can't read syscon status register\n");
+		return -ENXIO;
+	}
+
+	tick_rate = REG_TO_AHB_SPEED(val) * 1000000;
+	pr_info("Bus: %dMHz ", tick_rate / 1000000);
+
+	tick_rate /= 6;		/* APB bus run AHB*(1/6) */
+
+	switch (val & CPU_AHB_RATIO_MASK) {
+	case CPU_AHB_1_1:
+		pr_cont("(1/1)\n");
+		break;
+	case CPU_AHB_3_2:
+		pr_cont("(3/2)\n");
+		break;
+	case CPU_AHB_24_13:
+		pr_cont("(24/13)\n");
+		break;
+	case CPU_AHB_2_1:
+		pr_cont("(2/1)\n");
+		break;
+	}
+
+	return fttmr010_timer_common_init(np);
+}
+CLOCKSOURCE_OF_DECLARE(gemini, "cortina,gemini-timer", gemini_timer_of_init);
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index df6e672afc04..04ad3066e190 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -200,7 +200,7 @@ static int __init integrator_ap_timer_init_of(struct device_node *node)
 	err = of_property_read_string(of_aliases,
 				"arm,timer-primary", &path);
 	if (err) {
-		pr_warn("Failed to read property");
+		pr_warn("Failed to read property\n");
 		return err;
 	}
 
@@ -209,7 +209,7 @@ static int __init integrator_ap_timer_init_of(struct device_node *node)
 	err = of_property_read_string(of_aliases,
 				"arm,timer-secondary", &path);
 	if (err) {
-		pr_warn("Failed to read property");		
+		pr_warn("Failed to read property\n");
 		return err;
 	}
 
diff --git a/drivers/clocksource/timer-nps.c b/drivers/clocksource/timer-nps.c
index da1f7986e477..e74ea1722ad3 100644
--- a/drivers/clocksource/timer-nps.c
+++ b/drivers/clocksource/timer-nps.c
@@ -55,7 +55,7 @@ static int __init nps_get_timer_clk(struct device_node *node,
 	*clk = of_clk_get(node, 0);
 	ret = PTR_ERR_OR_ZERO(*clk);
 	if (ret) {
-		pr_err("timer missing clk");
+		pr_err("timer missing clk\n");
 		return ret;
 	}
 
@@ -247,7 +247,7 @@ static int __init nps_setup_clockevent(struct device_node *node)
 
 	nps_timer0_irq = irq_of_parse_and_map(node, 0);
 	if (nps_timer0_irq <= 0) {
-		pr_err("clockevent: missing irq");
+		pr_err("clockevent: missing irq\n");
 		return -EINVAL;
 	}
 
@@ -270,7 +270,7 @@ static int __init nps_setup_clockevent(struct device_node *node)
 				nps_timer_starting_cpu,
 				nps_timer_dying_cpu);
 	if (ret) {
-		pr_err("Failed to setup hotplug state");
+		pr_err("Failed to setup hotplug state\n");
 		clk_disable_unprepare(clk);
 		free_percpu_irq(nps_timer0_irq, &nps_clockevent_device);
 		return ret;
diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c
index bfa981ac1eaf..b4122ed1accb 100644
--- a/drivers/clocksource/timer-prima2.c
+++ b/drivers/clocksource/timer-prima2.c
@@ -196,20 +196,20 @@ static int __init sirfsoc_prima2_timer_init(struct device_node *np)
 
 	clk = of_clk_get(np, 0);
 	if (IS_ERR(clk)) {
-		pr_err("Failed to get clock");
+		pr_err("Failed to get clock\n");
 		return PTR_ERR(clk);
 	}
 
 	ret = clk_prepare_enable(clk);
 	if (ret) {
-		pr_err("Failed to enable clock");
+		pr_err("Failed to enable clock\n");
 		return ret;
 	}
 
 	rate = clk_get_rate(clk);
 
 	if (rate < PRIMA2_CLOCK_FREQ || rate % PRIMA2_CLOCK_FREQ) {
-		pr_err("Invalid clock rate");
+		pr_err("Invalid clock rate\n");
 		return -EINVAL;
 	}
 
@@ -229,7 +229,7 @@ static int __init sirfsoc_prima2_timer_init(struct device_node *np)
 
 	ret = clocksource_register_hz(&sirfsoc_clocksource, PRIMA2_CLOCK_FREQ);
 	if (ret) {
-		pr_err("Failed to register clocksource");
+		pr_err("Failed to register clocksource\n");
 		return ret;
 	}
 
@@ -237,7 +237,7 @@ static int __init sirfsoc_prima2_timer_init(struct device_node *np)
 
 	ret = setup_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq);
 	if (ret) {
-		pr_err("Failed to setup irq");
+		pr_err("Failed to setup irq\n");
 		return ret;
 	}
 
diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c
index d07863388e05..2d575a8c0939 100644
--- a/drivers/clocksource/timer-sp804.c
+++ b/drivers/clocksource/timer-sp804.c
@@ -299,13 +299,13 @@ static int __init integrator_cp_of_init(struct device_node *np)
 
 	base = of_iomap(np, 0);
 	if (!base) {
-		pr_err("Failed to iomap");
+		pr_err("Failed to iomap\n");
 		return -ENXIO;
 	}
 
 	clk = of_clk_get(np, 0);
 	if (IS_ERR(clk)) {
-		pr_err("Failed to get clock");
+		pr_err("Failed to get clock\n");
 		return PTR_ERR(clk);
 	}
 
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index a3e662b15964..2e9c830ae1cd 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -332,19 +332,19 @@ static int __init sun5i_timer_init(struct device_node *node)
 
 	timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
 	if (IS_ERR(timer_base)) {
-		pr_err("Can't map registers");
+		pr_err("Can't map registers\n");
 		return PTR_ERR(timer_base);;
 	}
 
 	irq = irq_of_parse_and_map(node, 0);
 	if (irq <= 0) {
-		pr_err("Can't parse IRQ");
+		pr_err("Can't parse IRQ\n");
 		return -EINVAL;
 	}
 
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock");
+		pr_err("Can't get timer clock\n");
 		return PTR_ERR(clk);
 	}
 
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
index 55d8d8402d90..e0849e20a307 100644
--- a/drivers/clocksource/vf_pit_timer.c
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -165,7 +165,7 @@ static int __init pit_timer_init(struct device_node *np)
 
 	timer_base = of_iomap(np, 0);
 	if (!timer_base) {
-		pr_err("Failed to iomap");
+		pr_err("Failed to iomap\n");
 		return -ENXIO;
 	}
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 74fa5c5904d3..74ed7e9a7f27 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -247,6 +247,12 @@ config ARM_TEGRA124_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
+config ARM_TEGRA186_CPUFREQ
+	tristate "Tegra186 CPUFreq support"
+	depends on ARCH_TEGRA && TEGRA_BPMP
+	help
+	  This adds the CPUFreq driver support for Tegra186 SOCs.
+
 config ARM_TI_CPUFREQ
 	bool "Texas Instruments CPUFreq support"
 	depends on ARCH_OMAP2PLUS
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 9f5a8045f36d..b7e78f063c4f 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
 obj-$(CONFIG_ARM_STI_CPUFREQ)		+= sti-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA186_CPUFREQ)	+= tegra186-cpufreq.o
 obj-$(CONFIG_ARM_TI_CPUFREQ)		+= ti-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
 obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index a47543281864..0e3f6496524d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -680,9 +680,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
 	unsigned int cur_freq = __cpufreq_get(policy);
-	if (!cur_freq)
-		return sprintf(buf, "<unknown>");
-	return sprintf(buf, "%u\n", cur_freq);
+
+	if (cur_freq)
+		return sprintf(buf, "%u\n", cur_freq);
+
+	return sprintf(buf, "<unknown>\n");
 }
 
 /**
@@ -916,11 +918,19 @@ static struct kobj_type ktype_cpufreq = {
 	.release	= cpufreq_sysfs_release,
 };
 
-static int add_cpu_dev_symlink(struct cpufreq_policy *policy,
-			       struct device *dev)
+static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
 {
+	struct device *dev = get_cpu_device(cpu);
+
+	if (!dev)
+		return;
+
+	if (cpumask_test_and_set_cpu(cpu, policy->real_cpus))
+		return;
+
 	dev_dbg(dev, "%s: Adding symlink\n", __func__);
-	return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
+	if (sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"))
+		dev_err(dev, "cpufreq symlink creation failed\n");
 }
 
 static void remove_cpu_dev_symlink(struct cpufreq_policy *policy,
@@ -1178,10 +1188,13 @@ static int cpufreq_online(unsigned int cpu)
 		policy->user_policy.min = policy->min;
 		policy->user_policy.max = policy->max;
 
-		write_lock_irqsave(&cpufreq_driver_lock, flags);
-		for_each_cpu(j, policy->related_cpus)
+		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
-		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+			add_cpu_dev_symlink(policy, j);
+		}
+	} else {
+		policy->min = policy->user_policy.min;
+		policy->max = policy->user_policy.max;
 	}
 
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
@@ -1270,13 +1283,15 @@ out_exit_policy:
 
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
+
+	for_each_cpu(j, policy->real_cpus)
+		remove_cpu_dev_symlink(policy, get_cpu_device(j));
+
 out_free_policy:
 	cpufreq_policy_free(policy);
 	return ret;
 }
 
-static int cpufreq_offline(unsigned int cpu);
-
 /**
  * cpufreq_add_dev - the cpufreq interface for a CPU device.
  * @dev: CPU device.
@@ -1298,16 +1313,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 
 	/* Create sysfs link on CPU registration */
 	policy = per_cpu(cpufreq_cpu_data, cpu);
-	if (!policy || cpumask_test_and_set_cpu(cpu, policy->real_cpus))
-		return 0;
+	if (policy)
+		add_cpu_dev_symlink(policy, cpu);
 
-	ret = add_cpu_dev_symlink(policy, dev);
-	if (ret) {
-		cpumask_clear_cpu(cpu, policy->real_cpus);
-		cpufreq_offline(cpu);
-	}
-
-	return ret;
+	return 0;
 }
 
 static int cpufreq_offline(unsigned int cpu)
@@ -2389,6 +2398,20 @@ EXPORT_SYMBOL_GPL(cpufreq_boost_enabled);
  *********************************************************************/
 static enum cpuhp_state hp_online;
 
+static int cpuhp_cpufreq_online(unsigned int cpu)
+{
+	cpufreq_online(cpu);
+
+	return 0;
+}
+
+static int cpuhp_cpufreq_offline(unsigned int cpu)
+{
+	cpufreq_offline(cpu);
+
+	return 0;
+}
+
 /**
  * cpufreq_register_driver - register a CPU Frequency driver
  * @driver_data: A struct cpufreq_driver containing the values#
@@ -2451,8 +2474,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	}
 
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
-					cpufreq_online,
-					cpufreq_offline);
+					cpuhp_cpufreq_online,
+					cpuhp_cpufreq_offline);
 	if (ret < 0)
 		goto err_if_unreg;
 	hp_online = ret;
@@ -2532,4 +2555,5 @@ static int __init cpufreq_core_init(void)
 
 	return 0;
 }
+module_param(off, int, 0444);
 core_initcall(cpufreq_core_init);
diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c
index 5c3ec1dd4921..3575b82210ba 100644
--- a/drivers/cpufreq/dbx500-cpufreq.c
+++ b/drivers/cpufreq/dbx500-cpufreq.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
@@ -18,6 +19,7 @@
 
 static struct cpufreq_frequency_table *freq_table;
 static struct clk *armss_clk;
+static struct thermal_cooling_device *cdev;
 
 static int dbx500_cpufreq_target(struct cpufreq_policy *policy,
 				unsigned int index)
@@ -32,6 +34,22 @@ static int dbx500_cpufreq_init(struct cpufreq_policy *policy)
 	return cpufreq_generic_init(policy, freq_table, 20 * 1000);
 }
 
+static int dbx500_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	if (!IS_ERR(cdev))
+		cpufreq_cooling_unregister(cdev);
+	return 0;
+}
+
+static void dbx500_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	cdev = cpufreq_cooling_register(policy->cpus);
+	if (IS_ERR(cdev))
+		pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev));
+	else
+		pr_info("Cooling device registered: %s\n", cdev->type);
+}
+
 static struct cpufreq_driver dbx500_cpufreq_driver = {
 	.flags  = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS |
 			CPUFREQ_NEED_INITIAL_FREQ_CHECK,
@@ -39,6 +57,8 @@ static struct cpufreq_driver dbx500_cpufreq_driver = {
 	.target_index = dbx500_cpufreq_target,
 	.get    = cpufreq_generic_get,
 	.init   = dbx500_cpufreq_init,
+	.exit  = dbx500_cpufreq_exit,
+	.ready  = dbx500_cpufreq_ready,
 	.name   = "DBX500",
 	.attr   = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index e28a31a40829..a757c0a1e7b5 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -34,6 +34,11 @@ struct cpufreq_acpi_io {
 	unsigned int				resume;
 };
 
+struct cpufreq_acpi_req {
+	unsigned int		cpu;
+	unsigned int		state;
+};
+
 static struct cpufreq_acpi_io	*acpi_io_data[NR_CPUS];
 
 static struct cpufreq_driver acpi_cpufreq_driver;
@@ -83,8 +88,7 @@ processor_get_pstate (
 static unsigned
 extract_clock (
 	struct cpufreq_acpi_io *data,
-	unsigned value,
-	unsigned int cpu)
+	unsigned value)
 {
 	unsigned long i;
 
@@ -98,60 +102,43 @@ extract_clock (
 }
 
 
-static unsigned int
+static long
 processor_get_freq (
-	struct cpufreq_acpi_io	*data,
-	unsigned int		cpu)
+	void *arg)
 {
-	int			ret = 0;
-	u32			value = 0;
-	cpumask_t		saved_mask;
-	unsigned long 		clock_freq;
+	struct cpufreq_acpi_req *req = arg;
+	unsigned int		cpu = req->cpu;
+	struct cpufreq_acpi_io	*data = acpi_io_data[cpu];
+	u32			value;
+	int			ret;
 
 	pr_debug("processor_get_freq\n");
-
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 	if (smp_processor_id() != cpu)
-		goto migrate_end;
+		return -EAGAIN;
 
 	/* processor_get_pstate gets the instantaneous frequency */
 	ret = processor_get_pstate(&value);
-
 	if (ret) {
-		set_cpus_allowed_ptr(current, &saved_mask);
 		pr_warn("get performance failed with error %d\n", ret);
-		ret = 0;
-		goto migrate_end;
+		return ret;
 	}
-	clock_freq = extract_clock(data, value, cpu);
-	ret = (clock_freq*1000);
-
-migrate_end:
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return ret;
+	return 1000 * extract_clock(data, value);
 }
 
 
-static int
+static long
 processor_set_freq (
-	struct cpufreq_acpi_io	*data,
-	struct cpufreq_policy   *policy,
-	int			state)
+	void *arg)
 {
-	int			ret = 0;
-	u32			value = 0;
-	cpumask_t		saved_mask;
-	int			retval;
+	struct cpufreq_acpi_req *req = arg;
+	unsigned int		cpu = req->cpu;
+	struct cpufreq_acpi_io	*data = acpi_io_data[cpu];
+	int			ret, state = req->state;
+	u32			value;
 
 	pr_debug("processor_set_freq\n");
-
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(policy->cpu));
-	if (smp_processor_id() != policy->cpu) {
-		retval = -EAGAIN;
-		goto migrate_end;
-	}
+	if (smp_processor_id() != cpu)
+		return -EAGAIN;
 
 	if (state == data->acpi_data.state) {
 		if (unlikely(data->resume)) {
@@ -159,8 +146,7 @@ processor_set_freq (
 			data->resume = 0;
 		} else {
 			pr_debug("Already at target state (P%d)\n", state);
-			retval = 0;
-			goto migrate_end;
+			return 0;
 		}
 	}
 
@@ -171,7 +157,6 @@ processor_set_freq (
 	 * First we write the target state's 'control' value to the
 	 * control_register.
 	 */
-
 	value = (u32) data->acpi_data.states[state].control;
 
 	pr_debug("Transitioning to state: 0x%08x\n", value);
@@ -179,17 +164,11 @@ processor_set_freq (
 	ret = processor_set_pstate(value);
 	if (ret) {
 		pr_warn("Transition failed with error %d\n", ret);
-		retval = -ENODEV;
-		goto migrate_end;
+		return -ENODEV;
 	}
 
 	data->acpi_data.state = state;
-
-	retval = 0;
-
-migrate_end:
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return (retval);
+	return 0;
 }
 
 
@@ -197,11 +176,13 @@ static unsigned int
 acpi_cpufreq_get (
 	unsigned int		cpu)
 {
-	struct cpufreq_acpi_io *data = acpi_io_data[cpu];
+	struct cpufreq_acpi_req req;
+	long ret;
 
-	pr_debug("acpi_cpufreq_get\n");
+	req.cpu = cpu;
+	ret = work_on_cpu(cpu, processor_get_freq, &req);
 
-	return processor_get_freq(data, cpu);
+	return ret > 0 ? (unsigned int) ret : 0;
 }
 
 
@@ -210,7 +191,12 @@ acpi_cpufreq_target (
 	struct cpufreq_policy   *policy,
 	unsigned int index)
 {
-	return processor_set_freq(acpi_io_data[policy->cpu], policy, index);
+	struct cpufreq_acpi_req req;
+
+	req.cpu = policy->cpu;
+	req.state = index;
+
+	return work_on_cpu(req.cpu, processor_set_freq, &req);
 }
 
 static int
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 7719b02e04f5..9c13f097fd8c 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -161,8 +161,13 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
+	int ret;
+
 	policy->clk = arm_clk;
-	return cpufreq_generic_init(policy, freq_table, transition_latency);
+	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
+	policy->suspend_freq = policy->max;
+
+	return ret;
 }
 
 static struct cpufreq_driver imx6q_cpufreq_driver = {
@@ -173,6 +178,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.init = imx6q_cpufreq_init,
 	.name = "imx6q-cpufreq",
 	.attr = cpufreq_generic_attr,
+	.suspend = cpufreq_generic_suspend,
 };
 
 static int imx6q_cpufreq_probe(struct platform_device *pdev)
@@ -222,6 +228,13 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	arm_reg = regulator_get(cpu_dev, "arm");
 	pu_reg = regulator_get_optional(cpu_dev, "pu");
 	soc_reg = regulator_get(cpu_dev, "soc");
+	if (PTR_ERR(arm_reg) == -EPROBE_DEFER ||
+			PTR_ERR(soc_reg) == -EPROBE_DEFER ||
+			PTR_ERR(pu_reg) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		dev_dbg(cpu_dev, "regulators not ready, defer\n");
+		goto put_reg;
+	}
 	if (IS_ERR(arm_reg) || IS_ERR(soc_reg)) {
 		dev_err(cpu_dev, "failed to get regulators\n");
 		ret = -ENOENT;
@@ -255,7 +268,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
-		goto put_reg;
+		goto out_free_opp;
 	}
 
 	/* Make imx6_soc_volt array's size same as arm opp number */
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b1fbaa30ae04..b7de5bd76a31 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -37,7 +37,11 @@
 #include <asm/cpufeature.h>
 #include <asm/intel-family.h>
 
+#define INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)
+#define INTEL_PSTATE_HWP_SAMPLING_INTERVAL	(50 * NSEC_PER_MSEC)
+
 #define INTEL_CPUFREQ_TRANSITION_LATENCY	20000
+#define INTEL_CPUFREQ_TRANSITION_DELAY		500
 
 #ifdef CONFIG_ACPI
 #include <acpi/processor.h>
@@ -74,6 +78,11 @@ static inline int ceiling_fp(int32_t x)
 	return ret;
 }
 
+static inline int32_t percent_fp(int percent)
+{
+	return div_fp(percent, 100);
+}
+
 static inline u64 mul_ext_fp(u64 x, u64 y)
 {
 	return (x * y) >> EXT_FRAC_BITS;
@@ -84,6 +93,11 @@ static inline u64 div_ext_fp(u64 x, u64 y)
 	return div64_u64(x << EXT_FRAC_BITS, y);
 }
 
+static inline int32_t percent_ext_fp(int percent)
+{
+	return div_ext_fp(percent, 100);
+}
+
 /**
  * struct sample -	Store performance sample
  * @core_avg_perf:	Ratio of APERF/MPERF which is the actual average
@@ -181,45 +195,22 @@ struct _pid {
 };
 
 /**
- * struct perf_limits - Store user and policy limits
- * @no_turbo:		User requested turbo state from intel_pstate sysfs
- * @turbo_disabled:	Platform turbo status either from msr
- *			MSR_IA32_MISC_ENABLE or when maximum available pstate
- *			matches the maximum turbo pstate
- * @max_perf_pct:	Effective maximum performance limit in percentage, this
- *			is minimum of either limits enforced by cpufreq policy
- *			or limits from user set limits via intel_pstate sysfs
- * @min_perf_pct:	Effective minimum performance limit in percentage, this
- *			is maximum of either limits enforced by cpufreq policy
- *			or limits from user set limits via intel_pstate sysfs
- * @max_perf:		This is a scaled value between 0 to 255 for max_perf_pct
- *			This value is used to limit max pstate
- * @min_perf:		This is a scaled value between 0 to 255 for min_perf_pct
- *			This value is used to limit min pstate
- * @max_policy_pct:	The maximum performance in percentage enforced by
- *			cpufreq setpolicy interface
- * @max_sysfs_pct:	The maximum performance in percentage enforced by
- *			intel pstate sysfs interface, unused when per cpu
- *			controls are enforced
- * @min_policy_pct:	The minimum performance in percentage enforced by
- *			cpufreq setpolicy interface
- * @min_sysfs_pct:	The minimum performance in percentage enforced by
- *			intel pstate sysfs interface, unused when per cpu
- *			controls are enforced
- *
- * Storage for user and policy defined limits.
+ * struct global_params - Global parameters, mostly tunable via sysfs.
+ * @no_turbo:		Whether or not to use turbo P-states.
+ * @turbo_disabled:	Whethet or not turbo P-states are available at all,
+ *			based on the MSR_IA32_MISC_ENABLE value and whether or
+ *			not the maximum reported turbo P-state is different from
+ *			the maximum reported non-turbo one.
+ * @min_perf_pct:	Minimum capacity limit in percent of the maximum turbo
+ *			P-state capacity.
+ * @max_perf_pct:	Maximum capacity limit in percent of the maximum turbo
+ *			P-state capacity.
  */
-struct perf_limits {
-	int no_turbo;
-	int turbo_disabled;
+struct global_params {
+	bool no_turbo;
+	bool turbo_disabled;
 	int max_perf_pct;
 	int min_perf_pct;
-	int32_t max_perf;
-	int32_t min_perf;
-	int max_policy_pct;
-	int max_sysfs_pct;
-	int min_policy_pct;
-	int min_sysfs_pct;
 };
 
 /**
@@ -240,9 +231,10 @@ struct perf_limits {
  * @prev_cummulative_iowait: IO Wait time difference from last and
  *			current sample
  * @sample:		Storage for storing last Sample data
- * @perf_limits:	Pointer to perf_limit unique to this CPU
- *			Not all field in the structure are applicable
- *			when per cpu controls are enforced
+ * @min_perf:		Minimum capacity limit as a fraction of the maximum
+ *			turbo P-state capacity.
+ * @max_perf:		Maximum capacity limit as a fraction of the maximum
+ *			turbo P-state capacity.
  * @acpi_perf_data:	Stores ACPI perf information read from _PSS
  * @valid_pss_table:	Set to true for valid ACPI _PSS entries found
  * @epp_powersave:	Last saved HWP energy performance preference
@@ -274,7 +266,8 @@ struct cpudata {
 	u64	prev_tsc;
 	u64	prev_cummulative_iowait;
 	struct sample sample;
-	struct perf_limits *perf_limits;
+	int32_t	min_perf;
+	int32_t	max_perf;
 #ifdef CONFIG_ACPI
 	struct acpi_processor_performance acpi_perf_data;
 	bool valid_pss_table;
@@ -319,7 +312,7 @@ struct pstate_adjust_policy {
  * @get_scaling:	Callback to get frequency scaling factor
  * @get_val:		Callback to convert P state to actual MSR write value
  * @get_vid:		Callback to get VID data for Atom platforms
- * @get_target_pstate:	Callback to a function to calculate next P state to use
+ * @update_util:	Active mode utilization update callback.
  *
  * Core and Atom CPU models have different way to get P State limits. This
  * structure is used to store those callbacks.
@@ -332,52 +325,31 @@ struct pstate_funcs {
 	int (*get_scaling)(void);
 	u64 (*get_val)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
-	int32_t (*get_target_pstate)(struct cpudata *);
+	void (*update_util)(struct update_util_data *data, u64 time,
+			    unsigned int flags);
 };
 
-/**
- * struct cpu_defaults- Per CPU model default config data
- * @pid_policy:	PID config data
- * @funcs:		Callback function data
- */
-struct cpu_defaults {
-	struct pstate_adjust_policy pid_policy;
-	struct pstate_funcs funcs;
+static struct pstate_funcs pstate_funcs __read_mostly;
+static struct pstate_adjust_policy pid_params __read_mostly = {
+	.sample_rate_ms = 10,
+	.sample_rate_ns = 10 * NSEC_PER_MSEC,
+	.deadband = 0,
+	.setpoint = 97,
+	.p_gain_pct = 20,
+	.d_gain_pct = 0,
+	.i_gain_pct = 0,
 };
 
-static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
-static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
-
-static struct pstate_adjust_policy pid_params __read_mostly;
-static struct pstate_funcs pstate_funcs __read_mostly;
 static int hwp_active __read_mostly;
 static bool per_cpu_limits __read_mostly;
 
-static bool driver_registered __read_mostly;
+static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
 #ifdef CONFIG_ACPI
 static bool acpi_ppc;
 #endif
 
-static struct perf_limits performance_limits;
-static struct perf_limits powersave_limits;
-static struct perf_limits *limits;
-
-static void intel_pstate_init_limits(struct perf_limits *limits)
-{
-	memset(limits, 0, sizeof(*limits));
-	limits->max_perf_pct = 100;
-	limits->max_perf = int_ext_tofp(1);
-	limits->max_policy_pct = 100;
-	limits->max_sysfs_pct = 100;
-}
-
-static void intel_pstate_set_performance_limits(struct perf_limits *limits)
-{
-	intel_pstate_init_limits(limits);
-	limits->min_perf_pct = 100;
-	limits->min_perf = int_ext_tofp(1);
-}
+static struct global_params global;
 
 static DEFINE_MUTEX(intel_pstate_driver_lock);
 static DEFINE_MUTEX(intel_pstate_limits_lock);
@@ -501,7 +473,7 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 	 * correct max turbo frequency based on the turbo state.
 	 * Also need to convert to MHz as _PSS freq is in MHz.
 	 */
-	if (!limits->turbo_disabled)
+	if (!global.turbo_disabled)
 		cpu->acpi_perf_data.states[0].core_frequency =
 					policy->cpuinfo.max_freq / 1000;
 	cpu->valid_pss_table = true;
@@ -534,29 +506,6 @@ static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
 }
 #endif
 
-static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
-			     int deadband, int integral) {
-	pid->setpoint = int_tofp(setpoint);
-	pid->deadband  = int_tofp(deadband);
-	pid->integral  = int_tofp(integral);
-	pid->last_err  = int_tofp(setpoint) - int_tofp(busy);
-}
-
-static inline void pid_p_gain_set(struct _pid *pid, int percent)
-{
-	pid->p_gain = div_fp(percent, 100);
-}
-
-static inline void pid_i_gain_set(struct _pid *pid, int percent)
-{
-	pid->i_gain = div_fp(percent, 100);
-}
-
-static inline void pid_d_gain_set(struct _pid *pid, int percent)
-{
-	pid->d_gain = div_fp(percent, 100);
-}
-
 static signed int pid_calc(struct _pid *pid, int32_t busy)
 {
 	signed int result;
@@ -594,23 +543,17 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
 	return (signed int)fp_toint(result);
 }
 
-static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu)
+static inline void intel_pstate_pid_reset(struct cpudata *cpu)
 {
-	pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct);
-	pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct);
-	pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct);
+	struct _pid *pid = &cpu->pid;
 
-	pid_reset(&cpu->pid, pid_params.setpoint, 100, pid_params.deadband, 0);
-}
-
-static inline void intel_pstate_reset_all_pid(void)
-{
-	unsigned int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (all_cpu_data[cpu])
-			intel_pstate_busy_pid_reset(all_cpu_data[cpu]);
-	}
+	pid->p_gain = percent_fp(pid_params.p_gain_pct);
+	pid->d_gain = percent_fp(pid_params.d_gain_pct);
+	pid->i_gain = percent_fp(pid_params.i_gain_pct);
+	pid->setpoint = int_tofp(pid_params.setpoint);
+	pid->last_err  = pid->setpoint - int_tofp(100);
+	pid->deadband  = int_tofp(pid_params.deadband);
+	pid->integral  = 0;
 }
 
 static inline void update_turbo_state(void)
@@ -620,11 +563,19 @@ static inline void update_turbo_state(void)
 
 	cpu = all_cpu_data[0];
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
-	limits->turbo_disabled =
+	global.turbo_disabled =
 		(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
 		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
 }
 
+static int min_perf_pct_min(void)
+{
+	struct cpudata *cpu = all_cpu_data[0];
+
+	return DIV_ROUND_UP(cpu->pstate.min_pstate * 100,
+			    cpu->pstate.turbo_pstate);
+}
+
 static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
 {
 	u64 epb;
@@ -842,99 +793,80 @@ static struct freq_attr *hwp_cpufreq_attrs[] = {
 	NULL,
 };
 
-static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
+static void intel_pstate_hwp_set(unsigned int cpu)
 {
-	int min, hw_min, max, hw_max, cpu, range, adj_range;
-	struct perf_limits *perf_limits = limits;
+	struct cpudata *cpu_data = all_cpu_data[cpu];
+	int min, hw_min, max, hw_max;
 	u64 value, cap;
+	s16 epp;
 
-	for_each_cpu(cpu, policy->cpus) {
-		int max_perf_pct, min_perf_pct;
-		struct cpudata *cpu_data = all_cpu_data[cpu];
-		s16 epp;
-
-		if (per_cpu_limits)
-			perf_limits = all_cpu_data[cpu]->perf_limits;
-
-		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
-		hw_min = HWP_LOWEST_PERF(cap);
-		if (limits->no_turbo)
-			hw_max = HWP_GUARANTEED_PERF(cap);
-		else
-			hw_max = HWP_HIGHEST_PERF(cap);
-		range = hw_max - hw_min;
+	rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+	hw_min = HWP_LOWEST_PERF(cap);
+	if (global.no_turbo)
+		hw_max = HWP_GUARANTEED_PERF(cap);
+	else
+		hw_max = HWP_HIGHEST_PERF(cap);
 
-		max_perf_pct = perf_limits->max_perf_pct;
-		min_perf_pct = perf_limits->min_perf_pct;
+	max = fp_ext_toint(hw_max * cpu_data->max_perf);
+	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
+		min = max;
+	else
+		min = fp_ext_toint(hw_max * cpu_data->min_perf);
 
-		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
-		adj_range = min_perf_pct * range / 100;
-		min = hw_min + adj_range;
-		value &= ~HWP_MIN_PERF(~0L);
-		value |= HWP_MIN_PERF(min);
+	rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
 
-		adj_range = max_perf_pct * range / 100;
-		max = hw_min + adj_range;
+	value &= ~HWP_MIN_PERF(~0L);
+	value |= HWP_MIN_PERF(min);
 
-		value &= ~HWP_MAX_PERF(~0L);
-		value |= HWP_MAX_PERF(max);
+	value &= ~HWP_MAX_PERF(~0L);
+	value |= HWP_MAX_PERF(max);
 
-		if (cpu_data->epp_policy == cpu_data->policy)
-			goto skip_epp;
+	if (cpu_data->epp_policy == cpu_data->policy)
+		goto skip_epp;
 
-		cpu_data->epp_policy = cpu_data->policy;
+	cpu_data->epp_policy = cpu_data->policy;
 
-		if (cpu_data->epp_saved >= 0) {
-			epp = cpu_data->epp_saved;
-			cpu_data->epp_saved = -EINVAL;
-			goto update_epp;
-		}
-
-		if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
-			epp = intel_pstate_get_epp(cpu_data, value);
-			cpu_data->epp_powersave = epp;
-			/* If EPP read was failed, then don't try to write */
-			if (epp < 0)
-				goto skip_epp;
+	if (cpu_data->epp_saved >= 0) {
+		epp = cpu_data->epp_saved;
+		cpu_data->epp_saved = -EINVAL;
+		goto update_epp;
+	}
 
+	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		epp = intel_pstate_get_epp(cpu_data, value);
+		cpu_data->epp_powersave = epp;
+		/* If EPP read was failed, then don't try to write */
+		if (epp < 0)
+			goto skip_epp;
 
-			epp = 0;
-		} else {
-			/* skip setting EPP, when saved value is invalid */
-			if (cpu_data->epp_powersave < 0)
-				goto skip_epp;
+		epp = 0;
+	} else {
+		/* skip setting EPP, when saved value is invalid */
+		if (cpu_data->epp_powersave < 0)
+			goto skip_epp;
 
-			/*
-			 * No need to restore EPP when it is not zero. This
-			 * means:
-			 *  - Policy is not changed
-			 *  - user has manually changed
-			 *  - Error reading EPB
-			 */
-			epp = intel_pstate_get_epp(cpu_data, value);
-			if (epp)
-				goto skip_epp;
+		/*
+		 * No need to restore EPP when it is not zero. This
+		 * means:
+		 *  - Policy is not changed
+		 *  - user has manually changed
+		 *  - Error reading EPB
+		 */
+		epp = intel_pstate_get_epp(cpu_data, value);
+		if (epp)
+			goto skip_epp;
 
-			epp = cpu_data->epp_powersave;
-		}
+		epp = cpu_data->epp_powersave;
+	}
 update_epp:
-		if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
-			value &= ~GENMASK_ULL(31, 24);
-			value |= (u64)epp << 24;
-		} else {
-			intel_pstate_set_epb(cpu, epp);
-		}
-skip_epp:
-		wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
+	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+		value &= ~GENMASK_ULL(31, 24);
+		value |= (u64)epp << 24;
+	} else {
+		intel_pstate_set_epb(cpu, epp);
 	}
-}
-
-static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy)
-{
-	if (hwp_active)
-		intel_pstate_hwp_set(policy);
-
-	return 0;
+skip_epp:
+	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 }
 
 static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
@@ -951,20 +883,17 @@ static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
 
 static int intel_pstate_resume(struct cpufreq_policy *policy)
 {
-	int ret;
-
 	if (!hwp_active)
 		return 0;
 
 	mutex_lock(&intel_pstate_limits_lock);
 
 	all_cpu_data[policy->cpu]->epp_policy = 0;
-
-	ret = intel_pstate_hwp_set_policy(policy);
+	intel_pstate_hwp_set(policy->cpu);
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
-	return ret;
+	return 0;
 }
 
 static void intel_pstate_update_policies(void)
@@ -978,8 +907,14 @@ static void intel_pstate_update_policies(void)
 /************************** debugfs begin ************************/
 static int pid_param_set(void *data, u64 val)
 {
+	unsigned int cpu;
+
 	*(u32 *)data = val;
-	intel_pstate_reset_all_pid();
+	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
+	for_each_possible_cpu(cpu)
+		if (all_cpu_data[cpu])
+			intel_pstate_pid_reset(all_cpu_data[cpu]);
+
 	return 0;
 }
 
@@ -1050,7 +985,7 @@ static void intel_pstate_debug_hide_params(void)
 	static ssize_t show_##file_name					\
 	(struct kobject *kobj, struct attribute *attr, char *buf)	\
 	{								\
-		return sprintf(buf, "%u\n", limits->object);		\
+		return sprintf(buf, "%u\n", global.object);		\
 	}
 
 static ssize_t intel_pstate_show_status(char *buf);
@@ -1090,7 +1025,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 
 	mutex_lock(&intel_pstate_driver_lock);
 
-	if (!driver_registered) {
+	if (!intel_pstate_driver) {
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EAGAIN;
 	}
@@ -1115,7 +1050,7 @@ static ssize_t show_num_pstates(struct kobject *kobj,
 
 	mutex_lock(&intel_pstate_driver_lock);
 
-	if (!driver_registered) {
+	if (!intel_pstate_driver) {
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EAGAIN;
 	}
@@ -1135,16 +1070,16 @@ static ssize_t show_no_turbo(struct kobject *kobj,
 
 	mutex_lock(&intel_pstate_driver_lock);
 
-	if (!driver_registered) {
+	if (!intel_pstate_driver) {
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EAGAIN;
 	}
 
 	update_turbo_state();
-	if (limits->turbo_disabled)
-		ret = sprintf(buf, "%u\n", limits->turbo_disabled);
+	if (global.turbo_disabled)
+		ret = sprintf(buf, "%u\n", global.turbo_disabled);
 	else
-		ret = sprintf(buf, "%u\n", limits->no_turbo);
+		ret = sprintf(buf, "%u\n", global.no_turbo);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -1163,7 +1098,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	mutex_lock(&intel_pstate_driver_lock);
 
-	if (!driver_registered) {
+	if (!intel_pstate_driver) {
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EAGAIN;
 	}
@@ -1171,14 +1106,23 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	mutex_lock(&intel_pstate_limits_lock);
 
 	update_turbo_state();
-	if (limits->turbo_disabled) {
+	if (global.turbo_disabled) {
 		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
 		mutex_unlock(&intel_pstate_limits_lock);
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EPERM;
 	}
 
-	limits->no_turbo = clamp_t(int, input, 0, 1);
+	global.no_turbo = clamp_t(int, input, 0, 1);
+
+	if (global.no_turbo) {
+		struct cpudata *cpu = all_cpu_data[0];
+		int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate;
+
+		/* Squash the global minimum into the permitted range. */
+		if (global.min_perf_pct > pct)
+			global.min_perf_pct = pct;
+	}
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
@@ -1201,21 +1145,14 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 
 	mutex_lock(&intel_pstate_driver_lock);
 
-	if (!driver_registered) {
+	if (!intel_pstate_driver) {
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EAGAIN;
 	}
 
 	mutex_lock(&intel_pstate_limits_lock);
 
-	limits->max_sysfs_pct = clamp_t(int, input, 0 , 100);
-	limits->max_perf_pct = min(limits->max_policy_pct,
-				   limits->max_sysfs_pct);
-	limits->max_perf_pct = max(limits->min_policy_pct,
-				   limits->max_perf_pct);
-	limits->max_perf_pct = max(limits->min_perf_pct,
-				   limits->max_perf_pct);
-	limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
+	global.max_perf_pct = clamp_t(int, input, global.min_perf_pct, 100);
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
@@ -1238,21 +1175,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 
 	mutex_lock(&intel_pstate_driver_lock);
 
-	if (!driver_registered) {
+	if (!intel_pstate_driver) {
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EAGAIN;
 	}
 
 	mutex_lock(&intel_pstate_limits_lock);
 
-	limits->min_sysfs_pct = clamp_t(int, input, 0 , 100);
-	limits->min_perf_pct = max(limits->min_policy_pct,
-				   limits->min_sysfs_pct);
-	limits->min_perf_pct = min(limits->max_policy_pct,
-				   limits->min_perf_pct);
-	limits->min_perf_pct = min(limits->max_perf_pct,
-				   limits->min_perf_pct);
-	limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
+	global.min_perf_pct = clamp_t(int, input,
+				      min_perf_pct_min(), global.max_perf_pct);
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
@@ -1377,7 +1308,7 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate)
 	u32 vid;
 
 	val = (u64)pstate << 8;
-	if (limits->no_turbo && !limits->turbo_disabled)
+	if (global.no_turbo && !global.turbo_disabled)
 		val |= (u64)1 << 32;
 
 	vid_fp = cpudata->vid.min + mul_fp(
@@ -1547,7 +1478,7 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate)
 	u64 val;
 
 	val = (u64)pstate << 8;
-	if (limits->no_turbo && !limits->turbo_disabled)
+	if (global.no_turbo && !global.turbo_disabled)
 		val |= (u64)1 << 32;
 
 	return val;
@@ -1566,132 +1497,10 @@ static int knl_get_turbo_pstate(void)
 	return ret;
 }
 
-static struct cpu_defaults core_params = {
-	.pid_policy = {
-		.sample_rate_ms = 10,
-		.deadband = 0,
-		.setpoint = 97,
-		.p_gain_pct = 20,
-		.d_gain_pct = 0,
-		.i_gain_pct = 0,
-	},
-	.funcs = {
-		.get_max = core_get_max_pstate,
-		.get_max_physical = core_get_max_pstate_physical,
-		.get_min = core_get_min_pstate,
-		.get_turbo = core_get_turbo_pstate,
-		.get_scaling = core_get_scaling,
-		.get_val = core_get_val,
-		.get_target_pstate = get_target_pstate_use_performance,
-	},
-};
-
-static const struct cpu_defaults silvermont_params = {
-	.pid_policy = {
-		.sample_rate_ms = 10,
-		.deadband = 0,
-		.setpoint = 60,
-		.p_gain_pct = 14,
-		.d_gain_pct = 0,
-		.i_gain_pct = 4,
-	},
-	.funcs = {
-		.get_max = atom_get_max_pstate,
-		.get_max_physical = atom_get_max_pstate,
-		.get_min = atom_get_min_pstate,
-		.get_turbo = atom_get_turbo_pstate,
-		.get_val = atom_get_val,
-		.get_scaling = silvermont_get_scaling,
-		.get_vid = atom_get_vid,
-		.get_target_pstate = get_target_pstate_use_cpu_load,
-	},
-};
-
-static const struct cpu_defaults airmont_params = {
-	.pid_policy = {
-		.sample_rate_ms = 10,
-		.deadband = 0,
-		.setpoint = 60,
-		.p_gain_pct = 14,
-		.d_gain_pct = 0,
-		.i_gain_pct = 4,
-	},
-	.funcs = {
-		.get_max = atom_get_max_pstate,
-		.get_max_physical = atom_get_max_pstate,
-		.get_min = atom_get_min_pstate,
-		.get_turbo = atom_get_turbo_pstate,
-		.get_val = atom_get_val,
-		.get_scaling = airmont_get_scaling,
-		.get_vid = atom_get_vid,
-		.get_target_pstate = get_target_pstate_use_cpu_load,
-	},
-};
-
-static const struct cpu_defaults knl_params = {
-	.pid_policy = {
-		.sample_rate_ms = 10,
-		.deadband = 0,
-		.setpoint = 97,
-		.p_gain_pct = 20,
-		.d_gain_pct = 0,
-		.i_gain_pct = 0,
-	},
-	.funcs = {
-		.get_max = core_get_max_pstate,
-		.get_max_physical = core_get_max_pstate_physical,
-		.get_min = core_get_min_pstate,
-		.get_turbo = knl_get_turbo_pstate,
-		.get_scaling = core_get_scaling,
-		.get_val = core_get_val,
-		.get_target_pstate = get_target_pstate_use_performance,
-	},
-};
-
-static const struct cpu_defaults bxt_params = {
-	.pid_policy = {
-		.sample_rate_ms = 10,
-		.deadband = 0,
-		.setpoint = 60,
-		.p_gain_pct = 14,
-		.d_gain_pct = 0,
-		.i_gain_pct = 4,
-	},
-	.funcs = {
-		.get_max = core_get_max_pstate,
-		.get_max_physical = core_get_max_pstate_physical,
-		.get_min = core_get_min_pstate,
-		.get_turbo = core_get_turbo_pstate,
-		.get_scaling = core_get_scaling,
-		.get_val = core_get_val,
-		.get_target_pstate = get_target_pstate_use_cpu_load,
-	},
-};
-
-static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
+static int intel_pstate_get_base_pstate(struct cpudata *cpu)
 {
-	int max_perf = cpu->pstate.turbo_pstate;
-	int max_perf_adj;
-	int min_perf;
-	struct perf_limits *perf_limits = limits;
-
-	if (limits->no_turbo || limits->turbo_disabled)
-		max_perf = cpu->pstate.max_pstate;
-
-	if (per_cpu_limits)
-		perf_limits = cpu->perf_limits;
-
-	/*
-	 * performance can be limited by user through sysfs, by cpufreq
-	 * policy, or by cpu specific default values determined through
-	 * experimentation.
-	 */
-	max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf);
-	*max = clamp_t(int, max_perf_adj,
-			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
-
-	min_perf = fp_ext_toint(max_perf * perf_limits->min_perf);
-	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
+	return global.no_turbo || global.turbo_disabled ?
+			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 }
 
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
@@ -1714,11 +1523,13 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 
 static void intel_pstate_max_within_limits(struct cpudata *cpu)
 {
-	int min_pstate, max_pstate;
+	int pstate;
 
 	update_turbo_state();
-	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
-	intel_pstate_set_pstate(cpu, max_pstate);
+	pstate = intel_pstate_get_base_pstate(cpu);
+	pstate = max(cpu->pstate.min_pstate,
+		     fp_ext_toint(pstate * cpu->max_perf));
+	intel_pstate_set_pstate(cpu, pstate);
 }
 
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
@@ -1779,7 +1590,11 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
 	 * that sample.time will always be reset before setting the utilization
 	 * update hook and make the caller skip the sample then.
 	 */
-	return !!cpu->last_sample_time;
+	if (cpu->last_sample_time) {
+		intel_pstate_calc_avg_perf(cpu);
+		return true;
+	}
+	return false;
 }
 
 static inline int32_t get_avg_frequency(struct cpudata *cpu)
@@ -1800,6 +1615,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 	int32_t busy_frac, boost;
 	int target, avg_pstate;
 
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
+		return cpu->pstate.turbo_pstate;
+
 	busy_frac = div_fp(sample->mperf, sample->tsc);
 
 	boost = cpu->iowait_boost;
@@ -1810,7 +1628,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 
 	sample->busy_scaled = busy_frac * 100;
 
-	target = limits->no_turbo || limits->turbo_disabled ?
+	target = global.no_turbo || global.turbo_disabled ?
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	target += target >> 2;
 	target = mul_fp(target, busy_frac);
@@ -1836,6 +1654,9 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	int32_t perf_scaled, max_pstate, current_pstate, sample_ratio;
 	u64 duration_ns;
 
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
+		return cpu->pstate.turbo_pstate;
+
 	/*
 	 * perf_scaled is the ratio of the average P-state during the last
 	 * sampling period to the P-state requested last time (in percent).
@@ -1870,17 +1691,17 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 
 static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
 {
-	int max_perf, min_perf;
+	int max_pstate = intel_pstate_get_base_pstate(cpu);
+	int min_pstate;
 
-	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
-	pstate = clamp_t(int, pstate, min_perf, max_perf);
-	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
-	return pstate;
+	min_pstate = max(cpu->pstate.min_pstate,
+			 fp_ext_toint(max_pstate * cpu->min_perf));
+	max_pstate = max(min_pstate, fp_ext_toint(max_pstate * cpu->max_perf));
+	return clamp_t(int, pstate, min_pstate, max_pstate);
 }
 
 static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
 {
-	pstate = intel_pstate_prepare_request(cpu, pstate);
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
@@ -1888,18 +1709,15 @@ static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
 	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
 }
 
-static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
+static void intel_pstate_adjust_pstate(struct cpudata *cpu, int target_pstate)
 {
-	int from, target_pstate;
+	int from = cpu->pstate.current_pstate;
 	struct sample *sample;
 
-	from = cpu->pstate.current_pstate;
-
-	target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
-		cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
-
 	update_turbo_state();
 
+	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
 	intel_pstate_update_pstate(cpu, target_pstate);
 
 	sample = &cpu->sample;
@@ -1914,76 +1732,155 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 		fp_toint(cpu->iowait_boost * 100));
 }
 
+static void intel_pstate_update_util_hwp(struct update_util_data *data,
+					 u64 time, unsigned int flags)
+{
+	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+	u64 delta_ns = time - cpu->sample.time;
+
+	if ((s64)delta_ns >= INTEL_PSTATE_HWP_SAMPLING_INTERVAL)
+		intel_pstate_sample(cpu, time);
+}
+
+static void intel_pstate_update_util_pid(struct update_util_data *data,
+					 u64 time, unsigned int flags)
+{
+	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+	u64 delta_ns = time - cpu->sample.time;
+
+	if ((s64)delta_ns < pid_params.sample_rate_ns)
+		return;
+
+	if (intel_pstate_sample(cpu, time)) {
+		int target_pstate;
+
+		target_pstate = get_target_pstate_use_performance(cpu);
+		intel_pstate_adjust_pstate(cpu, target_pstate);
+	}
+}
+
 static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 				     unsigned int flags)
 {
 	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
 	u64 delta_ns;
 
-	if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) {
-		if (flags & SCHED_CPUFREQ_IOWAIT) {
-			cpu->iowait_boost = int_tofp(1);
-		} else if (cpu->iowait_boost) {
-			/* Clear iowait_boost if the CPU may have been idle. */
-			delta_ns = time - cpu->last_update;
-			if (delta_ns > TICK_NSEC)
-				cpu->iowait_boost = 0;
-		}
-		cpu->last_update = time;
+	if (flags & SCHED_CPUFREQ_IOWAIT) {
+		cpu->iowait_boost = int_tofp(1);
+	} else if (cpu->iowait_boost) {
+		/* Clear iowait_boost if the CPU may have been idle. */
+		delta_ns = time - cpu->last_update;
+		if (delta_ns > TICK_NSEC)
+			cpu->iowait_boost = 0;
 	}
-
+	cpu->last_update = time;
 	delta_ns = time - cpu->sample.time;
-	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
-		bool sample_taken = intel_pstate_sample(cpu, time);
+	if ((s64)delta_ns < INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL)
+		return;
 
-		if (sample_taken) {
-			intel_pstate_calc_avg_perf(cpu);
-			if (!hwp_active)
-				intel_pstate_adjust_busy_pstate(cpu);
-		}
+	if (intel_pstate_sample(cpu, time)) {
+		int target_pstate;
+
+		target_pstate = get_target_pstate_use_cpu_load(cpu);
+		intel_pstate_adjust_pstate(cpu, target_pstate);
 	}
 }
 
+static struct pstate_funcs core_funcs = {
+	.get_max = core_get_max_pstate,
+	.get_max_physical = core_get_max_pstate_physical,
+	.get_min = core_get_min_pstate,
+	.get_turbo = core_get_turbo_pstate,
+	.get_scaling = core_get_scaling,
+	.get_val = core_get_val,
+	.update_util = intel_pstate_update_util_pid,
+};
+
+static const struct pstate_funcs silvermont_funcs = {
+	.get_max = atom_get_max_pstate,
+	.get_max_physical = atom_get_max_pstate,
+	.get_min = atom_get_min_pstate,
+	.get_turbo = atom_get_turbo_pstate,
+	.get_val = atom_get_val,
+	.get_scaling = silvermont_get_scaling,
+	.get_vid = atom_get_vid,
+	.update_util = intel_pstate_update_util,
+};
+
+static const struct pstate_funcs airmont_funcs = {
+	.get_max = atom_get_max_pstate,
+	.get_max_physical = atom_get_max_pstate,
+	.get_min = atom_get_min_pstate,
+	.get_turbo = atom_get_turbo_pstate,
+	.get_val = atom_get_val,
+	.get_scaling = airmont_get_scaling,
+	.get_vid = atom_get_vid,
+	.update_util = intel_pstate_update_util,
+};
+
+static const struct pstate_funcs knl_funcs = {
+	.get_max = core_get_max_pstate,
+	.get_max_physical = core_get_max_pstate_physical,
+	.get_min = core_get_min_pstate,
+	.get_turbo = knl_get_turbo_pstate,
+	.get_scaling = core_get_scaling,
+	.get_val = core_get_val,
+	.update_util = intel_pstate_update_util_pid,
+};
+
+static const struct pstate_funcs bxt_funcs = {
+	.get_max = core_get_max_pstate,
+	.get_max_physical = core_get_max_pstate_physical,
+	.get_min = core_get_min_pstate,
+	.get_turbo = core_get_turbo_pstate,
+	.get_scaling = core_get_scaling,
+	.get_val = core_get_val,
+	.update_util = intel_pstate_update_util,
+};
+
 #define ICPU(model, policy) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
 			(unsigned long)&policy }
 
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
-	ICPU(INTEL_FAM6_SANDYBRIDGE, 		core_params),
-	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		core_params),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1,	silvermont_params),
-	ICPU(INTEL_FAM6_IVYBRIDGE,		core_params),
-	ICPU(INTEL_FAM6_HASWELL_CORE,		core_params),
-	ICPU(INTEL_FAM6_BROADWELL_CORE,		core_params),
-	ICPU(INTEL_FAM6_IVYBRIDGE_X,		core_params),
-	ICPU(INTEL_FAM6_HASWELL_X,		core_params),
-	ICPU(INTEL_FAM6_HASWELL_ULT,		core_params),
-	ICPU(INTEL_FAM6_HASWELL_GT3E,		core_params),
-	ICPU(INTEL_FAM6_BROADWELL_GT3E,		core_params),
-	ICPU(INTEL_FAM6_ATOM_AIRMONT,		airmont_params),
-	ICPU(INTEL_FAM6_SKYLAKE_MOBILE,		core_params),
-	ICPU(INTEL_FAM6_BROADWELL_X,		core_params),
-	ICPU(INTEL_FAM6_SKYLAKE_DESKTOP,	core_params),
-	ICPU(INTEL_FAM6_BROADWELL_XEON_D,	core_params),
-	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_params),
-	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_params),
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		bxt_params),
+	ICPU(INTEL_FAM6_SANDYBRIDGE, 		core_funcs),
+	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		core_funcs),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT1,	silvermont_funcs),
+	ICPU(INTEL_FAM6_IVYBRIDGE,		core_funcs),
+	ICPU(INTEL_FAM6_HASWELL_CORE,		core_funcs),
+	ICPU(INTEL_FAM6_BROADWELL_CORE,		core_funcs),
+	ICPU(INTEL_FAM6_IVYBRIDGE_X,		core_funcs),
+	ICPU(INTEL_FAM6_HASWELL_X,		core_funcs),
+	ICPU(INTEL_FAM6_HASWELL_ULT,		core_funcs),
+	ICPU(INTEL_FAM6_HASWELL_GT3E,		core_funcs),
+	ICPU(INTEL_FAM6_BROADWELL_GT3E,		core_funcs),
+	ICPU(INTEL_FAM6_ATOM_AIRMONT,		airmont_funcs),
+	ICPU(INTEL_FAM6_SKYLAKE_MOBILE,		core_funcs),
+	ICPU(INTEL_FAM6_BROADWELL_X,		core_funcs),
+	ICPU(INTEL_FAM6_SKYLAKE_DESKTOP,	core_funcs),
+	ICPU(INTEL_FAM6_BROADWELL_XEON_D,	core_funcs),
+	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_funcs),
+	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_funcs),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		bxt_funcs),
+	ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE,       bxt_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
 
 static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
-	ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
-	ICPU(INTEL_FAM6_BROADWELL_X, core_params),
-	ICPU(INTEL_FAM6_SKYLAKE_X, core_params),
+	ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs),
+	ICPU(INTEL_FAM6_BROADWELL_X, core_funcs),
+	ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
 	{}
 };
 
 static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
-	ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params),
+	ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_funcs),
 	{}
 };
 
+static bool pid_in_use(void);
+
 static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
@@ -1991,18 +1888,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu = all_cpu_data[cpunum];
 
 	if (!cpu) {
-		unsigned int size = sizeof(struct cpudata);
-
-		if (per_cpu_limits)
-			size += sizeof(struct perf_limits);
-
-		cpu = kzalloc(size, GFP_KERNEL);
+		cpu = kzalloc(sizeof(*cpu), GFP_KERNEL);
 		if (!cpu)
 			return -ENOMEM;
 
 		all_cpu_data[cpunum] = cpu;
-		if (per_cpu_limits)
-			cpu->perf_limits = (struct perf_limits *)(cpu + 1);
 
 		cpu->epp_default = -EINVAL;
 		cpu->epp_powersave = -EINVAL;
@@ -2021,14 +1911,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 			intel_pstate_disable_ee(cpunum);
 
 		intel_pstate_hwp_enable(cpu);
-		pid_params.sample_rate_ms = 50;
-		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
+	} else if (pid_in_use()) {
+		intel_pstate_pid_reset(cpu);
 	}
 
 	intel_pstate_get_cpu_pstates(cpu);
 
-	intel_pstate_busy_pid_reset(cpu);
-
 	pr_debug("controlling: cpu %d\n", cpunum);
 
 	return 0;
@@ -2051,7 +1939,7 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
 	/* Prevent intel_pstate_update_util() from using stale data. */
 	cpu->sample.time = 0;
 	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
-				     intel_pstate_update_util);
+				     pstate_funcs.update_util);
 	cpu->update_util_set = true;
 }
 
@@ -2067,48 +1955,68 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu)
 	synchronize_sched();
 }
 
+static int intel_pstate_get_max_freq(struct cpudata *cpu)
+{
+	return global.turbo_disabled || global.no_turbo ?
+			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+}
+
 static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
-					    struct perf_limits *limits)
+					    struct cpudata *cpu)
 {
+	int max_freq = intel_pstate_get_max_freq(cpu);
+	int32_t max_policy_perf, min_policy_perf;
 
-	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
-					      policy->cpuinfo.max_freq);
-	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0, 100);
+	max_policy_perf = div_ext_fp(policy->max, max_freq);
+	max_policy_perf = clamp_t(int32_t, max_policy_perf, 0, int_ext_tofp(1));
 	if (policy->max == policy->min) {
-		limits->min_policy_pct = limits->max_policy_pct;
+		min_policy_perf = max_policy_perf;
 	} else {
-		limits->min_policy_pct = DIV_ROUND_UP(policy->min * 100,
-						      policy->cpuinfo.max_freq);
-		limits->min_policy_pct = clamp_t(int, limits->min_policy_pct,
-						 0, 100);
+		min_policy_perf = div_ext_fp(policy->min, max_freq);
+		min_policy_perf = clamp_t(int32_t, min_policy_perf,
+					  0, max_policy_perf);
 	}
 
-	/* Normalize user input to [min_policy_pct, max_policy_pct] */
-	limits->min_perf_pct = max(limits->min_policy_pct,
-				   limits->min_sysfs_pct);
-	limits->min_perf_pct = min(limits->max_policy_pct,
-				   limits->min_perf_pct);
-	limits->max_perf_pct = min(limits->max_policy_pct,
-				   limits->max_sysfs_pct);
-	limits->max_perf_pct = max(limits->min_policy_pct,
-				   limits->max_perf_pct);
+	/* Normalize user input to [min_perf, max_perf] */
+	if (per_cpu_limits) {
+		cpu->min_perf = min_policy_perf;
+		cpu->max_perf = max_policy_perf;
+	} else {
+		int32_t global_min, global_max;
+
+		/* Global limits are in percent of the maximum turbo P-state. */
+		global_max = percent_ext_fp(global.max_perf_pct);
+		global_min = percent_ext_fp(global.min_perf_pct);
+		if (max_freq != cpu->pstate.turbo_freq) {
+			int32_t turbo_factor;
+
+			turbo_factor = div_ext_fp(cpu->pstate.turbo_pstate,
+						  cpu->pstate.max_pstate);
+			global_min = mul_ext_fp(global_min, turbo_factor);
+			global_max = mul_ext_fp(global_max, turbo_factor);
+		}
+		global_min = clamp_t(int32_t, global_min, 0, global_max);
 
-	/* Make sure min_perf_pct <= max_perf_pct */
-	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
+		cpu->min_perf = max(min_policy_perf, global_min);
+		cpu->min_perf = min(cpu->min_perf, max_policy_perf);
+		cpu->max_perf = min(max_policy_perf, global_max);
+		cpu->max_perf = max(min_policy_perf, cpu->max_perf);
+
+		/* Make sure min_perf <= max_perf */
+		cpu->min_perf = min(cpu->min_perf, cpu->max_perf);
+	}
 
-	limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
-	limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
-	limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS);
-	limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS);
+	cpu->max_perf = round_up(cpu->max_perf, EXT_FRAC_BITS);
+	cpu->min_perf = round_up(cpu->min_perf, EXT_FRAC_BITS);
 
 	pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu,
-		 limits->max_perf_pct, limits->min_perf_pct);
+		 fp_ext_toint(cpu->max_perf * 100),
+		 fp_ext_toint(cpu->min_perf * 100));
 }
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
-	struct perf_limits *perf_limits = NULL;
 
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
@@ -2119,40 +2027,10 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	cpu = all_cpu_data[policy->cpu];
 	cpu->policy = policy->policy;
 
-	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
-	    policy->max < policy->cpuinfo.max_freq &&
-	    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
-		pr_debug("policy->max > max non turbo frequency\n");
-		policy->max = policy->cpuinfo.max_freq;
-	}
-
-	if (per_cpu_limits)
-		perf_limits = cpu->perf_limits;
-
 	mutex_lock(&intel_pstate_limits_lock);
 
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
-		if (!perf_limits) {
-			limits = &performance_limits;
-			perf_limits = limits;
-		}
-		if (policy->max >= policy->cpuinfo.max_freq &&
-		    !limits->no_turbo) {
-			pr_debug("set performance\n");
-			intel_pstate_set_performance_limits(perf_limits);
-			goto out;
-		}
-	} else {
-		pr_debug("set powersave\n");
-		if (!perf_limits) {
-			limits = &powersave_limits;
-			perf_limits = limits;
-		}
-
-	}
+	intel_pstate_update_perf_limits(policy, cpu);
 
-	intel_pstate_update_perf_limits(policy, perf_limits);
- out:
 	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		/*
 		 * NOHZ_FULL CPUs need this as the governor callback may not
@@ -2164,45 +2042,38 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	intel_pstate_set_update_util_hook(policy->cpu);
 
-	intel_pstate_hwp_set_policy(policy);
+	if (hwp_active)
+		intel_pstate_hwp_set(policy->cpu);
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
 	return 0;
 }
 
+static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
+					 struct cpudata *cpu)
+{
+	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+	    policy->max < policy->cpuinfo.max_freq &&
+	    policy->max > cpu->pstate.max_freq) {
+		pr_debug("policy->max > max non turbo frequency\n");
+		policy->max = policy->cpuinfo.max_freq;
+	}
+}
+
 static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
-	struct perf_limits *perf_limits;
-
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
-		perf_limits = &performance_limits;
-	else
-		perf_limits = &powersave_limits;
 
 	update_turbo_state();
-	policy->cpuinfo.max_freq = perf_limits->turbo_disabled ||
-					perf_limits->no_turbo ?
-					cpu->pstate.max_freq :
-					cpu->pstate.turbo_freq;
-
-	cpufreq_verify_within_cpu_limits(policy);
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     intel_pstate_get_max_freq(cpu));
 
 	if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
 	    policy->policy != CPUFREQ_POLICY_PERFORMANCE)
 		return -EINVAL;
 
-	/* When per-CPU limits are used, sysfs limits are not used */
-	if (!per_cpu_limits) {
-		unsigned int max_freq, min_freq;
-
-		max_freq = policy->cpuinfo.max_freq *
-						limits->max_sysfs_pct / 100;
-		min_freq = policy->cpuinfo.max_freq *
-						limits->min_sysfs_pct / 100;
-		cpufreq_verify_within_limits(policy, min_freq, max_freq);
-	}
+	intel_pstate_adjust_policy_max(policy, cpu);
 
 	return 0;
 }
@@ -2243,13 +2114,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	/*
-	 * We need sane value in the cpu->perf_limits, so inherit from global
-	 * perf_limits limits, which are seeded with values based on the
-	 * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up.
-	 */
-	if (per_cpu_limits)
-		memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits));
+	cpu->max_perf = int_ext_tofp(1);
+	cpu->min_perf = 0;
 
 	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
@@ -2257,7 +2123,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	update_turbo_state();
-	policy->cpuinfo.max_freq = limits->turbo_disabled ?
+	policy->cpuinfo.max_freq = global.turbo_disabled ?
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
 
@@ -2277,7 +2143,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 		return ret;
 
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
-	if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100)
+	if (IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE))
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
@@ -2301,46 +2167,18 @@ static struct cpufreq_driver intel_pstate = {
 static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
-	struct perf_limits *perf_limits = limits;
 
 	update_turbo_state();
-	policy->cpuinfo.max_freq = limits->turbo_disabled ?
-			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     intel_pstate_get_max_freq(cpu));
 
-	cpufreq_verify_within_cpu_limits(policy);
+	intel_pstate_adjust_policy_max(policy, cpu);
 
-	if (per_cpu_limits)
-		perf_limits = cpu->perf_limits;
-
-	mutex_lock(&intel_pstate_limits_lock);
-
-	intel_pstate_update_perf_limits(policy, perf_limits);
-
-	mutex_unlock(&intel_pstate_limits_lock);
+	intel_pstate_update_perf_limits(policy, cpu);
 
 	return 0;
 }
 
-static unsigned int intel_cpufreq_turbo_update(struct cpudata *cpu,
-					       struct cpufreq_policy *policy,
-					       unsigned int target_freq)
-{
-	unsigned int max_freq;
-
-	update_turbo_state();
-
-	max_freq = limits->no_turbo || limits->turbo_disabled ?
-			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
-	policy->cpuinfo.max_freq = max_freq;
-	if (policy->max > max_freq)
-		policy->max = max_freq;
-
-	if (target_freq > max_freq)
-		target_freq = max_freq;
-
-	return target_freq;
-}
-
 static int intel_cpufreq_target(struct cpufreq_policy *policy,
 				unsigned int target_freq,
 				unsigned int relation)
@@ -2349,8 +2187,10 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 	struct cpufreq_freqs freqs;
 	int target_pstate;
 
+	update_turbo_state();
+
 	freqs.old = policy->cur;
-	freqs.new = intel_cpufreq_turbo_update(cpu, policy, target_freq);
+	freqs.new = target_freq;
 
 	cpufreq_freq_transition_begin(policy, &freqs);
 	switch (relation) {
@@ -2370,6 +2210,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 		wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
 			      pstate_funcs.get_val(cpu, target_pstate));
 	}
+	freqs.new = target_pstate * cpu->pstate.scaling;
 	cpufreq_freq_transition_end(policy, &freqs, false);
 
 	return 0;
@@ -2381,10 +2222,12 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	int target_pstate;
 
-	target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq);
+	update_turbo_state();
+
 	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
+	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
 	intel_pstate_update_pstate(cpu, target_pstate);
-	return target_freq;
+	return target_pstate * cpu->pstate.scaling;
 }
 
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
@@ -2395,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return ret;
 
 	policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
+	policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
 	/* This reflects the intel_pstate_get_cpu_pstates() setting. */
 	policy->cur = policy->cpuinfo.min_freq;
 
@@ -2412,7 +2256,13 @@ static struct cpufreq_driver intel_cpufreq = {
 	.name		= "intel_cpufreq",
 };
 
-static struct cpufreq_driver *intel_pstate_driver = &intel_pstate;
+static struct cpufreq_driver *default_driver = &intel_pstate;
+
+static bool pid_in_use(void)
+{
+	return intel_pstate_driver == &intel_pstate &&
+		pstate_funcs.update_util == intel_pstate_update_util_pid;
+}
 
 static void intel_pstate_driver_cleanup(void)
 {
@@ -2429,29 +2279,26 @@ static void intel_pstate_driver_cleanup(void)
 		}
 	}
 	put_online_cpus();
+	intel_pstate_driver = NULL;
 }
 
-static int intel_pstate_register_driver(void)
+static int intel_pstate_register_driver(struct cpufreq_driver *driver)
 {
 	int ret;
 
-	intel_pstate_init_limits(&powersave_limits);
-	intel_pstate_set_performance_limits(&performance_limits);
-	limits = IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) ?
-			&performance_limits : &powersave_limits;
+	memset(&global, 0, sizeof(global));
+	global.max_perf_pct = 100;
 
+	intel_pstate_driver = driver;
 	ret = cpufreq_register_driver(intel_pstate_driver);
 	if (ret) {
 		intel_pstate_driver_cleanup();
 		return ret;
 	}
 
-	mutex_lock(&intel_pstate_limits_lock);
-	driver_registered = true;
-	mutex_unlock(&intel_pstate_limits_lock);
+	global.min_perf_pct = min_perf_pct_min();
 
-	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
-	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+	if (pid_in_use())
 		intel_pstate_debug_expose_params();
 
 	return 0;
@@ -2462,14 +2309,9 @@ static int intel_pstate_unregister_driver(void)
 	if (hwp_active)
 		return -EBUSY;
 
-	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
-	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+	if (pid_in_use())
 		intel_pstate_debug_hide_params();
 
-	mutex_lock(&intel_pstate_limits_lock);
-	driver_registered = false;
-	mutex_unlock(&intel_pstate_limits_lock);
-
 	cpufreq_unregister_driver(intel_pstate_driver);
 	intel_pstate_driver_cleanup();
 
@@ -2478,7 +2320,7 @@ static int intel_pstate_unregister_driver(void)
 
 static ssize_t intel_pstate_show_status(char *buf)
 {
-	if (!driver_registered)
+	if (!intel_pstate_driver)
 		return sprintf(buf, "off\n");
 
 	return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
@@ -2490,11 +2332,11 @@ static int intel_pstate_update_status(const char *buf, size_t size)
 	int ret;
 
 	if (size == 3 && !strncmp(buf, "off", size))
-		return driver_registered ?
+		return intel_pstate_driver ?
 			intel_pstate_unregister_driver() : -EINVAL;
 
 	if (size == 6 && !strncmp(buf, "active", size)) {
-		if (driver_registered) {
+		if (intel_pstate_driver) {
 			if (intel_pstate_driver == &intel_pstate)
 				return 0;
 
@@ -2503,13 +2345,12 @@ static int intel_pstate_update_status(const char *buf, size_t size)
 				return ret;
 		}
 
-		intel_pstate_driver = &intel_pstate;
-		return intel_pstate_register_driver();
+		return intel_pstate_register_driver(&intel_pstate);
 	}
 
 	if (size == 7 && !strncmp(buf, "passive", size)) {
-		if (driver_registered) {
-			if (intel_pstate_driver != &intel_pstate)
+		if (intel_pstate_driver) {
+			if (intel_pstate_driver == &intel_cpufreq)
 				return 0;
 
 			ret = intel_pstate_unregister_driver();
@@ -2517,8 +2358,7 @@ static int intel_pstate_update_status(const char *buf, size_t size)
 				return ret;
 		}
 
-		intel_pstate_driver = &intel_cpufreq;
-		return intel_pstate_register_driver();
+		return intel_pstate_register_driver(&intel_cpufreq);
 	}
 
 	return -EINVAL;
@@ -2539,23 +2379,17 @@ static int __init intel_pstate_msrs_not_valid(void)
 	return 0;
 }
 
-static void __init copy_pid_params(struct pstate_adjust_policy *policy)
-{
-	pid_params.sample_rate_ms = policy->sample_rate_ms;
-	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
-	pid_params.p_gain_pct = policy->p_gain_pct;
-	pid_params.i_gain_pct = policy->i_gain_pct;
-	pid_params.d_gain_pct = policy->d_gain_pct;
-	pid_params.deadband = policy->deadband;
-	pid_params.setpoint = policy->setpoint;
-}
-
 #ifdef CONFIG_ACPI
 static void intel_pstate_use_acpi_profile(void)
 {
-	if (acpi_gbl_FADT.preferred_profile == PM_MOBILE)
-		pstate_funcs.get_target_pstate =
-				get_target_pstate_use_cpu_load;
+	switch (acpi_gbl_FADT.preferred_profile) {
+	case PM_MOBILE:
+	case PM_TABLET:
+	case PM_APPLIANCE_PC:
+	case PM_DESKTOP:
+	case PM_WORKSTATION:
+		pstate_funcs.update_util = intel_pstate_update_util;
+	}
 }
 #else
 static void intel_pstate_use_acpi_profile(void)
@@ -2572,7 +2406,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs)
 	pstate_funcs.get_scaling = funcs->get_scaling;
 	pstate_funcs.get_val   = funcs->get_val;
 	pstate_funcs.get_vid   = funcs->get_vid;
-	pstate_funcs.get_target_pstate = funcs->get_target_pstate;
+	pstate_funcs.update_util = funcs->update_util;
 
 	intel_pstate_use_acpi_profile();
 }
@@ -2711,28 +2545,30 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = {
 
 static int __init intel_pstate_init(void)
 {
-	const struct x86_cpu_id *id;
-	struct cpu_defaults *cpu_def;
-	int rc = 0;
+	int rc;
 
 	if (no_load)
 		return -ENODEV;
 
-	if (x86_match_cpu(hwp_support_ids) && !no_hwp) {
-		copy_cpu_funcs(&core_params.funcs);
-		hwp_active++;
-		intel_pstate.attr = hwp_cpufreq_attrs;
-		goto hwp_cpu_matched;
-	}
-
-	id = x86_match_cpu(intel_pstate_cpu_ids);
-	if (!id)
-		return -ENODEV;
+	if (x86_match_cpu(hwp_support_ids)) {
+		copy_cpu_funcs(&core_funcs);
+		if (no_hwp) {
+			pstate_funcs.update_util = intel_pstate_update_util;
+		} else {
+			hwp_active++;
+			intel_pstate.attr = hwp_cpufreq_attrs;
+			pstate_funcs.update_util = intel_pstate_update_util_hwp;
+			goto hwp_cpu_matched;
+		}
+	} else {
+		const struct x86_cpu_id *id;
 
-	cpu_def = (struct cpu_defaults *)id->driver_data;
+		id = x86_match_cpu(intel_pstate_cpu_ids);
+		if (!id)
+			return -ENODEV;
 
-	copy_pid_params(&cpu_def->pid_policy);
-	copy_cpu_funcs(&cpu_def->funcs);
+		copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
+	}
 
 	if (intel_pstate_msrs_not_valid())
 		return -ENODEV;
@@ -2759,7 +2595,7 @@ hwp_cpu_matched:
 	intel_pstate_sysfs_expose_params();
 
 	mutex_lock(&intel_pstate_driver_lock);
-	rc = intel_pstate_register_driver();
+	rc = intel_pstate_register_driver(default_driver);
 	mutex_unlock(&intel_pstate_driver_lock);
 	if (rc)
 		return rc;
@@ -2780,7 +2616,7 @@ static int __init intel_pstate_setup(char *str)
 		no_load = 1;
 	} else if (!strcmp(str, "passive")) {
 		pr_info("Passive mode enabled\n");
-		intel_pstate_driver = &intel_cpufreq;
+		default_driver = &intel_cpufreq;
 		no_hwp = 1;
 	}
 	if (!strcmp(str, "no_hwp")) {
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index ab25b1235a5e..fd1886faf33a 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -573,14 +573,33 @@ static struct platform_driver mt8173_cpufreq_platdrv = {
 	.probe		= mt8173_cpufreq_probe,
 };
 
-static int mt8173_cpufreq_driver_init(void)
+/* List of machines supported by this driver */
+static const struct of_device_id mt8173_cpufreq_machines[] __initconst = {
+	{ .compatible = "mediatek,mt817x", },
+	{ .compatible = "mediatek,mt8173", },
+	{ .compatible = "mediatek,mt8176", },
+
+	{ }
+};
+
+static int __init mt8173_cpufreq_driver_init(void)
 {
+	struct device_node *np;
+	const struct of_device_id *match;
 	struct platform_device *pdev;
 	int err;
 
-	if (!of_machine_is_compatible("mediatek,mt8173"))
+	np = of_find_node_by_path("/");
+	if (!np)
 		return -ENODEV;
 
+	match = of_match_node(mt8173_cpufreq_machines, np);
+	of_node_put(np);
+	if (!match) {
+		pr_warn("Machine is not compatible with mt8173-cpufreq\n");
+		return -ENODEV;
+	}
+
 	err = platform_driver_register(&mt8173_cpufreq_platdrv);
 	if (err)
 		return err;
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index bfec1bcd3835..e2ea433a5f9c 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -52,17 +52,27 @@ static u32 get_bus_freq(void)
 {
 	struct device_node *soc;
 	u32 sysfreq;
+	struct clk *pltclk;
+	int ret;
 
+	/* get platform freq by searching bus-frequency property */
 	soc = of_find_node_by_type(NULL, "soc");
-	if (!soc)
-		return 0;
-
-	if (of_property_read_u32(soc, "bus-frequency", &sysfreq))
-		sysfreq = 0;
+	if (soc) {
+		ret = of_property_read_u32(soc, "bus-frequency", &sysfreq);
+		of_node_put(soc);
+		if (!ret)
+			return sysfreq;
+	}
 
-	of_node_put(soc);
+	/* get platform freq by its clock name */
+	pltclk = clk_get(NULL, "cg-pll0-div1");
+	if (IS_ERR(pltclk)) {
+		pr_err("%s: can't get bus frequency %ld\n",
+		       __func__, PTR_ERR(pltclk));
+		return PTR_ERR(pltclk);
+	}
 
-	return sysfreq;
+	return clk_get_rate(pltclk);
 }
 
 static struct clk *cpu_to_clk(int cpu)
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 86628e22b2a3..719c3d9f07fb 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -30,54 +30,63 @@
 
 static DEFINE_PER_CPU(struct clk, sh_cpuclk);
 
+struct cpufreq_target {
+	struct cpufreq_policy	*policy;
+	unsigned int		freq;
+};
+
 static unsigned int sh_cpufreq_get(unsigned int cpu)
 {
 	return (clk_get_rate(&per_cpu(sh_cpuclk, cpu)) + 500) / 1000;
 }
 
-/*
- * Here we notify other drivers of the proposed change and the final change.
- */
-static int sh_cpufreq_target(struct cpufreq_policy *policy,
-			     unsigned int target_freq,
-			     unsigned int relation)
+static long __sh_cpufreq_target(void *arg)
 {
-	unsigned int cpu = policy->cpu;
+	struct cpufreq_target *target = arg;
+	struct cpufreq_policy *policy = target->policy;
+	int cpu = policy->cpu;
 	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
-	cpumask_t cpus_allowed;
 	struct cpufreq_freqs freqs;
 	struct device *dev;
 	long freq;
 
-	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
-	BUG_ON(smp_processor_id() != cpu);
+	if (smp_processor_id() != cpu)
+		return -ENODEV;
 
 	dev = get_cpu_device(cpu);
 
 	/* Convert target_freq from kHz to Hz */
-	freq = clk_round_rate(cpuclk, target_freq * 1000);
+	freq = clk_round_rate(cpuclk, target->freq * 1000);
 
 	if (freq < (policy->min * 1000) || freq > (policy->max * 1000))
 		return -EINVAL;
 
-	dev_dbg(dev, "requested frequency %u Hz\n", target_freq * 1000);
+	dev_dbg(dev, "requested frequency %u Hz\n", target->freq * 1000);
 
 	freqs.old	= sh_cpufreq_get(cpu);
 	freqs.new	= (freq + 500) / 1000;
 	freqs.flags	= 0;
 
-	cpufreq_freq_transition_begin(policy, &freqs);
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+	cpufreq_freq_transition_begin(target->policy, &freqs);
 	clk_set_rate(cpuclk, freq);
-	cpufreq_freq_transition_end(policy, &freqs, 0);
+	cpufreq_freq_transition_end(target->policy, &freqs, 0);
 
 	dev_dbg(dev, "set frequency %lu Hz\n", freq);
-
 	return 0;
 }
 
+/*
+ * Here we notify other drivers of the proposed change and the final change.
+ */
+static int sh_cpufreq_target(struct cpufreq_policy *policy,
+			     unsigned int target_freq,
+			     unsigned int relation)
+{
+	struct cpufreq_target data = { .policy = policy, .freq = target_freq };
+
+	return work_on_cpu(policy->cpu, __sh_cpufreq_target, &data);
+}
+
 static int sh_cpufreq_verify(struct cpufreq_policy *policy)
 {
 	struct clk *cpuclk = &per_cpu(sh_cpuclk, policy->cpu);
diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c
index 35ddb6da93aa..90f33efee5fc 100644
--- a/drivers/cpufreq/sparc-us2e-cpufreq.c
+++ b/drivers/cpufreq/sparc-us2e-cpufreq.c
@@ -118,10 +118,6 @@ static void us2e_transition(unsigned long estar, unsigned long new_bits,
 			    unsigned long clock_tick,
 			    unsigned long old_divisor, unsigned long divisor)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-
 	estar &= ~ESTAR_MODE_DIV_MASK;
 
 	/* This is based upon the state transition diagram in the IIe manual.  */
@@ -152,8 +148,6 @@ static void us2e_transition(unsigned long estar, unsigned long new_bits,
 	} else {
 		BUG();
 	}
-
-	local_irq_restore(flags);
 }
 
 static unsigned long index_to_estar_mode(unsigned int index)
@@ -229,48 +223,51 @@ static unsigned long estar_to_divisor(unsigned long estar)
 	return ret;
 }
 
+static void __us2e_freq_get(void *arg)
+{
+	unsigned long *estar = arg;
+
+	*estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
+}
+
 static unsigned int us2e_freq_get(unsigned int cpu)
 {
-	cpumask_t cpus_allowed;
 	unsigned long clock_tick, estar;
 
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
 	clock_tick = sparc64_get_clock_tick(cpu) / 1000;
-	estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
-
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+	if (smp_call_function_single(cpu, __us2e_freq_get, &estar, 1))
+		return 0;
 
 	return clock_tick / estar_to_divisor(estar);
 }
 
-static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
+static void __us2e_freq_target(void *arg)
 {
-	unsigned int cpu = policy->cpu;
+	unsigned int cpu = smp_processor_id();
+	unsigned int *index = arg;
 	unsigned long new_bits, new_freq;
 	unsigned long clock_tick, divisor, old_divisor, estar;
-	cpumask_t cpus_allowed;
-
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	new_freq = clock_tick = sparc64_get_clock_tick(cpu) / 1000;
-	new_bits = index_to_estar_mode(index);
-	divisor = index_to_divisor(index);
+	new_bits = index_to_estar_mode(*index);
+	divisor = index_to_divisor(*index);
 	new_freq /= divisor;
 
 	estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
 
 	old_divisor = estar_to_divisor(estar);
 
-	if (old_divisor != divisor)
+	if (old_divisor != divisor) {
 		us2e_transition(estar, new_bits, clock_tick * 1000,
 				old_divisor, divisor);
+	}
+}
 
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
+{
+	unsigned int cpu = policy->cpu;
 
-	return 0;
+	return smp_call_function_single(cpu, __us2e_freq_target, &index, 1);
 }
 
 static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy)
diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c
index a8d86a449ca1..30645b0118f9 100644
--- a/drivers/cpufreq/sparc-us3-cpufreq.c
+++ b/drivers/cpufreq/sparc-us3-cpufreq.c
@@ -35,22 +35,28 @@ static struct us3_freq_percpu_info *us3_freq_table;
 #define SAFARI_CFG_DIV_32	0x0000000080000000UL
 #define SAFARI_CFG_DIV_MASK	0x00000000C0000000UL
 
-static unsigned long read_safari_cfg(void)
+static void read_safari_cfg(void *arg)
 {
-	unsigned long ret;
+	unsigned long ret, *val = arg;
 
 	__asm__ __volatile__("ldxa	[%%g0] %1, %0"
 			     : "=&r" (ret)
 			     : "i" (ASI_SAFARI_CONFIG));
-	return ret;
+	*val = ret;
 }
 
-static void write_safari_cfg(unsigned long val)
+static void update_safari_cfg(void *arg)
 {
+	unsigned long reg, *new_bits = arg;
+
+	read_safari_cfg(&reg);
+	reg &= ~SAFARI_CFG_DIV_MASK;
+	reg |= *new_bits;
+
 	__asm__ __volatile__("stxa	%0, [%%g0] %1\n\t"
 			     "membar	#Sync"
 			     : /* no outputs */
-			     : "r" (val), "i" (ASI_SAFARI_CONFIG)
+			     : "r" (reg), "i" (ASI_SAFARI_CONFIG)
 			     : "memory");
 }
 
@@ -78,29 +84,17 @@ static unsigned long get_current_freq(unsigned int cpu, unsigned long safari_cfg
 
 static unsigned int us3_freq_get(unsigned int cpu)
 {
-	cpumask_t cpus_allowed;
 	unsigned long reg;
-	unsigned int ret;
-
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
-	reg = read_safari_cfg();
-	ret = get_current_freq(cpu, reg);
-
-	set_cpus_allowed_ptr(current, &cpus_allowed);
 
-	return ret;
+	if (smp_call_function_single(cpu, read_safari_cfg, &reg, 1))
+		return 0;
+	return get_current_freq(cpu, reg);
 }
 
 static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	unsigned int cpu = policy->cpu;
-	unsigned long new_bits, new_freq, reg;
-	cpumask_t cpus_allowed;
-
-	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+	unsigned long new_bits, new_freq;
 
 	new_freq = sparc64_get_clock_tick(cpu) / 1000;
 	switch (index) {
@@ -121,15 +115,7 @@ static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
 		BUG();
 	}
 
-	reg = read_safari_cfg();
-
-	reg &= ~SAFARI_CFG_DIV_MASK;
-	reg |= new_bits;
-	write_safari_cfg(reg);
-
-	set_cpus_allowed_ptr(current, &cpus_allowed);
-
-	return 0;
+	return smp_call_function_single(cpu, update_safari_cfg, &new_bits, 1);
 }
 
 static int __init us3_freq_cpu_init(struct cpufreq_policy *policy)
diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c
new file mode 100644
index 000000000000..fe7875311d62
--- /dev/null
+++ b/drivers/cpufreq/tegra186-cpufreq.c
@@ -0,0 +1,275 @@
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include <soc/tegra/bpmp.h>
+#include <soc/tegra/bpmp-abi.h>
+
+#define EDVD_CORE_VOLT_FREQ(core)		(0x20 + (core) * 0x4)
+#define EDVD_CORE_VOLT_FREQ_F_SHIFT		0
+#define EDVD_CORE_VOLT_FREQ_V_SHIFT		16
+
+struct tegra186_cpufreq_cluster_info {
+	unsigned long offset;
+	int cpus[4];
+	unsigned int bpmp_cluster_id;
+};
+
+#define NO_CPU -1
+static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = {
+	/* Denver cluster */
+	{
+		.offset = SZ_64K * 7,
+		.cpus = { 1, 2, NO_CPU, NO_CPU },
+		.bpmp_cluster_id = 0,
+	},
+	/* A57 cluster */
+	{
+		.offset = SZ_64K * 6,
+		.cpus = { 0, 3, 4, 5 },
+		.bpmp_cluster_id = 1,
+	},
+};
+
+struct tegra186_cpufreq_cluster {
+	const struct tegra186_cpufreq_cluster_info *info;
+	struct cpufreq_frequency_table *table;
+};
+
+struct tegra186_cpufreq_data {
+	void __iomem *regs;
+
+	size_t num_clusters;
+	struct tegra186_cpufreq_cluster *clusters;
+};
+
+static int tegra186_cpufreq_init(struct cpufreq_policy *policy)
+{
+	struct tegra186_cpufreq_data *data = cpufreq_get_driver_data();
+	unsigned int i;
+
+	for (i = 0; i < data->num_clusters; i++) {
+		struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+		const struct tegra186_cpufreq_cluster_info *info =
+			cluster->info;
+		int core;
+
+		for (core = 0; core < ARRAY_SIZE(info->cpus); core++) {
+			if (info->cpus[core] == policy->cpu)
+				break;
+		}
+		if (core == ARRAY_SIZE(info->cpus))
+			continue;
+
+		policy->driver_data =
+			data->regs + info->offset + EDVD_CORE_VOLT_FREQ(core);
+		cpufreq_table_validate_and_show(policy, cluster->table);
+	}
+
+	policy->cpuinfo.transition_latency = 300 * 1000;
+
+	return 0;
+}
+
+static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy,
+				       unsigned int index)
+{
+	struct cpufreq_frequency_table *tbl = policy->freq_table + index;
+	void __iomem *edvd_reg = policy->driver_data;
+	u32 edvd_val = tbl->driver_data;
+
+	writel(edvd_val, edvd_reg);
+
+	return 0;
+}
+
+static struct cpufreq_driver tegra186_cpufreq_driver = {
+	.name = "tegra186",
+	.flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+	.verify = cpufreq_generic_frequency_table_verify,
+	.target_index = tegra186_cpufreq_set_target,
+	.init = tegra186_cpufreq_init,
+	.attr = cpufreq_generic_attr,
+};
+
+static struct cpufreq_frequency_table *init_vhint_table(
+	struct platform_device *pdev, struct tegra_bpmp *bpmp,
+	unsigned int cluster_id)
+{
+	struct cpufreq_frequency_table *table;
+	struct mrq_cpu_vhint_request req;
+	struct tegra_bpmp_message msg;
+	struct cpu_vhint_data *data;
+	int err, i, j, num_rates = 0;
+	dma_addr_t phys;
+	void *virt;
+
+	virt = dma_alloc_coherent(bpmp->dev, sizeof(*data), &phys,
+				  GFP_KERNEL | GFP_DMA32);
+	if (!virt)
+		return ERR_PTR(-ENOMEM);
+
+	data = (struct cpu_vhint_data *)virt;
+
+	memset(&req, 0, sizeof(req));
+	req.addr = phys;
+	req.cluster_id = cluster_id;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.mrq = MRQ_CPU_VHINT;
+	msg.tx.data = &req;
+	msg.tx.size = sizeof(req);
+
+	err = tegra_bpmp_transfer(bpmp, &msg);
+	if (err) {
+		table = ERR_PTR(err);
+		goto free;
+	}
+
+	for (i = data->vfloor; i <= data->vceil; i++) {
+		u16 ndiv = data->ndiv[i];
+
+		if (ndiv < data->ndiv_min || ndiv > data->ndiv_max)
+			continue;
+
+		/* Only store lowest voltage index for each rate */
+		if (i > 0 && ndiv == data->ndiv[i - 1])
+			continue;
+
+		num_rates++;
+	}
+
+	table = devm_kcalloc(&pdev->dev, num_rates + 1, sizeof(*table),
+			     GFP_KERNEL);
+	if (!table) {
+		table = ERR_PTR(-ENOMEM);
+		goto free;
+	}
+
+	for (i = data->vfloor, j = 0; i <= data->vceil; i++) {
+		struct cpufreq_frequency_table *point;
+		u16 ndiv = data->ndiv[i];
+		u32 edvd_val = 0;
+
+		if (ndiv < data->ndiv_min || ndiv > data->ndiv_max)
+			continue;
+
+		/* Only store lowest voltage index for each rate */
+		if (i > 0 && ndiv == data->ndiv[i - 1])
+			continue;
+
+		edvd_val |= i << EDVD_CORE_VOLT_FREQ_V_SHIFT;
+		edvd_val |= ndiv << EDVD_CORE_VOLT_FREQ_F_SHIFT;
+
+		point = &table[j++];
+		point->driver_data = edvd_val;
+		point->frequency = data->ref_clk_hz * ndiv / data->pdiv /
+			data->mdiv / 1000;
+	}
+
+	table[j].frequency = CPUFREQ_TABLE_END;
+
+free:
+	dma_free_coherent(bpmp->dev, sizeof(*data), virt, phys);
+
+	return table;
+}
+
+static int tegra186_cpufreq_probe(struct platform_device *pdev)
+{
+	struct tegra186_cpufreq_data *data;
+	struct tegra_bpmp *bpmp;
+	struct resource *res;
+	unsigned int i = 0, err;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->clusters = devm_kcalloc(&pdev->dev, ARRAY_SIZE(tegra186_clusters),
+				      sizeof(*data->clusters), GFP_KERNEL);
+	if (!data->clusters)
+		return -ENOMEM;
+
+	data->num_clusters = ARRAY_SIZE(tegra186_clusters);
+
+	bpmp = tegra_bpmp_get(&pdev->dev);
+	if (IS_ERR(bpmp))
+		return PTR_ERR(bpmp);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(data->regs)) {
+		err = PTR_ERR(data->regs);
+		goto put_bpmp;
+	}
+
+	for (i = 0; i < data->num_clusters; i++) {
+		struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+
+		cluster->info = &tegra186_clusters[i];
+		cluster->table = init_vhint_table(
+			pdev, bpmp, cluster->info->bpmp_cluster_id);
+		if (IS_ERR(cluster->table)) {
+			err = PTR_ERR(cluster->table);
+			goto put_bpmp;
+		}
+	}
+
+	tegra_bpmp_put(bpmp);
+
+	tegra186_cpufreq_driver.driver_data = data;
+
+	err = cpufreq_register_driver(&tegra186_cpufreq_driver);
+	if (err)
+		return err;
+
+	return 0;
+
+put_bpmp:
+	tegra_bpmp_put(bpmp);
+
+	return err;
+}
+
+static int tegra186_cpufreq_remove(struct platform_device *pdev)
+{
+	cpufreq_unregister_driver(&tegra186_cpufreq_driver);
+
+	return 0;
+}
+
+static const struct of_device_id tegra186_cpufreq_of_match[] = {
+	{ .compatible = "nvidia,tegra186-ccplex-cluster", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tegra186_cpufreq_of_match);
+
+static struct platform_driver tegra186_cpufreq_platform_driver = {
+	.driver = {
+		.name = "tegra186-cpufreq",
+		.of_match_table = tegra186_cpufreq_of_match,
+	},
+	.probe = tegra186_cpufreq_probe,
+	.remove = tegra186_cpufreq_remove,
+};
+module_platform_driver(tegra186_cpufreq_platform_driver);
+
+MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra186 cpufreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c
index 926ba9871c62..12b9145913de 100644
--- a/drivers/cpuidle/cpuidle-cps.c
+++ b/drivers/cpuidle/cpuidle-cps.c
@@ -118,7 +118,7 @@ static void __init cps_cpuidle_unregister(void)
 
 static int __init cps_cpuidle_init(void)
 {
-	int err, cpu, core, i;
+	int err, cpu, i;
 	struct cpuidle_device *device;
 
 	/* Detect supported states */
@@ -160,7 +160,6 @@ static int __init cps_cpuidle_init(void)
 	}
 
 	for_each_possible_cpu(cpu) {
-		core = cpu_data[cpu].core;
 		device = &per_cpu(cpuidle_dev, cpu);
 		device->cpu = cpu;
 #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 370593006f5f..12409a519cc5 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -56,10 +56,9 @@ static int snooze_loop(struct cpuidle_device *dev,
 
 	snooze_exit_time = get_tb() + snooze_timeout;
 	ppc64_runlatch_off();
+	HMT_very_low();
 	while (!need_resched()) {
-		HMT_low();
-		HMT_very_low();
-		if (snooze_timeout_en && get_tb() > snooze_exit_time)
+		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time)
 			break;
 	}
 
@@ -175,6 +174,24 @@ static int powernv_cpuidle_driver_init(void)
 		drv->state_count += 1;
 	}
 
+	/*
+	 * On the PowerNV platform cpu_present may be less than cpu_possible in
+	 * cases when firmware detects the CPU, but it is not available to the
+	 * OS.  If CONFIG_HOTPLUG_CPU=n, then such CPUs are not hotplugable at
+	 * run time and hence cpu_devices are not created for those CPUs by the
+	 * generic topology_init().
+	 *
+	 * drv->cpumask defaults to cpu_possible_mask in
+	 * __cpuidle_driver_init().  This breaks cpuidle on PowerNV where
+	 * cpu_devices are not created for CPUs in cpu_possible_mask that
+	 * cannot be hot-added later at run time.
+	 *
+	 * Trying cpuidle_register_device() on a CPU without a cpu_device is
+	 * incorrect, so pass a correct CPU mask to the generic cpuidle driver.
+	 */
+
+	drv->cpumask = (struct cpumask *)cpu_present_mask;
+
 	return 0;
 }
 
@@ -197,11 +214,25 @@ static inline void add_powernv_state(int index, const char *name,
 	stop_psscr_table[index].mask = psscr_mask;
 }
 
+/*
+ * Returns 0 if prop1_len == prop2_len. Else returns -1
+ */
+static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
+					 const char *prop2, int prop2_len)
+{
+	if (prop1_len == prop2_len)
+		return 0;
+
+	pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
+		prop1, prop2);
+	return -1;
+}
+
 static int powernv_add_idle_states(void)
 {
 	struct device_node *power_mgt;
 	int nr_idle_states = 1; /* Snooze */
-	int dt_idle_states;
+	int dt_idle_states, count;
 	u32 latency_ns[CPUIDLE_STATE_MAX];
 	u32 residency_ns[CPUIDLE_STATE_MAX];
 	u32 flags[CPUIDLE_STATE_MAX];
@@ -226,6 +257,21 @@ static int powernv_add_idle_states(void)
 		goto out;
 	}
 
+	count = of_property_count_u32_elems(power_mgt,
+					    "ibm,cpu-idle-state-latencies-ns");
+
+	if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
+				   "ibm,cpu-idle-state-latencies-ns",
+				   count) != 0)
+		goto out;
+
+	count = of_property_count_strings(power_mgt,
+					  "ibm,cpu-idle-state-names");
+	if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
+				   "ibm,cpu-idle-state-names",
+				   count) != 0)
+		goto out;
+
 	/*
 	 * Since snooze is used as first idle state, max idle states allowed is
 	 * CPUIDLE_STATE_MAX -1
@@ -260,6 +306,22 @@ static int powernv_add_idle_states(void)
 	has_stop_states = (flags[0] &
 			   (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
 	if (has_stop_states) {
+		count = of_property_count_u64_elems(power_mgt,
+						    "ibm,cpu-idle-state-psscr");
+		if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
+					   dt_idle_states,
+					   "ibm,cpu-idle-state-psscr",
+					   count) != 0)
+			goto out;
+
+		count = of_property_count_u64_elems(power_mgt,
+						    "ibm,cpu-idle-state-psscr-mask");
+		if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
+					   dt_idle_states,
+					   "ibm,cpu-idle-state-psscr-mask",
+					   count) != 0)
+			goto out;
+
 		if (of_property_read_u64_array(power_mgt,
 		    "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
 			pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
@@ -274,8 +336,21 @@ static int powernv_add_idle_states(void)
 		}
 	}
 
-	rc = of_property_read_u32_array(power_mgt,
-		"ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states);
+	count = of_property_count_u32_elems(power_mgt,
+					    "ibm,cpu-idle-state-residency-ns");
+
+	if (count < 0) {
+		rc = count;
+	} else if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
+					  dt_idle_states,
+					  "ibm,cpu-idle-state-residency-ns",
+					  count) != 0) {
+		goto out;
+	} else {
+		rc = of_property_read_u32_array(power_mgt,
+						"ibm,cpu-idle-state-residency-ns",
+						residency_ns, dt_idle_states);
+	}
 
 	for (i = 0; i < dt_idle_states; i++) {
 		unsigned int exit_latency, target_residency;
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index c5adc8c9ac43..ae948b1da93a 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -615,6 +615,18 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev)
 	struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu);
 	int error;
 
+	/*
+	 * Return if cpu_device is not setup for this CPU.
+	 *
+	 * This could happen if the arch did not set up cpu_device
+	 * since this CPU is not in cpu_present mask and the
+	 * driver did not send a correct CPU mask during registration.
+	 * Without this check we would end up passing bogus
+	 * value for &cpu_dev->kobj in kobject_init_and_add()
+	 */
+	if (!cpu_dev)
+		return -ENODEV;
+
 	kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
 	if (!kdev)
 		return -ENOMEM;
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 473d31288ad8..fb1e60f5002e 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -388,6 +388,21 @@ config CRYPTO_DEV_MXC_SCC
 	  This option enables support for the Security Controller (SCC)
 	  found in Freescale i.MX25 chips.
 
+config CRYPTO_DEV_EXYNOS_RNG
+	tristate "EXYNOS HW pseudo random number generator support"
+	depends on ARCH_EXYNOS || COMPILE_TEST
+	depends on HAS_IOMEM
+	select CRYPTO_RNG
+	---help---
+	  This driver provides kernel-side support through the
+	  cryptographic API for the pseudo random number generator hardware
+	  found on Exynos SoCs.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called exynos-rng.
+
+	  If unsure, say Y.
+
 config CRYPTO_DEV_S5P
 	tristate "Support for Samsung S5PV210/Exynos crypto accelerator"
 	depends on ARCH_S5PV210 || ARCH_EXYNOS || COMPILE_TEST
@@ -515,6 +530,13 @@ config CRYPTO_DEV_MXS_DCP
 source "drivers/crypto/qat/Kconfig"
 source "drivers/crypto/cavium/cpt/Kconfig"
 
+config CRYPTO_DEV_CAVIUM_ZIP
+	tristate "Cavium ZIP driver"
+	depends on PCI && 64BIT && (ARM64 || COMPILE_TEST)
+	---help---
+	  Select this option if you want to enable compression/decompression
+	  acceleration on Cavium's ARM based SoCs
+
 config CRYPTO_DEV_QCE
 	tristate "Qualcomm crypto engine accelerator"
 	depends on (ARCH_QCOM || COMPILE_TEST) && HAS_DMA && HAS_IOMEM
@@ -619,4 +641,6 @@ config CRYPTO_DEV_BCM_SPU
 	  Secure Processing Unit (SPU). The SPU driver registers ablkcipher,
 	  ahash, and aead algorithms with the kernel cryptographic API.
 
+source "drivers/crypto/stm32/Kconfig"
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 739609471169..463f33592d93 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -2,9 +2,11 @@ obj-$(CONFIG_CRYPTO_DEV_ATMEL_AES) += atmel-aes.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_SHA) += atmel-sha.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_TDES) += atmel-tdes.o
 obj-$(CONFIG_CRYPTO_DEV_BFIN_CRC) += bfin_crc.o
+obj-$(CONFIG_CRYPTO_DEV_CAVIUM_ZIP) += cavium/
 obj-$(CONFIG_CRYPTO_DEV_CCP) += ccp/
 obj-$(CONFIG_CRYPTO_DEV_CHELSIO) += chelsio/
 obj-$(CONFIG_CRYPTO_DEV_CPT) += cavium/cpt/
+obj-$(CONFIG_CRYPTO_DEV_EXYNOS_RNG) += exynos-rng.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam/
 obj-$(CONFIG_CRYPTO_DEV_GEODE) += geode-aes.o
 obj-$(CONFIG_CRYPTO_DEV_HIFN_795X) += hifn_795x.o
@@ -30,6 +32,7 @@ obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/
 obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o
+obj-$(CONFIG_CRYPTO_DEV_STM32) += stm32/
 obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sunxi-ss/
 obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o
 obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index d10b4ae5e0da..fdc83a2281ca 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -50,7 +50,7 @@
 static void crypto4xx_hw_init(struct crypto4xx_device *dev)
 {
 	union ce_ring_size ring_size;
-	union ce_ring_contol ring_ctrl;
+	union ce_ring_control ring_ctrl;
 	union ce_part_ring_size part_ring_size;
 	union ce_io_threshold io_threshold;
 	u32 rand_num;
diff --git a/drivers/crypto/amcc/crypto4xx_reg_def.h b/drivers/crypto/amcc/crypto4xx_reg_def.h
index 46fe57c8f6eb..279b8725559f 100644
--- a/drivers/crypto/amcc/crypto4xx_reg_def.h
+++ b/drivers/crypto/amcc/crypto4xx_reg_def.h
@@ -180,7 +180,7 @@ union ce_ring_size {
 } __attribute__((packed));
 
 #define CRYPTO4XX_RING_CONTROL_OFFSET		0x54
-union ce_ring_contol {
+union ce_ring_control {
 	struct {
 		u32 continuous:1;
 		u32 rsv:5;
diff --git a/drivers/crypto/bcm/util.c b/drivers/crypto/bcm/util.c
index 0502f460dacd..430c5570ea87 100644
--- a/drivers/crypto/bcm/util.c
+++ b/drivers/crypto/bcm/util.c
@@ -312,7 +312,7 @@ int do_shash(unsigned char *name, unsigned char *result,
 	}
 	rc = crypto_shash_final(&sdesc->shash, result);
 	if (rc)
-		pr_err("%s: Could not genereate %s hash", __func__, name);
+		pr_err("%s: Could not generate %s hash", __func__, name);
 
 do_shash_err:
 	crypto_free_shash(hash);
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index bc0d3569f8d9..e36aeacd7635 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -87,6 +87,23 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API
 	  To compile this as a module, choose M here: the module
 	  will be called caamalg.
 
+config CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI
+	tristate "Queue Interface as Crypto API backend"
+	depends on CRYPTO_DEV_FSL_CAAM_JR && FSL_DPAA && NET
+	default y
+	select CRYPTO_AUTHENC
+	select CRYPTO_BLKCIPHER
+	help
+	  Selecting this will use CAAM Queue Interface (QI) for sending
+	  & receiving crypto jobs to/from CAAM. This gives better performance
+	  than job ring interface when the number of cores are more than the
+	  number of job rings assigned to the kernel. The number of portals
+	  assigned to the kernel should also be more than the number of
+	  job rings.
+
+	  To compile this as a module, choose M here: the module
+	  will be called caamalg_qi.
+
 config CRYPTO_DEV_FSL_CAAM_AHASH_API
 	tristate "Register hash algorithm implementations with Crypto API"
 	depends on CRYPTO_DEV_FSL_CAAM_JR
@@ -136,4 +153,5 @@ config CRYPTO_DEV_FSL_CAAM_DEBUG
 	  information in the CAAM driver.
 
 config CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC
-	def_tristate CRYPTO_DEV_FSL_CAAM_CRYPTO_API
+	def_tristate (CRYPTO_DEV_FSL_CAAM_CRYPTO_API || \
+		      CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI)
diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile
index 6554742f357e..9e2e98856b9b 100644
--- a/drivers/crypto/caam/Makefile
+++ b/drivers/crypto/caam/Makefile
@@ -8,6 +8,7 @@ endif
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_JR) += caam_jr.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o
+obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI) += caamalg_qi.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC) += caamalg_desc.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o
@@ -16,3 +17,7 @@ obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_PKC_API) += caam_pkc.o
 caam-objs := ctrl.o
 caam_jr-objs := jr.o key_gen.o error.o
 caam_pkc-y := caampkc.o pkc_desc.o
+ifneq ($(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI),)
+	ccflags-y += -DCONFIG_CAAM_QI
+	caam-objs += qi.o
+endif
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 9bc80eb06934..398807d1b77e 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -266,8 +266,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 
 	/* aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
-	cnstr_shdsc_aead_encap(desc, &ctx->cdata, &ctx->adata, ctx->authsize,
-			       is_rfc3686, nonce, ctx1_iv_off);
+	cnstr_shdsc_aead_encap(desc, &ctx->cdata, &ctx->adata, ivsize,
+			       ctx->authsize, is_rfc3686, nonce, ctx1_iv_off,
+			       false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
 				   desc_bytes(desc), DMA_TO_DEVICE);
 
@@ -299,7 +300,7 @@ skip_enc:
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_aead_decap(desc, &ctx->cdata, &ctx->adata, ivsize,
 			       ctx->authsize, alg->caam.geniv, is_rfc3686,
-			       nonce, ctx1_iv_off);
+			       nonce, ctx1_iv_off, false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
 				   desc_bytes(desc), DMA_TO_DEVICE);
 
@@ -333,7 +334,7 @@ skip_enc:
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_aead_givencap(desc, &ctx->cdata, &ctx->adata, ivsize,
 				  ctx->authsize, is_rfc3686, nonce,
-				  ctx1_iv_off);
+				  ctx1_iv_off, false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
 				   desc_bytes(desc), DMA_TO_DEVICE);
 
diff --git a/drivers/crypto/caam/caamalg_desc.c b/drivers/crypto/caam/caamalg_desc.c
index f3f48c10b9d6..6f9c7ec0e339 100644
--- a/drivers/crypto/caam/caamalg_desc.c
+++ b/drivers/crypto/caam/caamalg_desc.c
@@ -265,17 +265,19 @@ static void init_sh_desc_key_aead(u32 * const desc,
  *         split key is to be used, the size of the split key itself is
  *         specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
  *         SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
  * @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
  * @nonce: pointer to rfc3686 nonce
  * @ctx1_iv_off: IV offset in CONTEXT1 register
+ * @is_qi: true when called from caam/qi
  *
  * Note: Requires an MDHA split key.
  */
 void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
-			    struct alginfo *adata, unsigned int icvsize,
-			    const bool is_rfc3686, u32 *nonce,
-			    const u32 ctx1_iv_off)
+			    struct alginfo *adata, unsigned int ivsize,
+			    unsigned int icvsize, const bool is_rfc3686,
+			    u32 *nonce, const u32 ctx1_iv_off, const bool is_qi)
 {
 	/* Note: Context registers are saved. */
 	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
@@ -284,6 +286,25 @@ void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, adata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_ENCRYPT);
 
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+
+		append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
+				LDST_SRCDST_BYTE_CONTEXT |
+				(ctx1_iv_off << LDST_OFFSET_SHIFT));
+	}
+
 	/* Read and write assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
@@ -338,6 +359,7 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_encap);
  * @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
  * @nonce: pointer to rfc3686 nonce
  * @ctx1_iv_off: IV offset in CONTEXT1 register
+ * @is_qi: true when called from caam/qi
  *
  * Note: Requires an MDHA split key.
  */
@@ -345,7 +367,7 @@ void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
 			    struct alginfo *adata, unsigned int ivsize,
 			    unsigned int icvsize, const bool geniv,
 			    const bool is_rfc3686, u32 *nonce,
-			    const u32 ctx1_iv_off)
+			    const u32 ctx1_iv_off, const bool is_qi)
 {
 	/* Note: Context registers are saved. */
 	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
@@ -354,6 +376,26 @@ void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, adata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+
+		if (!geniv)
+			append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
+					LDST_SRCDST_BYTE_CONTEXT |
+					(ctx1_iv_off << LDST_OFFSET_SHIFT));
+	}
+
 	/* Read and write assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	if (geniv)
@@ -423,21 +465,44 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_decap);
  * @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
  * @nonce: pointer to rfc3686 nonce
  * @ctx1_iv_off: IV offset in CONTEXT1 register
+ * @is_qi: true when called from caam/qi
  *
  * Note: Requires an MDHA split key.
  */
 void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
 			       struct alginfo *adata, unsigned int ivsize,
 			       unsigned int icvsize, const bool is_rfc3686,
-			       u32 *nonce, const u32 ctx1_iv_off)
+			       u32 *nonce, const u32 ctx1_iv_off,
+			       const bool is_qi)
 {
 	u32 geniv, moveiv;
 
 	/* Note: Context registers are saved. */
 	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
 
-	if (is_rfc3686)
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+	}
+
+	if (is_rfc3686) {
+		if (is_qi)
+			append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
+					LDST_SRCDST_BYTE_CONTEXT |
+					(ctx1_iv_off << LDST_OFFSET_SHIFT));
+
 		goto copy_iv;
+	}
 
 	/* Generate IV */
 	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
diff --git a/drivers/crypto/caam/caamalg_desc.h b/drivers/crypto/caam/caamalg_desc.h
index 95551737333a..8731e4a7ff05 100644
--- a/drivers/crypto/caam/caamalg_desc.h
+++ b/drivers/crypto/caam/caamalg_desc.h
@@ -12,6 +12,9 @@
 #define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 11 * CAAM_CMD_SZ)
 #define DESC_AEAD_DEC_LEN		(DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
 #define DESC_AEAD_GIVENC_LEN		(DESC_AEAD_ENC_LEN + 7 * CAAM_CMD_SZ)
+#define DESC_QI_AEAD_ENC_LEN		(DESC_AEAD_ENC_LEN + 3 * CAAM_CMD_SZ)
+#define DESC_QI_AEAD_DEC_LEN		(DESC_AEAD_DEC_LEN + 3 * CAAM_CMD_SZ)
+#define DESC_QI_AEAD_GIVENC_LEN		(DESC_AEAD_GIVENC_LEN + 3 * CAAM_CMD_SZ)
 
 /* Note: Nonce is counted in cdata.keylen */
 #define DESC_AEAD_CTR_RFC3686_LEN	(4 * CAAM_CMD_SZ)
@@ -45,20 +48,22 @@ void cnstr_shdsc_aead_null_decap(u32 * const desc, struct alginfo *adata,
 				 unsigned int icvsize);
 
 void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
-			    struct alginfo *adata, unsigned int icvsize,
-			    const bool is_rfc3686, u32 *nonce,
-			    const u32 ctx1_iv_off);
+			    struct alginfo *adata, unsigned int ivsize,
+			    unsigned int icvsize, const bool is_rfc3686,
+			    u32 *nonce, const u32 ctx1_iv_off,
+			    const bool is_qi);
 
 void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
 			    struct alginfo *adata, unsigned int ivsize,
 			    unsigned int icvsize, const bool geniv,
 			    const bool is_rfc3686, u32 *nonce,
-			    const u32 ctx1_iv_off);
+			    const u32 ctx1_iv_off, const bool is_qi);
 
 void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
 			       struct alginfo *adata, unsigned int ivsize,
 			       unsigned int icvsize, const bool is_rfc3686,
-			       u32 *nonce, const u32 ctx1_iv_off);
+			       u32 *nonce, const u32 ctx1_iv_off,
+			       const bool is_qi);
 
 void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
 			   unsigned int icvsize);
diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c
new file mode 100644
index 000000000000..ea0e5b8b9171
--- /dev/null
+++ b/drivers/crypto/caam/caamalg_qi.c
@@ -0,0 +1,2387 @@
+/*
+ * Freescale FSL CAAM support for crypto API over QI backend.
+ * Based on caamalg.c
+ *
+ * Copyright 2013-2016 Freescale Semiconductor, Inc.
+ * Copyright 2016-2017 NXP
+ */
+
+#include "compat.h"
+
+#include "regs.h"
+#include "intern.h"
+#include "desc_constr.h"
+#include "error.h"
+#include "sg_sw_sec4.h"
+#include "sg_sw_qm.h"
+#include "key_gen.h"
+#include "qi.h"
+#include "jr.h"
+#include "caamalg_desc.h"
+
+/*
+ * crypto alg
+ */
+#define CAAM_CRA_PRIORITY		2000
+/* max key is sum of AES_MAX_KEY_SIZE, max split key size */
+#define CAAM_MAX_KEY_SIZE		(AES_MAX_KEY_SIZE + \
+					 SHA512_DIGEST_SIZE * 2)
+
+#define DESC_MAX_USED_BYTES		(DESC_QI_AEAD_GIVENC_LEN + \
+					 CAAM_MAX_KEY_SIZE)
+#define DESC_MAX_USED_LEN		(DESC_MAX_USED_BYTES / CAAM_CMD_SZ)
+
+struct caam_alg_entry {
+	int class1_alg_type;
+	int class2_alg_type;
+	bool rfc3686;
+	bool geniv;
+};
+
+struct caam_aead_alg {
+	struct aead_alg aead;
+	struct caam_alg_entry caam;
+	bool registered;
+};
+
+/*
+ * per-session context
+ */
+struct caam_ctx {
+	struct device *jrdev;
+	u32 sh_desc_enc[DESC_MAX_USED_LEN];
+	u32 sh_desc_dec[DESC_MAX_USED_LEN];
+	u32 sh_desc_givenc[DESC_MAX_USED_LEN];
+	u8 key[CAAM_MAX_KEY_SIZE];
+	dma_addr_t key_dma;
+	struct alginfo adata;
+	struct alginfo cdata;
+	unsigned int authsize;
+	struct device *qidev;
+	spinlock_t lock;	/* Protects multiple init of driver context */
+	struct caam_drv_ctx *drv_ctx[NUM_OP];
+};
+
+static int aead_set_sh_desc(struct crypto_aead *aead)
+{
+	struct caam_aead_alg *alg = container_of(crypto_aead_alg(aead),
+						 typeof(*alg), aead);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+	u32 ctx1_iv_off = 0;
+	u32 *nonce = NULL;
+	unsigned int data_len[2];
+	u32 inl_mask;
+	const bool ctr_mode = ((ctx->cdata.algtype & OP_ALG_AAI_MASK) ==
+			       OP_ALG_AAI_CTR_MOD128);
+	const bool is_rfc3686 = alg->caam.rfc3686;
+
+	if (!ctx->cdata.keylen || !ctx->authsize)
+		return 0;
+
+	/*
+	 * AES-CTR needs to load IV in CONTEXT1 reg
+	 * at an offset of 128bits (16bytes)
+	 * CONTEXT1[255:128] = IV
+	 */
+	if (ctr_mode)
+		ctx1_iv_off = 16;
+
+	/*
+	 * RFC3686 specific:
+	 *	CONTEXT1[255:128] = {NONCE, IV, COUNTER}
+	 */
+	if (is_rfc3686) {
+		ctx1_iv_off = 16 + CTR_RFC3686_NONCE_SIZE;
+		nonce = (u32 *)((void *)ctx->key + ctx->adata.keylen_pad +
+				ctx->cdata.keylen - CTR_RFC3686_NONCE_SIZE);
+	}
+
+	data_len[0] = ctx->adata.keylen_pad;
+	data_len[1] = ctx->cdata.keylen;
+
+	if (alg->caam.geniv)
+		goto skip_enc;
+
+	/* aead_encrypt shared descriptor */
+	if (desc_inline_query(DESC_QI_AEAD_ENC_LEN +
+			      (is_rfc3686 ? DESC_AEAD_CTR_RFC3686_LEN : 0),
+			      DESC_JOB_IO_LEN, data_len, &inl_mask,
+			      ARRAY_SIZE(data_len)) < 0)
+		return -EINVAL;
+
+	if (inl_mask & 1)
+		ctx->adata.key_virt = ctx->key;
+	else
+		ctx->adata.key_dma = ctx->key_dma;
+
+	if (inl_mask & 2)
+		ctx->cdata.key_virt = ctx->key + ctx->adata.keylen_pad;
+	else
+		ctx->cdata.key_dma = ctx->key_dma + ctx->adata.keylen_pad;
+
+	ctx->adata.key_inline = !!(inl_mask & 1);
+	ctx->cdata.key_inline = !!(inl_mask & 2);
+
+	cnstr_shdsc_aead_encap(ctx->sh_desc_enc, &ctx->cdata, &ctx->adata,
+			       ivsize, ctx->authsize, is_rfc3686, nonce,
+			       ctx1_iv_off, true);
+
+skip_enc:
+	/* aead_decrypt shared descriptor */
+	if (desc_inline_query(DESC_QI_AEAD_DEC_LEN +
+			      (is_rfc3686 ? DESC_AEAD_CTR_RFC3686_LEN : 0),
+			      DESC_JOB_IO_LEN, data_len, &inl_mask,
+			      ARRAY_SIZE(data_len)) < 0)
+		return -EINVAL;
+
+	if (inl_mask & 1)
+		ctx->adata.key_virt = ctx->key;
+	else
+		ctx->adata.key_dma = ctx->key_dma;
+
+	if (inl_mask & 2)
+		ctx->cdata.key_virt = ctx->key + ctx->adata.keylen_pad;
+	else
+		ctx->cdata.key_dma = ctx->key_dma + ctx->adata.keylen_pad;
+
+	ctx->adata.key_inline = !!(inl_mask & 1);
+	ctx->cdata.key_inline = !!(inl_mask & 2);
+
+	cnstr_shdsc_aead_decap(ctx->sh_desc_dec, &ctx->cdata, &ctx->adata,
+			       ivsize, ctx->authsize, alg->caam.geniv,
+			       is_rfc3686, nonce, ctx1_iv_off, true);
+
+	if (!alg->caam.geniv)
+		goto skip_givenc;
+
+	/* aead_givencrypt shared descriptor */
+	if (desc_inline_query(DESC_QI_AEAD_GIVENC_LEN +
+			      (is_rfc3686 ? DESC_AEAD_CTR_RFC3686_LEN : 0),
+			      DESC_JOB_IO_LEN, data_len, &inl_mask,
+			      ARRAY_SIZE(data_len)) < 0)
+		return -EINVAL;
+
+	if (inl_mask & 1)
+		ctx->adata.key_virt = ctx->key;
+	else
+		ctx->adata.key_dma = ctx->key_dma;
+
+	if (inl_mask & 2)
+		ctx->cdata.key_virt = ctx->key + ctx->adata.keylen_pad;
+	else
+		ctx->cdata.key_dma = ctx->key_dma + ctx->adata.keylen_pad;
+
+	ctx->adata.key_inline = !!(inl_mask & 1);
+	ctx->cdata.key_inline = !!(inl_mask & 2);
+
+	cnstr_shdsc_aead_givencap(ctx->sh_desc_enc, &ctx->cdata, &ctx->adata,
+				  ivsize, ctx->authsize, is_rfc3686, nonce,
+				  ctx1_iv_off, true);
+
+skip_givenc:
+	return 0;
+}
+
+static int aead_setauthsize(struct crypto_aead *authenc, unsigned int authsize)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(authenc);
+
+	ctx->authsize = authsize;
+	aead_set_sh_desc(authenc);
+
+	return 0;
+}
+
+static int aead_setkey(struct crypto_aead *aead, const u8 *key,
+		       unsigned int keylen)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	struct crypto_authenc_keys keys;
+	int ret = 0;
+
+	if (crypto_authenc_extractkeys(&keys, key, keylen) != 0)
+		goto badkey;
+
+#ifdef DEBUG
+	dev_err(jrdev, "keylen %d enckeylen %d authkeylen %d\n",
+		keys.authkeylen + keys.enckeylen, keys.enckeylen,
+		keys.authkeylen);
+	print_hex_dump(KERN_ERR, "key in @" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
+#endif
+
+	ret = gen_split_key(jrdev, ctx->key, &ctx->adata, keys.authkey,
+			    keys.authkeylen, CAAM_MAX_KEY_SIZE -
+			    keys.enckeylen);
+	if (ret)
+		goto badkey;
+
+	/* postpend encryption key to auth split key */
+	memcpy(ctx->key + ctx->adata.keylen_pad, keys.enckey, keys.enckeylen);
+	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->adata.keylen_pad +
+				   keys.enckeylen, DMA_TO_DEVICE);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx.key@" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
+		       ctx->adata.keylen_pad + keys.enckeylen, 1);
+#endif
+
+	ctx->cdata.keylen = keys.enckeylen;
+
+	ret = aead_set_sh_desc(aead);
+	if (ret)
+		goto badkey;
+
+	/* Now update the driver contexts with the new shared descriptor */
+	if (ctx->drv_ctx[ENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[ENCRYPT],
+					  ctx->sh_desc_enc);
+		if (ret) {
+			dev_err(jrdev, "driver enc context update failed\n");
+			goto badkey;
+		}
+	}
+
+	if (ctx->drv_ctx[DECRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[DECRYPT],
+					  ctx->sh_desc_dec);
+		if (ret) {
+			dev_err(jrdev, "driver dec context update failed\n");
+			goto badkey;
+		}
+	}
+
+	return ret;
+badkey:
+	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	return -EINVAL;
+}
+
+static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
+			     const u8 *key, unsigned int keylen)
+{
+	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(ablkcipher);
+	const char *alg_name = crypto_tfm_alg_name(tfm);
+	struct device *jrdev = ctx->jrdev;
+	unsigned int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+	u32 ctx1_iv_off = 0;
+	const bool ctr_mode = ((ctx->cdata.algtype & OP_ALG_AAI_MASK) ==
+			       OP_ALG_AAI_CTR_MOD128);
+	const bool is_rfc3686 = (ctr_mode && strstr(alg_name, "rfc3686"));
+	int ret = 0;
+
+	memcpy(ctx->key, key, keylen);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "key in @" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
+#endif
+	/*
+	 * AES-CTR needs to load IV in CONTEXT1 reg
+	 * at an offset of 128bits (16bytes)
+	 * CONTEXT1[255:128] = IV
+	 */
+	if (ctr_mode)
+		ctx1_iv_off = 16;
+
+	/*
+	 * RFC3686 specific:
+	 *	| CONTEXT1[255:128] = {NONCE, IV, COUNTER}
+	 *	| *key = {KEY, NONCE}
+	 */
+	if (is_rfc3686) {
+		ctx1_iv_off = 16 + CTR_RFC3686_NONCE_SIZE;
+		keylen -= CTR_RFC3686_NONCE_SIZE;
+	}
+
+	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
+	ctx->cdata.keylen = keylen;
+	ctx->cdata.key_virt = ctx->key;
+	ctx->cdata.key_inline = true;
+
+	/* ablkcipher encrypt, decrypt, givencrypt shared descriptors */
+	cnstr_shdsc_ablkcipher_encap(ctx->sh_desc_enc, &ctx->cdata, ivsize,
+				     is_rfc3686, ctx1_iv_off);
+	cnstr_shdsc_ablkcipher_decap(ctx->sh_desc_dec, &ctx->cdata, ivsize,
+				     is_rfc3686, ctx1_iv_off);
+	cnstr_shdsc_ablkcipher_givencap(ctx->sh_desc_givenc, &ctx->cdata,
+					ivsize, is_rfc3686, ctx1_iv_off);
+
+	/* Now update the driver contexts with the new shared descriptor */
+	if (ctx->drv_ctx[ENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[ENCRYPT],
+					  ctx->sh_desc_enc);
+		if (ret) {
+			dev_err(jrdev, "driver enc context update failed\n");
+			goto badkey;
+		}
+	}
+
+	if (ctx->drv_ctx[DECRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[DECRYPT],
+					  ctx->sh_desc_dec);
+		if (ret) {
+			dev_err(jrdev, "driver dec context update failed\n");
+			goto badkey;
+		}
+	}
+
+	if (ctx->drv_ctx[GIVENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[GIVENCRYPT],
+					  ctx->sh_desc_givenc);
+		if (ret) {
+			dev_err(jrdev, "driver givenc context update failed\n");
+			goto badkey;
+		}
+	}
+
+	return ret;
+badkey:
+	crypto_ablkcipher_set_flags(ablkcipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	return -EINVAL;
+}
+
+static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
+				 const u8 *key, unsigned int keylen)
+{
+	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct device *jrdev = ctx->jrdev;
+	int ret = 0;
+
+	if (keylen != 2 * AES_MIN_KEY_SIZE  && keylen != 2 * AES_MAX_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(ablkcipher,
+					    CRYPTO_TFM_RES_BAD_KEY_LEN);
+		dev_err(jrdev, "key size mismatch\n");
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
+	ctx->cdata.keylen = keylen;
+	ctx->cdata.key_virt = ctx->key;
+	ctx->cdata.key_inline = true;
+
+	/* xts ablkcipher encrypt, decrypt shared descriptors */
+	cnstr_shdsc_xts_ablkcipher_encap(ctx->sh_desc_enc, &ctx->cdata);
+	cnstr_shdsc_xts_ablkcipher_decap(ctx->sh_desc_dec, &ctx->cdata);
+
+	/* Now update the driver contexts with the new shared descriptor */
+	if (ctx->drv_ctx[ENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[ENCRYPT],
+					  ctx->sh_desc_enc);
+		if (ret) {
+			dev_err(jrdev, "driver enc context update failed\n");
+			goto badkey;
+		}
+	}
+
+	if (ctx->drv_ctx[DECRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[DECRYPT],
+					  ctx->sh_desc_dec);
+		if (ret) {
+			dev_err(jrdev, "driver dec context update failed\n");
+			goto badkey;
+		}
+	}
+
+	return ret;
+badkey:
+	crypto_ablkcipher_set_flags(ablkcipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	return 0;
+}
+
+/*
+ * aead_edesc - s/w-extended aead descriptor
+ * @src_nents: number of segments in input scatterlist
+ * @dst_nents: number of segments in output scatterlist
+ * @iv_dma: dma address of iv for checking continuity and link table
+ * @qm_sg_bytes: length of dma mapped h/w link table
+ * @qm_sg_dma: bus physical mapped address of h/w link table
+ * @assoclen_dma: bus physical mapped address of req->assoclen
+ * @drv_req: driver-specific request structure
+ * @sgt: the h/w link table
+ */
+struct aead_edesc {
+	int src_nents;
+	int dst_nents;
+	dma_addr_t iv_dma;
+	int qm_sg_bytes;
+	dma_addr_t qm_sg_dma;
+	dma_addr_t assoclen_dma;
+	struct caam_drv_req drv_req;
+	struct qm_sg_entry sgt[0];
+};
+
+/*
+ * ablkcipher_edesc - s/w-extended ablkcipher descriptor
+ * @src_nents: number of segments in input scatterlist
+ * @dst_nents: number of segments in output scatterlist
+ * @iv_dma: dma address of iv for checking continuity and link table
+ * @qm_sg_bytes: length of dma mapped h/w link table
+ * @qm_sg_dma: bus physical mapped address of h/w link table
+ * @drv_req: driver-specific request structure
+ * @sgt: the h/w link table
+ */
+struct ablkcipher_edesc {
+	int src_nents;
+	int dst_nents;
+	dma_addr_t iv_dma;
+	int qm_sg_bytes;
+	dma_addr_t qm_sg_dma;
+	struct caam_drv_req drv_req;
+	struct qm_sg_entry sgt[0];
+};
+
+static struct caam_drv_ctx *get_drv_ctx(struct caam_ctx *ctx,
+					enum optype type)
+{
+	/*
+	 * This function is called on the fast path with values of 'type'
+	 * known at compile time. Invalid arguments are not expected and
+	 * thus no checks are made.
+	 */
+	struct caam_drv_ctx *drv_ctx = ctx->drv_ctx[type];
+	u32 *desc;
+
+	if (unlikely(!drv_ctx)) {
+		spin_lock(&ctx->lock);
+
+		/* Read again to check if some other core init drv_ctx */
+		drv_ctx = ctx->drv_ctx[type];
+		if (!drv_ctx) {
+			int cpu;
+
+			if (type == ENCRYPT)
+				desc = ctx->sh_desc_enc;
+			else if (type == DECRYPT)
+				desc = ctx->sh_desc_dec;
+			else /* (type == GIVENCRYPT) */
+				desc = ctx->sh_desc_givenc;
+
+			cpu = smp_processor_id();
+			drv_ctx = caam_drv_ctx_init(ctx->qidev, &cpu, desc);
+			if (likely(!IS_ERR_OR_NULL(drv_ctx)))
+				drv_ctx->op_type = type;
+
+			ctx->drv_ctx[type] = drv_ctx;
+		}
+
+		spin_unlock(&ctx->lock);
+	}
+
+	return drv_ctx;
+}
+
+static void caam_unmap(struct device *dev, struct scatterlist *src,
+		       struct scatterlist *dst, int src_nents,
+		       int dst_nents, dma_addr_t iv_dma, int ivsize,
+		       enum optype op_type, dma_addr_t qm_sg_dma,
+		       int qm_sg_bytes)
+{
+	if (dst != src) {
+		if (src_nents)
+			dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
+		dma_unmap_sg(dev, dst, dst_nents, DMA_FROM_DEVICE);
+	} else {
+		dma_unmap_sg(dev, src, src_nents, DMA_BIDIRECTIONAL);
+	}
+
+	if (iv_dma)
+		dma_unmap_single(dev, iv_dma, ivsize,
+				 op_type == GIVENCRYPT ? DMA_FROM_DEVICE :
+							 DMA_TO_DEVICE);
+	if (qm_sg_bytes)
+		dma_unmap_single(dev, qm_sg_dma, qm_sg_bytes, DMA_TO_DEVICE);
+}
+
+static void aead_unmap(struct device *dev,
+		       struct aead_edesc *edesc,
+		       struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	int ivsize = crypto_aead_ivsize(aead);
+
+	caam_unmap(dev, req->src, req->dst, edesc->src_nents, edesc->dst_nents,
+		   edesc->iv_dma, ivsize, edesc->drv_req.drv_ctx->op_type,
+		   edesc->qm_sg_dma, edesc->qm_sg_bytes);
+	dma_unmap_single(dev, edesc->assoclen_dma, 4, DMA_TO_DEVICE);
+}
+
+static void ablkcipher_unmap(struct device *dev,
+			     struct ablkcipher_edesc *edesc,
+			     struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+
+	caam_unmap(dev, req->src, req->dst, edesc->src_nents, edesc->dst_nents,
+		   edesc->iv_dma, ivsize, edesc->drv_req.drv_ctx->op_type,
+		   edesc->qm_sg_dma, edesc->qm_sg_bytes);
+}
+
+static void aead_done(struct caam_drv_req *drv_req, u32 status)
+{
+	struct device *qidev;
+	struct aead_edesc *edesc;
+	struct aead_request *aead_req = drv_req->app_ctx;
+	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
+	struct caam_ctx *caam_ctx = crypto_aead_ctx(aead);
+	int ecode = 0;
+
+	qidev = caam_ctx->qidev;
+
+	if (unlikely(status)) {
+		caam_jr_strstatus(qidev, status);
+		ecode = -EIO;
+	}
+
+	edesc = container_of(drv_req, typeof(*edesc), drv_req);
+	aead_unmap(qidev, edesc, aead_req);
+
+	aead_request_complete(aead_req, ecode);
+	qi_cache_free(edesc);
+}
+
+/*
+ * allocate and map the aead extended descriptor
+ */
+static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
+					   bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct caam_aead_alg *alg = container_of(crypto_aead_alg(aead),
+						 typeof(*alg), aead);
+	struct device *qidev = ctx->qidev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	int src_nents, mapped_src_nents, dst_nents = 0, mapped_dst_nents = 0;
+	struct aead_edesc *edesc;
+	dma_addr_t qm_sg_dma, iv_dma = 0;
+	int ivsize = 0;
+	unsigned int authsize = ctx->authsize;
+	int qm_sg_index = 0, qm_sg_ents = 0, qm_sg_bytes;
+	int in_len, out_len;
+	struct qm_sg_entry *sg_table, *fd_sgt;
+	struct caam_drv_ctx *drv_ctx;
+	enum optype op_type = encrypt ? ENCRYPT : DECRYPT;
+
+	drv_ctx = get_drv_ctx(ctx, op_type);
+	if (unlikely(IS_ERR_OR_NULL(drv_ctx)))
+		return (struct aead_edesc *)drv_ctx;
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = qi_cache_alloc(GFP_DMA | flags);
+	if (unlikely(!edesc)) {
+		dev_err(qidev, "could not allocate extended descriptor\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (likely(req->src == req->dst)) {
+		src_nents = sg_nents_for_len(req->src, req->assoclen +
+					     req->cryptlen +
+						(encrypt ? authsize : 0));
+		if (unlikely(src_nents < 0)) {
+			dev_err(qidev, "Insufficient bytes (%d) in src S/G\n",
+				req->assoclen + req->cryptlen +
+				(encrypt ? authsize : 0));
+			qi_cache_free(edesc);
+			return ERR_PTR(src_nents);
+		}
+
+		mapped_src_nents = dma_map_sg(qidev, req->src, src_nents,
+					      DMA_BIDIRECTIONAL);
+		if (unlikely(!mapped_src_nents)) {
+			dev_err(qidev, "unable to map source\n");
+			qi_cache_free(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		src_nents = sg_nents_for_len(req->src, req->assoclen +
+					     req->cryptlen);
+		if (unlikely(src_nents < 0)) {
+			dev_err(qidev, "Insufficient bytes (%d) in src S/G\n",
+				req->assoclen + req->cryptlen);
+			qi_cache_free(edesc);
+			return ERR_PTR(src_nents);
+		}
+
+		dst_nents = sg_nents_for_len(req->dst, req->assoclen +
+					     req->cryptlen +
+					     (encrypt ? authsize :
+							(-authsize)));
+		if (unlikely(dst_nents < 0)) {
+			dev_err(qidev, "Insufficient bytes (%d) in dst S/G\n",
+				req->assoclen + req->cryptlen +
+				(encrypt ? authsize : (-authsize)));
+			qi_cache_free(edesc);
+			return ERR_PTR(dst_nents);
+		}
+
+		if (src_nents) {
+			mapped_src_nents = dma_map_sg(qidev, req->src,
+						      src_nents, DMA_TO_DEVICE);
+			if (unlikely(!mapped_src_nents)) {
+				dev_err(qidev, "unable to map source\n");
+				qi_cache_free(edesc);
+				return ERR_PTR(-ENOMEM);
+			}
+		} else {
+			mapped_src_nents = 0;
+		}
+
+		mapped_dst_nents = dma_map_sg(qidev, req->dst, dst_nents,
+					      DMA_FROM_DEVICE);
+		if (unlikely(!mapped_dst_nents)) {
+			dev_err(qidev, "unable to map destination\n");
+			dma_unmap_sg(qidev, req->src, src_nents, DMA_TO_DEVICE);
+			qi_cache_free(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	if ((alg->caam.rfc3686 && encrypt) || !alg->caam.geniv) {
+		ivsize = crypto_aead_ivsize(aead);
+		iv_dma = dma_map_single(qidev, req->iv, ivsize, DMA_TO_DEVICE);
+		if (dma_mapping_error(qidev, iv_dma)) {
+			dev_err(qidev, "unable to map IV\n");
+			caam_unmap(qidev, req->src, req->dst, src_nents,
+				   dst_nents, 0, 0, op_type, 0, 0);
+			qi_cache_free(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	/*
+	 * Create S/G table: req->assoclen, [IV,] req->src [, req->dst].
+	 * Input is not contiguous.
+	 */
+	qm_sg_ents = 1 + !!ivsize + mapped_src_nents +
+		     (mapped_dst_nents > 1 ? mapped_dst_nents : 0);
+	sg_table = &edesc->sgt[0];
+	qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+
+	edesc->src_nents = src_nents;
+	edesc->dst_nents = dst_nents;
+	edesc->iv_dma = iv_dma;
+	edesc->drv_req.app_ctx = req;
+	edesc->drv_req.cbk = aead_done;
+	edesc->drv_req.drv_ctx = drv_ctx;
+
+	edesc->assoclen_dma = dma_map_single(qidev, &req->assoclen, 4,
+					     DMA_TO_DEVICE);
+	if (dma_mapping_error(qidev, edesc->assoclen_dma)) {
+		dev_err(qidev, "unable to map assoclen\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
+			   iv_dma, ivsize, op_type, 0, 0);
+		qi_cache_free(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dma_to_qm_sg_one(sg_table, edesc->assoclen_dma, 4, 0);
+	qm_sg_index++;
+	if (ivsize) {
+		dma_to_qm_sg_one(sg_table + qm_sg_index, iv_dma, ivsize, 0);
+		qm_sg_index++;
+	}
+	sg_to_qm_sg_last(req->src, mapped_src_nents, sg_table + qm_sg_index, 0);
+	qm_sg_index += mapped_src_nents;
+
+	if (mapped_dst_nents > 1)
+		sg_to_qm_sg_last(req->dst, mapped_dst_nents, sg_table +
+				 qm_sg_index, 0);
+
+	qm_sg_dma = dma_map_single(qidev, sg_table, qm_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(qidev, qm_sg_dma)) {
+		dev_err(qidev, "unable to map S/G table\n");
+		dma_unmap_single(qidev, edesc->assoclen_dma, 4, DMA_TO_DEVICE);
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
+			   iv_dma, ivsize, op_type, 0, 0);
+		qi_cache_free(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	edesc->qm_sg_dma = qm_sg_dma;
+	edesc->qm_sg_bytes = qm_sg_bytes;
+
+	out_len = req->assoclen + req->cryptlen +
+		  (encrypt ? ctx->authsize : (-ctx->authsize));
+	in_len = 4 + ivsize + req->assoclen + req->cryptlen;
+
+	fd_sgt = &edesc->drv_req.fd_sgt[0];
+	dma_to_qm_sg_one_last_ext(&fd_sgt[1], qm_sg_dma, in_len, 0);
+
+	if (req->dst == req->src) {
+		if (mapped_src_nents == 1)
+			dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->src),
+					 out_len, 0);
+		else
+			dma_to_qm_sg_one_ext(&fd_sgt[0], qm_sg_dma +
+					     (1 + !!ivsize) * sizeof(*sg_table),
+					     out_len, 0);
+	} else if (mapped_dst_nents == 1) {
+		dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->dst), out_len,
+				 0);
+	} else {
+		dma_to_qm_sg_one_ext(&fd_sgt[0], qm_sg_dma + sizeof(*sg_table) *
+				     qm_sg_index, out_len, 0);
+	}
+
+	return edesc;
+}
+
+static inline int aead_crypt(struct aead_request *req, bool encrypt)
+{
+	struct aead_edesc *edesc;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	int ret;
+
+	if (unlikely(caam_congested))
+		return -EAGAIN;
+
+	/* allocate extended descriptor */
+	edesc = aead_edesc_alloc(req, encrypt);
+	if (IS_ERR_OR_NULL(edesc))
+		return PTR_ERR(edesc);
+
+	/* Create and submit job descriptor */
+	ret = caam_qi_enqueue(ctx->qidev, &edesc->drv_req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		aead_unmap(ctx->qidev, edesc, req);
+		qi_cache_free(edesc);
+	}
+
+	return ret;
+}
+
+static int aead_encrypt(struct aead_request *req)
+{
+	return aead_crypt(req, true);
+}
+
+static int aead_decrypt(struct aead_request *req)
+{
+	return aead_crypt(req, false);
+}
+
+static void ablkcipher_done(struct caam_drv_req *drv_req, u32 status)
+{
+	struct ablkcipher_edesc *edesc;
+	struct ablkcipher_request *req = drv_req->app_ctx;
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	struct caam_ctx *caam_ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct device *qidev = caam_ctx->qidev;
+#ifdef DEBUG
+	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+
+	dev_err(qidev, "%s %d: status 0x%x\n", __func__, __LINE__, status);
+#endif
+
+	edesc = container_of(drv_req, typeof(*edesc), drv_req);
+
+	if (status)
+		caam_jr_strstatus(qidev, status);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "dstiv  @" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
+		       edesc->src_nents > 1 ? 100 : ivsize, 1);
+	dbg_dump_sg(KERN_ERR, "dst    @" __stringify(__LINE__)": ",
+		    DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
+		    edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
+#endif
+
+	ablkcipher_unmap(qidev, edesc, req);
+	qi_cache_free(edesc);
+
+	ablkcipher_request_complete(req, status);
+}
+
+static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
+						       *req, bool encrypt)
+{
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct device *qidev = ctx->qidev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+					  CRYPTO_TFM_REQ_MAY_SLEEP)) ?
+		       GFP_KERNEL : GFP_ATOMIC;
+	int src_nents, mapped_src_nents, dst_nents = 0, mapped_dst_nents = 0;
+	struct ablkcipher_edesc *edesc;
+	dma_addr_t iv_dma;
+	bool in_contig;
+	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+	int dst_sg_idx, qm_sg_ents;
+	struct qm_sg_entry *sg_table, *fd_sgt;
+	struct caam_drv_ctx *drv_ctx;
+	enum optype op_type = encrypt ? ENCRYPT : DECRYPT;
+
+	drv_ctx = get_drv_ctx(ctx, op_type);
+	if (unlikely(IS_ERR_OR_NULL(drv_ctx)))
+		return (struct ablkcipher_edesc *)drv_ctx;
+
+	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (unlikely(src_nents < 0)) {
+		dev_err(qidev, "Insufficient bytes (%d) in src S/G\n",
+			req->nbytes);
+		return ERR_PTR(src_nents);
+	}
+
+	if (unlikely(req->src != req->dst)) {
+		dst_nents = sg_nents_for_len(req->dst, req->nbytes);
+		if (unlikely(dst_nents < 0)) {
+			dev_err(qidev, "Insufficient bytes (%d) in dst S/G\n",
+				req->nbytes);
+			return ERR_PTR(dst_nents);
+		}
+
+		mapped_src_nents = dma_map_sg(qidev, req->src, src_nents,
+					      DMA_TO_DEVICE);
+		if (unlikely(!mapped_src_nents)) {
+			dev_err(qidev, "unable to map source\n");
+			return ERR_PTR(-ENOMEM);
+		}
+
+		mapped_dst_nents = dma_map_sg(qidev, req->dst, dst_nents,
+					      DMA_FROM_DEVICE);
+		if (unlikely(!mapped_dst_nents)) {
+			dev_err(qidev, "unable to map destination\n");
+			dma_unmap_sg(qidev, req->src, src_nents, DMA_TO_DEVICE);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		mapped_src_nents = dma_map_sg(qidev, req->src, src_nents,
+					      DMA_BIDIRECTIONAL);
+		if (unlikely(!mapped_src_nents)) {
+			dev_err(qidev, "unable to map source\n");
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	iv_dma = dma_map_single(qidev, req->info, ivsize, DMA_TO_DEVICE);
+	if (dma_mapping_error(qidev, iv_dma)) {
+		dev_err(qidev, "unable to map IV\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (mapped_src_nents == 1 &&
+	    iv_dma + ivsize == sg_dma_address(req->src)) {
+		in_contig = true;
+		qm_sg_ents = 0;
+	} else {
+		in_contig = false;
+		qm_sg_ents = 1 + mapped_src_nents;
+	}
+	dst_sg_idx = qm_sg_ents;
+
+	/* allocate space for base edesc and link tables */
+	edesc = qi_cache_alloc(GFP_DMA | flags);
+	if (unlikely(!edesc)) {
+		dev_err(qidev, "could not allocate extended descriptor\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
+			   iv_dma, ivsize, op_type, 0, 0);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	edesc->src_nents = src_nents;
+	edesc->dst_nents = dst_nents;
+	edesc->iv_dma = iv_dma;
+	qm_sg_ents += mapped_dst_nents > 1 ? mapped_dst_nents : 0;
+	sg_table = &edesc->sgt[0];
+	edesc->qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+	edesc->drv_req.app_ctx = req;
+	edesc->drv_req.cbk = ablkcipher_done;
+	edesc->drv_req.drv_ctx = drv_ctx;
+
+	if (!in_contig) {
+		dma_to_qm_sg_one(sg_table, iv_dma, ivsize, 0);
+		sg_to_qm_sg_last(req->src, mapped_src_nents, sg_table + 1, 0);
+	}
+
+	if (mapped_dst_nents > 1)
+		sg_to_qm_sg_last(req->dst, mapped_dst_nents, sg_table +
+				 dst_sg_idx, 0);
+
+	edesc->qm_sg_dma = dma_map_single(qidev, sg_table, edesc->qm_sg_bytes,
+					  DMA_TO_DEVICE);
+	if (dma_mapping_error(qidev, edesc->qm_sg_dma)) {
+		dev_err(qidev, "unable to map S/G table\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
+			   iv_dma, ivsize, op_type, 0, 0);
+		qi_cache_free(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fd_sgt = &edesc->drv_req.fd_sgt[0];
+
+	if (!in_contig)
+		dma_to_qm_sg_one_last_ext(&fd_sgt[1], edesc->qm_sg_dma,
+					  ivsize + req->nbytes, 0);
+	else
+		dma_to_qm_sg_one_last(&fd_sgt[1], iv_dma, ivsize + req->nbytes,
+				      0);
+
+	if (req->src == req->dst) {
+		if (!in_contig)
+			dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma +
+					     sizeof(*sg_table), req->nbytes, 0);
+		else
+			dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->src),
+					 req->nbytes, 0);
+	} else if (mapped_dst_nents > 1) {
+		dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma + dst_sg_idx *
+				     sizeof(*sg_table), req->nbytes, 0);
+	} else {
+		dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->dst),
+				 req->nbytes, 0);
+	}
+
+	return edesc;
+}
+
+static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
+	struct skcipher_givcrypt_request *creq)
+{
+	struct ablkcipher_request *req = &creq->creq;
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	struct device *qidev = ctx->qidev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+					  CRYPTO_TFM_REQ_MAY_SLEEP)) ?
+		       GFP_KERNEL : GFP_ATOMIC;
+	int src_nents, mapped_src_nents, dst_nents, mapped_dst_nents;
+	struct ablkcipher_edesc *edesc;
+	dma_addr_t iv_dma;
+	bool out_contig;
+	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+	struct qm_sg_entry *sg_table, *fd_sgt;
+	int dst_sg_idx, qm_sg_ents;
+	struct caam_drv_ctx *drv_ctx;
+
+	drv_ctx = get_drv_ctx(ctx, GIVENCRYPT);
+	if (unlikely(IS_ERR_OR_NULL(drv_ctx)))
+		return (struct ablkcipher_edesc *)drv_ctx;
+
+	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (unlikely(src_nents < 0)) {
+		dev_err(qidev, "Insufficient bytes (%d) in src S/G\n",
+			req->nbytes);
+		return ERR_PTR(src_nents);
+	}
+
+	if (unlikely(req->src != req->dst)) {
+		dst_nents = sg_nents_for_len(req->dst, req->nbytes);
+		if (unlikely(dst_nents < 0)) {
+			dev_err(qidev, "Insufficient bytes (%d) in dst S/G\n",
+				req->nbytes);
+			return ERR_PTR(dst_nents);
+		}
+
+		mapped_src_nents = dma_map_sg(qidev, req->src, src_nents,
+					      DMA_TO_DEVICE);
+		if (unlikely(!mapped_src_nents)) {
+			dev_err(qidev, "unable to map source\n");
+			return ERR_PTR(-ENOMEM);
+		}
+
+		mapped_dst_nents = dma_map_sg(qidev, req->dst, dst_nents,
+					      DMA_FROM_DEVICE);
+		if (unlikely(!mapped_dst_nents)) {
+			dev_err(qidev, "unable to map destination\n");
+			dma_unmap_sg(qidev, req->src, src_nents, DMA_TO_DEVICE);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		mapped_src_nents = dma_map_sg(qidev, req->src, src_nents,
+					      DMA_BIDIRECTIONAL);
+		if (unlikely(!mapped_src_nents)) {
+			dev_err(qidev, "unable to map source\n");
+			return ERR_PTR(-ENOMEM);
+		}
+
+		dst_nents = src_nents;
+		mapped_dst_nents = src_nents;
+	}
+
+	iv_dma = dma_map_single(qidev, creq->giv, ivsize, DMA_FROM_DEVICE);
+	if (dma_mapping_error(qidev, iv_dma)) {
+		dev_err(qidev, "unable to map IV\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	qm_sg_ents = mapped_src_nents > 1 ? mapped_src_nents : 0;
+	dst_sg_idx = qm_sg_ents;
+	if (mapped_dst_nents == 1 &&
+	    iv_dma + ivsize == sg_dma_address(req->dst)) {
+		out_contig = true;
+	} else {
+		out_contig = false;
+		qm_sg_ents += 1 + mapped_dst_nents;
+	}
+
+	/* allocate space for base edesc and link tables */
+	edesc = qi_cache_alloc(GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(qidev, "could not allocate extended descriptor\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
+			   iv_dma, ivsize, GIVENCRYPT, 0, 0);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	edesc->src_nents = src_nents;
+	edesc->dst_nents = dst_nents;
+	edesc->iv_dma = iv_dma;
+	sg_table = &edesc->sgt[0];
+	edesc->qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+	edesc->drv_req.app_ctx = req;
+	edesc->drv_req.cbk = ablkcipher_done;
+	edesc->drv_req.drv_ctx = drv_ctx;
+
+	if (mapped_src_nents > 1)
+		sg_to_qm_sg_last(req->src, mapped_src_nents, sg_table, 0);
+
+	if (!out_contig) {
+		dma_to_qm_sg_one(sg_table + dst_sg_idx, iv_dma, ivsize, 0);
+		sg_to_qm_sg_last(req->dst, mapped_dst_nents, sg_table +
+				 dst_sg_idx + 1, 0);
+	}
+
+	edesc->qm_sg_dma = dma_map_single(qidev, sg_table, edesc->qm_sg_bytes,
+					  DMA_TO_DEVICE);
+	if (dma_mapping_error(qidev, edesc->qm_sg_dma)) {
+		dev_err(qidev, "unable to map S/G table\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
+			   iv_dma, ivsize, GIVENCRYPT, 0, 0);
+		qi_cache_free(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fd_sgt = &edesc->drv_req.fd_sgt[0];
+
+	if (mapped_src_nents > 1)
+		dma_to_qm_sg_one_ext(&fd_sgt[1], edesc->qm_sg_dma, req->nbytes,
+				     0);
+	else
+		dma_to_qm_sg_one(&fd_sgt[1], sg_dma_address(req->src),
+				 req->nbytes, 0);
+
+	if (!out_contig)
+		dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma + dst_sg_idx *
+				     sizeof(*sg_table), ivsize + req->nbytes,
+				     0);
+	else
+		dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->dst),
+				 ivsize + req->nbytes, 0);
+
+	return edesc;
+}
+
+static inline int ablkcipher_crypt(struct ablkcipher_request *req, bool encrypt)
+{
+	struct ablkcipher_edesc *edesc;
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	int ret;
+
+	if (unlikely(caam_congested))
+		return -EAGAIN;
+
+	/* allocate extended descriptor */
+	edesc = ablkcipher_edesc_alloc(req, encrypt);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	ret = caam_qi_enqueue(ctx->qidev, &edesc->drv_req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ablkcipher_unmap(ctx->qidev, edesc, req);
+		qi_cache_free(edesc);
+	}
+
+	return ret;
+}
+
+static int ablkcipher_encrypt(struct ablkcipher_request *req)
+{
+	return ablkcipher_crypt(req, true);
+}
+
+static int ablkcipher_decrypt(struct ablkcipher_request *req)
+{
+	return ablkcipher_crypt(req, false);
+}
+
+static int ablkcipher_givencrypt(struct skcipher_givcrypt_request *creq)
+{
+	struct ablkcipher_request *req = &creq->creq;
+	struct ablkcipher_edesc *edesc;
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	int ret;
+
+	if (unlikely(caam_congested))
+		return -EAGAIN;
+
+	/* allocate extended descriptor */
+	edesc = ablkcipher_giv_edesc_alloc(creq);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	ret = caam_qi_enqueue(ctx->qidev, &edesc->drv_req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ablkcipher_unmap(ctx->qidev, edesc, req);
+		qi_cache_free(edesc);
+	}
+
+	return ret;
+}
+
+#define template_ablkcipher	template_u.ablkcipher
+struct caam_alg_template {
+	char name[CRYPTO_MAX_ALG_NAME];
+	char driver_name[CRYPTO_MAX_ALG_NAME];
+	unsigned int blocksize;
+	u32 type;
+	union {
+		struct ablkcipher_alg ablkcipher;
+	} template_u;
+	u32 class1_alg_type;
+	u32 class2_alg_type;
+};
+
+static struct caam_alg_template driver_algs[] = {
+	/* ablkcipher descriptor */
+	{
+		.name = "cbc(aes)",
+		.driver_name = "cbc-aes-caam-qi",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+		},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+	},
+	{
+		.name = "cbc(des3_ede)",
+		.driver_name = "cbc-3des-caam-qi",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+		},
+		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+	},
+	{
+		.name = "cbc(des)",
+		.driver_name = "cbc-des-caam-qi",
+		.blocksize = DES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = DES_BLOCK_SIZE,
+		},
+		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+	},
+	{
+		.name = "ctr(aes)",
+		.driver_name = "ctr-aes-caam-qi",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.geniv = "chainiv",
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+		},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
+	},
+	{
+		.name = "rfc3686(ctr(aes))",
+		.driver_name = "rfc3686-ctr-aes-caam-qi",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_GIVCIPHER,
+		.template_ablkcipher = {
+			.setkey = ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.givencrypt = ablkcipher_givencrypt,
+			.geniv = "<built-in>",
+			.min_keysize = AES_MIN_KEY_SIZE +
+				       CTR_RFC3686_NONCE_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE +
+				       CTR_RFC3686_NONCE_SIZE,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+		},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CTR_MOD128,
+	},
+	{
+		.name = "xts(aes)",
+		.driver_name = "xts-aes-caam-qi",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_ablkcipher = {
+			.setkey = xts_ablkcipher_setkey,
+			.encrypt = ablkcipher_encrypt,
+			.decrypt = ablkcipher_decrypt,
+			.geniv = "eseqiv",
+			.min_keysize = 2 * AES_MIN_KEY_SIZE,
+			.max_keysize = 2 * AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+		},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_XTS,
+	},
+};
+
+static struct caam_aead_alg driver_aeads[] = {
+	/* single-pass ipsec_esp descriptor */
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(md5),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-hmac-md5-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha1),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha1-cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha224),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha224-cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha256),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha256-cbc-aes-"
+						   "caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha384),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha384-cbc-aes-"
+						   "caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-aes-caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha512),"
+					    "cbc(aes)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha512-cbc-aes-"
+						   "caam-qi",
+				.cra_blocksize = AES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(md5),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-hmac-md5-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha1),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha1-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha224),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha224-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha256),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha256-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha384),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha384-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha512),"
+					    "cbc(des3_ede)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha512-"
+						   "cbc-des3_ede-caam-qi",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(md5),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-hmac-md5-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_MD5 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha1),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha1-cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA1 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha224),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha224-cbc-des-"
+						   "caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA224 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha256),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha256-cbc-desi-"
+						   "caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA256 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha384-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha384),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha384-cbc-des-"
+						   "caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA384 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),cbc(des))",
+				.cra_driver_name = "authenc-hmac-sha512-"
+						   "cbc-des-caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+		}
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "echainiv(authenc(hmac(sha512),"
+					    "cbc(des)))",
+				.cra_driver_name = "echainiv-authenc-"
+						   "hmac-sha512-cbc-des-"
+						   "caam-qi",
+				.cra_blocksize = DES_BLOCK_SIZE,
+			},
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+			.class2_alg_type = OP_ALG_ALGSEL_SHA512 |
+					   OP_ALG_AAI_HMAC_PRECOMP,
+			.geniv = true,
+		}
+	},
+};
+
+struct caam_crypto_alg {
+	struct list_head entry;
+	struct crypto_alg crypto_alg;
+	struct caam_alg_entry caam;
+};
+
+static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
+{
+	struct caam_drv_private *priv;
+
+	/*
+	 * distribute tfms across job rings to ensure in-order
+	 * crypto request processing per tfm
+	 */
+	ctx->jrdev = caam_jr_alloc();
+	if (IS_ERR(ctx->jrdev)) {
+		pr_err("Job Ring Device allocation for transform failed\n");
+		return PTR_ERR(ctx->jrdev);
+	}
+
+	ctx->key_dma = dma_map_single(ctx->jrdev, ctx->key, sizeof(ctx->key),
+				      DMA_TO_DEVICE);
+	if (dma_mapping_error(ctx->jrdev, ctx->key_dma)) {
+		dev_err(ctx->jrdev, "unable to map key\n");
+		caam_jr_free(ctx->jrdev);
+		return -ENOMEM;
+	}
+
+	/* copy descriptor header template value */
+	ctx->cdata.algtype = OP_TYPE_CLASS1_ALG | caam->class1_alg_type;
+	ctx->adata.algtype = OP_TYPE_CLASS2_ALG | caam->class2_alg_type;
+
+	priv = dev_get_drvdata(ctx->jrdev->parent);
+	ctx->qidev = priv->qidev;
+
+	spin_lock_init(&ctx->lock);
+	ctx->drv_ctx[ENCRYPT] = NULL;
+	ctx->drv_ctx[DECRYPT] = NULL;
+	ctx->drv_ctx[GIVENCRYPT] = NULL;
+
+	return 0;
+}
+
+static int caam_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct caam_crypto_alg *caam_alg = container_of(alg, typeof(*caam_alg),
+							crypto_alg);
+	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	return caam_init_common(ctx, &caam_alg->caam);
+}
+
+static int caam_aead_init(struct crypto_aead *tfm)
+{
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct caam_aead_alg *caam_alg = container_of(alg, typeof(*caam_alg),
+						      aead);
+	struct caam_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return caam_init_common(ctx, &caam_alg->caam);
+}
+
+static void caam_exit_common(struct caam_ctx *ctx)
+{
+	caam_drv_ctx_rel(ctx->drv_ctx[ENCRYPT]);
+	caam_drv_ctx_rel(ctx->drv_ctx[DECRYPT]);
+	caam_drv_ctx_rel(ctx->drv_ctx[GIVENCRYPT]);
+
+	dma_unmap_single(ctx->jrdev, ctx->key_dma, sizeof(ctx->key),
+			 DMA_TO_DEVICE);
+
+	caam_jr_free(ctx->jrdev);
+}
+
+static void caam_cra_exit(struct crypto_tfm *tfm)
+{
+	caam_exit_common(crypto_tfm_ctx(tfm));
+}
+
+static void caam_aead_exit(struct crypto_aead *tfm)
+{
+	caam_exit_common(crypto_aead_ctx(tfm));
+}
+
+static struct list_head alg_list;
+static void __exit caam_qi_algapi_exit(void)
+{
+	struct caam_crypto_alg *t_alg, *n;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
+		struct caam_aead_alg *t_alg = driver_aeads + i;
+
+		if (t_alg->registered)
+			crypto_unregister_aead(&t_alg->aead);
+	}
+
+	if (!alg_list.next)
+		return;
+
+	list_for_each_entry_safe(t_alg, n, &alg_list, entry) {
+		crypto_unregister_alg(&t_alg->crypto_alg);
+		list_del(&t_alg->entry);
+		kfree(t_alg);
+	}
+}
+
+static struct caam_crypto_alg *caam_alg_alloc(struct caam_alg_template
+					      *template)
+{
+	struct caam_crypto_alg *t_alg;
+	struct crypto_alg *alg;
+
+	t_alg = kzalloc(sizeof(*t_alg), GFP_KERNEL);
+	if (!t_alg)
+		return ERR_PTR(-ENOMEM);
+
+	alg = &t_alg->crypto_alg;
+
+	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", template->name);
+	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		 template->driver_name);
+	alg->cra_module = THIS_MODULE;
+	alg->cra_init = caam_cra_init;
+	alg->cra_exit = caam_cra_exit;
+	alg->cra_priority = CAAM_CRA_PRIORITY;
+	alg->cra_blocksize = template->blocksize;
+	alg->cra_alignmask = 0;
+	alg->cra_ctxsize = sizeof(struct caam_ctx);
+	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
+			 template->type;
+	switch (template->type) {
+	case CRYPTO_ALG_TYPE_GIVCIPHER:
+		alg->cra_type = &crypto_givcipher_type;
+		alg->cra_ablkcipher = template->template_ablkcipher;
+		break;
+	case CRYPTO_ALG_TYPE_ABLKCIPHER:
+		alg->cra_type = &crypto_ablkcipher_type;
+		alg->cra_ablkcipher = template->template_ablkcipher;
+		break;
+	}
+
+	t_alg->caam.class1_alg_type = template->class1_alg_type;
+	t_alg->caam.class2_alg_type = template->class2_alg_type;
+
+	return t_alg;
+}
+
+static void caam_aead_alg_init(struct caam_aead_alg *t_alg)
+{
+	struct aead_alg *alg = &t_alg->aead;
+
+	alg->base.cra_module = THIS_MODULE;
+	alg->base.cra_priority = CAAM_CRA_PRIORITY;
+	alg->base.cra_ctxsize = sizeof(struct caam_ctx);
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
+
+	alg->init = caam_aead_init;
+	alg->exit = caam_aead_exit;
+}
+
+static int __init caam_qi_algapi_init(void)
+{
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	struct caam_drv_private *priv;
+	int i = 0, err = 0;
+	u32 cha_vid, cha_inst, des_inst, aes_inst, md_inst;
+	unsigned int md_limit = SHA512_DIGEST_SIZE;
+	bool registered = false;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node) {
+		dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec4.0");
+		if (!dev_node)
+			return -ENODEV;
+	}
+
+	pdev = of_find_device_by_node(dev_node);
+	of_node_put(dev_node);
+	if (!pdev)
+		return -ENODEV;
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+
+	/*
+	 * If priv is NULL, it's probably because the caam driver wasn't
+	 * properly initialized (e.g. RNG4 init failed). Thus, bail out here.
+	 */
+	if (!priv || !priv->qi_present)
+		return -ENODEV;
+
+	INIT_LIST_HEAD(&alg_list);
+
+	/*
+	 * Register crypto algorithms the device supports.
+	 * First, detect presence and attributes of DES, AES, and MD blocks.
+	 */
+	cha_vid = rd_reg32(&priv->ctrl->perfmon.cha_id_ls);
+	cha_inst = rd_reg32(&priv->ctrl->perfmon.cha_num_ls);
+	des_inst = (cha_inst & CHA_ID_LS_DES_MASK) >> CHA_ID_LS_DES_SHIFT;
+	aes_inst = (cha_inst & CHA_ID_LS_AES_MASK) >> CHA_ID_LS_AES_SHIFT;
+	md_inst = (cha_inst & CHA_ID_LS_MD_MASK) >> CHA_ID_LS_MD_SHIFT;
+
+	/* If MD is present, limit digest size based on LP256 */
+	if (md_inst && ((cha_vid & CHA_ID_LS_MD_MASK) == CHA_ID_LS_MD_LP256))
+		md_limit = SHA256_DIGEST_SIZE;
+
+	for (i = 0; i < ARRAY_SIZE(driver_algs); i++) {
+		struct caam_crypto_alg *t_alg;
+		struct caam_alg_template *alg = driver_algs + i;
+		u32 alg_sel = alg->class1_alg_type & OP_ALG_ALGSEL_MASK;
+
+		/* Skip DES algorithms if not supported by device */
+		if (!des_inst &&
+		    ((alg_sel == OP_ALG_ALGSEL_3DES) ||
+		     (alg_sel == OP_ALG_ALGSEL_DES)))
+			continue;
+
+		/* Skip AES algorithms if not supported by device */
+		if (!aes_inst && (alg_sel == OP_ALG_ALGSEL_AES))
+			continue;
+
+		t_alg = caam_alg_alloc(alg);
+		if (IS_ERR(t_alg)) {
+			err = PTR_ERR(t_alg);
+			dev_warn(priv->qidev, "%s alg allocation failed\n",
+				 alg->driver_name);
+			continue;
+		}
+
+		err = crypto_register_alg(&t_alg->crypto_alg);
+		if (err) {
+			dev_warn(priv->qidev, "%s alg registration failed\n",
+				 t_alg->crypto_alg.cra_driver_name);
+			kfree(t_alg);
+			continue;
+		}
+
+		list_add_tail(&t_alg->entry, &alg_list);
+		registered = true;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
+		struct caam_aead_alg *t_alg = driver_aeads + i;
+		u32 c1_alg_sel = t_alg->caam.class1_alg_type &
+				 OP_ALG_ALGSEL_MASK;
+		u32 c2_alg_sel = t_alg->caam.class2_alg_type &
+				 OP_ALG_ALGSEL_MASK;
+		u32 alg_aai = t_alg->caam.class1_alg_type & OP_ALG_AAI_MASK;
+
+		/* Skip DES algorithms if not supported by device */
+		if (!des_inst &&
+		    ((c1_alg_sel == OP_ALG_ALGSEL_3DES) ||
+		     (c1_alg_sel == OP_ALG_ALGSEL_DES)))
+			continue;
+
+		/* Skip AES algorithms if not supported by device */
+		if (!aes_inst && (c1_alg_sel == OP_ALG_ALGSEL_AES))
+			continue;
+
+		/*
+		 * Check support for AES algorithms not available
+		 * on LP devices.
+		 */
+		if (((cha_vid & CHA_ID_LS_AES_MASK) == CHA_ID_LS_AES_LP) &&
+		    (alg_aai == OP_ALG_AAI_GCM))
+			continue;
+
+		/*
+		 * Skip algorithms requiring message digests
+		 * if MD or MD size is not supported by device.
+		 */
+		if (c2_alg_sel &&
+		    (!md_inst || (t_alg->aead.maxauthsize > md_limit)))
+			continue;
+
+		caam_aead_alg_init(t_alg);
+
+		err = crypto_register_aead(&t_alg->aead);
+		if (err) {
+			pr_warn("%s alg registration failed\n",
+				t_alg->aead.base.cra_driver_name);
+			continue;
+		}
+
+		t_alg->registered = true;
+		registered = true;
+	}
+
+	if (registered)
+		dev_info(priv->qidev, "algorithms registered in /proc/crypto\n");
+
+	return err;
+}
+
+module_init(caam_qi_algapi_init);
+module_exit(caam_qi_algapi_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Support for crypto API using CAAM-QI backend");
+MODULE_AUTHOR("Freescale Semiconductor");
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 32100c4851dd..49cbdcba7883 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -506,7 +506,7 @@ static int caam_rsa_init_tfm(struct crypto_akcipher *tfm)
 	ctx->dev = caam_jr_alloc();
 
 	if (IS_ERR(ctx->dev)) {
-		dev_err(ctx->dev, "Job Ring Device allocation for transform failed\n");
+		pr_err("Job Ring Device allocation for transform failed\n");
 		return PTR_ERR(ctx->dev);
 	}
 
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index fef39f9f41ee..dd353e342c12 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -18,6 +18,10 @@
 bool caam_little_end;
 EXPORT_SYMBOL(caam_little_end);
 
+#ifdef CONFIG_CAAM_QI
+#include "qi.h"
+#endif
+
 /*
  * i.MX targets tend to have clock control subsystems that can
  * enable/disable clocking to our device.
@@ -281,7 +285,8 @@ static int deinstantiate_rng(struct device *ctrldev, int state_handle_mask)
 			/* Try to run it through DECO0 */
 			ret = run_descriptor_deco0(ctrldev, desc, &status);
 
-			if (ret || status) {
+			if (ret ||
+			    (status && status != JRSTA_SSRC_JUMP_HALT_CC)) {
 				dev_err(ctrldev,
 					"Failed to deinstantiate RNG4 SH%d\n",
 					sh_idx);
@@ -301,15 +306,18 @@ static int caam_remove(struct platform_device *pdev)
 	struct device *ctrldev;
 	struct caam_drv_private *ctrlpriv;
 	struct caam_ctrl __iomem *ctrl;
-	int ring;
 
 	ctrldev = &pdev->dev;
 	ctrlpriv = dev_get_drvdata(ctrldev);
 	ctrl = (struct caam_ctrl __iomem *)ctrlpriv->ctrl;
 
-	/* Remove platform devices for JobRs */
-	for (ring = 0; ring < ctrlpriv->total_jobrs; ring++)
-		of_device_unregister(ctrlpriv->jrpdev[ring]);
+	/* Remove platform devices under the crypto node */
+	of_platform_depopulate(ctrldev);
+
+#ifdef CONFIG_CAAM_QI
+	if (ctrlpriv->qidev)
+		caam_qi_shutdown(ctrlpriv->qidev);
+#endif
 
 	/* De-initialize RNG state handles initialized by this driver. */
 	if (ctrlpriv->rng4_sh_init)
@@ -401,27 +409,21 @@ int caam_get_era(void)
 }
 EXPORT_SYMBOL(caam_get_era);
 
-#ifdef CONFIG_DEBUG_FS
-static int caam_debugfs_u64_get(void *data, u64 *val)
-{
-	*val = caam64_to_cpu(*(u64 *)data);
-	return 0;
-}
-
-static int caam_debugfs_u32_get(void *data, u64 *val)
-{
-	*val = caam32_to_cpu(*(u32 *)data);
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
-#endif
+static const struct of_device_id caam_match[] = {
+	{
+		.compatible = "fsl,sec-v4.0",
+	},
+	{
+		.compatible = "fsl,sec4.0",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, caam_match);
 
 /* Probe routine for CAAM top (controller) level */
 static int caam_probe(struct platform_device *pdev)
 {
-	int ret, ring, ridx, rspec, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
+	int ret, ring, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
 	u64 caam_id;
 	struct device *dev;
 	struct device_node *nprop, *np;
@@ -597,47 +599,36 @@ static int caam_probe(struct platform_device *pdev)
 		goto iounmap_ctrl;
 	}
 
+	ret = of_platform_populate(nprop, caam_match, NULL, dev);
+	if (ret) {
+		dev_err(dev, "JR platform devices creation error\n");
+		goto iounmap_ctrl;
+	}
+
+#ifdef CONFIG_DEBUG_FS
 	/*
-	 * Detect and enable JobRs
-	 * First, find out how many ring spec'ed, allocate references
-	 * for all, then go probe each one.
+	 * FIXME: needs better naming distinction, as some amalgamation of
+	 * "caam" and nprop->full_name. The OF name isn't distinctive,
+	 * but does separate instances
 	 */
-	rspec = 0;
-	for_each_available_child_of_node(nprop, np)
-		if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
-		    of_device_is_compatible(np, "fsl,sec4.0-job-ring"))
-			rspec++;
+	perfmon = (struct caam_perfmon __force *)&ctrl->perfmon;
 
-	ctrlpriv->jrpdev = devm_kcalloc(&pdev->dev, rspec,
-					sizeof(*ctrlpriv->jrpdev), GFP_KERNEL);
-	if (ctrlpriv->jrpdev == NULL) {
-		ret = -ENOMEM;
-		goto iounmap_ctrl;
-	}
+	ctrlpriv->dfs_root = debugfs_create_dir(dev_name(dev), NULL);
+	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
+#endif
 
 	ring = 0;
-	ridx = 0;
-	ctrlpriv->total_jobrs = 0;
 	for_each_available_child_of_node(nprop, np)
 		if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
 		    of_device_is_compatible(np, "fsl,sec4.0-job-ring")) {
-			ctrlpriv->jrpdev[ring] =
-				of_platform_device_create(np, NULL, dev);
-			if (!ctrlpriv->jrpdev[ring]) {
-				pr_warn("JR physical index %d: Platform device creation error\n",
-					ridx);
-				ridx++;
-				continue;
-			}
 			ctrlpriv->jr[ring] = (struct caam_job_ring __iomem __force *)
 					     ((__force uint8_t *)ctrl +
-					     (ridx + JR_BLOCK_NUMBER) *
+					     (ring + JR_BLOCK_NUMBER) *
 					      BLOCK_OFFSET
 					     );
 			ctrlpriv->total_jobrs++;
 			ring++;
-			ridx++;
-	}
+		}
 
 	/* Check to see if QI present. If so, enable */
 	ctrlpriv->qi_present =
@@ -650,6 +641,13 @@ static int caam_probe(struct platform_device *pdev)
 			       );
 		/* This is all that's required to physically enable QI */
 		wr_reg32(&ctrlpriv->qi->qi_control_lo, QICTL_DQEN);
+
+		/* If QMAN driver is present, init CAAM-QI backend */
+#ifdef CONFIG_CAAM_QI
+		ret = caam_qi_init(pdev);
+		if (ret)
+			dev_err(dev, "caam qi i/f init failed: %d\n", ret);
+#endif
 	}
 
 	/* If no QI and no rings specified, quit and go home */
@@ -737,17 +735,6 @@ static int caam_probe(struct platform_device *pdev)
 		 ctrlpriv->total_jobrs, ctrlpriv->qi_present);
 
 #ifdef CONFIG_DEBUG_FS
-	/*
-	 * FIXME: needs better naming distinction, as some amalgamation of
-	 * "caam" and nprop->full_name. The OF name isn't distinctive,
-	 * but does separate instances
-	 */
-	perfmon = (struct caam_perfmon __force *)&ctrl->perfmon;
-
-	ctrlpriv->dfs_root = debugfs_create_dir(dev_name(dev), NULL);
-	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
-
-	/* Controller-level - performance monitor counters */
 
 	ctrlpriv->ctl_rq_dequeued =
 		debugfs_create_file("rq_dequeued",
@@ -830,6 +817,9 @@ static int caam_probe(struct platform_device *pdev)
 	return 0;
 
 caam_remove:
+#ifdef CONFIG_DEBUG_FS
+	debugfs_remove_recursive(ctrlpriv->dfs_root);
+#endif
 	caam_remove(pdev);
 	return ret;
 
@@ -847,17 +837,6 @@ disable_caam_ipg:
 	return ret;
 }
 
-static struct of_device_id caam_match[] = {
-	{
-		.compatible = "fsl,sec-v4.0",
-	},
-	{
-		.compatible = "fsl,sec4.0",
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, caam_match);
-
 static struct platform_driver caam_driver = {
 	.driver = {
 		.name = "caam",
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index b9c8d98ef826..d8e83ca104e0 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -4,6 +4,9 @@
  * Copyright 2008-2012 Freescale Semiconductor, Inc.
  */
 
+#ifndef DESC_CONSTR_H
+#define DESC_CONSTR_H
+
 #include "desc.h"
 #include "regs.h"
 
@@ -491,3 +494,5 @@ static inline int desc_inline_query(unsigned int sd_base_len,
 
 	return (rem_bytes >= 0) ? 0 : -1;
 }
+
+#endif /* DESC_CONSTR_H */
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index e2bcacc1a921..85b6c5835b8f 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -66,7 +66,9 @@ struct caam_drv_private_jr {
 struct caam_drv_private {
 
 	struct device *dev;
-	struct platform_device **jrpdev; /* Alloc'ed array per sub-device */
+#ifdef CONFIG_CAAM_QI
+	struct device *qidev;
+#endif
 	struct platform_device *pdev;
 
 	/* Physical-presence section */
@@ -110,9 +112,30 @@ struct caam_drv_private {
 
 	struct debugfs_blob_wrapper ctl_kek_wrap, ctl_tkek_wrap, ctl_tdsk_wrap;
 	struct dentry *ctl_kek, *ctl_tkek, *ctl_tdsk;
+#ifdef CONFIG_CAAM_QI
+	struct dentry *qi_congested;
+#endif
 #endif
 };
 
 void caam_jr_algapi_init(struct device *dev);
 void caam_jr_algapi_remove(struct device *dev);
+
+#ifdef CONFIG_DEBUG_FS
+static int caam_debugfs_u64_get(void *data, u64 *val)
+{
+	*val = caam64_to_cpu(*(u64 *)data);
+	return 0;
+}
+
+static int caam_debugfs_u32_get(void *data, u64 *val)
+{
+	*val = caam32_to_cpu(*(u32 *)data);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
+#endif
+
 #endif /* INTERN_H */
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
new file mode 100644
index 000000000000..1990ed460c46
--- /dev/null
+++ b/drivers/crypto/caam/qi.c
@@ -0,0 +1,805 @@
+/*
+ * CAAM/SEC 4.x QI transport/backend driver
+ * Queue Interface backend functionality
+ *
+ * Copyright 2013-2016 Freescale Semiconductor, Inc.
+ * Copyright 2016-2017 NXP
+ */
+
+#include <linux/cpumask.h>
+#include <linux/kthread.h>
+#include <soc/fsl/qman.h>
+
+#include "regs.h"
+#include "qi.h"
+#include "desc.h"
+#include "intern.h"
+#include "desc_constr.h"
+
+#define PREHDR_RSLS_SHIFT	31
+
+/*
+ * Use a reasonable backlog of frames (per CPU) as congestion threshold,
+ * so that resources used by the in-flight buffers do not become a memory hog.
+ */
+#define MAX_RSP_FQ_BACKLOG_PER_CPU	256
+
+/* Length of a single buffer in the QI driver memory cache */
+#define CAAM_QI_MEMCACHE_SIZE	512
+
+#define CAAM_QI_ENQUEUE_RETRIES	10000
+
+#define CAAM_NAPI_WEIGHT	63
+
+/*
+ * caam_napi - struct holding CAAM NAPI-related params
+ * @irqtask: IRQ task for QI backend
+ * @p: QMan portal
+ */
+struct caam_napi {
+	struct napi_struct irqtask;
+	struct qman_portal *p;
+};
+
+/*
+ * caam_qi_pcpu_priv - percpu private data structure to main list of pending
+ *                     responses expected on each cpu.
+ * @caam_napi: CAAM NAPI params
+ * @net_dev: netdev used by NAPI
+ * @rsp_fq: response FQ from CAAM
+ */
+struct caam_qi_pcpu_priv {
+	struct caam_napi caam_napi;
+	struct net_device net_dev;
+	struct qman_fq *rsp_fq;
+} ____cacheline_aligned;
+
+static DEFINE_PER_CPU(struct caam_qi_pcpu_priv, pcpu_qipriv);
+
+/*
+ * caam_qi_priv - CAAM QI backend private params
+ * @cgr: QMan congestion group
+ * @qi_pdev: platform device for QI backend
+ */
+struct caam_qi_priv {
+	struct qman_cgr cgr;
+	struct platform_device *qi_pdev;
+};
+
+static struct caam_qi_priv qipriv ____cacheline_aligned;
+
+/*
+ * This is written by only one core - the one that initialized the CGR - and
+ * read by multiple cores (all the others).
+ */
+bool caam_congested __read_mostly;
+EXPORT_SYMBOL(caam_congested);
+
+#ifdef CONFIG_DEBUG_FS
+/*
+ * This is a counter for the number of times the congestion group (where all
+ * the request and response queueus are) reached congestion. Incremented
+ * each time the congestion callback is called with congested == true.
+ */
+static u64 times_congested;
+#endif
+
+/*
+ * CPU from where the module initialised. This is required because QMan driver
+ * requires CGRs to be removed from same CPU from where they were originally
+ * allocated.
+ */
+static int mod_init_cpu;
+
+/*
+ * This is a a cache of buffers, from which the users of CAAM QI driver
+ * can allocate short (CAAM_QI_MEMCACHE_SIZE) buffers. It's faster than
+ * doing malloc on the hotpath.
+ * NOTE: A more elegant solution would be to have some headroom in the frames
+ *       being processed. This could be added by the dpaa-ethernet driver.
+ *       This would pose a problem for userspace application processing which
+ *       cannot know of this limitation. So for now, this will work.
+ * NOTE: The memcache is SMP-safe. No need to handle spinlocks in-here
+ */
+static struct kmem_cache *qi_cache;
+
+int caam_qi_enqueue(struct device *qidev, struct caam_drv_req *req)
+{
+	struct qm_fd fd;
+	dma_addr_t addr;
+	int ret;
+	int num_retries = 0;
+
+	qm_fd_clear_fd(&fd);
+	qm_fd_set_compound(&fd, qm_sg_entry_get_len(&req->fd_sgt[1]));
+
+	addr = dma_map_single(qidev, req->fd_sgt, sizeof(req->fd_sgt),
+			      DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(qidev, addr)) {
+		dev_err(qidev, "DMA mapping error for QI enqueue request\n");
+		return -EIO;
+	}
+	qm_fd_addr_set64(&fd, addr);
+
+	do {
+		ret = qman_enqueue(req->drv_ctx->req_fq, &fd);
+		if (likely(!ret))
+			return 0;
+
+		if (ret != -EBUSY)
+			break;
+		num_retries++;
+	} while (num_retries < CAAM_QI_ENQUEUE_RETRIES);
+
+	dev_err(qidev, "qman_enqueue failed: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(caam_qi_enqueue);
+
+static void caam_fq_ern_cb(struct qman_portal *qm, struct qman_fq *fq,
+			   const union qm_mr_entry *msg)
+{
+	const struct qm_fd *fd;
+	struct caam_drv_req *drv_req;
+	struct device *qidev = &(raw_cpu_ptr(&pcpu_qipriv)->net_dev.dev);
+
+	fd = &msg->ern.fd;
+
+	if (qm_fd_get_format(fd) != qm_fd_compound) {
+		dev_err(qidev, "Non-compound FD from CAAM\n");
+		return;
+	}
+
+	drv_req = (struct caam_drv_req *)phys_to_virt(qm_fd_addr_get64(fd));
+	if (!drv_req) {
+		dev_err(qidev,
+			"Can't find original request for CAAM response\n");
+		return;
+	}
+
+	dma_unmap_single(drv_req->drv_ctx->qidev, qm_fd_addr(fd),
+			 sizeof(drv_req->fd_sgt), DMA_BIDIRECTIONAL);
+
+	drv_req->cbk(drv_req, -EIO);
+}
+
+static struct qman_fq *create_caam_req_fq(struct device *qidev,
+					  struct qman_fq *rsp_fq,
+					  dma_addr_t hwdesc,
+					  int fq_sched_flag)
+{
+	int ret;
+	struct qman_fq *req_fq;
+	struct qm_mcc_initfq opts;
+
+	req_fq = kzalloc(sizeof(*req_fq), GFP_ATOMIC);
+	if (!req_fq)
+		return ERR_PTR(-ENOMEM);
+
+	req_fq->cb.ern = caam_fq_ern_cb;
+	req_fq->cb.fqs = NULL;
+
+	ret = qman_create_fq(0, QMAN_FQ_FLAG_DYNAMIC_FQID |
+				QMAN_FQ_FLAG_TO_DCPORTAL, req_fq);
+	if (ret) {
+		dev_err(qidev, "Failed to create session req FQ\n");
+		goto create_req_fq_fail;
+	}
+
+	memset(&opts, 0, sizeof(opts));
+	opts.we_mask = cpu_to_be16(QM_INITFQ_WE_FQCTRL | QM_INITFQ_WE_DESTWQ |
+				   QM_INITFQ_WE_CONTEXTB |
+				   QM_INITFQ_WE_CONTEXTA | QM_INITFQ_WE_CGID);
+	opts.fqd.fq_ctrl = cpu_to_be16(QM_FQCTRL_CPCSTASH | QM_FQCTRL_CGE);
+	qm_fqd_set_destwq(&opts.fqd, qm_channel_caam, 2);
+	opts.fqd.context_b = cpu_to_be32(qman_fq_fqid(rsp_fq));
+	qm_fqd_context_a_set64(&opts.fqd, hwdesc);
+	opts.fqd.cgid = qipriv.cgr.cgrid;
+
+	ret = qman_init_fq(req_fq, fq_sched_flag, &opts);
+	if (ret) {
+		dev_err(qidev, "Failed to init session req FQ\n");
+		goto init_req_fq_fail;
+	}
+
+	dev_info(qidev, "Allocated request FQ %u for CPU %u\n", req_fq->fqid,
+		 smp_processor_id());
+	return req_fq;
+
+init_req_fq_fail:
+	qman_destroy_fq(req_fq);
+create_req_fq_fail:
+	kfree(req_fq);
+	return ERR_PTR(ret);
+}
+
+static int empty_retired_fq(struct device *qidev, struct qman_fq *fq)
+{
+	int ret;
+
+	ret = qman_volatile_dequeue(fq, QMAN_VOLATILE_FLAG_WAIT_INT |
+				    QMAN_VOLATILE_FLAG_FINISH,
+				    QM_VDQCR_PRECEDENCE_VDQCR |
+				    QM_VDQCR_NUMFRAMES_TILLEMPTY);
+	if (ret) {
+		dev_err(qidev, "Volatile dequeue fail for FQ: %u\n", fq->fqid);
+		return ret;
+	}
+
+	do {
+		struct qman_portal *p;
+
+		p = qman_get_affine_portal(smp_processor_id());
+		qman_p_poll_dqrr(p, 16);
+	} while (fq->flags & QMAN_FQ_STATE_NE);
+
+	return 0;
+}
+
+static int kill_fq(struct device *qidev, struct qman_fq *fq)
+{
+	u32 flags;
+	int ret;
+
+	ret = qman_retire_fq(fq, &flags);
+	if (ret < 0) {
+		dev_err(qidev, "qman_retire_fq failed: %d\n", ret);
+		return ret;
+	}
+
+	if (!ret)
+		goto empty_fq;
+
+	/* Async FQ retirement condition */
+	if (ret == 1) {
+		/* Retry till FQ gets in retired state */
+		do {
+			msleep(20);
+		} while (fq->state != qman_fq_state_retired);
+
+		WARN_ON(fq->flags & QMAN_FQ_STATE_BLOCKOOS);
+		WARN_ON(fq->flags & QMAN_FQ_STATE_ORL);
+	}
+
+empty_fq:
+	if (fq->flags & QMAN_FQ_STATE_NE) {
+		ret = empty_retired_fq(qidev, fq);
+		if (ret) {
+			dev_err(qidev, "empty_retired_fq fail for FQ: %u\n",
+				fq->fqid);
+			return ret;
+		}
+	}
+
+	ret = qman_oos_fq(fq);
+	if (ret)
+		dev_err(qidev, "OOS of FQID: %u failed\n", fq->fqid);
+
+	qman_destroy_fq(fq);
+
+	return ret;
+}
+
+static int empty_caam_fq(struct qman_fq *fq)
+{
+	int ret;
+	struct qm_mcr_queryfq_np np;
+
+	/* Wait till the older CAAM FQ get empty */
+	do {
+		ret = qman_query_fq_np(fq, &np);
+		if (ret)
+			return ret;
+
+		if (!qm_mcr_np_get(&np, frm_cnt))
+			break;
+
+		msleep(20);
+	} while (1);
+
+	/*
+	 * Give extra time for pending jobs from this FQ in holding tanks
+	 * to get processed
+	 */
+	msleep(20);
+	return 0;
+}
+
+int caam_drv_ctx_update(struct caam_drv_ctx *drv_ctx, u32 *sh_desc)
+{
+	int ret;
+	u32 num_words;
+	struct qman_fq *new_fq, *old_fq;
+	struct device *qidev = drv_ctx->qidev;
+
+	num_words = desc_len(sh_desc);
+	if (num_words > MAX_SDLEN) {
+		dev_err(qidev, "Invalid descriptor len: %d words\n", num_words);
+		return -EINVAL;
+	}
+
+	/* Note down older req FQ */
+	old_fq = drv_ctx->req_fq;
+
+	/* Create a new req FQ in parked state */
+	new_fq = create_caam_req_fq(drv_ctx->qidev, drv_ctx->rsp_fq,
+				    drv_ctx->context_a, 0);
+	if (unlikely(IS_ERR_OR_NULL(new_fq))) {
+		dev_err(qidev, "FQ allocation for shdesc update failed\n");
+		return PTR_ERR(new_fq);
+	}
+
+	/* Hook up new FQ to context so that new requests keep queuing */
+	drv_ctx->req_fq = new_fq;
+
+	/* Empty and remove the older FQ */
+	ret = empty_caam_fq(old_fq);
+	if (ret) {
+		dev_err(qidev, "Old CAAM FQ empty failed: %d\n", ret);
+
+		/* We can revert to older FQ */
+		drv_ctx->req_fq = old_fq;
+
+		if (kill_fq(qidev, new_fq))
+			dev_warn(qidev, "New CAAM FQ: %u kill failed\n",
+				 new_fq->fqid);
+
+		return ret;
+	}
+
+	/*
+	 * Re-initialise pre-header. Set RSLS and SDLEN.
+	 * Update the shared descriptor for driver context.
+	 */
+	drv_ctx->prehdr[0] = cpu_to_caam32((1 << PREHDR_RSLS_SHIFT) |
+					   num_words);
+	memcpy(drv_ctx->sh_desc, sh_desc, desc_bytes(sh_desc));
+	dma_sync_single_for_device(qidev, drv_ctx->context_a,
+				   sizeof(drv_ctx->sh_desc) +
+				   sizeof(drv_ctx->prehdr),
+				   DMA_BIDIRECTIONAL);
+
+	/* Put the new FQ in scheduled state */
+	ret = qman_schedule_fq(new_fq);
+	if (ret) {
+		dev_err(qidev, "Fail to sched new CAAM FQ, ecode = %d\n", ret);
+
+		/*
+		 * We can kill new FQ and revert to old FQ.
+		 * Since the desc is already modified, it is success case
+		 */
+
+		drv_ctx->req_fq = old_fq;
+
+		if (kill_fq(qidev, new_fq))
+			dev_warn(qidev, "New CAAM FQ: %u kill failed\n",
+				 new_fq->fqid);
+	} else if (kill_fq(qidev, old_fq)) {
+		dev_warn(qidev, "Old CAAM FQ: %u kill failed\n", old_fq->fqid);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(caam_drv_ctx_update);
+
+struct caam_drv_ctx *caam_drv_ctx_init(struct device *qidev,
+				       int *cpu,
+				       u32 *sh_desc)
+{
+	size_t size;
+	u32 num_words;
+	dma_addr_t hwdesc;
+	struct caam_drv_ctx *drv_ctx;
+	const cpumask_t *cpus = qman_affine_cpus();
+	static DEFINE_PER_CPU(int, last_cpu);
+
+	num_words = desc_len(sh_desc);
+	if (num_words > MAX_SDLEN) {
+		dev_err(qidev, "Invalid descriptor len: %d words\n",
+			num_words);
+		return ERR_PTR(-EINVAL);
+	}
+
+	drv_ctx = kzalloc(sizeof(*drv_ctx), GFP_ATOMIC);
+	if (!drv_ctx)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Initialise pre-header - set RSLS and SDLEN - and shared descriptor
+	 * and dma-map them.
+	 */
+	drv_ctx->prehdr[0] = cpu_to_caam32((1 << PREHDR_RSLS_SHIFT) |
+					   num_words);
+	memcpy(drv_ctx->sh_desc, sh_desc, desc_bytes(sh_desc));
+	size = sizeof(drv_ctx->prehdr) + sizeof(drv_ctx->sh_desc);
+	hwdesc = dma_map_single(qidev, drv_ctx->prehdr, size,
+				DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(qidev, hwdesc)) {
+		dev_err(qidev, "DMA map error for preheader + shdesc\n");
+		kfree(drv_ctx);
+		return ERR_PTR(-ENOMEM);
+	}
+	drv_ctx->context_a = hwdesc;
+
+	/* If given CPU does not own the portal, choose another one that does */
+	if (!cpumask_test_cpu(*cpu, cpus)) {
+		int *pcpu = &get_cpu_var(last_cpu);
+
+		*pcpu = cpumask_next(*pcpu, cpus);
+		if (*pcpu >= nr_cpu_ids)
+			*pcpu = cpumask_first(cpus);
+		*cpu = *pcpu;
+
+		put_cpu_var(last_cpu);
+	}
+	drv_ctx->cpu = *cpu;
+
+	/* Find response FQ hooked with this CPU */
+	drv_ctx->rsp_fq = per_cpu(pcpu_qipriv.rsp_fq, drv_ctx->cpu);
+
+	/* Attach request FQ */
+	drv_ctx->req_fq = create_caam_req_fq(qidev, drv_ctx->rsp_fq, hwdesc,
+					     QMAN_INITFQ_FLAG_SCHED);
+	if (unlikely(IS_ERR_OR_NULL(drv_ctx->req_fq))) {
+		dev_err(qidev, "create_caam_req_fq failed\n");
+		dma_unmap_single(qidev, hwdesc, size, DMA_BIDIRECTIONAL);
+		kfree(drv_ctx);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	drv_ctx->qidev = qidev;
+	return drv_ctx;
+}
+EXPORT_SYMBOL(caam_drv_ctx_init);
+
+void *qi_cache_alloc(gfp_t flags)
+{
+	return kmem_cache_alloc(qi_cache, flags);
+}
+EXPORT_SYMBOL(qi_cache_alloc);
+
+void qi_cache_free(void *obj)
+{
+	kmem_cache_free(qi_cache, obj);
+}
+EXPORT_SYMBOL(qi_cache_free);
+
+static int caam_qi_poll(struct napi_struct *napi, int budget)
+{
+	struct caam_napi *np = container_of(napi, struct caam_napi, irqtask);
+
+	int cleaned = qman_p_poll_dqrr(np->p, budget);
+
+	if (cleaned < budget) {
+		napi_complete(napi);
+		qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
+	}
+
+	return cleaned;
+}
+
+void caam_drv_ctx_rel(struct caam_drv_ctx *drv_ctx)
+{
+	if (IS_ERR_OR_NULL(drv_ctx))
+		return;
+
+	/* Remove request FQ */
+	if (kill_fq(drv_ctx->qidev, drv_ctx->req_fq))
+		dev_err(drv_ctx->qidev, "Crypto session req FQ kill failed\n");
+
+	dma_unmap_single(drv_ctx->qidev, drv_ctx->context_a,
+			 sizeof(drv_ctx->sh_desc) + sizeof(drv_ctx->prehdr),
+			 DMA_BIDIRECTIONAL);
+	kfree(drv_ctx);
+}
+EXPORT_SYMBOL(caam_drv_ctx_rel);
+
+int caam_qi_shutdown(struct device *qidev)
+{
+	int i, ret;
+	struct caam_qi_priv *priv = dev_get_drvdata(qidev);
+	const cpumask_t *cpus = qman_affine_cpus();
+	struct cpumask old_cpumask = current->cpus_allowed;
+
+	for_each_cpu(i, cpus) {
+		struct napi_struct *irqtask;
+
+		irqtask = &per_cpu_ptr(&pcpu_qipriv.caam_napi, i)->irqtask;
+		napi_disable(irqtask);
+		netif_napi_del(irqtask);
+
+		if (kill_fq(qidev, per_cpu(pcpu_qipriv.rsp_fq, i)))
+			dev_err(qidev, "Rsp FQ kill failed, cpu: %d\n", i);
+		kfree(per_cpu(pcpu_qipriv.rsp_fq, i));
+	}
+
+	/*
+	 * QMan driver requires CGRs to be deleted from same CPU from where they
+	 * were instantiated. Hence we get the module removal execute from the
+	 * same CPU from where it was originally inserted.
+	 */
+	set_cpus_allowed_ptr(current, get_cpu_mask(mod_init_cpu));
+
+	ret = qman_delete_cgr(&priv->cgr);
+	if (ret)
+		dev_err(qidev, "Deletion of CGR failed: %d\n", ret);
+	else
+		qman_release_cgrid(priv->cgr.cgrid);
+
+	kmem_cache_destroy(qi_cache);
+
+	/* Now that we're done with the CGRs, restore the cpus allowed mask */
+	set_cpus_allowed_ptr(current, &old_cpumask);
+
+	platform_device_unregister(priv->qi_pdev);
+	return ret;
+}
+
+static void cgr_cb(struct qman_portal *qm, struct qman_cgr *cgr, int congested)
+{
+	caam_congested = congested;
+
+	if (congested) {
+#ifdef CONFIG_DEBUG_FS
+		times_congested++;
+#endif
+		pr_debug_ratelimited("CAAM entered congestion\n");
+
+	} else {
+		pr_debug_ratelimited("CAAM exited congestion\n");
+	}
+}
+
+static int caam_qi_napi_schedule(struct qman_portal *p, struct caam_napi *np)
+{
+	/*
+	 * In case of threaded ISR, for RT kernels in_irq() does not return
+	 * appropriate value, so use in_serving_softirq to distinguish between
+	 * softirq and irq contexts.
+	 */
+	if (unlikely(in_irq() || !in_serving_softirq())) {
+		/* Disable QMan IRQ source and invoke NAPI */
+		qman_p_irqsource_remove(p, QM_PIRQ_DQRI);
+		np->p = p;
+		napi_schedule(&np->irqtask);
+		return 1;
+	}
+	return 0;
+}
+
+static enum qman_cb_dqrr_result caam_rsp_fq_dqrr_cb(struct qman_portal *p,
+						    struct qman_fq *rsp_fq,
+						    const struct qm_dqrr_entry *dqrr)
+{
+	struct caam_napi *caam_napi = raw_cpu_ptr(&pcpu_qipriv.caam_napi);
+	struct caam_drv_req *drv_req;
+	const struct qm_fd *fd;
+	struct device *qidev = &(raw_cpu_ptr(&pcpu_qipriv)->net_dev.dev);
+	u32 status;
+
+	if (caam_qi_napi_schedule(p, caam_napi))
+		return qman_cb_dqrr_stop;
+
+	fd = &dqrr->fd;
+	status = be32_to_cpu(fd->status);
+	if (unlikely(status))
+		dev_err(qidev, "Error: %#x in CAAM response FD\n", status);
+
+	if (unlikely(qm_fd_get_format(fd) != qm_fd_compound)) {
+		dev_err(qidev, "Non-compound FD from CAAM\n");
+		return qman_cb_dqrr_consume;
+	}
+
+	drv_req = (struct caam_drv_req *)phys_to_virt(qm_fd_addr_get64(fd));
+	if (unlikely(!drv_req)) {
+		dev_err(qidev,
+			"Can't find original request for caam response\n");
+		return qman_cb_dqrr_consume;
+	}
+
+	dma_unmap_single(drv_req->drv_ctx->qidev, qm_fd_addr(fd),
+			 sizeof(drv_req->fd_sgt), DMA_BIDIRECTIONAL);
+
+	drv_req->cbk(drv_req, status);
+	return qman_cb_dqrr_consume;
+}
+
+static int alloc_rsp_fq_cpu(struct device *qidev, unsigned int cpu)
+{
+	struct qm_mcc_initfq opts;
+	struct qman_fq *fq;
+	int ret;
+
+	fq = kzalloc(sizeof(*fq), GFP_KERNEL | GFP_DMA);
+	if (!fq)
+		return -ENOMEM;
+
+	fq->cb.dqrr = caam_rsp_fq_dqrr_cb;
+
+	ret = qman_create_fq(0, QMAN_FQ_FLAG_NO_ENQUEUE |
+			     QMAN_FQ_FLAG_DYNAMIC_FQID, fq);
+	if (ret) {
+		dev_err(qidev, "Rsp FQ create failed\n");
+		kfree(fq);
+		return -ENODEV;
+	}
+
+	memset(&opts, 0, sizeof(opts));
+	opts.we_mask = cpu_to_be16(QM_INITFQ_WE_FQCTRL | QM_INITFQ_WE_DESTWQ |
+				   QM_INITFQ_WE_CONTEXTB |
+				   QM_INITFQ_WE_CONTEXTA | QM_INITFQ_WE_CGID);
+	opts.fqd.fq_ctrl = cpu_to_be16(QM_FQCTRL_CTXASTASHING |
+				       QM_FQCTRL_CPCSTASH | QM_FQCTRL_CGE);
+	qm_fqd_set_destwq(&opts.fqd, qman_affine_channel(cpu), 3);
+	opts.fqd.cgid = qipriv.cgr.cgrid;
+	opts.fqd.context_a.stashing.exclusive =	QM_STASHING_EXCL_CTX |
+						QM_STASHING_EXCL_DATA;
+	qm_fqd_set_stashing(&opts.fqd, 0, 1, 1);
+
+	ret = qman_init_fq(fq, QMAN_INITFQ_FLAG_SCHED, &opts);
+	if (ret) {
+		dev_err(qidev, "Rsp FQ init failed\n");
+		kfree(fq);
+		return -ENODEV;
+	}
+
+	per_cpu(pcpu_qipriv.rsp_fq, cpu) = fq;
+
+	dev_info(qidev, "Allocated response FQ %u for CPU %u", fq->fqid, cpu);
+	return 0;
+}
+
+static int init_cgr(struct device *qidev)
+{
+	int ret;
+	struct qm_mcc_initcgr opts;
+	const u64 cpus = *(u64 *)qman_affine_cpus();
+	const int num_cpus = hweight64(cpus);
+	const u64 val = num_cpus * MAX_RSP_FQ_BACKLOG_PER_CPU;
+
+	ret = qman_alloc_cgrid(&qipriv.cgr.cgrid);
+	if (ret) {
+		dev_err(qidev, "CGR alloc failed for rsp FQs: %d\n", ret);
+		return ret;
+	}
+
+	qipriv.cgr.cb = cgr_cb;
+	memset(&opts, 0, sizeof(opts));
+	opts.we_mask = cpu_to_be16(QM_CGR_WE_CSCN_EN | QM_CGR_WE_CS_THRES |
+				   QM_CGR_WE_MODE);
+	opts.cgr.cscn_en = QM_CGR_EN;
+	opts.cgr.mode = QMAN_CGR_MODE_FRAME;
+	qm_cgr_cs_thres_set64(&opts.cgr.cs_thres, val, 1);
+
+	ret = qman_create_cgr(&qipriv.cgr, QMAN_CGR_FLAG_USE_INIT, &opts);
+	if (ret) {
+		dev_err(qidev, "Error %d creating CAAM CGRID: %u\n", ret,
+			qipriv.cgr.cgrid);
+		return ret;
+	}
+
+	dev_info(qidev, "Congestion threshold set to %llu\n", val);
+	return 0;
+}
+
+static int alloc_rsp_fqs(struct device *qidev)
+{
+	int ret, i;
+	const cpumask_t *cpus = qman_affine_cpus();
+
+	/*Now create response FQs*/
+	for_each_cpu(i, cpus) {
+		ret = alloc_rsp_fq_cpu(qidev, i);
+		if (ret) {
+			dev_err(qidev, "CAAM rsp FQ alloc failed, cpu: %u", i);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void free_rsp_fqs(void)
+{
+	int i;
+	const cpumask_t *cpus = qman_affine_cpus();
+
+	for_each_cpu(i, cpus)
+		kfree(per_cpu(pcpu_qipriv.rsp_fq, i));
+}
+
+int caam_qi_init(struct platform_device *caam_pdev)
+{
+	int err, i;
+	struct platform_device *qi_pdev;
+	struct device *ctrldev = &caam_pdev->dev, *qidev;
+	struct caam_drv_private *ctrlpriv;
+	const cpumask_t *cpus = qman_affine_cpus();
+	struct cpumask old_cpumask = current->cpus_allowed;
+	static struct platform_device_info qi_pdev_info = {
+		.name = "caam_qi",
+		.id = PLATFORM_DEVID_NONE
+	};
+
+	/*
+	 * QMAN requires CGRs to be removed from same CPU+portal from where it
+	 * was originally allocated. Hence we need to note down the
+	 * initialisation CPU and use the same CPU for module exit.
+	 * We select the first CPU to from the list of portal owning CPUs.
+	 * Then we pin module init to this CPU.
+	 */
+	mod_init_cpu = cpumask_first(cpus);
+	set_cpus_allowed_ptr(current, get_cpu_mask(mod_init_cpu));
+
+	qi_pdev_info.parent = ctrldev;
+	qi_pdev_info.dma_mask = dma_get_mask(ctrldev);
+	qi_pdev = platform_device_register_full(&qi_pdev_info);
+	if (IS_ERR(qi_pdev))
+		return PTR_ERR(qi_pdev);
+
+	ctrlpriv = dev_get_drvdata(ctrldev);
+	qidev = &qi_pdev->dev;
+
+	qipriv.qi_pdev = qi_pdev;
+	dev_set_drvdata(qidev, &qipriv);
+
+	/* Initialize the congestion detection */
+	err = init_cgr(qidev);
+	if (err) {
+		dev_err(qidev, "CGR initialization failed: %d\n", err);
+		platform_device_unregister(qi_pdev);
+		return err;
+	}
+
+	/* Initialise response FQs */
+	err = alloc_rsp_fqs(qidev);
+	if (err) {
+		dev_err(qidev, "Can't allocate CAAM response FQs: %d\n", err);
+		free_rsp_fqs();
+		platform_device_unregister(qi_pdev);
+		return err;
+	}
+
+	/*
+	 * Enable the NAPI contexts on each of the core which has an affine
+	 * portal.
+	 */
+	for_each_cpu(i, cpus) {
+		struct caam_qi_pcpu_priv *priv = per_cpu_ptr(&pcpu_qipriv, i);
+		struct caam_napi *caam_napi = &priv->caam_napi;
+		struct napi_struct *irqtask = &caam_napi->irqtask;
+		struct net_device *net_dev = &priv->net_dev;
+
+		net_dev->dev = *qidev;
+		INIT_LIST_HEAD(&net_dev->napi_list);
+
+		netif_napi_add(net_dev, irqtask, caam_qi_poll,
+			       CAAM_NAPI_WEIGHT);
+
+		napi_enable(irqtask);
+	}
+
+	/* Hook up QI device to parent controlling caam device */
+	ctrlpriv->qidev = qidev;
+
+	qi_cache = kmem_cache_create("caamqicache", CAAM_QI_MEMCACHE_SIZE, 0,
+				     SLAB_CACHE_DMA, NULL);
+	if (!qi_cache) {
+		dev_err(qidev, "Can't allocate CAAM cache\n");
+		free_rsp_fqs();
+		platform_device_unregister(qi_pdev);
+		return -ENOMEM;
+	}
+
+	/* Done with the CGRs; restore the cpus allowed mask */
+	set_cpus_allowed_ptr(current, &old_cpumask);
+#ifdef CONFIG_DEBUG_FS
+	ctrlpriv->qi_congested = debugfs_create_file("qi_congested", 0444,
+						     ctrlpriv->ctl,
+						     &times_congested,
+						     &caam_fops_u64_ro);
+#endif
+	dev_info(qidev, "Linux CAAM Queue I/F driver initialised\n");
+	return 0;
+}
diff --git a/drivers/crypto/caam/qi.h b/drivers/crypto/caam/qi.h
new file mode 100644
index 000000000000..33b0433f5f22
--- /dev/null
+++ b/drivers/crypto/caam/qi.h
@@ -0,0 +1,201 @@
+/*
+ * Public definitions for the CAAM/QI (Queue Interface) backend.
+ *
+ * Copyright 2013-2016 Freescale Semiconductor, Inc.
+ * Copyright 2016-2017 NXP
+ */
+
+#ifndef __QI_H__
+#define __QI_H__
+
+#include <soc/fsl/qman.h>
+#include "compat.h"
+#include "desc.h"
+#include "desc_constr.h"
+
+/*
+ * CAAM hardware constructs a job descriptor which points to a shared descriptor
+ * (as pointed by context_a of to-CAAM FQ).
+ * When the job descriptor is executed by DECO, the whole job descriptor
+ * together with shared descriptor gets loaded in DECO buffer, which is
+ * 64 words (each 32-bit) long.
+ *
+ * The job descriptor constructed by CAAM hardware has the following layout:
+ *
+ *	HEADER		(1 word)
+ *	Shdesc ptr	(1 or 2 words)
+ *	SEQ_OUT_PTR	(1 word)
+ *	Out ptr		(1 or 2 words)
+ *	Out length	(1 word)
+ *	SEQ_IN_PTR	(1 word)
+ *	In ptr		(1 or 2 words)
+ *	In length	(1 word)
+ *
+ * The shdesc ptr is used to fetch shared descriptor contents into DECO buffer.
+ *
+ * Apart from shdesc contents, the total number of words that get loaded in DECO
+ * buffer are '8' or '11'. The remaining words in DECO buffer can be used for
+ * storing shared descriptor.
+ */
+#define MAX_SDLEN	((CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN) / CAAM_CMD_SZ)
+
+extern bool caam_congested __read_mostly;
+
+/*
+ * This is the request structure the driver application should fill while
+ * submitting a job to driver.
+ */
+struct caam_drv_req;
+
+/*
+ * caam_qi_cbk - application's callback function invoked by the driver when the
+ *               request has been successfully processed.
+ * @drv_req: original request that was submitted
+ * @status: completion status of request (0 - success, non-zero - error code)
+ */
+typedef void (*caam_qi_cbk)(struct caam_drv_req *drv_req, u32 status);
+
+enum optype {
+	ENCRYPT,
+	DECRYPT,
+	GIVENCRYPT,
+	NUM_OP
+};
+
+/**
+ * caam_drv_ctx - CAAM/QI backend driver context
+ *
+ * The jobs are processed by the driver against a driver context.
+ * With every cryptographic context, a driver context is attached.
+ * The driver context contains data for private use by driver.
+ * For the applications, this is an opaque structure.
+ *
+ * @prehdr: preheader placed before shrd desc
+ * @sh_desc: shared descriptor
+ * @context_a: shared descriptor dma address
+ * @req_fq: to-CAAM request frame queue
+ * @rsp_fq: from-CAAM response frame queue
+ * @cpu: cpu on which to receive CAAM response
+ * @op_type: operation type
+ * @qidev: device pointer for CAAM/QI backend
+ */
+struct caam_drv_ctx {
+	u32 prehdr[2];
+	u32 sh_desc[MAX_SDLEN];
+	dma_addr_t context_a;
+	struct qman_fq *req_fq;
+	struct qman_fq *rsp_fq;
+	int cpu;
+	enum optype op_type;
+	struct device *qidev;
+} ____cacheline_aligned;
+
+/**
+ * caam_drv_req - The request structure the driver application should fill while
+ *                submitting a job to driver.
+ * @fd_sgt: QMan S/G pointing to output (fd_sgt[0]) and input (fd_sgt[1])
+ *          buffers.
+ * @cbk: callback function to invoke when job is completed
+ * @app_ctx: arbitrary context attached with request by the application
+ *
+ * The fields mentioned below should not be used by application.
+ * These are for private use by driver.
+ *
+ * @hdr__: linked list header to maintain list of outstanding requests to CAAM
+ * @hwaddr: DMA address for the S/G table.
+ */
+struct caam_drv_req {
+	struct qm_sg_entry fd_sgt[2];
+	struct caam_drv_ctx *drv_ctx;
+	caam_qi_cbk cbk;
+	void *app_ctx;
+} ____cacheline_aligned;
+
+/**
+ * caam_drv_ctx_init - Initialise a CAAM/QI driver context
+ *
+ * A CAAM/QI driver context must be attached with each cryptographic context.
+ * This function allocates memory for CAAM/QI context and returns a handle to
+ * the application. This handle must be submitted along with each enqueue
+ * request to the driver by the application.
+ *
+ * @cpu: CPU where the application prefers to the driver to receive CAAM
+ *       responses. The request completion callback would be issued from this
+ *       CPU.
+ * @sh_desc: shared descriptor pointer to be attached with CAAM/QI driver
+ *           context.
+ *
+ * Returns a driver context on success or negative error code on failure.
+ */
+struct caam_drv_ctx *caam_drv_ctx_init(struct device *qidev, int *cpu,
+				       u32 *sh_desc);
+
+/**
+ * caam_qi_enqueue - Submit a request to QI backend driver.
+ *
+ * The request structure must be properly filled as described above.
+ *
+ * @qidev: device pointer for QI backend
+ * @req: CAAM QI request structure
+ *
+ * Returns 0 on success or negative error code on failure.
+ */
+int caam_qi_enqueue(struct device *qidev, struct caam_drv_req *req);
+
+/**
+ * caam_drv_ctx_busy - Check if there are too many jobs pending with CAAM
+ *		       or too many CAAM responses are pending to be processed.
+ * @drv_ctx: driver context for which job is to be submitted
+ *
+ * Returns caam congestion status 'true/false'
+ */
+bool caam_drv_ctx_busy(struct caam_drv_ctx *drv_ctx);
+
+/**
+ * caam_drv_ctx_update - Update QI driver context
+ *
+ * Invoked when shared descriptor is required to be change in driver context.
+ *
+ * @drv_ctx: driver context to be updated
+ * @sh_desc: new shared descriptor pointer to be updated in QI driver context
+ *
+ * Returns 0 on success or negative error code on failure.
+ */
+int caam_drv_ctx_update(struct caam_drv_ctx *drv_ctx, u32 *sh_desc);
+
+/**
+ * caam_drv_ctx_rel - Release a QI driver context
+ * @drv_ctx: context to be released
+ */
+void caam_drv_ctx_rel(struct caam_drv_ctx *drv_ctx);
+
+int caam_qi_init(struct platform_device *pdev);
+int caam_qi_shutdown(struct device *dev);
+
+/**
+ * qi_cache_alloc - Allocate buffers from CAAM-QI cache
+ *
+ * Invoked when a user of the CAAM-QI (i.e. caamalg-qi) needs data which has
+ * to be allocated on the hotpath. Instead of using malloc, one can use the
+ * services of the CAAM QI memory cache (backed by kmem_cache). The buffers
+ * will have a size of 256B, which is sufficient for hosting 16 SG entries.
+ *
+ * @flags: flags that would be used for the equivalent malloc(..) call
+ *
+ * Returns a pointer to a retrieved buffer on success or NULL on failure.
+ */
+void *qi_cache_alloc(gfp_t flags);
+
+/**
+ * qi_cache_free - Frees buffers allocated from CAAM-QI cache
+ *
+ * Invoked when a user of the CAAM-QI (i.e. caamalg-qi) no longer needs
+ * the buffer previously allocated by a qi_cache_alloc call.
+ * No checking is being done, the call is a passthrough call to
+ * kmem_cache_free(...)
+ *
+ * @obj: object previously allocated using qi_cache_alloc()
+ */
+void qi_cache_free(void *obj);
+
+#endif /* __QI_H__ */
diff --git a/drivers/crypto/caam/sg_sw_qm.h b/drivers/crypto/caam/sg_sw_qm.h
new file mode 100644
index 000000000000..d000b4df745f
--- /dev/null
+++ b/drivers/crypto/caam/sg_sw_qm.h
@@ -0,0 +1,108 @@
+/*
+ * Copyright 2013-2016 Freescale Semiconductor, Inc.
+ * Copyright 2016-2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __SG_SW_QM_H
+#define __SG_SW_QM_H
+
+#include <soc/fsl/qman.h>
+#include "regs.h"
+
+static inline void __dma_to_qm_sg(struct qm_sg_entry *qm_sg_ptr, dma_addr_t dma,
+				  u16 offset)
+{
+	qm_sg_entry_set64(qm_sg_ptr, dma);
+	qm_sg_ptr->__reserved2 = 0;
+	qm_sg_ptr->bpid = 0;
+	qm_sg_ptr->offset = cpu_to_be16(offset & QM_SG_OFF_MASK);
+}
+
+static inline void dma_to_qm_sg_one(struct qm_sg_entry *qm_sg_ptr,
+				    dma_addr_t dma, u32 len, u16 offset)
+{
+	__dma_to_qm_sg(qm_sg_ptr, dma, offset);
+	qm_sg_entry_set_len(qm_sg_ptr, len);
+}
+
+static inline void dma_to_qm_sg_one_last(struct qm_sg_entry *qm_sg_ptr,
+					 dma_addr_t dma, u32 len, u16 offset)
+{
+	__dma_to_qm_sg(qm_sg_ptr, dma, offset);
+	qm_sg_entry_set_f(qm_sg_ptr, len);
+}
+
+static inline void dma_to_qm_sg_one_ext(struct qm_sg_entry *qm_sg_ptr,
+					dma_addr_t dma, u32 len, u16 offset)
+{
+	__dma_to_qm_sg(qm_sg_ptr, dma, offset);
+	qm_sg_ptr->cfg = cpu_to_be32(QM_SG_EXT | (len & QM_SG_LEN_MASK));
+}
+
+static inline void dma_to_qm_sg_one_last_ext(struct qm_sg_entry *qm_sg_ptr,
+					     dma_addr_t dma, u32 len,
+					     u16 offset)
+{
+	__dma_to_qm_sg(qm_sg_ptr, dma, offset);
+	qm_sg_ptr->cfg = cpu_to_be32(QM_SG_EXT | QM_SG_FIN |
+				     (len & QM_SG_LEN_MASK));
+}
+
+/*
+ * convert scatterlist to h/w link table format
+ * but does not have final bit; instead, returns last entry
+ */
+static inline struct qm_sg_entry *
+sg_to_qm_sg(struct scatterlist *sg, int sg_count,
+	    struct qm_sg_entry *qm_sg_ptr, u16 offset)
+{
+	while (sg_count && sg) {
+		dma_to_qm_sg_one(qm_sg_ptr, sg_dma_address(sg),
+				 sg_dma_len(sg), offset);
+		qm_sg_ptr++;
+		sg = sg_next(sg);
+		sg_count--;
+	}
+	return qm_sg_ptr - 1;
+}
+
+/*
+ * convert scatterlist to h/w link table format
+ * scatterlist must have been previously dma mapped
+ */
+static inline void sg_to_qm_sg_last(struct scatterlist *sg, int sg_count,
+				    struct qm_sg_entry *qm_sg_ptr, u16 offset)
+{
+	qm_sg_ptr = sg_to_qm_sg(sg, sg_count, qm_sg_ptr, offset);
+	qm_sg_entry_set_f(qm_sg_ptr, qm_sg_entry_get_len(qm_sg_ptr));
+}
+
+#endif /* __SG_SW_QM_H */
diff --git a/drivers/crypto/cavium/Makefile b/drivers/crypto/cavium/Makefile
new file mode 100644
index 000000000000..641268b784be
--- /dev/null
+++ b/drivers/crypto/cavium/Makefile
@@ -0,0 +1,4 @@
+#
+# Makefile for Cavium crypto device drivers
+#
+obj-$(CONFIG_CRYPTO_DEV_CAVIUM_ZIP) += zip/
diff --git a/drivers/crypto/cavium/zip/Makefile b/drivers/crypto/cavium/zip/Makefile
new file mode 100644
index 000000000000..b2f3baaff757
--- /dev/null
+++ b/drivers/crypto/cavium/zip/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for Cavium's ZIP Driver.
+#
+
+obj-$(CONFIG_CRYPTO_DEV_CAVIUM_ZIP) += thunderx_zip.o
+thunderx_zip-y := zip_main.o    \
+                  zip_device.o  \
+                  zip_crypto.o  \
+                  zip_mem.o     \
+                  zip_deflate.o \
+                  zip_inflate.o
diff --git a/drivers/crypto/cavium/zip/common.h b/drivers/crypto/cavium/zip/common.h
new file mode 100644
index 000000000000..dc451e0a43c5
--- /dev/null
+++ b/drivers/crypto/cavium/zip/common.h
@@ -0,0 +1,202 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __COMMON_H__
+#define __COMMON_H__
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/seq_file.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/version.h>
+
+/* Device specific zlib function definitions */
+#include "zip_device.h"
+
+/* ZIP device definitions */
+#include "zip_main.h"
+
+/* ZIP memory allocation/deallocation related definitions */
+#include "zip_mem.h"
+
+/* Device specific structure definitions */
+#include "zip_regs.h"
+
+#define ZIP_ERROR    -1
+
+#define ZIP_FLUSH_FINISH  4
+
+#define RAW_FORMAT		0  /* for rawpipe */
+#define ZLIB_FORMAT		1  /* for zpipe */
+#define GZIP_FORMAT		2  /* for gzpipe */
+#define LZS_FORMAT		3  /* for lzspipe */
+
+/* Max number of ZIP devices supported */
+#define MAX_ZIP_DEVICES		2
+
+/* Configures the number of zip queues to be used */
+#define ZIP_NUM_QUEUES		2
+
+#define DYNAMIC_STOP_EXCESS	1024
+
+/* Maximum buffer sizes in direct mode */
+#define MAX_INPUT_BUFFER_SIZE   (64 * 1024)
+#define MAX_OUTPUT_BUFFER_SIZE  (64 * 1024)
+
+/**
+ * struct zip_operation - common data structure for comp and decomp operations
+ * @input:               Next input byte is read from here
+ * @output:              Next output byte written here
+ * @ctx_addr:            Inflate context buffer address
+ * @history:             Pointer to the history buffer
+ * @input_len:           Number of bytes available at next_in
+ * @input_total_len:     Total number of input bytes read
+ * @output_len:          Remaining free space at next_out
+ * @output_total_len:    Total number of bytes output so far
+ * @csum:                Checksum value of the uncompressed data
+ * @flush:               Flush flag
+ * @format:              Format (depends on stream's wrap)
+ * @speed:               Speed depends on stream's level
+ * @ccode:               Compression code ( stream's strategy)
+ * @lzs_flag:            Flag for LZS support
+ * @begin_file:          Beginning of file indication for inflate
+ * @history_len:         Size of the history data
+ * @end_file:            Ending of the file indication for inflate
+ * @compcode:            Completion status of the ZIP invocation
+ * @bytes_read:          Input bytes read in current instruction
+ * @bits_processed:      Total bits processed for entire file
+ * @sizeofptr:           To distinguish between ILP32 and LP64
+ * @sizeofzops:          Optional just for padding
+ *
+ * This structure is used to maintain the required meta data for the
+ * comp and decomp operations.
+ */
+struct zip_operation {
+	u8    *input;
+	u8    *output;
+	u64   ctx_addr;
+	u64   history;
+
+	u32   input_len;
+	u32   input_total_len;
+
+	u32   output_len;
+	u32   output_total_len;
+
+	u32   csum;
+	u32   flush;
+
+	u32   format;
+	u32   speed;
+	u32   ccode;
+	u32   lzs_flag;
+
+	u32   begin_file;
+	u32   history_len;
+
+	u32   end_file;
+	u32   compcode;
+	u32   bytes_read;
+	u32   bits_processed;
+
+	u32   sizeofptr;
+	u32   sizeofzops;
+};
+
+/* error messages */
+#define zip_err(fmt, args...) pr_err("ZIP ERR:%s():%d: " \
+			      fmt "\n", __func__, __LINE__, ## args)
+
+#ifdef MSG_ENABLE
+/* Enable all messages */
+#define zip_msg(fmt, args...) pr_info("ZIP_MSG:" fmt "\n", ## args)
+#else
+#define zip_msg(fmt, args...)
+#endif
+
+#if defined(ZIP_DEBUG_ENABLE) && defined(MSG_ENABLE)
+
+#ifdef DEBUG_LEVEL
+
+#define FILE_NAME (strrchr(__FILE__, '/') ? strrchr(__FILE__, '/') + 1 : \
+	strrchr(__FILE__, '\\') ? strrchr(__FILE__, '\\') + 1 : __FILE__)
+
+#if DEBUG_LEVEL >= 4
+
+#define zip_dbg(fmt, args...) pr_info("ZIP DBG: %s: %s() : %d: " \
+			      fmt "\n", FILE_NAME, __func__, __LINE__, ## args)
+
+#elif DEBUG_LEVEL >= 3
+
+#define zip_dbg(fmt, args...) pr_info("ZIP DBG: %s: %s() : %d: " \
+			      fmt "\n", FILE_NAME, __func__, __LINE__, ## args)
+
+#elif DEBUG_LEVEL >= 2
+
+#define zip_dbg(fmt, args...) pr_info("ZIP DBG: %s() : %d: " \
+			      fmt "\n", __func__, __LINE__, ## args)
+
+#else
+
+#define zip_dbg(fmt, args...) pr_info("ZIP DBG:" fmt "\n", ## args)
+
+#endif /* DEBUG LEVEL >=4 */
+
+#else
+
+#define zip_dbg(fmt, args...) pr_info("ZIP DBG:" fmt "\n", ## args)
+
+#endif /* DEBUG_LEVEL */
+#else
+
+#define zip_dbg(fmt, args...)
+
+#endif /* ZIP_DEBUG_ENABLE && MSG_ENABLE*/
+
+#endif
diff --git a/drivers/crypto/cavium/zip/zip_crypto.c b/drivers/crypto/cavium/zip/zip_crypto.c
new file mode 100644
index 000000000000..8df4d26cf9d4
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_crypto.c
@@ -0,0 +1,313 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#include "zip_crypto.h"
+
+static void zip_static_init_zip_ops(struct zip_operation *zip_ops,
+				    int lzs_flag)
+{
+	zip_ops->flush        = ZIP_FLUSH_FINISH;
+
+	/* equivalent to level 6 of opensource zlib */
+	zip_ops->speed          = 1;
+
+	if (!lzs_flag) {
+		zip_ops->ccode		= 0; /* Auto Huffman */
+		zip_ops->lzs_flag	= 0;
+		zip_ops->format		= ZLIB_FORMAT;
+	} else {
+		zip_ops->ccode		= 3; /* LZS Encoding */
+		zip_ops->lzs_flag	= 1;
+		zip_ops->format		= LZS_FORMAT;
+	}
+	zip_ops->begin_file   = 1;
+	zip_ops->history_len  = 0;
+	zip_ops->end_file     = 1;
+	zip_ops->compcode     = 0;
+	zip_ops->csum	      = 1; /* Adler checksum desired */
+}
+
+int zip_ctx_init(struct zip_kernel_ctx *zip_ctx, int lzs_flag)
+{
+	struct zip_operation  *comp_ctx   = &zip_ctx->zip_comp;
+	struct zip_operation  *decomp_ctx = &zip_ctx->zip_decomp;
+
+	zip_static_init_zip_ops(comp_ctx, lzs_flag);
+	zip_static_init_zip_ops(decomp_ctx, lzs_flag);
+
+	comp_ctx->input  = zip_data_buf_alloc(MAX_INPUT_BUFFER_SIZE);
+	if (!comp_ctx->input)
+		return -ENOMEM;
+
+	comp_ctx->output = zip_data_buf_alloc(MAX_OUTPUT_BUFFER_SIZE);
+	if (!comp_ctx->output)
+		goto err_comp_input;
+
+	decomp_ctx->input  = zip_data_buf_alloc(MAX_INPUT_BUFFER_SIZE);
+	if (!decomp_ctx->input)
+		goto err_comp_output;
+
+	decomp_ctx->output = zip_data_buf_alloc(MAX_OUTPUT_BUFFER_SIZE);
+	if (!decomp_ctx->output)
+		goto err_decomp_input;
+
+	return 0;
+
+err_decomp_input:
+	zip_data_buf_free(decomp_ctx->input, MAX_INPUT_BUFFER_SIZE);
+
+err_comp_output:
+	zip_data_buf_free(comp_ctx->output, MAX_OUTPUT_BUFFER_SIZE);
+
+err_comp_input:
+	zip_data_buf_free(comp_ctx->input, MAX_INPUT_BUFFER_SIZE);
+
+	return -ENOMEM;
+}
+
+void zip_ctx_exit(struct zip_kernel_ctx *zip_ctx)
+{
+	struct zip_operation  *comp_ctx   = &zip_ctx->zip_comp;
+	struct zip_operation  *dec_ctx = &zip_ctx->zip_decomp;
+
+	zip_data_buf_free(comp_ctx->input, MAX_INPUT_BUFFER_SIZE);
+	zip_data_buf_free(comp_ctx->output, MAX_OUTPUT_BUFFER_SIZE);
+
+	zip_data_buf_free(dec_ctx->input, MAX_INPUT_BUFFER_SIZE);
+	zip_data_buf_free(dec_ctx->output, MAX_OUTPUT_BUFFER_SIZE);
+}
+
+int zip_compress(const u8 *src, unsigned int slen,
+		 u8 *dst, unsigned int *dlen,
+		 struct zip_kernel_ctx *zip_ctx)
+{
+	struct zip_operation  *zip_ops   = NULL;
+	struct zip_state      zip_state;
+	struct zip_device     *zip = NULL;
+	int ret;
+
+	if (!zip_ctx || !src || !dst || !dlen)
+		return -ENOMEM;
+
+	zip = zip_get_device(zip_get_node_id());
+	if (!zip)
+		return -ENODEV;
+
+	memset(&zip_state, 0, sizeof(struct zip_state));
+	zip_ops = &zip_ctx->zip_comp;
+
+	zip_ops->input_len  = slen;
+	zip_ops->output_len = *dlen;
+	memcpy(zip_ops->input, src, slen);
+
+	ret = zip_deflate(zip_ops, &zip_state, zip);
+
+	if (!ret) {
+		*dlen = zip_ops->output_len;
+		memcpy(dst, zip_ops->output, *dlen);
+	}
+
+	return ret;
+}
+
+int zip_decompress(const u8 *src, unsigned int slen,
+		   u8 *dst, unsigned int *dlen,
+		   struct zip_kernel_ctx *zip_ctx)
+{
+	struct zip_operation  *zip_ops   = NULL;
+	struct zip_state      zip_state;
+	struct zip_device     *zip = NULL;
+	int ret;
+
+	if (!zip_ctx || !src || !dst || !dlen)
+		return -ENOMEM;
+
+	zip = zip_get_device(zip_get_node_id());
+	if (!zip)
+		return -ENODEV;
+
+	memset(&zip_state, 0, sizeof(struct zip_state));
+	zip_ops = &zip_ctx->zip_decomp;
+	memcpy(zip_ops->input, src, slen);
+
+	/* Work around for a bug in zlib which needs an extra bytes sometimes */
+	if (zip_ops->ccode != 3) /* Not LZS Encoding */
+		zip_ops->input[slen++] = 0;
+
+	zip_ops->input_len  = slen;
+	zip_ops->output_len = *dlen;
+
+	ret = zip_inflate(zip_ops, &zip_state, zip);
+
+	if (!ret) {
+		*dlen = zip_ops->output_len;
+		memcpy(dst, zip_ops->output, *dlen);
+	}
+
+	return ret;
+}
+
+/* Legacy Compress framework start */
+int zip_alloc_comp_ctx_deflate(struct crypto_tfm *tfm)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm);
+
+	ret = zip_ctx_init(zip_ctx, 0);
+
+	return ret;
+}
+
+int zip_alloc_comp_ctx_lzs(struct crypto_tfm *tfm)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm);
+
+	ret = zip_ctx_init(zip_ctx, 1);
+
+	return ret;
+}
+
+void zip_free_comp_ctx(struct crypto_tfm *tfm)
+{
+	struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm);
+
+	zip_ctx_exit(zip_ctx);
+}
+
+int  zip_comp_compress(struct crypto_tfm *tfm,
+		       const u8 *src, unsigned int slen,
+		       u8 *dst, unsigned int *dlen)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm);
+
+	ret = zip_compress(src, slen, dst, dlen, zip_ctx);
+
+	return ret;
+}
+
+int  zip_comp_decompress(struct crypto_tfm *tfm,
+			 const u8 *src, unsigned int slen,
+			 u8 *dst, unsigned int *dlen)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm);
+
+	ret = zip_decompress(src, slen, dst, dlen, zip_ctx);
+
+	return ret;
+} /* Legacy compress framework end */
+
+/* SCOMP framework start */
+void *zip_alloc_scomp_ctx_deflate(struct crypto_scomp *tfm)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx;
+
+	zip_ctx = kzalloc(sizeof(*zip_ctx), GFP_KERNEL);
+	if (!zip_ctx)
+		return ERR_PTR(-ENOMEM);
+
+	ret = zip_ctx_init(zip_ctx, 0);
+
+	if (ret) {
+		kzfree(zip_ctx);
+		return ERR_PTR(ret);
+	}
+
+	return zip_ctx;
+}
+
+void *zip_alloc_scomp_ctx_lzs(struct crypto_scomp *tfm)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx;
+
+	zip_ctx = kzalloc(sizeof(*zip_ctx), GFP_KERNEL);
+	if (!zip_ctx)
+		return ERR_PTR(-ENOMEM);
+
+	ret = zip_ctx_init(zip_ctx, 1);
+
+	if (ret) {
+		kzfree(zip_ctx);
+		return ERR_PTR(ret);
+	}
+
+	return zip_ctx;
+}
+
+void zip_free_scomp_ctx(struct crypto_scomp *tfm, void *ctx)
+{
+	struct zip_kernel_ctx *zip_ctx = ctx;
+
+	zip_ctx_exit(zip_ctx);
+	kzfree(zip_ctx);
+}
+
+int zip_scomp_compress(struct crypto_scomp *tfm,
+		       const u8 *src, unsigned int slen,
+		       u8 *dst, unsigned int *dlen, void *ctx)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx  = ctx;
+
+	ret = zip_compress(src, slen, dst, dlen, zip_ctx);
+
+	return ret;
+}
+
+int zip_scomp_decompress(struct crypto_scomp *tfm,
+			 const u8 *src, unsigned int slen,
+			 u8 *dst, unsigned int *dlen, void *ctx)
+{
+	int ret;
+	struct zip_kernel_ctx *zip_ctx = ctx;
+
+	ret = zip_decompress(src, slen, dst, dlen, zip_ctx);
+
+	return ret;
+} /* SCOMP framework end */
diff --git a/drivers/crypto/cavium/zip/zip_crypto.h b/drivers/crypto/cavium/zip/zip_crypto.h
new file mode 100644
index 000000000000..b59ddfcacd34
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_crypto.h
@@ -0,0 +1,79 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_CRYPTO_H__
+#define __ZIP_CRYPTO_H__
+
+#include <linux/crypto.h>
+#include <crypto/internal/scompress.h>
+#include "common.h"
+#include "zip_deflate.h"
+#include "zip_inflate.h"
+
+struct zip_kernel_ctx {
+	struct zip_operation zip_comp;
+	struct zip_operation zip_decomp;
+};
+
+int  zip_alloc_comp_ctx_deflate(struct crypto_tfm *tfm);
+int  zip_alloc_comp_ctx_lzs(struct crypto_tfm *tfm);
+void zip_free_comp_ctx(struct crypto_tfm *tfm);
+int  zip_comp_compress(struct crypto_tfm *tfm,
+		       const u8 *src, unsigned int slen,
+		       u8 *dst, unsigned int *dlen);
+int  zip_comp_decompress(struct crypto_tfm *tfm,
+			 const u8 *src, unsigned int slen,
+			 u8 *dst, unsigned int *dlen);
+
+void *zip_alloc_scomp_ctx_deflate(struct crypto_scomp *tfm);
+void *zip_alloc_scomp_ctx_lzs(struct crypto_scomp *tfm);
+void  zip_free_scomp_ctx(struct crypto_scomp *tfm, void *zip_ctx);
+int   zip_scomp_compress(struct crypto_scomp *tfm,
+			 const u8 *src, unsigned int slen,
+			 u8 *dst, unsigned int *dlen, void *ctx);
+int   zip_scomp_decompress(struct crypto_scomp *tfm,
+			   const u8 *src, unsigned int slen,
+			   u8 *dst, unsigned int *dlen, void *ctx);
+#endif
diff --git a/drivers/crypto/cavium/zip/zip_deflate.c b/drivers/crypto/cavium/zip/zip_deflate.c
new file mode 100644
index 000000000000..9a944b8c1e29
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_deflate.c
@@ -0,0 +1,200 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#include <linux/delay.h>
+#include <linux/sched.h>
+
+#include "common.h"
+#include "zip_deflate.h"
+
+/* Prepares the deflate zip command */
+static int prepare_zip_command(struct zip_operation *zip_ops,
+			       struct zip_state *s, union zip_inst_s *zip_cmd)
+{
+	union zip_zres_s *result_ptr = &s->result;
+
+	memset(zip_cmd, 0, sizeof(s->zip_cmd));
+	memset(result_ptr, 0, sizeof(s->result));
+
+	/* IWORD #0 */
+	/* History gather */
+	zip_cmd->s.hg = 0;
+	/* compression enable = 1 for deflate */
+	zip_cmd->s.ce = 1;
+	/* sf (sync flush) */
+	zip_cmd->s.sf = 1;
+	/* ef (end of file) */
+	if (zip_ops->flush == ZIP_FLUSH_FINISH) {
+		zip_cmd->s.ef = 1;
+		zip_cmd->s.sf = 0;
+	}
+
+	zip_cmd->s.cc = zip_ops->ccode;
+	/* ss (compression speed/storage) */
+	zip_cmd->s.ss = zip_ops->speed;
+
+	/* IWORD #1 */
+	/* adler checksum */
+	zip_cmd->s.adlercrc32 = zip_ops->csum;
+	zip_cmd->s.historylength = zip_ops->history_len;
+	zip_cmd->s.dg = 0;
+
+	/* IWORD # 6 and 7 - compression input/history pointer */
+	zip_cmd->s.inp_ptr_addr.s.addr  = __pa(zip_ops->input);
+	zip_cmd->s.inp_ptr_ctl.s.length = (zip_ops->input_len +
+					   zip_ops->history_len);
+	zip_cmd->s.ds = 0;
+
+	/* IWORD # 8 and 9 - Output pointer */
+	zip_cmd->s.out_ptr_addr.s.addr  = __pa(zip_ops->output);
+	zip_cmd->s.out_ptr_ctl.s.length = zip_ops->output_len;
+	/* maximum number of output-stream bytes that can be written */
+	zip_cmd->s.totaloutputlength    = zip_ops->output_len;
+
+	/* IWORD # 10 and 11 - Result pointer */
+	zip_cmd->s.res_ptr_addr.s.addr = __pa(result_ptr);
+	/* Clearing completion code */
+	result_ptr->s.compcode = 0;
+
+	return 0;
+}
+
+/**
+ * zip_deflate - API to offload deflate operation to hardware
+ * @zip_ops: Pointer to zip operation structure
+ * @s:       Pointer to the structure representing zip state
+ * @zip_dev: Pointer to zip device structure
+ *
+ * This function prepares the zip deflate command and submits it to the zip
+ * engine for processing.
+ *
+ * Return: 0 if successful or error code
+ */
+int zip_deflate(struct zip_operation *zip_ops, struct zip_state *s,
+		struct zip_device *zip_dev)
+{
+	union zip_inst_s *zip_cmd = &s->zip_cmd;
+	union zip_zres_s *result_ptr = &s->result;
+	u32 queue;
+
+	/* Prepares zip command based on the input parameters */
+	prepare_zip_command(zip_ops, s, zip_cmd);
+
+	atomic64_add(zip_ops->input_len, &zip_dev->stats.comp_in_bytes);
+	/* Loads zip command into command queues and rings door bell */
+	queue = zip_load_instr(zip_cmd, zip_dev);
+
+	/* Stats update for compression requests submitted */
+	atomic64_inc(&zip_dev->stats.comp_req_submit);
+
+	while (!result_ptr->s.compcode)
+		continue;
+
+	/* Stats update for compression requests completed */
+	atomic64_inc(&zip_dev->stats.comp_req_complete);
+
+	zip_ops->compcode = result_ptr->s.compcode;
+	switch (zip_ops->compcode) {
+	case ZIP_CMD_NOTDONE:
+		zip_dbg("Zip instruction not yet completed");
+		return ZIP_ERROR;
+
+	case ZIP_CMD_SUCCESS:
+		zip_dbg("Zip instruction completed successfully");
+		zip_update_cmd_bufs(zip_dev, queue);
+		break;
+
+	case ZIP_CMD_DTRUNC:
+		zip_dbg("Output Truncate error");
+		/* Returning ZIP_ERROR to avoid copy to user */
+		return ZIP_ERROR;
+
+	default:
+		zip_err("Zip instruction failed. Code:%d", zip_ops->compcode);
+		return ZIP_ERROR;
+	}
+
+	/* Update the CRC depending on the format */
+	switch (zip_ops->format) {
+	case RAW_FORMAT:
+		zip_dbg("RAW Format: %d ", zip_ops->format);
+		/* Get checksum from engine, need to feed it again */
+		zip_ops->csum = result_ptr->s.adler32;
+		break;
+
+	case ZLIB_FORMAT:
+		zip_dbg("ZLIB Format: %d ", zip_ops->format);
+		zip_ops->csum = result_ptr->s.adler32;
+		break;
+
+	case GZIP_FORMAT:
+		zip_dbg("GZIP Format: %d ", zip_ops->format);
+		zip_ops->csum = result_ptr->s.crc32;
+		break;
+
+	case LZS_FORMAT:
+		zip_dbg("LZS Format: %d ", zip_ops->format);
+		break;
+
+	default:
+		zip_err("Unknown Format:%d\n", zip_ops->format);
+	}
+
+	atomic64_add(result_ptr->s.totalbyteswritten,
+		     &zip_dev->stats.comp_out_bytes);
+
+	/* Update output_len */
+	if (zip_ops->output_len < result_ptr->s.totalbyteswritten) {
+		/* Dynamic stop && strm->output_len < zipconstants[onfsize] */
+		zip_err("output_len (%d) < total bytes written(%d)\n",
+			zip_ops->output_len, result_ptr->s.totalbyteswritten);
+		zip_ops->output_len = 0;
+
+	} else {
+		zip_ops->output_len = result_ptr->s.totalbyteswritten;
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/cavium/zip/zip_deflate.h b/drivers/crypto/cavium/zip/zip_deflate.h
new file mode 100644
index 000000000000..1d32e76edc4d
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_deflate.h
@@ -0,0 +1,62 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_DEFLATE_H__
+#define __ZIP_DEFLATE_H__
+
+/**
+ * zip_deflate - API to offload deflate operation to hardware
+ * @zip_ops: Pointer to zip operation structure
+ * @s:       Pointer to the structure representing zip state
+ * @zip_dev: Pointer to the structure representing zip device
+ *
+ * This function prepares the zip deflate command and submits it to the zip
+ * engine by ringing the doorbell.
+ *
+ * Return: 0 if successful or error code
+ */
+int zip_deflate(struct zip_operation *zip_ops, struct zip_state *s,
+		struct zip_device *zip_dev);
+#endif
diff --git a/drivers/crypto/cavium/zip/zip_device.c b/drivers/crypto/cavium/zip/zip_device.c
new file mode 100644
index 000000000000..ccf21fb91513
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_device.c
@@ -0,0 +1,202 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#include "common.h"
+#include "zip_deflate.h"
+
+/**
+ * zip_cmd_queue_consumed - Calculates the space consumed in the command queue.
+ *
+ * @zip_dev: Pointer to zip device structure
+ * @queue:   Queue number
+ *
+ * Return: Bytes consumed in the command queue buffer.
+ */
+static inline u32 zip_cmd_queue_consumed(struct zip_device *zip_dev, int queue)
+{
+	return ((zip_dev->iq[queue].sw_head - zip_dev->iq[queue].sw_tail) *
+		sizeof(u64 *));
+}
+
+/**
+ * zip_load_instr - Submits the instruction into the ZIP command queue
+ * @instr:      Pointer to the instruction to be submitted
+ * @zip_dev:    Pointer to ZIP device structure to which the instruction is to
+ *              be submitted
+ *
+ * This function copies the ZIP instruction to the command queue and rings the
+ * doorbell to notify the engine of the instruction submission. The command
+ * queue is maintained in a circular fashion. When there is space for exactly
+ * one instruction in the queue, next chunk pointer of the queue is made to
+ * point to the head of the queue, thus maintaining a circular queue.
+ *
+ * Return: Queue number to which the instruction was submitted
+ */
+u32 zip_load_instr(union zip_inst_s *instr,
+		   struct zip_device *zip_dev)
+{
+	union zip_quex_doorbell dbell;
+	u32 queue = 0;
+	u32 consumed = 0;
+	u64 *ncb_ptr = NULL;
+	union zip_nptr_s ncp;
+
+	/*
+	 * Distribute the instructions between the enabled queues based on
+	 * the CPU id.
+	 */
+	if (smp_processor_id() % 2 == 0)
+		queue = 0;
+	else
+		queue = 1;
+
+	zip_dbg("CPU Core: %d Queue number:%d", smp_processor_id(), queue);
+
+	/* Take cmd buffer lock */
+	spin_lock(&zip_dev->iq[queue].lock);
+
+	/*
+	 * Command Queue implementation
+	 * 1. If there is place for new instructions, push the cmd at sw_head.
+	 * 2. If there is place for exactly one instruction, push the new cmd
+	 *    at the sw_head. Make sw_head point to the sw_tail to make it
+	 *    circular. Write sw_head's physical address to the "Next-Chunk
+	 *    Buffer Ptr" to make it cmd_hw_tail.
+	 * 3. Ring the door bell.
+	 */
+	zip_dbg("sw_head : %lx", zip_dev->iq[queue].sw_head);
+	zip_dbg("sw_tail : %lx", zip_dev->iq[queue].sw_tail);
+
+	consumed = zip_cmd_queue_consumed(zip_dev, queue);
+	/* Check if there is space to push just one cmd */
+	if ((consumed + 128) == (ZIP_CMD_QBUF_SIZE - 8)) {
+		zip_dbg("Cmd queue space available for single command");
+		/* Space for one cmd, pust it and make it circular queue */
+		memcpy((u8 *)zip_dev->iq[queue].sw_head, (u8 *)instr,
+		       sizeof(union zip_inst_s));
+		zip_dev->iq[queue].sw_head += 16; /* 16 64_bit words = 128B */
+
+		/* Now, point the "Next-Chunk Buffer Ptr" to sw_head */
+		ncb_ptr = zip_dev->iq[queue].sw_head;
+
+		zip_dbg("ncb addr :0x%lx sw_head addr :0x%lx",
+			ncb_ptr, zip_dev->iq[queue].sw_head - 16);
+
+		/* Using Circular command queue */
+		zip_dev->iq[queue].sw_head = zip_dev->iq[queue].sw_tail;
+		/* Mark this buffer for free */
+		zip_dev->iq[queue].free_flag = 1;
+
+		/* Write new chunk buffer address at "Next-Chunk Buffer Ptr" */
+		ncp.u_reg64 = 0ull;
+		ncp.s.addr = __pa(zip_dev->iq[queue].sw_head);
+		*ncb_ptr = ncp.u_reg64;
+		zip_dbg("*ncb_ptr :0x%lx sw_head[phys] :0x%lx",
+			*ncb_ptr, __pa(zip_dev->iq[queue].sw_head));
+
+		zip_dev->iq[queue].pend_cnt++;
+
+	} else {
+		zip_dbg("Enough space is available for commands");
+		/* Push this cmd to cmd queue buffer */
+		memcpy((u8 *)zip_dev->iq[queue].sw_head, (u8 *)instr,
+		       sizeof(union zip_inst_s));
+		zip_dev->iq[queue].sw_head += 16; /* 16 64_bit words = 128B */
+
+		zip_dev->iq[queue].pend_cnt++;
+	}
+	zip_dbg("sw_head :0x%lx sw_tail :0x%lx hw_tail :0x%lx",
+		zip_dev->iq[queue].sw_head, zip_dev->iq[queue].sw_tail,
+		zip_dev->iq[queue].hw_tail);
+
+	zip_dbg(" Pushed the new cmd : pend_cnt : %d",
+		zip_dev->iq[queue].pend_cnt);
+
+	/* Ring the doorbell */
+	dbell.u_reg64     = 0ull;
+	dbell.s.dbell_cnt = 1;
+	zip_reg_write(dbell.u_reg64,
+		      (zip_dev->reg_base + ZIP_QUEX_DOORBELL(queue)));
+
+	/* Unlock cmd buffer lock */
+	spin_unlock(&zip_dev->iq[queue].lock);
+
+	return queue;
+}
+
+/**
+ * zip_update_cmd_bufs - Updates the queue statistics after posting the
+ *                       instruction
+ * @zip_dev: Pointer to zip device structure
+ * @queue:   Queue number
+ */
+void zip_update_cmd_bufs(struct zip_device *zip_dev, u32 queue)
+{
+	/* Take cmd buffer lock */
+	spin_lock(&zip_dev->iq[queue].lock);
+
+	/* Check if the previous buffer can be freed */
+	if (zip_dev->iq[queue].free_flag == 1) {
+		zip_dbg("Free flag. Free cmd buffer, adjust sw head and tail");
+		/* Reset the free flag */
+		zip_dev->iq[queue].free_flag = 0;
+
+		/* Point the hw_tail to start of the new chunk buffer */
+		zip_dev->iq[queue].hw_tail = zip_dev->iq[queue].sw_head;
+	} else {
+		zip_dbg("Free flag not set. increment hw tail");
+		zip_dev->iq[queue].hw_tail += 16; /* 16 64_bit words = 128B */
+	}
+
+	zip_dev->iq[queue].done_cnt++;
+	zip_dev->iq[queue].pend_cnt--;
+
+	zip_dbg("sw_head :0x%lx sw_tail :0x%lx hw_tail :0x%lx",
+		zip_dev->iq[queue].sw_head, zip_dev->iq[queue].sw_tail,
+		zip_dev->iq[queue].hw_tail);
+	zip_dbg(" Got CC : pend_cnt : %d\n", zip_dev->iq[queue].pend_cnt);
+
+	spin_unlock(&zip_dev->iq[queue].lock);
+}
diff --git a/drivers/crypto/cavium/zip/zip_device.h b/drivers/crypto/cavium/zip/zip_device.h
new file mode 100644
index 000000000000..9e18b3b93d38
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_device.h
@@ -0,0 +1,108 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_DEVICE_H__
+#define __ZIP_DEVICE_H__
+
+#include <linux/types.h>
+#include "zip_main.h"
+
+struct sg_info {
+	/*
+	 * Pointer to the input data when scatter_gather == 0 and
+	 * pointer to the input gather list buffer when scatter_gather == 1
+	 */
+	union zip_zptr_s *gather;
+
+	/*
+	 * Pointer to the output data when scatter_gather == 0 and
+	 * pointer to the output scatter list buffer when scatter_gather == 1
+	 */
+	union zip_zptr_s *scatter;
+
+	/*
+	 * Holds size of the output buffer pointed by scatter list
+	 * when scatter_gather == 1
+	 */
+	u64 scatter_buf_size;
+
+	/* for gather data */
+	u64 gather_enable;
+
+	/* for scatter data */
+	u64 scatter_enable;
+
+	/* Number of gather list pointers for gather data */
+	u32 gbuf_cnt;
+
+	/* Number of scatter list pointers for scatter data */
+	u32 sbuf_cnt;
+
+	/* Buffers allocation state */
+	u8 alloc_state;
+};
+
+/**
+ * struct zip_state - Structure representing the required information related
+ *                    to a command
+ * @zip_cmd: Pointer to zip instruction structure
+ * @result:  Pointer to zip result structure
+ * @ctx:     Context pointer for inflate
+ * @history: Decompression history pointer
+ * @sginfo:  Scatter-gather info structure
+ */
+struct zip_state {
+	union zip_inst_s zip_cmd;
+	union zip_zres_s result;
+	union zip_zptr_s *ctx;
+	union zip_zptr_s *history;
+	struct sg_info   sginfo;
+};
+
+#define ZIP_CONTEXT_SIZE          2048
+#define ZIP_INFLATE_HISTORY_SIZE  32768
+#define ZIP_DEFLATE_HISTORY_SIZE  32768
+
+#endif
diff --git a/drivers/crypto/cavium/zip/zip_inflate.c b/drivers/crypto/cavium/zip/zip_inflate.c
new file mode 100644
index 000000000000..50cbdd83dbf2
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_inflate.c
@@ -0,0 +1,223 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#include <linux/delay.h>
+#include <linux/sched.h>
+
+#include "common.h"
+#include "zip_inflate.h"
+
+static int prepare_inflate_zcmd(struct zip_operation *zip_ops,
+				struct zip_state *s, union zip_inst_s *zip_cmd)
+{
+	union zip_zres_s *result_ptr = &s->result;
+
+	memset(zip_cmd, 0, sizeof(s->zip_cmd));
+	memset(result_ptr, 0, sizeof(s->result));
+
+	/* IWORD#0 */
+
+	/* Decompression History Gather list - no gather list */
+	zip_cmd->s.hg = 0;
+	/* For decompression, CE must be 0x0. */
+	zip_cmd->s.ce = 0;
+	/* For decompression, SS must be 0x0. */
+	zip_cmd->s.ss = 0;
+	/* For decompression, SF should always be set. */
+	zip_cmd->s.sf = 1;
+
+	/* Begin File */
+	if (zip_ops->begin_file == 0)
+		zip_cmd->s.bf = 0;
+	else
+		zip_cmd->s.bf = 1;
+
+	zip_cmd->s.ef = 1;
+	/* 0: for Deflate decompression, 3: for LZS decompression */
+	zip_cmd->s.cc = zip_ops->ccode;
+
+	/* IWORD #1*/
+
+	/* adler checksum */
+	zip_cmd->s.adlercrc32 = zip_ops->csum;
+
+	/*
+	 * HISTORYLENGTH must be 0x0 for any ZIP decompress operation.
+	 * History data is added to a decompression operation via IWORD3.
+	 */
+	zip_cmd->s.historylength = 0;
+	zip_cmd->s.ds = 0;
+
+	/* IWORD # 8 and 9 - Output pointer */
+	zip_cmd->s.out_ptr_addr.s.addr  = __pa(zip_ops->output);
+	zip_cmd->s.out_ptr_ctl.s.length = zip_ops->output_len;
+
+	/* Maximum number of output-stream bytes that can be written */
+	zip_cmd->s.totaloutputlength    = zip_ops->output_len;
+
+	zip_dbg("Data Direct Input case ");
+
+	/* IWORD # 6 and 7 - input pointer */
+	zip_cmd->s.dg = 0;
+	zip_cmd->s.inp_ptr_addr.s.addr  = __pa((u8 *)zip_ops->input);
+	zip_cmd->s.inp_ptr_ctl.s.length = zip_ops->input_len;
+
+	/* IWORD # 10 and 11 - Result pointer */
+	zip_cmd->s.res_ptr_addr.s.addr = __pa(result_ptr);
+
+	/* Clearing completion code */
+	result_ptr->s.compcode = 0;
+
+	/* Returning 0 for time being.*/
+	return 0;
+}
+
+/**
+ * zip_inflate - API to offload inflate operation to hardware
+ * @zip_ops: Pointer to zip operation structure
+ * @s:       Pointer to the structure representing zip state
+ * @zip_dev: Pointer to zip device structure
+ *
+ * This function prepares the zip inflate command and submits it to the zip
+ * engine for processing.
+ *
+ * Return: 0 if successful or error code
+ */
+int zip_inflate(struct zip_operation *zip_ops, struct zip_state *s,
+		struct zip_device *zip_dev)
+{
+	union zip_inst_s *zip_cmd    = &s->zip_cmd;
+	union zip_zres_s  *result_ptr = &s->result;
+	u32 queue;
+
+	/* Prepare inflate zip command */
+	prepare_inflate_zcmd(zip_ops, s, zip_cmd);
+
+	atomic64_add(zip_ops->input_len, &zip_dev->stats.decomp_in_bytes);
+
+	/* Load inflate command to zip queue and ring the doorbell */
+	queue = zip_load_instr(zip_cmd, zip_dev);
+
+	/* Decompression requests submitted stats update */
+	atomic64_inc(&zip_dev->stats.decomp_req_submit);
+
+	while (!result_ptr->s.compcode)
+		continue;
+
+	/* Decompression requests completed stats update */
+	atomic64_inc(&zip_dev->stats.decomp_req_complete);
+
+	zip_ops->compcode = result_ptr->s.compcode;
+	switch (zip_ops->compcode) {
+	case ZIP_CMD_NOTDONE:
+		zip_dbg("Zip Instruction not yet completed\n");
+		return ZIP_ERROR;
+
+	case ZIP_CMD_SUCCESS:
+		zip_dbg("Zip Instruction completed successfully\n");
+		break;
+
+	case ZIP_CMD_DYNAMIC_STOP:
+		zip_dbg(" Dynamic stop Initiated\n");
+		break;
+
+	default:
+		zip_dbg("Instruction failed. Code = %d\n", zip_ops->compcode);
+		atomic64_inc(&zip_dev->stats.decomp_bad_reqs);
+		zip_update_cmd_bufs(zip_dev, queue);
+		return ZIP_ERROR;
+	}
+
+	zip_update_cmd_bufs(zip_dev, queue);
+
+	if ((zip_ops->ccode == 3) && (zip_ops->flush == 4) &&
+	    (zip_ops->compcode != ZIP_CMD_DYNAMIC_STOP))
+		result_ptr->s.ef = 1;
+
+	zip_ops->csum = result_ptr->s.adler32;
+
+	atomic64_add(result_ptr->s.totalbyteswritten,
+		     &zip_dev->stats.decomp_out_bytes);
+
+	if (zip_ops->output_len < result_ptr->s.totalbyteswritten) {
+		zip_err("output_len (%d) < total bytes written (%d)\n",
+			zip_ops->output_len, result_ptr->s.totalbyteswritten);
+		zip_ops->output_len = 0;
+	} else {
+		zip_ops->output_len = result_ptr->s.totalbyteswritten;
+	}
+
+	zip_ops->bytes_read = result_ptr->s.totalbytesread;
+	zip_ops->bits_processed = result_ptr->s.totalbitsprocessed;
+	zip_ops->end_file = result_ptr->s.ef;
+	if (zip_ops->end_file) {
+		switch (zip_ops->format) {
+		case RAW_FORMAT:
+			zip_dbg("RAW Format: %d ", zip_ops->format);
+			/* Get checksum from engine */
+			zip_ops->csum = result_ptr->s.adler32;
+			break;
+
+		case ZLIB_FORMAT:
+			zip_dbg("ZLIB Format: %d ", zip_ops->format);
+			zip_ops->csum = result_ptr->s.adler32;
+			break;
+
+		case GZIP_FORMAT:
+			zip_dbg("GZIP Format: %d ", zip_ops->format);
+			zip_ops->csum = result_ptr->s.crc32;
+			break;
+
+		case LZS_FORMAT:
+			zip_dbg("LZS Format: %d ", zip_ops->format);
+			break;
+
+		default:
+			zip_err("Format error:%d\n", zip_ops->format);
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/cavium/zip/zip_inflate.h b/drivers/crypto/cavium/zip/zip_inflate.h
new file mode 100644
index 000000000000..6b20f179978e
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_inflate.h
@@ -0,0 +1,62 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_INFLATE_H__
+#define __ZIP_INFLATE_H__
+
+/**
+ * zip_inflate - API to offload inflate operation to hardware
+ * @zip_ops: Pointer to zip operation structure
+ * @s:       Pointer to the structure representing zip state
+ * @zip_dev: Pointer to the structure representing zip device
+ *
+ * This function prepares the zip inflate command and submits it to the zip
+ * engine for processing.
+ *
+ * Return: 0 if successful or error code
+ */
+int zip_inflate(struct zip_operation *zip_ops, struct zip_state *s,
+		struct zip_device *zip_dev);
+#endif
diff --git a/drivers/crypto/cavium/zip/zip_main.c b/drivers/crypto/cavium/zip/zip_main.c
new file mode 100644
index 000000000000..1cd8aa488185
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_main.c
@@ -0,0 +1,729 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#include "common.h"
+#include "zip_crypto.h"
+
+#define DRV_NAME		"ThunderX-ZIP"
+
+static struct zip_device *zip_dev[MAX_ZIP_DEVICES];
+
+static const struct pci_device_id zip_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDERX_ZIP) },
+	{ 0, }
+};
+
+void zip_reg_write(u64 val, u64 __iomem *addr)
+{
+	writeq(val, addr);
+}
+
+u64 zip_reg_read(u64 __iomem *addr)
+{
+	return readq(addr);
+}
+
+/*
+ * Allocates new ZIP device structure
+ * Returns zip_device pointer or NULL if cannot allocate memory for zip_device
+ */
+static struct zip_device *zip_alloc_device(struct pci_dev *pdev)
+{
+	struct zip_device *zip = NULL;
+	int idx;
+
+	for (idx = 0; idx < MAX_ZIP_DEVICES; idx++) {
+		if (!zip_dev[idx])
+			break;
+	}
+
+	/* To ensure that the index is within the limit */
+	if (idx < MAX_ZIP_DEVICES)
+		zip = devm_kzalloc(&pdev->dev, sizeof(*zip), GFP_KERNEL);
+
+	if (!zip)
+		return NULL;
+
+	zip_dev[idx] = zip;
+	zip->index = idx;
+	return zip;
+}
+
+/**
+ * zip_get_device - Get ZIP device based on node id of cpu
+ *
+ * @node: Node id of the current cpu
+ * Return: Pointer to Zip device structure
+ */
+struct zip_device *zip_get_device(int node)
+{
+	if ((node < MAX_ZIP_DEVICES) && (node >= 0))
+		return zip_dev[node];
+
+	zip_err("ZIP device not found for node id %d\n", node);
+	return NULL;
+}
+
+/**
+ * zip_get_node_id - Get the node id of the current cpu
+ *
+ * Return: Node id of the current cpu
+ */
+int zip_get_node_id(void)
+{
+	return cpu_to_node(smp_processor_id());
+}
+
+/* Initializes the ZIP h/w sub-system */
+static int zip_init_hw(struct zip_device *zip)
+{
+	union zip_cmd_ctl    cmd_ctl;
+	union zip_constants  constants;
+	union zip_que_ena    que_ena;
+	union zip_quex_map   que_map;
+	union zip_que_pri    que_pri;
+
+	union zip_quex_sbuf_addr que_sbuf_addr;
+	union zip_quex_sbuf_ctl  que_sbuf_ctl;
+
+	int q = 0;
+
+	/* Enable the ZIP Engine(Core) Clock */
+	cmd_ctl.u_reg64 = zip_reg_read(zip->reg_base + ZIP_CMD_CTL);
+	cmd_ctl.s.forceclk = 1;
+	zip_reg_write(cmd_ctl.u_reg64 & 0xFF, (zip->reg_base + ZIP_CMD_CTL));
+
+	zip_msg("ZIP_CMD_CTL  : 0x%016llx",
+		zip_reg_read(zip->reg_base + ZIP_CMD_CTL));
+
+	constants.u_reg64 = zip_reg_read(zip->reg_base + ZIP_CONSTANTS);
+	zip->depth    = constants.s.depth;
+	zip->onfsize  = constants.s.onfsize;
+	zip->ctxsize  = constants.s.ctxsize;
+
+	zip_msg("depth: 0x%016llx , onfsize : 0x%016llx , ctxsize : 0x%016llx",
+		zip->depth, zip->onfsize, zip->ctxsize);
+
+	/*
+	 * Program ZIP_QUE(0..7)_SBUF_ADDR and ZIP_QUE(0..7)_SBUF_CTL to
+	 * have the correct buffer pointer and size configured for each
+	 * instruction queue.
+	 */
+	for (q = 0; q < ZIP_NUM_QUEUES; q++) {
+		que_sbuf_ctl.u_reg64 = 0ull;
+		que_sbuf_ctl.s.size = (ZIP_CMD_QBUF_SIZE / sizeof(u64));
+		que_sbuf_ctl.s.inst_be   = 0;
+		que_sbuf_ctl.s.stream_id = 0;
+		zip_reg_write(que_sbuf_ctl.u_reg64,
+			      (zip->reg_base + ZIP_QUEX_SBUF_CTL(q)));
+
+		zip_msg("QUEX_SBUF_CTL[%d]: 0x%016llx", q,
+			zip_reg_read(zip->reg_base + ZIP_QUEX_SBUF_CTL(q)));
+	}
+
+	for (q = 0; q < ZIP_NUM_QUEUES; q++) {
+		memset(&zip->iq[q], 0x0, sizeof(struct zip_iq));
+
+		spin_lock_init(&zip->iq[q].lock);
+
+		if (zip_cmd_qbuf_alloc(zip, q)) {
+			while (q != 0) {
+				q--;
+				zip_cmd_qbuf_free(zip, q);
+			}
+			return -ENOMEM;
+		}
+
+		/* Initialize tail ptr to head */
+		zip->iq[q].sw_tail = zip->iq[q].sw_head;
+		zip->iq[q].hw_tail = zip->iq[q].sw_head;
+
+		/* Write the physical addr to register */
+		que_sbuf_addr.u_reg64   = 0ull;
+		que_sbuf_addr.s.ptr = (__pa(zip->iq[q].sw_head) >>
+				       ZIP_128B_ALIGN);
+
+		zip_msg("QUE[%d]_PTR(PHYS): 0x%016llx", q,
+			(u64)que_sbuf_addr.s.ptr);
+
+		zip_reg_write(que_sbuf_addr.u_reg64,
+			      (zip->reg_base + ZIP_QUEX_SBUF_ADDR(q)));
+
+		zip_msg("QUEX_SBUF_ADDR[%d]: 0x%016llx", q,
+			zip_reg_read(zip->reg_base + ZIP_QUEX_SBUF_ADDR(q)));
+
+		zip_dbg("sw_head :0x%lx sw_tail :0x%lx hw_tail :0x%lx",
+			zip->iq[q].sw_head, zip->iq[q].sw_tail,
+			zip->iq[q].hw_tail);
+		zip_dbg("sw_head phy addr : 0x%lx", que_sbuf_addr.s.ptr);
+	}
+
+	/*
+	 * Queue-to-ZIP core mapping
+	 * If a queue is not mapped to a particular core, it is equivalent to
+	 * the ZIP core being disabled.
+	 */
+	que_ena.u_reg64 = 0x0ull;
+	/* Enabling queues based on ZIP_NUM_QUEUES */
+	for (q = 0; q < ZIP_NUM_QUEUES; q++)
+		que_ena.s.ena |= (0x1 << q);
+	zip_reg_write(que_ena.u_reg64, (zip->reg_base + ZIP_QUE_ENA));
+
+	zip_msg("QUE_ENA      : 0x%016llx",
+		zip_reg_read(zip->reg_base + ZIP_QUE_ENA));
+
+	for (q = 0; q < ZIP_NUM_QUEUES; q++) {
+		que_map.u_reg64 = 0ull;
+		/* Mapping each queue to two ZIP cores */
+		que_map.s.zce = 0x3;
+		zip_reg_write(que_map.u_reg64,
+			      (zip->reg_base + ZIP_QUEX_MAP(q)));
+
+		zip_msg("QUE_MAP(%d)   : 0x%016llx", q,
+			zip_reg_read(zip->reg_base + ZIP_QUEX_MAP(q)));
+	}
+
+	que_pri.u_reg64 = 0ull;
+	for (q = 0; q < ZIP_NUM_QUEUES; q++)
+		que_pri.s.pri |= (0x1 << q); /* Higher Priority RR */
+	zip_reg_write(que_pri.u_reg64, (zip->reg_base + ZIP_QUE_PRI));
+
+	zip_msg("QUE_PRI %016llx", zip_reg_read(zip->reg_base + ZIP_QUE_PRI));
+
+	return 0;
+}
+
+static int zip_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct zip_device *zip = NULL;
+	int    err;
+
+	zip = zip_alloc_device(pdev);
+	if (!zip)
+		return -ENOMEM;
+
+	dev_info(dev, "Found ZIP device %d %x:%x on Node %d\n", zip->index,
+		 pdev->vendor, pdev->device, dev_to_node(dev));
+
+	pci_set_drvdata(pdev, zip);
+	zip->pdev = pdev;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device");
+		goto err_free_device;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(dev, "PCI request regions failed 0x%x", err);
+		goto err_disable_device;
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto err_release_regions;
+	}
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get 48-bit DMA for allocations\n");
+		goto err_release_regions;
+	}
+
+	/* MAP configuration registers */
+	zip->reg_base = pci_ioremap_bar(pdev, PCI_CFG_ZIP_PF_BAR0);
+	if (!zip->reg_base) {
+		dev_err(dev, "ZIP: Cannot map BAR0 CSR memory space, aborting");
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+
+	/* Initialize ZIP Hardware */
+	err = zip_init_hw(zip);
+	if (err)
+		goto err_release_regions;
+
+	return 0;
+
+err_release_regions:
+	if (zip->reg_base)
+		iounmap(zip->reg_base);
+	pci_release_regions(pdev);
+
+err_disable_device:
+	pci_disable_device(pdev);
+
+err_free_device:
+	pci_set_drvdata(pdev, NULL);
+
+	/* Remove zip_dev from zip_device list, free the zip_device memory */
+	zip_dev[zip->index] = NULL;
+	devm_kfree(dev, zip);
+
+	return err;
+}
+
+static void zip_remove(struct pci_dev *pdev)
+{
+	struct zip_device *zip = pci_get_drvdata(pdev);
+	union zip_cmd_ctl cmd_ctl;
+	int q = 0;
+
+	if (!zip)
+		return;
+
+	if (zip->reg_base) {
+		cmd_ctl.u_reg64 = 0x0ull;
+		cmd_ctl.s.reset = 1;  /* Forces ZIP cores to do reset */
+		zip_reg_write(cmd_ctl.u_reg64, (zip->reg_base + ZIP_CMD_CTL));
+		iounmap(zip->reg_base);
+	}
+
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+
+	/*
+	 * Free Command Queue buffers. This free should be called for all
+	 * the enabled Queues.
+	 */
+	for (q = 0; q < ZIP_NUM_QUEUES; q++)
+		zip_cmd_qbuf_free(zip, q);
+
+	pci_set_drvdata(pdev, NULL);
+	/* remove zip device from zip device list */
+	zip_dev[zip->index] = NULL;
+}
+
+/* PCI Sub-System Interface */
+static struct pci_driver zip_driver = {
+	.name	    =  DRV_NAME,
+	.id_table   =  zip_id_table,
+	.probe	    =  zip_probe,
+	.remove     =  zip_remove,
+};
+
+/* Kernel Crypto Subsystem Interface */
+
+static struct crypto_alg zip_comp_deflate = {
+	.cra_name		= "deflate",
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct zip_kernel_ctx),
+	.cra_priority           = 300,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= zip_alloc_comp_ctx_deflate,
+	.cra_exit		= zip_free_comp_ctx,
+	.cra_u			= { .compress = {
+		.coa_compress	= zip_comp_compress,
+		.coa_decompress	= zip_comp_decompress
+		 } }
+};
+
+static struct crypto_alg zip_comp_lzs = {
+	.cra_name		= "lzs",
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct zip_kernel_ctx),
+	.cra_priority           = 300,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= zip_alloc_comp_ctx_lzs,
+	.cra_exit		= zip_free_comp_ctx,
+	.cra_u			= { .compress = {
+		.coa_compress	= zip_comp_compress,
+		.coa_decompress	= zip_comp_decompress
+		 } }
+};
+
+static struct scomp_alg zip_scomp_deflate = {
+	.alloc_ctx		= zip_alloc_scomp_ctx_deflate,
+	.free_ctx		= zip_free_scomp_ctx,
+	.compress		= zip_scomp_compress,
+	.decompress		= zip_scomp_decompress,
+	.base			= {
+		.cra_name		= "deflate",
+		.cra_driver_name	= "deflate-scomp",
+		.cra_module		= THIS_MODULE,
+		.cra_priority           = 300,
+	}
+};
+
+static struct scomp_alg zip_scomp_lzs = {
+	.alloc_ctx		= zip_alloc_scomp_ctx_lzs,
+	.free_ctx		= zip_free_scomp_ctx,
+	.compress		= zip_scomp_compress,
+	.decompress		= zip_scomp_decompress,
+	.base			= {
+		.cra_name		= "lzs",
+		.cra_driver_name	= "lzs-scomp",
+		.cra_module		= THIS_MODULE,
+		.cra_priority           = 300,
+	}
+};
+
+static int zip_register_compression_device(void)
+{
+	int ret;
+
+	ret = crypto_register_alg(&zip_comp_deflate);
+	if (ret < 0) {
+		zip_err("Deflate algorithm registration failed\n");
+		return ret;
+	}
+
+	ret = crypto_register_alg(&zip_comp_lzs);
+	if (ret < 0) {
+		zip_err("LZS algorithm registration failed\n");
+		goto err_unregister_alg_deflate;
+	}
+
+	ret = crypto_register_scomp(&zip_scomp_deflate);
+	if (ret < 0) {
+		zip_err("Deflate scomp algorithm registration failed\n");
+		goto err_unregister_alg_lzs;
+	}
+
+	ret = crypto_register_scomp(&zip_scomp_lzs);
+	if (ret < 0) {
+		zip_err("LZS scomp algorithm registration failed\n");
+		goto err_unregister_scomp_deflate;
+	}
+
+	return ret;
+
+err_unregister_scomp_deflate:
+	crypto_unregister_scomp(&zip_scomp_deflate);
+err_unregister_alg_lzs:
+	crypto_unregister_alg(&zip_comp_lzs);
+err_unregister_alg_deflate:
+	crypto_unregister_alg(&zip_comp_deflate);
+
+	return ret;
+}
+
+static void zip_unregister_compression_device(void)
+{
+	crypto_unregister_alg(&zip_comp_deflate);
+	crypto_unregister_alg(&zip_comp_lzs);
+	crypto_unregister_scomp(&zip_scomp_deflate);
+	crypto_unregister_scomp(&zip_scomp_lzs);
+}
+
+/*
+ * debugfs functions
+ */
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+
+/* Displays ZIP device statistics */
+static int zip_show_stats(struct seq_file *s, void *unused)
+{
+	u64 val = 0ull;
+	u64 avg_chunk = 0ull, avg_cr = 0ull;
+	u32 q = 0;
+
+	int index  = 0;
+	struct zip_device *zip;
+	struct zip_stats  *st;
+
+	for (index = 0; index < MAX_ZIP_DEVICES; index++) {
+		if (zip_dev[index]) {
+			zip = zip_dev[index];
+			st  = &zip->stats;
+
+			/* Get all the pending requests */
+			for (q = 0; q < ZIP_NUM_QUEUES; q++) {
+				val = zip_reg_read((zip->reg_base +
+						    ZIP_DBG_COREX_STA(q)));
+				val = (val >> 32);
+				val = val & 0xffffff;
+				atomic64_add(val, &st->pending_req);
+			}
+
+			avg_chunk = (atomic64_read(&st->comp_in_bytes) /
+				     atomic64_read(&st->comp_req_complete));
+			avg_cr = (atomic64_read(&st->comp_in_bytes) /
+				  atomic64_read(&st->comp_out_bytes));
+			seq_printf(s, "        ZIP Device %d Stats\n"
+				      "-----------------------------------\n"
+				      "Comp Req Submitted        : \t%lld\n"
+				      "Comp Req Completed        : \t%lld\n"
+				      "Compress In Bytes         : \t%lld\n"
+				      "Compressed Out Bytes      : \t%lld\n"
+				      "Average Chunk size        : \t%llu\n"
+				      "Average Compression ratio : \t%llu\n"
+				      "Decomp Req Submitted      : \t%lld\n"
+				      "Decomp Req Completed      : \t%lld\n"
+				      "Decompress In Bytes       : \t%lld\n"
+				      "Decompressed Out Bytes    : \t%lld\n"
+				      "Decompress Bad requests   : \t%lld\n"
+				      "Pending Req               : \t%lld\n"
+					"---------------------------------\n",
+				       index,
+				       (u64)atomic64_read(&st->comp_req_submit),
+				       (u64)atomic64_read(&st->comp_req_complete),
+				       (u64)atomic64_read(&st->comp_in_bytes),
+				       (u64)atomic64_read(&st->comp_out_bytes),
+				       avg_chunk,
+				       avg_cr,
+				       (u64)atomic64_read(&st->decomp_req_submit),
+				       (u64)atomic64_read(&st->decomp_req_complete),
+				       (u64)atomic64_read(&st->decomp_in_bytes),
+				       (u64)atomic64_read(&st->decomp_out_bytes),
+				       (u64)atomic64_read(&st->decomp_bad_reqs),
+				       (u64)atomic64_read(&st->pending_req));
+
+			/* Reset pending requests  count */
+			atomic64_set(&st->pending_req, 0);
+		}
+	}
+	return 0;
+}
+
+/* Clears stats data */
+static int zip_clear_stats(struct seq_file *s, void *unused)
+{
+	int index = 0;
+
+	for (index = 0; index < MAX_ZIP_DEVICES; index++) {
+		if (zip_dev[index]) {
+			memset(&zip_dev[index]->stats, 0,
+			       sizeof(struct zip_stats));
+			seq_printf(s, "Cleared stats for zip %d\n", index);
+		}
+	}
+
+	return 0;
+}
+
+static struct zip_registers zipregs[64] = {
+	{"ZIP_CMD_CTL        ",  0x0000ull},
+	{"ZIP_THROTTLE       ",  0x0010ull},
+	{"ZIP_CONSTANTS      ",  0x00A0ull},
+	{"ZIP_QUE0_MAP       ",  0x1400ull},
+	{"ZIP_QUE1_MAP       ",  0x1408ull},
+	{"ZIP_QUE_ENA        ",  0x0500ull},
+	{"ZIP_QUE_PRI        ",  0x0508ull},
+	{"ZIP_QUE0_DONE      ",  0x2000ull},
+	{"ZIP_QUE1_DONE      ",  0x2008ull},
+	{"ZIP_QUE0_DOORBELL  ",  0x4000ull},
+	{"ZIP_QUE1_DOORBELL  ",  0x4008ull},
+	{"ZIP_QUE0_SBUF_ADDR ",  0x1000ull},
+	{"ZIP_QUE1_SBUF_ADDR ",  0x1008ull},
+	{"ZIP_QUE0_SBUF_CTL  ",  0x1200ull},
+	{"ZIP_QUE1_SBUF_CTL  ",  0x1208ull},
+	{ NULL, 0}
+};
+
+/* Prints registers' contents */
+static int zip_print_regs(struct seq_file *s, void *unused)
+{
+	u64 val = 0;
+	int i = 0, index = 0;
+
+	for (index = 0; index < MAX_ZIP_DEVICES; index++) {
+		if (zip_dev[index]) {
+			seq_printf(s, "--------------------------------\n"
+				      "     ZIP Device %d Registers\n"
+				      "--------------------------------\n",
+				      index);
+
+			i = 0;
+
+			while (zipregs[i].reg_name) {
+				val = zip_reg_read((zip_dev[index]->reg_base +
+						    zipregs[i].reg_offset));
+				seq_printf(s, "%s: 0x%016llx\n",
+					   zipregs[i].reg_name, val);
+				i++;
+			}
+		}
+	}
+	return 0;
+}
+
+static int zip_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, zip_show_stats, NULL);
+}
+
+static const struct file_operations zip_stats_fops = {
+	.owner = THIS_MODULE,
+	.open  = zip_stats_open,
+	.read  = seq_read,
+};
+
+static int zip_clear_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, zip_clear_stats, NULL);
+}
+
+static const struct file_operations zip_clear_fops = {
+	.owner = THIS_MODULE,
+	.open  = zip_clear_open,
+	.read  = seq_read,
+};
+
+static int zip_regs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, zip_print_regs, NULL);
+}
+
+static const struct file_operations zip_regs_fops = {
+	.owner = THIS_MODULE,
+	.open  = zip_regs_open,
+	.read  = seq_read,
+};
+
+/* Root directory for thunderx_zip debugfs entry */
+static struct dentry *zip_debugfs_root;
+
+static int __init zip_debugfs_init(void)
+{
+	struct dentry *zip_stats, *zip_clear, *zip_regs;
+
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	zip_debugfs_root = debugfs_create_dir("thunderx_zip", NULL);
+	if (!zip_debugfs_root)
+		return -ENOMEM;
+
+	/* Creating files for entries inside thunderx_zip directory */
+	zip_stats = debugfs_create_file("zip_stats", 0444,
+					zip_debugfs_root,
+					NULL, &zip_stats_fops);
+	if (!zip_stats)
+		goto failed_to_create;
+
+	zip_clear = debugfs_create_file("zip_clear", 0444,
+					zip_debugfs_root,
+					NULL, &zip_clear_fops);
+	if (!zip_clear)
+		goto failed_to_create;
+
+	zip_regs = debugfs_create_file("zip_regs", 0444,
+				       zip_debugfs_root,
+				       NULL, &zip_regs_fops);
+	if (!zip_regs)
+		goto failed_to_create;
+
+	return 0;
+
+failed_to_create:
+	debugfs_remove_recursive(zip_debugfs_root);
+	return -ENOENT;
+}
+
+static void __exit zip_debugfs_exit(void)
+{
+	debugfs_remove_recursive(zip_debugfs_root);
+}
+
+#else
+static int __init zip_debugfs_init(void)
+{
+	return 0;
+}
+
+static void __exit zip_debugfs_exit(void) { }
+
+#endif
+/* debugfs - end */
+
+static int __init zip_init_module(void)
+{
+	int ret;
+
+	zip_msg("%s\n", DRV_NAME);
+
+	ret = pci_register_driver(&zip_driver);
+	if (ret < 0) {
+		zip_err("ZIP: pci_register_driver() failed\n");
+		return ret;
+	}
+
+	/* Register with the Kernel Crypto Interface */
+	ret = zip_register_compression_device();
+	if (ret < 0) {
+		zip_err("ZIP: Kernel Crypto Registration failed\n");
+		goto err_pci_unregister;
+	}
+
+	/* comp-decomp statistics are handled with debugfs interface */
+	ret = zip_debugfs_init();
+	if (ret < 0) {
+		zip_err("ZIP: debugfs initialization failed\n");
+		goto err_crypto_unregister;
+	}
+
+	return ret;
+
+err_crypto_unregister:
+	zip_unregister_compression_device();
+
+err_pci_unregister:
+	pci_unregister_driver(&zip_driver);
+	return ret;
+}
+
+static void __exit zip_cleanup_module(void)
+{
+	zip_debugfs_exit();
+
+	/* Unregister from the kernel crypto interface */
+	zip_unregister_compression_device();
+
+	/* Unregister this driver for pci zip devices */
+	pci_unregister_driver(&zip_driver);
+}
+
+module_init(zip_init_module);
+module_exit(zip_cleanup_module);
+
+MODULE_AUTHOR("Cavium Inc");
+MODULE_DESCRIPTION("Cavium Inc ThunderX ZIP Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(pci, zip_id_table);
diff --git a/drivers/crypto/cavium/zip/zip_main.h b/drivers/crypto/cavium/zip/zip_main.h
new file mode 100644
index 000000000000..64e051f60784
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_main.h
@@ -0,0 +1,121 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_MAIN_H__
+#define __ZIP_MAIN_H__
+
+#include "zip_device.h"
+#include "zip_regs.h"
+
+/* PCI device IDs */
+#define PCI_DEVICE_ID_THUNDERX_ZIP   0xA01A
+
+/* ZIP device BARs */
+#define PCI_CFG_ZIP_PF_BAR0   0  /* Base addr for normal regs */
+
+/* Maximum available zip queues */
+#define ZIP_MAX_NUM_QUEUES    8
+
+#define ZIP_128B_ALIGN        7
+
+/* Command queue buffer size */
+#define ZIP_CMD_QBUF_SIZE     (8064 + 8)
+
+struct zip_registers {
+	char  *reg_name;
+	u64   reg_offset;
+};
+
+/* ZIP Compression - Decompression stats */
+struct zip_stats {
+	atomic64_t    comp_req_submit;
+	atomic64_t    comp_req_complete;
+	atomic64_t    decomp_req_submit;
+	atomic64_t    decomp_req_complete;
+	atomic64_t    pending_req;
+	atomic64_t    comp_in_bytes;
+	atomic64_t    comp_out_bytes;
+	atomic64_t    decomp_in_bytes;
+	atomic64_t    decomp_out_bytes;
+	atomic64_t    decomp_bad_reqs;
+};
+
+/* ZIP Instruction Queue */
+struct zip_iq {
+	u64        *sw_head;
+	u64        *sw_tail;
+	u64        *hw_tail;
+	u64        done_cnt;
+	u64        pend_cnt;
+	u64        free_flag;
+
+	/* ZIP IQ lock */
+	spinlock_t  lock;
+};
+
+/* ZIP Device */
+struct zip_device {
+	u32               index;
+	void __iomem      *reg_base;
+	struct pci_dev    *pdev;
+
+	/* Different ZIP Constants */
+	u64               depth;
+	u64               onfsize;
+	u64               ctxsize;
+
+	struct zip_iq     iq[ZIP_MAX_NUM_QUEUES];
+	struct zip_stats  stats;
+};
+
+/* Prototypes */
+struct zip_device *zip_get_device(int node_id);
+int zip_get_node_id(void);
+void zip_reg_write(u64 val, u64 __iomem *addr);
+u64 zip_reg_read(u64 __iomem *addr);
+void zip_update_cmd_bufs(struct zip_device *zip_dev, u32 queue);
+u32 zip_load_instr(union zip_inst_s *instr, struct zip_device *zip_dev);
+
+#endif /* ZIP_MAIN_H */
diff --git a/drivers/crypto/cavium/zip/zip_mem.c b/drivers/crypto/cavium/zip/zip_mem.c
new file mode 100644
index 000000000000..b3e0843a9169
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_mem.c
@@ -0,0 +1,114 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+
+#include "common.h"
+
+/**
+ * zip_cmd_qbuf_alloc - Allocates a cmd buffer for ZIP Instruction Queue
+ * @zip: Pointer to zip device structure
+ * @q:   Queue number to allocate bufffer to
+ * Return: 0 if successful, -ENOMEM otherwise
+ */
+int zip_cmd_qbuf_alloc(struct zip_device *zip, int q)
+{
+	zip->iq[q].sw_head = (u64 *)__get_free_pages((GFP_KERNEL | GFP_DMA),
+						get_order(ZIP_CMD_QBUF_SIZE));
+
+	if (!zip->iq[q].sw_head)
+		return -ENOMEM;
+
+	memset(zip->iq[q].sw_head, 0, ZIP_CMD_QBUF_SIZE);
+
+	zip_dbg("cmd_qbuf_alloc[%d] Success : %p\n", q, zip->iq[q].sw_head);
+	return 0;
+}
+
+/**
+ * zip_cmd_qbuf_free - Frees the cmd Queue buffer
+ * @zip: Pointer to zip device structure
+ * @q:   Queue number to free buffer of
+ */
+void zip_cmd_qbuf_free(struct zip_device *zip, int q)
+{
+	zip_dbg("Freeing cmd_qbuf 0x%lx\n", zip->iq[q].sw_tail);
+
+	free_pages((u64)zip->iq[q].sw_tail, get_order(ZIP_CMD_QBUF_SIZE));
+}
+
+/**
+ * zip_data_buf_alloc - Allocates memory for a data bufffer
+ * @size:   Size of the buffer to allocate
+ * Returns: Pointer to the buffer allocated
+ */
+u8 *zip_data_buf_alloc(u64 size)
+{
+	u8 *ptr;
+
+	ptr = (u8 *)__get_free_pages((GFP_KERNEL | GFP_DMA),
+					get_order(size));
+
+	if (!ptr)
+		return NULL;
+
+	memset(ptr, 0, size);
+
+	zip_dbg("Data buffer allocation success\n");
+	return ptr;
+}
+
+/**
+ * zip_data_buf_free - Frees the memory of a data buffer
+ * @ptr:  Pointer to the buffer
+ * @size: Buffer size
+ */
+void zip_data_buf_free(u8 *ptr, u64 size)
+{
+	zip_dbg("Freeing data buffer 0x%lx\n", ptr);
+
+	free_pages((u64)ptr, get_order(size));
+}
diff --git a/drivers/crypto/cavium/zip/zip_mem.h b/drivers/crypto/cavium/zip/zip_mem.h
new file mode 100644
index 000000000000..f8f2f08c4a5c
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_mem.h
@@ -0,0 +1,78 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_MEM_H__
+#define __ZIP_MEM_H__
+
+/**
+ * zip_cmd_qbuf_free - Frees the cmd Queue buffer
+ * @zip: Pointer to zip device structure
+ * @q:   Queue nmber to free buffer of
+ */
+void zip_cmd_qbuf_free(struct zip_device *zip, int q);
+
+/**
+ * zip_cmd_qbuf_alloc - Allocates a Chunk/cmd buffer for ZIP Inst(cmd) Queue
+ * @zip: Pointer to zip device structure
+ * @q:   Queue number to allocate bufffer to
+ * Return: 0 if successful, 1 otherwise
+ */
+int zip_cmd_qbuf_alloc(struct zip_device *zip, int q);
+
+/**
+ * zip_data_buf_alloc - Allocates memory for a data bufffer
+ * @size:   Size of the buffer to allocate
+ * Returns: Pointer to the buffer allocated
+ */
+u8 *zip_data_buf_alloc(u64 size);
+
+/**
+ * zip_data_buf_free - Frees the memory of a data buffer
+ * @ptr:  Pointer to the buffer
+ * @size: Buffer size
+ */
+void zip_data_buf_free(u8 *ptr, u64 size);
+
+#endif
diff --git a/drivers/crypto/cavium/zip/zip_regs.h b/drivers/crypto/cavium/zip/zip_regs.h
new file mode 100644
index 000000000000..d0be682305c1
--- /dev/null
+++ b/drivers/crypto/cavium/zip/zip_regs.h
@@ -0,0 +1,1347 @@
+/***********************license start************************************
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ * All rights reserved.
+ *
+ * License: one of 'Cavium License' or 'GNU General Public License Version 2'
+ *
+ * This file is provided under the terms of the Cavium License (see below)
+ * or under the terms of GNU General Public License, Version 2, as
+ * published by the Free Software Foundation. When using or redistributing
+ * this file, you may do so under either license.
+ *
+ * Cavium License:  Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ *  * Redistributions in binary form must reproduce the above
+ *    copyright notice, this list of conditions and the following
+ *    disclaimer in the documentation and/or other materials provided
+ *    with the distribution.
+ *
+ *  * Neither the name of Cavium Inc. nor the names of its contributors may be
+ *    used to endorse or promote products derived from this software without
+ *    specific prior written permission.
+ *
+ * This Software, including technical data, may be subject to U.S. export
+ * control laws, including the U.S. Export Administration Act and its
+ * associated regulations, and may be subject to export or import
+ * regulations in other countries.
+ *
+ * TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE SOFTWARE IS PROVIDED "AS IS"
+ * AND WITH ALL FAULTS AND CAVIUM INC. MAKES NO PROMISES, REPRESENTATIONS
+ * OR WARRANTIES, EITHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, WITH
+ * RESPECT TO THE SOFTWARE, INCLUDING ITS CONDITION, ITS CONFORMITY TO ANY
+ * REPRESENTATION OR DESCRIPTION, OR THE EXISTENCE OF ANY LATENT OR PATENT
+ * DEFECTS, AND CAVIUM SPECIFICALLY DISCLAIMS ALL IMPLIED (IF ANY)
+ * WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR A
+ * PARTICULAR PURPOSE, LACK OF VIRUSES, ACCURACY OR COMPLETENESS, QUIET
+ * ENJOYMENT, QUIET POSSESSION OR CORRESPONDENCE TO DESCRIPTION. THE
+ * ENTIRE  RISK ARISING OUT OF USE OR PERFORMANCE OF THE SOFTWARE LIES
+ * WITH YOU.
+ ***********************license end**************************************/
+
+#ifndef __ZIP_REGS_H__
+#define __ZIP_REGS_H__
+
+/*
+ * Configuration and status register (CSR) address and type definitions for
+ * Cavium ZIP.
+ */
+
+#include <linux/kern_levels.h>
+
+/* ZIP invocation result completion status codes */
+#define ZIP_CMD_NOTDONE        0x0
+
+/* Successful completion. */
+#define ZIP_CMD_SUCCESS        0x1
+
+/* Output truncated */
+#define ZIP_CMD_DTRUNC         0x2
+
+/* Dynamic Stop */
+#define ZIP_CMD_DYNAMIC_STOP   0x3
+
+/* Uncompress ran out of input data when IWORD0[EF] was set */
+#define ZIP_CMD_ITRUNC         0x4
+
+/* Uncompress found the reserved block type 3 */
+#define ZIP_CMD_RBLOCK         0x5
+
+/*
+ * Uncompress found LEN != ZIP_CMD_NLEN in an uncompressed block in the input.
+ */
+#define ZIP_CMD_NLEN           0x6
+
+/* Uncompress found a bad code in the main Huffman codes. */
+#define ZIP_CMD_BADCODE        0x7
+
+/* Uncompress found a bad code in the 19 Huffman codes encoding lengths. */
+#define ZIP_CMD_BADCODE2       0x8
+
+/* Compress found a zero-length input. */
+#define ZIP_CMD_ZERO_LEN       0x9
+
+/* The compress or decompress encountered an internal parity error. */
+#define ZIP_CMD_PARITY         0xA
+
+/*
+ * Uncompress found a string identifier that precedes the uncompressed data and
+ * decompression history.
+ */
+#define ZIP_CMD_FATAL          0xB
+
+/**
+ * enum zip_int_vec_e - ZIP MSI-X Vector Enumeration, enumerates the MSI-X
+ * interrupt vectors.
+ */
+enum zip_int_vec_e {
+	ZIP_INT_VEC_E_ECCE = 0x10,
+	ZIP_INT_VEC_E_FIFE = 0x11,
+	ZIP_INT_VEC_E_QUE0_DONE = 0x0,
+	ZIP_INT_VEC_E_QUE0_ERR = 0x8,
+	ZIP_INT_VEC_E_QUE1_DONE = 0x1,
+	ZIP_INT_VEC_E_QUE1_ERR = 0x9,
+	ZIP_INT_VEC_E_QUE2_DONE = 0x2,
+	ZIP_INT_VEC_E_QUE2_ERR = 0xa,
+	ZIP_INT_VEC_E_QUE3_DONE = 0x3,
+	ZIP_INT_VEC_E_QUE3_ERR = 0xb,
+	ZIP_INT_VEC_E_QUE4_DONE = 0x4,
+	ZIP_INT_VEC_E_QUE4_ERR = 0xc,
+	ZIP_INT_VEC_E_QUE5_DONE = 0x5,
+	ZIP_INT_VEC_E_QUE5_ERR = 0xd,
+	ZIP_INT_VEC_E_QUE6_DONE = 0x6,
+	ZIP_INT_VEC_E_QUE6_ERR = 0xe,
+	ZIP_INT_VEC_E_QUE7_DONE = 0x7,
+	ZIP_INT_VEC_E_QUE7_ERR = 0xf,
+	ZIP_INT_VEC_E_ENUM_LAST = 0x12,
+};
+
+/**
+ * union zip_zptr_addr_s - ZIP Generic Pointer Structure for ADDR.
+ *
+ * It is the generic format of pointers in ZIP_INST_S.
+ */
+union zip_zptr_addr_s {
+	u64 u_reg64;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_49_63              : 15;
+		u64 addr                        : 49;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 addr                        : 49;
+		u64 reserved_49_63              : 15;
+#endif
+	} s;
+
+};
+
+/**
+ * union zip_zptr_ctl_s - ZIP Generic Pointer Structure for CTL.
+ *
+ * It is the generic format of pointers in ZIP_INST_S.
+ */
+union zip_zptr_ctl_s {
+	u64 u_reg64;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_112_127            : 16;
+		u64 length                      : 16;
+		u64 reserved_67_95              : 29;
+		u64 fw                          : 1;
+		u64 nc                          : 1;
+		u64 data_be                     : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 data_be                     : 1;
+		u64 nc                          : 1;
+		u64 fw                          : 1;
+		u64 reserved_67_95              : 29;
+		u64 length                      : 16;
+		u64 reserved_112_127            : 16;
+#endif
+	} s;
+};
+
+/**
+ * union zip_inst_s - ZIP Instruction Structure.
+ * Each ZIP instruction has 16 words (they are called IWORD0 to IWORD15 within
+ * the structure).
+ */
+union zip_inst_s {
+	u64 u_reg64[16];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 doneint                     : 1;
+		u64 reserved_56_62              : 7;
+		u64 totaloutputlength           : 24;
+		u64 reserved_27_31              : 5;
+		u64 exn                         : 3;
+		u64 reserved_23_23              : 1;
+		u64 exbits                      : 7;
+		u64 reserved_12_15              : 4;
+		u64 sf                          : 1;
+		u64 ss                          : 2;
+		u64 cc                          : 2;
+		u64 ef                          : 1;
+		u64 bf                          : 1;
+		u64 ce                          : 1;
+		u64 reserved_3_3                : 1;
+		u64 ds                          : 1;
+		u64 dg                          : 1;
+		u64 hg                          : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 hg                          : 1;
+		u64 dg                          : 1;
+		u64 ds                          : 1;
+		u64 reserved_3_3                : 1;
+		u64 ce                          : 1;
+		u64 bf                          : 1;
+		u64 ef                          : 1;
+		u64 cc                          : 2;
+		u64 ss                          : 2;
+		u64 sf                          : 1;
+		u64 reserved_12_15              : 4;
+		u64 exbits                      : 7;
+		u64 reserved_23_23              : 1;
+		u64 exn                         : 3;
+		u64 reserved_27_31              : 5;
+		u64 totaloutputlength           : 24;
+		u64 reserved_56_62              : 7;
+		u64 doneint                     : 1;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 historylength               : 16;
+		u64 reserved_96_111             : 16;
+		u64 adlercrc32                  : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 adlercrc32                  : 32;
+		u64 reserved_96_111             : 16;
+		u64 historylength               : 16;
+#endif
+		union zip_zptr_addr_s ctx_ptr_addr;
+		union zip_zptr_ctl_s ctx_ptr_ctl;
+		union zip_zptr_addr_s his_ptr_addr;
+		union zip_zptr_ctl_s his_ptr_ctl;
+		union zip_zptr_addr_s inp_ptr_addr;
+		union zip_zptr_ctl_s inp_ptr_ctl;
+		union zip_zptr_addr_s out_ptr_addr;
+		union zip_zptr_ctl_s out_ptr_ctl;
+		union zip_zptr_addr_s res_ptr_addr;
+		union zip_zptr_ctl_s res_ptr_ctl;
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_817_831            : 15;
+		u64 wq_ptr                      : 49;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 wq_ptr                      : 49;
+		u64 reserved_817_831            : 15;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_882_895            : 14;
+		u64 tt                          : 2;
+		u64 reserved_874_879            : 6;
+		u64 grp                         : 10;
+		u64 tag                         : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 tag                         : 32;
+		u64 grp                         : 10;
+		u64 reserved_874_879            : 6;
+		u64 tt                          : 2;
+		u64 reserved_882_895            : 14;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_896_959            : 64;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 reserved_896_959            : 64;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_960_1023           : 64;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 reserved_960_1023           : 64;
+#endif
+	} s;
+};
+
+/**
+ * union zip_nptr_s - ZIP Instruction Next-Chunk-Buffer Pointer (NPTR)
+ * Structure
+ *
+ * ZIP_NPTR structure is used to chain all the zip instruction buffers
+ * together. ZIP instruction buffers are managed (allocated and released) by
+ * the software.
+ */
+union zip_nptr_s {
+	u64 u_reg64;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_49_63              : 15;
+		u64 addr                        : 49;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 addr                        : 49;
+		u64 reserved_49_63              : 15;
+#endif
+	} s;
+};
+
+/**
+ * union zip_zptr_s - ZIP Generic Pointer Structure.
+ *
+ * It is the generic format of pointers in ZIP_INST_S.
+ */
+union zip_zptr_s {
+	u64 u_reg64[2];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_49_63              : 15;
+		u64 addr                        : 49;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 addr                        : 49;
+		u64 reserved_49_63              : 15;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_112_127            : 16;
+		u64 length                      : 16;
+		u64 reserved_67_95              : 29;
+		u64 fw                          : 1;
+		u64 nc                          : 1;
+		u64 data_be                     : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 data_be                     : 1;
+		u64 nc                          : 1;
+		u64 fw                          : 1;
+		u64 reserved_67_95              : 29;
+		u64 length                      : 16;
+		u64 reserved_112_127            : 16;
+#endif
+	} s;
+};
+
+/**
+ * union zip_zres_s - ZIP Result Structure
+ *
+ * The ZIP coprocessor writes the result structure after it completes the
+ * invocation. The result structure is exactly 24 bytes, and each invocation of
+ * the ZIP coprocessor produces exactly one result structure.
+ */
+union zip_zres_s {
+	u64 u_reg64[3];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 crc32                       : 32;
+		u64 adler32                     : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 adler32                     : 32;
+		u64 crc32                       : 32;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 totalbyteswritten           : 32;
+		u64 totalbytesread              : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 totalbytesread              : 32;
+		u64 totalbyteswritten           : 32;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 totalbitsprocessed          : 32;
+		u64 doneint                     : 1;
+		u64 reserved_155_158            : 4;
+		u64 exn                         : 3;
+		u64 reserved_151_151            : 1;
+		u64 exbits                      : 7;
+		u64 reserved_137_143            : 7;
+		u64 ef                          : 1;
+
+		volatile u64 compcode           : 8;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+
+		volatile u64 compcode           : 8;
+		u64 ef                          : 1;
+		u64 reserved_137_143            : 7;
+		u64 exbits                      : 7;
+		u64 reserved_151_151            : 1;
+		u64 exn                         : 3;
+		u64 reserved_155_158            : 4;
+		u64 doneint                     : 1;
+		u64 totalbitsprocessed          : 32;
+#endif
+	} s;
+};
+
+/**
+ * union zip_cmd_ctl - Structure representing the register that controls
+ * clock and reset.
+ */
+union zip_cmd_ctl {
+	u64 u_reg64;
+	struct zip_cmd_ctl_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_2_63               : 62;
+		u64 forceclk                    : 1;
+		u64 reset                       : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 reset                       : 1;
+		u64 forceclk                    : 1;
+		u64 reserved_2_63               : 62;
+#endif
+	} s;
+};
+
+#define ZIP_CMD_CTL 0x0ull
+
+/**
+ * union zip_constants - Data structure representing the register that contains
+ * all of the current implementation-related parameters of the zip core in this
+ * chip.
+ */
+union zip_constants {
+	u64 u_reg64;
+	struct zip_constants_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 nexec                       : 8;
+		u64 reserved_49_55              : 7;
+		u64 syncflush_capable           : 1;
+		u64 depth                       : 16;
+		u64 onfsize                     : 12;
+		u64 ctxsize                     : 12;
+		u64 reserved_1_7                : 7;
+		u64 disabled                    : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 disabled                    : 1;
+		u64 reserved_1_7                : 7;
+		u64 ctxsize                     : 12;
+		u64 onfsize                     : 12;
+		u64 depth                       : 16;
+		u64 syncflush_capable           : 1;
+		u64 reserved_49_55              : 7;
+		u64 nexec                       : 8;
+#endif
+	} s;
+};
+
+#define ZIP_CONSTANTS 0x00A0ull
+
+/**
+ * union zip_corex_bist_status - Represents registers which have the BIST
+ * status of memories in zip cores.
+ *
+ * Each bit is the BIST result of an individual memory
+ * (per bit, 0 = pass and 1 = fail).
+ */
+union zip_corex_bist_status {
+	u64 u_reg64;
+	struct zip_corex_bist_status_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_53_63              : 11;
+		u64 bstatus                     : 53;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 bstatus                     : 53;
+		u64 reserved_53_63              : 11;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_COREX_BIST_STATUS(u64 param1)
+{
+	if (((param1 <= 1)))
+		return 0x0520ull + (param1 & 1) * 0x8ull;
+	pr_err("ZIP_COREX_BIST_STATUS: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_ctl_bist_status - Represents register that has the BIST status of
+ * memories in ZIP_CTL (instruction buffer, G/S pointer FIFO, input data
+ * buffer, output data buffers).
+ *
+ * Each bit is the BIST result of an individual memory
+ * (per bit, 0 = pass and 1 = fail).
+ */
+union zip_ctl_bist_status {
+	u64 u_reg64;
+	struct zip_ctl_bist_status_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_9_63               : 55;
+		u64 bstatus                     : 9;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 bstatus                     : 9;
+		u64 reserved_9_63               : 55;
+#endif
+	} s;
+};
+
+#define ZIP_CTL_BIST_STATUS 0x0510ull
+
+/**
+ * union zip_ctl_cfg - Represents the register that controls the behavior of
+ * the ZIP DMA engines.
+ *
+ * It is recommended to keep default values for normal operation. Changing the
+ * values of the fields may be useful for diagnostics.
+ */
+union zip_ctl_cfg {
+	u64 u_reg64;
+	struct zip_ctl_cfg_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_52_63              : 12;
+		u64 ildf                        : 4;
+		u64 reserved_36_47              : 12;
+		u64 drtf                        : 4;
+		u64 reserved_27_31              : 5;
+		u64 stcf                        : 3;
+		u64 reserved_19_23              : 5;
+		u64 ldf                         : 3;
+		u64 reserved_2_15               : 14;
+		u64 busy                        : 1;
+		u64 reserved_0_0                : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 reserved_0_0                : 1;
+		u64 busy                        : 1;
+		u64 reserved_2_15               : 14;
+		u64 ldf                         : 3;
+		u64 reserved_19_23              : 5;
+		u64 stcf                        : 3;
+		u64 reserved_27_31              : 5;
+		u64 drtf                        : 4;
+		u64 reserved_36_47              : 12;
+		u64 ildf                        : 4;
+		u64 reserved_52_63              : 12;
+#endif
+	} s;
+};
+
+#define ZIP_CTL_CFG 0x0560ull
+
+/**
+ * union zip_dbg_corex_inst - Represents the registers that reflect the status
+ * of the current instruction that the ZIP core is executing or has executed.
+ *
+ * These registers are only for debug use.
+ */
+union zip_dbg_corex_inst {
+	u64 u_reg64;
+	struct zip_dbg_corex_inst_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 busy                        : 1;
+		u64 reserved_35_62              : 28;
+		u64 qid                         : 3;
+		u64 iid                         : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 iid                         : 32;
+		u64 qid                         : 3;
+		u64 reserved_35_62              : 28;
+		u64 busy                        : 1;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_DBG_COREX_INST(u64 param1)
+{
+	if (((param1 <= 1)))
+		return 0x0640ull + (param1 & 1) * 0x8ull;
+	pr_err("ZIP_DBG_COREX_INST: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_dbg_corex_sta - Represents registers that reflect the status of
+ * the zip cores.
+ *
+ * They are for debug use only.
+ */
+union zip_dbg_corex_sta {
+	u64 u_reg64;
+	struct zip_dbg_corex_sta_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 busy                        : 1;
+		u64 reserved_37_62              : 26;
+		u64 ist                         : 5;
+		u64 nie                         : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 nie                         : 32;
+		u64 ist                         : 5;
+		u64 reserved_37_62              : 26;
+		u64 busy                        : 1;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_DBG_COREX_STA(u64 param1)
+{
+	if (((param1 <= 1)))
+		return 0x0680ull + (param1 & 1) * 0x8ull;
+	pr_err("ZIP_DBG_COREX_STA: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_dbg_quex_sta - Represets registers that reflect status of the zip
+ * instruction queues.
+ *
+ * They are for debug use only.
+ */
+union zip_dbg_quex_sta {
+	u64 u_reg64;
+	struct zip_dbg_quex_sta_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 busy                        : 1;
+		u64 reserved_56_62              : 7;
+		u64 rqwc                        : 24;
+		u64 nii                         : 32;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 nii                         : 32;
+		u64 rqwc                        : 24;
+		u64 reserved_56_62              : 7;
+		u64 busy                        : 1;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_DBG_QUEX_STA(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x1800ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_DBG_QUEX_STA: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_ecc_ctl - Represents the register that enables ECC for each
+ * individual internal memory that requires ECC.
+ *
+ * For debug purpose, it can also flip one or two bits in the ECC data.
+ */
+union zip_ecc_ctl {
+	u64 u_reg64;
+	struct zip_ecc_ctl_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_19_63              : 45;
+		u64 vmem_cdis                   : 1;
+		u64 vmem_fs                     : 2;
+		u64 reserved_15_15              : 1;
+		u64 idf1_cdis                   : 1;
+		u64 idf1_fs                     : 2;
+		u64 reserved_11_11              : 1;
+		u64 idf0_cdis                   : 1;
+		u64 idf0_fs                     : 2;
+		u64 reserved_7_7                : 1;
+		u64 gspf_cdis                   : 1;
+		u64 gspf_fs                     : 2;
+		u64 reserved_3_3                : 1;
+		u64 iqf_cdis                    : 1;
+		u64 iqf_fs                      : 2;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 iqf_fs                      : 2;
+		u64 iqf_cdis                    : 1;
+		u64 reserved_3_3                : 1;
+		u64 gspf_fs                     : 2;
+		u64 gspf_cdis                   : 1;
+		u64 reserved_7_7                : 1;
+		u64 idf0_fs                     : 2;
+		u64 idf0_cdis                   : 1;
+		u64 reserved_11_11              : 1;
+		u64 idf1_fs                     : 2;
+		u64 idf1_cdis                   : 1;
+		u64 reserved_15_15              : 1;
+		u64 vmem_fs                     : 2;
+		u64 vmem_cdis                   : 1;
+		u64 reserved_19_63              : 45;
+#endif
+	} s;
+};
+
+#define ZIP_ECC_CTL 0x0568ull
+
+/* NCB - zip_ecce_ena_w1c */
+union zip_ecce_ena_w1c {
+	u64 u_reg64;
+	struct zip_ecce_ena_w1c_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_37_63              : 27;
+		u64 dbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 sbe                         : 5;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 sbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 dbe                         : 5;
+		u64 reserved_37_63              : 27;
+#endif
+	} s;
+};
+
+#define ZIP_ECCE_ENA_W1C 0x0598ull
+
+/* NCB - zip_ecce_ena_w1s */
+union zip_ecce_ena_w1s {
+	u64 u_reg64;
+	struct zip_ecce_ena_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_37_63              : 27;
+		u64 dbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 sbe                         : 5;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 sbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 dbe                         : 5;
+		u64 reserved_37_63              : 27;
+#endif
+	} s;
+};
+
+#define ZIP_ECCE_ENA_W1S 0x0590ull
+
+/**
+ * union zip_ecce_int - Represents the register that contains the status of the
+ * ECC interrupt sources.
+ */
+union zip_ecce_int {
+	u64 u_reg64;
+	struct zip_ecce_int_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_37_63              : 27;
+		u64 dbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 sbe                         : 5;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 sbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 dbe                         : 5;
+		u64 reserved_37_63              : 27;
+#endif
+	} s;
+};
+
+#define ZIP_ECCE_INT 0x0580ull
+
+/* NCB - zip_ecce_int_w1s */
+union zip_ecce_int_w1s {
+	u64 u_reg64;
+	struct zip_ecce_int_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_37_63              : 27;
+		u64 dbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 sbe                         : 5;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 sbe                         : 5;
+		u64 reserved_5_31               : 27;
+		u64 dbe                         : 5;
+		u64 reserved_37_63              : 27;
+#endif
+	} s;
+};
+
+#define ZIP_ECCE_INT_W1S 0x0588ull
+
+/* NCB - zip_fife_ena_w1c */
+union zip_fife_ena_w1c {
+	u64 u_reg64;
+	struct zip_fife_ena_w1c_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_42_63              : 22;
+		u64 asserts                     : 42;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 asserts                     : 42;
+		u64 reserved_42_63              : 22;
+#endif
+	} s;
+};
+
+#define ZIP_FIFE_ENA_W1C 0x0090ull
+
+/* NCB - zip_fife_ena_w1s */
+union zip_fife_ena_w1s {
+	u64 u_reg64;
+	struct zip_fife_ena_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_42_63              : 22;
+		u64 asserts                     : 42;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 asserts                     : 42;
+		u64 reserved_42_63              : 22;
+#endif
+	} s;
+};
+
+#define ZIP_FIFE_ENA_W1S 0x0088ull
+
+/* NCB - zip_fife_int */
+union zip_fife_int {
+	u64 u_reg64;
+	struct zip_fife_int_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_42_63              : 22;
+		u64 asserts                     : 42;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 asserts                     : 42;
+		u64 reserved_42_63              : 22;
+#endif
+	} s;
+};
+
+#define ZIP_FIFE_INT 0x0078ull
+
+/* NCB - zip_fife_int_w1s */
+union zip_fife_int_w1s {
+	u64 u_reg64;
+	struct zip_fife_int_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_42_63              : 22;
+		u64 asserts                     : 42;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 asserts                     : 42;
+		u64 reserved_42_63              : 22;
+#endif
+	} s;
+};
+
+#define ZIP_FIFE_INT_W1S 0x0080ull
+
+/**
+ * union zip_msix_pbax - Represents the register that is the MSI-X PBA table
+ *
+ * The bit number is indexed by the ZIP_INT_VEC_E enumeration.
+ */
+union zip_msix_pbax {
+	u64 u_reg64;
+	struct zip_msix_pbax_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 pend                        : 64;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 pend                        : 64;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_MSIX_PBAX(u64 param1)
+{
+	if (((param1 == 0)))
+		return 0x0000838000FF0000ull;
+	pr_err("ZIP_MSIX_PBAX: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_msix_vecx_addr - Represents the register that is the MSI-X vector
+ * table, indexed by the ZIP_INT_VEC_E enumeration.
+ */
+union zip_msix_vecx_addr {
+	u64 u_reg64;
+	struct zip_msix_vecx_addr_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_49_63              : 15;
+		u64 addr                        : 47;
+		u64 reserved_1_1                : 1;
+		u64 secvec                      : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 secvec                      : 1;
+		u64 reserved_1_1                : 1;
+		u64 addr                        : 47;
+		u64 reserved_49_63              : 15;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_MSIX_VECX_ADDR(u64 param1)
+{
+	if (((param1 <= 17)))
+		return 0x0000838000F00000ull + (param1 & 31) * 0x10ull;
+	pr_err("ZIP_MSIX_VECX_ADDR: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_msix_vecx_ctl - Represents the register that is the MSI-X vector
+ * table, indexed by the ZIP_INT_VEC_E enumeration.
+ */
+union zip_msix_vecx_ctl {
+	u64 u_reg64;
+	struct zip_msix_vecx_ctl_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_33_63              : 31;
+		u64 mask                        : 1;
+		u64 reserved_20_31              : 12;
+		u64 data                        : 20;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 data                        : 20;
+		u64 reserved_20_31              : 12;
+		u64 mask                        : 1;
+		u64 reserved_33_63              : 31;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_MSIX_VECX_CTL(u64 param1)
+{
+	if (((param1 <= 17)))
+		return 0x0000838000F00008ull + (param1 & 31) * 0x10ull;
+	pr_err("ZIP_MSIX_VECX_CTL: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_done - Represents the registers that contain the per-queue
+ * instruction done count.
+ */
+union zip_quex_done {
+	u64 u_reg64;
+	struct zip_quex_done_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_20_63              : 44;
+		u64 done                        : 20;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 done                        : 20;
+		u64 reserved_20_63              : 44;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_DONE(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x2000ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_DONE: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_done_ack - Represents the registers on write to which will
+ * decrement the per-queue instructiona done count.
+ */
+union zip_quex_done_ack {
+	u64 u_reg64;
+	struct zip_quex_done_ack_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_20_63              : 44;
+		u64 done_ack                    : 20;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 done_ack                    : 20;
+		u64 reserved_20_63              : 44;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_DONE_ACK(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x2200ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_DONE_ACK: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_done_ena_w1c - Represents the register which when written
+ * 1 to will disable the DONEINT interrupt for the queue.
+ */
+union zip_quex_done_ena_w1c {
+	u64 u_reg64;
+	struct zip_quex_done_ena_w1c_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_1_63               : 63;
+		u64 done_ena                    : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 done_ena                    : 1;
+		u64 reserved_1_63               : 63;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_DONE_ENA_W1C(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x2600ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_DONE_ENA_W1C: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_done_ena_w1s - Represents the register that when written 1 to
+ * will enable the DONEINT interrupt for the queue.
+ */
+union zip_quex_done_ena_w1s {
+	u64 u_reg64;
+	struct zip_quex_done_ena_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_1_63               : 63;
+		u64 done_ena                    : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 done_ena                    : 1;
+		u64 reserved_1_63               : 63;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_DONE_ENA_W1S(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x2400ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_DONE_ENA_W1S: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_done_wait - Represents the register that specifies the per
+ * queue interrupt coalescing settings.
+ */
+union zip_quex_done_wait {
+	u64 u_reg64;
+	struct zip_quex_done_wait_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_48_63              : 16;
+		u64 time_wait                   : 16;
+		u64 reserved_20_31              : 12;
+		u64 num_wait                    : 20;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 num_wait                    : 20;
+		u64 reserved_20_31              : 12;
+		u64 time_wait                   : 16;
+		u64 reserved_48_63              : 16;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_DONE_WAIT(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x2800ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_DONE_WAIT: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_doorbell - Represents doorbell registers for the ZIP
+ * instruction queues.
+ */
+union zip_quex_doorbell {
+	u64 u_reg64;
+	struct zip_quex_doorbell_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_20_63              : 44;
+		u64 dbell_cnt                   : 20;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 dbell_cnt                   : 20;
+		u64 reserved_20_63              : 44;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_DOORBELL(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x4000ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_DOORBELL: %llu\n", param1);
+	return 0;
+}
+
+union zip_quex_err_ena_w1c {
+	u64 u_reg64;
+	struct zip_quex_err_ena_w1c_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_5_63               : 59;
+		u64 mdbe                        : 1;
+		u64 nwrp                        : 1;
+		u64 nrrp                        : 1;
+		u64 irde                        : 1;
+		u64 dovf                        : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 dovf                        : 1;
+		u64 irde                        : 1;
+		u64 nrrp                        : 1;
+		u64 nwrp                        : 1;
+		u64 mdbe                        : 1;
+		u64 reserved_5_63               : 59;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_ERR_ENA_W1C(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x3600ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_ERR_ENA_W1C: %llu\n", param1);
+	return 0;
+}
+
+union zip_quex_err_ena_w1s {
+	u64 u_reg64;
+	struct zip_quex_err_ena_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_5_63               : 59;
+		u64 mdbe                        : 1;
+		u64 nwrp                        : 1;
+		u64 nrrp                        : 1;
+		u64 irde                        : 1;
+		u64 dovf                        : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 dovf                        : 1;
+		u64 irde                        : 1;
+		u64 nrrp                        : 1;
+		u64 nwrp                        : 1;
+		u64 mdbe                        : 1;
+		u64 reserved_5_63               : 59;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_ERR_ENA_W1S(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x3400ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_ERR_ENA_W1S: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_err_int - Represents registers that contain the per-queue
+ * error interrupts.
+ */
+union zip_quex_err_int {
+	u64 u_reg64;
+	struct zip_quex_err_int_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_5_63               : 59;
+		u64 mdbe                        : 1;
+		u64 nwrp                        : 1;
+		u64 nrrp                        : 1;
+		u64 irde                        : 1;
+		u64 dovf                        : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 dovf                        : 1;
+		u64 irde                        : 1;
+		u64 nrrp                        : 1;
+		u64 nwrp                        : 1;
+		u64 mdbe                        : 1;
+		u64 reserved_5_63               : 59;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_ERR_INT(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x3000ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_ERR_INT: %llu\n", param1);
+	return 0;
+}
+
+/* NCB - zip_que#_err_int_w1s */
+union zip_quex_err_int_w1s {
+	u64 u_reg64;
+	struct zip_quex_err_int_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_5_63               : 59;
+		u64 mdbe                        : 1;
+		u64 nwrp                        : 1;
+		u64 nrrp                        : 1;
+		u64 irde                        : 1;
+		u64 dovf                        : 1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 dovf                        : 1;
+		u64 irde                        : 1;
+		u64 nrrp                        : 1;
+		u64 nwrp                        : 1;
+		u64 mdbe                        : 1;
+		u64 reserved_5_63               : 59;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_ERR_INT_W1S(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x3200ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_ERR_INT_W1S: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_gcfg - Represents the registers that reflect status of the
+ * zip instruction queues,debug use only.
+ */
+union zip_quex_gcfg {
+	u64 u_reg64;
+	struct zip_quex_gcfg_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_4_63               : 60;
+		u64 iqb_ldwb                    : 1;
+		u64 cbw_sty                     : 1;
+		u64 l2ld_cmd                    : 2;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 l2ld_cmd                    : 2;
+		u64 cbw_sty                     : 1;
+		u64 iqb_ldwb                    : 1;
+		u64 reserved_4_63               : 60;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_GCFG(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x1A00ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_GCFG: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_map - Represents the registers that control how each
+ * instruction queue maps to zip cores.
+ */
+union zip_quex_map {
+	u64 u_reg64;
+	struct zip_quex_map_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_2_63               : 62;
+		u64 zce                         : 2;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 zce                         : 2;
+		u64 reserved_2_63               : 62;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_MAP(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x1400ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_MAP: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_sbuf_addr - Represents the registers that set the buffer
+ * parameters for the instruction queues.
+ *
+ * When quiescent (i.e. outstanding doorbell count is 0), it is safe to rewrite
+ * this register to effectively reset the command buffer state machine.
+ * These registers must be programmed after SW programs the corresponding
+ * ZIP_QUE(0..7)_SBUF_CTL.
+ */
+union zip_quex_sbuf_addr {
+	u64 u_reg64;
+	struct zip_quex_sbuf_addr_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_49_63              : 15;
+		u64 ptr                         : 42;
+		u64 off                         : 7;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 off                         : 7;
+		u64 ptr                         : 42;
+		u64 reserved_49_63              : 15;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_SBUF_ADDR(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x1000ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_SBUF_ADDR: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_quex_sbuf_ctl - Represents the registers that set the buffer
+ * parameters for the instruction queues.
+ *
+ * When quiescent (i.e. outstanding doorbell count is 0), it is safe to rewrite
+ * this register to effectively reset the command buffer state machine.
+ * These registers must be programmed before SW programs the corresponding
+ * ZIP_QUE(0..7)_SBUF_ADDR.
+ */
+union zip_quex_sbuf_ctl {
+	u64 u_reg64;
+	struct zip_quex_sbuf_ctl_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_45_63              : 19;
+		u64 size                        : 13;
+		u64 inst_be                     : 1;
+		u64 reserved_24_30              : 7;
+		u64 stream_id                   : 8;
+		u64 reserved_12_15              : 4;
+		u64 aura                        : 12;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 aura                        : 12;
+		u64 reserved_12_15              : 4;
+		u64 stream_id                   : 8;
+		u64 reserved_24_30              : 7;
+		u64 inst_be                     : 1;
+		u64 size                        : 13;
+		u64 reserved_45_63              : 19;
+#endif
+	} s;
+};
+
+static inline u64 ZIP_QUEX_SBUF_CTL(u64 param1)
+{
+	if (((param1 <= 7)))
+		return 0x1200ull + (param1 & 7) * 0x8ull;
+	pr_err("ZIP_QUEX_SBUF_CTL: %llu\n", param1);
+	return 0;
+}
+
+/**
+ * union zip_que_ena - Represents queue enable register
+ *
+ * If a queue is disabled, ZIP_CTL stops fetching instructions from the queue.
+ */
+union zip_que_ena {
+	u64 u_reg64;
+	struct zip_que_ena_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_8_63               : 56;
+		u64 ena                         : 8;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 ena                         : 8;
+		u64 reserved_8_63               : 56;
+#endif
+	} s;
+};
+
+#define ZIP_QUE_ENA 0x0500ull
+
+/**
+ * union zip_que_pri - Represents the register that defines the priority
+ * between instruction queues.
+ */
+union zip_que_pri {
+	u64 u_reg64;
+	struct zip_que_pri_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_8_63               : 56;
+		u64 pri                         : 8;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 pri                         : 8;
+		u64 reserved_8_63               : 56;
+#endif
+	} s;
+};
+
+#define ZIP_QUE_PRI 0x0508ull
+
+/**
+ * union zip_throttle - Represents the register that controls the maximum
+ * number of in-flight X2I data fetch transactions.
+ *
+ * Writing 0 to this register causes the ZIP module to temporarily suspend NCB
+ * accesses; it is not recommended for normal operation, but may be useful for
+ * diagnostics.
+ */
+union zip_throttle {
+	u64 u_reg64;
+	struct zip_throttle_s {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved_6_63               : 58;
+		u64 ld_infl                     : 6;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+		u64 ld_infl                     : 6;
+		u64 reserved_6_63               : 58;
+#endif
+	} s;
+};
+
+#define ZIP_THROTTLE 0x0010ull
+
+#endif /* _CSRS_ZIP__ */
diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile
index 346ceb8f17bd..60919a3ec53b 100644
--- a/drivers/crypto/ccp/Makefile
+++ b/drivers/crypto/ccp/Makefile
@@ -12,4 +12,6 @@ ccp-crypto-objs := ccp-crypto-main.o \
 		   ccp-crypto-aes.o \
 		   ccp-crypto-aes-cmac.o \
 		   ccp-crypto-aes-xts.o \
+		   ccp-crypto-aes-galois.o \
+		   ccp-crypto-des3.o \
 		   ccp-crypto-sha.o
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-galois.c b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
new file mode 100644
index 000000000000..38ee6f348ea9
--- /dev/null
+++ b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
@@ -0,0 +1,252 @@
+/*
+ * AMD Cryptographic Coprocessor (CCP) AES GCM crypto API support
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Gary R Hook <gary.hook@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/scatterlist.h>
+#include <linux/crypto.h>
+#include <crypto/internal/aead.h>
+#include <crypto/algapi.h>
+#include <crypto/aes.h>
+#include <crypto/ctr.h>
+#include <crypto/scatterwalk.h>
+#include <linux/delay.h>
+
+#include "ccp-crypto.h"
+
+#define	AES_GCM_IVSIZE	12
+
+static int ccp_aes_gcm_complete(struct crypto_async_request *async_req, int ret)
+{
+	return ret;
+}
+
+static int ccp_aes_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
+			      unsigned int key_len)
+{
+	struct ccp_ctx *ctx = crypto_aead_ctx(tfm);
+
+	switch (key_len) {
+	case AES_KEYSIZE_128:
+		ctx->u.aes.type = CCP_AES_TYPE_128;
+		break;
+	case AES_KEYSIZE_192:
+		ctx->u.aes.type = CCP_AES_TYPE_192;
+		break;
+	case AES_KEYSIZE_256:
+		ctx->u.aes.type = CCP_AES_TYPE_256;
+		break;
+	default:
+		crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	ctx->u.aes.mode = CCP_AES_MODE_GCM;
+	ctx->u.aes.key_len = key_len;
+
+	memcpy(ctx->u.aes.key, key, key_len);
+	sg_init_one(&ctx->u.aes.key_sg, ctx->u.aes.key, key_len);
+
+	return 0;
+}
+
+static int ccp_aes_gcm_setauthsize(struct crypto_aead *tfm,
+				   unsigned int authsize)
+{
+	return 0;
+}
+
+static int ccp_aes_gcm_crypt(struct aead_request *req, bool encrypt)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct ccp_ctx *ctx = crypto_aead_ctx(tfm);
+	struct ccp_aes_req_ctx *rctx = aead_request_ctx(req);
+	struct scatterlist *iv_sg = NULL;
+	unsigned int iv_len = 0;
+	int i;
+	int ret = 0;
+
+	if (!ctx->u.aes.key_len)
+		return -EINVAL;
+
+	if (ctx->u.aes.mode != CCP_AES_MODE_GCM)
+		return -EINVAL;
+
+	if (!req->iv)
+		return -EINVAL;
+
+	/*
+	 * 5 parts:
+	 *   plaintext/ciphertext input
+	 *   AAD
+	 *   key
+	 *   IV
+	 *   Destination+tag buffer
+	 */
+
+	/* Prepare the IV: 12 bytes + an integer (counter) */
+	memcpy(rctx->iv, req->iv, AES_GCM_IVSIZE);
+	for (i = 0; i < 3; i++)
+		rctx->iv[i + AES_GCM_IVSIZE] = 0;
+	rctx->iv[AES_BLOCK_SIZE - 1] = 1;
+
+	/* Set up a scatterlist for the IV */
+	iv_sg = &rctx->iv_sg;
+	iv_len = AES_BLOCK_SIZE;
+	sg_init_one(iv_sg, rctx->iv, iv_len);
+
+	/* The AAD + plaintext are concatenated in the src buffer */
+	memset(&rctx->cmd, 0, sizeof(rctx->cmd));
+	INIT_LIST_HEAD(&rctx->cmd.entry);
+	rctx->cmd.engine = CCP_ENGINE_AES;
+	rctx->cmd.u.aes.type = ctx->u.aes.type;
+	rctx->cmd.u.aes.mode = ctx->u.aes.mode;
+	rctx->cmd.u.aes.action = encrypt;
+	rctx->cmd.u.aes.key = &ctx->u.aes.key_sg;
+	rctx->cmd.u.aes.key_len = ctx->u.aes.key_len;
+	rctx->cmd.u.aes.iv = iv_sg;
+	rctx->cmd.u.aes.iv_len = iv_len;
+	rctx->cmd.u.aes.src = req->src;
+	rctx->cmd.u.aes.src_len = req->cryptlen;
+	rctx->cmd.u.aes.aad_len = req->assoclen;
+
+	/* The cipher text + the tag are in the dst buffer */
+	rctx->cmd.u.aes.dst = req->dst;
+
+	ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd);
+
+	return ret;
+}
+
+static int ccp_aes_gcm_encrypt(struct aead_request *req)
+{
+	return ccp_aes_gcm_crypt(req, CCP_AES_ACTION_ENCRYPT);
+}
+
+static int ccp_aes_gcm_decrypt(struct aead_request *req)
+{
+	return ccp_aes_gcm_crypt(req, CCP_AES_ACTION_DECRYPT);
+}
+
+static int ccp_aes_gcm_cra_init(struct crypto_aead *tfm)
+{
+	struct ccp_ctx *ctx = crypto_aead_ctx(tfm);
+
+	ctx->complete = ccp_aes_gcm_complete;
+	ctx->u.aes.key_len = 0;
+
+	crypto_aead_set_reqsize(tfm, sizeof(struct ccp_aes_req_ctx));
+
+	return 0;
+}
+
+static void ccp_aes_gcm_cra_exit(struct crypto_tfm *tfm)
+{
+}
+
+static struct aead_alg ccp_aes_gcm_defaults = {
+	.setkey = ccp_aes_gcm_setkey,
+	.setauthsize = ccp_aes_gcm_setauthsize,
+	.encrypt = ccp_aes_gcm_encrypt,
+	.decrypt = ccp_aes_gcm_decrypt,
+	.init = ccp_aes_gcm_cra_init,
+	.ivsize = AES_GCM_IVSIZE,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.base = {
+		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_KERN_DRIVER_ONLY |
+				  CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize	= AES_BLOCK_SIZE,
+		.cra_ctxsize	= sizeof(struct ccp_ctx),
+		.cra_priority	= CCP_CRA_PRIORITY,
+		.cra_type	= &crypto_ablkcipher_type,
+		.cra_exit	= ccp_aes_gcm_cra_exit,
+		.cra_module	= THIS_MODULE,
+	},
+};
+
+struct ccp_aes_aead_def {
+	enum ccp_aes_mode mode;
+	unsigned int version;
+	const char *name;
+	const char *driver_name;
+	unsigned int blocksize;
+	unsigned int ivsize;
+	struct aead_alg *alg_defaults;
+};
+
+static struct ccp_aes_aead_def aes_aead_algs[] = {
+	{
+		.mode		= CCP_AES_MODE_GHASH,
+		.version	= CCP_VERSION(5, 0),
+		.name		= "gcm(aes)",
+		.driver_name	= "gcm-aes-ccp",
+		.blocksize	= 1,
+		.ivsize		= AES_BLOCK_SIZE,
+		.alg_defaults	= &ccp_aes_gcm_defaults,
+	},
+};
+
+static int ccp_register_aes_aead(struct list_head *head,
+				 const struct ccp_aes_aead_def *def)
+{
+	struct ccp_crypto_aead *ccp_aead;
+	struct aead_alg *alg;
+	int ret;
+
+	ccp_aead = kzalloc(sizeof(*ccp_aead), GFP_KERNEL);
+	if (!ccp_aead)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ccp_aead->entry);
+
+	ccp_aead->mode = def->mode;
+
+	/* Copy the defaults and override as necessary */
+	alg = &ccp_aead->alg;
+	*alg = *def->alg_defaults;
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		 def->driver_name);
+	alg->base.cra_blocksize = def->blocksize;
+	alg->base.cra_ablkcipher.ivsize = def->ivsize;
+
+	ret = crypto_register_aead(alg);
+	if (ret) {
+		pr_err("%s ablkcipher algorithm registration error (%d)\n",
+		       alg->base.cra_name, ret);
+		kfree(ccp_aead);
+		return ret;
+	}
+
+	list_add(&ccp_aead->entry, head);
+
+	return 0;
+}
+
+int ccp_register_aes_aeads(struct list_head *head)
+{
+	int i, ret;
+	unsigned int ccpversion = ccp_version();
+
+	for (i = 0; i < ARRAY_SIZE(aes_aead_algs); i++) {
+		if (aes_aead_algs[i].version > ccpversion)
+			continue;
+		ret = ccp_register_aes_aead(head, &aes_aead_algs[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/ccp/ccp-crypto-des3.c b/drivers/crypto/ccp/ccp-crypto-des3.c
new file mode 100644
index 000000000000..5af7347ae03c
--- /dev/null
+++ b/drivers/crypto/ccp/ccp-crypto-des3.c
@@ -0,0 +1,254 @@
+/*
+ * AMD Cryptographic Coprocessor (CCP) DES3 crypto API support
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Gary R Hook <ghook@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/scatterlist.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/des.h>
+
+#include "ccp-crypto.h"
+
+static int ccp_des3_complete(struct crypto_async_request *async_req, int ret)
+{
+	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
+	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct ccp_des3_req_ctx *rctx = ablkcipher_request_ctx(req);
+
+	if (ret)
+		return ret;
+
+	if (ctx->u.des3.mode != CCP_DES3_MODE_ECB)
+		memcpy(req->info, rctx->iv, DES3_EDE_BLOCK_SIZE);
+
+	return 0;
+}
+
+static int ccp_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+		unsigned int key_len)
+{
+	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ablkcipher_tfm(tfm));
+	struct ccp_crypto_ablkcipher_alg *alg =
+		ccp_crypto_ablkcipher_alg(crypto_ablkcipher_tfm(tfm));
+	u32 *flags = &tfm->base.crt_flags;
+
+
+	/* From des_generic.c:
+	 *
+	 * RFC2451:
+	 *   If the first two or last two independent 64-bit keys are
+	 *   equal (k1 == k2 or k2 == k3), then the DES3 operation is simply the
+	 *   same as DES.  Implementers MUST reject keys that exhibit this
+	 *   property.
+	 */
+	const u32 *K = (const u32 *)key;
+
+	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
+		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
+		     (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	/* It's not clear that there is any support for a keysize of 112.
+	 * If needed, the caller should make K1 == K3
+	 */
+	ctx->u.des3.type = CCP_DES3_TYPE_168;
+	ctx->u.des3.mode = alg->mode;
+	ctx->u.des3.key_len = key_len;
+
+	memcpy(ctx->u.des3.key, key, key_len);
+	sg_init_one(&ctx->u.des3.key_sg, ctx->u.des3.key, key_len);
+
+	return 0;
+}
+
+static int ccp_des3_crypt(struct ablkcipher_request *req, bool encrypt)
+{
+	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct ccp_des3_req_ctx *rctx = ablkcipher_request_ctx(req);
+	struct scatterlist *iv_sg = NULL;
+	unsigned int iv_len = 0;
+	int ret;
+
+	if (!ctx->u.des3.key_len)
+		return -EINVAL;
+
+	if (((ctx->u.des3.mode == CCP_DES3_MODE_ECB) ||
+	     (ctx->u.des3.mode == CCP_DES3_MODE_CBC)) &&
+	    (req->nbytes & (DES3_EDE_BLOCK_SIZE - 1)))
+		return -EINVAL;
+
+	if (ctx->u.des3.mode != CCP_DES3_MODE_ECB) {
+		if (!req->info)
+			return -EINVAL;
+
+		memcpy(rctx->iv, req->info, DES3_EDE_BLOCK_SIZE);
+		iv_sg = &rctx->iv_sg;
+		iv_len = DES3_EDE_BLOCK_SIZE;
+		sg_init_one(iv_sg, rctx->iv, iv_len);
+	}
+
+	memset(&rctx->cmd, 0, sizeof(rctx->cmd));
+	INIT_LIST_HEAD(&rctx->cmd.entry);
+	rctx->cmd.engine = CCP_ENGINE_DES3;
+	rctx->cmd.u.des3.type = ctx->u.des3.type;
+	rctx->cmd.u.des3.mode = ctx->u.des3.mode;
+	rctx->cmd.u.des3.action = (encrypt)
+				  ? CCP_DES3_ACTION_ENCRYPT
+				  : CCP_DES3_ACTION_DECRYPT;
+	rctx->cmd.u.des3.key = &ctx->u.des3.key_sg;
+	rctx->cmd.u.des3.key_len = ctx->u.des3.key_len;
+	rctx->cmd.u.des3.iv = iv_sg;
+	rctx->cmd.u.des3.iv_len = iv_len;
+	rctx->cmd.u.des3.src = req->src;
+	rctx->cmd.u.des3.src_len = req->nbytes;
+	rctx->cmd.u.des3.dst = req->dst;
+
+	ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd);
+
+	return ret;
+}
+
+static int ccp_des3_encrypt(struct ablkcipher_request *req)
+{
+	return ccp_des3_crypt(req, true);
+}
+
+static int ccp_des3_decrypt(struct ablkcipher_request *req)
+{
+	return ccp_des3_crypt(req, false);
+}
+
+static int ccp_des3_cra_init(struct crypto_tfm *tfm)
+{
+	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->complete = ccp_des3_complete;
+	ctx->u.des3.key_len = 0;
+
+	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_des3_req_ctx);
+
+	return 0;
+}
+
+static void ccp_des3_cra_exit(struct crypto_tfm *tfm)
+{
+}
+
+static struct crypto_alg ccp_des3_defaults = {
+	.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
+		CRYPTO_ALG_ASYNC |
+		CRYPTO_ALG_KERN_DRIVER_ONLY |
+		CRYPTO_ALG_NEED_FALLBACK,
+	.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize	= sizeof(struct ccp_ctx),
+	.cra_priority	= CCP_CRA_PRIORITY,
+	.cra_type	= &crypto_ablkcipher_type,
+	.cra_init	= ccp_des3_cra_init,
+	.cra_exit	= ccp_des3_cra_exit,
+	.cra_module	= THIS_MODULE,
+	.cra_ablkcipher	= {
+		.setkey		= ccp_des3_setkey,
+		.encrypt	= ccp_des3_encrypt,
+		.decrypt	= ccp_des3_decrypt,
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+	},
+};
+
+struct ccp_des3_def {
+	enum ccp_des3_mode mode;
+	unsigned int version;
+	const char *name;
+	const char *driver_name;
+	unsigned int blocksize;
+	unsigned int ivsize;
+	struct crypto_alg *alg_defaults;
+};
+
+static struct ccp_des3_def des3_algs[] = {
+	{
+		.mode		= CCP_DES3_MODE_ECB,
+		.version	= CCP_VERSION(5, 0),
+		.name		= "ecb(des3_ede)",
+		.driver_name	= "ecb-des3-ccp",
+		.blocksize	= DES3_EDE_BLOCK_SIZE,
+		.ivsize		= 0,
+		.alg_defaults	= &ccp_des3_defaults,
+	},
+	{
+		.mode		= CCP_DES3_MODE_CBC,
+		.version	= CCP_VERSION(5, 0),
+		.name		= "cbc(des3_ede)",
+		.driver_name	= "cbc-des3-ccp",
+		.blocksize	= DES3_EDE_BLOCK_SIZE,
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.alg_defaults	= &ccp_des3_defaults,
+	},
+};
+
+static int ccp_register_des3_alg(struct list_head *head,
+				 const struct ccp_des3_def *def)
+{
+	struct ccp_crypto_ablkcipher_alg *ccp_alg;
+	struct crypto_alg *alg;
+	int ret;
+
+	ccp_alg = kzalloc(sizeof(*ccp_alg), GFP_KERNEL);
+	if (!ccp_alg)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ccp_alg->entry);
+
+	ccp_alg->mode = def->mode;
+
+	/* Copy the defaults and override as necessary */
+	alg = &ccp_alg->alg;
+	*alg = *def->alg_defaults;
+	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+			def->driver_name);
+	alg->cra_blocksize = def->blocksize;
+	alg->cra_ablkcipher.ivsize = def->ivsize;
+
+	ret = crypto_register_alg(alg);
+	if (ret) {
+		pr_err("%s ablkcipher algorithm registration error (%d)\n",
+				alg->cra_name, ret);
+		kfree(ccp_alg);
+		return ret;
+	}
+
+	list_add(&ccp_alg->entry, head);
+
+	return 0;
+}
+
+int ccp_register_des3_algs(struct list_head *head)
+{
+	int i, ret;
+	unsigned int ccpversion = ccp_version();
+
+	for (i = 0; i < ARRAY_SIZE(des3_algs); i++) {
+		if (des3_algs[i].version > ccpversion)
+			continue;
+		ret = ccp_register_des3_alg(head, &des3_algs[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/ccp/ccp-crypto-main.c b/drivers/crypto/ccp/ccp-crypto-main.c
index e0380e59c361..8dccbddabef1 100644
--- a/drivers/crypto/ccp/ccp-crypto-main.c
+++ b/drivers/crypto/ccp/ccp-crypto-main.c
@@ -33,9 +33,14 @@ static unsigned int sha_disable;
 module_param(sha_disable, uint, 0444);
 MODULE_PARM_DESC(sha_disable, "Disable use of SHA - any non-zero value");
 
+static unsigned int des3_disable;
+module_param(des3_disable, uint, 0444);
+MODULE_PARM_DESC(des3_disable, "Disable use of 3DES - any non-zero value");
+
 /* List heads for the supported algorithms */
 static LIST_HEAD(hash_algs);
 static LIST_HEAD(cipher_algs);
+static LIST_HEAD(aead_algs);
 
 /* For any tfm, requests for that tfm must be returned on the order
  * received.  With multiple queues available, the CCP can process more
@@ -335,6 +340,16 @@ static int ccp_register_algs(void)
 		ret = ccp_register_aes_xts_algs(&cipher_algs);
 		if (ret)
 			return ret;
+
+		ret = ccp_register_aes_aeads(&aead_algs);
+		if (ret)
+			return ret;
+	}
+
+	if (!des3_disable) {
+		ret = ccp_register_des3_algs(&cipher_algs);
+		if (ret)
+			return ret;
 	}
 
 	if (!sha_disable) {
@@ -350,6 +365,7 @@ static void ccp_unregister_algs(void)
 {
 	struct ccp_crypto_ahash_alg *ahash_alg, *ahash_tmp;
 	struct ccp_crypto_ablkcipher_alg *ablk_alg, *ablk_tmp;
+	struct ccp_crypto_aead *aead_alg, *aead_tmp;
 
 	list_for_each_entry_safe(ahash_alg, ahash_tmp, &hash_algs, entry) {
 		crypto_unregister_ahash(&ahash_alg->alg);
@@ -362,6 +378,12 @@ static void ccp_unregister_algs(void)
 		list_del(&ablk_alg->entry);
 		kfree(ablk_alg);
 	}
+
+	list_for_each_entry_safe(aead_alg, aead_tmp, &aead_algs, entry) {
+		crypto_unregister_aead(&aead_alg->alg);
+		list_del(&aead_alg->entry);
+		kfree(aead_alg);
+	}
 }
 
 static int ccp_crypto_init(void)
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 84a652be4274..6b46eea94932 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -146,6 +146,12 @@ static int ccp_do_sha_update(struct ahash_request *req, unsigned int nbytes,
 	case CCP_SHA_TYPE_256:
 		rctx->cmd.u.sha.ctx_len = SHA256_DIGEST_SIZE;
 		break;
+	case CCP_SHA_TYPE_384:
+		rctx->cmd.u.sha.ctx_len = SHA384_DIGEST_SIZE;
+		break;
+	case CCP_SHA_TYPE_512:
+		rctx->cmd.u.sha.ctx_len = SHA512_DIGEST_SIZE;
+		break;
 	default:
 		/* Should never get here */
 		break;
@@ -393,6 +399,22 @@ static struct ccp_sha_def sha_algs[] = {
 		.digest_size	= SHA256_DIGEST_SIZE,
 		.block_size	= SHA256_BLOCK_SIZE,
 	},
+	{
+		.version	= CCP_VERSION(5, 0),
+		.name		= "sha384",
+		.drv_name	= "sha384-ccp",
+		.type		= CCP_SHA_TYPE_384,
+		.digest_size	= SHA384_DIGEST_SIZE,
+		.block_size	= SHA384_BLOCK_SIZE,
+	},
+	{
+		.version	= CCP_VERSION(5, 0),
+		.name		= "sha512",
+		.drv_name	= "sha512-ccp",
+		.type		= CCP_SHA_TYPE_512,
+		.digest_size	= SHA512_DIGEST_SIZE,
+		.block_size	= SHA512_BLOCK_SIZE,
+	},
 };
 
 static int ccp_register_hmac_alg(struct list_head *head,
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index 8335b32e815e..dd5bf15f06e5 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -19,10 +19,14 @@
 #include <linux/ccp.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/aead.h>
+#include <crypto/aead.h>
 #include <crypto/ctr.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
 
+#define	CCP_LOG_LEVEL	KERN_INFO
+
 #define CCP_CRA_PRIORITY	300
 
 struct ccp_crypto_ablkcipher_alg {
@@ -33,6 +37,14 @@ struct ccp_crypto_ablkcipher_alg {
 	struct crypto_alg alg;
 };
 
+struct ccp_crypto_aead {
+	struct list_head entry;
+
+	u32 mode;
+
+	struct aead_alg alg;
+};
+
 struct ccp_crypto_ahash_alg {
 	struct list_head entry;
 
@@ -95,6 +107,9 @@ struct ccp_aes_req_ctx {
 	struct scatterlist iv_sg;
 	u8 iv[AES_BLOCK_SIZE];
 
+	struct scatterlist tag_sg;
+	u8 tag[AES_BLOCK_SIZE];
+
 	/* Fields used for RFC3686 requests */
 	u8 *rfc3686_info;
 	u8 rfc3686_iv[AES_BLOCK_SIZE];
@@ -137,9 +152,29 @@ struct ccp_aes_cmac_exp_ctx {
 	u8 buf[AES_BLOCK_SIZE];
 };
 
-/***** SHA related defines *****/
-#define MAX_SHA_CONTEXT_SIZE	SHA256_DIGEST_SIZE
-#define MAX_SHA_BLOCK_SIZE	SHA256_BLOCK_SIZE
+/***** 3DES related defines *****/
+struct ccp_des3_ctx {
+	enum ccp_engine engine;
+	enum ccp_des3_type type;
+	enum ccp_des3_mode mode;
+
+	struct scatterlist key_sg;
+	unsigned int key_len;
+	u8 key[AES_MAX_KEY_SIZE];
+};
+
+struct ccp_des3_req_ctx {
+	struct scatterlist iv_sg;
+	u8 iv[AES_BLOCK_SIZE];
+
+	struct ccp_cmd cmd;
+};
+
+/* SHA-related defines
+ * These values must be large enough to accommodate any variant
+ */
+#define MAX_SHA_CONTEXT_SIZE	SHA512_DIGEST_SIZE
+#define MAX_SHA_BLOCK_SIZE	SHA512_BLOCK_SIZE
 
 struct ccp_sha_ctx {
 	struct scatterlist opad_sg;
@@ -199,6 +234,7 @@ struct ccp_ctx {
 	union {
 		struct ccp_aes_ctx aes;
 		struct ccp_sha_ctx sha;
+		struct ccp_des3_ctx des3;
 	} u;
 };
 
@@ -210,6 +246,8 @@ struct scatterlist *ccp_crypto_sg_table_add(struct sg_table *table,
 int ccp_register_aes_algs(struct list_head *head);
 int ccp_register_aes_cmac_algs(struct list_head *head);
 int ccp_register_aes_xts_algs(struct list_head *head);
+int ccp_register_aes_aeads(struct list_head *head);
 int ccp_register_sha_algs(struct list_head *head);
+int ccp_register_des3_algs(struct list_head *head);
 
 #endif
diff --git a/drivers/crypto/ccp/ccp-dev-v3.c b/drivers/crypto/ccp/ccp-dev-v3.c
index 7bc09989e18a..367c2e30656f 100644
--- a/drivers/crypto/ccp/ccp-dev-v3.c
+++ b/drivers/crypto/ccp/ccp-dev-v3.c
@@ -315,17 +315,73 @@ static int ccp_perform_ecc(struct ccp_op *op)
 	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
 }
 
+static void ccp_disable_queue_interrupts(struct ccp_device *ccp)
+{
+	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+}
+
+static void ccp_enable_queue_interrupts(struct ccp_device *ccp)
+{
+	iowrite32(ccp->qim, ccp->io_regs + IRQ_MASK_REG);
+}
+
+static void ccp_irq_bh(unsigned long data)
+{
+	struct ccp_device *ccp = (struct ccp_device *)data;
+	struct ccp_cmd_queue *cmd_q;
+	u32 q_int, status;
+	unsigned int i;
+
+	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
+
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
+		if (q_int) {
+			cmd_q->int_status = status;
+			cmd_q->q_status = ioread32(cmd_q->reg_status);
+			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
+
+			/* On error, only save the first error value */
+			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
+				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
+
+			cmd_q->int_rcvd = 1;
+
+			/* Acknowledge the interrupt and wake the kthread */
+			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
+			wake_up_interruptible(&cmd_q->int_queue);
+		}
+	}
+	ccp_enable_queue_interrupts(ccp);
+}
+
+static irqreturn_t ccp_irq_handler(int irq, void *data)
+{
+	struct device *dev = data;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+
+	ccp_disable_queue_interrupts(ccp);
+	if (ccp->use_tasklet)
+		tasklet_schedule(&ccp->irq_tasklet);
+	else
+		ccp_irq_bh((unsigned long)ccp);
+
+	return IRQ_HANDLED;
+}
+
 static int ccp_init(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
 	struct ccp_cmd_queue *cmd_q;
 	struct dma_pool *dma_pool;
 	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
-	unsigned int qmr, qim, i;
+	unsigned int qmr, i;
 	int ret;
 
 	/* Find available queues */
-	qim = 0;
+	ccp->qim = 0;
 	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
 	for (i = 0; i < MAX_HW_QUEUES; i++) {
 		if (!(qmr & (1 << i)))
@@ -370,7 +426,7 @@ static int ccp_init(struct ccp_device *ccp)
 		init_waitqueue_head(&cmd_q->int_queue);
 
 		/* Build queue interrupt mask (two interrupts per queue) */
-		qim |= cmd_q->int_ok | cmd_q->int_err;
+		ccp->qim |= cmd_q->int_ok | cmd_q->int_err;
 
 #ifdef CONFIG_ARM64
 		/* For arm64 set the recommended queue cache settings */
@@ -388,14 +444,14 @@ static int ccp_init(struct ccp_device *ccp)
 	dev_notice(dev, "%u command queues available\n", ccp->cmd_q_count);
 
 	/* Disable and clear interrupts until ready */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+	ccp_disable_queue_interrupts(ccp);
 	for (i = 0; i < ccp->cmd_q_count; i++) {
 		cmd_q = &ccp->cmd_q[i];
 
 		ioread32(cmd_q->reg_int_status);
 		ioread32(cmd_q->reg_status);
 	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
+	iowrite32(ccp->qim, ccp->io_regs + IRQ_STATUS_REG);
 
 	/* Request an irq */
 	ret = ccp->get_irq(ccp);
@@ -404,6 +460,11 @@ static int ccp_init(struct ccp_device *ccp)
 		goto e_pool;
 	}
 
+	/* Initialize the ISR tasklet? */
+	if (ccp->use_tasklet)
+		tasklet_init(&ccp->irq_tasklet, ccp_irq_bh,
+			     (unsigned long)ccp);
+
 	dev_dbg(dev, "Starting threads...\n");
 	/* Create a kthread for each queue */
 	for (i = 0; i < ccp->cmd_q_count; i++) {
@@ -426,7 +487,7 @@ static int ccp_init(struct ccp_device *ccp)
 
 	dev_dbg(dev, "Enabling interrupts...\n");
 	/* Enable interrupts */
-	iowrite32(qim, ccp->io_regs + IRQ_MASK_REG);
+	ccp_enable_queue_interrupts(ccp);
 
 	dev_dbg(dev, "Registering device...\n");
 	ccp_add_device(ccp);
@@ -463,7 +524,7 @@ static void ccp_destroy(struct ccp_device *ccp)
 {
 	struct ccp_cmd_queue *cmd_q;
 	struct ccp_cmd *cmd;
-	unsigned int qim, i;
+	unsigned int i;
 
 	/* Unregister the DMA engine */
 	ccp_dmaengine_unregister(ccp);
@@ -474,22 +535,15 @@ static void ccp_destroy(struct ccp_device *ccp)
 	/* Remove this device from the list of available units */
 	ccp_del_device(ccp);
 
-	/* Build queue interrupt mask (two interrupt masks per queue) */
-	qim = 0;
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-		qim |= cmd_q->int_ok | cmd_q->int_err;
-	}
-
 	/* Disable and clear interrupts */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+	ccp_disable_queue_interrupts(ccp);
 	for (i = 0; i < ccp->cmd_q_count; i++) {
 		cmd_q = &ccp->cmd_q[i];
 
 		ioread32(cmd_q->reg_int_status);
 		ioread32(cmd_q->reg_status);
 	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
+	iowrite32(ccp->qim, ccp->io_regs + IRQ_STATUS_REG);
 
 	/* Stop the queue kthreads */
 	for (i = 0; i < ccp->cmd_q_count; i++)
@@ -516,43 +570,10 @@ static void ccp_destroy(struct ccp_device *ccp)
 	}
 }
 
-static irqreturn_t ccp_irq_handler(int irq, void *data)
-{
-	struct device *dev = data;
-	struct ccp_device *ccp = dev_get_drvdata(dev);
-	struct ccp_cmd_queue *cmd_q;
-	u32 q_int, status;
-	unsigned int i;
-
-	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
-
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
-		if (q_int) {
-			cmd_q->int_status = status;
-			cmd_q->q_status = ioread32(cmd_q->reg_status);
-			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
-
-			/* On error, only save the first error value */
-			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
-				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
-
-			cmd_q->int_rcvd = 1;
-
-			/* Acknowledge the interrupt and wake the kthread */
-			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
-			wake_up_interruptible(&cmd_q->int_queue);
-		}
-	}
-
-	return IRQ_HANDLED;
-}
-
 static const struct ccp_actions ccp3_actions = {
 	.aes = ccp_perform_aes,
 	.xts_aes = ccp_perform_xts_aes,
+	.des3 = NULL,
 	.sha = ccp_perform_sha,
 	.rsa = ccp_perform_rsa,
 	.passthru = ccp_perform_passthru,
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index 41cc853f8569..ccbe32d5dd1c 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -108,6 +108,12 @@ union ccp_function {
 		u16 type:2;
 	} aes_xts;
 	struct {
+		u16 size:7;
+		u16 encrypt:1;
+		u16 mode:5;
+		u16 type:2;
+	} des3;
+	struct {
 		u16 rsvd1:10;
 		u16 type:4;
 		u16 rsvd2:1;
@@ -139,6 +145,10 @@ union ccp_function {
 #define	CCP_AES_TYPE(p)		((p)->aes.type)
 #define	CCP_XTS_SIZE(p)		((p)->aes_xts.size)
 #define	CCP_XTS_ENCRYPT(p)	((p)->aes_xts.encrypt)
+#define	CCP_DES3_SIZE(p)	((p)->des3.size)
+#define	CCP_DES3_ENCRYPT(p)	((p)->des3.encrypt)
+#define	CCP_DES3_MODE(p)	((p)->des3.mode)
+#define	CCP_DES3_TYPE(p)	((p)->des3.type)
 #define	CCP_SHA_TYPE(p)		((p)->sha.type)
 #define	CCP_RSA_SIZE(p)		((p)->rsa.size)
 #define	CCP_PT_BYTESWAP(p)	((p)->pt.byteswap)
@@ -388,6 +398,47 @@ static int ccp5_perform_sha(struct ccp_op *op)
 	return ccp5_do_cmd(&desc, op->cmd_q);
 }
 
+static int ccp5_perform_des3(struct ccp_op *op)
+{
+	struct ccp5_desc desc;
+	union ccp_function function;
+	u32 key_addr = op->sb_key * LSB_ITEM_SIZE;
+
+	/* Zero out all the fields of the command desc */
+	memset(&desc, 0, sizeof(struct ccp5_desc));
+
+	CCP5_CMD_ENGINE(&desc) = CCP_ENGINE_DES3;
+
+	CCP5_CMD_SOC(&desc) = op->soc;
+	CCP5_CMD_IOC(&desc) = 1;
+	CCP5_CMD_INIT(&desc) = op->init;
+	CCP5_CMD_EOM(&desc) = op->eom;
+	CCP5_CMD_PROT(&desc) = 0;
+
+	function.raw = 0;
+	CCP_DES3_ENCRYPT(&function) = op->u.des3.action;
+	CCP_DES3_MODE(&function) = op->u.des3.mode;
+	CCP_DES3_TYPE(&function) = op->u.des3.type;
+	CCP5_CMD_FUNCTION(&desc) = function.raw;
+
+	CCP5_CMD_LEN(&desc) = op->src.u.dma.length;
+
+	CCP5_CMD_SRC_LO(&desc) = ccp_addr_lo(&op->src.u.dma);
+	CCP5_CMD_SRC_HI(&desc) = ccp_addr_hi(&op->src.u.dma);
+	CCP5_CMD_SRC_MEM(&desc) = CCP_MEMTYPE_SYSTEM;
+
+	CCP5_CMD_DST_LO(&desc) = ccp_addr_lo(&op->dst.u.dma);
+	CCP5_CMD_DST_HI(&desc) = ccp_addr_hi(&op->dst.u.dma);
+	CCP5_CMD_DST_MEM(&desc) = CCP_MEMTYPE_SYSTEM;
+
+	CCP5_CMD_KEY_LO(&desc) = lower_32_bits(key_addr);
+	CCP5_CMD_KEY_HI(&desc) = 0;
+	CCP5_CMD_KEY_MEM(&desc) = CCP_MEMTYPE_SB;
+	CCP5_CMD_LSB_ID(&desc) = op->sb_ctx;
+
+	return ccp5_do_cmd(&desc, op->cmd_q);
+}
+
 static int ccp5_perform_rsa(struct ccp_op *op)
 {
 	struct ccp5_desc desc;
@@ -435,6 +486,7 @@ static int ccp5_perform_passthru(struct ccp_op *op)
 	struct ccp_dma_info *saddr = &op->src.u.dma;
 	struct ccp_dma_info *daddr = &op->dst.u.dma;
 
+
 	memset(&desc, 0, Q_DESC_SIZE);
 
 	CCP5_CMD_ENGINE(&desc) = CCP_ENGINE_PASSTHRU;
@@ -653,6 +705,65 @@ static int ccp_assign_lsbs(struct ccp_device *ccp)
 	return rc;
 }
 
+static void ccp5_disable_queue_interrupts(struct ccp_device *ccp)
+{
+	unsigned int i;
+
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		iowrite32(0x0, ccp->cmd_q[i].reg_int_enable);
+}
+
+static void ccp5_enable_queue_interrupts(struct ccp_device *ccp)
+{
+	unsigned int i;
+
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		iowrite32(SUPPORTED_INTERRUPTS, ccp->cmd_q[i].reg_int_enable);
+}
+
+static void ccp5_irq_bh(unsigned long data)
+{
+	struct ccp_device *ccp = (struct ccp_device *)data;
+	u32 status;
+	unsigned int i;
+
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		struct ccp_cmd_queue *cmd_q = &ccp->cmd_q[i];
+
+		status = ioread32(cmd_q->reg_interrupt_status);
+
+		if (status) {
+			cmd_q->int_status = status;
+			cmd_q->q_status = ioread32(cmd_q->reg_status);
+			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
+
+			/* On error, only save the first error value */
+			if ((status & INT_ERROR) && !cmd_q->cmd_error)
+				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
+
+			cmd_q->int_rcvd = 1;
+
+			/* Acknowledge the interrupt and wake the kthread */
+			iowrite32(status, cmd_q->reg_interrupt_status);
+			wake_up_interruptible(&cmd_q->int_queue);
+		}
+	}
+	ccp5_enable_queue_interrupts(ccp);
+}
+
+static irqreturn_t ccp5_irq_handler(int irq, void *data)
+{
+	struct device *dev = data;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+
+	ccp5_disable_queue_interrupts(ccp);
+	if (ccp->use_tasklet)
+		tasklet_schedule(&ccp->irq_tasklet);
+	else
+		ccp5_irq_bh((unsigned long)ccp);
+	return IRQ_HANDLED;
+}
+
 static int ccp5_init(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
@@ -729,6 +840,7 @@ static int ccp5_init(struct ccp_device *ccp)
 
 		dev_dbg(dev, "queue #%u available\n", i);
 	}
+
 	if (ccp->cmd_q_count == 0) {
 		dev_notice(dev, "no command queues available\n");
 		ret = -EIO;
@@ -736,19 +848,18 @@ static int ccp5_init(struct ccp_device *ccp)
 	}
 
 	/* Turn off the queues and disable interrupts until ready */
+	ccp5_disable_queue_interrupts(ccp);
 	for (i = 0; i < ccp->cmd_q_count; i++) {
 		cmd_q = &ccp->cmd_q[i];
 
 		cmd_q->qcontrol = 0; /* Start with nothing */
 		iowrite32(cmd_q->qcontrol, cmd_q->reg_control);
 
-		/* Disable the interrupts */
-		iowrite32(0x00, cmd_q->reg_int_enable);
 		ioread32(cmd_q->reg_int_status);
 		ioread32(cmd_q->reg_status);
 
-		/* Clear the interrupts */
-		iowrite32(ALL_INTERRUPTS, cmd_q->reg_interrupt_status);
+		/* Clear the interrupt status */
+		iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_interrupt_status);
 	}
 
 	dev_dbg(dev, "Requesting an IRQ...\n");
@@ -758,6 +869,10 @@ static int ccp5_init(struct ccp_device *ccp)
 		dev_err(dev, "unable to allocate an IRQ\n");
 		goto e_pool;
 	}
+	/* Initialize the ISR tasklet */
+	if (ccp->use_tasklet)
+		tasklet_init(&ccp->irq_tasklet, ccp5_irq_bh,
+			     (unsigned long)ccp);
 
 	dev_dbg(dev, "Loading LSB map...\n");
 	/* Copy the private LSB mask to the public registers */
@@ -826,11 +941,7 @@ static int ccp5_init(struct ccp_device *ccp)
 	}
 
 	dev_dbg(dev, "Enabling interrupts...\n");
-	/* Enable interrupts */
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-		iowrite32(ALL_INTERRUPTS, cmd_q->reg_int_enable);
-	}
+	ccp5_enable_queue_interrupts(ccp);
 
 	dev_dbg(dev, "Registering device...\n");
 	/* Put this on the unit list to make it available */
@@ -882,17 +993,15 @@ static void ccp5_destroy(struct ccp_device *ccp)
 	ccp_del_device(ccp);
 
 	/* Disable and clear interrupts */
+	ccp5_disable_queue_interrupts(ccp);
 	for (i = 0; i < ccp->cmd_q_count; i++) {
 		cmd_q = &ccp->cmd_q[i];
 
 		/* Turn off the run bit */
 		iowrite32(cmd_q->qcontrol & ~CMD5_Q_RUN, cmd_q->reg_control);
 
-		/* Disable the interrupts */
-		iowrite32(ALL_INTERRUPTS, cmd_q->reg_interrupt_status);
-
 		/* Clear the interrupt status */
-		iowrite32(0x00, cmd_q->reg_int_enable);
+		iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_interrupt_status);
 		ioread32(cmd_q->reg_int_status);
 		ioread32(cmd_q->reg_status);
 	}
@@ -925,38 +1034,6 @@ static void ccp5_destroy(struct ccp_device *ccp)
 	}
 }
 
-static irqreturn_t ccp5_irq_handler(int irq, void *data)
-{
-	struct device *dev = data;
-	struct ccp_device *ccp = dev_get_drvdata(dev);
-	u32 status;
-	unsigned int i;
-
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		struct ccp_cmd_queue *cmd_q = &ccp->cmd_q[i];
-
-		status = ioread32(cmd_q->reg_interrupt_status);
-
-		if (status) {
-			cmd_q->int_status = status;
-			cmd_q->q_status = ioread32(cmd_q->reg_status);
-			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
-
-			/* On error, only save the first error value */
-			if ((status & INT_ERROR) && !cmd_q->cmd_error)
-				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
-
-			cmd_q->int_rcvd = 1;
-
-			/* Acknowledge the interrupt and wake the kthread */
-			iowrite32(ALL_INTERRUPTS, cmd_q->reg_interrupt_status);
-			wake_up_interruptible(&cmd_q->int_queue);
-		}
-	}
-
-	return IRQ_HANDLED;
-}
-
 static void ccp5_config(struct ccp_device *ccp)
 {
 	/* Public side */
@@ -994,6 +1071,7 @@ static const struct ccp_actions ccp5_actions = {
 	.aes = ccp5_perform_aes,
 	.xts_aes = ccp5_perform_xts_aes,
 	.sha = ccp5_perform_sha,
+	.des3 = ccp5_perform_des3,
 	.rsa = ccp5_perform_rsa,
 	.passthru = ccp5_perform_passthru,
 	.ecc = ccp5_perform_ecc,
@@ -1015,6 +1093,7 @@ const struct ccp_vdata ccpv5a = {
 
 const struct ccp_vdata ccpv5b = {
 	.version = CCP_VERSION(5, 0),
+	.dma_chan_attr = DMA_PRIVATE,
 	.setup = ccp5other_config,
 	.perform = &ccp5_actions,
 	.bar = 2,
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 511ab042b5e7..92d1c6959f08 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -283,11 +283,14 @@ EXPORT_SYMBOL_GPL(ccp_version);
  */
 int ccp_enqueue_cmd(struct ccp_cmd *cmd)
 {
-	struct ccp_device *ccp = ccp_get_device();
+	struct ccp_device *ccp;
 	unsigned long flags;
 	unsigned int i;
 	int ret;
 
+	/* Some commands might need to be sent to a specific device */
+	ccp = cmd->ccp ? cmd->ccp : ccp_get_device();
+
 	if (!ccp)
 		return -ENODEV;
 
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 2b5c01fade05..0cb09d0feeaf 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -109,9 +109,8 @@
 #define INT_COMPLETION			0x1
 #define INT_ERROR			0x2
 #define INT_QUEUE_STOPPED		0x4
-#define ALL_INTERRUPTS			(INT_COMPLETION| \
-					 INT_ERROR| \
-					 INT_QUEUE_STOPPED)
+#define	INT_EMPTY_QUEUE			0x8
+#define SUPPORTED_INTERRUPTS		(INT_COMPLETION | INT_ERROR)
 
 #define LSB_REGION_WIDTH		5
 #define MAX_LSB_CNT			8
@@ -179,6 +178,10 @@
 
 /* ------------------------ General CCP Defines ------------------------ */
 
+#define	CCP_DMA_DFLT			0x0
+#define	CCP_DMA_PRIV			0x1
+#define	CCP_DMA_PUB			0x2
+
 #define CCP_DMAPOOL_MAX_SIZE		64
 #define CCP_DMAPOOL_ALIGN		BIT(5)
 
@@ -190,6 +193,9 @@
 #define CCP_XTS_AES_KEY_SB_COUNT	1
 #define CCP_XTS_AES_CTX_SB_COUNT	1
 
+#define CCP_DES3_KEY_SB_COUNT		1
+#define CCP_DES3_CTX_SB_COUNT		1
+
 #define CCP_SHA_SB_COUNT		1
 
 #define CCP_RSA_MAX_WIDTH		4096
@@ -333,7 +339,10 @@ struct ccp_device {
 	void *dev_specific;
 	int (*get_irq)(struct ccp_device *ccp);
 	void (*free_irq)(struct ccp_device *ccp);
+	unsigned int qim;
 	unsigned int irq;
+	bool use_tasklet;
+	struct tasklet_struct irq_tasklet;
 
 	/* I/O area used for device communication. The register mapping
 	 * starts at an offset into the mapped bar.
@@ -420,33 +429,33 @@ enum ccp_memtype {
 };
 #define	CCP_MEMTYPE_LSB	CCP_MEMTYPE_KSB
 
+
 struct ccp_dma_info {
 	dma_addr_t address;
 	unsigned int offset;
 	unsigned int length;
 	enum dma_data_direction dir;
-};
+} __packed __aligned(4);
 
 struct ccp_dm_workarea {
 	struct device *dev;
 	struct dma_pool *dma_pool;
-	unsigned int length;
 
 	u8 *address;
 	struct ccp_dma_info dma;
+	unsigned int length;
 };
 
 struct ccp_sg_workarea {
 	struct scatterlist *sg;
 	int nents;
+	unsigned int sg_used;
 
 	struct scatterlist *dma_sg;
 	struct device *dma_dev;
 	unsigned int dma_count;
 	enum dma_data_direction dma_dir;
 
-	unsigned int sg_used;
-
 	u64 bytes_left;
 };
 
@@ -475,6 +484,12 @@ struct ccp_xts_aes_op {
 	enum ccp_xts_aes_unit_size unit_size;
 };
 
+struct ccp_des3_op {
+	enum ccp_des3_type type;
+	enum ccp_des3_mode mode;
+	enum ccp_des3_action action;
+};
+
 struct ccp_sha_op {
 	enum ccp_sha_type type;
 	u64 msg_bits;
@@ -512,6 +527,7 @@ struct ccp_op {
 	union {
 		struct ccp_aes_op aes;
 		struct ccp_xts_aes_op xts;
+		struct ccp_des3_op des3;
 		struct ccp_sha_op sha;
 		struct ccp_rsa_op rsa;
 		struct ccp_passthru_op passthru;
@@ -620,13 +636,13 @@ void ccp_dmaengine_unregister(struct ccp_device *ccp);
 struct ccp_actions {
 	int (*aes)(struct ccp_op *);
 	int (*xts_aes)(struct ccp_op *);
+	int (*des3)(struct ccp_op *);
 	int (*sha)(struct ccp_op *);
 	int (*rsa)(struct ccp_op *);
 	int (*passthru)(struct ccp_op *);
 	int (*ecc)(struct ccp_op *);
 	u32 (*sballoc)(struct ccp_cmd_queue *, unsigned int);
-	void (*sbfree)(struct ccp_cmd_queue *, unsigned int,
-			       unsigned int);
+	void (*sbfree)(struct ccp_cmd_queue *, unsigned int, unsigned int);
 	unsigned int (*get_free_slots)(struct ccp_cmd_queue *);
 	int (*init)(struct ccp_device *);
 	void (*destroy)(struct ccp_device *);
@@ -636,6 +652,7 @@ struct ccp_actions {
 /* Structure to hold CCP version-specific values */
 struct ccp_vdata {
 	const unsigned int version;
+	const unsigned int dma_chan_attr;
 	void (*setup)(struct ccp_device *);
 	const struct ccp_actions *perform;
 	const unsigned int bar;
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index e5d9278f4019..e00be01fbf5a 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/dmaengine.h>
 #include <linux/spinlock.h>
@@ -25,6 +26,37 @@
 	(mask == 0) ? 64 : fls64(mask);	\
 })
 
+/* The CCP as a DMA provider can be configured for public or private
+ * channels. Default is specified in the vdata for the device (PCI ID).
+ * This module parameter will override for all channels on all devices:
+ *   dma_chan_attr = 0x2 to force all channels public
+ *                 = 0x1 to force all channels private
+ *                 = 0x0 to defer to the vdata setting
+ *                 = any other value: warning, revert to 0x0
+ */
+static unsigned int dma_chan_attr = CCP_DMA_DFLT;
+module_param(dma_chan_attr, uint, 0444);
+MODULE_PARM_DESC(dma_chan_attr, "Set DMA channel visibility: 0 (default) = device defaults, 1 = make private, 2 = make public");
+
+unsigned int ccp_get_dma_chan_attr(struct ccp_device *ccp)
+{
+	switch (dma_chan_attr) {
+	case CCP_DMA_DFLT:
+		return ccp->vdata->dma_chan_attr;
+
+	case CCP_DMA_PRIV:
+		return DMA_PRIVATE;
+
+	case CCP_DMA_PUB:
+		return 0;
+
+	default:
+		dev_info_once(ccp->dev, "Invalid value for dma_chan_attr: %d\n",
+			      dma_chan_attr);
+		return ccp->vdata->dma_chan_attr;
+	}
+}
+
 static void ccp_free_cmd_resources(struct ccp_device *ccp,
 				   struct list_head *list)
 {
@@ -390,6 +422,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan,
 			goto err;
 
 		ccp_cmd = &cmd->ccp_cmd;
+		ccp_cmd->ccp = chan->ccp;
 		ccp_pt = &ccp_cmd->u.passthru_nomap;
 		ccp_cmd->flags = CCP_CMD_MAY_BACKLOG;
 		ccp_cmd->flags |= CCP_CMD_PASSTHRU_NO_DMA_MAP;
@@ -674,6 +707,15 @@ int ccp_dmaengine_register(struct ccp_device *ccp)
 	dma_cap_set(DMA_SG, dma_dev->cap_mask);
 	dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask);
 
+	/* The DMA channels for this device can be set to public or private,
+	 * and overridden by the module parameter dma_chan_attr.
+	 * Default: according to the value in vdata (dma_chan_attr=0)
+	 * dma_chan_attr=0x1: all channels private (override vdata)
+	 * dma_chan_attr=0x2: all channels public (override vdata)
+	 */
+	if (ccp_get_dma_chan_attr(ccp) == DMA_PRIVATE)
+		dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
+
 	INIT_LIST_HEAD(&dma_dev->channels);
 	for (i = 0; i < ccp->cmd_q_count; i++) {
 		chan = ccp->ccp_dma_chan + i;
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index f1396c3aedac..c0dfdacbdff5 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -16,6 +16,7 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/des.h>
 #include <linux/ccp.h>
 
 #include "ccp-dev.h"
@@ -41,6 +42,20 @@ static const __be32 ccp_sha256_init[SHA256_DIGEST_SIZE / sizeof(__be32)] = {
 	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
 };
 
+static const __be64 ccp_sha384_init[SHA512_DIGEST_SIZE / sizeof(__be64)] = {
+	cpu_to_be64(SHA384_H0), cpu_to_be64(SHA384_H1),
+	cpu_to_be64(SHA384_H2), cpu_to_be64(SHA384_H3),
+	cpu_to_be64(SHA384_H4), cpu_to_be64(SHA384_H5),
+	cpu_to_be64(SHA384_H6), cpu_to_be64(SHA384_H7),
+};
+
+static const __be64 ccp_sha512_init[SHA512_DIGEST_SIZE / sizeof(__be64)] = {
+	cpu_to_be64(SHA512_H0), cpu_to_be64(SHA512_H1),
+	cpu_to_be64(SHA512_H2), cpu_to_be64(SHA512_H3),
+	cpu_to_be64(SHA512_H4), cpu_to_be64(SHA512_H5),
+	cpu_to_be64(SHA512_H6), cpu_to_be64(SHA512_H7),
+};
+
 #define	CCP_NEW_JOBID(ccp)	((ccp->vdata->version == CCP_VERSION(3, 0)) ? \
 					ccp_gen_jobid(ccp) : 0)
 
@@ -586,6 +601,255 @@ e_key:
 	return ret;
 }
 
+static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
+			       struct ccp_cmd *cmd)
+{
+	struct ccp_aes_engine *aes = &cmd->u.aes;
+	struct ccp_dm_workarea key, ctx, final_wa, tag;
+	struct ccp_data src, dst;
+	struct ccp_data aad;
+	struct ccp_op op;
+
+	unsigned long long *final;
+	unsigned int dm_offset;
+	unsigned int ilen;
+	bool in_place = true; /* Default value */
+	int ret;
+
+	struct scatterlist *p_inp, sg_inp[2];
+	struct scatterlist *p_tag, sg_tag[2];
+	struct scatterlist *p_outp, sg_outp[2];
+	struct scatterlist *p_aad;
+
+	if (!aes->iv)
+		return -EINVAL;
+
+	if (!((aes->key_len == AES_KEYSIZE_128) ||
+		(aes->key_len == AES_KEYSIZE_192) ||
+		(aes->key_len == AES_KEYSIZE_256)))
+		return -EINVAL;
+
+	if (!aes->key) /* Gotta have a key SGL */
+		return -EINVAL;
+
+	/* First, decompose the source buffer into AAD & PT,
+	 * and the destination buffer into AAD, CT & tag, or
+	 * the input into CT & tag.
+	 * It is expected that the input and output SGs will
+	 * be valid, even if the AAD and input lengths are 0.
+	 */
+	p_aad = aes->src;
+	p_inp = scatterwalk_ffwd(sg_inp, aes->src, aes->aad_len);
+	p_outp = scatterwalk_ffwd(sg_outp, aes->dst, aes->aad_len);
+	if (aes->action == CCP_AES_ACTION_ENCRYPT) {
+		ilen = aes->src_len;
+		p_tag = scatterwalk_ffwd(sg_tag, p_outp, ilen);
+	} else {
+		/* Input length for decryption includes tag */
+		ilen = aes->src_len - AES_BLOCK_SIZE;
+		p_tag = scatterwalk_ffwd(sg_tag, p_inp, ilen);
+	}
+
+	memset(&op, 0, sizeof(op));
+	op.cmd_q = cmd_q;
+	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
+	op.sb_key = cmd_q->sb_key; /* Pre-allocated */
+	op.sb_ctx = cmd_q->sb_ctx; /* Pre-allocated */
+	op.init = 1;
+	op.u.aes.type = aes->type;
+
+	/* Copy the key to the LSB */
+	ret = ccp_init_dm_workarea(&key, cmd_q,
+				   CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
+				   DMA_TO_DEVICE);
+	if (ret)
+		return ret;
+
+	dm_offset = CCP_SB_BYTES - aes->key_len;
+	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
+			     CCP_PASSTHRU_BYTESWAP_256BIT);
+	if (ret) {
+		cmd->engine_error = cmd_q->cmd_error;
+		goto e_key;
+	}
+
+	/* Copy the context (IV) to the LSB.
+	 * There is an assumption here that the IV is 96 bits in length, plus
+	 * a nonce of 32 bits. If no IV is present, use a zeroed buffer.
+	 */
+	ret = ccp_init_dm_workarea(&ctx, cmd_q,
+				   CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES,
+				   DMA_BIDIRECTIONAL);
+	if (ret)
+		goto e_key;
+
+	dm_offset = CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES - aes->iv_len;
+	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+
+	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
+			     CCP_PASSTHRU_BYTESWAP_256BIT);
+	if (ret) {
+		cmd->engine_error = cmd_q->cmd_error;
+		goto e_ctx;
+	}
+
+	op.init = 1;
+	if (aes->aad_len > 0) {
+		/* Step 1: Run a GHASH over the Additional Authenticated Data */
+		ret = ccp_init_data(&aad, cmd_q, p_aad, aes->aad_len,
+				    AES_BLOCK_SIZE,
+				    DMA_TO_DEVICE);
+		if (ret)
+			goto e_ctx;
+
+		op.u.aes.mode = CCP_AES_MODE_GHASH;
+		op.u.aes.action = CCP_AES_GHASHAAD;
+
+		while (aad.sg_wa.bytes_left) {
+			ccp_prepare_data(&aad, NULL, &op, AES_BLOCK_SIZE, true);
+
+			ret = cmd_q->ccp->vdata->perform->aes(&op);
+			if (ret) {
+				cmd->engine_error = cmd_q->cmd_error;
+				goto e_aad;
+			}
+
+			ccp_process_data(&aad, NULL, &op);
+			op.init = 0;
+		}
+	}
+
+	op.u.aes.mode = CCP_AES_MODE_GCTR;
+	op.u.aes.action = aes->action;
+
+	if (ilen > 0) {
+		/* Step 2: Run a GCTR over the plaintext */
+		in_place = (sg_virt(p_inp) == sg_virt(p_outp)) ? true : false;
+
+		ret = ccp_init_data(&src, cmd_q, p_inp, ilen,
+				    AES_BLOCK_SIZE,
+				    in_place ? DMA_BIDIRECTIONAL
+					     : DMA_TO_DEVICE);
+		if (ret)
+			goto e_ctx;
+
+		if (in_place) {
+			dst = src;
+		} else {
+			ret = ccp_init_data(&dst, cmd_q, p_outp, ilen,
+					    AES_BLOCK_SIZE, DMA_FROM_DEVICE);
+			if (ret)
+				goto e_src;
+		}
+
+		op.soc = 0;
+		op.eom = 0;
+		op.init = 1;
+		while (src.sg_wa.bytes_left) {
+			ccp_prepare_data(&src, &dst, &op, AES_BLOCK_SIZE, true);
+			if (!src.sg_wa.bytes_left) {
+				unsigned int nbytes = aes->src_len
+						      % AES_BLOCK_SIZE;
+
+				if (nbytes) {
+					op.eom = 1;
+					op.u.aes.size = (nbytes * 8) - 1;
+				}
+			}
+
+			ret = cmd_q->ccp->vdata->perform->aes(&op);
+			if (ret) {
+				cmd->engine_error = cmd_q->cmd_error;
+				goto e_dst;
+			}
+
+			ccp_process_data(&src, &dst, &op);
+			op.init = 0;
+		}
+	}
+
+	/* Step 3: Update the IV portion of the context with the original IV */
+	ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
+			       CCP_PASSTHRU_BYTESWAP_256BIT);
+	if (ret) {
+		cmd->engine_error = cmd_q->cmd_error;
+		goto e_dst;
+	}
+
+	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+
+	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
+			     CCP_PASSTHRU_BYTESWAP_256BIT);
+	if (ret) {
+		cmd->engine_error = cmd_q->cmd_error;
+		goto e_dst;
+	}
+
+	/* Step 4: Concatenate the lengths of the AAD and source, and
+	 * hash that 16 byte buffer.
+	 */
+	ret = ccp_init_dm_workarea(&final_wa, cmd_q, AES_BLOCK_SIZE,
+				   DMA_BIDIRECTIONAL);
+	if (ret)
+		goto e_dst;
+	final = (unsigned long long *) final_wa.address;
+	final[0] = cpu_to_be64(aes->aad_len * 8);
+	final[1] = cpu_to_be64(ilen * 8);
+
+	op.u.aes.mode = CCP_AES_MODE_GHASH;
+	op.u.aes.action = CCP_AES_GHASHFINAL;
+	op.src.type = CCP_MEMTYPE_SYSTEM;
+	op.src.u.dma.address = final_wa.dma.address;
+	op.src.u.dma.length = AES_BLOCK_SIZE;
+	op.dst.type = CCP_MEMTYPE_SYSTEM;
+	op.dst.u.dma.address = final_wa.dma.address;
+	op.dst.u.dma.length = AES_BLOCK_SIZE;
+	op.eom = 1;
+	op.u.aes.size = 0;
+	ret = cmd_q->ccp->vdata->perform->aes(&op);
+	if (ret)
+		goto e_dst;
+
+	if (aes->action == CCP_AES_ACTION_ENCRYPT) {
+		/* Put the ciphered tag after the ciphertext. */
+		ccp_get_dm_area(&final_wa, 0, p_tag, 0, AES_BLOCK_SIZE);
+	} else {
+		/* Does this ciphered tag match the input? */
+		ret = ccp_init_dm_workarea(&tag, cmd_q, AES_BLOCK_SIZE,
+					   DMA_BIDIRECTIONAL);
+		if (ret)
+			goto e_tag;
+		ccp_set_dm_area(&tag, 0, p_tag, 0, AES_BLOCK_SIZE);
+
+		ret = memcmp(tag.address, final_wa.address, AES_BLOCK_SIZE);
+		ccp_dm_free(&tag);
+	}
+
+e_tag:
+	ccp_dm_free(&final_wa);
+
+e_dst:
+	if (aes->src_len && !in_place)
+		ccp_free_data(&dst, cmd_q);
+
+e_src:
+	if (aes->src_len)
+		ccp_free_data(&src, cmd_q);
+
+e_aad:
+	if (aes->aad_len)
+		ccp_free_data(&aad, cmd_q);
+
+e_ctx:
+	ccp_dm_free(&ctx);
+
+e_key:
+	ccp_dm_free(&key);
+
+	return ret;
+}
+
 static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 {
 	struct ccp_aes_engine *aes = &cmd->u.aes;
@@ -599,6 +863,9 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	if (aes->mode == CCP_AES_MODE_CMAC)
 		return ccp_run_aes_cmac_cmd(cmd_q, cmd);
 
+	if (aes->mode == CCP_AES_MODE_GCM)
+		return ccp_run_aes_gcm_cmd(cmd_q, cmd);
+
 	if (!((aes->key_len == AES_KEYSIZE_128) ||
 	      (aes->key_len == AES_KEYSIZE_192) ||
 	      (aes->key_len == AES_KEYSIZE_256)))
@@ -925,6 +1192,200 @@ e_key:
 	return ret;
 }
 
+static int ccp_run_des3_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
+{
+	struct ccp_des3_engine *des3 = &cmd->u.des3;
+
+	struct ccp_dm_workarea key, ctx;
+	struct ccp_data src, dst;
+	struct ccp_op op;
+	unsigned int dm_offset;
+	unsigned int len_singlekey;
+	bool in_place = false;
+	int ret;
+
+	/* Error checks */
+	if (!cmd_q->ccp->vdata->perform->des3)
+		return -EINVAL;
+
+	if (des3->key_len != DES3_EDE_KEY_SIZE)
+		return -EINVAL;
+
+	if (((des3->mode == CCP_DES3_MODE_ECB) ||
+		(des3->mode == CCP_DES3_MODE_CBC)) &&
+		(des3->src_len & (DES3_EDE_BLOCK_SIZE - 1)))
+		return -EINVAL;
+
+	if (!des3->key || !des3->src || !des3->dst)
+		return -EINVAL;
+
+	if (des3->mode != CCP_DES3_MODE_ECB) {
+		if (des3->iv_len != DES3_EDE_BLOCK_SIZE)
+			return -EINVAL;
+
+		if (!des3->iv)
+			return -EINVAL;
+	}
+
+	ret = -EIO;
+	/* Zero out all the fields of the command desc */
+	memset(&op, 0, sizeof(op));
+
+	/* Set up the Function field */
+	op.cmd_q = cmd_q;
+	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
+	op.sb_key = cmd_q->sb_key;
+
+	op.init = (des3->mode == CCP_DES3_MODE_ECB) ? 0 : 1;
+	op.u.des3.type = des3->type;
+	op.u.des3.mode = des3->mode;
+	op.u.des3.action = des3->action;
+
+	/*
+	 * All supported key sizes fit in a single (32-byte) KSB entry and
+	 * (like AES) must be in little endian format. Use the 256-bit byte
+	 * swap passthru option to convert from big endian to little endian.
+	 */
+	ret = ccp_init_dm_workarea(&key, cmd_q,
+				   CCP_DES3_KEY_SB_COUNT * CCP_SB_BYTES,
+				   DMA_TO_DEVICE);
+	if (ret)
+		return ret;
+
+	/*
+	 * The contents of the key triplet are in the reverse order of what
+	 * is required by the engine. Copy the 3 pieces individually to put
+	 * them where they belong.
+	 */
+	dm_offset = CCP_SB_BYTES - des3->key_len; /* Basic offset */
+
+	len_singlekey = des3->key_len / 3;
+	ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
+			des3->key, 0, len_singlekey);
+	ccp_set_dm_area(&key, dm_offset + len_singlekey,
+			des3->key, len_singlekey, len_singlekey);
+	ccp_set_dm_area(&key, dm_offset,
+			des3->key, 2 * len_singlekey, len_singlekey);
+
+	/* Copy the key to the SB */
+	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
+			     CCP_PASSTHRU_BYTESWAP_256BIT);
+	if (ret) {
+		cmd->engine_error = cmd_q->cmd_error;
+		goto e_key;
+	}
+
+	/*
+	 * The DES3 context fits in a single (32-byte) KSB entry and
+	 * must be in little endian format. Use the 256-bit byte swap
+	 * passthru option to convert from big endian to little endian.
+	 */
+	if (des3->mode != CCP_DES3_MODE_ECB) {
+		u32 load_mode;
+
+		op.sb_ctx = cmd_q->sb_ctx;
+
+		ret = ccp_init_dm_workarea(&ctx, cmd_q,
+					   CCP_DES3_CTX_SB_COUNT * CCP_SB_BYTES,
+					   DMA_BIDIRECTIONAL);
+		if (ret)
+			goto e_key;
+
+		/* Load the context into the LSB */
+		dm_offset = CCP_SB_BYTES - des3->iv_len;
+		ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0, des3->iv_len);
+
+		if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
+			load_mode = CCP_PASSTHRU_BYTESWAP_NOOP;
+		else
+			load_mode = CCP_PASSTHRU_BYTESWAP_256BIT;
+		ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
+				     load_mode);
+		if (ret) {
+			cmd->engine_error = cmd_q->cmd_error;
+			goto e_ctx;
+		}
+	}
+
+	/*
+	 * Prepare the input and output data workareas. For in-place
+	 * operations we need to set the dma direction to BIDIRECTIONAL
+	 * and copy the src workarea to the dst workarea.
+	 */
+	if (sg_virt(des3->src) == sg_virt(des3->dst))
+		in_place = true;
+
+	ret = ccp_init_data(&src, cmd_q, des3->src, des3->src_len,
+			DES3_EDE_BLOCK_SIZE,
+			in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE);
+	if (ret)
+		goto e_ctx;
+
+	if (in_place)
+		dst = src;
+	else {
+		ret = ccp_init_data(&dst, cmd_q, des3->dst, des3->src_len,
+				DES3_EDE_BLOCK_SIZE, DMA_FROM_DEVICE);
+		if (ret)
+			goto e_src;
+	}
+
+	/* Send data to the CCP DES3 engine */
+	while (src.sg_wa.bytes_left) {
+		ccp_prepare_data(&src, &dst, &op, DES3_EDE_BLOCK_SIZE, true);
+		if (!src.sg_wa.bytes_left) {
+			op.eom = 1;
+
+			/* Since we don't retrieve the context in ECB mode
+			 * we have to wait for the operation to complete
+			 * on the last piece of data
+			 */
+			op.soc = 0;
+		}
+
+		ret = cmd_q->ccp->vdata->perform->des3(&op);
+		if (ret) {
+			cmd->engine_error = cmd_q->cmd_error;
+			goto e_dst;
+		}
+
+		ccp_process_data(&src, &dst, &op);
+	}
+
+	if (des3->mode != CCP_DES3_MODE_ECB) {
+		/* Retrieve the context and make BE */
+		ret = ccp_copy_from_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
+				       CCP_PASSTHRU_BYTESWAP_256BIT);
+		if (ret) {
+			cmd->engine_error = cmd_q->cmd_error;
+			goto e_dst;
+		}
+
+		/* ...but we only need the last DES3_EDE_BLOCK_SIZE bytes */
+		if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
+			dm_offset = CCP_SB_BYTES - des3->iv_len;
+		else
+			dm_offset = 0;
+		ccp_get_dm_area(&ctx, dm_offset, des3->iv, 0,
+				DES3_EDE_BLOCK_SIZE);
+	}
+e_dst:
+	if (!in_place)
+		ccp_free_data(&dst, cmd_q);
+
+e_src:
+	ccp_free_data(&src, cmd_q);
+
+e_ctx:
+	if (des3->mode != CCP_DES3_MODE_ECB)
+		ccp_dm_free(&ctx);
+
+e_key:
+	ccp_dm_free(&key);
+
+	return ret;
+}
+
 static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 {
 	struct ccp_sha_engine *sha = &cmd->u.sha;
@@ -955,6 +1416,18 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 			return -EINVAL;
 		block_size = SHA256_BLOCK_SIZE;
 		break;
+	case CCP_SHA_TYPE_384:
+		if (cmd_q->ccp->vdata->version < CCP_VERSION(4, 0)
+		    || sha->ctx_len < SHA384_DIGEST_SIZE)
+			return -EINVAL;
+		block_size = SHA384_BLOCK_SIZE;
+		break;
+	case CCP_SHA_TYPE_512:
+		if (cmd_q->ccp->vdata->version < CCP_VERSION(4, 0)
+		    || sha->ctx_len < SHA512_DIGEST_SIZE)
+			return -EINVAL;
+		block_size = SHA512_BLOCK_SIZE;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1042,6 +1515,21 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		sb_count = 1;
 		ooffset = ioffset = 0;
 		break;
+	case CCP_SHA_TYPE_384:
+		digest_size = SHA384_DIGEST_SIZE;
+		init = (void *) ccp_sha384_init;
+		ctx_size = SHA512_DIGEST_SIZE;
+		sb_count = 2;
+		ioffset = 0;
+		ooffset = 2 * CCP_SB_BYTES - SHA384_DIGEST_SIZE;
+		break;
+	case CCP_SHA_TYPE_512:
+		digest_size = SHA512_DIGEST_SIZE;
+		init = (void *) ccp_sha512_init;
+		ctx_size = SHA512_DIGEST_SIZE;
+		sb_count = 2;
+		ooffset = ioffset = 0;
+		break;
 	default:
 		ret = -EINVAL;
 		goto e_data;
@@ -1060,6 +1548,11 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	op.u.sha.type = sha->type;
 	op.u.sha.msg_bits = sha->msg_bits;
 
+	/* For SHA1/224/256 the context fits in a single (32-byte) SB entry;
+	 * SHA384/512 require 2 adjacent SB slots, with the right half in the
+	 * first slot, and the left half in the second. Each portion must then
+	 * be in little endian format: use the 256-bit byte swap option.
+	 */
 	ret = ccp_init_dm_workarea(&ctx, cmd_q, sb_count * CCP_SB_BYTES,
 				   DMA_BIDIRECTIONAL);
 	if (ret)
@@ -1071,6 +1564,13 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		case CCP_SHA_TYPE_256:
 			memcpy(ctx.address + ioffset, init, ctx_size);
 			break;
+		case CCP_SHA_TYPE_384:
+		case CCP_SHA_TYPE_512:
+			memcpy(ctx.address + ctx_size / 2, init,
+			       ctx_size / 2);
+			memcpy(ctx.address, init + ctx_size / 2,
+			       ctx_size / 2);
+			break;
 		default:
 			ret = -EINVAL;
 			goto e_ctx;
@@ -1137,6 +1637,15 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 					sha->ctx, 0,
 					digest_size);
 			break;
+		case CCP_SHA_TYPE_384:
+		case CCP_SHA_TYPE_512:
+			ccp_get_dm_area(&ctx, 0,
+					sha->ctx, LSB_ITEM_SIZE - ooffset,
+					LSB_ITEM_SIZE);
+			ccp_get_dm_area(&ctx, LSB_ITEM_SIZE + ooffset,
+					sha->ctx, 0,
+					LSB_ITEM_SIZE - ooffset);
+			break;
 		default:
 			ret = -EINVAL;
 			goto e_ctx;
@@ -1174,6 +1683,16 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 			       ctx.address + ooffset,
 			       digest_size);
 			break;
+		case CCP_SHA_TYPE_384:
+		case CCP_SHA_TYPE_512:
+			memcpy(hmac_buf + block_size,
+			       ctx.address + LSB_ITEM_SIZE + ooffset,
+			       LSB_ITEM_SIZE);
+			memcpy(hmac_buf + block_size +
+			       (LSB_ITEM_SIZE - ooffset),
+			       ctx.address,
+			       LSB_ITEM_SIZE);
+			break;
 		default:
 			ret = -EINVAL;
 			goto e_ctx;
@@ -1831,6 +2350,9 @@ int ccp_run_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	case CCP_ENGINE_XTS_AES_128:
 		ret = ccp_run_xts_aes_cmd(cmd_q, cmd);
 		break;
+	case CCP_ENGINE_DES3:
+		ret = ccp_run_des3_cmd(cmd_q, cmd);
+		break;
 	case CCP_ENGINE_SHA:
 		ret = ccp_run_sha_cmd(cmd_q, cmd);
 		break;
diff --git a/drivers/crypto/ccp/ccp-pci.c b/drivers/crypto/ccp/ccp-pci.c
index 28a9996c1085..e880d4cf4ada 100644
--- a/drivers/crypto/ccp/ccp-pci.c
+++ b/drivers/crypto/ccp/ccp-pci.c
@@ -69,6 +69,7 @@ static int ccp_get_msix_irqs(struct ccp_device *ccp)
 			goto e_irq;
 		}
 	}
+	ccp->use_tasklet = true;
 
 	return 0;
 
@@ -100,6 +101,7 @@ static int ccp_get_msi_irq(struct ccp_device *ccp)
 		dev_notice(dev, "unable to allocate MSI IRQ (%d)\n", ret);
 		goto e_msi;
 	}
+	ccp->use_tasklet = true;
 
 	return 0;
 
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 41bc7f4f58cd..f00e0d8bd039 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -294,7 +294,7 @@ static inline void get_aes_decrypt_key(unsigned char *dec_key,
 
 static struct crypto_shash *chcr_alloc_shash(unsigned int ds)
 {
-	struct crypto_shash *base_hash = NULL;
+	struct crypto_shash *base_hash = ERR_PTR(-EINVAL);
 
 	switch (ds) {
 	case SHA1_DIGEST_SIZE:
@@ -522,7 +522,7 @@ static inline void create_wreq(struct chcr_context *ctx,
 {
 	struct uld_ctx *u_ctx = ULD_CTX(ctx);
 	int iv_loc = IV_DSGL;
-	int qid = u_ctx->lldi.rxq_ids[ctx->tx_channel_id];
+	int qid = u_ctx->lldi.rxq_ids[ctx->rx_qidx];
 	unsigned int immdatalen = 0, nr_frags = 0;
 
 	if (is_ofld_imm(skb)) {
@@ -543,7 +543,7 @@ static inline void create_wreq(struct chcr_context *ctx,
 	chcr_req->wreq.cookie = cpu_to_be64((uintptr_t)req);
 	chcr_req->wreq.rx_chid_to_rx_q_id =
 		FILL_WR_RX_Q_ID(ctx->dev->rx_channel_id, qid,
-				is_iv ? iv_loc : IV_NOP, ctx->tx_channel_id);
+				is_iv ? iv_loc : IV_NOP, ctx->tx_qidx);
 
 	chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->dev->tx_channel_id,
 						       qid);
@@ -721,19 +721,19 @@ static int chcr_aes_encrypt(struct ablkcipher_request *req)
 	struct sk_buff *skb;
 
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    ctx->tx_channel_id))) {
+					    ctx->tx_qidx))) {
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
 
-	skb = create_cipher_wr(req, u_ctx->lldi.rxq_ids[ctx->tx_channel_id],
+	skb = create_cipher_wr(req, u_ctx->lldi.rxq_ids[ctx->rx_qidx],
 			       CHCR_ENCRYPT_OP);
 	if (IS_ERR(skb)) {
 		pr_err("chcr : %s : Failed to form WR. No memory\n", __func__);
 		return  PTR_ERR(skb);
 	}
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 	return -EINPROGRESS;
 }
@@ -746,19 +746,19 @@ static int chcr_aes_decrypt(struct ablkcipher_request *req)
 	struct sk_buff *skb;
 
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    ctx->tx_channel_id))) {
+					    ctx->tx_qidx))) {
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
 
-	skb = create_cipher_wr(req, u_ctx->lldi.rxq_ids[0],
+	skb = create_cipher_wr(req, u_ctx->lldi.rxq_ids[ctx->rx_qidx],
 			       CHCR_DECRYPT_OP);
 	if (IS_ERR(skb)) {
 		pr_err("chcr : %s : Failed to form WR. No memory\n", __func__);
 		return PTR_ERR(skb);
 	}
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 	return -EINPROGRESS;
 }
@@ -766,7 +766,9 @@ static int chcr_aes_decrypt(struct ablkcipher_request *req)
 static int chcr_device_init(struct chcr_context *ctx)
 {
 	struct uld_ctx *u_ctx;
+	struct adapter *adap;
 	unsigned int id;
+	int txq_perchan, txq_idx, ntxq;
 	int err = 0, rxq_perchan, rxq_idx;
 
 	id = smp_processor_id();
@@ -777,11 +779,18 @@ static int chcr_device_init(struct chcr_context *ctx)
 			goto out;
 		}
 		u_ctx = ULD_CTX(ctx);
+		adap = padap(ctx->dev);
+		ntxq = min_not_zero((unsigned int)u_ctx->lldi.nrxq,
+				    adap->vres.ncrypto_fc);
 		rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan;
+		txq_perchan = ntxq / u_ctx->lldi.nchan;
 		rxq_idx = ctx->dev->tx_channel_id * rxq_perchan;
 		rxq_idx += id % rxq_perchan;
+		txq_idx = ctx->dev->tx_channel_id * txq_perchan;
+		txq_idx += id % txq_perchan;
 		spin_lock(&ctx->dev->lock_chcr_dev);
-		ctx->tx_channel_id = rxq_idx;
+		ctx->rx_qidx = rxq_idx;
+		ctx->tx_qidx = txq_idx;
 		ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id;
 		ctx->dev->rx_channel_id = 0;
 		spin_unlock(&ctx->dev->lock_chcr_dev);
@@ -935,7 +944,7 @@ static int chcr_ahash_update(struct ahash_request *req)
 
 	u_ctx = ULD_CTX(ctx);
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    ctx->tx_channel_id))) {
+					    ctx->tx_qidx))) {
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
@@ -975,7 +984,7 @@ static int chcr_ahash_update(struct ahash_request *req)
 	}
 	req_ctx->reqlen = remainder;
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 
 	return -EINPROGRESS;
@@ -1028,7 +1037,7 @@ static int chcr_ahash_final(struct ahash_request *req)
 		return -ENOMEM;
 
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 	return -EINPROGRESS;
 }
@@ -1047,7 +1056,7 @@ static int chcr_ahash_finup(struct ahash_request *req)
 	u_ctx = ULD_CTX(ctx);
 
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    ctx->tx_channel_id))) {
+					    ctx->tx_qidx))) {
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
@@ -1079,7 +1088,7 @@ static int chcr_ahash_finup(struct ahash_request *req)
 		return -ENOMEM;
 
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 
 	return -EINPROGRESS;
@@ -1100,7 +1109,7 @@ static int chcr_ahash_digest(struct ahash_request *req)
 
 	u_ctx = ULD_CTX(ctx);
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    ctx->tx_channel_id))) {
+					    ctx->tx_qidx))) {
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
@@ -1130,7 +1139,7 @@ static int chcr_ahash_digest(struct ahash_request *req)
 		return -ENOMEM;
 
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 	return -EINPROGRESS;
 }
@@ -1334,20 +1343,36 @@ static int chcr_copy_assoc(struct aead_request *req,
 
 	return crypto_skcipher_encrypt(skreq);
 }
-
-static unsigned char get_hmac(unsigned int authsize)
+static int chcr_aead_need_fallback(struct aead_request *req, int src_nent,
+				   int aadmax, int wrlen,
+				   unsigned short op_type)
 {
-	switch (authsize) {
-	case ICV_8:
-		return CHCR_SCMD_HMAC_CTRL_PL1;
-	case ICV_10:
-		return CHCR_SCMD_HMAC_CTRL_TRUNC_RFC4366;
-	case ICV_12:
-		return CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT;
-	}
-	return CHCR_SCMD_HMAC_CTRL_NO_TRUNC;
+	unsigned int authsize = crypto_aead_authsize(crypto_aead_reqtfm(req));
+
+	if (((req->cryptlen - (op_type ? authsize : 0)) == 0) ||
+	    (req->assoclen > aadmax) ||
+	    (src_nent > MAX_SKB_FRAGS) ||
+	    (wrlen > MAX_WR_SIZE))
+		return 1;
+	return 0;
 }
 
+static int chcr_aead_fallback(struct aead_request *req, unsigned short op_type)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct chcr_context *ctx = crypto_aead_ctx(tfm);
+	struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
+	struct aead_request *subreq = aead_request_ctx(req);
+
+	aead_request_set_tfm(subreq, aeadctx->sw_cipher);
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	 aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
+				 req->iv);
+	 aead_request_set_ad(subreq, req->assoclen);
+	return op_type ? crypto_aead_decrypt(subreq) :
+		crypto_aead_encrypt(subreq);
+}
 
 static struct sk_buff *create_authenc_wr(struct aead_request *req,
 					 unsigned short qid,
@@ -1371,7 +1396,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	unsigned short stop_offset = 0;
 	unsigned int  assoclen = req->assoclen;
 	unsigned int  authsize = crypto_aead_authsize(tfm);
-	int err = 0;
+	int err = -EINVAL, src_nent;
 	int null = 0;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		GFP_ATOMIC;
@@ -1381,8 +1406,8 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 
 	if (op_type && req->cryptlen < crypto_aead_authsize(tfm))
 		goto err;
-
-	if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
+	src_nent = sg_nents_for_len(req->src, req->assoclen + req->cryptlen);
+	if (src_nent < 0)
 		goto err;
 	src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
 	reqctx->dst = src;
@@ -1400,7 +1425,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	}
 	reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
 					     (op_type ? -authsize : authsize));
-	if (reqctx->dst_nents <= 0) {
+	if (reqctx->dst_nents < 0) {
 		pr_err("AUTHENC:Invalid Destination sg entries\n");
 		goto err;
 	}
@@ -1408,6 +1433,12 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	kctx_len = (ntohl(KEY_CONTEXT_CTX_LEN_V(aeadctx->key_ctx_hdr)) << 4)
 		- sizeof(chcr_req->key_ctx);
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
+	if (chcr_aead_need_fallback(req, src_nent + MIN_AUTH_SG,
+			T6_MAX_AAD_SIZE,
+			transhdr_len + (sgl_len(src_nent + MIN_AUTH_SG) * 8),
+				op_type)) {
+		return ERR_PTR(chcr_aead_fallback(req, op_type));
+	}
 	skb = alloc_skb((transhdr_len + sizeof(struct sge_opaque_hdr)), flags);
 	if (!skb)
 		goto err;
@@ -1489,24 +1520,6 @@ err:
 	return ERR_PTR(-EINVAL);
 }
 
-static void aes_gcm_empty_pld_pad(struct scatterlist *sg,
-				  unsigned short offset)
-{
-	struct page *spage;
-	unsigned char *addr;
-
-	spage = sg_page(sg);
-	get_page(spage); /* so that it is not freed by NIC */
-#ifdef KMAP_ATOMIC_ARGS
-	addr = kmap_atomic(spage, KM_SOFTIRQ0);
-#else
-	addr = kmap_atomic(spage);
-#endif
-	memset(addr + sg->offset, 0, offset + 1);
-
-	kunmap_atomic(addr);
-}
-
 static int set_msg_len(u8 *block, unsigned int msglen, int csize)
 {
 	__be32 data;
@@ -1570,11 +1583,6 @@ static int ccm_format_packet(struct aead_request *req,
 	struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
 	int rc = 0;
 
-	if (req->assoclen > T5_MAX_AAD_SIZE) {
-		pr_err("CCM: Unsupported AAD data. It should be < %d\n",
-		       T5_MAX_AAD_SIZE);
-		return -EINVAL;
-	}
 	if (sub_type == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) {
 		reqctx->iv[0] = 3;
 		memcpy(reqctx->iv + 1, &aeadctx->salt[0], 3);
@@ -1600,13 +1608,13 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl,
 					  struct chcr_context *chcrctx)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct chcr_aead_ctx *aeadctx = AEAD_CTX(crypto_aead_ctx(tfm));
 	unsigned int ivsize = AES_BLOCK_SIZE;
 	unsigned int cipher_mode = CHCR_SCMD_CIPHER_MODE_AES_CCM;
 	unsigned int mac_mode = CHCR_SCMD_AUTH_MODE_CBCMAC;
 	unsigned int c_id = chcrctx->dev->rx_channel_id;
 	unsigned int ccm_xtra;
 	unsigned char tag_offset = 0, auth_offset = 0;
-	unsigned char hmac_ctrl = get_hmac(crypto_aead_authsize(tfm));
 	unsigned int assoclen;
 
 	if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)
@@ -1642,8 +1650,8 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl,
 					crypto_aead_authsize(tfm));
 	sec_cpl->seqno_numivs =  FILL_SEC_CPL_SCMD0_SEQNO(op_type,
 					(op_type == CHCR_ENCRYPT_OP) ? 0 : 1,
-					cipher_mode, mac_mode, hmac_ctrl,
-					ivsize >> 1);
+					cipher_mode, mac_mode,
+					aeadctx->hmac_ctrl, ivsize >> 1);
 
 	sec_cpl->ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1, 0,
 					1, dst_size);
@@ -1719,16 +1727,17 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	unsigned int dst_size = 0, kctx_len;
 	unsigned int sub_type;
 	unsigned int authsize = crypto_aead_authsize(tfm);
-	int err = 0;
+	int err = -EINVAL, src_nent;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		GFP_ATOMIC;
 
 
 	if (op_type && req->cryptlen < crypto_aead_authsize(tfm))
 		goto err;
-
-	if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
+	src_nent = sg_nents_for_len(req->src, req->assoclen + req->cryptlen);
+	if (src_nent < 0)
 		goto err;
+
 	sub_type = get_aead_subtype(tfm);
 	src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
 	reqctx->dst = src;
@@ -1744,7 +1753,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	}
 	reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
 					     (op_type ? -authsize : authsize));
-	if (reqctx->dst_nents <= 0) {
+	if (reqctx->dst_nents < 0) {
 		pr_err("CCM:Invalid Destination sg entries\n");
 		goto err;
 	}
@@ -1756,6 +1765,13 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	dst_size = get_space_for_phys_dsgl(reqctx->dst_nents);
 	kctx_len = ((DIV_ROUND_UP(aeadctx->enckey_len, 16)) << 4) * 2;
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
+	if (chcr_aead_need_fallback(req, src_nent + MIN_CCM_SG,
+			    T6_MAX_AAD_SIZE - 18,
+			    transhdr_len + (sgl_len(src_nent + MIN_CCM_SG) * 8),
+			    op_type)) {
+		return ERR_PTR(chcr_aead_fallback(req, op_type));
+	}
+
 	skb = alloc_skb((transhdr_len + sizeof(struct sge_opaque_hdr)),  flags);
 
 	if (!skb)
@@ -1820,8 +1836,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	unsigned char tag_offset = 0;
 	unsigned int crypt_len = 0;
 	unsigned int authsize = crypto_aead_authsize(tfm);
-	unsigned char hmac_ctrl = get_hmac(authsize);
-	int err = 0;
+	int err = -EINVAL, src_nent;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		GFP_ATOMIC;
 
@@ -1831,8 +1846,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 
 	if (op_type && req->cryptlen < crypto_aead_authsize(tfm))
 		goto err;
-
-	if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
+	src_nent = sg_nents_for_len(req->src, req->assoclen + req->cryptlen);
+	if (src_nent < 0)
 		goto err;
 
 	src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
@@ -1854,7 +1869,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 		crypt_len = req->cryptlen;
 	reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
 					     (op_type ? -authsize : authsize));
-	if (reqctx->dst_nents <= 0) {
+	if (reqctx->dst_nents < 0) {
 		pr_err("GCM:Invalid Destination sg entries\n");
 		goto err;
 	}
@@ -1864,6 +1879,12 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	kctx_len = ((DIV_ROUND_UP(aeadctx->enckey_len, 16)) << 4) +
 		AEAD_H_SIZE;
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
+	if (chcr_aead_need_fallback(req, src_nent + MIN_GCM_SG,
+			    T6_MAX_AAD_SIZE,
+			    transhdr_len + (sgl_len(src_nent + MIN_GCM_SG) * 8),
+			    op_type)) {
+		return ERR_PTR(chcr_aead_fallback(req, op_type));
+	}
 	skb = alloc_skb((transhdr_len + sizeof(struct sge_opaque_hdr)), flags);
 	if (!skb)
 		goto err;
@@ -1881,11 +1902,11 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	chcr_req->sec_cpl.op_ivinsrtofst = FILL_SEC_CPL_OP_IVINSR(
 					ctx->dev->rx_channel_id, 2, (ivsize ?
 					(req->assoclen + 1) : 0));
-	chcr_req->sec_cpl.pldlen = htonl(req->assoclen + ivsize + crypt_len);
+	chcr_req->sec_cpl.pldlen =
+		htonl(req->assoclen + ivsize + req->cryptlen);
 	chcr_req->sec_cpl.aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI(
 					req->assoclen ? 1 : 0, req->assoclen,
 					req->assoclen + ivsize + 1, 0);
-	if (req->cryptlen) {
 		chcr_req->sec_cpl.cipherstop_lo_authinsert =
 			FILL_SEC_CPL_AUTHINSERT(0, req->assoclen + ivsize + 1,
 						tag_offset, tag_offset);
@@ -1893,17 +1914,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 			FILL_SEC_CPL_SCMD0_SEQNO(op_type, (op_type ==
 					CHCR_ENCRYPT_OP) ? 1 : 0,
 					CHCR_SCMD_CIPHER_MODE_AES_GCM,
-					CHCR_SCMD_AUTH_MODE_GHASH, hmac_ctrl,
-					ivsize >> 1);
-	} else {
-		chcr_req->sec_cpl.cipherstop_lo_authinsert =
-			FILL_SEC_CPL_AUTHINSERT(0, 0, 0, 0);
-		chcr_req->sec_cpl.seqno_numivs =
-			FILL_SEC_CPL_SCMD0_SEQNO(op_type,
-					(op_type ==  CHCR_ENCRYPT_OP) ?
-					1 : 0, CHCR_SCMD_CIPHER_MODE_AES_CBC,
-					0, 0, ivsize >> 1);
-	}
+					CHCR_SCMD_AUTH_MODE_GHASH,
+					aeadctx->hmac_ctrl, ivsize >> 1);
 	chcr_req->sec_cpl.ivgen_hdrlen =  FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1,
 					0, 1, dst_size);
 	chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr;
@@ -1936,15 +1948,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	write_sg_to_skb(skb, &frags, req->src, req->assoclen);
 
 	write_buffer_to_skb(skb, &frags, reqctx->iv, ivsize);
-
-	if (req->cryptlen) {
-		write_sg_to_skb(skb, &frags, src, req->cryptlen);
-	} else {
-		aes_gcm_empty_pld_pad(req->dst, authsize - 1);
-		write_sg_to_skb(skb, &frags, reqctx->dst, crypt_len);
-
-	}
-
+	write_sg_to_skb(skb, &frags, src, req->cryptlen);
 	create_wreq(ctx, chcr_req, req, skb, kctx_len, size, 1,
 			sizeof(struct cpl_rx_phys_dsgl) + dst_size);
 	reqctx->skb = skb;
@@ -1965,8 +1969,15 @@ static int chcr_aead_cra_init(struct crypto_aead *tfm)
 {
 	struct chcr_context *ctx = crypto_aead_ctx(tfm);
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
-
-	crypto_aead_set_reqsize(tfm, sizeof(struct chcr_aead_reqctx));
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+
+	aeadctx->sw_cipher = crypto_alloc_aead(alg->base.cra_name, 0,
+					       CRYPTO_ALG_NEED_FALLBACK);
+	if  (IS_ERR(aeadctx->sw_cipher))
+		return PTR_ERR(aeadctx->sw_cipher);
+	crypto_aead_set_reqsize(tfm, max(sizeof(struct chcr_aead_reqctx),
+				 sizeof(struct aead_request) +
+				 crypto_aead_reqsize(aeadctx->sw_cipher)));
 	aeadctx->null = crypto_get_default_null_skcipher();
 	if (IS_ERR(aeadctx->null))
 		return PTR_ERR(aeadctx->null);
@@ -1975,7 +1986,11 @@ static int chcr_aead_cra_init(struct crypto_aead *tfm)
 
 static void chcr_aead_cra_exit(struct crypto_aead *tfm)
 {
+	struct chcr_context *ctx = crypto_aead_ctx(tfm);
+	struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
+
 	crypto_put_default_null_skcipher();
+	crypto_free_aead(aeadctx->sw_cipher);
 }
 
 static int chcr_authenc_null_setauthsize(struct crypto_aead *tfm,
@@ -1985,7 +2000,7 @@ static int chcr_authenc_null_setauthsize(struct crypto_aead *tfm,
 
 	aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NOP;
 	aeadctx->mayverify = VERIFY_HW;
-	return 0;
+	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
 }
 static int chcr_authenc_setauthsize(struct crypto_aead *tfm,
 				    unsigned int authsize)
@@ -2022,7 +2037,7 @@ static int chcr_authenc_setauthsize(struct crypto_aead *tfm,
 		aeadctx->hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC;
 		aeadctx->mayverify = VERIFY_SW;
 	}
-	return 0;
+	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
 }
 
 
@@ -2062,7 +2077,7 @@ static int chcr_gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 			CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
-	return 0;
+	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
 }
 
 static int chcr_4106_4309_setauthsize(struct crypto_aead *tfm,
@@ -2088,7 +2103,7 @@ static int chcr_4106_4309_setauthsize(struct crypto_aead *tfm,
 				     CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
-	return 0;
+	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
 }
 
 static int chcr_ccm_setauthsize(struct crypto_aead *tfm,
@@ -2130,10 +2145,10 @@ static int chcr_ccm_setauthsize(struct crypto_aead *tfm,
 				     CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
-	return 0;
+	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
 }
 
-static int chcr_aead_ccm_setkey(struct crypto_aead *aead,
+static int chcr_ccm_common_setkey(struct crypto_aead *aead,
 				const u8 *key,
 				unsigned int keylen)
 {
@@ -2142,8 +2157,6 @@ static int chcr_aead_ccm_setkey(struct crypto_aead *aead,
 	unsigned char ck_size, mk_size;
 	int key_ctx_size = 0;
 
-	memcpy(aeadctx->key, key, keylen);
-	aeadctx->enckey_len = keylen;
 	key_ctx_size = sizeof(struct _key_ctx) +
 		((DIV_ROUND_UP(keylen, 16)) << 4)  * 2;
 	if (keylen == AES_KEYSIZE_128) {
@@ -2163,9 +2176,32 @@ static int chcr_aead_ccm_setkey(struct crypto_aead *aead,
 	}
 	aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, mk_size, 0, 0,
 						key_ctx_size >> 4);
+	memcpy(aeadctx->key, key, keylen);
+	aeadctx->enckey_len = keylen;
+
 	return 0;
 }
 
+static int chcr_aead_ccm_setkey(struct crypto_aead *aead,
+				const u8 *key,
+				unsigned int keylen)
+{
+	struct chcr_context *ctx = crypto_aead_ctx(aead);
+	struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
+	int error;
+
+	crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(aead) &
+			      CRYPTO_TFM_REQ_MASK);
+	error = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen);
+	crypto_aead_clear_flags(aead, CRYPTO_TFM_RES_MASK);
+	crypto_aead_set_flags(aead, crypto_aead_get_flags(aeadctx->sw_cipher) &
+			      CRYPTO_TFM_RES_MASK);
+	if (error)
+		return error;
+	return chcr_ccm_common_setkey(aead, key, keylen);
+}
+
 static int chcr_aead_rfc4309_setkey(struct crypto_aead *aead, const u8 *key,
 				    unsigned int keylen)
 {
@@ -2180,7 +2216,7 @@ static int chcr_aead_rfc4309_setkey(struct crypto_aead *aead, const u8 *key,
 	}
 	keylen -= 3;
 	memcpy(aeadctx->salt, key + keylen, 3);
-	return chcr_aead_ccm_setkey(aead, key, keylen);
+	return chcr_ccm_common_setkey(aead, key, keylen);
 }
 
 static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key,
@@ -2193,6 +2229,17 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	unsigned int ck_size;
 	int ret = 0, key_ctx_size = 0;
 
+	aeadctx->enckey_len = 0;
+	crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(aead)
+			      & CRYPTO_TFM_REQ_MASK);
+	ret = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen);
+	crypto_aead_clear_flags(aead, CRYPTO_TFM_RES_MASK);
+	crypto_aead_set_flags(aead, crypto_aead_get_flags(aeadctx->sw_cipher) &
+			      CRYPTO_TFM_RES_MASK);
+	if (ret)
+		goto out;
+
 	if (get_aead_subtype(aead) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 &&
 	    keylen > 3) {
 		keylen -= 4;  /* nonce/salt is present in the last 4 bytes */
@@ -2207,8 +2254,7 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	} else {
 		crypto_tfm_set_flags((struct crypto_tfm *)aead,
 				     CRYPTO_TFM_RES_BAD_KEY_LEN);
-		aeadctx->enckey_len = 0;
-		pr_err("GCM: Invalid key length %d", keylen);
+		pr_err("GCM: Invalid key length %d\n", keylen);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -2259,11 +2305,21 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	int err = 0, i, key_ctx_len = 0;
 	unsigned char ck_size = 0;
 	unsigned char pad[CHCR_HASH_MAX_BLOCK_SIZE_128] = { 0 };
-	struct crypto_shash *base_hash = NULL;
+	struct crypto_shash *base_hash = ERR_PTR(-EINVAL);
 	struct algo_param param;
 	int align;
 	u8 *o_ptr = NULL;
 
+	crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(authenc)
+			      & CRYPTO_TFM_REQ_MASK);
+	err = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen);
+	crypto_aead_clear_flags(authenc, CRYPTO_TFM_RES_MASK);
+	crypto_aead_set_flags(authenc, crypto_aead_get_flags(aeadctx->sw_cipher)
+			      & CRYPTO_TFM_RES_MASK);
+	if (err)
+		goto out;
+
 	if (crypto_authenc_extractkeys(&keys, key, keylen) != 0) {
 		crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		goto out;
@@ -2296,7 +2352,8 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	base_hash  = chcr_alloc_shash(max_authsize);
 	if (IS_ERR(base_hash)) {
 		pr_err("chcr : Base driver cannot be loaded\n");
-		goto out;
+		aeadctx->enckey_len = 0;
+		return -EINVAL;
 	}
 	{
 		SHASH_DESC_ON_STACK(shash, base_hash);
@@ -2351,7 +2408,7 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	}
 out:
 	aeadctx->enckey_len = 0;
-	if (base_hash)
+	if (!IS_ERR(base_hash))
 		chcr_free_shash(base_hash);
 	return -EINVAL;
 }
@@ -2363,11 +2420,21 @@ static int chcr_aead_digest_null_setkey(struct crypto_aead *authenc,
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
 	struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx);
 	struct crypto_authenc_keys keys;
-
+	int err;
 	/* it contains auth and cipher key both*/
 	int key_ctx_len = 0;
 	unsigned char ck_size = 0;
 
+	crypto_aead_clear_flags(aeadctx->sw_cipher, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(aeadctx->sw_cipher, crypto_aead_get_flags(authenc)
+			      & CRYPTO_TFM_REQ_MASK);
+	err = crypto_aead_setkey(aeadctx->sw_cipher, key, keylen);
+	crypto_aead_clear_flags(authenc, CRYPTO_TFM_RES_MASK);
+	crypto_aead_set_flags(authenc, crypto_aead_get_flags(aeadctx->sw_cipher)
+			      & CRYPTO_TFM_RES_MASK);
+	if (err)
+		goto out;
+
 	if (crypto_authenc_extractkeys(&keys, key, keylen) != 0) {
 		crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		goto out;
@@ -2465,22 +2532,20 @@ static int chcr_aead_op(struct aead_request *req,
 	}
 	u_ctx = ULD_CTX(ctx);
 	if (cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-				   ctx->tx_channel_id)) {
+				   ctx->tx_qidx)) {
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
 
 	/* Form a WR from req */
-	skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[ctx->tx_channel_id], size,
+	skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[ctx->rx_qidx], size,
 			   op_type);
 
-	if (IS_ERR(skb) || skb == NULL) {
-		pr_err("chcr : %s : failed to form WR. No memory\n", __func__);
+	if (IS_ERR(skb) || !skb)
 		return PTR_ERR(skb);
-	}
 
 	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_channel_id);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, ctx->tx_qidx);
 	chcr_send_wr(skb);
 	return -EINPROGRESS;
 }
@@ -2673,6 +2738,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_name = "gcm(aes)",
 				.cra_driver_name = "gcm-aes-chcr",
 				.cra_blocksize	= 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_gcm_ctx),
@@ -2691,6 +2757,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_name = "rfc4106(gcm(aes))",
 				.cra_driver_name = "rfc4106-gcm-aes-chcr",
 				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY + 1,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_gcm_ctx),
@@ -2710,6 +2777,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_name = "ccm(aes)",
 				.cra_driver_name = "ccm-aes-chcr",
 				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx),
 
@@ -2728,6 +2796,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_name = "rfc4309(ccm(aes))",
 				.cra_driver_name = "rfc4309-ccm-aes-chcr",
 				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY + 1,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx),
 
@@ -2747,6 +2816,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_driver_name =
 					"authenc-hmac-sha1-cbc-aes-chcr",
 				.cra_blocksize	 = AES_BLOCK_SIZE,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_authenc_ctx),
@@ -2768,6 +2838,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_driver_name =
 					"authenc-hmac-sha256-cbc-aes-chcr",
 				.cra_blocksize	 = AES_BLOCK_SIZE,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_authenc_ctx),
@@ -2788,6 +2859,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_driver_name =
 					"authenc-hmac-sha224-cbc-aes-chcr",
 				.cra_blocksize	 = AES_BLOCK_SIZE,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_authenc_ctx),
@@ -2807,6 +2879,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_driver_name =
 					"authenc-hmac-sha384-cbc-aes-chcr",
 				.cra_blocksize	 = AES_BLOCK_SIZE,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_authenc_ctx),
@@ -2827,6 +2900,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_driver_name =
 					"authenc-hmac-sha512-cbc-aes-chcr",
 				.cra_blocksize	 = AES_BLOCK_SIZE,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_authenc_ctx),
@@ -2847,6 +2921,7 @@ static struct chcr_alg_template driver_algs[] = {
 				.cra_driver_name =
 					"authenc-digest_null-cbc-aes-chcr",
 				.cra_blocksize	 = AES_BLOCK_SIZE,
+				.cra_priority = CHCR_AEAD_PRIORITY,
 				.cra_ctxsize =	sizeof(struct chcr_context) +
 						sizeof(struct chcr_aead_ctx) +
 						sizeof(struct chcr_authenc_ctx),
@@ -2915,10 +2990,9 @@ static int chcr_register_alg(void)
 			name = driver_algs[i].alg.crypto.cra_driver_name;
 			break;
 		case CRYPTO_ALG_TYPE_AEAD:
-			driver_algs[i].alg.aead.base.cra_priority =
-				CHCR_CRA_PRIORITY;
 			driver_algs[i].alg.aead.base.cra_flags =
-				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
+				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_NEED_FALLBACK;
 			driver_algs[i].alg.aead.encrypt = chcr_aead_encrypt;
 			driver_algs[i].alg.aead.decrypt = chcr_aead_decrypt;
 			driver_algs[i].alg.aead.init = chcr_aead_cra_init;
diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h
index ba38bae7ce80..751d06a58101 100644
--- a/drivers/crypto/chelsio/chcr_algo.h
+++ b/drivers/crypto/chelsio/chcr_algo.h
@@ -218,6 +218,10 @@
 
 #define MAX_NK 8
 #define CRYPTO_MAX_IMM_TX_PKT_LEN 256
+#define MAX_WR_SIZE			512
+#define MIN_AUTH_SG			2 /*IV + AAD*/
+#define MIN_GCM_SG			2 /* IV + AAD*/
+#define MIN_CCM_SG			3 /*IV+AAD+B0*/
 
 struct algo_param {
 	unsigned int auth_mode;
diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h
index 79da22b5cdc9..cd0c35a18d92 100644
--- a/drivers/crypto/chelsio/chcr_core.h
+++ b/drivers/crypto/chelsio/chcr_core.h
@@ -54,6 +54,8 @@
 #define CHK_MAC_ERR_BIT(x)	(((x) >> MAC_ERROR_BIT) & 1)
 #define MAX_SALT                4
 
+#define padap(dev) pci_get_drvdata(dev->u_ctx->lldi.pdev)
+
 struct uld_ctx;
 
 struct _key_ctx {
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index 81cfd0ba132e..5b2fabb14229 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -41,15 +41,15 @@
 
 #define CCM_B0_SIZE             16
 #define CCM_AAD_FIELD_SIZE      2
-#define T5_MAX_AAD_SIZE 512
+#define T6_MAX_AAD_SIZE 511
 
 
 /* Define following if h/w is not dropping the AAD and IV data before
  * giving the processed data
  */
 
-#define CHCR_CRA_PRIORITY 3000
-
+#define CHCR_CRA_PRIORITY 500
+#define CHCR_AEAD_PRIORITY 6000
 #define CHCR_AES_MAX_KEY_LEN  (2 * (AES_MAX_KEY_SIZE)) /* consider xts */
 #define CHCR_MAX_CRYPTO_IV_LEN 16 /* AES IV len */
 
@@ -188,6 +188,7 @@ struct chcr_aead_ctx {
 	__be32 key_ctx_hdr;
 	unsigned int enckey_len;
 	struct crypto_skcipher *null;
+	struct crypto_aead *sw_cipher;
 	u8 salt[MAX_SALT];
 	u8 key[CHCR_AES_MAX_KEY_LEN];
 	u16 hmac_ctrl;
@@ -211,7 +212,8 @@ struct __crypto_ctx {
 
 struct chcr_context {
 	struct chcr_dev *dev;
-	unsigned char tx_channel_id;
+	unsigned char tx_qidx;
+	unsigned char rx_qidx;
 	struct __crypto_ctx crypto_ctx[0];
 };
 
diff --git a/drivers/crypto/exynos-rng.c b/drivers/crypto/exynos-rng.c
new file mode 100644
index 000000000000..451620b475a0
--- /dev/null
+++ b/drivers/crypto/exynos-rng.c
@@ -0,0 +1,389 @@
+/*
+ * exynos-rng.c - Random Number Generator driver for the Exynos
+ *
+ * Copyright (c) 2017 Krzysztof Kozlowski <krzk@kernel.org>
+ *
+ * Loosely based on old driver from drivers/char/hw_random/exynos-rng.c:
+ * Copyright (C) 2012 Samsung Electronics
+ * Jonghwa Lee <jonghwa3.lee@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation;
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <crypto/internal/rng.h>
+
+#define EXYNOS_RNG_CONTROL		0x0
+#define EXYNOS_RNG_STATUS		0x10
+#define EXYNOS_RNG_SEED_BASE		0x140
+#define EXYNOS_RNG_SEED(n)		(EXYNOS_RNG_SEED_BASE + (n * 0x4))
+#define EXYNOS_RNG_OUT_BASE		0x160
+#define EXYNOS_RNG_OUT(n)		(EXYNOS_RNG_OUT_BASE + (n * 0x4))
+
+/* EXYNOS_RNG_CONTROL bit fields */
+#define EXYNOS_RNG_CONTROL_START	0x18
+/* EXYNOS_RNG_STATUS bit fields */
+#define EXYNOS_RNG_STATUS_SEED_SETTING_DONE	BIT(1)
+#define EXYNOS_RNG_STATUS_RNG_DONE		BIT(5)
+
+/* Five seed and output registers, each 4 bytes */
+#define EXYNOS_RNG_SEED_REGS		5
+#define EXYNOS_RNG_SEED_SIZE		(EXYNOS_RNG_SEED_REGS * 4)
+
+/*
+ * Driver re-seeds itself with generated random numbers to increase
+ * the randomness.
+ *
+ * Time for next re-seed in ms.
+ */
+#define EXYNOS_RNG_RESEED_TIME		100
+/*
+ * In polling mode, do not wait infinitely for the engine to finish the work.
+ */
+#define EXYNOS_RNG_WAIT_RETRIES		100
+
+/* Context for crypto */
+struct exynos_rng_ctx {
+	struct exynos_rng_dev		*rng;
+};
+
+/* Device associated memory */
+struct exynos_rng_dev {
+	struct device			*dev;
+	void __iomem			*mem;
+	struct clk			*clk;
+	/* Generated numbers stored for seeding during resume */
+	u8				seed_save[EXYNOS_RNG_SEED_SIZE];
+	unsigned int			seed_save_len;
+	/* Time of last seeding in jiffies */
+	unsigned long			last_seeding;
+};
+
+static struct exynos_rng_dev *exynos_rng_dev;
+
+static u32 exynos_rng_readl(struct exynos_rng_dev *rng, u32 offset)
+{
+	return readl_relaxed(rng->mem + offset);
+}
+
+static void exynos_rng_writel(struct exynos_rng_dev *rng, u32 val, u32 offset)
+{
+	writel_relaxed(val, rng->mem + offset);
+}
+
+static int exynos_rng_set_seed(struct exynos_rng_dev *rng,
+			       const u8 *seed, unsigned int slen)
+{
+	u32 val;
+	int i;
+
+	/* Round seed length because loop iterates over full register size */
+	slen = ALIGN_DOWN(slen, 4);
+
+	if (slen < EXYNOS_RNG_SEED_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < slen ; i += 4) {
+		unsigned int seed_reg = (i / 4) % EXYNOS_RNG_SEED_REGS;
+
+		val = seed[i] << 24;
+		val |= seed[i + 1] << 16;
+		val |= seed[i + 2] << 8;
+		val |= seed[i + 3] << 0;
+
+		exynos_rng_writel(rng, val, EXYNOS_RNG_SEED(seed_reg));
+	}
+
+	val = exynos_rng_readl(rng, EXYNOS_RNG_STATUS);
+	if (!(val & EXYNOS_RNG_STATUS_SEED_SETTING_DONE)) {
+		dev_warn(rng->dev, "Seed setting not finished\n");
+		return -EIO;
+	}
+
+	rng->last_seeding = jiffies;
+
+	return 0;
+}
+
+/*
+ * Read from output registers and put the data under 'dst' array,
+ * up to dlen bytes.
+ *
+ * Returns number of bytes actually stored in 'dst' (dlen
+ * or EXYNOS_RNG_SEED_SIZE).
+ */
+static unsigned int exynos_rng_copy_random(struct exynos_rng_dev *rng,
+					   u8 *dst, unsigned int dlen)
+{
+	unsigned int cnt = 0;
+	int i, j;
+	u32 val;
+
+	for (j = 0; j < EXYNOS_RNG_SEED_REGS; j++) {
+		val = exynos_rng_readl(rng, EXYNOS_RNG_OUT(j));
+
+		for (i = 0; i < 4; i++) {
+			dst[cnt] = val & 0xff;
+			val >>= 8;
+			if (++cnt >= dlen)
+				return cnt;
+		}
+	}
+
+	return cnt;
+}
+
+/*
+ * Start the engine and poll for finish.  Then read from output registers
+ * filling the 'dst' buffer up to 'dlen' bytes or up to size of generated
+ * random data (EXYNOS_RNG_SEED_SIZE).
+ *
+ * On success: return 0 and store number of read bytes under 'read' address.
+ * On error: return -ERRNO.
+ */
+static int exynos_rng_get_random(struct exynos_rng_dev *rng,
+				 u8 *dst, unsigned int dlen,
+				 unsigned int *read)
+{
+	int retry = EXYNOS_RNG_WAIT_RETRIES;
+
+	exynos_rng_writel(rng, EXYNOS_RNG_CONTROL_START,
+			  EXYNOS_RNG_CONTROL);
+
+	while (!(exynos_rng_readl(rng,
+			EXYNOS_RNG_STATUS) & EXYNOS_RNG_STATUS_RNG_DONE) && --retry)
+		cpu_relax();
+
+	if (!retry)
+		return -ETIMEDOUT;
+
+	/* Clear status bit */
+	exynos_rng_writel(rng, EXYNOS_RNG_STATUS_RNG_DONE,
+			  EXYNOS_RNG_STATUS);
+	*read = exynos_rng_copy_random(rng, dst, dlen);
+
+	return 0;
+}
+
+/* Re-seed itself from time to time */
+static void exynos_rng_reseed(struct exynos_rng_dev *rng)
+{
+	unsigned long next_seeding = rng->last_seeding + \
+				     msecs_to_jiffies(EXYNOS_RNG_RESEED_TIME);
+	unsigned long now = jiffies;
+	unsigned int read = 0;
+	u8 seed[EXYNOS_RNG_SEED_SIZE];
+
+	if (time_before(now, next_seeding))
+		return;
+
+	if (exynos_rng_get_random(rng, seed, sizeof(seed), &read))
+		return;
+
+	exynos_rng_set_seed(rng, seed, read);
+}
+
+static int exynos_rng_generate(struct crypto_rng *tfm,
+			       const u8 *src, unsigned int slen,
+			       u8 *dst, unsigned int dlen)
+{
+	struct exynos_rng_ctx *ctx = crypto_rng_ctx(tfm);
+	struct exynos_rng_dev *rng = ctx->rng;
+	unsigned int read = 0;
+	int ret;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	do {
+		ret = exynos_rng_get_random(rng, dst, dlen, &read);
+		if (ret)
+			break;
+
+		dlen -= read;
+		dst += read;
+
+		exynos_rng_reseed(rng);
+	} while (dlen > 0);
+
+	clk_disable_unprepare(rng->clk);
+
+	return ret;
+}
+
+static int exynos_rng_seed(struct crypto_rng *tfm, const u8 *seed,
+			   unsigned int slen)
+{
+	struct exynos_rng_ctx *ctx = crypto_rng_ctx(tfm);
+	struct exynos_rng_dev *rng = ctx->rng;
+	int ret;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	ret = exynos_rng_set_seed(ctx->rng, seed, slen);
+
+	clk_disable_unprepare(rng->clk);
+
+	return ret;
+}
+
+static int exynos_rng_kcapi_init(struct crypto_tfm *tfm)
+{
+	struct exynos_rng_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->rng = exynos_rng_dev;
+
+	return 0;
+}
+
+static struct rng_alg exynos_rng_alg = {
+	.generate		= exynos_rng_generate,
+	.seed			= exynos_rng_seed,
+	.seedsize		= EXYNOS_RNG_SEED_SIZE,
+	.base			= {
+		.cra_name		= "stdrng",
+		.cra_driver_name	= "exynos_rng",
+		.cra_priority		= 100,
+		.cra_ctxsize		= sizeof(struct exynos_rng_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= exynos_rng_kcapi_init,
+	}
+};
+
+static int exynos_rng_probe(struct platform_device *pdev)
+{
+	struct exynos_rng_dev *rng;
+	struct resource *res;
+	int ret;
+
+	if (exynos_rng_dev)
+		return -EEXIST;
+
+	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
+	if (!rng)
+		return -ENOMEM;
+
+	rng->dev = &pdev->dev;
+	rng->clk = devm_clk_get(&pdev->dev, "secss");
+	if (IS_ERR(rng->clk)) {
+		dev_err(&pdev->dev, "Couldn't get clock.\n");
+		return PTR_ERR(rng->clk);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rng->mem = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rng->mem))
+		return PTR_ERR(rng->mem);
+
+	platform_set_drvdata(pdev, rng);
+
+	exynos_rng_dev = rng;
+
+	ret = crypto_register_rng(&exynos_rng_alg);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Couldn't register rng crypto alg: %d\n", ret);
+		exynos_rng_dev = NULL;
+	}
+
+	return ret;
+}
+
+static int exynos_rng_remove(struct platform_device *pdev)
+{
+	crypto_unregister_rng(&exynos_rng_alg);
+
+	exynos_rng_dev = NULL;
+
+	return 0;
+}
+
+static int __maybe_unused exynos_rng_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct exynos_rng_dev *rng = platform_get_drvdata(pdev);
+	int ret;
+
+	/* If we were never seeded then after resume it will be the same */
+	if (!rng->last_seeding)
+		return 0;
+
+	rng->seed_save_len = 0;
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	/* Get new random numbers and store them for seeding on resume. */
+	exynos_rng_get_random(rng, rng->seed_save, sizeof(rng->seed_save),
+			      &(rng->seed_save_len));
+	dev_dbg(rng->dev, "Stored %u bytes for seeding on system resume\n",
+		rng->seed_save_len);
+
+	clk_disable_unprepare(rng->clk);
+
+	return 0;
+}
+
+static int __maybe_unused exynos_rng_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct exynos_rng_dev *rng = platform_get_drvdata(pdev);
+	int ret;
+
+	/* Never seeded so nothing to do */
+	if (!rng->last_seeding)
+		return 0;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	ret = exynos_rng_set_seed(rng, rng->seed_save, rng->seed_save_len);
+
+	clk_disable_unprepare(rng->clk);
+
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(exynos_rng_pm_ops, exynos_rng_suspend,
+			 exynos_rng_resume);
+
+static const struct of_device_id exynos_rng_dt_match[] = {
+	{
+		.compatible = "samsung,exynos4-rng",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, exynos_rng_dt_match);
+
+static struct platform_driver exynos_rng_driver = {
+	.driver		= {
+		.name	= "exynos-rng",
+		.pm	= &exynos_rng_pm_ops,
+		.of_match_table = exynos_rng_dt_match,
+	},
+	.probe		= exynos_rng_probe,
+	.remove		= exynos_rng_remove,
+};
+
+module_platform_driver(exynos_rng_driver);
+
+MODULE_DESCRIPTION("Exynos H/W Random Number Generator driver");
+MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 7868765a70c5..771dd26c7076 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -806,7 +806,7 @@ static struct buffer_desc *chainup_buffers(struct device *dev,
 		void *ptr;
 
 		nbytes -= len;
-		ptr = page_address(sg_page(sg)) + sg->offset;
+		ptr = sg_virt(sg);
 		next_buf = dma_pool_alloc(buffer_pool, flags, &next_buf_phys);
 		if (!next_buf) {
 			buf = NULL;
diff --git a/drivers/crypto/mediatek/mtk-aes.c b/drivers/crypto/mediatek/mtk-aes.c
index 3a47cdb8f0c8..9e845e866dec 100644
--- a/drivers/crypto/mediatek/mtk-aes.c
+++ b/drivers/crypto/mediatek/mtk-aes.c
@@ -19,13 +19,10 @@
 #define AES_BUF_ORDER		2
 #define AES_BUF_SIZE		((PAGE_SIZE << AES_BUF_ORDER) \
 				& ~(AES_BLOCK_SIZE - 1))
+#define AES_MAX_STATE_BUF_SIZE	SIZE_IN_WORDS(AES_KEYSIZE_256 + \
+				AES_BLOCK_SIZE * 2)
+#define AES_MAX_CT_SIZE		6
 
-/* AES command token size */
-#define AES_CT_SIZE_ECB		2
-#define AES_CT_SIZE_CBC		3
-#define AES_CT_SIZE_CTR		3
-#define AES_CT_SIZE_GCM_OUT	5
-#define AES_CT_SIZE_GCM_IN	6
 #define AES_CT_CTRL_HDR		cpu_to_le32(0x00220000)
 
 /* AES-CBC/ECB/CTR command token */
@@ -50,6 +47,8 @@
 #define AES_TFM_128BITS		cpu_to_le32(0xb << 16)
 #define AES_TFM_192BITS		cpu_to_le32(0xd << 16)
 #define AES_TFM_256BITS		cpu_to_le32(0xf << 16)
+#define AES_TFM_GHASH_DIGEST	cpu_to_le32(0x2 << 21)
+#define AES_TFM_GHASH		cpu_to_le32(0x4 << 23)
 /* AES transform information word 1 fields */
 #define AES_TFM_ECB		cpu_to_le32(0x0 << 0)
 #define AES_TFM_CBC		cpu_to_le32(0x1 << 0)
@@ -59,10 +58,9 @@
 #define AES_TFM_FULL_IV		cpu_to_le32(0xf << 5)	/* using IV 0-3 */
 #define AES_TFM_IV_CTR_MODE	cpu_to_le32(0x1 << 10)
 #define AES_TFM_ENC_HASH	cpu_to_le32(0x1 << 17)
-#define AES_TFM_GHASH_DIG	cpu_to_le32(0x2 << 21)
-#define AES_TFM_GHASH		cpu_to_le32(0x4 << 23)
 
 /* AES flags */
+#define AES_FLAGS_CIPHER_MSK	GENMASK(2, 0)
 #define AES_FLAGS_ECB		BIT(0)
 #define AES_FLAGS_CBC		BIT(1)
 #define AES_FLAGS_CTR		BIT(2)
@@ -70,19 +68,15 @@
 #define AES_FLAGS_ENCRYPT	BIT(4)
 #define AES_FLAGS_BUSY		BIT(5)
 
+#define AES_AUTH_TAG_ERR	cpu_to_le32(BIT(26))
+
 /**
- * Command token(CT) is a set of hardware instructions that
- * are used to control engine's processing flow of AES.
- *
- * Transform information(TFM) is used to define AES state and
- * contains all keys and initial vectors.
- *
- * The engine requires CT and TFM to do:
- * - Commands decoding and control of the engine's data path.
- * - Coordinating hardware data fetch and store operations.
- * - Result token construction and output.
+ * mtk_aes_info - hardware information of AES
+ * @cmd:	command token, hardware instruction
+ * @tfm:	transform state of cipher algorithm.
+ * @state:	contains keys and initial vectors.
  *
- * Memory map of GCM's TFM:
+ * Memory layout of GCM buffer:
  * /-----------\
  * |  AES KEY  | 128/196/256 bits
  * |-----------|
@@ -90,14 +84,16 @@
  * |-----------|
  * |    IVs    | 4 * 4 bytes
  * \-----------/
+ *
+ * The engine requires all these info to do:
+ * - Commands decoding and control of the engine's data path.
+ * - Coordinating hardware data fetch and store operations.
+ * - Result token construction and output.
  */
-struct mtk_aes_ct {
-	__le32 cmd[AES_CT_SIZE_GCM_IN];
-};
-
-struct mtk_aes_tfm {
-	__le32 ctrl[2];
-	__le32 state[SIZE_IN_WORDS(AES_KEYSIZE_256 + AES_BLOCK_SIZE * 2)];
+struct mtk_aes_info {
+	__le32 cmd[AES_MAX_CT_SIZE];
+	__le32 tfm[2];
+	__le32 state[AES_MAX_STATE_BUF_SIZE];
 };
 
 struct mtk_aes_reqctx {
@@ -107,11 +103,12 @@ struct mtk_aes_reqctx {
 struct mtk_aes_base_ctx {
 	struct mtk_cryp *cryp;
 	u32 keylen;
+	__le32 keymode;
+
 	mtk_aes_fn start;
 
-	struct mtk_aes_ct ct;
+	struct mtk_aes_info info;
 	dma_addr_t ct_dma;
-	struct mtk_aes_tfm tfm;
 	dma_addr_t tfm_dma;
 
 	__le32 ct_hdr;
@@ -248,6 +245,33 @@ static inline void mtk_aes_restore_sg(const struct mtk_aes_dma *dma)
 	sg->length += dma->remainder;
 }
 
+static inline void mtk_aes_write_state_le(__le32 *dst, const u32 *src, u32 size)
+{
+	int i;
+
+	for (i = 0; i < SIZE_IN_WORDS(size); i++)
+		dst[i] = cpu_to_le32(src[i]);
+}
+
+static inline void mtk_aes_write_state_be(__be32 *dst, const u32 *src, u32 size)
+{
+	int i;
+
+	for (i = 0; i < SIZE_IN_WORDS(size); i++)
+		dst[i] = cpu_to_be32(src[i]);
+}
+
+static inline int mtk_aes_complete(struct mtk_cryp *cryp,
+				   struct mtk_aes_rec *aes,
+				   int err)
+{
+	aes->flags &= ~AES_FLAGS_BUSY;
+	aes->areq->complete(aes->areq, err);
+	/* Handle new request */
+	tasklet_schedule(&aes->queue_task);
+	return err;
+}
+
 /*
  * Write descriptors for processing. This will configure the engine, load
  * the transform information and then start the packet processing.
@@ -262,7 +286,7 @@ static int mtk_aes_xmit(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 
 	/* Write command descriptors */
 	for (nents = 0; nents < slen; ++nents, ssg = sg_next(ssg)) {
-		cmd = ring->cmd_base + ring->cmd_pos;
+		cmd = ring->cmd_next;
 		cmd->hdr = MTK_DESC_BUF_LEN(ssg->length);
 		cmd->buf = cpu_to_le32(sg_dma_address(ssg));
 
@@ -274,25 +298,30 @@ static int mtk_aes_xmit(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 			cmd->tfm = cpu_to_le32(aes->ctx->tfm_dma);
 		}
 
-		if (++ring->cmd_pos == MTK_DESC_NUM)
-			ring->cmd_pos = 0;
+		/* Shift ring buffer and check boundary */
+		if (++ring->cmd_next == ring->cmd_base + MTK_DESC_NUM)
+			ring->cmd_next = ring->cmd_base;
 	}
 	cmd->hdr |= MTK_DESC_LAST;
 
 	/* Prepare result descriptors */
 	for (nents = 0; nents < dlen; ++nents, dsg = sg_next(dsg)) {
-		res = ring->res_base + ring->res_pos;
+		res = ring->res_next;
 		res->hdr = MTK_DESC_BUF_LEN(dsg->length);
 		res->buf = cpu_to_le32(sg_dma_address(dsg));
 
 		if (nents == 0)
 			res->hdr |= MTK_DESC_FIRST;
 
-		if (++ring->res_pos == MTK_DESC_NUM)
-			ring->res_pos = 0;
+		/* Shift ring buffer and check boundary */
+		if (++ring->res_next == ring->res_base + MTK_DESC_NUM)
+			ring->res_next = ring->res_base;
 	}
 	res->hdr |= MTK_DESC_LAST;
 
+	/* Pointer to current result descriptor */
+	ring->res_prev = res;
+
 	/* Prepare enough space for authenticated tag */
 	if (aes->flags & AES_FLAGS_GCM)
 		res->hdr += AES_BLOCK_SIZE;
@@ -313,9 +342,7 @@ static void mtk_aes_unmap(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 {
 	struct mtk_aes_base_ctx *ctx = aes->ctx;
 
-	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(ctx->ct),
-			 DMA_TO_DEVICE);
-	dma_unmap_single(cryp->dev, ctx->tfm_dma, sizeof(ctx->tfm),
+	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(ctx->info),
 			 DMA_TO_DEVICE);
 
 	if (aes->src.sg == aes->dst.sg) {
@@ -346,16 +373,14 @@ static void mtk_aes_unmap(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 static int mtk_aes_map(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 {
 	struct mtk_aes_base_ctx *ctx = aes->ctx;
+	struct mtk_aes_info *info = &ctx->info;
 
-	ctx->ct_dma = dma_map_single(cryp->dev, &ctx->ct, sizeof(ctx->ct),
+	ctx->ct_dma = dma_map_single(cryp->dev, info, sizeof(*info),
 				     DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(cryp->dev, ctx->ct_dma)))
-		return -EINVAL;
+		goto exit;
 
-	ctx->tfm_dma = dma_map_single(cryp->dev, &ctx->tfm, sizeof(ctx->tfm),
-				      DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(cryp->dev, ctx->tfm_dma)))
-		goto tfm_map_err;
+	ctx->tfm_dma = ctx->ct_dma + sizeof(info->cmd);
 
 	if (aes->src.sg == aes->dst.sg) {
 		aes->src.sg_len = dma_map_sg(cryp->dev, aes->src.sg,
@@ -382,13 +407,9 @@ static int mtk_aes_map(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 	return mtk_aes_xmit(cryp, aes);
 
 sg_map_err:
-	dma_unmap_single(cryp->dev, ctx->tfm_dma, sizeof(ctx->tfm),
-			 DMA_TO_DEVICE);
-tfm_map_err:
-	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(ctx->ct),
-			 DMA_TO_DEVICE);
-
-	return -EINVAL;
+	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(*info), DMA_TO_DEVICE);
+exit:
+	return mtk_aes_complete(cryp, aes, -EINVAL);
 }
 
 /* Initialize transform information of CBC/ECB/CTR mode */
@@ -397,50 +418,43 @@ static void mtk_aes_info_init(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
 {
 	struct ablkcipher_request *req = ablkcipher_request_cast(aes->areq);
 	struct mtk_aes_base_ctx *ctx = aes->ctx;
+	struct mtk_aes_info *info = &ctx->info;
+	u32 cnt = 0;
 
 	ctx->ct_hdr = AES_CT_CTRL_HDR | cpu_to_le32(len);
-	ctx->ct.cmd[0] = AES_CMD0 | cpu_to_le32(len);
-	ctx->ct.cmd[1] = AES_CMD1;
+	info->cmd[cnt++] = AES_CMD0 | cpu_to_le32(len);
+	info->cmd[cnt++] = AES_CMD1;
 
+	info->tfm[0] = AES_TFM_SIZE(ctx->keylen) | ctx->keymode;
 	if (aes->flags & AES_FLAGS_ENCRYPT)
-		ctx->tfm.ctrl[0] = AES_TFM_BASIC_OUT;
+		info->tfm[0] |= AES_TFM_BASIC_OUT;
 	else
-		ctx->tfm.ctrl[0] = AES_TFM_BASIC_IN;
+		info->tfm[0] |= AES_TFM_BASIC_IN;
 
-	if (ctx->keylen == SIZE_IN_WORDS(AES_KEYSIZE_128))
-		ctx->tfm.ctrl[0] |= AES_TFM_128BITS;
-	else if (ctx->keylen == SIZE_IN_WORDS(AES_KEYSIZE_256))
-		ctx->tfm.ctrl[0] |= AES_TFM_256BITS;
-	else
-		ctx->tfm.ctrl[0] |= AES_TFM_192BITS;
-
-	if (aes->flags & AES_FLAGS_CBC) {
-		const u32 *iv = (const u32 *)req->info;
-		u32 *iv_state = ctx->tfm.state + ctx->keylen;
-		int i;
-
-		ctx->tfm.ctrl[0] |= AES_TFM_SIZE(ctx->keylen +
-				    SIZE_IN_WORDS(AES_BLOCK_SIZE));
-		ctx->tfm.ctrl[1] = AES_TFM_CBC | AES_TFM_FULL_IV;
-
-		for (i = 0; i < SIZE_IN_WORDS(AES_BLOCK_SIZE); i++)
-			iv_state[i] = cpu_to_le32(iv[i]);
-
-		ctx->ct.cmd[2] = AES_CMD2;
-		ctx->ct_size = AES_CT_SIZE_CBC;
-	} else if (aes->flags & AES_FLAGS_ECB) {
-		ctx->tfm.ctrl[0] |= AES_TFM_SIZE(ctx->keylen);
-		ctx->tfm.ctrl[1] = AES_TFM_ECB;
-
-		ctx->ct_size = AES_CT_SIZE_ECB;
-	} else if (aes->flags & AES_FLAGS_CTR) {
-		ctx->tfm.ctrl[0] |= AES_TFM_SIZE(ctx->keylen +
-				    SIZE_IN_WORDS(AES_BLOCK_SIZE));
-		ctx->tfm.ctrl[1] = AES_TFM_CTR_LOAD | AES_TFM_FULL_IV;
-
-		ctx->ct.cmd[2] = AES_CMD2;
-		ctx->ct_size = AES_CT_SIZE_CTR;
+	switch (aes->flags & AES_FLAGS_CIPHER_MSK) {
+	case AES_FLAGS_CBC:
+		info->tfm[1] = AES_TFM_CBC;
+		break;
+	case AES_FLAGS_ECB:
+		info->tfm[1] = AES_TFM_ECB;
+		goto ecb;
+	case AES_FLAGS_CTR:
+		info->tfm[1] = AES_TFM_CTR_LOAD;
+		goto ctr;
+
+	default:
+		/* Should not happen... */
+		return;
 	}
+
+	mtk_aes_write_state_le(info->state + ctx->keylen, req->info,
+			       AES_BLOCK_SIZE);
+ctr:
+	info->tfm[0] += AES_TFM_SIZE(SIZE_IN_WORDS(AES_BLOCK_SIZE));
+	info->tfm[1] |= AES_TFM_FULL_IV;
+	info->cmd[cnt++] = AES_CMD2;
+ecb:
+	ctx->ct_size = cnt;
 }
 
 static int mtk_aes_dma(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
@@ -465,7 +479,7 @@ static int mtk_aes_dma(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
 		padlen = mtk_aes_padlen(len);
 
 		if (len + padlen > AES_BUF_SIZE)
-			return -ENOMEM;
+			return mtk_aes_complete(cryp, aes, -ENOMEM);
 
 		if (!src_aligned) {
 			sg_copy_to_buffer(src, sg_nents(src), aes->buf, len);
@@ -525,13 +539,10 @@ static int mtk_aes_handle_queue(struct mtk_cryp *cryp, u8 id,
 	return ctx->start(cryp, aes);
 }
 
-static int mtk_aes_complete(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
+static int mtk_aes_transfer_complete(struct mtk_cryp *cryp,
+				     struct mtk_aes_rec *aes)
 {
-	aes->flags &= ~AES_FLAGS_BUSY;
-	aes->areq->complete(aes->areq, 0);
-
-	/* Handle new request */
-	return mtk_aes_handle_queue(cryp, aes->id, NULL);
+	return mtk_aes_complete(cryp, aes, 0);
 }
 
 static int mtk_aes_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
@@ -540,7 +551,7 @@ static int mtk_aes_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 	struct mtk_aes_reqctx *rctx = ablkcipher_request_ctx(req);
 
 	mtk_aes_set_mode(aes, rctx);
-	aes->resume = mtk_aes_complete;
+	aes->resume = mtk_aes_transfer_complete;
 
 	return mtk_aes_dma(cryp, aes, req->src, req->dst, req->nbytes);
 }
@@ -557,15 +568,14 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 	struct mtk_aes_ctr_ctx *cctx = mtk_aes_ctr_ctx_cast(ctx);
 	struct ablkcipher_request *req = ablkcipher_request_cast(aes->areq);
 	struct scatterlist *src, *dst;
-	int i;
-	u32 start, end, ctr, blocks, *iv_state;
+	u32 start, end, ctr, blocks;
 	size_t datalen;
 	bool fragmented = false;
 
 	/* Check for transfer completion. */
 	cctx->offset += aes->total;
 	if (cctx->offset >= req->nbytes)
-		return mtk_aes_complete(cryp, aes);
+		return mtk_aes_transfer_complete(cryp, aes);
 
 	/* Compute data length. */
 	datalen = req->nbytes - cctx->offset;
@@ -587,9 +597,8 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 	       scatterwalk_ffwd(cctx->dst, req->dst, cctx->offset));
 
 	/* Write IVs into transform state buffer. */
-	iv_state = ctx->tfm.state + ctx->keylen;
-	for (i = 0; i < SIZE_IN_WORDS(AES_BLOCK_SIZE); i++)
-		iv_state[i] = cpu_to_le32(cctx->iv[i]);
+	mtk_aes_write_state_le(ctx->info.state + ctx->keylen, cctx->iv,
+			       AES_BLOCK_SIZE);
 
 	if (unlikely(fragmented)) {
 	/*
@@ -599,7 +608,6 @@ static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 		cctx->iv[3] = cpu_to_be32(ctr);
 		crypto_inc((u8 *)cctx->iv, AES_BLOCK_SIZE);
 	}
-	aes->resume = mtk_aes_ctr_transfer;
 
 	return mtk_aes_dma(cryp, aes, src, dst, datalen);
 }
@@ -615,6 +623,7 @@ static int mtk_aes_ctr_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 	memcpy(cctx->iv, req->info, AES_BLOCK_SIZE);
 	cctx->offset = 0;
 	aes->total = 0;
+	aes->resume = mtk_aes_ctr_transfer;
 
 	return mtk_aes_ctr_transfer(cryp, aes);
 }
@@ -624,21 +633,25 @@ static int mtk_aes_setkey(struct crypto_ablkcipher *tfm,
 			  const u8 *key, u32 keylen)
 {
 	struct mtk_aes_base_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	const u32 *aes_key = (const u32 *)key;
-	u32 *key_state = ctx->tfm.state;
-	int i;
 
-	if (keylen != AES_KEYSIZE_128 &&
-	    keylen != AES_KEYSIZE_192 &&
-	    keylen != AES_KEYSIZE_256) {
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		ctx->keymode = AES_TFM_128BITS;
+		break;
+	case AES_KEYSIZE_192:
+		ctx->keymode = AES_TFM_192BITS;
+		break;
+	case AES_KEYSIZE_256:
+		ctx->keymode = AES_TFM_256BITS;
+		break;
+
+	default:
 		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
 	ctx->keylen = SIZE_IN_WORDS(keylen);
-
-	for (i = 0; i < ctx->keylen; i++)
-		key_state[i] = cpu_to_le32(aes_key[i]);
+	mtk_aes_write_state_le(ctx->info.state, (const u32 *)key, keylen);
 
 	return 0;
 }
@@ -789,6 +802,19 @@ mtk_aes_gcm_ctx_cast(struct mtk_aes_base_ctx *ctx)
 	return container_of(ctx, struct mtk_aes_gcm_ctx, base);
 }
 
+/*
+ * Engine will verify and compare tag automatically, so we just need
+ * to check returned status which stored in the result descriptor.
+ */
+static int mtk_aes_gcm_tag_verify(struct mtk_cryp *cryp,
+				  struct mtk_aes_rec *aes)
+{
+	u32 status = cryp->ring[aes->id]->res_prev->ct;
+
+	return mtk_aes_complete(cryp, aes, (status & AES_AUTH_TAG_ERR) ?
+				-EBADMSG : 0);
+}
+
 /* Initialize transform information of GCM mode */
 static void mtk_aes_gcm_info_init(struct mtk_cryp *cryp,
 				  struct mtk_aes_rec *aes,
@@ -797,45 +823,35 @@ static void mtk_aes_gcm_info_init(struct mtk_cryp *cryp,
 	struct aead_request *req = aead_request_cast(aes->areq);
 	struct mtk_aes_base_ctx *ctx = aes->ctx;
 	struct mtk_aes_gcm_ctx *gctx = mtk_aes_gcm_ctx_cast(ctx);
-	const u32 *iv = (const u32 *)req->iv;
-	u32 *iv_state = ctx->tfm.state + ctx->keylen +
-			SIZE_IN_WORDS(AES_BLOCK_SIZE);
+	struct mtk_aes_info *info = &ctx->info;
 	u32 ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(req));
-	int i;
+	u32 cnt = 0;
 
 	ctx->ct_hdr = AES_CT_CTRL_HDR | len;
 
-	ctx->ct.cmd[0] = AES_GCM_CMD0 | cpu_to_le32(req->assoclen);
-	ctx->ct.cmd[1] = AES_GCM_CMD1 | cpu_to_le32(req->assoclen);
-	ctx->ct.cmd[2] = AES_GCM_CMD2;
-	ctx->ct.cmd[3] = AES_GCM_CMD3 | cpu_to_le32(gctx->textlen);
+	info->cmd[cnt++] = AES_GCM_CMD0 | cpu_to_le32(req->assoclen);
+	info->cmd[cnt++] = AES_GCM_CMD1 | cpu_to_le32(req->assoclen);
+	info->cmd[cnt++] = AES_GCM_CMD2;
+	info->cmd[cnt++] = AES_GCM_CMD3 | cpu_to_le32(gctx->textlen);
 
 	if (aes->flags & AES_FLAGS_ENCRYPT) {
-		ctx->ct.cmd[4] = AES_GCM_CMD4 | cpu_to_le32(gctx->authsize);
-		ctx->ct_size = AES_CT_SIZE_GCM_OUT;
-		ctx->tfm.ctrl[0] = AES_TFM_GCM_OUT;
+		info->cmd[cnt++] = AES_GCM_CMD4 | cpu_to_le32(gctx->authsize);
+		info->tfm[0] = AES_TFM_GCM_OUT;
 	} else {
-		ctx->ct.cmd[4] = AES_GCM_CMD5 | cpu_to_le32(gctx->authsize);
-		ctx->ct.cmd[5] = AES_GCM_CMD6 | cpu_to_le32(gctx->authsize);
-		ctx->ct_size = AES_CT_SIZE_GCM_IN;
-		ctx->tfm.ctrl[0] = AES_TFM_GCM_IN;
+		info->cmd[cnt++] = AES_GCM_CMD5 | cpu_to_le32(gctx->authsize);
+		info->cmd[cnt++] = AES_GCM_CMD6 | cpu_to_le32(gctx->authsize);
+		info->tfm[0] = AES_TFM_GCM_IN;
 	}
+	ctx->ct_size = cnt;
 
-	if (ctx->keylen == SIZE_IN_WORDS(AES_KEYSIZE_128))
-		ctx->tfm.ctrl[0] |= AES_TFM_128BITS;
-	else if (ctx->keylen == SIZE_IN_WORDS(AES_KEYSIZE_256))
-		ctx->tfm.ctrl[0] |= AES_TFM_256BITS;
-	else
-		ctx->tfm.ctrl[0] |= AES_TFM_192BITS;
+	info->tfm[0] |= AES_TFM_GHASH_DIGEST | AES_TFM_GHASH | AES_TFM_SIZE(
+			ctx->keylen + SIZE_IN_WORDS(AES_BLOCK_SIZE + ivsize)) |
+			ctx->keymode;
+	info->tfm[1] = AES_TFM_CTR_INIT | AES_TFM_IV_CTR_MODE | AES_TFM_3IV |
+		       AES_TFM_ENC_HASH;
 
-	ctx->tfm.ctrl[0] |= AES_TFM_GHASH_DIG | AES_TFM_GHASH |
-			    AES_TFM_SIZE(ctx->keylen + SIZE_IN_WORDS(
-			    AES_BLOCK_SIZE + ivsize));
-	ctx->tfm.ctrl[1] = AES_TFM_CTR_INIT | AES_TFM_IV_CTR_MODE |
-			   AES_TFM_3IV | AES_TFM_ENC_HASH;
-
-	for (i = 0; i < SIZE_IN_WORDS(ivsize); i++)
-		iv_state[i] = cpu_to_le32(iv[i]);
+	mtk_aes_write_state_le(info->state + ctx->keylen + SIZE_IN_WORDS(
+			       AES_BLOCK_SIZE), (const u32 *)req->iv, ivsize);
 }
 
 static int mtk_aes_gcm_dma(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
@@ -856,7 +872,7 @@ static int mtk_aes_gcm_dma(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
 
 	if (!src_aligned || !dst_aligned) {
 		if (aes->total > AES_BUF_SIZE)
-			return -ENOMEM;
+			return mtk_aes_complete(cryp, aes, -ENOMEM);
 
 		if (!src_aligned) {
 			sg_copy_to_buffer(src, sg_nents(src), aes->buf, len);
@@ -892,6 +908,8 @@ static int mtk_aes_gcm_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 
 	if (aes->flags & AES_FLAGS_ENCRYPT) {
 		u32 tag[4];
+
+		aes->resume = mtk_aes_transfer_complete;
 		/* Compute total process length. */
 		aes->total = len + gctx->authsize;
 		/* Compute text length. */
@@ -899,10 +917,10 @@ static int mtk_aes_gcm_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
 		/* Hardware will append authenticated tag to output buffer */
 		scatterwalk_map_and_copy(tag, req->dst, len, gctx->authsize, 1);
 	} else {
+		aes->resume = mtk_aes_gcm_tag_verify;
 		aes->total = len;
 		gctx->textlen = req->cryptlen - gctx->authsize;
 	}
-	aes->resume = mtk_aes_complete;
 
 	return mtk_aes_gcm_dma(cryp, aes, req->src, req->dst, len);
 }
@@ -915,7 +933,7 @@ static int mtk_aes_gcm_crypt(struct aead_request *req, u64 mode)
 	rctx->mode = AES_FLAGS_GCM | mode;
 
 	return mtk_aes_handle_queue(ctx->cryp, !!(mode & AES_FLAGS_ENCRYPT),
-								&req->base);
+				    &req->base);
 }
 
 static void mtk_gcm_setkey_done(struct crypto_async_request *req, int err)
@@ -949,24 +967,26 @@ static int mtk_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 		struct scatterlist sg[1];
 		struct skcipher_request req;
 	} *data;
-	const u32 *aes_key;
-	u32 *key_state, *hash_state;
-	int err, i;
+	int err;
 
-	if (keylen != AES_KEYSIZE_256 &&
-	    keylen != AES_KEYSIZE_192 &&
-	    keylen != AES_KEYSIZE_128) {
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		ctx->keymode = AES_TFM_128BITS;
+		break;
+	case AES_KEYSIZE_192:
+		ctx->keymode = AES_TFM_192BITS;
+		break;
+	case AES_KEYSIZE_256:
+		ctx->keymode = AES_TFM_256BITS;
+		break;
+
+	default:
 		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	key_state = ctx->tfm.state;
-	aes_key = (u32 *)key;
 	ctx->keylen = SIZE_IN_WORDS(keylen);
 
-	for (i = 0; i < ctx->keylen; i++)
-		ctx->tfm.state[i] = cpu_to_le32(aes_key[i]);
-
 	/* Same as crypto_gcm_setkey() from crypto/gcm.c */
 	crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
 	crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
@@ -1001,10 +1021,11 @@ static int mtk_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	if (err)
 		goto out;
 
-	hash_state = key_state + ctx->keylen;
-
-	for (i = 0; i < 4; i++)
-		hash_state[i] = cpu_to_be32(data->hash[i]);
+	/* Write key into state buffer */
+	mtk_aes_write_state_le(ctx->info.state, (const u32 *)key, keylen);
+	/* Write key(H) into state buffer */
+	mtk_aes_write_state_be(ctx->info.state + ctx->keylen, data->hash,
+			       AES_BLOCK_SIZE);
 out:
 	kzfree(data);
 	return err;
@@ -1092,58 +1113,36 @@ static struct aead_alg aes_gcm_alg = {
 	},
 };
 
-static void mtk_aes_enc_task(unsigned long data)
+static void mtk_aes_queue_task(unsigned long data)
 {
-	struct mtk_cryp *cryp = (struct mtk_cryp *)data;
-	struct mtk_aes_rec *aes = cryp->aes[0];
+	struct mtk_aes_rec *aes = (struct mtk_aes_rec *)data;
 
-	mtk_aes_unmap(cryp, aes);
-	aes->resume(cryp, aes);
+	mtk_aes_handle_queue(aes->cryp, aes->id, NULL);
 }
 
-static void mtk_aes_dec_task(unsigned long data)
+static void mtk_aes_done_task(unsigned long data)
 {
-	struct mtk_cryp *cryp = (struct mtk_cryp *)data;
-	struct mtk_aes_rec *aes = cryp->aes[1];
+	struct mtk_aes_rec *aes = (struct mtk_aes_rec *)data;
+	struct mtk_cryp *cryp = aes->cryp;
 
 	mtk_aes_unmap(cryp, aes);
 	aes->resume(cryp, aes);
 }
 
-static irqreturn_t mtk_aes_enc_irq(int irq, void *dev_id)
+static irqreturn_t mtk_aes_irq(int irq, void *dev_id)
 {
-	struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
-	struct mtk_aes_rec *aes = cryp->aes[0];
-	u32 val = mtk_aes_read(cryp, RDR_STAT(RING0));
+	struct mtk_aes_rec *aes  = (struct mtk_aes_rec *)dev_id;
+	struct mtk_cryp *cryp = aes->cryp;
+	u32 val = mtk_aes_read(cryp, RDR_STAT(aes->id));
 
-	mtk_aes_write(cryp, RDR_STAT(RING0), val);
+	mtk_aes_write(cryp, RDR_STAT(aes->id), val);
 
 	if (likely(AES_FLAGS_BUSY & aes->flags)) {
-		mtk_aes_write(cryp, RDR_PROC_COUNT(RING0), MTK_CNT_RST);
-		mtk_aes_write(cryp, RDR_THRESH(RING0),
+		mtk_aes_write(cryp, RDR_PROC_COUNT(aes->id), MTK_CNT_RST);
+		mtk_aes_write(cryp, RDR_THRESH(aes->id),
 			      MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE);
 
-		tasklet_schedule(&aes->task);
-	} else {
-		dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
-	}
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t mtk_aes_dec_irq(int irq, void *dev_id)
-{
-	struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
-	struct mtk_aes_rec *aes = cryp->aes[1];
-	u32 val = mtk_aes_read(cryp, RDR_STAT(RING1));
-
-	mtk_aes_write(cryp, RDR_STAT(RING1), val);
-
-	if (likely(AES_FLAGS_BUSY & aes->flags)) {
-		mtk_aes_write(cryp, RDR_PROC_COUNT(RING1), MTK_CNT_RST);
-		mtk_aes_write(cryp, RDR_THRESH(RING1),
-			      MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE);
-
-		tasklet_schedule(&aes->task);
+		tasklet_schedule(&aes->done_task);
 	} else {
 		dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
 	}
@@ -1171,14 +1170,20 @@ static int mtk_aes_record_init(struct mtk_cryp *cryp)
 		if (!aes[i]->buf)
 			goto err_cleanup;
 
-		aes[i]->id = i;
+		aes[i]->cryp = cryp;
 
 		spin_lock_init(&aes[i]->lock);
 		crypto_init_queue(&aes[i]->queue, AES_QUEUE_SIZE);
+
+		tasklet_init(&aes[i]->queue_task, mtk_aes_queue_task,
+			     (unsigned long)aes[i]);
+		tasklet_init(&aes[i]->done_task, mtk_aes_done_task,
+			     (unsigned long)aes[i]);
 	}
 
-	tasklet_init(&aes[0]->task, mtk_aes_enc_task, (unsigned long)cryp);
-	tasklet_init(&aes[1]->task, mtk_aes_dec_task, (unsigned long)cryp);
+	/* Link to ring0 and ring1 respectively */
+	aes[0]->id = MTK_RING0;
+	aes[1]->id = MTK_RING1;
 
 	return 0;
 
@@ -1196,7 +1201,9 @@ static void mtk_aes_record_free(struct mtk_cryp *cryp)
 	int i;
 
 	for (i = 0; i < MTK_REC_NUM; i++) {
-		tasklet_kill(&cryp->aes[i]->task);
+		tasklet_kill(&cryp->aes[i]->done_task);
+		tasklet_kill(&cryp->aes[i]->queue_task);
+
 		free_page((unsigned long)cryp->aes[i]->buf);
 		kfree(cryp->aes[i]);
 	}
@@ -1246,25 +1253,23 @@ int mtk_cipher_alg_register(struct mtk_cryp *cryp)
 	if (ret)
 		goto err_record;
 
-	/* Ring0 is use by encryption record */
-	ret = devm_request_irq(cryp->dev, cryp->irq[RING0], mtk_aes_enc_irq,
-			       IRQF_TRIGGER_LOW, "mtk-aes", cryp);
+	ret = devm_request_irq(cryp->dev, cryp->irq[MTK_RING0], mtk_aes_irq,
+			       0, "mtk-aes", cryp->aes[0]);
 	if (ret) {
-		dev_err(cryp->dev, "unable to request AES encryption irq.\n");
+		dev_err(cryp->dev, "unable to request AES irq.\n");
 		goto err_res;
 	}
 
-	/* Ring1 is use by decryption record */
-	ret = devm_request_irq(cryp->dev, cryp->irq[RING1], mtk_aes_dec_irq,
-			       IRQF_TRIGGER_LOW, "mtk-aes", cryp);
+	ret = devm_request_irq(cryp->dev, cryp->irq[MTK_RING1], mtk_aes_irq,
+			       0, "mtk-aes", cryp->aes[1]);
 	if (ret) {
-		dev_err(cryp->dev, "unable to request AES decryption irq.\n");
+		dev_err(cryp->dev, "unable to request AES irq.\n");
 		goto err_res;
 	}
 
 	/* Enable ring0 and ring1 interrupt */
-	mtk_aes_write(cryp, AIC_ENABLE_SET(RING0), MTK_IRQ_RDR0);
-	mtk_aes_write(cryp, AIC_ENABLE_SET(RING1), MTK_IRQ_RDR1);
+	mtk_aes_write(cryp, AIC_ENABLE_SET(MTK_RING0), MTK_IRQ_RDR0);
+	mtk_aes_write(cryp, AIC_ENABLE_SET(MTK_RING1), MTK_IRQ_RDR1);
 
 	spin_lock(&mtk_aes.lock);
 	list_add_tail(&cryp->aes_list, &mtk_aes.dev_list);
diff --git a/drivers/crypto/mediatek/mtk-platform.c b/drivers/crypto/mediatek/mtk-platform.c
index a9c713d4c733..b6ecc288b540 100644
--- a/drivers/crypto/mediatek/mtk-platform.c
+++ b/drivers/crypto/mediatek/mtk-platform.c
@@ -334,7 +334,7 @@ static int mtk_packet_engine_setup(struct mtk_cryp *cryp)
 	/* Enable the 4 rings for the packet engines. */
 	mtk_desc_ring_link(cryp, 0xf);
 
-	for (i = 0; i < RING_MAX; i++) {
+	for (i = 0; i < MTK_RING_MAX; i++) {
 		mtk_cmd_desc_ring_setup(cryp, i, &cap);
 		mtk_res_desc_ring_setup(cryp, i, &cap);
 	}
@@ -359,7 +359,7 @@ static int mtk_aic_cap_check(struct mtk_cryp *cryp, int hw)
 {
 	u32 val;
 
-	if (hw == RING_MAX)
+	if (hw == MTK_RING_MAX)
 		val = readl(cryp->base + AIC_G_VERSION);
 	else
 		val = readl(cryp->base + AIC_VERSION(hw));
@@ -368,7 +368,7 @@ static int mtk_aic_cap_check(struct mtk_cryp *cryp, int hw)
 	if (val != MTK_AIC_VER11 && val != MTK_AIC_VER12)
 		return -ENXIO;
 
-	if (hw == RING_MAX)
+	if (hw == MTK_RING_MAX)
 		val = readl(cryp->base + AIC_G_OPTIONS);
 	else
 		val = readl(cryp->base + AIC_OPTIONS(hw));
@@ -389,7 +389,7 @@ static int mtk_aic_init(struct mtk_cryp *cryp, int hw)
 		return err;
 
 	/* Disable all interrupts and set initial configuration */
-	if (hw == RING_MAX) {
+	if (hw == MTK_RING_MAX) {
 		writel(0, cryp->base + AIC_G_ENABLE_CTRL);
 		writel(0, cryp->base + AIC_G_POL_CTRL);
 		writel(0, cryp->base + AIC_G_TYPE_CTRL);
@@ -431,7 +431,7 @@ static void mtk_desc_dma_free(struct mtk_cryp *cryp)
 {
 	int i;
 
-	for (i = 0; i < RING_MAX; i++) {
+	for (i = 0; i < MTK_RING_MAX; i++) {
 		dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ,
 				  cryp->ring[i]->res_base,
 				  cryp->ring[i]->res_dma);
@@ -447,7 +447,7 @@ static int mtk_desc_ring_alloc(struct mtk_cryp *cryp)
 	struct mtk_ring **ring = cryp->ring;
 	int i, err = ENOMEM;
 
-	for (i = 0; i < RING_MAX; i++) {
+	for (i = 0; i < MTK_RING_MAX; i++) {
 		ring[i] = kzalloc(sizeof(**ring), GFP_KERNEL);
 		if (!ring[i])
 			goto err_cleanup;
@@ -465,6 +465,9 @@ static int mtk_desc_ring_alloc(struct mtk_cryp *cryp)
 					   GFP_KERNEL);
 		if (!ring[i]->res_base)
 			goto err_cleanup;
+
+		ring[i]->cmd_next = ring[i]->cmd_base;
+		ring[i]->res_next = ring[i]->res_base;
 	}
 	return 0;
 
diff --git a/drivers/crypto/mediatek/mtk-platform.h b/drivers/crypto/mediatek/mtk-platform.h
index ed6d8717f7f4..303c152dc931 100644
--- a/drivers/crypto/mediatek/mtk-platform.h
+++ b/drivers/crypto/mediatek/mtk-platform.h
@@ -38,14 +38,14 @@
  * Ring 2/3 are used by SHA.
  */
 enum {
-	RING0 = 0,
-	RING1,
-	RING2,
-	RING3,
-	RING_MAX,
+	MTK_RING0,
+	MTK_RING1,
+	MTK_RING2,
+	MTK_RING3,
+	MTK_RING_MAX
 };
 
-#define MTK_REC_NUM		(RING_MAX / 2)
+#define MTK_REC_NUM		(MTK_RING_MAX / 2)
 #define MTK_IRQ_NUM		5
 
 /**
@@ -84,11 +84,12 @@ struct mtk_desc {
 /**
  * struct mtk_ring - Descriptor ring
  * @cmd_base:	pointer to command descriptor ring base
+ * @cmd_next:	pointer to the next command descriptor
  * @cmd_dma:	DMA address of command descriptor ring
- * @cmd_pos:	current position in the command descriptor ring
  * @res_base:	pointer to result descriptor ring base
+ * @res_next:	pointer to the next result descriptor
+ * @res_prev:	pointer to the previous result descriptor
  * @res_dma:	DMA address of result descriptor ring
- * @res_pos:	current position in the result descriptor ring
  *
  * A descriptor ring is a circular buffer that is used to manage
  * one or more descriptors. There are two type of descriptor rings;
@@ -96,11 +97,12 @@ struct mtk_desc {
  */
 struct mtk_ring {
 	struct mtk_desc *cmd_base;
+	struct mtk_desc *cmd_next;
 	dma_addr_t cmd_dma;
-	u32 cmd_pos;
 	struct mtk_desc *res_base;
+	struct mtk_desc *res_next;
+	struct mtk_desc *res_prev;
 	dma_addr_t res_dma;
-	u32 res_pos;
 };
 
 /**
@@ -125,9 +127,11 @@ typedef int (*mtk_aes_fn)(struct mtk_cryp *cryp, struct mtk_aes_rec *aes);
 
 /**
  * struct mtk_aes_rec - AES operation record
+ * @cryp:	pointer to Cryptographic device
  * @queue:	crypto request queue
  * @areq:	pointer to async request
- * @task:	the tasklet is use in AES interrupt
+ * @done_task:	the tasklet is use in AES interrupt
+ * @queue_task:	the tasklet is used to dequeue request
  * @ctx:	pointer to current context
  * @src:	the structure that holds source sg list info
  * @dst:	the structure that holds destination sg list info
@@ -136,16 +140,18 @@ typedef int (*mtk_aes_fn)(struct mtk_cryp *cryp, struct mtk_aes_rec *aes);
  * @resume:	pointer to resume function
  * @total:	request buffer length
  * @buf:	pointer to page buffer
- * @id:		record identification
+ * @id:		the current use of ring
  * @flags:	it's describing AES operation state
  * @lock:	the async queue lock
  *
  * Structure used to record AES execution state.
  */
 struct mtk_aes_rec {
+	struct mtk_cryp *cryp;
 	struct crypto_queue queue;
 	struct crypto_async_request *areq;
-	struct tasklet_struct task;
+	struct tasklet_struct done_task;
+	struct tasklet_struct queue_task;
 	struct mtk_aes_base_ctx *ctx;
 	struct mtk_aes_dma src;
 	struct mtk_aes_dma dst;
@@ -166,19 +172,23 @@ struct mtk_aes_rec {
 
 /**
  * struct mtk_sha_rec - SHA operation record
+ * @cryp:	pointer to Cryptographic device
  * @queue:	crypto request queue
  * @req:	pointer to ahash request
- * @task:	the tasklet is use in SHA interrupt
- * @id:		record identification
+ * @done_task:	the tasklet is use in SHA interrupt
+ * @queue_task:	the tasklet is used to dequeue request
+ * @id:		the current use of ring
  * @flags:	it's describing SHA operation state
- * @lock:	the ablkcipher queue lock
+ * @lock:	the async queue lock
  *
  * Structure used to record SHA execution state.
  */
 struct mtk_sha_rec {
+	struct mtk_cryp *cryp;
 	struct crypto_queue queue;
 	struct ahash_request *req;
-	struct tasklet_struct task;
+	struct tasklet_struct done_task;
+	struct tasklet_struct queue_task;
 
 	u8 id;
 	unsigned long flags;
@@ -193,13 +203,11 @@ struct mtk_sha_rec {
  * @clk_ethif:	pointer to ethif clock
  * @clk_cryp:	pointer to crypto clock
  * @irq:	global system and rings IRQ
- * @ring:	pointer to execution state of AES
- * @aes:	pointer to execution state of SHA
- * @sha:	each execution record map to a ring
+ * @ring:	pointer to descriptor rings
+ * @aes:	pointer to operation record of AES
+ * @sha:	pointer to operation record of SHA
  * @aes_list:	device list of AES
  * @sha_list:	device list of SHA
- * @tmp:	pointer to temporary buffer for internal use
- * @tmp_dma:	DMA address of temporary buffer
  * @rec:	it's used to select SHA record for tfm
  *
  * Structure storing cryptographic device information.
@@ -211,15 +219,13 @@ struct mtk_cryp {
 	struct clk *clk_cryp;
 	int irq[MTK_IRQ_NUM];
 
-	struct mtk_ring *ring[RING_MAX];
+	struct mtk_ring *ring[MTK_RING_MAX];
 	struct mtk_aes_rec *aes[MTK_REC_NUM];
 	struct mtk_sha_rec *sha[MTK_REC_NUM];
 
 	struct list_head aes_list;
 	struct list_head sha_list;
 
-	void *tmp;
-	dma_addr_t tmp_dma;
 	bool rec;
 };
 
diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c
index 55e3805fba07..2226f12d1c7a 100644
--- a/drivers/crypto/mediatek/mtk-sha.c
+++ b/drivers/crypto/mediatek/mtk-sha.c
@@ -17,13 +17,13 @@
 
 #define SHA_ALIGN_MSK		(sizeof(u32) - 1)
 #define SHA_QUEUE_SIZE		512
-#define SHA_TMP_BUF_SIZE	512
 #define SHA_BUF_SIZE		((u32)PAGE_SIZE)
 
 #define SHA_OP_UPDATE		1
 #define SHA_OP_FINAL		2
 
 #define SHA_DATA_LEN_MSK	cpu_to_le32(GENMASK(16, 0))
+#define SHA_MAX_DIGEST_BUF_SIZE	32
 
 /* SHA command token */
 #define SHA_CT_SIZE		5
@@ -34,7 +34,6 @@
 
 /* SHA transform information */
 #define SHA_TFM_HASH		cpu_to_le32(0x2 << 0)
-#define SHA_TFM_INNER_DIG	cpu_to_le32(0x1 << 21)
 #define SHA_TFM_SIZE(x)		cpu_to_le32((x) << 8)
 #define SHA_TFM_START		cpu_to_le32(0x1 << 4)
 #define SHA_TFM_CONTINUE	cpu_to_le32(0x1 << 5)
@@ -61,31 +60,17 @@
 #define SHA_FLAGS_PAD		BIT(10)
 
 /**
- * mtk_sha_ct is a set of hardware instructions(command token)
- * that are used to control engine's processing flow of SHA,
- * and it contains the first two words of transform state.
+ * mtk_sha_info - hardware information of AES
+ * @cmd:	command token, hardware instruction
+ * @tfm:	transform state of cipher algorithm.
+ * @state:	contains keys and initial vectors.
+ *
  */
-struct mtk_sha_ct {
+struct mtk_sha_info {
 	__le32 ctrl[2];
 	__le32 cmd[3];
-};
-
-/**
- * mtk_sha_tfm is used to define SHA transform state
- * and store result digest that produced by engine.
- */
-struct mtk_sha_tfm {
-	__le32 ctrl[2];
-	__le32 digest[SIZE_IN_WORDS(SHA512_DIGEST_SIZE)];
-};
-
-/**
- * mtk_sha_info consists of command token and transform state
- * of SHA, its role is similar to mtk_aes_info.
- */
-struct mtk_sha_info {
-	struct mtk_sha_ct ct;
-	struct mtk_sha_tfm tfm;
+	__le32 tfm[2];
+	__le32 digest[SHA_MAX_DIGEST_BUF_SIZE];
 };
 
 struct mtk_sha_reqctx {
@@ -94,7 +79,6 @@ struct mtk_sha_reqctx {
 	unsigned long op;
 
 	u64 digcnt;
-	bool start;
 	size_t bufcnt;
 	dma_addr_t dma_addr;
 
@@ -153,6 +137,21 @@ static inline void mtk_sha_write(struct mtk_cryp *cryp,
 	writel_relaxed(value, cryp->base + offset);
 }
 
+static inline void mtk_sha_ring_shift(struct mtk_ring *ring,
+				      struct mtk_desc **cmd_curr,
+				      struct mtk_desc **res_curr,
+				      int *count)
+{
+	*cmd_curr = ring->cmd_next++;
+	*res_curr = ring->res_next++;
+	(*count)++;
+
+	if (ring->cmd_next == ring->cmd_base + MTK_DESC_NUM) {
+		ring->cmd_next = ring->cmd_base;
+		ring->res_next = ring->res_base;
+	}
+}
+
 static struct mtk_cryp *mtk_sha_find_dev(struct mtk_sha_ctx *tctx)
 {
 	struct mtk_cryp *cryp = NULL;
@@ -251,7 +250,9 @@ static void mtk_sha_fill_padding(struct mtk_sha_reqctx *ctx, u32 len)
 	bits[1] = cpu_to_be64(size << 3);
 	bits[0] = cpu_to_be64(size >> 61);
 
-	if (ctx->flags & (SHA_FLAGS_SHA384 | SHA_FLAGS_SHA512)) {
+	switch (ctx->flags & SHA_FLAGS_ALGO_MSK) {
+	case SHA_FLAGS_SHA384:
+	case SHA_FLAGS_SHA512:
 		index = ctx->bufcnt & 0x7f;
 		padlen = (index < 112) ? (112 - index) : ((128 + 112) - index);
 		*(ctx->buffer + ctx->bufcnt) = 0x80;
@@ -259,7 +260,9 @@ static void mtk_sha_fill_padding(struct mtk_sha_reqctx *ctx, u32 len)
 		memcpy(ctx->buffer + ctx->bufcnt + padlen, bits, 16);
 		ctx->bufcnt += padlen + 16;
 		ctx->flags |= SHA_FLAGS_PAD;
-	} else {
+		break;
+
+	default:
 		index = ctx->bufcnt & 0x3f;
 		padlen = (index < 56) ? (56 - index) : ((64 + 56) - index);
 		*(ctx->buffer + ctx->bufcnt) = 0x80;
@@ -267,36 +270,35 @@ static void mtk_sha_fill_padding(struct mtk_sha_reqctx *ctx, u32 len)
 		memcpy(ctx->buffer + ctx->bufcnt + padlen, &bits[1], 8);
 		ctx->bufcnt += padlen + 8;
 		ctx->flags |= SHA_FLAGS_PAD;
+		break;
 	}
 }
 
 /* Initialize basic transform information of SHA */
 static void mtk_sha_info_init(struct mtk_sha_reqctx *ctx)
 {
-	struct mtk_sha_ct *ct = &ctx->info.ct;
-	struct mtk_sha_tfm *tfm = &ctx->info.tfm;
+	struct mtk_sha_info *info = &ctx->info;
 
 	ctx->ct_hdr = SHA_CT_CTRL_HDR;
 	ctx->ct_size = SHA_CT_SIZE;
 
-	tfm->ctrl[0] = SHA_TFM_HASH | SHA_TFM_INNER_DIG |
-		       SHA_TFM_SIZE(SIZE_IN_WORDS(ctx->ds));
+	info->tfm[0] = SHA_TFM_HASH | SHA_TFM_SIZE(SIZE_IN_WORDS(ctx->ds));
 
 	switch (ctx->flags & SHA_FLAGS_ALGO_MSK) {
 	case SHA_FLAGS_SHA1:
-		tfm->ctrl[0] |= SHA_TFM_SHA1;
+		info->tfm[0] |= SHA_TFM_SHA1;
 		break;
 	case SHA_FLAGS_SHA224:
-		tfm->ctrl[0] |= SHA_TFM_SHA224;
+		info->tfm[0] |= SHA_TFM_SHA224;
 		break;
 	case SHA_FLAGS_SHA256:
-		tfm->ctrl[0] |= SHA_TFM_SHA256;
+		info->tfm[0] |= SHA_TFM_SHA256;
 		break;
 	case SHA_FLAGS_SHA384:
-		tfm->ctrl[0] |= SHA_TFM_SHA384;
+		info->tfm[0] |= SHA_TFM_SHA384;
 		break;
 	case SHA_FLAGS_SHA512:
-		tfm->ctrl[0] |= SHA_TFM_SHA512;
+		info->tfm[0] |= SHA_TFM_SHA512;
 		break;
 
 	default:
@@ -304,13 +306,13 @@ static void mtk_sha_info_init(struct mtk_sha_reqctx *ctx)
 		return;
 	}
 
-	tfm->ctrl[1] = SHA_TFM_HASH_STORE;
-	ct->ctrl[0] = tfm->ctrl[0] | SHA_TFM_CONTINUE | SHA_TFM_START;
-	ct->ctrl[1] = tfm->ctrl[1];
+	info->tfm[1] = SHA_TFM_HASH_STORE;
+	info->ctrl[0] = info->tfm[0] | SHA_TFM_CONTINUE | SHA_TFM_START;
+	info->ctrl[1] = info->tfm[1];
 
-	ct->cmd[0] = SHA_CMD0;
-	ct->cmd[1] = SHA_CMD1;
-	ct->cmd[2] = SHA_CMD2 | SHA_TFM_DIGEST(SIZE_IN_WORDS(ctx->ds));
+	info->cmd[0] = SHA_CMD0;
+	info->cmd[1] = SHA_CMD1;
+	info->cmd[2] = SHA_CMD2 | SHA_TFM_DIGEST(SIZE_IN_WORDS(ctx->ds));
 }
 
 /*
@@ -319,23 +321,21 @@ static void mtk_sha_info_init(struct mtk_sha_reqctx *ctx)
  */
 static int mtk_sha_info_update(struct mtk_cryp *cryp,
 			       struct mtk_sha_rec *sha,
-			       size_t len)
+			       size_t len1, size_t len2)
 {
 	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
 	struct mtk_sha_info *info = &ctx->info;
-	struct mtk_sha_ct *ct = &info->ct;
-
-	if (ctx->start)
-		ctx->start = false;
-	else
-		ct->ctrl[0] &= ~SHA_TFM_START;
 
 	ctx->ct_hdr &= ~SHA_DATA_LEN_MSK;
-	ctx->ct_hdr |= cpu_to_le32(len);
-	ct->cmd[0] &= ~SHA_DATA_LEN_MSK;
-	ct->cmd[0] |= cpu_to_le32(len);
+	ctx->ct_hdr |= cpu_to_le32(len1 + len2);
+	info->cmd[0] &= ~SHA_DATA_LEN_MSK;
+	info->cmd[0] |= cpu_to_le32(len1 + len2);
+
+	/* Setting SHA_TFM_START only for the first iteration */
+	if (ctx->digcnt)
+		info->ctrl[0] &= ~SHA_TFM_START;
 
-	ctx->digcnt += len;
+	ctx->digcnt += len1;
 
 	ctx->ct_dma = dma_map_single(cryp->dev, info, sizeof(*info),
 				     DMA_BIDIRECTIONAL);
@@ -343,7 +343,8 @@ static int mtk_sha_info_update(struct mtk_cryp *cryp,
 		dev_err(cryp->dev, "dma %zu bytes error\n", sizeof(*info));
 		return -EINVAL;
 	}
-	ctx->tfm_dma = ctx->ct_dma + sizeof(*ct);
+
+	ctx->tfm_dma = ctx->ct_dma + sizeof(info->ctrl) + sizeof(info->cmd);
 
 	return 0;
 }
@@ -408,7 +409,6 @@ static int mtk_sha_init(struct ahash_request *req)
 	ctx->bufcnt = 0;
 	ctx->digcnt = 0;
 	ctx->buffer = tctx->buf;
-	ctx->start = true;
 
 	if (tctx->flags & SHA_FLAGS_HMAC) {
 		struct mtk_sha_hmac_ctx *bctx = tctx->base;
@@ -422,89 +422,39 @@ static int mtk_sha_init(struct ahash_request *req)
 }
 
 static int mtk_sha_xmit(struct mtk_cryp *cryp, struct mtk_sha_rec *sha,
-			dma_addr_t addr, size_t len)
+			dma_addr_t addr1, size_t len1,
+			dma_addr_t addr2, size_t len2)
 {
 	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
 	struct mtk_ring *ring = cryp->ring[sha->id];
-	struct mtk_desc *cmd = ring->cmd_base + ring->cmd_pos;
-	struct mtk_desc *res = ring->res_base + ring->res_pos;
-	int err;
-
-	err = mtk_sha_info_update(cryp, sha, len);
-	if (err)
-		return err;
-
-	/* Fill in the command/result descriptors */
-	res->hdr = MTK_DESC_FIRST | MTK_DESC_LAST | MTK_DESC_BUF_LEN(len);
-	res->buf = cpu_to_le32(cryp->tmp_dma);
-
-	cmd->hdr = MTK_DESC_FIRST | MTK_DESC_LAST | MTK_DESC_BUF_LEN(len) |
-		   MTK_DESC_CT_LEN(ctx->ct_size);
-
-	cmd->buf = cpu_to_le32(addr);
-	cmd->ct = cpu_to_le32(ctx->ct_dma);
-	cmd->ct_hdr = ctx->ct_hdr;
-	cmd->tfm = cpu_to_le32(ctx->tfm_dma);
-
-	if (++ring->cmd_pos == MTK_DESC_NUM)
-		ring->cmd_pos = 0;
-
-	ring->res_pos = ring->cmd_pos;
-	/*
-	 * Make sure that all changes to the DMA ring are done before we
-	 * start engine.
-	 */
-	wmb();
-	/* Start DMA transfer */
-	mtk_sha_write(cryp, RDR_PREP_COUNT(sha->id), MTK_DESC_CNT(1));
-	mtk_sha_write(cryp, CDR_PREP_COUNT(sha->id), MTK_DESC_CNT(1));
-
-	return -EINPROGRESS;
-}
-
-static int mtk_sha_xmit2(struct mtk_cryp *cryp,
-			 struct mtk_sha_rec *sha,
-			 struct mtk_sha_reqctx *ctx,
-			 size_t len1, size_t len2)
-{
-	struct mtk_ring *ring = cryp->ring[sha->id];
-	struct mtk_desc *cmd = ring->cmd_base + ring->cmd_pos;
-	struct mtk_desc *res = ring->res_base + ring->res_pos;
-	int err;
+	struct mtk_desc *cmd, *res;
+	int err, count = 0;
 
-	err = mtk_sha_info_update(cryp, sha, len1 + len2);
+	err = mtk_sha_info_update(cryp, sha, len1, len2);
 	if (err)
 		return err;
 
 	/* Fill in the command/result descriptors */
-	res->hdr = MTK_DESC_BUF_LEN(len1) | MTK_DESC_FIRST;
-	res->buf = cpu_to_le32(cryp->tmp_dma);
+	mtk_sha_ring_shift(ring, &cmd, &res, &count);
 
-	cmd->hdr = MTK_DESC_BUF_LEN(len1) | MTK_DESC_FIRST |
+	res->hdr = MTK_DESC_FIRST | MTK_DESC_BUF_LEN(len1);
+	cmd->hdr = MTK_DESC_FIRST | MTK_DESC_BUF_LEN(len1) |
 		   MTK_DESC_CT_LEN(ctx->ct_size);
-	cmd->buf = cpu_to_le32(sg_dma_address(ctx->sg));
+	cmd->buf = cpu_to_le32(addr1);
 	cmd->ct = cpu_to_le32(ctx->ct_dma);
 	cmd->ct_hdr = ctx->ct_hdr;
 	cmd->tfm = cpu_to_le32(ctx->tfm_dma);
 
-	if (++ring->cmd_pos == MTK_DESC_NUM)
-		ring->cmd_pos = 0;
-
-	ring->res_pos = ring->cmd_pos;
-
-	cmd = ring->cmd_base + ring->cmd_pos;
-	res = ring->res_base + ring->res_pos;
-
-	res->hdr = MTK_DESC_BUF_LEN(len2) | MTK_DESC_LAST;
-	res->buf = cpu_to_le32(cryp->tmp_dma);
+	if (len2) {
+		mtk_sha_ring_shift(ring, &cmd, &res, &count);
 
-	cmd->hdr = MTK_DESC_BUF_LEN(len2) | MTK_DESC_LAST;
-	cmd->buf = cpu_to_le32(ctx->dma_addr);
-
-	if (++ring->cmd_pos == MTK_DESC_NUM)
-		ring->cmd_pos = 0;
+		res->hdr = MTK_DESC_BUF_LEN(len2);
+		cmd->hdr = MTK_DESC_BUF_LEN(len2);
+		cmd->buf = cpu_to_le32(addr2);
+	}
 
-	ring->res_pos = ring->cmd_pos;
+	cmd->hdr |= MTK_DESC_LAST;
+	res->hdr |= MTK_DESC_LAST;
 
 	/*
 	 * Make sure that all changes to the DMA ring are done before we
@@ -512,8 +462,8 @@ static int mtk_sha_xmit2(struct mtk_cryp *cryp,
 	 */
 	wmb();
 	/* Start DMA transfer */
-	mtk_sha_write(cryp, RDR_PREP_COUNT(sha->id), MTK_DESC_CNT(2));
-	mtk_sha_write(cryp, CDR_PREP_COUNT(sha->id), MTK_DESC_CNT(2));
+	mtk_sha_write(cryp, RDR_PREP_COUNT(sha->id), MTK_DESC_CNT(count));
+	mtk_sha_write(cryp, CDR_PREP_COUNT(sha->id), MTK_DESC_CNT(count));
 
 	return -EINPROGRESS;
 }
@@ -532,7 +482,7 @@ static int mtk_sha_dma_map(struct mtk_cryp *cryp,
 
 	ctx->flags &= ~SHA_FLAGS_SG;
 
-	return mtk_sha_xmit(cryp, sha, ctx->dma_addr, count);
+	return mtk_sha_xmit(cryp, sha, ctx->dma_addr, count, 0, 0);
 }
 
 static int mtk_sha_update_slow(struct mtk_cryp *cryp,
@@ -625,7 +575,8 @@ static int mtk_sha_update_start(struct mtk_cryp *cryp,
 
 		if (len == 0) {
 			ctx->flags &= ~SHA_FLAGS_SG;
-			return mtk_sha_xmit(cryp, sha, ctx->dma_addr, count);
+			return mtk_sha_xmit(cryp, sha, ctx->dma_addr,
+					    count, 0, 0);
 
 		} else {
 			ctx->sg = sg;
@@ -635,7 +586,8 @@ static int mtk_sha_update_start(struct mtk_cryp *cryp,
 			}
 
 			ctx->flags |= SHA_FLAGS_SG;
-			return mtk_sha_xmit2(cryp, sha, ctx, len, count);
+			return mtk_sha_xmit(cryp, sha, sg_dma_address(ctx->sg),
+					    len, ctx->dma_addr, count);
 		}
 	}
 
@@ -646,7 +598,8 @@ static int mtk_sha_update_start(struct mtk_cryp *cryp,
 
 	ctx->flags |= SHA_FLAGS_SG;
 
-	return mtk_sha_xmit(cryp, sha, sg_dma_address(ctx->sg), len);
+	return mtk_sha_xmit(cryp, sha, sg_dma_address(ctx->sg),
+			    len, 0, 0);
 }
 
 static int mtk_sha_final_req(struct mtk_cryp *cryp,
@@ -668,7 +621,7 @@ static int mtk_sha_final_req(struct mtk_cryp *cryp,
 static int mtk_sha_finish(struct ahash_request *req)
 {
 	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-	u32 *digest = ctx->info.tfm.digest;
+	__le32 *digest = ctx->info.digest;
 	u32 *result = (u32 *)req->result;
 	int i;
 
@@ -694,7 +647,7 @@ static void mtk_sha_finish_req(struct mtk_cryp *cryp,
 	sha->req->base.complete(&sha->req->base, err);
 
 	/* Handle new request */
-	mtk_sha_handle_queue(cryp, sha->id - RING2, NULL);
+	tasklet_schedule(&sha->queue_task);
 }
 
 static int mtk_sha_handle_queue(struct mtk_cryp *cryp, u8 id,
@@ -1216,60 +1169,38 @@ static struct ahash_alg algs_sha384_sha512[] = {
 },
 };
 
-static void mtk_sha_task0(unsigned long data)
+static void mtk_sha_queue_task(unsigned long data)
 {
-	struct mtk_cryp *cryp = (struct mtk_cryp *)data;
-	struct mtk_sha_rec *sha = cryp->sha[0];
+	struct mtk_sha_rec *sha = (struct mtk_sha_rec *)data;
 
-	mtk_sha_unmap(cryp, sha);
-	mtk_sha_complete(cryp, sha);
+	mtk_sha_handle_queue(sha->cryp, sha->id - MTK_RING2, NULL);
 }
 
-static void mtk_sha_task1(unsigned long data)
+static void mtk_sha_done_task(unsigned long data)
 {
-	struct mtk_cryp *cryp = (struct mtk_cryp *)data;
-	struct mtk_sha_rec *sha = cryp->sha[1];
+	struct mtk_sha_rec *sha = (struct mtk_sha_rec *)data;
+	struct mtk_cryp *cryp = sha->cryp;
 
 	mtk_sha_unmap(cryp, sha);
 	mtk_sha_complete(cryp, sha);
 }
 
-static irqreturn_t mtk_sha_ring2_irq(int irq, void *dev_id)
+static irqreturn_t mtk_sha_irq(int irq, void *dev_id)
 {
-	struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
-	struct mtk_sha_rec *sha = cryp->sha[0];
-	u32 val = mtk_sha_read(cryp, RDR_STAT(RING2));
+	struct mtk_sha_rec *sha = (struct mtk_sha_rec *)dev_id;
+	struct mtk_cryp *cryp = sha->cryp;
+	u32 val = mtk_sha_read(cryp, RDR_STAT(sha->id));
 
-	mtk_sha_write(cryp, RDR_STAT(RING2), val);
+	mtk_sha_write(cryp, RDR_STAT(sha->id), val);
 
 	if (likely((SHA_FLAGS_BUSY & sha->flags))) {
-		mtk_sha_write(cryp, RDR_PROC_COUNT(RING2), MTK_CNT_RST);
-		mtk_sha_write(cryp, RDR_THRESH(RING2),
+		mtk_sha_write(cryp, RDR_PROC_COUNT(sha->id), MTK_CNT_RST);
+		mtk_sha_write(cryp, RDR_THRESH(sha->id),
 			      MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE);
 
-		tasklet_schedule(&sha->task);
+		tasklet_schedule(&sha->done_task);
 	} else {
-		dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
-	}
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t mtk_sha_ring3_irq(int irq, void *dev_id)
-{
-	struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
-	struct mtk_sha_rec *sha = cryp->sha[1];
-	u32 val = mtk_sha_read(cryp, RDR_STAT(RING3));
-
-	mtk_sha_write(cryp, RDR_STAT(RING3), val);
-
-	if (likely((SHA_FLAGS_BUSY & sha->flags))) {
-		mtk_sha_write(cryp, RDR_PROC_COUNT(RING3), MTK_CNT_RST);
-		mtk_sha_write(cryp, RDR_THRESH(RING3),
-			      MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE);
-
-		tasklet_schedule(&sha->task);
-	} else {
-		dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
+		dev_warn(cryp->dev, "SHA interrupt when no active requests.\n");
 	}
 	return IRQ_HANDLED;
 }
@@ -1288,14 +1219,20 @@ static int mtk_sha_record_init(struct mtk_cryp *cryp)
 		if (!sha[i])
 			goto err_cleanup;
 
-		sha[i]->id = i + RING2;
+		sha[i]->cryp = cryp;
 
 		spin_lock_init(&sha[i]->lock);
 		crypto_init_queue(&sha[i]->queue, SHA_QUEUE_SIZE);
+
+		tasklet_init(&sha[i]->queue_task, mtk_sha_queue_task,
+			     (unsigned long)sha[i]);
+		tasklet_init(&sha[i]->done_task, mtk_sha_done_task,
+			     (unsigned long)sha[i]);
 	}
 
-	tasklet_init(&sha[0]->task, mtk_sha_task0, (unsigned long)cryp);
-	tasklet_init(&sha[1]->task, mtk_sha_task1, (unsigned long)cryp);
+	/* Link to ring2 and ring3 respectively */
+	sha[0]->id = MTK_RING2;
+	sha[1]->id = MTK_RING3;
 
 	cryp->rec = 1;
 
@@ -1312,7 +1249,9 @@ static void mtk_sha_record_free(struct mtk_cryp *cryp)
 	int i;
 
 	for (i = 0; i < MTK_REC_NUM; i++) {
-		tasklet_kill(&cryp->sha[i]->task);
+		tasklet_kill(&cryp->sha[i]->done_task);
+		tasklet_kill(&cryp->sha[i]->queue_task);
+
 		kfree(cryp->sha[i]);
 	}
 }
@@ -1368,35 +1307,23 @@ int mtk_hash_alg_register(struct mtk_cryp *cryp)
 	if (err)
 		goto err_record;
 
-	/* Ring2 is use by SHA record0 */
-	err = devm_request_irq(cryp->dev, cryp->irq[RING2],
-			       mtk_sha_ring2_irq, IRQF_TRIGGER_LOW,
-			       "mtk-sha", cryp);
+	err = devm_request_irq(cryp->dev, cryp->irq[MTK_RING2], mtk_sha_irq,
+			       0, "mtk-sha", cryp->sha[0]);
 	if (err) {
 		dev_err(cryp->dev, "unable to request sha irq0.\n");
 		goto err_res;
 	}
 
-	/* Ring3 is use by SHA record1 */
-	err = devm_request_irq(cryp->dev, cryp->irq[RING3],
-			       mtk_sha_ring3_irq, IRQF_TRIGGER_LOW,
-			       "mtk-sha", cryp);
+	err = devm_request_irq(cryp->dev, cryp->irq[MTK_RING3], mtk_sha_irq,
+			       0, "mtk-sha", cryp->sha[1]);
 	if (err) {
 		dev_err(cryp->dev, "unable to request sha irq1.\n");
 		goto err_res;
 	}
 
 	/* Enable ring2 and ring3 interrupt for hash */
-	mtk_sha_write(cryp, AIC_ENABLE_SET(RING2), MTK_IRQ_RDR2);
-	mtk_sha_write(cryp, AIC_ENABLE_SET(RING3), MTK_IRQ_RDR3);
-
-	cryp->tmp = dma_alloc_coherent(cryp->dev, SHA_TMP_BUF_SIZE,
-					&cryp->tmp_dma, GFP_KERNEL);
-	if (!cryp->tmp) {
-		dev_err(cryp->dev, "unable to allocate tmp buffer.\n");
-		err = -EINVAL;
-		goto err_res;
-	}
+	mtk_sha_write(cryp, AIC_ENABLE_SET(MTK_RING2), MTK_IRQ_RDR2);
+	mtk_sha_write(cryp, AIC_ENABLE_SET(MTK_RING3), MTK_IRQ_RDR3);
 
 	spin_lock(&mtk_sha.lock);
 	list_add_tail(&cryp->sha_list, &mtk_sha.dev_list);
@@ -1412,8 +1339,6 @@ err_algs:
 	spin_lock(&mtk_sha.lock);
 	list_del(&cryp->sha_list);
 	spin_unlock(&mtk_sha.lock);
-	dma_free_coherent(cryp->dev, SHA_TMP_BUF_SIZE,
-			  cryp->tmp, cryp->tmp_dma);
 err_res:
 	mtk_sha_record_free(cryp);
 err_record:
@@ -1429,7 +1354,5 @@ void mtk_hash_alg_release(struct mtk_cryp *cryp)
 	spin_unlock(&mtk_sha.lock);
 
 	mtk_sha_unregister_algs();
-	dma_free_coherent(cryp->dev, SHA_TMP_BUF_SIZE,
-			  cryp->tmp, cryp->tmp_dma);
 	mtk_sha_record_free(cryp);
 }
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index c5aac25a5738..4ecb77aa60e1 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -65,6 +65,11 @@ struct spu_queue {
 	struct list_head	list;
 };
 
+struct spu_qreg {
+	struct spu_queue	*queue;
+	unsigned long		type;
+};
+
 static struct spu_queue **cpu_to_cwq;
 static struct spu_queue **cpu_to_mau;
 
@@ -1631,31 +1636,27 @@ static void queue_cache_destroy(void)
 	kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_CWQ - 1]);
 }
 
-static int spu_queue_register(struct spu_queue *p, unsigned long q_type)
+static long spu_queue_register_workfn(void *arg)
 {
-	cpumask_var_t old_allowed;
+	struct spu_qreg *qr = arg;
+	struct spu_queue *p = qr->queue;
+	unsigned long q_type = qr->type;
 	unsigned long hv_ret;
 
-	if (cpumask_empty(&p->sharing))
-		return -EINVAL;
-
-	if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
-		return -ENOMEM;
-
-	cpumask_copy(old_allowed, &current->cpus_allowed);
-
-	set_cpus_allowed_ptr(current, &p->sharing);
-
 	hv_ret = sun4v_ncs_qconf(q_type, __pa(p->q),
 				 CWQ_NUM_ENTRIES, &p->qhandle);
 	if (!hv_ret)
 		sun4v_ncs_sethead_marker(p->qhandle, 0);
 
-	set_cpus_allowed_ptr(current, old_allowed);
+	return hv_ret ? -EINVAL : 0;
+}
 
-	free_cpumask_var(old_allowed);
+static int spu_queue_register(struct spu_queue *p, unsigned long q_type)
+{
+	int cpu = cpumask_any_and(&p->sharing, cpu_online_mask);
+	struct spu_qreg qr = { .queue = p, .type = q_type };
 
-	return (hv_ret ? -EINVAL : 0);
+	return work_on_cpu_safe(cpu, spu_queue_register_workfn, &qr);
 }
 
 static int spu_queue_setup(struct spu_queue *p)
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 0d35dca2e925..2aab80bc241f 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -491,7 +491,7 @@ static void qat_dh_clear_ctx(struct device *dev, struct qat_dh_ctx *ctx)
 	ctx->g2 = false;
 }
 
-static int qat_dh_set_secret(struct crypto_kpp *tfm, void *buf,
+static int qat_dh_set_secret(struct crypto_kpp *tfm, const void *buf,
 			     unsigned int len)
 {
 	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index dce1af0ce85c..7ac657f46d15 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -170,6 +170,32 @@ struct s5p_aes_ctx {
 	int				keylen;
 };
 
+/**
+ * struct s5p_aes_dev - Crypto device state container
+ * @dev:	Associated device
+ * @clk:	Clock for accessing hardware
+ * @ioaddr:	Mapped IO memory region
+ * @aes_ioaddr:	Per-varian offset for AES block IO memory
+ * @irq_fc:	Feed control interrupt line
+ * @req:	Crypto request currently handled by the device
+ * @ctx:	Configuration for currently handled crypto request
+ * @sg_src:	Scatter list with source data for currently handled block
+ *		in device.  This is DMA-mapped into device.
+ * @sg_dst:	Scatter list with destination data for currently handled block
+ *		in device. This is DMA-mapped into device.
+ * @sg_src_cpy:	In case of unaligned access, copied scatter list
+ *		with source data.
+ * @sg_dst_cpy:	In case of unaligned access, copied scatter list
+ *		with destination data.
+ * @tasklet:	New request scheduling jib
+ * @queue:	Crypto queue
+ * @busy:	Indicates whether the device is currently handling some request
+ *		thus it uses some of the fields from this state, like:
+ *		req, ctx, sg_src/dst (and copies).  This essentially
+ *		protects against concurrent access to these fields.
+ * @lock:	Lock for protecting both access to device hardware registers
+ *		and fields related to current request (including the busy field).
+ */
 struct s5p_aes_dev {
 	struct device			*dev;
 	struct clk			*clk;
@@ -182,7 +208,6 @@ struct s5p_aes_dev {
 	struct scatterlist		*sg_src;
 	struct scatterlist		*sg_dst;
 
-	/* In case of unaligned access: */
 	struct scatterlist		*sg_src_cpy;
 	struct scatterlist		*sg_dst_cpy;
 
@@ -190,8 +215,6 @@ struct s5p_aes_dev {
 	struct crypto_queue		queue;
 	bool				busy;
 	spinlock_t			lock;
-
-	struct samsung_aes_variant	*variant;
 };
 
 static struct s5p_aes_dev *s5p_dev;
@@ -270,7 +293,7 @@ static void s5p_sg_copy_buf(void *buf, struct scatterlist *sg,
 	scatterwalk_done(&walk, out, 0);
 }
 
-static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+static void s5p_sg_done(struct s5p_aes_dev *dev)
 {
 	if (dev->sg_dst_cpy) {
 		dev_dbg(dev->dev,
@@ -281,10 +304,12 @@ static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
 	}
 	s5p_free_sg_cpy(dev, &dev->sg_src_cpy);
 	s5p_free_sg_cpy(dev, &dev->sg_dst_cpy);
+}
 
-	/* holding a lock outside */
+/* Calls the completion. Cannot be called with dev->lock hold. */
+static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+{
 	dev->req->base.complete(&dev->req->base, err);
-	dev->busy = false;
 }
 
 static void s5p_unset_outdata(struct s5p_aes_dev *dev)
@@ -368,51 +393,44 @@ exit:
 }
 
 /*
- * Returns true if new transmitting (output) data is ready and its
- * address+length have to be written to device (by calling
- * s5p_set_dma_outdata()). False otherwise.
+ * Returns -ERRNO on error (mapping of new data failed).
+ * On success returns:
+ *  - 0 if there is no more data,
+ *  - 1 if new transmitting (output) data is ready and its address+length
+ *     have to be written to device (by calling s5p_set_dma_outdata()).
  */
-static bool s5p_aes_tx(struct s5p_aes_dev *dev)
+static int s5p_aes_tx(struct s5p_aes_dev *dev)
 {
-	int err = 0;
-	bool ret = false;
+	int ret = 0;
 
 	s5p_unset_outdata(dev);
 
 	if (!sg_is_last(dev->sg_dst)) {
-		err = s5p_set_outdata(dev, sg_next(dev->sg_dst));
-		if (err)
-			s5p_aes_complete(dev, err);
-		else
-			ret = true;
-	} else {
-		s5p_aes_complete(dev, err);
-
-		dev->busy = true;
-		tasklet_schedule(&dev->tasklet);
+		ret = s5p_set_outdata(dev, sg_next(dev->sg_dst));
+		if (!ret)
+			ret = 1;
 	}
 
 	return ret;
 }
 
 /*
- * Returns true if new receiving (input) data is ready and its
- * address+length have to be written to device (by calling
- * s5p_set_dma_indata()). False otherwise.
+ * Returns -ERRNO on error (mapping of new data failed).
+ * On success returns:
+ *  - 0 if there is no more data,
+ *  - 1 if new receiving (input) data is ready and its address+length
+ *     have to be written to device (by calling s5p_set_dma_indata()).
  */
-static bool s5p_aes_rx(struct s5p_aes_dev *dev)
+static int s5p_aes_rx(struct s5p_aes_dev *dev/*, bool *set_dma*/)
 {
-	int err;
-	bool ret = false;
+	int ret = 0;
 
 	s5p_unset_indata(dev);
 
 	if (!sg_is_last(dev->sg_src)) {
-		err = s5p_set_indata(dev, sg_next(dev->sg_src));
-		if (err)
-			s5p_aes_complete(dev, err);
-		else
-			ret = true;
+		ret = s5p_set_indata(dev, sg_next(dev->sg_src));
+		if (!ret)
+			ret = 1;
 	}
 
 	return ret;
@@ -422,33 +440,74 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 {
 	struct platform_device *pdev = dev_id;
 	struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
-	bool set_dma_tx = false;
-	bool set_dma_rx = false;
+	int err_dma_tx = 0;
+	int err_dma_rx = 0;
+	bool tx_end = false;
 	unsigned long flags;
 	uint32_t status;
+	int err;
 
 	spin_lock_irqsave(&dev->lock, flags);
 
+	/*
+	 * Handle rx or tx interrupt. If there is still data (scatterlist did not
+	 * reach end), then map next scatterlist entry.
+	 * In case of such mapping error, s5p_aes_complete() should be called.
+	 *
+	 * If there is no more data in tx scatter list, call s5p_aes_complete()
+	 * and schedule new tasklet.
+	 */
 	status = SSS_READ(dev, FCINTSTAT);
 	if (status & SSS_FCINTSTAT_BRDMAINT)
-		set_dma_rx = s5p_aes_rx(dev);
-	if (status & SSS_FCINTSTAT_BTDMAINT)
-		set_dma_tx = s5p_aes_tx(dev);
+		err_dma_rx = s5p_aes_rx(dev);
+
+	if (status & SSS_FCINTSTAT_BTDMAINT) {
+		if (sg_is_last(dev->sg_dst))
+			tx_end = true;
+		err_dma_tx = s5p_aes_tx(dev);
+	}
 
 	SSS_WRITE(dev, FCINTPEND, status);
 
-	/*
-	 * Writing length of DMA block (either receiving or transmitting)
-	 * will start the operation immediately, so this should be done
-	 * at the end (even after clearing pending interrupts to not miss the
-	 * interrupt).
-	 */
-	if (set_dma_tx)
-		s5p_set_dma_outdata(dev, dev->sg_dst);
-	if (set_dma_rx)
-		s5p_set_dma_indata(dev, dev->sg_src);
+	if (err_dma_rx < 0) {
+		err = err_dma_rx;
+		goto error;
+	}
+	if (err_dma_tx < 0) {
+		err = err_dma_tx;
+		goto error;
+	}
+
+	if (tx_end) {
+		s5p_sg_done(dev);
+
+		spin_unlock_irqrestore(&dev->lock, flags);
 
+		s5p_aes_complete(dev, 0);
+		/* Device is still busy */
+		tasklet_schedule(&dev->tasklet);
+	} else {
+		/*
+		 * Writing length of DMA block (either receiving or
+		 * transmitting) will start the operation immediately, so this
+		 * should be done at the end (even after clearing pending
+		 * interrupts to not miss the interrupt).
+		 */
+		if (err_dma_tx == 1)
+			s5p_set_dma_outdata(dev, dev->sg_dst);
+		if (err_dma_rx == 1)
+			s5p_set_dma_indata(dev, dev->sg_src);
+
+		spin_unlock_irqrestore(&dev->lock, flags);
+	}
+
+	return IRQ_HANDLED;
+
+error:
+	s5p_sg_done(dev);
+	dev->busy = false;
 	spin_unlock_irqrestore(&dev->lock, flags);
+	s5p_aes_complete(dev, err);
 
 	return IRQ_HANDLED;
 }
@@ -597,8 +656,10 @@ outdata_error:
 	s5p_unset_indata(dev);
 
 indata_error:
-	s5p_aes_complete(dev, err);
+	s5p_sg_done(dev);
+	dev->busy = false;
 	spin_unlock_irqrestore(&dev->lock, flags);
+	s5p_aes_complete(dev, err);
 }
 
 static void s5p_tasklet_cb(unsigned long data)
@@ -805,15 +866,15 @@ static int s5p_aes_probe(struct platform_device *pdev)
 		dev_warn(dev, "feed control interrupt is not available.\n");
 		goto err_irq;
 	}
-	err = devm_request_irq(dev, pdata->irq_fc, s5p_aes_interrupt,
-			       IRQF_SHARED, pdev->name, pdev);
+	err = devm_request_threaded_irq(dev, pdata->irq_fc, NULL,
+					s5p_aes_interrupt, IRQF_ONESHOT,
+					pdev->name, pdev);
 	if (err < 0) {
 		dev_warn(dev, "feed control interrupt is not available.\n");
 		goto err_irq;
 	}
 
 	pdata->busy = false;
-	pdata->variant = variant;
 	pdata->dev = dev;
 	platform_set_drvdata(pdev, pdata);
 	s5p_dev = pdata;
diff --git a/drivers/crypto/stm32/Kconfig b/drivers/crypto/stm32/Kconfig
new file mode 100644
index 000000000000..09b4ec87c212
--- /dev/null
+++ b/drivers/crypto/stm32/Kconfig
@@ -0,0 +1,7 @@
+config CRYPTO_DEV_STM32
+	tristate "Support for STM32 crypto accelerators"
+	depends on ARCH_STM32
+	select CRYPTO_HASH
+	help
+          This enables support for the CRC32 hw accelerator which can be found
+	  on STMicroelectronis STM32 SOC.
diff --git a/drivers/crypto/stm32/Makefile b/drivers/crypto/stm32/Makefile
new file mode 100644
index 000000000000..73b4c6e47f5f
--- /dev/null
+++ b/drivers/crypto/stm32/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_STM32) += stm32_cryp.o
+stm32_cryp-objs := stm32_crc32.o
diff --git a/drivers/crypto/stm32/stm32_crc32.c b/drivers/crypto/stm32/stm32_crc32.c
new file mode 100644
index 000000000000..ec83b1e6bfe8
--- /dev/null
+++ b/drivers/crypto/stm32/stm32_crc32.c
@@ -0,0 +1,324 @@
+/*
+ * Copyright (C) STMicroelectronics SA 2017
+ * Author: Fabien Dessenne <fabien.dessenne@st.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/bitrev.h>
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <crypto/internal/hash.h>
+
+#include <asm/unaligned.h>
+
+#define DRIVER_NAME             "stm32-crc32"
+#define CHKSUM_DIGEST_SIZE      4
+#define CHKSUM_BLOCK_SIZE       1
+
+/* Registers */
+#define CRC_DR                  0x00000000
+#define CRC_CR                  0x00000008
+#define CRC_INIT                0x00000010
+#define CRC_POL                 0x00000014
+
+/* Registers values */
+#define CRC_CR_RESET            BIT(0)
+#define CRC_CR_REVERSE          (BIT(7) | BIT(6) | BIT(5))
+#define CRC_INIT_DEFAULT        0xFFFFFFFF
+
+/* Polynomial reversed */
+#define POLY_CRC32              0xEDB88320
+#define POLY_CRC32C             0x82F63B78
+
+struct stm32_crc {
+	struct list_head list;
+	struct device    *dev;
+	void __iomem     *regs;
+	struct clk       *clk;
+	u8               pending_data[sizeof(u32)];
+	size_t           nb_pending_bytes;
+};
+
+struct stm32_crc_list {
+	struct list_head dev_list;
+	spinlock_t       lock; /* protect dev_list */
+};
+
+static struct stm32_crc_list crc_list = {
+	.dev_list = LIST_HEAD_INIT(crc_list.dev_list),
+	.lock     = __SPIN_LOCK_UNLOCKED(crc_list.lock),
+};
+
+struct stm32_crc_ctx {
+	u32 key;
+	u32 poly;
+};
+
+struct stm32_crc_desc_ctx {
+	u32    partial; /* crc32c: partial in first 4 bytes of that struct */
+	struct stm32_crc *crc;
+};
+
+static int stm32_crc32_cra_init(struct crypto_tfm *tfm)
+{
+	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
+
+	mctx->key = CRC_INIT_DEFAULT;
+	mctx->poly = POLY_CRC32;
+	return 0;
+}
+
+static int stm32_crc32c_cra_init(struct crypto_tfm *tfm)
+{
+	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
+
+	mctx->key = CRC_INIT_DEFAULT;
+	mctx->poly = POLY_CRC32C;
+	return 0;
+}
+
+static int stm32_crc_setkey(struct crypto_shash *tfm, const u8 *key,
+			    unsigned int keylen)
+{
+	struct stm32_crc_ctx *mctx = crypto_shash_ctx(tfm);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	mctx->key = get_unaligned_le32(key);
+	return 0;
+}
+
+static int stm32_crc_init(struct shash_desc *desc)
+{
+	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
+	struct stm32_crc *crc;
+
+	spin_lock_bh(&crc_list.lock);
+	list_for_each_entry(crc, &crc_list.dev_list, list) {
+		ctx->crc = crc;
+		break;
+	}
+	spin_unlock_bh(&crc_list.lock);
+
+	/* Reset, set key, poly and configure in bit reverse mode */
+	writel(bitrev32(mctx->key), ctx->crc->regs + CRC_INIT);
+	writel(bitrev32(mctx->poly), ctx->crc->regs + CRC_POL);
+	writel(CRC_CR_RESET | CRC_CR_REVERSE, ctx->crc->regs + CRC_CR);
+
+	/* Store partial result */
+	ctx->partial = readl(ctx->crc->regs + CRC_DR);
+	ctx->crc->nb_pending_bytes = 0;
+
+	return 0;
+}
+
+static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
+			    unsigned int length)
+{
+	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct stm32_crc *crc = ctx->crc;
+	u32 *d32;
+	unsigned int i;
+
+	if (unlikely(crc->nb_pending_bytes)) {
+		while (crc->nb_pending_bytes != sizeof(u32) && length) {
+			/* Fill in pending data */
+			crc->pending_data[crc->nb_pending_bytes++] = *(d8++);
+			length--;
+		}
+
+		if (crc->nb_pending_bytes == sizeof(u32)) {
+			/* Process completed pending data */
+			writel(*(u32 *)crc->pending_data, crc->regs + CRC_DR);
+			crc->nb_pending_bytes = 0;
+		}
+	}
+
+	d32 = (u32 *)d8;
+	for (i = 0; i < length >> 2; i++)
+		/* Process 32 bits data */
+		writel(*(d32++), crc->regs + CRC_DR);
+
+	/* Store partial result */
+	ctx->partial = readl(crc->regs + CRC_DR);
+
+	/* Check for pending data (non 32 bits) */
+	length &= 3;
+	if (likely(!length))
+		return 0;
+
+	if ((crc->nb_pending_bytes + length) >= sizeof(u32)) {
+		/* Shall not happen */
+		dev_err(crc->dev, "Pending data overflow\n");
+		return -EINVAL;
+	}
+
+	d8 = (const u8 *)d32;
+	for (i = 0; i < length; i++)
+		/* Store pending data */
+		crc->pending_data[crc->nb_pending_bytes++] = *(d8++);
+
+	return 0;
+}
+
+static int stm32_crc_final(struct shash_desc *desc, u8 *out)
+{
+	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
+
+	/* Send computed CRC */
+	put_unaligned_le32(mctx->poly == POLY_CRC32C ?
+			   ~ctx->partial : ctx->partial, out);
+
+	return 0;
+}
+
+static int stm32_crc_finup(struct shash_desc *desc, const u8 *data,
+			   unsigned int length, u8 *out)
+{
+	return stm32_crc_update(desc, data, length) ?:
+	       stm32_crc_final(desc, out);
+}
+
+static int stm32_crc_digest(struct shash_desc *desc, const u8 *data,
+			    unsigned int length, u8 *out)
+{
+	return stm32_crc_init(desc) ?: stm32_crc_finup(desc, data, length, out);
+}
+
+static struct shash_alg algs[] = {
+	/* CRC-32 */
+	{
+		.setkey         = stm32_crc_setkey,
+		.init           = stm32_crc_init,
+		.update         = stm32_crc_update,
+		.final          = stm32_crc_final,
+		.finup          = stm32_crc_finup,
+		.digest         = stm32_crc_digest,
+		.descsize       = sizeof(struct stm32_crc_desc_ctx),
+		.digestsize     = CHKSUM_DIGEST_SIZE,
+		.base           = {
+			.cra_name               = "crc32",
+			.cra_driver_name        = DRIVER_NAME,
+			.cra_priority           = 200,
+			.cra_blocksize          = CHKSUM_BLOCK_SIZE,
+			.cra_alignmask          = 3,
+			.cra_ctxsize            = sizeof(struct stm32_crc_ctx),
+			.cra_module             = THIS_MODULE,
+			.cra_init               = stm32_crc32_cra_init,
+		}
+	},
+	/* CRC-32Castagnoli */
+	{
+		.setkey         = stm32_crc_setkey,
+		.init           = stm32_crc_init,
+		.update         = stm32_crc_update,
+		.final          = stm32_crc_final,
+		.finup          = stm32_crc_finup,
+		.digest         = stm32_crc_digest,
+		.descsize       = sizeof(struct stm32_crc_desc_ctx),
+		.digestsize     = CHKSUM_DIGEST_SIZE,
+		.base           = {
+			.cra_name               = "crc32c",
+			.cra_driver_name        = DRIVER_NAME,
+			.cra_priority           = 200,
+			.cra_blocksize          = CHKSUM_BLOCK_SIZE,
+			.cra_alignmask          = 3,
+			.cra_ctxsize            = sizeof(struct stm32_crc_ctx),
+			.cra_module             = THIS_MODULE,
+			.cra_init               = stm32_crc32c_cra_init,
+		}
+	}
+};
+
+static int stm32_crc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct stm32_crc *crc;
+	struct resource *res;
+	int ret;
+
+	crc = devm_kzalloc(dev, sizeof(*crc), GFP_KERNEL);
+	if (!crc)
+		return -ENOMEM;
+
+	crc->dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	crc->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(crc->regs)) {
+		dev_err(dev, "Cannot map CRC IO\n");
+		return PTR_ERR(crc->regs);
+	}
+
+	crc->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(crc->clk)) {
+		dev_err(dev, "Could not get clock\n");
+		return PTR_ERR(crc->clk);
+	}
+
+	ret = clk_prepare_enable(crc->clk);
+	if (ret) {
+		dev_err(crc->dev, "Failed to enable clock\n");
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, crc);
+
+	spin_lock(&crc_list.lock);
+	list_add(&crc->list, &crc_list.dev_list);
+	spin_unlock(&crc_list.lock);
+
+	ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+	if (ret) {
+		dev_err(dev, "Failed to register\n");
+		clk_disable_unprepare(crc->clk);
+		return ret;
+	}
+
+	dev_info(dev, "Initialized\n");
+
+	return 0;
+}
+
+static int stm32_crc_remove(struct platform_device *pdev)
+{
+	struct stm32_crc *crc = platform_get_drvdata(pdev);
+
+	spin_lock(&crc_list.lock);
+	list_del(&crc->list);
+	spin_unlock(&crc_list.lock);
+
+	crypto_unregister_shash(algs);
+
+	clk_disable_unprepare(crc->clk);
+
+	return 0;
+}
+
+static const struct of_device_id stm32_dt_ids[] = {
+	{ .compatible = "st,stm32f7-crc", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, stm32_dt_ids);
+
+static struct platform_driver stm32_crc_driver = {
+	.probe  = stm32_crc_probe,
+	.remove = stm32_crc_remove,
+	.driver = {
+		.name           = DRIVER_NAME,
+		.of_match_table = stm32_dt_ids,
+	},
+};
+
+module_platform_driver(stm32_crc_driver);
+
+MODULE_AUTHOR("Fabien Dessenne <fabien.dessenne@st.com>");
+MODULE_DESCRIPTION("STMicrolectronics STM32 CRC32 hardware driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c
index 43a0c8a26ab0..00a16ab601cb 100644
--- a/drivers/crypto/ux500/cryp/cryp.c
+++ b/drivers/crypto/ux500/cryp/cryp.c
@@ -82,7 +82,7 @@ void cryp_activity(struct cryp_device_data *device_data,
 void cryp_flush_inoutfifo(struct cryp_device_data *device_data)
 {
 	/*
-	 * We always need to disble the hardware before trying to flush the
+	 * We always need to disable the hardware before trying to flush the
 	 * FIFO. This is something that isn't written in the design
 	 * specification, but we have been informed by the hardware designers
 	 * that this must be done.
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 3e2ab3b14eea..9e95bf94eb13 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -2,6 +2,7 @@ menuconfig DEV_DAX
 	tristate "DAX: direct access to differentiated memory"
 	default m if NVDIMM_DAX
 	depends on TRANSPARENT_HUGEPAGE
+	select SRCU
 	help
 	  Support raw access to differentiated (persistence, bandwidth,
 	  latency...) memory via an mmap(2) capable character
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 8d9829ff2a78..806f180c80d8 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -25,6 +25,7 @@
 #include "dax.h"
 
 static dev_t dax_devt;
+DEFINE_STATIC_SRCU(dax_srcu);
 static struct class *dax_class;
 static DEFINE_IDA(dax_minor_ida);
 static int nr_dax = CONFIG_NR_DEV_DAX;
@@ -60,7 +61,7 @@ struct dax_region {
  * @region - parent region
  * @dev - device backing the character device
  * @cdev - core chardev data
- * @alive - !alive + rcu grace period == no new mappings can be established
+ * @alive - !alive + srcu grace period == no new mappings can be established
  * @id - child id in the region
  * @num_resources - number of physical address extents in this device
  * @res - array of physical address ranges
@@ -427,6 +428,7 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 	int rc = VM_FAULT_SIGBUS;
 	phys_addr_t phys;
 	pfn_t pfn;
+	unsigned int fault_size = PAGE_SIZE;
 
 	if (check_vma(dax_dev, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
@@ -437,9 +439,12 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
+	if (fault_size != dax_region->align)
+		return VM_FAULT_SIGBUS;
+
 	phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
 	if (phys == -1) {
-		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+		dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
 				vmf->pgoff);
 		return VM_FAULT_SIGBUS;
 	}
@@ -464,6 +469,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 	phys_addr_t phys;
 	pgoff_t pgoff;
 	pfn_t pfn;
+	unsigned int fault_size = PMD_SIZE;
 
 	if (check_vma(dax_dev, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
@@ -480,10 +486,20 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
+	if (fault_size < dax_region->align)
+		return VM_FAULT_SIGBUS;
+	else if (fault_size > dax_region->align)
+		return VM_FAULT_FALLBACK;
+
+	/* if we are outside of the VMA */
+	if (pmd_addr < vmf->vma->vm_start ||
+			(pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
 	pgoff = linear_page_index(vmf->vma, pmd_addr);
 	phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
 	if (phys == -1) {
-		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+		dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
 				pgoff);
 		return VM_FAULT_SIGBUS;
 	}
@@ -503,6 +519,8 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 	phys_addr_t phys;
 	pgoff_t pgoff;
 	pfn_t pfn;
+	unsigned int fault_size = PUD_SIZE;
+
 
 	if (check_vma(dax_dev, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
@@ -519,10 +537,20 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
+	if (fault_size < dax_region->align)
+		return VM_FAULT_SIGBUS;
+	else if (fault_size > dax_region->align)
+		return VM_FAULT_FALLBACK;
+
+	/* if we are outside of the VMA */
+	if (pud_addr < vmf->vma->vm_start ||
+			(pud_addr + PUD_SIZE) > vmf->vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
 	pgoff = linear_page_index(vmf->vma, pud_addr);
 	phys = pgoff_to_phys(dax_dev, pgoff, PUD_SIZE);
 	if (phys == -1) {
-		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+		dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
 				pgoff);
 		return VM_FAULT_SIGBUS;
 	}
@@ -542,7 +570,7 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 static int dax_dev_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
-	int rc;
+	int rc, id;
 	struct file *filp = vmf->vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
@@ -551,7 +579,7 @@ static int dax_dev_huge_fault(struct vm_fault *vmf,
 			? "write" : "read",
 			vmf->vma->vm_start, vmf->vma->vm_end);
 
-	rcu_read_lock();
+	id = srcu_read_lock(&dax_srcu);
 	switch (pe_size) {
 	case PE_SIZE_PTE:
 		rc = __dax_dev_pte_fault(dax_dev, vmf);
@@ -565,7 +593,7 @@ static int dax_dev_huge_fault(struct vm_fault *vmf,
 	default:
 		return VM_FAULT_FALLBACK;
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&dax_srcu, id);
 
 	return rc;
 }
@@ -686,11 +714,11 @@ static void unregister_dax_dev(void *dev)
 	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
 	 * ensuring that any fault handlers that might have seen
 	 * dax_dev->alive == true, have completed.  Any fault handlers
-	 * that start after synchronize_rcu() has started will abort
+	 * that start after synchronize_srcu() has started will abort
 	 * upon seeing dax_dev->alive == false.
 	 */
 	dax_dev->alive = false;
-	synchronize_rcu();
+	synchronize_srcu(&dax_srcu);
 	unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
 	cdev_del(cdev);
 	device_unregister(dev);
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 033f49b31fdc..cb0d742fa23f 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -43,6 +43,7 @@ static void dax_pmem_percpu_exit(void *data)
 	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	wait_for_completion(&dax_pmem->cmp);
 	percpu_ref_exit(ref);
 }
 
@@ -53,7 +54,6 @@ static void dax_pmem_percpu_kill(void *data)
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
 	percpu_ref_kill(ref);
-	wait_for_completion(&dax_pmem->cmp);
 }
 
 static int dax_pmem_probe(struct device *dev)
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index 71576b8bdfef..a4f2fa1091e4 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -25,6 +25,35 @@
 #define DEVFREQ_GOV_SUSPEND			0x4
 #define DEVFREQ_GOV_RESUME			0x5
 
+/**
+ * struct devfreq_governor - Devfreq policy governor
+ * @node:		list node - contains registered devfreq governors
+ * @name:		Governor's name
+ * @immutable:		Immutable flag for governor. If the value is 1,
+ *			this govenror is never changeable to other governor.
+ * @get_target_freq:	Returns desired operating frequency for the device.
+ *			Basically, get_target_freq will run
+ *			devfreq_dev_profile.get_dev_status() to get the
+ *			status of the device (load = busy_time / total_time).
+ *			If no_central_polling is set, this callback is called
+ *			only with update_devfreq() notified by OPP.
+ * @event_handler:      Callback for devfreq core framework to notify events
+ *                      to governors. Events include per device governor
+ *                      init and exit, opp changes out of devfreq, suspend
+ *                      and resume of per device devfreq during device idle.
+ *
+ * Note that the callbacks are called with devfreq->lock locked by devfreq.
+ */
+struct devfreq_governor {
+	struct list_head node;
+
+	const char name[DEVFREQ_NAME_LEN];
+	const unsigned int immutable;
+	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
+	int (*event_handler)(struct devfreq *devfreq,
+				unsigned int event, void *data);
+};
+
 /* Caution: devfreq->lock must be locked before calling update_devfreq */
 extern int update_devfreq(struct devfreq *devfreq);
 
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index e18dc596cf24..6204cc32d09c 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -251,8 +251,11 @@ static void bcm2835_dma_create_cb_set_length(
 	 */
 
 	/* have we filled in period_length yet? */
-	if (*total_len + control_block->length < period_len)
+	if (*total_len + control_block->length < period_len) {
+		/* update number of bytes in this period so far */
+		*total_len += control_block->length;
 		return;
+	}
 
 	/* calculate the length that remains to reach period_length */
 	control_block->length = period_len - *total_len;
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 24e0221fd66d..d9118ec23025 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1108,12 +1108,14 @@ static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
 	switch (order) {
 	case 0 ... 1:
 		return &unmap_pool[0];
+#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID)
 	case 2 ... 4:
 		return &unmap_pool[1];
 	case 5 ... 7:
 		return &unmap_pool[2];
 	case 8:
 		return &unmap_pool[3];
+#endif
 	default:
 		BUG();
 		return NULL;
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 82d85cce81f8..96afb2aeed18 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -10,26 +10,16 @@ config EDAC_SUPPORT
 	bool
 
 menuconfig EDAC
-	bool "EDAC (Error Detection And Correction) reporting"
-	depends on HAS_IOMEM && EDAC_SUPPORT
+	tristate "EDAC (Error Detection And Correction) reporting"
+	depends on HAS_IOMEM && EDAC_SUPPORT && RAS
 	help
-	  EDAC is designed to report errors in the core system.
-	  These are low-level errors that are reported in the CPU or
-	  supporting chipset or other subsystems:
+	  EDAC is a subsystem along with hardware-specific drivers designed to
+	  report hardware errors. These are low-level errors that are reported
+	  in the CPU or supporting chipset or other subsystems:
 	  memory errors, cache errors, PCI errors, thermal throttling, etc..
 	  If unsure, select 'Y'.
 
-	  If this code is reporting problems on your system, please
-	  see the EDAC project web pages for more information at:
-
-	  <http://bluesmoke.sourceforge.net/>
-
-	  and:
-
-	  <http://buttersideup.com/edacwiki>
-
-	  There is also a mailing list for the EDAC project, which can
-	  be found via the sourceforge page.
+	  The mailing list for the EDAC project is linux-edac@vger.kernel.org.
 
 if EDAC
 
@@ -43,6 +33,7 @@ config EDAC_LEGACY_SYSFS
 
 config EDAC_DEBUG
 	bool "Debugging"
+	select DEBUG_FS
 	help
 	  This turns on debugging information for the entire EDAC subsystem.
 	  You do so by inserting edac_module with "edac_debug_level=x." Valid
@@ -61,21 +52,9 @@ config EDAC_DECODE_MCE
 	  which occur really early upon boot, before the module infrastructure
 	  has been initialized.
 
-config EDAC_MM_EDAC
-	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
-	select RAS
-	help
-	  Some systems are able to detect and correct errors in main
-	  memory.  EDAC can report statistics on memory error
-	  detection and correction (EDAC - or commonly referred to ECC
-	  errors).  EDAC will also try to decode where these errors
-	  occurred so that a particular failing memory module can be
-	  replaced.  If unsure, select 'Y'.
-
 config EDAC_GHES
 	bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"
-	depends on ACPI_APEI_GHES && (EDAC_MM_EDAC=y)
-	default y
+	depends on ACPI_APEI_GHES && (EDAC=y)
 	help
 	  Not all machines support hardware-driven error report. Some of those
 	  provide a BIOS-driven error report mechanism via ACPI, using the
@@ -97,7 +76,7 @@ config EDAC_GHES
 
 config EDAC_AMD64
 	tristate "AMD64 (Opteron, Athlon64)"
-	depends on EDAC_MM_EDAC && AMD_NB && EDAC_DECODE_MCE
+	depends on AMD_NB && EDAC_DECODE_MCE
 	help
 	  Support for error detection and correction of DRAM ECC errors on
 	  the AMD64 families (>= K8) of memory controllers.
@@ -123,28 +102,28 @@ config EDAC_AMD64_ERROR_INJECTION
 
 config EDAC_AMD76X
 	tristate "AMD 76x (760, 762, 768)"
-	depends on EDAC_MM_EDAC && PCI && X86_32
+	depends on PCI && X86_32
 	help
 	  Support for error detection and correction on the AMD 76x
 	  series of chipsets used with the Athlon processor.
 
 config EDAC_E7XXX
 	tristate "Intel e7xxx (e7205, e7500, e7501, e7505)"
-	depends on EDAC_MM_EDAC && PCI && X86_32
+	depends on PCI && X86_32
 	help
 	  Support for error detection and correction on the Intel
 	  E7205, E7500, E7501 and E7505 server chipsets.
 
 config EDAC_E752X
 	tristate "Intel e752x (e7520, e7525, e7320) and 3100"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction on the Intel
 	  E7520, E7525, E7320 server chipsets.
 
 config EDAC_I82443BXGX
 	tristate "Intel 82443BX/GX (440BX/GX)"
-	depends on EDAC_MM_EDAC && PCI && X86_32
+	depends on PCI && X86_32
 	depends on BROKEN
 	help
 	  Support for error detection and correction on the Intel
@@ -152,56 +131,56 @@ config EDAC_I82443BXGX
 
 config EDAC_I82875P
 	tristate "Intel 82875p (D82875P, E7210)"
-	depends on EDAC_MM_EDAC && PCI && X86_32
+	depends on PCI && X86_32
 	help
 	  Support for error detection and correction on the Intel
 	  DP82785P and E7210 server chipsets.
 
 config EDAC_I82975X
 	tristate "Intel 82975x (D82975x)"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction on the Intel
 	  DP82975x server chipsets.
 
 config EDAC_I3000
 	tristate "Intel 3000/3010"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction on the Intel
 	  3000 and 3010 server chipsets.
 
 config EDAC_I3200
 	tristate "Intel 3200"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction on the Intel
 	  3200 and 3210 server chipsets.
 
 config EDAC_IE31200
 	tristate "Intel e312xx"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction on the Intel
 	  E3-1200 based DRAM controllers.
 
 config EDAC_X38
 	tristate "Intel X38"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction on the Intel
 	  X38 server chipsets.
 
 config EDAC_I5400
 	tristate "Intel 5400 (Seaburg) chipsets"
-	depends on EDAC_MM_EDAC && PCI && X86
+	depends on PCI && X86
 	help
 	  Support for error detection and correction the Intel
 	  i5400 MCH chipset (Seaburg).
 
 config EDAC_I7CORE
 	tristate "Intel i7 Core (Nehalem) processors"
-	depends on EDAC_MM_EDAC && PCI && X86 && X86_MCE_INTEL
+	depends on PCI && X86 && X86_MCE_INTEL
 	help
 	  Support for error detection and correction the Intel
 	  i7 Core (Nehalem) Integrated Memory Controller that exists on
@@ -210,87 +189,93 @@ config EDAC_I7CORE
 
 config EDAC_I82860
 	tristate "Intel 82860"
-	depends on EDAC_MM_EDAC && PCI && X86_32
+	depends on PCI && X86_32
 	help
 	  Support for error detection and correction on the Intel
 	  82860 chipset.
 
 config EDAC_R82600
 	tristate "Radisys 82600 embedded chipset"
-	depends on EDAC_MM_EDAC && PCI && X86_32
+	depends on PCI && X86_32
 	help
 	  Support for error detection and correction on the Radisys
 	  82600 embedded chipset.
 
 config EDAC_I5000
 	tristate "Intel Greencreek/Blackford chipset"
-	depends on EDAC_MM_EDAC && X86 && PCI
+	depends on X86 && PCI
 	help
 	  Support for error detection and correction the Intel
 	  Greekcreek/Blackford chipsets.
 
 config EDAC_I5100
 	tristate "Intel San Clemente MCH"
-	depends on EDAC_MM_EDAC && X86 && PCI
+	depends on X86 && PCI
 	help
 	  Support for error detection and correction the Intel
 	  San Clemente MCH.
 
 config EDAC_I7300
 	tristate "Intel Clarksboro MCH"
-	depends on EDAC_MM_EDAC && X86 && PCI
+	depends on X86 && PCI
 	help
 	  Support for error detection and correction the Intel
 	  Clarksboro MCH (Intel 7300 chipset).
 
 config EDAC_SBRIDGE
 	tristate "Intel Sandy-Bridge/Ivy-Bridge/Haswell Integrated MC"
-	depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
-	depends on PCI_MMCONFIG
+	depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG
 	help
 	  Support for error detection and correction the Intel
 	  Sandy Bridge, Ivy Bridge and Haswell Integrated Memory Controllers.
 
 config EDAC_SKX
 	tristate "Intel Skylake server Integrated MC"
-	depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
-	depends on PCI_MMCONFIG
+	depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG
 	help
 	  Support for error detection and correction the Intel
 	  Skylake server Integrated Memory Controllers.
 
+config EDAC_PND2
+	tristate "Intel Pondicherry2"
+	depends on PCI && X86_64 && X86_MCE_INTEL
+	help
+	  Support for error detection and correction on the Intel
+	  Pondicherry2 Integrated Memory Controller. This SoC IP is
+	  first used on the Apollo Lake platform and Denverton
+	  micro-server but may appear on others in the future.
+
 config EDAC_MPC85XX
 	tristate "Freescale MPC83xx / MPC85xx"
-	depends on EDAC_MM_EDAC && FSL_SOC
+	depends on FSL_SOC
 	help
 	  Support for error detection and correction on the Freescale
 	  MPC8349, MPC8560, MPC8540, MPC8548, T4240
 
 config EDAC_LAYERSCAPE
 	tristate "Freescale Layerscape DDR"
-	depends on EDAC_MM_EDAC && ARCH_LAYERSCAPE
+	depends on ARCH_LAYERSCAPE
 	help
 	  Support for error detection and correction on Freescale memory
 	  controllers on Layerscape SoCs.
 
 config EDAC_MV64X60
 	tristate "Marvell MV64x60"
-	depends on EDAC_MM_EDAC && MV64X60
+	depends on MV64X60
 	help
 	  Support for error detection and correction on the Marvell
 	  MV64360 and MV64460 chipsets.
 
 config EDAC_PASEMI
 	tristate "PA Semi PWRficient"
-	depends on EDAC_MM_EDAC && PCI
-	depends on PPC_PASEMI
+	depends on PPC_PASEMI && PCI
 	help
 	  Support for error detection and correction on PA Semi
 	  PWRficient.
 
 config EDAC_CELL
 	tristate "Cell Broadband Engine memory controller"
-	depends on EDAC_MM_EDAC && PPC_CELL_COMMON
+	depends on PPC_CELL_COMMON
 	help
 	  Support for error detection and correction on the
 	  Cell Broadband Engine internal memory controller
@@ -298,7 +283,7 @@ config EDAC_CELL
 
 config EDAC_PPC4XX
 	tristate "PPC4xx IBM DDR2 Memory Controller"
-	depends on EDAC_MM_EDAC && 4xx
+	depends on 4xx
 	help
 	  This enables support for EDAC on the ECC memory used
 	  with the IBM DDR2 memory controller found in various
@@ -307,7 +292,7 @@ config EDAC_PPC4XX
 
 config EDAC_AMD8131
 	tristate "AMD8131 HyperTransport PCI-X Tunnel"
-	depends on EDAC_MM_EDAC && PCI && PPC_MAPLE
+	depends on PCI && PPC_MAPLE
 	help
 	  Support for error detection and correction on the
 	  AMD8131 HyperTransport PCI-X Tunnel chip.
@@ -316,7 +301,7 @@ config EDAC_AMD8131
 
 config EDAC_AMD8111
 	tristate "AMD8111 HyperTransport I/O Hub"
-	depends on EDAC_MM_EDAC && PCI && PPC_MAPLE
+	depends on PCI && PPC_MAPLE
 	help
 	  Support for error detection and correction on the
 	  AMD8111 HyperTransport I/O Hub chip.
@@ -325,7 +310,7 @@ config EDAC_AMD8111
 
 config EDAC_CPC925
 	tristate "IBM CPC925 Memory Controller (PPC970FX)"
-	depends on EDAC_MM_EDAC && PPC64
+	depends on PPC64
 	help
 	  Support for error detection and correction on the
 	  IBM CPC925 Bridge and Memory Controller, which is
@@ -334,7 +319,7 @@ config EDAC_CPC925
 
 config EDAC_TILE
 	tristate "Tilera Memory Controller"
-	depends on EDAC_MM_EDAC && TILE
+	depends on TILE
 	default y
 	help
 	  Support for error detection and correction on the
@@ -342,49 +327,59 @@ config EDAC_TILE
 
 config EDAC_HIGHBANK_MC
 	tristate "Highbank Memory Controller"
-	depends on EDAC_MM_EDAC && ARCH_HIGHBANK
+	depends on ARCH_HIGHBANK
 	help
 	  Support for error detection and correction on the
 	  Calxeda Highbank memory controller.
 
 config EDAC_HIGHBANK_L2
 	tristate "Highbank L2 Cache"
-	depends on EDAC_MM_EDAC && ARCH_HIGHBANK
+	depends on ARCH_HIGHBANK
 	help
 	  Support for error detection and correction on the
 	  Calxeda Highbank memory controller.
 
 config EDAC_OCTEON_PC
 	tristate "Cavium Octeon Primary Caches"
-	depends on EDAC_MM_EDAC && CPU_CAVIUM_OCTEON
+	depends on CPU_CAVIUM_OCTEON
 	help
 	  Support for error detection and correction on the primary caches of
 	  the cnMIPS cores of Cavium Octeon family SOCs.
 
 config EDAC_OCTEON_L2C
 	tristate "Cavium Octeon Secondary Caches (L2C)"
-	depends on EDAC_MM_EDAC && CAVIUM_OCTEON_SOC
+	depends on CAVIUM_OCTEON_SOC
 	help
 	  Support for error detection and correction on the
 	  Cavium Octeon family of SOCs.
 
 config EDAC_OCTEON_LMC
 	tristate "Cavium Octeon DRAM Memory Controller (LMC)"
-	depends on EDAC_MM_EDAC && CAVIUM_OCTEON_SOC
+	depends on CAVIUM_OCTEON_SOC
 	help
 	  Support for error detection and correction on the
 	  Cavium Octeon family of SOCs.
 
 config EDAC_OCTEON_PCI
 	tristate "Cavium Octeon PCI Controller"
-	depends on EDAC_MM_EDAC && PCI && CAVIUM_OCTEON_SOC
+	depends on PCI && CAVIUM_OCTEON_SOC
 	help
 	  Support for error detection and correction on the
 	  Cavium Octeon family of SOCs.
 
+config EDAC_THUNDERX
+	tristate "Cavium ThunderX EDAC"
+	depends on ARM64
+	depends on PCI
+	help
+	  Support for error detection and correction on the
+	  Cavium ThunderX memory controllers (LMC), Cache
+	  Coherent Processor Interconnect (CCPI) and L2 cache
+	  blocks (TAD, CBC, MCI).
+
 config EDAC_ALTERA
 	bool "Altera SOCFPGA ECC"
-	depends on EDAC_MM_EDAC=y && ARCH_SOCFPGA
+	depends on EDAC=y && ARCH_SOCFPGA
 	help
 	  Support for error detection and correction on the
 	  Altera SOCs. This must be selected for SDRAM ECC.
@@ -450,14 +445,14 @@ config EDAC_ALTERA_SDMMC
 
 config EDAC_SYNOPSYS
 	tristate "Synopsys DDR Memory Controller"
-	depends on EDAC_MM_EDAC && ARCH_ZYNQ
+	depends on ARCH_ZYNQ
 	help
 	  Support for error detection and correction on the Synopsys DDR
 	  memory controller.
 
 config EDAC_XGENE
 	tristate "APM X-Gene SoC"
-	depends on EDAC_MM_EDAC && (ARM64 || COMPILE_TEST)
+	depends on (ARM64 || COMPILE_TEST)
 	help
 	  Support for error detection and correction on the
 	  APM X-Gene family of SOCs.
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 88e472e8b9a9..0fd9ffa63299 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -6,8 +6,7 @@
 # GNU General Public License.
 #
 
-obj-$(CONFIG_EDAC)			:= edac_stub.o
-obj-$(CONFIG_EDAC_MM_EDAC)		+= edac_core.o
+obj-$(CONFIG_EDAC)			:= edac_core.o
 
 edac_core-y	:= edac_mc.o edac_device.o edac_mc_sysfs.o
 edac_core-y	+= edac_module.o edac_device_sysfs.o wq.o
@@ -32,6 +31,7 @@ obj-$(CONFIG_EDAC_I7300)		+= i7300_edac.o
 obj-$(CONFIG_EDAC_I7CORE)		+= i7core_edac.o
 obj-$(CONFIG_EDAC_SBRIDGE)		+= sb_edac.o
 obj-$(CONFIG_EDAC_SKX)			+= skx_edac.o
+obj-$(CONFIG_EDAC_PND2)			+= pnd2_edac.o
 obj-$(CONFIG_EDAC_E7XXX)		+= e7xxx_edac.o
 obj-$(CONFIG_EDAC_E752X)		+= e752x_edac.o
 obj-$(CONFIG_EDAC_I82443BXGX)		+= i82443bxgx_edac.o
@@ -66,13 +66,14 @@ obj-$(CONFIG_EDAC_AMD8131)		+= amd8131_edac.o
 
 obj-$(CONFIG_EDAC_TILE)			+= tile_edac.o
 
-obj-$(CONFIG_EDAC_HIGHBANK_MC)	+= highbank_mc_edac.o
-obj-$(CONFIG_EDAC_HIGHBANK_L2)	+= highbank_l2_edac.o
+obj-$(CONFIG_EDAC_HIGHBANK_MC)		+= highbank_mc_edac.o
+obj-$(CONFIG_EDAC_HIGHBANK_L2)		+= highbank_l2_edac.o
 
 obj-$(CONFIG_EDAC_OCTEON_PC)		+= octeon_edac-pc.o
 obj-$(CONFIG_EDAC_OCTEON_L2C)		+= octeon_edac-l2c.o
 obj-$(CONFIG_EDAC_OCTEON_LMC)		+= octeon_edac-lmc.o
 obj-$(CONFIG_EDAC_OCTEON_PCI)		+= octeon_edac-pci.o
+obj-$(CONFIG_EDAC_THUNDERX)		+= thunderx_edac.o
 
 obj-$(CONFIG_EDAC_ALTERA)		+= altera_edac.o
 obj-$(CONFIG_EDAC_SYNOPSYS)		+= synopsys_edac.o
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index c5a5b91f37f0..7717b094fabb 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -1023,13 +1023,23 @@ out:
 	return ret;
 }
 
+static int socfpga_is_a10(void)
+{
+	return of_machine_is_compatible("altr,socfpga-arria10");
+}
+
 static int validate_parent_available(struct device_node *np);
 static const struct of_device_id altr_edac_a10_device_of_match[];
 static int __init __maybe_unused altr_init_a10_ecc_device_type(char *compat)
 {
 	int irq;
-	struct device_node *child, *np = of_find_compatible_node(NULL, NULL,
-					"altr,socfpga-a10-ecc-manager");
+	struct device_node *child, *np;
+
+	if (!socfpga_is_a10())
+		return -ENODEV;
+
+	np = of_find_compatible_node(NULL, NULL,
+				     "altr,socfpga-a10-ecc-manager");
 	if (!np) {
 		edac_printk(KERN_ERR, EDAC_DEVICE, "ECC Manager not found\n");
 		return -ENODEV;
@@ -1545,8 +1555,12 @@ static const struct edac_device_prv_data a10_sdmmceccb_data = {
 static int __init socfpga_init_sdmmc_ecc(void)
 {
 	int rc = -ENODEV;
-	struct device_node *child = of_find_compatible_node(NULL, NULL,
-						"altr,socfpga-sdmmc-ecc");
+	struct device_node *child;
+
+	if (!socfpga_is_a10())
+		return -ENODEV;
+
+	child = of_find_compatible_node(NULL, NULL, "altr,socfpga-sdmmc-ecc");
 	if (!child) {
 		edac_printk(KERN_WARNING, EDAC_DEVICE, "SDMMC node not found\n");
 		return -ENODEV;
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index e5573c56b15e..480072139b7a 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -40,6 +40,11 @@
 #define edac_atomic_scrub(va, size) do { } while (0)
 #endif
 
+int edac_op_state = EDAC_OPSTATE_INVAL;
+EXPORT_SYMBOL_GPL(edac_op_state);
+
+static int edac_report = EDAC_REPORTING_ENABLED;
+
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
 static LIST_HEAD(mc_devices);
@@ -52,6 +57,65 @@ static void const *edac_mc_owner;
 
 static struct bus_type mc_bus[EDAC_MAX_MCS];
 
+int edac_get_report_status(void)
+{
+	return edac_report;
+}
+EXPORT_SYMBOL_GPL(edac_get_report_status);
+
+void edac_set_report_status(int new)
+{
+	if (new == EDAC_REPORTING_ENABLED ||
+	    new == EDAC_REPORTING_DISABLED ||
+	    new == EDAC_REPORTING_FORCE)
+		edac_report = new;
+}
+EXPORT_SYMBOL_GPL(edac_set_report_status);
+
+static int edac_report_set(const char *str, const struct kernel_param *kp)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		edac_report = EDAC_REPORTING_ENABLED;
+	else if (!strncmp(str, "off", 3))
+		edac_report = EDAC_REPORTING_DISABLED;
+	else if (!strncmp(str, "force", 5))
+		edac_report = EDAC_REPORTING_FORCE;
+
+	return 0;
+}
+
+static int edac_report_get(char *buffer, const struct kernel_param *kp)
+{
+	int ret = 0;
+
+	switch (edac_report) {
+	case EDAC_REPORTING_ENABLED:
+		ret = sprintf(buffer, "on");
+		break;
+	case EDAC_REPORTING_DISABLED:
+		ret = sprintf(buffer, "off");
+		break;
+	case EDAC_REPORTING_FORCE:
+		ret = sprintf(buffer, "force");
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct kernel_param_ops edac_report_ops = {
+	.set = edac_report_set,
+	.get = edac_report_get,
+};
+
+module_param_cb(edac_report, &edac_report_ops, &edac_report, 0644);
+
 unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
 			         unsigned len)
 {
@@ -505,22 +569,6 @@ struct mem_ctl_info *find_mci_by_dev(struct device *dev)
 EXPORT_SYMBOL_GPL(find_mci_by_dev);
 
 /*
- * handler for EDAC to check if NMI type handler has asserted interrupt
- */
-static int edac_mc_assert_error_check_and_clear(void)
-{
-	int old_state;
-
-	if (edac_op_state == EDAC_OPSTATE_POLL)
-		return 1;
-
-	old_state = edac_err_assert;
-	edac_err_assert = 0;
-
-	return old_state;
-}
-
-/*
  * edac_mc_workq_function
  *	performs the operation scheduled by a workq request
  */
@@ -536,7 +584,7 @@ static void edac_mc_workq_function(struct work_struct *work_req)
 		return;
 	}
 
-	if (edac_mc_assert_error_check_and_clear())
+	if (edac_op_state == EDAC_OPSTATE_POLL)
 		mci->edac_check(mci);
 
 	mutex_unlock(&mem_ctls_mutex);
@@ -601,7 +649,6 @@ static int add_mc_to_global_list(struct mem_ctl_info *mci)
 	}
 
 	list_add_tail_rcu(&mci->link, insert_before);
-	atomic_inc(&edac_handlers);
 	return 0;
 
 fail0:
@@ -619,7 +666,6 @@ fail1:
 
 static int del_mc_from_global_list(struct mem_ctl_info *mci)
 {
-	int handlers = atomic_dec_return(&edac_handlers);
 	list_del_rcu(&mci->link);
 
 	/* these are for safe removal of devices from global list while
@@ -628,7 +674,7 @@ static int del_mc_from_global_list(struct mem_ctl_info *mci)
 	synchronize_rcu();
 	INIT_LIST_HEAD(&mci->link);
 
-	return handlers;
+	return list_empty(&mc_devices);
 }
 
 struct mem_ctl_info *edac_mc_find(int idx)
@@ -763,7 +809,7 @@ struct mem_ctl_info *edac_mc_del_mc(struct device *dev)
 	/* mark MCI offline: */
 	mci->op_state = OP_OFFLINE;
 
-	if (!del_mc_from_global_list(mci))
+	if (del_mc_from_global_list(mci))
 		edac_mc_owner = NULL;
 
 	mutex_unlock(&mem_ctls_mutex);
@@ -1195,10 +1241,13 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 
 	/* Report the error via the trace interface */
 	grain_bits = fls_long(e->grain) + 1;
-	trace_mc_event(type, e->msg, e->label, e->error_count,
-		       mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer,
-		       (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
-		       grain_bits, e->syndrome, e->other_detail);
+
+	if (IS_ENABLED(CONFIG_RAS))
+		trace_mc_event(type, e->msg, e->label, e->error_count,
+			       mci->mc_idx, e->top_layer, e->mid_layer,
+			       e->low_layer,
+			       (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
+			       grain_bits, e->syndrome, e->other_detail);
 
 	edac_raw_mc_handle_error(type, mci, e);
 }
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
deleted file mode 100644
index 952e411f01f2..000000000000
--- a/drivers/edac/edac_stub.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * common EDAC components that must be in kernel
- *
- * Author: Dave Jiang <djiang@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc.
- * 2010 (c) Advanced Micro Devices Inc.
- *	    Borislav Petkov <bp@alien8.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- *
- */
-#include <linux/module.h>
-#include <linux/edac.h>
-#include <linux/atomic.h>
-#include <linux/device.h>
-
-int edac_op_state = EDAC_OPSTATE_INVAL;
-EXPORT_SYMBOL_GPL(edac_op_state);
-
-atomic_t edac_handlers = ATOMIC_INIT(0);
-EXPORT_SYMBOL_GPL(edac_handlers);
-
-int edac_err_assert = 0;
-EXPORT_SYMBOL_GPL(edac_err_assert);
-
-int edac_report_status = EDAC_REPORTING_ENABLED;
-EXPORT_SYMBOL_GPL(edac_report_status);
-
-static int __init edac_report_setup(char *str)
-{
-	if (!str)
-		return -EINVAL;
-
-	if (!strncmp(str, "on", 2))
-		set_edac_report_status(EDAC_REPORTING_ENABLED);
-	else if (!strncmp(str, "off", 3))
-		set_edac_report_status(EDAC_REPORTING_DISABLED);
-	else if (!strncmp(str, "force", 5))
-		set_edac_report_status(EDAC_REPORTING_FORCE);
-
-	return 0;
-}
-__setup("edac_report=", edac_report_setup);
-
-/*
- * called to determine if there is an EDAC driver interested in
- * knowing an event (such as NMI) occurred
- */
-int edac_handler_set(void)
-{
-	if (edac_op_state == EDAC_OPSTATE_POLL)
-		return 0;
-
-	return atomic_read(&edac_handlers);
-}
-EXPORT_SYMBOL_GPL(edac_handler_set);
-
-/*
- * handler for NMI type of interrupts to assert error
- */
-void edac_atomic_assert_error(void)
-{
-	edac_err_assert++;
-}
-EXPORT_SYMBOL_GPL(edac_atomic_assert_error);
diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c
index 1670d27bcac8..f683919981b0 100644
--- a/drivers/edac/i5000_edac.c
+++ b/drivers/edac/i5000_edac.c
@@ -1293,7 +1293,7 @@ static int i5000_init_csrows(struct mem_ctl_info *mci)
 			dimm->mtype = MEM_FB_DDR2;
 
 			/* ask what device type on this row */
-			if (MTR_DRAM_WIDTH(mtr))
+			if (MTR_DRAM_WIDTH(mtr) == 8)
 				dimm->dtype = DEV_X8;
 			else
 				dimm->dtype = DEV_X4;
diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c
index abf6ef22e220..37a9ba71da44 100644
--- a/drivers/edac/i5400_edac.c
+++ b/drivers/edac/i5400_edac.c
@@ -1207,13 +1207,14 @@ static int i5400_init_dimms(struct mem_ctl_info *mci)
 
 			dimm->nr_pages = size_mb << 8;
 			dimm->grain = 8;
-			dimm->dtype = MTR_DRAM_WIDTH(mtr) ? DEV_X8 : DEV_X4;
+			dimm->dtype = MTR_DRAM_WIDTH(mtr) == 8 ?
+				      DEV_X8 : DEV_X4;
 			dimm->mtype = MEM_FB_DDR2;
 			/*
 			 * The eccc mechanism is SDDC (aka SECC), with
 			 * is similar to Chipkill.
 			 */
-			dimm->edac_mode = MTR_DRAM_WIDTH(mtr) ?
+			dimm->edac_mode = MTR_DRAM_WIDTH(mtr) == 8 ?
 					  EDAC_S8ECD8ED : EDAC_S4ECD4ED;
 			ndimms++;
 		}
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
new file mode 100644
index 000000000000..1cad5a9af8d0
--- /dev/null
+++ b/drivers/edac/pnd2_edac.c
@@ -0,0 +1,1546 @@
+/*
+ * Driver for Pondicherry2 memory controller.
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * [Derived from sb_edac.c]
+ *
+ * Translation of system physical addresses to DIMM addresses
+ * is a two stage process:
+ *
+ * First the Pondicherry 2 memory controller handles slice and channel interleaving
+ * in "sys2pmi()". This is (almost) completley common between platforms.
+ *
+ * Then a platform specific dunit (DIMM unit) completes the process to provide DIMM,
+ * rank, bank, row and column using the appropriate "dunit_ops" functions/parameters.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/edac.h>
+#include <linux/mmzone.h>
+#include <linux/smp.h>
+#include <linux/bitmap.h>
+#include <linux/math64.h>
+#include <linux/mod_devicetable.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/processor.h>
+#include <asm/mce.h>
+
+#include "edac_mc.h"
+#include "edac_module.h"
+#include "pnd2_edac.h"
+
+#define APL_NUM_CHANNELS	4
+#define DNV_NUM_CHANNELS	2
+#define DNV_MAX_DIMMS		2 /* Max DIMMs per channel */
+
+enum type {
+	APL,
+	DNV, /* All requests go to PMI CH0 on each slice (CH1 disabled) */
+};
+
+struct dram_addr {
+	int chan;
+	int dimm;
+	int rank;
+	int bank;
+	int row;
+	int col;
+};
+
+struct pnd2_pvt {
+	int dimm_geom[APL_NUM_CHANNELS];
+	u64 tolm, tohm;
+};
+
+/*
+ * System address space is divided into multiple regions with
+ * different interleave rules in each. The as0/as1 regions
+ * have no interleaving at all. The as2 region is interleaved
+ * between two channels. The mot region is magic and may overlap
+ * other regions, with its interleave rules taking precedence.
+ * Addresses not in any of these regions are interleaved across
+ * all four channels.
+ */
+static struct region {
+	u64	base;
+	u64	limit;
+	u8	enabled;
+} mot, as0, as1, as2;
+
+static struct dunit_ops {
+	char *name;
+	enum type type;
+	int pmiaddr_shift;
+	int pmiidx_shift;
+	int channels;
+	int dimms_per_channel;
+	int (*rd_reg)(int port, int off, int op, void *data, size_t sz, char *name);
+	int (*get_registers)(void);
+	int (*check_ecc)(void);
+	void (*mk_region)(char *name, struct region *rp, void *asym);
+	void (*get_dimm_config)(struct mem_ctl_info *mci);
+	int (*pmi2mem)(struct mem_ctl_info *mci, u64 pmiaddr, u32 pmiidx,
+				   struct dram_addr *daddr, char *msg);
+} *ops;
+
+static struct mem_ctl_info *pnd2_mci;
+
+#define PND2_MSG_SIZE	256
+
+/* Debug macros */
+#define pnd2_printk(level, fmt, arg...)			\
+	edac_printk(level, "pnd2", fmt, ##arg)
+
+#define pnd2_mc_printk(mci, level, fmt, arg...)	\
+	edac_mc_chipset_printk(mci, level, "pnd2", fmt, ##arg)
+
+#define MOT_CHAN_INTLV_BIT_1SLC_2CH 12
+#define MOT_CHAN_INTLV_BIT_2SLC_2CH 13
+#define SELECTOR_DISABLED (-1)
+#define _4GB (1ul << 32)
+
+#define PMI_ADDRESS_WIDTH	31
+#define PND_MAX_PHYS_BIT	39
+
+#define APL_ASYMSHIFT		28
+#define DNV_ASYMSHIFT		31
+#define CH_HASH_MASK_LSB	6
+#define SLICE_HASH_MASK_LSB	6
+#define MOT_SLC_INTLV_BIT	12
+#define LOG2_PMI_ADDR_GRANULARITY	5
+#define MOT_SHIFT	24
+
+#define GET_BITFIELD(v, lo, hi)	(((v) & GENMASK_ULL(hi, lo)) >> (lo))
+#define U64_LSHIFT(val, s)	((u64)(val) << (s))
+
+#ifdef CONFIG_X86_INTEL_SBI_APL
+#include "linux/platform_data/sbi_apl.h"
+int sbi_send(int port, int off, int op, u32 *data)
+{
+	struct sbi_apl_message sbi_arg;
+	int ret, read = 0;
+
+	memset(&sbi_arg, 0, sizeof(sbi_arg));
+
+	if (op == 0 || op == 4 || op == 6)
+		read = 1;
+	else
+		sbi_arg.data = *data;
+
+	sbi_arg.opcode = op;
+	sbi_arg.port_address = port;
+	sbi_arg.register_offset = off;
+	ret = sbi_apl_commit(&sbi_arg);
+	if (ret || sbi_arg.status)
+		edac_dbg(2, "sbi_send status=%d ret=%d data=%x\n",
+				 sbi_arg.status, ret, sbi_arg.data);
+
+	if (ret == 0)
+		ret = sbi_arg.status;
+
+	if (ret == 0 && read)
+		*data = sbi_arg.data;
+
+	return ret;
+}
+#else
+int sbi_send(int port, int off, int op, u32 *data)
+{
+	return -EUNATCH;
+}
+#endif
+
+static int apl_rd_reg(int port, int off, int op, void *data, size_t sz, char *name)
+{
+	int	ret = 0;
+
+	edac_dbg(2, "Read %s port=%x off=%x op=%x\n", name, port, off, op);
+	switch (sz) {
+	case 8:
+		ret = sbi_send(port, off + 4, op, (u32 *)(data + 4));
+	case 4:
+		ret = sbi_send(port, off, op, (u32 *)data);
+		pnd2_printk(KERN_DEBUG, "%s=%x%08x ret=%d\n", name,
+					sz == 8 ? *((u32 *)(data + 4)) : 0, *((u32 *)data), ret);
+		break;
+	}
+
+	return ret;
+}
+
+static u64 get_mem_ctrl_hub_base_addr(void)
+{
+	struct b_cr_mchbar_lo_pci lo;
+	struct b_cr_mchbar_hi_pci hi;
+	struct pci_dev *pdev;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x1980, NULL);
+	if (pdev) {
+		pci_read_config_dword(pdev, 0x48, (u32 *)&lo);
+		pci_read_config_dword(pdev, 0x4c, (u32 *)&hi);
+		pci_dev_put(pdev);
+	} else {
+		return 0;
+	}
+
+	if (!lo.enable) {
+		edac_dbg(2, "MMIO via memory controller hub base address is disabled!\n");
+		return 0;
+	}
+
+	return U64_LSHIFT(hi.base, 32) | U64_LSHIFT(lo.base, 15);
+}
+
+static u64 get_sideband_reg_base_addr(void)
+{
+	struct pci_dev *pdev;
+	u32 hi, lo;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x19dd, NULL);
+	if (pdev) {
+		pci_read_config_dword(pdev, 0x10, &lo);
+		pci_read_config_dword(pdev, 0x14, &hi);
+		pci_dev_put(pdev);
+		return (U64_LSHIFT(hi, 32) | U64_LSHIFT(lo, 0));
+	} else {
+		return 0xfd000000;
+	}
+}
+
+static int dnv_rd_reg(int port, int off, int op, void *data, size_t sz, char *name)
+{
+	struct pci_dev *pdev;
+	char *base;
+	u64 addr;
+
+	if (op == 4) {
+		pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x1980, NULL);
+		if (!pdev)
+			return -ENODEV;
+
+		pci_read_config_dword(pdev, off, data);
+		pci_dev_put(pdev);
+	} else {
+		/* MMIO via memory controller hub base address */
+		if (op == 0 && port == 0x4c) {
+			addr = get_mem_ctrl_hub_base_addr();
+			if (!addr)
+				return -ENODEV;
+		} else {
+			/* MMIO via sideband register base address */
+			addr = get_sideband_reg_base_addr();
+			if (!addr)
+				return -ENODEV;
+			addr += (port << 16);
+		}
+
+		base = ioremap((resource_size_t)addr, 0x10000);
+		if (!base)
+			return -ENODEV;
+
+		if (sz == 8)
+			*(u32 *)(data + 4) = *(u32 *)(base + off + 4);
+		*(u32 *)data = *(u32 *)(base + off);
+
+		iounmap(base);
+	}
+
+	edac_dbg(2, "Read %s=%.8x_%.8x\n", name,
+			(sz == 8) ? *(u32 *)(data + 4) : 0, *(u32 *)data);
+
+	return 0;
+}
+
+#define RD_REGP(regp, regname, port)	\
+	ops->rd_reg(port,					\
+		regname##_offset,				\
+		regname##_r_opcode,				\
+		regp, sizeof(struct regname),	\
+		#regname)
+
+#define RD_REG(regp, regname)			\
+	ops->rd_reg(regname ## _port,		\
+		regname##_offset,				\
+		regname##_r_opcode,				\
+		regp, sizeof(struct regname),	\
+		#regname)
+
+static u64 top_lm, top_hm;
+static bool two_slices;
+static bool two_channels; /* Both PMI channels in one slice enabled */
+
+static u8 sym_chan_mask;
+static u8 asym_chan_mask;
+static u8 chan_mask;
+
+static int slice_selector = -1;
+static int chan_selector = -1;
+static u64 slice_hash_mask;
+static u64 chan_hash_mask;
+
+static void mk_region(char *name, struct region *rp, u64 base, u64 limit)
+{
+	rp->enabled = 1;
+	rp->base = base;
+	rp->limit = limit;
+	edac_dbg(2, "Region:%s [%llx, %llx]\n", name, base, limit);
+}
+
+static void mk_region_mask(char *name, struct region *rp, u64 base, u64 mask)
+{
+	if (mask == 0) {
+		pr_info(FW_BUG "MOT mask cannot be zero\n");
+		return;
+	}
+	if (mask != GENMASK_ULL(PND_MAX_PHYS_BIT, __ffs(mask))) {
+		pr_info(FW_BUG "MOT mask not power of two\n");
+		return;
+	}
+	if (base & ~mask) {
+		pr_info(FW_BUG "MOT region base/mask alignment error\n");
+		return;
+	}
+	rp->base = base;
+	rp->limit = (base | ~mask) & GENMASK_ULL(PND_MAX_PHYS_BIT, 0);
+	rp->enabled = 1;
+	edac_dbg(2, "Region:%s [%llx, %llx]\n", name, base, rp->limit);
+}
+
+static bool in_region(struct region *rp, u64 addr)
+{
+	if (!rp->enabled)
+		return false;
+
+	return rp->base <= addr && addr <= rp->limit;
+}
+
+static int gen_sym_mask(struct b_cr_slice_channel_hash *p)
+{
+	int mask = 0;
+
+	if (!p->slice_0_mem_disabled)
+		mask |= p->sym_slice0_channel_enabled;
+
+	if (!p->slice_1_disabled)
+		mask |= p->sym_slice1_channel_enabled << 2;
+
+	if (p->ch_1_disabled || p->enable_pmi_dual_data_mode)
+		mask &= 0x5;
+
+	return mask;
+}
+
+static int gen_asym_mask(struct b_cr_slice_channel_hash *p,
+			 struct b_cr_asym_mem_region0_mchbar *as0,
+			 struct b_cr_asym_mem_region1_mchbar *as1,
+			 struct b_cr_asym_2way_mem_region_mchbar *as2way)
+{
+	const int intlv[] = { 0x5, 0xA, 0x3, 0xC };
+	int mask = 0;
+
+	if (as2way->asym_2way_interleave_enable)
+		mask = intlv[as2way->asym_2way_intlv_mode];
+	if (as0->slice0_asym_enable)
+		mask |= (1 << as0->slice0_asym_channel_select);
+	if (as1->slice1_asym_enable)
+		mask |= (4 << as1->slice1_asym_channel_select);
+	if (p->slice_0_mem_disabled)
+		mask &= 0xc;
+	if (p->slice_1_disabled)
+		mask &= 0x3;
+	if (p->ch_1_disabled || p->enable_pmi_dual_data_mode)
+		mask &= 0x5;
+
+	return mask;
+}
+
+static struct b_cr_tolud_pci tolud;
+static struct b_cr_touud_lo_pci touud_lo;
+static struct b_cr_touud_hi_pci touud_hi;
+static struct b_cr_asym_mem_region0_mchbar asym0;
+static struct b_cr_asym_mem_region1_mchbar asym1;
+static struct b_cr_asym_2way_mem_region_mchbar asym_2way;
+static struct b_cr_mot_out_base_mchbar mot_base;
+static struct b_cr_mot_out_mask_mchbar mot_mask;
+static struct b_cr_slice_channel_hash chash;
+
+/* Apollo Lake dunit */
+/*
+ * Validated on board with just two DIMMs in the [0] and [2] positions
+ * in this array. Other port number matches documentation, but caution
+ * advised.
+ */
+static const int apl_dports[APL_NUM_CHANNELS] = { 0x18, 0x10, 0x11, 0x19 };
+static struct d_cr_drp0 drp0[APL_NUM_CHANNELS];
+
+/* Denverton dunit */
+static const int dnv_dports[DNV_NUM_CHANNELS] = { 0x10, 0x12 };
+static struct d_cr_dsch dsch;
+static struct d_cr_ecc_ctrl ecc_ctrl[DNV_NUM_CHANNELS];
+static struct d_cr_drp drp[DNV_NUM_CHANNELS];
+static struct d_cr_dmap dmap[DNV_NUM_CHANNELS];
+static struct d_cr_dmap1 dmap1[DNV_NUM_CHANNELS];
+static struct d_cr_dmap2 dmap2[DNV_NUM_CHANNELS];
+static struct d_cr_dmap3 dmap3[DNV_NUM_CHANNELS];
+static struct d_cr_dmap4 dmap4[DNV_NUM_CHANNELS];
+static struct d_cr_dmap5 dmap5[DNV_NUM_CHANNELS];
+
+static void apl_mk_region(char *name, struct region *rp, void *asym)
+{
+	struct b_cr_asym_mem_region0_mchbar *a = asym;
+
+	mk_region(name, rp,
+			  U64_LSHIFT(a->slice0_asym_base, APL_ASYMSHIFT),
+			  U64_LSHIFT(a->slice0_asym_limit, APL_ASYMSHIFT) +
+			  GENMASK_ULL(APL_ASYMSHIFT - 1, 0));
+}
+
+static void dnv_mk_region(char *name, struct region *rp, void *asym)
+{
+	struct b_cr_asym_mem_region_denverton *a = asym;
+
+	mk_region(name, rp,
+			  U64_LSHIFT(a->slice_asym_base, DNV_ASYMSHIFT),
+			  U64_LSHIFT(a->slice_asym_limit, DNV_ASYMSHIFT) +
+			  GENMASK_ULL(DNV_ASYMSHIFT - 1, 0));
+}
+
+static int apl_get_registers(void)
+{
+	int i;
+
+	if (RD_REG(&asym_2way, b_cr_asym_2way_mem_region_mchbar))
+		return -ENODEV;
+
+	for (i = 0; i < APL_NUM_CHANNELS; i++)
+		if (RD_REGP(&drp0[i], d_cr_drp0, apl_dports[i]))
+			return -ENODEV;
+
+	return 0;
+}
+
+static int dnv_get_registers(void)
+{
+	int i;
+
+	if (RD_REG(&dsch, d_cr_dsch))
+		return -ENODEV;
+
+	for (i = 0; i < DNV_NUM_CHANNELS; i++)
+		if (RD_REGP(&ecc_ctrl[i], d_cr_ecc_ctrl, dnv_dports[i]) ||
+			RD_REGP(&drp[i], d_cr_drp, dnv_dports[i]) ||
+			RD_REGP(&dmap[i], d_cr_dmap, dnv_dports[i]) ||
+			RD_REGP(&dmap1[i], d_cr_dmap1, dnv_dports[i]) ||
+			RD_REGP(&dmap2[i], d_cr_dmap2, dnv_dports[i]) ||
+			RD_REGP(&dmap3[i], d_cr_dmap3, dnv_dports[i]) ||
+			RD_REGP(&dmap4[i], d_cr_dmap4, dnv_dports[i]) ||
+			RD_REGP(&dmap5[i], d_cr_dmap5, dnv_dports[i]))
+			return -ENODEV;
+
+	return 0;
+}
+
+/*
+ * Read all the h/w config registers once here (they don't
+ * change at run time. Figure out which address ranges have
+ * which interleave characteristics.
+ */
+static int get_registers(void)
+{
+	const int intlv[] = { 10, 11, 12, 12 };
+
+	if (RD_REG(&tolud, b_cr_tolud_pci) ||
+		RD_REG(&touud_lo, b_cr_touud_lo_pci) ||
+		RD_REG(&touud_hi, b_cr_touud_hi_pci) ||
+		RD_REG(&asym0, b_cr_asym_mem_region0_mchbar) ||
+		RD_REG(&asym1, b_cr_asym_mem_region1_mchbar) ||
+		RD_REG(&mot_base, b_cr_mot_out_base_mchbar) ||
+		RD_REG(&mot_mask, b_cr_mot_out_mask_mchbar) ||
+		RD_REG(&chash, b_cr_slice_channel_hash))
+		return -ENODEV;
+
+	if (ops->get_registers())
+		return -ENODEV;
+
+	if (ops->type == DNV) {
+		/* PMI channel idx (always 0) for asymmetric region */
+		asym0.slice0_asym_channel_select = 0;
+		asym1.slice1_asym_channel_select = 0;
+		/* PMI channel bitmap (always 1) for symmetric region */
+		chash.sym_slice0_channel_enabled = 0x1;
+		chash.sym_slice1_channel_enabled = 0x1;
+	}
+
+	if (asym0.slice0_asym_enable)
+		ops->mk_region("as0", &as0, &asym0);
+
+	if (asym1.slice1_asym_enable)
+		ops->mk_region("as1", &as1, &asym1);
+
+	if (asym_2way.asym_2way_interleave_enable) {
+		mk_region("as2way", &as2,
+				  U64_LSHIFT(asym_2way.asym_2way_base, APL_ASYMSHIFT),
+				  U64_LSHIFT(asym_2way.asym_2way_limit, APL_ASYMSHIFT) +
+				  GENMASK_ULL(APL_ASYMSHIFT - 1, 0));
+	}
+
+	if (mot_base.imr_en) {
+		mk_region_mask("mot", &mot,
+					   U64_LSHIFT(mot_base.mot_out_base, MOT_SHIFT),
+					   U64_LSHIFT(mot_mask.mot_out_mask, MOT_SHIFT));
+	}
+
+	top_lm = U64_LSHIFT(tolud.tolud, 20);
+	top_hm = U64_LSHIFT(touud_hi.touud, 32) | U64_LSHIFT(touud_lo.touud, 20);
+
+	two_slices = !chash.slice_1_disabled &&
+				 !chash.slice_0_mem_disabled &&
+				 (chash.sym_slice0_channel_enabled != 0) &&
+				 (chash.sym_slice1_channel_enabled != 0);
+	two_channels = !chash.ch_1_disabled &&
+				 !chash.enable_pmi_dual_data_mode &&
+				 ((chash.sym_slice0_channel_enabled == 3) ||
+				 (chash.sym_slice1_channel_enabled == 3));
+
+	sym_chan_mask = gen_sym_mask(&chash);
+	asym_chan_mask = gen_asym_mask(&chash, &asym0, &asym1, &asym_2way);
+	chan_mask = sym_chan_mask | asym_chan_mask;
+
+	if (two_slices && !two_channels) {
+		if (chash.hvm_mode)
+			slice_selector = 29;
+		else
+			slice_selector = intlv[chash.interleave_mode];
+	} else if (!two_slices && two_channels) {
+		if (chash.hvm_mode)
+			chan_selector = 29;
+		else
+			chan_selector = intlv[chash.interleave_mode];
+	} else if (two_slices && two_channels) {
+		if (chash.hvm_mode) {
+			slice_selector = 29;
+			chan_selector = 30;
+		} else {
+			slice_selector = intlv[chash.interleave_mode];
+			chan_selector = intlv[chash.interleave_mode] + 1;
+		}
+	}
+
+	if (two_slices) {
+		if (!chash.hvm_mode)
+			slice_hash_mask = chash.slice_hash_mask << SLICE_HASH_MASK_LSB;
+		if (!two_channels)
+			slice_hash_mask |= BIT_ULL(slice_selector);
+	}
+
+	if (two_channels) {
+		if (!chash.hvm_mode)
+			chan_hash_mask = chash.ch_hash_mask << CH_HASH_MASK_LSB;
+		if (!two_slices)
+			chan_hash_mask |= BIT_ULL(chan_selector);
+	}
+
+	return 0;
+}
+
+/* Get a contiguous memory address (remove the MMIO gap) */
+static u64 remove_mmio_gap(u64 sys)
+{
+	return (sys < _4GB) ? sys : sys - (_4GB - top_lm);
+}
+
+/* Squeeze out one address bit, shift upper part down to fill gap */
+static void remove_addr_bit(u64 *addr, int bitidx)
+{
+	u64	mask;
+
+	if (bitidx == -1)
+		return;
+
+	mask = (1ull << bitidx) - 1;
+	*addr = ((*addr >> 1) & ~mask) | (*addr & mask);
+}
+
+/* XOR all the bits from addr specified in mask */
+static int hash_by_mask(u64 addr, u64 mask)
+{
+	u64 result = addr & mask;
+
+	result = (result >> 32) ^ result;
+	result = (result >> 16) ^ result;
+	result = (result >> 8) ^ result;
+	result = (result >> 4) ^ result;
+	result = (result >> 2) ^ result;
+	result = (result >> 1) ^ result;
+
+	return (int)result & 1;
+}
+
+/*
+ * First stage decode. Take the system address and figure out which
+ * second stage will deal with it based on interleave modes.
+ */
+static int sys2pmi(const u64 addr, u32 *pmiidx, u64 *pmiaddr, char *msg)
+{
+	u64 contig_addr, contig_base, contig_offset, contig_base_adj;
+	int mot_intlv_bit = two_slices ? MOT_CHAN_INTLV_BIT_2SLC_2CH :
+						MOT_CHAN_INTLV_BIT_1SLC_2CH;
+	int slice_intlv_bit_rm = SELECTOR_DISABLED;
+	int chan_intlv_bit_rm = SELECTOR_DISABLED;
+	/* Determine if address is in the MOT region. */
+	bool mot_hit = in_region(&mot, addr);
+	/* Calculate the number of symmetric regions enabled. */
+	int sym_channels = hweight8(sym_chan_mask);
+
+	/*
+	 * The amount we need to shift the asym base can be determined by the
+	 * number of enabled symmetric channels.
+	 * NOTE: This can only work because symmetric memory is not supposed
+	 * to do a 3-way interleave.
+	 */
+	int sym_chan_shift = sym_channels >> 1;
+
+	/* Give up if address is out of range, or in MMIO gap */
+	if (addr >= (1ul << PND_MAX_PHYS_BIT) ||
+	   (addr >= top_lm && addr < _4GB) || addr >= top_hm) {
+		snprintf(msg, PND2_MSG_SIZE, "Error address 0x%llx is not DRAM", addr);
+		return -EINVAL;
+	}
+
+	/* Get a contiguous memory address (remove the MMIO gap) */
+	contig_addr = remove_mmio_gap(addr);
+
+	if (in_region(&as0, addr)) {
+		*pmiidx = asym0.slice0_asym_channel_select;
+
+		contig_base = remove_mmio_gap(as0.base);
+		contig_offset = contig_addr - contig_base;
+		contig_base_adj = (contig_base >> sym_chan_shift) *
+						  ((chash.sym_slice0_channel_enabled >> (*pmiidx & 1)) & 1);
+		contig_addr = contig_offset + ((sym_channels > 0) ? contig_base_adj : 0ull);
+	} else if (in_region(&as1, addr)) {
+		*pmiidx = 2u + asym1.slice1_asym_channel_select;
+
+		contig_base = remove_mmio_gap(as1.base);
+		contig_offset = contig_addr - contig_base;
+		contig_base_adj = (contig_base >> sym_chan_shift) *
+						  ((chash.sym_slice1_channel_enabled >> (*pmiidx & 1)) & 1);
+		contig_addr = contig_offset + ((sym_channels > 0) ? contig_base_adj : 0ull);
+	} else if (in_region(&as2, addr) && (asym_2way.asym_2way_intlv_mode == 0x3ul)) {
+		bool channel1;
+
+		mot_intlv_bit = MOT_CHAN_INTLV_BIT_1SLC_2CH;
+		*pmiidx = (asym_2way.asym_2way_intlv_mode & 1) << 1;
+		channel1 = mot_hit ? ((bool)((addr >> mot_intlv_bit) & 1)) :
+			hash_by_mask(contig_addr, chan_hash_mask);
+		*pmiidx |= (u32)channel1;
+
+		contig_base = remove_mmio_gap(as2.base);
+		chan_intlv_bit_rm = mot_hit ? mot_intlv_bit : chan_selector;
+		contig_offset = contig_addr - contig_base;
+		remove_addr_bit(&contig_offset, chan_intlv_bit_rm);
+		contig_addr = (contig_base >> sym_chan_shift) + contig_offset;
+	} else {
+		/* Otherwise we're in normal, boring symmetric mode. */
+		*pmiidx = 0u;
+
+		if (two_slices) {
+			bool slice1;
+
+			if (mot_hit) {
+				slice_intlv_bit_rm = MOT_SLC_INTLV_BIT;
+				slice1 = (addr >> MOT_SLC_INTLV_BIT) & 1;
+			} else {
+				slice_intlv_bit_rm = slice_selector;
+				slice1 = hash_by_mask(addr, slice_hash_mask);
+			}
+
+			*pmiidx = (u32)slice1 << 1;
+		}
+
+		if (two_channels) {
+			bool channel1;
+
+			mot_intlv_bit = two_slices ? MOT_CHAN_INTLV_BIT_2SLC_2CH :
+							MOT_CHAN_INTLV_BIT_1SLC_2CH;
+
+			if (mot_hit) {
+				chan_intlv_bit_rm = mot_intlv_bit;
+				channel1 = (addr >> mot_intlv_bit) & 1;
+			} else {
+				chan_intlv_bit_rm = chan_selector;
+				channel1 = hash_by_mask(contig_addr, chan_hash_mask);
+			}
+
+			*pmiidx |= (u32)channel1;
+		}
+	}
+
+	/* Remove the chan_selector bit first */
+	remove_addr_bit(&contig_addr, chan_intlv_bit_rm);
+	/* Remove the slice bit (we remove it second because it must be lower */
+	remove_addr_bit(&contig_addr, slice_intlv_bit_rm);
+	*pmiaddr = contig_addr;
+
+	return 0;
+}
+
+/* Translate PMI address to memory (rank, row, bank, column) */
+#define C(n) (0x10 | (n))	/* column */
+#define B(n) (0x20 | (n))	/* bank */
+#define R(n) (0x40 | (n))	/* row */
+#define RS   (0x80)			/* rank */
+
+/* addrdec values */
+#define AMAP_1KB	0
+#define AMAP_2KB	1
+#define AMAP_4KB	2
+#define AMAP_RSVD	3
+
+/* dden values */
+#define DEN_4Gb		0
+#define DEN_8Gb		2
+
+/* dwid values */
+#define X8		0
+#define X16		1
+
+static struct dimm_geometry {
+	u8	addrdec;
+	u8	dden;
+	u8	dwid;
+	u8	rowbits, colbits;
+	u16	bits[PMI_ADDRESS_WIDTH];
+} dimms[] = {
+	{
+		.addrdec = AMAP_1KB, .dden = DEN_4Gb, .dwid = X16,
+		.rowbits = 15, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  B(0),  B(1),  B(2),  R(0),
+			R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),  R(9),
+			R(10), C(7),  C(8),  C(9),  R(11), RS,    R(12), R(13), R(14),
+			0,     0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_1KB, .dden = DEN_4Gb, .dwid = X8,
+		.rowbits = 16, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  B(0),  B(1),  B(2),  R(0),
+			R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),  R(9),
+			R(10), C(7),  C(8),  C(9),  R(11), RS,    R(12), R(13), R(14),
+			R(15), 0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_1KB, .dden = DEN_8Gb, .dwid = X16,
+		.rowbits = 16, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  B(0),  B(1),  B(2),  R(0),
+			R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),  R(9),
+			R(10), C(7),  C(8),  C(9),  R(11), RS,    R(12), R(13), R(14),
+			R(15), 0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_1KB, .dden = DEN_8Gb, .dwid = X8,
+		.rowbits = 16, .colbits = 11,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  B(0),  B(1),  B(2),  R(0),
+			R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),  R(9),
+			R(10), C(7),  C(8),  C(9),  R(11), RS,    C(11), R(12), R(13),
+			R(14), R(15), 0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_2KB, .dden = DEN_4Gb, .dwid = X16,
+		.rowbits = 15, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  B(0),  B(1),  B(2),
+			R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),
+			R(9),  R(10), C(8),  C(9),  R(11), RS,    R(12), R(13), R(14),
+			0,     0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_2KB, .dden = DEN_4Gb, .dwid = X8,
+		.rowbits = 16, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  B(0),  B(1),  B(2),
+			R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),
+			R(9),  R(10), C(8),  C(9),  R(11), RS,    R(12), R(13), R(14),
+			R(15), 0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_2KB, .dden = DEN_8Gb, .dwid = X16,
+		.rowbits = 16, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  B(0),  B(1),  B(2),
+			R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),
+			R(9),  R(10), C(8),  C(9),  R(11), RS,    R(12), R(13), R(14),
+			R(15), 0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_2KB, .dden = DEN_8Gb, .dwid = X8,
+		.rowbits = 16, .colbits = 11,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  B(0),  B(1),  B(2),
+			R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),  R(8),
+			R(9),  R(10), C(8),  C(9),  R(11), RS,    C(11), R(12), R(13),
+			R(14), R(15), 0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_4KB, .dden = DEN_4Gb, .dwid = X16,
+		.rowbits = 15, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  C(8),  B(0),  B(1),
+			B(2),  R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),
+			R(8),  R(9),  R(10), C(9),  R(11), RS,    R(12), R(13), R(14),
+			0,     0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_4KB, .dden = DEN_4Gb, .dwid = X8,
+		.rowbits = 16, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  C(8),  B(0),  B(1),
+			B(2),  R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),
+			R(8),  R(9),  R(10), C(9),  R(11), RS,    R(12), R(13), R(14),
+			R(15), 0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_4KB, .dden = DEN_8Gb, .dwid = X16,
+		.rowbits = 16, .colbits = 10,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  C(8),  B(0),  B(1),
+			B(2),  R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),
+			R(8),  R(9),  R(10), C(9),  R(11), RS,    R(12), R(13), R(14),
+			R(15), 0,     0,     0
+		}
+	},
+	{
+		.addrdec = AMAP_4KB, .dden = DEN_8Gb, .dwid = X8,
+		.rowbits = 16, .colbits = 11,
+		.bits = {
+			C(2),  C(3),  C(4),  C(5),  C(6),  C(7),  C(8),  B(0),  B(1),
+			B(2),  R(0),  R(1),  R(2),  R(3),  R(4),  R(5),  R(6),  R(7),
+			R(8),  R(9),  R(10), C(9),  R(11), RS,    C(11), R(12), R(13),
+			R(14), R(15), 0,     0
+		}
+	}
+};
+
+static int bank_hash(u64 pmiaddr, int idx, int shft)
+{
+	int bhash = 0;
+
+	switch (idx) {
+	case 0:
+		bhash ^= ((pmiaddr >> (12 + shft)) ^ (pmiaddr >> (9 + shft))) & 1;
+		break;
+	case 1:
+		bhash ^= (((pmiaddr >> (10 + shft)) ^ (pmiaddr >> (8 + shft))) & 1) << 1;
+		bhash ^= ((pmiaddr >> 22) & 1) << 1;
+		break;
+	case 2:
+		bhash ^= (((pmiaddr >> (13 + shft)) ^ (pmiaddr >> (11 + shft))) & 1) << 2;
+		break;
+	}
+
+	return bhash;
+}
+
+static int rank_hash(u64 pmiaddr)
+{
+	return ((pmiaddr >> 16) ^ (pmiaddr >> 10)) & 1;
+}
+
+/* Second stage decode. Compute rank, bank, row & column. */
+static int apl_pmi2mem(struct mem_ctl_info *mci, u64 pmiaddr, u32 pmiidx,
+		       struct dram_addr *daddr, char *msg)
+{
+	struct d_cr_drp0 *cr_drp0 = &drp0[pmiidx];
+	struct pnd2_pvt *pvt = mci->pvt_info;
+	int g = pvt->dimm_geom[pmiidx];
+	struct dimm_geometry *d = &dimms[g];
+	int column = 0, bank = 0, row = 0, rank = 0;
+	int i, idx, type, skiprs = 0;
+
+	for (i = 0; i < PMI_ADDRESS_WIDTH; i++) {
+		int	bit = (pmiaddr >> i) & 1;
+
+		if (i + skiprs >= PMI_ADDRESS_WIDTH) {
+			snprintf(msg, PND2_MSG_SIZE, "Bad dimm_geometry[] table\n");
+			return -EINVAL;
+		}
+
+		type = d->bits[i + skiprs] & ~0xf;
+		idx = d->bits[i + skiprs] & 0xf;
+
+		/*
+		 * On single rank DIMMs ignore the rank select bit
+		 * and shift remainder of "bits[]" down one place.
+		 */
+		if (type == RS && (cr_drp0->rken0 + cr_drp0->rken1) == 1) {
+			skiprs = 1;
+			type = d->bits[i + skiprs] & ~0xf;
+			idx = d->bits[i + skiprs] & 0xf;
+		}
+
+		switch (type) {
+		case C(0):
+			column |= (bit << idx);
+			break;
+		case B(0):
+			bank |= (bit << idx);
+			if (cr_drp0->bahen)
+				bank ^= bank_hash(pmiaddr, idx, d->addrdec);
+			break;
+		case R(0):
+			row |= (bit << idx);
+			break;
+		case RS:
+			rank = bit;
+			if (cr_drp0->rsien)
+				rank ^= rank_hash(pmiaddr);
+			break;
+		default:
+			if (bit) {
+				snprintf(msg, PND2_MSG_SIZE, "Bad translation\n");
+				return -EINVAL;
+			}
+			goto done;
+		}
+	}
+
+done:
+	daddr->col = column;
+	daddr->bank = bank;
+	daddr->row = row;
+	daddr->rank = rank;
+	daddr->dimm = 0;
+
+	return 0;
+}
+
+/* Pluck bit "in" from pmiaddr and return value shifted to bit "out" */
+#define dnv_get_bit(pmi, in, out) ((int)(((pmi) >> (in)) & 1u) << (out))
+
+static int dnv_pmi2mem(struct mem_ctl_info *mci, u64 pmiaddr, u32 pmiidx,
+					   struct dram_addr *daddr, char *msg)
+{
+	/* Rank 0 or 1 */
+	daddr->rank = dnv_get_bit(pmiaddr, dmap[pmiidx].rs0 + 13, 0);
+	/* Rank 2 or 3 */
+	daddr->rank |= dnv_get_bit(pmiaddr, dmap[pmiidx].rs1 + 13, 1);
+
+	/*
+	 * Normally ranks 0,1 are DIMM0, and 2,3 are DIMM1, but we
+	 * flip them if DIMM1 is larger than DIMM0.
+	 */
+	daddr->dimm = (daddr->rank >= 2) ^ drp[pmiidx].dimmflip;
+
+	daddr->bank = dnv_get_bit(pmiaddr, dmap[pmiidx].ba0 + 6, 0);
+	daddr->bank |= dnv_get_bit(pmiaddr, dmap[pmiidx].ba1 + 6, 1);
+	daddr->bank |= dnv_get_bit(pmiaddr, dmap[pmiidx].bg0 + 6, 2);
+	if (dsch.ddr4en)
+		daddr->bank |= dnv_get_bit(pmiaddr, dmap[pmiidx].bg1 + 6, 3);
+	if (dmap1[pmiidx].bxor) {
+		if (dsch.ddr4en) {
+			daddr->bank ^= dnv_get_bit(pmiaddr, dmap3[pmiidx].row6 + 6, 0);
+			daddr->bank ^= dnv_get_bit(pmiaddr, dmap3[pmiidx].row7 + 6, 1);
+			if (dsch.chan_width == 0)
+				/* 64/72 bit dram channel width */
+				daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca3 + 6, 2);
+			else
+				/* 32/40 bit dram channel width */
+				daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca4 + 6, 2);
+			daddr->bank ^= dnv_get_bit(pmiaddr, dmap2[pmiidx].row2 + 6, 3);
+		} else {
+			daddr->bank ^= dnv_get_bit(pmiaddr, dmap2[pmiidx].row2 + 6, 0);
+			daddr->bank ^= dnv_get_bit(pmiaddr, dmap3[pmiidx].row6 + 6, 1);
+			if (dsch.chan_width == 0)
+				daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca3 + 6, 2);
+			else
+				daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca4 + 6, 2);
+		}
+	}
+
+	daddr->row = dnv_get_bit(pmiaddr, dmap2[pmiidx].row0 + 6, 0);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row1 + 6, 1);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row2 + 6, 2);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row3 + 6, 3);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row4 + 6, 4);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row5 + 6, 5);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row6 + 6, 6);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row7 + 6, 7);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row8 + 6, 8);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row9 + 6, 9);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row10 + 6, 10);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row11 + 6, 11);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row12 + 6, 12);
+	daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row13 + 6, 13);
+	if (dmap4[pmiidx].row14 != 31)
+		daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row14 + 6, 14);
+	if (dmap4[pmiidx].row15 != 31)
+		daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row15 + 6, 15);
+	if (dmap4[pmiidx].row16 != 31)
+		daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row16 + 6, 16);
+	if (dmap4[pmiidx].row17 != 31)
+		daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row17 + 6, 17);
+
+	daddr->col = dnv_get_bit(pmiaddr, dmap5[pmiidx].ca3 + 6, 3);
+	daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca4 + 6, 4);
+	daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca5 + 6, 5);
+	daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca6 + 6, 6);
+	daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca7 + 6, 7);
+	daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca8 + 6, 8);
+	daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca9 + 6, 9);
+	if (!dsch.ddr4en && dmap1[pmiidx].ca11 != 0x3f)
+		daddr->col |= dnv_get_bit(pmiaddr, dmap1[pmiidx].ca11 + 13, 11);
+
+	return 0;
+}
+
+static int check_channel(int ch)
+{
+	if (drp0[ch].dramtype != 0) {
+		pnd2_printk(KERN_INFO, "Unsupported DIMM in channel %d\n", ch);
+		return 1;
+	} else if (drp0[ch].eccen == 0) {
+		pnd2_printk(KERN_INFO, "ECC disabled on channel %d\n", ch);
+		return 1;
+	}
+	return 0;
+}
+
+static int apl_check_ecc_active(void)
+{
+	int	i, ret = 0;
+
+	/* Check dramtype and ECC mode for each present DIMM */
+	for (i = 0; i < APL_NUM_CHANNELS; i++)
+		if (chan_mask & BIT(i))
+			ret += check_channel(i);
+	return ret ? -EINVAL : 0;
+}
+
+#define DIMMS_PRESENT(d) ((d)->rken0 + (d)->rken1 + (d)->rken2 + (d)->rken3)
+
+static int check_unit(int ch)
+{
+	struct d_cr_drp *d = &drp[ch];
+
+	if (DIMMS_PRESENT(d) && !ecc_ctrl[ch].eccen) {
+		pnd2_printk(KERN_INFO, "ECC disabled on channel %d\n", ch);
+		return 1;
+	}
+	return 0;
+}
+
+static int dnv_check_ecc_active(void)
+{
+	int	i, ret = 0;
+
+	for (i = 0; i < DNV_NUM_CHANNELS; i++)
+		ret += check_unit(i);
+	return ret ? -EINVAL : 0;
+}
+
+static int get_memory_error_data(struct mem_ctl_info *mci, u64 addr,
+								 struct dram_addr *daddr, char *msg)
+{
+	u64	pmiaddr;
+	u32	pmiidx;
+	int	ret;
+
+	ret = sys2pmi(addr, &pmiidx, &pmiaddr, msg);
+	if (ret)
+		return ret;
+
+	pmiaddr >>= ops->pmiaddr_shift;
+	/* pmi channel idx to dimm channel idx */
+	pmiidx >>= ops->pmiidx_shift;
+	daddr->chan = pmiidx;
+
+	ret = ops->pmi2mem(mci, pmiaddr, pmiidx, daddr, msg);
+	if (ret)
+		return ret;
+
+	edac_dbg(0, "SysAddr=%llx PmiAddr=%llx Channel=%d DIMM=%d Rank=%d Bank=%d Row=%d Column=%d\n",
+			 addr, pmiaddr, daddr->chan, daddr->dimm, daddr->rank, daddr->bank, daddr->row, daddr->col);
+
+	return 0;
+}
+
+static void pnd2_mce_output_error(struct mem_ctl_info *mci, const struct mce *m,
+				  struct dram_addr *daddr)
+{
+	enum hw_event_mc_err_type tp_event;
+	char *optype, msg[PND2_MSG_SIZE];
+	bool ripv = m->mcgstatus & MCG_STATUS_RIPV;
+	bool overflow = m->status & MCI_STATUS_OVER;
+	bool uc_err = m->status & MCI_STATUS_UC;
+	bool recov = m->status & MCI_STATUS_S;
+	u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52);
+	u32 mscod = GET_BITFIELD(m->status, 16, 31);
+	u32 errcode = GET_BITFIELD(m->status, 0, 15);
+	u32 optypenum = GET_BITFIELD(m->status, 4, 6);
+	int rc;
+
+	tp_event = uc_err ? (ripv ? HW_EVENT_ERR_FATAL : HW_EVENT_ERR_UNCORRECTED) :
+						 HW_EVENT_ERR_CORRECTED;
+
+	/*
+	 * According with Table 15-9 of the Intel Architecture spec vol 3A,
+	 * memory errors should fit in this mask:
+	 *	000f 0000 1mmm cccc (binary)
+	 * where:
+	 *	f = Correction Report Filtering Bit. If 1, subsequent errors
+	 *	    won't be shown
+	 *	mmm = error type
+	 *	cccc = channel
+	 * If the mask doesn't match, report an error to the parsing logic
+	 */
+	if (!((errcode & 0xef80) == 0x80)) {
+		optype = "Can't parse: it is not a mem";
+	} else {
+		switch (optypenum) {
+		case 0:
+			optype = "generic undef request error";
+			break;
+		case 1:
+			optype = "memory read error";
+			break;
+		case 2:
+			optype = "memory write error";
+			break;
+		case 3:
+			optype = "addr/cmd error";
+			break;
+		case 4:
+			optype = "memory scrubbing error";
+			break;
+		default:
+			optype = "reserved";
+			break;
+		}
+	}
+
+	/* Only decode errors with an valid address (ADDRV) */
+	if (!(m->status & MCI_STATUS_ADDRV))
+		return;
+
+	rc = get_memory_error_data(mci, m->addr, daddr, msg);
+	if (rc)
+		goto address_error;
+
+	snprintf(msg, sizeof(msg),
+		 "%s%s err_code:%04x:%04x channel:%d DIMM:%d rank:%d row:%d bank:%d col:%d",
+		 overflow ? " OVERFLOW" : "", (uc_err && recov) ? " recoverable" : "", mscod,
+		 errcode, daddr->chan, daddr->dimm, daddr->rank, daddr->row, daddr->bank, daddr->col);
+
+	edac_dbg(0, "%s\n", msg);
+
+	/* Call the helper to output message */
+	edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT,
+						 m->addr & ~PAGE_MASK, 0, daddr->chan, daddr->dimm, -1, optype, msg);
+
+	return;
+
+address_error:
+	edac_mc_handle_error(tp_event, mci, core_err_cnt, 0, 0, 0, -1, -1, -1, msg, "");
+}
+
+static void apl_get_dimm_config(struct mem_ctl_info *mci)
+{
+	struct pnd2_pvt	*pvt = mci->pvt_info;
+	struct dimm_info *dimm;
+	struct d_cr_drp0 *d;
+	u64	capacity;
+	int	i, g;
+
+	for (i = 0; i < APL_NUM_CHANNELS; i++) {
+		if (!(chan_mask & BIT(i)))
+			continue;
+
+		dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, 0, 0);
+		if (!dimm) {
+			edac_dbg(0, "No allocated DIMM for channel %d\n", i);
+			continue;
+		}
+
+		d = &drp0[i];
+		for (g = 0; g < ARRAY_SIZE(dimms); g++)
+			if (dimms[g].addrdec == d->addrdec &&
+			    dimms[g].dden == d->dden &&
+			    dimms[g].dwid == d->dwid)
+				break;
+
+		if (g == ARRAY_SIZE(dimms)) {
+			edac_dbg(0, "Channel %d: unrecognized DIMM\n", i);
+			continue;
+		}
+
+		pvt->dimm_geom[i] = g;
+		capacity = (d->rken0 + d->rken1) * 8 * (1ul << dimms[g].rowbits) *
+				   (1ul << dimms[g].colbits);
+		edac_dbg(0, "Channel %d: %lld MByte DIMM\n", i, capacity >> (20 - 3));
+		dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3));
+		dimm->grain = 32;
+		dimm->dtype = (d->dwid == 0) ? DEV_X8 : DEV_X16;
+		dimm->mtype = MEM_DDR3;
+		dimm->edac_mode = EDAC_SECDED;
+		snprintf(dimm->label, sizeof(dimm->label), "Slice#%d_Chan#%d", i / 2, i % 2);
+	}
+}
+
+static const int dnv_dtypes[] = {
+	DEV_X8, DEV_X4, DEV_X16, DEV_UNKNOWN
+};
+
+static void dnv_get_dimm_config(struct mem_ctl_info *mci)
+{
+	int	i, j, ranks_of_dimm[DNV_MAX_DIMMS], banks, rowbits, colbits, memtype;
+	struct dimm_info *dimm;
+	struct d_cr_drp *d;
+	u64	capacity;
+
+	if (dsch.ddr4en) {
+		memtype = MEM_DDR4;
+		banks = 16;
+		colbits = 10;
+	} else {
+		memtype = MEM_DDR3;
+		banks = 8;
+	}
+
+	for (i = 0; i < DNV_NUM_CHANNELS; i++) {
+		if (dmap4[i].row14 == 31)
+			rowbits = 14;
+		else if (dmap4[i].row15 == 31)
+			rowbits = 15;
+		else if (dmap4[i].row16 == 31)
+			rowbits = 16;
+		else if (dmap4[i].row17 == 31)
+			rowbits = 17;
+		else
+			rowbits = 18;
+
+		if (memtype == MEM_DDR3) {
+			if (dmap1[i].ca11 != 0x3f)
+				colbits = 12;
+			else
+				colbits = 10;
+		}
+
+		d = &drp[i];
+		/* DIMM0 is present if rank0 and/or rank1 is enabled */
+		ranks_of_dimm[0] = d->rken0 + d->rken1;
+		/* DIMM1 is present if rank2 and/or rank3 is enabled */
+		ranks_of_dimm[1] = d->rken2 + d->rken3;
+
+		for (j = 0; j < DNV_MAX_DIMMS; j++) {
+			if (!ranks_of_dimm[j])
+				continue;
+
+			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0);
+			if (!dimm) {
+				edac_dbg(0, "No allocated DIMM for channel %d DIMM %d\n", i, j);
+				continue;
+			}
+
+			capacity = ranks_of_dimm[j] * banks * (1ul << rowbits) * (1ul << colbits);
+			edac_dbg(0, "Channel %d DIMM %d: %lld MByte DIMM\n", i, j, capacity >> (20 - 3));
+			dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3));
+			dimm->grain = 32;
+			dimm->dtype = dnv_dtypes[j ? d->dimmdwid0 : d->dimmdwid1];
+			dimm->mtype = memtype;
+			dimm->edac_mode = EDAC_SECDED;
+			snprintf(dimm->label, sizeof(dimm->label), "Chan#%d_DIMM#%d", i, j);
+		}
+	}
+}
+
+static int pnd2_register_mci(struct mem_ctl_info **ppmci)
+{
+	struct edac_mc_layer layers[2];
+	struct mem_ctl_info *mci;
+	struct pnd2_pvt *pvt;
+	int rc;
+
+	rc = ops->check_ecc();
+	if (rc < 0)
+		return rc;
+
+	/* Allocate a new MC control structure */
+	layers[0].type = EDAC_MC_LAYER_CHANNEL;
+	layers[0].size = ops->channels;
+	layers[0].is_virt_csrow = false;
+	layers[1].type = EDAC_MC_LAYER_SLOT;
+	layers[1].size = ops->dimms_per_channel;
+	layers[1].is_virt_csrow = true;
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*pvt));
+	if (!mci)
+		return -ENOMEM;
+
+	pvt = mci->pvt_info;
+	memset(pvt, 0, sizeof(*pvt));
+
+	mci->mod_name = "pnd2_edac.c";
+	mci->dev_name = ops->name;
+	mci->ctl_name = "Pondicherry2";
+
+	/* Get dimm basic config and the memory layout */
+	ops->get_dimm_config(mci);
+
+	if (edac_mc_add_mc(mci)) {
+		edac_dbg(0, "MC: failed edac_mc_add_mc()\n");
+		edac_mc_free(mci);
+		return -EINVAL;
+	}
+
+	*ppmci = mci;
+
+	return 0;
+}
+
+static void pnd2_unregister_mci(struct mem_ctl_info *mci)
+{
+	if (unlikely(!mci || !mci->pvt_info)) {
+		pnd2_printk(KERN_ERR, "Couldn't find mci handler\n");
+		return;
+	}
+
+	/* Remove MC sysfs nodes */
+	edac_mc_del_mc(NULL);
+	edac_dbg(1, "%s: free mci struct\n", mci->ctl_name);
+	edac_mc_free(mci);
+}
+
+/*
+ * Callback function registered with core kernel mce code.
+ * Called once for each logged error.
+ */
+static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	struct mem_ctl_info *mci;
+	struct dram_addr daddr;
+	char *type;
+
+	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
+		return NOTIFY_DONE;
+
+	mci = pnd2_mci;
+	if (!mci)
+		return NOTIFY_DONE;
+
+	/*
+	 * Just let mcelog handle it if the error is
+	 * outside the memory controller. A memory error
+	 * is indicated by bit 7 = 1 and bits = 8-11,13-15 = 0.
+	 * bit 12 has an special meaning.
+	 */
+	if ((mce->status & 0xefff) >> 7 != 1)
+		return NOTIFY_DONE;
+
+	if (mce->mcgstatus & MCG_STATUS_MCIP)
+		type = "Exception";
+	else
+		type = "Event";
+
+	pnd2_mc_printk(mci, KERN_INFO, "HANDLING MCE MEMORY ERROR\n");
+	pnd2_mc_printk(mci, KERN_INFO, "CPU %u: Machine Check %s: %llx Bank %u: %llx\n",
+				   mce->extcpu, type, mce->mcgstatus, mce->bank, mce->status);
+	pnd2_mc_printk(mci, KERN_INFO, "TSC %llx ", mce->tsc);
+	pnd2_mc_printk(mci, KERN_INFO, "ADDR %llx ", mce->addr);
+	pnd2_mc_printk(mci, KERN_INFO, "MISC %llx ", mce->misc);
+	pnd2_mc_printk(mci, KERN_INFO, "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+				   mce->cpuvendor, mce->cpuid, mce->time, mce->socketid, mce->apicid);
+
+	pnd2_mce_output_error(mci, mce, &daddr);
+
+	/* Advice mcelog that the error were handled */
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block pnd2_mce_dec = {
+	.notifier_call	= pnd2_mce_check_error,
+};
+
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Write an address to this file to exercise the address decode
+ * logic in this driver.
+ */
+static u64 pnd2_fake_addr;
+#define PND2_BLOB_SIZE 1024
+static char pnd2_result[PND2_BLOB_SIZE];
+static struct dentry *pnd2_test;
+static struct debugfs_blob_wrapper pnd2_blob = {
+	.data = pnd2_result,
+	.size = 0
+};
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+	struct dram_addr daddr;
+	struct mce m;
+
+	*(u64 *)data = val;
+	m.mcgstatus = 0;
+	/* ADDRV + MemRd + Unknown channel */
+	m.status = MCI_STATUS_ADDRV + 0x9f;
+	m.addr = val;
+	pnd2_mce_output_error(pnd2_mci, &m, &daddr);
+	snprintf(pnd2_blob.data, PND2_BLOB_SIZE,
+			 "SysAddr=%llx Channel=%d DIMM=%d Rank=%d Bank=%d Row=%d Column=%d\n",
+			 m.addr, daddr.chan, daddr.dimm, daddr.rank, daddr.bank, daddr.row, daddr.col);
+	pnd2_blob.size = strlen(pnd2_blob.data);
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static void setup_pnd2_debug(void)
+{
+	pnd2_test = edac_debugfs_create_dir("pnd2_test");
+	edac_debugfs_create_file("pnd2_debug_addr", 0200, pnd2_test,
+							 &pnd2_fake_addr, &fops_u64_wo);
+	debugfs_create_blob("pnd2_debug_results", 0400, pnd2_test, &pnd2_blob);
+}
+
+static void teardown_pnd2_debug(void)
+{
+	debugfs_remove_recursive(pnd2_test);
+}
+#else
+static void setup_pnd2_debug(void)	{}
+static void teardown_pnd2_debug(void)	{}
+#endif /* CONFIG_EDAC_DEBUG */
+
+
+static int pnd2_probe(void)
+{
+	int rc;
+
+	edac_dbg(2, "\n");
+	rc = get_registers();
+	if (rc)
+		return rc;
+
+	return pnd2_register_mci(&pnd2_mci);
+}
+
+static void pnd2_remove(void)
+{
+	edac_dbg(0, "\n");
+	pnd2_unregister_mci(pnd2_mci);
+}
+
+static struct dunit_ops apl_ops = {
+		.name			= "pnd2/apl",
+		.type			= APL,
+		.pmiaddr_shift		= LOG2_PMI_ADDR_GRANULARITY,
+		.pmiidx_shift		= 0,
+		.channels		= APL_NUM_CHANNELS,
+		.dimms_per_channel	= 1,
+		.rd_reg			= apl_rd_reg,
+		.get_registers		= apl_get_registers,
+		.check_ecc		= apl_check_ecc_active,
+		.mk_region		= apl_mk_region,
+		.get_dimm_config	= apl_get_dimm_config,
+		.pmi2mem		= apl_pmi2mem,
+};
+
+static struct dunit_ops dnv_ops = {
+		.name			= "pnd2/dnv",
+		.type			= DNV,
+		.pmiaddr_shift		= 0,
+		.pmiidx_shift		= 1,
+		.channels		= DNV_NUM_CHANNELS,
+		.dimms_per_channel	= 2,
+		.rd_reg			= dnv_rd_reg,
+		.get_registers		= dnv_get_registers,
+		.check_ecc		= dnv_check_ecc_active,
+		.mk_region		= dnv_mk_region,
+		.get_dimm_config	= dnv_get_dimm_config,
+		.pmi2mem		= dnv_pmi2mem,
+};
+
+static const struct x86_cpu_id pnd2_cpuids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops },
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON, 0, (kernel_ulong_t)&dnv_ops },
+	{ }
+};
+MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids);
+
+static int __init pnd2_init(void)
+{
+	const struct x86_cpu_id *id;
+	int rc;
+
+	edac_dbg(2, "\n");
+
+	id = x86_match_cpu(pnd2_cpuids);
+	if (!id)
+		return -ENODEV;
+
+	ops = (struct dunit_ops *)id->driver_data;
+
+	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
+	opstate_init();
+
+	rc = pnd2_probe();
+	if (rc < 0) {
+		pnd2_printk(KERN_ERR, "Failed to register device with error %d.\n", rc);
+		return rc;
+	}
+
+	if (!pnd2_mci)
+		return -ENODEV;
+
+	mce_register_decode_chain(&pnd2_mce_dec);
+	setup_pnd2_debug();
+
+	return 0;
+}
+
+static void __exit pnd2_exit(void)
+{
+	edac_dbg(2, "\n");
+	teardown_pnd2_debug();
+	mce_unregister_decode_chain(&pnd2_mce_dec);
+	pnd2_remove();
+}
+
+module_init(pnd2_init);
+module_exit(pnd2_exit);
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tony Luck");
+MODULE_DESCRIPTION("MC Driver for Intel SoC using Pondicherry memory controller");
diff --git a/drivers/edac/pnd2_edac.h b/drivers/edac/pnd2_edac.h
new file mode 100644
index 000000000000..61b6e79492bb
--- /dev/null
+++ b/drivers/edac/pnd2_edac.h
@@ -0,0 +1,301 @@
+/*
+ * Register bitfield descriptions for Pondicherry2 memory controller.
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _PND2_REGS_H
+#define _PND2_REGS_H
+
+struct b_cr_touud_lo_pci {
+	u32	lock : 1;
+	u32	reserved_1 : 19;
+	u32	touud : 12;
+};
+
+#define b_cr_touud_lo_pci_port 0x4c
+#define b_cr_touud_lo_pci_offset 0xa8
+#define b_cr_touud_lo_pci_r_opcode 0x04
+
+struct b_cr_touud_hi_pci {
+	u32	touud : 7;
+	u32	reserved_0 : 25;
+};
+
+#define b_cr_touud_hi_pci_port 0x4c
+#define b_cr_touud_hi_pci_offset 0xac
+#define b_cr_touud_hi_pci_r_opcode 0x04
+
+struct b_cr_tolud_pci {
+	u32	lock : 1;
+	u32	reserved_0 : 19;
+	u32	tolud : 12;
+};
+
+#define b_cr_tolud_pci_port 0x4c
+#define b_cr_tolud_pci_offset 0xbc
+#define b_cr_tolud_pci_r_opcode 0x04
+
+struct b_cr_mchbar_lo_pci {
+	u32 enable : 1;
+	u32 pad_3_1 : 3;
+	u32 pad_14_4: 11;
+	u32 base: 17;
+};
+
+struct b_cr_mchbar_hi_pci {
+	u32 base : 7;
+	u32 pad_31_7 : 25;
+};
+
+/* Symmetric region */
+struct b_cr_slice_channel_hash {
+	u64	slice_1_disabled : 1;
+	u64	hvm_mode : 1;
+	u64	interleave_mode : 2;
+	u64	slice_0_mem_disabled : 1;
+	u64	reserved_0 : 1;
+	u64	slice_hash_mask : 14;
+	u64	reserved_1 : 11;
+	u64	enable_pmi_dual_data_mode : 1;
+	u64	ch_1_disabled : 1;
+	u64	reserved_2 : 1;
+	u64	sym_slice0_channel_enabled : 2;
+	u64	sym_slice1_channel_enabled : 2;
+	u64	ch_hash_mask : 14;
+	u64	reserved_3 : 11;
+	u64	lock : 1;
+};
+
+#define b_cr_slice_channel_hash_port 0x4c
+#define b_cr_slice_channel_hash_offset 0x4c58
+#define b_cr_slice_channel_hash_r_opcode 0x06
+
+struct b_cr_mot_out_base_mchbar {
+	u32	reserved_0 : 14;
+	u32	mot_out_base : 15;
+	u32	reserved_1 : 1;
+	u32	tr_en : 1;
+	u32	imr_en : 1;
+};
+
+#define b_cr_mot_out_base_mchbar_port 0x4c
+#define b_cr_mot_out_base_mchbar_offset 0x6af0
+#define b_cr_mot_out_base_mchbar_r_opcode 0x00
+
+struct b_cr_mot_out_mask_mchbar {
+	u32	reserved_0 : 14;
+	u32	mot_out_mask : 15;
+	u32	reserved_1 : 1;
+	u32	ia_iwb_en : 1;
+	u32	gt_iwb_en : 1;
+};
+
+#define b_cr_mot_out_mask_mchbar_port 0x4c
+#define b_cr_mot_out_mask_mchbar_offset 0x6af4
+#define b_cr_mot_out_mask_mchbar_r_opcode 0x00
+
+struct b_cr_asym_mem_region0_mchbar {
+	u32	pad : 4;
+	u32	slice0_asym_base : 11;
+	u32	pad_18_15 : 4;
+	u32	slice0_asym_limit : 11;
+	u32	slice0_asym_channel_select : 1;
+	u32	slice0_asym_enable : 1;
+};
+
+#define b_cr_asym_mem_region0_mchbar_port 0x4c
+#define b_cr_asym_mem_region0_mchbar_offset 0x6e40
+#define b_cr_asym_mem_region0_mchbar_r_opcode 0x00
+
+struct b_cr_asym_mem_region1_mchbar {
+	u32	pad : 4;
+	u32	slice1_asym_base : 11;
+	u32	pad_18_15 : 4;
+	u32	slice1_asym_limit : 11;
+	u32	slice1_asym_channel_select : 1;
+	u32	slice1_asym_enable : 1;
+};
+
+#define b_cr_asym_mem_region1_mchbar_port 0x4c
+#define b_cr_asym_mem_region1_mchbar_offset 0x6e44
+#define b_cr_asym_mem_region1_mchbar_r_opcode 0x00
+
+/* Some bit fields moved in above two structs on Denverton */
+struct b_cr_asym_mem_region_denverton {
+	u32	pad : 4;
+	u32	slice_asym_base : 8;
+	u32	pad_19_12 : 8;
+	u32	slice_asym_limit : 8;
+	u32	pad_28_30 : 3;
+	u32	slice_asym_enable : 1;
+};
+
+struct b_cr_asym_2way_mem_region_mchbar {
+	u32	pad : 2;
+	u32	asym_2way_intlv_mode : 2;
+	u32	asym_2way_base : 11;
+	u32	pad_16_15 : 2;
+	u32	asym_2way_limit : 11;
+	u32	pad_30_28 : 3;
+	u32	asym_2way_interleave_enable : 1;
+};
+
+#define b_cr_asym_2way_mem_region_mchbar_port 0x4c
+#define b_cr_asym_2way_mem_region_mchbar_offset 0x6e50
+#define b_cr_asym_2way_mem_region_mchbar_r_opcode 0x00
+
+/* Apollo Lake d-unit */
+
+struct d_cr_drp0 {
+	u32	rken0 : 1;
+	u32	rken1 : 1;
+	u32	ddmen : 1;
+	u32	rsvd3 : 1;
+	u32	dwid : 2;
+	u32	dden : 3;
+	u32	rsvd13_9 : 5;
+	u32	rsien : 1;
+	u32	bahen : 1;
+	u32	rsvd18_16 : 3;
+	u32	caswizzle : 2;
+	u32	eccen : 1;
+	u32	dramtype : 3;
+	u32	blmode : 3;
+	u32	addrdec : 2;
+	u32	dramdevice_pr : 2;
+};
+
+#define d_cr_drp0_offset 0x1400
+#define d_cr_drp0_r_opcode 0x00
+
+/* Denverton d-unit */
+
+struct d_cr_dsch {
+	u32	ch0en : 1;
+	u32	ch1en : 1;
+	u32	ddr4en : 1;
+	u32	coldwake : 1;
+	u32	newbypdis : 1;
+	u32	chan_width : 1;
+	u32	rsvd6_6 : 1;
+	u32	ooodis : 1;
+	u32	rsvd18_8 : 11;
+	u32	ic : 1;
+	u32	rsvd31_20 : 12;
+};
+
+#define d_cr_dsch_port 0x16
+#define d_cr_dsch_offset 0x0
+#define d_cr_dsch_r_opcode 0x0
+
+struct d_cr_ecc_ctrl {
+	u32	eccen : 1;
+	u32	rsvd31_1 : 31;
+};
+
+#define d_cr_ecc_ctrl_offset 0x180
+#define d_cr_ecc_ctrl_r_opcode 0x0
+
+struct d_cr_drp {
+	u32	rken0 : 1;
+	u32	rken1 : 1;
+	u32	rken2 : 1;
+	u32	rken3 : 1;
+	u32	dimmdwid0 : 2;
+	u32	dimmdden0 : 2;
+	u32	dimmdwid1 : 2;
+	u32	dimmdden1 : 2;
+	u32	rsvd15_12 : 4;
+	u32	dimmflip : 1;
+	u32	rsvd31_17 : 15;
+};
+
+#define d_cr_drp_offset 0x158
+#define d_cr_drp_r_opcode 0x0
+
+struct d_cr_dmap {
+	u32	ba0 : 5;
+	u32	ba1 : 5;
+	u32	bg0 : 5; /* if ddr3, ba2 = bg0 */
+	u32	bg1 : 5; /* if ddr3, ba3 = bg1 */
+	u32	rs0 : 5;
+	u32	rs1 : 5;
+	u32	rsvd : 2;
+};
+
+#define d_cr_dmap_offset 0x174
+#define d_cr_dmap_r_opcode 0x0
+
+struct d_cr_dmap1 {
+	u32	ca11 : 6;
+	u32	bxor : 1;
+	u32	rsvd : 25;
+};
+
+#define d_cr_dmap1_offset 0xb4
+#define d_cr_dmap1_r_opcode 0x0
+
+struct d_cr_dmap2 {
+	u32	row0 : 5;
+	u32	row1 : 5;
+	u32	row2 : 5;
+	u32	row3 : 5;
+	u32	row4 : 5;
+	u32	row5 : 5;
+	u32	rsvd : 2;
+};
+
+#define d_cr_dmap2_offset 0x148
+#define d_cr_dmap2_r_opcode 0x0
+
+struct d_cr_dmap3 {
+	u32	row6 : 5;
+	u32	row7 : 5;
+	u32	row8 : 5;
+	u32	row9 : 5;
+	u32	row10 : 5;
+	u32	row11 : 5;
+	u32	rsvd : 2;
+};
+
+#define d_cr_dmap3_offset 0x14c
+#define d_cr_dmap3_r_opcode 0x0
+
+struct d_cr_dmap4 {
+	u32	row12 : 5;
+	u32	row13 : 5;
+	u32	row14 : 5;
+	u32	row15 : 5;
+	u32	row16 : 5;
+	u32	row17 : 5;
+	u32	rsvd : 2;
+};
+
+#define d_cr_dmap4_offset 0x150
+#define d_cr_dmap4_r_opcode 0x0
+
+struct d_cr_dmap5 {
+	u32	ca3 : 4;
+	u32	ca4 : 4;
+	u32	ca5 : 4;
+	u32	ca6 : 4;
+	u32	ca7 : 4;
+	u32	ca8 : 4;
+	u32	ca9 : 4;
+	u32	rsvd : 4;
+};
+
+#define d_cr_dmap5_offset 0x154
+#define d_cr_dmap5_r_opcode 0x0
+
+#endif /* _PND2_REGS_H */
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index a65ea44e3b0b..ea21cb651b3c 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -3075,7 +3075,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct sbridge_pvt *pvt;
 	char *type;
 
-	if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
 
 	mci = get_mci_for_node_id(mce->socketid);
@@ -3441,7 +3441,7 @@ static int __init sbridge_init(void)
 
 	if (rc >= 0) {
 		mce_register_decode_chain(&sbridge_mce_dec);
-		if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+		if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 			sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
 		return 0;
 	}
diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c
index 1159dba4671f..64bef6c9cfb4 100644
--- a/drivers/edac/skx_edac.c
+++ b/drivers/edac/skx_edac.c
@@ -971,7 +971,7 @@ static int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 	char *type;
 
-	if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
 
 	/* ignore unless this is memory related with an address */
diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c
new file mode 100644
index 000000000000..86d585cb6d32
--- /dev/null
+++ b/drivers/edac/thunderx_edac.c
@@ -0,0 +1,2174 @@
+/*
+ * Cavium ThunderX memory controller kernel module
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright Cavium, Inc. (C) 2015-2017. All rights reserved.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/edac.h>
+#include <linux/interrupt.h>
+#include <linux/string.h>
+#include <linux/stop_machine.h>
+#include <linux/delay.h>
+#include <linux/sizes.h>
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/circ_buf.h>
+
+#include <asm/page.h>
+
+#include "edac_module.h"
+
+#define phys_to_pfn(phys)	(PFN_DOWN(phys))
+
+#define THUNDERX_NODE		GENMASK(45, 44)
+
+enum {
+	ERR_CORRECTED	= 1,
+	ERR_UNCORRECTED	= 2,
+	ERR_UNKNOWN	= 3,
+};
+
+#define MAX_SYNDROME_REGS 4
+
+struct error_syndrome {
+	u64 reg[MAX_SYNDROME_REGS];
+};
+
+struct error_descr {
+	int	type;
+	u64	mask;
+	char	*descr;
+};
+
+static void decode_register(char *str, size_t size,
+			   const struct error_descr *descr,
+			   const uint64_t reg)
+{
+	int ret = 0;
+
+	while (descr->type && descr->mask && descr->descr) {
+		if (reg & descr->mask) {
+			ret = snprintf(str, size, "\n\t%s, %s",
+				       descr->type == ERR_CORRECTED ?
+					 "Corrected" : "Uncorrected",
+				       descr->descr);
+			str += ret;
+			size -= ret;
+		}
+		descr++;
+	}
+}
+
+static unsigned long get_bits(unsigned long data, int pos, int width)
+{
+	return (data >> pos) & ((1 << width) - 1);
+}
+
+#define L2C_CTL			0x87E080800000
+#define L2C_CTL_DISIDXALIAS	BIT(0)
+
+#define PCI_DEVICE_ID_THUNDER_LMC 0xa022
+
+#define LMC_FADR		0x20
+#define LMC_FADR_FDIMM(x)	((x >> 37) & 0x1)
+#define LMC_FADR_FBUNK(x)	((x >> 36) & 0x1)
+#define LMC_FADR_FBANK(x)	((x >> 32) & 0xf)
+#define LMC_FADR_FROW(x)	((x >> 14) & 0xffff)
+#define LMC_FADR_FCOL(x)	((x >> 0) & 0x1fff)
+
+#define LMC_NXM_FADR		0x28
+#define LMC_ECC_SYND		0x38
+
+#define LMC_ECC_PARITY_TEST	0x108
+
+#define LMC_INT_W1S		0x150
+
+#define LMC_INT_ENA_W1C		0x158
+#define LMC_INT_ENA_W1S		0x160
+
+#define LMC_CONFIG		0x188
+
+#define LMC_CONFIG_BG2		BIT(62)
+#define LMC_CONFIG_RANK_ENA	BIT(42)
+#define LMC_CONFIG_PBANK_LSB(x)	(((x) >> 5) & 0xF)
+#define LMC_CONFIG_ROW_LSB(x)	(((x) >> 2) & 0x7)
+
+#define LMC_CONTROL		0x190
+#define LMC_CONTROL_XOR_BANK	BIT(16)
+
+#define LMC_INT			0x1F0
+
+#define LMC_INT_DDR_ERR		BIT(11)
+#define LMC_INT_DED_ERR		(0xFUL << 5)
+#define LMC_INT_SEC_ERR         (0xFUL << 1)
+#define LMC_INT_NXM_WR_MASK	BIT(0)
+
+#define LMC_DDR_PLL_CTL		0x258
+#define LMC_DDR_PLL_CTL_DDR4	BIT(29)
+
+#define LMC_FADR_SCRAMBLED	0x330
+
+#define LMC_INT_UE              (LMC_INT_DDR_ERR | LMC_INT_DED_ERR | \
+				 LMC_INT_NXM_WR_MASK)
+
+#define LMC_INT_CE		(LMC_INT_SEC_ERR)
+
+static const struct error_descr lmc_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = LMC_INT_SEC_ERR,
+		.descr = "Single-bit ECC error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = LMC_INT_DDR_ERR,
+		.descr = "DDR chip error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = LMC_INT_DED_ERR,
+		.descr = "Double-bit ECC error",
+	},
+	{
+		.type = ERR_UNCORRECTED,
+		.mask = LMC_INT_NXM_WR_MASK,
+		.descr = "Non-existent memory write",
+	},
+	{0, 0, NULL},
+};
+
+#define LMC_INT_EN_DDR_ERROR_ALERT_ENA	BIT(5)
+#define LMC_INT_EN_DLCRAM_DED_ERR	BIT(4)
+#define LMC_INT_EN_DLCRAM_SEC_ERR	BIT(3)
+#define LMC_INT_INTR_DED_ENA		BIT(2)
+#define LMC_INT_INTR_SEC_ENA		BIT(1)
+#define LMC_INT_INTR_NXM_WR_ENA		BIT(0)
+
+#define LMC_INT_ENA_ALL			GENMASK(5, 0)
+
+#define LMC_DDR_PLL_CTL		0x258
+#define LMC_DDR_PLL_CTL_DDR4	BIT(29)
+
+#define LMC_CONTROL		0x190
+#define LMC_CONTROL_RDIMM	BIT(0)
+
+#define LMC_SCRAM_FADR		0x330
+
+#define LMC_CHAR_MASK0		0x228
+#define LMC_CHAR_MASK2		0x238
+
+#define RING_ENTRIES	8
+
+struct debugfs_entry {
+	const char *name;
+	umode_t mode;
+	const struct file_operations fops;
+};
+
+struct lmc_err_ctx {
+	u64 reg_int;
+	u64 reg_fadr;
+	u64 reg_nxm_fadr;
+	u64 reg_scram_fadr;
+	u64 reg_ecc_synd;
+};
+
+struct thunderx_lmc {
+	void __iomem *regs;
+	struct pci_dev *pdev;
+	struct msix_entry msix_ent;
+
+	atomic_t ecc_int;
+
+	u64 mask0;
+	u64 mask2;
+	u64 parity_test;
+	u64 node;
+
+	int xbits;
+	int bank_width;
+	int pbank_lsb;
+	int dimm_lsb;
+	int rank_lsb;
+	int bank_lsb;
+	int row_lsb;
+	int col_hi_lsb;
+
+	int xor_bank;
+	int l2c_alias;
+
+	struct page *mem;
+
+	struct lmc_err_ctx err_ctx[RING_ENTRIES];
+	unsigned long ring_head;
+	unsigned long ring_tail;
+};
+
+#define ring_pos(pos, size) ((pos) & (size - 1))
+
+#define DEBUGFS_STRUCT(_name, _mode, _write, _read)			    \
+static struct debugfs_entry debugfs_##_name = {				    \
+	.name = __stringify(_name),					    \
+	.mode = VERIFY_OCTAL_PERMISSIONS(_mode),			    \
+	.fops = {							    \
+		.open = simple_open,					    \
+		.write = _write,					    \
+		.read  = _read,						    \
+		.llseek = generic_file_llseek,				    \
+	},								    \
+}
+
+#define DEBUGFS_FIELD_ATTR(_type, _field)				    \
+static ssize_t thunderx_##_type##_##_field##_read(struct file *file,	    \
+					    char __user *data,		    \
+					    size_t count, loff_t *ppos)	    \
+{									    \
+	struct thunderx_##_type *pdata = file->private_data;		    \
+	char buf[20];							    \
+									    \
+	snprintf(buf, count, "0x%016llx", pdata->_field);		    \
+	return simple_read_from_buffer(data, count, ppos,		    \
+				       buf, sizeof(buf));		    \
+}									    \
+									    \
+static ssize_t thunderx_##_type##_##_field##_write(struct file *file,	    \
+					     const char __user *data,	    \
+					     size_t count, loff_t *ppos)    \
+{									    \
+	struct thunderx_##_type *pdata = file->private_data;		    \
+	int res;							    \
+									    \
+	res = kstrtoull_from_user(data, count, 0, &pdata->_field);	    \
+									    \
+	return res ? res : count;					    \
+}									    \
+									    \
+DEBUGFS_STRUCT(_field, 0600,						    \
+		   thunderx_##_type##_##_field##_write,			    \
+		   thunderx_##_type##_##_field##_read)			    \
+
+#define DEBUGFS_REG_ATTR(_type, _name, _reg)				    \
+static ssize_t thunderx_##_type##_##_name##_read(struct file *file,	    \
+					   char __user *data,		    \
+					   size_t count, loff_t *ppos)      \
+{									    \
+	struct thunderx_##_type *pdata = file->private_data;		    \
+	char buf[20];							    \
+									    \
+	sprintf(buf, "0x%016llx", readq(pdata->regs + _reg));		    \
+	return simple_read_from_buffer(data, count, ppos,		    \
+				       buf, sizeof(buf));		    \
+}									    \
+									    \
+static ssize_t thunderx_##_type##_##_name##_write(struct file *file,	    \
+					    const char __user *data,	    \
+					    size_t count, loff_t *ppos)     \
+{									    \
+	struct thunderx_##_type *pdata = file->private_data;		    \
+	u64 val;							    \
+	int res;							    \
+									    \
+	res = kstrtoull_from_user(data, count, 0, &val);		    \
+									    \
+	if (!res) {							    \
+		writeq(val, pdata->regs + _reg);			    \
+		res = count;						    \
+	}								    \
+									    \
+	return res;							    \
+}									    \
+									    \
+DEBUGFS_STRUCT(_name, 0600,						    \
+	       thunderx_##_type##_##_name##_write,			    \
+	       thunderx_##_type##_##_name##_read)
+
+#define LMC_DEBUGFS_ENT(_field)	DEBUGFS_FIELD_ATTR(lmc, _field)
+
+/*
+ * To get an ECC error injected, the following steps are needed:
+ * - Setup the ECC injection by writing the appropriate parameters:
+ *	echo <bit mask value> > /sys/kernel/debug/<device number>/ecc_mask0
+ *	echo <bit mask value> > /sys/kernel/debug/<device number>/ecc_mask2
+ *	echo 0x802 > /sys/kernel/debug/<device number>/ecc_parity_test
+ * - Do the actual injection:
+ *	echo 1 > /sys/kernel/debug/<device number>/inject_ecc
+ */
+static ssize_t thunderx_lmc_inject_int_write(struct file *file,
+					     const char __user *data,
+					     size_t count, loff_t *ppos)
+{
+	struct thunderx_lmc *lmc = file->private_data;
+	u64 val;
+	int res;
+
+	res = kstrtoull_from_user(data, count, 0, &val);
+
+	if (!res) {
+		/* Trigger the interrupt */
+		writeq(val, lmc->regs + LMC_INT_W1S);
+		res = count;
+	}
+
+	return res;
+}
+
+static ssize_t thunderx_lmc_int_read(struct file *file,
+				     char __user *data,
+				     size_t count, loff_t *ppos)
+{
+	struct thunderx_lmc *lmc = file->private_data;
+	char buf[20];
+	u64 lmc_int = readq(lmc->regs + LMC_INT);
+
+	snprintf(buf, sizeof(buf), "0x%016llx", lmc_int);
+	return simple_read_from_buffer(data, count, ppos, buf, sizeof(buf));
+}
+
+#define TEST_PATTERN 0xa5
+
+static int inject_ecc_fn(void *arg)
+{
+	struct thunderx_lmc *lmc = arg;
+	uintptr_t addr, phys;
+	unsigned int cline_size = cache_line_size();
+	const unsigned int lines = PAGE_SIZE / cline_size;
+	unsigned int i, cl_idx;
+
+	addr = (uintptr_t)page_address(lmc->mem);
+	phys = (uintptr_t)page_to_phys(lmc->mem);
+
+	cl_idx = (phys & 0x7f) >> 4;
+	lmc->parity_test &= ~(7ULL << 8);
+	lmc->parity_test |= (cl_idx << 8);
+
+	writeq(lmc->mask0, lmc->regs + LMC_CHAR_MASK0);
+	writeq(lmc->mask2, lmc->regs + LMC_CHAR_MASK2);
+	writeq(lmc->parity_test, lmc->regs + LMC_ECC_PARITY_TEST);
+
+	readq(lmc->regs + LMC_CHAR_MASK0);
+	readq(lmc->regs + LMC_CHAR_MASK2);
+	readq(lmc->regs + LMC_ECC_PARITY_TEST);
+
+	for (i = 0; i < lines; i++) {
+		memset((void *)addr, TEST_PATTERN, cline_size);
+		barrier();
+
+		/*
+		 * Flush L1 cachelines to the PoC (L2).
+		 * This will cause cacheline eviction to the L2.
+		 */
+		asm volatile("dc civac, %0\n"
+			     "dsb sy\n"
+			     : : "r"(addr + i * cline_size));
+	}
+
+	for (i = 0; i < lines; i++) {
+		/*
+		 * Flush L2 cachelines to the DRAM.
+		 * This will cause cacheline eviction to the DRAM
+		 * and ECC corruption according to the masks set.
+		 */
+		__asm__ volatile("sys #0,c11,C1,#2, %0\n"
+				 : : "r"(phys + i * cline_size));
+	}
+
+	for (i = 0; i < lines; i++) {
+		/*
+		 * Invalidate L2 cachelines.
+		 * The subsequent load will cause cacheline fetch
+		 * from the DRAM and an error interrupt
+		 */
+		__asm__ volatile("sys #0,c11,C1,#1, %0"
+				 : : "r"(phys + i * cline_size));
+	}
+
+	for (i = 0; i < lines; i++) {
+		/*
+		 * Invalidate L1 cachelines.
+		 * The subsequent load will cause cacheline fetch
+		 * from the L2 and/or DRAM
+		 */
+		asm volatile("dc ivac, %0\n"
+			     "dsb sy\n"
+			     : : "r"(addr + i * cline_size));
+	}
+
+	return 0;
+}
+
+static ssize_t thunderx_lmc_inject_ecc_write(struct file *file,
+					     const char __user *data,
+					     size_t count, loff_t *ppos)
+{
+	struct thunderx_lmc *lmc = file->private_data;
+
+	unsigned int cline_size = cache_line_size();
+
+	u8 tmp[cline_size];
+	void __iomem *addr;
+	unsigned int offs, timeout = 100000;
+
+	atomic_set(&lmc->ecc_int, 0);
+
+	lmc->mem = alloc_pages_node(lmc->node, GFP_KERNEL, 0);
+
+	if (!lmc->mem)
+		return -ENOMEM;
+
+	addr = page_address(lmc->mem);
+
+	while (!atomic_read(&lmc->ecc_int) && timeout--) {
+		stop_machine(inject_ecc_fn, lmc, NULL);
+
+		for (offs = 0; offs < PAGE_SIZE; offs += sizeof(tmp)) {
+			/*
+			 * Do a load from the previously rigged location
+			 * This should generate an error interrupt.
+			 */
+			memcpy(tmp, addr + offs, cline_size);
+			asm volatile("dsb ld\n");
+		}
+	}
+
+	__free_pages(lmc->mem, 0);
+
+	return count;
+}
+
+LMC_DEBUGFS_ENT(mask0);
+LMC_DEBUGFS_ENT(mask2);
+LMC_DEBUGFS_ENT(parity_test);
+
+DEBUGFS_STRUCT(inject_int, 0200, thunderx_lmc_inject_int_write, NULL);
+DEBUGFS_STRUCT(inject_ecc, 0200, thunderx_lmc_inject_ecc_write, NULL);
+DEBUGFS_STRUCT(int_w1c, 0400, NULL, thunderx_lmc_int_read);
+
+struct debugfs_entry *lmc_dfs_ents[] = {
+	&debugfs_mask0,
+	&debugfs_mask2,
+	&debugfs_parity_test,
+	&debugfs_inject_ecc,
+	&debugfs_inject_int,
+	&debugfs_int_w1c,
+};
+
+static int thunderx_create_debugfs_nodes(struct dentry *parent,
+					  struct debugfs_entry *attrs[],
+					  void *data,
+					  size_t num)
+{
+	int i;
+	struct dentry *ent;
+
+	if (!IS_ENABLED(CONFIG_EDAC_DEBUG))
+		return 0;
+
+	if (!parent)
+		return -ENOENT;
+
+	for (i = 0; i < num; i++) {
+		ent = edac_debugfs_create_file(attrs[i]->name, attrs[i]->mode,
+					       parent, data, &attrs[i]->fops);
+
+		if (!ent)
+			break;
+	}
+
+	return i;
+}
+
+static phys_addr_t thunderx_faddr_to_phys(u64 faddr, struct thunderx_lmc *lmc)
+{
+	phys_addr_t addr = 0;
+	int bank, xbits;
+
+	addr |= lmc->node << 40;
+	addr |= LMC_FADR_FDIMM(faddr) << lmc->dimm_lsb;
+	addr |= LMC_FADR_FBUNK(faddr) << lmc->rank_lsb;
+	addr |= LMC_FADR_FROW(faddr) << lmc->row_lsb;
+	addr |= (LMC_FADR_FCOL(faddr) >> 4) << lmc->col_hi_lsb;
+
+	bank = LMC_FADR_FBANK(faddr) << lmc->bank_lsb;
+
+	if (lmc->xor_bank)
+		bank ^= get_bits(addr, 12 + lmc->xbits, lmc->bank_width);
+
+	addr |= bank << lmc->bank_lsb;
+
+	xbits = PCI_FUNC(lmc->pdev->devfn);
+
+	if (lmc->l2c_alias)
+		xbits ^= get_bits(addr, 20, lmc->xbits) ^
+			 get_bits(addr, 12, lmc->xbits);
+
+	addr |= xbits << 7;
+
+	return addr;
+}
+
+static unsigned int thunderx_get_num_lmcs(unsigned int node)
+{
+	unsigned int number = 0;
+	struct pci_dev *pdev = NULL;
+
+	do {
+		pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+				      PCI_DEVICE_ID_THUNDER_LMC,
+				      pdev);
+		if (pdev) {
+#ifdef CONFIG_NUMA
+			if (pdev->dev.numa_node == node)
+				number++;
+#else
+			number++;
+#endif
+		}
+	} while (pdev);
+
+	return number;
+}
+
+#define LMC_MESSAGE_SIZE	120
+#define LMC_OTHER_SIZE		(50 * ARRAY_SIZE(lmc_errors))
+
+static irqreturn_t thunderx_lmc_err_isr(int irq, void *dev_id)
+{
+	struct mem_ctl_info *mci = dev_id;
+	struct thunderx_lmc *lmc = mci->pvt_info;
+
+	unsigned long head = ring_pos(lmc->ring_head, ARRAY_SIZE(lmc->err_ctx));
+	struct lmc_err_ctx *ctx = &lmc->err_ctx[head];
+
+	writeq(0, lmc->regs + LMC_CHAR_MASK0);
+	writeq(0, lmc->regs + LMC_CHAR_MASK2);
+	writeq(0x2, lmc->regs + LMC_ECC_PARITY_TEST);
+
+	ctx->reg_int = readq(lmc->regs + LMC_INT);
+	ctx->reg_fadr = readq(lmc->regs + LMC_FADR);
+	ctx->reg_nxm_fadr = readq(lmc->regs + LMC_NXM_FADR);
+	ctx->reg_scram_fadr = readq(lmc->regs + LMC_SCRAM_FADR);
+	ctx->reg_ecc_synd = readq(lmc->regs + LMC_ECC_SYND);
+
+	lmc->ring_head++;
+
+	atomic_set(&lmc->ecc_int, 1);
+
+	/* Clear the interrupt */
+	writeq(ctx->reg_int, lmc->regs + LMC_INT);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_lmc_threaded_isr(int irq, void *dev_id)
+{
+	struct mem_ctl_info *mci = dev_id;
+	struct thunderx_lmc *lmc = mci->pvt_info;
+	phys_addr_t phys_addr;
+
+	unsigned long tail;
+	struct lmc_err_ctx *ctx;
+
+	irqreturn_t ret = IRQ_NONE;
+
+	char *msg;
+	char *other;
+
+	msg = kmalloc(LMC_MESSAGE_SIZE, GFP_KERNEL);
+	other =  kmalloc(LMC_OTHER_SIZE, GFP_KERNEL);
+
+	if (!msg || !other)
+		goto err_free;
+
+	while (CIRC_CNT(lmc->ring_head, lmc->ring_tail,
+		ARRAY_SIZE(lmc->err_ctx))) {
+		tail = ring_pos(lmc->ring_tail, ARRAY_SIZE(lmc->err_ctx));
+
+		ctx = &lmc->err_ctx[tail];
+
+		dev_dbg(&lmc->pdev->dev, "LMC_INT: %016llx\n",
+			ctx->reg_int);
+		dev_dbg(&lmc->pdev->dev, "LMC_FADR: %016llx\n",
+			ctx->reg_fadr);
+		dev_dbg(&lmc->pdev->dev, "LMC_NXM_FADR: %016llx\n",
+			ctx->reg_nxm_fadr);
+		dev_dbg(&lmc->pdev->dev, "LMC_SCRAM_FADR: %016llx\n",
+			ctx->reg_scram_fadr);
+		dev_dbg(&lmc->pdev->dev, "LMC_ECC_SYND: %016llx\n",
+			ctx->reg_ecc_synd);
+
+		snprintf(msg, LMC_MESSAGE_SIZE,
+			 "DIMM %lld rank %lld bank %lld row %lld col %lld",
+			 LMC_FADR_FDIMM(ctx->reg_scram_fadr),
+			 LMC_FADR_FBUNK(ctx->reg_scram_fadr),
+			 LMC_FADR_FBANK(ctx->reg_scram_fadr),
+			 LMC_FADR_FROW(ctx->reg_scram_fadr),
+			 LMC_FADR_FCOL(ctx->reg_scram_fadr));
+
+		decode_register(other, LMC_OTHER_SIZE, lmc_errors,
+				ctx->reg_int);
+
+		phys_addr = thunderx_faddr_to_phys(ctx->reg_fadr, lmc);
+
+		if (ctx->reg_int & LMC_INT_UE)
+			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+					     phys_to_pfn(phys_addr),
+					     offset_in_page(phys_addr),
+					     0, -1, -1, -1, msg, other);
+		else if (ctx->reg_int & LMC_INT_CE)
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+					     phys_to_pfn(phys_addr),
+					     offset_in_page(phys_addr),
+					     0, -1, -1, -1, msg, other);
+
+		lmc->ring_tail++;
+	}
+
+	ret = IRQ_HANDLED;
+
+err_free:
+	kfree(msg);
+	kfree(other);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM
+static int thunderx_lmc_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	pci_save_state(pdev);
+	pci_disable_device(pdev);
+
+	pci_set_power_state(pdev, pci_choose_state(pdev, state));
+
+	return 0;
+}
+
+static int thunderx_lmc_resume(struct pci_dev *pdev)
+{
+	pci_set_power_state(pdev, PCI_D0);
+	pci_enable_wake(pdev, PCI_D0, 0);
+	pci_restore_state(pdev);
+
+	return 0;
+}
+#endif
+
+static const struct pci_device_id thunderx_lmc_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_LMC) },
+	{ 0, },
+};
+
+static inline int pci_dev_to_mc_idx(struct pci_dev *pdev)
+{
+	int node = dev_to_node(&pdev->dev);
+	int ret = PCI_FUNC(pdev->devfn);
+
+	ret += max(node, 0) << 3;
+
+	return ret;
+}
+
+static int thunderx_lmc_probe(struct pci_dev *pdev,
+				const struct pci_device_id *id)
+{
+	struct thunderx_lmc *lmc;
+	struct edac_mc_layer layer;
+	struct mem_ctl_info *mci;
+	u64 lmc_control, lmc_ddr_pll_ctl, lmc_config;
+	int ret;
+	u64 lmc_int;
+	void *l2c_ioaddr;
+
+	layer.type = EDAC_MC_LAYER_SLOT;
+	layer.size = 2;
+	layer.is_virt_csrow = false;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot enable PCI device: %d\n", ret);
+		return ret;
+	}
+
+	ret = pcim_iomap_regions(pdev, BIT(0), "thunderx_lmc");
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+		return ret;
+	}
+
+	mci = edac_mc_alloc(pci_dev_to_mc_idx(pdev), 1, &layer,
+			    sizeof(struct thunderx_lmc));
+	if (!mci)
+		return -ENOMEM;
+
+	mci->pdev = &pdev->dev;
+	lmc = mci->pvt_info;
+
+	pci_set_drvdata(pdev, mci);
+
+	lmc->regs = pcim_iomap_table(pdev)[0];
+
+	lmc_control = readq(lmc->regs + LMC_CONTROL);
+	lmc_ddr_pll_ctl = readq(lmc->regs + LMC_DDR_PLL_CTL);
+	lmc_config = readq(lmc->regs + LMC_CONFIG);
+
+	if (lmc_control & LMC_CONTROL_RDIMM) {
+		mci->mtype_cap = FIELD_GET(LMC_DDR_PLL_CTL_DDR4,
+					   lmc_ddr_pll_ctl) ?
+				MEM_RDDR4 : MEM_RDDR3;
+	} else {
+		mci->mtype_cap = FIELD_GET(LMC_DDR_PLL_CTL_DDR4,
+					   lmc_ddr_pll_ctl) ?
+				MEM_DDR4 : MEM_DDR3;
+	}
+
+	mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
+	mci->edac_cap = EDAC_FLAG_SECDED;
+
+	mci->mod_name = "thunderx-lmc";
+	mci->mod_ver = "1";
+	mci->ctl_name = "thunderx-lmc";
+	mci->dev_name = dev_name(&pdev->dev);
+	mci->scrub_mode = SCRUB_NONE;
+
+	lmc->pdev = pdev;
+	lmc->msix_ent.entry = 0;
+
+	lmc->ring_head = 0;
+	lmc->ring_tail = 0;
+
+	ret = pci_enable_msix_exact(pdev, &lmc->msix_ent, 1);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot enable interrupt: %d\n", ret);
+		goto err_free;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, lmc->msix_ent.vector,
+					thunderx_lmc_err_isr,
+					thunderx_lmc_threaded_isr, 0,
+					"[EDAC] ThunderX LMC", mci);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot set ISR: %d\n", ret);
+		goto err_free;
+	}
+
+	lmc->node = FIELD_GET(THUNDERX_NODE, pci_resource_start(pdev, 0));
+
+	lmc->xbits = thunderx_get_num_lmcs(lmc->node) >> 1;
+	lmc->bank_width = (FIELD_GET(LMC_DDR_PLL_CTL_DDR4, lmc_ddr_pll_ctl) &&
+			   FIELD_GET(LMC_CONFIG_BG2, lmc_config)) ? 4 : 3;
+
+	lmc->pbank_lsb = (lmc_config >> 5) & 0xf;
+	lmc->dimm_lsb  = 28 + lmc->pbank_lsb + lmc->xbits;
+	lmc->rank_lsb = lmc->dimm_lsb;
+	lmc->rank_lsb -= FIELD_GET(LMC_CONFIG_RANK_ENA, lmc_config) ? 1 : 0;
+	lmc->bank_lsb = 7 + lmc->xbits;
+	lmc->row_lsb = 14 + LMC_CONFIG_ROW_LSB(lmc_config) + lmc->xbits;
+
+	lmc->col_hi_lsb = lmc->bank_lsb + lmc->bank_width;
+
+	lmc->xor_bank = lmc_control & LMC_CONTROL_XOR_BANK;
+
+	l2c_ioaddr = ioremap(L2C_CTL | FIELD_PREP(THUNDERX_NODE, lmc->node),
+			     PAGE_SIZE);
+
+	if (!l2c_ioaddr) {
+		dev_err(&pdev->dev, "Cannot map L2C_CTL\n");
+		goto err_free;
+	}
+
+	lmc->l2c_alias = !(readq(l2c_ioaddr) & L2C_CTL_DISIDXALIAS);
+
+	iounmap(l2c_ioaddr);
+
+	ret = edac_mc_add_mc(mci);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot add the MC: %d\n", ret);
+		goto err_free;
+	}
+
+	lmc_int = readq(lmc->regs + LMC_INT);
+	writeq(lmc_int, lmc->regs + LMC_INT);
+
+	writeq(LMC_INT_ENA_ALL, lmc->regs + LMC_INT_ENA_W1S);
+
+	if (IS_ENABLED(CONFIG_EDAC_DEBUG)) {
+		ret = thunderx_create_debugfs_nodes(mci->debugfs,
+						    lmc_dfs_ents,
+						    lmc,
+						    ARRAY_SIZE(lmc_dfs_ents));
+
+		if (ret != ARRAY_SIZE(lmc_dfs_ents)) {
+			dev_warn(&pdev->dev, "Error creating debugfs entries: %d%s\n",
+				 ret, ret >= 0 ? " created" : "");
+		}
+	}
+
+	return 0;
+
+err_free:
+	pci_set_drvdata(pdev, NULL);
+	edac_mc_free(mci);
+
+	return ret;
+}
+
+static void thunderx_lmc_remove(struct pci_dev *pdev)
+{
+	struct mem_ctl_info *mci = pci_get_drvdata(pdev);
+	struct thunderx_lmc *lmc = mci->pvt_info;
+
+	writeq(LMC_INT_ENA_ALL, lmc->regs + LMC_INT_ENA_W1C);
+
+	edac_mc_del_mc(&pdev->dev);
+	edac_mc_free(mci);
+}
+
+MODULE_DEVICE_TABLE(pci, thunderx_lmc_pci_tbl);
+
+static struct pci_driver thunderx_lmc_driver = {
+	.name     = "thunderx_lmc_edac",
+	.probe    = thunderx_lmc_probe,
+	.remove   = thunderx_lmc_remove,
+#ifdef CONFIG_PM
+	.suspend  = thunderx_lmc_suspend,
+	.resume   = thunderx_lmc_resume,
+#endif
+	.id_table = thunderx_lmc_pci_tbl,
+};
+
+/*---------------------- OCX driver ---------------------------------*/
+
+#define PCI_DEVICE_ID_THUNDER_OCX 0xa013
+
+#define OCX_LINK_INTS		3
+#define OCX_INTS		(OCX_LINK_INTS + 1)
+#define OCX_RX_LANES		24
+#define OCX_RX_LANE_STATS	15
+
+#define OCX_COM_INT		0x100
+#define OCX_COM_INT_W1S		0x108
+#define OCX_COM_INT_ENA_W1S	0x110
+#define OCX_COM_INT_ENA_W1C	0x118
+
+#define OCX_COM_IO_BADID		BIT(54)
+#define OCX_COM_MEM_BADID		BIT(53)
+#define OCX_COM_COPR_BADID		BIT(52)
+#define OCX_COM_WIN_REQ_BADID		BIT(51)
+#define OCX_COM_WIN_REQ_TOUT		BIT(50)
+#define OCX_COM_RX_LANE			GENMASK(23, 0)
+
+#define OCX_COM_INT_CE			(OCX_COM_IO_BADID      | \
+					 OCX_COM_MEM_BADID     | \
+					 OCX_COM_COPR_BADID    | \
+					 OCX_COM_WIN_REQ_BADID | \
+					 OCX_COM_WIN_REQ_TOUT)
+
+static const struct error_descr ocx_com_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_IO_BADID,
+		.descr = "Invalid IO transaction node ID",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_MEM_BADID,
+		.descr = "Invalid memory transaction node ID",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_COPR_BADID,
+		.descr = "Invalid coprocessor transaction node ID",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_WIN_REQ_BADID,
+		.descr = "Invalid SLI transaction node ID",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_WIN_REQ_TOUT,
+		.descr = "Window/core request timeout",
+	},
+	{0, 0, NULL},
+};
+
+#define OCX_COM_LINKX_INT(x)		(0x120 + (x) * 8)
+#define OCX_COM_LINKX_INT_W1S(x)	(0x140 + (x) * 8)
+#define OCX_COM_LINKX_INT_ENA_W1S(x)	(0x160 + (x) * 8)
+#define OCX_COM_LINKX_INT_ENA_W1C(x)	(0x180 + (x) * 8)
+
+#define OCX_COM_LINK_BAD_WORD			BIT(13)
+#define OCX_COM_LINK_ALIGN_FAIL			BIT(12)
+#define OCX_COM_LINK_ALIGN_DONE			BIT(11)
+#define OCX_COM_LINK_UP				BIT(10)
+#define OCX_COM_LINK_STOP			BIT(9)
+#define OCX_COM_LINK_BLK_ERR			BIT(8)
+#define OCX_COM_LINK_REINIT			BIT(7)
+#define OCX_COM_LINK_LNK_DATA			BIT(6)
+#define OCX_COM_LINK_RXFIFO_DBE			BIT(5)
+#define OCX_COM_LINK_RXFIFO_SBE			BIT(4)
+#define OCX_COM_LINK_TXFIFO_DBE			BIT(3)
+#define OCX_COM_LINK_TXFIFO_SBE			BIT(2)
+#define OCX_COM_LINK_REPLAY_DBE			BIT(1)
+#define OCX_COM_LINK_REPLAY_SBE			BIT(0)
+
+static const struct error_descr ocx_com_link_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_LINK_REPLAY_SBE,
+		.descr = "Replay buffer single-bit error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_LINK_TXFIFO_SBE,
+		.descr = "TX FIFO single-bit error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_LINK_RXFIFO_SBE,
+		.descr = "RX FIFO single-bit error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_LINK_BLK_ERR,
+		.descr = "Block code error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_LINK_ALIGN_FAIL,
+		.descr = "Link alignment failure",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_COM_LINK_BAD_WORD,
+		.descr = "Bad code word",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = OCX_COM_LINK_REPLAY_DBE,
+		.descr = "Replay buffer double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = OCX_COM_LINK_TXFIFO_DBE,
+		.descr = "TX FIFO double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = OCX_COM_LINK_RXFIFO_DBE,
+		.descr = "RX FIFO double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = OCX_COM_LINK_STOP,
+		.descr = "Link stopped",
+	},
+	{0, 0, NULL},
+};
+
+#define OCX_COM_LINK_INT_UE       (OCX_COM_LINK_REPLAY_DBE | \
+				   OCX_COM_LINK_TXFIFO_DBE | \
+				   OCX_COM_LINK_RXFIFO_DBE | \
+				   OCX_COM_LINK_STOP)
+
+#define OCX_COM_LINK_INT_CE       (OCX_COM_LINK_REPLAY_SBE | \
+				   OCX_COM_LINK_TXFIFO_SBE | \
+				   OCX_COM_LINK_RXFIFO_SBE | \
+				   OCX_COM_LINK_BLK_ERR    | \
+				   OCX_COM_LINK_ALIGN_FAIL | \
+				   OCX_COM_LINK_BAD_WORD)
+
+#define OCX_LNE_INT(x)			(0x8018 + (x) * 0x100)
+#define OCX_LNE_INT_EN(x)		(0x8020 + (x) * 0x100)
+#define OCX_LNE_BAD_CNT(x)		(0x8028 + (x) * 0x100)
+#define OCX_LNE_CFG(x)			(0x8000 + (x) * 0x100)
+#define OCX_LNE_STAT(x, y)		(0x8040 + (x) * 0x100 + (y) * 8)
+
+#define OCX_LNE_CFG_RX_BDRY_LOCK_DIS		BIT(8)
+#define OCX_LNE_CFG_RX_STAT_WRAP_DIS		BIT(2)
+#define OCX_LNE_CFG_RX_STAT_RDCLR		BIT(1)
+#define OCX_LNE_CFG_RX_STAT_ENA			BIT(0)
+
+
+#define OCX_LANE_BAD_64B67B			BIT(8)
+#define OCX_LANE_DSKEW_FIFO_OVFL		BIT(5)
+#define OCX_LANE_SCRM_SYNC_LOSS			BIT(4)
+#define OCX_LANE_UKWN_CNTL_WORD			BIT(3)
+#define OCX_LANE_CRC32_ERR			BIT(2)
+#define OCX_LANE_BDRY_SYNC_LOSS			BIT(1)
+#define OCX_LANE_SERDES_LOCK_LOSS		BIT(0)
+
+#define OCX_COM_LANE_INT_UE       (0)
+#define OCX_COM_LANE_INT_CE       (OCX_LANE_SERDES_LOCK_LOSS | \
+				   OCX_LANE_BDRY_SYNC_LOSS   | \
+				   OCX_LANE_CRC32_ERR        | \
+				   OCX_LANE_UKWN_CNTL_WORD   | \
+				   OCX_LANE_SCRM_SYNC_LOSS   | \
+				   OCX_LANE_DSKEW_FIFO_OVFL  | \
+				   OCX_LANE_BAD_64B67B)
+
+static const struct error_descr ocx_lane_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_SERDES_LOCK_LOSS,
+		.descr = "RX SerDes lock lost",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_BDRY_SYNC_LOSS,
+		.descr = "RX word boundary lost",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_CRC32_ERR,
+		.descr = "CRC32 error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_UKWN_CNTL_WORD,
+		.descr = "Unknown control word",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_SCRM_SYNC_LOSS,
+		.descr = "Scrambler synchronization lost",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_DSKEW_FIFO_OVFL,
+		.descr = "RX deskew FIFO overflow",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = OCX_LANE_BAD_64B67B,
+		.descr = "Bad 64B/67B codeword",
+	},
+	{0, 0, NULL},
+};
+
+#define OCX_LNE_INT_ENA_ALL		(GENMASK(9, 8) | GENMASK(6, 0))
+#define OCX_COM_INT_ENA_ALL		(GENMASK(54, 50) | GENMASK(23, 0))
+#define OCX_COM_LINKX_INT_ENA_ALL	(GENMASK(13, 12) | \
+					 GENMASK(9, 7) | GENMASK(5, 0))
+
+#define OCX_TLKX_ECC_CTL(x)		(0x10018 + (x) * 0x2000)
+#define OCX_RLKX_ECC_CTL(x)		(0x18018 + (x) * 0x2000)
+
+struct ocx_com_err_ctx {
+	u64 reg_com_int;
+	u64 reg_lane_int[OCX_RX_LANES];
+	u64 reg_lane_stat11[OCX_RX_LANES];
+};
+
+struct ocx_link_err_ctx {
+	u64 reg_com_link_int;
+	int link;
+};
+
+struct thunderx_ocx {
+	void __iomem *regs;
+	int com_link;
+	struct pci_dev *pdev;
+	struct edac_device_ctl_info *edac_dev;
+
+	struct dentry *debugfs;
+	struct msix_entry msix_ent[OCX_INTS];
+
+	struct ocx_com_err_ctx com_err_ctx[RING_ENTRIES];
+	struct ocx_link_err_ctx link_err_ctx[RING_ENTRIES];
+
+	unsigned long com_ring_head;
+	unsigned long com_ring_tail;
+
+	unsigned long link_ring_head;
+	unsigned long link_ring_tail;
+};
+
+#define OCX_MESSAGE_SIZE	SZ_1K
+#define OCX_OTHER_SIZE		(50 * ARRAY_SIZE(ocx_com_link_errors))
+
+/* This handler is threaded */
+static irqreturn_t thunderx_ocx_com_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+						msix_ent[msix->entry]);
+
+	int lane;
+	unsigned long head = ring_pos(ocx->com_ring_head,
+				      ARRAY_SIZE(ocx->com_err_ctx));
+	struct ocx_com_err_ctx *ctx = &ocx->com_err_ctx[head];
+
+	ctx->reg_com_int = readq(ocx->regs + OCX_COM_INT);
+
+	for (lane = 0; lane < OCX_RX_LANES; lane++) {
+		ctx->reg_lane_int[lane] =
+			readq(ocx->regs + OCX_LNE_INT(lane));
+		ctx->reg_lane_stat11[lane] =
+			readq(ocx->regs + OCX_LNE_STAT(lane, 11));
+
+		writeq(ctx->reg_lane_int[lane], ocx->regs + OCX_LNE_INT(lane));
+	}
+
+	writeq(ctx->reg_com_int, ocx->regs + OCX_COM_INT);
+
+	ocx->com_ring_head++;
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+						msix_ent[msix->entry]);
+
+	irqreturn_t ret = IRQ_NONE;
+
+	unsigned long tail;
+	struct ocx_com_err_ctx *ctx;
+	int lane;
+	char *msg;
+	char *other;
+
+	msg = kmalloc(OCX_MESSAGE_SIZE, GFP_KERNEL);
+	other = kmalloc(OCX_OTHER_SIZE, GFP_KERNEL);
+
+	if (!msg || !other)
+		goto err_free;
+
+	while (CIRC_CNT(ocx->com_ring_head, ocx->com_ring_tail,
+			ARRAY_SIZE(ocx->com_err_ctx))) {
+		tail = ring_pos(ocx->com_ring_tail,
+				ARRAY_SIZE(ocx->com_err_ctx));
+		ctx = &ocx->com_err_ctx[tail];
+
+		snprintf(msg, OCX_MESSAGE_SIZE, "%s: OCX_COM_INT: %016llx",
+			ocx->edac_dev->ctl_name, ctx->reg_com_int);
+
+		decode_register(other, OCX_OTHER_SIZE,
+				ocx_com_errors, ctx->reg_com_int);
+
+		strncat(msg, other, OCX_MESSAGE_SIZE);
+
+		for (lane = 0; lane < OCX_RX_LANES; lane++)
+			if (ctx->reg_com_int & BIT(lane)) {
+				snprintf(other, OCX_OTHER_SIZE,
+					 "\n\tOCX_LNE_INT[%02d]: %016llx OCX_LNE_STAT11[%02d]: %016llx",
+					 lane, ctx->reg_lane_int[lane],
+					 lane, ctx->reg_lane_stat11[lane]);
+
+				strncat(msg, other, OCX_MESSAGE_SIZE);
+
+				decode_register(other, OCX_OTHER_SIZE,
+						ocx_lane_errors,
+						ctx->reg_lane_int[lane]);
+				strncat(msg, other, OCX_MESSAGE_SIZE);
+			}
+
+		if (ctx->reg_com_int & OCX_COM_INT_CE)
+			edac_device_handle_ce(ocx->edac_dev, 0, 0, msg);
+
+		ocx->com_ring_tail++;
+	}
+
+	ret = IRQ_HANDLED;
+
+err_free:
+	kfree(other);
+	kfree(msg);
+
+	return ret;
+}
+
+static irqreturn_t thunderx_ocx_lnk_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+						msix_ent[msix->entry]);
+	unsigned long head = ring_pos(ocx->link_ring_head,
+				      ARRAY_SIZE(ocx->link_err_ctx));
+	struct ocx_link_err_ctx *ctx = &ocx->link_err_ctx[head];
+
+	ctx->link = msix->entry;
+	ctx->reg_com_link_int = readq(ocx->regs + OCX_COM_LINKX_INT(ctx->link));
+
+	writeq(ctx->reg_com_link_int, ocx->regs + OCX_COM_LINKX_INT(ctx->link));
+
+	ocx->link_ring_head++;
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+						msix_ent[msix->entry]);
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long tail;
+	struct ocx_link_err_ctx *ctx;
+
+	char *msg;
+	char *other;
+
+	msg = kmalloc(OCX_MESSAGE_SIZE, GFP_KERNEL);
+	other = kmalloc(OCX_OTHER_SIZE, GFP_KERNEL);
+
+	if (!msg || !other)
+		goto err_free;
+
+	while (CIRC_CNT(ocx->link_ring_head, ocx->link_ring_tail,
+			ARRAY_SIZE(ocx->link_err_ctx))) {
+		tail = ring_pos(ocx->link_ring_head,
+				ARRAY_SIZE(ocx->link_err_ctx));
+
+		ctx = &ocx->link_err_ctx[tail];
+
+		snprintf(msg, OCX_MESSAGE_SIZE,
+			 "%s: OCX_COM_LINK_INT[%d]: %016llx",
+			 ocx->edac_dev->ctl_name,
+			 ctx->link, ctx->reg_com_link_int);
+
+		decode_register(other, OCX_OTHER_SIZE,
+				ocx_com_link_errors, ctx->reg_com_link_int);
+
+		strncat(msg, other, OCX_MESSAGE_SIZE);
+
+		if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE)
+			edac_device_handle_ue(ocx->edac_dev, 0, 0, msg);
+		else if (ctx->reg_com_link_int & OCX_COM_LINK_INT_CE)
+			edac_device_handle_ce(ocx->edac_dev, 0, 0, msg);
+
+		ocx->link_ring_tail++;
+	}
+
+	ret = IRQ_HANDLED;
+err_free:
+	kfree(other);
+	kfree(msg);
+
+	return ret;
+}
+
+#define OCX_DEBUGFS_ATTR(_name, _reg)	DEBUGFS_REG_ATTR(ocx, _name, _reg)
+
+OCX_DEBUGFS_ATTR(tlk0_ecc_ctl, OCX_TLKX_ECC_CTL(0));
+OCX_DEBUGFS_ATTR(tlk1_ecc_ctl, OCX_TLKX_ECC_CTL(1));
+OCX_DEBUGFS_ATTR(tlk2_ecc_ctl, OCX_TLKX_ECC_CTL(2));
+
+OCX_DEBUGFS_ATTR(rlk0_ecc_ctl, OCX_RLKX_ECC_CTL(0));
+OCX_DEBUGFS_ATTR(rlk1_ecc_ctl, OCX_RLKX_ECC_CTL(1));
+OCX_DEBUGFS_ATTR(rlk2_ecc_ctl, OCX_RLKX_ECC_CTL(2));
+
+OCX_DEBUGFS_ATTR(com_link0_int, OCX_COM_LINKX_INT_W1S(0));
+OCX_DEBUGFS_ATTR(com_link1_int, OCX_COM_LINKX_INT_W1S(1));
+OCX_DEBUGFS_ATTR(com_link2_int, OCX_COM_LINKX_INT_W1S(2));
+
+OCX_DEBUGFS_ATTR(lne00_badcnt, OCX_LNE_BAD_CNT(0));
+OCX_DEBUGFS_ATTR(lne01_badcnt, OCX_LNE_BAD_CNT(1));
+OCX_DEBUGFS_ATTR(lne02_badcnt, OCX_LNE_BAD_CNT(2));
+OCX_DEBUGFS_ATTR(lne03_badcnt, OCX_LNE_BAD_CNT(3));
+OCX_DEBUGFS_ATTR(lne04_badcnt, OCX_LNE_BAD_CNT(4));
+OCX_DEBUGFS_ATTR(lne05_badcnt, OCX_LNE_BAD_CNT(5));
+OCX_DEBUGFS_ATTR(lne06_badcnt, OCX_LNE_BAD_CNT(6));
+OCX_DEBUGFS_ATTR(lne07_badcnt, OCX_LNE_BAD_CNT(7));
+
+OCX_DEBUGFS_ATTR(lne08_badcnt, OCX_LNE_BAD_CNT(8));
+OCX_DEBUGFS_ATTR(lne09_badcnt, OCX_LNE_BAD_CNT(9));
+OCX_DEBUGFS_ATTR(lne10_badcnt, OCX_LNE_BAD_CNT(10));
+OCX_DEBUGFS_ATTR(lne11_badcnt, OCX_LNE_BAD_CNT(11));
+OCX_DEBUGFS_ATTR(lne12_badcnt, OCX_LNE_BAD_CNT(12));
+OCX_DEBUGFS_ATTR(lne13_badcnt, OCX_LNE_BAD_CNT(13));
+OCX_DEBUGFS_ATTR(lne14_badcnt, OCX_LNE_BAD_CNT(14));
+OCX_DEBUGFS_ATTR(lne15_badcnt, OCX_LNE_BAD_CNT(15));
+
+OCX_DEBUGFS_ATTR(lne16_badcnt, OCX_LNE_BAD_CNT(16));
+OCX_DEBUGFS_ATTR(lne17_badcnt, OCX_LNE_BAD_CNT(17));
+OCX_DEBUGFS_ATTR(lne18_badcnt, OCX_LNE_BAD_CNT(18));
+OCX_DEBUGFS_ATTR(lne19_badcnt, OCX_LNE_BAD_CNT(19));
+OCX_DEBUGFS_ATTR(lne20_badcnt, OCX_LNE_BAD_CNT(20));
+OCX_DEBUGFS_ATTR(lne21_badcnt, OCX_LNE_BAD_CNT(21));
+OCX_DEBUGFS_ATTR(lne22_badcnt, OCX_LNE_BAD_CNT(22));
+OCX_DEBUGFS_ATTR(lne23_badcnt, OCX_LNE_BAD_CNT(23));
+
+OCX_DEBUGFS_ATTR(com_int, OCX_COM_INT_W1S);
+
+struct debugfs_entry *ocx_dfs_ents[] = {
+	&debugfs_tlk0_ecc_ctl,
+	&debugfs_tlk1_ecc_ctl,
+	&debugfs_tlk2_ecc_ctl,
+
+	&debugfs_rlk0_ecc_ctl,
+	&debugfs_rlk1_ecc_ctl,
+	&debugfs_rlk2_ecc_ctl,
+
+	&debugfs_com_link0_int,
+	&debugfs_com_link1_int,
+	&debugfs_com_link2_int,
+
+	&debugfs_lne00_badcnt,
+	&debugfs_lne01_badcnt,
+	&debugfs_lne02_badcnt,
+	&debugfs_lne03_badcnt,
+	&debugfs_lne04_badcnt,
+	&debugfs_lne05_badcnt,
+	&debugfs_lne06_badcnt,
+	&debugfs_lne07_badcnt,
+	&debugfs_lne08_badcnt,
+	&debugfs_lne09_badcnt,
+	&debugfs_lne10_badcnt,
+	&debugfs_lne11_badcnt,
+	&debugfs_lne12_badcnt,
+	&debugfs_lne13_badcnt,
+	&debugfs_lne14_badcnt,
+	&debugfs_lne15_badcnt,
+	&debugfs_lne16_badcnt,
+	&debugfs_lne17_badcnt,
+	&debugfs_lne18_badcnt,
+	&debugfs_lne19_badcnt,
+	&debugfs_lne20_badcnt,
+	&debugfs_lne21_badcnt,
+	&debugfs_lne22_badcnt,
+	&debugfs_lne23_badcnt,
+
+	&debugfs_com_int,
+};
+
+static const struct pci_device_id thunderx_ocx_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_OCX) },
+	{ 0, },
+};
+
+static void thunderx_ocx_clearstats(struct thunderx_ocx *ocx)
+{
+	int lane, stat, cfg;
+
+	for (lane = 0; lane < OCX_RX_LANES; lane++) {
+		cfg = readq(ocx->regs + OCX_LNE_CFG(lane));
+		cfg |= OCX_LNE_CFG_RX_STAT_RDCLR;
+		cfg &= ~OCX_LNE_CFG_RX_STAT_ENA;
+		writeq(cfg, ocx->regs + OCX_LNE_CFG(lane));
+
+		for (stat = 0; stat < OCX_RX_LANE_STATS; stat++)
+			readq(ocx->regs + OCX_LNE_STAT(lane, stat));
+	}
+}
+
+static int thunderx_ocx_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	struct thunderx_ocx *ocx;
+	struct edac_device_ctl_info *edac_dev;
+	char name[32];
+	int idx;
+	int i;
+	int ret;
+	u64 reg;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot enable PCI device: %d\n", ret);
+		return ret;
+	}
+
+	ret = pcim_iomap_regions(pdev, BIT(0), "thunderx_ocx");
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+		return ret;
+	}
+
+	idx = edac_device_alloc_index();
+	snprintf(name, sizeof(name), "OCX%d", idx);
+	edac_dev = edac_device_alloc_ctl_info(sizeof(struct thunderx_ocx),
+					      name, 1, "CCPI", 1,
+					      0, NULL, 0, idx);
+	if (!edac_dev) {
+		dev_err(&pdev->dev, "Cannot allocate EDAC device: %d\n", ret);
+		return -ENOMEM;
+	}
+	ocx = edac_dev->pvt_info;
+	ocx->edac_dev = edac_dev;
+	ocx->com_ring_head = 0;
+	ocx->com_ring_tail = 0;
+	ocx->link_ring_head = 0;
+	ocx->link_ring_tail = 0;
+
+	ocx->regs = pcim_iomap_table(pdev)[0];
+	if (!ocx->regs) {
+		dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+		ret = -ENODEV;
+		goto err_free;
+	}
+
+	ocx->pdev = pdev;
+
+	for (i = 0; i < OCX_INTS; i++) {
+		ocx->msix_ent[i].entry = i;
+		ocx->msix_ent[i].vector = 0;
+	}
+
+	ret = pci_enable_msix_exact(pdev, ocx->msix_ent, OCX_INTS);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot enable interrupt: %d\n", ret);
+		goto err_free;
+	}
+
+	for (i = 0; i < OCX_INTS; i++) {
+		ret = devm_request_threaded_irq(&pdev->dev,
+						ocx->msix_ent[i].vector,
+						(i == 3) ?
+						 thunderx_ocx_com_isr :
+						 thunderx_ocx_lnk_isr,
+						(i == 3) ?
+						 thunderx_ocx_com_threaded_isr :
+						 thunderx_ocx_lnk_threaded_isr,
+						0, "[EDAC] ThunderX OCX",
+						&ocx->msix_ent[i]);
+		if (ret)
+			goto err_free;
+	}
+
+	edac_dev->dev = &pdev->dev;
+	edac_dev->dev_name = dev_name(&pdev->dev);
+	edac_dev->mod_name = "thunderx-ocx";
+	edac_dev->ctl_name = "thunderx-ocx";
+
+	ret = edac_device_add_device(edac_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot add EDAC device: %d\n", ret);
+		goto err_free;
+	}
+
+	if (IS_ENABLED(CONFIG_EDAC_DEBUG)) {
+		ocx->debugfs = edac_debugfs_create_dir(pdev->dev.kobj.name);
+
+		ret = thunderx_create_debugfs_nodes(ocx->debugfs,
+						    ocx_dfs_ents,
+						    ocx,
+						    ARRAY_SIZE(ocx_dfs_ents));
+		if (ret != ARRAY_SIZE(ocx_dfs_ents)) {
+			dev_warn(&pdev->dev, "Error creating debugfs entries: %d%s\n",
+				 ret, ret >= 0 ? " created" : "");
+		}
+	}
+
+	pci_set_drvdata(pdev, edac_dev);
+
+	thunderx_ocx_clearstats(ocx);
+
+	for (i = 0; i < OCX_RX_LANES; i++) {
+		writeq(OCX_LNE_INT_ENA_ALL,
+		       ocx->regs + OCX_LNE_INT_EN(i));
+
+		reg = readq(ocx->regs + OCX_LNE_INT(i));
+		writeq(reg, ocx->regs + OCX_LNE_INT(i));
+
+	}
+
+	for (i = 0; i < OCX_LINK_INTS; i++) {
+		reg = readq(ocx->regs + OCX_COM_LINKX_INT(i));
+		writeq(reg, ocx->regs + OCX_COM_LINKX_INT(i));
+
+		writeq(OCX_COM_LINKX_INT_ENA_ALL,
+		       ocx->regs + OCX_COM_LINKX_INT_ENA_W1S(i));
+	}
+
+	reg = readq(ocx->regs + OCX_COM_INT);
+	writeq(reg, ocx->regs + OCX_COM_INT);
+
+	writeq(OCX_COM_INT_ENA_ALL, ocx->regs + OCX_COM_INT_ENA_W1S);
+
+	return 0;
+err_free:
+	edac_device_free_ctl_info(edac_dev);
+
+	return ret;
+}
+
+static void thunderx_ocx_remove(struct pci_dev *pdev)
+{
+	struct edac_device_ctl_info *edac_dev = pci_get_drvdata(pdev);
+	struct thunderx_ocx *ocx = edac_dev->pvt_info;
+	int i;
+
+	writeq(OCX_COM_INT_ENA_ALL, ocx->regs + OCX_COM_INT_ENA_W1C);
+
+	for (i = 0; i < OCX_INTS; i++) {
+		writeq(OCX_COM_LINKX_INT_ENA_ALL,
+		       ocx->regs + OCX_COM_LINKX_INT_ENA_W1C(i));
+	}
+
+	edac_debugfs_remove_recursive(ocx->debugfs);
+
+	edac_device_del_device(&pdev->dev);
+	edac_device_free_ctl_info(edac_dev);
+}
+
+MODULE_DEVICE_TABLE(pci, thunderx_ocx_pci_tbl);
+
+static struct pci_driver thunderx_ocx_driver = {
+	.name     = "thunderx_ocx_edac",
+	.probe    = thunderx_ocx_probe,
+	.remove   = thunderx_ocx_remove,
+	.id_table = thunderx_ocx_pci_tbl,
+};
+
+/*---------------------- L2C driver ---------------------------------*/
+
+#define PCI_DEVICE_ID_THUNDER_L2C_TAD 0xa02e
+#define PCI_DEVICE_ID_THUNDER_L2C_CBC 0xa02f
+#define PCI_DEVICE_ID_THUNDER_L2C_MCI 0xa030
+
+#define L2C_TAD_INT_W1C		0x40000
+#define L2C_TAD_INT_W1S		0x40008
+
+#define L2C_TAD_INT_ENA_W1C	0x40020
+#define L2C_TAD_INT_ENA_W1S	0x40028
+
+
+#define L2C_TAD_INT_L2DDBE	 BIT(1)
+#define L2C_TAD_INT_SBFSBE	 BIT(2)
+#define L2C_TAD_INT_SBFDBE	 BIT(3)
+#define L2C_TAD_INT_FBFSBE	 BIT(4)
+#define L2C_TAD_INT_FBFDBE	 BIT(5)
+#define L2C_TAD_INT_TAGDBE	 BIT(9)
+#define L2C_TAD_INT_RDDISLMC	 BIT(15)
+#define L2C_TAD_INT_WRDISLMC	 BIT(16)
+#define L2C_TAD_INT_LFBTO	 BIT(17)
+#define L2C_TAD_INT_GSYNCTO	 BIT(18)
+#define L2C_TAD_INT_RTGSBE	 BIT(32)
+#define L2C_TAD_INT_RTGDBE	 BIT(33)
+#define L2C_TAD_INT_RDDISOCI	 BIT(34)
+#define L2C_TAD_INT_WRDISOCI	 BIT(35)
+
+#define L2C_TAD_INT_ECC		(L2C_TAD_INT_L2DDBE | \
+				 L2C_TAD_INT_SBFSBE | L2C_TAD_INT_SBFDBE | \
+				 L2C_TAD_INT_FBFSBE | L2C_TAD_INT_FBFDBE)
+
+#define L2C_TAD_INT_CE          (L2C_TAD_INT_SBFSBE | \
+				 L2C_TAD_INT_FBFSBE)
+
+#define L2C_TAD_INT_UE          (L2C_TAD_INT_L2DDBE | \
+				 L2C_TAD_INT_SBFDBE | \
+				 L2C_TAD_INT_FBFDBE | \
+				 L2C_TAD_INT_TAGDBE | \
+				 L2C_TAD_INT_RTGDBE | \
+				 L2C_TAD_INT_WRDISOCI | \
+				 L2C_TAD_INT_RDDISOCI | \
+				 L2C_TAD_INT_WRDISLMC | \
+				 L2C_TAD_INT_RDDISLMC | \
+				 L2C_TAD_INT_LFBTO    | \
+				 L2C_TAD_INT_GSYNCTO)
+
+static const struct error_descr l2_tad_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = L2C_TAD_INT_SBFSBE,
+		.descr = "SBF single-bit error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = L2C_TAD_INT_FBFSBE,
+		.descr = "FBF single-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_L2DDBE,
+		.descr = "L2D double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_SBFDBE,
+		.descr = "SBF double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_FBFDBE,
+		.descr = "FBF double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_TAGDBE,
+		.descr = "TAG double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_RTGDBE,
+		.descr = "RTG double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_WRDISOCI,
+		.descr = "Write to a disabled CCPI",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_RDDISOCI,
+		.descr = "Read from a disabled CCPI",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_WRDISLMC,
+		.descr = "Write to a disabled LMC",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_RDDISLMC,
+		.descr = "Read from a disabled LMC",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_LFBTO,
+		.descr = "LFB entry timeout",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_TAD_INT_GSYNCTO,
+		.descr = "Global sync CCPI timeout",
+	},
+	{0, 0, NULL},
+};
+
+#define L2C_TAD_INT_TAG		(L2C_TAD_INT_TAGDBE)
+
+#define L2C_TAD_INT_RTG		(L2C_TAD_INT_RTGDBE)
+
+#define L2C_TAD_INT_DISLMC	(L2C_TAD_INT_WRDISLMC | L2C_TAD_INT_RDDISLMC)
+
+#define L2C_TAD_INT_DISOCI	(L2C_TAD_INT_WRDISOCI | L2C_TAD_INT_RDDISOCI)
+
+#define L2C_TAD_INT_ENA_ALL	(L2C_TAD_INT_ECC | L2C_TAD_INT_TAG | \
+				 L2C_TAD_INT_RTG | \
+				 L2C_TAD_INT_DISLMC | L2C_TAD_INT_DISOCI | \
+				 L2C_TAD_INT_LFBTO)
+
+#define L2C_TAD_TIMETWO		0x50000
+#define L2C_TAD_TIMEOUT		0x50100
+#define L2C_TAD_ERR		0x60000
+#define L2C_TAD_TQD_ERR		0x60100
+#define L2C_TAD_TTG_ERR		0x60200
+
+
+#define L2C_CBC_INT_W1C		0x60000
+
+#define L2C_CBC_INT_RSDSBE	 BIT(0)
+#define L2C_CBC_INT_RSDDBE	 BIT(1)
+
+#define L2C_CBC_INT_RSD		 (L2C_CBC_INT_RSDSBE | L2C_CBC_INT_RSDDBE)
+
+#define L2C_CBC_INT_MIBSBE	 BIT(4)
+#define L2C_CBC_INT_MIBDBE	 BIT(5)
+
+#define L2C_CBC_INT_MIB		 (L2C_CBC_INT_MIBSBE | L2C_CBC_INT_MIBDBE)
+
+#define L2C_CBC_INT_IORDDISOCI	 BIT(6)
+#define L2C_CBC_INT_IOWRDISOCI	 BIT(7)
+
+#define L2C_CBC_INT_IODISOCI	 (L2C_CBC_INT_IORDDISOCI | \
+				  L2C_CBC_INT_IOWRDISOCI)
+
+#define L2C_CBC_INT_CE		 (L2C_CBC_INT_RSDSBE | L2C_CBC_INT_MIBSBE)
+#define L2C_CBC_INT_UE		 (L2C_CBC_INT_RSDDBE | L2C_CBC_INT_MIBDBE)
+
+
+static const struct error_descr l2_cbc_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = L2C_CBC_INT_RSDSBE,
+		.descr = "RSD single-bit error",
+	},
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = L2C_CBC_INT_MIBSBE,
+		.descr = "MIB single-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_CBC_INT_RSDDBE,
+		.descr = "RSD double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_CBC_INT_MIBDBE,
+		.descr = "MIB double-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_CBC_INT_IORDDISOCI,
+		.descr = "Read from a disabled CCPI",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_CBC_INT_IOWRDISOCI,
+		.descr = "Write to a disabled CCPI",
+	},
+	{0, 0, NULL},
+};
+
+#define L2C_CBC_INT_W1S		0x60008
+#define L2C_CBC_INT_ENA_W1C	0x60020
+
+#define L2C_CBC_INT_ENA_ALL	 (L2C_CBC_INT_RSD | L2C_CBC_INT_MIB | \
+				  L2C_CBC_INT_IODISOCI)
+
+#define L2C_CBC_INT_ENA_W1S	0x60028
+
+#define L2C_CBC_IODISOCIERR	0x80008
+#define L2C_CBC_IOCERR		0x80010
+#define L2C_CBC_RSDERR		0x80018
+#define L2C_CBC_MIBERR		0x80020
+
+
+#define L2C_MCI_INT_W1C		0x0
+
+#define L2C_MCI_INT_VBFSBE	 BIT(0)
+#define L2C_MCI_INT_VBFDBE	 BIT(1)
+
+static const struct error_descr l2_mci_errors[] = {
+	{
+		.type  = ERR_CORRECTED,
+		.mask  = L2C_MCI_INT_VBFSBE,
+		.descr = "VBF single-bit error",
+	},
+	{
+		.type  = ERR_UNCORRECTED,
+		.mask  = L2C_MCI_INT_VBFDBE,
+		.descr = "VBF double-bit error",
+	},
+	{0, 0, NULL},
+};
+
+#define L2C_MCI_INT_W1S		0x8
+#define L2C_MCI_INT_ENA_W1C	0x20
+
+#define L2C_MCI_INT_ENA_ALL	 (L2C_MCI_INT_VBFSBE | L2C_MCI_INT_VBFDBE)
+
+#define L2C_MCI_INT_ENA_W1S	0x28
+
+#define L2C_MCI_ERR		0x10000
+
+#define L2C_MESSAGE_SIZE	SZ_1K
+#define L2C_OTHER_SIZE		(50 * ARRAY_SIZE(l2_tad_errors))
+
+struct l2c_err_ctx {
+	char *reg_ext_name;
+	u64  reg_int;
+	u64  reg_ext;
+};
+
+struct thunderx_l2c {
+	void __iomem *regs;
+	struct pci_dev *pdev;
+	struct edac_device_ctl_info *edac_dev;
+
+	struct dentry *debugfs;
+
+	int index;
+
+	struct msix_entry msix_ent;
+
+	struct l2c_err_ctx err_ctx[RING_ENTRIES];
+	unsigned long ring_head;
+	unsigned long ring_tail;
+};
+
+static irqreturn_t thunderx_l2c_tad_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_l2c *tad = container_of(msix, struct thunderx_l2c,
+						msix_ent);
+
+	unsigned long head = ring_pos(tad->ring_head, ARRAY_SIZE(tad->err_ctx));
+	struct l2c_err_ctx *ctx = &tad->err_ctx[head];
+
+	ctx->reg_int = readq(tad->regs + L2C_TAD_INT_W1C);
+
+	if (ctx->reg_int & L2C_TAD_INT_ECC) {
+		ctx->reg_ext_name = "TQD_ERR";
+		ctx->reg_ext = readq(tad->regs + L2C_TAD_TQD_ERR);
+	} else if (ctx->reg_int & L2C_TAD_INT_TAG) {
+		ctx->reg_ext_name = "TTG_ERR";
+		ctx->reg_ext = readq(tad->regs + L2C_TAD_TTG_ERR);
+	} else if (ctx->reg_int & L2C_TAD_INT_LFBTO) {
+		ctx->reg_ext_name = "TIMEOUT";
+		ctx->reg_ext = readq(tad->regs + L2C_TAD_TIMEOUT);
+	} else if (ctx->reg_int & L2C_TAD_INT_DISOCI) {
+		ctx->reg_ext_name = "ERR";
+		ctx->reg_ext = readq(tad->regs + L2C_TAD_ERR);
+	}
+
+	writeq(ctx->reg_int, tad->regs + L2C_TAD_INT_W1C);
+
+	tad->ring_head++;
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_l2c_cbc_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_l2c *cbc = container_of(msix, struct thunderx_l2c,
+						msix_ent);
+
+	unsigned long head = ring_pos(cbc->ring_head, ARRAY_SIZE(cbc->err_ctx));
+	struct l2c_err_ctx *ctx = &cbc->err_ctx[head];
+
+	ctx->reg_int = readq(cbc->regs + L2C_CBC_INT_W1C);
+
+	if (ctx->reg_int & L2C_CBC_INT_RSD) {
+		ctx->reg_ext_name = "RSDERR";
+		ctx->reg_ext = readq(cbc->regs + L2C_CBC_RSDERR);
+	} else if (ctx->reg_int & L2C_CBC_INT_MIB) {
+		ctx->reg_ext_name = "MIBERR";
+		ctx->reg_ext = readq(cbc->regs + L2C_CBC_MIBERR);
+	} else if (ctx->reg_int & L2C_CBC_INT_IODISOCI) {
+		ctx->reg_ext_name = "IODISOCIERR";
+		ctx->reg_ext = readq(cbc->regs + L2C_CBC_IODISOCIERR);
+	}
+
+	writeq(ctx->reg_int, cbc->regs + L2C_CBC_INT_W1C);
+
+	cbc->ring_head++;
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_l2c_mci_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_l2c *mci = container_of(msix, struct thunderx_l2c,
+						msix_ent);
+
+	unsigned long head = ring_pos(mci->ring_head, ARRAY_SIZE(mci->err_ctx));
+	struct l2c_err_ctx *ctx = &mci->err_ctx[head];
+
+	ctx->reg_int = readq(mci->regs + L2C_MCI_INT_W1C);
+	ctx->reg_ext = readq(mci->regs + L2C_MCI_ERR);
+
+	writeq(ctx->reg_int, mci->regs + L2C_MCI_INT_W1C);
+
+	ctx->reg_ext_name = "ERR";
+
+	mci->ring_head++;
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id)
+{
+	struct msix_entry *msix = irq_id;
+	struct thunderx_l2c *l2c = container_of(msix, struct thunderx_l2c,
+						msix_ent);
+
+	unsigned long tail = ring_pos(l2c->ring_tail, ARRAY_SIZE(l2c->err_ctx));
+	struct l2c_err_ctx *ctx = &l2c->err_ctx[tail];
+	irqreturn_t ret = IRQ_NONE;
+
+	u64 mask_ue, mask_ce;
+	const struct error_descr *l2_errors;
+	char *reg_int_name;
+
+	char *msg;
+	char *other;
+
+	msg = kmalloc(OCX_MESSAGE_SIZE, GFP_KERNEL);
+	other = kmalloc(OCX_OTHER_SIZE, GFP_KERNEL);
+
+	if (!msg || !other)
+		goto err_free;
+
+	switch (l2c->pdev->device) {
+	case PCI_DEVICE_ID_THUNDER_L2C_TAD:
+		reg_int_name = "L2C_TAD_INT";
+		mask_ue = L2C_TAD_INT_UE;
+		mask_ce = L2C_TAD_INT_CE;
+		l2_errors = l2_tad_errors;
+		break;
+	case PCI_DEVICE_ID_THUNDER_L2C_CBC:
+		reg_int_name = "L2C_CBC_INT";
+		mask_ue = L2C_CBC_INT_UE;
+		mask_ce = L2C_CBC_INT_CE;
+		l2_errors = l2_cbc_errors;
+		break;
+	case PCI_DEVICE_ID_THUNDER_L2C_MCI:
+		reg_int_name = "L2C_MCI_INT";
+		mask_ue = L2C_MCI_INT_VBFDBE;
+		mask_ce = L2C_MCI_INT_VBFSBE;
+		l2_errors = l2_mci_errors;
+		break;
+	default:
+		dev_err(&l2c->pdev->dev, "Unsupported device: %04x\n",
+			l2c->pdev->device);
+		return IRQ_NONE;
+	}
+
+	while (CIRC_CNT(l2c->ring_head, l2c->ring_tail,
+			ARRAY_SIZE(l2c->err_ctx))) {
+		snprintf(msg, L2C_MESSAGE_SIZE,
+			 "%s: %s: %016llx, %s: %016llx",
+			 l2c->edac_dev->ctl_name, reg_int_name, ctx->reg_int,
+			 ctx->reg_ext_name, ctx->reg_ext);
+
+		decode_register(other, L2C_OTHER_SIZE, l2_errors, ctx->reg_int);
+
+		strncat(msg, other, L2C_MESSAGE_SIZE);
+
+		if (ctx->reg_int & mask_ue)
+			edac_device_handle_ue(l2c->edac_dev, 0, 0, msg);
+		else if (ctx->reg_int & mask_ce)
+			edac_device_handle_ce(l2c->edac_dev, 0, 0, msg);
+
+		l2c->ring_tail++;
+	}
+
+	return IRQ_HANDLED;
+
+err_free:
+	kfree(other);
+	kfree(msg);
+
+	return ret;
+}
+
+#define L2C_DEBUGFS_ATTR(_name, _reg)	DEBUGFS_REG_ATTR(l2c, _name, _reg)
+
+L2C_DEBUGFS_ATTR(tad_int, L2C_TAD_INT_W1S);
+
+struct debugfs_entry *l2c_tad_dfs_ents[] = {
+	&debugfs_tad_int,
+};
+
+L2C_DEBUGFS_ATTR(cbc_int, L2C_CBC_INT_W1S);
+
+struct debugfs_entry *l2c_cbc_dfs_ents[] = {
+	&debugfs_cbc_int,
+};
+
+L2C_DEBUGFS_ATTR(mci_int, L2C_MCI_INT_W1S);
+
+struct debugfs_entry *l2c_mci_dfs_ents[] = {
+	&debugfs_mci_int,
+};
+
+static const struct pci_device_id thunderx_l2c_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_L2C_TAD), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_L2C_CBC), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_L2C_MCI), },
+	{ 0, },
+};
+
+static int thunderx_l2c_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	struct thunderx_l2c *l2c;
+	struct edac_device_ctl_info *edac_dev;
+	struct debugfs_entry **l2c_devattr;
+	size_t dfs_entries;
+	irqreturn_t (*thunderx_l2c_isr)(int, void *) = NULL;
+	char name[32];
+	const char *fmt;
+	u64 reg_en_offs, reg_en_mask;
+	int idx;
+	int ret;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot enable PCI device: %d\n", ret);
+		return ret;
+	}
+
+	ret = pcim_iomap_regions(pdev, BIT(0), "thunderx_l2c");
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+		return ret;
+	}
+
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_THUNDER_L2C_TAD:
+		thunderx_l2c_isr = thunderx_l2c_tad_isr;
+		l2c_devattr = l2c_tad_dfs_ents;
+		dfs_entries = ARRAY_SIZE(l2c_tad_dfs_ents);
+		fmt = "L2C-TAD%d";
+		reg_en_offs = L2C_TAD_INT_ENA_W1S;
+		reg_en_mask = L2C_TAD_INT_ENA_ALL;
+		break;
+	case PCI_DEVICE_ID_THUNDER_L2C_CBC:
+		thunderx_l2c_isr = thunderx_l2c_cbc_isr;
+		l2c_devattr = l2c_cbc_dfs_ents;
+		dfs_entries = ARRAY_SIZE(l2c_cbc_dfs_ents);
+		fmt = "L2C-CBC%d";
+		reg_en_offs = L2C_CBC_INT_ENA_W1S;
+		reg_en_mask = L2C_CBC_INT_ENA_ALL;
+		break;
+	case PCI_DEVICE_ID_THUNDER_L2C_MCI:
+		thunderx_l2c_isr = thunderx_l2c_mci_isr;
+		l2c_devattr = l2c_mci_dfs_ents;
+		dfs_entries = ARRAY_SIZE(l2c_mci_dfs_ents);
+		fmt = "L2C-MCI%d";
+		reg_en_offs = L2C_MCI_INT_ENA_W1S;
+		reg_en_mask = L2C_MCI_INT_ENA_ALL;
+		break;
+	default:
+		//Should never ever get here
+		dev_err(&pdev->dev, "Unsupported PCI device: %04x\n",
+			pdev->device);
+		return -EINVAL;
+	}
+
+	idx = edac_device_alloc_index();
+	snprintf(name, sizeof(name), fmt, idx);
+
+	edac_dev = edac_device_alloc_ctl_info(sizeof(struct thunderx_l2c),
+					      name, 1, "L2C", 1, 0,
+					      NULL, 0, idx);
+	if (!edac_dev) {
+		dev_err(&pdev->dev, "Cannot allocate EDAC device\n");
+		return -ENOMEM;
+	}
+
+	l2c = edac_dev->pvt_info;
+	l2c->edac_dev = edac_dev;
+
+	l2c->regs = pcim_iomap_table(pdev)[0];
+	if (!l2c->regs) {
+		dev_err(&pdev->dev, "Cannot map PCI resources\n");
+		ret = -ENODEV;
+		goto err_free;
+	}
+
+	l2c->pdev = pdev;
+
+	l2c->ring_head = 0;
+	l2c->ring_tail = 0;
+
+	l2c->msix_ent.entry = 0;
+	l2c->msix_ent.vector = 0;
+
+	ret = pci_enable_msix_exact(pdev, &l2c->msix_ent, 1);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot enable interrupt: %d\n", ret);
+		goto err_free;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, l2c->msix_ent.vector,
+					thunderx_l2c_isr,
+					thunderx_l2c_threaded_isr,
+					0, "[EDAC] ThunderX L2C",
+					&l2c->msix_ent);
+	if (ret)
+		goto err_free;
+
+	edac_dev->dev = &pdev->dev;
+	edac_dev->dev_name = dev_name(&pdev->dev);
+	edac_dev->mod_name = "thunderx-l2c";
+	edac_dev->ctl_name = "thunderx-l2c";
+
+	ret = edac_device_add_device(edac_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot add EDAC device: %d\n", ret);
+		goto err_free;
+	}
+
+	if (IS_ENABLED(CONFIG_EDAC_DEBUG)) {
+		l2c->debugfs = edac_debugfs_create_dir(pdev->dev.kobj.name);
+
+		thunderx_create_debugfs_nodes(l2c->debugfs, l2c_devattr,
+					      l2c, dfs_entries);
+
+		if (ret != dfs_entries) {
+			dev_warn(&pdev->dev, "Error creating debugfs entries: %d%s\n",
+				 ret, ret >= 0 ? " created" : "");
+		}
+	}
+
+	pci_set_drvdata(pdev, edac_dev);
+
+	writeq(reg_en_mask, l2c->regs + reg_en_offs);
+
+	return 0;
+
+err_free:
+	edac_device_free_ctl_info(edac_dev);
+
+	return ret;
+}
+
+static void thunderx_l2c_remove(struct pci_dev *pdev)
+{
+	struct edac_device_ctl_info *edac_dev = pci_get_drvdata(pdev);
+	struct thunderx_l2c *l2c = edac_dev->pvt_info;
+
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_THUNDER_L2C_TAD:
+		writeq(L2C_TAD_INT_ENA_ALL, l2c->regs + L2C_TAD_INT_ENA_W1C);
+		break;
+	case PCI_DEVICE_ID_THUNDER_L2C_CBC:
+		writeq(L2C_CBC_INT_ENA_ALL, l2c->regs + L2C_CBC_INT_ENA_W1C);
+		break;
+	case PCI_DEVICE_ID_THUNDER_L2C_MCI:
+		writeq(L2C_MCI_INT_ENA_ALL, l2c->regs + L2C_MCI_INT_ENA_W1C);
+		break;
+	}
+
+	edac_debugfs_remove_recursive(l2c->debugfs);
+
+	edac_device_del_device(&pdev->dev);
+	edac_device_free_ctl_info(edac_dev);
+}
+
+MODULE_DEVICE_TABLE(pci, thunderx_l2c_pci_tbl);
+
+static struct pci_driver thunderx_l2c_driver = {
+	.name     = "thunderx_l2c_edac",
+	.probe    = thunderx_l2c_probe,
+	.remove   = thunderx_l2c_remove,
+	.id_table = thunderx_l2c_pci_tbl,
+};
+
+static int __init thunderx_edac_init(void)
+{
+	int rc = 0;
+
+	rc = pci_register_driver(&thunderx_lmc_driver);
+	if (rc)
+		return rc;
+
+	rc = pci_register_driver(&thunderx_ocx_driver);
+	if (rc)
+		goto err_lmc;
+
+	rc = pci_register_driver(&thunderx_l2c_driver);
+	if (rc)
+		goto err_ocx;
+
+	return rc;
+err_ocx:
+	pci_unregister_driver(&thunderx_ocx_driver);
+err_lmc:
+	pci_unregister_driver(&thunderx_lmc_driver);
+
+	return rc;
+}
+
+static void __exit thunderx_edac_exit(void)
+{
+	pci_unregister_driver(&thunderx_l2c_driver);
+	pci_unregister_driver(&thunderx_ocx_driver);
+	pci_unregister_driver(&thunderx_lmc_driver);
+
+}
+
+module_init(thunderx_edac_init);
+module_exit(thunderx_edac_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Cavium, Inc.");
+MODULE_DESCRIPTION("EDAC Driver for Cavium ThunderX");
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
index 6c270d9d304a..669246056812 100644
--- a/drivers/edac/xgene_edac.c
+++ b/drivers/edac/xgene_edac.c
@@ -1596,7 +1596,7 @@ static void xgene_edac_pa_report(struct edac_device_ctl_info *edac_dev)
 	reg = readl(ctx->dev_csr + IOBPATRANSERRINTSTS);
 	if (!reg)
 		goto chk_iob_axi0;
-	dev_err(edac_dev->dev, "IOB procesing agent (PA) transaction error\n");
+	dev_err(edac_dev->dev, "IOB processing agent (PA) transaction error\n");
 	if (reg & IOBPA_RDATA_CORRUPT_MASK)
 		dev_err(edac_dev->dev, "IOB PA read data RAM error\n");
 	if (reg & IOBPA_M_RDATA_CORRUPT_MASK)
diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig
index 96bbae579c0b..fc09c76248b4 100644
--- a/drivers/extcon/Kconfig
+++ b/drivers/extcon/Kconfig
@@ -44,7 +44,7 @@ config EXTCON_GPIO
 
 config EXTCON_INTEL_INT3496
 	tristate "Intel INT3496 ACPI device extcon driver"
-	depends on GPIOLIB && ACPI
+	depends on GPIOLIB && ACPI && (X86 || COMPILE_TEST)
 	help
 	  Say Y here to enable extcon support for USB OTG ports controlled by
 	  an Intel INT3496 ACPI device.
diff --git a/drivers/extcon/devres.c b/drivers/extcon/devres.c
index b40eb1805927..186fd735eb28 100644
--- a/drivers/extcon/devres.c
+++ b/drivers/extcon/devres.c
@@ -50,6 +50,13 @@ static void devm_extcon_dev_notifier_unreg(struct device *dev, void *res)
 	extcon_unregister_notifier(this->edev, this->id, this->nb);
 }
 
+static void devm_extcon_dev_notifier_all_unreg(struct device *dev, void *res)
+{
+	struct extcon_dev_notifier_devres *this = res;
+
+	extcon_unregister_notifier_all(this->edev, this->nb);
+}
+
 /**
  * devm_extcon_dev_allocate - Allocate managed extcon device
  * @dev:		device owning the extcon device being created
@@ -214,3 +221,57 @@ void devm_extcon_unregister_notifier(struct device *dev,
 			       devm_extcon_dev_match, edev));
 }
 EXPORT_SYMBOL(devm_extcon_unregister_notifier);
+
+/**
+ * devm_extcon_register_notifier_all()
+ *		- Resource-managed extcon_register_notifier_all()
+ * @dev:	device to allocate extcon device
+ * @edev:	the extcon device that has the external connecotr.
+ * @nb:		a notifier block to be registered.
+ *
+ * This function manages automatically the notifier of extcon device using
+ * device resource management and simplify the control of unregistering
+ * the notifier of extcon device. To get more information, refer that function.
+ *
+ * Returns 0 if success or negaive error number if failure.
+ */
+int devm_extcon_register_notifier_all(struct device *dev, struct extcon_dev *edev,
+				struct notifier_block *nb)
+{
+	struct extcon_dev_notifier_devres *ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_extcon_dev_notifier_all_unreg, sizeof(*ptr),
+				GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = extcon_register_notifier_all(edev, nb);
+	if (ret) {
+		devres_free(ptr);
+		return ret;
+	}
+
+	ptr->edev = edev;
+	ptr->nb = nb;
+	devres_add(dev, ptr);
+
+	return 0;
+}
+EXPORT_SYMBOL(devm_extcon_register_notifier_all);
+
+/**
+ * devm_extcon_unregister_notifier_all()
+ *		- Resource-managed extcon_unregister_notifier_all()
+ * @dev:	device to allocate extcon device
+ * @edev:	the extcon device that has the external connecotr.
+ * @nb:		a notifier block to be registered.
+ */
+void devm_extcon_unregister_notifier_all(struct device *dev,
+				struct extcon_dev *edev,
+				struct notifier_block *nb)
+{
+	WARN_ON(devres_release(dev, devm_extcon_dev_notifier_all_unreg,
+			       devm_extcon_dev_match, edev));
+}
+EXPORT_SYMBOL(devm_extcon_unregister_notifier_all);
diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c
index a3131b036de6..9d17984bbbd4 100644
--- a/drivers/extcon/extcon-intel-int3496.c
+++ b/drivers/extcon/extcon-intel-int3496.c
@@ -45,6 +45,17 @@ static const unsigned int int3496_cable[] = {
 	EXTCON_NONE,
 };
 
+static const struct acpi_gpio_params id_gpios = { INT3496_GPIO_USB_ID, 0, false };
+static const struct acpi_gpio_params vbus_gpios = { INT3496_GPIO_VBUS_EN, 0, false };
+static const struct acpi_gpio_params mux_gpios = { INT3496_GPIO_USB_MUX, 0, false };
+
+static const struct acpi_gpio_mapping acpi_int3496_default_gpios[] = {
+	{ "id-gpios", &id_gpios, 1 },
+	{ "vbus-gpios", &vbus_gpios, 1 },
+	{ "mux-gpios", &mux_gpios, 1 },
+	{ },
+};
+
 static void int3496_do_usb_id(struct work_struct *work)
 {
 	struct int3496_data *data =
@@ -83,6 +94,13 @@ static int int3496_probe(struct platform_device *pdev)
 	struct int3496_data *data;
 	int ret;
 
+	ret = acpi_dev_add_driver_gpios(ACPI_COMPANION(dev),
+					acpi_int3496_default_gpios);
+	if (ret) {
+		dev_err(dev, "can't add GPIO ACPI mapping\n");
+		return ret;
+	}
+
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -90,30 +108,27 @@ static int int3496_probe(struct platform_device *pdev)
 	data->dev = dev;
 	INIT_DELAYED_WORK(&data->work, int3496_do_usb_id);
 
-	data->gpio_usb_id = devm_gpiod_get_index(dev, "id",
-						INT3496_GPIO_USB_ID,
-						GPIOD_IN);
+	data->gpio_usb_id = devm_gpiod_get(dev, "id", GPIOD_IN);
 	if (IS_ERR(data->gpio_usb_id)) {
 		ret = PTR_ERR(data->gpio_usb_id);
 		dev_err(dev, "can't request USB ID GPIO: %d\n", ret);
 		return ret;
+	} else if (gpiod_get_direction(data->gpio_usb_id) != GPIOF_DIR_IN) {
+		dev_warn(dev, FW_BUG "USB ID GPIO not in input mode, fixing\n");
+		gpiod_direction_input(data->gpio_usb_id);
 	}
 
 	data->usb_id_irq = gpiod_to_irq(data->gpio_usb_id);
-	if (data->usb_id_irq <= 0) {
+	if (data->usb_id_irq < 0) {
 		dev_err(dev, "can't get USB ID IRQ: %d\n", data->usb_id_irq);
-		return -EINVAL;
+		return data->usb_id_irq;
 	}
 
-	data->gpio_vbus_en = devm_gpiod_get_index(dev, "vbus en",
-						 INT3496_GPIO_VBUS_EN,
-						 GPIOD_ASIS);
+	data->gpio_vbus_en = devm_gpiod_get(dev, "vbus", GPIOD_ASIS);
 	if (IS_ERR(data->gpio_vbus_en))
 		dev_info(dev, "can't request VBUS EN GPIO\n");
 
-	data->gpio_usb_mux = devm_gpiod_get_index(dev, "usb mux",
-						 INT3496_GPIO_USB_MUX,
-						 GPIOD_ASIS);
+	data->gpio_usb_mux = devm_gpiod_get(dev, "mux", GPIOD_ASIS);
 	if (IS_ERR(data->gpio_usb_mux))
 		dev_info(dev, "can't request USB MUX GPIO\n");
 
@@ -154,6 +169,8 @@ static int int3496_remove(struct platform_device *pdev)
 	devm_free_irq(&pdev->dev, data->usb_id_irq, data);
 	cancel_delayed_work_sync(&data->work);
 
+	acpi_dev_remove_driver_gpios(ACPI_COMPANION(&pdev->dev));
+
 	return 0;
 }
 
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 09ac5e70c2f3..e7750545469f 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -448,8 +448,19 @@ int extcon_sync(struct extcon_dev *edev, unsigned int id)
 	spin_lock_irqsave(&edev->lock, flags);
 
 	state = !!(edev->state & BIT(index));
+
+	/*
+	 * Call functions in a raw notifier chain for the specific one
+	 * external connector.
+	 */
 	raw_notifier_call_chain(&edev->nh[index], state, edev);
 
+	/*
+	 * Call functions in a raw notifier chain for the all supported
+	 * external connectors.
+	 */
+	raw_notifier_call_chain(&edev->nh_all, state, edev);
+
 	/* This could be in interrupt handler */
 	prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
 	if (!prop_buf) {
@@ -954,6 +965,59 @@ int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id,
 }
 EXPORT_SYMBOL_GPL(extcon_unregister_notifier);
 
+/**
+ * extcon_register_notifier_all() - Register a notifier block for all connectors
+ * @edev:	the extcon device that has the external connecotr.
+ * @nb:		a notifier block to be registered.
+ *
+ * This fucntion registers a notifier block in order to receive the state
+ * change of all supported external connectors from extcon device.
+ * And The second parameter given to the callback of nb (val) is
+ * the current state and third parameter is the edev pointer.
+ *
+ * Returns 0 if success or error number if fail
+ */
+int extcon_register_notifier_all(struct extcon_dev *edev,
+				struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	if (!edev || !nb)
+		return -EINVAL;
+
+	spin_lock_irqsave(&edev->lock, flags);
+	ret = raw_notifier_chain_register(&edev->nh_all, nb);
+	spin_unlock_irqrestore(&edev->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(extcon_register_notifier_all);
+
+/**
+ * extcon_unregister_notifier_all() - Unregister a notifier block from extcon.
+ * @edev:	the extcon device that has the external connecotr.
+ * @nb:		a notifier block to be registered.
+ *
+ * Returns 0 if success or error number if fail
+ */
+int extcon_unregister_notifier_all(struct extcon_dev *edev,
+				struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	if (!edev || !nb)
+		return -EINVAL;
+
+	spin_lock_irqsave(&edev->lock, flags);
+	ret = raw_notifier_chain_unregister(&edev->nh_all, nb);
+	spin_unlock_irqrestore(&edev->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(extcon_unregister_notifier_all);
+
 static struct attribute *extcon_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_name.attr,
@@ -1212,6 +1276,8 @@ int extcon_dev_register(struct extcon_dev *edev)
 	for (index = 0; index < edev->max_supported; index++)
 		RAW_INIT_NOTIFIER_HEAD(&edev->nh[index]);
 
+	RAW_INIT_NOTIFIER_HEAD(&edev->nh_all);
+
 	dev_set_drvdata(&edev->dev, edev);
 	edev->state = 0;
 
diff --git a/drivers/extcon/extcon.h b/drivers/extcon/extcon.h
index 993ddccafe11..dddddcfa0587 100644
--- a/drivers/extcon/extcon.h
+++ b/drivers/extcon/extcon.h
@@ -21,6 +21,8 @@
  * @dev:		Device of this extcon.
  * @state:		Attach/detach state of this extcon. Do not provide at
  *			register-time.
+ * @nh_all:		Notifier for the state change events for all supported
+ *			external connectors from this extcon.
  * @nh:			Notifier for the state change events from this extcon
  * @entry:		To support list of extcon devices so that users can
  *			search for extcon devices based on the extcon name.
@@ -43,6 +45,7 @@ struct extcon_dev {
 
 	/* Internal data. Please do not set. */
 	struct device dev;
+	struct raw_notifier_head nh_all;
 	struct raw_notifier_head *nh;
 	struct list_head entry;
 	int max_supported;
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index ad67342313ed..0329d319d89a 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -9,6 +9,7 @@
 #
 KASAN_SANITIZE_runtime-wrappers.o	:= n
 
+obj-$(CONFIG_ACPI_BGRT) 		+= efi-bgrt.o
 obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o memattr.o
 obj-$(CONFIG_EFI)			+= capsule.o memmap.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 349dc3e1e52e..974c5a31a005 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -65,6 +65,7 @@ static bool __init efi_virtmap_init(void)
 	bool systab_found;
 
 	efi_mm.pgd = pgd_alloc(&efi_mm);
+	mm_init_cpumask(&efi_mm);
 	init_new_context(NULL, &efi_mm);
 
 	systab_found = false;
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/drivers/firmware/efi/efi-bgrt.c
index 04ca8764f0c0..04ca8764f0c0 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/drivers/firmware/efi/efi-bgrt.c
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index f402ba2eed46..ed3137c1ceb0 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -28,26 +28,16 @@ static int efi_pstore_close(struct pstore_info *psi)
 	return 0;
 }
 
-struct pstore_read_data {
-	u64 *id;
-	enum pstore_type_id *type;
-	int *count;
-	struct timespec *timespec;
-	bool *compressed;
-	ssize_t *ecc_notice_size;
-	char **buf;
-};
-
 static inline u64 generic_id(unsigned long timestamp,
 			     unsigned int part, int count)
 {
 	return ((u64) timestamp * 100 + part) * 1000 + count;
 }
 
-static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
+static int efi_pstore_read_func(struct efivar_entry *entry,
+				struct pstore_record *record)
 {
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
-	struct pstore_read_data *cb_data = data;
 	char name[DUMP_NAME_LEN], data_type;
 	int i;
 	int cnt;
@@ -61,37 +51,37 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 		name[i] = entry->var.VariableName[i];
 
 	if (sscanf(name, "dump-type%u-%u-%d-%lu-%c",
-		   cb_data->type, &part, &cnt, &time, &data_type) == 5) {
-		*cb_data->id = generic_id(time, part, cnt);
-		*cb_data->count = cnt;
-		cb_data->timespec->tv_sec = time;
-		cb_data->timespec->tv_nsec = 0;
+		   &record->type, &part, &cnt, &time, &data_type) == 5) {
+		record->id = generic_id(time, part, cnt);
+		record->count = cnt;
+		record->time.tv_sec = time;
+		record->time.tv_nsec = 0;
 		if (data_type == 'C')
-			*cb_data->compressed = true;
+			record->compressed = true;
 		else
-			*cb_data->compressed = false;
-		*cb_data->ecc_notice_size = 0;
+			record->compressed = false;
+		record->ecc_notice_size = 0;
 	} else if (sscanf(name, "dump-type%u-%u-%d-%lu",
-		   cb_data->type, &part, &cnt, &time) == 4) {
-		*cb_data->id = generic_id(time, part, cnt);
-		*cb_data->count = cnt;
-		cb_data->timespec->tv_sec = time;
-		cb_data->timespec->tv_nsec = 0;
-		*cb_data->compressed = false;
-		*cb_data->ecc_notice_size = 0;
+		   &record->type, &part, &cnt, &time) == 4) {
+		record->id = generic_id(time, part, cnt);
+		record->count = cnt;
+		record->time.tv_sec = time;
+		record->time.tv_nsec = 0;
+		record->compressed = false;
+		record->ecc_notice_size = 0;
 	} else if (sscanf(name, "dump-type%u-%u-%lu",
-			  cb_data->type, &part, &time) == 3) {
+			  &record->type, &part, &time) == 3) {
 		/*
 		 * Check if an old format,
 		 * which doesn't support holding
 		 * multiple logs, remains.
 		 */
-		*cb_data->id = generic_id(time, part, 0);
-		*cb_data->count = 0;
-		cb_data->timespec->tv_sec = time;
-		cb_data->timespec->tv_nsec = 0;
-		*cb_data->compressed = false;
-		*cb_data->ecc_notice_size = 0;
+		record->id = generic_id(time, part, 0);
+		record->count = 0;
+		record->time.tv_sec = time;
+		record->time.tv_nsec = 0;
+		record->compressed = false;
+		record->ecc_notice_size = 0;
 	} else
 		return 0;
 
@@ -99,7 +89,7 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 	__efivar_entry_get(entry, &entry->var.Attributes,
 			   &entry->var.DataSize, entry->var.Data);
 	size = entry->var.DataSize;
-	memcpy(*cb_data->buf, entry->var.Data,
+	memcpy(record->buf, entry->var.Data,
 	       (size_t)min_t(unsigned long, EFIVARS_DATA_SIZE_MAX, size));
 
 	return size;
@@ -164,7 +154,7 @@ static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
 /**
  * efi_pstore_sysfs_entry_iter
  *
- * @data: function-specific data to pass to callback
+ * @record: pstore record to pass to callback
  * @pos: entry to begin iterating from
  *
  * You MUST call efivar_enter_iter_begin() before this function, and
@@ -175,7 +165,8 @@ static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
  * the next entry of the last one passed to efi_pstore_read_func().
  * To begin iterating from the beginning of the list @pos must be %NULL.
  */
-static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
+static int efi_pstore_sysfs_entry_iter(struct pstore_record *record,
+				       struct efivar_entry **pos)
 {
 	struct efivar_entry *entry, *n;
 	struct list_head *head = &efivar_sysfs_list;
@@ -186,7 +177,7 @@ static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
 		list_for_each_entry_safe(entry, n, head, list) {
 			efi_pstore_scan_sysfs_enter(entry, n, head);
 
-			size = efi_pstore_read_func(entry, data);
+			size = efi_pstore_read_func(entry, record);
 			ret = efi_pstore_scan_sysfs_exit(entry, n, head,
 							 size < 0);
 			if (ret)
@@ -201,7 +192,7 @@ static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
 	list_for_each_entry_safe_from((*pos), n, head, list) {
 		efi_pstore_scan_sysfs_enter((*pos), n, head);
 
-		size = efi_pstore_read_func((*pos), data);
+		size = efi_pstore_read_func((*pos), record);
 		ret = efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0);
 		if (ret)
 			return ret;
@@ -225,71 +216,57 @@ static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
  * size < 0: Failed to get data of entry logging via efi_pstore_write(),
  *           and pstore will stop reading entry.
  */
-static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
-			       int *count, struct timespec *timespec,
-			       char **buf, bool *compressed,
-			       ssize_t *ecc_notice_size,
-			       struct pstore_info *psi)
+static ssize_t efi_pstore_read(struct pstore_record *record)
 {
-	struct pstore_read_data data;
+	struct efivar_entry *entry = (struct efivar_entry *)record->psi->data;
 	ssize_t size;
 
-	data.id = id;
-	data.type = type;
-	data.count = count;
-	data.timespec = timespec;
-	data.compressed = compressed;
-	data.ecc_notice_size = ecc_notice_size;
-	data.buf = buf;
-
-	*data.buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
-	if (!*data.buf)
+	record->buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
+	if (!record->buf)
 		return -ENOMEM;
 
 	if (efivar_entry_iter_begin()) {
-		kfree(*data.buf);
-		return -EINTR;
+		size = -EINTR;
+		goto out;
 	}
-	size = efi_pstore_sysfs_entry_iter(&data,
-					   (struct efivar_entry **)&psi->data);
+	size = efi_pstore_sysfs_entry_iter(record, &entry);
 	efivar_entry_iter_end();
-	if (size <= 0)
-		kfree(*data.buf);
+
+out:
+	if (size <= 0) {
+		kfree(record->buf);
+		record->buf = NULL;
+	}
 	return size;
 }
 
-static int efi_pstore_write(enum pstore_type_id type,
-		enum kmsg_dump_reason reason, u64 *id,
-		unsigned int part, int count, bool compressed, size_t size,
-		struct pstore_info *psi)
+static int efi_pstore_write(struct pstore_record *record)
 {
 	char name[DUMP_NAME_LEN];
 	efi_char16_t efi_name[DUMP_NAME_LEN];
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
 	int i, ret = 0;
 
-	sprintf(name, "dump-type%u-%u-%d-%lu-%c", type, part, count,
-		get_seconds(), compressed ? 'C' : 'D');
+	snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu-%c",
+		 record->type, record->part, record->count,
+		 get_seconds(), record->compressed ? 'C' : 'D');
 
 	for (i = 0; i < DUMP_NAME_LEN; i++)
 		efi_name[i] = name[i];
 
-	efivar_entry_set_safe(efi_name, vendor, PSTORE_EFI_ATTRIBUTES,
-			      !pstore_cannot_block_path(reason),
-			      size, psi->buf);
+	ret = efivar_entry_set_safe(efi_name, vendor, PSTORE_EFI_ATTRIBUTES,
+			      !pstore_cannot_block_path(record->reason),
+			      record->size, record->psi->buf);
 
-	if (reason == KMSG_DUMP_OOPS)
+	if (record->reason == KMSG_DUMP_OOPS)
 		efivar_run_worker();
 
-	*id = part;
+	record->id = record->part;
 	return ret;
 };
 
 struct pstore_erase_data {
-	u64 id;
-	enum pstore_type_id type;
-	int count;
-	struct timespec time;
+	struct pstore_record *record;
 	efi_char16_t *name;
 };
 
@@ -315,8 +292,9 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data)
 		 * Check if an old format, which doesn't support
 		 * holding multiple logs, remains.
 		 */
-		sprintf(name_old, "dump-type%u-%u-%lu", ed->type,
-			(unsigned int)ed->id, ed->time.tv_sec);
+		snprintf(name_old, sizeof(name_old), "dump-type%u-%u-%lu",
+			ed->record->type, (unsigned int)ed->record->id,
+			ed->record->time.tv_sec);
 
 		for (i = 0; i < DUMP_NAME_LEN; i++)
 			efi_name_old[i] = name_old[i];
@@ -341,8 +319,7 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data)
 	return 1;
 }
 
-static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
-			    struct timespec time, struct pstore_info *psi)
+static int efi_pstore_erase(struct pstore_record *record)
 {
 	struct pstore_erase_data edata;
 	struct efivar_entry *entry = NULL;
@@ -351,17 +328,16 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 	int found, i;
 	unsigned int part;
 
-	do_div(id, 1000);
-	part = do_div(id, 100);
-	sprintf(name, "dump-type%u-%u-%d-%lu", type, part, count, time.tv_sec);
+	do_div(record->id, 1000);
+	part = do_div(record->id, 100);
+	snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu",
+		 record->type, record->part, record->count,
+		 record->time.tv_sec);
 
 	for (i = 0; i < DUMP_NAME_LEN; i++)
 		efi_name[i] = name[i];
 
-	edata.id = part;
-	edata.type = type;
-	edata.count = count;
-	edata.time = time;
+	edata.record = record;
 	edata.name = efi_name;
 
 	if (efivar_entry_iter_begin())
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e7d404059b73..b372aad3b449 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -389,7 +389,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 			return 0;
 		}
 	}
-	pr_err_once("requested map not found.\n");
 	return -ENOENT;
 }
 
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 08b026864d4e..8554d7aec31c 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -254,7 +254,7 @@ void __init efi_esrt_init(void)
 
 	rc = efi_mem_desc_lookup(efi.esrt, &md);
 	if (rc < 0) {
-		pr_err("ESRT header is not in the memory map.\n");
+		pr_warn("ESRT header is not in the memory map.\n");
 		return;
 	}
 
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index d4056c6be1ec..8181ac179d14 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -18,7 +18,27 @@
 
 #include "efistub.h"
 
-bool __nokaslr;
+/*
+ * This is the base address at which to start allocating virtual memory ranges
+ * for UEFI Runtime Services. This is in the low TTBR0 range so that we can use
+ * any allocation we choose, and eliminate the risk of a conflict after kexec.
+ * The value chosen is the largest non-zero power of 2 suitable for this purpose
+ * both on 32-bit and 64-bit ARM CPUs, to maximize the likelihood that it can
+ * be mapped efficiently.
+ * Since 32-bit ARM could potentially execute with a 1G/3G user/kernel split,
+ * map everything below 1 GB. (512 MB is a reasonable upper bound for the
+ * entire footprint of the UEFI runtime services memory regions)
+ */
+#define EFI_RT_VIRTUAL_BASE	SZ_512M
+#define EFI_RT_VIRTUAL_SIZE	SZ_512M
+
+#ifdef CONFIG_ARM64
+# define EFI_RT_VIRTUAL_LIMIT	TASK_SIZE_64
+#else
+# define EFI_RT_VIRTUAL_LIMIT	TASK_SIZE
+#endif
+
+static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
 			     void *__image, void **__fh)
@@ -118,8 +138,6 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		goto fail;
 
-	pr_efi(sys_table, "Booting Linux Kernel...\n");
-
 	status = check_platform_features(sys_table);
 	if (status != EFI_SUCCESS)
 		goto fail;
@@ -153,17 +171,15 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 		goto fail;
 	}
 
-	/* check whether 'nokaslr' was passed on the command line */
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
-		static const u8 default_cmdline[] = CONFIG_CMDLINE;
-		const u8 *str, *cmdline = cmdline_ptr;
+	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
+	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
+	    cmdline_size == 0)
+		efi_parse_options(CONFIG_CMDLINE);
 
-		if (IS_ENABLED(CONFIG_CMDLINE_FORCE))
-			cmdline = default_cmdline;
-		str = strstr(cmdline, "nokaslr");
-		if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
-			__nokaslr = true;
-	}
+	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline_size > 0)
+		efi_parse_options(cmdline_ptr);
+
+	pr_efi(sys_table, "Booting Linux Kernel...\n");
 
 	si = setup_graphics(sys_table);
 
@@ -176,10 +192,6 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 		goto fail_free_cmdline;
 	}
 
-	status = efi_parse_options(cmdline_ptr);
-	if (status != EFI_SUCCESS)
-		pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n");
-
 	secure_boot = efi_get_secureboot(sys_table);
 
 	/*
@@ -213,8 +225,9 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	if (!fdt_addr)
 		pr_efi(sys_table, "Generating empty DTB\n");
 
-	status = handle_cmdline_files(sys_table, image, cmdline_ptr,
-				      "initrd=", dram_base + SZ_512M,
+	status = handle_cmdline_files(sys_table, image, cmdline_ptr, "initrd=",
+				      efi_get_max_initrd_addr(dram_base,
+							      *image_addr),
 				      (unsigned long *)&initrd_addr,
 				      (unsigned long *)&initrd_size);
 	if (status != EFI_SUCCESS)
@@ -222,9 +235,29 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 
 	efi_random_get_seed(sys_table);
 
+	if (!nokaslr()) {
+		/*
+		 * Randomize the base of the UEFI runtime services region.
+		 * Preserve the 2 MB alignment of the region by taking a
+		 * shift of 21 bit positions into account when scaling
+		 * the headroom value using a 32-bit random value.
+		 */
+		static const u64 headroom = EFI_RT_VIRTUAL_LIMIT -
+					    EFI_RT_VIRTUAL_BASE -
+					    EFI_RT_VIRTUAL_SIZE;
+		u32 rnd;
+
+		status = efi_get_random_bytes(sys_table, sizeof(rnd),
+					      (u8 *)&rnd);
+		if (status == EFI_SUCCESS) {
+			virtmap_base = EFI_RT_VIRTUAL_BASE +
+				       (((headroom >> 21) * rnd) >> (32 - 21));
+		}
+	}
+
 	new_fdt_addr = fdt_addr;
 	status = allocate_new_fdt_and_exit_boot(sys_table, handle,
-				&new_fdt_addr, dram_base + MAX_FDT_OFFSET,
+				&new_fdt_addr, efi_get_max_fdt_addr(dram_base),
 				initrd_addr, initrd_size, cmdline_ptr,
 				fdt_addr, fdt_size);
 
@@ -251,18 +284,6 @@ fail:
 	return EFI_ERROR;
 }
 
-/*
- * This is the base address at which to start allocating virtual memory ranges
- * for UEFI Runtime Services. This is in the low TTBR0 range so that we can use
- * any allocation we choose, and eliminate the risk of a conflict after kexec.
- * The value chosen is the largest non-zero power of 2 suitable for this purpose
- * both on 32-bit and 64-bit ARM CPUs, to maximize the likelihood that it can
- * be mapped efficiently.
- * Since 32-bit ARM could potentially execute with a 1G/3G user/kernel split,
- * map everything below 1 GB.
- */
-#define EFI_RT_VIRTUAL_BASE	SZ_512M
-
 static int cmp_mem_desc(const void *l, const void *r)
 {
 	const efi_memory_desc_t *left = l, *right = r;
@@ -312,7 +333,7 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
 		     unsigned long desc_size, efi_memory_desc_t *runtime_map,
 		     int *count)
 {
-	u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
+	u64 efi_virt_base = virtmap_base;
 	efi_memory_desc_t *in, *prev = NULL, *out = runtime_map;
 	int l;
 
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index e1f0b28e1dcb..becbda445913 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -9,6 +9,8 @@
 #include <linux/efi.h>
 #include <asm/efi.h>
 
+#include "efistub.h"
+
 efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
 {
 	int block;
@@ -63,6 +65,132 @@ void free_screen_info(efi_system_table_t *sys_table_arg, struct screen_info *si)
 	efi_call_early(free_pool, si);
 }
 
+static efi_status_t reserve_kernel_base(efi_system_table_t *sys_table_arg,
+					unsigned long dram_base,
+					unsigned long *reserve_addr,
+					unsigned long *reserve_size)
+{
+	efi_physical_addr_t alloc_addr;
+	efi_memory_desc_t *memory_map;
+	unsigned long nr_pages, map_size, desc_size, buff_size;
+	efi_status_t status;
+	unsigned long l;
+
+	struct efi_boot_memmap map = {
+		.map		= &memory_map,
+		.map_size	= &map_size,
+		.desc_size	= &desc_size,
+		.desc_ver	= NULL,
+		.key_ptr	= NULL,
+		.buff_size	= &buff_size,
+	};
+
+	/*
+	 * Reserve memory for the uncompressed kernel image. This is
+	 * all that prevents any future allocations from conflicting
+	 * with the kernel. Since we can't tell from the compressed
+	 * image how much DRAM the kernel actually uses (due to BSS
+	 * size uncertainty) we allocate the maximum possible size.
+	 * Do this very early, as prints can cause memory allocations
+	 * that may conflict with this.
+	 */
+	alloc_addr = dram_base + MAX_UNCOMP_KERNEL_SIZE;
+	nr_pages = MAX_UNCOMP_KERNEL_SIZE / EFI_PAGE_SIZE;
+	status = efi_call_early(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS,
+				EFI_BOOT_SERVICES_DATA, nr_pages, &alloc_addr);
+	if (status == EFI_SUCCESS) {
+		if (alloc_addr == dram_base) {
+			*reserve_addr = alloc_addr;
+			*reserve_size = MAX_UNCOMP_KERNEL_SIZE;
+			return EFI_SUCCESS;
+		}
+		/*
+		 * If we end up here, the allocation succeeded but starts below
+		 * dram_base. This can only occur if the real base of DRAM is
+		 * not a multiple of 128 MB, in which case dram_base will have
+		 * been rounded up. Since this implies that a part of the region
+		 * was already occupied, we need to fall through to the code
+		 * below to ensure that the existing allocations don't conflict.
+		 * For this reason, we use EFI_BOOT_SERVICES_DATA above and not
+		 * EFI_LOADER_DATA, which we wouldn't able to distinguish from
+		 * allocations that we want to disallow.
+		 */
+	}
+
+	/*
+	 * If the allocation above failed, we may still be able to proceed:
+	 * if the only allocations in the region are of types that will be
+	 * released to the OS after ExitBootServices(), the decompressor can
+	 * safely overwrite them.
+	 */
+	status = efi_get_memory_map(sys_table_arg, &map);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table_arg,
+			   "reserve_kernel_base(): Unable to retrieve memory map.\n");
+		return status;
+	}
+
+	for (l = 0; l < map_size; l += desc_size) {
+		efi_memory_desc_t *desc;
+		u64 start, end;
+
+		desc = (void *)memory_map + l;
+		start = desc->phys_addr;
+		end = start + desc->num_pages * EFI_PAGE_SIZE;
+
+		/* Skip if entry does not intersect with region */
+		if (start >= dram_base + MAX_UNCOMP_KERNEL_SIZE ||
+		    end <= dram_base)
+			continue;
+
+		switch (desc->type) {
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+			/* Ignore types that are released to the OS anyway */
+			continue;
+
+		case EFI_CONVENTIONAL_MEMORY:
+			/*
+			 * Reserve the intersection between this entry and the
+			 * region.
+			 */
+			start = max(start, (u64)dram_base);
+			end = min(end, (u64)dram_base + MAX_UNCOMP_KERNEL_SIZE);
+
+			status = efi_call_early(allocate_pages,
+						EFI_ALLOCATE_ADDRESS,
+						EFI_LOADER_DATA,
+						(end - start) / EFI_PAGE_SIZE,
+						&start);
+			if (status != EFI_SUCCESS) {
+				pr_efi_err(sys_table_arg,
+					"reserve_kernel_base(): alloc failed.\n");
+				goto out;
+			}
+			break;
+
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+			/*
+			 * These regions may be released and reallocated for
+			 * another purpose (including EFI_RUNTIME_SERVICE_DATA)
+			 * at any time during the execution of the OS loader,
+			 * so we cannot consider them as safe.
+			 */
+		default:
+			/*
+			 * Treat any other allocation in the region as unsafe */
+			status = EFI_OUT_OF_RESOURCES;
+			goto out;
+		}
+	}
+
+	status = EFI_SUCCESS;
+out:
+	efi_call_early(free_pool, memory_map);
+	return status;
+}
+
 efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 				 unsigned long *image_addr,
 				 unsigned long *image_size,
@@ -71,10 +199,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 				 unsigned long dram_base,
 				 efi_loaded_image_t *image)
 {
-	unsigned long nr_pages;
 	efi_status_t status;
-	/* Use alloc_addr to tranlsate between types */
-	efi_physical_addr_t alloc_addr;
 
 	/*
 	 * Verify that the DRAM base address is compatible with the ARM
@@ -85,27 +210,12 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	 */
 	dram_base = round_up(dram_base, SZ_128M);
 
-	/*
-	 * Reserve memory for the uncompressed kernel image. This is
-	 * all that prevents any future allocations from conflicting
-	 * with the kernel. Since we can't tell from the compressed
-	 * image how much DRAM the kernel actually uses (due to BSS
-	 * size uncertainty) we allocate the maximum possible size.
-	 * Do this very early, as prints can cause memory allocations
-	 * that may conflict with this.
-	 */
-	alloc_addr = dram_base;
-	*reserve_size = MAX_UNCOMP_KERNEL_SIZE;
-	nr_pages = round_up(*reserve_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-	status = sys_table->boottime->allocate_pages(EFI_ALLOCATE_ADDRESS,
-						     EFI_LOADER_DATA,
-						     nr_pages, &alloc_addr);
+	status = reserve_kernel_base(sys_table, dram_base, reserve_addr,
+				     reserve_size);
 	if (status != EFI_SUCCESS) {
-		*reserve_size = 0;
 		pr_efi_err(sys_table, "Unable to allocate memory for uncompressed kernel.\n");
 		return status;
 	}
-	*reserve_addr = alloc_addr;
 
 	/*
 	 * Relocate the zImage, so that it appears in the lowest 128 MB
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index eae693eb3e91..b4c2589d7c91 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -16,8 +16,6 @@
 
 #include "efistub.h"
 
-extern bool __nokaslr;
-
 efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
 {
 	u64 tg;
@@ -52,7 +50,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
 	u64 phys_seed = 0;
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
-		if (!__nokaslr) {
+		if (!nokaslr()) {
 			status = efi_get_random_bytes(sys_table_arg,
 						      sizeof(phys_seed),
 						      (u8 *)&phys_seed);
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 919822b7773d..b0184360efc6 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -32,6 +32,18 @@
 
 static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
 
+static int __section(.data) __nokaslr;
+static int __section(.data) __quiet;
+
+int __pure nokaslr(void)
+{
+	return __nokaslr;
+}
+int __pure is_quiet(void)
+{
+	return __quiet;
+}
+
 #define EFI_MMAP_NR_SLACK_SLOTS	8
 
 struct file_info {
@@ -409,17 +421,17 @@ static efi_status_t efi_file_close(void *handle)
  * environments, first in the early boot environment of the EFI boot
  * stub, and subsequently during the kernel boot.
  */
-efi_status_t efi_parse_options(char *cmdline)
+efi_status_t efi_parse_options(char const *cmdline)
 {
 	char *str;
 
-	/*
-	 * Currently, the only efi= option we look for is 'nochunk', which
-	 * is intended to work around known issues on certain x86 UEFI
-	 * versions. So ignore for now on other architectures.
-	 */
-	if (!IS_ENABLED(CONFIG_X86))
-		return EFI_SUCCESS;
+	str = strstr(cmdline, "nokaslr");
+	if (str == cmdline || (str && str > cmdline && *(str - 1) == ' '))
+		__nokaslr = 1;
+
+	str = strstr(cmdline, "quiet");
+	if (str == cmdline || (str && str > cmdline && *(str - 1) == ' '))
+		__quiet = 1;
 
 	/*
 	 * If no EFI parameters were specified on the cmdline we've got
@@ -436,14 +448,14 @@ efi_status_t efi_parse_options(char *cmdline)
 	 * Remember, because efi= is also used by the kernel we need to
 	 * skip over arguments we don't understand.
 	 */
-	while (*str) {
+	while (*str && *str != ' ') {
 		if (!strncmp(str, "nochunk", 7)) {
 			str += strlen("nochunk");
 			__chunk_size = -1UL;
 		}
 
 		/* Group words together, delimited by "," */
-		while (*str && *str != ',')
+		while (*str && *str != ' ' && *str != ',')
 			str++;
 
 		if (*str == ',')
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 71c4d0e3c4ed..83f268c05007 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -24,6 +24,15 @@
 #define EFI_ALLOC_ALIGN		EFI_PAGE_SIZE
 #endif
 
+extern int __pure nokaslr(void);
+extern int __pure is_quiet(void);
+
+#define pr_efi(sys_table, msg)		do {				\
+	if (!is_quiet()) efi_printk(sys_table, "EFI stub: "msg);	\
+} while (0)
+
+#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
+
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 260c4b4b492e..41f457be64e8 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -206,6 +206,10 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 	return update_fdt_memmap(p->new_fdt_addr, map);
 }
 
+#ifndef MAX_FDT_SIZE
+#define MAX_FDT_SIZE	SZ_2M
+#endif
+
 /*
  * Allocate memory for a new FDT, then add EFI, commandline, and
  * initrd related fields to the FDT.  This routine increases the
@@ -233,7 +237,6 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	u32 desc_ver;
 	unsigned long mmap_key;
 	efi_memory_desc_t *memory_map, *runtime_map;
-	unsigned long new_fdt_size;
 	efi_status_t status;
 	int runtime_entry_count = 0;
 	struct efi_boot_memmap map;
@@ -262,41 +265,29 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	       "Exiting boot services and installing virtual address map...\n");
 
 	map.map = &memory_map;
+	status = efi_high_alloc(sys_table, MAX_FDT_SIZE, EFI_FDT_ALIGN,
+				new_fdt_addr, max_addr);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table,
+			   "Unable to allocate memory for new device tree.\n");
+		goto fail;
+	}
+
 	/*
-	 * Estimate size of new FDT, and allocate memory for it. We
-	 * will allocate a bigger buffer if this ends up being too
-	 * small, so a rough guess is OK here.
+	 * Now that we have done our final memory allocation (and free)
+	 * we can get the memory map key needed for exit_boot_services().
 	 */
-	new_fdt_size = fdt_size + EFI_PAGE_SIZE;
-	while (1) {
-		status = efi_high_alloc(sys_table, new_fdt_size, EFI_FDT_ALIGN,
-					new_fdt_addr, max_addr);
-		if (status != EFI_SUCCESS) {
-			pr_efi_err(sys_table, "Unable to allocate memory for new device tree.\n");
-			goto fail;
-		}
-
-		status = update_fdt(sys_table,
-				    (void *)fdt_addr, fdt_size,
-				    (void *)*new_fdt_addr, new_fdt_size,
-				    cmdline_ptr, initrd_addr, initrd_size);
+	status = efi_get_memory_map(sys_table, &map);
+	if (status != EFI_SUCCESS)
+		goto fail_free_new_fdt;
 
-		/* Succeeding the first time is the expected case. */
-		if (status == EFI_SUCCESS)
-			break;
+	status = update_fdt(sys_table, (void *)fdt_addr, fdt_size,
+			    (void *)*new_fdt_addr, MAX_FDT_SIZE, cmdline_ptr,
+			    initrd_addr, initrd_size);
 
-		if (status == EFI_BUFFER_TOO_SMALL) {
-			/*
-			 * We need to allocate more space for the new
-			 * device tree, so free existing buffer that is
-			 * too small.
-			 */
-			efi_free(sys_table, new_fdt_size, *new_fdt_addr);
-			new_fdt_size += EFI_PAGE_SIZE;
-		} else {
-			pr_efi_err(sys_table, "Unable to construct new device tree.\n");
-			goto fail_free_new_fdt;
-		}
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table, "Unable to construct new device tree.\n");
+		goto fail_free_new_fdt;
 	}
 
 	priv.runtime_map = runtime_map;
@@ -340,7 +331,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	pr_efi_err(sys_table, "Exit boot services failed.\n");
 
 fail_free_new_fdt:
-	efi_free(sys_table, new_fdt_size, *new_fdt_addr);
+	efi_free(sys_table, MAX_FDT_SIZE, *new_fdt_addr);
 
 fail:
 	sys_table->boottime->free_pool(runtime_map);
diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c
index 932742e4cf23..24c461dea7af 100644
--- a/drivers/firmware/efi/libstub/gop.c
+++ b/drivers/firmware/efi/libstub/gop.c
@@ -149,7 +149,8 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
 
 		status = __gop_query32(sys_table_arg, gop32, &info, &size,
 				       &current_fb_base);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+		if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+		    info->pixel_format != PIXEL_BLT_ONLY) {
 			/*
 			 * Systems that use the UEFI Console Splitter may
 			 * provide multiple GOP devices, not all of which are
@@ -266,7 +267,8 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si,
 
 		status = __gop_query64(sys_table_arg, gop64, &info, &size,
 				       &current_fb_base);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+		if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+		    info->pixel_format != PIXEL_BLT_ONLY) {
 			/*
 			 * Systems that use the UEFI Console Splitter may
 			 * provide multiple GOP devices, not all of which are
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 6def402bf569..8c34d50a4d80 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -12,6 +12,8 @@
 #include <linux/efi.h>
 #include <asm/efi.h>
 
+#include "efistub.h"
+
 /* BIOS variables */
 static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 static const efi_char16_t const efi_SecureBoot_name[] = {
@@ -45,6 +47,8 @@ enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
 	size = sizeof(secboot);
 	status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
 			     NULL, &size, &secboot);
+	if (status == EFI_NOT_FOUND)
+		return efi_secureboot_mode_disabled;
 	if (status != EFI_SUCCESS)
 		goto out_efi_err;
 
@@ -78,7 +82,5 @@ secure_boot_enabled:
 
 out_efi_err:
 	pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n");
-	if (status == EFI_NOT_FOUND)
-		return efi_secureboot_mode_disabled;
 	return efi_secureboot_mode_unknown;
 }
diff --git a/drivers/gpio/gpio-altera-a10sr.c b/drivers/gpio/gpio-altera-a10sr.c
index 9e1a138fed53..16a8951b2bed 100644
--- a/drivers/gpio/gpio-altera-a10sr.c
+++ b/drivers/gpio/gpio-altera-a10sr.c
@@ -96,7 +96,7 @@ static int altr_a10sr_gpio_probe(struct platform_device *pdev)
 	gpio->regmap = a10sr->regmap;
 
 	gpio->gp = altr_a10sr_gc;
-
+	gpio->gp.parent = pdev->dev.parent;
 	gpio->gp.of_node = pdev->dev.of_node;
 
 	ret = devm_gpiochip_add_data(&pdev->dev, &gpio->gp, gpio);
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 5bddbd507ca9..3fe6a21e05a5 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -90,21 +90,18 @@ static int altera_gpio_irq_set_type(struct irq_data *d,
 
 	altera_gc = gpiochip_get_data(irq_data_get_irq_chip_data(d));
 
-	if (type == IRQ_TYPE_NONE)
+	if (type == IRQ_TYPE_NONE) {
+		irq_set_handler_locked(d, handle_bad_irq);
 		return 0;
-	if (type == IRQ_TYPE_LEVEL_HIGH &&
-		altera_gc->interrupt_trigger == IRQ_TYPE_LEVEL_HIGH)
-		return 0;
-	if (type == IRQ_TYPE_EDGE_RISING &&
-		altera_gc->interrupt_trigger == IRQ_TYPE_EDGE_RISING)
-		return 0;
-	if (type == IRQ_TYPE_EDGE_FALLING &&
-		altera_gc->interrupt_trigger == IRQ_TYPE_EDGE_FALLING)
-		return 0;
-	if (type == IRQ_TYPE_EDGE_BOTH &&
-		altera_gc->interrupt_trigger == IRQ_TYPE_EDGE_BOTH)
+	}
+	if (type == altera_gc->interrupt_trigger) {
+		if (type == IRQ_TYPE_LEVEL_HIGH)
+			irq_set_handler_locked(d, handle_level_irq);
+		else
+			irq_set_handler_locked(d, handle_simple_irq);
 		return 0;
-
+	}
+	irq_set_handler_locked(d, handle_bad_irq);
 	return -EINVAL;
 }
 
@@ -230,7 +227,6 @@ static void altera_gpio_irq_edge_handler(struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
-
 static void altera_gpio_irq_leveL_high_handler(struct irq_desc *desc)
 {
 	struct altera_gpio_chip *altera_gc;
@@ -310,7 +306,7 @@ static int altera_gpio_probe(struct platform_device *pdev)
 	altera_gc->interrupt_trigger = reg;
 
 	ret = gpiochip_irqchip_add(&altera_gc->mmchip.gc, &altera_irq_chip, 0,
-		handle_simple_irq, IRQ_TYPE_NONE);
+		handle_bad_irq, IRQ_TYPE_NONE);
 
 	if (ret) {
 		dev_err(&pdev->dev, "could not add irqchip\n");
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index bdb692345428..2a57d024481d 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -270,8 +270,10 @@ mcp23s08_direction_output(struct gpio_chip *chip, unsigned offset, int value)
 static irqreturn_t mcp23s08_irq(int irq, void *data)
 {
 	struct mcp23s08 *mcp = data;
-	int intcap, intf, i;
+	int intcap, intf, i, gpio, gpio_orig, intcap_mask;
 	unsigned int child_irq;
+	bool intf_set, intcap_changed, gpio_bit_changed,
+		defval_changed, gpio_set;
 
 	mutex_lock(&mcp->lock);
 	if (mcp_read(mcp, MCP_INTF, &intf) < 0) {
@@ -287,14 +289,67 @@ static irqreturn_t mcp23s08_irq(int irq, void *data)
 	}
 
 	mcp->cache[MCP_INTCAP] = intcap;
+
+	/* This clears the interrupt(configurable on S18) */
+	if (mcp_read(mcp, MCP_GPIO, &gpio) < 0) {
+		mutex_unlock(&mcp->lock);
+		return IRQ_HANDLED;
+	}
+	gpio_orig = mcp->cache[MCP_GPIO];
+	mcp->cache[MCP_GPIO] = gpio;
 	mutex_unlock(&mcp->lock);
 
+	if (mcp->cache[MCP_INTF] == 0) {
+		/* There is no interrupt pending */
+		return IRQ_HANDLED;
+	}
+
+	dev_dbg(mcp->chip.parent,
+		"intcap 0x%04X intf 0x%04X gpio_orig 0x%04X gpio 0x%04X\n",
+		intcap, intf, gpio_orig, gpio);
 
 	for (i = 0; i < mcp->chip.ngpio; i++) {
-		if ((BIT(i) & mcp->cache[MCP_INTF]) &&
-		    ((BIT(i) & intcap & mcp->irq_rise) ||
-		     (mcp->irq_fall & ~intcap & BIT(i)) ||
-		     (BIT(i) & mcp->cache[MCP_INTCON]))) {
+		/* We must check all of the inputs on the chip,
+		 * otherwise we may not notice a change on >=2 pins.
+		 *
+		 * On at least the mcp23s17, INTCAP is only updated
+		 * one byte at a time(INTCAPA and INTCAPB are
+		 * not written to at the same time - only on a per-bank
+		 * basis).
+		 *
+		 * INTF only contains the single bit that caused the
+		 * interrupt per-bank.  On the mcp23s17, there is
+		 * INTFA and INTFB.  If two pins are changed on the A
+		 * side at the same time, INTF will only have one bit
+		 * set.  If one pin on the A side and one pin on the B
+		 * side are changed at the same time, INTF will have
+		 * two bits set.  Thus, INTF can't be the only check
+		 * to see if the input has changed.
+		 */
+
+		intf_set = BIT(i) & mcp->cache[MCP_INTF];
+		if (i < 8 && intf_set)
+			intcap_mask = 0x00FF;
+		else if (i >= 8 && intf_set)
+			intcap_mask = 0xFF00;
+		else
+			intcap_mask = 0x00;
+
+		intcap_changed = (intcap_mask &
+			(BIT(i) & mcp->cache[MCP_INTCAP])) !=
+			(intcap_mask & (BIT(i) & gpio_orig));
+		gpio_set = BIT(i) & mcp->cache[MCP_GPIO];
+		gpio_bit_changed = (BIT(i) & gpio_orig) !=
+			(BIT(i) & mcp->cache[MCP_GPIO]);
+		defval_changed = (BIT(i) & mcp->cache[MCP_INTCON]) &&
+			((BIT(i) & mcp->cache[MCP_GPIO]) !=
+			(BIT(i) & mcp->cache[MCP_DEFVAL]));
+
+		if (((gpio_bit_changed || intcap_changed) &&
+			(BIT(i) & mcp->irq_rise) && gpio_set) ||
+		    ((gpio_bit_changed || intcap_changed) &&
+			(BIT(i) & mcp->irq_fall) && !gpio_set) ||
+		    defval_changed) {
 			child_irq = irq_find_mapping(mcp->chip.irqdomain, i);
 			handle_nested_irq(child_irq);
 		}
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index 06dac72cb69c..d99338689213 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -197,7 +197,7 @@ static ssize_t gpio_mockup_event_write(struct file *file,
 	struct seq_file *sfile;
 	struct gpio_desc *desc;
 	struct gpio_chip *gc;
-	int status, val;
+	int val;
 	char buf;
 
 	sfile = file->private_data;
@@ -206,9 +206,8 @@ static ssize_t gpio_mockup_event_write(struct file *file,
 	chip = priv->chip;
 	gc = &chip->gc;
 
-	status = copy_from_user(&buf, usr_buf, 1);
-	if (status)
-		return status;
+	if (copy_from_user(&buf, usr_buf, 1))
+		return -EFAULT;
 
 	if (buf == '0')
 		val = 0;
diff --git a/drivers/gpio/gpio-xgene.c b/drivers/gpio/gpio-xgene.c
index 40a8881c2ce8..f1c6ec17b90a 100644
--- a/drivers/gpio/gpio-xgene.c
+++ b/drivers/gpio/gpio-xgene.c
@@ -42,9 +42,7 @@ struct xgene_gpio {
 	struct gpio_chip	chip;
 	void __iomem		*base;
 	spinlock_t		lock;
-#ifdef CONFIG_PM
 	u32			set_dr_val[XGENE_MAX_GPIO_BANKS];
-#endif
 };
 
 static int xgene_gpio_get(struct gpio_chip *gc, unsigned int offset)
@@ -138,8 +136,7 @@ static int xgene_gpio_dir_out(struct gpio_chip *gc,
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int xgene_gpio_suspend(struct device *dev)
+static __maybe_unused int xgene_gpio_suspend(struct device *dev)
 {
 	struct xgene_gpio *gpio = dev_get_drvdata(dev);
 	unsigned long bank_offset;
@@ -152,7 +149,7 @@ static int xgene_gpio_suspend(struct device *dev)
 	return 0;
 }
 
-static int xgene_gpio_resume(struct device *dev)
+static __maybe_unused int xgene_gpio_resume(struct device *dev)
 {
 	struct xgene_gpio *gpio = dev_get_drvdata(dev);
 	unsigned long bank_offset;
@@ -166,10 +163,6 @@ static int xgene_gpio_resume(struct device *dev)
 }
 
 static SIMPLE_DEV_PM_OPS(xgene_gpio_pm, xgene_gpio_suspend, xgene_gpio_resume);
-#define XGENE_GPIO_PM_OPS	(&xgene_gpio_pm)
-#else
-#define XGENE_GPIO_PM_OPS	NULL
-#endif
 
 static int xgene_gpio_probe(struct platform_device *pdev)
 {
@@ -241,7 +234,7 @@ static struct platform_driver xgene_gpio_driver = {
 		.name = "xgene-gpio",
 		.of_match_table = xgene_gpio_of_match,
 		.acpi_match_table = ACPI_PTR(xgene_gpio_acpi_match),
-		.pm     = XGENE_GPIO_PM_OPS,
+		.pm     = &xgene_gpio_pm,
 	},
 	.probe = xgene_gpio_probe,
 };
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 9b37a3692b3f..2bd683e2be02 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -266,6 +266,9 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 		goto fail_free_event;
 	}
 
+	if (agpio->wake_capable == ACPI_WAKE_CAPABLE)
+		enable_irq_wake(irq);
+
 	list_add_tail(&event->node, &acpi_gpio->events);
 	return AE_OK;
 
@@ -339,6 +342,9 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 	list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) {
 		struct gpio_desc *desc;
 
+		if (irqd_is_wakeup_set(irq_get_irq_data(event->irq)))
+			disable_irq_wake(event->irq);
+
 		free_irq(event->irq, event);
 		desc = event->desc;
 		if (WARN_ON(IS_ERR(desc)))
@@ -571,8 +577,10 @@ struct gpio_desc *acpi_find_gpio(struct device *dev,
 		}
 
 		desc = acpi_get_gpiod_by_index(adev, propname, idx, &info);
-		if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER))
+		if (!IS_ERR(desc))
 			break;
+		if (PTR_ERR(desc) == -EPROBE_DEFER)
+			return ERR_CAST(desc);
 	}
 
 	/* Then from plain _CRS GPIOs */
diff --git a/drivers/gpu/drm/amd/acp/Makefile b/drivers/gpu/drm/amd/acp/Makefile
index 8363cb57915b..8a08e81ee90d 100644
--- a/drivers/gpu/drm/amd/acp/Makefile
+++ b/drivers/gpu/drm/amd/acp/Makefile
@@ -3,6 +3,4 @@
 # of AMDSOC/AMDGPU drm driver.
 # It provides the HW control for ACP related functionalities.
 
-subdir-ccflags-y += -I$(AMDACPPATH)/ -I$(AMDACPPATH)/include
-
 AMD_ACP_FILES := $(AMDACPPATH)/acp_hw.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d2d0f60ff36d..99424cb8020b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -240,6 +240,8 @@ free_partial_kdata:
 	for (; i >= 0; i--)
 		drm_free_large(p->chunks[i].kdata);
 	kfree(p->chunks);
+	p->chunks = NULL;
+	p->nchunks = 0;
 put_ctx:
 	amdgpu_ctx_put(p->ctx);
 free_chunk:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6abb238b25c9..de0cf3315484 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -475,7 +475,7 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 	int r;
 
 	if (adev->wb.wb_obj == NULL) {
-		r = amdgpu_bo_create_kernel(adev, AMDGPU_MAX_WB * 4,
+		r = amdgpu_bo_create_kernel(adev, AMDGPU_MAX_WB * sizeof(uint32_t),
 					    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
 					    &adev->wb.wb_obj, &adev->wb.gpu_addr,
 					    (void **)&adev->wb.wb);
@@ -488,7 +488,7 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 		memset(&adev->wb.used, 0, sizeof(adev->wb.used));
 
 		/* clear wb memory */
-		memset((char *)adev->wb.wb, 0, AMDGPU_GPU_PAGE_SIZE);
+		memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t));
 	}
 
 	return 0;
@@ -2094,8 +2094,11 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	r = amdgpu_late_init(adev);
-	if (r)
+	if (r) {
+		if (fbcon)
+			console_unlock();
 		return r;
+	}
 
 	/* pin cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -2587,7 +2590,7 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
 		use_bank = 0;
 	}
 
-	*pos &= 0x3FFFF;
+	*pos &= (1UL << 22) - 1;
 
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
@@ -2663,7 +2666,7 @@ static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
 		use_bank = 0;
 	}
 
-	*pos &= 0x3FFFF;
+	*pos &= (1UL << 22) - 1;
 
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 75fc376ba735..b76cd699eb0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -59,9 +59,10 @@
  * - 3.7.0 - Add support for VCE clock list packet
  * - 3.8.0 - Add support raster config init in the kernel
  * - 3.9.0 - Add support for memory query info about VRAM and GTT.
+ * - 3.10.0 - Add support for new fences ioctl, new gem ioctl flags
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	9
+#define KMS_DRIVER_MINOR	10
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -420,6 +421,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x6985, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 	{0x1002, 0x6986, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 	{0x1002, 0x6987, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	{0x1002, 0x6995, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 	{0x1002, 0x699F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 
 	{0, 0, 0}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 51d759463384..106cf83c2e6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -202,6 +202,27 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	bool kernel = false;
 	int r;
 
+	/* reject invalid gem flags */
+	if (args->in.domain_flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+				      AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
+				      AMDGPU_GEM_CREATE_CPU_GTT_USWC |
+				      AMDGPU_GEM_CREATE_VRAM_CLEARED|
+				      AMDGPU_GEM_CREATE_SHADOW |
+				      AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
+		r = -EINVAL;
+		goto error_unlock;
+	}
+	/* reject invalid gem domains */
+	if (args->in.domains & ~(AMDGPU_GEM_DOMAIN_CPU |
+				 AMDGPU_GEM_DOMAIN_GTT |
+				 AMDGPU_GEM_DOMAIN_VRAM |
+				 AMDGPU_GEM_DOMAIN_GDS |
+				 AMDGPU_GEM_DOMAIN_GWS |
+				 AMDGPU_GEM_DOMAIN_OA)) {
+		r = -EINVAL;
+		goto error_unlock;
+	}
+
 	/* create a gem object to contain this object in */
 	if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
 	    AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 31375bdde6f1..011800f621c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -788,7 +788,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
 		}
 	}
 
-	/* disble sdma engine before programing it */
+	/* disable sdma engine before programing it */
 	sdma_v3_0_ctx_switch_enable(adev, false);
 	sdma_v3_0_enable(adev, false);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index f55e45b52fbc..c5dec210d529 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3464,6 +3464,16 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		    (adev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
 		}
+	} else if (adev->asic_type == CHIP_OLAND) {
+		if ((adev->pdev->revision == 0xC7) ||
+		    (adev->pdev->revision == 0x80) ||
+		    (adev->pdev->revision == 0x81) ||
+		    (adev->pdev->revision == 0x83) ||
+		    (adev->pdev->revision == 0x87) ||
+		    (adev->pdev->device == 0x6604) ||
+		    (adev->pdev->device == 0x6605)) {
+			max_sclk = 75000;
+		}
 	}
 
 	if (rps->vce_active) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 50bdb24ef8d6..4a785d6acfb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1051,7 +1051,7 @@ static int vi_common_early_init(void *handle)
 		/* rev0 hardware requires workarounds to support PG */
 		adev->pg_flags = 0;
 		if (adev->rev_id != 0x00) {
-			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+			adev->pg_flags |=
 				AMD_PG_SUPPORT_GFX_SMG |
 				AMD_PG_SUPPORT_GFX_PIPELINE |
 				AMD_PG_SUPPORT_CP |
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 8cf71f3c6d0e..261b828ad590 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -178,7 +178,7 @@ int smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	if (bgate) {
 		cgs_set_powergating_state(hwmgr->device,
 						AMD_IP_BLOCK_TYPE_VCE,
-						AMD_PG_STATE_UNGATE);
+						AMD_PG_STATE_GATE);
 		cgs_set_clockgating_state(hwmgr->device,
 				AMD_IP_BLOCK_TYPE_VCE,
 				AMD_CG_STATE_GATE);
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index 08e6a71f5d05..294b53697334 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -63,8 +63,7 @@ static void malidp_crtc_enable(struct drm_crtc *crtc)
 
 	clk_prepare_enable(hwdev->pxlclk);
 
-	/* mclk needs to be set to the same or higher rate than pxlclk */
-	clk_set_rate(hwdev->mclk, crtc->state->adjusted_mode.crtc_clock * 1000);
+	/* We rely on firmware to set mclk to a sensible level. */
 	clk_set_rate(hwdev->pxlclk, crtc->state->adjusted_mode.crtc_clock * 1000);
 
 	hwdev->modeset(hwdev, &vm);
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 488aedf5b58d..9f5513006eee 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -83,7 +83,7 @@ static const struct malidp_layer malidp550_layers[] = {
 	{ DE_VIDEO1, MALIDP550_DE_LV1_BASE, MALIDP550_DE_LV1_PTR_BASE, MALIDP_DE_LV_STRIDE0 },
 	{ DE_GRAPHICS1, MALIDP550_DE_LG_BASE, MALIDP550_DE_LG_PTR_BASE, MALIDP_DE_LG_STRIDE },
 	{ DE_VIDEO2, MALIDP550_DE_LV2_BASE, MALIDP550_DE_LV2_PTR_BASE, MALIDP_DE_LV_STRIDE0 },
-	{ DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE, 0 },
+	{ DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE, MALIDP550_DE_LS_R1_STRIDE },
 };
 
 #define MALIDP_DE_DEFAULT_PREFETCH_START	5
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 414aada10fe5..d5aec082294c 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -37,6 +37,8 @@
 #define   LAYER_V_VAL(x)		(((x) & 0x1fff) << 16)
 #define MALIDP_LAYER_COMP_SIZE		0x010
 #define MALIDP_LAYER_OFFSET		0x014
+#define MALIDP550_LS_ENABLE		0x01c
+#define MALIDP550_LS_R1_IN_SIZE		0x020
 
 /*
  * This 4-entry look-up-table is used to determine the full 8-bit alpha value
@@ -242,6 +244,11 @@ static void malidp_de_plane_update(struct drm_plane *plane,
 			LAYER_V_VAL(plane->state->crtc_y),
 			mp->layer->base + MALIDP_LAYER_OFFSET);
 
+	if (mp->layer->id == DE_SMART)
+		malidp_hw_write(mp->hwdev,
+				LAYER_H_VAL(src_w) | LAYER_V_VAL(src_h),
+				mp->layer->base + MALIDP550_LS_R1_IN_SIZE);
+
 	/* first clear the rotation bits */
 	val = malidp_hw_read(mp->hwdev, mp->layer->base + MALIDP_LAYER_CONTROL);
 	val &= ~LAYER_ROT_MASK;
@@ -330,9 +337,16 @@ int malidp_de_planes_init(struct drm_device *drm)
 		plane->hwdev = malidp->dev;
 		plane->layer = &map->layers[i];
 
-		/* Skip the features which the SMART layer doesn't have */
-		if (id == DE_SMART)
+		if (id == DE_SMART) {
+			/*
+			 * Enable the first rectangle in the SMART layer to be
+			 * able to use it as a drm plane.
+			 */
+			malidp_hw_write(malidp->dev, 1,
+					plane->layer->base + MALIDP550_LS_ENABLE);
+			/* Skip the features which the SMART layer doesn't have. */
 			continue;
+		}
 
 		drm_plane_create_rotation_property(&plane->base, DRM_ROTATE_0, flags);
 		malidp_hw_write(malidp->dev, MALIDP_ALPHA_LUT,
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index aff6d4a84e99..b816067a65c5 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -84,6 +84,7 @@
 /* Stride register offsets relative to Lx_BASE */
 #define MALIDP_DE_LG_STRIDE		0x18
 #define MALIDP_DE_LV_STRIDE0		0x18
+#define MALIDP550_DE_LS_R1_STRIDE	0x28
 
 /* macros to set values into registers */
 #define MALIDP_DE_H_FRONTPORCH(x)	(((x) & 0xfff) << 0)
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index c8baab9bee0d..ba58f1b11d1e 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -148,6 +148,9 @@ static const struct edid_quirk {
 
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
+
+	/* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/
+	{ "ETR", 13896, EDID_QUIRK_FORCE_8BPC },
 };
 
 /*
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index f6d4d9700734..324a688b3f30 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1260,9 +1260,9 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	 * to KMS, hence fail if different settings are requested.
 	 */
 	if (var->bits_per_pixel != fb->format->cpp[0] * 8 ||
-	    var->xres != fb->width || var->yres != fb->height ||
-	    var->xres_virtual != fb->width || var->yres_virtual != fb->height) {
-		DRM_DEBUG("fb userspace requested width/height/bpp different than current fb "
+	    var->xres > fb->width || var->yres > fb->height ||
+	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
+		DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
 			  "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n",
 			  var->xres, var->yres, var->bits_per_pixel,
 			  var->xres_virtual, var->yres_virtual,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 130d7d517a19..b78d9239e48f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1311,15 +1311,15 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
 		goto out_pm_put;
 	}
 
+	mutex_lock(&gpu->lock);
+
 	fence = etnaviv_gpu_fence_alloc(gpu);
 	if (!fence) {
 		event_free(gpu, event);
 		ret = -ENOMEM;
-		goto out_pm_put;
+		goto out_unlock;
 	}
 
-	mutex_lock(&gpu->lock);
-
 	gpu->event[event].fence = fence;
 	submit->fence = fence->seqno;
 	gpu->active_fence = submit->fence;
@@ -1357,6 +1357,7 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
 	hangcheck_timer_reset(gpu);
 	ret = 0;
 
+out_unlock:
 	mutex_unlock(&gpu->lock);
 
 out_pm_put:
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 0fd6f7a18364..c0e8d3302292 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -68,6 +68,8 @@ struct decon_context {
 	unsigned long			flags;
 	unsigned long			out_type;
 	int				first_win;
+	spinlock_t			vblank_lock;
+	u32				frame_id;
 };
 
 static const uint32_t decon_formats[] = {
@@ -103,7 +105,7 @@ static int decon_enable_vblank(struct exynos_drm_crtc *crtc)
 		if (ctx->out_type & IFTYPE_I80)
 			val |= VIDINTCON0_FRAMEDONE;
 		else
-			val |= VIDINTCON0_INTFRMEN;
+			val |= VIDINTCON0_INTFRMEN | VIDINTCON0_FRAMESEL_FP;
 
 		writel(val, ctx->addr + DECON_VIDINTCON0);
 	}
@@ -122,14 +124,56 @@ static void decon_disable_vblank(struct exynos_drm_crtc *crtc)
 		writel(0, ctx->addr + DECON_VIDINTCON0);
 }
 
+/* return number of starts/ends of frame transmissions since reset */
+static u32 decon_get_frame_count(struct decon_context *ctx, bool end)
+{
+	u32 frm, pfrm, status, cnt = 2;
+
+	/* To get consistent result repeat read until frame id is stable.
+	 * Usually the loop will be executed once, in rare cases when the loop
+	 * is executed at frame change time 2nd pass will be needed.
+	 */
+	frm = readl(ctx->addr + DECON_CRFMID);
+	do {
+		status = readl(ctx->addr + DECON_VIDCON1);
+		pfrm = frm;
+		frm = readl(ctx->addr + DECON_CRFMID);
+	} while (frm != pfrm && --cnt);
+
+	/* CRFMID is incremented on BPORCH in case of I80 and on VSYNC in case
+	 * of RGB, it should be taken into account.
+	 */
+	if (!frm)
+		return 0;
+
+	switch (status & (VIDCON1_VSTATUS_MASK | VIDCON1_I80_ACTIVE)) {
+	case VIDCON1_VSTATUS_VS:
+		if (!(ctx->out_type & IFTYPE_I80))
+			--frm;
+		break;
+	case VIDCON1_VSTATUS_BP:
+		--frm;
+		break;
+	case VIDCON1_I80_ACTIVE:
+	case VIDCON1_VSTATUS_AC:
+		if (end)
+			--frm;
+		break;
+	default:
+		break;
+	}
+
+	return frm;
+}
+
 static void decon_setup_trigger(struct decon_context *ctx)
 {
 	if (!(ctx->out_type & (IFTYPE_I80 | I80_HW_TRG)))
 		return;
 
 	if (!(ctx->out_type & I80_HW_TRG)) {
-		writel(TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN
-		       | TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN,
+		writel(TRIGCON_TRIGEN_PER_F | TRIGCON_TRIGEN_F |
+		       TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN,
 		       ctx->addr + DECON_TRIGCON);
 		return;
 	}
@@ -365,11 +409,14 @@ static void decon_disable_plane(struct exynos_drm_crtc *crtc,
 static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
+	unsigned long flags;
 	int i;
 
 	if (test_bit(BIT_SUSPENDED, &ctx->flags))
 		return;
 
+	spin_lock_irqsave(&ctx->vblank_lock, flags);
+
 	for (i = ctx->first_win; i < WINDOWS_NR; i++)
 		decon_shadow_protect_win(ctx, i, false);
 
@@ -378,11 +425,18 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
 
 	if (ctx->out_type & IFTYPE_I80)
 		set_bit(BIT_WIN_UPDATED, &ctx->flags);
+
+	ctx->frame_id = decon_get_frame_count(ctx, true);
+
+	exynos_crtc_handle_event(crtc);
+
+	spin_unlock_irqrestore(&ctx->vblank_lock, flags);
 }
 
 static void decon_swreset(struct decon_context *ctx)
 {
 	unsigned int tries;
+	unsigned long flags;
 
 	writel(0, ctx->addr + DECON_VIDCON0);
 	for (tries = 2000; tries; --tries) {
@@ -400,6 +454,10 @@ static void decon_swreset(struct decon_context *ctx)
 
 	WARN(tries == 0, "failed to software reset DECON\n");
 
+	spin_lock_irqsave(&ctx->vblank_lock, flags);
+	ctx->frame_id = 0;
+	spin_unlock_irqrestore(&ctx->vblank_lock, flags);
+
 	if (!(ctx->out_type & IFTYPE_HDMI))
 		return;
 
@@ -578,6 +636,24 @@ static const struct component_ops decon_component_ops = {
 	.unbind = decon_unbind,
 };
 
+static void decon_handle_vblank(struct decon_context *ctx)
+{
+	u32 frm;
+
+	spin_lock(&ctx->vblank_lock);
+
+	frm = decon_get_frame_count(ctx, true);
+
+	if (frm != ctx->frame_id) {
+		/* handle only if incremented, take care of wrap-around */
+		if ((s32)(frm - ctx->frame_id) > 0)
+			drm_crtc_handle_vblank(&ctx->crtc->base);
+		ctx->frame_id = frm;
+	}
+
+	spin_unlock(&ctx->vblank_lock);
+}
+
 static irqreturn_t decon_irq_handler(int irq, void *dev_id)
 {
 	struct decon_context *ctx = dev_id;
@@ -598,7 +674,7 @@ static irqreturn_t decon_irq_handler(int irq, void *dev_id)
 			    (VIDOUT_INTERLACE_EN_F | VIDOUT_INTERLACE_FIELD_F))
 				return IRQ_HANDLED;
 		}
-		drm_crtc_handle_vblank(&ctx->crtc->base);
+		decon_handle_vblank(ctx);
 	}
 
 out:
@@ -671,6 +747,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
 	__set_bit(BIT_SUSPENDED, &ctx->flags);
 	ctx->dev = dev;
 	ctx->out_type = (unsigned long)of_device_get_match_data(dev);
+	spin_lock_init(&ctx->vblank_lock);
 
 	if (ctx->out_type & IFTYPE_HDMI) {
 		ctx->first_win = 1;
@@ -678,7 +755,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
 		ctx->out_type |= IFTYPE_I80;
 	}
 
-	if (ctx->out_type | I80_HW_TRG) {
+	if (ctx->out_type & I80_HW_TRG) {
 		ctx->sysreg = syscon_regmap_lookup_by_phandle(dev->of_node,
 							"samsung,disp-sysreg");
 		if (IS_ERR(ctx->sysreg)) {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f9ab19e205e2..48811806fa27 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -526,6 +526,7 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
 
 	for (i = 0; i < WINDOWS_NR; i++)
 		decon_shadow_protect_win(ctx, i, false);
+	exynos_crtc_handle_event(crtc);
 }
 
 static void decon_init(struct decon_context *ctx)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 5367b6664fe3..c65f4509932c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -85,16 +85,28 @@ static void exynos_crtc_atomic_flush(struct drm_crtc *crtc,
 				     struct drm_crtc_state *old_crtc_state)
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
-	struct drm_pending_vblank_event *event;
-	unsigned long flags;
 
 	if (exynos_crtc->ops->atomic_flush)
 		exynos_crtc->ops->atomic_flush(exynos_crtc);
+}
+
+static const struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
+	.enable		= exynos_drm_crtc_enable,
+	.disable	= exynos_drm_crtc_disable,
+	.mode_set_nofb	= exynos_drm_crtc_mode_set_nofb,
+	.atomic_check	= exynos_crtc_atomic_check,
+	.atomic_begin	= exynos_crtc_atomic_begin,
+	.atomic_flush	= exynos_crtc_atomic_flush,
+};
+
+void exynos_crtc_handle_event(struct exynos_drm_crtc *exynos_crtc)
+{
+	struct drm_crtc *crtc = &exynos_crtc->base;
+	struct drm_pending_vblank_event *event = crtc->state->event;
+	unsigned long flags;
 
-	event = crtc->state->event;
 	if (event) {
 		crtc->state->event = NULL;
-
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 		if (drm_crtc_vblank_get(crtc) == 0)
 			drm_crtc_arm_vblank_event(crtc, event);
@@ -105,15 +117,6 @@ static void exynos_crtc_atomic_flush(struct drm_crtc *crtc,
 
 }
 
-static const struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
-	.enable		= exynos_drm_crtc_enable,
-	.disable	= exynos_drm_crtc_disable,
-	.mode_set_nofb	= exynos_drm_crtc_mode_set_nofb,
-	.atomic_check	= exynos_crtc_atomic_check,
-	.atomic_begin	= exynos_crtc_atomic_begin,
-	.atomic_flush	= exynos_crtc_atomic_flush,
-};
-
 static void exynos_drm_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index 6a581a8af465..abd5d6ceac0c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -40,4 +40,6 @@ int exynos_drm_crtc_get_pipe_from_type(struct drm_device *drm_dev,
  */
 void exynos_drm_crtc_te_handler(struct drm_crtc *crtc);
 
+void exynos_crtc_handle_event(struct exynos_drm_crtc *exynos_crtc);
+
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 812e2ec0761d..d7ef26370e67 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -86,7 +86,7 @@
 #define DSIM_SYNC_INFORM		(1 << 27)
 #define DSIM_EOT_DISABLE		(1 << 28)
 #define DSIM_MFLUSH_VS			(1 << 29)
-/* This flag is valid only for exynos3250/3472/4415/5260/5430 */
+/* This flag is valid only for exynos3250/3472/5260/5430 */
 #define DSIM_CLKLANE_STOP		(1 << 30)
 
 /* DSIM_ESCMODE */
@@ -473,17 +473,6 @@ static const struct exynos_dsi_driver_data exynos4_dsi_driver_data = {
 	.reg_values = reg_values,
 };
 
-static const struct exynos_dsi_driver_data exynos4415_dsi_driver_data = {
-	.reg_ofs = exynos_reg_ofs,
-	.plltmr_reg = 0x58,
-	.has_clklane_stop = 1,
-	.num_clks = 2,
-	.max_freq = 1000,
-	.wait_for_reset = 1,
-	.num_bits_resol = 11,
-	.reg_values = reg_values,
-};
-
 static const struct exynos_dsi_driver_data exynos5_dsi_driver_data = {
 	.reg_ofs = exynos_reg_ofs,
 	.plltmr_reg = 0x58,
@@ -521,8 +510,6 @@ static const struct of_device_id exynos_dsi_of_match[] = {
 	  .data = &exynos3_dsi_driver_data },
 	{ .compatible = "samsung,exynos4210-mipi-dsi",
 	  .data = &exynos4_dsi_driver_data },
-	{ .compatible = "samsung,exynos4415-mipi-dsi",
-	  .data = &exynos4415_dsi_driver_data },
 	{ .compatible = "samsung,exynos5410-mipi-dsi",
 	  .data = &exynos5_dsi_driver_data },
 	{ .compatible = "samsung,exynos5422-mipi-dsi",
@@ -979,7 +966,7 @@ static void exynos_dsi_send_to_fifo(struct exynos_dsi *dsi,
 	bool first = !xfer->tx_done;
 	u32 reg;
 
-	dev_dbg(dev, "< xfer %p: tx len %u, done %u, rx len %u, done %u\n",
+	dev_dbg(dev, "< xfer %pK: tx len %u, done %u, rx len %u, done %u\n",
 		xfer, length, xfer->tx_done, xfer->rx_len, xfer->rx_done);
 
 	if (length > DSI_TX_FIFO_SIZE)
@@ -1177,7 +1164,7 @@ static bool exynos_dsi_transfer_finish(struct exynos_dsi *dsi)
 	spin_unlock_irqrestore(&dsi->transfer_lock, flags);
 
 	dev_dbg(dsi->dev,
-		"> xfer %p, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n",
+		"> xfer %pK, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n",
 		xfer, xfer->packet.payload_length, xfer->tx_done, xfer->rx_len,
 		xfer->rx_done);
 
@@ -1348,9 +1335,12 @@ static int exynos_dsi_register_te_irq(struct exynos_dsi *dsi)
 	int te_gpio_irq;
 
 	dsi->te_gpio = of_get_named_gpio(dsi->panel_node, "te-gpios", 0);
+	if (dsi->te_gpio == -ENOENT)
+		return 0;
+
 	if (!gpio_is_valid(dsi->te_gpio)) {
-		dev_err(dsi->dev, "no te-gpios specified\n");
 		ret = dsi->te_gpio;
+		dev_err(dsi->dev, "cannot get te-gpios, %d\n", ret);
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 95871577015d..5b18b5c5fdf2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1695,7 +1695,7 @@ static int fimc_probe(struct platform_device *pdev)
 		goto err_put_clk;
 	}
 
-	DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
+	DRM_DEBUG_KMS("id[%d]ippdrv[%pK]\n", ctx->id, ippdrv);
 
 	spin_lock_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index a9fa444c6053..3f04d72c448d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -71,10 +71,10 @@
 #define TRIGCON				0x1A4
 #define TRGMODE_ENABLE			(1 << 0)
 #define SWTRGCMD_ENABLE			(1 << 1)
-/* Exynos3250, 3472, 4415, 5260 5410, 5420 and 5422 only supported. */
+/* Exynos3250, 3472, 5260 5410, 5420 and 5422 only supported. */
 #define HWTRGEN_ENABLE			(1 << 3)
 #define HWTRGMASK_ENABLE		(1 << 4)
-/* Exynos3250, 3472, 4415, 5260, 5420 and 5422 only supported. */
+/* Exynos3250, 3472, 5260, 5420 and 5422 only supported. */
 #define HWTRIGEN_PER_ENABLE		(1 << 31)
 
 /* display mode change control register except exynos4 */
@@ -138,18 +138,6 @@ static struct fimd_driver_data exynos4_fimd_driver_data = {
 	.has_vtsel = 1,
 };
 
-static struct fimd_driver_data exynos4415_fimd_driver_data = {
-	.timing_base = 0x20000,
-	.lcdblk_offset = 0x210,
-	.lcdblk_vt_shift = 10,
-	.lcdblk_bypass_shift = 1,
-	.trg_type = I80_HW_TRG,
-	.has_shadowcon = 1,
-	.has_vidoutcon = 1,
-	.has_vtsel = 1,
-	.has_trigger_per_te = 1,
-};
-
 static struct fimd_driver_data exynos5_fimd_driver_data = {
 	.timing_base = 0x20000,
 	.lcdblk_offset = 0x214,
@@ -210,8 +198,6 @@ static const struct of_device_id fimd_driver_dt_match[] = {
 	  .data = &exynos3_fimd_driver_data },
 	{ .compatible = "samsung,exynos4210-fimd",
 	  .data = &exynos4_fimd_driver_data },
-	{ .compatible = "samsung,exynos4415-fimd",
-	  .data = &exynos4415_fimd_driver_data },
 	{ .compatible = "samsung,exynos5250-fimd",
 	  .data = &exynos5_fimd_driver_data },
 	{ .compatible = "samsung,exynos5420-fimd",
@@ -257,7 +243,7 @@ static int fimd_enable_vblank(struct exynos_drm_crtc *crtc)
 			val |= VIDINTCON0_INT_FRAME;
 
 			val &= ~VIDINTCON0_FRAMESEL0_MASK;
-			val |= VIDINTCON0_FRAMESEL0_VSYNC;
+			val |= VIDINTCON0_FRAMESEL0_FRONTPORCH;
 			val &= ~VIDINTCON0_FRAMESEL1_MASK;
 			val |= VIDINTCON0_FRAMESEL1_NONE;
 		}
@@ -723,6 +709,8 @@ static void fimd_atomic_flush(struct exynos_drm_crtc *crtc)
 
 	for (i = 0; i < WINDOWS_NR; i++)
 		fimd_shadow_protect_win(ctx, i, false);
+
+	exynos_crtc_handle_event(crtc);
 }
 
 static void fimd_update_plane(struct exynos_drm_crtc *crtc,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 4c28f7ffcc4d..55a1579d11b3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -218,7 +218,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
-	DRM_DEBUG_KMS("created file object = %p\n", obj->filp);
+	DRM_DEBUG_KMS("created file object = %pK\n", obj->filp);
 
 	return exynos_gem;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index bef57987759d..0506b2b17ac1 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1723,7 +1723,7 @@ static int gsc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
+	DRM_DEBUG_KMS("id[%d]ippdrv[%pK]\n", ctx->id, ippdrv);
 
 	mutex_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 9c84ee76f18a..3edda18cc2d2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -208,7 +208,7 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
 	 * e.g PAUSE state, queue buf, command control.
 	 */
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
-		DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n", count++, ippdrv);
+		DRM_DEBUG_KMS("count[%d]ippdrv[%pK]\n", count++, ippdrv);
 
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
@@ -388,7 +388,7 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 	}
 	property->prop_id = ret;
 
-	DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%p]\n",
+	DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%pK]\n",
 		property->prop_id, property->cmd, ippdrv);
 
 	/* stored property information and ippdrv in private data */
@@ -518,7 +518,7 @@ static int ipp_put_mem_node(struct drm_device *drm_dev,
 {
 	int i;
 
-	DRM_DEBUG_KMS("node[%p]\n", m_node);
+	DRM_DEBUG_KMS("node[%pK]\n", m_node);
 
 	if (!m_node) {
 		DRM_ERROR("invalid dequeue node.\n");
@@ -562,7 +562,7 @@ static struct drm_exynos_ipp_mem_node
 	m_node->buf_id = qbuf->buf_id;
 	INIT_LIST_HEAD(&m_node->list);
 
-	DRM_DEBUG_KMS("m_node[%p]ops_id[%d]\n", m_node, qbuf->ops_id);
+	DRM_DEBUG_KMS("m_node[%pK]ops_id[%d]\n", m_node, qbuf->ops_id);
 	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]\n", qbuf->prop_id, m_node->buf_id);
 
 	for_each_ipp_planar(i) {
@@ -659,7 +659,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
 
 	mutex_lock(&c_node->event_lock);
 	list_for_each_entry_safe(e, te, &c_node->event_list, base.link) {
-		DRM_DEBUG_KMS("count[%d]e[%p]\n", count++, e);
+		DRM_DEBUG_KMS("count[%d]e[%pK]\n", count++, e);
 
 		/*
 		 * qbuf == NULL condition means all event deletion.
@@ -750,7 +750,7 @@ static struct drm_exynos_ipp_mem_node
 
 	/* find memory node from memory list */
 	list_for_each_entry(m_node, head, list) {
-		DRM_DEBUG_KMS("count[%d]m_node[%p]\n", count++, m_node);
+		DRM_DEBUG_KMS("count[%d]m_node[%pK]\n", count++, m_node);
 
 		/* compare buffer id */
 		if (m_node->buf_id == qbuf->buf_id)
@@ -767,7 +767,7 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
 	struct exynos_drm_ipp_ops *ops = NULL;
 	int ret = 0;
 
-	DRM_DEBUG_KMS("node[%p]\n", m_node);
+	DRM_DEBUG_KMS("node[%pK]\n", m_node);
 
 	if (!m_node) {
 		DRM_ERROR("invalid queue node.\n");
@@ -1232,7 +1232,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			m_node = list_first_entry(head,
 				struct drm_exynos_ipp_mem_node, list);
 
-			DRM_DEBUG_KMS("m_node[%p]\n", m_node);
+			DRM_DEBUG_KMS("m_node[%pK]\n", m_node);
 
 			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 			if (ret) {
@@ -1601,7 +1601,7 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 		}
 		ippdrv->prop_list.ipp_id = ret;
 
-		DRM_DEBUG_KMS("count[%d]ippdrv[%p]ipp_id[%d]\n",
+		DRM_DEBUG_KMS("count[%d]ippdrv[%pK]ipp_id[%d]\n",
 			count++, ippdrv, ret);
 
 		/* store parent device for node */
@@ -1659,7 +1659,7 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
 
 	file_priv->ipp_dev = dev;
 
-	DRM_DEBUG_KMS("done priv[%p]\n", dev);
+	DRM_DEBUG_KMS("done priv[%pK]\n", dev);
 
 	return 0;
 }
@@ -1676,7 +1676,7 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry_safe(c_node, tc_node,
 			&ippdrv->cmd_list, list) {
-			DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n",
+			DRM_DEBUG_KMS("count[%d]ippdrv[%pK]\n",
 				count++, ippdrv);
 
 			if (c_node->filp == file) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 6591e406084c..79282a820ecc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -748,7 +748,7 @@ static int rotator_probe(struct platform_device *pdev)
 		goto err_ippdrv_register;
 	}
 
-	DRM_DEBUG_KMS("ippdrv[%p]\n", ippdrv);
+	DRM_DEBUG_KMS("ippdrv[%pK]\n", ippdrv);
 
 	platform_set_drvdata(pdev, rot);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 57fe514d5c5b..5d9a62a87eec 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -170,6 +170,7 @@ static const struct exynos_drm_crtc_ops vidi_crtc_ops = {
 	.enable_vblank = vidi_enable_vblank,
 	.disable_vblank = vidi_disable_vblank,
 	.update_plane = vidi_update_plane,
+	.atomic_flush = exynos_crtc_handle_event,
 };
 
 static void vidi_fake_vblank_timer(unsigned long arg)
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 72143ac10525..25edb635a197 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -1012,6 +1012,7 @@ static void mixer_atomic_flush(struct exynos_drm_crtc *crtc)
 		return;
 
 	mixer_vsync_set_update(mixer_ctx, true);
+	exynos_crtc_handle_event(crtc);
 }
 
 static void mixer_enable(struct exynos_drm_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 3b6caaca9751..325618d969fe 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -242,7 +242,7 @@ static int alloc_resource(struct intel_vgpu *vgpu,
 	const char *item;
 
 	if (!param->low_gm_sz || !param->high_gm_sz || !param->fence_sz) {
-		gvt_err("Invalid vGPU creation params\n");
+		gvt_vgpu_err("Invalid vGPU creation params\n");
 		return -EINVAL;
 	}
 
@@ -285,9 +285,9 @@ static int alloc_resource(struct intel_vgpu *vgpu,
 	return 0;
 
 no_enough_resource:
-	gvt_err("vgpu%d: fail to allocate resource %s\n", vgpu->id, item);
-	gvt_err("vgpu%d: request %luMB avail %luMB max %luMB taken %luMB\n",
-		vgpu->id, BYTES_TO_MB(request), BYTES_TO_MB(avail),
+	gvt_vgpu_err("fail to allocate resource %s\n", item);
+	gvt_vgpu_err("request %luMB avail %luMB max %luMB taken %luMB\n",
+		BYTES_TO_MB(request), BYTES_TO_MB(avail),
 		BYTES_TO_MB(max), BYTES_TO_MB(taken));
 	return -ENOSPC;
 }
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 4a6a2ed65732..40af17ec6312 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -41,6 +41,54 @@ enum {
 	INTEL_GVT_PCI_BAR_MAX,
 };
 
+/* bitmap for writable bits (RW or RW1C bits, but cannot co-exist in one
+ * byte) byte by byte in standard pci configuration space. (not the full
+ * 256 bytes.)
+ */
+static const u8 pci_cfg_space_rw_bmp[PCI_INTERRUPT_LINE + 4] = {
+	[PCI_COMMAND]		= 0xff, 0x07,
+	[PCI_STATUS]		= 0x00, 0xf9, /* the only one RW1C byte */
+	[PCI_CACHE_LINE_SIZE]	= 0xff,
+	[PCI_BASE_ADDRESS_0 ... PCI_CARDBUS_CIS - 1] = 0xff,
+	[PCI_ROM_ADDRESS]	= 0x01, 0xf8, 0xff, 0xff,
+	[PCI_INTERRUPT_LINE]	= 0xff,
+};
+
+/**
+ * vgpu_pci_cfg_mem_write - write virtual cfg space memory
+ *
+ * Use this function to write virtual cfg space memory.
+ * For standard cfg space, only RW bits can be changed,
+ * and we emulates the RW1C behavior of PCI_STATUS register.
+ */
+static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off,
+				   u8 *src, unsigned int bytes)
+{
+	u8 *cfg_base = vgpu_cfg_space(vgpu);
+	u8 mask, new, old;
+	int i = 0;
+
+	for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) {
+		mask = pci_cfg_space_rw_bmp[off + i];
+		old = cfg_base[off + i];
+		new = src[i] & mask;
+
+		/**
+		 * The PCI_STATUS high byte has RW1C bits, here
+		 * emulates clear by writing 1 for these bits.
+		 * Writing a 0b to RW1C bits has no effect.
+		 */
+		if (off + i == PCI_STATUS + 1)
+			new = (~new & old) & mask;
+
+		cfg_base[off + i] = (old & ~mask) | new;
+	}
+
+	/* For other configuration space directly copy as it is. */
+	if (i < bytes)
+		memcpy(cfg_base + off + i, src + i, bytes - i);
+}
+
 /**
  * intel_vgpu_emulate_cfg_read - emulate vGPU configuration space read
  *
@@ -123,7 +171,7 @@ static int emulate_pci_command_write(struct intel_vgpu *vgpu,
 	u8 changed = old ^ new;
 	int ret;
 
-	memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+	vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
 	if (!(changed & PCI_COMMAND_MEMORY))
 		return 0;
 
@@ -274,10 +322,10 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset,
 		if (ret)
 			return ret;
 
-		memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+		vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
 		break;
 	default:
-		memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+		vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
 		break;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b9c8e2407682..2b92cc8a7d1a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -668,7 +668,7 @@ static inline void print_opcode(u32 cmd, int ring_id)
 	if (d_info == NULL)
 		return;
 
-	gvt_err("opcode=0x%x %s sub_ops:",
+	gvt_dbg_cmd("opcode=0x%x %s sub_ops:",
 			cmd >> (32 - d_info->op_len), d_info->name);
 
 	for (i = 0; i < d_info->nr_sub_op; i++)
@@ -693,23 +693,23 @@ static void parser_exec_state_dump(struct parser_exec_state *s)
 	int cnt = 0;
 	int i;
 
-	gvt_err("  vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)"
+	gvt_dbg_cmd("  vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)"
 			" ring_head(%08lx) ring_tail(%08lx)\n", s->vgpu->id,
 			s->ring_id, s->ring_start, s->ring_start + s->ring_size,
 			s->ring_head, s->ring_tail);
 
-	gvt_err("  %s %s ip_gma(%08lx) ",
+	gvt_dbg_cmd("  %s %s ip_gma(%08lx) ",
 			s->buf_type == RING_BUFFER_INSTRUCTION ?
 			"RING_BUFFER" : "BATCH_BUFFER",
 			s->buf_addr_type == GTT_BUFFER ?
 			"GTT" : "PPGTT", s->ip_gma);
 
 	if (s->ip_va == NULL) {
-		gvt_err(" ip_va(NULL)");
+		gvt_dbg_cmd(" ip_va(NULL)");
 		return;
 	}
 
-	gvt_err("  ip_va=%p: %08x %08x %08x %08x\n",
+	gvt_dbg_cmd("  ip_va=%p: %08x %08x %08x %08x\n",
 			s->ip_va, cmd_val(s, 0), cmd_val(s, 1),
 			cmd_val(s, 2), cmd_val(s, 3));
 
@@ -817,6 +817,25 @@ static bool is_shadowed_mmio(unsigned int offset)
 	return ret;
 }
 
+static inline bool is_force_nonpriv_mmio(unsigned int offset)
+{
+	return (offset >= 0x24d0 && offset < 0x2500);
+}
+
+static int force_nonpriv_reg_handler(struct parser_exec_state *s,
+				     unsigned int offset, unsigned int index)
+{
+	struct intel_gvt *gvt = s->vgpu->gvt;
+	unsigned int data = cmd_val(s, index + 1);
+
+	if (!intel_gvt_in_force_nonpriv_whitelist(gvt, data)) {
+		gvt_err("Unexpected forcenonpriv 0x%x LRI write, value=0x%x\n",
+			offset, data);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int cmd_reg_handler(struct parser_exec_state *s,
 	unsigned int offset, unsigned int index, char *cmd)
 {
@@ -824,23 +843,26 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 	struct intel_gvt *gvt = vgpu->gvt;
 
 	if (offset + 4 > gvt->device_info.mmio_size) {
-		gvt_err("%s access to (%x) outside of MMIO range\n",
+		gvt_vgpu_err("%s access to (%x) outside of MMIO range\n",
 				cmd, offset);
 		return -EINVAL;
 	}
 
 	if (!intel_gvt_mmio_is_cmd_access(gvt, offset)) {
-		gvt_err("vgpu%d: %s access to non-render register (%x)\n",
-				s->vgpu->id, cmd, offset);
+		gvt_vgpu_err("%s access to non-render register (%x)\n",
+				cmd, offset);
 		return 0;
 	}
 
 	if (is_shadowed_mmio(offset)) {
-		gvt_err("vgpu%d: found access of shadowed MMIO %x\n",
-				s->vgpu->id, offset);
+		gvt_vgpu_err("found access of shadowed MMIO %x\n", offset);
 		return 0;
 	}
 
+	if (is_force_nonpriv_mmio(offset) &&
+	    force_nonpriv_reg_handler(s, offset, index))
+		return -EINVAL;
+
 	if (offset == i915_mmio_reg_offset(DERRMR) ||
 		offset == i915_mmio_reg_offset(FORCEWAKE_MT)) {
 		/* Writing to HW VGT_PVINFO_PAGE offset will be discarded */
@@ -1008,7 +1030,7 @@ static int cmd_handler_pipe_control(struct parser_exec_state *s)
 			ret = cmd_reg_handler(s, 0x2358, 1, "pipe_ctrl");
 		else if (post_sync == 1) {
 			/* check ggtt*/
-			if ((cmd_val(s, 2) & (1 << 2))) {
+			if ((cmd_val(s, 1) & PIPE_CONTROL_GLOBAL_GTT_IVB)) {
 				gma = cmd_val(s, 2) & GENMASK(31, 3);
 				if (gmadr_bytes == 8)
 					gma |= (cmd_gma_hi(s, 3)) << 32;
@@ -1129,6 +1151,7 @@ static int skl_decode_mi_display_flip(struct parser_exec_state *s,
 		struct mi_display_flip_command_info *info)
 {
 	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
+	struct intel_vgpu *vgpu = s->vgpu;
 	u32 dword0 = cmd_val(s, 0);
 	u32 dword1 = cmd_val(s, 1);
 	u32 dword2 = cmd_val(s, 2);
@@ -1167,7 +1190,7 @@ static int skl_decode_mi_display_flip(struct parser_exec_state *s,
 		break;
 
 	default:
-		gvt_err("unknown plane code %d\n", plane);
+		gvt_vgpu_err("unknown plane code %d\n", plane);
 		return -EINVAL;
 	}
 
@@ -1274,25 +1297,26 @@ static int update_plane_mmio_from_mi_display_flip(
 static int cmd_handler_mi_display_flip(struct parser_exec_state *s)
 {
 	struct mi_display_flip_command_info info;
+	struct intel_vgpu *vgpu = s->vgpu;
 	int ret;
 	int i;
 	int len = cmd_length(s);
 
 	ret = decode_mi_display_flip(s, &info);
 	if (ret) {
-		gvt_err("fail to decode MI display flip command\n");
+		gvt_vgpu_err("fail to decode MI display flip command\n");
 		return ret;
 	}
 
 	ret = check_mi_display_flip(s, &info);
 	if (ret) {
-		gvt_err("invalid MI display flip command\n");
+		gvt_vgpu_err("invalid MI display flip command\n");
 		return ret;
 	}
 
 	ret = update_plane_mmio_from_mi_display_flip(s, &info);
 	if (ret) {
-		gvt_err("fail to update plane mmio\n");
+		gvt_vgpu_err("fail to update plane mmio\n");
 		return ret;
 	}
 
@@ -1350,7 +1374,8 @@ static inline int cmd_address_audit(struct parser_exec_state *s,
 	int ret;
 
 	if (op_size > max_surface_size) {
-		gvt_err("command address audit fail name %s\n", s->info->name);
+		gvt_vgpu_err("command address audit fail name %s\n",
+			s->info->name);
 		return -EINVAL;
 	}
 
@@ -1367,7 +1392,7 @@ static inline int cmd_address_audit(struct parser_exec_state *s,
 	}
 	return 0;
 err:
-	gvt_err("cmd_parser: Malicious %s detected, addr=0x%lx, len=%d!\n",
+	gvt_vgpu_err("cmd_parser: Malicious %s detected, addr=0x%lx, len=%d!\n",
 			s->info->name, guest_gma, op_size);
 
 	pr_err("cmd dump: ");
@@ -1412,8 +1437,10 @@ static int cmd_handler_mi_store_data_imm(struct parser_exec_state *s)
 
 static inline int unexpected_cmd(struct parser_exec_state *s)
 {
-	gvt_err("vgpu%d: Unexpected %s in command buffer!\n",
-			s->vgpu->id, s->info->name);
+	struct intel_vgpu *vgpu = s->vgpu;
+
+	gvt_vgpu_err("Unexpected %s in command buffer!\n", s->info->name);
+
 	return -EINVAL;
 }
 
@@ -1516,7 +1543,7 @@ static int copy_gma_to_hva(struct intel_vgpu *vgpu, struct intel_vgpu_mm *mm,
 	while (gma != end_gma) {
 		gpa = intel_vgpu_gma_to_gpa(mm, gma);
 		if (gpa == INTEL_GVT_INVALID_ADDR) {
-			gvt_err("invalid gma address: %lx\n", gma);
+			gvt_vgpu_err("invalid gma address: %lx\n", gma);
 			return -EFAULT;
 		}
 
@@ -1557,6 +1584,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
 	uint32_t bb_size = 0;
 	uint32_t cmd_len = 0;
 	bool met_bb_end = false;
+	struct intel_vgpu *vgpu = s->vgpu;
 	u32 cmd;
 
 	/* get the start gm address of the batch buffer */
@@ -1565,7 +1593,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
 
 	info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
 	if (info == NULL) {
-		gvt_err("unknown cmd 0x%x, opcode=0x%x\n",
+		gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
 				cmd, get_opcode(cmd, s->ring_id));
 		return -EINVAL;
 	}
@@ -1574,7 +1602,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
 				gma, gma + 4, &cmd);
 		info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
 		if (info == NULL) {
-			gvt_err("unknown cmd 0x%x, opcode=0x%x\n",
+			gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
 				cmd, get_opcode(cmd, s->ring_id));
 			return -EINVAL;
 		}
@@ -1599,6 +1627,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
 static int perform_bb_shadow(struct parser_exec_state *s)
 {
 	struct intel_shadow_bb_entry *entry_obj;
+	struct intel_vgpu *vgpu = s->vgpu;
 	unsigned long gma = 0;
 	uint32_t bb_size;
 	void *dst = NULL;
@@ -1633,7 +1662,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 
 	ret = i915_gem_object_set_to_cpu_domain(entry_obj->obj, false);
 	if (ret) {
-		gvt_err("failed to set shadow batch to CPU\n");
+		gvt_vgpu_err("failed to set shadow batch to CPU\n");
 		goto unmap_src;
 	}
 
@@ -1645,7 +1674,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 			      gma, gma + bb_size,
 			      dst);
 	if (ret) {
-		gvt_err("fail to copy guest ring buffer\n");
+		gvt_vgpu_err("fail to copy guest ring buffer\n");
 		goto unmap_src;
 	}
 
@@ -1676,15 +1705,16 @@ static int cmd_handler_mi_batch_buffer_start(struct parser_exec_state *s)
 {
 	bool second_level;
 	int ret = 0;
+	struct intel_vgpu *vgpu = s->vgpu;
 
 	if (s->buf_type == BATCH_BUFFER_2ND_LEVEL) {
-		gvt_err("Found MI_BATCH_BUFFER_START in 2nd level BB\n");
+		gvt_vgpu_err("Found MI_BATCH_BUFFER_START in 2nd level BB\n");
 		return -EINVAL;
 	}
 
 	second_level = BATCH_BUFFER_2ND_LEVEL_BIT(cmd_val(s, 0)) == 1;
 	if (second_level && (s->buf_type != BATCH_BUFFER_INSTRUCTION)) {
-		gvt_err("Jumping to 2nd level BB from RB is not allowed\n");
+		gvt_vgpu_err("Jumping to 2nd level BB from RB is not allowed\n");
 		return -EINVAL;
 	}
 
@@ -1702,7 +1732,7 @@ static int cmd_handler_mi_batch_buffer_start(struct parser_exec_state *s)
 	if (batch_buffer_needs_scan(s)) {
 		ret = perform_bb_shadow(s);
 		if (ret < 0)
-			gvt_err("invalid shadow batch buffer\n");
+			gvt_vgpu_err("invalid shadow batch buffer\n");
 	} else {
 		/* emulate a batch buffer end to do return right */
 		ret = cmd_handler_mi_batch_buffer_end(s);
@@ -2429,6 +2459,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
 	int ret = 0;
 	cycles_t t0, t1, t2;
 	struct parser_exec_state s_before_advance_custom;
+	struct intel_vgpu *vgpu = s->vgpu;
 
 	t0 = get_cycles();
 
@@ -2436,7 +2467,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
 
 	info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
 	if (info == NULL) {
-		gvt_err("unknown cmd 0x%x, opcode=0x%x\n",
+		gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
 				cmd, get_opcode(cmd, s->ring_id));
 		return -EINVAL;
 	}
@@ -2452,7 +2483,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
 	if (info->handler) {
 		ret = info->handler(s);
 		if (ret < 0) {
-			gvt_err("%s handler error\n", info->name);
+			gvt_vgpu_err("%s handler error\n", info->name);
 			return ret;
 		}
 	}
@@ -2463,7 +2494,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
 	if (!(info->flag & F_IP_ADVANCE_CUSTOM)) {
 		ret = cmd_advance_default(s);
 		if (ret) {
-			gvt_err("%s IP advance error\n", info->name);
+			gvt_vgpu_err("%s IP advance error\n", info->name);
 			return ret;
 		}
 	}
@@ -2486,6 +2517,7 @@ static int command_scan(struct parser_exec_state *s,
 
 	unsigned long gma_head, gma_tail, gma_bottom;
 	int ret = 0;
+	struct intel_vgpu *vgpu = s->vgpu;
 
 	gma_head = rb_start + rb_head;
 	gma_tail = rb_start + rb_tail;
@@ -2497,7 +2529,7 @@ static int command_scan(struct parser_exec_state *s,
 		if (s->buf_type == RING_BUFFER_INSTRUCTION) {
 			if (!(s->ip_gma >= rb_start) ||
 				!(s->ip_gma < gma_bottom)) {
-				gvt_err("ip_gma %lx out of ring scope."
+				gvt_vgpu_err("ip_gma %lx out of ring scope."
 					"(base:0x%lx, bottom: 0x%lx)\n",
 					s->ip_gma, rb_start,
 					gma_bottom);
@@ -2505,7 +2537,7 @@ static int command_scan(struct parser_exec_state *s,
 				return -EINVAL;
 			}
 			if (gma_out_of_range(s->ip_gma, gma_head, gma_tail)) {
-				gvt_err("ip_gma %lx out of range."
+				gvt_vgpu_err("ip_gma %lx out of range."
 					"base 0x%lx head 0x%lx tail 0x%lx\n",
 					s->ip_gma, rb_start,
 					rb_head, rb_tail);
@@ -2515,7 +2547,7 @@ static int command_scan(struct parser_exec_state *s,
 		}
 		ret = cmd_parser_exec(s);
 		if (ret) {
-			gvt_err("cmd parser error\n");
+			gvt_vgpu_err("cmd parser error\n");
 			parser_exec_state_dump(s);
 			break;
 		}
@@ -2639,7 +2671,7 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
 				gma_head, gma_top,
 				workload->shadow_ring_buffer_va);
 		if (ret) {
-			gvt_err("fail to copy guest ring buffer\n");
+			gvt_vgpu_err("fail to copy guest ring buffer\n");
 			return ret;
 		}
 		copy_len = gma_top - gma_head;
@@ -2651,7 +2683,7 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
 			gma_head, gma_tail,
 			workload->shadow_ring_buffer_va + copy_len);
 	if (ret) {
-		gvt_err("fail to copy guest ring buffer\n");
+		gvt_vgpu_err("fail to copy guest ring buffer\n");
 		return ret;
 	}
 	ring->tail += workload->rb_len;
@@ -2662,16 +2694,17 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
 int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 {
 	int ret;
+	struct intel_vgpu *vgpu = workload->vgpu;
 
 	ret = shadow_workload_ring_buffer(workload);
 	if (ret) {
-		gvt_err("fail to shadow workload ring_buffer\n");
+		gvt_vgpu_err("fail to shadow workload ring_buffer\n");
 		return ret;
 	}
 
 	ret = scan_workload(workload);
 	if (ret) {
-		gvt_err("scan workload error\n");
+		gvt_vgpu_err("scan workload error\n");
 		return ret;
 	}
 	return 0;
@@ -2681,6 +2714,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
 	int ctx_size = wa_ctx->indirect_ctx.size;
 	unsigned long guest_gma = wa_ctx->indirect_ctx.guest_gma;
+	struct intel_vgpu *vgpu = wa_ctx->workload->vgpu;
 	struct drm_i915_gem_object *obj;
 	int ret = 0;
 	void *map;
@@ -2694,14 +2728,14 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	/* get the va of the shadow batch buffer */
 	map = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(map)) {
-		gvt_err("failed to vmap shadow indirect ctx\n");
+		gvt_vgpu_err("failed to vmap shadow indirect ctx\n");
 		ret = PTR_ERR(map);
 		goto put_obj;
 	}
 
 	ret = i915_gem_object_set_to_cpu_domain(obj, false);
 	if (ret) {
-		gvt_err("failed to set shadow indirect ctx to CPU\n");
+		gvt_vgpu_err("failed to set shadow indirect ctx to CPU\n");
 		goto unmap_src;
 	}
 
@@ -2710,7 +2744,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 				guest_gma, guest_gma + ctx_size,
 				map);
 	if (ret) {
-		gvt_err("fail to copy guest indirect ctx\n");
+		gvt_vgpu_err("fail to copy guest indirect ctx\n");
 		goto unmap_src;
 	}
 
@@ -2744,13 +2778,14 @@ static int combine_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
 	int ret;
+	struct intel_vgpu *vgpu = wa_ctx->workload->vgpu;
 
 	if (wa_ctx->indirect_ctx.size == 0)
 		return 0;
 
 	ret = shadow_indirect_ctx(wa_ctx);
 	if (ret) {
-		gvt_err("fail to shadow indirect ctx\n");
+		gvt_vgpu_err("fail to shadow indirect ctx\n");
 		return ret;
 	}
 
@@ -2758,7 +2793,7 @@ int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 
 	ret = scan_wa_ctx(wa_ctx);
 	if (ret) {
-		gvt_err("scan wa ctx error\n");
+		gvt_vgpu_err("scan wa ctx error\n");
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/i915/gvt/debug.h b/drivers/gpu/drm/i915/gvt/debug.h
index 68cba7bd980a..b0cff4dc2684 100644
--- a/drivers/gpu/drm/i915/gvt/debug.h
+++ b/drivers/gpu/drm/i915/gvt/debug.h
@@ -27,6 +27,14 @@
 #define gvt_err(fmt, args...) \
 	DRM_ERROR("gvt: "fmt, ##args)
 
+#define gvt_vgpu_err(fmt, args...)					\
+do {									\
+	if (IS_ERR_OR_NULL(vgpu))					\
+		DRM_DEBUG_DRIVER("gvt: "fmt, ##args);			\
+	else								\
+		DRM_DEBUG_DRIVER("gvt: vgpu %d: "fmt, vgpu->id, ##args);\
+} while (0)
+
 #define gvt_dbg_core(fmt, args...) \
 	DRM_DEBUG_DRIVER("gvt: core: "fmt, ##args)
 
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8fde880c39..5419ae6ec633 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -83,44 +83,80 @@ static int pipe_is_enabled(struct intel_vgpu *vgpu, int pipe)
 	return 0;
 }
 
+static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = {
+	{
+/* EDID with 1024x768 as its resolution */
+		/*Header*/
+		0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+		/* Vendor & Product Identification */
+		0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
+		/* Version & Revision */
+		0x01, 0x04,
+		/* Basic Display Parameters & Features */
+		0xa5, 0x34, 0x20, 0x78, 0x23,
+		/* Color Characteristics */
+		0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
+		/* Established Timings: maximum resolution is 1024x768 */
+		0x21, 0x08, 0x00,
+		/* Standard Timings. All invalid */
+		0x00, 0xc0, 0x00, 0xc0, 0x00, 0x40, 0x00, 0x80, 0x00, 0x00,
+		0x00, 0x40, 0x00, 0x00, 0x00, 0x01,
+		/* 18 Byte Data Blocks 1: invalid */
+		0x00, 0x00, 0x80, 0xa0, 0x70, 0xb0,
+		0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
+		/* 18 Byte Data Blocks 2: invalid */
+		0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
+		0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+		/* 18 Byte Data Blocks 3: invalid */
+		0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
+		0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
+		/* 18 Byte Data Blocks 4: invalid */
+		0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
+		0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
+		/* Extension Block Count */
+		0x00,
+		/* Checksum */
+		0xef,
+	},
+	{
 /* EDID with 1920x1200 as its resolution */
-static unsigned char virtual_dp_monitor_edid[] = {
-	/*Header*/
-	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
-	/* Vendor & Product Identification */
-	0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
-	/* Version & Revision */
-	0x01, 0x04,
-	/* Basic Display Parameters & Features */
-	0xa5, 0x34, 0x20, 0x78, 0x23,
-	/* Color Characteristics */
-	0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
-	/* Established Timings: maximum resolution is 1024x768 */
-	0x21, 0x08, 0x00,
-	/*
-	 * Standard Timings.
-	 * below new resolutions can be supported:
-	 * 1920x1080, 1280x720, 1280x960, 1280x1024,
-	 * 1440x900, 1600x1200, 1680x1050
-	 */
-	0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00,
-	0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01,
-	/* 18 Byte Data Blocks 1: max resolution is 1920x1200 */
-	0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0,
-	0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
-	/* 18 Byte Data Blocks 2: invalid */
-	0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
-	0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-	/* 18 Byte Data Blocks 3: invalid */
-	0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
-	0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
-	/* 18 Byte Data Blocks 4: invalid */
-	0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
-	0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
-	/* Extension Block Count */
-	0x00,
-	/* Checksum */
-	0x45,
+		/*Header*/
+		0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+		/* Vendor & Product Identification */
+		0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
+		/* Version & Revision */
+		0x01, 0x04,
+		/* Basic Display Parameters & Features */
+		0xa5, 0x34, 0x20, 0x78, 0x23,
+		/* Color Characteristics */
+		0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
+		/* Established Timings: maximum resolution is 1024x768 */
+		0x21, 0x08, 0x00,
+		/*
+		 * Standard Timings.
+		 * below new resolutions can be supported:
+		 * 1920x1080, 1280x720, 1280x960, 1280x1024,
+		 * 1440x900, 1600x1200, 1680x1050
+		 */
+		0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00,
+		0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01,
+		/* 18 Byte Data Blocks 1: max resolution is 1920x1200 */
+		0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0,
+		0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
+		/* 18 Byte Data Blocks 2: invalid */
+		0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
+		0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+		/* 18 Byte Data Blocks 3: invalid */
+		0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
+		0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
+		/* 18 Byte Data Blocks 4: invalid */
+		0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
+		0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
+		/* Extension Block Count */
+		0x00,
+		/* Checksum */
+		0x45,
+	},
 };
 
 #define DPCD_HEADER_SIZE        0xb
@@ -140,14 +176,20 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 		vgpu_vreg(vgpu, SDEISR) &= ~(SDE_PORTA_HOTPLUG_SPT |
 				SDE_PORTE_HOTPLUG_SPT);
 
-	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B))
+	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTB_HOTPLUG_CPT;
+		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
+	}
 
-	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C))
+	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
+		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED;
+	}
 
-	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D))
+	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
+		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED;
+	}
 
 	if (IS_SKYLAKE(dev_priv) &&
 			intel_vgpu_has_monitor_on_port(vgpu, PORT_E)) {
@@ -160,6 +202,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				GEN8_PORT_DP_A_HOTPLUG;
 		else
 			vgpu_vreg(vgpu, SDEISR) |= SDE_PORTA_HOTPLUG_SPT;
+
+		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_A)) |= DDI_INIT_DISPLAY_DETECTED;
 	}
 }
 
@@ -175,10 +219,13 @@ static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num)
 }
 
 static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
-		int type)
+				    int type, unsigned int resolution)
 {
 	struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num);
 
+	if (WARN_ON(resolution >= GVT_EDID_NUM))
+		return -EINVAL;
+
 	port->edid = kzalloc(sizeof(*(port->edid)), GFP_KERNEL);
 	if (!port->edid)
 		return -ENOMEM;
@@ -189,7 +236,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
 		return -ENOMEM;
 	}
 
-	memcpy(port->edid->edid_block, virtual_dp_monitor_edid,
+	memcpy(port->edid->edid_block, virtual_dp_monitor_edid[resolution],
 			EDID_SIZE);
 	port->edid->data_valid = true;
 
@@ -322,16 +369,18 @@ void intel_vgpu_clean_display(struct intel_vgpu *vgpu)
  * Zero on success, negative error code if failed.
  *
  */
-int intel_vgpu_init_display(struct intel_vgpu *vgpu)
+int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
 	intel_vgpu_init_i2c_edid(vgpu);
 
 	if (IS_SKYLAKE(dev_priv))
-		return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D);
+		return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D,
+						resolution);
 	else
-		return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B);
+		return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B,
+						resolution);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h
index 8b234ea961f6..d73de22102e2 100644
--- a/drivers/gpu/drm/i915/gvt/display.h
+++ b/drivers/gpu/drm/i915/gvt/display.h
@@ -154,10 +154,28 @@ struct intel_vgpu_port {
 	int type;
 };
 
+enum intel_vgpu_edid {
+	GVT_EDID_1024_768,
+	GVT_EDID_1920_1200,
+	GVT_EDID_NUM,
+};
+
+static inline char *vgpu_edid_str(enum intel_vgpu_edid id)
+{
+	switch (id) {
+	case GVT_EDID_1024_768:
+		return "1024x768";
+	case GVT_EDID_1920_1200:
+		return "1920x1200";
+	default:
+		return "";
+	}
+}
+
 void intel_gvt_emulate_vblank(struct intel_gvt *gvt);
 void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt);
 
-int intel_vgpu_init_display(struct intel_vgpu *vgpu);
+int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution);
 void intel_vgpu_reset_display(struct intel_vgpu *vgpu);
 void intel_vgpu_clean_display(struct intel_vgpu *vgpu);
 
diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c
index bda85dff7b2a..42cd09ec63fa 100644
--- a/drivers/gpu/drm/i915/gvt/edid.c
+++ b/drivers/gpu/drm/i915/gvt/edid.c
@@ -52,16 +52,16 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
 	unsigned char chr = 0;
 
 	if (edid->state == I2C_NOT_SPECIFIED || !edid->slave_selected) {
-		gvt_err("Driver tries to read EDID without proper sequence!\n");
+		gvt_vgpu_err("Driver tries to read EDID without proper sequence!\n");
 		return 0;
 	}
 	if (edid->current_edid_read >= EDID_SIZE) {
-		gvt_err("edid_get_byte() exceeds the size of EDID!\n");
+		gvt_vgpu_err("edid_get_byte() exceeds the size of EDID!\n");
 		return 0;
 	}
 
 	if (!edid->edid_available) {
-		gvt_err("Reading EDID but EDID is not available!\n");
+		gvt_vgpu_err("Reading EDID but EDID is not available!\n");
 		return 0;
 	}
 
@@ -72,7 +72,7 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
 		chr = edid_data->edid_block[edid->current_edid_read];
 		edid->current_edid_read++;
 	} else {
-		gvt_err("No EDID available during the reading?\n");
+		gvt_vgpu_err("No EDID available during the reading?\n");
 	}
 	return chr;
 }
@@ -223,7 +223,7 @@ static int gmbus1_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 			vgpu_vreg(vgpu, PCH_GMBUS2) |= GMBUS_ACTIVE;
 			break;
 		default:
-			gvt_err("Unknown/reserved GMBUS cycle detected!\n");
+			gvt_vgpu_err("Unknown/reserved GMBUS cycle detected!\n");
 			break;
 		}
 		/*
@@ -292,8 +292,7 @@ static int gmbus3_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 		 */
 	} else {
 		memcpy(p_data, &vgpu_vreg(vgpu, offset), bytes);
-		gvt_err("vgpu%d: warning: gmbus3 read with nothing returned\n",
-				vgpu->id);
+		gvt_vgpu_err("warning: gmbus3 read with nothing returned\n");
 	}
 	return 0;
 }
@@ -496,7 +495,8 @@ void intel_gvt_i2c_handle_aux_ch_write(struct intel_vgpu *vgpu,
 			unsigned char val = edid_get_byte(vgpu);
 
 			aux_data_for_write = (val << 16);
-		}
+		} else
+			aux_data_for_write = (0xff << 16);
 	}
 	/* write the return value in AUX_CH_DATA reg which includes:
 	 * ACK of I2C_WRITE
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 46eb9fd3c03f..d186c157f65f 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -172,6 +172,7 @@ static int emulate_execlist_ctx_schedule_out(
 		struct intel_vgpu_execlist *execlist,
 		struct execlist_ctx_descriptor_format *ctx)
 {
+	struct intel_vgpu *vgpu = execlist->vgpu;
 	struct intel_vgpu_execlist_slot *running = execlist->running_slot;
 	struct intel_vgpu_execlist_slot *pending = execlist->pending_slot;
 	struct execlist_ctx_descriptor_format *ctx0 = &running->ctx[0];
@@ -183,7 +184,7 @@ static int emulate_execlist_ctx_schedule_out(
 	gvt_dbg_el("schedule out context id %x\n", ctx->context_id);
 
 	if (WARN_ON(!same_context(ctx, execlist->running_context))) {
-		gvt_err("schedule out context is not running context,"
+		gvt_vgpu_err("schedule out context is not running context,"
 				"ctx id %x running ctx id %x\n",
 				ctx->context_id,
 				execlist->running_context->context_id);
@@ -254,7 +255,7 @@ static struct intel_vgpu_execlist_slot *get_next_execlist_slot(
 	status.udw = vgpu_vreg(vgpu, status_reg + 4);
 
 	if (status.execlist_queue_full) {
-		gvt_err("virtual execlist slots are full\n");
+		gvt_vgpu_err("virtual execlist slots are full\n");
 		return NULL;
 	}
 
@@ -270,11 +271,12 @@ static int emulate_execlist_schedule_in(struct intel_vgpu_execlist *execlist,
 
 	struct execlist_ctx_descriptor_format *ctx0, *ctx1;
 	struct execlist_context_status_format status;
+	struct intel_vgpu *vgpu = execlist->vgpu;
 
 	gvt_dbg_el("emulate schedule-in\n");
 
 	if (!slot) {
-		gvt_err("no available execlist slot\n");
+		gvt_vgpu_err("no available execlist slot\n");
 		return -EINVAL;
 	}
 
@@ -375,7 +377,6 @@ static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 
 		vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0);
 		if (IS_ERR(vma)) {
-			gvt_err("Cannot pin\n");
 			return;
 		}
 
@@ -428,7 +429,6 @@ static void prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	vma = i915_gem_object_ggtt_pin(wa_ctx->indirect_ctx.obj, NULL,
 				       0, CACHELINE_BYTES, 0);
 	if (IS_ERR(vma)) {
-		gvt_err("Cannot pin indirect ctx obj\n");
 		return;
 	}
 
@@ -561,6 +561,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 {
 	struct execlist_ctx_descriptor_format *desc = &workload->ctx_desc;
 	struct intel_vgpu_mm *mm;
+	struct intel_vgpu *vgpu = workload->vgpu;
 	int page_table_level;
 	u32 pdp[8];
 
@@ -569,7 +570,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 	} else if (desc->addressing_mode == 3) { /* legacy 64 bit */
 		page_table_level = 4;
 	} else {
-		gvt_err("Advanced Context mode(SVM) is not supported!\n");
+		gvt_vgpu_err("Advanced Context mode(SVM) is not supported!\n");
 		return -EINVAL;
 	}
 
@@ -583,7 +584,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 		mm = intel_vgpu_create_mm(workload->vgpu, INTEL_GVT_MM_PPGTT,
 				pdp, page_table_level, 0);
 		if (IS_ERR(mm)) {
-			gvt_err("fail to create mm object.\n");
+			gvt_vgpu_err("fail to create mm object.\n");
 			return PTR_ERR(mm);
 		}
 	}
@@ -609,7 +610,7 @@ static int submit_context(struct intel_vgpu *vgpu, int ring_id,
 	ring_context_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm,
 			(u32)((desc->lrca + 1) << GTT_PAGE_SHIFT));
 	if (ring_context_gpa == INTEL_GVT_INVALID_ADDR) {
-		gvt_err("invalid guest context LRCA: %x\n", desc->lrca);
+		gvt_vgpu_err("invalid guest context LRCA: %x\n", desc->lrca);
 		return -EINVAL;
 	}
 
@@ -724,8 +725,7 @@ int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id)
 			continue;
 
 		if (!desc[i]->privilege_access) {
-			gvt_err("vgpu%d: unexpected GGTT elsp submission\n",
-					vgpu->id);
+			gvt_vgpu_err("unexpected GGTT elsp submission\n");
 			return -EINVAL;
 		}
 
@@ -735,15 +735,13 @@ int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id)
 	}
 
 	if (!valid_desc_bitmap) {
-		gvt_err("vgpu%d: no valid desc in a elsp submission\n",
-				vgpu->id);
+		gvt_vgpu_err("no valid desc in a elsp submission\n");
 		return -EINVAL;
 	}
 
 	if (!test_bit(0, (void *)&valid_desc_bitmap) &&
 			test_bit(1, (void *)&valid_desc_bitmap)) {
-		gvt_err("vgpu%d: weird elsp submission, desc 0 is not valid\n",
-				vgpu->id);
+		gvt_vgpu_err("weird elsp submission, desc 0 is not valid\n");
 		return -EINVAL;
 	}
 
@@ -752,8 +750,7 @@ int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id)
 		ret = submit_context(vgpu, ring_id, &valid_desc[i],
 				emulate_schedule_in);
 		if (ret) {
-			gvt_err("vgpu%d: fail to schedule workload\n",
-					vgpu->id);
+			gvt_vgpu_err("fail to schedule workload\n");
 			return ret;
 		}
 		emulate_schedule_in = false;
@@ -778,7 +775,8 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu, int ring_id)
 			_EL_OFFSET_STATUS_PTR);
 
 	ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
-	ctx_status_ptr.read_ptr = ctx_status_ptr.write_ptr = 0x7;
+	ctx_status_ptr.read_ptr = 0;
+	ctx_status_ptr.write_ptr = 0x7;
 	vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c
index 1cb29b2d7dc6..dce8d15f706f 100644
--- a/drivers/gpu/drm/i915/gvt/firmware.c
+++ b/drivers/gpu/drm/i915/gvt/firmware.c
@@ -75,12 +75,12 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt)
 	struct gvt_firmware_header *h;
 	void *firmware;
 	void *p;
-	unsigned long size;
+	unsigned long size, crc32_start;
 	int i;
 	int ret;
 
-	size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1;
-	firmware = vmalloc(size);
+	size = sizeof(*h) + info->mmio_size + info->cfg_space_size;
+	firmware = vzalloc(size);
 	if (!firmware)
 		return -ENOMEM;
 
@@ -112,6 +112,9 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt)
 
 	memcpy(gvt->firmware.mmio, p, info->mmio_size);
 
+	crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;
+	h->crc32 = crc32_le(0, firmware + crc32_start, size - crc32_start);
+
 	firmware_attr.size = size;
 	firmware_attr.private = firmware;
 
@@ -234,7 +237,7 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt)
 
 	firmware->mmio = mem;
 
-	sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%04x.golden_hw_state",
+	sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%02x.golden_hw_state",
 		 GVT_FIRMWARE_PATH, pdev->vendor, pdev->device,
 		 pdev->revision);
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 28c92346db0e..b832bea64e03 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -49,8 +49,8 @@ bool intel_gvt_ggtt_validate_range(struct intel_vgpu *vgpu, u64 addr, u32 size)
 {
 	if ((!vgpu_gmadr_is_valid(vgpu, addr)) || (size
 			&& !vgpu_gmadr_is_valid(vgpu, addr + size - 1))) {
-		gvt_err("vgpu%d: invalid range gmadr 0x%llx size 0x%x\n",
-				vgpu->id, addr, size);
+		gvt_vgpu_err("invalid range gmadr 0x%llx size 0x%x\n",
+				addr, size);
 		return false;
 	}
 	return true;
@@ -430,7 +430,7 @@ static int gtt_entry_p2m(struct intel_vgpu *vgpu, struct intel_gvt_gtt_entry *p,
 
 	mfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, gfn);
 	if (mfn == INTEL_GVT_INVALID_ADDR) {
-		gvt_err("fail to translate gfn: 0x%lx\n", gfn);
+		gvt_vgpu_err("fail to translate gfn: 0x%lx\n", gfn);
 		return -ENXIO;
 	}
 
@@ -611,7 +611,7 @@ static inline int init_shadow_page(struct intel_vgpu *vgpu,
 
 	daddr = dma_map_page(kdev, p->page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(kdev, daddr)) {
-		gvt_err("fail to map dma addr\n");
+		gvt_vgpu_err("fail to map dma addr\n");
 		return -EINVAL;
 	}
 
@@ -735,7 +735,7 @@ retry:
 		if (reclaim_one_mm(vgpu->gvt))
 			goto retry;
 
-		gvt_err("fail to allocate ppgtt shadow page\n");
+		gvt_vgpu_err("fail to allocate ppgtt shadow page\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -750,14 +750,14 @@ retry:
 	 */
 	ret = init_shadow_page(vgpu, &spt->shadow_page, type);
 	if (ret) {
-		gvt_err("fail to initialize shadow page for spt\n");
+		gvt_vgpu_err("fail to initialize shadow page for spt\n");
 		goto err;
 	}
 
 	ret = intel_vgpu_init_guest_page(vgpu, &spt->guest_page,
 			gfn, ppgtt_write_protection_handler, NULL);
 	if (ret) {
-		gvt_err("fail to initialize guest page for spt\n");
+		gvt_vgpu_err("fail to initialize guest page for spt\n");
 		goto err;
 	}
 
@@ -776,8 +776,7 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_find_shadow_page(
 	if (p)
 		return shadow_page_to_ppgtt_spt(p);
 
-	gvt_err("vgpu%d: fail to find ppgtt shadow page: 0x%lx\n",
-			vgpu->id, mfn);
+	gvt_vgpu_err("fail to find ppgtt shadow page: 0x%lx\n", mfn);
 	return NULL;
 }
 
@@ -827,8 +826,8 @@ static int ppgtt_invalidate_shadow_page_by_shadow_entry(struct intel_vgpu *vgpu,
 	}
 	s = ppgtt_find_shadow_page(vgpu, ops->get_pfn(e));
 	if (!s) {
-		gvt_err("vgpu%d: fail to find shadow page: mfn: 0x%lx\n",
-				vgpu->id, ops->get_pfn(e));
+		gvt_vgpu_err("fail to find shadow page: mfn: 0x%lx\n",
+				ops->get_pfn(e));
 		return -ENXIO;
 	}
 	return ppgtt_invalidate_shadow_page(s);
@@ -836,6 +835,7 @@ static int ppgtt_invalidate_shadow_page_by_shadow_entry(struct intel_vgpu *vgpu,
 
 static int ppgtt_invalidate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 {
+	struct intel_vgpu *vgpu = spt->vgpu;
 	struct intel_gvt_gtt_entry e;
 	unsigned long index;
 	int ret;
@@ -854,7 +854,7 @@ static int ppgtt_invalidate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 
 	for_each_present_shadow_entry(spt, &e, index) {
 		if (!gtt_type_is_pt(get_next_pt_type(e.type))) {
-			gvt_err("GVT doesn't support pse bit for now\n");
+			gvt_vgpu_err("GVT doesn't support pse bit for now\n");
 			return -EINVAL;
 		}
 		ret = ppgtt_invalidate_shadow_page_by_shadow_entry(
@@ -868,8 +868,8 @@ release:
 	ppgtt_free_shadow_page(spt);
 	return 0;
 fail:
-	gvt_err("vgpu%d: fail: shadow page %p shadow entry 0x%llx type %d\n",
-			spt->vgpu->id, spt, e.val64, e.type);
+	gvt_vgpu_err("fail: shadow page %p shadow entry 0x%llx type %d\n",
+			spt, e.val64, e.type);
 	return ret;
 }
 
@@ -914,8 +914,8 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_shadow_page_by_guest_entry(
 	}
 	return s;
 fail:
-	gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d\n",
-			vgpu->id, s, we->val64, we->type);
+	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
+			s, we->val64, we->type);
 	return ERR_PTR(ret);
 }
 
@@ -953,7 +953,7 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 
 	for_each_present_guest_entry(spt, &ge, i) {
 		if (!gtt_type_is_pt(get_next_pt_type(ge.type))) {
-			gvt_err("GVT doesn't support pse bit now\n");
+			gvt_vgpu_err("GVT doesn't support pse bit now\n");
 			ret = -EINVAL;
 			goto fail;
 		}
@@ -969,8 +969,8 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 	}
 	return 0;
 fail:
-	gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d\n",
-			vgpu->id, spt, ge.val64, ge.type);
+	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
+			spt, ge.val64, ge.type);
 	return ret;
 }
 
@@ -999,7 +999,7 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_guest_page *gpt,
 		struct intel_vgpu_ppgtt_spt *s =
 			ppgtt_find_shadow_page(vgpu, ops->get_pfn(&e));
 		if (!s) {
-			gvt_err("fail to find guest page\n");
+			gvt_vgpu_err("fail to find guest page\n");
 			ret = -ENXIO;
 			goto fail;
 		}
@@ -1011,8 +1011,8 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_guest_page *gpt,
 	ppgtt_set_shadow_entry(spt, &e, index);
 	return 0;
 fail:
-	gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d\n",
-			vgpu->id, spt, e.val64, e.type);
+	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
+			spt, e.val64, e.type);
 	return ret;
 }
 
@@ -1046,8 +1046,8 @@ static int ppgtt_handle_guest_entry_add(struct intel_vgpu_guest_page *gpt,
 	}
 	return 0;
 fail:
-	gvt_err("vgpu%d: fail: spt %p guest entry 0x%llx type %d\n", vgpu->id,
-			spt, we->val64, we->type);
+	gvt_vgpu_err("fail: spt %p guest entry 0x%llx type %d\n",
+		spt, we->val64, we->type);
 	return ret;
 }
 
@@ -1250,8 +1250,8 @@ static int ppgtt_handle_guest_write_page_table(
 	}
 	return 0;
 fail:
-	gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d.\n",
-			vgpu->id, spt, we->val64, we->type);
+	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d.\n",
+			spt, we->val64, we->type);
 	return ret;
 }
 
@@ -1493,7 +1493,7 @@ static int shadow_mm(struct intel_vgpu_mm *mm)
 
 		spt = ppgtt_populate_shadow_page_by_guest_entry(vgpu, &ge);
 		if (IS_ERR(spt)) {
-			gvt_err("fail to populate guest root pointer\n");
+			gvt_vgpu_err("fail to populate guest root pointer\n");
 			ret = PTR_ERR(spt);
 			goto fail;
 		}
@@ -1566,7 +1566,7 @@ struct intel_vgpu_mm *intel_vgpu_create_mm(struct intel_vgpu *vgpu,
 
 	ret = gtt->mm_alloc_page_table(mm);
 	if (ret) {
-		gvt_err("fail to allocate page table for mm\n");
+		gvt_vgpu_err("fail to allocate page table for mm\n");
 		goto fail;
 	}
 
@@ -1584,7 +1584,7 @@ struct intel_vgpu_mm *intel_vgpu_create_mm(struct intel_vgpu *vgpu,
 	}
 	return mm;
 fail:
-	gvt_err("fail to create mm\n");
+	gvt_vgpu_err("fail to create mm\n");
 	if (mm)
 		intel_gvt_mm_unreference(mm);
 	return ERR_PTR(ret);
@@ -1760,7 +1760,7 @@ unsigned long intel_vgpu_gma_to_gpa(struct intel_vgpu_mm *mm, unsigned long gma)
 			mm->page_table_level, gma, gpa);
 	return gpa;
 err:
-	gvt_err("invalid mm type: %d gma %lx\n", mm->type, gma);
+	gvt_vgpu_err("invalid mm type: %d gma %lx\n", mm->type, gma);
 	return INTEL_GVT_INVALID_ADDR;
 }
 
@@ -1825,11 +1825,8 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	gma = g_gtt_index << GTT_PAGE_SHIFT;
 
 	/* the VM may configure the whole GM space when ballooning is used */
-	if (WARN_ONCE(!vgpu_gmadr_is_valid(vgpu, gma),
-				"vgpu%d: found oob ggtt write, offset %x\n",
-				vgpu->id, off)) {
+	if (!vgpu_gmadr_is_valid(vgpu, gma))
 		return 0;
-	}
 
 	ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index);
 
@@ -1839,13 +1836,16 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	if (ops->test_present(&e)) {
 		ret = gtt_entry_p2m(vgpu, &e, &m);
 		if (ret) {
-			gvt_err("vgpu%d: fail to translate guest gtt entry\n",
-					vgpu->id);
-			return ret;
+			gvt_vgpu_err("fail to translate guest gtt entry\n");
+			/* guest driver may read/write the entry when partial
+			 * update the entry in this situation p2m will fail
+			 * settting the shadow entry to point to a scratch page
+			 */
+			ops->set_pfn(&m, gvt->gtt.scratch_ggtt_mfn);
 		}
 	} else {
 		m = e;
-		m.val64 = 0;
+		ops->set_pfn(&m, gvt->gtt.scratch_ggtt_mfn);
 	}
 
 	ggtt_set_shadow_entry(ggtt_mm, &m, g_gtt_index);
@@ -1896,14 +1896,14 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
 
 	scratch_pt = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!scratch_pt) {
-		gvt_err("fail to allocate scratch page\n");
+		gvt_vgpu_err("fail to allocate scratch page\n");
 		return -ENOMEM;
 	}
 
 	daddr = dma_map_page(dev, virt_to_page(scratch_pt), 0,
 			4096, PCI_DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, daddr)) {
-		gvt_err("fail to dmamap scratch_pt\n");
+		gvt_vgpu_err("fail to dmamap scratch_pt\n");
 		__free_page(virt_to_page(scratch_pt));
 		return -ENOMEM;
 	}
@@ -2006,7 +2006,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
 	ggtt_mm = intel_vgpu_create_mm(vgpu, INTEL_GVT_MM_GGTT,
 			NULL, 1, 0);
 	if (IS_ERR(ggtt_mm)) {
-		gvt_err("fail to create mm for ggtt.\n");
+		gvt_vgpu_err("fail to create mm for ggtt.\n");
 		return PTR_ERR(ggtt_mm);
 	}
 
@@ -2015,6 +2015,22 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
 	return create_scratch_page_tree(vgpu);
 }
 
+static void intel_vgpu_free_mm(struct intel_vgpu *vgpu, int type)
+{
+	struct list_head *pos, *n;
+	struct intel_vgpu_mm *mm;
+
+	list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) {
+		mm = container_of(pos, struct intel_vgpu_mm, list);
+		if (mm->type == type) {
+			vgpu->gvt->gtt.mm_free_page_table(mm);
+			list_del(&mm->list);
+			list_del(&mm->lru_list);
+			kfree(mm);
+		}
+	}
+}
+
 /**
  * intel_vgpu_clean_gtt - clean up per-vGPU graphics memory virulization
  * @vgpu: a vGPU
@@ -2027,19 +2043,11 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
  */
 void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu)
 {
-	struct list_head *pos, *n;
-	struct intel_vgpu_mm *mm;
-
 	ppgtt_free_all_shadow_page(vgpu);
 	release_scratch_page_tree(vgpu);
 
-	list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) {
-		mm = container_of(pos, struct intel_vgpu_mm, list);
-		vgpu->gvt->gtt.mm_free_page_table(mm);
-		list_del(&mm->list);
-		list_del(&mm->lru_list);
-		kfree(mm);
-	}
+	intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT);
+	intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_GGTT);
 }
 
 static void clean_spt_oos(struct intel_gvt *gvt)
@@ -2071,7 +2079,6 @@ static int setup_spt_oos(struct intel_gvt *gvt)
 	for (i = 0; i < preallocated_oos_pages; i++) {
 		oos_page = kzalloc(sizeof(*oos_page), GFP_KERNEL);
 		if (!oos_page) {
-			gvt_err("fail to pre-allocate oos page\n");
 			ret = -ENOMEM;
 			goto fail;
 		}
@@ -2161,7 +2168,7 @@ int intel_vgpu_g2v_create_ppgtt_mm(struct intel_vgpu *vgpu,
 		mm = intel_vgpu_create_mm(vgpu, INTEL_GVT_MM_PPGTT,
 				pdp, page_table_level, 0);
 		if (IS_ERR(mm)) {
-			gvt_err("fail to create mm\n");
+			gvt_vgpu_err("fail to create mm\n");
 			return PTR_ERR(mm);
 		}
 	}
@@ -2191,7 +2198,7 @@ int intel_vgpu_g2v_destroy_ppgtt_mm(struct intel_vgpu *vgpu,
 
 	mm = intel_vgpu_find_ppgtt_mm(vgpu, page_table_level, pdp);
 	if (!mm) {
-		gvt_err("fail to find ppgtt instance.\n");
+		gvt_vgpu_err("fail to find ppgtt instance.\n");
 		return -EINVAL;
 	}
 	intel_gvt_mm_unreference(mm);
@@ -2322,6 +2329,13 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr)
 	int i;
 
 	ppgtt_free_all_shadow_page(vgpu);
+
+	/* Shadow pages are only created when there is no page
+	 * table tracking data, so remove page tracking data after
+	 * removing the shadow pages.
+	 */
+	intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT);
+
 	if (!dmlr)
 		return;
 
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 3b9d59e457ba..ef3baa0c4754 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -52,6 +52,8 @@ static const struct intel_gvt_ops intel_gvt_ops = {
 	.vgpu_create = intel_gvt_create_vgpu,
 	.vgpu_destroy = intel_gvt_destroy_vgpu,
 	.vgpu_reset = intel_gvt_reset_vgpu,
+	.vgpu_activate = intel_gvt_activate_vgpu,
+	.vgpu_deactivate = intel_gvt_deactivate_vgpu,
 };
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index e227caf5859e..becae2fa3b29 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -143,6 +143,8 @@ struct intel_vgpu {
 	int id;
 	unsigned long handle; /* vGPU handle used by hypervisor MPT modules */
 	bool active;
+	bool pv_notified;
+	bool failsafe;
 	bool resetting;
 	void *sched_data;
 
@@ -160,7 +162,6 @@ struct intel_vgpu {
 	atomic_t running_workload_num;
 	DECLARE_BITMAP(tlb_handle_pending, I915_NUM_ENGINES);
 	struct i915_gem_context *shadow_ctx;
-	struct notifier_block shadow_ctx_notifier_block;
 
 #if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
 	struct {
@@ -203,18 +204,18 @@ struct intel_gvt_firmware {
 };
 
 struct intel_gvt_opregion {
-	void __iomem *opregion_va;
+	void *opregion_va;
 	u32 opregion_pa;
 };
 
 #define NR_MAX_INTEL_VGPU_TYPES 20
 struct intel_vgpu_type {
 	char name[16];
-	unsigned int max_instance;
 	unsigned int avail_instance;
 	unsigned int low_gm_size;
 	unsigned int high_gm_size;
 	unsigned int fence;
+	enum intel_vgpu_edid resolution;
 };
 
 struct intel_gvt {
@@ -231,6 +232,7 @@ struct intel_gvt {
 	struct intel_gvt_gtt gtt;
 	struct intel_gvt_opregion opregion;
 	struct intel_gvt_workload_scheduler scheduler;
+	struct notifier_block shadow_ctx_notifier_block[I915_NUM_ENGINES];
 	DECLARE_HASHTABLE(cmd_table, GVT_CMD_HASH_BITS);
 	struct intel_vgpu_type *types;
 	unsigned int num_types;
@@ -317,6 +319,7 @@ struct intel_vgpu_creation_params {
 	__u64 low_gm_sz;  /* in MB */
 	__u64 high_gm_sz; /* in MB */
 	__u64 fence_sz;
+	__u64 resolution;
 	__s32 primary;
 	__u64 vgpu_id;
 };
@@ -379,7 +382,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 				 unsigned int engine_mask);
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
-
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu);
 
 /* validating GM functions */
 #define vgpu_gmadr_is_aperture(vgpu, gmadr) \
@@ -446,9 +450,16 @@ struct intel_gvt_ops {
 				struct intel_vgpu_type *);
 	void (*vgpu_destroy)(struct intel_vgpu *);
 	void (*vgpu_reset)(struct intel_vgpu *);
+	void (*vgpu_activate)(struct intel_vgpu *);
+	void (*vgpu_deactivate)(struct intel_vgpu *);
 };
 
 
+enum {
+	GVT_FAILSAFE_UNSUPPORTED_GUEST,
+	GVT_FAILSAFE_INSUFFICIENT_RESOURCE,
+};
+
 #include "mpt.h"
 
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 1d450627ff65..6da9ae1618e3 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -121,6 +121,7 @@ static int new_mmio_info(struct intel_gvt *gvt,
 		info->size = size;
 		info->length = (i + 4) < end ? 4 : (end - i);
 		info->addr_mask = addr_mask;
+		info->ro_mask = ro_mask;
 		info->device = device;
 		info->read = read ? read : intel_vgpu_default_mmio_read;
 		info->write = write ? write : intel_vgpu_default_mmio_write;
@@ -150,15 +151,42 @@ static int render_mmio_to_ring_id(struct intel_gvt *gvt, unsigned int reg)
 #define fence_num_to_offset(num) \
 	(num * 8 + i915_mmio_reg_offset(FENCE_REG_GEN6_LO(0)))
 
+
+static void enter_failsafe_mode(struct intel_vgpu *vgpu, int reason)
+{
+	switch (reason) {
+	case GVT_FAILSAFE_UNSUPPORTED_GUEST:
+		pr_err("Detected your guest driver doesn't support GVT-g.\n");
+		break;
+	case GVT_FAILSAFE_INSUFFICIENT_RESOURCE:
+		pr_err("Graphics resource is not enough for the guest\n");
+	default:
+		break;
+	}
+	pr_err("Now vgpu %d will enter failsafe mode.\n", vgpu->id);
+	vgpu->failsafe = true;
+}
+
 static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 		unsigned int fence_num, void *p_data, unsigned int bytes)
 {
 	if (fence_num >= vgpu_fence_sz(vgpu)) {
-		gvt_err("vgpu%d: found oob fence register access\n",
-				vgpu->id);
-		gvt_err("vgpu%d: total fence num %d access fence num %d\n",
-				vgpu->id, vgpu_fence_sz(vgpu), fence_num);
+
+		/* When guest access oob fence regs without access
+		 * pv_info first, we treat guest not supporting GVT,
+		 * and we will let vgpu enter failsafe mode.
+		 */
+		if (!vgpu->pv_notified)
+			enter_failsafe_mode(vgpu,
+					GVT_FAILSAFE_UNSUPPORTED_GUEST);
+
+		if (!vgpu->mmio.disable_warn_untrack) {
+			gvt_vgpu_err("found oob fence register access\n");
+			gvt_vgpu_err("total fence %d, access fence %d\n",
+					vgpu_fence_sz(vgpu), fence_num);
+		}
 		memset(p_data, 0, bytes);
+		return -EINVAL;
 	}
 	return 0;
 }
@@ -219,7 +247,7 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 			break;
 		default:
 			/*should not hit here*/
-			gvt_err("invalid forcewake offset 0x%x\n", offset);
+			gvt_vgpu_err("invalid forcewake offset 0x%x\n", offset);
 			return -EINVAL;
 		}
 	} else {
@@ -369,6 +397,74 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	return 0;
 }
 
+/* ascendingly sorted */
+static i915_reg_t force_nonpriv_white_list[] = {
+	GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec)
+	GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248)
+	GEN8_CS_CHICKEN1,//_MMIO(0x2580)
+	_MMIO(0x2690),
+	_MMIO(0x2694),
+	_MMIO(0x2698),
+	_MMIO(0x4de0),
+	_MMIO(0x4de4),
+	_MMIO(0x4dfc),
+	GEN7_COMMON_SLICE_CHICKEN1,//_MMIO(0x7010)
+	_MMIO(0x7014),
+	HDC_CHICKEN0,//_MMIO(0x7300)
+	GEN8_HDC_CHICKEN1,//_MMIO(0x7304)
+	_MMIO(0x7700),
+	_MMIO(0x7704),
+	_MMIO(0x7708),
+	_MMIO(0x770c),
+	_MMIO(0xb110),
+	GEN8_L3SQCREG4,//_MMIO(0xb118)
+	_MMIO(0xe100),
+	_MMIO(0xe18c),
+	_MMIO(0xe48c),
+	_MMIO(0xe5f4),
+};
+
+/* a simple bsearch */
+static inline bool in_whitelist(unsigned int reg)
+{
+	int left = 0, right = ARRAY_SIZE(force_nonpriv_white_list);
+	i915_reg_t *array = force_nonpriv_white_list;
+
+	while (left < right) {
+		int mid = (left + right)/2;
+
+		if (reg > array[mid].reg)
+			left = mid + 1;
+		else if (reg < array[mid].reg)
+			right = mid;
+		else
+			return true;
+	}
+	return false;
+}
+
+static int force_nonpriv_write(struct intel_vgpu *vgpu,
+	unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 reg_nonpriv = *(u32 *)p_data;
+	int ret = -EINVAL;
+
+	if ((bytes != 4) || ((offset & (bytes - 1)) != 0)) {
+		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV offset %x(%dB)\n",
+			vgpu->id, offset, bytes);
+		return ret;
+	}
+
+	if (in_whitelist(reg_nonpriv)) {
+		ret = intel_vgpu_default_mmio_write(vgpu, offset, p_data,
+			bytes);
+	} else {
+		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x\n",
+			vgpu->id, reg_nonpriv);
+	}
+	return ret;
+}
+
 static int ddi_buf_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
@@ -432,7 +528,7 @@ static int check_fdi_rx_train_status(struct intel_vgpu *vgpu,
 		fdi_tx_train_bits = FDI_LINK_TRAIN_PATTERN_2;
 		fdi_iir_check_bits = FDI_RX_SYMBOL_LOCK;
 	} else {
-		gvt_err("Invalid train pattern %d\n", train_pattern);
+		gvt_vgpu_err("Invalid train pattern %d\n", train_pattern);
 		return -EINVAL;
 	}
 
@@ -490,7 +586,7 @@ static int update_fdi_rx_iir_status(struct intel_vgpu *vgpu,
 	else if (FDI_RX_IMR_TO_PIPE(offset) != INVALID_INDEX)
 		index = FDI_RX_IMR_TO_PIPE(offset);
 	else {
-		gvt_err("Unsupport registers %x\n", offset);
+		gvt_vgpu_err("Unsupport registers %x\n", offset);
 		return -EINVAL;
 	}
 
@@ -720,7 +816,7 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
 	u32 data;
 
 	if (!dpy_is_valid_port(port_index)) {
-		gvt_err("GVT(%d): Unsupported DP port access!\n", vgpu->id);
+		gvt_vgpu_err("Unsupported DP port access!\n");
 		return 0;
 	}
 
@@ -874,6 +970,14 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int mbctl_write(struct intel_vgpu *vgpu, unsigned int offset,
+		void *p_data, unsigned int bytes)
+{
+	*(u32 *)p_data &= (~GEN6_MBCTL_ENABLE_BOOT_FETCH);
+	write_vreg(vgpu, offset, p_data, bytes);
+	return 0;
+}
+
 static int vga_control_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
@@ -918,8 +1022,7 @@ static void write_virtual_sbi_register(struct intel_vgpu *vgpu,
 
 	if (i == num) {
 		if (num == SBI_REG_MAX) {
-			gvt_err("vgpu%d: SBI caching meets maximum limits\n",
-					vgpu->id);
+			gvt_vgpu_err("SBI caching meets maximum limits\n");
 			return;
 		}
 		display->sbi.number++;
@@ -999,8 +1102,9 @@ static int pvinfo_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 		break;
 	}
 	if (invalid_read)
-		gvt_err("invalid pvinfo read: [%x:%x] = %x\n",
+		gvt_vgpu_err("invalid pvinfo read: [%x:%x] = %x\n",
 				offset, bytes, *(u32 *)p_data);
+	vgpu->pv_notified = true;
 	return 0;
 }
 
@@ -1026,7 +1130,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
 	case 1:	/* Remove this in guest driver. */
 		break;
 	default:
-		gvt_err("Invalid PV notification %d\n", notification);
+		gvt_vgpu_err("Invalid PV notification %d\n", notification);
 	}
 	return ret;
 }
@@ -1039,7 +1143,7 @@ static int send_display_ready_uevent(struct intel_vgpu *vgpu, int ready)
 	char vmid_str[20];
 	char display_ready_str[20];
 
-	snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d\n", ready);
+	snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d", ready);
 	env[0] = display_ready_str;
 
 	snprintf(vmid_str, 20, "VMID=%d", vgpu->id);
@@ -1078,8 +1182,11 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	case _vgtif_reg(execlist_context_descriptor_lo):
 	case _vgtif_reg(execlist_context_descriptor_hi):
 		break;
+	case _vgtif_reg(rsv5[0])..._vgtif_reg(rsv5[3]):
+		enter_failsafe_mode(vgpu, GVT_FAILSAFE_INSUFFICIENT_RESOURCE);
+		break;
 	default:
-		gvt_err("invalid pvinfo write offset %x bytes %x data %x\n",
+		gvt_vgpu_err("invalid pvinfo write offset %x bytes %x data %x\n",
 				offset, bytes, data);
 		break;
 	}
@@ -1203,26 +1310,37 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 	u32 *data0 = &vgpu_vreg(vgpu, GEN6_PCODE_DATA);
 
 	switch (cmd) {
-	case 0x6:
-		/**
-		 * "Read memory latency" command on gen9.
-		 * Below memory latency values are read
-		 * from skylake platform.
-		 */
-		if (!*data0)
-			*data0 = 0x1e1a1100;
-		else
-			*data0 = 0x61514b3d;
+	case GEN9_PCODE_READ_MEM_LATENCY:
+		if (IS_SKYLAKE(vgpu->gvt->dev_priv)) {
+			/**
+			 * "Read memory latency" command on gen9.
+			 * Below memory latency values are read
+			 * from skylake platform.
+			 */
+			if (!*data0)
+				*data0 = 0x1e1a1100;
+			else
+				*data0 = 0x61514b3d;
+		}
 		break;
-	case 0x5:
+	case SKL_PCODE_CDCLK_CONTROL:
+		if (IS_SKYLAKE(vgpu->gvt->dev_priv))
+			*data0 = SKL_CDCLK_READY_FOR_CHANGE;
+		break;
+	case GEN6_PCODE_READ_RC6VIDS:
 		*data0 |= 0x1;
 		break;
 	}
 
 	gvt_dbg_core("VM(%d) write %x to mailbox, return data0 %x\n",
 		     vgpu->id, value, *data0);
-
-	value &= ~(1 << 31);
+	/**
+	 * PCODE_READY clear means ready for pcode read/write,
+	 * PCODE_ERROR_MASK clear means no error happened. In GVT-g we
+	 * always emulate as pcode read/write success and ready for access
+	 * anytime, since we don't touch real physical registers here.
+	 */
+	value &= ~(GEN6_PCODE_READY | GEN6_PCODE_ERROR_MASK);
 	return intel_vgpu_default_mmio_write(vgpu, offset, &value, bytes);
 }
 
@@ -1302,7 +1420,8 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	if (execlist->elsp_dwords.index == 3) {
 		ret = intel_vgpu_submit_execlist(vgpu, ring_id);
 		if(ret)
-			gvt_err("fail submit workload on ring %d\n", ring_id);
+			gvt_vgpu_err("fail submit workload on ring %d\n",
+				ring_id);
 	}
 
 	++execlist->elsp_dwords.index;
@@ -1318,6 +1437,17 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	bool enable_execlist;
 
 	write_vreg(vgpu, offset, p_data, bytes);
+
+	/* when PPGTT mode enabled, we will check if guest has called
+	 * pvinfo, if not, we will treat this guest as non-gvtg-aware
+	 * guest, and stop emulating its cfg space, mmio, gtt, etc.
+	 */
+	if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) ||
+			(data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)))
+			&& !vgpu->pv_notified) {
+		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
+		return 0;
+	}
 	if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))
 			|| (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) {
 		enable_execlist = !!(data & GFX_RUN_LIST_ENABLE);
@@ -1400,6 +1530,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
 #define MMIO_GM(reg, d, r, w) \
 	MMIO_F(reg, 4, F_GMADR, 0xFFFFF000, 0, d, r, w)
 
+#define MMIO_GM_RDR(reg, d, r, w) \
+	MMIO_F(reg, 4, F_GMADR | F_CMD_ACCESS, 0xFFFFF000, 0, d, r, w)
+
 #define MMIO_RO(reg, d, f, rm, r, w) \
 	MMIO_F(reg, 4, F_RO | f, 0, rm, d, r, w)
 
@@ -1419,6 +1552,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
 #define MMIO_RING_GM(prefix, d, r, w) \
 	MMIO_RING_F(prefix, 4, F_GMADR, 0xFFFF0000, 0, d, r, w)
 
+#define MMIO_RING_GM_RDR(prefix, d, r, w) \
+	MMIO_RING_F(prefix, 4, F_GMADR | F_CMD_ACCESS, 0xFFFF0000, 0, d, r, w)
+
 #define MMIO_RING_RO(prefix, d, f, rm, r, w) \
 	MMIO_RING_F(prefix, 4, F_RO | f, 0, rm, d, r, w)
 
@@ -1427,73 +1563,81 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
 
-	MMIO_RING_DFH(RING_IMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler);
+	MMIO_RING_DFH(RING_IMR, D_ALL, F_CMD_ACCESS, NULL,
+		intel_vgpu_reg_imr_handler);
 
 	MMIO_DFH(SDEIMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler);
 	MMIO_DFH(SDEIER, D_ALL, 0, NULL, intel_vgpu_reg_ier_handler);
 	MMIO_DFH(SDEIIR, D_ALL, 0, NULL, intel_vgpu_reg_iir_handler);
 	MMIO_D(SDEISR, D_ALL);
 
-	MMIO_RING_D(RING_HWSTAM, D_ALL);
+	MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_GM(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-	MMIO_GM(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-	MMIO_GM(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-	MMIO_GM(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 
 #define RING_REG(base) (base + 0x28)
-	MMIO_RING_D(RING_REG, D_ALL);
+	MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x134)
-	MMIO_RING_D(RING_REG, D_ALL);
+	MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL);
 #undef RING_REG
 
-	MMIO_GM(0x2148, D_ALL, NULL, NULL);
-	MMIO_GM(CCID, D_ALL, NULL, NULL);
-	MMIO_GM(0x12198, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(0x2148, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(CCID, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(0x12198, D_ALL, NULL, NULL);
 	MMIO_D(GEN7_CXT_SIZE, D_ALL);
 
-	MMIO_RING_D(RING_TAIL, D_ALL);
-	MMIO_RING_D(RING_HEAD, D_ALL);
-	MMIO_RING_D(RING_CTL, D_ALL);
-	MMIO_RING_D(RING_ACTHD, D_ALL);
-	MMIO_RING_GM(RING_START, D_ALL, NULL, NULL);
+	MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL);
 
 	/* RING MODE */
 #define RING_REG(base) (base + 0x29c)
-	MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK, NULL, ring_mode_mmio_write);
+	MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL,
+		ring_mode_mmio_write);
 #undef RING_REG
 
-	MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+			NULL, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS,
 			ring_timestamp_mmio_read, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS,
 			ring_timestamp_mmio_read, NULL);
 
-	MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	MMIO_DFH(CACHE_MODE_1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-
-	MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x2088, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x2470, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_D(GAM_ECOCHK, D_ALL);
-	MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(CACHE_MODE_0, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2124, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2088, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2470, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GAM_ECOCHK, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(0x9030, D_ALL);
-	MMIO_D(0x20a0, D_ALL);
-	MMIO_D(0x2420, D_ALL);
-	MMIO_D(0x2430, D_ALL);
-	MMIO_D(0x2434, D_ALL);
-	MMIO_D(0x2438, D_ALL);
-	MMIO_D(0x243c, D_ALL);
-	MMIO_DFH(0x7018, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(0x9030, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x20a0, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2420, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2430, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2434, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2438, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x243c, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x7018, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0xe100, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
 	/* display */
 	MMIO_F(0x60220, 0x20, 0, 0, 0, D_ALL, NULL, NULL);
@@ -2022,8 +2166,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(FORCEWAKE_ACK, D_ALL);
 	MMIO_D(GEN6_GT_CORE_STATUS, D_ALL);
 	MMIO_D(GEN6_GT_THREAD_STATUS_REG, D_ALL);
-	MMIO_D(GTFIFODBG, D_ALL);
-	MMIO_D(GTFIFOCTL, D_ALL);
+	MMIO_DFH(GTFIFODBG, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GTFIFOCTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DH(FORCEWAKE_MT, D_PRE_SKL, NULL, mul_force_wake_write);
 	MMIO_DH(FORCEWAKE_ACK_HSW, D_HSW | D_BDW, NULL, NULL);
 	MMIO_D(ECOBUS, D_ALL);
@@ -2080,7 +2224,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_F(0x4f000, 0x90, 0, 0, 0, D_ALL, NULL, NULL);
 
-	MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_SKL);
+	MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_BDW);
 	MMIO_D(GEN6_PCODE_DATA, D_ALL);
 	MMIO_D(0x13812c, D_ALL);
 	MMIO_DH(GEN7_ERR_INT, D_ALL, NULL, NULL);
@@ -2102,7 +2246,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x7180, D_ALL);
 	MMIO_D(0x7408, D_ALL);
 	MMIO_D(0x7c00, D_ALL);
-	MMIO_D(GEN6_MBCTL, D_ALL);
+	MMIO_DH(GEN6_MBCTL, D_ALL, NULL, mbctl_write);
 	MMIO_D(0x911c, D_ALL);
 	MMIO_D(0x9120, D_ALL);
 	MMIO_DFH(GEN7_UCGCTL4, D_ALL, F_CMD_ACCESS, NULL, NULL);
@@ -2159,36 +2303,35 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x1a054, D_ALL);
 
 	MMIO_D(0x44070, D_ALL);
-
-	MMIO_D(0x215c, D_HSW_PLUS);
+	MMIO_DFH(0x215c, D_HSW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x2178, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x12178, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x1217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_F(0x2290, 8, 0, 0, 0, D_HSW_PLUS, NULL, NULL);
-	MMIO_D(GEN7_OACONTROL, D_HSW);
+	MMIO_F(0x2290, 8, F_CMD_ACCESS, 0, 0, D_HSW_PLUS, NULL, NULL);
+	MMIO_DFH(GEN7_OACONTROL, D_HSW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0x2b00, D_BDW_PLUS);
 	MMIO_D(0x2360, D_BDW_PLUS);
-	MMIO_F(0x5200, 32, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(0x5240, 32, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(0x5280, 16, 0, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(0x5200, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(0x5240, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(0x5280, 16, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
 
 	MMIO_DFH(0x1c17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x1c178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(BCS_SWCTRL, D_ALL);
-
-	MMIO_F(HS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(DS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(IA_VERTICES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(IA_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(VS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(GS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(GS_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(CL_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(CL_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(PS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(PS_DEPTH_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
+	MMIO_DFH(BCS_SWCTRL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_F(HS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(DS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(IA_VERTICES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(IA_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(VS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(GS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(GS_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(CL_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(CL_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(PS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(PS_DEPTH_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
 	MMIO_DH(0x4260, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
 	MMIO_DH(0x4264, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
 	MMIO_DH(0x4268, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
@@ -2196,6 +2339,17 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(0x4270, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
 	MMIO_DFH(0x4094, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_DFH(ARB_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_GM_RDR(RING_BBADDR, D_ALL, NULL, NULL);
+	MMIO_DFH(0x2220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x12220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x22220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_SYNC_1, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_SYNC_0, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x22178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1a178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1a17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2217c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	return 0;
 }
 
@@ -2204,7 +2358,7 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
 
-	MMIO_DH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL,
+	MMIO_DFH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, NULL,
 			intel_vgpu_reg_imr_handler);
 
 	MMIO_DH(GEN8_GT_IMR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_imr_handler);
@@ -2269,24 +2423,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL,
 		intel_vgpu_reg_master_irq_handler);
 
-	MMIO_D(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(0x1c134, D_BDW_PLUS);
-
-	MMIO_D(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(RING_HEAD(GEN8_BSD2_RING_BASE),  D_BDW_PLUS);
-	MMIO_GM(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
-	MMIO_D(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK, NULL, ring_mode_mmio_write);
-	MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK,
-			NULL, NULL);
-	MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK,
-			NULL, NULL);
+	MMIO_DFH(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1c134, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DFH(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(RING_HEAD(GEN8_BSD2_RING_BASE),  D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_GM_RDR(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
+	MMIO_DFH(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL,
+		ring_mode_mmio_write);
+	MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(RING_TIMESTAMP(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
 			ring_timestamp_mmio_read, NULL);
 
-	MMIO_RING_D(RING_ACTHD_UDW, D_BDW_PLUS);
+	MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
 #define RING_REG(base) (base + 0xd0)
 	MMIO_RING_F(RING_REG, 4, F_RO, 0,
@@ -2303,13 +2464,16 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x234)
-	MMIO_RING_F(RING_REG, 8, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL);
-	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO, 0, ~0LL, D_BDW_PLUS, NULL, NULL);
+	MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS,
+		NULL, NULL);
+	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO | F_CMD_ACCESS, 0,
+		~0LL, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x244)
-	MMIO_RING_D(RING_REG, D_BDW_PLUS);
-	MMIO_D(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
+	MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+		NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x370)
@@ -2331,6 +2495,8 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GEN7_MISCCPCTL, D_BDW_PLUS);
 	MMIO_D(0x1c054, D_BDW_PLUS);
 
+	MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
+
 	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
 	MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
 
@@ -2341,14 +2507,14 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
-	MMIO_RING_GM(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
-	MMIO_GM(0x1c080, D_BDW_PLUS, NULL, NULL);
+	MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
+	MMIO_GM_RDR(RING_HWS_PGA(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
 
 	MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW);
-	MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW);
-	MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW);
+	MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW_PLUS);
+	MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW_PLUS);
+	MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW_PLUS);
 
 	MMIO_D(WM_MISC, D_BDW);
 	MMIO_D(BDW_EDP_PSR_BASE, D_BDW);
@@ -2362,27 +2528,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GEN8_EU_DISABLE1, D_BDW_PLUS);
 	MMIO_D(GEN8_EU_DISABLE2, D_BDW_PLUS);
 
-	MMIO_D(0xfdc, D_BDW);
-	MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(GEN7_ROW_CHICKEN2, D_BDW_PLUS);
-	MMIO_D(GEN8_UCGCTL6, D_BDW_PLUS);
+	MMIO_D(0xfdc, D_BDW_PLUS);
+	MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(GEN7_ROW_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(GEN8_UCGCTL6, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_D(0xb1f0, D_BDW);
-	MMIO_D(0xb1c0, D_BDW);
+	MMIO_DFH(0xb1f0, D_BDW, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xb1c0, D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(GEN8_L3SQCREG4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(0xb100, D_BDW);
-	MMIO_D(0xb10c, D_BDW);
+	MMIO_DFH(0xb100, D_BDW, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xb10c, D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0xb110, D_BDW);
 
-	MMIO_DFH(0x24d0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x24d4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x24d8, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x24dc, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_F(0x24d0, 48, F_CMD_ACCESS, 0, 0, D_BDW_PLUS,
+		NULL, force_nonpriv_write);
 
-	MMIO_D(0x83a4, D_BDW);
+	MMIO_D(0x22040, D_BDW_PLUS);
+	MMIO_D(0x44484, D_BDW_PLUS);
+	MMIO_D(0x4448c, D_BDW_PLUS);
+
+	MMIO_DFH(0x83a4, D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(GEN8_L3_LRA_1_GPGPU, D_BDW_PLUS);
 
-	MMIO_D(0x8430, D_BDW);
+	MMIO_DFH(0x8430, D_BDW, F_CMD_ACCESS, NULL, NULL);
 
 	MMIO_D(0x110000, D_BDW_PLUS);
 
@@ -2394,10 +2564,19 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0xe188, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(HALF_SLICE_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK, NULL, NULL);
-
-	MMIO_D(0x2248, D_BDW);
-
+	MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DFH(0x2248, D_BDW, F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DFH(0xe220, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe230, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe240, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe260, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe270, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe280, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe2a0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe2b0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe2c0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	return 0;
 }
 
@@ -2420,7 +2599,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(HSW_PWR_WELL_BIOS, D_SKL);
 	MMIO_DH(HSW_PWR_WELL_DRIVER, D_SKL, NULL, skl_power_well_ctl_write);
 
-	MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL, NULL, mailbox_write);
 	MMIO_D(0xa210, D_SKL_PLUS);
 	MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
 	MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
@@ -2578,16 +2756,16 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_F(0xb020, 0x80, F_CMD_ACCESS, 0, 0, D_SKL, NULL, NULL);
 
 	MMIO_D(0xd08, D_SKL);
-	MMIO_D(0x20e0, D_SKL);
-	MMIO_D(0x20ec, D_SKL);
+	MMIO_DFH(0x20e0, D_SKL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(0x20ec, D_SKL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
 	/* TRTT */
-	MMIO_D(0x4de0, D_SKL);
-	MMIO_D(0x4de4, D_SKL);
-	MMIO_D(0x4de8, D_SKL);
-	MMIO_D(0x4dec, D_SKL);
-	MMIO_D(0x4df0, D_SKL);
-	MMIO_DH(0x4df4, D_SKL, NULL, gen9_trtte_write);
+	MMIO_DFH(0x4de0, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4de4, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4de8, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4dec, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4df0, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4df4, D_SKL, F_CMD_ACCESS, NULL, gen9_trtte_write);
 	MMIO_DH(0x4dfc, D_SKL, NULL, gen9_trtt_chicken_write);
 
 	MMIO_D(0x45008, D_SKL);
@@ -2611,7 +2789,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x65f08, D_SKL);
 	MMIO_D(0x320f0, D_SKL);
 
-	MMIO_D(_REG_VCS2_EXCC, D_SKL);
+	MMIO_DFH(_REG_VCS2_EXCC, D_SKL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0x70034, D_SKL);
 	MMIO_D(0x71034, D_SKL);
 	MMIO_D(0x72034, D_SKL);
@@ -2624,6 +2802,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_PLANE_KEYMSK_1(PIPE_C), D_SKL);
 
 	MMIO_D(0x44500, D_SKL);
+	MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	return 0;
 }
 
@@ -2813,3 +2994,20 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	write_vreg(vgpu, offset, p_data, bytes);
 	return 0;
 }
+
+/**
+ * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be
+ * force-nopriv register
+ *
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ * Returns:
+ * True if the register is in force-nonpriv whitelist;
+ * False if outside;
+ */
+bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
+					  unsigned int offset)
+{
+	return in_whitelist(offset);
+}
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 0f7f5d97f582..e466259034e2 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -96,10 +96,10 @@ static int gvt_dma_map_iova(struct intel_vgpu *vgpu, kvm_pfn_t pfn,
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	dma_addr_t daddr;
 
-	page = pfn_to_page(pfn);
-	if (is_error_page(page))
+	if (unlikely(!pfn_valid(pfn)))
 		return -EFAULT;
 
+	page = pfn_to_page(pfn);
 	daddr = dma_map_page(dev, page, 0, PAGE_SIZE,
 			PCI_DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, daddr))
@@ -295,10 +295,10 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev,
 		return 0;
 
 	return sprintf(buf, "low_gm_size: %dMB\nhigh_gm_size: %dMB\n"
-				"fence: %d\n",
-				BYTES_TO_MB(type->low_gm_size),
-				BYTES_TO_MB(type->high_gm_size),
-				type->fence);
+		       "fence: %d\nresolution: %s\n",
+		       BYTES_TO_MB(type->low_gm_size),
+		       BYTES_TO_MB(type->high_gm_size),
+		       type->fence, vgpu_edid_str(type->resolution));
 }
 
 static MDEV_TYPE_ATTR_RO(available_instances);
@@ -426,7 +426,7 @@ static void kvmgt_protect_table_del(struct kvmgt_guest_info *info,
 
 static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 {
-	struct intel_vgpu *vgpu;
+	struct intel_vgpu *vgpu = NULL;
 	struct intel_vgpu_type *type;
 	struct device *pdev;
 	void *gvt;
@@ -437,7 +437,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 
 	type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
 	if (!type) {
-		gvt_err("failed to find type %s to create\n",
+		gvt_vgpu_err("failed to find type %s to create\n",
 						kobject_name(kobj));
 		ret = -EINVAL;
 		goto out;
@@ -446,7 +446,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 	vgpu = intel_gvt_ops->vgpu_create(gvt, type);
 	if (IS_ERR_OR_NULL(vgpu)) {
 		ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu);
-		gvt_err("failed to create intel vgpu: %d\n", ret);
+		gvt_vgpu_err("failed to create intel vgpu: %d\n", ret);
 		goto out;
 	}
 
@@ -526,7 +526,8 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &events,
 				&vgpu->vdev.iommu_notifier);
 	if (ret != 0) {
-		gvt_err("vfio_register_notifier for iommu failed: %d\n", ret);
+		gvt_vgpu_err("vfio_register_notifier for iommu failed: %d\n",
+			ret);
 		goto out;
 	}
 
@@ -534,7 +535,8 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &events,
 				&vgpu->vdev.group_notifier);
 	if (ret != 0) {
-		gvt_err("vfio_register_notifier for group failed: %d\n", ret);
+		gvt_vgpu_err("vfio_register_notifier for group failed: %d\n",
+			ret);
 		goto undo_iommu;
 	}
 
@@ -542,6 +544,8 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	if (ret)
 		goto undo_group;
 
+	intel_gvt_ops->vgpu_activate(vgpu);
+
 	atomic_set(&vgpu->vdev.released, 0);
 	return ret;
 
@@ -567,6 +571,8 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 	if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
 		return;
 
+	intel_gvt_ops->vgpu_deactivate(vgpu);
+
 	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
 					&vgpu->vdev.iommu_notifier);
 	WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);
@@ -635,7 +641,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 
 
 	if (index >= VFIO_PCI_NUM_REGIONS) {
-		gvt_err("invalid index: %u\n", index);
+		gvt_vgpu_err("invalid index: %u\n", index);
 		return -EINVAL;
 	}
 
@@ -669,7 +675,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 	case VFIO_PCI_VGA_REGION_INDEX:
 	case VFIO_PCI_ROM_REGION_INDEX:
 	default:
-		gvt_err("unsupported region: %u\n", index);
+		gvt_vgpu_err("unsupported region: %u\n", index);
 	}
 
 	return ret == 0 ? count : ret;
@@ -861,7 +867,7 @@ static int intel_vgpu_set_msi_trigger(struct intel_vgpu *vgpu,
 
 		trigger = eventfd_ctx_fdget(fd);
 		if (IS_ERR(trigger)) {
-			gvt_err("eventfd_ctx_fdget failed\n");
+			gvt_vgpu_err("eventfd_ctx_fdget failed\n");
 			return PTR_ERR(trigger);
 		}
 		vgpu->vdev.msi_trigger = trigger;
@@ -1120,7 +1126,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			ret = vfio_set_irqs_validate_and_prepare(&hdr, max,
 						VFIO_PCI_NUM_IRQS, &data_size);
 			if (ret) {
-				gvt_err("intel:vfio_set_irqs_validate_and_prepare failed\n");
+				gvt_vgpu_err("intel:vfio_set_irqs_validate_and_prepare failed\n");
 				return -EINVAL;
 			}
 			if (data_size) {
@@ -1310,7 +1316,7 @@ static int kvmgt_guest_init(struct mdev_device *mdev)
 
 	kvm = vgpu->vdev.kvm;
 	if (!kvm || kvm->mm != current->mm) {
-		gvt_err("KVM is required to use Intel vGPU\n");
+		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
 		return -ESRCH;
 	}
 
@@ -1324,6 +1330,7 @@ static int kvmgt_guest_init(struct mdev_device *mdev)
 	vgpu->handle = (unsigned long)info;
 	info->vgpu = vgpu;
 	info->kvm = kvm;
+	kvm_get_kvm(info->kvm);
 
 	kvmgt_protect_table_init(info);
 	gvt_cache_init(vgpu);
@@ -1337,12 +1344,8 @@ static int kvmgt_guest_init(struct mdev_device *mdev)
 
 static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
 {
-	if (!info) {
-		gvt_err("kvmgt_guest_info invalid\n");
-		return false;
-	}
-
 	kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
+	kvm_put_kvm(info->kvm);
 	kvmgt_protect_table_destroy(info);
 	gvt_cache_destroy(info->vgpu);
 	vfree(info);
@@ -1383,12 +1386,14 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
 	unsigned long iova, pfn;
 	struct kvmgt_guest_info *info;
 	struct device *dev;
+	struct intel_vgpu *vgpu;
 	int rc;
 
 	if (!handle_valid(handle))
 		return INTEL_GVT_INVALID_ADDR;
 
 	info = (struct kvmgt_guest_info *)handle;
+	vgpu = info->vgpu;
 	iova = gvt_cache_find(info->vgpu, gfn);
 	if (iova != INTEL_GVT_INVALID_ADDR)
 		return iova;
@@ -1397,13 +1402,14 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
 	dev = mdev_dev(info->vgpu->vdev.mdev);
 	rc = vfio_pin_pages(dev, &gfn, 1, IOMMU_READ | IOMMU_WRITE, &pfn);
 	if (rc != 1) {
-		gvt_err("vfio_pin_pages failed for gfn 0x%lx: %d\n", gfn, rc);
+		gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n",
+			gfn, rc);
 		return INTEL_GVT_INVALID_ADDR;
 	}
 	/* transfer to host iova for GFX to use DMA */
 	rc = gvt_dma_map_iova(info->vgpu, pfn, &iova);
 	if (rc) {
-		gvt_err("gvt_dma_map_iova failed for gfn: 0x%lx\n", gfn);
+		gvt_vgpu_err("gvt_dma_map_iova failed for gfn: 0x%lx\n", gfn);
 		vfio_unpin_pages(dev, &gfn, 1);
 		return INTEL_GVT_INVALID_ADDR;
 	}
@@ -1417,7 +1423,7 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa,
 {
 	struct kvmgt_guest_info *info;
 	struct kvm *kvm;
-	int ret;
+	int idx, ret;
 	bool kthread = current->mm == NULL;
 
 	if (!handle_valid(handle))
@@ -1429,8 +1435,10 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa,
 	if (kthread)
 		use_mm(kvm->mm);
 
+	idx = srcu_read_lock(&kvm->srcu);
 	ret = write ? kvm_write_guest(kvm, gpa, buf, len) :
 		      kvm_read_guest(kvm, gpa, buf, len);
+	srcu_read_unlock(&kvm->srcu, idx);
 
 	if (kthread)
 		unuse_mm(kvm->mm);
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 4df078bc5d04..1ba3bdb09341 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -57,6 +57,58 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa)
 	(reg >= gvt->device_info.gtt_start_offset \
 	 && reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt))
 
+static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
+		void *p_data, unsigned int bytes, bool read)
+{
+	struct intel_gvt *gvt = NULL;
+	void *pt = NULL;
+	unsigned int offset = 0;
+
+	if (!vgpu || !p_data)
+		return;
+
+	gvt = vgpu->gvt;
+	mutex_lock(&gvt->lock);
+	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
+	if (reg_is_mmio(gvt, offset)) {
+		if (read)
+			intel_vgpu_default_mmio_read(vgpu, offset, p_data,
+					bytes);
+		else
+			intel_vgpu_default_mmio_write(vgpu, offset, p_data,
+					bytes);
+	} else if (reg_is_gtt(gvt, offset) &&
+			vgpu->gtt.ggtt_mm->virtual_page_table) {
+		offset -= gvt->device_info.gtt_start_offset;
+		pt = vgpu->gtt.ggtt_mm->virtual_page_table + offset;
+		if (read)
+			memcpy(p_data, pt, bytes);
+		else
+			memcpy(pt, p_data, bytes);
+
+	} else if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
+		struct intel_vgpu_guest_page *gp;
+
+		/* Since we enter the failsafe mode early during guest boot,
+		 * guest may not have chance to set up its ppgtt table, so
+		 * there should not be any wp pages for guest. Keep the wp
+		 * related code here in case we need to handle it in furture.
+		 */
+		gp = intel_vgpu_find_guest_page(vgpu, pa >> PAGE_SHIFT);
+		if (gp) {
+			/* remove write protection to prevent furture traps */
+			intel_vgpu_clean_guest_page(vgpu, gp);
+			if (read)
+				intel_gvt_hypervisor_read_gpa(vgpu, pa,
+						p_data, bytes);
+			else
+				intel_gvt_hypervisor_write_gpa(vgpu, pa,
+						p_data, bytes);
+		}
+	}
+	mutex_unlock(&gvt->lock);
+}
+
 /**
  * intel_vgpu_emulate_mmio_read - emulate MMIO read
  * @vgpu: a vGPU
@@ -75,6 +127,11 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 	unsigned int offset = 0;
 	int ret = -EINVAL;
 
+
+	if (vgpu->failsafe) {
+		failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, true);
+		return 0;
+	}
 	mutex_lock(&gvt->lock);
 
 	if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
@@ -85,10 +142,10 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 			ret = intel_gvt_hypervisor_read_gpa(vgpu, pa,
 					p_data, bytes);
 			if (ret) {
-				gvt_err("vgpu%d: guest page read error %d, "
+				gvt_vgpu_err("guest page read error %d, "
 					"gfn 0x%lx, pa 0x%llx, var 0x%x, len %d\n",
-					vgpu->id, ret,
-					gp->gfn, pa, *(u32 *)p_data, bytes);
+					ret, gp->gfn, pa, *(u32 *)p_data,
+					bytes);
 			}
 			mutex_unlock(&gvt->lock);
 			return ret;
@@ -143,14 +200,13 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 		ret = intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
 
 		if (!vgpu->mmio.disable_warn_untrack) {
-			gvt_err("vgpu%d: read untracked MMIO %x(%dB) val %x\n",
-				vgpu->id, offset, bytes, *(u32 *)p_data);
+			gvt_vgpu_err("read untracked MMIO %x(%dB) val %x\n",
+				offset, bytes, *(u32 *)p_data);
 
 			if (offset == 0x206c) {
-				gvt_err("------------------------------------------\n");
-				gvt_err("vgpu%d: likely triggers a gfx reset\n",
-					vgpu->id);
-				gvt_err("------------------------------------------\n");
+				gvt_vgpu_err("------------------------------------------\n");
+				gvt_vgpu_err("likely triggers a gfx reset\n");
+				gvt_vgpu_err("------------------------------------------\n");
 				vgpu->mmio.disable_warn_untrack = true;
 			}
 		}
@@ -163,8 +219,8 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 	mutex_unlock(&gvt->lock);
 	return 0;
 err:
-	gvt_err("vgpu%d: fail to emulate MMIO read %08x len %d\n",
-			vgpu->id, offset, bytes);
+	gvt_vgpu_err("fail to emulate MMIO read %08x len %d\n",
+			offset, bytes);
 	mutex_unlock(&gvt->lock);
 	return ret;
 }
@@ -188,6 +244,11 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 	u32 old_vreg = 0, old_sreg = 0;
 	int ret = -EINVAL;
 
+	if (vgpu->failsafe) {
+		failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, false);
+		return 0;
+	}
+
 	mutex_lock(&gvt->lock);
 
 	if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
@@ -197,10 +258,11 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 		if (gp) {
 			ret = gp->handler(gp, pa, p_data, bytes);
 			if (ret) {
-				gvt_err("vgpu%d: guest page write error %d, "
-					"gfn 0x%lx, pa 0x%llx, var 0x%x, len %d\n",
-					vgpu->id, ret,
-					gp->gfn, pa, *(u32 *)p_data, bytes);
+				gvt_err("guest page write error %d, "
+					"gfn 0x%lx, pa 0x%llx, "
+					"var 0x%x, len %d\n",
+					ret, gp->gfn, pa,
+					*(u32 *)p_data, bytes);
 			}
 			mutex_unlock(&gvt->lock);
 			return ret;
@@ -236,7 +298,7 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 
 	mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
 	if (!mmio && !vgpu->mmio.disable_warn_untrack)
-		gvt_err("vgpu%d: write untracked MMIO %x len %d val %x\n",
+		gvt_dbg_mmio("vgpu%d: write untracked MMIO %x len %d val %x\n",
 				vgpu->id, offset, bytes, *(u32 *)p_data);
 
 	if (!intel_gvt_mmio_is_unalign(gvt, offset)) {
@@ -267,8 +329,8 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 
 			/* all register bits are RO. */
 			if (ro_mask == ~(u64)0) {
-				gvt_err("vgpu%d: try to write RO reg %x\n",
-						vgpu->id, offset);
+				gvt_vgpu_err("try to write RO reg %x\n",
+					offset);
 				ret = 0;
 				goto out;
 			}
@@ -298,8 +360,8 @@ out:
 	mutex_unlock(&gvt->lock);
 	return 0;
 err:
-	gvt_err("vgpu%d: fail to emulate MMIO write %08x len %d\n",
-			vgpu->id, offset, bytes);
+	gvt_vgpu_err("fail to emulate MMIO write %08x len %d\n", offset,
+		     bytes);
 	mutex_unlock(&gvt->lock);
 	return ret;
 }
@@ -322,6 +384,8 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu)
 
 	/* set the bit 0:2(Core C-State ) to C0 */
 	vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
+
+	vgpu->mmio.disable_warn_untrack = false;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 3bc620f56f35..a3a027025cd0 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -107,4 +107,7 @@ int intel_vgpu_default_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 				 void *p_data, unsigned int bytes);
 int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 				  void *p_data, unsigned int bytes);
+
+bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
+					  unsigned int offset);
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index d9fb41ab7119..311799136d7f 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -27,7 +27,6 @@
 
 static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
 {
-	void __iomem *host_va = vgpu->gvt->opregion.opregion_va;
 	u8 *buf;
 	int i;
 
@@ -43,8 +42,8 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
 	if (!vgpu_opregion(vgpu)->va)
 		return -ENOMEM;
 
-	memcpy_fromio(vgpu_opregion(vgpu)->va, host_va,
-			INTEL_GVT_OPREGION_SIZE);
+	memcpy(vgpu_opregion(vgpu)->va, vgpu->gvt->opregion.opregion_va,
+	       INTEL_GVT_OPREGION_SIZE);
 
 	for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++)
 		vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i;
@@ -68,14 +67,15 @@ static int map_vgpu_opregion(struct intel_vgpu *vgpu, bool map)
 		mfn = intel_gvt_hypervisor_virt_to_mfn(vgpu_opregion(vgpu)->va
 			+ i * PAGE_SIZE);
 		if (mfn == INTEL_GVT_INVALID_ADDR) {
-			gvt_err("fail to get MFN from VA\n");
+			gvt_vgpu_err("fail to get MFN from VA\n");
 			return -EINVAL;
 		}
 		ret = intel_gvt_hypervisor_map_gfn_to_mfn(vgpu,
 				vgpu_opregion(vgpu)->gfn[i],
 				mfn, 1, map);
 		if (ret) {
-			gvt_err("fail to map GFN to MFN, errno: %d\n", ret);
+			gvt_vgpu_err("fail to map GFN to MFN, errno: %d\n",
+				ret);
 			return ret;
 		}
 	}
@@ -288,7 +288,7 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
 	parm = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_PARM;
 
 	if (!(swsci & SWSCI_SCI_SELECT)) {
-		gvt_err("vgpu%d: requesting SMI service\n", vgpu->id);
+		gvt_vgpu_err("requesting SMI service\n");
 		return 0;
 	}
 	/* ignore non 0->1 trasitions */
@@ -301,9 +301,8 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
 	func = GVT_OPREGION_FUNC(*scic);
 	subfunc = GVT_OPREGION_SUBFUNC(*scic);
 	if (!querying_capabilities(*scic)) {
-		gvt_err("vgpu%d: requesting runtime service: func \"%s\","
+		gvt_vgpu_err("requesting runtime service: func \"%s\","
 				" subfunc \"%s\"\n",
-				vgpu->id,
 				opregion_func_name(func),
 				opregion_subfunc_name(subfunc));
 		/*
diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c
index 2b3a642284b6..0beb83563b08 100644
--- a/drivers/gpu/drm/i915/gvt/render.c
+++ b/drivers/gpu/drm/i915/gvt/render.c
@@ -53,6 +53,14 @@ static struct render_mmio gen8_render_mmio_list[] = {
 	{RCS, _MMIO(0x24d4), 0, false},
 	{RCS, _MMIO(0x24d8), 0, false},
 	{RCS, _MMIO(0x24dc), 0, false},
+	{RCS, _MMIO(0x24e0), 0, false},
+	{RCS, _MMIO(0x24e4), 0, false},
+	{RCS, _MMIO(0x24e8), 0, false},
+	{RCS, _MMIO(0x24ec), 0, false},
+	{RCS, _MMIO(0x24f0), 0, false},
+	{RCS, _MMIO(0x24f4), 0, false},
+	{RCS, _MMIO(0x24f8), 0, false},
+	{RCS, _MMIO(0x24fc), 0, false},
 	{RCS, _MMIO(0x7004), 0xffff, true},
 	{RCS, _MMIO(0x7008), 0xffff, true},
 	{RCS, _MMIO(0x7000), 0xffff, true},
@@ -76,6 +84,14 @@ static struct render_mmio gen9_render_mmio_list[] = {
 	{RCS, _MMIO(0x24d4), 0, false},
 	{RCS, _MMIO(0x24d8), 0, false},
 	{RCS, _MMIO(0x24dc), 0, false},
+	{RCS, _MMIO(0x24e0), 0, false},
+	{RCS, _MMIO(0x24e4), 0, false},
+	{RCS, _MMIO(0x24e8), 0, false},
+	{RCS, _MMIO(0x24ec), 0, false},
+	{RCS, _MMIO(0x24f0), 0, false},
+	{RCS, _MMIO(0x24f4), 0, false},
+	{RCS, _MMIO(0x24f8), 0, false},
+	{RCS, _MMIO(0x24fc), 0, false},
 	{RCS, _MMIO(0x7004), 0xffff, true},
 	{RCS, _MMIO(0x7008), 0xffff, true},
 	{RCS, _MMIO(0x7000), 0xffff, true},
@@ -151,7 +167,7 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
 	I915_WRITE_FW(reg, 0x1);
 
 	if (wait_for_atomic((I915_READ_FW(reg) == 0), 50))
-		gvt_err("timeout in invalidate ring (%d) tlb\n", ring_id);
+		gvt_vgpu_err("timeout in invalidate ring (%d) tlb\n", ring_id);
 	else
 		vgpu_vreg(vgpu, regs[ring_id]) = 0;
 
@@ -191,7 +207,7 @@ static void load_mocs(struct intel_vgpu *vgpu, int ring_id)
 		l3_offset.reg = 0xb020;
 		for (i = 0; i < 32; i++) {
 			gen9_render_mocs_L3[i] = I915_READ(l3_offset);
-			I915_WRITE(l3_offset, vgpu_vreg(vgpu, offset));
+			I915_WRITE(l3_offset, vgpu_vreg(vgpu, l3_offset));
 			POSTING_READ(l3_offset);
 			l3_offset.reg += 4;
 		}
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index 06c9584ac5f0..34b9acdf3479 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -101,7 +101,7 @@ struct tbs_sched_data {
 	struct list_head runq_head;
 };
 
-#define GVT_DEFAULT_TIME_SLICE (1 * HZ / 1000)
+#define GVT_DEFAULT_TIME_SLICE (msecs_to_jiffies(1))
 
 static void tbs_sched_func(struct work_struct *work)
 {
@@ -223,7 +223,7 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
 		return;
 
 	list_add_tail(&vgpu_data->list, &sched_data->runq_head);
-	schedule_delayed_work(&sched_data->work, sched_data->period);
+	schedule_delayed_work(&sched_data->work, 0);
 }
 
 static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index d6b6d0efdd1a..a44782412f2c 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -84,7 +84,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 				(u32)((workload->ctx_desc.lrca + i) <<
 				GTT_PAGE_SHIFT));
 		if (context_gpa == INTEL_GVT_INVALID_ADDR) {
-			gvt_err("Invalid guest context descriptor\n");
+			gvt_vgpu_err("Invalid guest context descriptor\n");
 			return -EINVAL;
 		}
 
@@ -127,18 +127,24 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	return 0;
 }
 
+static inline bool is_gvt_request(struct drm_i915_gem_request *req)
+{
+	return i915_gem_context_force_single_submission(req->ctx);
+}
+
 static int shadow_context_status_change(struct notifier_block *nb,
 		unsigned long action, void *data)
 {
-	struct intel_vgpu *vgpu = container_of(nb,
-			struct intel_vgpu, shadow_ctx_notifier_block);
-	struct drm_i915_gem_request *req =
-		(struct drm_i915_gem_request *)data;
-	struct intel_gvt_workload_scheduler *scheduler =
-		&vgpu->gvt->scheduler;
+	struct drm_i915_gem_request *req = (struct drm_i915_gem_request *)data;
+	struct intel_gvt *gvt = container_of(nb, struct intel_gvt,
+				shadow_ctx_notifier_block[req->engine->id]);
+	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload =
 		scheduler->current_workload[req->engine->id];
 
+	if (!is_gvt_request(req) || unlikely(!workload))
+		return NOTIFY_OK;
+
 	switch (action) {
 	case INTEL_CONTEXT_SCHEDULE_IN:
 		intel_gvt_load_render_mmio(workload->vgpu,
@@ -148,6 +154,15 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	case INTEL_CONTEXT_SCHEDULE_OUT:
 		intel_gvt_restore_render_mmio(workload->vgpu,
 					      workload->ring_id);
+		/* If the status is -EINPROGRESS means this workload
+		 * doesn't meet any issue during dispatching so when
+		 * get the SCHEDULE_OUT set the status to be zero for
+		 * good. If the status is NOT -EINPROGRESS means there
+		 * is something wrong happened during dispatching and
+		 * the status should not be set to zero
+		 */
+		if (workload->status == -EINPROGRESS)
+			workload->status = 0;
 		atomic_set(&workload->shadow_ctx_active, 0);
 		break;
 	default:
@@ -163,7 +178,9 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 	int ring_id = workload->ring_id;
 	struct i915_gem_context *shadow_ctx = workload->vgpu->shadow_ctx;
 	struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
+	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
 	struct drm_i915_gem_request *rq;
+	struct intel_vgpu *vgpu = workload->vgpu;
 	int ret;
 
 	gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n",
@@ -175,9 +192,24 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
+	/* pin shadow context by gvt even the shadow context will be pinned
+	 * when i915 alloc request. That is because gvt will update the guest
+	 * context from shadow context when workload is completed, and at that
+	 * moment, i915 may already unpined the shadow context to make the
+	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
+	 * the guest context, gvt can unpin the shadow_ctx safely.
+	 */
+	ret = engine->context_pin(engine, shadow_ctx);
+	if (ret) {
+		gvt_vgpu_err("fail to pin shadow context\n");
+		workload->status = ret;
+		mutex_unlock(&dev_priv->drm.struct_mutex);
+		return ret;
+	}
+
 	rq = i915_gem_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
 	if (IS_ERR(rq)) {
-		gvt_err("fail to allocate gem request\n");
+		gvt_vgpu_err("fail to allocate gem request\n");
 		ret = PTR_ERR(rq);
 		goto out;
 	}
@@ -190,9 +222,12 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 	if (ret)
 		goto out;
 
-	ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
-	if (ret)
-		goto out;
+	if ((workload->ring_id == RCS) &&
+	    (workload->wa_ctx.indirect_ctx.size != 0)) {
+		ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
+		if (ret)
+			goto out;
+	}
 
 	ret = populate_shadow_context(workload);
 	if (ret)
@@ -215,6 +250,9 @@ out:
 
 	if (!IS_ERR_OR_NULL(rq))
 		i915_add_request_no_flush(rq);
+	else
+		engine->context_unpin(engine, shadow_ctx);
+
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return ret;
 }
@@ -310,7 +348,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 				(u32)((workload->ctx_desc.lrca + i) <<
 					GTT_PAGE_SHIFT));
 		if (context_gpa == INTEL_GVT_INVALID_ADDR) {
-			gvt_err("invalid guest context descriptor\n");
+			gvt_vgpu_err("invalid guest context descriptor\n");
 			return;
 		}
 
@@ -359,15 +397,31 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	workload = scheduler->current_workload[ring_id];
 	vgpu = workload->vgpu;
 
-	if (!workload->status && !vgpu->resetting) {
+	/* For the workload w/ request, needs to wait for the context
+	 * switch to make sure request is completed.
+	 * For the workload w/o request, directly complete the workload.
+	 */
+	if (workload->req) {
+		struct drm_i915_private *dev_priv =
+			workload->vgpu->gvt->dev_priv;
+		struct intel_engine_cs *engine =
+			dev_priv->engine[workload->ring_id];
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
-		update_guest_context(workload);
+		i915_gem_request_put(fetch_and_zero(&workload->req));
+
+		if (!workload->status && !vgpu->resetting) {
+			update_guest_context(workload);
 
-		for_each_set_bit(event, workload->pending_events,
-				 INTEL_GVT_EVENT_MAX)
-			intel_vgpu_trigger_virtual_event(vgpu, event);
+			for_each_set_bit(event, workload->pending_events,
+					 INTEL_GVT_EVENT_MAX)
+				intel_vgpu_trigger_virtual_event(vgpu, event);
+		}
+		mutex_lock(&dev_priv->drm.struct_mutex);
+		/* unpin shadow ctx as the shadow_ctx update is done */
+		engine->context_unpin(engine, workload->vgpu->shadow_ctx);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -397,7 +451,7 @@ static int workload_thread(void *priv)
 	int ring_id = p->ring_id;
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload = NULL;
-	long lret;
+	struct intel_vgpu *vgpu = NULL;
 	int ret;
 	bool need_force_wake = IS_SKYLAKE(gvt->dev_priv);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -440,29 +494,19 @@ static int workload_thread(void *priv)
 		mutex_unlock(&gvt->lock);
 
 		if (ret) {
-			gvt_err("fail to dispatch workload, skip\n");
+			vgpu = workload->vgpu;
+			gvt_vgpu_err("fail to dispatch workload, skip\n");
 			goto complete;
 		}
 
 		gvt_dbg_sched("ring id %d wait workload %p\n",
 				workload->ring_id, workload);
-
-		lret = i915_wait_request(workload->req,
-					 0, MAX_SCHEDULE_TIMEOUT);
-		if (lret < 0) {
-			workload->status = lret;
-			gvt_err("fail to wait workload, skip\n");
-		} else {
-			workload->status = 0;
-		}
+		i915_wait_request(workload->req, 0, MAX_SCHEDULE_TIMEOUT);
 
 complete:
 		gvt_dbg_sched("will complete workload %p, status: %d\n",
 				workload, workload->status);
 
-		if (workload->req)
-			i915_gem_request_put(fetch_and_zero(&workload->req));
-
 		complete_current_workload(gvt, ring_id);
 
 		if (need_force_wake)
@@ -493,15 +537,16 @@ void intel_gvt_wait_vgpu_idle(struct intel_vgpu *vgpu)
 void intel_gvt_clean_workload_scheduler(struct intel_gvt *gvt)
 {
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
-	int i;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id i;
 
 	gvt_dbg_core("clean workload scheduler\n");
 
-	for (i = 0; i < I915_NUM_ENGINES; i++) {
-		if (scheduler->thread[i]) {
-			kthread_stop(scheduler->thread[i]);
-			scheduler->thread[i] = NULL;
-		}
+	for_each_engine(engine, gvt->dev_priv, i) {
+		atomic_notifier_chain_unregister(
+					&engine->context_status_notifier,
+					&gvt->shadow_ctx_notifier_block[i]);
+		kthread_stop(scheduler->thread[i]);
 	}
 }
 
@@ -509,18 +554,15 @@ int intel_gvt_init_workload_scheduler(struct intel_gvt *gvt)
 {
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct workload_thread_param *param = NULL;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id i;
 	int ret;
-	int i;
 
 	gvt_dbg_core("init workload scheduler\n");
 
 	init_waitqueue_head(&scheduler->workload_complete_wq);
 
-	for (i = 0; i < I915_NUM_ENGINES; i++) {
-		/* check ring mask at init time */
-		if (!HAS_ENGINE(gvt->dev_priv, i))
-			continue;
-
+	for_each_engine(engine, gvt->dev_priv, i) {
 		init_waitqueue_head(&scheduler->waitq[i]);
 
 		param = kzalloc(sizeof(*param), GFP_KERNEL);
@@ -539,6 +581,11 @@ int intel_gvt_init_workload_scheduler(struct intel_gvt *gvt)
 			ret = PTR_ERR(scheduler->thread[i]);
 			goto err;
 		}
+
+		gvt->shadow_ctx_notifier_block[i].notifier_call =
+					shadow_context_status_change;
+		atomic_notifier_chain_register(&engine->context_status_notifier,
+					&gvt->shadow_ctx_notifier_block[i]);
 	}
 	return 0;
 err:
@@ -550,9 +597,6 @@ err:
 
 void intel_vgpu_clean_gvt_context(struct intel_vgpu *vgpu)
 {
-	atomic_notifier_chain_unregister(&vgpu->shadow_ctx->status_notifier,
-			&vgpu->shadow_ctx_notifier_block);
-
 	i915_gem_context_put_unlocked(vgpu->shadow_ctx);
 }
 
@@ -567,10 +611,5 @@ int intel_vgpu_init_gvt_context(struct intel_vgpu *vgpu)
 
 	vgpu->shadow_ctx->engine[RCS].initialised = true;
 
-	vgpu->shadow_ctx_notifier_block.notifier_call =
-		shadow_context_status_change;
-
-	atomic_notifier_chain_register(&vgpu->shadow_ctx->status_notifier,
-				       &vgpu->shadow_ctx_notifier_block);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 95a97aa0051e..649ef280cc9a 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -64,6 +64,20 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 	WARN_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
 }
 
+static struct {
+	unsigned int low_mm;
+	unsigned int high_mm;
+	unsigned int fence;
+	enum intel_vgpu_edid edid;
+	char *name;
+} vgpu_types[] = {
+/* Fixed vGPU type table */
+	{ MB_TO_BYTES(64), MB_TO_BYTES(384), 4, GVT_EDID_1024_768, "8" },
+	{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" },
+	{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" },
+	{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" },
+};
+
 /**
  * intel_gvt_init_vgpu_types - initialize vGPU type list
  * @gvt : GVT device
@@ -78,9 +92,8 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 	unsigned int min_low;
 
 	/* vGPU type name is defined as GVTg_Vx_y which contains
-	 * physical GPU generation type and 'y' means maximum vGPU
-	 * instances user can create on one physical GPU for this
-	 * type.
+	 * physical GPU generation type (e.g V4 as BDW server, V5 as
+	 * SKL server).
 	 *
 	 * Depend on physical SKU resource, might see vGPU types like
 	 * GVTg_V4_8, GVTg_V4_4, GVTg_V4_2, etc. We can create
@@ -92,7 +105,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 	 */
 	low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE;
 	high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE;
-	num_types = 4;
+	num_types = sizeof(vgpu_types) / sizeof(vgpu_types[0]);
 
 	gvt->types = kzalloc(num_types * sizeof(struct intel_vgpu_type),
 			     GFP_KERNEL);
@@ -101,28 +114,29 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 
 	min_low = MB_TO_BYTES(32);
 	for (i = 0; i < num_types; ++i) {
-		if (low_avail / min_low == 0)
+		if (low_avail / vgpu_types[i].low_mm == 0)
 			break;
-		gvt->types[i].low_gm_size = min_low;
-		gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U));
-		gvt->types[i].fence = 4;
-		gvt->types[i].max_instance = min(low_avail / min_low,
-						 high_avail / gvt->types[i].high_gm_size);
-		gvt->types[i].avail_instance = gvt->types[i].max_instance;
+
+		gvt->types[i].low_gm_size = vgpu_types[i].low_mm;
+		gvt->types[i].high_gm_size = vgpu_types[i].high_mm;
+		gvt->types[i].fence = vgpu_types[i].fence;
+		gvt->types[i].resolution = vgpu_types[i].edid;
+		gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm,
+						   high_avail / vgpu_types[i].high_mm);
 
 		if (IS_GEN8(gvt->dev_priv))
-			sprintf(gvt->types[i].name, "GVTg_V4_%u",
-						gvt->types[i].max_instance);
+			sprintf(gvt->types[i].name, "GVTg_V4_%s",
+						vgpu_types[i].name);
 		else if (IS_GEN9(gvt->dev_priv))
-			sprintf(gvt->types[i].name, "GVTg_V5_%u",
-						gvt->types[i].max_instance);
+			sprintf(gvt->types[i].name, "GVTg_V5_%s",
+						vgpu_types[i].name);
 
-		min_low <<= 1;
-		gvt_dbg_core("type[%d]: %s max %u avail %u low %u high %u fence %u\n",
-			     i, gvt->types[i].name, gvt->types[i].max_instance,
+		gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u res %s\n",
+			     i, gvt->types[i].name,
 			     gvt->types[i].avail_instance,
 			     gvt->types[i].low_gm_size,
-			     gvt->types[i].high_gm_size, gvt->types[i].fence);
+			     gvt->types[i].high_gm_size, gvt->types[i].fence,
+			     vgpu_edid_str(gvt->types[i].resolution));
 	}
 
 	gvt->num_types = i;
@@ -138,7 +152,7 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
 {
 	int i;
 	unsigned int low_gm_avail, high_gm_avail, fence_avail;
-	unsigned int low_gm_min, high_gm_min, fence_min, total_min;
+	unsigned int low_gm_min, high_gm_min, fence_min;
 
 	/* Need to depend on maxium hw resource size but keep on
 	 * static config for now.
@@ -154,32 +168,45 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
 		low_gm_min = low_gm_avail / gvt->types[i].low_gm_size;
 		high_gm_min = high_gm_avail / gvt->types[i].high_gm_size;
 		fence_min = fence_avail / gvt->types[i].fence;
-		total_min = min(min(low_gm_min, high_gm_min), fence_min);
-		gvt->types[i].avail_instance = min(gvt->types[i].max_instance,
-						   total_min);
+		gvt->types[i].avail_instance = min(min(low_gm_min, high_gm_min),
+						   fence_min);
 
-		gvt_dbg_core("update type[%d]: %s max %u avail %u low %u high %u fence %u\n",
-		       i, gvt->types[i].name, gvt->types[i].max_instance,
+		gvt_dbg_core("update type[%d]: %s avail %u low %u high %u fence %u\n",
+		       i, gvt->types[i].name,
 		       gvt->types[i].avail_instance, gvt->types[i].low_gm_size,
 		       gvt->types[i].high_gm_size, gvt->types[i].fence);
 	}
 }
 
 /**
- * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * intel_gvt_active_vgpu - activate a virtual GPU
  * @vgpu: virtual GPU
  *
- * This function is called when user wants to destroy a virtual GPU.
+ * This function is called when user wants to activate a virtual GPU.
  *
  */
-void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
+{
+	mutex_lock(&vgpu->gvt->lock);
+	vgpu->active = true;
+	mutex_unlock(&vgpu->gvt->lock);
+}
+
+/**
+ * intel_gvt_deactive_vgpu - deactivate a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to deactivate a virtual GPU.
+ * All virtual GPU runtime information will be destroyed.
+ *
+ */
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 
 	mutex_lock(&gvt->lock);
 
 	vgpu->active = false;
-	idr_remove(&gvt->vgpu_idr, vgpu->id);
 
 	if (atomic_read(&vgpu->running_workload_num)) {
 		mutex_unlock(&gvt->lock);
@@ -188,6 +215,26 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 	}
 
 	intel_vgpu_stop_schedule(vgpu);
+
+	mutex_unlock(&gvt->lock);
+}
+
+/**
+ * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to destroy a virtual GPU.
+ *
+ */
+void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+
+	mutex_lock(&gvt->lock);
+
+	WARN(vgpu->active, "vGPU is still active!\n");
+
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_gvt_context(vgpu);
 	intel_vgpu_clean_execlist(vgpu);
@@ -248,7 +295,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_detach_hypervisor_vgpu;
 
-	ret = intel_vgpu_init_display(vgpu);
+	ret = intel_vgpu_init_display(vgpu, param->resolution);
 	if (ret)
 		goto out_clean_gtt;
 
@@ -264,7 +311,6 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_clean_shadow_ctx;
 
-	vgpu->active = true;
 	mutex_unlock(&gvt->lock);
 
 	return vgpu;
@@ -312,6 +358,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	param.low_gm_sz = type->low_gm_size;
 	param.high_gm_sz = type->high_gm_size;
 	param.fence_sz = type->fence;
+	param.resolution = type->resolution;
 
 	/* XXX current param based on MB */
 	param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz);
@@ -387,8 +434,12 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 		populate_pvinfo_page(vgpu);
 		intel_vgpu_reset_display(vgpu);
 
-		if (dmlr)
+		if (dmlr) {
 			intel_vgpu_reset_cfg_space(vgpu);
+			/* only reset the failsafe mode when dmlr reset */
+			vgpu->failsafe = false;
+			vgpu->pv_notified = false;
+		}
 	}
 
 	vgpu->resetting = false;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index e703556eba99..5c089b3c2a7e 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -248,6 +248,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_IRQ_ACTIVE:
 	case I915_PARAM_ALLOW_BATCHBUFFER:
 	case I915_PARAM_LAST_DISPATCH:
+	case I915_PARAM_HAS_EXEC_CONSTANTS:
 		/* Reject all old ums/dri params. */
 		return -ENODEV;
 	case I915_PARAM_CHIPSET_ID:
@@ -274,9 +275,6 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_BSD2:
 		value = !!dev_priv->engine[VCS2];
 		break;
-	case I915_PARAM_HAS_EXEC_CONSTANTS:
-		value = INTEL_GEN(dev_priv) >= 4;
-		break;
 	case I915_PARAM_HAS_LLC:
 		value = HAS_LLC(dev_priv);
 		break;
@@ -1436,8 +1434,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 		goto out;
 	}
 
-	intel_guc_suspend(dev_priv);
-
 	intel_display_suspend(dev);
 
 	intel_dp_mst_suspend(dev);
@@ -1788,7 +1784,7 @@ void i915_reset(struct drm_i915_private *dev_priv)
 		goto error;
 	}
 
-	i915_gem_reset_finish(dev_priv);
+	i915_gem_reset(dev_priv);
 	intel_overlay_reset(dev_priv);
 
 	/* Ok, now get things going again... */
@@ -1814,6 +1810,7 @@ void i915_reset(struct drm_i915_private *dev_priv)
 	i915_queue_hangcheck(dev_priv);
 
 wakeup:
+	i915_gem_reset_finish(dev_priv);
 	enable_irq(dev_priv->drm.irq);
 	wake_up_bit(&error->flags, I915_RESET_IN_PROGRESS);
 	return;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a4b42d31391..46fcd8b7080a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -293,6 +293,7 @@ enum plane_id {
 	PLANE_PRIMARY,
 	PLANE_SPRITE0,
 	PLANE_SPRITE1,
+	PLANE_SPRITE2,
 	PLANE_CURSOR,
 	I915_MAX_PLANES,
 };
@@ -805,6 +806,7 @@ struct intel_csr {
 	func(has_resource_streamer); \
 	func(has_runtime_pm); \
 	func(has_snoop); \
+	func(unfenced_needs_alignment); \
 	func(cursor_needs_physical); \
 	func(hws_needs_physical); \
 	func(overlay_needs_physical); \
@@ -1324,7 +1326,7 @@ struct intel_gen6_power_mgmt {
 	unsigned boosts;
 
 	/* manual wa residency calculations */
-	struct intel_rps_ei up_ei, down_ei;
+	struct intel_rps_ei ei;
 
 	/*
 	 * Protects RPS/RC6 register access and PCU communication.
@@ -2063,8 +2065,6 @@ struct drm_i915_private {
 
 	const struct intel_device_info info;
 
-	int relative_constants_mode;
-
 	void __iomem *regs;
 
 	struct intel_uncore uncore;
@@ -3341,6 +3341,7 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 }
 
 int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
+void i915_gem_reset(struct drm_i915_private *dev_priv);
 void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
 void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
 void i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6908123162d1..fe531f904062 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1434,6 +1434,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 
 	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
+	ret = -ENODEV;
+	if (obj->ops->pwrite)
+		ret = obj->ops->pwrite(obj, args);
+	if (ret != -ENODEV)
+		goto err;
+
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE |
 				   I915_WAIT_ALL,
@@ -2119,6 +2125,7 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj)
 	 */
 	shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
 	obj->mm.madv = __I915_MADV_PURGED;
+	obj->mm.pages = ERR_PTR(-EFAULT);
 }
 
 /* Try to discard unwanted pages */
@@ -2218,7 +2225,9 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 
 	__i915_gem_object_reset_page_iter(obj);
 
-	obj->ops->put_pages(obj, pages);
+	if (!IS_ERR(pages))
+		obj->ops->put_pages(obj, pages);
+
 unlock:
 	mutex_unlock(&obj->mm.lock);
 }
@@ -2437,7 +2446,7 @@ int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 	if (err)
 		return err;
 
-	if (unlikely(!obj->mm.pages)) {
+	if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
 		err = ____i915_gem_object_get_pages(obj);
 		if (err)
 			goto unlock;
@@ -2515,7 +2524,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 
 	pinned = true;
 	if (!atomic_inc_not_zero(&obj->mm.pages_pin_count)) {
-		if (unlikely(!obj->mm.pages)) {
+		if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
 			ret = ____i915_gem_object_get_pages(obj);
 			if (ret)
 				goto err_unlock;
@@ -2563,6 +2572,75 @@ err_unlock:
 	goto out_unlock;
 }
 
+static int
+i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
+			   const struct drm_i915_gem_pwrite *arg)
+{
+	struct address_space *mapping = obj->base.filp->f_mapping;
+	char __user *user_data = u64_to_user_ptr(arg->data_ptr);
+	u64 remain, offset;
+	unsigned int pg;
+
+	/* Before we instantiate/pin the backing store for our use, we
+	 * can prepopulate the shmemfs filp efficiently using a write into
+	 * the pagecache. We avoid the penalty of instantiating all the
+	 * pages, important if the user is just writing to a few and never
+	 * uses the object on the GPU, and using a direct write into shmemfs
+	 * allows it to avoid the cost of retrieving a page (either swapin
+	 * or clearing-before-use) before it is overwritten.
+	 */
+	if (READ_ONCE(obj->mm.pages))
+		return -ENODEV;
+
+	/* Before the pages are instantiated the object is treated as being
+	 * in the CPU domain. The pages will be clflushed as required before
+	 * use, and we can freely write into the pages directly. If userspace
+	 * races pwrite with any other operation; corruption will ensue -
+	 * that is userspace's prerogative!
+	 */
+
+	remain = arg->size;
+	offset = arg->offset;
+	pg = offset_in_page(offset);
+
+	do {
+		unsigned int len, unwritten;
+		struct page *page;
+		void *data, *vaddr;
+		int err;
+
+		len = PAGE_SIZE - pg;
+		if (len > remain)
+			len = remain;
+
+		err = pagecache_write_begin(obj->base.filp, mapping,
+					    offset, len, 0,
+					    &page, &data);
+		if (err < 0)
+			return err;
+
+		vaddr = kmap(page);
+		unwritten = copy_from_user(vaddr + pg, user_data, len);
+		kunmap(page);
+
+		err = pagecache_write_end(obj->base.filp, mapping,
+					  offset, len, len - unwritten,
+					  page, data);
+		if (err < 0)
+			return err;
+
+		if (unwritten)
+			return -EFAULT;
+
+		remain -= len;
+		user_data += len;
+		offset += len;
+		pg = 0;
+	} while (remain);
+
+	return 0;
+}
+
 static bool ban_context(const struct i915_gem_context *ctx)
 {
 	return (i915_gem_context_is_bannable(ctx) &&
@@ -2641,7 +2719,16 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 	for_each_engine(engine, dev_priv, id) {
 		struct drm_i915_gem_request *request;
 
+		/* Prevent request submission to the hardware until we have
+		 * completed the reset in i915_gem_reset_finish(). If a request
+		 * is completed by one engine, it may then queue a request
+		 * to a second via its engine->irq_tasklet *just* as we are
+		 * calling engine->init_hw() and also writing the ELSP.
+		 * Turning off the engine->irq_tasklet until the reset is over
+		 * prevents the race.
+		 */
 		tasklet_kill(&engine->irq_tasklet);
+		tasklet_disable(&engine->irq_tasklet);
 
 		if (engine_stalled(engine)) {
 			request = i915_gem_find_active_request(engine);
@@ -2756,7 +2843,7 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine)
 	engine->reset_hw(engine, request);
 }
 
-void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
+void i915_gem_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -2778,6 +2865,17 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
 	}
 }
 
+void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+
+	for_each_engine(engine, dev_priv, id)
+		tasklet_enable(&engine->irq_tasklet);
+}
+
 static void nop_submit_request(struct drm_i915_gem_request *request)
 {
 	dma_fence_set_error(&request->fence, -EIO);
@@ -3029,6 +3127,16 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		args->timeout_ns -= ktime_to_ns(ktime_sub(ktime_get(), start));
 		if (args->timeout_ns < 0)
 			args->timeout_ns = 0;
+
+		/*
+		 * Apparently ktime isn't accurate enough and occasionally has a
+		 * bit of mismatch in the jiffies<->nsecs<->ktime loop. So patch
+		 * things up to make the test happy. We allow up to 1 jiffy.
+		 *
+		 * This is a regression from the timespec->ktime conversion.
+		 */
+		if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns))
+			args->timeout_ns = 0;
 	}
 
 	i915_gem_object_put(obj);
@@ -3974,8 +4082,11 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE,
+
 	.get_pages = i915_gem_object_get_pages_gtt,
 	.put_pages = i915_gem_object_put_pages_gtt,
+
+	.pwrite = i915_gem_object_pwrite_gtt,
 };
 
 struct drm_i915_gem_object *
@@ -4237,6 +4348,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	i915_gem_context_lost(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
+	intel_guc_suspend(dev_priv);
+
 	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
 	cancel_delayed_work_sync(&dev_priv->gt.retire_work);
 
@@ -4583,8 +4696,6 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
 	init_waitqueue_head(&dev_priv->gpu_error.wait_queue);
 	init_waitqueue_head(&dev_priv->gpu_error.reset_queue);
 
-	dev_priv->relative_constants_mode = I915_EXEC_CONSTANTS_REL_GENERAL;
-
 	init_waitqueue_head(&dev_priv->pending_flip_queue);
 
 	dev_priv->mm.interruptible = true;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 17f90c618208..e2d83b6d376b 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -311,7 +311,6 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->ring_size = 4 * PAGE_SIZE;
 	ctx->desc_template = GEN8_CTX_ADDRESSING_MODE(dev_priv) <<
 			     GEN8_CTX_ADDRESSING_MODE_SHIFT;
-	ATOMIC_INIT_NOTIFIER_HEAD(&ctx->status_notifier);
 
 	/* GuC requires the ring to be placed above GUC_WOPCM_TOP. If GuC is not
 	 * present or not in use we still need a small bias as ring wraparound
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 0ac750b90f3d..e9c008fe14b1 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -160,9 +160,6 @@ struct i915_gem_context {
 	/** desc_template: invariant fields for the HW context descriptor */
 	u32 desc_template;
 
-	/** status_notifier: list of callbacks for context-switch changes */
-	struct atomic_notifier_head status_notifier;
-
 	/** guilty_count: How many times this context has caused a GPU hang. */
 	unsigned int guilty_count;
 	/**
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index c181b1bb3d2c..3be2503aa042 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -293,12 +293,12 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 		 * those as well to make room for our guard pages.
 		 */
 		if (check_color) {
-			if (vma->node.start + vma->node.size == node->start) {
-				if (vma->node.color == node->color)
+			if (node->start + node->size == target->start) {
+				if (node->color == target->color)
 					continue;
 			}
-			if (vma->node.start == node->start + node->size) {
-				if (vma->node.color == node->color)
+			if (node->start == target->start + target->size) {
+				if (node->color == target->color)
 					continue;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d02cfaefe1c8..15a15d00a6bf 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -888,6 +888,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *engine,
 	struct list_head ordered_vmas;
 	struct list_head pinned_vmas;
 	bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4;
+	bool needs_unfenced_map = INTEL_INFO(engine->i915)->unfenced_needs_alignment;
 	int retry;
 
 	vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
@@ -908,7 +909,8 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *engine,
 		if (!has_fenced_gpu_access)
 			entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
 		need_fence =
-			entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
+			(entry->flags & EXEC_OBJECT_NEEDS_FENCE ||
+			 needs_unfenced_map) &&
 			i915_gem_object_is_tiled(obj);
 		need_mappable = need_fence || need_reloc_mappable(vma);
 
@@ -1408,10 +1410,7 @@ execbuf_submit(struct i915_execbuffer_params *params,
 	       struct drm_i915_gem_execbuffer2 *args,
 	       struct list_head *vmas)
 {
-	struct drm_i915_private *dev_priv = params->request->i915;
 	u64 exec_start, exec_len;
-	int instp_mode;
-	u32 instp_mask;
 	int ret;
 
 	ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
@@ -1422,56 +1421,11 @@ execbuf_submit(struct i915_execbuffer_params *params,
 	if (ret)
 		return ret;
 
-	instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
-	instp_mask = I915_EXEC_CONSTANTS_MASK;
-	switch (instp_mode) {
-	case I915_EXEC_CONSTANTS_REL_GENERAL:
-	case I915_EXEC_CONSTANTS_ABSOLUTE:
-	case I915_EXEC_CONSTANTS_REL_SURFACE:
-		if (instp_mode != 0 && params->engine->id != RCS) {
-			DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
-			return -EINVAL;
-		}
-
-		if (instp_mode != dev_priv->relative_constants_mode) {
-			if (INTEL_INFO(dev_priv)->gen < 4) {
-				DRM_DEBUG("no rel constants on pre-gen4\n");
-				return -EINVAL;
-			}
-
-			if (INTEL_INFO(dev_priv)->gen > 5 &&
-			    instp_mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
-				DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
-				return -EINVAL;
-			}
-
-			/* The HW changed the meaning on this bit on gen6 */
-			if (INTEL_INFO(dev_priv)->gen >= 6)
-				instp_mask &= ~I915_EXEC_CONSTANTS_REL_SURFACE;
-		}
-		break;
-	default:
-		DRM_DEBUG("execbuf with unknown constants: %d\n", instp_mode);
+	if (args->flags & I915_EXEC_CONSTANTS_MASK) {
+		DRM_DEBUG("I915_EXEC_CONSTANTS_* unsupported\n");
 		return -EINVAL;
 	}
 
-	if (params->engine->id == RCS &&
-	    instp_mode != dev_priv->relative_constants_mode) {
-		struct intel_ring *ring = params->request->ring;
-
-		ret = intel_ring_begin(params->request, 4);
-		if (ret)
-			return ret;
-
-		intel_ring_emit(ring, MI_NOOP);
-		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(ring, INSTPM);
-		intel_ring_emit(ring, instp_mask << 16 | instp_mode);
-		intel_ring_advance(ring);
-
-		dev_priv->relative_constants_mode = instp_mode;
-	}
-
 	if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
 		ret = i915_reset_gen7_sol_offsets(params->request);
 		if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2801a4d56324..96e45a4d5441 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2704,7 +2704,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 
 	if (unlikely(ggtt->do_idle_maps)) {
-		if (i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED)) {
+		if (i915_gem_wait_for_idle(dev_priv, 0)) {
 			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index bf90b07163d1..76b80a0be797 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -54,6 +54,9 @@ struct drm_i915_gem_object_ops {
 	struct sg_table *(*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *, struct sg_table *);
 
+	int (*pwrite)(struct drm_i915_gem_object *,
+		      const struct drm_i915_gem_pwrite *);
+
 	int (*dmabuf_export)(struct drm_i915_gem_object *);
 	void (*release)(struct drm_i915_gem_object *);
 };
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index e7c3c0318ff6..da70bfe97ec5 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -37,6 +37,17 @@ static const char *i915_fence_get_driver_name(struct dma_fence *fence)
 
 static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
 {
+	/* The timeline struct (as part of the ppgtt underneath a context)
+	 * may be freed when the request is no longer in use by the GPU.
+	 * We could extend the life of a context to beyond that of all
+	 * fences, possibly keeping the hw resource around indefinitely,
+	 * or we just give them a false name. Since
+	 * dma_fence_ops.get_timeline_name is a debug feature, the occasional
+	 * lie seems justifiable.
+	 */
+	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		return "signaled";
+
 	return to_request(fence)->timeline->common->name;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 401006b4c6a3..70b3832a79dd 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -53,6 +53,17 @@ static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 	BUG();
 }
 
+static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock)
+{
+	if (!unlock)
+		return;
+
+	mutex_unlock(&dev->struct_mutex);
+
+	/* expedite the RCU grace period to free some request slabs */
+	synchronize_rcu_expedited();
+}
+
 static bool any_vma_pinned(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
@@ -232,11 +243,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		intel_runtime_pm_put(dev_priv);
 
 	i915_gem_retire_requests(dev_priv);
-	if (unlock)
-		mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	/* expedite the RCU grace period to free some request slabs */
-	synchronize_rcu_expedited();
+	i915_gem_shrinker_unlock(&dev_priv->drm, unlock);
 
 	return count;
 }
@@ -263,7 +271,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_ACTIVE);
-	rcu_barrier(); /* wait until our RCU delayed slab frees are completed */
+	synchronize_rcu(); /* wait for our earlier RCU delayed slab frees */
 
 	return freed;
 }
@@ -293,8 +301,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 			count += obj->base.size >> PAGE_SHIFT;
 	}
 
-	if (unlock)
-		mutex_unlock(&dev->struct_mutex);
+	i915_gem_shrinker_unlock(dev, unlock);
 
 	return count;
 }
@@ -321,8 +328,8 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 					 sc->nr_to_scan - freed,
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
-	if (unlock)
-		mutex_unlock(&dev->struct_mutex);
+
+	i915_gem_shrinker_unlock(dev, unlock);
 
 	return freed;
 }
@@ -364,8 +371,7 @@ i915_gem_shrinker_unlock_uninterruptible(struct drm_i915_private *dev_priv,
 					 struct shrinker_lock_uninterruptible *slu)
 {
 	dev_priv->mm.interruptible = slu->was_interruptible;
-	if (slu->unlock)
-		mutex_unlock(&dev_priv->drm.struct_mutex);
+	i915_gem_shrinker_unlock(&dev_priv->drm, slu->unlock);
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e6ffef2f707a..b6c886ac901b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1046,68 +1046,51 @@ static void vlv_c0_read(struct drm_i915_private *dev_priv,
 	ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT);
 }
 
-static bool vlv_c0_above(struct drm_i915_private *dev_priv,
-			 const struct intel_rps_ei *old,
-			 const struct intel_rps_ei *now,
-			 int threshold)
-{
-	u64 time, c0;
-	unsigned int mul = 100;
-
-	if (old->cz_clock == 0)
-		return false;
-
-	if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
-		mul <<= 8;
-
-	time = now->cz_clock - old->cz_clock;
-	time *= threshold * dev_priv->czclk_freq;
-
-	/* Workload can be split between render + media, e.g. SwapBuffers
-	 * being blitted in X after being rendered in mesa. To account for
-	 * this we need to combine both engines into our activity counter.
-	 */
-	c0 = now->render_c0 - old->render_c0;
-	c0 += now->media_c0 - old->media_c0;
-	c0 *= mul * VLV_CZ_CLOCK_TO_MILLI_SEC;
-
-	return c0 >= time;
-}
-
 void gen6_rps_reset_ei(struct drm_i915_private *dev_priv)
 {
-	vlv_c0_read(dev_priv, &dev_priv->rps.down_ei);
-	dev_priv->rps.up_ei = dev_priv->rps.down_ei;
+	memset(&dev_priv->rps.ei, 0, sizeof(dev_priv->rps.ei));
 }
 
 static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
 {
+	const struct intel_rps_ei *prev = &dev_priv->rps.ei;
 	struct intel_rps_ei now;
 	u32 events = 0;
 
-	if ((pm_iir & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED)) == 0)
+	if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0)
 		return 0;
 
 	vlv_c0_read(dev_priv, &now);
 	if (now.cz_clock == 0)
 		return 0;
 
-	if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) {
-		if (!vlv_c0_above(dev_priv,
-				  &dev_priv->rps.down_ei, &now,
-				  dev_priv->rps.down_threshold))
-			events |= GEN6_PM_RP_DOWN_THRESHOLD;
-		dev_priv->rps.down_ei = now;
-	}
+	if (prev->cz_clock) {
+		u64 time, c0;
+		unsigned int mul;
+
+		mul = VLV_CZ_CLOCK_TO_MILLI_SEC * 100; /* scale to threshold% */
+		if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
+			mul <<= 8;
 
-	if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
-		if (vlv_c0_above(dev_priv,
-				 &dev_priv->rps.up_ei, &now,
-				 dev_priv->rps.up_threshold))
-			events |= GEN6_PM_RP_UP_THRESHOLD;
-		dev_priv->rps.up_ei = now;
+		time = now.cz_clock - prev->cz_clock;
+		time *= dev_priv->czclk_freq;
+
+		/* Workload can be split between render + media,
+		 * e.g. SwapBuffers being blitted in X after being rendered in
+		 * mesa. To account for this we need to combine both engines
+		 * into our activity counter.
+		 */
+		c0 = now.render_c0 - prev->render_c0;
+		c0 += now.media_c0 - prev->media_c0;
+		c0 *= mul;
+
+		if (c0 > time * dev_priv->rps.up_threshold)
+			events = GEN6_PM_RP_UP_THRESHOLD;
+		else if (c0 < time * dev_priv->rps.down_threshold)
+			events = GEN6_PM_RP_DOWN_THRESHOLD;
 	}
 
+	dev_priv->rps.ei = now;
 	return events;
 }
 
@@ -4228,7 +4211,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	/* Let's track the enabled rps events */
 	if (IS_VALLEYVIEW(dev_priv))
 		/* WaGsvRC0ResidencyMethod:vlv */
-		dev_priv->pm_rps_events = GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED;
+		dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED;
 	else
 		dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
 
@@ -4266,6 +4249,16 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	if (!IS_GEN2(dev_priv))
 		dev->vblank_disable_immediate = true;
 
+	/* Most platforms treat the display irq block as an always-on
+	 * power domain. vlv/chv can disable it at runtime and need
+	 * special care to avoid writing any of the display block registers
+	 * outside of the power domain. We defer setting up the display irqs
+	 * in this case to the runtime pm.
+	 */
+	dev_priv->display_irqs_enabled = true;
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		dev_priv->display_irqs_enabled = false;
+
 	dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp;
 	dev->driver->get_scanout_position = i915_get_crtc_scanoutpos;
 
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index ecb487b5356f..9bbbd4e83e3c 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -60,6 +60,7 @@
 	.has_overlay = 1, .overlay_needs_physical = 1, \
 	.has_gmch_display = 1, \
 	.hws_needs_physical = 1, \
+	.unfenced_needs_alignment = 1, \
 	.ring_mask = RENDER_RING, \
 	GEN_DEFAULT_PIPEOFFSETS, \
 	CURSOR_OFFSETS
@@ -101,6 +102,7 @@ static const struct intel_device_info intel_i915g_info = {
 	.platform = INTEL_I915G, .cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.hws_needs_physical = 1,
+	.unfenced_needs_alignment = 1,
 };
 
 static const struct intel_device_info intel_i915gm_info = {
@@ -112,6 +114,7 @@ static const struct intel_device_info intel_i915gm_info = {
 	.supports_tv = 1,
 	.has_fbc = 1,
 	.hws_needs_physical = 1,
+	.unfenced_needs_alignment = 1,
 };
 
 static const struct intel_device_info intel_i945g_info = {
@@ -120,6 +123,7 @@ static const struct intel_device_info intel_i945g_info = {
 	.has_hotplug = 1, .cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.hws_needs_physical = 1,
+	.unfenced_needs_alignment = 1,
 };
 
 static const struct intel_device_info intel_i945gm_info = {
@@ -130,6 +134,7 @@ static const struct intel_device_info intel_i945gm_info = {
 	.supports_tv = 1,
 	.has_fbc = 1,
 	.hws_needs_physical = 1,
+	.unfenced_needs_alignment = 1,
 };
 
 static const struct intel_device_info intel_g33_info = {
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index a1b7eec58be2..70964ca9251e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1705,7 +1705,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 	 */
 	if (WARN_ON(stream->sample_flags != props->sample_flags)) {
 		ret = -ENODEV;
-		goto err_alloc;
+		goto err_flags;
 	}
 
 	list_add(&stream->link, &dev_priv->perf.streams);
@@ -1728,6 +1728,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 
 err_open:
 	list_del(&stream->link);
+err_flags:
 	if (stream->ops->destroy)
 		stream->ops->destroy(stream);
 err_alloc:
@@ -1793,6 +1794,11 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 		if (ret)
 			return ret;
 
+		if (id == 0 || id >= DRM_I915_PERF_PROP_MAX) {
+			DRM_DEBUG("Unknown i915 perf property ID\n");
+			return -EINVAL;
+		}
+
 		switch ((enum drm_i915_perf_property_id)id) {
 		case DRM_I915_PERF_PROP_CTX_HANDLE:
 			props->single_context = 1;
@@ -1862,9 +1868,8 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 			props->oa_periodic = true;
 			props->oa_period_exponent = value;
 			break;
-		default:
+		case DRM_I915_PERF_PROP_MAX:
 			MISSING_CASE(id);
-			DRM_DEBUG("Unknown i915 perf property ID\n");
 			return -EINVAL;
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 155906e84812..df20e9bc1c0f 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -512,10 +512,36 @@ err_unpin:
 	return ret;
 }
 
+static void
+i915_vma_remove(struct i915_vma *vma)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+
+	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
+
+	drm_mm_remove_node(&vma->node);
+	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
+
+	/* Since the unbound list is global, only move to that list if
+	 * no more VMAs exist.
+	 */
+	if (--obj->bind_count == 0)
+		list_move_tail(&obj->global_link,
+			       &to_i915(obj->base.dev)->mm.unbound_list);
+
+	/* And finally now the object is completely decoupled from this vma,
+	 * we can drop its hold on the backing storage and allow it to be
+	 * reaped by the shrinker.
+	 */
+	i915_gem_object_unpin_pages(obj);
+	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+}
+
 int __i915_vma_do_pin(struct i915_vma *vma,
 		      u64 size, u64 alignment, u64 flags)
 {
-	unsigned int bound = vma->flags;
+	const unsigned int bound = vma->flags;
 	int ret;
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
@@ -524,18 +550,18 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 
 	if (WARN_ON(bound & I915_VMA_PIN_OVERFLOW)) {
 		ret = -EBUSY;
-		goto err;
+		goto err_unpin;
 	}
 
 	if ((bound & I915_VMA_BIND_MASK) == 0) {
 		ret = i915_vma_insert(vma, size, alignment, flags);
 		if (ret)
-			goto err;
+			goto err_unpin;
 	}
 
 	ret = i915_vma_bind(vma, vma->obj->cache_level, flags);
 	if (ret)
-		goto err;
+		goto err_remove;
 
 	if ((bound ^ vma->flags) & I915_VMA_GLOBAL_BIND)
 		__i915_vma_set_map_and_fenceable(vma);
@@ -544,7 +570,12 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 	GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
 	return 0;
 
-err:
+err_remove:
+	if ((bound & I915_VMA_BIND_MASK) == 0) {
+		GEM_BUG_ON(vma->pages);
+		i915_vma_remove(vma);
+	}
+err_unpin:
 	__i915_vma_unpin(vma);
 	return ret;
 }
@@ -657,9 +688,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 	}
 	vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
 
-	drm_mm_remove_node(&vma->node);
-	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
-
 	if (vma->pages != obj->mm.pages) {
 		GEM_BUG_ON(!vma->pages);
 		sg_free_table(vma->pages);
@@ -667,18 +695,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 	}
 	vma->pages = NULL;
 
-	/* Since the unbound list is global, only move to that list if
-	 * no more VMAs exist. */
-	if (--obj->bind_count == 0)
-		list_move_tail(&obj->global_link,
-			       &to_i915(obj->base.dev)->mm.unbound_list);
-
-	/* And finally now the object is completely decoupled from this vma,
-	 * we can drop its hold on the backing storage and allow it to be
-	 * reaped by the shrinker.
-	 */
-	i915_gem_object_unpin_pages(obj);
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+	i915_vma_remove(vma);
 
 destroy:
 	if (unlikely(i915_vma_is_closed(vma)))
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 0085bc745f6a..de219b71fb76 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -35,7 +35,6 @@
  */
 
 #define I915_CSR_GLK "i915/glk_dmc_ver1_01.bin"
-MODULE_FIRMWARE(I915_CSR_GLK);
 #define GLK_CSR_VERSION_REQUIRED	CSR_VERSION(1, 1)
 
 #define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin"
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 01341670738f..ed1f4f272b4f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3669,10 +3669,6 @@ static void intel_update_pipe_config(struct intel_crtc *crtc,
 	/* drm_atomic_helper_update_legacy_modeset_state might not be called. */
 	crtc->base.mode = crtc->base.state->mode;
 
-	DRM_DEBUG_KMS("Updating pipe size %ix%i -> %ix%i\n",
-		      old_crtc_state->pipe_src_w, old_crtc_state->pipe_src_h,
-		      pipe_config->pipe_src_w, pipe_config->pipe_src_h);
-
 	/*
 	 * Update pipe size and adjust fitter if needed: the reason for this is
 	 * that in compute_mode_changes we check the native mode (not the pfit
@@ -4796,23 +4792,17 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc->config->scaler_state;
 
-	DRM_DEBUG_KMS("for crtc_state = %p\n", crtc->config);
-
 	if (crtc->config->pch_pfit.enabled) {
 		int id;
 
-		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) {
-			DRM_ERROR("Requesting pfit without getting a scaler first\n");
+		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
 			return;
-		}
 
 		id = scaler_state->scaler_id;
 		I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
 			PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
 		I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
 		I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
-
-		DRM_DEBUG_KMS("for crtc_state = %p scaler_id = %d\n", crtc->config, id);
 	}
 }
 
@@ -14379,6 +14369,24 @@ static void skl_update_crtcs(struct drm_atomic_state *state,
 	} while (progress);
 }
 
+static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv)
+{
+	struct intel_atomic_state *state, *next;
+	struct llist_node *freed;
+
+	freed = llist_del_all(&dev_priv->atomic_helper.free_list);
+	llist_for_each_entry_safe(state, next, freed, freed)
+		drm_atomic_state_put(&state->base);
+}
+
+static void intel_atomic_helper_free_state_worker(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), atomic_helper.free_work);
+
+	intel_atomic_helper_free_state(dev_priv);
+}
+
 static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -14545,6 +14553,8 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	 * can happen also when the device is completely off.
 	 */
 	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
+
+	intel_atomic_helper_free_state(dev_priv);
 }
 
 static void intel_atomic_commit_work(struct work_struct *work)
@@ -14946,17 +14956,19 @@ static void intel_begin_crtc_commit(struct drm_crtc *crtc,
 		to_intel_atomic_state(old_crtc_state->state);
 	bool modeset = needs_modeset(crtc->state);
 
+	if (!modeset &&
+	    (intel_cstate->base.color_mgmt_changed ||
+	     intel_cstate->update_pipe)) {
+		intel_color_set_csc(crtc->state);
+		intel_color_load_luts(crtc->state);
+	}
+
 	/* Perform vblank evasion around commit operation */
 	intel_pipe_update_start(intel_crtc);
 
 	if (modeset)
 		goto out;
 
-	if (crtc->state->color_mgmt_changed || to_intel_crtc_state(crtc->state)->update_pipe) {
-		intel_color_set_csc(crtc->state);
-		intel_color_load_luts(crtc->state);
-	}
-
 	if (intel_cstate->update_pipe)
 		intel_update_pipe_config(intel_crtc, old_intel_cstate);
 	else if (INTEL_GEN(dev_priv) >= 9)
@@ -16599,18 +16611,6 @@ fail:
 	drm_modeset_acquire_fini(&ctx);
 }
 
-static void intel_atomic_helper_free_state(struct work_struct *work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), atomic_helper.free_work);
-	struct intel_atomic_state *state, *next;
-	struct llist_node *freed;
-
-	freed = llist_del_all(&dev_priv->atomic_helper.free_list);
-	llist_for_each_entry_safe(state, next, freed, freed)
-		drm_atomic_state_put(&state->base);
-}
-
 int intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16631,7 +16631,7 @@ int intel_modeset_init(struct drm_device *dev)
 	dev->mode_config.funcs = &intel_mode_funcs;
 
 	INIT_WORK(&dev_priv->atomic_helper.free_work,
-		  intel_atomic_helper_free_state);
+		  intel_atomic_helper_free_state_worker);
 
 	intel_init_quirks(dev);
 
@@ -16696,12 +16696,11 @@ int intel_modeset_init(struct drm_device *dev)
 		}
 	}
 
-	intel_update_czclk(dev_priv);
-	intel_update_cdclk(dev_priv);
-	dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq;
-
 	intel_shared_dpll_init(dev);
 
+	intel_update_czclk(dev_priv);
+	intel_modeset_init_hw(dev);
+
 	if (dev_priv->max_cdclk_freq == 0)
 		intel_update_max_cdclk(dev_priv);
 
@@ -17258,8 +17257,6 @@ void intel_modeset_gem_init(struct drm_device *dev)
 
 	intel_init_gt_powersave(dev_priv);
 
-	intel_modeset_init_hw(dev);
-
 	intel_setup_overlay(dev_priv);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 371acf109e34..ab1be5c80ea5 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -105,6 +105,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
+
 	dev_priv->engine[id] = engine;
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 1b8ba2e77539..2d449fb5d1d2 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -357,14 +357,13 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 				    bool *enabled, int width, int height)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
-	unsigned long conn_configured, mask;
+	unsigned long conn_configured, conn_seq, mask;
 	unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
 	int i, j;
 	bool *save_enabled;
 	bool fallback = true;
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
-	int pass = 0;
 
 	save_enabled = kcalloc(count, sizeof(bool), GFP_KERNEL);
 	if (!save_enabled)
@@ -374,6 +373,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 	mask = BIT(count) - 1;
 	conn_configured = 0;
 retry:
+	conn_seq = conn_configured;
 	for (i = 0; i < count; i++) {
 		struct drm_fb_helper_connector *fb_conn;
 		struct drm_connector *connector;
@@ -387,7 +387,7 @@ retry:
 		if (conn_configured & BIT(i))
 			continue;
 
-		if (pass == 0 && !connector->has_tile)
+		if (conn_seq == 0 && !connector->has_tile)
 			continue;
 
 		if (connector->status == connector_status_connected)
@@ -498,10 +498,8 @@ retry:
 		conn_configured |= BIT(i);
 	}
 
-	if ((conn_configured & mask) != mask) {
-		pass++;
+	if ((conn_configured & mask) != mask && conn_configured != conn_seq)
 		goto retry;
-	}
 
 	/*
 	 * If the BIOS didn't enable everything it could, fall back to have the
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index d23c0fcff751..8c04eca84351 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -77,6 +77,11 @@ int intel_gvt_init(struct drm_i915_private *dev_priv)
 		goto bail;
 	}
 
+	if (!i915.enable_execlists) {
+		DRM_INFO("GPU guest virtualisation [GVT-g] disabled due to disabled execlist submission [i915.enable_execlists module parameter]\n");
+		goto bail;
+	}
+
 	/*
 	 * We're not in host or fail to find a MPT module, disable GVT-g
 	 */
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ebae2bd83918..24b2fa5b6282 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1298,16 +1298,34 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 
 static bool hdmi_12bpc_possible(struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_i915_private *dev_priv =
+		to_i915(crtc_state->base.crtc->dev);
+	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_connector_state *connector_state;
+	struct drm_connector *connector;
+	int i;
 
-	if (HAS_GMCH_DISPLAY(to_i915(dev)))
+	if (HAS_GMCH_DISPLAY(dev_priv))
 		return false;
 
 	/*
 	 * HDMI 12bpc affects the clocks, so it's only possible
 	 * when not cloning with other encoder types.
 	 */
-	return crtc_state->output_types == 1 << INTEL_OUTPUT_HDMI;
+	if (crtc_state->output_types != 1 << INTEL_OUTPUT_HDMI)
+		return false;
+
+	for_each_connector_in_state(state, connector, connector_state, i) {
+		const struct drm_display_info *info = &connector->display_info;
+
+		if (connector_state->crtc != crtc_state->base.crtc)
+			continue;
+
+		if ((info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_36) == 0)
+			return false;
+	}
+
+	return true;
 }
 
 bool intel_hdmi_compute_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index b62e3f8ad415..54208bef7a83 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -219,7 +219,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 			}
 		}
 	}
-	if (dev_priv->display.hpd_irq_setup)
+	if (dev_priv->display_irqs_enabled && dev_priv->display.hpd_irq_setup)
 		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
@@ -425,7 +425,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 		}
 	}
 
-	if (storm_detected)
+	if (storm_detected && dev_priv->display_irqs_enabled)
 		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock(&dev_priv->irq_lock);
 
@@ -471,10 +471,12 @@ void intel_hpd_init(struct drm_i915_private *dev_priv)
 	 * Interrupt setup is already guaranteed to be single-threaded, this is
 	 * just to make the assert_spin_locked checks happy.
 	 */
-	spin_lock_irq(&dev_priv->irq_lock);
-	if (dev_priv->display.hpd_irq_setup)
-		dev_priv->display.hpd_irq_setup(dev_priv);
-	spin_unlock_irq(&dev_priv->irq_lock);
+	if (dev_priv->display_irqs_enabled && dev_priv->display.hpd_irq_setup) {
+		spin_lock_irq(&dev_priv->irq_lock);
+		if (dev_priv->display_irqs_enabled)
+			dev_priv->display.hpd_irq_setup(dev_priv);
+		spin_unlock_irq(&dev_priv->irq_lock);
+	}
 }
 
 static void i915_hpd_poll_init_work(struct work_struct *work)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ebf8023d21e6..47517a02f0a4 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -345,7 +345,8 @@ execlists_context_status_change(struct drm_i915_gem_request *rq,
 	if (!IS_ENABLED(CONFIG_DRM_I915_GVT))
 		return;
 
-	atomic_notifier_call_chain(&rq->ctx->status_notifier, status, rq);
+	atomic_notifier_call_chain(&rq->engine->context_status_notifier,
+				   status, rq);
 }
 
 static void
@@ -669,15 +670,14 @@ static void execlists_submit_request(struct drm_i915_gem_request *request)
 static struct intel_engine_cs *
 pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked)
 {
-	struct intel_engine_cs *engine;
+	struct intel_engine_cs *engine =
+		container_of(pt, struct drm_i915_gem_request, priotree)->engine;
+
+	GEM_BUG_ON(!locked);
 
-	engine = container_of(pt,
-			      struct drm_i915_gem_request,
-			      priotree)->engine;
 	if (engine != locked) {
-		if (locked)
-			spin_unlock_irq(&locked->timeline->lock);
-		spin_lock_irq(&engine->timeline->lock);
+		spin_unlock(&locked->timeline->lock);
+		spin_lock(&engine->timeline->lock);
 	}
 
 	return engine;
@@ -685,7 +685,7 @@ pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked)
 
 static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
 {
-	struct intel_engine_cs *engine = NULL;
+	struct intel_engine_cs *engine;
 	struct i915_dependency *dep, *p;
 	struct i915_dependency stack;
 	LIST_HEAD(dfs);
@@ -719,26 +719,23 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
 	list_for_each_entry_safe(dep, p, &dfs, dfs_link) {
 		struct i915_priotree *pt = dep->signaler;
 
-		list_for_each_entry(p, &pt->signalers_list, signal_link)
+		/* Within an engine, there can be no cycle, but we may
+		 * refer to the same dependency chain multiple times
+		 * (redundant dependencies are not eliminated) and across
+		 * engines.
+		 */
+		list_for_each_entry(p, &pt->signalers_list, signal_link) {
+			GEM_BUG_ON(p->signaler->priority < pt->priority);
 			if (prio > READ_ONCE(p->signaler->priority))
 				list_move_tail(&p->dfs_link, &dfs);
+		}
 
 		list_safe_reset_next(dep, p, dfs_link);
-		if (!RB_EMPTY_NODE(&pt->node))
-			continue;
-
-		engine = pt_lock_engine(pt, engine);
-
-		/* If it is not already in the rbtree, we can update the
-		 * priority inplace and skip over it (and its dependencies)
-		 * if it is referenced *again* as we descend the dfs.
-		 */
-		if (prio > pt->priority && RB_EMPTY_NODE(&pt->node)) {
-			pt->priority = prio;
-			list_del_init(&dep->dfs_link);
-		}
 	}
 
+	engine = request->engine;
+	spin_lock_irq(&engine->timeline->lock);
+
 	/* Fifo and depth-first replacement ensure our deps execute before us */
 	list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
 		struct i915_priotree *pt = dep->signaler;
@@ -750,16 +747,15 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
 		if (prio <= pt->priority)
 			continue;
 
-		GEM_BUG_ON(RB_EMPTY_NODE(&pt->node));
-
 		pt->priority = prio;
-		rb_erase(&pt->node, &engine->execlist_queue);
-		if (insert_request(pt, &engine->execlist_queue))
-			engine->execlist_first = &pt->node;
+		if (!RB_EMPTY_NODE(&pt->node)) {
+			rb_erase(&pt->node, &engine->execlist_queue);
+			if (insert_request(pt, &engine->execlist_queue))
+				engine->execlist_first = &pt->node;
+		}
 	}
 
-	if (engine)
-		spin_unlock_irq(&engine->timeline->lock);
+	spin_unlock_irq(&engine->timeline->lock);
 
 	/* XXX Do we need to preempt to make room for us and our deps? */
 }
@@ -1439,7 +1435,9 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 	GEM_BUG_ON(request->ctx != port[0].request->ctx);
 
 	/* Reset WaIdleLiteRestore:bdw,skl as well */
-	request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32);
+	request->tail =
+		intel_ring_wrap(request->ring,
+				request->wa_tail - WA_TAIL_DWORDS*sizeof(u32));
 }
 
 static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 249623d45be0..6a29784d2b41 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4891,6 +4891,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		break;
 	}
 
+	/* When byt can survive without system hang with dynamic
+	 * sw freq adjustments, this restriction can be lifted.
+	 */
+	if (IS_VALLEYVIEW(dev_priv))
+		goto skip_hw_write;
+
 	I915_WRITE(GEN6_RP_UP_EI,
 		   GT_INTERVAL_FROM_US(dev_priv, ei_up));
 	I915_WRITE(GEN6_RP_UP_THRESHOLD,
@@ -4911,6 +4917,7 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		   GEN6_RP_UP_BUSY_AVG |
 		   GEN6_RP_DOWN_IDLE_AVG);
 
+skip_hw_write:
 	dev_priv->rps.power = new_power;
 	dev_priv->rps.up_threshold = threshold_up;
 	dev_priv->rps.down_threshold = threshold_down;
@@ -4921,8 +4928,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 {
 	u32 mask = 0;
 
+	/* We use UP_EI_EXPIRED interupts for both up/down in manual mode */
 	if (val > dev_priv->rps.min_freq_softlimit)
-		mask |= GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
+		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
 	if (val < dev_priv->rps.max_freq_softlimit)
 		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
 
@@ -5032,7 +5040,7 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
-		if (dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED))
+		if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED)
 			gen6_rps_reset_ei(dev_priv);
 		I915_WRITE(GEN6_PMINTRMSK,
 			   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
@@ -7916,10 +7924,10 @@ static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
  * @timeout_base_ms: timeout for polling with preemption enabled
  *
  * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
- * reports an error or an overall timeout of @timeout_base_ms+10 ms expires.
+ * reports an error or an overall timeout of @timeout_base_ms+50 ms expires.
  * The request is acknowledged once the PCODE reply dword equals @reply after
  * applying @reply_mask. Polling is first attempted with preemption enabled
- * for @timeout_base_ms and if this times out for another 10 ms with
+ * for @timeout_base_ms and if this times out for another 50 ms with
  * preemption disabled.
  *
  * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
@@ -7955,14 +7963,15 @@ int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
 	 * worst case) _and_ PCODE was busy for some reason even after a
 	 * (queued) request and @timeout_base_ms delay. As a workaround retry
 	 * the poll with preemption disabled to maximize the number of
-	 * requests. Increase the timeout from @timeout_base_ms to 10ms to
+	 * requests. Increase the timeout from @timeout_base_ms to 50ms to
 	 * account for interrupts that could reduce the number of these
-	 * requests.
+	 * requests, and for any quirks of the PCODE firmware that delays
+	 * the request completion.
 	 */
 	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
 	WARN_ON_ONCE(timeout_base_ms > 3);
 	preempt_disable();
-	ret = wait_for_atomic(COND, 10);
+	ret = wait_for_atomic(COND, 50);
 	preempt_enable();
 
 out:
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 91bc4abf5d3e..6c5f9958197d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2024,6 +2024,8 @@ static int intel_ring_context_pin(struct intel_engine_cs *engine,
 		ret = context_pin(ctx, flags);
 		if (ret)
 			goto error;
+
+		ce->state->obj->mm.dirty = true;
 	}
 
 	/* The kernel context is only used as a placeholder for flushing the
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 79c2b8d72322..8cb2078c5bfc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -403,6 +403,9 @@ struct intel_engine_cs {
 	 */
 	struct i915_gem_context *legacy_active_context;
 
+	/* status_notifier: list of callbacks for context-switch changes */
+	struct atomic_notifier_head context_status_notifier;
+
 	struct intel_engine_hangcheck hangcheck;
 
 	bool needs_cmd_parser;
@@ -518,11 +521,17 @@ static inline void intel_ring_advance(struct intel_ring *ring)
 	 */
 }
 
+static inline u32
+intel_ring_wrap(const struct intel_ring *ring, u32 pos)
+{
+	return pos & (ring->size - 1);
+}
+
 static inline u32 intel_ring_offset(struct intel_ring *ring, void *addr)
 {
 	/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
 	u32 offset = addr - ring->vaddr;
-	return offset & (ring->size - 1);
+	return intel_ring_wrap(ring, offset);
 }
 
 int __intel_ring_space(int head, int tail, int size);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 9ef54688872a..9481ca9a3ae7 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -254,9 +254,6 @@ skl_update_plane(struct drm_plane *drm_plane,
 		int scaler_id = plane_state->scaler_id;
 		const struct intel_scaler *scaler;
 
-		DRM_DEBUG_KMS("plane = %d PS_PLANE_SEL(plane) = 0x%x\n",
-			      plane_id, PS_PLANE_SEL(plane_id));
-
 		scaler = &crtc_state->scaler_state.scalers[scaler_id];
 
 		I915_WRITE(SKL_PS_CTRL(pipe, scaler_id),
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index abe08885a5ba..b7ff592b14f5 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -119,6 +119,8 @@ fw_domains_get(struct drm_i915_private *dev_priv, enum forcewake_domains fw_doma
 
 	for_each_fw_domain_masked(d, fw_domains, dev_priv)
 		fw_domain_wait_ack(d);
+
+	dev_priv->uncore.fw_domains_active |= fw_domains;
 }
 
 static void
@@ -130,6 +132,8 @@ fw_domains_put(struct drm_i915_private *dev_priv, enum forcewake_domains fw_doma
 		fw_domain_put(d);
 		fw_domain_posting_read(d);
 	}
+
+	dev_priv->uncore.fw_domains_active &= ~fw_domains;
 }
 
 static void
@@ -240,10 +244,8 @@ intel_uncore_fw_release_timer(struct hrtimer *timer)
 	if (WARN_ON(domain->wake_count == 0))
 		domain->wake_count++;
 
-	if (--domain->wake_count == 0) {
+	if (--domain->wake_count == 0)
 		dev_priv->uncore.funcs.force_wake_put(dev_priv, domain->mask);
-		dev_priv->uncore.fw_domains_active &= ~domain->mask;
-	}
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
@@ -454,10 +456,8 @@ static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
 			fw_domains &= ~domain->mask;
 	}
 
-	if (fw_domains) {
+	if (fw_domains)
 		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
-		dev_priv->uncore.fw_domains_active |= fw_domains;
-	}
 }
 
 /**
@@ -968,7 +968,6 @@ static noinline void ___force_wake_auto(struct drm_i915_private *dev_priv,
 		fw_domain_arm_timer(domain);
 
 	dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
-	dev_priv->uncore.fw_domains_active |= fw_domains;
 }
 
 static inline void __force_wake_auto(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 4414cf73735d..36602ac7e248 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1,4 +1,4 @@
-/* Copyright (c) 2016 The Linux Foundation. All rights reserved.
+/* Copyright (c) 2016-2017 The Linux Foundation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 and
@@ -534,7 +534,7 @@ static void a5xx_destroy(struct msm_gpu *gpu)
 	}
 
 	if (a5xx_gpu->gpmu_bo) {
-		if (a5xx_gpu->gpmu_bo)
+		if (a5xx_gpu->gpmu_iova)
 			msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->id);
 		drm_gem_object_unreference_unlocked(a5xx_gpu->gpmu_bo);
 	}
@@ -860,7 +860,9 @@ static const struct adreno_gpu_funcs funcs = {
 		.idle = a5xx_idle,
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
+#ifdef CONFIG_DEBUG_FS
 		.show = a5xx_show,
+#endif
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index c9bd1e6225f4..5ae65426b4e5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -418,18 +418,27 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	return 0;
 }
 
-void adreno_gpu_cleanup(struct adreno_gpu *gpu)
+void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 {
-	if (gpu->memptrs_bo) {
-		if (gpu->memptrs)
-			msm_gem_put_vaddr(gpu->memptrs_bo);
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if (adreno_gpu->memptrs_bo) {
+		if (adreno_gpu->memptrs)
+			msm_gem_put_vaddr(adreno_gpu->memptrs_bo);
+
+		if (adreno_gpu->memptrs_iova)
+			msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->id);
+
+		drm_gem_object_unreference_unlocked(adreno_gpu->memptrs_bo);
+	}
+	release_firmware(adreno_gpu->pm4);
+	release_firmware(adreno_gpu->pfp);
 
-		if (gpu->memptrs_iova)
-			msm_gem_put_iova(gpu->memptrs_bo, gpu->base.id);
+	msm_gpu_cleanup(gpu);
 
-		drm_gem_object_unreference_unlocked(gpu->memptrs_bo);
+	if (gpu->aspace) {
+		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
+			iommu_ports, ARRAY_SIZE(iommu_ports));
+		msm_gem_address_space_destroy(gpu->aspace);
 	}
-	release_firmware(gpu->pm4);
-	release_firmware(gpu->pfp);
-	msm_gpu_cleanup(&gpu->base);
 }
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 921270ea6059..a879ffa534b4 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -171,7 +171,7 @@ dsi_mgr_phy_enable(int id,
 			}
 		}
 	} else {
-		msm_dsi_host_reset_phy(mdsi->host);
+		msm_dsi_host_reset_phy(msm_dsi->host);
 		ret = enable_phy(msm_dsi, src_pll_id, &shared_timings[id]);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
index a54d3bb5baad..8177e8511afd 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
@@ -18,13 +18,6 @@
 #include <linux/hdmi.h>
 #include "hdmi.h"
 
-
-/* Supported HDMI Audio channels */
-#define MSM_HDMI_AUDIO_CHANNEL_2		0
-#define MSM_HDMI_AUDIO_CHANNEL_4		1
-#define MSM_HDMI_AUDIO_CHANNEL_6		2
-#define MSM_HDMI_AUDIO_CHANNEL_8		3
-
 /* maps MSM_HDMI_AUDIO_CHANNEL_n consts used by audio driver to # of channels: */
 static int nchannels[] = { 2, 4, 6, 8 };
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h
index 611da7a660c9..238901987e00 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h
@@ -18,7 +18,8 @@
 #ifndef __MDP5_PIPE_H__
 #define __MDP5_PIPE_H__
 
-#define SSPP_MAX	(SSPP_RGB3 + 1) /* TODO: Add SSPP_MAX in mdp5.xml.h */
+/* TODO: Add SSPP_MAX in mdp5.xml.h */
+#define SSPP_MAX	(SSPP_CURSOR1 + 1)
 
 /* represents a hw pipe, which is dynamically assigned to a plane */
 struct mdp5_hw_pipe {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 59811f29607d..68e509b3b9e4 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -812,6 +812,12 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev,
 
 	size = PAGE_ALIGN(size);
 
+	/* Disallow zero sized objects as they make the underlying
+	 * infrastructure grumpy
+	 */
+	if (size == 0)
+		return ERR_PTR(-EINVAL);
+
 	ret = msm_gem_new_impl(dev, size, flags, NULL, &obj);
 	if (ret)
 		goto fail;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 99e05aacbee1..af5b6ba4095b 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -706,9 +706,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 		msm_ringbuffer_destroy(gpu->rb);
 	}
 
-	if (gpu->aspace)
-		msm_gem_address_space_destroy(gpu->aspace);
-
 	if (gpu->fctx)
 		msm_fence_context_free(gpu->fctx);
 }
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
index e10a4eda4078..1144e0c9e894 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
@@ -65,13 +65,11 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb)
 	switch (format) {
 	case DRM_FORMAT_RGB565:
 		dev_dbg(drm->dev, "Setting up RGB565 mode\n");
-		ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT);
 		ctrl |= CTRL_SET_WORD_LENGTH(0);
 		ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0xf);
 		break;
 	case DRM_FORMAT_XRGB8888:
 		dev_dbg(drm->dev, "Setting up XRGB8888 mode\n");
-		ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT);
 		ctrl |= CTRL_SET_WORD_LENGTH(3);
 		/* Do not use packed pixels = one pixel per word instead. */
 		ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0x7);
@@ -87,6 +85,36 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb)
 	return 0;
 }
 
+static void mxsfb_set_bus_fmt(struct mxsfb_drm_private *mxsfb)
+{
+	struct drm_crtc *crtc = &mxsfb->pipe.crtc;
+	struct drm_device *drm = crtc->dev;
+	u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+	u32 reg;
+
+	reg = readl(mxsfb->base + LCDC_CTRL);
+
+	if (mxsfb->connector.display_info.num_bus_formats)
+		bus_format = mxsfb->connector.display_info.bus_formats[0];
+
+	reg &= ~CTRL_BUS_WIDTH_MASK;
+	switch (bus_format) {
+	case MEDIA_BUS_FMT_RGB565_1X16:
+		reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT);
+		break;
+	case MEDIA_BUS_FMT_RGB666_1X18:
+		reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_18BIT);
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+		reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT);
+		break;
+	default:
+		dev_err(drm->dev, "Unknown media bus format %d\n", bus_format);
+		break;
+	}
+	writel(reg, mxsfb->base + LCDC_CTRL);
+}
+
 static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
 {
 	u32 reg;
@@ -168,13 +196,22 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 		vdctrl0 |= VDCTRL0_HSYNC_ACT_HIGH;
 	if (m->flags & DRM_MODE_FLAG_PVSYNC)
 		vdctrl0 |= VDCTRL0_VSYNC_ACT_HIGH;
-	if (bus_flags & DRM_BUS_FLAG_DE_HIGH)
+	/* Make sure Data Enable is high active by default */
+	if (!(bus_flags & DRM_BUS_FLAG_DE_LOW))
 		vdctrl0 |= VDCTRL0_ENABLE_ACT_HIGH;
-	if (bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
+	/*
+	 * DRM_BUS_FLAG_PIXDATA_ defines are controller centric,
+	 * controllers VDCTRL0_DOTCLK is display centric.
+	 * Drive on positive edge       -> display samples on falling edge
+	 * DRM_BUS_FLAG_PIXDATA_POSEDGE -> VDCTRL0_DOTCLK_ACT_FALLING
+	 */
+	if (bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE)
 		vdctrl0 |= VDCTRL0_DOTCLK_ACT_FALLING;
 
 	writel(vdctrl0, mxsfb->base + LCDC_VDCTRL0);
 
+	mxsfb_set_bus_fmt(mxsfb);
+
 	/* Frame length in lines. */
 	writel(m->crtc_vtotal, mxsfb->base + LCDC_VDCTRL1);
 
@@ -184,8 +221,8 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 	       VDCTRL2_SET_HSYNC_PERIOD(m->crtc_htotal),
 	       mxsfb->base + LCDC_VDCTRL2);
 
-	writel(SET_HOR_WAIT_CNT(m->crtc_hblank_end - m->crtc_hsync_end) |
-	       SET_VERT_WAIT_CNT(m->crtc_vblank_end - m->crtc_vsync_end),
+	writel(SET_HOR_WAIT_CNT(m->crtc_htotal - m->crtc_hsync_start) |
+	       SET_VERT_WAIT_CNT(m->crtc_vtotal - m->crtc_vsync_start),
 	       mxsfb->base + LCDC_VDCTRL3);
 
 	writel(SET_DOTCLK_H_VALID_DATA_CNT(m->hdisplay),
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index cdfbe0284635..ff6d6a6f842e 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -102,14 +102,18 @@ static void mxsfb_pipe_enable(struct drm_simple_display_pipe *pipe,
 {
 	struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
 
+	drm_panel_prepare(mxsfb->panel);
 	mxsfb_crtc_enable(mxsfb);
+	drm_panel_enable(mxsfb->panel);
 }
 
 static void mxsfb_pipe_disable(struct drm_simple_display_pipe *pipe)
 {
 	struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
 
+	drm_panel_disable(mxsfb->panel);
 	mxsfb_crtc_disable(mxsfb);
+	drm_panel_unprepare(mxsfb->panel);
 }
 
 static void mxsfb_pipe_update(struct drm_simple_display_pipe *pipe,
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_out.c b/drivers/gpu/drm/mxsfb/mxsfb_out.c
index fa8d17399407..b8e81422d4e2 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_out.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_out.c
@@ -112,6 +112,7 @@ static int mxsfb_attach_endpoint(struct drm_device *drm,
 
 int mxsfb_create_output(struct drm_device *drm)
 {
+	struct mxsfb_drm_private *mxsfb = drm->dev_private;
 	struct device_node *ep_np = NULL;
 	struct of_endpoint ep;
 	int ret;
@@ -127,5 +128,8 @@ int mxsfb_create_output(struct drm_device *drm)
 		}
 	}
 
+	if (!mxsfb->panel)
+		return -EPROBE_DEFER;
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_regs.h b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
index 31d62cd0d3d7..66a6ba9ec533 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_regs.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
@@ -44,6 +44,7 @@
 #define CTRL_DATA_SELECT		(1 << 16)
 #define CTRL_SET_BUS_WIDTH(x)		(((x) & 0x3) << 10)
 #define CTRL_GET_BUS_WIDTH(x)		(((x) >> 10) & 0x3)
+#define CTRL_BUS_WIDTH_MASK		(0x3 << 10)
 #define CTRL_SET_WORD_LENGTH(x)		(((x) & 0x3) << 8)
 #define CTRL_GET_WORD_LENGTH(x)		(((x) >> 8) & 0x3)
 #define CTRL_MASTER			(1 << 5)
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 0b4440ffbeae..a9182d5e6011 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -995,7 +995,6 @@ nv50_wndw_atomic_destroy_state(struct drm_plane *plane,
 {
 	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
 	__drm_atomic_helper_plane_destroy_state(&asyw->state);
-	dma_fence_put(asyw->state.fence);
 	kfree(asyw);
 }
 
@@ -1007,7 +1006,6 @@ nv50_wndw_atomic_duplicate_state(struct drm_plane *plane)
 	if (!(asyw = kmalloc(sizeof(*asyw), GFP_KERNEL)))
 		return NULL;
 	__drm_atomic_helper_plane_duplicate_state(plane, &asyw->state);
-	asyw->state.fence = NULL;
 	asyw->interval = 1;
 	asyw->sema = armw->sema;
 	asyw->ntfy = armw->ntfy;
@@ -2036,6 +2034,7 @@ nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
 	u32 vbackp  = (mode->vtotal - mode->vsync_end) * vscan / ilace;
 	u32 hfrontp =  mode->hsync_start - mode->hdisplay;
 	u32 vfrontp = (mode->vsync_start - mode->vdisplay) * vscan / ilace;
+	u32 blankus;
 	struct nv50_head_mode *m = &asyh->mode;
 
 	m->h.active = mode->htotal;
@@ -2049,9 +2048,10 @@ nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
 	m->v.blanks = m->v.active - vfrontp - 1;
 
 	/*XXX: Safe underestimate, even "0" works */
-	m->v.blankus = (m->v.active - mode->vdisplay - 2) * m->h.active;
-	m->v.blankus *= 1000;
-	m->v.blankus /= mode->clock;
+	blankus = (m->v.active - mode->vdisplay - 2) * m->h.active;
+	blankus *= 1000;
+	blankus /= mode->clock;
+	m->v.blankus = blankus;
 
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		m->v.blank2e =  m->v.active + m->v.synce + vbackp;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 273562dd6bbd..3b86a7399567 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -714,7 +714,7 @@ nv4a_chipset = {
 	.i2c = nv04_i2c_new,
 	.imem = nv40_instmem_new,
 	.mc = nv44_mc_new,
-	.mmu = nv44_mmu_new,
+	.mmu = nv04_mmu_new,
 	.pci = nv40_pci_new,
 	.therm = nv40_therm_new,
 	.timer = nv41_timer_new,
@@ -2271,6 +2271,35 @@ nv136_chipset = {
 	.fifo = gp100_fifo_new,
 };
 
+static const struct nvkm_device_chip
+nv137_chipset = {
+	.name = "GP107",
+	.bar = gf100_bar_new,
+	.bios = nvkm_bios_new,
+	.bus = gf100_bus_new,
+	.devinit = gm200_devinit_new,
+	.fb = gp102_fb_new,
+	.fuse = gm107_fuse_new,
+	.gpio = gk104_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.ltc = gp100_ltc_new,
+	.mc = gp100_mc_new,
+	.mmu = gf100_mmu_new,
+	.pci = gp100_pci_new,
+	.pmu = gp102_pmu_new,
+	.timer = gk20a_timer_new,
+	.top = gk104_top_new,
+	.ce[0] = gp102_ce_new,
+	.ce[1] = gp102_ce_new,
+	.ce[2] = gp102_ce_new,
+	.ce[3] = gp102_ce_new,
+	.disp = gp102_disp_new,
+	.dma = gf119_dma_new,
+	.fifo = gp100_fifo_new,
+};
+
 static int
 nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
 		       struct nvkm_notify *notify)
@@ -2708,6 +2737,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x132: device->chip = &nv132_chipset; break;
 		case 0x134: device->chip = &nv134_chipset; break;
 		case 0x136: device->chip = &nv136_chipset; break;
+		case 0x137: device->chip = &nv137_chipset; break;
 		default:
 			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
 			goto done;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c
index 003ac915eaad..8a8895246d26 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c
@@ -198,7 +198,7 @@ nv31_mpeg_intr(struct nvkm_engine *engine)
 		}
 
 		if (type == 0x00000010) {
-			if (!nv31_mpeg_mthd(mpeg, mthd, data))
+			if (nv31_mpeg_mthd(mpeg, mthd, data))
 				show &= ~0x01000000;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c
index e536f37e24b0..c3cf02ed468e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c
@@ -172,7 +172,7 @@ nv44_mpeg_intr(struct nvkm_engine *engine)
 		}
 
 		if (type == 0x00000010) {
-			if (!nv44_mpeg_mthd(subdev->device, mthd, data))
+			if (nv44_mpeg_mthd(subdev->device, mthd, data))
 				show &= ~0x01000000;
 		}
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index af267c35d813..ee5883f59be5 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -147,9 +147,6 @@ static int omap_gem_dmabuf_mmap(struct dma_buf *buffer,
 	struct drm_gem_object *obj = buffer->priv;
 	int ret = 0;
 
-	if (WARN_ON(!obj->filp))
-		return -EINVAL;
-
 	ret = drm_gem_mmap_obj(obj, omap_gem_mmap_size(obj), vma);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 684f1703aa5c..aaa3e80fecb4 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -213,8 +213,8 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 			rbo->placement.num_busy_placement = 0;
 			for (i = 0; i < rbo->placement.num_placement; i++) {
 				if (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) {
-					if (rbo->placements[0].fpfn < fpfn)
-						rbo->placements[0].fpfn = fpfn;
+					if (rbo->placements[i].fpfn < fpfn)
+						rbo->placements[i].fpfn = fpfn;
 				} else {
 					rbo->placement.busy_placement =
 						&rbo->placements[i];
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index d12b8978142f..c7af9fdd20c7 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2984,6 +2984,16 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		    (rdev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
 		}
+	} else if (rdev->family == CHIP_OLAND) {
+		if ((rdev->pdev->revision == 0xC7) ||
+		    (rdev->pdev->revision == 0x80) ||
+		    (rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0x87) ||
+		    (rdev->pdev->device == 0x6604) ||
+		    (rdev->pdev->device == 0x6605)) {
+			max_sclk = 75000;
+		}
 	}
 
 	if (rps->vce_active) {
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index b5bfbe50bd87..b0ff304ce3dc 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -32,6 +32,10 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
 {
 	const struct drm_display_mode *mode = &crtc->crtc.state->adjusted_mode;
 	struct rcar_du_device *rcdu = crtc->group->dev;
+	struct vsp1_du_lif_config cfg = {
+		.width = mode->hdisplay,
+		.height = mode->vdisplay,
+	};
 	struct rcar_du_plane_state state = {
 		.state = {
 			.crtc = &crtc->crtc,
@@ -66,12 +70,12 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
 	 */
 	crtc->group->need_restart = true;
 
-	vsp1_du_setup_lif(crtc->vsp->vsp, mode->hdisplay, mode->vdisplay);
+	vsp1_du_setup_lif(crtc->vsp->vsp, &cfg);
 }
 
 void rcar_du_vsp_disable(struct rcar_du_crtc *crtc)
 {
-	vsp1_du_setup_lif(crtc->vsp->vsp, 0, 0);
+	vsp1_du_setup_lif(crtc->vsp->vsp, NULL);
 }
 
 void rcar_du_vsp_atomic_begin(struct rcar_du_crtc *crtc)
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index f80bf9385e41..d745e8b50fb8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -464,6 +464,7 @@ static void tilcdc_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
+	unsigned long flags;
 
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 	mutex_lock(&tilcdc_crtc->enable_lock);
@@ -484,7 +485,17 @@ static void tilcdc_crtc_enable(struct drm_crtc *crtc)
 	tilcdc_write_mask(dev, LCDC_RASTER_CTRL_REG,
 			  LCDC_PALETTE_LOAD_MODE(DATA_ONLY),
 			  LCDC_PALETTE_LOAD_MODE_MASK);
+
+	/* There is no real chance for a race here as the time stamp
+	 * is taken before the raster DMA is started. The spin-lock is
+	 * taken to have a memory barrier after taking the time-stamp
+	 * and to avoid a context switch between taking the stamp and
+	 * enabling the raster.
+	 */
+	spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+	tilcdc_crtc->last_vblank = ktime_get();
 	tilcdc_set(dev, LCDC_RASTER_CTRL_REG, LCDC_RASTER_ENABLE);
+	spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
 
 	drm_crtc_vblank_on(crtc);
 
@@ -539,7 +550,6 @@ static void tilcdc_crtc_off(struct drm_crtc *crtc, bool shutdown)
 	}
 
 	drm_flip_work_commit(&tilcdc_crtc->unref_work, priv->wq);
-	tilcdc_crtc->last_vblank = 0;
 
 	tilcdc_crtc->enabled = false;
 	mutex_unlock(&tilcdc_crtc->enable_lock);
@@ -602,7 +612,6 @@ int tilcdc_crtc_update_fb(struct drm_crtc *crtc,
 {
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	unsigned long flags;
 
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
@@ -614,28 +623,30 @@ int tilcdc_crtc_update_fb(struct drm_crtc *crtc,
 	drm_framebuffer_reference(fb);
 
 	crtc->primary->fb = fb;
+	tilcdc_crtc->event = event;
 
-	spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+	mutex_lock(&tilcdc_crtc->enable_lock);
 
-	if (crtc->hwmode.vrefresh && ktime_to_ns(tilcdc_crtc->last_vblank)) {
+	if (tilcdc_crtc->enabled) {
+		unsigned long flags;
 		ktime_t next_vblank;
 		s64 tdiff;
 
-		next_vblank = ktime_add_us(tilcdc_crtc->last_vblank,
-			1000000 / crtc->hwmode.vrefresh);
+		spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
 
+		next_vblank = ktime_add_us(tilcdc_crtc->last_vblank,
+					   1000000 / crtc->hwmode.vrefresh);
 		tdiff = ktime_to_us(ktime_sub(next_vblank, ktime_get()));
 
 		if (tdiff < TILCDC_VBLANK_SAFETY_THRESHOLD_US)
 			tilcdc_crtc->next_fb = fb;
-	}
-
-	if (tilcdc_crtc->next_fb != fb)
-		set_scanout(crtc, fb);
+		else
+			set_scanout(crtc, fb);
 
-	tilcdc_crtc->event = event;
+		spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
+	}
 
-	spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
+	mutex_unlock(&tilcdc_crtc->enable_lock);
 
 	return 0;
 }
@@ -1036,5 +1047,5 @@ int tilcdc_crtc_create(struct drm_device *dev)
 
 fail:
 	tilcdc_crtc_destroy(crtc);
-	return -ENOMEM;
+	return ret;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index fdb451e3ec01..26a7ad0f4789 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -179,7 +179,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile,
 	if (unlikely(ret != 0))
 		goto out_err0;
 
-	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false);
 	if (unlikely(ret != 0))
 		goto out_err1;
 
@@ -318,7 +318,8 @@ EXPORT_SYMBOL(ttm_ref_object_exists);
 
 int ttm_ref_object_add(struct ttm_object_file *tfile,
 		       struct ttm_base_object *base,
-		       enum ttm_ref_type ref_type, bool *existed)
+		       enum ttm_ref_type ref_type, bool *existed,
+		       bool require_existed)
 {
 	struct drm_open_hash *ht = &tfile->ref_hash[ref_type];
 	struct ttm_ref_object *ref;
@@ -345,6 +346,9 @@ int ttm_ref_object_add(struct ttm_object_file *tfile,
 		}
 
 		rcu_read_unlock();
+		if (require_existed)
+			return -EPERM;
+
 		ret = ttm_mem_global_alloc(mem_glob, sizeof(*ref),
 					   false, false);
 		if (unlikely(ret != 0))
@@ -449,10 +453,10 @@ void ttm_object_file_release(struct ttm_object_file **p_tfile)
 		ttm_ref_object_release(&ref->kref);
 	}
 
+	spin_unlock(&tfile->lock);
 	for (i = 0; i < TTM_REF_NUM; ++i)
 		drm_ht_remove(&tfile->ref_hash[i]);
 
-	spin_unlock(&tfile->lock);
 	ttm_object_file_unref(&tfile);
 }
 EXPORT_SYMBOL(ttm_object_file_release);
@@ -529,9 +533,7 @@ void ttm_object_device_release(struct ttm_object_device **p_tdev)
 
 	*p_tdev = NULL;
 
-	spin_lock(&tdev->object_lock);
 	drm_ht_remove(&tdev->object_hash);
-	spin_unlock(&tdev->object_lock);
 
 	kfree(tdev);
 }
@@ -635,7 +637,7 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
 	prime = (struct ttm_prime_object *) dma_buf->priv;
 	base = &prime->base;
 	*handle = base->hash.key;
-	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false);
 
 	dma_buf_put(dma_buf);
 
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 8e8d60e9a1a2..b1f0d523dff9 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -37,7 +37,7 @@ struct udl_fbdev {
 };
 
 #define DL_ALIGN_UP(x, a) ALIGN(x, a)
-#define DL_ALIGN_DOWN(x, a) ALIGN(x-(a-1), a)
+#define DL_ALIGN_DOWN(x, a) ALIGN_DOWN(x, a)
 
 /** Read the red component (0..255) of a 32 bpp colour. */
 #define DLO_RGB_GETRED(col) (uint8_t)((col) & 0xFF)
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index 917dcb978c2c..0c87b1ac6b68 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/fb.h>
 #include <linux/prefetch.h>
+#include <asm/unaligned.h>
 
 #include <drm/drmP.h>
 #include "udl_drv.h"
@@ -163,7 +164,7 @@ static void udl_compress_hline16(
 			const u8 *const start = pixel;
 			const uint16_t repeating_pixel_val16 = pixel_val16;
 
-			*(uint16_t *)cmd = cpu_to_be16(pixel_val16);
+			put_unaligned_be16(pixel_val16, cmd);
 
 			cmd += 2;
 			pixel += bpp;
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 0c06844af445..9fcf05ca492b 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -846,6 +846,17 @@ static void vc4_crtc_destroy_state(struct drm_crtc *crtc,
 	drm_atomic_helper_crtc_destroy_state(crtc, state);
 }
 
+static void
+vc4_crtc_reset(struct drm_crtc *crtc)
+{
+	if (crtc->state)
+		__drm_atomic_helper_crtc_destroy_state(crtc->state);
+
+	crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
+	if (crtc->state)
+		crtc->state->crtc = crtc;
+}
+
 static const struct drm_crtc_funcs vc4_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
 	.destroy = vc4_crtc_destroy,
@@ -853,7 +864,7 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = {
 	.set_property = NULL,
 	.cursor_set = NULL, /* handled by drm_mode_cursor_universal */
 	.cursor_move = NULL, /* handled by drm_mode_cursor_universal */
-	.reset = drm_atomic_helper_crtc_reset,
+	.reset = vc4_crtc_reset,
 	.atomic_duplicate_state = vc4_crtc_duplicate_state,
 	.atomic_destroy_state = vc4_crtc_destroy_state,
 	.gamma_set = vc4_crtc_gamma_set,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 6541dd8b82dc..6b2708b4eafe 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -538,7 +538,7 @@ int vmw_fence_create(struct vmw_fence_manager *fman,
 		     struct vmw_fence_obj **p_fence)
 {
 	struct vmw_fence_obj *fence;
-	int ret;
+ 	int ret;
 
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
 	if (unlikely(fence == NULL))
@@ -701,6 +701,41 @@ void vmw_fence_fifo_up(struct vmw_fence_manager *fman)
 }
 
 
+/**
+ * vmw_fence_obj_lookup - Look up a user-space fence object
+ *
+ * @tfile: A struct ttm_object_file identifying the caller.
+ * @handle: A handle identifying the fence object.
+ * @return: A struct vmw_user_fence base ttm object on success or
+ * an error pointer on failure.
+ *
+ * The fence object is looked up and type-checked. The caller needs
+ * to have opened the fence object first, but since that happens on
+ * creation and fence objects aren't shareable, that's not an
+ * issue currently.
+ */
+static struct ttm_base_object *
+vmw_fence_obj_lookup(struct ttm_object_file *tfile, u32 handle)
+{
+	struct ttm_base_object *base = ttm_base_object_lookup(tfile, handle);
+
+	if (!base) {
+		pr_err("Invalid fence object handle 0x%08lx.\n",
+		       (unsigned long)handle);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (base->refcount_release != vmw_user_fence_base_release) {
+		pr_err("Invalid fence object handle 0x%08lx.\n",
+		       (unsigned long)handle);
+		ttm_base_object_unref(&base);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return base;
+}
+
+
 int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv)
 {
@@ -726,13 +761,9 @@ int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
 		arg->kernel_cookie = jiffies + wait_timeout;
 	}
 
-	base = ttm_base_object_lookup(tfile, arg->handle);
-	if (unlikely(base == NULL)) {
-		printk(KERN_ERR "Wait invalid fence object handle "
-		       "0x%08lx.\n",
-		       (unsigned long)arg->handle);
-		return -EINVAL;
-	}
+	base = vmw_fence_obj_lookup(tfile, arg->handle);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	fence = &(container_of(base, struct vmw_user_fence, base)->fence);
 
@@ -771,13 +802,9 @@ int vmw_fence_obj_signaled_ioctl(struct drm_device *dev, void *data,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	struct vmw_private *dev_priv = vmw_priv(dev);
 
-	base = ttm_base_object_lookup(tfile, arg->handle);
-	if (unlikely(base == NULL)) {
-		printk(KERN_ERR "Fence signaled invalid fence object handle "
-		       "0x%08lx.\n",
-		       (unsigned long)arg->handle);
-		return -EINVAL;
-	}
+	base = vmw_fence_obj_lookup(tfile, arg->handle);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	fence = &(container_of(base, struct vmw_user_fence, base)->fence);
 	fman = fman_from_fence(fence);
@@ -1024,6 +1051,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 		(struct drm_vmw_fence_event_arg *) data;
 	struct vmw_fence_obj *fence = NULL;
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
+	struct ttm_object_file *tfile = vmw_fp->tfile;
 	struct drm_vmw_fence_rep __user *user_fence_rep =
 		(struct drm_vmw_fence_rep __user *)(unsigned long)
 		arg->fence_rep;
@@ -1037,24 +1065,18 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 	 */
 	if (arg->handle) {
 		struct ttm_base_object *base =
-			ttm_base_object_lookup_for_ref(dev_priv->tdev,
-						       arg->handle);
-
-		if (unlikely(base == NULL)) {
-			DRM_ERROR("Fence event invalid fence object handle "
-				  "0x%08lx.\n",
-				  (unsigned long)arg->handle);
-			return -EINVAL;
-		}
+			vmw_fence_obj_lookup(tfile, arg->handle);
+
+		if (IS_ERR(base))
+			return PTR_ERR(base);
+
 		fence = &(container_of(base, struct vmw_user_fence,
 				       base)->fence);
 		(void) vmw_fence_obj_reference(fence);
 
 		if (user_fence_rep != NULL) {
-			bool existed;
-
 			ret = ttm_ref_object_add(vmw_fp->tfile, base,
-						 TTM_REF_USAGE, &existed);
+						 TTM_REF_USAGE, NULL, false);
 			if (unlikely(ret != 0)) {
 				DRM_ERROR("Failed to reference a fence "
 					  "object.\n");
@@ -1097,8 +1119,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 	return 0;
 out_no_create:
 	if (user_fence_rep != NULL)
-		ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					  handle, TTM_REF_USAGE);
+		ttm_ref_object_base_unref(tfile, handle, TTM_REF_USAGE);
 out_no_ref_obj:
 	vmw_fence_obj_unreference(&fence);
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index b8c6a03c8c54..5ec24fd801cd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -114,8 +114,6 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 		param->value = dev_priv->has_dx;
 		break;
 	default:
-		DRM_ERROR("Illegal vmwgfx get param request: %d\n",
-			  param->param);
 		return -EINVAL;
 	}
 
@@ -186,7 +184,7 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 	bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS);
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 
-	if (unlikely(arg->pad64 != 0)) {
+	if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) {
 		DRM_ERROR("Illegal GET_3D_CAP argument.\n");
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 65b3f0369636..bf23153d4f55 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -589,7 +589,7 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
 		return ret;
 
 	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
-				 TTM_REF_SYNCCPU_WRITE, &existed);
+				 TTM_REF_SYNCCPU_WRITE, &existed, false);
 	if (ret != 0 || existed)
 		ttm_bo_synccpu_write_release(&user_bo->dma.base);
 
@@ -773,7 +773,7 @@ int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
 
 	*handle = user_bo->prime.base.hash.key;
 	return ttm_ref_object_add(tfile, &user_bo->prime.base,
-				  TTM_REF_USAGE, NULL);
+				  TTM_REF_USAGE, NULL, false);
 }
 
 /*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index b445ce9b9757..05fa092c942b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -713,11 +713,14 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 			128;
 
 	num_sizes = 0;
-	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i)
+	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) {
+		if (req->mip_levels[i] > DRM_VMW_MAX_MIP_LEVELS)
+			return -EINVAL;
 		num_sizes += req->mip_levels[i];
+	}
 
-	if (num_sizes > DRM_VMW_MAX_SURFACE_FACES *
-	    DRM_VMW_MAX_MIP_LEVELS)
+	if (num_sizes > DRM_VMW_MAX_SURFACE_FACES * DRM_VMW_MAX_MIP_LEVELS ||
+	    num_sizes == 0)
 		return -EINVAL;
 
 	size = vmw_user_surface_size + 128 +
@@ -891,17 +894,16 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 	uint32_t handle;
 	struct ttm_base_object *base;
 	int ret;
+	bool require_exist = false;
 
 	if (handle_type == DRM_VMW_HANDLE_PRIME) {
 		ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle);
 		if (unlikely(ret != 0))
 			return ret;
 	} else {
-		if (unlikely(drm_is_render_client(file_priv))) {
-			DRM_ERROR("Render client refused legacy "
-				  "surface reference.\n");
-			return -EACCES;
-		}
+		if (unlikely(drm_is_render_client(file_priv)))
+			require_exist = true;
+
 		if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) {
 			DRM_ERROR("Locked master refused legacy "
 				  "surface reference.\n");
@@ -929,17 +931,14 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 
 		/*
 		 * Make sure the surface creator has the same
-		 * authenticating master.
+		 * authenticating master, or is already registered with us.
 		 */
 		if (drm_is_primary_client(file_priv) &&
-		    user_srf->master != file_priv->master) {
-			DRM_ERROR("Trying to reference surface outside of"
-				  " master domain.\n");
-			ret = -EACCES;
-			goto out_bad_resource;
-		}
+		    user_srf->master != file_priv->master)
+			require_exist = true;
 
-		ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+		ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL,
+					 require_exist);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not add a reference to a surface.\n");
 			goto out_bad_resource;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 1aeb80e52424..fe40e5e499dd 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -98,6 +98,18 @@ config HID_A4TECH
 	---help---
 	Support for A4 tech X5 and WOP-35 / Trust 450L mice.
 
+config HID_ACCUTOUCH
+	tristate "Accutouch touch device"
+	depends on USB_HID
+	---help---
+	  This selects a driver for the Accutouch 2216 touch controller.
+
+	  The driver works around a problem in the reported device capabilities
+	  which causes userspace to detect the device as a mouse rather than
+          a touchscreen.
+
+	  Say Y here if you have a Accutouch 2216 touch controller.
+
 config HID_ACRUX
 	tristate "ACRUX game controller support"
 	depends on HID
@@ -136,13 +148,16 @@ config HID_APPLEIR
 
 config HID_ASUS
 	tristate "Asus"
-	depends on I2C_HID
+	depends on LEDS_CLASS
 	---help---
-	Support for Asus notebook built-in keyboard and touchpad via i2c.
+	Support for Asus notebook built-in keyboard and touchpad via i2c, and
+	the Asus Republic of Gamers laptop keyboard special keys.
 
 	Supported devices:
 	- EeeBook X205TA
 	- VivoBook E200HA
+	- GL553V series
+	- GL753V series
 
 config HID_AUREAL
 	tristate "Aureal"
@@ -175,11 +190,11 @@ config HID_CHERRY
 	Support for Cherry Cymotion keyboard.
 
 config HID_CHICONY
-	tristate "Chicony Tactical pad"
+	tristate "Chicony devices"
 	depends on HID
 	default !EXPERT
 	---help---
-	Support for Chicony Tactical pad.
+	Support for Chicony Tactical pad and special keys on Chicony keyboards.
 
 config HID_CORSAIR
 	tristate "Corsair devices"
@@ -190,6 +205,7 @@ config HID_CORSAIR
 
 	Supported devices:
 	- Vengeance K90
+	- Scimitar PRO RGB
 
 config HID_PRODIKEYS
 	tristate "Prodikeys PC-MIDI Keyboard support"
@@ -214,7 +230,8 @@ config HID_CMEDIA
 
 config HID_CP2112
 	tristate "Silicon Labs CP2112 HID USB-to-SMBus Bridge support"
-	depends on USB_HID && I2C && GPIOLIB && GPIOLIB_IRQCHIP
+	depends on USB_HID && I2C && GPIOLIB
+	select GPIOLIB_IRQCHIP
 	---help---
 	Support for Silicon Labs CP2112 HID USB to SMBus Master Bridge.
 	This is a HID device driver which registers as an i2c adapter
@@ -440,6 +457,7 @@ config HID_LOGITECH_DJ
 config HID_LOGITECH_HIDPP
 	tristate "Logitech HID++ devices support"
 	depends on HID_LOGITECH
+	select POWER_SUPPLY
 	---help---
 	Support for Logitech devices relyingon the HID++ Logitech specification
 
@@ -580,6 +598,12 @@ config HID_MULTITOUCH
 	  To compile this driver as a module, choose M here: the
 	  module will be called hid-multitouch.
 
+config HID_NTI
+	tristate "NTI keyboard adapters"
+	---help---
+	Support for the "extra" Sun keyboard keys on keyboards attached
+	through Network Technologies USB-SUN keyboard adapters.
+
 config HID_NTRIG
 	tristate "N-Trig touch screen"
 	depends on USB_HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index 4d111f23e801..fef027bc7fa3 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -21,6 +21,7 @@ hid-wiimote-y		:= hid-wiimote-core.o hid-wiimote-modules.o
 hid-wiimote-$(CONFIG_DEBUG_FS)	+= hid-wiimote-debug.o
 
 obj-$(CONFIG_HID_A4TECH)	+= hid-a4tech.o
+obj-$(CONFIG_HID_ACCUTOUCH)	+= hid-accutouch.o
 obj-$(CONFIG_HID_ALPS)		+= hid-alps.o
 obj-$(CONFIG_HID_ACRUX)		+= hid-axff.o
 obj-$(CONFIG_HID_APPLE)		+= hid-apple.o
@@ -62,6 +63,7 @@ obj-$(CONFIG_HID_MAYFLASH)	+= hid-mf.o
 obj-$(CONFIG_HID_MICROSOFT)	+= hid-microsoft.o
 obj-$(CONFIG_HID_MONTEREY)	+= hid-monterey.o
 obj-$(CONFIG_HID_MULTITOUCH)	+= hid-multitouch.o
+obj-$(CONFIG_HID_NTI)			+= hid-nti.o
 obj-$(CONFIG_HID_NTRIG)		+= hid-ntrig.o
 obj-$(CONFIG_HID_ORTEK)		+= hid-ortek.o
 obj-$(CONFIG_HID_PRODIKEYS)	+= hid-prodikeys.o
diff --git a/drivers/hid/hid-accutouch.c b/drivers/hid/hid-accutouch.c
new file mode 100644
index 000000000000..4e287160c50a
--- /dev/null
+++ b/drivers/hid/hid-accutouch.c
@@ -0,0 +1,52 @@
+/*
+ * HID driver for Elo Accutouch touchscreens
+ *
+ * Copyright (c) 2016, Collabora Ltd.
+ * Copyright (c) 2016, General Electric Company
+ *
+ * based on hid-penmount.c
+ *  Copyright (c) 2014 Christian Gmeiner <christian.gmeiner <at> gmail.com>
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/hid.h>
+#include <linux/module.h>
+#include "hid-ids.h"
+
+static int accutouch_input_mapping(struct hid_device *hdev,
+				   struct hid_input *hi,
+				   struct hid_field *field,
+				   struct hid_usage *usage,
+				   unsigned long **bit, int *max)
+{
+	if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) {
+		hid_map_usage(hi, usage, bit, max, EV_KEY, BTN_TOUCH);
+		return 1;
+	}
+
+	return 0;
+}
+
+static const struct hid_device_id accutouch_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_ACCUTOUCH_2216) },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, accutouch_devices);
+
+static struct hid_driver accutouch_driver = {
+	.name = "hid-accutouch",
+	.id_table = accutouch_devices,
+	.input_mapping = accutouch_input_mapping,
+};
+
+module_hid_driver(accutouch_driver);
+
+MODULE_AUTHOR("Martyn Welch <martyn.welch@collabora.co.uk");
+MODULE_DESCRIPTION("Elo Accutouch HID TouchScreen driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 70b12f89a193..16df6cc90235 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -40,8 +40,12 @@ MODULE_DESCRIPTION("Asus HID Keyboard and TouchPad");
 
 #define FEATURE_REPORT_ID 0x0d
 #define INPUT_REPORT_ID 0x5d
+#define FEATURE_KBD_REPORT_ID 0x5a
 
 #define INPUT_REPORT_SIZE 28
+#define FEATURE_KBD_REPORT_SIZE 16
+
+#define SUPPORT_KBD_BACKLIGHT BIT(0)
 
 #define MAX_CONTACTS 5
 
@@ -63,18 +67,31 @@ MODULE_DESCRIPTION("Asus HID Keyboard and TouchPad");
 #define QUIRK_NO_INIT_REPORTS		BIT(1)
 #define QUIRK_SKIP_INPUT_MAPPING	BIT(2)
 #define QUIRK_IS_MULTITOUCH		BIT(3)
+#define QUIRK_NO_CONSUMER_USAGES	BIT(4)
+#define QUIRK_USE_KBD_BACKLIGHT		BIT(5)
 
-#define KEYBOARD_QUIRKS			(QUIRK_FIX_NOTEBOOK_REPORT | \
-						 QUIRK_NO_INIT_REPORTS)
-#define TOUCHPAD_QUIRKS			(QUIRK_NO_INIT_REPORTS | \
+#define I2C_KEYBOARD_QUIRKS			(QUIRK_FIX_NOTEBOOK_REPORT | \
+						 QUIRK_NO_INIT_REPORTS | \
+						 QUIRK_NO_CONSUMER_USAGES)
+#define I2C_TOUCHPAD_QUIRKS			(QUIRK_NO_INIT_REPORTS | \
 						 QUIRK_SKIP_INPUT_MAPPING | \
 						 QUIRK_IS_MULTITOUCH)
 
 #define TRKID_SGN       ((TRKID_MAX + 1) >> 1)
 
+struct asus_kbd_leds {
+	struct led_classdev cdev;
+	struct hid_device *hdev;
+	struct work_struct work;
+	unsigned int brightness;
+	bool removed;
+};
+
 struct asus_drvdata {
 	unsigned long quirks;
 	struct input_dev *input;
+	struct asus_kbd_leds *kbd_backlight;
+	bool enable_backlight;
 };
 
 static void asus_report_contact_down(struct input_dev *input,
@@ -169,6 +186,148 @@ static int asus_raw_event(struct hid_device *hdev,
 	return 0;
 }
 
+static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size)
+{
+	unsigned char *dmabuf;
+	int ret;
+
+	dmabuf = kmemdup(buf, buf_size, GFP_KERNEL);
+	if (!dmabuf)
+		return -ENOMEM;
+
+	ret = hid_hw_raw_request(hdev, FEATURE_KBD_REPORT_ID, dmabuf,
+				 buf_size, HID_FEATURE_REPORT,
+				 HID_REQ_SET_REPORT);
+	kfree(dmabuf);
+
+	return ret;
+}
+
+static int asus_kbd_init(struct hid_device *hdev)
+{
+	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54,
+		     0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 };
+	int ret;
+
+	ret = asus_kbd_set_report(hdev, buf, sizeof(buf));
+	if (ret < 0)
+		hid_err(hdev, "Asus failed to send init command: %d\n", ret);
+
+	return ret;
+}
+
+static int asus_kbd_get_functions(struct hid_device *hdev,
+				  unsigned char *kbd_func)
+{
+	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 };
+	u8 *readbuf;
+	int ret;
+
+	ret = asus_kbd_set_report(hdev, buf, sizeof(buf));
+	if (ret < 0) {
+		hid_err(hdev, "Asus failed to send configuration command: %d\n", ret);
+		return ret;
+	}
+
+	readbuf = kzalloc(FEATURE_KBD_REPORT_SIZE, GFP_KERNEL);
+	if (!readbuf)
+		return -ENOMEM;
+
+	ret = hid_hw_raw_request(hdev, FEATURE_KBD_REPORT_ID, readbuf,
+				 FEATURE_KBD_REPORT_SIZE, HID_FEATURE_REPORT,
+				 HID_REQ_GET_REPORT);
+	if (ret < 0) {
+		hid_err(hdev, "Asus failed to request functions: %d\n", ret);
+		kfree(readbuf);
+		return ret;
+	}
+
+	*kbd_func = readbuf[6];
+
+	kfree(readbuf);
+	return ret;
+}
+
+static void asus_kbd_backlight_set(struct led_classdev *led_cdev,
+				   enum led_brightness brightness)
+{
+	struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds,
+						 cdev);
+	if (led->brightness == brightness)
+		return;
+
+	led->brightness = brightness;
+	schedule_work(&led->work);
+}
+
+static enum led_brightness asus_kbd_backlight_get(struct led_classdev *led_cdev)
+{
+	struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds,
+						 cdev);
+
+	return led->brightness;
+}
+
+static void asus_kbd_backlight_work(struct work_struct *work)
+{
+	struct asus_kbd_leds *led = container_of(work, struct asus_kbd_leds, work);
+	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0xba, 0xc5, 0xc4, 0x00 };
+	int ret;
+
+	if (led->removed)
+		return;
+
+	buf[4] = led->brightness;
+
+	ret = asus_kbd_set_report(led->hdev, buf, sizeof(buf));
+	if (ret < 0)
+		hid_err(led->hdev, "Asus failed to set keyboard backlight: %d\n", ret);
+}
+
+static int asus_kbd_register_leds(struct hid_device *hdev)
+{
+	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
+	unsigned char kbd_func;
+	int ret;
+
+	/* Initialize keyboard */
+	ret = asus_kbd_init(hdev);
+	if (ret < 0)
+		return ret;
+
+	/* Get keyboard functions */
+	ret = asus_kbd_get_functions(hdev, &kbd_func);
+	if (ret < 0)
+		return ret;
+
+	/* Check for backlight support */
+	if (!(kbd_func & SUPPORT_KBD_BACKLIGHT))
+		return -ENODEV;
+
+	drvdata->kbd_backlight = devm_kzalloc(&hdev->dev,
+					      sizeof(struct asus_kbd_leds),
+					      GFP_KERNEL);
+	if (!drvdata->kbd_backlight)
+		return -ENOMEM;
+
+	drvdata->kbd_backlight->removed = false;
+	drvdata->kbd_backlight->brightness = 0;
+	drvdata->kbd_backlight->hdev = hdev;
+	drvdata->kbd_backlight->cdev.name = "asus::kbd_backlight";
+	drvdata->kbd_backlight->cdev.max_brightness = 3;
+	drvdata->kbd_backlight->cdev.brightness_set = asus_kbd_backlight_set;
+	drvdata->kbd_backlight->cdev.brightness_get = asus_kbd_backlight_get;
+	INIT_WORK(&drvdata->kbd_backlight->work, asus_kbd_backlight_work);
+
+	ret = devm_led_classdev_register(&hdev->dev, &drvdata->kbd_backlight->cdev);
+	if (ret < 0) {
+		/* No need to have this still around */
+		devm_kfree(&hdev->dev, drvdata->kbd_backlight);
+	}
+
+	return ret;
+}
+
 static int asus_input_configured(struct hid_device *hdev, struct hid_input *hi)
 {
 	struct input_dev *input = hi->input;
@@ -196,9 +355,14 @@ static int asus_input_configured(struct hid_device *hdev, struct hid_input *hi)
 
 	drvdata->input = input;
 
+	if (drvdata->enable_backlight && asus_kbd_register_leds(hdev))
+		hid_warn(hdev, "Failed to initialize backlight.\n");
+
 	return 0;
 }
 
+#define asus_map_key_clear(c)	hid_map_usage_clear(hi, usage, bit, \
+						    max, EV_KEY, (c))
 static int asus_input_mapping(struct hid_device *hdev,
 		struct hid_input *hi, struct hid_field *field,
 		struct hid_usage *usage, unsigned long **bit,
@@ -213,6 +377,65 @@ static int asus_input_mapping(struct hid_device *hdev,
 		return -1;
 	}
 
+	/* ASUS-specific keyboard hotkeys */
+	if ((usage->hid & HID_USAGE_PAGE) == 0xff310000) {
+		set_bit(EV_REP, hi->input->evbit);
+		switch (usage->hid & HID_USAGE) {
+		case 0x10: asus_map_key_clear(KEY_BRIGHTNESSDOWN);	break;
+		case 0x20: asus_map_key_clear(KEY_BRIGHTNESSUP);		break;
+		case 0x35: asus_map_key_clear(KEY_DISPLAY_OFF);		break;
+		case 0x6c: asus_map_key_clear(KEY_SLEEP);		break;
+		case 0x82: asus_map_key_clear(KEY_CAMERA);		break;
+		case 0x88: asus_map_key_clear(KEY_RFKILL);			break;
+		case 0xb5: asus_map_key_clear(KEY_CALC);			break;
+		case 0xc4: asus_map_key_clear(KEY_KBDILLUMUP);		break;
+		case 0xc5: asus_map_key_clear(KEY_KBDILLUMDOWN);		break;
+
+		/* ASUS touchpad toggle */
+		case 0x6b: asus_map_key_clear(KEY_F21);			break;
+
+		/* ROG key */
+		case 0x38: asus_map_key_clear(KEY_PROG1);		break;
+
+		/* Fn+C ASUS Splendid */
+		case 0xba: asus_map_key_clear(KEY_PROG2);		break;
+
+		/* Fn+Space Power4Gear Hybrid */
+		case 0x5c: asus_map_key_clear(KEY_PROG3);		break;
+
+		default:
+			/* ASUS lazily declares 256 usages, ignore the rest,
+			 * as some make the keyboard appear as a pointer device. */
+			return -1;
+		}
+
+		/*
+		 * Check and enable backlight only on devices with UsagePage ==
+		 * 0xff31 to avoid initializing the keyboard firmware multiple
+		 * times on devices with multiple HID descriptors but same
+		 * PID/VID.
+		 */
+		if (drvdata->quirks & QUIRK_USE_KBD_BACKLIGHT)
+			drvdata->enable_backlight = true;
+
+		return 1;
+	}
+
+	if (drvdata->quirks & QUIRK_NO_CONSUMER_USAGES &&
+		(usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER) {
+		switch (usage->hid & HID_USAGE) {
+		case 0xe2: /* Mute */
+		case 0xe9: /* Volume up */
+		case 0xea: /* Volume down */
+			return 0;
+		default:
+			/* Ignore dummy Consumer usages which make the
+			 * keyboard incorrectly appear as a pointer device.
+			 */
+			return -1;
+		}
+	}
+
 	return 0;
 }
 
@@ -305,6 +528,16 @@ err_stop_hw:
 	return ret;
 }
 
+static void asus_remove(struct hid_device *hdev)
+{
+	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
+
+	if (drvdata->kbd_backlight) {
+		drvdata->kbd_backlight->removed = true;
+		cancel_work_sync(&drvdata->kbd_backlight->work);
+	}
+}
+
 static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
@@ -320,9 +553,13 @@ static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 
 static const struct hid_device_id asus_devices[] = {
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK,
-		 USB_DEVICE_ID_ASUSTEK_NOTEBOOK_KEYBOARD), KEYBOARD_QUIRKS},
+		USB_DEVICE_ID_ASUSTEK_I2C_KEYBOARD), I2C_KEYBOARD_QUIRKS},
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK,
-			 USB_DEVICE_ID_ASUSTEK_TOUCHPAD), TOUCHPAD_QUIRKS },
+		USB_DEVICE_ID_ASUSTEK_I2C_TOUCHPAD), I2C_TOUCHPAD_QUIRKS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+		USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+		USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2), QUIRK_USE_KBD_BACKLIGHT },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, asus_devices);
@@ -332,6 +569,7 @@ static struct hid_driver asus_driver = {
 	.id_table		= asus_devices,
 	.report_fixup		= asus_report_fixup,
 	.probe                  = asus_probe,
+	.remove			= asus_remove,
 	.input_mapping          = asus_input_mapping,
 	.input_configured       = asus_input_configured,
 #ifdef CONFIG_PM
diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c
index bc3cec199fee..f04ed9aabc3f 100644
--- a/drivers/hid/hid-chicony.c
+++ b/drivers/hid/hid-chicony.c
@@ -86,6 +86,7 @@ static const struct hid_device_id ch_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_AK1D) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_ACER_SWITCH12) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_JESS, USB_DEVICE_ID_JESS_ZEN_AIO_KBD) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, ch_devices);
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index e9e87d337446..37084b645785 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -819,8 +819,7 @@ static int hid_scan_report(struct hid_device *hid)
 		hid->group = HID_GROUP_WACOM;
 		break;
 	case USB_VENDOR_ID_SYNAPTICS:
-		if (hid->group == HID_GROUP_GENERIC ||
-		    hid->group == HID_GROUP_MULTITOUCH_WIN_8)
+		if (hid->group == HID_GROUP_GENERIC)
 			if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC)
 			    && (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER))
 				/*
@@ -1695,7 +1694,7 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask)
 		len += sprintf(buf + len, "input");
 	if (hdev->claimed & HID_CLAIMED_HIDDEV)
 		len += sprintf(buf + len, "%shiddev%d", len ? "," : "",
-				hdev->minor);
+				((struct hiddev *)hdev->hiddev)->minor);
 	if (hdev->claimed & HID_CLAIMED_HIDRAW)
 		len += sprintf(buf + len, "%shidraw%d", len ? "," : "",
 				((struct hidraw *)hdev->hidraw)->minor);
@@ -1852,8 +1851,10 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
-	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_NOTEBOOK_KEYBOARD) },
-	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_TOUCHPAD) },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_I2C_KEYBOARD) },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_I2C_TOUCHPAD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AUREAL, USB_DEVICE_ID_AUREAL_W01RN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BELKIN, USB_DEVICE_ID_FLIP_KVM) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185BFM, 0x2208) },
@@ -1870,6 +1871,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_AK1D) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_ACER_SWITCH12) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K90) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_PRODIKEYS_PCMIDI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_CP2112) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) },
@@ -1891,6 +1893,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0030) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_ACCUTOUCH_2216) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_EMS, USB_DEVICE_ID_EMS_TRIO_LINKER_PLUS_II) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_EZKEY, USB_DEVICE_ID_BTC_8193) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR) },
@@ -1910,6 +1913,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_TABLET) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_JESS, USB_DEVICE_ID_JESS_ZEN_AIO_KBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_JESS2, USB_DEVICE_ID_JESS2_COLOR_RUMBLE_PAD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ION, USB_DEVICE_ID_ICADE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) },
@@ -1990,6 +1994,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_NTI, USB_DEVICE_ID_USB_SUN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_2) },
@@ -2094,6 +2099,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SMARTJOY_PLUS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SUPER_JOY_BOX_3) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD) },
@@ -2110,6 +2116,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_X_TENSIONS, USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_THT_2P_ARCADE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0005) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0030) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZYDACRON, USB_DEVICE_ID_ZYDACRON_REMOTE_CONTROL) },
diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c
index c0303f61c26a..9ba5d98a1180 100644
--- a/drivers/hid/hid-corsair.c
+++ b/drivers/hid/hid-corsair.c
@@ -3,8 +3,10 @@
  *
  * Supported devices:
  *  - Vengeance K90 Keyboard
+ *  - Scimitar PRO RGB Gaming Mouse
  *
  * Copyright (c) 2015 Clement Vuchener
+ * Copyright (c) 2017 Oscar Campos
  */
 
 /*
@@ -670,10 +672,51 @@ static int corsair_input_mapping(struct hid_device *dev,
 	return 0;
 }
 
+/*
+ * The report descriptor of Corsair Scimitar RGB Pro gaming mouse is
+ * non parseable as they define two consecutive Logical Minimum for
+ * the Usage Page (Consumer) in rdescs bytes 75 and 77 being 77 0x16
+ * that should be obviousy 0x26 for Logical Magimum of 16 bits. This
+ * prevents poper parsing of the report descriptor due Logical
+ * Minimum being larger than Logical Maximum.
+ *
+ * This driver fixes the report descriptor for:
+ * - USB ID b1c:1b3e, sold as Scimitar RGB Pro Gaming mouse
+ */
+
+static __u8 *corsair_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+        unsigned int *rsize)
+{
+	struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
+
+	if (intf->cur_altsetting->desc.bInterfaceNumber == 1) {
+		/*
+		 * Corsair Scimitar RGB Pro report descriptor is broken and
+		 * defines two different Logical Minimum for the Consumer
+		 * Application. The byte 77 should be a 0x26 defining a 16
+		 * bits integer for the Logical Maximum but it is a 0x16
+		 * instead (Logical Minimum)
+		 */
+		switch (hdev->product) {
+		case USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB:
+			if (*rsize >= 172 && rdesc[75] == 0x15 && rdesc[77] == 0x16
+			&& rdesc[78] == 0xff && rdesc[79] == 0x0f) {
+				hid_info(hdev, "Fixing up report descriptor\n");
+				rdesc[77] = 0x26;
+			}
+			break;
+		}
+
+	}
+	return rdesc;
+}
+
 static const struct hid_device_id corsair_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K90),
 		.driver_data = CORSAIR_USE_K90_MACRO |
 			       CORSAIR_USE_K90_BACKLIGHT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR,
+            USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB) },
 	{}
 };
 
@@ -686,10 +729,14 @@ static struct hid_driver corsair_driver = {
 	.event = corsair_event,
 	.remove = corsair_remove,
 	.input_mapping = corsair_input_mapping,
+	.report_fixup = corsair_mouse_report_fixup,
 };
 
 module_hid_driver(corsair_driver);
 
 MODULE_LICENSE("GPL");
+/* Original K90 driver author */
 MODULE_AUTHOR("Clement Vuchener");
+/* Scimitar PRO RGB driver author */
+MODULE_AUTHOR("Oscar Campos");
 MODULE_DESCRIPTION("HID driver for Corsair devices");
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index b22d0f83f8e3..078026f63b6f 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -27,6 +27,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio/driver.h>
 #include <linux/hid.h>
+#include <linux/hidraw.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/nls.h>
@@ -1297,7 +1298,8 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	dev->adap.algo_data	= dev;
 	dev->adap.dev.parent	= &hdev->dev;
 	snprintf(dev->adap.name, sizeof(dev->adap.name),
-		 "CP2112 SMBus Bridge on hiddev%d", hdev->minor);
+		 "CP2112 SMBus Bridge on hidraw%d",
+		 ((struct hidraw *)hdev->hidraw)->minor);
 	dev->hwversion = buf[2];
 	init_waitqueue_head(&dev->wait);
 
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index c6c9c51c806f..5271db593478 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -140,9 +140,11 @@ static const struct hid_usage_entry hid_usage_table[] = {
     {0, 0x03, "LightPen"},
     {0, 0x04, "TouchScreen"},
     {0, 0x05, "TouchPad"},
+    {0, 0x0e, "DeviceConfiguration"},
     {0, 0x20, "Stylus"},
     {0, 0x21, "Puck"},
     {0, 0x22, "Finger"},
+    {0, 0x23, "DeviceSettings"},
     {0, 0x30, "TipPressure"},
     {0, 0x31, "BarrelPressure"},
     {0, 0x32, "InRange"},
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 86c95d30ac80..643390ba749d 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -173,8 +173,10 @@
 #define USB_VENDOR_ID_ASUSTEK		0x0b05
 #define USB_DEVICE_ID_ASUSTEK_LCM	0x1726
 #define USB_DEVICE_ID_ASUSTEK_LCM2	0x175b
-#define USB_DEVICE_ID_ASUSTEK_NOTEBOOK_KEYBOARD	0x8585
-#define USB_DEVICE_ID_ASUSTEK_TOUCHPAD	0x0101
+#define USB_DEVICE_ID_ASUSTEK_I2C_KEYBOARD	0x8585
+#define USB_DEVICE_ID_ASUSTEK_I2C_TOUCHPAD	0x0101
+#define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1 0x1854
+#define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2 0x1837
 
 #define USB_VENDOR_ID_ATEN		0x0557
 #define USB_DEVICE_ID_ATEN_UC100KM	0x2004
@@ -184,6 +186,7 @@
 #define USB_DEVICE_ID_ATEN_4PORTKVMC	0x2208
 #define USB_DEVICE_ID_ATEN_CS682	0x2213
 #define USB_DEVICE_ID_ATEN_CS692	0x8021
+#define USB_DEVICE_ID_ATEN_CS1758	0x2220
 
 #define USB_VENDOR_ID_ATMEL		0x03eb
 #define USB_DEVICE_ID_ATMEL_MULTITOUCH	0x211c
@@ -278,6 +281,9 @@
 #define USB_DEVICE_ID_CORSAIR_K70RGB    0x1b13
 #define USB_DEVICE_ID_CORSAIR_STRAFE    0x1b15
 #define USB_DEVICE_ID_CORSAIR_K65RGB    0x1b17
+#define USB_DEVICE_ID_CORSAIR_K70RGB_RAPIDFIRE  0x1b38
+#define USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE  0x1b39
+#define USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB  0x1b3e
 
 #define USB_VENDOR_ID_CREATIVELABS	0x041e
 #define USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51	0x322c
@@ -363,6 +369,7 @@
 #define USB_VENDOR_ID_ELO		0x04E7
 #define USB_DEVICE_ID_ELO_TS2515	0x0022
 #define USB_DEVICE_ID_ELO_TS2700	0x0020
+#define USB_DEVICE_ID_ELO_ACCUTOUCH_2216	0x0050
 
 #define USB_VENDOR_ID_EMS		0x2006
 #define USB_DEVICE_ID_EMS_TRIO_LINKER_PLUS_II 0x0118
@@ -545,6 +552,9 @@
 #define USB_VENDOR_ID_IRTOUCHSYSTEMS	0x6615
 #define USB_DEVICE_ID_IRTOUCH_INFRARED_USB	0x0070
 
+#define USB_VENDOR_ID_INNOMEDIA			0x1292
+#define USB_DEVICE_ID_INNEX_GENESIS_ATARI	0x4745
+
 #define USB_VENDOR_ID_ITE               0x048d
 #define USB_DEVICE_ID_ITE_LENOVO_YOGA   0x8386
 #define USB_DEVICE_ID_ITE_LENOVO_YOGA2  0x8350
@@ -557,6 +567,7 @@
 
 #define USB_VENDOR_ID_JESS		0x0c45
 #define USB_DEVICE_ID_JESS_YUREX	0x1010
+#define USB_DEVICE_ID_JESS_ZEN_AIO_KBD	0x5112
 
 #define USB_VENDOR_ID_JESS2		0x0f30
 #define USB_DEVICE_ID_JESS2_COLOR_RUMBLE_PAD 0x0111
@@ -767,6 +778,9 @@
 #define USB_DEVICE_ID_NOVATEK_PCT	0x0600
 #define USB_DEVICE_ID_NOVATEK_MOUSE	0x1602
 
+#define USB_VENDOR_ID_NTI               0x0757
+#define USB_DEVICE_ID_USB_SUN           0x0a00
+
 #define USB_VENDOR_ID_NTRIG		0x1b96
 #define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN   0x0001
 #define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1   0x0003
@@ -1024,6 +1038,9 @@
 #define USB_DEVICE_ID_UGEE_TABLET_45		0x0045
 #define USB_DEVICE_ID_YIYNOVA_TABLET		0x004d
 
+#define USB_VENDOR_ID_UGEE		0x28bd
+#define USB_DEVICE_ID_UGEE_TABLET_EX07S		0x0071
+
 #define USB_VENDOR_ID_UNITEC	0x227d
 #define USB_DEVICE_ID_UNITEC_USB_TOUCH_0709	0x0709
 #define USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19	0x0a19
@@ -1078,6 +1095,7 @@
 
 #define USB_VENDOR_ID_XIN_MO			0x16c0
 #define USB_DEVICE_ID_XIN_MO_DUAL_ARCADE	0x05e1
+#define USB_DEVICE_ID_THT_2P_ARCADE		0x75e1
 
 #define USB_VENDOR_ID_XIROKU		0x1477
 #define USB_DEVICE_ID_XIROKU_SPX	0x1006
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index d05f903c7614..a1ebdd7d4d4d 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1150,18 +1150,26 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 
 	/*
 	 * Ignore out-of-range values as per HID specification,
-	 * section 5.10 and 6.2.25.
+	 * section 5.10 and 6.2.25, when NULL state bit is present.
+	 * When it's not, clamp the value to match Microsoft's input
+	 * driver as mentioned in "Required HID usages for digitizers":
+	 * https://msdn.microsoft.com/en-us/library/windows/hardware/dn672278(v=vs.85).asp
 	 *
 	 * The logical_minimum < logical_maximum check is done so that we
 	 * don't unintentionally discard values sent by devices which
 	 * don't specify logical min and max.
 	 */
 	if ((field->flags & HID_MAIN_ITEM_VARIABLE) &&
-	    (field->logical_minimum < field->logical_maximum) &&
-	    (value < field->logical_minimum ||
-	     value > field->logical_maximum)) {
-		dbg_hid("Ignoring out-of-range value %x\n", value);
-		return;
+	    (field->logical_minimum < field->logical_maximum)) {
+		if (field->flags & HID_MAIN_ITEM_NULL_STATE &&
+		    (value < field->logical_minimum ||
+		     value > field->logical_maximum)) {
+			dbg_hid("Ignoring out-of-range value %x\n", value);
+			return;
+		}
+		value = clamp(value,
+			      field->logical_minimum,
+			      field->logical_maximum);
 	}
 
 	/*
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 5bc6d80d5be7..826fa1e1c8d9 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -692,8 +692,12 @@ static void logi_dj_ll_close(struct hid_device *hid)
 	dbg_hid("%s:%s\n", __func__, hid->phys);
 }
 
-static u8 unifying_name_query[]  = {0x10, 0xff, 0x83, 0xb5, 0x40, 0x00, 0x00};
-static u8 unifying_name_answer[] = {0x11, 0xff, 0x83, 0xb5};
+/*
+ * Register 0xB5 is "pairing information". It is solely intended for the
+ * receiver, so do not overwrite the device index.
+ */
+static u8 unifying_pairing_query[]  = {0x10, 0xff, 0x83, 0xb5};
+static u8 unifying_pairing_answer[] = {0x11, 0xff, 0x83, 0xb5};
 
 static int logi_dj_ll_raw_request(struct hid_device *hid,
 				  unsigned char reportnum, __u8 *buf,
@@ -712,9 +716,9 @@ static int logi_dj_ll_raw_request(struct hid_device *hid,
 
 		/* special case where we should not overwrite
 		 * the device_index */
-		if (count == 7 && !memcmp(buf, unifying_name_query,
-					  sizeof(unifying_name_query)))
-			buf[4] |= djdev->device_index - 1;
+		if (count == 7 && !memcmp(buf, unifying_pairing_query,
+					  sizeof(unifying_pairing_query)))
+			buf[4] = (buf[4] & 0xf0) | (djdev->device_index - 1);
 		else
 			buf[1] = djdev->device_index;
 		return hid_hw_raw_request(djrcv_dev->hdev, reportnum, buf,
@@ -911,9 +915,8 @@ static int logi_dj_hidpp_event(struct hid_device *hdev,
 		/* special case were the device wants to know its unifying
 		 * name */
 		if (size == HIDPP_REPORT_LONG_LENGTH &&
-		    !memcmp(data, unifying_name_answer,
-			    sizeof(unifying_name_answer)) &&
-		    ((data[4] & 0xF0) == 0x40))
+		    !memcmp(data, unifying_pairing_answer,
+			    sizeof(unifying_pairing_answer)))
 			device_index = (data[4] & 0x0F) + 1;
 		else
 			return false;
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 2e2515a4c070..41b39464ded8 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -56,15 +56,21 @@ MODULE_PARM_DESC(disable_tap_to_click,
 #define HIDPP_QUIRK_CLASS_M560			BIT(1)
 #define HIDPP_QUIRK_CLASS_K400			BIT(2)
 #define HIDPP_QUIRK_CLASS_G920			BIT(3)
+#define HIDPP_QUIRK_CLASS_K750			BIT(4)
 
 /* bits 2..20 are reserved for classes */
-#define HIDPP_QUIRK_CONNECT_EVENTS		BIT(21)
+/* #define HIDPP_QUIRK_CONNECT_EVENTS		BIT(21) disabled */
 #define HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS	BIT(22)
 #define HIDPP_QUIRK_NO_HIDINPUT			BIT(23)
 #define HIDPP_QUIRK_FORCE_OUTPUT_REPORTS	BIT(24)
+#define HIDPP_QUIRK_UNIFYING			BIT(25)
 
-#define HIDPP_QUIRK_DELAYED_INIT		(HIDPP_QUIRK_NO_HIDINPUT | \
-						 HIDPP_QUIRK_CONNECT_EVENTS)
+#define HIDPP_QUIRK_DELAYED_INIT		HIDPP_QUIRK_NO_HIDINPUT
+
+#define HIDPP_CAPABILITY_HIDPP10_BATTERY	BIT(0)
+#define HIDPP_CAPABILITY_HIDPP20_BATTERY	BIT(1)
+#define HIDPP_CAPABILITY_BATTERY_MILEAGE	BIT(2)
+#define HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS	BIT(3)
 
 /*
  * There are two hidpp protocols in use, the first version hidpp10 is known
@@ -110,6 +116,18 @@ struct hidpp_report {
 	};
 } __packed;
 
+struct hidpp_battery {
+	u8 feature_index;
+	u8 solar_feature_index;
+	struct power_supply_desc desc;
+	struct power_supply *ps;
+	char name[64];
+	int status;
+	int capacity;
+	int level;
+	bool online;
+};
+
 struct hidpp_device {
 	struct hid_device *hid_dev;
 	struct mutex send_mutex;
@@ -128,8 +146,10 @@ struct hidpp_device {
 	struct input_dev *delayed_input;
 
 	unsigned long quirks;
-};
+	unsigned long capabilities;
 
+	struct hidpp_battery battery;
+};
 
 /* HID++ 1.0 error codes */
 #define HIDPP_ERROR				0x8f
@@ -380,15 +400,220 @@ static void hidpp_prefix_name(char **name, int name_length)
 #define HIDPP_SET_LONG_REGISTER				0x82
 #define HIDPP_GET_LONG_REGISTER				0x83
 
+#define HIDPP_REG_GENERAL				0x00
+
+static int hidpp10_enable_battery_reporting(struct hidpp_device *hidpp_dev)
+{
+	struct hidpp_report response;
+	int ret;
+	u8 params[3] = { 0 };
+
+	ret = hidpp_send_rap_command_sync(hidpp_dev,
+					REPORT_ID_HIDPP_SHORT,
+					HIDPP_GET_REGISTER,
+					HIDPP_REG_GENERAL,
+					NULL, 0, &response);
+	if (ret)
+		return ret;
+
+	memcpy(params, response.rap.params, 3);
+
+	/* Set the battery bit */
+	params[0] |= BIT(4);
+
+	return hidpp_send_rap_command_sync(hidpp_dev,
+					REPORT_ID_HIDPP_SHORT,
+					HIDPP_SET_REGISTER,
+					HIDPP_REG_GENERAL,
+					params, 3, &response);
+}
+
+#define HIDPP_REG_BATTERY_STATUS			0x07
+
+static int hidpp10_battery_status_map_level(u8 param)
+{
+	int level;
+
+	switch (param) {
+	case 1 ... 2:
+		level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL;
+		break;
+	case 3 ... 4:
+		level = POWER_SUPPLY_CAPACITY_LEVEL_LOW;
+		break;
+	case 5 ... 6:
+		level = POWER_SUPPLY_CAPACITY_LEVEL_NORMAL;
+		break;
+	case 7:
+		level = POWER_SUPPLY_CAPACITY_LEVEL_HIGH;
+		break;
+	default:
+		level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN;
+	}
+
+	return level;
+}
+
+static int hidpp10_battery_status_map_status(u8 param)
+{
+	int status;
+
+	switch (param) {
+	case 0x00:
+		/* discharging (in use) */
+		status = POWER_SUPPLY_STATUS_DISCHARGING;
+		break;
+	case 0x21: /* (standard) charging */
+	case 0x24: /* fast charging */
+	case 0x25: /* slow charging */
+		status = POWER_SUPPLY_STATUS_CHARGING;
+		break;
+	case 0x26: /* topping charge */
+	case 0x22: /* charge complete */
+		status = POWER_SUPPLY_STATUS_FULL;
+		break;
+	case 0x20: /* unknown */
+		status = POWER_SUPPLY_STATUS_UNKNOWN;
+		break;
+	/*
+	 * 0x01...0x1F = reserved (not charging)
+	 * 0x23 = charging error
+	 * 0x27..0xff = reserved
+	 */
+	default:
+		status = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		break;
+	}
+
+	return status;
+}
+
+static int hidpp10_query_battery_status(struct hidpp_device *hidpp)
+{
+	struct hidpp_report response;
+	int ret, status;
+
+	ret = hidpp_send_rap_command_sync(hidpp,
+					REPORT_ID_HIDPP_SHORT,
+					HIDPP_GET_REGISTER,
+					HIDPP_REG_BATTERY_STATUS,
+					NULL, 0, &response);
+	if (ret)
+		return ret;
+
+	hidpp->battery.level =
+		hidpp10_battery_status_map_level(response.rap.params[0]);
+	status = hidpp10_battery_status_map_status(response.rap.params[1]);
+	hidpp->battery.status = status;
+	/* the capacity is only available when discharging or full */
+	hidpp->battery.online = status == POWER_SUPPLY_STATUS_DISCHARGING ||
+				status == POWER_SUPPLY_STATUS_FULL;
+
+	return 0;
+}
+
+#define HIDPP_REG_BATTERY_MILEAGE			0x0D
+
+static int hidpp10_battery_mileage_map_status(u8 param)
+{
+	int status;
+
+	switch (param >> 6) {
+	case 0x00:
+		/* discharging (in use) */
+		status = POWER_SUPPLY_STATUS_DISCHARGING;
+		break;
+	case 0x01: /* charging */
+		status = POWER_SUPPLY_STATUS_CHARGING;
+		break;
+	case 0x02: /* charge complete */
+		status = POWER_SUPPLY_STATUS_FULL;
+		break;
+	/*
+	 * 0x03 = charging error
+	 */
+	default:
+		status = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		break;
+	}
+
+	return status;
+}
+
+static int hidpp10_query_battery_mileage(struct hidpp_device *hidpp)
+{
+	struct hidpp_report response;
+	int ret, status;
+
+	ret = hidpp_send_rap_command_sync(hidpp,
+					REPORT_ID_HIDPP_SHORT,
+					HIDPP_GET_REGISTER,
+					HIDPP_REG_BATTERY_MILEAGE,
+					NULL, 0, &response);
+	if (ret)
+		return ret;
+
+	hidpp->battery.capacity = response.rap.params[0];
+	status = hidpp10_battery_mileage_map_status(response.rap.params[2]);
+	hidpp->battery.status = status;
+	/* the capacity is only available when discharging or full */
+	hidpp->battery.online = status == POWER_SUPPLY_STATUS_DISCHARGING ||
+				status == POWER_SUPPLY_STATUS_FULL;
+
+	return 0;
+}
+
+static int hidpp10_battery_event(struct hidpp_device *hidpp, u8 *data, int size)
+{
+	struct hidpp_report *report = (struct hidpp_report *)data;
+	int status, capacity, level;
+	bool changed;
+
+	if (report->report_id != REPORT_ID_HIDPP_SHORT)
+		return 0;
+
+	switch (report->rap.sub_id) {
+	case HIDPP_REG_BATTERY_STATUS:
+		capacity = hidpp->battery.capacity;
+		level = hidpp10_battery_status_map_level(report->rawbytes[1]);
+		status = hidpp10_battery_status_map_status(report->rawbytes[2]);
+		break;
+	case HIDPP_REG_BATTERY_MILEAGE:
+		capacity = report->rap.params[0];
+		level = hidpp->battery.level;
+		status = hidpp10_battery_mileage_map_status(report->rawbytes[3]);
+		break;
+	default:
+		return 0;
+	}
+
+	changed = capacity != hidpp->battery.capacity ||
+		  level != hidpp->battery.level ||
+		  status != hidpp->battery.status;
+
+	/* the capacity is only available when discharging or full */
+	hidpp->battery.online = status == POWER_SUPPLY_STATUS_DISCHARGING ||
+				status == POWER_SUPPLY_STATUS_FULL;
+
+	if (changed) {
+		hidpp->battery.level = level;
+		hidpp->battery.status = status;
+		if (hidpp->battery.ps)
+			power_supply_changed(hidpp->battery.ps);
+	}
+
+	return 0;
+}
+
 #define HIDPP_REG_PAIRING_INFORMATION			0xB5
-#define DEVICE_NAME					0x40
+#define HIDPP_EXTENDED_PAIRING				0x30
+#define HIDPP_DEVICE_NAME				0x40
 
-static char *hidpp_get_unifying_name(struct hidpp_device *hidpp_dev)
+static char *hidpp_unifying_get_name(struct hidpp_device *hidpp_dev)
 {
 	struct hidpp_report response;
 	int ret;
-	/* hid-logitech-dj is in charge of setting the right device index */
-	u8 params[1] = { DEVICE_NAME };
+	u8 params[1] = { HIDPP_DEVICE_NAME };
 	char *name;
 	int len;
 
@@ -417,6 +642,54 @@ static char *hidpp_get_unifying_name(struct hidpp_device *hidpp_dev)
 	return name;
 }
 
+static int hidpp_unifying_get_serial(struct hidpp_device *hidpp, u32 *serial)
+{
+	struct hidpp_report response;
+	int ret;
+	u8 params[1] = { HIDPP_EXTENDED_PAIRING };
+
+	ret = hidpp_send_rap_command_sync(hidpp,
+					REPORT_ID_HIDPP_SHORT,
+					HIDPP_GET_LONG_REGISTER,
+					HIDPP_REG_PAIRING_INFORMATION,
+					params, 1, &response);
+	if (ret)
+		return ret;
+
+	/*
+	 * We don't care about LE or BE, we will output it as a string
+	 * with %4phD, so we need to keep the order.
+	 */
+	*serial = *((u32 *)&response.rap.params[1]);
+	return 0;
+}
+
+static int hidpp_unifying_init(struct hidpp_device *hidpp)
+{
+	struct hid_device *hdev = hidpp->hid_dev;
+	const char *name;
+	u32 serial;
+	int ret;
+
+	ret = hidpp_unifying_get_serial(hidpp, &serial);
+	if (ret)
+		return ret;
+
+	snprintf(hdev->uniq, sizeof(hdev->uniq), "%04x-%4phD",
+		 hdev->product, &serial);
+	dbg_hid("HID++ Unifying: Got serial: %s\n", hdev->uniq);
+
+	name = hidpp_unifying_get_name(hidpp);
+	if (!name)
+		return -EIO;
+
+	snprintf(hdev->name, sizeof(hdev->name), "%s", name);
+	dbg_hid("HID++ Unifying: Got name: %s\n", name);
+
+	kfree(name);
+	return 0;
+}
+
 /* -------------------------------------------------------------------------- */
 /* 0x0000: Root                                                               */
 /* -------------------------------------------------------------------------- */
@@ -441,6 +714,9 @@ static int hidpp_root_get_feature(struct hidpp_device *hidpp, u16 feature,
 	if (ret)
 		return ret;
 
+	if (response.fap.params[0] == 0)
+		return -ENOENT;
+
 	*feature_index = response.fap.params[0];
 	*feature_type = response.fap.params[1];
 
@@ -607,6 +883,355 @@ static char *hidpp_get_device_name(struct hidpp_device *hidpp)
 }
 
 /* -------------------------------------------------------------------------- */
+/* 0x1000: Battery level status                                               */
+/* -------------------------------------------------------------------------- */
+
+#define HIDPP_PAGE_BATTERY_LEVEL_STATUS				0x1000
+
+#define CMD_BATTERY_LEVEL_STATUS_GET_BATTERY_LEVEL_STATUS	0x00
+#define CMD_BATTERY_LEVEL_STATUS_GET_BATTERY_CAPABILITY		0x10
+
+#define EVENT_BATTERY_LEVEL_STATUS_BROADCAST			0x00
+
+#define FLAG_BATTERY_LEVEL_DISABLE_OSD				BIT(0)
+#define FLAG_BATTERY_LEVEL_MILEAGE				BIT(1)
+#define FLAG_BATTERY_LEVEL_RECHARGEABLE				BIT(2)
+
+static int hidpp_map_battery_level(int capacity)
+{
+	if (capacity < 11)
+		return POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL;
+	else if (capacity < 31)
+		return POWER_SUPPLY_CAPACITY_LEVEL_LOW;
+	else if (capacity < 81)
+		return POWER_SUPPLY_CAPACITY_LEVEL_NORMAL;
+	return POWER_SUPPLY_CAPACITY_LEVEL_FULL;
+}
+
+static int hidpp20_batterylevel_map_status_capacity(u8 data[3], int *capacity,
+						    int *next_capacity,
+						    int *level)
+{
+	int status;
+
+	*capacity = data[0];
+	*next_capacity = data[1];
+	*level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN;
+
+	/* When discharging, we can rely on the device reported capacity.
+	 * For all other states the device reports 0 (unknown).
+	 */
+	switch (data[2]) {
+		case 0: /* discharging (in use) */
+			status = POWER_SUPPLY_STATUS_DISCHARGING;
+			*level = hidpp_map_battery_level(*capacity);
+			break;
+		case 1: /* recharging */
+			status = POWER_SUPPLY_STATUS_CHARGING;
+			break;
+		case 2: /* charge in final stage */
+			status = POWER_SUPPLY_STATUS_CHARGING;
+			break;
+		case 3: /* charge complete */
+			status = POWER_SUPPLY_STATUS_FULL;
+			*level = POWER_SUPPLY_CAPACITY_LEVEL_FULL;
+			*capacity = 100;
+			break;
+		case 4: /* recharging below optimal speed */
+			status = POWER_SUPPLY_STATUS_CHARGING;
+			break;
+		/* 5 = invalid battery type
+		   6 = thermal error
+		   7 = other charging error */
+		default:
+			status = POWER_SUPPLY_STATUS_NOT_CHARGING;
+			break;
+	}
+
+	return status;
+}
+
+static int hidpp20_batterylevel_get_battery_capacity(struct hidpp_device *hidpp,
+						     u8 feature_index,
+						     int *status,
+						     int *capacity,
+						     int *next_capacity,
+						     int *level)
+{
+	struct hidpp_report response;
+	int ret;
+	u8 *params = (u8 *)response.fap.params;
+
+	ret = hidpp_send_fap_command_sync(hidpp, feature_index,
+					  CMD_BATTERY_LEVEL_STATUS_GET_BATTERY_LEVEL_STATUS,
+					  NULL, 0, &response);
+	if (ret > 0) {
+		hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n",
+			__func__, ret);
+		return -EPROTO;
+	}
+	if (ret)
+		return ret;
+
+	*status = hidpp20_batterylevel_map_status_capacity(params, capacity,
+							   next_capacity,
+							   level);
+
+	return 0;
+}
+
+static int hidpp20_batterylevel_get_battery_info(struct hidpp_device *hidpp,
+						  u8 feature_index)
+{
+	struct hidpp_report response;
+	int ret;
+	u8 *params = (u8 *)response.fap.params;
+	unsigned int level_count, flags;
+
+	ret = hidpp_send_fap_command_sync(hidpp, feature_index,
+					  CMD_BATTERY_LEVEL_STATUS_GET_BATTERY_CAPABILITY,
+					  NULL, 0, &response);
+	if (ret > 0) {
+		hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n",
+			__func__, ret);
+		return -EPROTO;
+	}
+	if (ret)
+		return ret;
+
+	level_count = params[0];
+	flags = params[1];
+
+	if (level_count < 10 || !(flags & FLAG_BATTERY_LEVEL_MILEAGE))
+		hidpp->capabilities |= HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS;
+	else
+		hidpp->capabilities |= HIDPP_CAPABILITY_BATTERY_MILEAGE;
+
+	return 0;
+}
+
+static int hidpp20_query_battery_info(struct hidpp_device *hidpp)
+{
+	u8 feature_type;
+	int ret;
+	int status, capacity, next_capacity, level;
+
+	if (hidpp->battery.feature_index == 0xff) {
+		ret = hidpp_root_get_feature(hidpp,
+					     HIDPP_PAGE_BATTERY_LEVEL_STATUS,
+					     &hidpp->battery.feature_index,
+					     &feature_type);
+		if (ret)
+			return ret;
+	}
+
+	ret = hidpp20_batterylevel_get_battery_capacity(hidpp,
+						hidpp->battery.feature_index,
+						&status, &capacity,
+						&next_capacity, &level);
+	if (ret)
+		return ret;
+
+	ret = hidpp20_batterylevel_get_battery_info(hidpp,
+						hidpp->battery.feature_index);
+	if (ret)
+		return ret;
+
+	hidpp->battery.status = status;
+	hidpp->battery.capacity = capacity;
+	hidpp->battery.level = level;
+	/* the capacity is only available when discharging or full */
+	hidpp->battery.online = status == POWER_SUPPLY_STATUS_DISCHARGING ||
+				status == POWER_SUPPLY_STATUS_FULL;
+
+	return 0;
+}
+
+static int hidpp20_battery_event(struct hidpp_device *hidpp,
+				 u8 *data, int size)
+{
+	struct hidpp_report *report = (struct hidpp_report *)data;
+	int status, capacity, next_capacity, level;
+	bool changed;
+
+	if (report->fap.feature_index != hidpp->battery.feature_index ||
+	    report->fap.funcindex_clientid != EVENT_BATTERY_LEVEL_STATUS_BROADCAST)
+		return 0;
+
+	status = hidpp20_batterylevel_map_status_capacity(report->fap.params,
+							  &capacity,
+							  &next_capacity,
+							  &level);
+
+	/* the capacity is only available when discharging or full */
+	hidpp->battery.online = status == POWER_SUPPLY_STATUS_DISCHARGING ||
+				status == POWER_SUPPLY_STATUS_FULL;
+
+	changed = capacity != hidpp->battery.capacity ||
+		  level != hidpp->battery.level ||
+		  status != hidpp->battery.status;
+
+	if (changed) {
+		hidpp->battery.level = level;
+		hidpp->battery.capacity = capacity;
+		hidpp->battery.status = status;
+		if (hidpp->battery.ps)
+			power_supply_changed(hidpp->battery.ps);
+	}
+
+	return 0;
+}
+
+static enum power_supply_property hidpp_battery_props[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_SCOPE,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_SERIAL_NUMBER,
+	0, /* placeholder for POWER_SUPPLY_PROP_CAPACITY, */
+	0, /* placeholder for POWER_SUPPLY_PROP_CAPACITY_LEVEL, */
+};
+
+static int hidpp_battery_get_property(struct power_supply *psy,
+				      enum power_supply_property psp,
+				      union power_supply_propval *val)
+{
+	struct hidpp_device *hidpp = power_supply_get_drvdata(psy);
+	int ret = 0;
+
+	switch(psp) {
+		case POWER_SUPPLY_PROP_STATUS:
+			val->intval = hidpp->battery.status;
+			break;
+		case POWER_SUPPLY_PROP_CAPACITY:
+			val->intval = hidpp->battery.capacity;
+			break;
+		case POWER_SUPPLY_PROP_CAPACITY_LEVEL:
+			val->intval = hidpp->battery.level;
+			break;
+		case POWER_SUPPLY_PROP_SCOPE:
+			val->intval = POWER_SUPPLY_SCOPE_DEVICE;
+			break;
+		case POWER_SUPPLY_PROP_ONLINE:
+			val->intval = hidpp->battery.online;
+			break;
+		case POWER_SUPPLY_PROP_MODEL_NAME:
+			if (!strncmp(hidpp->name, "Logitech ", 9))
+				val->strval = hidpp->name + 9;
+			else
+				val->strval = hidpp->name;
+			break;
+		case POWER_SUPPLY_PROP_MANUFACTURER:
+			val->strval = "Logitech";
+			break;
+		case POWER_SUPPLY_PROP_SERIAL_NUMBER:
+			val->strval = hidpp->hid_dev->uniq;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+	}
+
+	return ret;
+}
+
+/* -------------------------------------------------------------------------- */
+/* 0x4301: Solar Keyboard                                                     */
+/* -------------------------------------------------------------------------- */
+
+#define HIDPP_PAGE_SOLAR_KEYBOARD			0x4301
+
+#define CMD_SOLAR_SET_LIGHT_MEASURE			0x00
+
+#define EVENT_SOLAR_BATTERY_BROADCAST			0x00
+#define EVENT_SOLAR_BATTERY_LIGHT_MEASURE		0x10
+#define EVENT_SOLAR_CHECK_LIGHT_BUTTON			0x20
+
+static int hidpp_solar_request_battery_event(struct hidpp_device *hidpp)
+{
+	struct hidpp_report response;
+	u8 params[2] = { 1, 1 };
+	u8 feature_type;
+	int ret;
+
+	if (hidpp->battery.feature_index == 0xff) {
+		ret = hidpp_root_get_feature(hidpp,
+					     HIDPP_PAGE_SOLAR_KEYBOARD,
+					     &hidpp->battery.solar_feature_index,
+					     &feature_type);
+		if (ret)
+			return ret;
+	}
+
+	ret = hidpp_send_fap_command_sync(hidpp,
+					  hidpp->battery.solar_feature_index,
+					  CMD_SOLAR_SET_LIGHT_MEASURE,
+					  params, 2, &response);
+	if (ret > 0) {
+		hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n",
+			__func__, ret);
+		return -EPROTO;
+	}
+	if (ret)
+		return ret;
+
+	hidpp->capabilities |= HIDPP_CAPABILITY_BATTERY_MILEAGE;
+
+	return 0;
+}
+
+static int hidpp_solar_battery_event(struct hidpp_device *hidpp,
+				     u8 *data, int size)
+{
+	struct hidpp_report *report = (struct hidpp_report *)data;
+	int capacity, lux, status;
+	u8 function;
+
+	function = report->fap.funcindex_clientid;
+
+
+	if (report->fap.feature_index != hidpp->battery.solar_feature_index ||
+	    !(function == EVENT_SOLAR_BATTERY_BROADCAST ||
+	      function == EVENT_SOLAR_BATTERY_LIGHT_MEASURE ||
+	      function == EVENT_SOLAR_CHECK_LIGHT_BUTTON))
+		return 0;
+
+	capacity = report->fap.params[0];
+
+	switch (function) {
+	case EVENT_SOLAR_BATTERY_LIGHT_MEASURE:
+		lux = (report->fap.params[1] << 8) | report->fap.params[2];
+		if (lux > 200)
+			status = POWER_SUPPLY_STATUS_CHARGING;
+		else
+			status = POWER_SUPPLY_STATUS_DISCHARGING;
+		break;
+	case EVENT_SOLAR_CHECK_LIGHT_BUTTON:
+	default:
+		if (capacity < hidpp->battery.capacity)
+			status = POWER_SUPPLY_STATUS_DISCHARGING;
+		else
+			status = POWER_SUPPLY_STATUS_CHARGING;
+
+	}
+
+	if (capacity == 100)
+		status = POWER_SUPPLY_STATUS_FULL;
+
+	hidpp->battery.online = true;
+	if (capacity != hidpp->battery.capacity ||
+	    status != hidpp->battery.status) {
+		hidpp->battery.capacity = capacity;
+		hidpp->battery.status = status;
+		if (hidpp->battery.ps)
+			power_supply_changed(hidpp->battery.ps);
+	}
+
+	return 0;
+}
+
+/* -------------------------------------------------------------------------- */
 /* 0x6010: Touchpad FW items                                                  */
 /* -------------------------------------------------------------------------- */
 
@@ -1599,9 +2224,6 @@ static int wtp_connect(struct hid_device *hdev, bool connected)
 	struct wtp_data *wd = hidpp->private_data;
 	int ret;
 
-	if (!connected)
-		return 0;
-
 	if (!wd->x_size) {
 		ret = wtp_get_config(hidpp);
 		if (ret) {
@@ -1669,9 +2291,6 @@ static int m560_send_config_command(struct hid_device *hdev, bool connected)
 
 	hidpp_dev = hid_get_drvdata(hdev);
 
-	if (!connected)
-		return -ENODEV;
-
 	return hidpp_send_rap_command_sync(
 		hidpp_dev,
 		REPORT_ID_HIDPP_SHORT,
@@ -1875,9 +2494,6 @@ static int k400_connect(struct hid_device *hdev, bool connected)
 {
 	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
 
-	if (!connected)
-		return 0;
-
 	if (!disable_tap_to_click)
 		return 0;
 
@@ -1974,6 +2590,7 @@ static int hidpp_raw_hidpp_event(struct hidpp_device *hidpp, u8 *data,
 	struct hidpp_report *question = hidpp->send_receive_buf;
 	struct hidpp_report *answer = hidpp->send_receive_buf;
 	struct hidpp_report *report = (struct hidpp_report *)data;
+	int ret;
 
 	/*
 	 * If the mutex is locked then we have a pending answer from a
@@ -2002,12 +2619,26 @@ static int hidpp_raw_hidpp_event(struct hidpp_device *hidpp, u8 *data,
 	if (unlikely(hidpp_report_is_connect_event(report))) {
 		atomic_set(&hidpp->connected,
 				!(report->rap.params[0] & (1 << 6)));
-		if ((hidpp->quirks & HIDPP_QUIRK_CONNECT_EVENTS) &&
-		    (schedule_work(&hidpp->work) == 0))
+		if (schedule_work(&hidpp->work) == 0)
 			dbg_hid("%s: connect event already queued\n", __func__);
 		return 1;
 	}
 
+	if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP20_BATTERY) {
+		ret = hidpp20_battery_event(hidpp, data, size);
+		if (ret != 0)
+			return ret;
+		ret = hidpp_solar_battery_event(hidpp, data, size);
+		if (ret != 0)
+			return ret;
+	}
+
+	if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP10_BATTERY) {
+		ret = hidpp10_battery_event(hidpp, data, size);
+		if (ret != 0)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -2058,20 +2689,90 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report,
 	return 0;
 }
 
-static void hidpp_overwrite_name(struct hid_device *hdev, bool use_unifying)
+static int hidpp_initialize_battery(struct hidpp_device *hidpp)
+{
+	static atomic_t battery_no = ATOMIC_INIT(0);
+	struct power_supply_config cfg = { .drv_data = hidpp };
+	struct power_supply_desc *desc = &hidpp->battery.desc;
+	enum power_supply_property *battery_props;
+	struct hidpp_battery *battery;
+	unsigned int num_battery_props;
+	unsigned long n;
+	int ret;
+
+	if (hidpp->battery.ps)
+		return 0;
+
+	hidpp->battery.feature_index = 0xff;
+	hidpp->battery.solar_feature_index = 0xff;
+
+	if (hidpp->protocol_major >= 2) {
+		if (hidpp->quirks & HIDPP_QUIRK_CLASS_K750)
+			ret = hidpp_solar_request_battery_event(hidpp);
+		else
+			ret = hidpp20_query_battery_info(hidpp);
+
+		if (ret)
+			return ret;
+		hidpp->capabilities |= HIDPP_CAPABILITY_HIDPP20_BATTERY;
+	} else {
+		ret = hidpp10_query_battery_status(hidpp);
+		if (ret) {
+			ret = hidpp10_query_battery_mileage(hidpp);
+			if (ret)
+				return -ENOENT;
+			hidpp->capabilities |= HIDPP_CAPABILITY_BATTERY_MILEAGE;
+		} else {
+			hidpp->capabilities |= HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS;
+		}
+		hidpp->capabilities |= HIDPP_CAPABILITY_HIDPP10_BATTERY;
+	}
+
+	battery_props = devm_kmemdup(&hidpp->hid_dev->dev,
+				     hidpp_battery_props,
+				     sizeof(hidpp_battery_props),
+				     GFP_KERNEL);
+	num_battery_props = ARRAY_SIZE(hidpp_battery_props) - 2;
+
+	if (hidpp->capabilities & HIDPP_CAPABILITY_BATTERY_MILEAGE)
+		battery_props[num_battery_props++] =
+				POWER_SUPPLY_PROP_CAPACITY;
+
+	if (hidpp->capabilities & HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS)
+		battery_props[num_battery_props++] =
+				POWER_SUPPLY_PROP_CAPACITY_LEVEL;
+
+	battery = &hidpp->battery;
+
+	n = atomic_inc_return(&battery_no) - 1;
+	desc->properties = battery_props;
+	desc->num_properties = num_battery_props;
+	desc->get_property = hidpp_battery_get_property;
+	sprintf(battery->name, "hidpp_battery_%ld", n);
+	desc->name = battery->name;
+	desc->type = POWER_SUPPLY_TYPE_BATTERY;
+	desc->use_for_apm = 0;
+
+	battery->ps = devm_power_supply_register(&hidpp->hid_dev->dev,
+						 &battery->desc,
+						 &cfg);
+	if (IS_ERR(battery->ps))
+		return PTR_ERR(battery->ps);
+
+	power_supply_powers(battery->ps, &hidpp->hid_dev->dev);
+
+	return ret;
+}
+
+static void hidpp_overwrite_name(struct hid_device *hdev)
 {
 	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
 	char *name;
 
-	if (use_unifying)
-		/*
-		 * the device is connected through an Unifying receiver, and
-		 * might not be already connected.
-		 * Ask the receiver for its name.
-		 */
-		name = hidpp_get_unifying_name(hidpp);
-	else
-		name = hidpp_get_device_name(hidpp);
+	if (hidpp->protocol_major < 2)
+		return;
+
+	name = hidpp_get_device_name(hidpp);
 
 	if (!name) {
 		hid_err(hdev, "unable to retrieve the name of the device");
@@ -2129,6 +2830,16 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 	struct input_dev *input;
 	char *name, *devm_name;
 
+	if (!connected) {
+		if (hidpp->battery.ps) {
+			hidpp->battery.online = false;
+			hidpp->battery.status = POWER_SUPPLY_STATUS_UNKNOWN;
+			hidpp->battery.level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN;
+			power_supply_changed(hidpp->battery.ps);
+		}
+		return;
+	}
+
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) {
 		ret = wtp_connect(hdev, connected);
 		if (ret)
@@ -2143,9 +2854,6 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 			return;
 	}
 
-	if (!connected || hidpp->delayed_input)
-		return;
-
 	/* the device is already connected, we can ask for its name and
 	 * protocol */
 	if (!hidpp->protocol_major) {
@@ -2158,11 +2866,7 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 			 hidpp->protocol_major, hidpp->protocol_minor);
 	}
 
-	if (!(hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT))
-		/* if HID created the input nodes for us, we can stop now */
-		return;
-
-	if (!hidpp->name || hidpp->name == hdev->name) {
+	if (hidpp->name == hdev->name && hidpp->protocol_major >= 2) {
 		name = hidpp_get_device_name(hidpp);
 		if (!name) {
 			hid_err(hdev,
@@ -2178,6 +2882,25 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 		hidpp->name = devm_name;
 	}
 
+	hidpp_initialize_battery(hidpp);
+
+	/* forward current battery state */
+	if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP10_BATTERY) {
+		hidpp10_enable_battery_reporting(hidpp);
+		if (hidpp->capabilities & HIDPP_CAPABILITY_BATTERY_MILEAGE)
+			hidpp10_query_battery_mileage(hidpp);
+		else
+			hidpp10_query_battery_status(hidpp);
+	} else if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP20_BATTERY) {
+		hidpp20_query_battery_info(hidpp);
+	}
+	if (hidpp->battery.ps)
+		power_supply_changed(hidpp->battery.ps);
+
+	if (!(hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT) || hidpp->delayed_input)
+		/* if the input nodes are already created, we can stop now */
+		return;
+
 	input = hidpp_allocate_input(hdev);
 	if (!input) {
 		hid_err(hdev, "cannot allocate new input device: %d\n", ret);
@@ -2193,6 +2916,17 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 	hidpp->delayed_input = input;
 }
 
+static DEVICE_ATTR(builtin_power_supply, 0000, NULL, NULL);
+
+static struct attribute *sysfs_attrs[] = {
+	&dev_attr_builtin_power_supply.attr,
+	NULL
+};
+
+static struct attribute_group ps_attribute_group = {
+	.attrs = sysfs_attrs
+};
+
 static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	struct hidpp_device *hidpp;
@@ -2211,9 +2945,11 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 
 	hidpp->quirks = id->driver_data;
 
+	if (id->group == HID_GROUP_LOGITECH_DJ_DEVICE)
+		hidpp->quirks |= HIDPP_QUIRK_UNIFYING;
+
 	if (disable_raw_mode) {
 		hidpp->quirks &= ~HIDPP_QUIRK_CLASS_WTP;
-		hidpp->quirks &= ~HIDPP_QUIRK_CONNECT_EVENTS;
 		hidpp->quirks &= ~HIDPP_QUIRK_NO_HIDINPUT;
 	}
 
@@ -2235,6 +2971,12 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	mutex_init(&hidpp->send_mutex);
 	init_waitqueue_head(&hidpp->wait);
 
+	/* indicates we are handling the battery properties in the kernel */
+	ret = sysfs_create_group(&hdev->dev.kobj, &ps_attribute_group);
+	if (ret)
+		hid_warn(hdev, "Cannot allocate sysfs group for %s\n",
+			 hdev->name);
+
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "%s:parse failed\n", __func__);
@@ -2263,8 +3005,12 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	/* Allow incoming packets */
 	hid_device_io_start(hdev);
 
+	if (hidpp->quirks & HIDPP_QUIRK_UNIFYING)
+		hidpp_unifying_init(hidpp);
+
 	connected = hidpp_is_connected(hidpp);
-	if (id->group != HID_GROUP_LOGITECH_DJ_DEVICE) {
+	atomic_set(&hidpp->connected, connected);
+	if (!(hidpp->quirks & HIDPP_QUIRK_UNIFYING)) {
 		if (!connected) {
 			ret = -ENODEV;
 			hid_err(hdev, "Device not connected");
@@ -2273,10 +3019,9 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 
 		hid_info(hdev, "HID++ %u.%u device connected.\n",
 			 hidpp->protocol_major, hidpp->protocol_minor);
-	}
 
-	hidpp_overwrite_name(hdev, id->group == HID_GROUP_LOGITECH_DJ_DEVICE);
-	atomic_set(&hidpp->connected, connected);
+		hidpp_overwrite_name(hdev);
+	}
 
 	if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)) {
 		ret = wtp_get_config(hidpp);
@@ -2299,12 +3044,10 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		}
 	}
 
-	if (hidpp->quirks & HIDPP_QUIRK_CONNECT_EVENTS) {
-		/* Allow incoming packets */
-		hid_device_io_start(hdev);
+	/* Allow incoming packets */
+	hid_device_io_start(hdev);
 
-		hidpp_connect_event(hidpp);
-	}
+	hidpp_connect_event(hidpp);
 
 	return ret;
 
@@ -2316,6 +3059,7 @@ hid_hw_open_failed:
 	}
 hid_hw_start_fail:
 hid_parse_fail:
+	sysfs_remove_group(&hdev->dev.kobj, &ps_attribute_group);
 	cancel_work_sync(&hidpp->work);
 	mutex_destroy(&hidpp->send_mutex);
 allocate_fail:
@@ -2327,6 +3071,8 @@ static void hidpp_remove(struct hid_device *hdev)
 {
 	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
 
+	sysfs_remove_group(&hdev->dev.kobj, &ps_attribute_group);
+
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) {
 		hidpp_ff_deinit(hdev);
 		hid_hw_close(hdev);
@@ -2357,7 +3103,11 @@ static const struct hid_device_id hidpp_devices[] = {
 	{ /* Keyboard logitech K400 */
 	  HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
 		USB_VENDOR_ID_LOGITECH, 0x4024),
-	  .driver_data = HIDPP_QUIRK_CONNECT_EVENTS | HIDPP_QUIRK_CLASS_K400 },
+	  .driver_data = HIDPP_QUIRK_CLASS_K400 },
+	{ /* Solar Keyboard Logitech K750 */
+	  HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
+		USB_VENDOR_ID_LOGITECH, 0x4002),
+	  .driver_data = HIDPP_QUIRK_CLASS_K750 },
 
 	{ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
 		USB_VENDOR_ID_LOGITECH, HID_ANY_ID)},
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 692647485a53..24d5b6deb571 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -69,6 +69,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_CONTACT_CNT_ACCURATE	(1 << 12)
 #define MT_QUIRK_FORCE_GET_FEATURE	(1 << 13)
 #define MT_QUIRK_FIX_CONST_CONTACT_ID	(1 << 14)
+#define MT_QUIRK_TOUCH_SIZE_SCALING	(1 << 15)
 
 #define MT_INPUTMODE_TOUCHSCREEN	0x02
 #define MT_INPUTMODE_TOUCHPAD		0x03
@@ -222,7 +223,8 @@ static struct mt_class mt_classes[] = {
 	 */
 	{ .name = MT_CLS_3M,
 		.quirks = MT_QUIRK_VALID_IS_CONFIDENCE |
-			MT_QUIRK_SLOT_IS_CONTACTID,
+			MT_QUIRK_SLOT_IS_CONTACTID |
+			MT_QUIRK_TOUCH_SIZE_SCALING,
 		.sn_move = 2048,
 		.sn_width = 128,
 		.sn_height = 128,
@@ -658,9 +660,17 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
 		if (active) {
 			/* this finger is in proximity of the sensor */
 			int wide = (s->w > s->h);
-			/* divided by two to match visual scale of touch */
-			int major = max(s->w, s->h) >> 1;
-			int minor = min(s->w, s->h) >> 1;
+			int major = max(s->w, s->h);
+			int minor = min(s->w, s->h);
+
+			/*
+			 * divided by two to match visual scale of touch
+			 * for devices with this quirk
+			 */
+			if (td->mtclass.quirks & MT_QUIRK_TOUCH_SIZE_SCALING) {
+				major = major >> 1;
+				minor = minor >> 1;
+			}
 
 			input_event(input, EV_ABS, ABS_MT_POSITION_X, s->x);
 			input_event(input, EV_ABS, ABS_MT_POSITION_Y, s->y);
diff --git a/drivers/hid/hid-nti.c b/drivers/hid/hid-nti.c
new file mode 100644
index 000000000000..5bb827b223ba
--- /dev/null
+++ b/drivers/hid/hid-nti.c
@@ -0,0 +1,59 @@
+/*
+ *  USB HID quirks support for Network Technologies, Inc. "USB-SUN" USB
+ *  adapter for pre-USB Sun keyboards
+ *
+ *  Copyright (c) 2011 Google, Inc.
+ *
+ * Based on HID apple driver by
+ *  Copyright (c) 1999 Andreas Gal
+ *  Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz>
+ *  Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc
+ *  Copyright (c) 2006-2007 Jiri Kosina
+ *  Copyright (c) 2008 Jiri Slaby <jirislaby@gmail.com>
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/input.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+
+#include "hid-ids.h"
+
+MODULE_AUTHOR("Jonathan Klabunde Tomer <jktomer@google.com>");
+MODULE_DESCRIPTION("HID driver for Network Technologies USB-SUN keyboard adapter");
+
+/*
+ * NTI Sun keyboard adapter has wrong logical maximum in report descriptor
+ */
+static __u8 *nti_usbsun_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int *rsize)
+{
+	if (*rsize >= 60 && rdesc[53] == 0x65 && rdesc[59] == 0x65) {
+		hid_info(hdev, "fixing up NTI USB-SUN keyboard adapter report descriptor\n");
+		rdesc[53] = rdesc[59] = 0xe7;
+	}
+	return rdesc;
+}
+
+static const struct hid_device_id nti_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_NTI, USB_DEVICE_ID_USB_SUN) },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, nti_devices);
+
+static struct hid_driver nti_driver = {
+	.name = "nti",
+	.id_table = nti_devices,
+	.report_fixup = nti_usbsun_report_fixup
+};
+
+module_hid_driver(nti_driver);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index f405b07d0381..d03203a82e8f 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -48,19 +48,21 @@
 #define PS3REMOTE                 BIT(4)
 #define DUALSHOCK4_CONTROLLER_USB BIT(5)
 #define DUALSHOCK4_CONTROLLER_BT  BIT(6)
-#define MOTION_CONTROLLER_USB     BIT(7)
-#define MOTION_CONTROLLER_BT      BIT(8)
-#define NAVIGATION_CONTROLLER_USB BIT(9)
-#define NAVIGATION_CONTROLLER_BT  BIT(10)
-#define SINO_LITE_CONTROLLER      BIT(11)
-#define FUTUREMAX_DANCE_MAT       BIT(12)
+#define DUALSHOCK4_DONGLE         BIT(7)
+#define MOTION_CONTROLLER_USB     BIT(8)
+#define MOTION_CONTROLLER_BT      BIT(9)
+#define NAVIGATION_CONTROLLER_USB BIT(10)
+#define NAVIGATION_CONTROLLER_BT  BIT(11)
+#define SINO_LITE_CONTROLLER      BIT(12)
+#define FUTUREMAX_DANCE_MAT       BIT(13)
 
 #define SIXAXIS_CONTROLLER (SIXAXIS_CONTROLLER_USB | SIXAXIS_CONTROLLER_BT)
 #define MOTION_CONTROLLER (MOTION_CONTROLLER_USB | MOTION_CONTROLLER_BT)
 #define NAVIGATION_CONTROLLER (NAVIGATION_CONTROLLER_USB |\
 				NAVIGATION_CONTROLLER_BT)
 #define DUALSHOCK4_CONTROLLER (DUALSHOCK4_CONTROLLER_USB |\
-				DUALSHOCK4_CONTROLLER_BT)
+				DUALSHOCK4_CONTROLLER_BT | \
+				DUALSHOCK4_DONGLE)
 #define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER | BUZZ_CONTROLLER |\
 				DUALSHOCK4_CONTROLLER | MOTION_CONTROLLER |\
 				NAVIGATION_CONTROLLER)
@@ -73,89 +75,6 @@
 
 #define MAX_LEDS 4
 
-/*
- * The Sixaxis reports both digital and analog values for each button on the
- * controller except for Start, Select and the PS button.  The controller ends
- * up reporting 27 axes which causes them to spill over into the multi-touch
- * axis values.  Additionally, the controller only has 20 actual, physical axes
- * so there are several unused axes in between the used ones.
- */
-static u8 sixaxis_rdesc[] = {
-	0x05, 0x01,         /*  Usage Page (Desktop),               */
-	0x09, 0x04,         /*  Usage (Joystick),                   */
-	0xA1, 0x01,         /*  Collection (Application),           */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0x01,         /*          Report ID (1),              */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x01,         /*          Report Count (1),           */
-	0x15, 0x00,         /*          Logical Minimum (0),        */
-	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
-	0x81, 0x03,         /*          Input (Constant, Variable), */
-	0x75, 0x01,         /*          Report Size (1),            */
-	0x95, 0x13,         /*          Report Count (19),          */
-	0x15, 0x00,         /*          Logical Minimum (0),        */
-	0x25, 0x01,         /*          Logical Maximum (1),        */
-	0x35, 0x00,         /*          Physical Minimum (0),       */
-	0x45, 0x01,         /*          Physical Maximum (1),       */
-	0x05, 0x09,         /*          Usage Page (Button),        */
-	0x19, 0x01,         /*          Usage Minimum (01h),        */
-	0x29, 0x13,         /*          Usage Maximum (13h),        */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x75, 0x01,         /*          Report Size (1),            */
-	0x95, 0x0D,         /*          Report Count (13),          */
-	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
-	0x81, 0x03,         /*          Input (Constant, Variable), */
-	0x15, 0x00,         /*          Logical Minimum (0),        */
-	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
-	0x05, 0x01,         /*          Usage Page (Desktop),       */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xA1, 0x00,         /*          Collection (Physical),      */
-	0x75, 0x08,         /*              Report Size (8),        */
-	0x95, 0x04,         /*              Report Count (4),       */
-	0x35, 0x00,         /*              Physical Minimum (0),   */
-	0x46, 0xFF, 0x00,   /*              Physical Maximum (255), */
-	0x09, 0x30,         /*              Usage (X),              */
-	0x09, 0x31,         /*              Usage (Y),              */
-	0x09, 0x32,         /*              Usage (Z),              */
-	0x09, 0x35,         /*              Usage (Rz),             */
-	0x81, 0x02,         /*              Input (Variable),       */
-	0xC0,               /*          End Collection,             */
-	0x05, 0x01,         /*          Usage Page (Desktop),       */
-	0x95, 0x13,         /*          Report Count (19),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x95, 0x0C,         /*          Report Count (12),          */
-	0x81, 0x01,         /*          Input (Constant),           */
-	0x75, 0x10,         /*          Report Size (16),           */
-	0x95, 0x04,         /*          Report Count (4),           */
-	0x26, 0xFF, 0x03,   /*          Logical Maximum (1023),     */
-	0x46, 0xFF, 0x03,   /*          Physical Maximum (1023),    */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0xC0,               /*      End Collection,                 */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0x02,         /*          Report ID (2),              */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0xEE,         /*          Report ID (238),            */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0xEF,         /*          Report ID (239),            */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xC0                /*  End Collection                      */
-};
 
 /* PS/3 Motion controller */
 static u8 motion_rdesc[] = {
@@ -254,567 +173,6 @@ static u8 motion_rdesc[] = {
 	0xC0                /*  End Collection                      */
 };
 
-/* PS/3 Navigation controller */
-static u8 navigation_rdesc[] = {
-	0x05, 0x01,         /*  Usage Page (Desktop),               */
-	0x09, 0x04,         /*  Usage (Joystick),                   */
-	0xA1, 0x01,         /*  Collection (Application),           */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0x01,         /*          Report ID (1),              */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x01,         /*          Report Count (1),           */
-	0x15, 0x00,         /*          Logical Minimum (0),        */
-	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
-	0x81, 0x03,         /*          Input (Constant, Variable), */
-	0x75, 0x01,         /*          Report Size (1),            */
-	0x95, 0x13,         /*          Report Count (19),          */
-	0x15, 0x00,         /*          Logical Minimum (0),        */
-	0x25, 0x01,         /*          Logical Maximum (1),        */
-	0x35, 0x00,         /*          Physical Minimum (0),       */
-	0x45, 0x01,         /*          Physical Maximum (1),       */
-	0x05, 0x09,         /*          Usage Page (Button),        */
-	0x19, 0x01,         /*          Usage Minimum (01h),        */
-	0x29, 0x13,         /*          Usage Maximum (13h),        */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x75, 0x01,         /*          Report Size (1),            */
-	0x95, 0x0D,         /*          Report Count (13),          */
-	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
-	0x81, 0x03,         /*          Input (Constant, Variable), */
-	0x15, 0x00,         /*          Logical Minimum (0),        */
-	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
-	0x05, 0x01,         /*          Usage Page (Desktop),       */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xA1, 0x00,         /*          Collection (Physical),      */
-	0x75, 0x08,         /*              Report Size (8),        */
-	0x95, 0x02,         /*              Report Count (2),       */
-	0x35, 0x00,         /*              Physical Minimum (0),   */
-	0x46, 0xFF, 0x00,   /*              Physical Maximum (255), */
-	0x09, 0x30,         /*              Usage (X),              */
-	0x09, 0x31,         /*              Usage (Y),              */
-	0x81, 0x02,         /*              Input (Variable),       */
-	0xC0,               /*          End Collection,             */
-	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
-	0x95, 0x06,         /*          Report Count (6),           */
-	0x81, 0x03,         /*          Input (Constant, Variable), */
-	0x05, 0x01,         /*          Usage Page (Desktop),       */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x05,         /*          Report Count (5),           */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
-	0x95, 0x01,         /*          Report Count (1),           */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x05, 0x01,         /*          Usage Page (Desktop),       */
-	0x95, 0x01,         /*          Report Count (1),           */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
-	0x95, 0x1E,         /*          Report Count (24),          */
-	0x81, 0x02,         /*          Input (Variable),           */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0x91, 0x02,         /*          Output (Variable),          */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0x02,         /*          Report ID (2),              */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0xEE,         /*          Report ID (238),            */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xA1, 0x02,         /*      Collection (Logical),           */
-	0x85, 0xEF,         /*          Report ID (239),            */
-	0x75, 0x08,         /*          Report Size (8),            */
-	0x95, 0x30,         /*          Report Count (48),          */
-	0x09, 0x01,         /*          Usage (Pointer),            */
-	0xB1, 0x02,         /*          Feature (Variable),         */
-	0xC0,               /*      End Collection,                 */
-	0xC0                /*  End Collection                      */
-};
-
-/*
- * The default descriptor doesn't provide mapping for the accelerometers
- * or orientation sensors.  This fixed descriptor maps the accelerometers
- * to usage values 0x40, 0x41 and 0x42 and maps the orientation sensors
- * to usage values 0x43, 0x44 and 0x45.
- */
-static u8 dualshock4_usb_rdesc[] = {
-	0x05, 0x01,         /*  Usage Page (Desktop),               */
-	0x09, 0x05,         /*  Usage (Gamepad),                    */
-	0xA1, 0x01,         /*  Collection (Application),           */
-	0x85, 0x01,         /*      Report ID (1),                  */
-	0x09, 0x30,         /*      Usage (X),                      */
-	0x09, 0x31,         /*      Usage (Y),                      */
-	0x09, 0x32,         /*      Usage (Z),                      */
-	0x09, 0x35,         /*      Usage (Rz),                     */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x26, 0xFF, 0x00,   /*      Logical Maximum (255),          */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x04,         /*      Report Count (4),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x39,         /*      Usage (Hat Switch),             */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x25, 0x07,         /*      Logical Maximum (7),            */
-	0x35, 0x00,         /*      Physical Minimum (0),           */
-	0x46, 0x3B, 0x01,   /*      Physical Maximum (315),         */
-	0x65, 0x14,         /*      Unit (Degrees),                 */
-	0x75, 0x04,         /*      Report Size (4),                */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0x81, 0x42,         /*      Input (Variable, Null State),   */
-	0x65, 0x00,         /*      Unit,                           */
-	0x05, 0x09,         /*      Usage Page (Button),            */
-	0x19, 0x01,         /*      Usage Minimum (01h),            */
-	0x29, 0x0D,         /*      Usage Maximum (0Dh),            */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x25, 0x01,         /*      Logical Maximum (1),            */
-	0x75, 0x01,         /*      Report Size (1),                */
-	0x95, 0x0E,         /*      Report Count (14),              */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x06, 0x00, 0xFF,   /*      Usage Page (FF00h),             */
-	0x09, 0x20,         /*      Usage (20h),                    */
-	0x75, 0x06,         /*      Report Size (6),                */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x25, 0x3F,         /*      Logical Maximum (63),           */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x05, 0x01,         /*      Usage Page (Desktop),           */
-	0x09, 0x33,         /*      Usage (Rx),                     */
-	0x09, 0x34,         /*      Usage (Ry),                     */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x26, 0xFF, 0x00,   /*      Logical Maximum (255),          */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x02,         /*      Report Count (2),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x06, 0x00, 0xFF,   /*      Usage Page (FF00h),             */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x05, 0x01,         /*      Usage Page (Desktop),           */
-	0x19, 0x40,         /*      Usage Minimum (40h),            */
-	0x29, 0x42,         /*      Usage Maximum (42h),            */
-	0x16, 0x00, 0x80,   /*      Logical Minimum (-32768),       */
-	0x26, 0xFF, 0x7F,   /*      Logical Maximum (32767),        */
-	0x75, 0x10,         /*      Report Size (16),               */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x19, 0x43,         /*      Usage Minimum (43h),            */
-	0x29, 0x45,         /*      Usage Maximum (45h),            */
-	0x16, 0x00, 0x80,   /*      Logical Minimum (-32768),       */
-	0x26, 0xFF, 0x7F,   /*      Logical Maximum (32767),        */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x06, 0x00, 0xFF,   /*      Usage Page (FF00h),             */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x26, 0xFF, 0x00,   /*      Logical Maximum (255),          */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x27,         /*      Report Count (39),              */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x85, 0x05,         /*      Report ID (5),                  */
-	0x09, 0x22,         /*      Usage (22h),                    */
-	0x95, 0x1F,         /*      Report Count (31),              */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x04,         /*      Report ID (4),                  */
-	0x09, 0x23,         /*      Usage (23h),                    */
-	0x95, 0x24,         /*      Report Count (36),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x02,         /*      Report ID (2),                  */
-	0x09, 0x24,         /*      Usage (24h),                    */
-	0x95, 0x24,         /*      Report Count (36),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x08,         /*      Report ID (8),                  */
-	0x09, 0x25,         /*      Usage (25h),                    */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x10,         /*      Report ID (16),                 */
-	0x09, 0x26,         /*      Usage (26h),                    */
-	0x95, 0x04,         /*      Report Count (4),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x11,         /*      Report ID (17),                 */
-	0x09, 0x27,         /*      Usage (27h),                    */
-	0x95, 0x02,         /*      Report Count (2),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x12,         /*      Report ID (18),                 */
-	0x06, 0x02, 0xFF,   /*      Usage Page (FF02h),             */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x95, 0x0F,         /*      Report Count (15),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x13,         /*      Report ID (19),                 */
-	0x09, 0x22,         /*      Usage (22h),                    */
-	0x95, 0x16,         /*      Report Count (22),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x14,         /*      Report ID (20),                 */
-	0x06, 0x05, 0xFF,   /*      Usage Page (FF05h),             */
-	0x09, 0x20,         /*      Usage (20h),                    */
-	0x95, 0x10,         /*      Report Count (16),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x15,         /*      Report ID (21),                 */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x95, 0x2C,         /*      Report Count (44),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x06, 0x80, 0xFF,   /*      Usage Page (FF80h),             */
-	0x85, 0x80,         /*      Report ID (128),                */
-	0x09, 0x20,         /*      Usage (20h),                    */
-	0x95, 0x06,         /*      Report Count (6),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x81,         /*      Report ID (129),                */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x95, 0x06,         /*      Report Count (6),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x82,         /*      Report ID (130),                */
-	0x09, 0x22,         /*      Usage (22h),                    */
-	0x95, 0x05,         /*      Report Count (5),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x83,         /*      Report ID (131),                */
-	0x09, 0x23,         /*      Usage (23h),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x84,         /*      Report ID (132),                */
-	0x09, 0x24,         /*      Usage (24h),                    */
-	0x95, 0x04,         /*      Report Count (4),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x85,         /*      Report ID (133),                */
-	0x09, 0x25,         /*      Usage (25h),                    */
-	0x95, 0x06,         /*      Report Count (6),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x86,         /*      Report ID (134),                */
-	0x09, 0x26,         /*      Usage (26h),                    */
-	0x95, 0x06,         /*      Report Count (6),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x87,         /*      Report ID (135),                */
-	0x09, 0x27,         /*      Usage (27h),                    */
-	0x95, 0x23,         /*      Report Count (35),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x88,         /*      Report ID (136),                */
-	0x09, 0x28,         /*      Usage (28h),                    */
-	0x95, 0x22,         /*      Report Count (34),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x89,         /*      Report ID (137),                */
-	0x09, 0x29,         /*      Usage (29h),                    */
-	0x95, 0x02,         /*      Report Count (2),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x90,         /*      Report ID (144),                */
-	0x09, 0x30,         /*      Usage (30h),                    */
-	0x95, 0x05,         /*      Report Count (5),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x91,         /*      Report ID (145),                */
-	0x09, 0x31,         /*      Usage (31h),                    */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x92,         /*      Report ID (146),                */
-	0x09, 0x32,         /*      Usage (32h),                    */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x93,         /*      Report ID (147),                */
-	0x09, 0x33,         /*      Usage (33h),                    */
-	0x95, 0x0C,         /*      Report Count (12),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA0,         /*      Report ID (160),                */
-	0x09, 0x40,         /*      Usage (40h),                    */
-	0x95, 0x06,         /*      Report Count (6),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA1,         /*      Report ID (161),                */
-	0x09, 0x41,         /*      Usage (41h),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA2,         /*      Report ID (162),                */
-	0x09, 0x42,         /*      Usage (42h),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA3,         /*      Report ID (163),                */
-	0x09, 0x43,         /*      Usage (43h),                    */
-	0x95, 0x30,         /*      Report Count (48),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA4,         /*      Report ID (164),                */
-	0x09, 0x44,         /*      Usage (44h),                    */
-	0x95, 0x0D,         /*      Report Count (13),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA5,         /*      Report ID (165),                */
-	0x09, 0x45,         /*      Usage (45h),                    */
-	0x95, 0x15,         /*      Report Count (21),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA6,         /*      Report ID (166),                */
-	0x09, 0x46,         /*      Usage (46h),                    */
-	0x95, 0x15,         /*      Report Count (21),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xF0,         /*      Report ID (240),                */
-	0x09, 0x47,         /*      Usage (47h),                    */
-	0x95, 0x3F,         /*      Report Count (63),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xF1,         /*      Report ID (241),                */
-	0x09, 0x48,         /*      Usage (48h),                    */
-	0x95, 0x3F,         /*      Report Count (63),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xF2,         /*      Report ID (242),                */
-	0x09, 0x49,         /*      Usage (49h),                    */
-	0x95, 0x0F,         /*      Report Count (15),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA7,         /*      Report ID (167),                */
-	0x09, 0x4A,         /*      Usage (4Ah),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA8,         /*      Report ID (168),                */
-	0x09, 0x4B,         /*      Usage (4Bh),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA9,         /*      Report ID (169),                */
-	0x09, 0x4C,         /*      Usage (4Ch),                    */
-	0x95, 0x08,         /*      Report Count (8),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xAA,         /*      Report ID (170),                */
-	0x09, 0x4E,         /*      Usage (4Eh),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xAB,         /*      Report ID (171),                */
-	0x09, 0x4F,         /*      Usage (4Fh),                    */
-	0x95, 0x39,         /*      Report Count (57),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xAC,         /*      Report ID (172),                */
-	0x09, 0x50,         /*      Usage (50h),                    */
-	0x95, 0x39,         /*      Report Count (57),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xAD,         /*      Report ID (173),                */
-	0x09, 0x51,         /*      Usage (51h),                    */
-	0x95, 0x0B,         /*      Report Count (11),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xAE,         /*      Report ID (174),                */
-	0x09, 0x52,         /*      Usage (52h),                    */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xAF,         /*      Report ID (175),                */
-	0x09, 0x53,         /*      Usage (53h),                    */
-	0x95, 0x02,         /*      Report Count (2),               */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xB0,         /*      Report ID (176),                */
-	0x09, 0x54,         /*      Usage (54h),                    */
-	0x95, 0x3F,         /*      Report Count (63),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0xC0                /*  End Collection                      */
-};
-
-/*
- * The default behavior of the Dualshock 4 is to send reports using report
- * type 1 when running over Bluetooth. However, when feature report 2 is
- * requested during the controller initialization it starts sending input
- * reports in report 17.  Since report 17 is undefined in the default HID
- * descriptor the button and axis definitions must be moved to report 17 or
- * the HID layer won't process the received input.
- */
-static u8 dualshock4_bt_rdesc[] = {
-	0x05, 0x01,         /*  Usage Page (Desktop),               */
-	0x09, 0x05,         /*  Usage (Gamepad),                    */
-	0xA1, 0x01,         /*  Collection (Application),           */
-	0x85, 0x01,         /*      Report ID (1),                  */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x0A,         /*      Report Count (9),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x06, 0x04, 0xFF,   /*      Usage Page (FF04h),             */
-	0x85, 0x02,         /*      Report ID (2),                  */
-	0x09, 0x24,         /*      Usage (24h),                    */
-	0x95, 0x24,         /*      Report Count (36),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA3,         /*      Report ID (163),                */
-	0x09, 0x25,         /*      Usage (25h),                    */
-	0x95, 0x30,         /*      Report Count (48),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x05,         /*      Report ID (5),                  */
-	0x09, 0x26,         /*      Usage (26h),                    */
-	0x95, 0x28,         /*      Report Count (40),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x06,         /*      Report ID (6),                  */
-	0x09, 0x27,         /*      Usage (27h),                    */
-	0x95, 0x34,         /*      Report Count (52),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x07,         /*      Report ID (7),                  */
-	0x09, 0x28,         /*      Usage (28h),                    */
-	0x95, 0x30,         /*      Report Count (48),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x08,         /*      Report ID (8),                  */
-	0x09, 0x29,         /*      Usage (29h),                    */
-	0x95, 0x2F,         /*      Report Count (47),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x06, 0x03, 0xFF,   /*      Usage Page (FF03h),             */
-	0x85, 0x03,         /*      Report ID (3),                  */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x95, 0x26,         /*      Report Count (38),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x04,         /*      Report ID (4),                  */
-	0x09, 0x22,         /*      Usage (22h),                    */
-	0x95, 0x2E,         /*      Report Count (46),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xF0,         /*      Report ID (240),                */
-	0x09, 0x47,         /*      Usage (47h),                    */
-	0x95, 0x3F,         /*      Report Count (63),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xF1,         /*      Report ID (241),                */
-	0x09, 0x48,         /*      Usage (48h),                    */
-	0x95, 0x3F,         /*      Report Count (63),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xF2,         /*      Report ID (242),                */
-	0x09, 0x49,         /*      Usage (49h),                    */
-	0x95, 0x0F,         /*      Report Count (15),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x11,         /*      Report ID (17),                 */
-	0x06, 0x00, 0xFF,   /*      Usage Page (FF00h),             */
-	0x09, 0x20,         /*      Usage (20h),                    */
-	0x95, 0x02,         /*      Report Count (2),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x05, 0x01,         /*      Usage Page (Desktop),           */
-	0x09, 0x30,         /*      Usage (X),                      */
-	0x09, 0x31,         /*      Usage (Y),                      */
-	0x09, 0x32,         /*      Usage (Z),                      */
-	0x09, 0x35,         /*      Usage (Rz),                     */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x26, 0xFF, 0x00,   /*      Logical Maximum (255),          */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x04,         /*      Report Count (4),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x39,         /*      Usage (Hat Switch),             */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x25, 0x07,         /*      Logical Maximum (7),            */
-	0x75, 0x04,         /*      Report Size (4),                */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0x81, 0x42,         /*      Input (Variable, Null State),   */
-	0x05, 0x09,         /*      Usage Page (Button),            */
-	0x19, 0x01,         /*      Usage Minimum (01h),            */
-	0x29, 0x0D,         /*      Usage Maximum (0Dh),            */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x25, 0x01,         /*      Logical Maximum (1),            */
-	0x75, 0x01,         /*      Report Size (1),                */
-	0x95, 0x0E,         /*      Report Count (14),              */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x75, 0x06,         /*      Report Size (6),                */
-	0x95, 0x01,         /*      Report Count (1),               */
-	0x81, 0x01,         /*      Input (Constant),               */
-	0x05, 0x01,         /*      Usage Page (Desktop),           */
-	0x09, 0x33,         /*      Usage (Rx),                     */
-	0x09, 0x34,         /*      Usage (Ry),                     */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x26, 0xFF, 0x00,   /*      Logical Maximum (255),          */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x02,         /*      Report Count (2),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x06, 0x00, 0xFF,   /*      Usage Page (FF00h),             */
-	0x09, 0x20,         /*      Usage (20h),                    */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x05, 0x01,         /*      Usage Page (Desktop),           */
-	0x19, 0x40,         /*      Usage Minimum (40h),            */
-	0x29, 0x42,         /*      Usage Maximum (42h),            */
-	0x16, 0x00, 0x80,   /*      Logical Minimum (-32768),       */
-	0x26, 0xFF, 0x7F,   /*      Logical Maximum (32767),        */
-	0x75, 0x10,         /*      Report Size (16),               */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x19, 0x43,         /*      Usage Minimum (43h),            */
-	0x29, 0x45,         /*      Usage Maximum (45h),            */
-	0x16, 0x00, 0x80,   /*      Logical Minimum (-32768),       */
-	0x26, 0xFF, 0x7F,   /*      Logical Maximum (32767),        */
-	0x95, 0x03,         /*      Report Count (3),               */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x06, 0x00, 0xFF,   /*      Usage Page (FF00h),             */
-	0x09, 0x20,         /*      Usage (20h),                    */
-	0x15, 0x00,         /*      Logical Minimum (0),            */
-	0x26, 0xFF, 0x00,   /*      Logical Maximum (255),          */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x31,         /*      Report Count (51),              */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x21,         /*      Usage (21h),                    */
-	0x75, 0x08,         /*      Report Size (8),                */
-	0x95, 0x4D,         /*      Report Count (77),              */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x12,         /*      Report ID (18),                 */
-	0x09, 0x22,         /*      Usage (22h),                    */
-	0x95, 0x8D,         /*      Report Count (141),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x23,         /*      Usage (23h),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x13,         /*      Report ID (19),                 */
-	0x09, 0x24,         /*      Usage (24h),                    */
-	0x95, 0xCD,         /*      Report Count (205),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x25,         /*      Usage (25h),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x14,         /*      Report ID (20),                 */
-	0x09, 0x26,         /*      Usage (26h),                    */
-	0x96, 0x0D, 0x01,   /*      Report Count (269),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x27,         /*      Usage (27h),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x15,         /*      Report ID (21),                 */
-	0x09, 0x28,         /*      Usage (28h),                    */
-	0x96, 0x4D, 0x01,   /*      Report Count (333),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x29,         /*      Usage (29h),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x16,         /*      Report ID (22),                 */
-	0x09, 0x2A,         /*      Usage (2Ah),                    */
-	0x96, 0x8D, 0x01,   /*      Report Count (397),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x2B,         /*      Usage (2Bh),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x17,         /*      Report ID (23),                 */
-	0x09, 0x2C,         /*      Usage (2Ch),                    */
-	0x96, 0xCD, 0x01,   /*      Report Count (461),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x2D,         /*      Usage (2Dh),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x18,         /*      Report ID (24),                 */
-	0x09, 0x2E,         /*      Usage (2Eh),                    */
-	0x96, 0x0D, 0x02,   /*      Report Count (525),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x2F,         /*      Usage (2Fh),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x85, 0x19,         /*      Report ID (25),                 */
-	0x09, 0x30,         /*      Usage (30h),                    */
-	0x96, 0x22, 0x02,   /*      Report Count (546),             */
-	0x81, 0x02,         /*      Input (Variable),               */
-	0x09, 0x31,         /*      Usage (31h),                    */
-	0x91, 0x02,         /*      Output (Variable),              */
-	0x06, 0x80, 0xFF,   /*      Usage Page (FF80h),             */
-	0x85, 0x82,         /*      Report ID (130),                */
-	0x09, 0x22,         /*      Usage (22h),                    */
-	0x95, 0x3F,         /*      Report Count (63),              */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x83,         /*      Report ID (131),                */
-	0x09, 0x23,         /*      Usage (23h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x84,         /*      Report ID (132),                */
-	0x09, 0x24,         /*      Usage (24h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x90,         /*      Report ID (144),                */
-	0x09, 0x30,         /*      Usage (30h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x91,         /*      Report ID (145),                */
-	0x09, 0x31,         /*      Usage (31h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x92,         /*      Report ID (146),                */
-	0x09, 0x32,         /*      Usage (32h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0x93,         /*      Report ID (147),                */
-	0x09, 0x33,         /*      Usage (33h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA0,         /*      Report ID (160),                */
-	0x09, 0x40,         /*      Usage (40h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0x85, 0xA4,         /*      Report ID (164),                */
-	0x09, 0x44,         /*      Usage (44h),                    */
-	0xB1, 0x02,         /*      Feature (Variable),             */
-	0xC0                /*  End Collection                      */
-};
-
 static u8 ps3remote_rdesc[] = {
 	0x05, 0x01,          /* GUsagePage Generic Desktop */
 	0x09, 0x05,          /* LUsage 0x05 [Game Pad] */
@@ -977,6 +335,67 @@ static const unsigned int buzz_keymap[] = {
 	[20] = BTN_TRIGGER_HAPPY20,
 };
 
+/* The Navigation controller is a partial DS3 and uses the same HID report
+ * and hence the same keymap indices, however not not all axes/buttons
+ * are physically present. We use the same axis and button mapping as
+ * the DS3, which uses the Linux gamepad spec.
+ */
+static const unsigned int navigation_absmap[] = {
+	[0x30] = ABS_X,
+	[0x31] = ABS_Y,
+	[0x33] = ABS_Z, /* L2 */
+};
+
+/* Buttons not physically available on the device, but still available
+ * in the reports are explicitly set to 0 for documentation purposes.
+ */
+static const unsigned int navigation_keymap[] = {
+	[0x01] = 0, /* Select */
+	[0x02] = BTN_THUMBL, /* L3 */
+	[0x03] = 0, /* R3 */
+	[0x04] = 0, /* Start */
+	[0x05] = BTN_DPAD_UP, /* Up */
+	[0x06] = BTN_DPAD_RIGHT, /* Right */
+	[0x07] = BTN_DPAD_DOWN, /* Down */
+	[0x08] = BTN_DPAD_LEFT, /* Left */
+	[0x09] = BTN_TL2, /* L2 */
+	[0x0a] = 0, /* R2 */
+	[0x0b] = BTN_TL, /* L1 */
+	[0x0c] = 0, /* R1 */
+	[0x0d] = BTN_NORTH, /* Triangle */
+	[0x0e] = BTN_EAST, /* Circle */
+	[0x0f] = BTN_SOUTH, /* Cross */
+	[0x10] = BTN_WEST, /* Square */
+	[0x11] = BTN_MODE, /* PS */
+};
+
+static const unsigned int sixaxis_absmap[] = {
+	[0x30] = ABS_X,
+	[0x31] = ABS_Y,
+	[0x32] = ABS_RX, /* right stick X */
+	[0x35] = ABS_RY, /* right stick Y */
+};
+
+static const unsigned int sixaxis_keymap[] = {
+	[0x01] = BTN_SELECT, /* Select */
+	[0x02] = BTN_THUMBL, /* L3 */
+	[0x03] = BTN_THUMBR, /* R3 */
+	[0x04] = BTN_START, /* Start */
+	[0x05] = BTN_DPAD_UP, /* Up */
+	[0x06] = BTN_DPAD_RIGHT, /* Right */
+	[0x07] = BTN_DPAD_DOWN, /* Down */
+	[0x08] = BTN_DPAD_LEFT, /* Left */
+	[0x09] = BTN_TL2, /* L2 */
+	[0x0a] = BTN_TR2, /* R2 */
+	[0x0b] = BTN_TL, /* L1 */
+	[0x0c] = BTN_TR, /* R1 */
+	[0x0d] = BTN_NORTH, /* Triangle */
+	[0x0e] = BTN_EAST, /* Circle */
+	[0x0f] = BTN_SOUTH, /* Cross */
+	[0x10] = BTN_WEST, /* Square */
+	[0x11] = BTN_MODE, /* PS */
+};
+
 static const unsigned int ds4_absmap[] = {
 	[0x30] = ABS_X,
 	[0x31] = ABS_Y,
@@ -1002,6 +421,10 @@ static const unsigned int ds4_keymap[] = {
 	[0xd] = BTN_MODE, /* PS */
 };
 
+static const struct {int x; int y; } ds4_hat_mapping[] = {
+	{0, -1}, {1, -1}, {1, 0}, {1, 1}, {0, 1}, {-1, 1}, {-1, 0}, {-1, -1},
+	{0, 0}
+};
 
 static enum power_supply_property sony_battery_props[] = {
 	POWER_SUPPLY_PROP_PRESENT,
@@ -1048,6 +471,7 @@ struct motion_output_report_02 {
 };
 
 #define DS4_FEATURE_REPORT_0x02_SIZE 37
+#define DS4_FEATURE_REPORT_0x05_SIZE 41
 #define DS4_FEATURE_REPORT_0x81_SIZE 7
 #define DS4_INPUT_REPORT_0x11_SIZE 78
 #define DS4_OUTPUT_REPORT_0x05_SIZE 32
@@ -1059,23 +483,62 @@ struct motion_output_report_02 {
 /* Offsets relative to USB input report (0x1). Bluetooth (0x11) requires an
  * additional +2.
  */
+#define DS4_INPUT_REPORT_AXIS_OFFSET      1
 #define DS4_INPUT_REPORT_BUTTON_OFFSET    5
+#define DS4_INPUT_REPORT_TIMESTAMP_OFFSET 10
+#define DS4_INPUT_REPORT_GYRO_X_OFFSET   13
 #define DS4_INPUT_REPORT_BATTERY_OFFSET  30
 #define DS4_INPUT_REPORT_TOUCHPAD_OFFSET 33
 
+#define SENSOR_SUFFIX " Motion Sensors"
 #define DS4_TOUCHPAD_SUFFIX " Touchpad"
 
+/* Default to 4ms poll interval, which is same as USB (not adjustable). */
+#define DS4_BT_DEFAULT_POLL_INTERVAL_MS 4
+#define DS4_BT_MAX_POLL_INTERVAL_MS 62
+#define DS4_GYRO_RES_PER_DEG_S 1024
+#define DS4_ACC_RES_PER_G      8192
+
+#define SIXAXIS_INPUT_REPORT_ACC_X_OFFSET 41
+#define SIXAXIS_ACC_RES_PER_G 113
+
 static DEFINE_SPINLOCK(sony_dev_list_lock);
 static LIST_HEAD(sony_device_list);
 static DEFINE_IDA(sony_device_id_allocator);
 
+/* Used for calibration of DS4 accelerometer and gyro. */
+struct ds4_calibration_data {
+	int abs_code;
+	short bias;
+	/* Calibration requires scaling against a sensitivity value, which is a
+	 * float. Store sensitivity as a fraction to limit floating point
+	 * calculations until final calibration.
+	 */
+	int sens_numer;
+	int sens_denom;
+};
+
+enum ds4_dongle_state {
+	DONGLE_DISCONNECTED,
+	DONGLE_CALIBRATING,
+	DONGLE_CONNECTED,
+	DONGLE_DISABLED
+};
+
+enum sony_worker {
+	SONY_WORKER_STATE,
+	SONY_WORKER_HOTPLUG
+};
+
 struct sony_sc {
 	spinlock_t lock;
 	struct list_head list_node;
 	struct hid_device *hdev;
 	struct input_dev *touchpad;
+	struct input_dev *sensor_dev;
 	struct led_classdev *leds[MAX_LEDS];
 	unsigned long quirks;
+	struct work_struct hotplug_worker;
 	struct work_struct state_worker;
 	void (*send_output_report)(struct sony_sc *);
 	struct power_supply *battery;
@@ -1089,46 +552,87 @@ struct sony_sc {
 #endif
 
 	u8 mac_address[6];
-	u8 worker_initialized;
+	u8 hotplug_worker_initialized;
+	u8 state_worker_initialized;
 	u8 defer_initialization;
 	u8 cable_state;
 	u8 battery_charging;
 	u8 battery_capacity;
 	u8 led_state[MAX_LEDS];
-	u8 resume_led_state[MAX_LEDS];
 	u8 led_delay_on[MAX_LEDS];
 	u8 led_delay_off[MAX_LEDS];
 	u8 led_count;
-	bool ds4_dongle_connected;
+
+	bool timestamp_initialized;
+	u16 prev_timestamp;
+	unsigned int timestamp_us;
+
+	u8 ds4_bt_poll_interval;
+	enum ds4_dongle_state ds4_dongle_state;
+	/* DS4 calibration data */
+	struct ds4_calibration_data ds4_calib_data[6];
 };
 
 static void sony_set_leds(struct sony_sc *sc);
 
-static inline void sony_schedule_work(struct sony_sc *sc)
+static inline void sony_schedule_work(struct sony_sc *sc,
+				      enum sony_worker which)
 {
-	if (!sc->defer_initialization)
-		schedule_work(&sc->state_worker);
+	switch (which) {
+	case SONY_WORKER_STATE:
+		if (!sc->defer_initialization)
+			schedule_work(&sc->state_worker);
+		break;
+	case SONY_WORKER_HOTPLUG:
+		if (sc->hotplug_worker_initialized)
+			schedule_work(&sc->hotplug_worker);
+		break;
+	}
 }
 
-static u8 *sixaxis_fixup(struct hid_device *hdev, u8 *rdesc,
-			     unsigned int *rsize)
+static ssize_t ds4_show_poll_interval(struct device *dev,
+				struct device_attribute
+				*attr, char *buf)
 {
-	*rsize = sizeof(sixaxis_rdesc);
-	return sixaxis_rdesc;
+	struct hid_device *hdev = to_hid_device(dev);
+	struct sony_sc *sc = hid_get_drvdata(hdev);
+
+	return snprintf(buf, PAGE_SIZE, "%i\n", sc->ds4_bt_poll_interval);
 }
 
-static u8 *motion_fixup(struct hid_device *hdev, u8 *rdesc,
-			     unsigned int *rsize)
+static ssize_t ds4_store_poll_interval(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
-	*rsize = sizeof(motion_rdesc);
-	return motion_rdesc;
+	struct hid_device *hdev = to_hid_device(dev);
+	struct sony_sc *sc = hid_get_drvdata(hdev);
+	unsigned long flags;
+	u8 interval;
+
+	if (kstrtou8(buf, 0, &interval))
+		return -EINVAL;
+
+	if (interval > DS4_BT_MAX_POLL_INTERVAL_MS)
+		return -EINVAL;
+
+	spin_lock_irqsave(&sc->lock, flags);
+	sc->ds4_bt_poll_interval = interval;
+	spin_unlock_irqrestore(&sc->lock, flags);
+
+	sony_schedule_work(sc, SONY_WORKER_STATE);
+
+	return count;
 }
 
-static u8 *navigation_fixup(struct hid_device *hdev, u8 *rdesc,
+static DEVICE_ATTR(bt_poll_interval, 0644, ds4_show_poll_interval,
+		ds4_store_poll_interval);
+
+
+static u8 *motion_fixup(struct hid_device *hdev, u8 *rdesc,
 			     unsigned int *rsize)
 {
-	*rsize = sizeof(navigation_rdesc);
-	return navigation_rdesc;
+	*rsize = sizeof(motion_rdesc);
+	return motion_rdesc;
 }
 
 static u8 *ps3remote_fixup(struct hid_device *hdev, u8 *rdesc,
@@ -1172,6 +676,102 @@ static int ps3remote_mapping(struct hid_device *hdev, struct hid_input *hi,
 	return 1;
 }
 
+static int navigation_mapping(struct hid_device *hdev, struct hid_input *hi,
+			  struct hid_field *field, struct hid_usage *usage,
+			  unsigned long **bit, int *max)
+{
+	if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) {
+		unsigned int key = usage->hid & HID_USAGE;
+
+		if (key >= ARRAY_SIZE(sixaxis_keymap))
+			return -1;
+
+		key = navigation_keymap[key];
+		if (!key)
+			return -1;
+
+		hid_map_usage_clear(hi, usage, bit, max, EV_KEY, key);
+		return 1;
+	} else if (usage->hid == HID_GD_POINTER) {
+		/* See comment in sixaxis_mapping, basically the L2 (and R2)
+		 * triggers are reported through GD Pointer.
+		 * In addition we ignore any analog button 'axes' and only
+		 * support digital buttons.
+		 */
+		switch (usage->usage_index) {
+		case 8: /* L2 */
+			usage->hid = HID_GD_Z;
+			break;
+		default:
+			return -1;
+		}
+
+		hid_map_usage_clear(hi, usage, bit, max, EV_ABS, usage->hid & 0xf);
+		return 1;
+	} else if ((usage->hid & HID_USAGE_PAGE) == HID_UP_GENDESK) {
+		unsigned int abs = usage->hid & HID_USAGE;
+
+		if (abs >= ARRAY_SIZE(navigation_absmap))
+			return -1;
+
+		abs = navigation_absmap[abs];
+
+		hid_map_usage_clear(hi, usage, bit, max, EV_ABS, abs);
+		return 1;
+	}
+
+	return -1;
+}
+
+
+static int sixaxis_mapping(struct hid_device *hdev, struct hid_input *hi,
+			  struct hid_field *field, struct hid_usage *usage,
+			  unsigned long **bit, int *max)
+{
+	if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) {
+		unsigned int key = usage->hid & HID_USAGE;
+
+		if (key >= ARRAY_SIZE(sixaxis_keymap))
+			return -1;
+
+		key = sixaxis_keymap[key];
+		hid_map_usage_clear(hi, usage, bit, max, EV_KEY, key);
+		return 1;
+	} else if (usage->hid == HID_GD_POINTER) {
+		/* The DS3 provides analog values for most buttons and even
+		 * for HAT axes through GD Pointer. L2 and R2 are reported
+		 * among these as well instead of as GD Z / RZ. Remap L2
+		 * and R2 and ignore other analog 'button axes' as there is
+		 * no good way for reporting them.
+		 */
+		switch (usage->usage_index) {
+		case 8: /* L2 */
+			usage->hid = HID_GD_Z;
+			break;
+		case 9: /* R2 */
+			usage->hid = HID_GD_RZ;
+			break;
+		default:
+			return -1;
+		}
+
+		hid_map_usage_clear(hi, usage, bit, max, EV_ABS, usage->hid & 0xf);
+		return 1;
+	} else if ((usage->hid & HID_USAGE_PAGE) == HID_UP_GENDESK) {
+		unsigned int abs = usage->hid & HID_USAGE;
+
+		if (abs >= ARRAY_SIZE(sixaxis_absmap))
+			return -1;
+
+		abs = sixaxis_absmap[abs];
+
+		hid_map_usage_clear(hi, usage, bit, max, EV_ABS, abs);
+		return 1;
+	}
+
+	return -1;
+}
+
 static int ds4_mapping(struct hid_device *hdev, struct hid_input *hi,
 		       struct hid_field *field, struct hid_usage *usage,
 		       unsigned long **bit, int *max)
@@ -1227,30 +827,9 @@ static u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc,
 		rdesc[55] = 0x06;
 	}
 
-	/*
-	 * The default Dualshock 4 USB descriptor doesn't assign
-	 * the gyroscope values to corresponding axes so we need a
-	 * modified one.
-	 */
-	if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
-		hid_info(hdev, "Using modified Dualshock 4 report descriptor with gyroscope axes\n");
-		rdesc = dualshock4_usb_rdesc;
-		*rsize = sizeof(dualshock4_usb_rdesc);
-	} else if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) {
-		hid_info(hdev, "Using modified Dualshock 4 Bluetooth report descriptor\n");
-		rdesc = dualshock4_bt_rdesc;
-		*rsize = sizeof(dualshock4_bt_rdesc);
-	}
-
-	if (sc->quirks & SIXAXIS_CONTROLLER)
-		return sixaxis_fixup(hdev, rdesc, rsize);
-
 	if (sc->quirks & MOTION_CONTROLLER)
 		return motion_fixup(hdev, rdesc, rsize);
 
-	if (sc->quirks & NAVIGATION_CONTROLLER)
-		return navigation_fixup(hdev, rdesc, rsize);
-
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_fixup(hdev, rdesc, rsize);
 
@@ -1288,22 +867,132 @@ static void sixaxis_parse_report(struct sony_sc *sc, u8 *rd, int size)
 	sc->battery_capacity = battery_capacity;
 	sc->battery_charging = battery_charging;
 	spin_unlock_irqrestore(&sc->lock, flags);
+
+	if (sc->quirks & SIXAXIS_CONTROLLER) {
+		int val;
+
+		offset = SIXAXIS_INPUT_REPORT_ACC_X_OFFSET;
+		val = ((rd[offset+1] << 8) | rd[offset]) - 511;
+		input_report_abs(sc->sensor_dev, ABS_X, val);
+
+		/* Y and Z are swapped and inversed */
+		val = 511 - ((rd[offset+5] << 8) | rd[offset+4]);
+		input_report_abs(sc->sensor_dev, ABS_Y, val);
+
+		val = 511 - ((rd[offset+3] << 8) | rd[offset+2]);
+		input_report_abs(sc->sensor_dev, ABS_Z, val);
+
+		input_sync(sc->sensor_dev);
+	}
 }
 
 static void dualshock4_parse_report(struct sony_sc *sc, u8 *rd, int size)
 {
+	struct hid_input *hidinput = list_entry(sc->hdev->inputs.next,
+						struct hid_input, list);
+	struct input_dev *input_dev = hidinput->input;
 	unsigned long flags;
 	int n, m, offset, num_touch_data, max_touch_data;
 	u8 cable_state, battery_capacity, battery_charging;
+	u16 timestamp;
 
 	/* When using Bluetooth the header is 2 bytes longer, so skip these. */
-	int data_offset = (sc->quirks & DUALSHOCK4_CONTROLLER_USB) ? 0 : 2;
+	int data_offset = (sc->quirks & DUALSHOCK4_CONTROLLER_BT) ? 2 : 0;
 
 	/* Second bit of third button byte is for the touchpad button. */
 	offset = data_offset + DS4_INPUT_REPORT_BUTTON_OFFSET;
 	input_report_key(sc->touchpad, BTN_LEFT, rd[offset+2] & 0x2);
 
 	/*
+	 * The default behavior of the Dualshock 4 is to send reports using
+	 * report type 1 when running over Bluetooth. However, when feature
+	 * report 2 is requested during the controller initialization it starts
+	 * sending input reports in report 17. Since report 17 is undefined
+	 * in the default HID descriptor, the HID layer won't generate events.
+	 * While it is possible (and this was done before) to fixup the HID
+	 * descriptor to add this mapping, it was better to do this manually.
+	 * The reason is there were various pieces software both open and closed
+	 * source, relying on the descriptors to be the same across various
+	 * operating systems. If the descriptors wouldn't match some
+	 * applications e.g. games on Wine would not be able to function due
+	 * to different descriptors, which such applications are not parsing.
+	 */
+	if (rd[0] == 17) {
+		int value;
+
+		offset = data_offset + DS4_INPUT_REPORT_AXIS_OFFSET;
+		input_report_abs(input_dev, ABS_X, rd[offset]);
+		input_report_abs(input_dev, ABS_Y, rd[offset+1]);
+		input_report_abs(input_dev, ABS_RX, rd[offset+2]);
+		input_report_abs(input_dev, ABS_RY, rd[offset+3]);
+
+		value = rd[offset+4] & 0xf;
+		if (value > 7)
+			value = 8; /* Center 0, 0 */
+		input_report_abs(input_dev, ABS_HAT0X, ds4_hat_mapping[value].x);
+		input_report_abs(input_dev, ABS_HAT0Y, ds4_hat_mapping[value].y);
+
+		input_report_key(input_dev, BTN_WEST, rd[offset+4] & 0x10);
+		input_report_key(input_dev, BTN_SOUTH, rd[offset+4] & 0x20);
+		input_report_key(input_dev, BTN_EAST, rd[offset+4] & 0x40);
+		input_report_key(input_dev, BTN_NORTH, rd[offset+4] & 0x80);
+
+		input_report_key(input_dev, BTN_TL, rd[offset+5] & 0x1);
+		input_report_key(input_dev, BTN_TR, rd[offset+5] & 0x2);
+		input_report_key(input_dev, BTN_TL2, rd[offset+5] & 0x4);
+		input_report_key(input_dev, BTN_TR2, rd[offset+5] & 0x8);
+		input_report_key(input_dev, BTN_SELECT, rd[offset+5] & 0x10);
+		input_report_key(input_dev, BTN_START, rd[offset+5] & 0x20);
+		input_report_key(input_dev, BTN_THUMBL, rd[offset+5] & 0x40);
+		input_report_key(input_dev, BTN_THUMBR, rd[offset+5] & 0x80);
+
+		input_report_key(input_dev, BTN_MODE, rd[offset+6] & 0x1);
+
+		input_report_abs(input_dev, ABS_Z, rd[offset+7]);
+		input_report_abs(input_dev, ABS_RZ, rd[offset+8]);
+
+		input_sync(input_dev);
+	}
+
+	/* Convert timestamp (in 5.33us unit) to timestamp_us */
+	offset = data_offset + DS4_INPUT_REPORT_TIMESTAMP_OFFSET;
+	timestamp = get_unaligned_le16(&rd[offset]);
+	if (!sc->timestamp_initialized) {
+		sc->timestamp_us = ((unsigned int)timestamp * 16) / 3;
+		sc->timestamp_initialized = true;
+	} else {
+		u16 delta;
+
+		if (sc->prev_timestamp > timestamp)
+			delta = (U16_MAX - sc->prev_timestamp + timestamp + 1);
+		else
+			delta = timestamp - sc->prev_timestamp;
+		sc->timestamp_us += (delta * 16) / 3;
+	}
+	sc->prev_timestamp = timestamp;
+	input_event(sc->sensor_dev, EV_MSC, MSC_TIMESTAMP, sc->timestamp_us);
+
+	offset = data_offset + DS4_INPUT_REPORT_GYRO_X_OFFSET;
+	for (n = 0; n < 6; n++) {
+		/* Store data in int for more precision during mult_frac. */
+		int raw_data = (short)((rd[offset+1] << 8) | rd[offset]);
+		struct ds4_calibration_data *calib = &sc->ds4_calib_data[n];
+
+		/* High precision is needed during calibration, but the
+		 * calibrated values are within 32-bit.
+		 * Note: we swap numerator 'x' and 'numer' in mult_frac for
+		 *       precision reasons so we don't need 64-bit.
+		 */
+		int calib_data = mult_frac(calib->sens_numer,
+					   raw_data - calib->bias,
+					   calib->sens_denom);
+
+		input_report_abs(sc->sensor_dev, calib->abs_code, calib_data);
+		offset += 2;
+	}
+	input_sync(sc->sensor_dev);
+
+	/*
 	 * The lower 4 bits of byte 30 (or 32 for BT) contain the battery level
 	 * and the 5th bit contains the USB cable state.
 	 */
@@ -1341,7 +1030,7 @@ static void dualshock4_parse_report(struct sony_sc *sc, u8 *rd, int size)
 	 * Trackpad data starts 2 bytes later (e.g. 35 for USB).
 	 */
 	offset = data_offset + DS4_INPUT_REPORT_TOUCHPAD_OFFSET;
-	max_touch_data = (sc->quirks & DUALSHOCK4_CONTROLLER_USB) ? 3 : 4;
+	max_touch_data = (sc->quirks & DUALSHOCK4_CONTROLLER_BT) ? 4 : 3;
 	if (rd[offset] > 0 && rd[offset] <= max_touch_data)
 		num_touch_data = rd[offset];
 	else
@@ -1415,47 +1104,79 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report,
 	} else if ((sc->quirks & NAVIGATION_CONTROLLER) && rd[0] == 0x01 &&
 			size == 49) {
 		sixaxis_parse_report(sc, rd, size);
-	} else if (((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && rd[0] == 0x01 &&
-			size == 64) || ((sc->quirks & DUALSHOCK4_CONTROLLER_BT)
-			&& rd[0] == 0x11 && size == 78)) {
-		if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) {
-			/* CRC check */
-			u8 bthdr = 0xA1;
-			u32 crc;
-			u32 report_crc;
+	} else if ((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && rd[0] == 0x01 &&
+			size == 64) {
+		dualshock4_parse_report(sc, rd, size);
+	} else if (((sc->quirks & DUALSHOCK4_CONTROLLER_BT) && rd[0] == 0x11 &&
+			size == 78)) {
+		/* CRC check */
+		u8 bthdr = 0xA1;
+		u32 crc;
+		u32 report_crc;
 
-			crc = crc32_le(0xFFFFFFFF, &bthdr, 1);
-			crc = ~crc32_le(crc, rd, DS4_INPUT_REPORT_0x11_SIZE-4);
-			report_crc = get_unaligned_le32(&rd[DS4_INPUT_REPORT_0x11_SIZE-4]);
-			if (crc != report_crc) {
-				hid_dbg(sc->hdev, "DualShock 4 input report's CRC check failed, received crc 0x%0x != 0x%0x\n",
-					report_crc, crc);
-				return -EILSEQ;
-			}
+		crc = crc32_le(0xFFFFFFFF, &bthdr, 1);
+		crc = ~crc32_le(crc, rd, DS4_INPUT_REPORT_0x11_SIZE-4);
+		report_crc = get_unaligned_le32(&rd[DS4_INPUT_REPORT_0x11_SIZE-4]);
+		if (crc != report_crc) {
+			hid_dbg(sc->hdev, "DualShock 4 input report's CRC check failed, received crc 0x%0x != 0x%0x\n",
+				report_crc, crc);
+			return -EILSEQ;
 		}
 
+		dualshock4_parse_report(sc, rd, size);
+	} else if ((sc->quirks & DUALSHOCK4_DONGLE) && rd[0] == 0x01 &&
+			size == 64) {
+		unsigned long flags;
+		enum ds4_dongle_state dongle_state;
+
 		/*
 		 * In the case of a DS4 USB dongle, bit[2] of byte 31 indicates
 		 * if a DS4 is actually connected (indicated by '0').
 		 * For non-dongle, this bit is always 0 (connected).
 		 */
-		if (sc->hdev->vendor == USB_VENDOR_ID_SONY &&
-		    sc->hdev->product == USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE) {
-			bool connected = (rd[31] & 0x04) ? false : true;
-
-			if (!sc->ds4_dongle_connected && connected) {
-				hid_info(sc->hdev, "DualShock 4 USB dongle: controller connected\n");
-				sony_set_leds(sc);
-				sc->ds4_dongle_connected = true;
-			} else if (sc->ds4_dongle_connected && !connected) {
-				hid_info(sc->hdev, "DualShock 4 USB dongle: controller disconnected\n");
-				sc->ds4_dongle_connected = false;
-				/* Return 0, so hidraw can get the report. */
-				return 0;
-			} else if (!sc->ds4_dongle_connected) {
-				/* Return 0, so hidraw can get the report. */
-				return 0;
-			}
+		bool connected = (rd[31] & 0x04) ? false : true;
+
+		spin_lock_irqsave(&sc->lock, flags);
+		dongle_state = sc->ds4_dongle_state;
+		spin_unlock_irqrestore(&sc->lock, flags);
+
+		/*
+		 * The dongle always sends input reports even when no
+		 * DS4 is attached. When a DS4 is connected, we need to
+		 * obtain calibration data before we can use it.
+		 * The code below tracks dongle state and kicks of
+		 * calibration when needed and only allows us to process
+		 * input if a DS4 is actually connected.
+		 */
+		if (dongle_state == DONGLE_DISCONNECTED && connected) {
+			hid_info(sc->hdev, "DualShock 4 USB dongle: controller connected\n");
+			sony_set_leds(sc);
+
+			spin_lock_irqsave(&sc->lock, flags);
+			sc->ds4_dongle_state = DONGLE_CALIBRATING;
+			spin_unlock_irqrestore(&sc->lock, flags);
+
+			sony_schedule_work(sc, SONY_WORKER_HOTPLUG);
+
+			/* Don't process the report since we don't have
+			 * calibration data, but let hidraw have it anyway.
+			 */
+			return 0;
+		} else if ((dongle_state == DONGLE_CONNECTED ||
+			    dongle_state == DONGLE_DISABLED) && !connected) {
+			hid_info(sc->hdev, "DualShock 4 USB dongle: controller disconnected\n");
+
+			spin_lock_irqsave(&sc->lock, flags);
+			sc->ds4_dongle_state = DONGLE_DISCONNECTED;
+			spin_unlock_irqrestore(&sc->lock, flags);
+
+			/* Return 0, so hidraw can get the report. */
+			return 0;
+		} else if (dongle_state == DONGLE_CALIBRATING ||
+			   dongle_state == DONGLE_DISABLED ||
+			   dongle_state == DONGLE_DISCONNECTED) {
+			/* Return 0, so hidraw can get the report. */
+			return 0;
 		}
 
 		dualshock4_parse_report(sc, rd, size);
@@ -1463,7 +1184,7 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report,
 
 	if (sc->defer_initialization) {
 		sc->defer_initialization = 0;
-		sony_schedule_work(sc);
+		sony_schedule_work(sc, SONY_WORKER_STATE);
 	}
 
 	return 0;
@@ -1501,10 +1222,16 @@ static int sony_mapping(struct hid_device *hdev, struct hid_input *hi,
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_mapping(hdev, hi, field, usage, bit, max);
 
+	if (sc->quirks & NAVIGATION_CONTROLLER)
+		return navigation_mapping(hdev, hi, field, usage, bit, max);
+
+	if (sc->quirks & SIXAXIS_CONTROLLER)
+		return sixaxis_mapping(hdev, hi, field, usage, bit, max);
 
 	if (sc->quirks & DUALSHOCK4_CONTROLLER)
 		return ds4_mapping(hdev, hi, field, usage, bit, max);
 
+
 	/* Let hid-core decide for the others */
 	return 0;
 }
@@ -1541,7 +1268,7 @@ static int sony_register_touchpad(struct sony_sc *sc, int touch_count,
 	snprintf(name, name_sz, "%s" DS4_TOUCHPAD_SUFFIX, sc->hdev->name);
 	sc->touchpad->name = name;
 
-	ret = input_mt_init_slots(sc->touchpad, touch_count, 0);
+	ret = input_mt_init_slots(sc->touchpad, touch_count, INPUT_MT_POINTER);
 	if (ret < 0)
 		goto err;
 
@@ -1581,6 +1308,103 @@ static void sony_unregister_touchpad(struct sony_sc *sc)
 	sc->touchpad = NULL;
 }
 
+static int sony_register_sensors(struct sony_sc *sc)
+{
+	size_t name_sz;
+	char *name;
+	int ret;
+	int range;
+
+	sc->sensor_dev = input_allocate_device();
+	if (!sc->sensor_dev)
+		return -ENOMEM;
+
+	input_set_drvdata(sc->sensor_dev, sc);
+	sc->sensor_dev->dev.parent = &sc->hdev->dev;
+	sc->sensor_dev->phys = sc->hdev->phys;
+	sc->sensor_dev->uniq = sc->hdev->uniq;
+	sc->sensor_dev->id.bustype = sc->hdev->bus;
+	sc->sensor_dev->id.vendor = sc->hdev->vendor;
+	sc->sensor_dev->id.product = sc->hdev->product;
+	sc->sensor_dev->id.version = sc->hdev->version;
+
+	/* Append a suffix to the controller name as there are various
+	 * DS4 compatible non-Sony devices with different names.
+	 */
+	name_sz = strlen(sc->hdev->name) + sizeof(SENSOR_SUFFIX);
+	name = kzalloc(name_sz, GFP_KERNEL);
+	if (!name) {
+		ret = -ENOMEM;
+		goto err;
+	}
+	snprintf(name, name_sz, "%s" SENSOR_SUFFIX, sc->hdev->name);
+	sc->sensor_dev->name = name;
+
+	if (sc->quirks & SIXAXIS_CONTROLLER) {
+		/* For the DS3 we only support the accelerometer, which works
+		 * quite well even without calibration. The device also has
+		 * a 1-axis gyro, but it is very difficult to manage from within
+		 * the driver even to get data, the sensor is inaccurate and
+		 * the behavior is very different between hardware revisions.
+		 */
+		input_set_abs_params(sc->sensor_dev, ABS_X, -512, 511, 4, 0);
+		input_set_abs_params(sc->sensor_dev, ABS_Y, -512, 511, 4, 0);
+		input_set_abs_params(sc->sensor_dev, ABS_Z, -512, 511, 4, 0);
+		input_abs_set_res(sc->sensor_dev, ABS_X, SIXAXIS_ACC_RES_PER_G);
+		input_abs_set_res(sc->sensor_dev, ABS_Y, SIXAXIS_ACC_RES_PER_G);
+		input_abs_set_res(sc->sensor_dev, ABS_Z, SIXAXIS_ACC_RES_PER_G);
+	} else if (sc->quirks & DUALSHOCK4_CONTROLLER) {
+		range = DS4_ACC_RES_PER_G*4;
+		input_set_abs_params(sc->sensor_dev, ABS_X, -range, range, 16, 0);
+		input_set_abs_params(sc->sensor_dev, ABS_Y, -range, range, 16, 0);
+		input_set_abs_params(sc->sensor_dev, ABS_Z, -range, range, 16, 0);
+		input_abs_set_res(sc->sensor_dev, ABS_X, DS4_ACC_RES_PER_G);
+		input_abs_set_res(sc->sensor_dev, ABS_Y, DS4_ACC_RES_PER_G);
+		input_abs_set_res(sc->sensor_dev, ABS_Z, DS4_ACC_RES_PER_G);
+
+		range = DS4_GYRO_RES_PER_DEG_S*2048;
+		input_set_abs_params(sc->sensor_dev, ABS_RX, -range, range, 16, 0);
+		input_set_abs_params(sc->sensor_dev, ABS_RY, -range, range, 16, 0);
+		input_set_abs_params(sc->sensor_dev, ABS_RZ, -range, range, 16, 0);
+		input_abs_set_res(sc->sensor_dev, ABS_RX, DS4_GYRO_RES_PER_DEG_S);
+		input_abs_set_res(sc->sensor_dev, ABS_RY, DS4_GYRO_RES_PER_DEG_S);
+		input_abs_set_res(sc->sensor_dev, ABS_RZ, DS4_GYRO_RES_PER_DEG_S);
+
+		__set_bit(EV_MSC, sc->sensor_dev->evbit);
+		__set_bit(MSC_TIMESTAMP, sc->sensor_dev->mscbit);
+	}
+
+	__set_bit(INPUT_PROP_ACCELEROMETER, sc->sensor_dev->propbit);
+
+	ret = input_register_device(sc->sensor_dev);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(sc->sensor_dev->name);
+	sc->sensor_dev->name = NULL;
+
+	input_free_device(sc->sensor_dev);
+	sc->sensor_dev = NULL;
+
+	return ret;
+}
+
+static void sony_unregister_sensors(struct sony_sc *sc)
+{
+	if (!sc->sensor_dev)
+		return;
+
+	kfree(sc->sensor_dev->name);
+	sc->sensor_dev->name = NULL;
+
+	input_unregister_device(sc->sensor_dev);
+	sc->sensor_dev = NULL;
+}
+
+
 /*
  * Sending HID_REQ_GET_REPORT changes the operation mode of the ps3 controller
  * to "operational".  Without this, the ps3 controller will not report any
@@ -1646,26 +1470,176 @@ static int sixaxis_set_operational_bt(struct hid_device *hdev)
 }
 
 /*
- * Requesting feature report 0x02 in Bluetooth mode changes the state of the
- * controller so that it sends full input reports of type 0x11.
+ * Request DS4 calibration data for the motion sensors.
+ * For Bluetooth this also affects the operating mode (see below).
  */
-static int dualshock4_set_operational_bt(struct hid_device *hdev)
+static int dualshock4_get_calibration_data(struct sony_sc *sc)
 {
 	u8 *buf;
 	int ret;
+	short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus;
+	short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus;
+	short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus;
+	short gyro_speed_plus, gyro_speed_minus;
+	short acc_x_plus, acc_x_minus;
+	short acc_y_plus, acc_y_minus;
+	short acc_z_plus, acc_z_minus;
+	int speed_2x;
+	int range_2g;
+
+	/* For Bluetooth we use a different request, which supports CRC.
+	 * Note: in Bluetooth mode feature report 0x02 also changes the state
+	 * of the controller, so that it sends input reports of type 0x11.
+	 */
+	if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE)) {
+		buf = kmalloc(DS4_FEATURE_REPORT_0x02_SIZE, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
 
-	buf = kmalloc(DS4_FEATURE_REPORT_0x02_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+		ret = hid_hw_raw_request(sc->hdev, 0x02, buf,
+					 DS4_FEATURE_REPORT_0x02_SIZE,
+					 HID_FEATURE_REPORT,
+					 HID_REQ_GET_REPORT);
+		if (ret < 0)
+			goto err_stop;
+	} else {
+		u8 bthdr = 0xA3;
+		u32 crc;
+		u32 report_crc;
+		int retries;
 
-	ret = hid_hw_raw_request(hdev, 0x02, buf, DS4_FEATURE_REPORT_0x02_SIZE,
-				HID_FEATURE_REPORT, HID_REQ_GET_REPORT);
+		buf = kmalloc(DS4_FEATURE_REPORT_0x05_SIZE, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
 
-	kfree(buf);
+		for (retries = 0; retries < 3; retries++) {
+			ret = hid_hw_raw_request(sc->hdev, 0x05, buf,
+						 DS4_FEATURE_REPORT_0x05_SIZE,
+						 HID_FEATURE_REPORT,
+						 HID_REQ_GET_REPORT);
+			if (ret < 0)
+				goto err_stop;
+
+			/* CRC check */
+			crc = crc32_le(0xFFFFFFFF, &bthdr, 1);
+			crc = ~crc32_le(crc, buf, DS4_FEATURE_REPORT_0x05_SIZE-4);
+			report_crc = get_unaligned_le32(&buf[DS4_FEATURE_REPORT_0x05_SIZE-4]);
+			if (crc != report_crc) {
+				hid_warn(sc->hdev, "DualShock 4 calibration report's CRC check failed, received crc 0x%0x != 0x%0x\n",
+					report_crc, crc);
+				if (retries < 2) {
+					hid_warn(sc->hdev, "Retrying DualShock 4 get calibration report request\n");
+					continue;
+				} else {
+					ret = -EILSEQ;
+					goto err_stop;
+				}
+			} else {
+				break;
+			}
+		}
+	}
+
+	gyro_pitch_bias  = get_unaligned_le16(&buf[1]);
+	gyro_yaw_bias    = get_unaligned_le16(&buf[3]);
+	gyro_roll_bias   = get_unaligned_le16(&buf[5]);
+	if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
+		gyro_pitch_plus  = get_unaligned_le16(&buf[7]);
+		gyro_pitch_minus = get_unaligned_le16(&buf[9]);
+		gyro_yaw_plus    = get_unaligned_le16(&buf[11]);
+		gyro_yaw_minus   = get_unaligned_le16(&buf[13]);
+		gyro_roll_plus   = get_unaligned_le16(&buf[15]);
+		gyro_roll_minus  = get_unaligned_le16(&buf[17]);
+	} else {
+		/* BT + Dongle */
+		gyro_pitch_plus  = get_unaligned_le16(&buf[7]);
+		gyro_yaw_plus    = get_unaligned_le16(&buf[9]);
+		gyro_roll_plus   = get_unaligned_le16(&buf[11]);
+		gyro_pitch_minus = get_unaligned_le16(&buf[13]);
+		gyro_yaw_minus   = get_unaligned_le16(&buf[15]);
+		gyro_roll_minus  = get_unaligned_le16(&buf[17]);
+	}
+	gyro_speed_plus  = get_unaligned_le16(&buf[19]);
+	gyro_speed_minus = get_unaligned_le16(&buf[21]);
+	acc_x_plus       = get_unaligned_le16(&buf[23]);
+	acc_x_minus      = get_unaligned_le16(&buf[25]);
+	acc_y_plus       = get_unaligned_le16(&buf[27]);
+	acc_y_minus      = get_unaligned_le16(&buf[29]);
+	acc_z_plus       = get_unaligned_le16(&buf[31]);
+	acc_z_minus      = get_unaligned_le16(&buf[33]);
+
+	/* Set gyroscope calibration and normalization parameters.
+	 * Data values will be normalized to 1/DS4_GYRO_RES_PER_DEG_S degree/s.
+	 */
+	speed_2x = (gyro_speed_plus + gyro_speed_minus);
+	sc->ds4_calib_data[0].abs_code = ABS_RX;
+	sc->ds4_calib_data[0].bias = gyro_pitch_bias;
+	sc->ds4_calib_data[0].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
+	sc->ds4_calib_data[0].sens_denom = gyro_pitch_plus - gyro_pitch_minus;
+
+	sc->ds4_calib_data[1].abs_code = ABS_RY;
+	sc->ds4_calib_data[1].bias = gyro_yaw_bias;
+	sc->ds4_calib_data[1].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
+	sc->ds4_calib_data[1].sens_denom = gyro_yaw_plus - gyro_yaw_minus;
+
+	sc->ds4_calib_data[2].abs_code = ABS_RZ;
+	sc->ds4_calib_data[2].bias = gyro_roll_bias;
+	sc->ds4_calib_data[2].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
+	sc->ds4_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
+
+	/* Set accelerometer calibration and normalization parameters.
+	 * Data values will be normalized to 1/DS4_ACC_RES_PER_G G.
+	 */
+	range_2g = acc_x_plus - acc_x_minus;
+	sc->ds4_calib_data[3].abs_code = ABS_X;
+	sc->ds4_calib_data[3].bias = acc_x_plus - range_2g / 2;
+	sc->ds4_calib_data[3].sens_numer = 2*DS4_ACC_RES_PER_G;
+	sc->ds4_calib_data[3].sens_denom = range_2g;
+
+	range_2g = acc_y_plus - acc_y_minus;
+	sc->ds4_calib_data[4].abs_code = ABS_Y;
+	sc->ds4_calib_data[4].bias = acc_y_plus - range_2g / 2;
+	sc->ds4_calib_data[4].sens_numer = 2*DS4_ACC_RES_PER_G;
+	sc->ds4_calib_data[4].sens_denom = range_2g;
+
+	range_2g = acc_z_plus - acc_z_minus;
+	sc->ds4_calib_data[5].abs_code = ABS_Z;
+	sc->ds4_calib_data[5].bias = acc_z_plus - range_2g / 2;
+	sc->ds4_calib_data[5].sens_numer = 2*DS4_ACC_RES_PER_G;
+	sc->ds4_calib_data[5].sens_denom = range_2g;
 
+err_stop:
+	kfree(buf);
 	return ret;
 }
 
+static void dualshock4_calibration_work(struct work_struct *work)
+{
+	struct sony_sc *sc = container_of(work, struct sony_sc, hotplug_worker);
+	unsigned long flags;
+	enum ds4_dongle_state dongle_state;
+	int ret;
+
+	ret = dualshock4_get_calibration_data(sc);
+	if (ret < 0) {
+		/* This call is very unlikely to fail for the dongle. When it
+		 * fails we are probably in a very bad state, so mark the
+		 * dongle as disabled. We will re-enable the dongle if a new
+		 * DS4 hotplug is detect from sony_raw_event as any issues
+		 * are likely resolved then (the dongle is quite stupid).
+		 */
+		hid_err(sc->hdev, "DualShock 4 USB dongle: calibration failed, disabling device\n");
+		dongle_state = DONGLE_DISABLED;
+	} else {
+		hid_info(sc->hdev, "DualShock 4 USB dongle: calibration completed\n");
+		dongle_state = DONGLE_CONNECTED;
+	}
+
+	spin_lock_irqsave(&sc->lock, flags);
+	sc->ds4_dongle_state = dongle_state;
+	spin_unlock_irqrestore(&sc->lock, flags);
+}
+
 static void sixaxis_set_leds_from_id(struct sony_sc *sc)
 {
 	static const u8 sixaxis_leds[10][4] = {
@@ -1696,10 +1670,10 @@ static void dualshock4_set_leds_from_id(struct sony_sc *sc)
 {
 	/* The first 4 color/index entries match what the PS4 assigns */
 	static const u8 color_code[7][3] = {
-			/* Blue   */	{ 0x00, 0x00, 0x01 },
-			/* Red	  */	{ 0x01, 0x00, 0x00 },
-			/* Green  */	{ 0x00, 0x01, 0x00 },
-			/* Pink   */	{ 0x02, 0x00, 0x01 },
+			/* Blue   */	{ 0x00, 0x00, 0x40 },
+			/* Red	  */	{ 0x40, 0x00, 0x00 },
+			/* Green  */	{ 0x00, 0x40, 0x00 },
+			/* Pink   */	{ 0x20, 0x00, 0x20 },
 			/* Orange */	{ 0x02, 0x01, 0x00 },
 			/* Teal   */	{ 0x00, 0x01, 0x01 },
 			/* White  */	{ 0x01, 0x01, 0x01 }
@@ -1740,7 +1714,7 @@ static void buzz_set_leds(struct sony_sc *sc)
 static void sony_set_leds(struct sony_sc *sc)
 {
 	if (!(sc->quirks & BUZZ_CONTROLLER))
-		sony_schedule_work(sc);
+		sony_schedule_work(sc, SONY_WORKER_STATE);
 	else
 		buzz_set_leds(sc);
 }
@@ -1851,7 +1825,7 @@ static int sony_led_blink_set(struct led_classdev *led, unsigned long *delay_on,
 		new_off != drv_data->led_delay_off[n]) {
 		drv_data->led_delay_on[n] = new_on;
 		drv_data->led_delay_off[n] = new_off;
-		sony_schedule_work(drv_data);
+		sony_schedule_work(drv_data, SONY_WORKER_STATE);
 	}
 
 	return 0;
@@ -1964,6 +1938,7 @@ static int sony_leds_init(struct sony_sc *sc)
 		led->name = name;
 		led->brightness = sc->led_state[n];
 		led->max_brightness = max_brightness[n];
+		led->flags = LED_CORE_SUSPENDRESUME;
 		led->brightness_get = sony_led_get_brightness;
 		led->brightness_set = sony_led_set_brightness;
 
@@ -2052,26 +2027,24 @@ static void dualshock4_send_output_report(struct sony_sc *sc)
 	int offset;
 
 	/*
-	 * NOTE: The buf[1] field of the Bluetooth report controls
-	 * the Dualshock 4 reporting rate.
-	 *
-	 * Known values include:
-	 *
-	 * 0x80 - 1000hz (full speed)
-	 * 0xA0 - 31hz
-	 * 0xB0 - 20hz
-	 * 0xD0 - 66hz
+	 * NOTE: The lower 6 bits of buf[1] field of the Bluetooth report
+	 * control the interval at which Dualshock 4 reports data:
+	 * 0x00 - 1ms
+	 * 0x01 - 1ms
+	 * 0x02 - 2ms
+	 * 0x3E - 62ms
+	 * 0x3F - disabled
 	 */
-	if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
+	if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE)) {
 		memset(buf, 0, DS4_OUTPUT_REPORT_0x05_SIZE);
 		buf[0] = 0x05;
-		buf[1] = 0xFF;
+		buf[1] = 0x07; /* blink + LEDs + motor */
 		offset = 4;
 	} else {
 		memset(buf, 0, DS4_OUTPUT_REPORT_0x11_SIZE);
 		buf[0] = 0x11;
-		buf[1] = 0xC0; /* HID + CRC */
-		buf[3] = 0x0F;
+		buf[1] = 0xC0 /* HID + CRC */ | sc->ds4_bt_poll_interval;
+		buf[3] = 0x07; /* blink + LEDs + motor */
 		offset = 6;
 	}
 
@@ -2095,7 +2068,7 @@ static void dualshock4_send_output_report(struct sony_sc *sc)
 	buf[offset++] = sc->led_delay_on[3];
 	buf[offset++] = sc->led_delay_off[3];
 
-	if (sc->quirks & DUALSHOCK4_CONTROLLER_USB)
+	if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE))
 		hid_hw_output_report(hdev, buf, DS4_OUTPUT_REPORT_0x05_SIZE);
 	else {
 		/* CRC generation */
@@ -2152,7 +2125,7 @@ static int sony_allocate_output_report(struct sony_sc *sc)
 	else if (sc->quirks & DUALSHOCK4_CONTROLLER_BT)
 		sc->output_report_dmabuf = kmalloc(DS4_OUTPUT_REPORT_0x11_SIZE,
 						GFP_KERNEL);
-	else if (sc->quirks & DUALSHOCK4_CONTROLLER_USB)
+	else if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE))
 		sc->output_report_dmabuf = kmalloc(DS4_OUTPUT_REPORT_0x05_SIZE,
 						GFP_KERNEL);
 	else if (sc->quirks & MOTION_CONTROLLER)
@@ -2180,7 +2153,7 @@ static int sony_play_effect(struct input_dev *dev, void *data,
 	sc->left = effect->u.rumble.strong_magnitude / 256;
 	sc->right = effect->u.rumble.weak_magnitude / 256;
 
-	sony_schedule_work(sc);
+	sony_schedule_work(sc, SONY_WORKER_STATE);
 	return 0;
 }
 
@@ -2397,7 +2370,7 @@ static int sony_check_add(struct sony_sc *sc)
 			hid_warn(sc->hdev, "UNIQ does not contain a MAC address; duplicate check skipped\n");
 			return 0;
 		}
-	} else if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) {
+	} else if (sc->quirks & (DUALSHOCK4_CONTROLLER_USB | DUALSHOCK4_DONGLE)) {
 		buf = kmalloc(DS4_FEATURE_REPORT_0x81_SIZE, GFP_KERNEL);
 		if (!buf)
 			return -ENOMEM;
@@ -2451,6 +2424,12 @@ static int sony_check_add(struct sony_sc *sc)
 		 */
 		for (n = 0; n < 6; n++)
 			sc->mac_address[5-n] = buf[4+n];
+
+		snprintf(sc->hdev->uniq, sizeof(sc->hdev->uniq),
+			"%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+			sc->mac_address[5], sc->mac_address[4],
+			sc->mac_address[3], sc->mac_address[2],
+			sc->mac_address[1], sc->mac_address[0]);
 	} else {
 		return 0;
 	}
@@ -2501,18 +2480,21 @@ static inline void sony_init_output_report(struct sony_sc *sc,
 {
 	sc->send_output_report = send_output_report;
 
-	if (!sc->worker_initialized)
+	if (!sc->state_worker_initialized)
 		INIT_WORK(&sc->state_worker, sony_state_worker);
 
-	sc->worker_initialized = 1;
+	sc->state_worker_initialized = 1;
 }
 
 static inline void sony_cancel_work_sync(struct sony_sc *sc)
 {
-	if (sc->worker_initialized)
+	if (sc->hotplug_worker_initialized)
+		cancel_work_sync(&sc->hotplug_worker);
+	if (sc->state_worker_initialized)
 		cancel_work_sync(&sc->state_worker);
 }
 
+
 static int sony_input_configured(struct hid_device *hdev,
 					struct hid_input *hidinput)
 {
@@ -2526,14 +2508,17 @@ static int sony_input_configured(struct hid_device *hdev,
 		goto err_stop;
 	}
 
+	ret = append_dev_id = sony_check_add(sc);
+	if (ret < 0)
+		goto err_stop;
+
 	ret = sony_allocate_output_report(sc);
 	if (ret < 0) {
 		hid_err(hdev, "failed to allocate the output report buffer\n");
 		goto err_stop;
 	}
 
-	if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
-			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
+	if (sc->quirks & NAVIGATION_CONTROLLER_USB) {
 		/*
 		 * The Sony Sixaxis does not handle HID Output Reports on the
 		 * Interrupt EP like it could, so we need to force HID Output
@@ -2553,24 +2538,79 @@ static int sony_input_configured(struct hid_device *hdev,
 		hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
 		hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
 		sc->defer_initialization = 1;
+
+		ret = sixaxis_set_operational_usb(hdev);
+		if (ret < 0) {
+			hid_err(hdev, "Failed to set controller into operational mode\n");
+			goto err_stop;
+		}
+
+		sony_init_output_report(sc, sixaxis_send_output_report);
+	} else if (sc->quirks & NAVIGATION_CONTROLLER_BT) {
+		/*
+		 * The Navigation controller wants output reports sent on the ctrl
+		 * endpoint when connected via Bluetooth.
+		 */
+		hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+
+		ret = sixaxis_set_operational_bt(hdev);
+		if (ret < 0) {
+			hid_err(hdev, "Failed to set controller into operational mode\n");
+			goto err_stop;
+		}
+
+		sony_init_output_report(sc, sixaxis_send_output_report);
+	} else if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
+		/*
+		 * The Sony Sixaxis does not handle HID Output Reports on the
+		 * Interrupt EP and the device only becomes active when the
+		 * PS button is pressed. See comment for Navigation controller
+		 * above for more details.
+		 */
+		hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+		hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
+		sc->defer_initialization = 1;
+
 		ret = sixaxis_set_operational_usb(hdev);
+		if (ret < 0) {
+			hid_err(hdev, "Failed to set controller into operational mode\n");
+			goto err_stop;
+		}
+
+		ret = sony_register_sensors(sc);
+		if (ret) {
+			hid_err(sc->hdev,
+			"Unable to initialize motion sensors: %d\n", ret);
+			goto err_stop;
+		}
+
 		sony_init_output_report(sc, sixaxis_send_output_report);
-	} else if ((sc->quirks & SIXAXIS_CONTROLLER_BT) ||
-			(sc->quirks & NAVIGATION_CONTROLLER_BT)) {
+	} else if (sc->quirks & SIXAXIS_CONTROLLER_BT) {
 		/*
 		 * The Sixaxis wants output reports sent on the ctrl endpoint
 		 * when connected via Bluetooth.
 		 */
 		hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+
 		ret = sixaxis_set_operational_bt(hdev);
+		if (ret < 0) {
+			hid_err(hdev, "Failed to set controller into operational mode\n");
+			goto err_stop;
+		}
+
+		ret = sony_register_sensors(sc);
+		if (ret) {
+			hid_err(sc->hdev,
+			"Unable to initialize motion sensors: %d\n", ret);
+			goto err_stop;
+		}
+
 		sony_init_output_report(sc, sixaxis_send_output_report);
 	} else if (sc->quirks & DUALSHOCK4_CONTROLLER) {
-		if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) {
-			ret = dualshock4_set_operational_bt(hdev);
-			if (ret < 0) {
-				hid_err(hdev, "failed to set the Dualshock 4 operational mode\n");
-				goto err_stop;
-			}
+		ret = dualshock4_get_calibration_data(sc);
+		if (ret < 0) {
+			hid_err(hdev, "Failed to get calibration data from Dualshock 4\n");
+			goto err_stop;
 		}
 
 		/*
@@ -2585,6 +2625,28 @@ static int sony_input_configured(struct hid_device *hdev,
 			goto err_stop;
 		}
 
+		ret = sony_register_sensors(sc);
+		if (ret) {
+			hid_err(sc->hdev,
+			"Unable to initialize motion sensors: %d\n", ret);
+			goto err_stop;
+		}
+
+		if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) {
+			sc->ds4_bt_poll_interval = DS4_BT_DEFAULT_POLL_INTERVAL_MS;
+			ret = device_create_file(&sc->hdev->dev, &dev_attr_bt_poll_interval);
+			if (ret)
+				hid_warn(sc->hdev,
+				 "can't create sysfs bt_poll_interval attribute err: %d\n",
+				 ret);
+		}
+
+		if (sc->quirks & DUALSHOCK4_DONGLE) {
+			INIT_WORK(&sc->hotplug_worker, dualshock4_calibration_work);
+			sc->hotplug_worker_initialized = 1;
+			sc->ds4_dongle_state = DONGLE_DISCONNECTED;
+		}
+
 		sony_init_output_report(sc, dualshock4_send_output_report);
 	} else if (sc->quirks & MOTION_CONTROLLER) {
 		sony_init_output_report(sc, motion_send_output_report);
@@ -2592,13 +2654,6 @@ static int sony_input_configured(struct hid_device *hdev,
 		ret = 0;
 	}
 
-	if (ret < 0)
-		goto err_stop;
-
-	ret = append_dev_id = sony_check_add(sc);
-	if (ret < 0)
-		goto err_stop;
-
 	if (sc->quirks & SONY_LED_SUPPORT) {
 		ret = sony_leds_init(sc);
 		if (ret < 0)
@@ -2628,10 +2683,20 @@ static int sony_input_configured(struct hid_device *hdev,
 err_close:
 	hid_hw_close(hdev);
 err_stop:
+	/* Piggy back on the default ds4_bt_ poll_interval to determine
+	 * if we need to remove the file as we don't know for sure if we
+	 * executed that logic.
+	 */
+	if (sc->ds4_bt_poll_interval)
+		device_remove_file(&sc->hdev->dev, &dev_attr_bt_poll_interval);
 	if (sc->quirks & SONY_LED_SUPPORT)
 		sony_leds_remove(sc);
 	if (sc->quirks & SONY_BATTERY_SUPPORT)
 		sony_battery_remove(sc);
+	if (sc->touchpad)
+		sony_unregister_touchpad(sc);
+	if (sc->sensor_dev)
+		sony_unregister_sensors(sc);
 	sony_cancel_work_sync(sc);
 	kfree(sc->output_report_dmabuf);
 	sony_remove_dev_list(sc);
@@ -2673,13 +2738,13 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	else if (sc->quirks & SIXAXIS_CONTROLLER)
 		connect_mask |= HID_CONNECT_HIDDEV_FORCE;
 
-	/* Patch the hw version on DS4 compatible devices, so applications can
+	/* Patch the hw version on DS3/4 compatible devices, so applications can
 	 * distinguish between the default HID mappings and the mappings defined
 	 * by the Linux game controller spec. This is important for the SDL2
 	 * library, which has a game controller database, which uses device ids
 	 * in combination with version as a key.
 	 */
-	if (sc->quirks & DUALSHOCK4_CONTROLLER)
+	if (sc->quirks & (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER))
 		hdev->version |= 0x8000;
 
 	ret = hid_hw_start(hdev, connect_mask);
@@ -2719,6 +2784,12 @@ static void sony_remove(struct hid_device *hdev)
 	if (sc->touchpad)
 		sony_unregister_touchpad(sc);
 
+	if (sc->sensor_dev)
+		sony_unregister_sensors(sc);
+
+	if (sc->quirks & DUALSHOCK4_CONTROLLER_BT)
+		device_remove_file(&sc->hdev->dev, &dev_attr_bt_poll_interval);
+
 	sony_cancel_work_sync(sc);
 
 	kfree(sc->output_report_dmabuf);
@@ -2734,47 +2805,32 @@ static void sony_remove(struct hid_device *hdev)
 
 static int sony_suspend(struct hid_device *hdev, pm_message_t message)
 {
-	/*
-	 * On suspend save the current LED state,
-	 * stop running force-feedback and blank the LEDS.
-	 */
-	if (SONY_LED_SUPPORT || SONY_FF_SUPPORT) {
-		struct sony_sc *sc = hid_get_drvdata(hdev);
-
 #ifdef CONFIG_SONY_FF
-		sc->left = sc->right = 0;
-#endif
 
-		memcpy(sc->resume_led_state, sc->led_state,
-			sizeof(sc->resume_led_state));
-		memset(sc->led_state, 0, sizeof(sc->led_state));
+	/* On suspend stop any running force-feedback events */
+	if (SONY_FF_SUPPORT) {
+		struct sony_sc *sc = hid_get_drvdata(hdev);
 
+		sc->left = sc->right = 0;
 		sony_send_output_report(sc);
 	}
 
+#endif
 	return 0;
 }
 
 static int sony_resume(struct hid_device *hdev)
 {
-	/* Restore the state of controller LEDs on resume */
-	if (SONY_LED_SUPPORT) {
-		struct sony_sc *sc = hid_get_drvdata(hdev);
-
-		memcpy(sc->led_state, sc->resume_led_state,
-			sizeof(sc->led_state));
-
-		/*
-		 * The Sixaxis and navigation controllers on USB need to be
-		 * reinitialized on resume or they won't behave properly.
-		 */
-		if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
-			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
-			sixaxis_set_operational_usb(sc->hdev);
-			sc->defer_initialization = 1;
-		}
+	struct sony_sc *sc = hid_get_drvdata(hdev);
 
-		sony_set_leds(sc);
+	/*
+	 * The Sixaxis and navigation controllers on USB need to be
+	 * reinitialized on resume or they won't behave properly.
+	 */
+	if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
+		(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
+		sixaxis_set_operational_usb(sc->hdev);
+		sc->defer_initialization = 1;
 	}
 
 	return 0;
@@ -2826,7 +2882,7 @@ static const struct hid_device_id sony_devices[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_2),
 		.driver_data = DUALSHOCK4_CONTROLLER_BT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE),
-		.driver_data = DUALSHOCK4_CONTROLLER_USB },
+		.driver_data = DUALSHOCK4_DONGLE },
 	/* Nyko Core Controller for PS3 */
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SINO_LITE, USB_DEVICE_ID_SINO_LITE_CONTROLLER),
 		.driver_data = SIXAXIS_CONTROLLER_USB | SINO_LITE_CONTROLLER },
diff --git a/drivers/hid/hid-uclogic.c b/drivers/hid/hid-uclogic.c
index 1509d7287ff3..e3e6e5c893cc 100644
--- a/drivers/hid/hid-uclogic.c
+++ b/drivers/hid/hid-uclogic.c
@@ -977,6 +977,7 @@ static int uclogic_probe(struct hid_device *hdev,
 		}
 		break;
 	case USB_DEVICE_ID_UGTIZER_TABLET_GP0610:
+	case USB_DEVICE_ID_UGEE_TABLET_EX07S:
 		/* If this is the pen interface */
 		if (intf->cur_altsetting->desc.bInterfaceNumber == 1) {
 			rc = uclogic_tablet_enable(hdev);
@@ -1069,6 +1070,7 @@ static const struct hid_device_id uclogic_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, uclogic_devices);
diff --git a/drivers/hid/hid-xinmo.c b/drivers/hid/hid-xinmo.c
index 7df5227a7e61..9ad7731d2e10 100644
--- a/drivers/hid/hid-xinmo.c
+++ b/drivers/hid/hid-xinmo.c
@@ -46,6 +46,7 @@ static int xinmo_event(struct hid_device *hdev, struct hid_field *field,
 
 static const struct hid_device_id xinmo_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_THT_2P_ARCADE) },
 	{ }
 };
 
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index ea3c3546cef7..8daa8ce64ebb 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -508,66 +508,6 @@ static int i2c_hid_get_report_length(struct hid_report *report)
 		report->device->report_enum[report->type].numbered + 2;
 }
 
-static void i2c_hid_init_report(struct hid_report *report, u8 *buffer,
-	size_t bufsize)
-{
-	struct hid_device *hid = report->device;
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-	unsigned int size, ret_size;
-
-	size = i2c_hid_get_report_length(report);
-	if (i2c_hid_get_report(client,
-			report->type == HID_FEATURE_REPORT ? 0x03 : 0x01,
-			report->id, buffer, size))
-		return;
-
-	i2c_hid_dbg(ihid, "report (len=%d): %*ph\n", size, size, buffer);
-
-	ret_size = buffer[0] | (buffer[1] << 8);
-
-	if (ret_size != size) {
-		dev_err(&client->dev, "error in %s size:%d / ret_size:%d\n",
-			__func__, size, ret_size);
-		return;
-	}
-
-	/* hid->driver_lock is held as we are in probe function,
-	 * we just need to setup the input fields, so using
-	 * hid_report_raw_event is safe. */
-	hid_report_raw_event(hid, report->type, buffer + 2, size - 2, 1);
-}
-
-/*
- * Initialize all reports
- */
-static void i2c_hid_init_reports(struct hid_device *hid)
-{
-	struct hid_report *report;
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-	u8 *inbuf = kzalloc(ihid->bufsize, GFP_KERNEL);
-
-	if (!inbuf) {
-		dev_err(&client->dev, "can not retrieve initial reports\n");
-		return;
-	}
-
-	/*
-	 * The device must be powered on while we fetch initial reports
-	 * from it.
-	 */
-	pm_runtime_get_sync(&client->dev);
-
-	list_for_each_entry(report,
-		&hid->report_enum[HID_FEATURE_REPORT].report_list, list)
-		i2c_hid_init_report(report, inbuf, ihid->bufsize);
-
-	pm_runtime_put(&client->dev);
-
-	kfree(inbuf);
-}
-
 /*
  * Traverse the supplied list of reports and find the longest
  */
@@ -789,9 +729,6 @@ static int i2c_hid_start(struct hid_device *hid)
 			return ret;
 	}
 
-	if (!(hid->quirks & HID_QUIRK_NO_INIT_REPORTS))
-		i2c_hid_init_reports(hid);
-
 	return 0;
 }
 
@@ -994,6 +931,11 @@ static int i2c_hid_of_probe(struct i2c_client *client,
 	}
 	pdata->hid_descriptor_address = val;
 
+	ret = of_property_read_u32(dev->of_node, "post-power-on-delay-ms",
+				   &val);
+	if (!ret)
+		pdata->post_power_delay_ms = val;
+
 	return 0;
 }
 
@@ -1053,6 +995,24 @@ static int i2c_hid_probe(struct i2c_client *client,
 		ihid->pdata = *platform_data;
 	}
 
+	ihid->pdata.supply = devm_regulator_get(&client->dev, "vdd");
+	if (IS_ERR(ihid->pdata.supply)) {
+		ret = PTR_ERR(ihid->pdata.supply);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&client->dev, "Failed to get regulator: %d\n",
+				ret);
+		goto err;
+	}
+
+	ret = regulator_enable(ihid->pdata.supply);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failed to enable regulator: %d\n",
+			ret);
+		goto err;
+	}
+	if (ihid->pdata.post_power_delay_ms)
+		msleep(ihid->pdata.post_power_delay_ms);
+
 	i2c_set_clientdata(client, ihid);
 
 	ihid->client = client;
@@ -1068,7 +1028,7 @@ static int i2c_hid_probe(struct i2c_client *client,
 	 * real computation later. */
 	ret = i2c_hid_alloc_buffers(ihid, HID_MIN_BUFFER_SIZE);
 	if (ret < 0)
-		goto err;
+		goto err_regulator;
 
 	pm_runtime_get_noresume(&client->dev);
 	pm_runtime_set_active(&client->dev);
@@ -1125,6 +1085,9 @@ err_pm:
 	pm_runtime_put_noidle(&client->dev);
 	pm_runtime_disable(&client->dev);
 
+err_regulator:
+	regulator_disable(ihid->pdata.supply);
+
 err:
 	i2c_hid_free_buffers(ihid);
 	kfree(ihid);
@@ -1149,6 +1112,8 @@ static int i2c_hid_remove(struct i2c_client *client)
 	if (ihid->bufsize)
 		i2c_hid_free_buffers(ihid);
 
+	regulator_disable(ihid->pdata.supply);
+
 	kfree(ihid);
 
 	return 0;
@@ -1199,6 +1164,10 @@ static int i2c_hid_suspend(struct device *dev)
 		else
 			hid_warn(hid, "Failed to enable irq wake: %d\n",
 				wake_status);
+	} else {
+		ret = regulator_disable(ihid->pdata.supply);
+		if (ret < 0)
+			hid_warn(hid, "Failed to disable supply: %d\n", ret);
 	}
 
 	return 0;
@@ -1212,7 +1181,13 @@ static int i2c_hid_resume(struct device *dev)
 	struct hid_device *hid = ihid->hid;
 	int wake_status;
 
-	if (device_may_wakeup(&client->dev) && ihid->irq_wake_enabled) {
+	if (!device_may_wakeup(&client->dev)) {
+		ret = regulator_enable(ihid->pdata.supply);
+		if (ret < 0)
+			hid_warn(hid, "Failed to enable supply: %d\n", ret);
+		if (ihid->pdata.post_power_delay_ms)
+			msleep(ihid->pdata.post_power_delay_ms);
+	} else if (ihid->irq_wake_enabled) {
 		wake_status = disable_irq_wake(client->irq);
 		if (!wake_status)
 			ihid->irq_wake_enabled = false;
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 961bc6fdd2d9..83772fa7d92a 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -52,6 +52,10 @@ static unsigned int hid_mousepoll_interval;
 module_param_named(mousepoll, hid_mousepoll_interval, uint, 0644);
 MODULE_PARM_DESC(mousepoll, "Polling interval of mice");
 
+static unsigned int hid_jspoll_interval;
+module_param_named(jspoll, hid_jspoll_interval, uint, 0644);
+MODULE_PARM_DESC(jspoll, "Polling interval of joysticks");
+
 static unsigned int ignoreled;
 module_param_named(ignoreled, ignoreled, uint, 0644);
 MODULE_PARM_DESC(ignoreled, "Autosuspend with active leds");
@@ -753,11 +757,9 @@ void usbhid_init_reports(struct hid_device *hid)
 	struct hid_report_enum *report_enum;
 	int err, ret;
 
-	if (!(hid->quirks & HID_QUIRK_NO_INIT_INPUT_REPORTS)) {
-		report_enum = &hid->report_enum[HID_INPUT_REPORT];
-		list_for_each_entry(report, &report_enum->report_list, list)
-			usbhid_submit_report(hid, report, USB_DIR_IN);
-	}
+	report_enum = &hid->report_enum[HID_INPUT_REPORT];
+	list_for_each_entry(report, &report_enum->report_list, list)
+		usbhid_submit_report(hid, report, USB_DIR_IN);
 
 	report_enum = &hid->report_enum[HID_FEATURE_REPORT];
 	list_for_each_entry(report, &report_enum->report_list, list)
@@ -1004,10 +1006,9 @@ static int usbhid_parse(struct hid_device *hid)
 		return -EINVAL;
 	}
 
-	if (!(rdesc = kmalloc(rsize, GFP_KERNEL))) {
-		dbg_hid("couldn't allocate rdesc memory\n");
+	rdesc = kmalloc(rsize, GFP_KERNEL);
+	if (!rdesc)
 		return -ENOMEM;
-	}
 
 	hid_set_idle(dev, interface->desc.bInterfaceNumber, 0, 0);
 
@@ -1077,13 +1078,21 @@ static int usbhid_start(struct hid_device *hid)
 		if (hid->quirks & HID_QUIRK_FULLSPEED_INTERVAL &&
 		    dev->speed == USB_SPEED_HIGH) {
 			interval = fls(endpoint->bInterval*8);
-			printk(KERN_INFO "%s: Fixing fullspeed to highspeed interval: %d -> %d\n",
-			       hid->name, endpoint->bInterval, interval);
+			pr_info("%s: Fixing fullspeed to highspeed interval: %d -> %d\n",
+				hid->name, endpoint->bInterval, interval);
 		}
 
-		/* Change the polling interval of mice. */
-		if (hid->collection->usage == HID_GD_MOUSE && hid_mousepoll_interval > 0)
-			interval = hid_mousepoll_interval;
+		/* Change the polling interval of mice and joysticks. */
+		switch (hid->collection->usage) {
+		case HID_GD_MOUSE:
+			if (hid_mousepoll_interval > 0)
+				interval = hid_mousepoll_interval;
+			break;
+		case HID_GD_JOYSTICK:
+			if (hid_jspoll_interval > 0)
+				interval = hid_jspoll_interval;
+			break;
+		}
 
 		ret = -ENOMEM;
 		if (usb_endpoint_dir_in(endpoint)) {
@@ -1120,9 +1129,6 @@ static int usbhid_start(struct hid_device *hid)
 	usbhid->urbctrl->transfer_dma = usbhid->ctrlbuf_dma;
 	usbhid->urbctrl->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 
-	if (!(hid->quirks & HID_QUIRK_NO_INIT_REPORTS))
-		usbhid_init_reports(hid);
-
 	set_bit(HID_STARTED, &usbhid->iofl);
 
 	if (hid->quirks & HID_QUIRK_ALWAYS_POLL) {
@@ -1456,10 +1462,9 @@ static int hid_post_reset(struct usb_interface *intf)
 	 * the size of the HID report descriptor has not changed.
 	 */
 	rdesc = kmalloc(hid->dev_rsize, GFP_KERNEL);
-	if (!rdesc) {
-		dbg_hid("couldn't allocate rdesc memory (post_reset)\n");
+	if (!rdesc)
 		return -ENOMEM;
-	}
+
 	status = hid_get_class_descriptor(dev,
 				interface->desc.bInterfaceNumber,
 				HID_DT_REPORT, rdesc, hid->dev_rsize);
@@ -1637,7 +1642,7 @@ static int __init hid_init(void)
 	retval = usb_register(&hid_driver);
 	if (retval)
 		goto usb_register_fail;
-	printk(KERN_INFO KBUILD_MODNAME ": " DRIVER_DESC "\n");
+	pr_info(KBUILD_MODNAME ": " DRIVER_DESC "\n");
 
 	return 0;
 usb_register_fail:
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index d6847a664446..6316498b7812 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -65,6 +65,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS692, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS1758, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
@@ -80,6 +81,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_STRAFE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB_RAPIDFIRE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT },
@@ -158,10 +162,11 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096, HID_QUIRK_NO_INIT_INPUT_REPORTS },
+	{ USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MULTIPLE_1781, USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_2NES2SNES, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_4NES4SNES, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_INNOMEDIA, USB_DEVICE_ID_INNEX_GENESIS_ATARI, HID_QUIRK_MULTI_INPUT },
 
 	{ 0, 0 }
 };
@@ -237,10 +242,8 @@ static int usbhid_modify_dquirk(const u16 idVendor, const u16 idProduct,
 	}
 
 	q_new = kmalloc(sizeof(struct quirks_list_struct), GFP_KERNEL);
-	if (!q_new) {
-		dbg_hid("Could not allocate quirks_list_struct\n");
+	if (!q_new)
 		return -ENOMEM;
-	}
 
 	q_new->hid_bl_item.idVendor = idVendor;
 	q_new->hid_bl_item.idProduct = idProduct;
@@ -306,10 +309,9 @@ int usbhid_quirks_init(char **quirks_param)
 				&idVendor, &idProduct, &quirks);
 
 		if (m != 3 ||
-				usbhid_modify_dquirk(idVendor, idProduct, quirks) != 0) {
-			printk(KERN_WARNING
-					"Could not parse HID quirk module param %s\n",
-					quirks_param[n]);
+		    usbhid_modify_dquirk(idVendor, idProduct, quirks) != 0) {
+			pr_warn("Could not parse HID quirk module param %s\n",
+				quirks_param[n]);
 		}
 	}
 
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 774bd701dae0..0e06368d1fbb 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -47,16 +47,6 @@
 #endif
 #define HIDDEV_BUFFER_SIZE	2048
 
-struct hiddev {
-	int exist;
-	int open;
-	struct mutex existancelock;
-	wait_queue_head_t wait;
-	struct hid_device *hid;
-	struct list_head list;
-	spinlock_t list_lock;
-};
-
 struct hiddev_list {
 	struct hiddev_usage_ref buffer[HIDDEV_BUFFER_SIZE];
 	int head;
@@ -690,6 +680,7 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case HIDIOCINITREPORT:
 		usbhid_init_reports(hid);
+		hiddev->initialized = true;
 		r = 0;
 		break;
 
@@ -791,6 +782,10 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case HIDIOCGUSAGES:
 	case HIDIOCSUSAGES:
 	case HIDIOCGCOLLECTIONINDEX:
+		if (!hiddev->initialized) {
+			usbhid_init_reports(hid);
+			hiddev->initialized = true;
+		}
 		r = hiddev_ioctl_usage(hiddev, cmd, user_arg);
 		break;
 
@@ -911,6 +906,15 @@ int hiddev_connect(struct hid_device *hid, unsigned int force)
 		kfree(hiddev);
 		return -1;
 	}
+
+	/*
+	 * If HID_QUIRK_NO_INIT_REPORTS is set, make sure we don't initialize
+	 * the reports.
+	 */
+	hiddev->initialized = hid->quirks & HID_QUIRK_NO_INIT_REPORTS;
+
+	hiddev->minor = usbhid->intf->minor;
+
 	return 0;
 }
 
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index 38ee2125412f..c7b9ab1907d8 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -110,6 +110,7 @@ enum wacom_worker {
 	WACOM_WORKER_WIRELESS,
 	WACOM_WORKER_BATTERY,
 	WACOM_WORKER_REMOTE,
+	WACOM_WORKER_MODE_CHANGE,
 };
 
 struct wacom;
@@ -167,6 +168,7 @@ struct wacom {
 	struct work_struct remote_work;
 	struct delayed_work init_work;
 	struct wacom_remote *remote;
+	struct work_struct mode_change_work;
 	bool generic_has_leds;
 	struct wacom_leds {
 		struct wacom_group_leds *groups;
@@ -196,6 +198,9 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac,
 	case WACOM_WORKER_REMOTE:
 		schedule_work(&wacom->remote_work);
 		break;
+	case WACOM_WORKER_MODE_CHANGE:
+		schedule_work(&wacom->mode_change_work);
+		break;
 	}
 }
 
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index be8f7e2a026f..0022c0dac88a 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -325,6 +325,13 @@ static void wacom_post_parse_hid(struct hid_device *hdev,
 
 	if (features->type == HID_GENERIC) {
 		/* Any last-minute generic device setup */
+		if (wacom_wac->has_mode_change) {
+			if (wacom_wac->is_direct_mode)
+				features->device_type |= WACOM_DEVICETYPE_DIRECT;
+			else
+				features->device_type &= ~WACOM_DEVICETYPE_DIRECT;
+		}
+
 		if (features->touch_max > 1) {
 			if (features->device_type & WACOM_DEVICETYPE_DIRECT)
 				input_mt_init_slots(wacom_wac->touch_input,
@@ -2093,8 +2100,10 @@ static void wacom_set_shared_values(struct wacom_wac *wacom_wac)
 		wacom_wac->shared->touch_input = wacom_wac->touch_input;
 	}
 
-	if (wacom_wac->has_mute_touch_switch)
+	if (wacom_wac->has_mute_touch_switch) {
 		wacom_wac->shared->has_mute_touch_switch = true;
+		wacom_wac->shared->is_touch_on = true;
+	}
 
 	if (wacom_wac->shared->has_mute_touch_switch &&
 	    wacom_wac->shared->touch_input) {
@@ -2165,6 +2174,14 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 
 	wacom_update_name(wacom, wireless ? " (WL)" : "");
 
+	/* pen only Bamboo neither support touch nor pad */
+	if ((features->type == BAMBOO_PEN) &&
+	    ((features->device_type & WACOM_DEVICETYPE_TOUCH) ||
+	    (features->device_type & WACOM_DEVICETYPE_PAD))) {
+		error = -ENODEV;
+		goto fail;
+	}
+
 	error = wacom_add_shared_data(hdev);
 	if (error)
 		goto fail;
@@ -2208,14 +2225,8 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 	/* touch only Bamboo doesn't support pen */
 	if ((features->type == BAMBOO_TOUCH) &&
 	    (features->device_type & WACOM_DEVICETYPE_PEN)) {
-		error = -ENODEV;
-		goto fail_quirks;
-	}
-
-	/* pen only Bamboo neither support touch nor pad */
-	if ((features->type == BAMBOO_PEN) &&
-	    ((features->device_type & WACOM_DEVICETYPE_TOUCH) ||
-	    (features->device_type & WACOM_DEVICETYPE_PAD))) {
+		cancel_delayed_work_sync(&wacom->init_work);
+		_wacom_query_tablet_data(wacom);
 		error = -ENODEV;
 		goto fail_quirks;
 	}
@@ -2488,6 +2499,46 @@ static void wacom_remote_work(struct work_struct *work)
 	}
 }
 
+static void wacom_mode_change_work(struct work_struct *work)
+{
+	struct wacom *wacom = container_of(work, struct wacom, mode_change_work);
+	struct wacom_shared *shared = wacom->wacom_wac.shared;
+	struct wacom *wacom1 = NULL;
+	struct wacom *wacom2 = NULL;
+	bool is_direct = wacom->wacom_wac.is_direct_mode;
+	int error = 0;
+
+	if (shared->pen) {
+		wacom1 = hid_get_drvdata(shared->pen);
+		wacom_release_resources(wacom1);
+		hid_hw_stop(wacom1->hdev);
+		wacom1->wacom_wac.has_mode_change = true;
+		wacom1->wacom_wac.is_direct_mode = is_direct;
+	}
+
+	if (shared->touch) {
+		wacom2 = hid_get_drvdata(shared->touch);
+		wacom_release_resources(wacom2);
+		hid_hw_stop(wacom2->hdev);
+		wacom2->wacom_wac.has_mode_change = true;
+		wacom2->wacom_wac.is_direct_mode = is_direct;
+	}
+
+	if (wacom1) {
+		error = wacom_parse_and_register(wacom1, false);
+		if (error)
+			return;
+	}
+
+	if (wacom2) {
+		error = wacom_parse_and_register(wacom2, false);
+		if (error)
+			return;
+	}
+
+	return;
+}
+
 static int wacom_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
@@ -2532,6 +2583,7 @@ static int wacom_probe(struct hid_device *hdev,
 	INIT_WORK(&wacom->wireless_work, wacom_wireless_work);
 	INIT_WORK(&wacom->battery_work, wacom_battery_work);
 	INIT_WORK(&wacom->remote_work, wacom_remote_work);
+	INIT_WORK(&wacom->mode_change_work, wacom_mode_change_work);
 
 	/* ask for the report descriptor to be loaded by HID */
 	error = hid_parse(hdev);
@@ -2574,12 +2626,15 @@ static void wacom_remove(struct hid_device *hdev)
 	cancel_work_sync(&wacom->wireless_work);
 	cancel_work_sync(&wacom->battery_work);
 	cancel_work_sync(&wacom->remote_work);
+	cancel_work_sync(&wacom->mode_change_work);
 	if (hdev->bus == BUS_BLUETOOTH)
 		device_remove_file(&hdev->dev, &dev_attr_speed);
 
 	/* make sure we don't trigger the LEDs */
 	wacom_led_groups_release(wacom);
-	wacom_release_resources(wacom);
+
+	if (wacom->wacom_wac.features.type != REMOTE)
+		wacom_release_resources(wacom);
 
 	hid_set_drvdata(hdev, NULL);
 }
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 4aa3de9f1163..4b225fb19a16 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -773,131 +773,6 @@ static int wacom_intuos_inout(struct wacom_wac *wacom)
 	return 0;
 }
 
-static int wacom_remote_irq(struct wacom_wac *wacom_wac, size_t len)
-{
-	unsigned char *data = wacom_wac->data;
-	struct input_dev *input;
-	struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
-	struct wacom_remote *remote = wacom->remote;
-	int bat_charging, bat_percent, touch_ring_mode;
-	__u32 serial;
-	int i, index = -1;
-	unsigned long flags;
-
-	if (data[0] != WACOM_REPORT_REMOTE) {
-		hid_dbg(wacom->hdev, "%s: received unknown report #%d",
-			__func__, data[0]);
-		return 0;
-	}
-
-	serial = data[3] + (data[4] << 8) + (data[5] << 16);
-	wacom_wac->id[0] = PAD_DEVICE_ID;
-
-	spin_lock_irqsave(&remote->remote_lock, flags);
-
-	for (i = 0; i < WACOM_MAX_REMOTES; i++) {
-		if (remote->remotes[i].serial == serial) {
-			index = i;
-			break;
-		}
-	}
-
-	if (index < 0 || !remote->remotes[index].registered)
-		goto out;
-
-	input = remote->remotes[index].input;
-
-	input_report_key(input, BTN_0, (data[9] & 0x01));
-	input_report_key(input, BTN_1, (data[9] & 0x02));
-	input_report_key(input, BTN_2, (data[9] & 0x04));
-	input_report_key(input, BTN_3, (data[9] & 0x08));
-	input_report_key(input, BTN_4, (data[9] & 0x10));
-	input_report_key(input, BTN_5, (data[9] & 0x20));
-	input_report_key(input, BTN_6, (data[9] & 0x40));
-	input_report_key(input, BTN_7, (data[9] & 0x80));
-
-	input_report_key(input, BTN_8, (data[10] & 0x01));
-	input_report_key(input, BTN_9, (data[10] & 0x02));
-	input_report_key(input, BTN_A, (data[10] & 0x04));
-	input_report_key(input, BTN_B, (data[10] & 0x08));
-	input_report_key(input, BTN_C, (data[10] & 0x10));
-	input_report_key(input, BTN_X, (data[10] & 0x20));
-	input_report_key(input, BTN_Y, (data[10] & 0x40));
-	input_report_key(input, BTN_Z, (data[10] & 0x80));
-
-	input_report_key(input, BTN_BASE, (data[11] & 0x01));
-	input_report_key(input, BTN_BASE2, (data[11] & 0x02));
-
-	if (data[12] & 0x80)
-		input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f));
-	else
-		input_report_abs(input, ABS_WHEEL, 0);
-
-	bat_percent = data[7] & 0x7f;
-	bat_charging = !!(data[7] & 0x80);
-
-	if (data[9] | data[10] | (data[11] & 0x03) | data[12])
-		input_report_abs(input, ABS_MISC, PAD_DEVICE_ID);
-	else
-		input_report_abs(input, ABS_MISC, 0);
-
-	input_event(input, EV_MSC, MSC_SERIAL, serial);
-
-	input_sync(input);
-
-	/*Which mode select (LED light) is currently on?*/
-	touch_ring_mode = (data[11] & 0xC0) >> 6;
-
-	for (i = 0; i < WACOM_MAX_REMOTES; i++) {
-		if (remote->remotes[i].serial == serial)
-			wacom->led.groups[i].select = touch_ring_mode;
-	}
-
-	__wacom_notify_battery(&remote->remotes[index].battery, bat_percent,
-				bat_charging, 1, bat_charging);
-
-out:
-	spin_unlock_irqrestore(&remote->remote_lock, flags);
-	return 0;
-}
-
-static void wacom_remote_status_irq(struct wacom_wac *wacom_wac, size_t len)
-{
-	struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
-	unsigned char *data = wacom_wac->data;
-	struct wacom_remote *remote = wacom->remote;
-	struct wacom_remote_data remote_data;
-	unsigned long flags;
-	int i, ret;
-
-	if (data[0] != WACOM_REPORT_DEVICE_LIST)
-		return;
-
-	memset(&remote_data, 0, sizeof(struct wacom_remote_data));
-
-	for (i = 0; i < WACOM_MAX_REMOTES; i++) {
-		int j = i * 6;
-		int serial = (data[j+6] << 16) + (data[j+5] << 8) + data[j+4];
-		bool connected = data[j+2];
-
-		remote_data.remote[i].serial = serial;
-		remote_data.remote[i].connected = connected;
-	}
-
-	spin_lock_irqsave(&remote->remote_lock, flags);
-
-	ret = kfifo_in(&remote->remote_fifo, &remote_data, sizeof(remote_data));
-	if (ret != sizeof(remote_data)) {
-		spin_unlock_irqrestore(&remote->remote_lock, flags);
-		hid_err(wacom->hdev, "Can't queue Remote status event.\n");
-		return;
-	}
-
-	spin_unlock_irqrestore(&remote->remote_lock, flags);
-
-	wacom_schedule_work(wacom_wac, WACOM_WORKER_REMOTE);
-}
-
 static inline bool report_touch_events(struct wacom_wac *wacom)
 {
 	return (touch_arbitration ? !wacom->shared->stylus_in_proximity : 1);
@@ -1116,6 +991,131 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 	return 0;
 }
 
+static int wacom_remote_irq(struct wacom_wac *wacom_wac, size_t len)
+{
+	unsigned char *data = wacom_wac->data;
+	struct input_dev *input;
+	struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
+	struct wacom_remote *remote = wacom->remote;
+	int bat_charging, bat_percent, touch_ring_mode;
+	__u32 serial;
+	int i, index = -1;
+	unsigned long flags;
+
+	if (data[0] != WACOM_REPORT_REMOTE) {
+		hid_dbg(wacom->hdev, "%s: received unknown report #%d",
+			__func__, data[0]);
+		return 0;
+	}
+
+	serial = data[3] + (data[4] << 8) + (data[5] << 16);
+	wacom_wac->id[0] = PAD_DEVICE_ID;
+
+	spin_lock_irqsave(&remote->remote_lock, flags);
+
+	for (i = 0; i < WACOM_MAX_REMOTES; i++) {
+		if (remote->remotes[i].serial == serial) {
+			index = i;
+			break;
+		}
+	}
+
+	if (index < 0 || !remote->remotes[index].registered)
+		goto out;
+
+	input = remote->remotes[index].input;
+
+	input_report_key(input, BTN_0, (data[9] & 0x01));
+	input_report_key(input, BTN_1, (data[9] & 0x02));
+	input_report_key(input, BTN_2, (data[9] & 0x04));
+	input_report_key(input, BTN_3, (data[9] & 0x08));
+	input_report_key(input, BTN_4, (data[9] & 0x10));
+	input_report_key(input, BTN_5, (data[9] & 0x20));
+	input_report_key(input, BTN_6, (data[9] & 0x40));
+	input_report_key(input, BTN_7, (data[9] & 0x80));
+
+	input_report_key(input, BTN_8, (data[10] & 0x01));
+	input_report_key(input, BTN_9, (data[10] & 0x02));
+	input_report_key(input, BTN_A, (data[10] & 0x04));
+	input_report_key(input, BTN_B, (data[10] & 0x08));
+	input_report_key(input, BTN_C, (data[10] & 0x10));
+	input_report_key(input, BTN_X, (data[10] & 0x20));
+	input_report_key(input, BTN_Y, (data[10] & 0x40));
+	input_report_key(input, BTN_Z, (data[10] & 0x80));
+
+	input_report_key(input, BTN_BASE, (data[11] & 0x01));
+	input_report_key(input, BTN_BASE2, (data[11] & 0x02));
+
+	if (data[12] & 0x80)
+		input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f));
+	else
+		input_report_abs(input, ABS_WHEEL, 0);
+
+	bat_percent = data[7] & 0x7f;
+	bat_charging = !!(data[7] & 0x80);
+
+	if (data[9] | data[10] | (data[11] & 0x03) | data[12])
+		input_report_abs(input, ABS_MISC, PAD_DEVICE_ID);
+	else
+		input_report_abs(input, ABS_MISC, 0);
+
+	input_event(input, EV_MSC, MSC_SERIAL, serial);
+
+	input_sync(input);
+
+	/*Which mode select (LED light) is currently on?*/
+	touch_ring_mode = (data[11] & 0xC0) >> 6;
+
+	for (i = 0; i < WACOM_MAX_REMOTES; i++) {
+		if (remote->remotes[i].serial == serial)
+			wacom->led.groups[i].select = touch_ring_mode;
+	}
+
+	__wacom_notify_battery(&remote->remotes[index].battery, bat_percent,
+				bat_charging, 1, bat_charging);
+
+out:
+	spin_unlock_irqrestore(&remote->remote_lock, flags);
+	return 0;
+}
+
+static void wacom_remote_status_irq(struct wacom_wac *wacom_wac, size_t len)
+{
+	struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
+	unsigned char *data = wacom_wac->data;
+	struct wacom_remote *remote = wacom->remote;
+	struct wacom_remote_data remote_data;
+	unsigned long flags;
+	int i, ret;
+
+	if (data[0] != WACOM_REPORT_DEVICE_LIST)
+		return;
+
+	memset(&remote_data, 0, sizeof(struct wacom_remote_data));
+
+	for (i = 0; i < WACOM_MAX_REMOTES; i++) {
+		int j = i * 6;
+		int serial = (data[j+6] << 16) + (data[j+5] << 8) + data[j+4];
+		bool connected = data[j+2];
+
+		remote_data.remote[i].serial = serial;
+		remote_data.remote[i].connected = connected;
+	}
+
+	spin_lock_irqsave(&remote->remote_lock, flags);
+
+	ret = kfifo_in(&remote->remote_fifo, &remote_data, sizeof(remote_data));
+	if (ret != sizeof(remote_data)) {
+		spin_unlock_irqrestore(&remote->remote_lock, flags);
+		hid_err(wacom->hdev, "Can't queue Remote status event.\n");
+		return;
+	}
+
+	spin_unlock_irqrestore(&remote->remote_lock, flags);
+
+	wacom_schedule_work(wacom_wac, WACOM_WORKER_REMOTE);
+}
+
 static int int_dist(int x1, int y1, int x2, int y2)
 {
 	int x = x2 - x1;
@@ -1739,6 +1739,7 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
 	case WACOM_HID_WD_TOUCHONOFF:
+	case WACOM_HID_WD_MUTE_DEVICE:
 		/*
 		 * This usage, which is used to mute touch events, comes
 		 * from the pad packet, but is reported on the touch
@@ -1768,6 +1769,26 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0);
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
+	case WACOM_HID_WD_BUTTONCONFIG:
+		wacom_map_usage(input, usage, field, EV_KEY, KEY_BUTTONCONFIG, 0);
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+		break;
+	case WACOM_HID_WD_ONSCREEN_KEYBOARD:
+		wacom_map_usage(input, usage, field, EV_KEY, KEY_ONSCREEN_KEYBOARD, 0);
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+		break;
+	case WACOM_HID_WD_CONTROLPANEL:
+		wacom_map_usage(input, usage, field, EV_KEY, KEY_CONTROLPANEL, 0);
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+		break;
+	case WACOM_HID_WD_MODE_CHANGE:
+		/* do not overwrite previous data */
+		if (!wacom_wac->has_mode_change) {
+			wacom_wac->has_mode_change = true;
+			wacom_wac->is_direct_mode = true;
+		}
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+		break;
 	}
 
 	switch (equivalent_usage & 0xfffffff0) {
@@ -1811,12 +1832,13 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 	struct wacom_features *features = &wacom_wac->features;
 	unsigned equivalent_usage = wacom_equivalent_usage(usage->hid);
 	int i;
+	bool is_touch_on = value;
 
 	/*
 	 * Avoid reporting this event and setting inrange_state if this usage
 	 * hasn't been mapped.
 	 */
-	if (!usage->type)
+	if (!usage->type && equivalent_usage != WACOM_HID_WD_MODE_CHANGE)
 		return;
 
 	if (wacom_equivalent_usage(field->physical) == HID_DG_TABLETFUNCTIONKEY) {
@@ -1830,14 +1852,28 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 			input_event(input, usage->type, usage->code, 0);
 		break;
 
+	case WACOM_HID_WD_MUTE_DEVICE:
+		if (wacom_wac->shared->touch_input && value) {
+			wacom_wac->shared->is_touch_on = !wacom_wac->shared->is_touch_on;
+			is_touch_on = wacom_wac->shared->is_touch_on;
+		}
+
+		/* fall through*/
 	case WACOM_HID_WD_TOUCHONOFF:
 		if (wacom_wac->shared->touch_input) {
 			input_report_switch(wacom_wac->shared->touch_input,
-					    SW_MUTE_DEVICE, !value);
+					    SW_MUTE_DEVICE, !is_touch_on);
 			input_sync(wacom_wac->shared->touch_input);
 		}
 		break;
 
+	case WACOM_HID_WD_MODE_CHANGE:
+		if (wacom_wac->is_direct_mode != value) {
+			wacom_wac->is_direct_mode = value;
+			wacom_schedule_work(&wacom->wacom_wac, WACOM_WORKER_MODE_CHANGE);
+		}
+		break;
+
 	case WACOM_HID_WD_BUTTONCENTER:
 		for (i = 0; i < wacom->led.count; i++)
 			wacom_update_led(wacom, features->numbered_buttons,
@@ -1845,6 +1881,8 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 		 /* fall through*/
 	default:
 		input_event(input, usage->type, usage->code, value);
+		if (value)
+			wacom_wac->hid_data.pad_input_event_flag = true;
 		break;
 	}
 }
@@ -1885,9 +1923,12 @@ static void wacom_wac_pad_report(struct hid_device *hdev,
 	bool active = wacom_wac->hid_data.inrange_state != 0;
 
 	/* report prox for expresskey events */
-	if (wacom_equivalent_usage(report->field[0]->physical) == HID_DG_TABLETFUNCTIONKEY) {
+	if ((wacom_equivalent_usage(report->field[0]->physical) == HID_DG_TABLETFUNCTIONKEY) &&
+	    wacom_wac->hid_data.pad_input_event_flag) {
 		input_event(input, EV_ABS, ABS_MISC, active ? PAD_DEVICE_ID : 0);
 		input_sync(input);
+		if (!active)
+			wacom_wac->hid_data.pad_input_event_flag = false;
 	}
 
 }
@@ -1959,8 +2000,10 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
 		input_set_capability(input, EV_KEY, BTN_TOOL_BRUSH);
 		input_set_capability(input, EV_KEY, BTN_TOOL_PENCIL);
 		input_set_capability(input, EV_KEY, BTN_TOOL_AIRBRUSH);
-		input_set_capability(input, EV_KEY, BTN_TOOL_MOUSE);
-		input_set_capability(input, EV_KEY, BTN_TOOL_LENS);
+		if (!(features->device_type & WACOM_DEVICETYPE_DIRECT)) {
+			input_set_capability(input, EV_KEY, BTN_TOOL_MOUSE);
+			input_set_capability(input, EV_KEY, BTN_TOOL_LENS);
+		}
 		break;
 	case WACOM_HID_WD_FINGERWHEEL:
 		wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0);
@@ -2004,7 +2047,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 		return;
 	case HID_DG_TOOLSERIALNUMBER:
 		wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL);
-		wacom_wac->serial[0] |= value;
+		wacom_wac->serial[0] |= (__u32)value;
 		return;
 	case WACOM_HID_WD_SENSE:
 		wacom_wac->hid_data.sense_state = value;
@@ -2174,6 +2217,16 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev,
 		wacom_wac->hid_data.cc_index = field->index;
 		wacom_wac->hid_data.cc_value_index = usage->usage_index;
 		break;
+	case HID_DG_CONTACTID:
+		if ((field->logical_maximum - field->logical_minimum) < touch_max) {
+			/*
+			 * The HID descriptor for G11 sensors leaves logical
+			 * maximum set to '1' despite it being a multitouch
+			 * device. Override to a sensible number.
+			 */
+			field->logical_maximum = 255;
+		}
+		break;
 	}
 }
 
@@ -2185,6 +2238,13 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac,
 	bool prox = hid_data->tipswitch &&
 		    report_touch_events(wacom_wac);
 
+	if (wacom_wac->shared->has_mute_touch_switch &&
+	    !wacom_wac->shared->is_touch_on) {
+		if (!wacom_wac->shared->touch_down)
+			return;
+		prox = 0;
+	}
+
 	wacom_wac->hid_data.num_received++;
 	if (wacom_wac->hid_data.num_received > wacom_wac->hid_data.num_expected)
 		return;
@@ -4115,7 +4175,7 @@ static const struct wacom_features wacom_features_0x300 =
 	  BAMBOO_PEN, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x301 =
 	{ "Wacom Bamboo One M", 21648, 13530, 1023, 31,
-	  BAMBOO_PT, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+	  BAMBOO_PEN, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x302 =
 	{ "Wacom Intuos PT S", 15200, 9500, 1023, 31,
 	  INTUOSHT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, .touch_max = 16,
@@ -4197,10 +4257,10 @@ static const struct wacom_features wacom_features_0x343 =
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
 static const struct wacom_features wacom_features_0x360 =
 	{ "Wacom Intuos Pro M", 44800, 29600, 8191, 63,
-	  INTUOSP2_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 9, .touch_max = 10 };
+	  INTUOSP2_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 9, .touch_max = 10 };
 static const struct wacom_features wacom_features_0x361 =
 	{ "Wacom Intuos Pro L", 62200, 43200, 8191, 63,
-	  INTUOSP2_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 9, .touch_max = 10 };
+	  INTUOSP2_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 9, .touch_max = 10 };
 
 static const struct wacom_features wacom_features_HID_ANY_ID =
 	{ "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID };
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 857ccee16f38..570d29582b82 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -120,6 +120,11 @@
 #define WACOM_HID_WD_BATTERY_LEVEL      (WACOM_HID_UP_WACOMDIGITIZER | 0x043b)
 #define WACOM_HID_WD_EXPRESSKEY00       (WACOM_HID_UP_WACOMDIGITIZER | 0x0910)
 #define WACOM_HID_WD_EXPRESSKEYCAP00    (WACOM_HID_UP_WACOMDIGITIZER | 0x0950)
+#define WACOM_HID_WD_MODE_CHANGE        (WACOM_HID_UP_WACOMDIGITIZER | 0x0980)
+#define WACOM_HID_WD_MUTE_DEVICE        (WACOM_HID_UP_WACOMDIGITIZER | 0x0981)
+#define WACOM_HID_WD_CONTROLPANEL       (WACOM_HID_UP_WACOMDIGITIZER | 0x0982)
+#define WACOM_HID_WD_ONSCREEN_KEYBOARD  (WACOM_HID_UP_WACOMDIGITIZER | 0x0983)
+#define WACOM_HID_WD_BUTTONCONFIG       (WACOM_HID_UP_WACOMDIGITIZER | 0x0986)
 #define WACOM_HID_WD_BUTTONHOME         (WACOM_HID_UP_WACOMDIGITIZER | 0x0990)
 #define WACOM_HID_WD_BUTTONUP           (WACOM_HID_UP_WACOMDIGITIZER | 0x0991)
 #define WACOM_HID_WD_BUTTONDOWN         (WACOM_HID_UP_WACOMDIGITIZER | 0x0992)
@@ -270,6 +275,7 @@ struct wacom_shared {
 	struct hid_device *pen;
 	struct hid_device *touch;
 	bool has_mute_touch_switch;
+	bool is_touch_on;
 };
 
 struct hid_data {
@@ -295,6 +301,7 @@ struct hid_data {
 	int bat_charging;
 	int bat_connected;
 	int ps_connected;
+	bool pad_input_event_flag;
 };
 
 struct wacom_remote_data {
@@ -327,6 +334,9 @@ struct wacom_wac {
 	int mode_value;
 	struct hid_data hid_data;
 	bool has_mute_touch_switch;
+	bool has_mode_change;
+	bool is_direct_mode;
+
 };
 
 #endif
diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c
index 7ef819680acd..26b05106f0d3 100644
--- a/drivers/hsi/clients/ssi_protocol.c
+++ b/drivers/hsi/clients/ssi_protocol.c
@@ -980,7 +980,7 @@ static int ssip_pn_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	/* Pad to 32-bits - FIXME: Revisit*/
 	if ((skb->len & 3) && skb_pad(skb, 4 - (skb->len & 3)))
-		goto drop;
+		goto inc_dropped;
 
 	/*
 	 * Modem sends Phonet messages over SSI with its own endianess...
@@ -1032,8 +1032,9 @@ static int ssip_pn_xmit(struct sk_buff *skb, struct net_device *dev)
 drop2:
 	hsi_free_msg(msg);
 drop:
-	dev->stats.tx_dropped++;
 	dev_kfree_skb(skb);
+inc_dropped:
+	dev->stats.tx_dropped++;
 
 	return 0;
 }
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 0403b51d20ba..c29cd5387a35 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -7,6 +7,9 @@ config HYPERV
 	  Select this option to run Linux as a Hyper-V client operating
 	  system.
 
+config HYPERV_TSCPAGE
+       def_bool HYPERV && X86_64
+
 config HYPERV_UTILS
 	tristate "Microsoft Hyper-V Utilities driver"
 	depends on HYPERV && CONNECTOR && NLS
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 81a80c82f1bd..321b8833fa6f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -502,12 +502,15 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 
 	wait_for_completion(&info->waitevent);
 
-	if (channel->rescind) {
-		ret = -ENODEV;
-		goto post_msg_err;
-	}
-
 post_msg_err:
+	/*
+	 * If the channel has been rescinded;
+	 * we will be awakened by the rescind
+	 * handler; set the error code to zero so we don't leak memory.
+	 */
+	if (channel->rescind)
+		ret = 0;
+
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
@@ -530,20 +533,18 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	int ret;
 
 	/*
-	 * vmbus_on_event(), running in the tasklet, can race
+	 * vmbus_on_event(), running in the per-channel tasklet, can race
 	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
 	 * the former is accessing channel->inbound.ring_buffer, the latter
-	 * could be freeing the ring_buffer pages.
-	 *
-	 * To resolve the race, we can serialize them by disabling the
-	 * tasklet when the latter is running here.
+	 * could be freeing the ring_buffer pages, so here we must stop it
+	 * first.
 	 */
-	hv_event_tasklet_disable(channel);
+	tasklet_disable(&channel->callback_event);
 
 	/*
 	 * In case a device driver's probe() fails (e.g.,
 	 * util_probe() -> vmbus_open() returns -ENOMEM) and the device is
-	 * rescinded later (e.g., we dynamically disble an Integrated Service
+	 * rescinded later (e.g., we dynamically disable an Integrated Service
 	 * in Hyper-V Manager), the driver's remove() invokes vmbus_close():
 	 * here we should skip most of the below cleanup work.
 	 */
@@ -605,8 +606,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
 out:
-	hv_event_tasklet_enable(channel);
-
 	return ret;
 }
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index f33465d78a02..fbcb06352308 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -350,7 +350,8 @@ static struct vmbus_channel *alloc_channel(void)
 static void free_channel(struct vmbus_channel *channel)
 {
 	tasklet_kill(&channel->callback_event);
-	kfree(channel);
+
+	kfree_rcu(channel, rcu);
 }
 
 static void percpu_channel_enq(void *arg)
@@ -359,14 +360,14 @@ static void percpu_channel_enq(void *arg)
 	struct hv_per_cpu_context *hv_cpu
 		= this_cpu_ptr(hv_context.cpu_context);
 
-	list_add_tail(&channel->percpu_list, &hv_cpu->chan_list);
+	list_add_tail_rcu(&channel->percpu_list, &hv_cpu->chan_list);
 }
 
 static void percpu_channel_deq(void *arg)
 {
 	struct vmbus_channel *channel = arg;
 
-	list_del(&channel->percpu_list);
+	list_del_rcu(&channel->percpu_list);
 }
 
 
@@ -381,19 +382,6 @@ static void vmbus_release_relid(u32 relid)
 		       true);
 }
 
-void hv_event_tasklet_disable(struct vmbus_channel *channel)
-{
-	tasklet_disable(&channel->callback_event);
-}
-
-void hv_event_tasklet_enable(struct vmbus_channel *channel)
-{
-	tasklet_enable(&channel->callback_event);
-
-	/* In case there is any pending event */
-	tasklet_schedule(&channel->callback_event);
-}
-
 void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 {
 	unsigned long flags;
@@ -402,7 +390,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 	BUG_ON(!channel->rescind);
 	BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
 
-	hv_event_tasklet_disable(channel);
 	if (channel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(channel->target_cpu,
@@ -411,7 +398,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		percpu_channel_deq(channel);
 		put_cpu();
 	}
-	hv_event_tasklet_enable(channel);
 
 	if (channel->primary_channel == NULL) {
 		list_del(&channel->listentry);
@@ -505,7 +491,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 
 	init_vp_index(newchannel, dev_type);
 
-	hv_event_tasklet_disable(newchannel);
 	if (newchannel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(newchannel->target_cpu,
@@ -515,7 +500,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 		percpu_channel_enq(newchannel);
 		put_cpu();
 	}
-	hv_event_tasklet_enable(newchannel);
 
 	/*
 	 * This state is used to indicate a successful open
@@ -565,7 +549,6 @@ err_deq_chan:
 	list_del(&newchannel->listentry);
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
-	hv_event_tasklet_disable(newchannel);
 	if (newchannel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(newchannel->target_cpu,
@@ -574,7 +557,6 @@ err_deq_chan:
 		percpu_channel_deq(newchannel);
 		put_cpu();
 	}
-	hv_event_tasklet_enable(newchannel);
 
 	vmbus_release_relid(newchannel->offermsg.child_relid);
 
@@ -814,6 +796,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 	/* Allocate the channel object and save this offer. */
 	newchannel = alloc_channel();
 	if (!newchannel) {
+		vmbus_release_relid(offer->child_relid);
 		pr_err("Unable to allocate channel object\n");
 		return;
 	}
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 9aee6014339d..a5596a642ed0 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -71,7 +71,6 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
 static const char fcopy_devname[] = "vmbus/hv_fcopy";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
-static struct completion release_event;
 /*
  * This state maintains the version number registered by the daemon.
  */
@@ -331,7 +330,6 @@ static void fcopy_on_reset(void)
 
 	if (cancel_delayed_work_sync(&fcopy_timeout_work))
 		fcopy_respond_to_host(HV_E_FAIL);
-	complete(&release_event);
 }
 
 int hv_fcopy_init(struct hv_util_service *srv)
@@ -339,7 +337,6 @@ int hv_fcopy_init(struct hv_util_service *srv)
 	recv_buffer = srv->recv_buffer;
 	fcopy_transaction.recv_channel = srv->channel;
 
-	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -361,5 +358,4 @@ void hv_fcopy_deinit(void)
 	fcopy_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&fcopy_timeout_work);
 	hvutil_transport_destroy(hvt);
-	wait_for_completion(&release_event);
 }
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index de263712e247..a1adfe2cfb34 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -101,7 +101,6 @@ static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
 static const char kvp_devname[] = "vmbus/hv_kvp";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
-static struct completion release_event;
 /*
  * Register the kernel component with the user-level daemon.
  * As part of this registration, pass the LIC version number.
@@ -714,7 +713,6 @@ static void kvp_on_reset(void)
 	if (cancel_delayed_work_sync(&kvp_timeout_work))
 		kvp_respond_to_host(NULL, HV_E_FAIL);
 	kvp_transaction.state = HVUTIL_DEVICE_INIT;
-	complete(&release_event);
 }
 
 int
@@ -723,7 +721,6 @@ hv_kvp_init(struct hv_util_service *srv)
 	recv_buffer = srv->recv_buffer;
 	kvp_transaction.recv_channel = srv->channel;
 
-	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -747,5 +744,4 @@ void hv_kvp_deinit(void)
 	cancel_delayed_work_sync(&kvp_timeout_work);
 	cancel_work_sync(&kvp_sendkey_work);
 	hvutil_transport_destroy(hvt);
-	wait_for_completion(&release_event);
 }
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index bcc03f0748d6..e659d1b94a57 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -79,7 +79,6 @@ static int dm_reg_value;
 static const char vss_devname[] = "vmbus/hv_vss";
 static __u8 *recv_buffer;
 static struct hvutil_transport *hvt;
-static struct completion release_event;
 
 static void vss_timeout_func(struct work_struct *dummy);
 static void vss_handle_request(struct work_struct *dummy);
@@ -361,13 +360,11 @@ static void vss_on_reset(void)
 	if (cancel_delayed_work_sync(&vss_timeout_work))
 		vss_respond_to_host(HV_E_FAIL);
 	vss_transaction.state = HVUTIL_DEVICE_INIT;
-	complete(&release_event);
 }
 
 int
 hv_vss_init(struct hv_util_service *srv)
 {
-	init_completion(&release_event);
 	if (vmbus_proto_version < VERSION_WIN8_1) {
 		pr_warn("Integration service 'Backup (volume snapshot)'"
 			" not supported on this host version.\n");
@@ -400,5 +397,4 @@ void hv_vss_deinit(void)
 	cancel_delayed_work_sync(&vss_timeout_work);
 	cancel_work_sync(&vss_handle_request_work);
 	hvutil_transport_destroy(hvt);
-	wait_for_completion(&release_event);
 }
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 3042eaa13062..186b10083c55 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -590,6 +590,8 @@ static int hv_timesync_init(struct hv_util_service *srv)
 	if (!hyperv_cs)
 		return -ENODEV;
 
+	spin_lock_init(&host_ts.lock);
+
 	INIT_WORK(&wrk.work, hv_set_host_time);
 
 	/*
diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c
index c235a9515267..4402a71e23f7 100644
--- a/drivers/hv/hv_utils_transport.c
+++ b/drivers/hv/hv_utils_transport.c
@@ -182,10 +182,11 @@ static int hvt_op_release(struct inode *inode, struct file *file)
 	 * connects back.
 	 */
 	hvt_reset(hvt);
-	mutex_unlock(&hvt->lock);
 
 	if (mode_old == HVUTIL_TRANSPORT_DESTROY)
-		hvt_transport_free(hvt);
+		complete(&hvt->release);
+
+	mutex_unlock(&hvt->lock);
 
 	return 0;
 }
@@ -304,6 +305,7 @@ struct hvutil_transport *hvutil_transport_init(const char *name,
 
 	init_waitqueue_head(&hvt->outmsg_q);
 	mutex_init(&hvt->lock);
+	init_completion(&hvt->release);
 
 	spin_lock(&hvt_list_lock);
 	list_add(&hvt->list, &hvt_list);
@@ -351,6 +353,8 @@ void hvutil_transport_destroy(struct hvutil_transport *hvt)
 	if (hvt->cn_id.idx > 0 && hvt->cn_id.val > 0)
 		cn_del_callback(&hvt->cn_id);
 
-	if (mode_old != HVUTIL_TRANSPORT_CHARDEV)
-		hvt_transport_free(hvt);
+	if (mode_old == HVUTIL_TRANSPORT_CHARDEV)
+		wait_for_completion(&hvt->release);
+
+	hvt_transport_free(hvt);
 }
diff --git a/drivers/hv/hv_utils_transport.h b/drivers/hv/hv_utils_transport.h
index d98f5225c3e6..79afb626e166 100644
--- a/drivers/hv/hv_utils_transport.h
+++ b/drivers/hv/hv_utils_transport.h
@@ -41,6 +41,7 @@ struct hvutil_transport {
 	int outmsg_len;                     /* its length */
 	wait_queue_head_t outmsg_q;         /* poll/read wait queue */
 	struct mutex lock;                  /* protects struct members */
+	struct completion release;          /* synchronize with fd release */
 };
 
 struct hvutil_transport *hvutil_transport_init(const char *name,
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 87799e81af97..c3f1a9e33cef 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -32,6 +32,8 @@
 
 #include "hyperv_vmbus.h"
 
+#define VMBUS_PKT_TRAILER	8
+
 /*
  * When we write to the ring buffer, check if the host needs to
  * be signaled. Here is the details of this protocol:
@@ -336,6 +338,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	return 0;
 }
 
+static inline void
+init_cached_read_index(struct hv_ring_buffer_info *rbi)
+{
+	rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
 int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
 		       u64 *requestid, bool raw)
@@ -366,7 +374,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 		return ret;
 	}
 
-	init_cached_read_index(channel);
+	init_cached_read_index(inring_info);
+
 	next_read_location = hv_get_next_read_location(inring_info);
 	next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
 						    sizeof(desc),
@@ -410,3 +419,86 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 
 	return ret;
 }
+
+/*
+ * Determine number of bytes available in ring buffer after
+ * the current iterator (priv_read_index) location.
+ *
+ * This is similar to hv_get_bytes_to_read but with private
+ * read index instead.
+ */
+static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
+{
+	u32 priv_read_loc = rbi->priv_read_index;
+	u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
+
+	if (write_loc >= priv_read_loc)
+		return write_loc - priv_read_loc;
+	else
+		return (rbi->ring_datasize - priv_read_loc) + write_loc;
+}
+
+/*
+ * Get first vmbus packet from ring buffer after read_index
+ *
+ * If ring buffer is empty, returns NULL and no other action needed.
+ */
+struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	/* set state for later hv_signal_on_read() */
+	init_cached_read_index(rbi);
+
+	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+		return NULL;
+
+	return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
+
+/*
+ * Get next vmbus packet from ring buffer.
+ *
+ * Advances the current location (priv_read_index) and checks for more
+ * data. If the end of the ring buffer is reached, then return NULL.
+ */
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+		   const struct vmpacket_descriptor *desc)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+	u32 packetlen = desc->len8 << 3;
+	u32 dsize = rbi->ring_datasize;
+
+	/* bump offset to next potential packet */
+	rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
+	if (rbi->priv_read_index >= dsize)
+		rbi->priv_read_index -= dsize;
+
+	/* more data? */
+	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+		return NULL;
+	else
+		return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
+
+/*
+ * Update host ring buffer after iterating over packets.
+ */
+void hv_pkt_iter_close(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	/*
+	 * Make sure all reads are done before we update the read index since
+	 * the writer may start writing to the read area once the read index
+	 * is updated.
+	 */
+	virt_rmb();
+	rbi->ring_buffer->read_index = rbi->priv_read_index;
+
+	hv_signal_on_read(channel);
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_close);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index da6b59ba5940..8370b9dc6037 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -939,8 +939,10 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 		if (relid == 0)
 			continue;
 
+		rcu_read_lock();
+
 		/* Find channel based on relid */
-		list_for_each_entry(channel, &hv_cpu->chan_list, percpu_list) {
+		list_for_each_entry_rcu(channel, &hv_cpu->chan_list, percpu_list) {
 			if (channel->offermsg.child_relid != relid)
 				continue;
 
@@ -956,6 +958,8 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 				tasklet_schedule(&channel->callback_event);
 			}
 		}
+
+		rcu_read_unlock();
 	}
 }
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 0649d53f3d16..22d5eafd6815 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -341,6 +341,15 @@ config SENSORS_ASB100
 	  This driver can also be built as a module.  If so, the module
 	  will be called asb100.
 
+config SENSORS_ASPEED
+	tristate "ASPEED AST2400/AST2500 PWM and Fan tach driver"
+	help
+	  This driver provides support for ASPEED AST2400/AST2500 PWM
+	  and Fan Tacho controllers.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called aspeed_pwm_tacho.
+
 config SENSORS_ATXP1
 	tristate "Attansic ATXP1 VID controller"
 	depends on I2C
@@ -1643,16 +1652,6 @@ config SENSORS_TMP421
 	  This driver can also be built as a module.  If so, the module
 	  will be called tmp421.
 
-config SENSORS_TWL4030_MADC
-	tristate "Texas Instruments TWL4030 MADC Hwmon"
-	depends on TWL4030_MADC
-	help
-	If you say yes here you get hwmon support for triton
-	TWL4030-MADC.
-
-	This driver can also be built as a module. If so it will be called
-	twl4030-madc-hwmon.
-
 config SENSORS_VEXPRESS
 	tristate "Versatile Express"
 	depends on VEXPRESS_CONFIG
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 5509edf6186a..d4641a9f16c1 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_SENSORS_ADT7475)	+= adt7475.o
 obj-$(CONFIG_SENSORS_APPLESMC)	+= applesmc.o
 obj-$(CONFIG_SENSORS_ARM_SCPI)	+= scpi-hwmon.o
 obj-$(CONFIG_SENSORS_ASC7621)	+= asc7621.o
+obj-$(CONFIG_SENSORS_ASPEED)	+= aspeed-pwm-tacho.o
 obj-$(CONFIG_SENSORS_ATXP1)	+= atxp1.o
 obj-$(CONFIG_SENSORS_CORETEMP)	+= coretemp.o
 obj-$(CONFIG_SENSORS_DA9052_ADC)+= da9052-hwmon.o
@@ -157,7 +158,6 @@ obj-$(CONFIG_SENSORS_TMP103)	+= tmp103.o
 obj-$(CONFIG_SENSORS_TMP108)	+= tmp108.o
 obj-$(CONFIG_SENSORS_TMP401)	+= tmp401.o
 obj-$(CONFIG_SENSORS_TMP421)	+= tmp421.o
-obj-$(CONFIG_SENSORS_TWL4030_MADC)+= twl4030-madc-hwmon.o
 obj-$(CONFIG_SENSORS_VEXPRESS)	+= vexpress-hwmon.o
 obj-$(CONFIG_SENSORS_VIA_CPUTEMP)+= via-cputemp.o
 obj-$(CONFIG_SENSORS_VIA686A)	+= via686a.o
diff --git a/drivers/hwmon/ad7414.c b/drivers/hwmon/ad7414.c
index 763490acc0df..cec227f13874 100644
--- a/drivers/hwmon/ad7414.c
+++ b/drivers/hwmon/ad7414.c
@@ -217,9 +217,16 @@ static const struct i2c_device_id ad7414_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ad7414_id);
 
+static const struct of_device_id ad7414_of_match[] = {
+	{ .compatible = "ad,ad7414" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ad7414_of_match);
+
 static struct i2c_driver ad7414_driver = {
 	.driver = {
 		.name	= "ad7414",
+		.of_match_table = of_match_ptr(ad7414_of_match),
 	},
 	.probe	= ad7414_probe,
 	.id_table = ad7414_id,
diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
index bbe3a5c5b3f5..a557b46dbe8e 100644
--- a/drivers/hwmon/adc128d818.c
+++ b/drivers/hwmon/adc128d818.c
@@ -546,10 +546,17 @@ static const struct i2c_device_id adc128_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, adc128_id);
 
+static const struct of_device_id adc128_of_match[] = {
+	{ .compatible = "ti,adc128d818" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, adc128_of_match);
+
 static struct i2c_driver adc128_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "adc128d818",
+		.of_match_table = of_match_ptr(adc128_of_match),
 	},
 	.probe		= adc128_probe,
 	.remove		= adc128_remove,
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 2b3105c8aed3..5140c27d16dd 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -31,6 +31,7 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/of.h>
 
 #include <linux/i2c/ads1015.h>
@@ -268,7 +269,12 @@ static int ads1015_probe(struct i2c_client *client,
 			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
-	data->id = id->driver_data;
+
+	if (client->dev.of_node)
+		data->id = (enum ads1015_chips)
+			of_device_get_match_data(&client->dev);
+	else
+		data->id = id->driver_data;
 	i2c_set_clientdata(client, data);
 	mutex_init(&data->update_lock);
 
@@ -303,9 +309,23 @@ static const struct i2c_device_id ads1015_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ads1015_id);
 
+static const struct of_device_id ads1015_of_match[] = {
+	{
+		.compatible = "ti,ads1015",
+		.data = (void *)ads1015
+	},
+	{
+		.compatible = "ti,ads1115",
+		.data = (void *)ads1115
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ads1015_of_match);
+
 static struct i2c_driver ads1015_driver = {
 	.driver = {
 		.name = "ads1015",
+		.of_match_table = of_match_ptr(ads1015_of_match),
 	},
 	.probe = ads1015_probe,
 	.remove = ads1015_remove,
diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
index ee396ff167d9..898607bf682b 100644
--- a/drivers/hwmon/ads7828.c
+++ b/drivers/hwmon/ads7828.c
@@ -31,9 +31,11 @@
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_data/ads7828.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
+#include <linux/regulator/consumer.h>
 
 /* The ADS7828 registers */
 #define ADS7828_CMD_SD_SE	0x80	/* Single ended inputs */
@@ -118,9 +120,12 @@ static int ads7828_probe(struct i2c_client *client,
 	struct ads7828_data *data;
 	struct device *hwmon_dev;
 	unsigned int vref_mv = ADS7828_INT_VREF_MV;
+	unsigned int vref_uv;
 	bool diff_input = false;
 	bool ext_vref = false;
 	unsigned int regval;
+	enum ads7828_chips chip;
+	struct regulator *reg;
 
 	data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL);
 	if (!data)
@@ -131,14 +136,32 @@ static int ads7828_probe(struct i2c_client *client,
 		ext_vref = pdata->ext_vref;
 		if (ext_vref && pdata->vref_mv)
 			vref_mv = pdata->vref_mv;
+	} else if (dev->of_node) {
+		diff_input = of_property_read_bool(dev->of_node,
+						   "ti,differential-input");
+		reg = devm_regulator_get_optional(dev, "vref");
+		if (!IS_ERR(reg)) {
+			vref_uv = regulator_get_voltage(reg);
+			vref_mv = DIV_ROUND_CLOSEST(vref_uv, 1000);
+			if (vref_mv < ADS7828_EXT_VREF_MV_MIN ||
+			    vref_mv > ADS7828_EXT_VREF_MV_MAX)
+				return -EINVAL;
+			ext_vref = true;
+		}
 	}
 
+	if (client->dev.of_node)
+		chip = (enum ads7828_chips)
+			of_device_get_match_data(&client->dev);
+	else
+		chip = id->driver_data;
+
 	/* Bound Vref with min/max values */
 	vref_mv = clamp_val(vref_mv, ADS7828_EXT_VREF_MV_MIN,
 			    ADS7828_EXT_VREF_MV_MAX);
 
 	/* ADS7828 uses 12-bit samples, while ADS7830 is 8-bit */
-	if (id->driver_data == ads7828) {
+	if (chip == ads7828) {
 		data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 4096);
 		data->regmap = devm_regmap_init_i2c(client,
 						    &ads2828_regmap_config);
@@ -177,9 +200,23 @@ static const struct i2c_device_id ads7828_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ads7828_device_ids);
 
+static const struct of_device_id ads7828_of_match[] = {
+	{
+		.compatible = "ti,ads7828",
+		.data = (void *)ads7828
+	},
+	{
+		.compatible = "ti,ads7830",
+		.data = (void *)ads7830
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ads7828_of_match);
+
 static struct i2c_driver ads7828_driver = {
 	.driver = {
 		.name = "ads7828",
+		.of_match_table = of_match_ptr(ads7828_of_match),
 	},
 
 	.id_table = ads7828_device_ids,
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index c646670b9ea9..c803e3c5fcd4 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
@@ -58,6 +59,8 @@
 #define REG_VENDID		0x3E
 #define REG_DEVID2		0x3F
 
+#define REG_CONFIG1		0x40
+
 #define REG_STATUS1		0x41
 #define REG_STATUS2		0x42
 
@@ -161,6 +164,27 @@ static const struct i2c_device_id adt7475_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, adt7475_id);
 
+static const struct of_device_id adt7475_of_match[] = {
+	{
+		.compatible = "adi,adt7473",
+		.data = (void *)adt7473
+	},
+	{
+		.compatible = "adi,adt7475",
+		.data = (void *)adt7475
+	},
+	{
+		.compatible = "adi,adt7476",
+		.data = (void *)adt7476
+	},
+	{
+		.compatible = "adi,adt7490",
+		.data = (void *)adt7490
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, adt7475_of_match);
+
 struct adt7475_data {
 	struct device *hwmon_dev;
 	struct mutex lock;
@@ -1250,6 +1274,7 @@ static void adt7475_remove_files(struct i2c_client *client,
 static int adt7475_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
+	enum chips chip;
 	static const char * const names[] = {
 		[adt7473] = "ADT7473",
 		[adt7475] = "ADT7475",
@@ -1268,8 +1293,13 @@ static int adt7475_probe(struct i2c_client *client,
 	mutex_init(&data->lock);
 	i2c_set_clientdata(client, data);
 
+	if (client->dev.of_node)
+		chip = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		chip = id->driver_data;
+
 	/* Initialize device-specific values */
-	switch (id->driver_data) {
+	switch (chip) {
 	case adt7476:
 		data->has_voltage = 0x0e;	/* in1 to in3 */
 		revision = adt7475_read(REG_DEVID2) & 0x07;
@@ -1343,6 +1373,17 @@ static int adt7475_probe(struct i2c_client *client,
 	for (i = 0; i < ADT7475_PWM_COUNT; i++)
 		adt7475_read_pwm(client, i);
 
+	/* Start monitoring */
+	switch (chip) {
+	case adt7475:
+	case adt7476:
+		i2c_smbus_write_byte_data(client, REG_CONFIG1,
+					  adt7475_read(REG_CONFIG1) | 0x01);
+		break;
+	default:
+		break;
+	}
+
 	ret = sysfs_create_group(&client->dev.kobj, &adt7475_attr_group);
 	if (ret)
 		return ret;
@@ -1428,6 +1469,7 @@ static struct i2c_driver adt7475_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "adt7475",
+		.of_match_table = of_match_ptr(adt7475_of_match),
 	},
 	.probe		= adt7475_probe,
 	.remove		= adt7475_remove,
diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
new file mode 100644
index 000000000000..48403a2115be
--- /dev/null
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -0,0 +1,835 @@
+/*
+ * Copyright (c) 2016 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 or later as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/gpio/consumer.h>
+#include <linux/delay.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/sysfs.h>
+#include <linux/regmap.h>
+
+/* ASPEED PWM & FAN Tach Register Definition */
+#define ASPEED_PTCR_CTRL		0x00
+#define ASPEED_PTCR_CLK_CTRL		0x04
+#define ASPEED_PTCR_DUTY0_CTRL		0x08
+#define ASPEED_PTCR_DUTY1_CTRL		0x0c
+#define ASPEED_PTCR_TYPEM_CTRL		0x10
+#define ASPEED_PTCR_TYPEM_CTRL1		0x14
+#define ASPEED_PTCR_TYPEN_CTRL		0x18
+#define ASPEED_PTCR_TYPEN_CTRL1		0x1c
+#define ASPEED_PTCR_TACH_SOURCE		0x20
+#define ASPEED_PTCR_TRIGGER		0x28
+#define ASPEED_PTCR_RESULT		0x2c
+#define ASPEED_PTCR_INTR_CTRL		0x30
+#define ASPEED_PTCR_INTR_STS		0x34
+#define ASPEED_PTCR_TYPEM_LIMIT		0x38
+#define ASPEED_PTCR_TYPEN_LIMIT		0x3C
+#define ASPEED_PTCR_CTRL_EXT		0x40
+#define ASPEED_PTCR_CLK_CTRL_EXT	0x44
+#define ASPEED_PTCR_DUTY2_CTRL		0x48
+#define ASPEED_PTCR_DUTY3_CTRL		0x4c
+#define ASPEED_PTCR_TYPEO_CTRL		0x50
+#define ASPEED_PTCR_TYPEO_CTRL1		0x54
+#define ASPEED_PTCR_TACH_SOURCE_EXT	0x60
+#define ASPEED_PTCR_TYPEO_LIMIT		0x78
+
+/* ASPEED_PTCR_CTRL : 0x00 - General Control Register */
+#define ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART1	15
+#define ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART2	6
+#define ASPEED_PTCR_CTRL_SET_PWMD_TYPE_MASK	(BIT(7) | BIT(15))
+
+#define ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART1	14
+#define ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART2	5
+#define ASPEED_PTCR_CTRL_SET_PWMC_TYPE_MASK	(BIT(6) | BIT(14))
+
+#define ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART1	13
+#define ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART2	4
+#define ASPEED_PTCR_CTRL_SET_PWMB_TYPE_MASK	(BIT(5) | BIT(13))
+
+#define ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART1	12
+#define ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART2	3
+#define ASPEED_PTCR_CTRL_SET_PWMA_TYPE_MASK	(BIT(4) | BIT(12))
+
+#define	ASPEED_PTCR_CTRL_FAN_NUM_EN(x)	BIT(16 + (x))
+
+#define	ASPEED_PTCR_CTRL_PWMD_EN	BIT(11)
+#define	ASPEED_PTCR_CTRL_PWMC_EN	BIT(10)
+#define	ASPEED_PTCR_CTRL_PWMB_EN	BIT(9)
+#define	ASPEED_PTCR_CTRL_PWMA_EN	BIT(8)
+
+#define	ASPEED_PTCR_CTRL_CLK_SRC	BIT(1)
+#define	ASPEED_PTCR_CTRL_CLK_EN		BIT(0)
+
+/* ASPEED_PTCR_CLK_CTRL : 0x04 - Clock Control Register */
+/* TYPE N */
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_MASK		GENMASK(31, 16)
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_UNIT		24
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_H		20
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_L		16
+/* TYPE M */
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_MASK         GENMASK(15, 0)
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_UNIT		8
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_H		4
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_L		0
+
+/*
+ * ASPEED_PTCR_DUTY_CTRL/1/2/3 : 0x08/0x0C/0x48/0x4C - PWM-FAN duty control
+ * 0/1/2/3 register
+ */
+#define DUTY_CTRL_PWM2_FALL_POINT	24
+#define DUTY_CTRL_PWM2_RISE_POINT	16
+#define DUTY_CTRL_PWM2_RISE_FALL_MASK	GENMASK(31, 16)
+#define DUTY_CTRL_PWM1_FALL_POINT	8
+#define DUTY_CTRL_PWM1_RISE_POINT	0
+#define DUTY_CTRL_PWM1_RISE_FALL_MASK   GENMASK(15, 0)
+
+/* ASPEED_PTCR_TYPEM_CTRL : 0x10/0x18/0x50 - Type M/N/O Ctrl 0 Register */
+#define TYPE_CTRL_FAN_MASK		(GENMASK(5, 1) | GENMASK(31, 16))
+#define TYPE_CTRL_FAN1_MASK		GENMASK(31, 0)
+#define TYPE_CTRL_FAN_PERIOD		16
+#define TYPE_CTRL_FAN_MODE		4
+#define TYPE_CTRL_FAN_DIVISION		1
+#define TYPE_CTRL_FAN_TYPE_EN		1
+
+/* ASPEED_PTCR_TACH_SOURCE : 0x20/0x60 - Tach Source Register */
+/* bit [0,1] at 0x20, bit [2] at 0x60 */
+#define TACH_PWM_SOURCE_BIT01(x)	((x) * 2)
+#define TACH_PWM_SOURCE_BIT2(x)		((x) * 2)
+#define TACH_PWM_SOURCE_MASK_BIT01(x)	(0x3 << ((x) * 2))
+#define TACH_PWM_SOURCE_MASK_BIT2(x)	BIT((x) * 2)
+
+/* ASPEED_PTCR_RESULT : 0x2c - Result Register */
+#define RESULT_STATUS_MASK		BIT(31)
+#define RESULT_VALUE_MASK		0xfffff
+
+/* ASPEED_PTCR_CTRL_EXT : 0x40 - General Control Extension #1 Register */
+#define ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART1	15
+#define ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART2	6
+#define ASPEED_PTCR_CTRL_SET_PWMH_TYPE_MASK	(BIT(7) | BIT(15))
+
+#define ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART1	14
+#define ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART2	5
+#define ASPEED_PTCR_CTRL_SET_PWMG_TYPE_MASK	(BIT(6) | BIT(14))
+
+#define ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART1	13
+#define ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART2	4
+#define ASPEED_PTCR_CTRL_SET_PWMF_TYPE_MASK	(BIT(5) | BIT(13))
+
+#define ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART1	12
+#define ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART2	3
+#define ASPEED_PTCR_CTRL_SET_PWME_TYPE_MASK	(BIT(4) | BIT(12))
+
+#define	ASPEED_PTCR_CTRL_PWMH_EN	BIT(11)
+#define	ASPEED_PTCR_CTRL_PWMG_EN	BIT(10)
+#define	ASPEED_PTCR_CTRL_PWMF_EN	BIT(9)
+#define	ASPEED_PTCR_CTRL_PWME_EN	BIT(8)
+
+/* ASPEED_PTCR_CLK_EXT_CTRL : 0x44 - Clock Control Extension #1 Register */
+/* TYPE O */
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_MASK         GENMASK(15, 0)
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_UNIT		8
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_H		4
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_L		0
+
+#define PWM_MAX 255
+
+#define M_PWM_DIV_H 0x00
+#define M_PWM_DIV_L 0x05
+#define M_PWM_PERIOD 0x5F
+#define M_TACH_CLK_DIV 0x00
+#define M_TACH_MODE 0x00
+#define M_TACH_UNIT 0x1000
+#define INIT_FAN_CTRL 0xFF
+
+struct aspeed_pwm_tacho_data {
+	struct regmap *regmap;
+	unsigned long clk_freq;
+	bool pwm_present[8];
+	bool fan_tach_present[16];
+	u8 type_pwm_clock_unit[3];
+	u8 type_pwm_clock_division_h[3];
+	u8 type_pwm_clock_division_l[3];
+	u8 type_fan_tach_clock_division[3];
+	u16 type_fan_tach_unit[3];
+	u8 pwm_port_type[8];
+	u8 pwm_port_fan_ctrl[8];
+	u8 fan_tach_ch_source[16];
+	const struct attribute_group *groups[3];
+};
+
+enum type { TYPEM, TYPEN, TYPEO };
+
+struct type_params {
+	u32 l_value;
+	u32 h_value;
+	u32 unit_value;
+	u32 clk_ctrl_mask;
+	u32 clk_ctrl_reg;
+	u32 ctrl_reg;
+	u32 ctrl_reg1;
+};
+
+static const struct type_params type_params[] = {
+	[TYPEM] = {
+		.l_value = ASPEED_PTCR_CLK_CTRL_TYPEM_L,
+		.h_value = ASPEED_PTCR_CLK_CTRL_TYPEM_H,
+		.unit_value = ASPEED_PTCR_CLK_CTRL_TYPEM_UNIT,
+		.clk_ctrl_mask = ASPEED_PTCR_CLK_CTRL_TYPEM_MASK,
+		.clk_ctrl_reg = ASPEED_PTCR_CLK_CTRL,
+		.ctrl_reg = ASPEED_PTCR_TYPEM_CTRL,
+		.ctrl_reg1 = ASPEED_PTCR_TYPEM_CTRL1,
+	},
+	[TYPEN] = {
+		.l_value = ASPEED_PTCR_CLK_CTRL_TYPEN_L,
+		.h_value = ASPEED_PTCR_CLK_CTRL_TYPEN_H,
+		.unit_value = ASPEED_PTCR_CLK_CTRL_TYPEN_UNIT,
+		.clk_ctrl_mask = ASPEED_PTCR_CLK_CTRL_TYPEN_MASK,
+		.clk_ctrl_reg = ASPEED_PTCR_CLK_CTRL,
+		.ctrl_reg = ASPEED_PTCR_TYPEN_CTRL,
+		.ctrl_reg1 = ASPEED_PTCR_TYPEN_CTRL1,
+	},
+	[TYPEO] = {
+		.l_value = ASPEED_PTCR_CLK_CTRL_TYPEO_L,
+		.h_value = ASPEED_PTCR_CLK_CTRL_TYPEO_H,
+		.unit_value = ASPEED_PTCR_CLK_CTRL_TYPEO_UNIT,
+		.clk_ctrl_mask = ASPEED_PTCR_CLK_CTRL_TYPEO_MASK,
+		.clk_ctrl_reg = ASPEED_PTCR_CLK_CTRL_EXT,
+		.ctrl_reg = ASPEED_PTCR_TYPEO_CTRL,
+		.ctrl_reg1 = ASPEED_PTCR_TYPEO_CTRL1,
+	}
+};
+
+enum pwm_port { PWMA, PWMB, PWMC, PWMD, PWME, PWMF, PWMG, PWMH };
+
+struct pwm_port_params {
+	u32 pwm_en;
+	u32 ctrl_reg;
+	u32 type_part1;
+	u32 type_part2;
+	u32 type_mask;
+	u32 duty_ctrl_rise_point;
+	u32 duty_ctrl_fall_point;
+	u32 duty_ctrl_reg;
+	u32 duty_ctrl_rise_fall_mask;
+};
+
+static const struct pwm_port_params pwm_port_params[] = {
+	[PWMA] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMA_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMA_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY0_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+	},
+	[PWMB] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMB_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMB_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY0_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+	},
+	[PWMC] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMC_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMC_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY1_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+	},
+	[PWMD] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMD_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMD_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY1_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+	},
+	[PWME] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWME_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWME_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY2_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+	},
+	[PWMF] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMF_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMF_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY2_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+	},
+	[PWMG] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMG_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMG_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY3_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+	},
+	[PWMH] = {
+		.pwm_en = ASPEED_PTCR_CTRL_PWMH_EN,
+		.ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+		.type_part1 = ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART1,
+		.type_part2 = ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART2,
+		.type_mask = ASPEED_PTCR_CTRL_SET_PWMH_TYPE_MASK,
+		.duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+		.duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+		.duty_ctrl_reg = ASPEED_PTCR_DUTY3_CTRL,
+		.duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+	}
+};
+
+static int regmap_aspeed_pwm_tacho_reg_write(void *context, unsigned int reg,
+					     unsigned int val)
+{
+	void __iomem *regs = (void __iomem *)context;
+
+	writel(val, regs + reg);
+	return 0;
+}
+
+static int regmap_aspeed_pwm_tacho_reg_read(void *context, unsigned int reg,
+					    unsigned int *val)
+{
+	void __iomem *regs = (void __iomem *)context;
+
+	*val = readl(regs + reg);
+	return 0;
+}
+
+static const struct regmap_config aspeed_pwm_tacho_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = ASPEED_PTCR_TYPEO_LIMIT,
+	.reg_write = regmap_aspeed_pwm_tacho_reg_write,
+	.reg_read = regmap_aspeed_pwm_tacho_reg_read,
+	.fast_io = true,
+};
+
+static void aspeed_set_clock_enable(struct regmap *regmap, bool val)
+{
+	regmap_update_bits(regmap, ASPEED_PTCR_CTRL,
+			   ASPEED_PTCR_CTRL_CLK_EN,
+			   val ? ASPEED_PTCR_CTRL_CLK_EN : 0);
+}
+
+static void aspeed_set_clock_source(struct regmap *regmap, int val)
+{
+	regmap_update_bits(regmap, ASPEED_PTCR_CTRL,
+			   ASPEED_PTCR_CTRL_CLK_SRC,
+			   val ? ASPEED_PTCR_CTRL_CLK_SRC : 0);
+}
+
+static void aspeed_set_pwm_clock_values(struct regmap *regmap, u8 type,
+					u8 div_high, u8 div_low, u8 unit)
+{
+	u32 reg_value = ((div_high << type_params[type].h_value) |
+			 (div_low << type_params[type].l_value) |
+			 (unit << type_params[type].unit_value));
+
+	regmap_update_bits(regmap, type_params[type].clk_ctrl_reg,
+			   type_params[type].clk_ctrl_mask, reg_value);
+}
+
+static void aspeed_set_pwm_port_enable(struct regmap *regmap, u8 pwm_port,
+				       bool enable)
+{
+	regmap_update_bits(regmap, pwm_port_params[pwm_port].ctrl_reg,
+			   pwm_port_params[pwm_port].pwm_en,
+			   enable ? pwm_port_params[pwm_port].pwm_en : 0);
+}
+
+static void aspeed_set_pwm_port_type(struct regmap *regmap,
+				     u8 pwm_port, u8 type)
+{
+	u32 reg_value = (type & 0x1) << pwm_port_params[pwm_port].type_part1;
+
+	reg_value |= (type & 0x2) << pwm_port_params[pwm_port].type_part2;
+
+	regmap_update_bits(regmap, pwm_port_params[pwm_port].ctrl_reg,
+			   pwm_port_params[pwm_port].type_mask, reg_value);
+}
+
+static void aspeed_set_pwm_port_duty_rising_falling(struct regmap *regmap,
+						    u8 pwm_port, u8 rising,
+						    u8 falling)
+{
+	u32 reg_value = (rising <<
+			 pwm_port_params[pwm_port].duty_ctrl_rise_point);
+	reg_value |= (falling <<
+		      pwm_port_params[pwm_port].duty_ctrl_fall_point);
+
+	regmap_update_bits(regmap, pwm_port_params[pwm_port].duty_ctrl_reg,
+			   pwm_port_params[pwm_port].duty_ctrl_rise_fall_mask,
+			   reg_value);
+}
+
+static void aspeed_set_tacho_type_enable(struct regmap *regmap, u8 type,
+					 bool enable)
+{
+	regmap_update_bits(regmap, type_params[type].ctrl_reg,
+			   TYPE_CTRL_FAN_TYPE_EN,
+			   enable ? TYPE_CTRL_FAN_TYPE_EN : 0);
+}
+
+static void aspeed_set_tacho_type_values(struct regmap *regmap, u8 type,
+					 u8 mode, u16 unit, u8 division)
+{
+	u32 reg_value = ((mode << TYPE_CTRL_FAN_MODE) |
+			 (unit << TYPE_CTRL_FAN_PERIOD) |
+			 (division << TYPE_CTRL_FAN_DIVISION));
+
+	regmap_update_bits(regmap, type_params[type].ctrl_reg,
+			   TYPE_CTRL_FAN_MASK, reg_value);
+	regmap_update_bits(regmap, type_params[type].ctrl_reg1,
+			   TYPE_CTRL_FAN1_MASK, unit << 16);
+}
+
+static void aspeed_set_fan_tach_ch_enable(struct regmap *regmap, u8 fan_tach_ch,
+					  bool enable)
+{
+	regmap_update_bits(regmap, ASPEED_PTCR_CTRL,
+			   ASPEED_PTCR_CTRL_FAN_NUM_EN(fan_tach_ch),
+			   enable ?
+			   ASPEED_PTCR_CTRL_FAN_NUM_EN(fan_tach_ch) : 0);
+}
+
+static void aspeed_set_fan_tach_ch_source(struct regmap *regmap, u8 fan_tach_ch,
+					  u8 fan_tach_ch_source)
+{
+	u32 reg_value1 = ((fan_tach_ch_source & 0x3) <<
+			  TACH_PWM_SOURCE_BIT01(fan_tach_ch));
+	u32 reg_value2 = (((fan_tach_ch_source & 0x4) >> 2) <<
+			  TACH_PWM_SOURCE_BIT2(fan_tach_ch));
+
+	regmap_update_bits(regmap, ASPEED_PTCR_TACH_SOURCE,
+			   TACH_PWM_SOURCE_MASK_BIT01(fan_tach_ch),
+			   reg_value1);
+
+	regmap_update_bits(regmap, ASPEED_PTCR_TACH_SOURCE_EXT,
+			   TACH_PWM_SOURCE_MASK_BIT2(fan_tach_ch),
+			   reg_value2);
+}
+
+static void aspeed_set_pwm_port_fan_ctrl(struct aspeed_pwm_tacho_data *priv,
+					 u8 index, u8 fan_ctrl)
+{
+	u16 period, dc_time_on;
+
+	period = priv->type_pwm_clock_unit[priv->pwm_port_type[index]];
+	period += 1;
+	dc_time_on = (fan_ctrl * period) / PWM_MAX;
+
+	if (dc_time_on == 0) {
+		aspeed_set_pwm_port_enable(priv->regmap, index, false);
+	} else {
+		if (dc_time_on == period)
+			dc_time_on = 0;
+
+		aspeed_set_pwm_port_duty_rising_falling(priv->regmap, index, 0,
+							dc_time_on);
+		aspeed_set_pwm_port_enable(priv->regmap, index, true);
+	}
+}
+
+static u32 aspeed_get_fan_tach_ch_measure_period(struct aspeed_pwm_tacho_data
+						 *priv, u8 type)
+{
+	u32 clk;
+	u16 tacho_unit;
+	u8 clk_unit, div_h, div_l, tacho_div;
+
+	clk = priv->clk_freq;
+	clk_unit = priv->type_pwm_clock_unit[type];
+	div_h = priv->type_pwm_clock_division_h[type];
+	div_h = 0x1 << div_h;
+	div_l = priv->type_pwm_clock_division_l[type];
+	if (div_l == 0)
+		div_l = 1;
+	else
+		div_l = div_l * 2;
+
+	tacho_unit = priv->type_fan_tach_unit[type];
+	tacho_div = priv->type_fan_tach_clock_division[type];
+
+	tacho_div = 0x4 << (tacho_div * 2);
+	return clk / (clk_unit * div_h * div_l * tacho_div * tacho_unit);
+}
+
+static u32 aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
+				      u8 fan_tach_ch)
+{
+	u32 raw_data, tach_div, clk_source, sec, val;
+	u8 fan_tach_ch_source, type;
+
+	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0);
+	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch);
+
+	fan_tach_ch_source = priv->fan_tach_ch_source[fan_tach_ch];
+	type = priv->pwm_port_type[fan_tach_ch_source];
+
+	sec = (1000 / aspeed_get_fan_tach_ch_measure_period(priv, type));
+	msleep(sec);
+
+	regmap_read(priv->regmap, ASPEED_PTCR_RESULT, &val);
+	raw_data = val & RESULT_VALUE_MASK;
+	tach_div = priv->type_fan_tach_clock_division[type];
+	tach_div = 0x4 << (tach_div * 2);
+	clk_source = priv->clk_freq;
+
+	if (raw_data == 0)
+		return 0;
+
+	return (clk_source * 60) / (2 * raw_data * tach_div);
+}
+
+static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
+{
+	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
+	int index = sensor_attr->index;
+	int ret;
+	struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+	long fan_ctrl;
+
+	ret = kstrtol(buf, 10, &fan_ctrl);
+	if (ret != 0)
+		return ret;
+
+	if (fan_ctrl < 0 || fan_ctrl > PWM_MAX)
+		return -EINVAL;
+
+	if (priv->pwm_port_fan_ctrl[index] == fan_ctrl)
+		return count;
+
+	priv->pwm_port_fan_ctrl[index] = fan_ctrl;
+	aspeed_set_pwm_port_fan_ctrl(priv, index, fan_ctrl);
+
+	return count;
+}
+
+static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
+	int index = sensor_attr->index;
+	struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%u\n", priv->pwm_port_fan_ctrl[index]);
+}
+
+static ssize_t show_rpm(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
+	int index = sensor_attr->index;
+	u32 rpm;
+	struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+	rpm = aspeed_get_fan_tach_ch_rpm(priv, index);
+
+	return sprintf(buf, "%u\n", rpm);
+}
+
+static umode_t pwm_is_visible(struct kobject *kobj,
+			      struct attribute *a, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+	if (!priv->pwm_present[index])
+		return 0;
+	return a->mode;
+}
+
+static umode_t fan_dev_is_visible(struct kobject *kobj,
+				  struct attribute *a, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+	if (!priv->fan_tach_present[index])
+		return 0;
+	return a->mode;
+}
+
+static SENSOR_DEVICE_ATTR(pwm0, 0644,
+			show_pwm, set_pwm, 0);
+static SENSOR_DEVICE_ATTR(pwm1, 0644,
+			show_pwm, set_pwm, 1);
+static SENSOR_DEVICE_ATTR(pwm2, 0644,
+			show_pwm, set_pwm, 2);
+static SENSOR_DEVICE_ATTR(pwm3, 0644,
+			show_pwm, set_pwm, 3);
+static SENSOR_DEVICE_ATTR(pwm4, 0644,
+			show_pwm, set_pwm, 4);
+static SENSOR_DEVICE_ATTR(pwm5, 0644,
+			show_pwm, set_pwm, 5);
+static SENSOR_DEVICE_ATTR(pwm6, 0644,
+			show_pwm, set_pwm, 6);
+static SENSOR_DEVICE_ATTR(pwm7, 0644,
+			show_pwm, set_pwm, 7);
+static struct attribute *pwm_dev_attrs[] = {
+	&sensor_dev_attr_pwm0.dev_attr.attr,
+	&sensor_dev_attr_pwm1.dev_attr.attr,
+	&sensor_dev_attr_pwm2.dev_attr.attr,
+	&sensor_dev_attr_pwm3.dev_attr.attr,
+	&sensor_dev_attr_pwm4.dev_attr.attr,
+	&sensor_dev_attr_pwm5.dev_attr.attr,
+	&sensor_dev_attr_pwm6.dev_attr.attr,
+	&sensor_dev_attr_pwm7.dev_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group pwm_dev_group = {
+	.attrs = pwm_dev_attrs,
+	.is_visible = pwm_is_visible,
+};
+
+static SENSOR_DEVICE_ATTR(fan0_input, 0444,
+		show_rpm, NULL, 0);
+static SENSOR_DEVICE_ATTR(fan1_input, 0444,
+		show_rpm, NULL, 1);
+static SENSOR_DEVICE_ATTR(fan2_input, 0444,
+		show_rpm, NULL, 2);
+static SENSOR_DEVICE_ATTR(fan3_input, 0444,
+		show_rpm, NULL, 3);
+static SENSOR_DEVICE_ATTR(fan4_input, 0444,
+		show_rpm, NULL, 4);
+static SENSOR_DEVICE_ATTR(fan5_input, 0444,
+		show_rpm, NULL, 5);
+static SENSOR_DEVICE_ATTR(fan6_input, 0444,
+		show_rpm, NULL, 6);
+static SENSOR_DEVICE_ATTR(fan7_input, 0444,
+		show_rpm, NULL, 7);
+static SENSOR_DEVICE_ATTR(fan8_input, 0444,
+		show_rpm, NULL, 8);
+static SENSOR_DEVICE_ATTR(fan9_input, 0444,
+		show_rpm, NULL, 9);
+static SENSOR_DEVICE_ATTR(fan10_input, 0444,
+		show_rpm, NULL, 10);
+static SENSOR_DEVICE_ATTR(fan11_input, 0444,
+		show_rpm, NULL, 11);
+static SENSOR_DEVICE_ATTR(fan12_input, 0444,
+		show_rpm, NULL, 12);
+static SENSOR_DEVICE_ATTR(fan13_input, 0444,
+		show_rpm, NULL, 13);
+static SENSOR_DEVICE_ATTR(fan14_input, 0444,
+		show_rpm, NULL, 14);
+static SENSOR_DEVICE_ATTR(fan15_input, 0444,
+		show_rpm, NULL, 15);
+static struct attribute *fan_dev_attrs[] = {
+	&sensor_dev_attr_fan0_input.dev_attr.attr,
+	&sensor_dev_attr_fan1_input.dev_attr.attr,
+	&sensor_dev_attr_fan2_input.dev_attr.attr,
+	&sensor_dev_attr_fan3_input.dev_attr.attr,
+	&sensor_dev_attr_fan4_input.dev_attr.attr,
+	&sensor_dev_attr_fan5_input.dev_attr.attr,
+	&sensor_dev_attr_fan6_input.dev_attr.attr,
+	&sensor_dev_attr_fan7_input.dev_attr.attr,
+	&sensor_dev_attr_fan8_input.dev_attr.attr,
+	&sensor_dev_attr_fan9_input.dev_attr.attr,
+	&sensor_dev_attr_fan10_input.dev_attr.attr,
+	&sensor_dev_attr_fan11_input.dev_attr.attr,
+	&sensor_dev_attr_fan12_input.dev_attr.attr,
+	&sensor_dev_attr_fan13_input.dev_attr.attr,
+	&sensor_dev_attr_fan14_input.dev_attr.attr,
+	&sensor_dev_attr_fan15_input.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group fan_dev_group = {
+	.attrs = fan_dev_attrs,
+	.is_visible = fan_dev_is_visible,
+};
+
+/*
+ * The clock type is type M :
+ * The PWM frequency = 24MHz / (type M clock division L bit *
+ * type M clock division H bit * (type M PWM period bit + 1))
+ */
+static void aspeed_create_type(struct aspeed_pwm_tacho_data *priv)
+{
+	priv->type_pwm_clock_division_h[TYPEM] = M_PWM_DIV_H;
+	priv->type_pwm_clock_division_l[TYPEM] = M_PWM_DIV_L;
+	priv->type_pwm_clock_unit[TYPEM] = M_PWM_PERIOD;
+	aspeed_set_pwm_clock_values(priv->regmap, TYPEM, M_PWM_DIV_H,
+				    M_PWM_DIV_L, M_PWM_PERIOD);
+	aspeed_set_tacho_type_enable(priv->regmap, TYPEM, true);
+	priv->type_fan_tach_clock_division[TYPEM] = M_TACH_CLK_DIV;
+	priv->type_fan_tach_unit[TYPEM] = M_TACH_UNIT;
+	aspeed_set_tacho_type_values(priv->regmap, TYPEM, M_TACH_MODE,
+				     M_TACH_UNIT, M_TACH_CLK_DIV);
+}
+
+static void aspeed_create_pwm_port(struct aspeed_pwm_tacho_data *priv,
+				   u8 pwm_port)
+{
+	aspeed_set_pwm_port_enable(priv->regmap, pwm_port, true);
+	priv->pwm_present[pwm_port] = true;
+
+	priv->pwm_port_type[pwm_port] = TYPEM;
+	aspeed_set_pwm_port_type(priv->regmap, pwm_port, TYPEM);
+
+	priv->pwm_port_fan_ctrl[pwm_port] = INIT_FAN_CTRL;
+	aspeed_set_pwm_port_fan_ctrl(priv, pwm_port, INIT_FAN_CTRL);
+}
+
+static void aspeed_create_fan_tach_channel(struct aspeed_pwm_tacho_data *priv,
+					   u8 *fan_tach_ch,
+					   int count,
+					   u8 pwm_source)
+{
+	u8 val, index;
+
+	for (val = 0; val < count; val++) {
+		index = fan_tach_ch[val];
+		aspeed_set_fan_tach_ch_enable(priv->regmap, index, true);
+		priv->fan_tach_present[index] = true;
+		priv->fan_tach_ch_source[index] = pwm_source;
+		aspeed_set_fan_tach_ch_source(priv->regmap, index, pwm_source);
+	}
+}
+
+static int aspeed_create_fan(struct device *dev,
+			     struct device_node *child,
+			     struct aspeed_pwm_tacho_data *priv)
+{
+	u8 *fan_tach_ch;
+	u32 pwm_port;
+	int ret, count;
+
+	ret = of_property_read_u32(child, "reg", &pwm_port);
+	if (ret)
+		return ret;
+	aspeed_create_pwm_port(priv, (u8)pwm_port);
+
+	count = of_property_count_u8_elems(child, "aspeed,fan-tach-ch");
+	if (count < 1)
+		return -EINVAL;
+	fan_tach_ch = devm_kzalloc(dev, sizeof(*fan_tach_ch) * count,
+				   GFP_KERNEL);
+	if (!fan_tach_ch)
+		return -ENOMEM;
+	ret = of_property_read_u8_array(child, "aspeed,fan-tach-ch",
+					fan_tach_ch, count);
+	if (ret)
+		return ret;
+	aspeed_create_fan_tach_channel(priv, fan_tach_ch, count, pwm_port);
+
+	return 0;
+}
+
+static int aspeed_pwm_tacho_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np, *child;
+	struct aspeed_pwm_tacho_data *priv;
+	void __iomem *regs;
+	struct resource *res;
+	struct device *hwmon;
+	struct clk *clk;
+	int ret;
+
+	np = dev->of_node;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOENT;
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs,
+			&aspeed_pwm_tacho_regmap_config);
+	if (IS_ERR(priv->regmap))
+		return PTR_ERR(priv->regmap);
+	regmap_write(priv->regmap, ASPEED_PTCR_TACH_SOURCE, 0);
+	regmap_write(priv->regmap, ASPEED_PTCR_TACH_SOURCE_EXT, 0);
+
+	clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(clk))
+		return -ENODEV;
+	priv->clk_freq = clk_get_rate(clk);
+	aspeed_set_clock_enable(priv->regmap, true);
+	aspeed_set_clock_source(priv->regmap, 0);
+
+	aspeed_create_type(priv);
+
+	for_each_child_of_node(np, child) {
+		ret = aspeed_create_fan(dev, child, priv);
+		of_node_put(child);
+		if (ret)
+			return ret;
+	}
+	of_node_put(np);
+
+	priv->groups[0] = &pwm_dev_group;
+	priv->groups[1] = &fan_dev_group;
+	priv->groups[2] = NULL;
+	hwmon = devm_hwmon_device_register_with_groups(dev,
+						       "aspeed_pwm_tacho",
+						       priv, priv->groups);
+	return PTR_ERR_OR_ZERO(hwmon);
+}
+
+static const struct of_device_id of_pwm_tacho_match_table[] = {
+	{ .compatible = "aspeed,ast2400-pwm-tacho", },
+	{ .compatible = "aspeed,ast2500-pwm-tacho", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_tacho_match_table);
+
+static struct platform_driver aspeed_pwm_tacho_driver = {
+	.probe		= aspeed_pwm_tacho_probe,
+	.driver		= {
+		.name	= "aspeed_pwm_tacho",
+		.of_match_table = of_pwm_tacho_match_table,
+	},
+};
+
+module_platform_driver(aspeed_pwm_tacho_driver);
+
+MODULE_AUTHOR("Jaghathiswari Rankappagounder Natarajan <jaghu@google.com>");
+MODULE_DESCRIPTION("ASPEED PWM and Fan Tacho device driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index cccef87963e0..975c43d446f8 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -646,6 +646,9 @@ static int atk_read_value(struct atk_sensor_data *sensor, u64 *value)
 		else
 			err = atk_read_value_new(sensor, value);
 
+		if (err)
+			return err;
+
 		sensor->is_valid = true;
 		sensor->last_updated = jiffies;
 		sensor->cached_value = *value;
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 34704b0451b4..3189246302a6 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -995,6 +995,13 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = {
 		},
 		.driver_data = (void *)&i8k_config_data[DELL_XPS],
 	},
+	{
+		.ident = "Dell XPS 15 9560",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9560"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 28375d59cc36..dd6e17c1076b 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -186,7 +186,7 @@ static ssize_t hwmon_attr_show_string(struct device *dev,
 				      char *buf)
 {
 	struct hwmon_device_attribute *hattr = to_hwmon_attr(devattr);
-	char *s;
+	const char *s;
 	int ret;
 
 	ret = hattr->ops->read_string(dev, hattr->type, hattr->attr,
diff --git a/drivers/hwmon/ina209.c b/drivers/hwmon/ina209.c
index 5378fdefc1f7..aa0768ce8aea 100644
--- a/drivers/hwmon/ina209.c
+++ b/drivers/hwmon/ina209.c
@@ -117,7 +117,7 @@ static long ina209_from_reg(const u8 reg, const u16 val)
 	case INA209_SHUNT_VOLTAGE_POS_WARN:
 	case INA209_SHUNT_VOLTAGE_NEG_WARN:
 		/* LSB=10 uV. Convert to mV. */
-		return DIV_ROUND_CLOSEST(val, 100);
+		return DIV_ROUND_CLOSEST((s16)val, 100);
 
 	case INA209_BUS_VOLTAGE:
 	case INA209_BUS_VOLTAGE_MAX_PEAK:
@@ -146,7 +146,7 @@ static long ina209_from_reg(const u8 reg, const u16 val)
 
 	case INA209_CURRENT:
 		/* LSB=1 mA (selected). Is in mA */
-		return val;
+		return (s16)val;
 	}
 
 	/* programmer goofed */
@@ -608,11 +608,18 @@ static const struct i2c_device_id ina209_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ina209_id);
 
+static const struct of_device_id ina209_of_match[] = {
+	{ .compatible = "ti,ina209" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ina209_of_match);
+
 /* This is the driver that will be inserted */
 static struct i2c_driver ina209_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "ina209",
+		.of_match_table = of_match_ptr(ina209_of_match),
 	},
 	.probe		= ina209_probe,
 	.remove		= ina209_remove,
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index b24f1d3045f0..62e38fa8cda2 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -34,6 +34,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/jiffies.h>
+#include <linux/of_device.h>
 #include <linux/of.h>
 #include <linux/delay.h>
 #include <linux/util_macros.h>
@@ -424,13 +425,19 @@ static int ina2xx_probe(struct i2c_client *client,
 	struct device *hwmon_dev;
 	u32 val;
 	int ret, group = 0;
+	enum ina2xx_ids chip;
+
+	if (client->dev.of_node)
+		chip = (enum ina2xx_ids)of_device_get_match_data(&client->dev);
+	else
+		chip = id->driver_data;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
 	/* set the device type */
-	data->config = &ina2xx_config[id->driver_data];
+	data->config = &ina2xx_config[chip];
 
 	if (of_property_read_u32(dev->of_node, "shunt-resistor", &val) < 0) {
 		struct ina2xx_platform_data *pdata = dev_get_platdata(dev);
@@ -487,9 +494,35 @@ static const struct i2c_device_id ina2xx_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ina2xx_id);
 
+static const struct of_device_id ina2xx_of_match[] = {
+	{
+		.compatible = "ti,ina219",
+		.data = (void *)ina219
+	},
+	{
+		.compatible = "ti,ina220",
+		.data = (void *)ina219
+	},
+	{
+		.compatible = "ti,ina226",
+		.data = (void *)ina226
+	},
+	{
+		.compatible = "ti,ina230",
+		.data = (void *)ina226
+	},
+	{
+		.compatible = "ti,ina231",
+		.data = (void *)ina226
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ina2xx_of_match);
+
 static struct i2c_driver ina2xx_driver = {
 	.driver = {
 		.name	= "ina2xx",
+		.of_match_table = of_match_ptr(ina2xx_of_match),
 	},
 	.probe		= ina2xx_probe,
 	.id_table	= ina2xx_id,
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index efb01c247e2d..4dfc7238313e 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -3198,7 +3198,7 @@ static int __init sm_it87_init(void)
 {
 	int sioaddr[2] = { REG_2E, REG_4E };
 	struct it87_sio_data sio_data;
-	unsigned short isa_address;
+	unsigned short isa_address[2];
 	bool found = false;
 	int i, err;
 
@@ -3208,15 +3208,29 @@ static int __init sm_it87_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(sioaddr); i++) {
 		memset(&sio_data, 0, sizeof(struct it87_sio_data));
-		isa_address = 0;
-		err = it87_find(sioaddr[i], &isa_address, &sio_data);
-		if (err || isa_address == 0)
+		isa_address[i] = 0;
+		err = it87_find(sioaddr[i], &isa_address[i], &sio_data);
+		if (err || isa_address[i] == 0)
 			continue;
+		/*
+		 * Don't register second chip if its ISA address matches
+		 * the first chip's ISA address.
+		 */
+		if (i && isa_address[i] == isa_address[0])
+			break;
 
-		err = it87_device_add(i, isa_address, &sio_data);
+		err = it87_device_add(i, isa_address[i], &sio_data);
 		if (err)
 			goto exit_dev_unregister;
+
 		found = true;
+
+		/*
+		 * IT8705F may respond on both SIO addresses.
+		 * Stop probing after finding one.
+		 */
+		if (sio_data.type == it87)
+			break;
 	}
 
 	if (!found) {
diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c
index 2e1948699114..4c1770920d29 100644
--- a/drivers/hwmon/lm63.c
+++ b/drivers/hwmon/lm63.c
@@ -46,6 +46,7 @@
 #include <linux/hwmon.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
 
@@ -1115,6 +1116,10 @@ static int lm63_probe(struct i2c_client *client,
 	mutex_init(&data->update_lock);
 
 	/* Set the device type */
+	if (client->dev.of_node)
+		data->kind = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		data->kind = id->driver_data;
 	data->kind = id->driver_data;
 	if (data->kind == lm64)
 		data->temp2_offset = 16000;
@@ -1149,10 +1154,28 @@ static const struct i2c_device_id lm63_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm63_id);
 
+static const struct of_device_id lm63_of_match[] = {
+	{
+		.compatible = "national,lm63",
+		.data = (void *)lm63
+	},
+	{
+		.compatible = "national,lm64",
+		.data = (void *)lm64
+	},
+	{
+		.compatible = "national,lm96163",
+		.data = (void *)lm96163
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, lm63_of_match);
+
 static struct i2c_driver lm63_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "lm63",
+		.of_match_table = of_match_ptr(lm63_of_match),
 	},
 	.probe		= lm63_probe,
 	.id_table	= lm63_id,
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index eff3b24d8473..005ffb5ffa92 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -26,6 +26,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
+#include <linux/of_device.h>
 #include <linux/of.h>
 #include <linux/regmap.h>
 #include "lm75.h"
@@ -273,7 +274,12 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	int status, err;
 	u8 set_mask, clr_mask;
 	int new;
-	enum lm75_type kind = id->driver_data;
+	enum lm75_type kind;
+
+	if (client->dev.of_node)
+		kind = (enum lm75_type)of_device_get_match_data(&client->dev);
+	else
+		kind = id->driver_data;
 
 	if (!i2c_check_functionality(client->adapter,
 			I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA))
@@ -424,6 +430,95 @@ static const struct i2c_device_id lm75_ids[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm75_ids);
 
+static const struct of_device_id lm75_of_match[] = {
+	{
+		.compatible = "adi,adt75",
+		.data = (void *)adt75
+	},
+	{
+		.compatible = "dallas,ds1775",
+		.data = (void *)ds1775
+	},
+	{
+		.compatible = "dallas,ds75",
+		.data = (void *)ds75
+	},
+	{
+		.compatible = "dallas,ds7505",
+		.data = (void *)ds7505
+	},
+	{
+		.compatible = "gmt,g751",
+		.data = (void *)g751
+	},
+	{
+		.compatible = "national,lm75",
+		.data = (void *)lm75
+	},
+	{
+		.compatible = "national,lm75a",
+		.data = (void *)lm75a
+	},
+	{
+		.compatible = "national,lm75b",
+		.data = (void *)lm75b
+	},
+	{
+		.compatible = "maxim,max6625",
+		.data = (void *)max6625
+	},
+	{
+		.compatible = "maxim,max6626",
+		.data = (void *)max6626
+	},
+	{
+		.compatible = "maxim,mcp980x",
+		.data = (void *)mcp980x
+	},
+	{
+		.compatible = "st,stds75",
+		.data = (void *)stds75
+	},
+	{
+		.compatible = "microchip,tcn75",
+		.data = (void *)tcn75
+	},
+	{
+		.compatible = "ti,tmp100",
+		.data = (void *)tmp100
+	},
+	{
+		.compatible = "ti,tmp101",
+		.data = (void *)tmp101
+	},
+	{
+		.compatible = "ti,tmp105",
+		.data = (void *)tmp105
+	},
+	{
+		.compatible = "ti,tmp112",
+		.data = (void *)tmp112
+	},
+	{
+		.compatible = "ti,tmp175",
+		.data = (void *)tmp175
+	},
+	{
+		.compatible = "ti,tmp275",
+		.data = (void *)tmp275
+	},
+	{
+		.compatible = "ti,tmp75",
+		.data = (void *)tmp75
+	},
+	{
+		.compatible = "ti,tmp75c",
+		.data = (void *)tmp75c
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, lm75_of_match);
+
 #define LM75A_ID 0xA1
 
 /* Return 0 if detection is successful, -ENODEV otherwise */
@@ -560,6 +655,7 @@ static struct i2c_driver lm75_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "lm75",
+		.of_match_table = of_match_ptr(lm75_of_match),
 		.pm	= LM75_DEV_PM_OPS,
 	},
 	.probe		= lm75_probe,
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index 691469ffa24e..0a325878e8f5 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -25,6 +25,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/jiffies.h>
@@ -1552,7 +1553,10 @@ static int lm85_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		return -ENOMEM;
 
 	data->client = client;
-	data->type = id->driver_data;
+	if (client->dev.of_node)
+		data->type = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		data->type = id->driver_data;
 	mutex_init(&data->update_lock);
 
 	/* Fill in the chip specific driver values */
@@ -1623,10 +1627,60 @@ static const struct i2c_device_id lm85_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm85_id);
 
+static const struct of_device_id lm85_of_match[] = {
+	{
+		.compatible = "adi,adm1027",
+		.data = (void *)adm1027
+	},
+	{
+		.compatible = "adi,adt7463",
+		.data = (void *)adt7463
+	},
+	{
+		.compatible = "adi,adt7468",
+		.data = (void *)adt7468
+	},
+	{
+		.compatible = "national,lm85",
+		.data = (void *)lm85
+	},
+	{
+		.compatible = "national,lm85b",
+		.data = (void *)lm85
+	},
+	{
+		.compatible = "national,lm85c",
+		.data = (void *)lm85
+	},
+	{
+		.compatible = "smsc,emc6d100",
+		.data = (void *)emc6d100
+	},
+	{
+		.compatible = "smsc,emc6d101",
+		.data = (void *)emc6d100
+	},
+	{
+		.compatible = "smsc,emc6d102",
+		.data = (void *)emc6d102
+	},
+	{
+		.compatible = "smsc,emc6d103",
+		.data = (void *)emc6d103
+	},
+	{
+		.compatible = "smsc,emc6d103s",
+		.data = (void *)emc6d103s
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, lm85_of_match);
+
 static struct i2c_driver lm85_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name   = "lm85",
+		.of_match_table = of_match_ptr(lm85_of_match),
 	},
 	.probe		= lm85_probe,
 	.id_table	= lm85_id,
diff --git a/drivers/hwmon/lm87.c b/drivers/hwmon/lm87.c
index e06faf9d3f0f..b48d30760388 100644
--- a/drivers/hwmon/lm87.c
+++ b/drivers/hwmon/lm87.c
@@ -66,6 +66,7 @@
 #include <linux/hwmon-vid.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/regulator/consumer.h>
 
 /*
  * Addresses to scan
@@ -74,8 +75,6 @@
 
 static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, I2C_CLIENT_END };
 
-enum chips { lm87, adm1024 };
-
 /*
  * The LM87 registers
  */
@@ -855,8 +854,26 @@ static int lm87_init_client(struct i2c_client *client)
 {
 	struct lm87_data *data = i2c_get_clientdata(client);
 	int rc;
-
-	if (dev_get_platdata(&client->dev)) {
+	struct device_node *of_node = client->dev.of_node;
+	u8 val = 0;
+	struct regulator *vcc = NULL;
+
+	if (of_node) {
+		if (of_property_read_bool(of_node, "has-temp3"))
+			val |= CHAN_TEMP3;
+		if (of_property_read_bool(of_node, "has-in6"))
+			val |= CHAN_NO_FAN(0);
+		if (of_property_read_bool(of_node, "has-in7"))
+			val |= CHAN_NO_FAN(1);
+		vcc = devm_regulator_get_optional(&client->dev, "vcc");
+		if (!IS_ERR(vcc)) {
+			if (regulator_get_voltage(vcc) == 5000000)
+				val |= CHAN_VCC_5V;
+		}
+		data->channel = val;
+		lm87_write_value(client,
+				LM87_REG_CHANNEL_MODE, data->channel);
+	} else if (dev_get_platdata(&client->dev)) {
 		data->channel = *(u8 *)dev_get_platdata(&client->dev);
 		lm87_write_value(client,
 				 LM87_REG_CHANNEL_MODE, data->channel);
@@ -962,16 +979,24 @@ static int lm87_probe(struct i2c_client *client, const struct i2c_device_id *id)
  */
 
 static const struct i2c_device_id lm87_id[] = {
-	{ "lm87", lm87 },
-	{ "adm1024", adm1024 },
+	{ "lm87", 0 },
+	{ "adm1024", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, lm87_id);
 
+static const struct of_device_id lm87_of_match[] = {
+	{ .compatible = "ti,lm87" },
+	{ .compatible = "adi,adm1024" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, lm87_of_match);
+
 static struct i2c_driver lm87_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "lm87",
+		.of_match_table = lm87_of_match,
 	},
 	.probe		= lm87_probe,
 	.id_table	= lm87_id,
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index aff5297bc2bc..c2f411c290bf 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -92,6 +92,7 @@
 #include <linux/hwmon.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/sysfs.h>
 #include <linux/interrupt.h>
 #include <linux/regulator/consumer.h>
@@ -235,6 +236,99 @@ static const struct i2c_device_id lm90_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm90_id);
 
+static const struct of_device_id lm90_of_match[] = {
+	{
+		.compatible = "adi,adm1032",
+		.data = (void *)adm1032
+	},
+	{
+		.compatible = "adi,adt7461",
+		.data = (void *)adt7461
+	},
+	{
+		.compatible = "adi,adt7461a",
+		.data = (void *)adt7461
+	},
+	{
+		.compatible = "gmt,g781",
+		.data = (void *)g781
+	},
+	{
+		.compatible = "national,lm90",
+		.data = (void *)lm90
+	},
+	{
+		.compatible = "national,lm86",
+		.data = (void *)lm86
+	},
+	{
+		.compatible = "national,lm89",
+		.data = (void *)lm86
+	},
+	{
+		.compatible = "national,lm99",
+		.data = (void *)lm99
+	},
+	{
+		.compatible = "dallas,max6646",
+		.data = (void *)max6646
+	},
+	{
+		.compatible = "dallas,max6647",
+		.data = (void *)max6646
+	},
+	{
+		.compatible = "dallas,max6649",
+		.data = (void *)max6646
+	},
+	{
+		.compatible = "dallas,max6657",
+		.data = (void *)max6657
+	},
+	{
+		.compatible = "dallas,max6658",
+		.data = (void *)max6657
+	},
+	{
+		.compatible = "dallas,max6659",
+		.data = (void *)max6659
+	},
+	{
+		.compatible = "dallas,max6680",
+		.data = (void *)max6680
+	},
+	{
+		.compatible = "dallas,max6681",
+		.data = (void *)max6680
+	},
+	{
+		.compatible = "dallas,max6695",
+		.data = (void *)max6696
+	},
+	{
+		.compatible = "dallas,max6696",
+		.data = (void *)max6696
+	},
+	{
+		.compatible = "onnn,nct1008",
+		.data = (void *)adt7461
+	},
+	{
+		.compatible = "winbond,w83l771",
+		.data = (void *)w83l771
+	},
+	{
+		.compatible = "nxp,sa56004",
+		.data = (void *)sa56004
+	},
+	{
+		.compatible = "ti,tmp451",
+		.data = (void *)tmp451
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, lm90_of_match);
+
 /*
  * chip type specific parameters
  */
@@ -1677,7 +1771,10 @@ static int lm90_probe(struct i2c_client *client,
 	mutex_init(&data->update_lock);
 
 	/* Set the device type */
-	data->kind = id->driver_data;
+	if (client->dev.of_node)
+		data->kind = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		data->kind = id->driver_data;
 	if (data->kind == adm1032) {
 		if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE))
 			client->flags &= ~I2C_CLIENT_PEC;
@@ -1816,6 +1913,7 @@ static struct i2c_driver lm90_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "lm90",
+		.of_match_table = of_match_ptr(lm90_of_match),
 	},
 	.probe		= lm90_probe,
 	.alert		= lm90_alert,
diff --git a/drivers/hwmon/lm95245.c b/drivers/hwmon/lm95245.c
index a3bfd88752ca..27cb06d65594 100644
--- a/drivers/hwmon/lm95245.c
+++ b/drivers/hwmon/lm95245.c
@@ -622,10 +622,18 @@ static const struct i2c_device_id lm95245_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm95245_id);
 
+static const struct of_device_id lm95245_of_match[] = {
+	{ .compatible = "national,lm95235" },
+	{ .compatible = "national,lm95245" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, lm95245_of_match);
+
 static struct i2c_driver lm95245_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "lm95245",
+		.of_match_table = of_match_ptr(lm95245_of_match),
 	},
 	.probe		= lm95245_probe,
 	.id_table	= lm95245_id,
diff --git a/drivers/hwmon/max31790.c b/drivers/hwmon/max31790.c
index c1b9275978f9..281491cca510 100644
--- a/drivers/hwmon/max31790.c
+++ b/drivers/hwmon/max31790.c
@@ -311,7 +311,7 @@ static int max31790_write_pwm(struct device *dev, u32 attr, int channel,
 		data->pwm[channel] = val << 8;
 		err = i2c_smbus_write_word_swapped(client,
 						   MAX31790_REG_PWMOUT(channel),
-						   val);
+						   data->pwm[channel]);
 		break;
 	case hwmon_pwm_enable:
 		fan_config = data->fan_config[channel];
diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
index f03a71722849..221fd1492057 100644
--- a/drivers/hwmon/max6697.c
+++ b/drivers/hwmon/max6697.c
@@ -24,6 +24,7 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/of.h>
 
 #include <linux/platform_data/max6697.h>
@@ -632,7 +633,10 @@ static int max6697_probe(struct i2c_client *client,
 	if (!data)
 		return -ENOMEM;
 
-	data->type = id->driver_data;
+	if (client->dev.of_node)
+		data->type = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		data->type = id->driver_data;
 	data->chip = &max6697_chip_data[data->type];
 	data->client = client;
 	mutex_init(&data->update_lock);
@@ -662,10 +666,56 @@ static const struct i2c_device_id max6697_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, max6697_id);
 
+static const struct of_device_id max6697_of_match[] = {
+	{
+		.compatible = "maxim,max6581",
+		.data = (void *)max6581
+	},
+	{
+		.compatible = "maxim,max6602",
+		.data = (void *)max6602
+	},
+	{
+		.compatible = "maxim,max6622",
+		.data = (void *)max6622
+	},
+	{
+		.compatible = "maxim,max6636",
+		.data = (void *)max6636
+	},
+	{
+		.compatible = "maxim,max6689",
+		.data = (void *)max6689
+	},
+	{
+		.compatible = "maxim,max6693",
+		.data = (void *)max6693
+	},
+	{
+		.compatible = "maxim,max6694",
+		.data = (void *)max6694
+	},
+	{
+		.compatible = "maxim,max6697",
+		.data = (void *)max6697
+	},
+	{
+		.compatible = "maxim,max6698",
+		.data = (void *)max6698
+	},
+	{
+		.compatible = "maxim,max6699",
+		.data = (void *)max6699
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, max6697_of_match);
+
 static struct i2c_driver max6697_driver = {
 	.class = I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "max6697",
+		.of_match_table = of_match_ptr(max6697_of_match),
 	},
 	.probe = max6697_probe,
 	.id_table = max6697_id,
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index 4ab5293c7bf0..00d6995af4c2 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -101,8 +101,8 @@ static const struct coefficients adm1075_coefficients[] = {
 	[0] = { 27169, 0, -1 },		/* voltage */
 	[1] = { 806, 20475, -1 },	/* current, irange25 */
 	[2] = { 404, 20475, -1 },	/* current, irange50 */
-	[3] = { 0, -1, 8549 },		/* power, irange25 */
-	[4] = { 0, -1, 4279 },		/* power, irange50 */
+	[3] = { 8549, 0, -1 },		/* power, irange25 */
+	[4] = { 4279, 0, -1 },		/* power, irange50 */
 };
 
 static const struct coefficients adm1275_coefficients[] = {
diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c
index 3e3aa950277f..3518f0c08934 100644
--- a/drivers/hwmon/pmbus/ucd9000.c
+++ b/drivers/hwmon/pmbus/ucd9000.c
@@ -21,6 +21,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -119,6 +120,35 @@ static const struct i2c_device_id ucd9000_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ucd9000_id);
 
+static const struct of_device_id ucd9000_of_match[] = {
+	{
+		.compatible = "ti,ucd9000",
+		.data = (void *)ucd9000
+	},
+	{
+		.compatible = "ti,ucd90120",
+		.data = (void *)ucd90120
+	},
+	{
+		.compatible = "ti,ucd90124",
+		.data = (void *)ucd90124
+	},
+	{
+		.compatible = "ti,ucd90160",
+		.data = (void *)ucd90160
+	},
+	{
+		.compatible = "ti,ucd9090",
+		.data = (void *)ucd9090
+	},
+	{
+		.compatible = "ti,ucd90910",
+		.data = (void *)ucd90910
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ucd9000_of_match);
+
 static int ucd9000_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -126,6 +156,7 @@ static int ucd9000_probe(struct i2c_client *client,
 	struct ucd9000_data *data;
 	struct pmbus_driver_info *info;
 	const struct i2c_device_id *mid;
+	enum chips chip;
 	int i, ret;
 
 	if (!i2c_check_functionality(client->adapter,
@@ -151,7 +182,12 @@ static int ucd9000_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
-	if (id->driver_data != ucd9000 && id->driver_data != mid->driver_data)
+	if (client->dev.of_node)
+		chip = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		chip = id->driver_data;
+
+	if (chip != ucd9000 && chip != mid->driver_data)
 		dev_notice(&client->dev,
 			   "Device mismatch: Configured %s, detected %s\n",
 			   id->name, mid->name);
@@ -234,6 +270,7 @@ static int ucd9000_probe(struct i2c_client *client,
 static struct i2c_driver ucd9000_driver = {
 	.driver = {
 		.name = "ucd9000",
+		.of_match_table = of_match_ptr(ucd9000_of_match),
 	},
 	.probe = ucd9000_probe,
 	.remove = pmbus_do_remove,
diff --git a/drivers/hwmon/pmbus/ucd9200.c b/drivers/hwmon/pmbus/ucd9200.c
index 033d6aca47d3..a8712c5ded4e 100644
--- a/drivers/hwmon/pmbus/ucd9200.c
+++ b/drivers/hwmon/pmbus/ucd9200.c
@@ -20,6 +20,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -46,12 +47,50 @@ static const struct i2c_device_id ucd9200_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ucd9200_id);
 
+static const struct of_device_id ucd9200_of_match[] = {
+	{
+		.compatible = "ti,cd9200",
+		.data = (void *)ucd9200
+	},
+	{
+		.compatible = "ti,cd9220",
+		.data = (void *)ucd9220
+	},
+	{
+		.compatible = "ti,cd9222",
+		.data = (void *)ucd9222
+	},
+	{
+		.compatible = "ti,cd9224",
+		.data = (void *)ucd9224
+	},
+	{
+		.compatible = "ti,cd9240",
+		.data = (void *)ucd9240
+	},
+	{
+		.compatible = "ti,cd9244",
+		.data = (void *)ucd9244
+	},
+	{
+		.compatible = "ti,cd9246",
+		.data = (void *)ucd9246
+	},
+	{
+		.compatible = "ti,cd9248",
+		.data = (void *)ucd9248
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ucd9200_of_match);
+
 static int ucd9200_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
 	u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1];
 	struct pmbus_driver_info *info;
 	const struct i2c_device_id *mid;
+	enum chips chip;
 	int i, j, ret;
 
 	if (!i2c_check_functionality(client->adapter,
@@ -76,7 +115,13 @@ static int ucd9200_probe(struct i2c_client *client,
 		dev_err(&client->dev, "Unsupported device\n");
 		return -ENODEV;
 	}
-	if (id->driver_data != ucd9200 && id->driver_data != mid->driver_data)
+
+	if (client->dev.of_node)
+		chip = (enum chips)of_device_get_match_data(&client->dev);
+	else
+		chip = id->driver_data;
+
+	if (chip != ucd9200 && chip != mid->driver_data)
 		dev_notice(&client->dev,
 			   "Device mismatch: Configured %s, detected %s\n",
 			   id->name, mid->name);
@@ -167,6 +212,7 @@ static int ucd9200_probe(struct i2c_client *client,
 static struct i2c_driver ucd9200_driver = {
 	.driver = {
 		.name = "ucd9200",
+		.of_match_table = of_match_ptr(ucd9200_of_match),
 	},
 	.probe = ucd9200_probe,
 	.remove = pmbus_do_remove,
diff --git a/drivers/hwmon/stts751.c b/drivers/hwmon/stts751.c
index 55450680fb58..d56251d6eec2 100644
--- a/drivers/hwmon/stts751.c
+++ b/drivers/hwmon/stts751.c
@@ -85,6 +85,12 @@ static const struct i2c_device_id stts751_id[] = {
 	{ }
 };
 
+static const struct of_device_id stts751_of_match[] = {
+	{ .compatible = "stts751" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, stts751_of_match);
+
 struct stts751_priv {
 	struct device *dev;
 	struct i2c_client *client;
@@ -819,6 +825,7 @@ static struct i2c_driver stts751_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= DEVNAME,
+		.of_match_table = of_match_ptr(stts751_of_match),
 	},
 	.probe		= stts751_probe,
 	.id_table	= stts751_id,
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 36bba2a816a4..5eafbaada795 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -323,8 +323,15 @@ static const struct i2c_device_id tmp102_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tmp102_id);
 
+static const struct of_device_id tmp102_of_match[] = {
+	{ .compatible = "ti,tmp102" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tmp102_of_match);
+
 static struct i2c_driver tmp102_driver = {
 	.driver.name	= DRIVER_NAME,
+	.driver.of_match_table = of_match_ptr(tmp102_of_match),
 	.driver.pm	= &tmp102_dev_pm_ops,
 	.probe		= tmp102_probe,
 	.id_table	= tmp102_id,
diff --git a/drivers/hwmon/tmp103.c b/drivers/hwmon/tmp103.c
index ad571ec795a3..7f85b14544df 100644
--- a/drivers/hwmon/tmp103.c
+++ b/drivers/hwmon/tmp103.c
@@ -150,8 +150,7 @@ static int tmp103_probe(struct i2c_client *client,
 	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
-#ifdef CONFIG_PM
-static int tmp103_suspend(struct device *dev)
+static int __maybe_unused tmp103_suspend(struct device *dev)
 {
 	struct regmap *regmap = dev_get_drvdata(dev);
 
@@ -159,7 +158,7 @@ static int tmp103_suspend(struct device *dev)
 				  TMP103_CONF_SD_MASK, 0);
 }
 
-static int tmp103_resume(struct device *dev)
+static int __maybe_unused tmp103_resume(struct device *dev)
 {
 	struct regmap *regmap = dev_get_drvdata(dev);
 
@@ -167,15 +166,7 @@ static int tmp103_resume(struct device *dev)
 				  TMP103_CONF_SD_MASK, TMP103_CONF_SD);
 }
 
-static const struct dev_pm_ops tmp103_dev_pm_ops = {
-	.suspend	= tmp103_suspend,
-	.resume		= tmp103_resume,
-};
-
-#define TMP103_DEV_PM_OPS (&tmp103_dev_pm_ops)
-#else
-#define	TMP103_DEV_PM_OPS NULL
-#endif /* CONFIG_PM */
+static SIMPLE_DEV_PM_OPS(tmp103_dev_pm_ops, tmp103_suspend, tmp103_resume);
 
 static const struct i2c_device_id tmp103_id[] = {
 	{ "tmp103", 0 },
@@ -183,10 +174,17 @@ static const struct i2c_device_id tmp103_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tmp103_id);
 
+static const struct of_device_id tmp103_of_match[] = {
+	{ .compatible = "ti,tmp103" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tmp103_of_match);
+
 static struct i2c_driver tmp103_driver = {
 	.driver = {
 		.name	= "tmp103",
-		.pm	= TMP103_DEV_PM_OPS,
+		.of_match_table = of_match_ptr(tmp103_of_match),
+		.pm	= &tmp103_dev_pm_ops,
 	},
 	.probe		= tmp103_probe,
 	.id_table	= tmp103_id,
diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c
index bfb98b96c781..e36399213324 100644
--- a/drivers/hwmon/tmp421.c
+++ b/drivers/hwmon/tmp421.c
@@ -29,6 +29,7 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/sysfs.h>
 
 /* Addresses to scan */
@@ -69,6 +70,31 @@ static const struct i2c_device_id tmp421_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tmp421_id);
 
+static const struct of_device_id tmp421_of_match[] = {
+	{
+		.compatible = "ti,tmp421",
+		.data = (void *)2
+	},
+	{
+		.compatible = "ti,tmp422",
+		.data = (void *)3
+	},
+	{
+		.compatible = "ti,tmp423",
+		.data = (void *)4
+	},
+	{
+		.compatible = "ti,tmp441",
+		.data = (void *)2
+	},
+	{
+		.compatible = "ti,tmp422",
+		.data = (void *)3
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tmp421_of_match);
+
 struct tmp421_data {
 	struct i2c_client *client;
 	struct mutex update_lock;
@@ -78,7 +104,7 @@ struct tmp421_data {
 	struct hwmon_chip_info chip;
 	char valid;
 	unsigned long last_updated;
-	int channels;
+	unsigned long channels;
 	u8 config;
 	s16 temp[4];
 };
@@ -272,7 +298,11 @@ static int tmp421_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	mutex_init(&data->update_lock);
-	data->channels = id->driver_data;
+	if (client->dev.of_node)
+		data->channels = (unsigned long)
+			of_device_get_match_data(&client->dev);
+	else
+		data->channels = id->driver_data;
 	data->client = client;
 
 	err = tmp421_init_client(client);
@@ -301,6 +331,7 @@ static struct i2c_driver tmp421_driver = {
 	.class = I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "tmp421",
+		.of_match_table = of_match_ptr(tmp421_of_match),
 	},
 	.probe = tmp421_probe,
 	.id_table = tmp421_id,
diff --git a/drivers/hwmon/twl4030-madc-hwmon.c b/drivers/hwmon/twl4030-madc-hwmon.c
deleted file mode 100644
index b5caf7fdb487..000000000000
--- a/drivers/hwmon/twl4030-madc-hwmon.c
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- *
- * TWL4030 MADC Hwmon driver-This driver monitors the real time
- * conversion of analog signals like battery temperature,
- * battery type, battery level etc. User can ask for the conversion on a
- * particular channel using the sysfs nodes.
- *
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
- * J Keerthy <j-keerthy@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- *
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/i2c/twl.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/i2c/twl4030-madc.h>
-#include <linux/hwmon.h>
-#include <linux/hwmon-sysfs.h>
-#include <linux/stddef.h>
-#include <linux/sysfs.h>
-#include <linux/err.h>
-#include <linux/types.h>
-
-/*
- * sysfs hook function
- */
-static ssize_t madc_read(struct device *dev,
-			 struct device_attribute *devattr, char *buf)
-{
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct twl4030_madc_request req = {
-		.channels = 1 << attr->index,
-		.method = TWL4030_MADC_SW2,
-		.type = TWL4030_MADC_WAIT,
-	};
-	long val;
-
-	val = twl4030_madc_conversion(&req);
-	if (val < 0)
-		return val;
-
-	return sprintf(buf, "%d\n", req.rbuf[attr->index]);
-}
-
-/* sysfs nodes to read individual channels from user side */
-static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, madc_read, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, madc_read, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, madc_read, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_input, S_IRUGO, madc_read, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_input, S_IRUGO, madc_read, NULL, 4);
-static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, madc_read, NULL, 5);
-static SENSOR_DEVICE_ATTR(in6_input, S_IRUGO, madc_read, NULL, 6);
-static SENSOR_DEVICE_ATTR(in7_input, S_IRUGO, madc_read, NULL, 7);
-static SENSOR_DEVICE_ATTR(in8_input, S_IRUGO, madc_read, NULL, 8);
-static SENSOR_DEVICE_ATTR(in9_input, S_IRUGO, madc_read, NULL, 9);
-static SENSOR_DEVICE_ATTR(curr10_input, S_IRUGO, madc_read, NULL, 10);
-static SENSOR_DEVICE_ATTR(in11_input, S_IRUGO, madc_read, NULL, 11);
-static SENSOR_DEVICE_ATTR(in12_input, S_IRUGO, madc_read, NULL, 12);
-static SENSOR_DEVICE_ATTR(in15_input, S_IRUGO, madc_read, NULL, 15);
-
-static struct attribute *twl4030_madc_attrs[] = {
-	&sensor_dev_attr_in0_input.dev_attr.attr,
-	&sensor_dev_attr_temp1_input.dev_attr.attr,
-	&sensor_dev_attr_in2_input.dev_attr.attr,
-	&sensor_dev_attr_in3_input.dev_attr.attr,
-	&sensor_dev_attr_in4_input.dev_attr.attr,
-	&sensor_dev_attr_in5_input.dev_attr.attr,
-	&sensor_dev_attr_in6_input.dev_attr.attr,
-	&sensor_dev_attr_in7_input.dev_attr.attr,
-	&sensor_dev_attr_in8_input.dev_attr.attr,
-	&sensor_dev_attr_in9_input.dev_attr.attr,
-	&sensor_dev_attr_curr10_input.dev_attr.attr,
-	&sensor_dev_attr_in11_input.dev_attr.attr,
-	&sensor_dev_attr_in12_input.dev_attr.attr,
-	&sensor_dev_attr_in15_input.dev_attr.attr,
-	NULL
-};
-ATTRIBUTE_GROUPS(twl4030_madc);
-
-static int twl4030_madc_hwmon_probe(struct platform_device *pdev)
-{
-	struct device *hwmon;
-
-	hwmon = devm_hwmon_device_register_with_groups(&pdev->dev,
-						       "twl4030_madc", NULL,
-						       twl4030_madc_groups);
-	return PTR_ERR_OR_ZERO(hwmon);
-}
-
-static struct platform_driver twl4030_madc_hwmon_driver = {
-	.probe = twl4030_madc_hwmon_probe,
-	.driver = {
-		   .name = "twl4030_madc_hwmon",
-		   },
-};
-
-module_platform_driver(twl4030_madc_hwmon_driver);
-
-MODULE_DESCRIPTION("TWL4030 ADC Hwmon driver");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("J Keerthy");
-MODULE_ALIAS("platform:twl4030_madc_hwmon");
diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
index ab346ed142de..ad68b6d9ff17 100644
--- a/drivers/hwmon/w83627ehf.c
+++ b/drivers/hwmon/w83627ehf.c
@@ -135,11 +135,16 @@ superio_select(int ioreg, int ld)
 	outb(ld, ioreg + 1);
 }
 
-static inline void
+static inline int
 superio_enter(int ioreg)
 {
+	if (!request_muxed_region(ioreg, 2, DRVNAME))
+		return -EBUSY;
+
 	outb(0x87, ioreg);
 	outb(0x87, ioreg);
+
+	return 0;
 }
 
 static inline void
@@ -148,6 +153,7 @@ superio_exit(int ioreg)
 	outb(0xaa, ioreg);
 	outb(0x02, ioreg);
 	outb(0x02, ioreg + 1);
+	release_region(ioreg, 2);
 }
 
 /*
@@ -1970,8 +1976,6 @@ w83627ehf_check_fan_inputs(const struct w83627ehf_sio_data *sio_data,
 		return;
 	}
 
-	superio_enter(sio_data->sioreg);
-
 	/* fan4 and fan5 share some pins with the GPIO and serial flash */
 	if (sio_data->kind == nct6775) {
 		/* On NCT6775, fan4 shares pins with the fdc interface */
@@ -2013,8 +2017,6 @@ w83627ehf_check_fan_inputs(const struct w83627ehf_sio_data *sio_data,
 		fan4min = fan4pin;
 	}
 
-	superio_exit(sio_data->sioreg);
-
 	data->has_fan = data->has_fan_min = 0x03; /* fan1 and fan2 */
 	data->has_fan |= (fan3pin << 2);
 	data->has_fan_min |= (fan3pin << 2);
@@ -2352,7 +2354,11 @@ static int w83627ehf_probe(struct platform_device *pdev)
 	w83627ehf_init_device(data, sio_data->kind);
 
 	data->vrm = vid_which_vrm();
-	superio_enter(sio_data->sioreg);
+
+	err = superio_enter(sio_data->sioreg);
+	if (err)
+		goto exit_release;
+
 	/* Read VID value */
 	if (sio_data->kind == w83667hg || sio_data->kind == w83667hg_b ||
 	    sio_data->kind == nct6775 || sio_data->kind == nct6776) {
@@ -2364,8 +2370,10 @@ static int w83627ehf_probe(struct platform_device *pdev)
 		superio_select(sio_data->sioreg, W83667HG_LD_VID);
 		data->vid = superio_inb(sio_data->sioreg, 0xe3);
 		err = device_create_file(dev, &dev_attr_cpu0_vid);
-		if (err)
+		if (err) {
+			superio_exit(sio_data->sioreg);
 			goto exit_release;
+		}
 	} else if (sio_data->kind != w83627uhg) {
 		superio_select(sio_data->sioreg, W83627EHF_LD_HWM);
 		if (superio_inb(sio_data->sioreg, SIO_REG_VID_CTRL) & 0x80) {
@@ -2401,8 +2409,10 @@ static int w83627ehf_probe(struct platform_device *pdev)
 				data->vid &= 0x3f;
 
 			err = device_create_file(dev, &dev_attr_cpu0_vid);
-			if (err)
+			if (err) {
+				superio_exit(sio_data->sioreg);
 				goto exit_release;
+			}
 		} else {
 			dev_info(dev,
 				 "VID pins in output mode, CPU VID not available\n");
@@ -2424,10 +2434,10 @@ static int w83627ehf_probe(struct platform_device *pdev)
 		pr_info("Enabled fan debounce for chip %s\n", data->name);
 	}
 
-	superio_exit(sio_data->sioreg);
-
 	w83627ehf_check_fan_inputs(sio_data, data);
 
+	superio_exit(sio_data->sioreg);
+
 	/* Read fan clock dividers immediately */
 	w83627ehf_update_fan_div_common(dev, data);
 
@@ -2712,8 +2722,11 @@ static int __init w83627ehf_find(int sioaddr, unsigned short *addr,
 
 	u16 val;
 	const char *sio_name;
+	int err;
 
-	superio_enter(sioaddr);
+	err = superio_enter(sioaddr);
+	if (err)
+		return err;
 
 	if (force_id)
 		val = force_id;
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index d7325c6534ad..979ea6ec7902 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -321,7 +321,7 @@ static int etb_set_buffer(struct coresight_device *csdev,
 
 static unsigned long etb_reset_buffer(struct coresight_device *csdev,
 				      struct perf_output_handle *handle,
-				      void *sink_config, bool *lost)
+				      void *sink_config)
 {
 	unsigned long size = 0;
 	struct cs_buffers *buf = sink_config;
@@ -343,7 +343,6 @@ static unsigned long etb_reset_buffer(struct coresight_device *csdev,
 		 * resetting parameters here and squaring off with the ring
 		 * buffer API in the tracer PMU is fine.
 		 */
-		*lost = !!local_xchg(&buf->lost, 0);
 		size = local_xchg(&buf->data_size, 0);
 	}
 
@@ -385,7 +384,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 			(unsigned long)write_ptr);
 
 		write_ptr &= ~(ETB_FRAME_SIZE_WORDS - 1);
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	}
 
 	/*
@@ -396,7 +395,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 	 */
 	status = readl_relaxed(drvdata->base + ETB_STATUS_REG);
 	if (status & ETB_STATUS_RAM_FULL) {
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 		to_read = capacity;
 		read_ptr = write_ptr;
 	} else {
@@ -429,7 +428,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 		if (read_ptr > (drvdata->buffer_depth - 1))
 			read_ptr -= drvdata->buffer_depth;
 		/* let the decoder know we've skipped ahead */
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	}
 
 	/* finally tell HW where we want to start reading from */
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 26cfac3e6de7..288a423c1b27 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -302,7 +302,8 @@ out:
 	return;
 
 fail_end_stop:
-	perf_aux_output_end(handle, 0, true);
+	perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+	perf_aux_output_end(handle, 0);
 fail:
 	event->hw.state = PERF_HES_STOPPED;
 	goto out;
@@ -310,7 +311,6 @@ fail:
 
 static void etm_event_stop(struct perf_event *event, int mode)
 {
-	bool lost;
 	int cpu = smp_processor_id();
 	unsigned long size;
 	struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
@@ -348,10 +348,9 @@ static void etm_event_stop(struct perf_event *event, int mode)
 			return;
 
 		size = sink_ops(sink)->reset_buffer(sink, handle,
-						    event_data->snk_config,
-						    &lost);
+						    event_data->snk_config);
 
-		perf_aux_output_end(handle, size, lost);
+		perf_aux_output_end(handle, size);
 	}
 
 	/* Disabling the path make its elements available to other sessions */
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index ef9d8e93e3b2..5f662d82052c 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -76,7 +76,6 @@ enum cs_mode {
  * @nr_pages:	max number of pages granted to us
  * @offset:	offset within the current buffer
  * @data_size:	how much we collected in this run
- * @lost:	other than zero if we had a HW buffer wrap around
  * @snapshot:	is this run in snapshot mode
  * @data_pages:	a handle the ring buffer
  */
@@ -85,7 +84,6 @@ struct cs_buffers {
 	unsigned int		nr_pages;
 	unsigned long		offset;
 	local_t			data_size;
-	local_t			lost;
 	bool			snapshot;
 	void			**data_pages;
 };
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 1549436e2492..aec61a6d5c63 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -329,7 +329,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev,
 
 static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
 					  struct perf_output_handle *handle,
-					  void *sink_config, bool *lost)
+					  void *sink_config)
 {
 	long size = 0;
 	struct cs_buffers *buf = sink_config;
@@ -350,7 +350,6 @@ static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
 		 * resetting parameters here and squaring off with the ring
 		 * buffer API in the tracer PMU is fine.
 		 */
-		*lost = !!local_xchg(&buf->lost, 0);
 		size = local_xchg(&buf->data_size, 0);
 	}
 
@@ -389,7 +388,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 	 */
 	status = readl_relaxed(drvdata->base + TMC_STS);
 	if (status & TMC_STS_FULL) {
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 		to_read = drvdata->size;
 	} else {
 		to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size);
@@ -434,7 +433,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 			read_ptr -= drvdata->size;
 		/* Tell the HW */
 		writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
-		local_inc(&buf->lost);
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	}
 
 	cur = buf->cur;
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index cdd9b3b26195..7563eceeaaea 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -221,8 +221,10 @@ static int intel_th_output_activate(struct intel_th_device *thdev)
 	else
 		intel_th_trace_enable(thdev);
 
-	if (ret)
+	if (ret) {
 		pm_runtime_put(&thdev->dev);
+		module_put(thdrv->driver.owner);
+	}
 
 	return ret;
 }
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 0bba3842336e..590cf90dd21a 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -85,6 +85,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6),
 		.driver_data = (kernel_ulong_t)0,
 	},
+	{
+		/* Denverton */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x19e1),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
+		/* Gemini Lake */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e),
+		.driver_data = (kernel_ulong_t)0,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c
index 0652281662a8..78792b4d6437 100644
--- a/drivers/i2c/busses/i2c-brcmstb.c
+++ b/drivers/i2c/busses/i2c-brcmstb.c
@@ -465,6 +465,7 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 	u8 *tmp_buf;
 	int len = 0;
 	int xfersz = brcmstb_i2c_get_xfersz(dev);
+	u32 cond, cond_per_msg;
 
 	if (dev->is_suspended)
 		return -EBUSY;
@@ -481,10 +482,11 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 			pmsg->buf ? pmsg->buf[0] : '0', pmsg->len);
 
 		if (i < (num - 1) && (msgs[i + 1].flags & I2C_M_NOSTART))
-			brcmstb_set_i2c_start_stop(dev, ~(COND_START_STOP));
+			cond = ~COND_START_STOP;
 		else
-			brcmstb_set_i2c_start_stop(dev,
-						   COND_RESTART | COND_NOSTOP);
+			cond = COND_RESTART | COND_NOSTOP;
+
+		brcmstb_set_i2c_start_stop(dev, cond);
 
 		/* Send slave address */
 		if (!(pmsg->flags & I2C_M_NOSTART)) {
@@ -497,13 +499,24 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 			}
 		}
 
+		cond_per_msg = cond;
+
 		/* Perform data transfer */
 		while (len) {
 			bytes_to_xfer = min(len, xfersz);
 
-			if (len <= xfersz && i == (num - 1))
-				brcmstb_set_i2c_start_stop(dev,
-							   ~(COND_START_STOP));
+			if (len <= xfersz) {
+				if (i == (num - 1))
+					cond_per_msg = cond_per_msg &
+						~(COND_RESTART | COND_NOSTOP);
+				else
+					cond_per_msg = cond;
+			} else {
+				cond_per_msg = (cond_per_msg & ~COND_RESTART) |
+					COND_NOSTOP;
+			}
+
+			brcmstb_set_i2c_start_stop(dev, cond_per_msg);
 
 			rc = brcmstb_i2c_xfer_bsc_data(dev, tmp_buf,
 						       bytes_to_xfer, pmsg);
@@ -512,6 +525,8 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 
 			len -=  bytes_to_xfer;
 			tmp_buf += bytes_to_xfer;
+
+			cond_per_msg = COND_NOSTART | COND_NOSTOP;
 		}
 	}
 
diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index c1db3a5a340f..d9aaf1790e0e 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -88,6 +88,7 @@ struct dw_i2c_dev {
 	void __iomem		*base;
 	struct completion	cmd_complete;
 	struct clk		*clk;
+	struct reset_control	*rst;
 	u32			(*get_clk_rate_khz) (struct dw_i2c_dev *dev);
 	struct dw_pci_controller *controller;
 	int			cmd_err;
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 6ce431323125..79c4b4ea0539 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -38,6 +38,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
 #include <linux/io.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/platform_data/i2c-designware.h>
@@ -199,6 +200,14 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	dev->irq = irq;
 	platform_set_drvdata(pdev, dev);
 
+	dev->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(dev->rst)) {
+		if (PTR_ERR(dev->rst) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+	} else {
+		reset_control_deassert(dev->rst);
+	}
+
 	if (pdata) {
 		dev->clk_freq = pdata->i2c_scl_freq;
 	} else {
@@ -235,12 +244,13 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	    && dev->clk_freq != 1000000 && dev->clk_freq != 3400000) {
 		dev_err(&pdev->dev,
 			"Only 100kHz, 400kHz, 1MHz and 3.4MHz supported");
-		return -EINVAL;
+		r = -EINVAL;
+		goto exit_reset;
 	}
 
 	r = i2c_dw_eval_lock_support(dev);
 	if (r)
-		return r;
+		goto exit_reset;
 
 	dev->functionality = I2C_FUNC_10BIT_ADDR | DW_IC_DEFAULT_FUNCTIONALITY;
 
@@ -286,10 +296,18 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	}
 
 	r = i2c_dw_probe(dev);
-	if (r && !dev->pm_runtime_disabled)
-		pm_runtime_disable(&pdev->dev);
+	if (r)
+		goto exit_probe;
 
 	return r;
+
+exit_probe:
+	if (!dev->pm_runtime_disabled)
+		pm_runtime_disable(&pdev->dev);
+exit_reset:
+	if (!IS_ERR_OR_NULL(dev->rst))
+		reset_control_assert(dev->rst);
+	return r;
 }
 
 static int dw_i2c_plat_remove(struct platform_device *pdev)
@@ -306,6 +324,8 @@ static int dw_i2c_plat_remove(struct platform_device *pdev)
 	pm_runtime_put_sync(&pdev->dev);
 	if (!dev->pm_runtime_disabled)
 		pm_runtime_disable(&pdev->dev);
+	if (!IS_ERR_OR_NULL(dev->rst))
+		reset_control_assert(dev->rst);
 
 	return 0;
 }
diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index cbd93ce0661f..736a82472101 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -457,7 +457,6 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id)
 
 	int_status = readl(i2c->regs + HSI2C_INT_STATUS);
 	writel(int_status, i2c->regs + HSI2C_INT_STATUS);
-	trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
 
 	/* handle interrupt related to the transfer status */
 	if (i2c->variant->hw == HSI2C_EXYNOS7) {
@@ -482,11 +481,13 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id)
 			goto stop;
 		}
 
+		trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
 		if ((trans_status & HSI2C_MASTER_ST_MASK) == HSI2C_MASTER_ST_LOSE) {
 			i2c->state = -EAGAIN;
 			goto stop;
 		}
 	} else if (int_status & HSI2C_INT_I2C) {
+		trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
 		if (trans_status & HSI2C_NO_DEV_ACK) {
 			dev_dbg(i2c->dev, "No ACK from device\n");
 			i2c->state = -ENXIO;
diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index 2aa61bbbd307..73b97c71a484 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -175,7 +175,7 @@ static void meson_i2c_put_data(struct meson_i2c *i2c, char *buf, int len)
 		wdata1 |= *buf++ << ((i - 4) * 8);
 
 	writel(wdata0, i2c->regs + REG_TOK_WDATA0);
-	writel(wdata0, i2c->regs + REG_TOK_WDATA1);
+	writel(wdata1, i2c->regs + REG_TOK_WDATA1);
 
 	dev_dbg(i2c->dev, "%s: data %08x %08x len %d\n", __func__,
 		wdata0, wdata1, len);
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 4a7d9bc2142b..45d61714c81b 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -172,14 +172,6 @@ static const struct i2c_adapter_quirks mt6577_i2c_quirks = {
 	.max_comb_2nd_msg_len = 31,
 };
 
-static const struct i2c_adapter_quirks mt8173_i2c_quirks = {
-	.max_num_msgs = 65535,
-	.max_write_len = 65535,
-	.max_read_len = 65535,
-	.max_comb_1st_msg_len = 65535,
-	.max_comb_2nd_msg_len = 65535,
-};
-
 static const struct mtk_i2c_compatible mt6577_compat = {
 	.quirks = &mt6577_i2c_quirks,
 	.pmic_i2c = 0,
@@ -199,7 +191,6 @@ static const struct mtk_i2c_compatible mt6589_compat = {
 };
 
 static const struct mtk_i2c_compatible mt8173_compat = {
-	.quirks = &mt8173_i2c_quirks,
 	.pmic_i2c = 0,
 	.dcm = 1,
 	.auto_restart = 1,
diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c
index 8f11d347b3ec..c811af4c8d81 100644
--- a/drivers/i2c/busses/i2c-riic.c
+++ b/drivers/i2c/busses/i2c-riic.c
@@ -218,8 +218,12 @@ static irqreturn_t riic_tend_isr(int irq, void *data)
 	}
 
 	if (riic->is_last || riic->err) {
-		riic_clear_set_bit(riic, 0, ICIER_SPIE, RIIC_ICIER);
+		riic_clear_set_bit(riic, ICIER_TEIE, ICIER_SPIE, RIIC_ICIER);
 		writeb(ICCR2_SP, riic->base + RIIC_ICCR2);
+	} else {
+		/* Transfer is complete, but do not send STOP */
+		riic_clear_set_bit(riic, ICIER_TEIE, 0, RIIC_ICIER);
+		complete(&riic->msg_done);
 	}
 
 	return IRQ_HANDLED;
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 83768e85a919..2178266bca79 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -429,6 +429,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 	while (muxc->num_adapters) {
 		struct i2c_adapter *adap = muxc->adapter[--muxc->num_adapters];
 		struct i2c_mux_priv *priv = adap->algo_data;
+		struct device_node *np = adap->dev.of_node;
 
 		muxc->adapter[muxc->num_adapters] = NULL;
 
@@ -438,6 +439,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 
 		sysfs_remove_link(&priv->adap.dev.kobj, "mux_device");
 		i2c_del_adapter(adap);
+		of_node_put(np);
 		kfree(priv);
 	}
 }
diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c
index dfc1c0e37c40..ad31d21da316 100644
--- a/drivers/i2c/muxes/i2c-mux-pca954x.c
+++ b/drivers/i2c/muxes/i2c-mux-pca954x.c
@@ -35,7 +35,6 @@
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/acpi.h>
 #include <linux/device.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -117,6 +116,10 @@ static const struct chip_desc chips[] = {
 		.has_irq = 1,
 		.muxtype = pca954x_isswi,
 	},
+	[pca_9546] = {
+		.nchans = 4,
+		.muxtype = pca954x_isswi,
+	},
 	[pca_9547] = {
 		.nchans = 8,
 		.enable = 0x8,
@@ -134,28 +137,13 @@ static const struct i2c_device_id pca954x_id[] = {
 	{ "pca9543", pca_9543 },
 	{ "pca9544", pca_9544 },
 	{ "pca9545", pca_9545 },
-	{ "pca9546", pca_9545 },
+	{ "pca9546", pca_9546 },
 	{ "pca9547", pca_9547 },
 	{ "pca9548", pca_9548 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pca954x_id);
 
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id pca954x_acpi_ids[] = {
-	{ .id = "PCA9540", .driver_data = pca_9540 },
-	{ .id = "PCA9542", .driver_data = pca_9542 },
-	{ .id = "PCA9543", .driver_data = pca_9543 },
-	{ .id = "PCA9544", .driver_data = pca_9544 },
-	{ .id = "PCA9545", .driver_data = pca_9545 },
-	{ .id = "PCA9546", .driver_data = pca_9545 },
-	{ .id = "PCA9547", .driver_data = pca_9547 },
-	{ .id = "PCA9548", .driver_data = pca_9548 },
-	{ }
-};
-MODULE_DEVICE_TABLE(acpi, pca954x_acpi_ids);
-#endif
-
 #ifdef CONFIG_OF
 static const struct of_device_id pca954x_of_match[] = {
 	{ .compatible = "nxp,pca9540", .data = &chips[pca_9540] },
@@ -393,17 +381,8 @@ static int pca954x_probe(struct i2c_client *client,
 	match = of_match_device(of_match_ptr(pca954x_of_match), &client->dev);
 	if (match)
 		data->chip = of_device_get_match_data(&client->dev);
-	else if (id)
+	else
 		data->chip = &chips[id->driver_data];
-	else {
-		const struct acpi_device_id *acpi_id;
-
-		acpi_id = acpi_match_device(ACPI_PTR(pca954x_acpi_ids),
-						&client->dev);
-		if (!acpi_id)
-			return -ENODEV;
-		data->chip = &chips[acpi_id->driver_data];
-	}
 
 	data->last_chan = 0;		   /* force the first selection */
 
@@ -492,7 +471,6 @@ static struct i2c_driver pca954x_driver = {
 		.name	= "pca954x",
 		.pm	= &pca954x_pm,
 		.of_match_table = of_match_ptr(pca954x_of_match),
-		.acpi_match_table = ACPI_PTR(pca954x_acpi_ids),
 	},
 	.probe		= pca954x_probe,
 	.remove		= pca954x_remove,
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index feb30061123b..5901937284e7 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -107,7 +107,8 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 	if (drive->media == ide_tape)
 		scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
-	error = blk_execute_rq(drive->queue, disk, rq, 0);
+	blk_execute_rq(drive->queue, disk, rq, 0);
+	error = scsi_req(rq)->result ? -EIO : 0;
 put_req:
 	blk_put_request(rq);
 	return error;
@@ -454,7 +455,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			debug_log("%s: I/O error\n", drive->name);
 
 			if (drive->media != ide_tape)
-				pc->rq->errors++;
+				scsi_req(pc->rq)->result++;
 
 			if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
 				printk(KERN_ERR PFX "%s: I/O error in request "
@@ -488,13 +489,13 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			drive->failed_pc = NULL;
 
 		if (ata_misc_request(rq)) {
-			rq->errors = 0;
+			scsi_req(rq)->result = 0;
 			error = 0;
 		} else {
 
 			if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
-				if (rq->errors == 0)
-					rq->errors = -EIO;
+				if (scsi_req(rq)->result == 0)
+					scsi_req(rq)->result = -EIO;
 			}
 
 			error = uptodate ? 0 : -EIO;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 74f1b7dc03f7..07e5ff3a64c3 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -247,10 +247,10 @@ static int ide_cd_breathe(ide_drive_t *drive, struct request *rq)
 
 	struct cdrom_info *info = drive->driver_data;
 
-	if (!rq->errors)
+	if (!scsi_req(rq)->result)
 		info->write_timeout = jiffies +	ATAPI_WAIT_WRITE_BUSY;
 
-	rq->errors = 1;
+	scsi_req(rq)->result = 1;
 
 	if (time_after(jiffies, info->write_timeout))
 		return 0;
@@ -294,8 +294,8 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 	}
 
 	/* if we have an error, pass CHECK_CONDITION as the SCSI status byte */
-	if (blk_rq_is_scsi(rq) && !rq->errors)
-		rq->errors = SAM_STAT_CHECK_CONDITION;
+	if (blk_rq_is_scsi(rq) && !scsi_req(rq)->result)
+		scsi_req(rq)->result = SAM_STAT_CHECK_CONDITION;
 
 	if (blk_noretry_request(rq))
 		do_end_request = 1;
@@ -325,7 +325,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		 * Arrange to retry the request but be sure to give up if we've
 		 * retried too many times.
 		 */
-		if (++rq->errors > ERROR_MAX)
+		if (++scsi_req(rq)->result > ERROR_MAX)
 			do_end_request = 1;
 		break;
 	case ILLEGAL_REQUEST:
@@ -372,7 +372,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 			/* go to the default handler for other errors */
 			ide_error(drive, "cdrom_decode_status", stat);
 			return 1;
-		} else if (++rq->errors > ERROR_MAX)
+		} else if (++scsi_req(rq)->result > ERROR_MAX)
 			/* we've racked up too many retries, abort */
 			do_end_request = 1;
 	}
@@ -452,7 +452,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 			}
 		}
 
-		error = blk_execute_rq(drive->queue, info->disk, rq, 0);
+		blk_execute_rq(drive->queue, info->disk, rq, 0);
+		error = scsi_req(rq)->result ? -EIO : 0;
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
@@ -683,8 +684,8 @@ out_end:
 			if (cmd->nleft == 0)
 				uptodate = 1;
 		} else {
-			if (uptodate <= 0 && rq->errors == 0)
-				rq->errors = -EIO;
+			if (uptodate <= 0 && scsi_req(rq)->result == 0)
+				scsi_req(rq)->result = -EIO;
 		}
 
 		if (uptodate == 0 && rq->bio)
@@ -1379,7 +1380,7 @@ static int ide_cdrom_prep_pc(struct request *rq)
 	 * appropriate action
 	 */
 	if (c[0] == MODE_SENSE || c[0] == MODE_SELECT) {
-		rq->errors = ILLEGAL_REQUEST;
+		scsi_req(rq)->result = ILLEGAL_REQUEST;
 		return BLKPREP_KILL;
 	}
 
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 9fcefbc8425e..55cd736c39c6 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -307,7 +307,8 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->rq_flags = RQF_QUIET;
-	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
+	blk_execute_rq(drive->queue, cd->disk, rq, 0);
+	ret = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 	/*
 	 * A reset will unlock the door. If it was previously locked,
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index a45dda5386e4..9b69c32ee560 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -173,8 +173,8 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	*(int *)&scsi_req(rq)->cmd[1] = arg;
 	rq->special = setting->set;
 
-	if (blk_execute_rq(q, NULL, rq, 0))
-		ret = rq->errors;
+	blk_execute_rq(q, NULL, rq, 0);
+	ret = scsi_req(rq)->result;
 	blk_put_request(rq);
 
 	return ret;
@@ -186,7 +186,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
 
 	err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
 	if (err)
-		rq->errors = err;
-	ide_complete_rq(drive, err, blk_rq_bytes(rq));
+		scsi_req(rq)->result = err;
+	ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 	return ide_stopped;
 }
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 186159715b71..7c06237f3479 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -470,7 +470,6 @@ ide_devset_get(multcount, mult_count);
 static int set_multcount(ide_drive_t *drive, int arg)
 {
 	struct request *rq;
-	int error;
 
 	if (arg < 0 || arg > (drive->id[ATA_ID_MAX_MULTSECT] & 0xff))
 		return -EINVAL;
@@ -484,7 +483,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
 
 	drive->mult_req = arg;
 	drive->special_flags |= IDE_SFLAG_SET_MULTMODE;
-	error = blk_execute_rq(drive->queue, NULL, rq, 0);
+	blk_execute_rq(drive->queue, NULL, rq, 0);
 	blk_put_request(rq);
 
 	return (drive->mult_count == arg) ? 0 : -EIO;
diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index 17a65ac56491..51c81223e56d 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -490,7 +490,7 @@ ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error)
 	 * make sure request is sane
 	 */
 	if (hwif->rq)
-		hwif->rq->errors = 0;
+		scsi_req(hwif->rq)->result = 0;
 	return ret;
 }
 
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index cf3af6840368..4b7ffd7d158d 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -12,7 +12,7 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
 	if ((stat & ATA_BUSY) ||
 	    ((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
 		/* other bits are useless when BUSY */
-		rq->errors |= ERROR_RESET;
+		scsi_req(rq)->result |= ERROR_RESET;
 	} else if (stat & ATA_ERR) {
 		/* err has different meaning on cdrom and tape */
 		if (err == ATA_ABORTED) {
@@ -25,10 +25,10 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
 			drive->crc_count++;
 		} else if (err & (ATA_BBK | ATA_UNC)) {
 			/* retries won't help these */
-			rq->errors = ERROR_MAX;
+			scsi_req(rq)->result = ERROR_MAX;
 		} else if (err & ATA_TRK0NF) {
 			/* help it find track zero */
-			rq->errors |= ERROR_RECAL;
+			scsi_req(rq)->result |= ERROR_RECAL;
 		}
 	}
 
@@ -39,23 +39,23 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
 		ide_pad_transfer(drive, READ, nsect * SECTOR_SIZE);
 	}
 
-	if (rq->errors >= ERROR_MAX || blk_noretry_request(rq)) {
+	if (scsi_req(rq)->result >= ERROR_MAX || blk_noretry_request(rq)) {
 		ide_kill_rq(drive, rq);
 		return ide_stopped;
 	}
 
 	if (hwif->tp_ops->read_status(hwif) & (ATA_BUSY | ATA_DRQ))
-		rq->errors |= ERROR_RESET;
+		scsi_req(rq)->result |= ERROR_RESET;
 
-	if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
-		++rq->errors;
+	if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+		++scsi_req(rq)->result;
 		return ide_do_reset(drive);
 	}
 
-	if ((rq->errors & ERROR_RECAL) == ERROR_RECAL)
+	if ((scsi_req(rq)->result & ERROR_RECAL) == ERROR_RECAL)
 		drive->special_flags |= IDE_SFLAG_RECALIBRATE;
 
-	++rq->errors;
+	++scsi_req(rq)->result;
 
 	return ide_stopped;
 }
@@ -68,7 +68,7 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq,
 	if ((stat & ATA_BUSY) ||
 	    ((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
 		/* other bits are useless when BUSY */
-		rq->errors |= ERROR_RESET;
+		scsi_req(rq)->result |= ERROR_RESET;
 	} else {
 		/* add decoding error stuff */
 	}
@@ -77,14 +77,14 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq,
 		/* force an abort */
 		hwif->tp_ops->exec_command(hwif, ATA_CMD_IDLEIMMEDIATE);
 
-	if (rq->errors >= ERROR_MAX) {
+	if (scsi_req(rq)->result >= ERROR_MAX) {
 		ide_kill_rq(drive, rq);
 	} else {
-		if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
-			++rq->errors;
+		if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+			++scsi_req(rq)->result;
 			return ide_do_reset(drive);
 		}
-		++rq->errors;
+		++scsi_req(rq)->result;
 	}
 
 	return ide_stopped;
@@ -130,11 +130,11 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 			if (cmd)
 				ide_complete_cmd(drive, cmd, stat, err);
 		} else if (ata_pm_request(rq)) {
-			rq->errors = 1;
+			scsi_req(rq)->result = 1;
 			ide_complete_pm_rq(drive, rq);
 			return ide_stopped;
 		}
-		rq->errors = err;
+		scsi_req(rq)->result = err;
 		ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
 		return ide_stopped;
 	}
@@ -149,8 +149,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 
 	if (rq && ata_misc_request(rq) &&
 	    scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
-		if (err <= 0 && rq->errors == 0)
-			rq->errors = -EIO;
+		if (err <= 0 && scsi_req(rq)->result == 0)
+			scsi_req(rq)->result = -EIO;
 		ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
 	}
 }
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index a69e8013f1df..8ac6048cd2df 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -98,7 +98,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 	}
 
 	if (ata_misc_request(rq))
-		rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
+		scsi_req(rq)->result = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
 
 	return uptodate;
 }
@@ -239,7 +239,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 					? rq->rq_disk->disk_name
 					: "dev?"));
 
-	if (rq->errors >= ERROR_MAX) {
+	if (scsi_req(rq)->result >= ERROR_MAX) {
 		if (drive->failed_pc) {
 			ide_floppy_report_error(floppy, drive->failed_pc);
 			drive->failed_pc = NULL;
@@ -247,7 +247,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 			printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
 
 		if (ata_misc_request(rq)) {
-			rq->errors = 0;
+			scsi_req(rq)->result = 0;
 			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 			return ide_stopped;
 		} else
@@ -301,8 +301,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 	return ide_floppy_issue_pc(drive, &cmd, pc);
 out_end:
 	drive->failed_pc = NULL;
-	if (blk_rq_is_passthrough(rq) && rq->errors == 0)
-		rq->errors = -EIO;
+	if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+		scsi_req(rq)->result = -EIO;
 	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 	return ide_stopped;
 }
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 043b1fb963cb..45b3f41a43d4 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -141,12 +141,12 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 	drive->failed_pc = NULL;
 
 	if ((media == ide_floppy || media == ide_tape) && drv_req) {
-		rq->errors = 0;
+		scsi_req(rq)->result = 0;
 	} else {
 		if (media == ide_tape)
-			rq->errors = IDE_DRV_ERROR_GENERAL;
-		else if (blk_rq_is_passthrough(rq) && rq->errors == 0)
-			rq->errors = -EIO;
+			scsi_req(rq)->result = IDE_DRV_ERROR_GENERAL;
+		else if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+			scsi_req(rq)->result = -EIO;
 	}
 
 	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
@@ -271,7 +271,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 #ifdef DEBUG
  	printk("%s: DRIVE_CMD (null)\n", drive->name);
 #endif
-	rq->errors = 0;
+	scsi_req(rq)->result = 0;
 	ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 
  	return ide_stopped;
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 248a3e0ceb46..8c0d17297a7a 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -128,7 +128,8 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
 		scsi_req_init(rq);
 		ide_req(rq)->type = ATA_PRIV_TASKFILE;
-		err = blk_execute_rq(drive->queue, NULL, rq, 0);
+		blk_execute_rq(drive->queue, NULL, rq, 0);
+		err = scsi_req(rq)->result ? -EIO : 0;
 		blk_put_request(rq);
 
 		return err;
@@ -227,8 +228,8 @@ static int generic_drive_reset(ide_drive_t *drive)
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd_len = 1;
 	scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
-	if (blk_execute_rq(drive->queue, NULL, rq, 1))
-		ret = rq->errors;
+	blk_execute_rq(drive->queue, NULL, rq, 1);
+	ret = scsi_req(rq)->result;
 	blk_put_request(rq);
 	return ret;
 }
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 101aed9a61ca..94e3107f59b9 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -37,7 +37,8 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	scsi_req(rq)->cmd_len = 1;
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = &timeout;
-	rc = blk_execute_rq(q, NULL, rq, 1);
+	blk_execute_rq(q, NULL, rq, 1);
+	rc = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 	if (rc)
 		goto out;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index ec951be4b0c8..0977fc1f40ce 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -27,7 +27,8 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 		mesg.event = PM_EVENT_FREEZE;
 	rqpm.pm_state = mesg.event;
 
-	ret = blk_execute_rq(drive->queue, NULL, rq, 0);
+	blk_execute_rq(drive->queue, NULL, rq, 0);
+	ret = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 
 	if (ret == 0 && ide_port_acpi(hwif)) {
@@ -55,8 +56,8 @@ static int ide_pm_execute_rq(struct request *rq)
 	spin_lock_irq(q->queue_lock);
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
-		rq->errors = -ENXIO;
-		__blk_end_request_all(rq, rq->errors);
+		scsi_req(rq)->result = -ENXIO;
+		__blk_end_request_all(rq, 0);
 		spin_unlock_irq(q->queue_lock);
 		return -ENXIO;
 	}
@@ -66,7 +67,7 @@ static int ide_pm_execute_rq(struct request *rq)
 
 	wait_for_completion_io(&wait);
 
-	return rq->errors ? -EIO : 0;
+	return scsi_req(rq)->result ? -EIO : 0;
 }
 
 int generic_ide_resume(struct device *dev)
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index d8a552b47718..a0651f948b76 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -366,7 +366,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
 			err = pc->error;
 		}
 	}
-	rq->errors = err;
+	scsi_req(rq)->result = err;
 
 	return uptodate;
 }
@@ -879,7 +879,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 		tape->valid = 0;
 
 	ret = size;
-	if (rq->errors == IDE_DRV_ERROR_GENERAL)
+	if (scsi_req(rq)->result == IDE_DRV_ERROR_GENERAL)
 		ret = -EIO;
 out_put:
 	blk_put_request(rq);
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index 4c0007cb74e3..d71199d23c9e 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -287,7 +287,7 @@ static void ide_pio_datablock(ide_drive_t *drive, struct ide_cmd *cmd,
 	u8 saved_io_32bit = drive->io_32bit;
 
 	if (cmd->tf_flags & IDE_TFLAG_FS)
-		cmd->rq->errors = 0;
+		scsi_req(cmd->rq)->result = 0;
 
 	if (cmd->tf_flags & IDE_TFLAG_IO_16BIT)
 		drive->io_32bit = 0;
@@ -329,7 +329,7 @@ void ide_finish_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat)
 	u8 set_xfer = !!(cmd->tf_flags & IDE_TFLAG_SET_XFER);
 
 	ide_complete_cmd(drive, cmd, stat, err);
-	rq->errors = err;
+	scsi_req(rq)->result = err;
 
 	if (err == 0 && set_xfer) {
 		ide_set_xfer_rate(drive, nsect);
@@ -452,8 +452,8 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 	rq->special = cmd;
 	cmd->rq = rq;
 
-	error = blk_execute_rq(drive->queue, NULL, rq, 0);
-
+	blk_execute_rq(drive->queue, NULL, rq, 0);
+	error = scsi_req(rq)->result ? -EIO : 0;
 put_req:
 	blk_put_request(rq);
 	return error;
diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c
index ca5759c0c318..43a6cb078193 100644
--- a/drivers/iio/accel/hid-sensor-accel-3d.c
+++ b/drivers/iio/accel/hid-sensor-accel-3d.c
@@ -370,10 +370,12 @@ static int hid_accel_3d_probe(struct platform_device *pdev)
 		name = "accel_3d";
 		channel_spec = accel_3d_channels;
 		channel_size = sizeof(accel_3d_channels);
+		indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
 	} else {
 		name = "gravity";
 		channel_spec = gravity_channels;
 		channel_size = sizeof(gravity_channels);
+		indio_dev->num_channels = ARRAY_SIZE(gravity_channels);
 	}
 	ret = hid_sensor_parse_common_attributes(hsdev, hsdev->usage,
 					&accel_state->common_attributes);
@@ -395,7 +397,6 @@ static int hid_accel_3d_probe(struct platform_device *pdev)
 		goto error_free_dev_mem;
 	}
 
-	indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
 	indio_dev->dev.parent = &pdev->dev;
 	indio_dev->info = &accel_3d_info;
 	indio_dev->name = name;
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index ad9dec30bb30..4282ceca3d8f 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -169,7 +169,9 @@ static irqreturn_t tiadc_irq_h(int irq, void *private)
 {
 	struct iio_dev *indio_dev = private;
 	struct tiadc_device *adc_dev = iio_priv(indio_dev);
-	unsigned int status, config;
+	unsigned int status, config, adc_fsm;
+	unsigned short count = 0;
+
 	status = tiadc_readl(adc_dev, REG_IRQSTATUS);
 
 	/*
@@ -183,6 +185,15 @@ static irqreturn_t tiadc_irq_h(int irq, void *private)
 		tiadc_writel(adc_dev, REG_CTRL, config);
 		tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1OVRRUN
 				| IRQENB_FIFO1UNDRFLW | IRQENB_FIFO1THRES);
+
+		/* wait for idle state.
+		 * ADC needs to finish the current conversion
+		 * before disabling the module
+		 */
+		do {
+			adc_fsm = tiadc_readl(adc_dev, REG_ADCFSM);
+		} while (adc_fsm != 0x10 && count++ < 100);
+
 		tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_TSCSSENB));
 		return IRQ_HANDLED;
 	} else if (status & IRQENB_FIFO1THRES) {
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index d6c372bb433b..c17596f7ed2c 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -61,7 +61,7 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev,
 		ret = st->core.read_ec_sensors_data(indio_dev, 1 << idx, &data);
 		if (ret < 0)
 			break;
-
+		ret = IIO_VAL_INT;
 		*val = data;
 		break;
 	case IIO_CHAN_INFO_CALIBBIAS:
@@ -76,7 +76,7 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev,
 		for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++)
 			st->core.calib[i] =
 				st->core.resp->sensor_offset.offset[i];
-
+		ret = IIO_VAL_INT;
 		*val = st->core.calib[idx];
 		break;
 	case IIO_CHAN_INFO_SCALE:
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index 7afdac42ed42..01e02b9926d4 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -379,6 +379,8 @@ int hid_sensor_parse_common_attributes(struct hid_sensor_hub_device *hsdev,
 {
 
 	struct hid_sensor_hub_attribute_info timestamp;
+	s32 value;
+	int ret;
 
 	hid_sensor_get_reporting_interval(hsdev, usage_id, st);
 
@@ -417,6 +419,14 @@ int hid_sensor_parse_common_attributes(struct hid_sensor_hub_device *hsdev,
 		st->sensitivity.index, st->sensitivity.report_id,
 		timestamp.index, timestamp.report_id);
 
+	ret = sensor_hub_get_feature(hsdev,
+				st->power_state.report_id,
+				st->power_state.index, sizeof(value), &value);
+	if (ret < 0)
+		return ret;
+	if (value < 0)
+		return -EINVAL;
+
 	return 0;
 }
 EXPORT_SYMBOL(hid_sensor_parse_common_attributes);
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index a3cce3a38300..ecf592d69043 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -51,8 +51,6 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 			st->report_state.report_id,
 			st->report_state.index,
 			HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM);
-
-		poll_value = hid_sensor_read_poll_value(st);
 	} else {
 		int val;
 
@@ -89,7 +87,9 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 	sensor_hub_get_feature(st->hsdev, st->power_state.report_id,
 			       st->power_state.index,
 			       sizeof(state_val), &state_val);
-	if (state && poll_value)
+	if (state)
+		poll_value = hid_sensor_read_poll_value(st);
+	if (poll_value > 0)
 		msleep_interruptible(poll_value * 2);
 
 	return 0;
diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c
index f7fcfa886f72..821919dd245b 100644
--- a/drivers/iio/gyro/bmg160_core.c
+++ b/drivers/iio/gyro/bmg160_core.c
@@ -27,6 +27,7 @@
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/triggered_buffer.h>
 #include <linux/regmap.h>
+#include <linux/delay.h>
 #include "bmg160.h"
 
 #define BMG160_IRQ_NAME		"bmg160_event"
@@ -52,6 +53,9 @@
 #define BMG160_DEF_BW			100
 #define BMG160_REG_PMU_BW_RES		BIT(7)
 
+#define BMG160_GYRO_REG_RESET		0x14
+#define BMG160_GYRO_RESET_VAL		0xb6
+
 #define BMG160_REG_INT_MAP_0		0x17
 #define BMG160_INT_MAP_0_BIT_ANY	BIT(1)
 
@@ -236,6 +240,14 @@ static int bmg160_chip_init(struct bmg160_data *data)
 	int ret;
 	unsigned int val;
 
+	/*
+	 * Reset chip to get it in a known good state. A delay of 30ms after
+	 * reset is required according to the datasheet.
+	 */
+	regmap_write(data->regmap, BMG160_GYRO_REG_RESET,
+		     BMG160_GYRO_RESET_VAL);
+	usleep_range(30000, 30700);
+
 	ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val);
 	if (ret < 0) {
 		dev_err(dev, "Error reading reg_chip_id\n");
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 78532ce07449..81b572d7699a 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -193,8 +193,8 @@ int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark)
 	if (err < 0)
 		goto out;
 
-	fifo_watermark = ((data & ~ST_LSM6DSX_FIFO_TH_MASK) << 8) |
-			  (fifo_watermark & ST_LSM6DSX_FIFO_TH_MASK);
+	fifo_watermark = ((data << 8) & ~ST_LSM6DSX_FIFO_TH_MASK) |
+			 (fifo_watermark & ST_LSM6DSX_FIFO_TH_MASK);
 
 	wdata = cpu_to_le16(fifo_watermark);
 	err = hw->tf->write(hw->dev, ST_LSM6DSX_REG_FIFO_THL_ADDR,
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index d18ded45bedd..3ff91e02fee3 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -610,10 +610,9 @@ static ssize_t __iio_format_value(char *buf, size_t len, unsigned int type,
 		tmp0 = (int)div_s64_rem(tmp, 1000000000, &tmp1);
 		return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
 	case IIO_VAL_FRACTIONAL_LOG2:
-		tmp = (s64)vals[0] * 1000000000LL >> vals[1];
-		tmp1 = do_div(tmp, 1000000000LL);
-		tmp0 = tmp;
-		return snprintf(buf, len, "%d.%09u", tmp0, tmp1);
+		tmp = shift_right((s64)vals[0] * 1000000000LL, vals[1]);
+		tmp0 = (int)div_s64_rem(tmp, 1000000000LL, &tmp1);
+		return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
 	case IIO_VAL_INT_MULTIPLE:
 	{
 		int i;
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 6dd8cbd7ce95..e13370dc9b1c 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -763,7 +763,7 @@ power_off:
 	return ret;
 }
 
-static int __exit ak8974_remove(struct i2c_client *i2c)
+static int ak8974_remove(struct i2c_client *i2c)
 {
 	struct iio_dev *indio_dev = i2c_get_clientdata(i2c);
 	struct ak8974 *ak8974 = iio_priv(indio_dev);
@@ -845,7 +845,7 @@ static struct i2c_driver ak8974_driver = {
 		.of_match_table = of_match_ptr(ak8974_of_match),
 	},
 	.probe	  = ak8974_probe,
-	.remove	  = __exit_p(ak8974_remove),
+	.remove	  = ak8974_remove,
 	.id_table = ak8974_id,
 };
 module_i2c_driver(ak8974_driver);
diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index 5f2680855552..fd0edca0e656 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -457,6 +457,7 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
 		.multi_read_bit = true,
+		.bootime = 2,
 	},
 };
 
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 0f58f46dbad7..329d08c884f6 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -88,7 +88,7 @@ static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
 		return false;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
-			nlmsg_len(nlh), ib_nl_addr_policy);
+			nlmsg_len(nlh), ib_nl_addr_policy, NULL);
 	if (ret)
 		return false;
 
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index e95510117a6d..f2ae75fa3128 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -29,7 +29,13 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
 {
 	int i, n, completed = 0;
 
-	while ((n = ib_poll_cq(cq, IB_POLL_BATCH, cq->wc)) > 0) {
+	/*
+	 * budget might be (-1) if the caller does not
+	 * want to bound this call, thus we need unsigned
+	 * minimum here.
+	 */
+	while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH,
+			budget - completed), cq->wc)) > 0) {
 		for (i = 0; i < n; i++) {
 			struct ib_wc *wc = &cq->wc[i];
 
@@ -196,7 +202,7 @@ void ib_free_cq(struct ib_cq *cq)
 		irq_poll_disable(&cq->iop);
 		break;
 	case IB_POLL_WORKQUEUE:
-		flush_work(&cq->work);
+		cancel_work_sync(&cq->work);
 		break;
 	default:
 		WARN_ON_ONCE(1);
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 593d2ce6ec7c..7c9e34d679d3 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -336,12 +336,26 @@ int ib_register_device(struct ib_device *device,
 	struct device *parent = device->dev.parent;
 
 	WARN_ON_ONCE(!parent);
-	if (!device->dev.dma_ops)
-		device->dev.dma_ops = parent->dma_ops;
-	if (!device->dev.dma_mask)
-		device->dev.dma_mask = parent->dma_mask;
-	if (!device->dev.coherent_dma_mask)
-		device->dev.coherent_dma_mask = parent->coherent_dma_mask;
+	WARN_ON_ONCE(device->dma_device);
+	if (device->dev.dma_ops) {
+		/*
+		 * The caller provided custom DMA operations. Copy the
+		 * DMA-related fields that are used by e.g. dma_alloc_coherent()
+		 * into device->dev.
+		 */
+		device->dma_device = &device->dev;
+		if (!device->dev.dma_mask)
+			device->dev.dma_mask = parent->dma_mask;
+		if (!device->dev.coherent_dma_mask)
+			device->dev.coherent_dma_mask =
+				parent->coherent_dma_mask;
+	} else {
+		/*
+		 * The caller did not provide custom DMA operations. Use the
+		 * DMA mapping operations of the parent device.
+		 */
+		device->dma_device = parent;
+	}
 
 	mutex_lock(&device_mutex);
 
@@ -1015,8 +1029,7 @@ static int __init ib_core_init(void)
 		return -ENOMEM;
 
 	ib_comp_wq = alloc_workqueue("ib-comp-wq",
-			WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
-			WQ_UNBOUND_MAX_ACTIVE);
+			WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
 	if (!ib_comp_wq) {
 		ret = -ENOMEM;
 		goto err;
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 3ef51a96bbf1..f13870e69ccd 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -472,12 +472,14 @@ int iwpm_parse_nlmsg(struct netlink_callback *cb, int policy_max,
 	int ret;
 	const char *err_str = "";
 
-	ret = nlmsg_validate(cb->nlh, nlh_len, policy_max-1, nlmsg_policy);
+	ret = nlmsg_validate(cb->nlh, nlh_len, policy_max - 1, nlmsg_policy,
+			     NULL);
 	if (ret) {
 		err_str = "Invalid attribute";
 		goto parse_nlmsg_error;
 	}
-	ret = nlmsg_parse(cb->nlh, nlh_len, nltb, policy_max-1, nlmsg_policy);
+	ret = nlmsg_parse(cb->nlh, nlh_len, nltb, policy_max - 1,
+			  nlmsg_policy, NULL);
 	if (ret) {
 		err_str = "Unable to parse the nlmsg";
 		goto parse_nlmsg_error;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 10469b0088b5..b784055423c8 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -146,7 +146,8 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 
-static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct ibnl_client *client;
 	int type = nlh->nlmsg_type;
@@ -209,7 +210,7 @@ static void ibnl_rcv_reply_skb(struct sk_buff *skb)
 		if (nlh->nlmsg_flags & NLM_F_REQUEST)
 			return;
 
-		ibnl_rcv_msg(skb, nlh);
+		ibnl_rcv_msg(skb, nlh, NULL);
 
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 81b742ca1639..ceae153997d0 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -808,7 +808,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 		return -EPERM;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
-			nlmsg_len(nlh), ib_nl_policy);
+			nlmsg_len(nlh), ib_nl_policy, NULL);
 	attr = (const struct nlattr *)tb[LS_NLA_TYPE_TIMEOUT];
 	if (ret || !attr)
 		goto settimeout_out;
@@ -860,7 +860,7 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 		return 0;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
-			nlmsg_len(nlh), ib_nl_policy);
+			nlmsg_len(nlh), ib_nl_policy, NULL);
 	if (ret)
 		return 0;
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index 0f5d43d1f5fc..70c3e9e79508 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -160,6 +160,9 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
 		return NOTIFY_DONE;
 
 	iwdev = &hdl->device;
+	if (iwdev->init_state < INET_NOTIFIER)
+		return NOTIFY_DONE;
+
 	netdev = iwdev->ldev->netdev;
 	upper_dev = netdev_master_upper_dev_get(netdev);
 	if (netdev != event_netdev)
@@ -214,6 +217,9 @@ int i40iw_inet6addr_event(struct notifier_block *notifier,
 		return NOTIFY_DONE;
 
 	iwdev = &hdl->device;
+	if (iwdev->init_state < INET_NOTIFIER)
+		return NOTIFY_DONE;
+
 	netdev = iwdev->ldev->netdev;
 	if (netdev != event_netdev)
 		return NOTIFY_DONE;
@@ -260,6 +266,8 @@ int i40iw_net_event(struct notifier_block *notifier, unsigned long event, void *
 		if (!iwhdl)
 			return NOTIFY_DONE;
 		iwdev = &iwhdl->device;
+		if (iwdev->init_state < INET_NOTIFIER)
+			return NOTIFY_DONE;
 		p = (__be32 *)neigh->primary_key;
 		i40iw_copy_ip_ntohl(local_ipaddr, p);
 		if (neigh->nud_state & NUD_VALID) {
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 3cd064b5f0bf..ce8ba617d46e 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -729,16 +729,6 @@ static inline struct mlx5_ib_mw *to_mmw(struct ib_mw *ibmw)
 	return container_of(ibmw, struct mlx5_ib_mw, ibmw);
 }
 
-struct mlx5_ib_ah {
-	struct ib_ah		ibah;
-	struct mlx5_av		av;
-};
-
-static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah)
-{
-	return container_of(ibah, struct mlx5_ib_ah, ibah);
-}
-
 int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
 			struct mlx5_db *db);
 void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ad8a2638e339..ed6320186f89 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -897,6 +897,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN |
 					IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK |
 					IB_QP_CREATE_IPOIB_UD_LSO |
+					IB_QP_CREATE_NETIF_QP |
 					mlx5_ib_create_qp_sqpn_qp1()))
 		return -EINVAL;
 
diff --git a/drivers/infiniband/hw/nes/nes.h b/drivers/infiniband/hw/nes/nes.h
index 85acd0843b50..3f9e56e8b379 100644
--- a/drivers/infiniband/hw/nes/nes.h
+++ b/drivers/infiniband/hw/nes/nes.h
@@ -36,6 +36,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
+#include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index bc9fb144e57b..c52edeafd616 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -372,7 +372,7 @@ static int _ocrdma_pd_mgr_put_bitmap(struct ocrdma_dev *dev, u16 pd_id,
 	return 0;
 }
 
-static u8 ocrdma_put_pd_num(struct ocrdma_dev *dev, u16 pd_id,
+static int ocrdma_put_pd_num(struct ocrdma_dev *dev, u16 pd_id,
 				   bool dpp_pool)
 {
 	int status;
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index b9b47e5cc8b3..ced0461d6e9f 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -587,9 +587,8 @@ void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle)
 #define EVENT_TYPE_CQ		1
 #define EVENT_TYPE_QP		2
 	struct qedr_dev *dev = (struct qedr_dev *)context;
-	union event_ring_data *data = fw_handle;
-	u64 roce_handle64 = ((u64)data->roce_handle.hi << 32) +
-			    data->roce_handle.lo;
+	struct regpair *async_handle = (struct regpair *)fw_handle;
+	u64 roce_handle64 = ((u64) async_handle->hi << 32) + async_handle->lo;
 	u8 event_type = EVENT_TYPE_NOT_DEFINED;
 	struct ib_event event;
 	struct ib_cq *ibcq;
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index bb32e4792ec9..5cb9195513bd 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -38,7 +38,8 @@
 #include <linux/qed/qed_chain.h>
 #include <linux/qed/qed_roce_if.h>
 #include <linux/qed/qede_roce.h>
-#include "qedr_hsi.h"
+#include <linux/qed/roce_common.h>
+#include "qedr_hsi_rdma.h"
 
 #define QEDR_MODULE_VERSION	"8.10.10.0"
 #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA"
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 699632893dd9..a6280ce3e2a5 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -43,14 +43,11 @@
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
 
-#include "qedr_hsi.h"
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_roce_if.h>
 #include "qedr.h"
-#include "qedr_hsi.h"
 #include "verbs.h"
 #include <rdma/qedr-abi.h>
-#include "qedr_hsi.h"
 #include "qedr_cm.h"
 
 void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info)
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 6b3bb32803bd..2091902848e6 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -43,7 +43,8 @@
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
 
-#include "qedr_hsi.h"
+#include <linux/qed/common_hsi.h>
+#include "qedr_hsi_rdma.h"
 #include <linux/qed/qed_if.h>
 #include "qedr.h"
 #include "verbs.h"
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 12c4208fd701..af9f596bb68b 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -7068,7 +7068,7 @@ static void qib_7322_txchk_change(struct qib_devdata *dd, u32 start,
 	unsigned long flags;
 
 	while (wait) {
-		unsigned long shadow;
+		unsigned long shadow = 0;
 		int cstart, previ = -1;
 
 		/*
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 3cd96c1b9502..9fbe22d3467b 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -69,6 +69,9 @@
  */
 #define PCI_DEVICE_ID_VMWARE_PVRDMA	0x0820
 
+#define PVRDMA_NUM_RING_PAGES		4
+#define PVRDMA_QP_NUM_HEADER_PAGES	1
+
 struct pvrdma_dev;
 
 struct pvrdma_page_dir {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
index e69d6f3cae32..09078ccfaec7 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
@@ -132,7 +132,7 @@ enum pvrdma_pci_resource {
 
 enum pvrdma_device_ctl {
 	PVRDMA_DEVICE_CTL_ACTIVATE,	/* Activate device. */
-	PVRDMA_DEVICE_CTL_QUIESCE,	/* Quiesce device. */
+	PVRDMA_DEVICE_CTL_UNQUIESCE,	/* Unquiesce device. */
 	PVRDMA_DEVICE_CTL_RESET,	/* Reset device. */
 };
 
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 100bea5c42ff..34ebc7615411 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -56,7 +56,7 @@
 #include "pvrdma.h"
 
 #define DRV_NAME	"vmw_pvrdma"
-#define DRV_VERSION	"1.0.0.0-k"
+#define DRV_VERSION	"1.0.1.0-k"
 
 static DEFINE_MUTEX(pvrdma_device_list_lock);
 static LIST_HEAD(pvrdma_device_list);
@@ -660,7 +660,16 @@ static void pvrdma_netdevice_event_handle(struct pvrdma_dev *dev,
 		pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ERR);
 		break;
 	case NETDEV_UP:
-		pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
+		pvrdma_write_reg(dev, PVRDMA_REG_CTL,
+				 PVRDMA_DEVICE_CTL_UNQUIESCE);
+
+		mb();
+
+		if (pvrdma_read_reg(dev, PVRDMA_REG_ERR))
+			dev_err(&dev->pdev->dev,
+				"failed to activate device during link up\n");
+		else
+			pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
 		break;
 	default:
 		dev_dbg(&dev->pdev->dev, "ignore netdevice event %ld on %s\n",
@@ -858,7 +867,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	dev->dsr->resp_slot_dma = (u64)slot_dma;
 
 	/* Async event ring */
-	dev->dsr->async_ring_pages.num_pages = 4;
+	dev->dsr->async_ring_pages.num_pages = PVRDMA_NUM_RING_PAGES;
 	ret = pvrdma_page_dir_init(dev, &dev->async_pdir,
 				   dev->dsr->async_ring_pages.num_pages, true);
 	if (ret)
@@ -867,7 +876,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	dev->dsr->async_ring_pages.pdir_dma = dev->async_pdir.dir_dma;
 
 	/* CQ notification ring */
-	dev->dsr->cq_ring_pages.num_pages = 4;
+	dev->dsr->cq_ring_pages.num_pages = PVRDMA_NUM_RING_PAGES;
 	ret = pvrdma_page_dir_init(dev, &dev->cq_pdir,
 				   dev->dsr->cq_ring_pages.num_pages, true);
 	if (ret)
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index dbbfd35e7da7..30062aad3af1 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -170,8 +170,9 @@ static int pvrdma_set_sq_size(struct pvrdma_dev *dev, struct ib_qp_cap *req_cap,
 					     sizeof(struct pvrdma_sge) *
 					     qp->sq.max_sg);
 	/* Note: one extra page for the header. */
-	qp->npages_send = 1 + (qp->sq.wqe_cnt * qp->sq.wqe_size +
-			       PAGE_SIZE - 1) / PAGE_SIZE;
+	qp->npages_send = PVRDMA_QP_NUM_HEADER_PAGES +
+			  (qp->sq.wqe_cnt * qp->sq.wqe_size + PAGE_SIZE - 1) /
+								PAGE_SIZE;
 
 	return 0;
 }
@@ -288,7 +289,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 			qp->npages = qp->npages_send + qp->npages_recv;
 
 			/* Skip header page. */
-			qp->sq.offset = PAGE_SIZE;
+			qp->sq.offset = PVRDMA_QP_NUM_HEADER_PAGES * PAGE_SIZE;
 
 			/* Recv queue pages are after send pages. */
 			qp->rq.offset = qp->npages_send * PAGE_SIZE;
@@ -341,7 +342,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 	cmd->qp_type = ib_qp_type_to_pvrdma(init_attr->qp_type);
 	cmd->access_flags = IB_ACCESS_LOCAL_WRITE;
 	cmd->total_chunks = qp->npages;
-	cmd->send_chunks = qp->npages_send - 1;
+	cmd->send_chunks = qp->npages_send - PVRDMA_QP_NUM_HEADER_PAGES;
 	cmd->pdir_dma = qp->pdir.dir_dma;
 
 	dev_dbg(&dev->pdev->dev, "create queuepair with %d, %d, %d, %d\n",
@@ -554,13 +555,13 @@ out:
 	return ret;
 }
 
-static inline void *get_sq_wqe(struct pvrdma_qp *qp, int n)
+static inline void *get_sq_wqe(struct pvrdma_qp *qp, unsigned int n)
 {
 	return pvrdma_page_dir_get_ptr(&qp->pdir,
 				       qp->sq.offset + n * qp->sq.wqe_size);
 }
 
-static inline void *get_rq_wqe(struct pvrdma_qp *qp, int n)
+static inline void *get_rq_wqe(struct pvrdma_qp *qp, unsigned int n)
 {
 	return pvrdma_page_dir_get_ptr(&qp->pdir,
 				       qp->rq.offset + n * qp->rq.wqe_size);
@@ -598,9 +599,7 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	unsigned long flags;
 	struct pvrdma_sq_wqe_hdr *wqe_hdr;
 	struct pvrdma_sge *sge;
-	int i, index;
-	int nreq;
-	int ret;
+	int i, ret;
 
 	/*
 	 * In states lower than RTS, we can fail immediately. In other states,
@@ -613,9 +612,8 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
 
-	index = pvrdma_idx(&qp->sq.ring->prod_tail, qp->sq.wqe_cnt);
-	for (nreq = 0; wr; nreq++, wr = wr->next) {
-		unsigned int tail;
+	while (wr) {
+		unsigned int tail = 0;
 
 		if (unlikely(!pvrdma_idx_ring_has_space(
 				qp->sq.ring, qp->sq.wqe_cnt, &tail))) {
@@ -680,7 +678,7 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			}
 		}
 
-		wqe_hdr = (struct pvrdma_sq_wqe_hdr *)get_sq_wqe(qp, index);
+		wqe_hdr = (struct pvrdma_sq_wqe_hdr *)get_sq_wqe(qp, tail);
 		memset(wqe_hdr, 0, sizeof(*wqe_hdr));
 		wqe_hdr->wr_id = wr->wr_id;
 		wqe_hdr->num_sge = wr->num_sge;
@@ -771,12 +769,11 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		/* Make sure wqe is written before index update */
 		smp_wmb();
 
-		index++;
-		if (unlikely(index >= qp->sq.wqe_cnt))
-			index = 0;
 		/* Update shared sq ring */
 		pvrdma_idx_ring_inc(&qp->sq.ring->prod_tail,
 				    qp->sq.wqe_cnt);
+
+		wr = wr->next;
 	}
 
 	ret = 0;
@@ -806,7 +803,6 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 	struct pvrdma_qp *qp = to_vqp(ibqp);
 	struct pvrdma_rq_wqe_hdr *wqe_hdr;
 	struct pvrdma_sge *sge;
-	int index, nreq;
 	int ret = 0;
 	int i;
 
@@ -821,9 +817,8 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 
 	spin_lock_irqsave(&qp->rq.lock, flags);
 
-	index = pvrdma_idx(&qp->rq.ring->prod_tail, qp->rq.wqe_cnt);
-	for (nreq = 0; wr; nreq++, wr = wr->next) {
-		unsigned int tail;
+	while (wr) {
+		unsigned int tail = 0;
 
 		if (unlikely(wr->num_sge > qp->rq.max_sg ||
 			     wr->num_sge < 0)) {
@@ -843,7 +838,7 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 			goto out;
 		}
 
-		wqe_hdr = (struct pvrdma_rq_wqe_hdr *)get_rq_wqe(qp, index);
+		wqe_hdr = (struct pvrdma_rq_wqe_hdr *)get_rq_wqe(qp, tail);
 		wqe_hdr->wr_id = wr->wr_id;
 		wqe_hdr->num_sge = wr->num_sge;
 		wqe_hdr->total_len = 0;
@@ -859,12 +854,11 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		/* Make sure wqe is written before index update */
 		smp_wmb();
 
-		index++;
-		if (unlikely(index >= qp->rq.wqe_cnt))
-			index = 0;
 		/* Update shared rq ring */
 		pvrdma_idx_ring_inc(&qp->rq.ring->prod_tail,
 				    qp->rq.wqe_cnt);
+
+		wr = wr->next;
 	}
 
 	spin_unlock_irqrestore(&qp->rq.lock, flags);
diff --git a/drivers/infiniband/sw/rdmavt/mmap.c b/drivers/infiniband/sw/rdmavt/mmap.c
index e202b8142759..6b712eecbd37 100644
--- a/drivers/infiniband/sw/rdmavt/mmap.c
+++ b/drivers/infiniband/sw/rdmavt/mmap.c
@@ -170,9 +170,9 @@ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
 
 	spin_lock_irq(&rdi->mmap_offset_lock);
 	if (rdi->mmap_offset == 0)
-		rdi->mmap_offset = PAGE_SIZE;
+		rdi->mmap_offset = ALIGN(PAGE_SIZE, SHMLBA);
 	ip->offset = rdi->mmap_offset;
-	rdi->mmap_offset += size;
+	rdi->mmap_offset += ALIGN(size, SHMLBA);
 	spin_unlock_irq(&rdi->mmap_offset_lock);
 
 	INIT_LIST_HEAD(&ip->pending_mmaps);
diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig
index 7d1ac27ed251..6332dedc11e8 100644
--- a/drivers/infiniband/sw/rxe/Kconfig
+++ b/drivers/infiniband/sw/rxe/Kconfig
@@ -22,4 +22,4 @@ config RDMA_RXE
 	To configure and work with soft-RoCE driver please use the
 	following wiki page under "configure Soft-RoCE (RXE)" section:
 
-	https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home
+	https://github.com/linux-rdma/rdma-core/blob/master/Documentation/rxe.md
diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c
index c572a4c09359..bd812e00988e 100644
--- a/drivers/infiniband/sw/rxe/rxe_mmap.c
+++ b/drivers/infiniband/sw/rxe/rxe_mmap.c
@@ -156,10 +156,10 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *rxe,
 	spin_lock_bh(&rxe->mmap_offset_lock);
 
 	if (rxe->mmap_offset == 0)
-		rxe->mmap_offset = PAGE_SIZE;
+		rxe->mmap_offset = ALIGN(PAGE_SIZE, SHMLBA);
 
 	ip->info.offset = rxe->mmap_offset;
-	rxe->mmap_offset += size;
+	rxe->mmap_offset += ALIGN(size, SHMLBA);
 
 	spin_unlock_bh(&rxe->mmap_offset_lock);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index dbfde0dc6ff7..9f95f50b2909 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -729,11 +729,11 @@ next_wqe:
 	ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb);
 	if (ret) {
 		qp->need_req_skb = 1;
-		kfree_skb(skb);
 
 		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
 
 		if (ret == -EAGAIN) {
+			kfree_skb(skb);
 			rxe_run_task(&qp->req.task, 1);
 			goto exit;
 		}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index d404a8aba7af..c9dd385ce62e 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -813,18 +813,17 @@ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
 		WARN_ON_ONCE(1);
 	}
 
-	/* We successfully processed this new request. */
-	qp->resp.msn++;
-
 	/* next expected psn, read handles this separately */
 	qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
 
 	qp->resp.opcode = pkt->opcode;
 	qp->resp.status = IB_WC_SUCCESS;
 
-	if (pkt->mask & RXE_COMP_MASK)
+	if (pkt->mask & RXE_COMP_MASK) {
+		/* We successfully processed this new request. */
+		qp->resp.msn++;
 		return RESPST_COMPLETE;
-	else if (qp_type(qp) == IB_QPT_RC)
+	} else if (qp_type(qp) == IB_QPT_RC)
 		return RESPST_ACKNOWLEDGE;
 	else
 		return RESPST_CLEANUP;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 9d0b22ad58c1..c1ae4aeae2f9 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -430,6 +430,7 @@ struct iser_fr_desc {
 	struct list_head		  list;
 	struct iser_reg_resources	  rsc;
 	struct iser_pi_context		 *pi_ctx;
+	struct list_head                  all_list;
 };
 
 /**
@@ -443,6 +444,7 @@ struct iser_fr_pool {
 	struct list_head        list;
 	spinlock_t              lock;
 	int                     size;
+	struct list_head        all_list;
 };
 
 /**
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 30b622f2ab73..c538a38c91ce 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -362,6 +362,7 @@ int iser_alloc_fastreg_pool(struct ib_conn *ib_conn,
 	int i, ret;
 
 	INIT_LIST_HEAD(&fr_pool->list);
+	INIT_LIST_HEAD(&fr_pool->all_list);
 	spin_lock_init(&fr_pool->lock);
 	fr_pool->size = 0;
 	for (i = 0; i < cmds_max; i++) {
@@ -373,6 +374,7 @@ int iser_alloc_fastreg_pool(struct ib_conn *ib_conn,
 		}
 
 		list_add_tail(&desc->list, &fr_pool->list);
+		list_add_tail(&desc->all_list, &fr_pool->all_list);
 		fr_pool->size++;
 	}
 
@@ -392,13 +394,13 @@ void iser_free_fastreg_pool(struct ib_conn *ib_conn)
 	struct iser_fr_desc *desc, *tmp;
 	int i = 0;
 
-	if (list_empty(&fr_pool->list))
+	if (list_empty(&fr_pool->all_list))
 		return;
 
 	iser_info("freeing conn %p fr pool\n", ib_conn);
 
-	list_for_each_entry_safe(desc, tmp, &fr_pool->list, list) {
-		list_del(&desc->list);
+	list_for_each_entry_safe(desc, tmp, &fr_pool->all_list, all_list) {
+		list_del(&desc->all_list);
 		iser_free_reg_res(&desc->rsc);
 		if (desc->pi_ctx)
 			iser_free_pi_ctx(desc->pi_ctx);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 91cbe86b25c8..fcbed35e95a8 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -817,6 +817,7 @@ isert_post_recvm(struct isert_conn *isert_conn, u32 count)
 		rx_wr->sg_list = &rx_desc->rx_sg;
 		rx_wr->num_sge = 1;
 		rx_wr->next = rx_wr + 1;
+		rx_desc->in_use = false;
 	}
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
@@ -835,6 +836,15 @@ isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc)
 	struct ib_recv_wr *rx_wr_failed, rx_wr;
 	int ret;
 
+	if (!rx_desc->in_use) {
+		/*
+		 * if the descriptor is not in-use we already reposted it
+		 * for recv, so just silently return
+		 */
+		return 0;
+	}
+
+	rx_desc->in_use = false;
 	rx_wr.wr_cqe = &rx_desc->rx_cqe;
 	rx_wr.sg_list = &rx_desc->rx_sg;
 	rx_wr.num_sge = 1;
@@ -1397,6 +1407,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
+	rx_desc->in_use = true;
+
 	ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr,
 			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
 
@@ -1659,10 +1671,23 @@ isert_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 	ret = isert_check_pi_status(cmd, isert_cmd->rw.sig->sig_mr);
 	isert_rdma_rw_ctx_destroy(isert_cmd, isert_conn);
 
-	if (ret)
-		transport_send_check_condition_and_sense(cmd, cmd->pi_err, 0);
-	else
-		isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd);
+	if (ret) {
+		/*
+		 * transport_generic_request_failure() expects to have
+		 * plus two references to handle queue-full, so re-add
+		 * one here as target-core will have already dropped
+		 * it after the first isert_put_datain() callback.
+		 */
+		kref_get(&cmd->cmd_kref);
+		transport_generic_request_failure(cmd, cmd->pi_err);
+	} else {
+		/*
+		 * XXX: isert_put_response() failure is not retried.
+		 */
+		ret = isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd);
+		if (ret)
+			pr_warn_ratelimited("isert_put_response() ret: %d\n", ret);
+	}
 }
 
 static void
@@ -1699,13 +1724,15 @@ isert_rdma_read_done(struct ib_cq *cq, struct ib_wc *wc)
 	cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT;
 	spin_unlock_bh(&cmd->istate_lock);
 
-	if (ret) {
-		target_put_sess_cmd(se_cmd);
-		transport_send_check_condition_and_sense(se_cmd,
-							 se_cmd->pi_err, 0);
-	} else {
+	/*
+	 * transport_generic_request_failure() will drop the extra
+	 * se_cmd->cmd_kref reference after T10-PI error, and handle
+	 * any non-zero ->queue_status() callback error retries.
+	 */
+	if (ret)
+		transport_generic_request_failure(se_cmd, se_cmd->pi_err);
+	else
 		target_execute_cmd(se_cmd);
-	}
 }
 
 static void
@@ -2171,26 +2198,28 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 		chain_wr = &isert_cmd->tx_desc.send_wr;
 	}
 
-	isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr);
-	isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ\n", isert_cmd);
-	return 1;
+	rc = isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr);
+	isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ rc: %d\n",
+		  isert_cmd, rc);
+	return rc;
 }
 
 static int
 isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 {
 	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+	int ret;
 
 	isert_dbg("Cmd: %p RDMA_READ data_length: %u write_data_done: %u\n",
 		 isert_cmd, cmd->se_cmd.data_length, cmd->write_data_done);
 
 	isert_cmd->tx_desc.tx_cqe.done = isert_rdma_read_done;
-	isert_rdma_rw_ctx_post(isert_cmd, conn->context,
-			&isert_cmd->tx_desc.tx_cqe, NULL);
+	ret = isert_rdma_rw_ctx_post(isert_cmd, conn->context,
+				     &isert_cmd->tx_desc.tx_cqe, NULL);
 
-	isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
-		 isert_cmd);
-	return 0;
+	isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE rc: %d\n",
+		 isert_cmd, ret);
+	return ret;
 }
 
 static int
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index c02ada57d7f5..87d994de8c91 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -60,7 +60,7 @@
 
 #define ISER_RX_PAD_SIZE	(ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \
 		(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \
-		 sizeof(struct ib_cqe)))
+		 sizeof(struct ib_cqe) + sizeof(bool)))
 
 #define ISCSI_ISER_SG_TABLESIZE		256
 
@@ -85,6 +85,7 @@ struct iser_rx_desc {
 	u64		dma_addr;
 	struct ib_sge	rx_sg;
 	struct ib_cqe	rx_cqe;
+	bool		in_use;
 	char		pad[ISER_RX_PAD_SIZE];
 } __packed;
 
diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index d96aa27dfcdc..db64adfbe1af 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -141,6 +141,9 @@ static int iforce_usb_probe(struct usb_interface *intf,
 
 	interface = intf->cur_altsetting;
 
+	if (interface->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
 	epirq = &interface->endpoint[0].desc;
 	epout = &interface->endpoint[1].desc;
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 155fcb3b6230..153b1ee13e03 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -202,6 +202,7 @@ static const struct xpad_device {
 	{ 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
 	{ 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 },
 	{ 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+	{ 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
 	{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
@@ -326,6 +327,7 @@ static struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x1430),		/* RedOctane X-Box 360 controllers */
 	XPAD_XBOX360_VENDOR(0x146b),		/* BigBen Interactive Controllers */
 	XPAD_XBOX360_VENDOR(0x1532),		/* Razer Sabertooth */
+	XPAD_XBOXONE_VENDOR(0x1532),		/* Razer Wildcat */
 	XPAD_XBOX360_VENDOR(0x15e4),		/* Numark X-Box 360 controllers */
 	XPAD_XBOX360_VENDOR(0x162e),		/* Joytech X-Box 360 controllers */
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index 9cc6d057c302..23c191a2a071 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -700,6 +700,10 @@ static int cm109_usb_probe(struct usb_interface *intf,
 	int error = -ENOMEM;
 
 	interface = intf->cur_altsetting;
+
+	if (interface->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	endpoint = &interface->endpoint[0].desc;
 
 	if (!usb_endpoint_is_int_in(endpoint))
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 9c0ea36913b4..f4e8fbec6a94 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1667,6 +1667,10 @@ static int ims_pcu_parse_cdc_data(struct usb_interface *intf, struct ims_pcu *pc
 		return -EINVAL;
 
 	alt = pcu->ctrl_intf->cur_altsetting;
+
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	pcu->ep_ctrl = &alt->endpoint[0].desc;
 	pcu->max_ctrl_size = usb_endpoint_maxp(pcu->ep_ctrl);
 
diff --git a/drivers/input/misc/yealink.c b/drivers/input/misc/yealink.c
index 79c964c075f1..6e7ff9561d92 100644
--- a/drivers/input/misc/yealink.c
+++ b/drivers/input/misc/yealink.c
@@ -875,6 +875,10 @@ static int usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	int ret, pipe, i;
 
 	interface = intf->cur_altsetting;
+
+	if (interface->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	endpoint = &interface->endpoint[0].desc;
 	if (!usb_endpoint_is_int_in(endpoint))
 		return -ENODEV;
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 72b28ebfe360..f210e19ddba6 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1282,10 +1282,8 @@ static int alps_decode_ss4_v2(struct alps_fields *f,
 	/* handle buttons */
 	if (pkt_id == SS4_PACKET_ID_STICK) {
 		f->ts_left = !!(SS4_BTN_V2(p) & 0x01);
-		if (!(priv->flags & ALPS_BUTTONPAD)) {
-			f->ts_right = !!(SS4_BTN_V2(p) & 0x02);
-			f->ts_middle = !!(SS4_BTN_V2(p) & 0x04);
-		}
+		f->ts_right = !!(SS4_BTN_V2(p) & 0x02);
+		f->ts_middle = !!(SS4_BTN_V2(p) & 0x04);
 	} else {
 		f->left = !!(SS4_BTN_V2(p) & 0x01);
 		if (!(priv->flags & ALPS_BUTTONPAD)) {
@@ -2462,14 +2460,34 @@ static int alps_update_device_area_ss4_v2(unsigned char otp[][4],
 	int num_y_electrode;
 	int x_pitch, y_pitch, x_phys, y_phys;
 
-	num_x_electrode = SS4_NUMSENSOR_XOFFSET + (otp[1][0] & 0x0F);
-	num_y_electrode = SS4_NUMSENSOR_YOFFSET + ((otp[1][0] >> 4) & 0x0F);
+	if (IS_SS4PLUS_DEV(priv->dev_id)) {
+		num_x_electrode =
+			SS4PLUS_NUMSENSOR_XOFFSET + (otp[0][2] & 0x0F);
+		num_y_electrode =
+			SS4PLUS_NUMSENSOR_YOFFSET + ((otp[0][2] >> 4) & 0x0F);
+
+		priv->x_max =
+			(num_x_electrode - 1) * SS4PLUS_COUNT_PER_ELECTRODE;
+		priv->y_max =
+			(num_y_electrode - 1) * SS4PLUS_COUNT_PER_ELECTRODE;
 
-	priv->x_max = (num_x_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
-	priv->y_max = (num_y_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
+		x_pitch = (otp[0][1] & 0x0F) + SS4PLUS_MIN_PITCH_MM;
+		y_pitch = ((otp[0][1] >> 4) & 0x0F) + SS4PLUS_MIN_PITCH_MM;
 
-	x_pitch = ((otp[1][2] >> 2) & 0x07) + SS4_MIN_PITCH_MM;
-	y_pitch = ((otp[1][2] >> 5) & 0x07) + SS4_MIN_PITCH_MM;
+	} else {
+		num_x_electrode =
+			SS4_NUMSENSOR_XOFFSET + (otp[1][0] & 0x0F);
+		num_y_electrode =
+			SS4_NUMSENSOR_YOFFSET + ((otp[1][0] >> 4) & 0x0F);
+
+		priv->x_max =
+			(num_x_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
+		priv->y_max =
+			(num_y_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
+
+		x_pitch = ((otp[1][2] >> 2) & 0x07) + SS4_MIN_PITCH_MM;
+		y_pitch = ((otp[1][2] >> 5) & 0x07) + SS4_MIN_PITCH_MM;
+	}
 
 	x_phys = x_pitch * (num_x_electrode - 1); /* In 0.1 mm units */
 	y_phys = y_pitch * (num_y_electrode - 1); /* In 0.1 mm units */
@@ -2485,7 +2503,10 @@ static int alps_update_btn_info_ss4_v2(unsigned char otp[][4],
 {
 	unsigned char is_btnless;
 
-	is_btnless = (otp[1][1] >> 3) & 0x01;
+	if (IS_SS4PLUS_DEV(priv->dev_id))
+		is_btnless = (otp[1][0] >> 1) & 0x01;
+	else
+		is_btnless = (otp[1][1] >> 3) & 0x01;
 
 	if (is_btnless)
 		priv->flags |= ALPS_BUTTONPAD;
@@ -2493,6 +2514,21 @@ static int alps_update_btn_info_ss4_v2(unsigned char otp[][4],
 	return 0;
 }
 
+static int alps_update_dual_info_ss4_v2(unsigned char otp[][4],
+				       struct alps_data *priv)
+{
+	bool is_dual = false;
+
+	if (IS_SS4PLUS_DEV(priv->dev_id))
+		is_dual = (otp[0][0] >> 4) & 0x01;
+
+	if (is_dual)
+		priv->flags |= ALPS_DUALPOINT |
+					ALPS_DUALPOINT_WITH_PRESSURE;
+
+	return 0;
+}
+
 static int alps_set_defaults_ss4_v2(struct psmouse *psmouse,
 				    struct alps_data *priv)
 {
@@ -2508,6 +2544,8 @@ static int alps_set_defaults_ss4_v2(struct psmouse *psmouse,
 
 	alps_update_btn_info_ss4_v2(otp, priv);
 
+	alps_update_dual_info_ss4_v2(otp, priv);
+
 	return 0;
 }
 
@@ -2753,10 +2791,6 @@ static int alps_set_protocol(struct psmouse *psmouse,
 		if (alps_set_defaults_ss4_v2(psmouse, priv))
 			return -EIO;
 
-		if (priv->fw_ver[1] == 0x1)
-			priv->flags |= ALPS_DUALPOINT |
-					ALPS_DUALPOINT_WITH_PRESSURE;
-
 		break;
 	}
 
@@ -2827,10 +2861,7 @@ static int alps_identify(struct psmouse *psmouse, struct alps_data *priv)
 			   ec[2] >= 0x90 && ec[2] <= 0x9d) {
 			protocol = &alps_v3_protocol_data;
 		} else if (e7[0] == 0x73 && e7[1] == 0x03 &&
-			   e7[2] == 0x14 && ec[1] == 0x02) {
-			protocol = &alps_v8_protocol_data;
-		} else if (e7[0] == 0x73 && e7[1] == 0x03 &&
-			   e7[2] == 0x28 && ec[1] == 0x01) {
+			   (e7[2] == 0x14 || e7[2] == 0x28)) {
 			protocol = &alps_v8_protocol_data;
 		} else {
 			psmouse_dbg(psmouse,
@@ -2840,7 +2871,8 @@ static int alps_identify(struct psmouse *psmouse, struct alps_data *priv)
 	}
 
 	if (priv) {
-		/* Save the Firmware version */
+		/* Save Device ID and Firmware version */
+		memcpy(priv->dev_id, e7, 3);
 		memcpy(priv->fw_ver, ec, 3);
 		error = alps_set_protocol(psmouse, priv, protocol);
 		if (error)
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index 6d279aa27cb9..4334f2805d93 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -54,6 +54,16 @@ enum SS4_PACKET_ID {
 
 #define SS4_MASK_NORMAL_BUTTONS		0x07
 
+#define SS4PLUS_COUNT_PER_ELECTRODE	128
+#define SS4PLUS_NUMSENSOR_XOFFSET	16
+#define SS4PLUS_NUMSENSOR_YOFFSET	5
+#define SS4PLUS_MIN_PITCH_MM		37
+
+#define IS_SS4PLUS_DEV(_b)	(((_b[0]) == 0x73) &&	\
+				 ((_b[1]) == 0x03) &&	\
+				 ((_b[2]) == 0x28)		\
+				)
+
 #define SS4_IS_IDLE_V2(_b)	(((_b[0]) == 0x18) &&		\
 				 ((_b[1]) == 0x10) &&		\
 				 ((_b[2]) == 0x00) &&		\
@@ -283,6 +293,7 @@ struct alps_data {
 	int addr_command;
 	u16 proto_version;
 	u8 byte0, mask0;
+	u8 dev_id[3];
 	u8 fw_ver[3];
 	int flags;
 	int x_max;
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 352050e9031d..d5ab9ddef3e3 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -218,17 +218,19 @@ static int elan_query_product(struct elan_tp_data *data)
 
 static int elan_check_ASUS_special_fw(struct elan_tp_data *data)
 {
-	if (data->ic_type != 0x0E)
-		return false;
-
-	switch (data->product_id) {
-	case 0x05 ... 0x07:
-	case 0x09:
-	case 0x13:
+	if (data->ic_type == 0x0E) {
+		switch (data->product_id) {
+		case 0x05 ... 0x07:
+		case 0x09:
+		case 0x13:
+			return true;
+		}
+	} else if (data->ic_type == 0x08 && data->product_id == 0x26) {
+		/* ASUS EeeBook X205TA */
 		return true;
-	default:
-		return false;
 	}
+
+	return false;
 }
 
 static int __elan_initialize(struct elan_tp_data *data)
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index efc8ec342351..e73d968023f7 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1118,6 +1118,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
  * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E547   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
  * Fujitsu T725            0x470f01        05, 12, 09      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
@@ -1524,6 +1525,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 		},
 	},
 	{
+		/* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"),
+		},
+	},
+	{
 		/* Fujitsu LIFEBOOK E554  does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c
index 198678613382..34dfee555b20 100644
--- a/drivers/input/rmi4/rmi_f30.c
+++ b/drivers/input/rmi4/rmi_f30.c
@@ -170,6 +170,10 @@ static int rmi_f30_config(struct rmi_function *fn)
 				rmi_get_platform_data(fn->rmi_dev);
 	int error;
 
+	/* can happen if f30_data.disable is set */
+	if (!f30)
+		return 0;
+
 	if (pdata->f30_data.trackstick_buttons) {
 		/* Try [re-]establish link to F03. */
 		f30->f03 = rmi_find_function(fn->rmi_dev, 0x03);
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 05afd16ea9c9..09720d950686 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -120,6 +120,13 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 		},
 	},
 	{
+		/* Dell Embedded Box PC 3000 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"),
+		},
+	},
+	{
 		/* OQO Model 01 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "OQO"),
@@ -513,6 +520,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
 		},
 	},
+	{
+		/* TUXEDO BU1406 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
+		},
+	},
 	{ }
 };
 
@@ -606,6 +620,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "20046"),
 		},
 	},
+	{
+		/* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/input/tablet/hanwang.c b/drivers/input/tablet/hanwang.c
index cd852059b99e..df4bea96d7ed 100644
--- a/drivers/input/tablet/hanwang.c
+++ b/drivers/input/tablet/hanwang.c
@@ -340,6 +340,9 @@ static int hanwang_probe(struct usb_interface *intf, const struct usb_device_id
 	int error;
 	int i;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	hanwang = kzalloc(sizeof(struct hanwang), GFP_KERNEL);
 	input_dev = input_allocate_device();
 	if (!hanwang || !input_dev) {
diff --git a/drivers/input/tablet/kbtab.c b/drivers/input/tablet/kbtab.c
index e850d7e8afbc..4d9d64908b59 100644
--- a/drivers/input/tablet/kbtab.c
+++ b/drivers/input/tablet/kbtab.c
@@ -122,6 +122,9 @@ static int kbtab_probe(struct usb_interface *intf, const struct usb_device_id *i
 	struct input_dev *input_dev;
 	int error = -ENOMEM;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	kbtab = kzalloc(sizeof(struct kbtab), GFP_KERNEL);
 	input_dev = input_allocate_device();
 	if (!kbtab || !input_dev)
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index aefb6e11f88a..4c0eecae065c 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -527,6 +527,9 @@ static int sur40_probe(struct usb_interface *interface,
 	if (iface_desc->desc.bInterfaceClass != 0xFF)
 		return -ENODEV;
 
+	if (iface_desc->desc.bNumEndpoints < 5)
+		return -ENODEV;
+
 	/* Use endpoint #4 (0x86). */
 	endpoint = &iface_desc->endpoint[4].desc;
 	if (endpoint->bEndpointAddress != TOUCH_ENDPOINT)
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 37e204f3d9be..6ee3a25ae731 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -327,6 +327,14 @@ config S390_IOMMU
 	help
 	  Support for the IOMMU API for s390 PCI devices.
 
+config S390_CCW_IOMMU
+	bool "S390 CCW IOMMU Support"
+	depends on S390 && CCW
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
 config MTK_IOMMU
 	bool "MTK IOMMU Support"
 	depends on ARM || ARM64
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 98940d1392cb..63cacf5d6cf2 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1234,7 +1234,7 @@ static void __domain_flush_pages(struct protection_domain *domain,
 
 	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
 
-	for (i = 0; i < amd_iommus_present; ++i) {
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
 			continue;
 
@@ -1278,7 +1278,7 @@ static void domain_flush_complete(struct protection_domain *domain)
 {
 	int i;
 
-	for (i = 0; i < amd_iommus_present; ++i) {
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (domain && !domain->dev_iommu[i])
 			continue;
 
@@ -3202,7 +3202,7 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 
 	region = iommu_alloc_resv_region(MSI_RANGE_START,
 					 MSI_RANGE_END - MSI_RANGE_START + 1,
-					 0, IOMMU_RESV_RESERVED);
+					 0, IOMMU_RESV_MSI);
 	if (!region)
 		return;
 	list_add_tail(&region->list, head);
@@ -3363,7 +3363,7 @@ static int __flush_pasid(struct protection_domain *domain, int pasid,
 	 * IOMMU TLB needs to be flushed before Device TLB to
 	 * prevent device TLB refill from IOMMU TLB
 	 */
-	for (i = 0; i < amd_iommus_present; ++i) {
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (domain->dev_iommu[i] == 0)
 			continue;
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6130278c5d71..5a11328f4d98 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -167,7 +167,9 @@ LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
 
 /* Array to assign indices to IOMMUs*/
 struct amd_iommu *amd_iommus[MAX_IOMMUS];
-int amd_iommus_present;
+
+/* Number of IOMMUs present in the system */
+static int amd_iommus_present;
 
 /* IOMMUs have a non-present cache? */
 bool amd_iommu_np_cache __read_mostly;
@@ -254,10 +256,6 @@ static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
 static void init_device_table_dma(void);
 
-static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
-				    u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write);
-
 static inline void update_last_devid(u16 devid)
 {
 	if (devid > amd_iommu_last_bdf)
@@ -272,6 +270,11 @@ static inline unsigned long tbl_size(int entry_size)
 	return 1UL << shift;
 }
 
+int amd_iommu_get_num_iommus(void)
+{
+	return amd_iommus_present;
+}
+
 /* Access to l1 and l2 indexed register spaces */
 
 static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
@@ -1336,7 +1339,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);
-	iommu->index             = amd_iommus_present++;
+	iommu->index = amd_iommus_present++;
 
 	if (unlikely(iommu->index >= MAX_IOMMUS)) {
 		WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n");
@@ -1477,6 +1480,8 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 	return 0;
 }
 
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value, bool is_write);
 
 static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 {
@@ -1488,8 +1493,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 	amd_iommu_pc_present = true;
 
 	/* Check if the performance counters can be written to */
-	if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) ||
-	    (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) ||
+	if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
+	    (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
 	    (val != val2)) {
 		pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
 		amd_iommu_pc_present = false;
@@ -2711,6 +2716,18 @@ bool amd_iommu_v2_supported(void)
 }
 EXPORT_SYMBOL(amd_iommu_v2_supported);
 
+struct amd_iommu *get_amd_iommu(unsigned int idx)
+{
+	unsigned int i = 0;
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		if (i++ == idx)
+			return iommu;
+	return NULL;
+}
+EXPORT_SYMBOL(get_amd_iommu);
+
 /****************************************************************************
  *
  * IOMMU EFR Performance Counter support functionality. This code allows
@@ -2718,17 +2735,14 @@ EXPORT_SYMBOL(amd_iommu_v2_supported);
  *
  ****************************************************************************/
 
-u8 amd_iommu_pc_get_max_banks(u16 devid)
+u8 amd_iommu_pc_get_max_banks(unsigned int idx)
 {
-	struct amd_iommu *iommu;
-	u8 ret = 0;
+	struct amd_iommu *iommu = get_amd_iommu(idx);
 
-	/* locate the iommu governing the devid */
-	iommu = amd_iommu_rlookup_table[devid];
 	if (iommu)
-		ret = iommu->max_banks;
+		return iommu->max_banks;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_max_banks);
 
@@ -2738,62 +2752,69 @@ bool amd_iommu_pc_supported(void)
 }
 EXPORT_SYMBOL(amd_iommu_pc_supported);
 
-u8 amd_iommu_pc_get_max_counters(u16 devid)
+u8 amd_iommu_pc_get_max_counters(unsigned int idx)
 {
-	struct amd_iommu *iommu;
-	u8 ret = 0;
+	struct amd_iommu *iommu = get_amd_iommu(idx);
 
-	/* locate the iommu governing the devid */
-	iommu = amd_iommu_rlookup_table[devid];
 	if (iommu)
-		ret = iommu->max_counters;
+		return iommu->max_counters;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
 
-static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
-				    u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write)
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value, bool is_write)
 {
 	u32 offset;
 	u32 max_offset_lim;
 
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_present)
+		return -ENODEV;
+
 	/* Check for valid iommu and pc register indexing */
-	if (WARN_ON((fxn > 0x28) || (fxn & 7)))
+	if (WARN_ON(!iommu || (fxn > 0x28) || (fxn & 7)))
 		return -ENODEV;
 
-	offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
+	offset = (u32)(((0x40 | bank) << 12) | (cntr << 8) | fxn);
 
 	/* Limit the offset to the hw defined mmio region aperture */
-	max_offset_lim = (u32)(((0x40|iommu->max_banks) << 12) |
+	max_offset_lim = (u32)(((0x40 | iommu->max_banks) << 12) |
 				(iommu->max_counters << 8) | 0x28);
 	if ((offset < MMIO_CNTR_REG_OFFSET) ||
 	    (offset > max_offset_lim))
 		return -EINVAL;
 
 	if (is_write) {
-		writel((u32)*value, iommu->mmio_base + offset);
-		writel((*value >> 32), iommu->mmio_base + offset + 4);
+		u64 val = *value & GENMASK_ULL(47, 0);
+
+		writel((u32)val, iommu->mmio_base + offset);
+		writel((val >> 32), iommu->mmio_base + offset + 4);
 	} else {
 		*value = readl(iommu->mmio_base + offset + 4);
 		*value <<= 32;
-		*value = readl(iommu->mmio_base + offset);
+		*value |= readl(iommu->mmio_base + offset);
+		*value &= GENMASK_ULL(47, 0);
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
 
-int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write)
+int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
 {
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+	if (!iommu)
+		return -EINVAL;
 
-	/* Make sure the IOMMU PC resource is available */
-	if (!amd_iommu_pc_present || iommu == NULL)
-		return -ENODEV;
+	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false);
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_reg);
+
+int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
+{
+	if (!iommu)
+		return -EINVAL;
 
-	return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn,
-					value, is_write);
+	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
 }
+EXPORT_SYMBOL(amd_iommu_pc_set_reg);
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 7eb60c15c582..466260f8a1df 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -21,6 +21,7 @@
 
 #include "amd_iommu_types.h"
 
+extern int amd_iommu_get_num_iommus(void);
 extern int amd_iommu_init_dma_ops(void);
 extern int amd_iommu_init_passthrough(void);
 extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
@@ -56,13 +57,6 @@ extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
 extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
 extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
 
-/* IOMMU Performance Counter functions */
-extern bool amd_iommu_pc_supported(void);
-extern u8 amd_iommu_pc_get_max_banks(u16 devid);
-extern u8 amd_iommu_pc_get_max_counters(u16 devid);
-extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
-				    u64 *value, bool is_write);
-
 #ifdef CONFIG_IRQ_REMAP
 extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
 #else
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 003f3ceb2661..4de8f4160bb8 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -611,9 +611,6 @@ extern struct list_head amd_iommu_list;
  */
 extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
 
-/* Number of IOMMUs present in the system */
-extern int amd_iommus_present;
-
 /*
  * Declarations for the global list of all protection domains
  */
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 5806a6acc94e..591bb96047c9 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1888,7 +1888,7 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
 
 	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
-					 prot, IOMMU_RESV_MSI);
+					 prot, IOMMU_RESV_SW_MSI);
 	if (!region)
 		return;
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index abf6496843a6..b493c99e17f7 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1608,7 +1608,7 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
 
 	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
-					 prot, IOMMU_RESV_MSI);
+					 prot, IOMMU_RESV_SW_MSI);
 	if (!region)
 		return;
 
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index a7e0821c9967..c01bfcdb2383 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -512,7 +512,13 @@ static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
 	spin_lock_irqsave(&data->lock, flags);
 	if (data->active && data->version >= MAKE_MMU_VER(3, 3)) {
 		clk_enable(data->clk_master);
-		__sysmmu_tlb_invalidate_entry(data, iova, 1);
+		if (sysmmu_block(data)) {
+			if (data->version >= MAKE_MMU_VER(5, 0))
+				__sysmmu_tlb_invalidate(data);
+			else
+				__sysmmu_tlb_invalidate_entry(data, iova, 1);
+			sysmmu_unblock(data);
+		}
 		clk_disable(data->clk_master);
 	}
 	spin_unlock_irqrestore(&data->lock, flags);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 238ad3447712..d412a313a372 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -916,7 +916,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 				 * which we used for the IOMMU lookup. Strictly speaking
 				 * we could do this for all PCI devices; we only need to
 				 * get the BDF# from the scope table for ACPI matches. */
-				if (pdev->is_virtfn)
+				if (pdev && pdev->is_virtfn)
 					goto got_pdev;
 
 				*bus = drhd->devices[i].bus;
@@ -5249,7 +5249,7 @@ static void intel_iommu_get_resv_regions(struct device *device,
 
 	reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
 				      IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
-				      0, IOMMU_RESV_RESERVED);
+				      0, IOMMU_RESV_MSI);
 	if (!reg)
 		return;
 	list_add_tail(&reg->list, head);
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 1c049e2e12bf..8d6ca28c3e1f 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -422,8 +422,12 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
 			pte |= ARM_V7S_ATTR_NS_TABLE;
 
 		__arm_v7s_set_pte(ptep, pte, 1, cfg);
-	} else {
+	} else if (ARM_V7S_PTE_IS_TABLE(pte, lvl)) {
 		cptep = iopte_deref(pte, lvl);
+	} else {
+		/* We require an unmap first */
+		WARN_ON(!selftest_running);
+		return -EEXIST;
 	}
 
 	/* Rinse, repeat */
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index feacc54bec68..f9bc6ebb8140 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -335,8 +335,12 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 		if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS)
 			pte |= ARM_LPAE_PTE_NSTABLE;
 		__arm_lpae_set_pte(ptep, pte, cfg);
-	} else {
+	} else if (!iopte_leaf(pte, lvl)) {
 		cptep = iopte_deref(pte, data);
+	} else {
+		/* We require an unmap first */
+		WARN_ON(!selftest_running);
+		return -EEXIST;
 	}
 
 	/* Rinse, repeat */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8ea14f41a979..3b67144dead2 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -72,6 +72,7 @@ static const char * const iommu_group_resv_type_string[] = {
 	[IOMMU_RESV_DIRECT]	= "direct",
 	[IOMMU_RESV_RESERVED]	= "reserved",
 	[IOMMU_RESV_MSI]	= "msi",
+	[IOMMU_RESV_SW_MSI]	= "msi",
 };
 
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
@@ -1743,8 +1744,8 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 }
 
 struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
-						  size_t length,
-						  int prot, int type)
+						  size_t length, int prot,
+						  enum iommu_resv_type type)
 {
 	struct iommu_resv_region *region;
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 125528f39e92..595d0c95563b 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -115,6 +115,12 @@ config DW_APB_ICTL
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 
+config FARADAY_FTINTC010
+	bool
+	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
+	select SPARSE_IRQ
+
 config HISILICON_IRQ_MBIGEN
 	bool
 	select ARM_GIC_V3
@@ -262,6 +268,7 @@ config IRQ_MXS
 
 config MVEBU_ODMI
 	bool
+	select GENERIC_MSI_IRQ_DOMAIN
 
 config MVEBU_PIC
 	bool
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 152bc40b6762..b64c59b838a0 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_ATH79)			+= irq-ath79-misc.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2836.o
 obj-$(CONFIG_ARCH_EXYNOS)		+= exynos-combiner.o
-obj-$(CONFIG_ARCH_GEMINI)		+= irq-gemini.o
+obj-$(CONFIG_FARADAY_FTINTC010)		+= irq-ftintc010.o
 obj-$(CONFIG_ARCH_HIP04)		+= irq-hip04.o
 obj-$(CONFIG_ARCH_LPC32XX)		+= irq-lpc32xx.o
 obj-$(CONFIG_ARCH_MMP)			+= irq-mmp.o
@@ -16,7 +16,6 @@ obj-$(CONFIG_ARCH_S3C24XX)		+= irq-s3c24xx.o
 obj-$(CONFIG_DW_APB_ICTL)		+= irq-dw-apb-ictl.o
 obj-$(CONFIG_METAG)			+= irq-metag-ext.o
 obj-$(CONFIG_METAG_PERFCOUNTER_IRQS)	+= irq-metag.o
-obj-$(CONFIG_ARCH_MOXART)		+= irq-moxart.o
 obj-$(CONFIG_CLPS711X_IRQCHIP)		+= irq-clps711x.o
 obj-$(CONFIG_OR1K_PIC)			+= irq-or1k-pic.o
 obj-$(CONFIG_ORION_IRQCHIP)		+= irq-orion.o
@@ -62,7 +61,7 @@ obj-$(CONFIG_BCM7120_L2_IRQ)		+= irq-bcm7120-l2.o
 obj-$(CONFIG_BRCMSTB_L2_IRQ)		+= irq-brcmstb-l2.o
 obj-$(CONFIG_KEYSTONE_IRQ)		+= irq-keystone.o
 obj-$(CONFIG_MIPS_GIC)			+= irq-mips-gic.o
-obj-$(CONFIG_ARCH_MEDIATEK)		+= irq-mtk-sysirq.o
+obj-$(CONFIG_ARCH_MEDIATEK)		+= irq-mtk-sysirq.o irq-mtk-cirq.o
 obj-$(CONFIG_ARCH_DIGICOLOR)		+= irq-digicolor.o
 obj-$(CONFIG_RENESAS_H8300H_INTC)	+= irq-renesas-h8300h.o
 obj-$(CONFIG_RENESAS_H8S_INTC)		+= irq-renesas-h8s.o
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 2a624d87a035..c04ee9a23d09 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -150,6 +150,8 @@ static int aic5_set_type(struct irq_data *d, unsigned type)
 }
 
 #ifdef CONFIG_PM
+static u32 *smr_cache;
+
 static void aic5_suspend(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
@@ -159,6 +161,12 @@ static void aic5_suspend(struct irq_data *d)
 	int i;
 	u32 mask;
 
+	if (smr_cache)
+		for (i = 0; i < domain->revmap_size; i++) {
+			irq_reg_writel(bgc, i, AT91_AIC5_SSR);
+			smr_cache[i] = irq_reg_readl(bgc, AT91_AIC5_SMR);
+		}
+
 	irq_gc_lock(bgc);
 	for (i = 0; i < dgc->irqs_per_chip; i++) {
 		mask = 1 << i;
@@ -184,9 +192,21 @@ static void aic5_resume(struct irq_data *d)
 	u32 mask;
 
 	irq_gc_lock(bgc);
+
+	if (smr_cache) {
+		irq_reg_writel(bgc, 0xffffffff, AT91_AIC5_SPU);
+		for (i = 0; i < domain->revmap_size; i++) {
+			irq_reg_writel(bgc, i, AT91_AIC5_SSR);
+			irq_reg_writel(bgc, i, AT91_AIC5_SVR);
+			irq_reg_writel(bgc, smr_cache[i], AT91_AIC5_SMR);
+		}
+	}
+
 	for (i = 0; i < dgc->irqs_per_chip; i++) {
 		mask = 1 << i;
-		if ((mask & gc->mask_cache) == (mask & gc->wake_active))
+
+		if (!smr_cache &&
+		    ((mask & gc->mask_cache) == (mask & gc->wake_active)))
 			continue;
 
 		irq_reg_writel(bgc, i + gc->irq_base, AT91_AIC5_SSR);
@@ -342,6 +362,13 @@ static int __init aic5_of_init(struct device_node *node,
 static int __init sama5d2_aic5_of_init(struct device_node *node,
 				       struct device_node *parent)
 {
+#ifdef CONFIG_PM
+	smr_cache = kcalloc(DIV_ROUND_UP(NR_SAMA5D2_IRQS, 32) * 32,
+			    sizeof(*smr_cache), GFP_KERNEL);
+	if (!smr_cache)
+		return -ENOMEM;
+#endif
+
 	return aic5_of_init(node, parent, NR_SAMA5D2_IRQS);
 }
 IRQCHIP_DECLARE(sama5d2_aic5, "atmel,sama5d2-aic", sama5d2_aic5_of_init);
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 1eef56a89b1f..f96601268f71 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = {
 
 static int __init crossbar_of_init(struct device_node *node)
 {
-	int i, size, max = 0, reserved = 0, entry;
+	u32 max = 0, entry, reg_size;
+	int i, size, reserved = 0;
 	const __be32 *irqsr;
 	int ret = -ENOMEM;
 
@@ -275,9 +276,9 @@ static int __init crossbar_of_init(struct device_node *node)
 	if (!cb->register_offsets)
 		goto err_irq_map;
 
-	of_property_read_u32(node, "ti,reg-size", &size);
+	of_property_read_u32(node, "ti,reg-size", &reg_size);
 
-	switch (size) {
+	switch (reg_size) {
 	case 1:
 		cb->write = crossbar_writeb;
 		break;
@@ -303,7 +304,7 @@ static int __init crossbar_of_init(struct device_node *node)
 			continue;
 
 		cb->register_offsets[i] = reserved;
-		reserved += size;
+		reserved += reg_size;
 	}
 
 	of_property_read_u32(node, "ti,irqs-safe-map", &cb->safe_map);
diff --git a/drivers/irqchip/irq-ftintc010.c b/drivers/irqchip/irq-ftintc010.c
new file mode 100644
index 000000000000..cd2dc8bbbe9c
--- /dev/null
+++ b/drivers/irqchip/irq-ftintc010.c
@@ -0,0 +1,194 @@
+/*
+ * irqchip for the Faraday Technology FTINTC010 Copyright (C) 2017 Linus
+ * Walleij <linus.walleij@linaro.org>
+ *
+ * Based on arch/arm/mach-gemini/irq.c
+ * Copyright (C) 2001-2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@gmail.com>
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/versatile-fpga.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/cpu.h>
+
+#include <asm/exception.h>
+#include <asm/mach/irq.h>
+
+#define FT010_NUM_IRQS 32
+
+#define FT010_IRQ_SOURCE(base_addr)	(base_addr + 0x00)
+#define FT010_IRQ_MASK(base_addr)	(base_addr + 0x04)
+#define FT010_IRQ_CLEAR(base_addr)	(base_addr + 0x08)
+/* Selects level- or edge-triggered */
+#define FT010_IRQ_MODE(base_addr)	(base_addr + 0x0C)
+/* Selects active low/high or falling/rising edge */
+#define FT010_IRQ_POLARITY(base_addr)	(base_addr + 0x10)
+#define FT010_IRQ_STATUS(base_addr)	(base_addr + 0x14)
+#define FT010_FIQ_SOURCE(base_addr)	(base_addr + 0x20)
+#define FT010_FIQ_MASK(base_addr)	(base_addr + 0x24)
+#define FT010_FIQ_CLEAR(base_addr)	(base_addr + 0x28)
+#define FT010_FIQ_MODE(base_addr)	(base_addr + 0x2C)
+#define FT010_FIQ_POLARITY(base_addr)	(base_addr + 0x30)
+#define FT010_FIQ_STATUS(base_addr)	(base_addr + 0x34)
+
+/**
+ * struct ft010_irq_data - irq data container for the Faraday IRQ controller
+ * @base: memory offset in virtual memory
+ * @chip: chip container for this instance
+ * @domain: IRQ domain for this instance
+ */
+struct ft010_irq_data {
+	void __iomem *base;
+	struct irq_chip chip;
+	struct irq_domain *domain;
+};
+
+static void ft010_irq_mask(struct irq_data *d)
+{
+	struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+	unsigned int mask;
+
+	mask = readl(FT010_IRQ_MASK(f->base));
+	mask &= ~BIT(irqd_to_hwirq(d));
+	writel(mask, FT010_IRQ_MASK(f->base));
+}
+
+static void ft010_irq_unmask(struct irq_data *d)
+{
+	struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+	unsigned int mask;
+
+	mask = readl(FT010_IRQ_MASK(f->base));
+	mask |= BIT(irqd_to_hwirq(d));
+	writel(mask, FT010_IRQ_MASK(f->base));
+}
+
+static void ft010_irq_ack(struct irq_data *d)
+{
+	struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+
+	writel(BIT(irqd_to_hwirq(d)), FT010_IRQ_CLEAR(f->base));
+}
+
+static int ft010_irq_set_type(struct irq_data *d, unsigned int trigger)
+{
+	struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+	int offset = irqd_to_hwirq(d);
+	u32 mode, polarity;
+
+	mode = readl(FT010_IRQ_MODE(f->base));
+	polarity = readl(FT010_IRQ_POLARITY(f->base));
+
+	if (trigger & (IRQ_TYPE_LEVEL_LOW)) {
+		irq_set_handler_locked(d, handle_level_irq);
+		mode &= ~BIT(offset);
+		polarity |= BIT(offset);
+	} else if (trigger & (IRQ_TYPE_LEVEL_HIGH)) {
+		irq_set_handler_locked(d, handle_level_irq);
+		mode &= ~BIT(offset);
+		polarity &= ~BIT(offset);
+	} else if (trigger & IRQ_TYPE_EDGE_FALLING) {
+		irq_set_handler_locked(d, handle_edge_irq);
+		mode |= BIT(offset);
+		polarity |= BIT(offset);
+	} else if (trigger & IRQ_TYPE_EDGE_RISING) {
+		irq_set_handler_locked(d, handle_edge_irq);
+		mode |= BIT(offset);
+		polarity &= ~BIT(offset);
+	} else {
+		irq_set_handler_locked(d, handle_bad_irq);
+		pr_warn("Faraday IRQ: no supported trigger selected for line %d\n",
+			offset);
+	}
+
+	writel(mode, FT010_IRQ_MODE(f->base));
+	writel(polarity, FT010_IRQ_POLARITY(f->base));
+
+	return 0;
+}
+
+static struct irq_chip ft010_irq_chip = {
+	.name		= "FTINTC010",
+	.irq_ack	= ft010_irq_ack,
+	.irq_mask	= ft010_irq_mask,
+	.irq_unmask	= ft010_irq_unmask,
+	.irq_set_type	= ft010_irq_set_type,
+};
+
+/* Local static for the IRQ entry call */
+static struct ft010_irq_data firq;
+
+asmlinkage void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *regs)
+{
+	struct ft010_irq_data *f = &firq;
+	int irq;
+	u32 status;
+
+	while ((status = readl(FT010_IRQ_STATUS(f->base)))) {
+		irq = ffs(status) - 1;
+		handle_domain_irq(f->domain, irq, regs);
+	}
+}
+
+static int ft010_irqdomain_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hwirq)
+{
+	struct ft010_irq_data *f = d->host_data;
+
+	irq_set_chip_data(irq, f);
+	/* All IRQs should set up their type, flags as bad by default */
+	irq_set_chip_and_handler(irq, &ft010_irq_chip, handle_bad_irq);
+	irq_set_probe(irq);
+
+	return 0;
+}
+
+static void ft010_irqdomain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops ft010_irqdomain_ops = {
+	.map = ft010_irqdomain_map,
+	.unmap = ft010_irqdomain_unmap,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+int __init ft010_of_init_irq(struct device_node *node,
+			      struct device_node *parent)
+{
+	struct ft010_irq_data *f = &firq;
+
+	/*
+	 * Disable the idle handler by default since it is buggy
+	 * For more info see arch/arm/mach-gemini/idle.c
+	 */
+	cpu_idle_poll_ctrl(true);
+
+	f->base = of_iomap(node, 0);
+	WARN(!f->base, "unable to map gemini irq registers\n");
+
+	/* Disable all interrupts */
+	writel(0, FT010_IRQ_MASK(f->base));
+	writel(0, FT010_FIQ_MASK(f->base));
+
+	f->domain = irq_domain_add_simple(node, FT010_NUM_IRQS, 0,
+					  &ft010_irqdomain_ops, f);
+	set_handle_irq(ft010_irqchip_handle_irq);
+
+	return 0;
+}
+IRQCHIP_DECLARE(faraday, "faraday,ftintc010",
+		ft010_of_init_irq);
+IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller",
+		ft010_of_init_irq);
+IRQCHIP_DECLARE(moxa, "moxa,moxart-ic",
+		ft010_of_init_irq);
diff --git a/drivers/irqchip/irq-gemini.c b/drivers/irqchip/irq-gemini.c
deleted file mode 100644
index 495224c743ee..000000000000
--- a/drivers/irqchip/irq-gemini.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * irqchip for the Cortina Systems Gemini Copyright (C) 2017 Linus
- * Walleij <linus.walleij@linaro.org>
- *
- * Based on arch/arm/mach-gemini/irq.c
- * Copyright (C) 2001-2006 Storlink, Corp.
- * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- */
-#include <linux/bitops.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/versatile-fpga.h>
-#include <linux/irqdomain.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/cpu.h>
-
-#include <asm/exception.h>
-#include <asm/mach/irq.h>
-
-#define GEMINI_NUM_IRQS 32
-
-#define GEMINI_IRQ_SOURCE(base_addr)	(base_addr + 0x00)
-#define GEMINI_IRQ_MASK(base_addr)	(base_addr + 0x04)
-#define GEMINI_IRQ_CLEAR(base_addr)	(base_addr + 0x08)
-#define GEMINI_IRQ_MODE(base_addr)	(base_addr + 0x0C)
-#define GEMINI_IRQ_POLARITY(base_addr)	(base_addr + 0x10)
-#define GEMINI_IRQ_STATUS(base_addr)	(base_addr + 0x14)
-#define GEMINI_FIQ_SOURCE(base_addr)	(base_addr + 0x20)
-#define GEMINI_FIQ_MASK(base_addr)	(base_addr + 0x24)
-#define GEMINI_FIQ_CLEAR(base_addr)	(base_addr + 0x28)
-#define GEMINI_FIQ_MODE(base_addr)	(base_addr + 0x2C)
-#define GEMINI_FIQ_POLARITY(base_addr)	(base_addr + 0x30)
-#define GEMINI_FIQ_STATUS(base_addr)	(base_addr + 0x34)
-
-/**
- * struct gemini_irq_data - irq data container for the Gemini IRQ controller
- * @base: memory offset in virtual memory
- * @chip: chip container for this instance
- * @domain: IRQ domain for this instance
- */
-struct gemini_irq_data {
-	void __iomem *base;
-	struct irq_chip chip;
-	struct irq_domain *domain;
-};
-
-static void gemini_irq_mask(struct irq_data *d)
-{
-	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
-	unsigned int mask;
-
-	mask = readl(GEMINI_IRQ_MASK(g->base));
-	mask &= ~BIT(irqd_to_hwirq(d));
-	writel(mask, GEMINI_IRQ_MASK(g->base));
-}
-
-static void gemini_irq_unmask(struct irq_data *d)
-{
-	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
-	unsigned int mask;
-
-	mask = readl(GEMINI_IRQ_MASK(g->base));
-	mask |= BIT(irqd_to_hwirq(d));
-	writel(mask, GEMINI_IRQ_MASK(g->base));
-}
-
-static void gemini_irq_ack(struct irq_data *d)
-{
-	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
-
-	writel(BIT(irqd_to_hwirq(d)), GEMINI_IRQ_CLEAR(g->base));
-}
-
-static int gemini_irq_set_type(struct irq_data *d, unsigned int trigger)
-{
-	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
-	int offset = irqd_to_hwirq(d);
-	u32 mode, polarity;
-
-	mode = readl(GEMINI_IRQ_MODE(g->base));
-	polarity = readl(GEMINI_IRQ_POLARITY(g->base));
-
-	if (trigger & (IRQ_TYPE_LEVEL_HIGH)) {
-		irq_set_handler_locked(d, handle_level_irq);
-		/* Disable edge detection */
-		mode &= ~BIT(offset);
-		polarity &= ~BIT(offset);
-	} else if (trigger & IRQ_TYPE_EDGE_RISING) {
-		irq_set_handler_locked(d, handle_edge_irq);
-		mode |= BIT(offset);
-		polarity |= BIT(offset);
-	} else if (trigger & IRQ_TYPE_EDGE_FALLING) {
-		irq_set_handler_locked(d, handle_edge_irq);
-		mode |= BIT(offset);
-		polarity &= ~BIT(offset);
-	} else {
-		irq_set_handler_locked(d, handle_bad_irq);
-		pr_warn("GEMINI IRQ: no supported trigger selected for line %d\n",
-			offset);
-	}
-
-	writel(mode, GEMINI_IRQ_MODE(g->base));
-	writel(polarity, GEMINI_IRQ_POLARITY(g->base));
-
-	return 0;
-}
-
-static struct irq_chip gemini_irq_chip = {
-	.name		= "GEMINI",
-	.irq_ack	= gemini_irq_ack,
-	.irq_mask	= gemini_irq_mask,
-	.irq_unmask	= gemini_irq_unmask,
-	.irq_set_type	= gemini_irq_set_type,
-};
-
-/* Local static for the IRQ entry call */
-static struct gemini_irq_data girq;
-
-asmlinkage void __exception_irq_entry gemini_irqchip_handle_irq(struct pt_regs *regs)
-{
-	struct gemini_irq_data *g = &girq;
-	int irq;
-	u32 status;
-
-	while ((status = readl(GEMINI_IRQ_STATUS(g->base)))) {
-		irq = ffs(status) - 1;
-		handle_domain_irq(g->domain, irq, regs);
-	}
-}
-
-static int gemini_irqdomain_map(struct irq_domain *d, unsigned int irq,
-				irq_hw_number_t hwirq)
-{
-	struct gemini_irq_data *g = d->host_data;
-
-	irq_set_chip_data(irq, g);
-	/* All IRQs should set up their type, flags as bad by default */
-	irq_set_chip_and_handler(irq, &gemini_irq_chip, handle_bad_irq);
-	irq_set_probe(irq);
-
-	return 0;
-}
-
-static void gemini_irqdomain_unmap(struct irq_domain *d, unsigned int irq)
-{
-	irq_set_chip_and_handler(irq, NULL, NULL);
-	irq_set_chip_data(irq, NULL);
-}
-
-static const struct irq_domain_ops gemini_irqdomain_ops = {
-	.map = gemini_irqdomain_map,
-	.unmap = gemini_irqdomain_unmap,
-	.xlate = irq_domain_xlate_onetwocell,
-};
-
-int __init gemini_of_init_irq(struct device_node *node,
-			      struct device_node *parent)
-{
-	struct gemini_irq_data *g = &girq;
-
-	/*
-	 * Disable the idle handler by default since it is buggy
-	 * For more info see arch/arm/mach-gemini/idle.c
-	 */
-	cpu_idle_poll_ctrl(true);
-
-	g->base = of_iomap(node, 0);
-	WARN(!g->base, "unable to map gemini irq registers\n");
-
-	/* Disable all interrupts */
-	writel(0, GEMINI_IRQ_MASK(g->base));
-	writel(0, GEMINI_FIQ_MASK(g->base));
-
-	g->domain = irq_domain_add_simple(node, GEMINI_NUM_IRQS, 0,
-					  &gemini_irqdomain_ops, g);
-	set_handle_irq(gemini_irqchip_handle_irq);
-
-	return 0;
-}
-IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller",
-		gemini_of_init_irq);
diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
index 470b4aa7d62c..9e9dda33eb17 100644
--- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi_iort.h>
 #include <linux/device.h>
 #include <linux/msi.h>
 #include <linux/of.h>
@@ -24,15 +25,11 @@ static struct irq_chip its_pmsi_irq_chip = {
 	.name			= "ITS-pMSI",
 };
 
-static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
-			    int nvec, msi_alloc_info_t *info)
+static int of_pmsi_get_dev_id(struct irq_domain *domain, struct device *dev,
+				  u32 *dev_id)
 {
-	struct msi_domain_info *msi_info;
-	u32 dev_id;
 	int ret, index = 0;
 
-	msi_info = msi_get_domain_info(domain->parent);
-
 	/* Suck the DeviceID out of the msi-parent property */
 	do {
 		struct of_phandle_args args;
@@ -43,11 +40,32 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 		if (args.np == irq_domain_get_of_node(domain)) {
 			if (WARN_ON(args.args_count != 1))
 				return -EINVAL;
-			dev_id = args.args[0];
+			*dev_id = args.args[0];
 			break;
 		}
 	} while (!ret);
 
+	return ret;
+}
+
+int __weak iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
+{
+	return -1;
+}
+
+static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
+			    int nvec, msi_alloc_info_t *info)
+{
+	struct msi_domain_info *msi_info;
+	u32 dev_id;
+	int ret;
+
+	msi_info = msi_get_domain_info(domain->parent);
+
+	if (dev->of_node)
+		ret = of_pmsi_get_dev_id(domain, dev, &dev_id);
+	else
+		ret = iort_pmsi_get_dev_id(dev, &dev_id);
 	if (ret)
 		return ret;
 
@@ -73,34 +91,79 @@ static struct of_device_id its_device_id[] = {
 	{},
 };
 
-static int __init its_pmsi_init(void)
+static int __init its_pmsi_init_one(struct fwnode_handle *fwnode,
+				const char *name)
 {
-	struct device_node *np;
 	struct irq_domain *parent;
 
+	parent = irq_find_matching_fwnode(fwnode, DOMAIN_BUS_NEXUS);
+	if (!parent || !msi_get_domain_info(parent)) {
+		pr_err("%s: unable to locate ITS domain\n", name);
+		return -ENXIO;
+	}
+
+	if (!platform_msi_create_irq_domain(fwnode, &its_pmsi_domain_info,
+					    parent)) {
+		pr_err("%s: unable to create platform domain\n", name);
+		return -ENXIO;
+	}
+
+	pr_info("Platform MSI: %s domain created\n", name);
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+static int __init
+its_pmsi_parse_madt(struct acpi_subtable_header *header,
+			const unsigned long end)
+{
+	struct acpi_madt_generic_translator *its_entry;
+	struct fwnode_handle *domain_handle;
+	const char *node_name;
+	int err = -ENXIO;
+
+	its_entry = (struct acpi_madt_generic_translator *)header;
+	node_name = kasprintf(GFP_KERNEL, "ITS@0x%lx",
+			      (long)its_entry->base_address);
+	domain_handle = iort_find_domain_token(its_entry->translation_id);
+	if (!domain_handle) {
+		pr_err("%s: Unable to locate ITS domain handle\n", node_name);
+		goto out;
+	}
+
+	err = its_pmsi_init_one(domain_handle, node_name);
+
+out:
+	kfree(node_name);
+	return err;
+}
+
+static void __init its_pmsi_acpi_init(void)
+{
+	acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR,
+			      its_pmsi_parse_madt, 0);
+}
+#else
+static inline void its_pmsi_acpi_init(void) { }
+#endif
+
+static void __init its_pmsi_of_init(void)
+{
+	struct device_node *np;
+
 	for (np = of_find_matching_node(NULL, its_device_id); np;
 	     np = of_find_matching_node(np, its_device_id)) {
 		if (!of_property_read_bool(np, "msi-controller"))
 			continue;
 
-		parent = irq_find_matching_host(np, DOMAIN_BUS_NEXUS);
-		if (!parent || !msi_get_domain_info(parent)) {
-			pr_err("%s: unable to locate ITS domain\n",
-			       np->full_name);
-			continue;
-		}
-
-		if (!platform_msi_create_irq_domain(of_node_to_fwnode(np),
-						    &its_pmsi_domain_info,
-						    parent)) {
-			pr_err("%s: unable to create platform domain\n",
-			       np->full_name);
-			continue;
-		}
-
-		pr_info("Platform MSI: %s domain created\n", np->full_name);
+		its_pmsi_init_one(of_node_to_fwnode(np), np->full_name);
 	}
+}
 
+static int __init its_pmsi_init(void)
+{
+	its_pmsi_of_init();
+	its_pmsi_acpi_init();
 	return 0;
 }
 early_initcall(its_pmsi_init);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 23201004fd7a..45ea193325d2 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -16,13 +16,13 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/acpi_iort.h>
 #include <linux/bitmap.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/dma-iommu.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
-#include <linux/acpi_iort.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -1601,6 +1601,14 @@ static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
 }
 
+static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
+{
+	struct its_node *its = data;
+
+	/* On QDF2400, the size of the ITE is 16Bytes */
+	its->ite_size = 16;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1618,6 +1626,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_cavium_23144,
 	},
 #endif
+#ifdef CONFIG_QCOM_QDF2400_ERRATUM_0065
+	{
+		.desc	= "ITS: QDF2400 erratum 0065",
+		.iidr	= 0x00001070, /* QDF2400 ITS rev 1.x */
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_qdf2400_e0065,
+	},
+#endif
 	{
 	}
 };
diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c
index 15af9a9753e5..9463f3557e82 100644
--- a/drivers/irqchip/irq-imx-gpcv2.c
+++ b/drivers/irqchip/irq-imx-gpcv2.c
@@ -230,6 +230,8 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node,
 		return -ENOMEM;
 	}
 
+	raw_spin_lock_init(&cd->rlock);
+
 	cd->gpc_base = of_iomap(node, 0);
 	if (!cd->gpc_base) {
 		pr_err("fsl-gpcv2: unable to map gpc registers\n");
@@ -266,6 +268,11 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node,
 	imx_gpcv2_instance = cd;
 	register_syscore_ops(&imx_gpcv2_syscore_ops);
 
+	/*
+	 * Clear the OF_POPULATED flag set in of_irq_init so that
+	 * later the GPC power domain driver will not be skipped.
+	 */
+	of_node_clear_flag(node, OF_POPULATED);
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 03b79b061d24..d2306c821ebb 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -16,6 +16,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/interrupt.h>
 #include <linux/irqchip.h>
 #include <linux/module.h>
@@ -180,7 +181,7 @@ static int mbigen_domain_translate(struct irq_domain *d,
 				    unsigned long *hwirq,
 				    unsigned int *type)
 {
-	if (is_of_node(fwspec->fwnode)) {
+	if (is_of_node(fwspec->fwnode) || is_acpi_device_node(fwspec->fwnode)) {
 		if (fwspec->param_count != 2)
 			return -EINVAL;
 
@@ -236,27 +237,15 @@ static struct irq_domain_ops mbigen_domain_ops = {
 	.free		= irq_domain_free_irqs_common,
 };
 
-static int mbigen_device_probe(struct platform_device *pdev)
+static int mbigen_of_create_domain(struct platform_device *pdev,
+				   struct mbigen_device *mgn_chip)
 {
-	struct mbigen_device *mgn_chip;
+	struct device *parent;
 	struct platform_device *child;
 	struct irq_domain *domain;
 	struct device_node *np;
-	struct device *parent;
-	struct resource *res;
 	u32 num_pins;
 
-	mgn_chip = devm_kzalloc(&pdev->dev, sizeof(*mgn_chip), GFP_KERNEL);
-	if (!mgn_chip)
-		return -ENOMEM;
-
-	mgn_chip->pdev = pdev;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mgn_chip->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(mgn_chip->base))
-		return PTR_ERR(mgn_chip->base);
-
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_property_read_bool(np, "interrupt-controller"))
 			continue;
@@ -280,6 +269,91 @@ static int mbigen_device_probe(struct platform_device *pdev)
 			return -ENOMEM;
 	}
 
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+static int mbigen_acpi_create_domain(struct platform_device *pdev,
+				     struct mbigen_device *mgn_chip)
+{
+	struct irq_domain *domain;
+	u32 num_pins = 0;
+	int ret;
+
+	/*
+	 * "num-pins" is the total number of interrupt pins implemented in
+	 * this mbigen instance, and mbigen is an interrupt controller
+	 * connected to ITS  converting wired interrupts into MSI, so we
+	 * use "num-pins" to alloc MSI vectors which are needed by client
+	 * devices connected to it.
+	 *
+	 * Here is the DSDT device node used for mbigen in firmware:
+	 *	Device(MBI0) {
+	 *		Name(_HID, "HISI0152")
+	 *		Name(_UID, Zero)
+	 *		Name(_CRS, ResourceTemplate() {
+	 *			Memory32Fixed(ReadWrite, 0xa0080000, 0x10000)
+	 *		})
+	 *
+	 *		Name(_DSD, Package () {
+	 *			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+	 *			Package () {
+	 *				Package () {"num-pins", 378}
+	 *			}
+	 *		})
+	 *	}
+	 */
+	ret = device_property_read_u32(&pdev->dev, "num-pins", &num_pins);
+	if (ret || num_pins == 0)
+		return -EINVAL;
+
+	domain = platform_msi_create_device_domain(&pdev->dev, num_pins,
+						   mbigen_write_msg,
+						   &mbigen_domain_ops,
+						   mgn_chip);
+	if (!domain)
+		return -ENOMEM;
+
+	return 0;
+}
+#else
+static inline int mbigen_acpi_create_domain(struct platform_device *pdev,
+					    struct mbigen_device *mgn_chip)
+{
+	return -ENODEV;
+}
+#endif
+
+static int mbigen_device_probe(struct platform_device *pdev)
+{
+	struct mbigen_device *mgn_chip;
+	struct resource *res;
+	int err;
+
+	mgn_chip = devm_kzalloc(&pdev->dev, sizeof(*mgn_chip), GFP_KERNEL);
+	if (!mgn_chip)
+		return -ENOMEM;
+
+	mgn_chip->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mgn_chip->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mgn_chip->base))
+		return PTR_ERR(mgn_chip->base);
+
+	if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node)
+		err = mbigen_of_create_domain(pdev, mgn_chip);
+	else if (ACPI_COMPANION(&pdev->dev))
+		err = mbigen_acpi_create_domain(pdev, mgn_chip);
+	else
+		err = -EINVAL;
+
+	if (err) {
+		dev_err(&pdev->dev, "Failed to create mbi-gen@%p irqdomain",
+			mgn_chip->base);
+		return err;
+	}
+
 	platform_set_drvdata(pdev, mgn_chip);
 	return 0;
 }
@@ -290,11 +364,17 @@ static const struct of_device_id mbigen_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mbigen_of_match);
 
+static const struct acpi_device_id mbigen_acpi_match[] = {
+	{ "HISI0152", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, mbigen_acpi_match);
+
 static struct platform_driver mbigen_platform_driver = {
 	.driver = {
 		.name		= "Hisilicon MBIGEN-V2",
-		.owner		= THIS_MODULE,
 		.of_match_table	= mbigen_of_match,
+		.acpi_match_table = ACPI_PTR(mbigen_acpi_match),
 	},
 	.probe			= mbigen_device_probe,
 };
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 11d12bccc4e7..eb7fbe159963 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -29,25 +29,12 @@ struct gic_pcpu_mask {
 	DECLARE_BITMAP(pcpu_mask, GIC_MAX_INTRS);
 };
 
-struct gic_irq_spec {
-	enum {
-		GIC_DEVICE,
-		GIC_IPI
-	} type;
-
-	union {
-		struct cpumask *ipimask;
-		unsigned int hwirq;
-	};
-};
-
 static unsigned long __gic_base_addr;
 
 static void __iomem *gic_base;
 static struct gic_pcpu_mask pcpu_masks[NR_CPUS];
 static DEFINE_SPINLOCK(gic_lock);
 static struct irq_domain *gic_irq_domain;
-static struct irq_domain *gic_dev_domain;
 static struct irq_domain *gic_ipi_domain;
 static int gic_shared_intrs;
 static int gic_vpes;
@@ -55,6 +42,7 @@ static unsigned int gic_cpu_pin;
 static unsigned int timer_cpu_pin;
 static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
 DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS);
+DECLARE_BITMAP(ipi_available, GIC_MAX_INTRS);
 
 static void __gic_irq_dispatch(void);
 
@@ -693,132 +681,7 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static int gic_setup_dev_chip(struct irq_domain *d, unsigned int virq,
-			      unsigned int hwirq)
-{
-	struct irq_chip *chip;
-	int err;
-
-	if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
-		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
-						    &gic_level_irq_controller,
-						    NULL);
-	} else {
-		switch (GIC_HWIRQ_TO_LOCAL(hwirq)) {
-		case GIC_LOCAL_INT_TIMER:
-		case GIC_LOCAL_INT_PERFCTR:
-		case GIC_LOCAL_INT_FDC:
-			/*
-			 * HACK: These are all really percpu interrupts, but
-			 * the rest of the MIPS kernel code does not use the
-			 * percpu IRQ API for them.
-			 */
-			chip = &gic_all_vpes_local_irq_controller;
-			irq_set_handler(virq, handle_percpu_irq);
-			break;
-
-		default:
-			chip = &gic_local_irq_controller;
-			irq_set_handler(virq, handle_percpu_devid_irq);
-			irq_set_percpu_devid(virq);
-			break;
-		}
-
-		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
-						    chip, NULL);
-	}
-
-	return err;
-}
-
-static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
-				unsigned int nr_irqs, void *arg)
-{
-	struct gic_irq_spec *spec = arg;
-	irq_hw_number_t hwirq, base_hwirq;
-	int cpu, ret, i;
-
-	if (spec->type == GIC_DEVICE) {
-		/* verify that shared irqs don't conflict with an IPI irq */
-		if ((spec->hwirq >= GIC_SHARED_HWIRQ_BASE) &&
-		    test_bit(GIC_HWIRQ_TO_SHARED(spec->hwirq), ipi_resrv))
-			return -EBUSY;
-
-		return gic_setup_dev_chip(d, virq, spec->hwirq);
-	} else {
-		base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
-		if (base_hwirq == gic_shared_intrs) {
-			return -ENOMEM;
-		}
-
-		/* check that we have enough space */
-		for (i = base_hwirq; i < nr_irqs; i++) {
-			if (!test_bit(i, ipi_resrv))
-				return -EBUSY;
-		}
-		bitmap_clear(ipi_resrv, base_hwirq, nr_irqs);
-
-		/* map the hwirq for each cpu consecutively */
-		i = 0;
-		for_each_cpu(cpu, spec->ipimask) {
-			hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
-
-			ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
-							    &gic_level_irq_controller,
-							    NULL);
-			if (ret)
-				goto error;
-
-			irq_set_handler(virq + i, handle_level_irq);
-
-			ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
-			if (ret)
-				goto error;
-
-			i++;
-		}
-
-		/*
-		 * tell the parent about the base hwirq we allocated so it can
-		 * set its own domain data
-		 */
-		spec->hwirq = base_hwirq;
-	}
-
-	return 0;
-error:
-	bitmap_set(ipi_resrv, base_hwirq, nr_irqs);
-	return ret;
-}
-
-void gic_irq_domain_free(struct irq_domain *d, unsigned int virq,
-			 unsigned int nr_irqs)
-{
-	irq_hw_number_t base_hwirq;
-	struct irq_data *data;
-
-	data = irq_get_irq_data(virq);
-	if (!data)
-		return;
-
-	base_hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(data));
-	bitmap_set(ipi_resrv, base_hwirq, nr_irqs);
-}
-
-int gic_irq_domain_match(struct irq_domain *d, struct device_node *node,
-			 enum irq_domain_bus_token bus_token)
-{
-	/* this domain should'nt be accessed directly */
-	return 0;
-}
-
-static const struct irq_domain_ops gic_irq_domain_ops = {
-	.alloc = gic_irq_domain_alloc,
-	.free = gic_irq_domain_free,
-	.match = gic_irq_domain_match,
-};
-
-static int gic_dev_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
+static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 				const u32 *intspec, unsigned int intsize,
 				irq_hw_number_t *out_hwirq,
 				unsigned int *out_type)
@@ -837,58 +700,82 @@ static int gic_dev_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 	return 0;
 }
 
-static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq,
-				unsigned int nr_irqs, void *arg)
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
+			      irq_hw_number_t hwirq)
 {
-	struct irq_fwspec *fwspec = arg;
-	struct gic_irq_spec spec = {
-		.type = GIC_DEVICE,
-	};
-	int i, ret;
+	int err;
 
-	if (fwspec->param[0] == GIC_SHARED)
-		spec.hwirq = GIC_SHARED_TO_HWIRQ(fwspec->param[1]);
-	else
-		spec.hwirq = GIC_LOCAL_TO_HWIRQ(fwspec->param[1]);
+	if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
+		/* verify that shared irqs don't conflict with an IPI irq */
+		if (test_bit(GIC_HWIRQ_TO_SHARED(hwirq), ipi_resrv))
+			return -EBUSY;
 
-	ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
-	if (ret)
-		return ret;
+		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+						    &gic_level_irq_controller,
+						    NULL);
+		if (err)
+			return err;
 
-	for (i = 0; i < nr_irqs; i++) {
-		ret = gic_setup_dev_chip(d, virq + i, spec.hwirq + i);
-		if (ret)
-			goto error;
+		return gic_shared_irq_domain_map(d, virq, hwirq, 0);
 	}
 
-	return 0;
+	switch (GIC_HWIRQ_TO_LOCAL(hwirq)) {
+	case GIC_LOCAL_INT_TIMER:
+	case GIC_LOCAL_INT_PERFCTR:
+	case GIC_LOCAL_INT_FDC:
+		/*
+		 * HACK: These are all really percpu interrupts, but
+		 * the rest of the MIPS kernel code does not use the
+		 * percpu IRQ API for them.
+		 */
+		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+						    &gic_all_vpes_local_irq_controller,
+						    NULL);
+		if (err)
+			return err;
 
-error:
-	irq_domain_free_irqs_parent(d, virq, nr_irqs);
-	return ret;
+		irq_set_handler(virq, handle_percpu_irq);
+		break;
+
+	default:
+		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+						    &gic_local_irq_controller,
+						    NULL);
+		if (err)
+			return err;
+
+		irq_set_handler(virq, handle_percpu_devid_irq);
+		irq_set_percpu_devid(virq);
+		break;
+	}
+
+	return gic_local_irq_domain_map(d, virq, hwirq);
 }
 
-void gic_dev_domain_free(struct irq_domain *d, unsigned int virq,
-			 unsigned int nr_irqs)
+static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
 {
-	/* no real allocation is done for dev irqs, so no need to free anything */
-	return;
+	struct irq_fwspec *fwspec = arg;
+	irq_hw_number_t hwirq;
+
+	if (fwspec->param[0] == GIC_SHARED)
+		hwirq = GIC_SHARED_TO_HWIRQ(fwspec->param[1]);
+	else
+		hwirq = GIC_LOCAL_TO_HWIRQ(fwspec->param[1]);
+
+	return gic_irq_domain_map(d, virq, hwirq);
 }
 
-static void gic_dev_domain_activate(struct irq_domain *domain,
-				    struct irq_data *d)
+void gic_irq_domain_free(struct irq_domain *d, unsigned int virq,
+			 unsigned int nr_irqs)
 {
-	if (GIC_HWIRQ_TO_LOCAL(d->hwirq) < GIC_NUM_LOCAL_INTRS)
-		gic_local_irq_domain_map(domain, d->irq, d->hwirq);
-	else
-		gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0);
 }
 
-static struct irq_domain_ops gic_dev_domain_ops = {
-	.xlate = gic_dev_domain_xlate,
-	.alloc = gic_dev_domain_alloc,
-	.free = gic_dev_domain_free,
-	.activate = gic_dev_domain_activate,
+static const struct irq_domain_ops gic_irq_domain_ops = {
+	.xlate = gic_irq_domain_xlate,
+	.alloc = gic_irq_domain_alloc,
+	.free = gic_irq_domain_free,
+	.map = gic_irq_domain_map,
 };
 
 static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
@@ -910,20 +797,32 @@ static int gic_ipi_domain_alloc(struct irq_domain *d, unsigned int virq,
 				unsigned int nr_irqs, void *arg)
 {
 	struct cpumask *ipimask = arg;
-	struct gic_irq_spec spec = {
-		.type = GIC_IPI,
-		.ipimask = ipimask
-	};
-	int ret, i;
-
-	ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
-	if (ret)
-		return ret;
-
-	/* the parent should have set spec.hwirq to the base_hwirq it allocated */
-	for (i = 0; i < nr_irqs; i++) {
-		ret = irq_domain_set_hwirq_and_chip(d, virq + i,
-						    GIC_SHARED_TO_HWIRQ(spec.hwirq + i),
+	irq_hw_number_t hwirq, base_hwirq;
+	int cpu, ret, i;
+
+	base_hwirq = find_first_bit(ipi_available, gic_shared_intrs);
+	if (base_hwirq == gic_shared_intrs)
+		return -ENOMEM;
+
+	/* check that we have enough space */
+	for (i = base_hwirq; i < nr_irqs; i++) {
+		if (!test_bit(i, ipi_available))
+			return -EBUSY;
+	}
+	bitmap_clear(ipi_available, base_hwirq, nr_irqs);
+
+	/* map the hwirq for each cpu consecutively */
+	i = 0;
+	for_each_cpu(cpu, ipimask) {
+		hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
+
+		ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
+						    &gic_edge_irq_controller,
+						    NULL);
+		if (ret)
+			goto error;
+
+		ret = irq_domain_set_hwirq_and_chip(d->parent, virq + i, hwirq,
 						    &gic_edge_irq_controller,
 						    NULL);
 		if (ret)
@@ -932,18 +831,32 @@ static int gic_ipi_domain_alloc(struct irq_domain *d, unsigned int virq,
 		ret = irq_set_irq_type(virq + i, IRQ_TYPE_EDGE_RISING);
 		if (ret)
 			goto error;
+
+		ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
+		if (ret)
+			goto error;
+
+		i++;
 	}
 
 	return 0;
 error:
-	irq_domain_free_irqs_parent(d, virq, nr_irqs);
+	bitmap_set(ipi_available, base_hwirq, nr_irqs);
 	return ret;
 }
 
 void gic_ipi_domain_free(struct irq_domain *d, unsigned int virq,
 			 unsigned int nr_irqs)
 {
-	irq_domain_free_irqs_parent(d, virq, nr_irqs);
+	irq_hw_number_t base_hwirq;
+	struct irq_data *data;
+
+	data = irq_get_irq_data(virq);
+	if (!data)
+		return;
+
+	base_hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(data));
+	bitmap_set(ipi_available, base_hwirq, nr_irqs);
 }
 
 int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
@@ -968,34 +881,6 @@ static struct irq_domain_ops gic_ipi_domain_ops = {
 	.match = gic_ipi_domain_match,
 };
 
-static void __init gic_map_single_int(struct device_node *node,
-				      unsigned int irq)
-{
-	unsigned int linux_irq;
-	struct irq_fwspec local_int_fwspec = {
-		.fwnode         = &node->fwnode,
-		.param_count    = 3,
-		.param          = {
-			[0]     = GIC_LOCAL,
-			[1]     = irq,
-			[2]     = IRQ_TYPE_NONE,
-		},
-	};
-
-	if (!gic_local_irq_is_routable(irq))
-		return;
-
-	linux_irq = irq_create_fwspec_mapping(&local_int_fwspec);
-	WARN_ON(!linux_irq);
-}
-
-static void __init gic_map_interrupts(struct device_node *node)
-{
-	gic_map_single_int(node, GIC_LOCAL_INT_TIMER);
-	gic_map_single_int(node, GIC_LOCAL_INT_PERFCTR);
-	gic_map_single_int(node, GIC_LOCAL_INT_FDC);
-}
-
 static void __init __gic_init(unsigned long gic_base_addr,
 			      unsigned long gic_addrspace_size,
 			      unsigned int cpu_vec, unsigned int irqbase,
@@ -1067,13 +952,6 @@ static void __init __gic_init(unsigned long gic_base_addr,
 		panic("Failed to add GIC IRQ domain");
 	gic_irq_domain->name = "mips-gic-irq";
 
-	gic_dev_domain = irq_domain_add_hierarchy(gic_irq_domain, 0,
-						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
-						  node, &gic_dev_domain_ops, NULL);
-	if (!gic_dev_domain)
-		panic("Failed to add GIC DEV domain");
-	gic_dev_domain->name = "mips-gic-dev";
-
 	gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
 						  IRQ_DOMAIN_FLAG_IPI_PER_CPU,
 						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
@@ -1094,8 +972,8 @@ static void __init __gic_init(unsigned long gic_base_addr,
 			   2 * gic_vpes);
 	}
 
+	bitmap_copy(ipi_available, ipi_resrv, GIC_MAX_INTRS);
 	gic_basic_init();
-	gic_map_interrupts(node);
 }
 
 void __init gic_init(unsigned long gic_base_addr,
diff --git a/drivers/irqchip/irq-moxart.c b/drivers/irqchip/irq-moxart.c
deleted file mode 100644
index a24b06a1718b..000000000000
--- a/drivers/irqchip/irq-moxart.c
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * MOXA ART SoCs IRQ chip driver.
- *
- * Copyright (C) 2013 Jonas Jensen
- *
- * Jonas Jensen <jonas.jensen@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/irqchip.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/irqdomain.h>
-
-#include <asm/exception.h>
-
-#define IRQ_SOURCE_REG		0
-#define IRQ_MASK_REG		0x04
-#define IRQ_CLEAR_REG		0x08
-#define IRQ_MODE_REG		0x0c
-#define IRQ_LEVEL_REG		0x10
-#define IRQ_STATUS_REG		0x14
-
-#define FIQ_SOURCE_REG		0x20
-#define FIQ_MASK_REG		0x24
-#define FIQ_CLEAR_REG		0x28
-#define FIQ_MODE_REG		0x2c
-#define FIQ_LEVEL_REG		0x30
-#define FIQ_STATUS_REG		0x34
-
-
-struct moxart_irq_data {
-	void __iomem *base;
-	struct irq_domain *domain;
-	unsigned int interrupt_mask;
-};
-
-static struct moxart_irq_data intc;
-
-static void __exception_irq_entry handle_irq(struct pt_regs *regs)
-{
-	u32 irqstat;
-	int hwirq;
-
-	irqstat = readl(intc.base + IRQ_STATUS_REG);
-
-	while (irqstat) {
-		hwirq = ffs(irqstat) - 1;
-		handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs);
-		irqstat &= ~(1 << hwirq);
-	}
-}
-
-static int __init moxart_of_intc_init(struct device_node *node,
-				      struct device_node *parent)
-{
-	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
-	int ret;
-	struct irq_chip_generic *gc;
-
-	intc.base = of_iomap(node, 0);
-	if (!intc.base) {
-		pr_err("%s: unable to map IC registers\n",
-		       node->full_name);
-		return -EINVAL;
-	}
-
-	intc.domain = irq_domain_add_linear(node, 32, &irq_generic_chip_ops,
-					    intc.base);
-	if (!intc.domain) {
-		pr_err("%s: unable to create IRQ domain\n", node->full_name);
-		return -EINVAL;
-	}
-
-	ret = irq_alloc_domain_generic_chips(intc.domain, 32, 1,
-					     "MOXARTINTC", handle_edge_irq,
-					     clr, 0, IRQ_GC_INIT_MASK_CACHE);
-	if (ret) {
-		pr_err("%s: could not allocate generic chip\n",
-		       node->full_name);
-		irq_domain_remove(intc.domain);
-		return -EINVAL;
-	}
-
-	ret = of_property_read_u32(node, "interrupt-mask",
-				   &intc.interrupt_mask);
-	if (ret)
-		pr_err("%s: could not read interrupt-mask DT property\n",
-		       node->full_name);
-
-	gc = irq_get_domain_generic_chip(intc.domain, 0);
-
-	gc->reg_base = intc.base;
-	gc->chip_types[0].regs.mask = IRQ_MASK_REG;
-	gc->chip_types[0].regs.ack = IRQ_CLEAR_REG;
-	gc->chip_types[0].chip.irq_ack = irq_gc_ack_set_bit;
-	gc->chip_types[0].chip.irq_mask = irq_gc_mask_clr_bit;
-	gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit;
-
-	writel(0, intc.base + IRQ_MASK_REG);
-	writel(0xffffffff, intc.base + IRQ_CLEAR_REG);
-
-	writel(intc.interrupt_mask, intc.base + IRQ_MODE_REG);
-	writel(intc.interrupt_mask, intc.base + IRQ_LEVEL_REG);
-
-	set_handle_irq(handle_irq);
-
-	return 0;
-}
-IRQCHIP_DECLARE(moxa_moxart_ic, "moxa,moxart-ic", moxart_of_intc_init);
diff --git a/drivers/irqchip/irq-mtk-cirq.c b/drivers/irqchip/irq-mtk-cirq.c
new file mode 100644
index 000000000000..18c65c16de28
--- /dev/null
+++ b/drivers/irqchip/irq-mtk-cirq.c
@@ -0,0 +1,306 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Youlin.Pei <youlin.pei@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/syscore_ops.h>
+
+#define CIRQ_ACK	0x40
+#define CIRQ_MASK_SET	0xc0
+#define CIRQ_MASK_CLR	0x100
+#define CIRQ_SENS_SET	0x180
+#define CIRQ_SENS_CLR	0x1c0
+#define CIRQ_POL_SET	0x240
+#define CIRQ_POL_CLR	0x280
+#define CIRQ_CONTROL	0x300
+
+#define CIRQ_EN	0x1
+#define CIRQ_EDGE	0x2
+#define CIRQ_FLUSH	0x4
+
+struct mtk_cirq_chip_data {
+	void __iomem *base;
+	unsigned int ext_irq_start;
+	unsigned int ext_irq_end;
+	struct irq_domain *domain;
+};
+
+static struct mtk_cirq_chip_data *cirq_data;
+
+static void mtk_cirq_write_mask(struct irq_data *data, unsigned int offset)
+{
+	struct mtk_cirq_chip_data *chip_data = data->chip_data;
+	unsigned int cirq_num = data->hwirq;
+	u32 mask = 1 << (cirq_num % 32);
+
+	writel_relaxed(mask, chip_data->base + offset + (cirq_num / 32) * 4);
+}
+
+static void mtk_cirq_mask(struct irq_data *data)
+{
+	mtk_cirq_write_mask(data, CIRQ_MASK_SET);
+	irq_chip_mask_parent(data);
+}
+
+static void mtk_cirq_unmask(struct irq_data *data)
+{
+	mtk_cirq_write_mask(data, CIRQ_MASK_CLR);
+	irq_chip_unmask_parent(data);
+}
+
+static int mtk_cirq_set_type(struct irq_data *data, unsigned int type)
+{
+	int ret;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_FALLING:
+		mtk_cirq_write_mask(data, CIRQ_POL_CLR);
+		mtk_cirq_write_mask(data, CIRQ_SENS_CLR);
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		mtk_cirq_write_mask(data, CIRQ_POL_SET);
+		mtk_cirq_write_mask(data, CIRQ_SENS_CLR);
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		mtk_cirq_write_mask(data, CIRQ_POL_CLR);
+		mtk_cirq_write_mask(data, CIRQ_SENS_SET);
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		mtk_cirq_write_mask(data, CIRQ_POL_SET);
+		mtk_cirq_write_mask(data, CIRQ_SENS_SET);
+		break;
+	default:
+		break;
+	}
+
+	data = data->parent_data;
+	ret = data->chip->irq_set_type(data, type);
+	return ret;
+}
+
+static struct irq_chip mtk_cirq_chip = {
+	.name			= "MT_CIRQ",
+	.irq_mask		= mtk_cirq_mask,
+	.irq_unmask		= mtk_cirq_unmask,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_type		= mtk_cirq_set_type,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+#endif
+};
+
+static int mtk_cirq_domain_translate(struct irq_domain *d,
+				     struct irq_fwspec *fwspec,
+				     unsigned long *hwirq,
+				     unsigned int *type)
+{
+	if (is_of_node(fwspec->fwnode)) {
+		if (fwspec->param_count != 3)
+			return -EINVAL;
+
+		/* No PPI should point to this domain */
+		if (fwspec->param[0] != 0)
+			return -EINVAL;
+
+		/* cirq support irq number check */
+		if (fwspec->param[1] < cirq_data->ext_irq_start ||
+		    fwspec->param[1] > cirq_data->ext_irq_end)
+			return -EINVAL;
+
+		*hwirq = fwspec->param[1] - cirq_data->ext_irq_start;
+		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int mtk_cirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *arg)
+{
+	int ret;
+	irq_hw_number_t hwirq;
+	unsigned int type;
+	struct irq_fwspec *fwspec = arg;
+	struct irq_fwspec parent_fwspec = *fwspec;
+
+	ret = mtk_cirq_domain_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	if (WARN_ON(nr_irqs != 1))
+		return -EINVAL;
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+				      &mtk_cirq_chip,
+				      domain->host_data);
+
+	parent_fwspec.fwnode = domain->parent->fwnode;
+	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs,
+					    &parent_fwspec);
+}
+
+static const struct irq_domain_ops cirq_domain_ops = {
+	.translate	= mtk_cirq_domain_translate,
+	.alloc		= mtk_cirq_domain_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_cirq_suspend(void)
+{
+	u32 value, mask;
+	unsigned int irq, hwirq_num;
+	bool pending, masked;
+	int i, pendret, maskret;
+
+	/*
+	 * When external interrupts happened, CIRQ will record the status
+	 * even CIRQ is not enabled. When execute flush command, CIRQ will
+	 * resend the signals according to the status. So if don't clear the
+	 * status, CIRQ will resend the wrong signals.
+	 *
+	 * arch_suspend_disable_irqs() will be called before CIRQ suspend
+	 * callback. If clear all the status simply, the external interrupts
+	 * which happened between arch_suspend_disable_irqs and CIRQ suspend
+	 * callback will be lost. Using following steps to avoid this issue;
+	 *
+	 * - Iterate over all the CIRQ supported interrupts;
+	 * - For each interrupt, inspect its pending and masked status at GIC
+	 *   level;
+	 * - If pending and unmasked, it happened between
+	 *   arch_suspend_disable_irqs and CIRQ suspend callback, don't ACK
+	 *   it. Otherwise, ACK it.
+	 */
+	hwirq_num = cirq_data->ext_irq_end - cirq_data->ext_irq_start + 1;
+	for (i = 0; i < hwirq_num; i++) {
+		irq = irq_find_mapping(cirq_data->domain, i);
+		if (irq) {
+			pendret = irq_get_irqchip_state(irq,
+							IRQCHIP_STATE_PENDING,
+							&pending);
+
+			maskret = irq_get_irqchip_state(irq,
+							IRQCHIP_STATE_MASKED,
+							&masked);
+
+			if (pendret == 0 && maskret == 0 &&
+			    (pending && !masked))
+				continue;
+		}
+
+		mask = 1 << (i % 32);
+		writel_relaxed(mask, cirq_data->base + CIRQ_ACK + (i / 32) * 4);
+	}
+
+	/* set edge_only mode, record edge-triggerd interrupts */
+	/* enable cirq */
+	value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
+	value |= (CIRQ_EDGE | CIRQ_EN);
+	writel_relaxed(value, cirq_data->base + CIRQ_CONTROL);
+
+	return 0;
+}
+
+static void mtk_cirq_resume(void)
+{
+	u32 value;
+
+	/* flush recored interrupts, will send signals to parent controller */
+	value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
+	writel_relaxed(value | CIRQ_FLUSH, cirq_data->base + CIRQ_CONTROL);
+
+	/* disable cirq */
+	value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
+	value &= ~(CIRQ_EDGE | CIRQ_EN);
+	writel_relaxed(value, cirq_data->base + CIRQ_CONTROL);
+}
+
+static struct syscore_ops mtk_cirq_syscore_ops = {
+	.suspend	= mtk_cirq_suspend,
+	.resume		= mtk_cirq_resume,
+};
+
+static void mtk_cirq_syscore_init(void)
+{
+	register_syscore_ops(&mtk_cirq_syscore_ops);
+}
+#else
+static inline void mtk_cirq_syscore_init(void) {}
+#endif
+
+static int __init mtk_cirq_of_init(struct device_node *node,
+				   struct device_node *parent)
+{
+	struct irq_domain *domain, *domain_parent;
+	unsigned int irq_num;
+	int ret;
+
+	domain_parent = irq_find_host(parent);
+	if (!domain_parent) {
+		pr_err("mtk_cirq: interrupt-parent not found\n");
+		return -EINVAL;
+	}
+
+	cirq_data = kzalloc(sizeof(*cirq_data), GFP_KERNEL);
+	if (!cirq_data)
+		return -ENOMEM;
+
+	cirq_data->base = of_iomap(node, 0);
+	if (!cirq_data->base) {
+		pr_err("mtk_cirq: unable to map cirq register\n");
+		ret = -ENXIO;
+		goto out_free;
+	}
+
+	ret = of_property_read_u32_index(node, "mediatek,ext-irq-range", 0,
+					 &cirq_data->ext_irq_start);
+	if (ret)
+		goto out_unmap;
+
+	ret = of_property_read_u32_index(node, "mediatek,ext-irq-range", 1,
+					 &cirq_data->ext_irq_end);
+	if (ret)
+		goto out_unmap;
+
+	irq_num = cirq_data->ext_irq_end - cirq_data->ext_irq_start + 1;
+	domain = irq_domain_add_hierarchy(domain_parent, 0,
+					  irq_num, node,
+					  &cirq_domain_ops, cirq_data);
+	if (!domain) {
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+	cirq_data->domain = domain;
+
+	mtk_cirq_syscore_init();
+
+	return 0;
+
+out_unmap:
+	iounmap(cirq_data->base);
+out_free:
+	kfree(cirq_data);
+	return ret;
+}
+
+IRQCHIP_DECLARE(mtk_cirq, "mediatek,mtk-cirq", mtk_cirq_of_init);
diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c
index 63ac73b1d9c8..eeac512ec5a8 100644
--- a/drivers/irqchip/irq-mtk-sysirq.c
+++ b/drivers/irqchip/irq-mtk-sysirq.c
@@ -24,22 +24,29 @@
 
 struct mtk_sysirq_chip_data {
 	spinlock_t lock;
-	void __iomem *intpol_base;
+	u32 nr_intpol_bases;
+	void __iomem **intpol_bases;
+	u32 *intpol_words;
+	u8 *intpol_idx;
+	u16 *which_word;
 };
 
 static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
 {
 	irq_hw_number_t hwirq = data->hwirq;
 	struct mtk_sysirq_chip_data *chip_data = data->chip_data;
+	u8 intpol_idx = chip_data->intpol_idx[hwirq];
+	void __iomem *base;
 	u32 offset, reg_index, value;
 	unsigned long flags;
 	int ret;
 
+	base = chip_data->intpol_bases[intpol_idx];
+	reg_index = chip_data->which_word[hwirq];
 	offset = hwirq & 0x1f;
-	reg_index = hwirq >> 5;
 
 	spin_lock_irqsave(&chip_data->lock, flags);
-	value = readl_relaxed(chip_data->intpol_base + reg_index * 4);
+	value = readl_relaxed(base + reg_index * 4);
 	if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_EDGE_FALLING) {
 		if (type == IRQ_TYPE_LEVEL_LOW)
 			type = IRQ_TYPE_LEVEL_HIGH;
@@ -49,7 +56,8 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
 	} else {
 		value &= ~(1 << offset);
 	}
-	writel(value, chip_data->intpol_base + reg_index * 4);
+
+	writel_relaxed(value, base + reg_index * 4);
 
 	data = data->parent_data;
 	ret = data->chip->irq_set_type(data, type);
@@ -124,8 +132,7 @@ static int __init mtk_sysirq_of_init(struct device_node *node,
 {
 	struct irq_domain *domain, *domain_parent;
 	struct mtk_sysirq_chip_data *chip_data;
-	int ret, size, intpol_num;
-	struct resource res;
+	int ret, size, intpol_num = 0, nr_intpol_bases = 0, i = 0;
 
 	domain_parent = irq_find_host(parent);
 	if (!domain_parent) {
@@ -133,36 +140,103 @@ static int __init mtk_sysirq_of_init(struct device_node *node,
 		return -EINVAL;
 	}
 
-	ret = of_address_to_resource(node, 0, &res);
-	if (ret)
-		return ret;
-
 	chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL);
 	if (!chip_data)
 		return -ENOMEM;
 
-	size = resource_size(&res);
-	intpol_num = size * 8;
-	chip_data->intpol_base = ioremap(res.start, size);
-	if (!chip_data->intpol_base) {
-		pr_err("mtk_sysirq: unable to map sysirq register\n");
-		ret = -ENXIO;
-		goto out_free;
+	while (of_get_address(node, i++, NULL, NULL))
+		nr_intpol_bases++;
+
+	if (nr_intpol_bases == 0) {
+		pr_err("mtk_sysirq: base address not specified\n");
+		ret = -EINVAL;
+		goto out_free_chip;
+	}
+
+	chip_data->intpol_words = kcalloc(nr_intpol_bases,
+					  sizeof(*chip_data->intpol_words),
+					  GFP_KERNEL);
+	if (!chip_data->intpol_words) {
+		ret = -ENOMEM;
+		goto out_free_chip;
+	}
+
+	chip_data->intpol_bases = kcalloc(nr_intpol_bases,
+					  sizeof(*chip_data->intpol_bases),
+					  GFP_KERNEL);
+	if (!chip_data->intpol_bases) {
+		ret = -ENOMEM;
+		goto out_free_intpol_words;
+	}
+
+	for (i = 0; i < nr_intpol_bases; i++) {
+		struct resource res;
+
+		ret = of_address_to_resource(node, i, &res);
+		size = resource_size(&res);
+		intpol_num += size * 8;
+		chip_data->intpol_words[i] = size / 4;
+		chip_data->intpol_bases[i] = of_iomap(node, i);
+		if (ret || !chip_data->intpol_bases[i]) {
+			pr_err("%s: couldn't map region %d\n",
+			       node->full_name, i);
+			ret = -ENODEV;
+			goto out_free_intpol;
+		}
+	}
+
+	chip_data->intpol_idx = kcalloc(intpol_num,
+					sizeof(*chip_data->intpol_idx),
+					GFP_KERNEL);
+	if (!chip_data->intpol_idx) {
+		ret = -ENOMEM;
+		goto out_free_intpol;
+	}
+
+	chip_data->which_word = kcalloc(intpol_num,
+					sizeof(*chip_data->which_word),
+					GFP_KERNEL);
+	if (!chip_data->which_word) {
+		ret = -ENOMEM;
+		goto out_free_intpol_idx;
+	}
+
+	/*
+	 * assign an index of the intpol_bases for each irq
+	 * to set it fast later
+	 */
+	for (i = 0; i < intpol_num ; i++) {
+		u32 word = i / 32, j;
+
+		for (j = 0; word >= chip_data->intpol_words[j] ; j++)
+			word -= chip_data->intpol_words[j];
+
+		chip_data->intpol_idx[i] = j;
+		chip_data->which_word[i] = word;
 	}
 
 	domain = irq_domain_add_hierarchy(domain_parent, 0, intpol_num, node,
 					  &sysirq_domain_ops, chip_data);
 	if (!domain) {
 		ret = -ENOMEM;
-		goto out_unmap;
+		goto out_free_which_word;
 	}
 	spin_lock_init(&chip_data->lock);
 
 	return 0;
 
-out_unmap:
-	iounmap(chip_data->intpol_base);
-out_free:
+out_free_which_word:
+	kfree(chip_data->which_word);
+out_free_intpol_idx:
+	kfree(chip_data->intpol_idx);
+out_free_intpol:
+	for (i = 0; i < nr_intpol_bases; i++)
+		if (chip_data->intpol_bases[i])
+			iounmap(chip_data->intpol_bases[i]);
+	kfree(chip_data->intpol_bases);
+out_free_intpol_words:
+	kfree(chip_data->intpol_words);
+out_free_chip:
 	kfree(chip_data);
 	return ret;
 }
diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 1dfd1085a04f..9ca691d6c13b 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -1032,6 +1032,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data)
 						     sizeof(avmb1_carddef))))
 				return -EFAULT;
 			cdef.cardtype = AVM_CARDTYPE_B1;
+			cdef.cardnr = 0;
 		} else {
 			if ((retval = copy_from_user(&cdef, data,
 						     sizeof(avmb1_extcarddef))))
diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c
index 50749a70c5ca..060d357f107f 100644
--- a/drivers/isdn/divert/isdn_divert.c
+++ b/drivers/isdn/divert/isdn_divert.c
@@ -157,10 +157,8 @@ int cf_command(int drvid, int mode,
 	/* allocate mem for information struct */
 	if (!(cs = kmalloc(sizeof(struct call_struc), GFP_ATOMIC)))
 		return (-ENOMEM); /* no memory */
-	init_timer(&cs->timer);
+	setup_timer(&cs->timer, deflect_timer_expire, (ulong)cs);
 	cs->info[0] = '\0';
-	cs->timer.function = deflect_timer_expire;
-	cs->timer.data = (ulong) cs; /* pointer to own structure */
 	cs->ics.driver = drvid;
 	cs->ics.command = ISDN_CMD_PROT_IO; /* protocol specific io */
 	cs->ics.arg = DSS1_CMD_INVOKE; /* invoke supplementary service */
@@ -452,10 +450,9 @@ static int isdn_divert_icall(isdn_ctrl *ic)
 					return (0); /* no external deflection needed */
 			if (!(cs = kmalloc(sizeof(struct call_struc), GFP_ATOMIC)))
 				return (0); /* no memory */
-			init_timer(&cs->timer);
+			setup_timer(&cs->timer, deflect_timer_expire,
+				    (ulong)cs);
 			cs->info[0] = '\0';
-			cs->timer.function = deflect_timer_expire;
-			cs->timer.data = (ulong) cs; /* pointer to own structure */
 
 			cs->ics = *ic; /* copy incoming data */
 			if (!cs->ics.parm.setup.phone[0]) strcpy(cs->ics.parm.setup.phone, "0");
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 11e13c56126f..2da3ff650e1d 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -2317,6 +2317,9 @@ static int gigaset_probe(struct usb_interface *interface,
 		return -ENODEV;
 	}
 
+	if (hostif->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	dev_info(&udev->dev,
 		 "%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n",
 		 __func__, le16_to_cpu(udev->descriptor.idVendor),
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
index cb88090f9cea..c61049585cbd 100644
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ b/drivers/isdn/hardware/eicon/divasi.c
@@ -300,9 +300,8 @@ static int um_idi_open_adapter(struct file *file, int adapter_nr)
 	p_os = (diva_um_idi_os_context_t *) diva_um_id_get_os_context(e);
 	init_waitqueue_head(&p_os->read_wait);
 	init_waitqueue_head(&p_os->close_wait);
-	init_timer(&p_os->diva_timer_id);
-	p_os->diva_timer_id.function = (void *) diva_um_timer_function;
-	p_os->diva_timer_id.data = (unsigned long) p_os;
+	setup_timer(&p_os->diva_timer_id, (void *)diva_um_timer_function,
+		    (unsigned long)p_os);
 	p_os->aborted = 0;
 	p_os->adapter_nr = adapter_nr;
 	return (1);
diff --git a/drivers/isdn/hardware/mISDN/Kconfig b/drivers/isdn/hardware/mISDN/Kconfig
index 09df54fc1fef..fda912b0833f 100644
--- a/drivers/isdn/hardware/mISDN/Kconfig
+++ b/drivers/isdn/hardware/mISDN/Kconfig
@@ -13,7 +13,7 @@ config MISDN_HFCPCI
 
 config MISDN_HFCMULTI
 	tristate "Support for HFC multiport cards (HFC-4S/8S/E1)"
-	depends on PCI || 8xx
+	depends on PCI || CPM1
 	depends on MISDN
 	help
 	  Enable support for cards with Cologne Chip AG's HFC multiport
@@ -27,8 +27,8 @@ config MISDN_HFCMULTI_8xx
 	bool "Support for XHFC embedded board in HFC multiport driver"
 	depends on MISDN
 	depends on MISDN_HFCMULTI
-	depends on 8xx
-	default 8xx
+	depends on CPM1
+	default CPM1
 	help
 	  Enable support for the XHFC embedded solution from Speech Design.
 
diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
index 0eafe9f04fca..8a254747768e 100644
--- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
+++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
@@ -6,7 +6,7 @@
  *
  */
 
-#include <asm/8xx_immap.h>
+#include <asm/cpm1.h>
 
 /* Change this to the value used by your board */
 #ifndef IMAP_ADDR
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 480c2d7794eb..961c07ee47b7 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -3878,9 +3878,8 @@ hfcmulti_initmode(struct dchannel *dch)
 		if (hc->dnum[pt]) {
 			mode_hfcmulti(hc, dch->slot, dch->dev.D.protocol,
 				      -1, 0, -1, 0);
-			dch->timer.function = (void *) hfcmulti_dbusy_timer;
-			dch->timer.data = (long) dch;
-			init_timer(&dch->timer);
+			setup_timer(&dch->timer, (void *)hfcmulti_dbusy_timer,
+				    (long)dch);
 		}
 		for (i = 1; i <= 31; i++) {
 			if (!((1 << i) & hc->bmask[pt])) /* skip unused chan */
@@ -3986,9 +3985,8 @@ hfcmulti_initmode(struct dchannel *dch)
 		hc->chan[i].slot_rx = -1;
 		hc->chan[i].conf = -1;
 		mode_hfcmulti(hc, i, dch->dev.D.protocol, -1, 0, -1, 0);
-		dch->timer.function = (void *) hfcmulti_dbusy_timer;
-		dch->timer.data = (long) dch;
-		init_timer(&dch->timer);
+		setup_timer(&dch->timer, (void *)hfcmulti_dbusy_timer,
+			    (long)dch);
 		hc->chan[i - 2].slot_tx = -1;
 		hc->chan[i - 2].slot_rx = -1;
 		hc->chan[i - 2].conf = -1;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index ff48da61c94c..5dc246d71c16 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1717,9 +1717,8 @@ static void
 inithfcpci(struct hfc_pci *hc)
 {
 	printk(KERN_DEBUG "inithfcpci: entered\n");
-	hc->dch.timer.function = (void *) hfcpci_dbusy_timer;
-	hc->dch.timer.data = (long) &hc->dch;
-	init_timer(&hc->dch.timer);
+	setup_timer(&hc->dch.timer, (void *)hfcpci_dbusy_timer,
+		    (long)&hc->dch);
 	hc->chanlimit = 2;
 	mode_hfcpci(&hc->bch[0], 1, -1);
 	mode_hfcpci(&hc->bch[1], 2, -1);
@@ -2044,9 +2043,7 @@ setup_hw(struct hfc_pci *hc)
 	Write_hfc(hc, HFCPCI_INT_M1, hc->hw.int_m1);
 	/* At this point the needed PCI config is done */
 	/* fifos are still not enabled */
-	hc->hw.timer.function = (void *) hfcpci_Timer;
-	hc->hw.timer.data = (long) hc;
-	init_timer(&hc->hw.timer);
+	setup_timer(&hc->hw.timer, (void *)hfcpci_Timer, (long)hc);
 	/* default PCM master */
 	test_and_set_bit(HFC_CFG_MASTER, &hc->cfg);
 	return 0;
diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index 77dec28ba874..6742b0dc0821 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -796,9 +796,8 @@ isac_init(struct isac_hw *isac)
 	}
 	isac->mon_tx = NULL;
 	isac->mon_rx = NULL;
-	isac->dch.timer.function = (void *) dbusy_timer_handler;
-	isac->dch.timer.data = (long)isac;
-	init_timer(&isac->dch.timer);
+	setup_timer(&isac->dch.timer, (void *)dbusy_timer_handler,
+		    (long)isac);
 	isac->mocr = 0xaa;
 	if (isac->type & IPAC_TYPE_ISACX) {
 		/* Disable all IRQ */
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index feafa91c2ed9..5b078591b6ee 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -1635,13 +1635,11 @@ init_isar(struct isar_hw *isar)
 	}
 	if (isar->version != 1)
 		return -EINVAL;
-	isar->ch[0].ftimer.function = &ftimer_handler;
-	isar->ch[0].ftimer.data = (long)&isar->ch[0];
-	init_timer(&isar->ch[0].ftimer);
+	setup_timer(&isar->ch[0].ftimer, &ftimer_handler,
+		    (long)&isar->ch[0]);
 	test_and_set_bit(FLG_INITIALIZED, &isar->ch[0].bch.Flags);
-	isar->ch[1].ftimer.function = &ftimer_handler;
-	isar->ch[1].ftimer.data = (long)&isar->ch[1];
-	init_timer(&isar->ch[1].ftimer);
+	setup_timer(&isar->ch[1].ftimer, &ftimer_handler,
+		    (long)&isar->ch[1]);
 	test_and_set_bit(FLG_INITIALIZED, &isar->ch[1].bch.Flags);
 	return 0;
 }
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index 3b067ea656bd..3052c836b89f 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -852,9 +852,8 @@ static void initW6692(struct w6692_hw *card)
 {
 	u8	val;
 
-	card->dch.timer.function = (void *)dbusy_timer_handler;
-	card->dch.timer.data = (u_long)&card->dch;
-	init_timer(&card->dch.timer);
+	setup_timer(&card->dch.timer, (void *)dbusy_timer_handler,
+		    (u_long)&card->dch);
 	w6692_mode(&card->bc[0], ISDN_P_NONE);
 	w6692_mode(&card->bc[1], ISDN_P_NONE);
 	WriteW6692(card, W_D_CTL, 0x00);
diff --git a/drivers/isdn/hisax/amd7930_fn.c b/drivers/isdn/hisax/amd7930_fn.c
index 36817e0a0b94..3a4c2f9e19e9 100644
--- a/drivers/isdn/hisax/amd7930_fn.c
+++ b/drivers/isdn/hisax/amd7930_fn.c
@@ -789,7 +789,5 @@ void Amd7930_init(struct IsdnCardState *cs)
 void setup_Amd7930(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, Amd7930_bh);
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 }
diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c
index 29ec2dfbd155..9826bad49e2c 100644
--- a/drivers/isdn/hisax/arcofi.c
+++ b/drivers/isdn/hisax/arcofi.c
@@ -125,9 +125,7 @@ clear_arcofi(struct IsdnCardState *cs) {
 
 void
 init_arcofi(struct IsdnCardState *cs) {
-	cs->dc.isac.arcofitimer.function = (void *) arcofi_timer;
-	cs->dc.isac.arcofitimer.data = (long) cs;
-	init_timer(&cs->dc.isac.arcofitimer);
+	setup_timer(&cs->dc.isac.arcofitimer, (void *)arcofi_timer, (long)cs);
 	init_waitqueue_head(&cs->dc.isac.arcofi_wait);
 	test_and_set_bit(HW_ARCOFI, &cs->HW_Flags);
 }
diff --git a/drivers/isdn/hisax/diva.c b/drivers/isdn/hisax/diva.c
index 4fc90de68d18..079336e593f9 100644
--- a/drivers/isdn/hisax/diva.c
+++ b/drivers/isdn/hisax/diva.c
@@ -976,9 +976,8 @@ static int setup_diva_common(struct IsdnCardState *cs)
 		printk(KERN_INFO "Diva: IPACX Design Id: %x\n",
 		       MemReadISAC_IPACX(cs, IPACX_ID) & 0x3F);
 	} else { /* DIVA 2.0 */
-		cs->hw.diva.tl.function = (void *) diva_led_handler;
-		cs->hw.diva.tl.data = (long) cs;
-		init_timer(&cs->hw.diva.tl);
+		setup_timer(&cs->hw.diva.tl, (void *)diva_led_handler,
+			    (long)cs);
 		cs->readisac  = &ReadISAC;
 		cs->writeisac = &WriteISAC;
 		cs->readisacfifo  = &ReadISACfifo;
diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c
index d8ef64da26f1..03bc5d504e22 100644
--- a/drivers/isdn/hisax/elsa.c
+++ b/drivers/isdn/hisax/elsa.c
@@ -1147,9 +1147,7 @@ static int setup_elsa_common(struct IsdnCard *card)
 	init_arcofi(cs);
 #endif
 	setup_isac(cs);
-	cs->hw.elsa.tl.function = (void *) elsa_led_handler;
-	cs->hw.elsa.tl.data = (long) cs;
-	init_timer(&cs->hw.elsa.tl);
+	setup_timer(&cs->hw.elsa.tl, (void *)elsa_led_handler, (long)cs);
 	/* Teste Timer */
 	if (cs->hw.elsa.timer) {
 		byteout(cs->hw.elsa.trig, 0xff);
diff --git a/drivers/isdn/hisax/fsm.c b/drivers/isdn/hisax/fsm.c
index c7a94713e9ec..d63266fa8cbd 100644
--- a/drivers/isdn/hisax/fsm.c
+++ b/drivers/isdn/hisax/fsm.c
@@ -98,13 +98,11 @@ void
 FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
 {
 	ft->fi = fi;
-	ft->tl.function = (void *) FsmExpireTimer;
-	ft->tl.data = (long) ft;
 #if FSM_TIMER_DEBUG
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "FsmInitTimer %lx", (long) ft);
 #endif
-	init_timer(&ft->tl);
+	setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
 }
 
 void
diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c
index e034ed847ff3..90f051ce0259 100644
--- a/drivers/isdn/hisax/hfc4s8s_l1.c
+++ b/drivers/isdn/hisax/hfc4s8s_l1.c
@@ -1396,9 +1396,8 @@ setup_instance(hfc4s8s_hw *hw)
 		l1p = hw->l1 + i;
 		spin_lock_init(&l1p->lock);
 		l1p->hw = hw;
-		l1p->l1_timer.function = (void *) hfc_l1_timer;
-		l1p->l1_timer.data = (long) (l1p);
-		init_timer(&l1p->l1_timer);
+		setup_timer(&l1p->l1_timer, (void *)hfc_l1_timer,
+			    (long)(l1p));
 		l1p->st_num = i;
 		skb_queue_head_init(&l1p->d_tx_queue);
 		l1p->d_if.ifc.priv = hw->l1 + i;
diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c
index a756e5cb6871..ad8597a1a07e 100644
--- a/drivers/isdn/hisax/hfc_2bds0.c
+++ b/drivers/isdn/hisax/hfc_2bds0.c
@@ -1073,8 +1073,6 @@ set_cs_func(struct IsdnCardState *cs)
 	cs->writeisacfifo = &dummyf;
 	cs->BC_Read_Reg = &ReadReg;
 	cs->BC_Write_Reg = &WriteReg;
-	cs->dbusytimer.function = (void *) hfc_dbusy_timer;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)hfc_dbusy_timer, (long)cs);
 	INIT_WORK(&cs->tqueue, hfcd_bh);
 }
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 90449e1e91e5..f9ca35cc32b1 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -1582,9 +1582,7 @@ inithfcpci(struct IsdnCardState *cs)
 	cs->bcs[1].BC_SetStack = setstack_2b;
 	cs->bcs[0].BC_Close = close_hfcpci;
 	cs->bcs[1].BC_Close = close_hfcpci;
-	cs->dbusytimer.function = (void *) hfcpci_dbusy_timer;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)hfcpci_dbusy_timer, (long)cs);
 	mode_hfcpci(cs->bcs, 0, 0);
 	mode_hfcpci(cs->bcs + 1, 0, 1);
 }
@@ -1746,9 +1744,7 @@ setup_hfcpci(struct IsdnCard *card)
 	cs->BC_Write_Reg = NULL;
 	cs->irq_func = &hfcpci_interrupt;
 	cs->irq_flags |= IRQF_SHARED;
-	cs->hw.hfcpci.timer.function = (void *) hfcpci_Timer;
-	cs->hw.hfcpci.timer.data = (long) cs;
-	init_timer(&cs->hw.hfcpci.timer);
+	setup_timer(&cs->hw.hfcpci.timer, (void *)hfcpci_Timer, (long)cs);
 	cs->cardmsg = &hfcpci_card_msg;
 	cs->auxcmd = &hfcpci_auxcmd;
 
diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c
index 13b2151c10f5..3aef8e1a90e4 100644
--- a/drivers/isdn/hisax/hfc_sx.c
+++ b/drivers/isdn/hisax/hfc_sx.c
@@ -1495,9 +1495,7 @@ int setup_hfcsx(struct IsdnCard *card)
 	} else
 		return (0);	/* no valid card type */
 
-	cs->dbusytimer.function = (void *) hfcsx_dbusy_timer;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)hfcsx_dbusy_timer, (long)cs);
 	INIT_WORK(&cs->tqueue, hfcsx_bh);
 	cs->readisac = NULL;
 	cs->writeisac = NULL;
@@ -1507,11 +1505,9 @@ int setup_hfcsx(struct IsdnCard *card)
 	cs->BC_Write_Reg = NULL;
 	cs->irq_func = &hfcsx_interrupt;
 
-	cs->hw.hfcsx.timer.function = (void *) hfcsx_Timer;
-	cs->hw.hfcsx.timer.data = (long) cs;
 	cs->hw.hfcsx.b_fifo_size = 0; /* fifo size still unknown */
 	cs->hw.hfcsx.cirm = ccd_sp_irqtab[cs->irq & 0xF]; /* RAM not evaluated */
-	init_timer(&cs->hw.hfcsx.timer);
+	setup_timer(&cs->hw.hfcsx.timer, (void *)hfcsx_Timer, (long)cs);
 
 	reset_hfcsx(cs);
 	cs->cardmsg = &hfcsx_card_msg;
diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index 678bd5224bc3..6dbd1f1da14f 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -1165,14 +1165,10 @@ hfc_usb_init(hfcusb_data *hfc)
 	hfc->old_led_state = 0;
 
 	/* init the t3 timer */
-	init_timer(&hfc->t3_timer);
-	hfc->t3_timer.data = (long) hfc;
-	hfc->t3_timer.function = (void *) l1_timer_expire_t3;
+	setup_timer(&hfc->t3_timer, (void *)l1_timer_expire_t3, (long)hfc);
 
 	/* init the t4 timer */
-	init_timer(&hfc->t4_timer);
-	hfc->t4_timer.data = (long) hfc;
-	hfc->t4_timer.function = (void *) l1_timer_expire_t4;
+	setup_timer(&hfc->t4_timer, (void *)l1_timer_expire_t4, (long)hfc);
 
 	/* init the background machinery for control requests */
 	hfc->ctrl_read.bRequestType = 0xc0;
diff --git a/drivers/isdn/hisax/hfcscard.c b/drivers/isdn/hisax/hfcscard.c
index 394da646e97b..467287096918 100644
--- a/drivers/isdn/hisax/hfcscard.c
+++ b/drivers/isdn/hisax/hfcscard.c
@@ -253,9 +253,7 @@ int setup_hfcs(struct IsdnCard *card)
 		outb(0x57, cs->hw.hfcD.addr | 1);
 	}
 	set_cs_func(cs);
-	cs->hw.hfcD.timer.function = (void *) hfcs_Timer;
-	cs->hw.hfcD.timer.data = (long) cs;
-	init_timer(&cs->hw.hfcD.timer);
+	setup_timer(&cs->hw.hfcD.timer, (void *)hfcs_Timer, (long)cs);
 	cs->cardmsg = &hfcs_card_msg;
 	cs->irq_func = &hfcs_interrupt;
 	return (1);
diff --git a/drivers/isdn/hisax/icc.c b/drivers/isdn/hisax/icc.c
index 96d1df05044f..c7c3797a817e 100644
--- a/drivers/isdn/hisax/icc.c
+++ b/drivers/isdn/hisax/icc.c
@@ -676,7 +676,5 @@ clear_pending_icc_ints(struct IsdnCardState *cs)
 void setup_icc(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, icc_bh);
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 }
diff --git a/drivers/isdn/hisax/ipacx.c b/drivers/isdn/hisax/ipacx.c
index 9cc26b40a437..43effe7082ed 100644
--- a/drivers/isdn/hisax/ipacx.c
+++ b/drivers/isdn/hisax/ipacx.c
@@ -424,9 +424,7 @@ dch_init(struct IsdnCardState *cs)
 
 	cs->setstack_d      = dch_setstack;
 
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 
 	cs->writeisac(cs, IPACX_TR_CONF0, 0x00);  // clear LDD
 	cs->writeisac(cs, IPACX_TR_CONF2, 0x00);  // enable transmitter
diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c
index df7e05ca8f9c..4273b4548825 100644
--- a/drivers/isdn/hisax/isac.c
+++ b/drivers/isdn/hisax/isac.c
@@ -677,7 +677,5 @@ void clear_pending_isac_ints(struct IsdnCardState *cs)
 void setup_isac(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, isac_bh);
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 }
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index f4956c73aa11..0dc60b287c4b 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1902,10 +1902,8 @@ void initisar(struct IsdnCardState *cs)
 	cs->bcs[1].BC_SetStack = setstack_isar;
 	cs->bcs[0].BC_Close = close_isarstate;
 	cs->bcs[1].BC_Close = close_isarstate;
-	cs->bcs[0].hw.isar.ftimer.function = (void *) ftimer_handler;
-	cs->bcs[0].hw.isar.ftimer.data = (long) &cs->bcs[0];
-	init_timer(&cs->bcs[0].hw.isar.ftimer);
-	cs->bcs[1].hw.isar.ftimer.function = (void *) ftimer_handler;
-	cs->bcs[1].hw.isar.ftimer.data = (long) &cs->bcs[1];
-	init_timer(&cs->bcs[1].hw.isar.ftimer);
+	setup_timer(&cs->bcs[0].hw.isar.ftimer, (void *)ftimer_handler,
+		    (long)&cs->bcs[0]);
+	setup_timer(&cs->bcs[1].hw.isar.ftimer, (void *)ftimer_handler,
+		    (long)&cs->bcs[1]);
 }
diff --git a/drivers/isdn/hisax/isdnl3.c b/drivers/isdn/hisax/isdnl3.c
index c754706f83cd..569ce52c567b 100644
--- a/drivers/isdn/hisax/isdnl3.c
+++ b/drivers/isdn/hisax/isdnl3.c
@@ -169,9 +169,7 @@ void
 L3InitTimer(struct l3_process *pc, struct L3Timer *t)
 {
 	t->pc = pc;
-	t->tl.function = (void *) L3ExpireTimer;
-	t->tl.data = (long) t;
-	init_timer(&t->tl);
+	setup_timer(&t->tl, (void *)L3ExpireTimer, (long)t);
 }
 
 void
diff --git a/drivers/isdn/hisax/st5481_b.c b/drivers/isdn/hisax/st5481_b.c
index 409849165838..f64a36007800 100644
--- a/drivers/isdn/hisax/st5481_b.c
+++ b/drivers/isdn/hisax/st5481_b.c
@@ -239,7 +239,7 @@ static void st5481B_mode(struct st5481_bcs *bcs, int mode)
 			}
 		}
 	} else {
-		// Disble B channel interrupts
+		// Disable B channel interrupts
 		st5481_usb_device_ctrl_msg(adapter, FFMSK_B1+(bcs->channel * 2), 0, NULL, NULL);
 
 		// Disable B channel FIFOs
diff --git a/drivers/isdn/hisax/teleint.c b/drivers/isdn/hisax/teleint.c
index bf647545c70c..950399f066ef 100644
--- a/drivers/isdn/hisax/teleint.c
+++ b/drivers/isdn/hisax/teleint.c
@@ -278,9 +278,7 @@ int setup_TeleInt(struct IsdnCard *card)
 	cs->bcs[0].hw.hfc.send = NULL;
 	cs->bcs[1].hw.hfc.send = NULL;
 	cs->hw.hfc.fifosize = 7 * 1024 + 512;
-	cs->hw.hfc.timer.function = (void *) TeleInt_Timer;
-	cs->hw.hfc.timer.data = (long) cs;
-	init_timer(&cs->hw.hfc.timer);
+	setup_timer(&cs->hw.hfc.timer, (void *)TeleInt_Timer, (long)cs);
 	if (!request_region(cs->hw.hfc.addr, 2, "TeleInt isdn")) {
 		printk(KERN_WARNING
 		       "HiSax: TeleInt config port %x-%x already in use\n",
diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c
index a85895585d90..c99f0ec58a01 100644
--- a/drivers/isdn/hisax/w6692.c
+++ b/drivers/isdn/hisax/w6692.c
@@ -901,9 +901,8 @@ static void initW6692(struct IsdnCardState *cs, int part)
 	if (part & 1) {
 		cs->setstack_d = setstack_W6692;
 		cs->DC_Close = DC_Close_W6692;
-		cs->dbusytimer.function = (void *) dbusy_timer_handler;
-		cs->dbusytimer.data = (long) cs;
-		init_timer(&cs->dbusytimer);
+		setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler,
+			    (long)cs);
 		resetW6692(cs);
 		ph_command(cs, W_L1CMD_RST);
 		cs->dc.w6692.ph_state = W_L1CMD_RST;
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 9c1e8adaf4fc..d07dd5196ffc 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -2370,9 +2370,8 @@ static struct ippp_ccp_reset_state *isdn_ppp_ccp_reset_alloc_state(struct ippp_s
 		rs->state = CCPResetIdle;
 		rs->is = is;
 		rs->id = id;
-		init_timer(&rs->timer);
-		rs->timer.data = (unsigned long)rs;
-		rs->timer.function = isdn_ppp_ccp_timer_callback;
+		setup_timer(&rs->timer, isdn_ppp_ccp_timer_callback,
+			    (unsigned long)rs);
 		is->reset->rs[id] = rs;
 	}
 	return rs;
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 1b169559a240..ddd8207e4e54 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1812,9 +1812,8 @@ isdn_tty_modem_init(void)
 		info->isdn_channel = -1;
 		info->drv_index = -1;
 		info->xmit_size = ISDN_SERIAL_XMIT_SIZE;
-		init_timer(&info->nc_timer);
-		info->nc_timer.function = isdn_tty_modem_do_ncarrier;
-		info->nc_timer.data = (unsigned long) info;
+		setup_timer(&info->nc_timer, isdn_tty_modem_do_ncarrier,
+			    (unsigned long)info);
 		skb_queue_head_init(&info->xmit_queue);
 #ifdef CONFIG_ISDN_AUDIO
 		skb_queue_head_init(&info->dtmf_queue);
diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c
index 9b85295aa657..880e9d367a39 100644
--- a/drivers/isdn/mISDN/dsp_core.c
+++ b/drivers/isdn/mISDN/dsp_core.c
@@ -1092,9 +1092,7 @@ dspcreate(struct channel_req *crq)
 	ndsp->pcm_bank_tx = -1;
 	ndsp->hfc_conf = -1; /* current conference number */
 	/* set tone timer */
-	ndsp->tone.tl.function = (void *)dsp_tone_timeout;
-	ndsp->tone.tl.data = (long) ndsp;
-	init_timer(&ndsp->tone.tl);
+	setup_timer(&ndsp->tone.tl, (void *)dsp_tone_timeout, (long)ndsp);
 
 	if (dtmfthreshold < 20 || dtmfthreshold > 500)
 		dtmfthreshold = 200;
diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c
index 26477d48bbda..78fc5d5e9051 100644
--- a/drivers/isdn/mISDN/fsm.c
+++ b/drivers/isdn/mISDN/fsm.c
@@ -110,13 +110,11 @@ void
 mISDN_FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
 {
 	ft->fi = fi;
-	ft->tl.function = (void *) FsmExpireTimer;
-	ft->tl.data = (long) ft;
 #if FSM_TIMER_DEBUG
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "mISDN_FsmInitTimer %lx", (long) ft);
 #endif
-	init_timer(&ft->tl);
+	setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
 }
 EXPORT_SYMBOL(mISDN_FsmInitTimer);
 
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 6ceca7db62ad..6be2041248d3 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -1443,9 +1443,7 @@ init_card(struct l1oip *hc, int pri, int bundle)
 	hc->keep_tl.expires = jiffies + 2 * HZ; /* two seconds first time */
 	add_timer(&hc->keep_tl);
 
-	hc->timeout_tl.function = (void *)l1oip_timeout;
-	hc->timeout_tl.data = (ulong)hc;
-	init_timer(&hc->timeout_tl);
+	setup_timer(&hc->timeout_tl, (void *)l1oip_timeout, (ulong)hc);
 	hc->timeout_on = 0; /* state that we have timer off */
 
 	return 0;
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 275f467956ee..6c2999872090 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -76,6 +76,15 @@ config LEDS_BCM6358
 	  This option enables support for LEDs connected to the BCM6358
 	  LED HW controller accessed via MMIO registers.
 
+config LEDS_CPCAP
+	tristate "LED Support for Motorola CPCAP"
+	depends on LEDS_CLASS
+	depends on MFD_CPCAP
+	depends on OF
+	help
+	  This option enables support for LEDs offered by Motorola's
+	  CPCAP PMIC.
+
 config LEDS_LM3530
 	tristate "LCD Backlight driver for LM3530"
 	depends on LEDS_CLASS
@@ -126,6 +135,14 @@ config LEDS_MIKROTIK_RB532
 	  This option enables support for the so called "User LED" of
 	  Mikrotik's Routerboard 532.
 
+config LEDS_MT6323
+	tristate "LED Support for Mediatek MT6323 PMIC"
+	depends on LEDS_CLASS
+	depends on MFD_MT6397
+	help
+	  This option enables support for on-chip LED drivers found on
+	  Mediatek MT6323 PMIC.
+
 config LEDS_S3C24XX
 	tristate "LED Support for Samsung S3C24XX GPIO LEDs"
 	depends on LEDS_CLASS
@@ -241,7 +258,6 @@ config LEDS_LP3952
 	tristate "LED Support for TI LP3952 2 channel LED driver"
 	depends on LEDS_CLASS
 	depends on I2C
-	depends on ACPI
 	depends on GPIOLIB
 	select REGMAP_I2C
 	help
@@ -463,15 +479,6 @@ config LEDS_ADP5520
 	  To compile this driver as a module, choose M here: the module will
 	  be called leds-adp5520.
 
-config LEDS_DELL_NETBOOKS
-	tristate "External LED on Dell Business Netbooks"
-	depends on LEDS_CLASS
-	depends on X86 && ACPI_WMI
-	depends on DELL_SMBIOS
-	help
-	  This adds support for the Latitude 2100 and similar
-	  notebooks that have an external LED.
-
 config LEDS_MC13783
 	tristate "LED Support for MC13XXX PMIC"
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 6b8273736478..45f133962ed8 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_LEDS_AAT1290)		+= leds-aat1290.o
 obj-$(CONFIG_LEDS_BCM6328)		+= leds-bcm6328.o
 obj-$(CONFIG_LEDS_BCM6358)		+= leds-bcm6358.o
 obj-$(CONFIG_LEDS_BD2802)		+= leds-bd2802.o
+obj-$(CONFIG_LEDS_CPCAP)		+= leds-cpcap.o
 obj-$(CONFIG_LEDS_LOCOMO)		+= leds-locomo.o
 obj-$(CONFIG_LEDS_LM3530)		+= leds-lm3530.o
 obj-$(CONFIG_LEDS_LM3533)		+= leds-lm3533.o
@@ -52,7 +53,6 @@ obj-$(CONFIG_LEDS_REGULATOR)		+= leds-regulator.o
 obj-$(CONFIG_LEDS_INTEL_SS4200)		+= leds-ss4200.o
 obj-$(CONFIG_LEDS_LT3593)		+= leds-lt3593.o
 obj-$(CONFIG_LEDS_ADP5520)		+= leds-adp5520.o
-obj-$(CONFIG_LEDS_DELL_NETBOOKS)	+= dell-led.o
 obj-$(CONFIG_LEDS_MC13783)		+= leds-mc13783.o
 obj-$(CONFIG_LEDS_NS2)			+= leds-ns2.o
 obj-$(CONFIG_LEDS_NETXBIG)		+= leds-netxbig.o
@@ -72,6 +72,7 @@ obj-$(CONFIG_LEDS_IS31FL32XX)		+= leds-is31fl32xx.o
 obj-$(CONFIG_LEDS_PM8058)		+= leds-pm8058.o
 obj-$(CONFIG_LEDS_MLXCPLD)		+= leds-mlxcpld.o
 obj-$(CONFIG_LEDS_NIC78BX)		+= leds-nic78bx.o
+obj-$(CONFIG_LEDS_MT6323)		+= leds-mt6323.o
 
 # LED SPI Drivers
 obj-$(CONFIG_LEDS_DAC124S085)		+= leds-dac124s085.o
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index f2b0a80a62b4..b0e2d55acbd6 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -244,11 +244,14 @@ static int led_classdev_next_name(const char *init_name, char *name,
 }
 
 /**
- * led_classdev_register - register a new object of led_classdev class.
- * @parent: The device to register.
+ * of_led_classdev_register - register a new object of led_classdev class.
+ *
+ * @parent: parent of LED device
  * @led_cdev: the led_classdev structure for this device.
+ * @np: DT node describing this LED
  */
-int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
+int of_led_classdev_register(struct device *parent, struct device_node *np,
+			    struct led_classdev *led_cdev)
 {
 	char name[LED_MAX_NAME_SIZE];
 	int ret;
@@ -261,6 +264,7 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 				led_cdev, led_cdev->groups, "%s", name);
 	if (IS_ERR(led_cdev->dev))
 		return PTR_ERR(led_cdev->dev);
+	led_cdev->dev->of_node = np;
 
 	if (ret)
 		dev_warn(parent, "Led %s renamed to %s due to name collision",
@@ -303,7 +307,7 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(led_classdev_register);
+EXPORT_SYMBOL_GPL(of_led_classdev_register);
 
 /**
  * led_classdev_unregister - unregisters a object of led_properties class.
@@ -348,12 +352,14 @@ static void devm_led_classdev_release(struct device *dev, void *res)
 }
 
 /**
- * devm_led_classdev_register - resource managed led_classdev_register()
- * @parent: The device to register.
+ * devm_of_led_classdev_register - resource managed led_classdev_register()
+ *
+ * @parent: parent of LED device
  * @led_cdev: the led_classdev structure for this device.
  */
-int devm_led_classdev_register(struct device *parent,
-			       struct led_classdev *led_cdev)
+int devm_of_led_classdev_register(struct device *parent,
+				  struct device_node *np,
+				  struct led_classdev *led_cdev)
 {
 	struct led_classdev **dr;
 	int rc;
@@ -362,7 +368,7 @@ int devm_led_classdev_register(struct device *parent,
 	if (!dr)
 		return -ENOMEM;
 
-	rc = led_classdev_register(parent, led_cdev);
+	rc = of_led_classdev_register(parent, np, led_cdev);
 	if (rc) {
 		devres_free(dr);
 		return rc;
@@ -373,7 +379,7 @@ int devm_led_classdev_register(struct device *parent,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(devm_led_classdev_register);
+EXPORT_SYMBOL_GPL(devm_of_led_classdev_register);
 
 static int devm_led_classdev_match(struct device *dev, void *res, void *data)
 {
diff --git a/drivers/leds/leds-cpcap.c b/drivers/leds/leds-cpcap.c
new file mode 100644
index 000000000000..f0f28c442807
--- /dev/null
+++ b/drivers/leds/leds-cpcap.c
@@ -0,0 +1,239 @@
+/*
+ * Copyright (c) 2017 Sebastian Reichel <sre@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 or
+ * later as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/leds.h>
+#include <linux/mfd/motorola-cpcap.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#define CPCAP_LED_NO_CURRENT 0x0001
+
+struct cpcap_led_info {
+	u16 reg;
+	u16 mask;
+	u16 limit;
+	u16 init_mask;
+	u16 init_val;
+};
+
+static const struct cpcap_led_info cpcap_led_red = {
+	.reg	= CPCAP_REG_REDC,
+	.mask	= 0x03FF,
+	.limit	= 31,
+};
+
+static const struct cpcap_led_info cpcap_led_green = {
+	.reg	= CPCAP_REG_GREENC,
+	.mask	= 0x03FF,
+	.limit	= 31,
+};
+
+static const struct cpcap_led_info cpcap_led_blue = {
+	.reg	= CPCAP_REG_BLUEC,
+	.mask	= 0x03FF,
+	.limit	= 31,
+};
+
+/* aux display light */
+static const struct cpcap_led_info cpcap_led_adl = {
+	.reg		= CPCAP_REG_ADLC,
+	.mask		= 0x000F,
+	.limit		= 1,
+	.init_mask	= 0x7FFF,
+	.init_val	= 0x5FF0,
+};
+
+/* camera privacy led */
+static const struct cpcap_led_info cpcap_led_cp = {
+	.reg		= CPCAP_REG_CLEDC,
+	.mask		= 0x0007,
+	.limit		= 1,
+	.init_mask	= 0x03FF,
+	.init_val	= 0x0008,
+};
+
+struct cpcap_led {
+	struct led_classdev led;
+	const struct cpcap_led_info *info;
+	struct device *dev;
+	struct regmap *regmap;
+	struct mutex update_lock;
+	struct regulator *vdd;
+	bool powered;
+
+	u32 current_limit;
+};
+
+static u16 cpcap_led_val(u8 current_limit, u8 duty_cycle)
+{
+	current_limit &= 0x1f; /* 5 bit */
+	duty_cycle &= 0x0f; /* 4 bit */
+
+	return current_limit << 4 | duty_cycle;
+}
+
+static int cpcap_led_set_power(struct cpcap_led *led, bool status)
+{
+	int err;
+
+	if (status == led->powered)
+		return 0;
+
+	if (status)
+		err = regulator_enable(led->vdd);
+	else
+		err = regulator_disable(led->vdd);
+
+	if (err) {
+		dev_err(led->dev, "regulator failure: %d", err);
+		return err;
+	}
+
+	led->powered = status;
+
+	return 0;
+}
+
+static int cpcap_led_set(struct led_classdev *ledc, enum led_brightness value)
+{
+	struct cpcap_led *led = container_of(ledc, struct cpcap_led, led);
+	int brightness;
+	int err;
+
+	mutex_lock(&led->update_lock);
+
+	if (value > LED_OFF) {
+		err = cpcap_led_set_power(led, true);
+		if (err)
+			goto exit;
+	}
+
+	if (value == LED_OFF) {
+		/* Avoid HW issue by turning off current before duty cycle */
+		err = regmap_update_bits(led->regmap,
+			led->info->reg, led->info->mask, CPCAP_LED_NO_CURRENT);
+		if (err) {
+			dev_err(led->dev, "regmap failed: %d", err);
+			goto exit;
+		}
+
+		brightness = cpcap_led_val(value, LED_OFF);
+	} else {
+		brightness = cpcap_led_val(value, LED_ON);
+	}
+
+	err = regmap_update_bits(led->regmap, led->info->reg, led->info->mask,
+		brightness);
+	if (err) {
+		dev_err(led->dev, "regmap failed: %d", err);
+		goto exit;
+	}
+
+	if (value == LED_OFF) {
+		err = cpcap_led_set_power(led, false);
+		if (err)
+			goto exit;
+	}
+
+exit:
+	mutex_unlock(&led->update_lock);
+	return err;
+}
+
+static const struct of_device_id cpcap_led_of_match[] = {
+	{ .compatible = "motorola,cpcap-led-red", .data = &cpcap_led_red },
+	{ .compatible = "motorola,cpcap-led-green", .data = &cpcap_led_green },
+	{ .compatible = "motorola,cpcap-led-blue",  .data = &cpcap_led_blue },
+	{ .compatible = "motorola,cpcap-led-adl", .data = &cpcap_led_adl },
+	{ .compatible = "motorola,cpcap-led-cp", .data = &cpcap_led_cp },
+	{},
+};
+MODULE_DEVICE_TABLE(of, cpcap_led_of_match);
+
+static int cpcap_led_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	struct cpcap_led *led;
+	int err;
+
+	match = of_match_device(of_match_ptr(cpcap_led_of_match), &pdev->dev);
+	if (!match || !match->data)
+		return -EINVAL;
+
+	led = devm_kzalloc(&pdev->dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, led);
+	led->info = match->data;
+	led->dev = &pdev->dev;
+
+	if (led->info->reg == 0x0000) {
+		dev_err(led->dev, "Unsupported LED");
+		return -ENODEV;
+	}
+
+	led->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!led->regmap)
+		return -ENODEV;
+
+	led->vdd = devm_regulator_get(&pdev->dev, "vdd");
+	if (IS_ERR(led->vdd)) {
+		err = PTR_ERR(led->vdd);
+		dev_err(led->dev, "Couldn't get regulator: %d", err);
+		return err;
+	}
+
+	err = device_property_read_string(&pdev->dev, "label", &led->led.name);
+	if (err) {
+		dev_err(led->dev, "Couldn't read LED label: %d", err);
+		return err;
+	}
+
+	if (led->info->init_mask) {
+		err = regmap_update_bits(led->regmap, led->info->reg,
+			led->info->init_mask, led->info->init_val);
+		if (err) {
+			dev_err(led->dev, "regmap failed: %d", err);
+			return err;
+		}
+	}
+
+	mutex_init(&led->update_lock);
+
+	led->led.max_brightness = led->info->limit;
+	led->led.brightness_set_blocking = cpcap_led_set;
+	err = devm_led_classdev_register(&pdev->dev, &led->led);
+	if (err) {
+		dev_err(led->dev, "Couldn't register LED: %d", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static struct platform_driver cpcap_led_driver = {
+	.probe = cpcap_led_probe,
+	.driver = {
+		.name = "cpcap-led",
+		.of_match_table = cpcap_led_of_match,
+	},
+};
+module_platform_driver(cpcap_led_driver);
+
+MODULE_DESCRIPTION("CPCAP LED driver");
+MODULE_AUTHOR("Sebastian Reichel <sre@kernel.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 066fc7590729..e753ba93ba1e 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -77,7 +77,7 @@ static int gpio_blink_set(struct led_classdev *led_cdev,
 
 static int create_gpio_led(const struct gpio_led *template,
 	struct gpio_led_data *led_dat, struct device *parent,
-	gpio_blink_set_t blink_set)
+	struct device_node *np, gpio_blink_set_t blink_set)
 {
 	int ret, state;
 
@@ -139,7 +139,7 @@ static int create_gpio_led(const struct gpio_led *template,
 	if (ret < 0)
 		return ret;
 
-	return devm_led_classdev_register(parent, &led_dat->cdev);
+	return devm_of_led_classdev_register(parent, np, &led_dat->cdev);
 }
 
 struct gpio_leds_priv {
@@ -208,7 +208,7 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev)
 		if (fwnode_property_present(child, "panic-indicator"))
 			led.panic_indicator = 1;
 
-		ret = create_gpio_led(&led, led_dat, dev, NULL);
+		ret = create_gpio_led(&led, led_dat, dev, np, NULL);
 		if (ret < 0) {
 			fwnode_handle_put(child);
 			return ERR_PTR(ret);
@@ -242,9 +242,9 @@ static int gpio_led_probe(struct platform_device *pdev)
 
 		priv->num_leds = pdata->num_leds;
 		for (i = 0; i < priv->num_leds; i++) {
-			ret = create_gpio_led(&pdata->leds[i],
-					      &priv->leds[i],
-					      &pdev->dev, pdata->gpio_blink_set);
+			ret = create_gpio_led(&pdata->leds[i], &priv->leds[i],
+					      &pdev->dev, NULL,
+					      pdata->gpio_blink_set);
 			if (ret < 0)
 				return ret;
 		}
diff --git a/drivers/leds/leds-lp3952.c b/drivers/leds/leds-lp3952.c
index 4847e89883a7..847f7f282126 100644
--- a/drivers/leds/leds-lp3952.c
+++ b/drivers/leds/leds-lp3952.c
@@ -10,7 +10,6 @@
  *
  */
 
-#include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
 #include <linux/i2c.h>
@@ -103,10 +102,11 @@ static int lp3952_get_label(struct device *dev, const char *label, char *dest)
 	const char *str;
 
 	ret = device_property_read_string(dev, label, &str);
-	if (!ret)
-		strncpy(dest, str, LP3952_LABEL_MAX_LEN);
+	if (ret)
+		return ret;
 
-	return ret;
+	strncpy(dest, str, LP3952_LABEL_MAX_LEN);
+	return 0;
 }
 
 static int lp3952_register_led_classdev(struct lp3952_led_array *priv)
@@ -276,19 +276,9 @@ static const struct i2c_device_id lp3952_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lp3952_id);
 
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id lp3952_acpi_match[] = {
-	{"TXNW3952", 0},
-	{}
-};
-
-MODULE_DEVICE_TABLE(acpi, lp3952_acpi_match);
-#endif
-
 static struct i2c_driver lp3952_i2c_driver = {
 	.driver = {
 			.name = LP3952_NAME,
-			.acpi_match_table = ACPI_PTR(lp3952_acpi_match),
 	},
 	.probe = lp3952_probe,
 	.remove = lp3952_remove,
diff --git a/drivers/leds/leds-mt6323.c b/drivers/leds/leds-mt6323.c
new file mode 100644
index 000000000000..8893c74e9a1f
--- /dev/null
+++ b/drivers/leds/leds-mt6323.c
@@ -0,0 +1,502 @@
+/*
+ * LED driver for Mediatek MT6323 PMIC
+ *
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/leds.h>
+#include <linux/mfd/mt6323/registers.h>
+#include <linux/mfd/mt6397/core.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+/*
+ * Register field for MT6323_TOP_CKPDN0 to enable
+ * 32K clock common for LED device.
+ */
+#define MT6323_RG_DRV_32K_CK_PDN	BIT(11)
+#define MT6323_RG_DRV_32K_CK_PDN_MASK	BIT(11)
+
+/*
+ * Register field for MT6323_TOP_CKPDN2 to enable
+ * individual clock for LED device.
+ */
+#define MT6323_RG_ISINK_CK_PDN(i)	BIT(i)
+#define MT6323_RG_ISINK_CK_PDN_MASK(i)	BIT(i)
+
+/*
+ * Register field for MT6323_TOP_CKCON1 to select
+ * clock source.
+ */
+#define MT6323_RG_ISINK_CK_SEL_MASK(i)	(BIT(10) << (i))
+
+/*
+ * Register for MT6323_ISINK_CON0 to setup the
+ * duty cycle of the blink.
+ */
+#define MT6323_ISINK_CON0(i)		(MT6323_ISINK0_CON0 + 0x8 * (i))
+#define MT6323_ISINK_DIM_DUTY_MASK	(0x1f << 8)
+#define MT6323_ISINK_DIM_DUTY(i)	(((i) << 8) & \
+					MT6323_ISINK_DIM_DUTY_MASK)
+
+/* Register to setup the period of the blink. */
+#define MT6323_ISINK_CON1(i)		(MT6323_ISINK0_CON1 + 0x8 * (i))
+#define MT6323_ISINK_DIM_FSEL_MASK	(0xffff)
+#define MT6323_ISINK_DIM_FSEL(i)	((i) & MT6323_ISINK_DIM_FSEL_MASK)
+
+/* Register to control the brightness. */
+#define MT6323_ISINK_CON2(i)		(MT6323_ISINK0_CON2 + 0x8 * (i))
+#define MT6323_ISINK_CH_STEP_SHIFT	12
+#define MT6323_ISINK_CH_STEP_MASK	(0x7 << 12)
+#define MT6323_ISINK_CH_STEP(i)		(((i) << 12) & \
+					MT6323_ISINK_CH_STEP_MASK)
+#define MT6323_ISINK_SFSTR0_TC_MASK	(0x3 << 1)
+#define MT6323_ISINK_SFSTR0_TC(i)	(((i) << 1) & \
+					MT6323_ISINK_SFSTR0_TC_MASK)
+#define MT6323_ISINK_SFSTR0_EN_MASK	BIT(0)
+#define MT6323_ISINK_SFSTR0_EN		BIT(0)
+
+/* Register to LED channel enablement. */
+#define MT6323_ISINK_CH_EN_MASK(i)	BIT(i)
+#define MT6323_ISINK_CH_EN(i)		BIT(i)
+
+#define MT6323_MAX_PERIOD		10000
+#define MT6323_MAX_LEDS			4
+#define MT6323_MAX_BRIGHTNESS		6
+#define MT6323_UNIT_DUTY		3125
+#define MT6323_CAL_HW_DUTY(o, p)	DIV_ROUND_CLOSEST((o) * 100000ul,\
+					(p) * MT6323_UNIT_DUTY)
+
+struct mt6323_leds;
+
+/**
+ * struct mt6323_led - state container for the LED device
+ * @id:			the identifier in MT6323 LED device
+ * @parent:		the pointer to MT6323 LED controller
+ * @cdev:		LED class device for this LED device
+ * @current_brightness: current state of the LED device
+ */
+struct mt6323_led {
+	int			id;
+	struct mt6323_leds	*parent;
+	struct led_classdev	cdev;
+	enum led_brightness	current_brightness;
+};
+
+/**
+ * struct mt6323_leds -	state container for holding LED controller
+ *			of the driver
+ * @dev:		the device pointer
+ * @hw:			the underlying hardware providing shared
+ *			bus for the register operations
+ * @lock:		the lock among process context
+ * @led:		the array that contains the state of individual
+ *			LED device
+ */
+struct mt6323_leds {
+	struct device		*dev;
+	struct mt6397_chip	*hw;
+	/* protect among process context */
+	struct mutex		lock;
+	struct mt6323_led	*led[MT6323_MAX_LEDS];
+};
+
+static int mt6323_led_hw_brightness(struct led_classdev *cdev,
+				    enum led_brightness brightness)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	struct mt6323_leds *leds = led->parent;
+	struct regmap *regmap = leds->hw->regmap;
+	u32 con2_mask = 0, con2_val = 0;
+	int ret;
+
+	/*
+	 * Setup current output for the corresponding
+	 * brightness level.
+	 */
+	con2_mask |= MT6323_ISINK_CH_STEP_MASK |
+		     MT6323_ISINK_SFSTR0_TC_MASK |
+		     MT6323_ISINK_SFSTR0_EN_MASK;
+	con2_val |=  MT6323_ISINK_CH_STEP(brightness - 1) |
+		     MT6323_ISINK_SFSTR0_TC(2) |
+		     MT6323_ISINK_SFSTR0_EN;
+
+	ret = regmap_update_bits(regmap, MT6323_ISINK_CON2(led->id),
+				 con2_mask, con2_val);
+	return ret;
+}
+
+static int mt6323_led_hw_off(struct led_classdev *cdev)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	struct mt6323_leds *leds = led->parent;
+	struct regmap *regmap = leds->hw->regmap;
+	unsigned int status;
+	int ret;
+
+	status = MT6323_ISINK_CH_EN(led->id);
+	ret = regmap_update_bits(regmap, MT6323_ISINK_EN_CTRL,
+				 MT6323_ISINK_CH_EN_MASK(led->id), ~status);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(100, 300);
+	ret = regmap_update_bits(regmap, MT6323_TOP_CKPDN2,
+				 MT6323_RG_ISINK_CK_PDN_MASK(led->id),
+				 MT6323_RG_ISINK_CK_PDN(led->id));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static enum led_brightness
+mt6323_get_led_hw_brightness(struct led_classdev *cdev)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	struct mt6323_leds *leds = led->parent;
+	struct regmap *regmap = leds->hw->regmap;
+	unsigned int status;
+	int ret;
+
+	ret = regmap_read(regmap, MT6323_TOP_CKPDN2, &status);
+	if (ret < 0)
+		return ret;
+
+	if (status & MT6323_RG_ISINK_CK_PDN_MASK(led->id))
+		return 0;
+
+	ret = regmap_read(regmap, MT6323_ISINK_EN_CTRL, &status);
+	if (ret < 0)
+		return ret;
+
+	if (!(status & MT6323_ISINK_CH_EN(led->id)))
+		return 0;
+
+	ret = regmap_read(regmap, MT6323_ISINK_CON2(led->id), &status);
+	if (ret < 0)
+		return ret;
+
+	return  ((status & MT6323_ISINK_CH_STEP_MASK)
+		  >> MT6323_ISINK_CH_STEP_SHIFT) + 1;
+}
+
+static int mt6323_led_hw_on(struct led_classdev *cdev,
+			    enum led_brightness brightness)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	struct mt6323_leds *leds = led->parent;
+	struct regmap *regmap = leds->hw->regmap;
+	unsigned int status;
+	int ret;
+
+	/*
+	 * Setup required clock source, enable the corresponding
+	 * clock and channel and let work with continuous blink as
+	 * the default.
+	 */
+	ret = regmap_update_bits(regmap, MT6323_TOP_CKCON1,
+				 MT6323_RG_ISINK_CK_SEL_MASK(led->id), 0);
+	if (ret < 0)
+		return ret;
+
+	status = MT6323_RG_ISINK_CK_PDN(led->id);
+	ret = regmap_update_bits(regmap, MT6323_TOP_CKPDN2,
+				 MT6323_RG_ISINK_CK_PDN_MASK(led->id),
+				 ~status);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(100, 300);
+
+	ret = regmap_update_bits(regmap, MT6323_ISINK_EN_CTRL,
+				 MT6323_ISINK_CH_EN_MASK(led->id),
+				 MT6323_ISINK_CH_EN(led->id));
+	if (ret < 0)
+		return ret;
+
+	ret = mt6323_led_hw_brightness(cdev, brightness);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_update_bits(regmap, MT6323_ISINK_CON0(led->id),
+				 MT6323_ISINK_DIM_DUTY_MASK,
+				 MT6323_ISINK_DIM_DUTY(31));
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_update_bits(regmap, MT6323_ISINK_CON1(led->id),
+				 MT6323_ISINK_DIM_FSEL_MASK,
+				 MT6323_ISINK_DIM_FSEL(1000));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int mt6323_led_set_blink(struct led_classdev *cdev,
+				unsigned long *delay_on,
+				unsigned long *delay_off)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	struct mt6323_leds *leds = led->parent;
+	struct regmap *regmap = leds->hw->regmap;
+	unsigned long period;
+	u8 duty_hw;
+	int ret;
+
+	/*
+	 * Units are in ms, if over the hardware able
+	 * to support, fallback into software blink
+	 */
+	period = *delay_on + *delay_off;
+
+	if (period > MT6323_MAX_PERIOD)
+		return -EINVAL;
+
+	/*
+	 * LED subsystem requires a default user
+	 * friendly blink pattern for the LED so using
+	 * 1Hz duty cycle 50% here if without specific
+	 * value delay_on and delay off being assigned.
+	 */
+	if (!*delay_on && !*delay_off) {
+		*delay_on = 500;
+		*delay_off = 500;
+	}
+
+	/*
+	 * Calculate duty_hw based on the percentage of period during
+	 * which the led is ON.
+	 */
+	duty_hw = MT6323_CAL_HW_DUTY(*delay_on, period);
+
+	/* hardware doesn't support zero duty cycle. */
+	if (!duty_hw)
+		return -EINVAL;
+
+	mutex_lock(&leds->lock);
+	/*
+	 * Set max_brightness as the software blink behavior
+	 * when no blink brightness.
+	 */
+	if (!led->current_brightness) {
+		ret = mt6323_led_hw_on(cdev, cdev->max_brightness);
+		if (ret < 0)
+			goto out;
+		led->current_brightness = cdev->max_brightness;
+	}
+
+	ret = regmap_update_bits(regmap, MT6323_ISINK_CON0(led->id),
+				 MT6323_ISINK_DIM_DUTY_MASK,
+				 MT6323_ISINK_DIM_DUTY(duty_hw - 1));
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(regmap, MT6323_ISINK_CON1(led->id),
+				 MT6323_ISINK_DIM_FSEL_MASK,
+				 MT6323_ISINK_DIM_FSEL(period - 1));
+out:
+	mutex_unlock(&leds->lock);
+
+	return ret;
+}
+
+static int mt6323_led_set_brightness(struct led_classdev *cdev,
+				     enum led_brightness brightness)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	struct mt6323_leds *leds = led->parent;
+	int ret;
+
+	mutex_lock(&leds->lock);
+
+	if (!led->current_brightness && brightness) {
+		ret = mt6323_led_hw_on(cdev, brightness);
+		if (ret < 0)
+			goto out;
+	} else if (brightness) {
+		ret = mt6323_led_hw_brightness(cdev, brightness);
+		if (ret < 0)
+			goto out;
+	} else {
+		ret = mt6323_led_hw_off(cdev);
+		if (ret < 0)
+			goto out;
+	}
+
+	led->current_brightness = brightness;
+out:
+	mutex_unlock(&leds->lock);
+
+	return ret;
+}
+
+static int mt6323_led_set_dt_default(struct led_classdev *cdev,
+				     struct device_node *np)
+{
+	struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+	const char *state;
+	int ret = 0;
+
+	led->cdev.name = of_get_property(np, "label", NULL) ? : np->name;
+	led->cdev.default_trigger = of_get_property(np,
+						    "linux,default-trigger",
+						    NULL);
+
+	state = of_get_property(np, "default-state", NULL);
+	if (state) {
+		if (!strcmp(state, "keep")) {
+			ret = mt6323_get_led_hw_brightness(cdev);
+			if (ret < 0)
+				return ret;
+			led->current_brightness = ret;
+			ret = 0;
+		} else if (!strcmp(state, "on")) {
+			ret =
+			mt6323_led_set_brightness(cdev, cdev->max_brightness);
+		} else  {
+			ret = mt6323_led_set_brightness(cdev, LED_OFF);
+		}
+	}
+
+	return ret;
+}
+
+static int mt6323_led_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *child;
+	struct mt6397_chip *hw = dev_get_drvdata(pdev->dev.parent);
+	struct mt6323_leds *leds;
+	struct mt6323_led *led;
+	int ret;
+	unsigned int status;
+	u32 reg;
+
+	leds = devm_kzalloc(dev, sizeof(*leds), GFP_KERNEL);
+	if (!leds)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, leds);
+	leds->dev = dev;
+
+	/*
+	 * leds->hw points to the underlying bus for the register
+	 * controlled.
+	 */
+	leds->hw = hw;
+	mutex_init(&leds->lock);
+
+	status = MT6323_RG_DRV_32K_CK_PDN;
+	ret = regmap_update_bits(leds->hw->regmap, MT6323_TOP_CKPDN0,
+				 MT6323_RG_DRV_32K_CK_PDN_MASK, ~status);
+	if (ret < 0) {
+		dev_err(leds->dev,
+			"Failed to update MT6323_TOP_CKPDN0 Register\n");
+		return ret;
+	}
+
+	for_each_available_child_of_node(np, child) {
+		ret = of_property_read_u32(child, "reg", &reg);
+		if (ret) {
+			dev_err(dev, "Failed to read led 'reg' property\n");
+			goto put_child_node;
+		}
+
+		if (reg >= MT6323_MAX_LEDS || leds->led[reg]) {
+			dev_err(dev, "Invalid led reg %u\n", reg);
+			ret = -EINVAL;
+			goto put_child_node;
+		}
+
+		led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+		if (!led) {
+			ret = -ENOMEM;
+			goto put_child_node;
+		}
+
+		leds->led[reg] = led;
+		leds->led[reg]->id = reg;
+		leds->led[reg]->cdev.max_brightness = MT6323_MAX_BRIGHTNESS;
+		leds->led[reg]->cdev.brightness_set_blocking =
+					mt6323_led_set_brightness;
+		leds->led[reg]->cdev.blink_set = mt6323_led_set_blink;
+		leds->led[reg]->cdev.brightness_get =
+					mt6323_get_led_hw_brightness;
+		leds->led[reg]->parent = leds;
+
+		ret = mt6323_led_set_dt_default(&leds->led[reg]->cdev, child);
+		if (ret < 0) {
+			dev_err(leds->dev,
+				"Failed to LED set default from devicetree\n");
+			goto put_child_node;
+		}
+
+		ret = devm_led_classdev_register(dev, &leds->led[reg]->cdev);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to register LED: %d\n",
+				ret);
+			goto put_child_node;
+		}
+		leds->led[reg]->cdev.dev->of_node = child;
+	}
+
+	return 0;
+
+put_child_node:
+	of_node_put(child);
+	return ret;
+}
+
+static int mt6323_led_remove(struct platform_device *pdev)
+{
+	struct mt6323_leds *leds = platform_get_drvdata(pdev);
+	int i;
+
+	/* Turn the LEDs off on driver removal. */
+	for (i = 0 ; leds->led[i] ; i++)
+		mt6323_led_hw_off(&leds->led[i]->cdev);
+
+	regmap_update_bits(leds->hw->regmap, MT6323_TOP_CKPDN0,
+			   MT6323_RG_DRV_32K_CK_PDN_MASK,
+			   MT6323_RG_DRV_32K_CK_PDN);
+
+	mutex_destroy(&leds->lock);
+
+	return 0;
+}
+
+static const struct of_device_id mt6323_led_dt_match[] = {
+	{ .compatible = "mediatek,mt6323-led" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mt6323_led_dt_match);
+
+static struct platform_driver mt6323_led_driver = {
+	.probe		= mt6323_led_probe,
+	.remove		= mt6323_led_remove,
+	.driver		= {
+		.name	= "mt6323-led",
+		.of_match_table = mt6323_led_dt_match,
+	},
+};
+
+module_platform_driver(mt6323_led_driver);
+
+MODULE_DESCRIPTION("LED driver for Mediatek MT6323 PMIC");
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 06e63106ae1e..7fea18b0c15d 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -254,6 +254,21 @@ static void pca9532_input_work(struct work_struct *work)
 	mutex_unlock(&data->update_lock);
 }
 
+static enum pca9532_state pca9532_getled(struct pca9532_led *led)
+{
+	struct i2c_client *client = led->client;
+	struct pca9532_data *data = i2c_get_clientdata(client);
+	u8 maxleds = data->chip_info->num_leds;
+	char reg;
+	enum pca9532_state ret;
+
+	mutex_lock(&data->update_lock);
+	reg = i2c_smbus_read_byte_data(client, LED_REG(maxleds, led->id));
+	ret = reg >> LED_NUM(led->id)/2;
+	mutex_unlock(&data->update_lock);
+	return ret;
+}
+
 #ifdef CONFIG_LEDS_PCA9532_GPIO
 static int pca9532_gpio_request_pin(struct gpio_chip *gc, unsigned offset)
 {
@@ -366,7 +381,10 @@ static int pca9532_configure(struct i2c_client *client,
 			gpios++;
 			break;
 		case PCA9532_TYPE_LED:
-			led->state = pled->state;
+			if (pled->state == PCA9532_KEEP)
+				led->state = pca9532_getled(led);
+			else
+				led->state = pled->state;
 			led->name = pled->name;
 			led->ldev.name = led->name;
 			led->ldev.default_trigger = pled->default_trigger;
@@ -456,6 +474,7 @@ pca9532_of_populate_pdata(struct device *dev, struct device_node *np)
 	const struct of_device_id *match;
 	int devid, maxleds;
 	int i = 0;
+	const char *state;
 
 	match = of_match_device(of_pca9532_leds_match, dev);
 	if (!match)
@@ -475,6 +494,12 @@ pca9532_of_populate_pdata(struct device *dev, struct device_node *np)
 		of_property_read_u32(child, "type", &pdata->leds[i].type);
 		of_property_read_string(child, "linux,default-trigger",
 					&pdata->leds[i].default_trigger);
+		if (!of_property_read_string(child, "default-state", &state)) {
+			if (!strcmp(state, "on"))
+				pdata->leds[i].state = PCA9532_ON;
+			else if (!strcmp(state, "keep"))
+				pdata->leds[i].state = PCA9532_KEEP;
+		}
 		if (++i >= maxleds) {
 			of_node_put(child);
 			break;
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index a41896468cb3..66a626091936 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -31,12 +31,16 @@
 #define MAX_NAME_LEN	8
 
 struct led_trigger_cpu {
+	bool is_active;
 	char name[MAX_NAME_LEN];
 	struct led_trigger *_trig;
 };
 
 static DEFINE_PER_CPU(struct led_trigger_cpu, cpu_trig);
 
+static struct led_trigger *trig_cpu_all;
+static atomic_t num_active_cpus = ATOMIC_INIT(0);
+
 /**
  * ledtrig_cpu - emit a CPU event as a trigger
  * @evt: CPU event to be emitted
@@ -47,26 +51,46 @@ static DEFINE_PER_CPU(struct led_trigger_cpu, cpu_trig);
 void ledtrig_cpu(enum cpu_led_event ledevt)
 {
 	struct led_trigger_cpu *trig = this_cpu_ptr(&cpu_trig);
+	bool is_active = trig->is_active;
 
 	/* Locate the correct CPU LED */
 	switch (ledevt) {
 	case CPU_LED_IDLE_END:
 	case CPU_LED_START:
 		/* Will turn the LED on, max brightness */
-		led_trigger_event(trig->_trig, LED_FULL);
+		is_active = true;
 		break;
 
 	case CPU_LED_IDLE_START:
 	case CPU_LED_STOP:
 	case CPU_LED_HALTED:
 		/* Will turn the LED off */
-		led_trigger_event(trig->_trig, LED_OFF);
+		is_active = false;
 		break;
 
 	default:
 		/* Will leave the LED as it is */
 		break;
 	}
+
+	if (is_active != trig->is_active) {
+		unsigned int active_cpus;
+		unsigned int total_cpus;
+
+		/* Update trigger state */
+		trig->is_active = is_active;
+		atomic_add(is_active ? 1 : -1, &num_active_cpus);
+		active_cpus = atomic_read(&num_active_cpus);
+		total_cpus = num_present_cpus();
+
+		led_trigger_event(trig->_trig,
+			is_active ? LED_FULL : LED_OFF);
+
+
+		led_trigger_event(trig_cpu_all,
+			DIV_ROUND_UP(LED_FULL * active_cpus, total_cpus));
+
+	}
 }
 EXPORT_SYMBOL(ledtrig_cpu);
 
@@ -113,6 +137,11 @@ static int __init ledtrig_cpu_init(void)
 	BUILD_BUG_ON(CONFIG_NR_CPUS > 9999);
 
 	/*
+	 * Registering a trigger for all CPUs.
+	 */
+	led_trigger_register_simple("cpu", &trig_cpu_all);
+
+	/*
 	 * Registering CPU led trigger for each CPU core here
 	 * ignores CPU hotplug, but after this CPU hotplug works
 	 * fine with this trigger.
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index d71f6323ac00..b4f79b923aea 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -504,7 +504,7 @@ void __init lguest_arch_host_init(void)
 		 * byte, not the size, hence the "-1").
 		 */
 		state->host_gdt_desc.size = GDT_SIZE-1;
-		state->host_gdt_desc.address = (long)get_cpu_gdt_table(i);
+		state->host_gdt_desc.address = (long)get_cpu_gdt_rw(i);
 
 		/*
 		 * All CPUs on the Host use the same Interrupt Descriptor
@@ -554,8 +554,8 @@ void __init lguest_arch_host_init(void)
 		 * The Host needs to be able to use the LGUEST segments on this
 		 * CPU, too, so put them in the Host GDT.
 		 */
-		get_cpu_gdt_table(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT;
-		get_cpu_gdt_table(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT;
+		get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT;
+		get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT;
 	}
 
 	/*
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 052714106b7b..ead61a93cb4e 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -33,4 +33,13 @@ config NVM_RRPC
 	host. The target is implemented using a linear mapping table and
 	cost-based garbage collection. It is optimized for 4K IO sizes.
 
+config NVM_PBLK
+	tristate "Physical Block Device Open-Channel SSD target"
+	---help---
+	Allows an open-channel SSD to be exposed as a block device to the
+	host. The target assumes the device exposes raw flash and must be
+	explicitly managed by the host.
+
+	Please note the disk format is considered EXPERIMENTAL for now.
+
 endif # NVM
diff --git a/drivers/lightnvm/Makefile b/drivers/lightnvm/Makefile
index b2a39e2d2895..82d1a117fb27 100644
--- a/drivers/lightnvm/Makefile
+++ b/drivers/lightnvm/Makefile
@@ -4,3 +4,8 @@
 
 obj-$(CONFIG_NVM)		:= core.o
 obj-$(CONFIG_NVM_RRPC)		+= rrpc.o
+obj-$(CONFIG_NVM_PBLK)		+= pblk.o
+pblk-y				:= pblk-init.o pblk-core.o pblk-rb.o \
+				   pblk-write.o pblk-cache.o pblk-read.o \
+				   pblk-gc.o pblk-recovery.o pblk-map.o \
+				   pblk-rl.o pblk-sysfs.o
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 5262ba66a7a7..54a06c3a2b8c 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -89,7 +89,7 @@ static void nvm_release_luns_err(struct nvm_dev *dev, int lun_begin,
 		WARN_ON(!test_and_clear_bit(i, dev->lun_map));
 }
 
-static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
+static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev, int clear)
 {
 	struct nvm_dev *dev = tgt_dev->parent;
 	struct nvm_dev_map *dev_map = tgt_dev->map;
@@ -100,11 +100,14 @@ static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
 		int *lun_offs = ch_map->lun_offs;
 		int ch = i + ch_map->ch_off;
 
-		for (j = 0; j < ch_map->nr_luns; j++) {
-			int lun = j + lun_offs[j];
-			int lunid = (ch * dev->geo.luns_per_chnl) + lun;
+		if (clear) {
+			for (j = 0; j < ch_map->nr_luns; j++) {
+				int lun = j + lun_offs[j];
+				int lunid = (ch * dev->geo.luns_per_chnl) + lun;
 
-			WARN_ON(!test_and_clear_bit(lunid, dev->lun_map));
+				WARN_ON(!test_and_clear_bit(lunid,
+							dev->lun_map));
+			}
 		}
 
 		kfree(ch_map->lun_offs);
@@ -232,6 +235,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 	struct nvm_target *t;
 	struct nvm_tgt_dev *tgt_dev;
 	void *targetdata;
+	int ret;
 
 	tt = nvm_find_target_type(create->tgttype, 1);
 	if (!tt) {
@@ -252,34 +256,43 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 		return -ENOMEM;
 
 	t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
-	if (!t)
+	if (!t) {
+		ret = -ENOMEM;
 		goto err_reserve;
+	}
 
 	tgt_dev = nvm_create_tgt_dev(dev, s->lun_begin, s->lun_end);
 	if (!tgt_dev) {
 		pr_err("nvm: could not create target device\n");
+		ret = -ENOMEM;
 		goto err_t;
 	}
 
-	tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
-	if (!tqueue)
+	tdisk = alloc_disk(0);
+	if (!tdisk) {
+		ret = -ENOMEM;
 		goto err_dev;
-	blk_queue_make_request(tqueue, tt->make_rq);
+	}
 
-	tdisk = alloc_disk(0);
-	if (!tdisk)
-		goto err_queue;
+	tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
+	if (!tqueue) {
+		ret = -ENOMEM;
+		goto err_disk;
+	}
+	blk_queue_make_request(tqueue, tt->make_rq);
 
-	sprintf(tdisk->disk_name, "%s", create->tgtname);
+	strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name));
 	tdisk->flags = GENHD_FL_EXT_DEVT;
 	tdisk->major = 0;
 	tdisk->first_minor = 0;
 	tdisk->fops = &nvm_fops;
 	tdisk->queue = tqueue;
 
-	targetdata = tt->init(tgt_dev, tdisk);
-	if (IS_ERR(targetdata))
+	targetdata = tt->init(tgt_dev, tdisk, create->flags);
+	if (IS_ERR(targetdata)) {
+		ret = PTR_ERR(targetdata);
 		goto err_init;
+	}
 
 	tdisk->private_data = targetdata;
 	tqueue->queuedata = targetdata;
@@ -289,8 +302,10 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 	set_capacity(tdisk, tt->capacity(targetdata));
 	add_disk(tdisk);
 
-	if (tt->sysfs_init && tt->sysfs_init(tdisk))
+	if (tt->sysfs_init && tt->sysfs_init(tdisk)) {
+		ret = -ENOMEM;
 		goto err_sysfs;
+	}
 
 	t->type = tt;
 	t->disk = tdisk;
@@ -305,16 +320,17 @@ err_sysfs:
 	if (tt->exit)
 		tt->exit(targetdata);
 err_init:
-	put_disk(tdisk);
-err_queue:
 	blk_cleanup_queue(tqueue);
+	tdisk->queue = NULL;
+err_disk:
+	put_disk(tdisk);
 err_dev:
-	nvm_remove_tgt_dev(tgt_dev);
+	nvm_remove_tgt_dev(tgt_dev, 0);
 err_t:
 	kfree(t);
 err_reserve:
 	nvm_release_luns_err(dev, s->lun_begin, s->lun_end);
-	return -ENOMEM;
+	return ret;
 }
 
 static void __nvm_remove_target(struct nvm_target *t)
@@ -332,7 +348,7 @@ static void __nvm_remove_target(struct nvm_target *t)
 	if (tt->exit)
 		tt->exit(tdisk->private_data);
 
-	nvm_remove_tgt_dev(t->dev);
+	nvm_remove_tgt_dev(t->dev, 1);
 	put_disk(tdisk);
 
 	list_del(&t->list);
@@ -411,6 +427,18 @@ err_rmap:
 	return -ENOMEM;
 }
 
+static void nvm_unregister_map(struct nvm_dev *dev)
+{
+	struct nvm_dev_map *rmap = dev->rmap;
+	int i;
+
+	for (i = 0; i < dev->geo.nr_chnls; i++)
+		kfree(rmap->chnls[i].lun_offs);
+
+	kfree(rmap->chnls);
+	kfree(rmap);
+}
+
 static void nvm_map_to_dev(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
 {
 	struct nvm_dev_map *dev_map = tgt_dev->map;
@@ -486,7 +514,6 @@ void nvm_part_to_tgt(struct nvm_dev *dev, sector_t *entries,
 		int *lun_roffs;
 		struct ppa_addr gaddr;
 		u64 pba = le64_to_cpu(entries[i]);
-		int off;
 		u64 diff;
 
 		if (!pba)
@@ -496,8 +523,6 @@ void nvm_part_to_tgt(struct nvm_dev *dev, sector_t *entries,
 		ch_rmap = &dev_rmap->chnls[gaddr.g.ch];
 		lun_roffs = ch_rmap->lun_offs;
 
-		off = gaddr.g.ch * geo->luns_per_chnl + gaddr.g.lun;
-
 		diff = ((ch_rmap->ch_off * geo->luns_per_chnl) +
 				(lun_roffs[gaddr.g.lun])) * geo->sec_per_lun;
 
@@ -590,11 +615,11 @@ int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
 
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
-	nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
+	nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1);
 	nvm_rq_tgt_to_dev(tgt_dev, &rqd);
 
 	ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type);
-	nvm_free_rqd_ppalist(dev, &rqd);
+	nvm_free_rqd_ppalist(tgt_dev, &rqd);
 	if (ret) {
 		pr_err("nvm: failed bb mark\n");
 		return -EINVAL;
@@ -626,34 +651,45 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
 }
 EXPORT_SYMBOL(nvm_submit_io);
 
-int nvm_erase_blk(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, int flags)
+static void nvm_end_io_sync(struct nvm_rq *rqd)
 {
-	struct nvm_dev *dev = tgt_dev->parent;
-	struct nvm_rq rqd;
-	int ret;
+	struct completion *waiting = rqd->private;
 
-	if (!dev->ops->erase_block)
-		return 0;
+	complete(waiting);
+}
 
-	nvm_map_to_dev(tgt_dev, ppas);
+int nvm_erase_sync(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
+								int nr_ppas)
+{
+	struct nvm_geo *geo = &tgt_dev->geo;
+	struct nvm_rq rqd;
+	int ret;
+	DECLARE_COMPLETION_ONSTACK(wait);
 
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
-	ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, 1, 1);
+	rqd.opcode = NVM_OP_ERASE;
+	rqd.end_io = nvm_end_io_sync;
+	rqd.private = &wait;
+	rqd.flags = geo->plane_mode >> 1;
+
+	ret = nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1);
 	if (ret)
 		return ret;
 
-	nvm_rq_tgt_to_dev(tgt_dev, &rqd);
-
-	rqd.flags = flags;
-
-	ret = dev->ops->erase_block(dev, &rqd);
+	ret = nvm_submit_io(tgt_dev, &rqd);
+	if (ret) {
+		pr_err("rrpr: erase I/O submission failed: %d\n", ret);
+		goto free_ppa_list;
+	}
+	wait_for_completion_io(&wait);
 
-	nvm_free_rqd_ppalist(dev, &rqd);
+free_ppa_list:
+	nvm_free_rqd_ppalist(tgt_dev, &rqd);
 
 	return ret;
 }
-EXPORT_SYMBOL(nvm_erase_blk);
+EXPORT_SYMBOL(nvm_erase_sync);
 
 int nvm_get_l2p_tbl(struct nvm_tgt_dev *tgt_dev, u64 slba, u32 nlb,
 		    nvm_l2p_update_fn *update_l2p, void *priv)
@@ -732,10 +768,11 @@ void nvm_put_area(struct nvm_tgt_dev *tgt_dev, sector_t begin)
 }
 EXPORT_SYMBOL(nvm_put_area);
 
-int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
+int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd,
 			const struct ppa_addr *ppas, int nr_ppas, int vblk)
 {
-	struct nvm_geo *geo = &dev->geo;
+	struct nvm_dev *dev = tgt_dev->parent;
+	struct nvm_geo *geo = &tgt_dev->geo;
 	int i, plane_cnt, pl_idx;
 	struct ppa_addr ppa;
 
@@ -773,12 +810,12 @@ int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
 }
 EXPORT_SYMBOL(nvm_set_rqd_ppalist);
 
-void nvm_free_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd)
+void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
 {
 	if (!rqd->ppa_list)
 		return;
 
-	nvm_dev_dma_free(dev, rqd->ppa_list, rqd->dma_ppa_list);
+	nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
 }
 EXPORT_SYMBOL(nvm_free_rqd_ppalist);
 
@@ -972,7 +1009,7 @@ err_fmtype:
 	return ret;
 }
 
-void nvm_free(struct nvm_dev *dev)
+static void nvm_free(struct nvm_dev *dev)
 {
 	if (!dev)
 		return;
@@ -980,7 +1017,7 @@ void nvm_free(struct nvm_dev *dev)
 	if (dev->dma_pool)
 		dev->ops->destroy_dma_pool(dev->dma_pool);
 
-	kfree(dev->rmap);
+	nvm_unregister_map(dev);
 	kfree(dev->lptbl);
 	kfree(dev->lun_map);
 	kfree(dev);
@@ -1174,13 +1211,13 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
 	list_for_each_entry(dev, &nvm_devices, devices) {
 		struct nvm_ioctl_device_info *info = &devices->info[i];
 
-		sprintf(info->devname, "%s", dev->name);
+		strlcpy(info->devname, dev->name, sizeof(info->devname));
 
 		/* kept for compatibility */
 		info->bmversion[0] = 1;
 		info->bmversion[1] = 0;
 		info->bmversion[2] = 0;
-		sprintf(info->bmname, "%s", "gennvm");
+		strlcpy(info->bmname, "gennvm", sizeof(info->bmname));
 		i++;
 
 		if (i > 31) {
@@ -1217,8 +1254,16 @@ static long nvm_ioctl_dev_create(struct file *file, void __user *arg)
 	create.tgtname[DISK_NAME_LEN - 1] = '\0';
 
 	if (create.flags != 0) {
-		pr_err("nvm: no flags supported\n");
-		return -EINVAL;
+		__u32 flags = create.flags;
+
+		/* Check for valid flags */
+		if (flags & NVM_TARGET_FACTORY)
+			flags &= ~NVM_TARGET_FACTORY;
+
+		if (flags) {
+			pr_err("nvm: flag not supported\n");
+			return -EINVAL;
+		}
 	}
 
 	return __nvm_configure_create(&create);
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
new file mode 100644
index 000000000000..59bcea88db84
--- /dev/null
+++ b/drivers/lightnvm/pblk-cache.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-cache.c - pblk's write cache
+ */
+
+#include "pblk.h"
+
+int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
+{
+	struct pblk_w_ctx w_ctx;
+	sector_t lba = pblk_get_lba(bio);
+	unsigned int bpos, pos;
+	int nr_entries = pblk_get_secs(bio);
+	int i, ret;
+
+	/* Update the write buffer head (mem) with the entries that we can
+	 * write. The write in itself cannot fail, so there is no need to
+	 * rollback from here on.
+	 */
+retry:
+	ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos);
+	if (ret == NVM_IO_REQUEUE) {
+		io_schedule();
+		goto retry;
+	}
+
+	if (unlikely(!bio_has_data(bio)))
+		goto out;
+
+	w_ctx.flags = flags;
+	pblk_ppa_set_empty(&w_ctx.ppa);
+
+	for (i = 0; i < nr_entries; i++) {
+		void *data = bio_data(bio);
+
+		w_ctx.lba = lba + i;
+
+		pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + i);
+		pblk_rb_write_entry_user(&pblk->rwb, data, w_ctx, pos);
+
+		bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(nr_entries, &pblk->inflight_writes);
+	atomic_long_add(nr_entries, &pblk->req_writes);
+#endif
+
+out:
+	pblk_write_should_kick(pblk);
+	return ret;
+}
+
+/*
+ * On GC the incoming lbas are not necessarily sequential. Also, some of the
+ * lbas might not be valid entries, which are marked as empty by the GC thread
+ */
+int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list,
+			   unsigned int nr_entries, unsigned int nr_rec_entries,
+			   struct pblk_line *gc_line, unsigned long flags)
+{
+	struct pblk_w_ctx w_ctx;
+	unsigned int bpos, pos;
+	int i, valid_entries;
+
+	/* Update the write buffer head (mem) with the entries that we can
+	 * write. The write in itself cannot fail, so there is no need to
+	 * rollback from here on.
+	 */
+retry:
+	if (!pblk_rb_may_write_gc(&pblk->rwb, nr_rec_entries, &bpos)) {
+		io_schedule();
+		goto retry;
+	}
+
+	w_ctx.flags = flags;
+	pblk_ppa_set_empty(&w_ctx.ppa);
+
+	for (i = 0, valid_entries = 0; i < nr_entries; i++) {
+		if (lba_list[i] == ADDR_EMPTY)
+			continue;
+
+		w_ctx.lba = lba_list[i];
+
+		pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + valid_entries);
+		pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_line, pos);
+
+		data += PBLK_EXPOSED_PAGE_SIZE;
+		valid_entries++;
+	}
+
+	WARN_ONCE(nr_rec_entries != valid_entries,
+					"pblk: inconsistent GC write\n");
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(valid_entries, &pblk->inflight_writes);
+	atomic_long_add(valid_entries, &pblk->recov_gc_writes);
+#endif
+
+	pblk_write_should_kick(pblk);
+	return NVM_IO_OK;
+}
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
new file mode 100644
index 000000000000..5e44768ccffa
--- /dev/null
+++ b/drivers/lightnvm/pblk-core.c
@@ -0,0 +1,1667 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-core.c - pblk's core functionality
+ *
+ */
+
+#include "pblk.h"
+#include <linux/time.h>
+
+static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
+			 struct ppa_addr *ppa)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	int pos = pblk_dev_ppa_to_pos(geo, *ppa);
+
+	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+	atomic_long_inc(&pblk->erase_failed);
+
+	atomic_dec(&line->blk_in_line);
+	if (test_and_set_bit(pos, line->blk_bitmap))
+		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+							line->id, pos);
+
+	pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb);
+}
+
+static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	struct pblk_line *line;
+
+	line = &pblk->lines[pblk_dev_ppa_to_line(rqd->ppa_addr)];
+	atomic_dec(&line->left_seblks);
+
+	if (rqd->error) {
+		struct ppa_addr *ppa;
+
+		ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC);
+		if (!ppa)
+			return;
+
+		*ppa = rqd->ppa_addr;
+		pblk_mark_bb(pblk, line, ppa);
+	}
+}
+
+/* Erase completion assumes that only one block is erased at the time */
+static void pblk_end_io_erase(struct nvm_rq *rqd)
+{
+	struct pblk *pblk = rqd->private;
+
+	up(&pblk->erase_sem);
+	__pblk_end_io_erase(pblk, rqd);
+	mempool_free(rqd, pblk->r_rq_pool);
+}
+
+static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
+				  u64 paddr)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct list_head *move_list = NULL;
+
+	/* Lines being reclaimed (GC'ed) cannot be invalidated. Before the L2P
+	 * table is modified with reclaimed sectors, a check is done to endure
+	 * that newer updates are not overwritten.
+	 */
+	spin_lock(&line->lock);
+	if (line->state == PBLK_LINESTATE_GC ||
+					line->state == PBLK_LINESTATE_FREE) {
+		spin_unlock(&line->lock);
+		return;
+	}
+
+	if (test_and_set_bit(paddr, line->invalid_bitmap)) {
+		WARN_ONCE(1, "pblk: double invalidate\n");
+		spin_unlock(&line->lock);
+		return;
+	}
+	line->vsc--;
+
+	if (line->state == PBLK_LINESTATE_CLOSED)
+		move_list = pblk_line_gc_list(pblk, line);
+	spin_unlock(&line->lock);
+
+	if (move_list) {
+		spin_lock(&l_mg->gc_lock);
+		spin_lock(&line->lock);
+		/* Prevent moving a line that has just been chosen for GC */
+		if (line->state == PBLK_LINESTATE_GC ||
+					line->state == PBLK_LINESTATE_FREE) {
+			spin_unlock(&line->lock);
+			spin_unlock(&l_mg->gc_lock);
+			return;
+		}
+		spin_unlock(&line->lock);
+
+		list_move_tail(&line->list, move_list);
+		spin_unlock(&l_mg->gc_lock);
+	}
+}
+
+void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
+{
+	struct pblk_line *line;
+	u64 paddr;
+	int line_id;
+
+#ifdef CONFIG_NVM_DEBUG
+	/* Callers must ensure that the ppa points to a device address */
+	BUG_ON(pblk_addr_in_cache(ppa));
+	BUG_ON(pblk_ppa_empty(ppa));
+#endif
+
+	line_id = pblk_tgt_ppa_to_line(ppa);
+	line = &pblk->lines[line_id];
+	paddr = pblk_dev_ppa_to_line_addr(pblk, ppa);
+
+	__pblk_map_invalidate(pblk, line, paddr);
+}
+
+void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
+			     u64 paddr)
+{
+	__pblk_map_invalidate(pblk, line, paddr);
+
+	pblk_rb_sync_init(&pblk->rwb, NULL);
+	line->left_ssecs--;
+	if (!line->left_ssecs)
+		pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
+	pblk_rb_sync_end(&pblk->rwb, NULL);
+}
+
+static void pblk_invalidate_range(struct pblk *pblk, sector_t slba,
+				  unsigned int nr_secs)
+{
+	sector_t lba;
+
+	spin_lock(&pblk->trans_lock);
+	for (lba = slba; lba < slba + nr_secs; lba++) {
+		struct ppa_addr ppa;
+
+		ppa = pblk_trans_map_get(pblk, lba);
+
+		if (!pblk_addr_in_cache(ppa) && !pblk_ppa_empty(ppa))
+			pblk_map_invalidate(pblk, ppa);
+
+		pblk_ppa_set_empty(&ppa);
+		pblk_trans_map_set(pblk, lba, ppa);
+	}
+	spin_unlock(&pblk->trans_lock);
+}
+
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
+{
+	mempool_t *pool;
+	struct nvm_rq *rqd;
+	int rq_size;
+
+	if (rw == WRITE) {
+		pool = pblk->w_rq_pool;
+		rq_size = pblk_w_rq_size;
+	} else {
+		pool = pblk->r_rq_pool;
+		rq_size = pblk_r_rq_size;
+	}
+
+	rqd = mempool_alloc(pool, GFP_KERNEL);
+	memset(rqd, 0, rq_size);
+
+	return rqd;
+}
+
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
+{
+	mempool_t *pool;
+
+	if (rw == WRITE)
+		pool = pblk->w_rq_pool;
+	else
+		pool = pblk->r_rq_pool;
+
+	mempool_free(rqd, pool);
+}
+
+void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
+			 int nr_pages)
+{
+	struct bio_vec bv;
+	int i;
+
+	WARN_ON(off + nr_pages != bio->bi_vcnt);
+
+	bio_advance(bio, off * PBLK_EXPOSED_PAGE_SIZE);
+	for (i = off; i < nr_pages + off; i++) {
+		bv = bio->bi_io_vec[i];
+		mempool_free(bv.bv_page, pblk->page_pool);
+	}
+}
+
+int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
+		       int nr_pages)
+{
+	struct request_queue *q = pblk->dev->q;
+	struct page *page;
+	int i, ret;
+
+	for (i = 0; i < nr_pages; i++) {
+		page = mempool_alloc(pblk->page_pool, flags);
+		if (!page)
+			goto err;
+
+		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
+		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
+			pr_err("pblk: could not add page to bio\n");
+			mempool_free(page, pblk->page_pool);
+			goto err;
+		}
+	}
+
+	return 0;
+err:
+	pblk_bio_free_pages(pblk, bio, 0, i - 1);
+	return -1;
+}
+
+static void pblk_write_kick(struct pblk *pblk)
+{
+	wake_up_process(pblk->writer_ts);
+	mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
+}
+
+void pblk_write_timer_fn(unsigned long data)
+{
+	struct pblk *pblk = (struct pblk *)data;
+
+	/* kick the write thread every tick to flush outstanding data */
+	pblk_write_kick(pblk);
+}
+
+void pblk_write_should_kick(struct pblk *pblk)
+{
+	unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb);
+
+	if (secs_avail >= pblk->min_write_pgs)
+		pblk_write_kick(pblk);
+}
+
+void pblk_end_bio_sync(struct bio *bio)
+{
+	struct completion *waiting = bio->bi_private;
+
+	complete(waiting);
+}
+
+void pblk_end_io_sync(struct nvm_rq *rqd)
+{
+	struct completion *waiting = rqd->private;
+
+	complete(waiting);
+}
+
+void pblk_flush_writer(struct pblk *pblk)
+{
+	struct bio *bio;
+	int ret;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	bio = bio_alloc(GFP_KERNEL, 1);
+	if (!bio)
+		return;
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_OP_FLUSH);
+	bio->bi_private = &wait;
+	bio->bi_end_io = pblk_end_bio_sync;
+
+	ret = pblk_write_to_cache(pblk, bio, 0);
+	if (ret == NVM_IO_OK) {
+		if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+			pr_err("pblk: flush cache timed out\n");
+		}
+	} else if (ret != NVM_IO_DONE) {
+		pr_err("pblk: tear down bio failed\n");
+	}
+
+	if (bio->bi_error)
+		pr_err("pblk: flush sync write failed (%u)\n", bio->bi_error);
+
+	bio_put(bio);
+}
+
+struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct list_head *move_list = NULL;
+
+	if (!line->vsc) {
+		if (line->gc_group != PBLK_LINEGC_FULL) {
+			line->gc_group = PBLK_LINEGC_FULL;
+			move_list = &l_mg->gc_full_list;
+		}
+	} else if (line->vsc < lm->mid_thrs) {
+		if (line->gc_group != PBLK_LINEGC_HIGH) {
+			line->gc_group = PBLK_LINEGC_HIGH;
+			move_list = &l_mg->gc_high_list;
+		}
+	} else if (line->vsc < lm->high_thrs) {
+		if (line->gc_group != PBLK_LINEGC_MID) {
+			line->gc_group = PBLK_LINEGC_MID;
+			move_list = &l_mg->gc_mid_list;
+		}
+	} else if (line->vsc < line->sec_in_line) {
+		if (line->gc_group != PBLK_LINEGC_LOW) {
+			line->gc_group = PBLK_LINEGC_LOW;
+			move_list = &l_mg->gc_low_list;
+		}
+	} else if (line->vsc == line->sec_in_line) {
+		if (line->gc_group != PBLK_LINEGC_EMPTY) {
+			line->gc_group = PBLK_LINEGC_EMPTY;
+			move_list = &l_mg->gc_empty_list;
+		}
+	} else {
+		line->state = PBLK_LINESTATE_CORRUPT;
+		line->gc_group = PBLK_LINEGC_NONE;
+		move_list =  &l_mg->corrupt_list;
+		pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+						line->id, line->vsc,
+						line->sec_in_line,
+						lm->high_thrs, lm->mid_thrs);
+	}
+
+	return move_list;
+}
+
+void pblk_discard(struct pblk *pblk, struct bio *bio)
+{
+	sector_t slba = pblk_get_lba(bio);
+	sector_t nr_secs = pblk_get_secs(bio);
+
+	pblk_invalidate_range(pblk, slba, nr_secs);
+}
+
+struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba)
+{
+	struct ppa_addr ppa;
+
+	spin_lock(&pblk->trans_lock);
+	ppa = pblk_trans_map_get(pblk, lba);
+	spin_unlock(&pblk->trans_lock);
+
+	return ppa;
+}
+
+void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	atomic_long_inc(&pblk->write_failed);
+#ifdef CONFIG_NVM_DEBUG
+	pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+}
+
+void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	/* Empty page read is not necessarily an error (e.g., L2P recovery) */
+	if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
+		atomic_long_inc(&pblk->read_empty);
+		return;
+	}
+
+	switch (rqd->error) {
+	case NVM_RSP_WARN_HIGHECC:
+		atomic_long_inc(&pblk->read_high_ecc);
+		break;
+	case NVM_RSP_ERR_FAILECC:
+	case NVM_RSP_ERR_FAILCRC:
+		atomic_long_inc(&pblk->read_failed);
+		break;
+	default:
+		pr_err("pblk: unknown read error:%d\n", rqd->error);
+	}
+#ifdef CONFIG_NVM_DEBUG
+	pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+}
+
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+
+#ifdef CONFIG_NVM_DEBUG
+	struct ppa_addr *ppa_list;
+
+	ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr;
+	if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (rqd->opcode == NVM_OP_PWRITE) {
+		struct pblk_line *line;
+		struct ppa_addr ppa;
+		int i;
+
+		for (i = 0; i < rqd->nr_ppas; i++) {
+			ppa = ppa_list[i];
+			line = &pblk->lines[pblk_dev_ppa_to_line(ppa)];
+
+			spin_lock(&line->lock);
+			if (line->state != PBLK_LINESTATE_OPEN) {
+				pr_err("pblk: bad ppa: line:%d,state:%d\n",
+							line->id, line->state);
+				WARN_ON(1);
+				spin_unlock(&line->lock);
+				return -EINVAL;
+			}
+			spin_unlock(&line->lock);
+		}
+	}
+#endif
+	return nvm_submit_io(dev, rqd);
+}
+
+struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
+			      unsigned int nr_secs, unsigned int len,
+			      gfp_t gfp_mask)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	void *kaddr = data;
+	struct page *page;
+	struct bio *bio;
+	int i, ret;
+
+	if (l_mg->emeta_alloc_type == PBLK_KMALLOC_META)
+		return bio_map_kern(dev->q, kaddr, len, gfp_mask);
+
+	bio = bio_kmalloc(gfp_mask, nr_secs);
+	if (!bio)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < nr_secs; i++) {
+		page = vmalloc_to_page(kaddr);
+		if (!page) {
+			pr_err("pblk: could not map vmalloc bio\n");
+			bio_put(bio);
+			bio = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
+		if (ret != PAGE_SIZE) {
+			pr_err("pblk: could not add page to bio\n");
+			bio_put(bio);
+			bio = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		kaddr += PAGE_SIZE;
+	}
+out:
+	return bio;
+}
+
+int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
+		   unsigned long secs_to_flush)
+{
+	int max = pblk->max_write_pgs;
+	int min = pblk->min_write_pgs;
+	int secs_to_sync = 0;
+
+	if (secs_avail >= max)
+		secs_to_sync = max;
+	else if (secs_avail >= min)
+		secs_to_sync = min * (secs_avail / min);
+	else if (secs_to_flush)
+		secs_to_sync = min;
+
+	return secs_to_sync;
+}
+
+static u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line,
+			     int nr_secs)
+{
+	u64 addr;
+	int i;
+
+	/* logic error: ppa out-of-bounds. Prevent generating bad address */
+	if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) {
+		WARN(1, "pblk: page allocation out of bounds\n");
+		nr_secs = pblk->lm.sec_per_line - line->cur_sec;
+	}
+
+	line->cur_sec = addr = find_next_zero_bit(line->map_bitmap,
+					pblk->lm.sec_per_line, line->cur_sec);
+	for (i = 0; i < nr_secs; i++, line->cur_sec++)
+		WARN_ON(test_and_set_bit(line->cur_sec, line->map_bitmap));
+
+	return addr;
+}
+
+u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
+{
+	u64 addr;
+
+	/* Lock needed in case a write fails and a recovery needs to remap
+	 * failed write buffer entries
+	 */
+	spin_lock(&line->lock);
+	addr = __pblk_alloc_page(pblk, line, nr_secs);
+	line->left_msecs -= nr_secs;
+	WARN(line->left_msecs < 0, "pblk: page allocation out of bounds\n");
+	spin_unlock(&line->lock);
+
+	return addr;
+}
+
+/*
+ * Submit emeta to one LUN in the raid line at the time to avoid a deadlock when
+ * taking the per LUN semaphore.
+ */
+static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
+				     u64 paddr, int dir)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct bio *bio;
+	struct nvm_rq rqd;
+	struct ppa_addr *ppa_list;
+	dma_addr_t dma_ppa_list;
+	void *emeta = line->emeta;
+	int min = pblk->min_write_pgs;
+	int left_ppas = lm->emeta_sec;
+	int id = line->id;
+	int rq_ppas, rq_len;
+	int cmd_op, bio_op;
+	int flags;
+	int i, j;
+	int ret;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	if (dir == WRITE) {
+		bio_op = REQ_OP_WRITE;
+		cmd_op = NVM_OP_PWRITE;
+		flags = pblk_set_progr_mode(pblk, WRITE);
+	} else if (dir == READ) {
+		bio_op = REQ_OP_READ;
+		cmd_op = NVM_OP_PREAD;
+		flags = pblk_set_read_mode(pblk);
+	} else
+		return -EINVAL;
+
+	ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_ppa_list);
+	if (!ppa_list)
+		return -ENOMEM;
+
+next_rq:
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	rq_len = rq_ppas * geo->sec_size;
+
+	bio = pblk_bio_map_addr(pblk, emeta, rq_ppas, rq_len, GFP_KERNEL);
+	if (IS_ERR(bio)) {
+		ret = PTR_ERR(bio);
+		goto free_rqd_dma;
+	}
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, bio_op, 0);
+
+	rqd.bio = bio;
+	rqd.opcode = cmd_op;
+	rqd.flags = flags;
+	rqd.nr_ppas = rq_ppas;
+	rqd.ppa_list = ppa_list;
+	rqd.dma_ppa_list = dma_ppa_list;
+	rqd.end_io = pblk_end_io_sync;
+	rqd.private = &wait;
+
+	if (dir == WRITE) {
+		for (i = 0; i < rqd.nr_ppas; ) {
+			spin_lock(&line->lock);
+			paddr = __pblk_alloc_page(pblk, line, min);
+			spin_unlock(&line->lock);
+			for (j = 0; j < min; j++, i++, paddr++)
+				rqd.ppa_list[i] =
+					addr_to_gen_ppa(pblk, paddr, id);
+		}
+	} else {
+		for (i = 0; i < rqd.nr_ppas; ) {
+			struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id);
+			int pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+			while (test_bit(pos, line->blk_bitmap)) {
+				paddr += min;
+				if (pblk_boundary_paddr_checks(pblk, paddr)) {
+					pr_err("pblk: corrupt emeta line:%d\n",
+								line->id);
+					bio_put(bio);
+					ret = -EINTR;
+					goto free_rqd_dma;
+				}
+
+				ppa = addr_to_gen_ppa(pblk, paddr, id);
+				pos = pblk_dev_ppa_to_pos(geo, ppa);
+			}
+
+			if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
+				pr_err("pblk: corrupt emeta line:%d\n",
+								line->id);
+				bio_put(bio);
+				ret = -EINTR;
+				goto free_rqd_dma;
+			}
+
+			for (j = 0; j < min; j++, i++, paddr++)
+				rqd.ppa_list[i] =
+					addr_to_gen_ppa(pblk, paddr, line->id);
+		}
+	}
+
+	ret = pblk_submit_io(pblk, &rqd);
+	if (ret) {
+		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		bio_put(bio);
+		goto free_rqd_dma;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: emeta I/O timed out\n");
+	}
+	reinit_completion(&wait);
+
+	bio_put(bio);
+
+	if (rqd.error) {
+		if (dir == WRITE)
+			pblk_log_write_err(pblk, &rqd);
+		else
+			pblk_log_read_err(pblk, &rqd);
+	}
+
+	emeta += rq_len;
+	left_ppas -= rq_ppas;
+	if (left_ppas)
+		goto next_rq;
+free_rqd_dma:
+	nvm_dev_dma_free(dev->parent, ppa_list, dma_ppa_list);
+	return ret;
+}
+
+u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	int bit;
+
+	/* This usually only happens on bad lines */
+	bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+	if (bit >= lm->blk_per_line)
+		return -1;
+
+	return bit * geo->sec_per_pl;
+}
+
+static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
+				     u64 paddr, int dir)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct bio *bio;
+	struct nvm_rq rqd;
+	__le64 *lba_list = NULL;
+	int i, ret;
+	int cmd_op, bio_op;
+	int flags;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	if (dir == WRITE) {
+		bio_op = REQ_OP_WRITE;
+		cmd_op = NVM_OP_PWRITE;
+		flags = pblk_set_progr_mode(pblk, WRITE);
+		lba_list = pblk_line_emeta_to_lbas(line->emeta);
+	} else if (dir == READ) {
+		bio_op = REQ_OP_READ;
+		cmd_op = NVM_OP_PREAD;
+		flags = pblk_set_read_mode(pblk);
+	} else
+		return -EINVAL;
+
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+
+	rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+							&rqd.dma_ppa_list);
+	if (!rqd.ppa_list)
+		return -ENOMEM;
+
+	bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
+	if (IS_ERR(bio)) {
+		ret = PTR_ERR(bio);
+		goto free_ppa_list;
+	}
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, bio_op, 0);
+
+	rqd.bio = bio;
+	rqd.opcode = cmd_op;
+	rqd.flags = flags;
+	rqd.nr_ppas = lm->smeta_sec;
+	rqd.end_io = pblk_end_io_sync;
+	rqd.private = &wait;
+
+	for (i = 0; i < lm->smeta_sec; i++, paddr++) {
+		rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
+		if (dir == WRITE)
+			lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+	}
+
+	/*
+	 * This I/O is sent by the write thread when a line is replace. Since
+	 * the write thread is the only one sending write and erase commands,
+	 * there is no need to take the LUN semaphore.
+	 */
+	ret = pblk_submit_io(pblk, &rqd);
+	if (ret) {
+		pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+		bio_put(bio);
+		goto free_ppa_list;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: smeta I/O timed out\n");
+	}
+
+	if (rqd.error) {
+		if (dir == WRITE)
+			pblk_log_write_err(pblk, &rqd);
+		else
+			pblk_log_read_err(pblk, &rqd);
+	}
+
+free_ppa_list:
+	nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+
+	return ret;
+}
+
+int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
+{
+	u64 bpaddr = pblk_line_smeta_start(pblk, line);
+
+	return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
+}
+
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line)
+{
+	return pblk_line_submit_emeta_io(pblk, line, line->emeta_ssec, READ);
+}
+
+static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
+			    struct ppa_addr ppa)
+{
+	rqd->opcode = NVM_OP_ERASE;
+	rqd->ppa_addr = ppa;
+	rqd->nr_ppas = 1;
+	rqd->flags = pblk_set_progr_mode(pblk, ERASE);
+	rqd->bio = NULL;
+}
+
+static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
+{
+	struct nvm_rq rqd;
+	int ret;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+
+	pblk_setup_e_rq(pblk, &rqd, ppa);
+
+	rqd.end_io = pblk_end_io_sync;
+	rqd.private = &wait;
+
+	/* The write thread schedules erases so that it minimizes disturbances
+	 * with writes. Thus, there is no need to take the LUN semaphore.
+	 */
+	ret = pblk_submit_io(pblk, &rqd);
+	if (ret) {
+		struct nvm_tgt_dev *dev = pblk->dev;
+		struct nvm_geo *geo = &dev->geo;
+
+		pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+					pblk_dev_ppa_to_line(ppa),
+					pblk_dev_ppa_to_pos(geo, ppa));
+
+		rqd.error = ret;
+		goto out;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: sync erase timed out\n");
+	}
+
+out:
+	rqd.private = pblk;
+	__pblk_end_io_erase(pblk, &rqd);
+
+	return 0;
+}
+
+int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct ppa_addr ppa;
+	int bit = -1;
+
+	/* Erase only good blocks, one at a time */
+	do {
+		spin_lock(&line->lock);
+		bit = find_next_zero_bit(line->erase_bitmap, lm->blk_per_line,
+								bit + 1);
+		if (bit >= lm->blk_per_line) {
+			spin_unlock(&line->lock);
+			break;
+		}
+
+		ppa = pblk->luns[bit].bppa; /* set ch and lun */
+		ppa.g.blk = line->id;
+
+		atomic_dec(&line->left_eblks);
+		WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
+		spin_unlock(&line->lock);
+
+		if (pblk_blk_erase_sync(pblk, ppa)) {
+			pr_err("pblk: failed to erase line %d\n", line->id);
+			return -ENOMEM;
+		}
+	} while (1);
+
+	return 0;
+}
+
+/* For now lines are always assumed full lines. Thus, smeta former and current
+ * lun bitmaps are omitted.
+ */
+static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line,
+				  struct pblk_line *cur)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct line_smeta *smeta = line->smeta;
+	struct line_emeta *emeta = line->emeta;
+	int nr_blk_line;
+
+	/* After erasing the line, new bad blocks might appear and we risk
+	 * having an invalid line
+	 */
+	nr_blk_line = lm->blk_per_line -
+			bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+	if (nr_blk_line < lm->min_blk_line) {
+		spin_lock(&l_mg->free_lock);
+		spin_lock(&line->lock);
+		line->state = PBLK_LINESTATE_BAD;
+		spin_unlock(&line->lock);
+
+		list_add_tail(&line->list, &l_mg->bad_list);
+		spin_unlock(&l_mg->free_lock);
+
+		pr_debug("pblk: line %d is bad\n", line->id);
+
+		return 0;
+	}
+
+	/* Run-time metadata */
+	line->lun_bitmap = ((void *)(smeta)) + sizeof(struct line_smeta);
+
+	/* Mark LUNs allocated in this line (all for now) */
+	bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len);
+
+	smeta->header.identifier = cpu_to_le32(PBLK_MAGIC);
+	memcpy(smeta->header.uuid, pblk->instance_uuid, 16);
+	smeta->header.id = cpu_to_le32(line->id);
+	smeta->header.type = cpu_to_le16(line->type);
+	smeta->header.version = cpu_to_le16(1);
+
+	/* Start metadata */
+	smeta->seq_nr = cpu_to_le64(line->seq_nr);
+	smeta->window_wr_lun = cpu_to_le32(geo->nr_luns);
+
+	/* Fill metadata among lines */
+	if (cur) {
+		memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len);
+		smeta->prev_id = cpu_to_le32(cur->id);
+		cur->emeta->next_id = cpu_to_le32(line->id);
+	} else {
+		smeta->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
+	}
+
+	/* All smeta must be set at this point */
+	smeta->header.crc = cpu_to_le32(pblk_calc_meta_header_crc(pblk, smeta));
+	smeta->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta));
+
+	/* End metadata */
+	memcpy(&emeta->header, &smeta->header, sizeof(struct line_header));
+	emeta->seq_nr = cpu_to_le64(line->seq_nr);
+	emeta->nr_lbas = cpu_to_le64(line->sec_in_line);
+	emeta->nr_valid_lbas = cpu_to_le64(0);
+	emeta->next_id = cpu_to_le32(PBLK_LINE_EMPTY);
+	emeta->crc = cpu_to_le32(0);
+	emeta->prev_id = smeta->prev_id;
+
+	return 1;
+}
+
+/* For now lines are always assumed full lines. Thus, smeta former and current
+ * lun bitmaps are omitted.
+ */
+static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
+			     int init)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	int nr_bb = 0;
+	u64 off;
+	int bit = -1;
+
+	line->sec_in_line = lm->sec_per_line;
+
+	/* Capture bad block information on line mapping bitmaps */
+	while ((bit = find_next_bit(line->blk_bitmap, lm->blk_per_line,
+					bit + 1)) < lm->blk_per_line) {
+		off = bit * geo->sec_per_pl;
+		bitmap_shift_left(l_mg->bb_aux, l_mg->bb_template, off,
+							lm->sec_per_line);
+		bitmap_or(line->map_bitmap, line->map_bitmap, l_mg->bb_aux,
+							lm->sec_per_line);
+		line->sec_in_line -= geo->sec_per_blk;
+		if (bit >= lm->emeta_bb)
+			nr_bb++;
+	}
+
+	/* Mark smeta metadata sectors as bad sectors */
+	bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+	off = bit * geo->sec_per_pl;
+retry_smeta:
+	bitmap_set(line->map_bitmap, off, lm->smeta_sec);
+	line->sec_in_line -= lm->smeta_sec;
+	line->smeta_ssec = off;
+	line->cur_sec = off + lm->smeta_sec;
+
+	if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) {
+		pr_debug("pblk: line smeta I/O failed. Retry\n");
+		off += geo->sec_per_pl;
+		goto retry_smeta;
+	}
+
+	bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
+
+	/* Mark emeta metadata sectors as bad sectors. We need to consider bad
+	 * blocks to make sure that there are enough sectors to store emeta
+	 */
+	bit = lm->sec_per_line;
+	off = lm->sec_per_line - lm->emeta_sec;
+	bitmap_set(line->invalid_bitmap, off, lm->emeta_sec);
+	while (nr_bb) {
+		off -= geo->sec_per_pl;
+		if (!test_bit(off, line->invalid_bitmap)) {
+			bitmap_set(line->invalid_bitmap, off, geo->sec_per_pl);
+			nr_bb--;
+		}
+	}
+
+	line->sec_in_line -= lm->emeta_sec;
+	line->emeta_ssec = off;
+	line->vsc = line->left_ssecs = line->left_msecs = line->sec_in_line;
+
+	if (lm->sec_per_line - line->sec_in_line !=
+		bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) {
+		spin_lock(&line->lock);
+		line->state = PBLK_LINESTATE_BAD;
+		spin_unlock(&line->lock);
+
+		list_add_tail(&line->list, &l_mg->bad_list);
+		pr_err("pblk: unexpected line %d is bad\n", line->id);
+
+		return 0;
+	}
+
+	return 1;
+}
+
+static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	int blk_in_line = atomic_read(&line->blk_in_line);
+
+	line->map_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+	if (!line->map_bitmap)
+		return -ENOMEM;
+	memset(line->map_bitmap, 0, lm->sec_bitmap_len);
+
+	/* invalid_bitmap is special since it is used when line is closed. No
+	 * need to zeroized; it will be initialized using bb info form
+	 * map_bitmap
+	 */
+	line->invalid_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+	if (!line->invalid_bitmap) {
+		mempool_free(line->map_bitmap, pblk->line_meta_pool);
+		return -ENOMEM;
+	}
+
+	spin_lock(&line->lock);
+	if (line->state != PBLK_LINESTATE_FREE) {
+		spin_unlock(&line->lock);
+		WARN(1, "pblk: corrupted line state\n");
+		return -EINTR;
+	}
+	line->state = PBLK_LINESTATE_OPEN;
+
+	atomic_set(&line->left_eblks, blk_in_line);
+	atomic_set(&line->left_seblks, blk_in_line);
+	spin_unlock(&line->lock);
+
+	/* Bad blocks do not need to be erased */
+	bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
+
+	kref_init(&line->ref);
+
+	return 0;
+}
+
+int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	int ret;
+
+	spin_lock(&l_mg->free_lock);
+	l_mg->data_line = line;
+	list_del(&line->list);
+
+	ret = pblk_line_prepare(pblk, line);
+	if (ret) {
+		list_add(&line->list, &l_mg->free_list);
+		spin_unlock(&l_mg->free_lock);
+		return ret;
+	}
+	spin_unlock(&l_mg->free_lock);
+
+	pblk_rl_free_lines_dec(&pblk->rl, line);
+
+	if (!pblk_line_init_bb(pblk, line, 0)) {
+		list_add(&line->list, &l_mg->free_list);
+		return -EINTR;
+	}
+
+	return 0;
+}
+
+void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
+{
+	mempool_free(line->map_bitmap, pblk->line_meta_pool);
+	line->map_bitmap = NULL;
+	line->smeta = NULL;
+	line->emeta = NULL;
+}
+
+struct pblk_line *pblk_line_get(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line *line = NULL;
+	int bit;
+
+	lockdep_assert_held(&l_mg->free_lock);
+
+retry_get:
+	if (list_empty(&l_mg->free_list)) {
+		pr_err("pblk: no free lines\n");
+		goto out;
+	}
+
+	line = list_first_entry(&l_mg->free_list, struct pblk_line, list);
+	list_del(&line->list);
+	l_mg->nr_free_lines--;
+
+	bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+	if (unlikely(bit >= lm->blk_per_line)) {
+		spin_lock(&line->lock);
+		line->state = PBLK_LINESTATE_BAD;
+		spin_unlock(&line->lock);
+
+		list_add_tail(&line->list, &l_mg->bad_list);
+
+		pr_debug("pblk: line %d is bad\n", line->id);
+		goto retry_get;
+	}
+
+	if (pblk_line_prepare(pblk, line)) {
+		pr_err("pblk: failed to prepare line %d\n", line->id);
+		list_add(&line->list, &l_mg->free_list);
+		return NULL;
+	}
+
+out:
+	return line;
+}
+
+static struct pblk_line *pblk_line_retry(struct pblk *pblk,
+					 struct pblk_line *line)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *retry_line;
+
+	spin_lock(&l_mg->free_lock);
+	retry_line = pblk_line_get(pblk);
+	if (!retry_line) {
+		l_mg->data_line = NULL;
+		spin_unlock(&l_mg->free_lock);
+		return NULL;
+	}
+
+	retry_line->smeta = line->smeta;
+	retry_line->emeta = line->emeta;
+	retry_line->meta_line = line->meta_line;
+
+	pblk_line_free(pblk, line);
+	l_mg->data_line = retry_line;
+	spin_unlock(&l_mg->free_lock);
+
+	if (pblk_line_erase(pblk, retry_line)) {
+		spin_lock(&l_mg->free_lock);
+		l_mg->data_line = NULL;
+		spin_unlock(&l_mg->free_lock);
+		return NULL;
+	}
+
+	pblk_rl_free_lines_dec(&pblk->rl, retry_line);
+
+	return retry_line;
+}
+
+struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *line;
+	int meta_line;
+	int is_next = 0;
+
+	spin_lock(&l_mg->free_lock);
+	line = pblk_line_get(pblk);
+	if (!line) {
+		spin_unlock(&l_mg->free_lock);
+		return NULL;
+	}
+
+	line->seq_nr = l_mg->d_seq_nr++;
+	line->type = PBLK_LINETYPE_DATA;
+	l_mg->data_line = line;
+
+	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+	set_bit(meta_line, &l_mg->meta_bitmap);
+	line->smeta = l_mg->sline_meta[meta_line].meta;
+	line->emeta = l_mg->eline_meta[meta_line].meta;
+	line->meta_line = meta_line;
+
+	/* Allocate next line for preparation */
+	l_mg->data_next = pblk_line_get(pblk);
+	if (l_mg->data_next) {
+		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+		l_mg->data_next->type = PBLK_LINETYPE_DATA;
+		is_next = 1;
+	}
+	spin_unlock(&l_mg->free_lock);
+
+	pblk_rl_free_lines_dec(&pblk->rl, line);
+	if (is_next)
+		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+
+	if (pblk_line_erase(pblk, line))
+		return NULL;
+
+retry_setup:
+	if (!pblk_line_set_metadata(pblk, line, NULL)) {
+		line = pblk_line_retry(pblk, line);
+		if (!line)
+			return NULL;
+
+		goto retry_setup;
+	}
+
+	if (!pblk_line_init_bb(pblk, line, 1)) {
+		line = pblk_line_retry(pblk, line);
+		if (!line)
+			return NULL;
+
+		goto retry_setup;
+	}
+
+	return line;
+}
+
+struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *cur, *new;
+	unsigned int left_seblks;
+	int meta_line;
+	int is_next = 0;
+
+	cur = l_mg->data_line;
+	new = l_mg->data_next;
+	if (!new)
+		return NULL;
+	l_mg->data_line = new;
+
+retry_line:
+	left_seblks = atomic_read(&new->left_seblks);
+	if (left_seblks) {
+		/* If line is not fully erased, erase it */
+		if (atomic_read(&new->left_eblks)) {
+			if (pblk_line_erase(pblk, new))
+				return NULL;
+		} else {
+			io_schedule();
+		}
+		goto retry_line;
+	}
+
+	spin_lock(&l_mg->free_lock);
+	/* Allocate next line for preparation */
+	l_mg->data_next = pblk_line_get(pblk);
+	if (l_mg->data_next) {
+		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+		l_mg->data_next->type = PBLK_LINETYPE_DATA;
+		is_next = 1;
+	}
+
+retry_meta:
+	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+	if (meta_line == PBLK_DATA_LINES) {
+		spin_unlock(&l_mg->free_lock);
+		io_schedule();
+		spin_lock(&l_mg->free_lock);
+		goto retry_meta;
+	}
+
+	set_bit(meta_line, &l_mg->meta_bitmap);
+	new->smeta = l_mg->sline_meta[meta_line].meta;
+	new->emeta = l_mg->eline_meta[meta_line].meta;
+	new->meta_line = meta_line;
+
+	memset(new->smeta, 0, lm->smeta_len);
+	memset(new->emeta, 0, lm->emeta_len);
+	spin_unlock(&l_mg->free_lock);
+
+	if (is_next)
+		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+
+retry_setup:
+	if (!pblk_line_set_metadata(pblk, new, cur)) {
+		new = pblk_line_retry(pblk, new);
+		if (!new)
+			return NULL;
+
+		goto retry_setup;
+	}
+
+	if (!pblk_line_init_bb(pblk, new, 1)) {
+		new = pblk_line_retry(pblk, new);
+		if (!new)
+			return NULL;
+
+		goto retry_setup;
+	}
+
+	return new;
+}
+
+void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
+{
+	if (line->map_bitmap)
+		mempool_free(line->map_bitmap, pblk->line_meta_pool);
+	if (line->invalid_bitmap)
+		mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+
+	line->map_bitmap = NULL;
+	line->invalid_bitmap = NULL;
+	line->smeta = NULL;
+	line->emeta = NULL;
+}
+
+void pblk_line_put(struct kref *ref)
+{
+	struct pblk_line *line = container_of(ref, struct pblk_line, ref);
+	struct pblk *pblk = line->pblk;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+
+	spin_lock(&line->lock);
+	WARN_ON(line->state != PBLK_LINESTATE_GC);
+	line->state = PBLK_LINESTATE_FREE;
+	line->gc_group = PBLK_LINEGC_NONE;
+	pblk_line_free(pblk, line);
+	spin_unlock(&line->lock);
+
+	spin_lock(&l_mg->free_lock);
+	list_add_tail(&line->list, &l_mg->free_list);
+	l_mg->nr_free_lines++;
+	spin_unlock(&l_mg->free_lock);
+
+	pblk_rl_free_lines_inc(&pblk->rl, line);
+}
+
+int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
+{
+	struct nvm_rq *rqd;
+	int err;
+
+	rqd = mempool_alloc(pblk->r_rq_pool, GFP_KERNEL);
+	memset(rqd, 0, pblk_r_rq_size);
+
+	pblk_setup_e_rq(pblk, rqd, ppa);
+
+	rqd->end_io = pblk_end_io_erase;
+	rqd->private = pblk;
+
+	/* The write thread schedules erases so that it minimizes disturbances
+	 * with writes. Thus, there is no need to take the LUN semaphore.
+	 */
+	err = pblk_submit_io(pblk, rqd);
+	if (err) {
+		struct nvm_tgt_dev *dev = pblk->dev;
+		struct nvm_geo *geo = &dev->geo;
+
+		pr_err("pblk: could not async erase line:%d,blk:%d\n",
+					pblk_dev_ppa_to_line(ppa),
+					pblk_dev_ppa_to_pos(geo, ppa));
+	}
+
+	return err;
+}
+
+struct pblk_line *pblk_line_get_data(struct pblk *pblk)
+{
+	return pblk->l_mg.data_line;
+}
+
+struct pblk_line *pblk_line_get_data_next(struct pblk *pblk)
+{
+	return pblk->l_mg.data_next;
+}
+
+int pblk_line_is_full(struct pblk_line *line)
+{
+	return (line->left_msecs == 0);
+}
+
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct list_head *move_list;
+
+	line->emeta->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, line->emeta));
+
+	if (pblk_line_submit_emeta_io(pblk, line, line->cur_sec, WRITE))
+		pr_err("pblk: line %d close I/O failed\n", line->id);
+
+	WARN(!bitmap_full(line->map_bitmap, line->sec_in_line),
+				"pblk: corrupt closed line %d\n", line->id);
+
+	spin_lock(&l_mg->free_lock);
+	WARN_ON(!test_and_clear_bit(line->meta_line, &l_mg->meta_bitmap));
+	spin_unlock(&l_mg->free_lock);
+
+	spin_lock(&l_mg->gc_lock);
+	spin_lock(&line->lock);
+	WARN_ON(line->state != PBLK_LINESTATE_OPEN);
+	line->state = PBLK_LINESTATE_CLOSED;
+	move_list = pblk_line_gc_list(pblk, line);
+
+	list_add_tail(&line->list, move_list);
+
+	mempool_free(line->map_bitmap, pblk->line_meta_pool);
+	line->map_bitmap = NULL;
+	line->smeta = NULL;
+	line->emeta = NULL;
+
+	spin_unlock(&line->lock);
+	spin_unlock(&l_mg->gc_lock);
+}
+
+void pblk_line_close_ws(struct work_struct *work)
+{
+	struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+									ws);
+	struct pblk *pblk = line_ws->pblk;
+	struct pblk_line *line = line_ws->line;
+
+	pblk_line_close(pblk, line);
+	mempool_free(line_ws, pblk->line_ws_pool);
+}
+
+void pblk_line_mark_bb(struct work_struct *work)
+{
+	struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+									ws);
+	struct pblk *pblk = line_ws->pblk;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct ppa_addr *ppa = line_ws->priv;
+	int ret;
+
+	ret = nvm_set_tgt_bb_tbl(dev, ppa, 1, NVM_BLK_T_GRWN_BAD);
+	if (ret) {
+		struct pblk_line *line;
+		int pos;
+
+		line = &pblk->lines[pblk_dev_ppa_to_line(*ppa)];
+		pos = pblk_dev_ppa_to_pos(&dev->geo, *ppa);
+
+		pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+				line->id, pos);
+	}
+
+	kfree(ppa);
+	mempool_free(line_ws, pblk->line_ws_pool);
+}
+
+void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+		      void (*work)(struct work_struct *))
+{
+	struct pblk_line_ws *line_ws;
+
+	line_ws = mempool_alloc(pblk->line_ws_pool, GFP_ATOMIC);
+	if (!line_ws)
+		return;
+
+	line_ws->pblk = pblk;
+	line_ws->line = line;
+	line_ws->priv = priv;
+
+	INIT_WORK(&line_ws->ws, work);
+	queue_work(pblk->kw_wq, &line_ws->ws);
+}
+
+void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+		  unsigned long *lun_bitmap)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_lun *rlun;
+	int lun_id = ppa_list[0].g.ch * geo->luns_per_chnl + ppa_list[0].g.lun;
+	int ret;
+
+	/*
+	 * Only send one inflight I/O per LUN. Since we map at a page
+	 * granurality, all ppas in the I/O will map to the same LUN
+	 */
+#ifdef CONFIG_NVM_DEBUG
+	int i;
+
+	for (i = 1; i < nr_ppas; i++)
+		WARN_ON(ppa_list[0].g.lun != ppa_list[i].g.lun ||
+				ppa_list[0].g.ch != ppa_list[i].g.ch);
+#endif
+	/* If the LUN has been locked for this same request, do no attempt to
+	 * lock it again
+	 */
+	if (test_and_set_bit(lun_id, lun_bitmap))
+		return;
+
+	rlun = &pblk->luns[lun_id];
+	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
+	if (ret) {
+		switch (ret) {
+		case -ETIME:
+			pr_err("pblk: lun semaphore timed out\n");
+			break;
+		case -EINTR:
+			pr_err("pblk: lun semaphore timed out\n");
+			break;
+		}
+	}
+}
+
+void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+		unsigned long *lun_bitmap)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_lun *rlun;
+	int nr_luns = geo->nr_luns;
+	int bit = -1;
+
+	while ((bit = find_next_bit(lun_bitmap, nr_luns, bit + 1)) < nr_luns) {
+		rlun = &pblk->luns[bit];
+		up(&rlun->wr_sem);
+	}
+
+	kfree(lun_bitmap);
+}
+
+void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
+{
+	struct ppa_addr l2p_ppa;
+
+	/* logic error: lba out-of-bounds. Ignore update */
+	if (!(lba < pblk->rl.nr_secs)) {
+		WARN(1, "pblk: corrupted L2P map request\n");
+		return;
+	}
+
+	spin_lock(&pblk->trans_lock);
+	l2p_ppa = pblk_trans_map_get(pblk, lba);
+
+	if (!pblk_addr_in_cache(l2p_ppa) && !pblk_ppa_empty(l2p_ppa))
+		pblk_map_invalidate(pblk, l2p_ppa);
+
+	pblk_trans_map_set(pblk, lba, ppa);
+	spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
+{
+#ifdef CONFIG_NVM_DEBUG
+	/* Callers must ensure that the ppa points to a cache address */
+	BUG_ON(!pblk_addr_in_cache(ppa));
+	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
+#endif
+
+	pblk_update_map(pblk, lba, ppa);
+}
+
+int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+		       struct pblk_line *gc_line)
+{
+	struct ppa_addr l2p_ppa;
+	int ret = 1;
+
+#ifdef CONFIG_NVM_DEBUG
+	/* Callers must ensure that the ppa points to a cache address */
+	BUG_ON(!pblk_addr_in_cache(ppa));
+	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
+#endif
+
+	/* logic error: lba out-of-bounds. Ignore update */
+	if (!(lba < pblk->rl.nr_secs)) {
+		WARN(1, "pblk: corrupted L2P map request\n");
+		return 0;
+	}
+
+	spin_lock(&pblk->trans_lock);
+	l2p_ppa = pblk_trans_map_get(pblk, lba);
+
+	/* Prevent updated entries to be overwritten by GC */
+	if (pblk_addr_in_cache(l2p_ppa) || pblk_ppa_empty(l2p_ppa) ||
+				pblk_tgt_ppa_to_line(l2p_ppa) != gc_line->id) {
+		ret = 0;
+		goto out;
+	}
+
+	pblk_trans_map_set(pblk, lba, ppa);
+out:
+	spin_unlock(&pblk->trans_lock);
+	return ret;
+}
+
+void pblk_update_map_dev(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+			 struct ppa_addr entry_line)
+{
+	struct ppa_addr l2p_line;
+
+#ifdef CONFIG_NVM_DEBUG
+	/* Callers must ensure that the ppa points to a device address */
+	BUG_ON(pblk_addr_in_cache(ppa));
+#endif
+	/* Invalidate and discard padded entries */
+	if (lba == ADDR_EMPTY) {
+#ifdef CONFIG_NVM_DEBUG
+		atomic_long_inc(&pblk->padded_wb);
+#endif
+		pblk_map_invalidate(pblk, ppa);
+		return;
+	}
+
+	/* logic error: lba out-of-bounds. Ignore update */
+	if (!(lba < pblk->rl.nr_secs)) {
+		WARN(1, "pblk: corrupted L2P map request\n");
+		return;
+	}
+
+	spin_lock(&pblk->trans_lock);
+	l2p_line = pblk_trans_map_get(pblk, lba);
+
+	/* Do not update L2P if the cacheline has been updated. In this case,
+	 * the mapped ppa must be invalidated
+	 */
+	if (l2p_line.ppa != entry_line.ppa) {
+		if (!pblk_ppa_empty(ppa))
+			pblk_map_invalidate(pblk, ppa);
+		goto out;
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	WARN_ON(!pblk_addr_in_cache(l2p_line) && !pblk_ppa_empty(l2p_line));
+#endif
+
+	pblk_trans_map_set(pblk, lba, ppa);
+out:
+	spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
+			 sector_t blba, int nr_secs)
+{
+	int i;
+
+	spin_lock(&pblk->trans_lock);
+	for (i = 0; i < nr_secs; i++)
+		ppas[i] = pblk_trans_map_get(pblk, blba + i);
+	spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
+			  u64 *lba_list, int nr_secs)
+{
+	sector_t lba;
+	int i;
+
+	spin_lock(&pblk->trans_lock);
+	for (i = 0; i < nr_secs; i++) {
+		lba = lba_list[i];
+		if (lba == ADDR_EMPTY) {
+			ppas[i].ppa = ADDR_EMPTY;
+		} else {
+			/* logic error: lba out-of-bounds. Ignore update */
+			if (!(lba < pblk->rl.nr_secs)) {
+				WARN(1, "pblk: corrupted L2P map request\n");
+				continue;
+			}
+			ppas[i] = pblk_trans_map_get(pblk, lba);
+		}
+	}
+	spin_unlock(&pblk->trans_lock);
+}
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
new file mode 100644
index 000000000000..eaf479c6b63c
--- /dev/null
+++ b/drivers/lightnvm/pblk-gc.c
@@ -0,0 +1,555 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-gc.c - pblk's garbage collector
+ */
+
+#include "pblk.h"
+#include <linux/delay.h>
+
+static void pblk_gc_free_gc_rq(struct pblk_gc_rq *gc_rq)
+{
+	kfree(gc_rq->data);
+	kfree(gc_rq->lba_list);
+	kfree(gc_rq);
+}
+
+static int pblk_gc_write(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+	struct pblk_gc_rq *gc_rq, *tgc_rq;
+	LIST_HEAD(w_list);
+
+	spin_lock(&gc->w_lock);
+	if (list_empty(&gc->w_list)) {
+		spin_unlock(&gc->w_lock);
+		return 1;
+	}
+
+	list_for_each_entry_safe(gc_rq, tgc_rq, &gc->w_list, list) {
+		list_move_tail(&gc_rq->list, &w_list);
+		gc->w_entries--;
+	}
+	spin_unlock(&gc->w_lock);
+
+	list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) {
+		pblk_write_gc_to_cache(pblk, gc_rq->data, gc_rq->lba_list,
+				gc_rq->nr_secs, gc_rq->secs_to_gc,
+				gc_rq->line, PBLK_IOTYPE_GC);
+
+		kref_put(&gc_rq->line->ref, pblk_line_put);
+
+		list_del(&gc_rq->list);
+		pblk_gc_free_gc_rq(gc_rq);
+	}
+
+	return 0;
+}
+
+static void pblk_gc_writer_kick(struct pblk_gc *gc)
+{
+	wake_up_process(gc->gc_writer_ts);
+}
+
+/*
+ * Responsible for managing all memory related to a gc request. Also in case of
+ * failure
+ */
+static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_line *line,
+				   u64 *lba_list, unsigned int nr_secs)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_gc *gc = &pblk->gc;
+	struct pblk_gc_rq *gc_rq;
+	void *data;
+	unsigned int secs_to_gc;
+	int ret = NVM_IO_OK;
+
+	data = kmalloc(nr_secs * geo->sec_size, GFP_KERNEL);
+	if (!data) {
+		ret = NVM_IO_ERR;
+		goto free_lba_list;
+	}
+
+	/* Read from GC victim block */
+	if (pblk_submit_read_gc(pblk, lba_list, data, nr_secs,
+							&secs_to_gc, line)) {
+		ret = NVM_IO_ERR;
+		goto free_data;
+	}
+
+	if (!secs_to_gc)
+		goto free_data;
+
+	gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
+	if (!gc_rq) {
+		ret = NVM_IO_ERR;
+		goto free_data;
+	}
+
+	gc_rq->line = line;
+	gc_rq->data = data;
+	gc_rq->lba_list = lba_list;
+	gc_rq->nr_secs = nr_secs;
+	gc_rq->secs_to_gc = secs_to_gc;
+
+	kref_get(&line->ref);
+
+retry:
+	spin_lock(&gc->w_lock);
+	if (gc->w_entries > 256) {
+		spin_unlock(&gc->w_lock);
+		usleep_range(256, 1024);
+		goto retry;
+	}
+	gc->w_entries++;
+	list_add_tail(&gc_rq->list, &gc->w_list);
+	spin_unlock(&gc->w_lock);
+
+	pblk_gc_writer_kick(&pblk->gc);
+
+	return NVM_IO_OK;
+
+free_data:
+	kfree(data);
+free_lba_list:
+	kfree(lba_list);
+
+	return ret;
+}
+
+static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct list_head *move_list;
+
+	spin_lock(&line->lock);
+	WARN_ON(line->state != PBLK_LINESTATE_GC);
+	line->state = PBLK_LINESTATE_CLOSED;
+	move_list = pblk_line_gc_list(pblk, line);
+	spin_unlock(&line->lock);
+
+	if (move_list) {
+		spin_lock(&l_mg->gc_lock);
+		list_add_tail(&line->list, move_list);
+		spin_unlock(&l_mg->gc_lock);
+	}
+}
+
+static void pblk_gc_line_ws(struct work_struct *work)
+{
+	struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+									ws);
+	struct pblk *pblk = line_ws->pblk;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *line = line_ws->line;
+	struct pblk_line_meta *lm = &pblk->lm;
+	__le64 *lba_list = line_ws->priv;
+	u64 *gc_list;
+	int sec_left;
+	int nr_ppas, bit;
+	int put_line = 1;
+
+	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+
+	spin_lock(&line->lock);
+	sec_left = line->vsc;
+	if (!sec_left) {
+		/* Lines are erased before being used (l_mg->data_/log_next) */
+		spin_unlock(&line->lock);
+		goto out;
+	}
+	spin_unlock(&line->lock);
+
+	if (sec_left < 0) {
+		pr_err("pblk: corrupted GC line (%d)\n", line->id);
+		put_line = 0;
+		pblk_put_line_back(pblk, line);
+		goto out;
+	}
+
+	bit = -1;
+next_rq:
+	gc_list = kmalloc_array(pblk->max_write_pgs, sizeof(u64), GFP_KERNEL);
+	if (!gc_list) {
+		put_line = 0;
+		pblk_put_line_back(pblk, line);
+		goto out;
+	}
+
+	nr_ppas = 0;
+	do {
+		bit = find_next_zero_bit(line->invalid_bitmap, lm->sec_per_line,
+								bit + 1);
+		if (bit > line->emeta_ssec)
+			break;
+
+		gc_list[nr_ppas++] = le64_to_cpu(lba_list[bit]);
+	} while (nr_ppas < pblk->max_write_pgs);
+
+	if (unlikely(!nr_ppas)) {
+		kfree(gc_list);
+		goto out;
+	}
+
+	if (pblk_gc_move_valid_secs(pblk, line, gc_list, nr_ppas)) {
+		pr_err("pblk: could not GC all sectors: line:%d (%d/%d/%d)\n",
+						line->id, line->vsc,
+						nr_ppas, nr_ppas);
+		put_line = 0;
+		pblk_put_line_back(pblk, line);
+		goto out;
+	}
+
+	sec_left -= nr_ppas;
+	if (sec_left > 0)
+		goto next_rq;
+
+out:
+	pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+	mempool_free(line_ws, pblk->line_ws_pool);
+	atomic_dec(&pblk->gc.inflight_gc);
+	if (put_line)
+		kref_put(&line->ref, pblk_line_put);
+}
+
+static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_ws *line_ws;
+	__le64 *lba_list;
+	int ret;
+
+	line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+	line->emeta = pblk_malloc(lm->emeta_len, l_mg->emeta_alloc_type,
+								GFP_KERNEL);
+	if (!line->emeta) {
+		pr_err("pblk: cannot use GC emeta\n");
+		goto fail_free_ws;
+	}
+
+	ret = pblk_line_read_emeta(pblk, line);
+	if (ret) {
+		pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
+		goto fail_free_emeta;
+	}
+
+	/* If this read fails, it means that emeta is corrupted. For now, leave
+	 * the line untouched. TODO: Implement a recovery routine that scans and
+	 * moves all sectors on the line.
+	 */
+	lba_list = pblk_recov_get_lba_list(pblk, line->emeta);
+	if (!lba_list) {
+		pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
+		goto fail_free_emeta;
+	}
+
+	line_ws->pblk = pblk;
+	line_ws->line = line;
+	line_ws->priv = lba_list;
+
+	INIT_WORK(&line_ws->ws, pblk_gc_line_ws);
+	queue_work(pblk->gc.gc_reader_wq, &line_ws->ws);
+
+	return 0;
+
+fail_free_emeta:
+	pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+fail_free_ws:
+	mempool_free(line_ws, pblk->line_ws_pool);
+	pblk_put_line_back(pblk, line);
+
+	return 1;
+}
+
+static void pblk_gc_lines(struct pblk *pblk, struct list_head *gc_list)
+{
+	struct pblk_line *line, *tline;
+
+	list_for_each_entry_safe(line, tline, gc_list, list) {
+		if (pblk_gc_line(pblk, line))
+			pr_err("pblk: failed to GC line %d\n", line->id);
+		list_del(&line->list);
+	}
+}
+
+/*
+ * Lines with no valid sectors will be returned to the free list immediately. If
+ * GC is activated - either because the free block count is under the determined
+ * threshold, or because it is being forced from user space - only lines with a
+ * high count of invalid sectors will be recycled.
+ */
+static void pblk_gc_run(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_gc *gc = &pblk->gc;
+	struct pblk_line *line, *tline;
+	unsigned int nr_blocks_free, nr_blocks_need;
+	struct list_head *group_list;
+	int run_gc, gc_group = 0;
+	int prev_gc = 0;
+	int inflight_gc = atomic_read(&gc->inflight_gc);
+	LIST_HEAD(gc_list);
+
+	spin_lock(&l_mg->gc_lock);
+	list_for_each_entry_safe(line, tline, &l_mg->gc_full_list, list) {
+		spin_lock(&line->lock);
+		WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
+		line->state = PBLK_LINESTATE_GC;
+		spin_unlock(&line->lock);
+
+		list_del(&line->list);
+		kref_put(&line->ref, pblk_line_put);
+	}
+	spin_unlock(&l_mg->gc_lock);
+
+	nr_blocks_need = pblk_rl_gc_thrs(&pblk->rl);
+	nr_blocks_free = pblk_rl_nr_free_blks(&pblk->rl);
+	run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+
+next_gc_group:
+	group_list = l_mg->gc_lists[gc_group++];
+	spin_lock(&l_mg->gc_lock);
+	while (run_gc && !list_empty(group_list)) {
+		/* No need to queue up more GC lines than we can handle */
+		if (!run_gc || inflight_gc > gc->gc_jobs_active) {
+			spin_unlock(&l_mg->gc_lock);
+			pblk_gc_lines(pblk, &gc_list);
+			return;
+		}
+
+		line = list_first_entry(group_list, struct pblk_line, list);
+		nr_blocks_free += atomic_read(&line->blk_in_line);
+
+		spin_lock(&line->lock);
+		WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
+		line->state = PBLK_LINESTATE_GC;
+		list_move_tail(&line->list, &gc_list);
+		atomic_inc(&gc->inflight_gc);
+		inflight_gc++;
+		spin_unlock(&line->lock);
+
+		prev_gc = 1;
+		run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+	}
+	spin_unlock(&l_mg->gc_lock);
+
+	pblk_gc_lines(pblk, &gc_list);
+
+	if (!prev_gc && pblk->rl.rb_state > gc_group &&
+						gc_group < PBLK_NR_GC_LISTS)
+		goto next_gc_group;
+}
+
+
+static void pblk_gc_kick(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+
+	wake_up_process(gc->gc_ts);
+	pblk_gc_writer_kick(gc);
+	mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
+}
+
+static void pblk_gc_timer(unsigned long data)
+{
+	struct pblk *pblk = (struct pblk *)data;
+
+	pblk_gc_kick(pblk);
+}
+
+static int pblk_gc_ts(void *data)
+{
+	struct pblk *pblk = data;
+
+	while (!kthread_should_stop()) {
+		pblk_gc_run(pblk);
+		set_current_state(TASK_INTERRUPTIBLE);
+		io_schedule();
+	}
+
+	return 0;
+}
+
+static int pblk_gc_writer_ts(void *data)
+{
+	struct pblk *pblk = data;
+
+	while (!kthread_should_stop()) {
+		if (!pblk_gc_write(pblk))
+			continue;
+		set_current_state(TASK_INTERRUPTIBLE);
+		io_schedule();
+	}
+
+	return 0;
+}
+
+static void pblk_gc_start(struct pblk *pblk)
+{
+	pblk->gc.gc_active = 1;
+
+	pr_debug("pblk: gc start\n");
+}
+
+int pblk_gc_status(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+	int ret;
+
+	spin_lock(&gc->lock);
+	ret = gc->gc_active;
+	spin_unlock(&gc->lock);
+
+	return ret;
+}
+
+static void __pblk_gc_should_start(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+
+	lockdep_assert_held(&gc->lock);
+
+	if (gc->gc_enabled && !gc->gc_active)
+		pblk_gc_start(pblk);
+}
+
+void pblk_gc_should_start(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+
+	spin_lock(&gc->lock);
+	__pblk_gc_should_start(pblk);
+	spin_unlock(&gc->lock);
+}
+
+/*
+ * If flush_wq == 1 then no lock should be held by the caller since
+ * flush_workqueue can sleep
+ */
+static void pblk_gc_stop(struct pblk *pblk, int flush_wq)
+{
+	spin_lock(&pblk->gc.lock);
+	pblk->gc.gc_active = 0;
+	spin_unlock(&pblk->gc.lock);
+
+	pr_debug("pblk: gc stop\n");
+}
+
+void pblk_gc_should_stop(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+
+	if (gc->gc_active && !gc->gc_forced)
+		pblk_gc_stop(pblk, 0);
+}
+
+void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
+			      int *gc_active)
+{
+	struct pblk_gc *gc = &pblk->gc;
+
+	spin_lock(&gc->lock);
+	*gc_enabled = gc->gc_enabled;
+	*gc_active = gc->gc_active;
+	spin_unlock(&gc->lock);
+}
+
+void pblk_gc_sysfs_force(struct pblk *pblk, int force)
+{
+	struct pblk_gc *gc = &pblk->gc;
+	int rsv = 0;
+
+	spin_lock(&gc->lock);
+	if (force) {
+		gc->gc_enabled = 1;
+		rsv = 64;
+	}
+	pblk_rl_set_gc_rsc(&pblk->rl, rsv);
+	gc->gc_forced = force;
+	__pblk_gc_should_start(pblk);
+	spin_unlock(&gc->lock);
+}
+
+int pblk_gc_init(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+	int ret;
+
+	gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
+	if (IS_ERR(gc->gc_ts)) {
+		pr_err("pblk: could not allocate GC main kthread\n");
+		return PTR_ERR(gc->gc_ts);
+	}
+
+	gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
+							"pblk-gc-writer-ts");
+	if (IS_ERR(gc->gc_writer_ts)) {
+		pr_err("pblk: could not allocate GC writer kthread\n");
+		ret = PTR_ERR(gc->gc_writer_ts);
+		goto fail_free_main_kthread;
+	}
+
+	setup_timer(&gc->gc_timer, pblk_gc_timer, (unsigned long)pblk);
+	mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
+
+	gc->gc_active = 0;
+	gc->gc_forced = 0;
+	gc->gc_enabled = 1;
+	gc->gc_jobs_active = 8;
+	gc->w_entries = 0;
+	atomic_set(&gc->inflight_gc, 0);
+
+	gc->gc_reader_wq = alloc_workqueue("pblk-gc-reader-wq",
+			WQ_MEM_RECLAIM | WQ_UNBOUND, gc->gc_jobs_active);
+	if (!gc->gc_reader_wq) {
+		pr_err("pblk: could not allocate GC reader workqueue\n");
+		ret = -ENOMEM;
+		goto fail_free_writer_kthread;
+	}
+
+	spin_lock_init(&gc->lock);
+	spin_lock_init(&gc->w_lock);
+	INIT_LIST_HEAD(&gc->w_list);
+
+	return 0;
+
+fail_free_writer_kthread:
+	kthread_stop(gc->gc_writer_ts);
+fail_free_main_kthread:
+	kthread_stop(gc->gc_ts);
+
+	return ret;
+}
+
+void pblk_gc_exit(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+
+	flush_workqueue(gc->gc_reader_wq);
+
+	del_timer(&gc->gc_timer);
+	pblk_gc_stop(pblk, 1);
+
+	if (gc->gc_ts)
+		kthread_stop(gc->gc_ts);
+
+	if (pblk->gc.gc_reader_wq)
+		destroy_workqueue(pblk->gc.gc_reader_wq);
+
+	if (gc->gc_writer_ts)
+		kthread_stop(gc->gc_writer_ts);
+}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
new file mode 100644
index 000000000000..ae8cd6d5af8b
--- /dev/null
+++ b/drivers/lightnvm/pblk-init.c
@@ -0,0 +1,962 @@
+/*
+ * Copyright (C) 2015 IT University of Copenhagen (rrpc.c)
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Implementation of a physical block-device target for Open-channel SSDs.
+ *
+ * pblk-init.c - pblk's initialization.
+ */
+
+#include "pblk.h"
+
+static struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_r_rq_cache,
+					*pblk_w_rq_cache, *pblk_line_meta_cache;
+static DECLARE_RWSEM(pblk_lock);
+
+static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
+			  struct bio *bio)
+{
+	int ret;
+
+	/* Read requests must be <= 256kb due to NVMe's 64 bit completion bitmap
+	 * constraint. Writes can be of arbitrary size.
+	 */
+	if (bio_data_dir(bio) == READ) {
+		blk_queue_split(q, &bio, q->bio_split);
+		ret = pblk_submit_read(pblk, bio);
+		if (ret == NVM_IO_DONE && bio_flagged(bio, BIO_CLONED))
+			bio_put(bio);
+
+		return ret;
+	}
+
+	/* Prevent deadlock in the case of a modest LUN configuration and large
+	 * user I/Os. Unless stalled, the rate limiter leaves at least 256KB
+	 * available for user I/O.
+	 */
+	if (unlikely(pblk_get_secs(bio) >= pblk_rl_sysfs_rate_show(&pblk->rl)))
+		blk_queue_split(q, &bio, q->bio_split);
+
+	return pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
+}
+
+static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
+{
+	struct pblk *pblk = q->queuedata;
+
+	if (bio_op(bio) == REQ_OP_DISCARD) {
+		pblk_discard(pblk, bio);
+		if (!(bio->bi_opf & REQ_PREFLUSH)) {
+			bio_endio(bio);
+			return BLK_QC_T_NONE;
+		}
+	}
+
+	switch (pblk_rw_io(q, pblk, bio)) {
+	case NVM_IO_ERR:
+		bio_io_error(bio);
+		break;
+	case NVM_IO_DONE:
+		bio_endio(bio);
+		break;
+	}
+
+	return BLK_QC_T_NONE;
+}
+
+static void pblk_l2p_free(struct pblk *pblk)
+{
+	vfree(pblk->trans_map);
+}
+
+static int pblk_l2p_init(struct pblk *pblk)
+{
+	sector_t i;
+	struct ppa_addr ppa;
+	int entry_size = 8;
+
+	if (pblk->ppaf_bitsize < 32)
+		entry_size = 4;
+
+	pblk->trans_map = vmalloc(entry_size * pblk->rl.nr_secs);
+	if (!pblk->trans_map)
+		return -ENOMEM;
+
+	pblk_ppa_set_empty(&ppa);
+
+	for (i = 0; i < pblk->rl.nr_secs; i++)
+		pblk_trans_map_set(pblk, i, ppa);
+
+	return 0;
+}
+
+static void pblk_rwb_free(struct pblk *pblk)
+{
+	if (pblk_rb_tear_down_check(&pblk->rwb))
+		pr_err("pblk: write buffer error on tear down\n");
+
+	pblk_rb_data_free(&pblk->rwb);
+	vfree(pblk_rb_entries_ref(&pblk->rwb));
+}
+
+static int pblk_rwb_init(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_rb_entry *entries;
+	unsigned long nr_entries;
+	unsigned int power_size, power_seg_sz;
+
+	nr_entries = pblk_rb_calculate_size(pblk->pgs_in_buffer);
+
+	entries = vzalloc(nr_entries * sizeof(struct pblk_rb_entry));
+	if (!entries)
+		return -ENOMEM;
+
+	power_size = get_count_order(nr_entries);
+	power_seg_sz = get_count_order(geo->sec_size);
+
+	return pblk_rb_init(&pblk->rwb, entries, power_size, power_seg_sz);
+}
+
+/* Minimum pages needed within a lun */
+#define PAGE_POOL_SIZE 16
+#define ADDR_POOL_SIZE 64
+
+static int pblk_set_ppaf(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_addr_format ppaf = geo->ppaf;
+	int power_len;
+
+	/* Re-calculate channel and lun format to adapt to configuration */
+	power_len = get_count_order(geo->nr_chnls);
+	if (1 << power_len != geo->nr_chnls) {
+		pr_err("pblk: supports only power-of-two channel config.\n");
+		return -EINVAL;
+	}
+	ppaf.ch_len = power_len;
+
+	power_len = get_count_order(geo->luns_per_chnl);
+	if (1 << power_len != geo->luns_per_chnl) {
+		pr_err("pblk: supports only power-of-two LUN config.\n");
+		return -EINVAL;
+	}
+	ppaf.lun_len = power_len;
+
+	pblk->ppaf.sec_offset = 0;
+	pblk->ppaf.pln_offset = ppaf.sect_len;
+	pblk->ppaf.ch_offset = pblk->ppaf.pln_offset + ppaf.pln_len;
+	pblk->ppaf.lun_offset = pblk->ppaf.ch_offset + ppaf.ch_len;
+	pblk->ppaf.pg_offset = pblk->ppaf.lun_offset + ppaf.lun_len;
+	pblk->ppaf.blk_offset = pblk->ppaf.pg_offset + ppaf.pg_len;
+	pblk->ppaf.sec_mask = (1ULL << ppaf.sect_len) - 1;
+	pblk->ppaf.pln_mask = ((1ULL << ppaf.pln_len) - 1) <<
+							pblk->ppaf.pln_offset;
+	pblk->ppaf.ch_mask = ((1ULL << ppaf.ch_len) - 1) <<
+							pblk->ppaf.ch_offset;
+	pblk->ppaf.lun_mask = ((1ULL << ppaf.lun_len) - 1) <<
+							pblk->ppaf.lun_offset;
+	pblk->ppaf.pg_mask = ((1ULL << ppaf.pg_len) - 1) <<
+							pblk->ppaf.pg_offset;
+	pblk->ppaf.blk_mask = ((1ULL << ppaf.blk_len) - 1) <<
+							pblk->ppaf.blk_offset;
+
+	pblk->ppaf_bitsize = pblk->ppaf.blk_offset + ppaf.blk_len;
+
+	return 0;
+}
+
+static int pblk_init_global_caches(struct pblk *pblk)
+{
+	char cache_name[PBLK_CACHE_NAME_LEN];
+
+	down_write(&pblk_lock);
+	pblk_blk_ws_cache = kmem_cache_create("pblk_blk_ws",
+				sizeof(struct pblk_line_ws), 0, 0, NULL);
+	if (!pblk_blk_ws_cache) {
+		up_write(&pblk_lock);
+		return -ENOMEM;
+	}
+
+	pblk_rec_cache = kmem_cache_create("pblk_rec",
+				sizeof(struct pblk_rec_ctx), 0, 0, NULL);
+	if (!pblk_rec_cache) {
+		kmem_cache_destroy(pblk_blk_ws_cache);
+		up_write(&pblk_lock);
+		return -ENOMEM;
+	}
+
+	pblk_r_rq_cache = kmem_cache_create("pblk_r_rq", pblk_r_rq_size,
+				0, 0, NULL);
+	if (!pblk_r_rq_cache) {
+		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_rec_cache);
+		up_write(&pblk_lock);
+		return -ENOMEM;
+	}
+
+	pblk_w_rq_cache = kmem_cache_create("pblk_w_rq", pblk_w_rq_size,
+				0, 0, NULL);
+	if (!pblk_w_rq_cache) {
+		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_rec_cache);
+		kmem_cache_destroy(pblk_r_rq_cache);
+		up_write(&pblk_lock);
+		return -ENOMEM;
+	}
+
+	snprintf(cache_name, sizeof(cache_name), "pblk_line_m_%s",
+							pblk->disk->disk_name);
+	pblk_line_meta_cache = kmem_cache_create(cache_name,
+				pblk->lm.sec_bitmap_len, 0, 0, NULL);
+	if (!pblk_line_meta_cache) {
+		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_rec_cache);
+		kmem_cache_destroy(pblk_r_rq_cache);
+		kmem_cache_destroy(pblk_w_rq_cache);
+		up_write(&pblk_lock);
+		return -ENOMEM;
+	}
+	up_write(&pblk_lock);
+
+	return 0;
+}
+
+static int pblk_core_init(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	int max_write_ppas;
+	int mod;
+
+	pblk->min_write_pgs = geo->sec_per_pl * (geo->sec_size / PAGE_SIZE);
+	max_write_ppas = pblk->min_write_pgs * geo->nr_luns;
+	pblk->max_write_pgs = (max_write_ppas < nvm_max_phys_sects(dev)) ?
+				max_write_ppas : nvm_max_phys_sects(dev);
+	pblk->pgs_in_buffer = NVM_MEM_PAGE_WRITE * geo->sec_per_pg *
+						geo->nr_planes * geo->nr_luns;
+
+	if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
+		pr_err("pblk: cannot support device max_phys_sect\n");
+		return -EINVAL;
+	}
+
+	div_u64_rem(geo->sec_per_blk, pblk->min_write_pgs, &mod);
+	if (mod) {
+		pr_err("pblk: bad configuration of sectors/pages\n");
+		return -EINVAL;
+	}
+
+	if (pblk_init_global_caches(pblk))
+		return -ENOMEM;
+
+	pblk->page_pool = mempool_create_page_pool(PAGE_POOL_SIZE, 0);
+	if (!pblk->page_pool)
+		return -ENOMEM;
+
+	pblk->line_ws_pool = mempool_create_slab_pool(geo->nr_luns,
+							pblk_blk_ws_cache);
+	if (!pblk->line_ws_pool)
+		goto free_page_pool;
+
+	pblk->rec_pool = mempool_create_slab_pool(geo->nr_luns, pblk_rec_cache);
+	if (!pblk->rec_pool)
+		goto free_blk_ws_pool;
+
+	pblk->r_rq_pool = mempool_create_slab_pool(64, pblk_r_rq_cache);
+	if (!pblk->r_rq_pool)
+		goto free_rec_pool;
+
+	pblk->w_rq_pool = mempool_create_slab_pool(64, pblk_w_rq_cache);
+	if (!pblk->w_rq_pool)
+		goto free_r_rq_pool;
+
+	pblk->line_meta_pool =
+			mempool_create_slab_pool(16, pblk_line_meta_cache);
+	if (!pblk->line_meta_pool)
+		goto free_w_rq_pool;
+
+	pblk->kw_wq = alloc_workqueue("pblk-aux-wq",
+					WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+	if (!pblk->kw_wq)
+		goto free_line_meta_pool;
+
+	if (pblk_set_ppaf(pblk))
+		goto free_kw_wq;
+
+	if (pblk_rwb_init(pblk))
+		goto free_kw_wq;
+
+	INIT_LIST_HEAD(&pblk->compl_list);
+	return 0;
+
+free_kw_wq:
+	destroy_workqueue(pblk->kw_wq);
+free_line_meta_pool:
+	mempool_destroy(pblk->line_meta_pool);
+free_w_rq_pool:
+	mempool_destroy(pblk->w_rq_pool);
+free_r_rq_pool:
+	mempool_destroy(pblk->r_rq_pool);
+free_rec_pool:
+	mempool_destroy(pblk->rec_pool);
+free_blk_ws_pool:
+	mempool_destroy(pblk->line_ws_pool);
+free_page_pool:
+	mempool_destroy(pblk->page_pool);
+	return -ENOMEM;
+}
+
+static void pblk_core_free(struct pblk *pblk)
+{
+	if (pblk->kw_wq)
+		destroy_workqueue(pblk->kw_wq);
+
+	mempool_destroy(pblk->page_pool);
+	mempool_destroy(pblk->line_ws_pool);
+	mempool_destroy(pblk->rec_pool);
+	mempool_destroy(pblk->r_rq_pool);
+	mempool_destroy(pblk->w_rq_pool);
+	mempool_destroy(pblk->line_meta_pool);
+
+	kmem_cache_destroy(pblk_blk_ws_cache);
+	kmem_cache_destroy(pblk_rec_cache);
+	kmem_cache_destroy(pblk_r_rq_cache);
+	kmem_cache_destroy(pblk_w_rq_cache);
+	kmem_cache_destroy(pblk_line_meta_cache);
+}
+
+static void pblk_luns_free(struct pblk *pblk)
+{
+	kfree(pblk->luns);
+}
+
+static void pblk_lines_free(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *line;
+	int i;
+
+	spin_lock(&l_mg->free_lock);
+	for (i = 0; i < l_mg->nr_lines; i++) {
+		line = &pblk->lines[i];
+
+		pblk_line_free(pblk, line);
+		kfree(line->blk_bitmap);
+		kfree(line->erase_bitmap);
+	}
+	spin_unlock(&l_mg->free_lock);
+}
+
+static void pblk_line_meta_free(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	int i;
+
+	kfree(l_mg->bb_template);
+	kfree(l_mg->bb_aux);
+
+	for (i = 0; i < PBLK_DATA_LINES; i++) {
+		pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type);
+		pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type);
+	}
+
+	kfree(pblk->lines);
+}
+
+static int pblk_bb_discovery(struct nvm_tgt_dev *dev, struct pblk_lun *rlun)
+{
+	struct nvm_geo *geo = &dev->geo;
+	struct ppa_addr ppa;
+	u8 *blks;
+	int nr_blks, ret;
+
+	nr_blks = geo->blks_per_lun * geo->plane_mode;
+	blks = kmalloc(nr_blks, GFP_KERNEL);
+	if (!blks)
+		return -ENOMEM;
+
+	ppa.ppa = 0;
+	ppa.g.ch = rlun->bppa.g.ch;
+	ppa.g.lun = rlun->bppa.g.lun;
+
+	ret = nvm_get_tgt_bb_tbl(dev, ppa, blks);
+	if (ret)
+		goto out;
+
+	nr_blks = nvm_bb_tbl_fold(dev->parent, blks, nr_blks);
+	if (nr_blks < 0) {
+		ret = nr_blks;
+		goto out;
+	}
+
+	rlun->bb_list = blks;
+
+	return 0;
+out:
+	kfree(blks);
+	return ret;
+}
+
+static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_lun *rlun;
+	int bb_cnt = 0;
+	int i;
+
+	line->blk_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
+	if (!line->blk_bitmap)
+		return -ENOMEM;
+
+	line->erase_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
+	if (!line->erase_bitmap) {
+		kfree(line->blk_bitmap);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < lm->blk_per_line; i++) {
+		rlun = &pblk->luns[i];
+		if (rlun->bb_list[line->id] == NVM_BLK_T_FREE)
+			continue;
+
+		set_bit(i, line->blk_bitmap);
+		bb_cnt++;
+	}
+
+	return bb_cnt;
+}
+
+static int pblk_luns_init(struct pblk *pblk, struct ppa_addr *luns)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_lun *rlun;
+	int i, ret;
+
+	/* TODO: Implement unbalanced LUN support */
+	if (geo->luns_per_chnl < 0) {
+		pr_err("pblk: unbalanced LUN config.\n");
+		return -EINVAL;
+	}
+
+	pblk->luns = kcalloc(geo->nr_luns, sizeof(struct pblk_lun), GFP_KERNEL);
+	if (!pblk->luns)
+		return -ENOMEM;
+
+	for (i = 0; i < geo->nr_luns; i++) {
+		/* Stripe across channels */
+		int ch = i % geo->nr_chnls;
+		int lun_raw = i / geo->nr_chnls;
+		int lunid = lun_raw + ch * geo->luns_per_chnl;
+
+		rlun = &pblk->luns[i];
+		rlun->bppa = luns[lunid];
+
+		sema_init(&rlun->wr_sem, 1);
+
+		ret = pblk_bb_discovery(dev, rlun);
+		if (ret) {
+			while (--i >= 0)
+				kfree(pblk->luns[i].bb_list);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int pblk_lines_configure(struct pblk *pblk, int flags)
+{
+	struct pblk_line *line = NULL;
+	int ret = 0;
+
+	if (!(flags & NVM_TARGET_FACTORY)) {
+		line = pblk_recov_l2p(pblk);
+		if (IS_ERR(line)) {
+			pr_err("pblk: could not recover l2p table\n");
+			ret = -EFAULT;
+		}
+	}
+
+	if (!line) {
+		/* Configure next line for user data */
+		line = pblk_line_get_first_data(pblk);
+		if (!line) {
+			pr_err("pblk: line list corrupted\n");
+			ret = -EFAULT;
+		}
+	}
+
+	return ret;
+}
+
+/* See comment over struct line_emeta definition */
+static unsigned int calc_emeta_len(struct pblk *pblk, struct pblk_line_meta *lm)
+{
+	return (sizeof(struct line_emeta) +
+			((lm->sec_per_line - lm->emeta_sec) * sizeof(u64)) +
+			(pblk->l_mg.nr_lines * sizeof(u32)) +
+			lm->blk_bitmap_len);
+}
+
+static void pblk_set_provision(struct pblk *pblk, long nr_free_blks)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	sector_t provisioned;
+
+	pblk->over_pct = 20;
+
+	provisioned = nr_free_blks;
+	provisioned *= (100 - pblk->over_pct);
+	sector_div(provisioned, 100);
+
+	/* Internally pblk manages all free blocks, but all calculations based
+	 * on user capacity consider only provisioned blocks
+	 */
+	pblk->rl.total_blocks = nr_free_blks;
+	pblk->rl.nr_secs = nr_free_blks * geo->sec_per_blk;
+	pblk->capacity = provisioned * geo->sec_per_blk;
+	atomic_set(&pblk->rl.free_blocks, nr_free_blks);
+}
+
+static int pblk_lines_init(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line *line;
+	unsigned int smeta_len, emeta_len;
+	long nr_bad_blks, nr_meta_blks, nr_free_blks;
+	int bb_distance;
+	int i;
+	int ret;
+
+	lm->sec_per_line = geo->sec_per_blk * geo->nr_luns;
+	lm->blk_per_line = geo->nr_luns;
+	lm->blk_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long);
+	lm->sec_bitmap_len = BITS_TO_LONGS(lm->sec_per_line) * sizeof(long);
+	lm->lun_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long);
+	lm->high_thrs = lm->sec_per_line / 2;
+	lm->mid_thrs = lm->sec_per_line / 4;
+
+	/* Calculate necessary pages for smeta. See comment over struct
+	 * line_smeta definition
+	 */
+	lm->smeta_len = sizeof(struct line_smeta) +
+				PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len;
+
+	i = 1;
+add_smeta_page:
+	lm->smeta_sec = i * geo->sec_per_pl;
+	lm->smeta_len = lm->smeta_sec * geo->sec_size;
+
+	smeta_len = sizeof(struct line_smeta) +
+				PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len;
+	if (smeta_len > lm->smeta_len) {
+		i++;
+		goto add_smeta_page;
+	}
+
+	/* Calculate necessary pages for emeta. See comment over struct
+	 * line_emeta definition
+	 */
+	i = 1;
+add_emeta_page:
+	lm->emeta_sec = i * geo->sec_per_pl;
+	lm->emeta_len = lm->emeta_sec * geo->sec_size;
+
+	emeta_len = calc_emeta_len(pblk, lm);
+	if (emeta_len > lm->emeta_len) {
+		i++;
+		goto add_emeta_page;
+	}
+	lm->emeta_bb = geo->nr_luns - i;
+
+	nr_meta_blks = (lm->smeta_sec + lm->emeta_sec +
+				(geo->sec_per_blk / 2)) / geo->sec_per_blk;
+	lm->min_blk_line = nr_meta_blks + 1;
+
+	l_mg->nr_lines = geo->blks_per_lun;
+	l_mg->log_line = l_mg->data_line = NULL;
+	l_mg->l_seq_nr = l_mg->d_seq_nr = 0;
+	l_mg->nr_free_lines = 0;
+	bitmap_zero(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+
+	/* smeta is always small enough to fit on a kmalloc memory allocation,
+	 * emeta depends on the number of LUNs allocated to the pblk instance
+	 */
+	l_mg->smeta_alloc_type = PBLK_KMALLOC_META;
+	for (i = 0; i < PBLK_DATA_LINES; i++) {
+		l_mg->sline_meta[i].meta = kmalloc(lm->smeta_len, GFP_KERNEL);
+		if (!l_mg->sline_meta[i].meta)
+			while (--i >= 0) {
+				kfree(l_mg->sline_meta[i].meta);
+				ret = -ENOMEM;
+				goto fail;
+			}
+	}
+
+	if (lm->emeta_len > KMALLOC_MAX_CACHE_SIZE) {
+		l_mg->emeta_alloc_type = PBLK_VMALLOC_META;
+
+		for (i = 0; i < PBLK_DATA_LINES; i++) {
+			l_mg->eline_meta[i].meta = vmalloc(lm->emeta_len);
+			if (!l_mg->eline_meta[i].meta)
+				while (--i >= 0) {
+					vfree(l_mg->eline_meta[i].meta);
+					ret = -ENOMEM;
+					goto fail;
+				}
+		}
+	} else {
+		l_mg->emeta_alloc_type = PBLK_KMALLOC_META;
+
+		for (i = 0; i < PBLK_DATA_LINES; i++) {
+			l_mg->eline_meta[i].meta =
+					kmalloc(lm->emeta_len, GFP_KERNEL);
+			if (!l_mg->eline_meta[i].meta)
+				while (--i >= 0) {
+					kfree(l_mg->eline_meta[i].meta);
+					ret = -ENOMEM;
+					goto fail;
+				}
+		}
+	}
+
+	l_mg->bb_template = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+	if (!l_mg->bb_template) {
+		ret = -ENOMEM;
+		goto fail_free_meta;
+	}
+
+	l_mg->bb_aux = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+	if (!l_mg->bb_aux) {
+		ret = -ENOMEM;
+		goto fail_free_bb_template;
+	}
+
+	bb_distance = (geo->nr_luns) * geo->sec_per_pl;
+	for (i = 0; i < lm->sec_per_line; i += bb_distance)
+		bitmap_set(l_mg->bb_template, i, geo->sec_per_pl);
+
+	INIT_LIST_HEAD(&l_mg->free_list);
+	INIT_LIST_HEAD(&l_mg->corrupt_list);
+	INIT_LIST_HEAD(&l_mg->bad_list);
+	INIT_LIST_HEAD(&l_mg->gc_full_list);
+	INIT_LIST_HEAD(&l_mg->gc_high_list);
+	INIT_LIST_HEAD(&l_mg->gc_mid_list);
+	INIT_LIST_HEAD(&l_mg->gc_low_list);
+	INIT_LIST_HEAD(&l_mg->gc_empty_list);
+
+	l_mg->gc_lists[0] = &l_mg->gc_high_list;
+	l_mg->gc_lists[1] = &l_mg->gc_mid_list;
+	l_mg->gc_lists[2] = &l_mg->gc_low_list;
+
+	spin_lock_init(&l_mg->free_lock);
+	spin_lock_init(&l_mg->gc_lock);
+
+	pblk->lines = kcalloc(l_mg->nr_lines, sizeof(struct pblk_line),
+								GFP_KERNEL);
+	if (!pblk->lines) {
+		ret = -ENOMEM;
+		goto fail_free_bb_aux;
+	}
+
+	nr_free_blks = 0;
+	for (i = 0; i < l_mg->nr_lines; i++) {
+		int blk_in_line;
+
+		line = &pblk->lines[i];
+
+		line->pblk = pblk;
+		line->id = i;
+		line->type = PBLK_LINETYPE_FREE;
+		line->state = PBLK_LINESTATE_FREE;
+		line->gc_group = PBLK_LINEGC_NONE;
+		spin_lock_init(&line->lock);
+
+		nr_bad_blks = pblk_bb_line(pblk, line);
+		if (nr_bad_blks < 0 || nr_bad_blks > lm->blk_per_line) {
+			ret = -EINVAL;
+			goto fail_free_lines;
+		}
+
+		blk_in_line = lm->blk_per_line - nr_bad_blks;
+		if (blk_in_line < lm->min_blk_line) {
+			line->state = PBLK_LINESTATE_BAD;
+			list_add_tail(&line->list, &l_mg->bad_list);
+			continue;
+		}
+
+		nr_free_blks += blk_in_line;
+		atomic_set(&line->blk_in_line, blk_in_line);
+
+		l_mg->nr_free_lines++;
+		list_add_tail(&line->list, &l_mg->free_list);
+	}
+
+	pblk_set_provision(pblk, nr_free_blks);
+
+	sema_init(&pblk->erase_sem, 1);
+
+	/* Cleanup per-LUN bad block lists - managed within lines on run-time */
+	for (i = 0; i < geo->nr_luns; i++)
+		kfree(pblk->luns[i].bb_list);
+
+	return 0;
+fail_free_lines:
+	kfree(pblk->lines);
+fail_free_bb_aux:
+	kfree(l_mg->bb_aux);
+fail_free_bb_template:
+	kfree(l_mg->bb_template);
+fail_free_meta:
+	for (i = 0; i < PBLK_DATA_LINES; i++) {
+		pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type);
+		pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type);
+	}
+fail:
+	for (i = 0; i < geo->nr_luns; i++)
+		kfree(pblk->luns[i].bb_list);
+
+	return ret;
+}
+
+static int pblk_writer_init(struct pblk *pblk)
+{
+	setup_timer(&pblk->wtimer, pblk_write_timer_fn, (unsigned long)pblk);
+	mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(100));
+
+	pblk->writer_ts = kthread_create(pblk_write_ts, pblk, "pblk-writer-t");
+	if (IS_ERR(pblk->writer_ts)) {
+		pr_err("pblk: could not allocate writer kthread\n");
+		return PTR_ERR(pblk->writer_ts);
+	}
+
+	return 0;
+}
+
+static void pblk_writer_stop(struct pblk *pblk)
+{
+	if (pblk->writer_ts)
+		kthread_stop(pblk->writer_ts);
+	del_timer(&pblk->wtimer);
+}
+
+static void pblk_free(struct pblk *pblk)
+{
+	pblk_luns_free(pblk);
+	pblk_lines_free(pblk);
+	pblk_line_meta_free(pblk);
+	pblk_core_free(pblk);
+	pblk_l2p_free(pblk);
+
+	kfree(pblk);
+}
+
+static void pblk_tear_down(struct pblk *pblk)
+{
+	pblk_flush_writer(pblk);
+	pblk_writer_stop(pblk);
+	pblk_rb_sync_l2p(&pblk->rwb);
+	pblk_recov_pad(pblk);
+	pblk_rwb_free(pblk);
+	pblk_rl_free(&pblk->rl);
+
+	pr_debug("pblk: consistent tear down\n");
+}
+
+static void pblk_exit(void *private)
+{
+	struct pblk *pblk = private;
+
+	down_write(&pblk_lock);
+	pblk_gc_exit(pblk);
+	pblk_tear_down(pblk);
+	pblk_free(pblk);
+	up_write(&pblk_lock);
+}
+
+static sector_t pblk_capacity(void *private)
+{
+	struct pblk *pblk = private;
+
+	return pblk->capacity * NR_PHY_IN_LOG;
+}
+
+static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
+		       int flags)
+{
+	struct nvm_geo *geo = &dev->geo;
+	struct request_queue *bqueue = dev->q;
+	struct request_queue *tqueue = tdisk->queue;
+	struct pblk *pblk;
+	int ret;
+
+	if (dev->identity.dom & NVM_RSP_L2P) {
+		pr_err("pblk: device-side L2P table not supported. (%x)\n",
+							dev->identity.dom);
+		return ERR_PTR(-EINVAL);
+	}
+
+	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+	if (!pblk)
+		return ERR_PTR(-ENOMEM);
+
+	pblk->dev = dev;
+	pblk->disk = tdisk;
+
+	spin_lock_init(&pblk->trans_lock);
+	spin_lock_init(&pblk->lock);
+
+	if (flags & NVM_TARGET_FACTORY)
+		pblk_setup_uuid(pblk);
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_set(&pblk->inflight_writes, 0);
+	atomic_long_set(&pblk->padded_writes, 0);
+	atomic_long_set(&pblk->padded_wb, 0);
+	atomic_long_set(&pblk->nr_flush, 0);
+	atomic_long_set(&pblk->req_writes, 0);
+	atomic_long_set(&pblk->sub_writes, 0);
+	atomic_long_set(&pblk->sync_writes, 0);
+	atomic_long_set(&pblk->compl_writes, 0);
+	atomic_long_set(&pblk->inflight_reads, 0);
+	atomic_long_set(&pblk->sync_reads, 0);
+	atomic_long_set(&pblk->recov_writes, 0);
+	atomic_long_set(&pblk->recov_writes, 0);
+	atomic_long_set(&pblk->recov_gc_writes, 0);
+#endif
+
+	atomic_long_set(&pblk->read_failed, 0);
+	atomic_long_set(&pblk->read_empty, 0);
+	atomic_long_set(&pblk->read_high_ecc, 0);
+	atomic_long_set(&pblk->read_failed_gc, 0);
+	atomic_long_set(&pblk->write_failed, 0);
+	atomic_long_set(&pblk->erase_failed, 0);
+
+	ret = pblk_luns_init(pblk, dev->luns);
+	if (ret) {
+		pr_err("pblk: could not initialize luns\n");
+		goto fail;
+	}
+
+	ret = pblk_lines_init(pblk);
+	if (ret) {
+		pr_err("pblk: could not initialize lines\n");
+		goto fail_free_luns;
+	}
+
+	ret = pblk_core_init(pblk);
+	if (ret) {
+		pr_err("pblk: could not initialize core\n");
+		goto fail_free_line_meta;
+	}
+
+	ret = pblk_l2p_init(pblk);
+	if (ret) {
+		pr_err("pblk: could not initialize maps\n");
+		goto fail_free_core;
+	}
+
+	ret = pblk_lines_configure(pblk, flags);
+	if (ret) {
+		pr_err("pblk: could not configure lines\n");
+		goto fail_free_l2p;
+	}
+
+	ret = pblk_writer_init(pblk);
+	if (ret) {
+		pr_err("pblk: could not initialize write thread\n");
+		goto fail_free_lines;
+	}
+
+	ret = pblk_gc_init(pblk);
+	if (ret) {
+		pr_err("pblk: could not initialize gc\n");
+		goto fail_stop_writer;
+	}
+
+	/* inherit the size from the underlying device */
+	blk_queue_logical_block_size(tqueue, queue_physical_block_size(bqueue));
+	blk_queue_max_hw_sectors(tqueue, queue_max_hw_sectors(bqueue));
+
+	blk_queue_write_cache(tqueue, true, false);
+
+	tqueue->limits.discard_granularity = geo->pgs_per_blk * geo->pfpg_size;
+	tqueue->limits.discard_alignment = 0;
+	blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, tqueue);
+
+	pr_info("pblk init: luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
+			geo->nr_luns, pblk->l_mg.nr_lines,
+			(unsigned long long)pblk->rl.nr_secs,
+			pblk->rwb.nr_entries);
+
+	wake_up_process(pblk->writer_ts);
+	return pblk;
+
+fail_stop_writer:
+	pblk_writer_stop(pblk);
+fail_free_lines:
+	pblk_lines_free(pblk);
+fail_free_l2p:
+	pblk_l2p_free(pblk);
+fail_free_core:
+	pblk_core_free(pblk);
+fail_free_line_meta:
+	pblk_line_meta_free(pblk);
+fail_free_luns:
+	pblk_luns_free(pblk);
+fail:
+	kfree(pblk);
+	return ERR_PTR(ret);
+}
+
+/* physical block device target */
+static struct nvm_tgt_type tt_pblk = {
+	.name		= "pblk",
+	.version	= {1, 0, 0},
+
+	.make_rq	= pblk_make_rq,
+	.capacity	= pblk_capacity,
+
+	.init		= pblk_init,
+	.exit		= pblk_exit,
+
+	.sysfs_init	= pblk_sysfs_init,
+	.sysfs_exit	= pblk_sysfs_exit,
+};
+
+static int __init pblk_module_init(void)
+{
+	return nvm_register_tgt_type(&tt_pblk);
+}
+
+static void pblk_module_exit(void)
+{
+	nvm_unregister_tgt_type(&tt_pblk);
+}
+
+module_init(pblk_module_init);
+module_exit(pblk_module_exit);
+MODULE_AUTHOR("Javier Gonzalez <javier@cnexlabs.com>");
+MODULE_AUTHOR("Matias Bjorling <matias@cnexlabs.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Physical Block-Device for Open-Channel SSDs");
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
new file mode 100644
index 000000000000..17c16955284d
--- /dev/null
+++ b/drivers/lightnvm/pblk-map.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-map.c - pblk's lba-ppa mapping strategy
+ *
+ */
+
+#include "pblk.h"
+
+static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
+			       struct ppa_addr *ppa_list,
+			       unsigned long *lun_bitmap,
+			       struct pblk_sec_meta *meta_list,
+			       unsigned int valid_secs)
+{
+	struct pblk_line *line = pblk_line_get_data(pblk);
+	struct line_emeta *emeta = line->emeta;
+	struct pblk_w_ctx *w_ctx;
+	__le64 *lba_list = pblk_line_emeta_to_lbas(emeta);
+	u64 paddr;
+	int nr_secs = pblk->min_write_pgs;
+	int i;
+
+	paddr = pblk_alloc_page(pblk, line, nr_secs);
+
+	for (i = 0; i < nr_secs; i++, paddr++) {
+		/* ppa to be sent to the device */
+		ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
+
+		/* Write context for target bio completion on write buffer. Note
+		 * that the write buffer is protected by the sync backpointer,
+		 * and a single writer thread have access to each specific entry
+		 * at a time. Thus, it is safe to modify the context for the
+		 * entry we are setting up for submission without taking any
+		 * lock or memory barrier.
+		 */
+		if (i < valid_secs) {
+			kref_get(&line->ref);
+			w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
+			w_ctx->ppa = ppa_list[i];
+			meta_list[i].lba = cpu_to_le64(w_ctx->lba);
+			lba_list[paddr] = cpu_to_le64(w_ctx->lba);
+			le64_add_cpu(&line->emeta->nr_valid_lbas, 1);
+		} else {
+			meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+			lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+			pblk_map_pad_invalidate(pblk, line, paddr);
+		}
+	}
+
+	if (pblk_line_is_full(line)) {
+		line = pblk_line_replace_data(pblk);
+		if (!line)
+			return;
+	}
+
+	pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
+}
+
+void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+		 unsigned long *lun_bitmap, unsigned int valid_secs,
+		 unsigned int off)
+{
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	unsigned int map_secs;
+	int min = pblk->min_write_pgs;
+	int i;
+
+	for (i = off; i < rqd->nr_ppas; i += min) {
+		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+		pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+					lun_bitmap, &meta_list[i], map_secs);
+	}
+}
+
+/* only if erase_ppa is set, acquire erase semaphore */
+void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+		       unsigned int sentry, unsigned long *lun_bitmap,
+		       unsigned int valid_secs, struct ppa_addr *erase_ppa)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line *e_line = pblk_line_get_data_next(pblk);
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	unsigned int map_secs;
+	int min = pblk->min_write_pgs;
+	int i, erase_lun;
+
+	for (i = 0; i < rqd->nr_ppas; i += min) {
+		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+		pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+					lun_bitmap, &meta_list[i], map_secs);
+
+		erase_lun = rqd->ppa_list[i].g.lun * geo->nr_chnls +
+							rqd->ppa_list[i].g.ch;
+
+		if (!test_bit(erase_lun, e_line->erase_bitmap)) {
+			if (down_trylock(&pblk->erase_sem))
+				continue;
+
+			set_bit(erase_lun, e_line->erase_bitmap);
+			atomic_dec(&e_line->left_eblks);
+			*erase_ppa = rqd->ppa_list[i];
+			erase_ppa->g.blk = e_line->id;
+
+			/* Avoid evaluating e_line->left_eblks */
+			return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
+							valid_secs, i + min);
+		}
+	}
+
+	/* Erase blocks that are bad in this line but might not be in next */
+	if (unlikely(ppa_empty(*erase_ppa))) {
+		struct pblk_line_meta *lm = &pblk->lm;
+
+		i = find_first_zero_bit(e_line->erase_bitmap, lm->blk_per_line);
+		if (i == lm->blk_per_line)
+			return;
+
+		set_bit(i, e_line->erase_bitmap);
+		atomic_dec(&e_line->left_eblks);
+		*erase_ppa = pblk->luns[i].bppa; /* set ch and lun */
+		erase_ppa->g.blk = e_line->id;
+	}
+}
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
new file mode 100644
index 000000000000..045384ddc1f9
--- /dev/null
+++ b/drivers/lightnvm/pblk-rb.c
@@ -0,0 +1,852 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * Based upon the circular ringbuffer.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-rb.c - pblk's write buffer
+ */
+
+#include <linux/circ_buf.h>
+
+#include "pblk.h"
+
+static DECLARE_RWSEM(pblk_rb_lock);
+
+void pblk_rb_data_free(struct pblk_rb *rb)
+{
+	struct pblk_rb_pages *p, *t;
+
+	down_write(&pblk_rb_lock);
+	list_for_each_entry_safe(p, t, &rb->pages, list) {
+		free_pages((unsigned long)page_address(p->pages), p->order);
+		list_del(&p->list);
+		kfree(p);
+	}
+	up_write(&pblk_rb_lock);
+}
+
+/*
+ * Initialize ring buffer. The data and metadata buffers must be previously
+ * allocated and their size must be a power of two
+ * (Documentation/circular-buffers.txt)
+ */
+int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
+		 unsigned int power_size, unsigned int power_seg_sz)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	unsigned int init_entry = 0;
+	unsigned int alloc_order = power_size;
+	unsigned int max_order = MAX_ORDER - 1;
+	unsigned int order, iter;
+
+	down_write(&pblk_rb_lock);
+	rb->entries = rb_entry_base;
+	rb->seg_size = (1 << power_seg_sz);
+	rb->nr_entries = (1 << power_size);
+	rb->mem = rb->subm = rb->sync = rb->l2p_update = 0;
+	rb->sync_point = EMPTY_ENTRY;
+
+	spin_lock_init(&rb->w_lock);
+	spin_lock_init(&rb->s_lock);
+
+	INIT_LIST_HEAD(&rb->pages);
+
+	if (alloc_order >= max_order) {
+		order = max_order;
+		iter = (1 << (alloc_order - max_order));
+	} else {
+		order = alloc_order;
+		iter = 1;
+	}
+
+	do {
+		struct pblk_rb_entry *entry;
+		struct pblk_rb_pages *page_set;
+		void *kaddr;
+		unsigned long set_size;
+		int i;
+
+		page_set = kmalloc(sizeof(struct pblk_rb_pages), GFP_KERNEL);
+		if (!page_set) {
+			up_write(&pblk_rb_lock);
+			return -ENOMEM;
+		}
+
+		page_set->order = order;
+		page_set->pages = alloc_pages(GFP_KERNEL, order);
+		if (!page_set->pages) {
+			kfree(page_set);
+			pblk_rb_data_free(rb);
+			up_write(&pblk_rb_lock);
+			return -ENOMEM;
+		}
+		kaddr = page_address(page_set->pages);
+
+		entry = &rb->entries[init_entry];
+		entry->data = kaddr;
+		entry->cacheline = pblk_cacheline_to_addr(init_entry++);
+		entry->w_ctx.flags = PBLK_WRITABLE_ENTRY;
+
+		set_size = (1 << order);
+		for (i = 1; i < set_size; i++) {
+			entry = &rb->entries[init_entry];
+			entry->cacheline = pblk_cacheline_to_addr(init_entry++);
+			entry->data = kaddr + (i * rb->seg_size);
+			entry->w_ctx.flags = PBLK_WRITABLE_ENTRY;
+			bio_list_init(&entry->w_ctx.bios);
+		}
+
+		list_add_tail(&page_set->list, &rb->pages);
+		iter--;
+	} while (iter > 0);
+	up_write(&pblk_rb_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_set(&rb->inflight_sync_point, 0);
+#endif
+
+	/*
+	 * Initialize rate-limiter, which controls access to the write buffer
+	 * but user and GC I/O
+	 */
+	pblk_rl_init(&pblk->rl, rb->nr_entries);
+
+	return 0;
+}
+
+/*
+ * pblk_rb_calculate_size -- calculate the size of the write buffer
+ */
+unsigned int pblk_rb_calculate_size(unsigned int nr_entries)
+{
+	/* Alloc a write buffer that can at least fit 128 entries */
+	return (1 << max(get_count_order(nr_entries), 7));
+}
+
+void *pblk_rb_entries_ref(struct pblk_rb *rb)
+{
+	return rb->entries;
+}
+
+static void clean_wctx(struct pblk_w_ctx *w_ctx)
+{
+	int flags;
+
+try:
+	flags = READ_ONCE(w_ctx->flags);
+	if (!(flags & PBLK_SUBMITTED_ENTRY))
+		goto try;
+
+	/* Release flags on context. Protect from writes and reads */
+	smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY);
+	pblk_ppa_set_empty(&w_ctx->ppa);
+}
+
+#define pblk_rb_ring_count(head, tail, size) CIRC_CNT(head, tail, size)
+#define pblk_rb_ring_space(rb, head, tail, size) \
+					(CIRC_SPACE(head, tail, size))
+
+/*
+ * Buffer space is calculated with respect to the back pointer signaling
+ * synchronized entries to the media.
+ */
+static unsigned int pblk_rb_space(struct pblk_rb *rb)
+{
+	unsigned int mem = READ_ONCE(rb->mem);
+	unsigned int sync = READ_ONCE(rb->sync);
+
+	return pblk_rb_ring_space(rb, mem, sync, rb->nr_entries);
+}
+
+/*
+ * Buffer count is calculated with respect to the submission entry signaling the
+ * entries that are available to send to the media
+ */
+unsigned int pblk_rb_read_count(struct pblk_rb *rb)
+{
+	unsigned int mem = READ_ONCE(rb->mem);
+	unsigned int subm = READ_ONCE(rb->subm);
+
+	return pblk_rb_ring_count(mem, subm, rb->nr_entries);
+}
+
+unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int nr_entries)
+{
+	unsigned int subm;
+
+	subm = READ_ONCE(rb->subm);
+	/* Commit read means updating submission pointer */
+	smp_store_release(&rb->subm,
+				(subm + nr_entries) & (rb->nr_entries - 1));
+
+	return subm;
+}
+
+static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd,
+				unsigned int to_update)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	struct pblk_line *line;
+	struct pblk_rb_entry *entry;
+	struct pblk_w_ctx *w_ctx;
+	unsigned int i;
+
+	for (i = 0; i < to_update; i++) {
+		entry = &rb->entries[*l2p_upd];
+		w_ctx = &entry->w_ctx;
+
+		pblk_update_map_dev(pblk, w_ctx->lba, w_ctx->ppa,
+							entry->cacheline);
+
+		line = &pblk->lines[pblk_tgt_ppa_to_line(w_ctx->ppa)];
+		kref_put(&line->ref, pblk_line_put);
+		clean_wctx(w_ctx);
+		*l2p_upd = (*l2p_upd + 1) & (rb->nr_entries - 1);
+	}
+
+	return 0;
+}
+
+/*
+ * When we move the l2p_update pointer, we update the l2p table - lookups will
+ * point to the physical address instead of to the cacheline in the write buffer
+ * from this moment on.
+ */
+static int pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int nr_entries,
+			      unsigned int mem, unsigned int sync)
+{
+	unsigned int space, count;
+	int ret = 0;
+
+	lockdep_assert_held(&rb->w_lock);
+
+	/* Update l2p only as buffer entries are being overwritten */
+	space = pblk_rb_ring_space(rb, mem, rb->l2p_update, rb->nr_entries);
+	if (space > nr_entries)
+		goto out;
+
+	count = nr_entries - space;
+	/* l2p_update used exclusively under rb->w_lock */
+	ret = __pblk_rb_update_l2p(rb, &rb->l2p_update, count);
+
+out:
+	return ret;
+}
+
+/*
+ * Update the l2p entry for all sectors stored on the write buffer. This means
+ * that all future lookups to the l2p table will point to a device address, not
+ * to the cacheline in the write buffer.
+ */
+void pblk_rb_sync_l2p(struct pblk_rb *rb)
+{
+	unsigned int sync;
+	unsigned int to_update;
+
+	spin_lock(&rb->w_lock);
+
+	/* Protect from reads and writes */
+	sync = smp_load_acquire(&rb->sync);
+
+	to_update = pblk_rb_ring_count(sync, rb->l2p_update, rb->nr_entries);
+	__pblk_rb_update_l2p(rb, &rb->l2p_update, to_update);
+
+	spin_unlock(&rb->w_lock);
+}
+
+/*
+ * Write @nr_entries to ring buffer from @data buffer if there is enough space.
+ * Typically, 4KB data chunks coming from a bio will be copied to the ring
+ * buffer, thus the write will fail if not all incoming data can be copied.
+ *
+ */
+static void __pblk_rb_write_entry(struct pblk_rb *rb, void *data,
+				  struct pblk_w_ctx w_ctx,
+				  struct pblk_rb_entry *entry)
+{
+	memcpy(entry->data, data, rb->seg_size);
+
+	entry->w_ctx.lba = w_ctx.lba;
+	entry->w_ctx.ppa = w_ctx.ppa;
+}
+
+void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
+			      struct pblk_w_ctx w_ctx, unsigned int ring_pos)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	struct pblk_rb_entry *entry;
+	int flags;
+
+	entry = &rb->entries[ring_pos];
+	flags = READ_ONCE(entry->w_ctx.flags);
+#ifdef CONFIG_NVM_DEBUG
+	/* Caller must guarantee that the entry is free */
+	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
+#endif
+
+	__pblk_rb_write_entry(rb, data, w_ctx, entry);
+
+	pblk_update_map_cache(pblk, w_ctx.lba, entry->cacheline);
+	flags = w_ctx.flags | PBLK_WRITTEN_DATA;
+
+	/* Release flags on write context. Protect from writes */
+	smp_store_release(&entry->w_ctx.flags, flags);
+}
+
+void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
+			    struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
+			    unsigned int ring_pos)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	struct pblk_rb_entry *entry;
+	int flags;
+
+	entry = &rb->entries[ring_pos];
+	flags = READ_ONCE(entry->w_ctx.flags);
+#ifdef CONFIG_NVM_DEBUG
+	/* Caller must guarantee that the entry is free */
+	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
+#endif
+
+	__pblk_rb_write_entry(rb, data, w_ctx, entry);
+
+	if (!pblk_update_map_gc(pblk, w_ctx.lba, entry->cacheline, gc_line))
+		entry->w_ctx.lba = ADDR_EMPTY;
+
+	flags = w_ctx.flags | PBLK_WRITTEN_DATA;
+
+	/* Release flags on write context. Protect from writes */
+	smp_store_release(&entry->w_ctx.flags, flags);
+}
+
+static int pblk_rb_sync_point_set(struct pblk_rb *rb, struct bio *bio,
+				  unsigned int pos)
+{
+	struct pblk_rb_entry *entry;
+	unsigned int subm, sync_point;
+	int flags;
+
+	subm = READ_ONCE(rb->subm);
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_inc(&rb->inflight_sync_point);
+#endif
+
+	if (pos == subm)
+		return 0;
+
+	sync_point = (pos == 0) ? (rb->nr_entries - 1) : (pos - 1);
+	entry = &rb->entries[sync_point];
+
+	flags = READ_ONCE(entry->w_ctx.flags);
+	flags |= PBLK_FLUSH_ENTRY;
+
+	/* Release flags on context. Protect from writes */
+	smp_store_release(&entry->w_ctx.flags, flags);
+
+	/* Protect syncs */
+	smp_store_release(&rb->sync_point, sync_point);
+
+	spin_lock_irq(&rb->s_lock);
+	bio_list_add(&entry->w_ctx.bios, bio);
+	spin_unlock_irq(&rb->s_lock);
+
+	return 1;
+}
+
+static int __pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
+			       unsigned int *pos)
+{
+	unsigned int mem;
+	unsigned int sync;
+
+	sync = READ_ONCE(rb->sync);
+	mem = READ_ONCE(rb->mem);
+
+	if (pblk_rb_ring_space(rb, mem, sync, rb->nr_entries) < nr_entries)
+		return 0;
+
+	if (pblk_rb_update_l2p(rb, nr_entries, mem, sync))
+		return 0;
+
+	*pos = mem;
+
+	return 1;
+}
+
+static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
+			     unsigned int *pos)
+{
+	if (!__pblk_rb_may_write(rb, nr_entries, pos))
+		return 0;
+
+	/* Protect from read count */
+	smp_store_release(&rb->mem, (*pos + nr_entries) & (rb->nr_entries - 1));
+	return 1;
+}
+
+static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
+				   unsigned int *pos, struct bio *bio,
+				   int *io_ret)
+{
+	unsigned int mem;
+
+	if (!__pblk_rb_may_write(rb, nr_entries, pos))
+		return 0;
+
+	mem = (*pos + nr_entries) & (rb->nr_entries - 1);
+	*io_ret = NVM_IO_DONE;
+
+	if (bio->bi_opf & REQ_PREFLUSH) {
+		struct pblk *pblk = container_of(rb, struct pblk, rwb);
+
+#ifdef CONFIG_NVM_DEBUG
+		atomic_long_inc(&pblk->nr_flush);
+#endif
+		if (pblk_rb_sync_point_set(&pblk->rwb, bio, mem))
+			*io_ret = NVM_IO_OK;
+	}
+
+	/* Protect from read count */
+	smp_store_release(&rb->mem, mem);
+	return 1;
+}
+
+/*
+ * Atomically check that (i) there is space on the write buffer for the
+ * incoming I/O, and (ii) the current I/O type has enough budget in the write
+ * buffer (rate-limiter).
+ */
+int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
+			   unsigned int nr_entries, unsigned int *pos)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	int flush_done;
+
+	spin_lock(&rb->w_lock);
+	if (!pblk_rl_user_may_insert(&pblk->rl, nr_entries)) {
+		spin_unlock(&rb->w_lock);
+		return NVM_IO_REQUEUE;
+	}
+
+	if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &flush_done)) {
+		spin_unlock(&rb->w_lock);
+		return NVM_IO_REQUEUE;
+	}
+
+	pblk_rl_user_in(&pblk->rl, nr_entries);
+	spin_unlock(&rb->w_lock);
+
+	return flush_done;
+}
+
+/*
+ * Look at pblk_rb_may_write_user comment
+ */
+int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
+			 unsigned int *pos)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+
+	spin_lock(&rb->w_lock);
+	if (!pblk_rl_gc_may_insert(&pblk->rl, nr_entries)) {
+		spin_unlock(&rb->w_lock);
+		return 0;
+	}
+
+	if (!pblk_rb_may_write(rb, nr_entries, pos)) {
+		spin_unlock(&rb->w_lock);
+		return 0;
+	}
+
+	pblk_rl_gc_in(&pblk->rl, nr_entries);
+	spin_unlock(&rb->w_lock);
+
+	return 1;
+}
+
+/*
+ * The caller of this function must ensure that the backpointer will not
+ * overwrite the entries passed on the list.
+ */
+unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
+				      struct list_head *list,
+				      unsigned int max)
+{
+	struct pblk_rb_entry *entry, *tentry;
+	struct page *page;
+	unsigned int read = 0;
+	int ret;
+
+	list_for_each_entry_safe(entry, tentry, list, index) {
+		if (read > max) {
+			pr_err("pblk: too many entries on list\n");
+			goto out;
+		}
+
+		page = virt_to_page(entry->data);
+		if (!page) {
+			pr_err("pblk: could not allocate write bio page\n");
+			goto out;
+		}
+
+		ret = bio_add_page(bio, page, rb->seg_size, 0);
+		if (ret != rb->seg_size) {
+			pr_err("pblk: could not add page to write bio\n");
+			goto out;
+		}
+
+		list_del(&entry->index);
+		read++;
+	}
+
+out:
+	return read;
+}
+
+/*
+ * Read available entries on rb and add them to the given bio. To avoid a memory
+ * copy, a page reference to the write buffer is used to be added to the bio.
+ *
+ * This function is used by the write thread to form the write bio that will
+ * persist data on the write buffer to the media.
+ */
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio,
+				 struct pblk_c_ctx *c_ctx,
+				 unsigned int pos,
+				 unsigned int nr_entries,
+				 unsigned int count)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	struct pblk_rb_entry *entry;
+	struct page *page;
+	unsigned int pad = 0, read = 0, to_read = nr_entries;
+	unsigned int user_io = 0, gc_io = 0;
+	unsigned int i;
+	int flags;
+	int ret;
+
+	if (count < nr_entries) {
+		pad = nr_entries - count;
+		to_read = count;
+	}
+
+	c_ctx->sentry = pos;
+	c_ctx->nr_valid = to_read;
+	c_ctx->nr_padded = pad;
+
+	for (i = 0; i < to_read; i++) {
+		entry = &rb->entries[pos];
+
+		/* A write has been allowed into the buffer, but data is still
+		 * being copied to it. It is ok to busy wait.
+		 */
+try:
+		flags = READ_ONCE(entry->w_ctx.flags);
+		if (!(flags & PBLK_WRITTEN_DATA))
+			goto try;
+
+		if (flags & PBLK_IOTYPE_USER)
+			user_io++;
+		else if (flags & PBLK_IOTYPE_GC)
+			gc_io++;
+		else
+			WARN(1, "pblk: unknown IO type\n");
+
+		page = virt_to_page(entry->data);
+		if (!page) {
+			pr_err("pblk: could not allocate write bio page\n");
+			flags &= ~PBLK_WRITTEN_DATA;
+			flags |= PBLK_SUBMITTED_ENTRY;
+			/* Release flags on context. Protect from writes */
+			smp_store_release(&entry->w_ctx.flags, flags);
+			goto out;
+		}
+
+		ret = bio_add_page(bio, page, rb->seg_size, 0);
+		if (ret != rb->seg_size) {
+			pr_err("pblk: could not add page to write bio\n");
+			flags &= ~PBLK_WRITTEN_DATA;
+			flags |= PBLK_SUBMITTED_ENTRY;
+			/* Release flags on context. Protect from writes */
+			smp_store_release(&entry->w_ctx.flags, flags);
+			goto out;
+		}
+
+		if (flags & PBLK_FLUSH_ENTRY) {
+			unsigned int sync_point;
+
+			sync_point = READ_ONCE(rb->sync_point);
+			if (sync_point == pos) {
+				/* Protect syncs */
+				smp_store_release(&rb->sync_point, EMPTY_ENTRY);
+			}
+
+			flags &= ~PBLK_FLUSH_ENTRY;
+#ifdef CONFIG_NVM_DEBUG
+			atomic_dec(&rb->inflight_sync_point);
+#endif
+		}
+
+		flags &= ~PBLK_WRITTEN_DATA;
+		flags |= PBLK_SUBMITTED_ENTRY;
+
+		/* Release flags on context. Protect from writes */
+		smp_store_release(&entry->w_ctx.flags, flags);
+
+		pos = (pos + 1) & (rb->nr_entries - 1);
+	}
+
+	read = to_read;
+	pblk_rl_out(&pblk->rl, user_io, gc_io);
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(pad, &((struct pblk *)
+			(container_of(rb, struct pblk, rwb)))->padded_writes);
+#endif
+out:
+	return read;
+}
+
+/*
+ * Copy to bio only if the lba matches the one on the given cache entry.
+ * Otherwise, it means that the entry has been overwritten, and the bio should
+ * be directed to disk.
+ */
+int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
+			u64 pos, int bio_iter)
+{
+	struct pblk_rb_entry *entry;
+	struct pblk_w_ctx *w_ctx;
+	void *data;
+	int flags;
+	int ret = 1;
+
+	spin_lock(&rb->w_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+	/* Caller must ensure that the access will not cause an overflow */
+	BUG_ON(pos >= rb->nr_entries);
+#endif
+	entry = &rb->entries[pos];
+	w_ctx = &entry->w_ctx;
+	flags = READ_ONCE(w_ctx->flags);
+
+	/* Check if the entry has been overwritten or is scheduled to be */
+	if (w_ctx->lba != lba || flags & PBLK_WRITABLE_ENTRY) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Only advance the bio if it hasn't been advanced already. If advanced,
+	 * this bio is at least a partial bio (i.e., it has partially been
+	 * filled with data from the cache). If part of the data resides on the
+	 * media, we will read later on
+	 */
+	if (unlikely(!bio->bi_iter.bi_idx))
+		bio_advance(bio, bio_iter * PBLK_EXPOSED_PAGE_SIZE);
+
+	data = bio_data(bio);
+	memcpy(data, entry->data, rb->seg_size);
+
+out:
+	spin_unlock(&rb->w_lock);
+	return ret;
+}
+
+struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos)
+{
+	unsigned int entry = pos & (rb->nr_entries - 1);
+
+	return &rb->entries[entry].w_ctx;
+}
+
+unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags)
+	__acquires(&rb->s_lock)
+{
+	if (flags)
+		spin_lock_irqsave(&rb->s_lock, *flags);
+	else
+		spin_lock_irq(&rb->s_lock);
+
+	return rb->sync;
+}
+
+void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags)
+	__releases(&rb->s_lock)
+{
+	lockdep_assert_held(&rb->s_lock);
+
+	if (flags)
+		spin_unlock_irqrestore(&rb->s_lock, *flags);
+	else
+		spin_unlock_irq(&rb->s_lock);
+}
+
+unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries)
+{
+	unsigned int sync;
+	unsigned int i;
+
+	lockdep_assert_held(&rb->s_lock);
+
+	sync = READ_ONCE(rb->sync);
+
+	for (i = 0; i < nr_entries; i++)
+		sync = (sync + 1) & (rb->nr_entries - 1);
+
+	/* Protect from counts */
+	smp_store_release(&rb->sync, sync);
+
+	return sync;
+}
+
+unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb)
+{
+	unsigned int subm, sync_point;
+	unsigned int count;
+
+	/* Protect syncs */
+	sync_point = smp_load_acquire(&rb->sync_point);
+	if (sync_point == EMPTY_ENTRY)
+		return 0;
+
+	subm = READ_ONCE(rb->subm);
+
+	/* The sync point itself counts as a sector to sync */
+	count = pblk_rb_ring_count(sync_point, subm, rb->nr_entries) + 1;
+
+	return count;
+}
+
+/*
+ * Scan from the current position of the sync pointer to find the entry that
+ * corresponds to the given ppa. This is necessary since write requests can be
+ * completed out of order. The assumption is that the ppa is close to the sync
+ * pointer thus the search will not take long.
+ *
+ * The caller of this function must guarantee that the sync pointer will no
+ * reach the entry while it is using the metadata associated with it. With this
+ * assumption in mind, there is no need to take the sync lock.
+ */
+struct pblk_rb_entry *pblk_rb_sync_scan_entry(struct pblk_rb *rb,
+					      struct ppa_addr *ppa)
+{
+	unsigned int sync, subm, count;
+	unsigned int i;
+
+	sync = READ_ONCE(rb->sync);
+	subm = READ_ONCE(rb->subm);
+	count = pblk_rb_ring_count(subm, sync, rb->nr_entries);
+
+	for (i = 0; i < count; i++)
+		sync = (sync + 1) & (rb->nr_entries - 1);
+
+	return NULL;
+}
+
+int pblk_rb_tear_down_check(struct pblk_rb *rb)
+{
+	struct pblk_rb_entry *entry;
+	int i;
+	int ret = 0;
+
+	spin_lock(&rb->w_lock);
+	spin_lock_irq(&rb->s_lock);
+
+	if ((rb->mem == rb->subm) && (rb->subm == rb->sync) &&
+				(rb->sync == rb->l2p_update) &&
+				(rb->sync_point == EMPTY_ENTRY)) {
+		goto out;
+	}
+
+	if (!rb->entries) {
+		ret = 1;
+		goto out;
+	}
+
+	for (i = 0; i < rb->nr_entries; i++) {
+		entry = &rb->entries[i];
+
+		if (!entry->data) {
+			ret = 1;
+			goto out;
+		}
+	}
+
+out:
+	spin_unlock(&rb->w_lock);
+	spin_unlock_irq(&rb->s_lock);
+
+	return ret;
+}
+
+unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos)
+{
+	return (pos & (rb->nr_entries - 1));
+}
+
+int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos)
+{
+	return (pos >= rb->nr_entries);
+}
+
+ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
+{
+	struct pblk *pblk = container_of(rb, struct pblk, rwb);
+	struct pblk_c_ctx *c;
+	ssize_t offset;
+	int queued_entries = 0;
+
+	spin_lock_irq(&rb->s_lock);
+	list_for_each_entry(c, &pblk->compl_list, list)
+		queued_entries++;
+	spin_unlock_irq(&rb->s_lock);
+
+	if (rb->sync_point != EMPTY_ENTRY)
+		offset = scnprintf(buf, PAGE_SIZE,
+			"%u\t%u\t%u\t%u\t%u\t%u\t%u - %u/%u/%u - %d\n",
+			rb->nr_entries,
+			rb->mem,
+			rb->subm,
+			rb->sync,
+			rb->l2p_update,
+#ifdef CONFIG_NVM_DEBUG
+			atomic_read(&rb->inflight_sync_point),
+#else
+			0,
+#endif
+			rb->sync_point,
+			pblk_rb_read_count(rb),
+			pblk_rb_space(rb),
+			pblk_rb_sync_point_count(rb),
+			queued_entries);
+	else
+		offset = scnprintf(buf, PAGE_SIZE,
+			"%u\t%u\t%u\t%u\t%u\t%u\tNULL - %u/%u/%u - %d\n",
+			rb->nr_entries,
+			rb->mem,
+			rb->subm,
+			rb->sync,
+			rb->l2p_update,
+#ifdef CONFIG_NVM_DEBUG
+			atomic_read(&rb->inflight_sync_point),
+#else
+			0,
+#endif
+			pblk_rb_read_count(rb),
+			pblk_rb_space(rb),
+			pblk_rb_sync_point_count(rb),
+			queued_entries);
+
+	return offset;
+}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
new file mode 100644
index 000000000000..4a12f14d78c6
--- /dev/null
+++ b/drivers/lightnvm/pblk-read.c
@@ -0,0 +1,529 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-read.c - pblk's read path
+ */
+
+#include "pblk.h"
+
+/*
+ * There is no guarantee that the value read from cache has not been updated and
+ * resides at another location in the cache. We guarantee though that if the
+ * value is read from the cache, it belongs to the mapped lba. In order to
+ * guarantee and order between writes and reads are ordered, a flush must be
+ * issued.
+ */
+static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
+				sector_t lba, struct ppa_addr ppa,
+				int bio_iter)
+{
+#ifdef CONFIG_NVM_DEBUG
+	/* Callers must ensure that the ppa points to a cache address */
+	BUG_ON(pblk_ppa_empty(ppa));
+	BUG_ON(!pblk_addr_in_cache(ppa));
+#endif
+
+	return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba,
+					pblk_addr_to_cacheline(ppa), bio_iter);
+}
+
+static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
+				 unsigned long *read_bitmap)
+{
+	struct bio *bio = rqd->bio;
+	struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
+	sector_t blba = pblk_get_lba(bio);
+	int nr_secs = rqd->nr_ppas;
+	int advanced_bio = 0;
+	int i, j = 0;
+
+	/* logic error: lba out-of-bounds. Ignore read request */
+	if (blba + nr_secs >= pblk->rl.nr_secs) {
+		WARN(1, "pblk: read lbas out of bounds\n");
+		return;
+	}
+
+	pblk_lookup_l2p_seq(pblk, ppas, blba, nr_secs);
+
+	for (i = 0; i < nr_secs; i++) {
+		struct ppa_addr p = ppas[i];
+		sector_t lba = blba + i;
+
+retry:
+		if (pblk_ppa_empty(p)) {
+			WARN_ON(test_and_set_bit(i, read_bitmap));
+			continue;
+		}
+
+		/* Try to read from write buffer. The address is later checked
+		 * on the write buffer to prevent retrieving overwritten data.
+		 */
+		if (pblk_addr_in_cache(p)) {
+			if (!pblk_read_from_cache(pblk, bio, lba, p, i)) {
+				pblk_lookup_l2p_seq(pblk, &p, lba, 1);
+				goto retry;
+			}
+			WARN_ON(test_and_set_bit(i, read_bitmap));
+			advanced_bio = 1;
+		} else {
+			/* Read from media non-cached sectors */
+			rqd->ppa_list[j++] = p;
+		}
+
+		if (advanced_bio)
+			bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(nr_secs, &pblk->inflight_reads);
+#endif
+}
+
+static int pblk_submit_read_io(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	int err;
+
+	rqd->flags = pblk_set_read_mode(pblk);
+
+	err = pblk_submit_io(pblk, rqd);
+	if (err)
+		return NVM_IO_ERR;
+
+	return NVM_IO_OK;
+}
+
+static void pblk_end_io_read(struct nvm_rq *rqd)
+{
+	struct pblk *pblk = rqd->private;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct bio *bio = rqd->bio;
+
+	if (rqd->error)
+		pblk_log_read_err(pblk, rqd);
+#ifdef CONFIG_NVM_DEBUG
+	else
+		WARN_ONCE(bio->bi_error, "pblk: corrupted read error\n");
+#endif
+
+	if (rqd->nr_ppas > 1)
+		nvm_dev_dma_free(dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
+
+	bio_put(bio);
+	if (r_ctx->orig_bio) {
+#ifdef CONFIG_NVM_DEBUG
+		WARN_ONCE(r_ctx->orig_bio->bi_error,
+						"pblk: corrupted read bio\n");
+#endif
+		bio_endio(r_ctx->orig_bio);
+		bio_put(r_ctx->orig_bio);
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
+	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
+#endif
+
+	pblk_free_rqd(pblk, rqd, READ);
+}
+
+static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+				      unsigned int bio_init_idx,
+				      unsigned long *read_bitmap)
+{
+	struct bio *new_bio, *bio = rqd->bio;
+	struct bio_vec src_bv, dst_bv;
+	void *ppa_ptr = NULL;
+	void *src_p, *dst_p;
+	dma_addr_t dma_ppa_list = 0;
+	int nr_secs = rqd->nr_ppas;
+	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+	int i, ret, hole;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+	if (!new_bio) {
+		pr_err("pblk: could not alloc read bio\n");
+		return NVM_IO_ERR;
+	}
+
+	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+		goto err;
+
+	if (nr_holes != new_bio->bi_vcnt) {
+		pr_err("pblk: malformed bio\n");
+		goto err;
+	}
+
+	new_bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+	new_bio->bi_private = &wait;
+	new_bio->bi_end_io = pblk_end_bio_sync;
+
+	rqd->bio = new_bio;
+	rqd->nr_ppas = nr_holes;
+	rqd->end_io = NULL;
+
+	if (unlikely(nr_secs > 1 && nr_holes == 1)) {
+		ppa_ptr = rqd->ppa_list;
+		dma_ppa_list = rqd->dma_ppa_list;
+		rqd->ppa_addr = rqd->ppa_list[0];
+	}
+
+	ret = pblk_submit_read_io(pblk, rqd);
+	if (ret) {
+		bio_put(rqd->bio);
+		pr_err("pblk: read IO submission failed\n");
+		goto err;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: partial read I/O timed out\n");
+	}
+
+	if (rqd->error) {
+		atomic_long_inc(&pblk->read_failed);
+#ifdef CONFIG_NVM_DEBUG
+		pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+	}
+
+	if (unlikely(nr_secs > 1 && nr_holes == 1)) {
+		rqd->ppa_list = ppa_ptr;
+		rqd->dma_ppa_list = dma_ppa_list;
+	}
+
+	/* Fill the holes in the original bio */
+	i = 0;
+	hole = find_first_zero_bit(read_bitmap, nr_secs);
+	do {
+		src_bv = new_bio->bi_io_vec[i++];
+		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+
+		src_p = kmap_atomic(src_bv.bv_page);
+		dst_p = kmap_atomic(dst_bv.bv_page);
+
+		memcpy(dst_p + dst_bv.bv_offset,
+			src_p + src_bv.bv_offset,
+			PBLK_EXPOSED_PAGE_SIZE);
+
+		kunmap_atomic(src_p);
+		kunmap_atomic(dst_p);
+
+		mempool_free(src_bv.bv_page, pblk->page_pool);
+
+		hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
+	} while (hole < nr_secs);
+
+	bio_put(new_bio);
+
+	/* Complete the original bio and associated request */
+	rqd->bio = bio;
+	rqd->nr_ppas = nr_secs;
+	rqd->private = pblk;
+
+	bio_endio(bio);
+	pblk_end_io_read(rqd);
+	return NVM_IO_OK;
+
+err:
+	/* Free allocated pages in new bio */
+	pblk_bio_free_pages(pblk, bio, 0, new_bio->bi_vcnt);
+	rqd->private = pblk;
+	pblk_end_io_read(rqd);
+	return NVM_IO_ERR;
+}
+
+static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd,
+			 unsigned long *read_bitmap)
+{
+	struct bio *bio = rqd->bio;
+	struct ppa_addr ppa;
+	sector_t lba = pblk_get_lba(bio);
+
+	/* logic error: lba out-of-bounds. Ignore read request */
+	if (lba >= pblk->rl.nr_secs) {
+		WARN(1, "pblk: read lba out of bounds\n");
+		return;
+	}
+
+	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_inc(&pblk->inflight_reads);
+#endif
+
+retry:
+	if (pblk_ppa_empty(ppa)) {
+		WARN_ON(test_and_set_bit(0, read_bitmap));
+		return;
+	}
+
+	/* Try to read from write buffer. The address is later checked on the
+	 * write buffer to prevent retrieving overwritten data.
+	 */
+	if (pblk_addr_in_cache(ppa)) {
+		if (!pblk_read_from_cache(pblk, bio, lba, ppa, 0)) {
+			pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
+			goto retry;
+		}
+		WARN_ON(test_and_set_bit(0, read_bitmap));
+	} else {
+		rqd->ppa_addr = ppa;
+	}
+}
+
+int pblk_submit_read(struct pblk *pblk, struct bio *bio)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	unsigned int nr_secs = pblk_get_secs(bio);
+	struct nvm_rq *rqd;
+	unsigned long read_bitmap; /* Max 64 ppas per request */
+	unsigned int bio_init_idx;
+	int ret = NVM_IO_ERR;
+
+	if (nr_secs > PBLK_MAX_REQ_ADDRS)
+		return NVM_IO_ERR;
+
+	bitmap_zero(&read_bitmap, nr_secs);
+
+	rqd = pblk_alloc_rqd(pblk, READ);
+	if (IS_ERR(rqd)) {
+		pr_err_ratelimited("pblk: not able to alloc rqd");
+		return NVM_IO_ERR;
+	}
+
+	rqd->opcode = NVM_OP_PREAD;
+	rqd->bio = bio;
+	rqd->nr_ppas = nr_secs;
+	rqd->private = pblk;
+	rqd->end_io = pblk_end_io_read;
+
+	/* Save the index for this bio's start. This is needed in case
+	 * we need to fill a partial read.
+	 */
+	bio_init_idx = pblk_get_bi_idx(bio);
+
+	if (nr_secs > 1) {
+		rqd->ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+						&rqd->dma_ppa_list);
+		if (!rqd->ppa_list) {
+			pr_err("pblk: not able to allocate ppa list\n");
+			goto fail_rqd_free;
+		}
+
+		pblk_read_ppalist_rq(pblk, rqd, &read_bitmap);
+	} else {
+		pblk_read_rq(pblk, rqd, &read_bitmap);
+	}
+
+	bio_get(bio);
+	if (bitmap_full(&read_bitmap, nr_secs)) {
+		bio_endio(bio);
+		pblk_end_io_read(rqd);
+		return NVM_IO_OK;
+	}
+
+	/* All sectors are to be read from the device */
+	if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+		struct bio *int_bio = NULL;
+		struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+
+		/* Clone read bio to deal with read errors internally */
+		int_bio = bio_clone_bioset(bio, GFP_KERNEL, fs_bio_set);
+		if (!int_bio) {
+			pr_err("pblk: could not clone read bio\n");
+			return NVM_IO_ERR;
+		}
+
+		rqd->bio = int_bio;
+		r_ctx->orig_bio = bio;
+
+		ret = pblk_submit_read_io(pblk, rqd);
+		if (ret) {
+			pr_err("pblk: read IO submission failed\n");
+			if (int_bio)
+				bio_put(int_bio);
+			return ret;
+		}
+
+		return NVM_IO_OK;
+	}
+
+	/* The read bio request could be partially filled by the write buffer,
+	 * but there are some holes that need to be read from the drive.
+	 */
+	ret = pblk_fill_partial_read_bio(pblk, rqd, bio_init_idx, &read_bitmap);
+	if (ret) {
+		pr_err("pblk: failed to perform partial read\n");
+		return ret;
+	}
+
+	return NVM_IO_OK;
+
+fail_rqd_free:
+	pblk_free_rqd(pblk, rqd, READ);
+	return ret;
+}
+
+static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
+			      struct pblk_line *line, u64 *lba_list,
+			      unsigned int nr_secs)
+{
+	struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
+	int valid_secs = 0;
+	int i;
+
+	pblk_lookup_l2p_rand(pblk, ppas, lba_list, nr_secs);
+
+	for (i = 0; i < nr_secs; i++) {
+		if (pblk_addr_in_cache(ppas[i]) || ppas[i].g.blk != line->id ||
+						pblk_ppa_empty(ppas[i])) {
+			lba_list[i] = ADDR_EMPTY;
+			continue;
+		}
+
+		rqd->ppa_list[valid_secs++] = ppas[i];
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(valid_secs, &pblk->inflight_reads);
+#endif
+	return valid_secs;
+}
+
+static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
+		      struct pblk_line *line, sector_t lba)
+{
+	struct ppa_addr ppa;
+	int valid_secs = 0;
+
+	if (lba == ADDR_EMPTY)
+		goto out;
+
+	/* logic error: lba out-of-bounds */
+	if (lba >= pblk->rl.nr_secs) {
+		WARN(1, "pblk: read lba out of bounds\n");
+		goto out;
+	}
+
+	spin_lock(&pblk->trans_lock);
+	ppa = pblk_trans_map_get(pblk, lba);
+	spin_unlock(&pblk->trans_lock);
+
+	/* Ignore updated values until the moment */
+	if (pblk_addr_in_cache(ppa) || ppa.g.blk != line->id ||
+							pblk_ppa_empty(ppa))
+		goto out;
+
+	rqd->ppa_addr = ppa;
+	valid_secs = 1;
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_inc(&pblk->inflight_reads);
+#endif
+
+out:
+	return valid_secs;
+}
+
+int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
+			unsigned int nr_secs, unsigned int *secs_to_gc,
+			struct pblk_line *line)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct request_queue *q = dev->q;
+	struct bio *bio;
+	struct nvm_rq rqd;
+	int ret, data_len;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+
+	if (nr_secs > 1) {
+		rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+							&rqd.dma_ppa_list);
+		if (!rqd.ppa_list)
+			return NVM_IO_ERR;
+
+		*secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, line, lba_list,
+								nr_secs);
+		if (*secs_to_gc == 1) {
+			struct ppa_addr ppa;
+
+			ppa = rqd.ppa_list[0];
+			nvm_dev_dma_free(dev->parent, rqd.ppa_list,
+							rqd.dma_ppa_list);
+			rqd.ppa_addr = ppa;
+		}
+	} else {
+		*secs_to_gc = read_rq_gc(pblk, &rqd, line, lba_list[0]);
+	}
+
+	if (!(*secs_to_gc))
+		goto out;
+
+	data_len = (*secs_to_gc) * geo->sec_size;
+	bio = bio_map_kern(q, data, data_len, GFP_KERNEL);
+	if (IS_ERR(bio)) {
+		pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+		goto err_free_dma;
+	}
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+	rqd.opcode = NVM_OP_PREAD;
+	rqd.end_io = pblk_end_io_sync;
+	rqd.private = &wait;
+	rqd.nr_ppas = *secs_to_gc;
+	rqd.bio = bio;
+
+	ret = pblk_submit_read_io(pblk, &rqd);
+	if (ret) {
+		bio_endio(bio);
+		pr_err("pblk: GC read request failed\n");
+		goto err_free_dma;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: GC read I/O timed out\n");
+	}
+
+	if (rqd.error) {
+		atomic_long_inc(&pblk->read_failed_gc);
+#ifdef CONFIG_NVM_DEBUG
+		pblk_print_failed_rqd(pblk, &rqd, rqd.error);
+#endif
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(*secs_to_gc, &pblk->sync_reads);
+	atomic_long_add(*secs_to_gc, &pblk->recov_gc_reads);
+	atomic_long_sub(*secs_to_gc, &pblk->inflight_reads);
+#endif
+
+out:
+	if (rqd.nr_ppas > 1)
+		nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+	return NVM_IO_OK;
+
+err_free_dma:
+	if (rqd.nr_ppas > 1)
+		nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+	return NVM_IO_ERR;
+}
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
new file mode 100644
index 000000000000..f8f85087cd3c
--- /dev/null
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -0,0 +1,998 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-recovery.c - pblk's recovery path
+ */
+
+#include "pblk.h"
+
+void pblk_submit_rec(struct work_struct *work)
+{
+	struct pblk_rec_ctx *recovery =
+			container_of(work, struct pblk_rec_ctx, ws_rec);
+	struct pblk *pblk = recovery->pblk;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_rq *rqd = recovery->rqd;
+	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+	int max_secs = nvm_max_phys_sects(dev);
+	struct bio *bio;
+	unsigned int nr_rec_secs;
+	unsigned int pgs_read;
+	int ret;
+
+	nr_rec_secs = bitmap_weight((unsigned long int *)&rqd->ppa_status,
+								max_secs);
+
+	bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
+	if (!bio) {
+		pr_err("pblk: not able to create recovery bio\n");
+		return;
+	}
+
+	bio->bi_iter.bi_sector = 0;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+	rqd->bio = bio;
+	rqd->nr_ppas = nr_rec_secs;
+
+	pgs_read = pblk_rb_read_to_bio_list(&pblk->rwb, bio, &recovery->failed,
+								nr_rec_secs);
+	if (pgs_read != nr_rec_secs) {
+		pr_err("pblk: could not read recovery entries\n");
+		goto err;
+	}
+
+	if (pblk_setup_w_rec_rq(pblk, rqd, c_ctx)) {
+		pr_err("pblk: could not setup recovery request\n");
+		goto err;
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(nr_rec_secs, &pblk->recov_writes);
+#endif
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		pr_err("pblk: I/O submission failed: %d\n", ret);
+		goto err;
+	}
+
+	mempool_free(recovery, pblk->rec_pool);
+	return;
+
+err:
+	bio_put(bio);
+	pblk_free_rqd(pblk, rqd, WRITE);
+}
+
+int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
+			struct pblk_rec_ctx *recovery, u64 *comp_bits,
+			unsigned int comp)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	int max_secs = nvm_max_phys_sects(dev);
+	struct nvm_rq *rec_rqd;
+	struct pblk_c_ctx *rec_ctx;
+	int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
+
+	rec_rqd = pblk_alloc_rqd(pblk, WRITE);
+	if (IS_ERR(rec_rqd)) {
+		pr_err("pblk: could not create recovery req.\n");
+		return -ENOMEM;
+	}
+
+	rec_ctx = nvm_rq_to_pdu(rec_rqd);
+
+	/* Copy completion bitmap, but exclude the first X completed entries */
+	bitmap_shift_right((unsigned long int *)&rec_rqd->ppa_status,
+				(unsigned long int *)comp_bits,
+				comp, max_secs);
+
+	/* Save the context for the entries that need to be re-written and
+	 * update current context with the completed entries.
+	 */
+	rec_ctx->sentry = pblk_rb_wrap_pos(&pblk->rwb, c_ctx->sentry + comp);
+	if (comp >= c_ctx->nr_valid) {
+		rec_ctx->nr_valid = 0;
+		rec_ctx->nr_padded = nr_entries - comp;
+
+		c_ctx->nr_padded = comp - c_ctx->nr_valid;
+	} else {
+		rec_ctx->nr_valid = c_ctx->nr_valid - comp;
+		rec_ctx->nr_padded = c_ctx->nr_padded;
+
+		c_ctx->nr_valid = comp;
+		c_ctx->nr_padded = 0;
+	}
+
+	recovery->rqd = rec_rqd;
+	recovery->pblk = pblk;
+
+	return 0;
+}
+
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta)
+{
+	u32 crc;
+
+	crc = pblk_calc_emeta_crc(pblk, emeta);
+	if (le32_to_cpu(emeta->crc) != crc)
+		return NULL;
+
+	if (le32_to_cpu(emeta->header.identifier) != PBLK_MAGIC)
+		return NULL;
+
+	return pblk_line_emeta_to_lbas(emeta);
+}
+
+static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct line_emeta *emeta = line->emeta;
+	__le64 *lba_list;
+	int data_start;
+	int nr_data_lbas, nr_valid_lbas, nr_lbas = 0;
+	int i;
+
+	lba_list = pblk_recov_get_lba_list(pblk, emeta);
+	if (!lba_list)
+		return 1;
+
+	data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec;
+	nr_data_lbas = lm->sec_per_line - lm->emeta_sec;
+	nr_valid_lbas = le64_to_cpu(emeta->nr_valid_lbas);
+
+	for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) {
+		struct ppa_addr ppa;
+		int pos;
+
+		ppa = addr_to_pblk_ppa(pblk, i, line->id);
+		pos = pblk_ppa_to_pos(geo, ppa);
+
+		/* Do not update bad blocks */
+		if (test_bit(pos, line->blk_bitmap))
+			continue;
+
+		if (le64_to_cpu(lba_list[i]) == ADDR_EMPTY) {
+			spin_lock(&line->lock);
+			if (test_and_set_bit(i, line->invalid_bitmap))
+				WARN_ONCE(1, "pblk: rec. double invalidate:\n");
+			else
+				line->vsc--;
+			spin_unlock(&line->lock);
+
+			continue;
+		}
+
+		pblk_update_map(pblk, le64_to_cpu(lba_list[i]), ppa);
+		nr_lbas++;
+	}
+
+	if (nr_valid_lbas != nr_lbas)
+		pr_err("pblk: line %d - inconsistent lba list(%llu/%d)\n",
+				line->id, line->emeta->nr_valid_lbas, nr_lbas);
+
+	line->left_msecs = 0;
+
+	return 0;
+}
+
+static int pblk_calc_sec_in_line(struct pblk *pblk, struct pblk_line *line)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	int nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+
+	return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec -
+				nr_bb * geo->sec_per_blk;
+}
+
+struct pblk_recov_alloc {
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	struct nvm_rq *rqd;
+	void *data;
+	dma_addr_t dma_ppa_list;
+	dma_addr_t dma_meta_list;
+};
+
+static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line,
+			       struct pblk_recov_alloc p, u64 r_ptr)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	struct nvm_rq *rqd;
+	struct bio *bio;
+	void *data;
+	dma_addr_t dma_ppa_list, dma_meta_list;
+	u64 r_ptr_int;
+	int left_ppas;
+	int rq_ppas, rq_len;
+	int i, j;
+	int ret = 0;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	ppa_list = p.ppa_list;
+	meta_list = p.meta_list;
+	rqd = p.rqd;
+	data = p.data;
+	dma_ppa_list = p.dma_ppa_list;
+	dma_meta_list = p.dma_meta_list;
+
+	left_ppas = line->cur_sec - r_ptr;
+	if (!left_ppas)
+		return 0;
+
+	r_ptr_int = r_ptr;
+
+next_read_rq:
+	memset(rqd, 0, pblk_r_rq_size);
+
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	if (!rq_ppas)
+		rq_ppas = pblk->min_write_pgs;
+	rq_len = rq_ppas * geo->sec_size;
+
+	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+	rqd->bio = bio;
+	rqd->opcode = NVM_OP_PREAD;
+	rqd->flags = pblk_set_read_mode(pblk);
+	rqd->meta_list = meta_list;
+	rqd->nr_ppas = rq_ppas;
+	rqd->ppa_list = ppa_list;
+	rqd->dma_ppa_list = dma_ppa_list;
+	rqd->dma_meta_list = dma_meta_list;
+	rqd->end_io = pblk_end_io_sync;
+	rqd->private = &wait;
+
+	for (i = 0; i < rqd->nr_ppas; ) {
+		struct ppa_addr ppa;
+		int pos;
+
+		ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+		pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+		while (test_bit(pos, line->blk_bitmap)) {
+			r_ptr_int += pblk->min_write_pgs;
+			ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+			pos = pblk_dev_ppa_to_pos(geo, ppa);
+		}
+
+		for (j = 0; j < pblk->min_write_pgs; j++, i++, r_ptr_int++)
+			rqd->ppa_list[i] =
+				addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+	}
+
+	/* If read fails, more padding is needed */
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		pr_err("pblk: I/O submission failed: %d\n", ret);
+		return ret;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: L2P recovery read timed out\n");
+		return -EINTR;
+	}
+
+	reinit_completion(&wait);
+
+	/* At this point, the read should not fail. If it does, it is a problem
+	 * we cannot recover from here. Need FTL log.
+	 */
+	if (rqd->error) {
+		pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+		return -EINTR;
+	}
+
+	for (i = 0; i < rqd->nr_ppas; i++) {
+		u64 lba = le64_to_cpu(meta_list[i].lba);
+
+		if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+			continue;
+
+		pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+	}
+
+	left_ppas -= rq_ppas;
+	if (left_ppas > 0)
+		goto next_read_rq;
+
+	return 0;
+}
+
+static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
+			      struct pblk_recov_alloc p, int left_ppas)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	struct nvm_rq *rqd;
+	struct bio *bio;
+	void *data;
+	dma_addr_t dma_ppa_list, dma_meta_list;
+	__le64 *lba_list = pblk_line_emeta_to_lbas(line->emeta);
+	u64 w_ptr = line->cur_sec;
+	int left_line_ppas = line->left_msecs;
+	int rq_ppas, rq_len;
+	int i, j;
+	int ret = 0;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	ppa_list = p.ppa_list;
+	meta_list = p.meta_list;
+	rqd = p.rqd;
+	data = p.data;
+	dma_ppa_list = p.dma_ppa_list;
+	dma_meta_list = p.dma_meta_list;
+
+next_pad_rq:
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	if (!rq_ppas)
+		rq_ppas = pblk->min_write_pgs;
+	rq_len = rq_ppas * geo->sec_size;
+
+	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+	memset(rqd, 0, pblk_r_rq_size);
+
+	rqd->bio = bio;
+	rqd->opcode = NVM_OP_PWRITE;
+	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+	rqd->meta_list = meta_list;
+	rqd->nr_ppas = rq_ppas;
+	rqd->ppa_list = ppa_list;
+	rqd->dma_ppa_list = dma_ppa_list;
+	rqd->dma_meta_list = dma_meta_list;
+	rqd->end_io = pblk_end_io_sync;
+	rqd->private = &wait;
+
+	for (i = 0; i < rqd->nr_ppas; ) {
+		struct ppa_addr ppa;
+		int pos;
+
+		w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+		ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
+		pos = pblk_ppa_to_pos(geo, ppa);
+
+		while (test_bit(pos, line->blk_bitmap)) {
+			w_ptr += pblk->min_write_pgs;
+			ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
+			pos = pblk_ppa_to_pos(geo, ppa);
+		}
+
+		for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
+			struct ppa_addr dev_ppa;
+
+			dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+
+			pblk_map_invalidate(pblk, dev_ppa);
+			meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+			lba_list[w_ptr] = cpu_to_le64(ADDR_EMPTY);
+			rqd->ppa_list[i] = dev_ppa;
+		}
+	}
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		pr_err("pblk: I/O submission failed: %d\n", ret);
+		return ret;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: L2P recovery write timed out\n");
+	}
+	reinit_completion(&wait);
+
+	left_line_ppas -= rq_ppas;
+	left_ppas -= rq_ppas;
+	if (left_ppas > 0 && left_line_ppas)
+		goto next_pad_rq;
+
+	return 0;
+}
+
+/* When this function is called, it means that not all upper pages have been
+ * written in a page that contains valid data. In order to recover this data, we
+ * first find the write pointer on the device, then we pad all necessary
+ * sectors, and finally attempt to read the valid data
+ */
+static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line,
+				   struct pblk_recov_alloc p)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	struct nvm_rq *rqd;
+	struct bio *bio;
+	void *data;
+	dma_addr_t dma_ppa_list, dma_meta_list;
+	u64 w_ptr = 0, r_ptr;
+	int rq_ppas, rq_len;
+	int i, j;
+	int ret = 0;
+	int rec_round;
+	int left_ppas = pblk_calc_sec_in_line(pblk, line) - line->cur_sec;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	ppa_list = p.ppa_list;
+	meta_list = p.meta_list;
+	rqd = p.rqd;
+	data = p.data;
+	dma_ppa_list = p.dma_ppa_list;
+	dma_meta_list = p.dma_meta_list;
+
+	/* we could recover up until the line write pointer */
+	r_ptr = line->cur_sec;
+	rec_round = 0;
+
+next_rq:
+	memset(rqd, 0, pblk_r_rq_size);
+
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	if (!rq_ppas)
+		rq_ppas = pblk->min_write_pgs;
+	rq_len = rq_ppas * geo->sec_size;
+
+	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+	rqd->bio = bio;
+	rqd->opcode = NVM_OP_PREAD;
+	rqd->flags = pblk_set_read_mode(pblk);
+	rqd->meta_list = meta_list;
+	rqd->nr_ppas = rq_ppas;
+	rqd->ppa_list = ppa_list;
+	rqd->dma_ppa_list = dma_ppa_list;
+	rqd->dma_meta_list = dma_meta_list;
+	rqd->end_io = pblk_end_io_sync;
+	rqd->private = &wait;
+
+	for (i = 0; i < rqd->nr_ppas; ) {
+		struct ppa_addr ppa;
+		int pos;
+
+		w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+		ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+		pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+		while (test_bit(pos, line->blk_bitmap)) {
+			w_ptr += pblk->min_write_pgs;
+			ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+			pos = pblk_dev_ppa_to_pos(geo, ppa);
+		}
+
+		for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++)
+			rqd->ppa_list[i] =
+				addr_to_gen_ppa(pblk, w_ptr, line->id);
+	}
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		pr_err("pblk: I/O submission failed: %d\n", ret);
+		return ret;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: L2P recovery read timed out\n");
+	}
+	reinit_completion(&wait);
+
+	/* This should not happen since the read failed during normal recovery,
+	 * but the media works funny sometimes...
+	 */
+	if (!rec_round++ && !rqd->error) {
+		rec_round = 0;
+		for (i = 0; i < rqd->nr_ppas; i++, r_ptr++) {
+			u64 lba = le64_to_cpu(meta_list[i].lba);
+
+			if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+				continue;
+
+			pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+		}
+	}
+
+	/* Reached the end of the written line */
+	if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
+		int pad_secs, nr_error_bits, bit;
+		int ret;
+
+		bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
+		nr_error_bits = rqd->nr_ppas - bit;
+
+		/* Roll back failed sectors */
+		line->cur_sec -= nr_error_bits;
+		line->left_msecs += nr_error_bits;
+		bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+
+		pad_secs = pblk_pad_distance(pblk);
+		if (pad_secs > line->left_msecs)
+			pad_secs = line->left_msecs;
+
+		ret = pblk_recov_pad_oob(pblk, line, p, pad_secs);
+		if (ret)
+			pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+
+		ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
+		if (ret)
+			pr_err("pblk: OOB read failed (err:%d)\n", ret);
+
+		line->left_ssecs = line->left_msecs;
+		left_ppas = 0;
+	}
+
+	left_ppas -= rq_ppas;
+	if (left_ppas > 0)
+		goto next_rq;
+
+	return ret;
+}
+
+static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
+			       struct pblk_recov_alloc p, int *done)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	struct nvm_rq *rqd;
+	struct bio *bio;
+	void *data;
+	dma_addr_t dma_ppa_list, dma_meta_list;
+	u64 paddr;
+	int rq_ppas, rq_len;
+	int i, j;
+	int ret = 0;
+	int left_ppas = pblk_calc_sec_in_line(pblk, line);
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	ppa_list = p.ppa_list;
+	meta_list = p.meta_list;
+	rqd = p.rqd;
+	data = p.data;
+	dma_ppa_list = p.dma_ppa_list;
+	dma_meta_list = p.dma_meta_list;
+
+	*done = 1;
+
+next_rq:
+	memset(rqd, 0, pblk_r_rq_size);
+
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	if (!rq_ppas)
+		rq_ppas = pblk->min_write_pgs;
+	rq_len = rq_ppas * geo->sec_size;
+
+	bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+	rqd->bio = bio;
+	rqd->opcode = NVM_OP_PREAD;
+	rqd->flags = pblk_set_read_mode(pblk);
+	rqd->meta_list = meta_list;
+	rqd->nr_ppas = rq_ppas;
+	rqd->ppa_list = ppa_list;
+	rqd->dma_ppa_list = dma_ppa_list;
+	rqd->dma_meta_list = dma_meta_list;
+	rqd->end_io = pblk_end_io_sync;
+	rqd->private = &wait;
+
+	for (i = 0; i < rqd->nr_ppas; ) {
+		struct ppa_addr ppa;
+		int pos;
+
+		paddr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+		ppa = addr_to_gen_ppa(pblk, paddr, line->id);
+		pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+		while (test_bit(pos, line->blk_bitmap)) {
+			paddr += pblk->min_write_pgs;
+			ppa = addr_to_gen_ppa(pblk, paddr, line->id);
+			pos = pblk_dev_ppa_to_pos(geo, ppa);
+		}
+
+		for (j = 0; j < pblk->min_write_pgs; j++, i++, paddr++)
+			rqd->ppa_list[i] =
+				addr_to_gen_ppa(pblk, paddr, line->id);
+	}
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		pr_err("pblk: I/O submission failed: %d\n", ret);
+		bio_put(bio);
+		return ret;
+	}
+
+	if (!wait_for_completion_io_timeout(&wait,
+				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+		pr_err("pblk: L2P recovery read timed out\n");
+	}
+	reinit_completion(&wait);
+
+	/* Reached the end of the written line */
+	if (rqd->error) {
+		int nr_error_bits, bit;
+
+		bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
+		nr_error_bits = rqd->nr_ppas - bit;
+
+		/* Roll back failed sectors */
+		line->cur_sec -= nr_error_bits;
+		line->left_msecs += nr_error_bits;
+		line->left_ssecs = line->left_msecs;
+		bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+
+		left_ppas = 0;
+		rqd->nr_ppas = bit;
+
+		if (rqd->error != NVM_RSP_ERR_EMPTYPAGE)
+			*done = 0;
+	}
+
+	for (i = 0; i < rqd->nr_ppas; i++) {
+		u64 lba = le64_to_cpu(meta_list[i].lba);
+
+		if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+			continue;
+
+		pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+	}
+
+	left_ppas -= rq_ppas;
+	if (left_ppas > 0)
+		goto next_rq;
+
+	return ret;
+}
+
+/* Scan line for lbas on out of bound area */
+static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_rq *rqd;
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	struct pblk_recov_alloc p;
+	void *data;
+	dma_addr_t dma_ppa_list, dma_meta_list;
+	int done, ret = 0;
+
+	rqd = pblk_alloc_rqd(pblk, READ);
+	if (IS_ERR(rqd))
+		return PTR_ERR(rqd);
+
+	meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+	if (!meta_list) {
+		ret = -ENOMEM;
+		goto free_rqd;
+	}
+
+	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+	data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto free_meta_list;
+	}
+
+	p.ppa_list = ppa_list;
+	p.meta_list = meta_list;
+	p.rqd = rqd;
+	p.data = data;
+	p.dma_ppa_list = dma_ppa_list;
+	p.dma_meta_list = dma_meta_list;
+
+	ret = pblk_recov_scan_oob(pblk, line, p, &done);
+	if (ret) {
+		pr_err("pblk: could not recover L2P from OOB\n");
+		goto out;
+	}
+
+	if (!done) {
+		ret = pblk_recov_scan_all_oob(pblk, line, p);
+		if (ret) {
+			pr_err("pblk: could not recover L2P from OOB\n");
+			goto out;
+		}
+	}
+
+	if (pblk_line_is_full(line))
+		pblk_line_recov_close(pblk, line);
+
+out:
+	kfree(data);
+free_meta_list:
+	nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+free_rqd:
+	pblk_free_rqd(pblk, rqd, READ);
+
+	return ret;
+}
+
+/* Insert lines ordered by sequence number (seq_num) on list */
+static void pblk_recov_line_add_ordered(struct list_head *head,
+					struct pblk_line *line)
+{
+	struct pblk_line *t = NULL;
+
+	list_for_each_entry(t, head, list)
+		if (t->seq_nr > line->seq_nr)
+			break;
+
+	__list_add(&line->list, t->list.prev, &t->list);
+}
+
+struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *line, *tline, *data_line = NULL;
+	struct line_smeta *smeta;
+	struct line_emeta *emeta;
+	int found_lines = 0, recovered_lines = 0, open_lines = 0;
+	int is_next = 0;
+	int meta_line;
+	int i, valid_uuid = 0;
+	LIST_HEAD(recov_list);
+
+	/* TODO: Implement FTL snapshot */
+
+	/* Scan recovery - takes place when FTL snapshot fails */
+	spin_lock(&l_mg->free_lock);
+	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+	set_bit(meta_line, &l_mg->meta_bitmap);
+	smeta = l_mg->sline_meta[meta_line].meta;
+	emeta = l_mg->eline_meta[meta_line].meta;
+	spin_unlock(&l_mg->free_lock);
+
+	/* Order data lines using their sequence number */
+	for (i = 0; i < l_mg->nr_lines; i++) {
+		u32 crc;
+
+		line = &pblk->lines[i];
+
+		memset(smeta, 0, lm->smeta_len);
+		line->smeta = smeta;
+		line->lun_bitmap = ((void *)(smeta)) +
+						sizeof(struct line_smeta);
+
+		/* Lines that cannot be read are assumed as not written here */
+		if (pblk_line_read_smeta(pblk, line))
+			continue;
+
+		crc = pblk_calc_smeta_crc(pblk, smeta);
+		if (le32_to_cpu(smeta->crc) != crc)
+			continue;
+
+		if (le32_to_cpu(smeta->header.identifier) != PBLK_MAGIC)
+			continue;
+
+		if (le16_to_cpu(smeta->header.version) != 1) {
+			pr_err("pblk: found incompatible line version %u\n",
+					smeta->header.version);
+			return ERR_PTR(-EINVAL);
+		}
+
+		/* The first valid instance uuid is used for initialization */
+		if (!valid_uuid) {
+			memcpy(pblk->instance_uuid, smeta->header.uuid, 16);
+			valid_uuid = 1;
+		}
+
+		if (memcmp(pblk->instance_uuid, smeta->header.uuid, 16)) {
+			pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+					i);
+			continue;
+		}
+
+		/* Update line metadata */
+		spin_lock(&line->lock);
+		line->id = le32_to_cpu(line->smeta->header.id);
+		line->type = le16_to_cpu(line->smeta->header.type);
+		line->seq_nr = le64_to_cpu(line->smeta->seq_nr);
+		spin_unlock(&line->lock);
+
+		/* Update general metadata */
+		spin_lock(&l_mg->free_lock);
+		if (line->seq_nr >= l_mg->d_seq_nr)
+			l_mg->d_seq_nr = line->seq_nr + 1;
+		l_mg->nr_free_lines--;
+		spin_unlock(&l_mg->free_lock);
+
+		if (pblk_line_recov_alloc(pblk, line))
+			goto out;
+
+		pblk_recov_line_add_ordered(&recov_list, line);
+		found_lines++;
+		pr_debug("pblk: recovering data line %d, seq:%llu\n",
+						line->id, smeta->seq_nr);
+	}
+
+	if (!found_lines) {
+		pblk_setup_uuid(pblk);
+
+		spin_lock(&l_mg->free_lock);
+		WARN_ON_ONCE(!test_and_clear_bit(meta_line,
+							&l_mg->meta_bitmap));
+		spin_unlock(&l_mg->free_lock);
+
+		goto out;
+	}
+
+	/* Verify closed blocks and recover this portion of L2P table*/
+	list_for_each_entry_safe(line, tline, &recov_list, list) {
+		int off, nr_bb;
+
+		recovered_lines++;
+		/* Calculate where emeta starts based on the line bb */
+		off = lm->sec_per_line - lm->emeta_sec;
+		nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+		off -= nr_bb * geo->sec_per_pl;
+
+		memset(emeta, 0, lm->emeta_len);
+		line->emeta = emeta;
+		line->emeta_ssec = off;
+
+		if (pblk_line_read_emeta(pblk, line)) {
+			pblk_recov_l2p_from_oob(pblk, line);
+			goto next;
+		}
+
+		if (pblk_recov_l2p_from_emeta(pblk, line))
+			pblk_recov_l2p_from_oob(pblk, line);
+
+next:
+		if (pblk_line_is_full(line)) {
+			struct list_head *move_list;
+
+			spin_lock(&line->lock);
+			line->state = PBLK_LINESTATE_CLOSED;
+			move_list = pblk_line_gc_list(pblk, line);
+			spin_unlock(&line->lock);
+
+			spin_lock(&l_mg->gc_lock);
+			list_move_tail(&line->list, move_list);
+			spin_unlock(&l_mg->gc_lock);
+
+			mempool_free(line->map_bitmap, pblk->line_meta_pool);
+			line->map_bitmap = NULL;
+			line->smeta = NULL;
+			line->emeta = NULL;
+		} else {
+			if (open_lines > 1)
+				pr_err("pblk: failed to recover L2P\n");
+
+			open_lines++;
+			line->meta_line = meta_line;
+			data_line = line;
+		}
+	}
+
+	spin_lock(&l_mg->free_lock);
+	if (!open_lines) {
+		WARN_ON_ONCE(!test_and_clear_bit(meta_line,
+							&l_mg->meta_bitmap));
+		pblk_line_replace_data(pblk);
+	} else {
+		/* Allocate next line for preparation */
+		l_mg->data_next = pblk_line_get(pblk);
+		if (l_mg->data_next) {
+			l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+			l_mg->data_next->type = PBLK_LINETYPE_DATA;
+			is_next = 1;
+		}
+	}
+	spin_unlock(&l_mg->free_lock);
+
+	if (is_next) {
+		pblk_line_erase(pblk, l_mg->data_next);
+		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+	}
+
+out:
+	if (found_lines != recovered_lines)
+		pr_err("pblk: failed to recover all found lines %d/%d\n",
+						found_lines, recovered_lines);
+
+	return data_line;
+}
+
+/*
+ * Pad until smeta can be read on current data line
+ */
+void pblk_recov_pad(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line *line;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct nvm_rq *rqd;
+	struct pblk_recov_alloc p;
+	struct ppa_addr *ppa_list;
+	struct pblk_sec_meta *meta_list;
+	void *data;
+	dma_addr_t dma_ppa_list, dma_meta_list;
+
+	spin_lock(&l_mg->free_lock);
+	line = l_mg->data_line;
+	spin_unlock(&l_mg->free_lock);
+
+	rqd = pblk_alloc_rqd(pblk, READ);
+	if (IS_ERR(rqd))
+		return;
+
+	meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+	if (!meta_list)
+		goto free_rqd;
+
+	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+	data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
+	if (!data)
+		goto free_meta_list;
+
+	p.ppa_list = ppa_list;
+	p.meta_list = meta_list;
+	p.rqd = rqd;
+	p.data = data;
+	p.dma_ppa_list = dma_ppa_list;
+	p.dma_meta_list = dma_meta_list;
+
+	if (pblk_recov_pad_oob(pblk, line, p, line->left_msecs)) {
+		pr_err("pblk: Tear down padding failed\n");
+		goto free_data;
+	}
+
+	pblk_line_close(pblk, line);
+
+free_data:
+	kfree(data);
+free_meta_list:
+	nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+free_rqd:
+	pblk_free_rqd(pblk, rqd, READ);
+}
diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
new file mode 100644
index 000000000000..ab7cbb144f3f
--- /dev/null
+++ b/drivers/lightnvm/pblk-rl.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-rl.c - pblk's rate limiter for user I/O
+ *
+ */
+
+#include "pblk.h"
+
+static void pblk_rl_kick_u_timer(struct pblk_rl *rl)
+{
+	mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000));
+}
+
+int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries)
+{
+	int rb_user_cnt = atomic_read(&rl->rb_user_cnt);
+
+	return (!(rb_user_cnt + nr_entries > rl->rb_user_max));
+}
+
+int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries)
+{
+	int rb_gc_cnt = atomic_read(&rl->rb_gc_cnt);
+	int rb_user_active;
+
+	/* If there is no user I/O let GC take over space on the write buffer */
+	rb_user_active = READ_ONCE(rl->rb_user_active);
+	return (!(rb_gc_cnt + nr_entries > rl->rb_gc_max && rb_user_active));
+}
+
+void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
+{
+	atomic_add(nr_entries, &rl->rb_user_cnt);
+
+	/* Release user I/O state. Protect from GC */
+	smp_store_release(&rl->rb_user_active, 1);
+	pblk_rl_kick_u_timer(rl);
+}
+
+void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
+{
+	atomic_add(nr_entries, &rl->rb_gc_cnt);
+}
+
+void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc)
+{
+	atomic_sub(nr_user, &rl->rb_user_cnt);
+	atomic_sub(nr_gc, &rl->rb_gc_cnt);
+}
+
+unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl)
+{
+	return atomic_read(&rl->free_blocks);
+}
+
+/*
+ * We check for (i) the number of free blocks in the current LUN and (ii) the
+ * total number of free blocks in the pblk instance. This is to even out the
+ * number of free blocks on each LUN when GC kicks in.
+ *
+ * Only the total number of free blocks is used to configure the rate limiter.
+ */
+static int pblk_rl_update_rates(struct pblk_rl *rl, unsigned long max)
+{
+	unsigned long free_blocks = pblk_rl_nr_free_blks(rl);
+
+	if (free_blocks >= rl->high) {
+		rl->rb_user_max = max - rl->rb_gc_rsv;
+		rl->rb_gc_max = rl->rb_gc_rsv;
+		rl->rb_state = PBLK_RL_HIGH;
+	} else if (free_blocks < rl->high) {
+		int shift = rl->high_pw - rl->rb_windows_pw;
+		int user_windows = free_blocks >> shift;
+		int user_max = user_windows << PBLK_MAX_REQ_ADDRS_PW;
+		int gc_max;
+
+		rl->rb_user_max = user_max;
+		gc_max = max - rl->rb_user_max;
+		rl->rb_gc_max = max(gc_max, rl->rb_gc_rsv);
+
+		if (free_blocks > rl->low)
+			rl->rb_state = PBLK_RL_MID;
+		else
+			rl->rb_state = PBLK_RL_LOW;
+	}
+
+	return rl->rb_state;
+}
+
+void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv)
+{
+	rl->rb_gc_rsv = rl->rb_gc_max = rsv;
+}
+
+void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line)
+{
+	struct pblk *pblk = container_of(rl, struct pblk, rl);
+	int blk_in_line = atomic_read(&line->blk_in_line);
+	int ret;
+
+	atomic_add(blk_in_line, &rl->free_blocks);
+	/* Rates will not change that often - no need to lock update */
+	ret = pblk_rl_update_rates(rl, rl->rb_budget);
+
+	if (ret == (PBLK_RL_MID | PBLK_RL_LOW))
+		pblk_gc_should_start(pblk);
+	else
+		pblk_gc_should_stop(pblk);
+}
+
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line)
+{
+	struct pblk *pblk = container_of(rl, struct pblk, rl);
+	int blk_in_line = atomic_read(&line->blk_in_line);
+	int ret;
+
+	atomic_sub(blk_in_line, &rl->free_blocks);
+
+	/* Rates will not change that often - no need to lock update */
+	ret = pblk_rl_update_rates(rl, rl->rb_budget);
+	if (ret == (PBLK_RL_MID | PBLK_RL_LOW))
+		pblk_gc_should_start(pblk);
+	else
+		pblk_gc_should_stop(pblk);
+}
+
+int pblk_rl_gc_thrs(struct pblk_rl *rl)
+{
+	return rl->high;
+}
+
+int pblk_rl_sysfs_rate_show(struct pblk_rl *rl)
+{
+	return rl->rb_user_max;
+}
+
+static void pblk_rl_u_timer(unsigned long data)
+{
+	struct pblk_rl *rl = (struct pblk_rl *)data;
+
+	/* Release user I/O state. Protect from GC */
+	smp_store_release(&rl->rb_user_active, 0);
+}
+
+void pblk_rl_free(struct pblk_rl *rl)
+{
+	del_timer(&rl->u_timer);
+}
+
+void pblk_rl_init(struct pblk_rl *rl, int budget)
+{
+	unsigned int rb_windows;
+
+	rl->high = rl->total_blocks / PBLK_USER_HIGH_THRS;
+	rl->low = rl->total_blocks / PBLK_USER_LOW_THRS;
+	rl->high_pw = get_count_order(rl->high);
+
+	/* This will always be a power-of-2 */
+	rb_windows = budget / PBLK_MAX_REQ_ADDRS;
+	rl->rb_windows_pw = get_count_order(rb_windows) + 1;
+
+	/* To start with, all buffer is available to user I/O writers */
+	rl->rb_budget = budget;
+	rl->rb_user_max = budget;
+	atomic_set(&rl->rb_user_cnt, 0);
+	rl->rb_gc_max = 0;
+	rl->rb_state = PBLK_RL_HIGH;
+	atomic_set(&rl->rb_gc_cnt, 0);
+
+	setup_timer(&rl->u_timer, pblk_rl_u_timer, (unsigned long)rl);
+	rl->rb_user_active = 0;
+}
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
new file mode 100644
index 000000000000..f0af1d1ceeff
--- /dev/null
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -0,0 +1,507 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Implementation of a physical block-device target for Open-channel SSDs.
+ *
+ * pblk-sysfs.c - pblk's sysfs
+ *
+ */
+
+#include "pblk.h"
+
+static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_lun *rlun;
+	ssize_t sz = 0;
+	int i;
+
+	for (i = 0; i < geo->nr_luns; i++) {
+		int active = 1;
+
+		rlun = &pblk->luns[i];
+		if (!down_trylock(&rlun->wr_sem)) {
+			active = 0;
+			up(&rlun->wr_sem);
+		}
+		sz += snprintf(page + sz, PAGE_SIZE - sz,
+				"pblk: pos:%d, ch:%d, lun:%d - %d\n",
+					i,
+					rlun->bppa.g.ch,
+					rlun->bppa.g.lun,
+					active);
+	}
+
+	return sz;
+}
+
+static ssize_t pblk_sysfs_rate_limiter(struct pblk *pblk, char *page)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	int free_blocks, total_blocks;
+	int rb_user_max, rb_user_cnt;
+	int rb_gc_max, rb_gc_rsv, rb_gc_cnt, rb_budget, rb_state;
+
+	free_blocks = atomic_read(&pblk->rl.free_blocks);
+	rb_user_max = pblk->rl.rb_user_max;
+	rb_user_cnt = atomic_read(&pblk->rl.rb_user_cnt);
+	rb_gc_max = pblk->rl.rb_gc_max;
+	rb_gc_rsv = pblk->rl.rb_gc_rsv;
+	rb_gc_cnt = atomic_read(&pblk->rl.rb_gc_cnt);
+	rb_budget = pblk->rl.rb_budget;
+	rb_state = pblk->rl.rb_state;
+
+	total_blocks = geo->blks_per_lun * geo->nr_luns;
+
+	return snprintf(page, PAGE_SIZE,
+		"u:%u/%u,gc:%u/%u/%u(%u/%u)(stop:<%u,full:>%u,free:%d/%d)-%d\n",
+				rb_user_cnt,
+				rb_user_max,
+				rb_gc_cnt,
+				rb_gc_max,
+				rb_gc_rsv,
+				rb_state,
+				rb_budget,
+				pblk->rl.low,
+				pblk->rl.high,
+				free_blocks,
+				total_blocks,
+				READ_ONCE(pblk->rl.rb_user_active));
+}
+
+static ssize_t pblk_sysfs_gc_state_show(struct pblk *pblk, char *page)
+{
+	int gc_enabled, gc_active;
+
+	pblk_gc_sysfs_state_show(pblk, &gc_enabled, &gc_active);
+	return snprintf(page, PAGE_SIZE, "gc_enabled=%d, gc_active=%d\n",
+					gc_enabled, gc_active);
+}
+
+static ssize_t pblk_sysfs_stats(struct pblk *pblk, char *page)
+{
+	ssize_t sz;
+
+	sz = snprintf(page, PAGE_SIZE,
+			"read_failed=%lu, read_high_ecc=%lu, read_empty=%lu, read_failed_gc=%lu, write_failed=%lu, erase_failed=%lu\n",
+			atomic_long_read(&pblk->read_failed),
+			atomic_long_read(&pblk->read_high_ecc),
+			atomic_long_read(&pblk->read_empty),
+			atomic_long_read(&pblk->read_failed_gc),
+			atomic_long_read(&pblk->write_failed),
+			atomic_long_read(&pblk->erase_failed));
+
+	return sz;
+}
+
+static ssize_t pblk_sysfs_write_buffer(struct pblk *pblk, char *page)
+{
+	return pblk_rb_sysfs(&pblk->rwb, page);
+}
+
+static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	ssize_t sz = 0;
+
+	sz = snprintf(page, PAGE_SIZE - sz,
+		"g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
+		pblk->ppaf_bitsize,
+		pblk->ppaf.blk_offset, geo->ppaf.blk_len,
+		pblk->ppaf.pg_offset, geo->ppaf.pg_len,
+		pblk->ppaf.lun_offset, geo->ppaf.lun_len,
+		pblk->ppaf.ch_offset, geo->ppaf.ch_len,
+		pblk->ppaf.pln_offset, geo->ppaf.pln_len,
+		pblk->ppaf.sec_offset, geo->ppaf.sect_len);
+
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+		"d:blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
+		geo->ppaf.blk_offset, geo->ppaf.blk_len,
+		geo->ppaf.pg_offset, geo->ppaf.pg_len,
+		geo->ppaf.lun_offset, geo->ppaf.lun_len,
+		geo->ppaf.ch_offset, geo->ppaf.ch_len,
+		geo->ppaf.pln_offset, geo->ppaf.pln_len,
+		geo->ppaf.sect_offset, geo->ppaf.sect_len);
+
+	return sz;
+}
+
+static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *line;
+	ssize_t sz = 0;
+	int nr_free_lines;
+	int cur_data, cur_log;
+	int free_line_cnt = 0, closed_line_cnt = 0;
+	int d_line_cnt = 0, l_line_cnt = 0;
+	int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0;
+	int free = 0, bad = 0, cor = 0;
+	int msecs = 0, ssecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
+	int map_weight = 0, meta_weight = 0;
+
+	spin_lock(&l_mg->free_lock);
+	cur_data = (l_mg->data_line) ? l_mg->data_line->id : -1;
+	cur_log = (l_mg->log_line) ? l_mg->log_line->id : -1;
+	nr_free_lines = l_mg->nr_free_lines;
+
+	list_for_each_entry(line, &l_mg->free_list, list)
+		free_line_cnt++;
+	spin_unlock(&l_mg->free_lock);
+
+	spin_lock(&l_mg->gc_lock);
+	list_for_each_entry(line, &l_mg->gc_full_list, list) {
+		if (line->type == PBLK_LINETYPE_DATA)
+			d_line_cnt++;
+		else if (line->type == PBLK_LINETYPE_LOG)
+			l_line_cnt++;
+		closed_line_cnt++;
+		gc_full++;
+	}
+
+	list_for_each_entry(line, &l_mg->gc_high_list, list) {
+		if (line->type == PBLK_LINETYPE_DATA)
+			d_line_cnt++;
+		else if (line->type == PBLK_LINETYPE_LOG)
+			l_line_cnt++;
+		closed_line_cnt++;
+		gc_high++;
+	}
+
+	list_for_each_entry(line, &l_mg->gc_mid_list, list) {
+		if (line->type == PBLK_LINETYPE_DATA)
+			d_line_cnt++;
+		else if (line->type == PBLK_LINETYPE_LOG)
+			l_line_cnt++;
+		closed_line_cnt++;
+		gc_mid++;
+	}
+
+	list_for_each_entry(line, &l_mg->gc_low_list, list) {
+		if (line->type == PBLK_LINETYPE_DATA)
+			d_line_cnt++;
+		else if (line->type == PBLK_LINETYPE_LOG)
+			l_line_cnt++;
+		closed_line_cnt++;
+		gc_low++;
+	}
+
+	list_for_each_entry(line, &l_mg->gc_empty_list, list) {
+		if (line->type == PBLK_LINETYPE_DATA)
+			d_line_cnt++;
+		else if (line->type == PBLK_LINETYPE_LOG)
+			l_line_cnt++;
+		closed_line_cnt++;
+		gc_empty++;
+	}
+
+	list_for_each_entry(line, &l_mg->free_list, list)
+		free++;
+	list_for_each_entry(line, &l_mg->bad_list, list)
+		bad++;
+	list_for_each_entry(line, &l_mg->corrupt_list, list)
+		cor++;
+	spin_unlock(&l_mg->gc_lock);
+
+	spin_lock(&l_mg->free_lock);
+	if (l_mg->data_line) {
+		cur_sec = l_mg->data_line->cur_sec;
+		msecs = l_mg->data_line->left_msecs;
+		ssecs = l_mg->data_line->left_ssecs;
+		vsc = l_mg->data_line->vsc;
+		sec_in_line = l_mg->data_line->sec_in_line;
+		meta_weight = bitmap_weight(&l_mg->meta_bitmap,
+							PBLK_DATA_LINES);
+		map_weight = bitmap_weight(l_mg->data_line->map_bitmap,
+							lm->sec_per_line);
+	}
+	spin_unlock(&l_mg->free_lock);
+
+	if (nr_free_lines != free_line_cnt)
+		pr_err("pblk: corrupted free line list\n");
+
+	sz = snprintf(page, PAGE_SIZE - sz,
+		"line: nluns:%d, nblks:%d, nsecs:%d\n",
+		geo->nr_luns, lm->blk_per_line, lm->sec_per_line);
+
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+		"lines:d:%d,l:%d-f:%d(%d),b:%d,co:%d,c:%d(d:%d,l:%d)t:%d\n",
+					cur_data, cur_log,
+					free, nr_free_lines, bad, cor,
+					closed_line_cnt,
+					d_line_cnt, l_line_cnt,
+					l_mg->nr_lines);
+
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+		"GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, queue:%d\n",
+			gc_full, gc_high, gc_mid, gc_low, gc_empty,
+			atomic_read(&pblk->gc.inflight_gc));
+
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+		"data (%d) cur:%d, left:%d/%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
+			cur_data, cur_sec, msecs, ssecs, vsc, sec_in_line,
+			map_weight, lm->sec_per_line, meta_weight);
+
+	return sz;
+}
+
+static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	ssize_t sz = 0;
+
+	sz = snprintf(page, PAGE_SIZE - sz,
+				"smeta - len:%d, secs:%d\n",
+					lm->smeta_len, lm->smeta_sec);
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+				"emeta - len:%d, sec:%d, bb_start:%d\n",
+					lm->emeta_len, lm->emeta_sec,
+					lm->emeta_bb);
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+				"bitmap lengths: sec:%d, blk:%d, lun:%d\n",
+					lm->sec_bitmap_len,
+					lm->blk_bitmap_len,
+					lm->lun_bitmap_len);
+	sz += snprintf(page + sz, PAGE_SIZE - sz,
+				"blk_line:%d, sec_line:%d, sec_blk:%d\n",
+					lm->blk_per_line,
+					lm->sec_per_line,
+					geo->sec_per_blk);
+
+	return sz;
+}
+
+#ifdef CONFIG_NVM_DEBUG
+static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
+{
+	return snprintf(page, PAGE_SIZE,
+		"%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\n",
+			atomic_long_read(&pblk->inflight_writes),
+			atomic_long_read(&pblk->inflight_reads),
+			atomic_long_read(&pblk->req_writes),
+			atomic_long_read(&pblk->nr_flush),
+			atomic_long_read(&pblk->padded_writes),
+			atomic_long_read(&pblk->padded_wb),
+			atomic_long_read(&pblk->sub_writes),
+			atomic_long_read(&pblk->sync_writes),
+			atomic_long_read(&pblk->compl_writes),
+			atomic_long_read(&pblk->recov_writes),
+			atomic_long_read(&pblk->recov_gc_writes),
+			atomic_long_read(&pblk->recov_gc_reads),
+			atomic_long_read(&pblk->sync_reads));
+}
+#endif
+
+static ssize_t pblk_sysfs_rate_store(struct pblk *pblk, const char *page,
+				     size_t len)
+{
+	struct pblk_gc *gc = &pblk->gc;
+	size_t c_len;
+	int value;
+
+	c_len = strcspn(page, "\n");
+	if (c_len >= len)
+		return -EINVAL;
+
+	if (kstrtouint(page, 0, &value))
+		return -EINVAL;
+
+	spin_lock(&gc->lock);
+	pblk_rl_set_gc_rsc(&pblk->rl, value);
+	spin_unlock(&gc->lock);
+
+	return len;
+}
+
+static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page,
+				   size_t len)
+{
+	size_t c_len;
+	int force;
+
+	c_len = strcspn(page, "\n");
+	if (c_len >= len)
+		return -EINVAL;
+
+	if (kstrtouint(page, 0, &force))
+		return -EINVAL;
+
+	if (force < 0 || force > 1)
+		return -EINVAL;
+
+	pblk_gc_sysfs_force(pblk, force);
+
+	return len;
+}
+
+static struct attribute sys_write_luns = {
+	.name = "write_luns",
+	.mode = 0444,
+};
+
+static struct attribute sys_rate_limiter_attr = {
+	.name = "rate_limiter",
+	.mode = 0444,
+};
+
+static struct attribute sys_gc_state = {
+	.name = "gc_state",
+	.mode = 0444,
+};
+
+static struct attribute sys_errors_attr = {
+	.name = "errors",
+	.mode = 0444,
+};
+
+static struct attribute sys_rb_attr = {
+	.name = "write_buffer",
+	.mode = 0444,
+};
+
+static struct attribute sys_stats_ppaf_attr = {
+	.name = "ppa_format",
+	.mode = 0444,
+};
+
+static struct attribute sys_lines_attr = {
+	.name = "lines",
+	.mode = 0444,
+};
+
+static struct attribute sys_lines_info_attr = {
+	.name = "lines_info",
+	.mode = 0444,
+};
+
+static struct attribute sys_gc_force = {
+	.name = "gc_force",
+	.mode = 0200,
+};
+
+static struct attribute sys_gc_rl_max = {
+	.name = "gc_rl_max",
+	.mode = 0200,
+};
+
+#ifdef CONFIG_NVM_DEBUG
+static struct attribute sys_stats_debug_attr = {
+	.name = "stats",
+	.mode = 0444,
+};
+#endif
+
+static struct attribute *pblk_attrs[] = {
+	&sys_write_luns,
+	&sys_rate_limiter_attr,
+	&sys_errors_attr,
+	&sys_gc_state,
+	&sys_gc_force,
+	&sys_gc_rl_max,
+	&sys_rb_attr,
+	&sys_stats_ppaf_attr,
+	&sys_lines_attr,
+	&sys_lines_info_attr,
+#ifdef CONFIG_NVM_DEBUG
+	&sys_stats_debug_attr,
+#endif
+	NULL,
+};
+
+static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
+			       char *buf)
+{
+	struct pblk *pblk = container_of(kobj, struct pblk, kobj);
+
+	if (strcmp(attr->name, "rate_limiter") == 0)
+		return pblk_sysfs_rate_limiter(pblk, buf);
+	else if (strcmp(attr->name, "write_luns") == 0)
+		return pblk_sysfs_luns_show(pblk, buf);
+	else if (strcmp(attr->name, "gc_state") == 0)
+		return pblk_sysfs_gc_state_show(pblk, buf);
+	else if (strcmp(attr->name, "errors") == 0)
+		return pblk_sysfs_stats(pblk, buf);
+	else if (strcmp(attr->name, "write_buffer") == 0)
+		return pblk_sysfs_write_buffer(pblk, buf);
+	else if (strcmp(attr->name, "ppa_format") == 0)
+		return pblk_sysfs_ppaf(pblk, buf);
+	else if (strcmp(attr->name, "lines") == 0)
+		return pblk_sysfs_lines(pblk, buf);
+	else if (strcmp(attr->name, "lines_info") == 0)
+		return pblk_sysfs_lines_info(pblk, buf);
+#ifdef CONFIG_NVM_DEBUG
+	else if (strcmp(attr->name, "stats") == 0)
+		return pblk_sysfs_stats_debug(pblk, buf);
+#endif
+	return 0;
+}
+
+static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr,
+				const char *buf, size_t len)
+{
+	struct pblk *pblk = container_of(kobj, struct pblk, kobj);
+
+	if (strcmp(attr->name, "gc_rl_max") == 0)
+		return pblk_sysfs_rate_store(pblk, buf, len);
+	else if (strcmp(attr->name, "gc_force") == 0)
+		return pblk_sysfs_gc_force(pblk, buf, len);
+
+	return 0;
+}
+
+static const struct sysfs_ops pblk_sysfs_ops = {
+	.show = pblk_sysfs_show,
+	.store = pblk_sysfs_store,
+};
+
+static struct kobj_type pblk_ktype = {
+	.sysfs_ops	= &pblk_sysfs_ops,
+	.default_attrs	= pblk_attrs,
+};
+
+int pblk_sysfs_init(struct gendisk *tdisk)
+{
+	struct pblk *pblk = tdisk->private_data;
+	struct device *parent_dev = disk_to_dev(pblk->disk);
+	int ret;
+
+	ret = kobject_init_and_add(&pblk->kobj, &pblk_ktype,
+					kobject_get(&parent_dev->kobj),
+					"%s", "pblk");
+	if (ret) {
+		pr_err("pblk: could not register %s/pblk\n",
+						tdisk->disk_name);
+		return ret;
+	}
+
+	kobject_uevent(&pblk->kobj, KOBJ_ADD);
+	return 0;
+}
+
+void pblk_sysfs_exit(struct gendisk *tdisk)
+{
+	struct pblk *pblk = tdisk->private_data;
+
+	kobject_uevent(&pblk->kobj, KOBJ_REMOVE);
+	kobject_del(&pblk->kobj);
+	kobject_put(&pblk->kobj);
+}
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
new file mode 100644
index 000000000000..aef6fd7c4a0c
--- /dev/null
+++ b/drivers/lightnvm/pblk-write.c
@@ -0,0 +1,414 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *                  Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * pblk-write.c - pblk's write path from write buffer to media
+ */
+
+#include "pblk.h"
+
+static void pblk_sync_line(struct pblk *pblk, struct pblk_line *line)
+{
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_inc(&pblk->sync_writes);
+#endif
+
+	/* Counter protected by rb sync lock */
+	line->left_ssecs--;
+	if (!line->left_ssecs)
+		pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
+}
+
+static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
+				    struct pblk_c_ctx *c_ctx)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct bio *original_bio;
+	unsigned long ret;
+	int i;
+
+	for (i = 0; i < c_ctx->nr_valid; i++) {
+		struct pblk_w_ctx *w_ctx;
+		struct ppa_addr p;
+		struct pblk_line *line;
+
+		w_ctx = pblk_rb_w_ctx(&pblk->rwb, c_ctx->sentry + i);
+
+		p = rqd->ppa_list[i];
+		line = &pblk->lines[pblk_dev_ppa_to_line(p)];
+		pblk_sync_line(pblk, line);
+
+		while ((original_bio = bio_list_pop(&w_ctx->bios)))
+			bio_endio(original_bio);
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(c_ctx->nr_valid, &pblk->compl_writes);
+#endif
+
+	ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
+
+	if (rqd->meta_list)
+		nvm_dev_dma_free(dev->parent, rqd->meta_list,
+							rqd->dma_meta_list);
+
+	bio_put(rqd->bio);
+	pblk_free_rqd(pblk, rqd, WRITE);
+
+	return ret;
+}
+
+static unsigned long pblk_end_queued_w_bio(struct pblk *pblk,
+					   struct nvm_rq *rqd,
+					   struct pblk_c_ctx *c_ctx)
+{
+	list_del(&c_ctx->list);
+	return pblk_end_w_bio(pblk, rqd, c_ctx);
+}
+
+static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
+				struct pblk_c_ctx *c_ctx)
+{
+	struct pblk_c_ctx *c, *r;
+	unsigned long flags;
+	unsigned long pos;
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
+#endif
+
+	pblk_up_rq(pblk, rqd->ppa_list, rqd->nr_ppas, c_ctx->lun_bitmap);
+
+	pos = pblk_rb_sync_init(&pblk->rwb, &flags);
+	if (pos == c_ctx->sentry) {
+		pos = pblk_end_w_bio(pblk, rqd, c_ctx);
+
+retry:
+		list_for_each_entry_safe(c, r, &pblk->compl_list, list) {
+			rqd = nvm_rq_from_c_ctx(c);
+			if (c->sentry == pos) {
+				pos = pblk_end_queued_w_bio(pblk, rqd, c);
+				goto retry;
+			}
+		}
+	} else {
+		WARN_ON(nvm_rq_from_c_ctx(c_ctx) != rqd);
+		list_add_tail(&c_ctx->list, &pblk->compl_list);
+	}
+	pblk_rb_sync_end(&pblk->rwb, &flags);
+}
+
+/* When a write fails, we are not sure whether the block has grown bad or a page
+ * range is more susceptible to write errors. If a high number of pages fail, we
+ * assume that the block is bad and we mark it accordingly. In all cases, we
+ * remap and resubmit the failed entries as fast as possible; if a flush is
+ * waiting on a completion, the whole stack would stall otherwise.
+ */
+static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	void *comp_bits = &rqd->ppa_status;
+	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_rec_ctx *recovery;
+	struct ppa_addr *ppa_list = rqd->ppa_list;
+	int nr_ppas = rqd->nr_ppas;
+	unsigned int c_entries;
+	int bit, ret;
+
+	if (unlikely(nr_ppas == 1))
+		ppa_list = &rqd->ppa_addr;
+
+	recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
+	if (!recovery) {
+		pr_err("pblk: could not allocate recovery context\n");
+		return;
+	}
+	INIT_LIST_HEAD(&recovery->failed);
+
+	bit = -1;
+	while ((bit = find_next_bit(comp_bits, nr_ppas, bit + 1)) < nr_ppas) {
+		struct pblk_rb_entry *entry;
+		struct ppa_addr ppa;
+
+		/* Logic error */
+		if (bit > c_ctx->nr_valid) {
+			WARN_ONCE(1, "pblk: corrupted write request\n");
+			mempool_free(recovery, pblk->rec_pool);
+			goto out;
+		}
+
+		ppa = ppa_list[bit];
+		entry = pblk_rb_sync_scan_entry(&pblk->rwb, &ppa);
+		if (!entry) {
+			pr_err("pblk: could not scan entry on write failure\n");
+			mempool_free(recovery, pblk->rec_pool);
+			goto out;
+		}
+
+		/* The list is filled first and emptied afterwards. No need for
+		 * protecting it with a lock
+		 */
+		list_add_tail(&entry->index, &recovery->failed);
+	}
+
+	c_entries = find_first_bit(comp_bits, nr_ppas);
+	ret = pblk_recov_setup_rq(pblk, c_ctx, recovery, comp_bits, c_entries);
+	if (ret) {
+		pr_err("pblk: could not recover from write failure\n");
+		mempool_free(recovery, pblk->rec_pool);
+		goto out;
+	}
+
+	INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
+	queue_work(pblk->kw_wq, &recovery->ws_rec);
+
+out:
+	pblk_complete_write(pblk, rqd, c_ctx);
+}
+
+static void pblk_end_io_write(struct nvm_rq *rqd)
+{
+	struct pblk *pblk = rqd->private;
+	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+
+	if (rqd->error) {
+		pblk_log_write_err(pblk, rqd);
+		return pblk_end_w_fail(pblk, rqd);
+	}
+#ifdef CONFIG_NVM_DEBUG
+	else
+		WARN_ONCE(rqd->bio->bi_error, "pblk: corrupted write error\n");
+#endif
+
+	pblk_complete_write(pblk, rqd, c_ctx);
+}
+
+static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
+			   unsigned int nr_secs)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+
+	/* Setup write request */
+	rqd->opcode = NVM_OP_PWRITE;
+	rqd->nr_ppas = nr_secs;
+	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+	rqd->private = pblk;
+	rqd->end_io = pblk_end_io_write;
+
+	rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+							&rqd->dma_meta_list);
+	if (!rqd->meta_list)
+		return -ENOMEM;
+
+	if (unlikely(nr_secs == 1))
+		return 0;
+
+	rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
+	rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
+
+	return 0;
+}
+
+static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
+			   struct pblk_c_ctx *c_ctx)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line *e_line = pblk_line_get_data_next(pblk);
+	struct ppa_addr erase_ppa;
+	unsigned int valid = c_ctx->nr_valid;
+	unsigned int padded = c_ctx->nr_padded;
+	unsigned int nr_secs = valid + padded;
+	unsigned long *lun_bitmap;
+	int ret = 0;
+
+	lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
+	if (!lun_bitmap) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	c_ctx->lun_bitmap = lun_bitmap;
+
+	ret = pblk_alloc_w_rq(pblk, rqd, nr_secs);
+	if (ret) {
+		kfree(lun_bitmap);
+		goto out;
+	}
+
+	ppa_set_empty(&erase_ppa);
+	if (likely(!e_line || !atomic_read(&e_line->left_eblks)))
+		pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, valid, 0);
+	else
+		pblk_map_erase_rq(pblk, rqd, c_ctx->sentry, lun_bitmap,
+							valid, &erase_ppa);
+
+out:
+	if (unlikely(e_line && !ppa_empty(erase_ppa))) {
+		if (pblk_blk_erase_async(pblk, erase_ppa)) {
+			struct nvm_tgt_dev *dev = pblk->dev;
+			struct nvm_geo *geo = &dev->geo;
+			int bit;
+
+			atomic_inc(&e_line->left_eblks);
+			bit = erase_ppa.g.lun * geo->nr_chnls + erase_ppa.g.ch;
+			WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap));
+			up(&pblk->erase_sem);
+		}
+	}
+
+	return ret;
+}
+
+int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
+			struct pblk_c_ctx *c_ctx)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	unsigned long *lun_bitmap;
+	int ret;
+
+	lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
+	if (!lun_bitmap)
+		return -ENOMEM;
+
+	c_ctx->lun_bitmap = lun_bitmap;
+
+	ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas);
+	if (ret)
+		return ret;
+
+	pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, c_ctx->nr_valid, 0);
+
+	rqd->ppa_status = (u64)0;
+	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+
+	return ret;
+}
+
+static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
+				  unsigned int secs_to_flush)
+{
+	int secs_to_sync;
+
+	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
+
+#ifdef CONFIG_NVM_DEBUG
+	if ((!secs_to_sync && secs_to_flush)
+			|| (secs_to_sync < 0)
+			|| (secs_to_sync > secs_avail && !secs_to_flush)) {
+		pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+				secs_avail, secs_to_sync, secs_to_flush);
+	}
+#endif
+
+	return secs_to_sync;
+}
+
+static int pblk_submit_write(struct pblk *pblk)
+{
+	struct bio *bio;
+	struct nvm_rq *rqd;
+	struct pblk_c_ctx *c_ctx;
+	unsigned int pgs_read;
+	unsigned int secs_avail, secs_to_sync, secs_to_com;
+	unsigned int secs_to_flush;
+	unsigned long pos;
+	int err;
+
+	/* If there are no sectors in the cache, flushes (bios without data)
+	 * will be cleared on the cache threads
+	 */
+	secs_avail = pblk_rb_read_count(&pblk->rwb);
+	if (!secs_avail)
+		return 1;
+
+	secs_to_flush = pblk_rb_sync_point_count(&pblk->rwb);
+	if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
+		return 1;
+
+	rqd = pblk_alloc_rqd(pblk, WRITE);
+	if (IS_ERR(rqd)) {
+		pr_err("pblk: cannot allocate write req.\n");
+		return 1;
+	}
+	c_ctx = nvm_rq_to_pdu(rqd);
+
+	bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs);
+	if (!bio) {
+		pr_err("pblk: cannot allocate write bio\n");
+		goto fail_free_rqd;
+	}
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+	rqd->bio = bio;
+
+	secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
+	if (secs_to_sync > pblk->max_write_pgs) {
+		pr_err("pblk: bad buffer sync calculation\n");
+		goto fail_put_bio;
+	}
+
+	secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
+	pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
+
+	pgs_read = pblk_rb_read_to_bio(&pblk->rwb, bio, c_ctx, pos,
+						secs_to_sync, secs_avail);
+	if (!pgs_read) {
+		pr_err("pblk: corrupted write bio\n");
+		goto fail_put_bio;
+	}
+
+	if (c_ctx->nr_padded)
+		if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, c_ctx->nr_padded))
+			goto fail_put_bio;
+
+	/* Assign lbas to ppas and populate request structure */
+	err = pblk_setup_w_rq(pblk, rqd, c_ctx);
+	if (err) {
+		pr_err("pblk: could not setup write request\n");
+		goto fail_free_bio;
+	}
+
+	err = pblk_submit_io(pblk, rqd);
+	if (err) {
+		pr_err("pblk: I/O submission failed: %d\n", err);
+		goto fail_free_bio;
+	}
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(secs_to_sync, &pblk->sub_writes);
+#endif
+
+	return 0;
+
+fail_free_bio:
+	if (c_ctx->nr_padded)
+		pblk_bio_free_pages(pblk, bio, secs_to_sync, c_ctx->nr_padded);
+fail_put_bio:
+	bio_put(bio);
+fail_free_rqd:
+	pblk_free_rqd(pblk, rqd, WRITE);
+
+	return 1;
+}
+
+int pblk_write_ts(void *data)
+{
+	struct pblk *pblk = data;
+
+	while (!kthread_should_stop()) {
+		if (!pblk_submit_write(pblk))
+			continue;
+		set_current_state(TASK_INTERRUPTIBLE);
+		io_schedule();
+	}
+
+	return 0;
+}
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
new file mode 100644
index 000000000000..99f3186b5288
--- /dev/null
+++ b/drivers/lightnvm/pblk.h
@@ -0,0 +1,1121 @@
+/*
+ * Copyright (C) 2015 IT University of Copenhagen (rrpc.h)
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Matias Bjorling <matias@cnexlabs.com>
+ * Write buffering: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Implementation of a Physical Block-device target for Open-channel SSDs.
+ *
+ */
+
+#ifndef PBLK_H_
+#define PBLK_H_
+
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/vmalloc.h>
+#include <linux/crc32.h>
+#include <linux/uuid.h>
+
+#include <linux/lightnvm.h>
+
+/* Run only GC if less than 1/X blocks are free */
+#define GC_LIMIT_INVERSE 5
+#define GC_TIME_MSECS 1000
+
+#define PBLK_SECTOR (512)
+#define PBLK_EXPOSED_PAGE_SIZE (4096)
+#define PBLK_MAX_REQ_ADDRS (64)
+#define PBLK_MAX_REQ_ADDRS_PW (6)
+
+#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
+
+#define PBLK_COMMAND_TIMEOUT_MS 30000
+
+/* Max 512 LUNs per device */
+#define PBLK_MAX_LUNS_BITMAP (4)
+
+#define NR_PHY_IN_LOG (PBLK_EXPOSED_PAGE_SIZE / PBLK_SECTOR)
+
+#define pblk_for_each_lun(pblk, rlun, i) \
+		for ((i) = 0, rlun = &(pblk)->luns[0]; \
+			(i) < (pblk)->nr_luns; (i)++, rlun = &(pblk)->luns[(i)])
+
+#define ERASE 2 /* READ = 0, WRITE = 1 */
+
+enum {
+	/* IO Types */
+	PBLK_IOTYPE_USER	= 1 << 0,
+	PBLK_IOTYPE_GC		= 1 << 1,
+
+	/* Write buffer flags */
+	PBLK_FLUSH_ENTRY	= 1 << 2,
+	PBLK_WRITTEN_DATA	= 1 << 3,
+	PBLK_SUBMITTED_ENTRY	= 1 << 4,
+	PBLK_WRITABLE_ENTRY	= 1 << 5,
+};
+
+enum {
+	PBLK_BLK_ST_OPEN =	0x1,
+	PBLK_BLK_ST_CLOSED =	0x2,
+};
+
+/* The number of GC lists and the rate-limiter states go together. This way the
+ * rate-limiter can dictate how much GC is needed based on resource utilization.
+ */
+#define PBLK_NR_GC_LISTS 3
+#define PBLK_MAX_GC_JOBS 32
+
+enum {
+	PBLK_RL_HIGH = 1,
+	PBLK_RL_MID = 2,
+	PBLK_RL_LOW = 3,
+};
+
+struct pblk_sec_meta {
+	u64 reserved;
+	__le64 lba;
+};
+
+#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS)
+
+/* write completion context */
+struct pblk_c_ctx {
+	struct list_head list;		/* Head for out-of-order completion */
+
+	unsigned long *lun_bitmap;	/* Luns used on current request */
+	unsigned int sentry;
+	unsigned int nr_valid;
+	unsigned int nr_padded;
+};
+
+/* Read context */
+struct pblk_r_ctx {
+	struct bio *orig_bio;
+};
+
+/* Recovery context */
+struct pblk_rec_ctx {
+	struct pblk *pblk;
+	struct nvm_rq *rqd;
+	struct list_head failed;
+	struct work_struct ws_rec;
+};
+
+/* Write context */
+struct pblk_w_ctx {
+	struct bio_list bios;		/* Original bios - used for completion
+					 * in REQ_FUA, REQ_FLUSH case
+					 */
+	u64 lba;			/* Logic addr. associated with entry */
+	struct ppa_addr ppa;		/* Physic addr. associated with entry */
+	int flags;			/* Write context flags */
+};
+
+struct pblk_rb_entry {
+	struct ppa_addr cacheline;	/* Cacheline for this entry */
+	void *data;			/* Pointer to data on this entry */
+	struct pblk_w_ctx w_ctx;	/* Context for this entry */
+	struct list_head index;		/* List head to enable indexes */
+};
+
+#define EMPTY_ENTRY (~0U)
+
+struct pblk_rb_pages {
+	struct page *pages;
+	int order;
+	struct list_head list;
+};
+
+struct pblk_rb {
+	struct pblk_rb_entry *entries;	/* Ring buffer entries */
+	unsigned int mem;		/* Write offset - points to next
+					 * writable entry in memory
+					 */
+	unsigned int subm;		/* Read offset - points to last entry
+					 * that has been submitted to the media
+					 * to be persisted
+					 */
+	unsigned int sync;		/* Synced - backpointer that signals
+					 * the last submitted entry that has
+					 * been successfully persisted to media
+					 */
+	unsigned int sync_point;	/* Sync point - last entry that must be
+					 * flushed to the media. Used with
+					 * REQ_FLUSH and REQ_FUA
+					 */
+	unsigned int l2p_update;	/* l2p update point - next entry for
+					 * which l2p mapping will be updated to
+					 * contain a device ppa address (instead
+					 * of a cacheline
+					 */
+	unsigned int nr_entries;	/* Number of entries in write buffer -
+					 * must be a power of two
+					 */
+	unsigned int seg_size;		/* Size of the data segments being
+					 * stored on each entry. Typically this
+					 * will be 4KB
+					 */
+
+	struct list_head pages;		/* List of data pages */
+
+	spinlock_t w_lock;		/* Write lock */
+	spinlock_t s_lock;		/* Sync lock */
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_t inflight_sync_point;	/* Not served REQ_FLUSH | REQ_FUA */
+#endif
+};
+
+#define PBLK_RECOVERY_SECTORS 16
+
+struct pblk_lun {
+	struct ppa_addr bppa;
+
+	u8 *bb_list;			/* Bad block list for LUN. Only used on
+					 * bring up. Bad blocks are managed
+					 * within lines on run-time.
+					 */
+
+	struct semaphore wr_sem;
+};
+
+struct pblk_gc_rq {
+	struct pblk_line *line;
+	void *data;
+	u64 *lba_list;
+	int nr_secs;
+	int secs_to_gc;
+	struct list_head list;
+};
+
+struct pblk_gc {
+	int gc_active;
+	int gc_enabled;
+	int gc_forced;
+	int gc_jobs_active;
+	atomic_t inflight_gc;
+
+	struct task_struct *gc_ts;
+	struct task_struct *gc_writer_ts;
+	struct workqueue_struct *gc_reader_wq;
+	struct timer_list gc_timer;
+
+	int w_entries;
+	struct list_head w_list;
+
+	spinlock_t lock;
+	spinlock_t w_lock;
+};
+
+struct pblk_rl {
+	unsigned int high;	/* Upper threshold for rate limiter (free run -
+				 * user I/O rate limiter
+				 */
+	unsigned int low;	/* Lower threshold for rate limiter (user I/O
+				 * rate limiter - stall)
+				 */
+	unsigned int high_pw;	/* High rounded up as a power of 2 */
+
+#define PBLK_USER_HIGH_THRS 2	/* Begin write limit at 50 percent
+				 * available blks
+				 */
+#define PBLK_USER_LOW_THRS 20	/* Aggressive GC at 5% available blocks */
+
+	int rb_windows_pw;	/* Number of rate windows in the write buffer
+				 * given as a power-of-2. This guarantees that
+				 * when user I/O is being rate limited, there
+				 * will be reserved enough space for the GC to
+				 * place its payload. A window is of
+				 * pblk->max_write_pgs size, which in NVMe is
+				 * 64, i.e., 256kb.
+				 */
+	int rb_budget;		/* Total number of entries available for I/O */
+	int rb_user_max;	/* Max buffer entries available for user I/O */
+	atomic_t rb_user_cnt;	/* User I/O buffer counter */
+	int rb_gc_max;		/* Max buffer entries available for GC I/O */
+	int rb_gc_rsv;		/* Reserved buffer entries for GC I/O */
+	int rb_state;		/* Rate-limiter current state */
+	atomic_t rb_gc_cnt;	/* GC I/O buffer counter */
+
+	int rb_user_active;
+	struct timer_list u_timer;
+
+	unsigned long long nr_secs;
+	unsigned long total_blocks;
+	atomic_t free_blocks;
+};
+
+#define PBLK_LINE_NR_LUN_BITMAP 2
+#define PBLK_LINE_NR_SEC_BITMAP 2
+#define PBLK_LINE_EMPTY (~0U)
+
+enum {
+	/* Line Types */
+	PBLK_LINETYPE_FREE = 0,
+	PBLK_LINETYPE_LOG = 1,
+	PBLK_LINETYPE_DATA = 2,
+
+	/* Line state */
+	PBLK_LINESTATE_FREE = 10,
+	PBLK_LINESTATE_OPEN = 11,
+	PBLK_LINESTATE_CLOSED = 12,
+	PBLK_LINESTATE_GC = 13,
+	PBLK_LINESTATE_BAD = 14,
+	PBLK_LINESTATE_CORRUPT = 15,
+
+	/* GC group */
+	PBLK_LINEGC_NONE = 20,
+	PBLK_LINEGC_EMPTY = 21,
+	PBLK_LINEGC_LOW = 22,
+	PBLK_LINEGC_MID = 23,
+	PBLK_LINEGC_HIGH = 24,
+	PBLK_LINEGC_FULL = 25,
+};
+
+#define PBLK_MAGIC 0x70626c6b /*pblk*/
+
+struct line_header {
+	__le32 crc;
+	__le32 identifier;	/* pblk identifier */
+	__u8 uuid[16];		/* instance uuid */
+	__le16 type;		/* line type */
+	__le16 version;		/* type version */
+	__le32 id;		/* line id for current line */
+};
+
+struct line_smeta {
+	struct line_header header;
+
+	__le32 crc;		/* Full structure including struct crc */
+	/* Previous line metadata */
+	__le32 prev_id;		/* Line id for previous line */
+
+	/* Current line metadata */
+	__le64 seq_nr;		/* Sequence number for current line */
+
+	/* Active writers */
+	__le32 window_wr_lun;	/* Number of parallel LUNs to write */
+
+	__le32 rsvd[2];
+};
+
+/*
+ * Metadata Layout:
+ *	1. struct pblk_emeta
+ *	2. nr_lbas u64 forming lba list
+ *	3. nr_lines (all) u32 valid sector count (vsc) (~0U: non-alloc line)
+ *	4. nr_luns bits (u64 format) forming line bad block bitmap
+ *
+ *	3. and 4. will be part of FTL log
+ */
+struct line_emeta {
+	struct line_header header;
+
+	__le32 crc;		/* Full structure including struct crc */
+
+	/* Previous line metadata */
+	__le32 prev_id;		/* Line id for prev line */
+
+	/* Current line metadata */
+	__le64 seq_nr;		/* Sequence number for current line */
+
+	/* Active writers */
+	__le32 window_wr_lun;	/* Number of parallel LUNs to write */
+
+	/* Bookkeeping for recovery */
+	__le32 next_id;		/* Line id for next line */
+	__le64 nr_lbas;		/* Number of lbas mapped in line */
+	__le64 nr_valid_lbas;	/* Number of valid lbas mapped in line */
+};
+
+struct pblk_line {
+	struct pblk *pblk;
+	unsigned int id;		/* Line number corresponds to the
+					 * block line
+					 */
+	unsigned int seq_nr;		/* Unique line sequence number */
+
+	int state;			/* PBLK_LINESTATE_X */
+	int type;			/* PBLK_LINETYPE_X */
+	int gc_group;			/* PBLK_LINEGC_X */
+	struct list_head list;		/* Free, GC lists */
+
+	unsigned long *lun_bitmap;	/* Bitmap for LUNs mapped in line */
+
+	struct line_smeta *smeta;	/* Start metadata */
+	struct line_emeta *emeta;	/* End metadata */
+	int meta_line;			/* Metadata line id */
+	u64 smeta_ssec;			/* Sector where smeta starts */
+	u64 emeta_ssec;			/* Sector where emeta starts */
+
+	unsigned int sec_in_line;	/* Number of usable secs in line */
+
+	atomic_t blk_in_line;		/* Number of good blocks in line */
+	unsigned long *blk_bitmap;	/* Bitmap for valid/invalid blocks */
+	unsigned long *erase_bitmap;	/* Bitmap for erased blocks */
+
+	unsigned long *map_bitmap;	/* Bitmap for mapped sectors in line */
+	unsigned long *invalid_bitmap;	/* Bitmap for invalid sectors in line */
+
+	atomic_t left_eblks;		/* Blocks left for erasing */
+	atomic_t left_seblks;		/* Blocks left for sync erasing */
+
+	int left_msecs;			/* Sectors left for mapping */
+	int left_ssecs;			/* Sectors left to sync */
+	unsigned int cur_sec;		/* Sector map pointer */
+	unsigned int vsc;		/* Valid sector count in line */
+
+	struct kref ref;		/* Write buffer L2P references */
+
+	spinlock_t lock;		/* Necessary for invalid_bitmap only */
+};
+
+#define PBLK_DATA_LINES 4
+
+enum{
+	PBLK_KMALLOC_META = 1,
+	PBLK_VMALLOC_META = 2,
+};
+
+struct pblk_line_metadata {
+	void *meta;
+};
+
+struct pblk_line_mgmt {
+	int nr_lines;			/* Total number of full lines */
+	int nr_free_lines;		/* Number of full lines in free list */
+
+	/* Free lists - use free_lock */
+	struct list_head free_list;	/* Full lines ready to use */
+	struct list_head corrupt_list;	/* Full lines corrupted */
+	struct list_head bad_list;	/* Full lines bad */
+
+	/* GC lists - use gc_lock */
+	struct list_head *gc_lists[PBLK_NR_GC_LISTS];
+	struct list_head gc_high_list;	/* Full lines ready to GC, high isc */
+	struct list_head gc_mid_list;	/* Full lines ready to GC, mid isc */
+	struct list_head gc_low_list;	/* Full lines ready to GC, low isc */
+
+	struct list_head gc_full_list;	/* Full lines ready to GC, no valid */
+	struct list_head gc_empty_list;	/* Full lines close, all valid */
+
+	struct pblk_line *log_line;	/* Current FTL log line */
+	struct pblk_line *data_line;	/* Current data line */
+	struct pblk_line *log_next;	/* Next FTL log line */
+	struct pblk_line *data_next;	/* Next data line */
+
+	/* Metadata allocation type: VMALLOC | KMALLOC */
+	int smeta_alloc_type;
+	int emeta_alloc_type;
+
+	/* Pre-allocated metadata for data lines */
+	struct pblk_line_metadata sline_meta[PBLK_DATA_LINES];
+	struct pblk_line_metadata eline_meta[PBLK_DATA_LINES];
+	unsigned long meta_bitmap;
+
+	/* Helpers for fast bitmap calculations */
+	unsigned long *bb_template;
+	unsigned long *bb_aux;
+
+	unsigned long d_seq_nr;		/* Data line unique sequence number */
+	unsigned long l_seq_nr;		/* Log line unique sequence number */
+
+	spinlock_t free_lock;
+	spinlock_t gc_lock;
+};
+
+struct pblk_line_meta {
+	unsigned int smeta_len;		/* Total length for smeta */
+	unsigned int smeta_sec;		/* Sectors needed for smeta*/
+	unsigned int emeta_len;		/* Total length for emeta */
+	unsigned int emeta_sec;		/* Sectors needed for emeta*/
+	unsigned int emeta_bb;		/* Boundary for bb that affects emeta */
+	unsigned int sec_bitmap_len;	/* Length for sector bitmap in line */
+	unsigned int blk_bitmap_len;	/* Length for block bitmap in line */
+	unsigned int lun_bitmap_len;	/* Length for lun bitmap in line */
+
+	unsigned int blk_per_line;	/* Number of blocks in a full line */
+	unsigned int sec_per_line;	/* Number of sectors in a line */
+	unsigned int min_blk_line;	/* Min. number of good blocks in line */
+
+	unsigned int mid_thrs;		/* Threshold for GC mid list */
+	unsigned int high_thrs;		/* Threshold for GC high list */
+};
+
+struct pblk_addr_format {
+	u64	ch_mask;
+	u64	lun_mask;
+	u64	pln_mask;
+	u64	blk_mask;
+	u64	pg_mask;
+	u64	sec_mask;
+	u8	ch_offset;
+	u8	lun_offset;
+	u8	pln_offset;
+	u8	blk_offset;
+	u8	pg_offset;
+	u8	sec_offset;
+};
+
+struct pblk {
+	struct nvm_tgt_dev *dev;
+	struct gendisk *disk;
+
+	struct kobject kobj;
+
+	struct pblk_lun *luns;
+
+	struct pblk_line *lines;		/* Line array */
+	struct pblk_line_mgmt l_mg;		/* Line management */
+	struct pblk_line_meta lm;		/* Line metadata */
+
+	int ppaf_bitsize;
+	struct pblk_addr_format ppaf;
+
+	struct pblk_rb rwb;
+
+	int min_write_pgs; /* Minimum amount of pages required by controller */
+	int max_write_pgs; /* Maximum amount of pages supported by controller */
+	int pgs_in_buffer; /* Number of pages that need to be held in buffer to
+			    * guarantee successful reads.
+			    */
+
+	sector_t capacity; /* Device capacity when bad blocks are subtracted */
+	int over_pct;      /* Percentage of device used for over-provisioning */
+
+	/* pblk provisioning values. Used by rate limiter */
+	struct pblk_rl rl;
+
+	struct semaphore erase_sem;
+
+	unsigned char instance_uuid[16];
+#ifdef CONFIG_NVM_DEBUG
+	/* All debug counters apply to 4kb sector I/Os */
+	atomic_long_t inflight_writes;	/* Inflight writes (user and gc) */
+	atomic_long_t padded_writes;	/* Sectors padded due to flush/fua */
+	atomic_long_t padded_wb;	/* Sectors padded in write buffer */
+	atomic_long_t nr_flush;		/* Number of flush/fua I/O */
+	atomic_long_t req_writes;	/* Sectors stored on write buffer */
+	atomic_long_t sub_writes;	/* Sectors submitted from buffer */
+	atomic_long_t sync_writes;	/* Sectors synced to media */
+	atomic_long_t compl_writes;	/* Sectors completed in write bio */
+	atomic_long_t inflight_reads;	/* Inflight sector read requests */
+	atomic_long_t sync_reads;	/* Completed sector read requests */
+	atomic_long_t recov_writes;	/* Sectors submitted from recovery */
+	atomic_long_t recov_gc_writes;	/* Sectors submitted from write GC */
+	atomic_long_t recov_gc_reads;	/* Sectors submitted from read GC */
+#endif
+
+	spinlock_t lock;
+
+	atomic_long_t read_failed;
+	atomic_long_t read_empty;
+	atomic_long_t read_high_ecc;
+	atomic_long_t read_failed_gc;
+	atomic_long_t write_failed;
+	atomic_long_t erase_failed;
+
+	struct task_struct *writer_ts;
+
+	/* Simple translation map of logical addresses to physical addresses.
+	 * The logical addresses is known by the host system, while the physical
+	 * addresses are used when writing to the disk block device.
+	 */
+	unsigned char *trans_map;
+	spinlock_t trans_lock;
+
+	struct list_head compl_list;
+
+	mempool_t *page_pool;
+	mempool_t *line_ws_pool;
+	mempool_t *rec_pool;
+	mempool_t *r_rq_pool;
+	mempool_t *w_rq_pool;
+	mempool_t *line_meta_pool;
+
+	struct workqueue_struct *kw_wq;
+	struct timer_list wtimer;
+
+	struct pblk_gc gc;
+};
+
+struct pblk_line_ws {
+	struct pblk *pblk;
+	struct pblk_line *line;
+	void *priv;
+	struct work_struct ws;
+};
+
+#define pblk_r_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_r_ctx))
+#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
+
+/*
+ * pblk ring buffer operations
+ */
+int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
+		 unsigned int power_size, unsigned int power_seg_sz);
+unsigned int pblk_rb_calculate_size(unsigned int nr_entries);
+void *pblk_rb_entries_ref(struct pblk_rb *rb);
+int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
+			   unsigned int nr_entries, unsigned int *pos);
+int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
+			 unsigned int *pos);
+void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
+			      struct pblk_w_ctx w_ctx, unsigned int pos);
+void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
+			    struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
+			    unsigned int pos);
+struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos);
+
+void pblk_rb_sync_l2p(struct pblk_rb *rb);
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio,
+				 struct pblk_c_ctx *c_ctx,
+				 unsigned int pos,
+				 unsigned int nr_entries,
+				 unsigned int count);
+unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
+				      struct list_head *list,
+				      unsigned int max);
+int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
+			u64 pos, int bio_iter);
+unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
+
+unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags);
+unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries);
+struct pblk_rb_entry *pblk_rb_sync_scan_entry(struct pblk_rb *rb,
+					      struct ppa_addr *ppa);
+void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags);
+unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb);
+
+unsigned int pblk_rb_read_count(struct pblk_rb *rb);
+unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos);
+
+int pblk_rb_tear_down_check(struct pblk_rb *rb);
+int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos);
+void pblk_rb_data_free(struct pblk_rb *rb);
+ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf);
+
+/*
+ * pblk core
+ */
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw);
+int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
+			struct pblk_c_ctx *c_ctx);
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw);
+void pblk_flush_writer(struct pblk *pblk);
+struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba);
+void pblk_discard(struct pblk *pblk, struct bio *bio);
+void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
+void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd);
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd);
+struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
+			      unsigned int nr_secs, unsigned int len,
+			      gfp_t gfp_mask);
+struct pblk_line *pblk_line_get(struct pblk *pblk);
+struct pblk_line *pblk_line_get_first_data(struct pblk *pblk);
+struct pblk_line *pblk_line_replace_data(struct pblk *pblk);
+int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line);
+struct pblk_line *pblk_line_get_data(struct pblk *pblk);
+struct pblk_line *pblk_line_get_data_next(struct pblk *pblk);
+int pblk_line_erase(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_is_full(struct pblk_line *line);
+void pblk_line_free(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_close_ws(struct work_struct *work);
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_mark_bb(struct work_struct *work);
+void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+		      void (*work)(struct work_struct *));
+u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line);
+int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa);
+void pblk_line_put(struct kref *ref);
+struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line);
+u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
+int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
+		   unsigned long secs_to_flush);
+void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+		  unsigned long *lun_bitmap);
+void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+		unsigned long *lun_bitmap);
+void pblk_end_bio_sync(struct bio *bio);
+void pblk_end_io_sync(struct nvm_rq *rqd);
+int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
+		       int nr_pages);
+void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
+			     u64 paddr);
+void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
+			 int nr_pages);
+void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa);
+void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa);
+void pblk_update_map_cache(struct pblk *pblk, sector_t lba,
+			   struct ppa_addr ppa);
+void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
+			 struct ppa_addr ppa, struct ppa_addr entry_line);
+int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+		       struct pblk_line *gc_line);
+void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
+			  u64 *lba_list, int nr_secs);
+void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
+			 sector_t blba, int nr_secs);
+
+/*
+ * pblk user I/O write path
+ */
+int pblk_write_to_cache(struct pblk *pblk, struct bio *bio,
+			unsigned long flags);
+int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list,
+			   unsigned int nr_entries, unsigned int nr_rec_entries,
+			   struct pblk_line *gc_line, unsigned long flags);
+
+/*
+ * pblk map
+ */
+void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+		       unsigned int sentry, unsigned long *lun_bitmap,
+		       unsigned int valid_secs, struct ppa_addr *erase_ppa);
+void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+		 unsigned long *lun_bitmap, unsigned int valid_secs,
+		 unsigned int off);
+
+/*
+ * pblk write thread
+ */
+int pblk_write_ts(void *data);
+void pblk_write_timer_fn(unsigned long data);
+void pblk_write_should_kick(struct pblk *pblk);
+
+/*
+ * pblk read path
+ */
+int pblk_submit_read(struct pblk *pblk, struct bio *bio);
+int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
+			unsigned int nr_secs, unsigned int *secs_to_gc,
+			struct pblk_line *line);
+/*
+ * pblk recovery
+ */
+void pblk_submit_rec(struct work_struct *work);
+struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
+void pblk_recov_pad(struct pblk *pblk);
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta);
+int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
+			struct pblk_rec_ctx *recovery, u64 *comp_bits,
+			unsigned int comp);
+
+/*
+ * pblk gc
+ */
+#define PBLK_GC_TRIES 3
+
+int pblk_gc_init(struct pblk *pblk);
+void pblk_gc_exit(struct pblk *pblk);
+void pblk_gc_should_start(struct pblk *pblk);
+void pblk_gc_should_stop(struct pblk *pblk);
+int pblk_gc_status(struct pblk *pblk);
+void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
+			      int *gc_active);
+void pblk_gc_sysfs_force(struct pblk *pblk, int force);
+
+/*
+ * pblk rate limiter
+ */
+void pblk_rl_init(struct pblk_rl *rl, int budget);
+void pblk_rl_free(struct pblk_rl *rl);
+int pblk_rl_gc_thrs(struct pblk_rl *rl);
+unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl);
+int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries);
+int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc);
+void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv);
+int pblk_rl_sysfs_rate_show(struct pblk_rl *rl);
+void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line);
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line);
+
+/*
+ * pblk sysfs
+ */
+int pblk_sysfs_init(struct gendisk *tdisk);
+void pblk_sysfs_exit(struct gendisk *tdisk);
+
+static inline void *pblk_malloc(size_t size, int type, gfp_t flags)
+{
+	if (type == PBLK_KMALLOC_META)
+		return kmalloc(size, flags);
+	return vmalloc(size);
+}
+
+static inline void pblk_mfree(void *ptr, int type)
+{
+	if (type == PBLK_KMALLOC_META)
+		kfree(ptr);
+	else
+		vfree(ptr);
+}
+
+static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx)
+{
+	return c_ctx - sizeof(struct nvm_rq);
+}
+
+static inline void *pblk_line_emeta_to_lbas(struct line_emeta *emeta)
+{
+	return (emeta) + 1;
+}
+
+#define NVM_MEM_PAGE_WRITE (8)
+
+static inline int pblk_pad_distance(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+
+	return NVM_MEM_PAGE_WRITE * geo->nr_luns * geo->sec_per_pl;
+}
+
+static inline int pblk_dev_ppa_to_line(struct ppa_addr p)
+{
+	return p.g.blk;
+}
+
+static inline int pblk_tgt_ppa_to_line(struct ppa_addr p)
+{
+	return p.g.blk;
+}
+
+static inline int pblk_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
+{
+	return p.g.lun * geo->nr_chnls + p.g.ch;
+}
+
+/* A block within a line corresponds to the lun */
+static inline int pblk_dev_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
+{
+	return p.g.lun * geo->nr_chnls + p.g.ch;
+}
+
+static inline struct ppa_addr pblk_ppa32_to_ppa64(struct pblk *pblk, u32 ppa32)
+{
+	struct ppa_addr ppa64;
+
+	ppa64.ppa = 0;
+
+	if (ppa32 == -1) {
+		ppa64.ppa = ADDR_EMPTY;
+	} else if (ppa32 & (1U << 31)) {
+		ppa64.c.line = ppa32 & ((~0U) >> 1);
+		ppa64.c.is_cached = 1;
+	} else {
+		ppa64.g.blk = (ppa32 & pblk->ppaf.blk_mask) >>
+							pblk->ppaf.blk_offset;
+		ppa64.g.pg = (ppa32 & pblk->ppaf.pg_mask) >>
+							pblk->ppaf.pg_offset;
+		ppa64.g.lun = (ppa32 & pblk->ppaf.lun_mask) >>
+							pblk->ppaf.lun_offset;
+		ppa64.g.ch = (ppa32 & pblk->ppaf.ch_mask) >>
+							pblk->ppaf.ch_offset;
+		ppa64.g.pl = (ppa32 & pblk->ppaf.pln_mask) >>
+							pblk->ppaf.pln_offset;
+		ppa64.g.sec = (ppa32 & pblk->ppaf.sec_mask) >>
+							pblk->ppaf.sec_offset;
+	}
+
+	return ppa64;
+}
+
+static inline struct ppa_addr pblk_trans_map_get(struct pblk *pblk,
+								sector_t lba)
+{
+	struct ppa_addr ppa;
+
+	if (pblk->ppaf_bitsize < 32) {
+		u32 *map = (u32 *)pblk->trans_map;
+
+		ppa = pblk_ppa32_to_ppa64(pblk, map[lba]);
+	} else {
+		struct ppa_addr *map = (struct ppa_addr *)pblk->trans_map;
+
+		ppa = map[lba];
+	}
+
+	return ppa;
+}
+
+static inline u32 pblk_ppa64_to_ppa32(struct pblk *pblk, struct ppa_addr ppa64)
+{
+	u32 ppa32 = 0;
+
+	if (ppa64.ppa == ADDR_EMPTY) {
+		ppa32 = ~0U;
+	} else if (ppa64.c.is_cached) {
+		ppa32 |= ppa64.c.line;
+		ppa32 |= 1U << 31;
+	} else {
+		ppa32 |= ppa64.g.blk << pblk->ppaf.blk_offset;
+		ppa32 |= ppa64.g.pg << pblk->ppaf.pg_offset;
+		ppa32 |= ppa64.g.lun << pblk->ppaf.lun_offset;
+		ppa32 |= ppa64.g.ch << pblk->ppaf.ch_offset;
+		ppa32 |= ppa64.g.pl << pblk->ppaf.pln_offset;
+		ppa32 |= ppa64.g.sec << pblk->ppaf.sec_offset;
+	}
+
+	return ppa32;
+}
+
+static inline void pblk_trans_map_set(struct pblk *pblk, sector_t lba,
+						struct ppa_addr ppa)
+{
+	if (pblk->ppaf_bitsize < 32) {
+		u32 *map = (u32 *)pblk->trans_map;
+
+		map[lba] = pblk_ppa64_to_ppa32(pblk, ppa);
+	} else {
+		u64 *map = (u64 *)pblk->trans_map;
+
+		map[lba] = ppa.ppa;
+	}
+}
+
+static inline u64 pblk_dev_ppa_to_line_addr(struct pblk *pblk,
+							struct ppa_addr p)
+{
+	u64 paddr;
+
+	paddr = 0;
+	paddr |= (u64)p.g.pg << pblk->ppaf.pg_offset;
+	paddr |= (u64)p.g.lun << pblk->ppaf.lun_offset;
+	paddr |= (u64)p.g.ch << pblk->ppaf.ch_offset;
+	paddr |= (u64)p.g.pl << pblk->ppaf.pln_offset;
+	paddr |= (u64)p.g.sec << pblk->ppaf.sec_offset;
+
+	return paddr;
+}
+
+static inline int pblk_ppa_empty(struct ppa_addr ppa_addr)
+{
+	return (ppa_addr.ppa == ADDR_EMPTY);
+}
+
+static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr)
+{
+	ppa_addr->ppa = ADDR_EMPTY;
+}
+
+static inline int pblk_addr_in_cache(struct ppa_addr ppa)
+{
+	return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached);
+}
+
+static inline int pblk_addr_to_cacheline(struct ppa_addr ppa)
+{
+	return ppa.c.line;
+}
+
+static inline struct ppa_addr pblk_cacheline_to_addr(int addr)
+{
+	struct ppa_addr p;
+
+	p.c.line = addr;
+	p.c.is_cached = 1;
+
+	return p;
+}
+
+static inline struct ppa_addr addr_to_gen_ppa(struct pblk *pblk, u64 paddr,
+					      u64 line_id)
+{
+	struct ppa_addr ppa;
+
+	ppa.ppa = 0;
+	ppa.g.blk = line_id;
+	ppa.g.pg = (paddr & pblk->ppaf.pg_mask) >> pblk->ppaf.pg_offset;
+	ppa.g.lun = (paddr & pblk->ppaf.lun_mask) >> pblk->ppaf.lun_offset;
+	ppa.g.ch = (paddr & pblk->ppaf.ch_mask) >> pblk->ppaf.ch_offset;
+	ppa.g.pl = (paddr & pblk->ppaf.pln_mask) >> pblk->ppaf.pln_offset;
+	ppa.g.sec = (paddr & pblk->ppaf.sec_mask) >> pblk->ppaf.sec_offset;
+
+	return ppa;
+}
+
+static inline struct ppa_addr addr_to_pblk_ppa(struct pblk *pblk, u64 paddr,
+					 u64 line_id)
+{
+	struct ppa_addr ppa;
+
+	ppa = addr_to_gen_ppa(pblk, paddr, line_id);
+
+	return ppa;
+}
+
+static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk,
+					    struct line_smeta *smeta)
+{
+	u32 crc = ~(u32)0;
+
+	crc = crc32_le(crc, (unsigned char *)smeta + sizeof(crc),
+				sizeof(struct line_header) - sizeof(crc));
+
+	return crc;
+}
+
+static inline u32 pblk_calc_smeta_crc(struct pblk *pblk,
+				      struct line_smeta *smeta)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	u32 crc = ~(u32)0;
+
+	crc = crc32_le(crc, (unsigned char *)smeta +
+				sizeof(struct line_header) + sizeof(crc),
+				lm->smeta_len -
+				sizeof(struct line_header) - sizeof(crc));
+
+	return crc;
+}
+
+static inline u32 pblk_calc_emeta_crc(struct pblk *pblk,
+				      struct line_emeta *emeta)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	u32 crc = ~(u32)0;
+
+	crc = crc32_le(crc, (unsigned char *)emeta +
+				sizeof(struct line_header) + sizeof(crc),
+				lm->emeta_len -
+				sizeof(struct line_header) - sizeof(crc));
+
+	return crc;
+}
+
+static inline int pblk_set_progr_mode(struct pblk *pblk, int type)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	int flags;
+
+	flags = geo->plane_mode >> 1;
+
+	if (type == WRITE)
+		flags |= NVM_IO_SCRAMBLE_ENABLE;
+
+	return flags;
+}
+
+static inline int pblk_set_read_mode(struct pblk *pblk)
+{
+	return NVM_IO_SNGL_ACCESS | NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE;
+}
+
+#ifdef CONFIG_NVM_DEBUG
+static inline void print_ppa(struct ppa_addr *p, char *msg, int error)
+{
+	if (p->c.is_cached) {
+		pr_err("ppa: (%s: %x) cache line: %llu\n",
+				msg, error, (u64)p->c.line);
+	} else {
+		pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+			msg, error,
+			p->g.ch, p->g.lun, p->g.blk,
+			p->g.pg, p->g.pl, p->g.sec);
+	}
+}
+
+static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
+					 int error)
+{
+	int bit = -1;
+
+	if (rqd->nr_ppas ==  1) {
+		print_ppa(&rqd->ppa_addr, "rqd", error);
+		return;
+	}
+
+	while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
+						bit + 1)) < rqd->nr_ppas) {
+		print_ppa(&rqd->ppa_list[bit], "rqd", error);
+	}
+
+	pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+}
+#endif
+
+static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
+				       struct ppa_addr *ppas, int nr_ppas)
+{
+	struct nvm_geo *geo = &tgt_dev->geo;
+	struct ppa_addr *ppa;
+	int i;
+
+	for (i = 0; i < nr_ppas; i++) {
+		ppa = &ppas[i];
+
+		if (!ppa->c.is_cached &&
+				ppa->g.ch < geo->nr_chnls &&
+				ppa->g.lun < geo->luns_per_chnl &&
+				ppa->g.pl < geo->nr_planes &&
+				ppa->g.blk < geo->blks_per_lun &&
+				ppa->g.pg < geo->pgs_per_blk &&
+				ppa->g.sec < geo->sec_per_pg)
+			continue;
+
+#ifdef CONFIG_NVM_DEBUG
+		print_ppa(ppa, "boundary", i);
+#endif
+		return 1;
+	}
+	return 0;
+}
+
+static inline int pblk_boundary_paddr_checks(struct pblk *pblk, u64 paddr)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+
+	if (paddr > lm->sec_per_line)
+		return 1;
+
+	return 0;
+}
+
+static inline unsigned int pblk_get_bi_idx(struct bio *bio)
+{
+	return bio->bi_iter.bi_idx;
+}
+
+static inline sector_t pblk_get_lba(struct bio *bio)
+{
+	return bio->bi_iter.bi_sector / NR_PHY_IN_LOG;
+}
+
+static inline unsigned int pblk_get_secs(struct bio *bio)
+{
+	return  bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE;
+}
+
+static inline sector_t pblk_get_sector(sector_t lba)
+{
+	return lba * NR_PHY_IN_LOG;
+}
+
+static inline void pblk_setup_uuid(struct pblk *pblk)
+{
+	uuid_le uuid;
+
+	uuid_le_gen(&uuid);
+	memcpy(pblk->instance_uuid, uuid.b, 16);
+}
+#endif /* PBLK_H_ */
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index e00b1d7b976f..cf0e28a0ff61 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -318,10 +318,6 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk)
 	}
 
 	page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
-	if (!page) {
-		bio_put(bio);
-		return -ENOMEM;
-	}
 
 	while ((slot = find_first_zero_bit(rblk->invalid_pages,
 					    nr_sec_per_blk)) < nr_sec_per_blk) {
@@ -414,7 +410,6 @@ static void rrpc_block_gc(struct work_struct *work)
 	struct rrpc *rrpc = gcb->rrpc;
 	struct rrpc_block *rblk = gcb->rblk;
 	struct rrpc_lun *rlun = rblk->rlun;
-	struct nvm_tgt_dev *dev = rrpc->dev;
 	struct ppa_addr ppa;
 
 	mempool_free(gcb, rrpc->gcb_pool);
@@ -430,7 +425,7 @@ static void rrpc_block_gc(struct work_struct *work)
 	ppa.g.lun = rlun->bppa.g.lun;
 	ppa.g.blk = rblk->id;
 
-	if (nvm_erase_blk(dev, &ppa, 0))
+	if (nvm_erase_sync(rrpc->dev, &ppa, 1))
 		goto put_back;
 
 	rrpc_put_blk(rrpc, rblk);
@@ -822,7 +817,7 @@ static int rrpc_read_ppalist_rq(struct rrpc *rrpc, struct bio *bio,
 
 	for (i = 0; i < npages; i++) {
 		/* We assume that mapping occurs at 4KB granularity */
-		BUG_ON(!(laddr + i >= 0 && laddr + i < rrpc->nr_sects));
+		BUG_ON(!(laddr + i < rrpc->nr_sects));
 		gp = &rrpc->trans_map[laddr + i];
 
 		if (gp->rblk) {
@@ -851,7 +846,7 @@ static int rrpc_read_rq(struct rrpc *rrpc, struct bio *bio, struct nvm_rq *rqd,
 	if (!is_gc && rrpc_lock_rq(rrpc, bio, rqd))
 		return NVM_IO_REQUEUE;
 
-	BUG_ON(!(laddr >= 0 && laddr < rrpc->nr_sects));
+	BUG_ON(!(laddr < rrpc->nr_sects));
 	gp = &rrpc->trans_map[laddr];
 
 	if (gp->rblk) {
@@ -1007,11 +1002,6 @@ static blk_qc_t rrpc_make_rq(struct request_queue *q, struct bio *bio)
 	}
 
 	rqd = mempool_alloc(rrpc->rq_pool, GFP_KERNEL);
-	if (!rqd) {
-		pr_err_ratelimited("rrpc: not able to queue bio.");
-		bio_io_error(bio);
-		return BLK_QC_T_NONE;
-	}
 	memset(rqd, 0, sizeof(struct nvm_rq));
 
 	err = rrpc_submit_io(rrpc, bio, rqd, NVM_IOTYPE_NONE);
@@ -1275,8 +1265,10 @@ static int rrpc_bb_discovery(struct nvm_tgt_dev *dev, struct rrpc_lun *rlun)
 	}
 
 	nr_blks = nvm_bb_tbl_fold(dev->parent, blks, nr_blks);
-	if (nr_blks < 0)
-		return nr_blks;
+	if (nr_blks < 0) {
+		ret = nr_blks;
+		goto out;
+	}
 
 	for (i = 0; i < nr_blks; i++) {
 		if (blks[i] == NVM_BLK_T_FREE)
@@ -1514,7 +1506,8 @@ err:
 
 static struct nvm_tgt_type tt_rrpc;
 
-static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk)
+static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
+		       int flags)
 {
 	struct request_queue *bqueue = dev->q;
 	struct request_queue *tqueue = tdisk->queue;
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 3f041b187033..f757cef293f8 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -392,6 +392,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	 * To get all the fields, copy all archdata
 	 */
 	dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata;
+	dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops;
 #endif /* CONFIG_PCI */
 
 #ifdef DEBUG
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index ceff415f201c..ee1a3d9147ef 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -144,12 +144,22 @@ config XGENE_SLIMPRO_MBOX
 	  want to use the APM X-Gene SLIMpro IPCM support.
 
 config BCM_PDC_MBOX
-	tristate "Broadcom PDC Mailbox"
-	depends on ARM64 || COMPILE_TEST
+	tristate "Broadcom FlexSparx DMA Mailbox"
+	depends on ARCH_BCM_IPROC || COMPILE_TEST
 	depends on HAS_DMA
+	help
+	  Mailbox implementation for the Broadcom FlexSparx DMA ring manager,
+	  which provides access to various offload engines on Broadcom
+	  SoCs, including FA2/FA+ on Northstar Plus and PDC on Northstar 2.
+
+config BCM_FLEXRM_MBOX
+	tristate "Broadcom FlexRM Mailbox"
+	depends on ARM64
+	depends on HAS_DMA
+	select GENERIC_MSI_IRQ_DOMAIN
 	default ARCH_BCM_IPROC
 	help
-	  Mailbox implementation for the Broadcom PDC ring manager,
+	  Mailbox implementation of the Broadcom FlexRM ring manager,
 	  which provides access to various offload engines on Broadcom
-	  SoCs. Say Y here if you want to use the Broadcom PDC.
+	  SoCs. Say Y here if you want to use the Broadcom FlexRM.
 endif
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 7dde4f609ae8..e2bcb03cd35b 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -30,4 +30,6 @@ obj-$(CONFIG_HI6220_MBOX)	+= hi6220-mailbox.o
 
 obj-$(CONFIG_BCM_PDC_MBOX)	+= bcm-pdc-mailbox.o
 
+obj-$(CONFIG_BCM_FLEXRM_MBOX)	+= bcm-flexrm-mailbox.o
+
 obj-$(CONFIG_TEGRA_HSP_MBOX)	+= tegra-hsp.o
diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c
new file mode 100644
index 000000000000..da67882caa7b
--- /dev/null
+++ b/drivers/mailbox/bcm-flexrm-mailbox.c
@@ -0,0 +1,1595 @@
+/* Broadcom FlexRM Mailbox Driver
+ *
+ * Copyright (C) 2017 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Each Broadcom FlexSparx4 offload engine is implemented as an
+ * extension to Broadcom FlexRM ring manager. The FlexRM ring
+ * manager provides a set of rings which can be used to submit
+ * work to a FlexSparx4 offload engine.
+ *
+ * This driver creates a mailbox controller using a set of FlexRM
+ * rings where each mailbox channel represents a separate FlexRM ring.
+ */
+
+#include <asm/barrier.h>
+#include <asm/byteorder.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/idr.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox_client.h>
+#include <linux/mailbox/brcm-message.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+/* ====== FlexRM register defines ===== */
+
+/* FlexRM configuration */
+#define RING_REGS_SIZE					0x10000
+#define RING_DESC_SIZE					8
+#define RING_DESC_INDEX(offset)				\
+			((offset) / RING_DESC_SIZE)
+#define RING_DESC_OFFSET(index)				\
+			((index) * RING_DESC_SIZE)
+#define RING_MAX_REQ_COUNT				1024
+#define RING_BD_ALIGN_ORDER				12
+#define RING_BD_ALIGN_CHECK(addr)			\
+			(!((addr) & ((0x1 << RING_BD_ALIGN_ORDER) - 1)))
+#define RING_BD_TOGGLE_INVALID(offset)			\
+			(((offset) >> RING_BD_ALIGN_ORDER) & 0x1)
+#define RING_BD_TOGGLE_VALID(offset)			\
+			(!RING_BD_TOGGLE_INVALID(offset))
+#define RING_BD_DESC_PER_REQ				32
+#define RING_BD_DESC_COUNT				\
+			(RING_MAX_REQ_COUNT * RING_BD_DESC_PER_REQ)
+#define RING_BD_SIZE					\
+			(RING_BD_DESC_COUNT * RING_DESC_SIZE)
+#define RING_CMPL_ALIGN_ORDER				13
+#define RING_CMPL_DESC_COUNT				RING_MAX_REQ_COUNT
+#define RING_CMPL_SIZE					\
+			(RING_CMPL_DESC_COUNT * RING_DESC_SIZE)
+#define RING_VER_MAGIC					0x76303031
+
+/* Per-Ring register offsets */
+#define RING_VER					0x000
+#define RING_BD_START_ADDR				0x004
+#define RING_BD_READ_PTR				0x008
+#define RING_BD_WRITE_PTR				0x00c
+#define RING_BD_READ_PTR_DDR_LS				0x010
+#define RING_BD_READ_PTR_DDR_MS				0x014
+#define RING_CMPL_START_ADDR				0x018
+#define RING_CMPL_WRITE_PTR				0x01c
+#define RING_NUM_REQ_RECV_LS				0x020
+#define RING_NUM_REQ_RECV_MS				0x024
+#define RING_NUM_REQ_TRANS_LS				0x028
+#define RING_NUM_REQ_TRANS_MS				0x02c
+#define RING_NUM_REQ_OUTSTAND				0x030
+#define RING_CONTROL					0x034
+#define RING_FLUSH_DONE					0x038
+#define RING_MSI_ADDR_LS				0x03c
+#define RING_MSI_ADDR_MS				0x040
+#define RING_MSI_CONTROL				0x048
+#define RING_BD_READ_PTR_DDR_CONTROL			0x04c
+#define RING_MSI_DATA_VALUE				0x064
+
+/* Register RING_BD_START_ADDR fields */
+#define BD_LAST_UPDATE_HW_SHIFT				28
+#define BD_LAST_UPDATE_HW_MASK				0x1
+#define BD_START_ADDR_VALUE(pa)				\
+	((u32)((((dma_addr_t)(pa)) >> RING_BD_ALIGN_ORDER) & 0x0fffffff))
+#define BD_START_ADDR_DECODE(val)			\
+	((dma_addr_t)((val) & 0x0fffffff) << RING_BD_ALIGN_ORDER)
+
+/* Register RING_CMPL_START_ADDR fields */
+#define CMPL_START_ADDR_VALUE(pa)			\
+	((u32)((((u64)(pa)) >> RING_CMPL_ALIGN_ORDER) & 0x03ffffff))
+
+/* Register RING_CONTROL fields */
+#define CONTROL_MASK_DISABLE_CONTROL			12
+#define CONTROL_FLUSH_SHIFT				5
+#define CONTROL_ACTIVE_SHIFT				4
+#define CONTROL_RATE_ADAPT_MASK				0xf
+#define CONTROL_RATE_DYNAMIC				0x0
+#define CONTROL_RATE_FAST				0x8
+#define CONTROL_RATE_MEDIUM				0x9
+#define CONTROL_RATE_SLOW				0xa
+#define CONTROL_RATE_IDLE				0xb
+
+/* Register RING_FLUSH_DONE fields */
+#define FLUSH_DONE_MASK					0x1
+
+/* Register RING_MSI_CONTROL fields */
+#define MSI_TIMER_VAL_SHIFT				16
+#define MSI_TIMER_VAL_MASK				0xffff
+#define MSI_ENABLE_SHIFT				15
+#define MSI_ENABLE_MASK					0x1
+#define MSI_COUNT_SHIFT					0
+#define MSI_COUNT_MASK					0x3ff
+
+/* Register RING_BD_READ_PTR_DDR_CONTROL fields */
+#define BD_READ_PTR_DDR_TIMER_VAL_SHIFT			16
+#define BD_READ_PTR_DDR_TIMER_VAL_MASK			0xffff
+#define BD_READ_PTR_DDR_ENABLE_SHIFT			15
+#define BD_READ_PTR_DDR_ENABLE_MASK			0x1
+
+/* ====== FlexRM ring descriptor defines ===== */
+
+/* Completion descriptor format */
+#define CMPL_OPAQUE_SHIFT			0
+#define CMPL_OPAQUE_MASK			0xffff
+#define CMPL_ENGINE_STATUS_SHIFT		16
+#define CMPL_ENGINE_STATUS_MASK			0xffff
+#define CMPL_DME_STATUS_SHIFT			32
+#define CMPL_DME_STATUS_MASK			0xffff
+#define CMPL_RM_STATUS_SHIFT			48
+#define CMPL_RM_STATUS_MASK			0xffff
+
+/* Completion DME status code */
+#define DME_STATUS_MEM_COR_ERR			BIT(0)
+#define DME_STATUS_MEM_UCOR_ERR			BIT(1)
+#define DME_STATUS_FIFO_UNDERFLOW		BIT(2)
+#define DME_STATUS_FIFO_OVERFLOW		BIT(3)
+#define DME_STATUS_RRESP_ERR			BIT(4)
+#define DME_STATUS_BRESP_ERR			BIT(5)
+#define DME_STATUS_ERROR_MASK			(DME_STATUS_MEM_COR_ERR | \
+						 DME_STATUS_MEM_UCOR_ERR | \
+						 DME_STATUS_FIFO_UNDERFLOW | \
+						 DME_STATUS_FIFO_OVERFLOW | \
+						 DME_STATUS_RRESP_ERR | \
+						 DME_STATUS_BRESP_ERR)
+
+/* Completion RM status code */
+#define RM_STATUS_CODE_SHIFT			0
+#define RM_STATUS_CODE_MASK			0x3ff
+#define RM_STATUS_CODE_GOOD			0x0
+#define RM_STATUS_CODE_AE_TIMEOUT		0x3ff
+
+/* General descriptor format */
+#define DESC_TYPE_SHIFT				60
+#define DESC_TYPE_MASK				0xf
+#define DESC_PAYLOAD_SHIFT			0
+#define DESC_PAYLOAD_MASK			0x0fffffffffffffff
+
+/* Null descriptor format  */
+#define NULL_TYPE				0
+#define NULL_TOGGLE_SHIFT			58
+#define NULL_TOGGLE_MASK			0x1
+
+/* Header descriptor format */
+#define HEADER_TYPE				1
+#define HEADER_TOGGLE_SHIFT			58
+#define HEADER_TOGGLE_MASK			0x1
+#define HEADER_ENDPKT_SHIFT			57
+#define HEADER_ENDPKT_MASK			0x1
+#define HEADER_STARTPKT_SHIFT			56
+#define HEADER_STARTPKT_MASK			0x1
+#define HEADER_BDCOUNT_SHIFT			36
+#define HEADER_BDCOUNT_MASK			0x1f
+#define HEADER_BDCOUNT_MAX			HEADER_BDCOUNT_MASK
+#define HEADER_FLAGS_SHIFT			16
+#define HEADER_FLAGS_MASK			0xffff
+#define HEADER_OPAQUE_SHIFT			0
+#define HEADER_OPAQUE_MASK			0xffff
+
+/* Source (SRC) descriptor format */
+#define SRC_TYPE				2
+#define SRC_LENGTH_SHIFT			44
+#define SRC_LENGTH_MASK				0xffff
+#define SRC_ADDR_SHIFT				0
+#define SRC_ADDR_MASK				0x00000fffffffffff
+
+/* Destination (DST) descriptor format */
+#define DST_TYPE				3
+#define DST_LENGTH_SHIFT			44
+#define DST_LENGTH_MASK				0xffff
+#define DST_ADDR_SHIFT				0
+#define DST_ADDR_MASK				0x00000fffffffffff
+
+/* Immediate (IMM) descriptor format */
+#define IMM_TYPE				4
+#define IMM_DATA_SHIFT				0
+#define IMM_DATA_MASK				0x0fffffffffffffff
+
+/* Next pointer (NPTR) descriptor format */
+#define NPTR_TYPE				5
+#define NPTR_TOGGLE_SHIFT			58
+#define NPTR_TOGGLE_MASK			0x1
+#define NPTR_ADDR_SHIFT				0
+#define NPTR_ADDR_MASK				0x00000fffffffffff
+
+/* Mega source (MSRC) descriptor format */
+#define MSRC_TYPE				6
+#define MSRC_LENGTH_SHIFT			44
+#define MSRC_LENGTH_MASK			0xffff
+#define MSRC_ADDR_SHIFT				0
+#define MSRC_ADDR_MASK				0x00000fffffffffff
+
+/* Mega destination (MDST) descriptor format */
+#define MDST_TYPE				7
+#define MDST_LENGTH_SHIFT			44
+#define MDST_LENGTH_MASK			0xffff
+#define MDST_ADDR_SHIFT				0
+#define MDST_ADDR_MASK				0x00000fffffffffff
+
+/* Source with tlast (SRCT) descriptor format */
+#define SRCT_TYPE				8
+#define SRCT_LENGTH_SHIFT			44
+#define SRCT_LENGTH_MASK			0xffff
+#define SRCT_ADDR_SHIFT				0
+#define SRCT_ADDR_MASK				0x00000fffffffffff
+
+/* Destination with tlast (DSTT) descriptor format */
+#define DSTT_TYPE				9
+#define DSTT_LENGTH_SHIFT			44
+#define DSTT_LENGTH_MASK			0xffff
+#define DSTT_ADDR_SHIFT				0
+#define DSTT_ADDR_MASK				0x00000fffffffffff
+
+/* Immediate with tlast (IMMT) descriptor format */
+#define IMMT_TYPE				10
+#define IMMT_DATA_SHIFT				0
+#define IMMT_DATA_MASK				0x0fffffffffffffff
+
+/* Descriptor helper macros */
+#define DESC_DEC(_d, _s, _m)			(((_d) >> (_s)) & (_m))
+#define DESC_ENC(_d, _v, _s, _m)		\
+			do { \
+				(_d) &= ~((u64)(_m) << (_s)); \
+				(_d) |= (((u64)(_v) & (_m)) << (_s)); \
+			} while (0)
+
+/* ====== FlexRM data structures ===== */
+
+struct flexrm_ring {
+	/* Unprotected members */
+	int num;
+	struct flexrm_mbox *mbox;
+	void __iomem *regs;
+	bool irq_requested;
+	unsigned int irq;
+	unsigned int msi_timer_val;
+	unsigned int msi_count_threshold;
+	struct ida requests_ida;
+	struct brcm_message *requests[RING_MAX_REQ_COUNT];
+	void *bd_base;
+	dma_addr_t bd_dma_base;
+	u32 bd_write_offset;
+	void *cmpl_base;
+	dma_addr_t cmpl_dma_base;
+	/* Protected members */
+	spinlock_t lock;
+	struct brcm_message *last_pending_msg;
+	u32 cmpl_read_offset;
+};
+
+struct flexrm_mbox {
+	struct device *dev;
+	void __iomem *regs;
+	u32 num_rings;
+	struct flexrm_ring *rings;
+	struct dma_pool *bd_pool;
+	struct dma_pool *cmpl_pool;
+	struct mbox_controller controller;
+};
+
+/* ====== FlexRM ring descriptor helper routines ===== */
+
+static u64 flexrm_read_desc(void *desc_ptr)
+{
+	return le64_to_cpu(*((u64 *)desc_ptr));
+}
+
+static void flexrm_write_desc(void *desc_ptr, u64 desc)
+{
+	*((u64 *)desc_ptr) = cpu_to_le64(desc);
+}
+
+static u32 flexrm_cmpl_desc_to_reqid(u64 cmpl_desc)
+{
+	return (u32)(cmpl_desc & CMPL_OPAQUE_MASK);
+}
+
+static int flexrm_cmpl_desc_to_error(u64 cmpl_desc)
+{
+	u32 status;
+
+	status = DESC_DEC(cmpl_desc, CMPL_DME_STATUS_SHIFT,
+			  CMPL_DME_STATUS_MASK);
+	if (status & DME_STATUS_ERROR_MASK)
+		return -EIO;
+
+	status = DESC_DEC(cmpl_desc, CMPL_RM_STATUS_SHIFT,
+			  CMPL_RM_STATUS_MASK);
+	status &= RM_STATUS_CODE_MASK;
+	if (status == RM_STATUS_CODE_AE_TIMEOUT)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static bool flexrm_is_next_table_desc(void *desc_ptr)
+{
+	u64 desc = flexrm_read_desc(desc_ptr);
+	u32 type = DESC_DEC(desc, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+
+	return (type == NPTR_TYPE) ? true : false;
+}
+
+static u64 flexrm_next_table_desc(u32 toggle, dma_addr_t next_addr)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, NPTR_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, toggle, NPTR_TOGGLE_SHIFT, NPTR_TOGGLE_MASK);
+	DESC_ENC(desc, next_addr, NPTR_ADDR_SHIFT, NPTR_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_null_desc(u32 toggle)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, NULL_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, toggle, NULL_TOGGLE_SHIFT, NULL_TOGGLE_MASK);
+
+	return desc;
+}
+
+static u32 flexrm_estimate_header_desc_count(u32 nhcnt)
+{
+	u32 hcnt = nhcnt / HEADER_BDCOUNT_MAX;
+
+	if (!(nhcnt % HEADER_BDCOUNT_MAX))
+		hcnt += 1;
+
+	return hcnt;
+}
+
+static void flexrm_flip_header_toogle(void *desc_ptr)
+{
+	u64 desc = flexrm_read_desc(desc_ptr);
+
+	if (desc & ((u64)0x1 << HEADER_TOGGLE_SHIFT))
+		desc &= ~((u64)0x1 << HEADER_TOGGLE_SHIFT);
+	else
+		desc |= ((u64)0x1 << HEADER_TOGGLE_SHIFT);
+
+	flexrm_write_desc(desc_ptr, desc);
+}
+
+static u64 flexrm_header_desc(u32 toggle, u32 startpkt, u32 endpkt,
+			       u32 bdcount, u32 flags, u32 opaque)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, HEADER_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, toggle, HEADER_TOGGLE_SHIFT, HEADER_TOGGLE_MASK);
+	DESC_ENC(desc, startpkt, HEADER_STARTPKT_SHIFT, HEADER_STARTPKT_MASK);
+	DESC_ENC(desc, endpkt, HEADER_ENDPKT_SHIFT, HEADER_ENDPKT_MASK);
+	DESC_ENC(desc, bdcount, HEADER_BDCOUNT_SHIFT, HEADER_BDCOUNT_MASK);
+	DESC_ENC(desc, flags, HEADER_FLAGS_SHIFT, HEADER_FLAGS_MASK);
+	DESC_ENC(desc, opaque, HEADER_OPAQUE_SHIFT, HEADER_OPAQUE_MASK);
+
+	return desc;
+}
+
+static void flexrm_enqueue_desc(u32 nhpos, u32 nhcnt, u32 reqid,
+				 u64 desc, void **desc_ptr, u32 *toggle,
+				 void *start_desc, void *end_desc)
+{
+	u64 d;
+	u32 nhavail, _toggle, _startpkt, _endpkt, _bdcount;
+
+	/* Sanity check */
+	if (nhcnt <= nhpos)
+		return;
+
+	/*
+	 * Each request or packet start with a HEADER descriptor followed
+	 * by one or more non-HEADER descriptors (SRC, SRCT, MSRC, DST,
+	 * DSTT, MDST, IMM, and IMMT). The number of non-HEADER descriptors
+	 * following a HEADER descriptor is represented by BDCOUNT field
+	 * of HEADER descriptor. The max value of BDCOUNT field is 31 which
+	 * means we can only have 31 non-HEADER descriptors following one
+	 * HEADER descriptor.
+	 *
+	 * In general use, number of non-HEADER descriptors can easily go
+	 * beyond 31. To tackle this situation, we have packet (or request)
+	 * extenstion bits (STARTPKT and ENDPKT) in the HEADER descriptor.
+	 *
+	 * To use packet extension, the first HEADER descriptor of request
+	 * (or packet) will have STARTPKT=1 and ENDPKT=0. The intermediate
+	 * HEADER descriptors will have STARTPKT=0 and ENDPKT=0. The last
+	 * HEADER descriptor will have STARTPKT=0 and ENDPKT=1. Also, the
+	 * TOGGLE bit of the first HEADER will be set to invalid state to
+	 * ensure that FlexRM does not start fetching descriptors till all
+	 * descriptors are enqueued. The user of this function will flip
+	 * the TOGGLE bit of first HEADER after all descriptors are
+	 * enqueued.
+	 */
+
+	if ((nhpos % HEADER_BDCOUNT_MAX == 0) && (nhcnt - nhpos)) {
+		/* Prepare the header descriptor */
+		nhavail = (nhcnt - nhpos);
+		_toggle = (nhpos == 0) ? !(*toggle) : (*toggle);
+		_startpkt = (nhpos == 0) ? 0x1 : 0x0;
+		_endpkt = (nhavail <= HEADER_BDCOUNT_MAX) ? 0x1 : 0x0;
+		_bdcount = (nhavail <= HEADER_BDCOUNT_MAX) ?
+				nhavail : HEADER_BDCOUNT_MAX;
+		if (nhavail <= HEADER_BDCOUNT_MAX)
+			_bdcount = nhavail;
+		else
+			_bdcount = HEADER_BDCOUNT_MAX;
+		d = flexrm_header_desc(_toggle, _startpkt, _endpkt,
+					_bdcount, 0x0, reqid);
+
+		/* Write header descriptor */
+		flexrm_write_desc(*desc_ptr, d);
+
+		/* Point to next descriptor */
+		*desc_ptr += sizeof(desc);
+		if (*desc_ptr == end_desc)
+			*desc_ptr = start_desc;
+
+		/* Skip next pointer descriptors */
+		while (flexrm_is_next_table_desc(*desc_ptr)) {
+			*toggle = (*toggle) ? 0 : 1;
+			*desc_ptr += sizeof(desc);
+			if (*desc_ptr == end_desc)
+				*desc_ptr = start_desc;
+		}
+	}
+
+	/* Write desired descriptor */
+	flexrm_write_desc(*desc_ptr, desc);
+
+	/* Point to next descriptor */
+	*desc_ptr += sizeof(desc);
+	if (*desc_ptr == end_desc)
+		*desc_ptr = start_desc;
+
+	/* Skip next pointer descriptors */
+	while (flexrm_is_next_table_desc(*desc_ptr)) {
+		*toggle = (*toggle) ? 0 : 1;
+		*desc_ptr += sizeof(desc);
+		if (*desc_ptr == end_desc)
+			*desc_ptr = start_desc;
+	}
+}
+
+static u64 flexrm_src_desc(dma_addr_t addr, unsigned int length)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, SRC_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, length, SRC_LENGTH_SHIFT, SRC_LENGTH_MASK);
+	DESC_ENC(desc, addr, SRC_ADDR_SHIFT, SRC_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_msrc_desc(dma_addr_t addr, unsigned int length_div_16)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, MSRC_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, length_div_16, MSRC_LENGTH_SHIFT, MSRC_LENGTH_MASK);
+	DESC_ENC(desc, addr, MSRC_ADDR_SHIFT, MSRC_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_dst_desc(dma_addr_t addr, unsigned int length)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, DST_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, length, DST_LENGTH_SHIFT, DST_LENGTH_MASK);
+	DESC_ENC(desc, addr, DST_ADDR_SHIFT, DST_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_mdst_desc(dma_addr_t addr, unsigned int length_div_16)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, MDST_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, length_div_16, MDST_LENGTH_SHIFT, MDST_LENGTH_MASK);
+	DESC_ENC(desc, addr, MDST_ADDR_SHIFT, MDST_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_imm_desc(u64 data)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, IMM_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, data, IMM_DATA_SHIFT, IMM_DATA_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_srct_desc(dma_addr_t addr, unsigned int length)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, SRCT_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, length, SRCT_LENGTH_SHIFT, SRCT_LENGTH_MASK);
+	DESC_ENC(desc, addr, SRCT_ADDR_SHIFT, SRCT_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_dstt_desc(dma_addr_t addr, unsigned int length)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, DSTT_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, length, DSTT_LENGTH_SHIFT, DSTT_LENGTH_MASK);
+	DESC_ENC(desc, addr, DSTT_ADDR_SHIFT, DSTT_ADDR_MASK);
+
+	return desc;
+}
+
+static u64 flexrm_immt_desc(u64 data)
+{
+	u64 desc = 0;
+
+	DESC_ENC(desc, IMMT_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+	DESC_ENC(desc, data, IMMT_DATA_SHIFT, IMMT_DATA_MASK);
+
+	return desc;
+}
+
+static bool flexrm_spu_sanity_check(struct brcm_message *msg)
+{
+	struct scatterlist *sg;
+
+	if (!msg->spu.src || !msg->spu.dst)
+		return false;
+	for (sg = msg->spu.src; sg; sg = sg_next(sg)) {
+		if (sg->length & 0xf) {
+			if (sg->length > SRC_LENGTH_MASK)
+				return false;
+		} else {
+			if (sg->length > (MSRC_LENGTH_MASK * 16))
+				return false;
+		}
+	}
+	for (sg = msg->spu.dst; sg; sg = sg_next(sg)) {
+		if (sg->length & 0xf) {
+			if (sg->length > DST_LENGTH_MASK)
+				return false;
+		} else {
+			if (sg->length > (MDST_LENGTH_MASK * 16))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static u32 flexrm_spu_estimate_nonheader_desc_count(struct brcm_message *msg)
+{
+	u32 cnt = 0;
+	unsigned int dst_target = 0;
+	struct scatterlist *src_sg = msg->spu.src, *dst_sg = msg->spu.dst;
+
+	while (src_sg || dst_sg) {
+		if (src_sg) {
+			cnt++;
+			dst_target = src_sg->length;
+			src_sg = sg_next(src_sg);
+		} else
+			dst_target = UINT_MAX;
+
+		while (dst_target && dst_sg) {
+			cnt++;
+			if (dst_sg->length < dst_target)
+				dst_target -= dst_sg->length;
+			else
+				dst_target = 0;
+			dst_sg = sg_next(dst_sg);
+		}
+	}
+
+	return cnt;
+}
+
+static int flexrm_spu_dma_map(struct device *dev, struct brcm_message *msg)
+{
+	int rc;
+
+	rc = dma_map_sg(dev, msg->spu.src, sg_nents(msg->spu.src),
+			DMA_TO_DEVICE);
+	if (rc < 0)
+		return rc;
+
+	rc = dma_map_sg(dev, msg->spu.dst, sg_nents(msg->spu.dst),
+			DMA_FROM_DEVICE);
+	if (rc < 0) {
+		dma_unmap_sg(dev, msg->spu.src, sg_nents(msg->spu.src),
+			     DMA_TO_DEVICE);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void flexrm_spu_dma_unmap(struct device *dev, struct brcm_message *msg)
+{
+	dma_unmap_sg(dev, msg->spu.dst, sg_nents(msg->spu.dst),
+		     DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, msg->spu.src, sg_nents(msg->spu.src),
+		     DMA_TO_DEVICE);
+}
+
+static void *flexrm_spu_write_descs(struct brcm_message *msg, u32 nhcnt,
+				     u32 reqid, void *desc_ptr, u32 toggle,
+				     void *start_desc, void *end_desc)
+{
+	u64 d;
+	u32 nhpos = 0;
+	void *orig_desc_ptr = desc_ptr;
+	unsigned int dst_target = 0;
+	struct scatterlist *src_sg = msg->spu.src, *dst_sg = msg->spu.dst;
+
+	while (src_sg || dst_sg) {
+		if (src_sg) {
+			if (sg_dma_len(src_sg) & 0xf)
+				d = flexrm_src_desc(sg_dma_address(src_sg),
+						     sg_dma_len(src_sg));
+			else
+				d = flexrm_msrc_desc(sg_dma_address(src_sg),
+						      sg_dma_len(src_sg)/16);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+			dst_target = sg_dma_len(src_sg);
+			src_sg = sg_next(src_sg);
+		} else
+			dst_target = UINT_MAX;
+
+		while (dst_target && dst_sg) {
+			if (sg_dma_len(dst_sg) & 0xf)
+				d = flexrm_dst_desc(sg_dma_address(dst_sg),
+						     sg_dma_len(dst_sg));
+			else
+				d = flexrm_mdst_desc(sg_dma_address(dst_sg),
+						      sg_dma_len(dst_sg)/16);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+			if (sg_dma_len(dst_sg) < dst_target)
+				dst_target -= sg_dma_len(dst_sg);
+			else
+				dst_target = 0;
+			dst_sg = sg_next(dst_sg);
+		}
+	}
+
+	/* Null descriptor with invalid toggle bit */
+	flexrm_write_desc(desc_ptr, flexrm_null_desc(!toggle));
+
+	/* Ensure that descriptors have been written to memory */
+	wmb();
+
+	/* Flip toggle bit in header */
+	flexrm_flip_header_toogle(orig_desc_ptr);
+
+	return desc_ptr;
+}
+
+static bool flexrm_sba_sanity_check(struct brcm_message *msg)
+{
+	u32 i;
+
+	if (!msg->sba.cmds || !msg->sba.cmds_count)
+		return false;
+
+	for (i = 0; i < msg->sba.cmds_count; i++) {
+		if (((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_B) ||
+		     (msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_C)) &&
+		    (msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_OUTPUT))
+			return false;
+		if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_B) &&
+		    (msg->sba.cmds[i].data_len > SRCT_LENGTH_MASK))
+			return false;
+		if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_C) &&
+		    (msg->sba.cmds[i].data_len > SRCT_LENGTH_MASK))
+			return false;
+		if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_RESP) &&
+		    (msg->sba.cmds[i].resp_len > DSTT_LENGTH_MASK))
+			return false;
+		if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_OUTPUT) &&
+		    (msg->sba.cmds[i].data_len > DSTT_LENGTH_MASK))
+			return false;
+	}
+
+	return true;
+}
+
+static u32 flexrm_sba_estimate_nonheader_desc_count(struct brcm_message *msg)
+{
+	u32 i, cnt;
+
+	cnt = 0;
+	for (i = 0; i < msg->sba.cmds_count; i++) {
+		cnt++;
+
+		if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_B) ||
+		    (msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_C))
+			cnt++;
+
+		if (msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_RESP)
+			cnt++;
+
+		if (msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_OUTPUT)
+			cnt++;
+	}
+
+	return cnt;
+}
+
+static void *flexrm_sba_write_descs(struct brcm_message *msg, u32 nhcnt,
+				     u32 reqid, void *desc_ptr, u32 toggle,
+				     void *start_desc, void *end_desc)
+{
+	u64 d;
+	u32 i, nhpos = 0;
+	struct brcm_sba_command *c;
+	void *orig_desc_ptr = desc_ptr;
+
+	/* Convert SBA commands into descriptors */
+	for (i = 0; i < msg->sba.cmds_count; i++) {
+		c = &msg->sba.cmds[i];
+
+		if ((c->flags & BRCM_SBA_CMD_HAS_RESP) &&
+		    (c->flags & BRCM_SBA_CMD_HAS_OUTPUT)) {
+			/* Destination response descriptor */
+			d = flexrm_dst_desc(c->resp, c->resp_len);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+		} else if (c->flags & BRCM_SBA_CMD_HAS_RESP) {
+			/* Destination response with tlast descriptor */
+			d = flexrm_dstt_desc(c->resp, c->resp_len);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+		}
+
+		if (c->flags & BRCM_SBA_CMD_HAS_OUTPUT) {
+			/* Destination with tlast descriptor */
+			d = flexrm_dstt_desc(c->data, c->data_len);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+		}
+
+		if (c->flags & BRCM_SBA_CMD_TYPE_B) {
+			/* Command as immediate descriptor */
+			d = flexrm_imm_desc(c->cmd);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+		} else {
+			/* Command as immediate descriptor with tlast */
+			d = flexrm_immt_desc(c->cmd);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+		}
+
+		if ((c->flags & BRCM_SBA_CMD_TYPE_B) ||
+		    (c->flags & BRCM_SBA_CMD_TYPE_C)) {
+			/* Source with tlast descriptor */
+			d = flexrm_srct_desc(c->data, c->data_len);
+			flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+					     d, &desc_ptr, &toggle,
+					     start_desc, end_desc);
+			nhpos++;
+		}
+	}
+
+	/* Null descriptor with invalid toggle bit */
+	flexrm_write_desc(desc_ptr, flexrm_null_desc(!toggle));
+
+	/* Ensure that descriptors have been written to memory */
+	wmb();
+
+	/* Flip toggle bit in header */
+	flexrm_flip_header_toogle(orig_desc_ptr);
+
+	return desc_ptr;
+}
+
+static bool flexrm_sanity_check(struct brcm_message *msg)
+{
+	if (!msg)
+		return false;
+
+	switch (msg->type) {
+	case BRCM_MESSAGE_SPU:
+		return flexrm_spu_sanity_check(msg);
+	case BRCM_MESSAGE_SBA:
+		return flexrm_sba_sanity_check(msg);
+	default:
+		return false;
+	};
+}
+
+static u32 flexrm_estimate_nonheader_desc_count(struct brcm_message *msg)
+{
+	if (!msg)
+		return 0;
+
+	switch (msg->type) {
+	case BRCM_MESSAGE_SPU:
+		return flexrm_spu_estimate_nonheader_desc_count(msg);
+	case BRCM_MESSAGE_SBA:
+		return flexrm_sba_estimate_nonheader_desc_count(msg);
+	default:
+		return 0;
+	};
+}
+
+static int flexrm_dma_map(struct device *dev, struct brcm_message *msg)
+{
+	if (!dev || !msg)
+		return -EINVAL;
+
+	switch (msg->type) {
+	case BRCM_MESSAGE_SPU:
+		return flexrm_spu_dma_map(dev, msg);
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void flexrm_dma_unmap(struct device *dev, struct brcm_message *msg)
+{
+	if (!dev || !msg)
+		return;
+
+	switch (msg->type) {
+	case BRCM_MESSAGE_SPU:
+		flexrm_spu_dma_unmap(dev, msg);
+		break;
+	default:
+		break;
+	}
+}
+
+static void *flexrm_write_descs(struct brcm_message *msg, u32 nhcnt,
+				u32 reqid, void *desc_ptr, u32 toggle,
+				void *start_desc, void *end_desc)
+{
+	if (!msg || !desc_ptr || !start_desc || !end_desc)
+		return ERR_PTR(-ENOTSUPP);
+
+	if ((desc_ptr < start_desc) || (end_desc <= desc_ptr))
+		return ERR_PTR(-ERANGE);
+
+	switch (msg->type) {
+	case BRCM_MESSAGE_SPU:
+		return flexrm_spu_write_descs(msg, nhcnt, reqid,
+					       desc_ptr, toggle,
+					       start_desc, end_desc);
+	case BRCM_MESSAGE_SBA:
+		return flexrm_sba_write_descs(msg, nhcnt, reqid,
+					       desc_ptr, toggle,
+					       start_desc, end_desc);
+	default:
+		return ERR_PTR(-ENOTSUPP);
+	};
+}
+
+/* ====== FlexRM driver helper routines ===== */
+
+static int flexrm_new_request(struct flexrm_ring *ring,
+				struct brcm_message *batch_msg,
+				struct brcm_message *msg)
+{
+	void *next;
+	unsigned long flags;
+	u32 val, count, nhcnt;
+	u32 read_offset, write_offset;
+	bool exit_cleanup = false;
+	int ret = 0, reqid;
+
+	/* Do sanity check on message */
+	if (!flexrm_sanity_check(msg))
+		return -EIO;
+	msg->error = 0;
+
+	/* If no requests possible then save data pointer and goto done. */
+	reqid = ida_simple_get(&ring->requests_ida, 0,
+				RING_MAX_REQ_COUNT, GFP_KERNEL);
+	if (reqid < 0) {
+		spin_lock_irqsave(&ring->lock, flags);
+		if (batch_msg)
+			ring->last_pending_msg = batch_msg;
+		else
+			ring->last_pending_msg = msg;
+		spin_unlock_irqrestore(&ring->lock, flags);
+		return 0;
+	}
+	ring->requests[reqid] = msg;
+
+	/* Do DMA mappings for the message */
+	ret = flexrm_dma_map(ring->mbox->dev, msg);
+	if (ret < 0) {
+		ring->requests[reqid] = NULL;
+		ida_simple_remove(&ring->requests_ida, reqid);
+		return ret;
+	}
+
+	/* If last_pending_msg is already set then goto done with error */
+	spin_lock_irqsave(&ring->lock, flags);
+	if (ring->last_pending_msg)
+		ret = -ENOSPC;
+	spin_unlock_irqrestore(&ring->lock, flags);
+	if (ret < 0) {
+		dev_warn(ring->mbox->dev, "no space in ring %d\n", ring->num);
+		exit_cleanup = true;
+		goto exit;
+	}
+
+	/* Determine current HW BD read offset */
+	read_offset = readl_relaxed(ring->regs + RING_BD_READ_PTR);
+	val = readl_relaxed(ring->regs + RING_BD_START_ADDR);
+	read_offset *= RING_DESC_SIZE;
+	read_offset += (u32)(BD_START_ADDR_DECODE(val) - ring->bd_dma_base);
+
+	/*
+	 * Number required descriptors = number of non-header descriptors +
+	 *				 number of header descriptors +
+	 *				 1x null descriptor
+	 */
+	nhcnt = flexrm_estimate_nonheader_desc_count(msg);
+	count = flexrm_estimate_header_desc_count(nhcnt) + nhcnt + 1;
+
+	/* Check for available descriptor space. */
+	write_offset = ring->bd_write_offset;
+	while (count) {
+		if (!flexrm_is_next_table_desc(ring->bd_base + write_offset))
+			count--;
+		write_offset += RING_DESC_SIZE;
+		if (write_offset == RING_BD_SIZE)
+			write_offset = 0x0;
+		if (write_offset == read_offset)
+			break;
+	}
+	if (count) {
+		spin_lock_irqsave(&ring->lock, flags);
+		if (batch_msg)
+			ring->last_pending_msg = batch_msg;
+		else
+			ring->last_pending_msg = msg;
+		spin_unlock_irqrestore(&ring->lock, flags);
+		ret = 0;
+		exit_cleanup = true;
+		goto exit;
+	}
+
+	/* Write descriptors to ring */
+	next = flexrm_write_descs(msg, nhcnt, reqid,
+			ring->bd_base + ring->bd_write_offset,
+			RING_BD_TOGGLE_VALID(ring->bd_write_offset),
+			ring->bd_base, ring->bd_base + RING_BD_SIZE);
+	if (IS_ERR(next)) {
+		ret = PTR_ERR(next);
+		exit_cleanup = true;
+		goto exit;
+	}
+
+	/* Save ring BD write offset */
+	ring->bd_write_offset = (unsigned long)(next - ring->bd_base);
+
+exit:
+	/* Update error status in message */
+	msg->error = ret;
+
+	/* Cleanup if we failed */
+	if (exit_cleanup) {
+		flexrm_dma_unmap(ring->mbox->dev, msg);
+		ring->requests[reqid] = NULL;
+		ida_simple_remove(&ring->requests_ida, reqid);
+	}
+
+	return ret;
+}
+
+static int flexrm_process_completions(struct flexrm_ring *ring)
+{
+	u64 desc;
+	int err, count = 0;
+	unsigned long flags;
+	struct brcm_message *msg = NULL;
+	u32 reqid, cmpl_read_offset, cmpl_write_offset;
+	struct mbox_chan *chan = &ring->mbox->controller.chans[ring->num];
+
+	spin_lock_irqsave(&ring->lock, flags);
+
+	/* Check last_pending_msg */
+	if (ring->last_pending_msg) {
+		msg = ring->last_pending_msg;
+		ring->last_pending_msg = NULL;
+	}
+
+	/*
+	 * Get current completion read and write offset
+	 *
+	 * Note: We should read completion write pointer atleast once
+	 * after we get a MSI interrupt because HW maintains internal
+	 * MSI status which will allow next MSI interrupt only after
+	 * completion write pointer is read.
+	 */
+	cmpl_write_offset = readl_relaxed(ring->regs + RING_CMPL_WRITE_PTR);
+	cmpl_write_offset *= RING_DESC_SIZE;
+	cmpl_read_offset = ring->cmpl_read_offset;
+	ring->cmpl_read_offset = cmpl_write_offset;
+
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	/* If last_pending_msg was set then queue it back */
+	if (msg)
+		mbox_send_message(chan, msg);
+
+	/* For each completed request notify mailbox clients */
+	reqid = 0;
+	while (cmpl_read_offset != cmpl_write_offset) {
+		/* Dequeue next completion descriptor */
+		desc = *((u64 *)(ring->cmpl_base + cmpl_read_offset));
+
+		/* Next read offset */
+		cmpl_read_offset += RING_DESC_SIZE;
+		if (cmpl_read_offset == RING_CMPL_SIZE)
+			cmpl_read_offset = 0;
+
+		/* Decode error from completion descriptor */
+		err = flexrm_cmpl_desc_to_error(desc);
+		if (err < 0) {
+			dev_warn(ring->mbox->dev,
+				 "got completion desc=0x%lx with error %d",
+				 (unsigned long)desc, err);
+		}
+
+		/* Determine request id from completion descriptor */
+		reqid = flexrm_cmpl_desc_to_reqid(desc);
+
+		/* Determine message pointer based on reqid */
+		msg = ring->requests[reqid];
+		if (!msg) {
+			dev_warn(ring->mbox->dev,
+				 "null msg pointer for completion desc=0x%lx",
+				 (unsigned long)desc);
+			continue;
+		}
+
+		/* Release reqid for recycling */
+		ring->requests[reqid] = NULL;
+		ida_simple_remove(&ring->requests_ida, reqid);
+
+		/* Unmap DMA mappings */
+		flexrm_dma_unmap(ring->mbox->dev, msg);
+
+		/* Give-back message to mailbox client */
+		msg->error = err;
+		mbox_chan_received_data(chan, msg);
+
+		/* Increment number of completions processed */
+		count++;
+	}
+
+	return count;
+}
+
+/* ====== FlexRM interrupt handler ===== */
+
+static irqreturn_t flexrm_irq_event(int irq, void *dev_id)
+{
+	/* We only have MSI for completions so just wakeup IRQ thread */
+	/* Ring related errors will be informed via completion descriptors */
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t flexrm_irq_thread(int irq, void *dev_id)
+{
+	flexrm_process_completions(dev_id);
+
+	return IRQ_HANDLED;
+}
+
+/* ====== FlexRM mailbox callbacks ===== */
+
+static int flexrm_send_data(struct mbox_chan *chan, void *data)
+{
+	int i, rc;
+	struct flexrm_ring *ring = chan->con_priv;
+	struct brcm_message *msg = data;
+
+	if (msg->type == BRCM_MESSAGE_BATCH) {
+		for (i = msg->batch.msgs_queued;
+		     i < msg->batch.msgs_count; i++) {
+			rc = flexrm_new_request(ring, msg,
+						 &msg->batch.msgs[i]);
+			if (rc) {
+				msg->error = rc;
+				return rc;
+			}
+			msg->batch.msgs_queued++;
+		}
+		return 0;
+	}
+
+	return flexrm_new_request(ring, NULL, data);
+}
+
+static bool flexrm_peek_data(struct mbox_chan *chan)
+{
+	int cnt = flexrm_process_completions(chan->con_priv);
+
+	return (cnt > 0) ? true : false;
+}
+
+static int flexrm_startup(struct mbox_chan *chan)
+{
+	u64 d;
+	u32 val, off;
+	int ret = 0;
+	dma_addr_t next_addr;
+	struct flexrm_ring *ring = chan->con_priv;
+
+	/* Allocate BD memory */
+	ring->bd_base = dma_pool_alloc(ring->mbox->bd_pool,
+				       GFP_KERNEL, &ring->bd_dma_base);
+	if (!ring->bd_base) {
+		dev_err(ring->mbox->dev, "can't allocate BD memory\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	/* Configure next table pointer entries in BD memory */
+	for (off = 0; off < RING_BD_SIZE; off += RING_DESC_SIZE) {
+		next_addr = off + RING_DESC_SIZE;
+		if (next_addr == RING_BD_SIZE)
+			next_addr = 0;
+		next_addr += ring->bd_dma_base;
+		if (RING_BD_ALIGN_CHECK(next_addr))
+			d = flexrm_next_table_desc(RING_BD_TOGGLE_VALID(off),
+						    next_addr);
+		else
+			d = flexrm_null_desc(RING_BD_TOGGLE_INVALID(off));
+		flexrm_write_desc(ring->bd_base + off, d);
+	}
+
+	/* Allocate completion memory */
+	ring->cmpl_base = dma_pool_alloc(ring->mbox->cmpl_pool,
+					 GFP_KERNEL, &ring->cmpl_dma_base);
+	if (!ring->cmpl_base) {
+		dev_err(ring->mbox->dev, "can't allocate completion memory\n");
+		ret = -ENOMEM;
+		goto fail_free_bd_memory;
+	}
+	memset(ring->cmpl_base, 0, RING_CMPL_SIZE);
+
+	/* Request IRQ */
+	if (ring->irq == UINT_MAX) {
+		dev_err(ring->mbox->dev, "ring IRQ not available\n");
+		ret = -ENODEV;
+		goto fail_free_cmpl_memory;
+	}
+	ret = request_threaded_irq(ring->irq,
+				   flexrm_irq_event,
+				   flexrm_irq_thread,
+				   0, dev_name(ring->mbox->dev), ring);
+	if (ret) {
+		dev_err(ring->mbox->dev, "failed to request ring IRQ\n");
+		goto fail_free_cmpl_memory;
+	}
+	ring->irq_requested = true;
+
+	/* Disable/inactivate ring */
+	writel_relaxed(0x0, ring->regs + RING_CONTROL);
+
+	/* Program BD start address */
+	val = BD_START_ADDR_VALUE(ring->bd_dma_base);
+	writel_relaxed(val, ring->regs + RING_BD_START_ADDR);
+
+	/* BD write pointer will be same as HW write pointer */
+	ring->bd_write_offset =
+			readl_relaxed(ring->regs + RING_BD_WRITE_PTR);
+	ring->bd_write_offset *= RING_DESC_SIZE;
+
+	/* Program completion start address */
+	val = CMPL_START_ADDR_VALUE(ring->cmpl_dma_base);
+	writel_relaxed(val, ring->regs + RING_CMPL_START_ADDR);
+
+	/* Ensure last pending message is cleared */
+	ring->last_pending_msg = NULL;
+
+	/* Completion read pointer will be same as HW write pointer */
+	ring->cmpl_read_offset =
+			readl_relaxed(ring->regs + RING_CMPL_WRITE_PTR);
+	ring->cmpl_read_offset *= RING_DESC_SIZE;
+
+	/* Read ring Tx, Rx, and Outstanding counts to clear */
+	readl_relaxed(ring->regs + RING_NUM_REQ_RECV_LS);
+	readl_relaxed(ring->regs + RING_NUM_REQ_RECV_MS);
+	readl_relaxed(ring->regs + RING_NUM_REQ_TRANS_LS);
+	readl_relaxed(ring->regs + RING_NUM_REQ_TRANS_MS);
+	readl_relaxed(ring->regs + RING_NUM_REQ_OUTSTAND);
+
+	/* Configure RING_MSI_CONTROL */
+	val = 0;
+	val |= (ring->msi_timer_val << MSI_TIMER_VAL_SHIFT);
+	val |= BIT(MSI_ENABLE_SHIFT);
+	val |= (ring->msi_count_threshold & MSI_COUNT_MASK) << MSI_COUNT_SHIFT;
+	writel_relaxed(val, ring->regs + RING_MSI_CONTROL);
+
+	/* Enable/activate ring */
+	val = BIT(CONTROL_ACTIVE_SHIFT);
+	writel_relaxed(val, ring->regs + RING_CONTROL);
+
+	return 0;
+
+fail_free_cmpl_memory:
+	dma_pool_free(ring->mbox->cmpl_pool,
+		      ring->cmpl_base, ring->cmpl_dma_base);
+	ring->cmpl_base = NULL;
+fail_free_bd_memory:
+	dma_pool_free(ring->mbox->bd_pool,
+		      ring->bd_base, ring->bd_dma_base);
+	ring->bd_base = NULL;
+fail:
+	return ret;
+}
+
+static void flexrm_shutdown(struct mbox_chan *chan)
+{
+	u32 reqid;
+	unsigned int timeout;
+	struct brcm_message *msg;
+	struct flexrm_ring *ring = chan->con_priv;
+
+	/* Disable/inactivate ring */
+	writel_relaxed(0x0, ring->regs + RING_CONTROL);
+
+	/* Flush ring with timeout of 1s */
+	timeout = 1000;
+	writel_relaxed(BIT(CONTROL_FLUSH_SHIFT),
+			ring->regs + RING_CONTROL);
+	do {
+		if (readl_relaxed(ring->regs + RING_FLUSH_DONE) &
+		    FLUSH_DONE_MASK)
+			break;
+		mdelay(1);
+	} while (timeout--);
+
+	/* Abort all in-flight requests */
+	for (reqid = 0; reqid < RING_MAX_REQ_COUNT; reqid++) {
+		msg = ring->requests[reqid];
+		if (!msg)
+			continue;
+
+		/* Release reqid for recycling */
+		ring->requests[reqid] = NULL;
+		ida_simple_remove(&ring->requests_ida, reqid);
+
+		/* Unmap DMA mappings */
+		flexrm_dma_unmap(ring->mbox->dev, msg);
+
+		/* Give-back message to mailbox client */
+		msg->error = -EIO;
+		mbox_chan_received_data(chan, msg);
+	}
+
+	/* Release IRQ */
+	if (ring->irq_requested) {
+		free_irq(ring->irq, ring);
+		ring->irq_requested = false;
+	}
+
+	/* Free-up completion descriptor ring */
+	if (ring->cmpl_base) {
+		dma_pool_free(ring->mbox->cmpl_pool,
+			      ring->cmpl_base, ring->cmpl_dma_base);
+		ring->cmpl_base = NULL;
+	}
+
+	/* Free-up BD descriptor ring */
+	if (ring->bd_base) {
+		dma_pool_free(ring->mbox->bd_pool,
+			      ring->bd_base, ring->bd_dma_base);
+		ring->bd_base = NULL;
+	}
+}
+
+static bool flexrm_last_tx_done(struct mbox_chan *chan)
+{
+	bool ret;
+	unsigned long flags;
+	struct flexrm_ring *ring = chan->con_priv;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	ret = (ring->last_pending_msg) ? false : true;
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	return ret;
+}
+
+static const struct mbox_chan_ops flexrm_mbox_chan_ops = {
+	.send_data	= flexrm_send_data,
+	.startup	= flexrm_startup,
+	.shutdown	= flexrm_shutdown,
+	.last_tx_done	= flexrm_last_tx_done,
+	.peek_data	= flexrm_peek_data,
+};
+
+static struct mbox_chan *flexrm_mbox_of_xlate(struct mbox_controller *cntlr,
+					const struct of_phandle_args *pa)
+{
+	struct mbox_chan *chan;
+	struct flexrm_ring *ring;
+
+	if (pa->args_count < 3)
+		return ERR_PTR(-EINVAL);
+
+	if (pa->args[0] >= cntlr->num_chans)
+		return ERR_PTR(-ENOENT);
+
+	if (pa->args[1] > MSI_COUNT_MASK)
+		return ERR_PTR(-EINVAL);
+
+	if (pa->args[2] > MSI_TIMER_VAL_MASK)
+		return ERR_PTR(-EINVAL);
+
+	chan = &cntlr->chans[pa->args[0]];
+	ring = chan->con_priv;
+	ring->msi_count_threshold = pa->args[1];
+	ring->msi_timer_val = pa->args[2];
+
+	return chan;
+}
+
+/* ====== FlexRM platform driver ===== */
+
+static void flexrm_mbox_msi_write(struct msi_desc *desc, struct msi_msg *msg)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	struct flexrm_mbox *mbox = dev_get_drvdata(dev);
+	struct flexrm_ring *ring = &mbox->rings[desc->platform.msi_index];
+
+	/* Configure per-Ring MSI registers */
+	writel_relaxed(msg->address_lo, ring->regs + RING_MSI_ADDR_LS);
+	writel_relaxed(msg->address_hi, ring->regs + RING_MSI_ADDR_MS);
+	writel_relaxed(msg->data, ring->regs + RING_MSI_DATA_VALUE);
+}
+
+static int flexrm_mbox_probe(struct platform_device *pdev)
+{
+	int index, ret = 0;
+	void __iomem *regs;
+	void __iomem *regs_end;
+	struct msi_desc *desc;
+	struct resource *iomem;
+	struct flexrm_ring *ring;
+	struct flexrm_mbox *mbox;
+	struct device *dev = &pdev->dev;
+
+	/* Allocate driver mailbox struct */
+	mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL);
+	if (!mbox) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+	mbox->dev = dev;
+	platform_set_drvdata(pdev, mbox);
+
+	/* Get resource for registers */
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!iomem || (resource_size(iomem) < RING_REGS_SIZE)) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	/* Map registers of all rings */
+	mbox->regs = devm_ioremap_resource(&pdev->dev, iomem);
+	if (IS_ERR(mbox->regs)) {
+		ret = PTR_ERR(mbox->regs);
+		dev_err(&pdev->dev, "Failed to remap mailbox regs: %d\n", ret);
+		goto fail;
+	}
+	regs_end = mbox->regs + resource_size(iomem);
+
+	/* Scan and count available rings */
+	mbox->num_rings = 0;
+	for (regs = mbox->regs; regs < regs_end; regs += RING_REGS_SIZE) {
+		if (readl_relaxed(regs + RING_VER) == RING_VER_MAGIC)
+			mbox->num_rings++;
+	}
+	if (!mbox->num_rings) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	/* Allocate driver ring structs */
+	ring = devm_kcalloc(dev, mbox->num_rings, sizeof(*ring), GFP_KERNEL);
+	if (!ring) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+	mbox->rings = ring;
+
+	/* Initialize members of driver ring structs */
+	regs = mbox->regs;
+	for (index = 0; index < mbox->num_rings; index++) {
+		ring = &mbox->rings[index];
+		ring->num = index;
+		ring->mbox = mbox;
+		while ((regs < regs_end) &&
+		       (readl_relaxed(regs + RING_VER) != RING_VER_MAGIC))
+			regs += RING_REGS_SIZE;
+		if (regs_end <= regs) {
+			ret = -ENODEV;
+			goto fail;
+		}
+		ring->regs = regs;
+		regs += RING_REGS_SIZE;
+		ring->irq = UINT_MAX;
+		ring->irq_requested = false;
+		ring->msi_timer_val = MSI_TIMER_VAL_MASK;
+		ring->msi_count_threshold = 0x1;
+		ida_init(&ring->requests_ida);
+		memset(ring->requests, 0, sizeof(ring->requests));
+		ring->bd_base = NULL;
+		ring->bd_dma_base = 0;
+		ring->cmpl_base = NULL;
+		ring->cmpl_dma_base = 0;
+		spin_lock_init(&ring->lock);
+		ring->last_pending_msg = NULL;
+		ring->cmpl_read_offset = 0;
+	}
+
+	/* FlexRM is capable of 40-bit physical addresses only */
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
+	if (ret) {
+		ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+		if (ret)
+			goto fail;
+	}
+
+	/* Create DMA pool for ring BD memory */
+	mbox->bd_pool = dma_pool_create("bd", dev, RING_BD_SIZE,
+					1 << RING_BD_ALIGN_ORDER, 0);
+	if (!mbox->bd_pool) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	/* Create DMA pool for ring completion memory */
+	mbox->cmpl_pool = dma_pool_create("cmpl", dev, RING_CMPL_SIZE,
+					  1 << RING_CMPL_ALIGN_ORDER, 0);
+	if (!mbox->cmpl_pool) {
+		ret = -ENOMEM;
+		goto fail_destroy_bd_pool;
+	}
+
+	/* Allocate platform MSIs for each ring */
+	ret = platform_msi_domain_alloc_irqs(dev, mbox->num_rings,
+						flexrm_mbox_msi_write);
+	if (ret)
+		goto fail_destroy_cmpl_pool;
+
+	/* Save alloced IRQ numbers for each ring */
+	for_each_msi_entry(desc, dev) {
+		ring = &mbox->rings[desc->platform.msi_index];
+		ring->irq = desc->irq;
+	}
+
+	/* Initialize mailbox controller */
+	mbox->controller.txdone_irq = false;
+	mbox->controller.txdone_poll = true;
+	mbox->controller.txpoll_period = 1;
+	mbox->controller.ops = &flexrm_mbox_chan_ops;
+	mbox->controller.dev = dev;
+	mbox->controller.num_chans = mbox->num_rings;
+	mbox->controller.of_xlate = flexrm_mbox_of_xlate;
+	mbox->controller.chans = devm_kcalloc(dev, mbox->num_rings,
+				sizeof(*mbox->controller.chans), GFP_KERNEL);
+	if (!mbox->controller.chans) {
+		ret = -ENOMEM;
+		goto fail_free_msis;
+	}
+	for (index = 0; index < mbox->num_rings; index++)
+		mbox->controller.chans[index].con_priv = &mbox->rings[index];
+
+	/* Register mailbox controller */
+	ret = mbox_controller_register(&mbox->controller);
+	if (ret)
+		goto fail_free_msis;
+
+	dev_info(dev, "registered flexrm mailbox with %d channels\n",
+			mbox->controller.num_chans);
+
+	return 0;
+
+fail_free_msis:
+	platform_msi_domain_free_irqs(dev);
+fail_destroy_cmpl_pool:
+	dma_pool_destroy(mbox->cmpl_pool);
+fail_destroy_bd_pool:
+	dma_pool_destroy(mbox->bd_pool);
+fail:
+	return ret;
+}
+
+static int flexrm_mbox_remove(struct platform_device *pdev)
+{
+	int index;
+	struct device *dev = &pdev->dev;
+	struct flexrm_ring *ring;
+	struct flexrm_mbox *mbox = platform_get_drvdata(pdev);
+
+	mbox_controller_unregister(&mbox->controller);
+
+	platform_msi_domain_free_irqs(dev);
+
+	dma_pool_destroy(mbox->cmpl_pool);
+	dma_pool_destroy(mbox->bd_pool);
+
+	for (index = 0; index < mbox->num_rings; index++) {
+		ring = &mbox->rings[index];
+		ida_destroy(&ring->requests_ida);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id flexrm_mbox_of_match[] = {
+	{ .compatible = "brcm,iproc-flexrm-mbox", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, flexrm_mbox_of_match);
+
+static struct platform_driver flexrm_mbox_driver = {
+	.driver = {
+		.name = "brcm-flexrm-mbox",
+		.of_match_table = flexrm_mbox_of_match,
+	},
+	.probe		= flexrm_mbox_probe,
+	.remove		= flexrm_mbox_remove,
+};
+module_platform_driver(flexrm_mbox_driver);
+
+MODULE_AUTHOR("Anup Patel <anup.patel@broadcom.com>");
+MODULE_DESCRIPTION("Broadcom FlexRM mailbox driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index 2aeb034d5fb9..4fe7be0bdd11 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -18,7 +18,8 @@
  * Broadcom PDC Mailbox Driver
  * The PDC provides a ring based programming interface to one or more hardware
  * offload engines. For example, the PDC driver works with both SPU-M and SPU2
- * cryptographic offload hardware. In some chips the PDC is referred to as MDE.
+ * cryptographic offload hardware. In some chips the PDC is referred to as MDE,
+ * and in others the FA2/FA+ hardware is used with this PDC driver.
  *
  * The PDC driver registers with the Linux mailbox framework as a mailbox
  * controller, once for each PDC instance. Ring 0 for each PDC is registered as
@@ -108,6 +109,7 @@
 #define PDC_INTMASK_OFFSET   0x24
 #define PDC_INTSTATUS_OFFSET 0x20
 #define PDC_RCVLAZY0_OFFSET  (0x30 + 4 * PDC_RINGSET)
+#define FA_RCVLAZY0_OFFSET   0x100
 
 /*
  * For SPU2, configure MDE_CKSUM_CONTROL to write 17 bytes of metadata
@@ -162,6 +164,11 @@
 /* Maximum size buffer the DMA engine can handle */
 #define PDC_DMA_BUF_MAX 16384
 
+enum pdc_hw {
+	FA_HW,		/* FA2/FA+ hardware (i.e. Northstar Plus) */
+	PDC_HW		/* PDC/MDE hardware (i.e. Northstar 2, Pegasus) */
+};
+
 struct pdc_dma_map {
 	void *ctx;          /* opaque context associated with frame */
 };
@@ -211,13 +218,13 @@ struct pdc_regs {
 	u32  gptimer;                /* 0x028 */
 
 	u32  PAD;
-	u32  intrcvlazy_0;           /* 0x030 */
-	u32  intrcvlazy_1;           /* 0x034 */
-	u32  intrcvlazy_2;           /* 0x038 */
-	u32  intrcvlazy_3;           /* 0x03c */
+	u32  intrcvlazy_0;           /* 0x030 (Only in PDC, not FA2) */
+	u32  intrcvlazy_1;           /* 0x034 (Only in PDC, not FA2) */
+	u32  intrcvlazy_2;           /* 0x038 (Only in PDC, not FA2) */
+	u32  intrcvlazy_3;           /* 0x03c (Only in PDC, not FA2) */
 
 	u32  PAD[48];
-	u32  removed_intrecvlazy;    /* 0x100 */
+	u32  fa_intrecvlazy;         /* 0x100 (Only in FA2, not PDC) */
 	u32  flowctlthresh;          /* 0x104 */
 	u32  wrrthresh;              /* 0x108 */
 	u32  gmac_idle_cnt_thresh;   /* 0x10c */
@@ -243,7 +250,7 @@ struct pdc_regs {
 	u32  serdes_status1;         /* 0x1b0 */
 	u32  PAD[11];                /* 0x1b4-1dc */
 	u32  clk_ctl_st;             /* 0x1e0 */
-	u32  hw_war;                 /* 0x1e4 */
+	u32  hw_war;                 /* 0x1e4 (Only in PDC, not FA2) */
 	u32  pwrctl;                 /* 0x1e8 */
 	u32  PAD[5];
 
@@ -410,6 +417,9 @@ struct pdc_state {
 	u32  txnobuf;          /* unable to create tx descriptor */
 	u32  rxnobuf;          /* unable to create rx descriptor */
 	u32  rx_oflow;         /* count of rx overflows */
+
+	/* hardware type - FA2 or PDC/MDE */
+	enum pdc_hw hw_type;
 };
 
 /* Global variables */
@@ -1396,7 +1406,13 @@ static int pdc_interrupts_init(struct pdc_state *pdcs)
 
 	/* interrupt configuration */
 	iowrite32(PDC_INTMASK, pdcs->pdc_reg_vbase + PDC_INTMASK_OFFSET);
-	iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase + PDC_RCVLAZY0_OFFSET);
+
+	if (pdcs->hw_type == FA_HW)
+		iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase +
+			  FA_RCVLAZY0_OFFSET);
+	else
+		iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase +
+			  PDC_RCVLAZY0_OFFSET);
 
 	/* read irq from device tree */
 	pdcs->pdc_irq = irq_of_parse_and_map(dn, 0);
@@ -1465,6 +1481,17 @@ static int pdc_mb_init(struct pdc_state *pdcs)
 	return 0;
 }
 
+/* Device tree API */
+static const int pdc_hw = PDC_HW;
+static const int fa_hw = FA_HW;
+
+static const struct of_device_id pdc_mbox_of_match[] = {
+	{.compatible = "brcm,iproc-pdc-mbox", .data = &pdc_hw},
+	{.compatible = "brcm,iproc-fa2-mbox", .data = &fa_hw},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, pdc_mbox_of_match);
+
 /**
  * pdc_dt_read() - Read application-specific data from device tree.
  * @pdev:  Platform device
@@ -1481,6 +1508,8 @@ static int pdc_dt_read(struct platform_device *pdev, struct pdc_state *pdcs)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *dn = pdev->dev.of_node;
+	const struct of_device_id *match;
+	const int *hw_type;
 	int err;
 
 	err = of_property_read_u32(dn, "brcm,rx-status-len",
@@ -1492,6 +1521,14 @@ static int pdc_dt_read(struct platform_device *pdev, struct pdc_state *pdcs)
 
 	pdcs->use_bcm_hdr = of_property_read_bool(dn, "brcm,use-bcm-hdr");
 
+	pdcs->hw_type = PDC_HW;
+
+	match = of_match_device(of_match_ptr(pdc_mbox_of_match), dev);
+	if (match != NULL) {
+		hw_type = match->data;
+		pdcs->hw_type = *hw_type;
+	}
+
 	return 0;
 }
 
@@ -1525,7 +1562,7 @@ static int pdc_probe(struct platform_device *pdev)
 	pdcs->pdc_idx = pdcg.num_spu;
 	pdcg.num_spu++;
 
-	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(39));
 	if (err) {
 		dev_warn(dev, "PDC device cannot perform DMA. Error %d.", err);
 		goto cleanup;
@@ -1611,12 +1648,6 @@ static int pdc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id pdc_mbox_of_match[] = {
-	{.compatible = "brcm,iproc-pdc-mbox"},
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, pdc_mbox_of_match);
-
 static struct platform_driver pdc_mbox_driver = {
 	.probe = pdc_probe,
 	.remove = pdc_remove,
diff --git a/drivers/mailbox/hi6220-mailbox.c b/drivers/mailbox/hi6220-mailbox.c
index 613722db5daf..519376d3534c 100644
--- a/drivers/mailbox/hi6220-mailbox.c
+++ b/drivers/mailbox/hi6220-mailbox.c
@@ -221,7 +221,7 @@ static void hi6220_mbox_shutdown(struct mbox_chan *chan)
 	mbox->irq_map_chan[mchan->ack_irq] = NULL;
 }
 
-static struct mbox_chan_ops hi6220_mbox_ops = {
+static const struct mbox_chan_ops hi6220_mbox_ops = {
 	.send_data    = hi6220_mbox_send_data,
 	.startup      = hi6220_mbox_startup,
 	.shutdown     = hi6220_mbox_shutdown,
diff --git a/drivers/mailbox/mailbox-xgene-slimpro.c b/drivers/mailbox/mailbox-xgene-slimpro.c
index dd2afbca51c9..a7040163dd43 100644
--- a/drivers/mailbox/mailbox-xgene-slimpro.c
+++ b/drivers/mailbox/mailbox-xgene-slimpro.c
@@ -174,7 +174,7 @@ static void slimpro_mbox_shutdown(struct mbox_chan *chan)
 	devm_free_irq(mb_chan->dev, mb_chan->irq, mb_chan);
 }
 
-static struct mbox_chan_ops slimpro_mbox_ops = {
+static const struct mbox_chan_ops slimpro_mbox_ops = {
 	.send_data = slimpro_mbox_send_data,
 	.startup = slimpro_mbox_startup,
 	.shutdown = slimpro_mbox_shutdown,
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index 4671f8a12872..9dfbf7ea10a2 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -103,11 +103,14 @@ static void tx_tick(struct mbox_chan *chan, int r)
 	/* Submit next message */
 	msg_submit(chan);
 
+	if (!mssg)
+		return;
+
 	/* Notify the client */
-	if (mssg && chan->cl->tx_done)
+	if (chan->cl->tx_done)
 		chan->cl->tx_done(chan->cl, mssg, r);
 
-	if (chan->cl->tx_block)
+	if (r != -ETIME && chan->cl->tx_block)
 		complete(&chan->tx_complete);
 }
 
@@ -260,7 +263,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg)
 
 	msg_submit(chan);
 
-	if (chan->cl->tx_block && chan->active_req) {
+	if (chan->cl->tx_block) {
 		unsigned long wait;
 		int ret;
 
@@ -271,8 +274,8 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg)
 
 		ret = wait_for_completion_timeout(&chan->tx_complete, wait);
 		if (ret == 0) {
-			t = -EIO;
-			tx_tick(chan, -EIO);
+			t = -ETIME;
+			tx_tick(chan, t);
 		}
 	}
 
@@ -453,6 +456,12 @@ int mbox_controller_register(struct mbox_controller *mbox)
 		txdone = TXDONE_BY_ACK;
 
 	if (txdone == TXDONE_BY_POLL) {
+
+		if (!mbox->ops->last_tx_done) {
+			dev_err(mbox->dev, "last_tx_done method is absent\n");
+			return -EINVAL;
+		}
+
 		hrtimer_init(&mbox->poll_hrt, CLOCK_MONOTONIC,
 			     HRTIMER_MODE_REL);
 		mbox->poll_hrt.function = txdone_hrtimer;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index a126919ed102..5d13930f0f22 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -4,7 +4,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/errno.h>
-#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/sched/clock.h>
 #include <linux/llist.h>
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index e4c2c1a1e993..6735c8d6a445 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -932,7 +932,7 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd,
 	*result = true;
 
 	r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
-				   from_cblock(begin), &cmd->dirty_cursor);
+				   from_cblock(cmd->cache_blocks), &cmd->dirty_cursor);
 	if (r) {
 		DMERR("%s: dm_bitset_cursor_begin for dirty failed", __func__);
 		return r;
@@ -959,14 +959,16 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd,
 			return 0;
 		}
 
+		begin = to_cblock(from_cblock(begin) + 1);
+		if (begin == end)
+			break;
+
 		r = dm_bitset_cursor_next(&cmd->dirty_cursor);
 		if (r) {
 			DMERR("%s: dm_bitset_cursor_next for dirty failed", __func__);
 			dm_bitset_cursor_end(&cmd->dirty_cursor);
 			return r;
 		}
-
-		begin = to_cblock(from_cblock(begin) + 1);
 	}
 
 	dm_bitset_cursor_end(&cmd->dirty_cursor);
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 9c689b34e6e7..975922c8f231 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2773,7 +2773,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 
 	ti->num_discard_bios = 1;
 	ti->discards_supported = true;
-	ti->discard_zeroes_data_unsupported = true;
 	ti->split_discard_bios = false;
 
 	cache->features = ca->features;
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 136fda3ff9e5..fea5bd52ada8 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -132,6 +132,7 @@ void dm_init_md_queue(struct mapped_device *md);
 void dm_init_normal_md_queue(struct mapped_device *md);
 int md_in_flight(struct mapped_device *md);
 void disable_write_same(struct mapped_device *md);
+void disable_write_zeroes(struct mapped_device *md);
 
 static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
 {
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 389a3637ffcc..ef1d836bd81b 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -2030,7 +2030,6 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	wake_up_process(cc->write_thread);
 
 	ti->num_flush_bios = 1;
-	ti->discard_zeroes_data_unsupported = true;
 
 	return 0;
 
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 03940bf36f6c..3702e502466d 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -312,9 +312,12 @@ static void do_region(int op, int op_flags, unsigned region,
 	 */
 	if (op == REQ_OP_DISCARD)
 		special_cmd_max_sectors = q->limits.max_discard_sectors;
+	else if (op == REQ_OP_WRITE_ZEROES)
+		special_cmd_max_sectors = q->limits.max_write_zeroes_sectors;
 	else if (op == REQ_OP_WRITE_SAME)
 		special_cmd_max_sectors = q->limits.max_write_same_sectors;
-	if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_SAME) &&
+	if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES ||
+	     op == REQ_OP_WRITE_SAME)  &&
 	    special_cmd_max_sectors == 0) {
 		dec_count(io, region, -EOPNOTSUPP);
 		return;
@@ -328,11 +331,18 @@ static void do_region(int op, int op_flags, unsigned region,
 		/*
 		 * Allocate a suitably sized-bio.
 		 */
-		if ((op == REQ_OP_DISCARD) || (op == REQ_OP_WRITE_SAME))
+		switch (op) {
+		case REQ_OP_DISCARD:
+		case REQ_OP_WRITE_ZEROES:
+			num_bvecs = 0;
+			break;
+		case REQ_OP_WRITE_SAME:
 			num_bvecs = 1;
-		else
+			break;
+		default:
 			num_bvecs = min_t(int, BIO_MAX_PAGES,
 					  dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
+		}
 
 		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
 		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
@@ -341,7 +351,7 @@ static void do_region(int op, int op_flags, unsigned region,
 		bio_set_op_attrs(bio, op, op_flags);
 		store_io_and_region_in_bio(bio, io, region);
 
-		if (op == REQ_OP_DISCARD) {
+		if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) {
 			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 			remaining -= num_sectors;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 9e9d04cb7d51..f85846741d50 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -733,11 +733,11 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 		job->pages = &zero_page_list;
 
 		/*
-		 * Use WRITE SAME to optimize zeroing if all dests support it.
+		 * Use WRITE ZEROES to optimize zeroing if all dests support it.
 		 */
-		job->rw = REQ_OP_WRITE_SAME;
+		job->rw = REQ_OP_WRITE_ZEROES;
 		for (i = 0; i < job->num_dests; i++)
-			if (!bdev_write_same(job->dests[i].bdev)) {
+			if (!bdev_write_zeroes_sectors(job->dests[i].bdev)) {
 				job->rw = WRITE;
 				break;
 			}
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 4788b0b989a9..e17fd44ceef5 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -59,6 +59,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
+	ti->num_write_zeroes_bios = 1;
 	ti->private = lc;
 	return 0;
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 7f223dbed49f..2950b145443d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1103,6 +1103,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
+	ti->num_write_zeroes_bios = 1;
 	if (m->queue_mode == DM_TYPE_BIO_BASED)
 		ti->per_io_data_size = multipath_per_bio_data_size();
 	else
@@ -1491,7 +1492,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	 */
 	int r = DM_ENDIO_REQUEUE;
 
-	if (!error && !clone->errors)
+	if (!error)
 		return 0;	/* I/O complete */
 
 	if (noretry_error(error))
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index f8564d63982f..2dae3e5b851c 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2813,7 +2813,9 @@ static void configure_discard_support(struct raid_set *rs)
 	/* Assume discards not supported until after checks below. */
 	ti->discards_supported = false;
 
-	/* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
+	/*
+	 * XXX: RAID level 4,5,6 require zeroing for safety.
+	 */
 	raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
 
 	for (i = 0; i < rs->raid_disks; i++) {
@@ -2827,8 +2829,6 @@ static void configure_discard_support(struct raid_set *rs)
 			return;
 
 		if (raid456) {
-			if (!q->limits.discard_zeroes_data)
-				return;
 			if (!devices_handle_discard_safely) {
 				DMERR("raid456 discard support disabled due to discard_zeroes_data uncertainty.");
 				DMERR("Set dm-raid.devices_handle_discard_safely=Y to override.");
@@ -3726,7 +3726,7 @@ static int raid_preresume(struct dm_target *ti)
 		return r;
 
 	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
-	if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) &&
+	if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
 	    mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
 		r = bitmap_resize(mddev->bitmap, mddev->dev_sectors,
 				  to_bytes(rs->requested_bitmap_chunk_sectors), 0);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 2ddc2d20e62d..a95cbb80fb34 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1124,7 +1124,6 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->per_io_data_size = sizeof(struct dm_raid1_bio_record);
-	ti->discard_zeroes_data_unsupported = true;
 
 	ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_MEM_RECLAIM, 0);
 	if (!ms->kmirrord_wq) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 28955b94d2b2..bff7e3bdb4ed 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -298,9 +298,14 @@ static void dm_done(struct request *clone, int error, bool mapped)
 			r = rq_end_io(tio->ti, clone, error, &tio->info);
 	}
 
-	if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
-		     !clone->q->limits.max_write_same_sectors))
-		disable_write_same(tio->md);
+	if (unlikely(r == -EREMOTEIO)) {
+		if (req_op(clone) == REQ_OP_WRITE_SAME &&
+		    !clone->q->limits.max_write_same_sectors)
+			disable_write_same(tio->md);
+		if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
+		    !clone->q->limits.max_write_zeroes_sectors)
+			disable_write_zeroes(tio->md);
+	}
 
 	if (r <= 0)
 		/* The target wants to complete the I/O */
@@ -358,7 +363,7 @@ static void dm_complete_request(struct request *rq, int error)
 	if (!rq->q->mq_ops)
 		blk_complete_request(rq);
 	else
-		blk_mq_complete_request(rq, error);
+		blk_mq_complete_request(rq);
 }
 
 /*
@@ -755,13 +760,14 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 		/* Undo dm_start_request() before requeuing */
 		rq_end_stats(md, rq);
 		rq_completed(md, rq_data_dir(rq), false);
+		blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
 		return BLK_MQ_RQ_QUEUE_BUSY;
 	}
 
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
-static struct blk_mq_ops dm_mq_ops = {
+static const struct blk_mq_ops dm_mq_ops = {
 	.queue_rq = dm_mq_queue_rq,
 	.complete = dm_softirq_done,
 	.init_request = dm_mq_init_request,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 28193a57bf47..5ef49c121d99 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -169,6 +169,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->num_flush_bios = stripes;
 	ti->num_discard_bios = stripes;
 	ti->num_write_same_bios = stripes;
+	ti->num_write_zeroes_bios = stripes;
 
 	sc->chunk_size = chunk_size;
 	if (chunk_size & (chunk_size - 1))
@@ -293,6 +294,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 	}
 	if (unlikely(bio_op(bio) == REQ_OP_DISCARD) ||
+	    unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES) ||
 	    unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) {
 		target_bio_nr = dm_bio_get_target_bio_nr(bio);
 		BUG_ON(target_bio_nr >= sc->stripes);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3ad16d9c9d5a..958275aca008 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1449,22 +1449,6 @@ static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush)
 	return false;
 }
 
-static bool dm_table_discard_zeroes_data(struct dm_table *t)
-{
-	struct dm_target *ti;
-	unsigned i = 0;
-
-	/* Ensure that all targets supports discard_zeroes_data. */
-	while (i < dm_table_get_num_targets(t)) {
-		ti = dm_table_get_target(t, i++);
-
-		if (ti->discard_zeroes_data_unsupported)
-			return false;
-	}
-
-	return true;
-}
-
 static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
 			    sector_t start, sector_t len, void *data)
 {
@@ -1533,6 +1517,34 @@ static bool dm_table_supports_write_same(struct dm_table *t)
 	return true;
 }
 
+static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev,
+					   sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !q->limits.max_write_zeroes_sectors;
+}
+
+static bool dm_table_supports_write_zeroes(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!ti->num_write_zeroes_bios)
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
+
 static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
@@ -1592,9 +1604,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 	blk_queue_write_cache(q, wc, fua);
 
-	if (!dm_table_discard_zeroes_data(t))
-		q->limits.discard_zeroes_data = 0;
-
 	/* Ensure that all underlying devices are non-rotational. */
 	if (dm_table_all_devices_attribute(t, device_is_nonrot))
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
@@ -1603,6 +1612,8 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 
 	if (!dm_table_supports_write_same(t))
 		q->limits.max_write_same_sectors = 0;
+	if (!dm_table_supports_write_zeroes(t))
+		q->limits.max_write_zeroes_sectors = 0;
 
 	if (dm_table_all_devices_attribute(t, queue_supports_sg_merge))
 		queue_flag_clear_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 2b266a2b5035..a5f1916f621a 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3263,7 +3263,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	 * them down to the data device.  The thin device's discard
 	 * processing will cause mappings to be removed from the btree.
 	 */
-	ti->discard_zeroes_data_unsupported = true;
 	if (pf.discard_enabled && pf.discard_passdown) {
 		ti->num_discard_bios = 1;
 
@@ -4119,7 +4118,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->per_io_data_size = sizeof(struct dm_thin_endio_hook);
 
 	/* In case the pool supports discards, pass them on. */
-	ti->discard_zeroes_data_unsupported = true;
 	if (tc->pool->pf.discard_enabled) {
 		ti->discards_supported = true;
 		ti->num_discard_bios = 1;
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 0f0eb8a3d922..78f36012eaca 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -146,8 +146,6 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
 		block = fec_buffer_rs_block(v, fio, n, i);
 		res = fec_decode_rs8(v, fio, block, &par[offset], neras);
 		if (res < 0) {
-			dm_bufio_release(buf);
-
 			r = res;
 			goto error;
 		}
@@ -172,6 +170,8 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
 done:
 	r = corrected;
 error:
+	dm_bufio_release(buf);
+
 	if (r < 0 && neras)
 		DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
 			    v->data_dev->name, (unsigned long long)rsb, r);
@@ -269,7 +269,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io,
 					  &is_zero) == 0) {
 			/* skip known zero blocks entirely */
 			if (is_zero)
-				continue;
+				goto done;
 
 			/*
 			 * skip if we have already found the theoretical
@@ -439,6 +439,13 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
 	if (!verity_fec_is_enabled(v))
 		return -EOPNOTSUPP;
 
+	if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) {
+		DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name);
+		return -EIO;
+	}
+
+	fio->level++;
+
 	if (type == DM_VERITY_BLOCK_TYPE_METADATA)
 		block += v->data_blocks;
 
@@ -470,7 +477,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
 	if (r < 0) {
 		r = fec_decode_rsb(v, io, fio, rsb, offset, true);
 		if (r < 0)
-			return r;
+			goto done;
 	}
 
 	if (dest)
@@ -480,6 +487,8 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
 		r = verity_for_bv_block(v, io, iter, fec_bv_copy);
 	}
 
+done:
+	fio->level--;
 	return r;
 }
 
@@ -520,6 +529,7 @@ void verity_fec_init_io(struct dm_verity_io *io)
 	memset(fio->bufs, 0, sizeof(fio->bufs));
 	fio->nbufs = 0;
 	fio->output = NULL;
+	fio->level = 0;
 }
 
 /*
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
index 7fa0298b995e..bb31ce87a933 100644
--- a/drivers/md/dm-verity-fec.h
+++ b/drivers/md/dm-verity-fec.h
@@ -27,6 +27,9 @@
 #define DM_VERITY_FEC_BUF_MAX \
 	(1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS))
 
+/* maximum recursion level for verity_fec_decode */
+#define DM_VERITY_FEC_MAX_RECURSION	4
+
 #define DM_VERITY_OPT_FEC_DEV		"use_fec_from_device"
 #define DM_VERITY_OPT_FEC_BLOCKS	"fec_blocks"
 #define DM_VERITY_OPT_FEC_START		"fec_start"
@@ -58,6 +61,7 @@ struct dm_verity_fec_io {
 	unsigned nbufs;		/* number of buffers allocated */
 	u8 *output;		/* buffer for corrected output */
 	size_t output_pos;
+	unsigned level;		/* recursion level */
 };
 
 #ifdef CONFIG_DM_VERITY_FEC
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f4ffd1eb8f44..8bf397729bbd 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -810,7 +810,6 @@ static void dec_pending(struct dm_io *io, int error)
 			queue_io(md, bio);
 		} else {
 			/* done with normal IO or empty flush */
-			trace_block_bio_complete(md->queue, bio, io_error);
 			bio->bi_error = io_error;
 			bio_endio(bio);
 		}
@@ -825,6 +824,14 @@ void disable_write_same(struct mapped_device *md)
 	limits->max_write_same_sectors = 0;
 }
 
+void disable_write_zeroes(struct mapped_device *md)
+{
+	struct queue_limits *limits = dm_get_queue_limits(md);
+
+	/* device doesn't really support WRITE ZEROES, disable it */
+	limits->max_write_zeroes_sectors = 0;
+}
+
 static void clone_endio(struct bio *bio)
 {
 	int error = bio->bi_error;
@@ -851,9 +858,14 @@ static void clone_endio(struct bio *bio)
 		}
 	}
 
-	if (unlikely(r == -EREMOTEIO && (bio_op(bio) == REQ_OP_WRITE_SAME) &&
-		     !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
-		disable_write_same(md);
+	if (unlikely(r == -EREMOTEIO)) {
+		if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+		    !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
+			disable_write_same(md);
+		if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+		    !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+			disable_write_zeroes(md);
+	}
 
 	free_tio(tio);
 	dec_pending(io, error);
@@ -989,26 +1001,29 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
 	struct dm_offload *o = container_of(cb, struct dm_offload, cb);
 	struct bio_list list;
 	struct bio *bio;
+	int i;
 
 	INIT_LIST_HEAD(&o->cb.list);
 
 	if (unlikely(!current->bio_list))
 		return;
 
-	list = *current->bio_list;
-	bio_list_init(current->bio_list);
-
-	while ((bio = bio_list_pop(&list))) {
-		struct bio_set *bs = bio->bi_pool;
-		if (unlikely(!bs) || bs == fs_bio_set) {
-			bio_list_add(current->bio_list, bio);
-			continue;
+	for (i = 0; i < 2; i++) {
+		list = current->bio_list[i];
+		bio_list_init(&current->bio_list[i]);
+
+		while ((bio = bio_list_pop(&list))) {
+			struct bio_set *bs = bio->bi_pool;
+			if (unlikely(!bs) || bs == fs_bio_set) {
+				bio_list_add(&current->bio_list[i], bio);
+				continue;
+			}
+
+			spin_lock(&bs->rescue_lock);
+			bio_list_add(&bs->rescue_list, bio);
+			queue_work(bs->rescue_workqueue, &bs->rescue_work);
+			spin_unlock(&bs->rescue_lock);
 		}
-
-		spin_lock(&bs->rescue_lock);
-		bio_list_add(&bs->rescue_list, bio);
-		queue_work(bs->rescue_workqueue, &bs->rescue_work);
-		spin_unlock(&bs->rescue_lock);
 	}
 }
 
@@ -1199,6 +1214,11 @@ static unsigned get_num_write_same_bios(struct dm_target *ti)
 	return ti->num_write_same_bios;
 }
 
+static unsigned get_num_write_zeroes_bios(struct dm_target *ti)
+{
+	return ti->num_write_zeroes_bios;
+}
+
 typedef bool (*is_split_required_fn)(struct dm_target *ti);
 
 static bool is_split_required_for_discard(struct dm_target *ti)
@@ -1253,6 +1273,11 @@ static int __send_write_same(struct clone_info *ci)
 	return __send_changing_extent_only(ci, get_num_write_same_bios, NULL);
 }
 
+static int __send_write_zeroes(struct clone_info *ci)
+{
+	return __send_changing_extent_only(ci, get_num_write_zeroes_bios, NULL);
+}
+
 /*
  * Select the correct strategy for processing a non-flush bio.
  */
@@ -1267,6 +1292,8 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 		return __send_discard(ci);
 	else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
 		return __send_write_same(ci);
+	else if (unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES))
+		return __send_write_zeroes(ci);
 
 	ti = dm_table_find_target(ci->map, ci->sector);
 	if (!dm_target_is_valid(ti))
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 3e38e0207a3e..377a8a3672e3 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -293,6 +293,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 						      split, disk_devt(mddev->gendisk),
 						      bio_sector);
 			mddev_check_writesame(mddev, split);
+			mddev_check_write_zeroes(mddev, split);
 			generic_make_request(split);
 		}
 	} while (split != bio);
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 2b13117fb918..321ecac23027 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -777,7 +777,6 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 		bm_lockres->flags |= DLM_LKF_NOQUEUE;
 		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
 		if (ret == -EAGAIN) {
-			memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE);
 			s = read_resync_info(mddev, bm_lockres);
 			if (s) {
 				pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
@@ -974,6 +973,7 @@ static int leave(struct mddev *mddev)
 	lockres_free(cinfo->bitmap_lockres);
 	unlock_all_bitmaps(mddev);
 	dlm_release_lockspace(cinfo->lockspace, 2);
+	kfree(cinfo);
 	return 0;
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 548d1b8014f8..f6ae1d67bcd0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -440,14 +440,6 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_flush_request);
 
-void md_unplug(struct blk_plug_cb *cb, bool from_schedule)
-{
-	struct mddev *mddev = cb->data;
-	md_wakeup_thread(mddev->thread);
-	kfree(cb);
-}
-EXPORT_SYMBOL(md_unplug);
-
 static inline struct mddev *mddev_get(struct mddev *mddev)
 {
 	atomic_inc(&mddev->active);
@@ -1887,7 +1879,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	}
 	sb = page_address(rdev->sb_page);
 	sb->data_size = cpu_to_le64(num_sectors);
-	sb->super_offset = rdev->sb_start;
+	sb->super_offset = cpu_to_le64(rdev->sb_start);
 	sb->sb_csum = calc_sb_1_csum(sb);
 	do {
 		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
@@ -2295,7 +2287,7 @@ static bool does_sb_need_changing(struct mddev *mddev)
 	/* Check if any mddev parameters have changed */
 	if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
 	    (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
-	    (mddev->layout != le64_to_cpu(sb->layout)) ||
+	    (mddev->layout != le32_to_cpu(sb->layout)) ||
 	    (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
 	    (mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
 		return true;
@@ -6458,11 +6450,10 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	mddev->layout        = info->layout;
 	mddev->chunk_sectors = info->chunk_size >> 9;
 
-	mddev->max_disks     = MD_SB_DISKS;
-
 	if (mddev->persistent) {
-		mddev->flags         = 0;
-		mddev->sb_flags         = 0;
+		mddev->max_disks = MD_SB_DISKS;
+		mddev->flags = 0;
+		mddev->sb_flags = 0;
 	}
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 
@@ -6533,8 +6524,12 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 			return -ENOSPC;
 	}
 	rv = mddev->pers->resize(mddev, num_sectors);
-	if (!rv)
-		revalidate_disk(mddev->gendisk);
+	if (!rv) {
+		if (mddev->queue) {
+			set_capacity(mddev->gendisk, mddev->array_sectors);
+			revalidate_disk(mddev->gendisk);
+		}
+	}
 	return rv;
 }
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b8859cbf84b6..1e76d64ce180 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -676,16 +676,10 @@ extern void mddev_resume(struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   struct mddev *mddev);
 
-extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
 extern void md_kick_rdev_from_array(struct md_rdev * rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
-static inline int mddev_check_plugged(struct mddev *mddev)
-{
-	return !!blk_check_plugged(md_unplug, mddev,
-				   sizeof(struct blk_plug_cb));
-}
 
 static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 {
@@ -715,4 +709,11 @@ static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio)
 	    !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
 		mddev->queue->limits.max_write_same_sectors = 0;
 }
+
+static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio)
+{
+	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+	    !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+		mddev->queue->limits.max_write_zeroes_sectors = 0;
+}
 #endif /* _MD_MD_H */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 79a12b59250b..e95d521d93e9 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -139,6 +139,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	mp_bh->bio.bi_end_io = multipath_end_request;
 	mp_bh->bio.bi_private = mp_bh;
 	mddev_check_writesame(mddev, &mp_bh->bio);
+	mddev_check_write_zeroes(mddev, &mp_bh->bio);
 	generic_make_request(&mp_bh->bio);
 	return;
 }
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 93347ca7c7a6..ce7a6a56cf73 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -383,6 +383,7 @@ static int raid0_run(struct mddev *mddev)
 
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
+		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
 
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
@@ -504,6 +505,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 						      split, disk_devt(mddev->gendisk),
 						      bio_sector);
 			mddev_check_writesame(mddev, split);
+			mddev_check_write_zeroes(mddev, split);
 			generic_make_request(split);
 		}
 	} while (split != bio);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fbc2d7851b49..b59cc100320a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1027,7 +1027,7 @@ static int get_unqueued_pending(struct r1conf *conf)
 static void freeze_array(struct r1conf *conf, int extra)
 {
 	/* Stop sync I/O and normal I/O and wait for everything to
-	 * go quite.
+	 * go quiet.
 	 * This is called in two situations:
 	 * 1) management command handlers (reshape, remove disk, quiesce).
 	 * 2) one normal I/O request failed.
@@ -1587,9 +1587,30 @@ static void raid1_make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
-		if (bio_data_dir(split) == READ)
+		if (bio_data_dir(split) == READ) {
 			raid1_read_request(mddev, split);
-		else
+
+			/*
+			 * If a bio is splitted, the first part of bio will
+			 * pass barrier but the bio is queued in
+			 * current->bio_list (see generic_make_request). If
+			 * there is a raise_barrier() called here, the second
+			 * part of bio can't pass barrier. But since the first
+			 * part bio isn't dispatched to underlaying disks yet,
+			 * the barrier is never released, hence raise_barrier
+			 * will alays wait. We have a deadlock.
+			 * Note, this only happens in read path. For write
+			 * path, the first part of bio is dispatched in a
+			 * schedule() call (because of blk plug) or offloaded
+			 * to raid10d.
+			 * Quitting from the function immediately can change
+			 * the bio order queued in bio_list and avoid the deadlock.
+			 */
+			if (split != bio) {
+				generic_make_request(bio);
+				break;
+			}
+		} else
 			raid1_write_request(mddev, split);
 	} while (split != bio);
 }
@@ -3156,8 +3177,10 @@ static int raid1_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (mddev->queue)
+	if (mddev->queue) {
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
+		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
+	}
 
 	rdev_for_each(rdev, mddev) {
 		if (!mddev->gendisk)
@@ -3246,8 +3269,6 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, newsize);
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > mddev->dev_sectors) {
 		mddev->recovery_cp = mddev->dev_sectors;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 063c43d83b72..28ec3a93acee 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -974,7 +974,8 @@ static void wait_barrier(struct r10conf *conf)
 				    !conf->barrier ||
 				    (atomic_read(&conf->nr_pending) &&
 				     current->bio_list &&
-				     !bio_list_empty(current->bio_list)),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1]))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 		if (!conf->nr_waiting)
@@ -1477,11 +1478,24 @@ retry_write:
 			mbio->bi_bdev = (void*)rdev;
 
 			atomic_inc(&r10_bio->remaining);
+
+			cb = blk_check_plugged(raid10_unplug, mddev,
+					       sizeof(*plug));
+			if (cb)
+				plug = container_of(cb, struct raid10_plug_cb,
+						    cb);
+			else
+				plug = NULL;
 			spin_lock_irqsave(&conf->device_lock, flags);
-			bio_list_add(&conf->pending_bio_list, mbio);
-			conf->pending_count++;
+			if (plug) {
+				bio_list_add(&plug->pending, mbio);
+				plug->pending_cnt++;
+			} else {
+				bio_list_add(&conf->pending_bio_list, mbio);
+				conf->pending_count++;
+			}
 			spin_unlock_irqrestore(&conf->device_lock, flags);
-			if (!mddev_check_plugged(mddev))
+			if (!plug)
 				md_wakeup_thread(mddev->thread);
 		}
 	}
@@ -1571,7 +1585,25 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
+		/*
+		 * If a bio is splitted, the first part of bio will pass
+		 * barrier but the bio is queued in current->bio_list (see
+		 * generic_make_request). If there is a raise_barrier() called
+		 * here, the second part of bio can't pass barrier. But since
+		 * the first part bio isn't dispatched to underlaying disks
+		 * yet, the barrier is never released, hence raise_barrier will
+		 * alays wait. We have a deadlock.
+		 * Note, this only happens in read path. For write path, the
+		 * first part of bio is dispatched in a schedule() call
+		 * (because of blk plug) or offloaded to raid10d.
+		 * Quitting from the function immediately can change the bio
+		 * order queued in bio_list and avoid the deadlock.
+		 */
 		__make_request(mddev, split);
+		if (split != bio && bio_data_dir(bio) == READ) {
+			generic_make_request(bio);
+			break;
+		}
 	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
@@ -3717,6 +3749,7 @@ static int raid10_run(struct mddev *mddev)
 		blk_queue_max_discard_sectors(mddev->queue,
 					      mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
+		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 		blk_queue_io_min(mddev->queue, chunk_size);
 		if (conf->geo.raid_disks % conf->geo.near_copies)
 			blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
@@ -3943,10 +3976,6 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, size);
-	if (mddev->queue) {
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
-	}
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > oldsize) {
 		mddev->recovery_cp = oldsize;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4fb09b3fcb41..2efdb0d67460 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1401,7 +1401,8 @@ static int set_syndrome_sources(struct page **srcs,
 		     (test_bit(R5_Wantdrain, &dev->flags) ||
 		      test_bit(R5_InJournal, &dev->flags))) ||
 		    (srctype == SYNDROME_SRC_WRITTEN &&
-		     dev->written)) {
+		     (dev->written ||
+		      test_bit(R5_InJournal, &dev->flags)))) {
 			if (test_bit(R5_InJournal, &dev->flags))
 				srcs[slot] = sh->dev[i].orig_page;
 			else
@@ -5030,8 +5031,6 @@ static void raid5_align_endio(struct bio *bi)
 	rdev_dec_pending(rdev, conf->mddev);
 
 	if (!error) {
-		trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
-					 raid_bi, 0);
 		bio_endio(raid_bi);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_quiescent);
@@ -7228,7 +7227,6 @@ static int raid5_run(struct mddev *mddev)
 
 	if (mddev->queue) {
 		int chunk_size;
-		bool discard_supported = true;
 		/* read-ahead size must cover two whole stripes, which
 		 * is 2 * (datadisks) * chunksize where 'n' is the
 		 * number of raid devices
@@ -7264,48 +7262,32 @@ static int raid5_run(struct mddev *mddev)
 		blk_queue_max_discard_sectors(mddev->queue,
 					      0xfffe * STRIPE_SECTORS);
 
-		/*
-		 * unaligned part of discard request will be ignored, so can't
-		 * guarantee discard_zeroes_data
-		 */
-		mddev->queue->limits.discard_zeroes_data = 0;
-
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
+		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 
 		rdev_for_each(rdev, mddev) {
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->new_data_offset << 9);
-			/*
-			 * discard_zeroes_data is required, otherwise data
-			 * could be lost. Consider a scenario: discard a stripe
-			 * (the stripe could be inconsistent if
-			 * discard_zeroes_data is 0); write one disk of the
-			 * stripe (the stripe could be inconsistent again
-			 * depending on which disks are used to calculate
-			 * parity); the disk is broken; The stripe data of this
-			 * disk is lost.
-			 */
-			if (!blk_queue_discard(bdev_get_queue(rdev->bdev)) ||
-			    !bdev_get_queue(rdev->bdev)->
-						limits.discard_zeroes_data)
-				discard_supported = false;
-			/* Unfortunately, discard_zeroes_data is not currently
-			 * a guarantee - just a hint.  So we only allow DISCARD
-			 * if the sysadmin has confirmed that only safe devices
-			 * are in use by setting a module parameter.
-			 */
-			if (!devices_handle_discard_safely) {
-				if (discard_supported) {
-					pr_info("md/raid456: discard support disabled due to uncertainty.\n");
-					pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
-				}
-				discard_supported = false;
-			}
 		}
 
-		if (discard_supported &&
+		/*
+		 * zeroing is required, otherwise data
+		 * could be lost. Consider a scenario: discard a stripe
+		 * (the stripe could be inconsistent if
+		 * discard_zeroes_data is 0); write one disk of the
+		 * stripe (the stripe could be inconsistent again
+		 * depending on which disks are used to calculate
+		 * parity); the disk is broken; The stripe data of this
+		 * disk is lost.
+		 *
+		 * We only allow DISCARD if the sysadmin has confirmed that
+		 * only safe devices are in use by setting a module parameter.
+		 * A better idea might be to turn DISCARD into WRITE_ZEROES
+		 * requests, as that is required to be safe.
+		 */
+		if (devices_handle_discard_safely &&
 		    mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
 		    mddev->queue->limits.discard_granularity >= stripe)
 			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
@@ -7605,8 +7587,6 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, newsize);
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > mddev->dev_sectors) {
 		mddev->recovery_cp = mddev->dev_sectors;
diff --git a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
index 7a681d8202c7..4442e478db72 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
+++ b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
@@ -256,8 +256,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
 *
 * The actual DAP implementation may be restricted to only one of the modes.
 * A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the mode defined below.
-*
+* overrides or cannot handle the mode defined below.
 */
 #ifndef DRXDAP_SINGLE_MASTER
 #define DRXDAP_SINGLE_MASTER 1
@@ -272,7 +271,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
 *
 * This maximum size may be restricted by the actual DAP implementation.
 * A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the chunksize defined below.
+* overrides or cannot handle the chunksize defined below.
 *
 * Beware that the DAP uses  DRXDAP_MAX_WCHUNKSIZE to create a temporary data
 * buffer. Do not undefine or choose too large, unless your system is able to
@@ -292,8 +291,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
 *
 * This maximum size may be restricted by the actual DAP implementation.
 * A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the chunksize defined below.
-*
+* overrides or cannot handle the chunksize defined below.
 */
 #ifndef DRXDAP_MAX_RCHUNKSIZE
 #define  DRXDAP_MAX_RCHUNKSIZE 60
diff --git a/drivers/media/platform/coda/imx-vdoa.c b/drivers/media/platform/coda/imx-vdoa.c
index 67fd8ffa60a4..669a4c82f1ff 100644
--- a/drivers/media/platform/coda/imx-vdoa.c
+++ b/drivers/media/platform/coda/imx-vdoa.c
@@ -321,7 +321,7 @@ static const struct of_device_id vdoa_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, vdoa_dt_ids);
 
-static const struct platform_driver vdoa_driver = {
+static struct platform_driver vdoa_driver = {
 	.probe		= vdoa_probe,
 	.remove		= vdoa_remove,
 	.driver		= {
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.c b/drivers/media/platform/exynos-gsc/gsc-core.c
index cbb03768f5d7..0f0c389f8897 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.c
+++ b/drivers/media/platform/exynos-gsc/gsc-core.c
@@ -861,9 +861,7 @@ int gsc_prepare_addr(struct gsc_ctx *ctx, struct vb2_buffer *vb,
 
 	if ((frame->fmt->pixelformat == V4L2_PIX_FMT_VYUY) ||
 		(frame->fmt->pixelformat == V4L2_PIX_FMT_YVYU) ||
-		(frame->fmt->pixelformat == V4L2_PIX_FMT_NV61) ||
 		(frame->fmt->pixelformat == V4L2_PIX_FMT_YVU420) ||
-		(frame->fmt->pixelformat == V4L2_PIX_FMT_NV21) ||
 		(frame->fmt->pixelformat == V4L2_PIX_FMT_YVU420M))
 		swap(addr->cb, addr->cr);
 
diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
index 823608112d89..7918b928f058 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
@@ -632,8 +632,8 @@ static int bdisp_open(struct file *file)
 
 error_ctrls:
 	bdisp_ctrls_delete(ctx);
-error_fh:
 	v4l2_fh_del(&ctx->fh);
+error_fh:
 	v4l2_fh_exit(&ctx->fh);
 	bdisp_hw_free_nodes(ctx);
 mem_ctx:
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index b4b583f7137a..b4c0f10fc3b0 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -54,12 +54,11 @@ EXPORT_SYMBOL_GPL(vsp1_du_init);
 /**
  * vsp1_du_setup_lif - Setup the output part of the VSP pipeline
  * @dev: the VSP device
- * @width: output frame width in pixels
- * @height: output frame height in pixels
+ * @cfg: the LIF configuration
  *
- * Configure the output part of VSP DRM pipeline for the given frame @width and
- * @height. This sets up formats on the BRU source pad, the WPF0 sink and source
- * pads, and the LIF sink pad.
+ * Configure the output part of VSP DRM pipeline for the given frame @cfg.width
+ * and @cfg.height. This sets up formats on the BRU source pad, the WPF0 sink
+ * and source pads, and the LIF sink pad.
  *
  * As the media bus code on the BRU source pad is conditioned by the
  * configuration of the BRU sink 0 pad, we also set up the formats on all BRU
@@ -69,8 +68,7 @@ EXPORT_SYMBOL_GPL(vsp1_du_init);
  *
  * Return 0 on success or a negative error code on failure.
  */
-int vsp1_du_setup_lif(struct device *dev, unsigned int width,
-		      unsigned int height)
+int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg)
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 	struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
@@ -79,11 +77,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	unsigned int i;
 	int ret;
 
-	dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
-		__func__, width, height);
-
-	if (width == 0 || height == 0) {
-		/* Zero width or height means the CRTC is being disabled, stop
+	if (!cfg) {
+		/* NULL configuration means the CRTC is being disabled, stop
 		 * the pipeline and turn the light off.
 		 */
 		ret = vsp1_pipeline_stop(pipe);
@@ -108,6 +103,9 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 		return 0;
 	}
 
+	dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
+		__func__, cfg->width, cfg->height);
+
 	/* Configure the format at the BRU sinks and propagate it through the
 	 * pipeline.
 	 */
@@ -117,8 +115,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	for (i = 0; i < bru->entity.source_pad; ++i) {
 		format.pad = i;
 
-		format.format.width = width;
-		format.format.height = height;
+		format.format.width = cfg->width;
+		format.format.height = cfg->height;
 		format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
 		format.format.field = V4L2_FIELD_NONE;
 
@@ -133,8 +131,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	}
 
 	format.pad = bru->entity.source_pad;
-	format.format.width = width;
-	format.format.height = height;
+	format.format.width = cfg->width;
+	format.format.height = cfg->height;
 	format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
 	format.format.field = V4L2_FIELD_NONE;
 
@@ -180,7 +178,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	/* Verify that the format at the output of the pipeline matches the
 	 * requested frame size and media bus code.
 	 */
-	if (format.format.width != width || format.format.height != height ||
+	if (format.format.width != cfg->width ||
+	    format.format.height != cfg->height ||
 	    format.format.code != MEDIA_BUS_FMT_ARGB8888_1X32) {
 		dev_dbg(vsp1->dev, "%s: format mismatch\n", __func__);
 		return -EPIPE;
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index 393dccaabdd0..1688893a65bb 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -436,6 +436,8 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 		return -ERESTARTSYS;
 
 	ir = irctls[iminor(inode)];
+	mutex_unlock(&lirc_dev_lock);
+
 	if (!ir) {
 		retval = -ENODEV;
 		goto error;
@@ -476,8 +478,6 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 	}
 
 error:
-	mutex_unlock(&lirc_dev_lock);
-
 	nonseekable_open(inode, file);
 
 	return retval;
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index b109f8246b96..ec4b25bd2ec2 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -176,12 +176,13 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev,
 {
 	u8 tolerance, config;
 	struct nvt_dev *nvt = dev->priv;
+	unsigned long flags;
 	int i;
 
 	/* hardcode the tolerance to 10% */
 	tolerance = DIV_ROUND_UP(count, 10);
 
-	spin_lock(&nvt->lock);
+	spin_lock_irqsave(&nvt->lock, flags);
 
 	nvt_clear_cir_wake_fifo(nvt);
 	nvt_cir_wake_reg_write(nvt, count, CIR_WAKE_FIFO_CMP_DEEP);
@@ -203,7 +204,7 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev,
 
 	nvt_cir_wake_reg_write(nvt, config, CIR_WAKE_IRCON);
 
-	spin_unlock(&nvt->lock);
+	spin_unlock_irqrestore(&nvt->lock, flags);
 }
 
 static ssize_t wakeup_data_show(struct device *dev,
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 2424946740e6..d84533699668 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1663,6 +1663,7 @@ static int rc_setup_rx_device(struct rc_dev *dev)
 {
 	int rc;
 	struct rc_map *rc_map;
+	u64 rc_type;
 
 	if (!dev->map_name)
 		return -EINVAL;
@@ -1677,15 +1678,18 @@ static int rc_setup_rx_device(struct rc_dev *dev)
 	if (rc)
 		return rc;
 
-	if (dev->change_protocol) {
-		u64 rc_type = (1ll << rc_map->rc_type);
+	rc_type = BIT_ULL(rc_map->rc_type);
 
+	if (dev->change_protocol) {
 		rc = dev->change_protocol(dev, &rc_type);
 		if (rc < 0)
 			goto out_table;
 		dev->enabled_protocols = rc_type;
 	}
 
+	if (dev->driver_type == RC_DRIVER_IR_RAW)
+		ir_raw_load_modules(&rc_type);
+
 	set_bit(EV_KEY, dev->input_dev->evbit);
 	set_bit(EV_REP, dev->input_dev->evbit);
 	set_bit(EV_MSC, dev->input_dev->evbit);
@@ -1777,12 +1781,6 @@ int rc_register_device(struct rc_dev *dev)
 		dev->input_name ?: "Unspecified device", path ?: "N/A");
 	kfree(path);
 
-	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
-		rc = rc_setup_rx_device(dev);
-		if (rc)
-			goto out_dev;
-	}
-
 	if (dev->driver_type == RC_DRIVER_IR_RAW ||
 	    dev->driver_type == RC_DRIVER_IR_RAW_TX) {
 		if (!raw_init) {
@@ -1791,7 +1789,13 @@ int rc_register_device(struct rc_dev *dev)
 		}
 		rc = ir_raw_event_register(dev);
 		if (rc < 0)
-			goto out_rx;
+			goto out_dev;
+	}
+
+	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
+		rc = rc_setup_rx_device(dev);
+		if (rc)
+			goto out_raw;
 	}
 
 	/* Allow the RC sysfs nodes to be accessible */
@@ -1803,8 +1807,8 @@ int rc_register_device(struct rc_dev *dev)
 
 	return 0;
 
-out_rx:
-	rc_free_rx_device(dev);
+out_raw:
+	ir_raw_event_unregister(dev);
 out_dev:
 	device_del(&dev->dev);
 out_unlock:
diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 923fb2299553..41b54e40176c 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -487,10 +487,69 @@ static void serial_ir_timeout(unsigned long arg)
 	ir_raw_event_handle(serial_ir.rcdev);
 }
 
+/* Needed by serial_ir_probe() */
+static int serial_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
+			unsigned int count);
+static int serial_ir_tx_duty_cycle(struct rc_dev *dev, u32 cycle);
+static int serial_ir_tx_carrier(struct rc_dev *dev, u32 carrier);
+static int serial_ir_open(struct rc_dev *rcdev);
+static void serial_ir_close(struct rc_dev *rcdev);
+
 static int serial_ir_probe(struct platform_device *dev)
 {
+	struct rc_dev *rcdev;
 	int i, nlow, nhigh, result;
 
+	rcdev = devm_rc_allocate_device(&dev->dev, RC_DRIVER_IR_RAW);
+	if (!rcdev)
+		return -ENOMEM;
+
+	if (hardware[type].send_pulse && hardware[type].send_space)
+		rcdev->tx_ir = serial_ir_tx;
+	if (hardware[type].set_send_carrier)
+		rcdev->s_tx_carrier = serial_ir_tx_carrier;
+	if (hardware[type].set_duty_cycle)
+		rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle;
+
+	switch (type) {
+	case IR_HOMEBREW:
+		rcdev->input_name = "Serial IR type home-brew";
+		break;
+	case IR_IRDEO:
+		rcdev->input_name = "Serial IR type IRdeo";
+		break;
+	case IR_IRDEO_REMOTE:
+		rcdev->input_name = "Serial IR type IRdeo remote";
+		break;
+	case IR_ANIMAX:
+		rcdev->input_name = "Serial IR type AnimaX";
+		break;
+	case IR_IGOR:
+		rcdev->input_name = "Serial IR type IgorPlug";
+		break;
+	}
+
+	rcdev->input_phys = KBUILD_MODNAME "/input0";
+	rcdev->input_id.bustype = BUS_HOST;
+	rcdev->input_id.vendor = 0x0001;
+	rcdev->input_id.product = 0x0001;
+	rcdev->input_id.version = 0x0100;
+	rcdev->open = serial_ir_open;
+	rcdev->close = serial_ir_close;
+	rcdev->dev.parent = &serial_ir.pdev->dev;
+	rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER;
+	rcdev->driver_name = KBUILD_MODNAME;
+	rcdev->map_name = RC_MAP_RC6_MCE;
+	rcdev->min_timeout = 1;
+	rcdev->timeout = IR_DEFAULT_TIMEOUT;
+	rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
+	rcdev->rx_resolution = 250000;
+
+	serial_ir.rcdev = rcdev;
+
+	setup_timer(&serial_ir.timeout_timer, serial_ir_timeout,
+		    (unsigned long)&serial_ir);
+
 	result = devm_request_irq(&dev->dev, irq, serial_ir_irq_handler,
 				  share_irq ? IRQF_SHARED : 0,
 				  KBUILD_MODNAME, &hardware);
@@ -516,9 +575,6 @@ static int serial_ir_probe(struct platform_device *dev)
 		return -EBUSY;
 	}
 
-	setup_timer(&serial_ir.timeout_timer, serial_ir_timeout,
-		    (unsigned long)&serial_ir);
-
 	result = hardware_init_port();
 	if (result < 0)
 		return result;
@@ -552,7 +608,8 @@ static int serial_ir_probe(struct platform_device *dev)
 			 sense ? "low" : "high");
 
 	dev_dbg(&dev->dev, "Interrupt %d, port %04x obtained\n", irq, io);
-	return 0;
+
+	return devm_rc_register_device(&dev->dev, rcdev);
 }
 
 static int serial_ir_open(struct rc_dev *rcdev)
@@ -723,7 +780,6 @@ static void serial_ir_exit(void)
 
 static int __init serial_ir_init_module(void)
 {
-	struct rc_dev *rcdev;
 	int result;
 
 	switch (type) {
@@ -754,63 +810,9 @@ static int __init serial_ir_init_module(void)
 		sense = !!sense;
 
 	result = serial_ir_init();
-	if (result)
-		return result;
-
-	rcdev = devm_rc_allocate_device(&serial_ir.pdev->dev, RC_DRIVER_IR_RAW);
-	if (!rcdev) {
-		result = -ENOMEM;
-		goto serial_cleanup;
-	}
-
-	if (hardware[type].send_pulse && hardware[type].send_space)
-		rcdev->tx_ir = serial_ir_tx;
-	if (hardware[type].set_send_carrier)
-		rcdev->s_tx_carrier = serial_ir_tx_carrier;
-	if (hardware[type].set_duty_cycle)
-		rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle;
-
-	switch (type) {
-	case IR_HOMEBREW:
-		rcdev->input_name = "Serial IR type home-brew";
-		break;
-	case IR_IRDEO:
-		rcdev->input_name = "Serial IR type IRdeo";
-		break;
-	case IR_IRDEO_REMOTE:
-		rcdev->input_name = "Serial IR type IRdeo remote";
-		break;
-	case IR_ANIMAX:
-		rcdev->input_name = "Serial IR type AnimaX";
-		break;
-	case IR_IGOR:
-		rcdev->input_name = "Serial IR type IgorPlug";
-		break;
-	}
-
-	rcdev->input_phys = KBUILD_MODNAME "/input0";
-	rcdev->input_id.bustype = BUS_HOST;
-	rcdev->input_id.vendor = 0x0001;
-	rcdev->input_id.product = 0x0001;
-	rcdev->input_id.version = 0x0100;
-	rcdev->open = serial_ir_open;
-	rcdev->close = serial_ir_close;
-	rcdev->dev.parent = &serial_ir.pdev->dev;
-	rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER;
-	rcdev->driver_name = KBUILD_MODNAME;
-	rcdev->map_name = RC_MAP_RC6_MCE;
-	rcdev->min_timeout = 1;
-	rcdev->timeout = IR_DEFAULT_TIMEOUT;
-	rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
-	rcdev->rx_resolution = 250000;
-
-	serial_ir.rcdev = rcdev;
-
-	result = rc_register_device(rcdev);
-
 	if (!result)
 		return 0;
-serial_cleanup:
+
 	serial_ir_exit();
 	return result;
 }
@@ -818,7 +820,6 @@ serial_cleanup:
 static void __exit serial_ir_exit_module(void)
 {
 	del_timer_sync(&serial_ir.timeout_timer);
-	rc_unregister_device(serial_ir.rcdev);
 	serial_ir_exit();
 }
 
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
index ab9866024ec7..04033efe7ad5 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
@@ -36,16 +36,18 @@ static int usb_cypress_writemem(struct usb_device *udev,u16 addr,u8 *data, u8 le
 int usb_cypress_load_firmware(struct usb_device *udev, const struct firmware *fw, int type)
 {
 	struct hexline *hx;
-	u8 reset;
-	int ret,pos=0;
+	u8 *buf;
+	int ret, pos = 0;
+	u16 cpu_cs_register = cypress[type].cpu_cs_register;
 
-	hx = kmalloc(sizeof(*hx), GFP_KERNEL);
-	if (!hx)
+	buf = kmalloc(sizeof(*hx), GFP_KERNEL);
+	if (!buf)
 		return -ENOMEM;
+	hx = (struct hexline *)buf;
 
 	/* stop the CPU */
-	reset = 1;
-	if ((ret = usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1)) != 1)
+	buf[0] = 1;
+	if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1)
 		err("could not stop the USB controller CPU.");
 
 	while ((ret = dvb_usb_get_hexline(fw, hx, &pos)) > 0) {
@@ -61,21 +63,21 @@ int usb_cypress_load_firmware(struct usb_device *udev, const struct firmware *fw
 	}
 	if (ret < 0) {
 		err("firmware download failed at %d with %d",pos,ret);
-		kfree(hx);
+		kfree(buf);
 		return ret;
 	}
 
 	if (ret == 0) {
 		/* restart the CPU */
-		reset = 0;
-		if (ret || usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1) != 1) {
+		buf[0] = 0;
+		if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1) {
 			err("could not restart the USB controller CPU.");
 			ret = -EINVAL;
 		}
 	} else
 		ret = -EIO;
 
-	kfree(hx);
+	kfree(buf);
 
 	return ret;
 }
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 6ca502d834b4..4f42d57f81d9 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -68,6 +68,7 @@
 struct dw2102_state {
 	u8 initialized;
 	u8 last_lock;
+	u8 data[MAX_XFER_SIZE + 4];
 	struct i2c_client *i2c_client_demod;
 	struct i2c_client *i2c_client_tuner;
 
@@ -661,62 +662,72 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 								int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
-	u8 obuf[0x40], ibuf[0x40];
+	struct dw2102_state *state;
 
 	if (!d)
 		return -ENODEV;
+
+	state = d->priv;
+
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
+	if (mutex_lock_interruptible(&d->data_mutex) < 0) {
+		mutex_unlock(&d->i2c_mutex);
+		return -EAGAIN;
+	}
 
 	switch (num) {
 	case 1:
 		switch (msg[0].addr) {
 		case SU3000_STREAM_CTRL:
-			obuf[0] = msg[0].buf[0] + 0x36;
-			obuf[1] = 3;
-			obuf[2] = 0;
-			if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 0, 0) < 0)
+			state->data[0] = msg[0].buf[0] + 0x36;
+			state->data[1] = 3;
+			state->data[2] = 0;
+			if (dvb_usb_generic_rw(d, state->data, 3,
+					state->data, 0, 0) < 0)
 				err("i2c transfer failed.");
 			break;
 		case DW2102_RC_QUERY:
-			obuf[0] = 0x10;
-			if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 2, 0) < 0)
+			state->data[0] = 0x10;
+			if (dvb_usb_generic_rw(d, state->data, 1,
+					state->data, 2, 0) < 0)
 				err("i2c transfer failed.");
-			msg[0].buf[1] = ibuf[0];
-			msg[0].buf[0] = ibuf[1];
+			msg[0].buf[1] = state->data[0];
+			msg[0].buf[0] = state->data[1];
 			break;
 		default:
 			/* always i2c write*/
-			obuf[0] = 0x08;
-			obuf[1] = msg[0].addr;
-			obuf[2] = msg[0].len;
+			state->data[0] = 0x08;
+			state->data[1] = msg[0].addr;
+			state->data[2] = msg[0].len;
 
-			memcpy(&obuf[3], msg[0].buf, msg[0].len);
+			memcpy(&state->data[3], msg[0].buf, msg[0].len);
 
-			if (dvb_usb_generic_rw(d, obuf, msg[0].len + 3,
-						ibuf, 1, 0) < 0)
+			if (dvb_usb_generic_rw(d, state->data, msg[0].len + 3,
+						state->data, 1, 0) < 0)
 				err("i2c transfer failed.");
 
 		}
 		break;
 	case 2:
 		/* always i2c read */
-		obuf[0] = 0x09;
-		obuf[1] = msg[0].len;
-		obuf[2] = msg[1].len;
-		obuf[3] = msg[0].addr;
-		memcpy(&obuf[4], msg[0].buf, msg[0].len);
-
-		if (dvb_usb_generic_rw(d, obuf, msg[0].len + 4,
-					ibuf, msg[1].len + 1, 0) < 0)
+		state->data[0] = 0x09;
+		state->data[1] = msg[0].len;
+		state->data[2] = msg[1].len;
+		state->data[3] = msg[0].addr;
+		memcpy(&state->data[4], msg[0].buf, msg[0].len);
+
+		if (dvb_usb_generic_rw(d, state->data, msg[0].len + 4,
+					state->data, msg[1].len + 1, 0) < 0)
 			err("i2c transfer failed.");
 
-		memcpy(msg[1].buf, &ibuf[1], msg[1].len);
+		memcpy(msg[1].buf, &state->data[1], msg[1].len);
 		break;
 	default:
 		warn("more than 2 i2c messages at a time is not handled yet.");
 		break;
 	}
+	mutex_unlock(&d->data_mutex);
 	mutex_unlock(&d->i2c_mutex);
 	return num;
 }
@@ -844,17 +855,23 @@ static int su3000_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 static int su3000_power_ctrl(struct dvb_usb_device *d, int i)
 {
 	struct dw2102_state *state = (struct dw2102_state *)d->priv;
-	u8 obuf[] = {0xde, 0};
+	int ret = 0;
 
 	info("%s: %d, initialized %d", __func__, i, state->initialized);
 
 	if (i && !state->initialized) {
+		mutex_lock(&d->data_mutex);
+
+		state->data[0] = 0xde;
+		state->data[1] = 0;
+
 		state->initialized = 1;
 		/* reset board */
-		return dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
+		ret = dvb_usb_generic_rw(d, state->data, 2, NULL, 0, 0);
+		mutex_unlock(&d->data_mutex);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6])
@@ -1309,49 +1326,57 @@ static int prof_7500_frontend_attach(struct dvb_usb_adapter *d)
 	return 0;
 }
 
-static int su3000_frontend_attach(struct dvb_usb_adapter *d)
+static int su3000_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	u8 obuf[3] = { 0xe, 0x80, 0 };
-	u8 ibuf[] = { 0 };
+	struct dvb_usb_device *d = adap->dev;
+	struct dw2102_state *state = d->priv;
+
+	mutex_lock(&d->data_mutex);
+
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x02;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x02;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 	msleep(300);
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 0;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0x51;
+	state->data[0] = 0x51;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	d->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config,
-					&d->dev->i2c_adap);
-	if (d->fe_adap[0].fe == NULL)
+	mutex_unlock(&d->data_mutex);
+
+	adap->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config,
+					&d->i2c_adap);
+	if (adap->fe_adap[0].fe == NULL)
 		return -EIO;
 
-	if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
+	if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe,
 				&dw2104_ts2020_config,
-				&d->dev->i2c_adap)) {
+				&d->i2c_adap)) {
 		info("Attached DS3000/TS2020!");
 		return 0;
 	}
@@ -1360,47 +1385,55 @@ static int su3000_frontend_attach(struct dvb_usb_adapter *d)
 	return -EIO;
 }
 
-static int t220_frontend_attach(struct dvb_usb_adapter *d)
+static int t220_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	u8 obuf[3] = { 0xe, 0x87, 0 };
-	u8 ibuf[] = { 0 };
+	struct dvb_usb_device *d = adap->dev;
+	struct dw2102_state *state = d->priv;
+
+	mutex_lock(&d->data_mutex);
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	state->data[0] = 0xe;
+	state->data[1] = 0x87;
+	state->data[2] = 0x0;
+
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x86;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x86;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x80;
-	obuf[2] = 0;
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
 	msleep(50);
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x80;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0x51;
+	state->data[0] = 0x51;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	d->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config,
-					&d->dev->i2c_adap, NULL);
-	if (d->fe_adap[0].fe != NULL) {
-		if (dvb_attach(tda18271_attach, d->fe_adap[0].fe, 0x60,
-					&d->dev->i2c_adap, &tda18271_config)) {
+	mutex_unlock(&d->data_mutex);
+
+	adap->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config,
+					&d->i2c_adap, NULL);
+	if (adap->fe_adap[0].fe != NULL) {
+		if (dvb_attach(tda18271_attach, adap->fe_adap[0].fe, 0x60,
+					&d->i2c_adap, &tda18271_config)) {
 			info("Attached TDA18271HD/CXD2820R!");
 			return 0;
 		}
@@ -1410,23 +1443,30 @@ static int t220_frontend_attach(struct dvb_usb_adapter *d)
 	return -EIO;
 }
 
-static int m88rs2000_frontend_attach(struct dvb_usb_adapter *d)
+static int m88rs2000_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	u8 obuf[] = { 0x51 };
-	u8 ibuf[] = { 0 };
+	struct dvb_usb_device *d = adap->dev;
+	struct dw2102_state *state = d->priv;
+
+	mutex_lock(&d->data_mutex);
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+	state->data[0] = 0x51;
+
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	d->fe_adap[0].fe = dvb_attach(m88rs2000_attach, &s421_m88rs2000_config,
-					&d->dev->i2c_adap);
+	mutex_unlock(&d->data_mutex);
 
-	if (d->fe_adap[0].fe == NULL)
+	adap->fe_adap[0].fe = dvb_attach(m88rs2000_attach,
+					&s421_m88rs2000_config,
+					&d->i2c_adap);
+
+	if (adap->fe_adap[0].fe == NULL)
 		return -EIO;
 
-	if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
+	if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe,
 				&dw2104_ts2020_config,
-				&d->dev->i2c_adap)) {
+				&d->i2c_adap)) {
 		info("Attached RS2000/TS2020!");
 		return 0;
 	}
@@ -1439,44 +1479,50 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
 {
 	struct dvb_usb_device *d = adap->dev;
 	struct dw2102_state *state = d->priv;
-	u8 obuf[3] = { 0xe, 0x80, 0 };
-	u8 ibuf[] = { 0 };
 	struct i2c_adapter *i2c_adapter;
 	struct i2c_client *client;
 	struct i2c_board_info board_info;
 	struct m88ds3103_platform_data m88ds3103_pdata = {};
 	struct ts2020_config ts2020_config = {};
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	mutex_lock(&d->data_mutex);
+
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 0x0;
+
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x02;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x02;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 	msleep(300);
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 0;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0x51;
+	state->data[0] = 0x51;
 
-	if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
+	mutex_unlock(&d->data_mutex);
+
 	/* attach demod */
 	m88ds3103_pdata.clk = 27000000;
 	m88ds3103_pdata.i2c_wr_max = 33;
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 5457c361ad58..bf0fe0137dfe 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -1947,9 +1947,7 @@ static int gpmc_probe_onenand_child(struct platform_device *pdev,
 	if (!of_property_read_u32(child, "dma-channel", &val))
 		gpmc_onenand_data->dma_channel = val;
 
-	gpmc_onenand_init(gpmc_onenand_data);
-
-	return 0;
+	return gpmc_onenand_init(gpmc_onenand_data);
 }
 #else
 static int gpmc_probe_onenand_child(struct platform_device *pdev,
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 91f645992c94..b27ea98b781f 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1792,15 +1792,14 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
 
 	/* If we're permanently dead, give up. */
 	if (state == pci_channel_io_perm_failure) {
-		/* Tell the AFU drivers; but we don't care what they
-		 * say, we're going away.
-		 */
 		for (i = 0; i < adapter->slices; i++) {
 			afu = adapter->afu[i];
-			/* Only participate in EEH if we are on a virtual PHB */
-			if (afu->phb == NULL)
-				return PCI_ERS_RESULT_NONE;
-			cxl_vphb_error_detected(afu, state);
+			/*
+			 * Tell the AFU drivers; but we don't care what they
+			 * say, we're going away.
+			 */
+			if (afu->phb != NULL)
+				cxl_vphb_error_detected(afu, state);
 		}
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 3600c9993a98..29f2daed37e0 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -112,11 +112,9 @@ struct mkhi_msg {
 
 static int mei_osver(struct mei_cl_device *cldev)
 {
-	int ret;
 	const size_t size = sizeof(struct mkhi_msg_hdr) +
 			    sizeof(struct mkhi_fwcaps) +
 			    sizeof(struct mei_os_ver);
-	size_t length = 8;
 	char buf[size];
 	struct mkhi_msg *req;
 	struct mkhi_fwcaps *fwcaps;
@@ -137,15 +135,7 @@ static int mei_osver(struct mei_cl_device *cldev)
 	os_ver = (struct mei_os_ver *)fwcaps->data;
 	os_ver->os_type = OSTYPE_LINUX;
 
-	ret = __mei_cl_send(cldev->cl, buf, size, mode);
-	if (ret < 0)
-		return ret;
-
-	ret = __mei_cl_recv(cldev->cl, buf, length, 0);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return __mei_cl_send(cldev->cl, buf, size, mode);
 }
 
 static void mei_mkhi_fix(struct mei_cl_device *cldev)
@@ -160,7 +150,7 @@ static void mei_mkhi_fix(struct mei_cl_device *cldev)
 		return;
 
 	ret = mei_osver(cldev);
-	if (ret)
+	if (ret < 0)
 		dev_err(&cldev->dev, "OS version command failed %d\n", ret);
 
 	mei_cldev_disable(cldev);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index cfb1cdf176fa..13c55b8f9261 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -124,8 +124,6 @@ int mei_reset(struct mei_device *dev)
 
 	mei_clear_interrupts(dev);
 
-	mei_synchronize_irq(dev);
-
 	/* we're already in reset, cancel the init timer
 	 * if the reset was called due the hbm protocol error
 	 * we need to call it before hw start
@@ -304,6 +302,9 @@ static void mei_reset_work(struct work_struct *work)
 		container_of(work, struct mei_device,  reset_work);
 	int ret;
 
+	mei_clear_interrupts(dev);
+	mei_synchronize_irq(dev);
+
 	mutex_lock(&dev->device_lock);
 
 	ret = mei_reset(dev);
@@ -328,6 +329,9 @@ void mei_stop(struct mei_device *dev)
 
 	mei_cancel_work(dev);
 
+	mei_clear_interrupts(dev);
+	mei_synchronize_irq(dev);
+
 	mutex_lock(&dev->device_lock);
 
 	dev->dev_state = MEI_DEV_POWER_DOWN;
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 6fb773dbcd0c..93be82fc338a 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -219,15 +219,20 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
 	int write, unsigned long *paddr, int *pageshift)
 {
 	pgd_t *pgdp;
-	pmd_t *pmdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
+	pmd_t *pmdp;
 	pte_t pte;
 
 	pgdp = pgd_offset(vma->vm_mm, vaddr);
 	if (unlikely(pgd_none(*pgdp)))
 		goto err;
 
-	pudp = pud_offset(pgdp, vaddr);
+	p4dp = p4d_offset(pgdp, vaddr);
+	if (unlikely(p4d_none(*p4dp)))
+		goto err;
+
+	pudp = pud_offset(p4dp, vaddr);
 	if (unlikely(pud_none(*pudp)))
 		goto err;
 
diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c
index 9d659542a335..dad5abee656e 100644
--- a/drivers/misc/vmw_vmci/vmci_guest.c
+++ b/drivers/misc/vmw_vmci/vmci_guest.c
@@ -566,10 +566,10 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
 	 */
 	error = pci_alloc_irq_vectors(pdev, VMCI_MAX_INTRS, VMCI_MAX_INTRS,
 			PCI_IRQ_MSIX);
-	if (error) {
+	if (error < 0) {
 		error = pci_alloc_irq_vectors(pdev, 1, 1,
 				PCI_IRQ_MSIX | PCI_IRQ_MSI | PCI_IRQ_LEGACY);
-		if (error)
+		if (error < 0)
 			goto err_remove_bitmap;
 	} else {
 		vmci_dev->exclusive_vectors = true;
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 1621fa08e206..8273b078686d 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -129,6 +129,13 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 				      struct mmc_blk_data *md);
 static int get_card_status(struct mmc_card *card, u32 *status, int retries);
 
+static void mmc_blk_requeue(struct request_queue *q, struct request *req)
+{
+	spin_lock_irq(q->queue_lock);
+	blk_requeue_request(q, req);
+	spin_unlock_irq(q->queue_lock);
+}
+
 static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk)
 {
 	struct mmc_blk_data *md;
@@ -721,10 +728,41 @@ static const struct block_device_operations mmc_bdops = {
 #endif
 };
 
+static int mmc_blk_part_switch_pre(struct mmc_card *card,
+				   unsigned int part_type)
+{
+	int ret = 0;
+
+	if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) {
+		if (card->ext_csd.cmdq_en) {
+			ret = mmc_cmdq_disable(card);
+			if (ret)
+				return ret;
+		}
+		mmc_retune_pause(card->host);
+	}
+
+	return ret;
+}
+
+static int mmc_blk_part_switch_post(struct mmc_card *card,
+				    unsigned int part_type)
+{
+	int ret = 0;
+
+	if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) {
+		mmc_retune_unpause(card->host);
+		if (card->reenable_cmdq && !card->ext_csd.cmdq_en)
+			ret = mmc_cmdq_enable(card);
+	}
+
+	return ret;
+}
+
 static inline int mmc_blk_part_switch(struct mmc_card *card,
 				      struct mmc_blk_data *md)
 {
-	int ret;
+	int ret = 0;
 	struct mmc_blk_data *main_md = dev_get_drvdata(&card->dev);
 
 	if (main_md->part_curr == md->part_type)
@@ -733,8 +771,9 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 	if (mmc_card_mmc(card)) {
 		u8 part_config = card->ext_csd.part_config;
 
-		if (md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
-			mmc_retune_pause(card->host);
+		ret = mmc_blk_part_switch_pre(card, md->part_type);
+		if (ret)
+			return ret;
 
 		part_config &= ~EXT_CSD_PART_CONFIG_ACC_MASK;
 		part_config |= md->part_type;
@@ -743,19 +782,17 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 				 EXT_CSD_PART_CONFIG, part_config,
 				 card->ext_csd.part_time);
 		if (ret) {
-			if (md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
-				mmc_retune_unpause(card->host);
+			mmc_blk_part_switch_post(card, md->part_type);
 			return ret;
 		}
 
 		card->ext_csd.part_config = part_config;
 
-		if (main_md->part_curr == EXT_CSD_PART_CONFIG_ACC_RPMB)
-			mmc_retune_unpause(card->host);
+		ret = mmc_blk_part_switch_post(card, main_md->part_curr);
 	}
 
 	main_md->part_curr = md->part_type;
-	return 0;
+	return ret;
 }
 
 static int mmc_sd_num_wr_blocks(struct mmc_card *card, u32 *written_blocks)
@@ -1272,7 +1309,7 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq,
 {
 	if (!(card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN)) {
 		/* Legacy mode imposes restrictions on transfers. */
-		if (!IS_ALIGNED(brq->cmd.arg, card->ext_csd.rel_sectors))
+		if (!IS_ALIGNED(blk_rq_pos(req), card->ext_csd.rel_sectors))
 			brq->data.blocks = 1;
 
 		if (brq->data.blocks > card->ext_csd.rel_sectors)
@@ -1396,36 +1433,39 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card,
 	return MMC_BLK_SUCCESS;
 }
 
-static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
-			       struct mmc_card *card,
-			       int disable_multi,
-			       struct mmc_queue *mq)
+static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
+			      int disable_multi, bool *do_rel_wr,
+			      bool *do_data_tag)
 {
-	u32 readcmd, writecmd;
+	struct mmc_blk_data *md = mq->blkdata;
+	struct mmc_card *card = md->queue.card;
 	struct mmc_blk_request *brq = &mqrq->brq;
 	struct request *req = mqrq->req;
-	struct mmc_blk_data *md = mq->blkdata;
-	bool do_data_tag;
 
 	/*
 	 * Reliable writes are used to implement Forced Unit Access and
 	 * are supported only on MMCs.
 	 */
-	bool do_rel_wr = (req->cmd_flags & REQ_FUA) &&
-		(rq_data_dir(req) == WRITE) &&
-		(md->flags & MMC_BLK_REL_WR);
+	*do_rel_wr = (req->cmd_flags & REQ_FUA) &&
+		     rq_data_dir(req) == WRITE &&
+		     (md->flags & MMC_BLK_REL_WR);
 
 	memset(brq, 0, sizeof(struct mmc_blk_request));
-	brq->mrq.cmd = &brq->cmd;
+
 	brq->mrq.data = &brq->data;
 
-	brq->cmd.arg = blk_rq_pos(req);
-	if (!mmc_card_blockaddr(card))
-		brq->cmd.arg <<= 9;
-	brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
-	brq->data.blksz = 512;
 	brq->stop.opcode = MMC_STOP_TRANSMISSION;
 	brq->stop.arg = 0;
+
+	if (rq_data_dir(req) == READ) {
+		brq->data.flags = MMC_DATA_READ;
+		brq->stop.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC;
+	} else {
+		brq->data.flags = MMC_DATA_WRITE;
+		brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+	}
+
+	brq->data.blksz = 512;
 	brq->data.blocks = blk_rq_sectors(req);
 
 	/*
@@ -1456,6 +1496,68 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 						brq->data.blocks);
 	}
 
+	if (*do_rel_wr)
+		mmc_apply_rel_rw(brq, card, req);
+
+	/*
+	 * Data tag is used only during writing meta data to speed
+	 * up write and any subsequent read of this meta data
+	 */
+	*do_data_tag = card->ext_csd.data_tag_unit_size &&
+		       (req->cmd_flags & REQ_META) &&
+		       (rq_data_dir(req) == WRITE) &&
+		       ((brq->data.blocks * brq->data.blksz) >=
+			card->ext_csd.data_tag_unit_size);
+
+	mmc_set_data_timeout(&brq->data, card);
+
+	brq->data.sg = mqrq->sg;
+	brq->data.sg_len = mmc_queue_map_sg(mq, mqrq);
+
+	/*
+	 * Adjust the sg list so it is the same size as the
+	 * request.
+	 */
+	if (brq->data.blocks != blk_rq_sectors(req)) {
+		int i, data_size = brq->data.blocks << 9;
+		struct scatterlist *sg;
+
+		for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) {
+			data_size -= sg->length;
+			if (data_size <= 0) {
+				sg->length += data_size;
+				i++;
+				break;
+			}
+		}
+		brq->data.sg_len = i;
+	}
+
+	mqrq->areq.mrq = &brq->mrq;
+
+	mmc_queue_bounce_pre(mqrq);
+}
+
+static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
+			       struct mmc_card *card,
+			       int disable_multi,
+			       struct mmc_queue *mq)
+{
+	u32 readcmd, writecmd;
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct request *req = mqrq->req;
+	struct mmc_blk_data *md = mq->blkdata;
+	bool do_rel_wr, do_data_tag;
+
+	mmc_blk_data_prep(mq, mqrq, disable_multi, &do_rel_wr, &do_data_tag);
+
+	brq->mrq.cmd = &brq->cmd;
+
+	brq->cmd.arg = blk_rq_pos(req);
+	if (!mmc_card_blockaddr(card))
+		brq->cmd.arg <<= 9;
+	brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
+
 	if (brq->data.blocks > 1 || do_rel_wr) {
 		/* SPI multiblock writes terminate using a special
 		 * token, not a STOP_TRANSMISSION request.
@@ -1470,32 +1572,7 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		readcmd = MMC_READ_SINGLE_BLOCK;
 		writecmd = MMC_WRITE_BLOCK;
 	}
-	if (rq_data_dir(req) == READ) {
-		brq->cmd.opcode = readcmd;
-		brq->data.flags = MMC_DATA_READ;
-		if (brq->mrq.stop)
-			brq->stop.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 |
-					MMC_CMD_AC;
-	} else {
-		brq->cmd.opcode = writecmd;
-		brq->data.flags = MMC_DATA_WRITE;
-		if (brq->mrq.stop)
-			brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B |
-					MMC_CMD_AC;
-	}
-
-	if (do_rel_wr)
-		mmc_apply_rel_rw(brq, card, req);
-
-	/*
-	 * Data tag is used only during writing meta data to speed
-	 * up write and any subsequent read of this meta data
-	 */
-	do_data_tag = (card->ext_csd.data_tag_unit_size) &&
-		(req->cmd_flags & REQ_META) &&
-		(rq_data_dir(req) == WRITE) &&
-		((brq->data.blocks * brq->data.blksz) >=
-		 card->ext_csd.data_tag_unit_size);
+	brq->cmd.opcode = rq_data_dir(req) == READ ? readcmd : writecmd;
 
 	/*
 	 * Pre-defined multi-block transfers are preferable to
@@ -1526,45 +1603,15 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		brq->mrq.sbc = &brq->sbc;
 	}
 
-	mmc_set_data_timeout(&brq->data, card);
-
-	brq->data.sg = mqrq->sg;
-	brq->data.sg_len = mmc_queue_map_sg(mq, mqrq);
-
-	/*
-	 * Adjust the sg list so it is the same size as the
-	 * request.
-	 */
-	if (brq->data.blocks != blk_rq_sectors(req)) {
-		int i, data_size = brq->data.blocks << 9;
-		struct scatterlist *sg;
-
-		for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) {
-			data_size -= sg->length;
-			if (data_size <= 0) {
-				sg->length += data_size;
-				i++;
-				break;
-			}
-		}
-		brq->data.sg_len = i;
-	}
-
-	mqrq->areq.mrq = &brq->mrq;
 	mqrq->areq.err_check = mmc_blk_err_check;
-
-	mmc_queue_bounce_pre(mqrq);
 }
 
 static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
 			       struct mmc_blk_request *brq, struct request *req,
 			       bool old_req_pending)
 {
-	struct mmc_queue_req *mq_rq;
 	bool req_pending;
 
-	mq_rq = container_of(brq, struct mmc_queue_req, brq);
-
 	/*
 	 * If this is an SD card and we're writing, we can first
 	 * mark the known good sectors as ok.
@@ -1588,11 +1635,14 @@ static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
 	return req_pending;
 }
 
-static void mmc_blk_rw_cmd_abort(struct mmc_card *card, struct request *req)
+static void mmc_blk_rw_cmd_abort(struct mmc_queue *mq, struct mmc_card *card,
+				 struct request *req,
+				 struct mmc_queue_req *mqrq)
 {
 	if (mmc_card_removed(card))
 		req->rq_flags |= RQF_QUIET;
 	while (blk_end_request(req, -EIO, blk_rq_cur_bytes(req)));
+	mmc_queue_req_free(mq, mqrq);
 }
 
 /**
@@ -1600,7 +1650,8 @@ static void mmc_blk_rw_cmd_abort(struct mmc_card *card, struct request *req)
  * @mq: the queue with the card and host to restart
  * @req: a new request that want to be started after the current one
  */
-static void mmc_blk_rw_try_restart(struct mmc_queue *mq, struct request *req)
+static void mmc_blk_rw_try_restart(struct mmc_queue *mq, struct request *req,
+				   struct mmc_queue_req *mqrq)
 {
 	if (!req)
 		return;
@@ -1611,11 +1662,12 @@ static void mmc_blk_rw_try_restart(struct mmc_queue *mq, struct request *req)
 	if (mmc_card_removed(mq->card)) {
 		req->rq_flags |= RQF_QUIET;
 		blk_end_request_all(req, -EIO);
+		mmc_queue_req_free(mq, mqrq);
 		return;
 	}
 	/* Else proceed and try to restart the current async request */
-	mmc_blk_rw_rq_prep(mq->mqrq_cur, mq->card, 0, mq);
-	mmc_start_areq(mq->card->host, &mq->mqrq_cur->areq, NULL);
+	mmc_blk_rw_rq_prep(mqrq, mq->card, 0, mq);
+	mmc_start_areq(mq->card->host, &mqrq->areq, NULL);
 }
 
 static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
@@ -1625,13 +1677,23 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 	struct mmc_blk_request *brq;
 	int disable_multi = 0, retry = 0, type, retune_retry_done = 0;
 	enum mmc_blk_status status;
+	struct mmc_queue_req *mqrq_cur = NULL;
 	struct mmc_queue_req *mq_rq;
 	struct request *old_req;
 	struct mmc_async_req *new_areq;
 	struct mmc_async_req *old_areq;
 	bool req_pending = true;
 
-	if (!new_req && !mq->mqrq_prev->req)
+	if (new_req) {
+		mqrq_cur = mmc_queue_req_find(mq, new_req);
+		if (!mqrq_cur) {
+			WARN_ON(1);
+			mmc_blk_requeue(mq->queue, new_req);
+			new_req = NULL;
+		}
+	}
+
+	if (!mq->qcnt)
 		return;
 
 	do {
@@ -1644,12 +1706,12 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 				!IS_ALIGNED(blk_rq_sectors(new_req), 8)) {
 				pr_err("%s: Transfer size is not 4KB sector size aligned\n",
 					new_req->rq_disk->disk_name);
-				mmc_blk_rw_cmd_abort(card, new_req);
+				mmc_blk_rw_cmd_abort(mq, card, new_req, mqrq_cur);
 				return;
 			}
 
-			mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
-			new_areq = &mq->mqrq_cur->areq;
+			mmc_blk_rw_rq_prep(mqrq_cur, card, 0, mq);
+			new_areq = &mqrq_cur->areq;
 		} else
 			new_areq = NULL;
 
@@ -1660,8 +1722,6 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 			 * and there is nothing more to do until it is
 			 * complete.
 			 */
-			if (status == MMC_BLK_NEW_REQUEST)
-				mq->new_request = true;
 			return;
 		}
 
@@ -1694,19 +1754,23 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 				pr_err("%s BUG rq_tot %d d_xfer %d\n",
 				       __func__, blk_rq_bytes(old_req),
 				       brq->data.bytes_xfered);
-				mmc_blk_rw_cmd_abort(card, old_req);
+				mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
 				return;
 			}
 			break;
 		case MMC_BLK_CMD_ERR:
 			req_pending = mmc_blk_rw_cmd_err(md, card, brq, old_req, req_pending);
 			if (mmc_blk_reset(md, card->host, type)) {
-				mmc_blk_rw_cmd_abort(card, old_req);
-				mmc_blk_rw_try_restart(mq, new_req);
+				if (req_pending)
+					mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
+				else
+					mmc_queue_req_free(mq, mq_rq);
+				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 				return;
 			}
 			if (!req_pending) {
-				mmc_blk_rw_try_restart(mq, new_req);
+				mmc_queue_req_free(mq, mq_rq);
+				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 				return;
 			}
 			break;
@@ -1718,8 +1782,8 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 		case MMC_BLK_ABORT:
 			if (!mmc_blk_reset(md, card->host, type))
 				break;
-			mmc_blk_rw_cmd_abort(card, old_req);
-			mmc_blk_rw_try_restart(mq, new_req);
+			mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
+			mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 			return;
 		case MMC_BLK_DATA_ERR: {
 			int err;
@@ -1728,8 +1792,8 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 			if (!err)
 				break;
 			if (err == -ENODEV) {
-				mmc_blk_rw_cmd_abort(card, old_req);
-				mmc_blk_rw_try_restart(mq, new_req);
+				mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
+				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 				return;
 			}
 			/* Fall through */
@@ -1750,19 +1814,20 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 			req_pending = blk_end_request(old_req, -EIO,
 						      brq->data.blksz);
 			if (!req_pending) {
-				mmc_blk_rw_try_restart(mq, new_req);
+				mmc_queue_req_free(mq, mq_rq);
+				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 				return;
 			}
 			break;
 		case MMC_BLK_NOMEDIUM:
-			mmc_blk_rw_cmd_abort(card, old_req);
-			mmc_blk_rw_try_restart(mq, new_req);
+			mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
+			mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 			return;
 		default:
 			pr_err("%s: Unhandled return value (%d)",
 					old_req->rq_disk->disk_name, status);
-			mmc_blk_rw_cmd_abort(card, old_req);
-			mmc_blk_rw_try_restart(mq, new_req);
+			mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
+			mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
 			return;
 		}
 
@@ -1778,6 +1843,8 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 			mq_rq->brq.retune_retry_done = retune_retry_done;
 		}
 	} while (req_pending);
+
+	mmc_queue_req_free(mq, mq_rq);
 }
 
 void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
@@ -1785,9 +1852,8 @@ void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	int ret;
 	struct mmc_blk_data *md = mq->blkdata;
 	struct mmc_card *card = md->queue.card;
-	bool req_is_special = mmc_req_is_special(req);
 
-	if (req && !mq->mqrq_prev->req)
+	if (req && !mq->qcnt)
 		/* claim host only for the first request */
 		mmc_get_card(card);
 
@@ -1799,34 +1865,28 @@ void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		goto out;
 	}
 
-	mq->new_request = false;
 	if (req && req_op(req) == REQ_OP_DISCARD) {
 		/* complete ongoing async transfer before issuing discard */
-		if (card->host->areq)
+		if (mq->qcnt)
 			mmc_blk_issue_rw_rq(mq, NULL);
 		mmc_blk_issue_discard_rq(mq, req);
 	} else if (req && req_op(req) == REQ_OP_SECURE_ERASE) {
 		/* complete ongoing async transfer before issuing secure erase*/
-		if (card->host->areq)
+		if (mq->qcnt)
 			mmc_blk_issue_rw_rq(mq, NULL);
 		mmc_blk_issue_secdiscard_rq(mq, req);
 	} else if (req && req_op(req) == REQ_OP_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
-		if (card->host->areq)
+		if (mq->qcnt)
 			mmc_blk_issue_rw_rq(mq, NULL);
 		mmc_blk_issue_flush(mq, req);
 	} else {
 		mmc_blk_issue_rw_rq(mq, req);
+		card->host->context_info.is_waiting_last_req = false;
 	}
 
 out:
-	if ((!req && !mq->new_request) || req_is_special)
-		/*
-		 * Release host when there are no more requests
-		 * and after special request(discard, flush) is done.
-		 * In case sepecial request, there is no reentry to
-		 * the 'mmc_blk_issue_rq' with 'mqrq_prev->req'.
-		 */
+	if (!mq->qcnt)
 		mmc_put_card(card);
 }
 
@@ -2106,6 +2166,7 @@ static int mmc_blk_probe(struct mmc_card *card)
 {
 	struct mmc_blk_data *md, *part_md;
 	char cap_str[10];
+	int ret;
 
 	/*
 	 * Check that the card supports the command class(es) we need.
@@ -2115,9 +2176,15 @@ static int mmc_blk_probe(struct mmc_card *card)
 
 	mmc_fixup_device(card, mmc_blk_fixups);
 
+	ret = mmc_queue_alloc_shared_queue(card);
+	if (ret)
+		return ret;
+
 	md = mmc_blk_alloc(card);
-	if (IS_ERR(md))
+	if (IS_ERR(md)) {
+		mmc_queue_free_shared_queue(card);
 		return PTR_ERR(md);
+	}
 
 	string_get_size((u64)get_capacity(md->disk), 512, STRING_UNITS_2,
 			cap_str, sizeof(cap_str));
@@ -2155,6 +2222,7 @@ static int mmc_blk_probe(struct mmc_card *card)
  out:
 	mmc_blk_remove_parts(card, md);
 	mmc_blk_remove_req(md);
+	mmc_queue_free_shared_queue(card);
 	return 0;
 }
 
@@ -2172,6 +2240,7 @@ static void mmc_blk_remove(struct mmc_card *card)
 	pm_runtime_put_noidle(&card->dev);
 	mmc_blk_remove_req(md);
 	dev_set_drvdata(&card->dev, NULL);
+	mmc_queue_free_shared_queue(card);
 }
 
 static int _mmc_blk_suspend(struct mmc_card *card)
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 926e0fde07d7..82c45ddfa202 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -172,14 +172,16 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 
 	trace_mmc_request_done(host, mrq);
 
-	if (err && cmd->retries && !mmc_card_removed(host->card)) {
-		/*
-		 * Request starter must handle retries - see
-		 * mmc_wait_for_req_done().
-		 */
-		if (mrq->done)
-			mrq->done(mrq);
-	} else {
+	/*
+	 * We list various conditions for the command to be considered
+	 * properly done:
+	 *
+	 * - There was no error, OK fine then
+	 * - We are not doing some kind of retry
+	 * - The card was removed (...so just complete everything no matter
+	 *   if there are errors or retries)
+	 */
+	if (!err || !cmd->retries || mmc_card_removed(host->card)) {
 		mmc_should_fail_request(host, mrq);
 
 		if (!host->ongoing_mrq)
@@ -211,10 +213,13 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 				mrq->stop->resp[0], mrq->stop->resp[1],
 				mrq->stop->resp[2], mrq->stop->resp[3]);
 		}
-
-		if (mrq->done)
-			mrq->done(mrq);
 	}
+	/*
+	 * Request starter must handle retries - see
+	 * mmc_wait_for_req_done().
+	 */
+	if (mrq->done)
+		mrq->done(mrq);
 }
 
 EXPORT_SYMBOL(mmc_request_done);
@@ -234,8 +239,10 @@ static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 	/*
 	 * For sdio rw commands we must wait for card busy otherwise some
 	 * sdio devices won't work properly.
+	 * And bypass I/O abort, reset and bus suspend operations.
 	 */
-	if (mmc_is_io_op(mrq->cmd->opcode) && host->ops->card_busy) {
+	if (sdio_is_io_busy(mrq->cmd->opcode, mrq->cmd->arg) &&
+	    host->ops->card_busy) {
 		int tries = 500; /* Wait aprox 500ms at maximum */
 
 		while (host->ops->card_busy(host) && --tries)
@@ -262,26 +269,19 @@ static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 	host->ops->request(host, mrq);
 }
 
-static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
+static void mmc_mrq_pr_debug(struct mmc_host *host, struct mmc_request *mrq)
 {
-#ifdef CONFIG_MMC_DEBUG
-	unsigned int i, sz;
-	struct scatterlist *sg;
-#endif
-	mmc_retune_hold(host);
-
-	if (mmc_card_removed(host->card))
-		return -ENOMEDIUM;
-
 	if (mrq->sbc) {
 		pr_debug("<%s: starting CMD%u arg %08x flags %08x>\n",
 			 mmc_hostname(host), mrq->sbc->opcode,
 			 mrq->sbc->arg, mrq->sbc->flags);
 	}
 
-	pr_debug("%s: starting CMD%u arg %08x flags %08x\n",
-		 mmc_hostname(host), mrq->cmd->opcode,
-		 mrq->cmd->arg, mrq->cmd->flags);
+	if (mrq->cmd) {
+		pr_debug("%s: starting CMD%u arg %08x flags %08x\n",
+			 mmc_hostname(host), mrq->cmd->opcode, mrq->cmd->arg,
+			 mrq->cmd->flags);
+	}
 
 	if (mrq->data) {
 		pr_debug("%s:     blksz %d blocks %d flags %08x "
@@ -297,11 +297,20 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 			 mmc_hostname(host), mrq->stop->opcode,
 			 mrq->stop->arg, mrq->stop->flags);
 	}
+}
 
-	WARN_ON(!host->claimed);
+static int mmc_mrq_prep(struct mmc_host *host, struct mmc_request *mrq)
+{
+#ifdef CONFIG_MMC_DEBUG
+	unsigned int i, sz;
+	struct scatterlist *sg;
+#endif
 
-	mrq->cmd->error = 0;
-	mrq->cmd->mrq = mrq;
+	if (mrq->cmd) {
+		mrq->cmd->error = 0;
+		mrq->cmd->mrq = mrq;
+		mrq->cmd->data = mrq->data;
+	}
 	if (mrq->sbc) {
 		mrq->sbc->error = 0;
 		mrq->sbc->mrq = mrq;
@@ -318,8 +327,6 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 		if (sz != mrq->data->blocks * mrq->data->blksz)
 			return -EINVAL;
 #endif
-
-		mrq->cmd->data = mrq->data;
 		mrq->data->error = 0;
 		mrq->data->mrq = mrq;
 		if (mrq->stop) {
@@ -328,6 +335,27 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 			mrq->stop->mrq = mrq;
 		}
 	}
+
+	return 0;
+}
+
+static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
+{
+	int err;
+
+	mmc_retune_hold(host);
+
+	if (mmc_card_removed(host->card))
+		return -ENOMEDIUM;
+
+	mmc_mrq_pr_debug(host, mrq);
+
+	WARN_ON(!host->claimed);
+
+	err = mmc_mrq_prep(host, mrq);
+	if (err)
+		return err;
+
 	led_trigger_event(host->led, LED_FULL);
 	__mmc_start_request(host, mrq);
 
@@ -485,56 +513,6 @@ static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
 	return err;
 }
 
-/*
- * mmc_wait_for_data_req_done() - wait for request completed
- * @host: MMC host to prepare the command.
- * @mrq: MMC request to wait for
- *
- * Blocks MMC context till host controller will ack end of data request
- * execution or new request notification arrives from the block layer.
- * Handles command retries.
- *
- * Returns enum mmc_blk_status after checking errors.
- */
-static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host,
-						      struct mmc_request *mrq)
-{
-	struct mmc_command *cmd;
-	struct mmc_context_info *context_info = &host->context_info;
-	enum mmc_blk_status status;
-
-	while (1) {
-		wait_event_interruptible(context_info->wait,
-				(context_info->is_done_rcv ||
-				 context_info->is_new_req));
-
-		if (context_info->is_done_rcv) {
-			context_info->is_done_rcv = false;
-			cmd = mrq->cmd;
-
-			if (!cmd->error || !cmd->retries ||
-			    mmc_card_removed(host->card)) {
-				status = host->areq->err_check(host->card,
-							       host->areq);
-				break; /* return status */
-			} else {
-				mmc_retune_recheck(host);
-				pr_info("%s: req failed (CMD%u): %d, retrying...\n",
-					mmc_hostname(host),
-					cmd->opcode, cmd->error);
-				cmd->retries--;
-				cmd->error = 0;
-				__mmc_start_request(host, mrq);
-				continue; /* wait for done/new event again */
-			}
-		}
-
-		return MMC_BLK_NEW_REQUEST;
-	}
-	mmc_retune_release(host);
-	return status;
-}
-
 void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
 {
 	struct mmc_command *cmd;
@@ -639,14 +617,44 @@ static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
  */
 static enum mmc_blk_status mmc_finalize_areq(struct mmc_host *host)
 {
+	struct mmc_context_info *context_info = &host->context_info;
 	enum mmc_blk_status status;
 
 	if (!host->areq)
 		return MMC_BLK_SUCCESS;
 
-	status = mmc_wait_for_data_req_done(host, host->areq->mrq);
-	if (status == MMC_BLK_NEW_REQUEST)
-		return status;
+	while (1) {
+		wait_event_interruptible(context_info->wait,
+				(context_info->is_done_rcv ||
+				 context_info->is_new_req));
+
+		if (context_info->is_done_rcv) {
+			struct mmc_command *cmd;
+
+			context_info->is_done_rcv = false;
+			cmd = host->areq->mrq->cmd;
+
+			if (!cmd->error || !cmd->retries ||
+			    mmc_card_removed(host->card)) {
+				status = host->areq->err_check(host->card,
+							       host->areq);
+				break; /* return status */
+			} else {
+				mmc_retune_recheck(host);
+				pr_info("%s: req failed (CMD%u): %d, retrying...\n",
+					mmc_hostname(host),
+					cmd->opcode, cmd->error);
+				cmd->retries--;
+				cmd->error = 0;
+				__mmc_start_request(host, host->areq->mrq);
+				continue; /* wait for done/new event again */
+			}
+		}
+
+		return MMC_BLK_NEW_REQUEST;
+	}
+
+	mmc_retune_release(host);
 
 	/*
 	 * Check BKOPS urgency for each R1 response
@@ -683,7 +691,7 @@ struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
 {
 	enum mmc_blk_status status;
 	int start_err = 0;
-	struct mmc_async_req *data = host->areq;
+	struct mmc_async_req *previous = host->areq;
 
 	/* Prepare a new request */
 	if (areq)
@@ -691,13 +699,12 @@ struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
 
 	/* Finalize previous request */
 	status = mmc_finalize_areq(host);
+	if (ret_stat)
+		*ret_stat = status;
 
 	/* The previous request is still going on... */
-	if (status == MMC_BLK_NEW_REQUEST) {
-		if (ret_stat)
-			*ret_stat = status;
+	if (status == MMC_BLK_NEW_REQUEST)
 		return NULL;
-	}
 
 	/* Fine so far, start the new request! */
 	if (status == MMC_BLK_SUCCESS && areq)
@@ -716,9 +723,7 @@ struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
 	else
 		host->areq = areq;
 
-	if (ret_stat)
-		*ret_stat = status;
-	return data;
+	return previous;
 }
 EXPORT_SYMBOL(mmc_start_areq);
 
@@ -2555,6 +2560,12 @@ unsigned int mmc_calc_max_discard(struct mmc_card *card)
 }
 EXPORT_SYMBOL(mmc_calc_max_discard);
 
+bool mmc_card_is_blockaddr(struct mmc_card *card)
+{
+	return card ? mmc_card_blockaddr(card) : false;
+}
+EXPORT_SYMBOL(mmc_card_is_blockaddr);
+
 int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen)
 {
 	struct mmc_command cmd = {};
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 7fd722868875..2c87dede5841 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -790,6 +790,7 @@ MMC_DEV_ATTR(enhanced_area_size, "%u\n", card->ext_csd.enhanced_area_size);
 MMC_DEV_ATTR(raw_rpmb_size_mult, "%#x\n", card->ext_csd.raw_rpmb_size_mult);
 MMC_DEV_ATTR(rel_sectors, "%#x\n", card->ext_csd.rel_sectors);
 MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
+MMC_DEV_ATTR(cmdq_en, "%d\n", card->ext_csd.cmdq_en);
 
 static ssize_t mmc_fwrev_show(struct device *dev,
 			      struct device_attribute *attr,
@@ -845,6 +846,7 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_rel_sectors.attr,
 	&dev_attr_ocr.attr,
 	&dev_attr_dsr.attr,
+	&dev_attr_cmdq_en.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(mmc_std);
@@ -1730,7 +1732,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		err = mmc_select_hs400(card);
 		if (err)
 			goto free_card;
-	} else {
+	} else if (!mmc_card_hs400es(card)) {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
 		if (err > 0 && mmc_card_hs(card)) {
@@ -1788,6 +1790,13 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	}
 
 	/*
+	 * In some cases (e.g. RPMB or mmc_test), the Command Queue must be
+	 * disabled for a time, so a flag is needed to indicate to re-enable the
+	 * Command Queue.
+	 */
+	card->reenable_cmdq = card->ext_csd.cmdq_en;
+
+	/*
 	 * The mandatory minimum values are defined for packed command.
 	 * read: 5, write: 3
 	 */
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index fe80f26d6971..78f75f00efc5 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -305,7 +305,7 @@ mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host,
 int mmc_send_csd(struct mmc_card *card, u32 *csd)
 {
 	int ret, i;
-	u32 *csd_tmp;
+	__be32 *csd_tmp;
 
 	if (!mmc_host_is_spi(card->host))
 		return mmc_send_cxd_native(card->host, card->rca << 16,
@@ -319,7 +319,7 @@ int mmc_send_csd(struct mmc_card *card, u32 *csd)
 	if (ret)
 		goto err;
 
-	for (i = 0;i < 4;i++)
+	for (i = 0; i < 4; i++)
 		csd[i] = be32_to_cpu(csd_tmp[i]);
 
 err:
@@ -330,7 +330,7 @@ err:
 int mmc_send_cid(struct mmc_host *host, u32 *cid)
 {
 	int ret, i;
-	u32 *cid_tmp;
+	__be32 *cid_tmp;
 
 	if (!mmc_host_is_spi(host)) {
 		if (!host->card)
@@ -347,7 +347,7 @@ int mmc_send_cid(struct mmc_host *host, u32 *cid)
 	if (ret)
 		goto err;
 
-	for (i = 0;i < 4;i++)
+	for (i = 0; i < 4; i++)
 		cid[i] = be32_to_cpu(cid_tmp[i]);
 
 err:
@@ -838,3 +838,31 @@ int mmc_can_ext_csd(struct mmc_card *card)
 {
 	return (card && card->csd.mmca_vsn > CSD_SPEC_VER_3);
 }
+
+static int mmc_cmdq_switch(struct mmc_card *card, bool enable)
+{
+	u8 val = enable ? EXT_CSD_CMDQ_MODE_ENABLED : 0;
+	int err;
+
+	if (!card->ext_csd.cmdq_support)
+		return -EOPNOTSUPP;
+
+	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_CMDQ_MODE_EN,
+			 val, card->ext_csd.generic_cmd6_time);
+	if (!err)
+		card->ext_csd.cmdq_en = enable;
+
+	return err;
+}
+
+int mmc_cmdq_enable(struct mmc_card *card)
+{
+	return mmc_cmdq_switch(card, true);
+}
+EXPORT_SYMBOL_GPL(mmc_cmdq_enable);
+
+int mmc_cmdq_disable(struct mmc_card *card)
+{
+	return mmc_cmdq_switch(card, false);
+}
+EXPORT_SYMBOL_GPL(mmc_cmdq_disable);
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index 74beea8a9c7e..978bd2e60f8a 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -46,6 +46,8 @@ int mmc_read_bkops_status(struct mmc_card *card);
 void mmc_start_bkops(struct mmc_card *card, bool from_exception);
 int mmc_can_reset(struct mmc_card *card);
 int mmc_flush_cache(struct mmc_card *card);
+int mmc_cmdq_enable(struct mmc_card *card);
+int mmc_cmdq_disable(struct mmc_card *card);
 
 #endif
 
diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c
index f99ac3123fd2..fd1b4b8510b9 100644
--- a/drivers/mmc/core/mmc_test.c
+++ b/drivers/mmc/core/mmc_test.c
@@ -26,6 +26,7 @@
 #include "card.h"
 #include "host.h"
 #include "bus.h"
+#include "mmc_ops.h"
 
 #define RESULT_OK		0
 #define RESULT_FAIL		1
@@ -3264,6 +3265,14 @@ static int mmc_test_probe(struct mmc_card *card)
 	if (ret)
 		return ret;
 
+	if (card->ext_csd.cmdq_en) {
+		mmc_claim_host(card->host);
+		ret = mmc_cmdq_disable(card);
+		mmc_release_host(card->host);
+		if (ret)
+			return ret;
+	}
+
 	dev_info(&card->dev, "Card claimed for testing.\n");
 
 	return 0;
@@ -3271,6 +3280,11 @@ static int mmc_test_probe(struct mmc_card *card)
 
 static void mmc_test_remove(struct mmc_card *card)
 {
+	if (card->reenable_cmdq) {
+		mmc_claim_host(card->host);
+		mmc_cmdq_enable(card);
+		mmc_release_host(card->host);
+	}
 	mmc_test_free_result(card);
 	mmc_test_free_dbgfs_file(card);
 }
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 493eb10ce580..5c37b6be3e7b 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -40,6 +40,35 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 	return BLKPREP_OK;
 }
 
+struct mmc_queue_req *mmc_queue_req_find(struct mmc_queue *mq,
+					 struct request *req)
+{
+	struct mmc_queue_req *mqrq;
+	int i = ffz(mq->qslots);
+
+	if (i >= mq->qdepth)
+		return NULL;
+
+	mqrq = &mq->mqrq[i];
+	WARN_ON(mqrq->req || mq->qcnt >= mq->qdepth ||
+		test_bit(mqrq->task_id, &mq->qslots));
+	mqrq->req = req;
+	mq->qcnt += 1;
+	__set_bit(mqrq->task_id, &mq->qslots);
+
+	return mqrq;
+}
+
+void mmc_queue_req_free(struct mmc_queue *mq,
+			struct mmc_queue_req *mqrq)
+{
+	WARN_ON(!mqrq->req || mq->qcnt < 1 ||
+		!test_bit(mqrq->task_id, &mq->qslots));
+	mqrq->req = NULL;
+	mq->qcnt -= 1;
+	__clear_bit(mqrq->task_id, &mq->qslots);
+}
+
 static int mmc_queue_thread(void *d)
 {
 	struct mmc_queue *mq = d;
@@ -50,7 +79,7 @@ static int mmc_queue_thread(void *d)
 
 	down(&mq->thread_sem);
 	do {
-		struct request *req = NULL;
+		struct request *req;
 
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -63,38 +92,17 @@ static int mmc_queue_thread(void *d)
 			 * Dispatch queue is empty so set flags for
 			 * mmc_request_fn() to wake us up.
 			 */
-			if (mq->mqrq_prev->req)
+			if (mq->qcnt)
 				cntx->is_waiting_last_req = true;
 			else
 				mq->asleep = true;
 		}
-		mq->mqrq_cur->req = req;
 		spin_unlock_irq(q->queue_lock);
 
-		if (req || mq->mqrq_prev->req) {
-			bool req_is_special = mmc_req_is_special(req);
-
+		if (req || mq->qcnt) {
 			set_current_state(TASK_RUNNING);
 			mmc_blk_issue_rq(mq, req);
 			cond_resched();
-			if (mq->new_request) {
-				mq->new_request = false;
-				continue; /* fetch again */
-			}
-
-			/*
-			 * Current request becomes previous request
-			 * and vice versa.
-			 * In case of special requests, current request
-			 * has been finished. Do not assign it to previous
-			 * request.
-			 */
-			if (req_is_special)
-				mq->mqrq_cur->req = NULL;
-
-			mq->mqrq_prev->brq.mrq.data = NULL;
-			mq->mqrq_prev->req = NULL;
-			swap(mq->mqrq_prev, mq->mqrq_cur);
 		} else {
 			if (kthread_should_stop()) {
 				set_current_state(TASK_RUNNING);
@@ -141,17 +149,13 @@ static void mmc_request_fn(struct request_queue *q)
 		wake_up_process(mq->thread);
 }
 
-static struct scatterlist *mmc_alloc_sg(int sg_len, int *err)
+static struct scatterlist *mmc_alloc_sg(int sg_len)
 {
 	struct scatterlist *sg;
 
 	sg = kmalloc_array(sg_len, sizeof(*sg), GFP_KERNEL);
-	if (!sg)
-		*err = -ENOMEM;
-	else {
-		*err = 0;
+	if (sg)
 		sg_init_table(sg, sg_len);
-	}
 
 	return sg;
 }
@@ -167,8 +171,6 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	blk_queue_max_discard_sectors(q, max_discard);
-	if (card->erased_byte == 0 && !mmc_can_discard(card))
-		q->limits.discard_zeroes_data = 1;
 	q->limits.discard_granularity = card->pref_erase << 9;
 	/* granularity must not be greater than max. discard */
 	if (card->pref_erase > max_discard)
@@ -177,80 +179,178 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 		queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
 }
 
-#ifdef CONFIG_MMC_BLOCK_BOUNCE
-static bool mmc_queue_alloc_bounce_bufs(struct mmc_queue *mq,
-					unsigned int bouncesz)
+static void mmc_queue_req_free_bufs(struct mmc_queue_req *mqrq)
+{
+	kfree(mqrq->bounce_sg);
+	mqrq->bounce_sg = NULL;
+
+	kfree(mqrq->sg);
+	mqrq->sg = NULL;
+
+	kfree(mqrq->bounce_buf);
+	mqrq->bounce_buf = NULL;
+}
+
+static void mmc_queue_reqs_free_bufs(struct mmc_queue_req *mqrq, int qdepth)
 {
 	int i;
 
-	for (i = 0; i < mq->qdepth; i++) {
-		mq->mqrq[i].bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
-		if (!mq->mqrq[i].bounce_buf)
-			goto out_err;
-	}
+	for (i = 0; i < qdepth; i++)
+		mmc_queue_req_free_bufs(&mqrq[i]);
+}
 
-	return true;
+static void mmc_queue_free_mqrqs(struct mmc_queue_req *mqrq, int qdepth)
+{
+	mmc_queue_reqs_free_bufs(mqrq, qdepth);
+	kfree(mqrq);
+}
 
-out_err:
-	while (--i >= 0) {
-		kfree(mq->mqrq[i].bounce_buf);
-		mq->mqrq[i].bounce_buf = NULL;
+static struct mmc_queue_req *mmc_queue_alloc_mqrqs(int qdepth)
+{
+	struct mmc_queue_req *mqrq;
+	int i;
+
+	mqrq = kcalloc(qdepth, sizeof(*mqrq), GFP_KERNEL);
+	if (mqrq) {
+		for (i = 0; i < qdepth; i++)
+			mqrq[i].task_id = i;
 	}
-	pr_warn("%s: unable to allocate bounce buffers\n",
-		mmc_card_name(mq->card));
-	return false;
+
+	return mqrq;
 }
 
-static int mmc_queue_alloc_bounce_sgs(struct mmc_queue *mq,
-				      unsigned int bouncesz)
+#ifdef CONFIG_MMC_BLOCK_BOUNCE
+static int mmc_queue_alloc_bounce_bufs(struct mmc_queue_req *mqrq, int qdepth,
+				       unsigned int bouncesz)
 {
-	int i, ret;
+	int i;
 
-	for (i = 0; i < mq->qdepth; i++) {
-		mq->mqrq[i].sg = mmc_alloc_sg(1, &ret);
-		if (ret)
-			return ret;
+	for (i = 0; i < qdepth; i++) {
+		mqrq[i].bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
+		if (!mqrq[i].bounce_buf)
+			return -ENOMEM;
 
-		mq->mqrq[i].bounce_sg = mmc_alloc_sg(bouncesz / 512, &ret);
-		if (ret)
-			return ret;
+		mqrq[i].sg = mmc_alloc_sg(1);
+		if (!mqrq[i].sg)
+			return -ENOMEM;
+
+		mqrq[i].bounce_sg = mmc_alloc_sg(bouncesz / 512);
+		if (!mqrq[i].bounce_sg)
+			return -ENOMEM;
 	}
 
 	return 0;
 }
+
+static bool mmc_queue_alloc_bounce(struct mmc_queue_req *mqrq, int qdepth,
+				   unsigned int bouncesz)
+{
+	int ret;
+
+	ret = mmc_queue_alloc_bounce_bufs(mqrq, qdepth, bouncesz);
+	if (ret)
+		mmc_queue_reqs_free_bufs(mqrq, qdepth);
+
+	return !ret;
+}
+
+static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host)
+{
+	unsigned int bouncesz = MMC_QUEUE_BOUNCESZ;
+
+	if (host->max_segs != 1)
+		return 0;
+
+	if (bouncesz > host->max_req_size)
+		bouncesz = host->max_req_size;
+	if (bouncesz > host->max_seg_size)
+		bouncesz = host->max_seg_size;
+	if (bouncesz > host->max_blk_count * 512)
+		bouncesz = host->max_blk_count * 512;
+
+	if (bouncesz <= 512)
+		return 0;
+
+	return bouncesz;
+}
+#else
+static inline bool mmc_queue_alloc_bounce(struct mmc_queue_req *mqrq,
+					  int qdepth, unsigned int bouncesz)
+{
+	return false;
+}
+
+static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host)
+{
+	return 0;
+}
 #endif
 
-static int mmc_queue_alloc_sgs(struct mmc_queue *mq, int max_segs)
+static int mmc_queue_alloc_sgs(struct mmc_queue_req *mqrq, int qdepth,
+			       int max_segs)
 {
-	int i, ret;
+	int i;
 
-	for (i = 0; i < mq->qdepth; i++) {
-		mq->mqrq[i].sg = mmc_alloc_sg(max_segs, &ret);
-		if (ret)
-			return ret;
+	for (i = 0; i < qdepth; i++) {
+		mqrq[i].sg = mmc_alloc_sg(max_segs);
+		if (!mqrq[i].sg)
+			return -ENOMEM;
 	}
 
 	return 0;
 }
 
-static void mmc_queue_req_free_bufs(struct mmc_queue_req *mqrq)
+void mmc_queue_free_shared_queue(struct mmc_card *card)
 {
-	kfree(mqrq->bounce_sg);
-	mqrq->bounce_sg = NULL;
+	if (card->mqrq) {
+		mmc_queue_free_mqrqs(card->mqrq, card->qdepth);
+		card->mqrq = NULL;
+	}
+}
 
-	kfree(mqrq->sg);
-	mqrq->sg = NULL;
+static int __mmc_queue_alloc_shared_queue(struct mmc_card *card, int qdepth)
+{
+	struct mmc_host *host = card->host;
+	struct mmc_queue_req *mqrq;
+	unsigned int bouncesz;
+	int ret = 0;
 
-	kfree(mqrq->bounce_buf);
-	mqrq->bounce_buf = NULL;
+	if (card->mqrq)
+		return -EINVAL;
+
+	mqrq = mmc_queue_alloc_mqrqs(qdepth);
+	if (!mqrq)
+		return -ENOMEM;
+
+	card->mqrq = mqrq;
+	card->qdepth = qdepth;
+
+	bouncesz = mmc_queue_calc_bouncesz(host);
+
+	if (bouncesz && !mmc_queue_alloc_bounce(mqrq, qdepth, bouncesz)) {
+		bouncesz = 0;
+		pr_warn("%s: unable to allocate bounce buffers\n",
+			mmc_card_name(card));
+	}
+
+	card->bouncesz = bouncesz;
+
+	if (!bouncesz) {
+		ret = mmc_queue_alloc_sgs(mqrq, qdepth, host->max_segs);
+		if (ret)
+			goto out_err;
+	}
+
+	return ret;
+
+out_err:
+	mmc_queue_free_shared_queue(card);
+	return ret;
 }
 
-static void mmc_queue_reqs_free_bufs(struct mmc_queue *mq)
+int mmc_queue_alloc_shared_queue(struct mmc_card *card)
 {
-	int i;
-
-	for (i = 0; i < mq->qdepth; i++)
-		mmc_queue_req_free_bufs(&mq->mqrq[i]);
+	return __mmc_queue_alloc_shared_queue(card, 2);
 }
 
 /**
@@ -267,7 +367,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 {
 	struct mmc_host *host = card->host;
 	u64 limit = BLK_BOUNCE_HIGH;
-	bool bounce = false;
 	int ret = -ENOMEM;
 
 	if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
@@ -278,13 +377,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	if (!mq->queue)
 		return -ENOMEM;
 
-	mq->qdepth = 2;
-	mq->mqrq = kcalloc(mq->qdepth, sizeof(struct mmc_queue_req),
-			   GFP_KERNEL);
-	if (!mq->mqrq)
-		goto blk_cleanup;
-	mq->mqrq_cur = &mq->mqrq[0];
-	mq->mqrq_prev = &mq->mqrq[1];
+	mq->mqrq = card->mqrq;
+	mq->qdepth = card->qdepth;
 	mq->queue->queuedata = mq;
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
@@ -293,44 +387,17 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	if (mmc_can_erase(card))
 		mmc_queue_setup_discard(mq->queue, card);
 
-#ifdef CONFIG_MMC_BLOCK_BOUNCE
-	if (host->max_segs == 1) {
-		unsigned int bouncesz;
-
-		bouncesz = MMC_QUEUE_BOUNCESZ;
-
-		if (bouncesz > host->max_req_size)
-			bouncesz = host->max_req_size;
-		if (bouncesz > host->max_seg_size)
-			bouncesz = host->max_seg_size;
-		if (bouncesz > (host->max_blk_count * 512))
-			bouncesz = host->max_blk_count * 512;
-
-		if (bouncesz > 512 &&
-		    mmc_queue_alloc_bounce_bufs(mq, bouncesz)) {
-			blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY);
-			blk_queue_max_hw_sectors(mq->queue, bouncesz / 512);
-			blk_queue_max_segments(mq->queue, bouncesz / 512);
-			blk_queue_max_segment_size(mq->queue, bouncesz);
-
-			ret = mmc_queue_alloc_bounce_sgs(mq, bouncesz);
-			if (ret)
-				goto cleanup_queue;
-			bounce = true;
-		}
-	}
-#endif
-
-	if (!bounce) {
+	if (card->bouncesz) {
+		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY);
+		blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512);
+		blk_queue_max_segments(mq->queue, card->bouncesz / 512);
+		blk_queue_max_segment_size(mq->queue, card->bouncesz);
+	} else {
 		blk_queue_bounce_limit(mq->queue, limit);
 		blk_queue_max_hw_sectors(mq->queue,
 			min(host->max_blk_count, host->max_req_size / 512));
 		blk_queue_max_segments(mq->queue, host->max_segs);
 		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
-
-		ret = mmc_queue_alloc_sgs(mq, host->max_segs);
-		if (ret)
-			goto cleanup_queue;
 	}
 
 	sema_init(&mq->thread_sem, 1);
@@ -345,11 +412,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 
 	return 0;
 
- cleanup_queue:
-	mmc_queue_reqs_free_bufs(mq);
-	kfree(mq->mqrq);
+cleanup_queue:
 	mq->mqrq = NULL;
-blk_cleanup:
 	blk_cleanup_queue(mq->queue);
 	return ret;
 }
@@ -371,10 +435,7 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 	blk_start_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
-	mmc_queue_reqs_free_bufs(mq);
-	kfree(mq->mqrq);
 	mq->mqrq = NULL;
-
 	mq->card = NULL;
 }
 EXPORT_SYMBOL(mmc_cleanup_queue);
diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h
index e298f100101b..871796c3f406 100644
--- a/drivers/mmc/core/queue.h
+++ b/drivers/mmc/core/queue.h
@@ -34,23 +34,25 @@ struct mmc_queue_req {
 	struct scatterlist	*bounce_sg;
 	unsigned int		bounce_sg_len;
 	struct mmc_async_req	areq;
+	int			task_id;
 };
 
 struct mmc_queue {
 	struct mmc_card		*card;
 	struct task_struct	*thread;
 	struct semaphore	thread_sem;
-	bool			new_request;
 	bool			suspended;
 	bool			asleep;
 	struct mmc_blk_data	*blkdata;
 	struct request_queue	*queue;
 	struct mmc_queue_req	*mqrq;
-	struct mmc_queue_req	*mqrq_cur;
-	struct mmc_queue_req	*mqrq_prev;
 	int			qdepth;
+	int			qcnt;
+	unsigned long		qslots;
 };
 
+extern int mmc_queue_alloc_shared_queue(struct mmc_card *card);
+extern void mmc_queue_free_shared_queue(struct mmc_card *card);
 extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
 			  const char *);
 extern void mmc_cleanup_queue(struct mmc_queue *);
@@ -64,4 +66,8 @@ extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 
 extern int mmc_access_rpmb(struct mmc_queue *);
 
+extern struct mmc_queue_req *mmc_queue_req_find(struct mmc_queue *,
+						struct request *);
+extern void mmc_queue_req_free(struct mmc_queue *, struct mmc_queue_req *);
+
 #endif
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 89531b48ae84..d109634fbfce 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -225,7 +225,7 @@ static int mmc_decode_scr(struct mmc_card *card)
 static int mmc_read_ssr(struct mmc_card *card)
 {
 	unsigned int au, es, et, eo;
-	u32 *raw_ssr;
+	__be32 *raw_ssr;
 	int i;
 
 	if (!(card->csd.cmdclass & CCC_APP_SPEC)) {
@@ -853,7 +853,7 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 		/*
 		 * Fetch SCR from card.
 		 */
-		err = mmc_app_send_scr(card, card->raw_scr);
+		err = mmc_app_send_scr(card);
 		if (err)
 			return err;
 
diff --git a/drivers/mmc/core/sd_ops.c b/drivers/mmc/core/sd_ops.c
index 9d5824a37586..47056d8d1bac 100644
--- a/drivers/mmc/core/sd_ops.c
+++ b/drivers/mmc/core/sd_ops.c
@@ -232,14 +232,14 @@ int mmc_send_relative_addr(struct mmc_host *host, unsigned int *rca)
 	return 0;
 }
 
-int mmc_app_send_scr(struct mmc_card *card, u32 *scr)
+int mmc_app_send_scr(struct mmc_card *card)
 {
 	int err;
 	struct mmc_request mrq = {};
 	struct mmc_command cmd = {};
 	struct mmc_data data = {};
 	struct scatterlist sg;
-	void *data_buf;
+	__be32 *scr;
 
 	/* NOTE: caller guarantees scr is heap-allocated */
 
@@ -250,8 +250,8 @@ int mmc_app_send_scr(struct mmc_card *card, u32 *scr)
 	/* dma onto stack is unsafe/nonportable, but callers to this
 	 * routine normally provide temporary on-stack buffers ...
 	 */
-	data_buf = kmalloc(sizeof(card->raw_scr), GFP_KERNEL);
-	if (data_buf == NULL)
+	scr = kmalloc(sizeof(card->raw_scr), GFP_KERNEL);
+	if (!scr)
 		return -ENOMEM;
 
 	mrq.cmd = &cmd;
@@ -267,23 +267,22 @@ int mmc_app_send_scr(struct mmc_card *card, u32 *scr)
 	data.sg = &sg;
 	data.sg_len = 1;
 
-	sg_init_one(&sg, data_buf, 8);
+	sg_init_one(&sg, scr, 8);
 
 	mmc_set_data_timeout(&data, card);
 
 	mmc_wait_for_req(card->host, &mrq);
 
-	memcpy(scr, data_buf, sizeof(card->raw_scr));
-	kfree(data_buf);
+	card->raw_scr[0] = be32_to_cpu(scr[0]);
+	card->raw_scr[1] = be32_to_cpu(scr[1]);
+
+	kfree(scr);
 
 	if (cmd.error)
 		return cmd.error;
 	if (data.error)
 		return data.error;
 
-	scr[0] = be32_to_cpu(scr[0]);
-	scr[1] = be32_to_cpu(scr[1]);
-
 	return 0;
 }
 
diff --git a/drivers/mmc/core/sd_ops.h b/drivers/mmc/core/sd_ops.h
index 784f8e6b6baa..0e6c3d51e66d 100644
--- a/drivers/mmc/core/sd_ops.h
+++ b/drivers/mmc/core/sd_ops.h
@@ -22,7 +22,7 @@ int mmc_app_set_bus_width(struct mmc_card *card, int width);
 int mmc_send_app_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_send_if_cond(struct mmc_host *host, u32 ocr);
 int mmc_send_relative_addr(struct mmc_host *host, unsigned int *rca);
-int mmc_app_send_scr(struct mmc_card *card, u32 *scr);
+int mmc_app_send_scr(struct mmc_card *card);
 int mmc_sd_switch(struct mmc_card *card, int mode, int group,
 	u8 value, u8 *resp);
 int mmc_app_sd_status(struct mmc_card *card, void *ssr);
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index e992a7f8a16f..2b32b88949ba 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -267,7 +267,7 @@ static void sdio_release_func(struct device *dev)
 	sdio_free_func_cis(func);
 
 	kfree(func->info);
-
+	kfree(func->tmpbuf);
 	kfree(func);
 }
 
@@ -282,6 +282,16 @@ struct sdio_func *sdio_alloc_func(struct mmc_card *card)
 	if (!func)
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * allocate buffer separately to make sure it's properly aligned for
+	 * DMA usage (incl. 64 bit DMA)
+	 */
+	func->tmpbuf = kmalloc(4, GFP_KERNEL);
+	if (!func->tmpbuf) {
+		kfree(func);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	func->card = card;
 
 	device_initialize(&func->dev);
diff --git a/drivers/mmc/core/sdio_io.c b/drivers/mmc/core/sdio_io.c
index 74195d772f5a..d40744bbafa9 100644
--- a/drivers/mmc/core/sdio_io.c
+++ b/drivers/mmc/core/sdio_io.c
@@ -373,19 +373,16 @@ u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret)
 	u8 val;
 
 	if (!func) {
-		*err_ret = -EINVAL;
+		if (err_ret)
+			*err_ret = -EINVAL;
 		return 0xFF;
 	}
 
-	if (err_ret)
-		*err_ret = 0;
-
 	ret = mmc_io_rw_direct(func->card, 0, func->num, addr, 0, &val);
-	if (ret) {
-		if (err_ret)
-			*err_ret = ret;
+	if (err_ret)
+		*err_ret = ret;
+	if (ret)
 		return 0xFF;
-	}
 
 	return val;
 }
@@ -407,7 +404,8 @@ void sdio_writeb(struct sdio_func *func, u8 b, unsigned int addr, int *err_ret)
 	int ret;
 
 	if (!func) {
-		*err_ret = -EINVAL;
+		if (err_ret)
+			*err_ret = -EINVAL;
 		return;
 	}
 
@@ -441,7 +439,7 @@ u8 sdio_writeb_readb(struct sdio_func *func, u8 write_byte,
 	if (err_ret)
 		*err_ret = ret;
 	if (ret)
-		val = 0xff;
+		return 0xff;
 
 	return val;
 }
@@ -529,15 +527,11 @@ u16 sdio_readw(struct sdio_func *func, unsigned int addr, int *err_ret)
 {
 	int ret;
 
-	if (err_ret)
-		*err_ret = 0;
-
 	ret = sdio_memcpy_fromio(func, func->tmpbuf, addr, 2);
-	if (ret) {
-		if (err_ret)
-			*err_ret = ret;
+	if (err_ret)
+		*err_ret = ret;
+	if (ret)
 		return 0xFFFF;
-	}
 
 	return le16_to_cpup((__le16 *)func->tmpbuf);
 }
@@ -581,15 +575,11 @@ u32 sdio_readl(struct sdio_func *func, unsigned int addr, int *err_ret)
 {
 	int ret;
 
-	if (err_ret)
-		*err_ret = 0;
-
 	ret = sdio_memcpy_fromio(func, func->tmpbuf, addr, 4);
-	if (ret) {
-		if (err_ret)
-			*err_ret = ret;
+	if (err_ret)
+		*err_ret = ret;
+	if (ret)
 		return 0xFFFFFFFF;
-	}
 
 	return le32_to_cpup((__le32 *)func->tmpbuf);
 }
@@ -635,19 +625,16 @@ unsigned char sdio_f0_readb(struct sdio_func *func, unsigned int addr,
 	unsigned char val;
 
 	if (!func) {
-		*err_ret = -EINVAL;
+		if (err_ret)
+			*err_ret = -EINVAL;
 		return 0xFF;
 	}
 
-	if (err_ret)
-		*err_ret = 0;
-
 	ret = mmc_io_rw_direct(func->card, 0, 0, addr, 0, &val);
-	if (ret) {
-		if (err_ret)
-			*err_ret = ret;
+	if (err_ret)
+		*err_ret = ret;
+	if (ret)
 		return 0xFF;
-	}
 
 	return val;
 }
@@ -673,7 +660,8 @@ void sdio_f0_writeb(struct sdio_func *func, unsigned char b, unsigned int addr,
 	int ret;
 
 	if (!func) {
-		*err_ret = -EINVAL;
+		if (err_ret)
+			*err_ret = -EINVAL;
 		return;
 	}
 
diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c
index 3c0d3ab4324c..abaaba38514f 100644
--- a/drivers/mmc/core/sdio_ops.c
+++ b/drivers/mmc/core/sdio_ops.c
@@ -152,7 +152,7 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	data.flags = write ? MMC_DATA_WRITE : MMC_DATA_READ;
 
 	left_size = data.blksz * data.blocks;
-	nents = (left_size - 1) / seg_size + 1;
+	nents = DIV_ROUND_UP(left_size, seg_size);
 	if (nents > 1) {
 		if (sg_alloc_table(&sgtable, nents, GFP_KERNEL))
 			return -ENOMEM;
@@ -161,10 +161,9 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 		data.sg_len = nents;
 
 		for_each_sg(data.sg, sg_ptr, data.sg_len, i) {
-			sg_set_page(sg_ptr, virt_to_page(buf + (i * seg_size)),
-					min(seg_size, left_size),
-					offset_in_page(buf + (i * seg_size)));
-			left_size = left_size - seg_size;
+			sg_set_buf(sg_ptr, buf + i * seg_size,
+				   min(seg_size, left_size));
+			left_size -= seg_size;
 		}
 	} else {
 		data.sg = &sg;
diff --git a/drivers/mmc/core/sdio_ops.h b/drivers/mmc/core/sdio_ops.h
index bed8a8377fec..ee35cb4d170e 100644
--- a/drivers/mmc/core/sdio_ops.h
+++ b/drivers/mmc/core/sdio_ops.h
@@ -26,9 +26,15 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 int sdio_reset(struct mmc_host *host);
 unsigned int mmc_align_data_size(struct mmc_card *card, unsigned int sz);
 
-static inline bool mmc_is_io_op(u32 opcode)
+static inline bool sdio_is_io_busy(u32 opcode, u32 arg)
 {
-	return opcode == SD_IO_RW_DIRECT || opcode == SD_IO_RW_EXTENDED;
+	u32 addr;
+
+	addr = (arg >> 9) & 0x1FFFF;
+
+	return (opcode == SD_IO_RW_EXTENDED ||
+		(opcode == SD_IO_RW_DIRECT &&
+		!(addr == SDIO_CCCR_ABORT || addr == SDIO_CCCR_SUSPEND)));
 }
 
 #endif
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index f08691a58d7e..2db84dd664d7 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -622,6 +622,27 @@ config SDH_BFIN_MISSING_CMD_PULLUP_WORKAROUND
 	help
 	  If you say yes here SD-Cards may work on the EZkit.
 
+config MMC_CAVIUM_OCTEON
+	tristate "Cavium OCTEON SD/MMC Card Interface support"
+	depends on CAVIUM_OCTEON_SOC
+	help
+	  This selects Cavium OCTEON SD/MMC card Interface.
+	  If you have an OCTEON board with a Multimedia Card slot,
+	  say Y or M here.
+
+	  If unsure, say N.
+
+config MMC_CAVIUM_THUNDERX
+	tristate "Cavium ThunderX SD/MMC Card Interface support"
+	depends on PCI && 64BIT && (ARM64 || COMPILE_TEST)
+	depends on GPIOLIB
+	depends on OF_ADDRESS
+	help
+	  This selects Cavium ThunderX SD/MMC Card Interface.
+	  If you have an Cavium ARM64 board with a Multimedia Card slot
+	  or builtin eMMC chip say Y or M here. If built as a module
+	  the module will be called thunderx_mmc.ko.
+
 config MMC_DW
 	tristate "Synopsys DesignWare Memory Card Interface"
 	depends on HAS_DMA
@@ -799,6 +820,20 @@ config MMC_TOSHIBA_PCI
 	depends on PCI
 	help
 
+config MMC_BCM2835
+	tristate "Broadcom BCM2835 SDHOST MMC Controller support"
+	depends on ARCH_BCM2835 || COMPILE_TEST
+	depends on HAS_DMA
+	help
+	  This selects the BCM2835 SDHOST MMC controller. If you have
+	  a BCM2835 platform with SD or MMC devices, say Y or M here.
+
+	  Note that the BCM2835 has two SD controllers: The Arasan
+	  sdhci controller (supported by MMC_SDHCI_IPROC) and a custom
+	  sdhost controller (supported by this driver).
+
+	  If unsure, say N.
+
 config MMC_MTK
 	tristate "MediaTek SD/MMC Card Interface support"
 	depends on HAS_DMA
@@ -828,3 +863,11 @@ config MMC_SDHCI_BRCMSTB
 	  Broadcom STB SoCs.
 
 	  If unsure, say Y.
+
+config MMC_SDHCI_XENON
+	tristate "Marvell Xenon eMMC/SD/SDIO SDHCI driver"
+	depends on MMC_SDHCI_PLTFM
+	help
+	  This selects Marvell Xenon eMMC/SD/SDIO SDHCI.
+	  If you have a controller with this interface, say Y or M here.
+	  If unsure, say N.
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 6d548c4ee2fa..926347c2eeb4 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -42,6 +42,10 @@ obj-$(CONFIG_MMC_SDHI)		+= sh_mobile_sdhi.o
 obj-$(CONFIG_MMC_CB710)		+= cb710-mmc.o
 obj-$(CONFIG_MMC_VIA_SDMMC)	+= via-sdmmc.o
 obj-$(CONFIG_SDH_BFIN)		+= bfin_sdh.o
+octeon-mmc-objs := cavium.o cavium-octeon.o
+obj-$(CONFIG_MMC_CAVIUM_OCTEON) += octeon-mmc.o
+thunderx-mmc-objs := cavium.o cavium-thunderx.o
+obj-$(CONFIG_MMC_CAVIUM_THUNDERX) += thunderx-mmc.o
 obj-$(CONFIG_MMC_DW)		+= dw_mmc.o
 obj-$(CONFIG_MMC_DW_PLTFM)	+= dw_mmc-pltfm.o
 obj-$(CONFIG_MMC_DW_EXYNOS)	+= dw_mmc-exynos.o
@@ -59,6 +63,7 @@ obj-$(CONFIG_MMC_MOXART)	+= moxart-mmc.o
 obj-$(CONFIG_MMC_SUNXI)		+= sunxi-mmc.o
 obj-$(CONFIG_MMC_USDHI6ROL0)	+= usdhi6rol0.o
 obj-$(CONFIG_MMC_TOSHIBA_PCI)	+= toshsd.o
+obj-$(CONFIG_MMC_BCM2835)	+= bcm2835.o
 
 obj-$(CONFIG_MMC_REALTEK_PCI)	+= rtsx_pci_sdmmc.o
 obj-$(CONFIG_MMC_REALTEK_USB)	+= rtsx_usb_sdmmc.o
@@ -83,3 +88,6 @@ obj-$(CONFIG_MMC_SDHCI_BRCMSTB)		+= sdhci-brcmstb.o
 ifeq ($(CONFIG_CB710_DEBUG),y)
 	CFLAGS-cb710-mmc	+= -DDEBUG
 endif
+
+obj-$(CONFIG_MMC_SDHCI_XENON)	+= sdhci-xenon-driver.o
+sdhci-xenon-driver-y		+= sdhci-xenon.o sdhci-xenon-phy.o
diff --git a/drivers/mmc/host/android-goldfish.c b/drivers/mmc/host/android-goldfish.c
index 590a8a4522be..5b3e1c9bb75f 100644
--- a/drivers/mmc/host/android-goldfish.c
+++ b/drivers/mmc/host/android-goldfish.c
@@ -212,10 +212,7 @@ static void goldfish_mmc_xfer_done(struct goldfish_mmc_host *host,
 	if (host->dma_in_use) {
 		enum dma_data_direction dma_data_dir;
 
-		if (data->flags & MMC_DATA_WRITE)
-			dma_data_dir = DMA_TO_DEVICE;
-		else
-			dma_data_dir = DMA_FROM_DEVICE;
+		dma_data_dir = mmc_get_dma_dir(data);
 
 		if (dma_data_dir == DMA_FROM_DEVICE) {
 			/*
@@ -390,10 +387,7 @@ static void goldfish_mmc_prepare_data(struct goldfish_mmc_host *host,
 	 */
 	sg_len = (data->blocks == 1) ? 1 : data->sg_len;
 
-	if (data->flags & MMC_DATA_WRITE)
-		dma_data_dir = DMA_TO_DEVICE;
-	else
-		dma_data_dir = DMA_FROM_DEVICE;
+	dma_data_dir = mmc_get_dma_dir(data);
 
 	host->sg_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
 				  sg_len, dma_data_dir);
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 0ad8ef565b74..388e4a3f13e6 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -954,8 +954,7 @@ static void atmci_pdc_cleanup(struct atmel_mci *host)
 	if (data)
 		dma_unmap_sg(&host->pdev->dev,
 				data->sg, data->sg_len,
-				((data->flags & MMC_DATA_WRITE)
-				 ? DMA_TO_DEVICE : DMA_FROM_DEVICE));
+				mmc_get_dma_dir(data));
 }
 
 /*
@@ -993,8 +992,7 @@ static void atmci_dma_cleanup(struct atmel_mci *host)
 	if (data)
 		dma_unmap_sg(host->dma.chan->device->dev,
 				data->sg, data->sg_len,
-				((data->flags & MMC_DATA_WRITE)
-				 ? DMA_TO_DEVICE : DMA_FROM_DEVICE));
+				mmc_get_dma_dir(data));
 }
 
 /*
@@ -1095,7 +1093,6 @@ atmci_prepare_data_pdc(struct atmel_mci *host, struct mmc_data *data)
 {
 	u32 iflags, tmp;
 	unsigned int sg_len;
-	enum dma_data_direction dir;
 	int i;
 
 	data->error = -EINPROGRESS;
@@ -1107,13 +1104,10 @@ atmci_prepare_data_pdc(struct atmel_mci *host, struct mmc_data *data)
 	/* Enable pdc mode */
 	atmci_writel(host, ATMCI_MR, host->mode_reg | ATMCI_MR_PDCMODE);
 
-	if (data->flags & MMC_DATA_READ) {
-		dir = DMA_FROM_DEVICE;
+	if (data->flags & MMC_DATA_READ)
 		iflags |= ATMCI_ENDRX | ATMCI_RXBUFF;
-	} else {
-		dir = DMA_TO_DEVICE;
+	else
 		iflags |= ATMCI_ENDTX | ATMCI_TXBUFE | ATMCI_BLKE;
-	}
 
 	/* Set BLKLEN */
 	tmp = atmci_readl(host, ATMCI_MR);
@@ -1123,7 +1117,8 @@ atmci_prepare_data_pdc(struct atmel_mci *host, struct mmc_data *data)
 
 	/* Configure PDC */
 	host->data_size = data->blocks * data->blksz;
-	sg_len = dma_map_sg(&host->pdev->dev, data->sg, data->sg_len, dir);
+	sg_len = dma_map_sg(&host->pdev->dev, data->sg, data->sg_len,
+			    mmc_get_dma_dir(data));
 
 	if ((!host->caps.has_rwproof)
 	    && (host->data->flags & MMC_DATA_WRITE)) {
@@ -1135,9 +1130,8 @@ atmci_prepare_data_pdc(struct atmel_mci *host, struct mmc_data *data)
 	}
 
 	if (host->data_size)
-		atmci_pdc_set_both_buf(host,
-			((dir == DMA_FROM_DEVICE) ? XFER_RECEIVE : XFER_TRANSMIT));
-
+		atmci_pdc_set_both_buf(host, data->flags & MMC_DATA_READ ?
+				       XFER_RECEIVE : XFER_TRANSMIT);
 	return iflags;
 }
 
@@ -1148,7 +1142,6 @@ atmci_prepare_data_dma(struct atmel_mci *host, struct mmc_data *data)
 	struct dma_async_tx_descriptor	*desc;
 	struct scatterlist		*sg;
 	unsigned int			i;
-	enum dma_data_direction		direction;
 	enum dma_transfer_direction	slave_dirn;
 	unsigned int			sglen;
 	u32				maxburst;
@@ -1186,12 +1179,10 @@ atmci_prepare_data_dma(struct atmel_mci *host, struct mmc_data *data)
 		return -ENODEV;
 
 	if (data->flags & MMC_DATA_READ) {
-		direction = DMA_FROM_DEVICE;
 		host->dma_conf.direction = slave_dirn = DMA_DEV_TO_MEM;
 		maxburst = atmci_convert_chksize(host,
 						 host->dma_conf.src_maxburst);
 	} else {
-		direction = DMA_TO_DEVICE;
 		host->dma_conf.direction = slave_dirn = DMA_MEM_TO_DEV;
 		maxburst = atmci_convert_chksize(host,
 						 host->dma_conf.dst_maxburst);
@@ -1202,7 +1193,7 @@ atmci_prepare_data_dma(struct atmel_mci *host, struct mmc_data *data)
 			ATMCI_DMAEN);
 
 	sglen = dma_map_sg(chan->device->dev, data->sg,
-			data->sg_len, direction);
+			data->sg_len, mmc_get_dma_dir(data));
 
 	dmaengine_slave_config(chan, &host->dma_conf);
 	desc = dmaengine_prep_slave_sg(chan,
@@ -1217,7 +1208,8 @@ atmci_prepare_data_dma(struct atmel_mci *host, struct mmc_data *data)
 
 	return iflags;
 unmap_exit:
-	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, direction);
+	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len,
+		     mmc_get_dma_dir(data));
 	return -ENOMEM;
 }
 
diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c
new file mode 100644
index 000000000000..1f343a477b3d
--- /dev/null
+++ b/drivers/mmc/host/bcm2835.c
@@ -0,0 +1,1466 @@
+/*
+ * bcm2835 sdhost driver.
+ *
+ * The 2835 has two SD controllers: The Arasan sdhci controller
+ * (supported by the iproc driver) and a custom sdhost controller
+ * (supported by this driver).
+ *
+ * The sdhci controller supports both sdcard and sdio.  The sdhost
+ * controller supports the sdcard only, but has better performance.
+ * Also note that the rpi3 has sdio wifi, so driving the sdcard with
+ * the sdhost controller allows to use the sdhci controller for wifi
+ * support.
+ *
+ * The configuration is done by devicetree via pin muxing.  Both
+ * SD controller are available on the same pins (2 pin groups = pin 22
+ * to 27 + pin 48 to 53).  So it's possible to use both SD controllers
+ * at the same time with different pin groups.
+ *
+ * Author:      Phil Elwell <phil@raspberrypi.org>
+ *              Copyright (C) 2015-2016 Raspberry Pi (Trading) Ltd.
+ *
+ * Based on
+ *  mmc-bcm2835.c by Gellert Weisz
+ * which is, in turn, based on
+ *  sdhci-bcm2708.c by Broadcom
+ *  sdhci-bcm2835.c by Stephen Warren and Oleksandr Tymoshenko
+ *  sdhci.c and sdhci-pci.c by Pierre Ossman
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/time.h>
+#include <linux/workqueue.h>
+
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+
+#define SDCMD  0x00 /* Command to SD card              - 16 R/W */
+#define SDARG  0x04 /* Argument to SD card             - 32 R/W */
+#define SDTOUT 0x08 /* Start value for timeout counter - 32 R/W */
+#define SDCDIV 0x0c /* Start value for clock divider   - 11 R/W */
+#define SDRSP0 0x10 /* SD card response (31:0)         - 32 R   */
+#define SDRSP1 0x14 /* SD card response (63:32)        - 32 R   */
+#define SDRSP2 0x18 /* SD card response (95:64)        - 32 R   */
+#define SDRSP3 0x1c /* SD card response (127:96)       - 32 R   */
+#define SDHSTS 0x20 /* SD host status                  - 11 R/W */
+#define SDVDD  0x30 /* SD card power control           -  1 R/W */
+#define SDEDM  0x34 /* Emergency Debug Mode            - 13 R/W */
+#define SDHCFG 0x38 /* Host configuration              -  2 R/W */
+#define SDHBCT 0x3c /* Host byte count (debug)         - 32 R/W */
+#define SDDATA 0x40 /* Data to/from SD card            - 32 R/W */
+#define SDHBLC 0x50 /* Host block count (SDIO/SDHC)    -  9 R/W */
+
+#define SDCMD_NEW_FLAG			0x8000
+#define SDCMD_FAIL_FLAG			0x4000
+#define SDCMD_BUSYWAIT			0x800
+#define SDCMD_NO_RESPONSE		0x400
+#define SDCMD_LONG_RESPONSE		0x200
+#define SDCMD_WRITE_CMD			0x80
+#define SDCMD_READ_CMD			0x40
+#define SDCMD_CMD_MASK			0x3f
+
+#define SDCDIV_MAX_CDIV			0x7ff
+
+#define SDHSTS_BUSY_IRPT		0x400
+#define SDHSTS_BLOCK_IRPT		0x200
+#define SDHSTS_SDIO_IRPT		0x100
+#define SDHSTS_REW_TIME_OUT		0x80
+#define SDHSTS_CMD_TIME_OUT		0x40
+#define SDHSTS_CRC16_ERROR		0x20
+#define SDHSTS_CRC7_ERROR		0x10
+#define SDHSTS_FIFO_ERROR		0x08
+/* Reserved */
+/* Reserved */
+#define SDHSTS_DATA_FLAG		0x01
+
+#define SDHSTS_TRANSFER_ERROR_MASK	(SDHSTS_CRC7_ERROR | \
+					 SDHSTS_CRC16_ERROR | \
+					 SDHSTS_REW_TIME_OUT | \
+					 SDHSTS_FIFO_ERROR)
+
+#define SDHSTS_ERROR_MASK		(SDHSTS_CMD_TIME_OUT | \
+					 SDHSTS_TRANSFER_ERROR_MASK)
+
+#define SDHCFG_BUSY_IRPT_EN	BIT(10)
+#define SDHCFG_BLOCK_IRPT_EN	BIT(8)
+#define SDHCFG_SDIO_IRPT_EN	BIT(5)
+#define SDHCFG_DATA_IRPT_EN	BIT(4)
+#define SDHCFG_SLOW_CARD	BIT(3)
+#define SDHCFG_WIDE_EXT_BUS	BIT(2)
+#define SDHCFG_WIDE_INT_BUS	BIT(1)
+#define SDHCFG_REL_CMD_LINE	BIT(0)
+
+#define SDVDD_POWER_OFF		0
+#define SDVDD_POWER_ON		1
+
+#define SDEDM_FORCE_DATA_MODE	BIT(19)
+#define SDEDM_CLOCK_PULSE	BIT(20)
+#define SDEDM_BYPASS		BIT(21)
+
+#define SDEDM_WRITE_THRESHOLD_SHIFT	9
+#define SDEDM_READ_THRESHOLD_SHIFT	14
+#define SDEDM_THRESHOLD_MASK		0x1f
+
+#define SDEDM_FSM_MASK		0xf
+#define SDEDM_FSM_IDENTMODE	0x0
+#define SDEDM_FSM_DATAMODE	0x1
+#define SDEDM_FSM_READDATA	0x2
+#define SDEDM_FSM_WRITEDATA	0x3
+#define SDEDM_FSM_READWAIT	0x4
+#define SDEDM_FSM_READCRC	0x5
+#define SDEDM_FSM_WRITECRC	0x6
+#define SDEDM_FSM_WRITEWAIT1	0x7
+#define SDEDM_FSM_POWERDOWN	0x8
+#define SDEDM_FSM_POWERUP	0x9
+#define SDEDM_FSM_WRITESTART1	0xa
+#define SDEDM_FSM_WRITESTART2	0xb
+#define SDEDM_FSM_GENPULSES	0xc
+#define SDEDM_FSM_WRITEWAIT2	0xd
+#define SDEDM_FSM_STARTPOWDOWN	0xf
+
+#define SDDATA_FIFO_WORDS	16
+
+#define FIFO_READ_THRESHOLD	4
+#define FIFO_WRITE_THRESHOLD	4
+#define SDDATA_FIFO_PIO_BURST	8
+
+#define PIO_THRESHOLD	1  /* Maximum block count for PIO (0 = always DMA) */
+
+struct bcm2835_host {
+	spinlock_t		lock;
+	struct mutex		mutex;
+
+	void __iomem		*ioaddr;
+	u32			phys_addr;
+
+	struct mmc_host		*mmc;
+	struct platform_device	*pdev;
+
+	int			clock;		/* Current clock speed */
+	unsigned int		max_clk;	/* Max possible freq */
+	struct work_struct	dma_work;
+	struct delayed_work	timeout_work;	/* Timer for timeouts */
+	struct sg_mapping_iter	sg_miter;	/* SG state for PIO */
+	unsigned int		blocks;		/* remaining PIO blocks */
+	int			irq;		/* Device IRQ */
+
+	u32			ns_per_fifo_word;
+
+	/* cached registers */
+	u32			hcfg;
+	u32			cdiv;
+
+	struct mmc_request	*mrq;		/* Current request */
+	struct mmc_command	*cmd;		/* Current command */
+	struct mmc_data		*data;		/* Current data request */
+	bool			data_complete:1;/* Data finished before cmd */
+	bool			use_busy:1;	/* Wait for busy interrupt */
+	bool			use_sbc:1;	/* Send CMD23 */
+
+	/* for threaded irq handler */
+	bool			irq_block;
+	bool			irq_busy;
+	bool			irq_data;
+
+	/* DMA part */
+	struct dma_chan		*dma_chan_rxtx;
+	struct dma_chan		*dma_chan;
+	struct dma_slave_config dma_cfg_rx;
+	struct dma_slave_config dma_cfg_tx;
+	struct dma_async_tx_descriptor	*dma_desc;
+	u32			dma_dir;
+	u32			drain_words;
+	struct page		*drain_page;
+	u32			drain_offset;
+	bool			use_dma;
+};
+
+static void bcm2835_dumpcmd(struct bcm2835_host *host, struct mmc_command *cmd,
+			    const char *label)
+{
+	struct device *dev = &host->pdev->dev;
+
+	if (!cmd)
+		return;
+
+	dev_dbg(dev, "%c%s op %d arg 0x%x flags 0x%x - resp %08x %08x %08x %08x, err %d\n",
+		(cmd == host->cmd) ? '>' : ' ',
+		label, cmd->opcode, cmd->arg, cmd->flags,
+		cmd->resp[0], cmd->resp[1], cmd->resp[2], cmd->resp[3],
+		cmd->error);
+}
+
+static void bcm2835_dumpregs(struct bcm2835_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	struct device *dev = &host->pdev->dev;
+
+	if (mrq) {
+		bcm2835_dumpcmd(host, mrq->sbc, "sbc");
+		bcm2835_dumpcmd(host, mrq->cmd, "cmd");
+		if (mrq->data) {
+			dev_dbg(dev, "data blocks %x blksz %x - err %d\n",
+				mrq->data->blocks,
+				mrq->data->blksz,
+				mrq->data->error);
+		}
+		bcm2835_dumpcmd(host, mrq->stop, "stop");
+	}
+
+	dev_dbg(dev, "=========== REGISTER DUMP ===========\n");
+	dev_dbg(dev, "SDCMD  0x%08x\n", readl(host->ioaddr + SDCMD));
+	dev_dbg(dev, "SDARG  0x%08x\n", readl(host->ioaddr + SDARG));
+	dev_dbg(dev, "SDTOUT 0x%08x\n", readl(host->ioaddr + SDTOUT));
+	dev_dbg(dev, "SDCDIV 0x%08x\n", readl(host->ioaddr + SDCDIV));
+	dev_dbg(dev, "SDRSP0 0x%08x\n", readl(host->ioaddr + SDRSP0));
+	dev_dbg(dev, "SDRSP1 0x%08x\n", readl(host->ioaddr + SDRSP1));
+	dev_dbg(dev, "SDRSP2 0x%08x\n", readl(host->ioaddr + SDRSP2));
+	dev_dbg(dev, "SDRSP3 0x%08x\n", readl(host->ioaddr + SDRSP3));
+	dev_dbg(dev, "SDHSTS 0x%08x\n", readl(host->ioaddr + SDHSTS));
+	dev_dbg(dev, "SDVDD  0x%08x\n", readl(host->ioaddr + SDVDD));
+	dev_dbg(dev, "SDEDM  0x%08x\n", readl(host->ioaddr + SDEDM));
+	dev_dbg(dev, "SDHCFG 0x%08x\n", readl(host->ioaddr + SDHCFG));
+	dev_dbg(dev, "SDHBCT 0x%08x\n", readl(host->ioaddr + SDHBCT));
+	dev_dbg(dev, "SDHBLC 0x%08x\n", readl(host->ioaddr + SDHBLC));
+	dev_dbg(dev, "===========================================\n");
+}
+
+static void bcm2835_reset_internal(struct bcm2835_host *host)
+{
+	u32 temp;
+
+	writel(SDVDD_POWER_OFF, host->ioaddr + SDVDD);
+	writel(0, host->ioaddr + SDCMD);
+	writel(0, host->ioaddr + SDARG);
+	writel(0xf00000, host->ioaddr + SDTOUT);
+	writel(0, host->ioaddr + SDCDIV);
+	writel(0x7f8, host->ioaddr + SDHSTS); /* Write 1s to clear */
+	writel(0, host->ioaddr + SDHCFG);
+	writel(0, host->ioaddr + SDHBCT);
+	writel(0, host->ioaddr + SDHBLC);
+
+	/* Limit fifo usage due to silicon bug */
+	temp = readl(host->ioaddr + SDEDM);
+	temp &= ~((SDEDM_THRESHOLD_MASK << SDEDM_READ_THRESHOLD_SHIFT) |
+		  (SDEDM_THRESHOLD_MASK << SDEDM_WRITE_THRESHOLD_SHIFT));
+	temp |= (FIFO_READ_THRESHOLD << SDEDM_READ_THRESHOLD_SHIFT) |
+		(FIFO_WRITE_THRESHOLD << SDEDM_WRITE_THRESHOLD_SHIFT);
+	writel(temp, host->ioaddr + SDEDM);
+	msleep(20);
+	writel(SDVDD_POWER_ON, host->ioaddr + SDVDD);
+	msleep(20);
+	host->clock = 0;
+	writel(host->hcfg, host->ioaddr + SDHCFG);
+	writel(host->cdiv, host->ioaddr + SDCDIV);
+}
+
+static void bcm2835_reset(struct mmc_host *mmc)
+{
+	struct bcm2835_host *host = mmc_priv(mmc);
+
+	if (host->dma_chan)
+		dmaengine_terminate_sync(host->dma_chan);
+	bcm2835_reset_internal(host);
+}
+
+static void bcm2835_finish_command(struct bcm2835_host *host);
+
+static void bcm2835_wait_transfer_complete(struct bcm2835_host *host)
+{
+	int timediff;
+	u32 alternate_idle;
+
+	alternate_idle = (host->mrq->data->flags & MMC_DATA_READ) ?
+		SDEDM_FSM_READWAIT : SDEDM_FSM_WRITESTART1;
+
+	timediff = 0;
+
+	while (1) {
+		u32 edm, fsm;
+
+		edm = readl(host->ioaddr + SDEDM);
+		fsm = edm & SDEDM_FSM_MASK;
+
+		if ((fsm == SDEDM_FSM_IDENTMODE) ||
+		    (fsm == SDEDM_FSM_DATAMODE))
+			break;
+		if (fsm == alternate_idle) {
+			writel(edm | SDEDM_FORCE_DATA_MODE,
+			       host->ioaddr + SDEDM);
+			break;
+		}
+
+		timediff++;
+		if (timediff == 100000) {
+			dev_err(&host->pdev->dev,
+				"wait_transfer_complete - still waiting after %d retries\n",
+				timediff);
+			bcm2835_dumpregs(host);
+			host->mrq->data->error = -ETIMEDOUT;
+			return;
+		}
+		cpu_relax();
+	}
+}
+
+static void bcm2835_dma_complete(void *param)
+{
+	struct bcm2835_host *host = param;
+
+	schedule_work(&host->dma_work);
+}
+
+static void bcm2835_transfer_block_pio(struct bcm2835_host *host, bool is_read)
+{
+	unsigned long flags;
+	size_t blksize;
+	unsigned long wait_max;
+
+	blksize = host->data->blksz;
+
+	wait_max = jiffies + msecs_to_jiffies(500);
+
+	local_irq_save(flags);
+
+	while (blksize) {
+		int copy_words;
+		u32 hsts = 0;
+		size_t len;
+		u32 *buf;
+
+		if (!sg_miter_next(&host->sg_miter)) {
+			host->data->error = -EINVAL;
+			break;
+		}
+
+		len = min(host->sg_miter.length, blksize);
+		if (len % 4) {
+			host->data->error = -EINVAL;
+			break;
+		}
+
+		blksize -= len;
+		host->sg_miter.consumed = len;
+
+		buf = (u32 *)host->sg_miter.addr;
+
+		copy_words = len / 4;
+
+		while (copy_words) {
+			int burst_words, words;
+			u32 edm;
+
+			burst_words = min(SDDATA_FIFO_PIO_BURST, copy_words);
+			edm = readl(host->ioaddr + SDEDM);
+			if (is_read)
+				words = ((edm >> 4) & 0x1f);
+			else
+				words = SDDATA_FIFO_WORDS - ((edm >> 4) & 0x1f);
+
+			if (words < burst_words) {
+				int fsm_state = (edm & SDEDM_FSM_MASK);
+				struct device *dev = &host->pdev->dev;
+
+				if ((is_read &&
+				     (fsm_state != SDEDM_FSM_READDATA &&
+				      fsm_state != SDEDM_FSM_READWAIT &&
+				      fsm_state != SDEDM_FSM_READCRC)) ||
+				    (!is_read &&
+				     (fsm_state != SDEDM_FSM_WRITEDATA &&
+				      fsm_state != SDEDM_FSM_WRITESTART1 &&
+				      fsm_state != SDEDM_FSM_WRITESTART2))) {
+					hsts = readl(host->ioaddr + SDHSTS);
+					dev_err(dev, "fsm %x, hsts %08x\n",
+						fsm_state, hsts);
+					if (hsts & SDHSTS_ERROR_MASK)
+						break;
+				}
+
+				if (time_after(jiffies, wait_max)) {
+					dev_err(dev, "PIO %s timeout - EDM %08x\n",
+						is_read ? "read" : "write",
+						edm);
+					hsts = SDHSTS_REW_TIME_OUT;
+					break;
+				}
+				ndelay((burst_words - words) *
+				       host->ns_per_fifo_word);
+				continue;
+			} else if (words > copy_words) {
+				words = copy_words;
+			}
+
+			copy_words -= words;
+
+			while (words) {
+				if (is_read)
+					*(buf++) = readl(host->ioaddr + SDDATA);
+				else
+					writel(*(buf++), host->ioaddr + SDDATA);
+				words--;
+			}
+		}
+
+		if (hsts & SDHSTS_ERROR_MASK)
+			break;
+	}
+
+	sg_miter_stop(&host->sg_miter);
+
+	local_irq_restore(flags);
+}
+
+static void bcm2835_transfer_pio(struct bcm2835_host *host)
+{
+	struct device *dev = &host->pdev->dev;
+	u32 sdhsts;
+	bool is_read;
+
+	is_read = (host->data->flags & MMC_DATA_READ) != 0;
+	bcm2835_transfer_block_pio(host, is_read);
+
+	sdhsts = readl(host->ioaddr + SDHSTS);
+	if (sdhsts & (SDHSTS_CRC16_ERROR |
+		      SDHSTS_CRC7_ERROR |
+		      SDHSTS_FIFO_ERROR)) {
+		dev_err(dev, "%s transfer error - HSTS %08x\n",
+			is_read ? "read" : "write", sdhsts);
+		host->data->error = -EILSEQ;
+	} else if ((sdhsts & (SDHSTS_CMD_TIME_OUT |
+			      SDHSTS_REW_TIME_OUT))) {
+		dev_err(dev, "%s timeout error - HSTS %08x\n",
+			is_read ? "read" : "write", sdhsts);
+		host->data->error = -ETIMEDOUT;
+	}
+}
+
+static
+void bcm2835_prepare_dma(struct bcm2835_host *host, struct mmc_data *data)
+{
+	int len, dir_data, dir_slave;
+	struct dma_async_tx_descriptor *desc = NULL;
+	struct dma_chan *dma_chan;
+
+	dma_chan = host->dma_chan_rxtx;
+	if (data->flags & MMC_DATA_READ) {
+		dir_data = DMA_FROM_DEVICE;
+		dir_slave = DMA_DEV_TO_MEM;
+	} else {
+		dir_data = DMA_TO_DEVICE;
+		dir_slave = DMA_MEM_TO_DEV;
+	}
+
+	/* The block doesn't manage the FIFO DREQs properly for
+	 * multi-block transfers, so don't attempt to DMA the final
+	 * few words.  Unfortunately this requires the final sg entry
+	 * to be trimmed.  N.B. This code demands that the overspill
+	 * is contained in a single sg entry.
+	 */
+
+	host->drain_words = 0;
+	if ((data->blocks > 1) && (dir_data == DMA_FROM_DEVICE)) {
+		struct scatterlist *sg;
+		u32 len;
+		int i;
+
+		len = min((u32)(FIFO_READ_THRESHOLD - 1) * 4,
+			  (u32)data->blocks * data->blksz);
+
+		for_each_sg(data->sg, sg, data->sg_len, i) {
+			if (sg_is_last(sg)) {
+				WARN_ON(sg->length < len);
+				sg->length -= len;
+				host->drain_page = sg_page(sg);
+				host->drain_offset = sg->offset + sg->length;
+			}
+		}
+		host->drain_words = len / 4;
+	}
+
+	/* The parameters have already been validated, so this will not fail */
+	(void)dmaengine_slave_config(dma_chan,
+				     (dir_data == DMA_FROM_DEVICE) ?
+				     &host->dma_cfg_rx :
+				     &host->dma_cfg_tx);
+
+	len = dma_map_sg(dma_chan->device->dev, data->sg, data->sg_len,
+			 dir_data);
+
+	if (len > 0) {
+		desc = dmaengine_prep_slave_sg(dma_chan, data->sg,
+					       len, dir_slave,
+					       DMA_PREP_INTERRUPT |
+					       DMA_CTRL_ACK);
+	}
+
+	if (desc) {
+		desc->callback = bcm2835_dma_complete;
+		desc->callback_param = host;
+		host->dma_desc = desc;
+		host->dma_chan = dma_chan;
+		host->dma_dir = dir_data;
+	}
+}
+
+static void bcm2835_start_dma(struct bcm2835_host *host)
+{
+	dmaengine_submit(host->dma_desc);
+	dma_async_issue_pending(host->dma_chan);
+}
+
+static void bcm2835_set_transfer_irqs(struct bcm2835_host *host)
+{
+	u32 all_irqs = SDHCFG_DATA_IRPT_EN | SDHCFG_BLOCK_IRPT_EN |
+		SDHCFG_BUSY_IRPT_EN;
+
+	if (host->dma_desc) {
+		host->hcfg = (host->hcfg & ~all_irqs) |
+			SDHCFG_BUSY_IRPT_EN;
+	} else {
+		host->hcfg = (host->hcfg & ~all_irqs) |
+			SDHCFG_DATA_IRPT_EN |
+			SDHCFG_BUSY_IRPT_EN;
+	}
+
+	writel(host->hcfg, host->ioaddr + SDHCFG);
+}
+
+static
+void bcm2835_prepare_data(struct bcm2835_host *host, struct mmc_command *cmd)
+{
+	struct mmc_data *data = cmd->data;
+
+	WARN_ON(host->data);
+
+	host->data = data;
+	if (!data)
+		return;
+
+	host->data_complete = false;
+	host->data->bytes_xfered = 0;
+
+	if (!host->dma_desc) {
+		/* Use PIO */
+		int flags = SG_MITER_ATOMIC;
+
+		if (data->flags & MMC_DATA_READ)
+			flags |= SG_MITER_TO_SG;
+		else
+			flags |= SG_MITER_FROM_SG;
+		sg_miter_start(&host->sg_miter, data->sg, data->sg_len, flags);
+		host->blocks = data->blocks;
+	}
+
+	bcm2835_set_transfer_irqs(host);
+
+	writel(data->blksz, host->ioaddr + SDHBCT);
+	writel(data->blocks, host->ioaddr + SDHBLC);
+}
+
+static u32 bcm2835_read_wait_sdcmd(struct bcm2835_host *host, u32 max_ms)
+{
+	struct device *dev = &host->pdev->dev;
+	u32 value;
+	int ret;
+
+	ret = readl_poll_timeout(host->ioaddr + SDCMD, value,
+				 !(value & SDCMD_NEW_FLAG), 1, 10);
+	if (ret == -ETIMEDOUT)
+		/* if it takes a while make poll interval bigger */
+		ret = readl_poll_timeout(host->ioaddr + SDCMD, value,
+					 !(value & SDCMD_NEW_FLAG),
+					 10, max_ms * 1000);
+	if (ret == -ETIMEDOUT)
+		dev_err(dev, "%s: timeout (%d ms)\n", __func__, max_ms);
+
+	return value;
+}
+
+static void bcm2835_finish_request(struct bcm2835_host *host)
+{
+	struct dma_chan *terminate_chan = NULL;
+	struct mmc_request *mrq;
+
+	cancel_delayed_work(&host->timeout_work);
+
+	mrq = host->mrq;
+
+	host->mrq = NULL;
+	host->cmd = NULL;
+	host->data = NULL;
+
+	host->dma_desc = NULL;
+	terminate_chan = host->dma_chan;
+	host->dma_chan = NULL;
+
+	if (terminate_chan) {
+		int err = dmaengine_terminate_all(terminate_chan);
+
+		if (err)
+			dev_err(&host->pdev->dev,
+				"failed to terminate DMA (%d)\n", err);
+	}
+
+	mmc_request_done(host->mmc, mrq);
+}
+
+static
+bool bcm2835_send_command(struct bcm2835_host *host, struct mmc_command *cmd)
+{
+	struct device *dev = &host->pdev->dev;
+	u32 sdcmd, sdhsts;
+	unsigned long timeout;
+
+	WARN_ON(host->cmd);
+
+	sdcmd = bcm2835_read_wait_sdcmd(host, 100);
+	if (sdcmd & SDCMD_NEW_FLAG) {
+		dev_err(dev, "previous command never completed.\n");
+		bcm2835_dumpregs(host);
+		cmd->error = -EILSEQ;
+		bcm2835_finish_request(host);
+		return false;
+	}
+
+	if (!cmd->data && cmd->busy_timeout > 9000)
+		timeout = DIV_ROUND_UP(cmd->busy_timeout, 1000) * HZ + HZ;
+	else
+		timeout = 10 * HZ;
+	schedule_delayed_work(&host->timeout_work, timeout);
+
+	host->cmd = cmd;
+
+	/* Clear any error flags */
+	sdhsts = readl(host->ioaddr + SDHSTS);
+	if (sdhsts & SDHSTS_ERROR_MASK)
+		writel(sdhsts, host->ioaddr + SDHSTS);
+
+	if ((cmd->flags & MMC_RSP_136) && (cmd->flags & MMC_RSP_BUSY)) {
+		dev_err(dev, "unsupported response type!\n");
+		cmd->error = -EINVAL;
+		bcm2835_finish_request(host);
+		return false;
+	}
+
+	bcm2835_prepare_data(host, cmd);
+
+	writel(cmd->arg, host->ioaddr + SDARG);
+
+	sdcmd = cmd->opcode & SDCMD_CMD_MASK;
+
+	host->use_busy = false;
+	if (!(cmd->flags & MMC_RSP_PRESENT)) {
+		sdcmd |= SDCMD_NO_RESPONSE;
+	} else {
+		if (cmd->flags & MMC_RSP_136)
+			sdcmd |= SDCMD_LONG_RESPONSE;
+		if (cmd->flags & MMC_RSP_BUSY) {
+			sdcmd |= SDCMD_BUSYWAIT;
+			host->use_busy = true;
+		}
+	}
+
+	if (cmd->data) {
+		if (cmd->data->flags & MMC_DATA_WRITE)
+			sdcmd |= SDCMD_WRITE_CMD;
+		if (cmd->data->flags & MMC_DATA_READ)
+			sdcmd |= SDCMD_READ_CMD;
+	}
+
+	writel(sdcmd | SDCMD_NEW_FLAG, host->ioaddr + SDCMD);
+
+	return true;
+}
+
+static void bcm2835_transfer_complete(struct bcm2835_host *host)
+{
+	struct mmc_data *data;
+
+	WARN_ON(!host->data_complete);
+
+	data = host->data;
+	host->data = NULL;
+
+	/* Need to send CMD12 if -
+	 * a) open-ended multiblock transfer (no CMD23)
+	 * b) error in multiblock transfer
+	 */
+	if (host->mrq->stop && (data->error || !host->use_sbc)) {
+		if (bcm2835_send_command(host, host->mrq->stop)) {
+			/* No busy, so poll for completion */
+			if (!host->use_busy)
+				bcm2835_finish_command(host);
+		}
+	} else {
+		bcm2835_wait_transfer_complete(host);
+		bcm2835_finish_request(host);
+	}
+}
+
+static void bcm2835_finish_data(struct bcm2835_host *host)
+{
+	struct device *dev = &host->pdev->dev;
+	struct mmc_data *data;
+
+	data = host->data;
+
+	host->hcfg &= ~(SDHCFG_DATA_IRPT_EN | SDHCFG_BLOCK_IRPT_EN);
+	writel(host->hcfg, host->ioaddr + SDHCFG);
+
+	data->bytes_xfered = data->error ? 0 : (data->blksz * data->blocks);
+
+	host->data_complete = true;
+
+	if (host->cmd) {
+		/* Data managed to finish before the
+		 * command completed. Make sure we do
+		 * things in the proper order.
+		 */
+		dev_dbg(dev, "Finished early - HSTS %08x\n",
+			readl(host->ioaddr + SDHSTS));
+	} else {
+		bcm2835_transfer_complete(host);
+	}
+}
+
+static void bcm2835_finish_command(struct bcm2835_host *host)
+{
+	struct device *dev = &host->pdev->dev;
+	struct mmc_command *cmd = host->cmd;
+	u32 sdcmd;
+
+	sdcmd = bcm2835_read_wait_sdcmd(host, 100);
+
+	/* Check for errors */
+	if (sdcmd & SDCMD_NEW_FLAG) {
+		dev_err(dev, "command never completed.\n");
+		bcm2835_dumpregs(host);
+		host->cmd->error = -EIO;
+		bcm2835_finish_request(host);
+		return;
+	} else if (sdcmd & SDCMD_FAIL_FLAG) {
+		u32 sdhsts = readl(host->ioaddr + SDHSTS);
+
+		/* Clear the errors */
+		writel(SDHSTS_ERROR_MASK, host->ioaddr + SDHSTS);
+
+		if (!(sdhsts & SDHSTS_CRC7_ERROR) ||
+		    (host->cmd->opcode != MMC_SEND_OP_COND)) {
+			if (sdhsts & SDHSTS_CMD_TIME_OUT) {
+				host->cmd->error = -ETIMEDOUT;
+			} else {
+				dev_err(dev, "unexpected command %d error\n",
+					host->cmd->opcode);
+				bcm2835_dumpregs(host);
+				host->cmd->error = -EILSEQ;
+			}
+			bcm2835_finish_request(host);
+			return;
+		}
+	}
+
+	if (cmd->flags & MMC_RSP_PRESENT) {
+		if (cmd->flags & MMC_RSP_136) {
+			int i;
+
+			for (i = 0; i < 4; i++) {
+				cmd->resp[3 - i] =
+					readl(host->ioaddr + SDRSP0 + i * 4);
+			}
+		} else {
+			cmd->resp[0] = readl(host->ioaddr + SDRSP0);
+		}
+	}
+
+	if (cmd == host->mrq->sbc) {
+		/* Finished CMD23, now send actual command. */
+		host->cmd = NULL;
+		if (bcm2835_send_command(host, host->mrq->cmd)) {
+			if (host->data && host->dma_desc)
+				/* DMA transfer starts now, PIO starts
+				 * after irq
+				 */
+				bcm2835_start_dma(host);
+
+			if (!host->use_busy)
+				bcm2835_finish_command(host);
+		}
+	} else if (cmd == host->mrq->stop) {
+		/* Finished CMD12 */
+		bcm2835_finish_request(host);
+	} else {
+		/* Processed actual command. */
+		host->cmd = NULL;
+		if (!host->data)
+			bcm2835_finish_request(host);
+		else if (host->data_complete)
+			bcm2835_transfer_complete(host);
+	}
+}
+
+static void bcm2835_timeout(struct work_struct *work)
+{
+	struct delayed_work *d = to_delayed_work(work);
+	struct bcm2835_host *host =
+		container_of(d, struct bcm2835_host, timeout_work);
+	struct device *dev = &host->pdev->dev;
+
+	mutex_lock(&host->mutex);
+
+	if (host->mrq) {
+		dev_err(dev, "timeout waiting for hardware interrupt.\n");
+		bcm2835_dumpregs(host);
+
+		if (host->data) {
+			host->data->error = -ETIMEDOUT;
+			bcm2835_finish_data(host);
+		} else {
+			if (host->cmd)
+				host->cmd->error = -ETIMEDOUT;
+			else
+				host->mrq->cmd->error = -ETIMEDOUT;
+
+			bcm2835_finish_request(host);
+		}
+	}
+
+	mutex_unlock(&host->mutex);
+}
+
+static bool bcm2835_check_cmd_error(struct bcm2835_host *host, u32 intmask)
+{
+	struct device *dev = &host->pdev->dev;
+
+	if (!(intmask & SDHSTS_ERROR_MASK))
+		return false;
+
+	if (!host->cmd)
+		return true;
+
+	dev_err(dev, "sdhost_busy_irq: intmask %08x\n", intmask);
+	if (intmask & SDHSTS_CRC7_ERROR) {
+		host->cmd->error = -EILSEQ;
+	} else if (intmask & (SDHSTS_CRC16_ERROR |
+			      SDHSTS_FIFO_ERROR)) {
+		if (host->mrq->data)
+			host->mrq->data->error = -EILSEQ;
+		else
+			host->cmd->error = -EILSEQ;
+	} else if (intmask & SDHSTS_REW_TIME_OUT) {
+		if (host->mrq->data)
+			host->mrq->data->error = -ETIMEDOUT;
+		else
+			host->cmd->error = -ETIMEDOUT;
+	} else if (intmask & SDHSTS_CMD_TIME_OUT) {
+		host->cmd->error = -ETIMEDOUT;
+	}
+	bcm2835_dumpregs(host);
+	return true;
+}
+
+static void bcm2835_check_data_error(struct bcm2835_host *host, u32 intmask)
+{
+	if (!host->data)
+		return;
+	if (intmask & (SDHSTS_CRC16_ERROR | SDHSTS_FIFO_ERROR))
+		host->data->error = -EILSEQ;
+	if (intmask & SDHSTS_REW_TIME_OUT)
+		host->data->error = -ETIMEDOUT;
+}
+
+static void bcm2835_busy_irq(struct bcm2835_host *host)
+{
+	if (WARN_ON(!host->cmd)) {
+		bcm2835_dumpregs(host);
+		return;
+	}
+
+	if (WARN_ON(!host->use_busy)) {
+		bcm2835_dumpregs(host);
+		return;
+	}
+	host->use_busy = false;
+
+	bcm2835_finish_command(host);
+}
+
+static void bcm2835_data_irq(struct bcm2835_host *host, u32 intmask)
+{
+	/* There are no dedicated data/space available interrupt
+	 * status bits, so it is necessary to use the single shared
+	 * data/space available FIFO status bits. It is therefore not
+	 * an error to get here when there is no data transfer in
+	 * progress.
+	 */
+	if (!host->data)
+		return;
+
+	bcm2835_check_data_error(host, intmask);
+	if (host->data->error)
+		goto finished;
+
+	if (host->data->flags & MMC_DATA_WRITE) {
+		/* Use the block interrupt for writes after the first block */
+		host->hcfg &= ~(SDHCFG_DATA_IRPT_EN);
+		host->hcfg |= SDHCFG_BLOCK_IRPT_EN;
+		writel(host->hcfg, host->ioaddr + SDHCFG);
+		bcm2835_transfer_pio(host);
+	} else {
+		bcm2835_transfer_pio(host);
+		host->blocks--;
+		if ((host->blocks == 0) || host->data->error)
+			goto finished;
+	}
+	return;
+
+finished:
+	host->hcfg &= ~(SDHCFG_DATA_IRPT_EN | SDHCFG_BLOCK_IRPT_EN);
+	writel(host->hcfg, host->ioaddr + SDHCFG);
+}
+
+static void bcm2835_data_threaded_irq(struct bcm2835_host *host)
+{
+	if (!host->data)
+		return;
+	if ((host->blocks == 0) || host->data->error)
+		bcm2835_finish_data(host);
+}
+
+static void bcm2835_block_irq(struct bcm2835_host *host)
+{
+	if (WARN_ON(!host->data)) {
+		bcm2835_dumpregs(host);
+		return;
+	}
+
+	if (!host->dma_desc) {
+		WARN_ON(!host->blocks);
+		if (host->data->error || (--host->blocks == 0))
+			bcm2835_finish_data(host);
+		else
+			bcm2835_transfer_pio(host);
+	} else if (host->data->flags & MMC_DATA_WRITE) {
+		bcm2835_finish_data(host);
+	}
+}
+
+static irqreturn_t bcm2835_irq(int irq, void *dev_id)
+{
+	irqreturn_t result = IRQ_NONE;
+	struct bcm2835_host *host = dev_id;
+	u32 intmask;
+
+	spin_lock(&host->lock);
+
+	intmask = readl(host->ioaddr + SDHSTS);
+
+	writel(SDHSTS_BUSY_IRPT |
+	       SDHSTS_BLOCK_IRPT |
+	       SDHSTS_SDIO_IRPT |
+	       SDHSTS_DATA_FLAG,
+	       host->ioaddr + SDHSTS);
+
+	if (intmask & SDHSTS_BLOCK_IRPT) {
+		bcm2835_check_data_error(host, intmask);
+		host->irq_block = true;
+		result = IRQ_WAKE_THREAD;
+	}
+
+	if (intmask & SDHSTS_BUSY_IRPT) {
+		if (!bcm2835_check_cmd_error(host, intmask)) {
+			host->irq_busy = true;
+			result = IRQ_WAKE_THREAD;
+		} else {
+			result = IRQ_HANDLED;
+		}
+	}
+
+	/* There is no true data interrupt status bit, so it is
+	 * necessary to qualify the data flag with the interrupt
+	 * enable bit.
+	 */
+	if ((intmask & SDHSTS_DATA_FLAG) &&
+	    (host->hcfg & SDHCFG_DATA_IRPT_EN)) {
+		bcm2835_data_irq(host, intmask);
+		host->irq_data = true;
+		result = IRQ_WAKE_THREAD;
+	}
+
+	spin_unlock(&host->lock);
+
+	return result;
+}
+
+static irqreturn_t bcm2835_threaded_irq(int irq, void *dev_id)
+{
+	struct bcm2835_host *host = dev_id;
+	unsigned long flags;
+	bool block, busy, data;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	block = host->irq_block;
+	busy  = host->irq_busy;
+	data  = host->irq_data;
+	host->irq_block = false;
+	host->irq_busy  = false;
+	host->irq_data  = false;
+
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	mutex_lock(&host->mutex);
+
+	if (block)
+		bcm2835_block_irq(host);
+	if (busy)
+		bcm2835_busy_irq(host);
+	if (data)
+		bcm2835_data_threaded_irq(host);
+
+	mutex_unlock(&host->mutex);
+
+	return IRQ_HANDLED;
+}
+
+static void bcm2835_dma_complete_work(struct work_struct *work)
+{
+	struct bcm2835_host *host =
+		container_of(work, struct bcm2835_host, dma_work);
+	struct mmc_data *data = host->data;
+
+	mutex_lock(&host->mutex);
+
+	if (host->dma_chan) {
+		dma_unmap_sg(host->dma_chan->device->dev,
+			     data->sg, data->sg_len,
+			     host->dma_dir);
+
+		host->dma_chan = NULL;
+	}
+
+	if (host->drain_words) {
+		unsigned long flags;
+		void *page;
+		u32 *buf;
+
+		if (host->drain_offset & PAGE_MASK) {
+			host->drain_page += host->drain_offset >> PAGE_SHIFT;
+			host->drain_offset &= ~PAGE_MASK;
+		}
+		local_irq_save(flags);
+		page = kmap_atomic(host->drain_page);
+		buf = page + host->drain_offset;
+
+		while (host->drain_words) {
+			u32 edm = readl(host->ioaddr + SDEDM);
+
+			if ((edm >> 4) & 0x1f)
+				*(buf++) = readl(host->ioaddr + SDDATA);
+			host->drain_words--;
+		}
+
+		kunmap_atomic(page);
+		local_irq_restore(flags);
+	}
+
+	bcm2835_finish_data(host);
+
+	mutex_unlock(&host->mutex);
+}
+
+static void bcm2835_set_clock(struct bcm2835_host *host, unsigned int clock)
+{
+	int div;
+
+	/* The SDCDIV register has 11 bits, and holds (div - 2).  But
+	 * in data mode the max is 50MHz wihout a minimum, and only
+	 * the bottom 3 bits are used. Since the switch over is
+	 * automatic (unless we have marked the card as slow...),
+	 * chosen values have to make sense in both modes.  Ident mode
+	 * must be 100-400KHz, so can range check the requested
+	 * clock. CMD15 must be used to return to data mode, so this
+	 * can be monitored.
+	 *
+	 * clock 250MHz -> 0->125MHz, 1->83.3MHz, 2->62.5MHz, 3->50.0MHz
+	 *                 4->41.7MHz, 5->35.7MHz, 6->31.3MHz, 7->27.8MHz
+	 *
+	 *		 623->400KHz/27.8MHz
+	 *		 reset value (507)->491159/50MHz
+	 *
+	 * BUT, the 3-bit clock divisor in data mode is too small if
+	 * the core clock is higher than 250MHz, so instead use the
+	 * SLOW_CARD configuration bit to force the use of the ident
+	 * clock divisor at all times.
+	 */
+
+	if (clock < 100000) {
+		/* Can't stop the clock, but make it as slow as possible
+		 * to show willing
+		 */
+		host->cdiv = SDCDIV_MAX_CDIV;
+		writel(host->cdiv, host->ioaddr + SDCDIV);
+		return;
+	}
+
+	div = host->max_clk / clock;
+	if (div < 2)
+		div = 2;
+	if ((host->max_clk / div) > clock)
+		div++;
+	div -= 2;
+
+	if (div > SDCDIV_MAX_CDIV)
+		div = SDCDIV_MAX_CDIV;
+
+	clock = host->max_clk / (div + 2);
+	host->mmc->actual_clock = clock;
+
+	/* Calibrate some delays */
+
+	host->ns_per_fifo_word = (1000000000 / clock) *
+		((host->mmc->caps & MMC_CAP_4_BIT_DATA) ? 8 : 32);
+
+	host->cdiv = div;
+	writel(host->cdiv, host->ioaddr + SDCDIV);
+
+	/* Set the timeout to 500ms */
+	writel(host->mmc->actual_clock / 2, host->ioaddr + SDTOUT);
+}
+
+static void bcm2835_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct bcm2835_host *host = mmc_priv(mmc);
+	struct device *dev = &host->pdev->dev;
+	u32 edm, fsm;
+
+	/* Reset the error statuses in case this is a retry */
+	if (mrq->sbc)
+		mrq->sbc->error = 0;
+	if (mrq->cmd)
+		mrq->cmd->error = 0;
+	if (mrq->data)
+		mrq->data->error = 0;
+	if (mrq->stop)
+		mrq->stop->error = 0;
+
+	if (mrq->data && !is_power_of_2(mrq->data->blksz)) {
+		dev_err(dev, "unsupported block size (%d bytes)\n",
+			mrq->data->blksz);
+		mrq->cmd->error = -EINVAL;
+		mmc_request_done(mmc, mrq);
+		return;
+	}
+
+	if (host->use_dma && mrq->data && (mrq->data->blocks > PIO_THRESHOLD))
+		bcm2835_prepare_dma(host, mrq->data);
+
+	mutex_lock(&host->mutex);
+
+	WARN_ON(host->mrq);
+	host->mrq = mrq;
+
+	edm = readl(host->ioaddr + SDEDM);
+	fsm = edm & SDEDM_FSM_MASK;
+
+	if ((fsm != SDEDM_FSM_IDENTMODE) &&
+	    (fsm != SDEDM_FSM_DATAMODE)) {
+		dev_err(dev, "previous command (%d) not complete (EDM %08x)\n",
+			readl(host->ioaddr + SDCMD) & SDCMD_CMD_MASK,
+			edm);
+		bcm2835_dumpregs(host);
+		mrq->cmd->error = -EILSEQ;
+		bcm2835_finish_request(host);
+		mutex_unlock(&host->mutex);
+		return;
+	}
+
+	host->use_sbc = !!mrq->sbc && host->mrq->data &&
+			(host->mrq->data->flags & MMC_DATA_READ);
+	if (host->use_sbc) {
+		if (bcm2835_send_command(host, mrq->sbc)) {
+			if (!host->use_busy)
+				bcm2835_finish_command(host);
+		}
+	} else if (bcm2835_send_command(host, mrq->cmd)) {
+		if (host->data && host->dma_desc) {
+			/* DMA transfer starts now, PIO starts after irq */
+			bcm2835_start_dma(host);
+		}
+
+		if (!host->use_busy)
+			bcm2835_finish_command(host);
+	}
+
+	mutex_unlock(&host->mutex);
+}
+
+static void bcm2835_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct bcm2835_host *host = mmc_priv(mmc);
+
+	mutex_lock(&host->mutex);
+
+	if (!ios->clock || ios->clock != host->clock) {
+		bcm2835_set_clock(host, ios->clock);
+		host->clock = ios->clock;
+	}
+
+	/* set bus width */
+	host->hcfg &= ~SDHCFG_WIDE_EXT_BUS;
+	if (ios->bus_width == MMC_BUS_WIDTH_4)
+		host->hcfg |= SDHCFG_WIDE_EXT_BUS;
+
+	host->hcfg |= SDHCFG_WIDE_INT_BUS;
+
+	/* Disable clever clock switching, to cope with fast core clocks */
+	host->hcfg |= SDHCFG_SLOW_CARD;
+
+	writel(host->hcfg, host->ioaddr + SDHCFG);
+
+	mutex_unlock(&host->mutex);
+}
+
+static struct mmc_host_ops bcm2835_ops = {
+	.request = bcm2835_request,
+	.set_ios = bcm2835_set_ios,
+	.hw_reset = bcm2835_reset,
+};
+
+static int bcm2835_add_host(struct bcm2835_host *host)
+{
+	struct mmc_host *mmc = host->mmc;
+	struct device *dev = &host->pdev->dev;
+	char pio_limit_string[20];
+	int ret;
+
+	mmc->f_max = host->max_clk;
+	mmc->f_min = host->max_clk / SDCDIV_MAX_CDIV;
+
+	mmc->max_busy_timeout = ~0 / (mmc->f_max / 1000);
+
+	dev_dbg(dev, "f_max %d, f_min %d, max_busy_timeout %d\n",
+		mmc->f_max, mmc->f_min, mmc->max_busy_timeout);
+
+	/* host controller capabilities */
+	mmc->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED |
+		     MMC_CAP_NEEDS_POLL | MMC_CAP_HW_RESET | MMC_CAP_ERASE |
+		     MMC_CAP_CMD23;
+
+	spin_lock_init(&host->lock);
+	mutex_init(&host->mutex);
+
+	if (IS_ERR_OR_NULL(host->dma_chan_rxtx)) {
+		dev_warn(dev, "unable to initialise DMA channel. Falling back to PIO\n");
+		host->use_dma = false;
+	} else {
+		host->use_dma = true;
+
+		host->dma_cfg_tx.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_cfg_tx.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_cfg_tx.slave_id = 13;		/* DREQ channel */
+		host->dma_cfg_tx.direction = DMA_MEM_TO_DEV;
+		host->dma_cfg_tx.src_addr = 0;
+		host->dma_cfg_tx.dst_addr = host->phys_addr + SDDATA;
+
+		host->dma_cfg_rx.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_cfg_rx.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_cfg_rx.slave_id = 13;		/* DREQ channel */
+		host->dma_cfg_rx.direction = DMA_DEV_TO_MEM;
+		host->dma_cfg_rx.src_addr = host->phys_addr + SDDATA;
+		host->dma_cfg_rx.dst_addr = 0;
+
+		if (dmaengine_slave_config(host->dma_chan_rxtx,
+					   &host->dma_cfg_tx) != 0 ||
+		    dmaengine_slave_config(host->dma_chan_rxtx,
+					   &host->dma_cfg_rx) != 0)
+			host->use_dma = false;
+	}
+
+	mmc->max_segs = 128;
+	mmc->max_req_size = 524288;
+	mmc->max_seg_size = mmc->max_req_size;
+	mmc->max_blk_size = 1024;
+	mmc->max_blk_count =  65535;
+
+	/* report supported voltage ranges */
+	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
+
+	INIT_WORK(&host->dma_work, bcm2835_dma_complete_work);
+	INIT_DELAYED_WORK(&host->timeout_work, bcm2835_timeout);
+
+	/* Set interrupt enables */
+	host->hcfg = SDHCFG_BUSY_IRPT_EN;
+
+	bcm2835_reset_internal(host);
+
+	ret = request_threaded_irq(host->irq, bcm2835_irq,
+				   bcm2835_threaded_irq,
+				   0, mmc_hostname(mmc), host);
+	if (ret) {
+		dev_err(dev, "failed to request IRQ %d: %d\n", host->irq, ret);
+		return ret;
+	}
+
+	ret = mmc_add_host(mmc);
+	if (ret) {
+		free_irq(host->irq, host);
+		return ret;
+	}
+
+	pio_limit_string[0] = '\0';
+	if (host->use_dma && (PIO_THRESHOLD > 0))
+		sprintf(pio_limit_string, " (>%d)", PIO_THRESHOLD);
+	dev_info(dev, "loaded - DMA %s%s\n",
+		 host->use_dma ? "enabled" : "disabled", pio_limit_string);
+
+	return 0;
+}
+
+static int bcm2835_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct clk *clk;
+	struct resource *iomem;
+	struct bcm2835_host *host;
+	struct mmc_host *mmc;
+	const __be32 *regaddr_p;
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+	mmc = mmc_alloc_host(sizeof(*host), dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	mmc->ops = &bcm2835_ops;
+	host = mmc_priv(mmc);
+	host->mmc = mmc;
+	host->pdev = pdev;
+	spin_lock_init(&host->lock);
+
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	host->ioaddr = devm_ioremap_resource(dev, iomem);
+	if (IS_ERR(host->ioaddr)) {
+		ret = PTR_ERR(host->ioaddr);
+		goto err;
+	}
+
+	/* Parse OF address directly to get the physical address for
+	 * DMA to our registers.
+	 */
+	regaddr_p = of_get_address(pdev->dev.of_node, 0, NULL, NULL);
+	if (!regaddr_p) {
+		dev_err(dev, "Can't get phys address\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	host->phys_addr = be32_to_cpup(regaddr_p);
+
+	host->dma_chan = NULL;
+	host->dma_desc = NULL;
+
+	host->dma_chan_rxtx = dma_request_slave_channel(dev, "rx-tx");
+
+	clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "could not get clk: %d\n", ret);
+		goto err;
+	}
+
+	host->max_clk = clk_get_rate(clk);
+
+	host->irq = platform_get_irq(pdev, 0);
+	if (host->irq <= 0) {
+		dev_err(dev, "get IRQ failed\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = mmc_of_parse(mmc);
+	if (ret)
+		goto err;
+
+	ret = bcm2835_add_host(host);
+	if (ret)
+		goto err;
+
+	platform_set_drvdata(pdev, host);
+
+	dev_dbg(dev, "%s -> OK\n", __func__);
+
+	return 0;
+
+err:
+	dev_dbg(dev, "%s -> err %d\n", __func__, ret);
+	mmc_free_host(mmc);
+
+	return ret;
+}
+
+static int bcm2835_remove(struct platform_device *pdev)
+{
+	struct bcm2835_host *host = platform_get_drvdata(pdev);
+
+	mmc_remove_host(host->mmc);
+
+	writel(SDVDD_POWER_OFF, host->ioaddr + SDVDD);
+
+	free_irq(host->irq, host);
+
+	cancel_work_sync(&host->dma_work);
+	cancel_delayed_work_sync(&host->timeout_work);
+
+	mmc_free_host(host->mmc);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id bcm2835_match[] = {
+	{ .compatible = "brcm,bcm2835-sdhost" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bcm2835_match);
+
+static struct platform_driver bcm2835_driver = {
+	.probe      = bcm2835_probe,
+	.remove     = bcm2835_remove,
+	.driver     = {
+		.name		= "sdhost-bcm2835",
+		.of_match_table	= bcm2835_match,
+	},
+};
+module_platform_driver(bcm2835_driver);
+
+MODULE_ALIAS("platform:sdhost-bcm2835");
+MODULE_DESCRIPTION("BCM2835 SDHost driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Phil Elwell");
diff --git a/drivers/mmc/host/cavium-octeon.c b/drivers/mmc/host/cavium-octeon.c
new file mode 100644
index 000000000000..772d0900026d
--- /dev/null
+++ b/drivers/mmc/host/cavium-octeon.c
@@ -0,0 +1,351 @@
+/*
+ * Driver for MMC and SSD cards for Cavium OCTEON SOCs.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012-2017 Cavium Inc.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/slot-gpio.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <asm/octeon/octeon.h>
+#include "cavium.h"
+
+#define CVMX_MIO_BOOT_CTL CVMX_ADD_IO_SEG(0x00011800000000D0ull)
+
+/*
+ * The l2c* functions below are used for the EMMC-17978 workaround.
+ *
+ * Due to a bug in the design of the MMC bus hardware, the 2nd to last
+ * cache block of a DMA read must be locked into the L2 Cache.
+ * Otherwise, data corruption may occur.
+ */
+static inline void *phys_to_ptr(u64 address)
+{
+	return (void *)(address | (1ull << 63)); /* XKPHYS */
+}
+
+/*
+ * Lock a single line into L2. The line is zeroed before locking
+ * to make sure no dram accesses are made.
+ */
+static void l2c_lock_line(u64 addr)
+{
+	char *addr_ptr = phys_to_ptr(addr);
+
+	asm volatile (
+		"cache 31, %[line]"	/* Unlock the line */
+		::[line] "m" (*addr_ptr));
+}
+
+/* Unlock a single line in the L2 cache. */
+static void l2c_unlock_line(u64 addr)
+{
+	char *addr_ptr = phys_to_ptr(addr);
+
+	asm volatile (
+		"cache 23, %[line]"	/* Unlock the line */
+		::[line] "m" (*addr_ptr));
+}
+
+/* Locks a memory region in the L2 cache. */
+static void l2c_lock_mem_region(u64 start, u64 len)
+{
+	u64 end;
+
+	/* Round start/end to cache line boundaries */
+	end = ALIGN(start + len - 1, CVMX_CACHE_LINE_SIZE);
+	start = ALIGN(start, CVMX_CACHE_LINE_SIZE);
+
+	while (start <= end) {
+		l2c_lock_line(start);
+		start += CVMX_CACHE_LINE_SIZE;
+	}
+	asm volatile("sync");
+}
+
+/* Unlock a memory region in the L2 cache. */
+static void l2c_unlock_mem_region(u64 start, u64 len)
+{
+	u64 end;
+
+	/* Round start/end to cache line boundaries */
+	end = ALIGN(start + len - 1, CVMX_CACHE_LINE_SIZE);
+	start = ALIGN(start, CVMX_CACHE_LINE_SIZE);
+
+	while (start <= end) {
+		l2c_unlock_line(start);
+		start += CVMX_CACHE_LINE_SIZE;
+	}
+}
+
+static void octeon_mmc_acquire_bus(struct cvm_mmc_host *host)
+{
+	if (!host->has_ciu3) {
+		down(&octeon_bootbus_sem);
+		/* For CN70XX, switch the MMC controller onto the bus. */
+		if (OCTEON_IS_MODEL(OCTEON_CN70XX))
+			writeq(0, (void __iomem *)CVMX_MIO_BOOT_CTL);
+	} else {
+		down(&host->mmc_serializer);
+	}
+}
+
+static void octeon_mmc_release_bus(struct cvm_mmc_host *host)
+{
+	if (!host->has_ciu3)
+		up(&octeon_bootbus_sem);
+	else
+		up(&host->mmc_serializer);
+}
+
+static void octeon_mmc_int_enable(struct cvm_mmc_host *host, u64 val)
+{
+	writeq(val, host->base + MIO_EMM_INT(host));
+	if (!host->dma_active || (host->dma_active && !host->has_ciu3))
+		writeq(val, host->base + MIO_EMM_INT_EN(host));
+}
+
+static void octeon_mmc_set_shared_power(struct cvm_mmc_host *host, int dir)
+{
+	if (dir == 0)
+		if (!atomic_dec_return(&host->shared_power_users))
+			gpiod_set_value_cansleep(host->global_pwr_gpiod, 0);
+	if (dir == 1)
+		if (atomic_inc_return(&host->shared_power_users) == 1)
+			gpiod_set_value_cansleep(host->global_pwr_gpiod, 1);
+}
+
+static void octeon_mmc_dmar_fixup(struct cvm_mmc_host *host,
+				  struct mmc_command *cmd,
+				  struct mmc_data *data,
+				  u64 addr)
+{
+	if (cmd->opcode != MMC_WRITE_MULTIPLE_BLOCK)
+		return;
+	if (data->blksz * data->blocks <= 1024)
+		return;
+
+	host->n_minus_one = addr + (data->blksz * data->blocks) - 1024;
+	l2c_lock_mem_region(host->n_minus_one, 512);
+}
+
+static void octeon_mmc_dmar_fixup_done(struct cvm_mmc_host *host)
+{
+	if (!host->n_minus_one)
+		return;
+	l2c_unlock_mem_region(host->n_minus_one, 512);
+	host->n_minus_one = 0;
+}
+
+static int octeon_mmc_probe(struct platform_device *pdev)
+{
+	struct device_node *cn, *node = pdev->dev.of_node;
+	struct cvm_mmc_host *host;
+	struct resource	*res;
+	void __iomem *base;
+	int mmc_irq[9];
+	int i, ret = 0;
+	u64 val;
+
+	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	spin_lock_init(&host->irq_handler_lock);
+	sema_init(&host->mmc_serializer, 1);
+
+	host->dev = &pdev->dev;
+	host->acquire_bus = octeon_mmc_acquire_bus;
+	host->release_bus = octeon_mmc_release_bus;
+	host->int_enable = octeon_mmc_int_enable;
+	host->set_shared_power = octeon_mmc_set_shared_power;
+	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) ||
+	    OCTEON_IS_MODEL(OCTEON_CNF7XXX)) {
+		host->dmar_fixup = octeon_mmc_dmar_fixup;
+		host->dmar_fixup_done = octeon_mmc_dmar_fixup_done;
+	}
+
+	host->sys_freq = octeon_get_io_clock_rate();
+
+	if (of_device_is_compatible(node, "cavium,octeon-7890-mmc")) {
+		host->big_dma_addr = true;
+		host->need_irq_handler_lock = true;
+		host->has_ciu3 = true;
+		host->use_sg = true;
+		/*
+		 * First seven are the EMM_INT bits 0..6, then two for
+		 * the EMM_DMA_INT bits
+		 */
+		for (i = 0; i < 9; i++) {
+			mmc_irq[i] = platform_get_irq(pdev, i);
+			if (mmc_irq[i] < 0)
+				return mmc_irq[i];
+
+			/* work around legacy u-boot device trees */
+			irq_set_irq_type(mmc_irq[i], IRQ_TYPE_EDGE_RISING);
+		}
+	} else {
+		host->big_dma_addr = false;
+		host->need_irq_handler_lock = false;
+		host->has_ciu3 = false;
+		/* First one is EMM second DMA */
+		for (i = 0; i < 2; i++) {
+			mmc_irq[i] = platform_get_irq(pdev, i);
+			if (mmc_irq[i] < 0)
+				return mmc_irq[i];
+		}
+	}
+
+	host->last_slot = -1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "Platform resource[0] is missing\n");
+		return -ENXIO;
+	}
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+	host->base = (void __iomem *)base;
+	host->reg_off = 0;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res) {
+		dev_err(&pdev->dev, "Platform resource[1] is missing\n");
+		return -EINVAL;
+	}
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+	host->dma_base = (void __iomem *)base;
+	/*
+	 * To keep the register addresses shared we intentionaly use
+	 * a negative offset here, first register used on Octeon therefore
+	 * starts at 0x20 (MIO_EMM_DMA_CFG).
+	 */
+	host->reg_off_dma = -0x20;
+
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret)
+		return ret;
+
+	/*
+	 * Clear out any pending interrupts that may be left over from
+	 * bootloader.
+	 */
+	val = readq(host->base + MIO_EMM_INT(host));
+	writeq(val, host->base + MIO_EMM_INT(host));
+
+	if (host->has_ciu3) {
+		/* Only CMD_DONE, DMA_DONE, CMD_ERR, DMA_ERR */
+		for (i = 1; i <= 4; i++) {
+			ret = devm_request_irq(&pdev->dev, mmc_irq[i],
+					       cvm_mmc_interrupt,
+					       0, cvm_mmc_irq_names[i], host);
+			if (ret < 0) {
+				dev_err(&pdev->dev, "Error: devm_request_irq %d\n",
+					mmc_irq[i]);
+				return ret;
+			}
+		}
+	} else {
+		ret = devm_request_irq(&pdev->dev, mmc_irq[0],
+				       cvm_mmc_interrupt, 0, KBUILD_MODNAME,
+				       host);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Error: devm_request_irq %d\n",
+				mmc_irq[0]);
+			return ret;
+		}
+	}
+
+	host->global_pwr_gpiod = devm_gpiod_get_optional(&pdev->dev,
+							 "power-gpios",
+							 GPIOD_OUT_HIGH);
+	if (IS_ERR(host->global_pwr_gpiod)) {
+		dev_err(&pdev->dev, "Invalid power GPIO\n");
+		return PTR_ERR(host->global_pwr_gpiod);
+	}
+
+	platform_set_drvdata(pdev, host);
+
+	i = 0;
+	for_each_child_of_node(node, cn) {
+		host->slot_pdev[i] =
+			of_platform_device_create(cn, NULL, &pdev->dev);
+		if (!host->slot_pdev[i]) {
+			i++;
+			continue;
+		}
+		ret = cvm_mmc_of_slot_probe(&host->slot_pdev[i]->dev, host);
+		if (ret) {
+			dev_err(&pdev->dev, "Error populating slots\n");
+			octeon_mmc_set_shared_power(host, 0);
+			return ret;
+		}
+		i++;
+	}
+	return 0;
+}
+
+static int octeon_mmc_remove(struct platform_device *pdev)
+{
+	struct cvm_mmc_host *host = platform_get_drvdata(pdev);
+	u64 dma_cfg;
+	int i;
+
+	for (i = 0; i < CAVIUM_MAX_MMC; i++)
+		if (host->slot[i])
+			cvm_mmc_of_slot_remove(host->slot[i]);
+
+	dma_cfg = readq(host->dma_base + MIO_EMM_DMA_CFG(host));
+	dma_cfg &= ~MIO_EMM_DMA_CFG_EN;
+	writeq(dma_cfg, host->dma_base + MIO_EMM_DMA_CFG(host));
+
+	octeon_mmc_set_shared_power(host, 0);
+	return 0;
+}
+
+static const struct of_device_id octeon_mmc_match[] = {
+	{
+		.compatible = "cavium,octeon-6130-mmc",
+	},
+	{
+		.compatible = "cavium,octeon-7890-mmc",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, octeon_mmc_match);
+
+static struct platform_driver octeon_mmc_driver = {
+	.probe		= octeon_mmc_probe,
+	.remove		= octeon_mmc_remove,
+	.driver		= {
+		.name	= KBUILD_MODNAME,
+		.of_match_table = octeon_mmc_match,
+	},
+};
+
+static int __init octeon_mmc_init(void)
+{
+	return platform_driver_register(&octeon_mmc_driver);
+}
+
+static void __exit octeon_mmc_cleanup(void)
+{
+	platform_driver_unregister(&octeon_mmc_driver);
+}
+
+module_init(octeon_mmc_init);
+module_exit(octeon_mmc_cleanup);
+
+MODULE_AUTHOR("Cavium Inc. <support@cavium.com>");
+MODULE_DESCRIPTION("Low-level driver for Cavium OCTEON MMC/SSD card");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mmc/host/cavium-thunderx.c b/drivers/mmc/host/cavium-thunderx.c
new file mode 100644
index 000000000000..fe3d77267cd6
--- /dev/null
+++ b/drivers/mmc/host/cavium-thunderx.c
@@ -0,0 +1,187 @@
+/*
+ * Driver for MMC and SSD cards for Cavium ThunderX SOCs.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2016 Cavium Inc.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/mmc/mmc.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include "cavium.h"
+
+static void thunder_mmc_acquire_bus(struct cvm_mmc_host *host)
+{
+	down(&host->mmc_serializer);
+}
+
+static void thunder_mmc_release_bus(struct cvm_mmc_host *host)
+{
+	up(&host->mmc_serializer);
+}
+
+static void thunder_mmc_int_enable(struct cvm_mmc_host *host, u64 val)
+{
+	writeq(val, host->base + MIO_EMM_INT(host));
+	writeq(val, host->base + MIO_EMM_INT_EN_SET(host));
+}
+
+static int thunder_mmc_register_interrupts(struct cvm_mmc_host *host,
+					   struct pci_dev *pdev)
+{
+	int nvec, ret, i;
+
+	nvec = pci_alloc_irq_vectors(pdev, 1, 9, PCI_IRQ_MSIX);
+	if (nvec < 0)
+		return nvec;
+
+	/* register interrupts */
+	for (i = 0; i < nvec; i++) {
+		ret = devm_request_irq(&pdev->dev, pci_irq_vector(pdev, i),
+				       cvm_mmc_interrupt,
+				       0, cvm_mmc_irq_names[i], host);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int thunder_mmc_probe(struct pci_dev *pdev,
+			     const struct pci_device_id *id)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	struct device_node *child_node;
+	struct cvm_mmc_host *host;
+	int ret, i = 0;
+
+	host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, host);
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	ret = pci_request_regions(pdev, KBUILD_MODNAME);
+	if (ret)
+		return ret;
+
+	host->base = pcim_iomap(pdev, 0, pci_resource_len(pdev, 0));
+	if (!host->base)
+		return -EINVAL;
+
+	/* On ThunderX these are identical */
+	host->dma_base = host->base;
+
+	host->reg_off = 0x2000;
+	host->reg_off_dma = 0x160;
+
+	host->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(host->clk))
+		return PTR_ERR(host->clk);
+
+	ret = clk_prepare_enable(host->clk);
+	if (ret)
+		return ret;
+	host->sys_freq = clk_get_rate(host->clk);
+
+	spin_lock_init(&host->irq_handler_lock);
+	sema_init(&host->mmc_serializer, 1);
+
+	host->dev = dev;
+	host->acquire_bus = thunder_mmc_acquire_bus;
+	host->release_bus = thunder_mmc_release_bus;
+	host->int_enable = thunder_mmc_int_enable;
+
+	host->use_sg = true;
+	host->big_dma_addr = true;
+	host->need_irq_handler_lock = true;
+	host->last_slot = -1;
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(48));
+	if (ret)
+		goto error;
+
+	/*
+	 * Clear out any pending interrupts that may be left over from
+	 * bootloader. Writing 1 to the bits clears them.
+	 */
+	writeq(127, host->base + MIO_EMM_INT_EN(host));
+	writeq(3, host->base + MIO_EMM_DMA_INT_ENA_W1C(host));
+	/* Clear DMA FIFO */
+	writeq(BIT_ULL(16), host->base + MIO_EMM_DMA_FIFO_CFG(host));
+
+	ret = thunder_mmc_register_interrupts(host, pdev);
+	if (ret)
+		goto error;
+
+	for_each_child_of_node(node, child_node) {
+		/*
+		 * mmc_of_parse and devm* require one device per slot.
+		 * Create a dummy device per slot and set the node pointer to
+		 * the slot. The easiest way to get this is using
+		 * of_platform_device_create.
+		 */
+		if (of_device_is_compatible(child_node, "mmc-slot")) {
+			host->slot_pdev[i] = of_platform_device_create(child_node, NULL,
+								       &pdev->dev);
+			if (!host->slot_pdev[i])
+				continue;
+
+			ret = cvm_mmc_of_slot_probe(&host->slot_pdev[i]->dev, host);
+			if (ret)
+				goto error;
+		}
+		i++;
+	}
+	dev_info(dev, "probed\n");
+	return 0;
+
+error:
+	clk_disable_unprepare(host->clk);
+	return ret;
+}
+
+static void thunder_mmc_remove(struct pci_dev *pdev)
+{
+	struct cvm_mmc_host *host = pci_get_drvdata(pdev);
+	u64 dma_cfg;
+	int i;
+
+	for (i = 0; i < CAVIUM_MAX_MMC; i++)
+		if (host->slot[i])
+			cvm_mmc_of_slot_remove(host->slot[i]);
+
+	dma_cfg = readq(host->dma_base + MIO_EMM_DMA_CFG(host));
+	dma_cfg &= ~MIO_EMM_DMA_CFG_EN;
+	writeq(dma_cfg, host->dma_base + MIO_EMM_DMA_CFG(host));
+
+	clk_disable_unprepare(host->clk);
+}
+
+static const struct pci_device_id thunder_mmc_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, 0xa010) },
+	{ 0, }  /* end of table */
+};
+
+static struct pci_driver thunder_mmc_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = thunder_mmc_id_table,
+	.probe = thunder_mmc_probe,
+	.remove = thunder_mmc_remove,
+};
+
+module_pci_driver(thunder_mmc_driver);
+
+MODULE_AUTHOR("Cavium Inc.");
+MODULE_DESCRIPTION("Cavium ThunderX eMMC Driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pci, thunder_mmc_id_table);
diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c
new file mode 100644
index 000000000000..58b51ba6aabd
--- /dev/null
+++ b/drivers/mmc/host/cavium.c
@@ -0,0 +1,1090 @@
+/*
+ * Shared part of driver for MMC/SDHC controller on Cavium OCTEON and
+ * ThunderX SOCs.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012-2017 Cavium Inc.
+ * Authors:
+ *   David Daney <david.daney@cavium.com>
+ *   Peter Swain <pswain@cavium.com>
+ *   Steven J. Hill <steven.hill@cavium.com>
+ *   Jan Glauber <jglauber@cavium.com>
+ */
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/dma-direction.h>
+#include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/slot-gpio.h>
+#include <linux/module.h>
+#include <linux/regulator/consumer.h>
+#include <linux/scatterlist.h>
+#include <linux/time.h>
+
+#include "cavium.h"
+
+const char *cvm_mmc_irq_names[] = {
+	"MMC Buffer",
+	"MMC Command",
+	"MMC DMA",
+	"MMC Command Error",
+	"MMC DMA Error",
+	"MMC Switch",
+	"MMC Switch Error",
+	"MMC DMA int Fifo",
+	"MMC DMA int",
+};
+
+/*
+ * The Cavium MMC host hardware assumes that all commands have fixed
+ * command and response types.  These are correct if MMC devices are
+ * being used.  However, non-MMC devices like SD use command and
+ * response types that are unexpected by the host hardware.
+ *
+ * The command and response types can be overridden by supplying an
+ * XOR value that is applied to the type.  We calculate the XOR value
+ * from the values in this table and the flags passed from the MMC
+ * core.
+ */
+static struct cvm_mmc_cr_type cvm_mmc_cr_types[] = {
+	{0, 0},		/* CMD0 */
+	{0, 3},		/* CMD1 */
+	{0, 2},		/* CMD2 */
+	{0, 1},		/* CMD3 */
+	{0, 0},		/* CMD4 */
+	{0, 1},		/* CMD5 */
+	{0, 1},		/* CMD6 */
+	{0, 1},		/* CMD7 */
+	{1, 1},		/* CMD8 */
+	{0, 2},		/* CMD9 */
+	{0, 2},		/* CMD10 */
+	{1, 1},		/* CMD11 */
+	{0, 1},		/* CMD12 */
+	{0, 1},		/* CMD13 */
+	{1, 1},		/* CMD14 */
+	{0, 0},		/* CMD15 */
+	{0, 1},		/* CMD16 */
+	{1, 1},		/* CMD17 */
+	{1, 1},		/* CMD18 */
+	{3, 1},		/* CMD19 */
+	{2, 1},		/* CMD20 */
+	{0, 0},		/* CMD21 */
+	{0, 0},		/* CMD22 */
+	{0, 1},		/* CMD23 */
+	{2, 1},		/* CMD24 */
+	{2, 1},		/* CMD25 */
+	{2, 1},		/* CMD26 */
+	{2, 1},		/* CMD27 */
+	{0, 1},		/* CMD28 */
+	{0, 1},		/* CMD29 */
+	{1, 1},		/* CMD30 */
+	{1, 1},		/* CMD31 */
+	{0, 0},		/* CMD32 */
+	{0, 0},		/* CMD33 */
+	{0, 0},		/* CMD34 */
+	{0, 1},		/* CMD35 */
+	{0, 1},		/* CMD36 */
+	{0, 0},		/* CMD37 */
+	{0, 1},		/* CMD38 */
+	{0, 4},		/* CMD39 */
+	{0, 5},		/* CMD40 */
+	{0, 0},		/* CMD41 */
+	{2, 1},		/* CMD42 */
+	{0, 0},		/* CMD43 */
+	{0, 0},		/* CMD44 */
+	{0, 0},		/* CMD45 */
+	{0, 0},		/* CMD46 */
+	{0, 0},		/* CMD47 */
+	{0, 0},		/* CMD48 */
+	{0, 0},		/* CMD49 */
+	{0, 0},		/* CMD50 */
+	{0, 0},		/* CMD51 */
+	{0, 0},		/* CMD52 */
+	{0, 0},		/* CMD53 */
+	{0, 0},		/* CMD54 */
+	{0, 1},		/* CMD55 */
+	{0xff, 0xff},	/* CMD56 */
+	{0, 0},		/* CMD57 */
+	{0, 0},		/* CMD58 */
+	{0, 0},		/* CMD59 */
+	{0, 0},		/* CMD60 */
+	{0, 0},		/* CMD61 */
+	{0, 0},		/* CMD62 */
+	{0, 0}		/* CMD63 */
+};
+
+static struct cvm_mmc_cr_mods cvm_mmc_get_cr_mods(struct mmc_command *cmd)
+{
+	struct cvm_mmc_cr_type *cr;
+	u8 hardware_ctype, hardware_rtype;
+	u8 desired_ctype = 0, desired_rtype = 0;
+	struct cvm_mmc_cr_mods r;
+
+	cr = cvm_mmc_cr_types + (cmd->opcode & 0x3f);
+	hardware_ctype = cr->ctype;
+	hardware_rtype = cr->rtype;
+	if (cmd->opcode == MMC_GEN_CMD)
+		hardware_ctype = (cmd->arg & 1) ? 1 : 2;
+
+	switch (mmc_cmd_type(cmd)) {
+	case MMC_CMD_ADTC:
+		desired_ctype = (cmd->data->flags & MMC_DATA_WRITE) ? 2 : 1;
+		break;
+	case MMC_CMD_AC:
+	case MMC_CMD_BC:
+	case MMC_CMD_BCR:
+		desired_ctype = 0;
+		break;
+	}
+
+	switch (mmc_resp_type(cmd)) {
+	case MMC_RSP_NONE:
+		desired_rtype = 0;
+		break;
+	case MMC_RSP_R1:/* MMC_RSP_R5, MMC_RSP_R6, MMC_RSP_R7 */
+	case MMC_RSP_R1B:
+		desired_rtype = 1;
+		break;
+	case MMC_RSP_R2:
+		desired_rtype = 2;
+		break;
+	case MMC_RSP_R3: /* MMC_RSP_R4 */
+		desired_rtype = 3;
+		break;
+	}
+	r.ctype_xor = desired_ctype ^ hardware_ctype;
+	r.rtype_xor = desired_rtype ^ hardware_rtype;
+	return r;
+}
+
+static void check_switch_errors(struct cvm_mmc_host *host)
+{
+	u64 emm_switch;
+
+	emm_switch = readq(host->base + MIO_EMM_SWITCH(host));
+	if (emm_switch & MIO_EMM_SWITCH_ERR0)
+		dev_err(host->dev, "Switch power class error\n");
+	if (emm_switch & MIO_EMM_SWITCH_ERR1)
+		dev_err(host->dev, "Switch hs timing error\n");
+	if (emm_switch & MIO_EMM_SWITCH_ERR2)
+		dev_err(host->dev, "Switch bus width error\n");
+}
+
+static void clear_bus_id(u64 *reg)
+{
+	u64 bus_id_mask = GENMASK_ULL(61, 60);
+
+	*reg &= ~bus_id_mask;
+}
+
+static void set_bus_id(u64 *reg, int bus_id)
+{
+	clear_bus_id(reg);
+	*reg |= FIELD_PREP(GENMASK(61, 60), bus_id);
+}
+
+static int get_bus_id(u64 reg)
+{
+	return FIELD_GET(GENMASK_ULL(61, 60), reg);
+}
+
+/*
+ * We never set the switch_exe bit since that would interfere
+ * with the commands send by the MMC core.
+ */
+static void do_switch(struct cvm_mmc_host *host, u64 emm_switch)
+{
+	int retries = 100;
+	u64 rsp_sts;
+	int bus_id;
+
+	/*
+	 * Modes setting only taken from slot 0. Work around that hardware
+	 * issue by first switching to slot 0.
+	 */
+	bus_id = get_bus_id(emm_switch);
+	clear_bus_id(&emm_switch);
+	writeq(emm_switch, host->base + MIO_EMM_SWITCH(host));
+
+	set_bus_id(&emm_switch, bus_id);
+	writeq(emm_switch, host->base + MIO_EMM_SWITCH(host));
+
+	/* wait for the switch to finish */
+	do {
+		rsp_sts = readq(host->base + MIO_EMM_RSP_STS(host));
+		if (!(rsp_sts & MIO_EMM_RSP_STS_SWITCH_VAL))
+			break;
+		udelay(10);
+	} while (--retries);
+
+	check_switch_errors(host);
+}
+
+static bool switch_val_changed(struct cvm_mmc_slot *slot, u64 new_val)
+{
+	/* Match BUS_ID, HS_TIMING, BUS_WIDTH, POWER_CLASS, CLK_HI, CLK_LO */
+	u64 match = 0x3001070fffffffffull;
+
+	return (slot->cached_switch & match) != (new_val & match);
+}
+
+static void set_wdog(struct cvm_mmc_slot *slot, unsigned int ns)
+{
+	u64 timeout;
+
+	if (!slot->clock)
+		return;
+
+	if (ns)
+		timeout = (slot->clock * ns) / NSEC_PER_SEC;
+	else
+		timeout = (slot->clock * 850ull) / 1000ull;
+	writeq(timeout, slot->host->base + MIO_EMM_WDOG(slot->host));
+}
+
+static void cvm_mmc_reset_bus(struct cvm_mmc_slot *slot)
+{
+	struct cvm_mmc_host *host = slot->host;
+	u64 emm_switch, wdog;
+
+	emm_switch = readq(slot->host->base + MIO_EMM_SWITCH(host));
+	emm_switch &= ~(MIO_EMM_SWITCH_EXE | MIO_EMM_SWITCH_ERR0 |
+			MIO_EMM_SWITCH_ERR1 | MIO_EMM_SWITCH_ERR2);
+	set_bus_id(&emm_switch, slot->bus_id);
+
+	wdog = readq(slot->host->base + MIO_EMM_WDOG(host));
+	do_switch(slot->host, emm_switch);
+
+	slot->cached_switch = emm_switch;
+
+	msleep(20);
+
+	writeq(wdog, slot->host->base + MIO_EMM_WDOG(host));
+}
+
+/* Switch to another slot if needed */
+static void cvm_mmc_switch_to(struct cvm_mmc_slot *slot)
+{
+	struct cvm_mmc_host *host = slot->host;
+	struct cvm_mmc_slot *old_slot;
+	u64 emm_sample, emm_switch;
+
+	if (slot->bus_id == host->last_slot)
+		return;
+
+	if (host->last_slot >= 0 && host->slot[host->last_slot]) {
+		old_slot = host->slot[host->last_slot];
+		old_slot->cached_switch = readq(host->base + MIO_EMM_SWITCH(host));
+		old_slot->cached_rca = readq(host->base + MIO_EMM_RCA(host));
+	}
+
+	writeq(slot->cached_rca, host->base + MIO_EMM_RCA(host));
+	emm_switch = slot->cached_switch;
+	set_bus_id(&emm_switch, slot->bus_id);
+	do_switch(host, emm_switch);
+
+	emm_sample = FIELD_PREP(MIO_EMM_SAMPLE_CMD_CNT, slot->cmd_cnt) |
+		     FIELD_PREP(MIO_EMM_SAMPLE_DAT_CNT, slot->dat_cnt);
+	writeq(emm_sample, host->base + MIO_EMM_SAMPLE(host));
+
+	host->last_slot = slot->bus_id;
+}
+
+static void do_read(struct cvm_mmc_host *host, struct mmc_request *req,
+		    u64 dbuf)
+{
+	struct sg_mapping_iter *smi = &host->smi;
+	int data_len = req->data->blocks * req->data->blksz;
+	int bytes_xfered, shift = -1;
+	u64 dat = 0;
+
+	/* Auto inc from offset zero */
+	writeq((0x10000 | (dbuf << 6)), host->base + MIO_EMM_BUF_IDX(host));
+
+	for (bytes_xfered = 0; bytes_xfered < data_len;) {
+		if (smi->consumed >= smi->length) {
+			if (!sg_miter_next(smi))
+				break;
+			smi->consumed = 0;
+		}
+
+		if (shift < 0) {
+			dat = readq(host->base + MIO_EMM_BUF_DAT(host));
+			shift = 56;
+		}
+
+		while (smi->consumed < smi->length && shift >= 0) {
+			((u8 *)smi->addr)[smi->consumed] = (dat >> shift) & 0xff;
+			bytes_xfered++;
+			smi->consumed++;
+			shift -= 8;
+		}
+	}
+
+	sg_miter_stop(smi);
+	req->data->bytes_xfered = bytes_xfered;
+	req->data->error = 0;
+}
+
+static void do_write(struct mmc_request *req)
+{
+	req->data->bytes_xfered = req->data->blocks * req->data->blksz;
+	req->data->error = 0;
+}
+
+static void set_cmd_response(struct cvm_mmc_host *host, struct mmc_request *req,
+			     u64 rsp_sts)
+{
+	u64 rsp_hi, rsp_lo;
+
+	if (!(rsp_sts & MIO_EMM_RSP_STS_RSP_VAL))
+		return;
+
+	rsp_lo = readq(host->base + MIO_EMM_RSP_LO(host));
+
+	switch (FIELD_GET(MIO_EMM_RSP_STS_RSP_TYPE, rsp_sts)) {
+	case 1:
+	case 3:
+		req->cmd->resp[0] = (rsp_lo >> 8) & 0xffffffff;
+		req->cmd->resp[1] = 0;
+		req->cmd->resp[2] = 0;
+		req->cmd->resp[3] = 0;
+		break;
+	case 2:
+		req->cmd->resp[3] = rsp_lo & 0xffffffff;
+		req->cmd->resp[2] = (rsp_lo >> 32) & 0xffffffff;
+		rsp_hi = readq(host->base + MIO_EMM_RSP_HI(host));
+		req->cmd->resp[1] = rsp_hi & 0xffffffff;
+		req->cmd->resp[0] = (rsp_hi >> 32) & 0xffffffff;
+		break;
+	}
+}
+
+static int get_dma_dir(struct mmc_data *data)
+{
+	return (data->flags & MMC_DATA_WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+}
+
+static int finish_dma_single(struct cvm_mmc_host *host, struct mmc_data *data)
+{
+	data->bytes_xfered = data->blocks * data->blksz;
+	data->error = 0;
+	return 1;
+}
+
+static int finish_dma_sg(struct cvm_mmc_host *host, struct mmc_data *data)
+{
+	u64 fifo_cfg;
+	int count;
+
+	/* Check if there are any pending requests left */
+	fifo_cfg = readq(host->dma_base + MIO_EMM_DMA_FIFO_CFG(host));
+	count = FIELD_GET(MIO_EMM_DMA_FIFO_CFG_COUNT, fifo_cfg);
+	if (count)
+		dev_err(host->dev, "%u requests still pending\n", count);
+
+	data->bytes_xfered = data->blocks * data->blksz;
+	data->error = 0;
+
+	/* Clear and disable FIFO */
+	writeq(BIT_ULL(16), host->dma_base + MIO_EMM_DMA_FIFO_CFG(host));
+	dma_unmap_sg(host->dev, data->sg, data->sg_len, get_dma_dir(data));
+	return 1;
+}
+
+static int finish_dma(struct cvm_mmc_host *host, struct mmc_data *data)
+{
+	if (host->use_sg && data->sg_len > 1)
+		return finish_dma_sg(host, data);
+	else
+		return finish_dma_single(host, data);
+}
+
+static int check_status(u64 rsp_sts)
+{
+	if (rsp_sts & MIO_EMM_RSP_STS_RSP_BAD_STS ||
+	    rsp_sts & MIO_EMM_RSP_STS_RSP_CRC_ERR ||
+	    rsp_sts & MIO_EMM_RSP_STS_BLK_CRC_ERR)
+		return -EILSEQ;
+	if (rsp_sts & MIO_EMM_RSP_STS_RSP_TIMEOUT ||
+	    rsp_sts & MIO_EMM_RSP_STS_BLK_TIMEOUT)
+		return -ETIMEDOUT;
+	if (rsp_sts & MIO_EMM_RSP_STS_DBUF_ERR)
+		return -EIO;
+	return 0;
+}
+
+/* Try to clean up failed DMA. */
+static void cleanup_dma(struct cvm_mmc_host *host, u64 rsp_sts)
+{
+	u64 emm_dma;
+
+	emm_dma = readq(host->base + MIO_EMM_DMA(host));
+	emm_dma |= FIELD_PREP(MIO_EMM_DMA_VAL, 1) |
+		   FIELD_PREP(MIO_EMM_DMA_DAT_NULL, 1);
+	set_bus_id(&emm_dma, get_bus_id(rsp_sts));
+	writeq(emm_dma, host->base + MIO_EMM_DMA(host));
+}
+
+irqreturn_t cvm_mmc_interrupt(int irq, void *dev_id)
+{
+	struct cvm_mmc_host *host = dev_id;
+	struct mmc_request *req;
+	unsigned long flags = 0;
+	u64 emm_int, rsp_sts;
+	bool host_done;
+
+	if (host->need_irq_handler_lock)
+		spin_lock_irqsave(&host->irq_handler_lock, flags);
+	else
+		__acquire(&host->irq_handler_lock);
+
+	/* Clear interrupt bits (write 1 clears ). */
+	emm_int = readq(host->base + MIO_EMM_INT(host));
+	writeq(emm_int, host->base + MIO_EMM_INT(host));
+
+	if (emm_int & MIO_EMM_INT_SWITCH_ERR)
+		check_switch_errors(host);
+
+	req = host->current_req;
+	if (!req)
+		goto out;
+
+	rsp_sts = readq(host->base + MIO_EMM_RSP_STS(host));
+	/*
+	 * dma_val set means DMA is still in progress. Don't touch
+	 * the request and wait for the interrupt indicating that
+	 * the DMA is finished.
+	 */
+	if ((rsp_sts & MIO_EMM_RSP_STS_DMA_VAL) && host->dma_active)
+		goto out;
+
+	if (!host->dma_active && req->data &&
+	    (emm_int & MIO_EMM_INT_BUF_DONE)) {
+		unsigned int type = (rsp_sts >> 7) & 3;
+
+		if (type == 1)
+			do_read(host, req, rsp_sts & MIO_EMM_RSP_STS_DBUF);
+		else if (type == 2)
+			do_write(req);
+	}
+
+	host_done = emm_int & MIO_EMM_INT_CMD_DONE ||
+		    emm_int & MIO_EMM_INT_DMA_DONE ||
+		    emm_int & MIO_EMM_INT_CMD_ERR  ||
+		    emm_int & MIO_EMM_INT_DMA_ERR;
+
+	if (!(host_done && req->done))
+		goto no_req_done;
+
+	req->cmd->error = check_status(rsp_sts);
+
+	if (host->dma_active && req->data)
+		if (!finish_dma(host, req->data))
+			goto no_req_done;
+
+	set_cmd_response(host, req, rsp_sts);
+	if ((emm_int & MIO_EMM_INT_DMA_ERR) &&
+	    (rsp_sts & MIO_EMM_RSP_STS_DMA_PEND))
+		cleanup_dma(host, rsp_sts);
+
+	host->current_req = NULL;
+	req->done(req);
+
+no_req_done:
+	if (host->dmar_fixup_done)
+		host->dmar_fixup_done(host);
+	if (host_done)
+		host->release_bus(host);
+out:
+	if (host->need_irq_handler_lock)
+		spin_unlock_irqrestore(&host->irq_handler_lock, flags);
+	else
+		__release(&host->irq_handler_lock);
+	return IRQ_RETVAL(emm_int != 0);
+}
+
+/*
+ * Program DMA_CFG and if needed DMA_ADR.
+ * Returns 0 on error, DMA address otherwise.
+ */
+static u64 prepare_dma_single(struct cvm_mmc_host *host, struct mmc_data *data)
+{
+	u64 dma_cfg, addr;
+	int count, rw;
+
+	count = dma_map_sg(host->dev, data->sg, data->sg_len,
+			   get_dma_dir(data));
+	if (!count)
+		return 0;
+
+	rw = (data->flags & MMC_DATA_WRITE) ? 1 : 0;
+	dma_cfg = FIELD_PREP(MIO_EMM_DMA_CFG_EN, 1) |
+		  FIELD_PREP(MIO_EMM_DMA_CFG_RW, rw);
+#ifdef __LITTLE_ENDIAN
+	dma_cfg |= FIELD_PREP(MIO_EMM_DMA_CFG_ENDIAN, 1);
+#endif
+	dma_cfg |= FIELD_PREP(MIO_EMM_DMA_CFG_SIZE,
+			      (sg_dma_len(&data->sg[0]) / 8) - 1);
+
+	addr = sg_dma_address(&data->sg[0]);
+	if (!host->big_dma_addr)
+		dma_cfg |= FIELD_PREP(MIO_EMM_DMA_CFG_ADR, addr);
+	writeq(dma_cfg, host->dma_base + MIO_EMM_DMA_CFG(host));
+
+	pr_debug("[%s] sg_dma_len: %u  total sg_elem: %d\n",
+		 (rw) ? "W" : "R", sg_dma_len(&data->sg[0]), count);
+
+	if (host->big_dma_addr)
+		writeq(addr, host->dma_base + MIO_EMM_DMA_ADR(host));
+	return addr;
+}
+
+/*
+ * Queue complete sg list into the FIFO.
+ * Returns 0 on error, 1 otherwise.
+ */
+static u64 prepare_dma_sg(struct cvm_mmc_host *host, struct mmc_data *data)
+{
+	struct scatterlist *sg;
+	u64 fifo_cmd, addr;
+	int count, i, rw;
+
+	count = dma_map_sg(host->dev, data->sg, data->sg_len,
+			   get_dma_dir(data));
+	if (!count)
+		return 0;
+	if (count > 16)
+		goto error;
+
+	/* Enable FIFO by removing CLR bit */
+	writeq(0, host->dma_base + MIO_EMM_DMA_FIFO_CFG(host));
+
+	for_each_sg(data->sg, sg, count, i) {
+		/* Program DMA address */
+		addr = sg_dma_address(sg);
+		if (addr & 7)
+			goto error;
+		writeq(addr, host->dma_base + MIO_EMM_DMA_FIFO_ADR(host));
+
+		/*
+		 * If we have scatter-gather support we also have an extra
+		 * register for the DMA addr, so no need to check
+		 * host->big_dma_addr here.
+		 */
+		rw = (data->flags & MMC_DATA_WRITE) ? 1 : 0;
+		fifo_cmd = FIELD_PREP(MIO_EMM_DMA_FIFO_CMD_RW, rw);
+
+		/* enable interrupts on the last element */
+		fifo_cmd |= FIELD_PREP(MIO_EMM_DMA_FIFO_CMD_INTDIS,
+				       (i + 1 == count) ? 0 : 1);
+
+#ifdef __LITTLE_ENDIAN
+		fifo_cmd |= FIELD_PREP(MIO_EMM_DMA_FIFO_CMD_ENDIAN, 1);
+#endif
+		fifo_cmd |= FIELD_PREP(MIO_EMM_DMA_FIFO_CMD_SIZE,
+				       sg_dma_len(sg) / 8 - 1);
+		/*
+		 * The write copies the address and the command to the FIFO
+		 * and increments the FIFO's COUNT field.
+		 */
+		writeq(fifo_cmd, host->dma_base + MIO_EMM_DMA_FIFO_CMD(host));
+		pr_debug("[%s] sg_dma_len: %u  sg_elem: %d/%d\n",
+			 (rw) ? "W" : "R", sg_dma_len(sg), i, count);
+	}
+
+	/*
+	 * In difference to prepare_dma_single we don't return the
+	 * address here, as it would not make sense for scatter-gather.
+	 * The dma fixup is only required on models that don't support
+	 * scatter-gather, so that is not a problem.
+	 */
+	return 1;
+
+error:
+	WARN_ON_ONCE(1);
+	dma_unmap_sg(host->dev, data->sg, data->sg_len, get_dma_dir(data));
+	/* Disable FIFO */
+	writeq(BIT_ULL(16), host->dma_base + MIO_EMM_DMA_FIFO_CFG(host));
+	return 0;
+}
+
+static u64 prepare_dma(struct cvm_mmc_host *host, struct mmc_data *data)
+{
+	if (host->use_sg && data->sg_len > 1)
+		return prepare_dma_sg(host, data);
+	else
+		return prepare_dma_single(host, data);
+}
+
+static u64 prepare_ext_dma(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct cvm_mmc_slot *slot = mmc_priv(mmc);
+	u64 emm_dma;
+
+	emm_dma = FIELD_PREP(MIO_EMM_DMA_VAL, 1) |
+		  FIELD_PREP(MIO_EMM_DMA_SECTOR,
+			     mmc_card_is_blockaddr(mmc->card) ? 1 : 0) |
+		  FIELD_PREP(MIO_EMM_DMA_RW,
+			     (mrq->data->flags & MMC_DATA_WRITE) ? 1 : 0) |
+		  FIELD_PREP(MIO_EMM_DMA_BLOCK_CNT, mrq->data->blocks) |
+		  FIELD_PREP(MIO_EMM_DMA_CARD_ADDR, mrq->cmd->arg);
+	set_bus_id(&emm_dma, slot->bus_id);
+
+	if (mmc_card_mmc(mmc->card) || (mmc_card_sd(mmc->card) &&
+	    (mmc->card->scr.cmds & SD_SCR_CMD23_SUPPORT)))
+		emm_dma |= FIELD_PREP(MIO_EMM_DMA_MULTI, 1);
+
+	pr_debug("[%s] blocks: %u  multi: %d\n",
+		(emm_dma & MIO_EMM_DMA_RW) ? "W" : "R",
+		 mrq->data->blocks, (emm_dma & MIO_EMM_DMA_MULTI) ? 1 : 0);
+	return emm_dma;
+}
+
+static void cvm_mmc_dma_request(struct mmc_host *mmc,
+				struct mmc_request *mrq)
+{
+	struct cvm_mmc_slot *slot = mmc_priv(mmc);
+	struct cvm_mmc_host *host = slot->host;
+	struct mmc_data *data;
+	u64 emm_dma, addr;
+
+	if (!mrq->data || !mrq->data->sg || !mrq->data->sg_len ||
+	    !mrq->stop || mrq->stop->opcode != MMC_STOP_TRANSMISSION) {
+		dev_err(&mmc->card->dev,
+			"Error: cmv_mmc_dma_request no data\n");
+		goto error;
+	}
+
+	cvm_mmc_switch_to(slot);
+
+	data = mrq->data;
+	pr_debug("DMA request  blocks: %d  block_size: %d  total_size: %d\n",
+		 data->blocks, data->blksz, data->blocks * data->blksz);
+	if (data->timeout_ns)
+		set_wdog(slot, data->timeout_ns);
+
+	WARN_ON(host->current_req);
+	host->current_req = mrq;
+
+	emm_dma = prepare_ext_dma(mmc, mrq);
+	addr = prepare_dma(host, data);
+	if (!addr) {
+		dev_err(host->dev, "prepare_dma failed\n");
+		goto error;
+	}
+
+	host->dma_active = true;
+	host->int_enable(host, MIO_EMM_INT_CMD_ERR | MIO_EMM_INT_DMA_DONE |
+			 MIO_EMM_INT_DMA_ERR);
+
+	if (host->dmar_fixup)
+		host->dmar_fixup(host, mrq->cmd, data, addr);
+
+	/*
+	 * If we have a valid SD card in the slot, we set the response
+	 * bit mask to check for CRC errors and timeouts only.
+	 * Otherwise, use the default power reset value.
+	 */
+	if (mmc_card_sd(mmc->card))
+		writeq(0x00b00000ull, host->base + MIO_EMM_STS_MASK(host));
+	else
+		writeq(0xe4390080ull, host->base + MIO_EMM_STS_MASK(host));
+	writeq(emm_dma, host->base + MIO_EMM_DMA(host));
+	return;
+
+error:
+	mrq->cmd->error = -EINVAL;
+	if (mrq->done)
+		mrq->done(mrq);
+	host->release_bus(host);
+}
+
+static void do_read_request(struct cvm_mmc_host *host, struct mmc_request *mrq)
+{
+	sg_miter_start(&host->smi, mrq->data->sg, mrq->data->sg_len,
+		       SG_MITER_ATOMIC | SG_MITER_TO_SG);
+}
+
+static void do_write_request(struct cvm_mmc_host *host, struct mmc_request *mrq)
+{
+	unsigned int data_len = mrq->data->blocks * mrq->data->blksz;
+	struct sg_mapping_iter *smi = &host->smi;
+	unsigned int bytes_xfered;
+	int shift = 56;
+	u64 dat = 0;
+
+	/* Copy data to the xmit buffer before issuing the command. */
+	sg_miter_start(smi, mrq->data->sg, mrq->data->sg_len, SG_MITER_FROM_SG);
+
+	/* Auto inc from offset zero, dbuf zero */
+	writeq(0x10000ull, host->base + MIO_EMM_BUF_IDX(host));
+
+	for (bytes_xfered = 0; bytes_xfered < data_len;) {
+		if (smi->consumed >= smi->length) {
+			if (!sg_miter_next(smi))
+				break;
+			smi->consumed = 0;
+		}
+
+		while (smi->consumed < smi->length && shift >= 0) {
+			dat |= (u64)((u8 *)smi->addr)[smi->consumed] << shift;
+			bytes_xfered++;
+			smi->consumed++;
+			shift -= 8;
+		}
+
+		if (shift < 0) {
+			writeq(dat, host->base + MIO_EMM_BUF_DAT(host));
+			shift = 56;
+			dat = 0;
+		}
+	}
+	sg_miter_stop(smi);
+}
+
+static void cvm_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct cvm_mmc_slot *slot = mmc_priv(mmc);
+	struct cvm_mmc_host *host = slot->host;
+	struct mmc_command *cmd = mrq->cmd;
+	struct cvm_mmc_cr_mods mods;
+	u64 emm_cmd, rsp_sts;
+	int retries = 100;
+
+	/*
+	 * Note about locking:
+	 * All MMC devices share the same bus and controller. Allow only a
+	 * single user of the bootbus/MMC bus at a time. The lock is acquired
+	 * on all entry points from the MMC layer.
+	 *
+	 * For requests the lock is only released after the completion
+	 * interrupt!
+	 */
+	host->acquire_bus(host);
+
+	if (cmd->opcode == MMC_READ_MULTIPLE_BLOCK ||
+	    cmd->opcode == MMC_WRITE_MULTIPLE_BLOCK)
+		return cvm_mmc_dma_request(mmc, mrq);
+
+	cvm_mmc_switch_to(slot);
+
+	mods = cvm_mmc_get_cr_mods(cmd);
+
+	WARN_ON(host->current_req);
+	host->current_req = mrq;
+
+	if (cmd->data) {
+		if (cmd->data->flags & MMC_DATA_READ)
+			do_read_request(host, mrq);
+		else
+			do_write_request(host, mrq);
+
+		if (cmd->data->timeout_ns)
+			set_wdog(slot, cmd->data->timeout_ns);
+	} else
+		set_wdog(slot, 0);
+
+	host->dma_active = false;
+	host->int_enable(host, MIO_EMM_INT_CMD_DONE | MIO_EMM_INT_CMD_ERR);
+
+	emm_cmd = FIELD_PREP(MIO_EMM_CMD_VAL, 1) |
+		  FIELD_PREP(MIO_EMM_CMD_CTYPE_XOR, mods.ctype_xor) |
+		  FIELD_PREP(MIO_EMM_CMD_RTYPE_XOR, mods.rtype_xor) |
+		  FIELD_PREP(MIO_EMM_CMD_IDX, cmd->opcode) |
+		  FIELD_PREP(MIO_EMM_CMD_ARG, cmd->arg);
+	set_bus_id(&emm_cmd, slot->bus_id);
+	if (cmd->data && mmc_cmd_type(cmd) == MMC_CMD_ADTC)
+		emm_cmd |= FIELD_PREP(MIO_EMM_CMD_OFFSET,
+				64 - ((cmd->data->blocks * cmd->data->blksz) / 8));
+
+	writeq(0, host->base + MIO_EMM_STS_MASK(host));
+
+retry:
+	rsp_sts = readq(host->base + MIO_EMM_RSP_STS(host));
+	if (rsp_sts & MIO_EMM_RSP_STS_DMA_VAL ||
+	    rsp_sts & MIO_EMM_RSP_STS_CMD_VAL ||
+	    rsp_sts & MIO_EMM_RSP_STS_SWITCH_VAL ||
+	    rsp_sts & MIO_EMM_RSP_STS_DMA_PEND) {
+		udelay(10);
+		if (--retries)
+			goto retry;
+	}
+	if (!retries)
+		dev_err(host->dev, "Bad status: %llx before command write\n", rsp_sts);
+	writeq(emm_cmd, host->base + MIO_EMM_CMD(host));
+}
+
+static void cvm_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct cvm_mmc_slot *slot = mmc_priv(mmc);
+	struct cvm_mmc_host *host = slot->host;
+	int clk_period = 0, power_class = 10, bus_width = 0;
+	u64 clock, emm_switch;
+
+	host->acquire_bus(host);
+	cvm_mmc_switch_to(slot);
+
+	/* Set the power state */
+	switch (ios->power_mode) {
+	case MMC_POWER_ON:
+		break;
+
+	case MMC_POWER_OFF:
+		cvm_mmc_reset_bus(slot);
+		if (host->global_pwr_gpiod)
+			host->set_shared_power(host, 0);
+		else
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
+		break;
+
+	case MMC_POWER_UP:
+		if (host->global_pwr_gpiod)
+			host->set_shared_power(host, 1);
+		else
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
+		break;
+	}
+
+	/* Convert bus width to HW definition */
+	switch (ios->bus_width) {
+	case MMC_BUS_WIDTH_8:
+		bus_width = 2;
+		break;
+	case MMC_BUS_WIDTH_4:
+		bus_width = 1;
+		break;
+	case MMC_BUS_WIDTH_1:
+		bus_width = 0;
+		break;
+	}
+
+	/* DDR is available for 4/8 bit bus width */
+	if (ios->bus_width && ios->timing == MMC_TIMING_MMC_DDR52)
+		bus_width |= 4;
+
+	/* Change the clock frequency. */
+	clock = ios->clock;
+	if (clock > 52000000)
+		clock = 52000000;
+	slot->clock = clock;
+
+	if (clock)
+		clk_period = (host->sys_freq + clock - 1) / (2 * clock);
+
+	emm_switch = FIELD_PREP(MIO_EMM_SWITCH_HS_TIMING,
+				(ios->timing == MMC_TIMING_MMC_HS)) |
+		     FIELD_PREP(MIO_EMM_SWITCH_BUS_WIDTH, bus_width) |
+		     FIELD_PREP(MIO_EMM_SWITCH_POWER_CLASS, power_class) |
+		     FIELD_PREP(MIO_EMM_SWITCH_CLK_HI, clk_period) |
+		     FIELD_PREP(MIO_EMM_SWITCH_CLK_LO, clk_period);
+	set_bus_id(&emm_switch, slot->bus_id);
+
+	if (!switch_val_changed(slot, emm_switch))
+		goto out;
+
+	set_wdog(slot, 0);
+	do_switch(host, emm_switch);
+	slot->cached_switch = emm_switch;
+out:
+	host->release_bus(host);
+}
+
+static const struct mmc_host_ops cvm_mmc_ops = {
+	.request        = cvm_mmc_request,
+	.set_ios        = cvm_mmc_set_ios,
+	.get_ro		= mmc_gpio_get_ro,
+	.get_cd		= mmc_gpio_get_cd,
+};
+
+static void cvm_mmc_set_clock(struct cvm_mmc_slot *slot, unsigned int clock)
+{
+	struct mmc_host *mmc = slot->mmc;
+
+	clock = min(clock, mmc->f_max);
+	clock = max(clock, mmc->f_min);
+	slot->clock = clock;
+}
+
+static int cvm_mmc_init_lowlevel(struct cvm_mmc_slot *slot)
+{
+	struct cvm_mmc_host *host = slot->host;
+	u64 emm_switch;
+
+	/* Enable this bus slot. */
+	host->emm_cfg |= (1ull << slot->bus_id);
+	writeq(host->emm_cfg, slot->host->base + MIO_EMM_CFG(host));
+	udelay(10);
+
+	/* Program initial clock speed and power. */
+	cvm_mmc_set_clock(slot, slot->mmc->f_min);
+	emm_switch = FIELD_PREP(MIO_EMM_SWITCH_POWER_CLASS, 10);
+	emm_switch |= FIELD_PREP(MIO_EMM_SWITCH_CLK_HI,
+				 (host->sys_freq / slot->clock) / 2);
+	emm_switch |= FIELD_PREP(MIO_EMM_SWITCH_CLK_LO,
+				 (host->sys_freq / slot->clock) / 2);
+
+	/* Make the changes take effect on this bus slot. */
+	set_bus_id(&emm_switch, slot->bus_id);
+	do_switch(host, emm_switch);
+
+	slot->cached_switch = emm_switch;
+
+	/*
+	 * Set watchdog timeout value and default reset value
+	 * for the mask register. Finally, set the CARD_RCA
+	 * bit so that we can get the card address relative
+	 * to the CMD register for CMD7 transactions.
+	 */
+	set_wdog(slot, 0);
+	writeq(0xe4390080ull, host->base + MIO_EMM_STS_MASK(host));
+	writeq(1, host->base + MIO_EMM_RCA(host));
+	return 0;
+}
+
+static int cvm_mmc_of_parse(struct device *dev, struct cvm_mmc_slot *slot)
+{
+	u32 id, cmd_skew = 0, dat_skew = 0, bus_width = 0;
+	struct device_node *node = dev->of_node;
+	struct mmc_host *mmc = slot->mmc;
+	u64 clock_period;
+	int ret;
+
+	ret = of_property_read_u32(node, "reg", &id);
+	if (ret) {
+		dev_err(dev, "Missing or invalid reg property on %s\n",
+			of_node_full_name(node));
+		return ret;
+	}
+
+	if (id >= CAVIUM_MAX_MMC || slot->host->slot[id]) {
+		dev_err(dev, "Invalid reg property on %s\n",
+			of_node_full_name(node));
+		return -EINVAL;
+	}
+
+	mmc->supply.vmmc = devm_regulator_get_optional(dev, "vmmc");
+	if (IS_ERR(mmc->supply.vmmc)) {
+		if (PTR_ERR(mmc->supply.vmmc) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		/*
+		 * Legacy Octeon firmware has no regulator entry, fall-back to
+		 * a hard-coded voltage to get a sane OCR.
+		 */
+		mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
+	} else {
+		ret = mmc_regulator_get_ocrmask(mmc->supply.vmmc);
+		if (ret > 0)
+			mmc->ocr_avail = ret;
+	}
+
+	/* Common MMC bindings */
+	ret = mmc_of_parse(mmc);
+	if (ret)
+		return ret;
+
+	/* Set bus width */
+	if (!(mmc->caps & (MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA))) {
+		of_property_read_u32(node, "cavium,bus-max-width", &bus_width);
+		if (bus_width == 8)
+			mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA;
+		else if (bus_width == 4)
+			mmc->caps |= MMC_CAP_4_BIT_DATA;
+	}
+
+	/* Set maximum and minimum frequency */
+	if (!mmc->f_max)
+		of_property_read_u32(node, "spi-max-frequency", &mmc->f_max);
+	if (!mmc->f_max || mmc->f_max > 52000000)
+		mmc->f_max = 52000000;
+	mmc->f_min = 400000;
+
+	/* Sampling register settings, period in picoseconds */
+	clock_period = 1000000000000ull / slot->host->sys_freq;
+	of_property_read_u32(node, "cavium,cmd-clk-skew", &cmd_skew);
+	of_property_read_u32(node, "cavium,dat-clk-skew", &dat_skew);
+	slot->cmd_cnt = (cmd_skew + clock_period / 2) / clock_period;
+	slot->dat_cnt = (dat_skew + clock_period / 2) / clock_period;
+
+	return id;
+}
+
+int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host)
+{
+	struct cvm_mmc_slot *slot;
+	struct mmc_host *mmc;
+	int ret, id;
+
+	mmc = mmc_alloc_host(sizeof(struct cvm_mmc_slot), dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	slot = mmc_priv(mmc);
+	slot->mmc = mmc;
+	slot->host = host;
+
+	ret = cvm_mmc_of_parse(dev, slot);
+	if (ret < 0)
+		goto error;
+	id = ret;
+
+	/* Set up host parameters */
+	mmc->ops = &cvm_mmc_ops;
+
+	/*
+	 * We only have a 3.3v supply, we cannot support any
+	 * of the UHS modes. We do support the high speed DDR
+	 * modes up to 52MHz.
+	 */
+	mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
+		     MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD |
+		     MMC_CAP_3_3V_DDR;
+
+	if (host->use_sg)
+		mmc->max_segs = 16;
+	else
+		mmc->max_segs = 1;
+
+	/* DMA size field can address up to 8 MB */
+	mmc->max_seg_size = 8 * 1024 * 1024;
+	mmc->max_req_size = mmc->max_seg_size;
+	/* External DMA is in 512 byte blocks */
+	mmc->max_blk_size = 512;
+	/* DMA block count field is 15 bits */
+	mmc->max_blk_count = 32767;
+
+	slot->clock = mmc->f_min;
+	slot->bus_id = id;
+	slot->cached_rca = 1;
+
+	host->acquire_bus(host);
+	host->slot[id] = slot;
+	cvm_mmc_switch_to(slot);
+	cvm_mmc_init_lowlevel(slot);
+	host->release_bus(host);
+
+	ret = mmc_add_host(mmc);
+	if (ret) {
+		dev_err(dev, "mmc_add_host() returned %d\n", ret);
+		slot->host->slot[id] = NULL;
+		goto error;
+	}
+	return 0;
+
+error:
+	mmc_free_host(slot->mmc);
+	return ret;
+}
+
+int cvm_mmc_of_slot_remove(struct cvm_mmc_slot *slot)
+{
+	mmc_remove_host(slot->mmc);
+	slot->host->slot[slot->bus_id] = NULL;
+	mmc_free_host(slot->mmc);
+	return 0;
+}
diff --git a/drivers/mmc/host/cavium.h b/drivers/mmc/host/cavium.h
new file mode 100644
index 000000000000..f3eea5eaa678
--- /dev/null
+++ b/drivers/mmc/host/cavium.h
@@ -0,0 +1,215 @@
+/*
+ * Driver for MMC and SSD cards for Cavium OCTEON and ThunderX SOCs.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012-2017 Cavium Inc.
+ */
+
+#ifndef _CAVIUM_MMC_H_
+#define _CAVIUM_MMC_H_
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/gpio/consumer.h>
+#include <linux/io.h>
+#include <linux/mmc/host.h>
+#include <linux/of.h>
+#include <linux/scatterlist.h>
+#include <linux/semaphore.h>
+
+#define CAVIUM_MAX_MMC		4
+
+/* DMA register addresses */
+#define MIO_EMM_DMA_FIFO_CFG(x)	(0x00 + x->reg_off_dma)
+#define MIO_EMM_DMA_FIFO_ADR(x)	(0x10 + x->reg_off_dma)
+#define MIO_EMM_DMA_FIFO_CMD(x)	(0x18 + x->reg_off_dma)
+#define MIO_EMM_DMA_CFG(x)	(0x20 + x->reg_off_dma)
+#define MIO_EMM_DMA_ADR(x)	(0x28 + x->reg_off_dma)
+#define MIO_EMM_DMA_INT(x)	(0x30 + x->reg_off_dma)
+#define MIO_EMM_DMA_INT_W1S(x)	(0x38 + x->reg_off_dma)
+#define MIO_EMM_DMA_INT_ENA_W1S(x) (0x40 + x->reg_off_dma)
+#define MIO_EMM_DMA_INT_ENA_W1C(x) (0x48 + x->reg_off_dma)
+
+/* register addresses */
+#define MIO_EMM_CFG(x)		(0x00 + x->reg_off)
+#define MIO_EMM_SWITCH(x)	(0x48 + x->reg_off)
+#define MIO_EMM_DMA(x)		(0x50 + x->reg_off)
+#define MIO_EMM_CMD(x)		(0x58 + x->reg_off)
+#define MIO_EMM_RSP_STS(x)	(0x60 + x->reg_off)
+#define MIO_EMM_RSP_LO(x)	(0x68 + x->reg_off)
+#define MIO_EMM_RSP_HI(x)	(0x70 + x->reg_off)
+#define MIO_EMM_INT(x)		(0x78 + x->reg_off)
+#define MIO_EMM_INT_EN(x)	(0x80 + x->reg_off)
+#define MIO_EMM_WDOG(x)		(0x88 + x->reg_off)
+#define MIO_EMM_SAMPLE(x)	(0x90 + x->reg_off)
+#define MIO_EMM_STS_MASK(x)	(0x98 + x->reg_off)
+#define MIO_EMM_RCA(x)		(0xa0 + x->reg_off)
+#define MIO_EMM_INT_EN_SET(x)	(0xb0 + x->reg_off)
+#define MIO_EMM_INT_EN_CLR(x)	(0xb8 + x->reg_off)
+#define MIO_EMM_BUF_IDX(x)	(0xe0 + x->reg_off)
+#define MIO_EMM_BUF_DAT(x)	(0xe8 + x->reg_off)
+
+struct cvm_mmc_host {
+	struct device *dev;
+	void __iomem *base;
+	void __iomem *dma_base;
+	int reg_off;
+	int reg_off_dma;
+	u64 emm_cfg;
+	u64 n_minus_one;	/* OCTEON II workaround location */
+	int last_slot;
+	struct clk *clk;
+	int sys_freq;
+
+	struct mmc_request *current_req;
+	struct sg_mapping_iter smi;
+	bool dma_active;
+	bool use_sg;
+
+	bool has_ciu3;
+	bool big_dma_addr;
+	bool need_irq_handler_lock;
+	spinlock_t irq_handler_lock;
+	struct semaphore mmc_serializer;
+
+	struct gpio_desc *global_pwr_gpiod;
+	atomic_t shared_power_users;
+
+	struct cvm_mmc_slot *slot[CAVIUM_MAX_MMC];
+	struct platform_device *slot_pdev[CAVIUM_MAX_MMC];
+
+	void (*set_shared_power)(struct cvm_mmc_host *, int);
+	void (*acquire_bus)(struct cvm_mmc_host *);
+	void (*release_bus)(struct cvm_mmc_host *);
+	void (*int_enable)(struct cvm_mmc_host *, u64);
+	/* required on some MIPS models */
+	void (*dmar_fixup)(struct cvm_mmc_host *, struct mmc_command *,
+			   struct mmc_data *, u64);
+	void (*dmar_fixup_done)(struct cvm_mmc_host *);
+};
+
+struct cvm_mmc_slot {
+	struct mmc_host *mmc;		/* slot-level mmc_core object */
+	struct cvm_mmc_host *host;	/* common hw for all slots */
+
+	u64 clock;
+
+	u64 cached_switch;
+	u64 cached_rca;
+
+	unsigned int cmd_cnt;		/* sample delay */
+	unsigned int dat_cnt;		/* sample delay */
+
+	int bus_id;
+};
+
+struct cvm_mmc_cr_type {
+	u8 ctype;
+	u8 rtype;
+};
+
+struct cvm_mmc_cr_mods {
+	u8 ctype_xor;
+	u8 rtype_xor;
+};
+
+/* Bitfield definitions */
+#define MIO_EMM_DMA_FIFO_CFG_CLR	BIT_ULL(16)
+#define MIO_EMM_DMA_FIFO_CFG_INT_LVL	GENMASK_ULL(12, 8)
+#define MIO_EMM_DMA_FIFO_CFG_COUNT	GENMASK_ULL(4, 0)
+
+#define MIO_EMM_DMA_FIFO_CMD_RW		BIT_ULL(62)
+#define MIO_EMM_DMA_FIFO_CMD_INTDIS	BIT_ULL(60)
+#define MIO_EMM_DMA_FIFO_CMD_SWAP32	BIT_ULL(59)
+#define MIO_EMM_DMA_FIFO_CMD_SWAP16	BIT_ULL(58)
+#define MIO_EMM_DMA_FIFO_CMD_SWAP8	BIT_ULL(57)
+#define MIO_EMM_DMA_FIFO_CMD_ENDIAN	BIT_ULL(56)
+#define MIO_EMM_DMA_FIFO_CMD_SIZE	GENMASK_ULL(55, 36)
+
+#define MIO_EMM_CMD_SKIP_BUSY		BIT_ULL(62)
+#define MIO_EMM_CMD_BUS_ID		GENMASK_ULL(61, 60)
+#define MIO_EMM_CMD_VAL			BIT_ULL(59)
+#define MIO_EMM_CMD_DBUF		BIT_ULL(55)
+#define MIO_EMM_CMD_OFFSET		GENMASK_ULL(54, 49)
+#define MIO_EMM_CMD_CTYPE_XOR		GENMASK_ULL(42, 41)
+#define MIO_EMM_CMD_RTYPE_XOR		GENMASK_ULL(40, 38)
+#define MIO_EMM_CMD_IDX			GENMASK_ULL(37, 32)
+#define MIO_EMM_CMD_ARG			GENMASK_ULL(31, 0)
+
+#define MIO_EMM_DMA_SKIP_BUSY		BIT_ULL(62)
+#define MIO_EMM_DMA_BUS_ID		GENMASK_ULL(61, 60)
+#define MIO_EMM_DMA_VAL			BIT_ULL(59)
+#define MIO_EMM_DMA_SECTOR		BIT_ULL(58)
+#define MIO_EMM_DMA_DAT_NULL		BIT_ULL(57)
+#define MIO_EMM_DMA_THRES		GENMASK_ULL(56, 51)
+#define MIO_EMM_DMA_REL_WR		BIT_ULL(50)
+#define MIO_EMM_DMA_RW			BIT_ULL(49)
+#define MIO_EMM_DMA_MULTI		BIT_ULL(48)
+#define MIO_EMM_DMA_BLOCK_CNT		GENMASK_ULL(47, 32)
+#define MIO_EMM_DMA_CARD_ADDR		GENMASK_ULL(31, 0)
+
+#define MIO_EMM_DMA_CFG_EN		BIT_ULL(63)
+#define MIO_EMM_DMA_CFG_RW		BIT_ULL(62)
+#define MIO_EMM_DMA_CFG_CLR		BIT_ULL(61)
+#define MIO_EMM_DMA_CFG_SWAP32		BIT_ULL(59)
+#define MIO_EMM_DMA_CFG_SWAP16		BIT_ULL(58)
+#define MIO_EMM_DMA_CFG_SWAP8		BIT_ULL(57)
+#define MIO_EMM_DMA_CFG_ENDIAN		BIT_ULL(56)
+#define MIO_EMM_DMA_CFG_SIZE		GENMASK_ULL(55, 36)
+#define MIO_EMM_DMA_CFG_ADR		GENMASK_ULL(35, 0)
+
+#define MIO_EMM_INT_SWITCH_ERR		BIT_ULL(6)
+#define MIO_EMM_INT_SWITCH_DONE		BIT_ULL(5)
+#define MIO_EMM_INT_DMA_ERR		BIT_ULL(4)
+#define MIO_EMM_INT_CMD_ERR		BIT_ULL(3)
+#define MIO_EMM_INT_DMA_DONE		BIT_ULL(2)
+#define MIO_EMM_INT_CMD_DONE		BIT_ULL(1)
+#define MIO_EMM_INT_BUF_DONE		BIT_ULL(0)
+
+#define MIO_EMM_RSP_STS_BUS_ID		GENMASK_ULL(61, 60)
+#define MIO_EMM_RSP_STS_CMD_VAL		BIT_ULL(59)
+#define MIO_EMM_RSP_STS_SWITCH_VAL	BIT_ULL(58)
+#define MIO_EMM_RSP_STS_DMA_VAL		BIT_ULL(57)
+#define MIO_EMM_RSP_STS_DMA_PEND	BIT_ULL(56)
+#define MIO_EMM_RSP_STS_DBUF_ERR	BIT_ULL(28)
+#define MIO_EMM_RSP_STS_DBUF		BIT_ULL(23)
+#define MIO_EMM_RSP_STS_BLK_TIMEOUT	BIT_ULL(22)
+#define MIO_EMM_RSP_STS_BLK_CRC_ERR	BIT_ULL(21)
+#define MIO_EMM_RSP_STS_RSP_BUSYBIT	BIT_ULL(20)
+#define MIO_EMM_RSP_STS_STP_TIMEOUT	BIT_ULL(19)
+#define MIO_EMM_RSP_STS_STP_CRC_ERR	BIT_ULL(18)
+#define MIO_EMM_RSP_STS_STP_BAD_STS	BIT_ULL(17)
+#define MIO_EMM_RSP_STS_STP_VAL		BIT_ULL(16)
+#define MIO_EMM_RSP_STS_RSP_TIMEOUT	BIT_ULL(15)
+#define MIO_EMM_RSP_STS_RSP_CRC_ERR	BIT_ULL(14)
+#define MIO_EMM_RSP_STS_RSP_BAD_STS	BIT_ULL(13)
+#define MIO_EMM_RSP_STS_RSP_VAL		BIT_ULL(12)
+#define MIO_EMM_RSP_STS_RSP_TYPE	GENMASK_ULL(11, 9)
+#define MIO_EMM_RSP_STS_CMD_TYPE	GENMASK_ULL(8, 7)
+#define MIO_EMM_RSP_STS_CMD_IDX		GENMASK_ULL(6, 1)
+#define MIO_EMM_RSP_STS_CMD_DONE	BIT_ULL(0)
+
+#define MIO_EMM_SAMPLE_CMD_CNT		GENMASK_ULL(25, 16)
+#define MIO_EMM_SAMPLE_DAT_CNT		GENMASK_ULL(9, 0)
+
+#define MIO_EMM_SWITCH_BUS_ID		GENMASK_ULL(61, 60)
+#define MIO_EMM_SWITCH_EXE		BIT_ULL(59)
+#define MIO_EMM_SWITCH_ERR0		BIT_ULL(58)
+#define MIO_EMM_SWITCH_ERR1		BIT_ULL(57)
+#define MIO_EMM_SWITCH_ERR2		BIT_ULL(56)
+#define MIO_EMM_SWITCH_HS_TIMING	BIT_ULL(48)
+#define MIO_EMM_SWITCH_BUS_WIDTH	GENMASK_ULL(42, 40)
+#define MIO_EMM_SWITCH_POWER_CLASS	GENMASK_ULL(35, 32)
+#define MIO_EMM_SWITCH_CLK_HI		GENMASK_ULL(31, 16)
+#define MIO_EMM_SWITCH_CLK_LO		GENMASK_ULL(15, 0)
+
+/* Protoypes */
+irqreturn_t cvm_mmc_interrupt(int irq, void *dev_id);
+int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host);
+int cvm_mmc_of_slot_remove(struct cvm_mmc_slot *slot);
+extern const char *cvm_mmc_irq_names[];
+
+#endif
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 1e2600da105f..621ce47e0e4a 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -478,18 +478,14 @@ static int mmc_davinci_start_dma_transfer(struct mmc_davinci_host *host,
 	int ret = 0;
 
 	host->sg_len = dma_map_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-				((data->flags & MMC_DATA_WRITE)
-				? DMA_TO_DEVICE
-				: DMA_FROM_DEVICE));
+				  mmc_get_dma_dir(data));
 
 	/* no individual DMA segment should need a partial FIFO */
 	for (i = 0; i < host->sg_len; i++) {
 		if (sg_dma_len(data->sg + i) & mask) {
 			dma_unmap_sg(mmc_dev(host->mmc),
-					data->sg, data->sg_len,
-					(data->flags & MMC_DATA_WRITE)
-					? DMA_TO_DEVICE
-					: DMA_FROM_DEVICE);
+				     data->sg, data->sg_len,
+				     mmc_get_dma_dir(data));
 			return -1;
 		}
 	}
@@ -802,9 +798,7 @@ mmc_davinci_xfer_done(struct mmc_davinci_host *host, struct mmc_data *data)
 		davinci_abort_dma(host);
 
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-			     (data->flags & MMC_DATA_WRITE)
-			     ? DMA_TO_DEVICE
-			     : DMA_FROM_DEVICE);
+			     mmc_get_dma_dir(data));
 		host->do_dma = false;
 	}
 	host->data_dir = DAVINCI_MMC_DATADIR_NONE;
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index a9ac0b457313..e45129f48174 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -19,9 +19,11 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
@@ -64,6 +66,8 @@
 
 struct idmac_desc_64addr {
 	u32		des0;	/* Control Descriptor */
+#define IDMAC_OWN_CLR64(x) \
+	!((x) & cpu_to_le32(IDMAC_DES0_OWN))
 
 	u32		des1;	/* Reserved */
 
@@ -103,11 +107,6 @@ struct idmac_desc {
 /* Each descriptor can transfer up to 4KB of data in chained mode */
 #define DW_MCI_DESC_DATA_LENGTH	0x1000
 
-static bool dw_mci_reset(struct dw_mci *host);
-static bool dw_mci_ctrl_reset(struct dw_mci *host, u32 reset);
-static int dw_mci_card_busy(struct mmc_host *mmc);
-static int dw_mci_get_cd(struct mmc_host *mmc);
-
 #if defined(CONFIG_DEBUG_FS)
 static int dw_mci_req_show(struct seq_file *s, void *v)
 {
@@ -231,7 +230,66 @@ err:
 }
 #endif /* defined(CONFIG_DEBUG_FS) */
 
-static void mci_send_cmd(struct dw_mci_slot *slot, u32 cmd, u32 arg);
+static bool dw_mci_ctrl_reset(struct dw_mci *host, u32 reset)
+{
+	u32 ctrl;
+
+	ctrl = mci_readl(host, CTRL);
+	ctrl |= reset;
+	mci_writel(host, CTRL, ctrl);
+
+	/* wait till resets clear */
+	if (readl_poll_timeout_atomic(host->regs + SDMMC_CTRL, ctrl,
+				      !(ctrl & reset),
+				      1, 500 * USEC_PER_MSEC)) {
+		dev_err(host->dev,
+			"Timeout resetting block (ctrl reset %#x)\n",
+			ctrl & reset);
+		return false;
+	}
+
+	return true;
+}
+
+static void dw_mci_wait_while_busy(struct dw_mci *host, u32 cmd_flags)
+{
+	u32 status;
+
+	/*
+	 * Databook says that before issuing a new data transfer command
+	 * we need to check to see if the card is busy.  Data transfer commands
+	 * all have SDMMC_CMD_PRV_DAT_WAIT set, so we'll key off that.
+	 *
+	 * ...also allow sending for SDMMC_CMD_VOLT_SWITCH where busy is
+	 * expected.
+	 */
+	if ((cmd_flags & SDMMC_CMD_PRV_DAT_WAIT) &&
+	    !(cmd_flags & SDMMC_CMD_VOLT_SWITCH)) {
+		if (readl_poll_timeout_atomic(host->regs + SDMMC_STATUS,
+					      status,
+					      !(status & SDMMC_STATUS_BUSY),
+					      10, 500 * USEC_PER_MSEC))
+			dev_err(host->dev, "Busy; trying anyway\n");
+	}
+}
+
+static void mci_send_cmd(struct dw_mci_slot *slot, u32 cmd, u32 arg)
+{
+	struct dw_mci *host = slot->host;
+	unsigned int cmd_status = 0;
+
+	mci_writel(host, CMDARG, arg);
+	wmb(); /* drain writebuffer */
+	dw_mci_wait_while_busy(host, cmd);
+	mci_writel(host, CMD, SDMMC_CMD_START | cmd);
+
+	if (readl_poll_timeout_atomic(host->regs + SDMMC_CMD, cmd_status,
+				      !(cmd_status & SDMMC_CMD_START),
+				      1, 500 * USEC_PER_MSEC))
+		dev_err(&slot->mmc->class_dev,
+			"Timeout sending command (cmd %#x arg %#x status %#x)\n",
+			cmd, arg, cmd_status);
+}
 
 static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 {
@@ -340,31 +398,6 @@ static u32 dw_mci_prep_stop_abort(struct dw_mci *host, struct mmc_command *cmd)
 	return cmdr;
 }
 
-static void dw_mci_wait_while_busy(struct dw_mci *host, u32 cmd_flags)
-{
-	unsigned long timeout = jiffies + msecs_to_jiffies(500);
-
-	/*
-	 * Databook says that before issuing a new data transfer command
-	 * we need to check to see if the card is busy.  Data transfer commands
-	 * all have SDMMC_CMD_PRV_DAT_WAIT set, so we'll key off that.
-	 *
-	 * ...also allow sending for SDMMC_CMD_VOLT_SWITCH where busy is
-	 * expected.
-	 */
-	if ((cmd_flags & SDMMC_CMD_PRV_DAT_WAIT) &&
-	    !(cmd_flags & SDMMC_CMD_VOLT_SWITCH)) {
-		while (mci_readl(host, STATUS) & SDMMC_STATUS_BUSY) {
-			if (time_after(jiffies, timeout)) {
-				/* Command will fail; we'll pass error then */
-				dev_err(host->dev, "Busy; trying anyway\n");
-				break;
-			}
-			udelay(10);
-		}
-	}
-}
-
 static void dw_mci_start_command(struct dw_mci *host,
 				 struct mmc_command *cmd, u32 cmd_flags)
 {
@@ -399,14 +432,6 @@ static void dw_mci_stop_dma(struct dw_mci *host)
 	set_bit(EVENT_XFER_COMPLETE, &host->pending_events);
 }
 
-static int dw_mci_get_dma_dir(struct mmc_data *data)
-{
-	if (data->flags & MMC_DATA_WRITE)
-		return DMA_TO_DEVICE;
-	else
-		return DMA_FROM_DEVICE;
-}
-
 static void dw_mci_dma_cleanup(struct dw_mci *host)
 {
 	struct mmc_data *data = host->data;
@@ -415,7 +440,7 @@ static void dw_mci_dma_cleanup(struct dw_mci *host)
 		dma_unmap_sg(host->dev,
 			     data->sg,
 			     data->sg_len,
-			     dw_mci_get_dma_dir(data));
+			     mmc_get_dma_dir(data));
 		data->host_cookie = COOKIE_UNMAPPED;
 	}
 }
@@ -554,7 +579,7 @@ static inline int dw_mci_prepare_desc64(struct dw_mci *host,
 {
 	unsigned int desc_len;
 	struct idmac_desc_64addr *desc_first, *desc_last, *desc;
-	unsigned long timeout;
+	u32 val;
 	int i;
 
 	desc_first = desc_last = desc = host->sg_cpu;
@@ -576,12 +601,10 @@ static inline int dw_mci_prepare_desc64(struct dw_mci *host,
 			 * isn't still owned by IDMAC as IDMAC's write
 			 * ops and CPU's read ops are asynchronous.
 			 */
-			timeout = jiffies + msecs_to_jiffies(100);
-			while (readl(&desc->des0) & IDMAC_DES0_OWN) {
-				if (time_after(jiffies, timeout))
-					goto err_own_bit;
-				udelay(10);
-			}
+			if (readl_poll_timeout_atomic(&desc->des0, val,
+						!(val & IDMAC_DES0_OWN),
+						10, 100 * USEC_PER_MSEC))
+				goto err_own_bit;
 
 			/*
 			 * Set the OWN bit and disable interrupts
@@ -628,7 +651,7 @@ static inline int dw_mci_prepare_desc32(struct dw_mci *host,
 {
 	unsigned int desc_len;
 	struct idmac_desc *desc_first, *desc_last, *desc;
-	unsigned long timeout;
+	u32 val;
 	int i;
 
 	desc_first = desc_last = desc = host->sg_cpu;
@@ -650,13 +673,11 @@ static inline int dw_mci_prepare_desc32(struct dw_mci *host,
 			 * isn't still owned by IDMAC as IDMAC's write
 			 * ops and CPU's read ops are asynchronous.
 			 */
-			timeout = jiffies + msecs_to_jiffies(100);
-			while (readl(&desc->des0) &
-			       cpu_to_le32(IDMAC_DES0_OWN)) {
-				if (time_after(jiffies, timeout))
-					goto err_own_bit;
-				udelay(10);
-			}
+			if (readl_poll_timeout_atomic(&desc->des0, val,
+						      IDMAC_OWN_CLR64(val),
+						      10,
+						      100 * USEC_PER_MSEC))
+				goto err_own_bit;
 
 			/*
 			 * Set the OWN bit and disable interrupts
@@ -875,7 +896,7 @@ static int dw_mci_pre_dma_transfer(struct dw_mci *host,
 	sg_len = dma_map_sg(host->dev,
 			    data->sg,
 			    data->sg_len,
-			    dw_mci_get_dma_dir(data));
+			    mmc_get_dma_dir(data));
 	if (sg_len == 0)
 		return -EINVAL;
 
@@ -915,10 +936,51 @@ static void dw_mci_post_req(struct mmc_host *mmc,
 		dma_unmap_sg(slot->host->dev,
 			     data->sg,
 			     data->sg_len,
-			     dw_mci_get_dma_dir(data));
+			     mmc_get_dma_dir(data));
 	data->host_cookie = COOKIE_UNMAPPED;
 }
 
+static int dw_mci_get_cd(struct mmc_host *mmc)
+{
+	int present;
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct dw_mci *host = slot->host;
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+
+	/* Use platform get_cd function, else try onboard card detect */
+	if (((mmc->caps & MMC_CAP_NEEDS_POLL)
+				|| !mmc_card_is_removable(mmc))) {
+		present = 1;
+
+		if (!test_bit(DW_MMC_CARD_PRESENT, &slot->flags)) {
+			if (mmc->caps & MMC_CAP_NEEDS_POLL) {
+				dev_info(&mmc->class_dev,
+					"card is polling.\n");
+			} else {
+				dev_info(&mmc->class_dev,
+					"card is non-removable.\n");
+			}
+			set_bit(DW_MMC_CARD_PRESENT, &slot->flags);
+		}
+
+		return present;
+	} else if (gpio_cd >= 0)
+		present = gpio_cd;
+	else
+		present = (mci_readl(slot->host, CDETECT) & (1 << slot->id))
+			== 0 ? 1 : 0;
+
+	spin_lock_bh(&host->lock);
+	if (present && !test_and_set_bit(DW_MMC_CARD_PRESENT, &slot->flags))
+		dev_dbg(&mmc->class_dev, "card is present\n");
+	else if (!present &&
+			!test_and_clear_bit(DW_MMC_CARD_PRESENT, &slot->flags))
+		dev_dbg(&mmc->class_dev, "card is not present\n");
+	spin_unlock_bh(&host->lock);
+
+	return present;
+}
+
 static void dw_mci_adjust_fifoth(struct dw_mci *host, struct mmc_data *data)
 {
 	unsigned int blksz = data->blksz;
@@ -1132,27 +1194,6 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 	}
 }
 
-static void mci_send_cmd(struct dw_mci_slot *slot, u32 cmd, u32 arg)
-{
-	struct dw_mci *host = slot->host;
-	unsigned long timeout = jiffies + msecs_to_jiffies(500);
-	unsigned int cmd_status = 0;
-
-	mci_writel(host, CMDARG, arg);
-	wmb(); /* drain writebuffer */
-	dw_mci_wait_while_busy(host, cmd);
-	mci_writel(host, CMD, SDMMC_CMD_START | cmd);
-
-	while (time_before(jiffies, timeout)) {
-		cmd_status = mci_readl(host, CMD);
-		if (!(cmd_status & SDMMC_CMD_START))
-			return;
-	}
-	dev_err(&slot->mmc->class_dev,
-		"Timeout sending command (cmd %#x arg %#x status %#x)\n",
-		cmd, arg, cmd_status);
-}
-
 static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 {
 	struct dw_mci *host = slot->host;
@@ -1533,47 +1574,6 @@ static int dw_mci_get_ro(struct mmc_host *mmc)
 	return read_only;
 }
 
-static int dw_mci_get_cd(struct mmc_host *mmc)
-{
-	int present;
-	struct dw_mci_slot *slot = mmc_priv(mmc);
-	struct dw_mci *host = slot->host;
-	int gpio_cd = mmc_gpio_get_cd(mmc);
-
-	/* Use platform get_cd function, else try onboard card detect */
-	if (((mmc->caps & MMC_CAP_NEEDS_POLL)
-				|| !mmc_card_is_removable(mmc))) {
-		present = 1;
-
-		if (!test_bit(DW_MMC_CARD_PRESENT, &slot->flags)) {
-			if (mmc->caps & MMC_CAP_NEEDS_POLL) {
-				dev_info(&mmc->class_dev,
-					"card is polling.\n");
-			} else {
-				dev_info(&mmc->class_dev,
-					"card is non-removable.\n");
-			}
-			set_bit(DW_MMC_CARD_PRESENT, &slot->flags);
-		}
-
-		return present;
-	} else if (gpio_cd >= 0)
-		present = gpio_cd;
-	else
-		present = (mci_readl(slot->host, CDETECT) & (1 << slot->id))
-			== 0 ? 1 : 0;
-
-	spin_lock_bh(&host->lock);
-	if (present && !test_and_set_bit(DW_MMC_CARD_PRESENT, &slot->flags))
-		dev_dbg(&mmc->class_dev, "card is present\n");
-	else if (!present &&
-			!test_and_clear_bit(DW_MMC_CARD_PRESENT, &slot->flags))
-		dev_dbg(&mmc->class_dev, "card is not present\n");
-	spin_unlock_bh(&host->lock);
-
-	return present;
-}
-
 static void dw_mci_hw_reset(struct mmc_host *mmc)
 {
 	struct dw_mci_slot *slot = mmc_priv(mmc);
@@ -1621,10 +1621,16 @@ static void dw_mci_init_card(struct mmc_host *mmc, struct mmc_card *card)
 
 		if (card->type == MMC_TYPE_SDIO ||
 		    card->type == MMC_TYPE_SD_COMBO) {
-			set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+			if (!test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) {
+				pm_runtime_get_noresume(mmc->parent);
+				set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+			}
 			clk_en_a = clk_en_a_old & ~clken_low_pwr;
 		} else {
-			clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+			if (test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) {
+				pm_runtime_put_noidle(mmc->parent);
+				clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+			}
 			clk_en_a = clk_en_a_old | clken_low_pwr;
 		}
 
@@ -1681,6 +1687,73 @@ static int dw_mci_prepare_hs400_tuning(struct mmc_host *mmc,
 	return 0;
 }
 
+static bool dw_mci_reset(struct dw_mci *host)
+{
+	u32 flags = SDMMC_CTRL_RESET | SDMMC_CTRL_FIFO_RESET;
+	bool ret = false;
+	u32 status = 0;
+
+	/*
+	 * Resetting generates a block interrupt, hence setting
+	 * the scatter-gather pointer to NULL.
+	 */
+	if (host->sg) {
+		sg_miter_stop(&host->sg_miter);
+		host->sg = NULL;
+	}
+
+	if (host->use_dma)
+		flags |= SDMMC_CTRL_DMA_RESET;
+
+	if (dw_mci_ctrl_reset(host, flags)) {
+		/*
+		 * In all cases we clear the RAWINTS
+		 * register to clear any interrupts.
+		 */
+		mci_writel(host, RINTSTS, 0xFFFFFFFF);
+
+		if (!host->use_dma) {
+			ret = true;
+			goto ciu_out;
+		}
+
+		/* Wait for dma_req to be cleared */
+		if (readl_poll_timeout_atomic(host->regs + SDMMC_STATUS,
+					      status,
+					      !(status & SDMMC_STATUS_DMA_REQ),
+					      1, 500 * USEC_PER_MSEC)) {
+			dev_err(host->dev,
+				"%s: Timeout waiting for dma_req to be cleared\n",
+				__func__);
+			goto ciu_out;
+		}
+
+		/* when using DMA next we reset the fifo again */
+		if (!dw_mci_ctrl_reset(host, SDMMC_CTRL_FIFO_RESET))
+			goto ciu_out;
+	} else {
+		/* if the controller reset bit did clear, then set clock regs */
+		if (!(mci_readl(host, CTRL) & SDMMC_CTRL_RESET)) {
+			dev_err(host->dev,
+				"%s: fifo/dma reset bits didn't clear but ciu was reset, doing clock update\n",
+				__func__);
+			goto ciu_out;
+		}
+	}
+
+	if (host->use_dma == TRANS_MODE_IDMAC)
+		/* It is also recommended that we reset and reprogram idmac */
+		dw_mci_idmac_reset(host);
+
+	ret = true;
+
+ciu_out:
+	/* After a CTRL reset we need to have CIU set clock registers  */
+	mci_send_cmd(host->cur_slot, SDMMC_CMD_UPD_CLK, 0);
+
+	return ret;
+}
+
 static const struct mmc_host_ops dw_mci_ops = {
 	.request		= dw_mci_request,
 	.pre_req		= dw_mci_pre_req,
@@ -2823,99 +2896,6 @@ no_dma:
 	host->use_dma = TRANS_MODE_PIO;
 }
 
-static bool dw_mci_ctrl_reset(struct dw_mci *host, u32 reset)
-{
-	unsigned long timeout = jiffies + msecs_to_jiffies(500);
-	u32 ctrl;
-
-	ctrl = mci_readl(host, CTRL);
-	ctrl |= reset;
-	mci_writel(host, CTRL, ctrl);
-
-	/* wait till resets clear */
-	do {
-		ctrl = mci_readl(host, CTRL);
-		if (!(ctrl & reset))
-			return true;
-	} while (time_before(jiffies, timeout));
-
-	dev_err(host->dev,
-		"Timeout resetting block (ctrl reset %#x)\n",
-		ctrl & reset);
-
-	return false;
-}
-
-static bool dw_mci_reset(struct dw_mci *host)
-{
-	u32 flags = SDMMC_CTRL_RESET | SDMMC_CTRL_FIFO_RESET;
-	bool ret = false;
-
-	/*
-	 * Reseting generates a block interrupt, hence setting
-	 * the scatter-gather pointer to NULL.
-	 */
-	if (host->sg) {
-		sg_miter_stop(&host->sg_miter);
-		host->sg = NULL;
-	}
-
-	if (host->use_dma)
-		flags |= SDMMC_CTRL_DMA_RESET;
-
-	if (dw_mci_ctrl_reset(host, flags)) {
-		/*
-		 * In all cases we clear the RAWINTS register to clear any
-		 * interrupts.
-		 */
-		mci_writel(host, RINTSTS, 0xFFFFFFFF);
-
-		/* if using dma we wait for dma_req to clear */
-		if (host->use_dma) {
-			unsigned long timeout = jiffies + msecs_to_jiffies(500);
-			u32 status;
-
-			do {
-				status = mci_readl(host, STATUS);
-				if (!(status & SDMMC_STATUS_DMA_REQ))
-					break;
-				cpu_relax();
-			} while (time_before(jiffies, timeout));
-
-			if (status & SDMMC_STATUS_DMA_REQ) {
-				dev_err(host->dev,
-					"%s: Timeout waiting for dma_req to clear during reset\n",
-					__func__);
-				goto ciu_out;
-			}
-
-			/* when using DMA next we reset the fifo again */
-			if (!dw_mci_ctrl_reset(host, SDMMC_CTRL_FIFO_RESET))
-				goto ciu_out;
-		}
-	} else {
-		/* if the controller reset bit did clear, then set clock regs */
-		if (!(mci_readl(host, CTRL) & SDMMC_CTRL_RESET)) {
-			dev_err(host->dev,
-				"%s: fifo/dma reset bits didn't clear but ciu was reset, doing clock update\n",
-				__func__);
-			goto ciu_out;
-		}
-	}
-
-	if (host->use_dma == TRANS_MODE_IDMAC)
-		/* It is also recommended that we reset and reprogram idmac */
-		dw_mci_idmac_reset(host);
-
-	ret = true;
-
-ciu_out:
-	/* After a CTRL reset we need to have CIU set clock registers  */
-	mci_send_cmd(host->cur_slot, SDMMC_CMD_UPD_CLK, 0);
-
-	return ret;
-}
-
 static void dw_mci_cmd11_timer(unsigned long arg)
 {
 	struct dw_mci *host = (struct dw_mci *)arg;
diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c
index 819ad32964fc..57e254aac48d 100644
--- a/drivers/mmc/host/jz4740_mmc.c
+++ b/drivers/mmc/host/jz4740_mmc.c
@@ -200,11 +200,6 @@ free_master_write:
 	return -ENODEV;
 }
 
-static inline int jz4740_mmc_get_dma_dir(struct mmc_data *data)
-{
-	return (data->flags & MMC_DATA_READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-}
-
 static inline struct dma_chan *jz4740_mmc_get_dma_chan(struct jz4740_mmc_host *host,
 						       struct mmc_data *data)
 {
@@ -215,7 +210,7 @@ static void jz4740_mmc_dma_unmap(struct jz4740_mmc_host *host,
 				 struct mmc_data *data)
 {
 	struct dma_chan *chan = jz4740_mmc_get_dma_chan(host, data);
-	enum dma_data_direction dir = jz4740_mmc_get_dma_dir(data);
+	enum dma_data_direction dir = mmc_get_dma_dir(data);
 
 	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
 }
@@ -227,7 +222,7 @@ static int jz4740_mmc_prepare_dma_data(struct jz4740_mmc_host *host,
 				       struct dma_chan *chan)
 {
 	struct jz4740_mmc_host_next *next_data = &host->next_data;
-	enum dma_data_direction dir = jz4740_mmc_get_dma_dir(data);
+	enum dma_data_direction dir = mmc_get_dma_dir(data);
 	int sg_len;
 
 	if (!next && data->host_cookie &&
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 5a959783304b..1842ed341af1 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -36,23 +36,21 @@
 #include <linux/clk-provider.h>
 #include <linux/regulator/consumer.h>
 #include <linux/interrupt.h>
+#include <linux/bitfield.h>
 
 #define DRIVER_NAME "meson-gx-mmc"
 
 #define SD_EMMC_CLOCK 0x0
-#define   CLK_DIV_SHIFT 0
-#define   CLK_DIV_WIDTH 6
-#define   CLK_DIV_MASK 0x3f
+#define   CLK_DIV_MASK GENMASK(5, 0)
 #define   CLK_DIV_MAX 63
-#define   CLK_SRC_SHIFT 6
-#define   CLK_SRC_WIDTH 2
-#define   CLK_SRC_MASK 0x3
+#define   CLK_SRC_MASK GENMASK(7, 6)
 #define   CLK_SRC_XTAL 0   /* external crystal */
 #define   CLK_SRC_XTAL_RATE 24000000
 #define   CLK_SRC_PLL 1    /* FCLK_DIV2 */
 #define   CLK_SRC_PLL_RATE 1000000000
-#define   CLK_PHASE_SHIFT 8
-#define   CLK_PHASE_MASK 0x3
+#define   CLK_CORE_PHASE_MASK GENMASK(9, 8)
+#define   CLK_TX_PHASE_MASK GENMASK(11, 10)
+#define   CLK_RX_PHASE_MASK GENMASK(13, 12)
 #define   CLK_PHASE_0 0
 #define   CLK_PHASE_90 1
 #define   CLK_PHASE_180 2
@@ -65,22 +63,17 @@
 #define SD_EMMC_START 0x40
 #define   START_DESC_INIT BIT(0)
 #define   START_DESC_BUSY BIT(1)
-#define   START_DESC_ADDR_SHIFT 2
-#define   START_DESC_ADDR_MASK (~0x3)
+#define   START_DESC_ADDR_MASK GENMASK(31, 2)
 
 #define SD_EMMC_CFG 0x44
-#define   CFG_BUS_WIDTH_SHIFT 0
-#define   CFG_BUS_WIDTH_MASK 0x3
+#define   CFG_BUS_WIDTH_MASK GENMASK(1, 0)
 #define   CFG_BUS_WIDTH_1 0x0
 #define   CFG_BUS_WIDTH_4 0x1
 #define   CFG_BUS_WIDTH_8 0x2
 #define   CFG_DDR BIT(2)
-#define   CFG_BLK_LEN_SHIFT 4
-#define   CFG_BLK_LEN_MASK 0xf
-#define   CFG_RESP_TIMEOUT_SHIFT 8
-#define   CFG_RESP_TIMEOUT_MASK 0xf
-#define   CFG_RC_CC_SHIFT 12
-#define   CFG_RC_CC_MASK 0xf
+#define   CFG_BLK_LEN_MASK GENMASK(7, 4)
+#define   CFG_RESP_TIMEOUT_MASK GENMASK(11, 8)
+#define   CFG_RC_CC_MASK GENMASK(15, 12)
 #define   CFG_STOP_CLOCK BIT(22)
 #define   CFG_CLK_ALWAYS_ON BIT(18)
 #define   CFG_CHK_DS BIT(20)
@@ -90,9 +83,8 @@
 #define   STATUS_BUSY BIT(31)
 
 #define SD_EMMC_IRQ_EN 0x4c
-#define   IRQ_EN_MASK 0x3fff
-#define   IRQ_RXD_ERR_SHIFT 0
-#define   IRQ_RXD_ERR_MASK 0xff
+#define   IRQ_EN_MASK GENMASK(13, 0)
+#define   IRQ_RXD_ERR_MASK GENMASK(7, 0)
 #define   IRQ_TXD_ERR BIT(8)
 #define   IRQ_DESC_ERR BIT(9)
 #define   IRQ_RESP_ERR BIT(10)
@@ -116,23 +108,39 @@
 
 #define SD_EMMC_CFG_BLK_SIZE 512 /* internal buffer max: 512 bytes */
 #define SD_EMMC_CFG_RESP_TIMEOUT 256 /* in clock cycles */
+#define SD_EMMC_CMD_TIMEOUT 1024 /* in ms */
+#define SD_EMMC_CMD_TIMEOUT_DATA 4096 /* in ms */
 #define SD_EMMC_CFG_CMD_GAP 16 /* in clock cycles */
+#define SD_EMMC_DESC_BUF_LEN PAGE_SIZE
+
+#define SD_EMMC_PRE_REQ_DONE BIT(0)
+#define SD_EMMC_DESC_CHAIN_MODE BIT(1)
+
 #define MUX_CLK_NUM_PARENTS 2
 
+struct meson_tuning_params {
+	u8 core_phase;
+	u8 tx_phase;
+	u8 rx_phase;
+};
+
+struct sd_emmc_desc {
+	u32 cmd_cfg;
+	u32 cmd_arg;
+	u32 cmd_data;
+	u32 cmd_resp;
+};
+
 struct meson_host {
 	struct	device		*dev;
 	struct	mmc_host	*mmc;
-	struct	mmc_request	*mrq;
 	struct	mmc_command	*cmd;
 
 	spinlock_t lock;
 	void __iomem *regs;
-	int irq;
-	u32 ocr_mask;
 	struct clk *core_clk;
 	struct clk_mux mux;
 	struct clk *mux_clk;
-	struct clk *mux_parent[MUX_CLK_NUM_PARENTS];
 	unsigned long current_clock;
 
 	struct clk_divider cfg_div;
@@ -141,23 +149,18 @@ struct meson_host {
 	unsigned int bounce_buf_size;
 	void *bounce_buf;
 	dma_addr_t bounce_dma_addr;
+	struct sd_emmc_desc *descs;
+	dma_addr_t descs_dma_addr;
 
+	struct meson_tuning_params tp;
 	bool vqmmc_enabled;
 };
 
-struct sd_emmc_desc {
-	u32 cmd_cfg;
-	u32 cmd_arg;
-	u32 cmd_data;
-	u32 cmd_resp;
-};
-#define CMD_CFG_LENGTH_SHIFT 0
-#define CMD_CFG_LENGTH_MASK 0x1ff
+#define CMD_CFG_LENGTH_MASK GENMASK(8, 0)
 #define CMD_CFG_BLOCK_MODE BIT(9)
 #define CMD_CFG_R1B BIT(10)
 #define CMD_CFG_END_OF_CHAIN BIT(11)
-#define CMD_CFG_TIMEOUT_SHIFT 12
-#define CMD_CFG_TIMEOUT_MASK 0xf
+#define CMD_CFG_TIMEOUT_MASK GENMASK(15, 12)
 #define CMD_CFG_NO_RESP BIT(16)
 #define CMD_CFG_NO_CMD BIT(17)
 #define CMD_CFG_DATA_IO BIT(18)
@@ -166,17 +169,99 @@ struct sd_emmc_desc {
 #define CMD_CFG_RESP_128 BIT(21)
 #define CMD_CFG_RESP_NUM BIT(22)
 #define CMD_CFG_DATA_NUM BIT(23)
-#define CMD_CFG_CMD_INDEX_SHIFT 24
-#define CMD_CFG_CMD_INDEX_MASK 0x3f
+#define CMD_CFG_CMD_INDEX_MASK GENMASK(29, 24)
 #define CMD_CFG_ERROR BIT(30)
 #define CMD_CFG_OWNER BIT(31)
 
-#define CMD_DATA_MASK (~0x3)
+#define CMD_DATA_MASK GENMASK(31, 2)
 #define CMD_DATA_BIG_ENDIAN BIT(1)
 #define CMD_DATA_SRAM BIT(0)
-#define CMD_RESP_MASK (~0x1)
+#define CMD_RESP_MASK GENMASK(31, 1)
 #define CMD_RESP_SRAM BIT(0)
 
+static unsigned int meson_mmc_get_timeout_msecs(struct mmc_data *data)
+{
+	unsigned int timeout = data->timeout_ns / NSEC_PER_MSEC;
+
+	if (!timeout)
+		return SD_EMMC_CMD_TIMEOUT_DATA;
+
+	timeout = roundup_pow_of_two(timeout);
+
+	return min(timeout, 32768U); /* max. 2^15 ms */
+}
+
+static struct mmc_command *meson_mmc_get_next_command(struct mmc_command *cmd)
+{
+	if (cmd->opcode == MMC_SET_BLOCK_COUNT && !cmd->error)
+		return cmd->mrq->cmd;
+	else if (mmc_op_multi(cmd->opcode) &&
+		 (!cmd->mrq->sbc || cmd->error || cmd->data->error))
+		return cmd->mrq->stop;
+	else
+		return NULL;
+}
+
+static void meson_mmc_get_transfer_mode(struct mmc_host *mmc,
+					struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+	struct scatterlist *sg;
+	int i;
+	bool use_desc_chain_mode = true;
+
+	for_each_sg(data->sg, sg, data->sg_len, i)
+		/* check for 8 byte alignment */
+		if (sg->offset & 7) {
+			WARN_ONCE(1, "unaligned scatterlist buffer\n");
+			use_desc_chain_mode = false;
+			break;
+		}
+
+	if (use_desc_chain_mode)
+		data->host_cookie |= SD_EMMC_DESC_CHAIN_MODE;
+}
+
+static inline bool meson_mmc_desc_chain_mode(const struct mmc_data *data)
+{
+	return data->host_cookie & SD_EMMC_DESC_CHAIN_MODE;
+}
+
+static inline bool meson_mmc_bounce_buf_read(const struct mmc_data *data)
+{
+	return data && data->flags & MMC_DATA_READ &&
+	       !meson_mmc_desc_chain_mode(data);
+}
+
+static void meson_mmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (!data)
+		return;
+
+	meson_mmc_get_transfer_mode(mmc, mrq);
+	data->host_cookie |= SD_EMMC_PRE_REQ_DONE;
+
+	if (!meson_mmc_desc_chain_mode(data))
+		return;
+
+	data->sg_count = dma_map_sg(mmc_dev(mmc), data->sg, data->sg_len,
+                                   mmc_get_dma_dir(data));
+	if (!data->sg_count)
+		dev_err(mmc_dev(mmc), "dma_map_sg failed");
+}
+
+static void meson_mmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
+			       int err)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (data && meson_mmc_desc_chain_mode(data) && data->sg_count)
+		dma_unmap_sg(mmc_dev(mmc), data->sg, data->sg_len,
+			     mmc_get_dma_dir(data));
+}
+
 static int meson_mmc_clk_set(struct meson_host *host, unsigned long clk_rate)
 {
 	struct mmc_host *mmc = host->mmc;
@@ -244,26 +329,23 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	char clk_name[32];
 	int i, ret = 0;
 	const char *mux_parent_names[MUX_CLK_NUM_PARENTS];
-	unsigned int mux_parent_count = 0;
 	const char *clk_div_parents[1];
 	u32 clk_reg, cfg;
 
 	/* get the mux parents */
 	for (i = 0; i < MUX_CLK_NUM_PARENTS; i++) {
+		struct clk *clk;
 		char name[16];
 
 		snprintf(name, sizeof(name), "clkin%d", i);
-		host->mux_parent[i] = devm_clk_get(host->dev, name);
-		if (IS_ERR(host->mux_parent[i])) {
-			ret = PTR_ERR(host->mux_parent[i]);
-			if (PTR_ERR(host->mux_parent[i]) != -EPROBE_DEFER)
+		clk = devm_clk_get(host->dev, name);
+		if (IS_ERR(clk)) {
+			if (clk != ERR_PTR(-EPROBE_DEFER))
 				dev_err(host->dev, "Missing clock %s\n", name);
-			host->mux_parent[i] = NULL;
-			return ret;
+			return PTR_ERR(clk);
 		}
 
-		mux_parent_names[i] = __clk_get_name(host->mux_parent[i]);
-		mux_parent_count++;
+		mux_parent_names[i] = __clk_get_name(clk);
 	}
 
 	/* create the mux */
@@ -272,10 +354,9 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	init.ops = &clk_mux_ops;
 	init.flags = 0;
 	init.parent_names = mux_parent_names;
-	init.num_parents = mux_parent_count;
-
+	init.num_parents = MUX_CLK_NUM_PARENTS;
 	host->mux.reg = host->regs + SD_EMMC_CLOCK;
-	host->mux.shift = CLK_SRC_SHIFT;
+	host->mux.shift = __bf_shf(CLK_SRC_MASK);
 	host->mux.mask = CLK_SRC_MASK;
 	host->mux.flags = 0;
 	host->mux.table = NULL;
@@ -287,7 +368,7 @@ static int meson_mmc_clk_init(struct meson_host *host)
 
 	/* create the divider */
 	snprintf(clk_name, sizeof(clk_name), "%s#div", dev_name(host->dev));
-	init.name = devm_kstrdup(host->dev, clk_name, GFP_KERNEL);
+	init.name = clk_name;
 	init.ops = &clk_divider_ops;
 	init.flags = CLK_SET_RATE_PARENT;
 	clk_div_parents[0] = __clk_get_name(host->mux_clk);
@@ -295,8 +376,8 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	init.num_parents = ARRAY_SIZE(clk_div_parents);
 
 	host->cfg_div.reg = host->regs + SD_EMMC_CLOCK;
-	host->cfg_div.shift = CLK_DIV_SHIFT;
-	host->cfg_div.width = CLK_DIV_WIDTH;
+	host->cfg_div.shift = __bf_shf(CLK_DIV_MASK);
+	host->cfg_div.width = __builtin_popcountl(CLK_DIV_MASK);
 	host->cfg_div.hw.init = &init;
 	host->cfg_div.flags = CLK_DIVIDER_ONE_BASED |
 		CLK_DIVIDER_ROUND_CLOSEST | CLK_DIVIDER_ALLOW_ZERO;
@@ -307,9 +388,11 @@ static int meson_mmc_clk_init(struct meson_host *host)
 
 	/* init SD_EMMC_CLOCK to sane defaults w/min clock rate */
 	clk_reg = 0;
-	clk_reg |= CLK_PHASE_180 << CLK_PHASE_SHIFT;
-	clk_reg |= CLK_SRC_XTAL << CLK_SRC_SHIFT;
-	clk_reg |= CLK_DIV_MAX << CLK_DIV_SHIFT;
+	clk_reg |= FIELD_PREP(CLK_CORE_PHASE_MASK, host->tp.core_phase);
+	clk_reg |= FIELD_PREP(CLK_TX_PHASE_MASK, host->tp.tx_phase);
+	clk_reg |= FIELD_PREP(CLK_RX_PHASE_MASK, host->tp.rx_phase);
+	clk_reg |= FIELD_PREP(CLK_SRC_MASK, CLK_SRC_XTAL);
+	clk_reg |= FIELD_PREP(CLK_DIV_MASK, CLK_DIV_MAX);
 	clk_reg &= ~CLK_ALWAYS_ON;
 	writel(clk_reg, host->regs + SD_EMMC_CLOCK);
 
@@ -327,12 +410,37 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	host->mmc->f_min = clk_round_rate(host->cfg_div_clk, 400000);
 
 	ret = meson_mmc_clk_set(host, host->mmc->f_min);
-	if (!ret)
+	if (ret)
 		clk_disable_unprepare(host->cfg_div_clk);
 
 	return ret;
 }
 
+static void meson_mmc_set_tuning_params(struct mmc_host *mmc)
+{
+	struct meson_host *host = mmc_priv(mmc);
+	u32 regval;
+
+	/* stop clock */
+	regval = readl(host->regs + SD_EMMC_CFG);
+	regval |= CFG_STOP_CLOCK;
+	writel(regval, host->regs + SD_EMMC_CFG);
+
+	regval = readl(host->regs + SD_EMMC_CLOCK);
+	regval &= ~CLK_CORE_PHASE_MASK;
+	regval |= FIELD_PREP(CLK_CORE_PHASE_MASK, host->tp.core_phase);
+	regval &= ~CLK_TX_PHASE_MASK;
+	regval |= FIELD_PREP(CLK_TX_PHASE_MASK, host->tp.tx_phase);
+	regval &= ~CLK_RX_PHASE_MASK;
+	regval |= FIELD_PREP(CLK_RX_PHASE_MASK, host->tp.rx_phase);
+	writel(regval, host->regs + SD_EMMC_CLOCK);
+
+	/* start clock */
+	regval = readl(host->regs + SD_EMMC_CFG);
+	regval &= ~CFG_STOP_CLOCK;
+	writel(regval, host->regs + SD_EMMC_CFG);
+}
+
 static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct meson_host *host = mmc_priv(mmc);
@@ -397,17 +505,8 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	val = readl(host->regs + SD_EMMC_CFG);
 	orig = val;
 
-	val &= ~(CFG_BUS_WIDTH_MASK << CFG_BUS_WIDTH_SHIFT);
-	val |= bus_width << CFG_BUS_WIDTH_SHIFT;
-
-	val &= ~(CFG_BLK_LEN_MASK << CFG_BLK_LEN_SHIFT);
-	val |= ilog2(SD_EMMC_CFG_BLK_SIZE) << CFG_BLK_LEN_SHIFT;
-
-	val &= ~(CFG_RESP_TIMEOUT_MASK << CFG_RESP_TIMEOUT_SHIFT);
-	val |= ilog2(SD_EMMC_CFG_RESP_TIMEOUT) << CFG_RESP_TIMEOUT_SHIFT;
-
-	val &= ~(CFG_RC_CC_MASK << CFG_RC_CC_SHIFT);
-	val |= ilog2(SD_EMMC_CFG_CMD_GAP) << CFG_RC_CC_SHIFT;
+	val &= ~CFG_BUS_WIDTH_MASK;
+	val |= FIELD_PREP(CFG_BUS_WIDTH_MASK, bus_width);
 
 	val &= ~CFG_DDR;
 	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
@@ -419,149 +518,189 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->timing == MMC_TIMING_MMC_HS400)
 		val |= CFG_CHK_DS;
 
-	writel(val, host->regs + SD_EMMC_CFG);
-
-	if (val != orig)
+	if (val != orig) {
+		writel(val, host->regs + SD_EMMC_CFG);
 		dev_dbg(host->dev, "%s: SD_EMMC_CFG: 0x%08x -> 0x%08x\n",
 			__func__, orig, val);
+	}
 }
 
-static int meson_mmc_request_done(struct mmc_host *mmc, struct mmc_request *mrq)
+static void meson_mmc_request_done(struct mmc_host *mmc,
+				   struct mmc_request *mrq)
 {
 	struct meson_host *host = mmc_priv(mmc);
 
-	WARN_ON(host->mrq != mrq);
-
-	host->mrq = NULL;
 	host->cmd = NULL;
 	mmc_request_done(host->mmc, mrq);
-
-	return 0;
 }
 
-static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd)
+static void meson_mmc_set_blksz(struct mmc_host *mmc, unsigned int blksz)
 {
 	struct meson_host *host = mmc_priv(mmc);
-	struct sd_emmc_desc *desc, desc_tmp;
-	u32 cfg;
-	u8 blk_len, cmd_cfg_timeout;
-	unsigned int xfer_bytes = 0;
+	u32 cfg, blksz_old;
 
-	/* Setup descriptors */
-	dma_rmb();
-	desc = &desc_tmp;
-	memset(desc, 0, sizeof(struct sd_emmc_desc));
+	cfg = readl(host->regs + SD_EMMC_CFG);
+	blksz_old = FIELD_GET(CFG_BLK_LEN_MASK, cfg);
+
+	if (!is_power_of_2(blksz))
+		dev_err(host->dev, "blksz %u is not a power of 2\n", blksz);
+
+	blksz = ilog2(blksz);
+
+	/* check if block-size matches, if not update */
+	if (blksz == blksz_old)
+		return;
 
-	desc->cmd_cfg |= (cmd->opcode & CMD_CFG_CMD_INDEX_MASK)	<<
-		CMD_CFG_CMD_INDEX_SHIFT;
-	desc->cmd_cfg |= CMD_CFG_OWNER;  /* owned by CPU */
-	desc->cmd_arg = cmd->arg;
+	dev_dbg(host->dev, "%s: update blk_len %d -> %d\n", __func__,
+		blksz_old, blksz);
 
-	/* Response */
+	cfg &= ~CFG_BLK_LEN_MASK;
+	cfg |= FIELD_PREP(CFG_BLK_LEN_MASK, blksz);
+	writel(cfg, host->regs + SD_EMMC_CFG);
+}
+
+static void meson_mmc_set_response_bits(struct mmc_command *cmd, u32 *cmd_cfg)
+{
 	if (cmd->flags & MMC_RSP_PRESENT) {
-		desc->cmd_cfg &= ~CMD_CFG_NO_RESP;
 		if (cmd->flags & MMC_RSP_136)
-			desc->cmd_cfg |= CMD_CFG_RESP_128;
-		desc->cmd_cfg |= CMD_CFG_RESP_NUM;
-		desc->cmd_resp = 0;
+			*cmd_cfg |= CMD_CFG_RESP_128;
+		*cmd_cfg |= CMD_CFG_RESP_NUM;
 
 		if (!(cmd->flags & MMC_RSP_CRC))
-			desc->cmd_cfg |= CMD_CFG_RESP_NOCRC;
+			*cmd_cfg |= CMD_CFG_RESP_NOCRC;
 
 		if (cmd->flags & MMC_RSP_BUSY)
-			desc->cmd_cfg |= CMD_CFG_R1B;
+			*cmd_cfg |= CMD_CFG_R1B;
 	} else {
-		desc->cmd_cfg |= CMD_CFG_NO_RESP;
+		*cmd_cfg |= CMD_CFG_NO_RESP;
 	}
+}
+
+static void meson_mmc_desc_chain_transfer(struct mmc_host *mmc, u32 cmd_cfg)
+{
+	struct meson_host *host = mmc_priv(mmc);
+	struct sd_emmc_desc *desc = host->descs;
+	struct mmc_data *data = host->cmd->data;
+	struct scatterlist *sg;
+	u32 start;
+	int i;
+
+	if (data->flags & MMC_DATA_WRITE)
+		cmd_cfg |= CMD_CFG_DATA_WR;
+
+	if (data->blocks > 1) {
+		cmd_cfg |= CMD_CFG_BLOCK_MODE;
+		meson_mmc_set_blksz(mmc, data->blksz);
+	}
+
+	for_each_sg(data->sg, sg, data->sg_count, i) {
+		unsigned int len = sg_dma_len(sg);
+
+		if (data->blocks > 1)
+			len /= data->blksz;
+
+		desc[i].cmd_cfg = cmd_cfg;
+		desc[i].cmd_cfg |= FIELD_PREP(CMD_CFG_LENGTH_MASK, len);
+		if (i > 0)
+			desc[i].cmd_cfg |= CMD_CFG_NO_CMD;
+		desc[i].cmd_arg = host->cmd->arg;
+		desc[i].cmd_resp = 0;
+		desc[i].cmd_data = sg_dma_address(sg);
+	}
+	desc[data->sg_count - 1].cmd_cfg |= CMD_CFG_END_OF_CHAIN;
+
+	dma_wmb(); /* ensure descriptor is written before kicked */
+	start = host->descs_dma_addr | START_DESC_BUSY;
+	writel(start, host->regs + SD_EMMC_START);
+}
+
+static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd)
+{
+	struct meson_host *host = mmc_priv(mmc);
+	struct mmc_data *data = cmd->data;
+	u32 cmd_cfg = 0, cmd_data = 0;
+	unsigned int xfer_bytes = 0;
+
+	/* Setup descriptors */
+	dma_rmb();
+
+	host->cmd = cmd;
+
+	cmd_cfg |= FIELD_PREP(CMD_CFG_CMD_INDEX_MASK, cmd->opcode);
+	cmd_cfg |= CMD_CFG_OWNER;  /* owned by CPU */
+
+	meson_mmc_set_response_bits(cmd, &cmd_cfg);
 
 	/* data? */
-	if (cmd->data) {
-		desc->cmd_cfg |= CMD_CFG_DATA_IO;
-		if (cmd->data->blocks > 1) {
-			desc->cmd_cfg |= CMD_CFG_BLOCK_MODE;
-			desc->cmd_cfg |=
-				(cmd->data->blocks & CMD_CFG_LENGTH_MASK) <<
-				CMD_CFG_LENGTH_SHIFT;
-
-			/* check if block-size matches, if not update */
-			cfg = readl(host->regs + SD_EMMC_CFG);
-			blk_len = cfg & (CFG_BLK_LEN_MASK << CFG_BLK_LEN_SHIFT);
-			blk_len >>= CFG_BLK_LEN_SHIFT;
-			if (blk_len != ilog2(cmd->data->blksz)) {
-				dev_dbg(host->dev, "%s: update blk_len %d -> %d\n",
-					__func__, blk_len,
-					ilog2(cmd->data->blksz));
-				blk_len = ilog2(cmd->data->blksz);
-				cfg &= ~(CFG_BLK_LEN_MASK << CFG_BLK_LEN_SHIFT);
-				cfg |= blk_len << CFG_BLK_LEN_SHIFT;
-				writel(cfg, host->regs + SD_EMMC_CFG);
-			}
+	if (data) {
+		data->bytes_xfered = 0;
+		cmd_cfg |= CMD_CFG_DATA_IO;
+		cmd_cfg |= FIELD_PREP(CMD_CFG_TIMEOUT_MASK,
+				      ilog2(meson_mmc_get_timeout_msecs(data)));
+
+		if (meson_mmc_desc_chain_mode(data)) {
+			meson_mmc_desc_chain_transfer(mmc, cmd_cfg);
+			return;
+		}
+
+		if (data->blocks > 1) {
+			cmd_cfg |= CMD_CFG_BLOCK_MODE;
+			cmd_cfg |= FIELD_PREP(CMD_CFG_LENGTH_MASK,
+					      data->blocks);
+			meson_mmc_set_blksz(mmc, data->blksz);
 		} else {
-			desc->cmd_cfg &= ~CMD_CFG_BLOCK_MODE;
-			desc->cmd_cfg |=
-				(cmd->data->blksz & CMD_CFG_LENGTH_MASK) <<
-				CMD_CFG_LENGTH_SHIFT;
+			cmd_cfg |= FIELD_PREP(CMD_CFG_LENGTH_MASK, data->blksz);
 		}
 
-		cmd->data->bytes_xfered = 0;
-		xfer_bytes = cmd->data->blksz * cmd->data->blocks;
-		if (cmd->data->flags & MMC_DATA_WRITE) {
-			desc->cmd_cfg |= CMD_CFG_DATA_WR;
+		xfer_bytes = data->blksz * data->blocks;
+		if (data->flags & MMC_DATA_WRITE) {
+			cmd_cfg |= CMD_CFG_DATA_WR;
 			WARN_ON(xfer_bytes > host->bounce_buf_size);
-			sg_copy_to_buffer(cmd->data->sg, cmd->data->sg_len,
+			sg_copy_to_buffer(data->sg, data->sg_len,
 					  host->bounce_buf, xfer_bytes);
-			cmd->data->bytes_xfered = xfer_bytes;
 			dma_wmb();
-		} else {
-			desc->cmd_cfg &= ~CMD_CFG_DATA_WR;
-		}
-
-		if (xfer_bytes > 0) {
-			desc->cmd_cfg &= ~CMD_CFG_DATA_NUM;
-			desc->cmd_data = host->bounce_dma_addr & CMD_DATA_MASK;
-		} else {
-			/* write data to data_addr */
-			desc->cmd_cfg |= CMD_CFG_DATA_NUM;
-			desc->cmd_data = 0;
 		}
 
-		cmd_cfg_timeout = 12;
+		cmd_data = host->bounce_dma_addr & CMD_DATA_MASK;
 	} else {
-		desc->cmd_cfg &= ~CMD_CFG_DATA_IO;
-		cmd_cfg_timeout = 10;
+		cmd_cfg |= FIELD_PREP(CMD_CFG_TIMEOUT_MASK,
+				      ilog2(SD_EMMC_CMD_TIMEOUT));
 	}
-	desc->cmd_cfg |= (cmd_cfg_timeout & CMD_CFG_TIMEOUT_MASK) <<
-		CMD_CFG_TIMEOUT_SHIFT;
-
-	host->cmd = cmd;
 
 	/* Last descriptor */
-	desc->cmd_cfg |= CMD_CFG_END_OF_CHAIN;
-	writel(desc->cmd_cfg, host->regs + SD_EMMC_CMD_CFG);
-	writel(desc->cmd_data, host->regs + SD_EMMC_CMD_DAT);
-	writel(desc->cmd_resp, host->regs + SD_EMMC_CMD_RSP);
+	cmd_cfg |= CMD_CFG_END_OF_CHAIN;
+	writel(cmd_cfg, host->regs + SD_EMMC_CMD_CFG);
+	writel(cmd_data, host->regs + SD_EMMC_CMD_DAT);
+	writel(0, host->regs + SD_EMMC_CMD_RSP);
 	wmb(); /* ensure descriptor is written before kicked */
-	writel(desc->cmd_arg, host->regs + SD_EMMC_CMD_ARG);
+	writel(cmd->arg, host->regs + SD_EMMC_CMD_ARG);
 }
 
 static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct meson_host *host = mmc_priv(mmc);
+	bool needs_pre_post_req = mrq->data &&
+			!(mrq->data->host_cookie & SD_EMMC_PRE_REQ_DONE);
 
-	WARN_ON(host->mrq != NULL);
+	if (needs_pre_post_req) {
+		meson_mmc_get_transfer_mode(mmc, mrq);
+		if (!meson_mmc_desc_chain_mode(mrq->data))
+			needs_pre_post_req = false;
+	}
+
+	if (needs_pre_post_req)
+		meson_mmc_pre_req(mmc, mrq);
 
 	/* Stop execution */
 	writel(0, host->regs + SD_EMMC_START);
 
-	host->mrq = mrq;
+	meson_mmc_start_cmd(mmc, mrq->sbc ?: mrq->cmd);
 
-	if (mrq->sbc)
-		meson_mmc_start_cmd(mmc, mrq->sbc);
-	else
-		meson_mmc_start_cmd(mmc, mrq->cmd);
+	if (needs_pre_post_req)
+		meson_mmc_post_req(mmc, mrq, 0);
 }
 
-static int meson_mmc_read_resp(struct mmc_host *mmc, struct mmc_command *cmd)
+static void meson_mmc_read_resp(struct mmc_host *mmc, struct mmc_command *cmd)
 {
 	struct meson_host *host = mmc_priv(mmc);
 
@@ -573,15 +712,13 @@ static int meson_mmc_read_resp(struct mmc_host *mmc, struct mmc_command *cmd)
 	} else if (cmd->flags & MMC_RSP_PRESENT) {
 		cmd->resp[0] = readl(host->regs + SD_EMMC_CMD_RSP);
 	}
-
-	return 0;
 }
 
 static irqreturn_t meson_mmc_irq(int irq, void *dev_id)
 {
 	struct meson_host *host = dev_id;
-	struct mmc_request *mrq;
 	struct mmc_command *cmd;
+	struct mmc_data *data;
 	u32 irq_en, status, raw_status;
 	irqreturn_t ret = IRQ_HANDLED;
 
@@ -590,14 +727,11 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id)
 
 	cmd = host->cmd;
 
-	mrq = host->mrq;
-
-	if (WARN_ON(!mrq))
-		return IRQ_NONE;
-
 	if (WARN_ON(!cmd))
 		return IRQ_NONE;
 
+	data = cmd->data;
+
 	spin_lock(&host->lock);
 	irq_en = readl(host->regs + SD_EMMC_IRQ_EN);
 	raw_status = readl(host->regs + SD_EMMC_STATUS);
@@ -610,6 +744,8 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id)
 		goto out;
 	}
 
+	meson_mmc_read_resp(host->mmc, cmd);
+
 	cmd->error = 0;
 	if (status & IRQ_RXD_ERR_MASK) {
 		dev_dbg(host->dev, "Unhandled IRQ: RXD error\n");
@@ -636,12 +772,16 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id)
 	if (status & IRQ_SDIO)
 		dev_dbg(host->dev, "Unhandled IRQ: SDIO.\n");
 
-	if (status & (IRQ_END_OF_CHAIN | IRQ_RESP_STATUS))
-		ret = IRQ_WAKE_THREAD;
-	else  {
+	if (status & (IRQ_END_OF_CHAIN | IRQ_RESP_STATUS)) {
+		if (data && !cmd->error)
+			data->bytes_xfered = data->blksz * data->blocks;
+		if (meson_mmc_bounce_buf_read(data) ||
+		    meson_mmc_get_next_command(cmd))
+			ret = IRQ_WAKE_THREAD;
+	} else {
 		dev_warn(host->dev, "Unknown IRQ! status=0x%04x: MMC CMD%u arg=0x%08x flags=0x%08x stop=%d\n",
 			 status, cmd->opcode, cmd->arg,
-			 cmd->flags, mrq->stop ? 1 : 0);
+			 cmd->flags, cmd->mrq->stop ? 1 : 0);
 		if (cmd->data) {
 			struct mmc_data *data = cmd->data;
 
@@ -656,10 +796,8 @@ out:
 	/* ack all (enabled) interrupts */
 	writel(status, host->regs + SD_EMMC_STATUS);
 
-	if (ret == IRQ_HANDLED) {
-		meson_mmc_read_resp(host->mmc, cmd);
+	if (ret == IRQ_HANDLED)
 		meson_mmc_request_done(host->mmc, cmd->mrq);
-	}
 
 	spin_unlock(&host->lock);
 	return ret;
@@ -668,35 +806,53 @@ out:
 static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id)
 {
 	struct meson_host *host = dev_id;
-	struct mmc_request *mrq = host->mrq;
-	struct mmc_command *cmd = host->cmd;
+	struct mmc_command *next_cmd, *cmd = host->cmd;
 	struct mmc_data *data;
 	unsigned int xfer_bytes;
 
-	if (WARN_ON(!mrq))
-		return IRQ_NONE;
-
 	if (WARN_ON(!cmd))
 		return IRQ_NONE;
 
 	data = cmd->data;
-	if (data && data->flags & MMC_DATA_READ) {
+	if (meson_mmc_bounce_buf_read(data)) {
 		xfer_bytes = data->blksz * data->blocks;
 		WARN_ON(xfer_bytes > host->bounce_buf_size);
 		sg_copy_from_buffer(data->sg, data->sg_len,
 				    host->bounce_buf, xfer_bytes);
-		data->bytes_xfered = xfer_bytes;
 	}
 
-	meson_mmc_read_resp(host->mmc, cmd);
-	if (!data || !data->stop || mrq->sbc)
-		meson_mmc_request_done(host->mmc, mrq);
+	next_cmd = meson_mmc_get_next_command(cmd);
+	if (next_cmd)
+		meson_mmc_start_cmd(host->mmc, next_cmd);
 	else
-		meson_mmc_start_cmd(host->mmc, data->stop);
+		meson_mmc_request_done(host->mmc, cmd->mrq);
 
 	return IRQ_HANDLED;
 }
 
+static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct meson_host *host = mmc_priv(mmc);
+	struct meson_tuning_params tp_old = host->tp;
+	int ret = -EINVAL, i, cmd_error;
+
+	dev_info(mmc_dev(mmc), "(re)tuning...\n");
+
+	for (i = CLK_PHASE_0; i <= CLK_PHASE_270; i++) {
+		host->tp.rx_phase = i;
+		/* exclude the active parameter set if retuning */
+		if (!memcmp(&tp_old, &host->tp, sizeof(tp_old)) &&
+		    mmc->doing_retune)
+			continue;
+		meson_mmc_set_tuning_params(mmc);
+		ret = mmc_send_tuning(mmc, opcode, &cmd_error);
+		if (!ret)
+			break;
+	}
+
+	return ret;
+}
+
 /*
  * NOTE: we only need this until the GPIO/pinctrl driver can handle
  * interrupts.  For now, the MMC core will use this for polling.
@@ -711,10 +867,25 @@ static int meson_mmc_get_cd(struct mmc_host *mmc)
 	return status;
 }
 
+static void meson_mmc_cfg_init(struct meson_host *host)
+{
+	u32 cfg = 0;
+
+	cfg |= FIELD_PREP(CFG_RESP_TIMEOUT_MASK,
+			  ilog2(SD_EMMC_CFG_RESP_TIMEOUT));
+	cfg |= FIELD_PREP(CFG_RC_CC_MASK, ilog2(SD_EMMC_CFG_CMD_GAP));
+	cfg |= FIELD_PREP(CFG_BLK_LEN_MASK, ilog2(SD_EMMC_CFG_BLK_SIZE));
+
+	writel(cfg, host->regs + SD_EMMC_CFG);
+}
+
 static const struct mmc_host_ops meson_mmc_ops = {
 	.request	= meson_mmc_request,
 	.set_ios	= meson_mmc_set_ios,
 	.get_cd         = meson_mmc_get_cd,
+	.pre_req	= meson_mmc_pre_req,
+	.post_req	= meson_mmc_post_req,
+	.execute_tuning = meson_mmc_execute_tuning,
 };
 
 static int meson_mmc_probe(struct platform_device *pdev)
@@ -722,7 +893,7 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct meson_host *host;
 	struct mmc_host *mmc;
-	int ret;
+	int ret, irq;
 
 	mmc = mmc_alloc_host(sizeof(struct meson_host), &pdev->dev);
 	if (!mmc)
@@ -754,8 +925,8 @@ static int meson_mmc_probe(struct platform_device *pdev)
 		goto free_host;
 	}
 
-	host->irq = platform_get_irq(pdev, 0);
-	if (host->irq == 0) {
+	irq = platform_get_irq(pdev, 0);
+	if (!irq) {
 		dev_err(&pdev->dev, "failed to get interrupt resource.\n");
 		ret = -EINVAL;
 		goto free_host;
@@ -771,9 +942,13 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	if (ret)
 		goto free_host;
 
+	host->tp.core_phase = CLK_PHASE_180;
+	host->tp.tx_phase = CLK_PHASE_0;
+	host->tp.rx_phase = CLK_PHASE_0;
+
 	ret = meson_mmc_clk_init(host);
 	if (ret)
-		goto free_host;
+		goto err_core_clk;
 
 	/* Stop execution */
 	writel(0, host->regs + SD_EMMC_START);
@@ -783,14 +958,20 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	writel(IRQ_EN_MASK, host->regs + SD_EMMC_STATUS);
 	writel(IRQ_EN_MASK, host->regs + SD_EMMC_IRQ_EN);
 
-	ret = devm_request_threaded_irq(&pdev->dev, host->irq,
-					meson_mmc_irq, meson_mmc_irq_thread,
-					IRQF_SHARED, DRIVER_NAME, host);
+	/* set config to sane default */
+	meson_mmc_cfg_init(host);
+
+	ret = devm_request_threaded_irq(&pdev->dev, irq, meson_mmc_irq,
+					meson_mmc_irq_thread, IRQF_SHARED,
+					NULL, host);
 	if (ret)
-		goto free_host;
+		goto err_div_clk;
 
+	mmc->caps |= MMC_CAP_CMD23;
 	mmc->max_blk_count = CMD_CFG_LENGTH_MASK;
 	mmc->max_req_size = mmc->max_blk_count * mmc->max_blk_size;
+	mmc->max_segs = SD_EMMC_DESC_BUF_LEN / sizeof(struct sd_emmc_desc);
+	mmc->max_seg_size = mmc->max_req_size;
 
 	/* data bounce buffer */
 	host->bounce_buf_size = mmc->max_req_size;
@@ -800,7 +981,15 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	if (host->bounce_buf == NULL) {
 		dev_err(host->dev, "Unable to map allocate DMA bounce buffer.\n");
 		ret = -ENOMEM;
-		goto free_host;
+		goto err_div_clk;
+	}
+
+	host->descs = dma_alloc_coherent(host->dev, SD_EMMC_DESC_BUF_LEN,
+		      &host->descs_dma_addr, GFP_KERNEL);
+	if (!host->descs) {
+		dev_err(host->dev, "Allocating descriptor DMA buffer failed\n");
+		ret = -ENOMEM;
+		goto err_bounce_buf;
 	}
 
 	mmc->ops = &meson_mmc_ops;
@@ -808,9 +997,14 @@ static int meson_mmc_probe(struct platform_device *pdev)
 
 	return 0;
 
-free_host:
+err_bounce_buf:
+	dma_free_coherent(host->dev, host->bounce_buf_size,
+			  host->bounce_buf, host->bounce_dma_addr);
+err_div_clk:
 	clk_disable_unprepare(host->cfg_div_clk);
+err_core_clk:
 	clk_disable_unprepare(host->core_clk);
+free_host:
 	mmc_free_host(mmc);
 	return ret;
 }
@@ -819,9 +1013,13 @@ static int meson_mmc_remove(struct platform_device *pdev)
 {
 	struct meson_host *host = dev_get_drvdata(&pdev->dev);
 
+	mmc_remove_host(host->mmc);
+
 	/* disable interrupts */
 	writel(0, host->regs + SD_EMMC_IRQ_EN);
 
+	dma_free_coherent(host->dev, SD_EMMC_DESC_BUF_LEN,
+			  host->descs, host->descs_dma_addr);
 	dma_free_coherent(host->dev, host->bounce_buf_size,
 			  host->bounce_buf, host->bounce_dma_addr);
 
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index e77d79c8cd9f..476e53d30128 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -888,10 +888,7 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 	u32			clock_rate;
 	unsigned long		timeout;
 
-	if (data->flags & MMC_DATA_READ)
-		direction = DMA_FROM_DEVICE;
-	else
-		direction = DMA_TO_DEVICE;
+	direction = mmc_get_dma_dir(data);
 	mmc_spi_setup_data_message(host, multiple, direction);
 	t = &host->t;
 
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 0c6420bb2f00..d1ca2f489054 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -516,17 +516,14 @@ static void mmci_dma_data_error(struct mmci_host *host)
 static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
 {
 	struct dma_chan *chan;
-	enum dma_data_direction dir;
 
-	if (data->flags & MMC_DATA_READ) {
-		dir = DMA_FROM_DEVICE;
+	if (data->flags & MMC_DATA_READ)
 		chan = host->dma_rx_channel;
-	} else {
-		dir = DMA_TO_DEVICE;
+	else
 		chan = host->dma_tx_channel;
-	}
 
-	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
+	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len,
+		     mmc_get_dma_dir(data));
 }
 
 static void mmci_dma_finalize(struct mmci_host *host, struct mmc_data *data)
@@ -589,17 +586,14 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	struct dma_chan *chan;
 	struct dma_device *device;
 	struct dma_async_tx_descriptor *desc;
-	enum dma_data_direction buffer_dirn;
 	int nr_sg;
 	unsigned long flags = DMA_CTRL_ACK;
 
 	if (data->flags & MMC_DATA_READ) {
 		conf.direction = DMA_DEV_TO_MEM;
-		buffer_dirn = DMA_FROM_DEVICE;
 		chan = host->dma_rx_channel;
 	} else {
 		conf.direction = DMA_MEM_TO_DEV;
-		buffer_dirn = DMA_TO_DEVICE;
 		chan = host->dma_tx_channel;
 	}
 
@@ -612,7 +606,8 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 		return -EINVAL;
 
 	device = chan->device;
-	nr_sg = dma_map_sg(device->dev, data->sg, data->sg_len, buffer_dirn);
+	nr_sg = dma_map_sg(device->dev, data->sg, data->sg_len,
+			   mmc_get_dma_dir(data));
 	if (nr_sg == 0)
 		return -EINVAL;
 
@@ -631,7 +626,8 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	return 0;
 
  unmap_exit:
-	dma_unmap_sg(device->dev, data->sg, data->sg_len, buffer_dirn);
+	dma_unmap_sg(device->dev, data->sg, data->sg_len,
+		     mmc_get_dma_dir(data));
 	return -ENOMEM;
 }
 
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index bbad309679cf..d4dc55ac7dea 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -256,7 +256,7 @@ static void moxart_dma_complete(void *param)
 
 static void moxart_transfer_dma(struct mmc_data *data, struct moxart_host *host)
 {
-	u32 len, dir_data, dir_slave;
+	u32 len, dir_slave;
 	long dma_time;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *dma_chan;
@@ -266,16 +266,14 @@ static void moxart_transfer_dma(struct mmc_data *data, struct moxart_host *host)
 
 	if (data->flags & MMC_DATA_WRITE) {
 		dma_chan = host->dma_chan_tx;
-		dir_data = DMA_TO_DEVICE;
 		dir_slave = DMA_MEM_TO_DEV;
 	} else {
 		dma_chan = host->dma_chan_rx;
-		dir_data = DMA_FROM_DEVICE;
 		dir_slave = DMA_DEV_TO_MEM;
 	}
 
 	len = dma_map_sg(dma_chan->device->dev, data->sg,
-			 data->sg_len, dir_data);
+			 data->sg_len, mmc_get_dma_dir(data));
 
 	if (len > 0) {
 		desc = dmaengine_prep_slave_sg(dma_chan, data->sg,
@@ -301,7 +299,7 @@ static void moxart_transfer_dma(struct mmc_data *data, struct moxart_host *host)
 
 	dma_unmap_sg(dma_chan->device->dev,
 		     data->sg, data->sg_len,
-		     dir_data);
+		     mmc_get_dma_dir(data));
 }
 
 
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 8e32580c12b5..5c1e178fc5f9 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -76,6 +76,7 @@
 #define MSDC_PATCH_BIT1  0xb4
 #define MSDC_PAD_TUNE    0xec
 #define PAD_DS_TUNE      0x188
+#define PAD_CMD_TUNE     0x18c
 #define EMMC50_CFG0      0x208
 
 /*--------------------------------------------------------------------------*/
@@ -211,13 +212,18 @@
 #define MSDC_PATCH_BIT_SPCPUSH    (0x1 << 29)	/* RW */
 #define MSDC_PATCH_BIT_DECRCTMO   (0x1 << 30)	/* RW */
 
+#define MSDC_PAD_TUNE_DATWRDLY	  (0x1f <<  0)	/* RW */
 #define MSDC_PAD_TUNE_DATRRDLY	  (0x1f <<  8)	/* RW */
 #define MSDC_PAD_TUNE_CMDRDLY	  (0x1f << 16)  /* RW */
+#define MSDC_PAD_TUNE_CMDRRDLY	  (0x1f << 22)	/* RW */
+#define MSDC_PAD_TUNE_CLKTDLY	  (0x1f << 27)  /* RW */
 
 #define PAD_DS_TUNE_DLY1	  (0x1f << 2)   /* RW */
 #define PAD_DS_TUNE_DLY2	  (0x1f << 7)   /* RW */
 #define PAD_DS_TUNE_DLY3	  (0x1f << 12)  /* RW */
 
+#define PAD_CMD_TUNE_RX_DLY3	  (0x1f << 1)  /* RW */
+
 #define EMMC50_CFG_PADCMD_LATCHCK (0x1 << 0)   /* RW */
 #define EMMC50_CFG_CRCSTS_EDGE    (0x1 << 3)   /* RW */
 #define EMMC50_CFG_CFCSTS_SEL     (0x1 << 4)   /* RW */
@@ -285,12 +291,14 @@ struct msdc_save_para {
 	u32 patch_bit0;
 	u32 patch_bit1;
 	u32 pad_ds_tune;
+	u32 pad_cmd_tune;
 	u32 emmc50_cfg0;
 };
 
 struct msdc_tune_para {
 	u32 iocon;
 	u32 pad_tune;
+	u32 pad_cmd_tune;
 };
 
 struct msdc_delay_phase {
@@ -332,6 +340,10 @@ struct msdc_host {
 	unsigned char timing;
 	bool vqmmc_enabled;
 	u32 hs400_ds_delay;
+	u32 hs200_cmd_int_delay; /* cmd internal delay for HS200/SDR104 */
+	u32 hs400_cmd_int_delay; /* cmd internal delay for HS400 */
+	bool hs400_cmd_resp_sel_rising;
+				 /* cmd response sample selection for HS400 */
 	bool hs400_mode;	/* current eMMC will run at hs400 mode */
 	struct msdc_save_para save_para; /* used when gate HCLK */
 	struct msdc_tune_para def_tune_para; /* default tune setting */
@@ -462,11 +474,9 @@ static void msdc_prepare_data(struct msdc_host *host, struct mmc_request *mrq)
 	struct mmc_data *data = mrq->data;
 
 	if (!(data->host_cookie & MSDC_PREPARE_FLAG)) {
-		bool read = (data->flags & MMC_DATA_READ) != 0;
-
 		data->host_cookie |= MSDC_PREPARE_FLAG;
 		data->sg_count = dma_map_sg(host->dev, data->sg, data->sg_len,
-					   read ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+					    mmc_get_dma_dir(data));
 	}
 }
 
@@ -478,10 +488,8 @@ static void msdc_unprepare_data(struct msdc_host *host, struct mmc_request *mrq)
 		return;
 
 	if (data->host_cookie & MSDC_PREPARE_FLAG) {
-		bool read = (data->flags & MMC_DATA_READ) != 0;
-
 		dma_unmap_sg(host->dev, data->sg, data->sg_len,
-			     read ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+			     mmc_get_dma_dir(data));
 		data->host_cookie &= ~MSDC_PREPARE_FLAG;
 	}
 }
@@ -580,7 +588,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz)
 		}
 	}
 	sdr_set_field(host->base + MSDC_CFG, MSDC_CFG_CKMOD | MSDC_CFG_CKDIV,
-			(mode << 8) | (div % 0xff));
+		      (mode << 8) | div);
 	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN);
 	while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB))
 		cpu_relax();
@@ -601,8 +609,14 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz)
 	} else {
 		writel(host->saved_tune_para.iocon, host->base + MSDC_IOCON);
 		writel(host->saved_tune_para.pad_tune, host->base + MSDC_PAD_TUNE);
+		writel(host->saved_tune_para.pad_cmd_tune,
+		       host->base + PAD_CMD_TUNE);
 	}
 
+	if (timing == MMC_TIMING_MMC_HS400)
+		sdr_set_field(host->base + PAD_CMD_TUNE,
+			      MSDC_PAD_TUNE_CMDRRDLY,
+			      host->hs400_cmd_int_delay);
 	dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->sclk, timing);
 }
 
@@ -1303,7 +1317,7 @@ static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u32 delay)
 			len_final = len;
 		}
 		start += len ? len : 1;
-		if (len >= 8 && start_final < 4)
+		if (len >= 12 && start_final < 4)
 			break;
 	}
 
@@ -1326,36 +1340,67 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 	struct msdc_host *host = mmc_priv(mmc);
 	u32 rise_delay = 0, fall_delay = 0;
 	struct msdc_delay_phase final_rise_delay, final_fall_delay = { 0,};
+	struct msdc_delay_phase internal_delay_phase;
 	u8 final_delay, final_maxlen;
+	u32 internal_delay = 0;
 	int cmd_err;
-	int i;
+	int i, j;
+
+	if (mmc->ios.timing == MMC_TIMING_MMC_HS200 ||
+	    mmc->ios.timing == MMC_TIMING_UHS_SDR104)
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_CMDRRDLY,
+			      host->hs200_cmd_int_delay);
 
 	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
 		sdr_set_field(host->base + MSDC_PAD_TUNE,
 			      MSDC_PAD_TUNE_CMDRDLY, i);
-		mmc_send_tuning(mmc, opcode, &cmd_err);
-		if (!cmd_err)
-			rise_delay |= (1 << i);
+		/*
+		 * Using the same parameters, it may sometimes pass the test,
+		 * but sometimes it may fail. To make sure the parameters are
+		 * more stable, we test each set of parameters 3 times.
+		 */
+		for (j = 0; j < 3; j++) {
+			mmc_send_tuning(mmc, opcode, &cmd_err);
+			if (!cmd_err) {
+				rise_delay |= (1 << i);
+			} else {
+				rise_delay &= ~(1 << i);
+				break;
+			}
+		}
 	}
 	final_rise_delay = get_best_delay(host, rise_delay);
 	/* if rising edge has enough margin, then do not scan falling edge */
-	if (final_rise_delay.maxlen >= 10 ||
-	    (final_rise_delay.start == 0 && final_rise_delay.maxlen >= 4))
+	if (final_rise_delay.maxlen >= 12 && final_rise_delay.start < 4)
 		goto skip_fall;
 
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 	for (i = 0; i < PAD_DELAY_MAX; i++) {
 		sdr_set_field(host->base + MSDC_PAD_TUNE,
 			      MSDC_PAD_TUNE_CMDRDLY, i);
-		mmc_send_tuning(mmc, opcode, &cmd_err);
-		if (!cmd_err)
-			fall_delay |= (1 << i);
+		/*
+		 * Using the same parameters, it may sometimes pass the test,
+		 * but sometimes it may fail. To make sure the parameters are
+		 * more stable, we test each set of parameters 3 times.
+		 */
+		for (j = 0; j < 3; j++) {
+			mmc_send_tuning(mmc, opcode, &cmd_err);
+			if (!cmd_err) {
+				fall_delay |= (1 << i);
+			} else {
+				fall_delay &= ~(1 << i);
+				break;
+			}
+		}
 	}
 	final_fall_delay = get_best_delay(host, fall_delay);
 
 skip_fall:
 	final_maxlen = max(final_rise_delay.maxlen, final_fall_delay.maxlen);
+	if (final_fall_delay.maxlen >= 12 && final_fall_delay.start < 4)
+		final_maxlen = final_fall_delay.maxlen;
 	if (final_maxlen == final_rise_delay.maxlen) {
 		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 		sdr_set_field(host->base + MSDC_PAD_TUNE, MSDC_PAD_TUNE_CMDRDLY,
@@ -1367,7 +1412,71 @@ skip_fall:
 			      final_fall_delay.final_phase);
 		final_delay = final_fall_delay.final_phase;
 	}
+	if (host->hs200_cmd_int_delay)
+		goto skip_internal;
+
+	for (i = 0; i < PAD_DELAY_MAX; i++) {
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_CMDRRDLY, i);
+		mmc_send_tuning(mmc, opcode, &cmd_err);
+		if (!cmd_err)
+			internal_delay |= (1 << i);
+	}
+	dev_dbg(host->dev, "Final internal delay: 0x%x\n", internal_delay);
+	internal_delay_phase = get_best_delay(host, internal_delay);
+	sdr_set_field(host->base + MSDC_PAD_TUNE, MSDC_PAD_TUNE_CMDRRDLY,
+		      internal_delay_phase.final_phase);
+skip_internal:
+	dev_dbg(host->dev, "Final cmd pad delay: %x\n", final_delay);
+	return final_delay == 0xff ? -EIO : 0;
+}
+
+static int hs400_tune_response(struct mmc_host *mmc, u32 opcode)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	u32 cmd_delay = 0;
+	struct msdc_delay_phase final_cmd_delay = { 0,};
+	u8 final_delay;
+	int cmd_err;
+	int i, j;
+
+	/* select EMMC50 PAD CMD tune */
+	sdr_set_bits(host->base + PAD_CMD_TUNE, BIT(0));
+
+	if (mmc->ios.timing == MMC_TIMING_MMC_HS200 ||
+	    mmc->ios.timing == MMC_TIMING_UHS_SDR104)
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_CMDRRDLY,
+			      host->hs200_cmd_int_delay);
+
+	if (host->hs400_cmd_resp_sel_rising)
+		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
+	else
+		sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
+	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+		sdr_set_field(host->base + PAD_CMD_TUNE,
+			      PAD_CMD_TUNE_RX_DLY3, i);
+		/*
+		 * Using the same parameters, it may sometimes pass the test,
+		 * but sometimes it may fail. To make sure the parameters are
+		 * more stable, we test each set of parameters 3 times.
+		 */
+		for (j = 0; j < 3; j++) {
+			mmc_send_tuning(mmc, opcode, &cmd_err);
+			if (!cmd_err) {
+				cmd_delay |= (1 << i);
+			} else {
+				cmd_delay &= ~(1 << i);
+				break;
+			}
+		}
+	}
+	final_cmd_delay = get_best_delay(host, cmd_delay);
+	sdr_set_field(host->base + PAD_CMD_TUNE, PAD_CMD_TUNE_RX_DLY3,
+		      final_cmd_delay.final_phase);
+	final_delay = final_cmd_delay.final_phase;
 
+	dev_dbg(host->dev, "Final cmd pad delay: %x\n", final_delay);
 	return final_delay == 0xff ? -EIO : 0;
 }
 
@@ -1390,7 +1499,7 @@ static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 	}
 	final_rise_delay = get_best_delay(host, rise_delay);
 	/* if rising edge has enough margin, then do not scan falling edge */
-	if (final_rise_delay.maxlen >= 10 ||
+	if (final_rise_delay.maxlen >= 12 ||
 	    (final_rise_delay.start == 0 && final_rise_delay.maxlen >= 4))
 		goto skip_fall;
 
@@ -1423,6 +1532,7 @@ skip_fall:
 		final_delay = final_fall_delay.final_phase;
 	}
 
+	dev_dbg(host->dev, "Final data pad delay: %x\n", final_delay);
 	return final_delay == 0xff ? -EIO : 0;
 }
 
@@ -1431,7 +1541,10 @@ static int msdc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	struct msdc_host *host = mmc_priv(mmc);
 	int ret;
 
-	ret = msdc_tune_response(mmc, opcode);
+	if (host->hs400_mode)
+		ret = hs400_tune_response(mmc, opcode);
+	else
+		ret = msdc_tune_response(mmc, opcode);
 	if (ret == -EIO) {
 		dev_err(host->dev, "Tune response fail!\n");
 		return ret;
@@ -1444,6 +1557,7 @@ static int msdc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 	host->saved_tune_para.iocon = readl(host->base + MSDC_IOCON);
 	host->saved_tune_para.pad_tune = readl(host->base + MSDC_PAD_TUNE);
+	host->saved_tune_para.pad_cmd_tune = readl(host->base + PAD_CMD_TUNE);
 	return ret;
 }
 
@@ -1478,6 +1592,25 @@ static struct mmc_host_ops mt_msdc_ops = {
 	.hw_reset = msdc_hw_reset,
 };
 
+static void msdc_of_property_parse(struct platform_device *pdev,
+				   struct msdc_host *host)
+{
+	of_property_read_u32(pdev->dev.of_node, "hs400-ds-delay",
+			     &host->hs400_ds_delay);
+
+	of_property_read_u32(pdev->dev.of_node, "mediatek,hs200-cmd-int-delay",
+			     &host->hs200_cmd_int_delay);
+
+	of_property_read_u32(pdev->dev.of_node, "mediatek,hs400-cmd-int-delay",
+			     &host->hs400_cmd_int_delay);
+
+	if (of_property_read_bool(pdev->dev.of_node,
+				  "mediatek,hs400-cmd-resp-sel-rising"))
+		host->hs400_cmd_resp_sel_rising = true;
+	else
+		host->hs400_cmd_resp_sel_rising = false;
+}
+
 static int msdc_drv_probe(struct platform_device *pdev)
 {
 	struct mmc_host *mmc;
@@ -1549,17 +1682,14 @@ static int msdc_drv_probe(struct platform_device *pdev)
 		goto host_free;
 	}
 
-	if (!of_property_read_u32(pdev->dev.of_node, "hs400-ds-delay",
-				  &host->hs400_ds_delay))
-		dev_dbg(&pdev->dev, "hs400-ds-delay: %x\n",
-			host->hs400_ds_delay);
+	msdc_of_property_parse(pdev, host);
 
 	host->dev = &pdev->dev;
 	host->mmc = mmc;
 	host->src_clk_freq = clk_get_rate(host->src_clk);
 	/* Set host parameters to mmc */
 	mmc->ops = &mt_msdc_ops;
-	mmc->f_min = host->src_clk_freq / (4 * 255);
+	mmc->f_min = DIV_ROUND_UP(host->src_clk_freq, 4 * 255);
 
 	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
 	/* MMC core transfer sizes tunable parameters */
@@ -1664,6 +1794,7 @@ static void msdc_save_reg(struct msdc_host *host)
 	host->save_para.patch_bit0 = readl(host->base + MSDC_PATCH_BIT);
 	host->save_para.patch_bit1 = readl(host->base + MSDC_PATCH_BIT1);
 	host->save_para.pad_ds_tune = readl(host->base + PAD_DS_TUNE);
+	host->save_para.pad_cmd_tune = readl(host->base + PAD_CMD_TUNE);
 	host->save_para.emmc50_cfg0 = readl(host->base + EMMC50_CFG0);
 }
 
@@ -1676,6 +1807,7 @@ static void msdc_restore_reg(struct msdc_host *host)
 	writel(host->save_para.patch_bit0, host->base + MSDC_PATCH_BIT);
 	writel(host->save_para.patch_bit1, host->base + MSDC_PATCH_BIT1);
 	writel(host->save_para.pad_ds_tune, host->base + PAD_DS_TUNE);
+	writel(host->save_para.pad_cmd_tune, host->base + PAD_CMD_TUNE);
 	writel(host->save_para.emmc50_cfg0, host->base + EMMC50_CFG0);
 }
 
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index 42296e55b9de..58d74b8d6c79 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -125,10 +125,10 @@ static int mvsd_setup_data(struct mvsd_host *host, struct mmc_data *data)
 		return 1;
 	} else {
 		dma_addr_t phys_addr;
-		int dma_dir = (data->flags & MMC_DATA_READ) ?
-			DMA_FROM_DEVICE : DMA_TO_DEVICE;
-		host->sg_frags = dma_map_sg(mmc_dev(host->mmc), data->sg,
-					    data->sg_len, dma_dir);
+
+		host->sg_frags = dma_map_sg(mmc_dev(host->mmc),
+					    data->sg, data->sg_len,
+					    mmc_get_dma_dir(data));
 		phys_addr = sg_dma_address(data->sg);
 		mvsd_write(MVSD_SYS_ADDR_LOW, (u32)phys_addr & 0xffff);
 		mvsd_write(MVSD_SYS_ADDR_HI,  (u32)phys_addr >> 16);
@@ -294,8 +294,7 @@ static u32 mvsd_finish_data(struct mvsd_host *host, struct mmc_data *data,
 		host->pio_size = 0;
 	} else {
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_frags,
-			     (data->flags & MMC_DATA_READ) ?
-				DMA_FROM_DEVICE : DMA_TO_DEVICE);
+			     mmc_get_dma_dir(data));
 	}
 
 	if (err_status & MVSD_ERR_DATA_TIMEOUT)
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index a58bd653ed8b..8c39dccacf39 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -935,15 +935,6 @@ omap_hsmmc_start_command(struct omap_hsmmc_host *host, struct mmc_command *cmd,
 	OMAP_HSMMC_WRITE(host->base, CMD, cmdreg);
 }
 
-static int
-omap_hsmmc_get_dma_dir(struct omap_hsmmc_host *host, struct mmc_data *data)
-{
-	if (data->flags & MMC_DATA_WRITE)
-		return DMA_TO_DEVICE;
-	else
-		return DMA_FROM_DEVICE;
-}
-
 static struct dma_chan *omap_hsmmc_get_dma_chan(struct omap_hsmmc_host *host,
 	struct mmc_data *data)
 {
@@ -1055,7 +1046,7 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno)
 		dmaengine_terminate_all(chan);
 		dma_unmap_sg(chan->device->dev,
 			host->data->sg, host->data->sg_len,
-			omap_hsmmc_get_dma_dir(host, host->data));
+			mmc_get_dma_dir(host->data));
 
 		host->data->host_cookie = 0;
 	}
@@ -1350,7 +1341,7 @@ static void omap_hsmmc_dma_callback(void *param)
 	if (!data->host_cookie)
 		dma_unmap_sg(chan->device->dev,
 			     data->sg, data->sg_len,
-			     omap_hsmmc_get_dma_dir(host, data));
+			     mmc_get_dma_dir(data));
 
 	req_in_progress = host->req_in_progress;
 	host->dma_ch = -1;
@@ -1383,7 +1374,7 @@ static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 	/* Check if next job is already prepared */
 	if (next || data->host_cookie != host->next_data.cookie) {
 		dma_len = dma_map_sg(chan->device->dev, data->sg, data->sg_len,
-				     omap_hsmmc_get_dma_dir(host, data));
+				     mmc_get_dma_dir(data));
 
 	} else {
 		dma_len = host->next_data.dma_len;
@@ -1569,7 +1560,7 @@ static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
 		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, data);
 
 		dma_unmap_sg(c->device->dev, data->sg, data->sg_len,
-			     omap_hsmmc_get_dma_dir(host, data));
+			     mmc_get_dma_dir(data));
 		data->host_cookie = 0;
 	}
 }
@@ -1770,8 +1761,8 @@ static int omap_hsmmc_configure_wake_irq(struct omap_hsmmc_host *host)
 	 */
 	if (host->pdata->controller_flags & OMAP_HSMMC_SWAKEUP_MISSING) {
 		struct pinctrl *p = devm_pinctrl_get(host->dev);
-		if (!p) {
-			ret = -ENODEV;
+		if (IS_ERR(p)) {
+			ret = PTR_ERR(p);
 			goto err_free_irq;
 		}
 		if (IS_ERR(pinctrl_lookup_state(p, PINCTRL_STATE_DEFAULT))) {
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 7a173f8c455b..8896bf533dc7 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -24,6 +24,10 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/mmc/slot-gpio.h>
 
 #include <plat/gpio-cfg.h>
 #include <mach/dma.h>
@@ -807,21 +811,6 @@ irq_out:
 
 }
 
-/*
- * ISR for the CardDetect Pin
-*/
-
-static irqreturn_t s3cmci_irq_cd(int irq, void *dev_id)
-{
-	struct s3cmci_host *host = (struct s3cmci_host *)dev_id;
-
-	dbg(host, dbg_irq, "card detect\n");
-
-	mmc_detect_change(host->mmc, msecs_to_jiffies(500));
-
-	return IRQ_HANDLED;
-}
-
 static void s3cmci_dma_done_callback(void *arg)
 {
 	struct s3cmci_host *host = arg;
@@ -1104,7 +1093,7 @@ static int s3cmci_prepare_dma(struct s3cmci_host *host, struct mmc_data *data)
 		conf.direction = DMA_MEM_TO_DEV;
 
 	dma_map_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-			     rw ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		   mmc_get_dma_dir(data));
 
 	dmaengine_slave_config(host->dma, &conf);
 	desc = dmaengine_prep_slave_sg(host->dma, data->sg, data->sg_len,
@@ -1121,7 +1110,7 @@ static int s3cmci_prepare_dma(struct s3cmci_host *host, struct mmc_data *data)
 
 unmap_exit:
 	dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-			     rw ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		     mmc_get_dma_dir(data));
 	return -ENOMEM;
 }
 
@@ -1177,19 +1166,6 @@ static void s3cmci_send_request(struct mmc_host *mmc)
 	s3cmci_enable_irq(host, true);
 }
 
-static int s3cmci_card_present(struct mmc_host *mmc)
-{
-	struct s3cmci_host *host = mmc_priv(mmc);
-	struct s3c24xx_mci_pdata *pdata = host->pdata;
-	int ret;
-
-	if (pdata->no_detect)
-		return -ENOSYS;
-
-	ret = gpio_get_value(pdata->gpio_detect) ? 0 : 1;
-	return ret ^ pdata->detect_invert;
-}
-
 static void s3cmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct s3cmci_host *host = mmc_priv(mmc);
@@ -1198,7 +1174,7 @@ static void s3cmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	host->cmd_is_stop = 0;
 	host->mrq = mrq;
 
-	if (s3cmci_card_present(mmc) == 0) {
+	if (mmc_gpio_get_cd(mmc) == 0) {
 		dbg(host, dbg_err, "%s: no medium present\n", __func__);
 		host->mrq->cmd->error = -ENOMEDIUM;
 		mmc_request_done(mmc, mrq);
@@ -1242,8 +1218,9 @@ static void s3cmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	case MMC_POWER_ON:
 	case MMC_POWER_UP:
 		/* Configure GPE5...GPE10 pins in SD mode */
-		s3c_gpio_cfgall_range(S3C2410_GPE(5), 6, S3C_GPIO_SFN(2),
-				      S3C_GPIO_PULL_NONE);
+		if (!host->pdev->dev.of_node)
+			s3c_gpio_cfgall_range(S3C2410_GPE(5), 6, S3C_GPIO_SFN(2),
+					      S3C_GPIO_PULL_NONE);
 
 		if (host->pdata->set_power)
 			host->pdata->set_power(ios->power_mode, ios->vdd);
@@ -1255,7 +1232,8 @@ static void s3cmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	case MMC_POWER_OFF:
 	default:
-		gpio_direction_output(S3C2410_GPE(5), 0);
+		if (!host->pdev->dev.of_node)
+			gpio_direction_output(S3C2410_GPE(5), 0);
 
 		if (host->is2440)
 			mci_con |= S3C2440_SDICON_SDRESET;
@@ -1295,21 +1273,6 @@ static void s3cmci_reset(struct s3cmci_host *host)
 	writel(con, host->base + S3C2410_SDICON);
 }
 
-static int s3cmci_get_ro(struct mmc_host *mmc)
-{
-	struct s3cmci_host *host = mmc_priv(mmc);
-	struct s3c24xx_mci_pdata *pdata = host->pdata;
-	int ret;
-
-	if (pdata->no_wprotect)
-		return 0;
-
-	ret = gpio_get_value(pdata->gpio_wprotect) ? 1 : 0;
-	ret ^= pdata->wprotect_invert;
-
-	return ret;
-}
-
 static void s3cmci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 {
 	struct s3cmci_host *host = mmc_priv(mmc);
@@ -1353,8 +1316,8 @@ static void s3cmci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 static struct mmc_host_ops s3cmci_ops = {
 	.request	= s3cmci_request,
 	.set_ios	= s3cmci_set_ios,
-	.get_ro		= s3cmci_get_ro,
-	.get_cd		= s3cmci_card_present,
+	.get_ro		= mmc_gpio_get_ro,
+	.get_cd		= mmc_gpio_get_cd,
 	.enable_sdio_irq = s3cmci_enable_sdio_irq,
 };
 
@@ -1545,21 +1508,14 @@ static inline void s3cmci_debugfs_remove(struct s3cmci_host *host) { }
 
 #endif /* CONFIG_DEBUG_FS */
 
-static int s3cmci_probe(struct platform_device *pdev)
+static int s3cmci_probe_pdata(struct s3cmci_host *host)
 {
-	struct s3cmci_host *host;
-	struct mmc_host	*mmc;
-	int ret;
-	int is2440;
-	int i;
+	struct platform_device *pdev = host->pdev;
+	struct mmc_host *mmc = host->mmc;
+	struct s3c24xx_mci_pdata *pdata;
+	int i, ret;
 
-	is2440 = platform_get_device_id(pdev)->driver_data;
-
-	mmc = mmc_alloc_host(sizeof(struct s3cmci_host), &pdev->dev);
-	if (!mmc) {
-		ret = -ENOMEM;
-		goto probe_out;
-	}
+	host->is2440 = platform_get_device_id(pdev)->driver_data;
 
 	for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++) {
 		ret = gpio_request(i, dev_name(&pdev->dev));
@@ -1569,25 +1525,101 @@ static int s3cmci_probe(struct platform_device *pdev)
 			for (i--; i >= S3C2410_GPE(5); i--)
 				gpio_free(i);
 
-			goto probe_free_host;
+			return ret;
+		}
+	}
+
+	if (!pdev->dev.platform_data)
+		pdev->dev.platform_data = &s3cmci_def_pdata;
+
+	pdata = pdev->dev.platform_data;
+
+	if (pdata->no_wprotect)
+		mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
+
+	if (pdata->no_detect)
+		mmc->caps |= MMC_CAP_NEEDS_POLL;
+
+	if (pdata->wprotect_invert)
+		mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+
+	if (pdata->detect_invert)
+		 mmc->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH;
+
+	if (gpio_is_valid(pdata->gpio_detect)) {
+		ret = mmc_gpio_request_cd(mmc, pdata->gpio_detect, 0);
+		if (ret) {
+			dev_err(&pdev->dev, "error requesting GPIO for CD %d\n",
+				ret);
+			return ret;
 		}
 	}
 
+	if (gpio_is_valid(pdata->gpio_wprotect)) {
+		ret = mmc_gpio_request_ro(mmc, pdata->gpio_wprotect);
+		if (ret) {
+			dev_err(&pdev->dev, "error requesting GPIO for WP %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int s3cmci_probe_dt(struct s3cmci_host *host)
+{
+	struct platform_device *pdev = host->pdev;
+	struct s3c24xx_mci_pdata *pdata;
+	struct mmc_host *mmc = host->mmc;
+	int ret;
+
+	host->is2440 = (int) of_device_get_match_data(&pdev->dev);
+
+	ret = mmc_of_parse(mmc);
+	if (ret)
+		return ret;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	pdev->dev.platform_data = pdata;
+
+	return 0;
+}
+
+static int s3cmci_probe(struct platform_device *pdev)
+{
+	struct s3cmci_host *host;
+	struct mmc_host	*mmc;
+	int ret;
+	int i;
+
+	mmc = mmc_alloc_host(sizeof(struct s3cmci_host), &pdev->dev);
+	if (!mmc) {
+		ret = -ENOMEM;
+		goto probe_out;
+	}
+
 	host = mmc_priv(mmc);
 	host->mmc 	= mmc;
 	host->pdev	= pdev;
-	host->is2440	= is2440;
+
+	if (pdev->dev.of_node)
+		ret = s3cmci_probe_dt(host);
+	else
+		ret = s3cmci_probe_pdata(host);
+
+	if (ret)
+		goto probe_free_host;
 
 	host->pdata = pdev->dev.platform_data;
-	if (!host->pdata) {
-		pdev->dev.platform_data = &s3cmci_def_pdata;
-		host->pdata = &s3cmci_def_pdata;
-	}
 
 	spin_lock_init(&host->complete_lock);
 	tasklet_init(&host->pio_tasklet, pio_tasklet, (unsigned long) host);
 
-	if (is2440) {
+	if (host->is2440) {
 		host->sdiimsk	= S3C2440_SDIIMSK;
 		host->sdidata	= S3C2440_SDIDATA;
 		host->clk_div	= 1;
@@ -1645,43 +1677,6 @@ static int s3cmci_probe(struct platform_device *pdev)
 	disable_irq(host->irq);
 	host->irq_state = false;
 
-	if (!host->pdata->no_detect) {
-		ret = gpio_request(host->pdata->gpio_detect, "s3cmci detect");
-		if (ret) {
-			dev_err(&pdev->dev, "failed to get detect gpio\n");
-			goto probe_free_irq;
-		}
-
-		host->irq_cd = gpio_to_irq(host->pdata->gpio_detect);
-
-		if (host->irq_cd >= 0) {
-			if (request_irq(host->irq_cd, s3cmci_irq_cd,
-					IRQF_TRIGGER_RISING |
-					IRQF_TRIGGER_FALLING,
-					DRIVER_NAME, host)) {
-				dev_err(&pdev->dev,
-					"can't get card detect irq.\n");
-				ret = -ENOENT;
-				goto probe_free_gpio_cd;
-			}
-		} else {
-			dev_warn(&pdev->dev,
-				 "host detect has no irq available\n");
-			gpio_direction_input(host->pdata->gpio_detect);
-		}
-	} else
-		host->irq_cd = -1;
-
-	if (!host->pdata->no_wprotect) {
-		ret = gpio_request(host->pdata->gpio_wprotect, "s3cmci wp");
-		if (ret) {
-			dev_err(&pdev->dev, "failed to get writeprotect\n");
-			goto probe_free_irq_cd;
-		}
-
-		gpio_direction_input(host->pdata->gpio_wprotect);
-	}
-
 	/* Depending on the dma state, get a DMA channel to use. */
 
 	if (s3cmci_host_usedma(host)) {
@@ -1689,7 +1684,7 @@ static int s3cmci_probe(struct platform_device *pdev)
 		ret = PTR_ERR_OR_ZERO(host->dma);
 		if (ret) {
 			dev_err(&pdev->dev, "cannot get DMA channel.\n");
-			goto probe_free_gpio_wp;
+			goto probe_free_irq;
 		}
 	}
 
@@ -1768,18 +1763,6 @@ static int s3cmci_probe(struct platform_device *pdev)
 	if (s3cmci_host_usedma(host))
 		dma_release_channel(host->dma);
 
- probe_free_gpio_wp:
-	if (!host->pdata->no_wprotect)
-		gpio_free(host->pdata->gpio_wprotect);
-
- probe_free_gpio_cd:
-	if (!host->pdata->no_detect)
-		gpio_free(host->pdata->gpio_detect);
-
- probe_free_irq_cd:
-	if (host->irq_cd >= 0)
-		free_irq(host->irq_cd, host);
-
  probe_free_irq:
 	free_irq(host->irq, host);
 
@@ -1790,8 +1773,9 @@ static int s3cmci_probe(struct platform_device *pdev)
 	release_mem_region(host->mem->start, resource_size(host->mem));
 
  probe_free_gpio:
-	for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++)
-		gpio_free(i);
+	if (!pdev->dev.of_node)
+		for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++)
+			gpio_free(i);
 
  probe_free_host:
 	mmc_free_host(mmc);
@@ -1818,7 +1802,6 @@ static int s3cmci_remove(struct platform_device *pdev)
 {
 	struct mmc_host		*mmc  = platform_get_drvdata(pdev);
 	struct s3cmci_host	*host = mmc_priv(mmc);
-	struct s3c24xx_mci_pdata *pd = host->pdata;
 	int i;
 
 	s3cmci_shutdown(pdev);
@@ -1832,15 +1815,9 @@ static int s3cmci_remove(struct platform_device *pdev)
 
 	free_irq(host->irq, host);
 
-	if (!pd->no_wprotect)
-		gpio_free(pd->gpio_wprotect);
-
-	if (!pd->no_detect)
-		gpio_free(pd->gpio_detect);
-
-	for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++)
-		gpio_free(i);
-
+	if (!pdev->dev.of_node)
+		for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++)
+			gpio_free(i);
 
 	iounmap(host->base);
 	release_mem_region(host->mem->start, resource_size(host->mem));
@@ -1849,6 +1826,23 @@ static int s3cmci_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id s3cmci_dt_match[] = {
+	{
+		.compatible = "samsung,s3c2410-sdi",
+		.data = (void *)0,
+	},
+	{
+		.compatible = "samsung,s3c2412-sdi",
+		.data = (void *)1,
+	},
+	{
+		.compatible = "samsung,s3c2440-sdi",
+		.data = (void *)1,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, s3cmci_dt_match);
+
 static const struct platform_device_id s3cmci_driver_ids[] = {
 	{
 		.name	= "s3c2410-sdi",
@@ -1868,6 +1862,7 @@ MODULE_DEVICE_TABLE(platform, s3cmci_driver_ids);
 static struct platform_driver s3cmci_driver = {
 	.driver	= {
 		.name	= "s3c-sdi",
+		.of_match_table = s3cmci_dt_match,
 	},
 	.id_table	= s3cmci_driver_ids,
 	.probe		= s3cmci_probe,
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 9dcb7048e3b1..c6a9a1bfaa22 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -263,10 +263,8 @@ static int sdhci_acpi_sd_probe_slot(struct platform_device *pdev,
 
 	/* Platform specific code during sd probe slot goes here */
 
-	if (hid && !strcmp(hid, "80865ACA")) {
+	if (hid && !strcmp(hid, "80865ACA"))
 		host->mmc_host_ops.get_cd = bxt_get_cd;
-		host->mmc->caps |= MMC_CAP_AGGRESSIVE_PM;
-	}
 
 	return 0;
 }
@@ -302,7 +300,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sd = {
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2 = SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON |
 		   SDHCI_QUIRK2_STOP_WITH_TC,
-	.caps    = MMC_CAP_WAIT_WHILE_BUSY,
+	.caps    = MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_AGGRESSIVE_PM,
 	.probe_slot	= sdhci_acpi_sd_probe_slot,
 };
 
@@ -524,8 +522,12 @@ static int sdhci_acpi_remove(struct platform_device *pdev)
 static int sdhci_acpi_suspend(struct device *dev)
 {
 	struct sdhci_acpi_host *c = dev_get_drvdata(dev);
+	struct sdhci_host *host = c->host;
+
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
 
-	return sdhci_suspend_host(c->host);
+	return sdhci_suspend_host(host);
 }
 
 static int sdhci_acpi_resume(struct device *dev)
@@ -544,8 +546,12 @@ static int sdhci_acpi_resume(struct device *dev)
 static int sdhci_acpi_runtime_suspend(struct device *dev)
 {
 	struct sdhci_acpi_host *c = dev_get_drvdata(dev);
+	struct sdhci_host *host = c->host;
+
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
 
-	return sdhci_runtime_suspend_host(c->host);
+	return sdhci_runtime_suspend_host(host);
 }
 
 static int sdhci_acpi_runtime_resume(struct device *dev)
diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index 159f6f64c68e..242c5dc7a81e 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -29,6 +29,9 @@ static int sdhci_brcmstb_suspend(struct device *dev)
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	int res;
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	res = sdhci_suspend_host(host);
 	if (res)
 		return res;
diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c
index 316cfec3f005..19d5698244b5 100644
--- a/drivers/mmc/host/sdhci-cadence.c
+++ b/drivers/mmc/host/sdhci-cadence.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
+#include <linux/of.h>
 
 #include "sdhci-pltfm.h"
 
@@ -40,6 +41,7 @@
 #define   SDHCI_CDNS_HRS06_MODE_MMC_DDR		0x3
 #define   SDHCI_CDNS_HRS06_MODE_MMC_HS200	0x4
 #define   SDHCI_CDNS_HRS06_MODE_MMC_HS400	0x5
+#define   SDHCI_CDNS_HRS06_MODE_MMC_HS400ES	0x6
 
 /* SRS - Slot Register Set (SDHCI-compatible) */
 #define SDHCI_CDNS_SRS_BASE		0x200
@@ -54,6 +56,9 @@
 #define SDHCI_CDNS_PHY_DLY_EMMC_LEGACY	0x06
 #define SDHCI_CDNS_PHY_DLY_EMMC_SDR	0x07
 #define SDHCI_CDNS_PHY_DLY_EMMC_DDR	0x08
+#define SDHCI_CDNS_PHY_DLY_SDCLK	0x0b
+#define SDHCI_CDNS_PHY_DLY_HSMMC	0x0c
+#define SDHCI_CDNS_PHY_DLY_STROBE	0x0d
 
 /*
  * The tuned val register is 6 bit-wide, but not the whole of the range is
@@ -64,13 +69,34 @@
 
 struct sdhci_cdns_priv {
 	void __iomem *hrs_addr;
+	bool enhanced_strobe;
 };
 
-static void sdhci_cdns_write_phy_reg(struct sdhci_cdns_priv *priv,
-				     u8 addr, u8 data)
+struct sdhci_cdns_phy_cfg {
+	const char *property;
+	u8 addr;
+};
+
+static const struct sdhci_cdns_phy_cfg sdhci_cdns_phy_cfgs[] = {
+	{ "cdns,phy-input-delay-sd-highspeed", SDHCI_CDNS_PHY_DLY_SD_HS, },
+	{ "cdns,phy-input-delay-legacy", SDHCI_CDNS_PHY_DLY_SD_DEFAULT, },
+	{ "cdns,phy-input-delay-sd-uhs-sdr12", SDHCI_CDNS_PHY_DLY_UHS_SDR12, },
+	{ "cdns,phy-input-delay-sd-uhs-sdr25", SDHCI_CDNS_PHY_DLY_UHS_SDR25, },
+	{ "cdns,phy-input-delay-sd-uhs-sdr50", SDHCI_CDNS_PHY_DLY_UHS_SDR50, },
+	{ "cdns,phy-input-delay-sd-uhs-ddr50", SDHCI_CDNS_PHY_DLY_UHS_DDR50, },
+	{ "cdns,phy-input-delay-mmc-highspeed", SDHCI_CDNS_PHY_DLY_EMMC_SDR, },
+	{ "cdns,phy-input-delay-mmc-ddr", SDHCI_CDNS_PHY_DLY_EMMC_DDR, },
+	{ "cdns,phy-dll-delay-sdclk", SDHCI_CDNS_PHY_DLY_SDCLK, },
+	{ "cdns,phy-dll-delay-sdclk-hsmmc", SDHCI_CDNS_PHY_DLY_HSMMC, },
+	{ "cdns,phy-dll-delay-strobe", SDHCI_CDNS_PHY_DLY_STROBE, },
+};
+
+static int sdhci_cdns_write_phy_reg(struct sdhci_cdns_priv *priv,
+				    u8 addr, u8 data)
 {
 	void __iomem *reg = priv->hrs_addr + SDHCI_CDNS_HRS04;
 	u32 tmp;
+	int ret;
 
 	tmp = (data << SDHCI_CDNS_HRS04_WDATA_SHIFT) |
 	      (addr << SDHCI_CDNS_HRS04_ADDR_SHIFT);
@@ -79,17 +105,36 @@ static void sdhci_cdns_write_phy_reg(struct sdhci_cdns_priv *priv,
 	tmp |= SDHCI_CDNS_HRS04_WR;
 	writel(tmp, reg);
 
+	ret = readl_poll_timeout(reg, tmp, tmp & SDHCI_CDNS_HRS04_ACK, 0, 10);
+	if (ret)
+		return ret;
+
 	tmp &= ~SDHCI_CDNS_HRS04_WR;
 	writel(tmp, reg);
+
+	return 0;
 }
 
-static void sdhci_cdns_phy_init(struct sdhci_cdns_priv *priv)
+static int sdhci_cdns_phy_init(struct device_node *np,
+			       struct sdhci_cdns_priv *priv)
 {
-	sdhci_cdns_write_phy_reg(priv, SDHCI_CDNS_PHY_DLY_SD_HS, 4);
-	sdhci_cdns_write_phy_reg(priv, SDHCI_CDNS_PHY_DLY_SD_DEFAULT, 4);
-	sdhci_cdns_write_phy_reg(priv, SDHCI_CDNS_PHY_DLY_EMMC_LEGACY, 9);
-	sdhci_cdns_write_phy_reg(priv, SDHCI_CDNS_PHY_DLY_EMMC_SDR, 2);
-	sdhci_cdns_write_phy_reg(priv, SDHCI_CDNS_PHY_DLY_EMMC_DDR, 3);
+	u32 val;
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(sdhci_cdns_phy_cfgs); i++) {
+		ret = of_property_read_u32(np, sdhci_cdns_phy_cfgs[i].property,
+					   &val);
+		if (ret)
+			continue;
+
+		ret = sdhci_cdns_write_phy_reg(priv,
+					       sdhci_cdns_phy_cfgs[i].addr,
+					       val);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static inline void *sdhci_cdns_priv(struct sdhci_host *host)
@@ -103,16 +148,35 @@ static unsigned int sdhci_cdns_get_timeout_clock(struct sdhci_host *host)
 {
 	/*
 	 * Cadence's spec says the Timeout Clock Frequency is the same as the
-	 * Base Clock Frequency.  Divide it by 1000 to return a value in kHz.
+	 * Base Clock Frequency.
 	 */
-	return host->max_clk / 1000;
+	return host->max_clk;
+}
+
+static void sdhci_cdns_set_emmc_mode(struct sdhci_cdns_priv *priv, u32 mode)
+{
+	u32 tmp;
+
+	/* The speed mode for eMMC is selected by HRS06 register */
+	tmp = readl(priv->hrs_addr + SDHCI_CDNS_HRS06);
+	tmp &= ~SDHCI_CDNS_HRS06_MODE_MASK;
+	tmp |= mode;
+	writel(tmp, priv->hrs_addr + SDHCI_CDNS_HRS06);
+}
+
+static u32 sdhci_cdns_get_emmc_mode(struct sdhci_cdns_priv *priv)
+{
+	u32 tmp;
+
+	tmp = readl(priv->hrs_addr + SDHCI_CDNS_HRS06);
+	return tmp & SDHCI_CDNS_HRS06_MODE_MASK;
 }
 
 static void sdhci_cdns_set_uhs_signaling(struct sdhci_host *host,
 					 unsigned int timing)
 {
 	struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host);
-	u32 mode, tmp;
+	u32 mode;
 
 	switch (timing) {
 	case MMC_TIMING_MMC_HS:
@@ -125,18 +189,17 @@ static void sdhci_cdns_set_uhs_signaling(struct sdhci_host *host,
 		mode = SDHCI_CDNS_HRS06_MODE_MMC_HS200;
 		break;
 	case MMC_TIMING_MMC_HS400:
-		mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400;
+		if (priv->enhanced_strobe)
+			mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400ES;
+		else
+			mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400;
 		break;
 	default:
 		mode = SDHCI_CDNS_HRS06_MODE_SD;
 		break;
 	}
 
-	/* The speed mode for eMMC is selected by HRS06 register */
-	tmp = readl(priv->hrs_addr + SDHCI_CDNS_HRS06);
-	tmp &= ~SDHCI_CDNS_HRS06_MODE_MASK;
-	tmp |= mode;
-	writel(tmp, priv->hrs_addr + SDHCI_CDNS_HRS06);
+	sdhci_cdns_set_emmc_mode(priv, mode);
 
 	/* For SD, fall back to the default handler */
 	if (mode == SDHCI_CDNS_HRS06_MODE_SD)
@@ -213,6 +276,26 @@ static int sdhci_cdns_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	return sdhci_cdns_set_tune_val(host, end_of_streak - max_streak / 2);
 }
 
+static void sdhci_cdns_hs400_enhanced_strobe(struct mmc_host *mmc,
+					     struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host);
+	u32 mode;
+
+	priv->enhanced_strobe = ios->enhanced_strobe;
+
+	mode = sdhci_cdns_get_emmc_mode(priv);
+
+	if (mode == SDHCI_CDNS_HRS06_MODE_MMC_HS400 && ios->enhanced_strobe)
+		sdhci_cdns_set_emmc_mode(priv,
+					 SDHCI_CDNS_HRS06_MODE_MMC_HS400ES);
+
+	if (mode == SDHCI_CDNS_HRS06_MODE_MMC_HS400ES && !ios->enhanced_strobe)
+		sdhci_cdns_set_emmc_mode(priv,
+					 SDHCI_CDNS_HRS06_MODE_MMC_HS400);
+}
+
 static int sdhci_cdns_probe(struct platform_device *pdev)
 {
 	struct sdhci_host *host;
@@ -220,8 +303,9 @@ static int sdhci_cdns_probe(struct platform_device *pdev)
 	struct sdhci_cdns_priv *priv;
 	struct clk *clk;
 	int ret;
+	struct device *dev = &pdev->dev;
 
-	clk = devm_clk_get(&pdev->dev, NULL);
+	clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
@@ -240,14 +324,21 @@ static int sdhci_cdns_probe(struct platform_device *pdev)
 
 	priv = sdhci_cdns_priv(host);
 	priv->hrs_addr = host->ioaddr;
+	priv->enhanced_strobe = false;
 	host->ioaddr += SDHCI_CDNS_SRS_BASE;
 	host->mmc_host_ops.execute_tuning = sdhci_cdns_execute_tuning;
+	host->mmc_host_ops.hs400_enhanced_strobe =
+				sdhci_cdns_hs400_enhanced_strobe;
+
+	sdhci_get_of_property(pdev);
 
 	ret = mmc_of_parse(host->mmc);
 	if (ret)
 		goto free;
 
-	sdhci_cdns_phy_init(priv);
+	ret = sdhci_cdns_phy_init(dev->of_node, priv);
+	if (ret)
+		goto free;
 
 	ret = sdhci_add_host(host);
 	if (ret)
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 7123ef96ed18..23d8b8a73ae9 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -830,6 +830,7 @@ static int esdhc_change_pinstate(struct sdhci_host *host,
 
 	switch (uhs) {
 	case MMC_TIMING_UHS_SDR50:
+	case MMC_TIMING_UHS_DDR50:
 		pinctrl = imx_data->pins_100mhz;
 		break;
 	case MMC_TIMING_UHS_SDR104:
@@ -888,6 +889,28 @@ static void esdhc_set_strobe_dll(struct sdhci_host *host)
 	}
 }
 
+static void esdhc_reset_tuning(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
+	u32 ctrl;
+
+	/* Rest the tuning circurt */
+	if (esdhc_is_usdhc(imx_data)) {
+		if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) {
+			ctrl = readl(host->ioaddr + ESDHC_MIX_CTRL);
+			ctrl &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
+			ctrl &= ~ESDHC_MIX_CTRL_FBCLK_SEL;
+			writel(ctrl, host->ioaddr + ESDHC_MIX_CTRL);
+			writel(0, host->ioaddr + ESDHC_TUNE_CTRL_STATUS);
+		} else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
+			ctrl = readl(host->ioaddr + SDHCI_ACMD12_ERR);
+			ctrl &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
+			writel(ctrl, host->ioaddr + SDHCI_ACMD12_ERR);
+		}
+	}
+}
+
 static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 {
 	u32 m;
@@ -931,6 +954,10 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 		host->ops->set_clock(host, host->clock);
 		esdhc_set_strobe_dll(host);
 		break;
+	case MMC_TIMING_LEGACY:
+	default:
+		esdhc_reset_tuning(host);
+		break;
 	}
 
 	esdhc_change_pinstate(host, timing);
@@ -1322,6 +1349,9 @@ static int sdhci_esdhc_suspend(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	return sdhci_suspend_host(host);
 }
 
@@ -1346,6 +1376,9 @@ static int sdhci_esdhc_runtime_suspend(struct device *dev)
 
 	ret = sdhci_runtime_suspend_host(host);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	if (!sdhci_sdio_irq_enabled(host)) {
 		clk_disable_unprepare(imx_data->clk_per);
 		clk_disable_unprepare(imx_data->clk_ipg);
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index ece8b37e51dd..c4bbd7485987 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -37,6 +37,7 @@
 
 /* Protocol Control Register */
 #define ESDHC_PROCTL			0x28
+#define ESDHC_VOLT_SEL			0x00000400
 #define ESDHC_CTRL_4BITBUS		(0x1 << 1)
 #define ESDHC_CTRL_8BITBUS		(0x2 << 1)
 #define ESDHC_CTRL_BUSWIDTH_MASK	(0x3 << 1)
@@ -52,8 +53,14 @@
 #define ESDHC_CLOCK_HCKEN		0x00000002
 #define ESDHC_CLOCK_IPGEN		0x00000001
 
+/* Tuning Block Control Register */
+#define ESDHC_TBCTL			0x120
+#define ESDHC_TB_EN			0x00000004
+
 /* Control Register for DMA transfer */
 #define ESDHC_DMA_SYSCTL		0x40c
+#define ESDHC_PERIPHERAL_CLK_SEL	0x00080000
+#define ESDHC_FLUSH_ASYNC_FIFO		0x00040000
 #define ESDHC_DMA_SNOOP			0x00000040
 
 #endif /* _DRIVERS_MMC_SDHCI_ESDHC_H */
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 10cdc84d5113..9d601dc0d646 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -991,12 +991,8 @@ static void sdhci_msm_set_uhs_signaling(struct sdhci_host *host,
 		mmc_hostname(host->mmc), host->clock, uhs, ctrl_2);
 	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
 
-	spin_unlock_irq(&host->lock);
-
 	if (mmc->ios.timing == MMC_TIMING_MMC_HS400)
 		sdhci_msm_hs400(host, &mmc->ios);
-
-	spin_lock_irq(&host->lock);
 }
 
 static void sdhci_msm_voltage_switch(struct sdhci_host *host)
@@ -1089,13 +1085,9 @@ static void sdhci_msm_set_clock(struct sdhci_host *host, unsigned int clock)
 		goto out;
 	}
 
-	spin_unlock_irq(&host->lock);
-
 	sdhci_msm_hc_select_mode(host);
 
 	msm_set_clock_rate_for_bus_mode(host, clock);
-
-	spin_lock_irq(&host->lock);
 out:
 	__sdhci_msm_set_clock(host, clock);
 }
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 410a55b1c25f..ea6b36c88ae7 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -28,13 +28,9 @@
 #include "sdhci-pltfm.h"
 #include <linux/of.h>
 
-#define SDHCI_ARASAN_CLK_CTRL_OFFSET	0x2c
 #define SDHCI_ARASAN_VENDOR_REGISTER	0x78
 
 #define VENDOR_ENHANCED_STROBE		BIT(0)
-#define CLK_CTRL_TIMEOUT_SHIFT		16
-#define CLK_CTRL_TIMEOUT_MASK		(0xf << CLK_CTRL_TIMEOUT_SHIFT)
-#define CLK_CTRL_TIMEOUT_MIN_EXP	13
 
 #define PHY_CLK_TOO_SLOW_HZ		400000
 
@@ -161,21 +157,6 @@ static int sdhci_arasan_syscon_write(struct sdhci_host *host,
 	return ret;
 }
 
-static unsigned int sdhci_arasan_get_timeout_clock(struct sdhci_host *host)
-{
-	u32 div;
-	unsigned long freq;
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-
-	div = readl(host->ioaddr + SDHCI_ARASAN_CLK_CTRL_OFFSET);
-	div = (div & CLK_CTRL_TIMEOUT_MASK) >> CLK_CTRL_TIMEOUT_SHIFT;
-
-	freq = clk_get_rate(pltfm_host->clk);
-	freq /= 1 << (CLK_CTRL_TIMEOUT_MIN_EXP + div);
-
-	return freq;
-}
-
 static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -198,9 +179,7 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 			 * through low speeds without power cycling.
 			 */
 			sdhci_set_clock(host, host->max_clk);
-			spin_unlock_irq(&host->lock);
 			phy_power_on(sdhci_arasan->phy);
-			spin_lock_irq(&host->lock);
 			sdhci_arasan->is_phy_on = true;
 
 			/*
@@ -219,18 +198,14 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 	}
 
 	if (ctrl_phy && sdhci_arasan->is_phy_on) {
-		spin_unlock_irq(&host->lock);
 		phy_power_off(sdhci_arasan->phy);
-		spin_lock_irq(&host->lock);
 		sdhci_arasan->is_phy_on = false;
 	}
 
 	sdhci_set_clock(host, clock);
 
 	if (ctrl_phy) {
-		spin_unlock_irq(&host->lock);
 		phy_power_on(sdhci_arasan->phy);
-		spin_lock_irq(&host->lock);
 		sdhci_arasan->is_phy_on = true;
 	}
 }
@@ -290,7 +265,7 @@ static int sdhci_arasan_voltage_switch(struct mmc_host *mmc,
 static struct sdhci_ops sdhci_arasan_ops = {
 	.set_clock = sdhci_arasan_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
-	.get_timeout_clock = sdhci_arasan_get_timeout_clock,
+	.get_timeout_clock = sdhci_pltfm_clk_get_max_clock,
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_arasan_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
@@ -319,6 +294,9 @@ static int sdhci_arasan_suspend(struct device *dev)
 	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
 	int ret;
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	ret = sdhci_suspend_host(host);
 	if (ret)
 		return ret;
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 2f9ad213377a..7611fd679f1a 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -29,6 +29,8 @@
 
 #include "sdhci-pltfm.h"
 
+#define SDMMC_MC1R	0x204
+#define		SDMMC_MC1R_DDR		BIT(3)
 #define SDMMC_CACR	0x230
 #define		SDMMC_CACR_CAPWREN	BIT(0)
 #define		SDMMC_CACR_KEY		(0x46 << 8)
@@ -85,11 +87,35 @@ static void sdhci_at91_set_clock(struct sdhci_host *host, unsigned int clock)
 	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 }
 
+/*
+ * In this specific implementation of the SDHCI controller, the power register
+ * needs to have a valid voltage set even when the power supply is managed by
+ * an external regulator.
+ */
+static void sdhci_at91_set_power(struct sdhci_host *host, unsigned char mode,
+		     unsigned short vdd)
+{
+	if (!IS_ERR(host->mmc->supply.vmmc)) {
+		struct mmc_host *mmc = host->mmc;
+
+		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
+	}
+	sdhci_set_power_noreg(host, mode, vdd);
+}
+
+void sdhci_at91_set_uhs_signaling(struct sdhci_host *host, unsigned int timing)
+{
+	if (timing == MMC_TIMING_MMC_DDR52)
+		sdhci_writeb(host, SDMMC_MC1R_DDR, SDMMC_MC1R);
+	sdhci_set_uhs_signaling(host, timing);
+}
+
 static const struct sdhci_ops sdhci_at91_sama5d2_ops = {
 	.set_clock		= sdhci_at91_set_clock,
 	.set_bus_width		= sdhci_set_bus_width,
 	.reset			= sdhci_reset,
-	.set_uhs_signaling	= sdhci_set_uhs_signaling,
+	.set_uhs_signaling	= sdhci_at91_set_uhs_signaling,
+	.set_power		= sdhci_at91_set_power,
 };
 
 static const struct sdhci_pltfm_data soc_data_sama5d2 = {
@@ -112,6 +138,9 @@ static int sdhci_at91_runtime_suspend(struct device *dev)
 
 	ret = sdhci_runtime_suspend_host(host);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	clk_disable_unprepare(priv->gck);
 	clk_disable_unprepare(priv->hclock);
 	clk_disable_unprepare(priv->mainck);
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index d3aa67142839..44b016baa585 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -16,9 +16,12 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/sys_soc.h>
+#include <linux/clk.h>
+#include <linux/ktime.h>
 #include <linux/mmc/host.h>
 #include "sdhci-pltfm.h"
 #include "sdhci-esdhc.h"
@@ -30,6 +33,7 @@ struct sdhci_esdhc {
 	u8 vendor_ver;
 	u8 spec_ver;
 	bool quirk_incorrect_hostver;
+	unsigned int peripheral_clock;
 };
 
 /**
@@ -414,15 +418,25 @@ static int esdhc_of_enable_dma(struct sdhci_host *host)
 static unsigned int esdhc_of_get_max_clock(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
 
-	return pltfm_host->clock;
+	if (esdhc->peripheral_clock)
+		return esdhc->peripheral_clock;
+	else
+		return pltfm_host->clock;
 }
 
 static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
+	unsigned int clock;
 
-	return pltfm_host->clock / 256 / 16;
+	if (esdhc->peripheral_clock)
+		clock = esdhc->peripheral_clock;
+	else
+		clock = pltfm_host->clock;
+	return clock / 256 / 16;
 }
 
 static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
@@ -431,7 +445,7 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
 	int pre_div = 1;
 	int div = 1;
-	u32 timeout;
+	ktime_t timeout;
 	u32 temp;
 
 	host->mmc->actual_clock = 0;
@@ -443,6 +457,20 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 	if (esdhc->vendor_ver < VENDOR_V_23)
 		pre_div = 2;
 
+	/*
+	 * Limit SD clock to 167MHz for ls1046a according to its datasheet
+	 */
+	if (clock > 167000000 &&
+	    of_find_compatible_node(NULL, NULL, "fsl,ls1046a-esdhc"))
+		clock = 167000000;
+
+	/*
+	 * Limit SD clock to 125MHz for ls1012a according to its datasheet
+	 */
+	if (clock > 125000000 &&
+	    of_find_compatible_node(NULL, NULL, "fsl,ls1012a-esdhc"))
+		clock = 125000000;
+
 	/* Workaround to reduce the clock frequency for p1010 esdhc */
 	if (of_find_compatible_node(NULL, NULL, "fsl,p1010-esdhc")) {
 		if (clock > 20000000)
@@ -475,15 +503,14 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 	sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);
 
 	/* Wait max 20 ms */
-	timeout = 20;
+	timeout = ktime_add_ms(ktime_get(), 20);
 	while (!(sdhci_readl(host, ESDHC_PRSSTAT) & ESDHC_CLOCK_STABLE)) {
-		if (timeout == 0) {
+		if (ktime_after(ktime_get(), timeout)) {
 			pr_err("%s: Internal clock never stabilised.\n",
 				mmc_hostname(host->mmc));
 			return;
 		}
-		timeout--;
-		mdelay(1);
+		udelay(10);
 	}
 
 	temp |= ESDHC_CLOCK_SDCLKEN;
@@ -512,6 +539,33 @@ static void esdhc_pltfm_set_bus_width(struct sdhci_host *host, int width)
 	sdhci_writel(host, ctrl, ESDHC_PROCTL);
 }
 
+static void esdhc_clock_enable(struct sdhci_host *host, bool enable)
+{
+	u32 val;
+	ktime_t timeout;
+
+	val = sdhci_readl(host, ESDHC_SYSTEM_CONTROL);
+
+	if (enable)
+		val |= ESDHC_CLOCK_SDCLKEN;
+	else
+		val &= ~ESDHC_CLOCK_SDCLKEN;
+
+	sdhci_writel(host, val, ESDHC_SYSTEM_CONTROL);
+
+	/* Wait max 20 ms */
+	timeout = ktime_add_ms(ktime_get(), 20);
+	val = ESDHC_CLOCK_STABLE;
+	while (!(sdhci_readl(host, ESDHC_PRSSTAT) & val)) {
+		if (ktime_after(ktime_get(), timeout)) {
+			pr_err("%s: Internal clock never stabilised.\n",
+				mmc_hostname(host->mmc));
+			break;
+		}
+		udelay(10);
+	}
+}
+
 static void esdhc_reset(struct sdhci_host *host, u8 mask)
 {
 	sdhci_reset(host, mask);
@@ -520,6 +574,95 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
+/* The SCFG, Supplemental Configuration Unit, provides SoC specific
+ * configuration and status registers for the device. There is a
+ * SDHC IO VSEL control register on SCFG for some platforms. It's
+ * used to support SDHC IO voltage switching.
+ */
+static const struct of_device_id scfg_device_ids[] = {
+	{ .compatible = "fsl,t1040-scfg", },
+	{ .compatible = "fsl,ls1012a-scfg", },
+	{ .compatible = "fsl,ls1046a-scfg", },
+	{}
+};
+
+/* SDHC IO VSEL control register definition */
+#define SCFG_SDHCIOVSELCR	0x408
+#define SDHCIOVSELCR_TGLEN	0x80000000
+#define SDHCIOVSELCR_VSELVAL	0x60000000
+#define SDHCIOVSELCR_SDHC_VS	0x00000001
+
+static int esdhc_signal_voltage_switch(struct mmc_host *mmc,
+				       struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct device_node *scfg_node;
+	void __iomem *scfg_base = NULL;
+	u32 sdhciovselcr;
+	u32 val;
+
+	/*
+	 * Signal Voltage Switching is only applicable for Host Controllers
+	 * v3.00 and above.
+	 */
+	if (host->version < SDHCI_SPEC_300)
+		return 0;
+
+	val = sdhci_readl(host, ESDHC_PROCTL);
+
+	switch (ios->signal_voltage) {
+	case MMC_SIGNAL_VOLTAGE_330:
+		val &= ~ESDHC_VOLT_SEL;
+		sdhci_writel(host, val, ESDHC_PROCTL);
+		return 0;
+	case MMC_SIGNAL_VOLTAGE_180:
+		scfg_node = of_find_matching_node(NULL, scfg_device_ids);
+		if (scfg_node)
+			scfg_base = of_iomap(scfg_node, 0);
+		if (scfg_base) {
+			sdhciovselcr = SDHCIOVSELCR_TGLEN |
+				       SDHCIOVSELCR_VSELVAL;
+			iowrite32be(sdhciovselcr,
+				scfg_base + SCFG_SDHCIOVSELCR);
+
+			val |= ESDHC_VOLT_SEL;
+			sdhci_writel(host, val, ESDHC_PROCTL);
+			mdelay(5);
+
+			sdhciovselcr = SDHCIOVSELCR_TGLEN |
+				       SDHCIOVSELCR_SDHC_VS;
+			iowrite32be(sdhciovselcr,
+				scfg_base + SCFG_SDHCIOVSELCR);
+			iounmap(scfg_base);
+		} else {
+			val |= ESDHC_VOLT_SEL;
+			sdhci_writel(host, val, ESDHC_PROCTL);
+		}
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static int esdhc_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	u32 val;
+
+	/* Use tuning block for tuning procedure */
+	esdhc_clock_enable(host, false);
+	val = sdhci_readl(host, ESDHC_DMA_SYSCTL);
+	val |= ESDHC_FLUSH_ASYNC_FIFO;
+	sdhci_writel(host, val, ESDHC_DMA_SYSCTL);
+
+	val = sdhci_readl(host, ESDHC_TBCTL);
+	val |= ESDHC_TB_EN;
+	sdhci_writel(host, val, ESDHC_TBCTL);
+	esdhc_clock_enable(host, true);
+
+	return sdhci_execute_tuning(mmc, opcode);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static u32 esdhc_proctl;
 static int esdhc_of_suspend(struct device *dev)
@@ -528,6 +671,9 @@ static int esdhc_of_suspend(struct device *dev)
 
 	esdhc_proctl = sdhci_readl(host, SDHCI_HOST_CONTROL);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	return sdhci_suspend_host(host);
 }
 
@@ -610,6 +756,9 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_esdhc *esdhc;
+	struct device_node *np;
+	struct clk *clk;
+	u32 val;
 	u16 host_ver;
 
 	pltfm_host = sdhci_priv(host);
@@ -623,6 +772,32 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host)
 		esdhc->quirk_incorrect_hostver = true;
 	else
 		esdhc->quirk_incorrect_hostver = false;
+
+	np = pdev->dev.of_node;
+	clk = of_clk_get(np, 0);
+	if (!IS_ERR(clk)) {
+		/*
+		 * esdhc->peripheral_clock would be assigned with a value
+		 * which is eSDHC base clock when use periperal clock.
+		 * For ls1046a, the clock value got by common clk API is
+		 * peripheral clock while the eSDHC base clock is 1/2
+		 * peripheral clock.
+		 */
+		if (of_device_is_compatible(np, "fsl,ls1046a-esdhc"))
+			esdhc->peripheral_clock = clk_get_rate(clk) / 2;
+		else
+			esdhc->peripheral_clock = clk_get_rate(clk);
+
+		clk_put(clk);
+	}
+
+	if (esdhc->peripheral_clock) {
+		esdhc_clock_enable(host, false);
+		val = sdhci_readl(host, ESDHC_DMA_SYSCTL);
+		val |= ESDHC_PERIPHERAL_CLK_SEL;
+		sdhci_writel(host, val, ESDHC_DMA_SYSCTL);
+		esdhc_clock_enable(host, true);
+	}
 }
 
 static int sdhci_esdhc_probe(struct platform_device *pdev)
@@ -645,6 +820,11 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
+	host->mmc_host_ops.start_signal_voltage_switch =
+		esdhc_signal_voltage_switch;
+	host->mmc_host_ops.execute_tuning = esdhc_execute_tuning;
+	host->tuning_delay = 1;
+
 	esdhc_init(pdev, host);
 
 	sdhci_get_of_property(pdev);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 982b3e349426..92fc3f7c538d 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -12,6 +12,7 @@
  *     - JMicron (hardware and technical support)
  */
 
+#include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
 #include <linux/module.h>
@@ -36,10 +37,138 @@
 static int sdhci_pci_enable_dma(struct sdhci_host *host);
 static void sdhci_pci_set_bus_width(struct sdhci_host *host, int width);
 static void sdhci_pci_hw_reset(struct sdhci_host *host);
-static int sdhci_pci_select_drive_strength(struct sdhci_host *host,
-					   struct mmc_card *card,
-					   unsigned int max_dtr, int host_drv,
-					   int card_drv, int *drv_type);
+
+#ifdef CONFIG_PM_SLEEP
+static int __sdhci_pci_suspend_host(struct sdhci_pci_chip *chip)
+{
+	int i, ret;
+
+	for (i = 0; i < chip->num_slots; i++) {
+		struct sdhci_pci_slot *slot = chip->slots[i];
+		struct sdhci_host *host;
+
+		if (!slot)
+			continue;
+
+		host = slot->host;
+
+		if (chip->pm_retune && host->tuning_mode != SDHCI_TUNING_MODE_3)
+			mmc_retune_needed(host->mmc);
+
+		ret = sdhci_suspend_host(host);
+		if (ret)
+			goto err_pci_suspend;
+
+		if (host->mmc->pm_flags & MMC_PM_WAKE_SDIO_IRQ)
+			sdhci_enable_irq_wakeups(host);
+	}
+
+	return 0;
+
+err_pci_suspend:
+	while (--i >= 0)
+		sdhci_resume_host(chip->slots[i]->host);
+	return ret;
+}
+
+static int sdhci_pci_init_wakeup(struct sdhci_pci_chip *chip)
+{
+	mmc_pm_flag_t pm_flags = 0;
+	int i;
+
+	for (i = 0; i < chip->num_slots; i++) {
+		struct sdhci_pci_slot *slot = chip->slots[i];
+
+		if (slot)
+			pm_flags |= slot->host->mmc->pm_flags;
+	}
+
+	return device_init_wakeup(&chip->pdev->dev,
+				  (pm_flags & MMC_PM_KEEP_POWER) &&
+				  (pm_flags & MMC_PM_WAKE_SDIO_IRQ));
+}
+
+static int sdhci_pci_suspend_host(struct sdhci_pci_chip *chip)
+{
+	int ret;
+
+	ret = __sdhci_pci_suspend_host(chip);
+	if (ret)
+		return ret;
+
+	sdhci_pci_init_wakeup(chip);
+
+	return 0;
+}
+
+int sdhci_pci_resume_host(struct sdhci_pci_chip *chip)
+{
+	struct sdhci_pci_slot *slot;
+	int i, ret;
+
+	for (i = 0; i < chip->num_slots; i++) {
+		slot = chip->slots[i];
+		if (!slot)
+			continue;
+
+		ret = sdhci_resume_host(slot->host);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PM
+static int sdhci_pci_runtime_suspend_host(struct sdhci_pci_chip *chip)
+{
+	struct sdhci_pci_slot *slot;
+	struct sdhci_host *host;
+	int i, ret;
+
+	for (i = 0; i < chip->num_slots; i++) {
+		slot = chip->slots[i];
+		if (!slot)
+			continue;
+
+		host = slot->host;
+
+		ret = sdhci_runtime_suspend_host(host);
+		if (ret)
+			goto err_pci_runtime_suspend;
+
+		if (chip->rpm_retune &&
+		    host->tuning_mode != SDHCI_TUNING_MODE_3)
+			mmc_retune_needed(host->mmc);
+	}
+
+	return 0;
+
+err_pci_runtime_suspend:
+	while (--i >= 0)
+		sdhci_runtime_resume_host(chip->slots[i]->host);
+	return ret;
+}
+
+static int sdhci_pci_runtime_resume_host(struct sdhci_pci_chip *chip)
+{
+	struct sdhci_pci_slot *slot;
+	int i, ret;
+
+	for (i = 0; i < chip->num_slots; i++) {
+		slot = chip->slots[i];
+		if (!slot)
+			continue;
+
+		ret = sdhci_runtime_resume_host(slot->host);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+#endif
 
 /*****************************************************************************\
  *                                                                           *
@@ -71,14 +200,16 @@ static int ricoh_mmc_probe_slot(struct sdhci_pci_slot *slot)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int ricoh_mmc_resume(struct sdhci_pci_chip *chip)
 {
 	/* Apply a delay to allow controller to settle */
 	/* Otherwise it becomes confused if card state changed
 		during suspend */
 	msleep(500);
-	return 0;
+	return sdhci_pci_resume_host(chip);
 }
+#endif
 
 static const struct sdhci_pci_fixes sdhci_ricoh = {
 	.probe		= ricoh_probe,
@@ -89,7 +220,9 @@ static const struct sdhci_pci_fixes sdhci_ricoh = {
 
 static const struct sdhci_pci_fixes sdhci_ricoh_mmc = {
 	.probe_slot	= ricoh_mmc_probe_slot,
+#ifdef CONFIG_PM_SLEEP
 	.resume		= ricoh_mmc_resume,
+#endif
 	.quirks		= SDHCI_QUIRK_32BIT_DMA_ADDR |
 			  SDHCI_QUIRK_CLOCK_BEFORE_RESET |
 			  SDHCI_QUIRK_NO_CARD_NO_RESET |
@@ -259,6 +392,81 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = {
 	.probe_slot	= pch_hc_probe_slot,
 };
 
+enum {
+	INTEL_DSM_FNS		=  0,
+	INTEL_DSM_DRV_STRENGTH	=  9,
+	INTEL_DSM_D3_RETUNE	= 10,
+};
+
+struct intel_host {
+	u32	dsm_fns;
+	int	drv_strength;
+	bool	d3_retune;
+};
+
+const u8 intel_dsm_uuid[] = {
+	0xA5, 0x3E, 0xC1, 0xF6, 0xCD, 0x65, 0x1F, 0x46,
+	0xAB, 0x7A, 0x29, 0xF7, 0xE8, 0xD5, 0xBD, 0x61,
+};
+
+static int __intel_dsm(struct intel_host *intel_host, struct device *dev,
+		       unsigned int fn, u32 *result)
+{
+	union acpi_object *obj;
+	int err = 0;
+	size_t len;
+
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(dev), intel_dsm_uuid, 0, fn, NULL);
+	if (!obj)
+		return -EOPNOTSUPP;
+
+	if (obj->type != ACPI_TYPE_BUFFER || obj->buffer.length < 1) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	len = min_t(size_t, obj->buffer.length, 4);
+
+	*result = 0;
+	memcpy(result, obj->buffer.pointer, len);
+out:
+	ACPI_FREE(obj);
+
+	return err;
+}
+
+static int intel_dsm(struct intel_host *intel_host, struct device *dev,
+		     unsigned int fn, u32 *result)
+{
+	if (fn > 31 || !(intel_host->dsm_fns & (1 << fn)))
+		return -EOPNOTSUPP;
+
+	return __intel_dsm(intel_host, dev, fn, result);
+}
+
+static void intel_dsm_init(struct intel_host *intel_host, struct device *dev,
+			   struct mmc_host *mmc)
+{
+	int err;
+	u32 val;
+
+	err = __intel_dsm(intel_host, dev, INTEL_DSM_FNS, &intel_host->dsm_fns);
+	if (err) {
+		pr_debug("%s: DSM not supported, error %d\n",
+			 mmc_hostname(mmc), err);
+		return;
+	}
+
+	pr_debug("%s: DSM function mask %#x\n",
+		 mmc_hostname(mmc), intel_host->dsm_fns);
+
+	err = intel_dsm(intel_host, dev, INTEL_DSM_DRV_STRENGTH, &val);
+	intel_host->drv_strength = err ? 0 : val;
+
+	err = intel_dsm(intel_host, dev, INTEL_DSM_D3_RETUNE, &val);
+	intel_host->d3_retune = err ? true : !!val;
+}
+
 static void sdhci_pci_int_hw_reset(struct sdhci_host *host)
 {
 	u8 reg;
@@ -274,67 +482,15 @@ static void sdhci_pci_int_hw_reset(struct sdhci_host *host)
 	usleep_range(300, 1000);
 }
 
-static int spt_select_drive_strength(struct sdhci_host *host,
-				     struct mmc_card *card,
-				     unsigned int max_dtr,
-				     int host_drv, int card_drv, int *drv_type)
-{
-	int drive_strength;
-
-	if (sdhci_pci_spt_drive_strength > 0)
-		drive_strength = sdhci_pci_spt_drive_strength & 0xf;
-	else
-		drive_strength = 0; /* Default 50-ohm */
-
-	if ((mmc_driver_type_mask(drive_strength) & card_drv) == 0)
-		drive_strength = 0; /* Default 50-ohm */
-
-	return drive_strength;
-}
-
-/* Try to read the drive strength from the card */
-static void spt_read_drive_strength(struct sdhci_host *host)
+static int intel_select_drive_strength(struct mmc_card *card,
+				       unsigned int max_dtr, int host_drv,
+				       int card_drv, int *drv_type)
 {
-	u32 val, i, t;
-	u16 m;
-
-	if (sdhci_pci_spt_drive_strength)
-		return;
-
-	sdhci_pci_spt_drive_strength = -1;
-
-	m = sdhci_readw(host, SDHCI_HOST_CONTROL2) & 0x7;
-	if (m != 3 && m != 5)
-		return;
-	val = sdhci_readl(host, SDHCI_PRESENT_STATE);
-	if (val & 0x3)
-		return;
-	sdhci_writel(host, 0x007f0023, SDHCI_INT_ENABLE);
-	sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
-	sdhci_writew(host, 0x10, SDHCI_TRANSFER_MODE);
-	sdhci_writeb(host, 0xe, SDHCI_TIMEOUT_CONTROL);
-	sdhci_writew(host, 512, SDHCI_BLOCK_SIZE);
-	sdhci_writew(host, 1, SDHCI_BLOCK_COUNT);
-	sdhci_writel(host, 0, SDHCI_ARGUMENT);
-	sdhci_writew(host, 0x83b, SDHCI_COMMAND);
-	for (i = 0; i < 1000; i++) {
-		val = sdhci_readl(host, SDHCI_INT_STATUS);
-		if (val & 0xffff8000)
-			return;
-		if (val & 0x20)
-			break;
-		udelay(1);
-	}
-	val = sdhci_readl(host, SDHCI_PRESENT_STATE);
-	if (!(val & 0x800))
-		return;
-	for (i = 0; i < 47; i++)
-		val = sdhci_readl(host, SDHCI_BUFFER);
-	t = val & 0xf00;
-	if (t != 0x200 && t != 0x300)
-		return;
+	struct sdhci_host *host = mmc_priv(card->host);
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct intel_host *intel_host = sdhci_pci_priv(slot);
 
-	sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf);
+	return intel_host->drv_strength;
 }
 
 static int bxt_get_cd(struct mmc_host *mmc)
@@ -359,8 +515,57 @@ out:
 	return ret;
 }
 
+#define SDHCI_INTEL_PWR_TIMEOUT_CNT	20
+#define SDHCI_INTEL_PWR_TIMEOUT_UDELAY	100
+
+static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
+				  unsigned short vdd)
+{
+	int cntr;
+	u8 reg;
+
+	sdhci_set_power(host, mode, vdd);
+
+	if (mode == MMC_POWER_OFF)
+		return;
+
+	/*
+	 * Bus power might not enable after D3 -> D0 transition due to the
+	 * present state not yet having propagated. Retry for up to 2ms.
+	 */
+	for (cntr = 0; cntr < SDHCI_INTEL_PWR_TIMEOUT_CNT; cntr++) {
+		reg = sdhci_readb(host, SDHCI_POWER_CONTROL);
+		if (reg & SDHCI_POWER_ON)
+			break;
+		udelay(SDHCI_INTEL_PWR_TIMEOUT_UDELAY);
+		reg |= SDHCI_POWER_ON;
+		sdhci_writeb(host, reg, SDHCI_POWER_CONTROL);
+	}
+}
+
+static const struct sdhci_ops sdhci_intel_byt_ops = {
+	.set_clock		= sdhci_set_clock,
+	.set_power		= sdhci_intel_set_power,
+	.enable_dma		= sdhci_pci_enable_dma,
+	.set_bus_width		= sdhci_pci_set_bus_width,
+	.reset			= sdhci_reset,
+	.set_uhs_signaling	= sdhci_set_uhs_signaling,
+	.hw_reset		= sdhci_pci_hw_reset,
+};
+
+static void byt_read_dsm(struct sdhci_pci_slot *slot)
+{
+	struct intel_host *intel_host = sdhci_pci_priv(slot);
+	struct device *dev = &slot->chip->pdev->dev;
+	struct mmc_host *mmc = slot->host->mmc;
+
+	intel_dsm_init(intel_host, dev, mmc);
+	slot->chip->rpm_retune = intel_host->d3_retune;
+}
+
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
+	byt_read_dsm(slot);
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 				 MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
 				 MMC_CAP_CMD_DURING_TFR |
@@ -369,10 +574,8 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 	slot->hw_reset = sdhci_pci_int_hw_reset;
 	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BSW_EMMC)
 		slot->host->timeout_clk = 1000; /* 1000 kHz i.e. 1 MHz */
-	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_SPT_EMMC) {
-		spt_read_drive_strength(slot->host);
-		slot->select_drive_strength = spt_select_drive_strength;
-	}
+	slot->host->mmc_host_ops.select_drive_strength =
+						intel_select_drive_strength;
 	return 0;
 }
 
@@ -405,6 +608,8 @@ static int ni_byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 {
 	int err;
 
+	byt_read_dsm(slot);
+
 	err = ni_set_max_freq(slot);
 	if (err)
 		return err;
@@ -416,6 +621,7 @@ static int ni_byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 
 static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 {
+	byt_read_dsm(slot);
 	slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE |
 				 MMC_CAP_WAIT_WHILE_BUSY;
 	return 0;
@@ -423,59 +629,20 @@ static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 
 static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 {
-	slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
+	byt_read_dsm(slot);
+	slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY |
+				 MMC_CAP_AGGRESSIVE_PM;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
 	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD ||
 	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXTM_SD ||
 	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD ||
-	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_SD) {
+	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_SD)
 		slot->host->mmc_host_ops.get_cd = bxt_get_cd;
-		slot->host->mmc->caps |= MMC_CAP_AGGRESSIVE_PM;
-	}
 
 	return 0;
 }
 
-#define SDHCI_INTEL_PWR_TIMEOUT_CNT	20
-#define SDHCI_INTEL_PWR_TIMEOUT_UDELAY	100
-
-static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
-				  unsigned short vdd)
-{
-	int cntr;
-	u8 reg;
-
-	sdhci_set_power(host, mode, vdd);
-
-	if (mode == MMC_POWER_OFF)
-		return;
-
-	/*
-	 * Bus power might not enable after D3 -> D0 transition due to the
-	 * present state not yet having propagated. Retry for up to 2ms.
-	 */
-	for (cntr = 0; cntr < SDHCI_INTEL_PWR_TIMEOUT_CNT; cntr++) {
-		reg = sdhci_readb(host, SDHCI_POWER_CONTROL);
-		if (reg & SDHCI_POWER_ON)
-			break;
-		udelay(SDHCI_INTEL_PWR_TIMEOUT_UDELAY);
-		reg |= SDHCI_POWER_ON;
-		sdhci_writeb(host, reg, SDHCI_POWER_CONTROL);
-	}
-}
-
-static const struct sdhci_ops sdhci_intel_byt_ops = {
-	.set_clock		= sdhci_set_clock,
-	.set_power		= sdhci_intel_set_power,
-	.enable_dma		= sdhci_pci_enable_dma,
-	.set_bus_width		= sdhci_pci_set_bus_width,
-	.reset			= sdhci_reset,
-	.set_uhs_signaling	= sdhci_set_uhs_signaling,
-	.hw_reset		= sdhci_pci_hw_reset,
-	.select_drive_strength	= sdhci_pci_select_drive_strength,
-};
-
 static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
 	.allow_runtime_pm = true,
 	.probe_slot	= byt_emmc_probe_slot,
@@ -484,6 +651,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
 			  SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 |
 			  SDHCI_QUIRK2_STOP_WITH_TC,
 	.ops		= &sdhci_intel_byt_ops,
+	.priv_size	= sizeof(struct intel_host),
 };
 
 static const struct sdhci_pci_fixes sdhci_ni_byt_sdio = {
@@ -493,6 +661,7 @@ static const struct sdhci_pci_fixes sdhci_ni_byt_sdio = {
 	.allow_runtime_pm = true,
 	.probe_slot	= ni_byt_sdio_probe_slot,
 	.ops		= &sdhci_intel_byt_ops,
+	.priv_size	= sizeof(struct intel_host),
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
@@ -502,6 +671,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
 	.allow_runtime_pm = true,
 	.probe_slot	= byt_sdio_probe_slot,
 	.ops		= &sdhci_intel_byt_ops,
+	.priv_size	= sizeof(struct intel_host),
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
@@ -513,6 +683,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
 	.own_cd_for_runtime_pm = true,
 	.probe_slot	= byt_sd_probe_slot,
 	.ops		= &sdhci_intel_byt_ops,
+	.priv_size	= sizeof(struct intel_host),
 };
 
 /* Define Host controllers for Intel Merrifield platform */
@@ -715,9 +886,14 @@ static void jmicron_remove_slot(struct sdhci_pci_slot *slot, int dead)
 		jmicron_enable_mmc(slot->host, 0);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int jmicron_suspend(struct sdhci_pci_chip *chip)
 {
-	int i;
+	int i, ret;
+
+	ret = __sdhci_pci_suspend_host(chip);
+	if (ret)
+		return ret;
 
 	if (chip->pdev->device == PCI_DEVICE_ID_JMICRON_JMB38X_MMC ||
 	    chip->pdev->device == PCI_DEVICE_ID_JMICRON_JMB388_ESD) {
@@ -725,6 +901,8 @@ static int jmicron_suspend(struct sdhci_pci_chip *chip)
 			jmicron_enable_mmc(chip->slots[i]->host, 0);
 	}
 
+	sdhci_pci_init_wakeup(chip);
+
 	return 0;
 }
 
@@ -744,15 +922,18 @@ static int jmicron_resume(struct sdhci_pci_chip *chip)
 		return ret;
 	}
 
-	return 0;
+	return sdhci_pci_resume_host(chip);
 }
+#endif
 
 static const struct sdhci_pci_fixes sdhci_o2 = {
 	.probe = sdhci_pci_o2_probe,
 	.quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2 = SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD,
 	.probe_slot = sdhci_pci_o2_probe_slot,
+#ifdef CONFIG_PM_SLEEP
 	.resume = sdhci_pci_o2_resume,
+#endif
 };
 
 static const struct sdhci_pci_fixes sdhci_jmicron = {
@@ -761,8 +942,10 @@ static const struct sdhci_pci_fixes sdhci_jmicron = {
 	.probe_slot	= jmicron_probe_slot,
 	.remove_slot	= jmicron_remove_slot,
 
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= jmicron_suspend,
 	.resume		= jmicron_resume,
+#endif
 };
 
 /* SysKonnect CardBus2SDIO extra registers */
@@ -1613,20 +1796,6 @@ static void sdhci_pci_hw_reset(struct sdhci_host *host)
 		slot->hw_reset(host);
 }
 
-static int sdhci_pci_select_drive_strength(struct sdhci_host *host,
-					   struct mmc_card *card,
-					   unsigned int max_dtr, int host_drv,
-					   int card_drv, int *drv_type)
-{
-	struct sdhci_pci_slot *slot = sdhci_priv(host);
-
-	if (!slot->select_drive_strength)
-		return 0;
-
-	return slot->select_drive_strength(host, card, max_dtr, host_drv,
-					   card_drv, drv_type);
-}
-
 static const struct sdhci_ops sdhci_pci_ops = {
 	.set_clock	= sdhci_set_clock,
 	.enable_dma	= sdhci_pci_enable_dma,
@@ -1634,7 +1803,6 @@ static const struct sdhci_ops sdhci_pci_ops = {
 	.reset		= sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
-	.select_drive_strength	= sdhci_pci_select_drive_strength,
 };
 
 /*****************************************************************************\
@@ -1647,83 +1815,29 @@ static const struct sdhci_ops sdhci_pci_ops = {
 static int sdhci_pci_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct sdhci_pci_chip *chip;
-	struct sdhci_pci_slot *slot;
-	mmc_pm_flag_t slot_pm_flags;
-	mmc_pm_flag_t pm_flags = 0;
-	int i, ret;
+	struct sdhci_pci_chip *chip = pci_get_drvdata(pdev);
 
-	chip = pci_get_drvdata(pdev);
 	if (!chip)
 		return 0;
 
-	for (i = 0; i < chip->num_slots; i++) {
-		slot = chip->slots[i];
-		if (!slot)
-			continue;
-
-		ret = sdhci_suspend_host(slot->host);
-
-		if (ret)
-			goto err_pci_suspend;
-
-		slot_pm_flags = slot->host->mmc->pm_flags;
-		if (slot_pm_flags & MMC_PM_WAKE_SDIO_IRQ)
-			sdhci_enable_irq_wakeups(slot->host);
-
-		pm_flags |= slot_pm_flags;
-	}
-
-	if (chip->fixes && chip->fixes->suspend) {
-		ret = chip->fixes->suspend(chip);
-		if (ret)
-			goto err_pci_suspend;
-	}
-
-	if (pm_flags & MMC_PM_KEEP_POWER) {
-		if (pm_flags & MMC_PM_WAKE_SDIO_IRQ)
-			device_init_wakeup(dev, true);
-		else
-			device_init_wakeup(dev, false);
-	} else
-		device_init_wakeup(dev, false);
-
-	return 0;
+	if (chip->fixes && chip->fixes->suspend)
+		return chip->fixes->suspend(chip);
 
-err_pci_suspend:
-	while (--i >= 0)
-		sdhci_resume_host(chip->slots[i]->host);
-	return ret;
+	return sdhci_pci_suspend_host(chip);
 }
 
 static int sdhci_pci_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct sdhci_pci_chip *chip;
-	struct sdhci_pci_slot *slot;
-	int i, ret;
+	struct sdhci_pci_chip *chip = pci_get_drvdata(pdev);
 
-	chip = pci_get_drvdata(pdev);
 	if (!chip)
 		return 0;
 
-	if (chip->fixes && chip->fixes->resume) {
-		ret = chip->fixes->resume(chip);
-		if (ret)
-			return ret;
-	}
-
-	for (i = 0; i < chip->num_slots; i++) {
-		slot = chip->slots[i];
-		if (!slot)
-			continue;
-
-		ret = sdhci_resume_host(slot->host);
-		if (ret)
-			return ret;
-	}
+	if (chip->fixes && chip->fixes->resume)
+		return chip->fixes->resume(chip);
 
-	return 0;
+	return sdhci_pci_resume_host(chip);
 }
 #endif
 
@@ -1731,67 +1845,29 @@ static int sdhci_pci_resume(struct device *dev)
 static int sdhci_pci_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct sdhci_pci_chip *chip;
-	struct sdhci_pci_slot *slot;
-	int i, ret;
+	struct sdhci_pci_chip *chip = pci_get_drvdata(pdev);
 
-	chip = pci_get_drvdata(pdev);
 	if (!chip)
 		return 0;
 
-	for (i = 0; i < chip->num_slots; i++) {
-		slot = chip->slots[i];
-		if (!slot)
-			continue;
-
-		ret = sdhci_runtime_suspend_host(slot->host);
-
-		if (ret)
-			goto err_pci_runtime_suspend;
-	}
+	if (chip->fixes && chip->fixes->runtime_suspend)
+		return chip->fixes->runtime_suspend(chip);
 
-	if (chip->fixes && chip->fixes->suspend) {
-		ret = chip->fixes->suspend(chip);
-		if (ret)
-			goto err_pci_runtime_suspend;
-	}
-
-	return 0;
-
-err_pci_runtime_suspend:
-	while (--i >= 0)
-		sdhci_runtime_resume_host(chip->slots[i]->host);
-	return ret;
+	return sdhci_pci_runtime_suspend_host(chip);
 }
 
 static int sdhci_pci_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct sdhci_pci_chip *chip;
-	struct sdhci_pci_slot *slot;
-	int i, ret;
+	struct sdhci_pci_chip *chip = pci_get_drvdata(pdev);
 
-	chip = pci_get_drvdata(pdev);
 	if (!chip)
 		return 0;
 
-	if (chip->fixes && chip->fixes->resume) {
-		ret = chip->fixes->resume(chip);
-		if (ret)
-			return ret;
-	}
+	if (chip->fixes && chip->fixes->runtime_resume)
+		return chip->fixes->runtime_resume(chip);
 
-	for (i = 0; i < chip->num_slots; i++) {
-		slot = chip->slots[i];
-		if (!slot)
-			continue;
-
-		ret = sdhci_runtime_resume_host(slot->host);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	return sdhci_pci_runtime_resume_host(chip);
 }
 #endif
 
@@ -1814,6 +1890,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 	struct sdhci_pci_slot *slot;
 	struct sdhci_host *host;
 	int ret, bar = first_bar + slotno;
+	size_t priv_size = chip->fixes ? chip->fixes->priv_size : 0;
 
 	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
 		dev_err(&pdev->dev, "BAR %d is not iomem. Aborting.\n", bar);
@@ -1835,7 +1912,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 		return ERR_PTR(-ENODEV);
 	}
 
-	host = sdhci_alloc_host(&pdev->dev, sizeof(struct sdhci_pci_slot));
+	host = sdhci_alloc_host(&pdev->dev, sizeof(*slot) + priv_size);
 	if (IS_ERR(host)) {
 		dev_err(&pdev->dev, "cannot allocate host\n");
 		return ERR_CAST(host);
@@ -1915,7 +1992,10 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 		}
 	}
 
-	ret = sdhci_add_host(host);
+	if (chip->fixes && chip->fixes->add_host)
+		ret = chip->fixes->add_host(slot);
+	else
+		ret = sdhci_add_host(host);
 	if (ret)
 		goto remove;
 
@@ -2038,6 +2118,8 @@ static int sdhci_pci_probe(struct pci_dev *pdev,
 		chip->allow_runtime_pm = chip->fixes->allow_runtime_pm;
 	}
 	chip->num_slots = slots;
+	chip->pm_retune = true;
+	chip->rpm_retune = true;
 
 	pci_set_drvdata(pdev, chip);
 
diff --git a/drivers/mmc/host/sdhci-pci-data.c b/drivers/mmc/host/sdhci-pci-data.c
index 56fddc622a54..a611217769f5 100644
--- a/drivers/mmc/host/sdhci-pci-data.c
+++ b/drivers/mmc/host/sdhci-pci-data.c
@@ -3,6 +3,3 @@
 
 struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno);
 EXPORT_SYMBOL_GPL(sdhci_pci_get_data);
-
-int sdhci_pci_spt_drive_strength;
-EXPORT_SYMBOL_GPL(sdhci_pci_spt_drive_strength);
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index d48f03104b5b..14273ca00641 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -384,8 +384,10 @@ int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
 int sdhci_pci_o2_resume(struct sdhci_pci_chip *chip)
 {
 	sdhci_pci_o2_probe(chip);
-	return 0;
+	return sdhci_pci_resume_host(chip);
 }
+#endif
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 36f743464fcc..37766d20a600 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -64,12 +64,20 @@ struct sdhci_pci_fixes {
 	int			(*probe) (struct sdhci_pci_chip *);
 
 	int			(*probe_slot) (struct sdhci_pci_slot *);
+	int			(*add_host) (struct sdhci_pci_slot *);
 	void			(*remove_slot) (struct sdhci_pci_slot *, int);
 
+#ifdef CONFIG_PM_SLEEP
 	int			(*suspend) (struct sdhci_pci_chip *);
 	int			(*resume) (struct sdhci_pci_chip *);
+#endif
+#ifdef CONFIG_PM
+	int			(*runtime_suspend) (struct sdhci_pci_chip *);
+	int			(*runtime_resume) (struct sdhci_pci_chip *);
+#endif
 
 	const struct sdhci_ops	*ops;
+	size_t			priv_size;
 };
 
 struct sdhci_pci_slot {
@@ -85,10 +93,7 @@ struct sdhci_pci_slot {
 	bool			cd_override_level;
 
 	void (*hw_reset)(struct sdhci_host *host);
-	int (*select_drive_strength)(struct sdhci_host *host,
-				     struct mmc_card *card,
-				     unsigned int max_dtr, int host_drv,
-				     int card_drv, int *drv_type);
+	unsigned long		private[0] ____cacheline_aligned;
 };
 
 struct sdhci_pci_chip {
@@ -97,10 +102,21 @@ struct sdhci_pci_chip {
 	unsigned int		quirks;
 	unsigned int		quirks2;
 	bool			allow_runtime_pm;
+	bool			pm_retune;
+	bool			rpm_retune;
 	const struct sdhci_pci_fixes *fixes;
 
 	int			num_slots;	/* Slots on controller */
 	struct sdhci_pci_slot	*slots[MAX_SLOTS]; /* Pointers to host slots */
 };
 
+static inline void *sdhci_pci_priv(struct sdhci_pci_slot *slot)
+{
+	return (void *)slot->private;
+}
+
+#ifdef CONFIG_PM_SLEEP
+int sdhci_pci_resume_host(struct sdhci_pci_chip *chip);
+#endif
+
 #endif /* __SDHCI_PCI_H */
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index ad49bfaf5bf8..e090d8c42ddb 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -213,6 +213,9 @@ static int sdhci_pltfm_suspend(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	return sdhci_suspend_host(host);
 }
 
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index 347eae2d7b6a..995083ce1c46 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -185,7 +185,11 @@ static int sdhci_pxav2_probe(struct platform_device *pdev)
 		goto err_clk_get;
 	}
 	pltfm_host->clk = clk;
-	clk_prepare_enable(clk);
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable io clock\n");
+		goto err_clk_enable;
+	}
 
 	host->quirks = SDHCI_QUIRK_BROKEN_ADMA
 		| SDHCI_QUIRK_BROKEN_TIMEOUT_VAL
@@ -222,12 +226,11 @@ static int sdhci_pxav2_probe(struct platform_device *pdev)
 		goto err_add_host;
 	}
 
-	platform_set_drvdata(pdev, host);
-
 	return 0;
 
 err_add_host:
 	clk_disable_unprepare(clk);
+err_clk_enable:
 	clk_put(clk);
 err_clk_get:
 	sdhci_pltfm_free(pdev);
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index d0f5c05fbc19..f953f35c2624 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -323,11 +323,8 @@ static void pxav3_set_power(struct sdhci_host *host, unsigned char mode,
 	if (host->pwr == 0)
 		vdd = 0;
 
-	if (!IS_ERR(mmc->supply.vmmc)) {
-		spin_unlock_irq(&host->lock);
+	if (!IS_ERR(mmc->supply.vmmc))
 		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
-		spin_lock_irq(&host->lock);
-	}
 }
 
 static const struct sdhci_ops pxav3_sdhci_ops = {
@@ -480,8 +477,6 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 		goto err_add_host;
 	}
 
-	platform_set_drvdata(pdev, host);
-
 	if (host->mmc->pm_caps & MMC_PM_WAKE_SDIO_IRQ)
 		device_init_wakeup(&pdev->dev, 1);
 
@@ -529,6 +524,8 @@ static int sdhci_pxav3_suspend(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
 	pm_runtime_get_sync(dev);
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
 	ret = sdhci_suspend_host(host);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
@@ -562,6 +559,9 @@ static int sdhci_pxav3_runtime_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	clk_disable_unprepare(pxa->clk_io);
 	if (!IS_ERR(pxa->clk_core))
 		clk_disable_unprepare(pxa->clk_core);
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 3e5c83d435ae..7c065a70f92b 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -190,9 +190,7 @@ static unsigned int sdhci_s3c_consider_clock(struct sdhci_s3c *ourhost,
 	 * speed possible with selected clock source and skip the division.
 	 */
 	if (ourhost->no_divider) {
-		spin_unlock_irq(&ourhost->host->lock);
 		rate = clk_round_rate(clksrc, wanted);
-		spin_lock_irq(&ourhost->host->lock);
 		return wanted - rate;
 	}
 
@@ -389,9 +387,7 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
 	clk &= ~SDHCI_CLOCK_CARD_EN;
 	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 
-	spin_unlock_irq(&host->lock);
 	ret = clk_set_rate(ourhost->clk_bus[ourhost->cur_clk], clock);
-	spin_lock_irq(&host->lock);
 	if (ret != 0) {
 		dev_err(dev, "%s: failed to set clock rate %uHz\n",
 			mmc_hostname(host->mmc), clock);
@@ -743,6 +739,9 @@ static int sdhci_s3c_suspend(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	return sdhci_suspend_host(host);
 }
 
@@ -764,6 +763,9 @@ static int sdhci_s3c_runtime_suspend(struct device *dev)
 
 	ret = sdhci_runtime_suspend_host(host);
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	if (ourhost->cur_clk >= 0)
 		clk_disable_unprepare(ourhost->clk_bus[ourhost->cur_clk]);
 	clk_disable_unprepare(busclk);
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 5d068639dd3f..c251c6c0a112 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -237,6 +237,9 @@ static int sdhci_sirf_suspend(struct device *dev)
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	int ret;
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	ret = sdhci_suspend_host(host);
 	if (ret)
 		return ret;
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index 255a896769b8..8c0f88428556 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -165,6 +165,9 @@ static int sdhci_suspend(struct device *dev)
 	struct spear_sdhci *sdhci = sdhci_priv(host);
 	int ret;
 
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
+
 	ret = sdhci_suspend_host(host);
 	if (!ret)
 		clk_disable(sdhci->clk);
diff --git a/drivers/mmc/host/sdhci-st.c b/drivers/mmc/host/sdhci-st.c
index ed92ce729dde..68c36c9fa231 100644
--- a/drivers/mmc/host/sdhci-st.c
+++ b/drivers/mmc/host/sdhci-st.c
@@ -418,8 +418,6 @@ static int sdhci_st_probe(struct platform_device *pdev)
 		goto err_out;
 	}
 
-	platform_set_drvdata(pdev, host);
-
 	host_version = readw_relaxed((host->ioaddr + SDHCI_HOST_VERSION));
 
 	dev_info(&pdev->dev, "SDHCI ST Initialised: Host Version: 0x%x Vendor Version 0x%x\n",
@@ -465,8 +463,12 @@ static int sdhci_st_suspend(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct st_mmc_platform_data *pdata = sdhci_pltfm_priv(pltfm_host);
-	int ret = sdhci_suspend_host(host);
+	int ret;
+
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
 
+	ret = sdhci_suspend_host(host);
 	if (ret)
 		goto out;
 
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 20b6ff5b4af1..7f93079c7a3a 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -21,6 +21,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/reset.h>
 #include <linux/mmc/card.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
@@ -65,6 +66,8 @@ struct sdhci_tegra {
 	struct gpio_desc *power_gpio;
 	bool ddr_signaling;
 	bool pad_calib_required;
+
+	struct reset_control *rst;
 };
 
 static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
@@ -431,7 +434,23 @@ static const struct sdhci_tegra_soc_data soc_data_tegra210 = {
 	.pdata = &sdhci_tegra210_pdata,
 };
 
+static const struct sdhci_pltfm_data sdhci_tegra186_pdata = {
+	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
+		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
+		  SDHCI_QUIRK_NO_HISPD_BIT |
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.ops  = &tegra114_sdhci_ops,
+};
+
+static const struct sdhci_tegra_soc_data soc_data_tegra186 = {
+	.pdata = &sdhci_tegra186_pdata,
+};
+
 static const struct of_device_id sdhci_tegra_dt_match[] = {
+	{ .compatible = "nvidia,tegra186-sdhci", .data = &soc_data_tegra186 },
 	{ .compatible = "nvidia,tegra210-sdhci", .data = &soc_data_tegra210 },
 	{ .compatible = "nvidia,tegra124-sdhci", .data = &soc_data_tegra124 },
 	{ .compatible = "nvidia,tegra114-sdhci", .data = &soc_data_tegra114 },
@@ -489,6 +508,25 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 	clk_prepare_enable(clk);
 	pltfm_host->clk = clk;
 
+	tegra_host->rst = devm_reset_control_get(&pdev->dev, "sdhci");
+	if (IS_ERR(tegra_host->rst)) {
+		rc = PTR_ERR(tegra_host->rst);
+		dev_err(&pdev->dev, "failed to get reset control: %d\n", rc);
+		goto err_rst_get;
+	}
+
+	rc = reset_control_assert(tegra_host->rst);
+	if (rc)
+		goto err_rst_get;
+
+	usleep_range(2000, 4000);
+
+	rc = reset_control_deassert(tegra_host->rst);
+	if (rc)
+		goto err_rst_get;
+
+	usleep_range(2000, 4000);
+
 	rc = sdhci_add_host(host);
 	if (rc)
 		goto err_add_host;
@@ -496,6 +534,8 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 	return 0;
 
 err_add_host:
+	reset_control_assert(tegra_host->rst);
+err_rst_get:
 	clk_disable_unprepare(pltfm_host->clk);
 err_clk_get:
 err_power_req:
@@ -504,6 +544,23 @@ err_parse_dt:
 	return rc;
 }
 
+static int sdhci_tegra_remove(struct platform_device *pdev)
+{
+	struct sdhci_host *host = platform_get_drvdata(pdev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = sdhci_pltfm_priv(pltfm_host);
+
+	sdhci_remove_host(host, 0);
+
+	reset_control_assert(tegra_host->rst);
+	usleep_range(2000, 4000);
+	clk_disable_unprepare(pltfm_host->clk);
+
+	sdhci_pltfm_free(pdev);
+
+	return 0;
+}
+
 static struct platform_driver sdhci_tegra_driver = {
 	.driver		= {
 		.name	= "sdhci-tegra",
@@ -511,7 +568,7 @@ static struct platform_driver sdhci_tegra_driver = {
 		.pm	= &sdhci_pltfm_pmops,
 	},
 	.probe		= sdhci_tegra_probe,
-	.remove		= sdhci_pltfm_unregister,
+	.remove		= sdhci_tegra_remove,
 };
 
 module_platform_driver(sdhci_tegra_driver);
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
new file mode 100644
index 000000000000..6356781f1cca
--- /dev/null
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -0,0 +1,837 @@
+/*
+ * PHY support for Xenon SDHC
+ *
+ * Copyright (C) 2016 Marvell, All Rights Reserved.
+ *
+ * Author:	Hu Ziji <huziji@marvell.com>
+ * Date:	2016-8-24
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/ktime.h>
+#include <linux/of_address.h>
+
+#include "sdhci-pltfm.h"
+#include "sdhci-xenon.h"
+
+/* Register base for eMMC PHY 5.0 Version */
+#define XENON_EMMC_5_0_PHY_REG_BASE		0x0160
+/* Register base for eMMC PHY 5.1 Version */
+#define XENON_EMMC_PHY_REG_BASE			0x0170
+
+#define XENON_EMMC_PHY_TIMING_ADJUST		XENON_EMMC_PHY_REG_BASE
+#define XENON_EMMC_5_0_PHY_TIMING_ADJUST	XENON_EMMC_5_0_PHY_REG_BASE
+#define XENON_TIMING_ADJUST_SLOW_MODE		BIT(29)
+#define XENON_TIMING_ADJUST_SDIO_MODE		BIT(28)
+#define XENON_SAMPL_INV_QSP_PHASE_SELECT	BIT(18)
+#define XENON_SAMPL_INV_QSP_PHASE_SELECT_SHIFT	18
+#define XENON_PHY_INITIALIZAION			BIT(31)
+#define XENON_WAIT_CYCLE_BEFORE_USING_MASK	0xF
+#define XENON_WAIT_CYCLE_BEFORE_USING_SHIFT	12
+#define XENON_FC_SYNC_EN_DURATION_MASK		0xF
+#define XENON_FC_SYNC_EN_DURATION_SHIFT		8
+#define XENON_FC_SYNC_RST_EN_DURATION_MASK	0xF
+#define XENON_FC_SYNC_RST_EN_DURATION_SHIFT	4
+#define XENON_FC_SYNC_RST_DURATION_MASK		0xF
+#define XENON_FC_SYNC_RST_DURATION_SHIFT	0
+
+#define XENON_EMMC_PHY_FUNC_CONTROL		(XENON_EMMC_PHY_REG_BASE + 0x4)
+#define XENON_EMMC_5_0_PHY_FUNC_CONTROL		\
+	(XENON_EMMC_5_0_PHY_REG_BASE + 0x4)
+#define XENON_ASYNC_DDRMODE_MASK		BIT(23)
+#define XENON_ASYNC_DDRMODE_SHIFT		23
+#define XENON_CMD_DDR_MODE			BIT(16)
+#define XENON_DQ_DDR_MODE_SHIFT			8
+#define XENON_DQ_DDR_MODE_MASK			0xFF
+#define XENON_DQ_ASYNC_MODE			BIT(4)
+
+#define XENON_EMMC_PHY_PAD_CONTROL		(XENON_EMMC_PHY_REG_BASE + 0x8)
+#define XENON_EMMC_5_0_PHY_PAD_CONTROL		\
+	(XENON_EMMC_5_0_PHY_REG_BASE + 0x8)
+#define XENON_REC_EN_SHIFT			24
+#define XENON_REC_EN_MASK			0xF
+#define XENON_FC_DQ_RECEN			BIT(24)
+#define XENON_FC_CMD_RECEN			BIT(25)
+#define XENON_FC_QSP_RECEN			BIT(26)
+#define XENON_FC_QSN_RECEN			BIT(27)
+#define XENON_OEN_QSN				BIT(28)
+#define XENON_AUTO_RECEN_CTRL			BIT(30)
+#define XENON_FC_ALL_CMOS_RECEIVER		0xF000
+
+#define XENON_EMMC5_FC_QSP_PD			BIT(18)
+#define XENON_EMMC5_FC_QSP_PU			BIT(22)
+#define XENON_EMMC5_FC_CMD_PD			BIT(17)
+#define XENON_EMMC5_FC_CMD_PU			BIT(21)
+#define XENON_EMMC5_FC_DQ_PD			BIT(16)
+#define XENON_EMMC5_FC_DQ_PU			BIT(20)
+
+#define XENON_EMMC_PHY_PAD_CONTROL1		(XENON_EMMC_PHY_REG_BASE + 0xC)
+#define XENON_EMMC5_1_FC_QSP_PD			BIT(9)
+#define XENON_EMMC5_1_FC_QSP_PU			BIT(25)
+#define XENON_EMMC5_1_FC_CMD_PD			BIT(8)
+#define XENON_EMMC5_1_FC_CMD_PU			BIT(24)
+#define XENON_EMMC5_1_FC_DQ_PD			0xFF
+#define XENON_EMMC5_1_FC_DQ_PU			(0xFF << 16)
+
+#define XENON_EMMC_PHY_PAD_CONTROL2		(XENON_EMMC_PHY_REG_BASE + 0x10)
+#define XENON_EMMC_5_0_PHY_PAD_CONTROL2		\
+	(XENON_EMMC_5_0_PHY_REG_BASE + 0xC)
+#define XENON_ZNR_MASK				0x1F
+#define XENON_ZNR_SHIFT				8
+#define XENON_ZPR_MASK				0x1F
+/* Preferred ZNR and ZPR value vary between different boards.
+ * The specific ZNR and ZPR value should be defined here
+ * according to board actual timing.
+ */
+#define XENON_ZNR_DEF_VALUE			0xF
+#define XENON_ZPR_DEF_VALUE			0xF
+
+#define XENON_EMMC_PHY_DLL_CONTROL		(XENON_EMMC_PHY_REG_BASE + 0x14)
+#define XENON_EMMC_5_0_PHY_DLL_CONTROL		\
+	(XENON_EMMC_5_0_PHY_REG_BASE + 0x10)
+#define XENON_DLL_ENABLE			BIT(31)
+#define XENON_DLL_UPDATE_STROBE_5_0		BIT(30)
+#define XENON_DLL_REFCLK_SEL			BIT(30)
+#define XENON_DLL_UPDATE			BIT(23)
+#define XENON_DLL_PHSEL1_SHIFT			24
+#define XENON_DLL_PHSEL0_SHIFT			16
+#define XENON_DLL_PHASE_MASK			0x3F
+#define XENON_DLL_PHASE_90_DEGREE		0x1F
+#define XENON_DLL_FAST_LOCK			BIT(5)
+#define XENON_DLL_GAIN2X			BIT(3)
+#define XENON_DLL_BYPASS_EN			BIT(0)
+
+#define XENON_EMMC_5_0_PHY_LOGIC_TIMING_ADJUST	\
+	(XENON_EMMC_5_0_PHY_REG_BASE + 0x14)
+#define XENON_EMMC_5_0_PHY_LOGIC_TIMING_VALUE	0x5A54
+#define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST	(XENON_EMMC_PHY_REG_BASE + 0x18)
+#define XENON_LOGIC_TIMING_VALUE		0x00AA8977
+
+/*
+ * List offset of PHY registers and some special register values
+ * in eMMC PHY 5.0 or eMMC PHY 5.1
+ */
+struct xenon_emmc_phy_regs {
+	/* Offset of Timing Adjust register */
+	u16 timing_adj;
+	/* Offset of Func Control register */
+	u16 func_ctrl;
+	/* Offset of Pad Control register */
+	u16 pad_ctrl;
+	/* Offset of Pad Control register 2 */
+	u16 pad_ctrl2;
+	/* Offset of DLL Control register */
+	u16 dll_ctrl;
+	/* Offset of Logic Timing Adjust register */
+	u16 logic_timing_adj;
+	/* DLL Update Enable bit */
+	u32 dll_update;
+	/* value in Logic Timing Adjustment register */
+	u32 logic_timing_val;
+};
+
+static const char * const phy_types[] = {
+	"emmc 5.0 phy",
+	"emmc 5.1 phy"
+};
+
+enum xenon_phy_type_enum {
+	EMMC_5_0_PHY,
+	EMMC_5_1_PHY,
+	NR_PHY_TYPES
+};
+
+enum soc_pad_ctrl_type {
+	SOC_PAD_SD,
+	SOC_PAD_FIXED_1_8V,
+};
+
+struct soc_pad_ctrl {
+	/* Register address of SoC PHY PAD ctrl */
+	void __iomem	*reg;
+	/* SoC PHY PAD ctrl type */
+	enum soc_pad_ctrl_type pad_type;
+	/* SoC specific operation to set SoC PHY PAD */
+	void (*set_soc_pad)(struct sdhci_host *host,
+			    unsigned char signal_voltage);
+};
+
+static struct xenon_emmc_phy_regs xenon_emmc_5_0_phy_regs = {
+	.timing_adj	= XENON_EMMC_5_0_PHY_TIMING_ADJUST,
+	.func_ctrl	= XENON_EMMC_5_0_PHY_FUNC_CONTROL,
+	.pad_ctrl	= XENON_EMMC_5_0_PHY_PAD_CONTROL,
+	.pad_ctrl2	= XENON_EMMC_5_0_PHY_PAD_CONTROL2,
+	.dll_ctrl	= XENON_EMMC_5_0_PHY_DLL_CONTROL,
+	.logic_timing_adj = XENON_EMMC_5_0_PHY_LOGIC_TIMING_ADJUST,
+	.dll_update	= XENON_DLL_UPDATE_STROBE_5_0,
+	.logic_timing_val = XENON_EMMC_5_0_PHY_LOGIC_TIMING_VALUE,
+};
+
+static struct xenon_emmc_phy_regs xenon_emmc_5_1_phy_regs = {
+	.timing_adj	= XENON_EMMC_PHY_TIMING_ADJUST,
+	.func_ctrl	= XENON_EMMC_PHY_FUNC_CONTROL,
+	.pad_ctrl	= XENON_EMMC_PHY_PAD_CONTROL,
+	.pad_ctrl2	= XENON_EMMC_PHY_PAD_CONTROL2,
+	.dll_ctrl	= XENON_EMMC_PHY_DLL_CONTROL,
+	.logic_timing_adj = XENON_EMMC_PHY_LOGIC_TIMING_ADJUST,
+	.dll_update	= XENON_DLL_UPDATE,
+	.logic_timing_val = XENON_LOGIC_TIMING_VALUE,
+};
+
+/*
+ * eMMC PHY configuration and operations
+ */
+struct xenon_emmc_phy_params {
+	bool	slow_mode;
+
+	u8	znr;
+	u8	zpr;
+
+	/* Nr of consecutive Sampling Points of a Valid Sampling Window */
+	u8	nr_tun_times;
+	/* Divider for calculating Tuning Step */
+	u8	tun_step_divider;
+
+	struct soc_pad_ctrl pad_ctrl;
+};
+
+static int xenon_alloc_emmc_phy(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_params *params;
+
+	params = devm_kzalloc(mmc_dev(host->mmc), sizeof(*params), GFP_KERNEL);
+	if (!params)
+		return -ENOMEM;
+
+	priv->phy_params = params;
+	if (priv->phy_type == EMMC_5_0_PHY)
+		priv->emmc_phy_regs = &xenon_emmc_5_0_phy_regs;
+	else
+		priv->emmc_phy_regs = &xenon_emmc_5_1_phy_regs;
+
+	return 0;
+}
+
+/*
+ * eMMC 5.0/5.1 PHY init/re-init.
+ * eMMC PHY init should be executed after:
+ * 1. SDCLK frequency changes.
+ * 2. SDCLK is stopped and re-enabled.
+ * 3. config in emmc_phy_regs->timing_adj and emmc_phy_regs->func_ctrl
+ * are changed
+ */
+static int xenon_emmc_phy_init(struct sdhci_host *host)
+{
+	u32 reg;
+	u32 wait, clock;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
+
+	reg = sdhci_readl(host, phy_regs->timing_adj);
+	reg |= XENON_PHY_INITIALIZAION;
+	sdhci_writel(host, reg, phy_regs->timing_adj);
+
+	/* Add duration of FC_SYNC_RST */
+	wait = ((reg >> XENON_FC_SYNC_RST_DURATION_SHIFT) &
+			XENON_FC_SYNC_RST_DURATION_MASK);
+	/* Add interval between FC_SYNC_EN and FC_SYNC_RST */
+	wait += ((reg >> XENON_FC_SYNC_RST_EN_DURATION_SHIFT) &
+			XENON_FC_SYNC_RST_EN_DURATION_MASK);
+	/* Add duration of asserting FC_SYNC_EN */
+	wait += ((reg >> XENON_FC_SYNC_EN_DURATION_SHIFT) &
+			XENON_FC_SYNC_EN_DURATION_MASK);
+	/* Add duration of waiting for PHY */
+	wait += ((reg >> XENON_WAIT_CYCLE_BEFORE_USING_SHIFT) &
+			XENON_WAIT_CYCLE_BEFORE_USING_MASK);
+	/* 4 additional bus clock and 4 AXI bus clock are required */
+	wait += 8;
+	wait <<= 20;
+
+	clock = host->clock;
+	if (!clock)
+		/* Use the possibly slowest bus frequency value */
+		clock = XENON_LOWEST_SDCLK_FREQ;
+	/* get the wait time */
+	wait /= clock;
+	wait++;
+	/* wait for host eMMC PHY init completes */
+	udelay(wait);
+
+	reg = sdhci_readl(host, phy_regs->timing_adj);
+	reg &= XENON_PHY_INITIALIZAION;
+	if (reg) {
+		dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n",
+			wait);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+#define ARMADA_3700_SOC_PAD_1_8V	0x1
+#define ARMADA_3700_SOC_PAD_3_3V	0x0
+
+static void armada_3700_soc_pad_voltage_set(struct sdhci_host *host,
+					    unsigned char signal_voltage)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_params *params = priv->phy_params;
+
+	if (params->pad_ctrl.pad_type == SOC_PAD_FIXED_1_8V) {
+		writel(ARMADA_3700_SOC_PAD_1_8V, params->pad_ctrl.reg);
+	} else if (params->pad_ctrl.pad_type == SOC_PAD_SD) {
+		if (signal_voltage == MMC_SIGNAL_VOLTAGE_180)
+			writel(ARMADA_3700_SOC_PAD_1_8V, params->pad_ctrl.reg);
+		else if (signal_voltage == MMC_SIGNAL_VOLTAGE_330)
+			writel(ARMADA_3700_SOC_PAD_3_3V, params->pad_ctrl.reg);
+	}
+}
+
+/*
+ * Set SoC PHY voltage PAD control register,
+ * according to the operation voltage on PAD.
+ * The detailed operation depends on SoC implementation.
+ */
+static void xenon_emmc_phy_set_soc_pad(struct sdhci_host *host,
+				       unsigned char signal_voltage)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_params *params = priv->phy_params;
+
+	if (!params->pad_ctrl.reg)
+		return;
+
+	if (params->pad_ctrl.set_soc_pad)
+		params->pad_ctrl.set_soc_pad(host, signal_voltage);
+}
+
+/*
+ * Enable eMMC PHY HW DLL
+ * DLL should be enabled and stable before HS200/SDR104 tuning,
+ * and before HS400 data strobe setting.
+ */
+static int xenon_emmc_phy_enable_dll(struct sdhci_host *host)
+{
+	u32 reg;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
+	ktime_t timeout;
+
+	if (WARN_ON(host->clock <= MMC_HIGH_52_MAX_DTR))
+		return -EINVAL;
+
+	reg = sdhci_readl(host, phy_regs->dll_ctrl);
+	if (reg & XENON_DLL_ENABLE)
+		return 0;
+
+	/* Enable DLL */
+	reg = sdhci_readl(host, phy_regs->dll_ctrl);
+	reg |= (XENON_DLL_ENABLE | XENON_DLL_FAST_LOCK);
+
+	/*
+	 * Set Phase as 90 degree, which is most common value.
+	 * Might set another value if necessary.
+	 * The granularity is 1 degree.
+	 */
+	reg &= ~((XENON_DLL_PHASE_MASK << XENON_DLL_PHSEL0_SHIFT) |
+		 (XENON_DLL_PHASE_MASK << XENON_DLL_PHSEL1_SHIFT));
+	reg |= ((XENON_DLL_PHASE_90_DEGREE << XENON_DLL_PHSEL0_SHIFT) |
+		(XENON_DLL_PHASE_90_DEGREE << XENON_DLL_PHSEL1_SHIFT));
+
+	reg &= ~XENON_DLL_BYPASS_EN;
+	reg |= phy_regs->dll_update;
+	if (priv->phy_type == EMMC_5_1_PHY)
+		reg &= ~XENON_DLL_REFCLK_SEL;
+	sdhci_writel(host, reg, phy_regs->dll_ctrl);
+
+	/* Wait max 32 ms */
+	timeout = ktime_add_ms(ktime_get(), 32);
+	while (!(sdhci_readw(host, XENON_SLOT_EXT_PRESENT_STATE) &
+		XENON_DLL_LOCK_STATE)) {
+		if (ktime_after(ktime_get(), timeout)) {
+			dev_err(mmc_dev(host->mmc), "Wait for DLL Lock time-out\n");
+			return -ETIMEDOUT;
+		}
+		udelay(100);
+	}
+	return 0;
+}
+
+/*
+ * Config to eMMC PHY to prepare for tuning.
+ * Enable HW DLL and set the TUNING_STEP
+ */
+static int xenon_emmc_phy_config_tuning(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_params *params = priv->phy_params;
+	u32 reg, tuning_step;
+	int ret;
+
+	if (host->clock <= MMC_HIGH_52_MAX_DTR)
+		return -EINVAL;
+
+	ret = xenon_emmc_phy_enable_dll(host);
+	if (ret)
+		return ret;
+
+	/* Achieve TUNING_STEP with HW DLL help */
+	reg = sdhci_readl(host, XENON_SLOT_DLL_CUR_DLY_VAL);
+	tuning_step = reg / params->tun_step_divider;
+	if (unlikely(tuning_step > XENON_TUNING_STEP_MASK)) {
+		dev_warn(mmc_dev(host->mmc),
+			 "HS200 TUNING_STEP %d is larger than MAX value\n",
+			 tuning_step);
+		tuning_step = XENON_TUNING_STEP_MASK;
+	}
+
+	/* Set TUNING_STEP for later tuning */
+	reg = sdhci_readl(host, XENON_SLOT_OP_STATUS_CTRL);
+	reg &= ~(XENON_TUN_CONSECUTIVE_TIMES_MASK <<
+		 XENON_TUN_CONSECUTIVE_TIMES_SHIFT);
+	reg |= (params->nr_tun_times << XENON_TUN_CONSECUTIVE_TIMES_SHIFT);
+	reg &= ~(XENON_TUNING_STEP_MASK << XENON_TUNING_STEP_SHIFT);
+	reg |= (tuning_step << XENON_TUNING_STEP_SHIFT);
+	sdhci_writel(host, reg, XENON_SLOT_OP_STATUS_CTRL);
+
+	return 0;
+}
+
+static void xenon_emmc_phy_disable_data_strobe(struct sdhci_host *host)
+{
+	u32 reg;
+
+	/* Disable SDHC Data Strobe */
+	reg = sdhci_readl(host, XENON_SLOT_EMMC_CTRL);
+	reg &= ~XENON_ENABLE_DATA_STROBE;
+	sdhci_writel(host, reg, XENON_SLOT_EMMC_CTRL);
+}
+
+/* Set HS400 Data Strobe */
+static void xenon_emmc_phy_strobe_delay_adj(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 reg;
+
+	if (WARN_ON(host->timing != MMC_TIMING_MMC_HS400))
+		return;
+
+	if (host->clock <= MMC_HIGH_52_MAX_DTR)
+		return;
+
+	dev_dbg(mmc_dev(host->mmc), "starts HS400 strobe delay adjustment\n");
+
+	xenon_emmc_phy_enable_dll(host);
+
+	/* Enable SDHC Data Strobe */
+	reg = sdhci_readl(host, XENON_SLOT_EMMC_CTRL);
+	reg |= XENON_ENABLE_DATA_STROBE;
+	sdhci_writel(host, reg, XENON_SLOT_EMMC_CTRL);
+
+	/* Set Data Strobe Pull down */
+	if (priv->phy_type == EMMC_5_0_PHY) {
+		reg = sdhci_readl(host, XENON_EMMC_5_0_PHY_PAD_CONTROL);
+		reg |= XENON_EMMC5_FC_QSP_PD;
+		reg &= ~XENON_EMMC5_FC_QSP_PU;
+		sdhci_writel(host, reg, XENON_EMMC_5_0_PHY_PAD_CONTROL);
+	} else {
+		reg = sdhci_readl(host, XENON_EMMC_PHY_PAD_CONTROL1);
+		reg |= XENON_EMMC5_1_FC_QSP_PD;
+		reg &= ~XENON_EMMC5_1_FC_QSP_PU;
+		sdhci_writel(host, reg, XENON_EMMC_PHY_PAD_CONTROL1);
+	}
+}
+
+/*
+ * If eMMC PHY Slow Mode is required in lower speed mode (SDCLK < 55MHz)
+ * in SDR mode, enable Slow Mode to bypass eMMC PHY.
+ * SDIO slower SDR mode also requires Slow Mode.
+ *
+ * If Slow Mode is enabled, return true.
+ * Otherwise, return false.
+ */
+static bool xenon_emmc_phy_slow_mode(struct sdhci_host *host,
+				     unsigned char timing)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_params *params = priv->phy_params;
+	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
+	u32 reg;
+	int ret;
+
+	if (host->clock > MMC_HIGH_52_MAX_DTR)
+		return false;
+
+	reg = sdhci_readl(host, phy_regs->timing_adj);
+	/* When in slower SDR mode, enable Slow Mode for SDIO
+	 * or when Slow Mode flag is set
+	 */
+	switch (timing) {
+	case MMC_TIMING_LEGACY:
+		/*
+		 * If Slow Mode is required, enable Slow Mode by default
+		 * in early init phase to avoid any potential issue.
+		 */
+		if (params->slow_mode) {
+			reg |= XENON_TIMING_ADJUST_SLOW_MODE;
+			ret = true;
+		} else {
+			reg &= ~XENON_TIMING_ADJUST_SLOW_MODE;
+			ret = false;
+		}
+		break;
+	case MMC_TIMING_UHS_SDR25:
+	case MMC_TIMING_UHS_SDR12:
+	case MMC_TIMING_SD_HS:
+	case MMC_TIMING_MMC_HS:
+		if ((priv->init_card_type == MMC_TYPE_SDIO) ||
+		    params->slow_mode) {
+			reg |= XENON_TIMING_ADJUST_SLOW_MODE;
+			ret = true;
+			break;
+		}
+	default:
+		reg &= ~XENON_TIMING_ADJUST_SLOW_MODE;
+		ret = false;
+	}
+
+	sdhci_writel(host, reg, phy_regs->timing_adj);
+	return ret;
+}
+
+/*
+ * Set-up eMMC 5.0/5.1 PHY.
+ * Specific configuration depends on the current speed mode in use.
+ */
+static void xenon_emmc_phy_set(struct sdhci_host *host,
+			       unsigned char timing)
+{
+	u32 reg;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	struct xenon_emmc_phy_params *params = priv->phy_params;
+	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
+
+	dev_dbg(mmc_dev(host->mmc), "eMMC PHY setting starts\n");
+
+	/* Setup pad, set bit[28] and bits[26:24] */
+	reg = sdhci_readl(host, phy_regs->pad_ctrl);
+	reg |= (XENON_FC_DQ_RECEN | XENON_FC_CMD_RECEN |
+		XENON_FC_QSP_RECEN | XENON_OEN_QSN);
+	/* All FC_XX_RECEIVCE should be set as CMOS Type */
+	reg |= XENON_FC_ALL_CMOS_RECEIVER;
+	sdhci_writel(host, reg, phy_regs->pad_ctrl);
+
+	/* Set CMD and DQ Pull Up */
+	if (priv->phy_type == EMMC_5_0_PHY) {
+		reg = sdhci_readl(host, XENON_EMMC_5_0_PHY_PAD_CONTROL);
+		reg |= (XENON_EMMC5_FC_CMD_PU | XENON_EMMC5_FC_DQ_PU);
+		reg &= ~(XENON_EMMC5_FC_CMD_PD | XENON_EMMC5_FC_DQ_PD);
+		sdhci_writel(host, reg, XENON_EMMC_5_0_PHY_PAD_CONTROL);
+	} else {
+		reg = sdhci_readl(host, XENON_EMMC_PHY_PAD_CONTROL1);
+		reg |= (XENON_EMMC5_1_FC_CMD_PU | XENON_EMMC5_1_FC_DQ_PU);
+		reg &= ~(XENON_EMMC5_1_FC_CMD_PD | XENON_EMMC5_1_FC_DQ_PD);
+		sdhci_writel(host, reg, XENON_EMMC_PHY_PAD_CONTROL1);
+	}
+
+	if (timing == MMC_TIMING_LEGACY) {
+		xenon_emmc_phy_slow_mode(host, timing);
+		goto phy_init;
+	}
+
+	/*
+	 * If SDIO card, set SDIO Mode
+	 * Otherwise, clear SDIO Mode
+	 */
+	reg = sdhci_readl(host, phy_regs->timing_adj);
+	if (priv->init_card_type == MMC_TYPE_SDIO)
+		reg |= XENON_TIMING_ADJUST_SDIO_MODE;
+	else
+		reg &= ~XENON_TIMING_ADJUST_SDIO_MODE;
+	sdhci_writel(host, reg, phy_regs->timing_adj);
+
+	if (xenon_emmc_phy_slow_mode(host, timing))
+		goto phy_init;
+
+	/*
+	 * Set preferred ZNR and ZPR value
+	 * The ZNR and ZPR value vary between different boards.
+	 * Define them both in sdhci-xenon-emmc-phy.h.
+	 */
+	reg = sdhci_readl(host, phy_regs->pad_ctrl2);
+	reg &= ~((XENON_ZNR_MASK << XENON_ZNR_SHIFT) | XENON_ZPR_MASK);
+	reg |= ((params->znr << XENON_ZNR_SHIFT) | params->zpr);
+	sdhci_writel(host, reg, phy_regs->pad_ctrl2);
+
+	/*
+	 * When setting EMMC_PHY_FUNC_CONTROL register,
+	 * SD clock should be disabled
+	 */
+	reg = sdhci_readl(host, SDHCI_CLOCK_CONTROL);
+	reg &= ~SDHCI_CLOCK_CARD_EN;
+	sdhci_writew(host, reg, SDHCI_CLOCK_CONTROL);
+
+	reg = sdhci_readl(host, phy_regs->func_ctrl);
+	switch (timing) {
+	case MMC_TIMING_MMC_HS400:
+		reg |= (XENON_DQ_DDR_MODE_MASK << XENON_DQ_DDR_MODE_SHIFT) |
+		       XENON_CMD_DDR_MODE;
+		reg &= ~XENON_DQ_ASYNC_MODE;
+		break;
+	case MMC_TIMING_UHS_DDR50:
+	case MMC_TIMING_MMC_DDR52:
+		reg |= (XENON_DQ_DDR_MODE_MASK << XENON_DQ_DDR_MODE_SHIFT) |
+		       XENON_CMD_DDR_MODE | XENON_DQ_ASYNC_MODE;
+		break;
+	default:
+		reg &= ~((XENON_DQ_DDR_MODE_MASK << XENON_DQ_DDR_MODE_SHIFT) |
+			 XENON_CMD_DDR_MODE);
+		reg |= XENON_DQ_ASYNC_MODE;
+	}
+	sdhci_writel(host, reg, phy_regs->func_ctrl);
+
+	/* Enable bus clock */
+	reg = sdhci_readl(host, SDHCI_CLOCK_CONTROL);
+	reg |= SDHCI_CLOCK_CARD_EN;
+	sdhci_writew(host, reg, SDHCI_CLOCK_CONTROL);
+
+	if (timing == MMC_TIMING_MMC_HS400)
+		/* Hardware team recommend a value for HS400 */
+		sdhci_writel(host, phy_regs->logic_timing_val,
+			     phy_regs->logic_timing_adj);
+	else
+		xenon_emmc_phy_disable_data_strobe(host);
+
+phy_init:
+	xenon_emmc_phy_init(host);
+
+	dev_dbg(mmc_dev(host->mmc), "eMMC PHY setting completes\n");
+}
+
+static int get_dt_pad_ctrl_data(struct sdhci_host *host,
+				struct device_node *np,
+				struct xenon_emmc_phy_params *params)
+{
+	int ret = 0;
+	const char *name;
+	struct resource iomem;
+
+	if (of_device_is_compatible(np, "marvell,armada-3700-sdhci"))
+		params->pad_ctrl.set_soc_pad = armada_3700_soc_pad_voltage_set;
+	else
+		return 0;
+
+	if (of_address_to_resource(np, 1, &iomem)) {
+		dev_err(mmc_dev(host->mmc), "Unable to find SoC PAD ctrl register address for %s\n",
+			np->name);
+		return -EINVAL;
+	}
+
+	params->pad_ctrl.reg = devm_ioremap_resource(mmc_dev(host->mmc),
+						     &iomem);
+	if (IS_ERR(params->pad_ctrl.reg))
+		return PTR_ERR(params->pad_ctrl.reg);
+
+	ret = of_property_read_string(np, "marvell,pad-type", &name);
+	if (ret) {
+		dev_err(mmc_dev(host->mmc), "Unable to determine SoC PHY PAD ctrl type\n");
+		return ret;
+	}
+	if (!strcmp(name, "sd")) {
+		params->pad_ctrl.pad_type = SOC_PAD_SD;
+	} else if (!strcmp(name, "fixed-1-8v")) {
+		params->pad_ctrl.pad_type = SOC_PAD_FIXED_1_8V;
+	} else {
+		dev_err(mmc_dev(host->mmc), "Unsupported SoC PHY PAD ctrl type %s\n",
+			name);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static int xenon_emmc_phy_parse_param_dt(struct sdhci_host *host,
+					 struct device_node *np,
+					 struct xenon_emmc_phy_params *params)
+{
+	u32 value;
+
+	params->slow_mode = false;
+	if (of_property_read_bool(np, "marvell,xenon-phy-slow-mode"))
+		params->slow_mode = true;
+
+	params->znr = XENON_ZNR_DEF_VALUE;
+	if (!of_property_read_u32(np, "marvell,xenon-phy-znr", &value))
+		params->znr = value & XENON_ZNR_MASK;
+
+	params->zpr = XENON_ZPR_DEF_VALUE;
+	if (!of_property_read_u32(np, "marvell,xenon-phy-zpr", &value))
+		params->zpr = value & XENON_ZPR_MASK;
+
+	params->nr_tun_times = XENON_TUN_CONSECUTIVE_TIMES;
+	if (!of_property_read_u32(np, "marvell,xenon-phy-nr-success-tun",
+				  &value))
+		params->nr_tun_times = value & XENON_TUN_CONSECUTIVE_TIMES_MASK;
+
+	params->tun_step_divider = XENON_TUNING_STEP_DIVIDER;
+	if (!of_property_read_u32(np, "marvell,xenon-phy-tun-step-divider",
+				  &value))
+		params->tun_step_divider = value & 0xFF;
+
+	return get_dt_pad_ctrl_data(host, np, params);
+}
+
+/* Set SoC PHY Voltage PAD */
+void xenon_soc_pad_ctrl(struct sdhci_host *host,
+			unsigned char signal_voltage)
+{
+	xenon_emmc_phy_set_soc_pad(host, signal_voltage);
+}
+
+/*
+ * Setting PHY when card is working in High Speed Mode.
+ * HS400 set data strobe line.
+ * HS200/SDR104 set tuning config to prepare for tuning.
+ */
+static int xenon_hs_delay_adj(struct sdhci_host *host)
+{
+	int ret = 0;
+
+	if (WARN_ON(host->clock <= XENON_DEFAULT_SDCLK_FREQ))
+		return -EINVAL;
+
+	switch (host->timing) {
+	case MMC_TIMING_MMC_HS400:
+		xenon_emmc_phy_strobe_delay_adj(host);
+		return 0;
+	case MMC_TIMING_MMC_HS200:
+	case MMC_TIMING_UHS_SDR104:
+		return xenon_emmc_phy_config_tuning(host);
+	case MMC_TIMING_MMC_DDR52:
+	case MMC_TIMING_UHS_DDR50:
+		/*
+		 * DDR Mode requires driver to scan Sampling Fixed Delay Line,
+		 * to find out a perfect operation sampling point.
+		 * It is hard to implement such a scan in host driver
+		 * since initiating commands by host driver is not safe.
+		 * Thus so far just keep PHY Sampling Fixed Delay in
+		 * default value of DDR mode.
+		 *
+		 * If any timing issue occurs in DDR mode on Marvell products,
+		 * please contact maintainer for internal support in Marvell.
+		 */
+		dev_warn_once(mmc_dev(host->mmc), "Timing issue might occur in DDR mode\n");
+		return 0;
+	}
+
+	return ret;
+}
+
+/*
+ * Adjust PHY setting.
+ * PHY setting should be adjusted when SDCLK frequency, Bus Width
+ * or Speed Mode is changed.
+ * Additional config are required when card is working in High Speed mode,
+ * after leaving Legacy Mode.
+ */
+int xenon_phy_adj(struct sdhci_host *host, struct mmc_ios *ios)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	int ret = 0;
+
+	if (!host->clock) {
+		priv->clock = 0;
+		return 0;
+	}
+
+	/*
+	 * The timing, frequency or bus width is changed,
+	 * better to set eMMC PHY based on current setting
+	 * and adjust Xenon SDHC delay.
+	 */
+	if ((host->clock == priv->clock) &&
+	    (ios->bus_width == priv->bus_width) &&
+	    (ios->timing == priv->timing))
+		return 0;
+
+	xenon_emmc_phy_set(host, ios->timing);
+
+	/* Update the record */
+	priv->bus_width = ios->bus_width;
+
+	priv->timing = ios->timing;
+	priv->clock = host->clock;
+
+	/* Legacy mode is a special case */
+	if (ios->timing == MMC_TIMING_LEGACY)
+		return 0;
+
+	if (host->clock > XENON_DEFAULT_SDCLK_FREQ)
+		ret = xenon_hs_delay_adj(host);
+	return ret;
+}
+
+void xenon_clean_phy(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+
+	kfree(priv->phy_params);
+}
+
+static int xenon_add_phy(struct device_node *np, struct sdhci_host *host,
+			 const char *phy_name)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	int i, ret;
+
+	for (i = 0; i < NR_PHY_TYPES; i++) {
+		if (!strcmp(phy_name, phy_types[i])) {
+			priv->phy_type = i;
+			break;
+		}
+	}
+	if (i == NR_PHY_TYPES) {
+		dev_err(mmc_dev(host->mmc),
+			"Unable to determine PHY name %s. Use default eMMC 5.1 PHY\n",
+			phy_name);
+		priv->phy_type = EMMC_5_1_PHY;
+	}
+
+	ret = xenon_alloc_emmc_phy(host);
+	if (ret)
+		return ret;
+
+	ret = xenon_emmc_phy_parse_param_dt(host, np, priv->phy_params);
+	if (ret)
+		xenon_clean_phy(host);
+
+	return ret;
+}
+
+int xenon_phy_parse_dt(struct device_node *np, struct sdhci_host *host)
+{
+	const char *phy_type = NULL;
+
+	if (!of_property_read_string(np, "marvell,xenon-phy-type", &phy_type))
+		return xenon_add_phy(np, host, phy_type);
+
+	return xenon_add_phy(np, host, "emmc 5.1 phy");
+}
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
new file mode 100644
index 000000000000..67246655315b
--- /dev/null
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -0,0 +1,548 @@
+/*
+ * Driver for Marvell Xenon SDHC as a platform device
+ *
+ * Copyright (C) 2016 Marvell, All Rights Reserved.
+ *
+ * Author:	Hu Ziji <huziji@marvell.com>
+ * Date:	2016-8-24
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * Inspired by Jisheng Zhang <jszhang@marvell.com>
+ * Special thanks to Video BG4 project team.
+ */
+
+#include <linux/delay.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+#include "sdhci-pltfm.h"
+#include "sdhci-xenon.h"
+
+static int xenon_enable_internal_clk(struct sdhci_host *host)
+{
+	u32 reg;
+	ktime_t timeout;
+
+	reg = sdhci_readl(host, SDHCI_CLOCK_CONTROL);
+	reg |= SDHCI_CLOCK_INT_EN;
+	sdhci_writel(host, reg, SDHCI_CLOCK_CONTROL);
+	/* Wait max 20 ms */
+	timeout = ktime_add_ms(ktime_get(), 20);
+	while (!((reg = sdhci_readw(host, SDHCI_CLOCK_CONTROL))
+			& SDHCI_CLOCK_INT_STABLE)) {
+		if (ktime_after(ktime_get(), timeout)) {
+			dev_err(mmc_dev(host->mmc), "Internal clock never stabilised.\n");
+			return -ETIMEDOUT;
+		}
+		usleep_range(900, 1100);
+	}
+
+	return 0;
+}
+
+/* Set SDCLK-off-while-idle */
+static void xenon_set_sdclk_off_idle(struct sdhci_host *host,
+				     unsigned char sdhc_id, bool enable)
+{
+	u32 reg;
+	u32 mask;
+
+	reg = sdhci_readl(host, XENON_SYS_OP_CTRL);
+	/* Get the bit shift basing on the SDHC index */
+	mask = (0x1 << (XENON_SDCLK_IDLEOFF_ENABLE_SHIFT + sdhc_id));
+	if (enable)
+		reg |= mask;
+	else
+		reg &= ~mask;
+
+	sdhci_writel(host, reg, XENON_SYS_OP_CTRL);
+}
+
+/* Enable/Disable the Auto Clock Gating function */
+static void xenon_set_acg(struct sdhci_host *host, bool enable)
+{
+	u32 reg;
+
+	reg = sdhci_readl(host, XENON_SYS_OP_CTRL);
+	if (enable)
+		reg &= ~XENON_AUTO_CLKGATE_DISABLE_MASK;
+	else
+		reg |= XENON_AUTO_CLKGATE_DISABLE_MASK;
+	sdhci_writel(host, reg, XENON_SYS_OP_CTRL);
+}
+
+/* Enable this SDHC */
+static void xenon_enable_sdhc(struct sdhci_host *host,
+			      unsigned char sdhc_id)
+{
+	u32 reg;
+
+	reg = sdhci_readl(host, XENON_SYS_OP_CTRL);
+	reg |= (BIT(sdhc_id) << XENON_SLOT_ENABLE_SHIFT);
+	sdhci_writel(host, reg, XENON_SYS_OP_CTRL);
+
+	host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
+	/*
+	 * Force to clear BUS_TEST to
+	 * skip bus_test_pre and bus_test_post
+	 */
+	host->mmc->caps &= ~MMC_CAP_BUS_WIDTH_TEST;
+}
+
+/* Disable this SDHC */
+static void xenon_disable_sdhc(struct sdhci_host *host,
+			       unsigned char sdhc_id)
+{
+	u32 reg;
+
+	reg = sdhci_readl(host, XENON_SYS_OP_CTRL);
+	reg &= ~(BIT(sdhc_id) << XENON_SLOT_ENABLE_SHIFT);
+	sdhci_writel(host, reg, XENON_SYS_OP_CTRL);
+}
+
+/* Enable Parallel Transfer Mode */
+static void xenon_enable_sdhc_parallel_tran(struct sdhci_host *host,
+					    unsigned char sdhc_id)
+{
+	u32 reg;
+
+	reg = sdhci_readl(host, XENON_SYS_EXT_OP_CTRL);
+	reg |= BIT(sdhc_id);
+	sdhci_writel(host, reg, XENON_SYS_EXT_OP_CTRL);
+}
+
+/* Mask command conflict error */
+static void xenon_mask_cmd_conflict_err(struct sdhci_host *host)
+{
+	u32  reg;
+
+	reg = sdhci_readl(host, XENON_SYS_EXT_OP_CTRL);
+	reg |= XENON_MASK_CMD_CONFLICT_ERR;
+	sdhci_writel(host, reg, XENON_SYS_EXT_OP_CTRL);
+}
+
+static void xenon_retune_setup(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 reg;
+
+	/* Disable the Re-Tuning Request functionality */
+	reg = sdhci_readl(host, XENON_SLOT_RETUNING_REQ_CTRL);
+	reg &= ~XENON_RETUNING_COMPATIBLE;
+	sdhci_writel(host, reg, XENON_SLOT_RETUNING_REQ_CTRL);
+
+	/* Disable the Re-tuning Interrupt */
+	reg = sdhci_readl(host, SDHCI_SIGNAL_ENABLE);
+	reg &= ~SDHCI_INT_RETUNE;
+	sdhci_writel(host, reg, SDHCI_SIGNAL_ENABLE);
+	reg = sdhci_readl(host, SDHCI_INT_ENABLE);
+	reg &= ~SDHCI_INT_RETUNE;
+	sdhci_writel(host, reg, SDHCI_INT_ENABLE);
+
+	/* Force to use Tuning Mode 1 */
+	host->tuning_mode = SDHCI_TUNING_MODE_1;
+	/* Set re-tuning period */
+	host->tuning_count = 1 << (priv->tuning_count - 1);
+}
+
+/*
+ * Operations inside struct sdhci_ops
+ */
+/* Recover the Register Setting cleared during SOFTWARE_RESET_ALL */
+static void xenon_reset_exit(struct sdhci_host *host,
+			     unsigned char sdhc_id, u8 mask)
+{
+	/* Only SOFTWARE RESET ALL will clear the register setting */
+	if (!(mask & SDHCI_RESET_ALL))
+		return;
+
+	/* Disable tuning request and auto-retuning again */
+	xenon_retune_setup(host);
+
+	xenon_set_acg(host, true);
+
+	xenon_set_sdclk_off_idle(host, sdhc_id, false);
+
+	xenon_mask_cmd_conflict_err(host);
+}
+
+static void xenon_reset(struct sdhci_host *host, u8 mask)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+
+	sdhci_reset(host, mask);
+	xenon_reset_exit(host, priv->sdhc_id, mask);
+}
+
+/*
+ * Xenon defines different values for HS200 and HS400
+ * in Host_Control_2
+ */
+static void xenon_set_uhs_signaling(struct sdhci_host *host,
+				    unsigned int timing)
+{
+	u16 ctrl_2;
+
+	ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	/* Select Bus Speed Mode for host */
+	ctrl_2 &= ~SDHCI_CTRL_UHS_MASK;
+	if (timing == MMC_TIMING_MMC_HS200)
+		ctrl_2 |= XENON_CTRL_HS200;
+	else if (timing == MMC_TIMING_UHS_SDR104)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR104;
+	else if (timing == MMC_TIMING_UHS_SDR12)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR12;
+	else if (timing == MMC_TIMING_UHS_SDR25)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR25;
+	else if (timing == MMC_TIMING_UHS_SDR50)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR50;
+	else if ((timing == MMC_TIMING_UHS_DDR50) ||
+		 (timing == MMC_TIMING_MMC_DDR52))
+		ctrl_2 |= SDHCI_CTRL_UHS_DDR50;
+	else if (timing == MMC_TIMING_MMC_HS400)
+		ctrl_2 |= XENON_CTRL_HS400;
+	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
+}
+
+static const struct sdhci_ops sdhci_xenon_ops = {
+	.set_clock		= sdhci_set_clock,
+	.set_bus_width		= sdhci_set_bus_width,
+	.reset			= xenon_reset,
+	.set_uhs_signaling	= xenon_set_uhs_signaling,
+	.get_max_clock		= sdhci_pltfm_clk_get_max_clock,
+};
+
+static const struct sdhci_pltfm_data sdhci_xenon_pdata = {
+	.ops = &sdhci_xenon_ops,
+	.quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC |
+		  SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+};
+
+/*
+ * Xenon Specific Operations in mmc_host_ops
+ */
+static void xenon_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 reg;
+
+	/*
+	 * HS400/HS200/eMMC HS doesn't have Preset Value register.
+	 * However, sdhci_set_ios will read HS400/HS200 Preset register.
+	 * Disable Preset Value register for HS400/HS200.
+	 * eMMC HS with preset_enabled set will trigger a bug in
+	 * get_preset_value().
+	 */
+	if ((ios->timing == MMC_TIMING_MMC_HS400) ||
+	    (ios->timing == MMC_TIMING_MMC_HS200) ||
+	    (ios->timing == MMC_TIMING_MMC_HS)) {
+		host->preset_enabled = false;
+		host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN;
+		host->flags &= ~SDHCI_PV_ENABLED;
+
+		reg = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+		reg &= ~SDHCI_CTRL_PRESET_VAL_ENABLE;
+		sdhci_writew(host, reg, SDHCI_HOST_CONTROL2);
+	} else {
+		host->quirks2 &= ~SDHCI_QUIRK2_PRESET_VALUE_BROKEN;
+	}
+
+	sdhci_set_ios(mmc, ios);
+	xenon_phy_adj(host, ios);
+
+	if (host->clock > XENON_DEFAULT_SDCLK_FREQ)
+		xenon_set_sdclk_off_idle(host, priv->sdhc_id, true);
+}
+
+static int xenon_start_signal_voltage_switch(struct mmc_host *mmc,
+					     struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	/*
+	 * Before SD/SDIO set signal voltage, SD bus clock should be
+	 * disabled. However, sdhci_set_clock will also disable the Internal
+	 * clock in mmc_set_signal_voltage().
+	 * If Internal clock is disabled, the 3.3V/1.8V bit can not be updated.
+	 * Thus here manually enable internal clock.
+	 *
+	 * After switch completes, it is unnecessary to disable internal clock,
+	 * since keeping internal clock active obeys SD spec.
+	 */
+	xenon_enable_internal_clk(host);
+
+	xenon_soc_pad_ctrl(host, ios->signal_voltage);
+
+	/*
+	 * If Vqmmc is fixed on platform, vqmmc regulator should be unavailable.
+	 * Thus SDHCI_CTRL_VDD_180 bit might not work then.
+	 * Skip the standard voltage switch to avoid any issue.
+	 */
+	if (PTR_ERR(mmc->supply.vqmmc) == -ENODEV)
+		return 0;
+
+	return sdhci_start_signal_voltage_switch(mmc, ios);
+}
+
+/*
+ * Update card type.
+ * priv->init_card_type will be used in PHY timing adjustment.
+ */
+static void xenon_init_card(struct mmc_host *mmc, struct mmc_card *card)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+
+	/* Update card type*/
+	priv->init_card_type = card->type;
+}
+
+static int xenon_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	if (host->timing == MMC_TIMING_UHS_DDR50)
+		return 0;
+
+	/*
+	 * Currently force Xenon driver back to support mode 1 only,
+	 * even though Xenon might claim to support mode 2 or mode 3.
+	 * It requires more time to test mode 2/mode 3 on more platforms.
+	 */
+	if (host->tuning_mode != SDHCI_TUNING_MODE_1)
+		xenon_retune_setup(host);
+
+	return sdhci_execute_tuning(mmc, opcode);
+}
+
+static void xenon_enable_sdio_irq(struct mmc_host *mmc, int enable)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 reg;
+	u8 sdhc_id = priv->sdhc_id;
+
+	sdhci_enable_sdio_irq(mmc, enable);
+
+	if (enable) {
+		/*
+		 * Set SDIO Card Inserted indication
+		 * to enable detecting SDIO async irq.
+		 */
+		reg = sdhci_readl(host, XENON_SYS_CFG_INFO);
+		reg |= (1 << (sdhc_id + XENON_SLOT_TYPE_SDIO_SHIFT));
+		sdhci_writel(host, reg, XENON_SYS_CFG_INFO);
+	} else {
+		/* Clear SDIO Card Inserted indication */
+		reg = sdhci_readl(host, XENON_SYS_CFG_INFO);
+		reg &= ~(1 << (sdhc_id + XENON_SLOT_TYPE_SDIO_SHIFT));
+		sdhci_writel(host, reg, XENON_SYS_CFG_INFO);
+	}
+}
+
+static void xenon_replace_mmc_host_ops(struct sdhci_host *host)
+{
+	host->mmc_host_ops.set_ios = xenon_set_ios;
+	host->mmc_host_ops.start_signal_voltage_switch =
+			xenon_start_signal_voltage_switch;
+	host->mmc_host_ops.init_card = xenon_init_card;
+	host->mmc_host_ops.execute_tuning = xenon_execute_tuning;
+	host->mmc_host_ops.enable_sdio_irq = xenon_enable_sdio_irq;
+}
+
+/*
+ * Parse Xenon specific DT properties:
+ * sdhc-id: the index of current SDHC.
+ *	    Refer to XENON_SYS_CFG_INFO register
+ * tun-count: the interval between re-tuning
+ */
+static int xenon_probe_dt(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct sdhci_host *host = platform_get_drvdata(pdev);
+	struct mmc_host *mmc = host->mmc;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 sdhc_id, nr_sdhc;
+	u32 tuning_count;
+
+	/* Disable HS200 on Armada AP806 */
+	if (of_device_is_compatible(np, "marvell,armada-ap806-sdhci"))
+		host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
+
+	sdhc_id = 0x0;
+	if (!of_property_read_u32(np, "marvell,xenon-sdhc-id", &sdhc_id)) {
+		nr_sdhc = sdhci_readl(host, XENON_SYS_CFG_INFO);
+		nr_sdhc &= XENON_NR_SUPPORTED_SLOT_MASK;
+		if (unlikely(sdhc_id > nr_sdhc)) {
+			dev_err(mmc_dev(mmc), "SDHC Index %d exceeds Number of SDHCs %d\n",
+				sdhc_id, nr_sdhc);
+			return -EINVAL;
+		}
+	}
+	priv->sdhc_id = sdhc_id;
+
+	tuning_count = XENON_DEF_TUNING_COUNT;
+	if (!of_property_read_u32(np, "marvell,xenon-tun-count",
+				  &tuning_count)) {
+		if (unlikely(tuning_count >= XENON_TMR_RETUN_NO_PRESENT)) {
+			dev_err(mmc_dev(mmc), "Wrong Re-tuning Count. Set default value %d\n",
+				XENON_DEF_TUNING_COUNT);
+			tuning_count = XENON_DEF_TUNING_COUNT;
+		}
+	}
+	priv->tuning_count = tuning_count;
+
+	return xenon_phy_parse_dt(np, host);
+}
+
+static int xenon_sdhc_prepare(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u8 sdhc_id = priv->sdhc_id;
+
+	/* Enable SDHC */
+	xenon_enable_sdhc(host, sdhc_id);
+
+	/* Enable ACG */
+	xenon_set_acg(host, true);
+
+	/* Enable Parallel Transfer Mode */
+	xenon_enable_sdhc_parallel_tran(host, sdhc_id);
+
+	/* Disable SDCLK-Off-While-Idle before card init */
+	xenon_set_sdclk_off_idle(host, sdhc_id, false);
+
+	xenon_mask_cmd_conflict_err(host);
+
+	return 0;
+}
+
+static void xenon_sdhc_unprepare(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u8 sdhc_id = priv->sdhc_id;
+
+	/* disable SDHC */
+	xenon_disable_sdhc(host, sdhc_id);
+}
+
+static int xenon_probe(struct platform_device *pdev)
+{
+	struct sdhci_pltfm_host *pltfm_host;
+	struct sdhci_host *host;
+	struct xenon_priv *priv;
+	int err;
+
+	host = sdhci_pltfm_init(pdev, &sdhci_xenon_pdata,
+				sizeof(struct xenon_priv));
+	if (IS_ERR(host))
+		return PTR_ERR(host);
+
+	pltfm_host = sdhci_priv(host);
+	priv = sdhci_pltfm_priv(pltfm_host);
+
+	/*
+	 * Link Xenon specific mmc_host_ops function,
+	 * to replace standard ones in sdhci_ops.
+	 */
+	xenon_replace_mmc_host_ops(host);
+
+	pltfm_host->clk = devm_clk_get(&pdev->dev, "core");
+	if (IS_ERR(pltfm_host->clk)) {
+		err = PTR_ERR(pltfm_host->clk);
+		dev_err(&pdev->dev, "Failed to setup input clk: %d\n", err);
+		goto free_pltfm;
+	}
+	err = clk_prepare_enable(pltfm_host->clk);
+	if (err)
+		goto free_pltfm;
+
+	err = mmc_of_parse(host->mmc);
+	if (err)
+		goto err_clk;
+
+	sdhci_get_of_property(pdev);
+
+	xenon_set_acg(host, false);
+
+	/* Xenon specific dt parse */
+	err = xenon_probe_dt(pdev);
+	if (err)
+		goto err_clk;
+
+	err = xenon_sdhc_prepare(host);
+	if (err)
+		goto clean_phy_param;
+
+	err = sdhci_add_host(host);
+	if (err)
+		goto remove_sdhc;
+
+	return 0;
+
+remove_sdhc:
+	xenon_sdhc_unprepare(host);
+clean_phy_param:
+	xenon_clean_phy(host);
+err_clk:
+	clk_disable_unprepare(pltfm_host->clk);
+free_pltfm:
+	sdhci_pltfm_free(pdev);
+	return err;
+}
+
+static int xenon_remove(struct platform_device *pdev)
+{
+	struct sdhci_host *host = platform_get_drvdata(pdev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+
+	xenon_clean_phy(host);
+
+	sdhci_remove_host(host, 0);
+
+	xenon_sdhc_unprepare(host);
+
+	clk_disable_unprepare(pltfm_host->clk);
+
+	sdhci_pltfm_free(pdev);
+
+	return 0;
+}
+
+static const struct of_device_id sdhci_xenon_dt_ids[] = {
+	{ .compatible = "marvell,armada-ap806-sdhci",},
+	{ .compatible = "marvell,armada-cp110-sdhci",},
+	{ .compatible = "marvell,armada-3700-sdhci",},
+	{}
+};
+MODULE_DEVICE_TABLE(of, sdhci_xenon_dt_ids);
+
+static struct platform_driver sdhci_xenon_driver = {
+	.driver	= {
+		.name	= "xenon-sdhci",
+		.of_match_table = sdhci_xenon_dt_ids,
+		.pm = &sdhci_pltfm_pmops,
+	},
+	.probe	= xenon_probe,
+	.remove	= xenon_remove,
+};
+
+module_platform_driver(sdhci_xenon_driver);
+
+MODULE_DESCRIPTION("SDHCI platform driver for Marvell Xenon SDHC");
+MODULE_AUTHOR("Hu Ziji <huziji@marvell.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h
new file mode 100644
index 000000000000..6e6523ea01ce
--- /dev/null
+++ b/drivers/mmc/host/sdhci-xenon.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2016 Marvell, All Rights Reserved.
+ *
+ * Author:	Hu Ziji <huziji@marvell.com>
+ * Date:	2016-8-24
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ */
+#ifndef SDHCI_XENON_H_
+#define SDHCI_XENON_H_
+
+/* Register Offset of Xenon SDHC self-defined register */
+#define XENON_SYS_CFG_INFO			0x0104
+#define XENON_SLOT_TYPE_SDIO_SHIFT		24
+#define XENON_NR_SUPPORTED_SLOT_MASK		0x7
+
+#define XENON_SYS_OP_CTRL			0x0108
+#define XENON_AUTO_CLKGATE_DISABLE_MASK		BIT(20)
+#define XENON_SDCLK_IDLEOFF_ENABLE_SHIFT	8
+#define XENON_SLOT_ENABLE_SHIFT			0
+
+#define XENON_SYS_EXT_OP_CTRL			0x010C
+#define XENON_MASK_CMD_CONFLICT_ERR		BIT(8)
+
+#define XENON_SLOT_OP_STATUS_CTRL		0x0128
+#define XENON_TUN_CONSECUTIVE_TIMES_SHIFT	16
+#define XENON_TUN_CONSECUTIVE_TIMES_MASK	0x7
+#define XENON_TUN_CONSECUTIVE_TIMES		0x4
+#define XENON_TUNING_STEP_SHIFT			12
+#define XENON_TUNING_STEP_MASK			0xF
+#define XENON_TUNING_STEP_DIVIDER		BIT(6)
+
+#define XENON_SLOT_EMMC_CTRL			0x0130
+#define XENON_ENABLE_DATA_STROBE		BIT(24)
+
+#define XENON_SLOT_RETUNING_REQ_CTRL		0x0144
+/* retuning compatible */
+#define XENON_RETUNING_COMPATIBLE		0x1
+
+#define XENON_SLOT_EXT_PRESENT_STATE		0x014C
+#define XENON_DLL_LOCK_STATE			0x1
+
+#define XENON_SLOT_DLL_CUR_DLY_VAL		0x0150
+
+/* Tuning Parameter */
+#define XENON_TMR_RETUN_NO_PRESENT		0xF
+#define XENON_DEF_TUNING_COUNT			0x9
+
+#define XENON_DEFAULT_SDCLK_FREQ		400000
+#define XENON_LOWEST_SDCLK_FREQ			100000
+
+/* Xenon specific Mode Select value */
+#define XENON_CTRL_HS200			0x5
+#define XENON_CTRL_HS400			0x6
+
+struct xenon_priv {
+	unsigned char	tuning_count;
+	/* idx of SDHC */
+	u8		sdhc_id;
+
+	/*
+	 * eMMC/SD/SDIO require different register settings.
+	 * Xenon driver has to recognize card type
+	 * before mmc_host->card is not available.
+	 * This field records the card type during init.
+	 * It is updated in xenon_init_card().
+	 *
+	 * It is only valid during initialization after it is updated.
+	 * Do not access this variable in normal transfers after
+	 * initialization completes.
+	 */
+	unsigned int	init_card_type;
+
+	/*
+	 * The bus_width, timing, and clock fields in below
+	 * record the current ios setting of Xenon SDHC.
+	 * Driver will adjust PHY setting if any change to
+	 * ios affects PHY timing.
+	 */
+	unsigned char	bus_width;
+	unsigned char	timing;
+	unsigned int	clock;
+
+	int		phy_type;
+	/*
+	 * Contains board-specific PHY parameters
+	 * passed from device tree.
+	 */
+	void		*phy_params;
+	struct xenon_emmc_phy_regs *emmc_phy_regs;
+};
+
+int xenon_phy_adj(struct sdhci_host *host, struct mmc_ios *ios);
+void xenon_clean_phy(struct sdhci_host *host);
+int xenon_phy_parse_dt(struct device_node *np,
+		       struct sdhci_host *host);
+void xenon_soc_pad_ctrl(struct sdhci_host *host,
+			unsigned char signal_voltage);
+#endif
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 6fdd7a70f229..ecd0d4350e8a 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/ktime.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
 #include <linux/module.h>
@@ -37,7 +38,10 @@
 #define DRIVER_NAME "sdhci"
 
 #define DBG(f, x...) \
-	pr_debug(DRIVER_NAME " [%s()]: " f, __func__,## x)
+	pr_debug("%s: " DRIVER_NAME ": " f, mmc_hostname(host->mmc), ## x)
+
+#define SDHCI_DUMP(f, x...) \
+	pr_err("%s: " DRIVER_NAME ": " f, mmc_hostname(host->mmc), ## x)
 
 #define MAX_TUNING_LOOP 40
 
@@ -48,61 +52,68 @@ static void sdhci_finish_data(struct sdhci_host *);
 
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable);
 
-static void sdhci_dumpregs(struct sdhci_host *host)
-{
-	pr_err(DRIVER_NAME ": =========== REGISTER DUMP (%s)===========\n",
-	       mmc_hostname(host->mmc));
-
-	pr_err(DRIVER_NAME ": Sys addr: 0x%08x | Version:  0x%08x\n",
-	       sdhci_readl(host, SDHCI_DMA_ADDRESS),
-	       sdhci_readw(host, SDHCI_HOST_VERSION));
-	pr_err(DRIVER_NAME ": Blk size: 0x%08x | Blk cnt:  0x%08x\n",
-	       sdhci_readw(host, SDHCI_BLOCK_SIZE),
-	       sdhci_readw(host, SDHCI_BLOCK_COUNT));
-	pr_err(DRIVER_NAME ": Argument: 0x%08x | Trn mode: 0x%08x\n",
-	       sdhci_readl(host, SDHCI_ARGUMENT),
-	       sdhci_readw(host, SDHCI_TRANSFER_MODE));
-	pr_err(DRIVER_NAME ": Present:  0x%08x | Host ctl: 0x%08x\n",
-	       sdhci_readl(host, SDHCI_PRESENT_STATE),
-	       sdhci_readb(host, SDHCI_HOST_CONTROL));
-	pr_err(DRIVER_NAME ": Power:    0x%08x | Blk gap:  0x%08x\n",
-	       sdhci_readb(host, SDHCI_POWER_CONTROL),
-	       sdhci_readb(host, SDHCI_BLOCK_GAP_CONTROL));
-	pr_err(DRIVER_NAME ": Wake-up:  0x%08x | Clock:    0x%08x\n",
-	       sdhci_readb(host, SDHCI_WAKE_UP_CONTROL),
-	       sdhci_readw(host, SDHCI_CLOCK_CONTROL));
-	pr_err(DRIVER_NAME ": Timeout:  0x%08x | Int stat: 0x%08x\n",
-	       sdhci_readb(host, SDHCI_TIMEOUT_CONTROL),
-	       sdhci_readl(host, SDHCI_INT_STATUS));
-	pr_err(DRIVER_NAME ": Int enab: 0x%08x | Sig enab: 0x%08x\n",
-	       sdhci_readl(host, SDHCI_INT_ENABLE),
-	       sdhci_readl(host, SDHCI_SIGNAL_ENABLE));
-	pr_err(DRIVER_NAME ": AC12 err: 0x%08x | Slot int: 0x%08x\n",
-	       sdhci_readw(host, SDHCI_ACMD12_ERR),
-	       sdhci_readw(host, SDHCI_SLOT_INT_STATUS));
-	pr_err(DRIVER_NAME ": Caps:     0x%08x | Caps_1:   0x%08x\n",
-	       sdhci_readl(host, SDHCI_CAPABILITIES),
-	       sdhci_readl(host, SDHCI_CAPABILITIES_1));
-	pr_err(DRIVER_NAME ": Cmd:      0x%08x | Max curr: 0x%08x\n",
-	       sdhci_readw(host, SDHCI_COMMAND),
-	       sdhci_readl(host, SDHCI_MAX_CURRENT));
-	pr_err(DRIVER_NAME ": Host ctl2: 0x%08x\n",
-	       sdhci_readw(host, SDHCI_HOST_CONTROL2));
+void sdhci_dumpregs(struct sdhci_host *host)
+{
+	SDHCI_DUMP("============ SDHCI REGISTER DUMP ===========\n");
+
+	SDHCI_DUMP("Sys addr:  0x%08x | Version:  0x%08x\n",
+		   sdhci_readl(host, SDHCI_DMA_ADDRESS),
+		   sdhci_readw(host, SDHCI_HOST_VERSION));
+	SDHCI_DUMP("Blk size:  0x%08x | Blk cnt:  0x%08x\n",
+		   sdhci_readw(host, SDHCI_BLOCK_SIZE),
+		   sdhci_readw(host, SDHCI_BLOCK_COUNT));
+	SDHCI_DUMP("Argument:  0x%08x | Trn mode: 0x%08x\n",
+		   sdhci_readl(host, SDHCI_ARGUMENT),
+		   sdhci_readw(host, SDHCI_TRANSFER_MODE));
+	SDHCI_DUMP("Present:   0x%08x | Host ctl: 0x%08x\n",
+		   sdhci_readl(host, SDHCI_PRESENT_STATE),
+		   sdhci_readb(host, SDHCI_HOST_CONTROL));
+	SDHCI_DUMP("Power:     0x%08x | Blk gap:  0x%08x\n",
+		   sdhci_readb(host, SDHCI_POWER_CONTROL),
+		   sdhci_readb(host, SDHCI_BLOCK_GAP_CONTROL));
+	SDHCI_DUMP("Wake-up:   0x%08x | Clock:    0x%08x\n",
+		   sdhci_readb(host, SDHCI_WAKE_UP_CONTROL),
+		   sdhci_readw(host, SDHCI_CLOCK_CONTROL));
+	SDHCI_DUMP("Timeout:   0x%08x | Int stat: 0x%08x\n",
+		   sdhci_readb(host, SDHCI_TIMEOUT_CONTROL),
+		   sdhci_readl(host, SDHCI_INT_STATUS));
+	SDHCI_DUMP("Int enab:  0x%08x | Sig enab: 0x%08x\n",
+		   sdhci_readl(host, SDHCI_INT_ENABLE),
+		   sdhci_readl(host, SDHCI_SIGNAL_ENABLE));
+	SDHCI_DUMP("AC12 err:  0x%08x | Slot int: 0x%08x\n",
+		   sdhci_readw(host, SDHCI_ACMD12_ERR),
+		   sdhci_readw(host, SDHCI_SLOT_INT_STATUS));
+	SDHCI_DUMP("Caps:      0x%08x | Caps_1:   0x%08x\n",
+		   sdhci_readl(host, SDHCI_CAPABILITIES),
+		   sdhci_readl(host, SDHCI_CAPABILITIES_1));
+	SDHCI_DUMP("Cmd:       0x%08x | Max curr: 0x%08x\n",
+		   sdhci_readw(host, SDHCI_COMMAND),
+		   sdhci_readl(host, SDHCI_MAX_CURRENT));
+	SDHCI_DUMP("Resp[0]:   0x%08x | Resp[1]:  0x%08x\n",
+		   sdhci_readl(host, SDHCI_RESPONSE),
+		   sdhci_readl(host, SDHCI_RESPONSE + 4));
+	SDHCI_DUMP("Resp[2]:   0x%08x | Resp[3]:  0x%08x\n",
+		   sdhci_readl(host, SDHCI_RESPONSE + 8),
+		   sdhci_readl(host, SDHCI_RESPONSE + 12));
+	SDHCI_DUMP("Host ctl2: 0x%08x\n",
+		   sdhci_readw(host, SDHCI_HOST_CONTROL2));
 
 	if (host->flags & SDHCI_USE_ADMA) {
-		if (host->flags & SDHCI_USE_64_BIT_DMA)
-			pr_err(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x%08x\n",
-			       readl(host->ioaddr + SDHCI_ADMA_ERROR),
-			       readl(host->ioaddr + SDHCI_ADMA_ADDRESS_HI),
-			       readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
-		else
-			pr_err(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x\n",
-			       readl(host->ioaddr + SDHCI_ADMA_ERROR),
-			       readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
+		if (host->flags & SDHCI_USE_64_BIT_DMA) {
+			SDHCI_DUMP("ADMA Err:  0x%08x | ADMA Ptr: 0x%08x%08x\n",
+				   sdhci_readl(host, SDHCI_ADMA_ERROR),
+				   sdhci_readl(host, SDHCI_ADMA_ADDRESS_HI),
+				   sdhci_readl(host, SDHCI_ADMA_ADDRESS));
+		} else {
+			SDHCI_DUMP("ADMA Err:  0x%08x | ADMA Ptr: 0x%08x\n",
+				   sdhci_readl(host, SDHCI_ADMA_ERROR),
+				   sdhci_readl(host, SDHCI_ADMA_ADDRESS));
+		}
 	}
 
-	pr_err(DRIVER_NAME ": ===========================================\n");
+	SDHCI_DUMP("============================================\n");
 }
+EXPORT_SYMBOL_GPL(sdhci_dumpregs);
 
 /*****************************************************************************\
  *                                                                           *
@@ -165,7 +176,7 @@ static void sdhci_runtime_pm_bus_off(struct sdhci_host *host)
 
 void sdhci_reset(struct sdhci_host *host, u8 mask)
 {
-	unsigned long timeout;
+	ktime_t timeout;
 
 	sdhci_writeb(host, mask, SDHCI_SOFTWARE_RESET);
 
@@ -177,18 +188,17 @@ void sdhci_reset(struct sdhci_host *host, u8 mask)
 	}
 
 	/* Wait max 100 ms */
-	timeout = 100;
+	timeout = ktime_add_ms(ktime_get(), 100);
 
 	/* hw clears the bit when it's done */
 	while (sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask) {
-		if (timeout == 0) {
+		if (ktime_after(ktime_get(), timeout)) {
 			pr_err("%s: Reset 0x%x never completed.\n",
 				mmc_hostname(host->mmc), (int)mask);
 			sdhci_dumpregs(host);
 			return;
 		}
-		timeout--;
-		mdelay(1);
+		udelay(10);
 	}
 }
 EXPORT_SYMBOL_GPL(sdhci_reset);
@@ -215,15 +225,8 @@ static void sdhci_do_reset(struct sdhci_host *host, u8 mask)
 	}
 }
 
-static void sdhci_init(struct sdhci_host *host, int soft)
+static void sdhci_set_default_irqs(struct sdhci_host *host)
 {
-	struct mmc_host *mmc = host->mmc;
-
-	if (soft)
-		sdhci_do_reset(host, SDHCI_RESET_CMD|SDHCI_RESET_DATA);
-	else
-		sdhci_do_reset(host, SDHCI_RESET_ALL);
-
 	host->ier = SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT |
 		    SDHCI_INT_DATA_CRC | SDHCI_INT_DATA_TIMEOUT |
 		    SDHCI_INT_INDEX | SDHCI_INT_END_BIT | SDHCI_INT_CRC |
@@ -236,6 +239,20 @@ static void sdhci_init(struct sdhci_host *host, int soft)
 
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+}
+
+static void sdhci_init(struct sdhci_host *host, int soft)
+{
+	struct mmc_host *mmc = host->mmc;
+
+	if (soft)
+		sdhci_do_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
+	else
+		sdhci_do_reset(host, SDHCI_RESET_ALL);
+
+	sdhci_set_default_irqs(host);
+
+	host->cqe_on = false;
 
 	if (soft) {
 		/* force clock reconfiguration */
@@ -485,8 +502,7 @@ static int sdhci_pre_dma_transfer(struct sdhci_host *host,
 		return data->sg_count;
 
 	sg_count = dma_map_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-				data->flags & MMC_DATA_WRITE ?
-				DMA_TO_DEVICE : DMA_FROM_DEVICE);
+			      mmc_get_dma_dir(data));
 
 	if (sg_count == 0)
 		return -ENOSPC;
@@ -715,8 +731,8 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 	}
 
 	if (count >= 0xF) {
-		DBG("%s: Too large timeout 0x%x requested for CMD%d!\n",
-		    mmc_hostname(host->mmc), count, cmd->opcode);
+		DBG("Too large timeout 0x%x requested for CMD%d!\n",
+		    count, cmd->opcode);
 		count = 0xE;
 	}
 
@@ -1346,23 +1362,22 @@ EXPORT_SYMBOL_GPL(sdhci_calc_clk);
 
 void sdhci_enable_clk(struct sdhci_host *host, u16 clk)
 {
-	unsigned long timeout;
+	ktime_t timeout;
 
 	clk |= SDHCI_CLOCK_INT_EN;
 	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 
 	/* Wait max 20 ms */
-	timeout = 20;
+	timeout = ktime_add_ms(ktime_get(), 20);
 	while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL))
 		& SDHCI_CLOCK_INT_STABLE)) {
-		if (timeout == 0) {
+		if (ktime_after(ktime_get(), timeout)) {
 			pr_err("%s: Internal clock never stabilised.\n",
 			       mmc_hostname(host->mmc));
 			sdhci_dumpregs(host);
 			return;
 		}
-		timeout--;
-		mdelay(1);
+		udelay(10);
 	}
 
 	clk |= SDHCI_CLOCK_CARD_EN;
@@ -1391,9 +1406,7 @@ static void sdhci_set_power_reg(struct sdhci_host *host, unsigned char mode,
 {
 	struct mmc_host *mmc = host->mmc;
 
-	spin_unlock_irq(&host->lock);
 	mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
-	spin_lock_irq(&host->lock);
 
 	if (mode != MMC_POWER_OFF)
 		sdhci_writeb(host, SDHCI_POWER_ON, SDHCI_POWER_CONTROL);
@@ -1570,19 +1583,15 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 }
 EXPORT_SYMBOL_GPL(sdhci_set_uhs_signaling);
 
-static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
-	unsigned long flags;
 	u8 ctrl;
 
 	if (ios->power_mode == MMC_POWER_UNDEFINED)
 		return;
 
-	spin_lock_irqsave(&host->lock, flags);
-
 	if (host->flags & SDHCI_DEVICE_DEAD) {
-		spin_unlock_irqrestore(&host->lock, flags);
 		if (!IS_ERR(mmc->supply.vmmc) &&
 		    ios->power_mode == MMC_POWER_OFF)
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
@@ -1728,8 +1737,8 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		sdhci_do_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
 
 	mmiowb();
-	spin_unlock_irqrestore(&host->lock, flags);
 }
+EXPORT_SYMBOL_GPL(sdhci_set_ios);
 
 static int sdhci_get_cd(struct mmc_host *mmc)
 {
@@ -1823,11 +1832,14 @@ static void sdhci_enable_sdio_irq_nolock(struct sdhci_host *host, int enable)
 	}
 }
 
-static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
+void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	unsigned long flags;
 
+	if (enable)
+		pm_runtime_get_noresume(host->mmc->parent);
+
 	spin_lock_irqsave(&host->lock, flags);
 	if (enable)
 		host->flags |= SDHCI_SDIO_IRQ_ENABLED;
@@ -1836,10 +1848,14 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 
 	sdhci_enable_sdio_irq_nolock(host, enable);
 	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (!enable)
+		pm_runtime_put_noidle(host->mmc->parent);
 }
+EXPORT_SYMBOL_GPL(sdhci_enable_sdio_irq);
 
-static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
-					     struct mmc_ios *ios)
+int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
+				      struct mmc_ios *ios)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	u16 ctrl;
@@ -1931,6 +1947,7 @@ static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 		return 0;
 	}
 }
+EXPORT_SYMBOL_GPL(sdhci_start_signal_voltage_switch);
 
 static int sdhci_card_busy(struct mmc_host *mmc)
 {
@@ -1995,8 +2012,7 @@ static void sdhci_reset_tuning(struct sdhci_host *host)
 	sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
 }
 
-static void sdhci_abort_tuning(struct sdhci_host *host, u32 opcode,
-			       unsigned long flags)
+static void sdhci_abort_tuning(struct sdhci_host *host, u32 opcode)
 {
 	sdhci_reset_tuning(host);
 
@@ -2005,9 +2021,7 @@ static void sdhci_abort_tuning(struct sdhci_host *host, u32 opcode,
 
 	sdhci_end_tuning(host);
 
-	spin_unlock_irqrestore(&host->lock, flags);
 	mmc_abort_tuning(host->mmc, opcode);
-	spin_lock_irqsave(&host->lock, flags);
 }
 
 /*
@@ -2017,12 +2031,14 @@ static void sdhci_abort_tuning(struct sdhci_host *host, u32 opcode,
  * interrupt setup is different to other commands and there is no timeout
  * interrupt so special handling is needed.
  */
-static void sdhci_send_tuning(struct sdhci_host *host, u32 opcode,
-			      unsigned long flags)
+static void sdhci_send_tuning(struct sdhci_host *host, u32 opcode)
 {
 	struct mmc_host *mmc = host->mmc;
 	struct mmc_command cmd = {};
 	struct mmc_request mrq = {};
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
 
 	cmd.opcode = opcode;
 	cmd.flags = MMC_RSP_R1 | MMC_CMD_ADTC;
@@ -2056,17 +2072,16 @@ static void sdhci_send_tuning(struct sdhci_host *host, u32 opcode,
 
 	host->tuning_done = 0;
 
+	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	/* Wait for Buffer Read Ready interrupt */
 	wait_event_timeout(host->buf_ready_int, (host->tuning_done == 1),
 			   msecs_to_jiffies(50));
 
-	spin_lock_irqsave(&host->lock, flags);
 }
 
-static void __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode,
-				   unsigned long flags)
+static void __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int i;
 
@@ -2077,12 +2092,12 @@ static void __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode,
 	for (i = 0; i < MAX_TUNING_LOOP; i++) {
 		u16 ctrl;
 
-		sdhci_send_tuning(host, opcode, flags);
+		sdhci_send_tuning(host, opcode);
 
 		if (!host->tuning_done) {
 			pr_info("%s: Tuning timeout, falling back to fixed sampling clock\n",
 				mmc_hostname(host->mmc));
-			sdhci_abort_tuning(host, opcode, flags);
+			sdhci_abort_tuning(host, opcode);
 			return;
 		}
 
@@ -2093,9 +2108,9 @@ static void __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode,
 			break;
 		}
 
-		/* eMMC spec does not require a delay between tuning cycles */
-		if (opcode == MMC_SEND_TUNING_BLOCK)
-			mdelay(1);
+		/* Spec does not require a delay between tuning cycles */
+		if (host->tuning_delay > 0)
+			mdelay(host->tuning_delay);
 	}
 
 	pr_info("%s: Tuning failed, falling back to fixed sampling clock\n",
@@ -2107,12 +2122,9 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	int err = 0;
-	unsigned long flags;
 	unsigned int tuning_count = 0;
 	bool hs400_tuning;
 
-	spin_lock_irqsave(&host->lock, flags);
-
 	hs400_tuning = host->flags & SDHCI_HS400_TUNING;
 
 	if (host->tuning_mode == SDHCI_TUNING_MODE_1)
@@ -2129,7 +2141,7 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	/* HS400 tuning is done in HS200 mode */
 	case MMC_TIMING_MMC_HS400:
 		err = -EINVAL;
-		goto out_unlock;
+		goto out;
 
 	case MMC_TIMING_MMC_HS200:
 		/*
@@ -2150,44 +2162,31 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		/* FALLTHROUGH */
 
 	default:
-		goto out_unlock;
+		goto out;
 	}
 
 	if (host->ops->platform_execute_tuning) {
-		spin_unlock_irqrestore(&host->lock, flags);
 		err = host->ops->platform_execute_tuning(host, opcode);
-		spin_lock_irqsave(&host->lock, flags);
-		goto out_unlock;
+		goto out;
 	}
 
 	host->mmc->retune_period = tuning_count;
 
+	if (host->tuning_delay < 0)
+		host->tuning_delay = opcode == MMC_SEND_TUNING_BLOCK;
+
 	sdhci_start_tuning(host);
 
-	__sdhci_execute_tuning(host, opcode, flags);
+	__sdhci_execute_tuning(host, opcode);
 
 	sdhci_end_tuning(host);
-out_unlock:
+out:
 	host->flags &= ~SDHCI_HS400_TUNING;
-	spin_unlock_irqrestore(&host->lock, flags);
 
 	return err;
 }
 EXPORT_SYMBOL_GPL(sdhci_execute_tuning);
 
-static int sdhci_select_drive_strength(struct mmc_card *card,
-				       unsigned int max_dtr, int host_drv,
-				       int card_drv, int *drv_type)
-{
-	struct sdhci_host *host = mmc_priv(card->host);
-
-	if (!host->ops->select_drive_strength)
-		return 0;
-
-	return host->ops->select_drive_strength(host, card, max_dtr, host_drv,
-						card_drv, drv_type);
-}
-
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable)
 {
 	/* Host Controller v3.00 defines preset value registers */
@@ -2225,8 +2224,7 @@ static void sdhci_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
 
 	if (data->host_cookie != COOKIE_UNMAPPED)
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-			     data->flags & MMC_DATA_WRITE ?
-			       DMA_TO_DEVICE : DMA_FROM_DEVICE);
+			     mmc_get_dma_dir(data));
 
 	data->host_cookie = COOKIE_UNMAPPED;
 }
@@ -2301,7 +2299,6 @@ static const struct mmc_host_ops sdhci_ops = {
 	.start_signal_voltage_switch	= sdhci_start_signal_voltage_switch,
 	.prepare_hs400_tuning		= sdhci_prepare_hs400_tuning,
 	.execute_tuning			= sdhci_execute_tuning,
-	.select_drive_strength		= sdhci_select_drive_strength,
 	.card_event			= sdhci_card_event,
 	.card_busy	= sdhci_card_busy,
 };
@@ -2343,8 +2340,7 @@ static bool sdhci_request_done(struct sdhci_host *host)
 
 		if (data && data->host_cookie == COOKIE_MAPPED) {
 			dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-				     (data->flags & MMC_DATA_READ) ?
-				     DMA_FROM_DEVICE : DMA_TO_DEVICE);
+				     mmc_get_dma_dir(data));
 			data->host_cookie = COOKIE_UNMAPPED;
 		}
 	}
@@ -2509,7 +2505,6 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
 #ifdef CONFIG_MMC_DEBUG
 static void sdhci_adma_show_error(struct sdhci_host *host)
 {
-	const char *name = mmc_hostname(host->mmc);
 	void *desc = host->adma_table;
 
 	sdhci_dumpregs(host);
@@ -2518,14 +2513,14 @@ static void sdhci_adma_show_error(struct sdhci_host *host)
 		struct sdhci_adma2_64_desc *dma_desc = desc;
 
 		if (host->flags & SDHCI_USE_64_BIT_DMA)
-			DBG("%s: %p: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
-			    name, desc, le32_to_cpu(dma_desc->addr_hi),
+			DBG("%p: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    desc, le32_to_cpu(dma_desc->addr_hi),
 			    le32_to_cpu(dma_desc->addr_lo),
 			    le16_to_cpu(dma_desc->len),
 			    le16_to_cpu(dma_desc->cmd));
 		else
-			DBG("%s: %p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
-			    name, desc, le32_to_cpu(dma_desc->addr_lo),
+			DBG("%p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    desc, le32_to_cpu(dma_desc->addr_lo),
 			    le16_to_cpu(dma_desc->len),
 			    le16_to_cpu(dma_desc->cmd));
 
@@ -2641,10 +2636,8 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 				~(SDHCI_DEFAULT_BOUNDARY_SIZE - 1)) +
 				SDHCI_DEFAULT_BOUNDARY_SIZE;
 			host->data->bytes_xfered = dmanow - dmastart;
-			DBG("%s: DMA base 0x%08x, transferred 0x%06x bytes,"
-				" next 0x%08x\n",
-				mmc_hostname(host->mmc), dmastart,
-				host->data->bytes_xfered, dmanow);
+			DBG("DMA base 0x%08x, transferred 0x%06x bytes, next 0x%08x\n",
+			    dmastart, host->data->bytes_xfered, dmanow);
 			sdhci_writel(host, dmanow, SDHCI_DMA_ADDRESS);
 		}
 
@@ -2684,14 +2677,19 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 	}
 
 	do {
+		DBG("IRQ status 0x%08x\n", intmask);
+
+		if (host->ops->irq) {
+			intmask = host->ops->irq(host, intmask);
+			if (!intmask)
+				goto cont;
+		}
+
 		/* Clear selected interrupts. */
 		mask = intmask & (SDHCI_INT_CMD_MASK | SDHCI_INT_DATA_MASK |
 				  SDHCI_INT_BUS_POWER);
 		sdhci_writel(host, mask, SDHCI_INT_STATUS);
 
-		DBG("*** %s got interrupt: 0x%08x\n",
-			mmc_hostname(host->mmc), intmask);
-
 		if (intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) {
 			u32 present = sdhci_readl(host, SDHCI_PRESENT_STATE) &
 				      SDHCI_CARD_PRESENT;
@@ -2751,7 +2749,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 			unexpected |= intmask;
 			sdhci_writel(host, intmask, SDHCI_INT_STATUS);
 		}
-
+cont:
 		if (result == IRQ_NONE)
 			result = IRQ_HANDLED;
 
@@ -2850,8 +2848,6 @@ int sdhci_suspend_host(struct sdhci_host *host)
 	sdhci_disable_card_detection(host);
 
 	mmc_retune_timer_stop(host->mmc);
-	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
-		mmc_retune_needed(host->mmc);
 
 	if (!device_may_wakeup(mmc_dev(host->mmc))) {
 		host->ier = 0;
@@ -2912,8 +2908,6 @@ int sdhci_runtime_suspend_host(struct sdhci_host *host)
 	unsigned long flags;
 
 	mmc_retune_timer_stop(host->mmc);
-	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
-		mmc_retune_needed(host->mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 	host->ier &= SDHCI_INT_CARD_INT;
@@ -2984,6 +2978,119 @@ EXPORT_SYMBOL_GPL(sdhci_runtime_resume_host);
 
 /*****************************************************************************\
  *                                                                           *
+ * Command Queue Engine (CQE) helpers                                        *
+ *                                                                           *
+\*****************************************************************************/
+
+void sdhci_cqe_enable(struct mmc_host *mmc)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	u8 ctrl;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
+	ctrl &= ~SDHCI_CTRL_DMA_MASK;
+	if (host->flags & SDHCI_USE_64_BIT_DMA)
+		ctrl |= SDHCI_CTRL_ADMA64;
+	else
+		ctrl |= SDHCI_CTRL_ADMA32;
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
+
+	sdhci_writew(host, SDHCI_MAKE_BLKSZ(SDHCI_DEFAULT_BOUNDARY_ARG, 512),
+		     SDHCI_BLOCK_SIZE);
+
+	/* Set maximum timeout */
+	sdhci_writeb(host, 0xE, SDHCI_TIMEOUT_CONTROL);
+
+	host->ier = host->cqe_ier;
+
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+
+	host->cqe_on = true;
+
+	pr_debug("%s: sdhci: CQE on, IRQ mask %#x, IRQ status %#x\n",
+		 mmc_hostname(mmc), host->ier,
+		 sdhci_readl(host, SDHCI_INT_STATUS));
+
+	mmiowb();
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+EXPORT_SYMBOL_GPL(sdhci_cqe_enable);
+
+void sdhci_cqe_disable(struct mmc_host *mmc, bool recovery)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	sdhci_set_default_irqs(host);
+
+	host->cqe_on = false;
+
+	if (recovery) {
+		sdhci_do_reset(host, SDHCI_RESET_CMD);
+		sdhci_do_reset(host, SDHCI_RESET_DATA);
+	}
+
+	pr_debug("%s: sdhci: CQE off, IRQ mask %#x, IRQ status %#x\n",
+		 mmc_hostname(mmc), host->ier,
+		 sdhci_readl(host, SDHCI_INT_STATUS));
+
+	mmiowb();
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+EXPORT_SYMBOL_GPL(sdhci_cqe_disable);
+
+bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error,
+		   int *data_error)
+{
+	u32 mask;
+
+	if (!host->cqe_on)
+		return false;
+
+	if (intmask & (SDHCI_INT_INDEX | SDHCI_INT_END_BIT | SDHCI_INT_CRC))
+		*cmd_error = -EILSEQ;
+	else if (intmask & SDHCI_INT_TIMEOUT)
+		*cmd_error = -ETIMEDOUT;
+	else
+		*cmd_error = 0;
+
+	if (intmask & (SDHCI_INT_DATA_END_BIT | SDHCI_INT_DATA_CRC))
+		*data_error = -EILSEQ;
+	else if (intmask & SDHCI_INT_DATA_TIMEOUT)
+		*data_error = -ETIMEDOUT;
+	else if (intmask & SDHCI_INT_ADMA_ERROR)
+		*data_error = -EIO;
+	else
+		*data_error = 0;
+
+	/* Clear selected interrupts. */
+	mask = intmask & host->cqe_ier;
+	sdhci_writel(host, mask, SDHCI_INT_STATUS);
+
+	if (intmask & SDHCI_INT_BUS_POWER)
+		pr_err("%s: Card is consuming too much power!\n",
+		       mmc_hostname(host->mmc));
+
+	intmask &= ~(host->cqe_ier | SDHCI_INT_ERROR);
+	if (intmask) {
+		sdhci_writel(host, intmask, SDHCI_INT_STATUS);
+		pr_err("%s: CQE: Unexpected interrupt 0x%08x.\n",
+		       mmc_hostname(host->mmc), intmask);
+		sdhci_dumpregs(host);
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(sdhci_cqe_irq);
+
+/*****************************************************************************\
+ *                                                                           *
  * Device allocation/registration                                            *
  *                                                                           *
 \*****************************************************************************/
@@ -3007,6 +3114,11 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 
 	host->flags = SDHCI_SIGNALING_330;
 
+	host->cqe_ier     = SDHCI_CQE_INT_MASK;
+	host->cqe_err_ier = SDHCI_CQE_INT_ERR_MASK;
+
+	host->tuning_delay = -1;
+
 	return host;
 }
 
@@ -3289,20 +3401,22 @@ int sdhci_setup_host(struct sdhci_host *host)
 	if (!(host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)) {
 		host->timeout_clk = (host->caps & SDHCI_TIMEOUT_CLK_MASK) >>
 					SDHCI_TIMEOUT_CLK_SHIFT;
+
+		if (host->caps & SDHCI_TIMEOUT_CLK_UNIT)
+			host->timeout_clk *= 1000;
+
 		if (host->timeout_clk == 0) {
-			if (host->ops->get_timeout_clock) {
-				host->timeout_clk =
-					host->ops->get_timeout_clock(host);
-			} else {
+			if (!host->ops->get_timeout_clock) {
 				pr_err("%s: Hardware doesn't specify timeout clock frequency.\n",
 					mmc_hostname(mmc));
 				ret = -ENODEV;
 				goto undma;
 			}
-		}
 
-		if (host->caps & SDHCI_TIMEOUT_CLK_UNIT)
-			host->timeout_clk *= 1000;
+			host->timeout_clk =
+				DIV_ROUND_UP(host->ops->get_timeout_clock(host),
+					     1000);
+		}
 
 		if (override_timeout_clk)
 			host->timeout_clk = override_timeout_clk;
@@ -3324,9 +3438,9 @@ int sdhci_setup_host(struct sdhci_host *host)
 	     !(host->flags & SDHCI_USE_SDMA)) &&
 	     !(host->quirks2 & SDHCI_QUIRK2_ACMD23_BROKEN)) {
 		host->flags |= SDHCI_AUTO_CMD23;
-		DBG("%s: Auto-CMD23 available\n", mmc_hostname(mmc));
+		DBG("Auto-CMD23 available\n");
 	} else {
-		DBG("%s: Auto-CMD23 unavailable\n", mmc_hostname(mmc));
+		DBG("Auto-CMD23 unavailable\n");
 	}
 
 	/*
@@ -3590,6 +3704,22 @@ undma:
 }
 EXPORT_SYMBOL_GPL(sdhci_setup_host);
 
+void sdhci_cleanup_host(struct sdhci_host *host)
+{
+	struct mmc_host *mmc = host->mmc;
+
+	if (!IS_ERR(mmc->supply.vqmmc))
+		regulator_disable(mmc->supply.vqmmc);
+
+	if (host->align_buffer)
+		dma_free_coherent(mmc_dev(mmc), host->align_buffer_sz +
+				  host->adma_table_sz, host->align_buffer,
+				  host->align_addr);
+	host->adma_table = NULL;
+	host->align_buffer = NULL;
+}
+EXPORT_SYMBOL_GPL(sdhci_cleanup_host);
+
 int __sdhci_add_host(struct sdhci_host *host)
 {
 	struct mmc_host *mmc = host->mmc;
@@ -3654,16 +3784,6 @@ unirq:
 untasklet:
 	tasklet_kill(&host->finish_tasklet);
 
-	if (!IS_ERR(mmc->supply.vqmmc))
-		regulator_disable(mmc->supply.vqmmc);
-
-	if (host->align_buffer)
-		dma_free_coherent(mmc_dev(mmc), host->align_buffer_sz +
-				  host->adma_table_sz, host->align_buffer,
-				  host->align_addr);
-	host->adma_table = NULL;
-	host->align_buffer = NULL;
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__sdhci_add_host);
@@ -3676,7 +3796,16 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (ret)
 		return ret;
 
-	return __sdhci_add_host(host);
+	ret = __sdhci_add_host(host);
+	if (ret)
+		goto cleanup;
+
+	return 0;
+
+cleanup:
+	sdhci_cleanup_host(host);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sdhci_add_host);
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index edf3adfbc213..0469fa191493 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -134,6 +134,7 @@
 #define  SDHCI_INT_CARD_REMOVE	0x00000080
 #define  SDHCI_INT_CARD_INT	0x00000100
 #define  SDHCI_INT_RETUNE	0x00001000
+#define  SDHCI_INT_CQE		0x00004000
 #define  SDHCI_INT_ERROR	0x00008000
 #define  SDHCI_INT_TIMEOUT	0x00010000
 #define  SDHCI_INT_CRC		0x00020000
@@ -158,6 +159,13 @@
 		SDHCI_INT_BLK_GAP)
 #define SDHCI_INT_ALL_MASK	((unsigned int)-1)
 
+#define SDHCI_CQE_INT_ERR_MASK ( \
+	SDHCI_INT_ADMA_ERROR | SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT | \
+	SDHCI_INT_DATA_CRC | SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_INDEX | \
+	SDHCI_INT_END_BIT | SDHCI_INT_CRC | SDHCI_INT_TIMEOUT)
+
+#define SDHCI_CQE_INT_MASK (SDHCI_CQE_INT_ERR_MASK | SDHCI_INT_CQE)
+
 #define SDHCI_ACMD12_ERR	0x3C
 
 #define SDHCI_HOST_CONTROL2		0x3E
@@ -518,6 +526,10 @@ struct sdhci_host {
 	/* cached registers */
 	u32			ier;
 
+	bool			cqe_on;		/* CQE is operating */
+	u32			cqe_ier;	/* CQE interrupt mask */
+	u32			cqe_err_ier;	/* CQE error interrupt mask */
+
 	wait_queue_head_t	buf_ready_int;	/* Waitqueue for Buffer Read Ready interrupt */
 	unsigned int		tuning_done;	/* Condition flag set when CMD19 succeeds */
 
@@ -526,6 +538,8 @@ struct sdhci_host {
 #define SDHCI_TUNING_MODE_1	0
 #define SDHCI_TUNING_MODE_2	1
 #define SDHCI_TUNING_MODE_3	2
+	/* Delay (ms) between tuning commands */
+	int			tuning_delay;
 
 	unsigned long private[0] ____cacheline_aligned;
 };
@@ -544,9 +558,12 @@ struct sdhci_ops {
 	void	(*set_power)(struct sdhci_host *host, unsigned char mode,
 			     unsigned short vdd);
 
+	u32		(*irq)(struct sdhci_host *host, u32 intmask);
+
 	int		(*enable_dma)(struct sdhci_host *host);
 	unsigned int	(*get_max_clock)(struct sdhci_host *host);
 	unsigned int	(*get_min_clock)(struct sdhci_host *host);
+	/* get_timeout_clock should return clk rate in unit of Hz */
 	unsigned int	(*get_timeout_clock)(struct sdhci_host *host);
 	unsigned int	(*get_max_timeout_count)(struct sdhci_host *host);
 	void		(*set_timeout)(struct sdhci_host *host,
@@ -562,10 +579,6 @@ struct sdhci_ops {
 	void    (*adma_workaround)(struct sdhci_host *host, u32 intmask);
 	void    (*card_event)(struct sdhci_host *host);
 	void	(*voltage_switch)(struct sdhci_host *host);
-	int	(*select_drive_strength)(struct sdhci_host *host,
-					 struct mmc_card *card,
-					 unsigned int max_dtr, int host_drv,
-					 int card_drv, int *drv_type);
 };
 
 #ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS
@@ -652,24 +665,23 @@ static inline u8 sdhci_readb(struct sdhci_host *host, int reg)
 
 #endif /* CONFIG_MMC_SDHCI_IO_ACCESSORS */
 
-extern struct sdhci_host *sdhci_alloc_host(struct device *dev,
-	size_t priv_size);
-extern void sdhci_free_host(struct sdhci_host *host);
+struct sdhci_host *sdhci_alloc_host(struct device *dev, size_t priv_size);
+void sdhci_free_host(struct sdhci_host *host);
 
 static inline void *sdhci_priv(struct sdhci_host *host)
 {
 	return host->private;
 }
 
-extern void sdhci_card_detect(struct sdhci_host *host);
-extern void __sdhci_read_caps(struct sdhci_host *host, u16 *ver, u32 *caps,
-			      u32 *caps1);
-extern int sdhci_setup_host(struct sdhci_host *host);
-extern int __sdhci_add_host(struct sdhci_host *host);
-extern int sdhci_add_host(struct sdhci_host *host);
-extern void sdhci_remove_host(struct sdhci_host *host, int dead);
-extern void sdhci_send_command(struct sdhci_host *host,
-				struct mmc_command *cmd);
+void sdhci_card_detect(struct sdhci_host *host);
+void __sdhci_read_caps(struct sdhci_host *host, u16 *ver, u32 *caps,
+		       u32 *caps1);
+int sdhci_setup_host(struct sdhci_host *host);
+void sdhci_cleanup_host(struct sdhci_host *host);
+int __sdhci_add_host(struct sdhci_host *host);
+int sdhci_add_host(struct sdhci_host *host);
+void sdhci_remove_host(struct sdhci_host *host, int dead);
+void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd);
 
 static inline void sdhci_read_caps(struct sdhci_host *host)
 {
@@ -693,13 +705,24 @@ void sdhci_set_bus_width(struct sdhci_host *host, int width);
 void sdhci_reset(struct sdhci_host *host, u8 mask);
 void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
+void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
+int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
+				      struct mmc_ios *ios);
+void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable);
 
 #ifdef CONFIG_PM
-extern int sdhci_suspend_host(struct sdhci_host *host);
-extern int sdhci_resume_host(struct sdhci_host *host);
-extern void sdhci_enable_irq_wakeups(struct sdhci_host *host);
-extern int sdhci_runtime_suspend_host(struct sdhci_host *host);
-extern int sdhci_runtime_resume_host(struct sdhci_host *host);
+int sdhci_suspend_host(struct sdhci_host *host);
+int sdhci_resume_host(struct sdhci_host *host);
+void sdhci_enable_irq_wakeups(struct sdhci_host *host);
+int sdhci_runtime_suspend_host(struct sdhci_host *host);
+int sdhci_runtime_resume_host(struct sdhci_host *host);
 #endif
 
+void sdhci_cqe_enable(struct mmc_host *mmc);
+void sdhci_cqe_disable(struct mmc_host *mmc, bool recovery);
+bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error,
+		   int *data_error);
+
+void sdhci_dumpregs(struct sdhci_host *host);
+
 #endif /* __SDHCI_HW_H */
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 6ffcd2838272..d6fa2214aaae 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -385,14 +385,6 @@ static void sunxi_mmc_init_idma_des(struct sunxi_mmc_host *host,
 	wmb();
 }
 
-static enum dma_data_direction sunxi_mmc_get_dma_dir(struct mmc_data *data)
-{
-	if (data->flags & MMC_DATA_WRITE)
-		return DMA_TO_DEVICE;
-	else
-		return DMA_FROM_DEVICE;
-}
-
 static int sunxi_mmc_map_dma(struct sunxi_mmc_host *host,
 			     struct mmc_data *data)
 {
@@ -400,7 +392,7 @@ static int sunxi_mmc_map_dma(struct sunxi_mmc_host *host,
 	struct scatterlist *sg;
 
 	dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-			     sunxi_mmc_get_dma_dir(data));
+			     mmc_get_dma_dir(data));
 	if (dma_len == 0) {
 		dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n");
 		return -ENOMEM;
@@ -489,7 +481,7 @@ static void sunxi_mmc_dump_errinfo(struct sunxi_mmc_host *host)
 				      cmd->opcode == SD_IO_RW_DIRECT))
 		return;
 
-	dev_err(mmc_dev(host->mmc),
+	dev_dbg(mmc_dev(host->mmc),
 		"smc %d err, cmd %d,%s%s%s%s%s%s%s%s%s%s !!\n",
 		host->mmc->index, cmd->opcode,
 		data ? (data->flags & MMC_DATA_WRITE ? " WR" : " RD") : "",
@@ -551,7 +543,7 @@ static irqreturn_t sunxi_mmc_finalize_request(struct sunxi_mmc_host *host)
 		rval |= SDXC_FIFO_RESET;
 		mmc_writel(host, REG_GCTRL, rval);
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-				     sunxi_mmc_get_dma_dir(data));
+			     mmc_get_dma_dir(data));
 	}
 
 	mmc_writel(host, REG_RINTR, 0xffff);
@@ -1022,7 +1014,7 @@ static void sunxi_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 		if (data)
 			dma_unmap_sg(mmc_dev(mmc), data->sg, data->sg_len,
-				     sunxi_mmc_get_dma_dir(data));
+				     mmc_get_dma_dir(data));
 
 		dev_err(mmc_dev(mmc), "request already pending\n");
 		mrq->cmd->error = -EBUSY;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 2b349d48fb9a..d0edb5730d3f 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -50,7 +50,11 @@
 #define CTL_CLK_AND_WAIT_CTL 0x138
 #define CTL_RESET_SDIO 0x1e0
 
-/* Definitions for values the CTRL_STATUS register can take. */
+/* Definitions for values the CTL_STOP_INTERNAL_ACTION register can take */
+#define TMIO_STOP_STP		BIT(0)
+#define TMIO_STOP_SEC		BIT(8)
+
+/* Definitions for values the CTL_STATUS register can take */
 #define TMIO_STAT_CMDRESPEND    BIT(0)
 #define TMIO_STAT_DATAEND       BIT(2)
 #define TMIO_STAT_CARD_REMOVE   BIT(3)
@@ -61,7 +65,7 @@
 #define TMIO_STAT_CARD_INSERT_A BIT(9)
 #define TMIO_STAT_SIGSTATE_A    BIT(10)
 
-/* These belong technically to CTRL_STATUS2, but the driver merges them */
+/* These belong technically to CTL_STATUS2, but the driver merges them */
 #define TMIO_STAT_CMD_IDX_ERR   BIT(16)
 #define TMIO_STAT_CRCFAIL       BIT(17)
 #define TMIO_STAT_STOPBIT_ERR   BIT(18)
@@ -85,7 +89,7 @@
 
 #define TMIO_BBS		512		/* Boot block size */
 
-/* Definitions for values the CTRL_SDIO_STATUS register can take. */
+/* Definitions for values the CTL_SDIO_STATUS register can take */
 #define TMIO_SDIO_STAT_IOIRQ	0x0001
 #define TMIO_SDIO_STAT_EXPUB52	0x4000
 #define TMIO_SDIO_STAT_EXWT	0x8000
@@ -137,7 +141,7 @@ struct tmio_mmc_host {
 	bool			force_pio;
 	struct dma_chan		*chan_rx;
 	struct dma_chan		*chan_tx;
-	struct tasklet_struct	dma_complete;
+	struct completion	dma_dataend;
 	struct tasklet_struct	dma_issue;
 	struct scatterlist	bounce_sg;
 	u8			*bounce_buf;
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index fa8a936a3d9b..e2093db2b7ff 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -43,6 +43,34 @@ void tmio_mmc_abort_dma(struct tmio_mmc_host *host)
 	tmio_mmc_enable_dma(host, true);
 }
 
+static void tmio_mmc_dma_callback(void *arg)
+{
+	struct tmio_mmc_host *host = arg;
+
+	spin_lock_irq(&host->lock);
+
+	if (!host->data)
+		goto out;
+
+	if (host->data->flags & MMC_DATA_READ)
+		dma_unmap_sg(host->chan_rx->device->dev,
+			     host->sg_ptr, host->sg_len,
+			     DMA_FROM_DEVICE);
+	else
+		dma_unmap_sg(host->chan_tx->device->dev,
+			     host->sg_ptr, host->sg_len,
+			     DMA_TO_DEVICE);
+
+	spin_unlock_irq(&host->lock);
+
+	wait_for_completion(&host->dma_dataend);
+
+	spin_lock_irq(&host->lock);
+	tmio_mmc_do_data_irq(host);
+out:
+	spin_unlock_irq(&host->lock);
+}
+
 static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host)
 {
 	struct scatterlist *sg = host->sg_ptr, *sg_tmp;
@@ -88,6 +116,10 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host)
 			DMA_DEV_TO_MEM, DMA_CTRL_ACK);
 
 	if (desc) {
+		reinit_completion(&host->dma_dataend);
+		desc->callback = tmio_mmc_dma_callback;
+		desc->callback_param = host;
+
 		cookie = dmaengine_submit(desc);
 		if (cookie < 0) {
 			desc = NULL;
@@ -162,6 +194,10 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host)
 			DMA_MEM_TO_DEV, DMA_CTRL_ACK);
 
 	if (desc) {
+		reinit_completion(&host->dma_dataend);
+		desc->callback = tmio_mmc_dma_callback;
+		desc->callback_param = host;
+
 		cookie = dmaengine_submit(desc);
 		if (cookie < 0) {
 			desc = NULL;
@@ -221,29 +257,6 @@ static void tmio_mmc_issue_tasklet_fn(unsigned long priv)
 		dma_async_issue_pending(chan);
 }
 
-static void tmio_mmc_tasklet_fn(unsigned long arg)
-{
-	struct tmio_mmc_host *host = (struct tmio_mmc_host *)arg;
-
-	spin_lock_irq(&host->lock);
-
-	if (!host->data)
-		goto out;
-
-	if (host->data->flags & MMC_DATA_READ)
-		dma_unmap_sg(host->chan_rx->device->dev,
-			     host->sg_ptr, host->sg_len,
-			     DMA_FROM_DEVICE);
-	else
-		dma_unmap_sg(host->chan_tx->device->dev,
-			     host->sg_ptr, host->sg_len,
-			     DMA_TO_DEVICE);
-
-	tmio_mmc_do_data_irq(host);
-out:
-	spin_unlock_irq(&host->lock);
-}
-
 void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata)
 {
 	/* We can only either use DMA for both Tx and Rx or not use it at all */
@@ -306,7 +319,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (!host->bounce_buf)
 			goto ebouncebuf;
 
-		tasklet_init(&host->dma_complete, tmio_mmc_tasklet_fn, (unsigned long)host);
+		init_completion(&host->dma_dataend);
 		tasklet_init(&host->dma_issue, tmio_mmc_issue_tasklet_fn, (unsigned long)host);
 	}
 
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 6b789a739d4d..a2d92f10501b 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -340,7 +340,7 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 
 	/* CMD12 is handled by hardware */
 	if (cmd->opcode == MMC_STOP_TRANSMISSION && !cmd->arg) {
-		sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x001);
+		sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, TMIO_STOP_STP);
 		return 0;
 	}
 
@@ -367,7 +367,7 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 	if (data) {
 		c |= DATA_PRESENT;
 		if (data->blocks > 1) {
-			sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x100);
+			sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, TMIO_STOP_SEC);
 			c |= TRANSFER_MULTI;
 
 			/*
@@ -553,10 +553,14 @@ void tmio_mmc_do_data_irq(struct tmio_mmc_host *host)
 	}
 
 	if (stop) {
-		if (stop->opcode == MMC_STOP_TRANSMISSION && !stop->arg)
-			sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x000);
-		else
-			BUG();
+		if (stop->opcode != MMC_STOP_TRANSMISSION || stop->arg)
+			dev_err(&host->pdev->dev, "unsupported stop: CMD%u,0x%x. We did CMD12,0\n",
+				stop->opcode, stop->arg);
+
+		/* fill in response from auto CMD12 */
+		stop->resp[0] = sd_ctrl_read16_and_16_as_32(host, CTL_RESPONSE);
+
+		sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0);
 	}
 
 	schedule_work(&host->done);
@@ -596,11 +600,11 @@ static void tmio_mmc_data_irq(struct tmio_mmc_host *host, unsigned int stat)
 
 		if (done) {
 			tmio_mmc_disable_mmc_irqs(host, TMIO_STAT_DATAEND);
-			tasklet_schedule(&host->dma_complete);
+			complete(&host->dma_dataend);
 		}
 	} else if (host->chan_rx && (data->flags & MMC_DATA_READ) && !host->force_pio) {
 		tmio_mmc_disable_mmc_irqs(host, TMIO_STAT_DATAEND);
-		tasklet_schedule(&host->dma_complete);
+		complete(&host->dma_dataend);
 	} else {
 		tmio_mmc_do_data_irq(host);
 		tmio_mmc_disable_mmc_irqs(host, TMIO_MASK_READOP | TMIO_MASK_WRITEOP);
@@ -811,16 +815,14 @@ static int tmio_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 	int i, ret = 0;
 
-	if (!host->tap_num) {
-		if (!host->init_tuning || !host->select_tuning)
-			/* Tuning is not supported */
-			goto out;
+	if (!host->init_tuning || !host->select_tuning)
+		/* Tuning is not supported */
+		goto out;
 
-		host->tap_num = host->init_tuning(host);
-		if (!host->tap_num)
-			/* Tuning is not supported */
-			goto out;
-	}
+	host->tap_num = host->init_tuning(host);
+	if (!host->tap_num)
+		/* Tuning is not supported */
+		goto out;
 
 	if (host->tap_num * 2 >= sizeof(host->taps) * BITS_PER_BYTE) {
 		dev_warn_once(&host->pdev->dev,
diff --git a/drivers/mmc/host/ushc.c b/drivers/mmc/host/ushc.c
index d2c386f09d69..1d843357422e 100644
--- a/drivers/mmc/host/ushc.c
+++ b/drivers/mmc/host/ushc.c
@@ -426,6 +426,9 @@ static int ushc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	struct ushc_data *ushc;
 	int ret;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	mmc = mmc_alloc_host(sizeof(struct ushc_data), &intf->dev);
 	if (mmc == NULL)
 		return -ENOMEM;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 66a9dedd1062..1517da3ddd7d 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -46,7 +46,7 @@
 
 #include "mtdcore.h"
 
-static struct backing_dev_info *mtd_bdi;
+struct backing_dev_info *mtd_bdi;
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -496,11 +496,9 @@ int add_mtd_device(struct mtd_info *mtd)
 	 * mtd_device_parse_register() multiple times on the same master MTD,
 	 * especially with CONFIG_MTD_PARTITIONED_MASTER=y.
 	 */
-	if (WARN_ONCE(mtd->backing_dev_info, "MTD already registered\n"))
+	if (WARN_ONCE(mtd->dev.type, "MTD already registered\n"))
 		return -EEXIST;
 
-	mtd->backing_dev_info = mtd_bdi;
-
 	BUG_ON(mtd->writesize == 0);
 	mutex_lock(&mtd_table_mutex);
 
@@ -1775,13 +1773,18 @@ static struct backing_dev_info * __init mtd_bdi_init(char *name)
 	struct backing_dev_info *bdi;
 	int ret;
 
-	bdi = kzalloc(sizeof(*bdi), GFP_KERNEL);
+	bdi = bdi_alloc(GFP_KERNEL);
 	if (!bdi)
 		return ERR_PTR(-ENOMEM);
 
-	ret = bdi_setup_and_register(bdi, name);
+	bdi->name = name;
+	/*
+	 * We put '-0' suffix to the name to get the same name format as we
+	 * used to get. Since this is called only once, we get a unique name. 
+	 */
+	ret = bdi_register(bdi, "%.28s-0", name);
 	if (ret)
-		kfree(bdi);
+		bdi_put(bdi);
 
 	return ret ? ERR_PTR(ret) : bdi;
 }
@@ -1813,8 +1816,7 @@ static int __init init_mtd(void)
 out_procfs:
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
-	bdi_destroy(mtd_bdi);
-	kfree(mtd_bdi);
+	bdi_put(mtd_bdi);
 err_bdi:
 	class_unregister(&mtd_class);
 err_reg:
@@ -1828,8 +1830,7 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
-	bdi_destroy(mtd_bdi);
-	kfree(mtd_bdi);
+	bdi_put(mtd_bdi);
 	idr_destroy(&mtd_idr);
 }
 
diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c
index 20c02a3b7417..e43fea896d1e 100644
--- a/drivers/mtd/mtdsuper.c
+++ b/drivers/mtd/mtdsuper.c
@@ -18,6 +18,7 @@
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <linux/major.h>
+#include <linux/backing-dev.h>
 
 /*
  * compare superblocks to see if they're equivalent
@@ -38,6 +39,8 @@ static int get_sb_mtd_compare(struct super_block *sb, void *_mtd)
 	return 0;
 }
 
+extern struct backing_dev_info *mtd_bdi;
+
 /*
  * mark the superblock by the MTD device it is using
  * - set the device number to be the correct MTD block device for pesuperstence
@@ -49,7 +52,8 @@ static int get_sb_mtd_set(struct super_block *sb, void *_mtd)
 
 	sb->s_mtd = mtd;
 	sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
-	sb->s_bdi = mtd->backing_dev_info;
+	sb->s_bdi = bdi_get(mtd_bdi);
+
 	return 0;
 }
 
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 1ae872bfc3ba..747645c74134 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -186,7 +186,7 @@ static inline int write_enable(struct spi_nor *nor)
 }
 
 /*
- * Send write disble instruction to the chip.
+ * Send write disable instruction to the chip.
  */
 static inline int write_disable(struct spi_nor *nor)
 {
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index c80869e60909..51f2be8889b5 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -347,7 +347,7 @@ static int ubiblock_init_request(void *data, struct request *req,
 	return 0;
 }
 
-static struct blk_mq_ops ubiblock_mq_ops = {
+static const struct blk_mq_ops ubiblock_mq_ops = {
 	.queue_rq       = ubiblock_queue_rq,
 	.init_request	= ubiblock_init_request,
 };
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index 0134ba32a057..39712560b4c1 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -148,11 +148,11 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 			return err;
 	}
 
-	if (bytes == 0) {
-		err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
-		if (err)
-			return err;
+	err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
+	if (err)
+		return err;
 
+	if (bytes == 0) {
 		err = clear_update_marker(ubi, vol, 0);
 		if (err)
 			return err;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 100fbdc9b95c..83a1616903f8 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -355,6 +355,14 @@ config NET_VRF
 	  This option enables the support for mapping interfaces into VRF's. The
 	  support enables VRF devices.
 
+config VSOCKMON
+    tristate "Virtual vsock monitoring device"
+    depends on VHOST_VSOCK
+    ---help---
+     This option enables a monitoring net device for vsock sockets. It is
+     mostly intended for developers or support to debug vsock issues. If
+     unsure, say N.
+
 endif # NET_CORE
 
 config SUNGEM_PHY
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 98ed4d96987c..b2f6556d8848 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_MII) += mii.o
 obj-$(CONFIG_MDIO) += mdio.o
 obj-$(CONFIG_NET) += Space.o loopback.o
 obj-$(CONFIG_NETCONSOLE) += netconsole.o
-obj-$(CONFIG_PHYLIB) += phy/
+obj-y += phy/
 obj-$(CONFIG_RIONET) += rionet.o
 obj-$(CONFIG_NET_TEAM) += team/
 obj-$(CONFIG_TUN) += tun.o
@@ -30,6 +30,7 @@ obj-$(CONFIG_GENEVE) += geneve.o
 obj-$(CONFIG_GTP) += gtp.o
 obj-$(CONFIG_NLMON) += nlmon.o
 obj-$(CONFIG_NET_VRF) += vrf.o
+obj-$(CONFIG_VSOCKMON) += vsockmon.o
 
 #
 # Networking Drivers
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index edc70ffad660..c5fd4259da33 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -92,6 +92,7 @@ enum ad_link_speed_type {
 	AD_LINK_SPEED_2500MBPS,
 	AD_LINK_SPEED_10000MBPS,
 	AD_LINK_SPEED_20000MBPS,
+	AD_LINK_SPEED_25000MBPS,
 	AD_LINK_SPEED_40000MBPS,
 	AD_LINK_SPEED_56000MBPS,
 	AD_LINK_SPEED_100000MBPS,
@@ -260,6 +261,7 @@ static inline int __check_agg_selection_timer(struct port *port)
  *     %AD_LINK_SPEED_2500MBPS,
  *     %AD_LINK_SPEED_10000MBPS
  *     %AD_LINK_SPEED_20000MBPS
+ *     %AD_LINK_SPEED_25000MBPS
  *     %AD_LINK_SPEED_40000MBPS
  *     %AD_LINK_SPEED_56000MBPS
  *     %AD_LINK_SPEED_100000MBPS
@@ -302,6 +304,10 @@ static u16 __get_link_speed(struct port *port)
 			speed = AD_LINK_SPEED_20000MBPS;
 			break;
 
+		case SPEED_25000:
+			speed = AD_LINK_SPEED_25000MBPS;
+			break;
+
 		case SPEED_40000:
 			speed = AD_LINK_SPEED_40000MBPS;
 			break;
@@ -707,6 +713,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 		case AD_LINK_SPEED_20000MBPS:
 			bandwidth = nports * 20000;
 			break;
+		case AD_LINK_SPEED_25000MBPS:
+			bandwidth = nports * 25000;
+			break;
 		case AD_LINK_SPEED_40000MBPS:
 			bandwidth = nports * 40000;
 			break;
@@ -1052,8 +1061,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 		port->sm_rx_state = AD_RX_INITIALIZE;
 		port->sm_vars |= AD_PORT_CHURNED;
 	/* check if port is not enabled */
-	} else if (!(port->sm_vars & AD_PORT_BEGIN)
-		 && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED))
+	} else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled)
 		port->sm_rx_state = AD_RX_PORT_DISABLED;
 	/* check if new lacpdu arrived */
 	else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) ||
@@ -1081,11 +1089,8 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			/* if no lacpdu arrived and no timer is on */
 			switch (port->sm_rx_state) {
 			case AD_RX_PORT_DISABLED:
-				if (port->sm_vars & AD_PORT_MOVED)
-					port->sm_rx_state = AD_RX_INITIALIZE;
-				else if (port->is_enabled
-					 && (port->sm_vars
-					     & AD_PORT_LACP_ENABLED))
+				if (port->is_enabled &&
+				    (port->sm_vars & AD_PORT_LACP_ENABLED))
 					port->sm_rx_state = AD_RX_EXPIRED;
 				else if (port->is_enabled
 					 && ((port->sm_vars
@@ -1115,7 +1120,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			port->sm_vars &= ~AD_PORT_SELECTED;
 			__record_default(port);
 			port->actor_oper_port_state &= ~AD_STATE_EXPIRED;
-			port->sm_vars &= ~AD_PORT_MOVED;
 			port->sm_rx_state = AD_RX_PORT_DISABLED;
 
 			/* Fall Through */
@@ -2442,9 +2446,9 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave)
 
 	spin_lock_bh(&slave->bond->mode_lock);
 	ad_update_actor_keys(port, false);
+	spin_unlock_bh(&slave->bond->mode_lock);
 	netdev_dbg(slave->bond->dev, "Port %d slave %s changed speed/duplex\n",
 		   port->actor_port_number, slave->dev->name);
-	spin_unlock_bh(&slave->bond->mode_lock);
 }
 
 /**
@@ -2488,12 +2492,12 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 	agg = __get_first_agg(port);
 	ad_agg_selection_logic(agg, &dummy);
 
+	spin_unlock_bh(&slave->bond->mode_lock);
+
 	netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n",
 		   port->actor_port_number,
 		   link == BOND_LINK_UP ? "UP" : "DOWN");
 
-	spin_unlock_bh(&slave->bond->mode_lock);
-
 	/* RTNL is held and mode_lock is released so it's safe
 	 * to update slave_array here.
 	 */
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c80b023092dd..7d7a3cec149a 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -687,7 +687,8 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		/* the arp must be sent on the selected rx channel */
 		tx_slave = rlb_choose_channel(skb, bond);
 		if (tx_slave)
-			ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr);
+			bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
+					  tx_slave->dev->addr_len);
 		netdev_dbg(bond->dev, "Server sent ARP Reply packet\n");
 	} else if (arp->op_code == htons(ARPOP_REQUEST)) {
 		/* Create an entry in the rx_hashtbl for this client as a
@@ -1017,22 +1018,23 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 	rcu_read_unlock();
 }
 
-static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
+static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[],
+				  unsigned int len)
 {
 	struct net_device *dev = slave->dev;
-	struct sockaddr s_addr;
+	struct sockaddr_storage ss;
 
 	if (BOND_MODE(slave->bond) == BOND_MODE_TLB) {
-		memcpy(dev->dev_addr, addr, dev->addr_len);
+		memcpy(dev->dev_addr, addr, len);
 		return 0;
 	}
 
 	/* for rlb each slave must have a unique hw mac addresses so that
 	 * each slave will receive packets destined to a different mac
 	 */
-	memcpy(s_addr.sa_data, addr, dev->addr_len);
-	s_addr.sa_family = dev->type;
-	if (dev_set_mac_address(dev, &s_addr)) {
+	memcpy(ss.__data, addr, len);
+	ss.ss_family = dev->type;
+	if (dev_set_mac_address(dev, (struct sockaddr *)&ss)) {
 		netdev_err(slave->bond->dev, "dev_set_mac_address of dev %s failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
 			   dev->name);
 		return -EOPNOTSUPP;
@@ -1046,11 +1048,14 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
  */
 static void alb_swap_mac_addr(struct slave *slave1, struct slave *slave2)
 {
-	u8 tmp_mac_addr[ETH_ALEN];
+	u8 tmp_mac_addr[MAX_ADDR_LEN];
 
-	ether_addr_copy(tmp_mac_addr, slave1->dev->dev_addr);
-	alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr);
-	alb_set_slave_mac_addr(slave2, tmp_mac_addr);
+	bond_hw_addr_copy(tmp_mac_addr, slave1->dev->dev_addr,
+			  slave1->dev->addr_len);
+	alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr,
+			       slave2->dev->addr_len);
+	alb_set_slave_mac_addr(slave2, tmp_mac_addr,
+			       slave1->dev->addr_len);
 
 }
 
@@ -1177,7 +1182,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 		/* Try setting slave mac to bond address and fall-through
 		 * to code handling that situation below...
 		 */
-		alb_set_slave_mac_addr(slave, bond->dev->dev_addr);
+		alb_set_slave_mac_addr(slave, bond->dev->dev_addr,
+				       bond->dev->addr_len);
 	}
 
 	/* The slave's address is equal to the address of the bond.
@@ -1202,7 +1208,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 	}
 
 	if (free_mac_slave) {
-		alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr);
+		alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr,
+				       free_mac_slave->dev->addr_len);
 
 		netdev_warn(bond->dev, "the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
 			    slave->dev->name, free_mac_slave->dev->name);
@@ -1234,8 +1241,8 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 {
 	struct slave *slave, *rollback_slave;
 	struct list_head *iter;
-	struct sockaddr sa;
-	char tmp_addr[ETH_ALEN];
+	struct sockaddr_storage ss;
+	char tmp_addr[MAX_ADDR_LEN];
 	int res;
 
 	if (bond->alb_info.rlb_enabled)
@@ -1243,12 +1250,14 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 
 	bond_for_each_slave(bond, slave, iter) {
 		/* save net_device's current hw address */
-		ether_addr_copy(tmp_addr, slave->dev->dev_addr);
+		bond_hw_addr_copy(tmp_addr, slave->dev->dev_addr,
+				  slave->dev->addr_len);
 
 		res = dev_set_mac_address(slave->dev, addr);
 
 		/* restore net_device's hw address */
-		ether_addr_copy(slave->dev->dev_addr, tmp_addr);
+		bond_hw_addr_copy(slave->dev->dev_addr, tmp_addr,
+				  slave->dev->addr_len);
 
 		if (res)
 			goto unwind;
@@ -1257,16 +1266,19 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 	return 0;
 
 unwind:
-	memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
-	sa.sa_family = bond->dev->type;
+	memcpy(ss.__data, bond->dev->dev_addr, bond->dev->addr_len);
+	ss.ss_family = bond->dev->type;
 
 	/* unwind from head to the slave that failed */
 	bond_for_each_slave(bond, rollback_slave, iter) {
 		if (rollback_slave == slave)
 			break;
-		ether_addr_copy(tmp_addr, rollback_slave->dev->dev_addr);
-		dev_set_mac_address(rollback_slave->dev, &sa);
-		ether_addr_copy(rollback_slave->dev->dev_addr, tmp_addr);
+		bond_hw_addr_copy(tmp_addr, rollback_slave->dev->dev_addr,
+				  rollback_slave->dev->addr_len);
+		dev_set_mac_address(rollback_slave->dev,
+				    (struct sockaddr *)&ss);
+		bond_hw_addr_copy(rollback_slave->dev->dev_addr, tmp_addr,
+				  rollback_slave->dev->addr_len);
 	}
 
 	return res;
@@ -1582,7 +1594,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave)
 {
 	int res;
 
-	res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr);
+	res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr,
+				     slave->dev->addr_len);
 	if (res)
 		return res;
 
@@ -1696,17 +1709,20 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	 * and thus filter bond->dev_addr's packets, so force bond's mac
 	 */
 	if (BOND_MODE(bond) == BOND_MODE_TLB) {
-		struct sockaddr sa;
-		u8 tmp_addr[ETH_ALEN];
+		struct sockaddr_storage ss;
+		u8 tmp_addr[MAX_ADDR_LEN];
 
-		ether_addr_copy(tmp_addr, new_slave->dev->dev_addr);
+		bond_hw_addr_copy(tmp_addr, new_slave->dev->dev_addr,
+				  new_slave->dev->addr_len);
 
-		memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
-		sa.sa_family = bond->dev->type;
+		bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+				  bond->dev->addr_len);
+		ss.ss_family = bond->dev->type;
 		/* we don't care if it can't change its mac, best effort */
-		dev_set_mac_address(new_slave->dev, &sa);
+		dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss);
 
-		ether_addr_copy(new_slave->dev->dev_addr, tmp_addr);
+		bond_hw_addr_copy(new_slave->dev->dev_addr, tmp_addr,
+				  new_slave->dev->addr_len);
 	}
 
 	/* curr_active_slave must be set before calling alb_swap_mac_addr */
@@ -1716,7 +1732,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 		alb_fasten_mac_swap(bond, swap_slave, new_slave);
 	} else {
 		/* set the new_slave to the bond mac address */
-		alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr);
+		alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr,
+				       bond->dev->addr_len);
 		alb_send_learning_packets(new_slave, bond->dev->dev_addr,
 					  false);
 	}
@@ -1726,19 +1743,19 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct sockaddr *sa = addr;
+	struct sockaddr_storage *ss = addr;
 	struct slave *curr_active;
 	struct slave *swap_slave;
 	int res;
 
-	if (!is_valid_ether_addr(sa->sa_data))
+	if (!is_valid_ether_addr(ss->__data))
 		return -EADDRNOTAVAIL;
 
 	res = alb_set_mac_address(bond, addr);
 	if (res)
 		return res;
 
-	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+	bond_hw_addr_copy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
 
 	/* If there is no curr_active_slave there is nothing else to do.
 	 * Otherwise we'll need to pass the new address to it and handle
@@ -1754,7 +1771,8 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 		alb_swap_mac_addr(swap_slave, curr_active);
 		alb_fasten_mac_swap(bond, swap_slave, curr_active);
 	} else {
-		alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr);
+		alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr,
+				       bond_dev->addr_len);
 
 		alb_send_learning_packets(curr_active,
 					  bond_dev->dev_addr, false);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8a4ba8b88e52..2be78807fd6e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -201,12 +201,6 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
-static __be32 arp_target[BOND_MAX_ARP_TARGETS];
-static int arp_ip_count;
-static int bond_mode	= BOND_MODE_ROUNDROBIN;
-static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
-static int lacp_fast;
-
 /*-------------------------- Forward declarations ---------------------------*/
 
 static int bond_init(struct net_device *bond_dev);
@@ -371,9 +365,10 @@ down:
 /* Get link speed and duplex from the slave's base driver
  * using ethtool. If for some reason the call fails or the
  * values are invalid, set speed and duplex to -1,
- * and return.
+ * and return. Return 1 if speed or duplex settings are
+ * UNKNOWN; 0 otherwise.
  */
-static void bond_update_speed_duplex(struct slave *slave)
+static int bond_update_speed_duplex(struct slave *slave)
 {
 	struct net_device *slave_dev = slave->dev;
 	struct ethtool_link_ksettings ecmd;
@@ -384,23 +379,21 @@ static void bond_update_speed_duplex(struct slave *slave)
 
 	res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
 	if (res < 0)
-		return;
-
+		return 1;
 	if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
-		return;
-
+		return 1;
 	switch (ecmd.base.duplex) {
 	case DUPLEX_FULL:
 	case DUPLEX_HALF:
 		break;
 	default:
-		return;
+		return 1;
 	}
 
 	slave->speed = ecmd.base.speed;
 	slave->duplex = ecmd.base.duplex;
 
-	return;
+	return 0;
 }
 
 const char *bond_slave_link_status(s8 link)
@@ -652,8 +645,8 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 				  struct slave *new_active,
 				  struct slave *old_active)
 {
-	u8 tmp_mac[ETH_ALEN];
-	struct sockaddr saddr;
+	u8 tmp_mac[MAX_ADDR_LEN];
+	struct sockaddr_storage ss;
 	int rv;
 
 	switch (bond->params.fail_over_mac) {
@@ -673,16 +666,20 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			old_active = bond_get_old_active(bond, new_active);
 
 		if (old_active) {
-			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
-			ether_addr_copy(saddr.sa_data,
-					old_active->dev->dev_addr);
-			saddr.sa_family = new_active->dev->type;
+			bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
+					  new_active->dev->addr_len);
+			bond_hw_addr_copy(ss.__data,
+					  old_active->dev->dev_addr,
+					  old_active->dev->addr_len);
+			ss.ss_family = new_active->dev->type;
 		} else {
-			ether_addr_copy(saddr.sa_data, bond->dev->dev_addr);
-			saddr.sa_family = bond->dev->type;
+			bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+					  bond->dev->addr_len);
+			ss.ss_family = bond->dev->type;
 		}
 
-		rv = dev_set_mac_address(new_active->dev, &saddr);
+		rv = dev_set_mac_address(new_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv) {
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -692,10 +689,12 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!old_active)
 			goto out;
 
-		ether_addr_copy(saddr.sa_data, tmp_mac);
-		saddr.sa_family = old_active->dev->type;
+		bond_hw_addr_copy(ss.__data, tmp_mac,
+				  new_active->dev->addr_len);
+		ss.ss_family = old_active->dev->type;
 
-		rv = dev_set_mac_address(old_active->dev, &saddr);
+		rv = dev_set_mac_address(old_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv)
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -1104,11 +1103,11 @@ static void bond_compute_features(struct bonding *bond)
 		gso_max_size = min(gso_max_size, slave->dev->gso_max_size);
 		gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs);
 	}
+	bond_dev->hard_header_len = max_hard_header_len;
 
 done:
 	bond_dev->vlan_features = vlan_features;
 	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL;
-	bond_dev->hard_header_len = max_hard_header_len;
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
 
@@ -1177,6 +1176,9 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
+	/* don't change skb->dev for link-local packets */
+	if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
+		return RX_HANDLER_PASS;
 	if (bond_should_deliver_exact_match(skb, slave, bond))
 		return RX_HANDLER_EXACT;
 
@@ -1191,7 +1193,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 			kfree_skb(skb);
 			return RX_HANDLER_CONSUMED;
 		}
-		ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr);
+		bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
+				  bond->dev->addr_len);
 	}
 
 	return ret;
@@ -1330,7 +1333,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
 	struct slave *new_slave = NULL, *prev_slave;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int link_reporting;
 	int res = 0, i;
 
@@ -1481,16 +1484,17 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * that need it, and for restoring it upon release, and then
 	 * set it to the master's address
 	 */
-	ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
+	bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
+			  slave_dev->addr_len);
 
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* Set slave to master's mac address.  The application already
 		 * set the master's mac address to that of the first slave
 		 */
-		memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-		addr.sa_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, &addr);
+		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 		if (res) {
 			netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
 			goto err_restore_mtu;
@@ -1565,7 +1569,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	new_slave->delay = 0;
 	new_slave->link_failure_count = 0;
 
-	bond_update_speed_duplex(new_slave);
+	if (bond_update_speed_duplex(new_slave))
+		new_slave->link = BOND_LINK_DOWN;
 
 	new_slave->last_rx = jiffies -
 		(msecs_to_jiffies(bond->params.arp_interval) + 1);
@@ -1773,9 +1778,10 @@ err_restore_mac:
 		 * MAC if this slave's MAC is in use by the bond, or at
 		 * least print a warning.
 		 */
-		ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
+				  new_slave->dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 	}
 
 err_restore_mtu:
@@ -1818,7 +1824,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *oldcurrent;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int old_flags = bond_dev->flags;
 	netdev_features_t old_features = bond_dev->features;
 
@@ -1953,9 +1959,10 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* restore original ("permanent") mac address */
-		ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
+				  slave->dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 	}
 
 	dev_set_mtu(slave_dev, slave->original_mtu);
@@ -2039,8 +2046,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
-						  BOND_SLAVE_NOTIFY_LATER);
+			bond_propose_link_state(slave, BOND_LINK_FAIL);
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2055,13 +2061,13 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
-				bond_set_slave_link_state(slave, BOND_LINK_UP,
-							  BOND_SLAVE_NOTIFY_LATER);
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave->last_link_up = jiffies;
 				netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
 					    (bond->params.downdelay - slave->delay) *
 					    bond->params.miimon,
 					    slave->dev->name);
+				commit++;
 				continue;
 			}
 
@@ -2078,8 +2084,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (!link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_BACK,
-						  BOND_SLAVE_NOTIFY_LATER);
+			bond_propose_link_state(slave, BOND_LINK_BACK);
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -2092,14 +2097,12 @@ static int bond_miimon_inspect(struct bonding *bond)
 			/*FALLTHRU*/
 		case BOND_LINK_BACK:
 			if (!link_state) {
-				bond_set_slave_link_state(slave,
-							  BOND_LINK_DOWN,
-							  BOND_SLAVE_NOTIFY_LATER);
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
 					    (bond->params.updelay - slave->delay) *
 					    bond->params.miimon,
 					    slave->dev->name);
-
+				commit++;
 				continue;
 			}
 
@@ -2132,7 +2135,13 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			bond_update_speed_duplex(slave);
+			if (bond_update_speed_duplex(slave)) {
+				slave->link = BOND_LINK_DOWN;
+				netdev_warn(bond->dev,
+					    "failed to get link speed/duplex for %s\n",
+					    slave->dev->name);
+				continue;
+			}
 			bond_set_slave_link_state(slave, BOND_LINK_UP,
 						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
@@ -2231,6 +2240,8 @@ static void bond_mii_monitor(struct work_struct *work)
 					    mii_work.work);
 	bool should_notify_peers = false;
 	unsigned long delay;
+	struct slave *slave;
+	struct list_head *iter;
 
 	delay = msecs_to_jiffies(bond->params.miimon);
 
@@ -2251,6 +2262,9 @@ static void bond_mii_monitor(struct work_struct *work)
 			goto re_arm;
 		}
 
+		bond_for_each_slave(bond, slave, iter) {
+			bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+		}
 		bond_miimon_commit(bond);
 
 		rtnl_unlock();	/* might sleep, hold no other locks */
@@ -2575,10 +2589,8 @@ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
  * arp is transmitted to generate traffic. see activebackup_arp_monitor for
  * arp monitoring in active backup mode.
  */
-static void bond_loadbalance_arp_mon(struct work_struct *work)
+static void bond_loadbalance_arp_mon(struct bonding *bond)
 {
-	struct bonding *bond = container_of(work, struct bonding,
-					    arp_work.work);
 	struct slave *slave, *oldcurrent;
 	struct list_head *iter;
 	int do_failover = 0, slave_state_changed = 0;
@@ -2916,10 +2928,8 @@ check_state:
 	return should_notify_rtnl;
 }
 
-static void bond_activebackup_arp_mon(struct work_struct *work)
+static void bond_activebackup_arp_mon(struct bonding *bond)
 {
-	struct bonding *bond = container_of(work, struct bonding,
-					    arp_work.work);
 	bool should_notify_peers = false;
 	bool should_notify_rtnl = false;
 	int delta_in_ticks;
@@ -2972,6 +2982,17 @@ re_arm:
 	}
 }
 
+static void bond_arp_monitor(struct work_struct *work)
+{
+	struct bonding *bond = container_of(work, struct bonding,
+					    arp_work.work);
+
+	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
+		bond_activebackup_arp_mon(bond);
+	else
+		bond_loadbalance_arp_mon(bond);
+}
+
 /*-------------------------- netdev event handling --------------------------*/
 
 /* Change device name */
@@ -3222,16 +3243,13 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 
 /*-------------------------- Device entry points ----------------------------*/
 
-static void bond_work_init_all(struct bonding *bond)
+void bond_work_init_all(struct bonding *bond)
 {
 	INIT_DELAYED_WORK(&bond->mcast_work,
 			  bond_resend_igmp_join_requests_delayed);
 	INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
 	INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
-	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
-		INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon);
-	else
-		INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon);
+	INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor);
 	INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
 	INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
 }
@@ -3266,8 +3284,6 @@ static int bond_open(struct net_device *bond_dev)
 		}
 	}
 
-	bond_work_init_all(bond);
-
 	if (bond_is_lb(bond)) {
 		/* bond_alb_initialize must be called before the timer
 		 * is started.
@@ -3327,12 +3343,17 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
 		u64 nv = new[i];
 		u64 ov = old[i];
+		s64 delta = nv - ov;
 
 		/* detects if this particular field is 32bit only */
 		if (((nv | ov) >> 32) == 0)
-			res[i] += (u32)nv - (u32)ov;
-		else
-			res[i] += nv - ov;
+			delta = (s64)(s32)((u32)nv - (u32)ov);
+
+		/* filter anomalies, some drivers reset their stats
+		 * at down/up events.
+		 */
+		if (delta > 0)
+			res[i] += delta;
 	}
 }
 
@@ -3619,7 +3640,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *rollback_slave;
-	struct sockaddr *sa = addr, tmp_sa;
+	struct sockaddr_storage *ss = addr, tmp_ss;
 	struct list_head *iter;
 	int res = 0;
 
@@ -3636,7 +3657,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	    BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		return 0;
 
-	if (!is_valid_ether_addr(sa->sa_data))
+	if (!is_valid_ether_addr(ss->__data))
 		return -EADDRNOTAVAIL;
 
 	bond_for_each_slave(bond, slave, iter) {
@@ -3655,12 +3676,12 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	}
 
 	/* success */
-	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+	memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
 	return 0;
 
 unwind:
-	memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-	tmp_sa.sa_family = bond_dev->type;
+	memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+	tmp_ss.ss_family = bond_dev->type;
 
 	/* unwind from head to the slave that failed */
 	bond_for_each_slave(bond, rollback_slave, iter) {
@@ -3669,7 +3690,8 @@ unwind:
 		if (rollback_slave == slave)
 			break;
 
-		tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa);
+		tmp_res = dev_set_mac_address(rollback_slave->dev,
+					      (struct sockaddr *)&tmp_ss);
 		if (tmp_res) {
 			netdev_dbg(bond_dev, "unwind err %d dev %s\n",
 				   tmp_res, rollback_slave->dev->name);
@@ -4252,6 +4274,12 @@ static int bond_check_params(struct bond_params *params)
 	int arp_all_targets_value;
 	u16 ad_actor_sys_prio = 0;
 	u16 ad_user_port_key = 0;
+	__be32 arp_target[BOND_MAX_ARP_TARGETS];
+	int arp_ip_count;
+	int bond_mode	= BOND_MODE_ROUNDROBIN;
+	int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
+	int lacp_fast = 0;
+	int tlb_dynamic_lb = 0;
 
 	/* Convert string parameters. */
 	if (mode) {
@@ -4564,6 +4592,17 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
+	if (bond_mode == BOND_MODE_TLB) {
+		bond_opt_initstr(&newval, "default");
+		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
+					&newval);
+		if (!valptr) {
+			pr_err("Error: No tlb_dynamic_lb default value");
+			return -EINVAL;
+		}
+		tlb_dynamic_lb = valptr->value;
+	}
+
 	if (lp_interval == 0) {
 		pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
 			INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
@@ -4591,7 +4630,7 @@ static int bond_check_params(struct bond_params *params)
 	params->min_links = min_links;
 	params->lp_interval = lp_interval;
 	params->packets_per_slave = packets_per_slave;
-	params->tlb_dynamic_lb = 1; /* Default value */
+	params->tlb_dynamic_lb = tlb_dynamic_lb;
 	params->ad_actor_sys_prio = ad_actor_sys_prio;
 	eth_zero_addr(params->ad_actor_system);
 	params->ad_user_port_key = ad_user_port_key;
@@ -4687,6 +4726,8 @@ int bond_create(struct net *net, const char *name)
 
 	netif_carrier_off(bond_dev);
 
+	bond_work_init_all(bond);
+
 	rtnl_unlock();
 	if (res < 0)
 		bond_destructor(bond_dev);
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index b8df0f5e8c25..c502c139d3bc 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -449,6 +449,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 	err = register_netdevice(bond_dev);
 
 	netif_carrier_off(bond_dev);
+	if (!err) {
+		struct bonding *bond = netdev_priv(bond_dev);
+
+		bond_work_init_all(bond);
+	}
 
 	return err;
 }
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index f514fe5e80a5..d8d4ada034b7 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -183,7 +183,8 @@ static void bond_info_show_slave(struct seq_file *seq,
 	seq_printf(seq, "Link Failure Count: %u\n",
 		   slave->link_failure_count);
 
-	seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr);
+	seq_printf(seq, "Permanent HW addr: %*phC\n",
+		   slave->dev->addr_len, slave->perm_hwaddr);
 	seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id);
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 22570ea3a8d2..ac4ff394bc56 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -9,6 +9,24 @@ config CAN_VCAN
 	  This driver can also be built as a module.  If so, the module
 	  will be called vcan.
 
+config CAN_VXCAN
+	tristate "Virtual CAN Tunnel (vxcan)"
+	---help---
+	  Similar to the virtual ethernet driver veth, vxcan implements a
+	  local CAN traffic tunnel between two virtual CAN network devices.
+	  When creating a vxcan, two vxcan devices are created as pair.
+	  When one end receives the packet it appears on its pair and vice
+	  versa. The vxcan can be used for cross namespace communication.
+
+	  In opposite to vcan loopback devices the vxcan only forwards CAN
+	  frames to its pair and does *not* provide a local echo of sent
+	  CAN frames. To disable a potential echo in af_can.c the vxcan driver
+	  announces IFF_ECHO in the interface flags. To have a clean start
+	  in each namespace the CAN GW hop counter is set to zero.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called vxcan.
+
 config CAN_SLCAN
 	tristate "Serial / USB serial CAN Adaptors (slcan)"
 	depends on TTY
@@ -142,6 +160,7 @@ source "drivers/net/can/cc770/Kconfig"
 source "drivers/net/can/ifi_canfd/Kconfig"
 source "drivers/net/can/m_can/Kconfig"
 source "drivers/net/can/mscan/Kconfig"
+source "drivers/net/can/peak_canfd/Kconfig"
 source "drivers/net/can/rcar/Kconfig"
 source "drivers/net/can/sja1000/Kconfig"
 source "drivers/net/can/softing/Kconfig"
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index 0da4f2f5c7e3..4aabbee133b8 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_CAN_VCAN)		+= vcan.o
+obj-$(CONFIG_CAN_VXCAN)		+= vxcan.o
 obj-$(CONFIG_CAN_SLCAN)		+= slcan.o
 
 obj-$(CONFIG_CAN_DEV)		+= can-dev.o
@@ -26,6 +27,7 @@ obj-$(CONFIG_CAN_IFI_CANFD)	+= ifi_canfd/
 obj-$(CONFIG_CAN_JANZ_ICAN3)	+= janz-ican3.o
 obj-$(CONFIG_CAN_MSCAN)		+= mscan/
 obj-$(CONFIG_CAN_M_CAN)		+= m_can/
+obj-$(CONFIG_CAN_PEAK_PCIEFD)	+= peak_canfd/
 obj-$(CONFIG_CAN_SJA1000)	+= sja1000/
 obj-$(CONFIG_CAN_SUN4I)		+= sun4i_can.o
 obj-$(CONFIG_CAN_TI_HECC)	+= ti_hecc.o
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index 138f5ae75c0b..4d1fe8d95042 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -557,7 +557,7 @@ static int ifi_canfd_poll(struct napi_struct *napi, int quota)
 	int work_done = 0;
 
 	u32 stcmd = readl(priv->base + IFI_CANFD_STCMD);
-	u32 rxstcmd = readl(priv->base + IFI_CANFD_STCMD);
+	u32 rxstcmd = readl(priv->base + IFI_CANFD_RXSTCMD);
 	u32 errctr = readl(priv->base + IFI_CANFD_ERROR_CTR);
 
 	/* Handle bus state changes */
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 7a6554efd42b..bf8fdaeb955e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -23,7 +23,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
-
+#include <linux/iopoll.h>
 #include <linux/can/dev.h>
 
 /* napi related */
@@ -37,17 +37,19 @@ enum m_can_reg {
 	M_CAN_CREL	= 0x0,
 	M_CAN_ENDN	= 0x4,
 	M_CAN_CUST	= 0x8,
-	M_CAN_FBTP	= 0xc,
+	M_CAN_DBTP	= 0xc,
 	M_CAN_TEST	= 0x10,
 	M_CAN_RWD	= 0x14,
 	M_CAN_CCCR	= 0x18,
-	M_CAN_BTP	= 0x1c,
+	M_CAN_NBTP	= 0x1c,
 	M_CAN_TSCC	= 0x20,
 	M_CAN_TSCV	= 0x24,
 	M_CAN_TOCC	= 0x28,
 	M_CAN_TOCV	= 0x2c,
 	M_CAN_ECR	= 0x40,
 	M_CAN_PSR	= 0x44,
+/* TDCR Register only available for version >=3.1.x */
+	M_CAN_TDCR	= 0x48,
 	M_CAN_IR	= 0x50,
 	M_CAN_IE	= 0x54,
 	M_CAN_ILS	= 0x58,
@@ -105,21 +107,29 @@ enum m_can_mram_cfg {
 	MRAM_CFG_NUM,
 };
 
-/* Fast Bit Timing & Prescaler Register (FBTP) */
-#define FBTR_FBRP_MASK		0x1f
-#define FBTR_FBRP_SHIFT		16
-#define FBTR_FTSEG1_SHIFT	8
-#define FBTR_FTSEG1_MASK	(0xf << FBTR_FTSEG1_SHIFT)
-#define FBTR_FTSEG2_SHIFT	4
-#define FBTR_FTSEG2_MASK	(0x7 << FBTR_FTSEG2_SHIFT)
-#define FBTR_FSJW_SHIFT		0
-#define FBTR_FSJW_MASK		0x3
+/* Core Release Register (CREL) */
+#define CREL_REL_SHIFT		28
+#define CREL_REL_MASK		(0xF << CREL_REL_SHIFT)
+#define CREL_STEP_SHIFT		24
+#define CREL_STEP_MASK		(0xF << CREL_STEP_SHIFT)
+#define CREL_SUBSTEP_SHIFT	20
+#define CREL_SUBSTEP_MASK	(0xF << CREL_SUBSTEP_SHIFT)
+
+/* Data Bit Timing & Prescaler Register (DBTP) */
+#define DBTP_TDC		BIT(23)
+#define DBTP_DBRP_SHIFT		16
+#define DBTP_DBRP_MASK		(0x1f << DBTP_DBRP_SHIFT)
+#define DBTP_DTSEG1_SHIFT	8
+#define DBTP_DTSEG1_MASK	(0x1f << DBTP_DTSEG1_SHIFT)
+#define DBTP_DTSEG2_SHIFT	4
+#define DBTP_DTSEG2_MASK	(0xf << DBTP_DTSEG2_SHIFT)
+#define DBTP_DSJW_SHIFT		0
+#define DBTP_DSJW_MASK		(0xf << DBTP_DSJW_SHIFT)
 
 /* Test Register (TEST) */
-#define TEST_LBCK	BIT(4)
+#define TEST_LBCK		BIT(4)
 
 /* CC Control Register(CCCR) */
-#define CCCR_TEST		BIT(7)
 #define CCCR_CMR_MASK		0x3
 #define CCCR_CMR_SHIFT		10
 #define CCCR_CMR_CANFD		0x1
@@ -130,21 +140,32 @@ enum m_can_mram_cfg {
 #define CCCR_CME_CAN		0
 #define CCCR_CME_CANFD		0x1
 #define CCCR_CME_CANFD_BRS	0x2
+#define CCCR_TXP		BIT(14)
 #define CCCR_TEST		BIT(7)
 #define CCCR_MON		BIT(5)
+#define CCCR_CSR		BIT(4)
+#define CCCR_CSA		BIT(3)
+#define CCCR_ASM		BIT(2)
 #define CCCR_CCE		BIT(1)
 #define CCCR_INIT		BIT(0)
 #define CCCR_CANFD		0x10
-
-/* Bit Timing & Prescaler Register (BTP) */
-#define BTR_BRP_MASK		0x3ff
-#define BTR_BRP_SHIFT		16
-#define BTR_TSEG1_SHIFT		8
-#define BTR_TSEG1_MASK		(0x3f << BTR_TSEG1_SHIFT)
-#define BTR_TSEG2_SHIFT		4
-#define BTR_TSEG2_MASK		(0xf << BTR_TSEG2_SHIFT)
-#define BTR_SJW_SHIFT		0
-#define BTR_SJW_MASK		0xf
+/* for version >=3.1.x */
+#define CCCR_EFBI		BIT(13)
+#define CCCR_PXHD		BIT(12)
+#define CCCR_BRSE		BIT(9)
+#define CCCR_FDOE		BIT(8)
+/* only for version >=3.2.x */
+#define CCCR_NISO		BIT(15)
+
+/* Nominal Bit Timing & Prescaler Register (NBTP) */
+#define NBTP_NSJW_SHIFT		25
+#define NBTP_NSJW_MASK		(0x7f << NBTP_NSJW_SHIFT)
+#define NBTP_NBRP_SHIFT		16
+#define NBTP_NBRP_MASK		(0x1ff << NBTP_NBRP_SHIFT)
+#define NBTP_NTSEG1_SHIFT	8
+#define NBTP_NTSEG1_MASK	(0xff << NBTP_NTSEG1_SHIFT)
+#define NBTP_NTSEG2_SHIFT	0
+#define NBTP_NTSEG2_MASK	(0x7f << NBTP_NTSEG2_SHIFT)
 
 /* Error Counter Register(ECR) */
 #define ECR_RP			BIT(15)
@@ -161,6 +182,13 @@ enum m_can_mram_cfg {
 
 /* Interrupt Register(IR) */
 #define IR_ALL_INT	0xffffffff
+
+/* Renamed bits for versions > 3.1.x */
+#define IR_ARA		BIT(29)
+#define IR_PED		BIT(28)
+#define IR_PEA		BIT(27)
+
+/* Bits for version 3.0.x */
 #define IR_STE		BIT(31)
 #define IR_FOE		BIT(30)
 #define IR_ACKE		BIT(29)
@@ -194,33 +222,40 @@ enum m_can_mram_cfg {
 #define IR_RF0W		BIT(1)
 #define IR_RF0N		BIT(0)
 #define IR_ERR_STATE	(IR_BO | IR_EW | IR_EP)
-#define IR_ERR_LEC	(IR_STE	| IR_FOE | IR_ACKE | IR_BE | IR_CRCE)
-#define IR_ERR_BUS	(IR_ERR_LEC | IR_WDI | IR_ELO | IR_BEU | \
+
+/* Interrupts for version 3.0.x */
+#define IR_ERR_LEC_30X	(IR_STE	| IR_FOE | IR_ACKE | IR_BE | IR_CRCE)
+#define IR_ERR_BUS_30X	(IR_ERR_LEC_30X | IR_WDI | IR_ELO | IR_BEU | \
 			 IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
 			 IR_RF1L | IR_RF0L)
-#define IR_ERR_ALL	(IR_ERR_STATE | IR_ERR_BUS)
+#define IR_ERR_ALL_30X	(IR_ERR_STATE | IR_ERR_BUS_30X)
+/* Interrupts for version >= 3.1.x */
+#define IR_ERR_LEC_31X	(IR_PED | IR_PEA)
+#define IR_ERR_BUS_31X      (IR_ERR_LEC_31X | IR_WDI | IR_ELO | IR_BEU | \
+			 IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
+			 IR_RF1L | IR_RF0L)
+#define IR_ERR_ALL_31X	(IR_ERR_STATE | IR_ERR_BUS_31X)
 
 /* Interrupt Line Select (ILS) */
 #define ILS_ALL_INT0	0x0
 #define ILS_ALL_INT1	0xFFFFFFFF
 
 /* Interrupt Line Enable (ILE) */
-#define ILE_EINT0	BIT(0)
 #define ILE_EINT1	BIT(1)
+#define ILE_EINT0	BIT(0)
 
 /* Rx FIFO 0/1 Configuration (RXF0C/RXF1C) */
-#define RXFC_FWM_OFF	24
-#define RXFC_FWM_MASK	0x7f
-#define RXFC_FWM_1	(1 << RXFC_FWM_OFF)
-#define RXFC_FS_OFF	16
-#define RXFC_FS_MASK	0x7f
+#define RXFC_FWM_SHIFT	24
+#define RXFC_FWM_MASK	(0x7f < RXFC_FWM_SHIFT)
+#define RXFC_FS_SHIFT	16
+#define RXFC_FS_MASK	(0x7f << RXFC_FS_SHIFT)
 
 /* Rx FIFO 0/1 Status (RXF0S/RXF1S) */
 #define RXFS_RFL	BIT(25)
 #define RXFS_FF		BIT(24)
-#define RXFS_FPI_OFF	16
+#define RXFS_FPI_SHIFT	16
 #define RXFS_FPI_MASK	0x3f0000
-#define RXFS_FGI_OFF	8
+#define RXFS_FGI_SHIFT	8
 #define RXFS_FGI_MASK	0x3f00
 #define RXFS_FFL_MASK	0x7f
 
@@ -229,23 +264,46 @@ enum m_can_mram_cfg {
 #define M_CAN_RXESC_64BYTES	0x777
 
 /* Tx Buffer Configuration(TXBC) */
-#define TXBC_NDTB_OFF		16
-#define TXBC_NDTB_MASK		0x3f
+#define TXBC_NDTB_SHIFT		16
+#define TXBC_NDTB_MASK		(0x3f << TXBC_NDTB_SHIFT)
+#define TXBC_TFQS_SHIFT		24
+#define TXBC_TFQS_MASK		(0x3f << TXBC_TFQS_SHIFT)
+
+/* Tx FIFO/Queue Status (TXFQS) */
+#define TXFQS_TFQF		BIT(21)
+#define TXFQS_TFQPI_SHIFT	16
+#define TXFQS_TFQPI_MASK	(0x1f << TXFQS_TFQPI_SHIFT)
+#define TXFQS_TFGI_SHIFT	8
+#define TXFQS_TFGI_MASK		(0x1f << TXFQS_TFGI_SHIFT)
+#define TXFQS_TFFL_SHIFT	0
+#define TXFQS_TFFL_MASK		(0x3f << TXFQS_TFFL_SHIFT)
 
 /* Tx Buffer Element Size Configuration(TXESC) */
 #define TXESC_TBDS_8BYTES	0x0
 #define TXESC_TBDS_64BYTES	0x7
 
-/* Tx Event FIFO Con.guration (TXEFC) */
-#define TXEFC_EFS_OFF		16
-#define TXEFC_EFS_MASK		0x3f
+/* Tx Event FIFO Configuration (TXEFC) */
+#define TXEFC_EFS_SHIFT		16
+#define TXEFC_EFS_MASK		(0x3f << TXEFC_EFS_SHIFT)
+
+/* Tx Event FIFO Status (TXEFS) */
+#define TXEFS_TEFL		BIT(25)
+#define TXEFS_EFF		BIT(24)
+#define TXEFS_EFGI_SHIFT	8
+#define	TXEFS_EFGI_MASK		(0x1f << TXEFS_EFGI_SHIFT)
+#define TXEFS_EFFL_SHIFT	0
+#define TXEFS_EFFL_MASK		(0x3f << TXEFS_EFFL_SHIFT)
+
+/* Tx Event FIFO Acknowledge (TXEFA) */
+#define TXEFA_EFAI_SHIFT	0
+#define TXEFA_EFAI_MASK		(0x1f << TXEFA_EFAI_SHIFT)
 
 /* Message RAM Configuration (in bytes) */
 #define SIDF_ELEMENT_SIZE	4
 #define XIDF_ELEMENT_SIZE	8
 #define RXF0_ELEMENT_SIZE	72
 #define RXF1_ELEMENT_SIZE	72
-#define RXB_ELEMENT_SIZE	16
+#define RXB_ELEMENT_SIZE	72
 #define TXE_ELEMENT_SIZE	8
 #define TXB_ELEMENT_SIZE	72
 
@@ -261,13 +319,25 @@ enum m_can_mram_cfg {
 #define RX_BUF_RTR		BIT(29)
 /* R1 */
 #define RX_BUF_ANMF		BIT(31)
-#define RX_BUF_EDL		BIT(21)
+#define RX_BUF_FDF		BIT(21)
 #define RX_BUF_BRS		BIT(20)
 
 /* Tx Buffer Element */
-/* R0 */
+/* T0 */
+#define TX_BUF_ESI		BIT(31)
 #define TX_BUF_XTD		BIT(30)
 #define TX_BUF_RTR		BIT(29)
+/* T1 */
+#define TX_BUF_EFC		BIT(23)
+#define TX_BUF_FDF		BIT(21)
+#define TX_BUF_BRS		BIT(20)
+#define TX_BUF_MM_SHIFT		24
+#define TX_BUF_MM_MASK		(0xff << TX_BUF_MM_SHIFT)
+
+/* Tx event FIFO Element */
+/* E1 */
+#define TX_EVENT_MM_SHIFT	TX_BUF_MM_SHIFT
+#define TX_EVENT_MM_MASK	(0xff << TX_EVENT_MM_SHIFT)
 
 /* address offset and element number for each FIFO/Buffer in the Message RAM */
 struct mram_cfg {
@@ -285,6 +355,7 @@ struct m_can_priv {
 	struct clk *cclk;
 	void __iomem *base;
 	u32 irqstatus;
+	int version;
 
 	/* message ram configuration */
 	void __iomem *mram_base;
@@ -316,6 +387,18 @@ static inline void m_can_fifo_write(const struct m_can_priv *priv,
 	       fpi * TXB_ELEMENT_SIZE + offset);
 }
 
+static inline u32 m_can_txe_fifo_read(const struct m_can_priv *priv,
+				      u32 fgi,
+				      u32 offset) {
+	return readl(priv->mram_base + priv->mcfg[MRAM_TXE].off +
+			fgi * TXE_ELEMENT_SIZE + offset);
+}
+
+static inline bool m_can_tx_fifo_full(const struct m_can_priv *priv)
+{
+		return !!(m_can_read(priv, M_CAN_TXFQS) & TXFQS_TFQF);
+}
+
 static inline void m_can_config_endisable(const struct m_can_priv *priv,
 					  bool enable)
 {
@@ -349,7 +432,8 @@ static inline void m_can_config_endisable(const struct m_can_priv *priv,
 
 static inline void m_can_enable_all_interrupts(const struct m_can_priv *priv)
 {
-	m_can_write(priv, M_CAN_ILE, ILE_EINT0 | ILE_EINT1);
+	/* Only interrupt line 0 is used in this driver */
+	m_can_write(priv, M_CAN_ILE, ILE_EINT0);
 }
 
 static inline void m_can_disable_all_interrupts(const struct m_can_priv *priv)
@@ -367,9 +451,9 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	int i;
 
 	/* calculate the fifo get index for where to read data */
-	fgi = (rxfs & RXFS_FGI_MASK) >> RXFS_FGI_OFF;
+	fgi = (rxfs & RXFS_FGI_MASK) >> RXFS_FGI_SHIFT;
 	dlc = m_can_fifo_read(priv, fgi, M_CAN_FIFO_DLC);
-	if (dlc & RX_BUF_EDL)
+	if (dlc & RX_BUF_FDF)
 		skb = alloc_canfd_skb(dev, &cf);
 	else
 		skb = alloc_can_skb(dev, (struct can_frame **)&cf);
@@ -378,7 +462,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 		return;
 	}
 
-	if (dlc & RX_BUF_EDL)
+	if (dlc & RX_BUF_FDF)
 		cf->len = can_dlc2len((dlc >> 16) & 0x0F);
 	else
 		cf->len = get_can_dlc((dlc >> 16) & 0x0F);
@@ -394,7 +478,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 		netdev_dbg(dev, "ESI Error\n");
 	}
 
-	if (!(dlc & RX_BUF_EDL) && (id & RX_BUF_RTR)) {
+	if (!(dlc & RX_BUF_FDF) && (id & RX_BUF_RTR)) {
 		cf->can_id |= CAN_RTR_FLAG;
 	} else {
 		if (dlc & RX_BUF_BRS)
@@ -532,7 +616,7 @@ static int __m_can_get_berr_counter(const struct net_device *dev,
 
 	ecr = m_can_read(priv, M_CAN_ECR);
 	bec->rxerr = (ecr & ECR_REC_MASK) >> ECR_REC_SHIFT;
-	bec->txerr = ecr & ECR_TEC_MASK;
+	bec->txerr = (ecr & ECR_TEC_MASK) >> ECR_TEC_SHIFT;
 
 	return 0;
 }
@@ -723,7 +807,7 @@ static int m_can_poll(struct napi_struct *napi, int quota)
 	if (irqstatus & IR_ERR_STATE)
 		work_done += m_can_handle_state_errors(dev, psr);
 
-	if (irqstatus & IR_ERR_BUS)
+	if (irqstatus & IR_ERR_BUS_30X)
 		work_done += m_can_handle_bus_errors(dev, irqstatus, psr);
 
 	if (irqstatus & IR_RF0N)
@@ -738,6 +822,44 @@ end:
 	return work_done;
 }
 
+static void m_can_echo_tx_event(struct net_device *dev)
+{
+	u32 txe_count = 0;
+	u32 m_can_txefs;
+	u32 fgi = 0;
+	int i = 0;
+	unsigned int msg_mark;
+
+	struct m_can_priv *priv = netdev_priv(dev);
+	struct net_device_stats *stats = &dev->stats;
+
+	/* read tx event fifo status */
+	m_can_txefs = m_can_read(priv, M_CAN_TXEFS);
+
+	/* Get Tx Event fifo element count */
+	txe_count = (m_can_txefs & TXEFS_EFFL_MASK)
+			>> TXEFS_EFFL_SHIFT;
+
+	/* Get and process all sent elements */
+	for (i = 0; i < txe_count; i++) {
+		/* retrieve get index */
+		fgi = (m_can_read(priv, M_CAN_TXEFS) & TXEFS_EFGI_MASK)
+			>> TXEFS_EFGI_SHIFT;
+
+		/* get message marker */
+		msg_mark = (m_can_txe_fifo_read(priv, fgi, 4) &
+			    TX_EVENT_MM_MASK) >> TX_EVENT_MM_SHIFT;
+
+		/* ack txe element */
+		m_can_write(priv, M_CAN_TXEFA, (TXEFA_EFAI_MASK &
+						(fgi << TXEFA_EFAI_SHIFT)));
+
+		/* update stats */
+		stats->tx_bytes += can_get_echo_skb(dev, msg_mark);
+		stats->tx_packets++;
+	}
+}
+
 static irqreturn_t m_can_isr(int irq, void *dev_id)
 {
 	struct net_device *dev = (struct net_device *)dev_id;
@@ -758,24 +880,35 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 	 * - state change IRQ
 	 * - bus error IRQ and bus error reporting
 	 */
-	if ((ir & IR_RF0N) || (ir & IR_ERR_ALL)) {
+	if ((ir & IR_RF0N) || (ir & IR_ERR_ALL_30X)) {
 		priv->irqstatus = ir;
 		m_can_disable_all_interrupts(priv);
 		napi_schedule(&priv->napi);
 	}
 
-	/* transmission complete interrupt */
-	if (ir & IR_TC) {
-		stats->tx_bytes += can_get_echo_skb(dev, 0);
-		stats->tx_packets++;
-		can_led_event(dev, CAN_LED_EVENT_TX);
-		netif_wake_queue(dev);
+	if (priv->version == 30) {
+		if (ir & IR_TC) {
+			/* Transmission Complete Interrupt*/
+			stats->tx_bytes += can_get_echo_skb(dev, 0);
+			stats->tx_packets++;
+			can_led_event(dev, CAN_LED_EVENT_TX);
+			netif_wake_queue(dev);
+		}
+	} else  {
+		if (ir & IR_TEFN) {
+			/* New TX FIFO Element arrived */
+			m_can_echo_tx_event(dev);
+			can_led_event(dev, CAN_LED_EVENT_TX);
+			if (netif_queue_stopped(dev) &&
+			    !m_can_tx_fifo_full(priv))
+				netif_wake_queue(dev);
+		}
 	}
 
 	return IRQ_HANDLED;
 }
 
-static const struct can_bittiming_const m_can_bittiming_const = {
+static const struct can_bittiming_const m_can_bittiming_const_30X = {
 	.name = KBUILD_MODNAME,
 	.tseg1_min = 2,		/* Time segment 1 = prop_seg + phase_seg1 */
 	.tseg1_max = 64,
@@ -787,7 +920,7 @@ static const struct can_bittiming_const m_can_bittiming_const = {
 	.brp_inc = 1,
 };
 
-static const struct can_bittiming_const m_can_data_bittiming_const = {
+static const struct can_bittiming_const m_can_data_bittiming_const_30X = {
 	.name = KBUILD_MODNAME,
 	.tseg1_min = 2,		/* Time segment 1 = prop_seg + phase_seg1 */
 	.tseg1_max = 16,
@@ -799,6 +932,30 @@ static const struct can_bittiming_const m_can_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const m_can_bittiming_const_31X = {
+	.name = KBUILD_MODNAME,
+	.tseg1_min = 2,		/* Time segment 1 = prop_seg + phase_seg1 */
+	.tseg1_max = 256,
+	.tseg2_min = 1,		/* Time segment 2 = phase_seg2 */
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const m_can_data_bittiming_const_31X = {
+	.name = KBUILD_MODNAME,
+	.tseg1_min = 1,		/* Time segment 1 = prop_seg + phase_seg1 */
+	.tseg1_max = 32,
+	.tseg2_min = 1,		/* Time segment 2 = phase_seg2 */
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 32,
+	.brp_inc = 1,
+};
+
 static int m_can_set_bittiming(struct net_device *dev)
 {
 	struct m_can_priv *priv = netdev_priv(dev);
@@ -811,19 +968,19 @@ static int m_can_set_bittiming(struct net_device *dev)
 	sjw = bt->sjw - 1;
 	tseg1 = bt->prop_seg + bt->phase_seg1 - 1;
 	tseg2 = bt->phase_seg2 - 1;
-	reg_btp = (brp << BTR_BRP_SHIFT) | (sjw << BTR_SJW_SHIFT) |
-			(tseg1 << BTR_TSEG1_SHIFT) | (tseg2 << BTR_TSEG2_SHIFT);
-	m_can_write(priv, M_CAN_BTP, reg_btp);
+	reg_btp = (brp << NBTP_NBRP_SHIFT) | (sjw << NBTP_NSJW_SHIFT) |
+		(tseg1 << NBTP_NTSEG1_SHIFT) | (tseg2 << NBTP_NTSEG2_SHIFT);
+	m_can_write(priv, M_CAN_NBTP, reg_btp);
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
 		brp = dbt->brp - 1;
 		sjw = dbt->sjw - 1;
 		tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1;
 		tseg2 = dbt->phase_seg2 - 1;
-		reg_btp = (brp << FBTR_FBRP_SHIFT) | (sjw << FBTR_FSJW_SHIFT) |
-				(tseg1 << FBTR_FTSEG1_SHIFT) |
-				(tseg2 << FBTR_FTSEG2_SHIFT);
-		m_can_write(priv, M_CAN_FBTP, reg_btp);
+		reg_btp = (brp << DBTP_DBRP_SHIFT) | (sjw << DBTP_DSJW_SHIFT) |
+			(tseg1 << DBTP_DTSEG1_SHIFT) |
+			(tseg2 << DBTP_DTSEG2_SHIFT);
+		m_can_write(priv, M_CAN_DBTP, reg_btp);
 	}
 
 	return 0;
@@ -834,6 +991,7 @@ static int m_can_set_bittiming(struct net_device *dev)
  * - configure rx fifo
  * - accept non-matching frame into fifo 0
  * - configure tx buffer
+ *		- >= v3.1.x: TX FIFO is used
  * - configure mode
  * - setup bittiming
  */
@@ -850,49 +1008,89 @@ static void m_can_chip_config(struct net_device *dev)
 	/* Accept Non-matching Frames Into FIFO 0 */
 	m_can_write(priv, M_CAN_GFC, 0x0);
 
-	/* only support one Tx Buffer currently */
-	m_can_write(priv, M_CAN_TXBC, (1 << TXBC_NDTB_OFF) |
-		    priv->mcfg[MRAM_TXB].off);
+	if (priv->version == 30) {
+		/* only support one Tx Buffer currently */
+		m_can_write(priv, M_CAN_TXBC, (1 << TXBC_NDTB_SHIFT) |
+				priv->mcfg[MRAM_TXB].off);
+	} else {
+		/* TX FIFO is used for newer IP Core versions */
+		m_can_write(priv, M_CAN_TXBC,
+			    (priv->mcfg[MRAM_TXB].num << TXBC_TFQS_SHIFT) |
+			    (priv->mcfg[MRAM_TXB].off));
+	}
 
 	/* support 64 bytes payload */
 	m_can_write(priv, M_CAN_TXESC, TXESC_TBDS_64BYTES);
 
-	m_can_write(priv, M_CAN_TXEFC, (1 << TXEFC_EFS_OFF) |
-		    priv->mcfg[MRAM_TXE].off);
+	/* TX Event FIFO */
+	if (priv->version == 30) {
+		m_can_write(priv, M_CAN_TXEFC, (1 << TXEFC_EFS_SHIFT) |
+				priv->mcfg[MRAM_TXE].off);
+	} else {
+		/* Full TX Event FIFO is used */
+		m_can_write(priv, M_CAN_TXEFC,
+			    ((priv->mcfg[MRAM_TXE].num << TXEFC_EFS_SHIFT)
+			     & TXEFC_EFS_MASK) |
+			    priv->mcfg[MRAM_TXE].off);
+	}
 
 	/* rx fifo configuration, blocking mode, fifo size 1 */
 	m_can_write(priv, M_CAN_RXF0C,
-		    (priv->mcfg[MRAM_RXF0].num << RXFC_FS_OFF) |
-		    RXFC_FWM_1 | priv->mcfg[MRAM_RXF0].off);
+		    (priv->mcfg[MRAM_RXF0].num << RXFC_FS_SHIFT) |
+		     priv->mcfg[MRAM_RXF0].off);
 
 	m_can_write(priv, M_CAN_RXF1C,
-		    (priv->mcfg[MRAM_RXF1].num << RXFC_FS_OFF) |
-		    RXFC_FWM_1 | priv->mcfg[MRAM_RXF1].off);
+		    (priv->mcfg[MRAM_RXF1].num << RXFC_FS_SHIFT) |
+		     priv->mcfg[MRAM_RXF1].off);
 
 	cccr = m_can_read(priv, M_CAN_CCCR);
-	cccr &= ~(CCCR_TEST | CCCR_MON | (CCCR_CMR_MASK << CCCR_CMR_SHIFT) |
-		(CCCR_CME_MASK << CCCR_CME_SHIFT));
 	test = m_can_read(priv, M_CAN_TEST);
 	test &= ~TEST_LBCK;
+	if (priv->version == 30) {
+	/* Version 3.0.x */
 
-	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
-		cccr |= CCCR_MON;
+		cccr &= ~(CCCR_TEST | CCCR_MON |
+			(CCCR_CMR_MASK << CCCR_CMR_SHIFT) |
+			(CCCR_CME_MASK << CCCR_CME_SHIFT));
+
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+			cccr |= CCCR_CME_CANFD_BRS << CCCR_CME_SHIFT;
+
+	} else {
+	/* Version 3.1.x or 3.2.x */
+		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE);
 
+		/* Only 3.2.x has NISO Bit implemented */
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
+			cccr |= CCCR_NISO;
+
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+			cccr |= (CCCR_BRSE | CCCR_FDOE);
+	}
+
+	/* Loopback Mode */
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) {
-		cccr |= CCCR_TEST;
+		cccr |= CCCR_TEST | CCCR_MON;
 		test |= TEST_LBCK;
 	}
 
-	if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
-		cccr |= CCCR_CME_CANFD_BRS << CCCR_CME_SHIFT;
+	/* Enable Monitoring (all versions) */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		cccr |= CCCR_MON;
 
+	/* Write config */
 	m_can_write(priv, M_CAN_CCCR, cccr);
 	m_can_write(priv, M_CAN_TEST, test);
 
-	/* enable interrupts */
+	/* Enable interrupts */
 	m_can_write(priv, M_CAN_IR, IR_ALL_INT);
 	if (!(priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING))
-		m_can_write(priv, M_CAN_IE, IR_ALL_INT & ~IR_ERR_LEC);
+		if (priv->version == 30)
+			m_can_write(priv, M_CAN_IE, IR_ALL_INT &
+				    ~(IR_ERR_LEC_30X));
+		else
+			m_can_write(priv, M_CAN_IE, IR_ALL_INT &
+				    ~(IR_ERR_LEC_31X));
 	else
 		m_can_write(priv, M_CAN_IE, IR_ALL_INT);
 
@@ -936,33 +1134,140 @@ static void free_m_can_dev(struct net_device *dev)
 	free_candev(dev);
 }
 
-static struct net_device *alloc_m_can_dev(void)
+/* Checks core release number of M_CAN
+ * returns 0 if an unsupported device is detected
+ * else it returns the release and step coded as:
+ * return value = 10 * <release> + 1 * <step>
+ */
+static int m_can_check_core_release(void __iomem *m_can_base)
+{
+	u32 crel_reg;
+	u8 rel;
+	u8 step;
+	int res;
+	struct m_can_priv temp_priv = {
+		.base = m_can_base
+	};
+
+	/* Read Core Release Version and split into version number
+	 * Example: Version 3.2.1 => rel = 3; step = 2; substep = 1;
+	 */
+	crel_reg = m_can_read(&temp_priv, M_CAN_CREL);
+	rel = (u8)((crel_reg & CREL_REL_MASK) >> CREL_REL_SHIFT);
+	step = (u8)((crel_reg & CREL_STEP_MASK) >> CREL_STEP_SHIFT);
+
+	if (rel == 3) {
+		/* M_CAN v3.x.y: create return value */
+		res = 30 + step;
+	} else {
+		/* Unsupported M_CAN version */
+		res = 0;
+	}
+
+	return res;
+}
+
+/* Selectable Non ISO support only in version 3.2.x
+ * This function checks if the bit is writable.
+ */
+static bool m_can_niso_supported(const struct m_can_priv *priv)
+{
+	u32 cccr_reg, cccr_poll;
+	int niso_timeout;
+
+	m_can_config_endisable(priv, true);
+	cccr_reg = m_can_read(priv, M_CAN_CCCR);
+	cccr_reg |= CCCR_NISO;
+	m_can_write(priv, M_CAN_CCCR, cccr_reg);
+
+	niso_timeout = readl_poll_timeout((priv->base + M_CAN_CCCR), cccr_poll,
+					  (cccr_poll == cccr_reg), 0, 10);
+
+	/* Clear NISO */
+	cccr_reg &= ~(CCCR_NISO);
+	m_can_write(priv, M_CAN_CCCR, cccr_reg);
+
+	m_can_config_endisable(priv, false);
+
+	/* return false if time out (-ETIMEDOUT), else return true */
+	return !niso_timeout;
+}
+
+static struct net_device *alloc_m_can_dev(struct platform_device *pdev,
+					  void __iomem *addr, u32 tx_fifo_size)
 {
 	struct net_device *dev;
 	struct m_can_priv *priv;
+	int m_can_version;
+	unsigned int echo_buffer_count;
+
+	m_can_version = m_can_check_core_release(addr);
+	/* return if unsupported version */
+	if (!m_can_version) {
+		dev = NULL;
+		goto return_dev;
+	}
 
-	dev = alloc_candev(sizeof(*priv), 1);
-	if (!dev)
-		return NULL;
+	/* If version < 3.1.x, then only one echo buffer is used */
+	echo_buffer_count = ((m_can_version == 30)
+				? 1U
+				: (unsigned int)tx_fifo_size);
 
+	dev = alloc_candev(sizeof(*priv), echo_buffer_count);
+	if (!dev) {
+		dev = NULL;
+		goto return_dev;
+	}
 	priv = netdev_priv(dev);
 	netif_napi_add(dev, &priv->napi, m_can_poll, M_CAN_NAPI_WEIGHT);
 
+	/* Shared properties of all M_CAN versions */
+	priv->version = m_can_version;
 	priv->dev = dev;
-	priv->can.bittiming_const = &m_can_bittiming_const;
-	priv->can.data_bittiming_const = &m_can_data_bittiming_const;
+	priv->base = addr;
 	priv->can.do_set_mode = m_can_set_mode;
 	priv->can.do_get_berr_counter = m_can_get_berr_counter;
 
-	/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.1 */
-	can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
-
-	/* CAN_CTRLMODE_FD_NON_ISO can not be changed with M_CAN IP v3.0.1 */
+	/* Set M_CAN supported operations */
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 					CAN_CTRLMODE_LISTENONLY |
 					CAN_CTRLMODE_BERR_REPORTING |
 					CAN_CTRLMODE_FD;
 
+	/* Set properties depending on M_CAN version */
+	switch (priv->version) {
+	case 30:
+		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */
+		can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
+		priv->can.bittiming_const = &m_can_bittiming_const_30X;
+		priv->can.data_bittiming_const =
+				&m_can_data_bittiming_const_30X;
+		break;
+	case 31:
+		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */
+		can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
+		priv->can.bittiming_const = &m_can_bittiming_const_31X;
+		priv->can.data_bittiming_const =
+				&m_can_data_bittiming_const_31X;
+		break;
+	case 32:
+		priv->can.bittiming_const = &m_can_bittiming_const_31X;
+		priv->can.data_bittiming_const =
+				&m_can_data_bittiming_const_31X;
+		priv->can.ctrlmode_supported |= (m_can_niso_supported(priv)
+						? CAN_CTRLMODE_FD_NON_ISO
+						: 0);
+		break;
+	default:
+		/* Unsupported device: free candev */
+		free_m_can_dev(dev);
+		dev_err(&pdev->dev, "Unsupported version number: %2d",
+			priv->version);
+		dev = NULL;
+		break;
+	}
+
+return_dev:
 	return dev;
 }
 
@@ -1040,19 +1345,34 @@ static int m_can_close(struct net_device *dev)
 	return 0;
 }
 
+static int m_can_next_echo_skb_occupied(struct net_device *dev, int putidx)
+{
+	struct m_can_priv *priv = netdev_priv(dev);
+	/*get wrap around for loopback skb index */
+	unsigned int wrap = priv->can.echo_skb_max;
+	int next_idx;
+
+	/* calculate next index */
+	next_idx = (++putidx >= wrap ? 0 : putidx);
+
+	/* check if occupied */
+	return !!priv->can.echo_skb[next_idx];
+}
+
 static netdev_tx_t m_can_start_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
 	struct m_can_priv *priv = netdev_priv(dev);
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
-	u32 id, cccr;
+	u32 id, cccr, fdflags;
 	int i;
+	int putidx;
 
 	if (can_dropped_invalid_skb(dev, skb))
 		return NETDEV_TX_OK;
 
-	netif_stop_queue(dev);
-
+	/* Generate ID field for TX buffer Element */
+	/* Common to all supported M_CAN versions */
 	if (cf->can_id & CAN_EFF_FLAG) {
 		id = cf->can_id & CAN_EFF_MASK;
 		id |= TX_BUF_XTD;
@@ -1063,33 +1383,93 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb,
 	if (cf->can_id & CAN_RTR_FLAG)
 		id |= TX_BUF_RTR;
 
-	/* message ram configuration */
-	m_can_fifo_write(priv, 0, M_CAN_FIFO_ID, id);
-	m_can_fifo_write(priv, 0, M_CAN_FIFO_DLC, can_len2dlc(cf->len) << 16);
+	if (priv->version == 30) {
+		netif_stop_queue(dev);
 
-	for (i = 0; i < cf->len; i += 4)
-		m_can_fifo_write(priv, 0, M_CAN_FIFO_DATA(i / 4),
-				 *(u32 *)(cf->data + i));
+		/* message ram configuration */
+		m_can_fifo_write(priv, 0, M_CAN_FIFO_ID, id);
+		m_can_fifo_write(priv, 0, M_CAN_FIFO_DLC,
+				 can_len2dlc(cf->len) << 16);
 
-	can_put_echo_skb(skb, dev, 0);
+		for (i = 0; i < cf->len; i += 4)
+			m_can_fifo_write(priv, 0,
+					 M_CAN_FIFO_DATA(i / 4),
+					 *(u32 *)(cf->data + i));
+
+		can_put_echo_skb(skb, dev, 0);
+
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+			cccr = m_can_read(priv, M_CAN_CCCR);
+			cccr &= ~(CCCR_CMR_MASK << CCCR_CMR_SHIFT);
+			if (can_is_canfd_skb(skb)) {
+				if (cf->flags & CANFD_BRS)
+					cccr |= CCCR_CMR_CANFD_BRS <<
+						CCCR_CMR_SHIFT;
+				else
+					cccr |= CCCR_CMR_CANFD <<
+						CCCR_CMR_SHIFT;
+			} else {
+				cccr |= CCCR_CMR_CAN << CCCR_CMR_SHIFT;
+			}
+			m_can_write(priv, M_CAN_CCCR, cccr);
+		}
+		m_can_write(priv, M_CAN_TXBTIE, 0x1);
+		m_can_write(priv, M_CAN_TXBAR, 0x1);
+		/* End of xmit function for version 3.0.x */
+	} else {
+		/* Transmit routine for version >= v3.1.x */
+
+		/* Check if FIFO full */
+		if (m_can_tx_fifo_full(priv)) {
+			/* This shouldn't happen */
+			netif_stop_queue(dev);
+			netdev_warn(dev,
+				    "TX queue active although FIFO is full.");
+			return NETDEV_TX_BUSY;
+		}
 
-	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
-		cccr = m_can_read(priv, M_CAN_CCCR);
-		cccr &= ~(CCCR_CMR_MASK << CCCR_CMR_SHIFT);
+		/* get put index for frame */
+		putidx = ((m_can_read(priv, M_CAN_TXFQS) & TXFQS_TFQPI_MASK)
+				  >> TXFQS_TFQPI_SHIFT);
+		/* Write ID Field to FIFO Element */
+		m_can_fifo_write(priv, putidx, M_CAN_FIFO_ID, id);
+
+		/* get CAN FD configuration of frame */
+		fdflags = 0;
 		if (can_is_canfd_skb(skb)) {
+			fdflags |= TX_BUF_FDF;
 			if (cf->flags & CANFD_BRS)
-				cccr |= CCCR_CMR_CANFD_BRS << CCCR_CMR_SHIFT;
-			else
-				cccr |= CCCR_CMR_CANFD << CCCR_CMR_SHIFT;
-		} else {
-			cccr |= CCCR_CMR_CAN << CCCR_CMR_SHIFT;
+				fdflags |= TX_BUF_BRS;
 		}
-		m_can_write(priv, M_CAN_CCCR, cccr);
-	}
 
-	/* enable first TX buffer to start transfer  */
-	m_can_write(priv, M_CAN_TXBTIE, 0x1);
-	m_can_write(priv, M_CAN_TXBAR, 0x1);
+		/* Construct DLC Field. Also contains CAN-FD configuration
+		 * use put index of fifo as message marker
+		 * it is used in TX interrupt for
+		 * sending the correct echo frame
+		 */
+		m_can_fifo_write(priv, putidx, M_CAN_FIFO_DLC,
+				 ((putidx << TX_BUF_MM_SHIFT) &
+				  TX_BUF_MM_MASK) |
+				 (can_len2dlc(cf->len) << 16) |
+				 fdflags | TX_BUF_EFC);
+
+		for (i = 0; i < cf->len; i += 4)
+			m_can_fifo_write(priv, putidx, M_CAN_FIFO_DATA(i / 4),
+					 *(u32 *)(cf->data + i));
+
+		/* Push loopback echo.
+		 * Will be looped back on TX interrupt based on message marker
+		 */
+		can_put_echo_skb(skb, dev, putidx);
+
+		/* Enable TX FIFO element to start transfer  */
+		m_can_write(priv, M_CAN_TXBAR, (1 << putidx));
+
+		/* stop network queue if fifo full */
+			if (m_can_tx_fifo_full(priv) ||
+			    m_can_next_echo_skb_occupied(dev, putidx))
+				netif_stop_queue(dev);
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -1109,55 +1489,37 @@ static int register_m_can_dev(struct net_device *dev)
 	return register_candev(dev);
 }
 
-static int m_can_of_parse_mram(struct platform_device *pdev,
-			       struct m_can_priv *priv)
+static void m_can_of_parse_mram(struct m_can_priv *priv,
+				const u32 *mram_config_vals)
 {
-	struct device_node *np = pdev->dev.of_node;
-	struct resource *res;
-	void __iomem *addr;
-	u32 out_val[MRAM_CFG_LEN];
-	int i, start, end, ret;
+	int i, start, end;
 
-	/* message ram could be shared */
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram");
-	if (!res)
-		return -ENODEV;
-
-	addr = devm_ioremap(&pdev->dev, res->start, resource_size(res));
-	if (!addr)
-		return -ENOMEM;
-
-	/* get message ram configuration */
-	ret = of_property_read_u32_array(np, "bosch,mram-cfg",
-					 out_val, sizeof(out_val) / 4);
-	if (ret) {
-		dev_err(&pdev->dev, "can not get message ram configuration\n");
-		return -ENODEV;
-	}
-
-	priv->mram_base = addr;
-	priv->mcfg[MRAM_SIDF].off = out_val[0];
-	priv->mcfg[MRAM_SIDF].num = out_val[1];
+	priv->mcfg[MRAM_SIDF].off = mram_config_vals[0];
+	priv->mcfg[MRAM_SIDF].num = mram_config_vals[1];
 	priv->mcfg[MRAM_XIDF].off = priv->mcfg[MRAM_SIDF].off +
 			priv->mcfg[MRAM_SIDF].num * SIDF_ELEMENT_SIZE;
-	priv->mcfg[MRAM_XIDF].num = out_val[2];
+	priv->mcfg[MRAM_XIDF].num = mram_config_vals[2];
 	priv->mcfg[MRAM_RXF0].off = priv->mcfg[MRAM_XIDF].off +
 			priv->mcfg[MRAM_XIDF].num * XIDF_ELEMENT_SIZE;
-	priv->mcfg[MRAM_RXF0].num = out_val[3] & RXFC_FS_MASK;
+	priv->mcfg[MRAM_RXF0].num = mram_config_vals[3] &
+			(RXFC_FS_MASK >> RXFC_FS_SHIFT);
 	priv->mcfg[MRAM_RXF1].off = priv->mcfg[MRAM_RXF0].off +
 			priv->mcfg[MRAM_RXF0].num * RXF0_ELEMENT_SIZE;
-	priv->mcfg[MRAM_RXF1].num = out_val[4] & RXFC_FS_MASK;
+	priv->mcfg[MRAM_RXF1].num = mram_config_vals[4] &
+			(RXFC_FS_MASK >> RXFC_FS_SHIFT);
 	priv->mcfg[MRAM_RXB].off = priv->mcfg[MRAM_RXF1].off +
 			priv->mcfg[MRAM_RXF1].num * RXF1_ELEMENT_SIZE;
-	priv->mcfg[MRAM_RXB].num = out_val[5];
+	priv->mcfg[MRAM_RXB].num = mram_config_vals[5];
 	priv->mcfg[MRAM_TXE].off = priv->mcfg[MRAM_RXB].off +
 			priv->mcfg[MRAM_RXB].num * RXB_ELEMENT_SIZE;
-	priv->mcfg[MRAM_TXE].num = out_val[6];
+	priv->mcfg[MRAM_TXE].num = mram_config_vals[6];
 	priv->mcfg[MRAM_TXB].off = priv->mcfg[MRAM_TXE].off +
 			priv->mcfg[MRAM_TXE].num * TXE_ELEMENT_SIZE;
-	priv->mcfg[MRAM_TXB].num = out_val[7] & TXBC_NDTB_MASK;
+	priv->mcfg[MRAM_TXB].num = mram_config_vals[7] &
+			(TXBC_NDTB_MASK >> TXBC_NDTB_SHIFT);
 
-	dev_dbg(&pdev->dev, "mram_base %p sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n",
+	dev_dbg(priv->device,
+		"mram_base %p sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n",
 		priv->mram_base,
 		priv->mcfg[MRAM_SIDF].off, priv->mcfg[MRAM_SIDF].num,
 		priv->mcfg[MRAM_XIDF].off, priv->mcfg[MRAM_XIDF].num,
@@ -1176,7 +1538,6 @@ static int m_can_of_parse_mram(struct platform_device *pdev,
 	for (i = start; i < end; i += 4)
 		writel(0x0, priv->mram_base + i);
 
-	return 0;
 }
 
 static int m_can_plat_probe(struct platform_device *pdev)
@@ -1185,38 +1546,86 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	struct m_can_priv *priv;
 	struct resource *res;
 	void __iomem *addr;
+	void __iomem *mram_addr;
 	struct clk *hclk, *cclk;
 	int irq, ret;
+	struct device_node *np;
+	u32 mram_config_vals[MRAM_CFG_LEN];
+	u32 tx_fifo_size;
+
+	np = pdev->dev.of_node;
 
 	hclk = devm_clk_get(&pdev->dev, "hclk");
 	cclk = devm_clk_get(&pdev->dev, "cclk");
+
 	if (IS_ERR(hclk) || IS_ERR(cclk)) {
-		dev_err(&pdev->dev, "no clock find\n");
-		return -ENODEV;
+		dev_err(&pdev->dev, "no clock found\n");
+		ret = -ENODEV;
+		goto failed_ret;
 	}
 
+	/* Enable clocks. Necessary to read Core Release in order to determine
+	 * M_CAN version
+	 */
+	ret = clk_prepare_enable(hclk);
+	if (ret)
+		goto disable_hclk_ret;
+
+	ret = clk_prepare_enable(cclk);
+	if (ret)
+		goto disable_cclk_ret;
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can");
 	addr = devm_ioremap_resource(&pdev->dev, res);
 	irq = platform_get_irq_byname(pdev, "int0");
-	if (IS_ERR(addr) || irq < 0)
-		return -EINVAL;
 
-	/* allocate the m_can device */
-	dev = alloc_m_can_dev();
-	if (!dev)
-		return -ENOMEM;
+	if (IS_ERR(addr) || irq < 0) {
+		ret = -EINVAL;
+		goto disable_cclk_ret;
+	}
+
+	/* message ram could be shared */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram");
+	if (!res) {
+		ret = -ENODEV;
+		goto disable_cclk_ret;
+	}
+
+	mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+	if (!mram_addr) {
+		ret = -ENOMEM;
+		goto disable_cclk_ret;
+	}
+
+	/* get message ram configuration */
+	ret = of_property_read_u32_array(np, "bosch,mram-cfg",
+					 mram_config_vals,
+					 sizeof(mram_config_vals) / 4);
+	if (ret) {
+		dev_err(&pdev->dev, "Could not get Message RAM configuration.");
+		goto disable_cclk_ret;
+	}
 
+	/* Get TX FIFO size
+	 * Defines the total amount of echo buffers for loopback
+	 */
+	tx_fifo_size = mram_config_vals[7];
+
+	/* allocate the m_can device */
+	dev = alloc_m_can_dev(pdev, addr, tx_fifo_size);
+	if (!dev) {
+		ret = -ENOMEM;
+		goto disable_cclk_ret;
+	}
 	priv = netdev_priv(dev);
 	dev->irq = irq;
-	priv->base = addr;
 	priv->device = &pdev->dev;
 	priv->hclk = hclk;
 	priv->cclk = cclk;
 	priv->can.clock.freq = clk_get_rate(cclk);
+	priv->mram_base = mram_addr;
 
-	ret = m_can_of_parse_mram(pdev, priv);
-	if (ret)
-		goto failed_free_dev;
+	m_can_of_parse_mram(priv, mram_config_vals);
 
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
@@ -1230,13 +1639,22 @@ static int m_can_plat_probe(struct platform_device *pdev)
 
 	devm_can_led_init(dev);
 
-	dev_info(&pdev->dev, "%s device registered (regs=%p, irq=%d)\n",
-		 KBUILD_MODNAME, priv->base, dev->irq);
+	dev_info(&pdev->dev, "%s device registered (irq=%d, version=%d)\n",
+		 KBUILD_MODNAME, dev->irq, priv->version);
 
-	return 0;
+	/* Probe finished
+	 * Stop clocks. They will be reactivated once the M_CAN device is opened
+	 */
+
+	goto disable_cclk_ret;
 
 failed_free_dev:
 	free_m_can_dev(dev);
+disable_cclk_ret:
+	clk_disable_unprepare(cclk);
+disable_hclk_ret:
+	clk_disable_unprepare(hclk);
+failed_ret:
 	return ret;
 }
 
diff --git a/drivers/net/can/peak_canfd/Kconfig b/drivers/net/can/peak_canfd/Kconfig
new file mode 100644
index 000000000000..84b30978a19f
--- /dev/null
+++ b/drivers/net/can/peak_canfd/Kconfig
@@ -0,0 +1,13 @@
+config CAN_PEAK_PCIEFD
+	depends on PCI
+	tristate "PEAK-System PCAN-PCIe FD cards"
+	---help---
+	  This driver adds support for the PEAK-System PCI Express FD
+	  CAN-FD cards family.
+	  These 1x or 2x CAN-FD channels cards offer CAN 2.0 a/b as well as
+	  CAN-FD access to the CAN bus. Besides the nominal bitrate of up to
+	  1 Mbit/s, the data bytes of CAN-FD frames can be transmitted with
+	  up to 12 Mbit/s. A galvanic isolation of the CAN ports protects the
+	  electronics of the card and the respective computer against
+	  disturbances of up to 500 Volts. The PCAN-PCI Express FD can be
+	  operated with ambient temperatures in a range of -40 to +85 °C.
diff --git a/drivers/net/can/peak_canfd/Makefile b/drivers/net/can/peak_canfd/Makefile
new file mode 100644
index 000000000000..3dc7a6a0ba59
--- /dev/null
+++ b/drivers/net/can/peak_canfd/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the PEAK-System CAN-FD IP module drivers
+#
+obj-$(CONFIG_CAN_PEAK_PCIEFD) += peak_pciefd.o
+peak_pciefd-y := peak_pciefd_main.o peak_canfd.o
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
new file mode 100644
index 000000000000..0d57be5ea97b
--- /dev/null
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -0,0 +1,801 @@
+/*
+ * Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ * Copyright (C) 2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ *
+ * Copyright (C) 2016  PEAK System-Technik GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+
+#include "peak_canfd_user.h"
+
+/* internal IP core cache size (used as default echo skbs max number) */
+#define PCANFD_ECHO_SKB_MAX		24
+
+/* bittiming ranges of the PEAK-System PC CAN-FD interfaces */
+static const struct can_bittiming_const peak_canfd_nominal_const = {
+	.name = "peak_canfd",
+	.tseg1_min = 1,
+	.tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS),
+	.tseg2_min = 1,
+	.tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS),
+	.sjw_max = (1 << PUCAN_TSLOW_SJW_BITS),
+	.brp_min = 1,
+	.brp_max = (1 << PUCAN_TSLOW_BRP_BITS),
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const peak_canfd_data_const = {
+	.name = "peak_canfd",
+	.tseg1_min = 1,
+	.tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS),
+	.tseg2_min = 1,
+	.tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS),
+	.sjw_max = (1 << PUCAN_TFAST_SJW_BITS),
+	.brp_min = 1,
+	.brp_max = (1 << PUCAN_TFAST_BRP_BITS),
+	.brp_inc = 1,
+};
+
+static struct peak_canfd_priv *pucan_init_cmd(struct peak_canfd_priv *priv)
+{
+	priv->cmd_len = 0;
+	return priv;
+}
+
+static void *pucan_add_cmd(struct peak_canfd_priv *priv, int cmd_op)
+{
+	struct pucan_command *cmd;
+
+	if (priv->cmd_len + sizeof(*cmd) > priv->cmd_maxlen)
+		return NULL;
+
+	cmd = priv->cmd_buffer + priv->cmd_len;
+
+	/* reset all unused bit to default */
+	memset(cmd, 0, sizeof(*cmd));
+
+	cmd->opcode_channel = pucan_cmd_opcode_channel(priv->index, cmd_op);
+	priv->cmd_len += sizeof(*cmd);
+
+	return cmd;
+}
+
+static int pucan_write_cmd(struct peak_canfd_priv *priv)
+{
+	int err;
+
+	if (priv->pre_cmd) {
+		err = priv->pre_cmd(priv);
+		if (err)
+			return err;
+	}
+
+	err = priv->write_cmd(priv);
+	if (err)
+		return err;
+
+	if (priv->post_cmd)
+		err = priv->post_cmd(priv);
+
+	return err;
+}
+
+/* uCAN commands interface functions */
+static int pucan_set_reset_mode(struct peak_canfd_priv *priv)
+{
+	pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_RESET_MODE);
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_set_normal_mode(struct peak_canfd_priv *priv)
+{
+	int err;
+
+	pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_NORMAL_MODE);
+	err = pucan_write_cmd(priv);
+	if (!err)
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	return err;
+}
+
+static int pucan_set_listen_only_mode(struct peak_canfd_priv *priv)
+{
+	int err;
+
+	pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_LISTEN_ONLY_MODE);
+	err = pucan_write_cmd(priv);
+	if (!err)
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	return err;
+}
+
+static int pucan_set_timing_slow(struct peak_canfd_priv *priv,
+				 const struct can_bittiming *pbt)
+{
+	struct pucan_timing_slow *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_TIMING_SLOW);
+
+	cmd->sjw_t = PUCAN_TSLOW_SJW_T(pbt->sjw - 1,
+				priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES);
+	cmd->tseg1 = PUCAN_TSLOW_TSEG1(pbt->prop_seg + pbt->phase_seg1 - 1);
+	cmd->tseg2 = PUCAN_TSLOW_TSEG2(pbt->phase_seg2 - 1);
+	cmd->brp = cpu_to_le16(PUCAN_TSLOW_BRP(pbt->brp - 1));
+
+	cmd->ewl = 96;	/* default */
+
+	netdev_dbg(priv->ndev,
+		   "nominal: brp=%u tseg1=%u tseg2=%u sjw=%u\n",
+		   le16_to_cpu(cmd->brp), cmd->tseg1, cmd->tseg2, cmd->sjw_t);
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_set_timing_fast(struct peak_canfd_priv *priv,
+				 const struct can_bittiming *pbt)
+{
+	struct pucan_timing_fast *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_TIMING_FAST);
+
+	cmd->sjw = PUCAN_TFAST_SJW(pbt->sjw - 1);
+	cmd->tseg1 = PUCAN_TFAST_TSEG1(pbt->prop_seg + pbt->phase_seg1 - 1);
+	cmd->tseg2 = PUCAN_TFAST_TSEG2(pbt->phase_seg2 - 1);
+	cmd->brp = cpu_to_le16(PUCAN_TFAST_BRP(pbt->brp - 1));
+
+	netdev_dbg(priv->ndev,
+		   "data: brp=%u tseg1=%u tseg2=%u sjw=%u\n",
+		   le16_to_cpu(cmd->brp), cmd->tseg1, cmd->tseg2, cmd->sjw);
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_set_std_filter(struct peak_canfd_priv *priv, u8 row, u32 mask)
+{
+	struct pucan_std_filter *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_SET_STD_FILTER);
+
+	/* all the 11-bits CAN ID values are represented by one bit in a
+	 * 64 rows array of 32 bits: the upper 6 bits of the CAN ID select the
+	 * row while the lowest 5 bits select the bit in that row.
+	 *
+	 * bit	filter
+	 * 1	passed
+	 * 0	discarded
+	 */
+
+	/* select the row */
+	cmd->idx = row;
+
+	/* set/unset bits in the row */
+	cmd->mask = cpu_to_le32(mask);
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_tx_abort(struct peak_canfd_priv *priv, u16 flags)
+{
+	struct pucan_tx_abort *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_TX_ABORT);
+
+	cmd->flags = cpu_to_le16(flags);
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_clr_err_counters(struct peak_canfd_priv *priv)
+{
+	struct pucan_wr_err_cnt *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_WR_ERR_CNT);
+
+	cmd->sel_mask = cpu_to_le16(PUCAN_WRERRCNT_TE | PUCAN_WRERRCNT_RE);
+	cmd->tx_counter = 0;
+	cmd->rx_counter = 0;
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_set_options(struct peak_canfd_priv *priv, u16 opt_mask)
+{
+	struct pucan_options *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_SET_EN_OPTION);
+
+	cmd->options = cpu_to_le16(opt_mask);
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_clr_options(struct peak_canfd_priv *priv, u16 opt_mask)
+{
+	struct pucan_options *cmd;
+
+	cmd = pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_CLR_DIS_OPTION);
+
+	cmd->options = cpu_to_le16(opt_mask);
+
+	return pucan_write_cmd(priv);
+}
+
+static int pucan_setup_rx_barrier(struct peak_canfd_priv *priv)
+{
+	pucan_add_cmd(pucan_init_cmd(priv), PUCAN_CMD_RX_BARRIER);
+
+	return pucan_write_cmd(priv);
+}
+
+/* handle the reception of one CAN frame */
+static int pucan_handle_can_rx(struct peak_canfd_priv *priv,
+			       struct pucan_rx_msg *msg)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct canfd_frame *cf;
+	struct sk_buff *skb;
+	const u16 rx_msg_flags = le16_to_cpu(msg->flags);
+	u8 cf_len;
+
+	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN)
+		cf_len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(msg)));
+	else
+		cf_len = get_can_dlc(pucan_msg_get_dlc(msg));
+
+	/* if this frame is an echo, */
+	if ((rx_msg_flags & PUCAN_MSG_LOOPED_BACK) &&
+	    !(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE)) {
+		int n;
+		unsigned long flags;
+
+		spin_lock_irqsave(&priv->echo_lock, flags);
+		n = can_get_echo_skb(priv->ndev, msg->client);
+		spin_unlock_irqrestore(&priv->echo_lock, flags);
+
+		/* count bytes of the echo instead of skb */
+		stats->tx_bytes += cf_len;
+		stats->tx_packets++;
+
+		if (n) {
+			/* restart tx queue only if a slot is free */
+			netif_wake_queue(priv->ndev);
+		}
+
+		return 0;
+	}
+
+	/* otherwise, it should be pushed into rx fifo */
+	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) {
+		/* CANFD frame case */
+		skb = alloc_canfd_skb(priv->ndev, &cf);
+		if (!skb)
+			return -ENOMEM;
+
+		if (rx_msg_flags & PUCAN_MSG_BITRATE_SWITCH)
+			cf->flags |= CANFD_BRS;
+
+		if (rx_msg_flags & PUCAN_MSG_ERROR_STATE_IND)
+			cf->flags |= CANFD_ESI;
+	} else {
+		/* CAN 2.0 frame case */
+		skb = alloc_can_skb(priv->ndev, (struct can_frame **)&cf);
+		if (!skb)
+			return -ENOMEM;
+	}
+
+	cf->can_id = le32_to_cpu(msg->can_id);
+	cf->len = cf_len;
+
+	if (rx_msg_flags & PUCAN_MSG_EXT_ID)
+		cf->can_id |= CAN_EFF_FLAG;
+
+	if (rx_msg_flags & PUCAN_MSG_RTR)
+		cf->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(cf->data, msg->d, cf->len);
+
+	stats->rx_bytes += cf->len;
+	stats->rx_packets++;
+
+	netif_rx(skb);
+
+	return 0;
+}
+
+/* handle rx/tx error counters notification */
+static int pucan_handle_error(struct peak_canfd_priv *priv,
+			      struct pucan_error_msg *msg)
+{
+	priv->bec.txerr = msg->tx_err_cnt;
+	priv->bec.rxerr = msg->rx_err_cnt;
+
+	return 0;
+}
+
+/* handle status notification */
+static int pucan_handle_status(struct peak_canfd_priv *priv,
+			       struct pucan_status_msg *msg)
+{
+	struct net_device *ndev = priv->ndev;
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	/* this STATUS is the CNF of the RX_BARRIER: Tx path can be setup */
+	if (pucan_status_is_rx_barrier(msg)) {
+		unsigned long flags;
+
+		if (priv->enable_tx_path) {
+			int err = priv->enable_tx_path(priv);
+
+			if (err)
+				return err;
+		}
+
+		/* restart network queue only if echo skb array is free */
+		spin_lock_irqsave(&priv->echo_lock, flags);
+
+		if (!priv->can.echo_skb[priv->echo_idx]) {
+			spin_unlock_irqrestore(&priv->echo_lock, flags);
+
+			netif_wake_queue(ndev);
+		} else {
+			spin_unlock_irqrestore(&priv->echo_lock, flags);
+		}
+
+		return 0;
+	}
+
+	skb = alloc_can_err_skb(ndev, &cf);
+
+	/* test state error bits according to their priority */
+	if (pucan_status_is_busoff(msg)) {
+		netdev_dbg(ndev, "Bus-off entry status\n");
+		priv->can.state = CAN_STATE_BUS_OFF;
+		priv->can.can_stats.bus_off++;
+		can_bus_off(ndev);
+		if (skb)
+			cf->can_id |= CAN_ERR_BUSOFF;
+
+	} else if (pucan_status_is_passive(msg)) {
+		netdev_dbg(ndev, "Error passive status\n");
+		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+		priv->can.can_stats.error_passive++;
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] = (priv->bec.txerr > priv->bec.rxerr) ?
+					CAN_ERR_CRTL_TX_PASSIVE :
+					CAN_ERR_CRTL_RX_PASSIVE;
+			cf->data[6] = priv->bec.txerr;
+			cf->data[7] = priv->bec.rxerr;
+		}
+
+	} else if (pucan_status_is_warning(msg)) {
+		netdev_dbg(ndev, "Error warning status\n");
+		priv->can.state = CAN_STATE_ERROR_WARNING;
+		priv->can.can_stats.error_warning++;
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] = (priv->bec.txerr > priv->bec.rxerr) ?
+					CAN_ERR_CRTL_TX_WARNING :
+					CAN_ERR_CRTL_RX_WARNING;
+			cf->data[6] = priv->bec.txerr;
+			cf->data[7] = priv->bec.rxerr;
+		}
+
+	} else if (priv->can.state != CAN_STATE_ERROR_ACTIVE) {
+		/* back to ERROR_ACTIVE */
+		netdev_dbg(ndev, "Error active status\n");
+		can_change_state(ndev, cf, CAN_STATE_ERROR_ACTIVE,
+				 CAN_STATE_ERROR_ACTIVE);
+	} else {
+		dev_kfree_skb(skb);
+		return 0;
+	}
+
+	if (!skb) {
+		stats->rx_dropped++;
+		return -ENOMEM;
+	}
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+
+	return 0;
+}
+
+/* handle uCAN Rx overflow notification */
+static int pucan_handle_cache_critical(struct peak_canfd_priv *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	stats->rx_over_errors++;
+	stats->rx_errors++;
+
+	skb = alloc_can_err_skb(priv->ndev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return -ENOMEM;
+	}
+
+	cf->can_id |= CAN_ERR_CRTL;
+	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+
+	cf->data[6] = priv->bec.txerr;
+	cf->data[7] = priv->bec.rxerr;
+
+	stats->rx_bytes += cf->can_dlc;
+	stats->rx_packets++;
+	netif_rx(skb);
+
+	return 0;
+}
+
+/* handle a single uCAN message */
+int peak_canfd_handle_msg(struct peak_canfd_priv *priv,
+			  struct pucan_rx_msg *msg)
+{
+	u16 msg_type = le16_to_cpu(msg->type);
+	int msg_size = le16_to_cpu(msg->size);
+	int err;
+
+	if (!msg_size || !msg_type) {
+		/* null packet found: end of list */
+		goto exit;
+	}
+
+	switch (msg_type) {
+	case PUCAN_MSG_CAN_RX:
+		err = pucan_handle_can_rx(priv, (struct pucan_rx_msg *)msg);
+		break;
+	case PUCAN_MSG_ERROR:
+		err = pucan_handle_error(priv, (struct pucan_error_msg *)msg);
+		break;
+	case PUCAN_MSG_STATUS:
+		err = pucan_handle_status(priv, (struct pucan_status_msg *)msg);
+		break;
+	case PUCAN_MSG_CACHE_CRITICAL:
+		err = pucan_handle_cache_critical(priv);
+		break;
+	default:
+		err = 0;
+	}
+
+	if (err < 0)
+		return err;
+
+exit:
+	return msg_size;
+}
+
+/* handle a list of rx_count messages from rx_msg memory address */
+int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv,
+				struct pucan_rx_msg *msg_list, int msg_count)
+{
+	void *msg_ptr = msg_list;
+	int i, msg_size;
+
+	for (i = 0; i < msg_count; i++) {
+		msg_size = peak_canfd_handle_msg(priv, msg_ptr);
+
+		/* a null packet can be found at the end of a list */
+		if (msg_size <= 0)
+			break;
+
+		msg_ptr += msg_size;
+	}
+
+	if (msg_size < 0)
+		return msg_size;
+
+	return i;
+}
+
+static int peak_canfd_start(struct peak_canfd_priv *priv)
+{
+	int err;
+
+	err = pucan_clr_err_counters(priv);
+	if (err)
+		goto err_exit;
+
+	priv->echo_idx = 0;
+
+	priv->bec.txerr = 0;
+	priv->bec.rxerr = 0;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		err = pucan_set_listen_only_mode(priv);
+	else
+		err = pucan_set_normal_mode(priv);
+
+err_exit:
+	return err;
+}
+
+static void peak_canfd_stop(struct peak_canfd_priv *priv)
+{
+	int err;
+
+	/* go back to RESET mode */
+	err = pucan_set_reset_mode(priv);
+	if (err) {
+		netdev_err(priv->ndev, "channel %u reset failed\n",
+			   priv->index);
+	} else {
+		/* abort last Tx (MUST be done in RESET mode only!) */
+		pucan_tx_abort(priv, PUCAN_TX_ABORT_FLUSH);
+	}
+}
+
+static int peak_canfd_set_mode(struct net_device *ndev, enum can_mode mode)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+
+	switch (mode) {
+	case CAN_MODE_START:
+		peak_canfd_start(priv);
+		netif_wake_queue(ndev);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int peak_canfd_get_berr_counter(const struct net_device *ndev,
+				       struct can_berr_counter *bec)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+
+	*bec = priv->bec;
+	return 0;
+}
+
+static int peak_canfd_open(struct net_device *ndev)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+	int i, err = 0;
+
+	err = open_candev(ndev);
+	if (err) {
+		netdev_err(ndev, "open_candev() failed, error %d\n", err);
+		goto err_exit;
+	}
+
+	err = pucan_set_reset_mode(priv);
+	if (err)
+		goto err_close;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
+			err = pucan_clr_options(priv, PUCAN_OPTION_CANDFDISO);
+		else
+			err = pucan_set_options(priv, PUCAN_OPTION_CANDFDISO);
+
+		if (err)
+			goto err_close;
+	}
+
+	/* set option: get rx/tx error counters */
+	err = pucan_set_options(priv, PUCAN_OPTION_ERROR);
+	if (err)
+		goto err_close;
+
+	/* accept all standard CAN ID */
+	for (i = 0; i <= PUCAN_FLTSTD_ROW_IDX_MAX; i++)
+		pucan_set_std_filter(priv, i, 0xffffffff);
+
+	err = peak_canfd_start(priv);
+	if (err)
+		goto err_close;
+
+	/* receiving the RB status says when Tx path is ready */
+	err = pucan_setup_rx_barrier(priv);
+	if (!err)
+		goto err_exit;
+
+err_close:
+	close_candev(ndev);
+err_exit:
+	return err;
+}
+
+static int peak_canfd_set_bittiming(struct net_device *ndev)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+
+	return pucan_set_timing_slow(priv, &priv->can.bittiming);
+}
+
+static int peak_canfd_set_data_bittiming(struct net_device *ndev)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+
+	return pucan_set_timing_fast(priv, &priv->can.data_bittiming);
+}
+
+static int peak_canfd_close(struct net_device *ndev)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	peak_canfd_stop(priv);
+	close_candev(ndev);
+
+	return 0;
+}
+
+static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
+					 struct net_device *ndev)
+{
+	struct peak_canfd_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
+	struct pucan_tx_msg *msg;
+	u16 msg_size, msg_flags;
+	unsigned long flags;
+	bool should_stop_tx_queue;
+	int room_left;
+	u8 can_dlc;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	msg_size = ALIGN(sizeof(*msg) + cf->len, 4);
+	msg = priv->alloc_tx_msg(priv, msg_size, &room_left);
+
+	/* should never happen except under bus-off condition and (auto-)restart
+	 * mechanism
+	 */
+	if (!msg) {
+		stats->tx_dropped++;
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
+	msg->size = cpu_to_le16(msg_size);
+	msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX);
+	msg_flags = 0;
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		msg_flags |= PUCAN_MSG_EXT_ID;
+		msg->can_id = cpu_to_le32(cf->can_id & CAN_EFF_MASK);
+	} else {
+		msg->can_id = cpu_to_le32(cf->can_id & CAN_SFF_MASK);
+	}
+
+	if (can_is_canfd_skb(skb)) {
+		/* CAN FD frame format */
+		can_dlc = can_len2dlc(cf->len);
+
+		msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
+
+		if (cf->flags & CANFD_BRS)
+			msg_flags |= PUCAN_MSG_BITRATE_SWITCH;
+
+		if (cf->flags & CANFD_ESI)
+			msg_flags |= PUCAN_MSG_ERROR_STATE_IND;
+	} else {
+		/* CAN 2.0 frame format */
+		can_dlc = cf->len;
+
+		if (cf->can_id & CAN_RTR_FLAG)
+			msg_flags |= PUCAN_MSG_RTR;
+	}
+
+	/* always ask loopback for echo management */
+	msg_flags |= PUCAN_MSG_LOOPED_BACK;
+
+	/* set driver specific bit to differentiate with application loopback */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		msg_flags |= PUCAN_MSG_SELF_RECEIVE;
+
+	msg->flags = cpu_to_le16(msg_flags);
+	msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(priv->index, can_dlc);
+	memcpy(msg->d, cf->data, cf->len);
+
+	/* struct msg client field is used as an index in the echo skbs ring */
+	msg->client = priv->echo_idx;
+
+	spin_lock_irqsave(&priv->echo_lock, flags);
+
+	/* prepare and save echo skb in internal slot */
+	can_put_echo_skb(skb, ndev, priv->echo_idx);
+
+	/* move echo index to the next slot */
+	priv->echo_idx = (priv->echo_idx + 1) % priv->can.echo_skb_max;
+
+	/* if next slot is not free, stop network queue (no slot free in echo
+	 * skb ring means that the controller did not write these frames on
+	 * the bus: no need to continue).
+	 */
+	should_stop_tx_queue = !!(priv->can.echo_skb[priv->echo_idx]);
+
+	spin_unlock_irqrestore(&priv->echo_lock, flags);
+
+	/* write the skb on the interface */
+	priv->write_tx_msg(priv, msg);
+
+	/* stop network tx queue if not enough room to save one more msg too */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+		should_stop_tx_queue |= (room_left <
+					(sizeof(*msg) + CANFD_MAX_DLEN));
+	else
+		should_stop_tx_queue |= (room_left <
+					(sizeof(*msg) + CAN_MAX_DLEN));
+
+	if (should_stop_tx_queue)
+		netif_stop_queue(ndev);
+
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops peak_canfd_netdev_ops = {
+	.ndo_open = peak_canfd_open,
+	.ndo_stop = peak_canfd_close,
+	.ndo_start_xmit = peak_canfd_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+struct net_device *alloc_peak_canfd_dev(int sizeof_priv, int index,
+					int echo_skb_max)
+{
+	struct net_device *ndev;
+	struct peak_canfd_priv *priv;
+
+	/* we DO support local echo */
+	if (echo_skb_max < 0)
+		echo_skb_max = PCANFD_ECHO_SKB_MAX;
+
+	/* allocate the candev object */
+	ndev = alloc_candev(sizeof_priv, echo_skb_max);
+	if (!ndev)
+		return NULL;
+
+	priv = netdev_priv(ndev);
+
+	/* complete now socket-can initialization side */
+	priv->can.state = CAN_STATE_STOPPED;
+	priv->can.bittiming_const = &peak_canfd_nominal_const;
+	priv->can.data_bittiming_const = &peak_canfd_data_const;
+
+	priv->can.do_set_mode = peak_canfd_set_mode;
+	priv->can.do_get_berr_counter = peak_canfd_get_berr_counter;
+	priv->can.do_set_bittiming = peak_canfd_set_bittiming;
+	priv->can.do_set_data_bittiming = peak_canfd_set_data_bittiming;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
+				       CAN_CTRLMODE_LISTENONLY |
+				       CAN_CTRLMODE_3_SAMPLES |
+				       CAN_CTRLMODE_FD |
+				       CAN_CTRLMODE_FD_NON_ISO |
+				       CAN_CTRLMODE_BERR_REPORTING;
+
+	priv->ndev = ndev;
+	priv->index = index;
+	priv->cmd_len = 0;
+	spin_lock_init(&priv->echo_lock);
+
+	ndev->flags |= IFF_ECHO;
+	ndev->netdev_ops = &peak_canfd_netdev_ops;
+	ndev->dev_id = index;
+
+	return ndev;
+}
diff --git a/drivers/net/can/peak_canfd/peak_canfd_user.h b/drivers/net/can/peak_canfd/peak_canfd_user.h
new file mode 100644
index 000000000000..bf6de47f69c2
--- /dev/null
+++ b/drivers/net/can/peak_canfd/peak_canfd_user.h
@@ -0,0 +1,55 @@
+/*
+ * CAN driver for PEAK System micro-CAN based adapters
+ *
+ * Copyright (C) 2003-2011 PEAK System-Technik GmbH
+ * Copyright (C) 2011-2013 Stephane Grosjean <s.grosjean@peak-system.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef PEAK_CANFD_USER_H
+#define PEAK_CANFD_USER_H
+
+#include <linux/can/dev/peak_canfd.h>
+
+#define PCANFD_ECHO_SKB_DEF		-1
+
+/* data structure private to each uCAN interface */
+struct peak_canfd_priv {
+	struct can_priv can;		/* socket-can private data */
+	struct net_device *ndev;	/* network device */
+	int index;			/* channel index */
+
+	struct can_berr_counter bec;	/* rx/tx err counters */
+
+	int echo_idx;			/* echo skb free slot index */
+	spinlock_t echo_lock;
+
+	int cmd_len;
+	void *cmd_buffer;
+	int cmd_maxlen;
+
+	int (*pre_cmd)(struct peak_canfd_priv *priv);
+	int (*write_cmd)(struct peak_canfd_priv *priv);
+	int (*post_cmd)(struct peak_canfd_priv *priv);
+
+	int (*enable_tx_path)(struct peak_canfd_priv *priv);
+	void *(*alloc_tx_msg)(struct peak_canfd_priv *priv, u16 msg_size,
+			      int *room_left);
+	int (*write_tx_msg)(struct peak_canfd_priv *priv,
+			    struct pucan_tx_msg *msg);
+};
+
+struct net_device *alloc_peak_canfd_dev(int sizeof_priv, int index,
+					int echo_skb_max);
+int peak_canfd_handle_msg(struct peak_canfd_priv *priv,
+			  struct pucan_rx_msg *msg);
+int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv,
+				struct pucan_rx_msg *rx_msg, int rx_count);
+#endif
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
new file mode 100644
index 000000000000..51c2d182a33a
--- /dev/null
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -0,0 +1,842 @@
+/*
+ * Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ * Copyright (C) 2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ *
+ * Derived from the PCAN project file driver/src/pcan_pci.c:
+ *
+ * Copyright (C) 2001-2006  PEAK System-Technik GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/io.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+
+#include "peak_canfd_user.h"
+
+MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
+MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe FD family cards");
+MODULE_SUPPORTED_DEVICE("PEAK PCAN PCIe FD CAN cards");
+MODULE_LICENSE("GPL v2");
+
+#define PCIEFD_DRV_NAME		"peak_pciefd"
+
+#define PEAK_PCI_VENDOR_ID	0x001c	/* The PCI device and vendor IDs */
+#define PEAK_PCIEFD_ID		0x0013	/* for PCIe slot cards */
+
+/* PEAK PCIe board access description */
+#define PCIEFD_BAR0_SIZE		(64 * 1024)
+#define PCIEFD_RX_DMA_SIZE		(4 * 1024)
+#define PCIEFD_TX_DMA_SIZE		(4 * 1024)
+
+#define PCIEFD_TX_PAGE_SIZE		(2 * 1024)
+
+/* System Control Registers */
+#define PCIEFD_REG_SYS_CTL_SET		0x0000	/* set bits */
+#define PCIEFD_REG_SYS_CTL_CLR		0x0004	/* clear bits */
+
+/* Version info registers */
+#define PCIEFD_REG_SYS_VER1		0x0040	/* version reg #1 */
+#define PCIEFD_REG_SYS_VER2		0x0044	/* version reg #2 */
+
+/* System Control Registers Bits */
+#define PCIEFD_SYS_CTL_TS_RST		0x00000001	/* timestamp clock */
+#define PCIEFD_SYS_CTL_CLK_EN		0x00000002	/* system clock */
+
+/* CAN-FD channel addresses */
+#define PCIEFD_CANX_OFF(c)		(((c) + 1) * 0x1000)
+
+#define PCIEFD_ECHO_SKB_MAX		PCANFD_ECHO_SKB_DEF
+
+/* CAN-FD channel registers */
+#define PCIEFD_REG_CAN_MISC		0x0000	/* Misc. control */
+#define PCIEFD_REG_CAN_CLK_SEL		0x0008	/* Clock selector */
+#define PCIEFD_REG_CAN_CMD_PORT_L	0x0010	/* 64-bits command port */
+#define PCIEFD_REG_CAN_CMD_PORT_H	0x0014
+#define PCIEFD_REG_CAN_TX_REQ_ACC	0x0020	/* Tx request accumulator */
+#define PCIEFD_REG_CAN_TX_CTL_SET	0x0030	/* Tx control set register */
+#define PCIEFD_REG_CAN_TX_CTL_CLR	0x0038	/* Tx control clear register */
+#define PCIEFD_REG_CAN_TX_DMA_ADDR_L	0x0040	/* 64-bits addr for Tx DMA */
+#define PCIEFD_REG_CAN_TX_DMA_ADDR_H	0x0044
+#define PCIEFD_REG_CAN_RX_CTL_SET	0x0050	/* Rx control set register */
+#define PCIEFD_REG_CAN_RX_CTL_CLR	0x0058	/* Rx control clear register */
+#define PCIEFD_REG_CAN_RX_CTL_WRT	0x0060	/* Rx control write register */
+#define PCIEFD_REG_CAN_RX_CTL_ACK	0x0068	/* Rx control ACK register */
+#define PCIEFD_REG_CAN_RX_DMA_ADDR_L	0x0070	/* 64-bits addr for Rx DMA */
+#define PCIEFD_REG_CAN_RX_DMA_ADDR_H	0x0074
+
+/* CAN-FD channel misc register bits */
+#define CANFD_MISC_TS_RST		0x00000001	/* timestamp cnt rst */
+
+/* CAN-FD channel Clock SELector Source & DIVider */
+#define CANFD_CLK_SEL_DIV_MASK		0x00000007
+#define CANFD_CLK_SEL_DIV_60MHZ		0x00000000	/* SRC=240MHz only */
+#define CANFD_CLK_SEL_DIV_40MHZ		0x00000001	/* SRC=240MHz only */
+#define CANFD_CLK_SEL_DIV_30MHZ		0x00000002	/* SRC=240MHz only */
+#define CANFD_CLK_SEL_DIV_24MHZ		0x00000003	/* SRC=240MHz only */
+#define CANFD_CLK_SEL_DIV_20MHZ		0x00000004	/* SRC=240MHz only */
+
+#define CANFD_CLK_SEL_SRC_MASK		0x00000008	/* 0=80MHz, 1=240MHz */
+#define CANFD_CLK_SEL_SRC_240MHZ	0x00000008
+#define CANFD_CLK_SEL_SRC_80MHZ		(~CANFD_CLK_SEL_SRC_240MHZ & \
+							CANFD_CLK_SEL_SRC_MASK)
+
+#define CANFD_CLK_SEL_20MHZ		(CANFD_CLK_SEL_SRC_240MHZ |\
+						CANFD_CLK_SEL_DIV_20MHZ)
+#define CANFD_CLK_SEL_24MHZ		(CANFD_CLK_SEL_SRC_240MHZ |\
+						CANFD_CLK_SEL_DIV_24MHZ)
+#define CANFD_CLK_SEL_30MHZ		(CANFD_CLK_SEL_SRC_240MHZ |\
+						CANFD_CLK_SEL_DIV_30MHZ)
+#define CANFD_CLK_SEL_40MHZ		(CANFD_CLK_SEL_SRC_240MHZ |\
+						CANFD_CLK_SEL_DIV_40MHZ)
+#define CANFD_CLK_SEL_60MHZ		(CANFD_CLK_SEL_SRC_240MHZ |\
+						CANFD_CLK_SEL_DIV_60MHZ)
+#define CANFD_CLK_SEL_80MHZ		(CANFD_CLK_SEL_SRC_80MHZ)
+
+/* CAN-FD channel Rx/Tx control register bits */
+#define CANFD_CTL_UNC_BIT		0x00010000	/* Uncached DMA mem */
+#define CANFD_CTL_RST_BIT		0x00020000	/* reset DMA action */
+#define CANFD_CTL_IEN_BIT		0x00040000	/* IRQ enable */
+
+/* Rx IRQ Count and Time Limits */
+#define CANFD_CTL_IRQ_CL_DEF	16	/* Rx msg max nb per IRQ in Rx DMA */
+#define CANFD_CTL_IRQ_TL_DEF	10	/* Time before IRQ if < CL (x100 µs) */
+
+#define CANFD_OPTIONS_SET	(CANFD_OPTION_ERROR | CANFD_OPTION_BUSLOAD)
+
+/* Tx anticipation window (link logical address should be aligned on 2K
+ * boundary)
+ */
+#define PCIEFD_TX_PAGE_COUNT	(PCIEFD_TX_DMA_SIZE / PCIEFD_TX_PAGE_SIZE)
+
+#define CANFD_MSG_LNK_TX	0x1001	/* Tx msgs link */
+
+/* 32-bits IRQ status fields, heading Rx DMA area */
+static inline int pciefd_irq_tag(u32 irq_status)
+{
+	return irq_status & 0x0000000f;
+}
+
+static inline int pciefd_irq_rx_cnt(u32 irq_status)
+{
+	return (irq_status & 0x000007f0) >> 4;
+}
+
+static inline int pciefd_irq_is_lnk(u32 irq_status)
+{
+	return irq_status & 0x00010000;
+}
+
+/* Rx record */
+struct pciefd_rx_dma {
+	__le32 irq_status;
+	__le32 sys_time_low;
+	__le32 sys_time_high;
+	struct pucan_rx_msg msg[0];
+} __packed __aligned(4);
+
+/* Tx Link record */
+struct pciefd_tx_link {
+	__le16 size;
+	__le16 type;
+	__le32 laddr_lo;
+	__le32 laddr_hi;
+} __packed __aligned(4);
+
+/* Tx page descriptor */
+struct pciefd_page {
+	void *vbase;			/* page virtual address */
+	dma_addr_t lbase;		/* page logical address */
+	u32 offset;
+	u32 size;
+};
+
+#define CANFD_IRQ_SET		0x00000001
+#define CANFD_TX_PATH_SET	0x00000002
+
+/* CAN-FD channel object */
+struct pciefd_board;
+struct pciefd_can {
+	struct peak_canfd_priv ucan;	/* must be the first member */
+	void __iomem *reg_base;		/* channel config base addr */
+	struct pciefd_board *board;	/* reverse link */
+
+	struct pucan_command pucan_cmd;	/* command buffer */
+
+	dma_addr_t rx_dma_laddr;	/* DMA virtual and logical addr */
+	void *rx_dma_vaddr;		/* for Rx and Tx areas */
+	dma_addr_t tx_dma_laddr;
+	void *tx_dma_vaddr;
+
+	struct pciefd_page tx_pages[PCIEFD_TX_PAGE_COUNT];
+	u16 tx_pages_free;		/* free Tx pages counter */
+	u16 tx_page_index;		/* current page used for Tx */
+	spinlock_t tx_lock;
+
+	u32 irq_status;
+	u32 irq_tag;				/* next irq tag */
+};
+
+/* PEAK-PCIe FD board object */
+struct pciefd_board {
+	void __iomem *reg_base;
+	struct pci_dev *pci_dev;
+	int can_count;
+	spinlock_t cmd_lock;		/* 64-bits cmds must be atomic */
+	struct pciefd_can *can[0];	/* array of network devices */
+};
+
+/* supported device ids. */
+static const struct pci_device_id peak_pciefd_tbl[] = {
+	{PEAK_PCI_VENDOR_ID, PEAK_PCIEFD_ID, PCI_ANY_ID, PCI_ANY_ID,},
+	{0,}
+};
+
+MODULE_DEVICE_TABLE(pci, peak_pciefd_tbl);
+
+/* read a 32 bits value from a SYS block register */
+static inline u32 pciefd_sys_readreg(const struct pciefd_board *priv, u16 reg)
+{
+	return readl(priv->reg_base + reg);
+}
+
+/* write a 32 bits value into a SYS block register */
+static inline void pciefd_sys_writereg(const struct pciefd_board *priv,
+				       u32 val, u16 reg)
+{
+	writel(val, priv->reg_base + reg);
+}
+
+/* read a 32 bits value from CAN-FD block register */
+static inline u32 pciefd_can_readreg(const struct pciefd_can *priv, u16 reg)
+{
+	return readl(priv->reg_base + reg);
+}
+
+/* write a 32 bits value into a CAN-FD block register */
+static inline void pciefd_can_writereg(const struct pciefd_can *priv,
+				       u32 val, u16 reg)
+{
+	writel(val, priv->reg_base + reg);
+}
+
+/* give a channel logical Rx DMA address to the board */
+static void pciefd_can_setup_rx_dma(struct pciefd_can *priv)
+{
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	const u32 dma_addr_h = (u32)(priv->rx_dma_laddr >> 32);
+#else
+	const u32 dma_addr_h = 0;
+#endif
+
+	/* (DMA must be reset for Rx) */
+	pciefd_can_writereg(priv, CANFD_CTL_RST_BIT, PCIEFD_REG_CAN_RX_CTL_SET);
+
+	/* write the logical address of the Rx DMA area for this channel */
+	pciefd_can_writereg(priv, (u32)priv->rx_dma_laddr,
+			    PCIEFD_REG_CAN_RX_DMA_ADDR_L);
+	pciefd_can_writereg(priv, dma_addr_h, PCIEFD_REG_CAN_RX_DMA_ADDR_H);
+
+	/* also indicates that Rx DMA is cacheable */
+	pciefd_can_writereg(priv, CANFD_CTL_UNC_BIT, PCIEFD_REG_CAN_RX_CTL_CLR);
+}
+
+/* clear channel logical Rx DMA address from the board */
+static void pciefd_can_clear_rx_dma(struct pciefd_can *priv)
+{
+	/* DMA must be reset for Rx */
+	pciefd_can_writereg(priv, CANFD_CTL_RST_BIT, PCIEFD_REG_CAN_RX_CTL_SET);
+
+	/* clear the logical address of the Rx DMA area for this channel */
+	pciefd_can_writereg(priv, 0, PCIEFD_REG_CAN_RX_DMA_ADDR_L);
+	pciefd_can_writereg(priv, 0, PCIEFD_REG_CAN_RX_DMA_ADDR_H);
+}
+
+/* give a channel logical Tx DMA address to the board */
+static void pciefd_can_setup_tx_dma(struct pciefd_can *priv)
+{
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	const u32 dma_addr_h = (u32)(priv->tx_dma_laddr >> 32);
+#else
+	const u32 dma_addr_h = 0;
+#endif
+
+	/* (DMA must be reset for Tx) */
+	pciefd_can_writereg(priv, CANFD_CTL_RST_BIT, PCIEFD_REG_CAN_TX_CTL_SET);
+
+	/* write the logical address of the Tx DMA area for this channel */
+	pciefd_can_writereg(priv, (u32)priv->tx_dma_laddr,
+			    PCIEFD_REG_CAN_TX_DMA_ADDR_L);
+	pciefd_can_writereg(priv, dma_addr_h, PCIEFD_REG_CAN_TX_DMA_ADDR_H);
+
+	/* also indicates that Tx DMA is cacheable */
+	pciefd_can_writereg(priv, CANFD_CTL_UNC_BIT, PCIEFD_REG_CAN_TX_CTL_CLR);
+}
+
+/* clear channel logical Tx DMA address from the board */
+static void pciefd_can_clear_tx_dma(struct pciefd_can *priv)
+{
+	/* DMA must be reset for Tx */
+	pciefd_can_writereg(priv, CANFD_CTL_RST_BIT, PCIEFD_REG_CAN_TX_CTL_SET);
+
+	/* clear the logical address of the Tx DMA area for this channel */
+	pciefd_can_writereg(priv, 0, PCIEFD_REG_CAN_TX_DMA_ADDR_L);
+	pciefd_can_writereg(priv, 0, PCIEFD_REG_CAN_TX_DMA_ADDR_H);
+}
+
+static void pciefd_can_ack_rx_dma(struct pciefd_can *priv)
+{
+	/* read value of current IRQ tag and inc it for next one */
+	priv->irq_tag = le32_to_cpu(*(__le32 *)priv->rx_dma_vaddr);
+	priv->irq_tag++;
+	priv->irq_tag &= 0xf;
+
+	/* write the next IRQ tag for this CAN */
+	pciefd_can_writereg(priv, priv->irq_tag, PCIEFD_REG_CAN_RX_CTL_ACK);
+}
+
+/* IRQ handler */
+static irqreturn_t pciefd_irq_handler(int irq, void *arg)
+{
+	struct pciefd_can *priv = arg;
+	struct pciefd_rx_dma *rx_dma = priv->rx_dma_vaddr;
+
+	/* INTA mode only to sync with PCIe transaction */
+	if (!pci_dev_msi_enabled(priv->board->pci_dev))
+		(void)pciefd_sys_readreg(priv->board, PCIEFD_REG_SYS_VER1);
+
+	/* read IRQ status from the first 32-bits of the Rx DMA area */
+	priv->irq_status = le32_to_cpu(rx_dma->irq_status);
+
+	/* check if this (shared) IRQ is for this CAN */
+	if (pciefd_irq_tag(priv->irq_status) != priv->irq_tag)
+		return IRQ_NONE;
+
+	/* handle rx messages (if any) */
+	peak_canfd_handle_msgs_list(&priv->ucan,
+				    rx_dma->msg,
+				    pciefd_irq_rx_cnt(priv->irq_status));
+
+	/* handle tx link interrupt (if any) */
+	if (pciefd_irq_is_lnk(priv->irq_status)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&priv->tx_lock, flags);
+		priv->tx_pages_free++;
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+		/* wake producer up */
+		netif_wake_queue(priv->ucan.ndev);
+	}
+
+	/* re-enable Rx DMA transfer for this CAN */
+	pciefd_can_ack_rx_dma(priv);
+
+	return IRQ_HANDLED;
+}
+
+static int pciefd_enable_tx_path(struct peak_canfd_priv *ucan)
+{
+	struct pciefd_can *priv = (struct pciefd_can *)ucan;
+	int i;
+
+	/* initialize the Tx pages descriptors */
+	priv->tx_pages_free = PCIEFD_TX_PAGE_COUNT - 1;
+	priv->tx_page_index = 0;
+
+	priv->tx_pages[0].vbase = priv->tx_dma_vaddr;
+	priv->tx_pages[0].lbase = priv->tx_dma_laddr;
+
+	for (i = 0; i < PCIEFD_TX_PAGE_COUNT; i++) {
+		priv->tx_pages[i].offset = 0;
+		priv->tx_pages[i].size = PCIEFD_TX_PAGE_SIZE -
+					 sizeof(struct pciefd_tx_link);
+		if (i) {
+			priv->tx_pages[i].vbase =
+					  priv->tx_pages[i - 1].vbase +
+					  PCIEFD_TX_PAGE_SIZE;
+			priv->tx_pages[i].lbase =
+					  priv->tx_pages[i - 1].lbase +
+					  PCIEFD_TX_PAGE_SIZE;
+		}
+	}
+
+	/* setup Tx DMA addresses into IP core */
+	pciefd_can_setup_tx_dma(priv);
+
+	/* start (TX_RST=0) Tx Path */
+	pciefd_can_writereg(priv, CANFD_CTL_RST_BIT, PCIEFD_REG_CAN_TX_CTL_CLR);
+
+	return 0;
+}
+
+/* board specific CANFD command pre-processing */
+static int pciefd_pre_cmd(struct peak_canfd_priv *ucan)
+{
+	struct pciefd_can *priv = (struct pciefd_can *)ucan;
+	u16 cmd = pucan_cmd_get_opcode(&priv->pucan_cmd);
+	int err;
+
+	/* pre-process command */
+	switch (cmd) {
+	case PUCAN_CMD_NORMAL_MODE:
+	case PUCAN_CMD_LISTEN_ONLY_MODE:
+
+		if (ucan->can.state == CAN_STATE_BUS_OFF)
+			break;
+
+		/* going into operational mode: setup IRQ handler */
+		err = request_irq(priv->board->pci_dev->irq,
+				  pciefd_irq_handler,
+				  IRQF_SHARED,
+				  PCIEFD_DRV_NAME,
+				  priv);
+		if (err)
+			return err;
+
+		/* setup Rx DMA address */
+		pciefd_can_setup_rx_dma(priv);
+
+		/* setup max count of msgs per IRQ */
+		pciefd_can_writereg(priv, (CANFD_CTL_IRQ_TL_DEF) << 8 |
+				    CANFD_CTL_IRQ_CL_DEF,
+				    PCIEFD_REG_CAN_RX_CTL_WRT);
+
+		/* clear DMA RST for Rx (Rx start) */
+		pciefd_can_writereg(priv, CANFD_CTL_RST_BIT,
+				    PCIEFD_REG_CAN_RX_CTL_CLR);
+
+		/* reset timestamps */
+		pciefd_can_writereg(priv, !CANFD_MISC_TS_RST,
+				    PCIEFD_REG_CAN_MISC);
+
+		/* do an initial ACK */
+		pciefd_can_ack_rx_dma(priv);
+
+		/* enable IRQ for this CAN after having set next irq_tag */
+		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
+				    PCIEFD_REG_CAN_RX_CTL_SET);
+
+		/* Tx path will be setup as soon as RX_BARRIER is received */
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/* write a command */
+static int pciefd_write_cmd(struct peak_canfd_priv *ucan)
+{
+	struct pciefd_can *priv = (struct pciefd_can *)ucan;
+	unsigned long flags;
+
+	/* 64-bits command is atomic */
+	spin_lock_irqsave(&priv->board->cmd_lock, flags);
+
+	pciefd_can_writereg(priv, *(u32 *)ucan->cmd_buffer,
+			    PCIEFD_REG_CAN_CMD_PORT_L);
+	pciefd_can_writereg(priv, *(u32 *)(ucan->cmd_buffer + 4),
+			    PCIEFD_REG_CAN_CMD_PORT_H);
+
+	spin_unlock_irqrestore(&priv->board->cmd_lock, flags);
+
+	return 0;
+}
+
+/* board specific CANFD command post-processing */
+static int pciefd_post_cmd(struct peak_canfd_priv *ucan)
+{
+	struct pciefd_can *priv = (struct pciefd_can *)ucan;
+	u16 cmd = pucan_cmd_get_opcode(&priv->pucan_cmd);
+
+	switch (cmd) {
+	case PUCAN_CMD_RESET_MODE:
+
+		if (ucan->can.state == CAN_STATE_STOPPED)
+			break;
+
+		/* controller now in reset mode: */
+
+		/* stop and reset DMA addresses in Tx/Rx engines */
+		pciefd_can_clear_tx_dma(priv);
+		pciefd_can_clear_rx_dma(priv);
+
+		/* disable IRQ for this CAN */
+		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
+				    PCIEFD_REG_CAN_RX_CTL_CLR);
+
+		free_irq(priv->board->pci_dev->irq, priv);
+
+		ucan->can.state = CAN_STATE_STOPPED;
+
+		break;
+	}
+
+	return 0;
+}
+
+static void *pciefd_alloc_tx_msg(struct peak_canfd_priv *ucan, u16 msg_size,
+				 int *room_left)
+{
+	struct pciefd_can *priv = (struct pciefd_can *)ucan;
+	struct pciefd_page *page = priv->tx_pages + priv->tx_page_index;
+	unsigned long flags;
+	void *msg;
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	if (page->offset + msg_size > page->size) {
+		struct pciefd_tx_link *lk;
+
+		/* not enough space in this page: try another one */
+		if (!priv->tx_pages_free) {
+			spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+			/* Tx overflow */
+			return NULL;
+		}
+
+		priv->tx_pages_free--;
+
+		/* keep address of the very last free slot of current page */
+		lk = page->vbase + page->offset;
+
+		/* next, move on a new free page */
+		priv->tx_page_index = (priv->tx_page_index + 1) %
+				      PCIEFD_TX_PAGE_COUNT;
+		page = priv->tx_pages + priv->tx_page_index;
+
+		/* put link record to this new page at the end of prev one */
+		lk->size = cpu_to_le16(sizeof(*lk));
+		lk->type = cpu_to_le16(CANFD_MSG_LNK_TX);
+		lk->laddr_lo = cpu_to_le32(page->lbase);
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		lk->laddr_hi = cpu_to_le32(page->lbase >> 32);
+#else
+		lk->laddr_hi = 0;
+#endif
+		/* next msgs will be put from the begininng of this new page */
+		page->offset = 0;
+	}
+
+	*room_left = priv->tx_pages_free * page->size;
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	msg = page->vbase + page->offset;
+
+	/* give back room left in the tx ring */
+	*room_left += page->size - (page->offset + msg_size);
+
+	return msg;
+}
+
+static int pciefd_write_tx_msg(struct peak_canfd_priv *ucan,
+			       struct pucan_tx_msg *msg)
+{
+	struct pciefd_can *priv = (struct pciefd_can *)ucan;
+	struct pciefd_page *page = priv->tx_pages + priv->tx_page_index;
+
+	/* this slot is now reserved for writing the frame */
+	page->offset += le16_to_cpu(msg->size);
+
+	/* tell the board a frame has been written in Tx DMA area */
+	pciefd_can_writereg(priv, 1, PCIEFD_REG_CAN_TX_REQ_ACC);
+
+	return 0;
+}
+
+/* probe for CAN-FD channel #pciefd_board->can_count */
+static int pciefd_can_probe(struct pciefd_board *pciefd)
+{
+	struct net_device *ndev;
+	struct pciefd_can *priv;
+	u32 clk;
+	int err;
+
+	/* allocate the candev object with default isize of echo skbs ring */
+	ndev = alloc_peak_canfd_dev(sizeof(*priv), pciefd->can_count,
+				    PCIEFD_ECHO_SKB_MAX);
+	if (!ndev) {
+		dev_err(&pciefd->pci_dev->dev,
+			"failed to alloc candev object\n");
+		goto failure;
+	}
+
+	priv = netdev_priv(ndev);
+
+	/* fill-in candev private object: */
+
+	/* setup PCIe-FD own callbacks */
+	priv->ucan.pre_cmd = pciefd_pre_cmd;
+	priv->ucan.write_cmd = pciefd_write_cmd;
+	priv->ucan.post_cmd = pciefd_post_cmd;
+	priv->ucan.enable_tx_path = pciefd_enable_tx_path;
+	priv->ucan.alloc_tx_msg = pciefd_alloc_tx_msg;
+	priv->ucan.write_tx_msg = pciefd_write_tx_msg;
+
+	/* setup PCIe-FD own command buffer */
+	priv->ucan.cmd_buffer = &priv->pucan_cmd;
+	priv->ucan.cmd_maxlen = sizeof(priv->pucan_cmd);
+
+	priv->board = pciefd;
+
+	/* CAN config regs block address */
+	priv->reg_base = pciefd->reg_base + PCIEFD_CANX_OFF(priv->ucan.index);
+
+	/* allocate non-cacheable DMA'able 4KB memory area for Rx */
+	priv->rx_dma_vaddr = dmam_alloc_coherent(&pciefd->pci_dev->dev,
+						 PCIEFD_RX_DMA_SIZE,
+						 &priv->rx_dma_laddr,
+						 GFP_KERNEL);
+	if (!priv->rx_dma_vaddr) {
+		dev_err(&pciefd->pci_dev->dev,
+			"Rx dmam_alloc_coherent(%u) failure\n",
+			PCIEFD_RX_DMA_SIZE);
+		goto err_free_candev;
+	}
+
+	/* allocate non-cacheable DMA'able 4KB memory area for Tx */
+	priv->tx_dma_vaddr = dmam_alloc_coherent(&pciefd->pci_dev->dev,
+						 PCIEFD_TX_DMA_SIZE,
+						 &priv->tx_dma_laddr,
+						 GFP_KERNEL);
+	if (!priv->tx_dma_vaddr) {
+		dev_err(&pciefd->pci_dev->dev,
+			"Tx dmaim_alloc_coherent(%u) failure\n",
+			PCIEFD_TX_DMA_SIZE);
+		goto err_free_candev;
+	}
+
+	/* CAN clock in RST mode */
+	pciefd_can_writereg(priv, CANFD_MISC_TS_RST, PCIEFD_REG_CAN_MISC);
+
+	/* read current clock value */
+	clk = pciefd_can_readreg(priv, PCIEFD_REG_CAN_CLK_SEL);
+	switch (clk) {
+	case CANFD_CLK_SEL_20MHZ:
+		priv->ucan.can.clock.freq = 20 * 1000 * 1000;
+		break;
+	case CANFD_CLK_SEL_24MHZ:
+		priv->ucan.can.clock.freq = 24 * 1000 * 1000;
+		break;
+	case CANFD_CLK_SEL_30MHZ:
+		priv->ucan.can.clock.freq = 30 * 1000 * 1000;
+		break;
+	case CANFD_CLK_SEL_40MHZ:
+		priv->ucan.can.clock.freq = 40 * 1000 * 1000;
+		break;
+	case CANFD_CLK_SEL_60MHZ:
+		priv->ucan.can.clock.freq = 60 * 1000 * 1000;
+		break;
+	default:
+		pciefd_can_writereg(priv, CANFD_CLK_SEL_80MHZ,
+				    PCIEFD_REG_CAN_CLK_SEL);
+
+		/* fallthough */
+	case CANFD_CLK_SEL_80MHZ:
+		priv->ucan.can.clock.freq = 80 * 1000 * 1000;
+		break;
+	}
+
+	ndev->irq = pciefd->pci_dev->irq;
+
+	SET_NETDEV_DEV(ndev, &pciefd->pci_dev->dev);
+
+	err = register_candev(ndev);
+	if (err) {
+		dev_err(&pciefd->pci_dev->dev,
+			"couldn't register CAN device: %d\n", err);
+		goto err_free_candev;
+	}
+
+	spin_lock_init(&priv->tx_lock);
+
+	/* save the object address in the board structure */
+	pciefd->can[pciefd->can_count] = priv;
+
+	dev_info(&pciefd->pci_dev->dev, "%s at reg_base=0x%p irq=%d\n",
+		 ndev->name, priv->reg_base, pciefd->pci_dev->irq);
+
+	return 0;
+
+err_free_candev:
+	free_candev(ndev);
+
+failure:
+	return -ENOMEM;
+}
+
+/* remove a CAN-FD channel by releasing all of its resources */
+static void pciefd_can_remove(struct pciefd_can *priv)
+{
+	/* unregister (close) the can device to go back to RST mode first */
+	unregister_candev(priv->ucan.ndev);
+
+	/* finally, free the candev object */
+	free_candev(priv->ucan.ndev);
+}
+
+/* remove all CAN-FD channels by releasing their own resources */
+static void pciefd_can_remove_all(struct pciefd_board *pciefd)
+{
+	while (pciefd->can_count > 0)
+		pciefd_can_remove(pciefd->can[--pciefd->can_count]);
+}
+
+/* probe for the entire device */
+static int peak_pciefd_probe(struct pci_dev *pdev,
+			     const struct pci_device_id *ent)
+{
+	struct pciefd_board *pciefd;
+	int err, can_count;
+	u16 sub_sys_id;
+	u8 hw_ver_major;
+	u8 hw_ver_minor;
+	u8 hw_ver_sub;
+	u32 v2;
+
+	err = pci_enable_device(pdev);
+	if (err)
+		return err;
+	err = pci_request_regions(pdev, PCIEFD_DRV_NAME);
+	if (err)
+		goto err_disable_pci;
+
+	/* the number of channels depends on sub-system id */
+	err = pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sub_sys_id);
+	if (err)
+		goto err_release_regions;
+
+	dev_dbg(&pdev->dev, "probing device %04x:%04x:%04x\n",
+		pdev->vendor, pdev->device, sub_sys_id);
+
+	if (sub_sys_id >= 0x0012)
+		can_count = 4;
+	else if (sub_sys_id >= 0x0010)
+		can_count = 3;
+	else if (sub_sys_id >= 0x0004)
+		can_count = 2;
+	else
+		can_count = 1;
+
+	/* allocate board structure object */
+	pciefd = devm_kzalloc(&pdev->dev, sizeof(*pciefd) +
+			      can_count * sizeof(*pciefd->can),
+			      GFP_KERNEL);
+	if (!pciefd) {
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+
+	/* initialize the board structure */
+	pciefd->pci_dev = pdev;
+	spin_lock_init(&pciefd->cmd_lock);
+
+	/* save the PCI BAR0 virtual address for further system regs access */
+	pciefd->reg_base = pci_iomap(pdev, 0, PCIEFD_BAR0_SIZE);
+	if (!pciefd->reg_base) {
+		dev_err(&pdev->dev, "failed to map PCI resource #0\n");
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+
+	/* read the firmware version number */
+	v2 = pciefd_sys_readreg(pciefd, PCIEFD_REG_SYS_VER2);
+
+	hw_ver_major = (v2 & 0x0000f000) >> 12;
+	hw_ver_minor = (v2 & 0x00000f00) >> 8;
+	hw_ver_sub = (v2 & 0x000000f0) >> 4;
+
+	dev_info(&pdev->dev,
+		 "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count,
+		 hw_ver_major, hw_ver_minor, hw_ver_sub);
+
+	/* stop system clock */
+	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN,
+			    PCIEFD_REG_SYS_CTL_CLR);
+
+	pci_set_master(pdev);
+
+	/* create now the corresponding channels objects */
+	while (pciefd->can_count < can_count) {
+		err = pciefd_can_probe(pciefd);
+		if (err)
+			goto err_free_canfd;
+
+		pciefd->can_count++;
+	}
+
+	/* set system timestamps counter in RST mode */
+	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_TS_RST,
+			    PCIEFD_REG_SYS_CTL_SET);
+
+	/* wait a bit (read cycle) */
+	(void)pciefd_sys_readreg(pciefd, PCIEFD_REG_SYS_VER1);
+
+	/* free all clocks */
+	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_TS_RST,
+			    PCIEFD_REG_SYS_CTL_CLR);
+
+	/* start system clock */
+	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN,
+			    PCIEFD_REG_SYS_CTL_SET);
+
+	/* remember the board structure address in the device user data */
+	pci_set_drvdata(pdev, pciefd);
+
+	return 0;
+
+err_free_canfd:
+	pciefd_can_remove_all(pciefd);
+
+	pci_iounmap(pdev, pciefd->reg_base);
+
+err_release_regions:
+	pci_release_regions(pdev);
+
+err_disable_pci:
+	pci_disable_device(pdev);
+
+	return err;
+}
+
+/* free the board structure object, as well as its resources: */
+static void peak_pciefd_remove(struct pci_dev *pdev)
+{
+	struct pciefd_board *pciefd = pci_get_drvdata(pdev);
+
+	/* release CAN-FD channels resources */
+	pciefd_can_remove_all(pciefd);
+
+	pci_iounmap(pdev, pciefd->reg_base);
+
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static struct pci_driver peak_pciefd_driver = {
+	.name = PCIEFD_DRV_NAME,
+	.id_table = peak_pciefd_tbl,
+	.probe = peak_pciefd_probe,
+	.remove = peak_pciefd_remove,
+};
+
+module_pci_driver(peak_pciefd_driver);
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index caed4e6960f8..11662f479e76 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -826,8 +826,7 @@ static int rcar_can_probe(struct platform_device *pdev)
 
 	devm_can_led_init(ndev);
 
-	dev_info(&pdev->dev, "device registered (regs @ %p, IRQ%d)\n",
-		 priv->regs, ndev->irq);
+	dev_info(&pdev->dev, "device registered (IRQ%d)\n", ndev->irq);
 
 	return 0;
 fail_candev:
diff --git a/drivers/net/can/spi/Kconfig b/drivers/net/can/spi/Kconfig
index 148cae5871a6..8f2e0dd7b756 100644
--- a/drivers/net/can/spi/Kconfig
+++ b/drivers/net/can/spi/Kconfig
@@ -1,6 +1,12 @@
 menu "CAN SPI interfaces"
 	depends on SPI
 
+config CAN_HI311X
+	tristate "Holt HI311x SPI CAN controllers"
+	depends on CAN_DEV && SPI && HAS_DMA
+	---help---
+	  Driver for the Holt HI311x SPI CAN controllers.
+
 config CAN_MCP251X
 	tristate "Microchip MCP251x SPI CAN controllers"
 	depends on HAS_DMA
diff --git a/drivers/net/can/spi/Makefile b/drivers/net/can/spi/Makefile
index 0e86040cdd8c..f59fa3731073 100644
--- a/drivers/net/can/spi/Makefile
+++ b/drivers/net/can/spi/Makefile
@@ -3,4 +3,5 @@
 #
 
 
+obj-$(CONFIG_CAN_HI311X)	+= hi311x.o
 obj-$(CONFIG_CAN_MCP251X)	+= mcp251x.o
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
new file mode 100644
index 000000000000..5590c559a8ca
--- /dev/null
+++ b/drivers/net/can/spi/hi311x.c
@@ -0,0 +1,1076 @@
+/* CAN bus driver for Holt HI3110 CAN Controller with SPI Interface
+ *
+ * Copyright(C) Timesys Corporation 2016
+ *
+ * Based on Microchip 251x CAN Controller (mcp251x) Linux kernel driver
+ * Copyright 2009 Christian Pellegrin EVOL S.r.l.
+ * Copyright 2007 Raymarine UK, Ltd. All Rights Reserved.
+ * Copyright 2006 Arcom Control Systems Ltd.
+ *
+ * Based on CAN bus driver for the CCAN controller written by
+ * - Sascha Hauer, Marc Kleine-Budde, Pengutronix
+ * - Simon Kallweit, intefo AG
+ * Copyright 2007
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/can/core.h>
+#include <linux/can/dev.h>
+#include <linux/can/led.h>
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/freezer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/uaccess.h>
+
+#define HI3110_MASTER_RESET 0x56
+#define HI3110_READ_CTRL0 0xD2
+#define HI3110_READ_CTRL1 0xD4
+#define HI3110_READ_STATF 0xE2
+#define HI3110_WRITE_CTRL0 0x14
+#define HI3110_WRITE_CTRL1 0x16
+#define HI3110_WRITE_INTE 0x1C
+#define HI3110_WRITE_BTR0 0x18
+#define HI3110_WRITE_BTR1 0x1A
+#define HI3110_READ_BTR0 0xD6
+#define HI3110_READ_BTR1 0xD8
+#define HI3110_READ_INTF 0xDE
+#define HI3110_READ_ERR 0xDC
+#define HI3110_READ_FIFO_WOTIME 0x48
+#define HI3110_WRITE_FIFO 0x12
+#define HI3110_READ_MESSTAT 0xDA
+#define HI3110_READ_REC 0xEA
+#define HI3110_READ_TEC 0xEC
+
+#define HI3110_CTRL0_MODE_MASK (7 << 5)
+#define HI3110_CTRL0_NORMAL_MODE (0 << 5)
+#define HI3110_CTRL0_LOOPBACK_MODE (1 << 5)
+#define HI3110_CTRL0_MONITOR_MODE (2 << 5)
+#define HI3110_CTRL0_SLEEP_MODE (3 << 5)
+#define HI3110_CTRL0_INIT_MODE (4 << 5)
+
+#define HI3110_CTRL1_TXEN BIT(7)
+
+#define HI3110_INT_RXTMP BIT(7)
+#define HI3110_INT_RXFIFO BIT(6)
+#define HI3110_INT_TXCPLT BIT(5)
+#define HI3110_INT_BUSERR BIT(4)
+#define HI3110_INT_MCHG BIT(3)
+#define HI3110_INT_WAKEUP BIT(2)
+#define HI3110_INT_F1MESS BIT(1)
+#define HI3110_INT_F0MESS BIT(0)
+
+#define HI3110_ERR_BUSOFF BIT(7)
+#define HI3110_ERR_TXERRP BIT(6)
+#define HI3110_ERR_RXERRP BIT(5)
+#define HI3110_ERR_BITERR BIT(4)
+#define HI3110_ERR_FRMERR BIT(3)
+#define HI3110_ERR_CRCERR BIT(2)
+#define HI3110_ERR_ACKERR BIT(1)
+#define HI3110_ERR_STUFERR BIT(0)
+#define HI3110_ERR_PROTOCOL_MASK (0x1F)
+#define HI3110_ERR_PASSIVE_MASK (0x60)
+
+#define HI3110_STAT_RXFMTY BIT(1)
+#define HI3110_STAT_BUSOFF BIT(2)
+#define HI3110_STAT_ERRP BIT(3)
+#define HI3110_STAT_ERRW BIT(4)
+
+#define HI3110_BTR0_SJW_SHIFT 6
+#define HI3110_BTR0_BRP_SHIFT 0
+
+#define HI3110_BTR1_SAMP_3PERBIT (1 << 7)
+#define HI3110_BTR1_SAMP_1PERBIT (0 << 7)
+#define HI3110_BTR1_TSEG2_SHIFT 4
+#define HI3110_BTR1_TSEG1_SHIFT 0
+
+#define HI3110_FIFO_WOTIME_TAG_OFF 0
+#define HI3110_FIFO_WOTIME_ID_OFF 1
+#define HI3110_FIFO_WOTIME_DLC_OFF 5
+#define HI3110_FIFO_WOTIME_DAT_OFF 6
+
+#define HI3110_FIFO_WOTIME_TAG_IDE BIT(7)
+#define HI3110_FIFO_WOTIME_ID_RTR BIT(0)
+
+#define HI3110_FIFO_TAG_OFF 0
+#define HI3110_FIFO_ID_OFF 1
+#define HI3110_FIFO_STD_DLC_OFF 3
+#define HI3110_FIFO_STD_DATA_OFF 4
+#define HI3110_FIFO_EXT_DLC_OFF 5
+#define HI3110_FIFO_EXT_DATA_OFF 6
+
+#define HI3110_CAN_MAX_DATA_LEN 8
+#define HI3110_RX_BUF_LEN 15
+#define HI3110_TX_STD_BUF_LEN 12
+#define HI3110_TX_EXT_BUF_LEN 14
+#define HI3110_CAN_FRAME_MAX_BITS 128
+#define HI3110_EFF_FLAGS 0x18 /* IDE + SRR */
+
+#define HI3110_TX_ECHO_SKB_MAX 1
+
+#define HI3110_OST_DELAY_MS (10)
+
+#define DEVICE_NAME "hi3110"
+
+static int hi3110_enable_dma = 1; /* Enable SPI DMA. Default: 1 (On) */
+module_param(hi3110_enable_dma, int, 0444);
+MODULE_PARM_DESC(hi3110_enable_dma, "Enable SPI DMA. Default: 1 (On)");
+
+static const struct can_bittiming_const hi3110_bittiming_const = {
+	.name = DEVICE_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 64,
+	.brp_inc = 1,
+};
+
+enum hi3110_model {
+	CAN_HI3110_HI3110 = 0x3110,
+};
+
+struct hi3110_priv {
+	struct can_priv can;
+	struct net_device *net;
+	struct spi_device *spi;
+	enum hi3110_model model;
+
+	struct mutex hi3110_lock; /* SPI device lock */
+
+	u8 *spi_tx_buf;
+	u8 *spi_rx_buf;
+	dma_addr_t spi_tx_dma;
+	dma_addr_t spi_rx_dma;
+
+	struct sk_buff *tx_skb;
+	int tx_len;
+
+	struct workqueue_struct *wq;
+	struct work_struct tx_work;
+	struct work_struct restart_work;
+
+	int force_quit;
+	int after_suspend;
+#define HI3110_AFTER_SUSPEND_UP 1
+#define HI3110_AFTER_SUSPEND_DOWN 2
+#define HI3110_AFTER_SUSPEND_POWER 4
+#define HI3110_AFTER_SUSPEND_RESTART 8
+	int restart_tx;
+	struct regulator *power;
+	struct regulator *transceiver;
+	struct clk *clk;
+};
+
+static void hi3110_clean(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+
+	if (priv->tx_skb || priv->tx_len)
+		net->stats.tx_errors++;
+	if (priv->tx_skb)
+		dev_kfree_skb(priv->tx_skb);
+	if (priv->tx_len)
+		can_free_echo_skb(priv->net, 0);
+	priv->tx_skb = NULL;
+	priv->tx_len = 0;
+}
+
+/* Note about handling of error return of hi3110_spi_trans: accessing
+ * registers via SPI is not really different conceptually than using
+ * normal I/O assembler instructions, although it's much more
+ * complicated from a practical POV. So it's not advisable to always
+ * check the return value of this function. Imagine that every
+ * read{b,l}, write{b,l} and friends would be bracketed in "if ( < 0)
+ * error();", it would be a great mess (well there are some situation
+ * when exception handling C++ like could be useful after all). So we
+ * just check that transfers are OK at the beginning of our
+ * conversation with the chip and to avoid doing really nasty things
+ * (like injecting bogus packets in the network stack).
+ */
+static int hi3110_spi_trans(struct spi_device *spi, int len)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct spi_transfer t = {
+		.tx_buf = priv->spi_tx_buf,
+		.rx_buf = priv->spi_rx_buf,
+		.len = len,
+		.cs_change = 0,
+	};
+	struct spi_message m;
+	int ret;
+
+	spi_message_init(&m);
+
+	if (hi3110_enable_dma) {
+		t.tx_dma = priv->spi_tx_dma;
+		t.rx_dma = priv->spi_rx_dma;
+		m.is_dma_mapped = 1;
+	}
+
+	spi_message_add_tail(&t, &m);
+
+	ret = spi_sync(spi, &m);
+
+	if (ret)
+		dev_err(&spi->dev, "spi transfer failed: ret = %d\n", ret);
+	return ret;
+}
+
+static u8 hi3110_cmd(struct spi_device *spi, u8 command)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = command;
+	dev_dbg(&spi->dev, "hi3110_cmd: %02X\n", command);
+
+	return hi3110_spi_trans(spi, 1);
+}
+
+static u8 hi3110_read(struct spi_device *spi, u8 command)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	u8 val = 0;
+
+	priv->spi_tx_buf[0] = command;
+	hi3110_spi_trans(spi, 2);
+	val = priv->spi_rx_buf[1];
+
+	return val;
+}
+
+static void hi3110_write(struct spi_device *spi, u8 reg, u8 val)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = reg;
+	priv->spi_tx_buf[1] = val;
+	hi3110_spi_trans(spi, 2);
+}
+
+static void hi3110_hw_tx_frame(struct spi_device *spi, u8 *buf, int len)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = HI3110_WRITE_FIFO;
+	memcpy(priv->spi_tx_buf + 1, buf, len);
+	hi3110_spi_trans(spi, len + 1);
+}
+
+static void hi3110_hw_tx(struct spi_device *spi, struct can_frame *frame)
+{
+	u8 buf[HI3110_TX_EXT_BUF_LEN];
+
+	buf[HI3110_FIFO_TAG_OFF] = 0;
+
+	if (frame->can_id & CAN_EFF_FLAG) {
+		/* Extended frame */
+		buf[HI3110_FIFO_ID_OFF] = (frame->can_id & CAN_EFF_MASK) >> 21;
+		buf[HI3110_FIFO_ID_OFF + 1] =
+			(((frame->can_id & CAN_EFF_MASK) >> 13) & 0xe0) |
+			HI3110_EFF_FLAGS |
+			(((frame->can_id & CAN_EFF_MASK) >> 15) & 0x07);
+		buf[HI3110_FIFO_ID_OFF + 2] =
+			(frame->can_id & CAN_EFF_MASK) >> 7;
+		buf[HI3110_FIFO_ID_OFF + 3] =
+			((frame->can_id & CAN_EFF_MASK) << 1) |
+			((frame->can_id & CAN_RTR_FLAG) ? 1 : 0);
+
+		buf[HI3110_FIFO_EXT_DLC_OFF] = frame->can_dlc;
+
+		memcpy(buf + HI3110_FIFO_EXT_DATA_OFF,
+		       frame->data, frame->can_dlc);
+
+		hi3110_hw_tx_frame(spi, buf, HI3110_TX_EXT_BUF_LEN -
+				   (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+	} else {
+		/* Standard frame */
+		buf[HI3110_FIFO_ID_OFF] =   (frame->can_id & CAN_SFF_MASK) >> 3;
+		buf[HI3110_FIFO_ID_OFF + 1] =
+			((frame->can_id & CAN_SFF_MASK) << 5) |
+			((frame->can_id & CAN_RTR_FLAG) ? (1 << 4) : 0);
+
+		buf[HI3110_FIFO_STD_DLC_OFF] = frame->can_dlc;
+
+		memcpy(buf + HI3110_FIFO_STD_DATA_OFF,
+		       frame->data, frame->can_dlc);
+
+		hi3110_hw_tx_frame(spi, buf, HI3110_TX_STD_BUF_LEN -
+				   (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+	}
+}
+
+static void hi3110_hw_rx_frame(struct spi_device *spi, u8 *buf)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = HI3110_READ_FIFO_WOTIME;
+	hi3110_spi_trans(spi, HI3110_RX_BUF_LEN);
+	memcpy(buf, priv->spi_rx_buf + 1, HI3110_RX_BUF_LEN - 1);
+}
+
+static void hi3110_hw_rx(struct spi_device *spi)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct sk_buff *skb;
+	struct can_frame *frame;
+	u8 buf[HI3110_RX_BUF_LEN - 1];
+
+	skb = alloc_can_skb(priv->net, &frame);
+	if (!skb) {
+		priv->net->stats.rx_dropped++;
+		return;
+	}
+
+	hi3110_hw_rx_frame(spi, buf);
+	if (buf[HI3110_FIFO_WOTIME_TAG_OFF] & HI3110_FIFO_WOTIME_TAG_IDE) {
+		/* IDE is recessive (1), indicating extended 29-bit frame */
+		frame->can_id = CAN_EFF_FLAG;
+		frame->can_id |=
+			(buf[HI3110_FIFO_WOTIME_ID_OFF] << 21) |
+			(((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0xE0) >> 5) << 18) |
+			((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0x07) << 15) |
+			(buf[HI3110_FIFO_WOTIME_ID_OFF + 2] << 7) |
+			(buf[HI3110_FIFO_WOTIME_ID_OFF + 3] >> 1);
+	} else {
+		/* IDE is dominant (0), frame indicating standard 11-bit */
+		frame->can_id =
+			(buf[HI3110_FIFO_WOTIME_ID_OFF] << 3) |
+			((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0xE0) >> 5);
+	}
+
+	/* Data length */
+	frame->can_dlc = get_can_dlc(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
+
+	if (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] & HI3110_FIFO_WOTIME_ID_RTR)
+		frame->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(frame->data, buf + HI3110_FIFO_WOTIME_DAT_OFF,
+		       frame->can_dlc);
+
+	priv->net->stats.rx_packets++;
+	priv->net->stats.rx_bytes += frame->can_dlc;
+
+	can_led_event(priv->net, CAN_LED_EVENT_RX);
+
+	netif_rx_ni(skb);
+}
+
+static void hi3110_hw_sleep(struct spi_device *spi)
+{
+	hi3110_write(spi, HI3110_WRITE_CTRL0, HI3110_CTRL0_SLEEP_MODE);
+}
+
+static netdev_tx_t hi3110_hard_start_xmit(struct sk_buff *skb,
+					  struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+
+	if (priv->tx_skb || priv->tx_len) {
+		dev_err(&spi->dev, "hard_xmit called while tx busy\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	if (can_dropped_invalid_skb(net, skb))
+		return NETDEV_TX_OK;
+
+	netif_stop_queue(net);
+	priv->tx_skb = skb;
+	queue_work(priv->wq, &priv->tx_work);
+
+	return NETDEV_TX_OK;
+}
+
+static int hi3110_do_set_mode(struct net_device *net, enum can_mode mode)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+
+	switch (mode) {
+	case CAN_MODE_START:
+		hi3110_clean(net);
+		/* We have to delay work since SPI I/O may sleep */
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		priv->restart_tx = 1;
+		if (priv->can.restart_ms == 0)
+			priv->after_suspend = HI3110_AFTER_SUSPEND_RESTART;
+		queue_work(priv->wq, &priv->restart_work);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int hi3110_get_berr_counter(const struct net_device *net,
+				   struct can_berr_counter *bec)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+
+	bec->txerr = hi3110_read(spi, HI3110_READ_TEC);
+	bec->rxerr = hi3110_read(spi, HI3110_READ_REC);
+
+	return 0;
+}
+
+static int hi3110_set_normal_mode(struct spi_device *spi)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	u8 reg = 0;
+
+	hi3110_write(spi, HI3110_WRITE_INTE, HI3110_INT_BUSERR |
+		     HI3110_INT_RXFIFO | HI3110_INT_TXCPLT);
+
+	/* Enable TX */
+	hi3110_write(spi, HI3110_WRITE_CTRL1, HI3110_CTRL1_TXEN);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		reg = HI3110_CTRL0_LOOPBACK_MODE;
+	else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		reg = HI3110_CTRL0_MONITOR_MODE;
+	else
+		reg = HI3110_CTRL0_NORMAL_MODE;
+
+	hi3110_write(spi, HI3110_WRITE_CTRL0, reg);
+
+	/* Wait for the device to enter the mode */
+	mdelay(HI3110_OST_DELAY_MS);
+	reg = hi3110_read(spi, HI3110_READ_CTRL0);
+	if ((reg & HI3110_CTRL0_MODE_MASK) != reg)
+		return -EBUSY;
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	return 0;
+}
+
+static int hi3110_do_set_bittiming(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct spi_device *spi = priv->spi;
+
+	hi3110_write(spi, HI3110_WRITE_BTR0,
+		     ((bt->sjw - 1) << HI3110_BTR0_SJW_SHIFT) |
+		     ((bt->brp - 1) << HI3110_BTR0_BRP_SHIFT));
+
+	hi3110_write(spi, HI3110_WRITE_BTR1,
+		     (priv->can.ctrlmode &
+		      CAN_CTRLMODE_3_SAMPLES ?
+		      HI3110_BTR1_SAMP_3PERBIT : HI3110_BTR1_SAMP_1PERBIT) |
+		     ((bt->phase_seg1 + bt->prop_seg - 1)
+		      << HI3110_BTR1_TSEG1_SHIFT) |
+		     ((bt->phase_seg2 - 1) << HI3110_BTR1_TSEG2_SHIFT));
+
+	dev_dbg(&spi->dev, "BT: 0x%02x 0x%02x\n",
+		hi3110_read(spi, HI3110_READ_BTR0),
+		hi3110_read(spi, HI3110_READ_BTR1));
+
+	return 0;
+}
+
+static int hi3110_setup(struct net_device *net)
+{
+	hi3110_do_set_bittiming(net);
+	return 0;
+}
+
+static int hi3110_hw_reset(struct spi_device *spi)
+{
+	u8 reg;
+	int ret;
+
+	/* Wait for oscillator startup timer after power up */
+	mdelay(HI3110_OST_DELAY_MS);
+
+	ret = hi3110_cmd(spi, HI3110_MASTER_RESET);
+	if (ret)
+		return ret;
+
+	/* Wait for oscillator startup timer after reset */
+	mdelay(HI3110_OST_DELAY_MS);
+
+	reg = hi3110_read(spi, HI3110_READ_CTRL0);
+	if ((reg & HI3110_CTRL0_MODE_MASK) != HI3110_CTRL0_INIT_MODE)
+		return -ENODEV;
+
+	/* As per the datasheet it appears the error flags are
+	 * not cleared on reset. Explicitly clear them by performing a read
+	 */
+	hi3110_read(spi, HI3110_READ_ERR);
+
+	return 0;
+}
+
+static int hi3110_hw_probe(struct spi_device *spi)
+{
+	u8 statf;
+
+	hi3110_hw_reset(spi);
+
+	/* Confirm correct operation by checking against reset values
+	 * in datasheet
+	 */
+	statf = hi3110_read(spi, HI3110_READ_STATF);
+
+	dev_dbg(&spi->dev, "statf: %02X\n", statf);
+
+	if (statf != 0x82)
+		return -ENODEV;
+
+	return 0;
+}
+
+static int hi3110_power_enable(struct regulator *reg, int enable)
+{
+	if (IS_ERR_OR_NULL(reg))
+		return 0;
+
+	if (enable)
+		return regulator_enable(reg);
+	else
+		return regulator_disable(reg);
+}
+
+static int hi3110_stop(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+
+	close_candev(net);
+
+	priv->force_quit = 1;
+	free_irq(spi->irq, priv);
+	destroy_workqueue(priv->wq);
+	priv->wq = NULL;
+
+	mutex_lock(&priv->hi3110_lock);
+
+	/* Disable transmit, interrupts and clear flags */
+	hi3110_write(spi, HI3110_WRITE_CTRL1, 0x0);
+	hi3110_write(spi, HI3110_WRITE_INTE, 0x0);
+	hi3110_read(spi, HI3110_READ_INTF);
+
+	hi3110_clean(net);
+
+	hi3110_hw_sleep(spi);
+
+	hi3110_power_enable(priv->transceiver, 0);
+
+	priv->can.state = CAN_STATE_STOPPED;
+
+	mutex_unlock(&priv->hi3110_lock);
+
+	can_led_event(net, CAN_LED_EVENT_STOP);
+
+	return 0;
+}
+
+static void hi3110_tx_work_handler(struct work_struct *ws)
+{
+	struct hi3110_priv *priv = container_of(ws, struct hi3110_priv,
+						tx_work);
+	struct spi_device *spi = priv->spi;
+	struct net_device *net = priv->net;
+	struct can_frame *frame;
+
+	mutex_lock(&priv->hi3110_lock);
+	if (priv->tx_skb) {
+		if (priv->can.state == CAN_STATE_BUS_OFF) {
+			hi3110_clean(net);
+		} else {
+			frame = (struct can_frame *)priv->tx_skb->data;
+			hi3110_hw_tx(spi, frame);
+			priv->tx_len = 1 + frame->can_dlc;
+			can_put_echo_skb(priv->tx_skb, net, 0);
+			priv->tx_skb = NULL;
+		}
+	}
+	mutex_unlock(&priv->hi3110_lock);
+}
+
+static void hi3110_restart_work_handler(struct work_struct *ws)
+{
+	struct hi3110_priv *priv = container_of(ws, struct hi3110_priv,
+						restart_work);
+	struct spi_device *spi = priv->spi;
+	struct net_device *net = priv->net;
+
+	mutex_lock(&priv->hi3110_lock);
+	if (priv->after_suspend) {
+		hi3110_hw_reset(spi);
+		hi3110_setup(net);
+		if (priv->after_suspend & HI3110_AFTER_SUSPEND_RESTART) {
+			hi3110_set_normal_mode(spi);
+		} else if (priv->after_suspend & HI3110_AFTER_SUSPEND_UP) {
+			netif_device_attach(net);
+			hi3110_clean(net);
+			hi3110_set_normal_mode(spi);
+			netif_wake_queue(net);
+		} else {
+			hi3110_hw_sleep(spi);
+		}
+		priv->after_suspend = 0;
+		priv->force_quit = 0;
+	}
+
+	if (priv->restart_tx) {
+		priv->restart_tx = 0;
+		hi3110_hw_reset(spi);
+		hi3110_setup(net);
+		hi3110_clean(net);
+		hi3110_set_normal_mode(spi);
+		netif_wake_queue(net);
+	}
+	mutex_unlock(&priv->hi3110_lock);
+}
+
+static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
+{
+	struct hi3110_priv *priv = dev_id;
+	struct spi_device *spi = priv->spi;
+	struct net_device *net = priv->net;
+
+	mutex_lock(&priv->hi3110_lock);
+
+	while (!priv->force_quit) {
+		enum can_state new_state;
+		u8 intf, eflag, statf;
+
+		while (!(HI3110_STAT_RXFMTY &
+			 (statf = hi3110_read(spi, HI3110_READ_STATF)))) {
+			hi3110_hw_rx(spi);
+		}
+
+		intf = hi3110_read(spi, HI3110_READ_INTF);
+		eflag = hi3110_read(spi, HI3110_READ_ERR);
+		/* Update can state */
+		if (eflag & HI3110_ERR_BUSOFF)
+			new_state = CAN_STATE_BUS_OFF;
+		else if (eflag & HI3110_ERR_PASSIVE_MASK)
+			new_state = CAN_STATE_ERROR_PASSIVE;
+		else if (statf & HI3110_STAT_ERRW)
+			new_state = CAN_STATE_ERROR_WARNING;
+		else
+			new_state = CAN_STATE_ERROR_ACTIVE;
+
+		if (new_state != priv->can.state) {
+			struct can_frame *cf;
+			struct sk_buff *skb;
+			enum can_state rx_state, tx_state;
+			u8 rxerr, txerr;
+
+			skb = alloc_can_err_skb(net, &cf);
+			if (!skb)
+				break;
+
+			txerr = hi3110_read(spi, HI3110_READ_TEC);
+			rxerr = hi3110_read(spi, HI3110_READ_REC);
+			cf->data[6] = txerr;
+			cf->data[7] = rxerr;
+			tx_state = txerr >= rxerr ? new_state : 0;
+			rx_state = txerr <= rxerr ? new_state : 0;
+			can_change_state(net, cf, tx_state, rx_state);
+			netif_rx_ni(skb);
+
+			if (new_state == CAN_STATE_BUS_OFF) {
+				can_bus_off(net);
+				if (priv->can.restart_ms == 0) {
+					priv->force_quit = 1;
+					hi3110_hw_sleep(spi);
+					break;
+				}
+			}
+		}
+
+		/* Update bus errors */
+		if ((intf & HI3110_INT_BUSERR) &&
+		    (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) {
+			struct can_frame *cf;
+			struct sk_buff *skb;
+
+			/* Check for protocol errors */
+			if (eflag & HI3110_ERR_PROTOCOL_MASK) {
+				skb = alloc_can_err_skb(net, &cf);
+				if (!skb)
+					break;
+
+				cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
+				priv->can.can_stats.bus_error++;
+				priv->net->stats.rx_errors++;
+				if (eflag & HI3110_ERR_BITERR)
+					cf->data[2] |= CAN_ERR_PROT_BIT;
+				else if (eflag & HI3110_ERR_FRMERR)
+					cf->data[2] |= CAN_ERR_PROT_FORM;
+				else if (eflag & HI3110_ERR_STUFERR)
+					cf->data[2] |= CAN_ERR_PROT_STUFF;
+				else if (eflag & HI3110_ERR_CRCERR)
+					cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+				else if (eflag & HI3110_ERR_ACKERR)
+					cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+
+				cf->data[6] = hi3110_read(spi, HI3110_READ_TEC);
+				cf->data[7] = hi3110_read(spi, HI3110_READ_REC);
+				netdev_dbg(priv->net, "Bus Error\n");
+				netif_rx_ni(skb);
+			}
+		}
+
+		if (intf == 0)
+			break;
+
+		if (intf & HI3110_INT_TXCPLT) {
+			net->stats.tx_packets++;
+			net->stats.tx_bytes += priv->tx_len - 1;
+			can_led_event(net, CAN_LED_EVENT_TX);
+			if (priv->tx_len) {
+				can_get_echo_skb(net, 0);
+				priv->tx_len = 0;
+			}
+			netif_wake_queue(net);
+		}
+	}
+	mutex_unlock(&priv->hi3110_lock);
+	return IRQ_HANDLED;
+}
+
+static int hi3110_open(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+	unsigned long flags = IRQF_ONESHOT | IRQF_TRIGGER_RISING;
+	int ret;
+
+	ret = open_candev(net);
+	if (ret)
+		return ret;
+
+	mutex_lock(&priv->hi3110_lock);
+	hi3110_power_enable(priv->transceiver, 1);
+
+	priv->force_quit = 0;
+	priv->tx_skb = NULL;
+	priv->tx_len = 0;
+
+	ret = request_threaded_irq(spi->irq, NULL, hi3110_can_ist,
+				   flags, DEVICE_NAME, priv);
+	if (ret) {
+		dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
+		goto out_close;
+	}
+
+	priv->wq = alloc_workqueue("hi3110_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
+				   0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto out_free_irq;
+	}
+	INIT_WORK(&priv->tx_work, hi3110_tx_work_handler);
+	INIT_WORK(&priv->restart_work, hi3110_restart_work_handler);
+
+	ret = hi3110_hw_reset(spi);
+	if (ret)
+		goto out_free_wq;
+
+	ret = hi3110_setup(net);
+	if (ret)
+		goto out_free_wq;
+
+	ret = hi3110_set_normal_mode(spi);
+	if (ret)
+		goto out_free_wq;
+
+	can_led_event(net, CAN_LED_EVENT_OPEN);
+	netif_wake_queue(net);
+	mutex_unlock(&priv->hi3110_lock);
+
+	return 0;
+
+ out_free_wq:
+	destroy_workqueue(priv->wq);
+ out_free_irq:
+	free_irq(spi->irq, priv);
+	hi3110_hw_sleep(spi);
+ out_close:
+	hi3110_power_enable(priv->transceiver, 0);
+	close_candev(net);
+	mutex_unlock(&priv->hi3110_lock);
+	return ret;
+}
+
+static const struct net_device_ops hi3110_netdev_ops = {
+	.ndo_open = hi3110_open,
+	.ndo_stop = hi3110_stop,
+	.ndo_start_xmit = hi3110_hard_start_xmit,
+};
+
+static const struct of_device_id hi3110_of_match[] = {
+	{
+		.compatible	= "holt,hi3110",
+		.data		= (void *)CAN_HI3110_HI3110,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, hi3110_of_match);
+
+static const struct spi_device_id hi3110_id_table[] = {
+	{
+		.name		= "hi3110",
+		.driver_data	= (kernel_ulong_t)CAN_HI3110_HI3110,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, hi3110_id_table);
+
+static int hi3110_can_probe(struct spi_device *spi)
+{
+	const struct of_device_id *of_id = of_match_device(hi3110_of_match,
+							   &spi->dev);
+	struct net_device *net;
+	struct hi3110_priv *priv;
+	struct clk *clk;
+	int freq, ret;
+
+	clk = devm_clk_get(&spi->dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(&spi->dev, "no CAN clock source defined\n");
+		return PTR_ERR(clk);
+	}
+	freq = clk_get_rate(clk);
+
+	/* Sanity check */
+	if (freq > 40000000)
+		return -ERANGE;
+
+	/* Allocate can/net device */
+	net = alloc_candev(sizeof(struct hi3110_priv), HI3110_TX_ECHO_SKB_MAX);
+	if (!net)
+		return -ENOMEM;
+
+	if (!IS_ERR(clk)) {
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			goto out_free;
+	}
+
+	net->netdev_ops = &hi3110_netdev_ops;
+	net->flags |= IFF_ECHO;
+
+	priv = netdev_priv(net);
+	priv->can.bittiming_const = &hi3110_bittiming_const;
+	priv->can.do_set_mode = hi3110_do_set_mode;
+	priv->can.do_get_berr_counter = hi3110_get_berr_counter;
+	priv->can.clock.freq = freq / 2;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
+		CAN_CTRLMODE_LOOPBACK |
+		CAN_CTRLMODE_LISTENONLY |
+		CAN_CTRLMODE_BERR_REPORTING;
+
+	if (of_id)
+		priv->model = (enum hi3110_model)of_id->data;
+	else
+		priv->model = spi_get_device_id(spi)->driver_data;
+	priv->net = net;
+	priv->clk = clk;
+
+	spi_set_drvdata(spi, priv);
+
+	/* Configure the SPI bus */
+	spi->bits_per_word = 8;
+	ret = spi_setup(spi);
+	if (ret)
+		goto out_clk;
+
+	priv->power = devm_regulator_get_optional(&spi->dev, "vdd");
+	priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver");
+	if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
+	    (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
+		ret = -EPROBE_DEFER;
+		goto out_clk;
+	}
+
+	ret = hi3110_power_enable(priv->power, 1);
+	if (ret)
+		goto out_clk;
+
+	priv->spi = spi;
+	mutex_init(&priv->hi3110_lock);
+
+	/* If requested, allocate DMA buffers */
+	if (hi3110_enable_dma) {
+		spi->dev.coherent_dma_mask = ~0;
+
+		/* Minimum coherent DMA allocation is PAGE_SIZE, so allocate
+		 * that much and share it between Tx and Rx DMA buffers.
+		 */
+		priv->spi_tx_buf = dmam_alloc_coherent(&spi->dev,
+						       PAGE_SIZE,
+						       &priv->spi_tx_dma,
+						       GFP_DMA);
+
+		if (priv->spi_tx_buf) {
+			priv->spi_rx_buf = (priv->spi_tx_buf + (PAGE_SIZE / 2));
+			priv->spi_rx_dma = (dma_addr_t)(priv->spi_tx_dma +
+							(PAGE_SIZE / 2));
+		} else {
+			/* Fall back to non-DMA */
+			hi3110_enable_dma = 0;
+		}
+	}
+
+	/* Allocate non-DMA buffers */
+	if (!hi3110_enable_dma) {
+		priv->spi_tx_buf = devm_kzalloc(&spi->dev, HI3110_RX_BUF_LEN,
+						GFP_KERNEL);
+		if (!priv->spi_tx_buf) {
+			ret = -ENOMEM;
+			goto error_probe;
+		}
+		priv->spi_rx_buf = devm_kzalloc(&spi->dev, HI3110_RX_BUF_LEN,
+						GFP_KERNEL);
+
+		if (!priv->spi_rx_buf) {
+			ret = -ENOMEM;
+			goto error_probe;
+		}
+	}
+
+	SET_NETDEV_DEV(net, &spi->dev);
+
+	ret = hi3110_hw_probe(spi);
+	if (ret) {
+		if (ret == -ENODEV)
+			dev_err(&spi->dev, "Cannot initialize %x. Wrong wiring?\n",
+				priv->model);
+		goto error_probe;
+	}
+	hi3110_hw_sleep(spi);
+
+	ret = register_candev(net);
+	if (ret)
+		goto error_probe;
+
+	devm_can_led_init(net);
+	netdev_info(net, "%x successfully initialized.\n", priv->model);
+
+	return 0;
+
+ error_probe:
+	hi3110_power_enable(priv->power, 0);
+
+ out_clk:
+	if (!IS_ERR(clk))
+		clk_disable_unprepare(clk);
+
+ out_free:
+	free_candev(net);
+
+	dev_err(&spi->dev, "Probe failed, err=%d\n", -ret);
+	return ret;
+}
+
+static int hi3110_can_remove(struct spi_device *spi)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct net_device *net = priv->net;
+
+	unregister_candev(net);
+
+	hi3110_power_enable(priv->power, 0);
+
+	if (!IS_ERR(priv->clk))
+		clk_disable_unprepare(priv->clk);
+
+	free_candev(net);
+
+	return 0;
+}
+
+static int __maybe_unused hi3110_can_suspend(struct device *dev)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct net_device *net = priv->net;
+
+	priv->force_quit = 1;
+	disable_irq(spi->irq);
+
+	/* Note: at this point neither IST nor workqueues are running.
+	 * open/stop cannot be called anyway so locking is not needed
+	 */
+	if (netif_running(net)) {
+		netif_device_detach(net);
+
+		hi3110_hw_sleep(spi);
+		hi3110_power_enable(priv->transceiver, 0);
+		priv->after_suspend = HI3110_AFTER_SUSPEND_UP;
+	} else {
+		priv->after_suspend = HI3110_AFTER_SUSPEND_DOWN;
+	}
+
+	if (!IS_ERR_OR_NULL(priv->power)) {
+		regulator_disable(priv->power);
+		priv->after_suspend |= HI3110_AFTER_SUSPEND_POWER;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused hi3110_can_resume(struct device *dev)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	if (priv->after_suspend & HI3110_AFTER_SUSPEND_POWER)
+		hi3110_power_enable(priv->power, 1);
+
+	if (priv->after_suspend & HI3110_AFTER_SUSPEND_UP) {
+		hi3110_power_enable(priv->transceiver, 1);
+		queue_work(priv->wq, &priv->restart_work);
+	} else {
+		priv->after_suspend = 0;
+	}
+
+	priv->force_quit = 0;
+	enable_irq(spi->irq);
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(hi3110_can_pm_ops, hi3110_can_suspend, hi3110_can_resume);
+
+static struct spi_driver hi3110_can_driver = {
+	.driver = {
+		.name = DEVICE_NAME,
+		.of_match_table = hi3110_of_match,
+		.pm = &hi3110_can_pm_ops,
+	},
+	.id_table = hi3110_id_table,
+	.probe = hi3110_can_probe,
+	.remove = hi3110_can_remove,
+};
+
+module_spi_driver(hi3110_can_driver);
+
+MODULE_AUTHOR("Akshay Bhat <akshay.bhat@timesys.com>");
+MODULE_AUTHOR("Casey Fitzpatrick <casey.fitzpatrick@timesys.com>");
+MODULE_DESCRIPTION("Holt HI-3110 CAN driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 6749b1829469..4d4941469cfc 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -17,25 +17,6 @@
  *
  */
 
-/*
- * Your platform definitions should specify module ram offsets and interrupt
- * number to use as follows:
- *
- * static struct ti_hecc_platform_data am3517_evm_hecc_pdata = {
- *         .scc_hecc_offset        = 0,
- *         .scc_ram_offset         = 0x3000,
- *         .hecc_ram_offset        = 0x3000,
- *         .mbx_offset             = 0x2000,
- *         .int_line               = 0,
- *         .revision               = 1,
- *         .transceiver_switch     = hecc_phy_control,
- * };
- *
- * Please see include/linux/can/platform/ti_hecc.h for description of
- * above fields.
- *
- */
-
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -46,11 +27,13 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
 #include <linux/can/led.h>
-#include <linux/can/platform/ti_hecc.h>
 
 #define DRV_NAME "ti_hecc"
 #define HECC_MODULE_VERSION     "0.7"
@@ -214,15 +197,14 @@ struct ti_hecc_priv {
 	struct net_device *ndev;
 	struct clk *clk;
 	void __iomem *base;
-	u32 scc_ram_offset;
-	u32 hecc_ram_offset;
-	u32 mbx_offset;
-	u32 int_line;
+	void __iomem *hecc_ram;
+	void __iomem *mbx;
+	bool use_hecc1int;
 	spinlock_t mbx_lock; /* CANME register needs protection */
 	u32 tx_head;
 	u32 tx_tail;
 	u32 rx_next;
-	void (*transceiver_switch)(int);
+	struct regulator *reg_xceiver;
 };
 
 static inline int get_tx_head_mb(struct ti_hecc_priv *priv)
@@ -242,20 +224,18 @@ static inline int get_tx_head_prio(struct ti_hecc_priv *priv)
 
 static inline void hecc_write_lam(struct ti_hecc_priv *priv, u32 mbxno, u32 val)
 {
-	__raw_writel(val, priv->base + priv->hecc_ram_offset + mbxno * 4);
+	__raw_writel(val, priv->hecc_ram + mbxno * 4);
 }
 
 static inline void hecc_write_mbx(struct ti_hecc_priv *priv, u32 mbxno,
 	u32 reg, u32 val)
 {
-	__raw_writel(val, priv->base + priv->mbx_offset + mbxno * 0x10 +
-			reg);
+	__raw_writel(val, priv->mbx + mbxno * 0x10 + reg);
 }
 
 static inline u32 hecc_read_mbx(struct ti_hecc_priv *priv, u32 mbxno, u32 reg)
 {
-	return __raw_readl(priv->base + priv->mbx_offset + mbxno * 0x10 +
-			reg);
+	return __raw_readl(priv->mbx + mbxno * 0x10 + reg);
 }
 
 static inline void hecc_write(struct ti_hecc_priv *priv, u32 reg, u32 val)
@@ -311,11 +291,16 @@ static int ti_hecc_set_btc(struct ti_hecc_priv *priv)
 	return 0;
 }
 
-static void ti_hecc_transceiver_switch(const struct ti_hecc_priv *priv,
-					int on)
+static int ti_hecc_transceiver_switch(const struct ti_hecc_priv *priv,
+				      int on)
 {
-	if (priv->transceiver_switch)
-		priv->transceiver_switch(on);
+	if (!priv->reg_xceiver)
+		return 0;
+
+	if (on)
+		return regulator_enable(priv->reg_xceiver);
+	else
+		return regulator_disable(priv->reg_xceiver);
 }
 
 static void ti_hecc_reset(struct net_device *ndev)
@@ -409,7 +394,7 @@ static void ti_hecc_start(struct net_device *ndev)
 
 	/* Prevent message over-write & Enable interrupts */
 	hecc_write(priv, HECC_CANOPC, HECC_SET_REG);
-	if (priv->int_line) {
+	if (priv->use_hecc1int) {
 		hecc_write(priv, HECC_CANMIL, HECC_SET_REG);
 		hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK |
 			HECC_CANGIM_I1EN | HECC_CANGIM_SIL);
@@ -760,7 +745,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 	unsigned long ack, flags;
 
 	int_status = hecc_read(priv,
-		(priv->int_line) ? HECC_CANGIF1 : HECC_CANGIF0);
+		(priv->use_hecc1int) ? HECC_CANGIF1 : HECC_CANGIF0);
 
 	if (!int_status)
 		return IRQ_NONE;
@@ -806,7 +791,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 	}
 
 	/* clear all interrupt conditions - read back to avoid spurious ints */
-	if (priv->int_line) {
+	if (priv->use_hecc1int) {
 		hecc_write(priv, HECC_CANGIF1, HECC_SET_REG);
 		int_status = hecc_read(priv, HECC_CANGIF1);
 	} else {
@@ -872,58 +857,87 @@ static const struct net_device_ops ti_hecc_netdev_ops = {
 	.ndo_change_mtu		= can_change_mtu,
 };
 
+static const struct of_device_id ti_hecc_dt_ids[] = {
+	{
+		.compatible = "ti,am3517-hecc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ti_hecc_dt_ids);
+
 static int ti_hecc_probe(struct platform_device *pdev)
 {
 	struct net_device *ndev = (struct net_device *)0;
 	struct ti_hecc_priv *priv;
-	struct ti_hecc_platform_data *pdata;
-	struct resource *mem, *irq;
-	void __iomem *addr;
+	struct device_node *np = pdev->dev.of_node;
+	struct resource *res, *irq;
+	struct regulator *reg_xceiver;
 	int err = -ENODEV;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (!pdata) {
-		dev_err(&pdev->dev, "No platform data\n");
-		goto probe_exit;
+	if (!IS_ENABLED(CONFIG_OF) || !np)
+		return -EINVAL;
+
+	reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver");
+	if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+	else if (IS_ERR(reg_xceiver))
+		reg_xceiver = NULL;
+
+	ndev = alloc_candev(sizeof(struct ti_hecc_priv), HECC_MAX_TX_MBOX);
+	if (!ndev) {
+		dev_err(&pdev->dev, "alloc_candev failed\n");
+		return -ENOMEM;
 	}
+	priv = netdev_priv(ndev);
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!mem) {
-		dev_err(&pdev->dev, "No mem resources\n");
-		goto probe_exit;
+	/* handle hecc memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hecc");
+	if (!res) {
+		dev_err(&pdev->dev, "can't get IORESOURCE_MEM hecc\n");
+		return -EINVAL;
 	}
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "No irq resource\n");
-		goto probe_exit;
+
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base)) {
+		dev_err(&pdev->dev, "hecc ioremap failed\n");
+		return PTR_ERR(priv->base);
 	}
-	if (!request_mem_region(mem->start, resource_size(mem), pdev->name)) {
-		dev_err(&pdev->dev, "HECC region already claimed\n");
-		err = -EBUSY;
-		goto probe_exit;
+
+	/* handle hecc-ram memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hecc-ram");
+	if (!res) {
+		dev_err(&pdev->dev, "can't get IORESOURCE_MEM hecc-ram\n");
+		return -EINVAL;
 	}
-	addr = ioremap(mem->start, resource_size(mem));
-	if (!addr) {
-		dev_err(&pdev->dev, "ioremap failed\n");
-		err = -ENOMEM;
-		goto probe_exit_free_region;
+
+	priv->hecc_ram = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->hecc_ram)) {
+		dev_err(&pdev->dev, "hecc-ram ioremap failed\n");
+		return PTR_ERR(priv->hecc_ram);
 	}
 
-	ndev = alloc_candev(sizeof(struct ti_hecc_priv), HECC_MAX_TX_MBOX);
-	if (!ndev) {
-		dev_err(&pdev->dev, "alloc_candev failed\n");
-		err = -ENOMEM;
-		goto probe_exit_iounmap;
+	/* handle mbx memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mbx");
+	if (!res) {
+		dev_err(&pdev->dev, "can't get IORESOURCE_MEM mbx\n");
+		return -EINVAL;
+	}
+
+	priv->mbx = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->mbx)) {
+		dev_err(&pdev->dev, "mbx ioremap failed\n");
+		return PTR_ERR(priv->mbx);
+	}
+
+	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!irq) {
+		dev_err(&pdev->dev, "No irq resource\n");
+		goto probe_exit;
 	}
 
-	priv = netdev_priv(ndev);
 	priv->ndev = ndev;
-	priv->base = addr;
-	priv->scc_ram_offset = pdata->scc_ram_offset;
-	priv->hecc_ram_offset = pdata->hecc_ram_offset;
-	priv->mbx_offset = pdata->mbx_offset;
-	priv->int_line = pdata->int_line;
-	priv->transceiver_switch = pdata->transceiver_switch;
+	priv->reg_xceiver = reg_xceiver;
+	priv->use_hecc1int = of_property_read_bool(np, "ti,use-hecc1int");
 
 	priv->can.bittiming_const = &ti_hecc_bittiming_const;
 	priv->can.do_set_mode = ti_hecc_do_set_mode;
@@ -971,32 +985,23 @@ probe_exit_clk:
 	clk_put(priv->clk);
 probe_exit_candev:
 	free_candev(ndev);
-probe_exit_iounmap:
-	iounmap(addr);
-probe_exit_free_region:
-	release_mem_region(mem->start, resource_size(mem));
 probe_exit:
 	return err;
 }
 
 static int ti_hecc_remove(struct platform_device *pdev)
 {
-	struct resource *res;
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct ti_hecc_priv *priv = netdev_priv(ndev);
 
 	unregister_candev(ndev);
 	clk_disable_unprepare(priv->clk);
 	clk_put(priv->clk);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	iounmap(priv->base);
-	release_mem_region(res->start, resource_size(res));
 	free_candev(ndev);
 
 	return 0;
 }
 
-
 #ifdef CONFIG_PM
 static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state)
 {
@@ -1045,6 +1050,7 @@ static int ti_hecc_resume(struct platform_device *pdev)
 static struct platform_driver ti_hecc_driver = {
 	.driver = {
 		.name    = DRV_NAME,
+		.of_match_table = ti_hecc_dt_ids,
 	},
 	.probe = ti_hecc_probe,
 	.remove = ti_hecc_remove,
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 8483a40e7e9e..c36f4bdcbf4f 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -72,6 +72,8 @@ config CAN_PEAK_USB
 	  PCAN-USB Pro         dual CAN 2.0b channels USB adapter
 	  PCAN-USB FD          single CAN-FD channel USB adapter
 	  PCAN-USB Pro FD      dual CAN-FD channels USB adapter
+	  PCAN-Chip USB        CAN-FD to USB stamp module
+	  PCAN-USB X6          6 CAN-FD channels USB adapter
 
 	  (see also http://www.peak-system.com).
 
@@ -81,4 +83,10 @@ config CAN_8DEV_USB
 	  This driver supports the USB2CAN interface
 	  from 8 devices (http://www.8devices.com).
 
+config CAN_MCBA_USB
+	tristate "Microchip CAN BUS Analyzer interface"
+	---help---
+	  This driver supports the CAN BUS Analyzer interface
+	  from Microchip (http://www.microchip.com/development-tools/).
+
 endmenu
diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index a64cf983fb87..164453fd55d0 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
 obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
 obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
+obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 300349fe8dc0..eecee7f8dfb7 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -739,13 +739,18 @@ static const struct net_device_ops gs_usb_netdev_ops = {
 static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
 {
 	struct gs_can *dev = netdev_priv(netdev);
-	struct gs_identify_mode imode;
+	struct gs_identify_mode *imode;
 	int rc;
 
+	imode = kmalloc(sizeof(*imode), GFP_KERNEL);
+
+	if (!imode)
+		return -ENOMEM;
+
 	if (do_identify)
-		imode.mode = GS_CAN_IDENTIFY_ON;
+		imode->mode = GS_CAN_IDENTIFY_ON;
 	else
-		imode.mode = GS_CAN_IDENTIFY_OFF;
+		imode->mode = GS_CAN_IDENTIFY_OFF;
 
 	rc = usb_control_msg(interface_to_usbdev(dev->iface),
 			     usb_sndctrlpipe(interface_to_usbdev(dev->iface),
@@ -755,10 +760,12 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
 			     USB_RECIP_INTERFACE,
 			     dev->channel,
 			     0,
-			     &imode,
-			     sizeof(imode),
+			     imode,
+			     sizeof(*imode),
 			     100);
 
+	kfree(imode);
+
 	return (rc > 0) ? 0 : rc;
 }
 
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
new file mode 100644
index 000000000000..7f0272558bef
--- /dev/null
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -0,0 +1,904 @@
+/* SocketCAN driver for Microchip CAN BUS Analyzer Tool
+ *
+ * Copyright (C) 2017 Mobica Limited
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.
+ *
+ * This driver is inspired by the 4.6.2 version of net/can/usb/usb_8dev.c
+ */
+
+#include <asm/unaligned.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/led.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+
+/* vendor and product id */
+#define MCBA_MODULE_NAME "mcba_usb"
+#define MCBA_VENDOR_ID 0x04d8
+#define MCBA_PRODUCT_ID 0x0a30
+
+/* driver constants */
+#define MCBA_MAX_RX_URBS 20
+#define MCBA_MAX_TX_URBS 20
+#define MCBA_CTX_FREE MCBA_MAX_TX_URBS
+
+/* RX buffer must be bigger than msg size since at the
+ * beggining USB messages are stacked.
+ */
+#define MCBA_USB_RX_BUFF_SIZE 64
+#define MCBA_USB_TX_BUFF_SIZE (sizeof(struct mcba_usb_msg))
+
+/* MCBA endpoint numbers */
+#define MCBA_USB_EP_IN 1
+#define MCBA_USB_EP_OUT 1
+
+/* Microchip command id */
+#define MBCA_CMD_RECEIVE_MESSAGE 0xE3
+#define MBCA_CMD_I_AM_ALIVE_FROM_CAN 0xF5
+#define MBCA_CMD_I_AM_ALIVE_FROM_USB 0xF7
+#define MBCA_CMD_CHANGE_BIT_RATE 0xA1
+#define MBCA_CMD_TRANSMIT_MESSAGE_EV 0xA3
+#define MBCA_CMD_SETUP_TERMINATION_RESISTANCE 0xA8
+#define MBCA_CMD_READ_FW_VERSION 0xA9
+#define MBCA_CMD_NOTHING_TO_SEND 0xFF
+#define MBCA_CMD_TRANSMIT_MESSAGE_RSP 0xE2
+
+#define MCBA_VER_REQ_USB 1
+#define MCBA_VER_REQ_CAN 2
+
+#define MCBA_SIDL_EXID_MASK 0x8
+#define MCBA_DLC_MASK 0xf
+#define MCBA_DLC_RTR_MASK 0x40
+
+#define MCBA_CAN_STATE_WRN_TH 95
+#define MCBA_CAN_STATE_ERR_PSV_TH 127
+
+#define MCBA_TERMINATION_DISABLED CAN_TERMINATION_DISABLED
+#define MCBA_TERMINATION_ENABLED 120
+
+struct mcba_usb_ctx {
+	struct mcba_priv *priv;
+	u32 ndx;
+	u8 dlc;
+	bool can;
+};
+
+/* Structure to hold all of our device specific stuff */
+struct mcba_priv {
+	struct can_priv can; /* must be the first member */
+	struct sk_buff *echo_skb[MCBA_MAX_TX_URBS];
+	struct mcba_usb_ctx tx_context[MCBA_MAX_TX_URBS];
+	struct usb_device *udev;
+	struct net_device *netdev;
+	struct usb_anchor tx_submitted;
+	struct usb_anchor rx_submitted;
+	struct can_berr_counter bec;
+	bool usb_ka_first_pass;
+	bool can_ka_first_pass;
+	bool can_speed_check;
+	atomic_t free_ctx_cnt;
+};
+
+/* CAN frame */
+struct __packed mcba_usb_msg_can {
+	u8 cmd_id;
+	__be16 eid;
+	__be16 sid;
+	u8 dlc;
+	u8 data[8];
+	u8 timestamp[4];
+	u8 checksum;
+};
+
+/* command frame */
+struct __packed mcba_usb_msg {
+	u8 cmd_id;
+	u8 unused[18];
+};
+
+struct __packed mcba_usb_msg_ka_usb {
+	u8 cmd_id;
+	u8 termination_state;
+	u8 soft_ver_major;
+	u8 soft_ver_minor;
+	u8 unused[15];
+};
+
+struct __packed mcba_usb_msg_ka_can {
+	u8 cmd_id;
+	u8 tx_err_cnt;
+	u8 rx_err_cnt;
+	u8 rx_buff_ovfl;
+	u8 tx_bus_off;
+	__be16 can_bitrate;
+	__le16 rx_lost;
+	u8 can_stat;
+	u8 soft_ver_major;
+	u8 soft_ver_minor;
+	u8 debug_mode;
+	u8 test_complete;
+	u8 test_result;
+	u8 unused[4];
+};
+
+struct __packed mcba_usb_msg_change_bitrate {
+	u8 cmd_id;
+	__be16 bitrate;
+	u8 unused[16];
+};
+
+struct __packed mcba_usb_msg_termination {
+	u8 cmd_id;
+	u8 termination;
+	u8 unused[17];
+};
+
+struct __packed mcba_usb_msg_fw_ver {
+	u8 cmd_id;
+	u8 pic;
+	u8 unused[17];
+};
+
+static const struct usb_device_id mcba_usb_table[] = {
+	{ USB_DEVICE(MCBA_VENDOR_ID, MCBA_PRODUCT_ID) },
+	{} /* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(usb, mcba_usb_table);
+
+static const u16 mcba_termination[] = { MCBA_TERMINATION_DISABLED,
+					MCBA_TERMINATION_ENABLED };
+
+static const u32 mcba_bitrate[] = { 20000,  33333,  50000,  80000,  83333,
+				    100000, 125000, 150000, 175000, 200000,
+				    225000, 250000, 275000, 300000, 500000,
+				    625000, 800000, 1000000 };
+
+static inline void mcba_init_ctx(struct mcba_priv *priv)
+{
+	int i = 0;
+
+	for (i = 0; i < MCBA_MAX_TX_URBS; i++) {
+		priv->tx_context[i].ndx = MCBA_CTX_FREE;
+		priv->tx_context[i].priv = priv;
+	}
+
+	atomic_set(&priv->free_ctx_cnt, ARRAY_SIZE(priv->tx_context));
+}
+
+static inline struct mcba_usb_ctx *mcba_usb_get_free_ctx(struct mcba_priv *priv,
+							 struct can_frame *cf)
+{
+	int i = 0;
+	struct mcba_usb_ctx *ctx = NULL;
+
+	for (i = 0; i < MCBA_MAX_TX_URBS; i++) {
+		if (priv->tx_context[i].ndx == MCBA_CTX_FREE) {
+			ctx = &priv->tx_context[i];
+			ctx->ndx = i;
+
+			if (cf) {
+				ctx->can = true;
+				ctx->dlc = cf->can_dlc;
+			} else {
+				ctx->can = false;
+				ctx->dlc = 0;
+			}
+
+			atomic_dec(&priv->free_ctx_cnt);
+			break;
+		}
+	}
+
+	if (!atomic_read(&priv->free_ctx_cnt))
+		/* That was the last free ctx. Slow down tx path */
+		netif_stop_queue(priv->netdev);
+
+	return ctx;
+}
+
+/* mcba_usb_free_ctx and mcba_usb_get_free_ctx are executed by different
+ * threads. The order of execution in below function is important.
+ */
+static inline void mcba_usb_free_ctx(struct mcba_usb_ctx *ctx)
+{
+	/* Increase number of free ctxs before freeing ctx */
+	atomic_inc(&ctx->priv->free_ctx_cnt);
+
+	ctx->ndx = MCBA_CTX_FREE;
+
+	/* Wake up the queue once ctx is marked free */
+	netif_wake_queue(ctx->priv->netdev);
+}
+
+static void mcba_usb_write_bulk_callback(struct urb *urb)
+{
+	struct mcba_usb_ctx *ctx = urb->context;
+	struct net_device *netdev;
+
+	WARN_ON(!ctx);
+
+	netdev = ctx->priv->netdev;
+
+	/* free up our allocated buffer */
+	usb_free_coherent(urb->dev, urb->transfer_buffer_length,
+			  urb->transfer_buffer, urb->transfer_dma);
+
+	if (ctx->can) {
+		if (!netif_device_present(netdev))
+			return;
+
+		netdev->stats.tx_packets++;
+		netdev->stats.tx_bytes += ctx->dlc;
+
+		can_led_event(netdev, CAN_LED_EVENT_TX);
+		can_get_echo_skb(netdev, ctx->ndx);
+	}
+
+	if (urb->status)
+		netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status);
+
+	/* Release the context */
+	mcba_usb_free_ctx(ctx);
+}
+
+/* Send data to device */
+static netdev_tx_t mcba_usb_xmit(struct mcba_priv *priv,
+				 struct mcba_usb_msg *usb_msg,
+				 struct mcba_usb_ctx *ctx)
+{
+	struct urb *urb;
+	u8 *buf;
+	int err;
+
+	/* create a URB, and a buffer for it, and copy the data to the URB */
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb)
+		return -ENOMEM;
+
+	buf = usb_alloc_coherent(priv->udev, MCBA_USB_TX_BUFF_SIZE, GFP_ATOMIC,
+				 &urb->transfer_dma);
+	if (!buf) {
+		err = -ENOMEM;
+		goto nomembuf;
+	}
+
+	memcpy(buf, usb_msg, MCBA_USB_TX_BUFF_SIZE);
+
+	usb_fill_bulk_urb(urb, priv->udev,
+			  usb_sndbulkpipe(priv->udev, MCBA_USB_EP_OUT), buf,
+			  MCBA_USB_TX_BUFF_SIZE, mcba_usb_write_bulk_callback,
+			  ctx);
+
+	urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+	usb_anchor_urb(urb, &priv->tx_submitted);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (unlikely(err))
+		goto failed;
+
+	/* Release our reference to this URB, the USB core will eventually free
+	 * it entirely.
+	 */
+	usb_free_urb(urb);
+
+	return 0;
+
+failed:
+	usb_unanchor_urb(urb);
+	usb_free_coherent(priv->udev, MCBA_USB_TX_BUFF_SIZE, buf,
+			  urb->transfer_dma);
+
+	if (err == -ENODEV)
+		netif_device_detach(priv->netdev);
+	else
+		netdev_warn(priv->netdev, "failed tx_urb %d\n", err);
+
+nomembuf:
+	usb_free_urb(urb);
+
+	return err;
+}
+
+/* Send data to device */
+static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb,
+				       struct net_device *netdev)
+{
+	struct mcba_priv *priv = netdev_priv(netdev);
+	struct can_frame *cf = (struct can_frame *)skb->data;
+	struct mcba_usb_ctx *ctx = NULL;
+	struct net_device_stats *stats = &priv->netdev->stats;
+	u16 sid;
+	int err;
+	struct mcba_usb_msg_can usb_msg = {
+		.cmd_id = MBCA_CMD_TRANSMIT_MESSAGE_EV
+	};
+
+	if (can_dropped_invalid_skb(netdev, skb))
+		return NETDEV_TX_OK;
+
+	ctx = mcba_usb_get_free_ctx(priv, cf);
+	if (!ctx)
+		return NETDEV_TX_BUSY;
+
+	can_put_echo_skb(skb, priv->netdev, ctx->ndx);
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		/* SIDH    | SIDL                 | EIDH   | EIDL
+		 * 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0
+		 */
+		sid = MCBA_SIDL_EXID_MASK;
+		/* store 28-18 bits */
+		sid |= (cf->can_id & 0x1ffc0000) >> 13;
+		/* store 17-16 bits */
+		sid |= (cf->can_id & 0x30000) >> 16;
+		put_unaligned_be16(sid, &usb_msg.sid);
+
+		/* store 15-0 bits */
+		put_unaligned_be16(cf->can_id & 0xffff, &usb_msg.eid);
+	} else {
+		/* SIDH   | SIDL
+		 * 10 - 3 | 2 1 0 x x x x x
+		 */
+		put_unaligned_be16((cf->can_id & CAN_SFF_MASK) << 5,
+				   &usb_msg.sid);
+		usb_msg.eid = 0;
+	}
+
+	usb_msg.dlc = cf->can_dlc;
+
+	memcpy(usb_msg.data, cf->data, usb_msg.dlc);
+
+	if (cf->can_id & CAN_RTR_FLAG)
+		usb_msg.dlc |= MCBA_DLC_RTR_MASK;
+
+	err = mcba_usb_xmit(priv, (struct mcba_usb_msg *)&usb_msg, ctx);
+	if (err)
+		goto xmit_failed;
+
+	return NETDEV_TX_OK;
+
+xmit_failed:
+	can_free_echo_skb(priv->netdev, ctx->ndx);
+	mcba_usb_free_ctx(ctx);
+	dev_kfree_skb(skb);
+	stats->tx_dropped++;
+
+	return NETDEV_TX_OK;
+}
+
+/* Send cmd to device */
+static void mcba_usb_xmit_cmd(struct mcba_priv *priv,
+			      struct mcba_usb_msg *usb_msg)
+{
+	struct mcba_usb_ctx *ctx = NULL;
+	int err;
+
+	ctx = mcba_usb_get_free_ctx(priv, NULL);
+	if (!ctx) {
+		netdev_err(priv->netdev,
+			   "Lack of free ctx. Sending (%d) cmd aborted",
+			   usb_msg->cmd_id);
+
+		return;
+	}
+
+	err = mcba_usb_xmit(priv, usb_msg, ctx);
+	if (err)
+		netdev_err(priv->netdev, "Failed to send cmd (%d)",
+			   usb_msg->cmd_id);
+}
+
+static void mcba_usb_xmit_change_bitrate(struct mcba_priv *priv, u16 bitrate)
+{
+	struct mcba_usb_msg_change_bitrate usb_msg = {
+		.cmd_id = MBCA_CMD_CHANGE_BIT_RATE
+	};
+
+	put_unaligned_be16(bitrate, &usb_msg.bitrate);
+
+	mcba_usb_xmit_cmd(priv, (struct mcba_usb_msg *)&usb_msg);
+}
+
+static void mcba_usb_xmit_read_fw_ver(struct mcba_priv *priv, u8 pic)
+{
+	struct mcba_usb_msg_fw_ver usb_msg = {
+		.cmd_id = MBCA_CMD_READ_FW_VERSION,
+		.pic = pic
+	};
+
+	mcba_usb_xmit_cmd(priv, (struct mcba_usb_msg *)&usb_msg);
+}
+
+static void mcba_usb_process_can(struct mcba_priv *priv,
+				 struct mcba_usb_msg_can *msg)
+{
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats = &priv->netdev->stats;
+	u16 sid;
+
+	skb = alloc_can_skb(priv->netdev, &cf);
+	if (!skb)
+		return;
+
+	sid = get_unaligned_be16(&msg->sid);
+
+	if (sid & MCBA_SIDL_EXID_MASK) {
+		/* SIDH    | SIDL                 | EIDH   | EIDL
+		 * 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0
+		 */
+		cf->can_id = CAN_EFF_FLAG;
+
+		/* store 28-18 bits */
+		cf->can_id |= (sid & 0xffe0) << 13;
+		/* store 17-16 bits */
+		cf->can_id |= (sid & 3) << 16;
+		/* store 15-0 bits */
+		cf->can_id |= get_unaligned_be16(&msg->eid);
+	} else {
+		/* SIDH   | SIDL
+		 * 10 - 3 | 2 1 0 x x x x x
+		 */
+		cf->can_id = (sid & 0xffe0) >> 5;
+	}
+
+	if (msg->dlc & MCBA_DLC_RTR_MASK)
+		cf->can_id |= CAN_RTR_FLAG;
+
+	cf->can_dlc = get_can_dlc(msg->dlc & MCBA_DLC_MASK);
+
+	memcpy(cf->data, msg->data, cf->can_dlc);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+
+	can_led_event(priv->netdev, CAN_LED_EVENT_RX);
+	netif_rx(skb);
+}
+
+static void mcba_usb_process_ka_usb(struct mcba_priv *priv,
+				    struct mcba_usb_msg_ka_usb *msg)
+{
+	if (unlikely(priv->usb_ka_first_pass)) {
+		netdev_info(priv->netdev, "PIC USB version %hhu.%hhu\n",
+			    msg->soft_ver_major, msg->soft_ver_minor);
+
+		priv->usb_ka_first_pass = false;
+	}
+
+	if (msg->termination_state)
+		priv->can.termination = MCBA_TERMINATION_ENABLED;
+	else
+		priv->can.termination = MCBA_TERMINATION_DISABLED;
+}
+
+static u32 convert_can2host_bitrate(struct mcba_usb_msg_ka_can *msg)
+{
+	const u32 bitrate = get_unaligned_be16(&msg->can_bitrate);
+
+	if ((bitrate == 33) || (bitrate == 83))
+		return bitrate * 1000 + 333;
+	else
+		return bitrate * 1000;
+}
+
+static void mcba_usb_process_ka_can(struct mcba_priv *priv,
+				    struct mcba_usb_msg_ka_can *msg)
+{
+	if (unlikely(priv->can_ka_first_pass)) {
+		netdev_info(priv->netdev, "PIC CAN version %hhu.%hhu\n",
+			    msg->soft_ver_major, msg->soft_ver_minor);
+
+		priv->can_ka_first_pass = false;
+	}
+
+	if (unlikely(priv->can_speed_check)) {
+		const u32 bitrate = convert_can2host_bitrate(msg);
+
+		priv->can_speed_check = false;
+
+		if (bitrate != priv->can.bittiming.bitrate)
+			netdev_err(
+			    priv->netdev,
+			    "Wrong bitrate reported by the device (%u). Expected %u",
+			    bitrate, priv->can.bittiming.bitrate);
+	}
+
+	priv->bec.txerr = msg->tx_err_cnt;
+	priv->bec.rxerr = msg->rx_err_cnt;
+
+	if (msg->tx_bus_off)
+		priv->can.state = CAN_STATE_BUS_OFF;
+
+	else if ((priv->bec.txerr > MCBA_CAN_STATE_ERR_PSV_TH) ||
+		 (priv->bec.rxerr > MCBA_CAN_STATE_ERR_PSV_TH))
+		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+
+	else if ((priv->bec.txerr > MCBA_CAN_STATE_WRN_TH) ||
+		 (priv->bec.rxerr > MCBA_CAN_STATE_WRN_TH))
+		priv->can.state = CAN_STATE_ERROR_WARNING;
+}
+
+static void mcba_usb_process_rx(struct mcba_priv *priv,
+				struct mcba_usb_msg *msg)
+{
+	switch (msg->cmd_id) {
+	case MBCA_CMD_I_AM_ALIVE_FROM_CAN:
+		mcba_usb_process_ka_can(priv,
+					(struct mcba_usb_msg_ka_can *)msg);
+		break;
+
+	case MBCA_CMD_I_AM_ALIVE_FROM_USB:
+		mcba_usb_process_ka_usb(priv,
+					(struct mcba_usb_msg_ka_usb *)msg);
+		break;
+
+	case MBCA_CMD_RECEIVE_MESSAGE:
+		mcba_usb_process_can(priv, (struct mcba_usb_msg_can *)msg);
+		break;
+
+	case MBCA_CMD_NOTHING_TO_SEND:
+		/* Side effect of communication between PIC_USB and PIC_CAN.
+		 * PIC_CAN is telling us that it has nothing to send
+		 */
+		break;
+
+	case MBCA_CMD_TRANSMIT_MESSAGE_RSP:
+		/* Transmission response from the device containing timestamp */
+		break;
+
+	default:
+		netdev_warn(priv->netdev, "Unsupported msg (0x%hhX)",
+			    msg->cmd_id);
+		break;
+	}
+}
+
+/* Callback for reading data from device
+ *
+ * Check urb status, call read function and resubmit urb read operation.
+ */
+static void mcba_usb_read_bulk_callback(struct urb *urb)
+{
+	struct mcba_priv *priv = urb->context;
+	struct net_device *netdev;
+	int retval;
+	int pos = 0;
+
+	netdev = priv->netdev;
+
+	if (!netif_device_present(netdev))
+		return;
+
+	switch (urb->status) {
+	case 0: /* success */
+		break;
+
+	case -ENOENT:
+	case -ESHUTDOWN:
+		return;
+
+	default:
+		netdev_info(netdev, "Rx URB aborted (%d)\n", urb->status);
+
+		goto resubmit_urb;
+	}
+
+	while (pos < urb->actual_length) {
+		struct mcba_usb_msg *msg;
+
+		if (pos + sizeof(struct mcba_usb_msg) > urb->actual_length) {
+			netdev_err(priv->netdev, "format error\n");
+			break;
+		}
+
+		msg = (struct mcba_usb_msg *)(urb->transfer_buffer + pos);
+		mcba_usb_process_rx(priv, msg);
+
+		pos += sizeof(struct mcba_usb_msg);
+	}
+
+resubmit_urb:
+
+	usb_fill_bulk_urb(urb, priv->udev,
+			  usb_rcvbulkpipe(priv->udev, MCBA_USB_EP_OUT),
+			  urb->transfer_buffer, MCBA_USB_RX_BUFF_SIZE,
+			  mcba_usb_read_bulk_callback, priv);
+
+	retval = usb_submit_urb(urb, GFP_ATOMIC);
+
+	if (retval == -ENODEV)
+		netif_device_detach(netdev);
+	else if (retval)
+		netdev_err(netdev, "failed resubmitting read bulk urb: %d\n",
+			   retval);
+}
+
+/* Start USB device */
+static int mcba_usb_start(struct mcba_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	int err, i;
+
+	mcba_init_ctx(priv);
+
+	for (i = 0; i < MCBA_MAX_RX_URBS; i++) {
+		struct urb *urb = NULL;
+		u8 *buf;
+
+		/* create a URB, and a buffer for it */
+		urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urb) {
+			err = -ENOMEM;
+			break;
+		}
+
+		buf = usb_alloc_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
+					 GFP_KERNEL, &urb->transfer_dma);
+		if (!buf) {
+			netdev_err(netdev, "No memory left for USB buffer\n");
+			usb_free_urb(urb);
+			err = -ENOMEM;
+			break;
+		}
+
+		usb_fill_bulk_urb(urb, priv->udev,
+				  usb_rcvbulkpipe(priv->udev, MCBA_USB_EP_IN),
+				  buf, MCBA_USB_RX_BUFF_SIZE,
+				  mcba_usb_read_bulk_callback, priv);
+		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+		usb_anchor_urb(urb, &priv->rx_submitted);
+
+		err = usb_submit_urb(urb, GFP_KERNEL);
+		if (err) {
+			usb_unanchor_urb(urb);
+			usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
+					  buf, urb->transfer_dma);
+			usb_free_urb(urb);
+			break;
+		}
+
+		/* Drop reference, USB core will take care of freeing it */
+		usb_free_urb(urb);
+	}
+
+	/* Did we submit any URBs */
+	if (i == 0) {
+		netdev_warn(netdev, "couldn't setup read URBs\n");
+		return err;
+	}
+
+	/* Warn if we've couldn't transmit all the URBs */
+	if (i < MCBA_MAX_RX_URBS)
+		netdev_warn(netdev, "rx performance may be slow\n");
+
+	mcba_usb_xmit_read_fw_ver(priv, MCBA_VER_REQ_USB);
+	mcba_usb_xmit_read_fw_ver(priv, MCBA_VER_REQ_CAN);
+
+	return err;
+}
+
+/* Open USB device */
+static int mcba_usb_open(struct net_device *netdev)
+{
+	struct mcba_priv *priv = netdev_priv(netdev);
+	int err;
+
+	/* common open */
+	err = open_candev(netdev);
+	if (err)
+		return err;
+
+	priv->can_speed_check = true;
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	can_led_event(netdev, CAN_LED_EVENT_OPEN);
+	netif_start_queue(netdev);
+
+	return 0;
+}
+
+static void mcba_urb_unlink(struct mcba_priv *priv)
+{
+	usb_kill_anchored_urbs(&priv->rx_submitted);
+	usb_kill_anchored_urbs(&priv->tx_submitted);
+}
+
+/* Close USB device */
+static int mcba_usb_close(struct net_device *netdev)
+{
+	struct mcba_priv *priv = netdev_priv(netdev);
+
+	priv->can.state = CAN_STATE_STOPPED;
+
+	netif_stop_queue(netdev);
+
+	/* Stop polling */
+	mcba_urb_unlink(priv);
+
+	close_candev(netdev);
+	can_led_event(netdev, CAN_LED_EVENT_STOP);
+
+	return 0;
+}
+
+/* Set network device mode
+ *
+ * Maybe we should leave this function empty, because the device
+ * set mode variable with open command.
+ */
+static int mcba_net_set_mode(struct net_device *netdev, enum can_mode mode)
+{
+	return 0;
+}
+
+static int mcba_net_get_berr_counter(const struct net_device *netdev,
+				     struct can_berr_counter *bec)
+{
+	struct mcba_priv *priv = netdev_priv(netdev);
+
+	bec->txerr = priv->bec.txerr;
+	bec->rxerr = priv->bec.rxerr;
+
+	return 0;
+}
+
+static const struct net_device_ops mcba_netdev_ops = {
+	.ndo_open = mcba_usb_open,
+	.ndo_stop = mcba_usb_close,
+	.ndo_start_xmit = mcba_usb_start_xmit,
+};
+
+/* Microchip CANBUS has hardcoded bittiming values by default.
+ * This function sends request via USB to change the speed and align bittiming
+ * values for presentation purposes only
+ */
+static int mcba_net_set_bittiming(struct net_device *netdev)
+{
+	struct mcba_priv *priv = netdev_priv(netdev);
+	const u16 bitrate_kbps = priv->can.bittiming.bitrate / 1000;
+
+	mcba_usb_xmit_change_bitrate(priv, bitrate_kbps);
+
+	return 0;
+}
+
+static int mcba_set_termination(struct net_device *netdev, u16 term)
+{
+	struct mcba_priv *priv = netdev_priv(netdev);
+	struct mcba_usb_msg_termination usb_msg = {
+		.cmd_id = MBCA_CMD_SETUP_TERMINATION_RESISTANCE
+	};
+
+	if (term == MCBA_TERMINATION_ENABLED)
+		usb_msg.termination = 1;
+	else
+		usb_msg.termination = 0;
+
+	mcba_usb_xmit_cmd(priv, (struct mcba_usb_msg *)&usb_msg);
+
+	return 0;
+}
+
+static int mcba_usb_probe(struct usb_interface *intf,
+			  const struct usb_device_id *id)
+{
+	struct net_device *netdev;
+	struct mcba_priv *priv;
+	int err = -ENOMEM;
+	struct usb_device *usbdev = interface_to_usbdev(intf);
+
+	netdev = alloc_candev(sizeof(struct mcba_priv), MCBA_MAX_TX_URBS);
+	if (!netdev) {
+		dev_err(&intf->dev, "Couldn't alloc candev\n");
+		return -ENOMEM;
+	}
+
+	priv = netdev_priv(netdev);
+
+	priv->udev = usbdev;
+	priv->netdev = netdev;
+	priv->usb_ka_first_pass = true;
+	priv->can_ka_first_pass = true;
+	priv->can_speed_check = false;
+
+	init_usb_anchor(&priv->rx_submitted);
+	init_usb_anchor(&priv->tx_submitted);
+
+	usb_set_intfdata(intf, priv);
+
+	/* Init CAN device */
+	priv->can.state = CAN_STATE_STOPPED;
+	priv->can.termination_const = mcba_termination;
+	priv->can.termination_const_cnt = ARRAY_SIZE(mcba_termination);
+	priv->can.bitrate_const = mcba_bitrate;
+	priv->can.bitrate_const_cnt = ARRAY_SIZE(mcba_bitrate);
+
+	priv->can.do_set_termination = mcba_set_termination;
+	priv->can.do_set_mode = mcba_net_set_mode;
+	priv->can.do_get_berr_counter = mcba_net_get_berr_counter;
+	priv->can.do_set_bittiming = mcba_net_set_bittiming;
+
+	netdev->netdev_ops = &mcba_netdev_ops;
+
+	netdev->flags |= IFF_ECHO; /* we support local echo */
+
+	SET_NETDEV_DEV(netdev, &intf->dev);
+
+	err = register_candev(netdev);
+	if (err) {
+		netdev_err(netdev, "couldn't register CAN device: %d\n", err);
+
+		goto cleanup_free_candev;
+	}
+
+	devm_can_led_init(netdev);
+
+	/* Start USB dev only if we have successfully registered CAN device */
+	err = mcba_usb_start(priv);
+	if (err) {
+		if (err == -ENODEV)
+			netif_device_detach(priv->netdev);
+
+		netdev_warn(netdev, "couldn't start device: %d\n", err);
+
+		goto cleanup_unregister_candev;
+	}
+
+	dev_info(&intf->dev, "Microchip CAN BUS analizer connected\n");
+
+	return 0;
+
+cleanup_unregister_candev:
+	unregister_candev(priv->netdev);
+
+cleanup_free_candev:
+	free_candev(netdev);
+
+	return err;
+}
+
+/* Called by the usb core when driver is unloaded or device is removed */
+static void mcba_usb_disconnect(struct usb_interface *intf)
+{
+	struct mcba_priv *priv = usb_get_intfdata(intf);
+
+	usb_set_intfdata(intf, NULL);
+
+	netdev_info(priv->netdev, "device disconnected\n");
+
+	unregister_candev(priv->netdev);
+	free_candev(priv->netdev);
+
+	mcba_urb_unlink(priv);
+}
+
+static struct usb_driver mcba_usb_driver = {
+	.name = MCBA_MODULE_NAME,
+	.probe = mcba_usb_probe,
+	.disconnect = mcba_usb_disconnect,
+	.id_table = mcba_usb_table,
+};
+
+module_usb_driver(mcba_usb_driver);
+
+MODULE_AUTHOR("Remigiusz Kołłątaj <remigiusz.kollataj@mobica.com>");
+MODULE_DESCRIPTION("SocketCAN driver for Microchip CAN BUS Analyzer Tool");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 0b0302af3bd2..57913dbbae0a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -39,6 +39,7 @@ static struct usb_device_id peak_usb_table[] = {
 	{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)},
 	{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)},
 	{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)},
+	{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBCHIP_PRODUCT_ID)},
 	{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBX6_PRODUCT_ID)},
 	{} /* Terminating entry */
 };
@@ -51,6 +52,7 @@ static const struct peak_usb_adapter *const peak_usb_adapters_list[] = {
 	&pcan_usb_pro,
 	&pcan_usb_fd,
 	&pcan_usb_pro_fd,
+	&pcan_usb_chip,
 	&pcan_usb_x6,
 };
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
index 3cbfb069893d..c01316cac354 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
@@ -27,6 +27,7 @@
 #define PCAN_USBPRO_PRODUCT_ID		0x000d
 #define PCAN_USBPROFD_PRODUCT_ID	0x0011
 #define PCAN_USBFD_PRODUCT_ID		0x0012
+#define PCAN_USBCHIP_PRODUCT_ID		0x0013
 #define PCAN_USBX6_PRODUCT_ID		0x0014
 
 #define PCAN_USB_DRIVER_NAME		"peak_usb"
@@ -90,6 +91,7 @@ struct peak_usb_adapter {
 extern const struct peak_usb_adapter pcan_usb;
 extern const struct peak_usb_adapter pcan_usb_pro;
 extern const struct peak_usb_adapter pcan_usb_fd;
+extern const struct peak_usb_adapter pcan_usb_chip;
 extern const struct peak_usb_adapter pcan_usb_pro_fd;
 extern const struct peak_usb_adapter pcan_usb_x6;
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 304732550f0a..7ccdc3e30c98 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -19,10 +19,10 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
+#include <linux/can/dev/peak_canfd.h>
 
 #include "pcan_usb_core.h"
 #include "pcan_usb_pro.h"
-#include "pcan_ucan.h"
 
 MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter");
 MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter");
@@ -238,7 +238,7 @@ static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf)
 
 	/* 1st, reset error counters: */
 	prc = (struct pucan_wr_err_cnt *)pc;
-	prc->opcode_channel = pucan_cmd_opcode_channel(dev,
+	prc->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 						       PUCAN_CMD_WR_ERR_CNT);
 
 	/* select both counters */
@@ -257,9 +257,10 @@ static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf)
 
 		puo->opcode_channel =
 			(dev->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) ?
-			pucan_cmd_opcode_channel(dev,
+			pucan_cmd_opcode_channel(dev->ctrl_idx,
 						 PUCAN_CMD_CLR_DIS_OPTION) :
-			pucan_cmd_opcode_channel(dev, PUCAN_CMD_SET_EN_OPTION);
+			pucan_cmd_opcode_channel(dev->ctrl_idx,
+						 PUCAN_CMD_SET_EN_OPTION);
 
 		puo->options = cpu_to_le16(PUCAN_OPTION_CANDFDISO);
 
@@ -274,7 +275,7 @@ static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf)
 
 	/* next, go back to operational mode */
 	cmd = (struct pucan_command *)pc;
-	cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+	cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 				(dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) ?
 						PUCAN_CMD_LISTEN_ONLY_MODE :
 						PUCAN_CMD_NORMAL_MODE);
@@ -296,7 +297,7 @@ static int pcan_usb_fd_set_bus(struct peak_usb_device *dev, u8 onoff)
 		struct pucan_command *cmd = (struct pucan_command *)pc;
 
 		/* build cmd to go back to reset mode */
-		cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+		cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 							PUCAN_CMD_RESET_MODE);
 		l = sizeof(struct pucan_command);
 	}
@@ -332,7 +333,7 @@ static int pcan_usb_fd_set_filter_std(struct peak_usb_device *dev, int idx,
 	}
 
 	for (i = idx; i < n; i++, cmd++) {
-		cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+		cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 							PUCAN_CMD_FILTER_STD);
 		cmd->idx = cpu_to_le16(i);
 		cmd->mask = cpu_to_le32(mask);
@@ -352,7 +353,7 @@ static int pcan_usb_fd_set_options(struct peak_usb_device *dev,
 {
 	struct pcan_ufd_options *cmd = pcan_usb_fd_cmd_buffer(dev);
 
-	cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+	cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 					(onoff) ? PUCAN_CMD_SET_EN_OPTION :
 						  PUCAN_CMD_CLR_DIS_OPTION);
 
@@ -368,7 +369,7 @@ static int pcan_usb_fd_set_can_led(struct peak_usb_device *dev, u8 led_mode)
 {
 	struct pcan_ufd_led *cmd = pcan_usb_fd_cmd_buffer(dev);
 
-	cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+	cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 						       PCAN_UFD_CMD_LED_SET);
 	cmd->mode = led_mode;
 
@@ -382,7 +383,7 @@ static int pcan_usb_fd_set_clock_domain(struct peak_usb_device *dev,
 {
 	struct pcan_ufd_clock *cmd = pcan_usb_fd_cmd_buffer(dev);
 
-	cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+	cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 						       PCAN_UFD_CMD_CLK_SET);
 	cmd->mode = clk_mode;
 
@@ -396,7 +397,7 @@ static int pcan_usb_fd_set_bittiming_slow(struct peak_usb_device *dev,
 {
 	struct pucan_timing_slow *cmd = pcan_usb_fd_cmd_buffer(dev);
 
-	cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+	cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 						       PUCAN_CMD_TIMING_SLOW);
 	cmd->sjw_t = PUCAN_TSLOW_SJW_T(bt->sjw - 1,
 				dev->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES);
@@ -417,7 +418,7 @@ static int pcan_usb_fd_set_bittiming_fast(struct peak_usb_device *dev,
 {
 	struct pucan_timing_fast *cmd = pcan_usb_fd_cmd_buffer(dev);
 
-	cmd->opcode_channel = pucan_cmd_opcode_channel(dev,
+	cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx,
 						       PUCAN_CMD_TIMING_FAST);
 	cmd->sjw = PUCAN_TFAST_SJW(bt->sjw - 1);
 	cmd->tseg2 = PUCAN_TFAST_TSEG2(bt->phase_seg2 - 1);
@@ -1061,6 +1062,78 @@ const struct peak_usb_adapter pcan_usb_fd = {
 	.do_get_berr_counter = pcan_usb_fd_get_berr_counter,
 };
 
+/* describes the PCAN-CHIP USB */
+static const struct can_bittiming_const pcan_usb_chip_const = {
+	.name = "pcan_chip_usb",
+	.tseg1_min = 1,
+	.tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS),
+	.tseg2_min = 1,
+	.tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS),
+	.sjw_max = (1 << PUCAN_TSLOW_SJW_BITS),
+	.brp_min = 1,
+	.brp_max = (1 << PUCAN_TSLOW_BRP_BITS),
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const pcan_usb_chip_data_const = {
+	.name = "pcan_chip_usb",
+	.tseg1_min = 1,
+	.tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS),
+	.tseg2_min = 1,
+	.tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS),
+	.sjw_max = (1 << PUCAN_TFAST_SJW_BITS),
+	.brp_min = 1,
+	.brp_max = (1 << PUCAN_TFAST_BRP_BITS),
+	.brp_inc = 1,
+};
+
+const struct peak_usb_adapter pcan_usb_chip = {
+	.name = "PCAN-Chip USB",
+	.device_id = PCAN_USBCHIP_PRODUCT_ID,
+	.ctrl_count = PCAN_USBFD_CHANNEL_COUNT,
+	.ctrlmode_supported = CAN_CTRLMODE_FD |
+		CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY,
+	.clock = {
+		.freq = PCAN_UFD_CRYSTAL_HZ,
+	},
+	.bittiming_const = &pcan_usb_chip_const,
+	.data_bittiming_const = &pcan_usb_chip_data_const,
+
+	/* size of device private data */
+	.sizeof_dev_private = sizeof(struct pcan_usb_fd_device),
+
+	/* timestamps usage */
+	.ts_used_bits = 32,
+	.ts_period = 1000000, /* calibration period in ts. */
+	.us_per_ts_scale = 1, /* us = (ts * scale) >> shift */
+	.us_per_ts_shift = 0,
+
+	/* give here messages in/out endpoints */
+	.ep_msg_in = PCAN_USBPRO_EP_MSGIN,
+	.ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0},
+
+	/* size of rx/tx usb buffers */
+	.rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE,
+	.tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE,
+
+	/* device callbacks */
+	.intf_probe = pcan_usb_pro_probe,	/* same as PCAN-USB Pro */
+	.dev_init = pcan_usb_fd_init,
+
+	.dev_exit = pcan_usb_fd_exit,
+	.dev_free = pcan_usb_fd_free,
+	.dev_set_bus = pcan_usb_fd_set_bus,
+	.dev_set_bittiming = pcan_usb_fd_set_bittiming_slow,
+	.dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast,
+	.dev_decode_buf = pcan_usb_fd_decode_buf,
+	.dev_start = pcan_usb_fd_start,
+	.dev_stop = pcan_usb_fd_stop,
+	.dev_restart_async = pcan_usb_fd_restart_async,
+	.dev_encode_msg = pcan_usb_fd_encode_msg,
+
+	.do_get_berr_counter = pcan_usb_fd_get_berr_counter,
+};
+
 /* describes the PCAN-USB Pro FD adapter */
 static const struct can_bittiming_const pcan_usb_pro_fd_const = {
 	.name = "pcan_usb_pro_fd",
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 674f367087c5..facca33d53e9 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -1,7 +1,7 @@
 /*
  * vcan.c - Virtual CAN interface
  *
- * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2017 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -50,9 +50,12 @@
 #include <linux/slab.h>
 #include <net/rtnetlink.h>
 
+#define DRV_NAME "vcan"
+
 MODULE_DESCRIPTION("virtual CAN interface");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
 
 
 /*
@@ -164,7 +167,7 @@ static void vcan_setup(struct net_device *dev)
 }
 
 static struct rtnl_link_ops vcan_link_ops __read_mostly = {
-	.kind	= "vcan",
+	.kind	= DRV_NAME,
 	.setup	= vcan_setup,
 };
 
diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
new file mode 100644
index 000000000000..7fbb24795681
--- /dev/null
+++ b/drivers/net/can/vxcan.c
@@ -0,0 +1,316 @@
+/*
+ * vxcan.c - Virtual CAN Tunnel for cross namespace communication
+ *
+ * This code is derived from drivers/net/can/vcan.c for the virtual CAN
+ * specific parts and from drivers/net/veth.c to implement the netlink API
+ * for network interface pairs in a common and established way.
+ *
+ * Copyright (c) 2017 Oliver Hartkopp <socketcan@hartkopp.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/skb.h>
+#include <linux/can/vxcan.h>
+#include <linux/slab.h>
+#include <net/rtnetlink.h>
+
+#define DRV_NAME "vxcan"
+
+MODULE_DESCRIPTION("Virtual CAN Tunnel");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
+
+struct vxcan_priv {
+	struct net_device __rcu	*peer;
+};
+
+static netdev_tx_t vxcan_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
+	struct net_device_stats *peerstats, *srcstats = &dev->stats;
+
+	if (can_dropped_invalid_skb(dev, skb))
+		return NETDEV_TX_OK;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	if (unlikely(!peer)) {
+		kfree_skb(skb);
+		dev->stats.tx_dropped++;
+		goto out_unlock;
+	}
+
+	skb = can_create_echo_skb(skb);
+	if (!skb)
+		goto out_unlock;
+
+	/* reset CAN GW hop counter */
+	skb->csum_start = 0;
+	skb->pkt_type   = PACKET_BROADCAST;
+	skb->dev        = peer;
+	skb->ip_summed  = CHECKSUM_UNNECESSARY;
+
+	if (netif_rx_ni(skb) == NET_RX_SUCCESS) {
+		srcstats->tx_packets++;
+		srcstats->tx_bytes += cfd->len;
+		peerstats = &peer->stats;
+		peerstats->rx_packets++;
+		peerstats->rx_bytes += cfd->len;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+	return NETDEV_TX_OK;
+}
+
+
+static int vxcan_open(struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	if (!peer)
+		return -ENOTCONN;
+
+	if (peer->flags & IFF_UP) {
+		netif_carrier_on(dev);
+		netif_carrier_on(peer);
+	}
+	return 0;
+}
+
+static int vxcan_close(struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	netif_carrier_off(dev);
+	if (peer)
+		netif_carrier_off(peer);
+
+	return 0;
+}
+
+static int vxcan_get_iflink(const struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	int iflink;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	iflink = peer ? peer->ifindex : 0;
+	rcu_read_unlock();
+
+	return iflink;
+}
+
+static int vxcan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* Do not allow changing the MTU while running */
+	if (dev->flags & IFF_UP)
+		return -EBUSY;
+
+	if (new_mtu != CAN_MTU && new_mtu != CANFD_MTU)
+		return -EINVAL;
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static const struct net_device_ops vxcan_netdev_ops = {
+	.ndo_open	= vxcan_open,
+	.ndo_stop	= vxcan_close,
+	.ndo_start_xmit	= vxcan_xmit,
+	.ndo_get_iflink	= vxcan_get_iflink,
+	.ndo_change_mtu = vxcan_change_mtu,
+};
+
+static void vxcan_setup(struct net_device *dev)
+{
+	dev->type		= ARPHRD_CAN;
+	dev->mtu		= CAN_MTU;
+	dev->hard_header_len	= 0;
+	dev->addr_len		= 0;
+	dev->tx_queue_len	= 0;
+	dev->flags		= (IFF_NOARP|IFF_ECHO);
+	dev->netdev_ops		= &vxcan_netdev_ops;
+	dev->destructor		= free_netdev;
+}
+
+/* forward declaration for rtnl_create_link() */
+static struct rtnl_link_ops vxcan_link_ops;
+
+static int vxcan_newlink(struct net *net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[])
+{
+	struct vxcan_priv *priv;
+	struct net_device *peer;
+	struct net *peer_net;
+
+	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb;
+	char ifname[IFNAMSIZ];
+	unsigned char name_assign_type;
+	struct ifinfomsg *ifmp = NULL;
+	int err;
+
+	/* register peer device */
+	if (data && data[VXCAN_INFO_PEER]) {
+		struct nlattr *nla_peer;
+
+		nla_peer = data[VXCAN_INFO_PEER];
+		ifmp = nla_data(nla_peer);
+		err = rtnl_nla_parse_ifla(peer_tb,
+					  nla_data(nla_peer) +
+					  sizeof(struct ifinfomsg),
+					  nla_len(nla_peer) -
+					  sizeof(struct ifinfomsg),
+					  NULL);
+		if (err < 0)
+			return err;
+
+		tbp = peer_tb;
+	}
+
+	if (tbp[IFLA_IFNAME]) {
+		nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+		name_assign_type = NET_NAME_USER;
+	} else {
+		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
+		name_assign_type = NET_NAME_ENUM;
+	}
+
+	peer_net = rtnl_link_get_net(net, tbp);
+	if (IS_ERR(peer_net))
+		return PTR_ERR(peer_net);
+
+	peer = rtnl_create_link(peer_net, ifname, name_assign_type,
+				&vxcan_link_ops, tbp);
+	if (IS_ERR(peer)) {
+		put_net(peer_net);
+		return PTR_ERR(peer);
+	}
+
+	if (ifmp && dev->ifindex)
+		peer->ifindex = ifmp->ifi_index;
+
+	err = register_netdevice(peer);
+	put_net(peer_net);
+	peer_net = NULL;
+	if (err < 0) {
+		free_netdev(peer);
+		return err;
+	}
+
+	netif_carrier_off(peer);
+
+	err = rtnl_configure_link(peer, ifmp);
+	if (err < 0) {
+		unregister_netdevice(peer);
+		return err;
+	}
+
+	/* register first device */
+	if (tb[IFLA_IFNAME])
+		nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+	else
+		snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
+
+	err = register_netdevice(dev);
+	if (err < 0) {
+		unregister_netdevice(peer);
+		return err;
+	}
+
+	netif_carrier_off(dev);
+
+	/* cross link the device pair */
+	priv = netdev_priv(dev);
+	rcu_assign_pointer(priv->peer, peer);
+
+	priv = netdev_priv(peer);
+	rcu_assign_pointer(priv->peer, dev);
+
+	return 0;
+}
+
+static void vxcan_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct vxcan_priv *priv;
+	struct net_device *peer;
+
+	priv = netdev_priv(dev);
+	peer = rtnl_dereference(priv->peer);
+
+	/* Note : dellink() is called from default_device_exit_batch(),
+	 * before a rcu_synchronize() point. The devices are guaranteed
+	 * not being freed before one RCU grace period.
+	 */
+	RCU_INIT_POINTER(priv->peer, NULL);
+	unregister_netdevice_queue(dev, head);
+
+	if (peer) {
+		priv = netdev_priv(peer);
+		RCU_INIT_POINTER(priv->peer, NULL);
+		unregister_netdevice_queue(peer, head);
+	}
+}
+
+static const struct nla_policy vxcan_policy[VXCAN_INFO_MAX + 1] = {
+	[VXCAN_INFO_PEER] = { .len = sizeof(struct ifinfomsg) },
+};
+
+static struct net *vxcan_get_link_net(const struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	return peer ? dev_net(peer) : dev_net(dev);
+}
+
+static struct rtnl_link_ops vxcan_link_ops = {
+	.kind		= DRV_NAME,
+	.priv_size	= sizeof(struct vxcan_priv),
+	.setup		= vxcan_setup,
+	.newlink	= vxcan_newlink,
+	.dellink	= vxcan_dellink,
+	.policy		= vxcan_policy,
+	.maxtype	= VXCAN_INFO_MAX,
+	.get_link_net	= vxcan_get_link_net,
+};
+
+static __init int vxcan_init(void)
+{
+	pr_info("vxcan: Virtual CAN Tunnel driver\n");
+
+	return rtnl_link_register(&vxcan_link_ops);
+}
+
+static __exit void vxcan_exit(void)
+{
+	rtnl_link_unregister(&vxcan_link_ops);
+}
+
+module_init(vxcan_init);
+module_exit(vxcan_exit);
diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c
index 91c876a0a647..da020418a652 100644
--- a/drivers/net/cris/eth_v10.c
+++ b/drivers/net/cris/eth_v10.c
@@ -1412,31 +1412,39 @@ e100_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return rc;
 }
 
-static int e100_get_settings(struct net_device *dev,
-			     struct ethtool_cmd *cmd)
+static int e100_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct net_local *np = netdev_priv(dev);
+	u32 supported;
 	int err;
 
 	spin_lock_irq(&np->lock);
-	err = mii_ethtool_gset(&np->mii_if, cmd);
+	err = mii_ethtool_get_link_ksettings(&np->mii_if, cmd);
 	spin_unlock_irq(&np->lock);
 
 	/* The PHY may support 1000baseT, but the Etrax100 does not.  */
-	cmd->supported &= ~(SUPPORTED_1000baseT_Half
-			    | SUPPORTED_1000baseT_Full);
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
+
+	supported &= ~(SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full);
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+
 	return err;
 }
 
-static int e100_set_settings(struct net_device *dev,
-			     struct ethtool_cmd *ecmd)
+static int e100_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *ecmd)
 {
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	if (ecmd->base.autoneg == AUTONEG_ENABLE) {
 		e100_set_duplex(dev, autoneg);
 		e100_set_speed(dev, 0);
 	} else {
-		e100_set_duplex(dev, ecmd->duplex == DUPLEX_HALF ? half : full);
-		e100_set_speed(dev, ecmd->speed == SPEED_10 ? 10: 100);
+		e100_set_duplex(dev, ecmd->base.duplex == DUPLEX_HALF ?
+				half : full);
+		e100_set_speed(dev, ecmd->base.speed == SPEED_10 ? 10 : 100);
 	}
 
 	return 0;
@@ -1459,11 +1467,11 @@ static int e100_nway_reset(struct net_device *dev)
 }
 
 static const struct ethtool_ops e100_ethtool_ops = {
-	.get_settings	= e100_get_settings,
-	.set_settings	= e100_set_settings,
 	.get_drvinfo	= e100_get_drvinfo,
 	.nway_reset	= e100_nway_reset,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings	= e100_get_link_ksettings,
+	.set_link_ksettings	= e100_set_link_ksettings,
 };
 
 static int
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 065984670ff1..862ee22303c2 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -11,7 +11,7 @@ config NET_DSA_MV88E6060
 
 config NET_DSA_BCM_SF2
 	tristate "Broadcom Starfighter 2 Ethernet switch support"
-	depends on HAS_IOMEM && NET_DSA
+	depends on HAS_IOMEM && NET_DSA && OF_MDIO
 	select NET_DSA_TAG_BRCM
 	select FIXED_PHY
 	select BCM7XXX_PHY
@@ -34,4 +34,44 @@ config NET_DSA_QCA8K
 	  This enables support for the Qualcomm Atheros QCA8K Ethernet
 	  switch chips.
 
+config NET_DSA_LOOP
+	tristate "DSA mock-up Ethernet switch chip support"
+	depends on NET_DSA
+	select FIXED_PHY
+	---help---
+	  This enables support for a fake mock-up switch chip which
+	  exercises the DSA APIs.
+
+config NET_DSA_MT7530
+	tristate "Mediatek MT7530 Ethernet switch support"
+	depends on NET_DSA
+	select NET_DSA_TAG_MTK
+	---help---
+	  This enables support for the Mediatek MT7530 Ethernet switch
+	  chip.
+
+config NET_DSA_SMSC_LAN9303
+	tristate
+	select NET_DSA_TAG_LAN9303
+	---help---
+	  This enables support for the SMSC/Microchip LAN9303 3 port ethernet
+	  switch chips.
+
+config NET_DSA_SMSC_LAN9303_I2C
+	tristate "SMSC/Microchip LAN9303 3-ports 10/100 ethernet switch in I2C managed mode"
+	depends on NET_DSA && I2C
+	select NET_DSA_SMSC_LAN9303
+	select REGMAP_I2C
+	---help---
+	  Enable access functions if the SMSC/Microchip LAN9303 is configured
+	  for I2C managed mode.
+
+config NET_DSA_SMSC_LAN9303_MDIO
+	tristate "SMSC/Microchip LAN9303 3-ports 10/100 ethernet switch in MDIO managed mode"
+	depends on NET_DSA
+	select NET_DSA_SMSC_LAN9303
+	---help---
+	  Enable access functions if the SMSC/Microchip LAN9303 is configured
+	  for MDIO managed mode.
+
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index a3c941632217..edd630361736 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -2,6 +2,10 @@ obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
 obj-$(CONFIG_NET_DSA_BCM_SF2)	+= bcm-sf2.o
 bcm-sf2-objs			:= bcm_sf2.o bcm_sf2_cfp.o
 obj-$(CONFIG_NET_DSA_QCA8K)	+= qca8k.o
-
+obj-$(CONFIG_NET_DSA_MT7530)	+= mt7530.o
+obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
+obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
+obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
 obj-y				+= b53/
 obj-y				+= mv88e6xxx/
+obj-$(CONFIG_NET_DSA_LOOP)	+= dsa_loop.o dsa_loop_bdinfo.o
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 8cf4801994e8..fa0eece21eef 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -326,6 +326,7 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
 
 static void b53_set_forwarding(struct b53_device *dev, int enable)
 {
+	struct dsa_switch *ds = dev->ds;
 	u8 mgmt;
 
 	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
@@ -336,6 +337,15 @@ static void b53_set_forwarding(struct b53_device *dev, int enable)
 		mgmt &= ~SM_SW_FWD_EN;
 
 	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+
+	/* Include IMP port in dumb forwarding mode when no tagging protocol is
+	 * set
+	 */
+	if (ds->ops->get_tag_protocol(ds) == DSA_TAG_PROTO_NONE) {
+		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
+		mgmt |= B53_MII_DUMB_FWDG_EN;
+		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
+	}
 }
 
 static void b53_enable_vlan(struct b53_device *dev, bool enable)
@@ -598,7 +608,8 @@ static void b53_switch_reset_gpio(struct b53_device *dev)
 
 static int b53_switch_reset(struct b53_device *dev)
 {
-	u8 mgmt;
+	unsigned int timeout = 1000;
+	u8 mgmt, reg;
 
 	b53_switch_reset_gpio(dev);
 
@@ -607,6 +618,28 @@ static int b53_switch_reset(struct b53_device *dev)
 		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x00);
 	}
 
+	/* This is specific to 58xx devices here, do not use is58xx() which
+	 * covers the larger Starfigther 2 family, including 7445/7278 which
+	 * still use this driver as a library and need to perform the reset
+	 * earlier.
+	 */
+	if (dev->chip_id == BCM58XX_DEVICE_ID) {
+		b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, &reg);
+		reg |= SW_RST | EN_SW_RST | EN_CH_RST;
+		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, reg);
+
+		do {
+			b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, &reg);
+			if (!(reg & SW_RST))
+				break;
+
+			usleep_range(1000, 2000);
+		} while (timeout-- > 0);
+
+		if (timeout == 0)
+			return -ETIMEDOUT;
+	}
+
 	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
 
 	if (!(mgmt & SM_SW_FWD_EN)) {
@@ -1731,7 +1764,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.vlans	= 4096,
 		.enabled_ports = 0x1ff,
 		.arl_entries = 4,
-		.cpu_port = B53_CPU_PORT_25,
+		.cpu_port = B53_CPU_PORT,
 		.vta_regs = B53_VTA_REGS,
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 9fd24c418fa4..e5c86d44667a 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -104,6 +104,10 @@
 #define  B53_UC_FWD_EN			BIT(6)
 #define  B53_MC_FWD_EN			BIT(7)
 
+/* Switch control (8 bit) */
+#define B53_SWITCH_CTRL			0x22
+#define  B53_MII_DUMB_FWDG_EN		BIT(6)
+
 /* (16 bit) */
 #define B53_UC_FLOOD_MASK		0x32
 #define B53_MC_FLOOD_MASK		0x34
@@ -139,6 +143,7 @@
 /* Software reset register (8 bit) */
 #define B53_SOFTRESET			0x79
 #define   SW_RST			BIT(7)
+#define   EN_CH_RST			BIT(6)
 #define   EN_SW_RST			BIT(4)
 
 /* Fast Aging Control register (8 bit) */
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 346dd9a1232d..2fb32d67065f 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -10,10 +10,11 @@
  */
 
 #include <linux/list.h>
-#include <net/dsa.h>
 #include <linux/ethtool.h>
 #include <linux/if_ether.h>
 #include <linux/in.h>
+#include <linux/netdevice.h>
+#include <net/dsa.h>
 #include <linux/bitmap.h>
 
 #include "bcm_sf2.h"
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
new file mode 100644
index 000000000000..f0fc4de4fc9a
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop.c
@@ -0,0 +1,328 @@
+/*
+ * Distributed Switch Architecture loopback driver
+ *
+ * Copyright (C) 2016, Florian Fainelli <f.fainelli@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/export.h>
+#include <linux/workqueue.h>
+#include <linux/module.h>
+#include <linux/if_bridge.h>
+#include <net/switchdev.h>
+#include <net/dsa.h>
+
+#include "dsa_loop.h"
+
+struct dsa_loop_vlan {
+	u16 members;
+	u16 untagged;
+};
+
+#define DSA_LOOP_VLANS	5
+
+struct dsa_loop_priv {
+	struct mii_bus	*bus;
+	unsigned int	port_base;
+	struct dsa_loop_vlan vlans[DSA_LOOP_VLANS];
+	struct net_device *netdev;
+	u16 pvid;
+};
+
+static struct phy_device *phydevs[PHY_MAX_ADDR];
+
+static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return DSA_TAG_PROTO_NONE;
+}
+
+static int dsa_loop_setup(struct dsa_switch *ds)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static int dsa_loop_set_addr(struct dsa_switch *ds, u8 *addr)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static int dsa_loop_phy_read(struct dsa_switch *ds, int port, int regnum)
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return mdiobus_read_nested(bus, ps->port_base + port, regnum);
+}
+
+static int dsa_loop_phy_write(struct dsa_switch *ds, int port,
+			      int regnum, u16 value)
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return mdiobus_write_nested(bus, ps->port_base + port, regnum, value);
+}
+
+static int dsa_loop_port_bridge_join(struct dsa_switch *ds, int port,
+				     struct net_device *bridge)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static void dsa_loop_port_bridge_leave(struct dsa_switch *ds, int port,
+				       struct net_device *bridge)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+}
+
+static void dsa_loop_port_stp_state_set(struct dsa_switch *ds, int port,
+					u8 state)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+}
+
+static int dsa_loop_port_vlan_filtering(struct dsa_switch *ds, int port,
+					bool vlan_filtering)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static int dsa_loop_port_vlan_prepare(struct dsa_switch *ds, int port,
+				      const struct switchdev_obj_port_vlan *vlan,
+				      struct switchdev_trans *trans)
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	if (vlan->vid_end > DSA_LOOP_VLANS)
+		return -ERANGE;
+
+	return 0;
+}
+
+static void dsa_loop_port_vlan_add(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan,
+				   struct switchdev_trans *trans)
+{
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+	struct dsa_loop_vlan *vl;
+	u16 vid;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &ps->vlans[vid];
+
+		vl->members |= BIT(port);
+		if (untagged)
+			vl->untagged |= BIT(port);
+		else
+			vl->untagged &= ~BIT(port);
+	}
+
+	if (pvid)
+		ps->pvid = vid;
+}
+
+static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port,
+				  const struct switchdev_obj_port_vlan *vlan)
+{
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+	struct dsa_loop_vlan *vl;
+	u16 vid, pvid = ps->pvid;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &ps->vlans[vid];
+
+		vl->members &= ~BIT(port);
+		if (untagged)
+			vl->untagged &= ~BIT(port);
+
+		if (pvid == vid)
+			pvid = 1;
+	}
+	ps->pvid = pvid;
+
+	return 0;
+}
+
+static int dsa_loop_port_vlan_dump(struct dsa_switch *ds, int port,
+				   struct switchdev_obj_port_vlan *vlan,
+				   int (*cb)(struct switchdev_obj *obj))
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+	struct dsa_loop_vlan *vl;
+	u16 vid, vid_start = 0;
+	int err = 0;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	for (vid = vid_start; vid < DSA_LOOP_VLANS; vid++) {
+		vl = &ps->vlans[vid];
+
+		if (!(vl->members & BIT(port)))
+			continue;
+
+		vlan->vid_begin = vlan->vid_end = vid;
+		vlan->flags = 0;
+
+		if (vl->untagged & BIT(port))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+		if (ps->pvid == vid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		err = cb(&vlan->obj);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static struct dsa_switch_ops dsa_loop_driver = {
+	.get_tag_protocol	= dsa_loop_get_protocol,
+	.setup			= dsa_loop_setup,
+	.set_addr		= dsa_loop_set_addr,
+	.phy_read		= dsa_loop_phy_read,
+	.phy_write		= dsa_loop_phy_write,
+	.port_bridge_join	= dsa_loop_port_bridge_join,
+	.port_bridge_leave	= dsa_loop_port_bridge_leave,
+	.port_stp_state_set	= dsa_loop_port_stp_state_set,
+	.port_vlan_filtering	= dsa_loop_port_vlan_filtering,
+	.port_vlan_prepare	= dsa_loop_port_vlan_prepare,
+	.port_vlan_add		= dsa_loop_port_vlan_add,
+	.port_vlan_del		= dsa_loop_port_vlan_del,
+	.port_vlan_dump		= dsa_loop_port_vlan_dump,
+};
+
+static int dsa_loop_drv_probe(struct mdio_device *mdiodev)
+{
+	struct dsa_loop_pdata *pdata = mdiodev->dev.platform_data;
+	struct dsa_loop_priv *ps;
+	struct dsa_switch *ds;
+
+	if (!pdata)
+		return -ENODEV;
+
+	dev_info(&mdiodev->dev, "%s: 0x%0x\n",
+		 pdata->name, pdata->enabled_ports);
+
+	ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS);
+	if (!ds)
+		return -ENOMEM;
+
+	ps = devm_kzalloc(&mdiodev->dev, sizeof(*ps), GFP_KERNEL);
+	ps->netdev = dev_get_by_name(&init_net, pdata->netdev);
+	if (!ps->netdev)
+		return -EPROBE_DEFER;
+
+	pdata->cd.netdev[DSA_LOOP_CPU_PORT] = &ps->netdev->dev;
+
+	ds->dev = &mdiodev->dev;
+	ds->ops = &dsa_loop_driver;
+	ds->priv = ps;
+	ps->bus = mdiodev->bus;
+
+	dev_set_drvdata(&mdiodev->dev, ds);
+
+	return dsa_register_switch(ds, ds->dev);
+}
+
+static void dsa_loop_drv_remove(struct mdio_device *mdiodev)
+{
+	struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev);
+	struct dsa_loop_priv *ps = ds->priv;
+
+	dsa_unregister_switch(ds);
+	dev_put(ps->netdev);
+}
+
+static struct mdio_driver dsa_loop_drv = {
+	.mdiodrv.driver	= {
+		.name	= "dsa-loop",
+	},
+	.probe	= dsa_loop_drv_probe,
+	.remove	= dsa_loop_drv_remove,
+};
+
+#define NUM_FIXED_PHYS	(DSA_LOOP_NUM_PORTS - 2)
+
+static void unregister_fixed_phys(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < NUM_FIXED_PHYS; i++)
+		if (phydevs[i])
+			fixed_phy_unregister(phydevs[i]);
+}
+
+static int __init dsa_loop_init(void)
+{
+	struct fixed_phy_status status = {
+		.link = 1,
+		.speed = SPEED_100,
+		.duplex = DUPLEX_FULL,
+	};
+	unsigned int i;
+
+	for (i = 0; i < NUM_FIXED_PHYS; i++)
+		phydevs[i] = fixed_phy_register(PHY_POLL, &status, -1, NULL);
+
+	return mdio_driver_register(&dsa_loop_drv);
+}
+module_init(dsa_loop_init);
+
+static void __exit dsa_loop_exit(void)
+{
+	mdio_driver_unregister(&dsa_loop_drv);
+	unregister_fixed_phys();
+}
+module_exit(dsa_loop_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Fainelli");
+MODULE_DESCRIPTION("DSA loopback driver");
diff --git a/drivers/net/dsa/dsa_loop.h b/drivers/net/dsa/dsa_loop.h
new file mode 100644
index 000000000000..dc396877fc95
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop.h
@@ -0,0 +1,19 @@
+#ifndef __DSA_LOOP_H
+#define __DSA_LOOP_H
+
+struct dsa_chip_data;
+
+struct dsa_loop_pdata {
+	/* Must be first, such that dsa_register_switch() can access this
+	 * without gory pointer manipulations
+	 */
+	struct dsa_chip_data cd;
+	const char *name;
+	unsigned int enabled_ports;
+	const char *netdev;
+};
+
+#define DSA_LOOP_NUM_PORTS	6
+#define DSA_LOOP_CPU_PORT	(DSA_LOOP_NUM_PORTS - 1)
+
+#endif /* __DSA_LOOP_H */
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
new file mode 100644
index 000000000000..fb8d5dc71013
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop_bdinfo.c
@@ -0,0 +1,34 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/phy.h>
+#include <net/dsa.h>
+
+#include "dsa_loop.h"
+
+static struct dsa_loop_pdata dsa_loop_pdata = {
+	.cd = {
+		.port_names[0] = "lan1",
+		.port_names[1] = "lan2",
+		.port_names[2] = "lan3",
+		.port_names[3] = "lan4",
+		.port_names[DSA_LOOP_CPU_PORT] = "cpu",
+	},
+	.name = "DSA mockup driver",
+	.enabled_ports = 0x1f,
+	.netdev = "eth0",
+};
+
+static const struct mdio_board_info bdinfo = {
+	.bus_id	= "fixed-0",
+	.modalias = "dsa-loop",
+	.mdio_addr = 31,
+	.platform_data = &dsa_loop_pdata,
+};
+
+static int __init dsa_loop_bdinfo_init(void)
+{
+	return mdiobus_register_board_info(&bdinfo, 1);
+}
+arch_initcall(dsa_loop_bdinfo_init)
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
new file mode 100644
index 000000000000..c8b2423c8ef7
--- /dev/null
+++ b/drivers/net/dsa/lan9303-core.c
@@ -0,0 +1,879 @@
+/*
+ * Copyright (C) 2017 Pengutronix, Juergen Borleis <kernel@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regmap.h>
+#include <linux/mutex.h>
+#include <linux/mii.h>
+
+#include "lan9303.h"
+
+#define LAN9303_CHIP_REV 0x14
+# define LAN9303_CHIP_ID 0x9303
+#define LAN9303_IRQ_CFG 0x15
+# define LAN9303_IRQ_CFG_IRQ_ENABLE BIT(8)
+# define LAN9303_IRQ_CFG_IRQ_POL BIT(4)
+# define LAN9303_IRQ_CFG_IRQ_TYPE BIT(0)
+#define LAN9303_INT_STS 0x16
+# define LAN9303_INT_STS_PHY_INT2 BIT(27)
+# define LAN9303_INT_STS_PHY_INT1 BIT(26)
+#define LAN9303_INT_EN 0x17
+# define LAN9303_INT_EN_PHY_INT2_EN BIT(27)
+# define LAN9303_INT_EN_PHY_INT1_EN BIT(26)
+#define LAN9303_HW_CFG 0x1D
+# define LAN9303_HW_CFG_READY BIT(27)
+# define LAN9303_HW_CFG_AMDX_EN_PORT2 BIT(26)
+# define LAN9303_HW_CFG_AMDX_EN_PORT1 BIT(25)
+#define LAN9303_PMI_DATA 0x29
+#define LAN9303_PMI_ACCESS 0x2A
+# define LAN9303_PMI_ACCESS_PHY_ADDR(x) (((x) & 0x1f) << 11)
+# define LAN9303_PMI_ACCESS_MIIRINDA(x) (((x) & 0x1f) << 6)
+# define LAN9303_PMI_ACCESS_MII_BUSY BIT(0)
+# define LAN9303_PMI_ACCESS_MII_WRITE BIT(1)
+#define LAN9303_MANUAL_FC_1 0x68
+#define LAN9303_MANUAL_FC_2 0x69
+#define LAN9303_MANUAL_FC_0 0x6a
+#define LAN9303_SWITCH_CSR_DATA 0x6b
+#define LAN9303_SWITCH_CSR_CMD 0x6c
+#define LAN9303_SWITCH_CSR_CMD_BUSY BIT(31)
+#define LAN9303_SWITCH_CSR_CMD_RW BIT(30)
+#define LAN9303_SWITCH_CSR_CMD_LANES (BIT(19) | BIT(18) | BIT(17) | BIT(16))
+#define LAN9303_VIRT_PHY_BASE 0x70
+#define LAN9303_VIRT_SPECIAL_CTRL 0x77
+
+#define LAN9303_SW_DEV_ID 0x0000
+#define LAN9303_SW_RESET 0x0001
+#define LAN9303_SW_RESET_RESET BIT(0)
+#define LAN9303_SW_IMR 0x0004
+#define LAN9303_SW_IPR 0x0005
+#define LAN9303_MAC_VER_ID_0 0x0400
+#define LAN9303_MAC_RX_CFG_0 0x0401
+# define LAN9303_MAC_RX_CFG_X_REJECT_MAC_TYPES BIT(1)
+# define LAN9303_MAC_RX_CFG_X_RX_ENABLE BIT(0)
+#define LAN9303_MAC_RX_UNDSZE_CNT_0 0x0410
+#define LAN9303_MAC_RX_64_CNT_0 0x0411
+#define LAN9303_MAC_RX_127_CNT_0 0x0412
+#define LAN9303_MAC_RX_255_CNT_0 0x413
+#define LAN9303_MAC_RX_511_CNT_0 0x0414
+#define LAN9303_MAC_RX_1023_CNT_0 0x0415
+#define LAN9303_MAC_RX_MAX_CNT_0 0x0416
+#define LAN9303_MAC_RX_OVRSZE_CNT_0 0x0417
+#define LAN9303_MAC_RX_PKTOK_CNT_0 0x0418
+#define LAN9303_MAC_RX_CRCERR_CNT_0 0x0419
+#define LAN9303_MAC_RX_MULCST_CNT_0 0x041a
+#define LAN9303_MAC_RX_BRDCST_CNT_0 0x041b
+#define LAN9303_MAC_RX_PAUSE_CNT_0 0x041c
+#define LAN9303_MAC_RX_FRAG_CNT_0 0x041d
+#define LAN9303_MAC_RX_JABB_CNT_0 0x041e
+#define LAN9303_MAC_RX_ALIGN_CNT_0 0x041f
+#define LAN9303_MAC_RX_PKTLEN_CNT_0 0x0420
+#define LAN9303_MAC_RX_GOODPKTLEN_CNT_0 0x0421
+#define LAN9303_MAC_RX_SYMBL_CNT_0 0x0422
+#define LAN9303_MAC_RX_CTLFRM_CNT_0 0x0423
+
+#define LAN9303_MAC_TX_CFG_0 0x0440
+# define LAN9303_MAC_TX_CFG_X_TX_IFG_CONFIG_DEFAULT (21 << 2)
+# define LAN9303_MAC_TX_CFG_X_TX_PAD_ENABLE BIT(1)
+# define LAN9303_MAC_TX_CFG_X_TX_ENABLE BIT(0)
+#define LAN9303_MAC_TX_DEFER_CNT_0 0x0451
+#define LAN9303_MAC_TX_PAUSE_CNT_0 0x0452
+#define LAN9303_MAC_TX_PKTOK_CNT_0 0x0453
+#define LAN9303_MAC_TX_64_CNT_0 0x0454
+#define LAN9303_MAC_TX_127_CNT_0 0x0455
+#define LAN9303_MAC_TX_255_CNT_0 0x0456
+#define LAN9303_MAC_TX_511_CNT_0 0x0457
+#define LAN9303_MAC_TX_1023_CNT_0 0x0458
+#define LAN9303_MAC_TX_MAX_CNT_0 0x0459
+#define LAN9303_MAC_TX_UNDSZE_CNT_0 0x045a
+#define LAN9303_MAC_TX_PKTLEN_CNT_0 0x045c
+#define LAN9303_MAC_TX_BRDCST_CNT_0 0x045d
+#define LAN9303_MAC_TX_MULCST_CNT_0 0x045e
+#define LAN9303_MAC_TX_LATECOL_0 0x045f
+#define LAN9303_MAC_TX_EXCOL_CNT_0 0x0460
+#define LAN9303_MAC_TX_SNGLECOL_CNT_0 0x0461
+#define LAN9303_MAC_TX_MULTICOL_CNT_0 0x0462
+#define LAN9303_MAC_TX_TOTALCOL_CNT_0 0x0463
+
+#define LAN9303_MAC_VER_ID_1 0x0800
+#define LAN9303_MAC_RX_CFG_1 0x0801
+#define LAN9303_MAC_TX_CFG_1 0x0840
+#define LAN9303_MAC_VER_ID_2 0x0c00
+#define LAN9303_MAC_RX_CFG_2 0x0c01
+#define LAN9303_MAC_TX_CFG_2 0x0c40
+#define LAN9303_SWE_ALR_CMD 0x1800
+#define LAN9303_SWE_VLAN_CMD 0x180b
+# define LAN9303_SWE_VLAN_CMD_RNW BIT(5)
+# define LAN9303_SWE_VLAN_CMD_PVIDNVLAN BIT(4)
+#define LAN9303_SWE_VLAN_WR_DATA 0x180c
+#define LAN9303_SWE_VLAN_RD_DATA 0x180e
+# define LAN9303_SWE_VLAN_MEMBER_PORT2 BIT(17)
+# define LAN9303_SWE_VLAN_UNTAG_PORT2 BIT(16)
+# define LAN9303_SWE_VLAN_MEMBER_PORT1 BIT(15)
+# define LAN9303_SWE_VLAN_UNTAG_PORT1 BIT(14)
+# define LAN9303_SWE_VLAN_MEMBER_PORT0 BIT(13)
+# define LAN9303_SWE_VLAN_UNTAG_PORT0 BIT(12)
+#define LAN9303_SWE_VLAN_CMD_STS 0x1810
+#define LAN9303_SWE_GLB_INGRESS_CFG 0x1840
+#define LAN9303_SWE_PORT_STATE 0x1843
+# define LAN9303_SWE_PORT_STATE_FORWARDING_PORT2 (0)
+# define LAN9303_SWE_PORT_STATE_LEARNING_PORT2 BIT(5)
+# define LAN9303_SWE_PORT_STATE_BLOCKING_PORT2 BIT(4)
+# define LAN9303_SWE_PORT_STATE_FORWARDING_PORT1 (0)
+# define LAN9303_SWE_PORT_STATE_LEARNING_PORT1 BIT(3)
+# define LAN9303_SWE_PORT_STATE_BLOCKING_PORT1 BIT(2)
+# define LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 (0)
+# define LAN9303_SWE_PORT_STATE_LEARNING_PORT0 BIT(1)
+# define LAN9303_SWE_PORT_STATE_BLOCKING_PORT0 BIT(0)
+#define LAN9303_SWE_PORT_MIRROR 0x1846
+# define LAN9303_SWE_PORT_MIRROR_SNIFF_ALL BIT(8)
+# define LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT2 BIT(7)
+# define LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT1 BIT(6)
+# define LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT0 BIT(5)
+# define LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT2 BIT(4)
+# define LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT1 BIT(3)
+# define LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT0 BIT(2)
+# define LAN9303_SWE_PORT_MIRROR_ENABLE_RX_MIRRORING BIT(1)
+# define LAN9303_SWE_PORT_MIRROR_ENABLE_TX_MIRRORING BIT(0)
+#define LAN9303_SWE_INGRESS_PORT_TYPE 0x1847
+#define LAN9303_BM_CFG 0x1c00
+#define LAN9303_BM_EGRSS_PORT_TYPE 0x1c0c
+# define LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT2 (BIT(17) | BIT(16))
+# define LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT1 (BIT(9) | BIT(8))
+# define LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0 (BIT(1) | BIT(0))
+
+#define LAN9303_PORT_0_OFFSET 0x400
+#define LAN9303_PORT_1_OFFSET 0x800
+#define LAN9303_PORT_2_OFFSET 0xc00
+
+/* the built-in PHYs are of type LAN911X */
+#define MII_LAN911X_SPECIAL_MODES 0x12
+#define MII_LAN911X_SPECIAL_CONTROL_STATUS 0x1f
+
+static const struct regmap_range lan9303_valid_regs[] = {
+	regmap_reg_range(0x14, 0x17), /* misc, interrupt */
+	regmap_reg_range(0x19, 0x19), /* endian test */
+	regmap_reg_range(0x1d, 0x1d), /* hardware config */
+	regmap_reg_range(0x23, 0x24), /* general purpose timer */
+	regmap_reg_range(0x27, 0x27), /* counter */
+	regmap_reg_range(0x29, 0x2a), /* PMI index regs */
+	regmap_reg_range(0x68, 0x6a), /* flow control */
+	regmap_reg_range(0x6b, 0x6c), /* switch fabric indirect regs */
+	regmap_reg_range(0x6d, 0x6f), /* misc */
+	regmap_reg_range(0x70, 0x77), /* virtual phy */
+	regmap_reg_range(0x78, 0x7a), /* GPIO */
+	regmap_reg_range(0x7c, 0x7e), /* MAC & reset */
+	regmap_reg_range(0x80, 0xb7), /* switch fabric direct regs (wr only) */
+};
+
+static const struct regmap_range lan9303_reserved_ranges[] = {
+	regmap_reg_range(0x00, 0x13),
+	regmap_reg_range(0x18, 0x18),
+	regmap_reg_range(0x1a, 0x1c),
+	regmap_reg_range(0x1e, 0x22),
+	regmap_reg_range(0x25, 0x26),
+	regmap_reg_range(0x28, 0x28),
+	regmap_reg_range(0x2b, 0x67),
+	regmap_reg_range(0x7b, 0x7b),
+	regmap_reg_range(0x7f, 0x7f),
+	regmap_reg_range(0xb8, 0xff),
+};
+
+const struct regmap_access_table lan9303_register_set = {
+	.yes_ranges = lan9303_valid_regs,
+	.n_yes_ranges = ARRAY_SIZE(lan9303_valid_regs),
+	.no_ranges = lan9303_reserved_ranges,
+	.n_no_ranges = ARRAY_SIZE(lan9303_reserved_ranges),
+};
+EXPORT_SYMBOL(lan9303_register_set);
+
+static int lan9303_read(struct regmap *regmap, unsigned int offset, u32 *reg)
+{
+	int ret, i;
+
+	/* we can lose arbitration for the I2C case, because the device
+	 * tries to detect and read an external EEPROM after reset and acts as
+	 * a master on the shared I2C bus itself. This conflicts with our
+	 * attempts to access the device as a slave at the same moment.
+	 */
+	for (i = 0; i < 5; i++) {
+		ret = regmap_read(regmap, offset, reg);
+		if (!ret)
+			return 0;
+		if (ret != -EAGAIN)
+			break;
+		msleep(500);
+	}
+
+	return -EIO;
+}
+
+static int lan9303_virt_phy_reg_read(struct lan9303 *chip, int regnum)
+{
+	int ret;
+	u32 val;
+
+	if (regnum > MII_EXPANSION)
+		return -EINVAL;
+
+	ret = lan9303_read(chip->regmap, LAN9303_VIRT_PHY_BASE + regnum, &val);
+	if (ret)
+		return ret;
+
+	return val & 0xffff;
+}
+
+static int lan9303_virt_phy_reg_write(struct lan9303 *chip, int regnum, u16 val)
+{
+	if (regnum > MII_EXPANSION)
+		return -EINVAL;
+
+	return regmap_write(chip->regmap, LAN9303_VIRT_PHY_BASE + regnum, val);
+}
+
+static int lan9303_port_phy_reg_wait_for_completion(struct lan9303 *chip)
+{
+	int ret, i;
+	u32 reg;
+
+	for (i = 0; i < 25; i++) {
+		ret = lan9303_read(chip->regmap, LAN9303_PMI_ACCESS, &reg);
+		if (ret) {
+			dev_err(chip->dev,
+				"Failed to read pmi access status: %d\n", ret);
+			return ret;
+		}
+		if (!(reg & LAN9303_PMI_ACCESS_MII_BUSY))
+			return 0;
+		msleep(1);
+	}
+
+	return -EIO;
+}
+
+static int lan9303_port_phy_reg_read(struct lan9303 *chip, int addr, int regnum)
+{
+	int ret;
+	u32 val;
+
+	val = LAN9303_PMI_ACCESS_PHY_ADDR(addr);
+	val |= LAN9303_PMI_ACCESS_MIIRINDA(regnum);
+
+	mutex_lock(&chip->indirect_mutex);
+
+	ret = lan9303_port_phy_reg_wait_for_completion(chip);
+	if (ret)
+		goto on_error;
+
+	/* start the MII read cycle */
+	ret = regmap_write(chip->regmap, LAN9303_PMI_ACCESS, val);
+	if (ret)
+		goto on_error;
+
+	ret = lan9303_port_phy_reg_wait_for_completion(chip);
+	if (ret)
+		goto on_error;
+
+	/* read the result of this operation */
+	ret = lan9303_read(chip->regmap, LAN9303_PMI_DATA, &val);
+	if (ret)
+		goto on_error;
+
+	mutex_unlock(&chip->indirect_mutex);
+
+	return val & 0xffff;
+
+on_error:
+	mutex_unlock(&chip->indirect_mutex);
+	return ret;
+}
+
+static int lan9303_phy_reg_write(struct lan9303 *chip, int addr, int regnum,
+				 unsigned int val)
+{
+	int ret;
+	u32 reg;
+
+	reg = LAN9303_PMI_ACCESS_PHY_ADDR(addr);
+	reg |= LAN9303_PMI_ACCESS_MIIRINDA(regnum);
+	reg |= LAN9303_PMI_ACCESS_MII_WRITE;
+
+	mutex_lock(&chip->indirect_mutex);
+
+	ret = lan9303_port_phy_reg_wait_for_completion(chip);
+	if (ret)
+		goto on_error;
+
+	/* write the data first... */
+	ret = regmap_write(chip->regmap, LAN9303_PMI_DATA, val);
+	if (ret)
+		goto on_error;
+
+	/* ...then start the MII write cycle */
+	ret = regmap_write(chip->regmap, LAN9303_PMI_ACCESS, reg);
+
+on_error:
+	mutex_unlock(&chip->indirect_mutex);
+	return ret;
+}
+
+static int lan9303_switch_wait_for_completion(struct lan9303 *chip)
+{
+	int ret, i;
+	u32 reg;
+
+	for (i = 0; i < 25; i++) {
+		ret = lan9303_read(chip->regmap, LAN9303_SWITCH_CSR_CMD, &reg);
+		if (ret) {
+			dev_err(chip->dev,
+				"Failed to read csr command status: %d\n", ret);
+			return ret;
+		}
+		if (!(reg & LAN9303_SWITCH_CSR_CMD_BUSY))
+			return 0;
+		msleep(1);
+	}
+
+	return -EIO;
+}
+
+static int lan9303_write_switch_reg(struct lan9303 *chip, u16 regnum, u32 val)
+{
+	u32 reg;
+	int ret;
+
+	reg = regnum;
+	reg |= LAN9303_SWITCH_CSR_CMD_LANES;
+	reg |= LAN9303_SWITCH_CSR_CMD_BUSY;
+
+	mutex_lock(&chip->indirect_mutex);
+
+	ret = lan9303_switch_wait_for_completion(chip);
+	if (ret)
+		goto on_error;
+
+	ret = regmap_write(chip->regmap, LAN9303_SWITCH_CSR_DATA, val);
+	if (ret) {
+		dev_err(chip->dev, "Failed to write csr data reg: %d\n", ret);
+		goto on_error;
+	}
+
+	/* trigger write */
+	ret = regmap_write(chip->regmap, LAN9303_SWITCH_CSR_CMD, reg);
+	if (ret)
+		dev_err(chip->dev, "Failed to write csr command reg: %d\n",
+			ret);
+
+on_error:
+	mutex_unlock(&chip->indirect_mutex);
+	return ret;
+}
+
+static int lan9303_read_switch_reg(struct lan9303 *chip, u16 regnum, u32 *val)
+{
+	u32 reg;
+	int ret;
+
+	reg = regnum;
+	reg |= LAN9303_SWITCH_CSR_CMD_LANES;
+	reg |= LAN9303_SWITCH_CSR_CMD_RW;
+	reg |= LAN9303_SWITCH_CSR_CMD_BUSY;
+
+	mutex_lock(&chip->indirect_mutex);
+
+	ret = lan9303_switch_wait_for_completion(chip);
+	if (ret)
+		goto on_error;
+
+	/* trigger read */
+	ret = regmap_write(chip->regmap, LAN9303_SWITCH_CSR_CMD, reg);
+	if (ret) {
+		dev_err(chip->dev, "Failed to write csr command reg: %d\n",
+			ret);
+		goto on_error;
+	}
+
+	ret = lan9303_switch_wait_for_completion(chip);
+	if (ret)
+		goto on_error;
+
+	ret = lan9303_read(chip->regmap, LAN9303_SWITCH_CSR_DATA, val);
+	if (ret)
+		dev_err(chip->dev, "Failed to read csr data reg: %d\n", ret);
+on_error:
+	mutex_unlock(&chip->indirect_mutex);
+	return ret;
+}
+
+static int lan9303_detect_phy_setup(struct lan9303 *chip)
+{
+	int reg;
+
+	/* depending on the 'phy_addr_sel_strap' setting, the three phys are
+	 * using IDs 0-1-2 or IDs 1-2-3. We cannot read back the
+	 * 'phy_addr_sel_strap' setting directly, so we need a test, which
+	 * configuration is active:
+	 * Special reg 18 of phy 3 reads as 0x0000, if 'phy_addr_sel_strap' is 0
+	 * and the IDs are 0-1-2, else it contains something different from
+	 * 0x0000, which means 'phy_addr_sel_strap' is 1 and the IDs are 1-2-3.
+	 */
+	reg = lan9303_port_phy_reg_read(chip, 3, MII_LAN911X_SPECIAL_MODES);
+	if (reg < 0) {
+		dev_err(chip->dev, "Failed to detect phy config: %d\n", reg);
+		return reg;
+	}
+
+	if (reg != 0)
+		chip->phy_addr_sel_strap = 1;
+	else
+		chip->phy_addr_sel_strap = 0;
+
+	dev_dbg(chip->dev, "Phy setup '%s' detected\n",
+		chip->phy_addr_sel_strap ? "1-2-3" : "0-1-2");
+
+	return 0;
+}
+
+#define LAN9303_MAC_RX_CFG_OFFS (LAN9303_MAC_RX_CFG_0 - LAN9303_PORT_0_OFFSET)
+#define LAN9303_MAC_TX_CFG_OFFS (LAN9303_MAC_TX_CFG_0 - LAN9303_PORT_0_OFFSET)
+
+static int lan9303_disable_packet_processing(struct lan9303 *chip,
+					     unsigned int port)
+{
+	int ret;
+
+	/* disable RX, but keep register reset default values else */
+	ret = lan9303_write_switch_reg(chip, LAN9303_MAC_RX_CFG_OFFS + port,
+				       LAN9303_MAC_RX_CFG_X_REJECT_MAC_TYPES);
+	if (ret)
+		return ret;
+
+	/* disable TX, but keep register reset default values else */
+	return lan9303_write_switch_reg(chip, LAN9303_MAC_TX_CFG_OFFS + port,
+				LAN9303_MAC_TX_CFG_X_TX_IFG_CONFIG_DEFAULT |
+				LAN9303_MAC_TX_CFG_X_TX_PAD_ENABLE);
+}
+
+static int lan9303_enable_packet_processing(struct lan9303 *chip,
+					    unsigned int port)
+{
+	int ret;
+
+	/* enable RX and keep register reset default values else */
+	ret = lan9303_write_switch_reg(chip, LAN9303_MAC_RX_CFG_OFFS + port,
+				       LAN9303_MAC_RX_CFG_X_REJECT_MAC_TYPES |
+				       LAN9303_MAC_RX_CFG_X_RX_ENABLE);
+	if (ret)
+		return ret;
+
+	/* enable TX and keep register reset default values else */
+	return lan9303_write_switch_reg(chip, LAN9303_MAC_TX_CFG_OFFS + port,
+				LAN9303_MAC_TX_CFG_X_TX_IFG_CONFIG_DEFAULT |
+				LAN9303_MAC_TX_CFG_X_TX_PAD_ENABLE |
+				LAN9303_MAC_TX_CFG_X_TX_ENABLE);
+}
+
+/* We want a special working switch:
+ * - do not forward packets between port 1 and 2
+ * - forward everything from port 1 to port 0
+ * - forward everything from port 2 to port 0
+ * - forward special tagged packets from port 0 to port 1 *or* port 2
+ */
+static int lan9303_separate_ports(struct lan9303 *chip)
+{
+	int ret;
+
+	ret = lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_MIRROR,
+				LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT0 |
+				LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT1 |
+				LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT2 |
+				LAN9303_SWE_PORT_MIRROR_ENABLE_RX_MIRRORING |
+				LAN9303_SWE_PORT_MIRROR_SNIFF_ALL);
+	if (ret)
+		return ret;
+
+	/* enable defining the destination port via special VLAN tagging
+	 * for port 0
+	 */
+	ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE,
+				       0x03);
+	if (ret)
+		return ret;
+
+	/* tag incoming packets at port 1 and 2 on their way to port 0 to be
+	 * able to discover their source port
+	 */
+	ret = lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE,
+			LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0);
+	if (ret)
+		return ret;
+
+	/* prevent port 1 and 2 from forwarding packets by their own */
+	return lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE,
+				LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 |
+				LAN9303_SWE_PORT_STATE_BLOCKING_PORT1 |
+				LAN9303_SWE_PORT_STATE_BLOCKING_PORT2);
+}
+
+static int lan9303_handle_reset(struct lan9303 *chip)
+{
+	if (!chip->reset_gpio)
+		return 0;
+
+	if (chip->reset_duration != 0)
+		msleep(chip->reset_duration);
+
+	/* release (deassert) reset and activate the device */
+	gpiod_set_value_cansleep(chip->reset_gpio, 0);
+
+	return 0;
+}
+
+/* stop processing packets for all ports */
+static int lan9303_disable_processing(struct lan9303 *chip)
+{
+	int ret;
+
+	ret = lan9303_disable_packet_processing(chip, LAN9303_PORT_0_OFFSET);
+	if (ret)
+		return ret;
+	ret = lan9303_disable_packet_processing(chip, LAN9303_PORT_1_OFFSET);
+	if (ret)
+		return ret;
+	return lan9303_disable_packet_processing(chip, LAN9303_PORT_2_OFFSET);
+}
+
+static int lan9303_check_device(struct lan9303 *chip)
+{
+	int ret;
+	u32 reg;
+
+	ret = lan9303_read(chip->regmap, LAN9303_CHIP_REV, &reg);
+	if (ret) {
+		dev_err(chip->dev, "failed to read chip revision register: %d\n",
+			ret);
+		if (!chip->reset_gpio) {
+			dev_dbg(chip->dev,
+				"hint: maybe failed due to missing reset GPIO\n");
+		}
+		return ret;
+	}
+
+	if ((reg >> 16) != LAN9303_CHIP_ID) {
+		dev_err(chip->dev, "expecting LAN9303 chip, but found: %X\n",
+			reg >> 16);
+		return ret;
+	}
+
+	/* The default state of the LAN9303 device is to forward packets between
+	 * all ports (if not configured differently by an external EEPROM).
+	 * The initial state of a DSA device must be forwarding packets only
+	 * between the external and the internal ports and no forwarding
+	 * between the external ports. In preparation we stop packet handling
+	 * at all for now until the LAN9303 device is re-programmed accordingly.
+	 */
+	ret = lan9303_disable_processing(chip);
+	if (ret)
+		dev_warn(chip->dev, "failed to disable switching %d\n", ret);
+
+	dev_info(chip->dev, "Found LAN9303 rev. %u\n", reg & 0xffff);
+
+	ret = lan9303_detect_phy_setup(chip);
+	if (ret) {
+		dev_err(chip->dev,
+			"failed to discover phy bootstrap setup: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* ---------------------------- DSA -----------------------------------*/
+
+static enum dsa_tag_protocol lan9303_get_tag_protocol(struct dsa_switch *ds)
+{
+	return DSA_TAG_PROTO_LAN9303;
+}
+
+static int lan9303_setup(struct dsa_switch *ds)
+{
+	struct lan9303 *chip = ds->priv;
+	int ret;
+
+	/* Make sure that port 0 is the cpu port */
+	if (!dsa_is_cpu_port(ds, 0)) {
+		dev_err(chip->dev, "port 0 is not the CPU port\n");
+		return -EINVAL;
+	}
+
+	ret = lan9303_separate_ports(chip);
+	if (ret)
+		dev_err(chip->dev, "failed to separate ports %d\n", ret);
+
+	ret = lan9303_enable_packet_processing(chip, LAN9303_PORT_0_OFFSET);
+	if (ret)
+		dev_err(chip->dev, "failed to re-enable switching %d\n", ret);
+
+	return 0;
+}
+
+struct lan9303_mib_desc {
+	unsigned int offset; /* offset of first MAC */
+	const char *name;
+};
+
+static const struct lan9303_mib_desc lan9303_mib[] = {
+	{ .offset = LAN9303_MAC_RX_BRDCST_CNT_0, .name = "RxBroad", },
+	{ .offset = LAN9303_MAC_RX_PAUSE_CNT_0, .name = "RxPause", },
+	{ .offset = LAN9303_MAC_RX_MULCST_CNT_0, .name = "RxMulti", },
+	{ .offset = LAN9303_MAC_RX_PKTOK_CNT_0, .name = "RxOk", },
+	{ .offset = LAN9303_MAC_RX_CRCERR_CNT_0, .name = "RxCrcErr", },
+	{ .offset = LAN9303_MAC_RX_ALIGN_CNT_0, .name = "RxAlignErr", },
+	{ .offset = LAN9303_MAC_RX_JABB_CNT_0, .name = "RxJabber", },
+	{ .offset = LAN9303_MAC_RX_FRAG_CNT_0, .name = "RxFragment", },
+	{ .offset = LAN9303_MAC_RX_64_CNT_0, .name = "Rx64Byte", },
+	{ .offset = LAN9303_MAC_RX_127_CNT_0, .name = "Rx128Byte", },
+	{ .offset = LAN9303_MAC_RX_255_CNT_0, .name = "Rx256Byte", },
+	{ .offset = LAN9303_MAC_RX_511_CNT_0, .name = "Rx512Byte", },
+	{ .offset = LAN9303_MAC_RX_1023_CNT_0, .name = "Rx1024Byte", },
+	{ .offset = LAN9303_MAC_RX_MAX_CNT_0, .name = "RxMaxByte", },
+	{ .offset = LAN9303_MAC_RX_PKTLEN_CNT_0, .name = "RxByteCnt", },
+	{ .offset = LAN9303_MAC_RX_SYMBL_CNT_0, .name = "RxSymbolCnt", },
+	{ .offset = LAN9303_MAC_RX_CTLFRM_CNT_0, .name = "RxCfs", },
+	{ .offset = LAN9303_MAC_RX_OVRSZE_CNT_0, .name = "RxOverFlow", },
+	{ .offset = LAN9303_MAC_TX_UNDSZE_CNT_0, .name = "TxShort", },
+	{ .offset = LAN9303_MAC_TX_BRDCST_CNT_0, .name = "TxBroad", },
+	{ .offset = LAN9303_MAC_TX_PAUSE_CNT_0, .name = "TxPause", },
+	{ .offset = LAN9303_MAC_TX_MULCST_CNT_0, .name = "TxMulti", },
+	{ .offset = LAN9303_MAC_RX_UNDSZE_CNT_0, .name = "TxUnderRun", },
+	{ .offset = LAN9303_MAC_TX_64_CNT_0, .name = "Tx64Byte", },
+	{ .offset = LAN9303_MAC_TX_127_CNT_0, .name = "Tx128Byte", },
+	{ .offset = LAN9303_MAC_TX_255_CNT_0, .name = "Tx256Byte", },
+	{ .offset = LAN9303_MAC_TX_511_CNT_0, .name = "Tx512Byte", },
+	{ .offset = LAN9303_MAC_TX_1023_CNT_0, .name = "Tx1024Byte", },
+	{ .offset = LAN9303_MAC_TX_MAX_CNT_0, .name = "TxMaxByte", },
+	{ .offset = LAN9303_MAC_TX_PKTLEN_CNT_0, .name = "TxByteCnt", },
+	{ .offset = LAN9303_MAC_TX_PKTOK_CNT_0, .name = "TxOk", },
+	{ .offset = LAN9303_MAC_TX_TOTALCOL_CNT_0, .name = "TxCollision", },
+	{ .offset = LAN9303_MAC_TX_MULTICOL_CNT_0, .name = "TxMultiCol", },
+	{ .offset = LAN9303_MAC_TX_SNGLECOL_CNT_0, .name = "TxSingleCol", },
+	{ .offset = LAN9303_MAC_TX_EXCOL_CNT_0, .name = "TxExcCol", },
+	{ .offset = LAN9303_MAC_TX_DEFER_CNT_0, .name = "TxDefer", },
+	{ .offset = LAN9303_MAC_TX_LATECOL_0, .name = "TxLateCol", },
+};
+
+static void lan9303_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+{
+	unsigned int u;
+
+	for (u = 0; u < ARRAY_SIZE(lan9303_mib); u++) {
+		strncpy(data + u * ETH_GSTRING_LEN, lan9303_mib[u].name,
+			ETH_GSTRING_LEN);
+	}
+}
+
+static void lan9303_get_ethtool_stats(struct dsa_switch *ds, int port,
+				      uint64_t *data)
+{
+	struct lan9303 *chip = ds->priv;
+	u32 reg;
+	unsigned int u, poff;
+	int ret;
+
+	poff = port * 0x400;
+
+	for (u = 0; u < ARRAY_SIZE(lan9303_mib); u++) {
+		ret = lan9303_read_switch_reg(chip,
+					      lan9303_mib[u].offset + poff,
+					      &reg);
+		if (ret)
+			dev_warn(chip->dev, "Reading status reg %u failed\n",
+				 lan9303_mib[u].offset + poff);
+		data[u] = reg;
+	}
+}
+
+static int lan9303_get_sset_count(struct dsa_switch *ds)
+{
+	return ARRAY_SIZE(lan9303_mib);
+}
+
+static int lan9303_phy_read(struct dsa_switch *ds, int phy, int regnum)
+{
+	struct lan9303 *chip = ds->priv;
+	int phy_base = chip->phy_addr_sel_strap;
+
+	if (phy == phy_base)
+		return lan9303_virt_phy_reg_read(chip, regnum);
+	if (phy > phy_base + 2)
+		return -ENODEV;
+
+	return lan9303_port_phy_reg_read(chip, phy, regnum);
+}
+
+static int lan9303_phy_write(struct dsa_switch *ds, int phy, int regnum,
+			     u16 val)
+{
+	struct lan9303 *chip = ds->priv;
+	int phy_base = chip->phy_addr_sel_strap;
+
+	if (phy == phy_base)
+		return lan9303_virt_phy_reg_write(chip, regnum, val);
+	if (phy > phy_base + 2)
+		return -ENODEV;
+
+	return lan9303_phy_reg_write(chip, phy, regnum, val);
+}
+
+static int lan9303_port_enable(struct dsa_switch *ds, int port,
+			       struct phy_device *phy)
+{
+	struct lan9303 *chip = ds->priv;
+
+	/* enable internal packet processing */
+	switch (port) {
+	case 1:
+		return lan9303_enable_packet_processing(chip,
+							LAN9303_PORT_1_OFFSET);
+	case 2:
+		return lan9303_enable_packet_processing(chip,
+							LAN9303_PORT_2_OFFSET);
+	default:
+		dev_dbg(chip->dev,
+			"Error: request to power up invalid port %d\n", port);
+	}
+
+	return -ENODEV;
+}
+
+static void lan9303_port_disable(struct dsa_switch *ds, int port,
+				 struct phy_device *phy)
+{
+	struct lan9303 *chip = ds->priv;
+
+	/* disable internal packet processing */
+	switch (port) {
+	case 1:
+		lan9303_disable_packet_processing(chip, LAN9303_PORT_1_OFFSET);
+		lan9303_phy_reg_write(chip, chip->phy_addr_sel_strap + 1,
+				      MII_BMCR, BMCR_PDOWN);
+		break;
+	case 2:
+		lan9303_disable_packet_processing(chip, LAN9303_PORT_2_OFFSET);
+		lan9303_phy_reg_write(chip, chip->phy_addr_sel_strap + 2,
+				      MII_BMCR, BMCR_PDOWN);
+		break;
+	default:
+		dev_dbg(chip->dev,
+			"Error: request to power down invalid port %d\n", port);
+	}
+}
+
+static struct dsa_switch_ops lan9303_switch_ops = {
+	.get_tag_protocol = lan9303_get_tag_protocol,
+	.setup = lan9303_setup,
+	.get_strings = lan9303_get_strings,
+	.phy_read = lan9303_phy_read,
+	.phy_write = lan9303_phy_write,
+	.get_ethtool_stats = lan9303_get_ethtool_stats,
+	.get_sset_count = lan9303_get_sset_count,
+	.port_enable = lan9303_port_enable,
+	.port_disable = lan9303_port_disable,
+};
+
+static int lan9303_register_switch(struct lan9303 *chip)
+{
+	chip->ds = dsa_switch_alloc(chip->dev, DSA_MAX_PORTS);
+	if (!chip->ds)
+		return -ENOMEM;
+
+	chip->ds->priv = chip;
+	chip->ds->ops = &lan9303_switch_ops;
+	chip->ds->phys_mii_mask = chip->phy_addr_sel_strap ? 0xe : 0x7;
+
+	return dsa_register_switch(chip->ds, chip->dev);
+}
+
+static void lan9303_probe_reset_gpio(struct lan9303 *chip,
+				     struct device_node *np)
+{
+	chip->reset_gpio = devm_gpiod_get_optional(chip->dev, "reset",
+						   GPIOD_OUT_LOW);
+
+	if (!chip->reset_gpio) {
+		dev_dbg(chip->dev, "No reset GPIO defined\n");
+		return;
+	}
+
+	chip->reset_duration = 200;
+
+	if (np) {
+		of_property_read_u32(np, "reset-duration",
+				     &chip->reset_duration);
+	} else {
+		dev_dbg(chip->dev, "reset duration defaults to 200 ms\n");
+	}
+
+	/* A sane reset duration should not be longer than 1s */
+	if (chip->reset_duration > 1000)
+		chip->reset_duration = 1000;
+}
+
+int lan9303_probe(struct lan9303 *chip, struct device_node *np)
+{
+	int ret;
+
+	mutex_init(&chip->indirect_mutex);
+
+	lan9303_probe_reset_gpio(chip, np);
+
+	ret = lan9303_handle_reset(chip);
+	if (ret)
+		return ret;
+
+	ret = lan9303_check_device(chip);
+	if (ret)
+		return ret;
+
+	ret = lan9303_register_switch(chip);
+	if (ret) {
+		dev_dbg(chip->dev, "Failed to register switch: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(lan9303_probe);
+
+int lan9303_remove(struct lan9303 *chip)
+{
+	int rc;
+
+	rc = lan9303_disable_processing(chip);
+	if (rc != 0)
+		dev_warn(chip->dev, "shutting down failed\n");
+
+	dsa_unregister_switch(chip->ds);
+
+	/* assert reset to the whole device to prevent it from doing anything */
+	gpiod_set_value_cansleep(chip->reset_gpio, 1);
+	gpiod_unexport(chip->reset_gpio);
+
+	return 0;
+}
+EXPORT_SYMBOL(lan9303_remove);
+
+MODULE_AUTHOR("Juergen Borleis <kernel@pengutronix.de>");
+MODULE_DESCRIPTION("Core driver for SMSC/Microchip LAN9303 three port ethernet switch");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/lan9303.h b/drivers/net/dsa/lan9303.h
new file mode 100644
index 000000000000..d1512dad2d90
--- /dev/null
+++ b/drivers/net/dsa/lan9303.h
@@ -0,0 +1,19 @@
+#include <linux/regmap.h>
+#include <linux/device.h>
+#include <net/dsa.h>
+
+struct lan9303 {
+	struct device *dev;
+	struct regmap *regmap;
+	struct regmap_irq_chip_data *irq_data;
+	struct gpio_desc *reset_gpio;
+	u32 reset_duration; /* in [ms] */
+	bool phy_addr_sel_strap;
+	struct dsa_switch *ds;
+	struct mutex indirect_mutex; /* protect indexed register access */
+};
+
+extern const struct regmap_access_table lan9303_register_set;
+
+int lan9303_probe(struct lan9303 *chip, struct device_node *np);
+int lan9303_remove(struct lan9303 *chip);
diff --git a/drivers/net/dsa/lan9303_i2c.c b/drivers/net/dsa/lan9303_i2c.c
new file mode 100644
index 000000000000..ab3ce0da5071
--- /dev/null
+++ b/drivers/net/dsa/lan9303_i2c.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) 2017 Pengutronix, Juergen Borleis <kernel@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/of.h>
+
+#include "lan9303.h"
+
+struct lan9303_i2c {
+	struct i2c_client *device;
+	struct lan9303 chip;
+};
+
+static const struct regmap_config lan9303_i2c_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 32,
+	.reg_stride = 1,
+	.can_multi_write = true,
+	.max_register = 0x0ff, /* address bits 0..1 are not used */
+	.reg_format_endian = REGMAP_ENDIAN_LITTLE,
+
+	.volatile_table = &lan9303_register_set,
+	.wr_table = &lan9303_register_set,
+	.rd_table = &lan9303_register_set,
+
+	.cache_type = REGCACHE_NONE,
+};
+
+static int lan9303_i2c_probe(struct i2c_client *client,
+			     const struct i2c_device_id *id)
+{
+	struct lan9303_i2c *sw_dev;
+	int ret;
+
+	sw_dev = devm_kzalloc(&client->dev, sizeof(struct lan9303_i2c),
+			      GFP_KERNEL);
+	if (!sw_dev)
+		return -ENOMEM;
+
+	sw_dev->chip.regmap = devm_regmap_init_i2c(client,
+						&lan9303_i2c_regmap_config);
+	if (IS_ERR(sw_dev->chip.regmap)) {
+		ret = PTR_ERR(sw_dev->chip.regmap);
+		dev_err(&client->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	/* link forward and backward */
+	sw_dev->device = client;
+	i2c_set_clientdata(client, sw_dev);
+	sw_dev->chip.dev = &client->dev;
+
+	ret = lan9303_probe(&sw_dev->chip, client->dev.of_node);
+	if (ret != 0)
+		return ret;
+
+	dev_info(&client->dev, "LAN9303 I2C driver loaded successfully\n");
+
+	return 0;
+}
+
+static int lan9303_i2c_remove(struct i2c_client *client)
+{
+	struct lan9303_i2c *sw_dev;
+
+	sw_dev = i2c_get_clientdata(client);
+	if (!sw_dev)
+		return -ENODEV;
+
+	return lan9303_remove(&sw_dev->chip);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static const struct i2c_device_id lan9303_i2c_id[] = {
+	{ "lan9303", 0 },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, lan9303_i2c_id);
+
+static const struct of_device_id lan9303_i2c_of_match[] = {
+	{ .compatible = "smsc,lan9303-i2c", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, lan9303_i2c_of_match);
+
+static struct i2c_driver lan9303_i2c_driver = {
+	.driver = {
+		.name = "LAN9303_I2C",
+		.of_match_table = of_match_ptr(lan9303_i2c_of_match),
+	},
+	.probe = lan9303_i2c_probe,
+	.remove = lan9303_i2c_remove,
+	.id_table = lan9303_i2c_id,
+};
+module_i2c_driver(lan9303_i2c_driver);
+
+MODULE_AUTHOR("Juergen Borleis <kernel@pengutronix.de>");
+MODULE_DESCRIPTION("Driver for SMSC/Microchip LAN9303 three port ethernet switch in I2C managed mode");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c
new file mode 100644
index 000000000000..93c36c0541cf
--- /dev/null
+++ b/drivers/net/dsa/lan9303_mdio.c
@@ -0,0 +1,148 @@
+/*
+ * Copyright (C) 2017 Pengutronix, Juergen Borleis <kernel@pengutronix.de>
+ *
+ * Partially based on a patch from
+ * Copyright (c) 2014 Stefan Roese <sr@denx.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+#include <linux/of.h>
+
+#include "lan9303.h"
+
+/* Generate phy-addr and -reg from the input address */
+#define PHY_ADDR(x) ((((x) >> 6) + 0x10) & 0x1f)
+#define PHY_REG(x) (((x) >> 1) & 0x1f)
+
+struct lan9303_mdio {
+	struct mdio_device *device;
+	struct lan9303 chip;
+};
+
+static void lan9303_mdio_real_write(struct mdio_device *mdio, int reg, u16 val)
+{
+	mdio->bus->write(mdio->bus, PHY_ADDR(reg), PHY_REG(reg), val);
+}
+
+static int lan9303_mdio_write(void *ctx, uint32_t reg, uint32_t val)
+{
+	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
+
+	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	lan9303_mdio_real_write(sw_dev->device, reg, val & 0xffff);
+	lan9303_mdio_real_write(sw_dev->device, reg + 2, (val >> 16) & 0xffff);
+	mutex_unlock(&sw_dev->device->bus->mdio_lock);
+
+	return 0;
+}
+
+static u16 lan9303_mdio_real_read(struct mdio_device *mdio, int reg)
+{
+	return mdio->bus->read(mdio->bus, PHY_ADDR(reg), PHY_REG(reg));
+}
+
+static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val)
+{
+	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
+
+	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	*val = lan9303_mdio_real_read(sw_dev->device, reg);
+	*val |= (lan9303_mdio_real_read(sw_dev->device, reg + 2) << 16);
+	mutex_unlock(&sw_dev->device->bus->mdio_lock);
+
+	return 0;
+}
+
+static const struct regmap_config lan9303_mdio_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 32,
+	.reg_stride = 1,
+	.can_multi_write = true,
+	.max_register = 0x0ff, /* address bits 0..1 are not used */
+	.reg_format_endian = REGMAP_ENDIAN_LITTLE,
+
+	.volatile_table = &lan9303_register_set,
+	.wr_table = &lan9303_register_set,
+	.rd_table = &lan9303_register_set,
+
+	.reg_read = lan9303_mdio_read,
+	.reg_write = lan9303_mdio_write,
+
+	.cache_type = REGCACHE_NONE,
+};
+
+static int lan9303_mdio_probe(struct mdio_device *mdiodev)
+{
+	struct lan9303_mdio *sw_dev;
+	int ret;
+
+	sw_dev = devm_kzalloc(&mdiodev->dev, sizeof(struct lan9303_mdio),
+			      GFP_KERNEL);
+	if (!sw_dev)
+		return -ENOMEM;
+
+	sw_dev->chip.regmap = devm_regmap_init(&mdiodev->dev, NULL, sw_dev,
+						&lan9303_mdio_regmap_config);
+	if (IS_ERR(sw_dev->chip.regmap)) {
+		ret = PTR_ERR(sw_dev->chip.regmap);
+		dev_err(&mdiodev->dev, "regmap init failed: %d\n", ret);
+		return ret;
+	}
+
+	/* link forward and backward */
+	sw_dev->device = mdiodev;
+	dev_set_drvdata(&mdiodev->dev, sw_dev);
+	sw_dev->chip.dev = &mdiodev->dev;
+
+	ret = lan9303_probe(&sw_dev->chip, mdiodev->dev.of_node);
+	if (ret != 0)
+		return ret;
+
+	dev_info(&mdiodev->dev, "LAN9303 MDIO driver loaded successfully\n");
+
+	return 0;
+}
+
+static void lan9303_mdio_remove(struct mdio_device *mdiodev)
+{
+	struct lan9303_mdio *sw_dev = dev_get_drvdata(&mdiodev->dev);
+
+	if (!sw_dev)
+		return;
+
+	lan9303_remove(&sw_dev->chip);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static const struct of_device_id lan9303_mdio_of_match[] = {
+	{ .compatible = "smsc,lan9303-mdio" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, lan9303_mdio_of_match);
+
+static struct mdio_driver lan9303_mdio_driver = {
+	.mdiodrv.driver = {
+		.name = "LAN9303_MDIO",
+		.of_match_table = of_match_ptr(lan9303_mdio_of_match),
+	},
+	.probe  = lan9303_mdio_probe,
+	.remove = lan9303_mdio_remove,
+};
+mdio_module_driver(lan9303_mdio_driver);
+
+MODULE_AUTHOR("Stefan Roese <sr@denx.de>, Juergen Borleis <kernel@pengutronix.de>");
+MODULE_DESCRIPTION("Driver for SMSC/Microchip LAN9303 three port ethernet switch in MDIO managed mode");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
new file mode 100644
index 000000000000..b070c167e70f
--- /dev/null
+++ b/drivers/net/dsa/mt7530.c
@@ -0,0 +1,1126 @@
+/*
+ * Mediatek MT7530 DSA Switch driver
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/iopoll.h>
+#include <linux/mdio.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_gpio.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+#include <linux/gpio/consumer.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+
+#include "mt7530.h"
+
+/* String, offset, and register size in bytes if different from 4 bytes */
+static const struct mt7530_mib_desc mt7530_mib[] = {
+	MIB_DESC(1, 0x00, "TxDrop"),
+	MIB_DESC(1, 0x04, "TxCrcErr"),
+	MIB_DESC(1, 0x08, "TxUnicast"),
+	MIB_DESC(1, 0x0c, "TxMulticast"),
+	MIB_DESC(1, 0x10, "TxBroadcast"),
+	MIB_DESC(1, 0x14, "TxCollision"),
+	MIB_DESC(1, 0x18, "TxSingleCollision"),
+	MIB_DESC(1, 0x1c, "TxMultipleCollision"),
+	MIB_DESC(1, 0x20, "TxDeferred"),
+	MIB_DESC(1, 0x24, "TxLateCollision"),
+	MIB_DESC(1, 0x28, "TxExcessiveCollistion"),
+	MIB_DESC(1, 0x2c, "TxPause"),
+	MIB_DESC(1, 0x30, "TxPktSz64"),
+	MIB_DESC(1, 0x34, "TxPktSz65To127"),
+	MIB_DESC(1, 0x38, "TxPktSz128To255"),
+	MIB_DESC(1, 0x3c, "TxPktSz256To511"),
+	MIB_DESC(1, 0x40, "TxPktSz512To1023"),
+	MIB_DESC(1, 0x44, "Tx1024ToMax"),
+	MIB_DESC(2, 0x48, "TxBytes"),
+	MIB_DESC(1, 0x60, "RxDrop"),
+	MIB_DESC(1, 0x64, "RxFiltering"),
+	MIB_DESC(1, 0x6c, "RxMulticast"),
+	MIB_DESC(1, 0x70, "RxBroadcast"),
+	MIB_DESC(1, 0x74, "RxAlignErr"),
+	MIB_DESC(1, 0x78, "RxCrcErr"),
+	MIB_DESC(1, 0x7c, "RxUnderSizeErr"),
+	MIB_DESC(1, 0x80, "RxFragErr"),
+	MIB_DESC(1, 0x84, "RxOverSzErr"),
+	MIB_DESC(1, 0x88, "RxJabberErr"),
+	MIB_DESC(1, 0x8c, "RxPause"),
+	MIB_DESC(1, 0x90, "RxPktSz64"),
+	MIB_DESC(1, 0x94, "RxPktSz65To127"),
+	MIB_DESC(1, 0x98, "RxPktSz128To255"),
+	MIB_DESC(1, 0x9c, "RxPktSz256To511"),
+	MIB_DESC(1, 0xa0, "RxPktSz512To1023"),
+	MIB_DESC(1, 0xa4, "RxPktSz1024ToMax"),
+	MIB_DESC(2, 0xa8, "RxBytes"),
+	MIB_DESC(1, 0xb0, "RxCtrlDrop"),
+	MIB_DESC(1, 0xb4, "RxIngressDrop"),
+	MIB_DESC(1, 0xb8, "RxArlDrop"),
+};
+
+static int
+mt7623_trgmii_write(struct mt7530_priv *priv,  u32 reg, u32 val)
+{
+	int ret;
+
+	ret =  regmap_write(priv->ethernet, TRGMII_BASE(reg), val);
+	if (ret < 0)
+		dev_err(priv->dev,
+			"failed to priv write register\n");
+	return ret;
+}
+
+static u32
+mt7623_trgmii_read(struct mt7530_priv *priv, u32 reg)
+{
+	int ret;
+	u32 val;
+
+	ret = regmap_read(priv->ethernet, TRGMII_BASE(reg), &val);
+	if (ret < 0) {
+		dev_err(priv->dev,
+			"failed to priv read register\n");
+		return ret;
+	}
+
+	return val;
+}
+
+static void
+mt7623_trgmii_rmw(struct mt7530_priv *priv, u32 reg,
+		  u32 mask, u32 set)
+{
+	u32 val;
+
+	val = mt7623_trgmii_read(priv, reg);
+	val &= ~mask;
+	val |= set;
+	mt7623_trgmii_write(priv, reg, val);
+}
+
+static void
+mt7623_trgmii_set(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	mt7623_trgmii_rmw(priv, reg, 0, val);
+}
+
+static void
+mt7623_trgmii_clear(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	mt7623_trgmii_rmw(priv, reg, val, 0);
+}
+
+static int
+core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad)
+{
+	struct mii_bus *bus = priv->bus;
+	int value, ret;
+
+	/* Write the desired MMD Devad */
+	ret = bus->write(bus, 0, MII_MMD_CTRL, devad);
+	if (ret < 0)
+		goto err;
+
+	/* Write the desired MMD register address */
+	ret = bus->write(bus, 0, MII_MMD_DATA, prtad);
+	if (ret < 0)
+		goto err;
+
+	/* Select the Function : DATA with no post increment */
+	ret = bus->write(bus, 0, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
+	if (ret < 0)
+		goto err;
+
+	/* Read the content of the MMD's selected register */
+	value = bus->read(bus, 0, MII_MMD_DATA);
+
+	return value;
+err:
+	dev_err(&bus->dev,  "failed to read mmd register\n");
+
+	return ret;
+}
+
+static int
+core_write_mmd_indirect(struct mt7530_priv *priv, int prtad,
+			int devad, u32 data)
+{
+	struct mii_bus *bus = priv->bus;
+	int ret;
+
+	/* Write the desired MMD Devad */
+	ret = bus->write(bus, 0, MII_MMD_CTRL, devad);
+	if (ret < 0)
+		goto err;
+
+	/* Write the desired MMD register address */
+	ret = bus->write(bus, 0, MII_MMD_DATA, prtad);
+	if (ret < 0)
+		goto err;
+
+	/* Select the Function : DATA with no post increment */
+	ret = bus->write(bus, 0, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
+	if (ret < 0)
+		goto err;
+
+	/* Write the data into MMD's selected register */
+	ret = bus->write(bus, 0, MII_MMD_DATA, data);
+err:
+	if (ret < 0)
+		dev_err(&bus->dev,
+			"failed to write mmd register\n");
+	return ret;
+}
+
+static void
+core_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	struct mii_bus *bus = priv->bus;
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	core_write_mmd_indirect(priv, reg, MDIO_MMD_VEND2, val);
+
+	mutex_unlock(&bus->mdio_lock);
+}
+
+static void
+core_rmw(struct mt7530_priv *priv, u32 reg, u32 mask, u32 set)
+{
+	struct mii_bus *bus = priv->bus;
+	u32 val;
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	val = core_read_mmd_indirect(priv, reg, MDIO_MMD_VEND2);
+	val &= ~mask;
+	val |= set;
+	core_write_mmd_indirect(priv, reg, MDIO_MMD_VEND2, val);
+
+	mutex_unlock(&bus->mdio_lock);
+}
+
+static void
+core_set(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	core_rmw(priv, reg, 0, val);
+}
+
+static void
+core_clear(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	core_rmw(priv, reg, val, 0);
+}
+
+static int
+mt7530_mii_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	struct mii_bus *bus = priv->bus;
+	u16 page, r, lo, hi;
+	int ret;
+
+	page = (reg >> 6) & 0x3ff;
+	r  = (reg >> 2) & 0xf;
+	lo = val & 0xffff;
+	hi = val >> 16;
+
+	/* MT7530 uses 31 as the pseudo port */
+	ret = bus->write(bus, 0x1f, 0x1f, page);
+	if (ret < 0)
+		goto err;
+
+	ret = bus->write(bus, 0x1f, r,  lo);
+	if (ret < 0)
+		goto err;
+
+	ret = bus->write(bus, 0x1f, 0x10, hi);
+err:
+	if (ret < 0)
+		dev_err(&bus->dev,
+			"failed to write mt7530 register\n");
+	return ret;
+}
+
+static u32
+mt7530_mii_read(struct mt7530_priv *priv, u32 reg)
+{
+	struct mii_bus *bus = priv->bus;
+	u16 page, r, lo, hi;
+	int ret;
+
+	page = (reg >> 6) & 0x3ff;
+	r = (reg >> 2) & 0xf;
+
+	/* MT7530 uses 31 as the pseudo port */
+	ret = bus->write(bus, 0x1f, 0x1f, page);
+	if (ret < 0) {
+		dev_err(&bus->dev,
+			"failed to read mt7530 register\n");
+		return ret;
+	}
+
+	lo = bus->read(bus, 0x1f, r);
+	hi = bus->read(bus, 0x1f, 0x10);
+
+	return (hi << 16) | (lo & 0xffff);
+}
+
+static void
+mt7530_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	struct mii_bus *bus = priv->bus;
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	mt7530_mii_write(priv, reg, val);
+
+	mutex_unlock(&bus->mdio_lock);
+}
+
+static u32
+_mt7530_read(struct mt7530_dummy_poll *p)
+{
+	struct mii_bus		*bus = p->priv->bus;
+	u32 val;
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	val = mt7530_mii_read(p->priv, p->reg);
+
+	mutex_unlock(&bus->mdio_lock);
+
+	return val;
+}
+
+static u32
+mt7530_read(struct mt7530_priv *priv, u32 reg)
+{
+	struct mt7530_dummy_poll p;
+
+	INIT_MT7530_DUMMY_POLL(&p, priv, reg);
+	return _mt7530_read(&p);
+}
+
+static void
+mt7530_rmw(struct mt7530_priv *priv, u32 reg,
+	   u32 mask, u32 set)
+{
+	struct mii_bus *bus = priv->bus;
+	u32 val;
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	val = mt7530_mii_read(priv, reg);
+	val &= ~mask;
+	val |= set;
+	mt7530_mii_write(priv, reg, val);
+
+	mutex_unlock(&bus->mdio_lock);
+}
+
+static void
+mt7530_set(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	mt7530_rmw(priv, reg, 0, val);
+}
+
+static void
+mt7530_clear(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+	mt7530_rmw(priv, reg, val, 0);
+}
+
+static int
+mt7530_fdb_cmd(struct mt7530_priv *priv, enum mt7530_fdb_cmd cmd, u32 *rsp)
+{
+	u32 val;
+	int ret;
+	struct mt7530_dummy_poll p;
+
+	/* Set the command operating upon the MAC address entries */
+	val = ATC_BUSY | ATC_MAT(0) | cmd;
+	mt7530_write(priv, MT7530_ATC, val);
+
+	INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_ATC);
+	ret = readx_poll_timeout(_mt7530_read, &p, val,
+				 !(val & ATC_BUSY), 20, 20000);
+	if (ret < 0) {
+		dev_err(priv->dev, "reset timeout\n");
+		return ret;
+	}
+
+	/* Additional sanity for read command if the specified
+	 * entry is invalid
+	 */
+	val = mt7530_read(priv, MT7530_ATC);
+	if ((cmd == MT7530_FDB_READ) && (val & ATC_INVALID))
+		return -EINVAL;
+
+	if (rsp)
+		*rsp = val;
+
+	return 0;
+}
+
+static void
+mt7530_fdb_read(struct mt7530_priv *priv, struct mt7530_fdb *fdb)
+{
+	u32 reg[3];
+	int i;
+
+	/* Read from ARL table into an array */
+	for (i = 0; i < 3; i++) {
+		reg[i] = mt7530_read(priv, MT7530_TSRA1 + (i * 4));
+
+		dev_dbg(priv->dev, "%s(%d) reg[%d]=0x%x\n",
+			__func__, __LINE__, i, reg[i]);
+	}
+
+	fdb->vid = (reg[1] >> CVID) & CVID_MASK;
+	fdb->aging = (reg[2] >> AGE_TIMER) & AGE_TIMER_MASK;
+	fdb->port_mask = (reg[2] >> PORT_MAP) & PORT_MAP_MASK;
+	fdb->mac[0] = (reg[0] >> MAC_BYTE_0) & MAC_BYTE_MASK;
+	fdb->mac[1] = (reg[0] >> MAC_BYTE_1) & MAC_BYTE_MASK;
+	fdb->mac[2] = (reg[0] >> MAC_BYTE_2) & MAC_BYTE_MASK;
+	fdb->mac[3] = (reg[0] >> MAC_BYTE_3) & MAC_BYTE_MASK;
+	fdb->mac[4] = (reg[1] >> MAC_BYTE_4) & MAC_BYTE_MASK;
+	fdb->mac[5] = (reg[1] >> MAC_BYTE_5) & MAC_BYTE_MASK;
+	fdb->noarp = ((reg[2] >> ENT_STATUS) & ENT_STATUS_MASK) == STATIC_ENT;
+}
+
+static void
+mt7530_fdb_write(struct mt7530_priv *priv, u16 vid,
+		 u8 port_mask, const u8 *mac,
+		 u8 aging, u8 type)
+{
+	u32 reg[3] = { 0 };
+	int i;
+
+	reg[1] |= vid & CVID_MASK;
+	reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
+	reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
+	/* STATIC_ENT indicate that entry is static wouldn't
+	 * be aged out and STATIC_EMP specified as erasing an
+	 * entry
+	 */
+	reg[2] |= (type & ENT_STATUS_MASK) << ENT_STATUS;
+	reg[1] |= mac[5] << MAC_BYTE_5;
+	reg[1] |= mac[4] << MAC_BYTE_4;
+	reg[0] |= mac[3] << MAC_BYTE_3;
+	reg[0] |= mac[2] << MAC_BYTE_2;
+	reg[0] |= mac[1] << MAC_BYTE_1;
+	reg[0] |= mac[0] << MAC_BYTE_0;
+
+	/* Write array into the ARL table */
+	for (i = 0; i < 3; i++)
+		mt7530_write(priv, MT7530_ATA1 + (i * 4), reg[i]);
+}
+
+static int
+mt7530_pad_clk_setup(struct dsa_switch *ds, int mode)
+{
+	struct mt7530_priv *priv = ds->priv;
+	u32 ncpo1, ssc_delta, trgint, i;
+
+	switch (mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		trgint = 0;
+		ncpo1 = 0x0c80;
+		ssc_delta = 0x87;
+		break;
+	case PHY_INTERFACE_MODE_TRGMII:
+		trgint = 1;
+		ncpo1 = 0x1400;
+		ssc_delta = 0x57;
+		break;
+	default:
+		dev_err(priv->dev, "xMII mode %d not supported\n", mode);
+		return -EINVAL;
+	}
+
+	mt7530_rmw(priv, MT7530_P6ECR, P6_INTF_MODE_MASK,
+		   P6_INTF_MODE(trgint));
+
+	/* Lower Tx Driving for TRGMII path */
+	for (i = 0 ; i < NUM_TRGMII_CTRL ; i++)
+		mt7530_write(priv, MT7530_TRGMII_TD_ODT(i),
+			     TD_DM_DRVP(8) | TD_DM_DRVN(8));
+
+	/* Setup core clock for MT7530 */
+	if (!trgint) {
+		/* Disable MT7530 core clock */
+		core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+
+		/* Disable PLL, since phy_device has not yet been created
+		 * provided for phy_[read,write]_mmd_indirect is called, we
+		 * provide our own core_write_mmd_indirect to complete this
+		 * function.
+		 */
+		core_write_mmd_indirect(priv,
+					CORE_GSWPLL_GRP1,
+					MDIO_MMD_VEND2,
+					0);
+
+		/* Set core clock into 500Mhz */
+		core_write(priv, CORE_GSWPLL_GRP2,
+			   RG_GSWPLL_POSDIV_500M(1) |
+			   RG_GSWPLL_FBKDIV_500M(25));
+
+		/* Enable PLL */
+		core_write(priv, CORE_GSWPLL_GRP1,
+			   RG_GSWPLL_EN_PRE |
+			   RG_GSWPLL_POSDIV_200M(2) |
+			   RG_GSWPLL_FBKDIV_200M(32));
+
+		/* Enable MT7530 core clock */
+		core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+	}
+
+	/* Setup the MT7530 TRGMII Tx Clock */
+	core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+	core_write(priv, CORE_PLL_GROUP5, RG_LCDDS_PCW_NCPO1(ncpo1));
+	core_write(priv, CORE_PLL_GROUP6, RG_LCDDS_PCW_NCPO0(0));
+	core_write(priv, CORE_PLL_GROUP10, RG_LCDDS_SSC_DELTA(ssc_delta));
+	core_write(priv, CORE_PLL_GROUP11, RG_LCDDS_SSC_DELTA1(ssc_delta));
+	core_write(priv, CORE_PLL_GROUP4,
+		   RG_SYSPLL_DDSFBK_EN | RG_SYSPLL_BIAS_EN |
+		   RG_SYSPLL_BIAS_LPF_EN);
+	core_write(priv, CORE_PLL_GROUP2,
+		   RG_SYSPLL_EN_NORMAL | RG_SYSPLL_VODEN |
+		   RG_SYSPLL_POSDIV(1));
+	core_write(priv, CORE_PLL_GROUP7,
+		   RG_LCDDS_PCW_NCPO_CHG | RG_LCCDS_C(3) |
+		   RG_LCDDS_PWDB | RG_LCDDS_ISO_EN);
+	core_set(priv, CORE_TRGMII_GSW_CLK_CG,
+		 REG_GSWCK_EN | REG_TRGMIICK_EN);
+
+	if (!trgint)
+		for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+			mt7530_rmw(priv, MT7530_TRGMII_RD(i),
+				   RD_TAP_MASK, RD_TAP(16));
+	else
+		mt7623_trgmii_set(priv, GSW_INTF_MODE, INTF_MODE_TRGMII);
+
+	return 0;
+}
+
+static int
+mt7623_pad_clk_setup(struct dsa_switch *ds)
+{
+	struct mt7530_priv *priv = ds->priv;
+	int i;
+
+	for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+		mt7623_trgmii_write(priv, GSW_TRGMII_TD_ODT(i),
+				    TD_DM_DRVP(8) | TD_DM_DRVN(8));
+
+	mt7623_trgmii_set(priv, GSW_TRGMII_RCK_CTRL, RX_RST | RXC_DQSISEL);
+	mt7623_trgmii_clear(priv, GSW_TRGMII_RCK_CTRL, RX_RST);
+
+	return 0;
+}
+
+static void
+mt7530_mib_reset(struct dsa_switch *ds)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_FLUSH);
+	mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_ACTIVATE);
+}
+
+static void
+mt7530_port_set_status(struct mt7530_priv *priv, int port, int enable)
+{
+	u32 mask = PMCR_TX_EN | PMCR_RX_EN;
+
+	if (enable)
+		mt7530_set(priv, MT7530_PMCR_P(port), mask);
+	else
+		mt7530_clear(priv, MT7530_PMCR_P(port), mask);
+}
+
+static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	return mdiobus_read_nested(priv->bus, port, regnum);
+}
+
+int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	return mdiobus_write_nested(priv->bus, port, regnum, val);
+}
+
+static void
+mt7530_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++)
+		strncpy(data + i * ETH_GSTRING_LEN, mt7530_mib[i].name,
+			ETH_GSTRING_LEN);
+}
+
+static void
+mt7530_get_ethtool_stats(struct dsa_switch *ds, int port,
+			 uint64_t *data)
+{
+	struct mt7530_priv *priv = ds->priv;
+	const struct mt7530_mib_desc *mib;
+	u32 reg, i;
+	u64 hi;
+
+	for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++) {
+		mib = &mt7530_mib[i];
+		reg = MT7530_PORT_MIB_COUNTER(port) + mib->offset;
+
+		data[i] = mt7530_read(priv, reg);
+		if (mib->size == 2) {
+			hi = mt7530_read(priv, reg + 4);
+			data[i] |= hi << 32;
+		}
+	}
+}
+
+static int
+mt7530_get_sset_count(struct dsa_switch *ds)
+{
+	return ARRAY_SIZE(mt7530_mib);
+}
+
+static void mt7530_adjust_link(struct dsa_switch *ds, int port,
+			       struct phy_device *phydev)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	if (phy_is_pseudo_fixed_link(phydev)) {
+		dev_dbg(priv->dev, "phy-mode for master device = %x\n",
+			phydev->interface);
+
+		/* Setup TX circuit incluing relevant PAD and driving */
+		mt7530_pad_clk_setup(ds, phydev->interface);
+
+		/* Setup RX circuit, relevant PAD and driving on the host
+		 * which must be placed after the setup on the device side is
+		 * all finished.
+		 */
+		mt7623_pad_clk_setup(ds);
+	}
+}
+
+static int
+mt7530_cpu_port_enable(struct mt7530_priv *priv,
+		       int port)
+{
+	/* Enable Mediatek header mode on the cpu port */
+	mt7530_write(priv, MT7530_PVC_P(port),
+		     PORT_SPEC_TAG);
+
+	/* Setup the MAC by default for the cpu port */
+	mt7530_write(priv, MT7530_PMCR_P(port), PMCR_CPUP_LINK);
+
+	/* Disable auto learning on the cpu port */
+	mt7530_set(priv, MT7530_PSC_P(port), SA_DIS);
+
+	/* Unknown unicast frame fordwarding to the cpu port */
+	mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port)));
+
+	/* CPU port gets connected to all user ports of
+	 * the switch
+	 */
+	mt7530_write(priv, MT7530_PCR_P(port),
+		     PCR_MATRIX(priv->ds->enabled_port_mask));
+
+	return 0;
+}
+
+static int
+mt7530_port_enable(struct dsa_switch *ds, int port,
+		   struct phy_device *phy)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mutex_lock(&priv->reg_mutex);
+
+	/* Setup the MAC for the user port */
+	mt7530_write(priv, MT7530_PMCR_P(port), PMCR_USERP_LINK);
+
+	/* Allow the user port gets connected to the cpu port and also
+	 * restore the port matrix if the port is the member of a certain
+	 * bridge.
+	 */
+	priv->ports[port].pm |= PCR_MATRIX(BIT(MT7530_CPU_PORT));
+	priv->ports[port].enable = true;
+	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
+		   priv->ports[port].pm);
+	mt7530_port_set_status(priv, port, 1);
+
+	mutex_unlock(&priv->reg_mutex);
+
+	return 0;
+}
+
+static void
+mt7530_port_disable(struct dsa_switch *ds, int port,
+		    struct phy_device *phy)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mutex_lock(&priv->reg_mutex);
+
+	/* Clear up all port matrix which could be restored in the next
+	 * enablement for the port.
+	 */
+	priv->ports[port].enable = false;
+	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
+		   PCR_MATRIX_CLR);
+	mt7530_port_set_status(priv, port, 0);
+
+	mutex_unlock(&priv->reg_mutex);
+}
+
+static void
+mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+{
+	struct mt7530_priv *priv = ds->priv;
+	u32 stp_state;
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		stp_state = MT7530_STP_DISABLED;
+		break;
+	case BR_STATE_BLOCKING:
+		stp_state = MT7530_STP_BLOCKING;
+		break;
+	case BR_STATE_LISTENING:
+		stp_state = MT7530_STP_LISTENING;
+		break;
+	case BR_STATE_LEARNING:
+		stp_state = MT7530_STP_LEARNING;
+		break;
+	case BR_STATE_FORWARDING:
+	default:
+		stp_state = MT7530_STP_FORWARDING;
+		break;
+	}
+
+	mt7530_rmw(priv, MT7530_SSP_P(port), FID_PST_MASK, stp_state);
+}
+
+static int
+mt7530_port_bridge_join(struct dsa_switch *ds, int port,
+			struct net_device *bridge)
+{
+	struct mt7530_priv *priv = ds->priv;
+	u32 port_bitmap = BIT(MT7530_CPU_PORT);
+	int i;
+
+	mutex_lock(&priv->reg_mutex);
+
+	for (i = 0; i < MT7530_NUM_PORTS; i++) {
+		/* Add this port to the port matrix of the other ports in the
+		 * same bridge. If the port is disabled, port matrix is kept
+		 * and not being setup until the port becomes enabled.
+		 */
+		if (ds->enabled_port_mask & BIT(i) && i != port) {
+			if (ds->ports[i].bridge_dev != bridge)
+				continue;
+			if (priv->ports[i].enable)
+				mt7530_set(priv, MT7530_PCR_P(i),
+					   PCR_MATRIX(BIT(port)));
+			priv->ports[i].pm |= PCR_MATRIX(BIT(port));
+
+			port_bitmap |= BIT(i);
+		}
+	}
+
+	/* Add the all other ports to this port matrix. */
+	if (priv->ports[port].enable)
+		mt7530_rmw(priv, MT7530_PCR_P(port),
+			   PCR_MATRIX_MASK, PCR_MATRIX(port_bitmap));
+	priv->ports[port].pm |= PCR_MATRIX(port_bitmap);
+
+	mutex_unlock(&priv->reg_mutex);
+
+	return 0;
+}
+
+static void
+mt7530_port_bridge_leave(struct dsa_switch *ds, int port,
+			 struct net_device *bridge)
+{
+	struct mt7530_priv *priv = ds->priv;
+	int i;
+
+	mutex_lock(&priv->reg_mutex);
+
+	for (i = 0; i < MT7530_NUM_PORTS; i++) {
+		/* Remove this port from the port matrix of the other ports
+		 * in the same bridge. If the port is disabled, port matrix
+		 * is kept and not being setup until the port becomes enabled.
+		 */
+		if (ds->enabled_port_mask & BIT(i) && i != port) {
+			if (ds->ports[i].bridge_dev != bridge)
+				continue;
+			if (priv->ports[i].enable)
+				mt7530_clear(priv, MT7530_PCR_P(i),
+					     PCR_MATRIX(BIT(port)));
+			priv->ports[i].pm &= ~PCR_MATRIX(BIT(port));
+		}
+	}
+
+	/* Set the cpu port to be the only one in the port matrix of
+	 * this port.
+	 */
+	if (priv->ports[port].enable)
+		mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
+			   PCR_MATRIX(BIT(MT7530_CPU_PORT)));
+	priv->ports[port].pm = PCR_MATRIX(BIT(MT7530_CPU_PORT));
+
+	mutex_unlock(&priv->reg_mutex);
+}
+
+static int
+mt7530_port_fdb_prepare(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_fdb *fdb,
+			struct switchdev_trans *trans)
+{
+	struct mt7530_priv *priv = ds->priv;
+	int ret;
+
+	/* Because auto-learned entrie shares the same FDB table.
+	 * an entry is reserved with no port_mask to make sure fdb_add
+	 * is called while the entry is still available.
+	 */
+	mutex_lock(&priv->reg_mutex);
+	mt7530_fdb_write(priv, fdb->vid, 0, fdb->addr, -1, STATIC_ENT);
+	ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, 0);
+	mutex_unlock(&priv->reg_mutex);
+
+	return ret;
+}
+
+static void
+mt7530_port_fdb_add(struct dsa_switch *ds, int port,
+		    const struct switchdev_obj_port_fdb *fdb,
+		    struct switchdev_trans *trans)
+{
+	struct mt7530_priv *priv = ds->priv;
+	u8 port_mask = BIT(port);
+
+	mutex_lock(&priv->reg_mutex);
+	mt7530_fdb_write(priv, fdb->vid, port_mask, fdb->addr, -1, STATIC_ENT);
+	mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, 0);
+	mutex_unlock(&priv->reg_mutex);
+}
+
+static int
+mt7530_port_fdb_del(struct dsa_switch *ds, int port,
+		    const struct switchdev_obj_port_fdb *fdb)
+{
+	struct mt7530_priv *priv = ds->priv;
+	int ret;
+	u8 port_mask = BIT(port);
+
+	mutex_lock(&priv->reg_mutex);
+	mt7530_fdb_write(priv, fdb->vid, port_mask, fdb->addr, -1, STATIC_EMP);
+	ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, 0);
+	mutex_unlock(&priv->reg_mutex);
+
+	return ret;
+}
+
+static int
+mt7530_port_fdb_dump(struct dsa_switch *ds, int port,
+		     struct switchdev_obj_port_fdb *fdb,
+		     int (*cb)(struct switchdev_obj *obj))
+{
+	struct mt7530_priv *priv = ds->priv;
+	struct mt7530_fdb _fdb = { 0 };
+	int cnt = MT7530_NUM_FDB_RECORDS;
+	int ret = 0;
+	u32 rsp = 0;
+
+	mutex_lock(&priv->reg_mutex);
+
+	ret = mt7530_fdb_cmd(priv, MT7530_FDB_START, &rsp);
+	if (ret < 0)
+		goto err;
+
+	do {
+		if (rsp & ATC_SRCH_HIT) {
+			mt7530_fdb_read(priv, &_fdb);
+			if (_fdb.port_mask & BIT(port)) {
+				ether_addr_copy(fdb->addr, _fdb.mac);
+				fdb->vid = _fdb.vid;
+				fdb->ndm_state = _fdb.noarp ?
+						NUD_NOARP : NUD_REACHABLE;
+				ret = cb(&fdb->obj);
+				if (ret < 0)
+					break;
+			}
+		}
+	} while (--cnt &&
+		 !(rsp & ATC_SRCH_END) &&
+		 !mt7530_fdb_cmd(priv, MT7530_FDB_NEXT, &rsp));
+err:
+	mutex_unlock(&priv->reg_mutex);
+
+	return 0;
+}
+
+static enum dsa_tag_protocol
+mtk_get_tag_protocol(struct dsa_switch *ds)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	if (!dsa_is_cpu_port(ds, MT7530_CPU_PORT)) {
+		dev_warn(priv->dev,
+			 "port not matched with tagging CPU port\n");
+		return DSA_TAG_PROTO_NONE;
+	} else {
+		return DSA_TAG_PROTO_MTK;
+	}
+}
+
+static int
+mt7530_setup(struct dsa_switch *ds)
+{
+	struct mt7530_priv *priv = ds->priv;
+	int ret, i;
+	u32 id, val;
+	struct device_node *dn;
+	struct mt7530_dummy_poll p;
+
+	/* The parent node of master_netdev which holds the common system
+	 * controller also is the container for two GMACs nodes representing
+	 * as two netdev instances.
+	 */
+	dn = ds->master_netdev->dev.of_node->parent;
+	priv->ethernet = syscon_node_to_regmap(dn);
+	if (IS_ERR(priv->ethernet))
+		return PTR_ERR(priv->ethernet);
+
+	regulator_set_voltage(priv->core_pwr, 1000000, 1000000);
+	ret = regulator_enable(priv->core_pwr);
+	if (ret < 0) {
+		dev_err(priv->dev,
+			"Failed to enable core power: %d\n", ret);
+		return ret;
+	}
+
+	regulator_set_voltage(priv->io_pwr, 3300000, 3300000);
+	ret = regulator_enable(priv->io_pwr);
+	if (ret < 0) {
+		dev_err(priv->dev, "Failed to enable io pwr: %d\n",
+			ret);
+		return ret;
+	}
+
+	/* Reset whole chip through gpio pin or memory-mapped registers for
+	 * different type of hardware
+	 */
+	if (priv->mcm) {
+		reset_control_assert(priv->rstc);
+		usleep_range(1000, 1100);
+		reset_control_deassert(priv->rstc);
+	} else {
+		gpiod_set_value_cansleep(priv->reset, 0);
+		usleep_range(1000, 1100);
+		gpiod_set_value_cansleep(priv->reset, 1);
+	}
+
+	/* Waiting for MT7530 got to stable */
+	INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_HWTRAP);
+	ret = readx_poll_timeout(_mt7530_read, &p, val, val != 0,
+				 20, 1000000);
+	if (ret < 0) {
+		dev_err(priv->dev, "reset timeout\n");
+		return ret;
+	}
+
+	id = mt7530_read(priv, MT7530_CREV);
+	id >>= CHIP_NAME_SHIFT;
+	if (id != MT7530_ID) {
+		dev_err(priv->dev, "chip %x can't be supported\n", id);
+		return -ENODEV;
+	}
+
+	/* Reset the switch through internal reset */
+	mt7530_write(priv, MT7530_SYS_CTRL,
+		     SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST |
+		     SYS_CTRL_REG_RST);
+
+	/* Enable Port 6 only; P5 as GMAC5 which currently is not supported */
+	val = mt7530_read(priv, MT7530_MHWTRAP);
+	val &= ~MHWTRAP_P6_DIS & ~MHWTRAP_PHY_ACCESS;
+	val |= MHWTRAP_MANUAL;
+	mt7530_write(priv, MT7530_MHWTRAP, val);
+
+	/* Enable and reset MIB counters */
+	mt7530_mib_reset(ds);
+
+	mt7530_clear(priv, MT7530_MFC, UNU_FFP_MASK);
+
+	for (i = 0; i < MT7530_NUM_PORTS; i++) {
+		/* Disable forwarding by default on all ports */
+		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
+			   PCR_MATRIX_CLR);
+
+		if (dsa_is_cpu_port(ds, i))
+			mt7530_cpu_port_enable(priv, i);
+		else
+			mt7530_port_disable(ds, i, NULL);
+	}
+
+	/* Flush the FDB table */
+	ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, 0);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static struct dsa_switch_ops mt7530_switch_ops = {
+	.get_tag_protocol	= mtk_get_tag_protocol,
+	.setup			= mt7530_setup,
+	.get_strings		= mt7530_get_strings,
+	.phy_read		= mt7530_phy_read,
+	.phy_write		= mt7530_phy_write,
+	.get_ethtool_stats	= mt7530_get_ethtool_stats,
+	.get_sset_count		= mt7530_get_sset_count,
+	.adjust_link		= mt7530_adjust_link,
+	.port_enable		= mt7530_port_enable,
+	.port_disable		= mt7530_port_disable,
+	.port_stp_state_set	= mt7530_stp_state_set,
+	.port_bridge_join	= mt7530_port_bridge_join,
+	.port_bridge_leave	= mt7530_port_bridge_leave,
+	.port_fdb_prepare	= mt7530_port_fdb_prepare,
+	.port_fdb_add		= mt7530_port_fdb_add,
+	.port_fdb_del		= mt7530_port_fdb_del,
+	.port_fdb_dump		= mt7530_port_fdb_dump,
+};
+
+static int
+mt7530_probe(struct mdio_device *mdiodev)
+{
+	struct mt7530_priv *priv;
+	struct device_node *dn;
+
+	dn = mdiodev->dev.of_node;
+
+	priv = devm_kzalloc(&mdiodev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS);
+	if (!priv->ds)
+		return -ENOMEM;
+
+	/* Use medatek,mcm property to distinguish hardware type that would
+	 * casues a little bit differences on power-on sequence.
+	 */
+	priv->mcm = of_property_read_bool(dn, "mediatek,mcm");
+	if (priv->mcm) {
+		dev_info(&mdiodev->dev, "MT7530 adapts as multi-chip module\n");
+
+		priv->rstc = devm_reset_control_get(&mdiodev->dev, "mcm");
+		if (IS_ERR(priv->rstc)) {
+			dev_err(&mdiodev->dev, "Couldn't get our reset line\n");
+			return PTR_ERR(priv->rstc);
+		}
+	}
+
+	priv->core_pwr = devm_regulator_get(&mdiodev->dev, "core");
+	if (IS_ERR(priv->core_pwr))
+		return PTR_ERR(priv->core_pwr);
+
+	priv->io_pwr = devm_regulator_get(&mdiodev->dev, "io");
+	if (IS_ERR(priv->io_pwr))
+		return PTR_ERR(priv->io_pwr);
+
+	/* Not MCM that indicates switch works as the remote standalone
+	 * integrated circuit so the GPIO pin would be used to complete
+	 * the reset, otherwise memory-mapped register accessing used
+	 * through syscon provides in the case of MCM.
+	 */
+	if (!priv->mcm) {
+		priv->reset = devm_gpiod_get_optional(&mdiodev->dev, "reset",
+						      GPIOD_OUT_LOW);
+		if (IS_ERR(priv->reset)) {
+			dev_err(&mdiodev->dev, "Couldn't get our reset line\n");
+			return PTR_ERR(priv->reset);
+		}
+	}
+
+	priv->bus = mdiodev->bus;
+	priv->dev = &mdiodev->dev;
+	priv->ds->priv = priv;
+	priv->ds->ops = &mt7530_switch_ops;
+	mutex_init(&priv->reg_mutex);
+	dev_set_drvdata(&mdiodev->dev, priv);
+
+	return dsa_register_switch(priv->ds, &mdiodev->dev);
+}
+
+static void
+mt7530_remove(struct mdio_device *mdiodev)
+{
+	struct mt7530_priv *priv = dev_get_drvdata(&mdiodev->dev);
+	int ret = 0;
+
+	ret = regulator_disable(priv->core_pwr);
+	if (ret < 0)
+		dev_err(priv->dev,
+			"Failed to disable core power: %d\n", ret);
+
+	ret = regulator_disable(priv->io_pwr);
+	if (ret < 0)
+		dev_err(priv->dev, "Failed to disable io pwr: %d\n",
+			ret);
+
+	dsa_unregister_switch(priv->ds);
+	mutex_destroy(&priv->reg_mutex);
+}
+
+static const struct of_device_id mt7530_of_match[] = {
+	{ .compatible = "mediatek,mt7530" },
+	{ /* sentinel */ },
+};
+
+static struct mdio_driver mt7530_mdio_driver = {
+	.probe  = mt7530_probe,
+	.remove = mt7530_remove,
+	.mdiodrv.driver = {
+		.name = "mt7530",
+		.of_match_table = mt7530_of_match,
+	},
+};
+
+mdio_module_driver(mt7530_mdio_driver);
+
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("Driver for Mediatek MT7530 Switch");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mediatek-mt7530");
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
new file mode 100644
index 000000000000..b83d76b99802
--- /dev/null
+++ b/drivers/net/dsa/mt7530.h
@@ -0,0 +1,402 @@
+/*
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT7530_H
+#define __MT7530_H
+
+#define MT7530_NUM_PORTS		7
+#define MT7530_CPU_PORT			6
+#define MT7530_NUM_FDB_RECORDS		2048
+
+#define	NUM_TRGMII_CTRL			5
+
+#define TRGMII_BASE(x)			(0x10000 + (x))
+
+/* Registers to ethsys access */
+#define ETHSYS_CLKCFG0			0x2c
+#define  ETHSYS_TRGMII_CLK_SEL362_5	BIT(11)
+
+#define SYSC_REG_RSTCTRL		0x34
+#define  RESET_MCM			BIT(2)
+
+/* Registers to mac forward control for unknown frames */
+#define MT7530_MFC			0x10
+#define  BC_FFP(x)			(((x) & 0xff) << 24)
+#define  UNM_FFP(x)			(((x) & 0xff) << 16)
+#define  UNU_FFP(x)			(((x) & 0xff) << 8)
+#define  UNU_FFP_MASK			UNU_FFP(~0)
+
+/* Registers for address table access */
+#define MT7530_ATA1			0x74
+#define  STATIC_EMP			0
+#define  STATIC_ENT			3
+#define MT7530_ATA2			0x78
+
+/* Register for address table write data */
+#define MT7530_ATWD			0x7c
+
+/* Register for address table control */
+#define MT7530_ATC			0x80
+#define  ATC_HASH			(((x) & 0xfff) << 16)
+#define  ATC_BUSY			BIT(15)
+#define  ATC_SRCH_END			BIT(14)
+#define  ATC_SRCH_HIT			BIT(13)
+#define  ATC_INVALID			BIT(12)
+#define  ATC_MAT(x)			(((x) & 0xf) << 8)
+#define  ATC_MAT_MACTAB			ATC_MAT(0)
+
+enum mt7530_fdb_cmd {
+	MT7530_FDB_READ	= 0,
+	MT7530_FDB_WRITE = 1,
+	MT7530_FDB_FLUSH = 2,
+	MT7530_FDB_START = 4,
+	MT7530_FDB_NEXT = 5,
+};
+
+/* Registers for table search read address */
+#define MT7530_TSRA1			0x84
+#define  MAC_BYTE_0			24
+#define  MAC_BYTE_1			16
+#define  MAC_BYTE_2			8
+#define  MAC_BYTE_3			0
+#define  MAC_BYTE_MASK			0xff
+
+#define MT7530_TSRA2			0x88
+#define  MAC_BYTE_4			24
+#define  MAC_BYTE_5			16
+#define  CVID				0
+#define  CVID_MASK			0xfff
+
+#define MT7530_ATRD			0x8C
+#define	 AGE_TIMER			24
+#define  AGE_TIMER_MASK			0xff
+#define  PORT_MAP			4
+#define  PORT_MAP_MASK			0xff
+#define  ENT_STATUS			2
+#define  ENT_STATUS_MASK		0x3
+
+/* Register for vlan table control */
+#define MT7530_VTCR			0x90
+#define  VTCR_BUSY			BIT(31)
+#define  VTCR_FUNC			(((x) & 0xf) << 12)
+#define  VTCR_FUNC_RD_VID		0x1
+#define  VTCR_FUNC_WR_VID		0x2
+#define  VTCR_FUNC_INV_VID		0x3
+#define  VTCR_FUNC_VAL_VID		0x4
+#define  VTCR_VID			((x) & 0xfff)
+
+/* Register for setup vlan and acl write data */
+#define MT7530_VAWD1			0x94
+#define  PORT_STAG			BIT(31)
+#define  IVL_MAC			BIT(30)
+#define  PORT_MEM(x)			(((x) & 0xff) << 16)
+#define  VALID				BIT(1)
+
+#define MT7530_VAWD2			0x98
+
+/* Register for port STP state control */
+#define MT7530_SSP_P(x)			(0x2000 + ((x) * 0x100))
+#define  FID_PST(x)			((x) & 0x3)
+#define  FID_PST_MASK			FID_PST(0x3)
+
+enum mt7530_stp_state {
+	MT7530_STP_DISABLED = 0,
+	MT7530_STP_BLOCKING = 1,
+	MT7530_STP_LISTENING = 1,
+	MT7530_STP_LEARNING = 2,
+	MT7530_STP_FORWARDING  = 3
+};
+
+/* Register for port control */
+#define MT7530_PCR_P(x)			(0x2004 + ((x) * 0x100))
+#define  PORT_VLAN(x)			((x) & 0x3)
+#define  PCR_MATRIX(x)			(((x) & 0xff) << 16)
+#define  PORT_PRI(x)			(((x) & 0x7) << 24)
+#define  EG_TAG(x)			(((x) & 0x3) << 28)
+#define  PCR_MATRIX_MASK		PCR_MATRIX(0xff)
+#define  PCR_MATRIX_CLR			PCR_MATRIX(0)
+
+/* Register for port security control */
+#define MT7530_PSC_P(x)			(0x200c + ((x) * 0x100))
+#define  SA_DIS				BIT(4)
+
+/* Register for port vlan control */
+#define MT7530_PVC_P(x)			(0x2010 + ((x) * 0x100))
+#define  PORT_SPEC_TAG			BIT(5)
+#define  VLAN_ATTR(x)			(((x) & 0x3) << 6)
+#define  STAG_VPID			(((x) & 0xffff) << 16)
+
+/* Register for port port-and-protocol based vlan 1 control */
+#define MT7530_PPBV1_P(x)		(0x2014 + ((x) * 0x100))
+
+/* Register for port MAC control register */
+#define MT7530_PMCR_P(x)		(0x3000 + ((x) * 0x100))
+#define  PMCR_IFG_XMIT(x)		(((x) & 0x3) << 18)
+#define  PMCR_MAC_MODE			BIT(16)
+#define  PMCR_FORCE_MODE		BIT(15)
+#define  PMCR_TX_EN			BIT(14)
+#define  PMCR_RX_EN			BIT(13)
+#define  PMCR_BACKOFF_EN		BIT(9)
+#define  PMCR_BACKPR_EN			BIT(8)
+#define  PMCR_TX_FC_EN			BIT(5)
+#define  PMCR_RX_FC_EN			BIT(4)
+#define  PMCR_FORCE_SPEED_1000		BIT(3)
+#define  PMCR_FORCE_FDX			BIT(1)
+#define  PMCR_FORCE_LNK			BIT(0)
+#define  PMCR_COMMON_LINK		(PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \
+					 PMCR_BACKOFF_EN | PMCR_BACKPR_EN | \
+					 PMCR_TX_EN | PMCR_RX_EN | \
+					 PMCR_TX_FC_EN | PMCR_RX_FC_EN)
+#define  PMCR_CPUP_LINK			(PMCR_COMMON_LINK | PMCR_FORCE_MODE | \
+					 PMCR_FORCE_SPEED_1000 | \
+					 PMCR_FORCE_FDX | \
+					 PMCR_FORCE_LNK)
+#define  PMCR_USERP_LINK		PMCR_COMMON_LINK
+#define  PMCR_FIXED_LINK		(PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \
+					 PMCR_FORCE_MODE | PMCR_TX_EN | \
+					 PMCR_RX_EN | PMCR_BACKPR_EN | \
+					 PMCR_BACKOFF_EN | \
+					 PMCR_FORCE_SPEED_1000 | \
+					 PMCR_FORCE_FDX | \
+					 PMCR_FORCE_LNK)
+#define PMCR_FIXED_LINK_FC		(PMCR_FIXED_LINK | \
+					 PMCR_TX_FC_EN | PMCR_RX_FC_EN)
+
+#define MT7530_PMSR_P(x)		(0x3008 + (x) * 0x100)
+
+/* Register for MIB */
+#define MT7530_PORT_MIB_COUNTER(x)	(0x4000 + (x) * 0x100)
+#define MT7530_MIB_CCR			0x4fe0
+#define  CCR_MIB_ENABLE			BIT(31)
+#define  CCR_RX_OCT_CNT_GOOD		BIT(7)
+#define  CCR_RX_OCT_CNT_BAD		BIT(6)
+#define  CCR_TX_OCT_CNT_GOOD		BIT(5)
+#define  CCR_TX_OCT_CNT_BAD		BIT(4)
+#define  CCR_MIB_FLUSH			(CCR_RX_OCT_CNT_GOOD | \
+					 CCR_RX_OCT_CNT_BAD | \
+					 CCR_TX_OCT_CNT_GOOD | \
+					 CCR_TX_OCT_CNT_BAD)
+#define  CCR_MIB_ACTIVATE		(CCR_MIB_ENABLE | \
+					 CCR_RX_OCT_CNT_GOOD | \
+					 CCR_RX_OCT_CNT_BAD | \
+					 CCR_TX_OCT_CNT_GOOD | \
+					 CCR_TX_OCT_CNT_BAD)
+/* Register for system reset */
+#define MT7530_SYS_CTRL			0x7000
+#define  SYS_CTRL_PHY_RST		BIT(2)
+#define  SYS_CTRL_SW_RST		BIT(1)
+#define  SYS_CTRL_REG_RST		BIT(0)
+
+/* Register for hw trap status */
+#define MT7530_HWTRAP			0x7800
+
+/* Register for hw trap modification */
+#define MT7530_MHWTRAP			0x7804
+#define  MHWTRAP_MANUAL			BIT(16)
+#define  MHWTRAP_P5_MAC_SEL		BIT(13)
+#define  MHWTRAP_P6_DIS			BIT(8)
+#define  MHWTRAP_P5_RGMII_MODE		BIT(7)
+#define  MHWTRAP_P5_DIS			BIT(6)
+#define  MHWTRAP_PHY_ACCESS		BIT(5)
+
+/* Register for TOP signal control */
+#define MT7530_TOP_SIG_CTRL		0x7808
+#define  TOP_SIG_CTRL_NORMAL		(BIT(17) | BIT(16))
+
+#define MT7530_IO_DRV_CR		0x7810
+#define  P5_IO_CLK_DRV(x)		((x) & 0x3)
+#define  P5_IO_DATA_DRV(x)		(((x) & 0x3) << 4)
+
+#define MT7530_P6ECR			0x7830
+#define  P6_INTF_MODE_MASK		0x3
+#define  P6_INTF_MODE(x)		((x) & 0x3)
+
+/* Registers for TRGMII on the both side */
+#define MT7530_TRGMII_RCK_CTRL		0x7a00
+#define GSW_TRGMII_RCK_CTRL		0x300
+#define  RX_RST				BIT(31)
+#define  RXC_DQSISEL			BIT(30)
+#define  DQSI1_TAP_MASK			(0x7f << 8)
+#define  DQSI0_TAP_MASK			0x7f
+#define  DQSI1_TAP(x)			(((x) & 0x7f) << 8)
+#define  DQSI0_TAP(x)			((x) & 0x7f)
+
+#define MT7530_TRGMII_RCK_RTT		0x7a04
+#define GSW_TRGMII_RCK_RTT		0x304
+#define  DQS1_GATE			BIT(31)
+#define  DQS0_GATE			BIT(30)
+
+#define MT7530_TRGMII_RD(x)		(0x7a10 + (x) * 8)
+#define GSW_TRGMII_RD(x)		(0x310 + (x) * 8)
+#define  BSLIP_EN			BIT(31)
+#define  EDGE_CHK			BIT(30)
+#define  RD_TAP_MASK			0x7f
+#define  RD_TAP(x)			((x) & 0x7f)
+
+#define GSW_TRGMII_TXCTRL		0x340
+#define MT7530_TRGMII_TXCTRL		0x7a40
+#define  TRAIN_TXEN			BIT(31)
+#define  TXC_INV			BIT(30)
+#define  TX_RST				BIT(28)
+
+#define MT7530_TRGMII_TD_ODT(i)		(0x7a54 + 8 * (i))
+#define GSW_TRGMII_TD_ODT(i)		(0x354 + 8 * (i))
+#define  TD_DM_DRVP(x)			((x) & 0xf)
+#define  TD_DM_DRVN(x)			(((x) & 0xf) << 4)
+
+#define GSW_INTF_MODE			0x390
+#define  INTF_MODE_TRGMII		BIT(1)
+
+#define MT7530_TRGMII_TCK_CTRL		0x7a78
+#define  TCK_TAP(x)			(((x) & 0xf) << 8)
+
+#define MT7530_P5RGMIIRXCR		0x7b00
+#define  CSR_RGMII_EDGE_ALIGN		BIT(8)
+#define  CSR_RGMII_RXC_0DEG_CFG(x)	((x) & 0xf)
+
+#define MT7530_P5RGMIITXCR		0x7b04
+#define  CSR_RGMII_TXC_CFG(x)		((x) & 0x1f)
+
+#define MT7530_CREV			0x7ffc
+#define  CHIP_NAME_SHIFT		16
+#define  MT7530_ID			0x7530
+
+/* Registers for core PLL access through mmd indirect */
+#define CORE_PLL_GROUP2			0x401
+#define  RG_SYSPLL_EN_NORMAL		BIT(15)
+#define  RG_SYSPLL_VODEN		BIT(14)
+#define  RG_SYSPLL_LF			BIT(13)
+#define  RG_SYSPLL_RST_DLY(x)		(((x) & 0x3) << 12)
+#define  RG_SYSPLL_LVROD_EN		BIT(10)
+#define  RG_SYSPLL_PREDIV(x)		(((x) & 0x3) << 8)
+#define  RG_SYSPLL_POSDIV(x)		(((x) & 0x3) << 5)
+#define  RG_SYSPLL_FBKSEL		BIT(4)
+#define  RT_SYSPLL_EN_AFE_OLT		BIT(0)
+
+#define CORE_PLL_GROUP4			0x403
+#define  RG_SYSPLL_DDSFBK_EN		BIT(12)
+#define  RG_SYSPLL_BIAS_EN		BIT(11)
+#define  RG_SYSPLL_BIAS_LPF_EN		BIT(10)
+
+#define CORE_PLL_GROUP5			0x404
+#define  RG_LCDDS_PCW_NCPO1(x)		((x) & 0xffff)
+
+#define CORE_PLL_GROUP6			0x405
+#define  RG_LCDDS_PCW_NCPO0(x)		((x) & 0xffff)
+
+#define CORE_PLL_GROUP7			0x406
+#define  RG_LCDDS_PWDB			BIT(15)
+#define  RG_LCDDS_ISO_EN		BIT(13)
+#define  RG_LCCDS_C(x)			(((x) & 0x7) << 4)
+#define  RG_LCDDS_PCW_NCPO_CHG		BIT(3)
+
+#define CORE_PLL_GROUP10		0x409
+#define  RG_LCDDS_SSC_DELTA(x)		((x) & 0xfff)
+
+#define CORE_PLL_GROUP11		0x40a
+#define  RG_LCDDS_SSC_DELTA1(x)		((x) & 0xfff)
+
+#define CORE_GSWPLL_GRP1		0x40d
+#define  RG_GSWPLL_PREDIV(x)		(((x) & 0x3) << 14)
+#define  RG_GSWPLL_POSDIV_200M(x)	(((x) & 0x3) << 12)
+#define  RG_GSWPLL_EN_PRE		BIT(11)
+#define  RG_GSWPLL_FBKSEL		BIT(10)
+#define  RG_GSWPLL_BP			BIT(9)
+#define  RG_GSWPLL_BR			BIT(8)
+#define  RG_GSWPLL_FBKDIV_200M(x)	((x) & 0xff)
+
+#define CORE_GSWPLL_GRP2		0x40e
+#define  RG_GSWPLL_POSDIV_500M(x)	(((x) & 0x3) << 8)
+#define  RG_GSWPLL_FBKDIV_500M(x)	((x) & 0xff)
+
+#define CORE_TRGMII_GSW_CLK_CG		0x410
+#define  REG_GSWCK_EN			BIT(0)
+#define  REG_TRGMIICK_EN		BIT(1)
+
+#define MIB_DESC(_s, _o, _n)	\
+	{			\
+		.size = (_s),	\
+		.offset = (_o),	\
+		.name = (_n),	\
+	}
+
+struct mt7530_mib_desc {
+	unsigned int size;
+	unsigned int offset;
+	const char *name;
+};
+
+struct mt7530_fdb {
+	u16 vid;
+	u8 port_mask;
+	u8 aging;
+	u8 mac[6];
+	bool noarp;
+};
+
+struct mt7530_port {
+	bool enable;
+	u32 pm;
+};
+
+/* struct mt7530_priv -	This is the main data structure for holding the state
+ *			of the driver
+ * @dev:		The device pointer
+ * @ds:			The pointer to the dsa core structure
+ * @bus:		The bus used for the device and built-in PHY
+ * @rstc:		The pointer to reset control used by MCM
+ * @ethernet:		The regmap used for access TRGMII-based registers
+ * @core_pwr:		The power supplied into the core
+ * @io_pwr:		The power supplied into the I/O
+ * @reset:		The descriptor for GPIO line tied to its reset pin
+ * @mcm:		Flag for distinguishing if standalone IC or module
+ *			coupling
+ * @ports:		Holding the state among ports
+ * @reg_mutex:		The lock for protecting among process accessing
+ *			registers
+ */
+struct mt7530_priv {
+	struct device		*dev;
+	struct dsa_switch	*ds;
+	struct mii_bus		*bus;
+	struct reset_control	*rstc;
+	struct regmap		*ethernet;
+	struct regulator	*core_pwr;
+	struct regulator	*io_pwr;
+	struct gpio_desc	*reset;
+	bool			mcm;
+
+	struct mt7530_port	ports[MT7530_NUM_PORTS];
+	/* protect among processes for registers access*/
+	struct mutex reg_mutex;
+};
+
+struct mt7530_hw_stats {
+	const char	*string;
+	u16		reg;
+	u8		sizeof_stat;
+};
+
+struct mt7530_dummy_poll {
+	struct mt7530_priv *priv;
+	u32 reg;
+};
+
+static inline void INIT_MT7530_DUMMY_POLL(struct mt7530_dummy_poll *p,
+					  struct mt7530_priv *priv, u32 reg)
+{
+	p->priv = priv;
+	p->reg = reg;
+}
+
+#endif /* __MT7530_H */
diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index c36be318de1a..6edd869c8d6f 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -1,5 +1,7 @@
 obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
 mv88e6xxx-objs := chip.o
 mv88e6xxx-objs += global1.o
+mv88e6xxx-objs += global1_atu.o
+mv88e6xxx-objs += global1_vtu.o
 mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o
 mv88e6xxx-objs += port.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 03dc886ed3d6..19581d783d8e 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3,11 +3,11 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2015 CMC Electronics, Inc.
- *	Added support for VLAN Table Unit operations
- *
  * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch>
  *
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -677,36 +677,6 @@ static int mv88e6xxx_phy_ppu_write(struct mv88e6xxx_chip *chip,
 	return err;
 }
 
-static bool mv88e6xxx_6097_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6097;
-}
-
-static bool mv88e6xxx_6165_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6165;
-}
-
-static bool mv88e6xxx_6320_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6320;
-}
-
-static bool mv88e6xxx_6341_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6341;
-}
-
-static bool mv88e6xxx_6351_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6351;
-}
-
-static bool mv88e6xxx_6352_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6352;
-}
-
 static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
 				    int link, int speed, int duplex,
 				    phy_interface_t mode)
@@ -1066,11 +1036,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
 	mutex_unlock(&chip->reg_lock);
 }
 
-static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip)
-{
-	return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY);
-}
-
 static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port,
 			     struct ethtool_eee *e)
 {
@@ -1130,143 +1095,42 @@ out:
 	return err;
 }
 
-static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_chip *chip, u16 fid, u16 cmd)
-{
-	u16 val;
-	int err;
-
-	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_ATU_FID)) {
-		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid);
-		if (err)
-			return err;
-	} else if (mv88e6xxx_num_databases(chip) == 256) {
-		/* ATU DBNum[7:4] are located in ATU Control 15:12 */
-		err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
-		if (err)
-			return err;
-
-		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL,
-					 (val & 0xfff) | ((fid << 8) & 0xf000));
-		if (err)
-			return err;
-
-		/* ATU DBNum[3:0] are located in ATU Operation 3:0 */
-		cmd |= fid & 0xf;
-	}
-
-	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, cmd);
-	if (err)
-		return err;
-
-	return _mv88e6xxx_atu_wait(chip);
-}
-
-static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_chip *chip,
-				     struct mv88e6xxx_atu_entry *entry)
-{
-	u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK;
-
-	if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
-		unsigned int mask, shift;
-
-		if (entry->trunk) {
-			data |= GLOBAL_ATU_DATA_TRUNK;
-			mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK;
-			shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT;
-		} else {
-			mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK;
-			shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT;
-		}
-
-		data |= (entry->portv_trunkid << shift) & mask;
-	}
-
-	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data);
-}
-
-static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip,
-				     struct mv88e6xxx_atu_entry *entry,
-				     bool static_too)
-{
-	int op;
-	int err;
-
-	err = _mv88e6xxx_atu_wait(chip);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_atu_data_write(chip, entry);
-	if (err)
-		return err;
-
-	if (entry->fid) {
-		op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB :
-			GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB;
-	} else {
-		op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL :
-			GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
-	}
-
-	return _mv88e6xxx_atu_cmd(chip, entry->fid, op);
-}
-
-static int _mv88e6xxx_atu_flush(struct mv88e6xxx_chip *chip,
-				u16 fid, bool static_too)
+static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
 {
-	struct mv88e6xxx_atu_entry entry = {
-		.fid = fid,
-		.state = 0, /* EntryState bits must be 0 */
-	};
+	struct dsa_switch *ds = NULL;
+	struct net_device *br;
+	u16 pvlan;
+	int i;
 
-	return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
-}
+	if (dev < DSA_MAX_SWITCHES)
+		ds = chip->ds->dst->ds[dev];
 
-static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
-			       int from_port, int to_port, bool static_too)
-{
-	struct mv88e6xxx_atu_entry entry = {
-		.trunk = false,
-		.fid = fid,
-	};
+	/* Prevent frames from unknown switch or port */
+	if (!ds || port >= ds->num_ports)
+		return 0;
 
-	/* EntryState bits must be 0xF */
-	entry.state = GLOBAL_ATU_DATA_STATE_MASK;
+	/* Frames from DSA links and CPU ports can egress any local port */
+	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+		return mv88e6xxx_port_mask(chip);
 
-	/* ToPort and FromPort are respectively in PortVec bits 7:4 and 3:0 */
-	entry.portv_trunkid = (to_port & 0x0f) << 4;
-	entry.portv_trunkid |= from_port & 0x0f;
+	br = ds->ports[port].bridge_dev;
+	pvlan = 0;
 
-	return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
-}
+	/* Frames from user ports can egress any local DSA links and CPU ports,
+	 * as well as any local member of their bridge group.
+	 */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
+		if (dsa_is_cpu_port(chip->ds, i) ||
+		    dsa_is_dsa_port(chip->ds, i) ||
+		    (br && chip->ds->ports[i].bridge_dev == br))
+			pvlan |= BIT(i);
 
-static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid,
-				 int port, bool static_too)
-{
-	/* Destination port 0xF means remove the entries */
-	return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too);
+	return pvlan;
 }
 
-static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_port_vlan_map(struct mv88e6xxx_chip *chip, int port)
 {
-	struct dsa_switch *ds = chip->ds;
-	struct net_device *bridge = ds->ports[port].bridge_dev;
-	u16 output_ports = 0;
-	int i;
-
-	/* allow CPU port or DSA link(s) to send frames to every port */
-	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
-		output_ports = ~0;
-	} else {
-		for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
-			/* allow sending frames to every group member */
-			if (bridge && ds->ports[i].bridge_dev == bridge)
-				output_ports |= BIT(i);
-
-			/* allow sending frames to CPU port and DSA link(s) */
-			if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
-				output_ports |= BIT(i);
-		}
-	}
+	u16 output_ports = mv88e6xxx_port_vlan(chip, chip->ds->index, port);
 
 	/* prevent frames from going back out of the port they came in on */
 	output_ports &= ~BIT(port);
@@ -1306,182 +1170,98 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
 		netdev_err(ds->ports[port].netdev, "failed to update state\n");
 }
 
-static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port)
+static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip)
 {
-	struct mv88e6xxx_chip *chip = ds->priv;
 	int err;
 
-	mutex_lock(&chip->reg_lock);
-	err = _mv88e6xxx_atu_remove(chip, 0, port, false);
-	mutex_unlock(&chip->reg_lock);
-
+	err = mv88e6xxx_g1_atu_flush(chip, 0, true);
 	if (err)
-		netdev_err(ds->ports[port].netdev, "failed to flush ATU\n");
-}
-
-static int _mv88e6xxx_vtu_wait(struct mv88e6xxx_chip *chip)
-{
-	return mv88e6xxx_g1_wait(chip, GLOBAL_VTU_OP, GLOBAL_VTU_OP_BUSY);
-}
-
-static int _mv88e6xxx_vtu_cmd(struct mv88e6xxx_chip *chip, u16 op)
-{
-	int err;
+		return err;
 
-	err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_OP, op);
+	err = mv88e6xxx_g1_atu_set_learn2all(chip, true);
 	if (err)
 		return err;
 
-	return _mv88e6xxx_vtu_wait(chip);
+	return mv88e6xxx_g1_atu_set_age_time(chip, 300000);
 }
 
-static int _mv88e6xxx_vtu_stu_flush(struct mv88e6xxx_chip *chip)
+static int mv88e6xxx_pvt_map(struct mv88e6xxx_chip *chip, int dev, int port)
 {
-	int ret;
+	u16 pvlan = 0;
 
-	ret = _mv88e6xxx_vtu_wait(chip);
-	if (ret < 0)
-		return ret;
+	if (!mv88e6xxx_has_pvt(chip))
+		return -EOPNOTSUPP;
+
+	/* Skip the local source device, which uses in-chip port VLAN */
+	if (dev != chip->ds->index)
+		pvlan = mv88e6xxx_port_vlan(chip, dev, port);
 
-	return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_FLUSH_ALL);
+	return mv88e6xxx_g2_pvt_write(chip, dev, port, pvlan);
 }
 
-static int _mv88e6xxx_vtu_stu_data_read(struct mv88e6xxx_chip *chip,
-					struct mv88e6xxx_vtu_entry *entry,
-					unsigned int nibble_offset)
+static int mv88e6xxx_pvt_setup(struct mv88e6xxx_chip *chip)
 {
-	u16 regs[3];
-	int i, err;
-
-	for (i = 0; i < 3; ++i) {
-		u16 *reg = &regs[i];
+	int dev, port;
+	int err;
 
-		err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_DATA_0_3 + i, reg);
-		if (err)
-			return err;
-	}
+	if (!mv88e6xxx_has_pvt(chip))
+		return 0;
 
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
-		unsigned int shift = (i % 4) * 4 + nibble_offset;
-		u16 reg = regs[i / 4];
+	/* Clear 5 Bit Port for usage with Marvell Link Street devices:
+	 * use 4 bits for the Src_Port/Src_Trunk and 5 bits for the Src_Dev.
+	 */
+	err = mv88e6xxx_g2_misc_4_bit_port(chip);
+	if (err)
+		return err;
 
-		entry->data[i] = (reg >> shift) & GLOBAL_VTU_STU_DATA_MASK;
+	for (dev = 0; dev < MV88E6XXX_MAX_PVT_SWITCHES; ++dev) {
+		for (port = 0; port < MV88E6XXX_MAX_PVT_PORTS; ++port) {
+			err = mv88e6xxx_pvt_map(chip, dev, port);
+			if (err)
+				return err;
+		}
 	}
 
 	return 0;
 }
 
-static int mv88e6xxx_vtu_data_read(struct mv88e6xxx_chip *chip,
-				   struct mv88e6xxx_vtu_entry *entry)
-{
-	return _mv88e6xxx_vtu_stu_data_read(chip, entry, 0);
-}
-
-static int mv88e6xxx_stu_data_read(struct mv88e6xxx_chip *chip,
-				   struct mv88e6xxx_vtu_entry *entry)
-{
-	return _mv88e6xxx_vtu_stu_data_read(chip, entry, 2);
-}
-
-static int _mv88e6xxx_vtu_stu_data_write(struct mv88e6xxx_chip *chip,
-					 struct mv88e6xxx_vtu_entry *entry,
-					 unsigned int nibble_offset)
+static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port)
 {
-	u16 regs[3] = { 0 };
-	int i, err;
-
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
-		unsigned int shift = (i % 4) * 4 + nibble_offset;
-		u8 data = entry->data[i];
-
-		regs[i / 4] |= (data & GLOBAL_VTU_STU_DATA_MASK) << shift;
-	}
-
-	for (i = 0; i < 3; ++i) {
-		u16 reg = regs[i];
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
 
-		err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_DATA_0_3 + i, reg);
-		if (err)
-			return err;
-	}
+	mutex_lock(&chip->reg_lock);
+	err = mv88e6xxx_g1_atu_remove(chip, 0, port, false);
+	mutex_unlock(&chip->reg_lock);
 
-	return 0;
+	if (err)
+		netdev_err(ds->ports[port].netdev, "failed to flush ATU\n");
 }
 
-static int mv88e6xxx_vtu_data_write(struct mv88e6xxx_chip *chip,
-				    struct mv88e6xxx_vtu_entry *entry)
+static int mv88e6xxx_vtu_setup(struct mv88e6xxx_chip *chip)
 {
-	return _mv88e6xxx_vtu_stu_data_write(chip, entry, 0);
-}
+	if (!chip->info->max_vid)
+		return 0;
 
-static int mv88e6xxx_stu_data_write(struct mv88e6xxx_chip *chip,
-				    struct mv88e6xxx_vtu_entry *entry)
-{
-	return _mv88e6xxx_vtu_stu_data_write(chip, entry, 2);
+	return mv88e6xxx_g1_vtu_flush(chip);
 }
 
-static int _mv88e6xxx_vtu_vid_write(struct mv88e6xxx_chip *chip, u16 vid)
+static int mv88e6xxx_vtu_getnext(struct mv88e6xxx_chip *chip,
+				 struct mv88e6xxx_vtu_entry *entry)
 {
-	return mv88e6xxx_g1_write(chip, GLOBAL_VTU_VID,
-				  vid & GLOBAL_VTU_VID_MASK);
+	if (!chip->info->ops->vtu_getnext)
+		return -EOPNOTSUPP;
+
+	return chip->info->ops->vtu_getnext(chip, entry);
 }
 
-static int _mv88e6xxx_vtu_getnext(struct mv88e6xxx_chip *chip,
-				  struct mv88e6xxx_vtu_entry *entry)
+static int mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+				   struct mv88e6xxx_vtu_entry *entry)
 {
-	struct mv88e6xxx_vtu_entry next = { 0 };
-	u16 val;
-	int err;
-
-	err = _mv88e6xxx_vtu_wait(chip);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_VTU_GET_NEXT);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_VID, &val);
-	if (err)
-		return err;
-
-	next.vid = val & GLOBAL_VTU_VID_MASK;
-	next.valid = !!(val & GLOBAL_VTU_VID_VALID);
-
-	if (next.valid) {
-		err = mv88e6xxx_vtu_data_read(chip, &next);
-		if (err)
-			return err;
-
-		if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_VTU_FID)) {
-			err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_FID, &val);
-			if (err)
-				return err;
-
-			next.fid = val & GLOBAL_VTU_FID_MASK;
-		} else if (mv88e6xxx_num_databases(chip) == 256) {
-			/* VTU DBNum[7:4] are located in VTU Operation 11:8, and
-			 * VTU DBNum[3:0] are located in VTU Operation 3:0
-			 */
-			err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_OP, &val);
-			if (err)
-				return err;
-
-			next.fid = (val & 0xf00) >> 4;
-			next.fid |= val & 0xf;
-		}
-
-		if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_STU)) {
-			err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_SID, &val);
-			if (err)
-				return err;
-
-			next.sid = val & GLOBAL_VTU_SID_MASK;
-		}
-	}
+	if (!chip->info->ops->vtu_loadpurge)
+		return -EOPNOTSUPP;
 
-	*entry = next;
-	return 0;
+	return chip->info->ops->vtu_loadpurge(chip, entry);
 }
 
 static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
@@ -1489,11 +1269,13 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 				    int (*cb)(struct switchdev_obj *obj))
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	struct mv88e6xxx_vtu_entry next;
+	struct mv88e6xxx_vtu_entry next = {
+		.vid = chip->info->max_vid,
+	};
 	u16 pvid;
 	int err;
 
-	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
+	if (!chip->info->max_vid)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&chip->reg_lock);
@@ -1502,19 +1284,15 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 	if (err)
 		goto unlock;
 
-	err = _mv88e6xxx_vtu_vid_write(chip, GLOBAL_VTU_VID_MASK);
-	if (err)
-		goto unlock;
-
 	do {
-		err = _mv88e6xxx_vtu_getnext(chip, &next);
+		err = mv88e6xxx_vtu_getnext(chip, &next);
 		if (err)
 			break;
 
 		if (!next.valid)
 			break;
 
-		if (next.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
+		if (next.member[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
 			continue;
 
 		/* reinit and dump this VLAN obj */
@@ -1522,7 +1300,7 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 		vlan->vid_end = next.vid;
 		vlan->flags = 0;
 
-		if (next.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_UNTAGGED)
+		if (next.member[port] == GLOBAL_VTU_DATA_MEMBER_TAG_UNTAGGED)
 			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
 
 		if (next.vid == pvid)
@@ -1531,7 +1309,7 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 		err = cb(&vlan->obj);
 		if (err)
 			break;
-	} while (next.vid < GLOBAL_VTU_VID_MASK);
+	} while (next.vid < chip->info->max_vid);
 
 unlock:
 	mutex_unlock(&chip->reg_lock);
@@ -1539,133 +1317,12 @@ unlock:
 	return err;
 }
 
-static int _mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_chip *chip,
-				    struct mv88e6xxx_vtu_entry *entry)
-{
-	u16 op = GLOBAL_VTU_OP_VTU_LOAD_PURGE;
-	u16 reg = 0;
-	int err;
-
-	err = _mv88e6xxx_vtu_wait(chip);
-	if (err)
-		return err;
-
-	if (!entry->valid)
-		goto loadpurge;
-
-	/* Write port member tags */
-	err = mv88e6xxx_vtu_data_write(chip, entry);
-	if (err)
-		return err;
-
-	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_STU)) {
-		reg = entry->sid & GLOBAL_VTU_SID_MASK;
-		err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_SID, reg);
-		if (err)
-			return err;
-	}
-
-	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_VTU_FID)) {
-		reg = entry->fid & GLOBAL_VTU_FID_MASK;
-		err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_FID, reg);
-		if (err)
-			return err;
-	} else if (mv88e6xxx_num_databases(chip) == 256) {
-		/* VTU DBNum[7:4] are located in VTU Operation 11:8, and
-		 * VTU DBNum[3:0] are located in VTU Operation 3:0
-		 */
-		op |= (entry->fid & 0xf0) << 8;
-		op |= entry->fid & 0xf;
-	}
-
-	reg = GLOBAL_VTU_VID_VALID;
-loadpurge:
-	reg |= entry->vid & GLOBAL_VTU_VID_MASK;
-	err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_VID, reg);
-	if (err)
-		return err;
-
-	return _mv88e6xxx_vtu_cmd(chip, op);
-}
-
-static int _mv88e6xxx_stu_getnext(struct mv88e6xxx_chip *chip, u8 sid,
-				  struct mv88e6xxx_vtu_entry *entry)
-{
-	struct mv88e6xxx_vtu_entry next = { 0 };
-	u16 val;
-	int err;
-
-	err = _mv88e6xxx_vtu_wait(chip);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_SID,
-				 sid & GLOBAL_VTU_SID_MASK);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_GET_NEXT);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_SID, &val);
-	if (err)
-		return err;
-
-	next.sid = val & GLOBAL_VTU_SID_MASK;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_VID, &val);
-	if (err)
-		return err;
-
-	next.valid = !!(val & GLOBAL_VTU_VID_VALID);
-
-	if (next.valid) {
-		err = mv88e6xxx_stu_data_read(chip, &next);
-		if (err)
-			return err;
-	}
-
-	*entry = next;
-	return 0;
-}
-
-static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_chip *chip,
-				    struct mv88e6xxx_vtu_entry *entry)
-{
-	u16 reg = 0;
-	int err;
-
-	err = _mv88e6xxx_vtu_wait(chip);
-	if (err)
-		return err;
-
-	if (!entry->valid)
-		goto loadpurge;
-
-	/* Write port states */
-	err = mv88e6xxx_stu_data_write(chip, entry);
-	if (err)
-		return err;
-
-	reg = GLOBAL_VTU_VID_VALID;
-loadpurge:
-	err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_VID, reg);
-	if (err)
-		return err;
-
-	reg = entry->sid & GLOBAL_VTU_SID_MASK;
-	err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_SID, reg);
-	if (err)
-		return err;
-
-	return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
-}
-
-static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
+static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid)
 {
 	DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID);
-	struct mv88e6xxx_vtu_entry vlan;
+	struct mv88e6xxx_vtu_entry vlan = {
+		.vid = chip->info->max_vid,
+	};
 	int i, err;
 
 	bitmap_zero(fid_bitmap, MV88E6XXX_N_FID);
@@ -1680,12 +1337,8 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
 	}
 
 	/* Set every FID bit used by the VLAN entries */
-	err = _mv88e6xxx_vtu_vid_write(chip, GLOBAL_VTU_VID_MASK);
-	if (err)
-		return err;
-
 	do {
-		err = _mv88e6xxx_vtu_getnext(chip, &vlan);
+		err = mv88e6xxx_vtu_getnext(chip, &vlan);
 		if (err)
 			return err;
 
@@ -1693,7 +1346,7 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
 			break;
 
 		set_bit(vlan.fid, fid_bitmap);
-	} while (vlan.vid < GLOBAL_VTU_VID_MASK);
+	} while (vlan.vid < chip->info->max_vid);
 
 	/* The reset value 0x000 is used to indicate that multiple address
 	 * databases are not needed. Return the next positive available.
@@ -1703,92 +1356,55 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
 		return -ENOSPC;
 
 	/* Clear the database */
-	return _mv88e6xxx_atu_flush(chip, *fid, true);
+	return mv88e6xxx_g1_atu_flush(chip, *fid, true);
 }
 
-static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid,
-			      struct mv88e6xxx_vtu_entry *entry)
-{
-	struct dsa_switch *ds = chip->ds;
-	struct mv88e6xxx_vtu_entry vlan = {
-		.valid = true,
-		.vid = vid,
-	};
-	int i, err;
-
-	err = _mv88e6xxx_fid_new(chip, &vlan.fid);
-	if (err)
-		return err;
-
-	/* exclude all ports except the CPU and DSA ports */
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
-		vlan.data[i] = dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i)
-			? GLOBAL_VTU_DATA_MEMBER_TAG_UNMODIFIED
-			: GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER;
-
-	if (mv88e6xxx_6097_family(chip) || mv88e6xxx_6165_family(chip) ||
-	    mv88e6xxx_6351_family(chip) || mv88e6xxx_6352_family(chip) ||
-	    mv88e6xxx_6341_family(chip)) {
-		struct mv88e6xxx_vtu_entry vstp;
-
-		/* Adding a VTU entry requires a valid STU entry. As VSTP is not
-		 * implemented, only one STU entry is needed to cover all VTU
-		 * entries. Thus, validate the SID 0.
-		 */
-		vlan.sid = 0;
-		err = _mv88e6xxx_stu_getnext(chip, GLOBAL_VTU_SID_MASK, &vstp);
-		if (err)
-			return err;
-
-		if (vstp.sid != vlan.sid || !vstp.valid) {
-			memset(&vstp, 0, sizeof(vstp));
-			vstp.valid = true;
-			vstp.sid = vlan.sid;
-
-			err = _mv88e6xxx_stu_loadpurge(chip, &vstp);
-			if (err)
-				return err;
-		}
-	}
-
-	*entry = vlan;
-	return 0;
-}
-
-static int _mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
-			      struct mv88e6xxx_vtu_entry *entry, bool creat)
+static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
+			     struct mv88e6xxx_vtu_entry *entry, bool new)
 {
 	int err;
 
 	if (!vid)
 		return -EINVAL;
 
-	err = _mv88e6xxx_vtu_vid_write(chip, vid - 1);
-	if (err)
-		return err;
+	entry->vid = vid - 1;
+	entry->valid = false;
 
-	err = _mv88e6xxx_vtu_getnext(chip, entry);
+	err = mv88e6xxx_vtu_getnext(chip, entry);
 	if (err)
 		return err;
 
-	if (entry->vid != vid || !entry->valid) {
-		if (!creat)
-			return -EOPNOTSUPP;
-		/* -ENOENT would've been more appropriate, but switchdev expects
-		 * -EOPNOTSUPP to inform bridge about an eventual software VLAN.
-		 */
+	if (entry->vid == vid && entry->valid)
+		return 0;
 
-		err = _mv88e6xxx_vtu_new(chip, vid, entry);
+	if (new) {
+		int i;
+
+		/* Initialize a fresh VLAN entry */
+		memset(entry, 0, sizeof(*entry));
+		entry->valid = true;
+		entry->vid = vid;
+
+		/* Include only CPU and DSA ports */
+		for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
+			entry->member[i] = dsa_is_normal_port(chip->ds, i) ?
+				GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER :
+				GLOBAL_VTU_DATA_MEMBER_TAG_UNMODIFIED;
+
+		return mv88e6xxx_atu_new(chip, &entry->fid);
 	}
 
-	return err;
+	/* switchdev expects -EOPNOTSUPP to honor software VLANs */
+	return -EOPNOTSUPP;
 }
 
 static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 					u16 vid_begin, u16 vid_end)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	struct mv88e6xxx_vtu_entry vlan;
+	struct mv88e6xxx_vtu_entry vlan = {
+		.vid = vid_begin - 1,
+	};
 	int i, err;
 
 	if (!vid_begin)
@@ -1796,12 +1412,8 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 
 	mutex_lock(&chip->reg_lock);
 
-	err = _mv88e6xxx_vtu_vid_write(chip, vid_begin - 1);
-	if (err)
-		goto unlock;
-
 	do {
-		err = _mv88e6xxx_vtu_getnext(chip, &vlan);
+		err = mv88e6xxx_vtu_getnext(chip, &vlan);
 		if (err)
 			goto unlock;
 
@@ -1818,7 +1430,7 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 			if (!ds->ports[port].netdev)
 				continue;
 
-			if (vlan.data[i] ==
+			if (vlan.member[i] ==
 			    GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
 				continue;
 
@@ -1852,7 +1464,7 @@ static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port,
 		PORT_CONTROL_2_8021Q_DISABLED;
 	int err;
 
-	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
+	if (!chip->info->max_vid)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&chip->reg_lock);
@@ -1870,7 +1482,7 @@ mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
 	struct mv88e6xxx_chip *chip = ds->priv;
 	int err;
 
-	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
+	if (!chip->info->max_vid)
 		return -EOPNOTSUPP;
 
 	/* If the requested port doesn't belong to the same bridge as the VLAN
@@ -1893,15 +1505,15 @@ static int _mv88e6xxx_port_vlan_add(struct mv88e6xxx_chip *chip, int port,
 	struct mv88e6xxx_vtu_entry vlan;
 	int err;
 
-	err = _mv88e6xxx_vtu_get(chip, vid, &vlan, true);
+	err = mv88e6xxx_vtu_get(chip, vid, &vlan, true);
 	if (err)
 		return err;
 
-	vlan.data[port] = untagged ?
+	vlan.member[port] = untagged ?
 		GLOBAL_VTU_DATA_MEMBER_TAG_UNTAGGED :
 		GLOBAL_VTU_DATA_MEMBER_TAG_TAGGED;
 
-	return _mv88e6xxx_vtu_loadpurge(chip, &vlan);
+	return mv88e6xxx_vtu_loadpurge(chip, &vlan);
 }
 
 static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port,
@@ -1913,7 +1525,7 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port,
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	u16 vid;
 
-	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
+	if (!chip->info->max_vid)
 		return;
 
 	mutex_lock(&chip->reg_lock);
@@ -1938,15 +1550,15 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip,
 	struct mv88e6xxx_vtu_entry vlan;
 	int i, err;
 
-	err = _mv88e6xxx_vtu_get(chip, vid, &vlan, false);
+	err = mv88e6xxx_vtu_get(chip, vid, &vlan, false);
 	if (err)
 		return err;
 
 	/* Tell switchdev if this VLAN is handled in software */
-	if (vlan.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
+	if (vlan.member[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
 		return -EOPNOTSUPP;
 
-	vlan.data[port] = GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER;
+	vlan.member[port] = GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER;
 
 	/* keep the VLAN unless all ports are excluded */
 	vlan.valid = false;
@@ -1954,17 +1566,17 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip,
 		if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
 			continue;
 
-		if (vlan.data[i] != GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER) {
+		if (vlan.member[i] != GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER) {
 			vlan.valid = true;
 			break;
 		}
 	}
 
-	err = _mv88e6xxx_vtu_loadpurge(chip, &vlan);
+	err = mv88e6xxx_vtu_loadpurge(chip, &vlan);
 	if (err)
 		return err;
 
-	return _mv88e6xxx_atu_remove(chip, vlan.fid, port, false);
+	return mv88e6xxx_g1_atu_remove(chip, vlan.fid, port, false);
 }
 
 static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
@@ -1974,7 +1586,7 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
 	u16 pvid, vid;
 	int err = 0;
 
-	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
+	if (!chip->info->max_vid)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&chip->reg_lock);
@@ -2001,96 +1613,6 @@ unlock:
 	return err;
 }
 
-static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_chip *chip,
-				    const unsigned char *addr)
-{
-	int i, err;
-
-	for (i = 0; i < 3; i++) {
-		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i,
-					 (addr[i * 2] << 8) | addr[i * 2 + 1]);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip,
-				   unsigned char *addr)
-{
-	u16 val;
-	int i, err;
-
-	for (i = 0; i < 3; i++) {
-		err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val);
-		if (err)
-			return err;
-
-		addr[i * 2] = val >> 8;
-		addr[i * 2 + 1] = val & 0xff;
-	}
-
-	return 0;
-}
-
-static int _mv88e6xxx_atu_load(struct mv88e6xxx_chip *chip,
-			       struct mv88e6xxx_atu_entry *entry)
-{
-	int ret;
-
-	ret = _mv88e6xxx_atu_wait(chip);
-	if (ret < 0)
-		return ret;
-
-	ret = _mv88e6xxx_atu_mac_write(chip, entry->mac);
-	if (ret < 0)
-		return ret;
-
-	ret = _mv88e6xxx_atu_data_write(chip, entry);
-	if (ret < 0)
-		return ret;
-
-	return _mv88e6xxx_atu_cmd(chip, entry->fid, GLOBAL_ATU_OP_LOAD_DB);
-}
-
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
-				  struct mv88e6xxx_atu_entry *entry);
-
-static int mv88e6xxx_atu_get(struct mv88e6xxx_chip *chip, int fid,
-			     const u8 *addr, struct mv88e6xxx_atu_entry *entry)
-{
-	struct mv88e6xxx_atu_entry next;
-	int err;
-
-	memcpy(next.mac, addr, ETH_ALEN);
-	eth_addr_dec(next.mac);
-
-	err = _mv88e6xxx_atu_mac_write(chip, next.mac);
-	if (err)
-		return err;
-
-	do {
-		err = _mv88e6xxx_atu_getnext(chip, fid, &next);
-		if (err)
-			return err;
-
-		if (next.state == GLOBAL_ATU_DATA_STATE_UNUSED)
-			break;
-
-		if (ether_addr_equal(next.mac, addr)) {
-			*entry = next;
-			return 0;
-		}
-	} while (ether_addr_greater(addr, next.mac));
-
-	memset(entry, 0, sizeof(*entry));
-	entry->fid = fid;
-	ether_addr_copy(entry->mac, addr);
-
-	return 0;
-}
-
 static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 					const unsigned char *addr, u16 vid,
 					u8 state)
@@ -2103,25 +1625,36 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 	if (vid == 0)
 		err = mv88e6xxx_port_get_fid(chip, port, &vlan.fid);
 	else
-		err = _mv88e6xxx_vtu_get(chip, vid, &vlan, false);
+		err = mv88e6xxx_vtu_get(chip, vid, &vlan, false);
 	if (err)
 		return err;
 
-	err = mv88e6xxx_atu_get(chip, vlan.fid, addr, &entry);
+	entry.state = GLOBAL_ATU_DATA_STATE_UNUSED;
+	ether_addr_copy(entry.mac, addr);
+	eth_addr_dec(entry.mac);
+
+	err = mv88e6xxx_g1_atu_getnext(chip, vlan.fid, &entry);
 	if (err)
 		return err;
 
+	/* Initialize a fresh ATU entry if it isn't found */
+	if (entry.state == GLOBAL_ATU_DATA_STATE_UNUSED ||
+	    !ether_addr_equal(entry.mac, addr)) {
+		memset(&entry, 0, sizeof(entry));
+		ether_addr_copy(entry.mac, addr);
+	}
+
 	/* Purge the ATU entry only if no port is using it anymore */
 	if (state == GLOBAL_ATU_DATA_STATE_UNUSED) {
-		entry.portv_trunkid &= ~BIT(port);
-		if (!entry.portv_trunkid)
+		entry.portvec &= ~BIT(port);
+		if (!entry.portvec)
 			entry.state = GLOBAL_ATU_DATA_STATE_UNUSED;
 	} else {
-		entry.portv_trunkid |= BIT(port);
+		entry.portvec |= BIT(port);
 		entry.state = state;
 	}
 
-	return _mv88e6xxx_atu_load(chip, &entry);
+	return mv88e6xxx_g1_atu_loadpurge(chip, vlan.fid, &entry);
 }
 
 static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port,
@@ -2161,75 +1694,26 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
-				  struct mv88e6xxx_atu_entry *entry)
-{
-	struct mv88e6xxx_atu_entry next = { 0 };
-	u16 val;
-	int err;
-
-	next.fid = fid;
-
-	err = _mv88e6xxx_atu_wait(chip);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_atu_cmd(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_atu_mac_read(chip, next.mac);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val);
-	if (err)
-		return err;
-
-	next.state = val & GLOBAL_ATU_DATA_STATE_MASK;
-	if (next.state != GLOBAL_ATU_DATA_STATE_UNUSED) {
-		unsigned int mask, shift;
-
-		if (val & GLOBAL_ATU_DATA_TRUNK) {
-			next.trunk = true;
-			mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK;
-			shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT;
-		} else {
-			next.trunk = false;
-			mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK;
-			shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT;
-		}
-
-		next.portv_trunkid = (val & mask) >> shift;
-	}
-
-	*entry = next;
-	return 0;
-}
-
 static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip,
 				      u16 fid, u16 vid, int port,
 				      struct switchdev_obj *obj,
 				      int (*cb)(struct switchdev_obj *obj))
 {
-	struct mv88e6xxx_atu_entry addr = {
-		.mac = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
-	};
+	struct mv88e6xxx_atu_entry addr;
 	int err;
 
-	err = _mv88e6xxx_atu_mac_write(chip, addr.mac);
-	if (err)
-		return err;
+	addr.state = GLOBAL_ATU_DATA_STATE_UNUSED;
+	eth_broadcast_addr(addr.mac);
 
 	do {
-		err = _mv88e6xxx_atu_getnext(chip, fid, &addr);
+		err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr);
 		if (err)
 			return err;
 
 		if (addr.state == GLOBAL_ATU_DATA_STATE_UNUSED)
 			break;
 
-		if (addr.trunk || (addr.portv_trunkid & BIT(port)) == 0)
+		if (addr.trunk || (addr.portvec & BIT(port)) == 0)
 			continue;
 
 		if (obj->id == SWITCHDEV_OBJ_ID_PORT_FDB) {
@@ -2271,7 +1755,7 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port,
 				  int (*cb)(struct switchdev_obj *obj))
 {
 	struct mv88e6xxx_vtu_entry vlan = {
-		.vid = GLOBAL_VTU_VID_MASK, /* all ones */
+		.vid = chip->info->max_vid,
 	};
 	u16 fid;
 	int err;
@@ -2286,12 +1770,8 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port,
 		return err;
 
 	/* Dump VLANs' Filtering Information Databases */
-	err = _mv88e6xxx_vtu_vid_write(chip, vlan.vid);
-	if (err)
-		return err;
-
 	do {
-		err = _mv88e6xxx_vtu_getnext(chip, &vlan);
+		err = mv88e6xxx_vtu_getnext(chip, &vlan);
 		if (err)
 			return err;
 
@@ -2302,7 +1782,7 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port,
 						 obj, cb);
 		if (err)
 			return err;
-	} while (vlan.vid < GLOBAL_VTU_VID_MASK);
+	} while (vlan.vid < chip->info->max_vid);
 
 	return err;
 }
@@ -2321,23 +1801,52 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port,
-				      struct net_device *br)
+static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip,
+				struct net_device *br)
 {
-	struct mv88e6xxx_chip *chip = ds->priv;
-	int i, err = 0;
-
-	mutex_lock(&chip->reg_lock);
+	struct dsa_switch *ds;
+	int port;
+	int dev;
+	int err;
 
-	/* Remap each port's VLANTable */
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
-		if (ds->ports[i].bridge_dev == br) {
-			err = _mv88e6xxx_port_based_vlan_map(chip, i);
+	/* Remap the Port VLAN of each local bridge group member */
+	for (port = 0; port < mv88e6xxx_num_ports(chip); ++port) {
+		if (chip->ds->ports[port].bridge_dev == br) {
+			err = mv88e6xxx_port_vlan_map(chip, port);
 			if (err)
-				break;
+				return err;
+		}
+	}
+
+	if (!mv88e6xxx_has_pvt(chip))
+		return 0;
+
+	/* Remap the Port VLAN of each cross-chip bridge group member */
+	for (dev = 0; dev < DSA_MAX_SWITCHES; ++dev) {
+		ds = chip->ds->dst->ds[dev];
+		if (!ds)
+			break;
+
+		for (port = 0; port < ds->num_ports; ++port) {
+			if (ds->ports[port].bridge_dev == br) {
+				err = mv88e6xxx_pvt_map(chip, dev, port);
+				if (err)
+					return err;
+			}
 		}
 	}
 
+	return 0;
+}
+
+static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port,
+				      struct net_device *br)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
+
+	mutex_lock(&chip->reg_lock);
+	err = mv88e6xxx_bridge_map(chip, br);
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2347,17 +1856,41 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port,
 					struct net_device *br)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	int i;
 
 	mutex_lock(&chip->reg_lock);
+	if (mv88e6xxx_bridge_map(chip, br) ||
+	    mv88e6xxx_port_vlan_map(chip, port))
+		dev_err(ds->dev, "failed to remap in-chip Port VLAN\n");
+	mutex_unlock(&chip->reg_lock);
+}
 
-	/* Remap each port's VLANTable */
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
-		if (i == port || ds->ports[i].bridge_dev == br)
-			if (_mv88e6xxx_port_based_vlan_map(chip, i))
-				netdev_warn(ds->ports[i].netdev,
-					    "failed to remap\n");
+static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, int dev,
+					   int port, struct net_device *br)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
+
+	if (!mv88e6xxx_has_pvt(chip))
+		return 0;
+
+	mutex_lock(&chip->reg_lock);
+	err = mv88e6xxx_pvt_map(chip, dev, port);
+	mutex_unlock(&chip->reg_lock);
+
+	return err;
+}
+
+static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, int dev,
+					     int port, struct net_device *br)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
 
+	if (!mv88e6xxx_has_pvt(chip))
+		return;
+
+	mutex_lock(&chip->reg_lock);
+	if (mv88e6xxx_pvt_map(chip, dev, port))
+		dev_err(ds->dev, "failed to remap cross-chip Port VLAN\n");
 	mutex_unlock(&chip->reg_lock);
 }
 
@@ -2433,70 +1966,85 @@ static int mv88e6xxx_serdes_power_on(struct mv88e6xxx_chip *chip)
 	return err;
 }
 
-static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port,
-				    int upstream_port)
+static int mv88e6xxx_set_port_mode(struct mv88e6xxx_chip *chip, int port,
+				   enum mv88e6xxx_frame_mode frame, u16 egress,
+				   u16 etype)
 {
 	int err;
 
-	err = chip->info->ops->port_set_frame_mode(
-		chip, port, MV88E6XXX_FRAME_MODE_DSA);
+	if (!chip->info->ops->port_set_frame_mode)
+		return -EOPNOTSUPP;
+
+	err = mv88e6xxx_port_set_egress_mode(chip, port, egress);
 	if (err)
 		return err;
 
-	return chip->info->ops->port_set_egress_unknowns(
-		chip, port, port == upstream_port);
+	err = chip->info->ops->port_set_frame_mode(chip, port, frame);
+	if (err)
+		return err;
+
+	if (chip->info->ops->port_set_ether_type)
+		return chip->info->ops->port_set_ether_type(chip, port, etype);
+
+	return 0;
 }
 
-static int mv88e6xxx_setup_port_cpu(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_set_port_mode_normal(struct mv88e6xxx_chip *chip, int port)
 {
-	int err;
+	return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_NORMAL,
+				       PORT_CONTROL_EGRESS_UNMODIFIED,
+				       PORT_ETH_TYPE_DEFAULT);
+}
 
-	switch (chip->info->tag_protocol) {
-	case DSA_TAG_PROTO_EDSA:
-		err = chip->info->ops->port_set_frame_mode(
-			chip, port, MV88E6XXX_FRAME_MODE_ETHERTYPE);
-		if (err)
-			return err;
+static int mv88e6xxx_set_port_mode_dsa(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_DSA,
+				       PORT_CONTROL_EGRESS_UNMODIFIED,
+				       PORT_ETH_TYPE_DEFAULT);
+}
 
-		err = mv88e6xxx_port_set_egress_mode(
-			chip, port, PORT_CONTROL_EGRESS_ADD_TAG);
-		if (err)
-			return err;
+static int mv88e6xxx_set_port_mode_edsa(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_set_port_mode(chip, port,
+				       MV88E6XXX_FRAME_MODE_ETHERTYPE,
+				       PORT_CONTROL_EGRESS_ADD_TAG, ETH_P_EDSA);
+}
 
-		if (chip->info->ops->port_set_ether_type)
-			err = chip->info->ops->port_set_ether_type(
-				chip, port, ETH_P_EDSA);
-		break;
+static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port)
+{
+	if (dsa_is_dsa_port(chip->ds, port))
+		return mv88e6xxx_set_port_mode_dsa(chip, port);
 
-	case DSA_TAG_PROTO_DSA:
-		err = chip->info->ops->port_set_frame_mode(
-			chip, port, MV88E6XXX_FRAME_MODE_DSA);
-		if (err)
-			return err;
+	if (dsa_is_normal_port(chip->ds, port))
+		return mv88e6xxx_set_port_mode_normal(chip, port);
 
-		err = mv88e6xxx_port_set_egress_mode(
-			chip, port, PORT_CONTROL_EGRESS_UNMODIFIED);
-		break;
-	default:
-		err = -EINVAL;
-	}
+	/* Setup CPU port mode depending on its supported tag format */
+	if (chip->info->tag_protocol == DSA_TAG_PROTO_DSA)
+		return mv88e6xxx_set_port_mode_dsa(chip, port);
 
-	if (err)
-		return err;
+	if (chip->info->tag_protocol == DSA_TAG_PROTO_EDSA)
+		return mv88e6xxx_set_port_mode_edsa(chip, port);
 
-	return chip->info->ops->port_set_egress_unknowns(chip, port, true);
+	return -EINVAL;
 }
 
-static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port)
 {
-	int err;
+	bool message = dsa_is_dsa_port(chip->ds, port);
 
-	err = chip->info->ops->port_set_frame_mode(
-		chip, port, MV88E6XXX_FRAME_MODE_NORMAL);
-	if (err)
-		return err;
+	return mv88e6xxx_port_set_message_port(chip, port, message);
+}
 
-	return chip->info->ops->port_set_egress_unknowns(chip, port, false);
+static int mv88e6xxx_setup_egress_floods(struct mv88e6xxx_chip *chip, int port)
+{
+	bool flood = port == dsa_upstream_port(chip->ds);
+
+	/* Upstream ports flood frames with unknown unicast or multicast DA */
+	if (chip->info->ops->port_set_egress_floods)
+		return chip->info->ops->port_set_egress_floods(chip, port,
+							       flood, flood);
+
+	return 0;
 }
 
 static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
@@ -2541,14 +2089,11 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	if (err)
 		return err;
 
-	if (dsa_is_cpu_port(ds, port)) {
-		err = mv88e6xxx_setup_port_cpu(chip, port);
-	} else if (dsa_is_dsa_port(ds, port)) {
-		err = mv88e6xxx_setup_port_dsa(chip, port,
-					       dsa_upstream_port(ds));
-	} else {
-		err = mv88e6xxx_setup_port_normal(chip, port);
-	}
+	err = mv88e6xxx_setup_port_mode(chip, port);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_setup_egress_floods(chip, port);
 	if (err)
 		return err;
 
@@ -2623,20 +2168,14 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 			return err;
 	}
 
-	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
-	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
-	    mv88e6xxx_6320_family(chip) || mv88e6xxx_6341_family(chip)) {
-		/* Port ATU control: disable limiting the number of
-		 * address database entries that this port is allowed
-		 * to use.
-		 */
-		err = mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL,
-					   0x0000);
-		/* Priority Override: disable DA, SA and VTU priority
-		 * override.
-		 */
-		err = mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE,
-					   0x0000);
+	if (chip->info->ops->port_disable_learn_limit) {
+		err = chip->info->ops->port_disable_learn_limit(chip, port);
+		if (err)
+			return err;
+	}
+
+	if (chip->info->ops->port_disable_pri_override) {
+		err = chip->info->ops->port_disable_pri_override(chip, port);
 		if (err)
 			return err;
 	}
@@ -2653,10 +2192,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 			return err;
 	}
 
-	/* Port Control 1: disable trunking, disable sending
-	 * learning messages to this port.
-	 */
-	err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, 0x0000);
+	err = mv88e6xxx_setup_message_port(chip, port);
 	if (err)
 		return err;
 
@@ -2668,7 +2204,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	if (err)
 		return err;
 
-	err = _mv88e6xxx_port_based_vlan_map(chip, port);
+	err = mv88e6xxx_port_vlan_map(chip, port);
 	if (err)
 		return err;
 
@@ -2697,33 +2233,6 @@ static int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr)
 	return 0;
 }
 
-static int mv88e6xxx_g1_set_age_time(struct mv88e6xxx_chip *chip,
-				     unsigned int msecs)
-{
-	const unsigned int coeff = chip->info->age_time_coeff;
-	const unsigned int min = 0x01 * coeff;
-	const unsigned int max = 0xff * coeff;
-	u8 age_time;
-	u16 val;
-	int err;
-
-	if (msecs < min || msecs > max)
-		return -ERANGE;
-
-	/* Round to nearest multiple of coeff */
-	age_time = (msecs + coeff / 2) / coeff;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
-	if (err)
-		return err;
-
-	/* AgeTime is 11:4 bits */
-	val &= ~0xff0;
-	val |= age_time << 4;
-
-	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
-}
-
 static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
 				     unsigned int ageing_time)
 {
@@ -2731,7 +2240,7 @@ static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
 	int err;
 
 	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_g1_set_age_time(chip, ageing_time);
+	err = mv88e6xxx_g1_atu_set_age_time(chip, ageing_time);
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2769,29 +2278,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip)
 	if (err)
 		return err;
 
-	/* Clear all the VTU and STU entries */
-	err = _mv88e6xxx_vtu_stu_flush(chip);
-	if (err < 0)
-		return err;
-
-	/* Set the default address aging time to 5 minutes, and
-	 * enable address learn messages to be sent to all message
-	 * ports.
-	 */
-	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL,
-				 GLOBAL_ATU_CONTROL_LEARN2ALL);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_set_age_time(chip, 300000);
-	if (err)
-		return err;
-
-	/* Clear all ATU entries */
-	err = _mv88e6xxx_atu_flush(chip, 0, true);
-	if (err)
-		return err;
-
 	/* Configure the IP ToS mapping registers. */
 	err = mv88e6xxx_g1_write(chip, GLOBAL_IP_PRI_0, 0x0000);
 	if (err)
@@ -2872,6 +2358,18 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 			goto unlock;
 	}
 
+	err = mv88e6xxx_vtu_setup(chip);
+	if (err)
+		goto unlock;
+
+	err = mv88e6xxx_pvt_setup(chip);
+	if (err)
+		goto unlock;
+
+	err = mv88e6xxx_atu_setup(chip);
+	if (err)
+		goto unlock;
+
 	/* Some generations have the configuration of sending reserved
 	 * management frames to the CPU in global2, others in
 	 * global1. Hence it does not fit the two setup functions
@@ -3101,10 +2599,12 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3116,6 +2616,8 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
 	.reset = mv88e6185_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6095_ops = {
@@ -3127,7 +2629,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3137,6 +2639,8 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
 	.reset = mv88e6185_g1_reset,
+	.vtu_getnext = mv88e6185_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6097_ops = {
@@ -3149,11 +2653,13 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3163,6 +2669,8 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6123_ops = {
@@ -3174,7 +2682,9 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6085_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3184,6 +2694,8 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6131_ops = {
@@ -3196,7 +2708,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
@@ -3213,6 +2725,41 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
 	.reset = mv88e6185_g1_reset,
+	.vtu_getnext = mv88e6185_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+};
+
+static const struct mv88e6xxx_ops mv88e6141_ops = {
+	/* MV88E6XXX_FAMILY_6341 */
+	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
+	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
+	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
+	.phy_read = mv88e6xxx_g2_smi_phy_read,
+	.phy_write = mv88e6xxx_g2_smi_phy_write,
+	.port_set_link = mv88e6xxx_port_set_link,
+	.port_set_duplex = mv88e6xxx_port_set_duplex,
+	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
+	.port_set_speed = mv88e6390_port_set_speed,
+	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
+	.port_set_ether_type = mv88e6351_port_set_ether_type,
+	.port_jumbo_config = mv88e6165_port_jumbo_config,
+	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
+	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.stats_snapshot = mv88e6390_g1_stats_snapshot,
+	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
+	.stats_get_strings = mv88e6320_stats_get_strings,
+	.stats_get_stats = mv88e6390_stats_get_stats,
+	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
+	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
+	.watchdog_ops = &mv88e6390_watchdog_ops,
+	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
+	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6161_ops = {
@@ -3225,11 +2772,13 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3239,6 +2788,8 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6165_ops = {
@@ -3249,6 +2800,8 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.port_set_link = mv88e6xxx_port_set_link,
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3258,6 +2811,8 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6171_ops = {
@@ -3271,11 +2826,13 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3285,6 +2842,8 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6172_ops = {
@@ -3300,11 +2859,13 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3314,6 +2875,8 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6175_ops = {
@@ -3327,11 +2890,13 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3341,6 +2906,8 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -3356,11 +2923,13 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3370,6 +2939,8 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6185_ops = {
@@ -3381,7 +2952,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
@@ -3395,6 +2966,8 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.ppu_enable = mv88e6185_g1_ppu_enable,
 	.ppu_disable = mv88e6185_g1_ppu_disable,
 	.reset = mv88e6185_g1_reset,
+	.vtu_getnext = mv88e6185_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6190_ops = {
@@ -3410,9 +2983,11 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3423,6 +2998,8 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6390_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6190x_ops = {
@@ -3438,9 +3015,11 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_set_speed = mv88e6390x_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3451,6 +3030,8 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6390_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6191_ops = {
@@ -3466,9 +3047,11 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3479,6 +3062,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6390_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6240_ops = {
@@ -3494,11 +3079,13 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3508,6 +3095,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6290_ops = {
@@ -3523,10 +3112,12 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
 	.port_set_cmode = mv88e6390x_port_set_cmode,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3537,6 +3128,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6390_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
@@ -3551,11 +3144,13 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
@@ -3564,6 +3159,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.g1_set_egress_port = mv88e6095_g1_set_egress_port,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6185_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
@@ -3578,11 +3175,13 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
@@ -3590,6 +3189,41 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.g1_set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.g1_set_egress_port = mv88e6095_g1_set_egress_port,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6185_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+};
+
+static const struct mv88e6xxx_ops mv88e6341_ops = {
+	/* MV88E6XXX_FAMILY_6341 */
+	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
+	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
+	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
+	.phy_read = mv88e6xxx_g2_smi_phy_read,
+	.phy_write = mv88e6xxx_g2_smi_phy_write,
+	.port_set_link = mv88e6xxx_port_set_link,
+	.port_set_duplex = mv88e6xxx_port_set_duplex,
+	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
+	.port_set_speed = mv88e6390_port_set_speed,
+	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
+	.port_set_ether_type = mv88e6351_port_set_ether_type,
+	.port_jumbo_config = mv88e6165_port_jumbo_config,
+	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
+	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.stats_snapshot = mv88e6390_g1_stats_snapshot,
+	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
+	.stats_get_strings = mv88e6320_stats_get_strings,
+	.stats_get_stats = mv88e6390_stats_get_stats,
+	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
+	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
+	.watchdog_ops = &mv88e6390_watchdog_ops,
+	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
+	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6350_ops = {
@@ -3603,11 +3237,13 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3617,6 +3253,8 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6351_ops = {
@@ -3630,11 +3268,13 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3644,6 +3284,8 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6352_ops = {
@@ -3659,11 +3301,13 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3673,64 +3317,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.watchdog_ops = &mv88e6097_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6095_g2_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
-};
-
-static const struct mv88e6xxx_ops mv88e6141_ops = {
-	/* MV88E6XXX_FAMILY_6341 */
-	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
-	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
-	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
-	.phy_read = mv88e6xxx_g2_smi_phy_read,
-	.phy_write = mv88e6xxx_g2_smi_phy_write,
-	.port_set_link = mv88e6xxx_port_set_link,
-	.port_set_duplex = mv88e6xxx_port_set_duplex,
-	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
-	.port_set_speed = mv88e6390_port_set_speed,
-	.port_tag_remap = mv88e6095_port_tag_remap,
-	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
-	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_jumbo_config = mv88e6165_port_jumbo_config,
-	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
-	.port_pause_config = mv88e6097_port_pause_config,
-	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
-	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
-	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
-	.watchdog_ops = &mv88e6390_watchdog_ops,
-	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
-	.reset = mv88e6352_g1_reset,
-};
-
-static const struct mv88e6xxx_ops mv88e6341_ops = {
-	/* MV88E6XXX_FAMILY_6341 */
-	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
-	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
-	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
-	.phy_read = mv88e6xxx_g2_smi_phy_read,
-	.phy_write = mv88e6xxx_g2_smi_phy_write,
-	.port_set_link = mv88e6xxx_port_set_link,
-	.port_set_duplex = mv88e6xxx_port_set_duplex,
-	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
-	.port_set_speed = mv88e6390_port_set_speed,
-	.port_tag_remap = mv88e6095_port_tag_remap,
-	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
-	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_jumbo_config = mv88e6165_port_jumbo_config,
-	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
-	.port_pause_config = mv88e6097_port_pause_config,
-	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
-	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
-	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
-	.watchdog_ops = &mv88e6390_watchdog_ops,
-	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
-	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6390_ops = {
@@ -3746,12 +3334,14 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6390_port_pause_config,
 	.port_set_cmode = mv88e6390x_port_set_cmode,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3762,6 +3352,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6390_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 };
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
@@ -3777,11 +3369,13 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_set_speed = mv88e6390x_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3792,52 +3386,10 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
 	.reset = mv88e6352_g1_reset,
+	.vtu_getnext = mv88e6390_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 };
 
-static const struct mv88e6xxx_ops mv88e6391_ops = {
-	/* MV88E6XXX_FAMILY_6390 */
-	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
-	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
-	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
-	.phy_read = mv88e6xxx_g2_smi_phy_read,
-	.phy_write = mv88e6xxx_g2_smi_phy_write,
-	.port_set_link = mv88e6xxx_port_set_link,
-	.port_set_duplex = mv88e6xxx_port_set_duplex,
-	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
-	.port_set_speed = mv88e6390_port_set_speed,
-	.port_tag_remap = mv88e6390_port_tag_remap,
-	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
-	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_pause_config = mv88e6390_port_pause_config,
-	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
-	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
-	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
-	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
-	.watchdog_ops = &mv88e6390_watchdog_ops,
-	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
-	.reset = mv88e6352_g1_reset,
-};
-
-static int mv88e6xxx_verify_madatory_ops(struct mv88e6xxx_chip *chip,
-					 const struct mv88e6xxx_ops *ops)
-{
-	if (!ops->port_set_frame_mode) {
-		dev_err(chip->dev, "Missing port_set_frame_mode");
-		return -EINVAL;
-	}
-
-	if (!ops->port_set_egress_unknowns) {
-		dev_err(chip->dev, "Missing port_set_egress_mode");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 	[MV88E6085] = {
 		.prod_num = PORT_SWITCH_ID_PROD_NUM_6085,
@@ -3845,10 +3397,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6085",
 		.num_databases = 4096,
 		.num_ports = 10,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6097,
 		.ops = &mv88e6085_ops,
@@ -3860,10 +3415,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6095/88E6095F",
 		.num_databases = 256,
 		.num_ports = 11,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6095,
 		.ops = &mv88e6095_ops,
@@ -3875,10 +3432,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6097/88E6097F",
 		.num_databases = 4096,
 		.num_ports = 11,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6097,
 		.ops = &mv88e6097_ops,
@@ -3890,10 +3450,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6123",
 		.num_databases = 4096,
 		.num_ports = 3,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 		.ops = &mv88e6123_ops,
@@ -3905,25 +3468,47 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6131",
 		.num_databases = 256,
 		.num_ports = 8,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 		.ops = &mv88e6131_ops,
 	},
 
+	[MV88E6141] = {
+		.prod_num = PORT_SWITCH_ID_PROD_NUM_6141,
+		.family = MV88E6XXX_FAMILY_6341,
+		.name = "Marvell 88E6341",
+		.num_databases = 4096,
+		.num_ports = 6,
+		.max_vid = 4095,
+		.port_base_addr = 0x10,
+		.global1_addr = 0x1b,
+		.age_time_coeff = 3750,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
+		.tag_protocol = DSA_TAG_PROTO_EDSA,
+		.flags = MV88E6XXX_FLAGS_FAMILY_6341,
+		.ops = &mv88e6141_ops,
+	},
+
 	[MV88E6161] = {
 		.prod_num = PORT_SWITCH_ID_PROD_NUM_6161,
 		.family = MV88E6XXX_FAMILY_6165,
 		.name = "Marvell 88E6161",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 		.ops = &mv88e6161_ops,
@@ -3935,10 +3520,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6165",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 		.ops = &mv88e6165_ops,
@@ -3950,10 +3538,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6171",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6171_ops,
@@ -3965,10 +3556,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6172",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6172_ops,
@@ -3980,10 +3574,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6175",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6175_ops,
@@ -3995,10 +3592,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6176",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6176_ops,
@@ -4010,10 +3610,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6185",
 		.num_databases = 256,
 		.num_ports = 10,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 		.ops = &mv88e6185_ops,
@@ -4025,11 +3627,14 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6190",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
+		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.pvt = true,
+		.atu_move_port_mask = 0x1f,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6190_ops,
 	},
@@ -4040,10 +3645,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6190X",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
+		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6190x_ops,
@@ -4055,13 +3663,16 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6191",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
+		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
-		.ops = &mv88e6391_ops,
+		.ops = &mv88e6191_ops,
 	},
 
 	[MV88E6240] = {
@@ -4070,10 +3681,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6240",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6240_ops,
@@ -4085,10 +3699,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6290",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
+		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6290_ops,
@@ -4100,10 +3717,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6320",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 		.ops = &mv88e6320_ops,
@@ -4115,38 +3735,29 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6321",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 		.ops = &mv88e6321_ops,
 	},
 
-	[MV88E6141] = {
-		.prod_num = PORT_SWITCH_ID_PROD_NUM_6141,
-		.family = MV88E6XXX_FAMILY_6341,
-		.name = "Marvell 88E6341",
-		.num_databases = 4096,
-		.num_ports = 6,
-		.port_base_addr = 0x10,
-		.global1_addr = 0x1b,
-		.age_time_coeff = 3750,
-		.tag_protocol = DSA_TAG_PROTO_EDSA,
-		.flags = MV88E6XXX_FLAGS_FAMILY_6341,
-		.ops = &mv88e6141_ops,
-	},
-
 	[MV88E6341] = {
 		.prod_num = PORT_SWITCH_ID_PROD_NUM_6341,
 		.family = MV88E6XXX_FAMILY_6341,
 		.name = "Marvell 88E6341",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6341,
 		.ops = &mv88e6341_ops,
@@ -4158,10 +3769,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6350",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6350_ops,
@@ -4173,10 +3787,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6351",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6351_ops,
@@ -4188,10 +3805,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6352",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.max_vid = 4095,
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6352_ops,
@@ -4202,10 +3822,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6390",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
+		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6390_ops,
@@ -4216,10 +3839,13 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6390X",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
+		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6390x_ops,
@@ -4455,6 +4081,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_mdb_add           = mv88e6xxx_port_mdb_add,
 	.port_mdb_del           = mv88e6xxx_port_mdb_del,
 	.port_mdb_dump          = mv88e6xxx_port_mdb_dump,
+	.crosschip_bridge_join	= mv88e6xxx_crosschip_bridge_join,
+	.crosschip_bridge_leave	= mv88e6xxx_crosschip_bridge_leave,
 };
 
 static struct dsa_switch_driver mv88e6xxx_switch_drv = {
@@ -4466,12 +4094,14 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip)
 	struct device *dev = chip->dev;
 	struct dsa_switch *ds;
 
-	ds = dsa_switch_alloc(dev, DSA_MAX_PORTS);
+	ds = dsa_switch_alloc(dev, mv88e6xxx_num_ports(chip));
 	if (!ds)
 		return -ENOMEM;
 
 	ds->priv = chip;
 	ds->ops = &mv88e6xxx_switch_ops;
+	ds->ageing_time_min = chip->info->age_time_coeff;
+	ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX;
 
 	dev_set_drvdata(dev, ds);
 
@@ -4502,10 +4132,6 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 
 	chip->info = compat_info;
 
-	err = mv88e6xxx_verify_madatory_ops(chip, chip->info->ops);
-	if (err)
-		return err;
-
 	err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr);
 	if (err)
 		return err;
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 75af86a7fad8..39825837a1c9 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 1aec7382c02d..46a4ea0f8c47 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -38,4 +39,29 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip);
 
+int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all);
+int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
+				  unsigned int msecs);
+int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
+			     struct mv88e6xxx_atu_entry *entry);
+int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid,
+			       struct mv88e6xxx_atu_entry *entry);
+int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all);
+int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port,
+			    bool all);
+
+int mv88e6185_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry);
+int mv88e6185_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+			       struct mv88e6xxx_vtu_entry *entry);
+int mv88e6352_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry);
+int mv88e6352_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+			       struct mv88e6xxx_vtu_entry *entry);
+int mv88e6390_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry);
+int mv88e6390_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+			       struct mv88e6xxx_vtu_entry *entry);
+int mv88e6xxx_g1_vtu_flush(struct mv88e6xxx_chip *chip);
+
 #endif /* _MV88E6XXX_GLOBAL1_H */
diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
new file mode 100644
index 000000000000..fa7e7db5171b
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -0,0 +1,305 @@
+/*
+ * Marvell 88E6xxx Address Translation Unit (ATU) support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2017 Savoir-faire Linux, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "mv88e6xxx.h"
+#include "global1.h"
+
+/* Offset 0x01: ATU FID Register */
+
+static int mv88e6xxx_g1_atu_fid_write(struct mv88e6xxx_chip *chip, u16 fid)
+{
+	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid & 0xfff);
+}
+
+/* Offset 0x0A: ATU Control Register */
+
+int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+	if (err)
+		return err;
+
+	if (learn2all)
+		val |= GLOBAL_ATU_CONTROL_LEARN2ALL;
+	else
+		val &= ~GLOBAL_ATU_CONTROL_LEARN2ALL;
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+}
+
+int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
+				  unsigned int msecs)
+{
+	const unsigned int coeff = chip->info->age_time_coeff;
+	const unsigned int min = 0x01 * coeff;
+	const unsigned int max = 0xff * coeff;
+	u8 age_time;
+	u16 val;
+	int err;
+
+	if (msecs < min || msecs > max)
+		return -ERANGE;
+
+	/* Round to nearest multiple of coeff */
+	age_time = (msecs + coeff / 2) / coeff;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+	if (err)
+		return err;
+
+	/* AgeTime is 11:4 bits */
+	val &= ~0xff0;
+	val |= age_time << 4;
+
+	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+	if (err)
+		return err;
+
+	dev_dbg(chip->dev, "AgeTime set to 0x%02x (%d ms)\n", age_time,
+		age_time * coeff);
+
+	return 0;
+}
+
+/* Offset 0x0B: ATU Operation Register */
+
+static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY);
+}
+
+static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op)
+{
+	u16 val;
+	int err;
+
+	/* FID bits are dispatched all around gradually as more are supported */
+	if (mv88e6xxx_num_databases(chip) > 256) {
+		err = mv88e6xxx_g1_atu_fid_write(chip, fid);
+		if (err)
+			return err;
+	} else {
+		if (mv88e6xxx_num_databases(chip) > 16) {
+			/* ATU DBNum[7:4] are located in ATU Control 15:12 */
+			err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+			if (err)
+				return err;
+
+			val = (val & 0x0fff) | ((fid << 8) & 0xf000);
+			err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+			if (err)
+				return err;
+		}
+
+		/* ATU DBNum[3:0] are located in ATU Operation 3:0 */
+		op |= fid & 0xf;
+	}
+
+	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, op);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_op_wait(chip);
+}
+
+/* Offset 0x0C: ATU Data Register */
+
+static int mv88e6xxx_g1_atu_data_read(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_atu_entry *entry)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val);
+	if (err)
+		return err;
+
+	entry->state = val & 0xf;
+	if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
+		entry->trunk = !!(val & GLOBAL_ATU_DATA_TRUNK);
+		entry->portvec = (val >> 4) & mv88e6xxx_port_mask(chip);
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip,
+				       struct mv88e6xxx_atu_entry *entry)
+{
+	u16 data = entry->state & 0xf;
+
+	if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
+		if (entry->trunk)
+			data |= GLOBAL_ATU_DATA_TRUNK;
+
+		data |= (entry->portvec & mv88e6xxx_port_mask(chip)) << 4;
+	}
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data);
+}
+
+/* Offset 0x0D: ATU MAC Address Register Bytes 0 & 1
+ * Offset 0x0E: ATU MAC Address Register Bytes 2 & 3
+ * Offset 0x0F: ATU MAC Address Register Bytes 4 & 5
+ */
+
+static int mv88e6xxx_g1_atu_mac_read(struct mv88e6xxx_chip *chip,
+				     struct mv88e6xxx_atu_entry *entry)
+{
+	u16 val;
+	int i, err;
+
+	for (i = 0; i < 3; i++) {
+		err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val);
+		if (err)
+			return err;
+
+		entry->mac[i * 2] = val >> 8;
+		entry->mac[i * 2 + 1] = val & 0xff;
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_atu_entry *entry)
+{
+	u16 val;
+	int i, err;
+
+	for (i = 0; i < 3; i++) {
+		val = (entry->mac[i * 2] << 8) | entry->mac[i * 2 + 1];
+		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, val);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/* Address Translation Unit operations */
+
+int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
+			     struct mv88e6xxx_atu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_atu_op_wait(chip);
+	if (err)
+		return err;
+
+	/* Write the MAC address to iterate from only once */
+	if (entry->state == GLOBAL_ATU_DATA_STATE_UNUSED) {
+		err = mv88e6xxx_g1_atu_mac_write(chip, entry);
+		if (err)
+			return err;
+	}
+
+	err = mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_data_read(chip, entry);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_mac_read(chip, entry);
+}
+
+int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid,
+			       struct mv88e6xxx_atu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_atu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_mac_write(chip, entry);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_data_write(chip, entry);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_LOAD_DB);
+}
+
+static int mv88e6xxx_g1_atu_flushmove(struct mv88e6xxx_chip *chip, u16 fid,
+				      struct mv88e6xxx_atu_entry *entry,
+				      bool all)
+{
+	u16 op;
+	int err;
+
+	err = mv88e6xxx_g1_atu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_data_write(chip, entry);
+	if (err)
+		return err;
+
+	/* Flush/Move all or non-static entries from all or a given database */
+	if (all && fid)
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB;
+	else if (fid)
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB;
+	else if (all)
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL;
+	else
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
+
+	return mv88e6xxx_g1_atu_op(chip, fid, op);
+}
+
+int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all)
+{
+	struct mv88e6xxx_atu_entry entry = {
+		.state = 0, /* Null EntryState means Flush */
+	};
+
+	return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all);
+}
+
+static int mv88e6xxx_g1_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
+				 int from_port, int to_port, bool all)
+{
+	struct mv88e6xxx_atu_entry entry = { 0 };
+	unsigned long mask;
+	int shift;
+
+	if (!chip->info->atu_move_port_mask)
+		return -EOPNOTSUPP;
+
+	mask = chip->info->atu_move_port_mask;
+	shift = bitmap_weight(&mask, 16);
+
+	entry.state = 0xf, /* Full EntryState means Move */
+	entry.portvec = from_port & mask;
+	entry.portvec |= (to_port & mask) << shift;
+
+	return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all);
+}
+
+int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port,
+			    bool all)
+{
+	int from_port = port;
+	int to_port = chip->info->atu_move_port_mask;
+
+	return mv88e6xxx_g1_atu_move(chip, fid, from_port, to_port, all);
+}
diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c
new file mode 100644
index 000000000000..9aea22d4c9e2
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c
@@ -0,0 +1,511 @@
+/*
+ * Marvell 88E6xxx VLAN [Spanning Tree] Translation Unit (VTU [STU]) support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2015 CMC Electronics, Inc.
+ * Copyright (c) 2017 Savoir-faire Linux, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "mv88e6xxx.h"
+#include "global1.h"
+
+/* Offset 0x02: VTU FID Register */
+
+static int mv88e6xxx_g1_vtu_fid_read(struct mv88e6xxx_chip *chip,
+				     struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_FID, &val);
+	if (err)
+		return err;
+
+	entry->fid = val & GLOBAL_VTU_FID_MASK;
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_vtu_fid_write(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val = entry->fid & GLOBAL_VTU_FID_MASK;
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_VTU_FID, val);
+}
+
+/* Offset 0x03: VTU SID Register */
+
+static int mv88e6xxx_g1_vtu_sid_read(struct mv88e6xxx_chip *chip,
+				     struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_SID, &val);
+	if (err)
+		return err;
+
+	entry->sid = val & GLOBAL_VTU_SID_MASK;
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_vtu_sid_write(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val = entry->sid & GLOBAL_VTU_SID_MASK;
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_VTU_SID, val);
+}
+
+/* Offset 0x05: VTU Operation Register */
+
+static int mv88e6xxx_g1_vtu_op_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g1_wait(chip, GLOBAL_VTU_OP, GLOBAL_VTU_OP_BUSY);
+}
+
+static int mv88e6xxx_g1_vtu_op(struct mv88e6xxx_chip *chip, u16 op)
+{
+	int err;
+
+	err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_OP, op);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_vtu_op_wait(chip);
+}
+
+/* Offset 0x06: VTU VID Register */
+
+static int mv88e6xxx_g1_vtu_vid_read(struct mv88e6xxx_chip *chip,
+				     struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_VID, &val);
+	if (err)
+		return err;
+
+	entry->vid = val & 0xfff;
+
+	if (val & GLOBAL_VTU_VID_PAGE)
+		entry->vid |= 0x1000;
+
+	entry->valid = !!(val & GLOBAL_VTU_VID_VALID);
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_vtu_vid_write(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val = entry->vid & 0xfff;
+
+	if (entry->vid & 0x1000)
+		val |= GLOBAL_VTU_VID_PAGE;
+
+	if (entry->valid)
+		val |= GLOBAL_VTU_VID_VALID;
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_VTU_VID, val);
+}
+
+/* Offset 0x07: VTU/STU Data Register 1
+ * Offset 0x08: VTU/STU Data Register 2
+ * Offset 0x09: VTU/STU Data Register 3
+ */
+
+static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 regs[3];
+	int i;
+
+	/* Read all 3 VTU/STU Data registers */
+	for (i = 0; i < 3; ++i) {
+		u16 *reg = &regs[i];
+		int err;
+
+		err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_DATA_0_3 + i, reg);
+		if (err)
+			return err;
+	}
+
+	/* Extract MemberTag and PortState data */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
+		unsigned int member_offset = (i % 4) * 4;
+		unsigned int state_offset = member_offset + 2;
+
+		entry->member[i] = (regs[i / 4] >> member_offset) & 0x3;
+		entry->state[i] = (regs[i / 4] >> state_offset) & 0x3;
+	}
+
+	return 0;
+}
+
+static int mv88e6185_g1_vtu_data_write(struct mv88e6xxx_chip *chip,
+				       struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 regs[3] = { 0 };
+	int i;
+
+	/* Insert MemberTag and PortState data */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
+		unsigned int member_offset = (i % 4) * 4;
+		unsigned int state_offset = member_offset + 2;
+
+		regs[i / 4] |= (entry->member[i] & 0x3) << member_offset;
+		regs[i / 4] |= (entry->state[i] & 0x3) << state_offset;
+	}
+
+	/* Write all 3 VTU/STU Data registers */
+	for (i = 0; i < 3; ++i) {
+		u16 reg = regs[i];
+		int err;
+
+		err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_DATA_0_3 + i, reg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int mv88e6390_g1_vtu_data_read(struct mv88e6xxx_chip *chip, u8 *data)
+{
+	u16 regs[2];
+	int i;
+
+	/* Read the 2 VTU/STU Data registers */
+	for (i = 0; i < 2; ++i) {
+		u16 *reg = &regs[i];
+		int err;
+
+		err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_DATA_0_3 + i, reg);
+		if (err)
+			return err;
+	}
+
+	/* Extract data */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
+		unsigned int offset = (i % 8) * 2;
+
+		data[i] = (regs[i / 8] >> offset) & 0x3;
+	}
+
+	return 0;
+}
+
+static int mv88e6390_g1_vtu_data_write(struct mv88e6xxx_chip *chip, u8 *data)
+{
+	u16 regs[2] = { 0 };
+	int i;
+
+	/* Insert data */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
+		unsigned int offset = (i % 8) * 2;
+
+		regs[i / 8] |= (data[i] & 0x3) << offset;
+	}
+
+	/* Write the 2 VTU/STU Data registers */
+	for (i = 0; i < 2; ++i) {
+		u16 reg = regs[i];
+		int err;
+
+		err = mv88e6xxx_g1_write(chip, GLOBAL_VTU_DATA_0_3 + i, reg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/* VLAN Translation Unit Operations */
+
+static int mv88e6xxx_g1_vtu_stu_getnext(struct mv88e6xxx_chip *chip,
+					struct mv88e6xxx_vtu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_vtu_sid_write(chip, entry);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_STU_GET_NEXT);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_vtu_sid_read(chip, entry);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_vtu_vid_read(chip, entry);
+}
+
+static int mv88e6xxx_g1_vtu_stu_get(struct mv88e6xxx_chip *chip,
+				    struct mv88e6xxx_vtu_entry *vtu)
+{
+	struct mv88e6xxx_vtu_entry stu;
+	int err;
+
+	err = mv88e6xxx_g1_vtu_sid_read(chip, vtu);
+	if (err)
+		return err;
+
+	stu.sid = vtu->sid - 1;
+
+	err = mv88e6xxx_g1_vtu_stu_getnext(chip, &stu);
+	if (err)
+		return err;
+
+	if (stu.sid != vtu->sid || !stu.valid)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+				    struct mv88e6xxx_vtu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_vtu_op_wait(chip);
+	if (err)
+		return err;
+
+	/* To get the next higher active VID, the VTU GetNext operation can be
+	 * started again without setting the VID registers since it already
+	 * contains the last VID.
+	 *
+	 * To save a few hardware accesses and abstract this to the caller,
+	 * write the VID only once, when the entry is given as invalid.
+	 */
+	if (!entry->valid) {
+		err = mv88e6xxx_g1_vtu_vid_write(chip, entry);
+		if (err)
+			return err;
+	}
+
+	err = mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_VTU_GET_NEXT);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_vtu_vid_read(chip, entry);
+}
+
+int mv88e6185_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_vtu_getnext(chip, entry);
+	if (err)
+		return err;
+
+	if (entry->valid) {
+		err = mv88e6185_g1_vtu_data_read(chip, entry);
+		if (err)
+			return err;
+
+		/* VTU DBNum[3:0] are located in VTU Operation 3:0
+		 * VTU DBNum[7:4] are located in VTU Operation 11:8
+		 */
+		err = mv88e6xxx_g1_read(chip, GLOBAL_VTU_OP, &val);
+		if (err)
+			return err;
+
+		entry->fid = val & 0x000f;
+		entry->fid |= (val & 0x0f00) >> 4;
+	}
+
+	return 0;
+}
+
+int mv88e6352_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry)
+{
+	int err;
+
+	/* Fetch VLAN MemberTag data from the VTU */
+	err = mv88e6xxx_g1_vtu_getnext(chip, entry);
+	if (err)
+		return err;
+
+	if (entry->valid) {
+		/* Fetch (and mask) VLAN PortState data from the STU */
+		err = mv88e6xxx_g1_vtu_stu_get(chip, entry);
+		if (err)
+			return err;
+
+		err = mv88e6185_g1_vtu_data_read(chip, entry);
+		if (err)
+			return err;
+
+		err = mv88e6xxx_g1_vtu_fid_read(chip, entry);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int mv88e6390_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry)
+{
+	int err;
+
+	/* Fetch VLAN MemberTag data from the VTU */
+	err = mv88e6xxx_g1_vtu_getnext(chip, entry);
+	if (err)
+		return err;
+
+	if (entry->valid) {
+		err = mv88e6390_g1_vtu_data_read(chip, entry->member);
+		if (err)
+			return err;
+
+		/* Fetch VLAN PortState data from the STU */
+		err = mv88e6xxx_g1_vtu_stu_get(chip, entry);
+		if (err)
+			return err;
+
+		err = mv88e6390_g1_vtu_data_read(chip, entry->state);
+		if (err)
+			return err;
+
+		err = mv88e6xxx_g1_vtu_fid_read(chip, entry);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int mv88e6185_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+			       struct mv88e6xxx_vtu_entry *entry)
+{
+	u16 op = GLOBAL_VTU_OP_VTU_LOAD_PURGE;
+	int err;
+
+	err = mv88e6xxx_g1_vtu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_vtu_vid_write(chip, entry);
+	if (err)
+		return err;
+
+	if (entry->valid) {
+		err = mv88e6185_g1_vtu_data_write(chip, entry);
+		if (err)
+			return err;
+
+		/* VTU DBNum[3:0] are located in VTU Operation 3:0
+		 * VTU DBNum[7:4] are located in VTU Operation 11:8
+		 */
+		op |= entry->fid & 0x000f;
+		op |= (entry->fid & 0x00f0) << 8;
+	}
+
+	return mv88e6xxx_g1_vtu_op(chip, op);
+}
+
+int mv88e6352_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+			       struct mv88e6xxx_vtu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_vtu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_vtu_vid_write(chip, entry);
+	if (err)
+		return err;
+
+	if (entry->valid) {
+		/* Write MemberTag and PortState data */
+		err = mv88e6185_g1_vtu_data_write(chip, entry);
+		if (err)
+			return err;
+
+		err = mv88e6xxx_g1_vtu_sid_write(chip, entry);
+		if (err)
+			return err;
+
+		/* Load STU entry */
+		err = mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
+		if (err)
+			return err;
+
+		err = mv88e6xxx_g1_vtu_fid_write(chip, entry);
+		if (err)
+			return err;
+	}
+
+	/* Load/Purge VTU entry */
+	return mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_VTU_LOAD_PURGE);
+}
+
+int mv88e6390_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
+			       struct mv88e6xxx_vtu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_vtu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_vtu_vid_write(chip, entry);
+	if (err)
+		return err;
+
+	if (entry->valid) {
+		/* Write PortState data */
+		err = mv88e6390_g1_vtu_data_write(chip, entry->state);
+		if (err)
+			return err;
+
+		err = mv88e6xxx_g1_vtu_sid_write(chip, entry);
+		if (err)
+			return err;
+
+		/* Load STU entry */
+		err = mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
+		if (err)
+			return err;
+
+		/* Write MemberTag data */
+		err = mv88e6390_g1_vtu_data_write(chip, entry->member);
+		if (err)
+			return err;
+
+		err = mv88e6xxx_g1_vtu_fid_write(chip, entry);
+		if (err)
+			return err;
+	}
+
+	/* Load/Purge VTU entry */
+	return mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_VTU_LOAD_PURGE);
+}
+
+int mv88e6xxx_g1_vtu_flush(struct mv88e6xxx_chip *chip)
+{
+	int err;
+
+	err = mv88e6xxx_g1_vtu_op_wait(chip);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_vtu_op(chip, GLOBAL_VTU_OP_FLUSH_ALL);
+}
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 8f15bc7b1f5f..b3fea55071e3 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -4,7 +4,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -12,6 +13,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include "mv88e6xxx.h"
 #include "global2.h"
@@ -170,6 +172,50 @@ static int mv88e6xxx_g2_clear_irl(struct mv88e6xxx_chip *chip)
 	return err;
 }
 
+/* Offset 0x0B: Cross-chip Port VLAN (Addr) Register
+ * Offset 0x0C: Cross-chip Port VLAN Data Register
+ */
+
+static int mv88e6xxx_g2_pvt_op_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g2_wait(chip, GLOBAL2_PVT_ADDR, GLOBAL2_PVT_ADDR_BUSY);
+}
+
+static int mv88e6xxx_g2_pvt_op(struct mv88e6xxx_chip *chip, int src_dev,
+			       int src_port, u16 op)
+{
+	int err;
+
+	/* 9-bit Cross-chip PVT pointer: with GLOBAL2_MISC_5_BIT_PORT cleared,
+	 * source device is 5-bit, source port is 4-bit.
+	 */
+	op |= (src_dev & 0x1f) << 4;
+	op |= (src_port & 0xf);
+
+	err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_ADDR, op);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g2_pvt_op_wait(chip);
+}
+
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+			   int src_port, u16 data)
+{
+	int err;
+
+	err = mv88e6xxx_g2_pvt_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_DATA, data);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g2_pvt_op(chip, src_dev, src_port,
+				   GLOBAL2_PVT_ADDR_OP_WRITE_PVLAN);
+}
+
 /* Offset 0x0D: Switch MAC/WoL/WoF register */
 
 static int mv88e6xxx_g2_switch_mac_write(struct mv88e6xxx_chip *chip,
@@ -522,8 +568,9 @@ static int mv88e6xxx_g2_smi_phy_write_addr(struct mv88e6xxx_chip *chip,
 	return mv88e6xxx_g2_smi_phy_cmd(chip, cmd);
 }
 
-int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, int addr,
-				  int reg_c45, u16 *val, bool external)
+static int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip,
+					 int addr, int reg_c45, u16 *val,
+					 bool external)
 {
 	int device = (reg_c45 >> 16) & 0x1f;
 	int reg = reg_c45 & 0xffff;
@@ -553,8 +600,9 @@ int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, int addr,
 	return 0;
 }
 
-int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip, int addr,
-				  int reg, u16 *val, bool external)
+static int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip,
+					 int addr, int reg, u16 *val,
+					 bool external)
 {
 	u16 cmd = GLOBAL2_SMI_PHY_CMD_OP_22_READ_DATA | (addr << 5) | reg;
 	int err;
@@ -586,8 +634,9 @@ int mv88e6xxx_g2_smi_phy_read(struct mv88e6xxx_chip *chip,
 	return mv88e6xxx_g2_smi_phy_read_c22(chip, addr, reg, val, external);
 }
 
-int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, int addr,
-				   int reg_c45, u16 val, bool external)
+static int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip,
+					  int addr, int reg_c45, u16 val,
+					  bool external)
 {
 	int device = (reg_c45 >> 16) & 0x1f;
 	int reg = reg_c45 & 0xffff;
@@ -615,8 +664,9 @@ int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, int addr,
 	return 0;
 }
 
-int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip, int addr,
-				   int reg, u16 val, bool external)
+static int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip,
+					  int addr, int reg, u16 val,
+					  bool external)
 {
 	u16 cmd = GLOBAL2_SMI_PHY_CMD_OP_22_WRITE_DATA | (addr << 5) | reg;
 	int err;
@@ -782,6 +832,31 @@ static int mv88e6xxx_g2_watchdog_setup(struct mv88e6xxx_chip *chip)
 	return err;
 }
 
+/* Offset 0x1D: Misc Register */
+
+static int mv88e6xxx_g2_misc_5_bit_port(struct mv88e6xxx_chip *chip,
+					bool port_5_bit)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g2_read(chip, GLOBAL2_MISC, &val);
+	if (err)
+		return err;
+
+	if (port_5_bit)
+		val |= GLOBAL2_MISC_5_BIT_PORT;
+	else
+		val &= ~GLOBAL2_MISC_5_BIT_PORT;
+
+	return mv88e6xxx_g2_write(chip, GLOBAL2_MISC, val);
+}
+
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g2_misc_5_bit_port(chip, false);
+}
+
 static void mv88e6xxx_g2_irq_mask(struct irq_data *d)
 {
 	struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d);
@@ -964,14 +1039,6 @@ int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
 				return err;
 	}
 
-	if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_PVT)) {
-		/* Initialize Cross-chip Port VLAN Table to reset defaults */
-		err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_ADDR,
-					 GLOBAL2_PVT_ADDR_OP_INIT_ONES);
-		if (err)
-			return err;
-	}
-
 	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_POT)) {
 		/* Clear the priority override table. */
 		err = mv88e6xxx_g2_clear_pot(chip);
diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h
index a8b2f9486a4a..96046bb12ca1 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.h
+++ b/drivers/net/dsa/mv88e6xxx/global2.h
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -41,6 +42,10 @@ int mv88e6xxx_g2_get_eeprom16(struct mv88e6xxx_chip *chip,
 int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip,
 			      struct ethtool_eeprom *eeprom, u8 *data);
 
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+			   int src_port, u16 data);
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip);
+
 int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip);
 int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_g2_irq_free(struct mv88e6xxx_chip *chip);
@@ -109,6 +114,17 @@ static inline int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip,
 	return -EOPNOTSUPP;
 }
 
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+			   int src_port, u16 data)
+{
+	return -EOPNOTSUPP;
+}
+
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
index 6033f2f6260a..77236cd72df2 100644
--- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
@@ -16,6 +16,7 @@
 #include <linux/irq.h>
 #include <linux/gpio/consumer.h>
 #include <linux/phy.h>
+#include <net/dsa.h>
 
 #ifndef UINT64_MAX
 #define UINT64_MAX		(u64)(~((u64)0))
@@ -132,18 +133,19 @@
 #define PORT_CONTROL_TAG_IF_BOTH	BIT(6)
 #define PORT_CONTROL_USE_IP		BIT(5)
 #define PORT_CONTROL_USE_TAG		BIT(4)
-#define PORT_CONTROL_FORWARD_UNKNOWN_MC	BIT(3)
 #define PORT_CONTROL_FORWARD_UNKNOWN	BIT(2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_DA		(0x0 << 2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_MULTICAST_DA	(0x1 << 2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_UNITCAST_DA	(0x2 << 2)
-#define PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA		(0x3 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_MASK			(0x3 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA	(0x0 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA	(0x1 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA	(0x2 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA	(0x3 << 2)
 #define PORT_CONTROL_STATE_MASK		0x03
 #define PORT_CONTROL_STATE_DISABLED	0x00
 #define PORT_CONTROL_STATE_BLOCKING	0x01
 #define PORT_CONTROL_STATE_LEARNING	0x02
 #define PORT_CONTROL_STATE_FORWARDING	0x03
 #define PORT_CONTROL_1		0x05
+#define PORT_CONTROL_1_MESSAGE_PORT	BIT(15)
 #define PORT_CONTROL_1_FID_11_4_MASK	(0xff << 0)
 #define PORT_BASE_VLAN		0x06
 #define PORT_BASE_VLAN_FID_3_0_MASK	(0xf << 12)
@@ -166,7 +168,6 @@
 #define PORT_CONTROL_2_DISCARD_UNTAGGED	BIT(8)
 #define PORT_CONTROL_2_MAP_DA		BIT(7)
 #define PORT_CONTROL_2_DEFAULT_FORWARD	BIT(6)
-#define PORT_CONTROL_2_FORWARD_UNKNOWN	BIT(6)
 #define PORT_CONTROL_2_EGRESS_MONITOR	BIT(5)
 #define PORT_CONTROL_2_INGRESS_MONITOR	BIT(4)
 #define PORT_CONTROL_2_UPSTREAM_MASK	0x0f
@@ -181,6 +182,7 @@
 #define PORT_ATU_CONTROL	0x0c
 #define PORT_PRI_OVERRIDE	0x0d
 #define PORT_ETH_TYPE		0x0f
+#define PORT_ETH_TYPE_DEFAULT	0x9100
 #define PORT_IN_DISCARD_LO	0x10
 #define PORT_IN_DISCARD_HI	0x11
 #define PORT_IN_FILTERED	0x12
@@ -247,6 +249,7 @@
 #define GLOBAL_VTU_OP_STU_GET_NEXT	((0x06 << 12) | GLOBAL_VTU_OP_BUSY)
 #define GLOBAL_VTU_VID		0x06
 #define GLOBAL_VTU_VID_MASK	0xfff
+#define GLOBAL_VTU_VID_PAGE	BIT(13)
 #define GLOBAL_VTU_VID_VALID	BIT(12)
 #define GLOBAL_VTU_DATA_0_3	0x07
 #define GLOBAL_VTU_DATA_4_7	0x08
@@ -437,9 +440,14 @@
 #define GLOBAL2_WDOG_FORCE_IRQ			BIT(0)
 #define GLOBAL2_QOS_WEIGHT	0x1c
 #define GLOBAL2_MISC		0x1d
+#define GLOBAL2_MISC_5_BIT_PORT	BIT(14)
 
 #define MV88E6XXX_N_FID		4096
 
+/* PVT limits for 4-bit port and 5-bit switch */
+#define MV88E6XXX_MAX_PVT_SWITCHES	32
+#define MV88E6XXX_MAX_PVT_PORTS		16
+
 enum mv88e6xxx_frame_mode {
 	MV88E6XXX_FRAME_MODE_NORMAL,
 	MV88E6XXX_FRAME_MODE_DSA,
@@ -525,8 +533,6 @@ enum mv88e6xxx_cap {
 	MV88E6XXX_CAP_G2_MGMT_EN_0X,	/* (0x03) MGMT Enable Register 0x */
 	MV88E6XXX_CAP_G2_IRL_CMD,	/* (0x09) Ingress Rate Command */
 	MV88E6XXX_CAP_G2_IRL_DATA,	/* (0x0a) Ingress Rate Data */
-	MV88E6XXX_CAP_G2_PVT_ADDR,	/* (0x0b) Cross Chip Port VLAN Addr */
-	MV88E6XXX_CAP_G2_PVT_DATA,	/* (0x0c) Cross Chip Port VLAN Data */
 	MV88E6XXX_CAP_G2_POT,		/* (0x0f) Priority Override Table */
 
 	/* Per VLAN Spanning Tree Unit (STU).
@@ -551,7 +557,6 @@ enum mv88e6xxx_cap {
 
 #define MV88E6XXX_FLAG_SERDES		BIT_ULL(MV88E6XXX_CAP_SERDES)
 
-#define MV88E6XXX_FLAG_G1_ATU_FID	BIT_ULL(MV88E6XXX_CAP_G1_ATU_FID)
 #define MV88E6XXX_FLAG_G1_VTU_FID	BIT_ULL(MV88E6XXX_CAP_G1_VTU_FID)
 
 #define MV88E6XXX_FLAG_GLOBAL2		BIT_ULL(MV88E6XXX_CAP_GLOBAL2)
@@ -560,13 +565,8 @@ enum mv88e6xxx_cap {
 #define MV88E6XXX_FLAG_G2_MGMT_EN_0X	BIT_ULL(MV88E6XXX_CAP_G2_MGMT_EN_0X)
 #define MV88E6XXX_FLAG_G2_IRL_CMD	BIT_ULL(MV88E6XXX_CAP_G2_IRL_CMD)
 #define MV88E6XXX_FLAG_G2_IRL_DATA	BIT_ULL(MV88E6XXX_CAP_G2_IRL_DATA)
-#define MV88E6XXX_FLAG_G2_PVT_ADDR	BIT_ULL(MV88E6XXX_CAP_G2_PVT_ADDR)
-#define MV88E6XXX_FLAG_G2_PVT_DATA	BIT_ULL(MV88E6XXX_CAP_G2_PVT_DATA)
 #define MV88E6XXX_FLAG_G2_POT		BIT_ULL(MV88E6XXX_CAP_G2_POT)
 
-#define MV88E6XXX_FLAG_STU		BIT_ULL(MV88E6XXX_CAP_STU)
-#define MV88E6XXX_FLAG_VTU		BIT_ULL(MV88E6XXX_CAP_VTU)
-
 /* Ingress Rate Limit unit */
 #define MV88E6XXX_FLAGS_IRL		\
 	(MV88E6XXX_FLAG_G2_IRL_CMD |	\
@@ -577,11 +577,6 @@ enum mv88e6xxx_cap {
 	(MV88E6XXX_FLAG_SMI_CMD |	\
 	 MV88E6XXX_FLAG_SMI_DATA)
 
-/* Cross-chip Port VLAN Table */
-#define MV88E6XXX_FLAGS_PVT		\
-	(MV88E6XXX_FLAG_G2_PVT_ADDR |	\
-	 MV88E6XXX_FLAG_G2_PVT_DATA)
-
 /* Fiber/SERDES Registers at SMI address F, page 1 */
 #define MV88E6XXX_FLAGS_SERDES		\
 	(MV88E6XXX_FLAG_PHY_PAGE |	\
@@ -590,43 +585,33 @@ enum mv88e6xxx_cap {
 #define MV88E6XXX_FLAGS_FAMILY_6095	\
 	(MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6097	\
-	(MV88E6XXX_FLAG_G1_ATU_FID |	\
-	 MV88E6XXX_FLAG_G1_VTU_FID |	\
+	(MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |        \
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
 	 MV88E6XXX_FLAG_G2_POT |	\
-	 MV88E6XXX_FLAG_STU |		\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6165	\
-	(MV88E6XXX_FLAG_G1_ATU_FID |	\
-	 MV88E6XXX_FLAG_G1_VTU_FID |	\
+	(MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
 	 MV88E6XXX_FLAG_G2_POT |	\
-	 MV88E6XXX_FLAG_STU |		\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6185	\
 	(MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAG_VTU)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6320	\
 	(MV88E6XXX_FLAG_EEE |		\
@@ -634,64 +619,47 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
 	 MV88E6XXX_FLAG_G2_POT |	\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6341	\
 	(MV88E6XXX_FLAG_EEE |		\
-	 MV88E6XXX_FLAG_G1_ATU_FID |	\
 	 MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_POT |	\
-	 MV88E6XXX_FLAG_STU |		\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
 	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT |		\
 	 MV88E6XXX_FLAGS_SERDES)
 
 #define MV88E6XXX_FLAGS_FAMILY_6351	\
-	(MV88E6XXX_FLAG_G1_ATU_FID |	\
-	 MV88E6XXX_FLAG_G1_VTU_FID |	\
+	(MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
 	 MV88E6XXX_FLAG_G2_POT |	\
-	 MV88E6XXX_FLAG_STU |		\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6352	\
 	(MV88E6XXX_FLAG_EEE |		\
-	 MV88E6XXX_FLAG_G1_ATU_FID |	\
 	 MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_0X |	\
 	 MV88E6XXX_FLAG_G2_POT |	\
-	 MV88E6XXX_FLAG_STU |		\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
 	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT |		\
 	 MV88E6XXX_FLAGS_SERDES)
 
 #define MV88E6XXX_FLAGS_FAMILY_6390	\
 	(MV88E6XXX_FLAG_EEE |		\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |        \
-	 MV88E6XXX_FLAG_STU |		\
-	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 struct mv88e6xxx_ops;
 
@@ -701,20 +669,26 @@ struct mv88e6xxx_info {
 	const char *name;
 	unsigned int num_databases;
 	unsigned int num_ports;
+	unsigned int max_vid;
 	unsigned int port_base_addr;
 	unsigned int global1_addr;
 	unsigned int age_time_coeff;
 	unsigned int g1_irqs;
+	bool pvt;
 	enum dsa_tag_protocol tag_protocol;
 	unsigned long long flags;
+
+	/* Mask for FromPort and ToPort value of PortVec used in ATU Move
+	 * operation. 0 means that the ATU Move operation is not supported.
+	 */
+	u8 atu_move_port_mask;
 	const struct mv88e6xxx_ops *ops;
 };
 
 struct mv88e6xxx_atu_entry {
-	u16	fid;
 	u8	state;
 	bool	trunk;
-	u16	portv_trunkid;
+	u16	portvec;
 	u8	mac[ETH_ALEN];
 };
 
@@ -723,7 +697,8 @@ struct mv88e6xxx_vtu_entry {
 	u16	fid;
 	u8	sid;
 	bool	valid;
-	u8	data[DSA_MAX_PORTS];
+	u8	member[DSA_MAX_PORTS];
+	u8	state[DSA_MAX_PORTS];
 };
 
 struct mv88e6xxx_bus_ops;
@@ -864,14 +839,16 @@ struct mv88e6xxx_ops {
 
 	int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port,
 				   enum mv88e6xxx_frame_mode mode);
-	int (*port_set_egress_unknowns)(struct mv88e6xxx_chip *chip, int port,
-					bool on);
+	int (*port_set_egress_floods)(struct mv88e6xxx_chip *chip, int port,
+				      bool unicast, bool multicast);
 	int (*port_set_ether_type)(struct mv88e6xxx_chip *chip, int port,
 				   u16 etype);
 	int (*port_jumbo_config)(struct mv88e6xxx_chip *chip, int port);
 
 	int (*port_egress_rate_limiting)(struct mv88e6xxx_chip *chip, int port);
 	int (*port_pause_config)(struct mv88e6xxx_chip *chip, int port);
+	int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port);
+	int (*port_disable_pri_override)(struct mv88e6xxx_chip *chip, int port);
 
 	/* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc.
 	 * Some chips allow this to be configured on specific ports.
@@ -906,6 +883,12 @@ struct mv88e6xxx_ops {
 
 	/* Can be either in g1 or g2, so don't use a prefix */
 	int (*mgmt_rsvd2cpu)(struct mv88e6xxx_chip *chip);
+
+	/* VLAN Translation Unit operations */
+	int (*vtu_getnext)(struct mv88e6xxx_chip *chip,
+			   struct mv88e6xxx_vtu_entry *entry);
+	int (*vtu_loadpurge)(struct mv88e6xxx_chip *chip,
+			     struct mv88e6xxx_vtu_entry *entry);
 };
 
 struct mv88e6xxx_irq_ops {
@@ -934,6 +917,11 @@ static inline bool mv88e6xxx_has(struct mv88e6xxx_chip *chip,
 	return (chip->info->flags & flags) == flags;
 }
 
+static inline bool mv88e6xxx_has_pvt(struct mv88e6xxx_chip *chip)
+{
+	return chip->info->pvt;
+}
+
 static inline unsigned int mv88e6xxx_num_databases(struct mv88e6xxx_chip *chip)
 {
 	return chip->info->num_databases;
@@ -944,6 +932,11 @@ static inline unsigned int mv88e6xxx_num_ports(struct mv88e6xxx_chip *chip)
 	return chip->info->num_ports;
 }
 
+static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip)
+{
+	return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+}
+
 int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val);
 int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val);
 int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg,
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 8875784c4718..548a956637ee 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -497,8 +498,8 @@ int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
 }
 
-int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on)
+static int mv88e6185_port_set_forward_unknown(struct mv88e6xxx_chip *chip,
+					      int port, bool unicast)
 {
 	int err;
 	u16 reg;
@@ -507,7 +508,7 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (on)
+	if (unicast)
 		reg |= PORT_CONTROL_FORWARD_UNKNOWN;
 	else
 		reg &= ~PORT_CONTROL_FORWARD_UNKNOWN;
@@ -515,8 +516,8 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
 }
 
-int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on)
+int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast)
 {
 	int err;
 	u16 reg;
@@ -525,21 +526,45 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (on)
-		reg |= PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA;
+	reg &= ~PORT_CONTROL_EGRESS_FLOODS_MASK;
+
+	if (unicast && multicast)
+		reg |= PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA;
+	else if (unicast)
+		reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA;
+	else if (multicast)
+		reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA;
 	else
-		reg &= ~PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA;
+		reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA;
 
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
 }
 
 /* Offset 0x05: Port Control 1 */
 
+int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port,
+				    bool message_port)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, &val);
+	if (err)
+		return err;
+
+	if (message_port)
+		val |= PORT_CONTROL_1_MESSAGE_PORT;
+	else
+		val &= ~PORT_CONTROL_1_MESSAGE_PORT;
+
+	return mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, val);
+}
+
 /* Offset 0x06: Port Based VLAN Map */
 
 int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map)
 {
-	const u16 mask = GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+	const u16 mask = mv88e6xxx_port_mask(chip);
 	u16 reg;
 	int err;
 
@@ -672,8 +697,8 @@ static const char * const mv88e6xxx_port_8021q_mode_names[] = {
 	[PORT_CONTROL_2_8021Q_SECURE] = "Secure",
 };
 
-int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on)
+static int mv88e6185_port_set_default_forward(struct mv88e6xxx_chip *chip,
+					      int port, bool multicast)
 {
 	int err;
 	u16 reg;
@@ -682,14 +707,26 @@ int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (on)
-		reg |= PORT_CONTROL_2_FORWARD_UNKNOWN;
+	if (multicast)
+		reg |= PORT_CONTROL_2_DEFAULT_FORWARD;
 	else
-		reg &= ~PORT_CONTROL_2_FORWARD_UNKNOWN;
+		reg &= ~PORT_CONTROL_2_DEFAULT_FORWARD;
 
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg);
 }
 
+int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast)
+{
+	int err;
+
+	err = mv88e6185_port_set_forward_unknown(chip, port, unicast);
+	if (err)
+		return err;
+
+	return mv88e6185_port_set_default_forward(chip, port, multicast);
+}
+
 int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
 				     int upstream_port)
 {
@@ -769,6 +806,20 @@ int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port)
 	return mv88e6xxx_port_write(chip, port, PORT_RATE_CONTROL, 0x0001);
 }
 
+/* Offset 0x0C: Port ATU Control */
+
+int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, 0);
+}
+
+/* Offset 0x0D: (Priority) Override Register */
+
+int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, 0);
+}
+
 /* Offset 0x0f: Port Ether type */
 
 int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index c83cbb3f4491..86f40887b6d2 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -56,14 +57,14 @@ int mv88e6085_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
 				  enum mv88e6xxx_frame_mode mode);
 int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
 				  enum mv88e6xxx_frame_mode mode);
-int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on);
-int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on);
-int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on);
+int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast);
+int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast);
 int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port,
 				  u16 etype);
+int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port,
+				    bool message_port);
 int mv88e6165_port_jumbo_config(struct mv88e6xxx_chip *chip, int port);
 int mv88e6095_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port);
 int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port);
@@ -75,4 +76,8 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
 int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
 int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
 				     int upstream_port);
+
+int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port);
+int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port);
+
 #endif /* _MV88E6XXX_PORT_H */
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 2c80611b94ae..149244aac20a 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/moduleparam.h>
 #include <linux/rtnetlink.h>
+#include <linux/net_tstamp.h>
 #include <net/rtnetlink.h>
 #include <linux/u64_stats_sync.h>
 
@@ -125,6 +126,7 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 	dstats->tx_bytes += skb->len;
 	u64_stats_update_end(&dstats->syncp);
 
+	skb_tx_timestamp(skb);
 	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
@@ -304,8 +306,21 @@ static void dummy_get_drvinfo(struct net_device *dev,
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
+static int dummy_get_ts_info(struct net_device *dev,
+			      struct ethtool_ts_info *ts_info)
+{
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				   SOF_TIMESTAMPING_RX_SOFTWARE |
+				   SOF_TIMESTAMPING_SOFTWARE;
+
+	ts_info->phc_index = -1;
+
+	return 0;
+};
+
 static const struct ethtool_ops dummy_ethtool_ops = {
 	.get_drvinfo            = dummy_get_drvinfo,
+	.get_ts_info		= dummy_get_ts_info,
 };
 
 static void dummy_free_netdev(struct net_device *dev)
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index 084a6d58543a..be823c186517 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -283,7 +283,6 @@ struct typhoon {
 	spinlock_t		command_lock	____cacheline_aligned;
 	struct basic_ring	cmdRing;
 	struct basic_ring	respRing;
-	struct net_device_stats	stats;
 	struct net_device_stats	stats_saved;
 	struct typhoon_shared *	shared;
 	dma_addr_t		shared_dma;
@@ -898,7 +897,7 @@ typhoon_set_rx_mode(struct net_device *dev)
 static int
 typhoon_do_get_stats(struct typhoon *tp)
 {
-	struct net_device_stats *stats = &tp->stats;
+	struct net_device_stats *stats = &tp->dev->stats;
 	struct net_device_stats *saved = &tp->stats_saved;
 	struct cmd_desc xp_cmd;
 	struct resp_desc xp_resp[7];
@@ -951,7 +950,7 @@ static struct net_device_stats *
 typhoon_get_stats(struct net_device *dev)
 {
 	struct typhoon *tp = netdev_priv(dev);
-	struct net_device_stats *stats = &tp->stats;
+	struct net_device_stats *stats = &tp->dev->stats;
 	struct net_device_stats *saved = &tp->stats_saved;
 
 	smp_rmb();
@@ -1991,7 +1990,7 @@ typhoon_stop_runtime(struct typhoon *tp, int wait_type)
 	tp->card_state = Sleeping;
 	smp_wmb();
 	typhoon_do_get_stats(tp);
-	memcpy(&tp->stats_saved, &tp->stats, sizeof(struct net_device_stats));
+	memcpy(&tp->stats_saved, &tp->dev->stats, sizeof(struct net_device_stats));
 
 	INIT_COMMAND_NO_RESPONSE(&xp_cmd, TYPHOON_CMD_HALT);
 	typhoon_issue_command(tp, 1, &xp_cmd, 0, NULL);
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 8c08f9deef92..edae15ac0e98 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -180,5 +180,6 @@ source "drivers/net/ethernet/via/Kconfig"
 source "drivers/net/ethernet/wiznet/Kconfig"
 source "drivers/net/ethernet/xilinx/Kconfig"
 source "drivers/net/ethernet/xircom/Kconfig"
+source "drivers/net/ethernet/synopsys/Kconfig"
 
 endif # ETHERNET
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 26dce5bf2c18..bf7f4502cabc 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -91,3 +91,4 @@ obj-$(CONFIG_NET_VENDOR_VIA) += via/
 obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/
 obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/
 obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/
+obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/
diff --git a/drivers/net/ethernet/adi/bfin_mac.h b/drivers/net/ethernet/adi/bfin_mac.h
index 8c3b56198e4b..4ad5b9be3f84 100644
--- a/drivers/net/ethernet/adi/bfin_mac.h
+++ b/drivers/net/ethernet/adi/bfin_mac.h
@@ -68,13 +68,6 @@ struct net_dma_desc_tx {
 };
 
 struct bfin_mac_local {
-	/*
-	 * these are things that the kernel wants me to keep, so users
-	 * can find out semi-useless statistics of how well the card is
-	 * performing
-	 */
-	struct net_device_stats stats;
-
 	spinlock_t lock;
 
 	int wol;		/* Wake On Lan */
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 9f7422ada704..d8e133ced7b8 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -34,6 +34,7 @@
 #include <linux/crc32.h>
 #include <linux/mii.h>
 #include <linux/of_device.h>
+#include <linux/of_net.h>
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -1454,11 +1455,10 @@ static int greth_of_probe(struct platform_device *ofdev)
 			break;
 	}
 	if (i == 6) {
-		const unsigned char *addr;
-		int len;
-		addr = of_get_property(ofdev->dev.of_node, "local-mac-address",
-					&len);
-		if (addr != NULL && len == 6) {
+		const u8 *addr;
+
+		addr = of_get_mac_address(ofdev->dev.of_node);
+		if (addr) {
 			for (i = 0; i < 6; i++)
 				macaddr[i] = (unsigned int) addr[i];
 		} else {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 35f19430c84a..7c1214d78855 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -133,7 +133,7 @@ static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
 		int irq_idx = ENA_IO_IRQ_IDX(i);
 
 		rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
-				      adapter->msix_entries[irq_idx].vector);
+				      pci_irq_vector(adapter->pdev, irq_idx));
 		if (rc) {
 			free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
 			adapter->netdev->rx_cpu_rmap = NULL;
@@ -1208,13 +1208,7 @@ static irqreturn_t ena_intr_msix_io(int irq, void *data)
 
 static int ena_enable_msix(struct ena_adapter *adapter, int num_queues)
 {
-	int i, msix_vecs, rc;
-
-	if (test_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags)) {
-		netif_err(adapter, probe, adapter->netdev,
-			  "Error, MSI-X is already enabled\n");
-		return -EPERM;
-	}
+	int msix_vecs, rc;
 
 	/* Reserved the max msix vectors we might need */
 	msix_vecs = ENA_MAX_MSIX_VEC(num_queues);
@@ -1222,16 +1216,9 @@ static int ena_enable_msix(struct ena_adapter *adapter, int num_queues)
 	netif_dbg(adapter, probe, adapter->netdev,
 		  "trying to enable MSI-X, vectors %d\n", msix_vecs);
 
-	adapter->msix_entries = vzalloc(msix_vecs * sizeof(struct msix_entry));
-
-	if (!adapter->msix_entries)
-		return -ENOMEM;
-
-	for (i = 0; i < msix_vecs; i++)
-		adapter->msix_entries[i].entry = i;
-
-	rc = pci_enable_msix(adapter->pdev, adapter->msix_entries, msix_vecs);
-	if (rc != 0) {
+	rc = pci_alloc_irq_vectors(adapter->pdev, msix_vecs, msix_vecs,
+			PCI_IRQ_MSIX);
+	if (rc < 0) {
 		netif_err(adapter, probe, adapter->netdev,
 			  "Failed to enable MSI-X, vectors %d rc %d\n",
 			  msix_vecs, rc);
@@ -1248,7 +1235,6 @@ static int ena_enable_msix(struct ena_adapter *adapter, int num_queues)
 	}
 
 	adapter->msix_vecs = msix_vecs;
-	set_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags);
 
 	return 0;
 }
@@ -1264,7 +1250,7 @@ static void ena_setup_mgmnt_intr(struct ena_adapter *adapter)
 		ena_intr_msix_mgmnt;
 	adapter->irq_tbl[ENA_MGMNT_IRQ_IDX].data = adapter;
 	adapter->irq_tbl[ENA_MGMNT_IRQ_IDX].vector =
-		adapter->msix_entries[ENA_MGMNT_IRQ_IDX].vector;
+		pci_irq_vector(adapter->pdev, ENA_MGMNT_IRQ_IDX);
 	cpu = cpumask_first(cpu_online_mask);
 	adapter->irq_tbl[ENA_MGMNT_IRQ_IDX].cpu = cpu;
 	cpumask_set_cpu(cpu,
@@ -1287,7 +1273,7 @@ static void ena_setup_io_intr(struct ena_adapter *adapter)
 		adapter->irq_tbl[irq_idx].handler = ena_intr_msix_io;
 		adapter->irq_tbl[irq_idx].data = &adapter->ena_napi[i];
 		adapter->irq_tbl[irq_idx].vector =
-			adapter->msix_entries[irq_idx].vector;
+			pci_irq_vector(adapter->pdev, irq_idx);
 		adapter->irq_tbl[irq_idx].cpu = cpu;
 
 		cpumask_set_cpu(cpu,
@@ -1325,12 +1311,6 @@ static int ena_request_io_irq(struct ena_adapter *adapter)
 	struct ena_irq *irq;
 	int rc = 0, i, k;
 
-	if (!test_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags)) {
-		netif_err(adapter, ifup, adapter->netdev,
-			  "Failed to request I/O IRQ: MSI-X is not enabled\n");
-		return -EINVAL;
-	}
-
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) {
 		irq = &adapter->irq_tbl[i];
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
@@ -1389,16 +1369,6 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	}
 }
 
-static void ena_disable_msix(struct ena_adapter *adapter)
-{
-	if (test_and_clear_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags))
-		pci_disable_msix(adapter->pdev);
-
-	if (adapter->msix_entries)
-		vfree(adapter->msix_entries);
-	adapter->msix_entries = NULL;
-}
-
 static void ena_disable_io_intr_sync(struct ena_adapter *adapter)
 {
 	int i;
@@ -2479,8 +2449,7 @@ static int ena_enable_msix_and_set_admin_interrupts(struct ena_adapter *adapter,
 	return 0;
 
 err_disable_msix:
-	ena_disable_msix(adapter);
-
+	pci_free_irq_vectors(adapter->pdev);
 	return rc;
 }
 
@@ -2518,7 +2487,7 @@ static void ena_fw_reset_device(struct work_struct *work)
 
 	ena_free_mgmnt_irq(adapter);
 
-	ena_disable_msix(adapter);
+	pci_free_irq_vectors(adapter->pdev);
 
 	ena_com_abort_admin_commands(ena_dev);
 
@@ -2569,7 +2538,7 @@ static void ena_fw_reset_device(struct work_struct *work)
 	return;
 err_disable_msix:
 	ena_free_mgmnt_irq(adapter);
-	ena_disable_msix(adapter);
+	pci_free_irq_vectors(adapter->pdev);
 err_device_destroy:
 	ena_com_admin_destroy(ena_dev);
 err:
@@ -3103,7 +3072,7 @@ err_rss:
 err_free_msix:
 	ena_com_dev_reset(ena_dev);
 	ena_free_mgmnt_irq(adapter);
-	ena_disable_msix(adapter);
+	pci_free_irq_vectors(adapter->pdev);
 err_worker_destroy:
 	ena_com_destroy_interrupt_moderation(ena_dev);
 	del_timer(&adapter->timer_service);
@@ -3188,7 +3157,7 @@ static void ena_remove(struct pci_dev *pdev)
 
 	ena_free_mgmnt_irq(adapter);
 
-	ena_disable_msix(adapter);
+	pci_free_irq_vectors(adapter->pdev);
 
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index ed62d8e231a1..0e22bce6239d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -248,7 +248,6 @@ enum ena_flags_t {
 	ENA_FLAG_DEVICE_RUNNING,
 	ENA_FLAG_DEV_UP,
 	ENA_FLAG_LINK_UP,
-	ENA_FLAG_MSIX_ENABLED,
 	ENA_FLAG_TRIGGER_RESET
 };
 
@@ -267,7 +266,6 @@ struct ena_adapter {
 
 	int num_queues;
 
-	struct msix_entry *msix_entries;
 	int msix_vecs;
 
 	u32 tx_usecs, rx_usecs; /* interrupt moderation */
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index b556c926557a..9c152d85840d 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -359,7 +359,6 @@ typedef struct _mace_statistics {
 
 typedef struct _mace_private {
 	struct pcmcia_device	*p_dev;
-    struct net_device_stats linux_stats; /* Linux statistics counters */
     mace_statistics mace_stats; /* MACE chip statistics counters */
 
     /* restore_multicast_list() state variables */
@@ -879,7 +878,7 @@ static netdev_tx_t mace_start_xmit(struct sk_buff *skb,
        service a transmit interrupt while we are in here.
     */
 
-    lp->linux_stats.tx_bytes += skb->len;
+    dev->stats.tx_bytes += skb->len;
     lp->tx_free_frames--;
 
     /* WARNING: Write the _exact_ number of bytes written in the header! */
@@ -967,7 +966,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 
       fifofc = inb(ioaddr + AM2150_MACE_BASE + MACE_FIFOFC);
       if ((fifofc & MACE_FIFOFC_XMTFC)==0) {
-	lp->linux_stats.tx_errors++;
+	dev->stats.tx_errors++;
 	outb(0xFF, ioaddr + AM2150_XMT_SKIP);
       }
 
@@ -1016,7 +1015,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 
       } /* if (xmtfs & MACE_XMTFS_XMTSV) */
 
-      lp->linux_stats.tx_packets++;
+      dev->stats.tx_packets++;
       lp->tx_free_frames++;
       netif_wake_queue(dev);
     } /* if (status & MACE_IR_XMTINT) */
@@ -1077,7 +1076,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt)
 	  " 0x%X.\n", dev->name, rx_framecnt, rx_status);
 
     if (rx_status & MACE_RCVFS_RCVSTS) { /* Error, update stats. */
-      lp->linux_stats.rx_errors++;
+      dev->stats.rx_errors++;
       if (rx_status & MACE_RCVFS_OFLO) {
         lp->mace_stats.oflo++;
       }
@@ -1114,14 +1113,14 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt)
 	
 	netif_rx(skb); /* Send the packet to the upper (protocol) layers. */
 
-	lp->linux_stats.rx_packets++;
-	lp->linux_stats.rx_bytes += pkt_len;
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += pkt_len;
 	outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */
 	continue;
       } else {
 	pr_debug("%s: couldn't allocate a sk_buff of size"
 	      " %d.\n", dev->name, pkt_len);
-	lp->linux_stats.rx_dropped++;
+	dev->stats.rx_dropped++;
       }
     }
     outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */
@@ -1231,13 +1230,13 @@ static void update_stats(unsigned int ioaddr, struct net_device *dev)
   lp->mace_stats.rntpc += mace_read(lp, ioaddr, MACE_RNTPC);
   lp->mace_stats.mpc += mace_read(lp, ioaddr, MACE_MPC);
   /* At this point, mace_stats is fully updated for this call.
-     We may now update the linux_stats. */
+     We may now update the netdev stats. */
 
-  /* The MACE has no equivalent for linux_stats field which are commented
+  /* The MACE has no equivalent for netdev stats field which are commented
      out. */
 
-  /* lp->linux_stats.multicast; */
-  lp->linux_stats.collisions = 
+  /* dev->stats.multicast; */
+  dev->stats.collisions =
     lp->mace_stats.rcvcco * 256 + lp->mace_stats.rcvcc;
     /* Collision: The MACE may retry sending a packet 15 times
        before giving up.  The retry count is in XMTRC.
@@ -1245,22 +1244,22 @@ static void update_stats(unsigned int ioaddr, struct net_device *dev)
        If so, why doesn't the RCVCC record these collisions? */
 
   /* detailed rx_errors: */
-  lp->linux_stats.rx_length_errors = 
+  dev->stats.rx_length_errors =
     lp->mace_stats.rntpco * 256 + lp->mace_stats.rntpc;
-  /* lp->linux_stats.rx_over_errors */
-  lp->linux_stats.rx_crc_errors = lp->mace_stats.fcs;
-  lp->linux_stats.rx_frame_errors = lp->mace_stats.fram;
-  lp->linux_stats.rx_fifo_errors = lp->mace_stats.oflo;
-  lp->linux_stats.rx_missed_errors = 
+  /* dev->stats.rx_over_errors */
+  dev->stats.rx_crc_errors = lp->mace_stats.fcs;
+  dev->stats.rx_frame_errors = lp->mace_stats.fram;
+  dev->stats.rx_fifo_errors = lp->mace_stats.oflo;
+  dev->stats.rx_missed_errors =
     lp->mace_stats.mpco * 256 + lp->mace_stats.mpc;
 
   /* detailed tx_errors */
-  lp->linux_stats.tx_aborted_errors = lp->mace_stats.rtry;
-  lp->linux_stats.tx_carrier_errors = lp->mace_stats.lcar;
+  dev->stats.tx_aborted_errors = lp->mace_stats.rtry;
+  dev->stats.tx_carrier_errors = lp->mace_stats.lcar;
     /* LCAR usually results from bad cabling. */
-  lp->linux_stats.tx_fifo_errors = lp->mace_stats.uflo;
-  lp->linux_stats.tx_heartbeat_errors = lp->mace_stats.cerr;
-  /* lp->linux_stats.tx_window_errors; */
+  dev->stats.tx_fifo_errors = lp->mace_stats.uflo;
+  dev->stats.tx_heartbeat_errors = lp->mace_stats.cerr;
+  /* dev->stats.tx_window_errors; */
 } /* update_stats */
 
 /* ----------------------------------------------------------------------------
@@ -1274,10 +1273,10 @@ static struct net_device_stats *mace_get_stats(struct net_device *dev)
   update_stats(dev->base_addr, dev);
 
   pr_debug("%s: updating the statistics.\n", dev->name);
-  pr_linux_stats(&lp->linux_stats);
+  pr_linux_stats(&dev->stats);
   pr_mace_stats(&lp->mace_stats);
 
-  return &lp->linux_stats;
+  return &dev->stats;
 } /* net_device_stats */
 
 /* ----------------------------------------------------------------------------
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 8a280e7d66bd..127adbeefb10 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -984,29 +984,29 @@
 #define XP_ECC_CNT1_DESC_DED_WIDTH		8
 #define XP_ECC_CNT1_DESC_SEC_INDEX		0
 #define XP_ECC_CNT1_DESC_SEC_WIDTH		8
-#define XP_ECC_IER_DESC_DED_INDEX		0
+#define XP_ECC_IER_DESC_DED_INDEX		5
 #define XP_ECC_IER_DESC_DED_WIDTH		1
-#define XP_ECC_IER_DESC_SEC_INDEX		1
+#define XP_ECC_IER_DESC_SEC_INDEX		4
 #define XP_ECC_IER_DESC_SEC_WIDTH		1
-#define XP_ECC_IER_RX_DED_INDEX			2
+#define XP_ECC_IER_RX_DED_INDEX			3
 #define XP_ECC_IER_RX_DED_WIDTH			1
-#define XP_ECC_IER_RX_SEC_INDEX			3
+#define XP_ECC_IER_RX_SEC_INDEX			2
 #define XP_ECC_IER_RX_SEC_WIDTH			1
-#define XP_ECC_IER_TX_DED_INDEX			4
+#define XP_ECC_IER_TX_DED_INDEX			1
 #define XP_ECC_IER_TX_DED_WIDTH			1
-#define XP_ECC_IER_TX_SEC_INDEX			5
+#define XP_ECC_IER_TX_SEC_INDEX			0
 #define XP_ECC_IER_TX_SEC_WIDTH			1
-#define XP_ECC_ISR_DESC_DED_INDEX		0
+#define XP_ECC_ISR_DESC_DED_INDEX		5
 #define XP_ECC_ISR_DESC_DED_WIDTH		1
-#define XP_ECC_ISR_DESC_SEC_INDEX		1
+#define XP_ECC_ISR_DESC_SEC_INDEX		4
 #define XP_ECC_ISR_DESC_SEC_WIDTH		1
-#define XP_ECC_ISR_RX_DED_INDEX			2
+#define XP_ECC_ISR_RX_DED_INDEX			3
 #define XP_ECC_ISR_RX_DED_WIDTH			1
-#define XP_ECC_ISR_RX_SEC_INDEX			3
+#define XP_ECC_ISR_RX_SEC_INDEX			2
 #define XP_ECC_ISR_RX_SEC_WIDTH			1
-#define XP_ECC_ISR_TX_DED_INDEX			4
+#define XP_ECC_ISR_TX_DED_INDEX			1
 #define XP_ECC_ISR_TX_DED_WIDTH			1
-#define XP_ECC_ISR_TX_SEC_INDEX			5
+#define XP_ECC_ISR_TX_SEC_INDEX			0
 #define XP_ECC_ISR_TX_SEC_WIDTH			1
 #define XP_I2C_MUTEX_BUSY_INDEX			31
 #define XP_I2C_MUTEX_BUSY_WIDTH			1
@@ -1148,8 +1148,8 @@
 #define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX	2
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_LAST_INDEX		2
+#define RX_PACKET_ATTRIBUTES_LAST_WIDTH		1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX	3
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX	4
@@ -1158,6 +1158,8 @@
 #define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX	6
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_FIRST_INDEX	7
+#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH	1
 
 #define RX_NORMAL_DESC0_OVT_INDEX		0
 #define RX_NORMAL_DESC0_OVT_WIDTH		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 937f37a5dcb2..24a687ce4388 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1896,10 +1896,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 
 	/* Get the header length */
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 1);
 		rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
 						      RX_NORMAL_DESC2, HL);
 		if (rdata->rx.hdr_len)
 			pdata->ext_stats.rx_split_header_packets++;
+	} else {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 0);
 	}
 
 	/* Get the RSS hash */
@@ -1922,19 +1927,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 		}
 	}
 
-	/* Get the packet length */
-	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
-
-	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
-		/* Not all the data has been transferred for this packet */
-		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-			       INCOMPLETE, 1);
+	/* Not all the data has been transferred for this packet */
+	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD))
 		return 0;
-	}
 
 	/* This is the last of the data for this packet */
 	XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-		       INCOMPLETE, 0);
+		       LAST, 1);
+
+	/* Get the packet length */
+	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
 
 	/* Set checksum done indicator as appropriate */
 	if (netdev->features & NETIF_F_RXCSUM)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 248f60d171a5..c772420fa41c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -118,6 +118,7 @@
 #include <linux/spinlock.h>
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
+#include <linux/interrupt.h>
 #include <net/busy_poll.h>
 #include <linux/clk.h>
 #include <linux/if_ether.h>
@@ -1854,7 +1855,8 @@ static int xgbe_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 	if (tc_to_netdev->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	tc = tc_to_netdev->tc;
+	tc_to_netdev->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	tc = tc_to_netdev->mqprio->num_tc;
 
 	if (tc > pdata->hw_feat.tc_cnt)
 		return -EINVAL;
@@ -1971,13 +1973,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 {
 	struct sk_buff *skb;
 	u8 *packet;
-	unsigned int copy_len;
 
 	skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
 	if (!skb)
 		return NULL;
 
-	/* Start with the header buffer which may contain just the header
+	/* Pull in the header buffer which may contain just the header
 	 * or the header plus data
 	 */
 	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1986,30 +1987,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
-	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
-	skb_copy_to_linear_data(skb, packet, copy_len);
-	skb_put(skb, copy_len);
-
-	len -= copy_len;
-	if (len) {
-		/* Add the remaining data as a frag */
-		dma_sync_single_range_for_cpu(pdata->dev,
-					      rdata->rx.buf.dma_base,
-					      rdata->rx.buf.dma_off,
-					      rdata->rx.buf.dma_len,
-					      DMA_FROM_DEVICE);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				rdata->rx.buf.pa.pages,
-				rdata->rx.buf.pa.pages_offset,
-				len, rdata->rx.buf.dma_len);
-		rdata->rx.buf.pa.pages = NULL;
-	}
+	skb_copy_to_linear_data(skb, packet, len);
+	skb_put(skb, len);
 
 	return skb;
 }
 
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet)
+{
+	/* Always zero if not the first descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+		return 0;
+
+	/* First descriptor with split header, return header length */
+	if (rdata->rx.hdr_len)
+		return rdata->rx.hdr_len;
+
+	/* First descriptor but not the last descriptor and no split header,
+	 * so the full buffer was used
+	 */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.hdr.dma_len;
+
+	/* First descriptor and last descriptor and no split header, so
+	 * calculate how much of the buffer was used
+	 */
+	return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet,
+				     unsigned int len)
+{
+	/* Always the full buffer if not the last descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.buf.dma_len;
+
+	/* Last descriptor so calculate how much of the buffer was used
+	 * for the last bit of data
+	 */
+	return rdata->rx.len - len;
+}
+
 static int xgbe_tx_poll(struct xgbe_channel *channel)
 {
 	struct xgbe_prv_data *pdata = channel->pdata;
@@ -2092,8 +2112,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct napi_struct *napi;
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
-	unsigned int incomplete, error, context_next, context;
-	unsigned int len, rdesc_len, max_len;
+	unsigned int last, error, context_next, context;
+	unsigned int len, buf1_len, buf2_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -2103,7 +2123,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
-	incomplete = 0;
+	last = 0;
 	context_next = 0;
 
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -2137,9 +2157,8 @@ read_again:
 		received++;
 		ring->cur++;
 
-		incomplete = XGMAC_GET_BITS(packet->attributes,
-					    RX_PACKET_ATTRIBUTES,
-					    INCOMPLETE);
+		last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				      LAST);
 		context_next = XGMAC_GET_BITS(packet->attributes,
 					      RX_PACKET_ATTRIBUTES,
 					      CONTEXT_NEXT);
@@ -2148,7 +2167,7 @@ read_again:
 					 CONTEXT);
 
 		/* Earlier error, just drain the remaining data */
-		if ((incomplete || context_next) && error)
+		if ((!last || context_next) && error)
 			goto read_again;
 
 		if (error || packet->errors) {
@@ -2160,16 +2179,22 @@ read_again:
 		}
 
 		if (!context) {
-			/* Length is cumulative, get this descriptor's length */
-			rdesc_len = rdata->rx.len - len;
-			len += rdesc_len;
+			/* Get the data length in the descriptor buffers */
+			buf1_len = xgbe_rx_buf1_len(rdata, packet);
+			len += buf1_len;
+			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+			len += buf2_len;
 
-			if (rdesc_len && !skb) {
+			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
-						      rdesc_len);
-				if (!skb)
+						      buf1_len);
+				if (!skb) {
 					error = 1;
-			} else if (rdesc_len) {
+					goto skip_data;
+				}
+			}
+
+			if (buf2_len) {
 				dma_sync_single_range_for_cpu(pdata->dev,
 							rdata->rx.buf.dma_base,
 							rdata->rx.buf.dma_off,
@@ -2179,13 +2204,14 @@ read_again:
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						rdesc_len,
+						buf2_len,
 						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-		if (incomplete || context_next)
+skip_data:
+		if (!last || context_next)
 			goto read_again;
 
 		if (!skb)
@@ -2243,7 +2269,7 @@ next_packet:
 	}
 
 	/* Check if we need to save state before leaving */
-	if (received && (incomplete || context_next)) {
+	if (received && (!last || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
 		rdata->state.skb = skb;
@@ -2272,10 +2298,7 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget)
 	processed = xgbe_rx_poll(channel, budget);
 
 	/* If we processed everything, we are done */
-	if (processed < budget) {
-		/* Turn off polling */
-		napi_complete_done(napi, processed);
-
+	if ((processed < budget) && napi_complete_done(napi, processed)) {
 		/* Enable Tx and Rx interrupts */
 		if (pdata->channel_irq_mode)
 			xgbe_enable_rx_tx_int(pdata, channel);
@@ -2317,10 +2340,7 @@ static int xgbe_all_poll(struct napi_struct *napi, int budget)
 	} while ((processed < budget) && (processed != last_processed));
 
 	/* If we processed everything, we are done */
-	if (processed < budget) {
-		/* Turn off polling */
-		napi_complete_done(napi, processed);
-
+	if ((processed < budget) && napi_complete_done(napi, processed)) {
 		/* Enable Tx and Rx interrupts */
 		xgbe_enable_rx_tx_ints(pdata);
 	}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index 0c7088a426e9..417bdb5982a9 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -115,6 +115,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/completion.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 4c5b90eea4af..b672d9249539 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -114,6 +114,7 @@
  *     THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/kmod.h>
 #include <linux/mdio.h>
diff --git a/drivers/net/ethernet/apm/Kconfig b/drivers/net/ethernet/apm/Kconfig
index ec63d706d464..59efe5b145dd 100644
--- a/drivers/net/ethernet/apm/Kconfig
+++ b/drivers/net/ethernet/apm/Kconfig
@@ -1 +1,2 @@
 source "drivers/net/ethernet/apm/xgene/Kconfig"
+source "drivers/net/ethernet/apm/xgene-v2/Kconfig"
diff --git a/drivers/net/ethernet/apm/Makefile b/drivers/net/ethernet/apm/Makefile
index 65ce32ad1b2c..946b2a4c882d 100644
--- a/drivers/net/ethernet/apm/Makefile
+++ b/drivers/net/ethernet/apm/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-$(CONFIG_NET_XGENE) += xgene/
+obj-$(CONFIG_NET_XGENE_V2) += xgene-v2/
diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig
new file mode 100644
index 000000000000..1205861b6318
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig
@@ -0,0 +1,11 @@
+config NET_XGENE_V2
+	tristate "APM X-Gene SoC Ethernet-v2 Driver"
+	depends on HAS_DMA
+	depends on ARCH_XGENE || COMPILE_TEST
+	help
+	  This is the Ethernet driver for the on-chip ethernet interface
+	  which uses a linked list of DMA descriptor architecture (v2) for
+	  APM X-Gene SoCs.
+
+	  To compile this driver as a module, choose M here. This module will
+	  be called xgene-enet-v2.
diff --git a/drivers/net/ethernet/apm/xgene-v2/Makefile b/drivers/net/ethernet/apm/xgene-v2/Makefile
new file mode 100644
index 000000000000..f16a2b3dde8b
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for APM X-Gene Ethernet v2 driver
+#
+
+xgene-enet-v2-objs := main.o mac.o enet.o ring.o mdio.o ethtool.o
+obj-$(CONFIG_NET_XGENE_V2) += xgene-enet-v2.o
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.c b/drivers/net/ethernet/apm/xgene-v2/enet.c
new file mode 100644
index 000000000000..5998da014923
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.c
@@ -0,0 +1,83 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val)
+{
+	void __iomem *addr = pdata->resources.base_addr + offset;
+
+	iowrite32(val, addr);
+}
+
+u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset)
+{
+	void __iomem *addr = pdata->resources.base_addr + offset;
+
+	return ioread32(addr);
+}
+
+int xge_port_reset(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	u32 data, wait = 10;
+
+	xge_wr_csr(pdata, ENET_CLKEN, 0x3);
+	xge_wr_csr(pdata, ENET_SRST, 0xf);
+	xge_wr_csr(pdata, ENET_SRST, 0);
+	xge_wr_csr(pdata, CFG_MEM_RAM_SHUTDOWN, 1);
+	xge_wr_csr(pdata, CFG_MEM_RAM_SHUTDOWN, 0);
+
+	do {
+		usleep_range(100, 110);
+		data = xge_rd_csr(pdata, BLOCK_MEM_RDY);
+	} while (data != MEM_RDY && wait--);
+
+	if (data != MEM_RDY) {
+		dev_err(dev, "ECC init failed: %x\n", data);
+		return -ETIMEDOUT;
+	}
+
+	xge_wr_csr(pdata, ENET_SHIM, DEVM_ARAUX_COH | DEVM_AWAUX_COH);
+
+	return 0;
+}
+
+static void xge_traffic_resume(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	xge_wr_csr(pdata, CFG_FORCE_LINK_STATUS_EN, 1);
+	xge_wr_csr(pdata, FORCE_LINK_STATUS, 1);
+
+	xge_wr_csr(pdata, CFG_LINK_AGGR_RESUME, 1);
+	xge_wr_csr(pdata, RX_DV_GATE_REG, 1);
+}
+
+void xge_port_init(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	pdata->phy_speed = SPEED_1000;
+	xge_mac_init(pdata);
+	xge_traffic_resume(ndev);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.h b/drivers/net/ethernet/apm/xgene-v2/enet.h
new file mode 100644
index 000000000000..3fd36dc66a23
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.h
@@ -0,0 +1,45 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_ENET_H__
+#define __XGENE_ENET_V2_ENET_H__
+
+#define ENET_CLKEN		0xc008
+#define ENET_SRST		0xc000
+#define ENET_SHIM		0xc010
+#define CFG_MEM_RAM_SHUTDOWN	0xd070
+#define BLOCK_MEM_RDY		0xd074
+
+#define MEM_RDY			0xffffffff
+#define DEVM_ARAUX_COH		BIT(19)
+#define DEVM_AWAUX_COH		BIT(3)
+
+#define CFG_FORCE_LINK_STATUS_EN	0x229c
+#define FORCE_LINK_STATUS		0x22a0
+#define CFG_LINK_AGGR_RESUME		0x27c8
+#define RX_DV_GATE_REG			0x2dfc
+
+void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val);
+u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset);
+int xge_port_reset(struct net_device *ndev);
+void xge_port_init(struct net_device *ndev);
+
+#endif  /* __XGENE_ENET_V2_ENET__H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
new file mode 100644
index 000000000000..b6666e418e79
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
@@ -0,0 +1,187 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+#define XGE_STAT(m)		{ #m, offsetof(struct xge_pdata, stats.m) }
+#define XGE_EXTD_STAT(m, n)					\
+	{							\
+		#m,						\
+		n,						\
+		0						\
+	}
+
+static const struct xge_gstrings_stats gstrings_stats[] = {
+	XGE_STAT(rx_packets),
+	XGE_STAT(tx_packets),
+	XGE_STAT(rx_bytes),
+	XGE_STAT(tx_bytes),
+	XGE_STAT(rx_errors)
+};
+
+static struct xge_gstrings_extd_stats gstrings_extd_stats[] = {
+	XGE_EXTD_STAT(tx_rx_64b_frame_cntr, TR64),
+	XGE_EXTD_STAT(tx_rx_127b_frame_cntr, TR127),
+	XGE_EXTD_STAT(tx_rx_255b_frame_cntr, TR255),
+	XGE_EXTD_STAT(tx_rx_511b_frame_cntr, TR511),
+	XGE_EXTD_STAT(tx_rx_1023b_frame_cntr, TR1K),
+	XGE_EXTD_STAT(tx_rx_1518b_frame_cntr, TRMAX),
+	XGE_EXTD_STAT(tx_rx_1522b_frame_cntr, TRMGV),
+	XGE_EXTD_STAT(rx_fcs_error_cntr, RFCS),
+	XGE_EXTD_STAT(rx_multicast_pkt_cntr, RMCA),
+	XGE_EXTD_STAT(rx_broadcast_pkt_cntr, RBCA),
+	XGE_EXTD_STAT(rx_ctrl_frame_pkt_cntr, RXCF),
+	XGE_EXTD_STAT(rx_pause_frame_pkt_cntr, RXPF),
+	XGE_EXTD_STAT(rx_unk_opcode_cntr, RXUO),
+	XGE_EXTD_STAT(rx_align_err_cntr, RALN),
+	XGE_EXTD_STAT(rx_frame_len_err_cntr, RFLR),
+	XGE_EXTD_STAT(rx_code_err_cntr, RCDE),
+	XGE_EXTD_STAT(rx_carrier_sense_err_cntr, RCSE),
+	XGE_EXTD_STAT(rx_undersize_pkt_cntr, RUND),
+	XGE_EXTD_STAT(rx_oversize_pkt_cntr, ROVR),
+	XGE_EXTD_STAT(rx_fragments_cntr, RFRG),
+	XGE_EXTD_STAT(rx_jabber_cntr, RJBR),
+	XGE_EXTD_STAT(rx_dropped_pkt_cntr, RDRP),
+	XGE_EXTD_STAT(tx_multicast_pkt_cntr, TMCA),
+	XGE_EXTD_STAT(tx_broadcast_pkt_cntr, TBCA),
+	XGE_EXTD_STAT(tx_pause_ctrl_frame_cntr, TXPF),
+	XGE_EXTD_STAT(tx_defer_pkt_cntr, TDFR),
+	XGE_EXTD_STAT(tx_excv_defer_pkt_cntr, TEDF),
+	XGE_EXTD_STAT(tx_single_col_pkt_cntr, TSCL),
+	XGE_EXTD_STAT(tx_multi_col_pkt_cntr, TMCL),
+	XGE_EXTD_STAT(tx_late_col_pkt_cntr, TLCL),
+	XGE_EXTD_STAT(tx_excv_col_pkt_cntr, TXCL),
+	XGE_EXTD_STAT(tx_total_col_cntr, TNCL),
+	XGE_EXTD_STAT(tx_pause_frames_hnrd_cntr, TPFH),
+	XGE_EXTD_STAT(tx_drop_frame_cntr, TDRP),
+	XGE_EXTD_STAT(tx_jabber_frame_cntr, TJBR),
+	XGE_EXTD_STAT(tx_fcs_error_cntr, TFCS),
+	XGE_EXTD_STAT(tx_ctrl_frame_cntr, TXCF),
+	XGE_EXTD_STAT(tx_oversize_frame_cntr, TOVR),
+	XGE_EXTD_STAT(tx_undersize_frame_cntr, TUND),
+	XGE_EXTD_STAT(tx_fragments_cntr, TFRG)
+};
+
+#define XGE_STATS_LEN		ARRAY_SIZE(gstrings_stats)
+#define XGE_EXTD_STATS_LEN	ARRAY_SIZE(gstrings_extd_stats)
+
+static void xge_mac_get_extd_stats(struct xge_pdata *pdata)
+{
+	u32 data;
+	int i;
+
+	for (i = 0; i < XGE_EXTD_STATS_LEN; i++) {
+		data = xge_rd_csr(pdata, gstrings_extd_stats[i].addr);
+		gstrings_extd_stats[i].value += data;
+	}
+}
+
+static void xge_get_drvinfo(struct net_device *ndev,
+			    struct ethtool_drvinfo *info)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct platform_device *pdev = pdata->pdev;
+
+	strcpy(info->driver, "xgene-enet-v2");
+	strcpy(info->version, XGENE_ENET_V2_VERSION);
+	snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A");
+	sprintf(info->bus_info, "%s", pdev->name);
+}
+
+static void xge_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	u8 *p = data;
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < XGE_STATS_LEN; i++) {
+		memcpy(p, gstrings_stats[i].name, ETH_GSTRING_LEN);
+		p += ETH_GSTRING_LEN;
+	}
+
+	for (i = 0; i < XGE_EXTD_STATS_LEN; i++) {
+		memcpy(p, gstrings_extd_stats[i].name, ETH_GSTRING_LEN);
+		p += ETH_GSTRING_LEN;
+	}
+}
+
+static int xge_get_sset_count(struct net_device *ndev, int sset)
+{
+	if (sset != ETH_SS_STATS)
+		return -EINVAL;
+
+	return XGE_STATS_LEN + XGE_EXTD_STATS_LEN;
+}
+
+static void xge_get_ethtool_stats(struct net_device *ndev,
+				  struct ethtool_stats *dummy,
+				  u64 *data)
+{
+	void *pdata = netdev_priv(ndev);
+	int i;
+
+	for (i = 0; i < XGE_STATS_LEN; i++)
+		*data++ = *(u64 *)(pdata + gstrings_stats[i].offset);
+
+	xge_mac_get_extd_stats(pdata);
+
+	for (i = 0; i < XGE_EXTD_STATS_LEN; i++)
+		*data++ = gstrings_extd_stats[i].value;
+}
+
+static int xge_get_link_ksettings(struct net_device *ndev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	struct phy_device *phydev = ndev->phydev;
+
+	if (!phydev)
+		return -ENODEV;
+
+	return phy_ethtool_ksettings_get(phydev, cmd);
+}
+
+static int xge_set_link_ksettings(struct net_device *ndev,
+				  const struct ethtool_link_ksettings *cmd)
+{
+	struct phy_device *phydev = ndev->phydev;
+
+	if (!phydev)
+		return -ENODEV;
+
+	return phy_ethtool_ksettings_set(phydev, cmd);
+}
+
+static const struct ethtool_ops xge_ethtool_ops = {
+	.get_drvinfo = xge_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_strings = xge_get_strings,
+	.get_sset_count = xge_get_sset_count,
+	.get_ethtool_stats = xge_get_ethtool_stats,
+	.get_link_ksettings = xge_get_link_ksettings,
+	.set_link_ksettings = xge_set_link_ksettings,
+};
+
+void xge_set_ethtool_ops(struct net_device *ndev)
+{
+	ndev->ethtool_ops = &xge_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.h b/drivers/net/ethernet/apm/xgene-v2/ethtool.h
new file mode 100644
index 000000000000..54b48d5561b8
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.h
@@ -0,0 +1,78 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_ETHTOOL_H__
+#define __XGENE_ENET_V2_ETHTOOL_H__
+
+struct xge_gstrings_stats {
+	char name[ETH_GSTRING_LEN];
+	int offset;
+};
+
+struct xge_gstrings_extd_stats {
+	char name[ETH_GSTRING_LEN];
+	u32 addr;
+	u32 value;
+};
+
+#define TR64			0xa080
+#define TR127			0xa084
+#define TR255			0xa088
+#define TR511			0xa08c
+#define TR1K			0xa090
+#define TRMAX			0xa094
+#define TRMGV			0xa098
+#define RFCS			0xa0a4
+#define RMCA			0xa0a8
+#define RBCA			0xa0ac
+#define RXCF			0xa0b0
+#define RXPF			0xa0b4
+#define RXUO			0xa0b8
+#define RALN			0xa0bc
+#define RFLR			0xa0c0
+#define RCDE			0xa0c4
+#define RCSE			0xa0c8
+#define RUND			0xa0cc
+#define ROVR			0xa0d0
+#define RFRG			0xa0d4
+#define RJBR			0xa0d8
+#define RDRP			0xa0dc
+#define TMCA			0xa0e8
+#define TBCA			0xa0ec
+#define TXPF			0xa0f0
+#define TDFR			0xa0f4
+#define TEDF			0xa0f8
+#define TSCL			0xa0fc
+#define TMCL			0xa100
+#define TLCL			0xa104
+#define TXCL			0xa108
+#define TNCL			0xa10c
+#define TPFH			0xa110
+#define TDRP			0xa114
+#define TJBR			0xa118
+#define TFCS			0xa11c
+#define TXCF			0xa120
+#define TOVR			0xa124
+#define TUND			0xa128
+#define TFRG			0xa12c
+
+void xge_set_ethtool_ops(struct net_device *ndev);
+
+#endif  /* __XGENE_ENET_V2_ETHTOOL_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c
new file mode 100644
index 000000000000..ee431e397e57
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.c
@@ -0,0 +1,116 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+void xge_mac_reset(struct xge_pdata *pdata)
+{
+	xge_wr_csr(pdata, MAC_CONFIG_1, SOFT_RESET);
+	xge_wr_csr(pdata, MAC_CONFIG_1, 0);
+}
+
+void xge_mac_set_speed(struct xge_pdata *pdata)
+{
+	u32 icm0, icm2, ecm0, mc2;
+	u32 intf_ctrl, rgmii;
+
+	icm0 = xge_rd_csr(pdata, ICM_CONFIG0_REG_0);
+	icm2 = xge_rd_csr(pdata, ICM_CONFIG2_REG_0);
+	ecm0 = xge_rd_csr(pdata, ECM_CONFIG0_REG_0);
+	rgmii = xge_rd_csr(pdata, RGMII_REG_0);
+	mc2 = xge_rd_csr(pdata, MAC_CONFIG_2);
+	intf_ctrl = xge_rd_csr(pdata, INTERFACE_CONTROL);
+	icm2 |= CFG_WAITASYNCRD_EN;
+
+	switch (pdata->phy_speed) {
+	case SPEED_10:
+		SET_REG_BITS(&mc2, INTF_MODE, 1);
+		SET_REG_BITS(&intf_ctrl, HD_MODE, 0);
+		SET_REG_BITS(&icm0, CFG_MACMODE, 0);
+		SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 500);
+		SET_REG_BIT(&rgmii, CFG_SPEED_125, 0);
+		break;
+	case SPEED_100:
+		SET_REG_BITS(&mc2, INTF_MODE, 1);
+		SET_REG_BITS(&intf_ctrl, HD_MODE, 1);
+		SET_REG_BITS(&icm0, CFG_MACMODE, 1);
+		SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 80);
+		SET_REG_BIT(&rgmii, CFG_SPEED_125, 0);
+		break;
+	default:
+		SET_REG_BITS(&mc2, INTF_MODE, 2);
+		SET_REG_BITS(&intf_ctrl, HD_MODE, 2);
+		SET_REG_BITS(&icm0, CFG_MACMODE, 2);
+		SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 16);
+		SET_REG_BIT(&rgmii, CFG_SPEED_125, 1);
+		break;
+	}
+
+	mc2 |= FULL_DUPLEX | CRC_EN | PAD_CRC;
+	SET_REG_BITS(&ecm0, CFG_WFIFOFULLTHR, 0x32);
+
+	xge_wr_csr(pdata, MAC_CONFIG_2, mc2);
+	xge_wr_csr(pdata, INTERFACE_CONTROL, intf_ctrl);
+	xge_wr_csr(pdata, RGMII_REG_0, rgmii);
+	xge_wr_csr(pdata, ICM_CONFIG0_REG_0, icm0);
+	xge_wr_csr(pdata, ICM_CONFIG2_REG_0, icm2);
+	xge_wr_csr(pdata, ECM_CONFIG0_REG_0, ecm0);
+}
+
+void xge_mac_set_station_addr(struct xge_pdata *pdata)
+{
+	u8 *dev_addr = pdata->ndev->dev_addr;
+	u32 addr0, addr1;
+
+	addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) |
+		(dev_addr[1] << 8) | dev_addr[0];
+	addr1 = (dev_addr[5] << 24) | (dev_addr[4] << 16);
+
+	xge_wr_csr(pdata, STATION_ADDR0, addr0);
+	xge_wr_csr(pdata, STATION_ADDR1, addr1);
+}
+
+void xge_mac_init(struct xge_pdata *pdata)
+{
+	xge_mac_reset(pdata);
+	xge_mac_set_speed(pdata);
+	xge_mac_set_station_addr(pdata);
+}
+
+void xge_mac_enable(struct xge_pdata *pdata)
+{
+	u32 data;
+
+	data = xge_rd_csr(pdata, MAC_CONFIG_1);
+	data |= TX_EN | RX_EN;
+	xge_wr_csr(pdata, MAC_CONFIG_1, data);
+
+	data = xge_rd_csr(pdata, MAC_CONFIG_1);
+}
+
+void xge_mac_disable(struct xge_pdata *pdata)
+{
+	u32 data;
+
+	data = xge_rd_csr(pdata, MAC_CONFIG_1);
+	data &= ~(TX_EN | RX_EN);
+	xge_wr_csr(pdata, MAC_CONFIG_1, data);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h
new file mode 100644
index 000000000000..3c83fa617356
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.h
@@ -0,0 +1,107 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_MAC_H__
+#define __XGENE_ENET_V2_MAC_H__
+
+/* Register offsets */
+#define MAC_CONFIG_1		0xa000
+#define MAC_CONFIG_2		0xa004
+#define MII_MGMT_CONFIG		0xa020
+#define MII_MGMT_COMMAND	0xa024
+#define MII_MGMT_ADDRESS	0xa028
+#define MII_MGMT_CONTROL	0xa02c
+#define MII_MGMT_STATUS		0xa030
+#define MII_MGMT_INDICATORS	0xa034
+#define INTERFACE_CONTROL	0xa038
+#define STATION_ADDR0		0xa040
+#define STATION_ADDR1		0xa044
+
+#define RGMII_REG_0		0x27e0
+#define ICM_CONFIG0_REG_0	0x2c00
+#define ICM_CONFIG2_REG_0	0x2c08
+#define ECM_CONFIG0_REG_0	0x2d00
+
+/* Register fields */
+#define SOFT_RESET		BIT(31)
+#define TX_EN			BIT(0)
+#define RX_EN			BIT(2)
+#define PAD_CRC			BIT(2)
+#define CRC_EN			BIT(1)
+#define FULL_DUPLEX		BIT(0)
+
+#define INTF_MODE_POS		8
+#define INTF_MODE_LEN		2
+#define HD_MODE_POS		25
+#define HD_MODE_LEN		2
+#define CFG_MACMODE_POS		18
+#define CFG_MACMODE_LEN		2
+#define CFG_WAITASYNCRD_POS	0
+#define CFG_WAITASYNCRD_LEN	16
+#define CFG_SPEED_125_POS	24
+#define CFG_WFIFOFULLTHR_POS	0
+#define CFG_WFIFOFULLTHR_LEN	7
+#define MGMT_CLOCK_SEL_POS	0
+#define MGMT_CLOCK_SEL_LEN	3
+#define PHY_ADDR_POS		8
+#define PHY_ADDR_LEN		5
+#define REG_ADDR_POS		0
+#define REG_ADDR_LEN		5
+#define MII_MGMT_BUSY		BIT(0)
+#define MII_READ_CYCLE		BIT(0)
+#define CFG_WAITASYNCRD_EN	BIT(16)
+
+static inline void xgene_set_reg_bits(u32 *var, int pos, int len, u32 val)
+{
+	u32 mask = GENMASK(pos + len, pos);
+
+	*var &= ~mask;
+	*var |= ((val << pos) & mask);
+}
+
+static inline u32 xgene_get_reg_bits(u32 var, int pos, int len)
+{
+	u32 mask = GENMASK(pos + len, pos);
+
+	return (var & mask) >> pos;
+}
+
+#define SET_REG_BITS(var, field, val)					\
+	xgene_set_reg_bits(var, field ## _POS, field ## _LEN, val)
+
+#define SET_REG_BIT(var, field, val)					\
+	xgene_set_reg_bits(var, field ## _POS, 1, val)
+
+#define GET_REG_BITS(var, field)					\
+	xgene_get_reg_bits(var, field ## _POS, field ## _LEN)
+
+#define GET_REG_BIT(var, field)		((var) & (field))
+
+struct xge_pdata;
+
+void xge_mac_reset(struct xge_pdata *pdata);
+void xge_mac_set_speed(struct xge_pdata *pdata);
+void xge_mac_enable(struct xge_pdata *pdata);
+void xge_mac_disable(struct xge_pdata *pdata);
+void xge_mac_init(struct xge_pdata *pdata);
+void xge_mac_set_station_addr(struct xge_pdata *pdata);
+
+#endif /* __XGENE_ENET_V2_MAC_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
new file mode 100644
index 000000000000..0f2ad50f3bd7
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -0,0 +1,759 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+static const struct acpi_device_id xge_acpi_match[];
+
+static int xge_get_resources(struct xge_pdata *pdata)
+{
+	struct platform_device *pdev;
+	struct net_device *ndev;
+	int phy_mode, ret = 0;
+	struct resource *res;
+	struct device *dev;
+
+	pdev = pdata->pdev;
+	dev = &pdev->dev;
+	ndev = pdata->ndev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Resource enet_csr not defined\n");
+		return -ENODEV;
+	}
+
+	pdata->resources.base_addr = devm_ioremap(dev, res->start,
+						  resource_size(res));
+	if (!pdata->resources.base_addr) {
+		dev_err(dev, "Unable to retrieve ENET Port CSR region\n");
+		return -ENOMEM;
+	}
+
+	if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN))
+		eth_hw_addr_random(ndev);
+
+	memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len);
+
+	phy_mode = device_get_phy_mode(dev);
+	if (phy_mode < 0) {
+		dev_err(dev, "Unable to get phy-connection-type\n");
+		return phy_mode;
+	}
+	pdata->resources.phy_mode = phy_mode;
+
+	if (pdata->resources.phy_mode != PHY_INTERFACE_MODE_RGMII) {
+		dev_err(dev, "Incorrect phy-connection-type specified\n");
+		return -ENODEV;
+	}
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
+		dev_err(dev, "Unable to get irq\n");
+		return ret;
+	}
+	pdata->resources.irq = ret;
+
+	return 0;
+}
+
+static int xge_refill_buffers(struct net_device *ndev, u32 nbuf)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	const u8 slots = XGENE_ENET_NUM_DESC - 1;
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_raw_desc *raw_desc;
+	u64 addr_lo, addr_hi;
+	u8 tail = ring->tail;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	u16 len;
+	int i;
+
+	for (i = 0; i < nbuf; i++) {
+		raw_desc = &ring->raw_desc[tail];
+
+		len = XGENE_ENET_STD_MTU;
+		skb = netdev_alloc_skb(ndev, len);
+		if (unlikely(!skb))
+			return -ENOMEM;
+
+		dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE);
+		if (dma_mapping_error(dev, dma_addr)) {
+			netdev_err(ndev, "DMA mapping error\n");
+			dev_kfree_skb_any(skb);
+			return -EINVAL;
+		}
+
+		ring->pkt_info[tail].skb = skb;
+		ring->pkt_info[tail].dma_addr = dma_addr;
+
+		addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+		addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+		raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+					   SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+					   SET_BITS(PKT_ADDRH,
+						    upper_32_bits(dma_addr)));
+
+		dma_wmb();
+		raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+					   SET_BITS(E, 1));
+		tail = (tail + 1) & slots;
+	}
+
+	ring->tail = tail;
+
+	return 0;
+}
+
+static int xge_init_hw(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = xge_port_reset(ndev);
+	if (ret)
+		return ret;
+
+	xge_port_init(ndev);
+	pdata->nbufs = NUM_BUFS;
+
+	return 0;
+}
+
+static irqreturn_t xge_irq(const int irq, void *data)
+{
+	struct xge_pdata *pdata = data;
+
+	if (napi_schedule_prep(&pdata->napi)) {
+		xge_intr_disable(pdata);
+		__napi_schedule(&pdata->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int xge_request_irq(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	snprintf(pdata->irq_name, IRQ_ID_SIZE, "%s", ndev->name);
+
+	ret = request_irq(pdata->resources.irq, xge_irq, 0, pdata->irq_name,
+			  pdata);
+	if (ret)
+		netdev_err(ndev, "Failed to request irq %s\n", pdata->irq_name);
+
+	return ret;
+}
+
+static void xge_free_irq(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	free_irq(pdata->resources.irq, pdata);
+}
+
+static bool is_tx_slot_available(struct xge_raw_desc *raw_desc)
+{
+	if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+	    (GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)) == SLOT_EMPTY))
+		return true;
+
+	return false;
+}
+
+static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	static dma_addr_t dma_addr;
+	u64 addr_lo, addr_hi;
+	void *pkt_buf;
+	u8 tail;
+	u16 len;
+
+	tx_ring = pdata->tx_ring;
+	tail = tx_ring->tail;
+	len = skb_headlen(skb);
+	raw_desc = &tx_ring->raw_desc[tail];
+
+	if (!is_tx_slot_available(raw_desc)) {
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Packet buffers should be 64B aligned */
+	pkt_buf = dma_zalloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr,
+				      GFP_ATOMIC);
+	if (unlikely(!pkt_buf)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+	memcpy(pkt_buf, skb->data, len);
+
+	addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+	addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+	raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+				   SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+				   SET_BITS(PKT_ADDRH,
+					    upper_32_bits(dma_addr)));
+
+	tx_ring->pkt_info[tail].skb = skb;
+	tx_ring->pkt_info[tail].dma_addr = dma_addr;
+	tx_ring->pkt_info[tail].pkt_buf = pkt_buf;
+
+	dma_wmb();
+
+	raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+				   SET_BITS(PKT_SIZE, len) |
+				   SET_BITS(E, 0));
+	skb_tx_timestamp(skb);
+	xge_wr_csr(pdata, DMATXCTRL, 1);
+
+	tx_ring->tail = (tail + 1) & (XGENE_ENET_NUM_DESC - 1);
+
+	return NETDEV_TX_OK;
+}
+
+static bool is_tx_hw_done(struct xge_raw_desc *raw_desc)
+{
+	if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+	    !GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)))
+		return true;
+
+	return false;
+}
+
+static void xge_txc_poll(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+	void *pkt_buf;
+	u32 data;
+	u8 head;
+
+	tx_ring = pdata->tx_ring;
+	head = tx_ring->head;
+
+	data = xge_rd_csr(pdata, DMATXSTATUS);
+	if (!GET_BITS(TXPKTCOUNT, data))
+		return;
+
+	while (1) {
+		raw_desc = &tx_ring->raw_desc[head];
+
+		if (!is_tx_hw_done(raw_desc))
+			break;
+
+		dma_rmb();
+
+		skb = tx_ring->pkt_info[head].skb;
+		dma_addr = tx_ring->pkt_info[head].dma_addr;
+		pkt_buf = tx_ring->pkt_info[head].pkt_buf;
+		pdata->stats.tx_packets++;
+		pdata->stats.tx_bytes += skb->len;
+		dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+		dev_kfree_skb_any(skb);
+
+		/* clear pktstart address and pktsize */
+		raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+					   SET_BITS(PKT_SIZE, SLOT_EMPTY));
+		xge_wr_csr(pdata, DMATXSTATUS, 1);
+
+		head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+	}
+
+	if (netif_queue_stopped(ndev))
+		netif_wake_queue(ndev);
+
+	tx_ring->head = head;
+}
+
+static int xge_rx_poll(struct net_device *ndev, unsigned int budget)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *rx_ring;
+	struct xge_raw_desc *raw_desc;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int processed = 0;
+	u8 head, rx_error;
+	int i, ret;
+	u32 data;
+	u16 len;
+
+	rx_ring = pdata->rx_ring;
+	head = rx_ring->head;
+
+	data = xge_rd_csr(pdata, DMARXSTATUS);
+	if (!GET_BITS(RXPKTCOUNT, data))
+		return 0;
+
+	for (i = 0; i < budget; i++) {
+		raw_desc = &rx_ring->raw_desc[head];
+
+		if (GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+			break;
+
+		dma_rmb();
+
+		skb = rx_ring->pkt_info[head].skb;
+		rx_ring->pkt_info[head].skb = NULL;
+		dma_addr = rx_ring->pkt_info[head].dma_addr;
+		len = GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0));
+		dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+				 DMA_FROM_DEVICE);
+
+		rx_error = GET_BITS(D, le64_to_cpu(raw_desc->m2));
+		if (unlikely(rx_error)) {
+			pdata->stats.rx_errors++;
+			dev_kfree_skb_any(skb);
+			goto out;
+		}
+
+		skb_put(skb, len);
+		skb->protocol = eth_type_trans(skb, ndev);
+
+		pdata->stats.rx_packets++;
+		pdata->stats.rx_bytes += len;
+		napi_gro_receive(&pdata->napi, skb);
+out:
+		ret = xge_refill_buffers(ndev, 1);
+		xge_wr_csr(pdata, DMARXSTATUS, 1);
+		xge_wr_csr(pdata, DMARXCTRL, 1);
+
+		if (ret)
+			break;
+
+		head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+		processed++;
+	}
+
+	rx_ring->head = head;
+
+	return processed;
+}
+
+static void xge_delete_desc_ring(struct net_device *ndev,
+				 struct xge_desc_ring *ring)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	u16 size;
+
+	if (!ring)
+		return;
+
+	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+	if (ring->desc_addr)
+		dma_free_coherent(dev, size, ring->desc_addr, ring->dma_addr);
+
+	kfree(ring->pkt_info);
+	kfree(ring);
+}
+
+static void xge_free_buffers(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	struct device *dev = &pdata->pdev->dev;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int i;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		skb = ring->pkt_info[i].skb;
+		dma_addr = ring->pkt_info[i].dma_addr;
+
+		if (!skb)
+			continue;
+
+		dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void xge_delete_desc_rings(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	xge_txc_poll(ndev);
+	xge_delete_desc_ring(ndev, pdata->tx_ring);
+
+	xge_rx_poll(ndev, 64);
+	xge_free_buffers(ndev);
+	xge_delete_desc_ring(ndev, pdata->rx_ring);
+}
+
+static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *ring;
+	u16 size;
+
+	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	ring->ndev = ndev;
+
+	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+	ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma_addr,
+					      GFP_KERNEL);
+	if (!ring->desc_addr)
+		goto err;
+
+	ring->pkt_info = kcalloc(XGENE_ENET_NUM_DESC, sizeof(*ring->pkt_info),
+				 GFP_KERNEL);
+	if (!ring->pkt_info)
+		goto err;
+
+	xge_setup_desc(ring);
+
+	return ring;
+
+err:
+	xge_delete_desc_ring(ndev, ring);
+
+	return NULL;
+}
+
+static int xge_create_desc_rings(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring;
+	int ret;
+
+	/* create tx ring */
+	ring = xge_create_desc_ring(ndev);
+	if (!ring)
+		goto err;
+
+	pdata->tx_ring = ring;
+	xge_update_tx_desc_addr(pdata);
+
+	/* create rx ring */
+	ring = xge_create_desc_ring(ndev);
+	if (!ring)
+		goto err;
+
+	pdata->rx_ring = ring;
+	xge_update_rx_desc_addr(pdata);
+
+	ret = xge_refill_buffers(ndev, XGENE_ENET_NUM_DESC);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	xge_delete_desc_rings(ndev);
+
+	return -ENOMEM;
+}
+
+static int xge_open(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = xge_create_desc_rings(ndev);
+	if (ret)
+		return ret;
+
+	napi_enable(&pdata->napi);
+	ret = xge_request_irq(ndev);
+	if (ret)
+		return ret;
+
+	xge_intr_enable(pdata);
+	xge_wr_csr(pdata, DMARXCTRL, 1);
+
+	phy_start(ndev->phydev);
+	xge_mac_enable(pdata);
+	netif_start_queue(ndev);
+
+	return 0;
+}
+
+static int xge_close(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	xge_mac_disable(pdata);
+	phy_stop(ndev->phydev);
+
+	xge_intr_disable(pdata);
+	xge_free_irq(ndev);
+	napi_disable(&pdata->napi);
+	xge_delete_desc_rings(ndev);
+
+	return 0;
+}
+
+static int xge_napi(struct napi_struct *napi, const int budget)
+{
+	struct net_device *ndev = napi->dev;
+	struct xge_pdata *pdata;
+	int processed;
+
+	pdata = netdev_priv(ndev);
+
+	xge_txc_poll(ndev);
+	processed = xge_rx_poll(ndev, budget);
+
+	if (processed < budget) {
+		napi_complete_done(napi, processed);
+		xge_intr_enable(pdata);
+	}
+
+	return processed;
+}
+
+static int xge_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = eth_mac_addr(ndev, addr);
+	if (ret)
+		return ret;
+
+	xge_mac_set_station_addr(pdata);
+
+	return 0;
+}
+
+static bool is_tx_pending(struct xge_raw_desc *raw_desc)
+{
+	if (!GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+		return true;
+
+	return false;
+}
+
+static void xge_free_pending_skb(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+	void *pkt_buf;
+	int i;
+
+	tx_ring = pdata->tx_ring;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		raw_desc = &tx_ring->raw_desc[i];
+
+		if (!is_tx_pending(raw_desc))
+			continue;
+
+		skb = tx_ring->pkt_info[i].skb;
+		dma_addr = tx_ring->pkt_info[i].dma_addr;
+		pkt_buf = tx_ring->pkt_info[i].pkt_buf;
+		dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void xge_timeout(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	rtnl_lock();
+
+	if (!netif_running(ndev))
+		goto out;
+
+	netif_stop_queue(ndev);
+	xge_intr_disable(pdata);
+	napi_disable(&pdata->napi);
+
+	xge_wr_csr(pdata, DMATXCTRL, 0);
+	xge_txc_poll(ndev);
+	xge_free_pending_skb(ndev);
+	xge_wr_csr(pdata, DMATXSTATUS, ~0U);
+
+	xge_setup_desc(pdata->tx_ring);
+	xge_update_tx_desc_addr(pdata);
+	xge_mac_init(pdata);
+
+	napi_enable(&pdata->napi);
+	xge_intr_enable(pdata);
+	xge_mac_enable(pdata);
+	netif_start_queue(ndev);
+
+out:
+	rtnl_unlock();
+}
+
+static void xge_get_stats64(struct net_device *ndev,
+			    struct rtnl_link_stats64 *storage)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_stats *stats = &pdata->stats;
+
+	storage->tx_packets += stats->tx_packets;
+	storage->tx_bytes += stats->tx_bytes;
+
+	storage->rx_packets += stats->rx_packets;
+	storage->rx_bytes += stats->rx_bytes;
+	storage->rx_errors += stats->rx_errors;
+}
+
+static const struct net_device_ops xgene_ndev_ops = {
+	.ndo_open = xge_open,
+	.ndo_stop = xge_close,
+	.ndo_start_xmit = xge_start_xmit,
+	.ndo_set_mac_address = xge_set_mac_addr,
+	.ndo_tx_timeout = xge_timeout,
+	.ndo_get_stats64 = xge_get_stats64,
+};
+
+static int xge_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct net_device *ndev;
+	struct xge_pdata *pdata;
+	int ret;
+
+	ndev = alloc_etherdev(sizeof(*pdata));
+	if (!ndev)
+		return -ENOMEM;
+
+	pdata = netdev_priv(ndev);
+
+	pdata->pdev = pdev;
+	pdata->ndev = ndev;
+	SET_NETDEV_DEV(ndev, dev);
+	platform_set_drvdata(pdev, pdata);
+	ndev->netdev_ops = &xgene_ndev_ops;
+
+	ndev->features |= NETIF_F_GSO |
+			  NETIF_F_GRO;
+
+	ret = xge_get_resources(pdata);
+	if (ret)
+		goto err;
+
+	ndev->hw_features = ndev->features;
+	xge_set_ethtool_ops(ndev);
+
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		netdev_err(ndev, "No usable DMA configuration\n");
+		goto err;
+	}
+
+	ret = xge_init_hw(ndev);
+	if (ret)
+		goto err;
+
+	ret = xge_mdio_config(ndev);
+	if (ret)
+		goto err;
+
+	netif_napi_add(ndev, &pdata->napi, xge_napi, NAPI_POLL_WEIGHT);
+
+	ret = register_netdev(ndev);
+	if (ret) {
+		netdev_err(ndev, "Failed to register netdev\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	free_netdev(ndev);
+
+	return ret;
+}
+
+static int xge_remove(struct platform_device *pdev)
+{
+	struct xge_pdata *pdata;
+	struct net_device *ndev;
+
+	pdata = platform_get_drvdata(pdev);
+	ndev = pdata->ndev;
+
+	rtnl_lock();
+	if (netif_running(ndev))
+		dev_close(ndev);
+	rtnl_unlock();
+
+	xge_mdio_remove(ndev);
+	unregister_netdev(ndev);
+	free_netdev(ndev);
+
+	return 0;
+}
+
+static void xge_shutdown(struct platform_device *pdev)
+{
+	struct xge_pdata *pdata;
+
+	pdata = platform_get_drvdata(pdev);
+	if (!pdata)
+		return;
+
+	if (!pdata->ndev)
+		return;
+
+	xge_remove(pdev);
+}
+
+static const struct acpi_device_id xge_acpi_match[] = {
+	{ "APMC0D80" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
+
+static struct platform_driver xge_driver = {
+	.driver = {
+		   .name = "xgene-enet-v2",
+		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+	},
+	.probe = xge_probe,
+	.remove = xge_remove,
+	.shutdown = xge_shutdown,
+};
+module_platform_driver(xge_driver);
+
+MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver");
+MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>");
+MODULE_VERSION(XGENE_ENET_V2_VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h
new file mode 100644
index 000000000000..969b258cb7de
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.h
@@ -0,0 +1,80 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_MAIN_H__
+#define __XGENE_ENET_V2_MAIN_H__
+
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/efi.h>
+#include <linux/if_vlan.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/prefetch.h>
+#include <linux/phy.h>
+#include <net/ip.h>
+#include "mac.h"
+#include "enet.h"
+#include "ring.h"
+#include "ethtool.h"
+
+#define XGENE_ENET_V2_VERSION	"v1.0"
+#define XGENE_ENET_STD_MTU	1536
+#define XGENE_ENET_MIN_FRAME	60
+#define IRQ_ID_SIZE             16
+
+struct xge_resource {
+	void __iomem *base_addr;
+	int phy_mode;
+	u32 irq;
+};
+
+struct xge_stats {
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 rx_errors;
+};
+
+/* ethernet private data */
+struct xge_pdata {
+	struct xge_resource resources;
+	struct xge_desc_ring *tx_ring;
+	struct xge_desc_ring *rx_ring;
+	struct platform_device *pdev;
+	char irq_name[IRQ_ID_SIZE];
+	struct mii_bus *mdio_bus;
+	struct net_device *ndev;
+	struct napi_struct napi;
+	struct xge_stats stats;
+	int phy_speed;
+	u8 nbufs;
+};
+
+int xge_mdio_config(struct net_device *ndev);
+void xge_mdio_remove(struct net_device *ndev);
+
+#endif /* __XGENE_ENET_V2_MAIN_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
new file mode 100644
index 000000000000..f5fe3bb2e59d
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -0,0 +1,168 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+static int xge_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 data)
+{
+	struct xge_pdata *pdata = bus->priv;
+	u32 done, val = 0;
+	u8 wait = 10;
+
+	SET_REG_BITS(&val, PHY_ADDR, phy_id);
+	SET_REG_BITS(&val, REG_ADDR, reg);
+	xge_wr_csr(pdata, MII_MGMT_ADDRESS, val);
+
+	xge_wr_csr(pdata, MII_MGMT_CONTROL, data);
+	do {
+		usleep_range(5, 10);
+		done = xge_rd_csr(pdata, MII_MGMT_INDICATORS);
+	} while ((done & MII_MGMT_BUSY) && wait--);
+
+	if (done & MII_MGMT_BUSY) {
+		dev_err(&bus->dev, "MII_MGMT write failed\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int xge_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+{
+	struct xge_pdata *pdata = bus->priv;
+	u32 data, done, val = 0;
+	u8 wait = 10;
+
+	SET_REG_BITS(&val, PHY_ADDR, phy_id);
+	SET_REG_BITS(&val, REG_ADDR, reg);
+	xge_wr_csr(pdata, MII_MGMT_ADDRESS, val);
+
+	xge_wr_csr(pdata, MII_MGMT_COMMAND, MII_READ_CYCLE);
+	do {
+		usleep_range(5, 10);
+		done = xge_rd_csr(pdata, MII_MGMT_INDICATORS);
+	} while ((done & MII_MGMT_BUSY) && wait--);
+
+	if (done & MII_MGMT_BUSY) {
+		dev_err(&bus->dev, "MII_MGMT read failed\n");
+		return -ETIMEDOUT;
+	}
+
+	data = xge_rd_csr(pdata, MII_MGMT_STATUS);
+	xge_wr_csr(pdata, MII_MGMT_COMMAND, 0);
+
+	return data;
+}
+
+static void xge_adjust_link(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct phy_device *phydev = ndev->phydev;
+
+	if (phydev->link) {
+		if (pdata->phy_speed != phydev->speed) {
+			pdata->phy_speed = phydev->speed;
+			xge_mac_set_speed(pdata);
+			xge_mac_enable(pdata);
+			phy_print_status(phydev);
+		}
+	} else {
+		if (pdata->phy_speed != SPEED_UNKNOWN) {
+			pdata->phy_speed = SPEED_UNKNOWN;
+			xge_mac_disable(pdata);
+			phy_print_status(phydev);
+		}
+	}
+}
+
+void xge_mdio_remove(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct mii_bus *mdio_bus = pdata->mdio_bus;
+
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
+
+	if (mdio_bus->state == MDIOBUS_REGISTERED)
+		mdiobus_unregister(mdio_bus);
+
+	mdiobus_free(mdio_bus);
+}
+
+int xge_mdio_config(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct mii_bus *mdio_bus;
+	struct phy_device *phydev;
+	int ret;
+
+	mdio_bus = mdiobus_alloc();
+	if (!mdio_bus)
+		return -ENOMEM;
+
+	mdio_bus->name = "APM X-Gene Ethernet (v2) MDIO Bus";
+	mdio_bus->read = xge_mdio_read;
+	mdio_bus->write = xge_mdio_write;
+	mdio_bus->priv = pdata;
+	mdio_bus->parent = dev;
+	snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev));
+	pdata->mdio_bus = mdio_bus;
+
+	mdio_bus->phy_mask = 0x1;
+	ret = mdiobus_register(mdio_bus);
+	if (ret)
+		goto err;
+
+	phydev = phy_find_first(mdio_bus);
+	if (!phydev) {
+		dev_err(dev, "no PHY found\n");
+		ret = -ENODEV;
+		goto err;
+	}
+	phydev = phy_connect(ndev, phydev_name(phydev),
+			     &xge_adjust_link,
+			     pdata->resources.phy_mode);
+
+	if (IS_ERR(phydev)) {
+		netdev_err(ndev, "Could not attach to PHY\n");
+		ret = PTR_ERR(phydev);
+		goto err;
+	}
+
+	phydev->supported &= ~(SUPPORTED_10baseT_Half |
+			       SUPPORTED_10baseT_Full |
+			       SUPPORTED_100baseT_Half |
+			       SUPPORTED_100baseT_Full |
+			       SUPPORTED_1000baseT_Half |
+			       SUPPORTED_AUI |
+			       SUPPORTED_MII |
+			       SUPPORTED_FIBRE |
+			       SUPPORTED_BNC);
+	phydev->advertising = phydev->supported;
+	pdata->phy_speed = SPEED_UNKNOWN;
+
+	return 0;
+err:
+	xge_mdio_remove(ndev);
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.c b/drivers/net/ethernet/apm/xgene-v2/ring.c
new file mode 100644
index 000000000000..38810828f8f0
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.c
@@ -0,0 +1,81 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+/* create circular linked list of descriptors */
+void xge_setup_desc(struct xge_desc_ring *ring)
+{
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_h, next_dma;
+	u16 offset;
+	int i;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		raw_desc = &ring->raw_desc[i];
+
+		offset = (i + 1) & (XGENE_ENET_NUM_DESC - 1);
+		next_dma = ring->dma_addr + (offset * XGENE_ENET_DESC_SIZE);
+
+		raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+					   SET_BITS(PKT_SIZE, SLOT_EMPTY));
+		dma_h = upper_32_bits(next_dma);
+		raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, next_dma) |
+					   SET_BITS(NEXT_DESC_ADDRH, dma_h));
+	}
+}
+
+void xge_update_tx_desc_addr(struct xge_pdata *pdata)
+{
+	struct xge_desc_ring *ring = pdata->tx_ring;
+	dma_addr_t dma_addr = ring->dma_addr;
+
+	xge_wr_csr(pdata, DMATXDESCL, dma_addr);
+	xge_wr_csr(pdata, DMATXDESCH, upper_32_bits(dma_addr));
+
+	ring->head = 0;
+	ring->tail = 0;
+}
+
+void xge_update_rx_desc_addr(struct xge_pdata *pdata)
+{
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	dma_addr_t dma_addr = ring->dma_addr;
+
+	xge_wr_csr(pdata, DMARXDESCL, dma_addr);
+	xge_wr_csr(pdata, DMARXDESCH, upper_32_bits(dma_addr));
+
+	ring->head = 0;
+	ring->tail = 0;
+}
+
+void xge_intr_enable(struct xge_pdata *pdata)
+{
+	u32 data;
+
+	data = RX_PKT_RCVD | TX_PKT_SENT;
+	xge_wr_csr(pdata, DMAINTRMASK, data);
+}
+
+void xge_intr_disable(struct xge_pdata *pdata)
+{
+	xge_wr_csr(pdata, DMAINTRMASK, 0);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.h b/drivers/net/ethernet/apm/xgene-v2/ring.h
new file mode 100644
index 000000000000..abc8c9a84954
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.h
@@ -0,0 +1,119 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_RING_H__
+#define __XGENE_ENET_V2_RING_H__
+
+#define XGENE_ENET_DESC_SIZE	64
+#define XGENE_ENET_NUM_DESC	256
+#define NUM_BUFS		8
+#define SLOT_EMPTY		0xfff
+
+#define DMATXCTRL		0xa180
+#define DMATXDESCL		0xa184
+#define DMATXDESCH		0xa1a0
+#define DMATXSTATUS		0xa188
+#define DMARXCTRL		0xa18c
+#define DMARXDESCL		0xa190
+#define DMARXDESCH		0xa1a4
+#define DMARXSTATUS		0xa194
+#define DMAINTRMASK		0xa198
+#define DMAINTERRUPT		0xa19c
+
+#define D_POS			62
+#define D_LEN			2
+#define E_POS			63
+#define E_LEN			1
+#define PKT_ADDRL_POS		0
+#define PKT_ADDRL_LEN		32
+#define PKT_ADDRH_POS		32
+#define PKT_ADDRH_LEN		10
+#define PKT_SIZE_POS		32
+#define PKT_SIZE_LEN		12
+#define NEXT_DESC_ADDRL_POS	0
+#define NEXT_DESC_ADDRL_LEN	32
+#define NEXT_DESC_ADDRH_POS	48
+#define NEXT_DESC_ADDRH_LEN	10
+
+#define TXPKTCOUNT_POS		16
+#define TXPKTCOUNT_LEN		8
+#define RXPKTCOUNT_POS		16
+#define RXPKTCOUNT_LEN		8
+
+#define TX_PKT_SENT		BIT(0)
+#define TX_BUS_ERROR		BIT(3)
+#define RX_PKT_RCVD		BIT(4)
+#define RX_BUS_ERROR		BIT(7)
+#define RXSTATUS_RXPKTRCVD	BIT(0)
+
+struct xge_raw_desc {
+	__le64 m0;
+	__le64 m1;
+	__le64 m2;
+	__le64 m3;
+	__le64 m4;
+	__le64 m5;
+	__le64 m6;
+	__le64 m7;
+};
+
+struct pkt_info {
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	void *pkt_buf;
+};
+
+/* software context of a descriptor ring */
+struct xge_desc_ring {
+	struct net_device *ndev;
+	dma_addr_t dma_addr;
+	u8 head;
+	u8 tail;
+	union {
+		void *desc_addr;
+		struct xge_raw_desc *raw_desc;
+	};
+	struct pkt_info (*pkt_info);
+};
+
+static inline u64 xge_set_desc_bits(int pos, int len, u64 val)
+{
+	return (val & ((1ULL << len) - 1)) << pos;
+}
+
+static inline u64 xge_get_desc_bits(int pos, int len, u64 src)
+{
+	return (src >> pos) & ((1ULL << len) - 1);
+}
+
+#define SET_BITS(field, val) \
+		xge_set_desc_bits(field ## _POS, field ## _LEN, val)
+
+#define GET_BITS(field, src) \
+		xge_get_desc_bits(field ## _POS, field ## _LEN, src)
+
+void xge_setup_desc(struct xge_desc_ring *ring);
+void xge_update_tx_desc_addr(struct xge_pdata *pdata);
+void xge_update_rx_desc_addr(struct xge_pdata *pdata);
+void xge_intr_enable(struct xge_pdata *pdata);
+void xge_intr_disable(struct xge_pdata *pdata);
+
+#endif  /* __XGENE_ENET_V2_RING_H__ */
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index 06e681697c17..2a835e07adfb 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -494,7 +494,7 @@ static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata)
 		break;
 	}
 
-	mc2 |= FULL_DUPLEX2 | PAD_CRC;
+	mc2 |= FULL_DUPLEX2 | PAD_CRC | LENGTH_CHK;
 	xgene_enet_wr_mcx_mac(pdata, MAC_CONFIG_2_ADDR, mc2);
 	xgene_enet_wr_mcx_mac(pdata, INTERFACE_CONTROL_ADDR, intf_ctl);
 	xgene_enet_wr_csr(pdata, RGMII_REG_0_ADDR, rgmii);
@@ -623,6 +623,7 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *pdata,
 	xgene_enet_rd_csr(pdata, CLE_BYPASS_REG0_0_ADDR, &cb);
 	cb |= CFG_CLE_BYPASS_EN0;
 	CFG_CLE_IP_PROTOCOL0_SET(&cb, 3);
+	CFG_CLE_IP_HDR_LEN_SET(&cb, 0);
 	xgene_enet_wr_csr(pdata, CLE_BYPASS_REG0_0_ADDR, cb);
 
 	xgene_enet_rd_csr(pdata, CLE_BYPASS_REG1_0_ADDR, &cb);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
index 5f83037bb96b..d250bfe94d24 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
@@ -163,6 +163,7 @@ enum xgene_enet_rm {
 #define CFG_RXCLK_MUXSEL0_SET(dst, val)	xgene_set_bits(dst, val, 26, 3)
 
 #define CFG_CLE_IP_PROTOCOL0_SET(dst, val)	xgene_set_bits(dst, val, 16, 2)
+#define CFG_CLE_IP_HDR_LEN_SET(dst, val)	xgene_set_bits(dst, val, 8, 5)
 #define CFG_CLE_DSTQID0_SET(dst, val)		xgene_set_bits(dst, val, 0, 12)
 #define CFG_CLE_FPSEL0_SET(dst, val)		xgene_set_bits(dst, val, 16, 4)
 #define CFG_CLE_NXTFPSEL0_SET(dst, val)		xgene_set_bits(dst, val, 20, 4)
@@ -215,6 +216,7 @@ enum xgene_enet_rm {
 #define ENET_GHD_MODE			BIT(26)
 #define FULL_DUPLEX2			BIT(0)
 #define PAD_CRC				BIT(2)
+#define LENGTH_CHK			BIT(4)
 #define SCAN_AUTO_INCR			BIT(5)
 #define TBYT_ADDR			0x38
 #define TPKT_ADDR			0x39
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index b3568c453b14..5f37ed3506d5 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -601,14 +601,24 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static void xgene_enet_skip_csum(struct sk_buff *skb)
+static void xgene_enet_rx_csum(struct sk_buff *skb)
 {
+	struct net_device *ndev = skb->dev;
 	struct iphdr *iph = ip_hdr(skb);
 
-	if (!ip_is_fragment(iph) ||
-	    (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-	}
+	if (!(ndev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return;
+
+	if (ip_is_fragment(iph))
+		return;
+
+	if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
+		return;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 }
 
 static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool,
@@ -648,12 +658,24 @@ static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool,
 	buf_pool->head = head;
 }
 
+/* Errata 10GE_8 and ENET_11 - allow packet with length <=64B */
+static bool xgene_enet_errata_10GE_8(struct sk_buff *skb, u32 len, u8 status)
+{
+	if (status == INGRESS_PKT_LEN && len == ETHER_MIN_PACKET) {
+		if (ntohs(eth_hdr(skb)->h_proto) < 46)
+			return true;
+	}
+
+	return false;
+}
+
 static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 			       struct xgene_enet_raw_desc *raw_desc,
 			       struct xgene_enet_raw_desc *exp_desc)
 {
 	struct xgene_enet_desc_ring *buf_pool, *page_pool;
 	u32 datalen, frag_size, skb_index;
+	struct xgene_enet_pdata *pdata;
 	struct net_device *ndev;
 	dma_addr_t dma_addr;
 	struct sk_buff *skb;
@@ -666,6 +688,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 	bool nv;
 
 	ndev = rx_ring->ndev;
+	pdata = netdev_priv(ndev);
 	dev = ndev_to_dev(rx_ring->ndev);
 	buf_pool = rx_ring->buf_pool;
 	page_pool = rx_ring->page_pool;
@@ -676,30 +699,29 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 	skb = buf_pool->rx_skb[skb_index];
 	buf_pool->rx_skb[skb_index] = NULL;
 
+	datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1));
+	skb_put(skb, datalen);
+	prefetch(skb->data - NET_IP_ALIGN);
+	skb->protocol = eth_type_trans(skb, ndev);
+
 	/* checking for error */
-	status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) ||
+	status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) |
 		  GET_VAL(LERR, le64_to_cpu(raw_desc->m0));
-	if (unlikely(status > 2)) {
-		dev_kfree_skb_any(skb);
-		xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc);
-		xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev),
-				       status);
-		ret = -EIO;
-		goto out;
+	if (unlikely(status)) {
+		if (!xgene_enet_errata_10GE_8(skb, datalen, status)) {
+			dev_kfree_skb_any(skb);
+			xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc);
+			xgene_enet_parse_error(rx_ring, pdata, status);
+			goto out;
+		}
 	}
 
-	/* strip off CRC as HW isn't doing this */
-	datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1));
-
 	nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0));
-	if (!nv)
+	if (!nv) {
+		/* strip off CRC as HW isn't doing this */
 		datalen -= 4;
-
-	skb_put(skb, datalen);
-	prefetch(skb->data - NET_IP_ALIGN);
-
-	if (!nv)
 		goto skip_jumbo;
+	}
 
 	slots = page_pool->slots - 1;
 	head = page_pool->head;
@@ -728,11 +750,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 
 skip_jumbo:
 	skb_checksum_none_assert(skb);
-	skb->protocol = eth_type_trans(skb, ndev);
-	if (likely((ndev->features & NETIF_F_IP_CSUM) &&
-		   skb->protocol == htons(ETH_P_IP))) {
-		xgene_enet_skip_csum(skb);
-	}
+	xgene_enet_rx_csum(skb);
 
 	rx_ring->rx_packets++;
 	rx_ring->rx_bytes += datalen;
@@ -2039,7 +2057,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	xgene_enet_setup_ops(pdata);
 
 	if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) {
-		ndev->features |= NETIF_F_TSO;
+		ndev->features |= NETIF_F_TSO | NETIF_F_RXCSUM;
 		spin_lock_init(&pdata->mss_lock);
 	}
 	ndev->hw_features = ndev->features;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index 52571741da9f..0d4be2425ebc 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -41,6 +41,7 @@
 #include "../../../phy/mdio-xgene.h"
 
 #define XGENE_DRV_VERSION	"v1.0"
+#define ETHER_MIN_PACKET	64
 #define XGENE_ENET_STD_MTU	1536
 #define XGENE_ENET_MAX_MTU	9600
 #define SKB_BUFFER_SIZE		(XGENE_ENET_STD_MTU - NET_IP_ALIGN)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index ece19e6d68e3..423240c97d39 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -341,8 +341,15 @@ static void xgene_xgmac_init(struct xgene_enet_pdata *pdata)
 
 	xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, &data);
 	data |= CFG_RSIF_FPBUFF_TIMEOUT_EN;
+	/* Errata 10GE_1 - FIFO threshold default value incorrect */
+	RSIF_CLE_BUFF_THRESH_SET(&data, XG_RSIF_CLE_BUFF_THRESH);
 	xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, data);
 
+	/* Errata 10GE_1 - FIFO threshold default value incorrect */
+	xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, &data);
+	RSIF_PLC_CLE_BUFF_THRESH_SET(&data, XG_RSIF_PLC_CLE_BUFF_THRESH);
+	xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, data);
+
 	xgene_enet_rd_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, &data);
 	data |= BIT(12);
 	xgene_enet_wr_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, data);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
index 03b847ad8937..e644a429ebf4 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
@@ -65,6 +65,11 @@
 #define XG_DEF_PAUSE_THRES		0x390
 #define XG_DEF_PAUSE_OFF_THRES		0x2c0
 #define XG_RSIF_CONFIG_REG_ADDR		0x00a0
+#define XG_RSIF_CLE_BUFF_THRESH                0x3
+#define RSIF_CLE_BUFF_THRESH_SET(dst, val)     xgene_set_bits(dst, val, 0, 3)
+#define XG_RSIF_CONFIG1_REG_ADDR       0x00b8
+#define XG_RSIF_PLC_CLE_BUFF_THRESH    0x1
+#define RSIF_PLC_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 2)
 #define XCLE_BYPASS_REG0_ADDR           0x0160
 #define XCLE_BYPASS_REG1_ADDR           0x0164
 #define XG_CFG_BYPASS_ADDR		0x0204
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index dad63623be6a..5d6c40d86775 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -98,11 +98,7 @@ static int aq_ndev_change_mtu(struct net_device *ndev, int new_mtu)
 
 	if (err < 0)
 		goto err_exit;
-
-	if (netif_running(ndev)) {
-		aq_ndev_close(ndev);
-		aq_ndev_open(ndev);
-	}
+	ndev->mtu = new_mtu;
 
 err_exit:
 	return err;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index ee78444bfb88..cdb02991f249 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -487,6 +487,9 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 		dx_buff->mss = skb_shinfo(skb)->gso_size;
 		dx_buff->is_txc = 1U;
 
+		dx_buff->is_ipv6 =
+			(ip_hdr(skb)->version == 6) ? 1U : 0U;
+
 		dx = aq_ring_next_dx(ring, dx);
 		dx_buff = &ring->buff_ring[dx];
 		++ret;
@@ -510,10 +513,22 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		dx_buff->is_ip_cso = (htons(ETH_P_IP) == skb->protocol) ?
 			1U : 0U;
-		dx_buff->is_tcp_cso =
-			(ip_hdr(skb)->protocol == IPPROTO_TCP) ? 1U : 0U;
-		dx_buff->is_udp_cso =
-			(ip_hdr(skb)->protocol == IPPROTO_UDP) ? 1U : 0U;
+
+		if (ip_hdr(skb)->version == 4) {
+			dx_buff->is_tcp_cso =
+				(ip_hdr(skb)->protocol == IPPROTO_TCP) ?
+					1U : 0U;
+			dx_buff->is_udp_cso =
+				(ip_hdr(skb)->protocol == IPPROTO_UDP) ?
+					1U : 0U;
+		} else if (ip_hdr(skb)->version == 6) {
+			dx_buff->is_tcp_cso =
+				(ipv6_hdr(skb)->nexthdr == NEXTHDR_TCP) ?
+					1U : 0U;
+			dx_buff->is_udp_cso =
+				(ipv6_hdr(skb)->nexthdr == NEXTHDR_UDP) ?
+					1U : 0U;
+		}
 	}
 
 	for (; nr_frags--; ++frag_count) {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 581de71a958a..4c6c882c6a1c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -213,9 +213,9 @@ void aq_pci_func_free_irqs(struct aq_pci_func_s *self)
 		if (!((1U << i) & self->msix_entry_mask))
 			continue;
 
-		free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
 		if (pdev->msix_enabled)
 			irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL);
+		free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
 		self->msix_entry_mask &= ~(1U << i);
 	}
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 0358e6072d45..3a8a4aa13687 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -101,6 +101,7 @@ int aq_ring_init(struct aq_ring_s *self)
 	self->hw_head = 0;
 	self->sw_head = 0;
 	self->sw_tail = 0;
+	spin_lock_init(&self->header.lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 257254645068..eecd6d1c4d73 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -58,7 +58,8 @@ struct __packed aq_ring_buff_s {
 			u8 len_l2;
 			u8 len_l3;
 			u8 len_l4;
-			u8 rsvd2;
+			u8 is_ipv6:1;
+			u8 rsvd2:7;
 			u32 len_pkt;
 		};
 	};
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index a2b746a2dd50..4ee15ff06a44 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -433,6 +433,9 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self,
 				    buff->len_l3 +
 				    buff->len_l2);
 			is_gso = true;
+
+			if (buff->is_ipv6)
+				txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_IPV6;
 		} else {
 			buff_pa_len = buff->len;
 
@@ -458,6 +461,7 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self,
 			if (unlikely(buff->is_eop)) {
 				txd->ctl |= HW_ATL_A0_TXD_CTL_EOP;
 				txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_WB;
+				is_gso = false;
 			}
 		}
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
index 1093ea18823a..0592a0330cf0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
@@ -137,6 +137,7 @@ static struct aq_hw_caps_s hw_atl_a0_hw_caps_ = {
 	.tx_rings = HW_ATL_A0_TX_RINGS,
 	.rx_rings = HW_ATL_A0_RX_RINGS,
 	.hw_features = NETIF_F_HW_CSUM |
+			NETIF_F_RXCSUM |
 			NETIF_F_RXHASH |
 			NETIF_F_SG |
 			NETIF_F_TSO,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index cab2931dab9a..42150708191d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -471,6 +471,9 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
 				    buff->len_l3 +
 				    buff->len_l2);
 			is_gso = true;
+
+			if (buff->is_ipv6)
+				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6;
 		} else {
 			buff_pa_len = buff->len;
 
@@ -496,6 +499,7 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
 			if (unlikely(buff->is_eop)) {
 				txd->ctl |= HW_ATL_B0_TXD_CTL_EOP;
 				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB;
+				is_gso = false;
 			}
 		}
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index 8bdee3ddd5a0..f3957e930340 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -188,6 +188,7 @@ static struct aq_hw_caps_s hw_atl_b0_hw_caps_ = {
 	.tx_rings = HW_ATL_B0_TX_RINGS,
 	.rx_rings = HW_ATL_B0_RX_RINGS,
 	.hw_features = NETIF_F_HW_CSUM |
+			NETIF_F_RXCSUM |
 			NETIF_F_RXHASH |
 			NETIF_F_SG |
 			NETIF_F_TSO |
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 23873395f100..68de2f2652f2 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -434,7 +434,7 @@ static int arc_emac_open(struct net_device *ndev)
 	/* Enable EMAC */
 	arc_reg_or(priv, R_CTRL, EN_MASK);
 
-	phy_start_aneg(ndev->phydev);
+	phy_start(ndev->phydev);
 
 	netif_start_queue(ndev);
 
@@ -556,6 +556,8 @@ static int arc_emac_stop(struct net_device *ndev)
 	napi_disable(&priv->napi);
 	netif_stop_queue(ndev);
 
+	phy_stop(ndev->phydev);
+
 	/* Disable interrupts */
 	arc_reg_clr(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK);
 
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index d4a409139ea2..78c5de467426 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -102,9 +102,6 @@ struct alx_napi {
 
 #define ALX_MAX_NAPIS 8
 
-#define ALX_FLAG_USING_MSIX	BIT(0)
-#define ALX_FLAG_USING_MSI	BIT(1)
-
 struct alx_priv {
 	struct net_device *dev;
 
@@ -112,7 +109,6 @@ struct alx_priv {
 
 	/* msi-x vectors */
 	int num_vec;
-	struct msix_entry *msix_entries;
 
 	/* all descriptor memory */
 	struct {
@@ -139,8 +135,6 @@ struct alx_priv {
 
 	u16 msg_enable;
 
-	int flags;
-
 	/* protects hw.stats */
 	spinlock_t stats_lock;
 };
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 6a27c2662675..a8c2db881b75 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -314,7 +314,7 @@ static int alx_poll(struct napi_struct *napi, int budget)
 	napi_complete_done(&np->napi, work);
 
 	/* enable interrupt */
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
+	if (alx->hw.pdev->msix_enabled) {
 		alx_mask_msix(hw, np->vec_idx, false);
 	} else {
 		spin_lock_irqsave(&alx->irq_lock, flags);
@@ -811,7 +811,7 @@ static void alx_config_vector_mapping(struct alx_priv *alx)
 	u32 tbl[2] = {0, 0};
 	int i, vector, idx, shift;
 
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
+	if (alx->hw.pdev->msix_enabled) {
 		/* tx mappings */
 		for (i = 0, vector = 1; i < alx->num_txq; i++, vector++) {
 			idx = txq_vec_mapping_shift[i * 2];
@@ -828,29 +828,19 @@ static void alx_config_vector_mapping(struct alx_priv *alx)
 	alx_write_mem32(hw, ALX_MSI_ID_MAP, 0);
 }
 
-static bool alx_enable_msix(struct alx_priv *alx)
+static int alx_enable_msix(struct alx_priv *alx)
 {
-	int i, err, num_vec, num_txq, num_rxq;
+	int err, num_vec, num_txq, num_rxq;
 
 	num_txq = min_t(int, num_online_cpus(), ALX_MAX_TX_QUEUES);
 	num_rxq = 1;
 	num_vec = max_t(int, num_txq, num_rxq) + 1;
 
-	alx->msix_entries = kcalloc(num_vec, sizeof(struct msix_entry),
-				    GFP_KERNEL);
-	if (!alx->msix_entries) {
-		netdev_warn(alx->dev, "Allocation of msix entries failed!\n");
-		return false;
-	}
-
-	for (i = 0; i < num_vec; i++)
-		alx->msix_entries[i].entry = i;
-
-	err = pci_enable_msix(alx->hw.pdev, alx->msix_entries, num_vec);
+	err = pci_alloc_irq_vectors(alx->hw.pdev, num_vec, num_vec,
+			PCI_IRQ_MSIX);
 	if (err) {
-		kfree(alx->msix_entries);
 		netdev_warn(alx->dev, "Enabling MSI-X interrupts failed!\n");
-		return false;
+		return err;
 	}
 
 	alx->num_vec = num_vec;
@@ -858,7 +848,7 @@ static bool alx_enable_msix(struct alx_priv *alx)
 	alx->num_txq = num_txq;
 	alx->num_rxq = num_rxq;
 
-	return true;
+	return err;
 }
 
 static int alx_request_msix(struct alx_priv *alx)
@@ -866,7 +856,7 @@ static int alx_request_msix(struct alx_priv *alx)
 	struct net_device *netdev = alx->dev;
 	int i, err, vector = 0, free_vector = 0;
 
-	err = request_irq(alx->msix_entries[0].vector, alx_intr_msix_misc,
+	err = request_irq(pci_irq_vector(alx->hw.pdev, 0), alx_intr_msix_misc,
 			  0, netdev->name, alx);
 	if (err)
 		goto out_err;
@@ -889,7 +879,7 @@ static int alx_request_msix(struct alx_priv *alx)
 			sprintf(np->irq_lbl, "%s-unused", netdev->name);
 
 		np->vec_idx = vector;
-		err = request_irq(alx->msix_entries[vector].vector,
+		err = request_irq(pci_irq_vector(alx->hw.pdev, vector),
 				  alx_intr_msix_ring, 0, np->irq_lbl, np);
 		if (err)
 			goto out_free;
@@ -897,47 +887,31 @@ static int alx_request_msix(struct alx_priv *alx)
 	return 0;
 
 out_free:
-	free_irq(alx->msix_entries[free_vector++].vector, alx);
+	free_irq(pci_irq_vector(alx->hw.pdev, free_vector++), alx);
 
 	vector--;
 	for (i = 0; i < vector; i++)
-		free_irq(alx->msix_entries[free_vector++].vector,
+		free_irq(pci_irq_vector(alx->hw.pdev,free_vector++),
 			 alx->qnapi[i]);
 
 out_err:
 	return err;
 }
 
-static void alx_init_intr(struct alx_priv *alx, bool msix)
+static int alx_init_intr(struct alx_priv *alx)
 {
-	if (msix) {
-		if (alx_enable_msix(alx))
-			alx->flags |= ALX_FLAG_USING_MSIX;
-	}
+	int ret;
 
-	if (!(alx->flags & ALX_FLAG_USING_MSIX)) {
-		alx->num_vec = 1;
-		alx->num_napi = 1;
-		alx->num_txq = 1;
-		alx->num_rxq = 1;
-
-		if (!pci_enable_msi(alx->hw.pdev))
-			alx->flags |= ALX_FLAG_USING_MSI;
-	}
-}
-
-static void alx_disable_advanced_intr(struct alx_priv *alx)
-{
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
-		kfree(alx->msix_entries);
-		pci_disable_msix(alx->hw.pdev);
-		alx->flags &= ~ALX_FLAG_USING_MSIX;
-	}
+	ret = pci_alloc_irq_vectors(alx->hw.pdev, 1, 1,
+			PCI_IRQ_MSI | PCI_IRQ_LEGACY);
+	if (ret)
+		return ret;
 
-	if (alx->flags & ALX_FLAG_USING_MSI) {
-		pci_disable_msi(alx->hw.pdev);
-		alx->flags &= ~ALX_FLAG_USING_MSI;
-	}
+	alx->num_vec = 1;
+	alx->num_napi = 1;
+	alx->num_txq = 1;
+	alx->num_rxq = 1;
+	return 0;
 }
 
 static void alx_irq_enable(struct alx_priv *alx)
@@ -950,10 +924,11 @@ static void alx_irq_enable(struct alx_priv *alx)
 	alx_write_mem32(hw, ALX_IMR, alx->int_mask);
 	alx_post_write(hw);
 
-	if (alx->flags & ALX_FLAG_USING_MSIX)
+	if (alx->hw.pdev->msix_enabled) {
 		/* enable all msix irqs */
 		for (i = 0; i < alx->num_vec; i++)
 			alx_mask_msix(hw, i, false);
+	}
 }
 
 static void alx_irq_disable(struct alx_priv *alx)
@@ -965,13 +940,13 @@ static void alx_irq_disable(struct alx_priv *alx)
 	alx_write_mem32(hw, ALX_IMR, 0);
 	alx_post_write(hw);
 
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
+	if (alx->hw.pdev->msix_enabled) {
 		for (i = 0; i < alx->num_vec; i++) {
 			alx_mask_msix(hw, i, true);
-			synchronize_irq(alx->msix_entries[i].vector);
+			synchronize_irq(pci_irq_vector(alx->hw.pdev, i));
 		}
 	} else {
-		synchronize_irq(alx->hw.pdev->irq);
+		synchronize_irq(pci_irq_vector(alx->hw.pdev, 0));
 	}
 }
 
@@ -981,8 +956,11 @@ static int alx_realloc_resources(struct alx_priv *alx)
 
 	alx_free_rings(alx);
 	alx_free_napis(alx);
-	alx_disable_advanced_intr(alx);
-	alx_init_intr(alx, false);
+	pci_free_irq_vectors(alx->hw.pdev);
+
+	err = alx_init_intr(alx);
+	if (err)
+		return err;
 
 	err = alx_alloc_napis(alx);
 	if (err)
@@ -1004,7 +982,7 @@ static int alx_request_irq(struct alx_priv *alx)
 
 	msi_ctrl = (hw->imt >> 1) << ALX_MSI_RETRANS_TM_SHIFT;
 
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
+	if (alx->hw.pdev->msix_enabled) {
 		alx_write_mem32(hw, ALX_MSI_RETRANS_TIMER, msi_ctrl);
 		err = alx_request_msix(alx);
 		if (!err)
@@ -1016,20 +994,20 @@ static int alx_request_irq(struct alx_priv *alx)
 			goto out;
 	}
 
-	if (alx->flags & ALX_FLAG_USING_MSI) {
+	if (alx->hw.pdev->msi_enabled) {
 		alx_write_mem32(hw, ALX_MSI_RETRANS_TIMER,
 				msi_ctrl | ALX_MSI_MASK_SEL_LINE);
-		err = request_irq(pdev->irq, alx_intr_msi, 0,
+		err = request_irq(pci_irq_vector(pdev, 0), alx_intr_msi, 0,
 				  alx->dev->name, alx);
 		if (!err)
 			goto out;
+
 		/* fall back to legacy interrupt */
-		alx->flags &= ~ALX_FLAG_USING_MSI;
-		pci_disable_msi(alx->hw.pdev);
+		pci_free_irq_vectors(alx->hw.pdev);
 	}
 
 	alx_write_mem32(hw, ALX_MSI_RETRANS_TIMER, 0);
-	err = request_irq(pdev->irq, alx_intr_legacy, IRQF_SHARED,
+	err = request_irq(pci_irq_vector(pdev, 0), alx_intr_legacy, IRQF_SHARED,
 			  alx->dev->name, alx);
 out:
 	if (!err)
@@ -1042,18 +1020,15 @@ out:
 static void alx_free_irq(struct alx_priv *alx)
 {
 	struct pci_dev *pdev = alx->hw.pdev;
-	int i, vector = 0;
+	int i;
 
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
-		free_irq(alx->msix_entries[vector++].vector, alx);
+	free_irq(pci_irq_vector(pdev, 0), alx);
+	if (alx->hw.pdev->msix_enabled) {
 		for (i = 0; i < alx->num_napi; i++)
-			free_irq(alx->msix_entries[vector++].vector,
-				 alx->qnapi[i]);
-	} else {
-		free_irq(pdev->irq, alx);
+			free_irq(pci_irq_vector(pdev, i + 1), alx->qnapi[i]);
 	}
 
-	alx_disable_advanced_intr(alx);
+	pci_free_irq_vectors(pdev);
 }
 
 static int alx_identify_hw(struct alx_priv *alx)
@@ -1221,7 +1196,12 @@ static int __alx_open(struct alx_priv *alx, bool resume)
 {
 	int err;
 
-	alx_init_intr(alx, true);
+	err = alx_enable_msix(alx);
+	if (err < 0) {
+		err = alx_init_intr(alx);
+		if (err)
+			return err;
+	}
 
 	if (!resume)
 		netif_carrier_off(alx->dev);
@@ -1264,7 +1244,7 @@ out_free_rings:
 	alx_free_rings(alx);
 	alx_free_napis(alx);
 out_disable_adv_intr:
-	alx_disable_advanced_intr(alx);
+	pci_free_irq_vectors(alx->hw.pdev);
 	return err;
 }
 
@@ -1637,11 +1617,11 @@ static void alx_poll_controller(struct net_device *netdev)
 	struct alx_priv *alx = netdev_priv(netdev);
 	int i;
 
-	if (alx->flags & ALX_FLAG_USING_MSIX) {
+	if (alx->hw.pdev->msix_enabled) {
 		alx_intr_msix_misc(0, alx);
 		for (i = 0; i < alx->num_txq; i++)
 			alx_intr_msix_ring(0, alx->qnapi[i]);
-	} else if (alx->flags & ALX_FLAG_USING_MSI)
+	} else if (alx->hw.pdev->msi_enabled)
 		alx_intr_msi(0, alx);
 	else
 		alx_intr_legacy(0, alx);
@@ -1783,7 +1763,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netdev->netdev_ops = &alx_netdev_ops;
 	netdev->ethtool_ops = &alx_ethtool_ops;
-	netdev->irq = pdev->irq;
+	netdev->irq = pci_irq_vector(pdev, 0);
 	netdev->watchdog_timeo = ALX_WATCHDOG_TIME;
 
 	if (ent->driver_data & ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG)
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 022772e1e249..83d2db2abb45 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1886,7 +1886,7 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter)
 		buffer_info->skb = skb;
 		buffer_info->length = (u16) adapter->rx_buffer_len;
 		page = virt_to_page(skb->data);
-		offset = (unsigned long)skb->data & ~PAGE_MASK;
+		offset = offset_in_page(skb->data);
 		buffer_info->dma = pci_map_page(pdev, page, offset,
 						adapter->rx_buffer_len,
 						PCI_DMA_FROMDEVICE);
@@ -2230,7 +2230,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		buffer_info->length = hdr_len;
 		page = virt_to_page(skb->data);
-		offset = (unsigned long)skb->data & ~PAGE_MASK;
+		offset = offset_in_page(skb->data);
 		buffer_info->dma = pci_map_page(adapter->pdev, page,
 						offset, hdr_len,
 						PCI_DMA_TODEVICE);
@@ -2254,9 +2254,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 				data_len -= buffer_info->length;
 				page = virt_to_page(skb->data +
 					(hdr_len + i * ATL1_MAX_TX_BUF_LEN));
-				offset = (unsigned long)(skb->data +
-					(hdr_len + i * ATL1_MAX_TX_BUF_LEN)) &
-					~PAGE_MASK;
+				offset = offset_in_page(skb->data +
+					(hdr_len + i * ATL1_MAX_TX_BUF_LEN));
 				buffer_info->dma = pci_map_page(adapter->pdev,
 					page, offset, buffer_info->length,
 					PCI_DMA_TODEVICE);
@@ -2268,7 +2267,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		/* not TSO */
 		buffer_info->length = buf_len;
 		page = virt_to_page(skb->data);
-		offset = (unsigned long)skb->data & ~PAGE_MASK;
+		offset = offset_in_page(skb->data);
 		buffer_info->dma = pci_map_page(adapter->pdev, page,
 			offset, buf_len, PCI_DMA_TODEVICE);
 		if (++next_to_use == tpd_ring->count)
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 940fb24bba21..96413808c726 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -109,7 +109,6 @@ config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
 	select PHYLIB
-	select HWMON
 	imply PTP_1588_CLOCK
 	---help---
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
@@ -117,6 +116,13 @@ config TIGON3
 	  To compile this driver as a module, choose M here: the module
 	  will be called tg3.  This is recommended.
 
+config TIGON3_HWMON
+	bool "Broadcom Tigon3 HWMON support"
+	default y
+	depends on TIGON3 && HWMON && !(TIGON3=y && HWMON=m)
+	---help---
+	  Say Y if you want to expose the thermal sensor on Tigon3 devices.
+
 config BNX2X
 	tristate "Broadcom NetXtremeII 10Gb support"
 	depends on PCI
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a68d4889f5db..099b374c1b17 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -22,6 +22,7 @@
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
+#include <net/dsa.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 
@@ -284,6 +285,7 @@ static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = {
 	STAT_MIB_SOFT("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
 	STAT_MIB_SOFT("rx_dma_failed", mib.rx_dma_failed),
 	STAT_MIB_SOFT("tx_dma_failed", mib.tx_dma_failed),
+	/* Per TX-queue statistics are dynamically appended */
 };
 
 #define BCM_SYSPORT_STATS_LEN	ARRAY_SIZE(bcm_sysport_gstrings_stats)
@@ -338,7 +340,8 @@ static int bcm_sysport_get_sset_count(struct net_device *dev, int string_set)
 				continue;
 			j++;
 		}
-		return j;
+		/* Include per-queue statistics */
+		return j + dev->num_tx_queues * NUM_SYSPORT_TXQ_STAT;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -349,6 +352,7 @@ static void bcm_sysport_get_strings(struct net_device *dev,
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	const struct bcm_sysport_stats *s;
+	char buf[128];
 	int i, j;
 
 	switch (stringset) {
@@ -363,6 +367,18 @@ static void bcm_sysport_get_strings(struct net_device *dev,
 			       ETH_GSTRING_LEN);
 			j++;
 		}
+
+		for (i = 0; i < dev->num_tx_queues; i++) {
+			snprintf(buf, sizeof(buf), "txq%d_packets", i);
+			memcpy(data + j * ETH_GSTRING_LEN, buf,
+			       ETH_GSTRING_LEN);
+			j++;
+
+			snprintf(buf, sizeof(buf), "txq%d_bytes", i);
+			memcpy(data + j * ETH_GSTRING_LEN, buf,
+			       ETH_GSTRING_LEN);
+			j++;
+		}
 		break;
 	default:
 		break;
@@ -418,6 +434,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_tx_ring *ring;
 	int i, j;
 
 	if (netif_running(dev))
@@ -436,6 +453,22 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		data[j] = *(unsigned long *)p;
 		j++;
 	}
+
+	/* For SYSTEMPORT Lite since we have holes in our statistics, j would
+	 * be equal to BCM_SYSPORT_STATS_LEN at the end of the loop, but it
+	 * needs to point to how many total statistics we have minus the
+	 * number of per TX queue statistics
+	 */
+	j = bcm_sysport_get_sset_count(dev, ETH_SS_STATS) -
+	    dev->num_tx_queues * NUM_SYSPORT_TXQ_STAT;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		ring = &priv->tx_rings[i];
+		data[j] = ring->packets;
+		j++;
+		data[j] = ring->bytes;
+		j++;
+	}
 }
 
 static void bcm_sysport_get_wol(struct net_device *dev,
@@ -637,6 +670,9 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 	u16 len, status;
 	struct bcm_rsb *rsb;
 
+	/* Clear status before servicing to reduce spurious interrupts */
+	intrl2_0_writel(priv, INTRL2_0_RDMA_MBDONE, INTRL2_CPU_CLEAR);
+
 	/* Determine how much we should process since last call, SYSTEMPORT Lite
 	 * groups the producer and consumer indexes into the same 32-bit
 	 * which we access using RDMA_CONS_INDEX
@@ -647,11 +683,7 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 		p_index = rdma_readl(priv, RDMA_CONS_INDEX);
 	p_index &= RDMA_PROD_INDEX_MASK;
 
-	if (p_index < priv->rx_c_index)
-		to_process = (RDMA_CONS_INDEX_MASK + 1) -
-			priv->rx_c_index + p_index;
-	else
-		to_process = p_index - priv->rx_c_index;
+	to_process = (p_index - priv->rx_c_index) & RDMA_CONS_INDEX_MASK;
 
 	netif_dbg(priv, rx_status, ndev,
 		  "p_index=%d rx_c_index=%d to_process=%d\n",
@@ -746,26 +778,26 @@ next:
 	return processed;
 }
 
-static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_priv *priv,
+static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
 				       struct bcm_sysport_cb *cb,
 				       unsigned int *bytes_compl,
 				       unsigned int *pkts_compl)
 {
+	struct bcm_sysport_priv *priv = ring->priv;
 	struct device *kdev = &priv->pdev->dev;
-	struct net_device *ndev = priv->netdev;
 
 	if (cb->skb) {
-		ndev->stats.tx_bytes += cb->skb->len;
+		ring->bytes += cb->skb->len;
 		*bytes_compl += cb->skb->len;
 		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
 				 dma_unmap_len(cb, dma_len),
 				 DMA_TO_DEVICE);
-		ndev->stats.tx_packets++;
+		ring->packets++;
 		(*pkts_compl)++;
 		bcm_sysport_free_cb(cb);
 	/* SKB fragment */
 	} else if (dma_unmap_addr(cb, dma_addr)) {
-		ndev->stats.tx_bytes += dma_unmap_len(cb, dma_len);
+		ring->bytes += dma_unmap_len(cb, dma_len);
 		dma_unmap_page(kdev, dma_unmap_addr(cb, dma_addr),
 			       dma_unmap_len(cb, dma_len), DMA_TO_DEVICE);
 		dma_unmap_addr_set(cb, dma_addr, 0);
@@ -782,6 +814,13 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	struct bcm_sysport_cb *cb;
 	u32 hw_ind;
 
+	/* Clear status before servicing to reduce spurious interrupts */
+	if (!ring->priv->is_lite)
+		intrl2_1_writel(ring->priv, BIT(ring->index), INTRL2_CPU_CLEAR);
+	else
+		intrl2_0_writel(ring->priv, BIT(ring->index +
+				INTRL2_0_TDMA_MBDONE_SHIFT), INTRL2_CPU_CLEAR);
+
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -803,7 +842,7 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 
 	while (last_tx_cn-- > 0) {
 		cb = ring->cbs + last_c_index;
-		bcm_sysport_tx_reclaim_one(priv, cb, &bytes_compl, &pkts_compl);
+		bcm_sysport_tx_reclaim_one(ring, cb, &bytes_compl, &pkts_compl);
 
 		ring->desc_count++;
 		last_c_index++;
@@ -1632,6 +1671,24 @@ static int bcm_sysport_change_mac(struct net_device *dev, void *p)
 	return 0;
 }
 
+static struct net_device_stats *bcm_sysport_get_nstats(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	unsigned long tx_bytes = 0, tx_packets = 0;
+	struct bcm_sysport_tx_ring *ring;
+	unsigned int q;
+
+	for (q = 0; q < dev->num_tx_queues; q++) {
+		ring = &priv->tx_rings[q];
+		tx_bytes += ring->bytes;
+		tx_packets += ring->packets;
+	}
+
+	dev->stats.tx_bytes = tx_bytes;
+	dev->stats.tx_packets = tx_packets;
+	return &dev->stats;
+}
+
 static void bcm_sysport_netif_start(struct net_device *dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -1893,6 +1950,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bcm_sysport_poll_controller,
 #endif
+	.ndo_get_stats		= bcm_sysport_get_nstats,
 };
 
 #define REV_FMT	"v%2x.%02x"
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 863ddd7870b7..77a51c167a69 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -647,6 +647,9 @@ enum bcm_sysport_stat_type {
 	.reg_offset = ofs, \
 }
 
+/* TX bytes and packets */
+#define NUM_SYSPORT_TXQ_STAT	2
+
 struct bcm_sysport_stats {
 	char stat_string[ETH_GSTRING_LEN];
 	int stat_sizeof;
@@ -690,6 +693,8 @@ struct bcm_sysport_tx_ring {
 	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
 	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
+	unsigned long	packets;	/* packets statistics */
+	unsigned long	bytes;		/* bytes statistics */
 };
 
 /* Driver private structure */
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index d59cfcc4c4d5..6322594ab260 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -11,6 +11,7 @@
 #include <linux/bcma/bcma.h>
 #include <linux/brcmphy.h>
 #include <linux/etherdevice.h>
+#include <linux/of_net.h>
 #include "bgmac.h"
 
 static inline bool bgmac_is_bcm4707_family(struct bcma_device *core)
@@ -114,7 +115,7 @@ static int bgmac_probe(struct bcma_device *core)
 	struct ssb_sprom *sprom = &core->bus->sprom;
 	struct mii_bus *mii_bus;
 	struct bgmac *bgmac;
-	u8 *mac;
+	const u8 *mac = NULL;
 	int err;
 
 	bgmac = bgmac_alloc(&core->dev);
@@ -127,21 +128,27 @@ static int bgmac_probe(struct bcma_device *core)
 
 	bcma_set_drvdata(core, bgmac);
 
-	switch (core->core_unit) {
-	case 0:
-		mac = sprom->et0mac;
-		break;
-	case 1:
-		mac = sprom->et1mac;
-		break;
-	case 2:
-		mac = sprom->et2mac;
-		break;
-	default:
-		dev_err(bgmac->dev, "Unsupported core_unit %d\n",
-			core->core_unit);
-		err = -ENOTSUPP;
-		goto err;
+	if (bgmac->dev->of_node)
+		mac = of_get_mac_address(bgmac->dev->of_node);
+
+	/* If no MAC address assigned via device tree, check SPROM */
+	if (!mac) {
+		switch (core->core_unit) {
+		case 0:
+			mac = sprom->et0mac;
+			break;
+		case 1:
+			mac = sprom->et1mac;
+			break;
+		case 2:
+			mac = sprom->et2mac;
+			break;
+		default:
+			dev_err(bgmac->dev, "Unsupported core_unit %d\n",
+				core->core_unit);
+			err = -ENOTSUPP;
+			goto err;
+		}
 	}
 
 	ether_addr_copy(bgmac->net_dev->dev_addr, mac);
@@ -192,36 +199,50 @@ static int bgmac_probe(struct bcma_device *core)
 		goto err1;
 	}
 
-	bgmac->has_robosw = !!(core->bus->sprom.boardflags_lo &
-			       BGMAC_BFL_ENETROBO);
+	bgmac->has_robosw = !!(sprom->boardflags_lo & BGMAC_BFL_ENETROBO);
 	if (bgmac->has_robosw)
 		dev_warn(bgmac->dev, "Support for Roboswitch not implemented\n");
 
-	if (core->bus->sprom.boardflags_lo & BGMAC_BFL_ENETADM)
+	if (sprom->boardflags_lo & BGMAC_BFL_ENETADM)
 		dev_warn(bgmac->dev, "Support for ADMtek ethernet switch not implemented\n");
 
 	/* Feature Flags */
-	switch (core->bus->chipinfo.id) {
+	switch (ci->id) {
+	/* BCM 471X/535X family */
+	case BCMA_CHIP_ID_BCM4716:
+		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
+		/* fallthrough */
+	case BCMA_CHIP_ID_BCM47162:
+		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2;
+		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
+		break;
 	case BCMA_CHIP_ID_BCM5357:
+	case BCMA_CHIP_ID_BCM53572:
 		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
 		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47186) {
-			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
+		if (ci->pkg == BCMA_PKG_ID_BCM47188 ||
+		    ci->pkg == BCMA_PKG_ID_BCM47186) {
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
+			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
 		}
-		if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM5358)
+		if (ci->pkg == BCMA_PKG_ID_BCM5358)
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII;
 		break;
-	case BCMA_CHIP_ID_BCM53572:
-		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
+	case BCMA_CHIP_ID_BCM53573:
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
-		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47188) {
-			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
+		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
+		if (ci->pkg == BCMA_PKG_ID_BCM47189)
 			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
+		if (core->core_unit == 0) {
+			bgmac->feature_flags |= BGMAC_FEAT_CC4_IF_SW_TYPE;
+			if (ci->pkg == BCMA_PKG_ID_BCM47189)
+				bgmac->feature_flags |=
+					BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII;
+		} else if (core->core_unit == 1) {
+			bgmac->feature_flags |= BGMAC_FEAT_IRQ_ID_OOB_6;
+			bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII;
 		}
 		break;
 	case BCMA_CHIP_ID_BCM4749:
@@ -229,18 +250,11 @@ static int bgmac_probe(struct bcma_device *core)
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
 		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (core->bus->chipinfo.pkg == 10) {
+		if (ci->pkg == 10) {
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
 			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
 		}
 		break;
-	case BCMA_CHIP_ID_BCM4716:
-		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		/* fallthrough */
-	case BCMA_CHIP_ID_BCM47162:
-		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2;
-		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
-		break;
 	/* bcm4707_family */
 	case BCMA_CHIP_ID_BCM4707:
 	case BCMA_CHIP_ID_BCM47094:
@@ -249,21 +263,6 @@ static int bgmac_probe(struct bcma_device *core)
 		bgmac->feature_flags |= BGMAC_FEAT_NO_RESET;
 		bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500;
 		break;
-	case BCMA_CHIP_ID_BCM53573:
-		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
-		if (ci->pkg == BCMA_PKG_ID_BCM47189)
-			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
-		if (core->core_unit == 0) {
-			bgmac->feature_flags |= BGMAC_FEAT_CC4_IF_SW_TYPE;
-			if (ci->pkg == BCMA_PKG_ID_BCM47189)
-				bgmac->feature_flags |=
-					BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII;
-		} else if (core->core_unit == 1) {
-			bgmac->feature_flags |= BGMAC_FEAT_IRQ_ID_OOB_6;
-			bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII;
-		}
-		break;
 	default:
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index da1b8b225eb9..73aca97a96bc 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -21,8 +21,12 @@
 #include <linux/of_net.h>
 #include "bgmac.h"
 
+#define NICPM_PADRING_CFG		0x00000004
 #define NICPM_IOMUX_CTRL		0x00000008
 
+#define NICPM_PADRING_CFG_INIT_VAL	0x74000000
+#define NICPM_IOMUX_CTRL_INIT_VAL_AX	0x21880000
+
 #define NICPM_IOMUX_CTRL_INIT_VAL	0x3196e000
 #define NICPM_IOMUX_CTRL_SPD_SHIFT	10
 #define NICPM_IOMUX_CTRL_SPD_10M	0
@@ -113,6 +117,10 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev)
 	if (!bgmac->plat.nicpm_base)
 		return;
 
+	/* SET RGMII IO CONFIG */
+	writel(NICPM_PADRING_CFG_INIT_VAL,
+	       bgmac->plat.nicpm_base + NICPM_PADRING_CFG);
+
 	val = NICPM_IOMUX_CTRL_INIT_VAL;
 	switch (bgmac->net_dev->phydev->speed) {
 	default:
@@ -244,6 +252,31 @@ static int bgmac_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int bgmac_suspend(struct device *dev)
+{
+	struct bgmac *bgmac = dev_get_drvdata(dev);
+
+	return bgmac_enet_suspend(bgmac);
+}
+
+static int bgmac_resume(struct device *dev)
+{
+	struct bgmac *bgmac = dev_get_drvdata(dev);
+
+	return bgmac_enet_resume(bgmac);
+}
+
+static const struct dev_pm_ops bgmac_pm_ops = {
+	.suspend = bgmac_suspend,
+	.resume = bgmac_resume
+};
+
+#define BGMAC_PM_OPS (&bgmac_pm_ops)
+#else
+#define BGMAC_PM_OPS NULL
+#endif /* CONFIG_PM */
+
 static const struct of_device_id bgmac_of_enet_match[] = {
 	{.compatible = "brcm,amac",},
 	{.compatible = "brcm,nsp-amac",},
@@ -257,6 +290,7 @@ static struct platform_driver bgmac_enet_driver = {
 	.driver = {
 		.name  = "bgmac-enet",
 		.of_match_table = bgmac_of_enet_match,
+		.pm = BGMAC_PM_OPS
 	},
 	.probe = bgmac_probe,
 	.remove = bgmac_remove,
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index fd66fca00e01..ba4d2e145bb9 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -11,6 +11,7 @@
 
 #include <linux/bcma/bcma.h>
 #include <linux/etherdevice.h>
+#include <linux/interrupt.h>
 #include <linux/bcm47xx_nvram.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
@@ -1480,6 +1481,7 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 
 	net_dev->irq = bgmac->irq;
 	SET_NETDEV_DEV(net_dev, bgmac->dev);
+	dev_set_drvdata(bgmac->dev, bgmac);
 
 	if (!is_valid_ether_addr(net_dev->dev_addr)) {
 		dev_err(bgmac->dev, "Invalid MAC addr: %pM\n",
@@ -1552,5 +1554,55 @@ void bgmac_enet_remove(struct bgmac *bgmac)
 }
 EXPORT_SYMBOL_GPL(bgmac_enet_remove);
 
+int bgmac_enet_suspend(struct bgmac *bgmac)
+{
+	if (!netif_running(bgmac->net_dev))
+		return 0;
+
+	phy_stop(bgmac->net_dev->phydev);
+
+	netif_stop_queue(bgmac->net_dev);
+
+	napi_disable(&bgmac->napi);
+
+	netif_tx_lock(bgmac->net_dev);
+	netif_device_detach(bgmac->net_dev);
+	netif_tx_unlock(bgmac->net_dev);
+
+	bgmac_chip_intrs_off(bgmac);
+	bgmac_chip_reset(bgmac);
+	bgmac_dma_cleanup(bgmac);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bgmac_enet_suspend);
+
+int bgmac_enet_resume(struct bgmac *bgmac)
+{
+	int rc;
+
+	if (!netif_running(bgmac->net_dev))
+		return 0;
+
+	rc = bgmac_dma_init(bgmac);
+	if (rc)
+		return rc;
+
+	bgmac_chip_init(bgmac);
+
+	napi_enable(&bgmac->napi);
+
+	netif_tx_lock(bgmac->net_dev);
+	netif_device_attach(bgmac->net_dev);
+	netif_tx_unlock(bgmac->net_dev);
+
+	netif_start_queue(bgmac->net_dev);
+
+	phy_start(bgmac->net_dev->phydev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bgmac_enet_resume);
+
 MODULE_AUTHOR("Rafał Miłecki");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 6d1c6ff1ed96..c1818766c501 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -402,7 +402,7 @@
 
 #define BGMAC_WEIGHT	64
 
-#define ETHER_MAX_LEN   1518
+#define ETHER_MAX_LEN	(ETH_FRAME_LEN + ETH_FCS_LEN)
 
 /* Feature Flags */
 #define BGMAC_FEAT_TX_MASK_SETUP	BIT(0)
@@ -537,6 +537,8 @@ int bgmac_enet_probe(struct bgmac *bgmac);
 void bgmac_enet_remove(struct bgmac *bgmac);
 void bgmac_adjust_link(struct net_device *net_dev);
 int bgmac_phy_connect_direct(struct bgmac *bgmac);
+int bgmac_enet_suspend(struct bgmac *bgmac);
+int bgmac_enet_resume(struct bgmac *bgmac);
 
 struct mii_bus *bcma_mdio_mii_register(struct bgmac *bgmac);
 void bcma_mdio_mii_unregister(struct mii_bus *mii_bus);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 0a23034bbe3f..352beff796ae 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -2277,7 +2277,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
 				 GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RBCP) | \
 				 GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RSVD_GRC))
 
-#define HW_INTERRUT_ASSERT_SET_0 \
+#define HW_INTERRUPT_ASSERT_SET_0 \
 				(AEU_INPUTS_ATTN_BITS_TSDM_HW_INTERRUPT | \
 				 AEU_INPUTS_ATTN_BITS_TCM_HW_INTERRUPT | \
 				 AEU_INPUTS_ATTN_BITS_TSEMI_HW_INTERRUPT | \
@@ -2290,7 +2290,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
 				 AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR |\
 				 AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR |\
 				 AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_1 \
+#define HW_INTERRUPT_ASSERT_SET_1 \
 				(AEU_INPUTS_ATTN_BITS_QM_HW_INTERRUPT | \
 				 AEU_INPUTS_ATTN_BITS_TIMERS_HW_INTERRUPT | \
 				 AEU_INPUTS_ATTN_BITS_XSDM_HW_INTERRUPT | \
@@ -2318,7 +2318,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
 				 AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR | \
 				 AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR |\
 				 AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_2 \
+#define HW_INTERRUPT_ASSERT_SET_2 \
 				(AEU_INPUTS_ATTN_BITS_CSEMI_HW_INTERRUPT | \
 				 AEU_INPUTS_ATTN_BITS_CDU_HW_INTERRUPT | \
 				 AEU_INPUTS_ATTN_BITS_DMAE_HW_INTERRUPT | \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9e8c06130c09..eccb3d1b6abb 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2021,6 +2021,7 @@ static void bnx2x_set_rx_buf_size(struct bnx2x *bp)
 				  ETH_OVERHEAD +
 				  mtu +
 				  BNX2X_FW_RX_ALIGN_END;
+		fp->rx_buf_size = SKB_DATA_ALIGN(fp->rx_buf_size);
 		/* Note : rx_buf_size doesn't take into account NET_SKB_PAD */
 		if (fp->rx_buf_size + NET_SKB_PAD <= PAGE_SIZE)
 			fp->rx_frag_size = fp->rx_buf_size + NET_SKB_PAD;
@@ -4277,7 +4278,10 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 {
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
-	return bnx2x_setup_tc(dev, tc->tc);
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return bnx2x_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 /* called with rtnl_lock */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index b209b7f6093e..7dd83d0ef0a0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6161,103 +6161,40 @@ static void bnx2x_link_int_ack(struct link_params *params,
 	}
 }
 
+static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len)
+{
+	str[0] = '\0';
+	(*len)--;
+	return 0;
+}
+
 static int bnx2x_format_ver(u32 num, u8 *str, u16 *len)
 {
-	u8 *str_ptr = str;
-	u32 mask = 0xf0000000;
-	u8 shift = 8*4;
-	u8 digit;
-	u8 remove_leading_zeros = 1;
+	u16 ret;
+
 	if (*len < 10) {
 		/* Need more than 10chars for this format */
-		*str_ptr = '\0';
-		(*len)--;
+		bnx2x_null_format_ver(num, str, len);
 		return -EINVAL;
 	}
-	while (shift > 0) {
 
-		shift -= 4;
-		digit = ((num & mask) >> shift);
-		if (digit == 0 && remove_leading_zeros) {
-			*str_ptr = '0';
-		} else {
-			if (digit < 0xa)
-				*str_ptr = digit + '0';
-			else
-				*str_ptr = digit - 0xa + 'a';
-
-			remove_leading_zeros = 0;
-			str_ptr++;
-			(*len)--;
-		}
-		mask = mask >> 4;
-		if (shift == 4*4) {
-			if (remove_leading_zeros) {
-				str_ptr++;
-				(*len)--;
-			}
-			*str_ptr = '.';
-			str_ptr++;
-			(*len)--;
-			remove_leading_zeros = 1;
-		}
-	}
-	if (remove_leading_zeros)
-		(*len)--;
+	ret = scnprintf(str, *len, "%hx.%hx", num >> 16, num);
+	*len -= ret;
 	return 0;
 }
 
 static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len)
 {
-	u8 *str_ptr = str;
-	u32 mask = 0x00f00000;
-	u8 shift = 8*3;
-	u8 digit;
-	u8 remove_leading_zeros = 1;
+	u16 ret;
 
 	if (*len < 10) {
 		/* Need more than 10chars for this format */
-		*str_ptr = '\0';
-		(*len)--;
+		bnx2x_null_format_ver(num, str, len);
 		return -EINVAL;
 	}
 
-	while (shift > 0) {
-		shift -= 4;
-		digit = ((num & mask) >> shift);
-		if (digit == 0 && remove_leading_zeros) {
-			*str_ptr = '0';
-		} else {
-			if (digit < 0xa)
-				*str_ptr = digit + '0';
-			else
-				*str_ptr = digit - 0xa + 'a';
-
-			remove_leading_zeros = 0;
-			str_ptr++;
-			(*len)--;
-		}
-		mask = mask >> 4;
-		if ((shift == 4*4) || (shift == 4*2)) {
-			if (remove_leading_zeros) {
-				str_ptr++;
-				(*len)--;
-			}
-			*str_ptr = '.';
-			str_ptr++;
-			(*len)--;
-			remove_leading_zeros = 1;
-		}
-	}
-	if (remove_leading_zeros)
-		(*len)--;
-	return 0;
-}
-
-static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len)
-{
-	str[0] = '\0';
-	(*len)--;
+	ret = scnprintf(str, *len, "%hhx.%hhx.%hhx", num >> 16, num >> 8, num);
+	*len -= ret;
 	return 0;
 }
 
@@ -10681,22 +10618,19 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy,
 
 static int bnx2x_8485x_format_ver(u32 raw_ver, u8 *str, u16 *len)
 {
-	int status = 0;
 	u32 num;
 
 	num = ((raw_ver & 0xF80) >> 7) << 16 | ((raw_ver & 0x7F) << 8) |
 	      ((raw_ver & 0xF000) >> 12);
-	status = bnx2x_3_seq_format_ver(num, str, len);
-	return status;
+	return bnx2x_3_seq_format_ver(num, str, len);
 }
 
 static int bnx2x_848xx_format_ver(u32 raw_ver, u8 *str, u16 *len)
 {
-	int status = 0;
 	u32 spirom_ver;
+
 	spirom_ver = ((raw_ver & 0xF80) >> 7) << 16 | (raw_ver & 0x7F);
-	status = bnx2x_format_ver(spirom_ver, str, len);
-	return status;
+	return bnx2x_format_ver(spirom_ver, str, len);
 }
 
 static void bnx2x_8481_hw_reset(struct bnx2x_phy *phy,
@@ -12547,13 +12481,12 @@ static int bnx2x_populate_ext_phy(struct bnx2x *bp,
 static int bnx2x_populate_phy(struct bnx2x *bp, u8 phy_index, u32 shmem_base,
 			      u32 shmem2_base, u8 port, struct bnx2x_phy *phy)
 {
-	int status = 0;
 	phy->type = PORT_HW_CFG_XGXS_EXT_PHY_TYPE_NOT_CONN;
 	if (phy_index == INT_PHY)
 		return bnx2x_populate_int_phy(bp, shmem_base, port, phy);
-	status = bnx2x_populate_ext_phy(bp, phy_index, shmem_base, shmem2_base,
+
+	return bnx2x_populate_ext_phy(bp, phy_index, shmem_base, shmem2_base,
 					port, phy);
-	return status;
 }
 
 static void bnx2x_phy_def_cfg(struct link_params *params,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index d8d06fdfc42b..a851f95c307a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -4166,14 +4166,14 @@ static void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn)
 		bnx2x_release_phy_lock(bp);
 	}
 
-	if (attn & HW_INTERRUT_ASSERT_SET_0) {
+	if (attn & HW_INTERRUPT_ASSERT_SET_0) {
 
 		val = REG_RD(bp, reg_offset);
-		val &= ~(attn & HW_INTERRUT_ASSERT_SET_0);
+		val &= ~(attn & HW_INTERRUPT_ASSERT_SET_0);
 		REG_WR(bp, reg_offset, val);
 
 		BNX2X_ERR("FATAL HW block attention set0 0x%x\n",
-			  (u32)(attn & HW_INTERRUT_ASSERT_SET_0));
+			  (u32)(attn & HW_INTERRUPT_ASSERT_SET_0));
 		bnx2x_panic();
 	}
 }
@@ -4191,7 +4191,7 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn)
 			BNX2X_ERR("FATAL error from DORQ\n");
 	}
 
-	if (attn & HW_INTERRUT_ASSERT_SET_1) {
+	if (attn & HW_INTERRUPT_ASSERT_SET_1) {
 
 		int port = BP_PORT(bp);
 		int reg_offset;
@@ -4200,11 +4200,11 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn)
 				     MISC_REG_AEU_ENABLE1_FUNC_0_OUT_1);
 
 		val = REG_RD(bp, reg_offset);
-		val &= ~(attn & HW_INTERRUT_ASSERT_SET_1);
+		val &= ~(attn & HW_INTERRUPT_ASSERT_SET_1);
 		REG_WR(bp, reg_offset, val);
 
 		BNX2X_ERR("FATAL HW block attention set1 0x%x\n",
-			  (u32)(attn & HW_INTERRUT_ASSERT_SET_1));
+			  (u32)(attn & HW_INTERRUPT_ASSERT_SET_1));
 		bnx2x_panic();
 	}
 }
@@ -4235,7 +4235,7 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn)
 		}
 	}
 
-	if (attn & HW_INTERRUT_ASSERT_SET_2) {
+	if (attn & HW_INTERRUPT_ASSERT_SET_2) {
 
 		int port = BP_PORT(bp);
 		int reg_offset;
@@ -4244,11 +4244,11 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn)
 				     MISC_REG_AEU_ENABLE1_FUNC_0_OUT_2);
 
 		val = REG_RD(bp, reg_offset);
-		val &= ~(attn & HW_INTERRUT_ASSERT_SET_2);
+		val &= ~(attn & HW_INTERRUPT_ASSERT_SET_2);
 		REG_WR(bp, reg_offset, val);
 
 		BNX2X_ERR("FATAL HW block attention set2 0x%x\n",
-			  (u32)(attn & HW_INTERRUT_ASSERT_SET_2));
+			  (u32)(attn & HW_INTERRUPT_ASSERT_SET_2));
 		bnx2x_panic();
 	}
 }
@@ -13292,17 +13292,15 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_HIGHDMA;
 
-	/* VF with OLD Hypervisor or old PF do not support filtering */
 	if (IS_PF(bp)) {
 		if (chip_is_e1x)
 			bp->accept_any_vlan = true;
 		else
 			dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-#ifdef CONFIG_BNX2X_SRIOV
-	} else if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) {
-		dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-#endif
 	}
+	/* For VF we'll know whether to enable VLAN filtering after
+	 * getting a response to CHANNEL_TLV_ACQUIRE from PF.
+	 */
 
 	dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX;
 	dev->features |= NETIF_F_HIGHDMA;
@@ -13738,7 +13736,7 @@ static int bnx2x_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 	if (!netif_running(bp->dev)) {
 		DP(BNX2X_MSG_PTP,
 		   "PTP adjfreq called while the interface is down\n");
-		return -EFAULT;
+		return -ENETDOWN;
 	}
 
 	if (ppb < 0) {
@@ -13797,6 +13795,12 @@ static int bnx2x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
 
+	if (!netif_running(bp->dev)) {
+		DP(BNX2X_MSG_PTP,
+		   "PTP adjtime called while the interface is down\n");
+		return -ENETDOWN;
+	}
+
 	DP(BNX2X_MSG_PTP, "PTP adjtime called, delta = %llx\n", delta);
 
 	timecounter_adjtime(&bp->timecounter, delta);
@@ -13809,6 +13813,12 @@ static int bnx2x_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
 	u64 ns;
 
+	if (!netif_running(bp->dev)) {
+		DP(BNX2X_MSG_PTP,
+		   "PTP gettime called while the interface is down\n");
+		return -ENETDOWN;
+	}
+
 	ns = timecounter_read(&bp->timecounter);
 
 	DP(BNX2X_MSG_PTP, "PTP gettime called, ns = %llu\n", ns);
@@ -13824,6 +13834,12 @@ static int bnx2x_ptp_settime(struct ptp_clock_info *ptp,
 	struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
 	u64 ns;
 
+	if (!netif_running(bp->dev)) {
+		DP(BNX2X_MSG_PTP,
+		   "PTP settime called while the interface is down\n");
+		return -ENETDOWN;
+	}
+
 	ns = timespec64_to_ns(ts);
 
 	DP(BNX2X_MSG_PTP, "PTP settime called, ns = %llu\n", ns);
@@ -13991,6 +14007,14 @@ static int bnx2x_init_one(struct pci_dev *pdev,
 		rc = bnx2x_vfpf_acquire(bp, tx_count, rx_count);
 		if (rc)
 			goto init_one_freemem;
+
+#ifdef CONFIG_BNX2X_SRIOV
+		/* VF with OLD Hypervisor or old PF do not support filtering */
+		if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) {
+			dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+			dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+		}
+#endif
 	}
 
 	/* Enable SRIOV if capability found in configuration space */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 6fad22adbbb9..bdfd53b46bc5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -434,7 +434,9 @@ static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp,
 
 	/* Add/Remove the filter */
 	rc = bnx2x_config_vlan_mac(bp, &ramrod);
-	if (rc && rc != -EEXIST) {
+	if (rc == -EEXIST)
+		return 0;
+	if (rc) {
 		BNX2X_ERR("Failed to %s %s\n",
 			  filter->add ? "add" : "delete",
 			  (filter->type == BNX2X_VF_FILTER_VLAN_MAC) ?
@@ -444,6 +446,8 @@ static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp,
 		return rc;
 	}
 
+	filter->applied = true;
+
 	return 0;
 }
 
@@ -469,8 +473,10 @@ int bnx2x_vf_mac_vlan_config_list(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	/* Rollback if needed */
 	if (i != filters->count) {
 		BNX2X_ERR("Managed only %d/%d filters - rolling back\n",
-			  i, filters->count + 1);
+			  i, filters->count);
 		while (--i >= 0) {
+			if (!filters->filters[i].applied)
+				continue;
 			filters->filters[i].add = !filters->filters[i].add;
 			bnx2x_vf_mac_vlan_config(bp, vf, qid,
 						 &filters->filters[i],
@@ -1899,7 +1905,8 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 			continue;
 		}
 
-		DP(BNX2X_MSG_IOV, "add addresses for vf %d\n", vf->abs_vfid);
+		DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+		       "add addresses for vf %d\n", vf->abs_vfid);
 		for_each_vfq(vf, j) {
 			struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
 
@@ -1920,11 +1927,12 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 				cpu_to_le32(U64_HI(q_stats_addr));
 			cur_query_entry->address.lo =
 				cpu_to_le32(U64_LO(q_stats_addr));
-			DP(BNX2X_MSG_IOV,
-			   "added address %x %x for vf %d queue %d client %d\n",
-			   cur_query_entry->address.hi,
-			   cur_query_entry->address.lo, cur_query_entry->funcID,
-			   j, cur_query_entry->index);
+			DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+			       "added address %x %x for vf %d queue %d client %d\n",
+			       cur_query_entry->address.hi,
+			       cur_query_entry->address.lo,
+			       cur_query_entry->funcID,
+			       j, cur_query_entry->index);
 			cur_query_entry++;
 			cur_data_offset += sizeof(struct per_queue_stats);
 			stats_count++;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 7a6d406f4c11..888d0b6632e8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -114,6 +114,7 @@ struct bnx2x_vf_mac_vlan_filter {
 	(BNX2X_VF_FILTER_MAC | BNX2X_VF_FILTER_VLAN) /*shortcut*/
 
 	bool add;
+	bool applied;
 	u8 *mac;
 	u16 vid;
 };
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index bfae300cf25f..76a4668c50fe 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -868,7 +868,7 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
 	struct bnx2x *bp = netdev_priv(dev);
 	struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters;
 	struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
-	int rc, i = 0;
+	int rc = 0, i = 0;
 	struct netdev_hw_addr *ha;
 
 	if (bp->state != BNX2X_STATE_OPEN) {
@@ -883,6 +883,15 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
 	/* Get Rx mode requested */
 	DP(NETIF_MSG_IFUP, "dev->flags = %x\n", dev->flags);
 
+	/* We support PFVF_MAX_MULTICAST_PER_VF mcast addresses tops */
+	if (netdev_mc_count(dev) > PFVF_MAX_MULTICAST_PER_VF) {
+		DP(NETIF_MSG_IFUP,
+		   "VF supports not more than %d multicast MAC addresses\n",
+		   PFVF_MAX_MULTICAST_PER_VF);
+		rc = -EINVAL;
+		goto out;
+	}
+
 	netdev_for_each_mc_addr(ha, dev) {
 		DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n",
 		   bnx2x_mc_addr(ha));
@@ -890,16 +899,6 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
 		i++;
 	}
 
-	/* We support four PFVF_MAX_MULTICAST_PER_VF mcast
-	  * addresses tops
-	  */
-	if (i >= PFVF_MAX_MULTICAST_PER_VF) {
-		DP(NETIF_MSG_IFUP,
-		   "VF supports not more than %d multicast MAC addresses\n",
-		   PFVF_MAX_MULTICAST_PER_VF);
-		return -EINVAL;
-	}
-
 	req->n_multicast = i;
 	req->flags |= VFPF_SET_Q_FILTERS_MULTICAST_CHANGED;
 	req->vf_qid = 0;
@@ -924,7 +923,7 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
 out:
 	bnx2x_vfpf_finalize(bp, &req->first_tlv);
 
-	return 0;
+	return rc;
 }
 
 /* request pf to add a vlan for the vf */
@@ -1778,6 +1777,23 @@ static int bnx2x_vf_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
 				goto op_err;
 		}
 
+		/* build vlan list */
+		fl = NULL;
+
+		rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+					       VFPF_VLAN_FILTER);
+		if (rc)
+			goto op_err;
+
+		if (fl) {
+			/* set vlan list */
+			rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl,
+							   msg->vf_qid,
+							   false);
+			if (rc)
+				goto op_err;
+		}
+
 	}
 
 	if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 235733e91c79..b3ba66032980 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1983,20 +1983,25 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 
 		for (j = 0; j < max_idx; j++) {
 			struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[j];
+			dma_addr_t mapping = rx_buf->mapping;
 			void *data = rx_buf->data;
 
 			if (!data)
 				continue;
 
-			dma_unmap_single(&pdev->dev, rx_buf->mapping,
-					 bp->rx_buf_use_size, bp->rx_dir);
-
 			rx_buf->data = NULL;
 
-			if (BNXT_RX_PAGE_MODE(bp))
+			if (BNXT_RX_PAGE_MODE(bp)) {
+				mapping -= bp->rx_dma_offset;
+				dma_unmap_page(&pdev->dev, mapping,
+					       PAGE_SIZE, bp->rx_dir);
 				__free_page(data);
-			else
+			} else {
+				dma_unmap_single(&pdev->dev, mapping,
+						 bp->rx_buf_use_size,
+						 bp->rx_dir);
 				kfree(data);
+			}
 		}
 
 		for (j = 0; j < max_agg_idx; j++) {
@@ -2455,6 +2460,18 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
 	return 0;
 }
 
+static void bnxt_init_cp_rings(struct bnxt *bp)
+{
+	int i;
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+		struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+
+		ring->fw_ring_id = INVALID_HW_RING_ID;
+	}
+}
+
 static int bnxt_init_rx_rings(struct bnxt *bp)
 {
 	int i, rc = 0;
@@ -4465,6 +4482,16 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
 	}
 #endif
+	if (BNXT_PF(bp)) {
+		u16 flags = le16_to_cpu(resp->flags);
+
+		if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED |
+			     FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED))
+			bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
+		if (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)
+			bp->flags |= BNXT_FLAG_MULTI_HOST;
+	}
+
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
@@ -4528,6 +4555,9 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		pf->max_tx_wm_flows = le32_to_cpu(resp->max_tx_wm_flows);
 		pf->max_rx_em_flows = le32_to_cpu(resp->max_rx_em_flows);
 		pf->max_rx_wm_flows = le32_to_cpu(resp->max_rx_wm_flows);
+		if (resp->flags &
+		    cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED))
+			bp->flags |= BNXT_FLAG_WOL_CAP;
 	} else {
 #ifdef CONFIG_BNXT_SRIOV
 		struct bnxt_vf_info *vf = &bp->vf;
@@ -4728,7 +4758,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n",
-				   rc, i);
+				   i, rc);
 			return rc;
 		}
 	}
@@ -5002,6 +5032,7 @@ static int bnxt_shutdown_nic(struct bnxt *bp, bool irq_re_init)
 
 static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init)
 {
+	bnxt_init_cp_rings(bp);
 	bnxt_init_rx_rings(bp);
 	bnxt_init_tx_rings(bp);
 	bnxt_init_ring_grps(bp, irq_re_init);
@@ -5176,9 +5207,10 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 #if defined(CONFIG_BNXT_SRIOV)
 	if (BNXT_VF(bp))
-		return bp->vf.max_irqs;
+		return min_t(unsigned int, bp->vf.max_irqs,
+			     bp->vf.max_cp_rings);
 #endif
-	return bp->pf.max_irqs;
+	return min_t(unsigned int, bp->pf.max_irqs, bp->pf.max_cp_rings);
 }
 
 void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
@@ -5445,7 +5477,8 @@ static void bnxt_report_link(struct bnxt *bp)
 	if (bp->link_info.link_up) {
 		const char *duplex;
 		const char *flow_ctrl;
-		u16 speed, fec;
+		u32 speed;
+		u16 fec;
 
 		netif_carrier_on(bp->dev);
 		if (bp->link_info.duplex == BNXT_LINK_DUPLEX_FULL)
@@ -5461,7 +5494,7 @@ static void bnxt_report_link(struct bnxt *bp)
 		else
 			flow_ctrl = "none";
 		speed = bnxt_fw_to_ethtool_speed(bp->link_info.link_speed);
-		netdev_info(bp->dev, "NIC Link is Up, %d Mbps %s duplex, Flow control: %s\n",
+		netdev_info(bp->dev, "NIC Link is Up, %u Mbps %s duplex, Flow control: %s\n",
 			    speed, duplex, flow_ctrl);
 		if (bp->flags & BNXT_FLAG_EEE_CAP)
 			netdev_info(bp->dev, "EEE is %s\n",
@@ -5507,8 +5540,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 		bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
 				 PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
 	}
-	link_info->support_auto_speeds =
-		le16_to_cpu(resp->supported_speeds_auto_mode);
+	if (resp->supported_speeds_auto_mode)
+		link_info->support_auto_speeds =
+			le16_to_cpu(resp->supported_speeds_auto_mode);
 
 hwrm_phy_qcaps_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -5834,6 +5868,76 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 	return 0;
 }
 
+int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp)
+{
+	struct hwrm_wol_filter_alloc_input req = {0};
+	struct hwrm_wol_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_ALLOC, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.wol_type = WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT;
+	req.enables = cpu_to_le32(WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS);
+	memcpy(req.mac_address, bp->dev->dev_addr, ETH_ALEN);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		bp->wol_filter_id = resp->wol_filter_id;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+int bnxt_hwrm_free_wol_fltr(struct bnxt *bp)
+{
+	struct hwrm_wol_filter_free_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_FREE, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.enables = cpu_to_le32(WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID);
+	req.wol_filter_id = bp->wol_filter_id;
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return rc;
+}
+
+static u16 bnxt_hwrm_get_wol_fltrs(struct bnxt *bp, u16 handle)
+{
+	struct hwrm_wol_filter_qcfg_input req = {0};
+	struct hwrm_wol_filter_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	u16 next_handle = 0;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_QCFG, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.handle = cpu_to_le16(handle);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		next_handle = le16_to_cpu(resp->next_handle);
+		if (next_handle != 0) {
+			if (resp->wol_type ==
+			    WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT) {
+				bp->wol = 1;
+				bp->wol_filter_id = resp->wol_filter_id;
+			}
+		}
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return next_handle;
+}
+
+static void bnxt_get_wol_settings(struct bnxt *bp)
+{
+	u16 handle = 0;
+
+	if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_WOL_CAP))
+		return;
+
+	do {
+		handle = bnxt_hwrm_get_wol_fltrs(bp, handle);
+	} while (handle && handle != 0xffff);
+}
+
 static bool bnxt_eee_config_ok(struct bnxt *bp)
 {
 	struct ethtool_eee *eee = &bp->eee;
@@ -6019,6 +6123,43 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	return rc;
 }
 
+/* rtnl_lock held, open the NIC half way by allocating all resources, but
+ * NAPI, IRQ, and TX are not enabled.  This is mainly used for offline
+ * self tests.
+ */
+int bnxt_half_open_nic(struct bnxt *bp)
+{
+	int rc = 0;
+
+	rc = bnxt_alloc_mem(bp, false);
+	if (rc) {
+		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
+		goto half_open_err;
+	}
+	rc = bnxt_init_nic(bp, false);
+	if (rc) {
+		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
+		goto half_open_err;
+	}
+	return 0;
+
+half_open_err:
+	bnxt_free_skbs(bp);
+	bnxt_free_mem(bp, false);
+	dev_close(bp->dev);
+	return rc;
+}
+
+/* rtnl_lock held, this call can only be made after a previous successful
+ * call to bnxt_half_open_nic().
+ */
+void bnxt_half_close_nic(struct bnxt *bp)
+{
+	bnxt_hwrm_resource_free(bp, false, false);
+	bnxt_free_skbs(bp);
+	bnxt_free_mem(bp, false);
+}
+
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -6495,8 +6636,14 @@ static void bnxt_reset_task(struct bnxt *bp, bool silent)
 	if (!silent)
 		bnxt_dbg_dump_states(bp);
 	if (netif_running(bp->dev)) {
+		int rc;
+
+		if (!silent)
+			bnxt_ulp_stop(bp);
 		bnxt_close_nic(bp, false, false);
-		bnxt_open_nic(bp, false, false);
+		rc = bnxt_open_nic(bp, false, false);
+		if (!silent && !rc)
+			bnxt_ulp_start(bp);
 	}
 }
 
@@ -6894,7 +7041,9 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return bnxt_setup_mq_tc(dev, ntc->tc);
+	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc);
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -7195,6 +7344,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
+	bnxt_ethtool_free(bp);
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
@@ -7444,6 +7594,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	rc = bnxt_hwrm_func_reset(bp);
+	if (rc)
+		goto init_err_pci_clean;
+
 	bnxt_hwrm_fw_set_time(bp);
 
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
@@ -7513,6 +7667,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bnxt_hwrm_func_qcfg(bp);
 	bnxt_hwrm_port_led_qcaps(bp);
+	bnxt_ethtool_init(bp);
 
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
@@ -7554,14 +7709,16 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
-	rc = bnxt_hwrm_func_reset(bp);
-	if (rc)
-		goto init_err_pci_clean;
-
 	rc = bnxt_init_int_mode(bp);
 	if (rc)
 		goto init_err_pci_clean;
 
+	bnxt_get_wol_settings(bp);
+	if (bp->flags & BNXT_FLAG_WOL_CAP)
+		device_set_wakeup_enable(&pdev->dev, bp->wol);
+	else
+		device_set_wakeup_capable(&pdev->dev, false);
+
 	rc = register_netdev(dev);
 	if (rc)
 		goto init_err_clr_int;
@@ -7585,6 +7742,88 @@ init_err_free:
 	return rc;
 }
 
+static void bnxt_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnxt *bp;
+
+	if (!dev)
+		return;
+
+	rtnl_lock();
+	bp = netdev_priv(dev);
+	if (!bp)
+		goto shutdown_exit;
+
+	if (netif_running(dev))
+		dev_close(dev);
+
+	if (system_state == SYSTEM_POWER_OFF) {
+		bnxt_clear_int_mode(bp);
+		pci_wake_from_d3(pdev, bp->wol);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
+
+shutdown_exit:
+	rtnl_unlock();
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int bnxt_suspend(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
+
+	rtnl_lock();
+	if (netif_running(dev)) {
+		netif_device_detach(dev);
+		rc = bnxt_close(dev);
+	}
+	bnxt_hwrm_func_drv_unrgtr(bp);
+	rtnl_unlock();
+	return rc;
+}
+
+static int bnxt_resume(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
+
+	rtnl_lock();
+	if (bnxt_hwrm_ver_get(bp) || bnxt_hwrm_func_drv_rgtr(bp)) {
+		rc = -ENODEV;
+		goto resume_exit;
+	}
+	rc = bnxt_hwrm_func_reset(bp);
+	if (rc) {
+		rc = -EBUSY;
+		goto resume_exit;
+	}
+	bnxt_get_wol_settings(bp);
+	if (netif_running(dev)) {
+		rc = bnxt_open(dev);
+		if (!rc)
+			netif_device_attach(dev);
+	}
+
+resume_exit:
+	rtnl_unlock();
+	return rc;
+}
+
+static SIMPLE_DEV_PM_OPS(bnxt_pm_ops, bnxt_suspend, bnxt_resume);
+#define BNXT_PM_OPS (&bnxt_pm_ops)
+
+#else
+
+#define BNXT_PM_OPS NULL
+
+#endif /* CONFIG_PM_SLEEP */
+
 /**
  * bnxt_io_error_detected - called when PCI error is detected
  * @pdev: Pointer to PCI device
@@ -7701,6 +7940,8 @@ static struct pci_driver bnxt_pci_driver = {
 	.id_table	= bnxt_pci_tbl,
 	.probe		= bnxt_init_one,
 	.remove		= bnxt_remove_one,
+	.shutdown	= bnxt_shutdown,
+	.driver.pm	= BNXT_PM_OPS,
 	.err_handler	= &bnxt_err_handler,
 #if defined(CONFIG_BNXT_SRIOV)
 	.sriov_configure = bnxt_sriov_configure,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index faf26a2f726b..3ef42dbc6327 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -18,6 +18,8 @@
 #define DRV_VER_MIN	7
 #define DRV_VER_UPD	0
 
+#include <linux/interrupt.h>
+
 struct tx_bd {
 	__le32 tx_bd_len_flags_type;
 	#define TX_BD_TYPE					(0x3f << 0)
@@ -424,8 +426,6 @@ struct rx_tpa_end_cmp_ext {
 
 #define BNXT_MIN_PKT_SIZE	52
 
-#define BNXT_NUM_TESTS(bp)	0
-
 #define BNXT_DEFAULT_RX_RING_SIZE	511
 #define BNXT_DEFAULT_TX_RING_SIZE	511
 
@@ -851,6 +851,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_25GB	PORT_PHY_QCFG_RESP_LINK_SPEED_25GB
 #define BNXT_LINK_SPEED_40GB	PORT_PHY_QCFG_RESP_LINK_SPEED_40GB
 #define BNXT_LINK_SPEED_50GB	PORT_PHY_QCFG_RESP_LINK_SPEED_50GB
+#define BNXT_LINK_SPEED_100GB	PORT_PHY_QCFG_RESP_LINK_SPEED_100GB
 	u16			support_speeds;
 	u16			auto_link_speeds;	/* fw adv setting */
 #define BNXT_LINK_SPEED_MSK_100MB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB
@@ -862,6 +863,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_MSK_25GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB
 #define BNXT_LINK_SPEED_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB
 #define BNXT_LINK_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB
+#define BNXT_LINK_SPEED_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB
 	u16			support_auto_speeds;
 	u16			lp_auto_link_speeds;
 	u16			force_link_speed;
@@ -909,6 +911,14 @@ struct bnxt_led_info {
 	__le16	led_color_caps;
 };
 
+#define BNXT_MAX_TEST	8
+
+struct bnxt_test_info {
+	u8 offline_mask;
+	u16 timeout;
+	char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
+};
+
 #define BNXT_GRCPF_REG_WINDOW_BASE_OUT	0x400
 #define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
 #define BNXT_CAG_REG_BASE		0x300000
@@ -987,12 +997,15 @@ struct bnxt {
 	#define BNXT_FLAG_UDP_RSS_CAP	0x800
 	#define BNXT_FLAG_EEE_CAP	0x1000
 	#define BNXT_FLAG_NEW_RSS_CAP	0x2000
+	#define BNXT_FLAG_WOL_CAP	0x4000
 	#define BNXT_FLAG_ROCEV1_CAP	0x8000
 	#define BNXT_FLAG_ROCEV2_CAP	0x10000
 	#define BNXT_FLAG_ROCE_CAP	(BNXT_FLAG_ROCEV1_CAP |	\
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
+	#define BNXT_FLAG_FW_LLDP_AGENT	0x80000
+	#define BNXT_FLAG_MULTI_HOST	0x100000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1002,7 +1015,8 @@ struct bnxt {
 #define BNXT_PF(bp)		(!((bp)->flags & BNXT_FLAG_VF))
 #define BNXT_VF(bp)		((bp)->flags & BNXT_FLAG_VF)
 #define BNXT_NPAR(bp)		((bp)->port_partition_type)
-#define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp))
+#define BNXT_MH(bp)		((bp)->flags & BNXT_FLAG_MULTI_HOST)
+#define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp) && !BNXT_MH(bp))
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
 
@@ -1177,6 +1191,12 @@ struct bnxt {
 	u32			lpi_tmr_lo;
 	u32			lpi_tmr_hi;
 
+	u8			num_tests;
+	struct bnxt_test_info	*test_info;
+
+	u8			wol_filter_id;
+	u8			wol;
+
 	u8			num_leds;
 	struct bnxt_led_info	leds[BNXT_MAX_LED];
 
@@ -1235,8 +1255,12 @@ void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
 int bnxt_hwrm_set_pause(struct bnxt *);
 int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool);
+int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp);
+int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
 int bnxt_hwrm_fw_set_time(struct bnxt *);
 int bnxt_open_nic(struct bnxt *, bool, bool);
+int bnxt_half_open_nic(struct bnxt *bp);
+void bnxt_half_close_nic(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
 int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, int tcs, int tx_xdp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index fdf2d8caf7bf..46de2f8ff024 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -14,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
+#include <rdma/ib_verbs.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_dcb.h"
@@ -241,6 +243,92 @@ static int bnxt_hwrm_queue_pfc_qcfg(struct bnxt *bp, struct ieee_pfc *pfc)
 	return 0;
 }
 
+static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app,
+				  bool add)
+{
+	struct hwrm_fw_set_structured_data_input set = {0};
+	struct hwrm_fw_get_structured_data_input get = {0};
+	struct hwrm_struct_data_dcbx_app *fw_app;
+	struct hwrm_struct_hdr *data;
+	dma_addr_t mapping;
+	size_t data_len;
+	int rc, n, i;
+
+	if (bp->hwrm_spec_code < 0x10601)
+		return 0;
+
+	n = IEEE_8021QAZ_MAX_TCS;
+	data_len = sizeof(*data) + sizeof(*fw_app) * n;
+	data = dma_alloc_coherent(&bp->pdev->dev, data_len, &mapping,
+				  GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	memset(data, 0, data_len);
+	bnxt_hwrm_cmd_hdr_init(bp, &get, HWRM_FW_GET_STRUCTURED_DATA, -1, -1);
+	get.dest_data_addr = cpu_to_le64(mapping);
+	get.structure_id = cpu_to_le16(STRUCT_HDR_STRUCT_ID_DCBX_APP);
+	get.subtype = cpu_to_le16(HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL);
+	get.count = 0;
+	rc = hwrm_send_message(bp, &get, sizeof(get), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto set_app_exit;
+
+	fw_app = (struct hwrm_struct_data_dcbx_app *)(data + 1);
+
+	if (data->struct_id != cpu_to_le16(STRUCT_HDR_STRUCT_ID_DCBX_APP)) {
+		rc = -ENODEV;
+		goto set_app_exit;
+	}
+
+	n = data->count;
+	for (i = 0; i < n; i++, fw_app++) {
+		if (fw_app->protocol_id == cpu_to_be16(app->protocol) &&
+		    fw_app->protocol_selector == app->selector &&
+		    fw_app->priority == app->priority) {
+			if (add)
+				goto set_app_exit;
+			else
+				break;
+		}
+	}
+	if (add) {
+		/* append */
+		n++;
+		fw_app->protocol_id = cpu_to_be16(app->protocol);
+		fw_app->protocol_selector = app->selector;
+		fw_app->priority = app->priority;
+		fw_app->valid = 1;
+	} else {
+		size_t len = 0;
+
+		/* not found, nothing to delete */
+		if (n == i)
+			goto set_app_exit;
+
+		len = (n - 1 - i) * sizeof(*fw_app);
+		if (len)
+			memmove(fw_app, fw_app + 1, len);
+		n--;
+		memset(fw_app + n, 0, sizeof(*fw_app));
+	}
+	data->count = n;
+	data->len = cpu_to_le16(sizeof(*fw_app) * n);
+	data->subtype = cpu_to_le16(HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL);
+
+	bnxt_hwrm_cmd_hdr_init(bp, &set, HWRM_FW_SET_STRUCTURED_DATA, -1, -1);
+	set.src_data_addr = cpu_to_le64(mapping);
+	set.data_len = cpu_to_le16(sizeof(*data) + sizeof(*fw_app) * n);
+	set.hdr_cnt = 1;
+	rc = hwrm_send_message(bp, &set, sizeof(set), HWRM_CMD_TIMEOUT);
+	if (rc)
+		rc = -EIO;
+
+set_app_exit:
+	dma_free_coherent(&bp->pdev->dev, data_len, data, mapping);
+	return rc;
+}
+
 static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 {
 	int total_ets_bw = 0;
@@ -417,6 +505,15 @@ static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 		return -EINVAL;
 
 	rc = dcb_ieee_setapp(dev, app);
+	if (rc)
+		return rc;
+
+	if ((app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE &&
+	     app->protocol == ETH_P_IBOE) ||
+	    (app->selector == IEEE_8021QAZ_APP_SEL_DGRAM &&
+	     app->protocol == ROCE_V2_UDP_DPORT))
+		rc = bnxt_hwrm_set_dcbx_app(bp, app, true);
+
 	return rc;
 }
 
@@ -425,10 +522,19 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
 
-	if (!(bp->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+	if (!(bp->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
+	    !(bp->dcbx_cap & DCB_CAP_DCBX_HOST))
 		return -EINVAL;
 
 	rc = dcb_ieee_delapp(dev, app);
+	if (rc)
+		return rc;
+	if ((app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE &&
+	     app->protocol == ETH_P_IBOE) ||
+	    (app->selector == IEEE_8021QAZ_APP_SEL_DGRAM &&
+	     app->protocol == ROCE_V2_UDP_DPORT))
+		rc = bnxt_hwrm_set_dcbx_app(bp, app, false);
+
 	return rc;
 }
 
@@ -474,7 +580,7 @@ void bnxt_dcb_init(struct bnxt *bp)
 		return;
 
 	bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
 		bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
 	else
 		bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
index 35a0d28cf2fd..ecd0a5e46a49 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 6903a873f072..11ddf0adc6e1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -17,6 +18,7 @@
 #include <linux/firmware.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_xdp.h"
 #include "bnxt_ethtool.h"
 #include "bnxt_nvm_defs.h"	/* NVRAM content constant and structure defs */
 #include "bnxt_fw_hdr.h"	/* Firmware hdr constant and structure defs */
@@ -209,6 +211,10 @@ static int bnxt_get_sset_count(struct net_device *dev, int sset)
 
 		return num_stats;
 	}
+	case ETH_SS_TEST:
+		if (!bp->num_tests)
+			return -EOPNOTSUPP;
+		return bp->num_tests;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -306,6 +312,11 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 			}
 		}
 		break;
+	case ETH_SS_TEST:
+		if (bp->num_tests)
+			memcpy(buf, bp->test_info->string,
+			       bp->num_tests * ETH_GSTRING_LEN);
+		break;
 	default:
 		netdev_err(bp->dev, "bnxt_get_strings invalid request %x\n",
 			   stringset);
@@ -824,7 +835,7 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 			sizeof(info->fw_version));
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 	info->n_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
-	info->testinfo_len = BNXT_NUM_TESTS(bp);
+	info->testinfo_len = bp->num_tests;
 	/* TODO CHIMP_FW: eeprom dump details */
 	info->eedump_len = 0;
 	/* TODO CHIMP FW: reg dump details */
@@ -832,6 +843,45 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 	kfree(pkglog);
 }
 
+static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	wol->supported = 0;
+	wol->wolopts = 0;
+	memset(&wol->sopass, 0, sizeof(wol->sopass));
+	if (bp->flags & BNXT_FLAG_WOL_CAP) {
+		wol->supported = WAKE_MAGIC;
+		if (bp->wol)
+			wol->wolopts = WAKE_MAGIC;
+	}
+}
+
+static int bnxt_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (wol->wolopts & ~WAKE_MAGIC)
+		return -EINVAL;
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		if (!(bp->flags & BNXT_FLAG_WOL_CAP))
+			return -EINVAL;
+		if (!bp->wol) {
+			if (bnxt_hwrm_alloc_wol_fltr(bp))
+				return -EBUSY;
+			bp->wol = 1;
+		}
+	} else {
+		if (bp->wol) {
+			if (bnxt_hwrm_free_wol_fltr(bp))
+				return -EBUSY;
+			bp->wol = 0;
+		}
+	}
+	return 0;
+}
+
 u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 {
 	u32 speed_mask = 0;
@@ -879,6 +929,9 @@ u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_50GB)			\
 		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
 						     50000baseCR2_Full);\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_100GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     100000baseCR4_Full);\
 	if ((fw_pause) & BNXT_LINK_PAUSE_RX) {				\
 		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
 						     Pause);		\
@@ -915,6 +968,9 @@ u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
 						  50000baseCR2_Full))	\
 		(fw_speeds) |= BNXT_LINK_SPEED_MSK_50GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  100000baseCR4_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_100GB;		\
 }
 
 static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info,
@@ -977,6 +1033,8 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
 		return SPEED_40000;
 	case BNXT_LINK_SPEED_50GB:
 		return SPEED_50000;
+	case BNXT_LINK_SPEED_100GB:
+		return SPEED_100000;
 	default:
 		return SPEED_UNKNOWN;
 	}
@@ -1042,7 +1100,7 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
-static u32 bnxt_get_fw_speed(struct net_device *dev, u16 ethtool_speed)
+static u32 bnxt_get_fw_speed(struct net_device *dev, u32 ethtool_speed)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
@@ -1082,6 +1140,10 @@ static u32 bnxt_get_fw_speed(struct net_device *dev, u16 ethtool_speed)
 		if (support_spds & BNXT_LINK_SPEED_MSK_50GB)
 			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB;
 		break;
+	case SPEED_100000:
+		if (support_spds & BNXT_LINK_SPEED_MSK_100GB)
+			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB;
+		break;
 	default:
 		netdev_err(dev, "unsupported speed!\n");
 		break;
@@ -2128,12 +2190,372 @@ static int bnxt_set_phys_id(struct net_device *dev,
 	return rc;
 }
 
+static int bnxt_hwrm_selftest_irq(struct bnxt *bp, u16 cmpl_ring)
+{
+	struct hwrm_selftest_irq_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_IRQ, cmpl_ring, -1);
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_test_irq(struct bnxt *bp)
+{
+	int i;
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		u16 cmpl_ring = bp->grp_info[i].cp_fw_ring_id;
+		int rc;
+
+		rc = bnxt_hwrm_selftest_irq(bp, cmpl_ring);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
+{
+	struct hwrm_port_mac_cfg_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1);
+
+	req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_LPBK);
+	if (enable)
+		req.lpbk = PORT_MAC_CFG_REQ_LPBK_LOCAL;
+	else
+		req.lpbk = PORT_MAC_CFG_REQ_LPBK_NONE;
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
+				    struct hwrm_port_phy_cfg_input *req)
+{
+	struct bnxt_link_info *link_info = &bp->link_info;
+	u16 fw_advertising = link_info->advertising;
+	u16 fw_speed;
+	int rc;
+
+	if (!link_info->autoneg)
+		return 0;
+
+	fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
+	if (netif_carrier_ok(bp->dev))
+		fw_speed = bp->link_info.link_speed;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_10GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_25GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_40GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_50GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB;
+
+	req->force_link_speed = cpu_to_le16(fw_speed);
+	req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE |
+				  PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
+	rc = hwrm_send_message(bp, req, sizeof(*req), HWRM_CMD_TIMEOUT);
+	req->flags = 0;
+	req->force_link_speed = cpu_to_le16(0);
+	return rc;
+}
+
+static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
+{
+	struct hwrm_port_phy_cfg_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
+
+	if (enable) {
+		bnxt_disable_an_for_lpbk(bp, &req);
+		req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
+	} else {
+		req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
+	}
+	req.enables = cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_LPBK);
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_rx_loopback(struct bnxt *bp, struct bnxt_napi *bnapi,
+			    u32 raw_cons, int pkt_size)
+{
+	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	struct bnxt_sw_rx_bd *rx_buf;
+	struct rx_cmp *rxcmp;
+	u16 cp_cons, cons;
+	u8 *data;
+	u32 len;
+	int i;
+
+	cp_cons = RING_CMP(raw_cons);
+	rxcmp = (struct rx_cmp *)
+		&cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)];
+	cons = rxcmp->rx_cmp_opaque;
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data_ptr;
+	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
+	if (len != pkt_size)
+		return -EIO;
+	i = ETH_ALEN;
+	if (!ether_addr_equal(data + i, bnapi->bp->dev->dev_addr))
+		return -EIO;
+	i += ETH_ALEN;
+	for (  ; i < pkt_size; i++) {
+		if (data[i] != (u8)(i & 0xff))
+			return -EIO;
+	}
+	return 0;
+}
+
+static int bnxt_poll_loopback(struct bnxt *bp, int pkt_size)
+{
+	struct bnxt_napi *bnapi = bp->bnapi[0];
+	struct bnxt_cp_ring_info *cpr;
+	struct tx_cmp *txcmp;
+	int rc = -EIO;
+	u32 raw_cons;
+	u32 cons;
+	int i;
+
+	cpr = &bnapi->cp_ring;
+	raw_cons = cpr->cp_raw_cons;
+	for (i = 0; i < 200; i++) {
+		cons = RING_CMP(raw_cons);
+		txcmp = &cpr->cp_desc_ring[CP_RING(cons)][CP_IDX(cons)];
+
+		if (!TX_CMP_VALID(txcmp, raw_cons)) {
+			udelay(5);
+			continue;
+		}
+
+		/* The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP) {
+			rc = bnxt_rx_loopback(bp, bnapi, raw_cons, pkt_size);
+			raw_cons = NEXT_RAW_CMP(raw_cons);
+			raw_cons = NEXT_RAW_CMP(raw_cons);
+			break;
+		}
+		raw_cons = NEXT_RAW_CMP(raw_cons);
+	}
+	cpr->cp_raw_cons = raw_cons;
+	return rc;
+}
+
+static int bnxt_run_loopback(struct bnxt *bp)
+{
+	struct bnxt_tx_ring_info *txr = &bp->tx_ring[0];
+	int pkt_size, i = 0;
+	struct sk_buff *skb;
+	dma_addr_t map;
+	u8 *data;
+	int rc;
+
+	pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
+	skb = netdev_alloc_skb(bp->dev, pkt_size);
+	if (!skb)
+		return -ENOMEM;
+	data = skb_put(skb, pkt_size);
+	eth_broadcast_addr(data);
+	i += ETH_ALEN;
+	ether_addr_copy(&data[i], bp->dev->dev_addr);
+	i += ETH_ALEN;
+	for ( ; i < pkt_size; i++)
+		data[i] = (u8)(i & 0xff);
+
+	map = dma_map_single(&bp->pdev->dev, skb->data, pkt_size,
+			     PCI_DMA_TODEVICE);
+	if (dma_mapping_error(&bp->pdev->dev, map)) {
+		dev_kfree_skb(skb);
+		return -EIO;
+	}
+	bnxt_xmit_xdp(bp, txr, map, pkt_size, 0);
+
+	/* Sync BD data before updating doorbell */
+	wmb();
+
+	writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+	writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+	rc = bnxt_poll_loopback(bp, pkt_size);
+
+	dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE);
+	dev_kfree_skb(skb);
+	return rc;
+}
+
+static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results)
+{
+	struct hwrm_selftest_exec_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_selftest_exec_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_EXEC, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	resp->test_success = 0;
+	req.flags = test_mask;
+	rc = _hwrm_send_message(bp, &req, sizeof(req), bp->test_info->timeout);
+	*test_results = resp->test_success;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+#define BNXT_DRV_TESTS			3
+#define BNXT_MACLPBK_TEST_IDX		(bp->num_tests - BNXT_DRV_TESTS)
+#define BNXT_PHYLPBK_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 1)
+#define BNXT_IRQ_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 2)
+
+static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
+			   u64 *buf)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	bool offline = false;
+	u8 test_results = 0;
+	u8 test_mask = 0;
+	int rc, i;
+
+	if (!bp->num_tests || !BNXT_SINGLE_PF(bp))
+		return;
+	memset(buf, 0, sizeof(u64) * bp->num_tests);
+	if (!netif_running(dev)) {
+		etest->flags |= ETH_TEST_FL_FAILED;
+		return;
+	}
+
+	if (etest->flags & ETH_TEST_FL_OFFLINE) {
+		if (bp->pf.active_vfs) {
+			etest->flags |= ETH_TEST_FL_FAILED;
+			netdev_warn(dev, "Offline tests cannot be run with active VFs\n");
+			return;
+		}
+		offline = true;
+	}
+
+	for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) {
+		u8 bit_val = 1 << i;
+
+		if (!(bp->test_info->offline_mask & bit_val))
+			test_mask |= bit_val;
+		else if (offline)
+			test_mask |= bit_val;
+	}
+	if (!offline) {
+		bnxt_run_fw_tests(bp, test_mask, &test_results);
+	} else {
+		rc = bnxt_close_nic(bp, false, false);
+		if (rc)
+			return;
+		bnxt_run_fw_tests(bp, test_mask, &test_results);
+
+		buf[BNXT_MACLPBK_TEST_IDX] = 1;
+		bnxt_hwrm_mac_loopback(bp, true);
+		msleep(250);
+		rc = bnxt_half_open_nic(bp);
+		if (rc) {
+			bnxt_hwrm_mac_loopback(bp, false);
+			etest->flags |= ETH_TEST_FL_FAILED;
+			return;
+		}
+		if (bnxt_run_loopback(bp))
+			etest->flags |= ETH_TEST_FL_FAILED;
+		else
+			buf[BNXT_MACLPBK_TEST_IDX] = 0;
+
+		bnxt_hwrm_mac_loopback(bp, false);
+		bnxt_hwrm_phy_loopback(bp, true);
+		msleep(1000);
+		if (bnxt_run_loopback(bp)) {
+			buf[BNXT_PHYLPBK_TEST_IDX] = 1;
+			etest->flags |= ETH_TEST_FL_FAILED;
+		}
+		bnxt_hwrm_phy_loopback(bp, false);
+		bnxt_half_close_nic(bp);
+		bnxt_open_nic(bp, false, true);
+	}
+	if (bnxt_test_irq(bp)) {
+		buf[BNXT_IRQ_TEST_IDX] = 1;
+		etest->flags |= ETH_TEST_FL_FAILED;
+	}
+	for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) {
+		u8 bit_val = 1 << i;
+
+		if ((test_mask & bit_val) && !(test_results & bit_val)) {
+			buf[i] = 1;
+			etest->flags |= ETH_TEST_FL_FAILED;
+		}
+	}
+}
+
+void bnxt_ethtool_init(struct bnxt *bp)
+{
+	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_selftest_qlist_input req = {0};
+	struct bnxt_test_info *test_info;
+	int i, rc;
+
+	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
+		return;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_QLIST, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto ethtool_init_exit;
+
+	test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL);
+	if (!test_info)
+		goto ethtool_init_exit;
+
+	bp->test_info = test_info;
+	bp->num_tests = resp->num_tests + BNXT_DRV_TESTS;
+	if (bp->num_tests > BNXT_MAX_TEST)
+		bp->num_tests = BNXT_MAX_TEST;
+
+	test_info->offline_mask = resp->offline_tests;
+	test_info->timeout = le16_to_cpu(resp->test_timeout);
+	if (!test_info->timeout)
+		test_info->timeout = HWRM_CMD_TIMEOUT;
+	for (i = 0; i < bp->num_tests; i++) {
+		char *str = test_info->string[i];
+		char *fw_str = resp->test0_name + i * 32;
+
+		if (i == BNXT_MACLPBK_TEST_IDX) {
+			strcpy(str, "Mac loopback test (offline)");
+		} else if (i == BNXT_PHYLPBK_TEST_IDX) {
+			strcpy(str, "Phy loopback test (offline)");
+		} else if (i == BNXT_IRQ_TEST_IDX) {
+			strcpy(str, "Interrupt_test (offline)");
+		} else {
+			strlcpy(str, fw_str, ETH_GSTRING_LEN);
+			strncat(str, " test", ETH_GSTRING_LEN - strlen(str));
+			if (test_info->offline_mask & (1 << i))
+				strncat(str, " (offline)",
+					ETH_GSTRING_LEN - strlen(str));
+			else
+				strncat(str, " (online)",
+					ETH_GSTRING_LEN - strlen(str));
+		}
+	}
+
+ethtool_init_exit:
+	mutex_unlock(&bp->hwrm_cmd_lock);
+}
+
+void bnxt_ethtool_free(struct bnxt *bp)
+{
+	kfree(bp->test_info);
+	bp->test_info = NULL;
+}
+
 const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_link_ksettings	= bnxt_get_link_ksettings,
 	.set_link_ksettings	= bnxt_set_link_ksettings,
 	.get_pauseparam		= bnxt_get_pauseparam,
 	.set_pauseparam		= bnxt_set_pauseparam,
 	.get_drvinfo		= bnxt_get_drvinfo,
+	.get_wol		= bnxt_get_wol,
+	.set_wol		= bnxt_set_wol,
 	.get_coalesce		= bnxt_get_coalesce,
 	.set_coalesce		= bnxt_set_coalesce,
 	.get_msglevel		= bnxt_get_msglevel,
@@ -2161,4 +2583,5 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_module_eeprom	= bnxt_get_module_eeprom,
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
+	.self_test		= bnxt_self_test,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index ed1e555292e9..f1bc90b6fb5b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -38,5 +39,7 @@ extern const struct ethtool_ops bnxt_ethtool_ops;
 u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8);
 u32 bnxt_fw_to_ethtool_speed(u16);
 u16 bnxt_get_fw_auto_link_speeds(u32);
+void bnxt_ethtool_init(struct bnxt *bp);
+void bnxt_ethtool_free(struct bnxt *bp);
 
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 6e275c23d68b..7dc71bb95837 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -11,19 +11,21 @@
 #ifndef BNXT_HSI_H
 #define BNXT_HSI_H
 
-/* HSI and HWRM Specification 1.7.0 */
+/* HSI and HWRM Specification 1.7.6 */
 #define HWRM_VERSION_MAJOR	1
 #define HWRM_VERSION_MINOR	7
-#define HWRM_VERSION_UPDATE	0
+#define HWRM_VERSION_UPDATE	6
 
-#define HWRM_VERSION_STR	"1.7.0"
+#define HWRM_VERSION_RSVD	2 /* non-zero means beta version */
+
+#define HWRM_VERSION_STR	"1.7.6.2"
 /*
  * Following is the signature for HWRM message field that indicates not
  * applicable (All F's). Need to cast it the size of the field if needed.
  */
 #define HWRM_NA_SIGNATURE	((__le32)(-1))
 #define HWRM_MAX_REQ_LEN    (128)  /* hwrm_func_buf_rgtr */
-#define HWRM_MAX_RESP_LEN    (176)  /* hwrm_func_qstats */
+#define HWRM_MAX_RESP_LEN    (248)  /* hwrm_selftest_qlist */
 #define HW_HASH_INDEX_SIZE      0x80    /* 7 bit indirection table index. */
 #define HW_HASH_KEY_SIZE	40
 #define HWRM_RESP_VALID_KEY      1 /* valid key for HWRM response */
@@ -571,9 +573,10 @@ struct hwrm_ver_get_output {
 	__le16 max_req_win_len;
 	__le16 max_resp_len;
 	__le16 def_req_timeout;
+	u8 init_pending;
+	#define VER_GET_RESP_INIT_PENDING_DEV_NOT_RDY		    0x1UL
 	u8 unused_0;
 	u8 unused_1;
-	u8 unused_2;
 	u8 valid;
 };
 
@@ -809,6 +812,8 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED	    0x2UL
 	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED	    0x4UL
 	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED      0x8UL
+	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED	    0x10UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST			    0x20UL
 	u8 mac_address[6];
 	__le16 pci_id;
 	__le16 alloc_rsscos_ctx;
@@ -827,10 +832,12 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5	   0x3UL
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0	   0x4UL
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN	   0xffUL
-	u8 unused_0;
+	u8 port_pf_cnt;
+	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL		   0x0UL
 	__le16 dflt_vnic_id;
-	u8 unused_1;
-	u8 unused_2;
+	u8 host_cnt;
+	#define FUNC_QCFG_RESP_HOST_CNT_UNAVAIL		   0x0UL
+	u8 unused_0;
 	__le32 min_bw;
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK		    0xfffffffUL
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT		    0
@@ -867,12 +874,12 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB			   0x0UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEB			   0x1UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA			   0x2UL
-	u8 unused_3;
+	u8 unused_1;
 	__le16 alloc_vfs;
 	__le32 alloc_mcast_filters;
 	__le32 alloc_hw_ring_grps;
 	__le16 alloc_sp_tx_rings;
-	u8 unused_4;
+	u8 unused_2;
 	u8 valid;
 };
 
@@ -888,16 +895,13 @@ struct hwrm_func_cfg_input {
 	u8 unused_0;
 	u8 unused_1;
 	__le32 flags;
-	#define FUNC_CFG_REQ_FLAGS_PROM_MODE			    0x1UL
-	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK		    0x2UL
-	#define FUNC_CFG_REQ_FLAGS_SRC_IP_ADDR_CHECK		    0x4UL
-	#define FUNC_CFG_REQ_FLAGS_VLAN_PRI_MATCH		    0x8UL
-	#define FUNC_CFG_REQ_FLAGS_DFLT_PRI_NOMATCH		    0x10UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_PAUSE		    0x20UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_STP			    0x40UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_LLDP		    0x80UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_PTPV2		    0x100UL
-	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE		    0x200UL
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE      0x1UL
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE       0x2UL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_MASK			    0x1fcUL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_SFT			    2
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE	    0x200UL
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE	    0x400UL
+	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST		    0x800UL
 	__le32 enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU			    0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU			    0x2UL
@@ -1013,7 +1017,7 @@ struct hwrm_func_qstats_output {
 	__le64 tx_ucast_pkts;
 	__le64 tx_mcast_pkts;
 	__le64 tx_bcast_pkts;
-	__le64 tx_err_pkts;
+	__le64 tx_discard_pkts;
 	__le64 tx_drop_pkts;
 	__le64 tx_ucast_bytes;
 	__le64 tx_mcast_bytes;
@@ -1021,7 +1025,7 @@ struct hwrm_func_qstats_output {
 	__le64 rx_ucast_pkts;
 	__le64 rx_mcast_pkts;
 	__le64 rx_bcast_pkts;
-	__le64 rx_err_pkts;
+	__le64 rx_discard_pkts;
 	__le64 rx_drop_pkts;
 	__le64 rx_ucast_bytes;
 	__le64 rx_mcast_bytes;
@@ -4743,25 +4747,72 @@ struct hwrm_temp_monitor_query_output {
 	u8 valid;
 };
 
-/* hwrm_nvm_read */
-/* Input (40 bytes) */
-struct hwrm_nvm_read_input {
+/* hwrm_wol_filter_alloc */
+/* Input (64 bytes) */
+struct hwrm_wol_filter_alloc_input {
 	__le16 req_type;
 	__le16 cmpl_ring;
 	__le16 seq_id;
 	__le16 target_id;
 	__le64 resp_addr;
-	__le64 host_dest_addr;
-	__le16 dir_idx;
+	__le32 flags;
+	__le32 enables;
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS	    0x1UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET	    0x2UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE      0x4UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR      0x8UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR     0x10UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE     0x20UL
+	__le16 port_id;
+	u8 wol_type;
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT		   0x0UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP		   0x1UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID		   0xffUL
 	u8 unused_0;
-	u8 unused_1;
-	__le32 offset;
-	__le32 len;
+	__le32 unused_1;
+	u8 mac_address[6];
+	__le16 pattern_offset;
+	__le16 pattern_buf_size;
+	__le16 pattern_mask_size;
 	__le32 unused_2;
+	__le64 pattern_buf_addr;
+	__le64 pattern_mask_addr;
 };
 
 /* Output (16 bytes) */
-struct hwrm_nvm_read_output {
+struct hwrm_wol_filter_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 wol_filter_id;
+	u8 unused_0;
+	__le16 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 valid;
+};
+
+/* hwrm_wol_filter_free */
+/* Input (32 bytes) */
+struct hwrm_wol_filter_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 flags;
+	#define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS     0x1UL
+	__le32 enables;
+	#define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID	    0x1UL
+	__le16 port_id;
+	u8 wol_filter_id;
+	u8 unused_0[5];
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_filter_free_output {
 	__le16 error_code;
 	__le16 req_type;
 	__le16 seq_id;
@@ -4773,21 +4824,107 @@ struct hwrm_nvm_read_output {
 	u8 valid;
 };
 
-/* hwrm_nvm_raw_dump */
-/* Input (32 bytes) */
-struct hwrm_nvm_raw_dump_input {
+/* hwrm_wol_filter_qcfg */
+/* Input (56 bytes) */
+struct hwrm_wol_filter_qcfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 port_id;
+	__le16 handle;
+	__le32 unused_0;
+	__le64 pattern_buf_addr;
+	__le16 pattern_buf_size;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3[3];
+	u8 unused_4;
+	__le64 pattern_mask_addr;
+	__le16 pattern_mask_size;
+	__le16 unused_5[3];
+};
+
+/* Output (32 bytes) */
+struct hwrm_wol_filter_qcfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 next_handle;
+	u8 wol_filter_id;
+	u8 wol_type;
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT		   0x0UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP		   0x1UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID		   0xffUL
+	__le32 unused_0;
+	u8 mac_address[6];
+	__le16 pattern_offset;
+	__le16 pattern_size;
+	__le16 pattern_mask_size;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_wol_reason_qcfg */
+/* Input (40 bytes) */
+struct hwrm_wol_reason_qcfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 port_id;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2[3];
+	u8 unused_3;
+	__le64 wol_pkt_buf_addr;
+	__le16 wol_pkt_buf_size;
+	__le16 unused_4[3];
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_reason_qcfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 wol_filter_id;
+	u8 wol_reason;
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT	   0x0UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_BMP		   0x1UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID	   0xffUL
+	u8 wol_pkt_len;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_nvm_read */
+/* Input (40 bytes) */
+struct hwrm_nvm_read_input {
 	__le16 req_type;
 	__le16 cmpl_ring;
 	__le16 seq_id;
 	__le16 target_id;
 	__le64 resp_addr;
 	__le64 host_dest_addr;
+	__le16 dir_idx;
+	u8 unused_0;
+	u8 unused_1;
 	__le32 offset;
 	__le32 len;
+	__le32 unused_2;
 };
 
 /* Output (16 bytes) */
-struct hwrm_nvm_raw_dump_output {
+struct hwrm_nvm_read_output {
 	__le16 error_code;
 	__le16 req_type;
 	__le16 seq_id;
@@ -4881,6 +5018,15 @@ struct hwrm_nvm_write_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_write_cmd_err {
+	u8 code;
+	#define NVM_WRITE_CMD_ERR_CODE_UNKNOWN			   0x0UL
+	#define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR		   0x1UL
+	#define NVM_WRITE_CMD_ERR_CODE_NO_SPACE		   0x2UL
+	u8 unused_0[7];
+};
+
 /* hwrm_nvm_modify */
 /* Input (40 bytes) */
 struct hwrm_nvm_modify_input {
@@ -5112,6 +5258,100 @@ struct hwrm_nvm_install_update_cmd_err {
 	u8 unused_0[7];
 };
 
+/* hwrm_selftest_qlist */
+/* Input (16 bytes) */
+struct hwrm_selftest_qlist_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+};
+
+/* Output (248 bytes) */
+struct hwrm_selftest_qlist_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 num_tests;
+	u8 available_tests;
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST       0x1UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST      0x2UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST  0x4UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST    0x8UL
+	u8 offline_tests;
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST	    0x1UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST	    0x2UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST    0x4UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST      0x8UL
+	u8 unused_0;
+	__le16 test_timeout;
+	u8 unused_1;
+	u8 unused_2;
+	char test0_name[32];
+	char test1_name[32];
+	char test2_name[32];
+	char test3_name[32];
+	char test4_name[32];
+	char test5_name[32];
+	char test6_name[32];
+	char test7_name[32];
+};
+
+/* hwrm_selftest_exec */
+/* Input (24 bytes) */
+struct hwrm_selftest_exec_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	u8 flags;
+	#define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST		    0x1UL
+	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST		    0x2UL
+	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST		    0x4UL
+	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST		    0x8UL
+	u8 unused_0[7];
+};
+
+/* Output (16 bytes) */
+struct hwrm_selftest_exec_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 requested_tests;
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST	    0x1UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST       0x2UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST   0x4UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST     0x8UL
+	u8 test_success;
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST	    0x1UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST	    0x2UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST      0x4UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST	    0x8UL
+	__le16 unused_0[3];
+};
+
+/* hwrm_selftest_irq */
+/* Input (16 bytes) */
+struct hwrm_selftest_irq_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+};
+
+/* Output (8 bytes) */
+struct hwrm_selftest_irq_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+};
+
 /* Hardware Resource Manager Specification */
 /* Input (16 bytes) */
 struct input {
@@ -5130,6 +5370,16 @@ struct output {
 	__le16 resp_len;
 };
 
+/* Short Command Structure (16 bytes) */
+struct hwrm_short_input {
+	__le16 req_type;
+	__le16 signature;
+	#define SHORT_REQ_SIGNATURE_SHORT_CMD			   0x4321UL
+	__le16 unused_0;
+	__le16 size;
+	__le64 req_addr;
+};
+
 /* Command numbering (8 bytes) */
 struct cmd_nums {
 	__le16 req_type;
@@ -5252,11 +5502,15 @@ struct cmd_nums {
 	#define HWRM_CFA_FLOW_FLUSH				   (0x105UL)
 	#define HWRM_CFA_FLOW_STATS				   (0x106UL)
 	#define HWRM_CFA_FLOW_INFO				   (0x107UL)
+	#define HWRM_SELFTEST_QLIST				   (0x200UL)
+	#define HWRM_SELFTEST_EXEC				   (0x201UL)
+	#define HWRM_SELFTEST_IRQ				   (0x202UL)
 	#define HWRM_DBG_READ_DIRECT				   (0xff10UL)
 	#define HWRM_DBG_READ_INDIRECT				   (0xff11UL)
 	#define HWRM_DBG_WRITE_DIRECT				   (0xff12UL)
 	#define HWRM_DBG_WRITE_INDIRECT			   (0xff13UL)
 	#define HWRM_DBG_DUMP					   (0xff14UL)
+	#define HWRM_NVM_FACTORY_DEFAULTS			   (0xffeeUL)
 	#define HWRM_NVM_VALIDATE_OPTION			   (0xffefUL)
 	#define HWRM_NVM_FLUSH					   (0xfff0UL)
 	#define HWRM_NVM_GET_VARIABLE				   (0xfff1UL)
@@ -5464,6 +5718,7 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE	   0x422UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC		   0x424UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE		   0x426UL
+	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE		   0x1UL
 	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION		   0xaUL
 	__le16 len;
 	u8 version;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 0b8cd7443843..b8e7248294d9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -84,6 +85,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	u32 func_flags;
 	int rc;
 
+	if (bp->hwrm_spec_code < 0x10701)
+		return -ENOTSUPP;
+
 	rc = bnxt_vf_ndo_prep(bp, vf_id);
 	if (rc)
 		return rc;
@@ -96,9 +100,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 
 	func_flags = vf->func_flags;
 	if (setting)
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK;
+		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
 	else
-		func_flags &= ~FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK;
+		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
 	/*TODO: if the driver supports VLAN filter on guest VLAN,
 	 * the spoof check should also include vlan anti-spoofing
 	 */
@@ -134,8 +138,11 @@ int bnxt_get_vf_config(struct net_device *dev, int vf_id,
 	ivi->max_tx_rate = vf->max_tx_rate;
 	ivi->min_tx_rate = vf->min_tx_rate;
 	ivi->vlan = vf->vlan;
-	ivi->qos = vf->flags & BNXT_VF_QOS;
-	ivi->spoofchk = vf->flags & BNXT_VF_SPOOFCHK;
+	if (vf->flags & BNXT_VF_QOS)
+		ivi->qos = vf->vlan >> VLAN_PRIO_SHIFT;
+	else
+		ivi->qos = 0;
+	ivi->spoofchk = !!(vf->flags & BNXT_VF_SPOOFCHK);
 	if (!(vf->flags & BNXT_VF_LINK_FORCED))
 		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
 	else if (vf->flags & BNXT_VF_LINK_UP)
@@ -300,7 +307,6 @@ static int bnxt_set_vf_attr(struct bnxt *bp, int num_vfs)
 	for (i = 0; i < num_vfs; i++) {
 		vf = &bp->pf.vf[i];
 		memset(vf, 0, sizeof(*vf));
-		vf->flags = BNXT_VF_QOS | BNXT_VF_LINK_UP;
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
index 1ab72e4820af..dbc8d977fc5a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 899c30fb5188..9dae32756767 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -19,11 +19,10 @@
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 
-static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			  dma_addr_t mapping, u32 len, u16 rx_prod)
+void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+		   dma_addr_t mapping, u32 len, u16 rx_prod)
 {
 	struct bnxt_sw_tx_bd *tx_buf;
-	struct tx_bd_ext *txbd1;
 	struct tx_bd *txbd;
 	u32 flags;
 	u16 prod;
@@ -33,23 +32,13 @@ static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	tx_buf->rx_prod = rx_prod;
 
 	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
-	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
-		(2 << TX_BD_FLAGS_BD_CNT_SHIFT) | TX_BD_FLAGS_COAL_NOW |
+	flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) |
 		TX_BD_FLAGS_PACKET_END | bnxt_lhint_arr[len >> 9];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 	txbd->tx_bd_opaque = prod;
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
 	prod = NEXT_TX(prod);
-	txbd1 = (struct tx_bd_ext *)
-		&txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
-
-	txbd1->tx_bd_hsize_lflags = cpu_to_le32(0);
-	txbd1->tx_bd_mss = cpu_to_le32(0);
-	txbd1->tx_bd_cfa_action = cpu_to_le32(0);
-	txbd1->tx_bd_cfa_meta = cpu_to_le32(0);
-
-	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
 }
 
@@ -66,7 +55,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 	for (i = 0; i < nr_pkts; i++) {
 		last_tx_cons = tx_cons;
 		tx_cons = NEXT_TX(tx_cons);
-		tx_cons = NEXT_TX(tx_cons);
 	}
 	txr->tx_cons = tx_cons;
 	if (bnxt_tx_avail(bp, txr) == bp->tx_ring_size) {
@@ -133,7 +121,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		return false;
 
 	case XDP_TX:
-		if (tx_avail < 2) {
+		if (tx_avail < 1) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
 			bnxt_reuse_rx_data(rxr, cons, page);
 			return true;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index b529f2c5355b..12a5ad66b564 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -10,6 +10,8 @@
 #ifndef BNXT_XDP_H
 #define BNXT_XDP_H
 
+void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+		   dma_addr_t mapping, u32 len, u16 rx_prod);
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 struct page *page, u8 **data_ptr, unsigned int *len,
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f92896835d2a..a205a9ff9e17 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -450,6 +450,22 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
 			genet_dma_ring_regs[r]);
 }
 
+static int bcmgenet_begin(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+
+	/* Turn on the clock */
+	return clk_prepare_enable(priv->clk);
+}
+
+static void bcmgenet_complete(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+
+	/* Turn off the clock */
+	clk_disable_unprepare(priv->clk);
+}
+
 static int bcmgenet_get_link_ksettings(struct net_device *dev,
 				       struct ethtool_link_ksettings *cmd)
 {
@@ -605,7 +621,7 @@ static int bcmgenet_set_coalesce(struct net_device *dev,
 
 	/* GENET TDMA hardware does not support a configurable timeout, but will
 	 * always generate an interrupt either after MBDONE packets have been
-	 * transmitted, or when the ring is emtpy.
+	 * transmitted, or when the ring is empty.
 	 */
 	if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high ||
 	    ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low)
@@ -691,6 +707,19 @@ struct bcmgenet_stats {
 	.reg_offset = offset, \
 }
 
+#define STAT_GENET_Q(num) \
+	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
+			tx_rings[num].packets), \
+	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
+			tx_rings[num].bytes), \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
+			rx_rings[num].bytes),	 \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
+			rx_rings[num].packets), \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
+			rx_rings[num].errors), \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
+			rx_rings[num].dropped)
 
 /* There is a 0xC gap between the end of RX and beginning of TX stats and then
  * between the end of TX stats and the beginning of the RX RUNT
@@ -778,12 +807,19 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes),
 	/* Misc UniMAC counters */
 	STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt,
-			UMAC_RBUF_OVFL_CNT),
-	STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, UMAC_RBUF_ERR_CNT),
+			UMAC_RBUF_OVFL_CNT_V1),
+	STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt,
+			UMAC_RBUF_ERR_CNT_V1),
 	STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT),
 	STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
 	STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed),
 	STAT_GENET_SOFT_MIB("tx_dma_failed", mib.tx_dma_failed),
+	/* Per TX queues */
+	STAT_GENET_Q(0),
+	STAT_GENET_Q(1),
+	STAT_GENET_Q(2),
+	STAT_GENET_Q(3),
+	STAT_GENET_Q(16),
 };
 
 #define BCMGENET_STATS_LEN	ARRAY_SIZE(bcmgenet_gstrings_stats)
@@ -821,6 +857,45 @@ static void bcmgenet_get_strings(struct net_device *dev, u32 stringset,
 	}
 }
 
+static u32 bcmgenet_update_stat_misc(struct bcmgenet_priv *priv, u16 offset)
+{
+	u16 new_offset;
+	u32 val;
+
+	switch (offset) {
+	case UMAC_RBUF_OVFL_CNT_V1:
+		if (GENET_IS_V2(priv))
+			new_offset = RBUF_OVFL_CNT_V2;
+		else
+			new_offset = RBUF_OVFL_CNT_V3PLUS;
+
+		val = bcmgenet_rbuf_readl(priv,	new_offset);
+		/* clear if overflowed */
+		if (val == ~0)
+			bcmgenet_rbuf_writel(priv, 0, new_offset);
+		break;
+	case UMAC_RBUF_ERR_CNT_V1:
+		if (GENET_IS_V2(priv))
+			new_offset = RBUF_ERR_CNT_V2;
+		else
+			new_offset = RBUF_ERR_CNT_V3PLUS;
+
+		val = bcmgenet_rbuf_readl(priv,	new_offset);
+		/* clear if overflowed */
+		if (val == ~0)
+			bcmgenet_rbuf_writel(priv, 0, new_offset);
+		break;
+	default:
+		val = bcmgenet_umac_readl(priv, offset);
+		/* clear if overflowed */
+		if (val == ~0)
+			bcmgenet_umac_writel(priv, 0, offset);
+		break;
+	}
+
+	return val;
+}
+
 static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 {
 	int i, j = 0;
@@ -836,19 +911,28 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 		case BCMGENET_STAT_NETDEV:
 		case BCMGENET_STAT_SOFT:
 			continue;
-		case BCMGENET_STAT_MIB_RX:
-		case BCMGENET_STAT_MIB_TX:
 		case BCMGENET_STAT_RUNT:
-			if (s->type != BCMGENET_STAT_MIB_RX)
-				offset = BCMGENET_STAT_OFFSET;
+			offset += BCMGENET_STAT_OFFSET;
+			/* fall through */
+		case BCMGENET_STAT_MIB_TX:
+			offset += BCMGENET_STAT_OFFSET;
+			/* fall through */
+		case BCMGENET_STAT_MIB_RX:
 			val = bcmgenet_umac_readl(priv,
 						  UMAC_MIB_START + j + offset);
+			offset = 0;	/* Reset Offset */
 			break;
 		case BCMGENET_STAT_MISC:
-			val = bcmgenet_umac_readl(priv, s->reg_offset);
-			/* clear if overflowed */
-			if (val == ~0)
-				bcmgenet_umac_writel(priv, 0, s->reg_offset);
+			if (GENET_IS_V1(priv)) {
+				val = bcmgenet_umac_readl(priv, s->reg_offset);
+				/* clear if overflowed */
+				if (val == ~0)
+					bcmgenet_umac_writel(priv, 0,
+							     s->reg_offset);
+			} else {
+				val = bcmgenet_update_stat_misc(priv,
+								s->reg_offset);
+			}
 			break;
 		}
 
@@ -973,6 +1057,8 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 
 /* standard ethtool support functions. */
 static const struct ethtool_ops bcmgenet_ethtool_ops = {
+	.begin			= bcmgenet_begin,
+	.complete		= bcmgenet_complete,
 	.get_strings		= bcmgenet_get_strings,
 	.get_sset_count		= bcmgenet_get_sset_count,
 	.get_ethtool_stats	= bcmgenet_get_ethtool_stats,
@@ -1011,8 +1097,17 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 		/* Power down LED */
 		if (priv->hw_params->flags & GENET_HAS_EXT) {
 			reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-			reg |= (EXT_PWR_DOWN_PHY |
-				EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+			if (GENET_IS_V5(priv))
+				reg |= EXT_PWR_DOWN_PHY_EN |
+				       EXT_PWR_DOWN_PHY_RD |
+				       EXT_PWR_DOWN_PHY_SD |
+				       EXT_PWR_DOWN_PHY_RX |
+				       EXT_PWR_DOWN_PHY_TX |
+				       EXT_IDDQ_GLBL_PWR;
+			else
+				reg |= EXT_PWR_DOWN_PHY;
+
+			reg |= (EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
 			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 
 			bcmgenet_phy_power_set(priv->dev, false);
@@ -1037,12 +1132,34 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 
 	switch (mode) {
 	case GENET_POWER_PASSIVE:
-		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY |
-				EXT_PWR_DOWN_BIAS);
-		/* fallthrough */
+		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+		if (GENET_IS_V5(priv)) {
+			reg &= ~(EXT_PWR_DOWN_PHY_EN |
+				 EXT_PWR_DOWN_PHY_RD |
+				 EXT_PWR_DOWN_PHY_SD |
+				 EXT_PWR_DOWN_PHY_RX |
+				 EXT_PWR_DOWN_PHY_TX |
+				 EXT_IDDQ_GLBL_PWR);
+			reg |=   EXT_PHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+			mdelay(1);
+
+			reg &=  ~EXT_PHY_RESET;
+		} else {
+			reg &= ~EXT_PWR_DOWN_PHY;
+			reg |= EXT_PWR_DN_EN_LD;
+		}
+		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+		bcmgenet_phy_power_set(priv->dev, true);
+		bcmgenet_mii_reset(priv->dev);
+		break;
+
 	case GENET_POWER_CABLE_SENSE:
 		/* enable APD */
-		reg |= EXT_PWR_DN_EN_LD;
+		if (!GENET_IS_V5(priv)) {
+			reg |= EXT_PWR_DN_EN_LD;
+			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+		}
 		break;
 	case GENET_POWER_WOL_MAGIC:
 		bcmgenet_wol_power_up_cfg(priv, mode);
@@ -1050,39 +1167,20 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 	default:
 		break;
 	}
-
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	if (mode == GENET_POWER_PASSIVE) {
-		bcmgenet_phy_power_set(priv->dev, true);
-		bcmgenet_mii_reset(priv->dev);
-	}
 }
 
 /* ioctl handle special commands that are not present in ethtool. */
 static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int val = 0;
 
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		if (!priv->phydev)
-			val = -ENODEV;
-		else
-			val = phy_mii_ioctl(priv->phydev, rq, cmd);
-		break;
-
-	default:
-		val = -EINVAL;
-		break;
-	}
+	if (!priv->phydev)
+		return -ENODEV;
 
-	return val;
+	return phy_mii_ioctl(priv->phydev, rq, cmd);
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1167,21 +1265,24 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
-	struct netdev_queue *txq;
 	unsigned int pkts_compl = 0;
 	unsigned int bytes_compl = 0;
 	unsigned int c_index;
 	unsigned int txbds_ready;
 	unsigned int txbds_processed = 0;
 
-	/* Compute how many buffers are transmitted since last xmit call */
-	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
-	c_index &= DMA_C_INDEX_MASK;
-
-	if (likely(c_index >= ring->c_index))
-		txbds_ready = c_index - ring->c_index;
+	/* Clear status before servicing to reduce spurious interrupts */
+	if (ring->index == DESC_INDEX)
+		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
+					 INTRL2_CPU_CLEAR);
 	else
-		txbds_ready = (DMA_C_INDEX_MASK + 1) - ring->c_index + c_index;
+		bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
+					 INTRL2_CPU_CLEAR);
+
+	/* Compute how many buffers are transmitted since last xmit call */
+	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
+		& DMA_C_INDEX_MASK;
+	txbds_ready = (c_index - ring->c_index) & DMA_C_INDEX_MASK;
 
 	netif_dbg(priv, tx_done, dev,
 		  "%s ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
@@ -1214,20 +1315,15 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	}
 
 	ring->free_bds += txbds_processed;
-	ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK;
+	ring->c_index = c_index;
 
-	dev->stats.tx_packets += pkts_compl;
-	dev->stats.tx_bytes += bytes_compl;
+	ring->packets += pkts_compl;
+	ring->bytes += bytes_compl;
 
-	txq = netdev_get_tx_queue(dev, ring->queue);
-	netdev_tx_completed_queue(txq, pkts_compl, bytes_compl);
-
-	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
-		if (netif_tx_queue_stopped(txq))
-			netif_tx_wake_queue(txq);
-	}
+	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
+				  pkts_compl, bytes_compl);
 
-	return pkts_compl;
+	return txbds_processed;
 }
 
 static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
@@ -1248,8 +1344,16 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 	struct bcmgenet_tx_ring *ring =
 		container_of(napi, struct bcmgenet_tx_ring, napi);
 	unsigned int work_done = 0;
+	struct netdev_queue *txq;
+	unsigned long flags;
 
-	work_done = bcmgenet_tx_reclaim(ring->priv->dev, ring);
+	spin_lock_irqsave(&ring->lock, flags);
+	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
+	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
+		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
+		netif_tx_wake_queue(txq);
+	}
+	spin_unlock_irqrestore(&ring->lock, flags);
 
 	if (work_done == 0) {
 		napi_complete(napi);
@@ -1588,18 +1692,28 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	unsigned long dma_flag;
 	int len;
 	unsigned int rxpktprocessed = 0, rxpkttoprocess;
-	unsigned int p_index;
+	unsigned int p_index, mask;
 	unsigned int discards;
 	unsigned int chksum_ok = 0;
 
+	/* Clear status before servicing to reduce spurious interrupts */
+	if (ring->index == DESC_INDEX) {
+		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
+					 INTRL2_CPU_CLEAR);
+	} else {
+		mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
+		bcmgenet_intrl2_1_writel(priv,
+					 mask,
+					 INTRL2_CPU_CLEAR);
+	}
+
 	p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);
 
 	discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) &
 		   DMA_P_INDEX_DISCARD_CNT_MASK;
 	if (discards > ring->old_discards) {
 		discards = discards - ring->old_discards;
-		dev->stats.rx_missed_errors += discards;
-		dev->stats.rx_errors += discards;
+		ring->errors += discards;
 		ring->old_discards += discards;
 
 		/* Clear HW register when we reach 75% of maximum 0xFFFF */
@@ -1611,12 +1725,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	}
 
 	p_index &= DMA_P_INDEX_MASK;
-
-	if (likely(p_index >= ring->c_index))
-		rxpkttoprocess = p_index - ring->c_index;
-	else
-		rxpkttoprocess = (DMA_C_INDEX_MASK + 1) - ring->c_index +
-				 p_index;
+	rxpkttoprocess = (p_index - ring->c_index) & DMA_C_INDEX_MASK;
 
 	netif_dbg(priv, rx_status, dev,
 		  "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess);
@@ -1627,7 +1736,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		skb = bcmgenet_rx_refill(priv, cb);
 
 		if (unlikely(!skb)) {
-			dev->stats.rx_dropped++;
+			ring->dropped++;
 			goto next;
 		}
 
@@ -1655,7 +1764,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
-			dev->stats.rx_errors++;
+			ring->errors++;
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -1704,8 +1813,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		/*Finish setting up the received SKB and send it to the kernel*/
 		skb->protocol = eth_type_trans(skb, priv->dev);
-		dev->stats.rx_packets++;
-		dev->stats.rx_bytes += len;
+		ring->packets++;
+		ring->bytes += len;
 		if (dma_flag & DMA_RX_MULT)
 			dev->stats.multicast++;
 
@@ -1843,10 +1952,8 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
 	/* Mask all interrupts.*/
 	bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
 	bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
-	bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
 	bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
 	bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
 }
 
 static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
@@ -1873,8 +1980,6 @@ static int init_umac(struct bcmgenet_priv *priv)
 	int ret;
 	u32 reg;
 	u32 int0_enable = 0;
-	u32 int1_enable = 0;
-	int i;
 
 	dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
 
@@ -1901,12 +2006,6 @@ static int init_umac(struct bcmgenet_priv *priv)
 
 	bcmgenet_intr_disable(priv);
 
-	/* Enable Rx default queue 16 interrupts */
-	int0_enable |= UMAC_IRQ_RXDMA_DONE;
-
-	/* Enable Tx default queue 16 interrupts */
-	int0_enable |= UMAC_IRQ_TXDMA_DONE;
-
 	/* Configure backpressure vectors for MoCA */
 	if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 		reg = bcmgenet_bp_mc_get(priv);
@@ -1924,18 +2023,8 @@ static int init_umac(struct bcmgenet_priv *priv)
 	if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
 		int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
 
-	/* Enable Rx priority queue interrupts */
-	for (i = 0; i < priv->hw_params->rx_queues; ++i)
-		int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
-
-	/* Enable Tx priority queue interrupts */
-	for (i = 0; i < priv->hw_params->tx_queues; ++i)
-		int1_enable |= (1 << i);
-
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 
-	/* Enable rx/tx engine.*/
 	dev_dbg(kdev, "done init umac\n");
 
 	return 0;
@@ -2067,22 +2156,33 @@ static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv)
 static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_enable = UMAC_IRQ_TXDMA_DONE;
+	u32 int1_enable = 0;
 	struct bcmgenet_tx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
+		int1_enable |= (1 << i);
 	}
 
 	ring = &priv->tx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
+
+	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_disable = UMAC_IRQ_TXDMA_DONE;
+	u32 int1_disable = 0xffff;
 	struct bcmgenet_tx_ring *ring;
 
+	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
+	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
+
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
@@ -2195,22 +2295,33 @@ static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv)
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_enable = UMAC_IRQ_RXDMA_DONE;
+	u32 int1_enable = 0;
 	struct bcmgenet_rx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
+		int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
 	}
 
 	ring = &priv->rx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
+
+	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_disable = UMAC_IRQ_RXDMA_DONE;
+	u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT;
 	struct bcmgenet_rx_ring *ring;
 
+	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
+	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
+
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
@@ -2457,24 +2568,28 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 /* Interrupt bottom half */
 static void bcmgenet_irq_task(struct work_struct *work)
 {
+	unsigned long flags;
+	unsigned int status;
 	struct bcmgenet_priv *priv = container_of(
 			work, struct bcmgenet_priv, bcmgenet_irq_work);
 
 	netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
 
-	if (priv->irq0_stat & UMAC_IRQ_MPD_R) {
-		priv->irq0_stat &= ~UMAC_IRQ_MPD_R;
+	spin_lock_irqsave(&priv->lock, flags);
+	status = priv->irq0_stat;
+	priv->irq0_stat = 0;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (status & UMAC_IRQ_MPD_R) {
 		netif_dbg(priv, wol, priv->dev,
 			  "magic packet detected, waking up\n");
 		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
 	}
 
 	/* Link UP/DOWN event */
-	if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
+	if (status & UMAC_IRQ_LINK_EVENT)
 		phy_mac_interrupt(priv->phydev,
-				  !!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
-		priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
-	}
+				  !!(status & UMAC_IRQ_LINK_UP));
 }
 
 /* bcmgenet_isr1: handle Rx and Tx priority queues */
@@ -2483,22 +2598,21 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 	struct bcmgenet_priv *priv = dev_id;
 	struct bcmgenet_rx_ring *rx_ring;
 	struct bcmgenet_tx_ring *tx_ring;
-	unsigned int index;
+	unsigned int index, status;
 
-	/* Save irq status for bottom-half processing. */
-	priv->irq1_stat =
-		bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
+	/* Read irq status */
+	status = bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
 		~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
 
 	/* clear interrupts */
-	bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, status, INTRL2_CPU_CLEAR);
 
 	netif_dbg(priv, intr, priv->dev,
-		  "%s: IRQ=0x%x\n", __func__, priv->irq1_stat);
+		  "%s: IRQ=0x%x\n", __func__, status);
 
 	/* Check Rx priority queue interrupts */
 	for (index = 0; index < priv->hw_params->rx_queues; index++) {
-		if (!(priv->irq1_stat & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
+		if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
 			continue;
 
 		rx_ring = &priv->rx_rings[index];
@@ -2511,7 +2625,7 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 
 	/* Check Tx priority queue interrupts */
 	for (index = 0; index < priv->hw_params->tx_queues; index++) {
-		if (!(priv->irq1_stat & BIT(index)))
+		if (!(status & BIT(index)))
 			continue;
 
 		tx_ring = &priv->tx_rings[index];
@@ -2531,19 +2645,20 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	struct bcmgenet_priv *priv = dev_id;
 	struct bcmgenet_rx_ring *rx_ring;
 	struct bcmgenet_tx_ring *tx_ring;
+	unsigned int status;
+	unsigned long flags;
 
-	/* Save irq status for bottom-half processing. */
-	priv->irq0_stat =
-		bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
+	/* Read irq status */
+	status = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
 		~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
 
 	/* clear interrupts */
-	bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_0_writel(priv, status, INTRL2_CPU_CLEAR);
 
 	netif_dbg(priv, intr, priv->dev,
-		  "IRQ=0x%x\n", priv->irq0_stat);
+		  "IRQ=0x%x\n", status);
 
-	if (priv->irq0_stat & UMAC_IRQ_RXDMA_DONE) {
+	if (status & UMAC_IRQ_RXDMA_DONE) {
 		rx_ring = &priv->rx_rings[DESC_INDEX];
 
 		if (likely(napi_schedule_prep(&rx_ring->napi))) {
@@ -2552,7 +2667,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 		}
 	}
 
-	if (priv->irq0_stat & UMAC_IRQ_TXDMA_DONE) {
+	if (status & UMAC_IRQ_TXDMA_DONE) {
 		tx_ring = &priv->tx_rings[DESC_INDEX];
 
 		if (likely(napi_schedule_prep(&tx_ring->napi))) {
@@ -2565,18 +2680,28 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 				UMAC_IRQ_PHY_DET_F |
 				UMAC_IRQ_LINK_EVENT |
 				UMAC_IRQ_HFB_SM |
-				UMAC_IRQ_HFB_MM |
-				UMAC_IRQ_MPD_R)) {
+				UMAC_IRQ_HFB_MM)) {
 		/* all other interested interrupts handled in bottom half */
 		schedule_work(&priv->bcmgenet_irq_work);
 	}
 
 	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
-	    priv->irq0_stat & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
-		priv->irq0_stat &= ~(UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
+		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
 		wake_up(&priv->wq);
 	}
 
+	/* all other interested interrupts handled in bottom half */
+	status &= (UMAC_IRQ_LINK_EVENT |
+		   UMAC_IRQ_MPD_R);
+	if (status) {
+		/* Save irq status for bottom-half processing. */
+		spin_lock_irqsave(&priv->lock, flags);
+		priv->irq0_stat |= status;
+		spin_unlock_irqrestore(&priv->lock, flags);
+
+		schedule_work(&priv->bcmgenet_irq_work);
+	}
+
 	return IRQ_HANDLED;
 }
 
@@ -2801,6 +2926,8 @@ err_irq0:
 err_fini_dma:
 	bcmgenet_fini_dma(priv);
 err_clk_disable:
+	if (priv->internal_phy)
+		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }
@@ -2845,7 +2972,7 @@ static int bcmgenet_close(struct net_device *dev)
 	if (ret)
 		return ret;
 
-	/* Disable MAC transmit. TX DMA disabled have to done before this */
+	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
 	/* tx reclaim */
@@ -3025,6 +3152,48 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
+static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	unsigned long tx_bytes = 0, tx_packets = 0;
+	unsigned long rx_bytes = 0, rx_packets = 0;
+	unsigned long rx_errors = 0, rx_dropped = 0;
+	struct bcmgenet_tx_ring *tx_ring;
+	struct bcmgenet_rx_ring *rx_ring;
+	unsigned int q;
+
+	for (q = 0; q < priv->hw_params->tx_queues; q++) {
+		tx_ring = &priv->tx_rings[q];
+		tx_bytes += tx_ring->bytes;
+		tx_packets += tx_ring->packets;
+	}
+	tx_ring = &priv->tx_rings[DESC_INDEX];
+	tx_bytes += tx_ring->bytes;
+	tx_packets += tx_ring->packets;
+
+	for (q = 0; q < priv->hw_params->rx_queues; q++) {
+		rx_ring = &priv->rx_rings[q];
+
+		rx_bytes += rx_ring->bytes;
+		rx_packets += rx_ring->packets;
+		rx_errors += rx_ring->errors;
+		rx_dropped += rx_ring->dropped;
+	}
+	rx_ring = &priv->rx_rings[DESC_INDEX];
+	rx_bytes += rx_ring->bytes;
+	rx_packets += rx_ring->packets;
+	rx_errors += rx_ring->errors;
+	rx_dropped += rx_ring->dropped;
+
+	dev->stats.tx_bytes = tx_bytes;
+	dev->stats.tx_packets = tx_packets;
+	dev->stats.rx_bytes = rx_bytes;
+	dev->stats.rx_packets = rx_packets;
+	dev->stats.rx_errors = rx_errors;
+	dev->stats.rx_missed_errors = rx_errors;
+	return &dev->stats;
+}
+
 static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_open		= bcmgenet_open,
 	.ndo_stop		= bcmgenet_close,
@@ -3037,6 +3206,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bcmgenet_poll_controller,
 #endif
+	.ndo_get_stats		= bcmgenet_get_stats,
 };
 
 /* Array of GENET hardware parameters/characteristics */
@@ -3110,6 +3280,25 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
 		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
 			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 	},
+	[GENET_V5] = {
+		.tx_queues = 4,
+		.tx_bds_per_q = 32,
+		.rx_queues = 0,
+		.rx_bds_per_q = 0,
+		.bp_in_en_shift = 17,
+		.bp_in_mask = 0x1ffff,
+		.hfb_filter_cnt = 48,
+		.hfb_filter_size = 128,
+		.qtag_mask = 0x3F,
+		.tbuf_offset = 0x0600,
+		.hfb_offset = 0x8000,
+		.hfb_reg_offset = 0xfc00,
+		.rdma_offset = 0x2000,
+		.tdma_offset = 0x4000,
+		.words_per_bd = 3,
+		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
+	},
 };
 
 /* Infer hardware parameters from the detected GENET version */
@@ -3120,26 +3309,22 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	u8 major;
 	u16 gphy_rev;
 
-	if (GENET_IS_V4(priv)) {
+	if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v4;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
-		priv->version = GENET_V4;
 	} else if (GENET_IS_V3(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
-		priv->version = GENET_V3;
 	} else if (GENET_IS_V2(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
-		priv->version = GENET_V2;
 	} else if (GENET_IS_V1(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
-		priv->version = GENET_V1;
 	}
 
 	/* enum genet_version starts at 1 */
@@ -3149,7 +3334,9 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	/* Read GENET HW version */
 	reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
 	major = (reg >> 24 & 0x0f);
-	if (major == 5)
+	if (major == 6)
+		major = 5;
+	else if (major == 5)
 		major = 4;
 	else if (major == 0)
 		major = 1;
@@ -3177,18 +3364,24 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	 */
 	gphy_rev = reg & 0xffff;
 
+	if (GENET_IS_V5(priv)) {
+		/* The EPHY revision should come from the MDIO registers of
+		 * the PHY not from GENET.
+		 */
+		if (gphy_rev != 0) {
+			pr_warn("GENET is reporting EPHY revision: 0x%04x\n",
+				gphy_rev);
+		}
+	/* This is reserved so should require special treatment */
+	} else if (gphy_rev == 0 || gphy_rev == 0x01ff) {
+		pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev);
+		return;
 	/* This is the good old scheme, just GPHY major, no minor nor patch */
-	if ((gphy_rev & 0xf0) != 0)
+	} else if ((gphy_rev & 0xf0) != 0) {
 		priv->gphy_rev = gphy_rev << 8;
-
 	/* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */
-	else if ((gphy_rev & 0xff00) != 0)
+	} else if ((gphy_rev & 0xff00) != 0) {
 		priv->gphy_rev = gphy_rev;
-
-	/* This is reserved so should require special treatment */
-	else if (gphy_rev == 0 || gphy_rev == 0x01ff) {
-		pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev);
-		return;
 	}
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
@@ -3219,6 +3412,7 @@ static const struct of_device_id bcmgenet_match[] = {
 	{ .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 },
 	{ .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 },
 	{ .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 },
+	{ .compatible = "brcm,genet-v5", .data = (void *)GENET_V5 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bcmgenet_match);
@@ -3233,6 +3427,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	const void *macaddr;
 	struct resource *r;
 	int err = -EIO;
+	const char *phy_mode_str;
 
 	/* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */
 	dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1,
@@ -3276,6 +3471,8 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		goto err;
 	}
 
+	spin_lock_init(&priv->lock);
+
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	dev_set_drvdata(&pdev->dev, dev);
 	ether_addr_copy(dev->dev_addr, macaddr);
@@ -3338,6 +3535,13 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		priv->clk_eee = NULL;
 	}
 
+	/* If this is an internal GPHY, power it on now, before UniMAC is
+	 * brought out of reset as absolutely no UniMAC activity is allowed
+	 */
+	if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) &&
+	    !strcasecmp(phy_mode_str, "internal"))
+		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
+
 	err = reset_umac(priv);
 	if (err)
 		goto err_clk_disable;
@@ -3395,7 +3599,8 @@ static int bcmgenet_suspend(struct device *d)
 
 	bcmgenet_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_suspend(priv->phydev);
 
 	netif_device_detach(dev);
 
@@ -3406,7 +3611,7 @@ static int bcmgenet_suspend(struct device *d)
 	if (ret)
 		return ret;
 
-	/* Disable MAC transmit. TX DMA disabled have to done before this */
+	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
 	/* tx reclaim */
@@ -3492,7 +3697,8 @@ static int bcmgenet_resume(struct device *d)
 
 	netif_device_attach(dev);
 
-	phy_resume(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_resume(priv->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
@@ -3502,6 +3708,8 @@ static int bcmgenet_resume(struct device *d)
 	return 0;
 
 out_clk_disable:
+	if (priv->internal_phy)
+		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 1e2dc34d331a..efd07020b89f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -214,7 +214,9 @@ struct bcmgenet_mib_counters {
 #define  MDIO_REG_SHIFT			16
 #define  MDIO_REG_MASK			0x1F
 
-#define UMAC_RBUF_OVFL_CNT		0x61C
+#define UMAC_RBUF_OVFL_CNT_V1		0x61C
+#define RBUF_OVFL_CNT_V2		0x80
+#define RBUF_OVFL_CNT_V3PLUS		0x94
 
 #define UMAC_MPD_CTRL			0x620
 #define  MPD_EN				(1 << 0)
@@ -224,7 +226,9 @@ struct bcmgenet_mib_counters {
 
 #define UMAC_MPD_PW_MS			0x624
 #define UMAC_MPD_PW_LS			0x628
-#define UMAC_RBUF_ERR_CNT		0x634
+#define UMAC_RBUF_ERR_CNT_V1		0x634
+#define RBUF_ERR_CNT_V2			0x84
+#define RBUF_ERR_CNT_V3PLUS		0x98
 #define UMAC_MDF_ERR_CNT		0x638
 #define UMAC_MDF_CTRL			0x650
 #define UMAC_MDF_ADDR			0x654
@@ -351,8 +355,14 @@ struct bcmgenet_mib_counters {
 #define  EXT_PWR_DN_EN_LD		(1 << 3)
 #define  EXT_ENERGY_DET			(1 << 4)
 #define  EXT_IDDQ_FROM_PHY		(1 << 5)
+#define  EXT_IDDQ_GLBL_PWR		(1 << 7)
 #define  EXT_PHY_RESET			(1 << 8)
 #define  EXT_ENERGY_DET_MASK		(1 << 12)
+#define  EXT_PWR_DOWN_PHY_TX		(1 << 16)
+#define  EXT_PWR_DOWN_PHY_RX		(1 << 17)
+#define  EXT_PWR_DOWN_PHY_SD		(1 << 18)
+#define  EXT_PWR_DOWN_PHY_RD		(1 << 19)
+#define  EXT_PWR_DOWN_PHY_EN		(1 << 20)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
 #define  RGMII_LINK			(1 << 4)
@@ -495,13 +505,15 @@ enum bcmgenet_version {
 	GENET_V1 = 1,
 	GENET_V2,
 	GENET_V3,
-	GENET_V4
+	GENET_V4,
+	GENET_V5
 };
 
 #define GENET_IS_V1(p)	((p)->version == GENET_V1)
 #define GENET_IS_V2(p)	((p)->version == GENET_V2)
 #define GENET_IS_V3(p)	((p)->version == GENET_V3)
 #define GENET_IS_V4(p)	((p)->version == GENET_V4)
+#define GENET_IS_V5(p)	((p)->version == GENET_V5)
 
 /* Hardware flags */
 #define GENET_HAS_40BITS	(1 << 0)
@@ -540,6 +552,8 @@ struct bcmgenet_skb_cb {
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
 	struct napi_struct napi;	/* NAPI per tx queue */
+	unsigned long	packets;
+	unsigned long	bytes;
 	unsigned int	index;		/* ring index */
 	unsigned int	queue;		/* queue index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
@@ -558,6 +572,10 @@ struct bcmgenet_tx_ring {
 
 struct bcmgenet_rx_ring {
 	struct napi_struct napi;	/* Rx NAPI struct */
+	unsigned long	bytes;
+	unsigned long	packets;
+	unsigned long	errors;
+	unsigned long	dropped;
 	unsigned int	index;		/* Rx ring index */
 	struct enet_cb	*cbs;		/* Rx ring buffer control block */
 	unsigned int	size;		/* Rx ring size */
@@ -619,11 +637,13 @@ struct bcmgenet_priv {
 	struct work_struct bcmgenet_irq_work;
 	int irq0;
 	int irq1;
-	unsigned int irq0_stat;
-	unsigned int irq1_stat;
 	int wol_irq;
 	bool wol_irq_disabled;
 
+	/* shared status */
+	spinlock_t lock;
+	unsigned int irq0_stat;
+
 	/* HW descriptors/checksum variables */
 	bool desc_64b_en;
 	bool desc_rxchk_en;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index b97122926d3a..2fbd027f0148 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -127,7 +127,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
 	struct net_device *dev = priv->dev;
-	u32 cpu_mask_clear;
 	int retries = 0;
 	u32 reg;
 
@@ -173,18 +172,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 	}
 
-	/* Enable the MPD interrupt */
-	cpu_mask_clear = UMAC_IRQ_MPD_R;
-
-	bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR);
-
 	return 0;
 }
 
 void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 			       enum bcmgenet_power_mode mode)
 {
-	u32 cpu_mask_set;
 	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
@@ -201,10 +194,4 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~CMD_CRC_FWD;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	priv->crc_fwd_en = 0;
-
-	/* Stop monitoring magic packet IRQ */
-	cpu_mask_set = UMAC_IRQ_MPD_R;
-
-	/* Stop monitoring magic packet IRQ */
-	bcmgenet_intrl2_0_writel(priv, cpu_mask_set, INTRL2_CPU_MASK_SET);
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e87607621e62..285676f8da6b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom GENET MDIO routines
  *
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -195,53 +195,43 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	u32 reg = 0;
 
 	/* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
-	if (!GENET_IS_V4(priv))
-		return;
-
-	reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
-	if (enable) {
-		reg &= ~EXT_CK25_DIS;
-		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
-		mdelay(1);
-
-		reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
-		reg |= EXT_GPHY_RESET;
+	if (GENET_IS_V4(priv)) {
+		reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
+		if (enable) {
+			reg &= ~EXT_CK25_DIS;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+
+			reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
+			reg |= EXT_GPHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+
+			reg &= ~EXT_GPHY_RESET;
+		} else {
+			reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN |
+			       EXT_GPHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+			reg |= EXT_CK25_DIS;
+		}
 		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
-		mdelay(1);
-
-		reg &= ~EXT_GPHY_RESET;
+		udelay(60);
 	} else {
-		reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | EXT_GPHY_RESET;
-		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
 		mdelay(1);
-		reg |= EXT_CK25_DIS;
 	}
-	bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
-	udelay(60);
-}
-
-static void bcmgenet_internal_phy_setup(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	/* Power up PHY */
-	bcmgenet_phy_power_set(dev, true);
-	/* enable APD */
-	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-	reg |= EXT_PWR_DN_EN_LD;
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	bcmgenet_mii_reset(dev);
 }
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
 	u32 reg;
 
-	/* Speed settings are set in bcmgenet_mii_setup() */
-	reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
-	reg |= LED_ACT_SOURCE_MAC;
-	bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+	if (!GENET_IS_V5(priv)) {
+		/* Speed settings are set in bcmgenet_mii_setup() */
+		reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
+		reg |= LED_ACT_SOURCE_MAC;
+		bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+	}
 
 	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
 		fixed_phy_set_link_update(priv->phydev,
@@ -281,7 +271,6 @@ int bcmgenet_mii_config(struct net_device *dev)
 
 		if (priv->internal_phy) {
 			phy_name = "internal PHY";
-			bcmgenet_internal_phy_setup(dev);
 		} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 			phy_name = "MoCA";
 			bcmgenet_moca_phy_setup(priv);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 30d1eb9ebec9..f395b951f5e7 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -825,6 +825,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us)
 	return timeout_us ? 0 : -EBUSY;
 }
 
+#ifdef CONFIG_TIGON3_HWMON
 static int tg3_ape_wait_for_event(struct tg3 *tp, u32 timeout_us)
 {
 	u32 i, apedata;
@@ -904,6 +905,7 @@ static int tg3_ape_scratchpad_read(struct tg3 *tp, u32 *data, u32 base_off,
 
 	return 0;
 }
+#endif
 
 static int tg3_ape_send_event(struct tg3 *tp, u32 event)
 {
@@ -10744,6 +10746,7 @@ static int tg3_init_hw(struct tg3 *tp, bool reset_phy)
 	return tg3_reset_hw(tp, reset_phy);
 }
 
+#ifdef CONFIG_TIGON3_HWMON
 static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir)
 {
 	int i;
@@ -10826,6 +10829,10 @@ static void tg3_hwmon_open(struct tg3 *tp)
 		dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n");
 	}
 }
+#else
+static inline void tg3_hwmon_close(struct tg3 *tp) { }
+static inline void tg3_hwmon_open(struct tg3 *tp) { }
+#endif /* CONFIG_TIGON3_HWMON */
 
 
 #define TG3_STAT_ADD32(PSTAT, REG) \
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 9e59663a6ead..0f6811860ad5 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1930,13 +1930,13 @@ static void
 bfa_ioc_send_enable(struct bfa_ioc *ioc)
 {
 	struct bfi_ioc_ctrl_req enable_req;
-	struct timeval tv;
 
 	bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ,
 		    bfa_ioc_portid(ioc));
 	enable_req.clscode = htons(ioc->clscode);
-	do_gettimeofday(&tv);
-	enable_req.tv_sec = ntohl(tv.tv_sec);
+	enable_req.rsvd = htons(0);
+	/* overflow in 2106 */
+	enable_req.tv_sec = ntohl(ktime_get_real_seconds());
 	bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req));
 }
 
@@ -1947,6 +1947,10 @@ bfa_ioc_send_disable(struct bfa_ioc *ioc)
 
 	bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ,
 		    bfa_ioc_portid(ioc));
+	disable_req.clscode = htons(ioc->clscode);
+	disable_req.rsvd = htons(0);
+	/* overflow in 2106 */
+	disable_req.tv_sec = ntohl(ktime_get_real_seconds());
 	bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req));
 }
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
index 05c1c1dd7751..cebfe3bd086e 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -325,7 +325,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf,
 		return PTR_ERR(kern_buf);
 
 	rc = sscanf(kern_buf, "%x:%x", &addr, &len);
-	if (rc < 2) {
+	if (rc < 2 || len > UINT_MAX >> 2) {
 		netdev_warn(bnad->netdev, "failed to read user buffer\n");
 		kfree(kern_buf);
 		return -EINVAL;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 30606b11b128..91f7492623d3 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -432,15 +432,17 @@ static int macb_mii_probe(struct net_device *dev)
 	}
 
 	pdata = dev_get_platdata(&bp->pdev->dev);
-	if (pdata && gpio_is_valid(pdata->phy_irq_pin)) {
-		ret = devm_gpio_request(&bp->pdev->dev, pdata->phy_irq_pin,
-					"phy int");
-		if (!ret) {
-			phy_irq = gpio_to_irq(pdata->phy_irq_pin);
-			phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+	if (pdata) {
+		if (gpio_is_valid(pdata->phy_irq_pin)) {
+			ret = devm_gpio_request(&bp->pdev->dev,
+						pdata->phy_irq_pin, "phy int");
+			if (!ret) {
+				phy_irq = gpio_to_irq(pdata->phy_irq_pin);
+				phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+			}
+		} else {
+			phydev->irq = PHY_POLL;
 		}
-	} else {
-		phydev->irq = PHY_POLL;
 	}
 
 	/* attach the mac to the phy */
@@ -684,8 +686,8 @@ static void macb_tx_error_task(struct work_struct *work)
 				netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n",
 					    macb_tx_ring_wrap(bp, tail),
 					    skb->data);
-				bp->stats.tx_packets++;
-				bp->stats.tx_bytes += skb->len;
+				bp->dev->stats.tx_packets++;
+				bp->dev->stats.tx_bytes += skb->len;
 			}
 		} else {
 			/* "Buffers exhausted mid-frame" errors may only happen
@@ -778,8 +780,8 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 				netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
 					    macb_tx_ring_wrap(bp, tail),
 					    skb->data);
-				bp->stats.tx_packets++;
-				bp->stats.tx_bytes += skb->len;
+				bp->dev->stats.tx_packets++;
+				bp->dev->stats.tx_bytes += skb->len;
 			}
 
 			/* Now we can safely release resources */
@@ -911,14 +913,14 @@ static int gem_rx(struct macb *bp, int budget)
 		if (!(ctrl & MACB_BIT(RX_SOF) && ctrl & MACB_BIT(RX_EOF))) {
 			netdev_err(bp->dev,
 				   "not whole frame pointed by descriptor\n");
-			bp->stats.rx_dropped++;
+			bp->dev->stats.rx_dropped++;
 			break;
 		}
 		skb = bp->rx_skbuff[entry];
 		if (unlikely(!skb)) {
 			netdev_err(bp->dev,
 				   "inconsistent Rx descriptor chain\n");
-			bp->stats.rx_dropped++;
+			bp->dev->stats.rx_dropped++;
 			break;
 		}
 		/* now everything is ready for receiving packet */
@@ -938,8 +940,8 @@ static int gem_rx(struct macb *bp, int budget)
 		    GEM_BFEXT(RX_CSUM, ctrl) & GEM_RX_CSUM_CHECKED_MASK)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-		bp->stats.rx_packets++;
-		bp->stats.rx_bytes += skb->len;
+		bp->dev->stats.rx_packets++;
+		bp->dev->stats.rx_bytes += skb->len;
 
 #if defined(DEBUG) && defined(VERBOSE_DEBUG)
 		netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
@@ -984,7 +986,7 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
 	 */
 	skb = netdev_alloc_skb(bp->dev, len + NET_IP_ALIGN);
 	if (!skb) {
-		bp->stats.rx_dropped++;
+		bp->dev->stats.rx_dropped++;
 		for (frag = first_frag; ; frag++) {
 			desc = macb_rx_desc(bp, frag);
 			desc->addr &= ~MACB_BIT(RX_USED);
@@ -1030,8 +1032,8 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
 	__skb_pull(skb, NET_IP_ALIGN);
 	skb->protocol = eth_type_trans(skb, bp->dev);
 
-	bp->stats.rx_packets++;
-	bp->stats.rx_bytes += skb->len;
+	bp->dev->stats.rx_packets++;
+	bp->dev->stats.rx_bytes += skb->len;
 	netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
 		    skb->len, skb->csum);
 	netif_receive_skb(skb);
@@ -2210,7 +2212,7 @@ static void gem_update_stats(struct macb *bp)
 static struct net_device_stats *gem_get_stats(struct macb *bp)
 {
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
-	struct net_device_stats *nstat = &bp->stats;
+	struct net_device_stats *nstat = &bp->dev->stats;
 
 	gem_update_stats(bp);
 
@@ -2281,7 +2283,7 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 static struct net_device_stats *macb_get_stats(struct net_device *dev)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct net_device_stats *nstat = &bp->stats;
+	struct net_device_stats *nstat = &bp->dev->stats;
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
 	if (macb_is_gem(bp))
@@ -2993,15 +2995,15 @@ static void at91ether_rx(struct net_device *dev)
 			memcpy(skb_put(skb, pktlen), p_recv, pktlen);
 
 			skb->protocol = eth_type_trans(skb, dev);
-			lp->stats.rx_packets++;
-			lp->stats.rx_bytes += pktlen;
+			dev->stats.rx_packets++;
+			dev->stats.rx_bytes += pktlen;
 			netif_rx(skb);
 		} else {
-			lp->stats.rx_dropped++;
+			dev->stats.rx_dropped++;
 		}
 
 		if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH))
-			lp->stats.multicast++;
+			dev->stats.multicast++;
 
 		/* reset ownership bit */
 		desc->addr &= ~MACB_BIT(RX_USED);
@@ -3036,15 +3038,15 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id)
 	if (intstatus & MACB_BIT(TCOMP)) {
 		/* The TCOM bit is set even if the transmission failed */
 		if (intstatus & (MACB_BIT(ISR_TUND) | MACB_BIT(ISR_RLE)))
-			lp->stats.tx_errors++;
+			dev->stats.tx_errors++;
 
 		if (lp->skb) {
 			dev_kfree_skb_irq(lp->skb);
 			lp->skb = NULL;
 			dma_unmap_single(NULL, lp->skb_physaddr,
 					 lp->skb_length, DMA_TO_DEVICE);
-			lp->stats.tx_packets++;
-			lp->stats.tx_bytes += lp->skb_length;
+			dev->stats.tx_packets++;
+			dev->stats.tx_bytes += lp->skb_length;
 		}
 		netif_wake_queue(dev);
 	}
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 234a49eaccfd..ec037b0fa2a4 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -919,7 +919,6 @@ struct macb {
 	struct clk		*rx_clk;
 	struct net_device	*dev;
 	struct napi_struct	napi;
-	struct net_device_stats	stats;
 	union {
 		struct macb_stats	macb;
 		struct gem_stats	gem;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
index 2fedd91f3df8..dee604651ba7 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
@@ -43,6 +43,8 @@ struct octeon_cn23xx_pf {
 	struct octeon_config *conf;
 };
 
+#define CN23XX_SLI_DEF_BP			0x40
+
 int setup_cn23xx_octeon_pf_device(struct octeon_device *oct);
 
 int validate_cn23xx_pf_config_info(struct octeon_device *oct,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index f629c2fe04a4..796c2cbc11f6 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -26,6 +26,9 @@
 #include "octeon_main.h"
 #include "octeon_network.h"
 
+/* OOM task polling interval */
+#define LIO_OOM_POLL_INTERVAL_MS 250
+
 int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
 {
 	struct lio *lio = GET_LIO(netdev);
@@ -124,6 +127,17 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 	struct octeon_device *oct = lio->oct_dev;
 	u8 *mac;
 
+	if (nctrl->completion && nctrl->response_code) {
+		/* Signal whoever is interested that the response code from the
+		 * firmware has arrived.
+		 */
+		WRITE_ONCE(*nctrl->response_code, nctrl->status);
+		complete(nctrl->completion);
+	}
+
+	if (nctrl->status)
+		return;
+
 	switch (nctrl->ncmd.s.cmd) {
 	case OCTNET_CMD_CHANGE_DEVFLAGS:
 	case OCTNET_CMD_SET_MULTI_LIST:
@@ -131,11 +145,20 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 
 	case OCTNET_CMD_CHANGE_MACADDR:
 		mac = ((u8 *)&nctrl->udd[0]) + 2;
-		netif_info(lio, probe, lio->netdev,
-			   "MACAddr changed to %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n",
-			   mac[0], mac[1],
-			   mac[2], mac[3],
-			   mac[4], mac[5]);
+		if (nctrl->ncmd.s.param1) {
+			/* vfidx is 0 based, but vf_num (param1) is 1 based */
+			int vfidx = nctrl->ncmd.s.param1 - 1;
+			bool mac_is_admin_assigned = nctrl->ncmd.s.param2;
+
+			if (mac_is_admin_assigned)
+				netif_info(lio, probe, lio->netdev,
+					   "MAC Address %pM is configured for VF %d\n",
+					   mac, vfidx);
+		} else {
+			netif_info(lio, probe, lio->netdev,
+				   " MACAddr changed to %pM\n",
+				   mac);
+		}
 		break;
 
 	case OCTNET_CMD_CHANGE_MTU:
@@ -284,3 +307,56 @@ void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac)
 	 * the PF did that already
 	 */
 }
+
+static void octnet_poll_check_rxq_oom_status(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct lio *lio = (struct lio *)wk->ctxptr;
+	struct octeon_device *oct = lio->oct_dev;
+	struct octeon_droq *droq;
+	int q, q_no = 0;
+
+	if (ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
+		for (q = 0; q < lio->linfo.num_rxpciq; q++) {
+			q_no = lio->linfo.rxpciq[q].s.q_no;
+			droq = oct->droq[q_no];
+			if (!droq)
+				continue;
+			octeon_droq_check_oom(droq);
+		}
+	}
+	queue_delayed_work(lio->rxq_status_wq.wq,
+			   &lio->rxq_status_wq.wk.work,
+			   msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS));
+}
+
+int setup_rx_oom_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	lio->rxq_status_wq.wq = alloc_workqueue("rxq-oom-status",
+						WQ_MEM_RECLAIM, 0);
+	if (!lio->rxq_status_wq.wq) {
+		dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n");
+		return -ENOMEM;
+	}
+	INIT_DELAYED_WORK(&lio->rxq_status_wq.wk.work,
+			  octnet_poll_check_rxq_oom_status);
+	lio->rxq_status_wq.wk.ctxptr = lio;
+	queue_delayed_work(lio->rxq_status_wq.wq,
+			   &lio->rxq_status_wq.wk.work,
+			   msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS));
+	return 0;
+}
+
+void cleanup_rx_oom_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	if (lio->rxq_status_wq.wq) {
+		cancel_delayed_work_sync(&lio->rxq_status_wq.wk.work);
+		flush_workqueue(lio->rxq_status_wq.wq);
+		destroy_workqueue(lio->rxq_status_wq.wq);
+	}
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 50384cede8be..579dc7336f58 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -33,6 +33,19 @@
 
 static int octnet_get_link_stats(struct net_device *netdev);
 
+struct oct_intrmod_context {
+	int octeon_id;
+	wait_queue_head_t wc;
+	int cond;
+	int status;
+};
+
+struct oct_intrmod_resp {
+	u64     rh;
+	struct oct_intrmod_cfg intrmod;
+	u64     status;
+};
+
 struct oct_mdio_cmd_context {
 	int octeon_id;
 	wait_queue_head_t wc;
@@ -213,17 +226,23 @@ static int lio_get_link_ksettings(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct oct_link_info *linfo;
-	u32 supported, advertising;
+	u32 supported = 0, advertising = 0;
 
 	linfo = &lio->linfo;
 
 	if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
 	    linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_XLAUI ||
 	    linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
 		ecmd->base.port = PORT_FIBRE;
-		supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE |
-			     SUPPORTED_Pause);
-		advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause);
+
+		if (linfo->link.s.speed == SPEED_10000) {
+			supported = SUPPORTED_10000baseT_Full;
+			advertising = ADVERTISED_10000baseT_Full;
+		}
+
+		supported |= SUPPORTED_FIBRE | SUPPORTED_Pause;
+		advertising |= ADVERTISED_Pause;
 		ethtool_convert_legacy_u32_to_link_mode(
 			ecmd->link_modes.supported, supported);
 		ethtool_convert_legacy_u32_to_link_mode(
@@ -1292,95 +1311,101 @@ static int lio_vf_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
-static int lio_get_intr_coalesce(struct net_device *netdev,
-				 struct ethtool_coalesce *intr_coal)
+/* Callback function for intrmod */
+static void octnet_intrmod_callback(struct octeon_device *oct_dev,
+				    u32 status,
+				    void *ptr)
 {
-	struct lio *lio = GET_LIO(netdev);
-	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_instr_queue *iq;
-	struct oct_intrmod_cfg *intrmod_cfg;
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
+	struct oct_intrmod_context *ctx;
 
-	intrmod_cfg = &oct->intrmod;
+	ctx  = (struct oct_intrmod_context *)sc->ctxptr;
 
-	switch (oct->chip_id) {
-	case OCTEON_CN23XX_PF_VID:
-	case OCTEON_CN23XX_VF_VID:
-		if (!intrmod_cfg->rx_enable) {
-			intr_coal->rx_coalesce_usecs = intrmod_cfg->rx_usecs;
-			intr_coal->rx_max_coalesced_frames =
-				intrmod_cfg->rx_frames;
-		}
-		if (!intrmod_cfg->tx_enable)
-			intr_coal->tx_max_coalesced_frames =
-				intrmod_cfg->tx_frames;
-		break;
-	case OCTEON_CN68XX:
-	case OCTEON_CN66XX: {
-		struct octeon_cn6xxx *cn6xxx =
-			(struct octeon_cn6xxx *)oct->chip;
+	ctx->status = status;
 
-		if (!intrmod_cfg->rx_enable) {
-			intr_coal->rx_coalesce_usecs =
-				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
-			intr_coal->rx_max_coalesced_frames =
-				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
-		}
-		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
-		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
-		break;
-	}
-	default:
-		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
+	WRITE_ONCE(ctx->cond, 1);
+
+	/* This barrier is required to be sure that the response has been
+	 * written fully before waking up the handler
+	 */
+	wmb();
+
+	wake_up_interruptible(&ctx->wc);
+}
+
+/*  get interrupt moderation parameters */
+static int octnet_get_intrmod_cfg(struct lio *lio,
+				  struct oct_intrmod_cfg *intr_cfg)
+{
+	struct octeon_soft_command *sc;
+	struct oct_intrmod_context *ctx;
+	struct oct_intrmod_resp *resp;
+	int retval;
+	struct octeon_device *oct_dev = lio->oct_dev;
+
+	/* Alloc soft command */
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct_dev,
+					  0,
+					  sizeof(struct oct_intrmod_resp),
+					  sizeof(struct oct_intrmod_context));
+
+	if (!sc)
+		return -ENOMEM;
+
+	resp = (struct oct_intrmod_resp *)sc->virtrptr;
+	memset(resp, 0, sizeof(struct oct_intrmod_resp));
+
+	ctx = (struct oct_intrmod_context *)sc->ctxptr;
+	memset(ctx, 0, sizeof(struct oct_intrmod_context));
+	WRITE_ONCE(ctx->cond, 0);
+	ctx->octeon_id = lio_get_device_id(oct_dev);
+	init_waitqueue_head(&ctx->wc);
+
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+				    OPCODE_NIC_INTRMOD_PARAMS, 0, 0, 0);
+
+	sc->callback = octnet_intrmod_callback;
+	sc->callback_arg = sc;
+	sc->wait_time = 1000;
+
+	retval = octeon_send_soft_command(oct_dev, sc);
+	if (retval == IQ_SEND_FAILED) {
+		octeon_free_soft_command(oct_dev, sc);
 		return -EINVAL;
 	}
-	if (intrmod_cfg->rx_enable) {
-		intr_coal->use_adaptive_rx_coalesce =
-			intrmod_cfg->rx_enable;
-		intr_coal->rate_sample_interval =
-			intrmod_cfg->check_intrvl;
-		intr_coal->pkt_rate_high =
-			intrmod_cfg->maxpkt_ratethr;
-		intr_coal->pkt_rate_low =
-			intrmod_cfg->minpkt_ratethr;
-		intr_coal->rx_max_coalesced_frames_high =
-			intrmod_cfg->rx_maxcnt_trigger;
-		intr_coal->rx_coalesce_usecs_high =
-			intrmod_cfg->rx_maxtmr_trigger;
-		intr_coal->rx_coalesce_usecs_low =
-			intrmod_cfg->rx_mintmr_trigger;
-		intr_coal->rx_max_coalesced_frames_low =
-		    intrmod_cfg->rx_mincnt_trigger;
+
+	/* Sleep on a wait queue till the cond flag indicates that the
+	 * response arrived or timed-out.
+	 */
+	if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
+		dev_err(&oct_dev->pci_dev->dev, "Wait interrupted\n");
+		goto intrmod_info_wait_intr;
 	}
-	if ((OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) &&
-	    (intrmod_cfg->tx_enable)) {
-		intr_coal->use_adaptive_tx_coalesce = intrmod_cfg->tx_enable;
-		intr_coal->tx_max_coalesced_frames_high =
-		    intrmod_cfg->tx_maxcnt_trigger;
-		intr_coal->tx_max_coalesced_frames_low =
-		    intrmod_cfg->tx_mincnt_trigger;
+
+	retval = ctx->status || resp->status;
+	if (retval) {
+		dev_err(&oct_dev->pci_dev->dev,
+			"Get interrupt moderation parameters failed\n");
+		goto intrmod_info_wait_fail;
 	}
-	return 0;
-}
 
-/* Callback function for intrmod */
-static void octnet_intrmod_callback(struct octeon_device *oct_dev,
-				    u32 status,
-				    void *ptr)
-{
-	struct oct_intrmod_cmd *cmd = ptr;
-	struct octeon_soft_command *sc = cmd->sc;
+	octeon_swap_8B_data((u64 *)&resp->intrmod,
+			    (sizeof(struct oct_intrmod_cfg)) / 8);
+	memcpy(intr_cfg, &resp->intrmod, sizeof(struct oct_intrmod_cfg));
+	octeon_free_soft_command(oct_dev, sc);
 
-	oct_dev = cmd->oct_dev;
+	return 0;
 
-	if (status)
-		dev_err(&oct_dev->pci_dev->dev, "intrmod config failed. Status: %llx\n",
-			CVM_CAST64(status));
-	else
-		dev_info(&oct_dev->pci_dev->dev,
-			 "Rx-Adaptive Interrupt moderation enabled:%llx\n",
-			 oct_dev->intrmod.rx_enable);
+intrmod_info_wait_fail:
 
 	octeon_free_soft_command(oct_dev, sc);
+
+intrmod_info_wait_intr:
+
+	return -ENODEV;
 }
 
 /*  Configure interrupt moderation parameters */
@@ -1388,7 +1413,7 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 				  struct oct_intrmod_cfg *intr_cfg)
 {
 	struct octeon_soft_command *sc;
-	struct oct_intrmod_cmd *cmd;
+	struct oct_intrmod_context *ctx;
 	struct oct_intrmod_cfg *cfg;
 	int retval;
 	struct octeon_device *oct_dev = lio->oct_dev;
@@ -1398,19 +1423,21 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 		octeon_alloc_soft_command(oct_dev,
 					  sizeof(struct oct_intrmod_cfg),
 					  0,
-					  sizeof(struct oct_intrmod_cmd));
+					  sizeof(struct oct_intrmod_context));
 
 	if (!sc)
 		return -ENOMEM;
 
-	cmd = (struct oct_intrmod_cmd *)sc->ctxptr;
+	ctx = (struct oct_intrmod_context *)sc->ctxptr;
+
+	WRITE_ONCE(ctx->cond, 0);
+	ctx->octeon_id = lio_get_device_id(oct_dev);
+	init_waitqueue_head(&ctx->wc);
+
 	cfg = (struct oct_intrmod_cfg *)sc->virtdptr;
 
 	memcpy(cfg, intr_cfg, sizeof(struct oct_intrmod_cfg));
 	octeon_swap_8B_data((u64 *)cfg, (sizeof(struct oct_intrmod_cfg)) / 8);
-	cmd->sc = sc;
-	cmd->cfg = cfg;
-	cmd->oct_dev = oct_dev;
 
 	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
 
@@ -1418,7 +1445,7 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 				    OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
 
 	sc->callback = octnet_intrmod_callback;
-	sc->callback_arg = cmd;
+	sc->callback_arg = sc;
 	sc->wait_time = 1000;
 
 	retval = octeon_send_soft_command(oct_dev, sc);
@@ -1427,7 +1454,29 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 		return -EINVAL;
 	}
 
-	return 0;
+	/* Sleep on a wait queue till the cond flag indicates that the
+	 * response arrived or timed-out.
+	 */
+	if (sleep_cond(&ctx->wc, &ctx->cond) != -EINTR) {
+		retval = ctx->status;
+		if (retval)
+			dev_err(&oct_dev->pci_dev->dev,
+				"intrmod config failed. Status: %llx\n",
+				CVM_CAST64(retval));
+		else
+			dev_info(&oct_dev->pci_dev->dev,
+				 "Rx-Adaptive Interrupt moderation %s\n",
+				 (intr_cfg->rx_enable) ?
+				 "enabled" : "disabled");
+
+		octeon_free_soft_command(oct_dev, sc);
+
+		return ((retval) ? -ENODEV : 0);
+	}
+
+	dev_err(&oct_dev->pci_dev->dev, "iq/oq config failed\n");
+
+	return -EINTR;
 }
 
 static void
@@ -1584,80 +1633,106 @@ static int octnet_get_link_stats(struct net_device *netdev)
 	return 0;
 }
 
-/* Enable/Disable auto interrupt Moderation */
-static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
-				 *intr_coal)
+static int lio_get_intr_coalesce(struct net_device *netdev,
+				 struct ethtool_coalesce *intr_coal)
 {
-	int ret = 0;
+	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
-	struct oct_intrmod_cfg *intrmod_cfg;
-
-	intrmod_cfg = &oct->intrmod;
-
-	if (oct->intrmod.rx_enable || oct->intrmod.tx_enable) {
-		if (intr_coal->rate_sample_interval)
-			intrmod_cfg->check_intrvl =
-				intr_coal->rate_sample_interval;
-		else
-			intrmod_cfg->check_intrvl =
-				LIO_INTRMOD_CHECK_INTERVAL;
+	struct octeon_instr_queue *iq;
+	struct oct_intrmod_cfg intrmod_cfg;
 
-		if (intr_coal->pkt_rate_high)
-			intrmod_cfg->maxpkt_ratethr =
-				intr_coal->pkt_rate_high;
-		else
-			intrmod_cfg->maxpkt_ratethr =
-				LIO_INTRMOD_MAXPKT_RATETHR;
+	if (octnet_get_intrmod_cfg(lio, &intrmod_cfg))
+		return -ENODEV;
 
-		if (intr_coal->pkt_rate_low)
-			intrmod_cfg->minpkt_ratethr =
-				intr_coal->pkt_rate_low;
-		else
-			intrmod_cfg->minpkt_ratethr =
-				LIO_INTRMOD_MINPKT_RATETHR;
+	switch (oct->chip_id) {
+	case OCTEON_CN23XX_PF_VID:
+	case OCTEON_CN23XX_VF_VID: {
+		if (!intrmod_cfg.rx_enable) {
+			intr_coal->rx_coalesce_usecs = oct->rx_coalesce_usecs;
+			intr_coal->rx_max_coalesced_frames =
+				oct->rx_max_coalesced_frames;
+		}
+		if (!intrmod_cfg.tx_enable)
+			intr_coal->tx_max_coalesced_frames =
+				oct->tx_max_coalesced_frames;
+		break;
 	}
-	if (oct->intrmod.rx_enable) {
-		if (intr_coal->rx_max_coalesced_frames_high)
-			intrmod_cfg->rx_maxcnt_trigger =
-				intr_coal->rx_max_coalesced_frames_high;
-		else
-			intrmod_cfg->rx_maxcnt_trigger =
-				LIO_INTRMOD_RXMAXCNT_TRIGGER;
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
 
-		if (intr_coal->rx_coalesce_usecs_high)
-			intrmod_cfg->rx_maxtmr_trigger =
-				intr_coal->rx_coalesce_usecs_high;
-		else
-			intrmod_cfg->rx_maxtmr_trigger =
-				LIO_INTRMOD_RXMAXTMR_TRIGGER;
+		if (!intrmod_cfg.rx_enable) {
+			intr_coal->rx_coalesce_usecs =
+				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
+			intr_coal->rx_max_coalesced_frames =
+				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
+		}
+		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
+		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
+		break;
+	}
+	default:
+		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
+		return -EINVAL;
+	}
+	if (intrmod_cfg.rx_enable) {
+		intr_coal->use_adaptive_rx_coalesce =
+			intrmod_cfg.rx_enable;
+		intr_coal->rate_sample_interval =
+			intrmod_cfg.check_intrvl;
+		intr_coal->pkt_rate_high =
+			intrmod_cfg.maxpkt_ratethr;
+		intr_coal->pkt_rate_low =
+			intrmod_cfg.minpkt_ratethr;
+		intr_coal->rx_max_coalesced_frames_high =
+			intrmod_cfg.rx_maxcnt_trigger;
+		intr_coal->rx_coalesce_usecs_high =
+			intrmod_cfg.rx_maxtmr_trigger;
+		intr_coal->rx_coalesce_usecs_low =
+			intrmod_cfg.rx_mintmr_trigger;
+		intr_coal->rx_max_coalesced_frames_low =
+			intrmod_cfg.rx_mincnt_trigger;
+	}
+	if ((OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) &&
+	    (intrmod_cfg.tx_enable)) {
+		intr_coal->use_adaptive_tx_coalesce =
+			intrmod_cfg.tx_enable;
+		intr_coal->tx_max_coalesced_frames_high =
+			intrmod_cfg.tx_maxcnt_trigger;
+		intr_coal->tx_max_coalesced_frames_low =
+			intrmod_cfg.tx_mincnt_trigger;
+	}
+	return 0;
+}
 
-		if (intr_coal->rx_coalesce_usecs_low)
-			intrmod_cfg->rx_mintmr_trigger =
-				intr_coal->rx_coalesce_usecs_low;
-		else
-			intrmod_cfg->rx_mintmr_trigger =
-				LIO_INTRMOD_RXMINTMR_TRIGGER;
+/* Enable/Disable auto interrupt Moderation */
+static int oct_cfg_adaptive_intr(struct lio *lio,
+				 struct oct_intrmod_cfg *intrmod_cfg,
+				 struct ethtool_coalesce *intr_coal)
+{
+	int ret = 0;
 
-		if (intr_coal->rx_max_coalesced_frames_low)
-			intrmod_cfg->rx_mincnt_trigger =
-				intr_coal->rx_max_coalesced_frames_low;
-		else
-			intrmod_cfg->rx_mincnt_trigger =
-				LIO_INTRMOD_RXMINCNT_TRIGGER;
+	if (intrmod_cfg->rx_enable || intrmod_cfg->tx_enable) {
+		intrmod_cfg->check_intrvl = intr_coal->rate_sample_interval;
+		intrmod_cfg->maxpkt_ratethr = intr_coal->pkt_rate_high;
+		intrmod_cfg->minpkt_ratethr = intr_coal->pkt_rate_low;
 	}
-	if (oct->intrmod.tx_enable) {
-		if (intr_coal->tx_max_coalesced_frames_high)
-			intrmod_cfg->tx_maxcnt_trigger =
-				intr_coal->tx_max_coalesced_frames_high;
-		else
-			intrmod_cfg->tx_maxcnt_trigger =
-				LIO_INTRMOD_TXMAXCNT_TRIGGER;
-		if (intr_coal->tx_max_coalesced_frames_low)
-			intrmod_cfg->tx_mincnt_trigger =
-				intr_coal->tx_max_coalesced_frames_low;
-		else
-			intrmod_cfg->tx_mincnt_trigger =
-				LIO_INTRMOD_TXMINCNT_TRIGGER;
+	if (intrmod_cfg->rx_enable) {
+		intrmod_cfg->rx_maxcnt_trigger =
+			intr_coal->rx_max_coalesced_frames_high;
+		intrmod_cfg->rx_maxtmr_trigger =
+			intr_coal->rx_coalesce_usecs_high;
+		intrmod_cfg->rx_mintmr_trigger =
+			intr_coal->rx_coalesce_usecs_low;
+		intrmod_cfg->rx_mincnt_trigger =
+			intr_coal->rx_max_coalesced_frames_low;
+	}
+	if (intrmod_cfg->tx_enable) {
+		intrmod_cfg->tx_maxcnt_trigger =
+			intr_coal->tx_max_coalesced_frames_high;
+		intrmod_cfg->tx_mincnt_trigger =
+			intr_coal->tx_max_coalesced_frames_low;
 	}
 
 	ret = octnet_set_intrmod_cfg(lio, intrmod_cfg);
@@ -1666,7 +1741,9 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
 }
 
 static int
-oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
+oct_cfg_rx_intrcnt(struct lio *lio,
+		   struct oct_intrmod_cfg *intrmod,
+		   struct ethtool_coalesce *intr_coal)
 {
 	struct octeon_device *oct = lio->oct_dev;
 	u32 rx_max_coalesced_frames;
@@ -1692,7 +1769,7 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 		int q_no;
 
 		if (!intr_coal->rx_max_coalesced_frames)
-			rx_max_coalesced_frames = oct->intrmod.rx_frames;
+			rx_max_coalesced_frames = intrmod->rx_frames;
 		else
 			rx_max_coalesced_frames =
 			    intr_coal->rx_max_coalesced_frames;
@@ -1703,17 +1780,18 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 			    (octeon_read_csr64(
 				 oct, CN23XX_SLI_OQ_PKT_INT_LEVELS(q_no)) &
 			     (0x3fffff00000000UL)) |
-				rx_max_coalesced_frames);
+				(rx_max_coalesced_frames - 1));
 			/*consider setting resend bit*/
 		}
-		oct->intrmod.rx_frames = rx_max_coalesced_frames;
+		intrmod->rx_frames = rx_max_coalesced_frames;
+		oct->rx_max_coalesced_frames = rx_max_coalesced_frames;
 		break;
 	}
 	case OCTEON_CN23XX_VF_VID: {
 		int q_no;
 
 		if (!intr_coal->rx_max_coalesced_frames)
-			rx_max_coalesced_frames = oct->intrmod.rx_frames;
+			rx_max_coalesced_frames = intrmod->rx_frames;
 		else
 			rx_max_coalesced_frames =
 			    intr_coal->rx_max_coalesced_frames;
@@ -1724,9 +1802,10 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 				 oct, CN23XX_VF_SLI_OQ_PKT_INT_LEVELS(q_no)) &
 			     (0x3fffff00000000UL)) |
 				rx_max_coalesced_frames);
-			/* consider writing to resend bit here */
+			/*consider writing to resend bit here*/
 		}
-		oct->intrmod.rx_frames = rx_max_coalesced_frames;
+		intrmod->rx_frames = rx_max_coalesced_frames;
+		oct->rx_max_coalesced_frames = rx_max_coalesced_frames;
 		break;
 	}
 	default:
@@ -1736,6 +1815,7 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 }
 
 static int oct_cfg_rx_intrtime(struct lio *lio,
+			       struct oct_intrmod_cfg *intrmod,
 			       struct ethtool_coalesce *intr_coal)
 {
 	struct octeon_device *oct = lio->oct_dev;
@@ -1766,7 +1846,7 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 		int q_no;
 
 		if (!intr_coal->rx_coalesce_usecs)
-			rx_coalesce_usecs = oct->intrmod.rx_usecs;
+			rx_coalesce_usecs = intrmod->rx_usecs;
 		else
 			rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
 		time_threshold =
@@ -1775,11 +1855,12 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 			q_no += oct->sriov_info.pf_srn;
 			octeon_write_csr64(oct,
 					   CN23XX_SLI_OQ_PKT_INT_LEVELS(q_no),
-					   (oct->intrmod.rx_frames |
-					    (time_threshold << 32)));
+					   (intrmod->rx_frames |
+					    ((u64)time_threshold << 32)));
 			/*consider writing to resend bit here*/
 		}
-		oct->intrmod.rx_usecs = rx_coalesce_usecs;
+		intrmod->rx_usecs = rx_coalesce_usecs;
+		oct->rx_coalesce_usecs = rx_coalesce_usecs;
 		break;
 	}
 	case OCTEON_CN23XX_VF_VID: {
@@ -1787,7 +1868,7 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 		int q_no;
 
 		if (!intr_coal->rx_coalesce_usecs)
-			rx_coalesce_usecs = oct->intrmod.rx_usecs;
+			rx_coalesce_usecs = intrmod->rx_usecs;
 		else
 			rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
 
@@ -1796,11 +1877,12 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 		for (q_no = 0; q_no < oct->num_oqs; q_no++) {
 			octeon_write_csr64(
 				oct, CN23XX_VF_SLI_OQ_PKT_INT_LEVELS(q_no),
-				(oct->intrmod.rx_frames |
-				 (time_threshold << 32)));
-			/* consider setting resend bit */
+				(intrmod->rx_frames |
+				 ((u64)time_threshold << 32)));
+			/*consider setting resend bit*/
 		}
-		oct->intrmod.rx_usecs = rx_coalesce_usecs;
+		intrmod->rx_usecs = rx_coalesce_usecs;
+		oct->rx_coalesce_usecs = rx_coalesce_usecs;
 		break;
 	}
 	default:
@@ -1811,8 +1893,9 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 }
 
 static int
-oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
-		   __attribute__((unused)))
+oct_cfg_tx_intrcnt(struct lio *lio,
+		   struct oct_intrmod_cfg *intrmod,
+		   struct ethtool_coalesce *intr_coal)
 {
 	struct octeon_device *oct = lio->oct_dev;
 	u32 iq_intr_pkt;
@@ -1839,12 +1922,13 @@ oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
 			val = readq(inst_cnt_reg);
 			/*clear wmark and count.dont want to write count back*/
 			val = (val & 0xFFFF000000000000ULL) |
-			      ((u64)iq_intr_pkt
+			      ((u64)(iq_intr_pkt - 1)
 			       << CN23XX_PKT_IN_DONE_WMARK_BIT_POS);
 			writeq(val, inst_cnt_reg);
 			/*consider setting resend bit*/
 		}
-		oct->intrmod.tx_frames = iq_intr_pkt;
+		intrmod->tx_frames = iq_intr_pkt;
+		oct->tx_max_coalesced_frames = iq_intr_pkt;
 		break;
 	}
 	default:
@@ -1859,6 +1943,7 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	int ret;
 	struct octeon_device *oct = lio->oct_dev;
+	struct oct_intrmod_cfg intrmod = {0};
 	u32 j, q_no;
 	int db_max, db_min;
 
@@ -1877,8 +1962,8 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 		} else {
 			dev_err(&oct->pci_dev->dev,
 				"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
-				intr_coal->tx_max_coalesced_frames, db_min,
-				db_max);
+				intr_coal->tx_max_coalesced_frames,
+				db_min, db_max);
 			return -EINVAL;
 		}
 		break;
@@ -1889,24 +1974,36 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 		return -EINVAL;
 	}
 
-	oct->intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
-	oct->intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+	intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
+	intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+	intrmod.rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
+	intrmod.rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
+	intrmod.tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 
-	ret = oct_cfg_adaptive_intr(lio, intr_coal);
+	ret = oct_cfg_adaptive_intr(lio, &intrmod, intr_coal);
 
 	if (!intr_coal->use_adaptive_rx_coalesce) {
-		ret = oct_cfg_rx_intrtime(lio, intr_coal);
+		ret = oct_cfg_rx_intrtime(lio, &intrmod, intr_coal);
 		if (ret)
 			goto ret_intrmod;
 
-		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+		ret = oct_cfg_rx_intrcnt(lio, &intrmod, intr_coal);
 		if (ret)
 			goto ret_intrmod;
+	} else {
+		oct->rx_coalesce_usecs =
+			CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
+		oct->rx_max_coalesced_frames =
+			CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
 	}
+
 	if (!intr_coal->use_adaptive_tx_coalesce) {
-		ret = oct_cfg_tx_intrcnt(lio, intr_coal);
+		ret = oct_cfg_tx_intrcnt(lio, &intrmod, intr_coal);
 		if (ret)
 			goto ret_intrmod;
+	} else {
+		oct->tx_max_coalesced_frames =
+			CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index be9c0e3f5ade..927617cbf6a9 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -16,6 +16,7 @@
  * NONINFRINGEMENT.  See the GNU General Public License for more details.
  ***********************************************************************/
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/firmware.h>
 #include <net/vxlan.h>
@@ -60,12 +61,6 @@ MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\"");
 
 static int ptp_enable = 1;
 
-/* Bit mask values for lio->ifstate */
-#define   LIO_IFSTATE_DROQ_OPS             0x01
-#define   LIO_IFSTATE_REGISTERED           0x02
-#define   LIO_IFSTATE_RUNNING              0x04
-#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
-
 /* Polling interval for determining when NIC application is alive */
 #define LIQUIDIO_STARTER_POLL_INTERVAL_MS 100
 
@@ -152,7 +147,7 @@ struct octnic_gather {
 	 */
 	struct octeon_sg_entry *sg;
 
-	u64 sg_dma_ptr;
+	dma_addr_t sg_dma_ptr;
 };
 
 struct handshake {
@@ -178,6 +173,8 @@ static int liquidio_stop(struct net_device *netdev);
 static void liquidio_remove(struct pci_dev *pdev);
 static int liquidio_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *ent);
+static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
+				      int linkstate);
 
 static struct handshake handshake[MAX_OCTEON_DEVICES];
 static struct completion first_stage;
@@ -531,36 +528,6 @@ static void liquidio_deinit_pci(void)
 }
 
 /**
- * \brief check interface state
- * @param lio per-network private data
- * @param state_flag flag state to check
- */
-static inline int ifstate_check(struct lio *lio, int state_flag)
-{
-	return atomic_read(&lio->ifstate) & state_flag;
-}
-
-/**
- * \brief set interface state
- * @param lio per-network private data
- * @param state_flag flag state to set
- */
-static inline void ifstate_set(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
-}
-
-/**
- * \brief clear interface state
- * @param lio per-network private data
- * @param state_flag flag state to clear
- */
-static inline void ifstate_reset(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
-}
-
-/**
  * \brief Stop Tx queues
  * @param netdev network device
  */
@@ -734,6 +701,9 @@ static void delete_glists(struct lio *lio)
 	struct octnic_gather *g;
 	int i;
 
+	kfree(lio->glist_lock);
+	lio->glist_lock = NULL;
+
 	if (!lio->glist)
 		return;
 
@@ -741,23 +711,27 @@ static void delete_glists(struct lio *lio)
 		do {
 			g = (struct octnic_gather *)
 				list_delete_head(&lio->glist[i]);
-			if (g) {
-				if (g->sg) {
-					dma_unmap_single(&lio->oct_dev->
-							 pci_dev->dev,
-							 g->sg_dma_ptr,
-							 g->sg_size,
-							 DMA_TO_DEVICE);
-					kfree((void *)((unsigned long)g->sg -
-						       g->adjust));
-				}
+			if (g)
 				kfree(g);
-			}
 		} while (g);
+
+		if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+		    lio->glists_dma_base && lio->glists_dma_base[i]) {
+			lio_dma_free(lio->oct_dev,
+				     lio->glist_entry_size * lio->tx_qsize,
+				     lio->glists_virt_base[i],
+				     lio->glists_dma_base[i]);
+		}
 	}
 
-	kfree((void *)lio->glist);
-	kfree((void *)lio->glist_lock);
+	kfree(lio->glists_virt_base);
+	lio->glists_virt_base = NULL;
+
+	kfree(lio->glists_dma_base);
+	lio->glists_dma_base = NULL;
+
+	kfree(lio->glist);
+	lio->glist = NULL;
 }
 
 /**
@@ -772,22 +746,49 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
 	lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock),
 				  GFP_KERNEL);
 	if (!lio->glist_lock)
-		return 1;
+		return -ENOMEM;
 
 	lio->glist = kcalloc(num_iqs, sizeof(*lio->glist),
 			     GFP_KERNEL);
 	if (!lio->glist) {
-		kfree((void *)lio->glist_lock);
-		return 1;
+		kfree(lio->glist_lock);
+		lio->glist_lock = NULL;
+		return -ENOMEM;
+	}
+
+	lio->glist_entry_size =
+		ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+	/* allocate memory to store virtual and dma base address of
+	 * per glist consistent memory
+	 */
+	lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+					GFP_KERNEL);
+	lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+				       GFP_KERNEL);
+
+	if (!lio->glists_virt_base || !lio->glists_dma_base) {
+		delete_glists(lio);
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < num_iqs; i++) {
-		int numa_node = cpu_to_node(i % num_online_cpus());
+		int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 		spin_lock_init(&lio->glist_lock[i]);
 
 		INIT_LIST_HEAD(&lio->glist[i]);
 
+		lio->glists_virt_base[i] =
+			lio_dma_alloc(oct,
+				      lio->glist_entry_size * lio->tx_qsize,
+				      &lio->glists_dma_base[i]);
+
+		if (!lio->glists_virt_base[i]) {
+			delete_glists(lio);
+			return -ENOMEM;
+		}
+
 		for (j = 0; j < lio->tx_qsize; j++) {
 			g = kzalloc_node(sizeof(*g), GFP_KERNEL,
 					 numa_node);
@@ -796,43 +797,18 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
 			if (!g)
 				break;
 
-			g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
-				      OCT_SG_ENTRY_SIZE);
+			g->sg = lio->glists_virt_base[i] +
+				(j * lio->glist_entry_size);
 
-			g->sg = kmalloc_node(g->sg_size + 8,
-					     GFP_KERNEL, numa_node);
-			if (!g->sg)
-				g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
-			if (!g->sg) {
-				kfree(g);
-				break;
-			}
-
-			/* The gather component should be aligned on 64-bit
-			 * boundary
-			 */
-			if (((unsigned long)g->sg) & 7) {
-				g->adjust = 8 - (((unsigned long)g->sg) & 7);
-				g->sg = (struct octeon_sg_entry *)
-					((unsigned long)g->sg + g->adjust);
-			}
-			g->sg_dma_ptr = dma_map_single(&oct->pci_dev->dev,
-						       g->sg, g->sg_size,
-						       DMA_TO_DEVICE);
-			if (dma_mapping_error(&oct->pci_dev->dev,
-					      g->sg_dma_ptr)) {
-				kfree((void *)((unsigned long)g->sg -
-					       g->adjust));
-				kfree(g);
-				break;
-			}
+			g->sg_dma_ptr = lio->glists_dma_base[i] +
+					(j * lio->glist_entry_size);
 
 			list_add_tail(&g->list, &lio->glist[i]);
 		}
 
 		if (j != lio->tx_qsize) {
 			delete_glists(lio);
-			return 1;
+			return -ENOMEM;
 		}
 	}
 
@@ -959,14 +935,13 @@ static void update_txq_status(struct octeon_device *oct, int iq_num)
 			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
 						  tx_restart, 1);
 			netif_wake_subqueue(netdev, iq->q_index);
-		} else {
-			if (!octnet_iq_is_full(oct, lio->txq)) {
-				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
-							  lio->txq,
-							  tx_restart, 1);
-				wake_q(netdev, lio->txq);
-			}
 		}
+	} else if (netif_queue_stopped(netdev) &&
+		   lio->linfo.link.s.link_up &&
+		   (!octnet_iq_is_full(oct, lio->txq))) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+					  lio->txq, tx_restart, 1);
+		netif_wake_queue(netdev);
 	}
 }
 
@@ -1076,16 +1051,35 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 	int i;
 	int num_ioq_vectors;
 	int num_alloc_ioq_vectors;
+	char *queue_irq_names = NULL;
+	char *aux_irq_name = NULL;
 
 	if (OCTEON_CN23XX_PF(oct) && oct->msix_on) {
 		oct->num_msix_irqs = oct->sriov_info.num_pf_rings;
 		/* one non ioq interrupt for handling sli_mac_pf_int_sum */
 		oct->num_msix_irqs += 1;
 
+		/* allocate storage for the names assigned to each irq */
+		oct->irq_name_storage =
+			kcalloc((MAX_IOQ_INTERRUPTS_PER_PF + 1), INTRNAMSIZ,
+				GFP_KERNEL);
+		if (!oct->irq_name_storage) {
+			dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+			return -ENOMEM;
+		}
+
+		queue_irq_names = oct->irq_name_storage;
+		aux_irq_name = &queue_irq_names
+				[IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)];
+
 		oct->msix_entries = kcalloc(
 		    oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL);
-		if (!oct->msix_entries)
-			return 1;
+		if (!oct->msix_entries) {
+			dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return -ENOMEM;
+		}
 
 		msix_entries = (struct msix_entry *)oct->msix_entries;
 		/*Assumption is that pf msix vectors start from pf srn to pf to
@@ -1103,7 +1097,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 			dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return num_alloc_ioq_vectors;
 		}
 		dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
 
@@ -1111,9 +1107,12 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 
 		/** For PF, there is one non-ioq interrupt handler */
 		num_ioq_vectors -= 1;
+
+		snprintf(aux_irq_name, INTRNAMSIZ,
+			 "LiquidIO%u-pf%u-aux", oct->octeon_id, oct->pf_num);
 		irqret = request_irq(msix_entries[num_ioq_vectors].vector,
-				     liquidio_legacy_intr_handler, 0, "octeon",
-				     oct);
+				     liquidio_legacy_intr_handler, 0,
+				     aux_irq_name, oct);
 		if (irqret) {
 			dev_err(&oct->pci_dev->dev,
 				"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -1121,13 +1120,20 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 			pci_disable_msix(oct->pci_dev);
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return irqret;
 		}
 
 		for (i = 0; i < num_ioq_vectors; i++) {
+			snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ,
+				 "LiquidIO%u-pf%u-rxtx-%u",
+				 oct->octeon_id, oct->pf_num, i);
+
 			irqret = request_irq(msix_entries[i].vector,
 					     liquidio_msix_intr_handler, 0,
-					     "octeon", &oct->ioq_vector[i]);
+					     &queue_irq_names[IRQ_NAME_OFF(i)],
+					     &oct->ioq_vector[i]);
 			if (irqret) {
 				dev_err(&oct->pci_dev->dev,
 					"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -1147,7 +1153,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 				pci_disable_msix(oct->pci_dev);
 				kfree(oct->msix_entries);
 				oct->msix_entries = NULL;
-				return 1;
+				kfree(oct->irq_name_storage);
+				oct->irq_name_storage = NULL;
+				return irqret;
 			}
 			oct->ioq_vector[i].vector = msix_entries[i].vector;
 			/* assign the cpu mask for this msix interrupt vector */
@@ -1165,111 +1173,150 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 		else
 			oct->flags |= LIO_FLAG_MSI_ENABLED;
 
+		/* allocate storage for the names assigned to the irq */
+		oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL);
+		if (!oct->irq_name_storage)
+			return -ENOMEM;
+
+		queue_irq_names = oct->irq_name_storage;
+
+		snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ,
+			 "LiquidIO%u-pf%u-rxtx-%u",
+			 oct->octeon_id, oct->pf_num, 0);
+
 		irqret = request_irq(oct->pci_dev->irq,
-				     liquidio_legacy_intr_handler, IRQF_SHARED,
-				     "octeon", oct);
+				     liquidio_legacy_intr_handler,
+				     IRQF_SHARED,
+				     &queue_irq_names[IRQ_NAME_OFF(0)], oct);
 		if (irqret) {
 			if (oct->flags & LIO_FLAG_MSI_ENABLED)
 				pci_disable_msi(oct->pci_dev);
 			dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n",
 				irqret);
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return irqret;
 		}
 	}
 	return 0;
 }
 
+static struct octeon_device *get_other_octeon_device(struct octeon_device *oct)
+{
+	struct octeon_device *other_oct;
+
+	other_oct = lio_get_device(oct->octeon_id + 1);
+
+	if (other_oct && other_oct->pci_dev) {
+		int oct_busnum, other_oct_busnum;
+
+		oct_busnum = oct->pci_dev->bus->number;
+		other_oct_busnum = other_oct->pci_dev->bus->number;
+
+		if (oct_busnum == other_oct_busnum) {
+			int oct_slot, other_oct_slot;
+
+			oct_slot = PCI_SLOT(oct->pci_dev->devfn);
+			other_oct_slot = PCI_SLOT(other_oct->pci_dev->devfn);
+
+			if (oct_slot == other_oct_slot)
+				return other_oct;
+		}
+	}
+
+	return NULL;
+}
+
+static void disable_all_vf_links(struct octeon_device *oct)
+{
+	struct net_device *netdev;
+	int max_vfs, vf, i;
+
+	if (!oct)
+		return;
+
+	max_vfs = oct->sriov_info.max_vfs;
+
+	for (i = 0; i < oct->ifcount; i++) {
+		netdev = oct->props[i].netdev;
+		if (!netdev)
+			continue;
+
+		for (vf = 0; vf < max_vfs; vf++)
+			liquidio_set_vf_link_state(netdev, vf,
+						   IFLA_VF_LINK_STATE_DISABLE);
+	}
+}
+
 static int liquidio_watchdog(void *param)
 {
-	u64 wdog;
-	u16 mask_of_stuck_cores = 0;
-	u16 mask_of_crashed_cores = 0;
-	int core_num;
-	u8 core_is_stuck[LIO_MAX_CORES];
-	u8 core_crashed[LIO_MAX_CORES];
+	bool err_msg_was_printed[LIO_MAX_CORES];
+	u16 mask_of_crashed_or_stuck_cores = 0;
+	bool all_vf_links_are_disabled = false;
 	struct octeon_device *oct = param;
+	struct octeon_device *other_oct;
+#ifdef CONFIG_MODULE_UNLOAD
+	long refcount, vfs_referencing_pf;
+	u64 vfs_mask1, vfs_mask2;
+#endif
+	int core;
 
-	memset(core_is_stuck, 0, sizeof(core_is_stuck));
-	memset(core_crashed, 0, sizeof(core_crashed));
+	memset(err_msg_was_printed, 0, sizeof(err_msg_was_printed));
 
 	while (!kthread_should_stop()) {
-		mask_of_crashed_cores =
+		/* sleep for a couple of seconds so that we don't hog the CPU */
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(msecs_to_jiffies(2000));
+
+		mask_of_crashed_or_stuck_cores =
 		    (u16)octeon_read_csr64(oct, CN23XX_SLI_SCRATCH2);
 
-		for (core_num = 0; core_num < LIO_MAX_CORES; core_num++) {
-			if (!core_is_stuck[core_num]) {
-				wdog = lio_pci_readq(oct, CIU3_WDOG(core_num));
-
-				/* look at watchdog state field */
-				wdog &= CIU3_WDOG_MASK;
-				if (wdog) {
-					/* this watchdog timer has expired */
-					core_is_stuck[core_num] =
-						LIO_MONITOR_WDOG_EXPIRE;
-					mask_of_stuck_cores |= (1 << core_num);
-				}
-			}
+		if (!mask_of_crashed_or_stuck_cores)
+			continue;
 
-			if (!core_crashed[core_num])
-				core_crashed[core_num] =
-				    (mask_of_crashed_cores >> core_num) & 1;
-		}
+		WRITE_ONCE(oct->cores_crashed, true);
+		other_oct = get_other_octeon_device(oct);
+		if (other_oct)
+			WRITE_ONCE(other_oct->cores_crashed, true);
 
-		if (mask_of_stuck_cores) {
-			for (core_num = 0; core_num < LIO_MAX_CORES;
-			     core_num++) {
-				if (core_is_stuck[core_num] == 1) {
-					dev_err(&oct->pci_dev->dev,
-						"ERROR: Octeon core %d is stuck!\n",
-						core_num);
-					/* 2 means we have printk'd  an error
-					 * so no need to repeat the same printk
-					 */
-					core_is_stuck[core_num] =
-						LIO_MONITOR_CORE_STUCK_MSGD;
-				}
-			}
-		}
+		for (core = 0; core < LIO_MAX_CORES; core++) {
+			bool core_crashed_or_got_stuck;
 
-		if (mask_of_crashed_cores) {
-			for (core_num = 0; core_num < LIO_MAX_CORES;
-			     core_num++) {
-				if (core_crashed[core_num] == 1) {
-					dev_err(&oct->pci_dev->dev,
-						"ERROR: Octeon core %d crashed!  See oct-fwdump for details.\n",
-						core_num);
-					/* 2 means we have printk'd  an error
-					 * so no need to repeat the same printk
-					 */
-					core_crashed[core_num] =
-						LIO_MONITOR_CORE_STUCK_MSGD;
-				}
+			core_crashed_or_got_stuck =
+						(mask_of_crashed_or_stuck_cores
+						 >> core) & 1;
+
+			if (core_crashed_or_got_stuck &&
+			    !err_msg_was_printed[core]) {
+				dev_err(&oct->pci_dev->dev,
+					"ERROR: Octeon core %d crashed or got stuck!  See oct-fwdump for details.\n",
+					core);
+					err_msg_was_printed[core] = true;
 			}
 		}
+
+		if (all_vf_links_are_disabled)
+			continue;
+
+		disable_all_vf_links(oct);
+		disable_all_vf_links(other_oct);
+		all_vf_links_are_disabled = true;
+
 #ifdef CONFIG_MODULE_UNLOAD
-		if (mask_of_stuck_cores || mask_of_crashed_cores) {
-			/* make module refcount=0 so that rmmod will work */
-			long refcount;
+		vfs_mask1 = READ_ONCE(oct->sriov_info.vf_drv_loaded_mask);
+		vfs_mask2 = READ_ONCE(other_oct->sriov_info.vf_drv_loaded_mask);
 
-			refcount = module_refcount(THIS_MODULE);
+		vfs_referencing_pf  = hweight64(vfs_mask1);
+		vfs_referencing_pf += hweight64(vfs_mask2);
 
-			while (refcount > 0) {
+		refcount = module_refcount(THIS_MODULE);
+		if (refcount >= vfs_referencing_pf) {
+			while (vfs_referencing_pf) {
 				module_put(THIS_MODULE);
-				refcount = module_refcount(THIS_MODULE);
-			}
-
-			/* compensate for and withstand an unlikely (but still
-			 * possible) race condition
-			 */
-			while (refcount < 0) {
-				try_module_get(THIS_MODULE);
-				refcount = module_refcount(THIS_MODULE);
+				vfs_referencing_pf--;
 			}
 		}
 #endif
-		/* sleep for two seconds */
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(2 * HZ);
 	}
 
 	return 0;
@@ -1361,6 +1408,12 @@ liquidio_probe(struct pci_dev *pdev,
 	return 0;
 }
 
+static bool fw_type_is_none(void)
+{
+	return strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
+		       sizeof(LIO_FW_NAME_TYPE_NONE)) == 0;
+}
+
 /**
  *\brief Destroy resources associated with octeon device
  * @param pdev PCI device structure
@@ -1441,6 +1494,9 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 				pci_disable_msi(oct->pci_dev);
 		}
 
+		kfree(oct->irq_name_storage);
+		oct->irq_name_storage = NULL;
+
 	/* fallthrough */
 	case OCT_DEV_MSIX_ALLOC_VECTOR_DONE:
 		if (OCTEON_CN23XX_PF(oct))
@@ -1500,9 +1556,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_PCI_MAP_DONE:
-		/* Soft reset the octeon device before exiting */
-		if ((!OCTEON_CN23XX_PF(oct)) || !oct->octeon_id)
-			oct->fn_list.soft_reset(oct);
+		if (!fw_type_is_none()) {
+			/* Soft reset the octeon device before exiting */
+			if (!OCTEON_CN23XX_PF(oct) ||
+			    (OCTEON_CN23XX_PF(oct) && !oct->octeon_id))
+				oct->fn_list.soft_reset(oct);
+		}
 
 		octeon_unmap_pci_barx(oct, 0);
 		octeon_unmap_pci_barx(oct, 1);
@@ -1635,6 +1694,15 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING)
 		liquidio_stop(netdev);
 
+	if (fw_type_is_none()) {
+		struct octnic_ctrl_pkt nctrl;
+
+		memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+		nctrl.ncmd.s.cmd = OCTNET_CMD_RESET_PF;
+		nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+		octnet_send_nic_ctrl_pkt(oct, &nctrl);
+	}
+
 	if (oct->props[lio->ifidx].napi_enabled == 1) {
 		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
 			napi_disable(napi);
@@ -1650,6 +1718,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 
 	cleanup_link_status_change_wq(netdev);
 
+	cleanup_rx_oom_poll_fn(netdev);
+
 	delete_glists(lio);
 
 	free_netdev(netdev);
@@ -1885,9 +1955,6 @@ static void free_netsgbuf(void *buf)
 		i++;
 	}
 
-	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
-				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
-
 	iq = skb_iq(lio, skb);
 	spin_lock(&lio->glist_lock[iq]);
 	list_add_tail(&g->list, &lio->glist[iq]);
@@ -1933,9 +2000,6 @@ static void free_netsgbuf_with_resp(void *buf)
 		i++;
 	}
 
-	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
-				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
-
 	iq = skb_iq(lio, skb);
 
 	spin_lock(&lio->glist_lock[iq]);
@@ -2124,8 +2188,7 @@ static int load_firmware(struct octeon_device *oct)
 	char fw_name[LIO_MAX_FW_FILENAME_LEN];
 	char *tmp_fw_type;
 
-	if (strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
-		    sizeof(LIO_FW_NAME_TYPE_NONE)) == 0) {
+	if (fw_type_is_none()) {
 		dev_info(&oct->pci_dev->dev, "Skipping firmware load\n");
 		return ret;
 	}
@@ -2209,8 +2272,8 @@ static void if_cfg_callback(struct octeon_device *oct,
 
 	oct = lio_get_device(ctx->octeon_id);
 	if (resp->status)
-		dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
-			CVM_CAST64(resp->status));
+		dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: 0x%llx (0x%08x)\n",
+			CVM_CAST64(resp->status), status);
 	WRITE_ONCE(ctx->cond, 1);
 
 	snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
@@ -2435,8 +2498,11 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 	/* Flush the instruction queue */
 	iq = oct->instr_queue[iq_no];
 	if (iq) {
-		/* Process iq buffers with in the budget limits */
-		tx_done = octeon_flush_iq(oct, iq, budget);
+		if (atomic_read(&iq->instr_pending))
+			/* Process iq buffers with in the budget limits */
+			tx_done = octeon_flush_iq(oct, iq, budget);
+		else
+			tx_done = 1;
 		/* Update iq read-index rather than waiting for next interrupt.
 		 * Return back if tx_done is false.
 		 */
@@ -2553,6 +2619,15 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev,
 				__func__);
 			return 1;
 		}
+
+		if (octeon_dev->ioq_vector) {
+			struct octeon_ioq_vector *ioq_vector;
+
+			ioq_vector = &octeon_dev->ioq_vector[q];
+			netif_set_xps_queue(netdev,
+					    &ioq_vector->affinity_mask,
+					    ioq_vector->iq_index);
+		}
 	}
 
 	return 0;
@@ -3273,8 +3348,6 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 			i++;
 		}
 
-		dma_sync_single_for_device(&oct->pci_dev->dev, g->sg_dma_ptr,
-					   g->sg_size, DMA_TO_DEVICE);
 		dptr = g->sg_dma_ptr;
 
 		if (OCTEON_CN23XX_PF(oct))
@@ -3426,6 +3499,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
 	struct octnic_ctrl_pkt nctrl;
 	int ret = 0;
 
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = command;
 	nctrl.ncmd.s.param1 = rx_cmd;
@@ -3459,6 +3534,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
 	struct octnic_ctrl_pkt nctrl;
 	int ret = 0;
 
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = command;
 	nctrl.ncmd.s.more = vxlan_cmd_bit;
@@ -3596,7 +3673,8 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
 	nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0);
 	nctrl.ncmd.s.more = 1;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 	nctrl.wait_time = LIO_CMD_WAIT_TM;
 
 	nctrl.udd[0] = 0;
@@ -4122,6 +4200,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		if (setup_link_status_change_wq(netdev))
 			goto setup_nic_dev_fail;
 
+		if (setup_rx_oom_poll_fn(netdev))
+			goto setup_nic_dev_fail;
+
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
 			dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
@@ -4271,7 +4352,6 @@ static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
  */
 static int liquidio_init_nic_module(struct octeon_device *oct)
 {
-	struct oct_intrmod_cfg *intrmod_cfg;
 	int i, retval = 0;
 	int num_nic_ports = CFG_GET_NUM_NIC_PORTS(octeon_get_conf(oct));
 
@@ -4296,22 +4376,6 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 
 	liquidio_ptp_init(oct);
 
-	/* Initialize interrupt moderation params */
-	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
-	intrmod_cfg->rx_enable = 1;
-	intrmod_cfg->check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
-	intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
-	intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
-	intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
-	intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
-	intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
-	intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
-	intrmod_cfg->tx_enable = 1;
-	intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
-	intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
-	intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
-	intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
-	intrmod_cfg->tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
 
 	return retval;
@@ -4373,6 +4437,7 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
 	struct octeon_device *oct = (struct octeon_device *)buf;
 	struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
 	int i, notice, vf_idx;
+	bool cores_crashed;
 	u64 *data, vf_num;
 
 	notice = recv_pkt->rh.r.ossp;
@@ -4383,19 +4448,23 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
 	octeon_swap_8B_data(&vf_num, 1);
 	vf_idx = (int)vf_num - 1;
 
+	cores_crashed = READ_ONCE(oct->cores_crashed);
+
 	if (notice == VF_DRV_LOADED) {
 		if (!(oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx))) {
 			oct->sriov_info.vf_drv_loaded_mask |= BIT_ULL(vf_idx);
 			dev_info(&oct->pci_dev->dev,
 				 "driver for VF%d was loaded\n", vf_idx);
-			try_module_get(THIS_MODULE);
+			if (!cores_crashed)
+				try_module_get(THIS_MODULE);
 		}
 	} else if (notice == VF_DRV_REMOVED) {
 		if (oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx)) {
 			oct->sriov_info.vf_drv_loaded_mask &= ~BIT_ULL(vf_idx);
 			dev_info(&oct->pci_dev->dev,
 				 "driver for VF%d was removed\n", vf_idx);
-			module_put(THIS_MODULE);
+			if (!cores_crashed)
+				module_put(THIS_MODULE);
 		}
 	} else if (notice == VF_DRV_MACADDR_CHANGED) {
 		u8 *b = (u8 *)&data[1];
@@ -4447,14 +4516,16 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 	if (OCTEON_CN23XX_PF(octeon_dev)) {
 		if (!cn23xx_fw_loaded(octeon_dev)) {
 			fw_loaded = 0;
-			/* Do a soft reset of the Octeon device. */
-			if (octeon_dev->fn_list.soft_reset(octeon_dev))
-				return 1;
-			/* things might have changed */
-			if (!cn23xx_fw_loaded(octeon_dev))
-				fw_loaded = 0;
-			else
-				fw_loaded = 1;
+			if (!fw_type_is_none()) {
+				/* Do a soft reset of the Octeon device. */
+				if (octeon_dev->fn_list.soft_reset(octeon_dev))
+					return 1;
+				/* things might have changed */
+				if (!cn23xx_fw_loaded(octeon_dev))
+					fw_loaded = 0;
+				else
+					fw_loaded = 1;
+			}
 		} else {
 			fw_loaded = 1;
 		}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 9d5e03502c76..34c77821fad9 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -16,6 +16,7 @@
  * NONINFRINGEMENT.  See the GNU General Public License for more details.
  ***********************************************************************/
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <net/vxlan.h>
 #include "liquidio_common.h"
@@ -39,12 +40,6 @@ MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
 
 #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
-/* Bit mask values for lio->ifstate */
-#define   LIO_IFSTATE_DROQ_OPS             0x01
-#define   LIO_IFSTATE_REGISTERED           0x02
-#define   LIO_IFSTATE_RUNNING              0x04
-#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
-
 struct liquidio_if_cfg_context {
 	int octeon_id;
 
@@ -108,6 +103,8 @@ struct octnic_gather {
 	 * received from the IP layer.
 	 */
 	struct octeon_sg_entry *sg;
+
+	dma_addr_t sg_dma_ptr;
 };
 
 struct octeon_device_priv {
@@ -334,36 +331,6 @@ static struct pci_driver liquidio_vf_pci_driver = {
 };
 
 /**
- * \brief check interface state
- * @param lio per-network private data
- * @param state_flag flag state to check
- */
-static int ifstate_check(struct lio *lio, int state_flag)
-{
-	return atomic_read(&lio->ifstate) & state_flag;
-}
-
-/**
- * \brief set interface state
- * @param lio per-network private data
- * @param state_flag flag state to set
- */
-static void ifstate_set(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
-}
-
-/**
- * \brief clear interface state
- * @param lio per-network private data
- * @param state_flag flag state to clear
- */
-static void ifstate_reset(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
-}
-
-/**
  * \brief Stop Tx queues
  * @param netdev network device
  */
@@ -490,6 +457,9 @@ static void delete_glists(struct lio *lio)
 	struct octnic_gather *g;
 	int i;
 
+	kfree(lio->glist_lock);
+	lio->glist_lock = NULL;
+
 	if (!lio->glist)
 		return;
 
@@ -497,17 +467,27 @@ static void delete_glists(struct lio *lio)
 		do {
 			g = (struct octnic_gather *)
 			    list_delete_head(&lio->glist[i]);
-			if (g) {
-				if (g->sg)
-					kfree((void *)((unsigned long)g->sg -
-							g->adjust));
+			if (g)
 				kfree(g);
-			}
 		} while (g);
+
+		if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+		    lio->glists_dma_base && lio->glists_dma_base[i]) {
+			lio_dma_free(lio->oct_dev,
+				     lio->glist_entry_size * lio->tx_qsize,
+				     lio->glists_virt_base[i],
+				     lio->glists_dma_base[i]);
+		}
 	}
 
+	kfree(lio->glists_virt_base);
+	lio->glists_virt_base = NULL;
+
+	kfree(lio->glists_dma_base);
+	lio->glists_dma_base = NULL;
+
 	kfree(lio->glist);
-	kfree(lio->glist_lock);
+	lio->glist = NULL;
 }
 
 /**
@@ -522,13 +502,30 @@ static int setup_glists(struct lio *lio, int num_iqs)
 	lio->glist_lock =
 	    kzalloc(sizeof(*lio->glist_lock) * num_iqs, GFP_KERNEL);
 	if (!lio->glist_lock)
-		return 1;
+		return -ENOMEM;
 
 	lio->glist =
 	    kzalloc(sizeof(*lio->glist) * num_iqs, GFP_KERNEL);
 	if (!lio->glist) {
 		kfree(lio->glist_lock);
-		return 1;
+		lio->glist_lock = NULL;
+		return -ENOMEM;
+	}
+
+	lio->glist_entry_size =
+		ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+	/* allocate memory to store virtual and dma base address of
+	 * per glist consistent memory
+	 */
+	lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+					GFP_KERNEL);
+	lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+				       GFP_KERNEL);
+
+	if (!lio->glists_virt_base || !lio->glists_dma_base) {
+		delete_glists(lio);
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < num_iqs; i++) {
@@ -536,34 +533,33 @@ static int setup_glists(struct lio *lio, int num_iqs)
 
 		INIT_LIST_HEAD(&lio->glist[i]);
 
+		lio->glists_virt_base[i] =
+			lio_dma_alloc(lio->oct_dev,
+				      lio->glist_entry_size * lio->tx_qsize,
+				      &lio->glists_dma_base[i]);
+
+		if (!lio->glists_virt_base[i]) {
+			delete_glists(lio);
+			return -ENOMEM;
+		}
+
 		for (j = 0; j < lio->tx_qsize; j++) {
 			g = kzalloc(sizeof(*g), GFP_KERNEL);
 			if (!g)
 				break;
 
-			g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
-				      OCT_SG_ENTRY_SIZE);
+			g->sg = lio->glists_virt_base[i] +
+				(j * lio->glist_entry_size);
 
-			g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
-			if (!g->sg) {
-				kfree(g);
-				break;
-			}
+			g->sg_dma_ptr = lio->glists_dma_base[i] +
+					(j * lio->glist_entry_size);
 
-			/* The gather component should be aligned on 64-bit
-			 * boundary
-			 */
-			if (((unsigned long)g->sg) & 7) {
-				g->adjust = 8 - (((unsigned long)g->sg) & 7);
-				g->sg = (struct octeon_sg_entry *)
-					((unsigned long)g->sg + g->adjust);
-			}
 			list_add_tail(&g->list, &lio->glist[i]);
 		}
 
 		if (j != lio->tx_qsize) {
 			delete_glists(lio);
-			return 1;
+			return -ENOMEM;
 		}
 	}
 
@@ -692,13 +688,12 @@ static void update_txq_status(struct octeon_device *oct, int iq_num)
 			netif_wake_subqueue(netdev, iq->q_index);
 			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
 						  tx_restart, 1);
-		} else {
-			if (!octnet_iq_is_full(oct, lio->txq)) {
-				INCR_INSTRQUEUE_PKT_COUNT(
-				    lio->oct_dev, lio->txq, tx_restart, 1);
-				wake_q(netdev, lio->txq);
-			}
 		}
+	} else if (netif_queue_stopped(netdev) && lio->linfo.link.s.link_up &&
+		   (!octnet_iq_is_full(oct, lio->txq))) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+					  lio->txq, tx_restart, 1);
+		netif_wake_queue(netdev);
 	}
 }
 
@@ -750,6 +745,7 @@ liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev)
 static int octeon_setup_interrupt(struct octeon_device *oct)
 {
 	struct msix_entry *msix_entries;
+	char *queue_irq_names = NULL;
 	int num_alloc_ioq_vectors;
 	int num_ioq_vectors;
 	int irqret;
@@ -758,10 +754,25 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 	if (oct->msix_on) {
 		oct->num_msix_irqs = oct->sriov_info.rings_per_vf;
 
+		/* allocate storage for the names assigned to each irq */
+		oct->irq_name_storage =
+			kcalloc(MAX_IOQ_INTERRUPTS_PER_VF, INTRNAMSIZ,
+				GFP_KERNEL);
+		if (!oct->irq_name_storage) {
+			dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+			return -ENOMEM;
+		}
+
+		queue_irq_names = oct->irq_name_storage;
+
 		oct->msix_entries = kcalloc(
 		    oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL);
-		if (!oct->msix_entries)
-			return 1;
+		if (!oct->msix_entries) {
+			dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return -ENOMEM;
+		}
 
 		msix_entries = (struct msix_entry *)oct->msix_entries;
 
@@ -775,16 +786,23 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 			dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return num_alloc_ioq_vectors;
 		}
 		dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
 
 		num_ioq_vectors = oct->num_msix_irqs;
 
 		for (i = 0; i < num_ioq_vectors; i++) {
+			snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ,
+				 "LiquidIO%u-vf%u-rxtx-%u",
+				 oct->octeon_id, oct->vf_num, i);
+
 			irqret = request_irq(msix_entries[i].vector,
 					     liquidio_msix_intr_handler, 0,
-					     "octeon", &oct->ioq_vector[i]);
+					     &queue_irq_names[IRQ_NAME_OFF(i)],
+					     &oct->ioq_vector[i]);
 			if (irqret) {
 				dev_err(&oct->pci_dev->dev,
 					"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -800,7 +818,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 				pci_disable_msix(oct->pci_dev);
 				kfree(oct->msix_entries);
 				oct->msix_entries = NULL;
-				return 1;
+				kfree(oct->irq_name_storage);
+				oct->irq_name_storage = NULL;
+				return irqret;
 			}
 			oct->ioq_vector[i].vector = msix_entries[i].vector;
 			/* assign the cpu mask for this msix interrupt vector */
@@ -945,6 +965,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 			pci_disable_msix(oct->pci_dev);
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
 		}
 		/* Soft reset the octeon device before exiting */
 		if (oct->pci_dev->reset_fn)
@@ -1133,6 +1155,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
 		unregister_netdev(netdev);
 
+	cleanup_rx_oom_poll_fn(netdev);
+
 	cleanup_link_status_change_wq(netdev);
 
 	delete_glists(lio);
@@ -1324,10 +1348,6 @@ static void free_netsgbuf(void *buf)
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
-
 	iq = skb_iq(lio, skb);
 
 	spin_lock(&lio->glist_lock[iq]);
@@ -1374,10 +1394,6 @@ static void free_netsgbuf_with_resp(void *buf)
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
-
 	iq = skb_iq(lio, skb);
 
 	spin_lock(&lio->glist_lock[iq]);
@@ -1620,8 +1636,12 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 	/* Flush the instruction queue */
 	iq = oct->instr_queue[iq_no];
 	if (iq) {
-		/* Process iq buffers with in the budget limits */
-		tx_done = octeon_flush_iq(oct, iq, budget);
+		if (atomic_read(&iq->instr_pending))
+			/* Process iq buffers with in the budget limits */
+			tx_done = octeon_flush_iq(oct, iq, budget);
+		else
+			tx_done = 1;
+
 		/* Update iq read-index rather than waiting for next interrupt.
 		 * Return back if tx_done is false.
 		 */
@@ -2382,23 +2402,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 			i++;
 		}
 
-		dptr = dma_map_single(&oct->pci_dev->dev,
-				      g->sg, g->sg_size,
-				      DMA_TO_DEVICE);
-		if (dma_mapping_error(&oct->pci_dev->dev, dptr)) {
-			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 4\n",
-				__func__);
-			dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0],
-					 skb->len - skb->data_len,
-					 DMA_TO_DEVICE);
-			for (j = 1; j <= frags; j++) {
-				frag = &skb_shinfo(skb)->frags[j - 1];
-				dma_unmap_page(&oct->pci_dev->dev,
-					       g->sg[j >> 2].ptr[j & 3],
-					       frag->size, DMA_TO_DEVICE);
-			}
-			return NETDEV_TX_BUSY;
-		}
+		dptr = g->sg_dma_ptr;
 
 		ndata.cmd.cmd3.dptr = dptr;
 		finfo->dptr = dptr;
@@ -2480,6 +2484,8 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
+	struct completion compl;
+	u16 response_code;
 	int ret = 0;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
@@ -2491,14 +2497,25 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev,
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+	init_completion(&compl);
+	nctrl.completion = &compl;
+	nctrl.response_code = &response_code;
 
 	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
 			ret);
+		return -EIO;
 	}
 
-	return ret;
+	if (!wait_for_completion_timeout(&compl,
+					 msecs_to_jiffies(nctrl.wait_time)))
+		return -EPERM;
+
+	if (READ_ONCE(response_code))
+		return -EPERM;
+
+	return 0;
 }
 
 static int
@@ -2543,6 +2560,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
 	struct octnic_ctrl_pkt nctrl;
 	int ret = 0;
 
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = command;
 	nctrl.ncmd.s.param1 = rx_cmd;
@@ -2575,6 +2594,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
 	struct octnic_ctrl_pkt nctrl;
 	int ret = 0;
 
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = command;
 	nctrl.ncmd.s.more = vxlan_cmd_bit;
@@ -2997,6 +3018,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		if (setup_link_status_change_wq(netdev))
 			goto setup_nic_dev_fail;
 
+		if (setup_rx_oom_poll_fn(netdev))
+			goto setup_nic_dev_fail;
+
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
 			dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
@@ -3051,7 +3075,6 @@ setup_nic_wait_intr:
  */
 static int liquidio_init_nic_module(struct octeon_device *oct)
 {
-	struct oct_intrmod_cfg *intrmod_cfg;
 	int num_nic_ports = 1;
 	int i, retval = 0;
 
@@ -3073,22 +3096,6 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 		goto octnet_init_failure;
 	}
 
-	/* Initialize interrupt moderation params */
-	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
-	intrmod_cfg->rx_enable = 1;
-	intrmod_cfg->check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
-	intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
-	intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
-	intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
-	intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
-	intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
-	intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
-	intrmod_cfg->tx_enable = 1;
-	intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
-	intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
-	intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
-	intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
-	intrmod_cfg->tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
 
 	return retval;
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 294c6f3c6b48..8ea2323d8d67 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -27,7 +27,7 @@
 
 #define LIQUIDIO_PACKAGE ""
 #define LIQUIDIO_BASE_MAJOR_VERSION 1
-#define LIQUIDIO_BASE_MINOR_VERSION 4
+#define LIQUIDIO_BASE_MINOR_VERSION 5
 #define LIQUIDIO_BASE_MICRO_VERSION 1
 #define LIQUIDIO_BASE_VERSION   __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \
 				__stringify(LIQUIDIO_BASE_MINOR_VERSION)
@@ -83,6 +83,7 @@ enum octeon_tag_type {
 #define OPCODE_NIC_INTRMOD_CFG         0x08
 #define OPCODE_NIC_IF_CFG              0x09
 #define OPCODE_NIC_VF_DRV_NOTICE       0x0A
+#define OPCODE_NIC_INTRMOD_PARAMS      0x0B
 #define VF_DRV_LOADED                  1
 #define VF_DRV_REMOVED                -1
 #define VF_DRV_MACADDR_CHANGED         2
@@ -100,6 +101,11 @@ enum octeon_tag_type {
 
 #define BYTES_PER_DHLEN_UNIT        8
 #define MAX_REG_CNT                 2000000U
+#define INTRNAMSIZ                  32
+#define IRQ_NAME_OFF(i)             ((i) * INTRNAMSIZ)
+#define MAX_IOQ_INTERRUPTS_PER_PF   (64 * 2)
+#define MAX_IOQ_INTERRUPTS_PER_VF   (8 * 2)
+
 
 static inline u32 incr_index(u32 index, u32 count, u32 max)
 {
@@ -181,6 +187,7 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
 #define   OCTNET_CMD_Q                0
 
 /* NIC Command types */
+#define   OCTNET_CMD_RESET_PF         0x0
 #define   OCTNET_CMD_CHANGE_MTU       0x1
 #define   OCTNET_CMD_CHANGE_MACADDR   0x2
 #define   OCTNET_CMD_CHANGE_DEVFLAGS  0x3
@@ -845,29 +852,6 @@ struct oct_mdio_cmd {
 
 #define OCT_LINK_STATS_SIZE   (sizeof(struct oct_link_stats))
 
-/* intrmod: max. packet rate threshold */
-#define LIO_INTRMOD_MAXPKT_RATETHR	196608
-/* intrmod: min. packet rate threshold */
-#define LIO_INTRMOD_MINPKT_RATETHR	9216
-/* intrmod: max. packets to trigger interrupt */
-#define LIO_INTRMOD_RXMAXCNT_TRIGGER	384
-/* intrmod: min. packets to trigger interrupt */
-#define LIO_INTRMOD_RXMINCNT_TRIGGER	0
-/* intrmod: max. time to trigger interrupt */
-#define LIO_INTRMOD_RXMAXTMR_TRIGGER	128
-/* 66xx:intrmod: min. time to trigger interrupt
- * (value of 1 is optimum for TCP_RR)
- */
-#define LIO_INTRMOD_RXMINTMR_TRIGGER	1
-
-/* intrmod: max. packets to trigger interrupt */
-#define LIO_INTRMOD_TXMAXCNT_TRIGGER	64
-/* intrmod: min. packets to trigger interrupt */
-#define LIO_INTRMOD_TXMINCNT_TRIGGER	0
-
-/* intrmod: poll interval in seconds */
-#define LIO_INTRMOD_CHECK_INTERVAL  1
-
 struct oct_intrmod_cfg {
 	u64 rx_enable;
 	u64 tx_enable;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index b3dc2e9651a8..d29ebc531151 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -71,17 +71,17 @@
 #define   CN23XX_MAX_RINGS_PER_VF          8
 
 #define   CN23XX_MAX_INPUT_QUEUES	CN23XX_MAX_RINGS_PER_PF
-#define   CN23XX_MAX_IQ_DESCRIPTORS	2048
+#define   CN23XX_MAX_IQ_DESCRIPTORS	512
 #define   CN23XX_DB_MIN                 1
 #define   CN23XX_DB_MAX                 8
 #define   CN23XX_DB_TIMEOUT             1
 
 #define   CN23XX_MAX_OUTPUT_QUEUES	CN23XX_MAX_RINGS_PER_PF
-#define   CN23XX_MAX_OQ_DESCRIPTORS	2048
+#define   CN23XX_MAX_OQ_DESCRIPTORS	512
 #define   CN23XX_OQ_BUF_SIZE		1536
 #define   CN23XX_OQ_PKTSPER_INTR	128
 /*#define CAVIUM_ONLY_CN23XX_RX_PERF*/
-#define   CN23XX_OQ_REFIL_THRESHOLD	128
+#define   CN23XX_OQ_REFIL_THRESHOLD	16
 
 #define   CN23XX_OQ_INTR_PKT		64
 #define   CN23XX_OQ_INTR_TIME		100
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 9675ffbf25e6..e21b477d0159 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -793,7 +793,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct)
 	u32 num_descs = 0;
 	u32 iq_no = 0;
 	union oct_txpciq txpciq;
-	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (OCTEON_CN6XXX(oct))
 		num_descs =
@@ -837,7 +837,7 @@ int octeon_setup_output_queues(struct octeon_device *oct)
 	u32 num_descs = 0;
 	u32 desc_size = 0;
 	u32 oq_no = 0;
-	int numa_node = cpu_to_node(oq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (OCTEON_CN6XXX(oct)) {
 		num_descs =
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index c301a3852482..92f67de111aa 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -453,9 +453,6 @@ struct octeon_device {
 	/** List of dispatch functions */
 	struct octeon_dispatch_list dispatch;
 
-	/* Interrupt Moderation */
-	struct oct_intrmod_cfg intrmod;
-
 	u32 int_status;
 
 	u64 droq_intr;
@@ -517,6 +514,9 @@ struct octeon_device {
 
 	void *msix_entries;
 
+	/* when requesting IRQs, the names are stored here */
+	void *irq_name_storage;
+
 	struct octeon_sriov_info sriov_info;
 
 	struct octeon_pf_vf_hs_word pfvf_hsword;
@@ -538,6 +538,12 @@ struct octeon_device {
 	u32 priv_flags;
 
 	void *watchdog_task;
+
+	u32 rx_coalesce_usecs;
+	u32 rx_max_coalesced_frames;
+	u32 tx_max_coalesced_frames;
+
+	bool cores_crashed;
 };
 
 #define  OCT_DRV_ONLINE 1
@@ -551,12 +557,6 @@ struct octeon_device {
 #define CHIP_CONF(oct, TYPE)             \
 	(((struct octeon_ ## TYPE  *)((oct)->chip))->conf)
 
-struct oct_intrmod_cmd {
-	struct octeon_device *oct_dev;
-	struct octeon_soft_command *sc;
-	struct oct_intrmod_cfg *cfg;
-};
-
 /*------------------ Function Prototypes ----------------------*/
 
 /** Initialize device list memory */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 0be87d119a97..286be5539cef 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -155,11 +155,6 @@ octeon_droq_destroy_ring_buffers(struct octeon_device *oct,
 			recv_buffer_destroy(droq->recv_buf_list[i].buffer,
 					    pg_info);
 
-		if (droq->desc_ring && droq->desc_ring[i].info_ptr)
-			lio_unmap_ring_info(oct->pci_dev,
-					    (u64)droq->
-					    desc_ring[i].info_ptr,
-					    OCT_DROQ_INFO_SIZE);
 		droq->recv_buf_list[i].buffer = NULL;
 	}
 
@@ -211,10 +206,7 @@ int octeon_delete_droq(struct octeon_device *oct, u32 q_no)
 	vfree(droq->recv_buf_list);
 
 	if (droq->info_base_addr)
-		cnnic_free_aligned_dma(oct->pci_dev, droq->info_list,
-				       droq->info_alloc_size,
-				       droq->info_base_addr,
-				       droq->info_list_dma);
+		lio_free_info_buffer(oct, droq);
 
 	if (droq->desc_ring)
 		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
@@ -234,8 +226,7 @@ int octeon_init_droq(struct octeon_device *oct,
 	struct octeon_droq *droq;
 	u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0;
 	u32 c_pkts_per_intr = 0, c_refill_threshold = 0;
-	int orig_node = dev_to_node(&oct->pci_dev->dev);
-	int numa_node = cpu_to_node(q_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
 
@@ -275,13 +266,8 @@ int octeon_init_droq(struct octeon_device *oct,
 	droq->buffer_size = c_buf_size;
 
 	desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE;
-	set_dev_node(&oct->pci_dev->dev, numa_node);
 	droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
 					(dma_addr_t *)&droq->desc_ring_dma);
-	set_dev_node(&oct->pci_dev->dev, orig_node);
-	if (!droq->desc_ring)
-		droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
-					(dma_addr_t *)&droq->desc_ring_dma);
 
 	if (!droq->desc_ring) {
 		dev_err(&oct->pci_dev->dev,
@@ -294,12 +280,7 @@ int octeon_init_droq(struct octeon_device *oct,
 	dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no,
 		droq->max_count);
 
-	droq->info_list =
-		cnnic_numa_alloc_aligned_dma((droq->max_count *
-					      OCT_DROQ_INFO_SIZE),
-					     &droq->info_alloc_size,
-					     &droq->info_base_addr,
-					     numa_node);
+	droq->info_list = lio_alloc_info_buffer(oct, droq);
 	if (!droq->info_list) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n");
 		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
@@ -532,6 +513,32 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
 	return desc_refilled;
 }
 
+/** check if we can allocate packets to get out of oom.
+ *  @param  droq - Droq being checked.
+ *  @return does not return anything
+ */
+void octeon_droq_check_oom(struct octeon_droq *droq)
+{
+	int desc_refilled;
+	struct octeon_device *oct = droq->oct_dev;
+
+	if (readl(droq->pkts_credit_reg) <= CN23XX_SLI_DEF_BP) {
+		spin_lock_bh(&droq->lock);
+		desc_refilled = octeon_droq_refill(oct, droq);
+		if (desc_refilled) {
+			/* Flush the droq descriptor data to memory to be sure
+			 * that when we update the credits the data in memory
+			 * is accurate.
+			 */
+			wmb();
+			writel(desc_refilled, droq->pkts_credit_reg);
+			/* make sure mmio write completes */
+			mmiowb();
+		}
+		spin_unlock_bh(&droq->lock);
+	}
+}
+
 static inline u32
 octeon_droq_get_bufcount(u32 buf_size, u32 total_len)
 {
@@ -983,7 +990,7 @@ int octeon_create_droq(struct octeon_device *oct,
 		       u32 desc_size, void *app_ctx)
 {
 	struct octeon_droq *droq;
-	int numa_node = cpu_to_node(q_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (oct->droq[q_no]) {
 		dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n",
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index e62074090681..9781577115e7 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -325,10 +325,10 @@ struct octeon_droq {
 	size_t desc_ring_dma;
 
 	/** Info ptr list are allocated at this virtual address. */
-	size_t info_base_addr;
+	void *info_base_addr;
 
 	/** DMA mapped address of the info list */
-	size_t info_list_dma;
+	dma_addr_t info_list_dma;
 
 	/** Allocated size of info list. */
 	u32 info_alloc_size;
@@ -426,4 +426,6 @@ int octeon_droq_process_packets(struct octeon_device *oct,
 int octeon_process_droq_poll_cmd(struct octeon_device *oct, u32 q_no,
 				 int cmd, u32 arg);
 
+void octeon_droq_check_oom(struct octeon_droq *droq);
+
 #endif	/*__OCTEON_DROQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 4608a5af35a3..5063a12613e5 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -152,7 +152,7 @@ struct octeon_instr_queue {
 	struct oct_iq_stats stats;
 
 	/** DMA mapped base address of the input descriptor ring. */
-	u64 base_addr_dma;
+	dma_addr_t base_addr_dma;
 
 	/** Application context */
 	void *app_ctx;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
index 201b9875f9bb..5cca73b8880b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
@@ -313,6 +313,7 @@ int octeon_mbox_process_message(struct octeon_mbox *mbox)
 		return 0;
 	}
 
+	spin_unlock_irqrestore(&mbox->lock, flags);
 	WARN_ON(1);
 
 	return 0;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index aa36e9ae7676..bed9ef17bc26 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -140,48 +140,6 @@ err_release_region:
 	return 1;
 }
 
-static inline void *
-cnnic_numa_alloc_aligned_dma(u32 size,
-			     u32 *alloc_size,
-			     size_t *orig_ptr,
-			     int numa_node)
-{
-	int retries = 0;
-	void *ptr = NULL;
-
-#define OCTEON_MAX_ALLOC_RETRIES     1
-	do {
-		struct page *page = NULL;
-
-		page = alloc_pages_node(numa_node,
-					GFP_KERNEL,
-					get_order(size));
-		if (!page)
-			page = alloc_pages(GFP_KERNEL,
-					   get_order(size));
-		ptr = (void *)page_address(page);
-		if ((unsigned long)ptr & 0x07) {
-			__free_pages(page, get_order(size));
-			ptr = NULL;
-			/* Increment the size required if the first
-			 * attempt failed.
-			 */
-			if (!retries)
-				size += 7;
-		}
-		retries++;
-	} while ((retries <= OCTEON_MAX_ALLOC_RETRIES) && !ptr);
-
-	*alloc_size = size;
-	*orig_ptr = (unsigned long)ptr;
-	if ((unsigned long)ptr & 0x07)
-		ptr = (void *)(((unsigned long)ptr + 7) & ~(7UL));
-	return ptr;
-}
-
-#define cnnic_free_aligned_dma(pci_dev, ptr, size, orig_ptr, dma_addr) \
-		free_pages(orig_ptr, get_order(size))
-
 static inline int
 sleep_cond(wait_queue_head_t *wait_queue, int *condition)
 {
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index 6bb89419006e..bf483932ff25 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -28,6 +28,12 @@
 #define LIO_MAX_MTU_SIZE (OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE)
 #define LIO_MIN_MTU_SIZE ETH_MIN_MTU
 
+/* Bit mask values for lio->ifstate */
+#define   LIO_IFSTATE_DROQ_OPS             0x01
+#define   LIO_IFSTATE_REGISTERED           0x02
+#define   LIO_IFSTATE_RUNNING              0x04
+#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
+
 struct oct_nic_stats_resp {
 	u64     rh;
 	struct oct_link_stats stats;
@@ -62,6 +68,9 @@ struct lio {
 
 	/** Array of gather component linked lists */
 	struct list_head *glist;
+	void **glists_virt_base;
+	dma_addr_t *glists_dma_base;
+	u32 glist_entry_size;
 
 	/** Pointer to the NIC properties for the Octeon device this network
 	 *  interface is associated with.
@@ -120,6 +129,9 @@ struct lio {
 	/* work queue for  txq status */
 	struct cavium_wq	txq_status_wq;
 
+	/* work queue for  rxq oom status */
+	struct cavium_wq	rxq_status_wq;
+
 	/* work queue for  link status */
 	struct cavium_wq	link_status_wq;
 
@@ -129,10 +141,6 @@ struct lio {
 #define LIO_SIZE         (sizeof(struct lio))
 #define GET_LIO(netdev)  ((struct lio *)netdev_priv(netdev))
 
-#define CIU3_WDOG(c)                 (0x1010000020000ULL + ((c) << 3))
-#define CIU3_WDOG_MASK               12ULL
-#define LIO_MONITOR_WDOG_EXPIRE      1
-#define LIO_MONITOR_CORE_STUCK_MSGD  2
 #define LIO_MAX_CORES                12
 
 /**
@@ -143,6 +151,10 @@ struct lio {
  */
 int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1);
 
+int setup_rx_oom_poll_fn(struct net_device *netdev);
+
+void cleanup_rx_oom_poll_fn(struct net_device *netdev);
+
 /**
  * \brief Link control command completion callback
  * @param nctrl_ptr pointer to control packet structure
@@ -344,6 +356,29 @@ static inline void tx_buffer_free(void *buffer)
 #define lio_dma_free(oct, size, virt_addr, dma_addr) \
 	dma_free_coherent(&(oct)->pci_dev->dev, size, virt_addr, dma_addr)
 
+static inline void *
+lio_alloc_info_buffer(struct octeon_device *oct,
+		      struct octeon_droq *droq)
+{
+	void *virt_ptr;
+
+	virt_ptr = lio_dma_alloc(oct, (droq->max_count * OCT_DROQ_INFO_SIZE),
+				 &droq->info_list_dma);
+	if (virt_ptr) {
+		droq->info_alloc_size = droq->max_count * OCT_DROQ_INFO_SIZE;
+		droq->info_base_addr = virt_ptr;
+	}
+
+	return virt_ptr;
+}
+
+static inline void lio_free_info_buffer(struct octeon_device *oct,
+					struct octeon_droq *droq)
+{
+	lio_dma_free(oct, droq->info_alloc_size, droq->info_base_addr,
+		     droq->info_list_dma);
+}
+
 static inline
 void *get_rbd(struct sk_buff *skb)
 {
@@ -359,22 +394,7 @@ void *get_rbd(struct sk_buff *skb)
 static inline u64
 lio_map_ring_info(struct octeon_droq *droq, u32 i)
 {
-	dma_addr_t dma_addr;
-	struct octeon_device *oct = droq->oct_dev;
-
-	dma_addr = dma_map_single(&oct->pci_dev->dev, &droq->info_list[i],
-				  OCT_DROQ_INFO_SIZE, DMA_FROM_DEVICE);
-
-	WARN_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr));
-
-	return (u64)dma_addr;
-}
-
-static inline void
-lio_unmap_ring_info(struct pci_dev *pci_dev,
-		    u64 info_ptr, u32 size)
-{
-	dma_unmap_single(&pci_dev->dev, info_ptr, size, DMA_FROM_DEVICE);
+	return droq->info_list_dma + (i * sizeof(struct octeon_droq_info));
 }
 
 static inline u64
@@ -427,4 +447,34 @@ static inline void octeon_fast_packet_next(struct octeon_droq *droq,
 	       get_rbd(droq->recv_buf_list[idx].buffer), copy_len);
 }
 
+/**
+ * \brief check interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to check
+ */
+static inline int ifstate_check(struct lio *lio, int state_flag)
+{
+	return atomic_read(&lio->ifstate) & state_flag;
+}
+
+/**
+ * \brief set interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to set
+ */
+static inline void ifstate_set(struct lio *lio, int state_flag)
+{
+	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
+}
+
+/**
+ * \brief clear interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to clear
+ */
+static inline void ifstate_reset(struct lio *lio, int state_flag)
+{
+	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
+}
+
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index 0243be8dd56f..b457cf23fce6 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -100,14 +100,16 @@ static void octnet_link_ctrl_callback(struct octeon_device *oct,
 
 	nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr;
 
-	/* Call the callback function if status is OK.
-	 * Status is OK only if a response was expected and core returned
-	 * success.
+	/* Call the callback function if status is zero (meaning OK) or status
+	 * contains a firmware status code bigger than zero (meaning the
+	 * firmware is reporting an error).
 	 * If no response was expected, status is OK if the command was posted
 	 * successfully.
 	 */
-	if (!status && nctrl->cb_fn)
+	if ((!status || status > FIRMWARE_STATUS_CODE(0)) && nctrl->cb_fn) {
+		nctrl->status = status;
 		nctrl->cb_fn(nctrl);
+	}
 
 	octeon_free_soft_command(oct, sc);
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 0c7a5c9b2932..6480ef863441 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -62,6 +62,10 @@ struct octnic_ctrl_pkt {
 
 	/** Callback function called when the command has been fetched */
 	octnic_ctrl_pkt_cb_fn_t cb_fn;
+
+	u32 status;
+	u16 *response_code;
+	struct completion *completion;
 };
 
 #define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd))
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 707bc15adec6..261f448f9de2 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -62,8 +62,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	u32 iq_no = (u32)txpciq.s.q_no;
 	u32 q_size;
 	struct cavium_wq *db_wq;
-	int orig_node = dev_to_node(&oct->pci_dev->dev);
-	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (OCTEON_CN6XXX(oct))
 		conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn6xxx)));
@@ -91,13 +90,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	iq->oct_dev = oct;
 
-	set_dev_node(&oct->pci_dev->dev, numa_node);
-	iq->base_addr = lio_dma_alloc(oct, q_size,
-				      (dma_addr_t *)&iq->base_addr_dma);
-	set_dev_node(&oct->pci_dev->dev, orig_node);
-	if (!iq->base_addr)
-		iq->base_addr = lio_dma_alloc(oct, q_size,
-					      (dma_addr_t *)&iq->base_addr_dma);
+	iq->base_addr = lio_dma_alloc(oct, q_size, &iq->base_addr_dma);
 	if (!iq->base_addr) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n",
 			iq_no);
@@ -211,7 +204,7 @@ int octeon_setup_iq(struct octeon_device *oct,
 		    void *app_ctx)
 {
 	u32 iq_no = (u32)txpciq.s.q_no;
-	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (oct->instr_queue[iq_no]) {
 		dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n",
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index 2fbaae96b505..3d691c69f74d 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -69,50 +69,53 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 	int resp_to_process = MAX_ORD_REQS_TO_PROCESS;
 	u32 status;
 	u64 status64;
-	struct octeon_instr_rdp *rdp;
-	u64 rptr;
 
 	ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
 
 	do {
 		spin_lock_bh(&ordered_sc_list->lock);
 
-		if (ordered_sc_list->head.next == &ordered_sc_list->head) {
+		if (list_empty(&ordered_sc_list->head)) {
 			spin_unlock_bh(&ordered_sc_list->lock);
 			return 1;
 		}
 
-		sc = (struct octeon_soft_command *)ordered_sc_list->
-		    head.next;
-		if (OCTEON_CN23XX_PF(octeon_dev) ||
-		    OCTEON_CN23XX_VF(octeon_dev)) {
-			rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd3.rdp;
-			rptr = sc->cmd.cmd3.rptr;
-		} else {
-			rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
-			rptr = sc->cmd.cmd2.rptr;
-		}
+		sc = list_first_entry(&ordered_sc_list->head,
+				      struct octeon_soft_command, node);
 
 		status = OCTEON_REQUEST_PENDING;
 
 		/* check if octeon has finished DMA'ing a response
 		 * to where rptr is pointing to
 		 */
-		dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev,
-					rptr, rdp->rlen,
-					DMA_FROM_DEVICE);
 		status64 = *sc->status_word;
 
 		if (status64 != COMPLETION_WORD_INIT) {
+			/* This logic ensures that all 64b have been written.
+			 * 1. check byte 0 for non-FF
+			 * 2. if non-FF, then swap result from BE to host order
+			 * 3. check byte 7 (swapped to 0) for non-FF
+			 * 4. if non-FF, use the low 32-bit status code
+			 * 5. if either byte 0 or byte 7 is FF, don't use status
+			 */
 			if ((status64 & 0xff) != 0xff) {
 				octeon_swap_8B_data(&status64, 1);
 				if (((status64 & 0xff) != 0xff)) {
-					status = (u32)(status64 &
-						       0xffffffffULL);
+					/* retrieve 16-bit firmware status */
+					status = (u32)(status64 & 0xffffULL);
+					if (status) {
+						status =
+						  FIRMWARE_STATUS_CODE(status);
+					} else {
+						/* i.e. no error */
+						status = OCTEON_REQUEST_DONE;
+					}
 				}
 			}
 		} else if (force_quit || (sc->timeout &&
 			time_after(jiffies, (unsigned long)sc->timeout))) {
+			dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n",
+				__func__, (long)jiffies, (long)sc->timeout);
 			status = OCTEON_REQUEST_TIMEOUT;
 		}
 
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h
index cbb2d84e8932..9169c2815dba 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.h
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h
@@ -78,6 +78,8 @@ enum {
 
 /*------------   Error codes used by host driver   -----------------*/
 #define DRIVER_MAJOR_ERROR_CODE           0x0000
+/*------   Error codes used by firmware (bits 15..0 set by firmware */
+#define FIRMWARE_MAJOR_ERROR_CODE         0x0001
 
 /**  A value of 0x00000000 indicates no error i.e. success */
 #define DRIVER_ERROR_NONE                 0x00000000
@@ -116,6 +118,9 @@ enum {
 
 };
 
+#define FIRMWARE_STATUS_CODE(status) \
+	((FIRMWARE_MAJOR_ERROR_CODE << 16) | (status))
+
 /** Initialize the response lists. The number of response lists to create is
  * given by count.
  * @param octeon_dev      - the octeon device structure.
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index e739c7153562..4a02e618e318 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -252,12 +252,14 @@ struct nicvf_drv_stats {
 	u64 tx_csum_overflow;
 
 	/* driver debug stats */
-	u64 rcv_buffer_alloc_failures;
 	u64 tx_tso;
 	u64 tx_timeout;
 	u64 txq_stop;
 	u64 txq_wake;
 
+	u64 rcv_buffer_alloc_failures;
+	u64 page_alloc;
+
 	struct u64_stats_sync   syncp;
 };
 
@@ -266,9 +268,10 @@ struct nicvf {
 	struct net_device	*netdev;
 	struct pci_dev		*pdev;
 	void __iomem		*reg_base;
+	struct bpf_prog         *xdp_prog;
 #define	MAX_QUEUES_PER_QSET			8
 	struct queue_set	*qs;
-	struct nicvf_cq_poll	*napi[8];
+	void			*iommu_domain;
 	u8			vf_id;
 	u8			sqs_id;
 	bool                    sqs_mode;
@@ -293,6 +296,7 @@ struct nicvf {
 	/* Queue count */
 	u8			rx_queues;
 	u8			tx_queues;
+	u8			xdp_tx_queues;
 	u8			max_queues;
 
 	u8			node;
@@ -317,10 +321,11 @@ struct nicvf {
 	struct nicvf_drv_stats  __percpu *drv_stats;
 	struct bgx_stats	bgx_stats;
 
+	/* Napi */
+	struct nicvf_cq_poll	*napi[8];
+
 	/* MSI-X  */
-	bool			msix_enabled;
 	u8			num_vec;
-	struct msix_entry	msix_entries[NIC_VF_MSIX_VECTORS];
 	char			irq_name[NIC_VF_MSIX_VECTORS][IFNAMSIZ + 15];
 	bool			irq_allocated[NIC_VF_MSIX_VECTORS];
 	cpumask_var_t		affinity_mask[NIC_VF_MSIX_VECTORS];
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 767234e2e8f9..fb770b0182d3 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -65,9 +65,7 @@ struct nicpf {
 	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
 
 	/* MSI-X */
-	bool			msix_enabled;
 	u8			num_vec;
-	struct msix_entry	*msix_entries;
 	bool			irq_allocated[NIC_PF_MSIX_VECTORS];
 	char			irq_name[NIC_PF_MSIX_VECTORS][20];
 };
@@ -1088,7 +1086,7 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
 	u64 intr;
 	u8  vf, vf_per_mbx_reg = 64;
 
-	if (irq == nic->msix_entries[NIC_PF_INTR_ID_MBOX0].vector)
+	if (irq == pci_irq_vector(nic->pdev, NIC_PF_INTR_ID_MBOX0))
 		mbx = 0;
 	else
 		mbx = 1;
@@ -1107,51 +1105,13 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
 	return IRQ_HANDLED;
 }
 
-static int nic_enable_msix(struct nicpf *nic)
-{
-	int i, ret;
-
-	nic->num_vec = pci_msix_vec_count(nic->pdev);
-
-	nic->msix_entries = kmalloc_array(nic->num_vec,
-					  sizeof(struct msix_entry),
-					  GFP_KERNEL);
-	if (!nic->msix_entries)
-		return -ENOMEM;
-
-	for (i = 0; i < nic->num_vec; i++)
-		nic->msix_entries[i].entry = i;
-
-	ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec);
-	if (ret) {
-		dev_err(&nic->pdev->dev,
-			"Request for #%d msix vectors failed, returned %d\n",
-			   nic->num_vec, ret);
-		kfree(nic->msix_entries);
-		return ret;
-	}
-
-	nic->msix_enabled = 1;
-	return 0;
-}
-
-static void nic_disable_msix(struct nicpf *nic)
-{
-	if (nic->msix_enabled) {
-		pci_disable_msix(nic->pdev);
-		kfree(nic->msix_entries);
-		nic->msix_enabled = 0;
-		nic->num_vec = 0;
-	}
-}
-
 static void nic_free_all_interrupts(struct nicpf *nic)
 {
 	int irq;
 
 	for (irq = 0; irq < nic->num_vec; irq++) {
 		if (nic->irq_allocated[irq])
-			free_irq(nic->msix_entries[irq].vector, nic);
+			free_irq(pci_irq_vector(nic->pdev, irq), nic);
 		nic->irq_allocated[irq] = false;
 	}
 }
@@ -1159,18 +1119,24 @@ static void nic_free_all_interrupts(struct nicpf *nic)
 static int nic_register_interrupts(struct nicpf *nic)
 {
 	int i, ret;
+	nic->num_vec = pci_msix_vec_count(nic->pdev);
 
 	/* Enable MSI-X */
-	ret = nic_enable_msix(nic);
-	if (ret)
-		return ret;
+	ret = pci_alloc_irq_vectors(nic->pdev, nic->num_vec, nic->num_vec,
+				    PCI_IRQ_MSIX);
+	if (ret < 0) {
+		dev_err(&nic->pdev->dev,
+			"Request for #%d msix vectors failed, returned %d\n",
+			   nic->num_vec, ret);
+		return 1;
+	}
 
 	/* Register mailbox interrupt handler */
 	for (i = NIC_PF_INTR_ID_MBOX0; i < nic->num_vec; i++) {
 		sprintf(nic->irq_name[i],
 			"NICPF Mbox%d", (i - NIC_PF_INTR_ID_MBOX0));
 
-		ret = request_irq(nic->msix_entries[i].vector,
+		ret = request_irq(pci_irq_vector(nic->pdev, i),
 				  nic_mbx_intr_handler, 0,
 				  nic->irq_name[i], nic);
 		if (ret)
@@ -1186,14 +1152,16 @@ static int nic_register_interrupts(struct nicpf *nic)
 fail:
 	dev_err(&nic->pdev->dev, "Request irq failed\n");
 	nic_free_all_interrupts(nic);
-	nic_disable_msix(nic);
+	pci_free_irq_vectors(nic->pdev);
+	nic->num_vec = 0;
 	return ret;
 }
 
 static void nic_unregister_interrupts(struct nicpf *nic)
 {
 	nic_free_all_interrupts(nic);
-	nic_disable_msix(nic);
+	pci_free_irq_vectors(nic->pdev);
+	nic->num_vec = 0;
 }
 
 static int nic_num_sqs_en(struct nicpf *nic, int vf_en)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 02a986cdbb39..b9ece9cbf98b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -100,11 +100,12 @@ static const struct nicvf_stat nicvf_drv_stats[] = {
 	NICVF_DRV_STAT(tx_csum_overlap),
 	NICVF_DRV_STAT(tx_csum_overflow),
 
-	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_timeout),
 	NICVF_DRV_STAT(txq_stop),
 	NICVF_DRV_STAT(txq_wake),
+	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
+	NICVF_DRV_STAT(page_alloc),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -720,7 +721,7 @@ static int nicvf_set_channels(struct net_device *dev,
 	struct nicvf *nic = netdev_priv(dev);
 	int err = 0;
 	bool if_up = netif_running(dev);
-	int cqcount;
+	u8 cqcount, txq_count;
 
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
@@ -729,10 +730,26 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (channel->tx_count > nic->max_queues)
 		return -EINVAL;
 
+	if (nic->xdp_prog &&
+	    ((channel->tx_count + channel->rx_count) > nic->max_queues)) {
+		netdev_err(nic->netdev,
+			   "XDP mode, RXQs + TXQs > Max %d\n",
+			   nic->max_queues);
+		return -EINVAL;
+	}
+
 	if (if_up)
 		nicvf_stop(dev);
 
-	cqcount = max(channel->rx_count, channel->tx_count);
+	nic->rx_queues = channel->rx_count;
+	nic->tx_queues = channel->tx_count;
+	if (!nic->xdp_prog)
+		nic->xdp_tx_queues = 0;
+	else
+		nic->xdp_tx_queues = channel->rx_count;
+
+	txq_count = nic->xdp_tx_queues + nic->tx_queues;
+	cqcount = max(nic->rx_queues, txq_count);
 
 	if (cqcount > MAX_CMP_QUEUES_PER_QS) {
 		nic->sqs_count = roundup(cqcount, MAX_CMP_QUEUES_PER_QS);
@@ -741,12 +758,10 @@ static int nicvf_set_channels(struct net_device *dev,
 		nic->sqs_count = 0;
 	}
 
-	nic->qs->rq_cnt = min_t(u32, channel->rx_count, MAX_RCV_QUEUES_PER_QS);
-	nic->qs->sq_cnt = min_t(u32, channel->tx_count, MAX_SND_QUEUES_PER_QS);
+	nic->qs->rq_cnt = min_t(u8, nic->rx_queues, MAX_RCV_QUEUES_PER_QS);
+	nic->qs->sq_cnt = min_t(u8, txq_count, MAX_SND_QUEUES_PER_QS);
 	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
 
-	nic->rx_queues = channel->rx_count;
-	nic->tx_queues = channel->tx_count;
 	err = nicvf_set_real_num_queues(dev, nic->tx_queues, nic->rx_queues);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 6feaa24bcfd4..d6477af88085 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -16,6 +16,10 @@
 #include <linux/log2.h>
 #include <linux/prefetch.h>
 #include <linux/irq.h>
+#include <linux/iommu.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
 
 #include "nic_reg.h"
 #include "nic.h"
@@ -396,8 +400,10 @@ static void nicvf_request_sqs(struct nicvf *nic)
 
 	if (nic->rx_queues > MAX_RCV_QUEUES_PER_QS)
 		rx_queues = nic->rx_queues - MAX_RCV_QUEUES_PER_QS;
-	if (nic->tx_queues > MAX_SND_QUEUES_PER_QS)
-		tx_queues = nic->tx_queues - MAX_SND_QUEUES_PER_QS;
+
+	tx_queues = nic->tx_queues + nic->xdp_tx_queues;
+	if (tx_queues > MAX_SND_QUEUES_PER_QS)
+		tx_queues = tx_queues - MAX_SND_QUEUES_PER_QS;
 
 	/* Set no of Rx/Tx queues in each of the SQsets */
 	for (sqs = 0; sqs < nic->sqs_count; sqs++) {
@@ -495,12 +501,99 @@ static int nicvf_init_resources(struct nicvf *nic)
 	return 0;
 }
 
+static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
+				struct cqe_rx_t *cqe_rx, struct snd_queue *sq,
+				struct sk_buff **skb)
+{
+	struct xdp_buff xdp;
+	struct page *page;
+	u32 action;
+	u16 len, offset = 0;
+	u64 dma_addr, cpu_addr;
+	void *orig_data;
+
+	/* Retrieve packet buffer's DMA address and length */
+	len = *((u16 *)((void *)cqe_rx + (3 * sizeof(u64))));
+	dma_addr = *((u64 *)((void *)cqe_rx + (7 * sizeof(u64))));
+
+	cpu_addr = nicvf_iova_to_phys(nic, dma_addr);
+	if (!cpu_addr)
+		return false;
+	cpu_addr = (u64)phys_to_virt(cpu_addr);
+	page = virt_to_page((void *)cpu_addr);
+
+	xdp.data_hard_start = page_address(page);
+	xdp.data = (void *)cpu_addr;
+	xdp.data_end = xdp.data + len;
+	orig_data = xdp.data;
+
+	rcu_read_lock();
+	action = bpf_prog_run_xdp(prog, &xdp);
+	rcu_read_unlock();
+
+	/* Check if XDP program has changed headers */
+	if (orig_data != xdp.data) {
+		len = xdp.data_end - xdp.data;
+		offset = orig_data - xdp.data;
+		dma_addr -= offset;
+	}
+
+	switch (action) {
+	case XDP_PASS:
+		/* Check if it's a recycled page, if not
+		 * unmap the DMA mapping.
+		 *
+		 * Recycled page holds an extra reference.
+		 */
+		if (page_ref_count(page) == 1) {
+			dma_addr &= PAGE_MASK;
+			dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
+					     RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
+					     DMA_FROM_DEVICE,
+					     DMA_ATTR_SKIP_CPU_SYNC);
+		}
+
+		/* Build SKB and pass on packet to network stack */
+		*skb = build_skb(xdp.data,
+				 RCV_FRAG_LEN - cqe_rx->align_pad + offset);
+		if (!*skb)
+			put_page(page);
+		else
+			skb_put(*skb, len);
+		return false;
+	case XDP_TX:
+		nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len);
+		return true;
+	default:
+		bpf_warn_invalid_xdp_action(action);
+	case XDP_ABORTED:
+		trace_xdp_exception(nic->netdev, prog, action);
+	case XDP_DROP:
+		/* Check if it's a recycled page, if not
+		 * unmap the DMA mapping.
+		 *
+		 * Recycled page holds an extra reference.
+		 */
+		if (page_ref_count(page) == 1) {
+			dma_addr &= PAGE_MASK;
+			dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
+					     RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
+					     DMA_FROM_DEVICE,
+					     DMA_ATTR_SKIP_CPU_SYNC);
+		}
+		put_page(page);
+		return true;
+	}
+	return false;
+}
+
 static void nicvf_snd_pkt_handler(struct net_device *netdev,
 				  struct cqe_send_t *cqe_tx,
-				  int cqe_type, int budget,
+				  int budget, int *subdesc_cnt,
 				  unsigned int *tx_pkts, unsigned int *tx_bytes)
 {
 	struct sk_buff *skb = NULL;
+	struct page *page;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct snd_queue *sq;
 	struct sq_hdr_subdesc *hdr;
@@ -512,12 +605,26 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 	if (hdr->subdesc_type != SQ_DESC_TYPE_HEADER)
 		return;
 
-	netdev_dbg(nic->netdev,
-		   "%s Qset #%d SQ #%d SQ ptr #%d subdesc count %d\n",
-		   __func__, cqe_tx->sq_qs, cqe_tx->sq_idx,
-		   cqe_tx->sqe_ptr, hdr->subdesc_cnt);
+	/* Check for errors */
+	if (cqe_tx->send_status)
+		nicvf_check_cqe_tx_errs(nic->pnicvf, cqe_tx);
+
+	/* Is this a XDP designated Tx queue */
+	if (sq->is_xdp) {
+		page = (struct page *)sq->xdp_page[cqe_tx->sqe_ptr];
+		/* Check if it's recycled page or else unmap DMA mapping */
+		if (page && (page_ref_count(page) == 1))
+			nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr,
+						 hdr->subdesc_cnt);
+
+		/* Release page reference for recycling */
+		if (page)
+			put_page(page);
+		sq->xdp_page[cqe_tx->sqe_ptr] = (u64)NULL;
+		*subdesc_cnt += hdr->subdesc_cnt + 1;
+		return;
+	}
 
-	nicvf_check_cqe_tx_errs(nic, cqe_tx);
 	skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
 	if (skb) {
 		/* Check for dummy descriptor used for HW TSO offload on 88xx */
@@ -525,9 +632,14 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 			/* Get actual TSO descriptors and free them */
 			tso_sqe =
 			 (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
-			nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+			nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
+						 tso_sqe->subdesc_cnt);
+			*subdesc_cnt += tso_sqe->subdesc_cnt + 1;
+		} else {
+			nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr,
+						 hdr->subdesc_cnt);
 		}
-		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
+		*subdesc_cnt += hdr->subdesc_cnt + 1;
 		prefetch(skb);
 		(*tx_pkts)++;
 		*tx_bytes += skb->len;
@@ -538,7 +650,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 		 * a SKB attached, so just free SQEs here.
 		 */
 		if (!nic->hw_tso)
-			nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
+			*subdesc_cnt += hdr->subdesc_cnt + 1;
 	}
 }
 
@@ -572,10 +684,11 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cqe_rx_t *cqe_rx)
+				  struct cqe_rx_t *cqe_rx, struct snd_queue *sq)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct nicvf *nic = netdev_priv(netdev);
+	struct nicvf *snic = nic;
 	int err = 0;
 	int rq_idx;
 
@@ -588,16 +701,25 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	}
 
 	/* Check for errors */
-	err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
-	if (err && !cqe_rx->rb_cnt)
-		return;
+	if (cqe_rx->err_level || cqe_rx->err_opcode) {
+		err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
+		if (err && !cqe_rx->rb_cnt)
+			return;
+	}
 
-	skb = nicvf_get_rcv_skb(nic, cqe_rx);
-	if (!skb) {
-		netdev_dbg(nic->netdev, "Packet not received\n");
-		return;
+	/* For XDP, ignore pkts spanning multiple pages */
+	if (nic->xdp_prog && (cqe_rx->rb_cnt == 1)) {
+		/* Packet consumed by XDP */
+		if (nicvf_xdp_rx(snic, nic->xdp_prog, cqe_rx, sq, &skb))
+			return;
+	} else {
+		skb = nicvf_get_rcv_skb(snic, cqe_rx,
+					nic->xdp_prog ? true : false);
 	}
 
+	if (!skb)
+		return;
+
 	if (netif_msg_pktdata(nic)) {
 		netdev_info(nic->netdev, "%s: skb 0x%p, len=%d\n", netdev->name,
 			    skb, skb->len);
@@ -639,13 +761,14 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 {
 	int processed_cqe, work_done = 0, tx_done = 0;
 	int cqe_count, cqe_head;
+	int subdesc_cnt = 0;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct cmp_queue *cq = &qs->cq[cq_idx];
 	struct cqe_rx_t *cq_desc;
 	struct netdev_queue *txq;
-	struct snd_queue *sq;
-	unsigned int tx_pkts = 0, tx_bytes = 0;
+	struct snd_queue *sq = &qs->sq[cq_idx];
+	unsigned int tx_pkts = 0, tx_bytes = 0, txq_idx;
 
 	spin_lock_bh(&cq->lock);
 loop:
@@ -660,8 +783,6 @@ loop:
 	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
 	cqe_head &= 0xFFFF;
 
-	netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
-		   __func__, cq_idx, cqe_count, cqe_head);
 	while (processed_cqe < cqe_count) {
 		/* Get the CQ descriptor */
 		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -675,17 +796,15 @@ loop:
 			break;
 		}
 
-		netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
-			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq_desc);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc, sq);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
-			nicvf_snd_pkt_handler(netdev,
-					      (void *)cq_desc, CQE_TYPE_SEND,
-					      budget, &tx_pkts, &tx_bytes);
+			nicvf_snd_pkt_handler(netdev, (void *)cq_desc,
+					      budget, &subdesc_cnt,
+					      &tx_pkts, &tx_bytes);
 			tx_done++;
 		break;
 		case CQE_TYPE_INVALID:
@@ -697,9 +816,6 @@ loop:
 		}
 		processed_cqe++;
 	}
-	netdev_dbg(nic->netdev,
-		   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
-		   __func__, cq_idx, processed_cqe, work_done, budget);
 
 	/* Ring doorbell to inform H/W to reuse processed CQEs */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -709,13 +825,26 @@ loop:
 		goto loop;
 
 done:
+	/* Update SQ's descriptor free count */
+	if (subdesc_cnt)
+		nicvf_put_sq_desc(sq, subdesc_cnt);
+
+	txq_idx = nicvf_netdev_qidx(nic, cq_idx);
+	/* Handle XDP TX queues */
+	if (nic->pnicvf->xdp_prog) {
+		if (txq_idx < nic->pnicvf->xdp_tx_queues) {
+			nicvf_xdp_sq_doorbell(nic, sq, cq_idx);
+			goto out;
+		}
+		nic = nic->pnicvf;
+		txq_idx -= nic->pnicvf->xdp_tx_queues;
+	}
+
 	/* Wakeup TXQ if its stopped earlier due to SQ full */
-	sq = &nic->qs->sq[cq_idx];
 	if (tx_done ||
 	    (atomic_read(&sq->free_cnt) >= MIN_SQ_DESC_PER_PKT_XMIT)) {
 		netdev = nic->pnicvf->netdev;
-		txq = netdev_get_tx_queue(netdev,
-					  nicvf_netdev_qidx(nic, cq_idx));
+		txq = netdev_get_tx_queue(netdev, txq_idx);
 		if (tx_pkts)
 			netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
 
@@ -728,10 +857,11 @@ done:
 			if (netif_msg_tx_err(nic))
 				netdev_warn(netdev,
 					    "%s: Transmit queue wakeup SQ%d\n",
-					    netdev->name, cq_idx);
+					    netdev->name, txq_idx);
 		}
 	}
 
+out:
 	spin_unlock_bh(&cq->lock);
 	return work_done;
 }
@@ -875,38 +1005,9 @@ static irqreturn_t nicvf_qs_err_intr_handler(int irq, void *nicvf_irq)
 	return IRQ_HANDLED;
 }
 
-static int nicvf_enable_msix(struct nicvf *nic)
-{
-	int ret, vec;
-
-	nic->num_vec = NIC_VF_MSIX_VECTORS;
-
-	for (vec = 0; vec < nic->num_vec; vec++)
-		nic->msix_entries[vec].entry = vec;
-
-	ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec);
-	if (ret) {
-		netdev_err(nic->netdev,
-			   "Req for #%d msix vectors failed\n", nic->num_vec);
-		return 0;
-	}
-	nic->msix_enabled = 1;
-	return 1;
-}
-
-static void nicvf_disable_msix(struct nicvf *nic)
-{
-	if (nic->msix_enabled) {
-		pci_disable_msix(nic->pdev);
-		nic->msix_enabled = 0;
-		nic->num_vec = 0;
-	}
-}
-
 static void nicvf_set_irq_affinity(struct nicvf *nic)
 {
 	int vec, cpu;
-	int irqnum;
 
 	for (vec = 0; vec < nic->num_vec; vec++) {
 		if (!nic->irq_allocated[vec])
@@ -923,15 +1024,14 @@ static void nicvf_set_irq_affinity(struct nicvf *nic)
 
 		cpumask_set_cpu(cpumask_local_spread(cpu, nic->node),
 				nic->affinity_mask[vec]);
-		irqnum = nic->msix_entries[vec].vector;
-		irq_set_affinity_hint(irqnum, nic->affinity_mask[vec]);
+		irq_set_affinity_hint(pci_irq_vector(nic->pdev, vec),
+				      nic->affinity_mask[vec]);
 	}
 }
 
 static int nicvf_register_interrupts(struct nicvf *nic)
 {
 	int irq, ret = 0;
-	int vector;
 
 	for_each_cq_irq(irq)
 		sprintf(nic->irq_name[irq], "%s-rxtx-%d",
@@ -950,8 +1050,8 @@ static int nicvf_register_interrupts(struct nicvf *nic)
 
 	/* Register CQ interrupts */
 	for (irq = 0; irq < nic->qs->cq_cnt; irq++) {
-		vector = nic->msix_entries[irq].vector;
-		ret = request_irq(vector, nicvf_intr_handler,
+		ret = request_irq(pci_irq_vector(nic->pdev, irq),
+				  nicvf_intr_handler,
 				  0, nic->irq_name[irq], nic->napi[irq]);
 		if (ret)
 			goto err;
@@ -961,8 +1061,8 @@ static int nicvf_register_interrupts(struct nicvf *nic)
 	/* Register RBDR interrupt */
 	for (irq = NICVF_INTR_ID_RBDR;
 	     irq < (NICVF_INTR_ID_RBDR + nic->qs->rbdr_cnt); irq++) {
-		vector = nic->msix_entries[irq].vector;
-		ret = request_irq(vector, nicvf_rbdr_intr_handler,
+		ret = request_irq(pci_irq_vector(nic->pdev, irq),
+				  nicvf_rbdr_intr_handler,
 				  0, nic->irq_name[irq], nic);
 		if (ret)
 			goto err;
@@ -974,7 +1074,7 @@ static int nicvf_register_interrupts(struct nicvf *nic)
 		nic->pnicvf->netdev->name,
 		nic->sqs_mode ? (nic->sqs_id + 1) : 0);
 	irq = NICVF_INTR_ID_QS_ERR;
-	ret = request_irq(nic->msix_entries[irq].vector,
+	ret = request_irq(pci_irq_vector(nic->pdev, irq),
 			  nicvf_qs_err_intr_handler,
 			  0, nic->irq_name[irq], nic);
 	if (ret)
@@ -994,6 +1094,7 @@ err:
 
 static void nicvf_unregister_interrupts(struct nicvf *nic)
 {
+	struct pci_dev *pdev = nic->pdev;
 	int irq;
 
 	/* Free registered interrupts */
@@ -1001,19 +1102,20 @@ static void nicvf_unregister_interrupts(struct nicvf *nic)
 		if (!nic->irq_allocated[irq])
 			continue;
 
-		irq_set_affinity_hint(nic->msix_entries[irq].vector, NULL);
+		irq_set_affinity_hint(pci_irq_vector(pdev, irq), NULL);
 		free_cpumask_var(nic->affinity_mask[irq]);
 
 		if (irq < NICVF_INTR_ID_SQ)
-			free_irq(nic->msix_entries[irq].vector, nic->napi[irq]);
+			free_irq(pci_irq_vector(pdev, irq), nic->napi[irq]);
 		else
-			free_irq(nic->msix_entries[irq].vector, nic);
+			free_irq(pci_irq_vector(pdev, irq), nic);
 
 		nic->irq_allocated[irq] = false;
 	}
 
 	/* Disable MSI-X */
-	nicvf_disable_msix(nic);
+	pci_free_irq_vectors(pdev);
+	nic->num_vec = 0;
 }
 
 /* Initialize MSIX vectors and register MISC interrupt.
@@ -1025,16 +1127,22 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic)
 	int irq = NICVF_INTR_ID_MISC;
 
 	/* Return if mailbox interrupt is already registered */
-	if (nic->msix_enabled)
+	if (nic->pdev->msix_enabled)
 		return 0;
 
 	/* Enable MSI-X */
-	if (!nicvf_enable_msix(nic))
+	nic->num_vec = pci_msix_vec_count(nic->pdev);
+	ret = pci_alloc_irq_vectors(nic->pdev, nic->num_vec, nic->num_vec,
+				    PCI_IRQ_MSIX);
+	if (ret < 0) {
+		netdev_err(nic->netdev,
+			   "Req for #%d msix vectors failed\n", nic->num_vec);
 		return 1;
+	}
 
 	sprintf(nic->irq_name[irq], "%s Mbox", "NICVF");
 	/* Register Misc interrupt */
-	ret = request_irq(nic->msix_entries[irq].vector,
+	ret = request_irq(pci_irq_vector(nic->pdev, irq),
 			  nicvf_misc_intr_handler, 0, nic->irq_name[irq], nic);
 
 	if (ret)
@@ -1069,6 +1177,13 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_OK;
 	}
 
+	/* In XDP case, initial HW tx queues are used for XDP,
+	 * but stack's queue mapping starts at '0', so skip the
+	 * Tx queues attached to Rx queues for XDP.
+	 */
+	if (nic->xdp_prog)
+		qid += nic->xdp_tx_queues;
+
 	snic = nic;
 	/* Get secondary Qset's SQ structure */
 	if (qid >= MAX_SND_QUEUES_PER_QS) {
@@ -1157,7 +1272,7 @@ int nicvf_stop(struct net_device *netdev)
 
 	/* Wait for pending IRQ handlers to finish */
 	for (irq = 0; irq < nic->num_vec; irq++)
-		synchronize_irq(nic->msix_entries[irq].vector);
+		synchronize_irq(pci_irq_vector(nic->pdev, irq));
 
 	tasklet_kill(&nic->rbdr_task);
 	tasklet_kill(&nic->qs_err_task);
@@ -1358,7 +1473,7 @@ static int nicvf_set_mac_address(struct net_device *netdev, void *p)
 
 	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 
-	if (nic->msix_enabled) {
+	if (nic->pdev->msix_enabled) {
 		if (nicvf_hw_set_mac_addr(nic, netdev))
 			return -EBUSY;
 	} else {
@@ -1546,6 +1661,114 @@ static int nicvf_set_features(struct net_device *netdev,
 	return 0;
 }
 
+static void nicvf_set_xdp_queues(struct nicvf *nic, bool bpf_attached)
+{
+	u8 cq_count, txq_count;
+
+	/* Set XDP Tx queue count same as Rx queue count */
+	if (!bpf_attached)
+		nic->xdp_tx_queues = 0;
+	else
+		nic->xdp_tx_queues = nic->rx_queues;
+
+	/* If queue count > MAX_CMP_QUEUES_PER_QS, then additional qsets
+	 * needs to be allocated, check how many.
+	 */
+	txq_count = nic->xdp_tx_queues + nic->tx_queues;
+	cq_count = max(nic->rx_queues, txq_count);
+	if (cq_count > MAX_CMP_QUEUES_PER_QS) {
+		nic->sqs_count = roundup(cq_count, MAX_CMP_QUEUES_PER_QS);
+		nic->sqs_count = (nic->sqs_count / MAX_CMP_QUEUES_PER_QS) - 1;
+	} else {
+		nic->sqs_count = 0;
+	}
+
+	/* Set primary Qset's resources */
+	nic->qs->rq_cnt = min_t(u8, nic->rx_queues, MAX_RCV_QUEUES_PER_QS);
+	nic->qs->sq_cnt = min_t(u8, txq_count, MAX_SND_QUEUES_PER_QS);
+	nic->qs->cq_cnt = max_t(u8, nic->qs->rq_cnt, nic->qs->sq_cnt);
+
+	/* Update stack */
+	nicvf_set_real_num_queues(nic->netdev, nic->tx_queues, nic->rx_queues);
+}
+
+static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
+{
+	struct net_device *dev = nic->netdev;
+	bool if_up = netif_running(nic->netdev);
+	struct bpf_prog *old_prog;
+	bool bpf_attached = false;
+
+	/* For now just support only the usual MTU sized frames */
+	if (prog && (dev->mtu > 1500)) {
+		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    dev->mtu);
+		return -EOPNOTSUPP;
+	}
+
+	/* ALL SQs attached to CQs i.e same as RQs, are treated as
+	 * XDP Tx queues and more Tx queues are allocated for
+	 * network stack to send pkts out.
+	 *
+	 * No of Tx queues are either same as Rx queues or whatever
+	 * is left in max no of queues possible.
+	 */
+	if ((nic->rx_queues + nic->tx_queues) > nic->max_queues) {
+		netdev_warn(dev,
+			    "Failed to attach BPF prog, RXQs + TXQs > Max %d\n",
+			    nic->max_queues);
+		return -ENOMEM;
+	}
+
+	if (if_up)
+		nicvf_stop(nic->netdev);
+
+	old_prog = xchg(&nic->xdp_prog, prog);
+	/* Detach old prog, if any */
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (nic->xdp_prog) {
+		/* Attach BPF program */
+		nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
+		if (!IS_ERR(nic->xdp_prog))
+			bpf_attached = true;
+	}
+
+	/* Calculate Tx queues needed for XDP and network stack */
+	nicvf_set_xdp_queues(nic, bpf_attached);
+
+	if (if_up) {
+		/* Reinitialize interface, clean slate */
+		nicvf_open(nic->netdev);
+		netif_trans_update(nic->netdev);
+	}
+
+	return 0;
+}
+
+static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	/* To avoid checks while retrieving buffer address from CQE_RX,
+	 * do not support XDP for T88 pass1.x silicons which are anyway
+	 * not in use widely.
+	 */
+	if (pass1_silicon(nic->pdev))
+		return -EOPNOTSUPP;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return nicvf_xdp_setup(nic, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = !!nic->xdp_prog;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_open		= nicvf_open,
 	.ndo_stop		= nicvf_stop,
@@ -1556,6 +1779,7 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_tx_timeout         = nicvf_tx_timeout,
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
+	.ndo_xdp		= nicvf_xdp,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -1643,6 +1867,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!pass1_silicon(nic->pdev))
 		nic->hw_tso = true;
 
+	/* Get iommu domain for iova to physical addr conversion */
+	nic->iommu_domain = iommu_get_domain_for_dev(dev);
+
 	pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid);
 	if (sdevid == 0xA134)
 		nic->t88 = true;
@@ -1655,8 +1882,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_unregister_interrupts;
 
-	netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG |
-			       NETIF_F_TSO | NETIF_F_GRO |
+	netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_SG |
+			       NETIF_F_TSO | NETIF_F_GRO | NETIF_F_TSO6 |
+			       NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			       NETIF_F_HW_VLAN_CTAG_RX);
 
 	netdev->hw_features |= NETIF_F_RXHASH;
@@ -1664,7 +1892,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->features |= netdev->hw_features;
 	netdev->hw_features |= NETIF_F_LOOPBACK;
 
-	netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
+	netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM |
+				NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
 
 	netdev->netdev_ops = &nicvf_netdev_ops;
 	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index ac0390be3b12..2b181762ad49 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -10,6 +10,7 @@
 #include <linux/netdevice.h>
 #include <linux/ip.h>
 #include <linux/etherdevice.h>
+#include <linux/iommu.h>
 #include <net/ip.h>
 #include <net/tso.h>
 
@@ -18,6 +19,8 @@
 #include "q_struct.h"
 #include "nicvf_queues.h"
 
+static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
+					       int size, u64 data);
 static void nicvf_get_page(struct nicvf *nic)
 {
 	if (!nic->rb_pageref || !nic->rb_page)
@@ -79,19 +82,110 @@ static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem)
 	dmem->base = NULL;
 }
 
-/* Allocate buffer for packet reception
- * HW returns memory address where packet is DMA'ed but not a pointer
- * into RBDR ring, so save buffer address at the start of fragment and
- * align the start address to a cache aligned address
+#define XDP_PAGE_REFCNT_REFILL 256
+
+/* Allocate a new page or recycle one if possible
+ *
+ * We cannot optimize dma mapping here, since
+ * 1. It's only one RBDR ring for 8 Rx queues.
+ * 2. CQE_RX gives address of the buffer where pkt has been DMA'ed
+ *    and not idx into RBDR ring, so can't refer to saved info.
+ * 3. There are multiple receive buffers per page
  */
-static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
-					 u32 buf_len, u64 **rbuf)
+static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
+					       struct rbdr *rbdr, gfp_t gfp)
 {
-	int order = (PAGE_SIZE <= 4096) ?  PAGE_ALLOC_COSTLY_ORDER : 0;
+	int ref_count;
+	struct page *page = NULL;
+	struct pgcache *pgcache, *next;
+
+	/* Check if page is already allocated */
+	pgcache = &rbdr->pgcache[rbdr->pgidx];
+	page = pgcache->page;
+	/* Check if page can be recycled */
+	if (page) {
+		ref_count = page_ref_count(page);
+		/* Check if this page has been used once i.e 'put_page'
+		 * called after packet transmission i.e internal ref_count
+		 * and page's ref_count are equal i.e page can be recycled.
+		 */
+		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
+			pgcache->ref_count--;
+		else
+			page = NULL;
+
+		/* In non-XDP mode, page's ref_count needs to be '1' for it
+		 * to be recycled.
+		 */
+		if (!rbdr->is_xdp && (ref_count != 1))
+			page = NULL;
+	}
+
+	if (!page) {
+		page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, 0);
+		if (!page)
+			return NULL;
+
+		this_cpu_inc(nic->pnicvf->drv_stats->page_alloc);
 
-	/* Check if request can be accomodated in previous allocated page */
-	if (nic->rb_page &&
-	    ((nic->rb_page_offset + buf_len) < (PAGE_SIZE << order))) {
+		/* Check for space */
+		if (rbdr->pgalloc >= rbdr->pgcnt) {
+			/* Page can still be used */
+			nic->rb_page = page;
+			return NULL;
+		}
+
+		/* Save the page in page cache */
+		pgcache->page = page;
+		pgcache->dma_addr = 0;
+		pgcache->ref_count = 0;
+		rbdr->pgalloc++;
+	}
+
+	/* Take additional page references for recycling */
+	if (rbdr->is_xdp) {
+		/* Since there is single RBDR (i.e single core doing
+		 * page recycling) per 8 Rx queues, in XDP mode adjusting
+		 * page references atomically is the biggest bottleneck, so
+		 * take bunch of references at a time.
+		 *
+		 * So here, below reference counts defer by '1'.
+		 */
+		if (!pgcache->ref_count) {
+			pgcache->ref_count = XDP_PAGE_REFCNT_REFILL;
+			page_ref_add(page, XDP_PAGE_REFCNT_REFILL);
+		}
+	} else {
+		/* In non-XDP case, single 64K page is divided across multiple
+		 * receive buffers, so cost of recycling is less anyway.
+		 * So we can do with just one extra reference.
+		 */
+		page_ref_add(page, 1);
+	}
+
+	rbdr->pgidx++;
+	rbdr->pgidx &= (rbdr->pgcnt - 1);
+
+	/* Prefetch refcount of next page in page cache */
+	next = &rbdr->pgcache[rbdr->pgidx];
+	page = next->page;
+	if (page)
+		prefetch(&page->_refcount);
+
+	return pgcache;
+}
+
+/* Allocate buffer for packet reception */
+static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, struct rbdr *rbdr,
+					 gfp_t gfp, u32 buf_len, u64 *rbuf)
+{
+	struct pgcache *pgcache = NULL;
+
+	/* Check if request can be accomodated in previous allocated page.
+	 * But in XDP mode only one buffer per page is permitted.
+	 */
+	if (!rbdr->is_xdp && nic->rb_page &&
+	    ((nic->rb_page_offset + buf_len) <= PAGE_SIZE)) {
 		nic->rb_pageref++;
 		goto ret;
 	}
@@ -99,21 +193,41 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 	nicvf_get_page(nic);
 	nic->rb_page = NULL;
 
-	/* Allocate a new page */
-	if (!nic->rb_page) {
-		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
-					   order);
-		if (!nic->rb_page) {
-			this_cpu_inc(nic->pnicvf->drv_stats->
-				     rcv_buffer_alloc_failures);
-			return -ENOMEM;
-		}
-		nic->rb_page_offset = 0;
+	/* Get new page, either recycled or new one */
+	pgcache = nicvf_alloc_page(nic, rbdr, gfp);
+	if (!pgcache && !nic->rb_page) {
+		this_cpu_inc(nic->pnicvf->drv_stats->rcv_buffer_alloc_failures);
+		return -ENOMEM;
 	}
 
+	nic->rb_page_offset = 0;
+
+	/* Reserve space for header modifications by BPF program */
+	if (rbdr->is_xdp)
+		buf_len += XDP_PACKET_HEADROOM;
+
+	/* Check if it's recycled */
+	if (pgcache)
+		nic->rb_page = pgcache->page;
 ret:
-	*rbuf = (u64 *)((u64)page_address(nic->rb_page) + nic->rb_page_offset);
-	nic->rb_page_offset += buf_len;
+	if (rbdr->is_xdp && pgcache && pgcache->dma_addr) {
+		*rbuf = pgcache->dma_addr;
+	} else {
+		/* HW will ensure data coherency, CPU sync not required */
+		*rbuf = (u64)dma_map_page_attrs(&nic->pdev->dev, nic->rb_page,
+						nic->rb_page_offset, buf_len,
+						DMA_FROM_DEVICE,
+						DMA_ATTR_SKIP_CPU_SYNC);
+		if (dma_mapping_error(&nic->pdev->dev, (dma_addr_t)*rbuf)) {
+			if (!nic->rb_page_offset)
+				__free_pages(nic->rb_page, 0);
+			nic->rb_page = NULL;
+			return -ENOMEM;
+		}
+		if (pgcache)
+			pgcache->dma_addr = *rbuf + XDP_PACKET_HEADROOM;
+		nic->rb_page_offset += buf_len;
+	}
 
 	return 0;
 }
@@ -143,7 +257,7 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 			    int ring_len, int buf_size)
 {
 	int idx;
-	u64 *rbuf;
+	u64 rbuf;
 	struct rbdr_entry_t *desc;
 	int err;
 
@@ -158,16 +272,45 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 	rbdr->dma_size = buf_size;
 	rbdr->enable = true;
 	rbdr->thresh = RBDR_THRESH;
+	rbdr->head = 0;
+	rbdr->tail = 0;
+
+	/* Initialize page recycling stuff.
+	 *
+	 * Can't use single buffer per page especially with 64K pages.
+	 * On embedded platforms i.e 81xx/83xx available memory itself
+	 * is low and minimum ring size of RBDR is 8K, that takes away
+	 * lots of memory.
+	 *
+	 * But for XDP it has to be a single buffer per page.
+	 */
+	if (!nic->pnicvf->xdp_prog) {
+		rbdr->pgcnt = ring_len / (PAGE_SIZE / buf_size);
+		rbdr->is_xdp = false;
+	} else {
+		rbdr->pgcnt = ring_len;
+		rbdr->is_xdp = true;
+	}
+	rbdr->pgcnt = roundup_pow_of_two(rbdr->pgcnt);
+	rbdr->pgcache = kzalloc(sizeof(*rbdr->pgcache) *
+				rbdr->pgcnt, GFP_KERNEL);
+	if (!rbdr->pgcache)
+		return -ENOMEM;
+	rbdr->pgidx = 0;
+	rbdr->pgalloc = 0;
 
 	nic->rb_page = NULL;
 	for (idx = 0; idx < ring_len; idx++) {
-		err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN,
-					     &rbuf);
-		if (err)
+		err = nicvf_alloc_rcv_buffer(nic, rbdr, GFP_KERNEL,
+					     RCV_FRAG_LEN, &rbuf);
+		if (err) {
+			/* To free already allocated and mapped ones */
+			rbdr->tail = idx - 1;
 			return err;
+		}
 
 		desc = GET_RBDR_DESC(rbdr, idx);
-		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+		desc->buf_addr = rbuf & ~(NICVF_RCV_BUF_ALIGN_BYTES - 1);
 	}
 
 	nicvf_get_page(nic);
@@ -179,7 +322,8 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 {
 	int head, tail;
-	u64 buf_addr;
+	u64 buf_addr, phys_addr;
+	struct pgcache *pgcache;
 	struct rbdr_entry_t *desc;
 
 	if (!rbdr)
@@ -192,18 +336,44 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	head = rbdr->head;
 	tail = rbdr->tail;
 
-	/* Free SKBs */
+	/* Release page references */
 	while (head != tail) {
 		desc = GET_RBDR_DESC(rbdr, head);
-		buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
-		put_page(virt_to_page(phys_to_virt(buf_addr)));
+		buf_addr = desc->buf_addr;
+		phys_addr = nicvf_iova_to_phys(nic, buf_addr);
+		dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
+				     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+		if (phys_addr)
+			put_page(virt_to_page(phys_to_virt(phys_addr)));
 		head++;
 		head &= (rbdr->dmem.q_len - 1);
 	}
-	/* Free SKB of tail desc */
+	/* Release buffer of tail desc */
 	desc = GET_RBDR_DESC(rbdr, tail);
-	buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
-	put_page(virt_to_page(phys_to_virt(buf_addr)));
+	buf_addr = desc->buf_addr;
+	phys_addr = nicvf_iova_to_phys(nic, buf_addr);
+	dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
+			     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	if (phys_addr)
+		put_page(virt_to_page(phys_to_virt(phys_addr)));
+
+	/* Sync page cache info */
+	smp_rmb();
+
+	/* Release additional page references held for recycling */
+	head = 0;
+	while (head < rbdr->pgcnt) {
+		pgcache = &rbdr->pgcache[head];
+		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
+			if (!rbdr->is_xdp) {
+				put_page(pgcache->page);
+				continue;
+			}
+			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
+			put_page(pgcache->page);
+		}
+		head++;
+	}
 
 	/* Free RBDR ring */
 	nicvf_free_q_desc_mem(nic, &rbdr->dmem);
@@ -219,7 +389,7 @@ static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp)
 	int refill_rb_cnt;
 	struct rbdr *rbdr;
 	struct rbdr_entry_t *desc;
-	u64 *rbuf;
+	u64 rbuf;
 	int new_rb = 0;
 
 refill:
@@ -240,17 +410,20 @@ refill:
 	else
 		refill_rb_cnt = qs->rbdr_len - qcount - 1;
 
+	/* Sync page cache info */
+	smp_rmb();
+
 	/* Start filling descs from tail */
 	tail = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_TAIL, rbdr_idx) >> 3;
 	while (refill_rb_cnt) {
 		tail++;
 		tail &= (rbdr->dmem.q_len - 1);
 
-		if (nicvf_alloc_rcv_buffer(nic, gfp, RCV_FRAG_LEN, &rbuf))
+		if (nicvf_alloc_rcv_buffer(nic, rbdr, gfp, RCV_FRAG_LEN, &rbuf))
 			break;
 
 		desc = GET_RBDR_DESC(rbdr, tail);
-		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+		desc->buf_addr = rbuf & ~(NICVF_RCV_BUF_ALIGN_BYTES - 1);
 		refill_rb_cnt--;
 		new_rb++;
 	}
@@ -333,7 +506,7 @@ static void nicvf_free_cmp_queue(struct nicvf *nic, struct cmp_queue *cq)
 
 /* Initialize transmit queue */
 static int nicvf_init_snd_queue(struct nicvf *nic,
-				struct snd_queue *sq, int q_len)
+				struct snd_queue *sq, int q_len, int qidx)
 {
 	int err;
 
@@ -346,24 +519,66 @@ static int nicvf_init_snd_queue(struct nicvf *nic,
 	sq->skbuff = kcalloc(q_len, sizeof(u64), GFP_KERNEL);
 	if (!sq->skbuff)
 		return -ENOMEM;
+
 	sq->head = 0;
 	sq->tail = 0;
-	atomic_set(&sq->free_cnt, q_len - 1);
 	sq->thresh = SND_QUEUE_THRESH;
 
-	/* Preallocate memory for TSO segment's header */
-	sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev,
-					  q_len * TSO_HEADER_SIZE,
-					  &sq->tso_hdrs_phys, GFP_KERNEL);
-	if (!sq->tso_hdrs)
-		return -ENOMEM;
+	/* Check if this SQ is a XDP TX queue */
+	if (nic->sqs_mode)
+		qidx += ((nic->sqs_id + 1) * MAX_SND_QUEUES_PER_QS);
+	if (qidx < nic->pnicvf->xdp_tx_queues) {
+		/* Alloc memory to save page pointers for XDP_TX */
+		sq->xdp_page = kcalloc(q_len, sizeof(u64), GFP_KERNEL);
+		if (!sq->xdp_page)
+			return -ENOMEM;
+		sq->xdp_desc_cnt = 0;
+		sq->xdp_free_cnt = q_len - 1;
+		sq->is_xdp = true;
+	} else {
+		sq->xdp_page = NULL;
+		sq->xdp_desc_cnt = 0;
+		sq->xdp_free_cnt = 0;
+		sq->is_xdp = false;
+
+		atomic_set(&sq->free_cnt, q_len - 1);
+
+		/* Preallocate memory for TSO segment's header */
+		sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev,
+						  q_len * TSO_HEADER_SIZE,
+						  &sq->tso_hdrs_phys,
+						  GFP_KERNEL);
+		if (!sq->tso_hdrs)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
 
+void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
+			      int hdr_sqe, u8 subdesc_cnt)
+{
+	u8 idx;
+	struct sq_gather_subdesc *gather;
+
+	/* Unmap DMA mapped skb data buffers */
+	for (idx = 0; idx < subdesc_cnt; idx++) {
+		hdr_sqe++;
+		hdr_sqe &= (sq->dmem.q_len - 1);
+		gather = (struct sq_gather_subdesc *)GET_SQ_DESC(sq, hdr_sqe);
+		/* HW will ensure data coherency, CPU sync not required */
+		dma_unmap_page_attrs(&nic->pdev->dev, gather->addr,
+				     gather->size, DMA_TO_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
+	}
+}
+
 static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 {
 	struct sk_buff *skb;
+	struct page *page;
+	struct sq_hdr_subdesc *hdr;
+	struct sq_hdr_subdesc *tso_sqe;
 
 	if (!sq)
 		return;
@@ -379,12 +594,35 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 	smp_rmb();
 	while (sq->head != sq->tail) {
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (!skb || !sq->xdp_page)
+			goto next;
+
+		page = (struct page *)sq->xdp_page[sq->head];
+		if (!page)
+			goto next;
+		else
+			put_page(page);
+
+		hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head);
+		/* Check for dummy descriptor used for HW TSO offload on 88xx */
+		if (hdr->dont_send) {
+			/* Get actual TSO descriptors and unmap them */
+			tso_sqe =
+			 (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+			nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
+						 tso_sqe->subdesc_cnt);
+		} else {
+			nicvf_unmap_sndq_buffers(nic, sq, sq->head,
+						 hdr->subdesc_cnt);
+		}
 		if (skb)
 			dev_kfree_skb_any(skb);
+next:
 		sq->head++;
 		sq->head &= (sq->dmem.q_len - 1);
 	}
 	kfree(sq->skbuff);
+	kfree(sq->xdp_page);
 	nicvf_free_q_desc_mem(nic, &sq->dmem);
 }
 
@@ -559,9 +797,11 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 	nicvf_send_msg_to_pf(nic, &mbx);
 
 	if (!nic->sqs_mode && (qidx == 0)) {
-		/* Enable checking L3/L4 length and TCP/UDP checksums */
+		/* Enable checking L3/L4 length and TCP/UDP checksums
+		 * Also allow IPv6 pkts with zero UDP checksum.
+		 */
 		nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0,
-				      (BIT(24) | BIT(23) | BIT(21)));
+				      (BIT(24) | BIT(23) | BIT(21) | BIT(20)));
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
 	}
 
@@ -773,7 +1013,7 @@ static int nicvf_alloc_resources(struct nicvf *nic)
 
 	/* Alloc send queue */
 	for (qidx = 0; qidx < qs->sq_cnt; qidx++) {
-		if (nicvf_init_snd_queue(nic, &qs->sq[qidx], qs->sq_len))
+		if (nicvf_init_snd_queue(nic, &qs->sq[qidx], qs->sq_len, qidx))
 			goto alloc_fail;
 	}
 
@@ -811,6 +1051,7 @@ int nicvf_set_qset_resources(struct nicvf *nic)
 
 	nic->rx_queues = qs->rq_cnt;
 	nic->tx_queues = qs->sq_cnt;
+	nic->xdp_tx_queues = 0;
 
 	return 0;
 }
@@ -875,17 +1116,31 @@ static inline int nicvf_get_sq_desc(struct snd_queue *sq, int desc_cnt)
 	int qentry;
 
 	qentry = sq->tail;
-	atomic_sub(desc_cnt, &sq->free_cnt);
+	if (!sq->is_xdp)
+		atomic_sub(desc_cnt, &sq->free_cnt);
+	else
+		sq->xdp_free_cnt -= desc_cnt;
 	sq->tail += desc_cnt;
 	sq->tail &= (sq->dmem.q_len - 1);
 
 	return qentry;
 }
 
+/* Rollback to previous tail pointer when descriptors not used */
+static inline void nicvf_rollback_sq_desc(struct snd_queue *sq,
+					  int qentry, int desc_cnt)
+{
+	sq->tail = qentry;
+	atomic_add(desc_cnt, &sq->free_cnt);
+}
+
 /* Free descriptor back to SQ for future use */
 void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt)
 {
-	atomic_add(desc_cnt, &sq->free_cnt);
+	if (!sq->is_xdp)
+		atomic_add(desc_cnt, &sq->free_cnt);
+	else
+		sq->xdp_free_cnt += desc_cnt;
 	sq->head += desc_cnt;
 	sq->head &= (sq->dmem.q_len - 1);
 }
@@ -943,6 +1198,58 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq,
 	}
 }
 
+/* XDP Transmit APIs */
+void nicvf_xdp_sq_doorbell(struct nicvf *nic,
+			   struct snd_queue *sq, int sq_num)
+{
+	if (!sq->xdp_desc_cnt)
+		return;
+
+	/* make sure all memory stores are done before ringing doorbell */
+	wmb();
+
+	/* Inform HW to xmit all TSO segments */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
+			      sq_num, sq->xdp_desc_cnt);
+	sq->xdp_desc_cnt = 0;
+}
+
+static inline void
+nicvf_xdp_sq_add_hdr_subdesc(struct snd_queue *sq, int qentry,
+			     int subdesc_cnt, u64 data, int len)
+{
+	struct sq_hdr_subdesc *hdr;
+
+	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
+	memset(hdr, 0, SND_QUEUE_DESC_SIZE);
+	hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
+	hdr->subdesc_cnt = subdesc_cnt;
+	hdr->tot_len = len;
+	hdr->post_cqe = 1;
+	sq->xdp_page[qentry] = (u64)virt_to_page((void *)data);
+}
+
+int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq,
+			    u64 bufaddr, u64 dma_addr, u16 len)
+{
+	int subdesc_cnt = MIN_SQ_DESC_PER_PKT_XMIT;
+	int qentry;
+
+	if (subdesc_cnt > sq->xdp_free_cnt)
+		return 0;
+
+	qentry = nicvf_get_sq_desc(sq, subdesc_cnt);
+
+	nicvf_xdp_sq_add_hdr_subdesc(sq, qentry, subdesc_cnt - 1, bufaddr, len);
+
+	qentry = nicvf_get_nxt_sqentry(sq, qentry);
+	nicvf_sq_add_gather_subdesc(sq, qentry, len, dma_addr);
+
+	sq->xdp_desc_cnt += subdesc_cnt;
+
+	return 1;
+}
+
 /* Calculate no of SQ subdescriptors needed to transmit all
  * segments of this TSO packet.
  * Taken from 'Tilera network driver' with a minor modification.
@@ -1021,7 +1328,13 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 {
 	int proto;
 	struct sq_hdr_subdesc *hdr;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
 
+	ip.hdr = skb_network_header(skb);
 	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
 	memset(hdr, 0, SND_QUEUE_DESC_SIZE);
 	hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
@@ -1046,7 +1359,9 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		hdr->l3_offset = skb_network_offset(skb);
 		hdr->l4_offset = skb_transport_offset(skb);
 
-		proto = ip_hdr(skb)->protocol;
+		proto = (ip.v4->version == 4) ? ip.v4->protocol :
+			ip.v6->nexthdr;
+
 		switch (proto) {
 		case IPPROTO_TCP:
 			hdr->csum_l4 = SEND_L4_CSUM_TCP;
@@ -1207,8 +1522,9 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
 			struct sk_buff *skb, u8 sq_num)
 {
 	int i, size;
-	int subdesc_cnt, tso_sqe = 0;
+	int subdesc_cnt, hdr_sqe = 0;
 	int qentry;
+	u64 dma_addr;
 
 	subdesc_cnt = nicvf_sq_subdesc_required(nic, skb);
 	if (subdesc_cnt > atomic_read(&sq->free_cnt))
@@ -1223,12 +1539,21 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
 	/* Add SQ header subdesc */
 	nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1,
 				 skb, skb->len);
-	tso_sqe = qentry;
+	hdr_sqe = qentry;
 
 	/* Add SQ gather subdescs */
 	qentry = nicvf_get_nxt_sqentry(sq, qentry);
 	size = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len;
-	nicvf_sq_add_gather_subdesc(sq, qentry, size, virt_to_phys(skb->data));
+	/* HW will ensure data coherency, CPU sync not required */
+	dma_addr = dma_map_page_attrs(&nic->pdev->dev, virt_to_page(skb->data),
+				      offset_in_page(skb->data), size,
+				      DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
+		nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt);
+		return 0;
+	}
+
+	nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr);
 
 	/* Check for scattered buffer */
 	if (!skb_is_nonlinear(skb))
@@ -1241,15 +1566,26 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
 
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
 		size = skb_frag_size(frag);
-		nicvf_sq_add_gather_subdesc(sq, qentry, size,
-					    virt_to_phys(
-					    skb_frag_address(frag)));
+		dma_addr = dma_map_page_attrs(&nic->pdev->dev,
+					      skb_frag_page(frag),
+					      frag->page_offset, size,
+					      DMA_TO_DEVICE,
+					      DMA_ATTR_SKIP_CPU_SYNC);
+		if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
+			/* Free entire chain of mapped buffers
+			 * here 'i' = frags mapped + above mapped skb->data
+			 */
+			nicvf_unmap_sndq_buffers(nic, sq, hdr_sqe, i);
+			nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt);
+			return 0;
+		}
+		nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr);
 	}
 
 doorbell:
 	if (nic->t88 && skb_shinfo(skb)->gso_size) {
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
-		nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb);
+		nicvf_sq_add_cqe_subdesc(sq, qentry, hdr_sqe, skb);
 	}
 
 	nicvf_sq_doorbell(nic, skb, sq_num, subdesc_cnt);
@@ -1272,8 +1608,33 @@ static inline unsigned frag_num(unsigned i)
 #endif
 }
 
+static void nicvf_unmap_rcv_buffer(struct nicvf *nic, u64 dma_addr,
+				   u64 buf_addr, bool xdp)
+{
+	struct page *page = NULL;
+	int len = RCV_FRAG_LEN;
+
+	if (xdp) {
+		page = virt_to_page(phys_to_virt(buf_addr));
+		/* Check if it's a recycled page, if not
+		 * unmap the DMA mapping.
+		 *
+		 * Recycled page holds an extra reference.
+		 */
+		if (page_ref_count(page) != 1)
+			return;
+
+		len += XDP_PACKET_HEADROOM;
+		/* Receive buffers in XDP mode are mapped from page start */
+		dma_addr &= PAGE_MASK;
+	}
+	dma_unmap_page_attrs(&nic->pdev->dev, dma_addr, len,
+			     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+}
+
 /* Returns SKB for a received packet */
-struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
+struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic,
+				  struct cqe_rx_t *cqe_rx, bool xdp)
 {
 	int frag;
 	int payload_len = 0;
@@ -1282,6 +1643,7 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 	int offset;
 	u16 *rb_lens = NULL;
 	u64 *rb_ptrs = NULL;
+	u64 phys_addr;
 
 	rb_lens = (void *)cqe_rx + (3 * sizeof(u64));
 	/* Except 88xx pass1 on all other chips CQE_RX2_S is added to
@@ -1296,15 +1658,22 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 	else
 		rb_ptrs = (void *)cqe_rx + (7 * sizeof(u64));
 
-	netdev_dbg(nic->netdev, "%s rb_cnt %d rb0_ptr %llx rb0_sz %d\n",
-		   __func__, cqe_rx->rb_cnt, cqe_rx->rb0_ptr, cqe_rx->rb0_sz);
-
 	for (frag = 0; frag < cqe_rx->rb_cnt; frag++) {
 		payload_len = rb_lens[frag_num(frag)];
+		phys_addr = nicvf_iova_to_phys(nic, *rb_ptrs);
+		if (!phys_addr) {
+			if (skb)
+				dev_kfree_skb_any(skb);
+			return NULL;
+		}
+
 		if (!frag) {
 			/* First fragment */
+			nicvf_unmap_rcv_buffer(nic,
+					       *rb_ptrs - cqe_rx->align_pad,
+					       phys_addr, xdp);
 			skb = nicvf_rb_ptr_to_skb(nic,
-						  *rb_ptrs - cqe_rx->align_pad,
+						  phys_addr - cqe_rx->align_pad,
 						  payload_len);
 			if (!skb)
 				return NULL;
@@ -1312,8 +1681,9 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 			skb_put(skb, payload_len);
 		} else {
 			/* Add fragments */
-			page = virt_to_page(phys_to_virt(*rb_ptrs));
-			offset = phys_to_virt(*rb_ptrs) - page_address(page);
+			nicvf_unmap_rcv_buffer(nic, *rb_ptrs, phys_addr, xdp);
+			page = virt_to_page(phys_to_virt(phys_addr));
+			offset = phys_to_virt(phys_addr) - page_address(page);
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
 					offset, payload_len, RCV_FRAG_LEN);
 		}
@@ -1441,9 +1811,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 /* Check for errors in the receive cmp.queue entry */
 int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
-	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
-		return 0;
-
 	if (netif_msg_rx_err(nic))
 		netdev_err(nic->netdev,
 			   "%s: RX error CQE err_level 0x%x err_opcode 0x%x\n",
@@ -1532,8 +1899,6 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx)
 {
 	switch (cqe_tx->send_status) {
-	case CQ_TX_ERROP_GOOD:
-		return 0;
 	case CQ_TX_ERROP_DESC_FAULT:
 		this_cpu_inc(nic->drv_stats->tx_desc_fault);
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 5cb84da99a2d..57858522c33c 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -10,6 +10,7 @@
 #define NICVF_QUEUES_H
 
 #include <linux/netdevice.h>
+#include <linux/iommu.h>
 #include "q_struct.h"
 
 #define MAX_QUEUE_SET			128
@@ -87,7 +88,7 @@
 #define RCV_BUF_COUNT		(1ULL << (RBDR_SIZE + 13))
 #define MAX_RCV_BUF_COUNT	(1ULL << (RBDR_SIZE6 + 13))
 #define RBDR_THRESH		(RCV_BUF_COUNT / 2)
-#define DMA_BUFFER_LEN		2048 /* In multiples of 128bytes */
+#define DMA_BUFFER_LEN		1536 /* In multiples of 128bytes */
 #define RCV_FRAG_LEN	 (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \
 			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
@@ -213,6 +214,12 @@ struct q_desc_mem {
 	void		*unalign_base;
 };
 
+struct pgcache {
+	struct page	*page;
+	int		ref_count;
+	u64		dma_addr;
+};
+
 struct rbdr {
 	bool		enable;
 	u32		dma_size;
@@ -222,6 +229,13 @@ struct rbdr {
 	u32		head;
 	u32		tail;
 	struct q_desc_mem   dmem;
+	bool		is_xdp;
+
+	/* For page recycling */
+	int		pgidx;
+	int		pgcnt;
+	int		pgalloc;
+	struct pgcache	*pgcache;
 } ____cacheline_aligned_in_smp;
 
 struct rcv_queue {
@@ -258,6 +272,10 @@ struct snd_queue {
 	u32		tail;
 	u64		*skbuff;
 	void		*desc;
+	u64		*xdp_page;
+	u16		xdp_desc_cnt;
+	u16		xdp_free_cnt;
+	bool		is_xdp;
 
 #define	TSO_HEADER_SIZE	128
 	/* For TSO segment's header */
@@ -301,6 +319,16 @@ struct queue_set {
 
 #define	CQ_ERR_MASK	(CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT)
 
+static inline u64 nicvf_iova_to_phys(struct nicvf *nic, dma_addr_t dma_addr)
+{
+	/* Translation is installed only when IOMMU is present */
+	if (nic->iommu_domain)
+		return iommu_iova_to_phys(nic->iommu_domain, dma_addr);
+	return dma_addr;
+}
+
+void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
+			      int hdr_sqe, u8 subdesc_cnt);
 void nicvf_config_vlan_stripping(struct nicvf *nic,
 				 netdev_features_t features);
 int nicvf_set_qset_resources(struct nicvf *nic);
@@ -316,8 +344,12 @@ void nicvf_sq_free_used_descs(struct net_device *netdev,
 			      struct snd_queue *sq, int qidx);
 int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
 			struct sk_buff *skb, u8 sq_num);
+int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq,
+			    u64 bufaddr, u64 dma_addr, u16 len);
+void nicvf_xdp_sq_doorbell(struct nicvf *nic, struct snd_queue *sq, int sq_num);
 
-struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
+struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic,
+				  struct cqe_rx_t *cqe_rx, bool xdp);
 void nicvf_rbdr_task(unsigned long data);
 void nicvf_rbdr_work(struct work_struct *work);
 
diff --git a/drivers/net/ethernet/cavium/thunder/q_struct.h b/drivers/net/ethernet/cavium/thunder/q_struct.h
index f36347237a54..e47205aa87ea 100644
--- a/drivers/net/ethernet/cavium/thunder/q_struct.h
+++ b/drivers/net/ethernet/cavium/thunder/q_struct.h
@@ -359,15 +359,7 @@ union cq_desc_t {
 };
 
 struct rbdr_entry_t {
-#if defined(__BIG_ENDIAN_BITFIELD)
-	u64   rsvd0:15;
-	u64   buf_addr:42;
-	u64   cache_align:7;
-#elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u64   cache_align:7;
-	u64   buf_addr:42;
-	u64   rsvd0:15;
-#endif
+	u64   buf_addr;
 };
 
 /* TCP reassembly context */
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 4c8e8cf730bb..a0ca68ce3fbb 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -123,14 +123,45 @@ static int bgx_poll_reg(struct bgx *bgx, u8 lmac, u64 reg, u64 mask, bool zero)
 	return 1;
 }
 
+static int max_bgx_per_node;
+static void set_max_bgx_per_node(struct pci_dev *pdev)
+{
+	u16 sdevid;
+
+	if (max_bgx_per_node)
+		return;
+
+	pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid);
+	switch (sdevid) {
+	case PCI_SUBSYS_DEVID_81XX_BGX:
+	case PCI_SUBSYS_DEVID_81XX_RGX:
+		max_bgx_per_node = MAX_BGX_PER_CN81XX;
+		break;
+	case PCI_SUBSYS_DEVID_83XX_BGX:
+		max_bgx_per_node = MAX_BGX_PER_CN83XX;
+		break;
+	case PCI_SUBSYS_DEVID_88XX_BGX:
+	default:
+		max_bgx_per_node = MAX_BGX_PER_CN88XX;
+		break;
+	}
+}
+
+static struct bgx *get_bgx(int node, int bgx_idx)
+{
+	int idx = (node * max_bgx_per_node) + bgx_idx;
+
+	return bgx_vnic[idx];
+}
+
 /* Return number of BGX present in HW */
 unsigned bgx_get_map(int node)
 {
 	int i;
 	unsigned map = 0;
 
-	for (i = 0; i < MAX_BGX_PER_NODE; i++) {
-		if (bgx_vnic[(node * MAX_BGX_PER_NODE) + i])
+	for (i = 0; i < max_bgx_per_node; i++) {
+		if (bgx_vnic[(node * max_bgx_per_node) + i])
 			map |= (1 << i);
 	}
 
@@ -143,7 +174,7 @@ int bgx_get_lmac_count(int node, int bgx_idx)
 {
 	struct bgx *bgx;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (bgx)
 		return bgx->lmac_count;
 
@@ -158,7 +189,7 @@ void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status)
 	struct bgx *bgx;
 	struct lmac *lmac;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return;
 
@@ -172,7 +203,7 @@ EXPORT_SYMBOL(bgx_get_lmac_link_state);
 
 const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid)
 {
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 
 	if (bgx)
 		return bgx->lmac[lmacid].mac;
@@ -183,7 +214,7 @@ EXPORT_SYMBOL(bgx_get_lmac_mac);
 
 void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac)
 {
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 
 	if (!bgx)
 		return;
@@ -194,7 +225,7 @@ EXPORT_SYMBOL(bgx_set_lmac_mac);
 
 void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
 {
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 	struct lmac *lmac;
 	u64 cfg;
 
@@ -217,7 +248,7 @@ EXPORT_SYMBOL(bgx_lmac_rx_tx_enable);
 void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause)
 {
 	struct pfc *pfc = (struct pfc *)pause;
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 	struct lmac *lmac;
 	u64 cfg;
 
@@ -237,7 +268,7 @@ EXPORT_SYMBOL(bgx_lmac_get_pfc);
 void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause)
 {
 	struct pfc *pfc = (struct pfc *)pause;
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 	struct lmac *lmac;
 	u64 cfg;
 
@@ -369,7 +400,7 @@ u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx)
 {
 	struct bgx *bgx;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return 0;
 
@@ -383,7 +414,7 @@ u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx)
 {
 	struct bgx *bgx;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return 0;
 
@@ -411,7 +442,7 @@ void bgx_lmac_internal_loopback(int node, int bgx_idx,
 	struct lmac *lmac;
 	u64    cfg;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return;
 
@@ -1011,12 +1042,6 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid)
 			dev_info(dev, "%s: 40G_KR4\n", (char *)str);
 		break;
 	case BGX_MODE_QSGMII:
-		if ((lmacid == 0) &&
-		    (bgx_get_lane2sds_cfg(bgx, lmac) != lmacid))
-			return;
-		if ((lmacid == 2) &&
-		    (bgx_get_lane2sds_cfg(bgx, lmac) == lmacid))
-			return;
 		dev_info(dev, "%s: QSGMII\n", (char *)str);
 		break;
 	case BGX_MODE_RGMII:
@@ -1334,11 +1359,13 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_release_regions;
 	}
 
+	set_max_bgx_per_node(pdev);
+
 	pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid);
 	if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) {
 		bgx->bgx_id = (pci_resource_start(pdev,
 			PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK;
-		bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE;
+		bgx->bgx_id += nic_get_node_id(pdev) * max_bgx_per_node;
 		bgx->max_lmac = MAX_LMAC_PER_BGX;
 		bgx_vnic[bgx->bgx_id] = bgx;
 	} else {
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index a60f189429bb..6b7fe6fdd13b 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -16,13 +16,13 @@
 /* Subsystem device IDs */
 #define PCI_SUBSYS_DEVID_88XX_BGX		0xA126
 #define PCI_SUBSYS_DEVID_81XX_BGX		0xA226
+#define PCI_SUBSYS_DEVID_81XX_RGX		0xA254
 #define PCI_SUBSYS_DEVID_83XX_BGX		0xA326
 
 #define    MAX_BGX_THUNDER			8 /* Max 2 nodes, 4 per node */
 #define    MAX_BGX_PER_CN88XX			2
 #define    MAX_BGX_PER_CN81XX			3 /* 2 BGXs + 1 RGX */
 #define    MAX_BGX_PER_CN83XX			4
-#define    MAX_BGX_PER_NODE			4
 #define    MAX_LMAC_PER_BGX			4
 #define    MAX_BGX_CHANS_PER_LMAC		16
 #define    MAX_DMAC_PER_LMAC			8
diff --git a/drivers/net/ethernet/chelsio/cxgb/common.h b/drivers/net/ethernet/chelsio/cxgb/common.h
index 6916c62f2487..94b9482f14a5 100644
--- a/drivers/net/ethernet/chelsio/cxgb/common.h
+++ b/drivers/net/ethernet/chelsio/cxgb/common.h
@@ -223,7 +223,6 @@ struct port_info {
 	struct cmac *mac;
 	struct cphy *phy;
 	struct link_config link_config;
-	struct net_device_stats netstats;
 };
 
 struct sge;
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index d8aff7a4b3c7..8623be13bf86 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -296,7 +296,7 @@ static struct net_device_stats *t1_get_stats(struct net_device *dev)
 {
 	struct adapter *adapter = dev->ml_priv;
 	struct port_info *p = &adapter->port[dev->if_port];
-	struct net_device_stats *ns = &p->netstats;
+	struct net_device_stats *ns = &dev->stats;
 	const struct cmac_statistics *pstats;
 
 	/* Do a full update of the MAC stats */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
index 8b395b537330..087ff0ffb597 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
@@ -72,7 +72,6 @@ struct port_info {
 	struct cphy phy;
 	struct cmac mac;
 	struct link_config link_config;
-	struct net_device_stats netstats;
 	int activity;
 	__be32 iscsi_ipv4addr;
 	struct iscsi_config iscsic;
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index d76491676b51..2ff6bd139c96 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1489,7 +1489,7 @@ static struct net_device_stats *cxgb_get_stats(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
-	struct net_device_stats *ns = &pi->netstats;
+	struct net_device_stats *ns = &dev->stats;
 	const struct mac_stats *pstats;
 
 	spin_lock(&adapter->stats_lock);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index afb0967d2ce6..c12c4a3b82b5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2338,6 +2338,10 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 	f->locked = 1;
 	f->fs.rpttid = 1;
 
+	/* Save the actual tid. We need this to get the corresponding
+	 * filter entry structure in filter_rpl.
+	 */
+	f->tid = stid + adap->tids.ftid_base;
 	ret = set_filter_wr(adap, stid);
 	if (ret) {
 		clear_filter(adap, f);
@@ -3809,6 +3813,15 @@ static int adap_init0(struct adapter *adap)
 	}
 	if (caps_cmd.cryptocaps) {
 		/* Should query params here...TODO */
+		params[0] = FW_PARAM_PFVF(NCRYPTO_LOOKASIDE);
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
+				      params, val);
+		if (ret < 0) {
+			if (ret != -EINVAL)
+				goto bye;
+		} else {
+			adap->vres.ncrypto_fc = val[0];
+		}
 		adap->params.crypto |= ULP_CRYPTO_LOOKASIDE;
 		adap->num_uld += 1;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 4c856605fdfa..6e74040af49a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -272,6 +272,7 @@ struct cxgb4_virt_res {                      /* virtualized HW resources */
 	struct cxgb4_range qp;
 	struct cxgb4_range cq;
 	struct cxgb4_range ocq;
+	unsigned int ncrypto_fc;
 };
 
 #define OCQ_WIN_OFFSET(pdev, vres) \
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 87000cd39737..0de8eb72325c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -6369,7 +6369,6 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 	unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
 	unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
 	unsigned int fl_align_log = fls(fl_align) - 1;
-	unsigned int ingpad;
 
 	t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A,
 		     HOSTPAGESIZEPF0_V(sge_hps) |
@@ -6389,6 +6388,10 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 						  INGPADBOUNDARY_SHIFT_X) |
 				 EGRSTATUSPAGESIZE_V(stat_len != 64));
 	} else {
+		unsigned int pack_align;
+		unsigned int ingpad, ingpack;
+		unsigned int pcie_cap;
+
 		/* T5 introduced the separation of the Free List Padding and
 		 * Packing Boundaries.  Thus, we can select a smaller Padding
 		 * Boundary to avoid uselessly chewing up PCIe Link and Memory
@@ -6401,27 +6404,62 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 		 * Size (the minimum unit of transfer to/from Memory).  If we
 		 * have a Padding Boundary which is smaller than the Memory
 		 * Line Size, that'll involve a Read-Modify-Write cycle on the
-		 * Memory Controller which is never good.  For T5 the smallest
-		 * Padding Boundary which we can select is 32 bytes which is
-		 * larger than any known Memory Controller Line Size so we'll
-		 * use that.
-		 *
-		 * T5 has a different interpretation of the "0" value for the
-		 * Packing Boundary.  This corresponds to 16 bytes instead of
-		 * the expected 32 bytes.  We never have a Packing Boundary
-		 * less than 32 bytes so we can't use that special value but
-		 * on the other hand, if we wanted 32 bytes, the best we can
-		 * really do is 64 bytes.
-		*/
-		if (fl_align <= 32) {
+		 * Memory Controller which is never good.
+		 */
+
+		/* We want the Packing Boundary to be based on the Cache Line
+		 * Size in order to help avoid False Sharing performance
+		 * issues between CPUs, etc.  We also want the Packing
+		 * Boundary to incorporate the PCI-E Maximum Payload Size.  We
+		 * get best performance when the Packing Boundary is a
+		 * multiple of the Maximum Payload Size.
+		 */
+		pack_align = fl_align;
+		pcie_cap = pci_find_capability(adap->pdev, PCI_CAP_ID_EXP);
+		if (pcie_cap) {
+			unsigned int mps, mps_log;
+			u16 devctl;
+
+			/* The PCIe Device Control Maximum Payload Size field
+			 * [bits 7:5] encodes sizes as powers of 2 starting at
+			 * 128 bytes.
+			 */
+			pci_read_config_word(adap->pdev,
+					     pcie_cap + PCI_EXP_DEVCTL,
+					     &devctl);
+			mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
+			mps = 1 << mps_log;
+			if (mps > pack_align)
+				pack_align = mps;
+		}
+
+		/* N.B. T5/T6 have a crazy special interpretation of the "0"
+		 * value for the Packing Boundary.  This corresponds to 16
+		 * bytes instead of the expected 32 bytes.  So if we want 32
+		 * bytes, the best we can really do is 64 bytes ...
+		 */
+		if (pack_align <= 16) {
+			ingpack = INGPACKBOUNDARY_16B_X;
+			fl_align = 16;
+		} else if (pack_align == 32) {
+			ingpack = INGPACKBOUNDARY_64B_X;
 			fl_align = 64;
-			fl_align_log = 6;
+		} else {
+			unsigned int pack_align_log = fls(pack_align) - 1;
+
+			ingpack = pack_align_log - INGPACKBOUNDARY_SHIFT_X;
+			fl_align = pack_align;
 		}
 
+		/* Use the smallest Ingress Padding which isn't smaller than
+		 * the Memory Controller Read/Write Size.  We'll take that as
+		 * being 8 bytes since we don't know of any system with a
+		 * wider Memory Controller Bus Width.
+		 */
 		if (is_t5(adap->params.chip))
-			ingpad = INGPCIEBOUNDARY_32B_X;
+			ingpad = INGPADBOUNDARY_32B_X;
 		else
-			ingpad = T6_INGPADBOUNDARY_32B_X;
+			ingpad = T6_INGPADBOUNDARY_8B_X;
 
 		t4_set_reg_field(adap, SGE_CONTROL_A,
 				 INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
@@ -6430,8 +6468,7 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 				 EGRSTATUSPAGESIZE_V(stat_len != 64));
 		t4_set_reg_field(adap, SGE_CONTROL2_A,
 				 INGPACKBOUNDARY_V(INGPACKBOUNDARY_M),
-				 INGPACKBOUNDARY_V(fl_align_log -
-						   INGPACKBOUNDARY_SHIFT_X));
+				 INGPACKBOUNDARY_V(ingpack));
 	}
 	/*
 	 * Adjust various SGE Free List Host Buffer Sizes.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
index 36cf3073ca37..f6558cbfc54e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
@@ -54,11 +54,15 @@
 #define INGPADBOUNDARY_SHIFT_X		5
 
 #define T6_INGPADBOUNDARY_SHIFT_X	3
+#define T6_INGPADBOUNDARY_8B_X		0
 #define T6_INGPADBOUNDARY_32B_X		2
 
+#define INGPADBOUNDARY_32B_X		0
+
 /* CONTROL2 register */
 #define INGPACKBOUNDARY_SHIFT_X		5
 #define INGPACKBOUNDARY_16B_X		0
+#define INGPACKBOUNDARY_64B_X		1
 
 /* GTS register */
 #define SGE_TIMERREGS			6
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index ccc05f874419..8f8c079d0d2b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1167,7 +1167,8 @@ enum fw_params_param_pfvf {
 	FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_START = 0x2D,
 	FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_END = 0x2E,
 	FW_PARAMS_PARAM_PFVF_ETHOFLD_END = 0x30,
-	FW_PARAMS_PARAM_PFVF_CPLFW4MSG_ENCAP = 0x31
+	FW_PARAMS_PARAM_PFVF_CPLFW4MSG_ENCAP = 0x31,
+	FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x32
 };
 
 /*
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 3647b28e8de0..47384f7323ac 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -1896,7 +1896,7 @@ static int cs89x0_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct __maybe_unused of_device_id cs89x0_match[] = {
+static const struct of_device_id __maybe_unused cs89x0_match[] = {
 	{ .compatible = "cirrus,cs8900", },
 	{ .compatible = "cirrus,cs8920", },
 	{ },
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 127ce9707378..91b8f6f5a765 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -312,8 +312,6 @@ struct de_private {
 
 	u32			msg_enable;
 
-	struct net_device_stats net_stats;
-
 	struct pci_dev		*pdev;
 
 	u16			setup_frame[DE_SETUP_FRAME_WORDS];
@@ -388,14 +386,14 @@ static void de_rx_err_acct (struct de_private *de, unsigned rx_tail,
 			netif_warn(de, rx_err, de->dev,
 				   "Oversized Ethernet frame spanned multiple buffers, status %08x!\n",
 				   status);
-			de->net_stats.rx_length_errors++;
+			de->dev->stats.rx_length_errors++;
 		}
 	} else if (status & RxError) {
 		/* There was a fatal error. */
-		de->net_stats.rx_errors++; /* end of a packet.*/
-		if (status & 0x0890) de->net_stats.rx_length_errors++;
-		if (status & RxErrCRC) de->net_stats.rx_crc_errors++;
-		if (status & RxErrFIFO) de->net_stats.rx_fifo_errors++;
+		de->dev->stats.rx_errors++; /* end of a packet.*/
+		if (status & 0x0890) de->dev->stats.rx_length_errors++;
+		if (status & RxErrCRC) de->dev->stats.rx_crc_errors++;
+		if (status & RxErrFIFO) de->dev->stats.rx_fifo_errors++;
 	}
 }
 
@@ -423,7 +421,7 @@ static void de_rx (struct de_private *de)
 		mapping = de->rx_skb[rx_tail].mapping;
 
 		if (unlikely(drop)) {
-			de->net_stats.rx_dropped++;
+			de->dev->stats.rx_dropped++;
 			goto rx_next;
 		}
 
@@ -441,7 +439,7 @@ static void de_rx (struct de_private *de)
 		buflen = copying_skb ? (len + RX_OFFSET) : de->rx_buf_sz;
 		copy_skb = netdev_alloc_skb(de->dev, buflen);
 		if (unlikely(!copy_skb)) {
-			de->net_stats.rx_dropped++;
+			de->dev->stats.rx_dropped++;
 			drop = 1;
 			rx_work = 100;
 			goto rx_next;
@@ -470,8 +468,8 @@ static void de_rx (struct de_private *de)
 
 		skb->protocol = eth_type_trans (skb, de->dev);
 
-		de->net_stats.rx_packets++;
-		de->net_stats.rx_bytes += skb->len;
+		de->dev->stats.rx_packets++;
+		de->dev->stats.rx_bytes += skb->len;
 		rc = netif_rx (skb);
 		if (rc == NET_RX_DROP)
 			drop = 1;
@@ -572,18 +570,18 @@ static void de_tx (struct de_private *de)
 				netif_dbg(de, tx_err, de->dev,
 					  "tx err, status 0x%x\n",
 					  status);
-				de->net_stats.tx_errors++;
+				de->dev->stats.tx_errors++;
 				if (status & TxOWC)
-					de->net_stats.tx_window_errors++;
+					de->dev->stats.tx_window_errors++;
 				if (status & TxMaxCol)
-					de->net_stats.tx_aborted_errors++;
+					de->dev->stats.tx_aborted_errors++;
 				if (status & TxLinkFail)
-					de->net_stats.tx_carrier_errors++;
+					de->dev->stats.tx_carrier_errors++;
 				if (status & TxFIFOUnder)
-					de->net_stats.tx_fifo_errors++;
+					de->dev->stats.tx_fifo_errors++;
 			} else {
-				de->net_stats.tx_packets++;
-				de->net_stats.tx_bytes += skb->len;
+				de->dev->stats.tx_packets++;
+				de->dev->stats.tx_bytes += skb->len;
 				netif_dbg(de, tx_done, de->dev,
 					  "tx done, slot %d\n", tx_tail);
 			}
@@ -814,9 +812,9 @@ static void de_set_rx_mode (struct net_device *dev)
 static inline void de_rx_missed(struct de_private *de, u32 rx_missed)
 {
 	if (unlikely(rx_missed & RxMissedOver))
-		de->net_stats.rx_missed_errors += RxMissedMask;
+		de->dev->stats.rx_missed_errors += RxMissedMask;
 	else
-		de->net_stats.rx_missed_errors += (rx_missed & RxMissedMask);
+		de->dev->stats.rx_missed_errors += (rx_missed & RxMissedMask);
 }
 
 static void __de_get_stats(struct de_private *de)
@@ -836,7 +834,7 @@ static struct net_device_stats *de_get_stats(struct net_device *dev)
  		__de_get_stats(de);
 	spin_unlock_irq(&de->lock);
 
-	return &de->net_stats;
+	return &dev->stats;
 }
 
 static inline int de_is_running (struct de_private *de)
@@ -1348,7 +1346,7 @@ static void de_clean_rings (struct de_private *de)
 		struct sk_buff *skb = de->tx_skb[i].skb;
 		if ((skb) && (skb != DE_DUMMY_SKB)) {
 			if (skb != DE_SETUP_SKB) {
-				de->net_stats.tx_dropped++;
+				de->dev->stats.tx_dropped++;
 				pci_unmap_single(de->pdev,
 					de->tx_skb[i].mapping,
 					skb->len, PCI_DMA_TODEVICE);
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 1e350135f11d..778f974e2928 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -878,10 +878,10 @@ tx_error (struct net_device *dev, int tx_status)
 	frame_id = (tx_status & 0xffff0000);
 	printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n",
 		dev->name, tx_status, frame_id);
-	np->stats.tx_errors++;
+	dev->stats.tx_errors++;
 	/* Ttransmit Underrun */
 	if (tx_status & 0x10) {
-		np->stats.tx_fifo_errors++;
+		dev->stats.tx_fifo_errors++;
 		dw16(TxStartThresh, dr16(TxStartThresh) + 0x10);
 		/* Transmit Underrun need to set TxReset, DMARest, FIFOReset */
 		dw16(ASICCtrl + 2,
@@ -903,7 +903,7 @@ tx_error (struct net_device *dev, int tx_status)
 	}
 	/* Late Collision */
 	if (tx_status & 0x04) {
-		np->stats.tx_fifo_errors++;
+		dev->stats.tx_fifo_errors++;
 		/* TxReset and clear FIFO */
 		dw16(ASICCtrl + 2, TxReset | FIFOReset);
 		/* Wait reset done */
@@ -916,13 +916,8 @@ tx_error (struct net_device *dev, int tx_status)
 		/* Let TxStartThresh stay default value */
 	}
 	/* Maximum Collisions */
-#ifdef ETHER_STATS
 	if (tx_status & 0x08)
-		np->stats.collisions16++;
-#else
-	if (tx_status & 0x08)
-		np->stats.collisions++;
-#endif
+		dev->stats.collisions++;
 	/* Restart the Tx */
 	dw32(MACCtrl, dr16(MACCtrl) | TxEnable);
 }
@@ -952,15 +947,15 @@ receive_packet (struct net_device *dev)
 			break;
 		/* Update rx error statistics, drop packet. */
 		if (frame_status & RFS_Errors) {
-			np->stats.rx_errors++;
+			dev->stats.rx_errors++;
 			if (frame_status & (RxRuntFrame | RxLengthError))
-				np->stats.rx_length_errors++;
+				dev->stats.rx_length_errors++;
 			if (frame_status & RxFCSError)
-				np->stats.rx_crc_errors++;
+				dev->stats.rx_crc_errors++;
 			if (frame_status & RxAlignmentError && np->speed != 1000)
-				np->stats.rx_frame_errors++;
+				dev->stats.rx_frame_errors++;
 			if (frame_status & RxFIFOOverrun)
-	 			np->stats.rx_fifo_errors++;
+				dev->stats.rx_fifo_errors++;
 		} else {
 			struct sk_buff *skb;
 
@@ -1096,23 +1091,23 @@ get_stats (struct net_device *dev)
 	/* All statistics registers need to be acknowledged,
 	   else statistic overflow could cause problems */
 
-	np->stats.rx_packets += dr32(FramesRcvOk);
-	np->stats.tx_packets += dr32(FramesXmtOk);
-	np->stats.rx_bytes += dr32(OctetRcvOk);
-	np->stats.tx_bytes += dr32(OctetXmtOk);
+	dev->stats.rx_packets += dr32(FramesRcvOk);
+	dev->stats.tx_packets += dr32(FramesXmtOk);
+	dev->stats.rx_bytes += dr32(OctetRcvOk);
+	dev->stats.tx_bytes += dr32(OctetXmtOk);
 
-	np->stats.multicast = dr32(McstFramesRcvdOk);
-	np->stats.collisions += dr32(SingleColFrames)
+	dev->stats.multicast = dr32(McstFramesRcvdOk);
+	dev->stats.collisions += dr32(SingleColFrames)
 			     +  dr32(MultiColFrames);
 
 	/* detailed tx errors */
 	stat_reg = dr16(FramesAbortXSColls);
-	np->stats.tx_aborted_errors += stat_reg;
-	np->stats.tx_errors += stat_reg;
+	dev->stats.tx_aborted_errors += stat_reg;
+	dev->stats.tx_errors += stat_reg;
 
 	stat_reg = dr16(CarrierSenseErrors);
-	np->stats.tx_carrier_errors += stat_reg;
-	np->stats.tx_errors += stat_reg;
+	dev->stats.tx_carrier_errors += stat_reg;
+	dev->stats.tx_errors += stat_reg;
 
 	/* Clear all other statistic register. */
 	dr32(McstOctetXmtOk);
@@ -1142,7 +1137,7 @@ get_stats (struct net_device *dev)
 	dr16(TCPCheckSumErrors);
 	dr16(UDPCheckSumErrors);
 	dr16(IPCheckSumErrors);
-	return &np->stats;
+	return &dev->stats;
 }
 
 static int
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 5d8ae5320242..10e98ba33ebf 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -377,7 +377,6 @@ struct netdev_private {
 	void __iomem *eeprom_addr;
 	spinlock_t tx_lock;
 	spinlock_t rx_lock;
-	struct net_device_stats stats;
 	unsigned int rx_buf_sz;		/* Based on MTU+slack. */
 	unsigned int speed;		/* Operating speed */
 	unsigned int vlan;		/* VLAN Id */
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index d49528ad7821..50566243e6fa 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -567,6 +567,12 @@ struct be_error_recovery {
 /* Ethtool priv_flags */
 #define	BE_DISABLE_TPE_RECOVERY	0x1
 
+struct be_vxlan_port {
+	struct list_head list;
+	__be16 port;		/* VxLAN UDP dst port */
+	int port_aliases;	/* alias count */
+};
+
 struct be_adapter {
 	struct pci_dev *pdev;
 	struct net_device *netdev;
@@ -671,9 +677,9 @@ struct be_adapter {
 	u32 sli_family;
 	u8 hba_port_num;
 	u16 pvid;
-	__be16 vxlan_port;
-	int vxlan_port_count;
-	int vxlan_port_aliases;
+	__be16 vxlan_port;		/* offloaded vxlan port num */
+	int vxlan_port_count;		/* active vxlan port count */
+	struct list_head vxlan_port_list;	/* vxlan port list */
 	struct phy_info phy;
 	u8 wol_cap;
 	bool wol_en;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 30e855004c57..02dd5246dfae 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -4939,8 +4939,9 @@ static int
 __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 				 int link_state, int version, u8 domain)
 {
-	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_set_ll_link *req;
+	struct be_mcc_wrb *wrb;
+	u32 link_config = 0;
 	int status;
 
 	mutex_lock(&adapter->mcc_lock);
@@ -4962,10 +4963,12 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 
 	if (link_state == IFLA_VF_LINK_STATE_ENABLE ||
 	    link_state == IFLA_VF_LINK_STATE_AUTO)
-		req->link_config |= PLINK_ENABLE;
+		link_config |= PLINK_ENABLE;
 
 	if (link_state == IFLA_VF_LINK_STATE_AUTO)
-		req->link_config |= PLINK_TRACK;
+		link_config |= PLINK_TRACK;
+
+	req->link_config = cpu_to_le32(link_config);
 
 	status = be_mcc_notify_wait(adapter);
 err:
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 6be3b9aba8ed..f3a09ab55900 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3857,6 +3857,44 @@ static void be_cancel_err_detection(struct be_adapter *adapter)
 	}
 }
 
+static int be_enable_vxlan_offloads(struct be_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct device *dev = &adapter->pdev->dev;
+	struct be_vxlan_port *vxlan_port;
+	__be16 port;
+	int status;
+
+	vxlan_port = list_first_entry(&adapter->vxlan_port_list,
+				      struct be_vxlan_port, list);
+	port = vxlan_port->port;
+
+	status = be_cmd_manage_iface(adapter, adapter->if_handle,
+				     OP_CONVERT_NORMAL_TO_TUNNEL);
+	if (status) {
+		dev_warn(dev, "Failed to convert normal interface to tunnel\n");
+		return status;
+	}
+	adapter->flags |= BE_FLAGS_VXLAN_OFFLOADS;
+
+	status = be_cmd_set_vxlan_port(adapter, port);
+	if (status) {
+		dev_warn(dev, "Failed to add VxLAN port\n");
+		return status;
+	}
+	adapter->vxlan_port = port;
+
+	netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+				   NETIF_F_TSO | NETIF_F_TSO6 |
+				   NETIF_F_GSO_UDP_TUNNEL;
+	netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+	netdev->features |= NETIF_F_GSO_UDP_TUNNEL;
+
+	dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n",
+		 be16_to_cpu(port));
+	return 0;
+}
+
 static void be_disable_vxlan_offloads(struct be_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -4903,63 +4941,59 @@ static struct be_cmd_work *be_alloc_work(struct be_adapter *adapter,
  * those other tunnels are unexported on the fly through ndo_features_check().
  *
  * Skyhawk supports VxLAN offloads only for one UDP dport. So, if the stack
- * adds more than one port, disable offloads and don't re-enable them again
- * until after all the tunnels are removed.
+ * adds more than one port, disable offloads and re-enable them again when
+ * there's only one port left. We maintain a list of ports for this purpose.
  */
 static void be_work_add_vxlan_port(struct work_struct *work)
 {
 	struct be_cmd_work *cmd_work =
 				container_of(work, struct be_cmd_work, work);
 	struct be_adapter *adapter = cmd_work->adapter;
-	struct net_device *netdev = adapter->netdev;
 	struct device *dev = &adapter->pdev->dev;
 	__be16 port = cmd_work->info.vxlan_port;
+	struct be_vxlan_port *vxlan_port;
 	int status;
 
-	if (adapter->vxlan_port == port && adapter->vxlan_port_count) {
-		adapter->vxlan_port_aliases++;
-		goto done;
+	/* Bump up the alias count if it is an existing port */
+	list_for_each_entry(vxlan_port, &adapter->vxlan_port_list, list) {
+		if (vxlan_port->port == port) {
+			vxlan_port->port_aliases++;
+			goto done;
+		}
 	}
 
+	/* Add a new port to our list. We don't need a lock here since port
+	 * add/delete are done only in the context of a single-threaded work
+	 * queue (be_wq).
+	 */
+	vxlan_port = kzalloc(sizeof(*vxlan_port), GFP_KERNEL);
+	if (!vxlan_port)
+		goto done;
+
+	vxlan_port->port = port;
+	INIT_LIST_HEAD(&vxlan_port->list);
+	list_add_tail(&vxlan_port->list, &adapter->vxlan_port_list);
+	adapter->vxlan_port_count++;
+
 	if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) {
 		dev_info(dev,
 			 "Only one UDP port supported for VxLAN offloads\n");
 		dev_info(dev, "Disabling VxLAN offloads\n");
-		adapter->vxlan_port_count++;
 		goto err;
 	}
 
-	if (adapter->vxlan_port_count++ >= 1)
+	if (adapter->vxlan_port_count > 1)
 		goto done;
 
-	status = be_cmd_manage_iface(adapter, adapter->if_handle,
-				     OP_CONVERT_NORMAL_TO_TUNNEL);
-	if (status) {
-		dev_warn(dev, "Failed to convert normal interface to tunnel\n");
-		goto err;
-	}
-
-	status = be_cmd_set_vxlan_port(adapter, port);
-	if (status) {
-		dev_warn(dev, "Failed to add VxLAN port\n");
-		goto err;
-	}
-	adapter->flags |= BE_FLAGS_VXLAN_OFFLOADS;
-	adapter->vxlan_port = port;
-
-	netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-				   NETIF_F_TSO | NETIF_F_TSO6 |
-				   NETIF_F_GSO_UDP_TUNNEL;
-	netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
-	netdev->features |= NETIF_F_GSO_UDP_TUNNEL;
+	status = be_enable_vxlan_offloads(adapter);
+	if (!status)
+		goto done;
 
-	dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n",
-		 be16_to_cpu(port));
-	goto done;
 err:
 	be_disable_vxlan_offloads(adapter);
 done:
 	kfree(cmd_work);
+	return;
 }
 
 static void be_work_del_vxlan_port(struct work_struct *work)
@@ -4968,23 +5002,40 @@ static void be_work_del_vxlan_port(struct work_struct *work)
 				container_of(work, struct be_cmd_work, work);
 	struct be_adapter *adapter = cmd_work->adapter;
 	__be16 port = cmd_work->info.vxlan_port;
+	struct be_vxlan_port *vxlan_port;
 
-	if (adapter->vxlan_port != port)
-		goto done;
+	/* Nothing to be done if a port alias is being deleted */
+	list_for_each_entry(vxlan_port, &adapter->vxlan_port_list, list) {
+		if (vxlan_port->port == port) {
+			if (vxlan_port->port_aliases) {
+				vxlan_port->port_aliases--;
+				goto done;
+			}
+			break;
+		}
+	}
+
+	/* No port aliases left; delete the port from the list */
+	list_del(&vxlan_port->list);
+	adapter->vxlan_port_count--;
 
-	if (adapter->vxlan_port_aliases) {
-		adapter->vxlan_port_aliases--;
+	/* Disable VxLAN offload if this is the offloaded port */
+	if (adapter->vxlan_port == vxlan_port->port) {
+		WARN_ON(adapter->vxlan_port_count);
+		be_disable_vxlan_offloads(adapter);
+		dev_info(&adapter->pdev->dev,
+			 "Disabled VxLAN offloads for UDP port %d\n",
+			 be16_to_cpu(port));
 		goto out;
 	}
 
-	be_disable_vxlan_offloads(adapter);
+	/* If only 1 port is left, re-enable VxLAN offload */
+	if (adapter->vxlan_port_count == 1)
+		be_enable_vxlan_offloads(adapter);
 
-	dev_info(&adapter->pdev->dev,
-		 "Disabled VxLAN offloads for UDP port %d\n",
-		 be16_to_cpu(port));
-done:
-	adapter->vxlan_port_count--;
 out:
+	kfree(vxlan_port);
+done:
 	kfree(cmd_work);
 }
 
@@ -5217,15 +5268,15 @@ static bool be_err_is_recoverable(struct be_adapter *adapter)
 	dev_err(&adapter->pdev->dev, "Recoverable HW error code: 0x%x\n",
 		ue_err_code);
 
-	if (jiffies - err_rec->probe_time <= initial_idle_time) {
+	if (time_before_eq(jiffies - err_rec->probe_time, initial_idle_time)) {
 		dev_err(&adapter->pdev->dev,
 			"Cannot recover within %lu sec from driver load\n",
 			jiffies_to_msecs(initial_idle_time) / MSEC_PER_SEC);
 		return false;
 	}
 
-	if (err_rec->last_recovery_time &&
-	    (jiffies - err_rec->last_recovery_time <= recovery_interval)) {
+	if (err_rec->last_recovery_time && time_before_eq(
+		jiffies - err_rec->last_recovery_time, recovery_interval)) {
 		dev_err(&adapter->pdev->dev,
 			"Cannot recover within %lu sec from last recovery\n",
 			jiffies_to_msecs(recovery_interval) / MSEC_PER_SEC);
@@ -5626,6 +5677,7 @@ static int be_drv_init(struct be_adapter *adapter)
 	/* Must be a power of 2 or else MODULO will BUG_ON */
 	adapter->be_get_temp_freq = 64;
 
+	INIT_LIST_HEAD(&adapter->vxlan_port_list);
 	return 0;
 
 free_rx_filter:
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 23d82748f52b..e863ba74d005 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1148,14 +1148,14 @@ static int ethoc_probe(struct platform_device *pdev)
 
 	/* Allow the platform setup code to pass in a MAC address. */
 	if (pdata) {
-		memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN);
+		ether_addr_copy(netdev->dev_addr, pdata->hwaddr);
 		priv->phy_id = pdata->phy_id;
 	} else {
 		const void *mac;
 
 		mac = of_get_mac_address(pdev->dev.of_node);
 		if (mac)
-			memcpy(netdev->dev_addr, mac, IFHWADDRLEN);
+			ether_addr_copy(netdev->dev_addr, mac);
 		priv->phy_id = -1;
 	}
 
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 992ebe973d25..659f1ad37e96 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -16,6 +16,7 @@
 
 #include <linux/module.h>
 #include <linux/etherdevice.h>
+#include <linux/interrupt.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_net.h>
@@ -189,11 +190,9 @@ static int nps_enet_poll(struct napi_struct *napi, int budget)
 
 	nps_enet_tx_handler(ndev);
 	work_done = nps_enet_rx_handler(ndev);
-	if (work_done < budget) {
+	if ((work_done < budget) && napi_complete_done(napi, work_done)) {
 		u32 buf_int_enable_value = 0;
 
-		napi_complete_done(napi, work_done);
-
 		/* set tx_done and rx_rdy bits */
 		buf_int_enable_value |= NPS_ENET_ENABLE << RX_RDY_SHIFT;
 		buf_int_enable_value |= NPS_ENET_ENABLE << TX_DONE_SHIFT;
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 928b0df2b8e0..95bf5e89cfd1 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -28,8 +28,13 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/crc32.h>
+#include <linux/if_vlan.h>
+#include <linux/of_net.h>
 #include <net/ip.h>
 #include <net/ncsi.h>
 
@@ -38,103 +43,137 @@
 #define DRV_NAME	"ftgmac100"
 #define DRV_VERSION	"0.7"
 
-#define RX_QUEUE_ENTRIES	256	/* must be power of 2 */
-#define TX_QUEUE_ENTRIES	512	/* must be power of 2 */
+/* Arbitrary values, I am not sure the HW has limits */
+#define MAX_RX_QUEUE_ENTRIES	1024
+#define MAX_TX_QUEUE_ENTRIES	1024
+#define MIN_RX_QUEUE_ENTRIES	32
+#define MIN_TX_QUEUE_ENTRIES	32
 
-#define MAX_PKT_SIZE		1518
-#define RX_BUF_SIZE		PAGE_SIZE	/* must be smaller than 0x3fff */
+/* Defaults */
+#define DEF_RX_QUEUE_ENTRIES	128
+#define DEF_TX_QUEUE_ENTRIES	128
 
-/******************************************************************************
- * private data
- *****************************************************************************/
-struct ftgmac100_descs {
-	struct ftgmac100_rxdes rxdes[RX_QUEUE_ENTRIES];
-	struct ftgmac100_txdes txdes[TX_QUEUE_ENTRIES];
-};
+#define MAX_PKT_SIZE		1536
+#define RX_BUF_SIZE		MAX_PKT_SIZE	/* must be smaller than 0x3fff */
+
+/* Min number of tx ring entries before stopping queue */
+#define TX_THRESHOLD		(MAX_SKB_FRAGS + 1)
 
 struct ftgmac100 {
+	/* Registers */
 	struct resource *res;
 	void __iomem *base;
-	int irq;
-
-	struct ftgmac100_descs *descs;
-	dma_addr_t descs_dma_addr;
-
-	struct page *rx_pages[RX_QUEUE_ENTRIES];
 
+	/* Rx ring */
+	unsigned int rx_q_entries;
+	struct ftgmac100_rxdes *rxdes;
+	dma_addr_t rxdes_dma;
+	struct sk_buff **rx_skbs;
 	unsigned int rx_pointer;
+	u32 rxdes0_edorr_mask;
+
+	/* Tx ring */
+	unsigned int tx_q_entries;
+	struct ftgmac100_txdes *txdes;
+	dma_addr_t txdes_dma;
+	struct sk_buff **tx_skbs;
 	unsigned int tx_clean_pointer;
 	unsigned int tx_pointer;
-	unsigned int tx_pending;
+	u32 txdes0_edotr_mask;
+
+	/* Used to signal the reset task of ring change request */
+	unsigned int new_rx_q_entries;
+	unsigned int new_tx_q_entries;
 
-	spinlock_t tx_lock;
+	/* Scratch page to use when rx skb alloc fails */
+	void *rx_scratch;
+	dma_addr_t rx_scratch_dma;
 
+	/* Component structures */
 	struct net_device *netdev;
 	struct device *dev;
 	struct ncsi_dev *ndev;
 	struct napi_struct napi;
-
+	struct work_struct reset_task;
 	struct mii_bus *mii_bus;
-	int old_speed;
-	int int_mask_all;
-	bool use_ncsi;
-	bool enabled;
-
-	u32 rxdes0_edorr_mask;
-	u32 txdes0_edotr_mask;
-};
 
-static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv,
-				   struct ftgmac100_rxdes *rxdes, gfp_t gfp);
-
-/******************************************************************************
- * internal functions (hardware register access)
- *****************************************************************************/
-static void ftgmac100_set_rx_ring_base(struct ftgmac100 *priv, dma_addr_t addr)
-{
-	iowrite32(addr, priv->base + FTGMAC100_OFFSET_RXR_BADR);
-}
+	/* Link management */
+	int cur_speed;
+	int cur_duplex;
+	bool use_ncsi;
 
-static void ftgmac100_set_rx_buffer_size(struct ftgmac100 *priv,
-		unsigned int size)
-{
-	size = FTGMAC100_RBSR_SIZE(size);
-	iowrite32(size, priv->base + FTGMAC100_OFFSET_RBSR);
-}
+	/* Multicast filter settings */
+	u32 maht0;
+	u32 maht1;
 
-static void ftgmac100_set_normal_prio_tx_ring_base(struct ftgmac100 *priv,
-						   dma_addr_t addr)
-{
-	iowrite32(addr, priv->base + FTGMAC100_OFFSET_NPTXR_BADR);
-}
+	/* Flow control settings */
+	bool tx_pause;
+	bool rx_pause;
+	bool aneg_pause;
 
-static void ftgmac100_txdma_normal_prio_start_polling(struct ftgmac100 *priv)
-{
-	iowrite32(1, priv->base + FTGMAC100_OFFSET_NPTXPD);
-}
+	/* Misc */
+	bool need_mac_restart;
+	bool is_aspeed;
+};
 
-static int ftgmac100_reset_hw(struct ftgmac100 *priv)
+static int ftgmac100_reset_mac(struct ftgmac100 *priv, u32 maccr)
 {
 	struct net_device *netdev = priv->netdev;
 	int i;
 
 	/* NOTE: reset clears all registers */
-	iowrite32(FTGMAC100_MACCR_SW_RST, priv->base + FTGMAC100_OFFSET_MACCR);
-	for (i = 0; i < 5; i++) {
+	iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
+	iowrite32(maccr | FTGMAC100_MACCR_SW_RST,
+		  priv->base + FTGMAC100_OFFSET_MACCR);
+	for (i = 0; i < 50; i++) {
 		unsigned int maccr;
 
 		maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR);
 		if (!(maccr & FTGMAC100_MACCR_SW_RST))
 			return 0;
 
-		udelay(1000);
+		udelay(1);
 	}
 
-	netdev_err(netdev, "software reset failed\n");
+	netdev_err(netdev, "Hardware reset failed\n");
 	return -EIO;
 }
 
-static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac)
+static int ftgmac100_reset_and_config_mac(struct ftgmac100 *priv)
+{
+	u32 maccr = 0;
+
+	switch (priv->cur_speed) {
+	case SPEED_10:
+	case 0: /* no link */
+		break;
+
+	case SPEED_100:
+		maccr |= FTGMAC100_MACCR_FAST_MODE;
+		break;
+
+	case SPEED_1000:
+		maccr |= FTGMAC100_MACCR_GIGA_MODE;
+		break;
+	default:
+		netdev_err(priv->netdev, "Unknown speed %d !\n",
+			   priv->cur_speed);
+		break;
+	}
+
+	/* (Re)initialize the queue pointers */
+	priv->rx_pointer = 0;
+	priv->tx_clean_pointer = 0;
+	priv->tx_pointer = 0;
+
+	/* The doc says reset twice with 10us interval */
+	if (ftgmac100_reset_mac(priv, maccr))
+		return -EIO;
+	usleep_range(10, 1000);
+	return ftgmac100_reset_mac(priv, maccr);
+}
+
+static void ftgmac100_write_mac_addr(struct ftgmac100 *priv, const u8 *mac)
 {
 	unsigned int maddr = mac[0] << 8 | mac[1];
 	unsigned int laddr = mac[2] << 24 | mac[3] << 16 | mac[4] << 8 | mac[5];
@@ -143,7 +182,7 @@ static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac)
 	iowrite32(laddr, priv->base + FTGMAC100_OFFSET_MAC_LADR);
 }
 
-static void ftgmac100_setup_mac(struct ftgmac100 *priv)
+static void ftgmac100_initial_mac(struct ftgmac100 *priv)
 {
 	u8 mac[ETH_ALEN];
 	unsigned int m;
@@ -187,716 +226,833 @@ static int ftgmac100_set_mac_addr(struct net_device *dev, void *p)
 		return ret;
 
 	eth_commit_mac_addr_change(dev, p);
-	ftgmac100_set_mac(netdev_priv(dev), dev->dev_addr);
+	ftgmac100_write_mac_addr(netdev_priv(dev), dev->dev_addr);
 
 	return 0;
 }
 
-static void ftgmac100_init_hw(struct ftgmac100 *priv)
-{
-	/* setup ring buffer base registers */
-	ftgmac100_set_rx_ring_base(priv,
-				   priv->descs_dma_addr +
-				   offsetof(struct ftgmac100_descs, rxdes));
-	ftgmac100_set_normal_prio_tx_ring_base(priv,
-					       priv->descs_dma_addr +
-					       offsetof(struct ftgmac100_descs, txdes));
-
-	ftgmac100_set_rx_buffer_size(priv, RX_BUF_SIZE);
-
-	iowrite32(FTGMAC100_APTC_RXPOLL_CNT(1), priv->base + FTGMAC100_OFFSET_APTC);
-
-	ftgmac100_set_mac(priv, priv->netdev->dev_addr);
-}
-
-#define MACCR_ENABLE_ALL	(FTGMAC100_MACCR_TXDMA_EN	| \
-				 FTGMAC100_MACCR_RXDMA_EN	| \
-				 FTGMAC100_MACCR_TXMAC_EN	| \
-				 FTGMAC100_MACCR_RXMAC_EN	| \
-				 FTGMAC100_MACCR_FULLDUP	| \
-				 FTGMAC100_MACCR_CRC_APD	| \
-				 FTGMAC100_MACCR_RX_RUNT	| \
-				 FTGMAC100_MACCR_RX_BROADPKT)
-
-static void ftgmac100_start_hw(struct ftgmac100 *priv, int speed)
+static void ftgmac100_config_pause(struct ftgmac100 *priv)
 {
-	int maccr = MACCR_ENABLE_ALL;
+	u32 fcr = FTGMAC100_FCR_PAUSE_TIME(16);
 
-	switch (speed) {
-	default:
-	case 10:
-		break;
-
-	case 100:
-		maccr |= FTGMAC100_MACCR_FAST_MODE;
-		break;
+	/* Throttle tx queue when receiving pause frames */
+	if (priv->rx_pause)
+		fcr |= FTGMAC100_FCR_FC_EN;
 
-	case 1000:
-		maccr |= FTGMAC100_MACCR_GIGA_MODE;
-		break;
-	}
+	/* Enables sending pause frames when the RX queue is past a
+	 * certain threshold.
+	 */
+	if (priv->tx_pause)
+		fcr |= FTGMAC100_FCR_FCTHR_EN;
 
-	iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
+	iowrite32(fcr, priv->base + FTGMAC100_OFFSET_FCR);
 }
 
-static void ftgmac100_stop_hw(struct ftgmac100 *priv)
+static void ftgmac100_init_hw(struct ftgmac100 *priv)
 {
-	iowrite32(0, priv->base + FTGMAC100_OFFSET_MACCR);
-}
+	u32 reg, rfifo_sz, tfifo_sz;
 
-/******************************************************************************
- * internal functions (receive descriptor)
- *****************************************************************************/
-static bool ftgmac100_rxdes_first_segment(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FRS);
-}
+	/* Clear stale interrupts */
+	reg = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
+	iowrite32(reg, priv->base + FTGMAC100_OFFSET_ISR);
 
-static bool ftgmac100_rxdes_last_segment(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_LRS);
-}
+	/* Setup RX ring buffer base */
+	iowrite32(priv->rxdes_dma, priv->base + FTGMAC100_OFFSET_RXR_BADR);
 
-static bool ftgmac100_rxdes_packet_ready(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY);
-}
+	/* Setup TX ring buffer base */
+	iowrite32(priv->txdes_dma, priv->base + FTGMAC100_OFFSET_NPTXR_BADR);
 
-static void ftgmac100_rxdes_set_dma_own(const struct ftgmac100 *priv,
-					struct ftgmac100_rxdes *rxdes)
-{
-	/* clear status bits */
-	rxdes->rxdes0 &= cpu_to_le32(priv->rxdes0_edorr_mask);
-}
+	/* Configure RX buffer size */
+	iowrite32(FTGMAC100_RBSR_SIZE(RX_BUF_SIZE),
+		  priv->base + FTGMAC100_OFFSET_RBSR);
 
-static bool ftgmac100_rxdes_rx_error(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ERR);
-}
+	/* Set RX descriptor autopoll */
+	iowrite32(FTGMAC100_APTC_RXPOLL_CNT(1),
+		  priv->base + FTGMAC100_OFFSET_APTC);
 
-static bool ftgmac100_rxdes_crc_error(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_CRC_ERR);
-}
+	/* Write MAC address */
+	ftgmac100_write_mac_addr(priv, priv->netdev->dev_addr);
 
-static bool ftgmac100_rxdes_frame_too_long(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FTL);
-}
+	/* Write multicast filter */
+	iowrite32(priv->maht0, priv->base + FTGMAC100_OFFSET_MAHT0);
+	iowrite32(priv->maht1, priv->base + FTGMAC100_OFFSET_MAHT1);
 
-static bool ftgmac100_rxdes_runt(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RUNT);
+	/* Configure descriptor sizes and increase burst sizes according
+	 * to values in Aspeed SDK. The FIFO arbitration is enabled and
+	 * the thresholds set based on the recommended values in the
+	 * AST2400 specification.
+	 */
+	iowrite32(FTGMAC100_DBLAC_RXDES_SIZE(2) |   /* 2*8 bytes RX descs */
+		  FTGMAC100_DBLAC_TXDES_SIZE(2) |   /* 2*8 bytes TX descs */
+		  FTGMAC100_DBLAC_RXBURST_SIZE(3) | /* 512 bytes max RX bursts */
+		  FTGMAC100_DBLAC_TXBURST_SIZE(3) | /* 512 bytes max TX bursts */
+		  FTGMAC100_DBLAC_RX_THR_EN |       /* Enable fifo threshold arb */
+		  FTGMAC100_DBLAC_RXFIFO_HTHR(6) |  /* 6/8 of FIFO high threshold */
+		  FTGMAC100_DBLAC_RXFIFO_LTHR(2),   /* 2/8 of FIFO low threshold */
+		  priv->base + FTGMAC100_OFFSET_DBLAC);
+
+	/* Interrupt mitigation configured for 1 interrupt/packet. HW interrupt
+	 * mitigation doesn't seem to provide any benefit with NAPI so leave
+	 * it at that.
+	 */
+	iowrite32(FTGMAC100_ITC_RXINT_THR(1) |
+		  FTGMAC100_ITC_TXINT_THR(1),
+		  priv->base + FTGMAC100_OFFSET_ITC);
+
+	/* Configure FIFO sizes in the TPAFCR register */
+	reg = ioread32(priv->base + FTGMAC100_OFFSET_FEAR);
+	rfifo_sz = reg & 0x00000007;
+	tfifo_sz = (reg >> 3) & 0x00000007;
+	reg = ioread32(priv->base + FTGMAC100_OFFSET_TPAFCR);
+	reg &= ~0x3f000000;
+	reg |= (tfifo_sz << 27);
+	reg |= (rfifo_sz << 24);
+	iowrite32(reg, priv->base + FTGMAC100_OFFSET_TPAFCR);
+}
+
+static void ftgmac100_start_hw(struct ftgmac100 *priv)
+{
+	u32 maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR);
+
+	/* Keep the original GMAC and FAST bits */
+	maccr &= (FTGMAC100_MACCR_FAST_MODE | FTGMAC100_MACCR_GIGA_MODE);
+
+	/* Add all the main enable bits */
+	maccr |= FTGMAC100_MACCR_TXDMA_EN	|
+		 FTGMAC100_MACCR_RXDMA_EN	|
+		 FTGMAC100_MACCR_TXMAC_EN	|
+		 FTGMAC100_MACCR_RXMAC_EN	|
+		 FTGMAC100_MACCR_CRC_APD	|
+		 FTGMAC100_MACCR_PHY_LINK_LEVEL	|
+		 FTGMAC100_MACCR_RX_RUNT	|
+		 FTGMAC100_MACCR_RX_BROADPKT;
+
+	/* Add other bits as needed */
+	if (priv->cur_duplex == DUPLEX_FULL)
+		maccr |= FTGMAC100_MACCR_FULLDUP;
+	if (priv->netdev->flags & IFF_PROMISC)
+		maccr |= FTGMAC100_MACCR_RX_ALL;
+	if (priv->netdev->flags & IFF_ALLMULTI)
+		maccr |= FTGMAC100_MACCR_RX_MULTIPKT;
+	else if (netdev_mc_count(priv->netdev))
+		maccr |= FTGMAC100_MACCR_HT_MULTI_EN;
+
+	/* Vlan filtering enabled */
+	if (priv->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		maccr |= FTGMAC100_MACCR_RM_VLAN;
+
+	/* Hit the HW */
+	iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
 }
 
-static bool ftgmac100_rxdes_odd_nibble(struct ftgmac100_rxdes *rxdes)
+static void ftgmac100_stop_hw(struct ftgmac100 *priv)
 {
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ODD_NB);
+	iowrite32(0, priv->base + FTGMAC100_OFFSET_MACCR);
 }
 
-static unsigned int ftgmac100_rxdes_data_length(struct ftgmac100_rxdes *rxdes)
+static void ftgmac100_calc_mc_hash(struct ftgmac100 *priv)
 {
-	return le32_to_cpu(rxdes->rxdes0) & FTGMAC100_RXDES0_VDBC;
-}
+	struct netdev_hw_addr *ha;
 
-static bool ftgmac100_rxdes_multicast(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_MULTICAST);
-}
+	priv->maht1 = 0;
+	priv->maht0 = 0;
+	netdev_for_each_mc_addr(ha, priv->netdev) {
+		u32 crc_val = ether_crc_le(ETH_ALEN, ha->addr);
 
-static void ftgmac100_rxdes_set_end_of_ring(const struct ftgmac100 *priv,
-					    struct ftgmac100_rxdes *rxdes)
-{
-	rxdes->rxdes0 |= cpu_to_le32(priv->rxdes0_edorr_mask);
+		crc_val = (~(crc_val >> 2)) & 0x3f;
+		if (crc_val >= 32)
+			priv->maht1 |= 1ul << (crc_val - 32);
+		else
+			priv->maht0 |= 1ul << (crc_val);
+	}
 }
 
-static void ftgmac100_rxdes_set_dma_addr(struct ftgmac100_rxdes *rxdes,
-					 dma_addr_t addr)
+static void ftgmac100_set_rx_mode(struct net_device *netdev)
 {
-	rxdes->rxdes3 = cpu_to_le32(addr);
-}
+	struct ftgmac100 *priv = netdev_priv(netdev);
 
-static dma_addr_t ftgmac100_rxdes_get_dma_addr(struct ftgmac100_rxdes *rxdes)
-{
-	return le32_to_cpu(rxdes->rxdes3);
-}
+	/* Setup the hash filter */
+	ftgmac100_calc_mc_hash(priv);
 
-static bool ftgmac100_rxdes_is_tcp(struct ftgmac100_rxdes *rxdes)
-{
-	return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) ==
-	       cpu_to_le32(FTGMAC100_RXDES1_PROT_TCPIP);
-}
+	/* Interface down ? that's all there is to do */
+	if (!netif_running(netdev))
+		return;
 
-static bool ftgmac100_rxdes_is_udp(struct ftgmac100_rxdes *rxdes)
-{
-	return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) ==
-	       cpu_to_le32(FTGMAC100_RXDES1_PROT_UDPIP);
-}
+	/* Update the HW */
+	iowrite32(priv->maht0, priv->base + FTGMAC100_OFFSET_MAHT0);
+	iowrite32(priv->maht1, priv->base + FTGMAC100_OFFSET_MAHT1);
 
-static bool ftgmac100_rxdes_tcpcs_err(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_TCP_CHKSUM_ERR);
+	/* Reconfigure MACCR */
+	ftgmac100_start_hw(priv);
 }
 
-static bool ftgmac100_rxdes_udpcs_err(struct ftgmac100_rxdes *rxdes)
+static int ftgmac100_alloc_rx_buf(struct ftgmac100 *priv, unsigned int entry,
+				  struct ftgmac100_rxdes *rxdes, gfp_t gfp)
 {
-	return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_UDP_CHKSUM_ERR);
-}
+	struct net_device *netdev = priv->netdev;
+	struct sk_buff *skb;
+	dma_addr_t map;
+	int err;
 
-static bool ftgmac100_rxdes_ipcs_err(struct ftgmac100_rxdes *rxdes)
-{
-	return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_IP_CHKSUM_ERR);
-}
+	skb = netdev_alloc_skb_ip_align(netdev, RX_BUF_SIZE);
+	if (unlikely(!skb)) {
+		if (net_ratelimit())
+			netdev_warn(netdev, "failed to allocate rx skb\n");
+		err = -ENOMEM;
+		map = priv->rx_scratch_dma;
+	} else {
+		map = dma_map_single(priv->dev, skb->data, RX_BUF_SIZE,
+				     DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(priv->dev, map))) {
+			if (net_ratelimit())
+				netdev_err(netdev, "failed to map rx page\n");
+			dev_kfree_skb_any(skb);
+			map = priv->rx_scratch_dma;
+			skb = NULL;
+			err = -ENOMEM;
+		}
+	}
 
-static inline struct page **ftgmac100_rxdes_page_slot(struct ftgmac100 *priv,
-						      struct ftgmac100_rxdes *rxdes)
-{
-	return &priv->rx_pages[rxdes - priv->descs->rxdes];
-}
+	/* Store skb */
+	priv->rx_skbs[entry] = skb;
 
-/*
- * rxdes2 is not used by hardware. We use it to keep track of page.
- * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu().
- */
-static void ftgmac100_rxdes_set_page(struct ftgmac100 *priv,
-				     struct ftgmac100_rxdes *rxdes,
-				     struct page *page)
-{
-	*ftgmac100_rxdes_page_slot(priv, rxdes) = page;
-}
+	/* Store DMA address into RX desc */
+	rxdes->rxdes3 = cpu_to_le32(map);
 
-static struct page *ftgmac100_rxdes_get_page(struct ftgmac100 *priv,
-					     struct ftgmac100_rxdes *rxdes)
-{
-	return *ftgmac100_rxdes_page_slot(priv, rxdes);
-}
+	/* Ensure the above is ordered vs clearing the OWN bit */
+	dma_wmb();
 
-/******************************************************************************
- * internal functions (receive)
- *****************************************************************************/
-static int ftgmac100_next_rx_pointer(int pointer)
-{
-	return (pointer + 1) & (RX_QUEUE_ENTRIES - 1);
-}
+	/* Clean status (which resets own bit) */
+	if (entry == (priv->rx_q_entries - 1))
+		rxdes->rxdes0 = cpu_to_le32(priv->rxdes0_edorr_mask);
+	else
+		rxdes->rxdes0 = 0;
 
-static void ftgmac100_rx_pointer_advance(struct ftgmac100 *priv)
-{
-	priv->rx_pointer = ftgmac100_next_rx_pointer(priv->rx_pointer);
-}
-
-static struct ftgmac100_rxdes *ftgmac100_current_rxdes(struct ftgmac100 *priv)
-{
-	return &priv->descs->rxdes[priv->rx_pointer];
+	return 0;
 }
 
-static struct ftgmac100_rxdes *
-ftgmac100_rx_locate_first_segment(struct ftgmac100 *priv)
+static unsigned int ftgmac100_next_rx_pointer(struct ftgmac100 *priv,
+					      unsigned int pointer)
 {
-	struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv);
-
-	while (ftgmac100_rxdes_packet_ready(rxdes)) {
-		if (ftgmac100_rxdes_first_segment(rxdes))
-			return rxdes;
-
-		ftgmac100_rxdes_set_dma_own(priv, rxdes);
-		ftgmac100_rx_pointer_advance(priv);
-		rxdes = ftgmac100_current_rxdes(priv);
-	}
-
-	return NULL;
+	return (pointer + 1) & (priv->rx_q_entries - 1);
 }
 
-static bool ftgmac100_rx_packet_error(struct ftgmac100 *priv,
-				      struct ftgmac100_rxdes *rxdes)
+static void ftgmac100_rx_packet_error(struct ftgmac100 *priv, u32 status)
 {
 	struct net_device *netdev = priv->netdev;
-	bool error = false;
-
-	if (unlikely(ftgmac100_rxdes_rx_error(rxdes))) {
-		if (net_ratelimit())
-			netdev_info(netdev, "rx err\n");
 
+	if (status & FTGMAC100_RXDES0_RX_ERR)
 		netdev->stats.rx_errors++;
-		error = true;
-	}
-
-	if (unlikely(ftgmac100_rxdes_crc_error(rxdes))) {
-		if (net_ratelimit())
-			netdev_info(netdev, "rx crc err\n");
 
+	if (status & FTGMAC100_RXDES0_CRC_ERR)
 		netdev->stats.rx_crc_errors++;
-		error = true;
-	} else if (unlikely(ftgmac100_rxdes_ipcs_err(rxdes))) {
-		if (net_ratelimit())
-			netdev_info(netdev, "rx IP checksum err\n");
-
-		error = true;
-	}
-
-	if (unlikely(ftgmac100_rxdes_frame_too_long(rxdes))) {
-		if (net_ratelimit())
-			netdev_info(netdev, "rx frame too long\n");
-
-		netdev->stats.rx_length_errors++;
-		error = true;
-	} else if (unlikely(ftgmac100_rxdes_runt(rxdes))) {
-		if (net_ratelimit())
-			netdev_info(netdev, "rx runt\n");
-
-		netdev->stats.rx_length_errors++;
-		error = true;
-	} else if (unlikely(ftgmac100_rxdes_odd_nibble(rxdes))) {
-		if (net_ratelimit())
-			netdev_info(netdev, "rx odd nibble\n");
 
+	if (status & (FTGMAC100_RXDES0_FTL |
+		      FTGMAC100_RXDES0_RUNT |
+		      FTGMAC100_RXDES0_RX_ODD_NB))
 		netdev->stats.rx_length_errors++;
-		error = true;
-	}
-
-	return error;
 }
 
-static void ftgmac100_rx_drop_packet(struct ftgmac100 *priv)
+static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
 {
 	struct net_device *netdev = priv->netdev;
-	struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv);
-	bool done = false;
+	struct ftgmac100_rxdes *rxdes;
+	struct sk_buff *skb;
+	unsigned int pointer, size;
+	u32 status, csum_vlan;
+	dma_addr_t map;
 
-	if (net_ratelimit())
-		netdev_dbg(netdev, "drop packet %p\n", rxdes);
+	/* Grab next RX descriptor */
+	pointer = priv->rx_pointer;
+	rxdes = &priv->rxdes[pointer];
 
-	do {
-		if (ftgmac100_rxdes_last_segment(rxdes))
-			done = true;
+	/* Grab descriptor status */
+	status = le32_to_cpu(rxdes->rxdes0);
 
-		ftgmac100_rxdes_set_dma_own(priv, rxdes);
-		ftgmac100_rx_pointer_advance(priv);
-		rxdes = ftgmac100_current_rxdes(priv);
-	} while (!done && ftgmac100_rxdes_packet_ready(rxdes));
+	/* Do we have a packet ? */
+	if (!(status & FTGMAC100_RXDES0_RXPKT_RDY))
+		return false;
 
-	netdev->stats.rx_dropped++;
-}
+	/* Order subsequent reads with the test for the ready bit */
+	dma_rmb();
 
-static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
-{
-	struct net_device *netdev = priv->netdev;
-	struct ftgmac100_rxdes *rxdes;
-	struct sk_buff *skb;
-	bool done = false;
+	/* We don't cope with fragmented RX packets */
+	if (unlikely(!(status & FTGMAC100_RXDES0_FRS) ||
+		     !(status & FTGMAC100_RXDES0_LRS)))
+		goto drop;
 
-	rxdes = ftgmac100_rx_locate_first_segment(priv);
-	if (!rxdes)
-		return false;
+	/* Grab received size and csum vlan field in the descriptor */
+	size = status & FTGMAC100_RXDES0_VDBC;
+	csum_vlan = le32_to_cpu(rxdes->rxdes1);
 
-	if (unlikely(ftgmac100_rx_packet_error(priv, rxdes))) {
-		ftgmac100_rx_drop_packet(priv);
-		return true;
+	/* Any error (other than csum offload) flagged ? */
+	if (unlikely(status & RXDES0_ANY_ERROR)) {
+		/* Correct for incorrect flagging of runt packets
+		 * with vlan tags... Just accept a runt packet that
+		 * has been flagged as vlan and whose size is at
+		 * least 60 bytes.
+		 */
+		if ((status & FTGMAC100_RXDES0_RUNT) &&
+		    (csum_vlan & FTGMAC100_RXDES1_VLANTAG_AVAIL) &&
+		    (size >= 60))
+			status &= ~FTGMAC100_RXDES0_RUNT;
+
+		/* Any error still in there ? */
+		if (status & RXDES0_ANY_ERROR) {
+			ftgmac100_rx_packet_error(priv, status);
+			goto drop;
+		}
 	}
 
-	/* start processing */
-	skb = netdev_alloc_skb_ip_align(netdev, 128);
-	if (unlikely(!skb)) {
-		if (net_ratelimit())
-			netdev_err(netdev, "rx skb alloc failed\n");
-
-		ftgmac100_rx_drop_packet(priv);
-		return true;
+	/* If the packet had no skb (failed to allocate earlier)
+	 * then try to allocate one and skip
+	 */
+	skb = priv->rx_skbs[pointer];
+	if (!unlikely(skb)) {
+		ftgmac100_alloc_rx_buf(priv, pointer, rxdes, GFP_ATOMIC);
+		goto drop;
 	}
 
-	if (unlikely(ftgmac100_rxdes_multicast(rxdes)))
+	if (unlikely(status & FTGMAC100_RXDES0_MULTICAST))
 		netdev->stats.multicast++;
 
-	/*
-	 * It seems that HW does checksum incorrectly with fragmented packets,
-	 * so we are conservative here - if HW checksum error, let software do
-	 * the checksum again.
+	/* If the HW found checksum errors, bounce it to software.
+	 *
+	 * If we didn't, we need to see if the packet was recognized
+	 * by HW as one of the supported checksummed protocols before
+	 * we accept the HW test results.
 	 */
-	if ((ftgmac100_rxdes_is_tcp(rxdes) && !ftgmac100_rxdes_tcpcs_err(rxdes)) ||
-	    (ftgmac100_rxdes_is_udp(rxdes) && !ftgmac100_rxdes_udpcs_err(rxdes)))
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-
-	do {
-		dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes);
-		struct page *page = ftgmac100_rxdes_get_page(priv, rxdes);
-		unsigned int size;
+	if (netdev->features & NETIF_F_RXCSUM) {
+		u32 err_bits = FTGMAC100_RXDES1_TCP_CHKSUM_ERR |
+			FTGMAC100_RXDES1_UDP_CHKSUM_ERR |
+			FTGMAC100_RXDES1_IP_CHKSUM_ERR;
+		if ((csum_vlan & err_bits) ||
+		    !(csum_vlan & FTGMAC100_RXDES1_PROT_MASK))
+			skb->ip_summed = CHECKSUM_NONE;
+		else
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 
-		dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+	/* Transfer received size to skb */
+	skb_put(skb, size);
 
-		size = ftgmac100_rxdes_data_length(rxdes);
-		skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, page, 0, size);
+	/* Extract vlan tag */
+	if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+	    (csum_vlan & FTGMAC100_RXDES1_VLANTAG_AVAIL))
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       csum_vlan & 0xffff);
 
-		skb->len += size;
-		skb->data_len += size;
-		skb->truesize += PAGE_SIZE;
+	/* Tear down DMA mapping, do necessary cache management */
+	map = le32_to_cpu(rxdes->rxdes3);
 
-		if (ftgmac100_rxdes_last_segment(rxdes))
-			done = true;
+#if defined(CONFIG_ARM) && !defined(CONFIG_ARM_DMA_USE_IOMMU)
+	/* When we don't have an iommu, we can save cycles by not
+	 * invalidating the cache for the part of the packet that
+	 * wasn't received.
+	 */
+	dma_unmap_single(priv->dev, map, size, DMA_FROM_DEVICE);
+#else
+	dma_unmap_single(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+#endif
 
-		ftgmac100_alloc_rx_page(priv, rxdes, GFP_ATOMIC);
 
-		ftgmac100_rx_pointer_advance(priv);
-		rxdes = ftgmac100_current_rxdes(priv);
-	} while (!done);
+	/* Resplenish rx ring */
+	ftgmac100_alloc_rx_buf(priv, pointer, rxdes, GFP_ATOMIC);
+	priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer);
 
-	/* Small frames are copied into linear part of skb to free one page */
-	if (skb->len <= 128) {
-		skb->truesize -= PAGE_SIZE;
-		__pskb_pull_tail(skb, skb->len);
-	} else {
-		/* We pull the minimum amount into linear part */
-		__pskb_pull_tail(skb, ETH_HLEN);
-	}
 	skb->protocol = eth_type_trans(skb, netdev);
 
 	netdev->stats.rx_packets++;
-	netdev->stats.rx_bytes += skb->len;
+	netdev->stats.rx_bytes += size;
 
 	/* push packet to protocol stack */
-	napi_gro_receive(&priv->napi, skb);
+	if (skb->ip_summed == CHECKSUM_NONE)
+		netif_receive_skb(skb);
+	else
+		napi_gro_receive(&priv->napi, skb);
 
 	(*processed)++;
 	return true;
+
+ drop:
+	/* Clean rxdes0 (which resets own bit) */
+	rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask);
+	priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer);
+	netdev->stats.rx_dropped++;
+	return true;
 }
 
-/******************************************************************************
- * internal functions (transmit descriptor)
- *****************************************************************************/
-static void ftgmac100_txdes_reset(const struct ftgmac100 *priv,
-				  struct ftgmac100_txdes *txdes)
+static u32 ftgmac100_base_tx_ctlstat(struct ftgmac100 *priv,
+				     unsigned int index)
 {
-	/* clear all except end of ring bit */
-	txdes->txdes0 &= cpu_to_le32(priv->txdes0_edotr_mask);
-	txdes->txdes1 = 0;
-	txdes->txdes2 = 0;
-	txdes->txdes3 = 0;
+	if (index == (priv->tx_q_entries - 1))
+		return priv->txdes0_edotr_mask;
+	else
+		return 0;
 }
 
-static bool ftgmac100_txdes_owned_by_dma(struct ftgmac100_txdes *txdes)
+static unsigned int ftgmac100_next_tx_pointer(struct ftgmac100 *priv,
+					      unsigned int pointer)
 {
-	return txdes->txdes0 & cpu_to_le32(FTGMAC100_TXDES0_TXDMA_OWN);
+	return (pointer + 1) & (priv->tx_q_entries - 1);
 }
 
-static void ftgmac100_txdes_set_dma_own(struct ftgmac100_txdes *txdes)
+static u32 ftgmac100_tx_buf_avail(struct ftgmac100 *priv)
 {
-	/*
-	 * Make sure dma own bit will not be set before any other
-	 * descriptor fields.
+	/* Returns the number of available slots in the TX queue
+	 *
+	 * This always leaves one free slot so we don't have to
+	 * worry about empty vs. full, and this simplifies the
+	 * test for ftgmac100_tx_buf_cleanable() below
 	 */
-	wmb();
-	txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_TXDMA_OWN);
+	return (priv->tx_clean_pointer - priv->tx_pointer - 1) &
+		(priv->tx_q_entries - 1);
 }
 
-static void ftgmac100_txdes_set_end_of_ring(const struct ftgmac100 *priv,
-					    struct ftgmac100_txdes *txdes)
+static bool ftgmac100_tx_buf_cleanable(struct ftgmac100 *priv)
 {
-	txdes->txdes0 |= cpu_to_le32(priv->txdes0_edotr_mask);
+	return priv->tx_pointer != priv->tx_clean_pointer;
 }
 
-static void ftgmac100_txdes_set_first_segment(struct ftgmac100_txdes *txdes)
+static void ftgmac100_free_tx_packet(struct ftgmac100 *priv,
+				     unsigned int pointer,
+				     struct sk_buff *skb,
+				     struct ftgmac100_txdes *txdes,
+				     u32 ctl_stat)
 {
-	txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_FTS);
-}
+	dma_addr_t map = le32_to_cpu(txdes->txdes3);
+	size_t len;
 
-static void ftgmac100_txdes_set_last_segment(struct ftgmac100_txdes *txdes)
-{
-	txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_LTS);
-}
+	if (ctl_stat & FTGMAC100_TXDES0_FTS) {
+		len = skb_headlen(skb);
+		dma_unmap_single(priv->dev, map, len, DMA_TO_DEVICE);
+	} else {
+		len = FTGMAC100_TXDES0_TXBUF_SIZE(ctl_stat);
+		dma_unmap_page(priv->dev, map, len, DMA_TO_DEVICE);
+	}
 
-static void ftgmac100_txdes_set_buffer_size(struct ftgmac100_txdes *txdes,
-					    unsigned int len)
-{
-	txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_TXBUF_SIZE(len));
+	/* Free SKB on last segment */
+	if (ctl_stat & FTGMAC100_TXDES0_LTS)
+		dev_kfree_skb(skb);
+	priv->tx_skbs[pointer] = NULL;
 }
 
-static void ftgmac100_txdes_set_txint(struct ftgmac100_txdes *txdes)
+static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv)
 {
-	txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_TXIC);
-}
+	struct net_device *netdev = priv->netdev;
+	struct ftgmac100_txdes *txdes;
+	struct sk_buff *skb;
+	unsigned int pointer;
+	u32 ctl_stat;
 
-static void ftgmac100_txdes_set_tcpcs(struct ftgmac100_txdes *txdes)
-{
-	txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_TCP_CHKSUM);
-}
+	pointer = priv->tx_clean_pointer;
+	txdes = &priv->txdes[pointer];
 
-static void ftgmac100_txdes_set_udpcs(struct ftgmac100_txdes *txdes)
-{
-	txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_UDP_CHKSUM);
-}
+	ctl_stat = le32_to_cpu(txdes->txdes0);
+	if (ctl_stat & FTGMAC100_TXDES0_TXDMA_OWN)
+		return false;
 
-static void ftgmac100_txdes_set_ipcs(struct ftgmac100_txdes *txdes)
-{
-	txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_IP_CHKSUM);
-}
+	skb = priv->tx_skbs[pointer];
+	netdev->stats.tx_packets++;
+	netdev->stats.tx_bytes += skb->len;
+	ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat);
+	txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask);
 
-static void ftgmac100_txdes_set_dma_addr(struct ftgmac100_txdes *txdes,
-					 dma_addr_t addr)
-{
-	txdes->txdes3 = cpu_to_le32(addr);
-}
+	priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv, pointer);
 
-static dma_addr_t ftgmac100_txdes_get_dma_addr(struct ftgmac100_txdes *txdes)
-{
-	return le32_to_cpu(txdes->txdes3);
+	return true;
 }
 
-/*
- * txdes2 is not used by hardware. We use it to keep track of socket buffer.
- * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu().
- */
-static void ftgmac100_txdes_set_skb(struct ftgmac100_txdes *txdes,
-				    struct sk_buff *skb)
+static void ftgmac100_tx_complete(struct ftgmac100 *priv)
 {
-	txdes->txdes2 = (unsigned int)skb;
-}
+	struct net_device *netdev = priv->netdev;
 
-static struct sk_buff *ftgmac100_txdes_get_skb(struct ftgmac100_txdes *txdes)
-{
-	return (struct sk_buff *)txdes->txdes2;
-}
+	/* Process all completed packets */
+	while (ftgmac100_tx_buf_cleanable(priv) &&
+	       ftgmac100_tx_complete_packet(priv))
+		;
 
-/******************************************************************************
- * internal functions (transmit)
- *****************************************************************************/
-static int ftgmac100_next_tx_pointer(int pointer)
-{
-	return (pointer + 1) & (TX_QUEUE_ENTRIES - 1);
+	/* Restart queue if needed */
+	smp_mb();
+	if (unlikely(netif_queue_stopped(netdev) &&
+		     ftgmac100_tx_buf_avail(priv) >= TX_THRESHOLD)) {
+		struct netdev_queue *txq;
+
+		txq = netdev_get_tx_queue(netdev, 0);
+		__netif_tx_lock(txq, smp_processor_id());
+		if (netif_queue_stopped(netdev) &&
+		    ftgmac100_tx_buf_avail(priv) >= TX_THRESHOLD)
+			netif_wake_queue(netdev);
+		__netif_tx_unlock(txq);
+	}
 }
 
-static void ftgmac100_tx_pointer_advance(struct ftgmac100 *priv)
+static bool ftgmac100_prep_tx_csum(struct sk_buff *skb, u32 *csum_vlan)
 {
-	priv->tx_pointer = ftgmac100_next_tx_pointer(priv->tx_pointer);
-}
+	if (skb->protocol == cpu_to_be16(ETH_P_IP)) {
+		u8 ip_proto = ip_hdr(skb)->protocol;
 
-static void ftgmac100_tx_clean_pointer_advance(struct ftgmac100 *priv)
-{
-	priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv->tx_clean_pointer);
+		*csum_vlan |= FTGMAC100_TXDES1_IP_CHKSUM;
+		switch(ip_proto) {
+		case IPPROTO_TCP:
+			*csum_vlan |= FTGMAC100_TXDES1_TCP_CHKSUM;
+			return true;
+		case IPPROTO_UDP:
+			*csum_vlan |= FTGMAC100_TXDES1_UDP_CHKSUM;
+			return true;
+		case IPPROTO_IP:
+			return true;
+		}
+	}
+	return skb_checksum_help(skb) == 0;
 }
 
-static struct ftgmac100_txdes *ftgmac100_current_txdes(struct ftgmac100 *priv)
+static int ftgmac100_hard_start_xmit(struct sk_buff *skb,
+				     struct net_device *netdev)
 {
-	return &priv->descs->txdes[priv->tx_pointer];
-}
+	struct ftgmac100 *priv = netdev_priv(netdev);
+	struct ftgmac100_txdes *txdes, *first;
+	unsigned int pointer, nfrags, len, i, j;
+	u32 f_ctl_stat, ctl_stat, csum_vlan;
+	dma_addr_t map;
 
-static struct ftgmac100_txdes *
-ftgmac100_current_clean_txdes(struct ftgmac100 *priv)
-{
-	return &priv->descs->txdes[priv->tx_clean_pointer];
-}
+	/* The HW doesn't pad small frames */
+	if (eth_skb_pad(skb)) {
+		netdev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 
-static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv)
-{
-	struct net_device *netdev = priv->netdev;
-	struct ftgmac100_txdes *txdes;
-	struct sk_buff *skb;
-	dma_addr_t map;
+	/* Reject oversize packets */
+	if (unlikely(skb->len > MAX_PKT_SIZE)) {
+		if (net_ratelimit())
+			netdev_dbg(netdev, "tx packet too big\n");
+		goto drop;
+	}
 
-	if (priv->tx_pending == 0)
-		return false;
+	/* Do we have a limit on #fragments ? I yet have to get a reply
+	 * from Aspeed. If there's one I haven't hit it.
+	 */
+	nfrags = skb_shinfo(skb)->nr_frags;
 
-	txdes = ftgmac100_current_clean_txdes(priv);
+	/* Get header len */
+	len = skb_headlen(skb);
 
-	if (ftgmac100_txdes_owned_by_dma(txdes))
-		return false;
+	/* Map the packet head */
+	map = dma_map_single(priv->dev, skb->data, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(priv->dev, map)) {
+		if (net_ratelimit())
+			netdev_err(netdev, "map tx packet head failed\n");
+		goto drop;
+	}
 
-	skb = ftgmac100_txdes_get_skb(txdes);
-	map = ftgmac100_txdes_get_dma_addr(txdes);
+	/* Grab the next free tx descriptor */
+	pointer = priv->tx_pointer;
+	txdes = first = &priv->txdes[pointer];
 
-	netdev->stats.tx_packets++;
-	netdev->stats.tx_bytes += skb->len;
+	/* Setup it up with the packet head. Don't write the head to the
+	 * ring just yet
+	 */
+	priv->tx_skbs[pointer] = skb;
+	f_ctl_stat = ftgmac100_base_tx_ctlstat(priv, pointer);
+	f_ctl_stat |= FTGMAC100_TXDES0_TXDMA_OWN;
+	f_ctl_stat |= FTGMAC100_TXDES0_TXBUF_SIZE(len);
+	f_ctl_stat |= FTGMAC100_TXDES0_FTS;
+	if (nfrags == 0)
+		f_ctl_stat |= FTGMAC100_TXDES0_LTS;
+	txdes->txdes3 = cpu_to_le32(map);
+
+	/* Setup HW checksumming */
+	csum_vlan = 0;
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
+		goto drop;
+
+	/* Add VLAN tag */
+	if (skb_vlan_tag_present(skb)) {
+		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
+		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
+	}
 
-	dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE);
+	txdes->txdes1 = cpu_to_le32(csum_vlan);
+
+	/* Next descriptor */
+	pointer = ftgmac100_next_tx_pointer(priv, pointer);
+
+	/* Add the fragments */
+	for (i = 0; i < nfrags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		len = frag->size;
+
+		/* Map it */
+		map = skb_frag_dma_map(priv->dev, frag, 0, len,
+				       DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->dev, map))
+			goto dma_err;
+
+		/* Setup descriptor */
+		priv->tx_skbs[pointer] = skb;
+		txdes = &priv->txdes[pointer];
+		ctl_stat = ftgmac100_base_tx_ctlstat(priv, pointer);
+		ctl_stat |= FTGMAC100_TXDES0_TXDMA_OWN;
+		ctl_stat |= FTGMAC100_TXDES0_TXBUF_SIZE(len);
+		if (i == (nfrags - 1))
+			ctl_stat |= FTGMAC100_TXDES0_LTS;
+		txdes->txdes0 = cpu_to_le32(ctl_stat);
+		txdes->txdes1 = 0;
+		txdes->txdes3 = cpu_to_le32(map);
+
+		/* Next one */
+		pointer = ftgmac100_next_tx_pointer(priv, pointer);
+	}
 
-	dev_kfree_skb(skb);
+	/* Order the previous packet and descriptor udpates
+	 * before setting the OWN bit on the first descriptor.
+	 */
+	dma_wmb();
+	first->txdes0 = cpu_to_le32(f_ctl_stat);
 
-	ftgmac100_txdes_reset(priv, txdes);
+	/* Update next TX pointer */
+	priv->tx_pointer = pointer;
 
-	ftgmac100_tx_clean_pointer_advance(priv);
+	/* If there isn't enough room for all the fragments of a new packet
+	 * in the TX ring, stop the queue. The sequence below is race free
+	 * vs. a concurrent restart in ftgmac100_poll()
+	 */
+	if (unlikely(ftgmac100_tx_buf_avail(priv) < TX_THRESHOLD)) {
+		netif_stop_queue(netdev);
+		/* Order the queue stop with the test below */
+		smp_mb();
+		if (ftgmac100_tx_buf_avail(priv) >= TX_THRESHOLD)
+			netif_wake_queue(netdev);
+	}
 
-	spin_lock(&priv->tx_lock);
-	priv->tx_pending--;
-	spin_unlock(&priv->tx_lock);
-	netif_wake_queue(netdev);
+	/* Poke transmitter to read the updated TX descriptors */
+	iowrite32(1, priv->base + FTGMAC100_OFFSET_NPTXPD);
 
-	return true;
-}
+	return NETDEV_TX_OK;
 
-static void ftgmac100_tx_complete(struct ftgmac100 *priv)
-{
-	while (ftgmac100_tx_complete_packet(priv))
-		;
+ dma_err:
+	if (net_ratelimit())
+		netdev_err(netdev, "map tx fragment failed\n");
+
+	/* Free head */
+	pointer = priv->tx_pointer;
+	ftgmac100_free_tx_packet(priv, pointer, skb, first, f_ctl_stat);
+	first->txdes0 = cpu_to_le32(f_ctl_stat & priv->txdes0_edotr_mask);
+
+	/* Then all fragments */
+	for (j = 0; j < i; j++) {
+		pointer = ftgmac100_next_tx_pointer(priv, pointer);
+		txdes = &priv->txdes[pointer];
+		ctl_stat = le32_to_cpu(txdes->txdes0);
+		ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat);
+		txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask);
+	}
+
+	/* This cannot be reached if we successfully mapped the
+	 * last fragment, so we know ftgmac100_free_tx_packet()
+	 * hasn't freed the skb yet.
+	 */
+ drop:
+	/* Drop the packet */
+	dev_kfree_skb_any(skb);
+	netdev->stats.tx_dropped++;
+
+	return NETDEV_TX_OK;
 }
 
-static int ftgmac100_xmit(struct ftgmac100 *priv, struct sk_buff *skb,
-			  dma_addr_t map)
+static void ftgmac100_free_buffers(struct ftgmac100 *priv)
 {
-	struct net_device *netdev = priv->netdev;
-	struct ftgmac100_txdes *txdes;
-	unsigned int len = (skb->len < ETH_ZLEN) ? ETH_ZLEN : skb->len;
-
-	txdes = ftgmac100_current_txdes(priv);
-	ftgmac100_tx_pointer_advance(priv);
-
-	/* setup TX descriptor */
-	ftgmac100_txdes_set_skb(txdes, skb);
-	ftgmac100_txdes_set_dma_addr(txdes, map);
-	ftgmac100_txdes_set_buffer_size(txdes, len);
-
-	ftgmac100_txdes_set_first_segment(txdes);
-	ftgmac100_txdes_set_last_segment(txdes);
-	ftgmac100_txdes_set_txint(txdes);
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		__be16 protocol = skb->protocol;
-
-		if (protocol == cpu_to_be16(ETH_P_IP)) {
-			u8 ip_proto = ip_hdr(skb)->protocol;
-
-			ftgmac100_txdes_set_ipcs(txdes);
-			if (ip_proto == IPPROTO_TCP)
-				ftgmac100_txdes_set_tcpcs(txdes);
-			else if (ip_proto == IPPROTO_UDP)
-				ftgmac100_txdes_set_udpcs(txdes);
-		}
+	int i;
+
+	/* Free all RX buffers */
+	for (i = 0; i < priv->rx_q_entries; i++) {
+		struct ftgmac100_rxdes *rxdes = &priv->rxdes[i];
+		struct sk_buff *skb = priv->rx_skbs[i];
+		dma_addr_t map = le32_to_cpu(rxdes->rxdes3);
+
+		if (!skb)
+			continue;
+
+		priv->rx_skbs[i] = NULL;
+		dma_unmap_single(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
 	}
 
-	spin_lock(&priv->tx_lock);
-	priv->tx_pending++;
-	if (priv->tx_pending == TX_QUEUE_ENTRIES)
-		netif_stop_queue(netdev);
+	/* Free all TX buffers */
+	for (i = 0; i < priv->tx_q_entries; i++) {
+		struct ftgmac100_txdes *txdes = &priv->txdes[i];
+		struct sk_buff *skb = priv->tx_skbs[i];
+
+		if (!skb)
+			continue;
+		ftgmac100_free_tx_packet(priv, i, skb, txdes,
+					 le32_to_cpu(txdes->txdes0));
+	}
+}
 
-	/* start transmit */
-	ftgmac100_txdes_set_dma_own(txdes);
-	spin_unlock(&priv->tx_lock);
+static void ftgmac100_free_rings(struct ftgmac100 *priv)
+{
+	/* Free skb arrays */
+	kfree(priv->rx_skbs);
+	kfree(priv->tx_skbs);
 
-	ftgmac100_txdma_normal_prio_start_polling(priv);
+	/* Free descriptors */
+	if (priv->rxdes)
+		dma_free_coherent(priv->dev, MAX_RX_QUEUE_ENTRIES *
+				  sizeof(struct ftgmac100_rxdes),
+				  priv->rxdes, priv->rxdes_dma);
+	priv->rxdes = NULL;
 
-	return NETDEV_TX_OK;
+	if (priv->txdes)
+		dma_free_coherent(priv->dev, MAX_TX_QUEUE_ENTRIES *
+				  sizeof(struct ftgmac100_txdes),
+				  priv->txdes, priv->txdes_dma);
+	priv->txdes = NULL;
+
+	/* Free scratch packet buffer */
+	if (priv->rx_scratch)
+		dma_free_coherent(priv->dev, RX_BUF_SIZE,
+				  priv->rx_scratch, priv->rx_scratch_dma);
 }
 
-/******************************************************************************
- * internal functions (buffer)
- *****************************************************************************/
-static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv,
-				   struct ftgmac100_rxdes *rxdes, gfp_t gfp)
+static int ftgmac100_alloc_rings(struct ftgmac100 *priv)
 {
-	struct net_device *netdev = priv->netdev;
-	struct page *page;
-	dma_addr_t map;
+	/* Allocate skb arrays */
+	priv->rx_skbs = kcalloc(MAX_RX_QUEUE_ENTRIES, sizeof(void *),
+				GFP_KERNEL);
+	if (!priv->rx_skbs)
+		return -ENOMEM;
+	priv->tx_skbs = kcalloc(MAX_TX_QUEUE_ENTRIES, sizeof(void *),
+				GFP_KERNEL);
+	if (!priv->tx_skbs)
+		return -ENOMEM;
 
-	page = alloc_page(gfp);
-	if (!page) {
-		if (net_ratelimit())
-			netdev_err(netdev, "failed to allocate rx page\n");
+	/* Allocate descriptors */
+	priv->rxdes = dma_zalloc_coherent(priv->dev,
+					  MAX_RX_QUEUE_ENTRIES *
+					  sizeof(struct ftgmac100_rxdes),
+					  &priv->rxdes_dma, GFP_KERNEL);
+	if (!priv->rxdes)
+		return -ENOMEM;
+	priv->txdes = dma_zalloc_coherent(priv->dev,
+					  MAX_TX_QUEUE_ENTRIES *
+					  sizeof(struct ftgmac100_txdes),
+					  &priv->txdes_dma, GFP_KERNEL);
+	if (!priv->txdes)
 		return -ENOMEM;
-	}
 
-	map = dma_map_page(priv->dev, page, 0, RX_BUF_SIZE, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(priv->dev, map))) {
-		if (net_ratelimit())
-			netdev_err(netdev, "failed to map rx page\n");
-		__free_page(page);
+	/* Allocate scratch packet buffer */
+	priv->rx_scratch = dma_alloc_coherent(priv->dev,
+					      RX_BUF_SIZE,
+					      &priv->rx_scratch_dma,
+					      GFP_KERNEL);
+	if (!priv->rx_scratch)
 		return -ENOMEM;
-	}
 
-	ftgmac100_rxdes_set_page(priv, rxdes, page);
-	ftgmac100_rxdes_set_dma_addr(rxdes, map);
-	ftgmac100_rxdes_set_dma_own(priv, rxdes);
 	return 0;
 }
 
-static void ftgmac100_free_buffers(struct ftgmac100 *priv)
+static void ftgmac100_init_rings(struct ftgmac100 *priv)
 {
+	struct ftgmac100_rxdes *rxdes = NULL;
+	struct ftgmac100_txdes *txdes = NULL;
 	int i;
 
-	for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
-		struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i];
-		struct page *page = ftgmac100_rxdes_get_page(priv, rxdes);
-		dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes);
+	/* Update entries counts */
+	priv->rx_q_entries = priv->new_rx_q_entries;
+	priv->tx_q_entries = priv->new_tx_q_entries;
 
-		if (!page)
-			continue;
+	if (WARN_ON(priv->rx_q_entries < MIN_RX_QUEUE_ENTRIES))
+		return;
 
-		dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
-		__free_page(page);
+	/* Initialize RX ring */
+	for (i = 0; i < priv->rx_q_entries; i++) {
+		rxdes = &priv->rxdes[i];
+		rxdes->rxdes0 = 0;
+		rxdes->rxdes3 = cpu_to_le32(priv->rx_scratch_dma);
 	}
+	/* Mark the end of the ring */
+	rxdes->rxdes0 |= cpu_to_le32(priv->rxdes0_edorr_mask);
 
-	for (i = 0; i < TX_QUEUE_ENTRIES; i++) {
-		struct ftgmac100_txdes *txdes = &priv->descs->txdes[i];
-		struct sk_buff *skb = ftgmac100_txdes_get_skb(txdes);
-		dma_addr_t map = ftgmac100_txdes_get_dma_addr(txdes);
-
-		if (!skb)
-			continue;
+	if (WARN_ON(priv->tx_q_entries < MIN_RX_QUEUE_ENTRIES))
+		return;
 
-		dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE);
-		kfree_skb(skb);
+	/* Initialize TX ring */
+	for (i = 0; i < priv->tx_q_entries; i++) {
+		txdes = &priv->txdes[i];
+		txdes->txdes0 = 0;
 	}
-
-	dma_free_coherent(priv->dev, sizeof(struct ftgmac100_descs),
-			  priv->descs, priv->descs_dma_addr);
+	txdes->txdes0 |= cpu_to_le32(priv->txdes0_edotr_mask);
 }
 
-static int ftgmac100_alloc_buffers(struct ftgmac100 *priv)
+static int ftgmac100_alloc_rx_buffers(struct ftgmac100 *priv)
 {
 	int i;
 
-	priv->descs = dma_zalloc_coherent(priv->dev,
-					  sizeof(struct ftgmac100_descs),
-					  &priv->descs_dma_addr, GFP_KERNEL);
-	if (!priv->descs)
-		return -ENOMEM;
-
-	/* initialize RX ring */
-	ftgmac100_rxdes_set_end_of_ring(priv,
-					&priv->descs->rxdes[RX_QUEUE_ENTRIES - 1]);
-
-	for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
-		struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i];
+	for (i = 0; i < priv->rx_q_entries; i++) {
+		struct ftgmac100_rxdes *rxdes = &priv->rxdes[i];
 
-		if (ftgmac100_alloc_rx_page(priv, rxdes, GFP_KERNEL))
-			goto err;
+		if (ftgmac100_alloc_rx_buf(priv, i, rxdes, GFP_KERNEL))
+			return -ENOMEM;
 	}
-
-	/* initialize TX ring */
-	ftgmac100_txdes_set_end_of_ring(priv,
-					&priv->descs->txdes[TX_QUEUE_ENTRIES - 1]);
 	return 0;
-
-err:
-	ftgmac100_free_buffers(priv);
-	return -ENOMEM;
 }
 
-/******************************************************************************
- * internal functions (mdio)
- *****************************************************************************/
 static void ftgmac100_adjust_link(struct net_device *netdev)
 {
 	struct ftgmac100 *priv = netdev_priv(netdev);
 	struct phy_device *phydev = netdev->phydev;
-	int ier;
+	bool tx_pause, rx_pause;
+	int new_speed;
+
+	/* We store "no link" as speed 0 */
+	if (!phydev->link)
+		new_speed = 0;
+	else
+		new_speed = phydev->speed;
+
+	/* Grab pause settings from PHY if configured to do so */
+	if (priv->aneg_pause) {
+		rx_pause = tx_pause = phydev->pause;
+		if (phydev->asym_pause)
+			tx_pause = !rx_pause;
+	} else {
+		rx_pause = priv->rx_pause;
+		tx_pause = priv->tx_pause;
+	}
 
-	if (phydev->speed == priv->old_speed)
+	/* Link hasn't changed, do nothing */
+	if (phydev->speed == priv->cur_speed &&
+	    phydev->duplex == priv->cur_duplex &&
+	    rx_pause == priv->rx_pause &&
+	    tx_pause == priv->tx_pause)
 		return;
 
-	priv->old_speed = phydev->speed;
-
-	ier = ioread32(priv->base + FTGMAC100_OFFSET_IER);
+	/* Print status if we have a link or we had one and just lost it,
+	 * don't print otherwise.
+	 */
+	if (new_speed || priv->cur_speed)
+		phy_print_status(phydev);
 
-	/* disable all interrupts */
-	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+	priv->cur_speed = new_speed;
+	priv->cur_duplex = phydev->duplex;
+	priv->rx_pause = rx_pause;
+	priv->tx_pause = tx_pause;
 
-	netif_stop_queue(netdev);
-	ftgmac100_stop_hw(priv);
+	/* Link is down, do nothing else */
+	if (!new_speed)
+		return;
 
-	netif_start_queue(netdev);
-	ftgmac100_init_hw(priv);
-	ftgmac100_start_hw(priv, phydev->speed);
+	/* Disable all interrupts */
+	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
 
-	/* re-enable interrupts */
-	iowrite32(ier, priv->base + FTGMAC100_OFFSET_IER);
+	/* Reset the adapter asynchronously */
+	schedule_work(&priv->reset_task);
 }
 
-static int ftgmac100_mii_probe(struct ftgmac100 *priv)
+static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf)
 {
 	struct net_device *netdev = priv->netdev;
 	struct phy_device *phydev;
@@ -908,19 +1064,25 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv)
 	}
 
 	phydev = phy_connect(netdev, phydev_name(phydev),
-			     &ftgmac100_adjust_link, PHY_INTERFACE_MODE_GMII);
+			     &ftgmac100_adjust_link, intf);
 
 	if (IS_ERR(phydev)) {
 		netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name);
 		return PTR_ERR(phydev);
 	}
 
+	/* Indicate that we support PAUSE frames (see comment in
+	 * Documentation/networking/phy.txt)
+	 */
+	phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	phydev->advertising = phydev->supported;
+
+	/* Display what we found */
+	phy_attached_info(phydev);
+
 	return 0;
 }
 
-/******************************************************************************
- * struct mii_bus functions
- *****************************************************************************/
 static int ftgmac100_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
 {
 	struct net_device *netdev = bus->priv;
@@ -992,9 +1154,6 @@ static int ftgmac100_mdiobus_write(struct mii_bus *bus, int phy_addr,
 	return -EIO;
 }
 
-/******************************************************************************
- * struct ethtool_ops functions
- *****************************************************************************/
 static void ftgmac100_get_drvinfo(struct net_device *netdev,
 				  struct ethtool_drvinfo *info)
 {
@@ -1003,175 +1162,365 @@ static void ftgmac100_get_drvinfo(struct net_device *netdev,
 	strlcpy(info->bus_info, dev_name(&netdev->dev), sizeof(info->bus_info));
 }
 
+static void ftgmac100_get_ringparam(struct net_device *netdev,
+				    struct ethtool_ringparam *ering)
+{
+	struct ftgmac100 *priv = netdev_priv(netdev);
+
+	memset(ering, 0, sizeof(*ering));
+	ering->rx_max_pending = MAX_RX_QUEUE_ENTRIES;
+	ering->tx_max_pending = MAX_TX_QUEUE_ENTRIES;
+	ering->rx_pending = priv->rx_q_entries;
+	ering->tx_pending = priv->tx_q_entries;
+}
+
+static int ftgmac100_set_ringparam(struct net_device *netdev,
+				   struct ethtool_ringparam *ering)
+{
+	struct ftgmac100 *priv = netdev_priv(netdev);
+
+	if (ering->rx_pending > MAX_RX_QUEUE_ENTRIES ||
+	    ering->tx_pending > MAX_TX_QUEUE_ENTRIES ||
+	    ering->rx_pending < MIN_RX_QUEUE_ENTRIES ||
+	    ering->tx_pending < MIN_TX_QUEUE_ENTRIES ||
+	    !is_power_of_2(ering->rx_pending) ||
+	    !is_power_of_2(ering->tx_pending))
+		return -EINVAL;
+
+	priv->new_rx_q_entries = ering->rx_pending;
+	priv->new_tx_q_entries = ering->tx_pending;
+	if (netif_running(netdev))
+		schedule_work(&priv->reset_task);
+
+	return 0;
+}
+
+static void ftgmac100_get_pauseparam(struct net_device *netdev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct ftgmac100 *priv = netdev_priv(netdev);
+
+	pause->autoneg = priv->aneg_pause;
+	pause->tx_pause = priv->tx_pause;
+	pause->rx_pause = priv->rx_pause;
+}
+
+static int ftgmac100_set_pauseparam(struct net_device *netdev,
+				    struct ethtool_pauseparam *pause)
+{
+	struct ftgmac100 *priv = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
+
+	priv->aneg_pause = pause->autoneg;
+	priv->tx_pause = pause->tx_pause;
+	priv->rx_pause = pause->rx_pause;
+
+	if (phydev) {
+		phydev->advertising &= ~ADVERTISED_Pause;
+		phydev->advertising &= ~ADVERTISED_Asym_Pause;
+
+		if (pause->rx_pause) {
+			phydev->advertising |= ADVERTISED_Pause;
+			phydev->advertising |= ADVERTISED_Asym_Pause;
+		}
+
+		if (pause->tx_pause)
+			phydev->advertising ^= ADVERTISED_Asym_Pause;
+	}
+	if (netif_running(netdev)) {
+		if (phydev && priv->aneg_pause)
+			phy_start_aneg(phydev);
+		else
+			ftgmac100_config_pause(priv);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops ftgmac100_ethtool_ops = {
 	.get_drvinfo		= ftgmac100_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
+	.nway_reset		= phy_ethtool_nway_reset,
+	.get_ringparam		= ftgmac100_get_ringparam,
+	.set_ringparam		= ftgmac100_set_ringparam,
+	.get_pauseparam		= ftgmac100_get_pauseparam,
+	.set_pauseparam		= ftgmac100_set_pauseparam,
 };
 
-/******************************************************************************
- * interrupt handler
- *****************************************************************************/
 static irqreturn_t ftgmac100_interrupt(int irq, void *dev_id)
 {
 	struct net_device *netdev = dev_id;
 	struct ftgmac100 *priv = netdev_priv(netdev);
+	unsigned int status, new_mask = FTGMAC100_INT_BAD;
 
-	/* When running in NCSI mode, the interface should be ready for
-	 * receiving or transmitting NCSI packets before it's opened.
-	 */
-	if (likely(priv->use_ncsi || netif_running(netdev))) {
-		/* Disable interrupts for polling */
-		iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
-		napi_schedule(&priv->napi);
+	/* Fetch and clear interrupt bits, process abnormal ones */
+	status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
+	iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+	if (unlikely(status & FTGMAC100_INT_BAD)) {
+
+		/* RX buffer unavailable */
+		if (status & FTGMAC100_INT_NO_RXBUF)
+			netdev->stats.rx_over_errors++;
+
+		/* received packet lost due to RX FIFO full */
+		if (status & FTGMAC100_INT_RPKT_LOST)
+			netdev->stats.rx_fifo_errors++;
+
+		/* sent packet lost due to excessive TX collision */
+		if (status & FTGMAC100_INT_XPKT_LOST)
+			netdev->stats.tx_fifo_errors++;
+
+		/* AHB error -> Reset the chip */
+		if (status & FTGMAC100_INT_AHB_ERR) {
+			if (net_ratelimit())
+				netdev_warn(netdev,
+					   "AHB bus error ! Resetting chip.\n");
+			iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+			schedule_work(&priv->reset_task);
+			return IRQ_HANDLED;
+		}
+
+		/* We may need to restart the MAC after such errors, delay
+		 * this until after we have freed some Rx buffers though
+		 */
+		priv->need_mac_restart = true;
+
+		/* Disable those errors until we restart */
+		new_mask &= ~status;
 	}
 
+	/* Only enable "bad" interrupts while NAPI is on */
+	iowrite32(new_mask, priv->base + FTGMAC100_OFFSET_IER);
+
+	/* Schedule NAPI bh */
+	napi_schedule_irqoff(&priv->napi);
+
 	return IRQ_HANDLED;
 }
 
-/******************************************************************************
- * struct napi_struct functions
- *****************************************************************************/
+static bool ftgmac100_check_rx(struct ftgmac100 *priv)
+{
+	struct ftgmac100_rxdes *rxdes = &priv->rxdes[priv->rx_pointer];
+
+	/* Do we have a packet ? */
+	return !!(rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY));
+}
+
 static int ftgmac100_poll(struct napi_struct *napi, int budget)
 {
 	struct ftgmac100 *priv = container_of(napi, struct ftgmac100, napi);
-	struct net_device *netdev = priv->netdev;
-	unsigned int status;
-	bool completed = true;
-	int rx = 0;
+	int work_done = 0;
+	bool more;
 
-	status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
-	iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+	/* Handle TX completions */
+	if (ftgmac100_tx_buf_cleanable(priv))
+		ftgmac100_tx_complete(priv);
 
-	if (status & (FTGMAC100_INT_RPKT_BUF | FTGMAC100_INT_NO_RXBUF)) {
-		/*
-		 * FTGMAC100_INT_RPKT_BUF:
-		 *	RX DMA has received packets into RX buffer successfully
-		 *
-		 * FTGMAC100_INT_NO_RXBUF:
-		 *	RX buffer unavailable
-		 */
-		bool retry;
+	/* Handle RX packets */
+	do {
+		more = ftgmac100_rx_packet(priv, &work_done);
+	} while (more && work_done < budget);
 
-		do {
-			retry = ftgmac100_rx_packet(priv, &rx);
-		} while (retry && rx < budget);
 
-		if (retry && rx == budget)
-			completed = false;
-	}
+	/* The interrupt is telling us to kick the MAC back to life
+	 * after an RX overflow
+	 */
+	if (unlikely(priv->need_mac_restart)) {
+		ftgmac100_start_hw(priv);
 
-	if (status & (FTGMAC100_INT_XPKT_ETH | FTGMAC100_INT_XPKT_LOST)) {
-		/*
-		 * FTGMAC100_INT_XPKT_ETH:
-		 *	packet transmitted to ethernet successfully
-		 *
-		 * FTGMAC100_INT_XPKT_LOST:
-		 *	packet transmitted to ethernet lost due to late
-		 *	collision or excessive collision
-		 */
-		ftgmac100_tx_complete(priv);
+		/* Re-enable "bad" interrupts */
+		iowrite32(FTGMAC100_INT_BAD,
+			  priv->base + FTGMAC100_OFFSET_IER);
 	}
 
-	if (status & priv->int_mask_all & (FTGMAC100_INT_NO_RXBUF |
-			FTGMAC100_INT_RPKT_LOST | FTGMAC100_INT_AHB_ERR)) {
-		if (net_ratelimit())
-			netdev_info(netdev, "[ISR] = 0x%x: %s%s%s\n", status,
-				    status & FTGMAC100_INT_NO_RXBUF ? "NO_RXBUF " : "",
-				    status & FTGMAC100_INT_RPKT_LOST ? "RPKT_LOST " : "",
-				    status & FTGMAC100_INT_AHB_ERR ? "AHB_ERR " : "");
+	/* As long as we are waiting for transmit packets to be
+	 * completed we keep NAPI going
+	 */
+	if (ftgmac100_tx_buf_cleanable(priv))
+		work_done = budget;
+
+	if (work_done < budget) {
+		/* We are about to re-enable all interrupts. However
+		 * the HW has been latching RX/TX packet interrupts while
+		 * they were masked. So we clear them first, then we need
+		 * to re-check if there's something to process
+		 */
+		iowrite32(FTGMAC100_INT_RXTX,
+			  priv->base + FTGMAC100_OFFSET_ISR);
 
-		if (status & FTGMAC100_INT_NO_RXBUF) {
-			/* RX buffer unavailable */
-			netdev->stats.rx_over_errors++;
-		}
+		/* Push the above (and provides a barrier vs. subsequent
+		 * reads of the descriptor).
+		 */
+		ioread32(priv->base + FTGMAC100_OFFSET_ISR);
 
-		if (status & FTGMAC100_INT_RPKT_LOST) {
-			/* received packet lost due to RX FIFO full */
-			netdev->stats.rx_fifo_errors++;
-		}
-	}
+		/* Check RX and TX descriptors for more work to do */
+		if (ftgmac100_check_rx(priv) ||
+		    ftgmac100_tx_buf_cleanable(priv))
+			return budget;
 
-	if (completed) {
+		/* deschedule NAPI */
 		napi_complete(napi);
 
 		/* enable all interrupts */
-		iowrite32(priv->int_mask_all,
+		iowrite32(FTGMAC100_INT_ALL,
 			  priv->base + FTGMAC100_OFFSET_IER);
 	}
 
-	return rx;
+	return work_done;
 }
 
-/******************************************************************************
- * struct net_device_ops functions
- *****************************************************************************/
-static int ftgmac100_open(struct net_device *netdev)
+static int ftgmac100_init_all(struct ftgmac100 *priv, bool ignore_alloc_err)
 {
-	struct ftgmac100 *priv = netdev_priv(netdev);
-	unsigned int status;
+	int err = 0;
+
+	/* Re-init descriptors (adjust queue sizes) */
+	ftgmac100_init_rings(priv);
+
+	/* Realloc rx descriptors */
+	err = ftgmac100_alloc_rx_buffers(priv);
+	if (err && !ignore_alloc_err)
+		return err;
+
+	/* Reinit and restart HW */
+	ftgmac100_init_hw(priv);
+	ftgmac100_config_pause(priv);
+	ftgmac100_start_hw(priv);
+
+	/* Re-enable the device */
+	napi_enable(&priv->napi);
+	netif_start_queue(priv->netdev);
+
+	/* Enable all interrupts */
+	iowrite32(FTGMAC100_INT_ALL, priv->base + FTGMAC100_OFFSET_IER);
+
+	return err;
+}
+
+static void ftgmac100_reset_task(struct work_struct *work)
+{
+	struct ftgmac100 *priv = container_of(work, struct ftgmac100,
+					      reset_task);
+	struct net_device *netdev = priv->netdev;
 	int err;
 
-	err = ftgmac100_alloc_buffers(priv);
+	netdev_dbg(netdev, "Resetting NIC...\n");
+
+	/* Lock the world */
+	rtnl_lock();
+	if (netdev->phydev)
+		mutex_lock(&netdev->phydev->lock);
+	if (priv->mii_bus)
+		mutex_lock(&priv->mii_bus->mdio_lock);
+
+
+	/* Check if the interface is still up */
+	if (!netif_running(netdev))
+		goto bail;
+
+	/* Stop the network stack */
+	netif_trans_update(netdev);
+	napi_disable(&priv->napi);
+	netif_tx_disable(netdev);
+
+	/* Stop and reset the MAC */
+	ftgmac100_stop_hw(priv);
+	err = ftgmac100_reset_and_config_mac(priv);
 	if (err) {
-		netdev_err(netdev, "failed to allocate buffers\n");
-		goto err_alloc;
+		/* Not much we can do ... it might come back... */
+		netdev_err(netdev, "attempting to continue...\n");
 	}
 
-	err = request_irq(priv->irq, ftgmac100_interrupt, 0, netdev->name, netdev);
+	/* Free all rx and tx buffers */
+	ftgmac100_free_buffers(priv);
+
+	/* Setup everything again and restart chip */
+	ftgmac100_init_all(priv, true);
+
+	netdev_dbg(netdev, "Reset done !\n");
+ bail:
+	if (priv->mii_bus)
+		mutex_unlock(&priv->mii_bus->mdio_lock);
+	if (netdev->phydev)
+		mutex_unlock(&netdev->phydev->lock);
+	rtnl_unlock();
+}
+
+static int ftgmac100_open(struct net_device *netdev)
+{
+	struct ftgmac100 *priv = netdev_priv(netdev);
+	int err;
+
+	/* Allocate ring buffers  */
+	err = ftgmac100_alloc_rings(priv);
 	if (err) {
-		netdev_err(netdev, "failed to request irq %d\n", priv->irq);
-		goto err_irq;
+		netdev_err(netdev, "Failed to allocate descriptors\n");
+		return err;
 	}
 
-	priv->rx_pointer = 0;
-	priv->tx_clean_pointer = 0;
-	priv->tx_pointer = 0;
-	priv->tx_pending = 0;
+	/* When using NC-SI we force the speed to 100Mbit/s full duplex,
+	 *
+	 * Otherwise we leave it set to 0 (no link), the link
+	 * message from the PHY layer will handle setting it up to
+	 * something else if needed.
+	 */
+	if (priv->use_ncsi) {
+		priv->cur_duplex = DUPLEX_FULL;
+		priv->cur_speed = SPEED_100;
+	} else {
+		priv->cur_duplex = 0;
+		priv->cur_speed = 0;
+	}
 
-	err = ftgmac100_reset_hw(priv);
+	/* Reset the hardware */
+	err = ftgmac100_reset_and_config_mac(priv);
 	if (err)
 		goto err_hw;
 
-	ftgmac100_init_hw(priv);
-	ftgmac100_start_hw(priv, priv->use_ncsi ? 100 : 10);
+	/* Initialize NAPI */
+	netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64);
 
-	/* Clear stale interrupts */
-	status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
-	iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+	/* Grab our interrupt */
+	err = request_irq(netdev->irq, ftgmac100_interrupt, 0, netdev->name, netdev);
+	if (err) {
+		netdev_err(netdev, "failed to request irq %d\n", netdev->irq);
+		goto err_irq;
+	}
 
-	if (netdev->phydev)
+	/* Start things up */
+	err = ftgmac100_init_all(priv, false);
+	if (err) {
+		netdev_err(netdev, "Failed to allocate packet buffers\n");
+		goto err_alloc;
+	}
+
+	if (netdev->phydev) {
+		/* If we have a PHY, start polling */
 		phy_start(netdev->phydev);
-	else if (priv->use_ncsi)
+	} else if (priv->use_ncsi) {
+		/* If using NC-SI, set our carrier on and start the stack */
 		netif_carrier_on(netdev);
 
-	napi_enable(&priv->napi);
-	netif_start_queue(netdev);
-
-	/* enable all interrupts */
-	iowrite32(priv->int_mask_all, priv->base + FTGMAC100_OFFSET_IER);
-
-	/* Start the NCSI device */
-	if (priv->use_ncsi) {
+		/* Start the NCSI device */
 		err = ncsi_start_dev(priv->ndev);
 		if (err)
 			goto err_ncsi;
 	}
 
-	priv->enabled = true;
-
 	return 0;
 
-err_ncsi:
+ err_ncsi:
 	napi_disable(&priv->napi);
 	netif_stop_queue(netdev);
-	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
-err_hw:
-	free_irq(priv->irq, netdev);
-err_irq:
+ err_alloc:
 	ftgmac100_free_buffers(priv);
-err_alloc:
+	free_irq(netdev->irq, netdev);
+ err_irq:
+	netif_napi_del(&priv->napi);
+ err_hw:
+	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+	ftgmac100_free_rings(priv);
 	return err;
 }
 
@@ -1179,64 +1528,87 @@ static int ftgmac100_stop(struct net_device *netdev)
 {
 	struct ftgmac100 *priv = netdev_priv(netdev);
 
-	if (!priv->enabled)
-		return 0;
+	/* Note about the reset task: We are called with the rtnl lock
+	 * held, so we are synchronized against the core of the reset
+	 * task. We must not try to synchronously cancel it otherwise
+	 * we can deadlock. But since it will test for netif_running()
+	 * which has already been cleared by the net core, we don't
+	 * anything special to do.
+	 */
 
 	/* disable all interrupts */
-	priv->enabled = false;
 	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
 
 	netif_stop_queue(netdev);
 	napi_disable(&priv->napi);
+	netif_napi_del(&priv->napi);
 	if (netdev->phydev)
 		phy_stop(netdev->phydev);
 	else if (priv->use_ncsi)
 		ncsi_stop_dev(priv->ndev);
 
 	ftgmac100_stop_hw(priv);
-	free_irq(priv->irq, netdev);
+	free_irq(netdev->irq, netdev);
 	ftgmac100_free_buffers(priv);
+	ftgmac100_free_rings(priv);
 
 	return 0;
 }
 
-static int ftgmac100_hard_start_xmit(struct sk_buff *skb,
-				     struct net_device *netdev)
+/* optional */
+static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	if (!netdev->phydev)
+		return -ENXIO;
+
+	return phy_mii_ioctl(netdev->phydev, ifr, cmd);
+}
+
+static void ftgmac100_tx_timeout(struct net_device *netdev)
 {
 	struct ftgmac100 *priv = netdev_priv(netdev);
-	dma_addr_t map;
 
-	if (unlikely(skb->len > MAX_PKT_SIZE)) {
-		if (net_ratelimit())
-			netdev_dbg(netdev, "tx packet too big\n");
+	/* Disable all interrupts */
+	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
 
-		netdev->stats.tx_dropped++;
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
+	/* Do the reset outside of interrupt context */
+	schedule_work(&priv->reset_task);
+}
 
-	map = dma_map_single(priv->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(priv->dev, map))) {
-		/* drop packet */
-		if (net_ratelimit())
-			netdev_err(netdev, "map socket buffer failed\n");
+static int ftgmac100_set_features(struct net_device *netdev,
+				  netdev_features_t features)
+{
+	struct ftgmac100 *priv = netdev_priv(netdev);
+	netdev_features_t changed = netdev->features ^ features;
 
-		netdev->stats.tx_dropped++;
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
+	if (!netif_running(netdev))
+		return 0;
+
+	/* Update the vlan filtering bit */
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX) {
+		u32 maccr;
+
+		maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR);
+		if (priv->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+			maccr |= FTGMAC100_MACCR_RM_VLAN;
+		else
+			maccr &= ~FTGMAC100_MACCR_RM_VLAN;
+		iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
 	}
 
-	return ftgmac100_xmit(priv, skb, map);
+	return 0;
 }
 
-/* optional */
-static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void ftgmac100_poll_controller(struct net_device *netdev)
 {
-	if (!netdev->phydev)
-		return -ENXIO;
+	unsigned long flags;
 
-	return phy_mii_ioctl(netdev->phydev, ifr, cmd);
+	local_irq_save(flags);
+	ftgmac100_interrupt(netdev->irq, netdev);
+	local_irq_restore(flags);
 }
+#endif
 
 static const struct net_device_ops ftgmac100_netdev_ops = {
 	.ndo_open		= ftgmac100_open,
@@ -1245,12 +1617,20 @@ static const struct net_device_ops ftgmac100_netdev_ops = {
 	.ndo_set_mac_address	= ftgmac100_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= ftgmac100_do_ioctl,
+	.ndo_tx_timeout		= ftgmac100_tx_timeout,
+	.ndo_set_rx_mode	= ftgmac100_set_rx_mode,
+	.ndo_set_features	= ftgmac100_set_features,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= ftgmac100_poll_controller,
+#endif
 };
 
 static int ftgmac100_setup_mdio(struct net_device *netdev)
 {
 	struct ftgmac100 *priv = netdev_priv(netdev);
 	struct platform_device *pdev = to_platform_device(priv->dev);
+	int phy_intf = PHY_INTERFACE_MODE_RGMII;
+	struct device_node *np = pdev->dev.of_node;
 	int i, err = 0;
 	u32 reg;
 
@@ -1259,14 +1639,46 @@ static int ftgmac100_setup_mdio(struct net_device *netdev)
 	if (!priv->mii_bus)
 		return -EIO;
 
-	if (of_machine_is_compatible("aspeed,ast2400") ||
-	    of_machine_is_compatible("aspeed,ast2500")) {
+	if (priv->is_aspeed) {
 		/* This driver supports the old MDIO interface */
 		reg = ioread32(priv->base + FTGMAC100_OFFSET_REVR);
 		reg &= ~FTGMAC100_REVR_NEW_MDIO_INTERFACE;
 		iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR);
 	};
 
+	/* Get PHY mode from device-tree */
+	if (np) {
+		/* Default to RGMII. It's a gigabit part after all */
+		phy_intf = of_get_phy_mode(np);
+		if (phy_intf < 0)
+			phy_intf = PHY_INTERFACE_MODE_RGMII;
+
+		/* Aspeed only supports these. I don't know about other IP
+		 * block vendors so I'm going to just let them through for
+		 * now. Note that this is only a warning if for some obscure
+		 * reason the DT really means to lie about it or it's a newer
+		 * part we don't know about.
+		 *
+		 * On the Aspeed SoC there are additionally straps and SCU
+		 * control bits that could tell us what the interface is
+		 * (or allow us to configure it while the IP block is held
+		 * in reset). For now I chose to keep this driver away from
+		 * those SoC specific bits and assume the device-tree is
+		 * right and the SCU has been configured properly by pinmux
+		 * or the firmware.
+		 */
+		if (priv->is_aspeed &&
+		    phy_intf != PHY_INTERFACE_MODE_RMII &&
+		    phy_intf != PHY_INTERFACE_MODE_RGMII &&
+		    phy_intf != PHY_INTERFACE_MODE_RGMII_ID &&
+		    phy_intf != PHY_INTERFACE_MODE_RGMII_RXID &&
+		    phy_intf != PHY_INTERFACE_MODE_RGMII_TXID) {
+			netdev_warn(netdev,
+				   "Unsupported PHY mode %s !\n",
+				   phy_modes(phy_intf));
+		}
+	}
+
 	priv->mii_bus->name = "ftgmac100_mdio";
 	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d",
 		 pdev->name, pdev->id);
@@ -1283,7 +1695,7 @@ static int ftgmac100_setup_mdio(struct net_device *netdev)
 		goto err_register_mdiobus;
 	}
 
-	err = ftgmac100_mii_probe(priv);
+	err = ftgmac100_mii_probe(priv, phy_intf);
 	if (err) {
 		dev_err(priv->dev, "MII Probe failed!\n");
 		goto err_mii_probe;
@@ -1319,15 +1731,13 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd)
 		    nd->link_up ? "up" : "down");
 }
 
-/******************************************************************************
- * struct platform_driver functions
- *****************************************************************************/
 static int ftgmac100_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	int irq;
 	struct net_device *netdev;
 	struct ftgmac100 *priv;
+	struct device_node *np;
 	int err = 0;
 
 	if (!pdev)
@@ -1352,6 +1762,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 
 	netdev->ethtool_ops = &ftgmac100_ethtool_ops;
 	netdev->netdev_ops = &ftgmac100_netdev_ops;
+	netdev->watchdog_timeo = 5 * HZ;
 
 	platform_set_drvdata(pdev, netdev);
 
@@ -1359,11 +1770,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 	priv = netdev_priv(netdev);
 	priv->netdev = netdev;
 	priv->dev = &pdev->dev;
-
-	spin_lock_init(&priv->tx_lock);
-
-	/* initialize NAPI */
-	netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64);
+	INIT_WORK(&priv->reset_task, ftgmac100_reset_task);
 
 	/* map io memory */
 	priv->res = request_mem_region(res->start, resource_size(res),
@@ -1381,29 +1788,28 @@ static int ftgmac100_probe(struct platform_device *pdev)
 		goto err_ioremap;
 	}
 
-	priv->irq = irq;
+	netdev->irq = irq;
 
-	/* MAC address from chip or random one */
-	ftgmac100_setup_mac(priv);
+	/* Enable pause */
+	priv->tx_pause = true;
+	priv->rx_pause = true;
+	priv->aneg_pause = true;
 
-	priv->int_mask_all = (FTGMAC100_INT_RPKT_LOST |
-			      FTGMAC100_INT_XPKT_ETH |
-			      FTGMAC100_INT_XPKT_LOST |
-			      FTGMAC100_INT_AHB_ERR |
-			      FTGMAC100_INT_RPKT_BUF |
-			      FTGMAC100_INT_NO_RXBUF);
+	/* MAC address from chip or random one */
+	ftgmac100_initial_mac(priv);
 
-	if (of_machine_is_compatible("aspeed,ast2400") ||
-	    of_machine_is_compatible("aspeed,ast2500")) {
+	np = pdev->dev.of_node;
+	if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac") ||
+		   of_device_is_compatible(np, "aspeed,ast2500-mac"))) {
 		priv->rxdes0_edorr_mask = BIT(30);
 		priv->txdes0_edotr_mask = BIT(30);
+		priv->is_aspeed = true;
 	} else {
 		priv->rxdes0_edorr_mask = BIT(15);
 		priv->txdes0_edotr_mask = BIT(15);
 	}
 
-	if (pdev->dev.of_node &&
-	    of_get_property(pdev->dev.of_node, "use-ncsi", NULL)) {
+	if (np && of_get_property(np, "use-ncsi", NULL)) {
 		if (!IS_ENABLED(CONFIG_NET_NCSI)) {
 			dev_err(&pdev->dev, "NCSI stack not enabled\n");
 			goto err_ncsi_dev;
@@ -1421,15 +1827,21 @@ static int ftgmac100_probe(struct platform_device *pdev)
 			goto err_setup_mdio;
 	}
 
-	/* We have to disable on-chip IP checksum functionality
-	 * when NCSI is enabled on the interface. It doesn't work
-	 * in that case.
-	 */
-	netdev->features = NETIF_F_IP_CSUM | NETIF_F_GRO;
-	if (priv->use_ncsi &&
-	    of_get_property(pdev->dev.of_node, "no-hw-checksum", NULL))
-		netdev->features &= ~NETIF_F_IP_CSUM;
+	/* Default ring sizes */
+	priv->rx_q_entries = priv->new_rx_q_entries = DEF_RX_QUEUE_ENTRIES;
+	priv->tx_q_entries = priv->new_tx_q_entries = DEF_TX_QUEUE_ENTRIES;
 
+	/* Base feature set */
+	netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+		NETIF_F_GRO | NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX |
+		NETIF_F_HW_VLAN_CTAG_TX;
+
+	/* AST2400  doesn't have working HW checksum generation */
+	if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac")))
+		netdev->hw_features &= ~NETIF_F_HW_CSUM;
+	if (np && of_get_property(np, "no-hw-checksum", NULL))
+		netdev->hw_features &= ~(NETIF_F_HW_CSUM | NETIF_F_RXCSUM);
+	netdev->features |= netdev->hw_features;
 
 	/* register network device */
 	err = register_netdev(netdev);
@@ -1438,7 +1850,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 		goto err_register_netdev;
 	}
 
-	netdev_info(netdev, "irq %d, mapped at %p\n", priv->irq, priv->base);
+	netdev_info(netdev, "irq %d, mapped at %p\n", netdev->irq, priv->base);
 
 	return 0;
 
@@ -1465,6 +1877,12 @@ static int ftgmac100_remove(struct platform_device *pdev)
 	priv = netdev_priv(netdev);
 
 	unregister_netdev(netdev);
+
+	/* There's a small chance the reset task will have been re-queued,
+	 * during stop, make sure it's gone before we free the structure.
+	 */
+	cancel_work_sync(&priv->reset_task);
+
 	ftgmac100_destroy_mdio(netdev);
 
 	iounmap(priv->base);
diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h
index a7ce0ac8858a..0653d8176e6a 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.h
+++ b/drivers/net/ethernet/faraday/ftgmac100.h
@@ -86,6 +86,20 @@
 #define FTGMAC100_INT_PHYSTS_CHG	(1 << 9)
 #define FTGMAC100_INT_NO_HPTXBUF	(1 << 10)
 
+/* Interrupts we care about in NAPI mode */
+#define FTGMAC100_INT_BAD  (FTGMAC100_INT_RPKT_LOST | \
+			    FTGMAC100_INT_XPKT_LOST | \
+			    FTGMAC100_INT_AHB_ERR   | \
+			    FTGMAC100_INT_NO_RXBUF)
+
+/* Normal RX/TX interrupts, enabled when NAPI off */
+#define FTGMAC100_INT_RXTX (FTGMAC100_INT_XPKT_ETH  | \
+			    FTGMAC100_INT_RPKT_BUF)
+
+/* All the interrupts we care about */
+#define FTGMAC100_INT_ALL (FTGMAC100_INT_RPKT_BUF  |  \
+			   FTGMAC100_INT_BAD)
+
 /*
  * Interrupt timer control register
  */
@@ -185,13 +199,20 @@
 #define FTGMAC100_PHYDATA_MIIRDATA(phydata)	(((phydata) >> 16) & 0xffff)
 
 /*
+ * Flow control register
+ */
+#define FTGMAC100_FCR_FC_EN		(1 << 0)
+#define FTGMAC100_FCR_FCTHR_EN		(1 << 2)
+#define FTGMAC100_FCR_PAUSE_TIME(x)	(((x) & 0xffff) << 16)
+
+/*
  * Transmit descriptor, aligned to 16 bytes
  */
 struct ftgmac100_txdes {
-	unsigned int	txdes0;
-	unsigned int	txdes1;
-	unsigned int	txdes2;	/* not used by HW */
-	unsigned int	txdes3;	/* TXBUF_BADR */
+	__le32	txdes0; /* Control & status bits */
+	__le32	txdes1; /* Irq, checksum and vlan control */
+	__le32	txdes2; /* Reserved */
+	__le32	txdes3; /* DMA buffer address */
 } __attribute__ ((aligned(16)));
 
 #define FTGMAC100_TXDES0_TXBUF_SIZE(x)	((x) & 0x3fff)
@@ -213,10 +234,10 @@ struct ftgmac100_txdes {
  * Receive descriptor, aligned to 16 bytes
  */
 struct ftgmac100_rxdes {
-	unsigned int	rxdes0;
-	unsigned int	rxdes1;
-	unsigned int	rxdes2;	/* not used by HW */
-	unsigned int	rxdes3;	/* RXBUF_BADR */
+	__le32	rxdes0; /* Control & status bits */
+	__le32	rxdes1;	/* Checksum and vlan status */
+	__le32	rxdes2; /* length/type on AST2500 */
+	__le32	rxdes3;	/* DMA buffer address */
 } __attribute__ ((aligned(16)));
 
 #define FTGMAC100_RXDES0_VDBC		0x3fff
@@ -234,6 +255,14 @@ struct ftgmac100_rxdes {
 #define FTGMAC100_RXDES0_FRS		(1 << 29)
 #define FTGMAC100_RXDES0_RXPKT_RDY	(1 << 31)
 
+/* Errors we care about for dropping packets */
+#define RXDES0_ANY_ERROR		( \
+	FTGMAC100_RXDES0_RX_ERR		| \
+	FTGMAC100_RXDES0_CRC_ERR	| \
+	FTGMAC100_RXDES0_FTL		| \
+	FTGMAC100_RXDES0_RUNT		| \
+	FTGMAC100_RXDES0_RX_ODD_NB)
+
 #define FTGMAC100_RXDES1_VLANTAG_CI	0xffff
 #define FTGMAC100_RXDES1_PROT_MASK	(0x3 << 20)
 #define FTGMAC100_RXDES1_PROT_NONIP	(0x0 << 20)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e2ca107f9d94..9a520e4f0df9 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -137,6 +137,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
 /* L4 Type field: TCP */
 #define FM_L4_PARSE_RESULT_TCP	0x20
 
+/* FD status field indicating whether the FM Parser has attempted to validate
+ * the L4 csum of the frame.
+ * Note that having this bit set doesn't necessarily imply that the checksum
+ * is valid. One would have to check the parse results to find that out.
+ */
+#define FM_FD_STAT_L4CV         0x00000004
+
 #define DPAA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */
 #define DPAA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */
 
@@ -235,6 +242,7 @@ static int dpaa_netdev_init(struct net_device *net_dev,
 	 * For conformity, we'll still declare GSO explicitly.
 	 */
 	net_dev->features |= NETIF_F_GSO;
+	net_dev->features |= NETIF_F_RXCSUM;
 
 	net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	/* we do not want shared skbs on TX */
@@ -334,6 +342,45 @@ static void dpaa_get_stats64(struct net_device *net_dev,
 	}
 }
 
+static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
+			 struct tc_to_netdev *tc)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	u8 num_tc;
+	int i;
+
+	if (tc->type != TC_SETUP_MQPRIO)
+		return -EINVAL;
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_tc = tc->mqprio->num_tc;
+
+	if (num_tc == priv->num_tc)
+		return 0;
+
+	if (!num_tc) {
+		netdev_reset_tc(net_dev);
+		goto out;
+	}
+
+	if (num_tc > DPAA_TC_NUM) {
+		netdev_err(net_dev, "Too many traffic classes: max %d supported.\n",
+			   DPAA_TC_NUM);
+		return -EINVAL;
+	}
+
+	netdev_set_num_tc(net_dev, num_tc);
+
+	for (i = 0; i < num_tc; i++)
+		netdev_set_tc_queue(net_dev, i, DPAA_TC_TXQ_NUM,
+				    i * DPAA_TC_TXQ_NUM);
+
+out:
+	priv->num_tc = num_tc ? : 1;
+	netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM);
+	return 0;
+}
+
 static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev)
 {
 	struct platform_device *of_dev;
@@ -557,16 +604,18 @@ static void dpaa_bps_free(struct dpaa_priv *priv)
 
 /* Use multiple WQs for FQ assignment:
  *	- Tx Confirmation queues go to WQ1.
- *	- Rx Error and Tx Error queues go to WQ2 (giving them a better chance
- *	  to be scheduled, in case there are many more FQs in WQ3).
- *	- Rx Default and Tx queues go to WQ3 (no differentiation between
- *	  Rx and Tx traffic).
+ *	- Rx Error and Tx Error queues go to WQ5 (giving them a better chance
+ *	  to be scheduled, in case there are many more FQs in WQ6).
+ *	- Rx Default goes to WQ6.
+ *	- Tx queues go to different WQs depending on their priority. Equal
+ *	  chunks of NR_CPUS queues go to WQ6 (lowest priority), WQ2, WQ1 and
+ *	  WQ0 (highest priority).
  * This ensures that Tx-confirmed buffers are timely released. In particular,
  * it avoids congestion on the Tx Confirm FQs, which can pile up PFDRs if they
  * are greatly outnumbered by other FQs in the system, while
  * dequeue scheduling is round-robin.
  */
-static inline void dpaa_assign_wq(struct dpaa_fq *fq)
+static inline void dpaa_assign_wq(struct dpaa_fq *fq, int idx)
 {
 	switch (fq->fq_type) {
 	case FQ_TYPE_TX_CONFIRM:
@@ -575,11 +624,33 @@ static inline void dpaa_assign_wq(struct dpaa_fq *fq)
 		break;
 	case FQ_TYPE_RX_ERROR:
 	case FQ_TYPE_TX_ERROR:
-		fq->wq = 2;
+		fq->wq = 5;
 		break;
 	case FQ_TYPE_RX_DEFAULT:
+		fq->wq = 6;
+		break;
 	case FQ_TYPE_TX:
-		fq->wq = 3;
+		switch (idx / DPAA_TC_TXQ_NUM) {
+		case 0:
+			/* Low priority (best effort) */
+			fq->wq = 6;
+			break;
+		case 1:
+			/* Medium priority */
+			fq->wq = 2;
+			break;
+		case 2:
+			/* High priority */
+			fq->wq = 1;
+			break;
+		case 3:
+			/* Very high priority */
+			fq->wq = 0;
+			break;
+		default:
+			WARN(1, "Too many TX FQs: more than %d!\n",
+			     DPAA_ETH_TXQ_NUM);
+		}
 		break;
 	default:
 		WARN(1, "Invalid FQ type %d for FQID %d!\n",
@@ -607,7 +678,7 @@ static struct dpaa_fq *dpaa_fq_alloc(struct device *dev,
 	}
 
 	for (i = 0; i < count; i++)
-		dpaa_assign_wq(dpaa_fq + i);
+		dpaa_assign_wq(dpaa_fq + i, i);
 
 	return dpaa_fq;
 }
@@ -903,7 +974,7 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
 		 * Tx Confirmation FQs.
 		 */
 		if (dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM)
-			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE);
+			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_AVOIDBLOCK);
 
 		/* FQ placement */
 		initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_DESTWQ);
@@ -985,7 +1056,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
 		/* Initialization common to all ingress queues */
 		if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) {
 			initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTA);
-			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE);
+			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE |
+						QM_FQCTRL_CTXASTASHING);
 			initfq.fqd.context_a.stashing.exclusive =
 				QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX |
 				QM_STASHING_EXCL_ANNOTATION;
@@ -1055,9 +1127,9 @@ static int dpaa_fq_free(struct device *dev, struct list_head *list)
 	return err;
 }
 
-static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
-				  struct dpaa_fq *defq,
-				  struct dpaa_buffer_layout *buf_layout)
+static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
+				 struct dpaa_fq *defq,
+				 struct dpaa_buffer_layout *buf_layout)
 {
 	struct fman_buffer_prefix_content buf_prefix_content;
 	struct fman_port_params params;
@@ -1076,23 +1148,29 @@ static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
 	params.specific_params.non_rx_params.dflt_fqid = defq->fqid;
 
 	err = fman_port_config(port, &params);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_config failed\n", __func__);
+		return err;
+	}
 
 	err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
 		       __func__);
+		return err;
+	}
 
 	err = fman_port_init(port);
 	if (err)
 		pr_err("%s: fm_port_init failed\n", __func__);
+
+	return err;
 }
 
-static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
-				  size_t count, struct dpaa_fq *errq,
-				  struct dpaa_fq *defq,
-				  struct dpaa_buffer_layout *buf_layout)
+static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
+				 size_t count, struct dpaa_fq *errq,
+				 struct dpaa_fq *defq,
+				 struct dpaa_buffer_layout *buf_layout)
 {
 	struct fman_buffer_prefix_content buf_prefix_content;
 	struct fman_port_rx_params *rx_p;
@@ -1120,32 +1198,44 @@ static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
 	}
 
 	err = fman_port_config(port, &params);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_config failed\n", __func__);
+		return err;
+	}
 
 	err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
 		       __func__);
+		return err;
+	}
 
 	err = fman_port_init(port);
 	if (err)
 		pr_err("%s: fm_port_init failed\n", __func__);
+
+	return err;
 }
 
-static void dpaa_eth_init_ports(struct mac_device *mac_dev,
-				struct dpaa_bp **bps, size_t count,
-				struct fm_port_fqs *port_fqs,
-				struct dpaa_buffer_layout *buf_layout,
-				struct device *dev)
+static int dpaa_eth_init_ports(struct mac_device *mac_dev,
+			       struct dpaa_bp **bps, size_t count,
+			       struct fm_port_fqs *port_fqs,
+			       struct dpaa_buffer_layout *buf_layout,
+			       struct device *dev)
 {
 	struct fman_port *rxport = mac_dev->port[RX];
 	struct fman_port *txport = mac_dev->port[TX];
+	int err;
+
+	err = dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
+				    port_fqs->tx_defq, &buf_layout[TX]);
+	if (err)
+		return err;
+
+	err = dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
+				    port_fqs->rx_defq, &buf_layout[RX]);
 
-	dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
-			      port_fqs->tx_defq, &buf_layout[TX]);
-	dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
-			      port_fqs->rx_defq, &buf_layout[RX]);
+	return err;
 }
 
 static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp,
@@ -1526,6 +1616,23 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 	return skb;
 }
 
+static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd)
+{
+	/* The parser has run and performed L4 checksum validation.
+	 * We know there were no parser errors (and implicitly no
+	 * L4 csum error), otherwise we wouldn't be here.
+	 */
+	if ((priv->net_dev->features & NETIF_F_RXCSUM) &&
+	    (be32_to_cpu(fd->status) & FM_FD_STAT_L4CV))
+		return CHECKSUM_UNNECESSARY;
+
+	/* We're here because either the parser didn't run or the L4 checksum
+	 * was not verified. This may include the case of a UDP frame with
+	 * checksum zero or an L4 proto other than TCP/UDP
+	 */
+	return CHECKSUM_NONE;
+}
+
 /* Build a linear skb around the received buffer.
  * We are guaranteed there is enough room at the end of the data buffer to
  * accommodate the shared info area of the skb.
@@ -1556,7 +1663,7 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv,
 	skb_reserve(skb, fd_off);
 	skb_put(skb, qm_fd_get_length(fd));
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb->ip_summed = rx_csum_offload(priv, fd);
 
 	return skb;
 
@@ -1616,7 +1723,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv,
 			if (WARN_ON(unlikely(!skb)))
 				goto free_buffers;
 
-			skb->ip_summed = CHECKSUM_NONE;
+			skb->ip_summed = rx_csum_offload(priv, fd);
 
 			/* Make sure forwarded skbs will have enough space
 			 * on Tx, if extra headers are added.
@@ -2093,7 +2200,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	dma_addr_t addr = qm_fd_addr(fd);
 	enum qm_fd_format fd_format;
 	struct net_device *net_dev;
-	u32 fd_status = fd->status;
+	u32 fd_status;
 	struct dpaa_bp *dpaa_bp;
 	struct dpaa_priv *priv;
 	unsigned int skb_len;
@@ -2350,6 +2457,7 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
 	.ndo_do_ioctl = dpaa_ioctl,
+	.ndo_setup_tc = dpaa_setup_tc,
 };
 
 static int dpaa_napi_add(struct net_device *net_dev)
@@ -2624,8 +2732,10 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
 
 	/* All real interfaces need their ports initialized */
-	dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
-			    &priv->buf_layout[0], dev);
+	err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
+				  &priv->buf_layout[0], dev);
+	if (err)
+		goto init_ports_failed;
 
 	priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv);
 	if (!priv->percpu_priv) {
@@ -2638,6 +2748,9 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 		memset(percpu_priv, 0, sizeof(*percpu_priv));
 	}
 
+	priv->num_tc = 1;
+	netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM);
+
 	/* Initialize NAPI */
 	err = dpaa_napi_add(net_dev);
 	if (err < 0)
@@ -2658,6 +2771,7 @@ netdev_init_failed:
 napi_add_failed:
 	dpaa_napi_del(net_dev);
 alloc_percpu_failed:
+init_ports_failed:
 	dpaa_fq_free(dev, &priv->dpaa_fq_list);
 fq_alloc_failed:
 	qman_delete_cgr_safe(&priv->ingress_cgr);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 1f9aebf3f3c5..9941a7866ebe 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -39,7 +39,12 @@
 #include "mac.h"
 #include "dpaa_eth_trace.h"
 
-#define DPAA_ETH_TXQ_NUM	NR_CPUS
+/* Number of prioritised traffic classes */
+#define DPAA_TC_NUM		4
+/* Number of Tx queues per traffic class */
+#define DPAA_TC_TXQ_NUM		NR_CPUS
+/* Total number of Tx queues */
+#define DPAA_ETH_TXQ_NUM	(DPAA_TC_NUM * DPAA_TC_TXQ_NUM)
 
 #define DPAA_BPS_NUM 3 /* number of bpools per interface */
 
@@ -152,6 +157,7 @@ struct dpaa_priv {
 	u16 channel;
 	struct list_head dpaa_fq_list;
 
+	u8 num_tc;
 	u32 msg_enable;	/* net_device message level */
 
 	struct {
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 91a16641e851..a92bf94f8e94 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -117,8 +117,9 @@ static struct platform_device_id fec_devtype[] = {
 		.name = "imx6ul-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_BUG_CAPTURE |
-				FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
+				FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
+				FEC_QUIRK_HAS_COALESCE,
 	}, {
 		/* sentinel */
 	}
@@ -235,14 +236,14 @@ static struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp,
 					     struct bufdesc_prop *bd)
 {
 	return (bdp >= bd->last) ? bd->base
-			: (struct bufdesc *)(((unsigned)bdp) + bd->dsize);
+			: (struct bufdesc *)(((void *)bdp) + bd->dsize);
 }
 
 static struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp,
 					     struct bufdesc_prop *bd)
 {
 	return (bdp <= bd->base) ? bd->last
-			: (struct bufdesc *)(((unsigned)bdp) - bd->dsize);
+			: (struct bufdesc *)(((void *)bdp) - bd->dsize);
 }
 
 static int fec_enet_get_bd_index(struct bufdesc *bdp,
@@ -1266,7 +1267,7 @@ skb_done:
 		}
 	}
 
-	/* ERR006538: Keep the transmitter going */
+	/* ERR006358: Keep the transmitter going */
 	if (bdp != txq->bd.cur &&
 	    readl(txq->bd.reg_desc_active) == 0)
 		writel(0, txq->bd.reg_desc_active);
@@ -2651,7 +2652,7 @@ static void fec_enet_free_queue(struct net_device *ndev)
 	for (i = 0; i < fep->num_tx_queues; i++)
 		if (fep->tx_queue[i] && fep->tx_queue[i]->tso_hdrs) {
 			txq = fep->tx_queue[i];
-			dma_free_coherent(NULL,
+			dma_free_coherent(&fep->pdev->dev,
 					  txq->bd.ring_size * TSO_HEADER_SIZE,
 					  txq->tso_hdrs,
 					  txq->tso_hdrs_dma);
@@ -2685,7 +2686,7 @@ static int fec_enet_alloc_queue(struct net_device *ndev)
 		txq->tx_wake_threshold =
 			(txq->bd.ring_size - txq->tx_stop_threshold) / 2;
 
-		txq->tso_hdrs = dma_alloc_coherent(NULL,
+		txq->tso_hdrs = dma_alloc_coherent(&fep->pdev->dev,
 					txq->bd.ring_size * TSO_HEADER_SIZE,
 					&txq->tso_hdrs_dma,
 					GFP_KERNEL);
@@ -3187,7 +3188,7 @@ static int fec_enet_init(struct net_device *ndev)
 }
 
 #ifdef CONFIG_OF
-static void fec_reset_phy(struct platform_device *pdev)
+static int fec_reset_phy(struct platform_device *pdev)
 {
 	int err, phy_reset;
 	bool active_high = false;
@@ -3195,16 +3196,18 @@ static void fec_reset_phy(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 
 	if (!np)
-		return;
+		return 0;
 
-	of_property_read_u32(np, "phy-reset-duration", &msec);
+	err = of_property_read_u32(np, "phy-reset-duration", &msec);
 	/* A sane reset duration should not be longer than 1s */
-	if (msec > 1000)
+	if (!err && msec > 1000)
 		msec = 1;
 
 	phy_reset = of_get_named_gpio(np, "phy-reset-gpios", 0);
-	if (!gpio_is_valid(phy_reset))
-		return;
+	if (phy_reset == -EPROBE_DEFER)
+		return phy_reset;
+	else if (!gpio_is_valid(phy_reset))
+		return 0;
 
 	active_high = of_property_read_bool(np, "phy-reset-active-high");
 
@@ -3213,7 +3216,7 @@ static void fec_reset_phy(struct platform_device *pdev)
 			"phy-reset");
 	if (err) {
 		dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err);
-		return;
+		return err;
 	}
 
 	if (msec > 20)
@@ -3222,14 +3225,17 @@ static void fec_reset_phy(struct platform_device *pdev)
 		usleep_range(msec * 1000, msec * 1000 + 1000);
 
 	gpio_set_value_cansleep(phy_reset, !active_high);
+
+	return 0;
 }
 #else /* CONFIG_OF */
-static void fec_reset_phy(struct platform_device *pdev)
+static int fec_reset_phy(struct platform_device *pdev)
 {
 	/*
 	 * In case of platform probe, the reset has been done
 	 * by machine code.
 	 */
+	return 0;
 }
 #endif /* CONFIG_OF */
 
@@ -3400,6 +3406,7 @@ fec_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev,
 				"Failed to enable phy regulator: %d\n", ret);
+			clk_disable_unprepare(fep->clk_ipg);
 			goto failed_regulator;
 		}
 	} else {
@@ -3412,7 +3419,9 @@ fec_probe(struct platform_device *pdev)
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	fec_reset_phy(pdev);
+	ret = fec_reset_phy(pdev);
+	if (ret)
+		goto failed_reset;
 
 	if (fep->bufdesc_ex)
 		fec_ptp_init(pdev);
@@ -3473,8 +3482,10 @@ failed_init:
 	fec_ptp_stop(pdev);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
+failed_reset:
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 failed_regulator:
-	clk_disable_unprepare(fep->clk_ipg);
 failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index f60845f0c6ca..4aefe2438969 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -59,6 +59,7 @@
 #define DMA_OFFSET		0x000C2000
 #define FPM_OFFSET		0x000C3000
 #define IMEM_OFFSET		0x000C4000
+#define HWP_OFFSET		0x000C7000
 #define CGP_OFFSET		0x000DB000
 
 /* Exceptions bit map */
@@ -218,6 +219,9 @@
 
 #define QMI_GS_HALT_NOT_BUSY		0x00000002
 
+/* HWP defines */
+#define HWP_RPIMAC_PEN			0x00000001
+
 /* IRAM defines */
 #define IRAM_IADD_AIE			0x80000000
 #define IRAM_READY			0x80000000
@@ -475,6 +479,12 @@ struct fman_dma_regs {
 	u32 res00e0[0x400 - 56];
 };
 
+struct fman_hwp_regs {
+	u32 res0000[0x844 / 4];		/* 0x000..0x843 */
+	u32 fmprrpimac;	/* FM Parser Internal memory access control */
+	u32 res[(0x1000 - 0x848) / 4];	/* 0x848..0xFFF */
+};
+
 /* Structure that holds current FMan state.
  * Used for saving run time information.
  */
@@ -606,6 +616,7 @@ struct fman {
 	struct fman_bmi_regs __iomem *bmi_regs;
 	struct fman_qmi_regs __iomem *qmi_regs;
 	struct fman_dma_regs __iomem *dma_regs;
+	struct fman_hwp_regs __iomem *hwp_regs;
 	fman_exceptions_cb *exception_cb;
 	fman_bus_error_cb *bus_error_cb;
 	/* Spinlock for FMan use */
@@ -999,6 +1010,12 @@ static void qmi_init(struct fman_qmi_regs __iomem *qmi_rg,
 	iowrite32be(tmp_reg, &qmi_rg->fmqm_ien);
 }
 
+static void hwp_init(struct fman_hwp_regs __iomem *hwp_rg)
+{
+	/* enable HW Parser */
+	iowrite32be(HWP_RPIMAC_PEN, &hwp_rg->fmprrpimac);
+}
+
 static int enable(struct fman *fman, struct fman_cfg *cfg)
 {
 	u32 cfg_reg = 0;
@@ -1195,7 +1212,7 @@ static int fill_soc_specific_params(struct fman_state_struct *state)
 		state->max_num_of_open_dmas	= 32;
 		state->fm_port_num_of_cg	= 256;
 		state->num_of_rx_ports	= 6;
-		state->total_fifo_size	= 122 * 1024;
+		state->total_fifo_size	= 136 * 1024;
 		break;
 
 	case 2:
@@ -1793,6 +1810,7 @@ static int fman_config(struct fman *fman)
 	fman->bmi_regs = base_addr + BMI_OFFSET;
 	fman->qmi_regs = base_addr + QMI_OFFSET;
 	fman->dma_regs = base_addr + DMA_OFFSET;
+	fman->hwp_regs = base_addr + HWP_OFFSET;
 	fman->base_addr = base_addr;
 
 	spin_lock_init(&fman->spinlock);
@@ -2062,6 +2080,9 @@ static int fman_init(struct fman *fman)
 	/* Init QMI Registers */
 	qmi_init(fman->qmi_regs, fman->cfg);
 
+	/* Init HW Parser */
+	hwp_init(fman->hwp_regs);
+
 	err = enable(fman, cfg);
 	if (err != 0)
 		return err;
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index 57aae8d17d77..f53e1473dbcc 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -134,14 +134,14 @@ enum fman_exceptions {
 struct fman_prs_result {
 	u8 lpid;		/* Logical port id */
 	u8 shimr;		/* Shim header result  */
-	u16 l2r;		/* Layer 2 result */
-	u16 l3r;		/* Layer 3 result */
+	__be16 l2r;		/* Layer 2 result */
+	__be16 l3r;		/* Layer 3 result */
 	u8 l4r;		/* Layer 4 result */
 	u8 cplan;		/* Classification plan id */
-	u16 nxthdr;		/* Next Header  */
-	u16 cksum;		/* Running-sum */
+	__be16 nxthdr;		/* Next Header  */
+	__be16 cksum;		/* Running-sum */
 	/* Flags&fragment-offset field of the last IP-header */
-	u16 flags_frag_off;
+	__be16 flags_frag_off;
 	/* Routing type field of a IPV6 routing extension header */
 	u8 route_type;
 	/* Routing Extension Header Present; last bit is IP valid */
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 84ea130eed36..98bba10fc38c 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -381,6 +381,9 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg,
 
 	/* check RGMII support */
 	if (iface == PHY_INTERFACE_MODE_RGMII ||
+	    iface == PHY_INTERFACE_MODE_RGMII_ID ||
+	    iface == PHY_INTERFACE_MODE_RGMII_RXID ||
+	    iface == PHY_INTERFACE_MODE_RGMII_TXID ||
 	    iface == PHY_INTERFACE_MODE_RMII)
 		if (tmp & DTSEC_ID2_INT_REDUCED_OFF)
 			return -EINVAL;
@@ -390,7 +393,10 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg,
 		if (tmp & DTSEC_ID2_INT_REDUCED_OFF)
 			return -EINVAL;
 
-	is_rgmii = iface == PHY_INTERFACE_MODE_RGMII;
+	is_rgmii = iface == PHY_INTERFACE_MODE_RGMII ||
+		   iface == PHY_INTERFACE_MODE_RGMII_ID ||
+		   iface == PHY_INTERFACE_MODE_RGMII_RXID ||
+		   iface == PHY_INTERFACE_MODE_RGMII_TXID;
 	is_sgmii = iface == PHY_INTERFACE_MODE_SGMII;
 	is_qsgmii = iface == PHY_INTERFACE_MODE_QSGMII;
 
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index cd6a53eaf161..c0296880feba 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -443,7 +443,10 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg,
 		break;
 	default:
 		tmp |= IF_MODE_GMII;
-		if (phy_if == PHY_INTERFACE_MODE_RGMII)
+		if (phy_if == PHY_INTERFACE_MODE_RGMII ||
+		    phy_if == PHY_INTERFACE_MODE_RGMII_ID ||
+		    phy_if == PHY_INTERFACE_MODE_RGMII_RXID ||
+		    phy_if == PHY_INTERFACE_MODE_RGMII_TXID)
 			tmp |= IF_MODE_RGMII | IF_MODE_RGMII_AUTO;
 	}
 	iowrite32be(tmp, &regs->if_mode);
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h
index 173d8e0fd716..c4a66469a907 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.h
@@ -36,6 +36,7 @@
 #include "fman_mac.h"
 
 #include <linux/netdevice.h>
+#include <linux/phy_fixed.h>
 
 struct fman_mac *memac_config(struct fman_mac_params *params);
 int memac_set_promiscuous(struct fman_mac *memac, bool new_val);
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 9f3bb50a2365..57bf44fa16a1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -62,6 +62,7 @@
 
 #define BMI_PORT_REGS_OFFSET				0
 #define QMI_PORT_REGS_OFFSET				0x400
+#define HWP_PORT_REGS_OFFSET				0x800
 
 /* Default values */
 #define DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN		\
@@ -182,7 +183,7 @@
 #define NIA_ENG_BMI					0x00500000
 #define NIA_ENG_QMI_ENQ					0x00540000
 #define NIA_ENG_QMI_DEQ					0x00580000
-
+#define NIA_ENG_HWP					0x00440000
 #define NIA_BMI_AC_ENQ_FRAME				0x00000002
 #define NIA_BMI_AC_TX_RELEASE				0x000002C0
 #define NIA_BMI_AC_RELEASE				0x000000C0
@@ -317,6 +318,19 @@ struct fman_port_qmi_regs {
 	u32 fmqm_pndcc;		/* PortID n Dequeue Confirm Counter */
 };
 
+#define HWP_HXS_COUNT 16
+#define HWP_HXS_PHE_REPORT 0x00000800
+#define HWP_HXS_PCAC_PSTAT 0x00000100
+#define HWP_HXS_PCAC_PSTOP 0x00000001
+struct fman_port_hwp_regs {
+	struct {
+		u32 ssa; /* Soft Sequence Attachment */
+		u32 lcv; /* Line-up Enable Confirmation Mask */
+	} pmda[HWP_HXS_COUNT]; /* Parse Memory Direct Access Registers */
+	u32 reserved080[(0x3f8 - 0x080) / 4]; /* (0x080-0x3f7) */
+	u32 fmpr_pcac; /* Configuration Access Control */
+};
+
 /* QMI dequeue prefetch modes */
 enum fman_port_deq_prefetch {
 	FMAN_PORT_DEQ_NO_PREFETCH, /* No prefetch mode */
@@ -436,6 +450,7 @@ struct fman_port {
 
 	union fman_port_bmi_regs __iomem *bmi_regs;
 	struct fman_port_qmi_regs __iomem *qmi_regs;
+	struct fman_port_hwp_regs __iomem *hwp_regs;
 
 	struct fman_sp_buffer_offsets buffer_offsets;
 
@@ -521,9 +536,12 @@ static int init_bmi_rx(struct fman_port *port)
 	/* NIA */
 	tmp = (u32)cfg->rx_fd_bits << BMI_NEXT_ENG_FD_BITS_SHIFT;
 
-	tmp |= NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME;
+	tmp |= NIA_ENG_HWP;
 	iowrite32be(tmp, &regs->fmbm_rfne);
 
+	/* Parser Next Engine NIA */
+	iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME, &regs->fmbm_rfpne);
+
 	/* Enqueue NIA */
 	iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, &regs->fmbm_rfene);
 
@@ -665,6 +683,50 @@ static int init_qmi(struct fman_port *port)
 	return 0;
 }
 
+static void stop_port_hwp(struct fman_port *port)
+{
+	struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+	int cnt = 100;
+
+	iowrite32be(HWP_HXS_PCAC_PSTOP, &regs->fmpr_pcac);
+
+	while (cnt-- > 0 &&
+	       (ioread32be(&regs->fmpr_pcac) & HWP_HXS_PCAC_PSTAT))
+		udelay(10);
+	if (!cnt)
+		pr_err("Timeout stopping HW Parser\n");
+}
+
+static void start_port_hwp(struct fman_port *port)
+{
+	struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+	int cnt = 100;
+
+	iowrite32be(0, &regs->fmpr_pcac);
+
+	while (cnt-- > 0 &&
+	       !(ioread32be(&regs->fmpr_pcac) & HWP_HXS_PCAC_PSTAT))
+		udelay(10);
+	if (!cnt)
+		pr_err("Timeout starting HW Parser\n");
+}
+
+static void init_hwp(struct fman_port *port)
+{
+	struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+	int i;
+
+	stop_port_hwp(port);
+
+	for (i = 0; i < HWP_HXS_COUNT; i++) {
+		/* enable HXS error reporting into FD[STATUS] PHE */
+		iowrite32be(0x00000000, &regs->pmda[i].ssa);
+		iowrite32be(0xffffffff, &regs->pmda[i].lcv);
+	}
+
+	start_port_hwp(port);
+}
+
 static int init(struct fman_port *port)
 {
 	int err;
@@ -673,6 +735,8 @@ static int init(struct fman_port *port)
 	switch (port->port_type) {
 	case FMAN_PORT_TYPE_RX:
 		err = init_bmi_rx(port);
+		if (!err)
+			init_hwp(port);
 		break;
 	case FMAN_PORT_TYPE_TX:
 		err = init_bmi_tx(port);
@@ -686,7 +750,8 @@ static int init(struct fman_port *port)
 
 	/* Init QMI registers */
 	err = init_qmi(port);
-	return err;
+	if (err)
+		return err;
 
 	return 0;
 }
@@ -1247,7 +1312,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 	/* Allocate the FM driver's parameters structure */
 	port->cfg = kzalloc(sizeof(*port->cfg), GFP_KERNEL);
 	if (!port->cfg)
-		goto err_params;
+		return -EINVAL;
 
 	/* Initialize FM port parameters which will be kept by the driver */
 	port->port_type = port->dts_params.type;
@@ -1276,6 +1341,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 	/* set memory map pointers */
 	port->bmi_regs = base_addr + BMI_PORT_REGS_OFFSET;
 	port->qmi_regs = base_addr + QMI_PORT_REGS_OFFSET;
+	port->hwp_regs = base_addr + HWP_PORT_REGS_OFFSET;
 
 	port->max_frame_length = DFLT_PORT_MAX_FRAME_LENGTH;
 	/* resource distribution. */
@@ -1327,8 +1393,6 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 
 err_port_cfg:
 	kfree(port->cfg);
-err_params:
-	kfree(port);
 	return -EINVAL;
 }
 EXPORT_SYMBOL(fman_port_config);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index db9c0bcf54cd..1fc27c97e3b2 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -38,12 +38,6 @@
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_8xx
-#include <asm/8xx_immap.h>
-#include <asm/pgtable.h>
-#include <asm/cpm1.h>
-#endif
-
 #include "fs_enet.h"
 #include "fec.h"
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 96d44cf44fe0..64300ac13e02 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -37,12 +37,6 @@
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_8xx
-#include <asm/8xx_immap.h>
-#include <asm/pgtable.h>
-#include <asm/cpm1.h>
-#endif
-
 #include "fs_enet.h"
 
 /*************************************************/
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index b6ed818f78ff..9d9b6e6dd988 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -9,9 +9,9 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
-
 #include "hnae.h"
 
 #define cls_to_ae_dev(dev) container_of(dev, struct hnae_ae_dev, cls_dev)
@@ -57,11 +57,15 @@ static int hnae_alloc_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
 
 static void hnae_free_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
 {
+	if (unlikely(!cb->priv))
+		return;
+
 	if (cb->type == DESC_TYPE_SKB)
 		dev_kfree_skb_any((struct sk_buff *)cb->priv);
 	else if (unlikely(is_rx_ring(ring)))
 		put_page((struct page *)cb->priv);
-	memset(cb, 0, sizeof(*cb));
+
+	cb->priv = NULL;
 }
 
 static int hnae_map_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
@@ -197,6 +201,7 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
 
 	ring->q = q;
 	ring->flags = flags;
+	spin_lock_init(&ring->lock);
 	assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
 
 	/* not matter for tx or rx ring, the ntc and ntc start from 0 */
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 8016854796fb..04211ac73b36 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -67,6 +67,8 @@ do { \
 #define AE_IS_VER1(ver) ((ver) == AE_VERSION_1)
 #define AE_NAME_SIZE 16
 
+#define BD_SIZE_2048_MAX_MTU   6000
+
 /* some said the RX and TX RCB format should not be the same in the future. But
  * it is the same now...
  */
@@ -101,7 +103,6 @@ enum hnae_led_state {
 #define HNS_RX_FLAG_L4ID_TCP 0x1
 #define HNS_RX_FLAG_L4ID_SCTP 0x3
 
-
 #define HNS_TXD_ASID_S 0
 #define HNS_TXD_ASID_M (0xff << HNS_TXD_ASID_S)
 #define HNS_TXD_BUFNUM_S 8
@@ -273,6 +274,9 @@ struct hnae_ring {
 	/* statistic */
 	struct ring_stats stats;
 
+	/* ring lock for poll one */
+	spinlock_t lock;
+
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
@@ -483,11 +487,11 @@ struct hnae_ae_ops {
 			      u32 auto_neg, u32 rx_en, u32 tx_en);
 	void (*get_coalesce_usecs)(struct hnae_handle *handle,
 				   u32 *tx_usecs, u32 *rx_usecs);
-	void (*get_rx_max_coalesced_frames)(struct hnae_handle *handle,
-					    u32 *tx_frames, u32 *rx_frames);
+	void (*get_max_coalesced_frames)(struct hnae_handle *handle,
+					 u32 *tx_frames, u32 *rx_frames);
 	int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout);
 	int (*set_coalesce_frames)(struct hnae_handle *handle,
-				   u32 coalesce_frames);
+				   u32 tx_frames, u32 rx_frames);
 	void (*get_coalesce_range)(struct hnae_handle *handle,
 				   u32 *tx_frames_low, u32 *rx_frames_low,
 				   u32 *tx_frames_high, u32 *rx_frames_high,
@@ -646,6 +650,41 @@ static inline void hnae_reuse_buffer(struct hnae_ring *ring, int i)
 	ring->desc[i].rx.ipoff_bnum_pid_flag = 0;
 }
 
+/* when reinit buffer size, we should reinit buffer description */
+static inline void hnae_reinit_all_ring_desc(struct hnae_handle *h)
+{
+	int i, j;
+	struct hnae_ring *ring;
+
+	for (i = 0; i < h->q_num; i++) {
+		ring = &h->qs[i]->rx_ring;
+		for (j = 0; j < ring->desc_num; j++)
+			ring->desc[j].addr = cpu_to_le64(ring->desc_cb[j].dma);
+	}
+
+	wmb();	/* commit all data before submit */
+}
+
+/* when reinit buffer size, we should reinit page offset */
+static inline void hnae_reinit_all_ring_page_off(struct hnae_handle *h)
+{
+	int i, j;
+	struct hnae_ring *ring;
+
+	for (i = 0; i < h->q_num; i++) {
+		ring = &h->qs[i]->rx_ring;
+		for (j = 0; j < ring->desc_num; j++) {
+			ring->desc_cb[j].page_offset = 0;
+			if (ring->desc[j].addr !=
+			    cpu_to_le64(ring->desc_cb[j].dma))
+				ring->desc[j].addr =
+					cpu_to_le64(ring->desc_cb[j].dma);
+		}
+	}
+
+	wmb();	/* commit all data before submit */
+}
+
 #define hnae_set_field(origin, mask, shift, val) \
 	do { \
 		(origin) &= (~(mask)); \
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index 0a9cdf00b31a..ff864a187d5a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -267,8 +267,32 @@ static int hns_ae_clr_multicast(struct hnae_handle *handle)
 static int hns_ae_set_mtu(struct hnae_handle *handle, int new_mtu)
 {
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+	struct hnae_queue *q;
+	u32 rx_buf_size;
+	int i, ret;
+
+	/* when buf_size is 2048, max mtu is 6K for rx ring max bd num is 3. */
+	if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) {
+		if (new_mtu <= BD_SIZE_2048_MAX_MTU)
+			rx_buf_size = 2048;
+		else
+			rx_buf_size = 4096;
+	} else {
+		rx_buf_size = mac_cb->dsaf_dev->buf_size;
+	}
+
+	ret = hns_mac_set_mtu(mac_cb, new_mtu, rx_buf_size);
 
-	return hns_mac_set_mtu(mac_cb, new_mtu);
+	if (!ret) {
+		/* reinit ring buf_size */
+		for (i = 0; i < handle->q_num; i++) {
+			q = handle->qs[i];
+			q->rx_ring.buf_size = rx_buf_size;
+			hns_rcb_set_rx_ring_bs(q, rx_buf_size);
+		}
+	}
+
+	return ret;
 }
 
 static void hns_ae_set_tso_stats(struct hnae_handle *handle, int enable)
@@ -463,15 +487,21 @@ static void hns_ae_get_coalesce_usecs(struct hnae_handle *handle,
 					       ring_pair->port_id_in_comm);
 }
 
-static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle,
-					       u32 *tx_frames, u32 *rx_frames)
+static void hns_ae_get_max_coalesced_frames(struct hnae_handle *handle,
+					    u32 *tx_frames, u32 *rx_frames)
 {
 	struct ring_pair_cb *ring_pair =
 		container_of(handle->qs[0], struct ring_pair_cb, q);
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
-	*tx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common,
-						  ring_pair->port_id_in_comm);
-	*rx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common,
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    handle->port_type == HNAE_PORT_DEBUG)
+		*tx_frames = hns_rcb_get_rx_coalesced_frames(
+			ring_pair->rcb_common, ring_pair->port_id_in_comm);
+	else
+		*tx_frames = hns_rcb_get_tx_coalesced_frames(
+			ring_pair->rcb_common, ring_pair->port_id_in_comm);
+	*rx_frames = hns_rcb_get_rx_coalesced_frames(ring_pair->rcb_common,
 						  ring_pair->port_id_in_comm);
 }
 
@@ -485,15 +515,34 @@ static int hns_ae_set_coalesce_usecs(struct hnae_handle *handle,
 		ring_pair->rcb_common, ring_pair->port_id_in_comm, timeout);
 }
 
-static int  hns_ae_set_coalesce_frames(struct hnae_handle *handle,
-				       u32 coalesce_frames)
+static int hns_ae_set_coalesce_frames(struct hnae_handle *handle,
+				      u32 tx_frames, u32 rx_frames)
 {
+	int ret;
 	struct ring_pair_cb *ring_pair =
 		container_of(handle->qs[0], struct ring_pair_cb, q);
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
-	return hns_rcb_set_coalesced_frames(
-		ring_pair->rcb_common,
-		ring_pair->port_id_in_comm, coalesce_frames);
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    handle->port_type == HNAE_PORT_DEBUG) {
+		if (tx_frames != rx_frames)
+			return -EINVAL;
+		return hns_rcb_set_rx_coalesced_frames(
+			ring_pair->rcb_common,
+			ring_pair->port_id_in_comm, rx_frames);
+	} else {
+		if (tx_frames != 1)
+			return -EINVAL;
+		ret = hns_rcb_set_tx_coalesced_frames(
+			ring_pair->rcb_common,
+			ring_pair->port_id_in_comm, tx_frames);
+		if (ret)
+			return ret;
+
+		return hns_rcb_set_rx_coalesced_frames(
+			ring_pair->rcb_common,
+			ring_pair->port_id_in_comm, rx_frames);
+	}
 }
 
 static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
@@ -504,20 +553,27 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
 {
 	struct dsaf_device *dsaf_dev;
 
+	assert(handle);
+
 	dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
-	*tx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
-	*rx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
-	*tx_frames_high =
-		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
-		HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
-	*rx_frames_high =
-		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
-		 HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
-	*tx_usecs_low   = 0;
-	*rx_usecs_low   = 0;
-	*tx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
-	*rx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
+	*tx_frames_low  = HNS_RCB_TX_FRAMES_LOW;
+	*rx_frames_low  = HNS_RCB_RX_FRAMES_LOW;
+
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    handle->port_type == HNAE_PORT_DEBUG)
+		*tx_frames_high =
+			(dsaf_dev->desc_num - 1 > HNS_RCB_TX_FRAMES_HIGH) ?
+			HNS_RCB_TX_FRAMES_HIGH : dsaf_dev->desc_num - 1;
+	else
+		*tx_frames_high = 1;
+
+	*rx_frames_high = (dsaf_dev->desc_num - 1 > HNS_RCB_RX_FRAMES_HIGH) ?
+		HNS_RCB_RX_FRAMES_HIGH : dsaf_dev->desc_num - 1;
+	*tx_usecs_low   = HNS_RCB_TX_USECS_LOW;
+	*rx_usecs_low   = HNS_RCB_RX_USECS_LOW;
+	*tx_usecs_high  = HNS_RCB_TX_USECS_HIGH;
+	*rx_usecs_high  = HNS_RCB_RX_USECS_HIGH;
 }
 
 void hns_ae_update_stats(struct hnae_handle *handle,
@@ -802,8 +858,9 @@ static int hns_ae_get_rss(struct hnae_handle *handle, u32 *indir, u8 *key,
 		memcpy(key, ppe_cb->rss_key, HNS_PPEV2_RSS_KEY_SIZE);
 
 	/* update the current hash->queue mappings from the shadow RSS table */
-	memcpy(indir, ppe_cb->rss_indir_table,
-	       HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
+	if (indir)
+		memcpy(indir, ppe_cb->rss_indir_table,
+		       HNS_PPEV2_RSS_IND_TBL_SIZE  * sizeof(*indir));
 
 	return 0;
 }
@@ -814,15 +871,19 @@ static int hns_ae_set_rss(struct hnae_handle *handle, const u32 *indir,
 	struct hns_ppe_cb *ppe_cb = hns_get_ppe_cb(handle);
 
 	/* set the RSS Hash Key if specififed by the user */
-	if (key)
-		hns_ppe_set_rss_key(ppe_cb, (u32 *)key);
+	if (key) {
+		memcpy(ppe_cb->rss_key, key, HNS_PPEV2_RSS_KEY_SIZE);
+		hns_ppe_set_rss_key(ppe_cb, ppe_cb->rss_key);
+	}
 
-	/* update the shadow RSS table with user specified qids */
-	memcpy(ppe_cb->rss_indir_table, indir,
-	       HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
+	if (indir) {
+		/* update the shadow RSS table with user specified qids */
+		memcpy(ppe_cb->rss_indir_table, indir,
+		       HNS_PPEV2_RSS_IND_TBL_SIZE  * sizeof(*indir));
 
-	/* now update the hardware */
-	hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table);
+		/* now update the hardware */
+		hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table);
+	}
 
 	return 0;
 }
@@ -846,7 +907,7 @@ static struct hnae_ae_ops hns_dsaf_ops = {
 	.get_autoneg = hns_ae_get_autoneg,
 	.set_pauseparam = hns_ae_set_pauseparam,
 	.get_coalesce_usecs = hns_ae_get_coalesce_usecs,
-	.get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames,
+	.get_max_coalesced_frames = hns_ae_get_max_coalesced_frames,
 	.set_coalesce_usecs = hns_ae_set_coalesce_usecs,
 	.set_coalesce_frames = hns_ae_set_coalesce_frames,
 	.get_coalesce_range = hns_ae_get_coalesce_range,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 3382441fe7b5..86944bc3b273 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -86,12 +86,11 @@ static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode)
 		dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 0);
 }
 
-/**
-*hns_gmac_get_en - get port enable
-*@mac_drv:mac device
-*@rx:rx enable
-*@tx:tx enable
-*/
+/* hns_gmac_get_en - get port enable
+ * @mac_drv:mac device
+ * @rx:rx enable
+ * @tx:tx enable
+ */
 static void hns_gmac_get_en(void *mac_drv, u32 *rx, u32 *tx)
 {
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
@@ -148,6 +147,17 @@ static void hns_gmac_config_max_frame_length(void *mac_drv, u16 newval)
 			   GMAC_MAX_FRM_SIZE_S, newval);
 }
 
+static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval)
+{
+	u32 tx_ctrl;
+	struct mac_driver *drv = (struct mac_driver *)mac_drv;
+
+	tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
+	dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval);
+	dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval);
+	dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
+}
+
 static void hns_gmac_config_an_mode(void *mac_drv, u8 newval)
 {
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
@@ -250,7 +260,6 @@ static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en,
 static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed,
 				u32 full_duplex)
 {
-	u32 tx_ctrl;
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
 
 	dsaf_set_dev_bit(drv, GMAC_DUPLEX_TYPE_REG,
@@ -279,14 +288,6 @@ static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed,
 		return -EINVAL;
 	}
 
-	tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, 1);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, 1);
-	dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
-
-	dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG,
-			 GMAC_MODE_CHANGE_EB_B, 1);
-
 	return 0;
 }
 
@@ -325,6 +326,17 @@ static void hns_gmac_init(void *mac_drv)
 	hns_gmac_tx_loop_pkt_dis(mac_drv);
 	if (drv->mac_cb->mac_type == HNAE_PORT_DEBUG)
 		hns_gmac_set_uc_match(mac_drv, 0);
+
+	hns_gmac_config_pad_and_crc(mac_drv, 1);
+
+	dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG,
+			 GMAC_MODE_CHANGE_EB_B, 1);
+
+	/* reduce gmac tx water line to avoid gmac hang-up
+	 * in speed 100M and duplex half.
+	 */
+	dsaf_set_dev_field(drv, GMAC_TX_WATER_LINE_REG, GMAC_TX_WATER_LINE_MASK,
+			   GMAC_TX_WATER_LINE_SHIFT, 8);
 }
 
 void hns_gmac_update_stats(void *mac_drv)
@@ -453,24 +465,6 @@ static int hns_gmac_config_loopback(void *mac_drv, enum hnae_loop loop_mode,
 	return 0;
 }
 
-static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval)
-{
-	u32 tx_ctrl;
-	struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
-	tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval);
-	dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
-}
-
-static void hns_gmac_get_id(void *mac_drv, u8 *mac_id)
-{
-	struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
-	*mac_id = drv->mac_id;
-}
-
 static void hns_gmac_get_info(void *mac_drv, struct mac_info *mac_info)
 {
 	enum hns_gmac_duplex_mdoe duplex;
@@ -672,7 +666,7 @@ static void hns_gmac_get_strings(u32 stringset, u8 *data)
 
 static int hns_gmac_get_sset_count(int stringset)
 {
-	if (stringset == ETH_SS_STATS)
+	if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS)
 		return ARRAY_SIZE(g_gmac_stats_string);
 
 	return 0;
@@ -712,7 +706,6 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
 	mac_drv->config_pad_and_crc = hns_gmac_config_pad_and_crc;
 	mac_drv->config_half_duplex = hns_gmac_set_duplex_type;
 	mac_drv->set_rx_ignore_pause_frames = hns_gmac_set_rx_auto_pause_frames;
-	mac_drv->mac_get_id = hns_gmac_get_id;
 	mac_drv->get_info = hns_gmac_get_info;
 	mac_drv->autoneg_stat = hns_gmac_autoneg_stat;
 	mac_drv->get_pause_enable = hns_gmac_get_pausefrm_cfg;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 3239d27143b9..8b5cdf490850 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -82,9 +82,12 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status)
 	else
 		*link_status = 0;
 
-	ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt);
-	if (!ret)
-		*link_status = *link_status && sfp_prsnt;
+	if (mac_cb->media_type == HNAE_MEDIA_TYPE_FIBER) {
+		ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb,
+							       &sfp_prsnt);
+		if (!ret)
+			*link_status = *link_status && sfp_prsnt;
+	}
 
 	mac_cb->link = *link_status;
 }
@@ -332,44 +335,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
 	return 0;
 }
 
-/**
- *hns_mac_del_mac - delete mac address into dsaf table,can't delete the same
- *                  address twice
- *@net_dev: net device
- *@vfn :   vf lan
- *@mac : mac address
- *return status
- */
-int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac)
-{
-	struct mac_entry_idx *old_mac;
-	struct dsaf_device *dsaf_dev;
-	u32 ret;
-
-	dsaf_dev = mac_cb->dsaf_dev;
-
-	if (vfn < DSAF_MAX_VM_NUM) {
-		old_mac = &mac_cb->addr_entry_idx[vfn];
-	} else {
-		dev_err(mac_cb->dev,
-			"vf queue is too large, %s mac%d queue = %#x!\n",
-			mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vfn);
-		return -EINVAL;
-	}
-
-	if (dsaf_dev) {
-		ret = hns_dsaf_del_mac_entry(dsaf_dev, old_mac->vlan_id,
-					     mac_cb->mac_id, old_mac->addr);
-		if (ret)
-			return ret;
-
-		if (memcmp(old_mac->addr, mac, sizeof(old_mac->addr)) == 0)
-			old_mac->valid = 0;
-	}
-
-	return 0;
-}
-
 int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
 {
 	struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
@@ -491,10 +456,9 @@ void hns_mac_reset(struct hns_mac_cb *mac_cb)
 	}
 }
 
-int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu)
+int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size)
 {
 	struct mac_driver *drv = hns_mac_get_drv(mac_cb);
-	u32 buf_size = mac_cb->dsaf_dev->buf_size;
 	u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ?
 			MAC_MAX_MTU : MAC_MAX_MTU_V2;
@@ -732,6 +696,8 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 	rc = phy_device_register(phy);
 	if (rc) {
 		phy_device_free(phy);
+		dev_err(&mdio->dev, "registered phy fail at address %i\n",
+			addr);
 		return -ENODEV;
 	}
 
@@ -742,7 +708,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 	return 0;
 }
 
-static void hns_mac_register_phy(struct hns_mac_cb *mac_cb)
+static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 {
 	struct acpi_reference_args args;
 	struct platform_device *pdev;
@@ -752,24 +718,39 @@ static void hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 
 	/* Loop over the child nodes and register a phy_device for each one */
 	if (!to_acpi_device_node(mac_cb->fw_port))
-		return;
+		return -ENODEV;
 
 	rc = acpi_node_get_property_reference(
 			mac_cb->fw_port, "mdio-node", 0, &args);
 	if (rc)
-		return;
+		return rc;
 
 	addr = hns_mac_phy_parse_addr(mac_cb->dev, mac_cb->fw_port);
 	if (addr < 0)
-		return;
+		return addr;
 
 	/* dev address in adev */
 	pdev = hns_dsaf_find_platform_device(acpi_fwnode_handle(args.adev));
+	if (!pdev) {
+		dev_err(mac_cb->dev, "mac%d mdio pdev is NULL\n",
+			mac_cb->mac_id);
+		return  -EINVAL;
+	}
+
 	mii_bus = platform_get_drvdata(pdev);
+	if (!mii_bus) {
+		dev_err(mac_cb->dev,
+			"mac%d mdio is NULL, dsaf will probe again later\n",
+			mac_cb->mac_id);
+		return -EPROBE_DEFER;
+	}
+
 	rc = hns_mac_register_phydev(mii_bus, mac_cb, addr);
 	if (!rc)
 		dev_dbg(mac_cb->dev, "mac%d register phy addr:%d\n",
 			mac_cb->mac_id, addr);
+
+	return rc;
 }
 
 #define MAC_MEDIA_TYPE_MAX_LEN		16
@@ -790,7 +771,7 @@ static const struct {
  *@np:device node
  * return: 0 --success, negative --fail
  */
-static int  hns_mac_get_info(struct hns_mac_cb *mac_cb)
+static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
 {
 	struct device_node *np;
 	struct regmap *syscon;
@@ -855,7 +836,7 @@ static int  hns_mac_get_info(struct hns_mac_cb *mac_cb)
 		of_node_put(np);
 
 		np = of_parse_phandle(to_of_node(mac_cb->fw_port),
-					"serdes-syscon", 0);
+				      "serdes-syscon", 0);
 		syscon = syscon_node_to_regmap(np);
 		of_node_put(np);
 		if (IS_ERR_OR_NULL(syscon)) {
@@ -900,7 +881,15 @@ static int  hns_mac_get_info(struct hns_mac_cb *mac_cb)
 			}
 		}
 	} else if (is_acpi_node(mac_cb->fw_port)) {
-		hns_mac_register_phy(mac_cb);
+		ret = hns_mac_register_phy(mac_cb);
+		/*
+		 * Mac can work well if there is phy or not.If the port don't
+		 * connect with phy, the return value will be ignored. Only
+		 * when there is phy but can't find mdio bus, the return value
+		 * will be handled.
+		 */
+		if (ret == -EPROBE_DEFER)
+			return ret;
 	} else {
 		dev_err(mac_cb->dev, "mac%d cannot find phy node\n",
 			mac_cb->mac_id);
@@ -1062,6 +1051,7 @@ int hns_mac_init(struct dsaf_device *dsaf_dev)
 			dsaf_dev->mac_cb[port_id] = mac_cb;
 		}
 	}
+
 	/* init mac_cb for all port */
 	for (port_id = 0; port_id < max_port_num; port_id++) {
 		mac_cb = dsaf_dev->mac_cb[port_id];
@@ -1071,6 +1061,7 @@ int hns_mac_init(struct dsaf_device *dsaf_dev)
 		ret = hns_mac_get_cfg(dsaf_dev, mac_cb);
 		if (ret)
 			return ret;
+
 		ret = hns_mac_init_ex(mac_cb);
 		if (ret)
 			return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index 2bb3d1e93c64..24dfba53a0f2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -373,8 +373,6 @@ struct mac_driver {
 	void (*set_rx_ignore_pause_frames)(void *mac_drv, u32 enable);
 	/* config rx mode for promiscuous*/
 	void (*set_promiscuous)(void *mac_drv, u8 enable);
-	/* get mac id */
-	void (*mac_get_id)(void *mac_drv, u8 *mac_id);
 	void (*mac_pausefrm_cfg)(void *mac_drv, u32 rx_en, u32 tx_en);
 
 	void (*autoneg_stat)(void *mac_drv, u32 *enable);
@@ -436,7 +434,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
 int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable);
 void hns_mac_start(struct hns_mac_cb *mac_cb);
 void hns_mac_stop(struct hns_mac_cb *mac_cb);
-int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac);
 void hns_mac_uninit(struct dsaf_device *dsaf_dev);
 void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex);
 void hns_mac_reset(struct hns_mac_cb *mac_cb);
@@ -444,7 +441,7 @@ void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg);
 void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en);
 int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable);
 int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en);
-int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu);
+int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size);
 int hns_mac_get_port_info(struct hns_mac_cb *mac_cb,
 			  u8 *auto_neg, u16 *speed, u8 *duplex);
 int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 90dbda792614..e0bc79ea3d88 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -510,10 +510,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 48);
+			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 55);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 80);
+			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 110);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 
 		/* for no enable pfc mode */
@@ -521,10 +521,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 192);
+			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 128);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 240);
+			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 192);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 	}
 
@@ -1519,6 +1519,7 @@ static void hns_dsaf_set_mac_key(
 	mac_key->high.bits.mac_3 = addr[3];
 	mac_key->low.bits.mac_4 = addr[4];
 	mac_key->low.bits.mac_5 = addr[5];
+	mac_key->low.bits.port_vlan = 0;
 	dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M,
 		       DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
 	dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
@@ -1647,87 +1648,6 @@ int hns_dsaf_rm_mac_addr(
 				      mac_entry->addr);
 }
 
-/**
- * hns_dsaf_set_mac_mc_entry - set mac mc-entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mc-mac entry
- */
-int hns_dsaf_set_mac_mc_entry(
-	struct dsaf_device *dsaf_dev,
-	struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
-	u16 entry_index = DSAF_INVALID_ENTRY_IDX;
-	struct dsaf_drv_tbl_tcam_key mac_key;
-	struct dsaf_tbl_tcam_mcast_cfg mac_data;
-	struct dsaf_drv_priv *priv =
-	    (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
-	struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
-	struct dsaf_drv_tbl_tcam_key tmp_mac_key;
-	struct dsaf_tbl_tcam_data tcam_data;
-
-	/* mac addr check */
-	if (MAC_IS_ALL_ZEROS(mac_entry->addr)) {
-		dev_err(dsaf_dev->dev, "set uc %s Mac %pM err!\n",
-			dsaf_dev->ae_dev.name, mac_entry->addr);
-		return -EINVAL;
-	}
-
-	/*config key */
-	hns_dsaf_set_mac_key(dsaf_dev, &mac_key,
-			     mac_entry->in_vlan_id,
-			     mac_entry->in_port_num, mac_entry->addr);
-
-	/* entry ie exist? */
-	entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
-	if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-		/*if hasnot, find enpty entry*/
-		entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev);
-		if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-			/*if hasnot empty, error*/
-			dev_err(dsaf_dev->dev,
-				"set_uc_entry failed, %s Mac key(%#x:%#x)\n",
-				dsaf_dev->ae_dev.name,
-				mac_key.high.val, mac_key.low.val);
-			return -EINVAL;
-		}
-
-		/* config hardware entry */
-		memset(mac_data.tbl_mcast_port_msk,
-		       0, sizeof(mac_data.tbl_mcast_port_msk));
-	} else {
-		/* config hardware entry */
-		hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
-				     &mac_data);
-
-		tmp_mac_key.high.val =
-			le32_to_cpu(tcam_data.tbl_tcam_data_high);
-		tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-	}
-	mac_data.tbl_mcast_old_en = 0;
-	mac_data.tbl_mcast_item_vld = 1;
-	dsaf_set_field(mac_data.tbl_mcast_port_msk[0],
-		       0x3F, 0, mac_entry->port_mask[0]);
-
-	dev_dbg(dsaf_dev->dev,
-		"set_uc_entry, %s key(%#x:%#x) entry_index%d\n",
-		dsaf_dev->ae_dev.name, mac_key.high.val,
-		mac_key.low.val, entry_index);
-
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
-
-	hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, NULL,
-			     &mac_data);
-
-	/* config software entry */
-	soft_mac_entry += entry_index;
-	soft_mac_entry->index = entry_index;
-	soft_mac_entry->tcam_key.high.val = mac_key.high.val;
-	soft_mac_entry->tcam_key.low.val = mac_key.low.val;
-
-	return 0;
-}
-
 static void hns_dsaf_mc_mask_bit_clear(char *dst, const char *src)
 {
 	u16 *a = (u16 *)dst;
@@ -2089,166 +2009,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id,
 	return ret;
 }
 
-/**
- * hns_dsaf_get_mac_uc_entry - get mac uc entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_single_dest_entry *mac_entry)
-{
-	u16 entry_index = DSAF_INVALID_ENTRY_IDX;
-	struct dsaf_drv_tbl_tcam_key mac_key;
-
-	struct dsaf_tbl_tcam_ucast_cfg mac_data;
-	struct dsaf_tbl_tcam_data tcam_data;
-
-	/* check macaddr */
-	if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
-	    MAC_IS_BROADCAST(mac_entry->addr)) {
-		dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n",
-			mac_entry->addr);
-		return -EINVAL;
-	}
-
-	/*config key */
-	hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
-			     mac_entry->in_port_num, mac_entry->addr);
-
-	/*check exist? */
-	entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
-	if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-		/*find none, error */
-		dev_err(dsaf_dev->dev,
-			"get_uc_entry failed, %s Mac key(%#x:%#x)\n",
-			dsaf_dev->ae_dev.name,
-			mac_key.high.val, mac_key.low.val);
-		return -EINVAL;
-	}
-	dev_dbg(dsaf_dev->dev,
-		"get_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
-		dsaf_dev->ae_dev.name, mac_key.high.val,
-		mac_key.low.val, entry_index);
-
-	/* read entry */
-	hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
-	mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-	mac_entry->port_num = mac_data.tbl_ucast_out_port;
-
-	return 0;
-}
-
-/**
- * hns_dsaf_get_mac_mc_entry - get mac mc entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
-	u16 entry_index = DSAF_INVALID_ENTRY_IDX;
-	struct dsaf_drv_tbl_tcam_key mac_key;
-
-	struct dsaf_tbl_tcam_mcast_cfg mac_data;
-	struct dsaf_tbl_tcam_data tcam_data;
-
-	/*check mac addr */
-	if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
-	    MAC_IS_BROADCAST(mac_entry->addr)) {
-		dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n",
-			mac_entry->addr);
-		return -EINVAL;
-	}
-
-	/*config key */
-	hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
-			     mac_entry->in_port_num, mac_entry->addr);
-
-	/*check exist? */
-	entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
-	if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-		/* find none, error */
-		dev_err(dsaf_dev->dev,
-			"get_mac_uc_entry failed, %s Mac key(%#x:%#x)\n",
-			dsaf_dev->ae_dev.name, mac_key.high.val,
-			mac_key.low.val);
-		return -EINVAL;
-	}
-	dev_dbg(dsaf_dev->dev,
-		"get_mac_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
-		dsaf_dev->ae_dev.name, mac_key.high.val,
-		mac_key.low.val, entry_index);
-
-	/*read entry */
-	hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
-	mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-	mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
-	return 0;
-}
-
-/**
- * hns_dsaf_get_mac_entry_by_index - get mac entry by tab index
- * @dsaf_dev: dsa fabric device struct pointer
- * @entry_index: tab entry index
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_entry_by_index(
-	struct dsaf_device *dsaf_dev,
-	u16 entry_index, struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
-	struct dsaf_drv_tbl_tcam_key mac_key;
-
-	struct dsaf_tbl_tcam_mcast_cfg mac_data;
-	struct dsaf_tbl_tcam_ucast_cfg mac_uc_data;
-	struct dsaf_tbl_tcam_data tcam_data;
-	char mac_addr[ETH_ALEN] = {0};
-
-	if (entry_index >= dsaf_dev->tcam_max_num) {
-		/* find none, del error */
-		dev_err(dsaf_dev->dev, "get_uc_entry failed, %s\n",
-			dsaf_dev->ae_dev.name);
-		return -EINVAL;
-	}
-
-	/* mc entry, do read opt */
-	hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
-	mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-	mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
-
-	/***get mac addr*/
-	mac_addr[0] = mac_key.high.bits.mac_0;
-	mac_addr[1] = mac_key.high.bits.mac_1;
-	mac_addr[2] = mac_key.high.bits.mac_2;
-	mac_addr[3] = mac_key.high.bits.mac_3;
-	mac_addr[4] = mac_key.low.bits.mac_4;
-	mac_addr[5] = mac_key.low.bits.mac_5;
-	/**is mc or uc*/
-	if (MAC_IS_MULTICAST((u8 *)mac_addr) ||
-	    MAC_IS_L3_MULTICAST((u8 *)mac_addr)) {
-		/**mc donot do*/
-	} else {
-		/*is not mc, just uc... */
-		hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data,
-				     &mac_uc_data);
-
-		mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-		mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-		mac_entry->port_mask[0] = (1 << mac_uc_data.tbl_ucast_out_port);
-	}
-
-	return 0;
-}
-
 static struct dsaf_device *hns_dsaf_alloc_dev(struct device *dev,
 					      size_t sizeof_priv)
 {
@@ -2924,10 +2684,11 @@ void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev,
 	/* find the tcam entry index for promisc */
 	entry_index = dsaf_promisc_tcam_entry(port);
 
+	memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
+	memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
+
 	/* config key mask */
 	if (enable) {
-		memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
-		memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
 		dsaf_set_field(tbl_tcam_data.low.bits.port_vlan,
 			       DSAF_TBL_TCAM_KEY_PORT_M,
 			       DSAF_TBL_TCAM_KEY_PORT_S, port);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index cef6bf46ae93..4507e8222683 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -68,7 +68,7 @@ enum dsaf_roce_qos_sl {
 };
 
 #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
-#define HNS_DSAF_IS_DEBUG(dev) (dev->dsaf_mode == DSAF_MODE_DISABLE_SP)
+#define HNS_DSAF_IS_DEBUG(dev) ((dev)->dsaf_mode == DSAF_MODE_DISABLE_SP)
 
 enum hal_dsaf_mode {
 	HRD_DSAF_NO_DSAF_MODE	= 0x0,
@@ -429,23 +429,12 @@ static inline struct hnae_vf_cb *hns_ae_get_vf_cb(
 
 int hns_dsaf_set_mac_uc_entry(struct dsaf_device *dsaf_dev,
 			      struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_set_mac_mc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_multi_dest_entry *mac_entry);
 int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     struct dsaf_drv_mac_single_dest_entry *mac_entry);
 int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id,
 			   u8 in_port_num, u8 *addr);
 int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_multi_dest_entry *mac_entry);
-int hns_dsaf_get_mac_entry_by_index(
-	struct dsaf_device *dsaf_dev,
-	u16 entry_index,
-	struct dsaf_drv_mac_multi_dest_entry *mac_entry);
-
 void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb);
 
 int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev);
@@ -475,5 +464,4 @@ int hns_dsaf_rm_mac_addr(
 int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     u8 mac_id, u8 port_num);
 
-
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index a2c22d084ce9..e13aa064a8e9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -461,6 +461,32 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 	return 0;
 }
 
+int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+{
+	union acpi_object *obj;
+	union acpi_object obj_args, argv4;
+
+	obj_args.integer.type = ACPI_TYPE_INTEGER;
+	obj_args.integer.value = mac_cb->mac_id;
+
+	argv4.type = ACPI_TYPE_PACKAGE,
+	argv4.package.count = 1,
+	argv4.package.elements = &obj_args,
+
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
+				hns_dsaf_acpi_dsm_uuid, 0,
+				HNS_OP_GET_SFP_STAT_FUNC, &argv4);
+
+	if (!obj || obj->type != ACPI_TYPE_INTEGER)
+		return -ENODEV;
+
+	*sfp_prsnt = obj->integer.value;
+
+	ACPI_FREE(obj);
+
+	return 0;
+}
+
 /**
  * hns_mac_config_sds_loopback - set loop back for serdes
  * @mac_cb: mac control block
@@ -592,7 +618,7 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
 		misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi;
 
 		misc_op->get_phy_if = hns_mac_get_phy_if_acpi;
-		misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
+		misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi;
 
 		misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi;
 	} else {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 6ea872287307..b62816c1574e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -422,7 +422,7 @@ void hns_ppe_update_stats(struct hns_ppe_cb *ppe_cb)
 
 int hns_ppe_get_sset_count(int stringset)
 {
-	if (stringset == ETH_SS_STATS)
+	if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS)
 		return ETH_PPE_STATIC_NUM;
 	return 0;
 }
@@ -496,21 +496,23 @@ void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data)
  */
 int hns_ppe_init(struct dsaf_device *dsaf_dev)
 {
-	int i, k;
 	int ret;
+	int i;
 
 	for (i = 0; i < HNS_PPE_COM_NUM; i++) {
 		ret = hns_ppe_common_get_cfg(dsaf_dev, i);
 		if (ret)
-			goto get_ppe_cfg_fail;
+			goto get_cfg_fail;
 
 		ret = hns_rcb_common_get_cfg(dsaf_dev, i);
 		if (ret)
-			goto get_rcb_cfg_fail;
+			goto get_cfg_fail;
 
 		hns_ppe_get_cfg(dsaf_dev->ppe_common[i]);
 
-		hns_rcb_get_cfg(dsaf_dev->rcb_common[i]);
+		ret = hns_rcb_get_cfg(dsaf_dev->rcb_common[i]);
+		if (ret)
+			goto get_cfg_fail;
 	}
 
 	for (i = 0; i < HNS_PPE_COM_NUM; i++)
@@ -518,13 +520,12 @@ int hns_ppe_init(struct dsaf_device *dsaf_dev)
 
 	return 0;
 
-get_rcb_cfg_fail:
-	hns_ppe_common_free_cfg(dsaf_dev, i);
-get_ppe_cfg_fail:
-	for (k = i - 1; k >= 0; k--) {
-		hns_rcb_common_free_cfg(dsaf_dev, k);
-		hns_ppe_common_free_cfg(dsaf_dev, k);
+get_cfg_fail:
+	for (i = 0; i < HNS_PPE_COM_NUM; i++) {
+		hns_rcb_common_free_cfg(dsaf_dev, i);
+		hns_ppe_common_free_cfg(dsaf_dev, i);
 	}
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index f0ed80d6ef9c..6f3570cfb501 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -32,6 +32,9 @@
 #define RCB_RESET_WAIT_TIMES 30
 #define RCB_RESET_TRY_TIMES 10
 
+/* Because default mtu is 1500, rcb buffer size is set to 2048 enough */
+#define RCB_DEFAULT_BUFFER_SIZE 2048
+
 /**
  *hns_rcb_wait_fbd_clean - clean fbd
  *@qs: ring struct pointer array
@@ -192,6 +195,30 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common)
 	wmb();	/* Sync point after breakpoint */
 }
 
+/* hns_rcb_set_tx_ring_bs - init rcb ring buf size regester
+ *@q: hnae_queue
+ *@buf_size: buffer size set to hw
+ */
+void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size)
+{
+	u32 bd_size_type = hns_rcb_buf_size2type(buf_size);
+
+	dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG,
+		       bd_size_type);
+}
+
+/* hns_rcb_set_rx_ring_bs - init rcb ring buf size regester
+ *@q: hnae_queue
+ *@buf_size: buffer size set to hw
+ */
+void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size)
+{
+	u32 bd_size_type = hns_rcb_buf_size2type(buf_size);
+
+	dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG,
+		       bd_size_type);
+}
+
 /**
  *hns_rcb_ring_init - init rcb ring
  *@ring_pair: ring pair control block
@@ -200,8 +227,6 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common)
 static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
 {
 	struct hnae_queue *q = &ring_pair->q;
-	struct rcb_common_cb *rcb_common = ring_pair->rcb_common;
-	u32 bd_size_type = rcb_common->dsaf_dev->buf_size_type;
 	struct hnae_ring *ring =
 		(ring_type == RX_RING) ? &q->rx_ring : &q->tx_ring;
 	dma_addr_t dma = ring->desc_dma_addr;
@@ -212,8 +237,8 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
 		dsaf_write_dev(q, RCB_RING_RX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
-		dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG,
-			       bd_size_type);
+		hns_rcb_set_rx_ring_bs(q, ring->buf_size);
+
 		dsaf_write_dev(q, RCB_RING_RX_RING_BD_NUM_REG,
 			       ring_pair->port_id_in_comm);
 		dsaf_write_dev(q, RCB_RING_RX_RING_PKTLINE_REG,
@@ -224,12 +249,12 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
 		dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
-		dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG,
-			       bd_size_type);
+		hns_rcb_set_tx_ring_bs(q, ring->buf_size);
+
 		dsaf_write_dev(q, RCB_RING_TX_RING_BD_NUM_REG,
 			       ring_pair->port_id_in_comm);
 		dsaf_write_dev(q, RCB_RING_TX_RING_PKTLINE_REG,
-			       ring_pair->port_id_in_comm);
+			ring_pair->port_id_in_comm + HNS_RCB_TX_PKTLINE_OFFSET);
 	}
 }
 
@@ -259,13 +284,27 @@ static void hns_rcb_set_port_desc_cnt(struct rcb_common_cb *rcb_common,
 static void hns_rcb_set_port_timeout(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout)
 {
-	if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver))
+	if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
 		dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG,
 			       timeout * HNS_RCB_CLK_FREQ_MHZ);
-	else
+	} else if (!HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev)) {
+		if (timeout > HNS_RCB_DEF_GAP_TIME_USECS)
+			dsaf_write_dev(rcb_common,
+				       RCB_PORT_INT_GAPTIME_REG + port_idx * 4,
+				       HNS_RCB_DEF_GAP_TIME_USECS);
+		else
+			dsaf_write_dev(rcb_common,
+				       RCB_PORT_INT_GAPTIME_REG + port_idx * 4,
+				       timeout);
+
+		dsaf_write_dev(rcb_common,
+			       RCB_PORT_CFG_OVERTIME_REG + port_idx * 4,
+			       timeout);
+	} else {
 		dsaf_write_dev(rcb_common,
 			       RCB_PORT_CFG_OVERTIME_REG + port_idx * 4,
 			       timeout);
+	}
 }
 
 static int hns_rcb_common_get_port_num(struct rcb_common_cb *rcb_common)
@@ -327,8 +366,12 @@ int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common)
 
 	for (i = 0; i < port_num; i++) {
 		hns_rcb_set_port_desc_cnt(rcb_common, i, rcb_common->desc_num);
-		(void)hns_rcb_set_coalesced_frames(
-			rcb_common, i, HNS_RCB_DEF_COALESCED_FRAMES);
+		hns_rcb_set_rx_coalesced_frames(
+			rcb_common, i, HNS_RCB_DEF_RX_COALESCED_FRAMES);
+		if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver) &&
+		    !HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev))
+			hns_rcb_set_tx_coalesced_frames(
+				rcb_common, i, HNS_RCB_DEF_TX_COALESCED_FRAMES);
 		hns_rcb_set_port_timeout(
 			rcb_common, i, HNS_RCB_DEF_COALESCED_USECS);
 	}
@@ -380,7 +423,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 	struct hnae_ring *ring;
 	struct rcb_common_cb *rcb_common;
 	struct ring_pair_cb *ring_pair_cb;
-	u32 buf_size;
 	u16 desc_num, mdnum_ppkt;
 	bool irq_idx, is_ver1;
 
@@ -401,7 +443,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 	}
 
 	rcb_common = ring_pair_cb->rcb_common;
-	buf_size = rcb_common->dsaf_dev->buf_size;
 	desc_num = rcb_common->dsaf_dev->desc_num;
 
 	ring->desc = NULL;
@@ -410,7 +451,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 	ring->irq = ring_pair_cb->virq[irq_idx];
 	ring->desc_dma_addr = 0;
 
-	ring->buf_size = buf_size;
+	ring->buf_size = RCB_DEFAULT_BUFFER_SIZE;
 	ring->desc_num = desc_num;
 	ring->max_desc_num_per_pkt = mdnum_ppkt;
 	ring->max_raw_data_sz_per_desc = HNS_RCB_MAX_PKT_SIZE;
@@ -430,7 +471,6 @@ static void hns_rcb_ring_pair_get_cfg(struct ring_pair_cb *ring_pair_cb)
 static int hns_rcb_get_port_in_comm(
 	struct rcb_common_cb *rcb_common, int ring_idx)
 {
-
 	return ring_idx / (rcb_common->max_q_per_vf * rcb_common->max_vfn);
 }
 
@@ -452,7 +492,7 @@ static int hns_rcb_get_base_irq_idx(struct rcb_common_cb *rcb_common)
  *hns_rcb_get_cfg - get rcb config
  *@rcb_common: rcb common device
  */
-void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common)
+int hns_rcb_get_cfg(struct rcb_common_cb *rcb_common)
 {
 	struct ring_pair_cb *ring_pair_cb;
 	u32 i;
@@ -477,26 +517,48 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common)
 		ring_pair_cb->virq[HNS_RCB_IRQ_IDX_RX] =
 		is_ver1 ? platform_get_irq(pdev, base_irq_idx + i * 2 + 1) :
 			  platform_get_irq(pdev, base_irq_idx + i * 3);
+		if ((ring_pair_cb->virq[HNS_RCB_IRQ_IDX_TX] == -EPROBE_DEFER) ||
+		    (ring_pair_cb->virq[HNS_RCB_IRQ_IDX_RX] == -EPROBE_DEFER))
+			return -EPROBE_DEFER;
+
 		ring_pair_cb->q.phy_base =
 			RCB_COMM_BASE_TO_RING_BASE(rcb_common->phy_base, i);
 		hns_rcb_ring_pair_get_cfg(ring_pair_cb);
 	}
+
+	return 0;
 }
 
 /**
- *hns_rcb_get_coalesced_frames - get rcb port coalesced frames
+ *hns_rcb_get_rx_coalesced_frames - get rcb port rx coalesced frames
  *@rcb_common: rcb_common device
  *@port_idx:port id in comm
  *
  *Returns: coalesced_frames
  */
-u32 hns_rcb_get_coalesced_frames(
+u32 hns_rcb_get_rx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx)
 {
 	return dsaf_read_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4);
 }
 
 /**
+ *hns_rcb_get_tx_coalesced_frames - get rcb port tx coalesced frames
+ *@rcb_common: rcb_common device
+ *@port_idx:port id in comm
+ *
+ *Returns: coalesced_frames
+ */
+u32 hns_rcb_get_tx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx)
+{
+	u64 reg;
+
+	reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
+	return dsaf_read_dev(rcb_common, reg);
+}
+
+/**
  *hns_rcb_get_coalesce_usecs - get rcb port coalesced time_out
  *@rcb_common: rcb_common device
  *@port_idx:port id in comm
@@ -538,33 +600,47 @@ int hns_rcb_set_coalesce_usecs(
 			return -EINVAL;
 		}
 	}
-	if (timeout > HNS_RCB_MAX_COALESCED_USECS) {
+	if (timeout > HNS_RCB_MAX_COALESCED_USECS || timeout == 0) {
 		dev_err(rcb_common->dsaf_dev->dev,
-			"error: coalesce_usecs setting supports 0~1023us\n");
+			"error: coalesce_usecs setting supports 1~1023us\n");
 		return -EINVAL;
 	}
+	hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
+	return 0;
+}
 
-	if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
-		if (timeout == 0)
-			/* set timeout to 0, Disable gap time */
-			dsaf_set_reg_field(rcb_common->io_base,
-					   RCB_INT_GAP_TIME_REG + port_idx * 4,
-					   PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
-					   0);
-		else
-			/* set timeout non 0, restore gap time to 1 */
-			dsaf_set_reg_field(rcb_common->io_base,
-					   RCB_INT_GAP_TIME_REG + port_idx * 4,
-					   PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
-					   1);
+/**
+ *hns_rcb_set_tx_coalesced_frames - set rcb coalesced frames
+ *@rcb_common: rcb_common device
+ *@port_idx:port id in comm
+ *@coalesced_frames:tx/rx BD num for coalesced frames
+ *
+ * Returns:
+ * Zero for success, or an error code in case of failure
+ */
+int hns_rcb_set_tx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames)
+{
+	u32 old_waterline =
+		hns_rcb_get_tx_coalesced_frames(rcb_common, port_idx);
+	u64 reg;
+
+	if (coalesced_frames == old_waterline)
+		return 0;
+
+	if (coalesced_frames != 1) {
+		dev_err(rcb_common->dsaf_dev->dev,
+			"error: not support tx coalesce_frames setting!\n");
+		return -EINVAL;
 	}
 
-	hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
+	reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
+	dsaf_write_dev(rcb_common, reg,	coalesced_frames);
 	return 0;
 }
 
 /**
- *hns_rcb_set_coalesced_frames - set rcb coalesced frames
+ *hns_rcb_set_rx_coalesced_frames - set rcb rx coalesced frames
  *@rcb_common: rcb_common device
  *@port_idx:port id in comm
  *@coalesced_frames:tx/rx BD num for coalesced frames
@@ -572,10 +648,11 @@ int hns_rcb_set_coalesce_usecs(
  * Returns:
  * Zero for success, or an error code in case of failure
  */
-int hns_rcb_set_coalesced_frames(
+int hns_rcb_set_rx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames)
 {
-	u32 old_waterline = hns_rcb_get_coalesced_frames(rcb_common, port_idx);
+	u32 old_waterline =
+		hns_rcb_get_rx_coalesced_frames(rcb_common, port_idx);
 
 	if (coalesced_frames == old_waterline)
 		return 0;
@@ -799,7 +876,7 @@ void hns_rcb_get_stats(struct hnae_queue *queue, u64 *data)
  */
 int hns_rcb_get_ring_sset_count(int stringset)
 {
-	if (stringset == ETH_SS_STATS)
+	if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS)
 		return HNS_RING_STATIC_REG_NUM;
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index 99b4e1ba0a94..602816498c8d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -35,12 +35,23 @@ struct rcb_common_cb;
 
 #define HNS_RCB_REG_OFFSET			0x10000
 
+#define HNS_RCB_TX_FRAMES_LOW		1
+#define HNS_RCB_RX_FRAMES_LOW		1
+#define HNS_RCB_TX_FRAMES_HIGH		1023
+#define HNS_RCB_RX_FRAMES_HIGH		1023
+#define HNS_RCB_TX_USECS_LOW		1
+#define HNS_RCB_RX_USECS_LOW		1
+#define HNS_RCB_TX_USECS_HIGH		1023
+#define HNS_RCB_RX_USECS_HIGH		1023
 #define HNS_RCB_MAX_COALESCED_FRAMES		1023
 #define HNS_RCB_MIN_COALESCED_FRAMES		1
-#define HNS_RCB_DEF_COALESCED_FRAMES		50
+#define HNS_RCB_DEF_RX_COALESCED_FRAMES		50
+#define HNS_RCB_DEF_TX_COALESCED_FRAMES		1
 #define HNS_RCB_CLK_FREQ_MHZ			350
 #define HNS_RCB_MAX_COALESCED_USECS		0x3ff
-#define HNS_RCB_DEF_COALESCED_USECS		50
+#define HNS_RCB_DEF_COALESCED_USECS		30
+#define HNS_RCB_DEF_GAP_TIME_USECS		20
+#define HNS_RCB_TX_PKTLINE_OFFSET		8
 
 #define HNS_RCB_COMMON_ENDIAN			1
 
@@ -110,7 +121,7 @@ int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index);
 void hns_rcb_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index);
 int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common);
 void hns_rcb_start(struct hnae_queue *q, u32 val);
-void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common);
+int hns_rcb_get_cfg(struct rcb_common_cb *rcb_common);
 void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode,
 			    u16 *max_vfn, u16 *max_q_per_vf);
 
@@ -125,13 +136,17 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag);
 void hns_rcb_init_hw(struct ring_pair_cb *ring);
 void hns_rcb_reset_ring_hw(struct hnae_queue *q);
 void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag);
-u32 hns_rcb_get_coalesced_frames(
+u32 hns_rcb_get_rx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx);
+u32 hns_rcb_get_tx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx);
 u32 hns_rcb_get_coalesce_usecs(
 	struct rcb_common_cb *rcb_common, u32 port_idx);
 int hns_rcb_set_coalesce_usecs(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout);
-int hns_rcb_set_coalesced_frames(
+int hns_rcb_set_rx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames);
+int hns_rcb_set_tx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames);
 void hns_rcb_update_stats(struct hnae_queue *queue);
 
@@ -146,4 +161,7 @@ int hns_rcb_get_ring_regs_count(void);
 void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data);
 
 void hns_rcb_get_strings(int stringset, u8 *data, int index);
+void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size);
+void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size);
+
 #endif /* _HNS_DSAF_RCB_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 8fa18fc17cd2..46a52d9bb196 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -421,7 +421,7 @@
 #define RCB_CFG_OVERTIME_REG			0x9300
 #define RCB_CFG_PKTLINE_INT_NUM_REG		0x9304
 #define RCB_CFG_OVERTIME_INT_NUM_REG		0x9308
-#define RCB_INT_GAP_TIME_REG			0x9400
+#define RCB_PORT_INT_GAPTIME_REG		0x9400
 #define RCB_PORT_CFG_OVERTIME_REG		0x9430
 
 #define RCB_RING_RX_RING_BASEADDR_L_REG		0x00000
@@ -466,6 +466,7 @@
 
 #define GMAC_DUPLEX_TYPE_REG			0x0008UL
 #define GMAC_FD_FC_TYPE_REG			0x000CUL
+#define GMAC_TX_WATER_LINE_REG			0x0010UL
 #define GMAC_FC_TX_TIMER_REG			0x001CUL
 #define GMAC_FD_FC_ADDR_LOW_REG			0x0020UL
 #define GMAC_FD_FC_ADDR_HIGH_REG		0x0024UL
@@ -912,6 +913,9 @@
 
 #define GMAC_DUPLEX_TYPE_B 0
 
+#define GMAC_TX_WATER_LINE_MASK		((1UL << 8) - 1)
+#define GMAC_TX_WATER_LINE_SHIFT	0
+
 #define GMAC_FC_TX_TIMER_S 0
 #define GMAC_FC_TX_TIMER_M 0xffff
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index aae830a93050..51e7e9f5af49 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -300,18 +300,6 @@ static void hns_xgmac_set_tx_auto_pause_frames(void *mac_drv, u16 enable)
 }
 
 /**
- *hns_xgmac_get_id - get xgmac port id
- *@mac_drv: mac driver
- *@newval:xgmac max frame length
- */
-static void hns_xgmac_get_id(void *mac_drv, u8 *mac_id)
-{
-	struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
-	*mac_id = drv->mac_id;
-}
-
-/**
  *hns_xgmac_config_max_frame_length - set xgmac max frame length
  *@mac_drv: mac driver
  *@newval:xgmac max frame length
@@ -793,7 +781,7 @@ static void hns_xgmac_get_strings(u32 stringset, u8 *data)
  */
 static int hns_xgmac_get_sset_count(int stringset)
 {
-	if (stringset == ETH_SS_STATS)
+	if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS)
 		return ARRAY_SIZE(g_xgmac_stats_string);
 
 	return 0;
@@ -833,7 +821,6 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
 	mac_drv->config_half_duplex = NULL;
 	mac_drv->set_rx_ignore_pause_frames =
 		hns_xgmac_set_rx_ignore_pause_frames;
-	mac_drv->mac_get_id = hns_xgmac_get_id;
 	mac_drv->mac_free = hns_xgmac_free;
 	mac_drv->adjust_link = NULL;
 	mac_drv->set_tx_auto_pause_frames = hns_xgmac_set_tx_auto_pause_frames;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index fca37e2c7f01..c6700b91a2df 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -512,7 +512,8 @@ static void hns_nic_reuse_page(struct sk_buff *skb, int i,
 	int last_offset;
 	bool twobufs;
 
-	twobufs = ((PAGE_SIZE < 8192) && hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048);
+	twobufs = ((PAGE_SIZE < 8192) &&
+		hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048);
 
 	desc = &ring->desc[ring->next_to_clean];
 	size = le16_to_cpu(desc->rx.size);
@@ -859,7 +860,7 @@ out:
 	return recv_pkts;
 }
 
-static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
 	int num = 0;
@@ -873,22 +874,23 @@ static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
 		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
 			ring_data->ring, 1);
 
-		napi_schedule(&ring_data->napi);
+		return false;
+	} else {
+		return true;
 	}
 }
 
-static void hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
-	int num = 0;
+	int num;
 
 	num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
 
-	if (num == 0)
-		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
-			ring, 0);
+	if (!num)
+		return true;
 	else
-		napi_schedule(&ring_data->napi);
+		return false;
 }
 
 static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring,
@@ -921,12 +923,13 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
 
 /* netif_tx_lock will turn down the performance, set only when necessary */
 #ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ndev) netif_tx_lock(ndev)
-#define NETIF_TX_UNLOCK(ndev) netif_tx_unlock(ndev)
+#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
+#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
 #else
-#define NETIF_TX_LOCK(ndev)
-#define NETIF_TX_UNLOCK(ndev)
+#define NETIF_TX_LOCK(ring)
+#define NETIF_TX_UNLOCK(ring)
 #endif
+
 /* reclaim all desc in one budget
  * return error or number of desc left
  */
@@ -940,13 +943,13 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ndev);
+	NETIF_TX_LOCK(ring);
 
 	head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 	rmb(); /* make sure head is ready before touch any data */
 
 	if (is_ring_empty(ring) || head == ring->next_to_clean) {
-		NETIF_TX_UNLOCK(ndev);
+		NETIF_TX_UNLOCK(ring);
 		return 0; /* no data to poll */
 	}
 
@@ -954,7 +957,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 		ring->stats.io_err_cnt++;
-		NETIF_TX_UNLOCK(ndev);
+		NETIF_TX_UNLOCK(ring);
 		return -EIO;
 	}
 
@@ -966,7 +969,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		prefetch(&ring->desc_cb[ring->next_to_clean]);
 	}
 
-	NETIF_TX_UNLOCK(ndev);
+	NETIF_TX_UNLOCK(ring);
 
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_completed_queue(dev_queue, pkts, bytes);
@@ -989,7 +992,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	return 0;
 }
 
-static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
 	int head;
@@ -1002,20 +1005,21 @@ static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
 		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
 			ring_data->ring, 1);
 
-		napi_schedule(&ring_data->napi);
+		return false;
+	} else {
+		return true;
 	}
 }
 
-static void hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
 	int head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 
 	if (head == ring->next_to_clean)
-		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
-			ring, 0);
+		return true;
 	else
-		napi_schedule(&ring_data->napi);
+		return false;
 }
 
 static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
@@ -1026,7 +1030,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ndev);
+	NETIF_TX_LOCK(ring);
 
 	head = ring->next_to_use; /* ntu :soft setted ring position*/
 	bytes = 0;
@@ -1034,7 +1038,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	while (head != ring->next_to_clean)
 		hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
 
-	NETIF_TX_UNLOCK(ndev);
+	NETIF_TX_UNLOCK(ring);
 
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_reset_queue(dev_queue);
@@ -1042,15 +1046,23 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 
 static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 {
+	int clean_complete = 0;
 	struct hns_nic_ring_data *ring_data =
 		container_of(napi, struct hns_nic_ring_data, napi);
-	int clean_complete = ring_data->poll_one(
-				ring_data, budget, ring_data->ex_process);
+	struct hnae_ring *ring = ring_data->ring;
 
-	if (clean_complete >= 0 && clean_complete < budget) {
-		napi_complete(napi);
-		ring_data->fini_process(ring_data);
-		return 0;
+try_again:
+	clean_complete += ring_data->poll_one(
+				ring_data, budget - clean_complete,
+				ring_data->ex_process);
+
+	if (clean_complete < budget) {
+		if (ring_data->fini_process(ring_data)) {
+			napi_complete(napi);
+			ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
+		} else {
+			goto try_again;
+		}
 	}
 
 	return clean_complete;
@@ -1196,54 +1208,31 @@ static void hns_nic_ring_close(struct net_device *netdev, int idx)
 	napi_disable(&priv->ring_data[idx].napi);
 }
 
-static void hns_set_irq_affinity(struct hns_nic_priv *priv)
+static int hns_nic_init_affinity_mask(int q_num, int ring_idx,
+				      struct hnae_ring *ring, cpumask_t *mask)
 {
-	struct hnae_handle *h = priv->ae_handle;
-	struct hns_nic_ring_data *rd;
-	int i;
 	int cpu;
-	cpumask_var_t mask;
-
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
-		return;
 
-	/*diffrent irq banlance for 16core and 32core*/
-	if (h->q_num == num_possible_cpus()) {
-		for (i = 0; i < h->q_num * 2; i++) {
-			rd = &priv->ring_data[i];
-			if (cpu_online(rd->queue_index)) {
-				cpumask_clear(mask);
-				cpu = rd->queue_index;
-				cpumask_set_cpu(cpu, mask);
-				(void)irq_set_affinity_hint(rd->ring->irq,
-							    mask);
-			}
-		}
+	/* Diffrent irq banlance between 16core and 32core.
+	 * The cpu mask set by ring index according to the ring flag
+	 * which indicate the ring is tx or rx.
+	 */
+	if (q_num == num_possible_cpus()) {
+		if (is_tx_ring(ring))
+			cpu = ring_idx;
+		else
+			cpu = ring_idx - q_num;
 	} else {
-		for (i = 0; i < h->q_num; i++) {
-			rd = &priv->ring_data[i];
-			if (cpu_online(rd->queue_index * 2)) {
-				cpumask_clear(mask);
-				cpu = rd->queue_index * 2;
-				cpumask_set_cpu(cpu, mask);
-				(void)irq_set_affinity_hint(rd->ring->irq,
-							    mask);
-			}
-		}
-
-		for (i = h->q_num; i < h->q_num * 2; i++) {
-			rd = &priv->ring_data[i];
-			if (cpu_online(rd->queue_index * 2 + 1)) {
-				cpumask_clear(mask);
-				cpu = rd->queue_index * 2 + 1;
-				cpumask_set_cpu(cpu, mask);
-				(void)irq_set_affinity_hint(rd->ring->irq,
-							    mask);
-			}
-		}
+		if (is_tx_ring(ring))
+			cpu = ring_idx * 2;
+		else
+			cpu = (ring_idx - q_num) * 2 + 1;
 	}
 
-	free_cpumask_var(mask);
+	cpumask_clear(mask);
+	cpumask_set_cpu(cpu, mask);
+
+	return cpu;
 }
 
 static int hns_nic_init_irq(struct hns_nic_priv *priv)
@@ -1252,6 +1241,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
 	struct hns_nic_ring_data *rd;
 	int i;
 	int ret;
+	int cpu;
 
 	for (i = 0; i < h->q_num * 2; i++) {
 		rd = &priv->ring_data[i];
@@ -1261,7 +1251,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
 
 		snprintf(rd->ring->ring_name, RCB_RING_NAME_LEN,
 			 "%s-%s%d", priv->netdev->name,
-			 (i < h->q_num ? "tx" : "rx"), rd->queue_index);
+			 (is_tx_ring(rd->ring) ? "tx" : "rx"), rd->queue_index);
 
 		rd->ring->ring_name[RCB_RING_NAME_LEN - 1] = '\0';
 
@@ -1273,12 +1263,17 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
 			return ret;
 		}
 		disable_irq(rd->ring->irq);
+
+		cpu = hns_nic_init_affinity_mask(h->q_num, i,
+						 rd->ring, &rd->mask);
+
+		if (cpu_online(cpu))
+			irq_set_affinity_hint(rd->ring->irq,
+					      &rd->mask);
+
 		rd->ring->irq_init_flag = RCB_IRQ_INITED;
 	}
 
-	/*set cpu affinity*/
-	hns_set_irq_affinity(priv);
-
 	return 0;
 }
 
@@ -1487,32 +1482,259 @@ static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb,
 	return (netdev_tx_t)ret;
 }
 
+static void hns_nic_drop_rx_fetch(struct hns_nic_ring_data *ring_data,
+				  struct sk_buff *skb)
+{
+	dev_kfree_skb_any(skb);
+}
+
+#define HNS_LB_TX_RING	0
+static struct sk_buff *hns_assemble_skb(struct net_device *ndev)
+{
+	struct sk_buff *skb;
+	struct ethhdr *ethhdr;
+	int frame_len;
+
+	/* allocate test skb */
+	skb = alloc_skb(64, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	skb_put(skb, 64);
+	skb->dev = ndev;
+	memset(skb->data, 0xFF, skb->len);
+
+	/* must be tcp/ip package */
+	ethhdr = (struct ethhdr *)skb->data;
+	ethhdr->h_proto = htons(ETH_P_IP);
+
+	frame_len = skb->len & (~1ul);
+	memset(&skb->data[frame_len / 2], 0xAA,
+	       frame_len / 2 - 1);
+
+	skb->queue_mapping = HNS_LB_TX_RING;
+
+	return skb;
+}
+
+static int hns_enable_serdes_lb(struct net_device *ndev)
+{
+	struct hns_nic_priv *priv = netdev_priv(ndev);
+	struct hnae_handle *h = priv->ae_handle;
+	struct hnae_ae_ops *ops = h->dev->ops;
+	int speed, duplex;
+	int ret;
+
+	ret = ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 1);
+	if (ret)
+		return ret;
+
+	ret = ops->start ? ops->start(h) : 0;
+	if (ret)
+		return ret;
+
+	/* link adjust duplex*/
+	if (h->phy_if != PHY_INTERFACE_MODE_XGMII)
+		speed = 1000;
+	else
+		speed = 10000;
+	duplex = 1;
+
+	ops->adjust_link(h, speed, duplex);
+
+	/* wait h/w ready */
+	mdelay(300);
+
+	return 0;
+}
+
+static void hns_disable_serdes_lb(struct net_device *ndev)
+{
+	struct hns_nic_priv *priv = netdev_priv(ndev);
+	struct hnae_handle *h = priv->ae_handle;
+	struct hnae_ae_ops *ops = h->dev->ops;
+
+	ops->stop(h);
+	ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 0);
+}
+
+/**
+ *hns_nic_clear_all_rx_fetch - clear the chip fetched descriptions. The
+ *function as follows:
+ *    1. if one rx ring has found the page_offset is not equal 0 between head
+ *       and tail, it means that the chip fetched the wrong descs for the ring
+ *       which buffer size is 4096.
+ *    2. we set the chip serdes loopback and set rss indirection to the ring.
+ *    3. construct 64-bytes ip broadcast packages, wait the associated rx ring
+ *       recieving all packages and it will fetch new descriptions.
+ *    4. recover to the original state.
+ *
+ *@ndev: net device
+ */
+static int hns_nic_clear_all_rx_fetch(struct net_device *ndev)
+{
+	struct hns_nic_priv *priv = netdev_priv(ndev);
+	struct hnae_handle *h = priv->ae_handle;
+	struct hnae_ae_ops *ops = h->dev->ops;
+	struct hns_nic_ring_data *rd;
+	struct hnae_ring *ring;
+	struct sk_buff *skb;
+	u32 *org_indir;
+	u32 *cur_indir;
+	int indir_size;
+	int head, tail;
+	int fetch_num;
+	int i, j;
+	bool found;
+	int retry_times;
+	int ret = 0;
+
+	/* alloc indir memory */
+	indir_size = ops->get_rss_indir_size(h) * sizeof(*org_indir);
+	org_indir = kzalloc(indir_size, GFP_KERNEL);
+	if (!org_indir)
+		return -ENOMEM;
+
+	/* store the orginal indirection */
+	ops->get_rss(h, org_indir, NULL, NULL);
+
+	cur_indir = kzalloc(indir_size, GFP_KERNEL);
+	if (!cur_indir) {
+		ret = -ENOMEM;
+		goto cur_indir_alloc_err;
+	}
+
+	/* set loopback */
+	if (hns_enable_serdes_lb(ndev)) {
+		ret = -EINVAL;
+		goto enable_serdes_lb_err;
+	}
+
+	/* foreach every rx ring to clear fetch desc */
+	for (i = 0; i < h->q_num; i++) {
+		ring = &h->qs[i]->rx_ring;
+		head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
+		tail = readl_relaxed(ring->io_base + RCB_REG_TAIL);
+		found = false;
+		fetch_num = ring_dist(ring, head, tail);
+
+		while (head != tail) {
+			if (ring->desc_cb[head].page_offset != 0) {
+				found = true;
+				break;
+			}
+
+			head++;
+			if (head == ring->desc_num)
+				head = 0;
+		}
+
+		if (found) {
+			for (j = 0; j < indir_size / sizeof(*org_indir); j++)
+				cur_indir[j] = i;
+			ops->set_rss(h, cur_indir, NULL, 0);
+
+			for (j = 0; j < fetch_num; j++) {
+				/* alloc one skb and init */
+				skb = hns_assemble_skb(ndev);
+				if (!skb)
+					goto out;
+				rd = &tx_ring_data(priv, skb->queue_mapping);
+				hns_nic_net_xmit_hw(ndev, skb, rd);
+
+				retry_times = 0;
+				while (retry_times++ < 10) {
+					mdelay(10);
+					/* clean rx */
+					rd = &rx_ring_data(priv, i);
+					if (rd->poll_one(rd, fetch_num,
+							 hns_nic_drop_rx_fetch))
+						break;
+				}
+
+				retry_times = 0;
+				while (retry_times++ < 10) {
+					mdelay(10);
+					/* clean tx ring 0 send package */
+					rd = &tx_ring_data(priv,
+							   HNS_LB_TX_RING);
+					if (rd->poll_one(rd, fetch_num, NULL))
+						break;
+				}
+			}
+		}
+	}
+
+out:
+	/* restore everything */
+	ops->set_rss(h, org_indir, NULL, 0);
+	hns_disable_serdes_lb(ndev);
+enable_serdes_lb_err:
+	kfree(cur_indir);
+cur_indir_alloc_err:
+	kfree(org_indir);
+
+	return ret;
+}
+
 static int hns_nic_change_mtu(struct net_device *ndev, int new_mtu)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
+	bool if_running = netif_running(ndev);
 	int ret;
 
+	/* MTU < 68 is an error and causes problems on some kernels */
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	/* MTU no change */
+	if (new_mtu == ndev->mtu)
+		return 0;
+
 	if (!h->dev->ops->set_mtu)
 		return -ENOTSUPP;
 
-	if (netif_running(ndev)) {
+	if (if_running) {
 		(void)hns_nic_net_stop(ndev);
 		msleep(100);
+	}
 
-		ret = h->dev->ops->set_mtu(h, new_mtu);
-		if (ret)
-			netdev_err(ndev, "set mtu fail, return value %d\n",
-				   ret);
+	if (priv->enet_ver != AE_VERSION_1 &&
+	    ndev->mtu <= BD_SIZE_2048_MAX_MTU &&
+	    new_mtu > BD_SIZE_2048_MAX_MTU) {
+		/* update desc */
+		hnae_reinit_all_ring_desc(h);
 
-		if (hns_nic_net_open(ndev))
-			netdev_err(ndev, "hns net open fail\n");
-	} else {
-		ret = h->dev->ops->set_mtu(h, new_mtu);
+		/* clear the package which the chip has fetched */
+		ret = hns_nic_clear_all_rx_fetch(ndev);
+
+		/* the page offset must be consist with desc */
+		hnae_reinit_all_ring_page_off(h);
+
+		if (ret) {
+			netdev_err(ndev, "clear the fetched desc fail\n");
+			goto out;
+		}
+	}
+
+	ret = h->dev->ops->set_mtu(h, new_mtu);
+	if (ret) {
+		netdev_err(ndev, "set mtu fail, return value %d\n",
+			   ret);
+		goto out;
 	}
 
-	if (!ret)
-		ndev->mtu = new_mtu;
+	/* finally, set new mtu to netdevice */
+	ndev->mtu = new_mtu;
+
+out:
+	if (if_running) {
+		if (hns_nic_net_open(ndev)) {
+			netdev_err(ndev, "hns net open fail\n");
+			ret = -EINVAL;
+		}
+	}
 
 	return ret;
 }
@@ -1791,7 +2013,7 @@ static void hns_nic_reset_subtask(struct hns_nic_priv *priv)
 static void hns_nic_service_event_complete(struct hns_nic_priv *priv)
 {
 	WARN_ON(!test_bit(NIC_STATE_SERVICE_SCHED, &priv->state));
-
+	/* make sure to commit the things */
 	smp_mb__before_atomic();
 	clear_bit(NIC_STATE_SERVICE_SCHED, &priv->state);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index 5b412de350aa..1b83232082b2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -37,10 +37,11 @@ enum hns_nic_state {
 struct hns_nic_ring_data {
 	struct hnae_ring *ring;
 	struct napi_struct napi;
+	cpumask_t mask; /* affinity mask */
 	int queue_index;
 	int (*poll_one)(struct hns_nic_ring_data *, int, void *);
 	void (*ex_process)(struct hns_nic_ring_data *, struct sk_buff *);
-	void (*fini_process)(struct hns_nic_ring_data *);
+	bool (*fini_process)(struct hns_nic_ring_data *);
 };
 
 /* compatible the difference between two versions */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3ac2183dbd21..b8fab149690f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -146,7 +146,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev,
 
 	/* When there is no phy, autoneg is off. */
 	cmd->base.autoneg = false;
-	cmd->base.cmd = speed;
+	cmd->base.speed = speed;
 	cmd->base.duplex = duplex;
 
 	if (net_dev->phydev)
@@ -764,14 +764,14 @@ static int hns_get_coalesce(struct net_device *net_dev,
 	ec->use_adaptive_tx_coalesce = 1;
 
 	if ((!ops->get_coalesce_usecs) ||
-	    (!ops->get_rx_max_coalesced_frames))
+	    (!ops->get_max_coalesced_frames))
 		return -ESRCH;
 
 	ops->get_coalesce_usecs(priv->ae_handle,
 					&ec->tx_coalesce_usecs,
 					&ec->rx_coalesce_usecs);
 
-	ops->get_rx_max_coalesced_frames(
+	ops->get_max_coalesced_frames(
 		priv->ae_handle,
 		&ec->tx_max_coalesced_frames,
 		&ec->rx_max_coalesced_frames);
@@ -801,30 +801,28 @@ static int hns_set_coalesce(struct net_device *net_dev,
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
-	int ret;
+	int rc1, rc2;
 
 	ops = priv->ae_handle->dev->ops;
 
 	if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs)
 		return -EINVAL;
 
-	if (ec->rx_max_coalesced_frames != ec->tx_max_coalesced_frames)
-		return -EINVAL;
-
 	if ((!ops->set_coalesce_usecs) ||
 	    (!ops->set_coalesce_frames))
 		return -ESRCH;
 
-	ret = ops->set_coalesce_usecs(priv->ae_handle,
+	rc1 = ops->set_coalesce_usecs(priv->ae_handle,
 				      ec->rx_coalesce_usecs);
-	if (ret)
-		return ret;
 
-	ret = ops->set_coalesce_frames(
-		priv->ae_handle,
-		ec->rx_max_coalesced_frames);
+	rc2 = ops->set_coalesce_frames(priv->ae_handle,
+				       ec->tx_max_coalesced_frames,
+				       ec->rx_max_coalesced_frames);
 
-	return ret;
+	if (rc1 || rc2)
+		return -EINVAL;
+
+	return 0;
 }
 
 /**
@@ -1253,12 +1251,10 @@ hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
 
 	ops = priv->ae_handle->dev->ops;
 
-	/* currently hfunc can only be Toeplitz hash */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+		netdev_err(netdev, "Invalid hfunc!\n");
 		return -EOPNOTSUPP;
-	if (!indir)
-		return 0;
+	}
 
 	return ops->set_rss(priv->ae_handle, indir, key, hfunc);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 501eb2090ca6..e5221d95afe1 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -23,17 +23,9 @@
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/spinlock_types.h>
 
 #define MDIO_DRV_NAME "Hi-HNS_MDIO"
 #define MDIO_BUS_NAME "Hisilicon MII Bus"
-#define MDIO_DRV_VERSION "1.3.0"
-#define MDIO_COPYRIGHT "Copyright(c) 2015 Huawei Corporation."
-#define MDIO_DRV_STRING MDIO_BUS_NAME
-#define MDIO_DEFAULT_DEVICE_DESCR MDIO_BUS_NAME
-
-#define MDIO_CTL_DEV_ADDR(x)	(x & 0x1f)
-#define MDIO_CTL_PORT_ADDR(x)	((x & 0x1f) << 5)
 
 #define MDIO_TIMEOUT			1000000
 
@@ -64,9 +56,7 @@ struct hns_mdio_device {
 #define MDIO_CMD_DEVAD_S	0
 #define MDIO_CMD_PRTAD_M	0x1f
 #define MDIO_CMD_PRTAD_S	5
-#define MDIO_CMD_OP_M		0x3
 #define MDIO_CMD_OP_S		10
-#define MDIO_CMD_ST_M		0x3
 #define MDIO_CMD_ST_S		12
 #define MDIO_CMD_START_B	14
 
@@ -185,18 +175,20 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev,
 static int hns_mdio_wait_ready(struct mii_bus *bus)
 {
 	struct hns_mdio_device *mdio_dev = bus->priv;
+	u32 cmd_reg_value;
 	int i;
-	u32 cmd_reg_value = 1;
 
 	/* waitting for MDIO_COMMAND_REG 's mdio_start==0 */
 	/* after that can do read or write*/
-	for (i = 0; cmd_reg_value; i++) {
+	for (i = 0; i < MDIO_TIMEOUT; i++) {
 		cmd_reg_value = MDIO_GET_REG_BIT(mdio_dev,
 						 MDIO_COMMAND_REG,
 						 MDIO_CMD_START_B);
-		if (i == MDIO_TIMEOUT)
-			return -ETIMEDOUT;
+		if (!cmd_reg_value)
+			break;
 	}
+	if ((i == MDIO_TIMEOUT) && cmd_reg_value)
+		return -ETIMEDOUT;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ibm/emac/Makefile b/drivers/net/ethernet/ibm/emac/Makefile
index eba21835d90d..98768ba0955a 100644
--- a/drivers/net/ethernet/ibm/emac/Makefile
+++ b/drivers/net/ethernet/ibm/emac/Makefile
@@ -8,4 +8,3 @@ ibm_emac-y := mal.o core.o phy.o
 ibm_emac-$(CONFIG_IBM_EMAC_ZMII) += zmii.o
 ibm_emac-$(CONFIG_IBM_EMAC_RGMII) += rgmii.o
 ibm_emac-$(CONFIG_IBM_EMAC_TAH) += tah.o
-ibm_emac-$(CONFIG_IBM_EMAC_DEBUG) += debug.o
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 275c2e2349ad..508923f39ccf 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1929,7 +1929,7 @@ static struct net_device_stats *emac_stats(struct net_device *ndev)
 	struct emac_instance *dev = netdev_priv(ndev);
 	struct emac_stats *st = &dev->stats;
 	struct emac_error_stats *est = &dev->estats;
-	struct net_device_stats *nst = &dev->nstats;
+	struct net_device_stats *nst = &ndev->stats;
 	unsigned long flags;
 
 	DBG2(dev, "stats" NL);
@@ -2589,8 +2589,6 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
 static int emac_dt_phy_connect(struct emac_instance *dev,
 			       struct device_node *phy_handle)
 {
-	int res;
-
 	dev->phy.def = devm_kzalloc(&dev->ofdev->dev, sizeof(*dev->phy.def),
 				    GFP_KERNEL);
 	if (!dev->phy.def)
@@ -2617,7 +2615,7 @@ static int emac_dt_phy_probe(struct emac_instance *dev)
 {
 	struct device_node *np = dev->ofdev->dev.of_node;
 	struct device_node *phy_handle;
-	int res = 0;
+	int res = 1;
 
 	phy_handle = of_parse_phandle(np, "phy-handle", 0);
 
@@ -2714,13 +2712,24 @@ static int emac_init_phy(struct emac_instance *dev)
 	if (emac_has_feature(dev, EMAC_FTR_HAS_RGMII)) {
 		int res = emac_dt_phy_probe(dev);
 
-		mutex_unlock(&emac_phy_map_lock);
-		if (!res)
+		switch (res) {
+		case 1:
+			/* No phy-handle property configured.
+			 * Continue with the existing phy probe
+			 * and setup code.
+			 */
+			break;
+
+		case 0:
+			mutex_unlock(&emac_phy_map_lock);
 			goto init_phy;
 
-		dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n",
-			res);
-		return res;
+		default:
+			mutex_unlock(&emac_phy_map_lock);
+			dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n",
+				res);
+			return res;
+		}
 	}
 
 	if (dev->phy_address != 0xffffffff)
@@ -3164,8 +3173,6 @@ static int emac_probe(struct platform_device *ofdev)
 		printk("%s: found %s PHY (0x%02x)\n", ndev->name,
 		       dev->phy.def->name, dev->phy.address);
 
-	emac_dbg_register(dev);
-
 	/* Life is good */
 	return 0;
 
@@ -3234,7 +3241,6 @@ static int emac_remove(struct platform_device *ofdev)
 	mal_unregister_commac(dev->mal, &dev->commac);
 	emac_put_deps(dev);
 
-	emac_dbg_unregister(dev);
 	iounmap(dev->emacp);
 
 	if (dev->wol_irq)
@@ -3317,9 +3323,6 @@ static int __init emac_init(void)
 
 	printk(KERN_INFO DRV_DESC ", version " DRV_VERSION "\n");
 
-	/* Init debug stuff */
-	emac_init_debug();
-
 	/* Build EMAC boot list */
 	emac_make_bootlist();
 
@@ -3364,7 +3367,6 @@ static void __exit emac_exit(void)
 	rgmii_exit();
 	zmii_exit();
 	mal_exit();
-	emac_fini_debug();
 
 	/* Destroy EMAC boot list */
 	for (i = 0; i < EMAC_BOOT_LIST_SIZE; i++)
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 0710a6685489..f10e156641d5 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -265,7 +265,6 @@ struct emac_instance {
 	/* Stats
 	 */
 	struct emac_error_stats		estats;
-	struct net_device_stats		nstats;
 	struct emac_stats 		stats;
 
 	/* Misc
diff --git a/drivers/net/ethernet/ibm/emac/debug.c b/drivers/net/ethernet/ibm/emac/debug.c
deleted file mode 100644
index a559f326bf63..000000000000
--- a/drivers/net/ethernet/ibm/emac/debug.c
+++ /dev/null
@@ -1,270 +0,0 @@
-/*
- * drivers/net/ethernet/ibm/emac/debug.c
- *
- * Driver for PowerPC 4xx on-chip ethernet controller, debug print routines.
- *
- * Copyright 2007 Benjamin Herrenschmidt, IBM Corp.
- *                <benh@kernel.crashing.org>
- *
- * Based on the arch/ppc version of the driver:
- *
- * Copyright (c) 2004, 2005 Zultys Technologies
- * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/sysrq.h>
-#include <asm/io.h>
-
-#include "core.h"
-
-static DEFINE_SPINLOCK(emac_dbg_lock);
-
-static void emac_desc_dump(struct emac_instance *p)
-{
-	int i;
-	printk("** EMAC %s TX BDs **\n"
-	       " tx_cnt = %d tx_slot = %d ack_slot = %d\n",
-	       p->ofdev->dev.of_node->full_name,
-	       p->tx_cnt, p->tx_slot, p->ack_slot);
-	for (i = 0; i < NUM_TX_BUFF / 2; ++i)
-		printk
-		    ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n",
-		     i, p->tx_desc[i].data_ptr, p->tx_skb[i] ? 'V' : ' ',
-		     p->tx_desc[i].ctrl, p->tx_desc[i].data_len,
-		     NUM_TX_BUFF / 2 + i,
-		     p->tx_desc[NUM_TX_BUFF / 2 + i].data_ptr,
-		     p->tx_skb[NUM_TX_BUFF / 2 + i] ? 'V' : ' ',
-		     p->tx_desc[NUM_TX_BUFF / 2 + i].ctrl,
-		     p->tx_desc[NUM_TX_BUFF / 2 + i].data_len);
-
-	printk("** EMAC %s RX BDs **\n"
-	       " rx_slot = %d flags = 0x%lx rx_skb_size = %d rx_sync_size = %d\n"
-	       " rx_sg_skb = 0x%p\n",
-	       p->ofdev->dev.of_node->full_name,
-	       p->rx_slot, p->commac.flags, p->rx_skb_size,
-	       p->rx_sync_size, p->rx_sg_skb);
-	for (i = 0; i < NUM_RX_BUFF / 2; ++i)
-		printk
-		    ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n",
-		     i, p->rx_desc[i].data_ptr, p->rx_skb[i] ? 'V' : ' ',
-		     p->rx_desc[i].ctrl, p->rx_desc[i].data_len,
-		     NUM_RX_BUFF / 2 + i,
-		     p->rx_desc[NUM_RX_BUFF / 2 + i].data_ptr,
-		     p->rx_skb[NUM_RX_BUFF / 2 + i] ? 'V' : ' ',
-		     p->rx_desc[NUM_RX_BUFF / 2 + i].ctrl,
-		     p->rx_desc[NUM_RX_BUFF / 2 + i].data_len);
-}
-
-static void emac_mac_dump(struct emac_instance *dev)
-{
-	struct emac_regs __iomem *p = dev->emacp;
-	const int xaht_regs = EMAC_XAHT_REGS(dev);
-	u32 *gaht_base = emac_gaht_base(dev);
-	u32 *iaht_base = emac_iaht_base(dev);
-	int emac4sync = emac_has_feature(dev, EMAC_FTR_EMAC4SYNC);
-	int n;
-
-	printk("** EMAC %s registers **\n"
-	       "MR0 = 0x%08x MR1 = 0x%08x TMR0 = 0x%08x TMR1 = 0x%08x\n"
-	       "RMR = 0x%08x ISR = 0x%08x ISER = 0x%08x\n"
-	       "IAR = %04x%08x VTPID = 0x%04x VTCI = 0x%04x\n",
-	       dev->ofdev->dev.of_node->full_name,
-	       in_be32(&p->mr0), in_be32(&p->mr1),
-	       in_be32(&p->tmr0), in_be32(&p->tmr1),
-	       in_be32(&p->rmr), in_be32(&p->isr), in_be32(&p->iser),
-	       in_be32(&p->iahr), in_be32(&p->ialr), in_be32(&p->vtpid),
-	       in_be32(&p->vtci)
-	       );
-
-	if (emac4sync)
-		printk("MAR = %04x%08x MMAR = %04x%08x\n",
-		       in_be32(&p->u0.emac4sync.mahr),
-		       in_be32(&p->u0.emac4sync.malr),
-		       in_be32(&p->u0.emac4sync.mmahr),
-		       in_be32(&p->u0.emac4sync.mmalr)
-		       );
-
-	for (n = 0; n < xaht_regs; n++)
-		printk("IAHT%02d = 0x%08x\n", n + 1, in_be32(iaht_base + n));
-
-	for (n = 0; n < xaht_regs; n++)
-		printk("GAHT%02d = 0x%08x\n", n + 1, in_be32(gaht_base + n));
-
-	printk("LSA = %04x%08x IPGVR = 0x%04x\n"
-	       "STACR = 0x%08x TRTR = 0x%08x RWMR = 0x%08x\n"
-	       "OCTX = 0x%08x OCRX = 0x%08x\n",
-	       in_be32(&p->lsah), in_be32(&p->lsal), in_be32(&p->ipgvr),
-	       in_be32(&p->stacr), in_be32(&p->trtr), in_be32(&p->rwmr),
-	       in_be32(&p->octx), in_be32(&p->ocrx)
-	       );
-
-	if (!emac4sync) {
-		printk("IPCR = 0x%08x\n",
-		       in_be32(&p->u1.emac4.ipcr)
-		       );
-	} else {
-		printk("REVID = 0x%08x TPC = 0x%08x\n",
-		       in_be32(&p->u1.emac4sync.revid),
-		       in_be32(&p->u1.emac4sync.tpc)
-		       );
-	}
-
-	emac_desc_dump(dev);
-}
-
-static void emac_mal_dump(struct mal_instance *mal)
-{
-	int i;
-
-	printk("** MAL %s Registers **\n"
-	       "CFG = 0x%08x ESR = 0x%08x IER = 0x%08x\n"
-	       "TX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n"
-	       "RX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n",
-	       mal->ofdev->dev.of_node->full_name,
-	       get_mal_dcrn(mal, MAL_CFG), get_mal_dcrn(mal, MAL_ESR),
-	       get_mal_dcrn(mal, MAL_IER),
-	       get_mal_dcrn(mal, MAL_TXCASR), get_mal_dcrn(mal, MAL_TXCARR),
-	       get_mal_dcrn(mal, MAL_TXEOBISR), get_mal_dcrn(mal, MAL_TXDEIR),
-	       get_mal_dcrn(mal, MAL_RXCASR), get_mal_dcrn(mal, MAL_RXCARR),
-	       get_mal_dcrn(mal, MAL_RXEOBISR), get_mal_dcrn(mal, MAL_RXDEIR)
-	    );
-
-	printk("TX|");
-	for (i = 0; i < mal->num_tx_chans; ++i) {
-		if (i && !(i % 4))
-			printk("\n   ");
-		printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_TXCTPR(i)));
-	}
-	printk("\nRX|");
-	for (i = 0; i < mal->num_rx_chans; ++i) {
-		if (i && !(i % 4))
-			printk("\n   ");
-		printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_RXCTPR(i)));
-	}
-	printk("\n   ");
-	for (i = 0; i < mal->num_rx_chans; ++i) {
-		u32 r = get_mal_dcrn(mal, MAL_RCBS(i));
-		if (i && !(i % 3))
-			printk("\n   ");
-		printk("RCBS%d = 0x%08x (%d) ", i, r, r * 16);
-	}
-	printk("\n");
-}
-
-static struct emac_instance *__emacs[4];
-static struct mal_instance *__mals[1];
-
-void emac_dbg_register(struct emac_instance *dev)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__emacs); i++)
-		if (__emacs[i] == NULL) {
-			__emacs[i] = dev;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void emac_dbg_unregister(struct emac_instance *dev)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__emacs); i++)
-		if (__emacs[i] == dev) {
-			__emacs[i] = NULL;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void mal_dbg_register(struct mal_instance *mal)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__mals); i++)
-		if (__mals[i] == NULL) {
-			__mals[i] = mal;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void mal_dbg_unregister(struct mal_instance *mal)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__mals); i++)
-		if (__mals[i] == mal) {
-			__mals[i] = NULL;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void emac_dbg_dump_all(void)
-{
-	unsigned int i;
-	unsigned long flags;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-
-	for (i = 0; i < ARRAY_SIZE(__mals); ++i)
-		if (__mals[i])
-			emac_mal_dump(__mals[i]);
-
-	for (i = 0; i < ARRAY_SIZE(__emacs); ++i)
-		if (__emacs[i])
-			emac_mac_dump(__emacs[i]);
-
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-#if defined(CONFIG_MAGIC_SYSRQ)
-static void emac_sysrq_handler(int key)
-{
-	emac_dbg_dump_all();
-}
-
-static struct sysrq_key_op emac_sysrq_op = {
-	.handler = emac_sysrq_handler,
-	.help_msg = "emac(c)",
-	.action_msg = "Show EMAC(s) status",
-};
-
-int __init emac_init_debug(void)
-{
-	return register_sysrq_key('c', &emac_sysrq_op);
-}
-
-void __exit emac_fini_debug(void)
-{
-	unregister_sysrq_key('c', &emac_sysrq_op);
-}
-
-#else
-int __init emac_init_debug(void)
-{
-	return 0;
-}
-void __exit emac_fini_debug(void)
-{
-}
-#endif				/* CONFIG_MAGIC_SYSRQ */
diff --git a/drivers/net/ethernet/ibm/emac/debug.h b/drivers/net/ethernet/ibm/emac/debug.h
index 9c45efe4c8fe..5bdfc174a07e 100644
--- a/drivers/net/ethernet/ibm/emac/debug.h
+++ b/drivers/net/ethernet/ibm/emac/debug.h
@@ -25,32 +25,9 @@
 #include "core.h"
 
 #if defined(CONFIG_IBM_EMAC_DEBUG)
-
-struct emac_instance;
-struct mal_instance;
-
-void emac_dbg_register(struct emac_instance *dev);
-void emac_dbg_unregister(struct emac_instance *dev);
-void mal_dbg_register(struct mal_instance *mal);
-void mal_dbg_unregister(struct mal_instance *mal);
-int emac_init_debug(void) __init;
-void emac_fini_debug(void) __exit;
-void emac_dbg_dump_all(void);
-
 # define DBG_LEVEL		1
-
 #else
-
-# define emac_dbg_register(x)	do { } while(0)
-# define emac_dbg_unregister(x)	do { } while(0)
-# define mal_dbg_register(x)	do { } while(0)
-# define mal_dbg_unregister(x)	do { } while(0)
-# define emac_init_debug()	do { } while(0)
-# define emac_fini_debug()	do { } while(0)
-# define emac_dbg_dump_all()	do { } while(0)
-
 # define DBG_LEVEL		0
-
 #endif
 
 #define EMAC_DBG(d, name, fmt, arg...) \
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index cd3227b088b7..91b1a558f37d 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -695,8 +695,6 @@ static int mal_probe(struct platform_device *ofdev)
 	wmb();
 	platform_set_drvdata(ofdev, mal);
 
-	mal_dbg_register(mal);
-
 	return 0;
 
  fail6:
@@ -740,8 +738,6 @@ static int mal_remove(struct platform_device *ofdev)
 
 	mal_reset(mal);
 
-	mal_dbg_unregister(mal);
-
 	dma_free_coherent(&ofdev->dev,
 			  sizeof(struct mal_descriptor) *
 			  (NUM_TX_BUFF * mal->num_tx_chans +
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 7acda04d034e..ed8780cca982 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -146,7 +146,6 @@ struct ibmveth_adapter {
     struct vio_dev *vdev;
     struct net_device *netdev;
     struct napi_struct napi;
-    struct net_device_stats stats;
     unsigned int mcastFilterSize;
     void * buffer_list_addr;
     void * filter_list_addr;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 9198e6bd5160..4fcd2f0378ba 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -65,7 +65,6 @@
 #include <linux/irq.h>
 #include <linux/kthread.h>
 #include <linux/seq_file.h>
-#include <linux/debugfs.h>
 #include <linux/interrupt.h>
 #include <net/net_namespace.h>
 #include <asm/hvcall.h>
@@ -75,6 +74,7 @@
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
 #include <linux/workqueue.h>
+#include <linux/if_vlan.h>
 
 #include "ibmvnic.h"
 
@@ -89,7 +89,6 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
 static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
 static int ibmvnic_remove(struct vio_dev *);
 static void release_sub_crqs(struct ibmvnic_adapter *);
-static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *);
 static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
 static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
 static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
@@ -110,6 +109,11 @@ static int ibmvnic_poll(struct napi_struct *napi, int data);
 static void send_map_query(struct ibmvnic_adapter *adapter);
 static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
 static void send_request_unmap(struct ibmvnic_adapter *, u8);
+static void send_login(struct ibmvnic_adapter *adapter);
+static void send_cap_queries(struct ibmvnic_adapter *adapter);
+static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
+static int ibmvnic_init(struct ibmvnic_adapter *);
+static void release_crq_queue(struct ibmvnic_adapter *);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -159,21 +163,6 @@ static long h_reg_sub_crq(unsigned long unit_address, unsigned long token,
 	return rc;
 }
 
-/* net_device_ops functions */
-
-static void init_rx_pool(struct ibmvnic_adapter *adapter,
-			 struct ibmvnic_rx_pool *rx_pool, int num, int index,
-			 int buff_size, int active)
-{
-	netdev_dbg(adapter->netdev,
-		   "Initializing rx_pool %d, %d buffs, %d bytes each\n",
-		   index, num, buff_size);
-	rx_pool->size = num;
-	rx_pool->index = index;
-	rx_pool->buff_size = buff_size;
-	rx_pool->active = active;
-}
-
 static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 				struct ibmvnic_long_term_buff *ltb, int size)
 {
@@ -202,45 +191,12 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 {
 	struct device *dev = &adapter->vdev->dev;
 
-	dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
+	if (!ltb->buff)
+		return;
+
 	if (!adapter->failover)
 		send_request_unmap(adapter, ltb->map_id);
-}
-
-static int alloc_rx_pool(struct ibmvnic_adapter *adapter,
-			 struct ibmvnic_rx_pool *pool)
-{
-	struct device *dev = &adapter->vdev->dev;
-	int i;
-
-	pool->free_map = kcalloc(pool->size, sizeof(int), GFP_KERNEL);
-	if (!pool->free_map)
-		return -ENOMEM;
-
-	pool->rx_buff = kcalloc(pool->size, sizeof(struct ibmvnic_rx_buff),
-				GFP_KERNEL);
-
-	if (!pool->rx_buff) {
-		dev_err(dev, "Couldn't alloc rx buffers\n");
-		kfree(pool->free_map);
-		return -ENOMEM;
-	}
-
-	if (alloc_long_term_buff(adapter, &pool->long_term_buff,
-				 pool->size * pool->buff_size)) {
-		kfree(pool->free_map);
-		kfree(pool->rx_buff);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < pool->size; ++i)
-		pool->free_map[i] = i;
-
-	atomic_set(&pool->available, 0);
-	pool->next_alloc = 0;
-	pool->next_free = 0;
-
-	return 0;
+	dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
 }
 
 static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
@@ -347,114 +303,379 @@ static void replenish_pools(struct ibmvnic_adapter *adapter)
 	}
 }
 
-static void free_rx_pool(struct ibmvnic_adapter *adapter,
-			 struct ibmvnic_rx_pool *pool)
+static void release_stats_token(struct ibmvnic_adapter *adapter)
 {
-	int i;
+	struct device *dev = &adapter->vdev->dev;
+
+	if (!adapter->stats_token)
+		return;
+
+	dma_unmap_single(dev, adapter->stats_token,
+			 sizeof(struct ibmvnic_statistics),
+			 DMA_FROM_DEVICE);
+	adapter->stats_token = 0;
+}
+
+static int init_stats_token(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+	dma_addr_t stok;
+
+	stok = dma_map_single(dev, &adapter->stats,
+			      sizeof(struct ibmvnic_statistics),
+			      DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, stok)) {
+		dev_err(dev, "Couldn't map stats buffer\n");
+		return -1;
+	}
+
+	adapter->stats_token = stok;
+	return 0;
+}
 
-	kfree(pool->free_map);
-	pool->free_map = NULL;
+static void release_rx_pools(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_rx_pool *rx_pool;
+	int rx_scrqs;
+	int i, j;
 
-	if (!pool->rx_buff)
+	if (!adapter->rx_pool)
 		return;
 
-	for (i = 0; i < pool->size; i++) {
-		if (pool->rx_buff[i].skb) {
-			dev_kfree_skb_any(pool->rx_buff[i].skb);
-			pool->rx_buff[i].skb = NULL;
+	rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+	for (i = 0; i < rx_scrqs; i++) {
+		rx_pool = &adapter->rx_pool[i];
+
+		kfree(rx_pool->free_map);
+		free_long_term_buff(adapter, &rx_pool->long_term_buff);
+
+		if (!rx_pool->rx_buff)
+		continue;
+
+		for (j = 0; j < rx_pool->size; j++) {
+			if (rx_pool->rx_buff[j].skb) {
+				dev_kfree_skb_any(rx_pool->rx_buff[i].skb);
+				rx_pool->rx_buff[i].skb = NULL;
+			}
 		}
+
+		kfree(rx_pool->rx_buff);
 	}
-	kfree(pool->rx_buff);
-	pool->rx_buff = NULL;
+
+	kfree(adapter->rx_pool);
+	adapter->rx_pool = NULL;
 }
 
-static int ibmvnic_open(struct net_device *netdev)
+static int init_rx_pools(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_tx_pool *tx_pool;
-	union ibmvnic_crq crq;
+	struct ibmvnic_rx_pool *rx_pool;
 	int rxadd_subcrqs;
 	u64 *size_array;
-	int tx_subcrqs;
 	int i, j;
 
 	rxadd_subcrqs =
-	    be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
-	tx_subcrqs =
-	    be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+		be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
 	size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
-				  be32_to_cpu(adapter->login_rsp_buf->
-					      off_rxadd_buff_size));
-	adapter->map_id = 1;
-	adapter->napi = kcalloc(adapter->req_rx_queues,
-				sizeof(struct napi_struct), GFP_KERNEL);
-	if (!adapter->napi)
-		goto alloc_napi_failed;
-	for (i = 0; i < adapter->req_rx_queues; i++) {
-		netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll,
-			       NAPI_POLL_WEIGHT);
-		napi_enable(&adapter->napi[i]);
+		be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
+
+	adapter->rx_pool = kcalloc(rxadd_subcrqs,
+				   sizeof(struct ibmvnic_rx_pool),
+				   GFP_KERNEL);
+	if (!adapter->rx_pool) {
+		dev_err(dev, "Failed to allocate rx pools\n");
+		return -1;
 	}
-	adapter->rx_pool =
-	    kcalloc(rxadd_subcrqs, sizeof(struct ibmvnic_rx_pool), GFP_KERNEL);
 
-	if (!adapter->rx_pool)
-		goto rx_pool_arr_alloc_failed;
-	send_map_query(adapter);
 	for (i = 0; i < rxadd_subcrqs; i++) {
-		init_rx_pool(adapter, &adapter->rx_pool[i],
-			     IBMVNIC_BUFFS_PER_POOL, i,
-			     be64_to_cpu(size_array[i]), 1);
-		if (alloc_rx_pool(adapter, &adapter->rx_pool[i])) {
-			dev_err(dev, "Couldn't alloc rx pool\n");
-			goto rx_pool_alloc_failed;
+		rx_pool = &adapter->rx_pool[i];
+
+		netdev_dbg(adapter->netdev,
+			   "Initializing rx_pool %d, %lld buffs, %lld bytes each\n",
+			   i, adapter->req_rx_add_entries_per_subcrq,
+			   be64_to_cpu(size_array[i]));
+
+		rx_pool->size = adapter->req_rx_add_entries_per_subcrq;
+		rx_pool->index = i;
+		rx_pool->buff_size = be64_to_cpu(size_array[i]);
+		rx_pool->active = 1;
+
+		rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int),
+					    GFP_KERNEL);
+		if (!rx_pool->free_map) {
+			release_rx_pools(adapter);
+			return -1;
+		}
+
+		rx_pool->rx_buff = kcalloc(rx_pool->size,
+					   sizeof(struct ibmvnic_rx_buff),
+					   GFP_KERNEL);
+		if (!rx_pool->rx_buff) {
+			dev_err(dev, "Couldn't alloc rx buffers\n");
+			release_rx_pools(adapter);
+			return -1;
+		}
+
+		if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff,
+					 rx_pool->size * rx_pool->buff_size)) {
+			release_rx_pools(adapter);
+			return -1;
 		}
+
+		for (j = 0; j < rx_pool->size; ++j)
+			rx_pool->free_map[j] = j;
+
+		atomic_set(&rx_pool->available, 0);
+		rx_pool->next_alloc = 0;
+		rx_pool->next_free = 0;
+	}
+
+	return 0;
+}
+
+static void release_tx_pools(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_tx_pool *tx_pool;
+	int i, tx_scrqs;
+
+	if (!adapter->tx_pool)
+		return;
+
+	tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+	for (i = 0; i < tx_scrqs; i++) {
+		tx_pool = &adapter->tx_pool[i];
+		kfree(tx_pool->tx_buff);
+		free_long_term_buff(adapter, &tx_pool->long_term_buff);
+		kfree(tx_pool->free_map);
 	}
-	adapter->tx_pool =
-	    kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
 
+	kfree(adapter->tx_pool);
+	adapter->tx_pool = NULL;
+}
+
+static int init_tx_pools(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->vdev->dev;
+	struct ibmvnic_tx_pool *tx_pool;
+	int tx_subcrqs;
+	int i, j;
+
+	tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+	adapter->tx_pool = kcalloc(tx_subcrqs,
+				   sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
 	if (!adapter->tx_pool)
-		goto tx_pool_arr_alloc_failed;
+		return -1;
+
 	for (i = 0; i < tx_subcrqs; i++) {
 		tx_pool = &adapter->tx_pool[i];
-		tx_pool->tx_buff =
-		    kcalloc(adapter->max_tx_entries_per_subcrq,
-			    sizeof(struct ibmvnic_tx_buff), GFP_KERNEL);
-		if (!tx_pool->tx_buff)
-			goto tx_pool_alloc_failed;
+		tx_pool->tx_buff = kcalloc(adapter->req_tx_entries_per_subcrq,
+					   sizeof(struct ibmvnic_tx_buff),
+					   GFP_KERNEL);
+		if (!tx_pool->tx_buff) {
+			dev_err(dev, "tx pool buffer allocation failed\n");
+			release_tx_pools(adapter);
+			return -1;
+		}
 
 		if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
-					 adapter->max_tx_entries_per_subcrq *
-					 adapter->req_mtu))
-			goto tx_ltb_alloc_failed;
+					 adapter->req_tx_entries_per_subcrq *
+					 adapter->req_mtu)) {
+			release_tx_pools(adapter);
+			return -1;
+		}
 
-		tx_pool->free_map =
-		    kcalloc(adapter->max_tx_entries_per_subcrq,
-			    sizeof(int), GFP_KERNEL);
-		if (!tx_pool->free_map)
-			goto tx_fm_alloc_failed;
+		tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq,
+					    sizeof(int), GFP_KERNEL);
+		if (!tx_pool->free_map) {
+			release_tx_pools(adapter);
+			return -1;
+		}
 
-		for (j = 0; j < adapter->max_tx_entries_per_subcrq; j++)
+		for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++)
 			tx_pool->free_map[j] = j;
 
 		tx_pool->consumer_index = 0;
 		tx_pool->producer_index = 0;
 	}
-	adapter->bounce_buffer_size =
-	    (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1;
-	adapter->bounce_buffer = kmalloc(adapter->bounce_buffer_size,
-					 GFP_KERNEL);
-	if (!adapter->bounce_buffer)
-		goto bounce_alloc_failed;
 
-	adapter->bounce_buffer_dma = dma_map_single(dev, adapter->bounce_buffer,
-						    adapter->bounce_buffer_size,
-						    DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
-		dev_err(dev, "Couldn't map tx bounce buffer\n");
-		goto bounce_map_failed;
+	return 0;
+}
+
+static void release_error_buffers(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+	struct ibmvnic_error_buff *error_buff, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&adapter->error_list_lock, flags);
+	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list) {
+		list_del(&error_buff->list);
+		dma_unmap_single(dev, error_buff->dma, error_buff->len,
+				 DMA_FROM_DEVICE);
+		kfree(error_buff->buff);
+		kfree(error_buff);
+	}
+	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
+}
+
+static int ibmvnic_login(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	unsigned long timeout = msecs_to_jiffies(30000);
+	struct device *dev = &adapter->vdev->dev;
+
+	do {
+		if (adapter->renegotiate) {
+			adapter->renegotiate = false;
+			release_sub_crqs(adapter);
+
+			reinit_completion(&adapter->init_done);
+			send_cap_queries(adapter);
+			if (!wait_for_completion_timeout(&adapter->init_done,
+							 timeout)) {
+				dev_err(dev, "Capabilities query timeout\n");
+				return -1;
+			}
+		}
+
+		reinit_completion(&adapter->init_done);
+		send_login(adapter);
+		if (!wait_for_completion_timeout(&adapter->init_done,
+						 timeout)) {
+			dev_err(dev, "Login timeout\n");
+			return -1;
+		}
+	} while (adapter->renegotiate);
+
+	return 0;
+}
+
+static void release_resources(struct ibmvnic_adapter *adapter)
+{
+	release_tx_pools(adapter);
+	release_rx_pools(adapter);
+
+	release_stats_token(adapter);
+	release_error_buffers(adapter);
+}
+
+static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state)
+{
+	struct net_device *netdev = adapter->netdev;
+	unsigned long timeout = msecs_to_jiffies(30000);
+	union ibmvnic_crq crq;
+	bool resend;
+	int rc;
+
+	if (adapter->logical_link_state == link_state) {
+		netdev_dbg(netdev, "Link state already %d\n", link_state);
+		return 0;
+	}
+
+	netdev_err(netdev, "setting link state %d\n", link_state);
+	memset(&crq, 0, sizeof(crq));
+	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
+	crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
+	crq.logical_link_state.link_state = link_state;
+
+	do {
+		resend = false;
+
+		reinit_completion(&adapter->init_done);
+		rc = ibmvnic_send_crq(adapter, &crq);
+		if (rc) {
+			netdev_err(netdev, "Failed to set link state\n");
+			return rc;
+		}
+
+		if (!wait_for_completion_timeout(&adapter->init_done,
+						 timeout)) {
+			netdev_err(netdev, "timeout setting link state\n");
+			return -1;
+		}
+
+		if (adapter->init_done_rc == 1) {
+			/* Partuial success, delay and re-send */
+			mdelay(1000);
+			resend = true;
+		}
+	} while (resend);
+
+	return 0;
+}
+
+static int set_real_num_queues(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	int rc;
+
+	rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues);
+	if (rc) {
+		netdev_err(netdev, "failed to set the number of tx queues\n");
+		return rc;
+	}
+
+	rc = netif_set_real_num_rx_queues(netdev, adapter->req_rx_queues);
+	if (rc)
+		netdev_err(netdev, "failed to set the number of rx queues\n");
+
+	return rc;
+}
+
+static int ibmvnic_open(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->vdev->dev;
+	int rc = 0;
+	int i;
+
+	if (adapter->is_closed) {
+		rc = ibmvnic_init(adapter);
+		if (rc)
+			return rc;
+	}
+
+	rc = ibmvnic_login(netdev);
+	if (rc)
+		return rc;
+
+	rc = set_real_num_queues(netdev);
+	if (rc)
+		return rc;
+
+	rc = init_sub_crq_irqs(adapter);
+	if (rc) {
+		dev_err(dev, "failed to initialize sub crq irqs\n");
+		return -1;
+	}
+
+	rc = init_stats_token(adapter);
+	if (rc)
+		return rc;
+
+	adapter->map_id = 1;
+	adapter->napi = kcalloc(adapter->req_rx_queues,
+				sizeof(struct napi_struct), GFP_KERNEL);
+	if (!adapter->napi)
+		goto ibmvnic_open_fail;
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll,
+			       NAPI_POLL_WEIGHT);
+		napi_enable(&adapter->napi[i]);
 	}
+
+	send_map_query(adapter);
+
+	rc = init_rx_pools(netdev);
+	if (rc)
+		goto ibmvnic_open_fail;
+
+	rc = init_tx_pools(netdev);
+	if (rc)
+		goto ibmvnic_open_fail;
+
 	replenish_pools(adapter);
 
 	/* We're ready to receive frames, enable the sub-crq interrupts and
@@ -466,106 +687,63 @@ static int ibmvnic_open(struct net_device *netdev)
 	for (i = 0; i < adapter->req_tx_queues; i++)
 		enable_scrq_irq(adapter, adapter->tx_scrq[i]);
 
-	memset(&crq, 0, sizeof(crq));
-	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
-	crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
-	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP;
-	ibmvnic_send_crq(adapter, &crq);
+	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
+	if (rc)
+		goto ibmvnic_open_fail;
 
 	netif_tx_start_all_queues(netdev);
+	adapter->is_closed = false;
 
 	return 0;
 
-bounce_map_failed:
-	kfree(adapter->bounce_buffer);
-bounce_alloc_failed:
-	i = tx_subcrqs - 1;
-	kfree(adapter->tx_pool[i].free_map);
-tx_fm_alloc_failed:
-	free_long_term_buff(adapter, &adapter->tx_pool[i].long_term_buff);
-tx_ltb_alloc_failed:
-	kfree(adapter->tx_pool[i].tx_buff);
-tx_pool_alloc_failed:
-	for (j = 0; j < i; j++) {
-		kfree(adapter->tx_pool[j].tx_buff);
-		free_long_term_buff(adapter,
-				    &adapter->tx_pool[j].long_term_buff);
-		kfree(adapter->tx_pool[j].free_map);
-	}
-	kfree(adapter->tx_pool);
-	adapter->tx_pool = NULL;
-tx_pool_arr_alloc_failed:
-	i = rxadd_subcrqs;
-rx_pool_alloc_failed:
-	for (j = 0; j < i; j++) {
-		free_rx_pool(adapter, &adapter->rx_pool[j]);
-		free_long_term_buff(adapter,
-				    &adapter->rx_pool[j].long_term_buff);
-	}
-	kfree(adapter->rx_pool);
-	adapter->rx_pool = NULL;
-rx_pool_arr_alloc_failed:
+ibmvnic_open_fail:
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_disable(&adapter->napi[i]);
-alloc_napi_failed:
+	release_resources(adapter);
 	return -ENOMEM;
 }
 
+static void disable_sub_crqs(struct ibmvnic_adapter *adapter)
+{
+	int i;
+
+	if (adapter->tx_scrq) {
+		for (i = 0; i < adapter->req_tx_queues; i++)
+			if (adapter->tx_scrq[i])
+				disable_irq(adapter->tx_scrq[i]->irq);
+	}
+
+	if (adapter->rx_scrq) {
+		for (i = 0; i < adapter->req_rx_queues; i++)
+			if (adapter->rx_scrq[i])
+				disable_irq(adapter->rx_scrq[i]->irq);
+	}
+}
+
 static int ibmvnic_close(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq crq;
+	int rc = 0;
 	int i;
 
 	adapter->closing = true;
+	disable_sub_crqs(adapter);
 
-	for (i = 0; i < adapter->req_rx_queues; i++)
-		napi_disable(&adapter->napi[i]);
+	if (adapter->napi) {
+		for (i = 0; i < adapter->req_rx_queues; i++)
+			napi_disable(&adapter->napi[i]);
+	}
 
 	if (!adapter->failover)
 		netif_tx_stop_all_queues(netdev);
 
-	if (adapter->bounce_buffer) {
-		if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
-			dma_unmap_single(&adapter->vdev->dev,
-					 adapter->bounce_buffer_dma,
-					 adapter->bounce_buffer_size,
-					 DMA_BIDIRECTIONAL);
-			adapter->bounce_buffer_dma = DMA_ERROR_CODE;
-		}
-		kfree(adapter->bounce_buffer);
-		adapter->bounce_buffer = NULL;
-	}
-
-	memset(&crq, 0, sizeof(crq));
-	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
-	crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
-	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_DN;
-	ibmvnic_send_crq(adapter, &crq);
-
-	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
-	     i++) {
-		kfree(adapter->tx_pool[i].tx_buff);
-		free_long_term_buff(adapter,
-				    &adapter->tx_pool[i].long_term_buff);
-		kfree(adapter->tx_pool[i].free_map);
-	}
-	kfree(adapter->tx_pool);
-	adapter->tx_pool = NULL;
+	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_DN);
 
-	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
-	     i++) {
-		free_rx_pool(adapter, &adapter->rx_pool[i]);
-		free_long_term_buff(adapter,
-				    &adapter->rx_pool[i].long_term_buff);
-	}
-	kfree(adapter->rx_pool);
-	adapter->rx_pool = NULL;
+	release_resources(adapter);
 
+	adapter->is_closed = true;
 	adapter->closing = false;
-
-	return 0;
+	return rc;
 }
 
 /**
@@ -705,6 +883,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_tx_buff *tx_buff = NULL;
+	struct ibmvnic_sub_crq_queue *tx_scrq;
 	struct ibmvnic_tx_pool *tx_pool;
 	unsigned int tx_send_failed = 0;
 	unsigned int tx_map_failed = 0;
@@ -713,7 +892,6 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	unsigned int tx_bytes = 0;
 	dma_addr_t data_dma_addr;
 	struct netdev_queue *txq;
-	bool used_bounce = false;
 	unsigned long lpar_rc;
 	union sub_crq tx_crq;
 	unsigned int offset;
@@ -724,14 +902,19 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int ret = 0;
 
 	tx_pool = &adapter->tx_pool[queue_num];
+	tx_scrq = adapter->tx_scrq[queue_num];
 	txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
 	handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
 				   be32_to_cpu(adapter->login_rsp_buf->
 					       off_txsubm_subcrqs));
 	if (adapter->migrated) {
+		if (!netif_subqueue_stopped(netdev, skb))
+			netif_stop_subqueue(netdev, queue_num);
+		dev_kfree_skb_any(skb);
+
 		tx_send_failed++;
 		tx_dropped++;
-		ret = NETDEV_TX_BUSY;
+		ret = NETDEV_TX_OK;
 		goto out;
 	}
 
@@ -744,7 +927,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	tx_pool->consumer_index =
 	    (tx_pool->consumer_index + 1) %
-		adapter->max_tx_entries_per_subcrq;
+		adapter->req_tx_entries_per_subcrq;
 
 	tx_buff = &tx_pool->tx_buff[index];
 	tx_buff->skb = skb;
@@ -753,7 +936,6 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->index = index;
 	tx_buff->pool_index = queue_num;
 	tx_buff->last_frag = true;
-	tx_buff->used_bounce = used_bounce;
 
 	memset(&tx_crq, 0, sizeof(tx_crq));
 	tx_crq.v1.first = IBMVNIC_CRQ_CMD;
@@ -798,11 +980,13 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 						    sizeof(tx_buff->indir_arr),
 						    DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, tx_buff->indir_dma)) {
+			dev_kfree_skb_any(skb);
+			tx_buff->skb = NULL;
 			if (!firmware_has_feature(FW_FEATURE_CMO))
 				dev_err(dev, "tx: unable to map descriptor array\n");
 			tx_map_failed++;
 			tx_dropped++;
-			ret = NETDEV_TX_BUSY;
+			ret = NETDEV_TX_OK;
 			goto out;
 		}
 		lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
@@ -817,15 +1001,28 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 		if (tx_pool->consumer_index == 0)
 			tx_pool->consumer_index =
-				adapter->max_tx_entries_per_subcrq - 1;
+				adapter->req_tx_entries_per_subcrq - 1;
 		else
 			tx_pool->consumer_index--;
 
+		dev_kfree_skb_any(skb);
+		tx_buff->skb = NULL;
+
+		if (lpar_rc == H_CLOSED)
+			netif_stop_subqueue(netdev, queue_num);
+
 		tx_send_failed++;
 		tx_dropped++;
-		ret = NETDEV_TX_BUSY;
+		ret = NETDEV_TX_OK;
 		goto out;
 	}
+
+	if (atomic_inc_return(&tx_scrq->used)
+					>= adapter->req_tx_entries_per_subcrq) {
+		netdev_info(netdev, "Stopping queue %d\n", queue_num);
+		netif_stop_subqueue(netdev, queue_num);
+	}
+
 	tx_packets++;
 	tx_bytes += skb->len;
 	txq->trans_start = jiffies;
@@ -965,7 +1162,15 @@ restart_poll:
 		skb = rx_buff->skb;
 		skb_copy_to_linear_data(skb, rx_buff->data + offset,
 					length);
-		skb->vlan_tci = be16_to_cpu(next->rx_comp.vlan_tci);
+
+		/* VLAN Header has been stripped by the system firmware and
+		 * needs to be inserted by the driver
+		 */
+		if (adapter->rx_vlan_header_insertion &&
+		    (flags & IBMVNIC_VLAN_STRIPPED))
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       ntohs(next->rx_comp.vlan_tci));
+
 		/* free the entry */
 		next->rx_comp.first = 0;
 		remove_buff_from_pool(adapter, rx_buff);
@@ -1166,6 +1371,12 @@ static void release_sub_crq_queue(struct ibmvnic_adapter *adapter,
 					scrq->crq_num);
 	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
 
+	if (rc) {
+		netdev_err(adapter->netdev,
+			   "Failed to release sub-CRQ %16lx, rc = %ld\n",
+			   scrq->crq_num, rc);
+	}
+
 	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);
 	free_pages((unsigned long)scrq->msgs, 2);
@@ -1179,12 +1390,12 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 	struct ibmvnic_sub_crq_queue *scrq;
 	int rc;
 
-	scrq = kmalloc(sizeof(*scrq), GFP_ATOMIC);
+	scrq = kzalloc(sizeof(*scrq), GFP_KERNEL);
 	if (!scrq)
 		return NULL;
 
-	scrq->msgs = (union sub_crq *)__get_free_pages(GFP_ATOMIC, 2);
-	memset(scrq->msgs, 0, 4 * PAGE_SIZE);
+	scrq->msgs =
+		(union sub_crq *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 2);
 	if (!scrq->msgs) {
 		dev_warn(dev, "Couldn't allocate crq queue messages page\n");
 		goto zero_page_failed;
@@ -1212,8 +1423,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 
 	scrq->adapter = adapter;
 	scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
-	scrq->cur = 0;
-	scrq->rx_skb_top = NULL;
 	spin_lock_init(&scrq->lock);
 
 	netdev_dbg(adapter->netdev,
@@ -1238,47 +1447,40 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter)
 	int i;
 
 	if (adapter->tx_scrq) {
-		for (i = 0; i < adapter->req_tx_queues; i++)
-			if (adapter->tx_scrq[i]) {
+		for (i = 0; i < adapter->req_tx_queues; i++) {
+			if (!adapter->tx_scrq[i])
+				continue;
+
+			if (adapter->tx_scrq[i]->irq) {
 				free_irq(adapter->tx_scrq[i]->irq,
 					 adapter->tx_scrq[i]);
 				irq_dispose_mapping(adapter->tx_scrq[i]->irq);
-				release_sub_crq_queue(adapter,
-						      adapter->tx_scrq[i]);
+				adapter->tx_scrq[i]->irq = 0;
 			}
+
+			release_sub_crq_queue(adapter, adapter->tx_scrq[i]);
+		}
+
+		kfree(adapter->tx_scrq);
 		adapter->tx_scrq = NULL;
 	}
 
 	if (adapter->rx_scrq) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			if (adapter->rx_scrq[i]) {
+		for (i = 0; i < adapter->req_rx_queues; i++) {
+			if (!adapter->rx_scrq[i])
+				continue;
+
+			if (adapter->rx_scrq[i]->irq) {
 				free_irq(adapter->rx_scrq[i]->irq,
 					 adapter->rx_scrq[i]);
 				irq_dispose_mapping(adapter->rx_scrq[i]->irq);
-				release_sub_crq_queue(adapter,
-						      adapter->rx_scrq[i]);
+				adapter->rx_scrq[i]->irq = 0;
 			}
-		adapter->rx_scrq = NULL;
-	}
-}
-
-static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter)
-{
-	int i;
 
-	if (adapter->tx_scrq) {
-		for (i = 0; i < adapter->req_tx_queues; i++)
-			if (adapter->tx_scrq[i])
-				release_sub_crq_queue(adapter,
-						      adapter->tx_scrq[i]);
-		adapter->tx_scrq = NULL;
-	}
+			release_sub_crq_queue(adapter, adapter->rx_scrq[i]);
+		}
 
-	if (adapter->rx_scrq) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			if (adapter->rx_scrq[i])
-				release_sub_crq_queue(adapter,
-						      adapter->rx_scrq[i]);
+		kfree(adapter->rx_scrq);
 		adapter->rx_scrq = NULL;
 	}
 }
@@ -1345,7 +1547,6 @@ restart_loop:
 					continue;
 
 				txbuff->data_dma[j] = 0;
-				txbuff->used_bounce = false;
 			}
 			/* if sub_crq was sent indirectly */
 			first = txbuff->indir_arr[0].generic.first;
@@ -1355,14 +1556,27 @@ restart_loop:
 						 DMA_TO_DEVICE);
 			}
 
-			if (txbuff->last_frag)
+			if (txbuff->last_frag) {
+				if (atomic_sub_return(next->tx_comp.num_comps,
+						      &scrq->used) <=
+				    (adapter->req_tx_entries_per_subcrq / 2) &&
+				    netif_subqueue_stopped(adapter->netdev,
+							   txbuff->skb)) {
+					netif_wake_subqueue(adapter->netdev,
+							    scrq->pool_index);
+					netdev_dbg(adapter->netdev,
+						   "Started queue %d\n",
+						   scrq->pool_index);
+				}
+
 				dev_kfree_skb_any(txbuff->skb);
+			}
 
 			adapter->tx_pool[pool].free_map[adapter->tx_pool[pool].
 						     producer_index] = index;
 			adapter->tx_pool[pool].producer_index =
 			    (adapter->tx_pool[pool].producer_index + 1) %
-			    adapter->max_tx_entries_per_subcrq;
+			    adapter->req_tx_entries_per_subcrq;
 		}
 		/* remove tx_comp scrq*/
 		next->tx_comp.first = 0;
@@ -1460,52 +1674,24 @@ req_tx_irq_failed:
 		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
 		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
 	}
-	release_sub_crqs_no_irqs(adapter);
+	release_sub_crqs(adapter);
 	return rc;
 }
 
-static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
+static int init_sub_crqs(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_sub_crq_queue **allqueues;
 	int registered_queues = 0;
-	union ibmvnic_crq crq;
 	int total_queues;
 	int more = 0;
 	int i;
 
-	if (!retry) {
-		/* Sub-CRQ entries are 32 byte long */
-		int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4);
-
-		if (adapter->min_tx_entries_per_subcrq > entries_page ||
-		    adapter->min_rx_add_entries_per_subcrq > entries_page) {
-			dev_err(dev, "Fatal, invalid entries per sub-crq\n");
-			goto allqueues_failed;
-		}
-
-		/* Get the minimum between the queried max and the entries
-		 * that fit in our PAGE_SIZE
-		 */
-		adapter->req_tx_entries_per_subcrq =
-		    adapter->max_tx_entries_per_subcrq > entries_page ?
-		    entries_page : adapter->max_tx_entries_per_subcrq;
-		adapter->req_rx_add_entries_per_subcrq =
-		    adapter->max_rx_add_entries_per_subcrq > entries_page ?
-		    entries_page : adapter->max_rx_add_entries_per_subcrq;
-
-		adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues;
-		adapter->req_rx_queues = adapter->opt_rx_comp_queues;
-		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
-
-		adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
-	}
-
 	total_queues = adapter->req_tx_queues + adapter->req_rx_queues;
 
-	allqueues = kcalloc(total_queues, sizeof(*allqueues), GFP_ATOMIC);
+	allqueues = kcalloc(total_queues, sizeof(*allqueues), GFP_KERNEL);
 	if (!allqueues)
-		goto allqueues_failed;
+		return -1;
 
 	for (i = 0; i < total_queues; i++) {
 		allqueues[i] = init_sub_crq_queue(adapter);
@@ -1543,7 +1729,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	}
 
 	adapter->tx_scrq = kcalloc(adapter->req_tx_queues,
-				   sizeof(*adapter->tx_scrq), GFP_ATOMIC);
+				   sizeof(*adapter->tx_scrq), GFP_KERNEL);
 	if (!adapter->tx_scrq)
 		goto tx_failed;
 
@@ -1553,7 +1739,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	}
 
 	adapter->rx_scrq = kcalloc(adapter->req_rx_queues,
-				   sizeof(*adapter->rx_scrq), GFP_ATOMIC);
+				   sizeof(*adapter->rx_scrq), GFP_KERNEL);
 	if (!adapter->rx_scrq)
 		goto rx_failed;
 
@@ -1562,6 +1748,51 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 		adapter->rx_scrq[i]->scrq_num = i;
 	}
 
+	kfree(allqueues);
+	return 0;
+
+rx_failed:
+	kfree(adapter->tx_scrq);
+	adapter->tx_scrq = NULL;
+tx_failed:
+	for (i = 0; i < registered_queues; i++)
+		release_sub_crq_queue(adapter, allqueues[i]);
+	kfree(allqueues);
+	return -1;
+}
+
+static void ibmvnic_send_req_caps(struct ibmvnic_adapter *adapter, int retry)
+{
+	struct device *dev = &adapter->vdev->dev;
+	union ibmvnic_crq crq;
+
+	if (!retry) {
+		/* Sub-CRQ entries are 32 byte long */
+		int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4);
+
+		if (adapter->min_tx_entries_per_subcrq > entries_page ||
+		    adapter->min_rx_add_entries_per_subcrq > entries_page) {
+			dev_err(dev, "Fatal, invalid entries per sub-crq\n");
+			return;
+		}
+
+		/* Get the minimum between the queried max and the entries
+		 * that fit in our PAGE_SIZE
+		 */
+		adapter->req_tx_entries_per_subcrq =
+		    adapter->max_tx_entries_per_subcrq > entries_page ?
+		    entries_page : adapter->max_tx_entries_per_subcrq;
+		adapter->req_rx_add_entries_per_subcrq =
+		    adapter->max_rx_add_entries_per_subcrq > entries_page ?
+		    entries_page : adapter->max_rx_add_entries_per_subcrq;
+
+		adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues;
+		adapter->req_rx_queues = adapter->opt_rx_comp_queues;
+		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
+
+		adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
+	}
+
 	memset(&crq, 0, sizeof(crq));
 	crq.request_capability.first = IBMVNIC_CRQ_CMD;
 	crq.request_capability.cmd = REQUEST_CAPABILITY;
@@ -1615,20 +1846,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 		atomic_inc(&adapter->running_cap_crqs);
 		ibmvnic_send_crq(adapter, &crq);
 	}
-
-	kfree(allqueues);
-
-	return;
-
-rx_failed:
-	kfree(adapter->tx_scrq);
-	adapter->tx_scrq = NULL;
-tx_failed:
-	for (i = 0; i < registered_queues; i++)
-		release_sub_crq_queue(adapter, allqueues[i]);
-	kfree(allqueues);
-allqueues_failed:
-	ibmvnic_remove(adapter->vdev);
 }
 
 static int pending_scrq(struct ibmvnic_adapter *adapter,
@@ -1802,13 +2019,11 @@ static void send_login(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
 	struct ibmvnic_login_buffer *login_buffer;
-	struct ibmvnic_inflight_cmd *inflight_cmd;
 	struct device *dev = &adapter->vdev->dev;
 	dma_addr_t rsp_buffer_token;
 	dma_addr_t buffer_token;
 	size_t rsp_buffer_size;
 	union ibmvnic_crq crq;
-	unsigned long flags;
 	size_t buffer_size;
 	__be64 *tx_list_p;
 	__be64 *rx_list_p;
@@ -1845,11 +2060,7 @@ static void send_login(struct ibmvnic_adapter *adapter)
 		dev_err(dev, "Couldn't map login rsp buffer\n");
 		goto buf_rsp_map_failed;
 	}
-	inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
-	if (!inflight_cmd) {
-		dev_err(dev, "Couldn't allocate inflight_cmd\n");
-		goto inflight_alloc_failed;
-	}
+
 	adapter->login_buf = login_buffer;
 	adapter->login_buf_token = buffer_token;
 	adapter->login_buf_sz = buffer_size;
@@ -1900,20 +2111,10 @@ static void send_login(struct ibmvnic_adapter *adapter)
 	crq.login.cmd = LOGIN;
 	crq.login.ioba = cpu_to_be32(buffer_token);
 	crq.login.len = cpu_to_be32(buffer_size);
-
-	memcpy(&inflight_cmd->crq, &crq, sizeof(crq));
-
-	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_add_tail(&inflight_cmd->list, &adapter->inflight);
-	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
-
 	ibmvnic_send_crq(adapter, &crq);
 
 	return;
 
-inflight_alloc_failed:
-	dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size,
-			 DMA_FROM_DEVICE);
 buf_rsp_map_failed:
 	kfree(login_rsp_buffer);
 buf_rsp_alloc_failed:
@@ -2037,6 +2238,10 @@ static void send_cap_queries(struct ibmvnic_adapter *adapter)
 	atomic_inc(&adapter->running_cap_crqs);
 	ibmvnic_send_crq(adapter, &crq);
 
+	crq.query_capability.capability = cpu_to_be16(RX_VLAN_HEADER_INSERTION);
+	atomic_inc(&adapter->running_cap_crqs);
+	ibmvnic_send_crq(adapter, &crq);
+
 	crq.query_capability.capability = cpu_to_be16(MAX_TX_SG_ENTRIES);
 	atomic_inc(&adapter->running_cap_crqs);
 	ibmvnic_send_crq(adapter, &crq);
@@ -2215,77 +2420,22 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 	kfree(error_buff);
 }
 
-static void handle_dump_size_rsp(union ibmvnic_crq *crq,
-				 struct ibmvnic_adapter *adapter)
-{
-	int len = be32_to_cpu(crq->request_dump_size_rsp.len);
-	struct ibmvnic_inflight_cmd *inflight_cmd;
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq newcrq;
-	unsigned long flags;
-
-	/* allocate and map buffer */
-	adapter->dump_data = kmalloc(len, GFP_KERNEL);
-	if (!adapter->dump_data) {
-		complete(&adapter->fw_done);
-		return;
-	}
-
-	adapter->dump_data_token = dma_map_single(dev, adapter->dump_data, len,
-						  DMA_FROM_DEVICE);
-
-	if (dma_mapping_error(dev, adapter->dump_data_token)) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(dev, "Couldn't map dump data\n");
-		kfree(adapter->dump_data);
-		complete(&adapter->fw_done);
-		return;
-	}
-
-	inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
-	if (!inflight_cmd) {
-		dma_unmap_single(dev, adapter->dump_data_token, len,
-				 DMA_FROM_DEVICE);
-		kfree(adapter->dump_data);
-		complete(&adapter->fw_done);
-		return;
-	}
-
-	memset(&newcrq, 0, sizeof(newcrq));
-	newcrq.request_dump.first = IBMVNIC_CRQ_CMD;
-	newcrq.request_dump.cmd = REQUEST_DUMP;
-	newcrq.request_dump.ioba = cpu_to_be32(adapter->dump_data_token);
-	newcrq.request_dump.len = cpu_to_be32(adapter->dump_data_size);
-
-	memcpy(&inflight_cmd->crq, &newcrq, sizeof(newcrq));
-
-	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_add_tail(&inflight_cmd->list, &adapter->inflight);
-	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
-
-	ibmvnic_send_crq(adapter, &newcrq);
-}
-
-static void handle_error_indication(union ibmvnic_crq *crq,
-				    struct ibmvnic_adapter *adapter)
+static void request_error_information(struct ibmvnic_adapter *adapter,
+				      union ibmvnic_crq *err_crq)
 {
-	int detail_len = be32_to_cpu(crq->error_indication.detail_error_sz);
-	struct ibmvnic_inflight_cmd *inflight_cmd;
 	struct device *dev = &adapter->vdev->dev;
+	struct net_device *netdev = adapter->netdev;
 	struct ibmvnic_error_buff *error_buff;
-	union ibmvnic_crq new_crq;
+	unsigned long timeout = msecs_to_jiffies(30000);
+	union ibmvnic_crq crq;
 	unsigned long flags;
-
-	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
-		crq->error_indication.
-		    flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "",
-		be32_to_cpu(crq->error_indication.error_id),
-		be16_to_cpu(crq->error_indication.error_cause));
+	int rc, detail_len;
 
 	error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
 	if (!error_buff)
 		return;
 
+	detail_len = be32_to_cpu(err_crq->error_indication.detail_error_sz);
 	error_buff->buff = kmalloc(detail_len, GFP_ATOMIC);
 	if (!error_buff->buff) {
 		kfree(error_buff);
@@ -2295,43 +2445,61 @@ static void handle_error_indication(union ibmvnic_crq *crq,
 	error_buff->dma = dma_map_single(dev, error_buff->buff, detail_len,
 					 DMA_FROM_DEVICE);
 	if (dma_mapping_error(dev, error_buff->dma)) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(dev, "Couldn't map error buffer\n");
-		kfree(error_buff->buff);
-		kfree(error_buff);
-		return;
-	}
-
-	inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
-	if (!inflight_cmd) {
-		dma_unmap_single(dev, error_buff->dma, detail_len,
-				 DMA_FROM_DEVICE);
+		netdev_err(netdev, "Couldn't map error buffer\n");
 		kfree(error_buff->buff);
 		kfree(error_buff);
 		return;
 	}
 
 	error_buff->len = detail_len;
-	error_buff->error_id = crq->error_indication.error_id;
+	error_buff->error_id = err_crq->error_indication.error_id;
 
 	spin_lock_irqsave(&adapter->error_list_lock, flags);
 	list_add_tail(&error_buff->list, &adapter->errors);
 	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
 
-	memset(&new_crq, 0, sizeof(new_crq));
-	new_crq.request_error_info.first = IBMVNIC_CRQ_CMD;
-	new_crq.request_error_info.cmd = REQUEST_ERROR_INFO;
-	new_crq.request_error_info.ioba = cpu_to_be32(error_buff->dma);
-	new_crq.request_error_info.len = cpu_to_be32(detail_len);
-	new_crq.request_error_info.error_id = crq->error_indication.error_id;
+	memset(&crq, 0, sizeof(crq));
+	crq.request_error_info.first = IBMVNIC_CRQ_CMD;
+	crq.request_error_info.cmd = REQUEST_ERROR_INFO;
+	crq.request_error_info.ioba = cpu_to_be32(error_buff->dma);
+	crq.request_error_info.len = cpu_to_be32(detail_len);
+	crq.request_error_info.error_id = err_crq->error_indication.error_id;
+
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc) {
+		netdev_err(netdev, "failed to request error information\n");
+		goto err_info_fail;
+	}
+
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+		netdev_err(netdev, "timeout waiting for error information\n");
+		goto err_info_fail;
+	}
+
+	return;
+
+err_info_fail:
+	spin_lock_irqsave(&adapter->error_list_lock, flags);
+	list_del(&error_buff->list);
+	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
+
+	kfree(error_buff->buff);
+	kfree(error_buff);
+}
 
-	memcpy(&inflight_cmd->crq, &crq, sizeof(crq));
+static void handle_error_indication(union ibmvnic_crq *crq,
+				    struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
 
-	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_add_tail(&inflight_cmd->list, &adapter->inflight);
-	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
+	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
+		crq->error_indication.flags
+			& IBMVNIC_FATAL_ERROR ? "FATAL " : "",
+		be32_to_cpu(crq->error_indication.error_id),
+		be16_to_cpu(crq->error_indication.error_cause));
 
-	ibmvnic_send_crq(adapter, &new_crq);
+	if (be32_to_cpu(crq->error_indication.error_id))
+		request_error_information(adapter, crq);
 }
 
 static void handle_change_mac_rsp(union ibmvnic_crq *crq,
@@ -2401,9 +2569,9 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 			 *req_value,
 			 (long int)be64_to_cpu(crq->request_capability_rsp.
 					       number), name);
-		release_sub_crqs_no_irqs(adapter);
+		release_sub_crqs(adapter);
 		*req_value = be64_to_cpu(crq->request_capability_rsp.number);
-		init_sub_crqs(adapter, 1);
+		ibmvnic_send_req_caps(adapter, 1);
 		return;
 	default:
 		dev_err(dev, "Error %d in request cap rsp\n",
@@ -2446,7 +2614,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf;
 	struct ibmvnic_login_buffer *login = adapter->login_buf;
-	union ibmvnic_crq crq;
 	int i;
 
 	dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
@@ -2481,11 +2648,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	}
 	complete(&adapter->init_done);
 
-	memset(&crq, 0, sizeof(crq));
-	crq.request_ras_comp_num.first = IBMVNIC_CRQ_CMD;
-	crq.request_ras_comp_num.cmd = REQUEST_RAS_COMP_NUM;
-	ibmvnic_send_crq(adapter, &crq);
-
 	return 0;
 }
 
@@ -2660,6 +2822,12 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 		netdev_dbg(netdev, "vlan_header_insertion = %lld\n",
 			   adapter->vlan_header_insertion);
 		break;
+	case RX_VLAN_HEADER_INSERTION:
+		adapter->rx_vlan_header_insertion =
+		    be64_to_cpu(crq->query_capability.number);
+		netdev_dbg(netdev, "rx_vlan_header_insertion = %lld\n",
+			   adapter->rx_vlan_header_insertion);
+		break;
 	case MAX_TX_SG_ENTRIES:
 		adapter->max_tx_sg_entries =
 		    be64_to_cpu(crq->query_capability.number);
@@ -2716,524 +2884,8 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 out:
 	if (atomic_read(&adapter->running_cap_crqs) == 0) {
 		adapter->wait_capability = false;
-		init_sub_crqs(adapter, 0);
-		/* We're done querying the capabilities, initialize sub-crqs */
-	}
-}
-
-static void handle_control_ras_rsp(union ibmvnic_crq *crq,
-				   struct ibmvnic_adapter *adapter)
-{
-	u8 correlator = crq->control_ras_rsp.correlator;
-	struct device *dev = &adapter->vdev->dev;
-	bool found = false;
-	int i;
-
-	if (crq->control_ras_rsp.rc.code) {
-		dev_warn(dev, "Control ras failed rc=%d\n",
-			 crq->control_ras_rsp.rc.code);
-		return;
-	}
-
-	for (i = 0; i < adapter->ras_comp_num; i++) {
-		if (adapter->ras_comps[i].correlator == correlator) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		dev_warn(dev, "Correlator not found on control_ras_rsp\n");
-		return;
-	}
-
-	switch (crq->control_ras_rsp.op) {
-	case IBMVNIC_TRACE_LEVEL:
-		adapter->ras_comps[i].trace_level = crq->control_ras.level;
-		break;
-	case IBMVNIC_ERROR_LEVEL:
-		adapter->ras_comps[i].error_check_level =
-		    crq->control_ras.level;
-		break;
-	case IBMVNIC_TRACE_PAUSE:
-		adapter->ras_comp_int[i].paused = 1;
-		break;
-	case IBMVNIC_TRACE_RESUME:
-		adapter->ras_comp_int[i].paused = 0;
-		break;
-	case IBMVNIC_TRACE_ON:
-		adapter->ras_comps[i].trace_on = 1;
-		break;
-	case IBMVNIC_TRACE_OFF:
-		adapter->ras_comps[i].trace_on = 0;
-		break;
-	case IBMVNIC_CHG_TRACE_BUFF_SZ:
-		/* trace_buff_sz is 3 bytes, stuff it into an int */
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[0] = 0;
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[1] =
-		    crq->control_ras_rsp.trace_buff_sz[0];
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[2] =
-		    crq->control_ras_rsp.trace_buff_sz[1];
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[3] =
-		    crq->control_ras_rsp.trace_buff_sz[2];
-		break;
-	default:
-		dev_err(dev, "invalid op %d on control_ras_rsp",
-			crq->control_ras_rsp.op);
-	}
-}
-
-static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len,
-			  loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_fw_trace_entry *trace;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	dma_addr_t trace_tok;
-
-	if (*ppos >= be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
-		return 0;
-
-	trace =
-	    dma_alloc_coherent(dev,
-			       be32_to_cpu(adapter->ras_comps[num].
-					   trace_buff_size), &trace_tok,
-			       GFP_KERNEL);
-	if (!trace) {
-		dev_err(dev, "Couldn't alloc trace buffer\n");
-		return 0;
+		ibmvnic_send_req_caps(adapter, 0);
 	}
-
-	memset(&crq, 0, sizeof(crq));
-	crq.collect_fw_trace.first = IBMVNIC_CRQ_CMD;
-	crq.collect_fw_trace.cmd = COLLECT_FW_TRACE;
-	crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
-	crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
-	crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
-
-	init_completion(&adapter->fw_done);
-	ibmvnic_send_crq(adapter, &crq);
-	wait_for_completion(&adapter->fw_done);
-
-	if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
-		len =
-		    be32_to_cpu(adapter->ras_comps[num].trace_buff_size) -
-		    *ppos;
-
-	copy_to_user(user_buf, &((u8 *)trace)[*ppos], len);
-
-	dma_free_coherent(dev,
-			  be32_to_cpu(adapter->ras_comps[num].trace_buff_size),
-			  trace, trace_tok);
-	*ppos += len;
-	return len;
-}
-
-static const struct file_operations trace_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= trace_read,
-};
-
-static ssize_t paused_read(struct file *file, char __user *user_buf, size_t len,
-			   loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /*  1 or 0 plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comp_int[num].paused);
-
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t paused_write(struct file *file, const char __user *user_buf,
-			    size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	adapter->ras_comp_int[num].paused = val ? 1 : 0;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator = adapter->ras_comps[num].correlator;
-	crq.control_ras.op = val ? IBMVNIC_TRACE_PAUSE : IBMVNIC_TRACE_RESUME;
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations paused_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= paused_read,
-	.write		= paused_write,
-};
-
-static ssize_t tracing_read(struct file *file, char __user *user_buf,
-			    size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /*  1 or 0 plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_on);
-
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t tracing_write(struct file *file, const char __user *user_buf,
-			     size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator = adapter->ras_comps[num].correlator;
-	crq.control_ras.op = val ? IBMVNIC_TRACE_ON : IBMVNIC_TRACE_OFF;
-
-	return len;
-}
-
-static const struct file_operations tracing_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= tracing_read,
-	.write		= tracing_write,
-};
-
-static ssize_t error_level_read(struct file *file, char __user *user_buf,
-				size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /* decimal max char plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].error_check_level);
-
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t error_level_write(struct file *file, const char __user *user_buf,
-				 size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	if (val > 9)
-		val = 9;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator = adapter->ras_comps[num].correlator;
-	crq.control_ras.op = IBMVNIC_ERROR_LEVEL;
-	crq.control_ras.level = val;
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations error_level_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= error_level_read,
-	.write		= error_level_write,
-};
-
-static ssize_t trace_level_read(struct file *file, char __user *user_buf,
-				size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /* decimal max char plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_level);
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t trace_level_write(struct file *file, const char __user *user_buf,
-				 size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-	if (val > 9)
-		val = 9;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator =
-	    adapter->ras_comps[ras_comp_int->num].correlator;
-	crq.control_ras.op = IBMVNIC_TRACE_LEVEL;
-	crq.control_ras.level = val;
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations trace_level_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= trace_level_read,
-	.write		= trace_level_write,
-};
-
-static ssize_t trace_buff_size_read(struct file *file, char __user *user_buf,
-				    size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[9]; /* decimal max int plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_buff_size);
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t trace_buff_size_write(struct file *file,
-				     const char __user *user_buf, size_t len,
-				     loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator =
-	    adapter->ras_comps[ras_comp_int->num].correlator;
-	crq.control_ras.op = IBMVNIC_CHG_TRACE_BUFF_SZ;
-	/* trace_buff_sz is 3 bytes, stuff an int into it */
-	crq.control_ras.trace_buff_sz[0] = ((u8 *)(&val))[5];
-	crq.control_ras.trace_buff_sz[1] = ((u8 *)(&val))[6];
-	crq.control_ras.trace_buff_sz[2] = ((u8 *)(&val))[7];
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations trace_size_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= trace_buff_size_read,
-	.write		= trace_buff_size_write,
-};
-
-static void handle_request_ras_comps_rsp(union ibmvnic_crq *crq,
-					 struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct dentry *dir_ent;
-	struct dentry *ent;
-	int i;
-
-	debugfs_remove_recursive(adapter->ras_comps_ent);
-
-	adapter->ras_comps_ent = debugfs_create_dir("ras_comps",
-						    adapter->debugfs_dir);
-	if (!adapter->ras_comps_ent || IS_ERR(adapter->ras_comps_ent)) {
-		dev_info(dev, "debugfs create ras_comps dir failed\n");
-		return;
-	}
-
-	for (i = 0; i < adapter->ras_comp_num; i++) {
-		dir_ent = debugfs_create_dir(adapter->ras_comps[i].name,
-					     adapter->ras_comps_ent);
-		if (!dir_ent || IS_ERR(dir_ent)) {
-			dev_info(dev, "debugfs create %s dir failed\n",
-				 adapter->ras_comps[i].name);
-			continue;
-		}
-
-		adapter->ras_comp_int[i].adapter = adapter;
-		adapter->ras_comp_int[i].num = i;
-		adapter->ras_comp_int[i].desc_blob.data =
-		    &adapter->ras_comps[i].description;
-		adapter->ras_comp_int[i].desc_blob.size =
-		    sizeof(adapter->ras_comps[i].description);
-
-		/* Don't need to remember the dentry's because the debugfs dir
-		 * gets removed recursively
-		 */
-		ent = debugfs_create_blob("description", S_IRUGO, dir_ent,
-					  &adapter->ras_comp_int[i].desc_blob);
-		ent = debugfs_create_file("trace_buf_size", S_IRUGO | S_IWUSR,
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &trace_size_ops);
-		ent = debugfs_create_file("trace_level",
-					  S_IRUGO |
-					  (adapter->ras_comps[i].trace_level !=
-					   0xFF  ? S_IWUSR : 0),
-					   dir_ent, &adapter->ras_comp_int[i],
-					   &trace_level_ops);
-		ent = debugfs_create_file("error_level",
-					  S_IRUGO |
-					  (adapter->
-					   ras_comps[i].error_check_level !=
-					   0xFF ? S_IWUSR : 0),
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &trace_level_ops);
-		ent = debugfs_create_file("tracing", S_IRUGO | S_IWUSR,
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &tracing_ops);
-		ent = debugfs_create_file("paused", S_IRUGO | S_IWUSR,
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &paused_ops);
-		ent = debugfs_create_file("trace", S_IRUGO, dir_ent,
-					  &adapter->ras_comp_int[i],
-					  &trace_ops);
-	}
-}
-
-static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq,
-					    struct ibmvnic_adapter *adapter)
-{
-	int len = adapter->ras_comp_num * sizeof(struct ibmvnic_fw_component);
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq newcrq;
-
-	adapter->ras_comps = dma_alloc_coherent(dev, len,
-						&adapter->ras_comps_tok,
-						GFP_KERNEL);
-	if (!adapter->ras_comps) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(dev, "Couldn't alloc fw comps buffer\n");
-		return;
-	}
-
-	adapter->ras_comp_int = kmalloc(adapter->ras_comp_num *
-					sizeof(struct ibmvnic_fw_comp_internal),
-					GFP_KERNEL);
-	if (!adapter->ras_comp_int)
-		dma_free_coherent(dev, len, adapter->ras_comps,
-				  adapter->ras_comps_tok);
-
-	memset(&newcrq, 0, sizeof(newcrq));
-	newcrq.request_ras_comps.first = IBMVNIC_CRQ_CMD;
-	newcrq.request_ras_comps.cmd = REQUEST_RAS_COMPS;
-	newcrq.request_ras_comps.ioba = cpu_to_be32(adapter->ras_comps_tok);
-	newcrq.request_ras_comps.len = cpu_to_be32(len);
-	ibmvnic_send_crq(adapter, &newcrq);
-}
-
-static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
-{
-	struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff, *tmp2;
-	unsigned long flags;
-	unsigned long flags2;
-
-	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) {
-		switch (inflight_cmd->crq.generic.cmd) {
-		case LOGIN:
-			dma_unmap_single(dev, adapter->login_buf_token,
-					 adapter->login_buf_sz,
-					 DMA_BIDIRECTIONAL);
-			dma_unmap_single(dev, adapter->login_rsp_buf_token,
-					 adapter->login_rsp_buf_sz,
-					 DMA_BIDIRECTIONAL);
-			kfree(adapter->login_rsp_buf);
-			kfree(adapter->login_buf);
-			break;
-		case REQUEST_DUMP:
-			complete(&adapter->fw_done);
-			break;
-		case REQUEST_ERROR_INFO:
-			spin_lock_irqsave(&adapter->error_list_lock, flags2);
-			list_for_each_entry_safe(error_buff, tmp2,
-						 &adapter->errors, list) {
-				dma_unmap_single(dev, error_buff->dma,
-						 error_buff->len,
-						 DMA_FROM_DEVICE);
-				kfree(error_buff->buff);
-				list_del(&error_buff->list);
-				kfree(error_buff);
-			}
-			spin_unlock_irqrestore(&adapter->error_list_lock,
-					       flags2);
-			break;
-		}
-		list_del(&inflight_cmd->list);
-		kfree(inflight_cmd);
-	}
-	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
 }
 
 static void ibmvnic_xport_event(struct work_struct *work)
@@ -3244,7 +2896,6 @@ static void ibmvnic_xport_event(struct work_struct *work)
 	struct device *dev = &adapter->vdev->dev;
 	long rc;
 
-	ibmvnic_free_inflight(adapter);
 	release_sub_crqs(adapter);
 	if (adapter->migrated) {
 		rc = ibmvnic_reenable_crq_queue(adapter);
@@ -3263,11 +2914,12 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 	struct ibmvnic_generic_crq *gen_crq = &crq->generic;
 	struct net_device *netdev = adapter->netdev;
 	struct device *dev = &adapter->vdev->dev;
+	u64 *u64_crq = (u64 *)crq;
 	long rc;
 
 	netdev_dbg(netdev, "Handling CRQ: %016lx %016lx\n",
-		   ((unsigned long int *)crq)[0],
-		   ((unsigned long int *)crq)[1]);
+		   (unsigned long int)cpu_to_be64(u64_crq[0]),
+		   (unsigned long int)cpu_to_be64(u64_crq[1]));
 	switch (gen_crq->first) {
 	case IBMVNIC_CRQ_INIT_RSP:
 		switch (gen_crq->cmd) {
@@ -3347,9 +2999,14 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		handle_login_rsp(crq, adapter);
 		break;
 	case LOGICAL_LINK_STATE_RSP:
-		netdev_dbg(netdev, "Got Logical Link State Response\n");
+		netdev_dbg(netdev,
+			   "Got Logical Link State Response, state: %d rc: %d\n",
+			   crq->logical_link_state_rsp.link_state,
+			   crq->logical_link_state_rsp.rc.code);
 		adapter->logical_link_state =
 		    crq->logical_link_state_rsp.link_state;
+		adapter->init_done_rc = crq->logical_link_state_rsp.rc.code;
+		complete(&adapter->init_done);
 		break;
 	case LINK_STATE_INDICATION:
 		netdev_dbg(netdev, "Got Logical Link State Indication\n");
@@ -3374,14 +3031,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		netdev_dbg(netdev, "Got Statistics Response\n");
 		complete(&adapter->stats_done);
 		break;
-	case REQUEST_DUMP_SIZE_RSP:
-		netdev_dbg(netdev, "Got Request Dump Size Response\n");
-		handle_dump_size_rsp(crq, adapter);
-		break;
-	case REQUEST_DUMP_RSP:
-		netdev_dbg(netdev, "Got Request Dump Response\n");
-		complete(&adapter->fw_done);
-		break;
 	case QUERY_IP_OFFLOAD_RSP:
 		netdev_dbg(netdev, "Got Query IP offload Response\n");
 		handle_query_ip_offload_rsp(adapter);
@@ -3394,26 +3043,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		dma_unmap_single(dev, adapter->ip_offload_ctrl_tok,
 				 sizeof(adapter->ip_offload_ctrl),
 				 DMA_TO_DEVICE);
-		/* We're done with the queries, perform the login */
-		send_login(adapter);
-		break;
-	case REQUEST_RAS_COMP_NUM_RSP:
-		netdev_dbg(netdev, "Got Request RAS Comp Num Response\n");
-		if (crq->request_ras_comp_num_rsp.rc.code == 10) {
-			netdev_dbg(netdev, "Request RAS Comp Num not supported\n");
-			break;
-		}
-		adapter->ras_comp_num =
-		    be32_to_cpu(crq->request_ras_comp_num_rsp.num_components);
-		handle_request_ras_comp_num_rsp(crq, adapter);
-		break;
-	case REQUEST_RAS_COMPS_RSP:
-		netdev_dbg(netdev, "Got Request RAS Comps Response\n");
-		handle_request_ras_comps_rsp(crq, adapter);
-		break;
-	case CONTROL_RAS_RSP:
-		netdev_dbg(netdev, "Got Control RAS Response\n");
-		handle_control_ras_rsp(crq, adapter);
+		complete(&adapter->init_done);
 		break;
 	case COLLECT_FW_TRACE_RSP:
 		netdev_dbg(netdev, "Got Collect firmware trace Response\n");
@@ -3428,12 +3058,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 static irqreturn_t ibmvnic_interrupt(int irq, void *instance)
 {
 	struct ibmvnic_adapter *adapter = instance;
-	unsigned long flags;
 
-	spin_lock_irqsave(&adapter->crq.lock, flags);
-	vio_disable_interrupts(adapter->vdev);
 	tasklet_schedule(&adapter->tasklet);
-	spin_unlock_irqrestore(&adapter->crq.lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -3441,32 +3067,23 @@ static void ibmvnic_tasklet(void *data)
 {
 	struct ibmvnic_adapter *adapter = data;
 	struct ibmvnic_crq_queue *queue = &adapter->crq;
-	struct vio_dev *vdev = adapter->vdev;
 	union ibmvnic_crq *crq;
 	unsigned long flags;
 	bool done = false;
 
 	spin_lock_irqsave(&queue->lock, flags);
-	vio_disable_interrupts(vdev);
 	while (!done) {
 		/* Pull all the valid messages off the CRQ */
 		while ((crq = ibmvnic_next_crq(adapter)) != NULL) {
 			ibmvnic_handle_crq(crq, adapter);
 			crq->generic.first = 0;
 		}
-		vio_enable_interrupts(vdev);
-		crq = ibmvnic_next_crq(adapter);
-		if (crq) {
-			vio_disable_interrupts(vdev);
-			ibmvnic_handle_crq(crq, adapter);
-			crq->generic.first = 0;
-		} else {
-			/* remain in tasklet until all
-			 * capabilities responses are received
-			 */
-			if (!adapter->wait_capability)
-				done = true;
-		}
+
+		/* remain in tasklet until all
+		 * capabilities responses are received
+		 */
+		if (!adapter->wait_capability)
+			done = true;
 	}
 	/* if capabilities CRQ's were sent in this tasklet, the following
 	 * tasklet must wait until all responses are received
@@ -3520,12 +3137,15 @@ static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter)
 	return rc;
 }
 
-static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter)
+static void release_crq_queue(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_crq_queue *crq = &adapter->crq;
 	struct vio_dev *vdev = adapter->vdev;
 	long rc;
 
+	if (!crq->msgs)
+		return;
+
 	netdev_dbg(adapter->netdev, "Releasing CRQ\n");
 	free_irq(vdev->irq, adapter);
 	tasklet_kill(&adapter->tasklet);
@@ -3536,15 +3156,19 @@ static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter)
 	dma_unmap_single(&vdev->dev, crq->msg_token, PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);
 	free_page((unsigned long)crq->msgs);
+	crq->msgs = NULL;
 }
 
-static int ibmvnic_init_crq_queue(struct ibmvnic_adapter *adapter)
+static int init_crq_queue(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_crq_queue *crq = &adapter->crq;
 	struct device *dev = &adapter->vdev->dev;
 	struct vio_dev *vdev = adapter->vdev;
 	int rc, retrc = -ENOMEM;
 
+	if (crq->msgs)
+		return 0;
+
 	crq->msgs = (union ibmvnic_crq *)get_zeroed_page(GFP_KERNEL);
 	/* Should we allocate more than one page? */
 
@@ -3606,48 +3230,10 @@ reg_crq_failed:
 	dma_unmap_single(dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
 map_failed:
 	free_page((unsigned long)crq->msgs);
+	crq->msgs = NULL;
 	return retrc;
 }
 
-/* debugfs for dump */
-static int ibmvnic_dump_show(struct seq_file *seq, void *v)
-{
-	struct net_device *netdev = seq->private;
-	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq crq;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
-	crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
-
-	init_completion(&adapter->fw_done);
-	ibmvnic_send_crq(adapter, &crq);
-	wait_for_completion(&adapter->fw_done);
-
-	seq_write(seq, adapter->dump_data, adapter->dump_data_size);
-
-	dma_unmap_single(dev, adapter->dump_data_token, adapter->dump_data_size,
-			 DMA_BIDIRECTIONAL);
-
-	kfree(adapter->dump_data);
-
-	return 0;
-}
-
-static int ibmvnic_dump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ibmvnic_dump_show, inode->i_private);
-}
-
-static const struct file_operations ibmvnic_dump_ops = {
-	.owner          = THIS_MODULE,
-	.open           = ibmvnic_dump_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = single_release,
-};
-
 static void handle_crq_init_rsp(struct work_struct *work)
 {
 	struct ibmvnic_adapter *adapter = container_of(work,
@@ -3675,26 +3261,6 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		goto task_failed;
 	}
 
-	do {
-		if (adapter->renegotiate) {
-			adapter->renegotiate = false;
-			release_sub_crqs_no_irqs(adapter);
-
-			reinit_completion(&adapter->init_done);
-			send_cap_queries(adapter);
-			if (!wait_for_completion_timeout(&adapter->init_done,
-							 timeout)) {
-				dev_err(dev, "Passive init timeout\n");
-				goto task_failed;
-			}
-		}
-	} while (adapter->renegotiate);
-	rc = init_sub_crq_irqs(adapter);
-
-	if (rc)
-		goto task_failed;
-
-	netdev->real_num_tx_queues = adapter->req_tx_queues;
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	if (adapter->failover) {
@@ -3726,14 +3292,40 @@ task_failed:
 	dev_err(dev, "Passive initialization was not successful\n");
 }
 
-static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
+static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 {
+	struct device *dev = &adapter->vdev->dev;
 	unsigned long timeout = msecs_to_jiffies(30000);
+	int rc;
+
+	rc = init_crq_queue(adapter);
+	if (rc) {
+		dev_err(dev, "Couldn't initialize crq. rc=%d\n", rc);
+		return rc;
+	}
+
+	init_completion(&adapter->init_done);
+	ibmvnic_send_crq_init(adapter);
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+		dev_err(dev, "Initialization sequence timed out\n");
+		release_crq_queue(adapter);
+		return -1;
+	}
+
+	rc = init_sub_crqs(adapter);
+	if (rc) {
+		dev_err(dev, "Initialization of sub crqs failed\n");
+		release_crq_queue(adapter);
+	}
+
+	return rc;
+}
+
+static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
+{
 	struct ibmvnic_adapter *adapter;
 	struct net_device *netdev;
 	unsigned char *mac_addr_p;
-	struct dentry *ent;
-	char buf[17]; /* debugfs name buf */
 	int rc;
 
 	dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n",
@@ -3771,91 +3363,27 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	spin_lock_init(&adapter->stats_lock);
 
-	rc = ibmvnic_init_crq_queue(adapter);
-	if (rc) {
-		dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", rc);
-		goto free_netdev;
-	}
-
 	INIT_LIST_HEAD(&adapter->errors);
-	INIT_LIST_HEAD(&adapter->inflight);
 	spin_lock_init(&adapter->error_list_lock);
-	spin_lock_init(&adapter->inflight_lock);
-
-	adapter->stats_token = dma_map_single(&dev->dev, &adapter->stats,
-					      sizeof(struct ibmvnic_statistics),
-					      DMA_FROM_DEVICE);
-	if (dma_mapping_error(&dev->dev, adapter->stats_token)) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(&dev->dev, "Couldn't map stats buffer\n");
-		rc = -ENOMEM;
-		goto free_crq;
-	}
-
-	snprintf(buf, sizeof(buf), "ibmvnic_%x", dev->unit_address);
-	ent = debugfs_create_dir(buf, NULL);
-	if (!ent || IS_ERR(ent)) {
-		dev_info(&dev->dev, "debugfs create directory failed\n");
-		adapter->debugfs_dir = NULL;
-	} else {
-		adapter->debugfs_dir = ent;
-		ent = debugfs_create_file("dump", S_IRUGO, adapter->debugfs_dir,
-					  netdev, &ibmvnic_dump_ops);
-		if (!ent || IS_ERR(ent)) {
-			dev_info(&dev->dev,
-				 "debugfs create dump file failed\n");
-			adapter->debugfs_dump = NULL;
-		} else {
-			adapter->debugfs_dump = ent;
-		}
-	}
 
-	init_completion(&adapter->init_done);
-	ibmvnic_send_crq_init(adapter);
-	if (!wait_for_completion_timeout(&adapter->init_done, timeout))
-		return 0;
-
-	do {
-		if (adapter->renegotiate) {
-			adapter->renegotiate = false;
-			release_sub_crqs_no_irqs(adapter);
-
-			reinit_completion(&adapter->init_done);
-			send_cap_queries(adapter);
-			if (!wait_for_completion_timeout(&adapter->init_done,
-							 timeout))
-				return 0;
-		}
-	} while (adapter->renegotiate);
-
-	rc = init_sub_crq_irqs(adapter);
+	rc = ibmvnic_init(adapter);
 	if (rc) {
-		dev_err(&dev->dev, "failed to initialize sub crq irqs\n");
-		goto free_debugfs;
+		free_netdev(netdev);
+		return rc;
 	}
 
-	netdev->real_num_tx_queues = adapter->req_tx_queues;
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
+	adapter->is_closed = false;
 
 	rc = register_netdev(netdev);
 	if (rc) {
 		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
-		goto free_sub_crqs;
+		free_netdev(netdev);
+		return rc;
 	}
 	dev_info(&dev->dev, "ibmvnic registered\n");
 
 	return 0;
-
-free_sub_crqs:
-	release_sub_crqs(adapter);
-free_debugfs:
-	if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
-		debugfs_remove_recursive(adapter->debugfs_dir);
-free_crq:
-	ibmvnic_release_crq_queue(adapter);
-free_netdev:
-	free_netdev(netdev);
-	return rc;
 }
 
 static int ibmvnic_remove(struct vio_dev *dev)
@@ -3865,23 +3393,9 @@ static int ibmvnic_remove(struct vio_dev *dev)
 
 	unregister_netdev(netdev);
 
+	release_resources(adapter);
 	release_sub_crqs(adapter);
-
-	ibmvnic_release_crq_queue(adapter);
-
-	if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
-		debugfs_remove_recursive(adapter->debugfs_dir);
-
-	dma_unmap_single(&dev->dev, adapter->stats_token,
-			 sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE);
-
-	if (adapter->ras_comps)
-		dma_free_coherent(&dev->dev,
-				  adapter->ras_comp_num *
-				  sizeof(struct ibmvnic_fw_component),
-				  adapter->ras_comps, adapter->ras_comps_tok);
-
-	kfree(adapter->ras_comp_int);
+	release_crq_queue(adapter);
 
 	free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
@@ -3906,7 +3420,6 @@ static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev)
 	adapter = netdev_priv(netdev);
 
 	ret += PAGE_SIZE; /* the crq message queue */
-	ret += adapter->bounce_buffer_size;
 	ret += IOMMU_PAGE_ALIGN(sizeof(struct ibmvnic_statistics), tbl);
 
 	for (i = 0; i < adapter->req_tx_queues + adapter->req_rx_queues; i++)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 422824f1f42a..a69979f6f19d 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -518,8 +518,8 @@ struct ibmvnic_change_mac_addr {
 	u8 first;
 	u8 cmd;
 	u8 mac_addr[6];
-	struct ibmvnic_rc rc;
 	u8 reserved[4];
+	struct ibmvnic_rc rc;
 } __packed __aligned(8);
 
 struct ibmvnic_multicast_ctrl {
@@ -733,6 +733,7 @@ enum ibmvnic_capabilities {
 	REQ_MTU = 21,
 	MAX_MULTICAST_FILTERS = 22,
 	VLAN_HEADER_INSERTION = 23,
+	RX_VLAN_HEADER_INSERTION = 24,
 	MAX_TX_SG_ENTRIES = 25,
 	RX_SG_SUPPORTED = 26,
 	RX_SG_REQUESTED = 27,
@@ -772,20 +773,10 @@ enum ibmvnic_commands {
 	ERROR_INDICATION = 0x08,
 	REQUEST_ERROR_INFO = 0x09,
 	REQUEST_ERROR_RSP = 0x89,
-	REQUEST_DUMP_SIZE = 0x0A,
-	REQUEST_DUMP_SIZE_RSP = 0x8A,
-	REQUEST_DUMP = 0x0B,
-	REQUEST_DUMP_RSP = 0x8B,
 	LOGICAL_LINK_STATE = 0x0C,
 	LOGICAL_LINK_STATE_RSP = 0x8C,
 	REQUEST_STATISTICS = 0x0D,
 	REQUEST_STATISTICS_RSP = 0x8D,
-	REQUEST_RAS_COMP_NUM = 0x0E,
-	REQUEST_RAS_COMP_NUM_RSP = 0x8E,
-	REQUEST_RAS_COMPS = 0x0F,
-	REQUEST_RAS_COMPS_RSP = 0x8F,
-	CONTROL_RAS = 0x10,
-	CONTROL_RAS_RSP = 0x90,
 	COLLECT_FW_TRACE = 0x11,
 	COLLECT_FW_TRACE_RSP = 0x91,
 	LINK_STATE_INDICATION = 0x12,
@@ -806,8 +797,6 @@ enum ibmvnic_commands {
 	ACL_CHANGE_INDICATION = 0x1A,
 	ACL_QUERY = 0x1B,
 	ACL_QUERY_RSP = 0x9B,
-	REQUEST_DEBUG_STATS = 0x1C,
-	REQUEST_DEBUG_STATS_RSP = 0x9C,
 	QUERY_MAP = 0x1D,
 	QUERY_MAP_RSP = 0x9D,
 	REQUEST_MAP = 0x1E,
@@ -863,6 +852,7 @@ struct ibmvnic_sub_crq_queue {
 	spinlock_t lock;
 	struct sk_buff *rx_skb_top;
 	struct ibmvnic_adapter *adapter;
+	atomic_t used;
 };
 
 struct ibmvnic_long_term_buff {
@@ -879,7 +869,6 @@ struct ibmvnic_tx_buff {
 	int index;
 	int pool_index;
 	bool last_frag;
-	bool used_bounce;
 	union sub_crq indir_arr[6];
 	u8 hdr_data[140];
 	dma_addr_t indir_dma;
@@ -924,18 +913,6 @@ struct ibmvnic_error_buff {
 	__be32 error_id;
 };
 
-struct ibmvnic_fw_comp_internal {
-	struct ibmvnic_adapter *adapter;
-	int num;
-	struct debugfs_blob_wrapper desc_blob;
-	int paused;
-};
-
-struct ibmvnic_inflight_cmd {
-	union ibmvnic_crq crq;
-	struct list_head list;
-};
-
 struct ibmvnic_adapter {
 	struct vio_dev *vdev;
 	struct net_device *netdev;
@@ -947,12 +924,8 @@ struct ibmvnic_adapter {
 	dma_addr_t ip_offload_ctrl_tok;
 	bool migrated;
 	u32 msg_enable;
-	void *bounce_buffer;
-	int bounce_buffer_size;
-	dma_addr_t bounce_buffer_dma;
 
 	/* Statistics */
-	struct net_device_stats net_stats;
 	struct ibmvnic_statistics stats;
 	dma_addr_t stats_token;
 	struct completion stats_done;
@@ -991,26 +964,12 @@ struct ibmvnic_adapter {
 	struct ibmvnic_tx_pool *tx_pool;
 	bool closing;
 	struct completion init_done;
+	int init_done_rc;
 
 	struct list_head errors;
 	spinlock_t error_list_lock;
 
-	/* debugfs */
-	struct dentry *debugfs_dir;
-	struct dentry *debugfs_dump;
 	struct completion fw_done;
-	char *dump_data;
-	dma_addr_t dump_data_token;
-	int dump_data_size;
-	int ras_comp_num;
-	struct ibmvnic_fw_component *ras_comps;
-	struct ibmvnic_fw_comp_internal *ras_comp_int;
-	dma_addr_t ras_comps_tok;
-	struct dentry *ras_comps_ent;
-
-	/* in-flight commands that allocate and/or map memory*/
-	struct list_head inflight;
-	spinlock_t inflight_lock;
 
 	/* partner capabilities */
 	u64 min_tx_queues;
@@ -1036,6 +995,7 @@ struct ibmvnic_adapter {
 	u64 req_mtu;
 	u64 max_multicast_filters;
 	u64 vlan_header_insertion;
+	u64 rx_vlan_header_insertion;
 	u64 max_tx_sg_entries;
 	u64 rx_sg_supported;
 	u64 rx_sg_requested;
@@ -1051,4 +1011,5 @@ struct ibmvnic_adapter {
 	struct work_struct ibmvnic_xport;
 	struct tasklet_struct tasklet;
 	bool failover;
+	bool is_closed;
 };
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 1349b45f014d..1542a2158e96 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -235,17 +235,6 @@ config I40E_DCB
 
 	  If unsure, say N.
 
-config I40E_FCOE
-	bool "Fibre Channel over Ethernet (FCoE)"
-	default n
-	depends on I40E && DCB && FCOE
-	---help---
-	  Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
-	  in the driver. This will create new netdev for exclusive FCoE
-	  use with XL710 FCoE offloads enabled.
-
-	  If unsure, say N.
-
 config I40EVF
 	tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
 	depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 975eeb885ca2..ec8aa4562cc9 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -103,104 +103,104 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define E1000_TEST_LEN	ARRAY_SIZE(e1000_gstrings_test)
 
-static int e1000_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 supported, advertising;
 
 	if (hw->media_type == e1000_media_type_copper) {
-		ecmd->supported = (SUPPORTED_10baseT_Half |
-				   SUPPORTED_10baseT_Full |
-				   SUPPORTED_100baseT_Half |
-				   SUPPORTED_100baseT_Full |
-				   SUPPORTED_1000baseT_Full|
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP);
-		ecmd->advertising = ADVERTISED_TP;
+		supported = (SUPPORTED_10baseT_Half |
+			     SUPPORTED_10baseT_Full |
+			     SUPPORTED_100baseT_Half |
+			     SUPPORTED_100baseT_Full |
+			     SUPPORTED_1000baseT_Full|
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_TP);
+		advertising = ADVERTISED_TP;
 
 		if (hw->autoneg == 1) {
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 			/* the e1000 autoneg seems to match ethtool nicely */
-			ecmd->advertising |= hw->autoneg_advertised;
+			advertising |= hw->autoneg_advertised;
 		}
 
-		ecmd->port = PORT_TP;
-		ecmd->phy_address = hw->phy_addr;
-
-		if (hw->mac_type == e1000_82543)
-			ecmd->transceiver = XCVR_EXTERNAL;
-		else
-			ecmd->transceiver = XCVR_INTERNAL;
-
+		cmd->base.port = PORT_TP;
+		cmd->base.phy_address = hw->phy_addr;
 	} else {
-		ecmd->supported   = (SUPPORTED_1000baseT_Full |
-				     SUPPORTED_FIBRE |
-				     SUPPORTED_Autoneg);
+		supported   = (SUPPORTED_1000baseT_Full |
+			       SUPPORTED_FIBRE |
+			       SUPPORTED_Autoneg);
 
-		ecmd->advertising = (ADVERTISED_1000baseT_Full |
-				     ADVERTISED_FIBRE |
-				     ADVERTISED_Autoneg);
+		advertising = (ADVERTISED_1000baseT_Full |
+			       ADVERTISED_FIBRE |
+			       ADVERTISED_Autoneg);
 
-		ecmd->port = PORT_FIBRE;
-
-		if (hw->mac_type >= e1000_82545)
-			ecmd->transceiver = XCVR_INTERNAL;
-		else
-			ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.port = PORT_FIBRE;
 	}
 
 	if (er32(STATUS) & E1000_STATUS_LU) {
 		e1000_get_speed_and_duplex(hw, &adapter->link_speed,
 					   &adapter->link_duplex);
-		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+		cmd->base.speed = adapter->link_speed;
 
 		/* unfortunately FULL_DUPLEX != DUPLEX_FULL
 		 * and HALF_DUPLEX != DUPLEX_HALF
 		 */
 		if (adapter->link_duplex == FULL_DUPLEX)
-			ecmd->duplex = DUPLEX_FULL;
+			cmd->base.duplex = DUPLEX_FULL;
 		else
-			ecmd->duplex = DUPLEX_HALF;
+			cmd->base.duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) ||
+	cmd->base.autoneg = ((hw->media_type == e1000_media_type_fiber) ||
 			 hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
 
 	/* MDI-X => 1; MDI => 0 */
 	if ((hw->media_type == e1000_media_type_copper) &&
 	    netif_carrier_ok(netdev))
-		ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
+		cmd->base.eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
 				     ETH_TP_MDI_X : ETH_TP_MDI);
 	else
-		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
 
 	if (hw->mdix == AUTO_ALL_MODES)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
 	else
-		ecmd->eth_tp_mdix_ctrl = hw->mdix;
+		cmd->base.eth_tp_mdix_ctrl = hw->mdix;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
+
 	return 0;
 }
 
-static int e1000_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	/* MDI setting is only allowed when autoneg enabled because
 	 * some hardware doesn't allow MDI setting when speed or
 	 * duplex is forced.
 	 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (hw->media_type != e1000_media_type_copper)
 			return -EOPNOTSUPP;
 
-		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
-		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			return -EINVAL;
 		}
@@ -209,32 +209,31 @@ static int e1000_set_settings(struct net_device *netdev,
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
 
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		hw->autoneg = 1;
 		if (hw->media_type == e1000_media_type_fiber)
 			hw->autoneg_advertised = ADVERTISED_1000baseT_Full |
-				     ADVERTISED_FIBRE |
-				     ADVERTISED_Autoneg;
+						 ADVERTISED_FIBRE |
+						 ADVERTISED_Autoneg;
 		else
-			hw->autoneg_advertised = ecmd->advertising |
+			hw->autoneg_advertised = advertising |
 						 ADVERTISED_TP |
 						 ADVERTISED_Autoneg;
-		ecmd->advertising = hw->autoneg_advertised;
 	} else {
-		u32 speed = ethtool_cmd_speed(ecmd);
+		u32 speed = cmd->base.speed;
 		/* calling this overrides forced MDI setting */
-		if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+		if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
 			clear_bit(__E1000_RESETTING, &adapter->flags);
 			return -EINVAL;
 		}
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
-	if (ecmd->eth_tp_mdix_ctrl) {
-		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
 			hw->mdix = AUTO_ALL_MODES;
 		else
-			hw->mdix = ecmd->eth_tp_mdix_ctrl;
+			hw->mdix = cmd->base.eth_tp_mdix_ctrl;
 	}
 
 	/* reset the link */
@@ -1875,8 +1874,6 @@ static void e1000_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 static const struct ethtool_ops e1000_ethtool_ops = {
-	.get_settings		= e1000_get_settings,
-	.set_settings		= e1000_set_settings,
 	.get_drvinfo		= e1000_get_drvinfo,
 	.get_regs_len		= e1000_get_regs_len,
 	.get_regs		= e1000_get_regs,
@@ -1901,6 +1898,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 	.get_coalesce		= e1000_get_coalesce,
 	.set_coalesce		= e1000_set_coalesce,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_link_ksettings	= e1000_get_link_ksettings,
+	.set_link_ksettings	= e1000_set_link_ksettings,
 };
 
 void e1000_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 93fc6c67306b..bd8b05fe8258 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -131,7 +131,6 @@ static void e1000_watchdog(struct work_struct *work);
 static void e1000_82547_tx_fifo_stall_task(struct work_struct *work);
 static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				    struct net_device *netdev);
-static struct net_device_stats *e1000_get_stats(struct net_device *netdev);
 static int e1000_change_mtu(struct net_device *netdev, int new_mtu);
 static int e1000_set_mac(struct net_device *netdev, void *p);
 static irqreturn_t e1000_intr(int irq, void *data);
@@ -846,7 +845,6 @@ static const struct net_device_ops e1000_netdev_ops = {
 	.ndo_open		= e1000_open,
 	.ndo_stop		= e1000_close,
 	.ndo_start_xmit		= e1000_xmit_frame,
-	.ndo_get_stats		= e1000_get_stats,
 	.ndo_set_rx_mode	= e1000_set_rx_mode,
 	.ndo_set_mac_address	= e1000_set_mac,
 	.ndo_tx_timeout		= e1000_tx_timeout,
@@ -3530,19 +3528,6 @@ static void e1000_reset_task(struct work_struct *work)
 }
 
 /**
- * e1000_get_stats - Get System Network Statistics
- * @netdev: network interface device structure
- *
- * Returns the address of the device statistics structure.
- * The statistics are actually updated from the watchdog.
- **/
-static struct net_device_stats *e1000_get_stats(struct net_device *netdev)
-{
-	/* only return the current stats */
-	return &netdev->stats;
-}
-
-/**
  * e1000_change_mtu - Change the Maximum Transfer Unit
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index a29b12e80855..c7c994eb410e 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -135,7 +135,8 @@ enum e1000_boards {
 	board_pchlan,
 	board_pch2lan,
 	board_pch_lpt,
-	board_pch_spt
+	board_pch_spt,
+	board_pch_cnp
 };
 
 struct e1000_ps_page {
@@ -378,18 +379,22 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
  * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n)
  * bits to count nanoseconds leaving the rest for fractional nonseconds.
  */
-#define INCVALUE_96MHz		125
-#define INCVALUE_SHIFT_96MHz	17
-#define INCPERIOD_SHIFT_96MHz	2
-#define INCPERIOD_96MHz		(12 >> INCPERIOD_SHIFT_96MHz)
+#define INCVALUE_96MHZ		125
+#define INCVALUE_SHIFT_96MHZ	17
+#define INCPERIOD_SHIFT_96MHZ	2
+#define INCPERIOD_96MHZ		(12 >> INCPERIOD_SHIFT_96MHZ)
 
-#define INCVALUE_25MHz		40
-#define INCVALUE_SHIFT_25MHz	18
-#define INCPERIOD_25MHz		1
+#define INCVALUE_25MHZ		40
+#define INCVALUE_SHIFT_25MHZ	18
+#define INCPERIOD_25MHZ		1
 
-#define INCVALUE_24MHz		125
-#define INCVALUE_SHIFT_24MHz	14
-#define INCPERIOD_24MHz		3
+#define INCVALUE_24MHZ		125
+#define INCVALUE_SHIFT_24MHZ	14
+#define INCPERIOD_24MHZ		3
+
+#define INCVALUE_38400KHZ	26
+#define INCVALUE_SHIFT_38400KHZ	19
+#define INCPERIOD_38400KHZ	1
 
 /* Another drawback of scaling the incvalue by a large factor is the
  * 64-bit SYSTIM register overflows more quickly.  This is dealt with
@@ -515,6 +520,7 @@ extern const struct e1000_info e1000_pch_info;
 extern const struct e1000_info e1000_pch2_info;
 extern const struct e1000_info e1000_pch_lpt_info;
 extern const struct e1000_info e1000_pch_spt_info;
+extern const struct e1000_info e1000_pch_cnp_info;
 extern const struct e1000_info e1000_es2_info;
 
 void e1000e_ptp_init(struct e1000_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 7aff68a4a4df..e23dbd9190d6 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -117,55 +117,52 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define E1000_TEST_LEN ARRAY_SIZE(e1000_gstrings_test)
 
-static int e1000_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 speed;
+	u32 speed, supported, advertising;
 
 	if (hw->phy.media_type == e1000_media_type_copper) {
-		ecmd->supported = (SUPPORTED_10baseT_Half |
-				   SUPPORTED_10baseT_Full |
-				   SUPPORTED_100baseT_Half |
-				   SUPPORTED_100baseT_Full |
-				   SUPPORTED_1000baseT_Full |
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP);
+		supported = (SUPPORTED_10baseT_Half |
+			     SUPPORTED_10baseT_Full |
+			     SUPPORTED_100baseT_Half |
+			     SUPPORTED_100baseT_Full |
+			     SUPPORTED_1000baseT_Full |
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_TP);
 		if (hw->phy.type == e1000_phy_ife)
-			ecmd->supported &= ~SUPPORTED_1000baseT_Full;
-		ecmd->advertising = ADVERTISED_TP;
+			supported &= ~SUPPORTED_1000baseT_Full;
+		advertising = ADVERTISED_TP;
 
 		if (hw->mac.autoneg == 1) {
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 			/* the e1000 autoneg seems to match ethtool nicely */
-			ecmd->advertising |= hw->phy.autoneg_advertised;
+			advertising |= hw->phy.autoneg_advertised;
 		}
 
-		ecmd->port = PORT_TP;
-		ecmd->phy_address = hw->phy.addr;
-		ecmd->transceiver = XCVR_INTERNAL;
-
+		cmd->base.port = PORT_TP;
+		cmd->base.phy_address = hw->phy.addr;
 	} else {
-		ecmd->supported   = (SUPPORTED_1000baseT_Full |
-				     SUPPORTED_FIBRE |
-				     SUPPORTED_Autoneg);
+		supported   = (SUPPORTED_1000baseT_Full |
+			       SUPPORTED_FIBRE |
+			       SUPPORTED_Autoneg);
 
-		ecmd->advertising = (ADVERTISED_1000baseT_Full |
-				     ADVERTISED_FIBRE |
-				     ADVERTISED_Autoneg);
+		advertising = (ADVERTISED_1000baseT_Full |
+			       ADVERTISED_FIBRE |
+			       ADVERTISED_Autoneg);
 
-		ecmd->port = PORT_FIBRE;
-		ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.port = PORT_FIBRE;
 	}
 
 	speed = SPEED_UNKNOWN;
-	ecmd->duplex = DUPLEX_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
 
 	if (netif_running(netdev)) {
 		if (netif_carrier_ok(netdev)) {
 			speed = adapter->link_speed;
-			ecmd->duplex = adapter->link_duplex - 1;
+			cmd->base.duplex = adapter->link_duplex - 1;
 		}
 	} else if (!pm_runtime_suspended(netdev->dev.parent)) {
 		u32 status = er32(STATUS);
@@ -179,30 +176,36 @@ static int e1000_get_settings(struct net_device *netdev,
 				speed = SPEED_10;
 
 			if (status & E1000_STATUS_FD)
-				ecmd->duplex = DUPLEX_FULL;
+				cmd->base.duplex = DUPLEX_FULL;
 			else
-				ecmd->duplex = DUPLEX_HALF;
+				cmd->base.duplex = DUPLEX_HALF;
 		}
 	}
 
-	ethtool_cmd_speed_set(ecmd, speed);
-	ecmd->autoneg = ((hw->phy.media_type == e1000_media_type_fiber) ||
+	cmd->base.speed = speed;
+	cmd->base.autoneg = ((hw->phy.media_type == e1000_media_type_fiber) ||
 			 hw->mac.autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
 
 	/* MDI-X => 2; MDI =>1; Invalid =>0 */
 	if ((hw->phy.media_type == e1000_media_type_copper) &&
 	    netif_carrier_ok(netdev))
-		ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : ETH_TP_MDI;
+		cmd->base.eth_tp_mdix = hw->phy.is_mdix ?
+			ETH_TP_MDI_X : ETH_TP_MDI;
 	else
-		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
 
 	if (hw->phy.mdix == AUTO_ALL_MODES)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
 	else
-		ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+		cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
 
 	if (hw->phy.media_type != e1000_media_type_copper)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
@@ -262,12 +265,16 @@ err_inval:
 	return -EINVAL;
 }
 
-static int e1000_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	int ret_val = 0;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	pm_runtime_get_sync(netdev->dev.parent);
 
@@ -285,14 +292,14 @@ static int e1000_set_settings(struct net_device *netdev,
 	 * some hardware doesn't allow MDI setting when speed or
 	 * duplex is forced.
 	 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (hw->phy.media_type != e1000_media_type_copper) {
 			ret_val = -EOPNOTSUPP;
 			goto out;
 		}
 
-		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
-		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			ret_val = -EINVAL;
 			goto out;
@@ -302,35 +309,35 @@ static int e1000_set_settings(struct net_device *netdev,
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		hw->mac.autoneg = 1;
 		if (hw->phy.media_type == e1000_media_type_fiber)
 			hw->phy.autoneg_advertised = ADVERTISED_1000baseT_Full |
 			    ADVERTISED_FIBRE | ADVERTISED_Autoneg;
 		else
-			hw->phy.autoneg_advertised = ecmd->advertising |
+			hw->phy.autoneg_advertised = advertising |
 			    ADVERTISED_TP | ADVERTISED_Autoneg;
-		ecmd->advertising = hw->phy.autoneg_advertised;
+		advertising = hw->phy.autoneg_advertised;
 		if (adapter->fc_autoneg)
 			hw->fc.requested_mode = e1000_fc_default;
 	} else {
-		u32 speed = ethtool_cmd_speed(ecmd);
+		u32 speed = cmd->base.speed;
 		/* calling this overrides forced MDI setting */
-		if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+		if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
 			ret_val = -EINVAL;
 			goto out;
 		}
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		/* fix up the value for auto (3 => 0) as zero is mapped
 		 * internally to auto
 		 */
-		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
 			hw->phy.mdix = AUTO_ALL_MODES;
 		else
-			hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+			hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
 	}
 
 	/* reset the link */
@@ -904,19 +911,20 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data)
 	case e1000_pch2lan:
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+		/* fall through */
+	case e1000_pch_cnp:
 		mask |= BIT(18);
 		break;
 	default:
 		break;
 	}
 
-	if ((mac->type == e1000_pch_lpt) || (mac->type == e1000_pch_spt))
+	if (mac->type >= e1000_pch_lpt)
 		wlock_mac = (er32(FWSM) & E1000_FWSM_WLOCK_MAC_MASK) >>
 		    E1000_FWSM_WLOCK_MAC_SHIFT;
 
 	for (i = 0; i < mac->rar_entry_count; i++) {
-		if ((mac->type == e1000_pch_lpt) ||
-		    (mac->type == e1000_pch_spt)) {
+		if (mac->type >= e1000_pch_lpt) {
 			/* Cannot test write-protected SHRAL[n] registers */
 			if ((wlock_mac == 1) || (wlock_mac && (i > wlock_mac)))
 				continue;
@@ -1525,7 +1533,7 @@ static int e1000_setup_loopback_test(struct e1000_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 rctl, fext_nvm11, tarc0;
 
-	if (hw->mac.type == e1000_pch_spt) {
+	if (hw->mac.type >= e1000_pch_spt) {
 		fext_nvm11 = er32(FEXTNVM11);
 		fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX;
 		ew32(FEXTNVM11, fext_nvm11);
@@ -1569,6 +1577,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 
 	switch (hw->mac.type) {
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		fext_nvm11 = er32(FEXTNVM11);
 		fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX;
 		ew32(FEXTNVM11, fext_nvm11);
@@ -2313,8 +2322,6 @@ static int e1000e_get_ts_info(struct net_device *netdev,
 }
 
 static const struct ethtool_ops e1000_ethtool_ops = {
-	.get_settings		= e1000_get_settings,
-	.set_settings		= e1000_set_settings,
 	.get_drvinfo		= e1000_get_drvinfo,
 	.get_regs_len		= e1000_get_regs_len,
 	.get_regs		= e1000_get_regs,
@@ -2342,6 +2349,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 	.get_ts_info		= e1000e_get_ts_info,
 	.get_eee		= e1000e_get_eee,
 	.set_eee		= e1000e_set_eee,
+	.get_link_ksettings	= e1000_get_link_ksettings,
+	.set_link_ksettings	= e1000_set_link_ksettings,
 };
 
 void e1000e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 4e733bf1a38e..66bd5060a65b 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -96,6 +96,10 @@ struct e1000_hw;
 #define E1000_DEV_ID_PCH_SPT_I219_V4		0x15D8
 #define E1000_DEV_ID_PCH_SPT_I219_LM5		0x15E3
 #define E1000_DEV_ID_PCH_SPT_I219_V5		0x15D6
+#define E1000_DEV_ID_PCH_CNP_I219_LM6		0x15BD
+#define E1000_DEV_ID_PCH_CNP_I219_V6		0x15BE
+#define E1000_DEV_ID_PCH_CNP_I219_LM7		0x15BB
+#define E1000_DEV_ID_PCH_CNP_I219_V7		0x15BC
 
 #define E1000_REVISION_4	4
 
@@ -118,6 +122,7 @@ enum e1000_mac_type {
 	e1000_pch2lan,
 	e1000_pch_lpt,
 	e1000_pch_spt,
+	e1000_pch_cnp,
 };
 
 enum e1000_media_type {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index f3aaca743ea3..68ea8b4555ab 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -237,7 +237,7 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw)
 	if (ret_val)
 		return false;
 out:
-	if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) {
+	if (hw->mac.type >= e1000_pch_lpt) {
 		/* Only unforce SMBus if ME is not active */
 		if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
 			/* Unforce SMBus mode in PHY */
@@ -333,6 +333,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	switch (hw->mac.type) {
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -474,6 +475,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 		case e1000_pch2lan:
 		case e1000_pch_lpt:
 		case e1000_pch_spt:
+		case e1000_pch_cnp:
 			/* In case the PHY needs to be in mdio slow mode,
 			 * set slow mode and try to get the PHY id again.
 			 */
@@ -607,7 +609,7 @@ static s32 e1000_init_nvm_params_ich8lan(struct e1000_hw *hw)
 
 	nvm->type = e1000_nvm_flash_sw;
 
-	if (hw->mac.type == e1000_pch_spt) {
+	if (hw->mac.type >= e1000_pch_spt) {
 		/* in SPT, gfpreg doesn't exist. NVM size is taken from the
 		 * STRAP register. This is because in SPT the GbE Flash region
 		 * is no longer accessed through the flash registers. Instead,
@@ -715,6 +717,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 		/* fall-through */
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 	case e1000_pchlan:
 		/* check management mode */
 		mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan;
@@ -732,7 +735,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 		break;
 	}
 
-	if ((mac->type == e1000_pch_lpt) || (mac->type == e1000_pch_spt)) {
+	if (mac->type >= e1000_pch_lpt) {
 		mac->rar_entry_count = E1000_PCH_LPT_RAR_ENTRIES;
 		mac->ops.rar_set = e1000_rar_set_pch_lpt;
 		mac->ops.setup_physical_interface =
@@ -1399,9 +1402,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 	 * aggressive resulting in many collisions. To avoid this, increase
 	 * the IPG and reduce Rx latency in the PHY.
 	 */
-	if (((hw->mac.type == e1000_pch2lan) ||
-	     (hw->mac.type == e1000_pch_lpt) ||
-	     (hw->mac.type == e1000_pch_spt)) && link) {
+	if ((hw->mac.type >= e1000_pch2lan) && link) {
 		u16 speed, duplex;
 
 		e1000e_get_speed_and_duplex_copper(hw, &speed, &duplex);
@@ -1412,7 +1413,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 			tipg_reg |= 0xFF;
 			/* Reduce Rx latency in analog PHY */
 			emi_val = 0;
-		} else if (hw->mac.type == e1000_pch_spt &&
+		} else if (hw->mac.type >= e1000_pch_spt &&
 			   duplex == FULL_DUPLEX && speed != SPEED_1000) {
 			tipg_reg |= 0xC;
 			emi_val = 1;
@@ -1435,8 +1436,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 			emi_addr = I217_RX_CONFIG;
 		ret_val = e1000_write_emi_reg_locked(hw, emi_addr, emi_val);
 
-		if (hw->mac.type == e1000_pch_lpt ||
-		    hw->mac.type == e1000_pch_spt) {
+		if (hw->mac.type >= e1000_pch_lpt) {
 			u16 phy_reg;
 
 			e1e_rphy_locked(hw, I217_PLL_CLOCK_GATE_REG, &phy_reg);
@@ -1452,7 +1452,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 		if (ret_val)
 			return ret_val;
 
-		if (hw->mac.type == e1000_pch_spt) {
+		if (hw->mac.type >= e1000_pch_spt) {
 			u16 data;
 			u16 ptr_gap;
 
@@ -1502,7 +1502,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 	 * on power up.
 	 * Set the Beacon Duration for I217 to 8 usec
 	 */
-	if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) {
+	if (hw->mac.type >= e1000_pch_lpt) {
 		u32 mac_reg;
 
 		mac_reg = er32(FEXTNVM4);
@@ -1520,8 +1520,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 		if (ret_val)
 			return ret_val;
 	}
-	if ((hw->mac.type == e1000_pch_lpt) ||
-	    (hw->mac.type == e1000_pch_spt)) {
+	if (hw->mac.type >= e1000_pch_lpt) {
 		/* Set platform power management values for
 		 * Latency Tolerance Reporting (LTR)
 		 */
@@ -1533,15 +1532,18 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 	/* Clear link partner's EEE ability */
 	hw->dev_spec.ich8lan.eee_lp_ability = 0;
 
-	/* FEXTNVM6 K1-off workaround */
-	if (hw->mac.type == e1000_pch_spt) {
-		u32 pcieanacfg = er32(PCIEANACFG);
+	if (hw->mac.type >= e1000_pch_lpt) {
 		u32 fextnvm6 = er32(FEXTNVM6);
 
-		if (pcieanacfg & E1000_FEXTNVM6_K1_OFF_ENABLE)
-			fextnvm6 |= E1000_FEXTNVM6_K1_OFF_ENABLE;
-		else
-			fextnvm6 &= ~E1000_FEXTNVM6_K1_OFF_ENABLE;
+		if (hw->mac.type == e1000_pch_spt) {
+			/* FEXTNVM6 K1-off workaround - for SPT only */
+			u32 pcieanacfg = er32(PCIEANACFG);
+
+			if (pcieanacfg & E1000_FEXTNVM6_K1_OFF_ENABLE)
+				fextnvm6 |= E1000_FEXTNVM6_K1_OFF_ENABLE;
+			else
+				fextnvm6 &= ~E1000_FEXTNVM6_K1_OFF_ENABLE;
+		}
 
 		ew32(FEXTNVM6, fextnvm6);
 	}
@@ -1640,6 +1642,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter)
 	case e1000_pch2lan:
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		rc = e1000_init_phy_params_pchlan(hw);
 		break;
 	default:
@@ -2091,6 +2094,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 	case e1000_pch2lan:
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M;
 		break;
 	default:
@@ -3125,6 +3129,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank)
 
 	switch (hw->mac.type) {
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		bank1_offset = nvm->flash_bank_size;
 		act_offset = E1000_ICH_NVM_SIG_WORD;
 
@@ -3380,7 +3385,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw)
 	/* Clear FCERR and DAEL in hw status by writing 1 */
 	hsfsts.hsf_status.flcerr = 1;
 	hsfsts.hsf_status.dael = 1;
-	if (hw->mac.type == e1000_pch_spt)
+	if (hw->mac.type >= e1000_pch_spt)
 		ew32flash(ICH_FLASH_HSFSTS, hsfsts.regval & 0xFFFF);
 	else
 		ew16flash(ICH_FLASH_HSFSTS, hsfsts.regval);
@@ -3399,7 +3404,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw)
 		 * Begin by setting Flash Cycle Done.
 		 */
 		hsfsts.hsf_status.flcdone = 1;
-		if (hw->mac.type == e1000_pch_spt)
+		if (hw->mac.type >= e1000_pch_spt)
 			ew32flash(ICH_FLASH_HSFSTS, hsfsts.regval & 0xFFFF);
 		else
 			ew16flash(ICH_FLASH_HSFSTS, hsfsts.regval);
@@ -3423,7 +3428,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw)
 			 * now set the Flash Cycle Done.
 			 */
 			hsfsts.hsf_status.flcdone = 1;
-			if (hw->mac.type == e1000_pch_spt)
+			if (hw->mac.type >= e1000_pch_spt)
 				ew32flash(ICH_FLASH_HSFSTS,
 					  hsfsts.regval & 0xFFFF);
 			else
@@ -3450,13 +3455,13 @@ static s32 e1000_flash_cycle_ich8lan(struct e1000_hw *hw, u32 timeout)
 	u32 i = 0;
 
 	/* Start a cycle by writing 1 in Flash Cycle Go in Hw Flash Control */
-	if (hw->mac.type == e1000_pch_spt)
+	if (hw->mac.type >= e1000_pch_spt)
 		hsflctl.regval = er32flash(ICH_FLASH_HSFSTS) >> 16;
 	else
 		hsflctl.regval = er16flash(ICH_FLASH_HSFCTL);
 	hsflctl.hsf_ctrl.flcgo = 1;
 
-	if (hw->mac.type == e1000_pch_spt)
+	if (hw->mac.type >= e1000_pch_spt)
 		ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16);
 	else
 		ew16flash(ICH_FLASH_HSFCTL, hsflctl.regval);
@@ -3527,7 +3532,7 @@ static s32 e1000_read_flash_byte_ich8lan(struct e1000_hw *hw, u32 offset,
 	/* In SPT, only 32 bits access is supported,
 	 * so this function should not be called.
 	 */
-	if (hw->mac.type == e1000_pch_spt)
+	if (hw->mac.type >= e1000_pch_spt)
 		return -E1000_ERR_NVM;
 	else
 		ret_val = e1000_read_flash_data_ich8lan(hw, offset, 1, &word);
@@ -3634,8 +3639,7 @@ static s32 e1000_read_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset,
 	s32 ret_val = -E1000_ERR_NVM;
 	u8 count = 0;
 
-	if (offset > ICH_FLASH_LINEAR_ADDR_MASK ||
-	    hw->mac.type != e1000_pch_spt)
+	if (offset > ICH_FLASH_LINEAR_ADDR_MASK || hw->mac.type < e1000_pch_spt)
 		return -E1000_ERR_NVM;
 	flash_linear_addr = ((ICH_FLASH_LINEAR_ADDR_MASK & offset) +
 			     hw->nvm.flash_base_addr);
@@ -4068,6 +4072,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw)
 	switch (hw->mac.type) {
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		word = NVM_COMPAT;
 		valid_csum_mask = NVM_COMPAT_VALID_CSUM;
 		break;
@@ -4153,7 +4158,7 @@ static s32 e1000_write_flash_data_ich8lan(struct e1000_hw *hw, u32 offset,
 	s32 ret_val;
 	u8 count = 0;
 
-	if (hw->mac.type == e1000_pch_spt) {
+	if (hw->mac.type >= e1000_pch_spt) {
 		if (size != 4 || offset > ICH_FLASH_LINEAR_ADDR_MASK)
 			return -E1000_ERR_NVM;
 	} else {
@@ -4173,7 +4178,7 @@ static s32 e1000_write_flash_data_ich8lan(struct e1000_hw *hw, u32 offset,
 		/* In SPT, This register is in Lan memory space, not
 		 * flash.  Therefore, only 32 bit access is supported
 		 */
-		if (hw->mac.type == e1000_pch_spt)
+		if (hw->mac.type >= e1000_pch_spt)
 			hsflctl.regval = er32flash(ICH_FLASH_HSFSTS) >> 16;
 		else
 			hsflctl.regval = er16flash(ICH_FLASH_HSFCTL);
@@ -4185,7 +4190,7 @@ static s32 e1000_write_flash_data_ich8lan(struct e1000_hw *hw, u32 offset,
 		 * not flash.  Therefore, only 32 bit access is
 		 * supported
 		 */
-		if (hw->mac.type == e1000_pch_spt)
+		if (hw->mac.type >= e1000_pch_spt)
 			ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16);
 		else
 			ew16flash(ICH_FLASH_HSFCTL, hsflctl.regval);
@@ -4243,7 +4248,7 @@ static s32 e1000_write_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset,
 	s32 ret_val;
 	u8 count = 0;
 
-	if (hw->mac.type == e1000_pch_spt) {
+	if (hw->mac.type >= e1000_pch_spt) {
 		if (offset > ICH_FLASH_LINEAR_ADDR_MASK)
 			return -E1000_ERR_NVM;
 	}
@@ -4259,7 +4264,7 @@ static s32 e1000_write_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset,
 		/* In SPT, This register is in Lan memory space, not
 		 * flash.  Therefore, only 32 bit access is supported
 		 */
-		if (hw->mac.type == e1000_pch_spt)
+		if (hw->mac.type >= e1000_pch_spt)
 			hsflctl.regval = er32flash(ICH_FLASH_HSFSTS)
 			    >> 16;
 		else
@@ -4272,7 +4277,7 @@ static s32 e1000_write_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset,
 		 * not flash.  Therefore, only 32 bit access is
 		 * supported
 		 */
-		if (hw->mac.type == e1000_pch_spt)
+		if (hw->mac.type >= e1000_pch_spt)
 			ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16);
 		else
 			ew16flash(ICH_FLASH_HSFCTL, hsflctl.regval);
@@ -4464,14 +4469,14 @@ static s32 e1000_erase_flash_bank_ich8lan(struct e1000_hw *hw, u32 bank)
 			/* Write a value 11 (block Erase) in Flash
 			 * Cycle field in hw flash control
 			 */
-			if (hw->mac.type == e1000_pch_spt)
+			if (hw->mac.type >= e1000_pch_spt)
 				hsflctl.regval =
 				    er32flash(ICH_FLASH_HSFSTS) >> 16;
 			else
 				hsflctl.regval = er16flash(ICH_FLASH_HSFCTL);
 
 			hsflctl.hsf_ctrl.flcycle = ICH_CYCLE_ERASE;
-			if (hw->mac.type == e1000_pch_spt)
+			if (hw->mac.type >= e1000_pch_spt)
 				ew32flash(ICH_FLASH_HSFSTS,
 					  hsflctl.regval << 16);
 			else
@@ -4894,8 +4899,7 @@ static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw)
 	ew32(RFCTL, reg);
 
 	/* Enable ECC on Lynxpoint */
-	if ((hw->mac.type == e1000_pch_lpt) ||
-	    (hw->mac.type == e1000_pch_spt)) {
+	if (hw->mac.type >= e1000_pch_lpt) {
 		reg = er32(PBECCSTS);
 		reg |= E1000_PBECCSTS_ECC_ENABLE;
 		ew32(PBECCSTS, reg);
@@ -5299,7 +5303,7 @@ void e1000_suspend_workarounds_ich8lan(struct e1000_hw *hw)
 		    (device_id == E1000_DEV_ID_PCH_LPTLP_I218_V) ||
 		    (device_id == E1000_DEV_ID_PCH_I218_LM3) ||
 		    (device_id == E1000_DEV_ID_PCH_I218_V3) ||
-		    (hw->mac.type == e1000_pch_spt)) {
+		    (hw->mac.type >= e1000_pch_spt)) {
 			u32 fextnvm6 = er32(FEXTNVM6);
 
 			ew32(FEXTNVM6, fextnvm6 & ~E1000_FEXTNVM6_REQ_PLL_CLK);
@@ -5865,7 +5869,8 @@ const struct e1000_info e1000_pch2_info = {
 				  | FLAG_HAS_JUMBO_FRAMES
 				  | FLAG_APME_IN_WUC,
 	.flags2			= FLAG2_HAS_PHY_STATS
-				  | FLAG2_HAS_EEE,
+				  | FLAG2_HAS_EEE
+				  | FLAG2_CHECK_SYSTIM_OVERFLOW,
 	.pba			= 26,
 	.max_hw_frame_size	= 9022,
 	.get_variants		= e1000_get_variants_ich8lan,
@@ -5914,3 +5919,23 @@ const struct e1000_info e1000_pch_spt_info = {
 	.phy_ops		= &ich8_phy_ops,
 	.nvm_ops		= &spt_nvm_ops,
 };
+
+const struct e1000_info e1000_pch_cnp_info = {
+	.mac			= e1000_pch_cnp,
+	.flags			= FLAG_IS_ICH
+				  | FLAG_HAS_WOL
+				  | FLAG_HAS_HW_TIMESTAMP
+				  | FLAG_HAS_CTRLEXT_ON_LOAD
+				  | FLAG_HAS_AMT
+				  | FLAG_HAS_FLASH
+				  | FLAG_HAS_JUMBO_FRAMES
+				  | FLAG_APME_IN_WUC,
+	.flags2			= FLAG2_HAS_PHY_STATS
+				  | FLAG2_HAS_EEE,
+	.pba			= 26,
+	.max_hw_frame_size	= 9022,
+	.get_variants		= e1000_get_variants_ich8lan,
+	.mac_ops		= &ich8_mac_ops,
+	.phy_ops		= &ich8_phy_ops,
+	.nvm_ops		= &spt_nvm_ops,
+};
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 2175cced402f..b3679728caac 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -71,6 +71,7 @@ static const struct e1000_info *e1000_info_tbl[] = {
 	[board_pch2lan]		= &e1000_pch2_info,
 	[board_pch_lpt]		= &e1000_pch_lpt_info,
 	[board_pch_spt]		= &e1000_pch_spt_info,
+	[board_pch_cnp]		= &e1000_pch_cnp_info,
 };
 
 struct e1000_reg_info {
@@ -1791,8 +1792,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
 	}
 
 	/* Reset on uncorrectable ECC error */
-	if ((icr & E1000_ICR_ECCER) && ((hw->mac.type == e1000_pch_lpt) ||
-					(hw->mac.type == e1000_pch_spt))) {
+	if ((icr & E1000_ICR_ECCER) && (hw->mac.type >= e1000_pch_lpt)) {
 		u32 pbeccsts = er32(PBECCSTS);
 
 		adapter->corr_errors +=
@@ -1872,8 +1872,7 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data)
 	}
 
 	/* Reset on uncorrectable ECC error */
-	if ((icr & E1000_ICR_ECCER) && ((hw->mac.type == e1000_pch_lpt) ||
-					(hw->mac.type == e1000_pch_spt))) {
+	if ((icr & E1000_ICR_ECCER) && (hw->mac.type >= e1000_pch_lpt)) {
 		u32 pbeccsts = er32(PBECCSTS);
 
 		adapter->corr_errors +=
@@ -2241,8 +2240,7 @@ static void e1000_irq_enable(struct e1000_adapter *adapter)
 	if (adapter->msix_entries) {
 		ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574);
 		ew32(IMS, adapter->eiac_mask | E1000_IMS_LSC);
-	} else if ((hw->mac.type == e1000_pch_lpt) ||
-		   (hw->mac.type == e1000_pch_spt)) {
+	} else if (hw->mac.type >= e1000_pch_lpt) {
 		ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER);
 	} else {
 		ew32(IMS, IMS_ENABLE_MASK);
@@ -3000,8 +2998,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 
 	hw->mac.ops.config_collision_dist(hw);
 
-	/* SPT Si errata workaround to avoid data corruption */
-	if (hw->mac.type == e1000_pch_spt) {
+	/* SPT and CNP Si errata workaround to avoid data corruption */
+	if (hw->mac.type >= e1000_pch_spt) {
 		u32 reg_val;
 
 		reg_val = er32(IOSFPC);
@@ -3497,8 +3495,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	/* Make sure clock is enabled on I217/I218/I219  before checking
 	 * the frequency
 	 */
-	if (((hw->mac.type == e1000_pch_lpt) ||
-	     (hw->mac.type == e1000_pch_spt)) &&
+	if ((hw->mac.type >= e1000_pch_lpt) &&
 	    !(er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) &&
 	    !(er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_ENABLED)) {
 		u32 fextnvm7 = er32(FEXTNVM7);
@@ -3511,37 +3508,58 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 
 	switch (hw->mac.type) {
 	case e1000_pch2lan:
+		/* Stable 96MHz frequency */
+		incperiod = INCPERIOD_96MHZ;
+		incvalue = INCVALUE_96MHZ;
+		shift = INCVALUE_SHIFT_96MHZ;
+		adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHZ;
+		break;
 	case e1000_pch_lpt:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 96MHz frequency */
-			incperiod = INCPERIOD_96MHz;
-			incvalue = INCVALUE_96MHz;
-			shift = INCVALUE_SHIFT_96MHz;
-			adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHz;
+			incperiod = INCPERIOD_96MHZ;
+			incvalue = INCVALUE_96MHZ;
+			shift = INCVALUE_SHIFT_96MHZ;
+			adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHZ;
 		} else {
 			/* Stable 25MHz frequency */
-			incperiod = INCPERIOD_25MHz;
-			incvalue = INCVALUE_25MHz;
-			shift = INCVALUE_SHIFT_25MHz;
+			incperiod = INCPERIOD_25MHZ;
+			incvalue = INCVALUE_25MHZ;
+			shift = INCVALUE_SHIFT_25MHZ;
 			adapter->cc.shift = shift;
 		}
 		break;
 	case e1000_pch_spt:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
-			incperiod = INCPERIOD_24MHz;
-			incvalue = INCVALUE_24MHz;
-			shift = INCVALUE_SHIFT_24MHz;
+			incperiod = INCPERIOD_24MHZ;
+			incvalue = INCVALUE_24MHZ;
+			shift = INCVALUE_SHIFT_24MHZ;
 			adapter->cc.shift = shift;
 			break;
 		}
 		return -EINVAL;
+	case e1000_pch_cnp:
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
+			/* Stable 24MHz frequency */
+			incperiod = INCPERIOD_24MHZ;
+			incvalue = INCVALUE_24MHZ;
+			shift = INCVALUE_SHIFT_24MHZ;
+			adapter->cc.shift = shift;
+		} else {
+			/* Stable 38400KHz frequency */
+			incperiod = INCPERIOD_38400KHZ;
+			incvalue = INCVALUE_38400KHZ;
+			shift = INCVALUE_SHIFT_38400KHZ;
+			adapter->cc.shift = shift;
+		}
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		/* Stable 25MHz frequency */
-		incperiod = INCPERIOD_25MHz;
-		incvalue = INCVALUE_25MHz;
-		shift = INCVALUE_SHIFT_25MHz;
+		incperiod = INCPERIOD_25MHZ;
+		incvalue = INCVALUE_25MHZ;
+		shift = INCVALUE_SHIFT_25MHZ;
 		adapter->cc.shift = shift;
 		break;
 	default:
@@ -4032,6 +4050,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch2lan:
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
+	case e1000_pch_cnp:
 		fc->refresh_time = 0x0400;
 
 		if (adapter->netdev->mtu <= ETH_DATA_LEN) {
@@ -4076,7 +4095,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 		}
 	}
 
-	if (hw->mac.type == e1000_pch_spt)
+	if (hw->mac.type >= e1000_pch_spt)
 		e1000_flush_desc_rings(adapter);
 	/* Allow time for pending master requests to run */
 	mac->ops.reset_hw(hw);
@@ -4151,7 +4170,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 		phy_data &= ~IGP02E1000_PM_SPD;
 		e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data);
 	}
-	if (hw->mac.type == e1000_pch_spt && adapter->int_mode == 0) {
+	if (hw->mac.type >= e1000_pch_spt && adapter->int_mode == 0) {
 		u32 reg;
 
 		/* Fextnvm7 @ 0xe4[2] = 1 */
@@ -4285,7 +4304,7 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 	if (!pci_channel_offline(adapter->pdev)) {
 		if (reset)
 			e1000e_reset(adapter);
-		else if (hw->mac.type == e1000_pch_spt)
+		else if (hw->mac.type >= e1000_pch_spt)
 			e1000_flush_desc_rings(adapter);
 	}
 	e1000_clean_tx_ring(adapter->tx_ring);
@@ -4973,8 +4992,7 @@ static void e1000e_update_stats(struct e1000_adapter *adapter)
 	adapter->stats.mgpdc += er32(MGTPDC);
 
 	/* Correctable ECC Errors */
-	if ((hw->mac.type == e1000_pch_lpt) ||
-	    (hw->mac.type == e1000_pch_spt)) {
+	if (hw->mac.type >= e1000_pch_lpt) {
 		u32 pbeccsts = er32(PBECCSTS);
 
 		adapter->corr_errors +=
@@ -6274,8 +6292,8 @@ static int e1000e_pm_freeze(struct device *dev)
 		/* Quiesce the device without resetting the hardware */
 		e1000e_down(adapter, false);
 		e1000_free_irq(adapter);
-		e1000e_reset_interrupt_capability(adapter);
 	}
+	e1000e_reset_interrupt_capability(adapter);
 
 	/* Allow time for pending master requests to run */
 	e1000e_disable_pcie_master(&adapter->hw);
@@ -6348,8 +6366,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 
 	if (adapter->hw.phy.type == e1000_phy_igp_3) {
 		e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
-	} else if ((hw->mac.type == e1000_pch_lpt) ||
-		   (hw->mac.type == e1000_pch_spt)) {
+	} else if (hw->mac.type >= e1000_pch_lpt) {
 		if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
 			/* ULP does not support wake from unicast, multicast
 			 * or broadcast.
@@ -7508,6 +7525,10 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V4), board_pch_spt },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM5), board_pch_spt },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V5), board_pch_spt },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM6), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V6), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM7), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V7), board_pch_cnp },
 
 	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
 };
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 34cc3be0df8e..b366885487a8 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -301,8 +301,8 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch2lan:
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
-		if (((hw->mac.type != e1000_pch_lpt) &&
-		     (hw->mac.type != e1000_pch_spt)) ||
+	case e1000_pch_cnp:
+		if ((hw->mac.type < e1000_pch_lpt) ||
 		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
 			adapter->ptp_clock_info.max_adj = 24000000 - 1;
 			break;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 52b979443cde..689c413b7782 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -65,14 +65,16 @@ enum fm10k_ring_state_t {
 	__FM10K_TX_DETECT_HANG,
 	__FM10K_HANG_CHECK_ARMED,
 	__FM10K_TX_XPS_INIT_DONE,
+	/* This must be last and is used to calculate BITMAP size */
+	__FM10K_TX_STATE_SIZE__,
 };
 
 #define check_for_tx_hang(ring) \
-	test_bit(__FM10K_TX_DETECT_HANG, &(ring)->state)
+	test_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
 #define set_check_for_tx_hang(ring) \
-	set_bit(__FM10K_TX_DETECT_HANG, &(ring)->state)
+	set_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
 #define clear_check_for_tx_hang(ring) \
-	clear_bit(__FM10K_TX_DETECT_HANG, &(ring)->state)
+	clear_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
 
 struct fm10k_tx_buffer {
 	struct fm10k_tx_desc *next_to_watch;
@@ -126,7 +128,7 @@ struct fm10k_ring {
 		struct fm10k_rx_buffer *rx_buffer;
 	};
 	u32 __iomem *tail;
-	unsigned long state;
+	DECLARE_BITMAP(state, __FM10K_TX_STATE_SIZE__);
 	dma_addr_t dma;			/* phys. address of descriptor ring */
 	unsigned int size;		/* length in bytes */
 
@@ -249,18 +251,46 @@ struct fm10k_udp_port {
 /* one work queue for entire driver */
 extern struct workqueue_struct *fm10k_workqueue;
 
+/* The following enumeration contains flags which indicate or enable modified
+ * driver behaviors. To avoid race conditions, the flags are stored in
+ * a BITMAP in the fm10k_intfc structure. The BITMAP should be accessed using
+ * atomic *_bit() operations.
+ */
+enum fm10k_flags_t {
+	FM10K_FLAG_RESET_REQUESTED,
+	FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+	FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+	FM10K_FLAG_SWPRI_CONFIG,
+	/* __FM10K_FLAGS_SIZE__ is used to calculate the size of
+	 * interface->flags and must be the last value in this
+	 * enumeration.
+	 */
+	__FM10K_FLAGS_SIZE__
+};
+
+enum fm10k_state_t {
+	__FM10K_RESETTING,
+	__FM10K_DOWN,
+	__FM10K_SERVICE_SCHED,
+	__FM10K_SERVICE_REQUEST,
+	__FM10K_SERVICE_DISABLE,
+	__FM10K_MBX_LOCK,
+	__FM10K_LINK_DOWN,
+	__FM10K_UPDATING_STATS,
+	/* This value must be last and determines the BITMAP size */
+	__FM10K_STATE_SIZE__,
+};
+
 struct fm10k_intfc {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	struct net_device *netdev;
 	struct fm10k_l2_accel *l2_accel; /* pointer to L2 acceleration list */
 	struct pci_dev *pdev;
-	unsigned long state;
+	DECLARE_BITMAP(state, __FM10K_STATE_SIZE__);
+
+	/* Access flag values using atomic *_bit() operations */
+	DECLARE_BITMAP(flags, __FM10K_FLAGS_SIZE__);
 
-	u32 flags;
-#define FM10K_FLAG_RESET_REQUESTED		(u32)(BIT(0))
-#define FM10K_FLAG_RSS_FIELD_IPV4_UDP		(u32)(BIT(1))
-#define FM10K_FLAG_RSS_FIELD_IPV6_UDP		(u32)(BIT(2))
-#define FM10K_FLAG_SWPRI_CONFIG			(u32)(BIT(3))
 	int xcast_mode;
 
 	/* Tx fast path data */
@@ -352,22 +382,12 @@ struct fm10k_intfc {
 	u16 vid;
 };
 
-enum fm10k_state_t {
-	__FM10K_RESETTING,
-	__FM10K_DOWN,
-	__FM10K_SERVICE_SCHED,
-	__FM10K_SERVICE_DISABLE,
-	__FM10K_MBX_LOCK,
-	__FM10K_LINK_DOWN,
-	__FM10K_UPDATING_STATS,
-};
-
 static inline void fm10k_mbx_lock(struct fm10k_intfc *interface)
 {
 	/* busy loop if we cannot obtain the lock as some calls
 	 * such as ndo_set_rx_mode may be made in atomic context
 	 */
-	while (test_and_set_bit(__FM10K_MBX_LOCK, &interface->state))
+	while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state))
 		udelay(20);
 }
 
@@ -375,12 +395,12 @@ static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface)
 {
 	/* flush memory to make sure state is correct */
 	smp_mb__before_atomic();
-	clear_bit(__FM10K_MBX_LOCK, &interface->state);
+	clear_bit(__FM10K_MBX_LOCK, interface->state);
 }
 
 static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface)
 {
-	return !test_and_set_bit(__FM10K_MBX_LOCK, &interface->state);
+	return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state);
 }
 
 /* fm10k_test_staterr - test bits in Rx descriptor status and error fields */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 0c84fef750f4..c7234f35f8ff 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -562,7 +562,7 @@ static int fm10k_set_ringparam(struct net_device *netdev,
 		return 0;
 	}
 
-	while (test_and_set_bit(__FM10K_RESETTING, &interface->state))
+	while (test_and_set_bit(__FM10K_RESETTING, interface->state))
 		usleep_range(1000, 2000);
 
 	if (!netif_running(interface->netdev)) {
@@ -648,7 +648,7 @@ err_setup:
 	fm10k_up(interface);
 	vfree(temp_ring);
 clear_reset:
-	clear_bit(__FM10K_RESETTING, &interface->state);
+	clear_bit(__FM10K_RESETTING, interface->state);
 	return err;
 }
 
@@ -716,7 +716,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		/* fall through */
 	case UDP_V4_FLOW:
-		if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP)
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+			     interface->flags))
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		/* fall through */
 	case SCTP_V4_FLOW:
@@ -732,7 +733,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
 		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
 		break;
 	case UDP_V6_FLOW:
-		if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP)
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+			     interface->flags))
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
 		break;
@@ -764,12 +766,13 @@ static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return ret;
 }
 
-#define UDP_RSS_FLAGS (FM10K_FLAG_RSS_FIELD_IPV4_UDP | \
-		       FM10K_FLAG_RSS_FIELD_IPV6_UDP)
 static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
 				  struct ethtool_rxnfc *nfc)
 {
-	u32 flags = interface->flags;
+	int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				    interface->flags);
+	int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				    interface->flags);
 
 	/* RSS does not support anything other than hashing
 	 * to queues on src and dst IPs and ports
@@ -793,10 +796,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
 			return -EINVAL;
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			flags &= ~FM10K_FLAG_RSS_FIELD_IPV4_UDP;
+			clear_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				  interface->flags);
 			break;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
-			flags |= FM10K_FLAG_RSS_FIELD_IPV4_UDP;
+			set_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				interface->flags);
 			break;
 		default:
 			return -EINVAL;
@@ -808,10 +813,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
 			return -EINVAL;
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			flags &= ~FM10K_FLAG_RSS_FIELD_IPV6_UDP;
+			clear_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				  interface->flags);
 			break;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
-			flags |= FM10K_FLAG_RSS_FIELD_IPV6_UDP;
+			set_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				interface->flags);
 			break;
 		default:
 			return -EINVAL;
@@ -835,28 +842,41 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
 		return -EINVAL;
 	}
 
-	/* if we changed something we need to update flags */
-	if (flags != interface->flags) {
+	/* If something changed we need to update the MRQC register. Note that
+	 * test_bit() is guaranteed to return strictly 0 or 1, so testing for
+	 * equality is safe.
+	 */
+	if ((rss_ipv4_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				      interface->flags)) ||
+	    (rss_ipv6_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				      interface->flags))) {
 		struct fm10k_hw *hw = &interface->hw;
+		bool warn = false;
 		u32 mrqc;
 
-		if ((flags & UDP_RSS_FLAGS) &&
-		    !(interface->flags & UDP_RSS_FLAGS))
-			netif_warn(interface, drv, interface->netdev,
-				   "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
-
-		interface->flags = flags;
-
 		/* Perform hash on these packet types */
 		mrqc = FM10K_MRQC_IPV4 |
 		       FM10K_MRQC_TCP_IPV4 |
 		       FM10K_MRQC_IPV6 |
 		       FM10K_MRQC_TCP_IPV6;
 
-		if (flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP)
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+			     interface->flags)) {
 			mrqc |= FM10K_MRQC_UDP_IPV4;
-		if (flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP)
+			warn = true;
+		}
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+			     interface->flags)) {
 			mrqc |= FM10K_MRQC_UDP_IPV6;
+			warn = true;
+		}
+
+		/* If we enable UDP RSS display a warning that this may cause
+		 * fragmented UDP packets to arrive out of order.
+		 */
+		if (warn)
+			netif_warn(interface, drv, interface->netdev,
+				   "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
 
 		fm10k_write_reg(hw, FM10K_MRQC(0), mrqc);
 	}
@@ -939,7 +959,7 @@ static void fm10k_self_test(struct net_device *dev,
 
 	memset(data, 0, sizeof(*data) * FM10K_TEST_LEN);
 
-	if (FM10K_REMOVED(hw)) {
+	if (FM10K_REMOVED(hw->hw_addr)) {
 		netif_err(interface, drv, dev,
 			  "Interface removed - test blocked\n");
 		eth_test->flags |= ETH_TEST_FL_FAILED;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 5bb233a9614c..9dffaba85ae6 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -34,7 +34,7 @@ const char fm10k_driver_version[] = DRV_VERSION;
 char fm10k_driver_name[] = "fm10k";
 static const char fm10k_driver_string[] = DRV_SUMMARY;
 static const char fm10k_copyright[] =
-	"Copyright (c) 2013 - 2016 Intel Corporation.";
+	"Copyright(c) 2013 - 2017 Intel Corporation.";
 
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
 MODULE_DESCRIPTION(DRV_SUMMARY);
@@ -1175,13 +1175,13 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring)
 		/* update completed stats and continue */
 		tx_ring->tx_stats.tx_done_old = tx_done;
 		/* reset the countdown */
-		clear_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state);
+		clear_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state);
 
 		return false;
 	}
 
 	/* make sure it is true for two checks in a row */
-	return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state);
+	return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state);
 }
 
 /**
@@ -1191,9 +1191,9 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring)
 void fm10k_tx_timeout_reset(struct fm10k_intfc *interface)
 {
 	/* Do the reset outside of interrupt context */
-	if (!test_bit(__FM10K_DOWN, &interface->state)) {
+	if (!test_bit(__FM10K_DOWN, interface->state)) {
 		interface->tx_timeout_count++;
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 		fm10k_service_event_schedule(interface);
 	}
 }
@@ -1214,7 +1214,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector,
 	unsigned int budget = q_vector->tx.work_limit;
 	unsigned int i = tx_ring->next_to_clean;
 
-	if (test_bit(__FM10K_DOWN, &interface->state))
+	if (test_bit(__FM10K_DOWN, interface->state))
 		return true;
 
 	tx_buffer = &tx_ring->tx_buffer[i];
@@ -1344,7 +1344,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector,
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->queue_index) &&
-		    !test_bit(__FM10K_DOWN, &interface->state)) {
+		    !test_bit(__FM10K_DOWN, interface->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 			++tx_ring->tx_stats.restart_queue;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 01db688cf539..24f2f6f86f5a 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -737,6 +737,23 @@ static void fm10k_tx_timeout(struct net_device *netdev)
 	}
 }
 
+/**
+ * fm10k_host_mbx_ready - Check PF interface's mailbox readiness
+ * @interface: board private structure
+ *
+ * This function checks if the PF interface's mailbox is ready before queueing
+ * mailbox messages for transmission. This will prevent filling the TX mailbox
+ * queue when the receiver is not ready. VF interfaces are exempt from this
+ * check since it will block all PF-VF mailbox messages from being sent from
+ * the VF to the PF at initialization.
+ **/
+static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	return (hw->mac.type == fm10k_mac_vf || interface->host_ready);
+}
+
 static int fm10k_uc_vlan_unsync(struct net_device *netdev,
 				const unsigned char *uc_addr)
 {
@@ -745,12 +762,15 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev,
 	u16 glort = interface->glort;
 	u16 vid = interface->vid;
 	bool set = !!(vid / VLAN_N_VID);
-	int err;
+	int err = -EHOSTDOWN;
 
 	/* drop any leading bits on the VLAN ID */
 	vid &= VLAN_N_VID - 1;
 
-	err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, vid, set, 0);
+	if (fm10k_host_mbx_ready(interface))
+		err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr,
+						 vid, set, 0);
+
 	if (err)
 		return err;
 
@@ -766,12 +786,14 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev,
 	u16 glort = interface->glort;
 	u16 vid = interface->vid;
 	bool set = !!(vid / VLAN_N_VID);
-	int err;
+	int err = -EHOSTDOWN;
 
 	/* drop any leading bits on the VLAN ID */
 	vid &= VLAN_N_VID - 1;
 
-	err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set);
+	if (fm10k_host_mbx_ready(interface))
+		err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set);
+
 	if (err)
 		return err;
 
@@ -822,7 +844,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
 	/* Do not throw an error if the interface is down. We will sync once
 	 * we come up
 	 */
-	if (test_bit(__FM10K_DOWN, &interface->state))
+	if (test_bit(__FM10K_DOWN, interface->state))
 		return 0;
 
 	fm10k_mbx_lock(interface);
@@ -834,9 +856,13 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
 			goto err_out;
 	}
 
-	/* update our base MAC address */
-	err = hw->mac.ops.update_uc_addr(hw, interface->glort, hw->mac.addr,
-					 vid, set, 0);
+	/* update our base MAC address if host's mailbox is ready */
+	if (fm10k_host_mbx_ready(interface))
+		err = hw->mac.ops.update_uc_addr(hw, interface->glort,
+						 hw->mac.addr, vid, set, 0);
+	else
+		err = -EHOSTDOWN;
+
 	if (err)
 		goto err_out;
 
@@ -907,12 +933,15 @@ static int __fm10k_uc_sync(struct net_device *dev,
 	if (!is_valid_ether_addr(addr))
 		return -EADDRNOTAVAIL;
 
-	/* update table with current entries */
+	/* update table with current entries if host's mailbox is ready */
+	if (!fm10k_host_mbx_ready(interface))
+		return -EHOSTDOWN;
+
 	for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
 		err = hw->mac.ops.update_uc_addr(hw, glort, addr,
-						  vid, sync, 0);
+						 vid, sync, 0);
 		if (err)
 			return err;
 	}
@@ -970,7 +999,10 @@ static int __fm10k_mc_sync(struct net_device *dev,
 	struct fm10k_hw *hw = &interface->hw;
 	u16 vid, glort = interface->glort;
 
-	/* update table with current entries */
+	/* update table with current entries if host's mailbox is ready */
+	if (!fm10k_host_mbx_ready(interface))
+		return 0;
+
 	for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
@@ -1018,8 +1050,10 @@ static void fm10k_set_rx_mode(struct net_device *dev)
 		if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC)
 			fm10k_clear_unused_vlans(interface);
 
-		/* update xcast mode */
-		hw->mac.ops.update_xcast_mode(hw, interface->glort, xcast_mode);
+		/* update xcast mode if host's mailbox is ready */
+		if (fm10k_host_mbx_ready(interface))
+			hw->mac.ops.update_xcast_mode(hw, interface->glort,
+						      xcast_mode);
 
 		/* record updated xcast mode state */
 		interface->xcast_mode = xcast_mode;
@@ -1054,8 +1088,10 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface)
 
 	fm10k_mbx_lock(interface);
 
-	/* Enable logical port */
-	hw->mac.ops.update_lport_state(hw, glort, interface->glort_count, true);
+	/* Enable logical port if host's mailbox is ready */
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_lport_state(hw, glort,
+					       interface->glort_count, true);
 
 	/* update VLAN table */
 	hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0,
@@ -1069,12 +1105,18 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface)
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
 		hw->mac.ops.update_vlan(hw, vid, 0, true);
-		hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr,
-					   vid, true, 0);
+
+		/* Update unicast entries if host's mailbox is ready */
+		if (fm10k_host_mbx_ready(interface))
+			hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr,
+						   vid, true, 0);
 	}
 
-	/* update xcast mode before synchronizing addresses */
-	hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode);
+	/* update xcast mode before synchronizing addresses if host's mailbox
+	 * is ready
+	 */
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode);
 
 	/* synchronize all of the addresses */
 	__dev_uc_sync(netdev, fm10k_uc_sync, fm10k_uc_unsync);
@@ -1096,9 +1138,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface)
 
 	fm10k_mbx_lock(interface);
 
-	/* clear the logical port state on lower device */
-	hw->mac.ops.update_lport_state(hw, interface->glort,
-				       interface->glort_count, false);
+	/* clear the logical port state on lower device if host's mailbox is
+	 * ready
+	 */
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_lport_state(hw, interface->glort,
+					       interface->glort_count, false);
 
 	fm10k_mbx_unlock(interface);
 
@@ -1115,8 +1160,8 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface)
  * @netdev: network interface device structure
  * @stats: storage space for 64bit statistics
  *
- * Returns 64bit statistics, for use in the ndo_get_stats64 callback. This
- * function replaces fm10k_get_stats for kernels which support it.
+ * Obtain 64bit statistics in a way that is safe for both 32bit and 64bit
+ * architectures.
  */
 static void fm10k_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
@@ -1207,7 +1252,7 @@ int fm10k_setup_tc(struct net_device *dev, u8 tc)
 		goto err_open;
 
 	/* flag to indicate SWPRI has yet to be updated */
-	interface->flags |= FM10K_FLAG_SWPRI_CONFIG;
+	set_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags);
 
 	return 0;
 err_open:
@@ -1226,7 +1271,9 @@ static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return fm10k_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return fm10k_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 static void fm10k_assign_l2_accel(struct fm10k_intfc *interface,
@@ -1317,8 +1364,13 @@ static void *fm10k_dfwd_add_station(struct net_device *dev,
 	fm10k_mbx_lock(interface);
 
 	glort = l2_accel->dglort + 1 + i;
-	hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI);
-	hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, true, 0);
+
+	if (fm10k_host_mbx_ready(interface)) {
+		hw->mac.ops.update_xcast_mode(hw, glort,
+					      FM10K_XCAST_MODE_MULTI);
+		hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
+					   0, true, 0);
+	}
 
 	fm10k_mbx_unlock(interface);
 
@@ -1352,8 +1404,13 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv)
 	fm10k_mbx_lock(interface);
 
 	glort = l2_accel->dglort + 1 + i;
-	hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE);
-	hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, false, 0);
+
+	if (fm10k_host_mbx_ready(interface)) {
+		hw->mac.ops.update_xcast_mode(hw, glort,
+					      FM10K_XCAST_MODE_NONE);
+		hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
+					   0, false, 0);
+	}
 
 	fm10k_mbx_unlock(interface);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index e372a5823480..3e26d27ad213 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -19,6 +19,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/aer.h>
 
 #include "fm10k.h"
@@ -92,18 +93,29 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface)
 
 void fm10k_service_event_schedule(struct fm10k_intfc *interface)
 {
-	if (!test_bit(__FM10K_SERVICE_DISABLE, &interface->state) &&
-	    !test_and_set_bit(__FM10K_SERVICE_SCHED, &interface->state))
+	if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) &&
+	    !test_and_set_bit(__FM10K_SERVICE_SCHED, interface->state)) {
+		clear_bit(__FM10K_SERVICE_REQUEST, interface->state);
 		queue_work(fm10k_workqueue, &interface->service_task);
+	} else {
+		set_bit(__FM10K_SERVICE_REQUEST, interface->state);
+	}
 }
 
 static void fm10k_service_event_complete(struct fm10k_intfc *interface)
 {
-	WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, &interface->state));
+	WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, interface->state));
 
 	/* flush memory to make sure state is correct before next watchog */
 	smp_mb__before_atomic();
-	clear_bit(__FM10K_SERVICE_SCHED, &interface->state);
+	clear_bit(__FM10K_SERVICE_SCHED, interface->state);
+
+	/* If a service event was requested since we started, immediately
+	 * re-schedule now. This ensures we don't drop a request until the
+	 * next timer event.
+	 */
+	if (test_bit(__FM10K_SERVICE_REQUEST, interface->state))
+		fm10k_service_event_schedule(interface);
 }
 
 /**
@@ -136,7 +148,7 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface)
 	if (~value) {
 		interface->hw.hw_addr = interface->uc_addr;
 		netif_device_attach(netdev);
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 		netdev_warn(netdev, "PCIe link restored, device now attached\n");
 		return;
 	}
@@ -158,7 +170,7 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
 	/* put off any impending NetWatchDogTimeout */
 	netif_trans_update(netdev);
 
-	while (test_and_set_bit(__FM10K_RESETTING, &interface->state))
+	while (test_and_set_bit(__FM10K_RESETTING, interface->state))
 		usleep_range(1000, 2000);
 
 	rtnl_lock();
@@ -241,7 +253,7 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
 
 	rtnl_unlock();
 
-	clear_bit(__FM10K_RESETTING, &interface->state);
+	clear_bit(__FM10K_RESETTING, interface->state);
 
 	return err;
 err_open:
@@ -253,7 +265,7 @@ reinit_err:
 
 	rtnl_unlock();
 
-	clear_bit(__FM10K_RESETTING, &interface->state);
+	clear_bit(__FM10K_RESETTING, interface->state);
 
 	return err;
 }
@@ -272,11 +284,10 @@ static void fm10k_reinit(struct fm10k_intfc *interface)
 
 static void fm10k_reset_subtask(struct fm10k_intfc *interface)
 {
-	if (!(interface->flags & FM10K_FLAG_RESET_REQUESTED))
+	if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED,
+				interface->flags))
 		return;
 
-	interface->flags &= ~FM10K_FLAG_RESET_REQUESTED;
-
 	netdev_err(interface->netdev, "Reset interface\n");
 
 	fm10k_reinit(interface);
@@ -295,7 +306,7 @@ static void fm10k_configure_swpri_map(struct fm10k_intfc *interface)
 	int i;
 
 	/* clear flag indicating update is needed */
-	interface->flags &= ~FM10K_FLAG_SWPRI_CONFIG;
+	clear_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags);
 
 	/* these registers are only available on the PF */
 	if (hw->mac.type != fm10k_mac_pf)
@@ -316,14 +327,14 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
 	struct fm10k_hw *hw = &interface->hw;
 	s32 err;
 
-	if (test_bit(__FM10K_LINK_DOWN, &interface->state)) {
+	if (test_bit(__FM10K_LINK_DOWN, interface->state)) {
 		interface->host_ready = false;
 		if (time_is_after_jiffies(interface->link_down_event))
 			return;
-		clear_bit(__FM10K_LINK_DOWN, &interface->state);
+		clear_bit(__FM10K_LINK_DOWN, interface->state);
 	}
 
-	if (interface->flags & FM10K_FLAG_SWPRI_CONFIG) {
+	if (test_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags)) {
 		if (rtnl_trylock()) {
 			fm10k_configure_swpri_map(interface);
 			rtnl_unlock();
@@ -335,7 +346,7 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
 
 	err = hw->mac.ops.get_host_state(hw, &interface->host_ready);
 	if (err && time_is_before_jiffies(interface->last_reset))
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 
 	/* free the lock */
 	fm10k_mbx_unlock(interface);
@@ -411,7 +422,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface)
 	int i;
 
 	/* ensure only one thread updates stats at a time */
-	if (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state))
+	if (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state))
 		return;
 
 	/* do not allow stats update via service task for next second */
@@ -492,7 +503,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface)
 	net_stats->rx_errors = rx_errors;
 	net_stats->rx_dropped = interface->stats.nodesc_drop.count;
 
-	clear_bit(__FM10K_UPDATING_STATS, &interface->state);
+	clear_bit(__FM10K_UPDATING_STATS, interface->state);
 }
 
 /**
@@ -522,7 +533,7 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface)
 	 * controller to flush Tx.
 	 */
 	if (some_tx_pending)
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 }
 
 /**
@@ -532,8 +543,8 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface)
 static void fm10k_watchdog_subtask(struct fm10k_intfc *interface)
 {
 	/* if interface is down do nothing */
-	if (test_bit(__FM10K_DOWN, &interface->state) ||
-	    test_bit(__FM10K_RESETTING, &interface->state))
+	if (test_bit(__FM10K_DOWN, interface->state) ||
+	    test_bit(__FM10K_RESETTING, interface->state))
 		return;
 
 	if (interface->host_ready)
@@ -563,8 +574,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface)
 	int i;
 
 	/* If we're down or resetting, just bail */
-	if (test_bit(__FM10K_DOWN, &interface->state) ||
-	    test_bit(__FM10K_RESETTING, &interface->state))
+	if (test_bit(__FM10K_DOWN, interface->state) ||
+	    test_bit(__FM10K_RESETTING, interface->state))
 		return;
 
 	/* rate limit tx hang checks to only once every 2 seconds */
@@ -663,7 +674,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface,
 			FM10K_PFVTCTL_FTAG_DESC_ENABLE);
 
 	/* Initialize XPS */
-	if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, &ring->state) &&
+	if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, ring->state) &&
 	    ring->q_vector)
 		netif_set_xps_queue(ring->netdev,
 				    &ring->q_vector->affinity_mask,
@@ -743,6 +754,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface,
 	/* disable queue to avoid issues while updating state */
 	rxqctl = fm10k_read_reg(hw, FM10K_RXQCTL(reg_idx));
 	rxqctl &= ~FM10K_RXQCTL_ENABLE;
+	fm10k_write_reg(hw, FM10K_RXQCTL(reg_idx), rxqctl);
 	fm10k_write_flush(hw);
 
 	/* possible poll here to verify ring resources have been cleaned */
@@ -863,9 +875,9 @@ static void fm10k_configure_dglort(struct fm10k_intfc *interface)
 	       FM10K_MRQC_IPV6 |
 	       FM10K_MRQC_TCP_IPV6;
 
-	if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP)
+	if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, interface->flags))
 		mrqc |= FM10K_MRQC_UDP_IPV4;
-	if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP)
+	if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, interface->flags))
 		mrqc |= FM10K_MRQC_UDP_IPV6;
 
 	fm10k_write_reg(hw, FM10K_MRQC(0), mrqc);
@@ -980,7 +992,7 @@ void fm10k_netpoll(struct net_device *netdev)
 	int i;
 
 	/* if interface is down do nothing */
-	if (test_bit(__FM10K_DOWN, &interface->state))
+	if (test_bit(__FM10K_DOWN, interface->state))
 		return;
 
 	for (i = 0; i < interface->num_q_vectors; i++)
@@ -1167,13 +1179,13 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data)
 	}
 
 	if (err == FM10K_ERR_RESET_REQUESTED)
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 
 	/* if switch toggled state we should reset GLORTs */
 	if (eicr & FM10K_EICR_SWITCHNOTREADY) {
 		/* force link down for at least 4 seconds */
 		interface->link_down_event = jiffies + (4 * HZ);
-		set_bit(__FM10K_LINK_DOWN, &interface->state);
+		set_bit(__FM10K_LINK_DOWN, interface->state);
 
 		/* reset dglort_map back to no config */
 		hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
@@ -1246,12 +1258,12 @@ static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results,
 	/* MAC was changed so we need reset */
 	if (is_valid_ether_addr(hw->mac.perm_addr) &&
 	    !ether_addr_equal(hw->mac.perm_addr, hw->mac.addr))
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 
 	/* VLAN override was changed, or default VLAN changed */
 	if ((vlan_override != hw->mac.vlan_override) ||
 	    (default_vid != hw->mac.default_vid))
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 
 	return 0;
 }
@@ -1325,7 +1337,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results,
 	if (!err && hw->swapi.status) {
 		/* force link down for a reasonable delay */
 		interface->link_down_event = jiffies + (2 * HZ);
-		set_bit(__FM10K_LINK_DOWN, &interface->state);
+		set_bit(__FM10K_LINK_DOWN, interface->state);
 
 		/* reset dglort_map back to no config */
 		hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
@@ -1356,7 +1368,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results,
 
 	/* we need to reset if port count was just updated */
 	if (dglort_map != hw->mac.dglort_map)
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 
 	return 0;
 }
@@ -1395,7 +1407,7 @@ static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results,
 
 	/* we need to reset if default VLAN was just updated */
 	if (pvid != hw->mac.default_vid)
-		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
 
 	hw->mac.default_vid = pvid;
 
@@ -1623,10 +1635,10 @@ void fm10k_up(struct fm10k_intfc *interface)
 	hw->mac.ops.update_int_moderator(hw);
 
 	/* enable statistics capture again */
-	clear_bit(__FM10K_UPDATING_STATS, &interface->state);
+	clear_bit(__FM10K_UPDATING_STATS, interface->state);
 
 	/* clear down bit to indicate we are ready to go */
-	clear_bit(__FM10K_DOWN, &interface->state);
+	clear_bit(__FM10K_DOWN, interface->state);
 
 	/* enable polling cleanups */
 	fm10k_napi_enable_all(interface);
@@ -1660,7 +1672,7 @@ void fm10k_down(struct fm10k_intfc *interface)
 	int err, i = 0, count = 0;
 
 	/* signal that we are down to the interrupt handler and service task */
-	if (test_and_set_bit(__FM10K_DOWN, &interface->state))
+	if (test_and_set_bit(__FM10K_DOWN, interface->state))
 		return;
 
 	/* call carrier off first to avoid false dev_watchdog timeouts */
@@ -1680,7 +1692,7 @@ void fm10k_down(struct fm10k_intfc *interface)
 	fm10k_update_stats(interface);
 
 	/* prevent updating statistics while we're down */
-	while (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state))
+	while (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state))
 		usleep_range(1000, 2000);
 
 	/* skip waiting for TX DMA if we lost PCIe link */
@@ -1849,8 +1861,8 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
 	memcpy(interface->rssrk, rss_key, sizeof(rss_key));
 
 	/* Start off interface as being down */
-	set_bit(__FM10K_DOWN, &interface->state);
-	set_bit(__FM10K_UPDATING_STATS, &interface->state);
+	set_bit(__FM10K_DOWN, interface->state);
+	set_bit(__FM10K_UPDATING_STATS, interface->state);
 
 	return 0;
 }
@@ -2027,7 +2039,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * must ensure it is disabled since we haven't yet requested the timer
 	 * or work item.
 	 */
-	set_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
 
 	err = fm10k_mbx_request_irq(interface);
 	if (err)
@@ -2068,7 +2080,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	fm10k_iov_configure(pdev, 0);
 
 	/* clear the service task disable bit to allow service task to start */
-	clear_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
 
 	return 0;
 
@@ -2106,7 +2118,7 @@ static void fm10k_remove(struct pci_dev *pdev)
 
 	del_timer_sync(&interface->service_timer);
 
-	set_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
 	cancel_work_sync(&interface->service_task);
 
 	/* free netdev, this may bounce the interrupts due to setup_tc */
@@ -2145,7 +2157,7 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface)
 	 * stopped. We stop the watchdog task until after we resume software
 	 * activity.
 	 */
-	set_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
 	cancel_work_sync(&interface->service_task);
 
 	fm10k_prepare_for_reset(interface);
@@ -2171,10 +2183,10 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
 
 	/* force link to stay down for a second to prevent link flutter */
 	interface->link_down_event = jiffies + (HZ);
-	set_bit(__FM10K_LINK_DOWN, &interface->state);
+	set_bit(__FM10K_LINK_DOWN, interface->state);
 
 	/* clear the service task disable bit to allow service task to start */
-	clear_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
 	fm10k_service_event_schedule(interface);
 
 	return err;
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 3b3c63e54ed6..3da482c3d68d 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -28,6 +28,9 @@
 # Makefile for the Intel(R) Ethernet Connection XL710 (i40e.ko) driver
 #
 
+ccflags-y += -I$(src)
+subdir-ccflags-y += -I$(src)
+
 obj-$(CONFIG_I40E) += i40e.o
 
 i40e-objs := i40e_main.o \
@@ -45,4 +48,3 @@ i40e-objs := i40e_main.o \
 	i40e_virtchnl_pf.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 82d8040fa418..cdde3cc28fb5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -56,9 +56,6 @@
 #include <linux/ptp_clock_kernel.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
-#ifdef I40E_FCOE
-#include "i40e_fcoe.h"
-#endif
 #include "i40e_client.h"
 #include "i40e_virtchnl.h"
 #include "i40e_virtchnl_pf.h"
@@ -85,10 +82,6 @@
 		(((pf)->flags & I40E_FLAG_128_QP_RSS_CAPABLE) ? 128 : 64)
 #define I40E_FDIR_RING			0
 #define I40E_FDIR_RING_COUNT		32
-#ifdef I40E_FCOE
-#define I40E_DEFAULT_FCOE		8 /* default number of QPs for FCoE */
-#define I40E_MINIMUM_FCOE		1 /* minimum number of QPs for FCoE */
-#endif /* I40E_FCOE */
 #define I40E_MAX_AQ_BUF_SIZE		4096
 #define I40E_AQ_LEN			256
 #define I40E_AQ_WORK_LIMIT		66 /* max number of VFs + a little */
@@ -98,14 +91,6 @@
 #define I40E_QUEUE_WAIT_RETRY_LIMIT	10
 #define I40E_INT_NAME_STR_LEN		(IFNAMSIZ + 16)
 
-/* Ethtool Private Flags */
-#define I40E_PRIV_FLAGS_MFP_FLAG		BIT(0)
-#define I40E_PRIV_FLAGS_LINKPOLL_FLAG		BIT(1)
-#define I40E_PRIV_FLAGS_FD_ATR			BIT(2)
-#define I40E_PRIV_FLAGS_VEB_STATS		BIT(3)
-#define I40E_PRIV_FLAGS_HW_ATR_EVICT		BIT(4)
-#define I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT	BIT(5)
-
 #define I40E_NVM_VERSION_LO_SHIFT	0
 #define I40E_NVM_VERSION_LO_MASK	(0xff << I40E_NVM_VERSION_LO_SHIFT)
 #define I40E_NVM_VERSION_HI_SHIFT	12
@@ -140,7 +125,6 @@ enum i40e_state_t {
 	__I40E_CONFIG_BUSY,
 	__I40E_CONFIG_DONE,
 	__I40E_DOWN,
-	__I40E_NEEDS_RESTART,
 	__I40E_SERVICE_SCHED,
 	__I40E_ADMINQ_EVENT_PENDING,
 	__I40E_MDD_EVENT_PENDING,
@@ -153,15 +137,28 @@ enum i40e_state_t {
 	__I40E_GLOBAL_RESET_REQUESTED,
 	__I40E_EMP_RESET_REQUESTED,
 	__I40E_EMP_RESET_INTR_RECEIVED,
-	__I40E_FILTER_OVERFLOW_PROMISC,
 	__I40E_SUSPENDED,
 	__I40E_PTP_TX_IN_PROGRESS,
 	__I40E_BAD_EEPROM,
 	__I40E_DOWN_REQUESTED,
 	__I40E_FD_FLUSH_REQUESTED,
 	__I40E_RESET_FAILED,
-	__I40E_PORT_TX_SUSPENDED,
+	__I40E_PORT_SUSPENDED,
 	__I40E_VF_DISABLE,
+	/* This must be last as it determines the size of the BITMAP */
+	__I40E_STATE_SIZE__,
+};
+
+/* VSI state flags */
+enum i40e_vsi_state_t {
+	__I40E_VSI_DOWN,
+	__I40E_VSI_NEEDS_RESTART,
+	__I40E_VSI_SYNCING_FILTERS,
+	__I40E_VSI_OVERFLOW_PROMISC,
+	__I40E_VSI_REINIT_REQUESTED,
+	__I40E_VSI_DOWN_REQUESTED,
+	/* This must be last as it determines the size of the BITMAP */
+	__I40E_VSI_STATE_SIZE__,
 };
 
 enum i40e_interrupt_policy {
@@ -202,17 +199,32 @@ enum i40e_fd_stat_idx {
 #define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL)
 
+/* The following structure contains the data parsed from the user-defined
+ * field of the ethtool_rx_flow_spec structure.
+ */
+struct i40e_rx_flow_userdef {
+	bool flex_filter;
+	u16 flex_word;
+	u16 flex_offset;
+};
+
 struct i40e_fdir_filter {
 	struct hlist_node fdir_node;
 	/* filter ipnut set */
 	u8 flow_type;
 	u8 ip4_proto;
 	/* TX packet view of src and dst */
-	__be32 dst_ip[4];
-	__be32 src_ip[4];
+	__be32 dst_ip;
+	__be32 src_ip;
 	__be16 src_port;
 	__be16 dst_port;
 	__be32 sctp_v_tag;
+
+	/* Flexible data to match within the packet payload */
+	__be16 flex_word;
+	u16 flex_offset;
+	bool flex_filter;
+
 	/* filter control */
 	u16 q_index;
 	u8  flex_off;
@@ -244,15 +256,85 @@ struct i40e_tc_configuration {
 };
 
 struct i40e_udp_port_config {
-	__be16 index;
+	/* AdminQ command interface expects port number in Host byte order */
+	u16 port;
 	u8 type;
 };
 
+/* macros related to FLX_PIT */
+#define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \
+				    I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \
+				    I40E_PRTQF_FLX_PIT_FSIZE_MASK)
+#define I40E_FLEX_SET_DST_WORD(dst) (((dst) << \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT) & \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_MASK)
+#define I40E_FLEX_SET_SRC_WORD(src) (((src) << \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT) & \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK)
+#define I40E_FLEX_PREP_VAL(dst, fsize, src) (I40E_FLEX_SET_DST_WORD(dst) | \
+					     I40E_FLEX_SET_FSIZE(fsize) | \
+					     I40E_FLEX_SET_SRC_WORD(src))
+
+#define I40E_FLEX_PIT_GET_SRC(flex) (((flex) & \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK) >> \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT)
+#define I40E_FLEX_PIT_GET_DST(flex) (((flex) & \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_MASK) >> \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT)
+#define I40E_FLEX_PIT_GET_FSIZE(flex) (((flex) & \
+				       I40E_PRTQF_FLX_PIT_FSIZE_MASK) >> \
+				       I40E_PRTQF_FLX_PIT_FSIZE_SHIFT)
+
+#define I40E_MAX_FLEX_SRC_OFFSET 0x1F
+
+/* macros related to GLQF_ORT */
+#define I40E_ORT_SET_IDX(idx)		(((idx) << \
+					  I40E_GLQF_ORT_PIT_INDX_SHIFT) & \
+					 I40E_GLQF_ORT_PIT_INDX_MASK)
+
+#define I40E_ORT_SET_COUNT(count)	(((count) << \
+					  I40E_GLQF_ORT_FIELD_CNT_SHIFT) & \
+					 I40E_GLQF_ORT_FIELD_CNT_MASK)
+
+#define I40E_ORT_SET_PAYLOAD(payload)	(((payload) << \
+					  I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT) & \
+					 I40E_GLQF_ORT_FLX_PAYLOAD_MASK)
+
+#define I40E_ORT_PREP_VAL(idx, count, payload) (I40E_ORT_SET_IDX(idx) | \
+						I40E_ORT_SET_COUNT(count) | \
+						I40E_ORT_SET_PAYLOAD(payload))
+
+#define I40E_L3_GLQF_ORT_IDX		34
+#define I40E_L4_GLQF_ORT_IDX		35
+
+/* Flex PIT register index */
+#define I40E_FLEX_PIT_IDX_START_L2	0
+#define I40E_FLEX_PIT_IDX_START_L3	3
+#define I40E_FLEX_PIT_IDX_START_L4	6
+
+#define I40E_FLEX_PIT_TABLE_SIZE	3
+
+#define I40E_FLEX_DEST_UNUSED		63
+
+#define I40E_FLEX_INDEX_ENTRIES		8
+
+/* Flex MASK to disable all flexible entries */
+#define I40E_FLEX_INPUT_MASK	(I40E_FLEX_50_MASK | I40E_FLEX_51_MASK | \
+				 I40E_FLEX_52_MASK | I40E_FLEX_53_MASK | \
+				 I40E_FLEX_54_MASK | I40E_FLEX_55_MASK | \
+				 I40E_FLEX_56_MASK | I40E_FLEX_57_MASK)
+
+struct i40e_flex_pit {
+	struct list_head list;
+	u16 src_offset;
+	u8 pit_index;
+};
+
 /* struct that defines the Ethernet device */
 struct i40e_pf {
 	struct pci_dev *pdev;
 	struct i40e_hw hw;
-	unsigned long state;
+	DECLARE_BITMAP(state, __I40E_STATE_SIZE__);
 	struct msix_entry *msix_entries;
 	bool fc_autoneg_status;
 
@@ -262,10 +344,6 @@ struct i40e_pf {
 	u16 num_vmdq_msix;         /* num queue vectors per vmdq pool */
 	u16 num_req_vfs;           /* num VFs requested for this VF */
 	u16 num_vf_qps;            /* num queue pairs per VF */
-#ifdef I40E_FCOE
-	u16 num_fcoe_qps;          /* num fcoe queues this PF has set up */
-	u16 num_fcoe_msix;         /* num queue vectors per fcoe pool */
-#endif /* I40E_FCOE */
 	u16 num_lan_qps;           /* num lan queues this PF has set up */
 	u16 num_lan_msix;          /* num queue vectors for the base PF vsi */
 	u16 num_fdsb_msix;         /* num queue vectors for sideband Fdir */
@@ -285,7 +363,23 @@ struct i40e_pf {
 	u32 fd_flush_cnt;
 	u32 fd_add_err;
 	u32 fd_atr_cnt;
-	u32 fd_tcp_rule;
+
+	/* Book-keeping of side-band filter count per flow-type.
+	 * This is used to detect and handle input set changes for
+	 * respective flow-type.
+	 */
+	u16 fd_tcp4_filter_cnt;
+	u16 fd_udp4_filter_cnt;
+	u16 fd_sctp4_filter_cnt;
+	u16 fd_ip4_filter_cnt;
+
+	/* Flexible filter table values that need to be programmed into
+	 * hardware, which expects L3 and L4 to be programmed separately. We
+	 * need to ensure that the values are in ascended order and don't have
+	 * duplicates, so we track each L3 and L4 values in separate lists.
+	 */
+	struct list_head l3_flex_pit_list;
+	struct list_head l4_flex_pit_list;
 
 	struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
 	u16 pending_udp_bitmap;
@@ -307,21 +401,15 @@ struct i40e_pf {
 #define I40E_FLAG_MSIX_ENABLED			BIT_ULL(3)
 #define I40E_FLAG_RSS_ENABLED			BIT_ULL(6)
 #define I40E_FLAG_VMDQ_ENABLED			BIT_ULL(7)
-#define I40E_FLAG_FDIR_REQUIRES_REINIT		BIT_ULL(8)
-#define I40E_FLAG_NEED_LINK_UPDATE		BIT_ULL(9)
 #define I40E_FLAG_IWARP_ENABLED			BIT_ULL(10)
-#ifdef I40E_FCOE
-#define I40E_FLAG_FCOE_ENABLED			BIT_ULL(11)
-#endif /* I40E_FCOE */
-#define I40E_FLAG_CLEAN_ADMINQ			BIT_ULL(14)
 #define I40E_FLAG_FILTER_SYNC			BIT_ULL(15)
 #define I40E_FLAG_SERVICE_CLIENT_REQUESTED	BIT_ULL(16)
-#define I40E_FLAG_PROCESS_MDD_EVENT		BIT_ULL(17)
-#define I40E_FLAG_PROCESS_VFLR_EVENT		BIT_ULL(18)
 #define I40E_FLAG_SRIOV_ENABLED			BIT_ULL(19)
 #define I40E_FLAG_DCB_ENABLED			BIT_ULL(20)
 #define I40E_FLAG_FD_SB_ENABLED			BIT_ULL(21)
 #define I40E_FLAG_FD_ATR_ENABLED		BIT_ULL(22)
+#define I40E_FLAG_FD_SB_AUTO_DISABLED		BIT_ULL(23)
+#define I40E_FLAG_FD_ATR_AUTO_DISABLED		BIT_ULL(24)
 #define I40E_FLAG_PTP				BIT_ULL(25)
 #define I40E_FLAG_MFP_ENABLED			BIT_ULL(26)
 #define I40E_FLAG_UDP_FILTER_SYNC		BIT_ULL(27)
@@ -348,16 +436,13 @@ struct i40e_pf {
 #define I40E_FLAG_TRUE_PROMISC_SUPPORT		BIT_ULL(51)
 #define I40E_FLAG_HAVE_CRT_RETIMER		BIT_ULL(52)
 #define I40E_FLAG_PTP_L4_CAPABLE		BIT_ULL(53)
-#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(54)
+#define I40E_FLAG_CLIENT_RESET			BIT_ULL(54)
 #define I40E_FLAG_TEMP_LINK_POLLING		BIT_ULL(55)
+#define I40E_FLAG_CLIENT_L2_CHANGE		BIT_ULL(56)
+#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(57)
+#define I40E_FLAG_LEGACY_RX			BIT_ULL(58)
 
-	/* tracks features that get auto disabled by errors */
-	u64 auto_disable_flags;
-
-#ifdef I40E_FCOE
-	struct i40e_fcoe fcoe;
-
-#endif /* I40E_FCOE */
+	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
 	struct i40e_hw_port_stats stats;
 	struct i40e_hw_port_stats stats_offsets;
@@ -412,8 +497,6 @@ struct i40e_pf {
 	 */
 	u16 dcbx_cap;
 
-	u32 fcoe_hmc_filt_num;
-	u32 fcoe_hmc_cntx_num;
 	struct i40e_filter_control_settings filter_settings;
 
 	struct ptp_clock *ptp_clock;
@@ -517,7 +600,7 @@ struct i40e_vsi {
 	bool stat_offsets_loaded;
 
 	u32 current_netdev_flags;
-	unsigned long state;
+	DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__);
 #define I40E_VSI_FLAG_FILTER_CHANGED	BIT(0)
 #define I40E_VSI_FLAG_VEB_OWNER		BIT(1)
 	unsigned long flags;
@@ -533,16 +616,10 @@ struct i40e_vsi {
 	struct rtnl_link_stats64 net_stats_offsets;
 	struct i40e_eth_stats eth_stats;
 	struct i40e_eth_stats eth_stats_offsets;
-#ifdef I40E_FCOE
-	struct i40e_fcoe_stats fcoe_stats;
-	struct i40e_fcoe_stats fcoe_stats_offsets;
-	bool fcoe_stat_offsets_loaded;
-#endif
 	u32 tx_restart;
 	u32 tx_busy;
 	u64 tx_linearize;
 	u64 tx_force_wb;
-	u64 tx_lost_interrupt;
 	u32 rx_buf_failed;
 	u32 rx_page_failed;
 
@@ -628,9 +705,6 @@ struct i40e_q_vector {
 
 	u8 num_ringpairs;	/* total number of ring pairs in vector */
 
-#define I40E_Q_VECTOR_HUNG_DETECT 0 /* Bit Index for hung detection logic */
-	unsigned long hung_detected; /* Set/Reset for hung_detection logic */
-
 	cpumask_t affinity_mask;
 	struct irq_affinity_notify affinity_notify;
 
@@ -696,27 +770,49 @@ static inline void i40e_vsi_setup_irqhandler(struct i40e_vsi *vsi,
 }
 
 /**
- * i40e_rx_is_programming_status - check for programming status descriptor
- * @qw: the first quad word of the program status descriptor
+ * i40e_get_fd_cnt_all - get the total FD filter space available
+ * @pf: pointer to the PF struct
+ **/
+static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf)
+{
+	return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count;
+}
+
+/**
+ * i40e_read_fd_input_set - reads value of flow director input set register
+ * @pf: pointer to the PF struct
+ * @addr: register addr
  *
- * The value of in the descriptor length field indicate if this
- * is a programming status descriptor for flow director or FCoE
- * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
- * it is a packet descriptor.
+ * This function reads value of flow director input set register
+ * specified by 'addr' (which is specific to flow-type)
  **/
-static inline bool i40e_rx_is_programming_status(u64 qw)
+static inline u64 i40e_read_fd_input_set(struct i40e_pf *pf, u16 addr)
 {
-	return I40E_RX_PROG_STATUS_DESC_LENGTH ==
-		(qw >> I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT);
+	u64 val;
+
+	val = i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1));
+	val <<= 32;
+	val += i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0));
+
+	return val;
 }
 
 /**
- * i40e_get_fd_cnt_all - get the total FD filter space available
+ * i40e_write_fd_input_set - writes value into flow director input set register
  * @pf: pointer to the PF struct
+ * @addr: register addr
+ * @val: value to be written
+ *
+ * This function writes specified value to the register specified by 'addr'.
+ * This register is input set register based on flow-type.
  **/
-static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf)
+static inline void i40e_write_fd_input_set(struct i40e_pf *pf,
+					   u16 addr, u64 val)
 {
-	return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count;
+	i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1),
+			  (u32)(val >> 32));
+	i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0),
+			  (u32)(val & 0xFFFFFFFFULL));
 }
 
 /* needed by i40e_ethtool.c */
@@ -725,7 +821,7 @@ void i40e_down(struct i40e_vsi *vsi);
 extern const char i40e_driver_name[];
 extern const char i40e_driver_version_str[];
 void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags);
-void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags);
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired);
 int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut,
@@ -773,17 +869,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
 struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 				u16 uplink, u32 param1);
 int i40e_vsi_release(struct i40e_vsi *vsi);
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
-			      struct i40e_vsi_context *ctxt,
-			      u8 enabled_tc, bool is_add);
-#endif
 void i40e_service_event_schedule(struct i40e_pf *pf);
 void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id,
 				  u8 *msg, u16 len);
 
 int i40e_vsi_start_rings(struct i40e_vsi *vsi);
 void i40e_vsi_stop_rings(struct i40e_vsi *vsi);
+void i40e_vsi_stop_rings_no_wait(struct  i40e_vsi *vsi);
+int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi);
 int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count);
 struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid,
 				u16 downlink_seid, u8 enabled_tc);
@@ -813,8 +906,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi);
 void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset);
 void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs);
 void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id);
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
-			   enum i40e_client_type type);
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id);
 /**
  * i40e_irq_dynamic_enable - Enable default interrupt generation settings
  * @vsi: pointer to a vsi
@@ -838,20 +930,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 
 void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
 void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba);
-#ifdef I40E_FCOE
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
-				  struct rtnl_link_stats64 *storage);
-int i40e_set_mac(struct net_device *netdev, void *p);
-void i40e_set_rx_mode(struct net_device *netdev);
-#endif
 int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev);
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
-			 __always_unused __be16 proto, u16 vid);
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
-			  __always_unused __be16 proto, u16 vid);
-#endif
 int i40e_open(struct net_device *netdev);
 int i40e_close(struct net_device *netdev);
 int i40e_vsi_open(struct i40e_vsi *vsi);
@@ -865,25 +944,6 @@ struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi,
 int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr);
 bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
 struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr);
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
-		    struct tc_to_netdev *tc);
-void i40e_netpoll(struct net_device *netdev);
-int i40e_fcoe_enable(struct net_device *netdev);
-int i40e_fcoe_disable(struct net_device *netdev);
-int i40e_fcoe_vsi_init(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt);
-u8 i40e_get_fcoe_tc_map(struct i40e_pf *pf);
-void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi);
-void i40e_fcoe_vsi_setup(struct i40e_pf *pf);
-void i40e_init_pf_fcoe(struct i40e_pf *pf);
-int i40e_fcoe_setup_ddp_resources(struct i40e_vsi *vsi);
-void i40e_fcoe_free_ddp_resources(struct i40e_vsi *vsi);
-int i40e_fcoe_handle_offload(struct i40e_ring *rx_ring,
-			     union i40e_rx_desc *rx_desc,
-			     struct sk_buff *skb);
-void i40e_fcoe_handle_status(struct i40e_ring *rx_ring,
-			     union i40e_rx_desc *rx_desc, u8 prog_id);
-#endif /* I40E_FCOE */
 void i40e_vlan_stripping_enable(struct i40e_vsi *vsi);
 #ifdef CONFIG_I40E_DCB
 void i40e_dcbnl_flush_apps(struct i40e_pf *pf,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 56fb27298936..ba04988e0598 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -850,8 +850,8 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 			 */
 			if (i40e_asq_done(hw))
 				break;
-			usleep_range(1000, 2000);
-			total_delay++;
+			udelay(50);
+			total_delay += 50;
 		} while (total_delay < hw->aq.asq_cmd_timeout);
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index d92aad38afdc..2349fbe04bd2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -151,7 +151,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 
 /* general information */
 #define I40E_AQ_LARGE_BUF	512
-#define I40E_ASQ_CMD_TIMEOUT	250  /* msecs */
+#define I40E_ASQ_CMD_TIMEOUT	250000  /* usecs */
 
 void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
 				       u16 opcode);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 451f48b7540a..5eb04114e13f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_list_func_capabilities	= 0x000A,
 	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
 
+	/* Proxy commands */
+	i40e_aqc_opc_set_proxy_config		= 0x0104,
+	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
 	/* LAA */
 	i40e_aqc_opc_mac_address_read	= 0x0107,
 	i40e_aqc_opc_mac_address_write	= 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
 	/* PXE */
 	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
 
+	/* WoL commands */
+	i40e_aqc_opc_set_wol_filter	= 0x0120,
+	i40e_aqc_opc_get_wake_reason	= 0x0121,
+
 	/* internal switch commands */
 	i40e_aqc_opc_get_switch_config		= 0x0200,
 	i40e_aqc_opc_add_statistics		= 0x0201,
@@ -177,10 +185,15 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
 	i40e_aqc_opc_add_cloud_filters		= 0x025C,
 	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
+	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
 
 	i40e_aqc_opc_add_mirror_rule	= 0x0260,
 	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
 
+	/* Pipeline Personalization Profile */
+	i40e_aqc_opc_write_personalization_profile	= 0x0270,
+	i40e_aqc_opc_get_personalization_profile_list	= 0x0271,
+
 	/* DCB commands */
 	i40e_aqc_opc_dcb_ignore_pfc	= 0x0301,
 	i40e_aqc_opc_dcb_updated	= 0x0302,
@@ -563,6 +576,56 @@ struct i40e_aqc_clear_pxe {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+	__le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
+		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
+		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+	__le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER				0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
+	__le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
+	u8 reserved[2];
+	__le32	address_high;
+	__le32	address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+	u8 filter[128];
+	u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+	u8 reserved_1[2];
+	__le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+	u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
 /* Switch configuration commands (0x02xx) */
 
 /* Used by many indirect commands that only pass an seid and a buffer in the
@@ -645,6 +708,8 @@ struct i40e_aqc_set_port_parameters {
 #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
 #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -696,6 +761,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 /* Set Switch Configuration (direct 0x0205) */
 struct i40e_aqc_set_switch_config {
 	__le16	flags;
+/* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
@@ -1369,6 +1435,36 @@ struct i40e_aqc_add_delete_mirror_rule_completion {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion);
 
+/* Pipeline Personalization Profile */
+struct i40e_aqc_write_personalization_profile {
+	u8      flags;
+	u8      reserved[3];
+	__le32  profile_track_id;
+	__le32  addr_high;
+	__le32  addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile);
+
+struct i40e_aqc_write_ppp_resp {
+	__le32 error_offset;
+	__le32 error_info;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct i40e_aqc_get_applied_profiles {
+	u8      flags;
+#define I40E_AQC_GET_PPP_GET_CONF	0x1
+#define I40E_AQC_GET_PPP_GET_RDPU_CONF	0x2
+	u8      rsv[3];
+	__le32  reserved;
+	__le32  addr_high;
+	__le32  addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles);
+
 /* DCB 0x03xx*/
 
 /* PFC Ignore (direct 0x0301)
@@ -1844,11 +1940,12 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	external_power_ability;
+	u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
+#define I40E_AQ_PWR_CLASS_MASK		0x03
 	u8	reserved[4];
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index d570219efd9f..c3b81a97558e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -32,16 +32,10 @@
 #include "i40e_client.h"
 
 static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR;
-
+static struct i40e_client *registered_client;
 static LIST_HEAD(i40e_devices);
 static DEFINE_MUTEX(i40e_device_mutex);
 
-static LIST_HEAD(i40e_clients);
-static DEFINE_MUTEX(i40e_client_mutex);
-
-static LIST_HEAD(i40e_client_instances);
-static DEFINE_MUTEX(i40e_client_instance_mutex);
-
 static int i40e_client_virtchnl_send(struct i40e_info *ldev,
 				     struct i40e_client *client,
 				     u32 vf_id, u8 *msg, u16 len);
@@ -67,28 +61,6 @@ static struct i40e_ops i40e_lan_ops = {
 };
 
 /**
- * i40e_client_type_to_vsi_type - convert client type to vsi type
- * @client_type: the i40e_client type
- *
- * returns the related vsi type value
- **/
-static
-enum i40e_vsi_type i40e_client_type_to_vsi_type(enum i40e_client_type type)
-{
-	switch (type) {
-	case I40E_CLIENT_IWARP:
-		return I40E_VSI_IWARP;
-
-	case I40E_CLIENT_VMDQ2:
-		return I40E_VSI_VMDQ2;
-
-	default:
-		pr_err("i40e: Client type unknown\n");
-		return I40E_VSI_TYPE_UNKNOWN;
-	}
-}
-
-/**
  * i40e_client_get_params - Get the params that can change at runtime
  * @vsi: the VSI with the message
  * @param: clinet param struct
@@ -134,31 +106,22 @@ int i40e_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params)
 void
 i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!vsi)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->virtchnl_receive) {
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance virtual channel receive routine\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == vsi->back) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->virtchnl_receive) {
-				dev_dbg(&vsi->back->pdev->dev,
-					"Cannot locate client instance virtual channel receive routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort virtchnl_receive\n");
-				continue;
-			}
-			cdev->client->ops->virtchnl_receive(&cdev->lan_info,
-							    cdev->client,
-							    vf_id, msg, len);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort virtchnl_receive\n");
+		return;
+	}
+	cdev->client->ops->virtchnl_receive(&cdev->lan_info, cdev->client,
+					    vf_id, msg, len);
 }
 
 /**
@@ -169,39 +132,30 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
  **/
 void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_client_instance *cdev = pf->cinst;
 	struct i40e_params params;
 
-	if (!vsi)
+	if (!cdev || !cdev->client)
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == vsi->back) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->l2_param_change) {
-				dev_dbg(&vsi->back->pdev->dev,
-					"Cannot locate client instance l2_param_change routine\n");
-				continue;
-			}
+	if (!cdev->client->ops || !cdev->client->ops->l2_param_change) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance l2_param_change routine\n");
+		return;
+	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
+		return;
+	}
 	memset(&params, 0, sizeof(params));
 	i40e_client_get_params(vsi, &params);
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
-				continue;
-			}
-			cdev->lan_info.params = params;
-			cdev->client->ops->l2_param_change(&cdev->lan_info,
-							   cdev->client,
-							   &params);
-		}
-	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	memcpy(&cdev->lan_info.params, &params, sizeof(struct i40e_params));
+	cdev->client->ops->l2_param_change(&cdev->lan_info, cdev->client,
+					   &params);
 }
 
 /**
- * i40e_client_release_qvlist
+ * i40e_client_release_qvlist - release MSI-X vector mapping for client
  * @ldev: pointer to L2 context.
  *
  **/
@@ -237,26 +191,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev)
  **/
 void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!vsi)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->close) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance close routine\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.netdev == vsi->netdev) {
-			if (!cdev->client ||
-			    !cdev->client->ops || !cdev->client->ops->close) {
-				dev_dbg(&vsi->back->pdev->dev,
-					"Cannot locate client instance close routine\n");
-				continue;
-			}
-			cdev->client->ops->close(&cdev->lan_info, cdev->client,
-						 reset);
-			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
-			i40e_client_release_qvlist(&cdev->lan_info);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	cdev->client->ops->close(&cdev->lan_info, cdev->client, reset);
+	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+	i40e_client_release_qvlist(&cdev->lan_info);
 }
 
 /**
@@ -268,30 +215,20 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
  **/
 void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!pf)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->vf_reset) {
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance VF reset routine\n");
+		return;
+	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,  &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == pf) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->vf_reset) {
-				dev_dbg(&pf->pdev->dev,
-					"Cannot locate client instance VF reset routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n");
-				continue;
-			}
-			cdev->client->ops->vf_reset(&cdev->lan_info,
-						    cdev->client, vf_id);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	cdev->client->ops->vf_reset(&cdev->lan_info, cdev->client, vf_id);
 }
 
 /**
@@ -303,30 +240,21 @@ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id)
  **/
 void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!pf)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->vf_enable) {
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance VF enable routine\n");
+		return;
+	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+		      &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == pf) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->vf_enable) {
-				dev_dbg(&pf->pdev->dev,
-					"Cannot locate client instance VF enable routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n");
-				continue;
-			}
-			cdev->client->ops->vf_enable(&cdev->lan_info,
-						     cdev->client, num_vfs);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	cdev->client->ops->vf_enable(&cdev->lan_info, cdev->client, num_vfs);
 }
 
 /**
@@ -337,37 +265,25 @@ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs)
  * If there is a client of the specified type attached to this PF, call
  * its vf_capable routine
  **/
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
-			   enum i40e_client_type type)
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = pf->cinst;
 	int capable = false;
 
-	if (!pf)
-		return false;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == pf) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->vf_capable ||
-			    !(cdev->client->type == type)) {
-				dev_dbg(&pf->pdev->dev,
-					"Cannot locate client instance VF capability routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-capable\n");
-				continue;
-			}
-			capable = cdev->client->ops->vf_capable(&cdev->lan_info,
-								cdev->client,
-								vf_id);
-			break;
-		}
+	if (!cdev || !cdev->client)
+		goto out;
+	if (!cdev->client->ops || !cdev->client->ops->vf_capable) {
+		dev_info(&pf->pdev->dev,
+			 "Cannot locate client instance VF capability routine\n");
+		goto out;
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state))
+		goto out;
+
+	capable = cdev->client->ops->vf_capable(&cdev->lan_info,
+						cdev->client,
+						vf_id);
+out:
 	return capable;
 }
 
@@ -377,27 +293,19 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
  * @client: pointer to a client struct in the client list.
  * @existing: if there was already an existing instance
  *
- * Returns cdev ptr on success or if already exists, NULL on failure
  **/
-static
-struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
-						     struct i40e_client *client,
-						     bool *existing)
+static void i40e_client_add_instance(struct i40e_pf *pf)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = NULL;
 	struct netdev_hw_addr *mac = NULL;
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if ((cdev->lan_info.pf == pf) && (cdev->client == client)) {
-			*existing = true;
-			goto out;
-		}
-	}
+	if (!registered_client || pf->cinst)
+		return;
+
 	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
 	if (!cdev)
-		goto out;
+		return;
 
 	cdev->lan_info.pf = (void *)pf;
 	cdev->lan_info.netdev = vsi->netdev;
@@ -417,7 +325,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
 	if (i40e_client_get_params(vsi, &cdev->lan_info.params)) {
 		kfree(cdev);
 		cdev = NULL;
-		goto out;
+		return;
 	}
 
 	cdev->lan_info.msix_count = pf->num_iwarp_msix;
@@ -430,41 +338,20 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
 	else
 		dev_err(&pf->pdev->dev, "MAC address list is empty!\n");
 
-	cdev->client = client;
-	INIT_LIST_HEAD(&cdev->list);
-	list_add(&cdev->list, &i40e_client_instances);
-out:
-	mutex_unlock(&i40e_client_instance_mutex);
-	return cdev;
+	cdev->client = registered_client;
+	pf->cinst = cdev;
 }
 
 /**
  * i40e_client_del_instance - removes a client instance from the list
  * @pf: pointer to the board struct
  *
- * Returns 0 on success or non-0 on error
  **/
 static
-int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client)
+void i40e_client_del_instance(struct i40e_pf *pf)
 {
-	struct i40e_client_instance *cdev, *tmp;
-	int ret = -ENODEV;
-
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) {
-		if ((cdev->lan_info.pf != pf) || (cdev->client != client))
-			continue;
-
-		dev_info(&pf->pdev->dev, "Deleted instance of Client %s, of dev %d bus=0x%02x func=0x%02x)\n",
-			 client->name, pf->hw.pf_id,
-			 pf->hw.bus.device, pf->hw.bus.func);
-		list_del(&cdev->list);
-		kfree(cdev);
-		ret = 0;
-		break;
-	}
-	mutex_unlock(&i40e_client_instance_mutex);
-	return ret;
+	kfree(pf->cinst);
+	pf->cinst = NULL;
 }
 
 /**
@@ -473,67 +360,50 @@ int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client)
  **/
 void i40e_client_subtask(struct i40e_pf *pf)
 {
+	struct i40e_client *client = registered_client;
 	struct i40e_client_instance *cdev;
-	struct i40e_client *client;
-	bool existing = false;
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	int ret = 0;
 
 	if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED))
 		return;
 	pf->flags &= ~I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+	cdev = pf->cinst;
 
 	/* If we're down or resetting, just bail */
-	if (test_bit(__I40E_DOWN, &pf->state) ||
-	    test_bit(__I40E_CONFIG_BUSY, &pf->state))
+	if (test_bit(__I40E_DOWN, pf->state) ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return;
 
-	/* Check client state and instantiate client if client registered */
-	mutex_lock(&i40e_client_mutex);
-	list_for_each_entry(client, &i40e_clients, list) {
-		/* first check client is registered */
-		if (!test_bit(__I40E_CLIENT_REGISTERED, &client->state))
-			continue;
-
-		/* Do we also need the LAN VSI to be up, to create instance */
-		if (!(client->flags & I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE)) {
-			/* check if L2 VSI is up, if not we are not ready */
-			if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
-				continue;
-		} else {
-			dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n",
-				 client->name);
-		}
-
-		/* Add the client instance to the instance list */
-		cdev = i40e_client_add_instance(pf, client, &existing);
-		if (!cdev)
-			continue;
-
-		if (!existing) {
-			dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n",
-				 client->name, pf->hw.pf_id,
-				 pf->hw.bus.bus_id, pf->hw.bus.device,
-				 pf->hw.bus.func);
-		}
+	if (!client || !cdev)
+		return;
 
-		mutex_lock(&i40e_client_instance_mutex);
-		if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-			      &cdev->state)) {
-			/* Send an Open request to the client */
-			if (client->ops && client->ops->open)
-				ret = client->ops->open(&cdev->lan_info,
-							client);
-			if (!ret) {
-				set_bit(__I40E_CLIENT_INSTANCE_OPENED,
-					&cdev->state);
-			} else {
-				/* remove client instance */
-				i40e_client_del_instance(pf, client);
+	/* Here we handle client opens. If the client is down, but
+	 * the netdev is up, then open the client.
+	 */
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		if (!test_bit(__I40E_VSI_DOWN, vsi->state) &&
+		    client->ops && client->ops->open) {
+			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+			ret = client->ops->open(&cdev->lan_info, client);
+			if (ret) {
+				/* Remove failed client instance */
+				clear_bit(__I40E_CLIENT_INSTANCE_OPENED,
+					  &cdev->state);
+				i40e_client_del_instance(pf);
 			}
 		}
-		mutex_unlock(&i40e_client_instance_mutex);
+	} else {
+	/* Likewise for client close. If the client is up, but the netdev
+	 * is down, then close the client.
+	 */
+		if (test_bit(__I40E_VSI_DOWN, vsi->state) &&
+		    client->ops && client->ops->close) {
+			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+			client->ops->close(&cdev->lan_info, client, false);
+			i40e_client_release_qvlist(&cdev->lan_info);
+		}
 	}
-	mutex_unlock(&i40e_client_mutex);
 }
 
 /**
@@ -566,6 +436,12 @@ int i40e_lan_add_device(struct i40e_pf *pf)
 		 pf->hw.pf_id, pf->hw.bus.bus_id,
 		 pf->hw.bus.device, pf->hw.bus.func);
 
+	/* If a client has already been registered, we need to add an instance
+	 * of it to our new LAN device.
+	 */
+	if (registered_client)
+		i40e_client_add_instance(pf);
+
 	/* Since in some cases register may have happened before a device gets
 	 * added, we can schedule a subtask to go initiate the clients if
 	 * they can be launched at probe time.
@@ -589,6 +465,9 @@ int i40e_lan_del_device(struct i40e_pf *pf)
 	struct i40e_device *ldev, *tmp;
 	int ret = -ENODEV;
 
+	/* First, remove any client instance. */
+	i40e_client_del_instance(pf);
+
 	mutex_lock(&i40e_device_mutex);
 	list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) {
 		if (ldev->pf == pf) {
@@ -601,7 +480,6 @@ int i40e_lan_del_device(struct i40e_pf *pf)
 			break;
 		}
 	}
-
 	mutex_unlock(&i40e_device_mutex);
 	return ret;
 }
@@ -610,22 +488,24 @@ int i40e_lan_del_device(struct i40e_pf *pf)
  * i40e_client_release - release client specific resources
  * @client: pointer to the registered client
  *
- * Return 0 on success or < 0 on error
  **/
-static int i40e_client_release(struct i40e_client *client)
+static void i40e_client_release(struct i40e_client *client)
 {
-	struct i40e_client_instance *cdev, *tmp;
+	struct i40e_client_instance *cdev;
+	struct i40e_device *ldev;
 	struct i40e_pf *pf;
-	int ret = 0;
 
-	LIST_HEAD(cdevs_tmp);
-
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) {
-		if (strncmp(cdev->client->name, client->name,
-			    I40E_CLIENT_STR_LENGTH))
+	mutex_lock(&i40e_device_mutex);
+	list_for_each_entry(ldev, &i40e_devices, list) {
+		pf = ldev->pf;
+		cdev = pf->cinst;
+		if (!cdev)
 			continue;
-		pf = (struct i40e_pf *)cdev->lan_info.pf;
+
+		while (test_and_set_bit(__I40E_SERVICE_SCHED,
+					pf->state))
+			usleep_range(500, 1000);
+
 		if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
 			if (client->ops && client->ops->close)
 				client->ops->close(&cdev->lan_info, client,
@@ -637,18 +517,13 @@ static int i40e_client_release(struct i40e_client *client)
 				 "Client %s instance for PF id %d closed\n",
 				 client->name, pf->hw.pf_id);
 		}
-		/* delete the client instance from the list */
-		list_move(&cdev->list, &cdevs_tmp);
+		/* delete the client instance */
+		i40e_client_del_instance(pf);
 		dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n",
 			 client->name);
+		clear_bit(__I40E_SERVICE_SCHED, pf->state);
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
-
-	/* free the client device and release its vsi */
-	list_for_each_entry_safe(cdev, tmp, &cdevs_tmp, list) {
-		kfree(cdev);
-	}
-	return ret;
+	mutex_unlock(&i40e_device_mutex);
 }
 
 /**
@@ -664,6 +539,7 @@ static void i40e_client_prepare(struct i40e_client *client)
 	mutex_lock(&i40e_device_mutex);
 	list_for_each_entry(ldev, &i40e_devices, list) {
 		pf = ldev->pf;
+		i40e_client_add_instance(pf);
 		/* Start the client subtask */
 		pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
 		i40e_service_event_schedule(pf);
@@ -785,15 +661,15 @@ static void i40e_client_request_reset(struct i40e_info *ldev,
 
 	switch (reset_level) {
 	case I40E_CLIENT_RESET_LEVEL_PF:
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		break;
 	case I40E_CLIENT_RESET_LEVEL_CORE:
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		break;
 	default:
 		dev_warn(&pf->pdev->dev,
-			 "Client %s instance for PF id %d request an unsupported reset: %d.\n",
-			 client->name, pf->hw.pf_id, reset_level);
+			 "Client for PF id %d requested an unsupported reset: %d.\n",
+			 pf->hw.pf_id, reset_level);
 		break;
 	}
 
@@ -852,8 +728,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 	} else {
 		update = false;
 		dev_warn(&pf->pdev->dev,
-			 "Client %s instance for PF id %d request an unsupported Config: %x.\n",
-			 client->name, pf->hw.pf_id, flag);
+			 "Client for PF id %d request an unsupported Config: %x.\n",
+			 pf->hw.pf_id, flag);
 	}
 
 	if (update) {
@@ -878,7 +754,6 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 int i40e_register_client(struct i40e_client *client)
 {
 	int ret = 0;
-	enum i40e_vsi_type vsi_type;
 
 	if (!client) {
 		ret = -EIO;
@@ -891,11 +766,9 @@ int i40e_register_client(struct i40e_client *client)
 		goto out;
 	}
 
-	mutex_lock(&i40e_client_mutex);
-	if (i40e_client_is_registered(client)) {
+	if (registered_client) {
 		pr_info("i40e: Client %s has already been registered!\n",
 			client->name);
-		mutex_unlock(&i40e_client_mutex);
 		ret = -EEXIST;
 		goto out;
 	}
@@ -908,22 +781,11 @@ int i40e_register_client(struct i40e_client *client)
 			client->version.major, client->version.minor,
 			client->version.build,
 			i40e_client_interface_version_str);
-		mutex_unlock(&i40e_client_mutex);
 		ret = -EIO;
 		goto out;
 	}
 
-	vsi_type = i40e_client_type_to_vsi_type(client->type);
-	if (vsi_type == I40E_VSI_TYPE_UNKNOWN) {
-		pr_info("i40e: Failed to register client %s due to unknown client type %d\n",
-			client->name, client->type);
-		mutex_unlock(&i40e_client_mutex);
-		ret = -EIO;
-		goto out;
-	}
-	list_add(&client->list, &i40e_clients);
-	set_bit(__I40E_CLIENT_REGISTERED, &client->state);
-	mutex_unlock(&i40e_client_mutex);
+	registered_client = client;
 
 	i40e_client_prepare(client);
 
@@ -943,29 +805,21 @@ int i40e_unregister_client(struct i40e_client *client)
 {
 	int ret = 0;
 
-	/* When a unregister request comes through we would have to send
-	 * a close for each of the client instances that were opened.
-	 * client_release function is called to handle this.
-	 */
-	mutex_lock(&i40e_client_mutex);
-	if (!client || i40e_client_release(client)) {
-		ret = -EIO;
-		goto out;
-	}
-
-	/* TODO: check if device is in reset, or if that matters? */
-	if (!i40e_client_is_registered(client)) {
+	if (registered_client != client) {
 		pr_info("i40e: Client %s has not been registered\n",
 			client->name);
 		ret = -ENODEV;
 		goto out;
 	}
-	clear_bit(__I40E_CLIENT_REGISTERED, &client->state);
-	list_del(&client->list);
-	pr_info("i40e: Unregistered client %s with return code %d\n",
-		client->name, ret);
+	registered_client = NULL;
+	/* When a unregister request comes through we would have to send
+	 * a close for each of the client instances that were opened.
+	 * client_release function is called to handle this.
+	 */
+	i40e_client_release(client);
+
+	pr_info("i40e: Unregistered client %s\n", client->name);
 out:
-	mutex_unlock(&i40e_client_mutex);
 	return ret;
 }
 EXPORT_SYMBOL(i40e_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h
index 528bd79b05fe..15b21a5315b5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.h
@@ -57,11 +57,6 @@ enum i40e_client_instance_state {
 	__I40E_CLIENT_INSTANCE_OPENED,
 };
 
-enum i40e_client_type {
-	I40E_CLIENT_IWARP,
-	I40E_CLIENT_VMDQ2
-};
-
 struct i40e_ops;
 struct i40e_client;
 
@@ -214,7 +209,8 @@ struct i40e_client {
 	u32 flags;
 #define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
 #define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
-	enum i40e_client_type type;
+	u8 type;
+#define I40E_CLIENT_IWARP 0
 	const struct i40e_client_ops *ops; /* client ops provided by the client */
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index ece57d6a6e23..24f020655291 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1088,33 +1088,6 @@ void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable)
 
 	wr32(hw, I40E_GLLAN_TXPRE_QDIS(reg_block), reg_val);
 }
-#ifdef I40E_FCOE
-
-/**
- * i40e_get_san_mac_addr - get SAN MAC address
- * @hw: pointer to the HW structure
- * @mac_addr: pointer to SAN MAC address
- *
- * Reads the adapter's SAN MAC address from NVM
- **/
-i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr)
-{
-	struct i40e_aqc_mac_address_read_data addrs;
-	i40e_status status;
-	u16 flags = 0;
-
-	status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL);
-	if (status)
-		return status;
-
-	if (flags & I40E_AQC_SAN_ADDR_VALID)
-		ether_addr_copy(mac_addr, addrs.pf_san_mac);
-	else
-		status = I40E_ERR_INVALID_MAC_ADDR;
-
-	return status;
-}
-#endif
 
 /**
  *  i40e_read_pba_string - Reads part number string from EEPROM
@@ -4990,7 +4963,9 @@ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 	int retry = 5;
 	u32 val = 0;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
@@ -5049,7 +5024,9 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 	bool use_register;
 	int retry = 5;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
@@ -5065,3 +5042,215 @@ do_retry:
 	if (status || use_register)
 		wr32(hw, reg_addr, reg_val);
 }
+
+/**
+ * i40e_aq_write_ppp - Write pipeline personalization profile (ppp)
+ * @hw: pointer to the hw struct
+ * @buff: command buffer (size in bytes = buff_size)
+ * @buff_size: buffer size in bytes
+ * @track_id: package tracking id
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+enum
+i40e_status_code i40e_aq_write_ppp(struct i40e_hw *hw, void *buff,
+				   u16 buff_size, u32 track_id,
+				   u32 *error_offset, u32 *error_info,
+				   struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_write_personalization_profile *cmd =
+		(struct i40e_aqc_write_personalization_profile *)
+		&desc.params.raw;
+	struct i40e_aqc_write_ppp_resp *resp;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_write_personalization_profile);
+
+	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
+	if (buff_size > I40E_AQ_LARGE_BUF)
+		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+	desc.datalen = cpu_to_le16(buff_size);
+
+	cmd->profile_track_id = cpu_to_le32(track_id);
+
+	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+	if (!status) {
+		resp = (struct i40e_aqc_write_ppp_resp *)&desc.params.raw;
+		if (error_offset)
+			*error_offset = le32_to_cpu(resp->error_offset);
+		if (error_info)
+			*error_info = le32_to_cpu(resp->error_info);
+	}
+
+	return status;
+}
+
+/**
+ * i40e_aq_get_ppp_list - Read pipeline personalization profile (ppp)
+ * @hw: pointer to the hw struct
+ * @buff: command buffer (size in bytes = buff_size)
+ * @buff_size: buffer size in bytes
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+enum
+i40e_status_code i40e_aq_get_ppp_list(struct i40e_hw *hw, void *buff,
+				      u16 buff_size, u8 flags,
+				      struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_get_applied_profiles *cmd =
+		(struct i40e_aqc_get_applied_profiles *)&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_get_personalization_profile_list);
+
+	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	if (buff_size > I40E_AQ_LARGE_BUF)
+		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+	desc.datalen = cpu_to_le16(buff_size);
+
+	cmd->flags = flags;
+
+	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+
+	return status;
+}
+
+/**
+ * i40e_find_segment_in_package
+ * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E)
+ * @pkg_hdr: pointer to the package header to be searched
+ *
+ * This function searches a package file for a particular segment type. On
+ * success it returns a pointer to the segment header, otherwise it will
+ * return NULL.
+ **/
+struct i40e_generic_seg_header *
+i40e_find_segment_in_package(u32 segment_type,
+			     struct i40e_package_header *pkg_hdr)
+{
+	struct i40e_generic_seg_header *segment;
+	u32 i;
+
+	/* Search all package segments for the requested segment type */
+	for (i = 0; i < pkg_hdr->segment_count; i++) {
+		segment =
+			(struct i40e_generic_seg_header *)((u8 *)pkg_hdr +
+			 pkg_hdr->segment_offset[i]);
+
+		if (segment->type == segment_type)
+			return segment;
+	}
+
+	return NULL;
+}
+
+/**
+ * i40e_write_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be downloaded
+ * @track_id: package tracking id
+ *
+ * Handles the download of a complete package.
+ */
+enum i40e_status_code
+i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+		   u32 track_id)
+{
+	i40e_status status = 0;
+	struct i40e_section_table *sec_tbl;
+	struct i40e_profile_section_header *sec = NULL;
+	u32 dev_cnt;
+	u32 vendor_dev_id;
+	u32 *nvm;
+	u32 section_size = 0;
+	u32 offset = 0, info = 0;
+	u32 i;
+
+	if (!track_id) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Track_id can't be 0.");
+		return I40E_NOT_SUPPORTED;
+	}
+
+	dev_cnt = profile->device_table_count;
+
+	for (i = 0; i < dev_cnt; i++) {
+		vendor_dev_id = profile->device_table[i].vendor_dev_id;
+		if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL)
+			if (hw->device_id == (vendor_dev_id & 0xFFFF))
+				break;
+	}
+	if (i == dev_cnt) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support PPP");
+		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+	}
+
+	nvm = (u32 *)&profile->device_table[dev_cnt];
+	sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1];
+
+	for (i = 0; i < sec_tbl->section_count; i++) {
+		sec = (struct i40e_profile_section_header *)((u8 *)profile +
+					     sec_tbl->section_offset[i]);
+
+		/* Skip 'AQ', 'note' and 'name' sections */
+		if (sec->section.type != SECTION_TYPE_MMIO)
+			continue;
+
+		section_size = sec->section.size +
+			sizeof(struct i40e_profile_section_header);
+
+		/* Write profile */
+		status = i40e_aq_write_ppp(hw, (void *)sec, (u16)section_size,
+					   track_id, &offset, &info, NULL);
+		if (status) {
+			i40e_debug(hw, I40E_DEBUG_PACKAGE,
+				   "Failed to write profile: offset %d, info %d",
+				   offset, info);
+			break;
+		}
+	}
+	return status;
+}
+
+/**
+ * i40e_add_pinfo_to_list
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package
+ * @profile_info_sec: buffer for information section
+ * @track_id: package tracking id
+ *
+ * Register a profile to the list of loaded profiles.
+ */
+enum i40e_status_code
+i40e_add_pinfo_to_list(struct i40e_hw *hw,
+		       struct i40e_profile_segment *profile,
+		       u8 *profile_info_sec, u32 track_id)
+{
+	i40e_status status = 0;
+	struct i40e_profile_section_header *sec = NULL;
+	struct i40e_profile_info *pinfo;
+	u32 offset = 0, info = 0;
+
+	sec = (struct i40e_profile_section_header *)profile_info_sec;
+	sec->tbl_size = 1;
+	sec->data_end = sizeof(struct i40e_profile_section_header) +
+			sizeof(struct i40e_profile_info);
+	sec->section.type = SECTION_TYPE_INFO;
+	sec->section.offset = sizeof(struct i40e_profile_section_header);
+	sec->section.size = sizeof(struct i40e_profile_info);
+	pinfo = (struct i40e_profile_info *)(profile_info_sec +
+					     sec->section.offset);
+	pinfo->track_id = track_id;
+	pinfo->version = profile->version;
+	pinfo->op = I40E_PPP_ADD_TRACKID;
+	memcpy(pinfo->name, profile->name, I40E_PPP_NAME_SIZE);
+
+	status = i40e_aq_write_ppp(hw, (void *)sec, sec->data_end,
+				   track_id, &offset, &info, NULL);
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 267ad2588255..8f326f87a815 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -158,9 +158,12 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 	dev_info(&pf->pdev->dev,
 		 "    vlgrp: & = %p\n", vsi->active_vlans);
 	dev_info(&pf->pdev->dev,
-		 "    state = %li flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n",
-		 vsi->state, vsi->flags,
-		 vsi->netdev_registered, vsi->current_netdev_flags);
+		 "    flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n",
+		 vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags);
+	for (i = 0; i < BITS_TO_LONGS(__I40E_VSI_STATE_SIZE__); i++)
+		dev_info(&pf->pdev->dev,
+			 "    state[%d] = %08lx\n",
+			 i, vsi->state[i]);
 	if (vsi == pf->vsi[pf->lan_vsi])
 		dev_info(&pf->pdev->dev, "    MAC address: %pM SAN MAC: %pM Port MAC: %pM\n",
 			 pf->hw.mac.addr,
@@ -174,7 +177,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 	}
 	dev_info(&pf->pdev->dev, "    active_filters %u, promisc_threshold %u, overflow promisc %s\n",
 		 vsi->active_filters, vsi->promisc_threshold,
-		 (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) ?
+		 (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) ?
 		  "ON" : "OFF"));
 	nstat = i40e_get_vsi_stats_struct(vsi);
 	dev_info(&pf->pdev->dev,
@@ -384,6 +387,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 		 "    base_queue = %d, num_queue_pairs = %d, num_desc = %d\n",
 		 vsi->base_queue, vsi->num_queue_pairs, vsi->num_desc);
 	dev_info(&pf->pdev->dev, "    type = %i\n", vsi->type);
+	if (vsi->type == I40E_VSI_SRIOV)
+		dev_info(&pf->pdev->dev, "    VF ID = %i\n", vsi->vf_id);
 	dev_info(&pf->pdev->dev,
 		 "    info: valid_sections = 0x%04x, switch_id = 0x%04x\n",
 		 vsi->info.valid_sections, vsi->info.switch_id);
@@ -484,25 +489,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 vsi->bw_ets_limit_credits[i],
 			 vsi->bw_ets_max_quanta[i]);
 	}
-#ifdef I40E_FCOE
-	if (vsi->type == I40E_VSI_FCOE) {
-		dev_info(&pf->pdev->dev,
-			 "    fcoe_stats: rx_packets = %llu, rx_dwords = %llu, rx_dropped = %llu\n",
-			 vsi->fcoe_stats.rx_fcoe_packets,
-			 vsi->fcoe_stats.rx_fcoe_dwords,
-			 vsi->fcoe_stats.rx_fcoe_dropped);
-		dev_info(&pf->pdev->dev,
-			 "    fcoe_stats: tx_packets = %llu, tx_dwords = %llu\n",
-			 vsi->fcoe_stats.tx_fcoe_packets,
-			 vsi->fcoe_stats.tx_fcoe_dwords);
-		dev_info(&pf->pdev->dev,
-			 "    fcoe_stats: bad_crc = %llu, last_error = %llu\n",
-			 vsi->fcoe_stats.fcoe_bad_fccrc,
-			 vsi->fcoe_stats.fcoe_last_error);
-		dev_info(&pf->pdev->dev, "    fcoe_stats: ddp_count = %llu\n",
-			 vsi->fcoe_stats.fcoe_ddp_count);
-	}
-#endif
 }
 
 /**
@@ -713,6 +699,47 @@ static void i40e_dbg_dump_veb_all(struct i40e_pf *pf)
 	}
 }
 
+/**
+ * i40e_dbg_dump_vf - dump VF info
+ * @pf: the i40e_pf created in command write
+ * @vf_id: the vf_id from the user
+ **/
+static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id)
+{
+	struct i40e_vf *vf;
+	struct i40e_vsi *vsi;
+
+	if (!pf->num_alloc_vfs) {
+		dev_info(&pf->pdev->dev, "no VFs allocated\n");
+	} else if ((vf_id >= 0) && (vf_id < pf->num_alloc_vfs)) {
+		vf = &pf->vf[vf_id];
+		vsi = pf->vsi[vf->lan_vsi_idx];
+		dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n",
+			 vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs);
+		dev_info(&pf->pdev->dev, "       num MDD=%lld, invalid msg=%lld, valid msg=%lld\n",
+			 vf->num_mdd_events,
+			 vf->num_invalid_msgs,
+			 vf->num_valid_msgs);
+	} else {
+		dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id);
+	}
+}
+
+/**
+ * i40e_dbg_dump_vf_all - dump VF info for all VFs
+ * @pf: the i40e_pf created in command write
+ **/
+static void i40e_dbg_dump_vf_all(struct i40e_pf *pf)
+{
+	int i;
+
+	if (!pf->num_alloc_vfs)
+		dev_info(&pf->pdev->dev, "no VFs enabled!\n");
+	else
+		for (i = 0; i < pf->num_alloc_vfs; i++)
+			i40e_dbg_dump_vf(pf, i);
+}
+
 #define I40E_MAX_DEBUG_OUT_BUFFER (4096*4)
 /**
  * i40e_dbg_command_write - write into command datum
@@ -731,6 +758,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 	struct i40e_vsi *vsi;
 	int vsi_seid;
 	int veb_seid;
+	int vf_id;
 	int cnt;
 
 	/* don't allow partial writes */
@@ -933,6 +961,12 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 				i40e_dbg_dump_veb_seid(pf, vsi_seid);
 			else
 				i40e_dbg_dump_veb_all(pf);
+		} else if (strncmp(&cmd_buf[5], "vf", 2) == 0) {
+			cnt = sscanf(&cmd_buf[7], "%i", &vf_id);
+			if (cnt > 0)
+				i40e_dbg_dump_vf(pf, vf_id);
+			else
+				i40e_dbg_dump_vf_all(pf);
 		} else if (strncmp(&cmd_buf[5], "desc", 4) == 0) {
 			int ring_id, desc_n;
 			if (strncmp(&cmd_buf[10], "rx", 2) == 0) {
@@ -1128,6 +1162,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "dump vsi [seid]\n");
 			dev_info(&pf->pdev->dev, "dump reset stats\n");
 			dev_info(&pf->pdev->dev, "dump port\n");
+			dev_info(&pf->pdev->dev, "dump vf [vf_id]\n");
 			dev_info(&pf->pdev->dev,
 				 "dump debug fwdata <cluster_id> <table_id> <index>\n");
 		}
@@ -1674,7 +1709,7 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 		} else if (!vsi->netdev) {
 			dev_info(&pf->pdev->dev, "tx_timeout: no netdev for VSI %d\n",
 				 vsi_seid);
-		} else if (test_bit(__I40E_DOWN, &vsi->state)) {
+		} else if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
 			dev_info(&pf->pdev->dev, "tx_timeout: VSI %d not UP\n",
 				 vsi_seid);
 		} else if (rtnl_trylock()) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index a22e26200bcc..7a8eb486b9ea 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -89,7 +89,6 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = {
 	I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
 	I40E_VSI_STAT("tx_linearize", tx_linearize),
 	I40E_VSI_STAT("tx_force_wb", tx_force_wb),
-	I40E_VSI_STAT("tx_lost_interrupt", tx_lost_interrupt),
 	I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed),
 	I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
 };
@@ -162,19 +161,6 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_lpi_count", stats.rx_lpi_count),
 };
 
-#ifdef I40E_FCOE
-static const struct i40e_stats i40e_gstrings_fcoe_stats[] = {
-	I40E_VSI_STAT("fcoe_bad_fccrc", fcoe_stats.fcoe_bad_fccrc),
-	I40E_VSI_STAT("rx_fcoe_dropped", fcoe_stats.rx_fcoe_dropped),
-	I40E_VSI_STAT("rx_fcoe_packets", fcoe_stats.rx_fcoe_packets),
-	I40E_VSI_STAT("rx_fcoe_dwords", fcoe_stats.rx_fcoe_dwords),
-	I40E_VSI_STAT("fcoe_ddp_count", fcoe_stats.fcoe_ddp_count),
-	I40E_VSI_STAT("fcoe_last_error", fcoe_stats.fcoe_last_error),
-	I40E_VSI_STAT("tx_fcoe_packets", fcoe_stats.tx_fcoe_packets),
-	I40E_VSI_STAT("tx_fcoe_dwords", fcoe_stats.tx_fcoe_dwords),
-};
-
-#endif /* I40E_FCOE */
 #define I40E_QUEUE_STATS_LEN(n) \
 	(((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs \
 	    * 2 /* Tx and Rx together */                                     \
@@ -182,17 +168,9 @@ static const struct i40e_stats i40e_gstrings_fcoe_stats[] = {
 #define I40E_GLOBAL_STATS_LEN	ARRAY_SIZE(i40e_gstrings_stats)
 #define I40E_NETDEV_STATS_LEN   ARRAY_SIZE(i40e_gstrings_net_stats)
 #define I40E_MISC_STATS_LEN	ARRAY_SIZE(i40e_gstrings_misc_stats)
-#ifdef I40E_FCOE
-#define I40E_FCOE_STATS_LEN	ARRAY_SIZE(i40e_gstrings_fcoe_stats)
-#define I40E_VSI_STATS_LEN(n)	(I40E_NETDEV_STATS_LEN + \
-				 I40E_FCOE_STATS_LEN + \
-				 I40E_MISC_STATS_LEN + \
-				 I40E_QUEUE_STATS_LEN((n)))
-#else
 #define I40E_VSI_STATS_LEN(n)   (I40E_NETDEV_STATS_LEN + \
 				 I40E_MISC_STATS_LEN + \
 				 I40E_QUEUE_STATS_LEN((n)))
-#endif /* I40E_FCOE */
 #define I40E_PFC_STATS_LEN ( \
 		(FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
 		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \
@@ -228,22 +206,37 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN)
 
-static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = {
-	"MFP",
-	"LinkPolling",
-	"flow-director-atr",
-	"veb-stats",
-	"hw-atr-eviction",
+struct i40e_priv_flags {
+	char flag_string[ETH_GSTRING_LEN];
+	u64 flag;
+	bool read_only;
 };
 
-#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings)
+#define I40E_PRIV_FLAG(_name, _flag, _read_only) { \
+	.flag_string = _name, \
+	.flag = _flag, \
+	.read_only = _read_only, \
+}
+
+static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
+	/* NOTE: MFP setting cannot be changed */
+	I40E_PRIV_FLAG("MFP", I40E_FLAG_MFP_ENABLED, 1),
+	I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENABLED, 0),
+	I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0),
+	I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0),
+	I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_CAPABLE, 0),
+	I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0),
+};
+
+#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
 
 /* Private flags with a global effect, restricted to PF 0 */
-static const char i40e_gl_priv_flags_strings[][ETH_GSTRING_LEN] = {
-	"vf-true-promisc-support",
+static const struct i40e_priv_flags i40e_gl_gstrings_priv_flags[] = {
+	I40E_PRIV_FLAG("vf-true-promisc-support",
+		       I40E_FLAG_TRUE_PROMISC_SUPPORT, 0),
 };
 
-#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_priv_flags_strings)
+#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_gstrings_priv_flags)
 
 /**
  * i40e_partition_setting_complaint - generic complaint for MFP restriction
@@ -387,7 +380,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
  *
  **/
 static void i40e_get_settings_link_up(struct i40e_hw *hw,
-				      struct ethtool_cmd *ecmd,
+				      struct ethtool_link_ksettings *cmd,
 				      struct net_device *netdev,
 				      struct i40e_pf *pf)
 {
@@ -395,90 +388,96 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	u32 link_speed = hw_link_info->link_speed;
 	u32 e_advertising = 0x0;
 	u32 e_supported = 0x0;
+	u32 supported, advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	/* Initialize supported and advertised settings based on phy settings */
 	switch (hw_link_info->phy_type) {
 	case I40E_PHY_TYPE_40GBASE_CR4:
 	case I40E_PHY_TYPE_40GBASE_CR4_CU:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_40000baseCR4_Full;
-		ecmd->advertising = ADVERTISED_Autoneg |
-				    ADVERTISED_40000baseCR4_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_40000baseCR4_Full;
+		advertising = ADVERTISED_Autoneg |
+			      ADVERTISED_40000baseCR4_Full;
 		break;
 	case I40E_PHY_TYPE_XLAUI:
 	case I40E_PHY_TYPE_XLPPI:
 	case I40E_PHY_TYPE_40GBASE_AOC:
-		ecmd->supported = SUPPORTED_40000baseCR4_Full;
+		supported = SUPPORTED_40000baseCR4_Full;
 		break;
 	case I40E_PHY_TYPE_40GBASE_SR4:
-		ecmd->supported = SUPPORTED_40000baseSR4_Full;
+		supported = SUPPORTED_40000baseSR4_Full;
 		break;
 	case I40E_PHY_TYPE_40GBASE_LR4:
-		ecmd->supported = SUPPORTED_40000baseLR4_Full;
+		supported = SUPPORTED_40000baseLR4_Full;
 		break;
 	case I40E_PHY_TYPE_10GBASE_SR:
 	case I40E_PHY_TYPE_10GBASE_LR:
 	case I40E_PHY_TYPE_1000BASE_SX:
 	case I40E_PHY_TYPE_1000BASE_LX:
-		ecmd->supported = SUPPORTED_10000baseT_Full;
+		supported = SUPPORTED_10000baseT_Full;
 		if (hw_link_info->module_type[2] &
 		    I40E_MODULE_TYPE_1000BASE_SX ||
 		    hw_link_info->module_type[2] &
 		    I40E_MODULE_TYPE_1000BASE_LX) {
-			ecmd->supported |= SUPPORTED_1000baseT_Full;
+			supported |= SUPPORTED_1000baseT_Full;
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_1GB)
-				ecmd->advertising |= ADVERTISED_1000baseT_Full;
+				advertising |= ADVERTISED_1000baseT_Full;
 		}
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			ecmd->advertising |= ADVERTISED_10000baseT_Full;
+			advertising |= ADVERTISED_10000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_10GBASE_T:
 	case I40E_PHY_TYPE_1000BASE_T:
 	case I40E_PHY_TYPE_100BASE_TX:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_10000baseT_Full |
-				  SUPPORTED_1000baseT_Full |
-				  SUPPORTED_100baseT_Full;
-		ecmd->advertising = ADVERTISED_Autoneg;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_10000baseT_Full |
+			    SUPPORTED_1000baseT_Full |
+			    SUPPORTED_100baseT_Full;
+		advertising = ADVERTISED_Autoneg;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			ecmd->advertising |= ADVERTISED_10000baseT_Full;
+			advertising |= ADVERTISED_10000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			ecmd->advertising |= ADVERTISED_1000baseT_Full;
+			advertising |= ADVERTISED_1000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
-			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 		break;
 	case I40E_PHY_TYPE_1000BASE_T_OPTICAL:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_1000baseT_Full;
-		ecmd->advertising = ADVERTISED_Autoneg |
-				    ADVERTISED_1000baseT_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_1000baseT_Full;
+		advertising = ADVERTISED_Autoneg |
+			      ADVERTISED_1000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_10GBASE_CR1_CU:
 	case I40E_PHY_TYPE_10GBASE_CR1:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_10000baseT_Full;
-		ecmd->advertising = ADVERTISED_Autoneg |
-				    ADVERTISED_10000baseT_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_10000baseT_Full;
+		advertising = ADVERTISED_Autoneg |
+			      ADVERTISED_10000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_XAUI:
 	case I40E_PHY_TYPE_XFI:
 	case I40E_PHY_TYPE_SFI:
 	case I40E_PHY_TYPE_10GBASE_SFPP_CU:
 	case I40E_PHY_TYPE_10GBASE_AOC:
-		ecmd->supported = SUPPORTED_10000baseT_Full;
-		ecmd->advertising = SUPPORTED_10000baseT_Full;
+		supported = SUPPORTED_10000baseT_Full;
+		advertising = SUPPORTED_10000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_SGMII:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_1000baseT_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_1000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			ecmd->advertising |= ADVERTISED_1000baseT_Full;
+			advertising |= ADVERTISED_1000baseT_Full;
 		if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
-			ecmd->supported |= SUPPORTED_100baseT_Full;
+			supported |= SUPPORTED_100baseT_Full;
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_100MB)
-				ecmd->advertising |= ADVERTISED_100baseT_Full;
+				advertising |= ADVERTISED_100baseT_Full;
 		}
 		break;
 	case I40E_PHY_TYPE_40GBASE_KR4:
@@ -486,25 +485,25 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	case I40E_PHY_TYPE_10GBASE_KR:
 	case I40E_PHY_TYPE_10GBASE_KX4:
 	case I40E_PHY_TYPE_1000BASE_KX:
-		ecmd->supported |= SUPPORTED_40000baseKR4_Full |
-				   SUPPORTED_20000baseKR2_Full |
-				   SUPPORTED_10000baseKR_Full |
-				   SUPPORTED_10000baseKX4_Full |
-				   SUPPORTED_1000baseKX_Full |
-				   SUPPORTED_Autoneg;
-		ecmd->advertising |= ADVERTISED_40000baseKR4_Full |
-				     ADVERTISED_20000baseKR2_Full |
-				     ADVERTISED_10000baseKR_Full |
-				     ADVERTISED_10000baseKX4_Full |
-				     ADVERTISED_1000baseKX_Full |
-				     ADVERTISED_Autoneg;
+		supported |= SUPPORTED_40000baseKR4_Full |
+			     SUPPORTED_20000baseKR2_Full |
+			     SUPPORTED_10000baseKR_Full |
+			     SUPPORTED_10000baseKX4_Full |
+			     SUPPORTED_1000baseKX_Full |
+			     SUPPORTED_Autoneg;
+		advertising |= ADVERTISED_40000baseKR4_Full |
+			       ADVERTISED_20000baseKR2_Full |
+			       ADVERTISED_10000baseKR_Full |
+			       ADVERTISED_10000baseKX4_Full |
+			       ADVERTISED_1000baseKX_Full |
+			       ADVERTISED_Autoneg;
 		break;
 	case I40E_PHY_TYPE_25GBASE_KR:
 	case I40E_PHY_TYPE_25GBASE_CR:
 	case I40E_PHY_TYPE_25GBASE_SR:
 	case I40E_PHY_TYPE_25GBASE_LR:
-		ecmd->supported = SUPPORTED_Autoneg;
-		ecmd->advertising = ADVERTISED_Autoneg;
+		supported = SUPPORTED_Autoneg;
+		advertising = ADVERTISED_Autoneg;
 		/* TODO: add speeds when ethtool is ready to support*/
 		break;
 	default:
@@ -520,38 +519,43 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	i40e_phy_type_to_ethtool(pf, &e_supported,
 				 &e_advertising);
 
-	ecmd->supported = ecmd->supported & e_supported;
-	ecmd->advertising = ecmd->advertising & e_advertising;
+	supported = supported & e_supported;
+	advertising = advertising & e_advertising;
 
 	/* Set speed and duplex */
 	switch (link_speed) {
 	case I40E_LINK_SPEED_40GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_40000);
+		cmd->base.speed = SPEED_40000;
 		break;
 	case I40E_LINK_SPEED_25GB:
 #ifdef SPEED_25000
-		ethtool_cmd_speed_set(ecmd, SPEED_25000);
+		cmd->base.speed = SPEED_25000;
 #else
 		netdev_info(netdev,
 			    "Speed is 25G, display not supported by this version of ethtool.\n");
 #endif
 		break;
 	case I40E_LINK_SPEED_20GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_20000);
+		cmd->base.speed = SPEED_20000;
 		break;
 	case I40E_LINK_SPEED_10GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_10000);
+		cmd->base.speed = SPEED_10000;
 		break;
 	case I40E_LINK_SPEED_1GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 		break;
 	case I40E_LINK_SPEED_100MB:
-		ethtool_cmd_speed_set(ecmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 		break;
 	default:
 		break;
 	}
-	ecmd->duplex = DUPLEX_FULL;
+	cmd->base.duplex = DUPLEX_FULL;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 }
 
 /**
@@ -562,18 +566,24 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
  * Reports link settings that can be determined when link is down
  **/
 static void i40e_get_settings_link_down(struct i40e_hw *hw,
-					struct ethtool_cmd *ecmd,
+					struct ethtool_link_ksettings *cmd,
 					struct i40e_pf *pf)
 {
+	u32 supported, advertising;
+
 	/* link is down and the driver needs to fall back on
 	 * supported phy types to figure out what info to display
 	 */
-	i40e_phy_type_to_ethtool(pf, &ecmd->supported,
-				 &ecmd->advertising);
+	i40e_phy_type_to_ethtool(pf, &supported, &advertising);
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	/* With no link speed and duplex are unknown */
-	ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-	ecmd->duplex = DUPLEX_UNKNOWN;
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
 }
 
 /**
@@ -583,74 +593,85 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw,
  *
  * Reports speed/duplex settings based on media_type
  **/
-static int i40e_get_settings(struct net_device *netdev,
-			     struct ethtool_cmd *ecmd)
+static int i40e_get_link_ksettings(struct net_device *netdev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_link_status *hw_link_info = &hw->phy.link_info;
 	bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP;
+	u32 advertising;
 
 	if (link_up)
-		i40e_get_settings_link_up(hw, ecmd, netdev, pf);
+		i40e_get_settings_link_up(hw, cmd, netdev, pf);
 	else
-		i40e_get_settings_link_down(hw, ecmd, pf);
+		i40e_get_settings_link_down(hw, cmd, pf);
 
 	/* Now set the settings that don't rely on link being up/down */
 	/* Set autoneg settings */
-	ecmd->autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
+	cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
 			  AUTONEG_ENABLE : AUTONEG_DISABLE);
 
 	switch (hw->phy.media_type) {
 	case I40E_MEDIA_TYPE_BACKPLANE:
-		ecmd->supported |= SUPPORTED_Autoneg |
-				   SUPPORTED_Backplane;
-		ecmd->advertising |= ADVERTISED_Autoneg |
-				     ADVERTISED_Backplane;
-		ecmd->port = PORT_NONE;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     Backplane);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Backplane);
+		cmd->base.port = PORT_NONE;
 		break;
 	case I40E_MEDIA_TYPE_BASET:
-		ecmd->supported |= SUPPORTED_TP;
-		ecmd->advertising |= ADVERTISED_TP;
-		ecmd->port = PORT_TP;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+		cmd->base.port = PORT_TP;
 		break;
 	case I40E_MEDIA_TYPE_DA:
 	case I40E_MEDIA_TYPE_CX4:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_DA;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+		cmd->base.port = PORT_DA;
 		break;
 	case I40E_MEDIA_TYPE_FIBER:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->port = PORT_FIBRE;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+		cmd->base.port = PORT_FIBRE;
 		break;
 	case I40E_MEDIA_TYPE_UNKNOWN:
 	default:
-		ecmd->port = PORT_OTHER;
+		cmd->base.port = PORT_OTHER;
 		break;
 	}
 
-	/* Set transceiver */
-	ecmd->transceiver = XCVR_EXTERNAL;
-
 	/* Set flow control settings */
-	ecmd->supported |= SUPPORTED_Pause;
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
 
 	switch (hw->fc.requested_mode) {
 	case I40E_FC_FULL:
-		ecmd->advertising |= ADVERTISED_Pause;
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Pause);
 		break;
 	case I40E_FC_TX_PAUSE:
-		ecmd->advertising |= ADVERTISED_Asym_Pause;
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
 		break;
 	case I40E_FC_RX_PAUSE:
-		ecmd->advertising |= (ADVERTISED_Pause |
-				      ADVERTISED_Asym_Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
 		break;
 	default:
-		ecmd->advertising &= ~(ADVERTISED_Pause |
-				       ADVERTISED_Asym_Pause);
+		ethtool_convert_link_mode_to_legacy_u32(
+			&advertising, cmd->link_modes.advertising);
+
+		advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+
+		ethtool_convert_legacy_u32_to_link_mode(
+			cmd->link_modes.advertising, advertising);
 		break;
 	}
 
@@ -664,8 +685,8 @@ static int i40e_get_settings(struct net_device *netdev,
  *
  * Set speed/duplex per media_types advertised/forced
  **/
-static int i40e_set_settings(struct net_device *netdev,
-			     struct ethtool_cmd *ecmd)
+static int i40e_set_link_ksettings(struct net_device *netdev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_aq_get_phy_abilities_resp abilities;
@@ -673,12 +694,15 @@ static int i40e_set_settings(struct net_device *netdev,
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_hw *hw = &pf->hw;
-	struct ethtool_cmd safe_ecmd;
+	struct ethtool_link_ksettings safe_cmd;
+	struct ethtool_link_ksettings copy_cmd;
 	i40e_status status = 0;
 	bool change = false;
+	int timeout = 50;
 	int err = 0;
-	u8 autoneg;
+	u32 autoneg;
 	u32 advertise;
+	u32 tmp;
 
 	/* Changing port settings is not supported if this isn't the
 	 * port's controlling PF
@@ -706,33 +730,47 @@ static int i40e_set_settings(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
+	/* copy the cmd to copy_cmd to avoid modifying the origin */
+	memcpy(&copy_cmd, cmd, sizeof(struct ethtool_link_ksettings));
+
 	/* get our own copy of the bits to check against */
-	memset(&safe_ecmd, 0, sizeof(struct ethtool_cmd));
-	i40e_get_settings(netdev, &safe_ecmd);
+	memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings));
+	i40e_get_link_ksettings(netdev, &safe_cmd);
 
-	/* save autoneg and speed out of ecmd */
-	autoneg = ecmd->autoneg;
-	advertise = ecmd->advertising;
+	/* save autoneg and speed out of cmd */
+	autoneg = cmd->base.autoneg;
+	ethtool_convert_link_mode_to_legacy_u32(&advertise,
+						cmd->link_modes.advertising);
 
 	/* set autoneg and speed back to what they currently are */
-	ecmd->autoneg = safe_ecmd.autoneg;
-	ecmd->advertising = safe_ecmd.advertising;
+	copy_cmd.base.autoneg = safe_cmd.base.autoneg;
+	ethtool_convert_link_mode_to_legacy_u32(
+		&tmp, safe_cmd.link_modes.advertising);
+	ethtool_convert_legacy_u32_to_link_mode(
+		copy_cmd.link_modes.advertising, tmp);
+
+	copy_cmd.base.cmd = safe_cmd.base.cmd;
 
-	ecmd->cmd = safe_ecmd.cmd;
-	/* If ecmd and safe_ecmd are not the same now, then they are
+	/* If copy_cmd and safe_cmd are not the same now, then they are
 	 * trying to set something that we do not support
 	 */
-	if (memcmp(ecmd, &safe_ecmd, sizeof(struct ethtool_cmd)))
+	if (memcmp(&copy_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings)))
 		return -EOPNOTSUPP;
 
-	while (test_bit(__I40E_CONFIG_BUSY, &vsi->state))
+	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
+		timeout--;
+		if (!timeout)
+			return -EBUSY;
 		usleep_range(1000, 2000);
+	}
 
 	/* Get the current phy config */
 	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
 					      NULL);
-	if (status)
-		return -EAGAIN;
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
 
 	/* Copy abilities to config in case autoneg is not
 	 * set below
@@ -745,9 +783,11 @@ static int i40e_set_settings(struct net_device *netdev,
 		/* If autoneg was not already enabled */
 		if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) {
 			/* If autoneg is not supported, return error */
-			if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) {
+			if (!ethtool_link_ksettings_test_link_mode(
+				    &safe_cmd, supported, Autoneg)) {
 				netdev_info(netdev, "Autoneg not supported on this phy\n");
-				return -EINVAL;
+				err = -EINVAL;
+				goto done;
 			}
 			/* Autoneg is allowed to change */
 			config.abilities = abilities.abilities |
@@ -760,11 +800,13 @@ static int i40e_set_settings(struct net_device *netdev,
 			/* If autoneg is supported 10GBASE_T is the only PHY
 			 * that can disable it, so otherwise return error
 			 */
-			if (safe_ecmd.supported & SUPPORTED_Autoneg &&
+			if (ethtool_link_ksettings_test_link_mode(
+				    &safe_cmd, supported, Autoneg) &&
 			    hw->phy.link_info.phy_type !=
 			    I40E_PHY_TYPE_10GBASE_T) {
 				netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
-				return -EINVAL;
+				err = -EINVAL;
+				goto done;
 			}
 			/* Autoneg is allowed to change */
 			config.abilities = abilities.abilities &
@@ -773,8 +815,12 @@ static int i40e_set_settings(struct net_device *netdev,
 		}
 	}
 
-	if (advertise & ~safe_ecmd.supported)
-		return -EINVAL;
+	ethtool_convert_link_mode_to_legacy_u32(&tmp,
+						safe_cmd.link_modes.supported);
+	if (advertise & ~tmp) {
+		err = -EINVAL;
+		goto done;
+	}
 
 	if (advertise & ADVERTISED_100baseT_Full)
 		config.link_speed |= I40E_LINK_SPEED_100MB;
@@ -830,7 +876,8 @@ static int i40e_set_settings(struct net_device *netdev,
 			netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n",
 				    i40e_stat_str(hw, status),
 				    i40e_aq_str(hw, hw->aq.asq_last_status));
-			return -EAGAIN;
+			err = -EAGAIN;
+			goto done;
 		}
 
 		status = i40e_update_link_info(hw);
@@ -843,6 +890,9 @@ static int i40e_set_settings(struct net_device *netdev,
 		netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
 	}
 
+done:
+	clear_bit(__I40E_CONFIG_BUSY, pf->state);
+
 	return err;
 }
 
@@ -937,7 +987,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	}
 
 	/* If we have link and don't have autoneg */
-	if (!test_bit(__I40E_DOWN, &pf->state) &&
+	if (!test_bit(__I40E_DOWN, pf->state) &&
 	    !(hw_link_info->an_info & I40E_AQ_AN_COMPLETED)) {
 		/* Send message that it might not necessarily work*/
 		netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
@@ -989,10 +1039,10 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 		err = -EAGAIN;
 	}
 
-	if (!test_bit(__I40E_DOWN, &pf->state)) {
+	if (!test_bit(__I40E_DOWN, pf->state)) {
 		/* Give it a little more time to try to come back */
 		msleep(75);
-		if (!test_bit(__I40E_DOWN, &pf->state))
+		if (!test_bit(__I40E_DOWN, pf->state))
 			return i40e_nway_reset(netdev);
 	}
 
@@ -1089,8 +1139,8 @@ static int i40e_get_eeprom(struct net_device *netdev,
 		/* make sure it is the right magic for NVMUpdate */
 		if ((eeprom->magic >> 16) != hw->device_id)
 			errno = -EINVAL;
-		else if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
-			 test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
+		else if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+			 test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
 			errno = -EBUSY;
 		else
 			ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
@@ -1165,6 +1215,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev)
 	struct i40e_hw *hw = &np->vsi->back->hw;
 	u32 val;
 
+#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF
+	if (hw->mac.type == I40E_MAC_X722) {
+		val = X722_EEPROM_SCOPE_LIMIT + 1;
+		return val;
+	}
 	val = (rd32(hw, I40E_GLPCI_LBARCTRL)
 		& I40E_GLPCI_LBARCTRL_FL_SIZE_MASK)
 		>> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT;
@@ -1191,8 +1246,8 @@ static int i40e_set_eeprom(struct net_device *netdev,
 	/* check for NVMUpdate access method */
 	else if (!eeprom->magic || (eeprom->magic >> 16) != hw->device_id)
 		errno = -EINVAL;
-	else if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
-		 test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
+	else if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+		 test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
 		errno = -EBUSY;
 	else
 		ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
@@ -1252,6 +1307,7 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	u32 new_rx_count, new_tx_count;
+	int timeout = 50;
 	int i, err = 0;
 
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
@@ -1276,8 +1332,12 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	    (new_rx_count == vsi->rx_rings[0]->count))
 		return 0;
 
-	while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state))
+	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
+		timeout--;
+		if (!timeout)
+			return -EBUSY;
 		usleep_range(1000, 2000);
+	}
 
 	if (!netif_running(vsi->netdev)) {
 		/* simple case - set for the next time the netdev is started */
@@ -1425,7 +1485,7 @@ free_tx:
 	}
 
 done:
-	clear_bit(__I40E_CONFIG_BUSY, &pf->state);
+	clear_bit(__I40E_CONFIG_BUSY, pf->state);
 
 	return err;
 }
@@ -1483,13 +1543,6 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 		data[i++] = (i40e_gstrings_misc_stats[j].sizeof_stat ==
 			    sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
-#ifdef I40E_FCOE
-	for (j = 0; j < I40E_FCOE_STATS_LEN; j++) {
-		p = (char *)vsi + i40e_gstrings_fcoe_stats[j].stat_offset;
-		data[i++] = (i40e_gstrings_fcoe_stats[j].sizeof_stat ==
-			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
-#endif
 	rcu_read_lock();
 	for (j = 0; j < vsi->num_queue_pairs; j++) {
 		tx_ring = ACCESS_ONCE(vsi->tx_rings[j]);
@@ -1577,13 +1630,6 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
 				 i40e_gstrings_misc_stats[i].stat_string);
 			p += ETH_GSTRING_LEN;
 		}
-#ifdef I40E_FCOE
-		for (i = 0; i < I40E_FCOE_STATS_LEN; i++) {
-			snprintf(p, ETH_GSTRING_LEN, "%s",
-				 i40e_gstrings_fcoe_stats[i].stat_string);
-			p += ETH_GSTRING_LEN;
-		}
-#endif
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
 			snprintf(p, ETH_GSTRING_LEN, "tx-%d.tx_packets", i);
 			p += ETH_GSTRING_LEN;
@@ -1648,12 +1694,18 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
 		/* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
 	case ETH_SS_PRIV_FLAGS:
-		memcpy(data, i40e_priv_flags_strings,
-		       I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
-		data += I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN;
-		if (pf->hw.pf_id == 0)
-			memcpy(data, i40e_gl_priv_flags_strings,
-			       I40E_GL_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+		for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40e_gstrings_priv_flags[i].flag_string);
+			p += ETH_GSTRING_LEN;
+		}
+		if (pf->hw.pf_id != 0)
+			break;
+		for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40e_gl_gstrings_priv_flags[i].flag_string);
+			p += ETH_GSTRING_LEN;
+		}
 		break;
 	default:
 		break;
@@ -1774,7 +1826,7 @@ static inline bool i40e_active_vfs(struct i40e_pf *pf)
 	int i;
 
 	for (i = 0; i < pf->num_alloc_vfs; i++)
-		if (test_bit(I40E_VF_STAT_ACTIVE, &vfs[i].vf_states))
+		if (test_bit(I40E_VF_STATE_ACTIVE, &vfs[i].vf_states))
 			return true;
 	return false;
 }
@@ -1795,7 +1847,7 @@ static void i40e_diag_test(struct net_device *netdev,
 		/* Offline tests */
 		netif_info(pf, drv, netdev, "offline testing starting\n");
 
-		set_bit(__I40E_TESTING, &pf->state);
+		set_bit(__I40E_TESTING, pf->state);
 
 		if (i40e_active_vfs(pf) || i40e_active_vmdqs(pf)) {
 			dev_warn(&pf->pdev->dev,
@@ -1805,7 +1857,7 @@ static void i40e_diag_test(struct net_device *netdev,
 			data[I40E_ETH_TEST_INTR]	= 1;
 			data[I40E_ETH_TEST_LINK]	= 1;
 			eth_test->flags |= ETH_TEST_FL_FAILED;
-			clear_bit(__I40E_TESTING, &pf->state);
+			clear_bit(__I40E_TESTING, pf->state);
 			goto skip_ol_tests;
 		}
 
@@ -1819,7 +1871,7 @@ static void i40e_diag_test(struct net_device *netdev,
 			 * link then the following link test would have
 			 * to be moved to before the reset
 			 */
-			i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
+			i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
 
 		if (i40e_link_test(netdev, &data[I40E_ETH_TEST_LINK]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -1834,8 +1886,8 @@ static void i40e_diag_test(struct net_device *netdev,
 		if (i40e_reg_test(netdev, &data[I40E_ETH_TEST_REG]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
 
-		clear_bit(__I40E_TESTING, &pf->state);
-		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
+		clear_bit(__I40E_TESTING, pf->state);
+		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
 
 		if (if_running)
 			i40e_open(netdev);
@@ -2285,6 +2337,102 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
 }
 
 /**
+ * i40e_check_mask - Check whether a mask field is set
+ * @mask: the full mask value
+ * @field; mask of the field to check
+ *
+ * If the given mask is fully set, return positive value. If the mask for the
+ * field is fully unset, return zero. Otherwise return a negative error code.
+ **/
+static int i40e_check_mask(u64 mask, u64 field)
+{
+	u64 value = mask & field;
+
+	if (value == field)
+		return 1;
+	else if (!value)
+		return 0;
+	else
+		return -1;
+}
+
+/**
+ * i40e_parse_rx_flow_user_data - Deconstruct user-defined data
+ * @fsp: pointer to rx flow specification
+ * @data: pointer to userdef data structure for storage
+ *
+ * Read the user-defined data and deconstruct the value into a structure. No
+ * other code should read the user-defined data, so as to ensure that every
+ * place consistently reads the value correctly.
+ *
+ * The user-defined field is a 64bit Big Endian format value, which we
+ * deconstruct by reading bits or bit fields from it. Single bit flags shall
+ * be defined starting from the highest bits, while small bit field values
+ * shall be defined starting from the lowest bits.
+ *
+ * Returns 0 if the data is valid, and non-zero if the userdef data is invalid
+ * and the filter should be rejected. The data structure will always be
+ * modified even if FLOW_EXT is not set.
+ *
+ **/
+static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+					struct i40e_rx_flow_userdef *data)
+{
+	u64 value, mask;
+	int valid;
+
+	/* Zero memory first so it's always consistent. */
+	memset(data, 0, sizeof(*data));
+
+	if (!(fsp->flow_type & FLOW_EXT))
+		return 0;
+
+	value = be64_to_cpu(*((__be64 *)fsp->h_ext.data));
+	mask = be64_to_cpu(*((__be64 *)fsp->m_ext.data));
+
+#define I40E_USERDEF_FLEX_WORD		GENMASK_ULL(15, 0)
+#define I40E_USERDEF_FLEX_OFFSET	GENMASK_ULL(31, 16)
+#define I40E_USERDEF_FLEX_FILTER	GENMASK_ULL(31, 0)
+
+	valid = i40e_check_mask(mask, I40E_USERDEF_FLEX_FILTER);
+	if (valid < 0) {
+		return -EINVAL;
+	} else if (valid) {
+		data->flex_word = value & I40E_USERDEF_FLEX_WORD;
+		data->flex_offset =
+			(value & I40E_USERDEF_FLEX_OFFSET) >> 16;
+		data->flex_filter = true;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_fill_rx_flow_user_data - Fill in user-defined data field
+ * @fsp: pointer to rx_flow specification
+ *
+ * Reads the userdef data structure and properly fills in the user defined
+ * fields of the rx_flow_spec.
+ **/
+static void i40e_fill_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+					struct i40e_rx_flow_userdef *data)
+{
+	u64 value = 0, mask = 0;
+
+	if (data->flex_filter) {
+		value |= data->flex_word;
+		value |= (u64)data->flex_offset << 16;
+		mask |= I40E_USERDEF_FLEX_FILTER;
+	}
+
+	if (value || mask)
+		fsp->flow_type |= FLOW_EXT;
+
+	*((__be64 *)fsp->h_ext.data) = cpu_to_be64(value);
+	*((__be64 *)fsp->m_ext.data) = cpu_to_be64(mask);
+}
+
+/**
  * i40e_get_ethtool_fdir_all - Populates the rule count of a command
  * @pf: Pointer to the physical function struct
  * @cmd: The command to get or set Rx flow classification rules
@@ -2335,8 +2483,11 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 {
 	struct ethtool_rx_flow_spec *fsp =
 			(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct i40e_rx_flow_userdef userdef = {0};
 	struct i40e_fdir_filter *rule = NULL;
 	struct hlist_node *node2;
+	u64 input_set;
+	u16 index;
 
 	hlist_for_each_entry_safe(rule, node2,
 				  &pf->fdir_filter_list, fdir_node) {
@@ -2359,8 +2510,48 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 	 */
 	fsp->h_u.tcp_ip4_spec.psrc = rule->dst_port;
 	fsp->h_u.tcp_ip4_spec.pdst = rule->src_port;
-	fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip[0];
-	fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip[0];
+	fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip;
+	fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip;
+
+	switch (rule->flow_type) {
+	case SCTP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		break;
+	case TCP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		break;
+	case UDP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		break;
+	case IP_USER_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		break;
+	default:
+		/* If we have stored a filter with a flow type not listed here
+		 * it is almost certainly a driver bug. WARN(), and then
+		 * assign the input_set as if all fields are enabled to avoid
+		 * reading unassigned memory.
+		 */
+		WARN(1, "Missing input set index for flow_type %d\n",
+		     rule->flow_type);
+		input_set = 0xFFFFFFFFFFFFFFFFULL;
+		goto no_input_set;
+	}
+
+	input_set = i40e_read_fd_input_set(pf, index);
+
+no_input_set:
+	if (input_set & I40E_L3_SRC_MASK)
+		fsp->m_u.tcp_ip4_spec.ip4src = htonl(0xFFFF);
+
+	if (input_set & I40E_L3_DST_MASK)
+		fsp->m_u.tcp_ip4_spec.ip4dst = htonl(0xFFFF);
+
+	if (input_set & I40E_L4_SRC_MASK)
+		fsp->m_u.tcp_ip4_spec.psrc = htons(0xFFFFFFFF);
+
+	if (input_set & I40E_L4_DST_MASK)
+		fsp->m_u.tcp_ip4_spec.pdst = htons(0xFFFFFFFF);
 
 	if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET)
 		fsp->ring_cookie = RX_CLS_FLOW_DISC;
@@ -2372,11 +2563,24 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 
 		vsi = i40e_find_vsi_from_id(pf, rule->dest_vsi);
 		if (vsi && vsi->type == I40E_VSI_SRIOV) {
-			fsp->h_ext.data[1] = htonl(vsi->vf_id);
-			fsp->m_ext.data[1] = htonl(0x1);
+			/* VFs are zero-indexed by the driver, but ethtool
+			 * expects them to be one-indexed, so add one here
+			 */
+			u64 ring_vf = vsi->vf_id + 1;
+
+			ring_vf <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+			fsp->ring_cookie |= ring_vf;
 		}
 	}
 
+	if (rule->flex_filter) {
+		userdef.flex_filter = true;
+		userdef.flex_word = be16_to_cpu(rule->flex_word);
+		userdef.flex_offset = rule->flex_offset;
+	}
+
+	i40e_fill_rx_flow_user_data(fsp, &userdef);
+
 	return 0;
 }
 
@@ -2574,24 +2778,6 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 }
 
 /**
- * i40e_match_fdir_input_set - Match a new filter against an existing one
- * @rule: The filter already added
- * @input: The new filter to comapre against
- *
- * Returns true if the two input set match
- **/
-static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule,
-				      struct i40e_fdir_filter *input)
-{
-	if ((rule->dst_ip[0] != input->dst_ip[0]) ||
-	    (rule->src_ip[0] != input->src_ip[0]) ||
-	    (rule->dst_port != input->dst_port) ||
-	    (rule->src_port != input->src_port))
-		return false;
-	return true;
-}
-
-/**
  * i40e_update_ethtool_fdir_entry - Updates the fdir filter entry
  * @vsi: Pointer to the targeted VSI
  * @input: The filter to update or NULL to indicate deletion
@@ -2626,22 +2812,22 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
 
 	/* if there is an old rule occupying our place remove it */
 	if (rule && (rule->fd_id == sw_idx)) {
-		if (input && !i40e_match_fdir_input_set(rule, input))
-			err = i40e_add_del_fdir(vsi, rule, false);
-		else if (!input)
-			err = i40e_add_del_fdir(vsi, rule, false);
+		/* Remove this rule, since we're either deleting it, or
+		 * replacing it.
+		 */
+		err = i40e_add_del_fdir(vsi, rule, false);
 		hlist_del(&rule->fdir_node);
 		kfree(rule);
 		pf->fdir_pf_active_filters--;
 	}
 
-	/* If no input this was a delete, err should be 0 if a rule was
-	 * successfully found and removed from the list else -EINVAL
+	/* If we weren't given an input, this is a delete, so just return the
+	 * error code indicating if there was an entry at the requested slot
 	 */
 	if (!input)
 		return err;
 
-	/* initialize node and set software index */
+	/* Otherwise, install the new rule as requested */
 	INIT_HLIST_NODE(&input->fdir_node);
 
 	/* add filter to the list */
@@ -2658,6 +2844,69 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
 }
 
 /**
+ * i40e_prune_flex_pit_list - Cleanup unused entries in FLX_PIT table
+ * @pf: pointer to PF structure
+ *
+ * This function searches the list of filters and determines which FLX_PIT
+ * entries are still required. It will prune any entries which are no longer
+ * in use after the deletion.
+ **/
+static void i40e_prune_flex_pit_list(struct i40e_pf *pf)
+{
+	struct i40e_flex_pit *entry, *tmp;
+	struct i40e_fdir_filter *rule;
+
+	/* First, we'll check the l3 table */
+	list_for_each_entry_safe(entry, tmp, &pf->l3_flex_pit_list, list) {
+		bool found = false;
+
+		hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) {
+			if (rule->flow_type != IP_USER_FLOW)
+				continue;
+			if (rule->flex_filter &&
+			    rule->flex_offset == entry->src_offset) {
+				found = true;
+				break;
+			}
+		}
+
+		/* If we didn't find the filter, then we can prune this entry
+		 * from the list.
+		 */
+		if (!found) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+
+	/* Followed by the L4 table */
+	list_for_each_entry_safe(entry, tmp, &pf->l4_flex_pit_list, list) {
+		bool found = false;
+
+		hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) {
+			/* Skip this filter if it's L3, since we already
+			 * checked those in the above loop
+			 */
+			if (rule->flow_type == IP_USER_FLOW)
+				continue;
+			if (rule->flex_filter &&
+			    rule->flex_offset == entry->src_offset) {
+				found = true;
+				break;
+			}
+		}
+
+		/* If we didn't find the filter, then we can prune this entry
+		 * from the list.
+		 */
+		if (!found) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+}
+
+/**
  * i40e_del_fdir_entry - Deletes a Flow Director filter entry
  * @vsi: Pointer to the targeted VSI
  * @cmd: The command to get or set Rx flow classification rules
@@ -2675,20 +2924,700 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
 	struct i40e_pf *pf = vsi->back;
 	int ret = 0;
 
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
-	    test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+	    test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
 		return -EBUSY;
 
-	if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+	if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 		return -EBUSY;
 
 	ret = i40e_update_ethtool_fdir_entry(vsi, NULL, fsp->location, cmd);
 
+	i40e_prune_flex_pit_list(pf);
+
 	i40e_fdir_check_and_reenable(pf);
 	return ret;
 }
 
 /**
+ * i40e_unused_pit_index - Find an unused PIT index for given list
+ * @pf: the PF data structure
+ *
+ * Find the first unused flexible PIT index entry. We search both the L3 and
+ * L4 flexible PIT lists so that the returned index is unique and unused by
+ * either currently programmed L3 or L4 filters. We use a bit field as storage
+ * to track which indexes are already used.
+ **/
+static u8 i40e_unused_pit_index(struct i40e_pf *pf)
+{
+	unsigned long available_index = 0xFF;
+	struct i40e_flex_pit *entry;
+
+	/* We need to make sure that the new index isn't in use by either L3
+	 * or L4 filters so that IP_USER_FLOW filters can program both L3 and
+	 * L4 to use the same index.
+	 */
+
+	list_for_each_entry(entry, &pf->l4_flex_pit_list, list)
+		clear_bit(entry->pit_index, &available_index);
+
+	list_for_each_entry(entry, &pf->l3_flex_pit_list, list)
+		clear_bit(entry->pit_index, &available_index);
+
+	return find_first_bit(&available_index, 8);
+}
+
+/**
+ * i40e_find_flex_offset - Find an existing flex src_offset
+ * @flex_pit_list: L3 or L4 flex PIT list
+ * @src_offset: new src_offset to find
+ *
+ * Searches the flex_pit_list for an existing offset. If no offset is
+ * currently programmed, then this will return an ERR_PTR if there is no space
+ * to add a new offset, otherwise it returns NULL.
+ **/
+static
+struct i40e_flex_pit *i40e_find_flex_offset(struct list_head *flex_pit_list,
+					    u16 src_offset)
+{
+	struct i40e_flex_pit *entry;
+	int size = 0;
+
+	/* Search for the src_offset first. If we find a matching entry
+	 * already programmed, we can simply re-use it.
+	 */
+	list_for_each_entry(entry, flex_pit_list, list) {
+		size++;
+		if (entry->src_offset == src_offset)
+			return entry;
+	}
+
+	/* If we haven't found an entry yet, then the provided src offset has
+	 * not yet been programmed. We will program the src offset later on,
+	 * but we need to indicate whether there is enough space to do so
+	 * here. We'll make use of ERR_PTR for this purpose.
+	 */
+	if (size >= I40E_FLEX_PIT_TABLE_SIZE)
+		return ERR_PTR(-ENOSPC);
+
+	return NULL;
+}
+
+/**
+ * i40e_add_flex_offset - Add src_offset to flex PIT table list
+ * @flex_pit_list: L3 or L4 flex PIT list
+ * @src_offset: new src_offset to add
+ * @pit_index: the PIT index to program
+ *
+ * This function programs the new src_offset to the list. It is expected that
+ * i40e_find_flex_offset has already been tried and returned NULL, indicating
+ * that this offset is not programmed, and that the list has enough space to
+ * store another offset.
+ *
+ * Returns 0 on success, and negative value on error.
+ **/
+static int i40e_add_flex_offset(struct list_head *flex_pit_list,
+				u16 src_offset,
+				u8 pit_index)
+{
+	struct i40e_flex_pit *new_pit, *entry;
+
+	new_pit = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!new_pit)
+		return -ENOMEM;
+
+	new_pit->src_offset = src_offset;
+	new_pit->pit_index = pit_index;
+
+	/* We need to insert this item such that the list is sorted by
+	 * src_offset in ascending order.
+	 */
+	list_for_each_entry(entry, flex_pit_list, list) {
+		if (new_pit->src_offset < entry->src_offset) {
+			list_add_tail(&new_pit->list, &entry->list);
+			return 0;
+		}
+
+		/* If we found an entry with our offset already programmed we
+		 * can simply return here, after freeing the memory. However,
+		 * if the pit_index does not match we need to report an error.
+		 */
+		if (new_pit->src_offset == entry->src_offset) {
+			int err = 0;
+
+			/* If the PIT index is not the same we can't re-use
+			 * the entry, so we must report an error.
+			 */
+			if (new_pit->pit_index != entry->pit_index)
+				err = -EINVAL;
+
+			kfree(new_pit);
+			return err;
+		}
+	}
+
+	/* If we reached here, then we haven't yet added the item. This means
+	 * that we should add the item at the end of the list.
+	 */
+	list_add_tail(&new_pit->list, flex_pit_list);
+	return 0;
+}
+
+/**
+ * __i40e_reprogram_flex_pit - Re-program specific FLX_PIT table
+ * @pf: Pointer to the PF structure
+ * @flex_pit_list: list of flexible src offsets in use
+ * #flex_pit_start: index to first entry for this section of the table
+ *
+ * In order to handle flexible data, the hardware uses a table of values
+ * called the FLX_PIT table. This table is used to indicate which sections of
+ * the input correspond to what PIT index values. Unfortunately, hardware is
+ * very restrictive about programming this table. Entries must be ordered by
+ * src_offset in ascending order, without duplicates. Additionally, unused
+ * entries must be set to the unused index value, and must have valid size and
+ * length according to the src_offset ordering.
+ *
+ * This function will reprogram the FLX_PIT register from a book-keeping
+ * structure that we guarantee is already ordered correctly, and has no more
+ * than 3 entries.
+ *
+ * To make things easier, we only support flexible values of one word length,
+ * rather than allowing variable length flexible values.
+ **/
+static void __i40e_reprogram_flex_pit(struct i40e_pf *pf,
+				      struct list_head *flex_pit_list,
+				      int flex_pit_start)
+{
+	struct i40e_flex_pit *entry = NULL;
+	u16 last_offset = 0;
+	int i = 0, j = 0;
+
+	/* First, loop over the list of flex PIT entries, and reprogram the
+	 * registers.
+	 */
+	list_for_each_entry(entry, flex_pit_list, list) {
+		/* We have to be careful when programming values for the
+		 * largest SRC_OFFSET value. It is possible that adding
+		 * additional empty values at the end would overflow the space
+		 * for the SRC_OFFSET in the FLX_PIT register. To avoid this,
+		 * we check here and add the empty values prior to adding the
+		 * largest value.
+		 *
+		 * To determine this, we will use a loop from i+1 to 3, which
+		 * will determine whether the unused entries would have valid
+		 * SRC_OFFSET. Note that there cannot be extra entries past
+		 * this value, because the only valid values would have been
+		 * larger than I40E_MAX_FLEX_SRC_OFFSET, and thus would not
+		 * have been added to the list in the first place.
+		 */
+		for (j = i + 1; j < 3; j++) {
+			u16 offset = entry->src_offset + j;
+			int index = flex_pit_start + i;
+			u32 value = I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED,
+						       1,
+						       offset - 3);
+
+			if (offset > I40E_MAX_FLEX_SRC_OFFSET) {
+				i40e_write_rx_ctl(&pf->hw,
+						  I40E_PRTQF_FLX_PIT(index),
+						  value);
+				i++;
+			}
+		}
+
+		/* Now, we can program the actual value into the table */
+		i40e_write_rx_ctl(&pf->hw,
+				  I40E_PRTQF_FLX_PIT(flex_pit_start + i),
+				  I40E_FLEX_PREP_VAL(entry->pit_index + 50,
+						     1,
+						     entry->src_offset));
+		i++;
+	}
+
+	/* In order to program the last entries in the table, we need to
+	 * determine the valid offset. If the list is empty, we'll just start
+	 * with 0. Otherwise, we'll start with the last item offset and add 1.
+	 * This ensures that all entries have valid sizes. If we don't do this
+	 * correctly, the hardware will disable flexible field parsing.
+	 */
+	if (!list_empty(flex_pit_list))
+		last_offset = list_prev_entry(entry, list)->src_offset + 1;
+
+	for (; i < 3; i++, last_offset++) {
+		i40e_write_rx_ctl(&pf->hw,
+				  I40E_PRTQF_FLX_PIT(flex_pit_start + i),
+				  I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED,
+						     1,
+						     last_offset));
+	}
+}
+
+/**
+ * i40e_reprogram_flex_pit - Reprogram all FLX_PIT tables after input set change
+ * @pf: pointer to the PF structure
+ *
+ * This function reprograms both the L3 and L4 FLX_PIT tables. See the
+ * internal helper function for implementation details.
+ **/
+static void i40e_reprogram_flex_pit(struct i40e_pf *pf)
+{
+	__i40e_reprogram_flex_pit(pf, &pf->l3_flex_pit_list,
+				  I40E_FLEX_PIT_IDX_START_L3);
+
+	__i40e_reprogram_flex_pit(pf, &pf->l4_flex_pit_list,
+				  I40E_FLEX_PIT_IDX_START_L4);
+
+	/* We also need to program the L3 and L4 GLQF ORT register */
+	i40e_write_rx_ctl(&pf->hw,
+			  I40E_GLQF_ORT(I40E_L3_GLQF_ORT_IDX),
+			  I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L3,
+					    3, 1));
+
+	i40e_write_rx_ctl(&pf->hw,
+			  I40E_GLQF_ORT(I40E_L4_GLQF_ORT_IDX),
+			  I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L4,
+					    3, 1));
+}
+
+/**
+ * i40e_flow_str - Converts a flow_type into a human readable string
+ * @flow_type: the flow type from a flow specification
+ *
+ * Currently only flow types we support are included here, and the string
+ * value attempts to match what ethtool would use to configure this flow type.
+ **/
+static const char *i40e_flow_str(struct ethtool_rx_flow_spec *fsp)
+{
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case TCP_V4_FLOW:
+		return "tcp4";
+	case UDP_V4_FLOW:
+		return "udp4";
+	case SCTP_V4_FLOW:
+		return "sctp4";
+	case IP_USER_FLOW:
+		return "ip4";
+	default:
+		return "unknown";
+	}
+}
+
+/**
+ * i40e_pit_index_to_mask - Return the FLEX mask for a given PIT index
+ * @pit_index: PIT index to convert
+ *
+ * Returns the mask for a given PIT index. Will return 0 if the pit_index is
+ * of range.
+ **/
+static u64 i40e_pit_index_to_mask(int pit_index)
+{
+	switch (pit_index) {
+	case 0:
+		return I40E_FLEX_50_MASK;
+	case 1:
+		return I40E_FLEX_51_MASK;
+	case 2:
+		return I40E_FLEX_52_MASK;
+	case 3:
+		return I40E_FLEX_53_MASK;
+	case 4:
+		return I40E_FLEX_54_MASK;
+	case 5:
+		return I40E_FLEX_55_MASK;
+	case 6:
+		return I40E_FLEX_56_MASK;
+	case 7:
+		return I40E_FLEX_57_MASK;
+	default:
+		return 0;
+	}
+}
+
+/**
+ * i40e_print_input_set - Show changes between two input sets
+ * @vsi: the vsi being configured
+ * @old: the old input set
+ * @new: the new input set
+ *
+ * Print the difference between old and new input sets by showing which series
+ * of words are toggled on or off. Only displays the bits we actually support
+ * changing.
+ **/
+static void i40e_print_input_set(struct i40e_vsi *vsi, u64 old, u64 new)
+{
+	struct i40e_pf *pf = vsi->back;
+	bool old_value, new_value;
+	int i;
+
+	old_value = !!(old & I40E_L3_SRC_MASK);
+	new_value = !!(new & I40E_L3_SRC_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L3 source address: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_L3_DST_MASK);
+	new_value = !!(new & I40E_L3_DST_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L3 destination address: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_L4_SRC_MASK);
+	new_value = !!(new & I40E_L4_SRC_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L4 source port: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_L4_DST_MASK);
+	new_value = !!(new & I40E_L4_DST_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L4 destination port: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_VERIFY_TAG_MASK);
+	new_value = !!(new & I40E_VERIFY_TAG_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "SCTP verification tag: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	/* Show change of flexible filter entries */
+	for (i = 0; i < I40E_FLEX_INDEX_ENTRIES; i++) {
+		u64 flex_mask = i40e_pit_index_to_mask(i);
+
+		old_value = !!(old & flex_mask);
+		new_value = !!(new & flex_mask);
+		if (old_value != new_value)
+			netif_info(pf, drv, vsi->netdev, "FLEX index %d: %s -> %s\n",
+				   i,
+				   old_value ? "ON" : "OFF",
+				   new_value ? "ON" : "OFF");
+	}
+
+	netif_info(pf, drv, vsi->netdev, "  Current input set: %0llx\n",
+		   old);
+	netif_info(pf, drv, vsi->netdev, "Requested input set: %0llx\n",
+		   new);
+}
+
+/**
+ * i40e_check_fdir_input_set - Check that a given rx_flow_spec mask is valid
+ * @vsi: pointer to the targeted VSI
+ * @fsp: pointer to Rx flow specification
+ * @userdef: userdefined data from flow specification
+ *
+ * Ensures that a given ethtool_rx_flow_spec has a valid mask. Some support
+ * for partial matches exists with a few limitations. First, hardware only
+ * supports masking by word boundary (2 bytes) and not per individual bit.
+ * Second, hardware is limited to using one mask for a flow type and cannot
+ * use a separate mask for each filter.
+ *
+ * To support these limitations, if we already have a configured filter for
+ * the specified type, this function enforces that new filters of the type
+ * match the configured input set. Otherwise, if we do not have a filter of
+ * the specified type, we allow the input set to be updated to match the
+ * desired filter.
+ *
+ * To help ensure that administrators understand why filters weren't displayed
+ * as supported, we print a diagnostic message displaying how the input set
+ * would change and warning to delete the preexisting filters if required.
+ *
+ * Returns 0 on successful input set match, and a negative return code on
+ * failure.
+ **/
+static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
+				     struct ethtool_rx_flow_spec *fsp,
+				     struct i40e_rx_flow_userdef *userdef)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct ethtool_tcpip4_spec *tcp_ip4_spec;
+	struct ethtool_usrip4_spec *usr_ip4_spec;
+	u64 current_mask, new_mask;
+	bool new_flex_offset = false;
+	bool flex_l3 = false;
+	u16 *fdir_filter_count;
+	u16 index, src_offset = 0;
+	u8 pit_index = 0;
+	int err;
+
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case SCTP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		fdir_filter_count = &pf->fd_sctp4_filter_cnt;
+		break;
+	case TCP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		fdir_filter_count = &pf->fd_tcp4_filter_cnt;
+		break;
+	case UDP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		fdir_filter_count = &pf->fd_udp4_filter_cnt;
+		break;
+	case IP_USER_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		fdir_filter_count = &pf->fd_ip4_filter_cnt;
+		flex_l3 = true;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Read the current input set from register memory. */
+	current_mask = i40e_read_fd_input_set(pf, index);
+	new_mask = current_mask;
+
+	/* Determine, if any, the required changes to the input set in order
+	 * to support the provided mask.
+	 *
+	 * Hardware only supports masking at word (2 byte) granularity and does
+	 * not support full bitwise masking. This implementation simplifies
+	 * even further and only supports fully enabled or fully disabled
+	 * masks for each field, even though we could split the ip4src and
+	 * ip4dst fields.
+	 */
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case SCTP_V4_FLOW:
+		new_mask &= ~I40E_VERIFY_TAG_MASK;
+		/* Fall through */
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		tcp_ip4_spec = &fsp->m_u.tcp_ip4_spec;
+
+		/* IPv4 source address */
+		if (tcp_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_SRC_MASK;
+		else if (!tcp_ip4_spec->ip4src)
+			new_mask &= ~I40E_L3_SRC_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* IPv4 destination address */
+		if (tcp_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_DST_MASK;
+		else if (!tcp_ip4_spec->ip4dst)
+			new_mask &= ~I40E_L3_DST_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* L4 source port */
+		if (tcp_ip4_spec->psrc == htons(0xFFFF))
+			new_mask |= I40E_L4_SRC_MASK;
+		else if (!tcp_ip4_spec->psrc)
+			new_mask &= ~I40E_L4_SRC_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* L4 destination port */
+		if (tcp_ip4_spec->pdst == htons(0xFFFF))
+			new_mask |= I40E_L4_DST_MASK;
+		else if (!tcp_ip4_spec->pdst)
+			new_mask &= ~I40E_L4_DST_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* Filtering on Type of Service is not supported. */
+		if (tcp_ip4_spec->tos)
+			return -EOPNOTSUPP;
+
+		break;
+	case IP_USER_FLOW:
+		usr_ip4_spec = &fsp->m_u.usr_ip4_spec;
+
+		/* IPv4 source address */
+		if (usr_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_SRC_MASK;
+		else if (!usr_ip4_spec->ip4src)
+			new_mask &= ~I40E_L3_SRC_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* IPv4 destination address */
+		if (usr_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_DST_MASK;
+		else if (!usr_ip4_spec->ip4dst)
+			new_mask &= ~I40E_L3_DST_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* First 4 bytes of L4 header */
+		if (usr_ip4_spec->l4_4_bytes == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK;
+		else if (!usr_ip4_spec->l4_4_bytes)
+			new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+		else
+			return -EOPNOTSUPP;
+
+		/* Filtering on Type of Service is not supported. */
+		if (usr_ip4_spec->tos)
+			return -EOPNOTSUPP;
+
+		/* Filtering on IP version is not supported */
+		if (usr_ip4_spec->ip_ver)
+			return -EINVAL;
+
+		/* Filtering on L4 protocol is not supported */
+		if (usr_ip4_spec->proto)
+			return -EINVAL;
+
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* First, clear all flexible filter entries */
+	new_mask &= ~I40E_FLEX_INPUT_MASK;
+
+	/* If we have a flexible filter, try to add this offset to the correct
+	 * flexible filter PIT list. Once finished, we can update the mask.
+	 * If the src_offset changed, we will get a new mask value which will
+	 * trigger an input set change.
+	 */
+	if (userdef->flex_filter) {
+		struct i40e_flex_pit *l3_flex_pit = NULL, *flex_pit = NULL;
+
+		/* Flexible offset must be even, since the flexible payload
+		 * must be aligned on 2-byte boundary.
+		 */
+		if (userdef->flex_offset & 0x1) {
+			dev_warn(&pf->pdev->dev,
+				 "Flexible data offset must be 2-byte aligned\n");
+			return -EINVAL;
+		}
+
+		src_offset = userdef->flex_offset >> 1;
+
+		/* FLX_PIT source offset value is only so large */
+		if (src_offset > I40E_MAX_FLEX_SRC_OFFSET) {
+			dev_warn(&pf->pdev->dev,
+				 "Flexible data must reside within first 64 bytes of the packet payload\n");
+			return -EINVAL;
+		}
+
+		/* See if this offset has already been programmed. If we get
+		 * an ERR_PTR, then the filter is not safe to add. Otherwise,
+		 * if we get a NULL pointer, this means we will need to add
+		 * the offset.
+		 */
+		flex_pit = i40e_find_flex_offset(&pf->l4_flex_pit_list,
+						 src_offset);
+		if (IS_ERR(flex_pit))
+			return PTR_ERR(flex_pit);
+
+		/* IP_USER_FLOW filters match both L4 (ICMP) and L3 (unknown)
+		 * packet types, and thus we need to program both L3 and L4
+		 * flexible values. These must have identical flexible index,
+		 * as otherwise we can't correctly program the input set. So
+		 * we'll find both an L3 and L4 index and make sure they are
+		 * the same.
+		 */
+		if (flex_l3) {
+			l3_flex_pit =
+				i40e_find_flex_offset(&pf->l3_flex_pit_list,
+						      src_offset);
+			if (IS_ERR(l3_flex_pit))
+				return PTR_ERR(l3_flex_pit);
+
+			if (flex_pit) {
+				/* If we already had a matching L4 entry, we
+				 * need to make sure that the L3 entry we
+				 * obtained uses the same index.
+				 */
+				if (l3_flex_pit) {
+					if (l3_flex_pit->pit_index !=
+					    flex_pit->pit_index) {
+						return -EINVAL;
+					}
+				} else {
+					new_flex_offset = true;
+				}
+			} else {
+				flex_pit = l3_flex_pit;
+			}
+		}
+
+		/* If we didn't find an existing flex offset, we need to
+		 * program a new one. However, we don't immediately program it
+		 * here because we will wait to program until after we check
+		 * that it is safe to change the input set.
+		 */
+		if (!flex_pit) {
+			new_flex_offset = true;
+			pit_index = i40e_unused_pit_index(pf);
+		} else {
+			pit_index = flex_pit->pit_index;
+		}
+
+		/* Update the mask with the new offset */
+		new_mask |= i40e_pit_index_to_mask(pit_index);
+	}
+
+	/* If the mask and flexible filter offsets for this filter match the
+	 * currently programmed values we don't need any input set change, so
+	 * this filter is safe to install.
+	 */
+	if (new_mask == current_mask && !new_flex_offset)
+		return 0;
+
+	netif_info(pf, drv, vsi->netdev, "Input set change requested for %s flows:\n",
+		   i40e_flow_str(fsp));
+	i40e_print_input_set(vsi, current_mask, new_mask);
+	if (new_flex_offset) {
+		netif_info(pf, drv, vsi->netdev, "FLEX index %d: Offset -> %d",
+			   pit_index, src_offset);
+	}
+
+	/* Hardware input sets are global across multiple ports, so even the
+	 * main port cannot change them when in MFP mode as this would impact
+	 * any filters on the other ports.
+	 */
+	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+		netif_err(pf, drv, vsi->netdev, "Cannot change Flow Director input sets while MFP is enabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* This filter requires us to update the input set. However, hardware
+	 * only supports one input set per flow type, and does not support
+	 * separate masks for each filter. This means that we can only support
+	 * a single mask for all filters of a specific type.
+	 *
+	 * If we have preexisting filters, they obviously depend on the
+	 * current programmed input set. Display a diagnostic message in this
+	 * case explaining why the filter could not be accepted.
+	 */
+	if (*fdir_filter_count) {
+		netif_err(pf, drv, vsi->netdev, "Cannot change input set for %s flows until %d preexisting filters are removed\n",
+			  i40e_flow_str(fsp),
+			  *fdir_filter_count);
+		return -EOPNOTSUPP;
+	}
+
+	i40e_write_fd_input_set(pf, index, new_mask);
+
+	/* Add the new offset and update table, if necessary */
+	if (new_flex_offset) {
+		err = i40e_add_flex_offset(&pf->l4_flex_pit_list, src_offset,
+					   pit_index);
+		if (err)
+			return err;
+
+		if (flex_l3) {
+			err = i40e_add_flex_offset(&pf->l3_flex_pit_list,
+						   src_offset,
+						   pit_index);
+			if (err)
+				return err;
+		}
+
+		i40e_reprogram_flex_pit(pf);
+	}
+
+	return 0;
+}
+
+/**
  * i40e_add_fdir_ethtool - Add/Remove Flow Director filters
  * @vsi: pointer to the targeted VSI
  * @cmd: command to get or set RX flow classification rules
@@ -2699,11 +3628,13 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
 static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 				 struct ethtool_rxnfc *cmd)
 {
+	struct i40e_rx_flow_userdef userdef;
 	struct ethtool_rx_flow_spec *fsp;
 	struct i40e_fdir_filter *input;
+	u16 dest_vsi = 0, q_index = 0;
 	struct i40e_pf *pf;
 	int ret = -EINVAL;
-	u16 vf_id;
+	u8 dest_ctl;
 
 	if (!vsi)
 		return -EINVAL;
@@ -2712,26 +3643,61 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return -EOPNOTSUPP;
 
-	if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)
+	if (pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED)
 		return -ENOSPC;
 
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
-	    test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+	    test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
 		return -EBUSY;
 
-	if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+	if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 		return -EBUSY;
 
 	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
 
+	/* Parse the user-defined field */
+	if (i40e_parse_rx_flow_user_data(fsp, &userdef))
+		return -EINVAL;
+
+	/* Extended MAC field is not supported */
+	if (fsp->flow_type & FLOW_MAC_EXT)
+		return -EINVAL;
+
+	ret = i40e_check_fdir_input_set(vsi, fsp, &userdef);
+	if (ret)
+		return ret;
+
 	if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort +
 			      pf->hw.func_caps.fd_filters_guaranteed)) {
 		return -EINVAL;
 	}
 
-	if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
-	    (fsp->ring_cookie >= vsi->num_queue_pairs))
-		return -EINVAL;
+	/* ring_cookie is either the drop index, or is a mask of the queue
+	 * index and VF id we wish to target.
+	 */
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
+	} else {
+		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+		if (!vf) {
+			if (ring >= vsi->num_queue_pairs)
+				return -EINVAL;
+			dest_vsi = vsi->id;
+		} else {
+			/* VFs are zero-indexed, so we subtract one here */
+			vf--;
+
+			if (vf >= pf->num_alloc_vfs)
+				return -EINVAL;
+			if (ring >= pf->vf[vf].num_queue_pairs)
+				return -EINVAL;
+			dest_vsi = pf->vf[vf].lan_vsi_id;
+		}
+		dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
+		q_index = ring;
+	}
 
 	input = kzalloc(sizeof(*input), GFP_KERNEL);
 
@@ -2739,20 +3705,14 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 		return -ENOMEM;
 
 	input->fd_id = fsp->location;
-
-	if (fsp->ring_cookie == RX_CLS_FLOW_DISC)
-		input->dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
-	else
-		input->dest_ctl =
-			     I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
-
-	input->q_index = fsp->ring_cookie;
-	input->flex_off = 0;
-	input->pctype = 0;
-	input->dest_vsi = vsi->id;
+	input->q_index = q_index;
+	input->dest_vsi = dest_vsi;
+	input->dest_ctl = dest_ctl;
 	input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
 	input->cnt_index  = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
-	input->flow_type = fsp->flow_type;
+	input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+	input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+	input->flow_type = fsp->flow_type & ~FLOW_EXT;
 	input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
 
 	/* Reverse the src and dest notion, since the HW expects them to be from
@@ -2760,33 +3720,29 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	 */
 	input->dst_port = fsp->h_u.tcp_ip4_spec.psrc;
 	input->src_port = fsp->h_u.tcp_ip4_spec.pdst;
-	input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src;
-	input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst;
-
-	if (ntohl(fsp->m_ext.data[1])) {
-		vf_id = ntohl(fsp->h_ext.data[1]);
-		if (vf_id >= pf->num_alloc_vfs) {
-			netif_info(pf, drv, vsi->netdev,
-				   "Invalid VF id %d\n", vf_id);
-			goto free_input;
-		}
-		/* Find vsi id from vf id and override dest vsi */
-		input->dest_vsi = pf->vf[vf_id].lan_vsi_id;
-		if (input->q_index >= pf->vf[vf_id].num_queue_pairs) {
-			netif_info(pf, drv, vsi->netdev,
-				   "Invalid queue id %d for VF %d\n",
-				   input->q_index, vf_id);
-			goto free_input;
-		}
+	input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+	input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+
+	if (userdef.flex_filter) {
+		input->flex_filter = true;
+		input->flex_word = cpu_to_be16(userdef.flex_word);
+		input->flex_offset = userdef.flex_offset;
 	}
 
 	ret = i40e_add_del_fdir(vsi, input, true);
-free_input:
 	if (ret)
-		kfree(input);
-	else
-		i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
+		goto free_input;
+
+	/* Add the input filter to the fdir_input_list, possibly replacing
+	 * a previous filter. Do not free the input structure after adding it
+	 * to the list as this would cause a use-after-free bug.
+	 */
+	i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
 
+	return 0;
+
+free_input:
+	kfree(input);
 	return ret;
 }
 
@@ -3036,7 +3992,7 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
  * @dev: network interface device structure
  *
  * The get string set count and the string set should be matched for each
- * flag returned.  Add new strings for each flag to the i40e_priv_flags_strings
+ * flag returned.  Add new strings for each flag to the i40e_gstrings_priv_flags
  * array.
  *
  * Returns a u32 bitmap of flags.
@@ -3046,19 +4002,27 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u32 ret_flags = 0;
+	u32 i, j, ret_flags = 0;
+
+	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40e_priv_flags *priv_flags;
+
+		priv_flags = &i40e_gstrings_priv_flags[i];
+
+		if (priv_flags->flag & pf->flags)
+			ret_flags |= BIT(i);
+	}
+
+	if (pf->hw.pf_id != 0)
+		return ret_flags;
+
+	for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
+		const struct i40e_priv_flags *priv_flags;
 
-	ret_flags |= pf->flags & I40E_FLAG_LINK_POLLING_ENABLED ?
-		I40E_PRIV_FLAGS_LINKPOLL_FLAG : 0;
-	ret_flags |= pf->flags & I40E_FLAG_FD_ATR_ENABLED ?
-		I40E_PRIV_FLAGS_FD_ATR : 0;
-	ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ?
-		I40E_PRIV_FLAGS_VEB_STATS : 0;
-	ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ?
-		0 : I40E_PRIV_FLAGS_HW_ATR_EVICT;
-	if (pf->hw.pf_id == 0) {
-		ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ?
-			I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT : 0;
+		priv_flags = &i40e_gl_gstrings_priv_flags[j];
+
+		if (priv_flags->flag & pf->flags)
+			ret_flags |= BIT(i + j);
 	}
 
 	return ret_flags;
@@ -3074,54 +4038,66 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u16 sw_flags = 0, valid_flags = 0;
-	bool reset_required = false;
-	bool promisc_change = false;
-	int ret;
+	u64 changed_flags;
+	u32 i, j;
 
-	/* NOTE: MFP is not settable */
+	changed_flags = pf->flags;
 
-	if (flags & I40E_PRIV_FLAGS_LINKPOLL_FLAG)
-		pf->flags |= I40E_FLAG_LINK_POLLING_ENABLED;
-	else
-		pf->flags &= ~I40E_FLAG_LINK_POLLING_ENABLED;
+	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40e_priv_flags *priv_flags;
 
-	/* allow the user to control the state of the Flow
-	 * Director ATR (Application Targeted Routing) feature
-	 * of the driver
+		priv_flags = &i40e_gstrings_priv_flags[i];
+
+		if (priv_flags->read_only)
+			continue;
+
+		if (flags & BIT(i))
+			pf->flags |= priv_flags->flag;
+		else
+			pf->flags &= ~(priv_flags->flag);
+	}
+
+	if (pf->hw.pf_id != 0)
+		goto flags_complete;
+
+	for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
+		const struct i40e_priv_flags *priv_flags;
+
+		priv_flags = &i40e_gl_gstrings_priv_flags[j];
+
+		if (priv_flags->read_only)
+			continue;
+
+		if (flags & BIT(i + j))
+			pf->flags |= priv_flags->flag;
+		else
+			pf->flags &= ~(priv_flags->flag);
+	}
+
+flags_complete:
+	/* check for flags that changed */
+	changed_flags ^= pf->flags;
+
+	/* Process any additional changes needed as a result of flag changes.
+	 * The changed_flags value reflects the list of bits that were
+	 * changed in the code above.
 	 */
-	if (flags & I40E_PRIV_FLAGS_FD_ATR) {
-		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-	} else {
-		pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
-
-		/* flush current ATR settings */
-		set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
-	}
-
-	if ((flags & I40E_PRIV_FLAGS_VEB_STATS) &&
-	    !(pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
-		pf->flags |= I40E_FLAG_VEB_STATS_ENABLED;
-		reset_required = true;
-	} else if (!(flags & I40E_PRIV_FLAGS_VEB_STATS) &&
-		   (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
-		pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
-		reset_required = true;
-	}
-
-	if (pf->hw.pf_id == 0) {
-		if ((flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) &&
-		    !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
-			pf->flags |= I40E_FLAG_TRUE_PROMISC_SUPPORT;
-			promisc_change = true;
-		} else if (!(flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) &&
-			   (pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
-			pf->flags &= ~I40E_FLAG_TRUE_PROMISC_SUPPORT;
-			promisc_change = true;
-		}
+
+	/* Flush current ATR settings if ATR was disabled */
+	if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) &&
+	    !(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) {
+		pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED;
+		set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
 	}
-	if (promisc_change) {
+
+	/* Only allow ATR evict on hardware that is capable of handling it */
+	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
+		pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+
+	if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) {
+		u16 sw_flags = 0, valid_flags = 0;
+		int ret;
+
 		if (!(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
 			sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
@@ -3137,22 +4113,17 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 		}
 	}
 
-	if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) &&
-	    (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))
-		pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
-	else
-		pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE;
-
-	/* if needed, issue reset to cause things to take effect */
-	if (reset_required)
-		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
+	/* Issue reset to cause things to take effect, as additional bits
+	 * are added we will need to create a mask of bits requiring reset
+	 */
+	if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) ||
+	    ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev)))
+		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
 
 	return 0;
 }
 
 static const struct ethtool_ops i40e_ethtool_ops = {
-	.get_settings		= i40e_get_settings,
-	.set_settings		= i40e_set_settings,
 	.get_drvinfo		= i40e_get_drvinfo,
 	.get_regs_len		= i40e_get_regs_len,
 	.get_regs		= i40e_get_regs,
@@ -3189,6 +4160,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_priv_flags		= i40e_set_priv_flags,
 	.get_per_queue_coalesce	= i40e_get_per_queue_coalesce,
 	.set_per_queue_coalesce	= i40e_set_per_queue_coalesce,
+	.get_link_ksettings	= i40e_get_link_ksettings,
+	.set_link_ksettings	= i40e_set_link_ksettings,
 };
 
 void i40e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index e8a8351c8ea9..d5c9c9e06ff5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -32,6 +32,12 @@
 #include "i40e.h"
 #include "i40e_diag.h"
 #include <net/udp_tunnel.h>
+/* All i40e tracepoints are defined by the include below, which
+ * must be included exactly once across the whole kernel with
+ * CREATE_TRACE_POINTS defined
+ */
+#define CREATE_TRACE_POINTS
+#include "i40e_trace.h"
 
 const char i40e_driver_name[] = "i40e";
 static const char i40e_driver_string[] =
@@ -39,9 +45,9 @@ static const char i40e_driver_string[] =
 
 #define DRV_KERN "-k"
 
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 14
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -50,13 +56,16 @@ static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporatio
 
 /* a bit of forward declarations */
 static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
-static void i40e_handle_reset_warning(struct i40e_pf *pf);
+static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired);
 static int i40e_add_vsi(struct i40e_vsi *vsi);
 static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi);
 static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit);
 static int i40e_setup_misc_vector(struct i40e_pf *pf);
 static void i40e_determine_queue_usage(struct i40e_pf *pf);
 static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
+static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
+static int i40e_reset(struct i40e_pf *pf);
+static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
 static void i40e_fdir_sb_setup(struct i40e_pf *pf);
 static int i40e_veb_get_bw_info(struct i40e_veb *veb);
 
@@ -286,8 +295,8 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id)
  **/
 void i40e_service_event_schedule(struct i40e_pf *pf)
 {
-	if (!test_bit(__I40E_DOWN, &pf->state) &&
-	    !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+	if (!test_bit(__I40E_VSI_DOWN, pf->state) &&
+	    !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
 		queue_work(i40e_wq, &pf->service_task);
 }
 
@@ -299,11 +308,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf)
  * device is munged, not just the one netdev port, so go for the full
  * reset.
  **/
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev)
-#else
 static void i40e_tx_timeout(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -372,13 +377,13 @@ static void i40e_tx_timeout(struct net_device *netdev)
 
 	switch (pf->tx_timeout_recovery_level) {
 	case 1:
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		break;
 	case 2:
-		set_bit(__I40E_CORE_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_CORE_RESET_REQUESTED, pf->state);
 		break;
 	case 3:
-		set_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 		break;
 	default:
 		netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
@@ -408,10 +413,7 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi)
  * Returns the address of the device statistics structure.
  * The statistics are actually updated from the service task.
  **/
-#ifndef I40E_FCOE
-static
-#endif
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
+static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 				  struct rtnl_link_stats64 *stats)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
@@ -420,7 +422,7 @@ void i40e_get_netdev_stats_struct(struct net_device *netdev,
 	struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi);
 	int i;
 
-	if (test_bit(__I40E_DOWN, &vsi->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
 	if (!vsi->tx_rings)
@@ -723,55 +725,6 @@ static void i40e_update_veb_stats(struct i40e_veb *veb)
 	veb->stat_offsets_loaded = true;
 }
 
-#ifdef I40E_FCOE
-/**
- * i40e_update_fcoe_stats - Update FCoE-specific ethernet statistics counters.
- * @vsi: the VSI that is capable of doing FCoE
- **/
-static void i40e_update_fcoe_stats(struct i40e_vsi *vsi)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	struct i40e_fcoe_stats *ofs;
-	struct i40e_fcoe_stats *fs;     /* device's eth stats */
-	int idx;
-
-	if (vsi->type != I40E_VSI_FCOE)
-		return;
-
-	idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET;
-	fs = &vsi->fcoe_stats;
-	ofs = &vsi->fcoe_stats_offsets;
-
-	i40e_stat_update32(hw, I40E_GL_FCOEPRC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_packets, &fs->rx_fcoe_packets);
-	i40e_stat_update48(hw, I40E_GL_FCOEDWRCH(idx), I40E_GL_FCOEDWRCL(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_dwords, &fs->rx_fcoe_dwords);
-	i40e_stat_update32(hw, I40E_GL_FCOERPDC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_dropped, &fs->rx_fcoe_dropped);
-	i40e_stat_update32(hw, I40E_GL_FCOEPTC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->tx_fcoe_packets, &fs->tx_fcoe_packets);
-	i40e_stat_update48(hw, I40E_GL_FCOEDWTCH(idx), I40E_GL_FCOEDWTCL(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->tx_fcoe_dwords, &fs->tx_fcoe_dwords);
-	i40e_stat_update32(hw, I40E_GL_FCOECRC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_bad_fccrc, &fs->fcoe_bad_fccrc);
-	i40e_stat_update32(hw, I40E_GL_FCOELAST(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_last_error, &fs->fcoe_last_error);
-	i40e_stat_update32(hw, I40E_GL_FCOEDDPC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_ddp_count, &fs->fcoe_ddp_count);
-
-	vsi->fcoe_stat_offsets_loaded = true;
-}
-
-#endif
 /**
  * i40e_update_vsi_stats - Update the vsi statistics counters.
  * @vsi: the VSI to be updated
@@ -790,7 +743,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	struct i40e_eth_stats *oes;
 	struct i40e_eth_stats *es;     /* device's eth stats */
 	u32 tx_restart, tx_busy;
-	u64 tx_lost_interrupt;
 	struct i40e_ring *p;
 	u32 rx_page, rx_buf;
 	u64 bytes, packets;
@@ -801,8 +753,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	u64 tx_p, tx_b;
 	u16 q;
 
-	if (test_bit(__I40E_DOWN, &vsi->state) ||
-	    test_bit(__I40E_CONFIG_BUSY, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state) ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return;
 
 	ns = i40e_get_vsi_stats_struct(vsi);
@@ -816,7 +768,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	rx_b = rx_p = 0;
 	tx_b = tx_p = 0;
 	tx_restart = tx_busy = tx_linearize = tx_force_wb = 0;
-	tx_lost_interrupt = 0;
 	rx_page = 0;
 	rx_buf = 0;
 	rcu_read_lock();
@@ -835,7 +786,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 		tx_busy += p->tx_stats.tx_busy;
 		tx_linearize += p->tx_stats.tx_linearize;
 		tx_force_wb += p->tx_stats.tx_force_wb;
-		tx_lost_interrupt += p->tx_stats.tx_lost_interrupt;
 
 		/* Rx queue is part of the same block as Tx queue */
 		p = &p[1];
@@ -854,7 +804,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	vsi->tx_busy = tx_busy;
 	vsi->tx_linearize = tx_linearize;
 	vsi->tx_force_wb = tx_force_wb;
-	vsi->tx_lost_interrupt = tx_lost_interrupt;
 	vsi->rx_page_failed = rx_page;
 	vsi->rx_buf_failed = rx_buf;
 
@@ -1101,13 +1050,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_lpi_count, &nsd->rx_lpi_count);
 
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED &&
-	    !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED))
+	    !(pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED))
 		nsd->fd_sb_status = true;
 	else
 		nsd->fd_sb_status = false;
 
 	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED &&
-	    !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	    !(pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED))
 		nsd->fd_atr_status = true;
 	else
 		nsd->fd_atr_status = false;
@@ -1129,9 +1078,6 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 		i40e_update_pf_stats(pf);
 
 	i40e_update_vsi_stats(vsi);
-#ifdef I40E_FCOE
-	i40e_update_fcoe_stats(vsi);
-#endif
 }
 
 /**
@@ -1400,7 +1346,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 		 * to failed, so we don't bother to try sending the filter
 		 * to the hardware.
 		 */
-		if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state))
+		if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state))
 			f->state = I40E_FILTER_FAILED;
 		else
 			f->state = I40E_FILTER_NEW;
@@ -1562,11 +1508,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr)
  *
  * Returns 0 on success, negative on failure
  **/
-#ifdef I40E_FCOE
-int i40e_set_mac(struct net_device *netdev, void *p)
-#else
 static int i40e_set_mac(struct net_device *netdev, void *p)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1583,8 +1525,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		return 0;
 	}
 
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
+	    test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
 		return -EADDRNOTAVAIL;
 
 	if (ether_addr_equal(hw->mac.addr, addr->sa_data))
@@ -1626,17 +1568,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
  *
  * Setup VSI queue mapping for enabled traffic classes.
  **/
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
-			      struct i40e_vsi_context *ctxt,
-			      u8 enabled_tc,
-			      bool is_add)
-#else
 static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				     struct i40e_vsi_context *ctxt,
 				     u8 enabled_tc,
 				     bool is_add)
-#endif
 {
 	struct i40e_pf *pf = vsi->back;
 	u16 sections = 0;
@@ -1686,11 +1621,6 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				qcount = min_t(int, pf->alloc_rss_size,
 					       num_tc_qps);
 				break;
-#ifdef I40E_FCOE
-			case I40E_VSI_FCOE:
-				qcount = num_tc_qps;
-				break;
-#endif
 			case I40E_VSI_FDIR:
 			case I40E_VSI_SRIOV:
 			case I40E_VSI_VMDQ2:
@@ -1800,11 +1730,7 @@ static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr)
  * i40e_set_rx_mode - NDO callback to set the netdev filters
  * @netdev: network interface device structure
  **/
-#ifdef I40E_FCOE
-void i40e_set_rx_mode(struct net_device *netdev)
-#else
 static void i40e_set_rx_mode(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1883,19 +1809,12 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi,
 static
 struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next)
 {
-	while (next) {
-		next = hlist_entry(next->hlist.next,
-				   typeof(struct i40e_new_mac_filter),
-				   hlist);
-
-		/* keep going if we found a broadcast filter */
-		if (next && is_broadcast_ether_addr(next->f->macaddr))
-			continue;
-
-		break;
+	hlist_for_each_entry_continue(next, hlist) {
+		if (!is_broadcast_ether_addr(next->f->macaddr))
+			return next;
 	}
 
-	return next;
+	return NULL;
 }
 
 /**
@@ -2001,7 +1920,7 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 
 	if (fcnt != num_add) {
 		*promisc_changed = true;
-		set_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		dev_warn(&vsi->back->pdev->dev,
 			 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
 			 i40e_aq_str(hw, aq_err),
@@ -2084,7 +2003,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	struct i40e_aqc_add_macvlan_element_data *add_list;
 	struct i40e_aqc_remove_macvlan_element_data *del_list;
 
-	while (test_and_set_bit(__I40E_CONFIG_BUSY, &vsi->state))
+	while (test_and_set_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state))
 		usleep_range(1000, 2000);
 	pf = vsi->back;
 
@@ -2220,8 +2139,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 
 		num_add = 0;
 		hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) {
-			if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
-				     &vsi->state)) {
+			if (test_bit(__I40E_VSI_OVERFLOW_PROMISC,
+				     vsi->state)) {
 				new->state = I40E_FILTER_FAILED;
 				continue;
 			}
@@ -2308,20 +2227,20 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	 * safely exit if we didn't just enter, we no longer have any failed
 	 * filters, and we have reduced filters below the threshold value.
 	 */
-	if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) &&
+	if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) &&
 	    !promisc_changed && !failed_filters &&
 	    (vsi->active_filters < vsi->promisc_threshold)) {
 		dev_info(&pf->pdev->dev,
 			 "filter logjam cleared on %s, leaving overflow promiscuous mode\n",
 			 vsi_name);
-		clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+		clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		promisc_changed = true;
 		vsi->promisc_threshold = 0;
 	}
 
 	/* if the VF is not trusted do not do promisc */
 	if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) {
-		clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+		clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		goto out;
 	}
 
@@ -2346,12 +2265,12 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	}
 	if ((changed_flags & IFF_PROMISC) ||
 	    (promisc_changed &&
-	     test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state))) {
+	     test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state))) {
 		bool cur_promisc;
 
 		cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
-			       test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
-					&vsi->state));
+			       test_bit(__I40E_VSI_OVERFLOW_PROMISC,
+					vsi->state));
 		if ((vsi->type == I40E_VSI_MAIN) &&
 		    (pf->lan_veb != I40E_NO_VEB) &&
 		    !(pf->flags & I40E_FLAG_MFP_ENABLED)) {
@@ -2434,7 +2353,7 @@ out:
 	if (retval)
 		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
 
-	clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
+	clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state);
 	return retval;
 
 err_no_memory:
@@ -2446,7 +2365,7 @@ err_no_memory_locked:
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
 
 	vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
-	clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
+	clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state);
 	return -ENOMEM;
 }
 
@@ -2487,13 +2406,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 
 	netdev_info(netdev, "changing MTU from %d to %d\n",
 		    netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 	if (netif_running(netdev))
 		i40e_vsi_reinit_locked(vsi);
-	i40e_notify_client_of_l2_param_changes(vsi);
+	pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+		      I40E_FLAG_CLIENT_L2_CHANGE);
 	return 0;
 }
 
@@ -2707,13 +2628,8 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid)
  *
  * net_device_ops implementation for adding vlan ids
  **/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
-			 __always_unused __be16 proto, u16 vid)
-#else
 static int i40e_vlan_rx_add_vid(struct net_device *netdev,
 				__always_unused __be16 proto, u16 vid)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -2744,13 +2660,8 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev,
  *
  * net_device_ops implementation for removing vlan ids
  **/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
-			  __always_unused __be16 proto, u16 vid)
-#else
 static int i40e_vlan_rx_kill_vid(struct net_device *netdev,
 				 __always_unused __be16 proto, u16 vid)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -2920,9 +2831,6 @@ static int i40e_vsi_setup_rx_resources(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_setup_rx_descriptors(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
-	i40e_fcoe_setup_ddp_resources(vsi);
-#endif
 	return err;
 }
 
@@ -2942,9 +2850,6 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
 	for (i = 0; i < vsi->num_queue_pairs; i++)
 		if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
 			i40e_free_rx_resources(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
-	i40e_fcoe_free_ddp_resources(vsi);
-#endif
 }
 
 /**
@@ -3015,9 +2920,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	tx_ctx.qlen = ring->count;
 	tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED |
 					       I40E_FLAG_FD_ATR_ENABLED));
-#ifdef I40E_FCOE
-	tx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
 	tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP);
 	/* FDIR VSI tx ring can still use RS bit and writebacks */
 	if (vsi->type != I40E_VSI_FDIR)
@@ -3098,7 +3000,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 
 	ring->rx_buf_len = vsi->rx_buf_len;
 
-	rx_ctx.dbuff = ring->rx_buf_len >> I40E_RXQ_CTX_DBUFF_SHIFT;
+	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
+				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
 
 	rx_ctx.base = (ring->dma / 128);
 	rx_ctx.qlen = ring->count;
@@ -3120,9 +3023,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	rx_ctx.l2tsel = 1;
 	/* this controls whether VLAN is stripped from inner headers */
 	rx_ctx.showiv = 0;
-#ifdef I40E_FCOE
-	rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
 	/* set the prefena field to 1 because the manual says to */
 	rx_ctx.prefena = 1;
 
@@ -3144,6 +3044,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		return -ENOMEM;
 	}
 
+	/* configure Rx buffer alignment */
+	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX))
+		clear_ring_build_skb_enabled(ring);
+	else
+		set_ring_build_skb_enabled(ring);
+
 	/* cache tail for quicker writes, and clear the reg before use */
 	ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
 	writel(0, ring->tail);
@@ -3181,27 +3087,21 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi)
 	int err = 0;
 	u16 i;
 
-	if (vsi->netdev && (vsi->netdev->mtu > ETH_DATA_LEN))
-		vsi->max_frame = vsi->netdev->mtu + ETH_HLEN
-			       + ETH_FCS_LEN + VLAN_HLEN;
-	else
-		vsi->max_frame = I40E_RXBUFFER_2048;
-
-	vsi->rx_buf_len = I40E_RXBUFFER_2048;
-
-#ifdef I40E_FCOE
-	/* setup rx buffer for FCoE */
-	if ((vsi->type == I40E_VSI_FCOE) &&
-	    (vsi->back->flags & I40E_FLAG_FCOE_ENABLED)) {
-		vsi->rx_buf_len = I40E_RXBUFFER_3072;
-		vsi->max_frame = I40E_RXBUFFER_3072;
+	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) {
+		vsi->max_frame = I40E_MAX_RXBUFFER;
+		vsi->rx_buf_len = I40E_RXBUFFER_2048;
+#if (PAGE_SIZE < 8192)
+	} else if (!I40E_2K_TOO_SMALL_WITH_PADDING &&
+		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
+		vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+		vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+#endif
+	} else {
+		vsi->max_frame = I40E_MAX_RXBUFFER;
+		vsi->rx_buf_len = (PAGE_SIZE < 8192) ? I40E_RXBUFFER_3072 :
+						       I40E_RXBUFFER_2048;
 	}
 
-#endif /* I40E_FCOE */
-	/* round up for the chip's needs */
-	vsi->rx_buf_len = ALIGN(vsi->rx_buf_len,
-				BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
-
 	/* set up individual rings */
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_configure_rx_ring(vsi->rx_rings[i]);
@@ -3281,6 +3181,12 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi)
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return;
 
+	/* Reset FDir counters as we're replaying all existing filters */
+	pf->fd_tcp4_filter_cnt = 0;
+	pf->fd_udp4_filter_cnt = 0;
+	pf->fd_sctp4_filter_cnt = 0;
+	pf->fd_ip4_filter_cnt = 0;
+
 	hlist_for_each_entry_safe(filter, node,
 				  &pf->fdir_filter_list, fdir_node) {
 		i40e_add_del_fdir(vsi, filter, true);
@@ -3705,29 +3611,29 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		 * this is not a performance path and napi_schedule()
 		 * can deal with rescheduling.
 		 */
-		if (!test_bit(__I40E_DOWN, &pf->state))
+		if (!test_bit(__I40E_VSI_DOWN, pf->state))
 			napi_schedule_irqoff(&q_vector->napi);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
-		set_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+		set_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state);
 		i40e_debug(&pf->hw, I40E_DEBUG_NVM, "AdminQ event\n");
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
-		set_bit(__I40E_MDD_EVENT_PENDING, &pf->state);
+		set_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK;
-		set_bit(__I40E_VFLR_EVENT_PENDING, &pf->state);
+		set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_GRST_MASK) {
-		if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
-			set_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
+		if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+			set_bit(__I40E_RESET_INTR_RECEIVED, pf->state);
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_GRST_MASK;
 		val = rd32(hw, I40E_GLGEN_RSTAT);
 		val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK)
@@ -3738,7 +3644,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 			pf->globr_count++;
 		} else if (val == I40E_RESET_EMPR) {
 			pf->empr_count++;
-			set_bit(__I40E_EMP_RESET_INTR_RECEIVED, &pf->state);
+			set_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state);
 		}
 	}
 
@@ -3771,7 +3677,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		    (icr0_remaining & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK) ||
 		    (icr0_remaining & I40E_PFINT_ICR0_ECC_ERR_MASK)) {
 			dev_info(&pf->pdev->dev, "device will be reset\n");
-			set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+			set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 			i40e_service_event_schedule(pf);
 		}
 		ena_mask &= ~icr0_remaining;
@@ -3781,7 +3687,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 enable_intr:
 	/* re-enable interrupt causes */
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
-	if (!test_bit(__I40E_DOWN, &pf->state)) {
+	if (!test_bit(__I40E_VSI_DOWN, pf->state)) {
 		i40e_service_event_schedule(pf);
 		i40e_irq_dynamic_enable_icr0(pf, false);
 	}
@@ -3993,11 +3899,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
  * This is used by netconsole to send skbs without having to re-enable
  * interrupts.  It's not called while the normal interrupt routine is executing.
  **/
-#ifdef I40E_FCOE
-void i40e_netpoll(struct net_device *netdev)
-#else
 static void i40e_netpoll(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -4005,7 +3907,7 @@ static void i40e_netpoll(struct net_device *netdev)
 	int i;
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &vsi->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
@@ -4017,6 +3919,8 @@ static void i40e_netpoll(struct net_device *netdev)
 }
 #endif
 
+#define I40E_QTX_ENA_WAIT_COUNT 50
+
 /**
  * i40e_pf_txq_wait - Wait for a PF's Tx queue to be enabled or disabled
  * @pf: the PF being configured
@@ -4047,6 +3951,50 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 }
 
 /**
+ * i40e_control_tx_q - Start or stop a particular Tx queue
+ * @pf: the PF structure
+ * @pf_q: the PF queue to configure
+ * @enable: start or stop the queue
+ *
+ * This function enables or disables a single queue. Note that any delay
+ * required after the operation is expected to be handled by the caller of
+ * this function.
+ **/
+static void i40e_control_tx_q(struct i40e_pf *pf, int pf_q, bool enable)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u32 tx_reg;
+	int i;
+
+	/* warn the TX unit of coming changes */
+	i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable);
+	if (!enable)
+		usleep_range(10, 20);
+
+	for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) {
+		tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
+		if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) ==
+		    ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1))
+			break;
+		usleep_range(1000, 2000);
+	}
+
+	/* Skip if the queue is already in the requested state */
+	if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
+		return;
+
+	/* turn on/off the queue */
+	if (enable) {
+		wr32(hw, I40E_QTX_HEAD(pf_q), 0);
+		tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK;
+	} else {
+		tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
+	}
+
+	wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
+}
+
+/**
  * i40e_vsi_control_tx - Start or stop a VSI's rings
  * @vsi: the VSI being configured
  * @enable: start or stop the rings
@@ -4054,41 +4002,11 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 {
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	int i, j, pf_q, ret = 0;
-	u32 tx_reg;
+	int i, pf_q, ret = 0;
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-
-		/* warn the TX unit of coming changes */
-		i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable);
-		if (!enable)
-			usleep_range(10, 20);
-
-		for (j = 0; j < 50; j++) {
-			tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
-			if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) ==
-			    ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1))
-				break;
-			usleep_range(1000, 2000);
-		}
-		/* Skip if the queue is already in the requested state */
-		if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
-			continue;
-
-		/* turn on/off the queue */
-		if (enable) {
-			wr32(hw, I40E_QTX_HEAD(pf_q), 0);
-			tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK;
-		} else {
-			tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
-		}
-
-		wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
-		/* No waiting for the Tx queue to disable */
-		if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state))
-			continue;
+		i40e_control_tx_q(pf, pf_q, enable);
 
 		/* wait for the change to finish */
 		ret = i40e_pf_txq_wait(pf, pf_q, enable);
@@ -4100,8 +4018,6 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 		}
 	}
 
-	if (hw->revision_id == 0)
-		mdelay(50);
 	return ret;
 }
 
@@ -4135,6 +4051,43 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 }
 
 /**
+ * i40e_control_rx_q - Start or stop a particular Rx queue
+ * @pf: the PF structure
+ * @pf_q: the PF queue to configure
+ * @enable: start or stop the queue
+ *
+ * This function enables or disables a single queue. Note that any delay
+ * required after the operation is expected to be handled by the caller of
+ * this function.
+ **/
+static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u32 rx_reg;
+	int i;
+
+	for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) {
+		rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
+		if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) ==
+		    ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1))
+			break;
+		usleep_range(1000, 2000);
+	}
+
+	/* Skip if the queue is already in the requested state */
+	if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+		return;
+
+	/* turn on/off the queue */
+	if (enable)
+		rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK;
+	else
+		rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
+
+	wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
+}
+
+/**
  * i40e_vsi_control_rx - Start or stop a VSI's rings
  * @vsi: the VSI being configured
  * @enable: start or stop the rings
@@ -4142,33 +4095,11 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 {
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	int i, j, pf_q, ret = 0;
-	u32 rx_reg;
+	int i, pf_q, ret = 0;
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		for (j = 0; j < 50; j++) {
-			rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
-			if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) ==
-			    ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1))
-				break;
-			usleep_range(1000, 2000);
-		}
-
-		/* Skip if the queue is already in the requested state */
-		if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
-			continue;
-
-		/* turn on/off the queue */
-		if (enable)
-			rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK;
-		else
-			rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
-		wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
-		/* No waiting for the Tx queue to disable */
-		if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state))
-			continue;
+		i40e_control_rx_q(pf, pf_q, enable);
 
 		/* wait for the change to finish */
 		ret = i40e_pf_rxq_wait(pf, pf_q, enable);
@@ -4180,6 +4111,12 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 		}
 	}
 
+	/* Due to HW errata, on Rx disable only, the register can indicate done
+	 * before it really is. Needs 50ms to be sure
+	 */
+	if (!enable)
+		mdelay(50);
+
 	return ret;
 }
 
@@ -4206,6 +4143,10 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
  **/
 void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 {
+	/* When port TX is suspended, don't wait */
+	if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
+		return i40e_vsi_stop_rings_no_wait(vsi);
+
 	/* do rx first for enable and last for disable
 	 * Ignore return value, we need to shutdown whatever we can
 	 */
@@ -4214,6 +4155,29 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_vsi_stop_rings_no_wait - Stop a VSI's rings and do not delay
+ * @vsi: the VSI being shutdown
+ *
+ * This function stops all the rings for a VSI but does not delay to verify
+ * that rings have been disabled. It is expected that the caller is shutting
+ * down multiple VSIs at once and will delay together for all the VSIs after
+ * initiating the shutdown. This is particularly useful for shutting down lots
+ * of VFs together. Otherwise, a large delay can be incurred while configuring
+ * each VSI in serial.
+ **/
+void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+	int i, pf_q;
+
+	pf_q = vsi->base_queue;
+	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+		i40e_control_tx_q(pf, pf_q, false);
+		i40e_control_rx_q(pf, pf_q, false);
+	}
+}
+
+/**
  * i40e_vsi_free_irq - Free the irq association with the OS
  * @vsi: the VSI being configured
  **/
@@ -4438,8 +4402,12 @@ static void i40e_napi_enable_all(struct i40e_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_enable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_enable(&q_vector->napi);
+	}
 }
 
 /**
@@ -4453,8 +4421,12 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_disable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_disable(&q_vector->napi);
+	}
 }
 
 /**
@@ -4463,17 +4435,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
  **/
 static void i40e_vsi_close(struct i40e_vsi *vsi)
 {
-	bool reset = false;
-
-	if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
+	struct i40e_pf *pf = vsi->back;
+	if (!test_and_set_bit(__I40E_VSI_DOWN, vsi->state))
 		i40e_down(vsi);
 	i40e_vsi_free_irq(vsi);
 	i40e_vsi_free_tx_resources(vsi);
 	i40e_vsi_free_rx_resources(vsi);
 	vsi->current_netdev_flags = 0;
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		reset = true;
-	i40e_notify_client_of_netdev_close(vsi, reset);
+	pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+		pf->flags |=  I40E_FLAG_CLIENT_RESET;
 }
 
 /**
@@ -4482,18 +4453,10 @@ static void i40e_vsi_close(struct i40e_vsi *vsi)
  **/
 static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
 {
-	if (test_bit(__I40E_DOWN, &vsi->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
-	/* No need to disable FCoE VSI when Tx suspended */
-	if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) &&
-	    vsi->type == I40E_VSI_FCOE) {
-		dev_dbg(&vsi->back->pdev->dev,
-			 "VSI seid %d skipping FCoE VSI disable\n", vsi->seid);
-		return;
-	}
-
-	set_bit(__I40E_NEEDS_RESTART, &vsi->state);
+	set_bit(__I40E_VSI_NEEDS_RESTART, vsi->state);
 	if (vsi->netdev && netif_running(vsi->netdev))
 		vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
 	else
@@ -4506,10 +4469,9 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
  **/
 static void i40e_unquiesce_vsi(struct i40e_vsi *vsi)
 {
-	if (!test_bit(__I40E_NEEDS_RESTART, &vsi->state))
+	if (!test_and_clear_bit(__I40E_VSI_NEEDS_RESTART, vsi->state))
 		return;
 
-	clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
 	if (vsi->netdev && netif_running(vsi->netdev))
 		vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
 	else
@@ -4544,21 +4506,20 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
 	}
 }
 
-#ifdef CONFIG_I40E_DCB
 /**
  * i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled
  * @vsi: the VSI being configured
  *
- * This function waits for the given VSI's queues to be disabled.
+ * Wait until all queues on a given VSI have been disabled.
  **/
-static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
+int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
 	int i, pf_q, ret;
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		/* Check and wait for the disable status of the queue */
+		/* Check and wait for the Tx queue */
 		ret = i40e_pf_txq_wait(pf, pf_q, false);
 		if (ret) {
 			dev_info(&pf->pdev->dev,
@@ -4566,11 +4527,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 				 vsi->seid, pf_q);
 			return ret;
 		}
-	}
-
-	pf_q = vsi->base_queue;
-	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		/* Check and wait for the disable status of the queue */
+		/* Check and wait for the Tx queue */
 		ret = i40e_pf_rxq_wait(pf, pf_q, false);
 		if (ret) {
 			dev_info(&pf->pdev->dev,
@@ -4583,6 +4540,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 	return 0;
 }
 
+#ifdef CONFIG_I40E_DCB
 /**
  * i40e_pf_wait_queues_disabled - Wait for all queues of PF VSIs to be disabled
  * @pf: the PF
@@ -4595,8 +4553,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 	int v, ret = 0;
 
 	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
-		/* No need to wait for FCoE VSI queues */
-		if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) {
+		if (pf->vsi[v]) {
 			ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
 			if (ret)
 				break;
@@ -4614,16 +4571,15 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
  * @vsi: Pointer to VSI struct
  *
  * This function checks specified queue for given VSI. Detects hung condition.
- * Sets hung bit since it is two step process. Before next run of service task
- * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not,
- * hung condition remain unchanged and during subsequent run, this function
- * issues SW interrupt to recover from hung condition.
+ * We proactively detect hung TX queues by checking if interrupts are disabled
+ * but there are pending descriptors.  If it appears hung, attempt to recover
+ * by triggering a SW interrupt.
  **/
 static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 {
 	struct i40e_ring *tx_ring = NULL;
 	struct i40e_pf	*pf;
-	u32 head, val, tx_pending_hw;
+	u32 val, tx_pending;
 	int i;
 
 	pf = vsi->back;
@@ -4649,47 +4605,15 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 	else
 		val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
 
-	head = i40e_get_head(tx_ring);
+	tx_pending = i40e_get_tx_pending(tx_ring);
 
-	tx_pending_hw = i40e_get_tx_pending(tx_ring, false);
-
-	/* HW is done executing descriptors, updated HEAD write back,
-	 * but SW hasn't processed those descriptors. If interrupt is
-	 * not generated from this point ON, it could result into
-	 * dev_watchdog detecting timeout on those netdev_queue,
-	 * hence proactively trigger SW interrupt.
-	 */
-	if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
-		/* NAPI Poll didn't run and clear since it was set */
-		if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT,
-				       &tx_ring->q_vector->hung_detected)) {
-			netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n",
-				    vsi->seid, q_idx, tx_pending_hw,
-				    tx_ring->next_to_clean, head,
-				    tx_ring->next_to_use,
-				    readl(tx_ring->tail));
-			netdev_info(vsi->netdev, "VSI_seid %d, Issuing force_wb for TX queue %d, Interrupt Reg: 0x%x\n",
-				    vsi->seid, q_idx, val);
-			i40e_force_wb(vsi, tx_ring->q_vector);
-		} else {
-			/* First Chance - detected possible hung */
-			set_bit(I40E_Q_VECTOR_HUNG_DETECT,
-				&tx_ring->q_vector->hung_detected);
-		}
-	}
-
-	/* This is the case where we have interrupts missing,
-	 * so the tx_pending in HW will most likely be 0, but we
-	 * will have tx_pending in SW since the WB happened but the
-	 * interrupt got lost.
+	/* Interrupts are disabled and TX pending is non-zero,
+	 * trigger the SW interrupt (don't wait). Worst case
+	 * there will be one extra interrupt which may result
+	 * into not cleaning any queues because queues are cleaned.
 	 */
-	if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) &&
-	    (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
-		local_bh_disable();
-		if (napi_reschedule(&tx_ring->q_vector->napi))
-			tx_ring->tx_stats.tx_lost_interrupt++;
-		local_bh_enable();
-	}
+	if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)))
+		i40e_force_wb(vsi, tx_ring->q_vector);
 }
 
 /**
@@ -4713,8 +4637,8 @@ static void i40e_detect_recover_hung(struct i40e_pf *pf)
 		return;
 
 	/* Make sure, VSI state is not DOWN/RECOVERY_PENDING */
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
+	    test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
 		return;
 
 	/* Make sure type is MAIN VSI */
@@ -5220,20 +5144,12 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 			continue;
 
 		/* - Enable all TCs for the LAN VSI
-#ifdef I40E_FCOE
-		 * - For FCoE VSI only enable the TC configured
-		 *   as per the APP TLV
-#endif
 		 * - For all others keep them at TC0 for now
 		 */
 		if (v == pf->lan_vsi)
 			tc_map = i40e_pf_get_tc_map(pf);
 		else
 			tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
-#ifdef I40E_FCOE
-		if (pf->vsi[v]->type == I40E_VSI_FCOE)
-			tc_map = i40e_get_fcoe_tc_map(pf);
-#endif /* #ifdef I40E_FCOE */
 
 		ret = i40e_vsi_config_tc(pf->vsi[v], tc_map);
 		if (ret) {
@@ -5269,7 +5185,7 @@ static int i40e_resume_port_tx(struct i40e_pf *pf)
 			  i40e_stat_str(&pf->hw, ret),
 			  i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 		/* Schedule PF reset to recover */
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		i40e_service_event_schedule(pf);
 	}
 
@@ -5300,10 +5216,6 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 		    (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED)) {
 			dev_info(&pf->pdev->dev,
 				 "DCBX offload is not supported or is disabled for this PF.\n");
-
-			if (pf->flags & I40E_FLAG_MFP_ENABLED)
-				goto out;
-
 		} else {
 			/* When status is not DISABLED then DCBX in FW */
 			pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED |
@@ -5441,7 +5353,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	if (err)
 		return err;
 
-	clear_bit(__I40E_DOWN, &vsi->state);
+	clear_bit(__I40E_VSI_DOWN, vsi->state);
 	i40e_napi_enable_all(vsi);
 	i40e_vsi_enable_irq(vsi);
 
@@ -5464,13 +5376,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	/* replay FDIR SB filters */
 	if (vsi->type == I40E_VSI_FDIR) {
 		/* reset fd counters */
-		pf->fd_add_err = pf->fd_atr_cnt = 0;
-		if (pf->fd_tcp_rule > 0) {
-			pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
-				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
-			pf->fd_tcp_rule = 0;
-		}
+		pf->fd_add_err = 0;
+		pf->fd_atr_cnt = 0;
 		i40e_fdir_filter_restore(vsi);
 	}
 
@@ -5495,12 +5402,12 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = vsi->back;
 
 	WARN_ON(in_interrupt());
-	while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state))
+	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state))
 		usleep_range(1000, 2000);
 	i40e_down(vsi);
 
 	i40e_up(vsi);
-	clear_bit(__I40E_CONFIG_BUSY, &pf->state);
+	clear_bit(__I40E_CONFIG_BUSY, pf->state);
 }
 
 /**
@@ -5527,7 +5434,7 @@ void i40e_down(struct i40e_vsi *vsi)
 	int i;
 
 	/* It is assumed that the caller of this function
-	 * sets the vsi->state __I40E_DOWN bit.
+	 * sets the vsi->state __I40E_VSI_DOWN bit.
 	 */
 	if (vsi->netdev) {
 		netif_carrier_off(vsi->netdev);
@@ -5542,8 +5449,6 @@ void i40e_down(struct i40e_vsi *vsi)
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
-	i40e_notify_client_of_netdev_close(vsi, false);
-
 }
 
 /**
@@ -5604,17 +5509,15 @@ exit:
 	return ret;
 }
 
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
-		    struct tc_to_netdev *tc)
-#else
 static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 			   struct tc_to_netdev *tc)
-#endif
 {
-	if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO)
+	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
-	return i40e_setup_tc(netdev, tc->tc);
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return i40e_setup_tc(netdev, tc->mqprio->num_tc);
 }
 
 /**
@@ -5637,8 +5540,8 @@ int i40e_open(struct net_device *netdev)
 	int err;
 
 	/* disallow open during test or if eeprom is broken */
-	if (test_bit(__I40E_TESTING, &pf->state) ||
-	    test_bit(__I40E_BAD_EEPROM, &pf->state))
+	if (test_bit(__I40E_TESTING, pf->state) ||
+	    test_bit(__I40E_BAD_EEPROM, pf->state))
 		return -EBUSY;
 
 	netif_carrier_off(netdev);
@@ -5667,6 +5570,8 @@ int i40e_open(struct net_device *netdev)
  * Finish initialization of the VSI.
  *
  * Returns 0 on success, negative value on failure
+ *
+ * Note: expects to be called while under rtnl_lock()
  **/
 int i40e_vsi_open(struct i40e_vsi *vsi)
 {
@@ -5730,7 +5635,7 @@ err_setup_rx:
 err_setup_tx:
 	i40e_vsi_free_tx_resources(vsi);
 	if (vsi == pf->vsi[pf->lan_vsi])
-		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
 
 	return err;
 }
@@ -5745,6 +5650,7 @@ err_setup_tx:
 static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 {
 	struct i40e_fdir_filter *filter;
+	struct i40e_flex_pit *pit_entry, *tmp;
 	struct hlist_node *node2;
 
 	hlist_for_each_entry_safe(filter, node2,
@@ -5752,7 +5658,43 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 		hlist_del(&filter->fdir_node);
 		kfree(filter);
 	}
+
+	list_for_each_entry_safe(pit_entry, tmp, &pf->l3_flex_pit_list, list) {
+		list_del(&pit_entry->list);
+		kfree(pit_entry);
+	}
+	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+
+	list_for_each_entry_safe(pit_entry, tmp, &pf->l4_flex_pit_list, list) {
+		list_del(&pit_entry->list);
+		kfree(pit_entry);
+	}
+	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
 	pf->fdir_pf_active_filters = 0;
+	pf->fd_tcp4_filter_cnt = 0;
+	pf->fd_udp4_filter_cnt = 0;
+	pf->fd_sctp4_filter_cnt = 0;
+	pf->fd_ip4_filter_cnt = 0;
+
+	/* Reprogram the default input set for TCP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for UDP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for SCTP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for Other/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 }
 
 /**
@@ -5779,12 +5721,14 @@ int i40e_close(struct net_device *netdev)
  * i40e_do_reset - Start a PF or Core Reset sequence
  * @pf: board private structure
  * @reset_flags: which reset is requested
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
  *
  * The essential difference in resets is that the PF Reset
  * doesn't clear the packet buffers, doesn't reset the PE
  * firmware, and doesn't bother the other PFs on the chip.
  **/
-void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 {
 	u32 val;
 
@@ -5830,7 +5774,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 		 * for the Core Reset.
 		 */
 		dev_dbg(&pf->pdev->dev, "PFR requested\n");
-		i40e_handle_reset_warning(pf);
+		i40e_handle_reset_warning(pf, lock_acquired);
 
 	} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
 		int v;
@@ -5842,10 +5786,9 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 			struct i40e_vsi *vsi = pf->vsi[v];
 
 			if (vsi != NULL &&
-			    test_bit(__I40E_REINIT_REQUESTED, &vsi->state)) {
+			    test_and_clear_bit(__I40E_VSI_REINIT_REQUESTED,
+					       vsi->state))
 				i40e_vsi_reinit_locked(pf->vsi[v]);
-				clear_bit(__I40E_REINIT_REQUESTED, &vsi->state);
-			}
 		}
 	} else if (reset_flags & BIT_ULL(__I40E_DOWN_REQUESTED)) {
 		int v;
@@ -5856,10 +5799,10 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 			struct i40e_vsi *vsi = pf->vsi[v];
 
 			if (vsi != NULL &&
-			    test_bit(__I40E_DOWN_REQUESTED, &vsi->state)) {
-				set_bit(__I40E_DOWN, &vsi->state);
+			    test_and_clear_bit(__I40E_VSI_DOWN_REQUESTED,
+					       vsi->state)) {
+				set_bit(__I40E_VSI_DOWN, vsi->state);
 				i40e_down(vsi);
-				clear_bit(__I40E_DOWN_REQUESTED, &vsi->state);
 			}
 		}
 	} else {
@@ -5999,7 +5942,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	else
 		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
 
-	set_bit(__I40E_PORT_TX_SUSPENDED, &pf->state);
+	set_bit(__I40E_PORT_SUSPENDED, pf->state);
 	/* Reconfiguration needed quiesce all VSIs */
 	i40e_pf_quiesce_all_vsi(pf);
 
@@ -6008,7 +5951,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 
 	ret = i40e_resume_port_tx(pf);
 
-	clear_bit(__I40E_PORT_TX_SUSPENDED, &pf->state);
+	clear_bit(__I40E_PORT_SUSPENDED, pf->state);
 	/* In case of error no point in resuming VSIs */
 	if (ret)
 		goto exit;
@@ -6017,12 +5960,12 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	ret = i40e_pf_wait_queues_disabled(pf);
 	if (ret) {
 		/* Schedule PF reset to recover */
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		i40e_service_event_schedule(pf);
 	} else {
 		i40e_pf_unquiesce_all_vsi(pf);
-		/* Notify the client for the DCB changes */
-		i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]);
+	pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+		      I40E_FLAG_CLIENT_L2_CHANGE);
 	}
 
 exit:
@@ -6039,7 +5982,7 @@ exit:
 void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags)
 {
 	rtnl_lock();
-	i40e_do_reset(pf, reset_flags);
+	i40e_do_reset(pf, reset_flags, true);
 	rtnl_unlock();
 }
 
@@ -6132,34 +6075,33 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 	u32 fcnt_prog, fcnt_avail;
 	struct hlist_node *node;
 
-	if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+	if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 		return;
 
-	/* Check if, FD SB or ATR was auto disabled and if there is enough room
-	 * to re-enable
-	 */
+	/* Check if we have enough room to re-enable FDir SB capability. */
 	fcnt_prog = i40e_get_global_fd_count(pf);
 	fcnt_avail = pf->fdir_pf_filter_count;
 	if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM)) ||
 	    (pf->fd_add_err == 0) ||
 	    (i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) {
-		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+		if (pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED) {
+			pf->flags &= ~I40E_FLAG_FD_SB_AUTO_DISABLED;
+			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
+			    (I40E_DEBUG_FD & pf->hw.debug_mask))
 				dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
 		}
 	}
 
-	/* Wait for some more space to be available to turn on ATR. We also
-	 * must check that no existing ntuple rules for TCP are in effect
+	/* We should wait for even more space before re-enabling ATR.
+	 * Additionally, we cannot enable ATR as long as we still have TCP SB
+	 * rules active.
 	 */
-	if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) {
-		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->fd_tcp_rule == 0)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+	if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) &&
+	    (pf->fd_tcp4_filter_cnt == 0)) {
+		if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) {
+			pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED;
+			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+			    (I40E_DEBUG_FD & pf->hw.debug_mask))
 				dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n");
 		}
 	}
@@ -6210,7 +6152,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 	}
 
 	pf->fd_flush_timestamp = jiffies;
-	pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+	pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED;
 	/* flush all filters */
 	wr32(&pf->hw, I40E_PFQF_CTL_1,
 	     I40E_PFQF_CTL_1_CLEARFDTABLE_MASK);
@@ -6229,9 +6171,9 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 	} else {
 		/* replay sideband filters */
 		i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
-		if (!disable_atr)
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-		clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
+		if (!disable_atr && !pf->fd_tcp4_filter_cnt)
+			pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED;
+		clear_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
 		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
 	}
@@ -6261,10 +6203,10 @@ static void i40e_fdir_reinit_subtask(struct i40e_pf *pf)
 {
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, pf->state))
 		return;
 
-	if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+	if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 		i40e_fdir_flush_and_replay(pf);
 
 	i40e_fdir_check_and_reenable(pf);
@@ -6278,14 +6220,11 @@ static void i40e_fdir_reinit_subtask(struct i40e_pf *pf)
  **/
 static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
 {
-	if (!vsi || test_bit(__I40E_DOWN, &vsi->state))
+	if (!vsi || test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
 	switch (vsi->type) {
 	case I40E_VSI_MAIN:
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-#endif
 		if (!vsi->netdev || !vsi->netdev_registered)
 			break;
 
@@ -6374,11 +6313,11 @@ static void i40e_link_event(struct i40e_pf *pf)
 
 	if (new_link == old_link &&
 	    new_link_speed == old_link_speed &&
-	    (test_bit(__I40E_DOWN, &vsi->state) ||
+	    (test_bit(__I40E_VSI_DOWN, vsi->state) ||
 	     new_link == netif_carrier_ok(vsi->netdev)))
 		return;
 
-	if (!test_bit(__I40E_DOWN, &vsi->state))
+	if (!test_bit(__I40E_VSI_DOWN, vsi->state))
 		i40e_print_link_message(vsi, new_link);
 
 	/* Notify the base of the switch tree connected to
@@ -6405,8 +6344,8 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf)
 	int i;
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &pf->state) ||
-	    test_bit(__I40E_CONFIG_BUSY, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, pf->state) ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return;
 
 	/* make sure we don't do these things too often */
@@ -6444,44 +6383,44 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
 {
 	u32 reset_flags = 0;
 
-	rtnl_lock();
-	if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_REINIT_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_REINIT_REQUESTED);
-		clear_bit(__I40E_REINIT_REQUESTED, &pf->state);
+		clear_bit(__I40E_REINIT_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_PF_RESET_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_PF_RESET_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_PF_RESET_REQUESTED);
-		clear_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		clear_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_CORE_RESET_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_CORE_RESET_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_CORE_RESET_REQUESTED);
-		clear_bit(__I40E_CORE_RESET_REQUESTED, &pf->state);
+		clear_bit(__I40E_CORE_RESET_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_GLOBAL_RESET_REQUESTED);
-		clear_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state);
+		clear_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_DOWN_REQUESTED, &pf->state)) {
-		reset_flags |= BIT(__I40E_DOWN_REQUESTED);
-		clear_bit(__I40E_DOWN_REQUESTED, &pf->state);
+	if (test_bit(__I40E_VSI_DOWN_REQUESTED, pf->state)) {
+		reset_flags |= BIT(__I40E_VSI_DOWN_REQUESTED);
+		clear_bit(__I40E_VSI_DOWN_REQUESTED, pf->state);
 	}
 
 	/* If there's a recovery already waiting, it takes
 	 * precedence before starting a new reset sequence.
 	 */
-	if (test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) {
-		i40e_handle_reset_warning(pf);
-		goto unlock;
+	if (test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) {
+		i40e_prep_for_reset(pf, false);
+		i40e_reset(pf);
+		i40e_rebuild(pf, false, false);
 	}
 
 	/* If we're already down or resetting, just bail */
 	if (reset_flags &&
-	    !test_bit(__I40E_DOWN, &pf->state) &&
-	    !test_bit(__I40E_CONFIG_BUSY, &pf->state))
-		i40e_do_reset(pf, reset_flags);
-
-unlock:
-	rtnl_unlock();
+	    !test_bit(__I40E_VSI_DOWN, pf->state) &&
+	    !test_bit(__I40E_CONFIG_BUSY, pf->state)) {
+		rtnl_lock();
+		i40e_do_reset(pf, reset_flags, true);
+		rtnl_unlock();
+	}
 }
 
 /**
@@ -6526,7 +6465,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 	u32 val;
 
 	/* Do not run clean AQ when PF reset fails */
-	if (test_bit(__I40E_RESET_FAILED, &pf->state))
+	if (test_bit(__I40E_RESET_FAILED, pf->state))
 		return;
 
 	/* check for error indications */
@@ -6627,9 +6566,11 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 				 opcode);
 			break;
 		}
-	} while (pending && (i++ < pf->adminq_work_limit));
+	} while (i++ < pf->adminq_work_limit);
+
+	if (i < pf->adminq_work_limit)
+		clear_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state);
 
-	clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
 	/* re-enable Admin queue interrupt cause */
 	val = rd32(hw, I40E_PFINT_ICR0_ENA);
 	val |=  I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
@@ -6654,13 +6595,13 @@ static void i40e_verify_eeprom(struct i40e_pf *pf)
 		if (err) {
 			dev_info(&pf->pdev->dev, "eeprom check failed (%d), Tx/Rx traffic disabled\n",
 				 err);
-			set_bit(__I40E_BAD_EEPROM, &pf->state);
+			set_bit(__I40E_BAD_EEPROM, pf->state);
 		}
 	}
 
-	if (!err && test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+	if (!err && test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		dev_info(&pf->pdev->dev, "eeprom check passed, Tx/Rx traffic enabled\n");
-		clear_bit(__I40E_BAD_EEPROM, &pf->state);
+		clear_bit(__I40E_BAD_EEPROM, pf->state);
 	}
 }
 
@@ -6967,17 +6908,19 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
 /**
  * i40e_prep_for_reset - prep for the core to reset
  * @pf: board private structure
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
  *
  * Close up the VFs and other things in prep for PF Reset.
   **/
-static void i40e_prep_for_reset(struct i40e_pf *pf)
+static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired)
 {
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret = 0;
 	u32 v;
 
-	clear_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
-	if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+	clear_bit(__I40E_RESET_INTR_RECEIVED, pf->state);
+	if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
 		return;
 	if (i40e_check_asq_alive(&pf->hw))
 		i40e_vc_notify_reset(pf);
@@ -6985,7 +6928,12 @@ static void i40e_prep_for_reset(struct i40e_pf *pf)
 	dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
 
 	/* quiesce the VSIs and their queues that are not already DOWN */
+	/* pf_quiesce_all_vsi modifies netdev structures -rtnl_lock needed */
+	if (!lock_acquired)
+		rtnl_lock();
 	i40e_pf_quiesce_all_vsi(pf);
+	if (!lock_acquired)
+		rtnl_unlock();
 
 	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v])
@@ -7020,31 +6968,41 @@ static void i40e_send_version(struct i40e_pf *pf)
 }
 
 /**
- * i40e_reset_and_rebuild - reset and rebuild using a saved config
+ * i40e_reset - wait for core reset to finish reset, reset pf if corer not seen
  * @pf: board private structure
- * @reinit: if the Main VSI needs to re-initialized.
  **/
-static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
+static int i40e_reset(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
-	u8 set_fc_aq_fail = 0;
 	i40e_status ret;
-	u32 val;
-	u32 v;
 
-	/* Now we wait for GRST to settle out.
-	 * We don't have to delete the VEBs or VSIs from the hw switch
-	 * because the reset will make them disappear.
-	 */
 	ret = i40e_pf_reset(hw);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
-		set_bit(__I40E_RESET_FAILED, &pf->state);
-		goto clear_recovery;
+		set_bit(__I40E_RESET_FAILED, pf->state);
+		clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+	} else {
+		pf->pfr_count++;
 	}
-	pf->pfr_count++;
+	return ret;
+}
 
-	if (test_bit(__I40E_DOWN, &pf->state))
+/**
+ * i40e_rebuild - rebuild using a saved config
+ * @pf: board private structure
+ * @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
+ **/
+static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u8 set_fc_aq_fail = 0;
+	i40e_status ret;
+	u32 val;
+	int v;
+
+	if (test_bit(__I40E_VSI_DOWN, pf->state))
 		goto clear_recovery;
 	dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
@@ -7058,7 +7016,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	}
 
 	/* re-verify the eeprom if we just had an EMP reset */
-	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, &pf->state))
+	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
 		i40e_verify_eeprom(pf);
 
 	i40e_clear_pxe_mode(hw);
@@ -7067,8 +7025,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		goto end_core_reset;
 
 	ret = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
-				hw->func_caps.num_rx_qp,
-				pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+				hw->func_caps.num_rx_qp, 0, 0);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "init_lan_hmc failed: %d\n", ret);
 		goto end_core_reset;
@@ -7087,14 +7044,12 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */
-#ifdef I40E_FCOE
-	i40e_init_pf_fcoe(pf);
-
-#endif
 	/* do basic switch setup */
+	if (!lock_acquired)
+		rtnl_lock();
 	ret = i40e_setup_pf_switch(pf, reinit);
 	if (ret)
-		goto end_core_reset;
+		goto end_unlock;
 
 	/* The driver only wants link up/down and module qualification
 	 * reports from firmware.  Note the negative logic.
@@ -7165,7 +7120,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		if (ret) {
 			dev_info(&pf->pdev->dev,
 				 "rebuild of Main VSI failed: %d\n", ret);
-			goto end_core_reset;
+			goto end_unlock;
 		}
 	}
 
@@ -7208,18 +7163,45 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	/* restart the VSIs that were rebuilt and running before the reset */
 	i40e_pf_unquiesce_all_vsi(pf);
 
-	if (pf->num_alloc_vfs) {
-		for (v = 0; v < pf->num_alloc_vfs; v++)
-			i40e_reset_vf(&pf->vf[v], true);
-	}
+	/* Release the RTNL lock before we start resetting VFs */
+	if (!lock_acquired)
+		rtnl_unlock();
+
+	i40e_reset_all_vfs(pf, true);
 
 	/* tell the firmware that we're starting */
 	i40e_send_version(pf);
 
+	/* We've already released the lock, so don't do it again */
+	goto end_core_reset;
+
+end_unlock:
+	if (!lock_acquired)
+		rtnl_unlock();
 end_core_reset:
-	clear_bit(__I40E_RESET_FAILED, &pf->state);
+	clear_bit(__I40E_RESET_FAILED, pf->state);
 clear_recovery:
-	clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
+	clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+}
+
+/**
+ * i40e_reset_and_rebuild - reset and rebuild using a saved config
+ * @pf: board private structure
+ * @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
+ **/
+static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
+				   bool lock_acquired)
+{
+	int ret;
+	/* Now we wait for GRST to settle out.
+	 * We don't have to delete the VEBs or VSIs from the hw switch
+	 * because the reset will make them disappear.
+	 */
+	ret = i40e_reset(pf);
+	if (!ret)
+		i40e_rebuild(pf, reinit, lock_acquired);
 }
 
 /**
@@ -7228,11 +7210,13 @@ clear_recovery:
  *
  * Close up the VFs and other things in prep for a Core Reset,
  * then get ready to rebuild the world.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
  **/
-static void i40e_handle_reset_warning(struct i40e_pf *pf)
+static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired)
 {
-	i40e_prep_for_reset(pf);
-	i40e_reset_and_rebuild(pf, false);
+	i40e_prep_for_reset(pf, lock_acquired);
+	i40e_reset_and_rebuild(pf, false, lock_acquired);
 }
 
 /**
@@ -7250,7 +7234,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	u32 reg;
 	int i;
 
-	if (!test_bit(__I40E_MDD_EVENT_PENDING, &pf->state))
+	if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state))
 		return;
 
 	/* find what triggered the MDD event */
@@ -7302,7 +7286,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 		}
 		/* Queue belongs to the PF, initiate a reset */
 		if (pf_mdd_detected) {
-			set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+			set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 			i40e_service_event_schedule(pf);
 		}
 	}
@@ -7331,12 +7315,12 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 				 "Too many MDD events on VF %d, disabled\n", i);
 			dev_info(&pf->pdev->dev,
 				 "Use PF Control I/F to re-enable the VF\n");
-			set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
+			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
 		}
 	}
 
 	/* re-enable mdd interrupt cause */
-	clear_bit(__I40E_MDD_EVENT_PENDING, &pf->state);
+	clear_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	reg = rd32(hw, I40E_PFINT_ICR0_ENA);
 	reg |=  I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
@@ -7344,6 +7328,23 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters
+ * @pf: board private structure
+ **/
+static void i40e_sync_udp_filters(struct i40e_pf *pf)
+{
+	int i;
+
+	/* loop through and set pending bit for all active UDP filters */
+	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
+		if (pf->udp_ports[i].port)
+			pf->pending_udp_bitmap |= BIT_ULL(i);
+	}
+
+	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
+}
+
+/**
  * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW
  * @pf: board private structure
  **/
@@ -7351,7 +7352,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
-	__be16 port;
+	u16 port;
 	int i;
 
 	if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC))
@@ -7362,7 +7363,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
 		if (pf->pending_udp_bitmap & BIT_ULL(i)) {
 			pf->pending_udp_bitmap &= ~BIT_ULL(i);
-			port = pf->udp_ports[i].index;
+			port = pf->udp_ports[i].port;
 			if (port)
 				ret = i40e_aq_add_udp_tunnel(hw, port,
 							pf->udp_ports[i].type,
@@ -7375,11 +7376,11 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 					"%s %s port %d, index %d failed, err %s aq_err %s\n",
 					pf->udp_ports[i].type ? "vxlan" : "geneve",
 					port ? "add" : "delete",
-					ntohs(port), i,
+					port, i,
 					i40e_stat_str(&pf->hw, ret),
 					i40e_aq_str(&pf->hw,
 						    pf->hw.aq.asq_last_status));
-				pf->udp_ports[i].index = 0;
+				pf->udp_ports[i].port = 0;
 			}
 		}
 	}
@@ -7397,11 +7398,10 @@ static void i40e_service_task(struct work_struct *work)
 	unsigned long start_time = jiffies;
 
 	/* don't bother with service tasks if a reset is in progress */
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) {
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
 		return;
-	}
 
-	if (test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
+	if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
 		return;
 
 	i40e_detect_recover_hung(pf);
@@ -7411,23 +7411,34 @@ static void i40e_service_task(struct work_struct *work)
 	i40e_vc_process_vflr_event(pf);
 	i40e_watchdog_subtask(pf);
 	i40e_fdir_reinit_subtask(pf);
-	i40e_client_subtask(pf);
+	if (pf->flags & I40E_FLAG_CLIENT_RESET) {
+		/* Client subtask will reopen next time through. */
+		i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+		pf->flags &= ~I40E_FLAG_CLIENT_RESET;
+	} else {
+		i40e_client_subtask(pf);
+		if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) {
+			i40e_notify_client_of_l2_param_changes(
+							pf->vsi[pf->lan_vsi]);
+			pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE;
+		}
+	}
 	i40e_sync_filters_subtask(pf);
 	i40e_sync_udp_filters_subtask(pf);
 	i40e_clean_adminq_subtask(pf);
 
 	/* flush memory to make sure state is correct before next watchdog */
 	smp_mb__before_atomic();
-	clear_bit(__I40E_SERVICE_SCHED, &pf->state);
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
 
 	/* If the tasks have taken longer than one timer cycle or there
 	 * is more work to be done, reschedule the service task now
 	 * rather than wait for the timer to tick again.
 	 */
 	if (time_after(jiffies, (start_time + pf->service_timer_period)) ||
-	    test_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state)		 ||
-	    test_bit(__I40E_MDD_EVENT_PENDING, &pf->state)		 ||
-	    test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state))
+	    test_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state)		 ||
+	    test_bit(__I40E_MDD_EVENT_PENDING, pf->state)		 ||
+	    test_bit(__I40E_VFLR_EVENT_PENDING, pf->state))
 		i40e_service_event_schedule(pf);
 }
 
@@ -7484,15 +7495,6 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 				      I40E_REQ_DESCRIPTOR_MULTIPLE);
 		break;
 
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-		vsi->alloc_queue_pairs = pf->num_fcoe_qps;
-		vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
-		vsi->num_q_vectors = pf->num_fcoe_msix;
-		break;
-
-#endif /* I40E_FCOE */
 	default:
 		WARN_ON(1);
 		return -ENODATA;
@@ -7585,7 +7587,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	}
 	vsi->type = type;
 	vsi->back = pf;
-	set_bit(__I40E_DOWN, &vsi->state);
+	set_bit(__I40E_VSI_DOWN, vsi->state);
 	vsi->flags = 0;
 	vsi->idx = vsi_idx;
 	vsi->int_rate_limit = 0;
@@ -7809,6 +7811,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
 static int i40e_init_msix(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
+	int cpus, extra_vectors;
 	int vectors_left;
 	int v_budget, i;
 	int v_actual;
@@ -7827,9 +7830,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	 *	- assumes symmetric Tx/Rx pairing
 	 *   - The number of VMDq pairs
 	 *   - The CPU count within the NUMA node if iWARP is enabled
-#ifdef I40E_FCOE
-	 *   - The number of FCOE qps.
-#endif
 	 * Once we count this up, try the request.
 	 *
 	 * If we can't get what we want, we'll simplify to nearly nothing
@@ -7844,10 +7844,16 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		vectors_left--;
 	}
 
-	/* reserve vectors for the main PF traffic queues */
-	pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left);
+	/* reserve some vectors for the main PF traffic queues. Initially we
+	 * only reserve at most 50% of the available vectors, in the case that
+	 * the number of online CPUs is large. This ensures that we can enable
+	 * extra features as well. Once we've enabled the other features, we
+	 * will use any remaining vectors to reach as close as we can to the
+	 * number of online CPUs.
+	 */
+	cpus = num_online_cpus();
+	pf->num_lan_msix = min_t(int, cpus, vectors_left / 2);
 	vectors_left -= pf->num_lan_msix;
-	v_budget += pf->num_lan_msix;
 
 	/* reserve one vector for sideband flow director */
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -7860,20 +7866,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
-#ifdef I40E_FCOE
-	/* can we reserve enough for FCoE? */
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-		if (!vectors_left)
-			pf->num_fcoe_msix = 0;
-		else if (vectors_left >= pf->num_fcoe_qps)
-			pf->num_fcoe_msix = pf->num_fcoe_qps;
-		else
-			pf->num_fcoe_msix = 1;
-		v_budget += pf->num_fcoe_msix;
-		vectors_left -= pf->num_fcoe_msix;
-	}
-
-#endif
 	/* can we reserve enough for iWARP? */
 	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
 		iwarp_requested = pf->num_iwarp_msix;
@@ -7910,6 +7902,23 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
+	/* On systems with a large number of SMP cores, we previously limited
+	 * the number of vectors for num_lan_msix to be at most 50% of the
+	 * available vectors, to allow for other features. Now, we add back
+	 * the remaining vectors. However, we ensure that the total
+	 * num_lan_msix will not exceed num_online_cpus(). To do this, we
+	 * calculate the number of vectors we can add without going over the
+	 * cap of CPUs. For systems with a small number of CPUs this will be
+	 * zero.
+	 */
+	extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left);
+	pf->num_lan_msix += extra_vectors;
+	vectors_left -= extra_vectors;
+
+	WARN(vectors_left < 0,
+	     "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n");
+
+	v_budget += pf->num_lan_msix;
 	pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
 				   GFP_KERNEL);
 	if (!pf->msix_entries)
@@ -7950,10 +7959,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		pf->num_vmdq_msix = 1;    /* force VMDqs to only one vector */
 		pf->num_vmdq_vsis = 1;
 		pf->num_vmdq_qps = 1;
-#ifdef I40E_FCOE
-		pf->num_fcoe_qps = 0;
-		pf->num_fcoe_msix = 0;
-#endif
 
 		/* partition out the remaining vectors */
 		switch (vec) {
@@ -7967,13 +7972,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			} else {
 				pf->num_lan_msix = 2;
 			}
-#ifdef I40E_FCOE
-			/* give one vector to FCoE */
-			if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-				pf->num_lan_msix = 1;
-				pf->num_fcoe_msix = 1;
-			}
-#endif
 			break;
 		default:
 			if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
@@ -7993,13 +7991,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			       (vec - (pf->num_iwarp_msix + pf->num_vmdq_vsis)),
 							      pf->num_lan_msix);
 			pf->num_lan_qps = pf->num_lan_msix;
-#ifdef I40E_FCOE
-			/* give one vector to FCoE */
-			if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-				pf->num_fcoe_msix = 1;
-				vec--;
-			}
-#endif
 			break;
 		}
 	}
@@ -8020,13 +8011,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		dev_info(&pf->pdev->dev, "IWARP disabled, not enough MSI-X vectors\n");
 		pf->flags &= ~I40E_FLAG_IWARP_ENABLED;
 	}
-#ifdef I40E_FCOE
-
-	if ((pf->flags & I40E_FLAG_FCOE_ENABLED) && (pf->num_fcoe_msix == 0)) {
-		dev_info(&pf->pdev->dev, "FCOE disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
-	}
-#endif
 	i40e_debug(&pf->hw, I40E_DEBUG_INIT,
 		   "MSI-X vector distribution: PF %d, VMDq %d, FDSB %d, iWARP %d\n",
 		   pf->num_lan_msix,
@@ -8125,9 +8109,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 		if (vectors < 0) {
 			pf->flags &= ~(I40E_FLAG_MSIX_ENABLED	|
 				       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-				       I40E_FLAG_FCOE_ENABLED	|
-#endif
 				       I40E_FLAG_RSS_ENABLED	|
 				       I40E_FLAG_DCB_CAPABLE	|
 				       I40E_FLAG_DCB_ENABLED	|
@@ -8188,7 +8169,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
 	/* Only request the irq if this is the first time through, and
 	 * not when we're rebuilding after a Reset
 	 */
-	if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) {
+	if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) {
 		err = request_irq(pf->msix_entries[0].vector,
 				  i40e_intr, 0, pf->int_name, pf);
 		if (err) {
@@ -8360,13 +8341,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 
 		if (vsi->type == I40E_VSI_MAIN) {
 			for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i),
-						  seed_dw[i]);
+				wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]);
 		} else if (vsi->type == I40E_VSI_SRIOV) {
 			for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw,
-						  I40E_VFQF_HKEY1(i, vf_id),
-						  seed_dw[i]);
+				wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]);
 		} else {
 			dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n");
 		}
@@ -8384,9 +8362,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 			if (lut_size != I40E_VF_HLUT_ARRAY_SIZE)
 				return -EINVAL;
 			for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw,
-						  I40E_VFQF_HLUT1(i, vf_id),
-						  lut_dw[i]);
+				wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]);
 		} else {
 			dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n");
 		}
@@ -8514,9 +8490,12 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val);
 
 	/* Determine the RSS size of the VSI */
-	if (!vsi->rss_size)
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
+	if (!vsi->rss_size) {
+		u16 qcount;
+
+		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
+	}
 	if (!vsi->rss_size)
 		return -EINVAL;
 
@@ -8550,6 +8529,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
  *
  * returns 0 if rss is not enabled, if enabled returns the final rss queue
  * count which may be different from the requested queue count.
+ * Note: expects to be called while under rtnl_lock()
  **/
 int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 {
@@ -8562,12 +8542,14 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 	new_rss_size = min_t(int, queue_count, pf->rss_size_max);
 
 	if (queue_count != vsi->num_queue_pairs) {
+		u16 qcount;
+
 		vsi->req_queue_pairs = queue_count;
-		i40e_prep_for_reset(pf);
+		i40e_prep_for_reset(pf, true);
 
 		pf->alloc_rss_size = new_rss_size;
 
-		i40e_reset_and_rebuild(pf, true);
+		i40e_reset_and_rebuild(pf, true, true);
 
 		/* Discard the user configured hash keys and lut, if less
 		 * queues are enabled.
@@ -8579,8 +8561,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 		}
 
 		/* Reset vsi->rss_size, as number of enabled queues changed */
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
+		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
 
 		i40e_pf_config_rss(pf);
 	}
@@ -8813,10 +8795,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
 	}
 
-#ifdef I40E_FCOE
-	i40e_init_pf_fcoe(pf);
-
-#endif /* I40E_FCOE */
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
 		pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
@@ -8843,9 +8821,9 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		    (pf->hw.aq.api_min_ver > 4))) {
 		/* Supported in FW API version higher than 1.4 */
 		pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
-		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	} else {
-		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	}
 
 	pf->eeprom_version = 0xDEAD;
@@ -8905,16 +8883,16 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 			need_reset = true;
 			i40e_fdir_filter_exit(pf);
 		}
-		pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-		pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		pf->flags &= ~(I40E_FLAG_FD_SB_ENABLED |
+			       I40E_FLAG_FD_SB_AUTO_DISABLED);
 		/* reset fd counters */
-		pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
-		pf->fdir_pf_active_filters = 0;
+		pf->fd_add_err = 0;
+		pf->fd_atr_cnt = 0;
 		/* if ATR was auto disabled it can be re-enabled. */
-		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+		if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) {
+			pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED;
+			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+			    (I40E_DEBUG_FD & pf->hw.debug_mask))
 				dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 		}
 	}
@@ -8947,6 +8925,7 @@ static void i40e_clear_rss_lut(struct i40e_vsi *vsi)
  * i40e_set_features - set the netdev feature flags
  * @netdev: ptr to the netdev being adjusted
  * @features: the feature set that the stack is suggesting
+ * Note: expects to be called while under rtnl_lock()
  **/
 static int i40e_set_features(struct net_device *netdev,
 			     netdev_features_t features)
@@ -8970,7 +8949,7 @@ static int i40e_set_features(struct net_device *netdev,
 	need_reset = i40e_set_ntuple(pf, features);
 
 	if (need_reset)
-		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
 
 	return 0;
 }
@@ -8982,12 +8961,12 @@ static int i40e_set_features(struct net_device *netdev,
  *
  * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
  **/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port)
+static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
 {
 	u8 i;
 
 	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		if (pf->udp_ports[i].index == port)
+		if (pf->udp_ports[i].port == port)
 			return i;
 	}
 
@@ -9005,7 +8984,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	__be16 port = ti->port;
+	u16 port = ntohs(ti->port);
 	u8 next_idx;
 	u8 idx;
 
@@ -9013,8 +8992,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 
 	/* Check if port already exists */
 	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "port %d already offloaded\n",
-			    ntohs(port));
+		netdev_info(netdev, "port %d already offloaded\n", port);
 		return;
 	}
 
@@ -9023,7 +9001,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 
 	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
 		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
-			    ntohs(port));
+			    port);
 		return;
 	}
 
@@ -9041,7 +9019,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 	}
 
 	/* New port: add it and mark its index in the bitmap */
-	pf->udp_ports[next_idx].index = port;
+	pf->udp_ports[next_idx].port = port;
 	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
 }
@@ -9057,7 +9035,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	__be16 port = ti->port;
+	u16 port = ntohs(ti->port);
 	u8 idx;
 
 	idx = i40e_get_udp_port_idx(pf, port);
@@ -9082,14 +9060,14 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
 	/* if port exists, set it to 0 (mark for deletion)
 	 * and make it pending
 	 */
-	pf->udp_ports[idx].index = 0;
+	pf->udp_ports[idx].port = 0;
 	pf->pending_udp_bitmap |= BIT_ULL(idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
 
 	return;
 not_found:
 	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
-		    ntohs(port));
+		    port);
 }
 
 static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -9166,6 +9144,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
  * is to change the mode then that requires a PF reset to
  * allow rebuild of the components with required hardware
  * bridge mode enabled.
+ *
+ * Note: expects to be called while under rtnl_lock()
  **/
 static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				   struct nlmsghdr *nlh,
@@ -9221,7 +9201,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 			else
 				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
-			i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+			i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED),
+				      true);
 			break;
 		}
 	}
@@ -9344,10 +9325,6 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_poll_controller	= i40e_netpoll,
 #endif
 	.ndo_setup_tc		= __i40e_setup_tc,
-#ifdef I40E_FCOE
-	.ndo_fcoe_enable	= i40e_fcoe_enable,
-	.ndo_fcoe_disable	= i40e_fcoe_disable,
-#endif
 	.ndo_set_features	= i40e_set_features,
 	.ndo_set_vf_mac		= i40e_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= i40e_ndo_set_vf_port_vlan,
@@ -9380,6 +9357,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	u8 broadcast[ETH_ALEN];
 	u8 mac_addr[ETH_ALEN];
 	int etherdev_size;
+	netdev_features_t hw_enc_features;
+	netdev_features_t hw_features;
 
 	etherdev_size = sizeof(struct i40e_netdev_priv);
 	netdev = alloc_etherdev_mq(etherdev_size, vsi->alloc_queue_pairs);
@@ -9390,52 +9369,57 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	np = netdev_priv(netdev);
 	np->vsi = vsi;
 
-	netdev->hw_enc_features |= NETIF_F_SG			|
-				   NETIF_F_IP_CSUM		|
-				   NETIF_F_IPV6_CSUM		|
-				   NETIF_F_HIGHDMA		|
-				   NETIF_F_SOFT_FEATURES	|
-				   NETIF_F_TSO			|
-				   NETIF_F_TSO_ECN		|
-				   NETIF_F_TSO6			|
-				   NETIF_F_GSO_GRE		|
-				   NETIF_F_GSO_GRE_CSUM		|
-				   NETIF_F_GSO_IPXIP4		|
-				   NETIF_F_GSO_IPXIP6		|
-				   NETIF_F_GSO_UDP_TUNNEL	|
-				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
-				   NETIF_F_GSO_PARTIAL		|
-				   NETIF_F_SCTP_CRC		|
-				   NETIF_F_RXHASH		|
-				   NETIF_F_RXCSUM		|
-				   0;
+	hw_enc_features = NETIF_F_SG			|
+			  NETIF_F_IP_CSUM		|
+			  NETIF_F_IPV6_CSUM		|
+			  NETIF_F_HIGHDMA		|
+			  NETIF_F_SOFT_FEATURES		|
+			  NETIF_F_TSO			|
+			  NETIF_F_TSO_ECN		|
+			  NETIF_F_TSO6			|
+			  NETIF_F_GSO_GRE		|
+			  NETIF_F_GSO_GRE_CSUM		|
+			  NETIF_F_GSO_PARTIAL		|
+			  NETIF_F_GSO_UDP_TUNNEL	|
+			  NETIF_F_GSO_UDP_TUNNEL_CSUM	|
+			  NETIF_F_SCTP_CRC		|
+			  NETIF_F_RXHASH		|
+			  NETIF_F_RXCSUM		|
+			  0;
 
 	if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE))
 		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
 	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
+	netdev->hw_enc_features |= hw_enc_features;
+
 	/* record features VLANs can make use of */
-	netdev->vlan_features |= netdev->hw_enc_features |
-				 NETIF_F_TSO_MANGLEID;
+	netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
 
 	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
 		netdev->hw_features |= NETIF_F_NTUPLE;
+	hw_features = hw_enc_features		|
+		      NETIF_F_HW_VLAN_CTAG_TX	|
+		      NETIF_F_HW_VLAN_CTAG_RX;
 
-	netdev->hw_features |= netdev->hw_enc_features	|
-			       NETIF_F_HW_VLAN_CTAG_TX	|
-			       NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features |= hw_features;
 
-	netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
+	netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
 
 	if (vsi->type == I40E_VSI_MAIN) {
 		SET_NETDEV_DEV(netdev, &pf->pdev->dev);
 		ether_addr_copy(mac_addr, hw->mac.perm_addr);
-		/* The following steps are necessary to prevent reception
-		 * of tagged packets - some older NVM configurations load a
-		 * default a MAC-VLAN filter that accepts any tagged packet
-		 * which must be replaced by a normal filter.
+		/* The following steps are necessary for two reasons. First,
+		 * some older NVM configurations load a default MAC-VLAN
+		 * filter that will accept any tagged packet, and we want to
+		 * replace this with a normal filter. Additionally, it is
+		 * possible our MAC address was provided by the platform using
+		 * Open Firmware or similar.
+		 *
+		 * Thus, we need to remove the default filter and install one
+		 * specific to the MAC address.
 		 */
 		i40e_rm_default_mac_filter(vsi, mac_addr);
 		spin_lock_bh(&vsi->mac_filter_hash_lock);
@@ -9481,9 +9465,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	netdev->netdev_ops = &i40e_netdev_ops;
 	netdev->watchdog_timeo = 5 * HZ;
 	i40e_set_ethtool_ops(netdev);
-#ifdef I40E_FCOE
-	i40e_fcoe_config_netdev(netdev, vsi);
-#endif
 
 	/* MTU range: 68 - 9706 */
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -9707,16 +9688,6 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
 		break;
 
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-		ret = i40e_fcoe_vsi_init(vsi, &ctxt);
-		if (ret) {
-			dev_info(&pf->pdev->dev, "failed to initialize FCoE VSI\n");
-			return ret;
-		}
-		break;
-
-#endif /* I40E_FCOE */
 	case I40E_VSI_IWARP:
 		/* send down message to iWARP */
 		break;
@@ -9743,7 +9714,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 	}
 
 	vsi->active_filters = 0;
-	clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+	clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 	/* If macvlan filters already exist, force them to get loaded */
 	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
@@ -9796,7 +9767,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		return -ENODEV;
 	}
 	if (vsi == pf->vsi[pf->lan_vsi] &&
-	    !test_bit(__I40E_DOWN, &pf->state)) {
+	    !test_bit(__I40E_VSI_DOWN, pf->state)) {
 		dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
 		return -ENODEV;
 	}
@@ -10133,7 +10104,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 			}
 		}
 	case I40E_VSI_VMDQ2:
-	case I40E_VSI_FCOE:
 		ret = i40e_config_netdev(vsi);
 		if (ret)
 			goto err_netdev;
@@ -10781,6 +10751,9 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 
 	i40e_ptp_init(pf);
 
+	/* repopulate tunnel port filters */
+	i40e_sync_udp_filters(pf);
+
 	return ret;
 }
 
@@ -10793,9 +10766,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	int queues_left;
 
 	pf->num_lan_qps = 0;
-#ifdef I40E_FCOE
-	pf->num_fcoe_qps = 0;
-#endif
 
 	/* Find the max queues to be put into basic use.  We'll always be
 	 * using TC0, whether or not DCB is running, and TC0 will get the
@@ -10812,9 +10782,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		/* make sure all the fancies are disabled */
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-			       I40E_FLAG_FCOE_ENABLED	|
-#endif
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_CAPABLE	|
@@ -10831,9 +10798,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-			       I40E_FLAG_FCOE_ENABLED	|
-#endif
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_ENABLED	|
@@ -10854,22 +10818,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		queues_left -= pf->num_lan_qps;
 	}
 
-#ifdef I40E_FCOE
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-		if (I40E_DEFAULT_FCOE <= queues_left) {
-			pf->num_fcoe_qps = I40E_DEFAULT_FCOE;
-		} else if (I40E_MINIMUM_FCOE <= queues_left) {
-			pf->num_fcoe_qps = I40E_MINIMUM_FCOE;
-		} else {
-			pf->num_fcoe_qps = 0;
-			pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
-			dev_info(&pf->pdev->dev, "not enough queues for FCoE. FCoE feature will be disabled\n");
-		}
-
-		queues_left -= pf->num_fcoe_qps;
-	}
-
-#endif
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
 		if (queues_left > 1) {
 			queues_left -= 1; /* save 1 queue for FD */
@@ -10901,9 +10849,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		pf->num_lan_qps, pf->alloc_rss_size, pf->num_req_vfs,
 		pf->num_vf_qps, pf->num_vmdq_vsis, pf->num_vmdq_qps,
 		queues_left);
-#ifdef I40E_FCOE
-	dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps);
-#endif
 }
 
 /**
@@ -10970,10 +10915,6 @@ static void i40e_print_features(struct i40e_pf *pf)
 	i += snprintf(&buf[i], REMAIN(i), " Geneve");
 	if (pf->flags & I40E_FLAG_PTP)
 		i += snprintf(&buf[i], REMAIN(i), " PTP");
-#ifdef I40E_FCOE
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED)
-		i += snprintf(&buf[i], REMAIN(i), " FCOE");
-#endif
 	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
 		i += snprintf(&buf[i], REMAIN(i), " VEB");
 	else
@@ -10986,20 +10927,18 @@ static void i40e_print_features(struct i40e_pf *pf)
 
 /**
  * i40e_get_platform_mac_addr - get platform-specific MAC address
- *
  * @pdev: PCI device information struct
  * @pf: board private structure
  *
- * Look up the MAC address in Open Firmware  on systems that support it,
- * and use IDPROM on SPARC if no OF address is found. On return, the
- * I40E_FLAG_PF_MAC will be wset in pf->flags if a platform-specific value
- * has been selected.
+ * Look up the MAC address for the device. First we'll try
+ * eth_platform_get_mac_address, which will check Open Firmware, or arch
+ * specific fallback. Otherwise, we'll default to the stored value in
+ * firmware.
  **/
 static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 {
-	pf->flags &= ~I40E_FLAG_PF_MAC;
-	if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
-		pf->flags |= I40E_FLAG_PF_MAC;
+	if (eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
+		i40e_get_mac_addr(&pf->hw, pf->hw.mac.addr);
 }
 
 /**
@@ -11064,7 +11003,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	pf->next_vsi = 0;
 	pf->pdev = pdev;
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 
 	hw = &pf->hw;
 	hw->back = pf;
@@ -11090,6 +11029,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->bus.bus_id = pdev->bus->number;
 	pf->instance = pfs_found;
 
+	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
 	/* set up the locks for the AQ, do this only once in probe
 	 * and destroy them only once in remove
 	 */
@@ -11188,8 +11130,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
-				hw->func_caps.num_rx_qp,
-				pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+				hw->func_caps.num_rx_qp, 0, 0);
 	if (err) {
 		dev_info(&pdev->dev, "init_lan_hmc failed: %d\n", err);
 		goto err_init_lan_hmc;
@@ -11211,9 +11152,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		i40e_aq_stop_lldp(hw, true, NULL);
 	}
 
-	i40e_get_mac_addr(hw, hw->mac.addr);
 	/* allow a platform config to override the HW addr */
 	i40e_get_platform_mac_addr(pdev, pf);
+
 	if (!is_valid_ether_addr(hw->mac.addr)) {
 		dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr);
 		err = -EIO;
@@ -11224,18 +11165,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	i40e_get_port_mac_addr(hw, hw->mac.port_addr);
 	if (is_valid_ether_addr(hw->mac.port_addr))
 		pf->flags |= I40E_FLAG_PORT_ID_VALID;
-#ifdef I40E_FCOE
-	err = i40e_get_san_mac_addr(hw, hw->mac.san_addr);
-	if (err)
-		dev_info(&pdev->dev,
-			 "(non-fatal) SAN MAC retrieval failed: %d\n", err);
-	if (!is_valid_ether_addr(hw->mac.san_addr)) {
-		dev_warn(&pdev->dev, "invalid SAN MAC address %pM, falling back to LAN MAC\n",
-			 hw->mac.san_addr);
-		ether_addr_copy(hw->mac.san_addr, hw->mac.addr);
-	}
-	dev_info(&pf->pdev->dev, "SAN MAC: %pM\n", hw->mac.san_addr);
-#endif /* I40E_FCOE */
 
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
@@ -11253,8 +11182,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pf->service_timer_period = HZ;
 
 	INIT_WORK(&pf->service_task, i40e_service_task);
-	clear_bit(__I40E_SERVICE_SCHED, &pf->state);
-	pf->flags |= I40E_FLAG_NEED_LINK_UPDATE;
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
 
 	/* NVM bit on means WoL disabled for the port */
 	i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits);
@@ -11292,7 +11220,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* prep for VF support */
 	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
-	    !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+	    !test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		if (pci_num_vf(pdev))
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 	}
@@ -11365,7 +11293,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * before setting up the misc vector or we get a race and the vector
 	 * ends up disabled forever.
 	 */
-	clear_bit(__I40E_DOWN, &pf->state);
+	clear_bit(__I40E_VSI_DOWN, pf->state);
 
 	/* In case of MSIX we are going to setup the misc vector right here
 	 * to handle admin queue events etc. In case of legacy and MSI
@@ -11385,7 +11313,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* prep for VF support */
 	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
-	    !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+	    !test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		/* disable link interrupts for VFs */
 		val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM);
 		val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK;
@@ -11426,16 +11354,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		  round_jiffies(jiffies + pf->service_timer_period));
 
 	/* add this PF to client device list and launch a client service task */
-	err = i40e_lan_add_device(pf);
-	if (err)
-		dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
-			 err);
-
-#ifdef I40E_FCOE
-	/* create FCoE interface */
-	i40e_fcoe_vsi_setup(pf);
+	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+		err = i40e_lan_add_device(pf);
+		if (err)
+			dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
+				 err);
+	}
 
-#endif
 #define PCI_SPEED_SIZE 8
 #define PCI_WIDTH_SIZE 8
 	/* Devices on the IOSF bus do not have this information
@@ -11523,7 +11448,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Unwind what we've done if something failed in the setup */
 err_vsis:
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 	i40e_clear_interrupt_scheme(pf);
 	kfree(pf->vsi);
 err_switch_setup:
@@ -11574,13 +11499,18 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
 
 	/* no more scheduling of any task */
-	set_bit(__I40E_SUSPENDED, &pf->state);
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_SUSPENDED, pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 	if (pf->service_timer.data)
 		del_timer_sync(&pf->service_timer);
 	if (pf->service_task.func)
 		cancel_work_sync(&pf->service_task);
 
+	/* Client close must be called explicitly here because the timer
+	 * has been stopped.
+	 */
+	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+
 	if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
 		i40e_free_vfs(pf);
 		pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
@@ -11607,10 +11537,11 @@ static void i40e_remove(struct pci_dev *pdev)
 		i40e_vsi_release(pf->vsi[pf->lan_vsi]);
 
 	/* remove attached clients */
-	ret_code = i40e_lan_del_device(pf);
-	if (ret_code) {
-		dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
-			 ret_code);
+	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+		ret_code = i40e_lan_del_device(pf);
+		if (ret_code)
+			dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+				 ret_code);
 	}
 
 	/* shutdown and destroy the HMC */
@@ -11677,9 +11608,9 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
 	}
 
 	/* shutdown all operations */
-	if (!test_bit(__I40E_SUSPENDED, &pf->state)) {
+	if (!test_bit(__I40E_SUSPENDED, pf->state)) {
 		rtnl_lock();
-		i40e_prep_for_reset(pf);
+		i40e_prep_for_reset(pf, true);
 		rtnl_unlock();
 	}
 
@@ -11744,11 +11675,11 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
-	if (test_bit(__I40E_SUSPENDED, &pf->state))
+	if (test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
 	rtnl_lock();
-	i40e_handle_reset_warning(pf);
+	i40e_handle_reset_warning(pf, true);
 	rtnl_unlock();
 }
 
@@ -11808,10 +11739,10 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 	struct i40e_hw *hw = &pf->hw;
 
-	set_bit(__I40E_SUSPENDED, &pf->state);
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_SUSPENDED, pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 	rtnl_lock();
-	i40e_prep_for_reset(pf);
+	i40e_prep_for_reset(pf, true);
 	rtnl_unlock();
 
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11821,11 +11752,16 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	cancel_work_sync(&pf->service_task);
 	i40e_fdir_teardown(pf);
 
+	/* Client close must be called explicitly here because the timer
+	 * has been stopped.
+	 */
+	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+
 	if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE))
 		i40e_enable_mc_magic_wake(pf);
 
 	rtnl_lock();
-	i40e_prep_for_reset(pf);
+	i40e_prep_for_reset(pf, true);
 	rtnl_unlock();
 
 	wr32(hw, I40E_PFPM_APM,
@@ -11852,14 +11788,14 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 	struct i40e_hw *hw = &pf->hw;
 	int retval = 0;
 
-	set_bit(__I40E_SUSPENDED, &pf->state);
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_SUSPENDED, pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 
 	if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE))
 		i40e_enable_mc_magic_wake(pf);
 
 	rtnl_lock();
-	i40e_prep_for_reset(pf);
+	i40e_prep_for_reset(pf, true);
 	rtnl_unlock();
 
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11904,10 +11840,10 @@ static int i40e_resume(struct pci_dev *pdev)
 	pci_wake_from_d3(pdev, false);
 
 	/* handling the reset will rebuild the device state */
-	if (test_and_clear_bit(__I40E_SUSPENDED, &pf->state)) {
-		clear_bit(__I40E_DOWN, &pf->state);
+	if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) {
+		clear_bit(__I40E_VSI_DOWN, pf->state);
 		rtnl_lock();
-		i40e_reset_and_rebuild(pf, false);
+		i40e_reset_and_rebuild(pf, false, true);
 		rtnl_unlock();
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 38ee18f11124..800bd55d0159 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 {
 	enum i40e_status_code ret_code = 0;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
-		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
-		if (!ret_code) {
+	ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+	if (!ret_code) {
+		if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
 			ret_code = i40e_read_nvm_word_aq(hw, offset, data);
-			i40e_release_nvm(hw);
+		} else {
+			ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
 		}
-	} else {
-		ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
+		i40e_release_nvm(hw);
 	}
 	return ret_code;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index fea81ed065db..80e66da6b145 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,4 @@ do {								\
 } while (0)
 
 typedef enum i40e_status_code i40e_status;
-#ifdef CONFIG_I40E_FCOE
-#define I40E_FCOE
-#endif
 #endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 2551fc827444..c56d976cf85a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -304,9 +304,6 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
 				 u32 pba_num_size);
 i40e_status i40e_validate_mac_addr(u8 *mac_addr);
 void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable);
-#ifdef I40E_FCOE
-i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr);
-#endif
 /* prototype for functions used for NVM access */
 i40e_status i40e_init_nvm(struct i40e_hw *hw);
 i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
@@ -380,4 +377,21 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
 u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
 i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
 				    u32 time, u32 interval);
+i40e_status i40e_aq_write_ppp(struct i40e_hw *hw, void *buff,
+			      u16 buff_size, u32 track_id,
+			      u32 *error_offset, u32 *error_info,
+			      struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_ppp_list(struct i40e_hw *hw, void *buff,
+				 u16 buff_size, u8 flags,
+				 struct i40e_asq_cmd_details *cmd_details);
+struct i40e_generic_seg_header *
+i40e_find_segment_in_package(u32 segment_type,
+			     struct i40e_package_header *pkg_header);
+enum i40e_status_code
+i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
+		   u32 track_id);
+enum i40e_status_code
+i40e_add_pinfo_to_list(struct i40e_hw *hw,
+		       struct i40e_profile_segment *profile,
+		       u8 *profile_info_sec, u32 track_id);
 #endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 2caee35528fa..18c1cc08da97 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -358,7 +358,7 @@ void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf)
 	skb_tstamp_tx(pf->ptp_tx_skb, &shhwtstamps);
 	dev_kfree_skb_any(pf->ptp_tx_skb);
 	pf->ptp_tx_skb = NULL;
-	clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, &pf->state);
+	clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state);
 }
 
 /**
@@ -768,7 +768,7 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 	if (pf->ptp_tx_skb) {
 		dev_kfree_skb_any(pf->ptp_tx_skb);
 		pf->ptp_tx_skb = NULL;
-		clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, &pf->state);
+		clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state);
 	}
 
 	if (pf->ptp_clock) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h
new file mode 100644
index 000000000000..d3e55f54a05e
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h
@@ -0,0 +1,229 @@
+/*******************************************************************************
+ *
+ * Intel(R) 40-10 Gigabit Ethernet Connection Network Driver
+ * Copyright(c) 2013 - 2017 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+/* Modeled on trace-events-sample.h */
+
+/* The trace subsystem name for i40e will be "i40e".
+ *
+ * This file is named i40e_trace.h.
+ *
+ * Since this include file's name is different from the trace
+ * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end
+ * of this file.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM i40e
+
+/* See trace-events-sample.h for a detailed description of why this
+ * guard clause is different from most normal include files.
+ */
+#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _I40E_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+/**
+ * i40e_trace() macro enables shared code to refer to trace points
+ * like:
+ *
+ * trace_i40e{,vf}_example(args...)
+ *
+ * ... as:
+ *
+ * i40e_trace(example, args...)
+ *
+ * ... to resolve to the PF or VF version of the tracepoint without
+ * ifdefs, and to allow tracepoints to be disabled entirely at build
+ * time.
+ *
+ * Trace point should always be referred to in the driver via this
+ * macro.
+ *
+ * Similarly, i40e_trace_enabled(trace_name) wraps references to
+ * trace_i40e{,vf}_<trace_name>_enabled() functions.
+ */
+#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40e ## _ ## trace_name)
+#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name)
+
+#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args)
+
+#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)()
+
+/* Events common to PF and VF. Corresponding versions will be defined
+ * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace()
+ * macro above will select the right trace point name for the driver
+ * being built from shared code.
+ */
+
+/* Events related to a vsi & ring */
+DECLARE_EVENT_CLASS(
+	i40e_tx_template,
+
+	TP_PROTO(struct i40e_ring *ring,
+		 struct i40e_tx_desc *desc,
+		 struct i40e_tx_buffer *buf),
+
+	TP_ARGS(ring, desc, buf),
+
+	/* The convention here is to make the first fields in the
+	 * TP_STRUCT match the TP_PROTO exactly. This enables the use
+	 * of the args struct generated by the tplist tool (from the
+	 * bcc-tools package) to be used for those fields. To access
+	 * fields other than the tracepoint args will require the
+	 * tplist output to be adjusted.
+	 */
+	TP_STRUCT__entry(
+		__field(void*, ring)
+		__field(void*, desc)
+		__field(void*, buf)
+		__string(devname, ring->netdev->name)
+	),
+
+	TP_fast_assign(
+		__entry->ring = ring;
+		__entry->desc = desc;
+		__entry->buf = buf;
+		__assign_str(devname, ring->netdev->name);
+	),
+
+	TP_printk(
+		"netdev: %s ring: %p desc: %p buf %p",
+		__get_str(devname), __entry->ring,
+		__entry->desc, __entry->buf)
+);
+
+DEFINE_EVENT(
+	i40e_tx_template, i40e_clean_tx_irq,
+	TP_PROTO(struct i40e_ring *ring,
+		 struct i40e_tx_desc *desc,
+		 struct i40e_tx_buffer *buf),
+
+	TP_ARGS(ring, desc, buf));
+
+DEFINE_EVENT(
+	i40e_tx_template, i40e_clean_tx_irq_unmap,
+	TP_PROTO(struct i40e_ring *ring,
+		 struct i40e_tx_desc *desc,
+		 struct i40e_tx_buffer *buf),
+
+	TP_ARGS(ring, desc, buf));
+
+DECLARE_EVENT_CLASS(
+	i40e_rx_template,
+
+	TP_PROTO(struct i40e_ring *ring,
+		 union i40e_32byte_rx_desc *desc,
+		 struct sk_buff *skb),
+
+	TP_ARGS(ring, desc, skb),
+
+	TP_STRUCT__entry(
+		__field(void*, ring)
+		__field(void*, desc)
+		__field(void*, skb)
+		__string(devname, ring->netdev->name)
+	),
+
+	TP_fast_assign(
+		__entry->ring = ring;
+		__entry->desc = desc;
+		__entry->skb = skb;
+		__assign_str(devname, ring->netdev->name);
+	),
+
+	TP_printk(
+		"netdev: %s ring: %p desc: %p skb %p",
+		__get_str(devname), __entry->ring,
+		__entry->desc, __entry->skb)
+);
+
+DEFINE_EVENT(
+	i40e_rx_template, i40e_clean_rx_irq,
+	TP_PROTO(struct i40e_ring *ring,
+		 union i40e_32byte_rx_desc *desc,
+		 struct sk_buff *skb),
+
+	TP_ARGS(ring, desc, skb));
+
+DEFINE_EVENT(
+	i40e_rx_template, i40e_clean_rx_irq_rx,
+	TP_PROTO(struct i40e_ring *ring,
+		 union i40e_32byte_rx_desc *desc,
+		 struct sk_buff *skb),
+
+	TP_ARGS(ring, desc, skb));
+
+DECLARE_EVENT_CLASS(
+	i40e_xmit_template,
+
+	TP_PROTO(struct sk_buff *skb,
+		 struct i40e_ring *ring),
+
+	TP_ARGS(skb, ring),
+
+	TP_STRUCT__entry(
+		__field(void*, skb)
+		__field(void*, ring)
+		__string(devname, ring->netdev->name)
+	),
+
+	TP_fast_assign(
+		__entry->skb = skb;
+		__entry->ring = ring;
+		__assign_str(devname, ring->netdev->name);
+	),
+
+	TP_printk(
+		"netdev: %s skb: %p ring: %p",
+		__get_str(devname), __entry->skb,
+		__entry->ring)
+);
+
+DEFINE_EVENT(
+	i40e_xmit_template, i40e_xmit_frame_ring,
+	TP_PROTO(struct sk_buff *skb,
+		 struct i40e_ring *ring),
+
+	TP_ARGS(skb, ring));
+
+DEFINE_EVENT(
+	i40e_xmit_template, i40e_xmit_frame_ring_drop,
+	TP_PROTO(struct sk_buff *skb,
+		 struct i40e_ring *ring),
+
+	TP_ARGS(skb, ring));
+
+/* Events unique to the PF. */
+
+#endif /* _I40E_TRACE_H_ */
+/* This must be outside ifdef _I40E_TRACE_H */
+
+/* This trace include file is not located in the .../include/trace
+ * with the kernel tracepoint definitions, because we're a loadable
+ * module.
+ */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE i40e_trace
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 97d46058d71d..29321a6167a6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -27,6 +27,7 @@
 #include <linux/prefetch.h>
 #include <net/busy_poll.h>
 #include "i40e.h"
+#include "i40e_trace.h"
 #include "i40e_prototype.h"
 
 static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
@@ -71,6 +72,9 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
 	flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
 		      (fdata->pctype << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
 
+	flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
+		      (fdata->flex_offset << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT);
+
 	/* Use LAN VSI Id if not programmed by user */
 	flex_ptype |= I40E_TXD_FLTR_QW0_DEST_VSI_MASK &
 		      ((u32)(fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id) <<
@@ -203,7 +207,6 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 	struct i40e_pf *pf = vsi->back;
 	struct udphdr *udp;
 	struct iphdr *ip;
-	bool err = false;
 	u8 *raw_packet;
 	int ret;
 	static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
@@ -219,18 +222,28 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 	udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET
 	      + sizeof(struct iphdr));
 
-	ip->daddr = fd_data->dst_ip[0];
+	ip->daddr = fd_data->dst_ip;
 	udp->dest = fd_data->dst_port;
-	ip->saddr = fd_data->src_ip[0];
+	ip->saddr = fd_data->src_ip;
 	udp->source = fd_data->src_port;
 
+	if (fd_data->flex_filter) {
+		u8 *payload = raw_packet + I40E_UDPIP_DUMMY_PACKET_LEN;
+		__be16 pattern = fd_data->flex_word;
+		u16 off = fd_data->flex_offset;
+
+		*((__force __be16 *)(payload + off)) = pattern;
+	}
+
 	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
 	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
 			 fd_data->pctype, fd_data->fd_id, ret);
-		err = true;
+		/* Free the packet buffer since it wasn't added to the ring */
+		kfree(raw_packet);
+		return -EOPNOTSUPP;
 	} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
 		if (add)
 			dev_info(&pf->pdev->dev,
@@ -241,10 +254,13 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 				 "Filter deleted for PCTYPE %d loc = %d\n",
 				 fd_data->pctype, fd_data->fd_id);
 	}
-	if (err)
-		kfree(raw_packet);
 
-	return err ? -EOPNOTSUPP : 0;
+	if (add)
+		pf->fd_udp4_filter_cnt++;
+	else
+		pf->fd_udp4_filter_cnt--;
+
+	return 0;
 }
 
 #define I40E_TCPIP_DUMMY_PACKET_LEN 54
@@ -263,7 +279,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	struct i40e_pf *pf = vsi->back;
 	struct tcphdr *tcp;
 	struct iphdr *ip;
-	bool err = false;
 	u8 *raw_packet;
 	int ret;
 	/* Dummy packet */
@@ -281,39 +296,110 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET
 	      + sizeof(struct iphdr));
 
-	ip->daddr = fd_data->dst_ip[0];
+	ip->daddr = fd_data->dst_ip;
 	tcp->dest = fd_data->dst_port;
-	ip->saddr = fd_data->src_ip[0];
+	ip->saddr = fd_data->src_ip;
 	tcp->source = fd_data->src_port;
 
+	if (fd_data->flex_filter) {
+		u8 *payload = raw_packet + I40E_TCPIP_DUMMY_PACKET_LEN;
+		__be16 pattern = fd_data->flex_word;
+		u16 off = fd_data->flex_offset;
+
+		*((__force __be16 *)(payload + off)) = pattern;
+	}
+
+	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
+			 fd_data->pctype, fd_data->fd_id, ret);
+		/* Free the packet buffer since it wasn't added to the ring */
+		kfree(raw_packet);
+		return -EOPNOTSUPP;
+	} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
+		if (add)
+			dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n",
+				 fd_data->pctype, fd_data->fd_id);
+		else
+			dev_info(&pf->pdev->dev,
+				 "Filter deleted for PCTYPE %d loc = %d\n",
+				 fd_data->pctype, fd_data->fd_id);
+	}
+
 	if (add) {
-		pf->fd_tcp_rule++;
+		pf->fd_tcp4_filter_cnt++;
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
-		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+		pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED;
 	} else {
-		pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ?
-				  (pf->fd_tcp_rule - 1) : 0;
-		if (pf->fd_tcp_rule == 0) {
-			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
-			    I40E_DEBUG_FD & pf->hw.debug_mask)
-				dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-		}
+		pf->fd_tcp4_filter_cnt--;
 	}
 
-	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
-	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+	return 0;
+}
+
+#define I40E_SCTPIP_DUMMY_PACKET_LEN 46
+/**
+ * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
+				    struct i40e_fdir_filter *fd_data,
+				    bool add)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct sctphdr *sctp;
+	struct iphdr *ip;
+	u8 *raw_packet;
+	int ret;
+	/* Dummy packet */
+	static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
+		0x45, 0, 0, 0x20, 0, 0, 0x40, 0, 0x40, 0x84, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+
+	raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL);
+	if (!raw_packet)
+		return -ENOMEM;
+	memcpy(raw_packet, packet, I40E_SCTPIP_DUMMY_PACKET_LEN);
+
+	ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
+	sctp = (struct sctphdr *)(raw_packet + IP_HEADER_OFFSET
+	      + sizeof(struct iphdr));
 
+	ip->daddr = fd_data->dst_ip;
+	sctp->dest = fd_data->dst_port;
+	ip->saddr = fd_data->src_ip;
+	sctp->source = fd_data->src_port;
+
+	if (fd_data->flex_filter) {
+		u8 *payload = raw_packet + I40E_SCTPIP_DUMMY_PACKET_LEN;
+		__be16 pattern = fd_data->flex_word;
+		u16 off = fd_data->flex_offset;
+
+		*((__force __be16 *)(payload + off)) = pattern;
+	}
+
+	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
 			 fd_data->pctype, fd_data->fd_id, ret);
-		err = true;
+		/* Free the packet buffer since it wasn't added to the ring */
+		kfree(raw_packet);
+		return -EOPNOTSUPP;
 	} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
 		if (add)
-			dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n",
+			dev_info(&pf->pdev->dev,
+				 "Filter OK for PCTYPE %d loc = %d\n",
 				 fd_data->pctype, fd_data->fd_id);
 		else
 			dev_info(&pf->pdev->dev,
@@ -321,10 +407,12 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 				 fd_data->pctype, fd_data->fd_id);
 	}
 
-	if (err)
-		kfree(raw_packet);
+	if (add)
+		pf->fd_sctp4_filter_cnt++;
+	else
+		pf->fd_sctp4_filter_cnt--;
 
-	return err ? -EOPNOTSUPP : 0;
+	return 0;
 }
 
 #define I40E_IP_DUMMY_PACKET_LEN 34
@@ -343,7 +431,6 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 {
 	struct i40e_pf *pf = vsi->back;
 	struct iphdr *ip;
-	bool err = false;
 	u8 *raw_packet;
 	int ret;
 	int i;
@@ -359,18 +446,29 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 		memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN);
 		ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
 
-		ip->saddr = fd_data->src_ip[0];
-		ip->daddr = fd_data->dst_ip[0];
+		ip->saddr = fd_data->src_ip;
+		ip->daddr = fd_data->dst_ip;
 		ip->protocol = 0;
 
+		if (fd_data->flex_filter) {
+			u8 *payload = raw_packet + I40E_IP_DUMMY_PACKET_LEN;
+			__be16 pattern = fd_data->flex_word;
+			u16 off = fd_data->flex_offset;
+
+			*((__force __be16 *)(payload + off)) = pattern;
+		}
+
 		fd_data->pctype = i;
 		ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
-
 		if (ret) {
 			dev_info(&pf->pdev->dev,
 				 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
 				 fd_data->pctype, fd_data->fd_id, ret);
-			err = true;
+			/* The packet buffer wasn't added to the ring so we
+			 * need to free it now.
+			 */
+			kfree(raw_packet);
+			return -EOPNOTSUPP;
 		} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
 			if (add)
 				dev_info(&pf->pdev->dev,
@@ -383,10 +481,12 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 		}
 	}
 
-	if (err)
-		kfree(raw_packet);
+	if (add)
+		pf->fd_ip4_filter_cnt++;
+	else
+		pf->fd_ip4_filter_cnt--;
 
-	return err ? -EOPNOTSUPP : 0;
+	return 0;
 }
 
 /**
@@ -409,6 +509,9 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 	case UDP_V4_FLOW:
 		ret = i40e_add_del_fdir_udpv4(vsi, input, add);
 		break;
+	case SCTP_V4_FLOW:
+		ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
+		break;
 	case IP_USER_FLOW:
 		switch (input->ip4_proto) {
 		case IPPROTO_TCP:
@@ -417,19 +520,23 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 		case IPPROTO_UDP:
 			ret = i40e_add_del_fdir_udpv4(vsi, input, add);
 			break;
+		case IPPROTO_SCTP:
+			ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
+			break;
 		case IPPROTO_IP:
 			ret = i40e_add_del_fdir_ipv4(vsi, input, add);
 			break;
 		default:
 			/* We cannot support masking based on protocol */
-			goto unsupported_flow;
+			dev_info(&pf->pdev->dev, "Unsupported IPv4 protocol 0x%02x\n",
+				 input->ip4_proto);
+			return -EINVAL;
 		}
 		break;
 	default:
-unsupported_flow:
-		dev_info(&pf->pdev->dev, "Could not specify spec type %d\n",
+		dev_info(&pf->pdev->dev, "Unsupported flow type 0x%02x\n",
 			 input->flow_type);
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
 	/* The buffer allocated here will be normally be freed by
@@ -476,7 +583,7 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		 * progress do nothing, once flush is complete the state will
 		 * be cleared.
 		 */
-		if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+		if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 			return;
 
 		pf->fd_add_err++;
@@ -484,9 +591,9 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
 
 		if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
-			pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
-			set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
+		    pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED) {
+			pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED;
+			set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
 		}
 
 		/* filter programming failed most likely due to table full */
@@ -498,12 +605,10 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		 */
 		if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
 			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
-			    !(pf->auto_disable_flags &
-				     I40E_FLAG_FD_SB_ENABLED)) {
+			    !(pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED)) {
+				pf->flags |= I40E_FLAG_FD_SB_AUTO_DISABLED;
 				if (I40E_DEBUG_FD & pf->hw.debug_mask)
 					dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
-				pf->auto_disable_flags |=
-							I40E_FLAG_FD_SB_ENABLED;
 			}
 		}
 	} else if (error == BIT(I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) {
@@ -599,19 +704,15 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring)
 /**
  * i40e_get_tx_pending - how many tx descriptors not processed
  * @tx_ring: the ring of descriptors
- * @in_sw: is tx_pending being checked in SW or HW
  *
  * Since there is no access to the ring head register
  * in XL710, we need to use our local copies
  **/
-u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
+u32 i40e_get_tx_pending(struct i40e_ring *ring)
 {
 	u32 head, tail;
 
-	if (!in_sw)
-		head = i40e_get_head(ring);
-	else
-		head = ring->next_to_clean;
+	head = i40e_get_head(ring);
 	tail = readl(ring->tail);
 
 	if (head != tail)
@@ -657,6 +758,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		/* prevent any other reads prior to eop_desc */
 		read_barrier_depends();
 
+		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */
 		if (tx_head == tx_desc)
 			break;
@@ -683,6 +785,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
+			i40e_trace(clean_tx_irq_unmap,
+				   tx_ring, tx_desc, tx_buf);
 
 			tx_buf++;
 			tx_desc++;
@@ -734,11 +838,11 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		 * them to be written back in case we stay in NAPI.
 		 * In this mode on X722 we do not enable Interrupt.
 		 */
-		unsigned int j = i40e_get_tx_pending(tx_ring, false);
+		unsigned int j = i40e_get_tx_pending(tx_ring);
 
 		if (budget &&
 		    ((j / WB_STRIDE) == 0) && (j > 0) &&
-		    !test_bit(__I40E_DOWN, &vsi->state) &&
+		    !test_bit(__I40E_VSI_DOWN, vsi->state) &&
 		    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
 			tx_ring->arm_wb = true;
 	}
@@ -756,7 +860,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->queue_index) &&
-		   !test_bit(__I40E_DOWN, &vsi->state)) {
+		   !test_bit(__I40E_VSI_DOWN, vsi->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 			++tx_ring->tx_stats.restart_queue;
@@ -930,9 +1034,29 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 }
 
 /**
+ * i40e_rx_is_programming_status - check for programming status descriptor
+ * @qw: qword representing status_error_len in CPU ordering
+ *
+ * The value of in the descriptor length field indicate if this
+ * is a programming status descriptor for flow director or FCoE
+ * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
+ * it is a packet descriptor.
+ **/
+static inline bool i40e_rx_is_programming_status(u64 qw)
+{
+	/* The Rx filter programming status and SPH bit occupy the same
+	 * spot in the descriptor. Since we don't support packet split we
+	 * can just reuse the bit as an indication that this is a
+	 * programming status descriptor.
+	 */
+	return qw & I40E_RXD_QW1_LENGTH_SPH_MASK;
+}
+
+/**
  * i40e_clean_programming_status - clean the programming status descriptor
  * @rx_ring: the rx ring that has this descriptor
  * @rx_desc: the rx descriptor written back by HW
+ * @qw: qword representing status_error_len in CPU ordering
  *
  * Flow director should handle FD_FILTER_STATUS to check its filter programming
  * status being successful or not and take actions accordingly. FCoE should
@@ -940,22 +1064,23 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
  *
  **/
 static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
-					  union i40e_rx_desc *rx_desc)
+					  union i40e_rx_desc *rx_desc,
+					  u64 qw)
 {
-	u64 qw;
+	u32 ntc = rx_ring->next_to_clean + 1;
 	u8 id;
 
-	qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+	/* fetch, update, and store next to clean */
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+
+	prefetch(I40E_RX_DESC(rx_ring, ntc));
+
 	id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
 		  I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
 
 	if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
 		i40e_fd_handle_status(rx_ring, rx_desc, id);
-#ifdef I40E_FCOE
-	else if ((id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS) ||
-		 (id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS))
-		i40e_fcoe_handle_status(rx_ring, rx_desc, id);
-#endif
 }
 
 /**
@@ -1010,7 +1135,6 @@ err:
  **/
 void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -1030,8 +1154,22 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
-		__free_pages(rx_bi->page, 0);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->dma,
+					      rx_bi->page_offset,
+					      rx_ring->rx_buf_len,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     i40e_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
+
+		__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
 
 		rx_bi->page = NULL;
 		rx_bi->page_offset = 0;
@@ -1132,6 +1270,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
 }
 
 /**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
+/**
  * i40e_alloc_mapped_page - recycle or make a new page
  * @rx_ring: ring to use
  * @bi: rx_buffer struct to modify
@@ -1152,27 +1301,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* alloc new page for storage */
-	page = dev_alloc_page();
+	page = dev_alloc_pages(i40e_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_page_failed++;
 		return false;
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 i40e_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 I40E_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
 	 */
 	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_pages(page, 0);
+		__free_pages(page, i40e_rx_pg_order(rx_ring));
 		rx_ring->rx_stats.alloc_page_failed++;
 		return false;
 	}
 
 	bi->dma = dma;
 	bi->page = page;
-	bi->page_offset = 0;
+	bi->page_offset = i40e_rx_offset(rx_ring);
+
+	/* initialize pagecnt_bias to 1 representing we fully own page */
+	bi->pagecnt_bias = 1;
 
 	return true;
 }
@@ -1219,6 +1374,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 rx_ring->rx_buf_len,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -1259,8 +1420,6 @@ no_buffers:
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
  **/
 static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    struct sk_buff *skb,
@@ -1422,12 +1581,12 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 
 	i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 
-	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
 	i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
+
+	/* modifies the skb - consumes the enet header */
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
 /**
@@ -1472,7 +1631,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 /**
@@ -1493,8 +1655,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
  * the adapter for another receive
  *
  * @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
  *
  * If page is reusable, rx_buffer->page_offset is adjusted to point to
  * an unused region in the page.
@@ -1517,13 +1677,10 @@ static inline bool i40e_page_is_reusable(struct page *page)
  *
  * In either case, if the page is reusable its refcount is increased.
  **/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
-				   struct page *page,
-				   const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 {
-#if (PAGE_SIZE >= 8192)
-	unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
-#endif
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* Is any reuse possible? */
 	if (unlikely(!i40e_page_is_reusable(page)))
@@ -1531,21 +1688,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
-	if (rx_buffer->page_offset > last_offset)
+#define I40E_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048)
+	if (rx_buffer->page_offset > I40E_LAST_OFFSET)
 		return false;
 #endif
 
-	/* Inc ref count on page before passing it up to the stack */
-	get_page(page);
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
+	 */
+	if (unlikely(!pagecnt_bias)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
@@ -1554,145 +1713,201 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
  * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
  * @rx_buffer: buffer containing page to add
- * @size: packet length from rx_desc
  * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
  *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
  **/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
 			     struct i40e_rx_buffer *rx_buffer,
-			     unsigned int size,
-			     struct sk_buff *skb)
+			     struct sk_buff *skb,
+			     unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = I40E_RXBUFFER_2048;
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
 #endif
-	unsigned int pull_len;
-
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
-
-	/* will the data fit in the skb we allocated? if so, just
-	 * copy it as it is pretty small anyway
-	 */
-	if (size <= I40E_RX_HDR_SIZE) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
 
-		/* page is reusable, we can reuse buffer as-is */
-		if (likely(i40e_page_is_reusable(page)))
-			return true;
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
 
-		/* this page cannot be reused so discard it */
-		__free_pages(page, 0);
-		return false;
-	}
+	/* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
 
-	/* we need the header to contain the greater of either
-	 * ETH_HLEN or 60 bytes if the skb->len is less than
-	 * 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+/**
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @size: size of buffer to add to skb
+ *
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
+ */
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+						 const unsigned int size)
+{
+	struct i40e_rx_buffer *rx_buffer;
 
-	/* align pull length to size of long to optimize
-	 * memcpy performance
-	 */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
 
-	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
 
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	/* We have pulled a buffer for use, so decrement pagecnt_bias */
+	rx_buffer->pagecnt_bias--;
 
-	return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+	return rx_buffer;
 }
 
 /**
- * i40e_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
  *
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function allocates an skb.  It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
  */
-static inline
-struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
-				     union i40e_rx_desc *rx_desc,
-				     struct sk_buff *skb)
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+					  struct i40e_rx_buffer *rx_buffer,
+					  unsigned int size)
 {
-	u64 local_status_error_len =
-		le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	unsigned int size =
-		(local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
-	struct i40e_rx_buffer *rx_buffer;
-	struct page *page;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	unsigned int headlen;
+	struct sk_buff *skb;
 
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       I40E_RX_HDR_SIZE,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > I40E_RX_HDR_SIZE)
+		headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+	/* update all of the pointers */
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				rx_buffer->page_offset + headlen,
+				size, truesize);
 
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) + rx_buffer->page_offset;
+		/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		/* buffer is unused, reset bias back to rx_buffer */
+		rx_buffer->pagecnt_bias++;
+	}
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	return skb;
+}
+
+/**
+ * i40e_build_skb - Build skb around an existing buffer
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buffer: Rx buffer to pull data from
+ * @size: size of buffer to add to skb
+ *
+ * This function builds an skb around an existing Rx buffer, taking care
+ * to set up the skb correctly and avoid any memcpy overhead.
+ */
+static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
+				      struct i40e_rx_buffer *rx_buffer,
+				      unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
+	/* build an skb around the page buffer */
+	skb = build_skb(va - I40E_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* allocate a skb to store the frags */
-		skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-				       I40E_RX_HDR_SIZE,
-				       GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_buff_failed++;
-			return NULL;
-		}
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, I40E_SKB_PAD);
+	__skb_put(skb, size);
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
-	}
+	/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
 
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
+	return skb;
+}
 
-	/* pull page into skb */
-	if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer.  It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+			       struct i40e_rx_buffer *rx_buffer)
+{
+	if (i40e_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		i40e_reuse_rx_page(rx_ring, rx_buffer);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     i40e_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of buffer_info */
 	rx_buffer->page = NULL;
-
-	return skb;
 }
 
 /**
@@ -1718,11 +1933,6 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 
 	prefetch(I40E_RX_DESC(rx_ring, ntc));
 
-#define staterrlen rx_desc->wb.qword1.status_error_len
-	if (unlikely(i40e_rx_is_programming_status(le64_to_cpu(staterrlen)))) {
-		i40e_clean_programming_status(rx_ring, rx_desc);
-		return true;
-	}
 	/* if we are the last buffer then there is nothing else to do */
 #define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT)
 	if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF)))
@@ -1753,7 +1963,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < budget)) {
+		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
+		unsigned int size;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1770,22 +1982,44 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		 * hardware wrote DD then the length will be non-zero
 		 */
-		if (!i40e_test_staterr(rx_desc,
-				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
-			break;
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 
 		/* This memory barrier is needed to keep us from reading
-		 * any other fields out of the rx_desc until we know the
-		 * DD bit is set.
+		 * any other fields out of the rx_desc until we have
+		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
 
-		skb = i40e_fetch_rx_buffer(rx_ring, rx_desc, skb);
-		if (!skb)
+		if (unlikely(i40e_rx_is_programming_status(qword))) {
+			i40e_clean_programming_status(rx_ring, rx_desc, qword);
+			continue;
+		}
+		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		if (!size)
 			break;
 
+		i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb);
+		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+		/* retrieve a buffer from the ring */
+		if (skb)
+			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = i40e_build_skb(rx_ring, rx_buffer, size);
+		else
+			skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			rx_buffer->pagecnt_bias++;
+			break;
+		}
+
+		i40e_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1798,6 +2032,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
 			dev_kfree_skb_any(skb);
+			skb = NULL;
 			continue;
 		}
 
@@ -1816,18 +2051,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* populate checksum, VLAN, and protocol */
 		i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
-#ifdef I40E_FCOE
-		if (unlikely(
-		    i40e_rx_is_fcoe(rx_ptype) &&
-		    !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
-			dev_kfree_skb_any(skb);
-			continue;
-		}
-#endif
-
 		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
 
+		i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 		skb = NULL;
 
@@ -1944,7 +2171,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	}
 
 enable_int:
-	if (!test_bit(__I40E_DOWN, &vsi->state))
+	if (!test_bit(__I40E_VSI_DOWN, vsi->state))
 		wr32(hw, INTREG(vector - 1), txval);
 
 	if (q_vector->itr_countdown)
@@ -1973,13 +2200,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	int budget_per_ring;
 	int work_done = 0;
 
-	if (test_bit(__I40E_DOWN, &vsi->state)) {
+	if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
 		napi_complete(napi);
 		return 0;
 	}
 
-	/* Clear hung_detected bit */
-	clear_bit(I40E_Q_VECTOR_HUNG_DETECT, &q_vector->hung_detected);
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
@@ -2079,7 +2304,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 
-	if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED)
 		return;
 
 	/* if sampling is disabled do nothing */
@@ -2113,10 +2338,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	th = (struct tcphdr *)(hdr.network + hlen);
 
 	/* Due to lack of space, no more new filters can be programmed */
-	if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	if (th->syn && (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED))
 		return;
-	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
+	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) {
 		/* HW ATR eviction will take care of removing filters on FIN
 		 * and RST packets.
 		 */
@@ -2178,8 +2402,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
 			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
-	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
+	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
 		dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
@@ -2200,15 +2423,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * Returns error code indicate the frame should be dropped upon error and the
  * otherwise  returns 0 to indicate the flags has been set properly.
  **/
-#ifdef I40E_FCOE
-inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring,
-				      u32 *flags)
-#else
 static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 					     struct i40e_ring *tx_ring,
 					     u32 *flags)
-#endif
 {
 	__be16 protocol = skb->protocol;
 	u32  tx_flags = 0;
@@ -2409,7 +2626,7 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		return 0;
 
 	if (pf->ptp_tx &&
-	    !test_and_set_bit_lock(__I40E_PTP_TX_IN_PROGRESS, &pf->state)) {
+	    !test_and_set_bit_lock(__I40E_PTP_TX_IN_PROGRESS, pf->state)) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		pf->ptp_tx_skb = skb_get(skb);
 	} else {
@@ -2716,15 +2933,9 @@ bool __i40e_chk_linearize(struct sk_buff *skb)
  * @td_cmd:   the command field in the descriptor
  * @td_offset: offset for checksum or crc
  **/
-#ifdef I40E_FCOE
-inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
-			struct i40e_tx_buffer *first, u32 tx_flags,
-			const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#else
 static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			       struct i40e_tx_buffer *first, u32 tx_flags,
 			       const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#endif
 {
 	unsigned int data_len = skb->data_len;
 	unsigned int size = skb_headlen(skb);
@@ -2925,6 +3136,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	/* prefetch the data, we'll need it later */
 	prefetch(skb->data);
 
+	i40e_trace(xmit_frame_ring, skb, tx_ring);
+
 	count = i40e_xmit_descriptor_count(skb);
 	if (i40e_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb)) {
@@ -3003,6 +3216,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 out_drop:
+	i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring);
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index f80979025c01..f5de51124cae 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -117,10 +117,9 @@ enum i40e_dyn_idx_t {
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
+#define I40E_RXBUFFER_1536  1536  /* 128B aligned standard Ethernet frame */
 #define I40E_RXBUFFER_2048  2048
-#define I40E_RXBUFFER_3072  3072   /* For FCoE MTU of 2158 */
-#define I40E_RXBUFFER_4096  4096
-#define I40E_RXBUFFER_8192  8192
+#define I40E_RXBUFFER_3072  3072  /* Used for large frames w/ padding */
 #define I40E_MAX_RXBUFFER   9728  /* largest size for single descriptor */
 
 /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
@@ -133,6 +132,61 @@ enum i40e_dyn_idx_t {
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+/* Attempt to maximize the headroom available for incoming frames.  We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame.  This leaves us with 512 bytes of room.  From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ *	 up negative.  In these cases we should fall back to the legacy
+ *	 receive path.
+ */
+#if (PAGE_SIZE < 8192)
+#define I40E_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048))
+
+static inline int i40e_compute_pad(int rx_buf_len)
+{
+	int page_size, pad_size;
+
+	page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+	pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+	return pad_size;
+}
+
+static inline int i40e_skb_pad(void)
+{
+	int rx_buf_len;
+
+	/* If a 2K buffer cannot handle a standard Ethernet frame then
+	 * optimize padding for a 3K buffer instead of a 1.5K buffer.
+	 *
+	 * For a 3K buffer we need to add enough padding to allow for
+	 * tailroom due to NET_IP_ALIGN possibly shifting us out of
+	 * cache-line alignment.
+	 */
+	if (I40E_2K_TOO_SMALL_WITH_PADDING)
+		rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
+	else
+		rx_buf_len = I40E_RXBUFFER_1536;
+
+	/* if needed make room for NET_IP_ALIGN */
+	rx_buf_len -= NET_IP_ALIGN;
+
+	return i40e_compute_pad(rx_buf_len);
+}
+
+#define I40E_SKB_PAD i40e_skb_pad()
+#else
+#define I40E_2K_TOO_SMALL_WITH_PADDING false
+#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#endif
+
 /**
  * i40e_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -255,7 +309,12 @@ struct i40e_tx_buffer {
 struct i40e_rx_buffer {
 	dma_addr_t dma;
 	struct page *page;
-	unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
 };
 
 struct i40e_queue_stats {
@@ -269,7 +328,6 @@ struct i40e_tx_queue_stats {
 	u64 tx_done_old;
 	u64 tx_linearize;
 	u64 tx_force_wb;
-	u64 tx_lost_interrupt;
 };
 
 struct i40e_rx_queue_stats {
@@ -335,7 +393,8 @@ struct i40e_ring {
 	u8 packet_stride;
 
 	u16 flags;
-#define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
+#define I40E_TXR_FLAGS_WB_ON_ITR		BIT(0)
+#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED	BIT(1)
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
@@ -363,6 +422,21 @@ struct i40e_ring {
 					 */
 } ____cacheline_internodealigned_in_smp;
 
+static inline bool ring_uses_build_skb(struct i40e_ring *ring)
+{
+	return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED);
+}
+
+static inline void set_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+	ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
+static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+	ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
 enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
@@ -384,6 +458,17 @@ struct i40e_ring_container {
 #define i40e_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
+static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring->rx_buf_len > (PAGE_SIZE / 2))
+		return 1;
+#endif
+	return 0;
+}
+
+#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring))
+
 bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
 netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
 void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
@@ -393,15 +478,8 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring);
 void i40e_free_tx_resources(struct i40e_ring *tx_ring);
 void i40e_free_rx_resources(struct i40e_ring *rx_ring);
 int i40e_napi_poll(struct napi_struct *napi, int budget);
-#ifdef I40E_FCOE
-void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		 struct i40e_tx_buffer *first, u32 tx_flags,
-		 const u8 hdr_len, u32 td_cmd, u32 td_offset);
-int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-			       struct i40e_ring *tx_ring, u32 *flags);
-#endif
 void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
-u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
+u32 i40e_get_tx_pending(struct i40e_ring *ring);
 int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
 
@@ -483,16 +561,6 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
 }
 
 /**
- * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
- * @ptype: the packet type field from Rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
-	return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
-	       (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
-/**
  * txring_txq - Find the netdev Tx ring based on the i40e Tx ring
  * @ring: Tx ring to find the netdev equivalent of
  **/
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 939f9fdc8f85..3a18ed13edc4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -78,6 +78,7 @@ enum i40e_debug_mask {
 	I40E_DEBUG_DCB			= 0x00000400,
 	I40E_DEBUG_DIAG			= 0x00000800,
 	I40E_DEBUG_FD			= 0x00001000,
+	I40E_DEBUG_PACKAGE		= 0x00002000,
 	I40E_DEBUG_IWARP		= 0x00F00000,
 	I40E_DEBUG_AQ_MESSAGE		= 0x01000000,
 	I40E_DEBUG_AQ_DESCRIPTOR	= 0x02000000,
@@ -1213,25 +1214,6 @@ struct i40e_veb_tc_stats {
 	u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS];
 };
 
-#ifdef I40E_FCOE
-/* Statistics collected per function for FCoE */
-struct i40e_fcoe_stats {
-	u64 rx_fcoe_packets;		/* fcoeprc */
-	u64 rx_fcoe_dwords;		/* focedwrc */
-	u64 rx_fcoe_dropped;		/* fcoerpdc */
-	u64 tx_fcoe_packets;		/* fcoeptc */
-	u64 tx_fcoe_dwords;		/* focedwtc */
-	u64 fcoe_bad_fccrc;		/* fcoecrc */
-	u64 fcoe_last_error;		/* fcoelast */
-	u64 fcoe_ddp_count;		/* fcoeddpc */
-};
-
-/* offset to per function FCoE statistics block */
-#define I40E_FCOE_VF_STAT_OFFSET	0
-#define I40E_FCOE_PF_STAT_OFFSET	128
-#define I40E_FCOE_STAT_MAX		(I40E_FCOE_PF_STAT_OFFSET + I40E_MAX_PF)
-
-#endif
 /* Statistics collected by the MAC */
 struct i40e_hw_port_stats {
 	/* eth stats collected by the port */
@@ -1319,125 +1301,6 @@ struct i40e_hw_port_stats {
 
 #define I40E_SRRD_SRCTL_ATTEMPTS	100000
 
-#ifdef I40E_FCOE
-/* FCoE Tx context descriptor - Use the i40e_tx_context_desc struct */
-
-enum i40E_fcoe_tx_ctx_desc_cmd_bits {
-	I40E_FCOE_TX_CTX_DESC_OPCODE_SINGLE_SEND	= 0x00, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS2	= 0x01, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS3	= 0x05, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS2	= 0x02, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS3	= 0x06, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS2	= 0x03, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS3	= 0x07, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DDP_CTX_INVL	= 0x08, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_CTX_INVL	= 0x09, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_RELOFF			= 0x10,
-	I40E_FCOE_TX_CTX_DESC_CLRSEQ			= 0x20,
-	I40E_FCOE_TX_CTX_DESC_DIFENA			= 0x40,
-	I40E_FCOE_TX_CTX_DESC_IL2TAG2			= 0x80
-};
-
-/* FCoE DDP Context descriptor */
-struct i40e_fcoe_ddp_context_desc {
-	__le64 rsvd;
-	__le64 type_cmd_foff_lsize;
-};
-
-#define I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT	0
-#define I40E_FCOE_DDP_CTX_QW1_DTYPE_MASK	(0xFULL << \
-					I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT)
-
-#define I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT	4
-#define I40E_FCOE_DDP_CTX_QW1_CMD_MASK	(0xFULL << \
-					 I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT)
-
-enum i40e_fcoe_ddp_ctx_desc_cmd_bits {
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_512B	= 0x00, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_4K		= 0x01, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_8K		= 0x02, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_16K	= 0x03, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_DIFENA		= 0x04, /* 1 BIT  */
-	I40E_FCOE_DDP_CTX_DESC_LASTSEQH		= 0x08, /* 1 BIT  */
-};
-
-#define I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT	16
-#define I40E_FCOE_DDP_CTX_QW1_FOFF_MASK	(0x3FFFULL << \
-					 I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT)
-
-#define I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT	32
-#define I40E_FCOE_DDP_CTX_QW1_LSIZE_MASK	(0x3FFFULL << \
-					I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT)
-
-/* FCoE DDP/DWO Queue Context descriptor */
-struct i40e_fcoe_queue_context_desc {
-	__le64 dmaindx_fbase;           /* 0:11 DMAINDX, 12:63 FBASE */
-	__le64 flen_tph;                /* 0:12 FLEN, 13:15 TPH */
-};
-
-#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT	0
-#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_MASK	(0xFFFULL << \
-					I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT	12
-#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_MASK	(0xFFFFFFFFFFFFFULL << \
-					I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT	0
-#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_MASK	(0x1FFFULL << \
-					I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW1_TPH_SHIFT	13
-#define I40E_FCOE_QUEUE_CTX_QW1_TPH_MASK	(0x7ULL << \
-					I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT)
-
-enum i40e_fcoe_queue_ctx_desc_tph_bits {
-	I40E_FCOE_QUEUE_CTX_DESC_TPHRDESC	= 0x1,
-	I40E_FCOE_QUEUE_CTX_DESC_TPHDATA	= 0x2
-};
-
-#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT	30
-#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_MASK	(0x3ULL << \
-					I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT)
-
-/* FCoE DDP/DWO Filter Context descriptor */
-struct i40e_fcoe_filter_context_desc {
-	__le32 param;
-	__le16 seqn;
-
-	/* 48:51(0:3) RSVD, 52:63(4:15) DMAINDX */
-	__le16 rsvd_dmaindx;
-
-	/* 0:7 FLAGS, 8:52 RSVD, 53:63 LANQ */
-	__le64 flags_rsvd_lanq;
-};
-
-#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT	4
-#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_MASK	(0xFFF << \
-					I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT)
-
-enum i40e_fcoe_filter_ctx_desc_flags_bits {
-	I40E_FCOE_FILTER_CTX_DESC_CTYP_DDP	= 0x00,
-	I40E_FCOE_FILTER_CTX_DESC_CTYP_DWO	= 0x01,
-	I40E_FCOE_FILTER_CTX_DESC_ENODE_INIT	= 0x00,
-	I40E_FCOE_FILTER_CTX_DESC_ENODE_RSP	= 0x02,
-	I40E_FCOE_FILTER_CTX_DESC_FC_CLASS2	= 0x00,
-	I40E_FCOE_FILTER_CTX_DESC_FC_CLASS3	= 0x04
-};
-
-#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT	0
-#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_MASK	(0xFFULL << \
-					I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT)
-
-#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT     8
-#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_MASK      (0x3FULL << \
-			I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT)
-
-#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT     53
-#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_MASK      (0x7FFULL << \
-			I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT)
-
-#endif /* I40E_FCOE */
 enum i40e_switch_element_types {
 	I40E_SWITCH_ELEMENT_TYPE_MAC	= 1,
 	I40E_SWITCH_ELEMENT_TYPE_PF	= 2,
@@ -1600,4 +1463,83 @@ struct i40e_lldp_variables {
 #define I40E_FLEX_56_MASK		(0x1ULL << I40E_FLEX_56_SHIFT)
 #define I40E_FLEX_57_SHIFT		6
 #define I40E_FLEX_57_MASK		(0x1ULL << I40E_FLEX_57_SHIFT)
+
+/* Version format for PPP */
+struct i40e_ppp_version {
+	u8 major;
+	u8 minor;
+	u8 update;
+	u8 draft;
+};
+
+#define I40E_PPP_NAME_SIZE	32
+
+/* Package header */
+struct i40e_package_header {
+	struct i40e_ppp_version version;
+	u32 segment_count;
+	u32 segment_offset[1];
+};
+
+/* Generic segment header */
+struct i40e_generic_seg_header {
+#define SEGMENT_TYPE_METADATA	0x00000001
+#define SEGMENT_TYPE_NOTES	0x00000002
+#define SEGMENT_TYPE_I40E	0x00000011
+#define SEGMENT_TYPE_X722	0x00000012
+	u32 type;
+	struct i40e_ppp_version version;
+	u32 size;
+	char name[I40E_PPP_NAME_SIZE];
+};
+
+struct i40e_metadata_segment {
+	struct i40e_generic_seg_header header;
+	struct i40e_ppp_version version;
+	u32 track_id;
+	char name[I40E_PPP_NAME_SIZE];
+};
+
+struct i40e_device_id_entry {
+	u32 vendor_dev_id;
+	u32 sub_vendor_dev_id;
+};
+
+struct i40e_profile_segment {
+	struct i40e_generic_seg_header header;
+	struct i40e_ppp_version version;
+	char name[I40E_PPP_NAME_SIZE];
+	u32 device_table_count;
+	struct i40e_device_id_entry device_table[1];
+};
+
+struct i40e_section_table {
+	u32 section_count;
+	u32 section_offset[1];
+};
+
+struct i40e_profile_section_header {
+	u16 tbl_size;
+	u16 data_end;
+	struct {
+#define SECTION_TYPE_INFO	0x00000010
+#define SECTION_TYPE_MMIO	0x00000800
+#define SECTION_TYPE_AQ		0x00000801
+#define SECTION_TYPE_NOTE	0x80000000
+#define SECTION_TYPE_NAME	0x80000001
+		u32 type;
+		u32 offset;
+		u32 size;
+	} section;
+};
+
+struct i40e_profile_info {
+	u32 track_id;
+	struct i40e_ppp_version version;
+	u8 op;
+#define I40E_PPP_ADD_TRACKID		0x01
+#define I40E_PPP_REMOVE_TRACKID	0x02
+	u8 reserved[7];
+	u8 name[I40E_PPP_NAME_SIZE];
+};
 #endif /* _I40E_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
index 974ba2baf6ea..8552192a5bde 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
@@ -163,7 +163,8 @@ struct i40e_virtchnl_vsi_resource {
 #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING	0x00020000
 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2	0x00040000
 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF		0X00080000
-#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM	0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP		0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM	0X00200000
 
 #define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \
 				    I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 78460c52b7c4..95c23fbaa211 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -50,8 +50,8 @@ static void i40e_vc_vf_broadcast(struct i40e_pf *pf,
 	for (i = 0; i < pf->num_alloc_vfs; i++, vf++) {
 		int abs_vf_id = vf->vf_id + (int)hw->func_caps.vf_base_id;
 		/* Not all vfs are enabled so skip the ones that are not */
-		if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states) &&
-		    !test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states))
+		if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states) &&
+		    !test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
 			continue;
 
 		/* Ignore return value on purpose - a given VF may fail, but
@@ -137,8 +137,8 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
 		return;
 
 	/* verify if the VF is in either init or active before proceeding */
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states) &&
-	    !test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states))
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states) &&
+	    !test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
 		return;
 
 	abs_vf_id = vf->vf_id + (int)vf->pf->hw.func_caps.vf_base_id;
@@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
-		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
-				  (u32)hena);
-		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
-				  (u32)(hena >> 32));
+		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena);
+		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32));
 	}
 
 	/* program mac filter */
@@ -811,6 +809,11 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	u32 reg_idx, reg;
 	int i, msix_vf;
 
+	/* Start by disabling VF's configuration API to prevent the OS from
+	 * accessing the VF's VSI after it's freed / invalidated.
+	 */
+	clear_bit(I40E_VF_STATE_INIT, &vf->vf_states);
+
 	/* free vsi & disconnect it from the parent uplink */
 	if (vf->lan_vsi_idx) {
 		i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]);
@@ -850,7 +853,6 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	/* reset some of the state variables keeping track of the resources */
 	vf->num_queue_pairs = 0;
 	vf->vf_states = 0;
-	clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
 }
 
 /**
@@ -882,7 +884,7 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf)
 	vf->num_queue_pairs = total_queue_pairs;
 
 	/* VF is now completely initialized */
-	set_bit(I40E_VF_STAT_INIT, &vf->vf_states);
+	set_bit(I40E_VF_STATE_INIT, &vf->vf_states);
 
 error_alloc:
 	if (ret)
@@ -921,25 +923,30 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf)
 }
 
 /**
- * i40e_reset_vf
+ * i40e_trigger_vf_reset
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * reset the VF
+ * Trigger hardware to start a reset for a particular VF. Expects the caller
+ * to wait the proper amount of time to allow hardware to reset the VF before
+ * it cleans up and restores VF functionality.
  **/
-void i40e_reset_vf(struct i40e_vf *vf, bool flr)
+static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr)
 {
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_hw *hw = &pf->hw;
 	u32 reg, reg_idx, bit_idx;
-	bool rsd = false;
-	int i;
-
-	if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state))
-		return;
 
 	/* warn the VF */
-	clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
+	clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);
+
+	/* Disable VF's configuration API during reset. The flag is re-enabled
+	 * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI.
+	 * It's normally disabled in i40e_free_vf_res(), but it's safer
+	 * to do it earlier to give some time to finish to any VF config
+	 * functions that may still be running at this point.
+	 */
+	clear_bit(I40E_VF_STATE_INIT, &vf->vf_states);
 
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
@@ -960,6 +967,79 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	if (i40e_quiesce_vf_pci(vf))
 		dev_err(&pf->pdev->dev, "VF %d PCI transactions stuck\n",
 			vf->vf_id);
+}
+
+/**
+ * i40e_cleanup_reset_vf
+ * @vf: pointer to the VF structure
+ *
+ * Cleanup a VF after the hardware reset is finished. Expects the caller to
+ * have verified whether the reset is finished properly, and ensure the
+ * minimum amount of wait time has passed.
+ **/
+static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
+{
+	struct i40e_pf *pf = vf->pf;
+	struct i40e_hw *hw = &pf->hw;
+	u32 reg;
+
+	/* free VF resources to begin resetting the VSI state */
+	i40e_free_vf_res(vf);
+
+	/* Enable hardware by clearing the reset bit in the VPGEN_VFRTRIG reg.
+	 * By doing this we allow HW to access VF memory at any point. If we
+	 * did it any sooner, HW could access memory while it was being freed
+	 * in i40e_free_vf_res(), causing an IOMMU fault.
+	 *
+	 * On the other hand, this needs to be done ASAP, because the VF driver
+	 * is waiting for this to happen and may report a timeout. It's
+	 * harmless, but it gets logged into Guest OS kernel log, so best avoid
+	 * it.
+	 */
+	reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
+	reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
+	wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+
+	/* reallocate VF resources to finish resetting the VSI state */
+	if (!i40e_alloc_vf_res(vf)) {
+		int abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
+		i40e_enable_vf_mappings(vf);
+		set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);
+		clear_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+		/* Do not notify the client during VF init */
+		if (test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE,
+				       &vf->vf_states))
+			i40e_notify_client_of_vf_reset(pf, abs_vf_id);
+		vf->num_vlan = 0;
+	}
+
+	/* Tell the VF driver the reset is done. This needs to be done only
+	 * after VF has been fully initialized, because the VF driver may
+	 * request resources immediately after setting this flag.
+	 */
+	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
+}
+
+/**
+ * i40e_reset_vf
+ * @vf: pointer to the VF structure
+ * @flr: VFLR was issued or not
+ *
+ * reset the VF
+ **/
+void i40e_reset_vf(struct i40e_vf *vf, bool flr)
+{
+	struct i40e_pf *pf = vf->pf;
+	struct i40e_hw *hw = &pf->hw;
+	bool rsd = false;
+	u32 reg;
+	int i;
+
+	/* If VFs have been disabled, there is no need to reset */
+	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
+		return;
+
+	i40e_trigger_vf_reset(vf, flr);
 
 	/* poll VPGEN_VFRSTAT reg to make sure
 	 * that reset is complete
@@ -984,35 +1064,116 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	if (!rsd)
 		dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
 			vf->vf_id);
-	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_COMPLETED);
-	/* clear the reset bit in the VPGEN_VFRTRIG reg */
-	reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
-	reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
-	wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+	usleep_range(10000, 20000);
 
-	/* On initial reset, we won't have any queues */
-	if (vf->lan_vsi_idx == 0)
-		goto complete_reset;
+	/* On initial reset, we don't have any queues to disable */
+	if (vf->lan_vsi_idx != 0)
+		i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
 
-	i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
-complete_reset:
-	/* reallocate VF resources to reset the VSI state */
-	i40e_free_vf_res(vf);
-	if (!i40e_alloc_vf_res(vf)) {
-		int abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
-		i40e_enable_vf_mappings(vf);
-		set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
-		clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
-		/* Do not notify the client during VF init */
-		if (vf->pf->num_alloc_vfs)
-			i40e_notify_client_of_vf_reset(pf, abs_vf_id);
-		vf->num_vlan = 0;
+	i40e_cleanup_reset_vf(vf);
+
+	i40e_flush(hw);
+	clear_bit(__I40E_VF_DISABLE, pf->state);
+}
+
+/**
+ * i40e_reset_all_vfs
+ * @pf: pointer to the PF structure
+ * @flr: VFLR was issued or not
+ *
+ * Reset all allocated VFs in one go. First, tell the hardware to reset each
+ * VF, then do all the waiting in one chunk, and finally finish restoring each
+ * VF after the wait. This is useful during PF routines which need to reset
+ * all VFs, as otherwise it must perform these resets in a serialized fashion.
+ **/
+void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
+{
+	struct i40e_hw *hw = &pf->hw;
+	struct i40e_vf *vf;
+	int i, v;
+	u32 reg;
+
+	/* If we don't have any VFs, then there is nothing to reset */
+	if (!pf->num_alloc_vfs)
+		return;
+
+	/* If VFs have been disabled, there is no need to reset */
+	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
+		return;
+
+	/* Begin reset on all VFs at once */
+	for (v = 0; v < pf->num_alloc_vfs; v++)
+		i40e_trigger_vf_reset(&pf->vf[v], flr);
+
+	/* HW requires some time to make sure it can flush the FIFO for a VF
+	 * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
+	 * sequence to make sure that it has completed. We'll keep track of
+	 * the VFs using a simple iterator that increments once that VF has
+	 * finished resetting.
+	 */
+	for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) {
+		usleep_range(10000, 20000);
+
+		/* Check each VF in sequence, beginning with the VF to fail
+		 * the previous check.
+		 */
+		while (v < pf->num_alloc_vfs) {
+			vf = &pf->vf[v];
+			reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
+			if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
+				break;
+
+			/* If the current VF has finished resetting, move on
+			 * to the next VF in sequence.
+			 */
+			v++;
+		}
 	}
-	/* tell the VF the reset is done */
-	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
+
+	if (flr)
+		usleep_range(10000, 20000);
+
+	/* Display a warning if at least one VF didn't manage to reset in
+	 * time, but continue on with the operation.
+	 */
+	if (v < pf->num_alloc_vfs)
+		dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
+			pf->vf[v].vf_id);
+	usleep_range(10000, 20000);
+
+	/* Begin disabling all the rings associated with VFs, but do not wait
+	 * between each VF.
+	 */
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		/* On initial reset, we don't have any queues to disable */
+		if (pf->vf[v].lan_vsi_idx == 0)
+			continue;
+
+		i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]);
+	}
+
+	/* Now that we've notified HW to disable all of the VF rings, wait
+	 * until they finish.
+	 */
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		/* On initial reset, we don't have any queues to disable */
+		if (pf->vf[v].lan_vsi_idx == 0)
+			continue;
+
+		i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]);
+	}
+
+	/* Hw may need up to 50ms to finish disabling the RX queues. We
+	 * minimize the wait by delaying only once for all VFs.
+	 */
+	mdelay(50);
+
+	/* Finish the reset on each VF */
+	for (v = 0; v < pf->num_alloc_vfs; v++)
+		i40e_cleanup_reset_vf(&pf->vf[v]);
 
 	i40e_flush(hw);
-	clear_bit(__I40E_VF_DISABLE, &pf->state);
+	clear_bit(__I40E_VF_DISABLE, pf->state);
 }
 
 /**
@@ -1029,13 +1190,25 @@ void i40e_free_vfs(struct i40e_pf *pf)
 
 	if (!pf->vf)
 		return;
-	while (test_and_set_bit(__I40E_VF_DISABLE, &pf->state))
+	while (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
 		usleep_range(1000, 2000);
 
 	i40e_notify_client_of_vf_enable(pf, 0);
-	for (i = 0; i < pf->num_alloc_vfs; i++)
-		if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states))
-			i40e_vsi_stop_rings(pf->vsi[pf->vf[i].lan_vsi_idx]);
+
+	/* Amortize wait time by stopping all VFs at the same time */
+	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states))
+			continue;
+
+		i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[i].lan_vsi_idx]);
+	}
+
+	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states))
+			continue;
+
+		i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[i].lan_vsi_idx]);
+	}
 
 	/* Disable IOV before freeing resources. This lets any VF drivers
 	 * running in the host get themselves cleaned up before we yank
@@ -1046,13 +1219,11 @@ void i40e_free_vfs(struct i40e_pf *pf)
 	else
 		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
 
-	msleep(20); /* let any messages in transit get finished up */
-
 	/* free up VF resources */
 	tmp = pf->num_alloc_vfs;
 	pf->num_alloc_vfs = 0;
 	for (i = 0; i < tmp; i++) {
-		if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states))
+		if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states))
 			i40e_free_vf_res(&pf->vf[i]);
 		/* disable qp mappings */
 		i40e_disable_vf_mappings(&pf->vf[i]);
@@ -1075,7 +1246,7 @@ void i40e_free_vfs(struct i40e_pf *pf)
 			wr32(hw, I40E_GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
 		}
 	}
-	clear_bit(__I40E_VF_DISABLE, &pf->state);
+	clear_bit(__I40E_VF_DISABLE, pf->state);
 }
 
 #ifdef CONFIG_PCI_IOV
@@ -1120,12 +1291,15 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 		/* assign default capabilities */
 		set_bit(I40E_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
 		vfs[i].spoofchk = true;
-		/* VF resources get allocated during reset */
-		i40e_reset_vf(&vfs[i], false);
+
+		set_bit(I40E_VF_STATE_PRE_ENABLE, &vfs[i].vf_states);
 
 	}
 	pf->num_alloc_vfs = num_alloc_vfs;
 
+	/* VF resources get allocated during reset */
+	i40e_reset_all_vfs(pf, false);
+
 	i40e_notify_client_of_vf_enable(pf, num_alloc_vfs);
 
 err_alloc:
@@ -1152,7 +1326,7 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	int pre_existing_vfs = pci_num_vf(pdev);
 	int err = 0;
 
-	if (test_bit(__I40E_TESTING, &pf->state)) {
+	if (test_bit(__I40E_TESTING, pf->state)) {
 		dev_warn(&pdev->dev,
 			 "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n");
 		err = -EPERM;
@@ -1258,7 +1432,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
 				"Number of invalid messages exceeded for VF %d\n",
 				vf->vf_id);
 			dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n");
-			set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
+			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
 		}
 	} else {
 		vf->num_valid_msgs++;
@@ -1333,7 +1507,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	int len = 0;
 	int ret;
 
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -1359,10 +1533,10 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	if (!vsi->info.pvid)
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN;
 
-	if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) &&
+	if (i40e_vf_client_capable(pf, vf->vf_id) &&
 	    (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) {
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP;
-		set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states);
+		set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states);
 	}
 
 	if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) {
@@ -1383,6 +1557,13 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 				I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
 	}
 
+	if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP)
+		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP;
+
+	if ((pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) &&
+	    (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
+		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
+
 	if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING) {
 		if (pf->flags & I40E_FLAG_MFP_ENABLED) {
 			dev_err(&pf->pdev->dev,
@@ -1416,7 +1597,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 		ether_addr_copy(vfres->vsi_res[0].default_mac_addr,
 				vf->default_lan_addr.addr);
 	}
-	set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
+	set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);
 
 err:
 	/* send the response back to the VF */
@@ -1439,7 +1620,7 @@ err:
  **/
 static void i40e_vc_reset_vf_msg(struct i40e_vf *vf)
 {
-	if (test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states))
+	if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
 		i40e_reset_vf(vf, false);
 }
 
@@ -1487,7 +1668,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
 	int bkt;
 
 	vsi = i40e_find_vsi_from_id(pf, info->vsi_id);
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, info->vsi_id) ||
 	    !vsi) {
 		aq_ret = I40E_ERR_PARAM;
@@ -1548,9 +1729,9 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
 			 "VF %d successfully set multicast promiscuous mode\n",
 			 vf->vf_id);
 		if (allmulti)
-			set_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states);
+			set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
 		else
-			clear_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states);
+			clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
 	}
 
 	if (info->flags & I40E_FLAG_VF_UNICAST_PROMISC)
@@ -1599,9 +1780,9 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
 			 "VF %d successfully set unicast promiscuous mode\n",
 			 vf->vf_id);
 		if (alluni)
-			set_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states);
+			set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
 		else
-			clear_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states);
+			clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
 	}
 
 error_param:
@@ -1630,7 +1811,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	i40e_status aq_ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -1687,7 +1868,7 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	unsigned long tempmap;
 	int i;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -1747,7 +1928,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	u16 vsi_id = vqs->vsi_id;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -1786,7 +1967,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	struct i40e_pf *pf = vf->pf;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -1828,7 +2009,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	memset(&stats, 0, sizeof(struct i40e_eth_stats));
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -1853,7 +2034,7 @@ error_param:
 }
 
 /* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 8
+#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
 #define I40E_VC_MAX_VLAN_PER_VF 8
 
 /**
@@ -1915,7 +2096,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	i40e_status ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
 		ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -1984,7 +2165,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	i40e_status ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
 		ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -2050,7 +2231,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 			"VF is not trusted, switch the VF to trusted to add more VLAN addresses\n");
 		goto error_param;
 	}
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -2077,12 +2258,12 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 		if (!ret)
 			vf->num_vlan++;
 
-		if (test_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states))
+		if (test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states))
 			i40e_aq_set_vsi_uc_promisc_on_vlan(&pf->hw, vsi->seid,
 							   true,
 							   vfl->vlan_id[i],
 							   NULL);
-		if (test_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states))
+		if (test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states))
 			i40e_aq_set_vsi_mc_promisc_on_vlan(&pf->hw, vsi->seid,
 							   true,
 							   vfl->vlan_id[i],
@@ -2117,7 +2298,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	i40e_status aq_ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -2140,12 +2321,12 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 		i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]);
 		vf->num_vlan--;
 
-		if (test_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states))
+		if (test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states))
 			i40e_aq_set_vsi_uc_promisc_on_vlan(&pf->hw, vsi->seid,
 							   false,
 							   vfl->vlan_id[i],
 							   NULL);
-		if (test_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states))
+		if (test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states))
 			i40e_aq_set_vsi_mc_promisc_on_vlan(&pf->hw, vsi->seid,
 							   false,
 							   vfl->vlan_id[i],
@@ -2171,8 +2352,8 @@ static int i40e_vc_iwarp_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	int abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
-	    !test_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	    !test_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2202,8 +2383,8 @@ static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, u16 msglen,
 				(struct i40e_virtchnl_iwarp_qvlist_info *)msg;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
-	    !test_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	    !test_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2240,7 +2421,7 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	u16 vsi_id = vrk->vsi_id;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vsi_id) ||
 	    (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) {
 		aq_ret = I40E_ERR_PARAM;
@@ -2272,7 +2453,7 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	u16 vsi_id = vrl->vsi_id;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vsi_id) ||
 	    (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) {
 		aq_ret = I40E_ERR_PARAM;
@@ -2302,7 +2483,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	i40e_status aq_ret = 0;
 	int len = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -2339,7 +2520,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -2369,7 +2550,7 @@ static int i40e_vc_validate_vf_msg(struct i40e_vf *vf, u32 v_opcode,
 	int valid_len = 0;
 
 	/* Check if VF is disabled. */
-	if (test_bit(I40E_VF_STAT_DISABLED, &vf->vf_states))
+	if (test_bit(I40E_VF_STATE_DISABLED, &vf->vf_states))
 		return I40E_ERR_PARAM;
 
 	/* Validate message length. */
@@ -2637,7 +2818,7 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 	struct i40e_vf *vf;
 	int vf_id;
 
-	if (!test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state))
+	if (!test_bit(__I40E_VFLR_EVENT_PENDING, pf->state))
 		return 0;
 
 	/* Re-enable the VFLR interrupt cause here, before looking for which
@@ -2650,7 +2831,7 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
 	i40e_flush(hw);
 
-	clear_bit(__I40E_VFLR_EVENT_PENDING, &pf->state);
+	clear_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
 	for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
 		reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32;
 		bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32;
@@ -2693,7 +2874,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 
 	vf = &(pf->vf[vf_id]);
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
 		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
 			vf_id);
 		ret = -EAGAIN;
@@ -2782,7 +2963,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 
 	vf = &(pf->vf[vf_id]);
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
 		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
 			vf_id);
 		ret = -EAGAIN;
@@ -2914,7 +3095,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 
 	vf = &(pf->vf[vf_id]);
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
 		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
 			vf_id);
 		ret = -EAGAIN;
@@ -2995,7 +3176,7 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 	vf = &(pf->vf[vf_id]);
 	/* first vsi is always the LAN vsi */
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
 		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
 			vf_id);
 		ret = -EAGAIN;
@@ -3114,7 +3295,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable)
 	}
 
 	vf = &(pf->vf[vf_id]);
-	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
 		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
 			vf_id);
 		ret = -EAGAIN;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 4012d069939a..20d7c8160e9e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -56,13 +56,14 @@ enum i40e_queue_ctrl {
 
 /* VF states */
 enum i40e_vf_states {
-	I40E_VF_STAT_INIT = 0,
-	I40E_VF_STAT_ACTIVE,
-	I40E_VF_STAT_IWARPENA,
-	I40E_VF_STAT_FCOEENA,
-	I40E_VF_STAT_DISABLED,
-	I40E_VF_STAT_MC_PROMISC,
-	I40E_VF_STAT_UC_PROMISC,
+	I40E_VF_STATE_INIT = 0,
+	I40E_VF_STATE_ACTIVE,
+	I40E_VF_STATE_IWARPENA,
+	I40E_VF_STATE_FCOEENA,
+	I40E_VF_STATE_DISABLED,
+	I40E_VF_STATE_MC_PROMISC,
+	I40E_VF_STATE_UC_PROMISC,
+	I40E_VF_STATE_PRE_ENABLE,
 };
 
 /* VF capabilities */
@@ -87,7 +88,6 @@ struct i40e_vf {
 	u16 stag;
 
 	struct i40e_virtchnl_ether_addr default_lan_addr;
-	struct i40e_virtchnl_ether_addr default_fcoe_addr;
 	u16 port_vlan_id;
 	bool pf_set_mac;	/* The VMM admin set the VF MAC address */
 	bool trusted;
@@ -125,6 +125,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 			   u32 v_retval, u8 *msg, u16 msglen);
 int i40e_vc_process_vflr_event(struct i40e_pf *pf);
 void i40e_reset_vf(struct i40e_vf *vf, bool flr);
+void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
 void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
 
 /* VF configuration related iplink handlers */
diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile
index 3a423836a565..a393f4a07f06 100644
--- a/drivers/net/ethernet/intel/i40evf/Makefile
+++ b/drivers/net/ethernet/intel/i40evf/Makefile
@@ -29,8 +29,11 @@
 #
 #
 
+ccflags-y += -I$(src)
+subdir-ccflags-y += -I$(src)
+
 obj-$(CONFIG_I40EVF) += i40evf.o
 
 i40evf-objs :=	i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \
-		i40e_txrx.o i40e_common.o i40e_adminq.o
+		i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index 96385156b824..8b0d4b255dea 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -797,8 +797,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 			 */
 			if (i40evf_asq_done(hw))
 				break;
-			usleep_range(1000, 2000);
-			total_delay++;
+			udelay(50);
+			total_delay += 50;
 		} while (total_delay < hw->aq.asq_cmd_timeout);
 	}
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
index 1f9b3b5d946d..e0bfaa3d4a21 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
@@ -151,7 +151,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 
 /* general information */
 #define I40E_AQ_LARGE_BUF	512
-#define I40E_ASQ_CMD_TIMEOUT	250  /* msecs */
+#define I40E_ASQ_CMD_TIMEOUT	250000  /* usecs */
 
 void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
 				       u16 opcode);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index eeb9864bc5b1..91d8786d386d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_list_func_capabilities	= 0x000A,
 	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
 
+	/* Proxy commands */
+	i40e_aqc_opc_set_proxy_config		= 0x0104,
+	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
 	/* LAA */
 	i40e_aqc_opc_mac_address_read	= 0x0107,
 	i40e_aqc_opc_mac_address_write	= 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
 	/* PXE */
 	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
 
+	/* WoL commands */
+	i40e_aqc_opc_set_wol_filter	= 0x0120,
+	i40e_aqc_opc_get_wake_reason	= 0x0121,
+
 	/* internal switch commands */
 	i40e_aqc_opc_get_switch_config		= 0x0200,
 	i40e_aqc_opc_add_statistics		= 0x0201,
@@ -177,10 +185,15 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
 	i40e_aqc_opc_add_cloud_filters		= 0x025C,
 	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
+	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
 
 	i40e_aqc_opc_add_mirror_rule	= 0x0260,
 	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
 
+	/* Pipeline Personalization Profile */
+	i40e_aqc_opc_write_personalization_profile	= 0x0270,
+	i40e_aqc_opc_get_personalization_profile_list	= 0x0271,
+
 	/* DCB commands */
 	i40e_aqc_opc_dcb_ignore_pfc	= 0x0301,
 	i40e_aqc_opc_dcb_updated	= 0x0302,
@@ -558,6 +571,56 @@ struct i40e_aqc_clear_pxe {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+	__le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
+		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
+		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+	__le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER				0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
+	__le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
+	u8 reserved[2];
+	__le32	address_high;
+	__le32	address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+	u8 filter[128];
+	u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+	u8 reserved_1[2];
+	__le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+	u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
 /* Switch configuration commands (0x02xx) */
 
 /* Used by many indirect commands that only pass an seid and a buffer in the
@@ -640,6 +703,8 @@ struct i40e_aqc_set_port_parameters {
 #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
 #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -691,6 +756,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 /* Set Switch Configuration (direct 0x0205) */
 struct i40e_aqc_set_switch_config {
 	__le16	flags;
+/* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
@@ -1364,6 +1430,36 @@ struct i40e_aqc_add_delete_mirror_rule_completion {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion);
 
+/* Pipeline Personalization Profile */
+struct i40e_aqc_write_personalization_profile {
+	u8      flags;
+	u8      reserved[3];
+	__le32  profile_track_id;
+	__le32  addr_high;
+	__le32  addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile);
+
+struct i40e_aqc_write_ppp_resp {
+	__le32 error_offset;
+	__le32 error_info;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct i40e_aqc_get_applied_profiles {
+	u8      flags;
+#define I40E_AQC_GET_PPP_GET_CONF	0x1
+#define I40E_AQC_GET_PPP_GET_RDPU_CONF	0x2
+	u8      rsv[3];
+	__le32  reserved;
+	__le32  addr_high;
+	__le32  addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles);
+
 /* DCB 0x03xx*/
 
 /* PFC Ignore (direct 0x0301)
@@ -1839,11 +1935,12 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	external_power_ability;
+	u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
+#define I40E_AQ_PWR_CLASS_MASK		0x03
 	u8	reserved[4];
 };
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 89dfdbca13db..43f10761f4ba 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -958,7 +958,9 @@ u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 	int retry = 5;
 	u32 val = 0;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40evf_aq_rx_ctl_read_register(hw, reg_addr,
@@ -1019,7 +1021,9 @@ void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 	bool use_register;
 	int retry = 5;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40evf_aq_rx_ctl_write_register(hw, reg_addr,
@@ -1127,3 +1131,215 @@ i40e_status i40e_vf_reset(struct i40e_hw *hw)
 	return i40e_aq_send_msg_to_pf(hw, I40E_VIRTCHNL_OP_RESET_VF,
 				      0, NULL, 0, NULL);
 }
+
+/**
+ * i40evf_aq_write_ppp - Write pipeline personalization profile (ppp)
+ * @hw: pointer to the hw struct
+ * @buff: command buffer (size in bytes = buff_size)
+ * @buff_size: buffer size in bytes
+ * @track_id: package tracking id
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+enum
+i40e_status_code i40evf_aq_write_ppp(struct i40e_hw *hw, void *buff,
+				     u16 buff_size, u32 track_id,
+				     u32 *error_offset, u32 *error_info,
+				     struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_write_personalization_profile *cmd =
+		(struct i40e_aqc_write_personalization_profile *)
+		&desc.params.raw;
+	struct i40e_aqc_write_ppp_resp *resp;
+	i40e_status status;
+
+	i40evf_fill_default_direct_cmd_desc(&desc,
+					    i40e_aqc_opc_write_personalization_profile);
+
+	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
+	if (buff_size > I40E_AQ_LARGE_BUF)
+		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+
+	desc.datalen = cpu_to_le16(buff_size);
+
+	cmd->profile_track_id = cpu_to_le32(track_id);
+
+	status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+	if (!status) {
+		resp = (struct i40e_aqc_write_ppp_resp *)&desc.params.raw;
+		if (error_offset)
+			*error_offset = le32_to_cpu(resp->error_offset);
+		if (error_info)
+			*error_info = le32_to_cpu(resp->error_info);
+	}
+
+	return status;
+}
+
+/**
+ * i40evf_aq_get_ppp_list - Read pipeline personalization profile (ppp)
+ * @hw: pointer to the hw struct
+ * @buff: command buffer (size in bytes = buff_size)
+ * @buff_size: buffer size in bytes
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+enum
+i40e_status_code i40evf_aq_get_ppp_list(struct i40e_hw *hw, void *buff,
+					u16 buff_size, u8 flags,
+				      struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_get_applied_profiles *cmd =
+		(struct i40e_aqc_get_applied_profiles *)&desc.params.raw;
+	i40e_status status;
+
+	i40evf_fill_default_direct_cmd_desc(&desc,
+					    i40e_aqc_opc_get_personalization_profile_list);
+
+	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	if (buff_size > I40E_AQ_LARGE_BUF)
+		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+	desc.datalen = cpu_to_le16(buff_size);
+
+	cmd->flags = flags;
+
+	status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
+
+	return status;
+}
+
+/**
+ * i40evf_find_segment_in_package
+ * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E)
+ * @pkg_hdr: pointer to the package header to be searched
+ *
+ * This function searches a package file for a particular segment type. On
+ * success it returns a pointer to the segment header, otherwise it will
+ * return NULL.
+ **/
+struct i40e_generic_seg_header *
+i40evf_find_segment_in_package(u32 segment_type,
+			       struct i40e_package_header *pkg_hdr)
+{
+	struct i40e_generic_seg_header *segment;
+	u32 i;
+
+	/* Search all package segments for the requested segment type */
+	for (i = 0; i < pkg_hdr->segment_count; i++) {
+		segment =
+			(struct i40e_generic_seg_header *)((u8 *)pkg_hdr +
+			 pkg_hdr->segment_offset[i]);
+
+		if (segment->type == segment_type)
+			return segment;
+	}
+
+	return NULL;
+}
+
+/**
+ * i40evf_write_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be downloaded
+ * @track_id: package tracking id
+ *
+ * Handles the download of a complete package.
+ */
+enum i40e_status_code
+i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+		     u32 track_id)
+{
+	i40e_status status = 0;
+	struct i40e_section_table *sec_tbl;
+	struct i40e_profile_section_header *sec = NULL;
+	u32 dev_cnt;
+	u32 vendor_dev_id;
+	u32 *nvm;
+	u32 section_size = 0;
+	u32 offset = 0, info = 0;
+	u32 i;
+
+	if (!track_id) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Track_id can't be 0.");
+		return I40E_NOT_SUPPORTED;
+	}
+
+	dev_cnt = profile->device_table_count;
+
+	for (i = 0; i < dev_cnt; i++) {
+		vendor_dev_id = profile->device_table[i].vendor_dev_id;
+		if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL)
+			if (hw->device_id == (vendor_dev_id & 0xFFFF))
+				break;
+	}
+	if (i == dev_cnt) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support PPP");
+		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+	}
+
+	nvm = (u32 *)&profile->device_table[dev_cnt];
+	sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1];
+
+	for (i = 0; i < sec_tbl->section_count; i++) {
+		sec = (struct i40e_profile_section_header *)((u8 *)profile +
+					     sec_tbl->section_offset[i]);
+
+		/* Skip 'AQ', 'note' and 'name' sections */
+		if (sec->section.type != SECTION_TYPE_MMIO)
+			continue;
+
+		section_size = sec->section.size +
+			sizeof(struct i40e_profile_section_header);
+
+		/* Write profile */
+		status = i40evf_aq_write_ppp(hw, (void *)sec, (u16)section_size,
+					     track_id, &offset, &info, NULL);
+		if (status) {
+			i40e_debug(hw, I40E_DEBUG_PACKAGE,
+				   "Failed to write profile: offset %d, info %d",
+				   offset, info);
+			break;
+		}
+	}
+	return status;
+}
+
+/**
+ * i40evf_add_pinfo_to_list
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package
+ * @profile_info_sec: buffer for information section
+ * @track_id: package tracking id
+ *
+ * Register a profile to the list of loaded profiles.
+ */
+enum i40e_status_code
+i40evf_add_pinfo_to_list(struct i40e_hw *hw,
+			 struct i40e_profile_segment *profile,
+			 u8 *profile_info_sec, u32 track_id)
+{
+	i40e_status status = 0;
+	struct i40e_profile_section_header *sec = NULL;
+	struct i40e_profile_info *pinfo;
+	u32 offset = 0, info = 0;
+
+	sec = (struct i40e_profile_section_header *)profile_info_sec;
+	sec->tbl_size = 1;
+	sec->data_end = sizeof(struct i40e_profile_section_header) +
+			sizeof(struct i40e_profile_info);
+	sec->section.type = SECTION_TYPE_INFO;
+	sec->section.offset = sizeof(struct i40e_profile_section_header);
+	sec->section.size = sizeof(struct i40e_profile_info);
+	pinfo = (struct i40e_profile_info *)(profile_info_sec +
+					     sec->section.offset);
+	pinfo->track_id = track_id;
+	pinfo->version = profile->version;
+	pinfo->op = I40E_PPP_ADD_TRACKID;
+	memcpy(pinfo->name, profile->name, I40E_PPP_NAME_SIZE);
+
+	status = i40evf_aq_write_ppp(hw, (void *)sec, sec->data_end,
+				     track_id, &offset, &info, NULL);
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index ba6c6bda0e22..741223d5d809 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -122,4 +122,21 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
 u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
 i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
 				    u32 time, u32 interval);
+i40e_status i40evf_aq_write_ppp(struct i40e_hw *hw, void *buff,
+				u16 buff_size, u32 track_id,
+				u32 *error_offset, u32 *error_info,
+				struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40evf_aq_get_ppp_list(struct i40e_hw *hw, void *buff,
+				   u16 buff_size, u8 flags,
+				   struct i40e_asq_cmd_details *cmd_details);
+struct i40e_generic_seg_header *
+i40evf_find_segment_in_package(u32 segment_type,
+			       struct i40e_package_header *pkg_header);
+enum i40e_status_code
+i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
+		     u32 track_id);
+enum i40e_status_code
+i40evf_add_pinfo_to_list(struct i40e_hw *hw,
+			 struct i40e_profile_segment *profile,
+			 u8 *profile_info_sec, u32 track_id);
 #endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/i40evf/i40e_trace.h
new file mode 100644
index 000000000000..9a5100b2b7c7
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40e_trace.h
@@ -0,0 +1,229 @@
+/*******************************************************************************
+ *
+ * Intel(R) 40-10 Gigabit Ethernet Virtual Function Driver
+ * Copyright(c) 2013 - 2017 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ ******************************************************************************/
+
+/* Modeled on trace-events-sample.h */
+
+/* The trace subsystem name for i40evf will be "i40evf".
+ *
+ * This file is named i40e_trace.h.
+ *
+ * Since this include file's name is different from the trace
+ * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end
+ * of this file.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM i40evf
+
+/* See trace-events-sample.h for a detailed description of why this
+ * guard clause is different from most normal include files.
+ */
+#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _I40E_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+/**
+ * i40e_trace() macro enables shared code to refer to trace points
+ * like:
+ *
+ * trace_i40e{,vf}_example(args...)
+ *
+ * ... as:
+ *
+ * i40e_trace(example, args...)
+ *
+ * ... to resolve to the PF or VF version of the tracepoint without
+ * ifdefs, and to allow tracepoints to be disabled entirely at build
+ * time.
+ *
+ * Trace point should always be referred to in the driver via this
+ * macro.
+ *
+ * Similarly, i40e_trace_enabled(trace_name) wraps references to
+ * trace_i40e{,vf}_<trace_name>_enabled() functions.
+ */
+#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40evf ## _ ## trace_name)
+#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name)
+
+#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args)
+
+#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)()
+
+/* Events common to PF and VF. Corresponding versions will be defined
+ * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace()
+ * macro above will select the right trace point name for the driver
+ * being built from shared code.
+ */
+
+/* Events related to a vsi & ring */
+DECLARE_EVENT_CLASS(
+	i40evf_tx_template,
+
+	TP_PROTO(struct i40e_ring *ring,
+		 struct i40e_tx_desc *desc,
+		 struct i40e_tx_buffer *buf),
+
+	TP_ARGS(ring, desc, buf),
+
+	/* The convention here is to make the first fields in the
+	 * TP_STRUCT match the TP_PROTO exactly. This enables the use
+	 * of the args struct generated by the tplist tool (from the
+	 * bcc-tools package) to be used for those fields. To access
+	 * fields other than the tracepoint args will require the
+	 * tplist output to be adjusted.
+	 */
+	TP_STRUCT__entry(
+		__field(void*, ring)
+		__field(void*, desc)
+		__field(void*, buf)
+		__string(devname, ring->netdev->name)
+	),
+
+	TP_fast_assign(
+		__entry->ring = ring;
+		__entry->desc = desc;
+		__entry->buf = buf;
+		__assign_str(devname, ring->netdev->name);
+	),
+
+	TP_printk(
+		"netdev: %s ring: %p desc: %p buf %p",
+		__get_str(devname), __entry->ring,
+		__entry->desc, __entry->buf)
+);
+
+DEFINE_EVENT(
+	i40evf_tx_template, i40evf_clean_tx_irq,
+	TP_PROTO(struct i40e_ring *ring,
+		 struct i40e_tx_desc *desc,
+		 struct i40e_tx_buffer *buf),
+
+	TP_ARGS(ring, desc, buf));
+
+DEFINE_EVENT(
+	i40evf_tx_template, i40evf_clean_tx_irq_unmap,
+	TP_PROTO(struct i40e_ring *ring,
+		 struct i40e_tx_desc *desc,
+		 struct i40e_tx_buffer *buf),
+
+	TP_ARGS(ring, desc, buf));
+
+DECLARE_EVENT_CLASS(
+	i40evf_rx_template,
+
+	TP_PROTO(struct i40e_ring *ring,
+		 union i40e_32byte_rx_desc *desc,
+		 struct sk_buff *skb),
+
+	TP_ARGS(ring, desc, skb),
+
+	TP_STRUCT__entry(
+		__field(void*, ring)
+		__field(void*, desc)
+		__field(void*, skb)
+		__string(devname, ring->netdev->name)
+	),
+
+	TP_fast_assign(
+		__entry->ring = ring;
+		__entry->desc = desc;
+		__entry->skb = skb;
+		__assign_str(devname, ring->netdev->name);
+	),
+
+	TP_printk(
+		"netdev: %s ring: %p desc: %p skb %p",
+		__get_str(devname), __entry->ring,
+		__entry->desc, __entry->skb)
+);
+
+DEFINE_EVENT(
+	i40evf_rx_template, i40evf_clean_rx_irq,
+	TP_PROTO(struct i40e_ring *ring,
+		 union i40e_32byte_rx_desc *desc,
+		 struct sk_buff *skb),
+
+	TP_ARGS(ring, desc, skb));
+
+DEFINE_EVENT(
+	i40evf_rx_template, i40evf_clean_rx_irq_rx,
+	TP_PROTO(struct i40e_ring *ring,
+		 union i40e_32byte_rx_desc *desc,
+		 struct sk_buff *skb),
+
+	TP_ARGS(ring, desc, skb));
+
+DECLARE_EVENT_CLASS(
+	i40evf_xmit_template,
+
+	TP_PROTO(struct sk_buff *skb,
+		 struct i40e_ring *ring),
+
+	TP_ARGS(skb, ring),
+
+	TP_STRUCT__entry(
+		__field(void*, skb)
+		__field(void*, ring)
+		__string(devname, ring->netdev->name)
+	),
+
+	TP_fast_assign(
+		__entry->skb = skb;
+		__entry->ring = ring;
+		__assign_str(devname, ring->netdev->name);
+	),
+
+	TP_printk(
+		"netdev: %s skb: %p ring: %p",
+		__get_str(devname), __entry->skb,
+		__entry->ring)
+);
+
+DEFINE_EVENT(
+	i40evf_xmit_template, i40evf_xmit_frame_ring,
+	TP_PROTO(struct sk_buff *skb,
+		 struct i40e_ring *ring),
+
+	TP_ARGS(skb, ring));
+
+DEFINE_EVENT(
+	i40evf_xmit_template, i40evf_xmit_frame_ring_drop,
+	TP_PROTO(struct sk_buff *skb,
+		 struct i40e_ring *ring),
+
+	TP_ARGS(skb, ring));
+
+/* Events unique to the VF. */
+
+#endif /* _I40E_TRACE_H_ */
+/* This must be outside ifdef _I40E_TRACE_H */
+
+/* This trace include file is not located in the .../include/trace
+ * with the kernel tracepoint definitions, because we're a loadable
+ * module.
+ */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE i40e_trace
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c91fcf43ccbc..dfe241a12ad0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -28,6 +28,7 @@
 #include <net/busy_poll.h>
 
 #include "i40evf.h"
+#include "i40e_trace.h"
 #include "i40e_prototype.h"
 
 static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
@@ -137,10 +138,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw)
 {
 	u32 head, tail;
 
-	if (!in_sw)
-		head = i40e_get_head(ring);
-	else
-		head = ring->next_to_clean;
+	head = ring->next_to_clean;
 	tail = readl(ring->tail);
 
 	if (head != tail)
@@ -165,7 +163,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 {
 	u16 i = tx_ring->next_to_clean;
 	struct i40e_tx_buffer *tx_buf;
-	struct i40e_tx_desc *tx_head;
 	struct i40e_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
 	unsigned int budget = vsi->work_limit;
@@ -174,8 +171,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 	tx_desc = I40E_TX_DESC(tx_ring, i);
 	i -= tx_ring->count;
 
-	tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring));
-
 	do {
 		struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
 
@@ -186,8 +181,10 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		/* prevent any other reads prior to eop_desc */
 		read_barrier_depends();
 
-		/* we have caught up to head, no work left to do */
-		if (tx_head == tx_desc)
+		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
+		/* if the descriptor isn't done, no work yet to do */
+		if (!(eop_desc->cmd_type_offset_bsz &
+		      cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
 			break;
 
 		/* clear next_to_watch to prevent false hangs */
@@ -212,6 +209,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
+			i40e_trace(clean_tx_irq_unmap,
+				   tx_ring, tx_desc, tx_buf);
 
 			tx_buf++;
 			tx_desc++;
@@ -267,7 +266,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 		if (budget &&
 		    ((j / WB_STRIDE) == 0) && (j > 0) &&
-		    !test_bit(__I40E_DOWN, &vsi->state) &&
+		    !test_bit(__I40E_VSI_DOWN, vsi->state) &&
 		    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
 			tx_ring->arm_wb = true;
 	}
@@ -285,7 +284,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->queue_index) &&
-		   !test_bit(__I40E_DOWN, &vsi->state)) {
+		   !test_bit(__I40E_VSI_DOWN, vsi->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 			++tx_ring->tx_stats.restart_queue;
@@ -464,10 +463,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
 
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
-	/* add u32 for head writeback, align after this takes care of
-	 * guaranteeing this is at least one cache line in size
-	 */
-	tx_ring->size += sizeof(u32);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 	tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
 					   &tx_ring->dma, GFP_KERNEL);
@@ -493,7 +488,6 @@ err:
  **/
 void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -513,8 +507,22 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
-		__free_pages(rx_bi->page, 0);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->dma,
+					      rx_bi->page_offset,
+					      rx_ring->rx_buf_len,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     i40e_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
+
+		__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
 
 		rx_bi->page = NULL;
 		rx_bi->page_offset = 0;
@@ -615,6 +623,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
 }
 
 /**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
+/**
  * i40e_alloc_mapped_page - recycle or make a new page
  * @rx_ring: ring to use
  * @bi: rx_buffer struct to modify
@@ -635,27 +654,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* alloc new page for storage */
-	page = dev_alloc_page();
+	page = dev_alloc_pages(i40e_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_page_failed++;
 		return false;
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 i40e_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 I40E_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
 	 */
 	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_pages(page, 0);
+		__free_pages(page, i40e_rx_pg_order(rx_ring));
 		rx_ring->rx_stats.alloc_page_failed++;
 		return false;
 	}
 
 	bi->dma = dma;
 	bi->page = page;
-	bi->page_offset = 0;
+	bi->page_offset = i40e_rx_offset(rx_ring);
+
+	/* initialize pagecnt_bias to 1 representing we fully own page */
+	bi->pagecnt_bias = 1;
 
 	return true;
 }
@@ -702,6 +727,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 rx_ring->rx_buf_len,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -742,8 +773,6 @@ no_buffers:
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
  **/
 static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    struct sk_buff *skb,
@@ -806,13 +835,6 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* If there is an outer header present that might contain a checksum
-	 * we need to bump the checksum level by 1 to reflect the fact that
-	 * we are indicating we validated the inner checksum.
-	 */
-	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
-		skb->csum_level = 1;
-
 	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
 	switch (decoded.inner_prot) {
 	case I40E_RX_PTYPE_INNER_PROT_TCP:
@@ -895,12 +917,12 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring,
 {
 	i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 
-	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
 	i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
+
+	/* modifies the skb - consumes the enet header */
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
 /**
@@ -945,7 +967,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 /**
@@ -966,8 +991,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
  * the adapter for another receive
  *
  * @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
  *
  * If page is reusable, rx_buffer->page_offset is adjusted to point to
  * an unused region in the page.
@@ -990,13 +1013,10 @@ static inline bool i40e_page_is_reusable(struct page *page)
  *
  * In either case, if the page is reusable its refcount is increased.
  **/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
-				   struct page *page,
-				   const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 {
-#if (PAGE_SIZE >= 8192)
-	unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
-#endif
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* Is any reuse possible? */
 	if (unlikely(!i40e_page_is_reusable(page)))
@@ -1004,21 +1024,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
-	if (rx_buffer->page_offset > last_offset)
+#define I40E_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048)
+	if (rx_buffer->page_offset > I40E_LAST_OFFSET)
 		return false;
 #endif
 
-	/* Inc ref count on page before passing it up to the stack */
-	get_page(page);
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
+	 */
+	if (unlikely(!pagecnt_bias)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
@@ -1027,145 +1049,201 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
  * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
  * @rx_buffer: buffer containing page to add
- * @size: packet length from rx_desc
  * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
  *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
  **/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
 			     struct i40e_rx_buffer *rx_buffer,
-			     unsigned int size,
-			     struct sk_buff *skb)
+			     struct sk_buff *skb,
+			     unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = I40E_RXBUFFER_2048;
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
 #endif
-	unsigned int pull_len;
-
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
 
-	/* will the data fit in the skb we allocated? if so, just
-	 * copy it as it is pretty small anyway
-	 */
-	if (size <= I40E_RX_HDR_SIZE) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
-		/* page is reusable, we can reuse buffer as-is */
-		if (likely(i40e_page_is_reusable(page)))
-			return true;
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
 
-		/* this page cannot be reused so discard it */
-		__free_pages(page, 0);
-		return false;
-	}
+	/* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
 
-	/* we need the header to contain the greater of either
-	 * ETH_HLEN or 60 bytes if the skb->len is less than
-	 * 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+/**
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @size: size of buffer to add to skb
+ *
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
+ */
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+						 const unsigned int size)
+{
+	struct i40e_rx_buffer *rx_buffer;
 
-	/* align pull length to size of long to optimize
-	 * memcpy performance
-	 */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
 
-	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
 
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	/* We have pulled a buffer for use, so decrement pagecnt_bias */
+	rx_buffer->pagecnt_bias--;
 
-	return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+	return rx_buffer;
 }
 
 /**
- * i40evf_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
  *
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function allocates an skb.  It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
  */
-static inline
-struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
-				       union i40e_rx_desc *rx_desc,
-				       struct sk_buff *skb)
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+					  struct i40e_rx_buffer *rx_buffer,
+					  unsigned int size)
 {
-	u64 local_status_error_len =
-		le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	unsigned int size =
-		(local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
-	struct i40e_rx_buffer *rx_buffer;
-	struct page *page;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	unsigned int headlen;
+	struct sk_buff *skb;
 
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       I40E_RX_HDR_SIZE,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > I40E_RX_HDR_SIZE)
+		headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+	/* update all of the pointers */
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				rx_buffer->page_offset + headlen,
+				size, truesize);
+
+		/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		/* buffer is unused, reset bias back to rx_buffer */
+		rx_buffer->pagecnt_bias++;
+	}
+
+	return skb;
+}
 
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) + rx_buffer->page_offset;
+/**
+ * i40e_build_skb - Build skb around an existing buffer
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buffer: Rx buffer to pull data from
+ * @size: size of buffer to add to skb
+ *
+ * This function builds an skb around an existing Rx buffer, taking care
+ * to set up the skb correctly and avoid any memcpy overhead.
+ */
+static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
+				      struct i40e_rx_buffer *rx_buffer,
+				      unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	struct sk_buff *skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
+	/* build an skb around the page buffer */
+	skb = build_skb(va - I40E_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* allocate a skb to store the frags */
-		skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-				       I40E_RX_HDR_SIZE,
-				       GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_buff_failed++;
-			return NULL;
-		}
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, I40E_SKB_PAD);
+	__skb_put(skb, size);
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
-	}
+	/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
 
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
+	return skb;
+}
 
-	/* pull page into skb */
-	if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer.  It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+			       struct i40e_rx_buffer *rx_buffer)
+{
+	if (i40e_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		i40e_reuse_rx_page(rx_ring, rx_buffer);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     i40e_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of buffer_info */
 	rx_buffer->page = NULL;
-
-	return skb;
 }
 
 /**
@@ -1221,7 +1299,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < budget)) {
+		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
+		unsigned int size;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1238,22 +1318,40 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		 * hardware wrote DD then the length will be non-zero
 		 */
-		if (!i40e_test_staterr(rx_desc,
-				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
-			break;
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 
 		/* This memory barrier is needed to keep us from reading
-		 * any other fields out of the rx_desc until we know the
-		 * DD bit is set.
+		 * any other fields out of the rx_desc until we have
+		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
 
-		skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb);
-		if (!skb)
+		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		if (!size)
 			break;
 
+		i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb);
+		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+		/* retrieve a buffer from the ring */
+		if (skb)
+			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = i40e_build_skb(rx_ring, rx_buffer, size);
+		else
+			skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			rx_buffer->pagecnt_bias++;
+			break;
+		}
+
+		i40e_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1266,6 +1364,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
 			dev_kfree_skb_any(skb);
+			skb = NULL;
 			continue;
 		}
 
@@ -1288,6 +1387,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
 
+		i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 		skb = NULL;
 
@@ -1408,7 +1508,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	}
 
 enable_int:
-	if (!test_bit(__I40E_DOWN, &vsi->state))
+	if (!test_bit(__I40E_VSI_DOWN, vsi->state))
 		wr32(hw, INTREG(vector - 1), txval);
 
 	if (q_vector->itr_countdown)
@@ -1437,7 +1537,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	int budget_per_ring;
 	int work_done = 0;
 
-	if (test_bit(__I40E_DOWN, &vsi->state)) {
+	if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
 		napi_complete(napi);
 		return 0;
 	}
@@ -1980,7 +2080,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	u16 i = tx_ring->next_to_use;
 	u32 td_tag = 0;
 	dma_addr_t dma;
-	u16 desc_count = 1;
 
 	if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
 		td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -2016,7 +2115,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 			tx_desc++;
 			i++;
-			desc_count++;
 
 			if (i == tx_ring->count) {
 				tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2038,7 +2136,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 		tx_desc++;
 		i++;
-		desc_count++;
 
 		if (i == tx_ring->count) {
 			tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2064,46 +2161,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	/* write last descriptor with EOP bit */
-	td_cmd |= I40E_TX_DESC_CMD_EOP;
-
-	/* We can OR these values together as they both are checked against
-	 * 4 below and at this point desc_count will be used as a boolean value
-	 * after this if/else block.
-	 */
-	desc_count |= ++tx_ring->packet_stride;
-
-	/* Algorithm to optimize tail and RS bit setting:
-	 * if queue is stopped
-	 *	mark RS bit
-	 *	reset packet counter
-	 * else if xmit_more is supported and is true
-	 *	advance packet counter to 4
-	 *	reset desc_count to 0
-	 *
-	 * if desc_count >= 4
-	 *	mark RS bit
-	 *	reset packet counter
-	 * if desc_count > 0
-	 *	update tail
-	 *
-	 * Note: If there are less than 4 descriptors
-	 * pending and interrupts were disabled the service task will
-	 * trigger a force WB.
-	 */
-	if (netif_xmit_stopped(txring_txq(tx_ring))) {
-		goto do_rs;
-	} else if (skb->xmit_more) {
-		/* set stride to arm on next packet and reset desc_count */
-		tx_ring->packet_stride = WB_STRIDE;
-		desc_count = 0;
-	} else if (desc_count >= WB_STRIDE) {
-do_rs:
-		/* write last descriptor with RS bit set */
-		td_cmd |= I40E_TX_DESC_CMD_RS;
-		tx_ring->packet_stride = 0;
-	}
-
+	/* write last descriptor with RS and EOP bits */
+	td_cmd |= I40E_TXD_CMD;
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
@@ -2119,7 +2178,7 @@ do_rs:
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (desc_count) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
@@ -2170,6 +2229,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	/* prefetch the data, we'll need it later */
 	prefetch(skb->data);
 
+	i40e_trace(xmit_frame_ring, skb, tx_ring);
+
 	count = i40e_xmit_descriptor_count(skb);
 	if (i40e_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb)) {
@@ -2237,6 +2298,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 out_drop:
+	i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring);
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 8274ba68bd32..901282c87cf6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -104,10 +104,9 @@ enum i40e_dyn_idx_t {
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
+#define I40E_RXBUFFER_1536  1536  /* 128B aligned standard Ethernet frame */
 #define I40E_RXBUFFER_2048  2048
-#define I40E_RXBUFFER_3072  3072   /* For FCoE MTU of 2158 */
-#define I40E_RXBUFFER_4096  4096
-#define I40E_RXBUFFER_8192  8192
+#define I40E_RXBUFFER_3072  3072  /* Used for large frames w/ padding */
 #define I40E_MAX_RXBUFFER   9728  /* largest size for single descriptor */
 
 /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
@@ -120,6 +119,61 @@ enum i40e_dyn_idx_t {
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+/* Attempt to maximize the headroom available for incoming frames.  We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame.  This leaves us with 512 bytes of room.  From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ *	 up negative.  In these cases we should fall back to the legacy
+ *	 receive path.
+ */
+#if (PAGE_SIZE < 8192)
+#define I40E_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048))
+
+static inline int i40e_compute_pad(int rx_buf_len)
+{
+	int page_size, pad_size;
+
+	page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+	pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+	return pad_size;
+}
+
+static inline int i40e_skb_pad(void)
+{
+	int rx_buf_len;
+
+	/* If a 2K buffer cannot handle a standard Ethernet frame then
+	 * optimize padding for a 3K buffer instead of a 1.5K buffer.
+	 *
+	 * For a 3K buffer we need to add enough padding to allow for
+	 * tailroom due to NET_IP_ALIGN possibly shifting us out of
+	 * cache-line alignment.
+	 */
+	if (I40E_2K_TOO_SMALL_WITH_PADDING)
+		rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
+	else
+		rx_buf_len = I40E_RXBUFFER_1536;
+
+	/* if needed make room for NET_IP_ALIGN */
+	rx_buf_len -= NET_IP_ALIGN;
+
+	return i40e_compute_pad(rx_buf_len);
+}
+
+#define I40E_SKB_PAD i40e_skb_pad()
+#else
+#define I40E_2K_TOO_SMALL_WITH_PADDING false
+#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#endif
+
 /**
  * i40e_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -241,7 +295,12 @@ struct i40e_tx_buffer {
 struct i40e_rx_buffer {
 	dma_addr_t dma;
 	struct page *page;
-	unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
 };
 
 struct i40e_queue_stats {
@@ -321,7 +380,8 @@ struct i40e_ring {
 	u8 packet_stride;
 
 	u16 flags;
-#define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
+#define I40E_TXR_FLAGS_WB_ON_ITR		BIT(0)
+#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED	BIT(1)
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
@@ -349,6 +409,21 @@ struct i40e_ring {
 					 */
 } ____cacheline_internodealigned_in_smp;
 
+static inline bool ring_uses_build_skb(struct i40e_ring *ring)
+{
+	return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED);
+}
+
+static inline void set_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+	ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
+static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+	ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
 enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
@@ -370,6 +445,17 @@ struct i40e_ring_container {
 #define i40e_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
+static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring->rx_buf_len > (PAGE_SIZE / 2))
+		return 1;
+#endif
+	return 0;
+}
+
+#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring))
+
 bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
 netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
 void i40evf_clean_tx_ring(struct i40e_ring *tx_ring);
@@ -385,20 +471,6 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40evf_chk_linearize(struct sk_buff *skb);
 
 /**
- * i40e_get_head - Retrieve head from head writeback
- * @tx_ring: Tx ring to fetch head of
- *
- * Returns value of Tx ring head based on value stored
- * in head write-back location
- **/
-static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
-{
-	void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
-
-	return le32_to_cpu(*(volatile __le32 *)head);
-}
-
-/**
  * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
@@ -460,19 +532,7 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
 	/* we can support up to 8 data buffers for a single send */
 	return count != I40E_MAX_BUFFER_TXD;
 }
-
-/**
- * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
- * @ptype: the packet type field from Rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
-	return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
-	       (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
 /**
- * txring_txq - Find the netdev Tx ring based on the i40e Tx ring
  * @ring: Tx ring to find the netdev equivalent of
  **/
 static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 16bb88084bb9..bde7f24af1c6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -78,6 +78,7 @@ enum i40e_debug_mask {
 	I40E_DEBUG_DCB			= 0x00000400,
 	I40E_DEBUG_DIAG			= 0x00000800,
 	I40E_DEBUG_FD			= 0x00001000,
+	I40E_DEBUG_PACKAGE		= 0x00002000,
 
 	I40E_DEBUG_AQ_MESSAGE		= 0x01000000,
 	I40E_DEBUG_AQ_DESCRIPTOR	= 0x02000000,
@@ -1396,4 +1397,83 @@ enum i40e_reset_type {
 #define I40E_FD_INSET_FLEX_WORD57_SHIFT		10
 #define I40E_FD_INSET_FLEX_WORD57_MASK		(0x1ULL << \
 					I40E_FD_INSET_FLEX_WORD57_SHIFT)
+
+/* Version format for PPP */
+struct i40e_ppp_version {
+	u8 major;
+	u8 minor;
+	u8 update;
+	u8 draft;
+};
+
+#define I40E_PPP_NAME_SIZE	32
+
+/* Package header */
+struct i40e_package_header {
+	struct i40e_ppp_version version;
+	u32 segment_count;
+	u32 segment_offset[1];
+};
+
+/* Generic segment header */
+struct i40e_generic_seg_header {
+#define SEGMENT_TYPE_METADATA	0x00000001
+#define SEGMENT_TYPE_NOTES	0x00000002
+#define SEGMENT_TYPE_I40E	0x00000011
+#define SEGMENT_TYPE_X722	0x00000012
+	u32 type;
+	struct i40e_ppp_version version;
+	u32 size;
+	char name[I40E_PPP_NAME_SIZE];
+};
+
+struct i40e_metadata_segment {
+	struct i40e_generic_seg_header header;
+	struct i40e_ppp_version version;
+	u32 track_id;
+	char name[I40E_PPP_NAME_SIZE];
+};
+
+struct i40e_device_id_entry {
+	u32 vendor_dev_id;
+	u32 sub_vendor_dev_id;
+};
+
+struct i40e_profile_segment {
+	struct i40e_generic_seg_header header;
+	struct i40e_ppp_version version;
+	char name[I40E_PPP_NAME_SIZE];
+	u32 device_table_count;
+	struct i40e_device_id_entry device_table[1];
+};
+
+struct i40e_section_table {
+	u32 section_count;
+	u32 section_offset[1];
+};
+
+struct i40e_profile_section_header {
+	u16 tbl_size;
+	u16 data_end;
+	struct {
+#define SECTION_TYPE_INFO	0x00000010
+#define SECTION_TYPE_MMIO	0x00000800
+#define SECTION_TYPE_AQ		0x00000801
+#define SECTION_TYPE_NOTE	0x80000000
+#define SECTION_TYPE_NAME	0x80000001
+		u32 type;
+		u32 offset;
+		u32 size;
+	} section;
+};
+
+struct i40e_profile_info {
+	u32 track_id;
+	struct i40e_ppp_version version;
+	u8 op;
+#define I40E_PPP_ADD_TRACKID		0x01
+#define I40E_PPP_REMOVE_TRACKID	0x02
+	u8 reserved[7];
+	u8 name[I40E_PPP_NAME_SIZE];
+};
 #endif /* _I40E_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
index d38a2b2aea2b..c5ad0388c3d5 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
@@ -81,7 +81,9 @@ enum i40e_virtchnl_ops {
 	I40E_VIRTCHNL_OP_GET_STATS = 15,
 	I40E_VIRTCHNL_OP_FCOE = 16,
 	I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+	I40E_VIRTCHNL_OP_IWARP = 20,
 	I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21,
+	I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22,
 	I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23,
 	I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24,
 	I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25,
@@ -161,7 +163,8 @@ struct i40e_virtchnl_vsi_resource {
 #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING	0x00020000
 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2	0x00040000
 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF		0X00080000
-#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM	0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP		0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM	0X00200000
 
 #define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \
 				    I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \
@@ -393,6 +396,37 @@ struct i40e_virtchnl_pf_event {
 	int severity;
 };
 
+/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP
+ * VF uses this message to request PF to map IWARP vectors to IWARP queues.
+ * The request for this originates from the VF IWARP driver through
+ * a client interface between VF LAN and VF IWARP driver.
+ * A vector could have an AEQ and CEQ attached to it although
+ * there is a single AEQ per VF IWARP instance in which case
+ * most vectors will have an INVALID_IDX for aeq and valid idx for ceq.
+ * There will never be a case where there will be multiple CEQs attached
+ * to a single vector.
+ * PF configures interrupt mapping and returns status.
+ */
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX  0xFFFF
+
+struct i40e_virtchnl_iwarp_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_virtchnl_iwarp_qvlist_info {
+	u32 num_vectors;
+	struct i40e_virtchnl_iwarp_qv_info qv_info[1];
+};
+
 /* VF reset states - these are written into the RSTAT register:
  * I40E_VFGEN_RSTAT1 on the PF
  * I40E_VFGEN_RSTAT on the VF
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 00c42d803276..b8ada6d8d890 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -49,6 +49,13 @@
 #define DEFAULT_DEBUG_LEVEL_SHIFT 3
 #define PFX "i40evf: "
 
+/* VSI state flags shared with common code */
+enum i40evf_vsi_state_t {
+	__I40E_VSI_DOWN,
+	/* This must be last as it determines the size of the BITMAP */
+	__I40E_VSI_STATE_SIZE__,
+};
+
 /* dummy struct to make common code less painful */
 struct i40e_vsi {
 	struct i40evf_adapter *back;
@@ -56,10 +63,11 @@ struct i40e_vsi {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	u16 seid;
 	u16 id;
-	unsigned long state;
+	DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__);
 	int base_vector;
 	u16 work_limit;
 	u16 qs_handle;
+	void *priv;     /* client driver data reference. */
 };
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
@@ -71,10 +79,6 @@ struct i40e_vsi {
 #define I40EVF_MAX_RXD		4096
 #define I40EVF_MIN_RXD		64
 #define I40EVF_REQ_DESCRIPTOR_MULTIPLE	32
-
-/* Supported Rx Buffer Sizes */
-#define I40EVF_RXBUFFER_2048	2048
-#define I40EVF_MAX_RXBUFFER	16384  /* largest size for single descriptor */
 #define I40EVF_MAX_AQ_BUF_SIZE	4096
 #define I40EVF_AQ_LEN		32
 #define I40EVF_AQ_MAX_ERR	20 /* times to try before resetting AQ */
@@ -169,15 +173,15 @@ enum i40evf_state_t {
 
 enum i40evf_critical_section_t {
 	__I40EVF_IN_CRITICAL_TASK,	/* cannot be interrupted */
+	__I40EVF_IN_CLIENT_TASK,
 };
-/* make common code happy */
-#define __I40E_DOWN __I40EVF_DOWN
 
 /* board specific private data structure */
 struct i40evf_adapter {
 	struct timer_list watchdog_timer;
 	struct work_struct reset_task;
 	struct work_struct adminq_task;
+	struct delayed_work client_task;
 	struct delayed_work init_task;
 	struct i40e_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
@@ -195,15 +199,16 @@ struct i40evf_adapter {
 	u64 hw_csum_rx_error;
 	u32 rx_desc_count;
 	int num_msix_vectors;
+	int num_iwarp_msix;
+	int iwarp_base_vector;
 	u32 client_pending;
+	struct i40e_client_instance *cinst;
 	struct msix_entry *msix_entries;
 
 	u32 flags;
 #define I40EVF_FLAG_RX_CSUM_ENABLED		BIT(0)
-#define I40EVF_FLAG_IN_NETPOLL			BIT(4)
 #define I40EVF_FLAG_IMIR_ENABLED		BIT(5)
 #define I40EVF_FLAG_MQ_CAPABLE			BIT(6)
-#define I40EVF_FLAG_NEED_LINK_UPDATE		BIT(7)
 #define I40EVF_FLAG_PF_COMMS_FAILED		BIT(8)
 #define I40EVF_FLAG_RESET_PENDING		BIT(9)
 #define I40EVF_FLAG_RESET_NEEDED		BIT(10)
@@ -211,15 +216,18 @@ struct i40evf_adapter {
 #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE	BIT(12)
 #define I40EVF_FLAG_ADDR_SET_BY_PF		BIT(13)
 #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED	BIT(14)
-#define I40EVF_FLAG_PROMISC_ON			BIT(15)
-#define I40EVF_FLAG_ALLMULTI_ON			BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_OPEN		BIT(15)
+#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE		BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS	BIT(17)
+#define I40EVF_FLAG_PROMISC_ON			BIT(18)
+#define I40EVF_FLAG_ALLMULTI_ON			BIT(19)
+#define I40EVF_FLAG_LEGACY_RX			BIT(20)
 /* duplicates for common code */
-#define I40E_FLAG_FDIR_ATR_ENABLED		0
 #define I40E_FLAG_DCB_ENABLED			0
-#define I40E_FLAG_IN_NETPOLL			I40EVF_FLAG_IN_NETPOLL
 #define I40E_FLAG_RX_CSUM_ENABLED		I40EVF_FLAG_RX_CSUM_ENABLED
 #define I40E_FLAG_WB_ON_ITR_CAPABLE		I40EVF_FLAG_WB_ON_ITR_CAPABLE
 #define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE	I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE
+#define I40E_FLAG_LEGACY_RX			I40EVF_FLAG_LEGACY_RX
 	/* flags for admin queue service task */
 	u32 aq_required;
 #define I40EVF_FLAG_AQ_ENABLE_QUEUES		BIT(0)
@@ -246,7 +254,6 @@ struct i40evf_adapter {
 	/* OS defined structs */
 	struct net_device *netdev;
 	struct pci_dev *pdev;
-	struct net_device_stats net_stats;
 
 	struct i40e_hw hw; /* defined in i40e_type.h */
 
@@ -258,10 +265,11 @@ struct i40evf_adapter {
 	bool link_up;
 	enum i40e_aq_link_speed link_speed;
 	enum i40e_virtchnl_ops current_op;
-#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \
+#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
 			    (_a)->vf_res->vf_offload_flags & \
 				I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \
 			    0)
+#define CLIENT_ENABLED(_a) ((_a)->cinst)
 /* RSS by the PF should be preferred over RSS via other methods. */
 #define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \
 		    I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF)
@@ -292,6 +300,12 @@ struct i40evf_adapter {
 
 /* Ethtool Private Flags */
 
+/* lan device */
+struct i40e_device {
+	struct list_head list;
+	struct i40evf_adapter *vf;
+};
+
 /* needed by i40evf_ethtool.c */
 extern char i40evf_driver_name[];
 extern const char i40evf_driver_version[];
@@ -337,4 +351,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 				enum i40e_virtchnl_ops v_opcode,
 				i40e_status v_retval, u8 *msg, u16 msglen);
 int i40evf_config_rss(struct i40evf_adapter *adapter);
+int i40evf_lan_add_device(struct i40evf_adapter *adapter);
+int i40evf_lan_del_device(struct i40evf_adapter *adapter);
+void i40evf_client_subtask(struct i40evf_adapter *adapter);
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len);
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi);
+void i40evf_notify_client_open(struct i40e_vsi *vsi);
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset);
 #endif /* _I40EVF_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
new file mode 100644
index 000000000000..ee737680a0e9
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
@@ -0,0 +1,564 @@
+#include <linux/list.h>
+#include <linux/errno.h>
+
+#include "i40evf.h"
+#include "i40e_prototype.h"
+#include "i40evf_client.h"
+
+static
+const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR;
+static struct i40e_client *vf_registered_client;
+static LIST_HEAD(i40evf_devices);
+static DEFINE_MUTEX(i40evf_device_mutex);
+
+static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
+				       struct i40e_client *client,
+				       u8 *msg, u16 len);
+
+static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
+				      struct i40e_client *client,
+				      struct i40e_qvlist_info *qvlist_info);
+
+static struct i40e_ops i40evf_lan_ops = {
+	.virtchnl_send = i40evf_client_virtchnl_send,
+	.setup_qvlist = i40evf_client_setup_qvlist,
+};
+
+/**
+ * i40evf_notify_client_message - call the client message receive callback
+ * @vsi: the VSI associated with this client
+ * @msg: message buffer
+ * @len: length of message
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len)
+{
+	struct i40e_client_instance *cinst;
+
+	if (!vsi)
+		return;
+
+	cinst = vsi->back->cinst;
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->virtchnl_receive) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance virtchnl_receive function\n");
+		return;
+	}
+	cinst->client->ops->virtchnl_receive(&cinst->lan_info,  cinst->client,
+					     msg, len);
+}
+
+/**
+ * i40evf_notify_client_l2_params - call the client notify callback
+ * @vsi: the VSI with l2 param changes
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi)
+{
+	struct i40e_client_instance *cinst;
+	struct i40e_params params;
+
+	if (!vsi)
+		return;
+
+	cinst = vsi->back->cinst;
+	memset(&params, 0, sizeof(params));
+	params.mtu = vsi->netdev->mtu;
+	params.link_up = vsi->back->link_up;
+	params.qos.prio_qos[0].qs_handle = vsi->qs_handle;
+
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->l2_param_change) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance l2_param_change function\n");
+		return;
+	}
+	cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client,
+					    &params);
+}
+
+/**
+ * i40evf_notify_client_open - call the client open callback
+ * @vsi: the VSI with netdev opened
+ *
+ * If there is a client to this netdev, call the client with open
+ **/
+void i40evf_notify_client_open(struct i40e_vsi *vsi)
+{
+	struct i40evf_adapter *adapter = vsi->back;
+	struct i40e_client_instance *cinst = adapter->cinst;
+	int ret;
+
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->open) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance open function\n");
+		return;
+	}
+	if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) {
+		ret = cinst->client->ops->open(&cinst->lan_info, cinst->client);
+		if (!ret)
+			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+	}
+}
+
+/**
+ * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map
+ * @ldev: pointer to L2 context.
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int i40evf_client_release_qvlist(struct i40e_info *ldev)
+{
+	struct i40evf_adapter *adapter = ldev->vf;
+	i40e_status err;
+
+	if (adapter->aq_required)
+		return -EAGAIN;
+
+	err = i40e_aq_send_msg_to_pf(&adapter->hw,
+			I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
+			I40E_SUCCESS, NULL, 0, NULL);
+
+	if (err)
+		dev_err(&adapter->pdev->dev,
+			"Unable to send iWarp vector release message to PF, error %d, aq status %d\n",
+			err, adapter->hw.aq.asq_last_status);
+
+	return err;
+}
+
+/**
+ * i40evf_notify_client_close - call the client close callback
+ * @vsi: the VSI with netdev closed
+ * @reset: true when close called due to reset pending
+ *
+ * If there is a client to this netdev, call the client with close
+ **/
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset)
+{
+	struct i40evf_adapter *adapter = vsi->back;
+	struct i40e_client_instance *cinst = adapter->cinst;
+
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->close) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance close function\n");
+		return;
+	}
+	cinst->client->ops->close(&cinst->lan_info, cinst->client, reset);
+	i40evf_client_release_qvlist(&cinst->lan_info);
+	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+}
+
+/**
+ * i40evf_client_add_instance - add a client instance to the instance list
+ * @adapter: pointer to the board struct
+ * @client: pointer to a client struct in the client list.
+ *
+ * Returns cinst ptr on success, NULL on failure
+ **/
+static struct i40e_client_instance *
+i40evf_client_add_instance(struct i40evf_adapter *adapter)
+{
+	struct i40e_client_instance *cinst = NULL;
+	struct netdev_hw_addr *mac = NULL;
+	struct i40e_vsi *vsi = &adapter->vsi;
+	int i;
+
+	if (!vf_registered_client)
+		goto out;
+
+	if (adapter->cinst) {
+		cinst = adapter->cinst;
+		goto out;
+	}
+
+	cinst = kzalloc(sizeof(*cinst), GFP_KERNEL);
+	if (!cinst)
+		goto out;
+
+	cinst->lan_info.vf = (void *)adapter;
+	cinst->lan_info.netdev = vsi->netdev;
+	cinst->lan_info.pcidev = adapter->pdev;
+	cinst->lan_info.fid = 0;
+	cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF;
+	cinst->lan_info.hw_addr = adapter->hw.hw_addr;
+	cinst->lan_info.ops = &i40evf_lan_ops;
+	cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR;
+	cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR;
+	cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD;
+	set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state);
+
+	cinst->lan_info.msix_count = adapter->num_iwarp_msix;
+	cinst->lan_info.msix_entries =
+			&adapter->msix_entries[adapter->iwarp_base_vector];
+
+	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+		cinst->lan_info.params.qos.prio_qos[i].tc = 0;
+		cinst->lan_info.params.qos.prio_qos[i].qs_handle =
+								vsi->qs_handle;
+	}
+
+	mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list,
+			       struct netdev_hw_addr, list);
+	if (mac)
+		ether_addr_copy(cinst->lan_info.lanmac, mac->addr);
+	else
+		dev_err(&adapter->pdev->dev, "MAC address list is empty!\n");
+
+	cinst->client = vf_registered_client;
+	adapter->cinst = cinst;
+out:
+	return cinst;
+}
+
+/**
+ * i40evf_client_del_instance - removes a client instance from the list
+ * @adapter: pointer to the board struct
+ * @client: pointer to the client struct
+ *
+ **/
+static
+void i40evf_client_del_instance(struct i40evf_adapter *adapter)
+{
+	kfree(adapter->cinst);
+	adapter->cinst = NULL;
+}
+
+/**
+ * i40evf_client_subtask - client maintenance work
+ * @adapter: board private structure
+ **/
+void i40evf_client_subtask(struct i40evf_adapter *adapter)
+{
+	struct i40e_client *client = vf_registered_client;
+	struct i40e_client_instance *cinst;
+	int ret = 0;
+
+	if (adapter->state < __I40EVF_DOWN)
+		return;
+
+	/* first check client is registered */
+	if (!client)
+		return;
+
+	/* Add the client instance to the instance list */
+	cinst = i40evf_client_add_instance(adapter);
+	if (!cinst)
+		return;
+
+	dev_info(&adapter->pdev->dev, "Added instance of Client %s\n",
+		 client->name);
+
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+		/* Send an Open request to the client */
+
+		if (client->ops && client->ops->open)
+			ret = client->ops->open(&cinst->lan_info, client);
+		if (!ret)
+			set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+				&cinst->state);
+		else
+			/* remove client instance */
+			i40evf_client_del_instance(adapter);
+	}
+}
+
+/**
+ * i40evf_lan_add_device - add a lan device struct to the list of lan devices
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or none 0 on error
+ **/
+int i40evf_lan_add_device(struct i40evf_adapter *adapter)
+{
+	struct i40e_device *ldev;
+	int ret = 0;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry(ldev, &i40evf_devices, list) {
+		if (ldev->vf == adapter) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+	ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+	if (!ldev) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ldev->vf = adapter;
+	INIT_LIST_HEAD(&ldev->list);
+	list_add(&ldev->list, &i40evf_devices);
+	dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+		 adapter->hw.bus.bus_id, adapter->hw.bus.device,
+		 adapter->hw.bus.func);
+
+	/* Since in some cases register may have happened before a device gets
+	 * added, we can schedule a subtask to go initiate the clients.
+	 */
+	adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+
+out:
+	mutex_unlock(&i40evf_device_mutex);
+	return ret;
+}
+
+/**
+ * i40evf_lan_del_device - removes a lan device from the device list
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_lan_del_device(struct i40evf_adapter *adapter)
+{
+	struct i40e_device *ldev, *tmp;
+	int ret = -ENODEV;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) {
+		if (ldev->vf == adapter) {
+			dev_info(&adapter->pdev->dev,
+				 "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+				 adapter->hw.bus.bus_id, adapter->hw.bus.device,
+				 adapter->hw.bus.func);
+			list_del(&ldev->list);
+			kfree(ldev);
+			ret = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&i40evf_device_mutex);
+	return ret;
+}
+
+/**
+ * i40evf_client_release - release client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void i40evf_client_release(struct i40e_client *client)
+{
+	struct i40e_client_instance *cinst;
+	struct i40e_device *ldev;
+	struct i40evf_adapter *adapter;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry(ldev, &i40evf_devices, list) {
+		adapter = ldev->vf;
+		cinst = adapter->cinst;
+		if (!cinst)
+			continue;
+		if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+			if (client->ops && client->ops->close)
+				client->ops->close(&cinst->lan_info, client,
+						   false);
+			i40evf_client_release_qvlist(&cinst->lan_info);
+			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+
+			dev_warn(&adapter->pdev->dev,
+				 "Client %s instance closed\n", client->name);
+		}
+		/* delete the client instance */
+		i40evf_client_del_instance(adapter);
+		dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n",
+			 client->name);
+	}
+	mutex_unlock(&i40evf_device_mutex);
+}
+
+/**
+ * i40evf_client_prepare - prepare client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void i40evf_client_prepare(struct i40e_client *client)
+{
+	struct i40e_device *ldev;
+	struct i40evf_adapter *adapter;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry(ldev, &i40evf_devices, list) {
+		adapter = ldev->vf;
+		/* Signal the watchdog to service the client */
+		adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+	}
+	mutex_unlock(&i40evf_device_mutex);
+}
+
+/**
+ * i40evf_client_virtchnl_send - send a message to the PF instance
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @msg: pointer to message buffer
+ * @len: message length
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
+				       struct i40e_client *client,
+				       u8 *msg, u16 len)
+{
+	struct i40evf_adapter *adapter = ldev->vf;
+	i40e_status err;
+
+	if (adapter->aq_required)
+		return -EAGAIN;
+
+	err = i40e_aq_send_msg_to_pf(&adapter->hw, I40E_VIRTCHNL_OP_IWARP,
+				     I40E_SUCCESS, msg, len, NULL);
+	if (err)
+		dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n",
+			err, adapter->hw.aq.asq_last_status);
+
+	return err;
+}
+
+/**
+ * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @qv_info: queue and vector list
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
+				      struct i40e_client *client,
+				      struct i40e_qvlist_info *qvlist_info)
+{
+	struct i40e_virtchnl_iwarp_qvlist_info *v_qvlist_info;
+	struct i40evf_adapter *adapter = ldev->vf;
+	struct i40e_qv_info *qv_info;
+	i40e_status err;
+	u32 v_idx, i;
+	u32 msg_size;
+
+	if (adapter->aq_required)
+		return -EAGAIN;
+
+	/* A quick check on whether the vectors belong to the client */
+	for (i = 0; i < qvlist_info->num_vectors; i++) {
+		qv_info = &qvlist_info->qv_info[i];
+		if (!qv_info)
+			continue;
+		v_idx = qv_info->v_idx;
+		if ((v_idx >=
+		    (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) ||
+		    (v_idx < adapter->iwarp_base_vector))
+			return -EINVAL;
+	}
+
+	v_qvlist_info = (struct i40e_virtchnl_iwarp_qvlist_info *)qvlist_info;
+	msg_size = sizeof(struct i40e_virtchnl_iwarp_qvlist_info) +
+			(sizeof(struct i40e_virtchnl_iwarp_qv_info) *
+			(v_qvlist_info->num_vectors - 1));
+
+	adapter->client_pending |= BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP);
+	err = i40e_aq_send_msg_to_pf(&adapter->hw,
+			I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP,
+			I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL);
+
+	if (err) {
+		dev_err(&adapter->pdev->dev,
+			"Unable to send iWarp vector config message to PF, error %d, aq status %d\n",
+			err, adapter->hw.aq.asq_last_status);
+		goto out;
+	}
+
+	err = -EBUSY;
+	for (i = 0; i < 5; i++) {
+		msleep(100);
+		if (!(adapter->client_pending &
+		      BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) {
+			err = 0;
+			break;
+		}
+	}
+out:
+	return err;
+}
+
+/**
+ * i40evf_register_client - Register a i40e client driver with the L2 driver
+ * @client: pointer to the i40e_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_register_client(struct i40e_client *client)
+{
+	int ret = 0;
+
+	if (!client) {
+		ret = -EIO;
+		goto out;
+	}
+
+	if (strlen(client->name) == 0) {
+		pr_info("i40evf: Failed to register client with no name\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	if (vf_registered_client) {
+		pr_info("i40evf: Client %s has already been registered!\n",
+			client->name);
+		ret = -EEXIST;
+		goto out;
+	}
+
+	if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) ||
+	    (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) {
+		pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n",
+			client->name);
+		pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n",
+			client->version.major, client->version.minor,
+			client->version.build,
+			i40evf_client_interface_version_str);
+		ret = -EIO;
+		goto out;
+	}
+
+	vf_registered_client = client;
+
+	i40evf_client_prepare(client);
+
+	pr_info("i40evf: Registered client %s with return code %d\n",
+		client->name, ret);
+out:
+	return ret;
+}
+EXPORT_SYMBOL(i40evf_register_client);
+
+/**
+ * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver
+ * @client: pointer to the i40e_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_unregister_client(struct i40e_client *client)
+{
+	int ret = 0;
+
+	/* When a unregister request comes through we would have to send
+	 * a close for each of the client instances that were opened.
+	 * client_release function is called to handle this.
+	 */
+	i40evf_client_release(client);
+
+	if (vf_registered_client != client) {
+		pr_info("i40evf: Client %s has not been registered\n",
+			client->name);
+		ret = -ENODEV;
+		goto out;
+	}
+	vf_registered_client = NULL;
+	pr_info("i40evf: Unregistered client %s\n", client->name);
+out:
+	return ret;
+}
+EXPORT_SYMBOL(i40evf_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
new file mode 100644
index 000000000000..7d283c7506a5
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
@@ -0,0 +1,166 @@
+#ifndef _I40E_CLIENT_H_
+#define _I40E_CLIENT_H_
+
+#define I40EVF_CLIENT_STR_LENGTH 10
+
+/* Client interface version should be updated anytime there is a change in the
+ * existing APIs or data structures.
+ */
+#define I40EVF_CLIENT_VERSION_MAJOR 0
+#define I40EVF_CLIENT_VERSION_MINOR 01
+#define I40EVF_CLIENT_VERSION_BUILD 00
+#define I40EVF_CLIENT_VERSION_STR     \
+	__stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \
+	__stringify(I40EVF_CLIENT_VERSION_MINOR) "." \
+	__stringify(I40EVF_CLIENT_VERSION_BUILD)
+
+struct i40e_client_version {
+	u8 major;
+	u8 minor;
+	u8 build;
+	u8 rsvd;
+};
+
+enum i40e_client_state {
+	__I40E_CLIENT_NULL,
+	__I40E_CLIENT_REGISTERED
+};
+
+enum i40e_client_instance_state {
+	__I40E_CLIENT_INSTANCE_NONE,
+	__I40E_CLIENT_INSTANCE_OPENED,
+};
+
+struct i40e_ops;
+struct i40e_client;
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX	0xFFFF
+
+struct i40e_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_qvlist_info {
+	u32 num_vectors;
+	struct i40e_qv_info qv_info[1];
+};
+
+#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
+
+/* set of LAN parameters useful for clients managed by LAN */
+
+/* Struct to hold per priority info */
+struct i40e_prio_qos_params {
+	u16 qs_handle; /* qs handle for prio */
+	u8 tc; /* TC mapped to prio */
+	u8 reserved;
+};
+
+#define I40E_CLIENT_MAX_USER_PRIORITY        8
+/* Struct to hold Client QoS */
+struct i40e_qos_params {
+	struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
+};
+
+struct i40e_params {
+	struct i40e_qos_params qos;
+	u16 mtu;
+	u16 link_up; /* boolean */
+};
+
+/* Structure to hold LAN device info for a client device */
+struct i40e_info {
+	struct i40e_client_version version;
+	u8 lanmac[6];
+	struct net_device *netdev;
+	struct pci_dev *pcidev;
+	u8 __iomem *hw_addr;
+	u8 fid;	/* function id, PF id or VF id */
+#define I40E_CLIENT_FTYPE_PF 0
+#define I40E_CLIENT_FTYPE_VF 1
+	u8 ftype; /* function type, PF or VF */
+	void *vf; /* cast to i40evf_adapter */
+
+	/* All L2 params that could change during the life span of the device
+	 * and needs to be communicated to the client when they change
+	 */
+	struct i40e_params params;
+	struct i40e_ops *ops;
+
+	u16 msix_count;	 /* number of msix vectors*/
+	/* Array down below will be dynamically allocated based on msix_count */
+	struct msix_entry *msix_entries;
+	u16 itr_index; /* Which ITR index the PE driver is suppose to use */
+};
+
+struct i40e_ops {
+	/* setup_q_vector_list enables queues with a particular vector */
+	int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
+			    struct i40e_qvlist_info *qv_info);
+
+	u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
+			     u8 *msg, u16 len);
+
+	/* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
+	void (*request_reset)(struct i40e_info *ldev,
+			      struct i40e_client *client);
+};
+
+struct i40e_client_ops {
+	/* Should be called from register_client() or whenever the driver is
+	 * ready to create a specific client instance.
+	 */
+	int (*open)(struct i40e_info *ldev, struct i40e_client *client);
+
+	/* Should be closed when netdev is unavailable or when unregister
+	 * call comes in. If the close happens due to a reset, set the reset
+	 * bit to true.
+	 */
+	void (*close)(struct i40e_info *ldev, struct i40e_client *client,
+		      bool reset);
+
+	/* called when some l2 managed parameters changes - mss */
+	void (*l2_param_change)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				struct i40e_params *params);
+
+	/* called when a message is received from the PF */
+	int (*virtchnl_receive)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				u8 *msg, u16 len);
+};
+
+/* Client device */
+struct i40e_client_instance {
+	struct list_head list;
+	struct i40e_info lan_info;
+	struct i40e_client *client;
+	unsigned long  state;
+};
+
+struct i40e_client {
+	struct list_head list;		/* list of registered clients */
+	char name[I40EVF_CLIENT_STR_LENGTH];
+	struct i40e_client_version version;
+	unsigned long state;		/* client state */
+	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
+	u32 flags;
+#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
+#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
+	u8 type;
+#define I40E_CLIENT_IWARP 0
+	struct i40e_client_ops *ops;	/* client ops provided by the client */
+};
+
+/* used by clients */
+int i40evf_register_client(struct i40e_client *client);
+int i40evf_unregister_client(struct i40e_client *client);
+#endif /* _I40E_CLIENT_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 272d600c1ed0..9bb2cc7dd4e4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -63,52 +63,74 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = {
 #define I40EVF_STATS_LEN(_dev) \
 	(I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev))
 
+/* For now we have one and only one private flag and it is only defined
+ * when we have support for the SKIP_CPU_SYNC DMA attribute.  Instead
+ * of leaving all this code sitting around empty we will strip it unless
+ * our one private flag is actually available.
+ */
+struct i40evf_priv_flags {
+	char flag_string[ETH_GSTRING_LEN];
+	u32 flag;
+	bool read_only;
+};
+
+#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \
+	.flag_string = _name, \
+	.flag = _flag, \
+	.read_only = _read_only, \
+}
+
+static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = {
+	I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0),
+};
+
+#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags)
+
 /**
- * i40evf_get_settings - Get Link Speed and Duplex settings
+ * i40evf_get_link_ksettings - Get Link Speed and Duplex settings
  * @netdev: network interface device structure
- * @ecmd: ethtool command
+ * @cmd: ethtool command
  *
  * Reports speed/duplex settings. Because this is a VF, we don't know what
  * kind of link we really have, so we fake it.
  **/
-static int i40evf_get_settings(struct net_device *netdev,
-			       struct ethtool_cmd *ecmd)
+static int i40evf_get_link_ksettings(struct net_device *netdev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
-	ecmd->supported = 0;
-	ecmd->autoneg = AUTONEG_DISABLE;
-	ecmd->transceiver = XCVR_DUMMY1;
-	ecmd->port = PORT_NONE;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	cmd->base.autoneg = AUTONEG_DISABLE;
+	cmd->base.port = PORT_NONE;
 	/* Set speed and duplex */
 	switch (adapter->link_speed) {
 	case I40E_LINK_SPEED_40GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_40000);
+		cmd->base.speed = SPEED_40000;
 		break;
 	case I40E_LINK_SPEED_25GB:
 #ifdef SPEED_25000
-		ethtool_cmd_speed_set(ecmd, SPEED_25000);
+		cmd->base.speed = SPEED_25000;
 #else
 		netdev_info(netdev,
 			    "Speed is 25G, display not supported by this version of ethtool.\n");
 #endif
 		break;
 	case I40E_LINK_SPEED_20GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_20000);
+		cmd->base.speed = SPEED_20000;
 		break;
 	case I40E_LINK_SPEED_10GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_10000);
+		cmd->base.speed = SPEED_10000;
 		break;
 	case I40E_LINK_SPEED_1GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 		break;
 	case I40E_LINK_SPEED_100MB:
-		ethtool_cmd_speed_set(ecmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 		break;
 	default:
 		break;
 	}
-	ecmd->duplex = DUPLEX_FULL;
+	cmd->base.duplex = DUPLEX_FULL;
 
 	return 0;
 }
@@ -125,6 +147,8 @@ static int i40evf_get_sset_count(struct net_device *netdev, int sset)
 {
 	if (sset == ETH_SS_STATS)
 		return I40EVF_STATS_LEN(netdev);
+	else if (sset == ETH_SS_PRIV_FLAGS)
+		return I40EVF_PRIV_FLAGS_STR_LEN;
 	else
 		return -EINVAL;
 }
@@ -190,7 +214,83 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 			snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
+	} else if (sset == ETH_SS_PRIV_FLAGS) {
+		for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40evf_gstrings_priv_flags[i].flag_string);
+			p += ETH_GSTRING_LEN;
+		}
+	}
+}
+
+/**
+ * i40evf_get_priv_flags - report device private flags
+ * @dev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned.  Add new strings for each flag to the i40e_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ **/
+static u32 i40evf_get_priv_flags(struct net_device *netdev)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	u32 i, ret_flags = 0;
+
+	for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40evf_priv_flags *priv_flags;
+
+		priv_flags = &i40evf_gstrings_priv_flags[i];
+
+		if (priv_flags->flag & adapter->flags)
+			ret_flags |= BIT(i);
+	}
+
+	return ret_flags;
+}
+
+/**
+ * i40evf_set_priv_flags - set private flags
+ * @dev: network interface device structure
+ * @flags: bit flags to be set
+ **/
+static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	u64 changed_flags;
+	u32 i;
+
+	changed_flags = adapter->flags;
+
+	for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40evf_priv_flags *priv_flags;
+
+		priv_flags = &i40evf_gstrings_priv_flags[i];
+
+		if (priv_flags->read_only)
+			continue;
+
+		if (flags & BIT(i))
+			adapter->flags |= priv_flags->flag;
+		else
+			adapter->flags &= ~(priv_flags->flag);
+	}
+
+	/* check for flags that changed */
+	changed_flags ^= adapter->flags;
+
+	/* Process any additional changes needed as a result of flag changes. */
+
+	/* issue a reset to force legacy-rx change to take effect */
+	if (changed_flags & I40EVF_FLAG_LEGACY_RX) {
+		if (netif_running(netdev)) {
+			adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
+			schedule_work(&adapter->reset_task);
+		}
 	}
+
+	return 0;
 }
 
 /**
@@ -239,6 +339,7 @@ static void i40evf_get_drvinfo(struct net_device *netdev,
 	strlcpy(drvinfo->version, i40evf_driver_version, 32);
 	strlcpy(drvinfo->fw_version, "N/A", 4);
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN;
 }
 
 /**
@@ -643,7 +744,6 @@ static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir,
 }
 
 static const struct ethtool_ops i40evf_ethtool_ops = {
-	.get_settings		= i40evf_get_settings,
 	.get_drvinfo		= i40evf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= i40evf_get_ringparam,
@@ -651,6 +751,8 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
 	.get_strings		= i40evf_get_strings,
 	.get_ethtool_stats	= i40evf_get_ethtool_stats,
 	.get_sset_count		= i40evf_get_sset_count,
+	.get_priv_flags		= i40evf_get_priv_flags,
+	.set_priv_flags		= i40evf_set_priv_flags,
 	.get_msglevel		= i40evf_get_msglevel,
 	.set_msglevel		= i40evf_set_msglevel,
 	.get_coalesce		= i40evf_get_coalesce,
@@ -663,6 +765,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
 	.set_rxfh		= i40evf_set_rxfh,
 	.get_channels		= i40evf_get_channels,
 	.get_rxfh_key_size	= i40evf_get_rxfh_key_size,
+	.get_link_ksettings	= i40evf_get_link_ksettings,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index f35dcaac5bb7..ea110a730e16 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -26,6 +26,14 @@
 
 #include "i40evf.h"
 #include "i40e_prototype.h"
+#include "i40evf_client.h"
+/* All i40evf tracepoints are defined by the include below, which must
+ * be included exactly once across the whole kernel with
+ * CREATE_TRACE_POINTS defined
+ */
+#define CREATE_TRACE_POINTS
+#include "i40e_trace.h"
+
 static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter);
 static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter);
 static int i40evf_close(struct net_device *netdev);
@@ -36,9 +44,9 @@ static const char i40evf_driver_string[] =
 
 #define DRV_KERN "-k"
 
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 14
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \
@@ -489,7 +497,7 @@ static void i40evf_netpoll(struct net_device *netdev)
 	int i;
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &adapter->vsi.state))
+	if (test_bit(__I40E_VSI_DOWN, adapter->vsi.state))
 		return;
 
 	for (i = 0; i < q_vectors; i++)
@@ -685,12 +693,39 @@ static void i40evf_configure_tx(struct i40evf_adapter *adapter)
  **/
 static void i40evf_configure_rx(struct i40evf_adapter *adapter)
 {
+	unsigned int rx_buf_len = I40E_RXBUFFER_2048;
 	struct i40e_hw *hw = &adapter->hw;
 	int i;
 
+	/* Legacy Rx will always default to a 2048 buffer size. */
+#if (PAGE_SIZE < 8192)
+	if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) {
+		struct net_device *netdev = adapter->netdev;
+
+		/* For jumbo frames on systems with 4K pages we have to use
+		 * an order 1 page, so we might as well increase the size
+		 * of our Rx buffer to make better use of the available space
+		 */
+		rx_buf_len = I40E_RXBUFFER_3072;
+
+		/* We use a 1536 buffer size for configurations with
+		 * standard Ethernet mtu.  On x86 this gives us enough room
+		 * for shared info and 192 bytes of padding.
+		 */
+		if (!I40E_2K_TOO_SMALL_WITH_PADDING &&
+		    (netdev->mtu <= ETH_DATA_LEN))
+			rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+	}
+#endif
+
 	for (i = 0; i < adapter->num_active_queues; i++) {
 		adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i);
-		adapter->rx_rings[i].rx_buf_len = I40EVF_RXBUFFER_2048;
+		adapter->rx_rings[i].rx_buf_len = rx_buf_len;
+
+		if (adapter->flags & I40EVF_FLAG_LEGACY_RX)
+			clear_ring_build_skb_enabled(&adapter->rx_rings[i]);
+		else
+			set_ring_build_skb_enabled(&adapter->rx_rings[i]);
 	}
 }
 
@@ -1053,11 +1088,13 @@ static void i40evf_configure(struct i40evf_adapter *adapter)
 static void i40evf_up_complete(struct i40evf_adapter *adapter)
 {
 	adapter->state = __I40EVF_RUNNING;
-	clear_bit(__I40E_DOWN, &adapter->vsi.state);
+	clear_bit(__I40E_VSI_DOWN, adapter->vsi.state);
 
 	i40evf_napi_enable_all(adapter);
 
 	adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES;
+	if (CLIENT_ENABLED(adapter))
+		adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN;
 	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
 }
 
@@ -1235,13 +1272,13 @@ static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter)
 	}
 	pairs = adapter->num_active_queues;
 
-	/* It's easy to be greedy for MSI-X vectors, but it really
-	 * doesn't do us much good if we have a lot more vectors
-	 * than CPU's.  So let's be conservative and only ask for
-	 * (roughly) twice the number of vectors as there are CPU's.
+	/* It's easy to be greedy for MSI-X vectors, but it really doesn't do
+	 * us much good if we have more vectors than CPUs. However, we already
+	 * limit the total number of queues by the number of CPUs so we do not
+	 * need any further limiting here.
 	 */
-	v_budget = min_t(int, pairs, (int)(num_online_cpus() * 2)) + NONQ_VECS;
-	v_budget = min_t(int, v_budget, (int)adapter->vf_res->max_vectors);
+	v_budget = min_t(int, pairs + NONQ_VECS,
+			 (int)adapter->vf_res->max_vectors);
 
 	adapter->msix_entries = kcalloc(v_budget,
 					sizeof(struct msix_entry), GFP_KERNEL);
@@ -1472,6 +1509,13 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter)
 {
 	int err;
 
+	err = i40evf_alloc_queues(adapter);
+	if (err) {
+		dev_err(&adapter->pdev->dev,
+			"Unable to allocate memory for queues\n");
+		goto err_alloc_queues;
+	}
+
 	rtnl_lock();
 	err = i40evf_set_interrupt_capability(adapter);
 	rtnl_unlock();
@@ -1488,23 +1532,16 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter)
 		goto err_alloc_q_vectors;
 	}
 
-	err = i40evf_alloc_queues(adapter);
-	if (err) {
-		dev_err(&adapter->pdev->dev,
-			"Unable to allocate memory for queues\n");
-		goto err_alloc_queues;
-	}
-
 	dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u",
 		 (adapter->num_active_queues > 1) ? "Enabled" : "Disabled",
 		 adapter->num_active_queues);
 
 	return 0;
-err_alloc_queues:
-	i40evf_free_q_vectors(adapter);
 err_alloc_q_vectors:
 	i40evf_reset_interrupt_capability(adapter);
 err_set_interrupt:
+	i40evf_free_queues(adapter);
+err_alloc_queues:
 	return err;
 }
 
@@ -1685,6 +1722,7 @@ static void i40evf_watchdog_task(struct work_struct *work)
 		i40evf_set_promiscuous(adapter, 0);
 		goto watchdog_done;
 	}
+	schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
 
 	if (adapter->state == __I40EVF_RUNNING)
 		i40evf_request_stats(adapter);
@@ -1716,7 +1754,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter)
 	adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
 
 	if (netif_running(adapter->netdev)) {
-		set_bit(__I40E_DOWN, &adapter->vsi.state);
+		set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
 		netif_carrier_off(adapter->netdev);
 		netif_tx_disable(adapter->netdev);
 		adapter->link_up = false;
@@ -1773,10 +1811,17 @@ static void i40evf_reset_task(struct work_struct *work)
 	u32 reg_val;
 	int i = 0, err;
 
-	while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
+	while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK,
 				&adapter->crit_section))
 		usleep_range(500, 1000);
-
+	if (CLIENT_ENABLED(adapter)) {
+		adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN |
+				    I40EVF_FLAG_CLIENT_NEEDS_CLOSE |
+				    I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS |
+				    I40EVF_FLAG_SERVICE_CLIENT_REQUESTED);
+		cancel_delayed_work_sync(&adapter->client_task);
+		i40evf_notify_client_close(&adapter->vsi, true);
+	}
 	i40evf_misc_irq_disable(adapter);
 	if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
 		adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED;
@@ -1819,6 +1864,7 @@ static void i40evf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		i40evf_disable_vf(adapter);
+		clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -1861,9 +1907,8 @@ continue_reset:
 	}
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
-	/* Open RDMA Client again */
-	adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
 	i40evf_misc_irq_enable(adapter);
 
 	mod_timer(&adapter->watchdog_timer, jiffies + 2);
@@ -1980,6 +2025,48 @@ out:
 }
 
 /**
+ * i40evf_client_task - worker thread to perform client work
+ * @work: pointer to work_struct containing our data
+ *
+ * This task handles client interactions. Because client calls can be
+ * reentrant, we can't handle them in the watchdog.
+ **/
+static void i40evf_client_task(struct work_struct *work)
+{
+	struct i40evf_adapter *adapter =
+		container_of(work, struct i40evf_adapter, client_task.work);
+
+	/* If we can't get the client bit, just give up. We'll be rescheduled
+	 * later.
+	 */
+
+	if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section))
+		return;
+
+	if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) {
+		i40evf_client_subtask(adapter);
+		adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) {
+		i40evf_notify_client_close(&adapter->vsi, false);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) {
+		i40evf_notify_client_open(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
+	}
+out:
+	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
+}
+
+/**
  * i40evf_free_all_tx_resources - Free Tx Resources for All Queues
  * @adapter: board private structure
  *
@@ -2147,7 +2234,9 @@ static int i40evf_close(struct net_device *netdev)
 		return 0;
 
 
-	set_bit(__I40E_DOWN, &adapter->vsi.state);
+	set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
+	if (CLIENT_ENABLED(adapter))
+		adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
 
 	i40evf_down(adapter);
 	adapter->state = __I40EVF_DOWN_PENDING;
@@ -2162,21 +2251,6 @@ static int i40evf_close(struct net_device *netdev)
 }
 
 /**
- * i40evf_get_stats - Get System Network Statistics
- * @netdev: network interface device structure
- *
- * Returns the address of the device statistics structure.
- * The statistics are actually updated from the timer callback.
- **/
-static struct net_device_stats *i40evf_get_stats(struct net_device *netdev)
-{
-	struct i40evf_adapter *adapter = netdev_priv(netdev);
-
-	/* only return the current stats */
-	return &adapter->net_stats;
-}
-
-/**
  * i40evf_change_mtu - Change the Maximum Transfer Unit
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
@@ -2188,6 +2262,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	netdev->mtu = new_mtu;
+	if (CLIENT_ENABLED(adapter)) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+	}
 	adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
 	schedule_work(&adapter->reset_task);
 
@@ -2278,7 +2356,6 @@ static const struct net_device_ops i40evf_netdev_ops = {
 	.ndo_open		= i40evf_open,
 	.ndo_stop		= i40evf_close,
 	.ndo_start_xmit		= i40evf_xmit_frame,
-	.ndo_get_stats		= i40evf_get_stats,
 	.ndo_set_rx_mode	= i40evf_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= i40evf_set_mac,
@@ -2328,6 +2405,8 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	struct net_device *netdev = adapter->netdev;
 	struct i40e_vsi *vsi = &adapter->vsi;
 	int i;
+	netdev_features_t hw_enc_features;
+	netdev_features_t hw_features;
 
 	/* got VF config message back from PF, now we can parse it */
 	for (i = 0; i < vfres->num_vsis; i++) {
@@ -2339,46 +2418,52 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 		return -ENODEV;
 	}
 
-	netdev->hw_enc_features |= NETIF_F_SG			|
-				   NETIF_F_IP_CSUM		|
-				   NETIF_F_IPV6_CSUM		|
-				   NETIF_F_HIGHDMA		|
-				   NETIF_F_SOFT_FEATURES	|
-				   NETIF_F_TSO			|
-				   NETIF_F_TSO_ECN		|
-				   NETIF_F_TSO6			|
+	hw_enc_features = NETIF_F_SG			|
+			  NETIF_F_IP_CSUM		|
+			  NETIF_F_IPV6_CSUM		|
+			  NETIF_F_HIGHDMA		|
+			  NETIF_F_SOFT_FEATURES	|
+			  NETIF_F_TSO			|
+			  NETIF_F_TSO_ECN		|
+			  NETIF_F_TSO6			|
+			  NETIF_F_SCTP_CRC		|
+			  NETIF_F_RXHASH		|
+			  NETIF_F_RXCSUM		|
+			  0;
+
+	/* advertise to stack only if offloads for encapsulated packets is
+	 * supported
+	 */
+	if (vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP) {
+		hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_GRE		|
 				   NETIF_F_GSO_GRE_CSUM		|
 				   NETIF_F_GSO_IPXIP4		|
 				   NETIF_F_GSO_IPXIP6		|
-				   NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
 				   NETIF_F_GSO_PARTIAL		|
-				   NETIF_F_SCTP_CRC		|
-				   NETIF_F_RXHASH		|
-				   NETIF_F_RXCSUM		|
 				   0;
 
-	if (!(adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE))
-		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
-	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+		if (!(vfres->vf_offload_flags &
+		      I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
+			netdev->gso_partial_features |=
+				NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
+		netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+		netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
+		netdev->hw_enc_features |= hw_enc_features;
+	}
 	/* record features VLANs can make use of */
-	netdev->vlan_features |= netdev->hw_enc_features |
-				 NETIF_F_TSO_MANGLEID;
+	netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
 
 	/* Write features and hw_features separately to avoid polluting
-	 * with, or dropping, features that are set when we registgered.
+	 * with, or dropping, features that are set when we registered.
 	 */
-	netdev->hw_features |= netdev->hw_enc_features;
+	hw_features = hw_enc_features;
 
-	netdev->features |= netdev->hw_enc_features | I40EVF_VLAN_FEATURES;
-	netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
+	netdev->hw_features |= hw_features;
 
-	/* disable VLAN features if not supported */
-	if (!(vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_VLAN))
-		netdev->features ^= I40EVF_VLAN_FEATURES;
+	netdev->features |= hw_features | I40EVF_VLAN_FEATURES;
 
 	adapter->vsi.id = adapter->vsi_res->vsi_id;
 
@@ -2519,9 +2604,6 @@ static void i40evf_init_task(struct work_struct *work)
 		goto err_alloc;
 	}
 
-	if (hw->mac.type == I40E_MAC_X722_VF)
-		adapter->flags |= I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE;
-
 	if (i40evf_process_config(adapter))
 		goto err_alloc;
 	adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
@@ -2581,13 +2663,19 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->netdev_registered = true;
 
 	netif_tx_stop_all_queues(netdev);
+	if (CLIENT_ALLOWED(adapter)) {
+		err = i40evf_lan_add_device(adapter);
+		if (err)
+			dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
+				 err);
+	}
 
 	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
 	if (netdev->features & NETIF_F_GRO)
 		dev_info(&pdev->dev, "GRO is enabled\n");
 
 	adapter->state = __I40EVF_DOWN;
-	set_bit(__I40E_DOWN, &adapter->vsi.state);
+	set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
 	i40evf_misc_irq_enable(adapter);
 
 	adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
@@ -2745,6 +2833,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&adapter->reset_task, i40evf_reset_task);
 	INIT_WORK(&adapter->adminq_task, i40evf_adminq_task);
 	INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task);
+	INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task);
 	INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task);
 	schedule_delayed_work(&adapter->init_task,
 			      msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
@@ -2857,14 +2946,21 @@ static void i40evf_remove(struct pci_dev *pdev)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40evf_mac_filter *f, *ftmp;
 	struct i40e_hw *hw = &adapter->hw;
+	int err;
 
 	cancel_delayed_work_sync(&adapter->init_task);
 	cancel_work_sync(&adapter->reset_task);
-
+	cancel_delayed_work_sync(&adapter->client_task);
 	if (adapter->netdev_registered) {
 		unregister_netdev(netdev);
 		adapter->netdev_registered = false;
 	}
+	if (CLIENT_ALLOWED(adapter)) {
+		err = i40evf_lan_del_device(adapter);
+		if (err)
+			dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+				 err);
+	}
 
 	/* Shut down all the garbage mashers on the detention level */
 	adapter->state = __I40EVF_REMOVE;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index bee58af390e1..deb2cb8dac6b 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -26,6 +26,7 @@
 
 #include "i40evf.h"
 #include "i40e_prototype.h"
+#include "i40evf_client.h"
 
 /* busy wait delay in msec */
 #define I40EVF_BUSY_WAIT_DELAY 10
@@ -158,7 +159,9 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter)
 	       I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG |
 	       I40E_VIRTCHNL_VF_OFFLOAD_VLAN |
 	       I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR |
-	       I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
+	       I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 |
+	       I40E_VIRTCHNL_VF_OFFLOAD_ENCAP |
+	       I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
 
 	adapter->current_op = I40E_VIRTCHNL_OP_GET_VF_RESOURCES;
 	adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG;
@@ -233,7 +236,7 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_vsi_queue_config_info *vqci;
 	struct i40e_virtchnl_queue_pair_info *vqpi;
 	int pairs = adapter->num_active_queues;
-	int i, len;
+	int i, len, max_frame = I40E_MAX_RXBUFFER;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -248,6 +251,11 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 	if (!vqci)
 		return;
 
+	/* Limit maximum frame size when jumbo frames is not enabled */
+	if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) &&
+	    (adapter->netdev->mtu <= ETH_DATA_LEN))
+		max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -259,17 +267,14 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 		vqpi->txq.queue_id = i;
 		vqpi->txq.ring_len = adapter->tx_rings[i].count;
 		vqpi->txq.dma_ring_addr = adapter->tx_rings[i].dma;
-		vqpi->txq.headwb_enabled = 1;
-		vqpi->txq.dma_headwb_addr = vqpi->txq.dma_ring_addr +
-		    (vqpi->txq.ring_len * sizeof(struct i40e_tx_desc));
-
 		vqpi->rxq.vsi_id = vqci->vsi_id;
 		vqpi->rxq.queue_id = i;
 		vqpi->rxq.ring_len = adapter->rx_rings[i].count;
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
-		vqpi->rxq.max_pkt_size = adapter->netdev->mtu
-					+ ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN;
-		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+		vqpi->rxq.max_pkt_size = max_frame;
+		vqpi->rxq.databuffer_size =
+			ALIGN(adapter->rx_rings[i].rx_buf_len,
+			      BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
 		vqpi++;
 	}
 
@@ -955,17 +960,17 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 	case I40E_VIRTCHNL_OP_GET_STATS: {
 		struct i40e_eth_stats *stats =
 			(struct i40e_eth_stats *)msg;
-		adapter->net_stats.rx_packets = stats->rx_unicast +
-						 stats->rx_multicast +
-						 stats->rx_broadcast;
-		adapter->net_stats.tx_packets = stats->tx_unicast +
-						 stats->tx_multicast +
-						 stats->tx_broadcast;
-		adapter->net_stats.rx_bytes = stats->rx_bytes;
-		adapter->net_stats.tx_bytes = stats->tx_bytes;
-		adapter->net_stats.tx_errors = stats->tx_errors;
-		adapter->net_stats.rx_dropped = stats->rx_discards;
-		adapter->net_stats.tx_dropped = stats->tx_discards;
+		netdev->stats.rx_packets = stats->rx_unicast +
+					   stats->rx_multicast +
+					   stats->rx_broadcast;
+		netdev->stats.tx_packets = stats->tx_unicast +
+					   stats->tx_multicast +
+					   stats->tx_broadcast;
+		netdev->stats.rx_bytes = stats->rx_bytes;
+		netdev->stats.tx_bytes = stats->tx_bytes;
+		netdev->stats.tx_errors = stats->tx_errors;
+		netdev->stats.rx_dropped = stats->rx_discards;
+		netdev->stats.tx_dropped = stats->tx_discards;
 		adapter->current_stats = *stats;
 		}
 		break;
@@ -999,6 +1004,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		if (v_opcode != adapter->current_op)
 			return;
 		break;
+	case I40E_VIRTCHNL_OP_IWARP:
+		/* Gobble zero-length replies from the PF. They indicate that
+		 * a previous message was received OK, and the client doesn't
+		 * care about that.
+		 */
+		if (msglen && CLIENT_ENABLED(adapter))
+			i40evf_notify_client_message(&adapter->vsi,
+						     msg, msglen);
+		break;
+
 	case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
 		adapter->client_pending &=
 				~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP));
@@ -1014,7 +1029,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		}
 		break;
 	default:
-		if (v_opcode != adapter->current_op)
+		if (adapter->current_op && (v_opcode != adapter->current_op))
 			dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",
 				 adapter->current_op, v_opcode);
 		break;
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 8aee314332a8..d8517779439b 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -39,6 +39,27 @@
 #define E1000_WUFC_MC   0x00000008 /* Directed Multicast Wakeup Enable */
 #define E1000_WUFC_BC   0x00000010 /* Broadcast Wakeup Enable */
 
+/* Wake Up Status */
+#define E1000_WUS_EX	0x00000004 /* Directed Exact */
+#define E1000_WUS_ARPD	0x00000020 /* Directed ARP Request */
+#define E1000_WUS_IPV4	0x00000040 /* Directed IPv4 */
+#define E1000_WUS_IPV6	0x00000080 /* Directed IPv6 */
+#define E1000_WUS_NSD	0x00000400 /* Directed IPv6 Neighbor Solicitation */
+
+/* Packet types that are enabled for wake packet delivery */
+#define WAKE_PKT_WUS ( \
+	E1000_WUS_EX   | \
+	E1000_WUS_ARPD | \
+	E1000_WUS_IPV4 | \
+	E1000_WUS_IPV6 | \
+	E1000_WUS_NSD)
+
+/* Wake Up Packet Length */
+#define E1000_WUPL_MASK	0x00000FFF
+
+/* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */
+#define E1000_WUPM_BYTES	128
+
 /* Extended Device Control */
 #define E1000_CTRL_EXT_SDP2_DATA 0x00000040 /* Value of SW Defineable Pin 2 */
 #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Defineable Pin 3 */
diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h
index d20af6b2f581..3e7fed73df15 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mbx.h
+++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h
@@ -55,6 +55,10 @@
 
 #define E1000_VF_RESET		0x01 /* VF requests reset */
 #define E1000_VF_SET_MAC_ADDR	0x02 /* VF requests to set MAC addr */
+/* VF requests to clear all unicast MAC filters */
+#define E1000_VF_MAC_FILTER_CLR	(0x01 << E1000_VT_MSGINFO_SHIFT)
+/* VF requests to add unicast MAC filter */
+#define E1000_VF_MAC_FILTER_ADD	(0x02 << E1000_VT_MSGINFO_SHIFT)
 #define E1000_VF_SET_MULTICAST	0x03 /* VF requests to set MC addr */
 #define E1000_VF_SET_VLAN	0x04 /* VF requests to set VLAN */
 #define E1000_VF_SET_LPE	0x05 /* VF requests to set VMOLR.LPE */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index acbc3abe2ddd..bf9bf9056d0c 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -111,6 +111,16 @@ struct vf_data_storage {
 	bool spoofchk_enabled;
 };
 
+/* Number of unicast MAC filters reserved for the PF in the RAR registers */
+#define IGB_PF_MAC_FILTERS_RESERVED	3
+
+struct vf_mac_filter {
+	struct list_head l;
+	int vf;
+	bool free;
+	u8 vf_mac[ETH_ALEN];
+};
+
 #define IGB_VF_FLAG_CTS            0x00000001 /* VF is clear to send data */
 #define IGB_VF_FLAG_UNI_PROMISC    0x00000002 /* VF has unicast promisc */
 #define IGB_VF_FLAG_MULTI_PROMISC  0x00000004 /* VF has multicast promisc */
@@ -142,12 +152,24 @@ struct vf_data_storage {
 /* Supported Rx Buffer Sizes */
 #define IGB_RXBUFFER_256	256
 #define IGB_RXBUFFER_2048	2048
+#define IGB_RXBUFFER_3072	3072
 #define IGB_RX_HDR_LEN		IGB_RXBUFFER_256
-#define IGB_RX_BUFSZ		IGB_RXBUFFER_2048
+#define IGB_TS_HDR_LEN		16
+
+#define IGB_SKB_PAD		(NET_SKB_PAD + NET_IP_ALIGN)
+#if (PAGE_SIZE < 8192)
+#define IGB_MAX_FRAME_BUILD_SKB \
+	(SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN)
+#else
+#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN)
+#endif
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IGB_RX_BUFFER_WRITE	16 /* Must be power of 2 */
 
+#define IGB_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 #define AUTO_ALL_MODES		0
 #define IGB_EEPROM_APME		0x0400
 
@@ -301,12 +323,51 @@ struct igb_q_vector {
 };
 
 enum e1000_ring_flags_t {
+	IGB_RING_FLAG_RX_3K_BUFFER,
+	IGB_RING_FLAG_RX_BUILD_SKB_ENABLED,
 	IGB_RING_FLAG_RX_SCTP_CSUM,
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGB_RING_FLAG_TX_CTX_IDX,
 	IGB_RING_FLAG_TX_DETECT_HANG
 };
 
+#define ring_uses_large_buffer(ring) \
+	test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+#define set_ring_uses_large_buffer(ring) \
+	set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+#define clear_ring_uses_large_buffer(ring) \
+	clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+
+#define ring_uses_build_skb(ring) \
+	test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define set_ring_build_skb_enabled(ring) \
+	set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define clear_ring_build_skb_enabled(ring) \
+	clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+
+static inline unsigned int igb_rx_bufsz(struct igb_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_large_buffer(ring))
+		return IGB_RXBUFFER_3072;
+
+	if (ring_uses_build_skb(ring))
+		return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN;
+#endif
+	return IGB_RXBUFFER_2048;
+}
+
+static inline unsigned int igb_rx_pg_order(struct igb_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_large_buffer(ring))
+		return 1;
+#endif
+	return 0;
+}
+
+#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring))
+
 #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS)
 
 #define IGB_RX_DESC(R, i)	\
@@ -398,6 +459,15 @@ struct igb_nfc_filter {
 	u16 action;
 };
 
+struct igb_mac_addr {
+	u8 addr[ETH_ALEN];
+	u8 queue;
+	u8 state; /* bitmask */
+};
+
+#define IGB_MAC_STATE_DEFAULT	0x1
+#define IGB_MAC_STATE_IN_USE	0x2
+
 /* board specific private data structure */
 struct igb_adapter {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
@@ -524,6 +594,10 @@ struct igb_adapter {
 	/* lock for RX network flow classification filter */
 	spinlock_t nfc_lock;
 	bool etype_bitmap[MAX_ETYPE_FILTER];
+
+	struct igb_mac_addr *mac_table;
+	struct vf_mac_filter vf_macs;
+	struct vf_mac_filter *vf_mac_list;
 };
 
 /* flags controlling PTP/1588 function */
@@ -545,6 +619,7 @@ struct igb_adapter {
 #define IGB_FLAG_HAS_MSIX		BIT(13)
 #define IGB_FLAG_EEE			BIT(14)
 #define IGB_FLAG_VLAN_PROMISC		BIT(15)
+#define IGB_FLAG_RX_LEGACY		BIT(16)
 
 /* Media Auto Sense */
 #define IGB_MAS_ENABLE_0		0X0001
@@ -558,7 +633,6 @@ struct igb_adapter {
 #define IGB_DMCTLX_DCFLUSH_DIS	0x80000000  /* Disable DMA Coal Flush */
 
 #define IGB_82576_TSYNC_SHIFT	19
-#define IGB_TS_HDR_LEN		16
 enum e1000_state_t {
 	__IGB_TESTING,
 	__IGB_RESETTING,
@@ -591,7 +665,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
 void igb_setup_tctl(struct igb_adapter *);
 void igb_setup_rctl(struct igb_adapter *);
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
-void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *);
 void igb_alloc_rx_buffers(struct igb_ring *, u16);
 void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
 bool igb_has_link(struct igb_adapter *adapter);
@@ -604,7 +677,7 @@ void igb_ptp_reset(struct igb_adapter *adapter);
 void igb_ptp_suspend(struct igb_adapter *adapter);
 void igb_ptp_rx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va,
+void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			 struct sk_buff *skb);
 int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 737b664d004c..0efb62db6efd 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -144,7 +144,15 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = {
 };
 #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN)
 
-static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IGB_PRIV_FLAGS_LEGACY_RX	BIT(0)
+	"legacy-rx",
+};
+
+#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings)
+
+static int igb_get_link_ksettings(struct net_device *netdev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -152,76 +160,73 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags;
 	u32 status;
 	u32 speed;
+	u32 supported, advertising;
 
 	status = rd32(E1000_STATUS);
 	if (hw->phy.media_type == e1000_media_type_copper) {
 
-		ecmd->supported = (SUPPORTED_10baseT_Half |
-				   SUPPORTED_10baseT_Full |
-				   SUPPORTED_100baseT_Half |
-				   SUPPORTED_100baseT_Full |
-				   SUPPORTED_1000baseT_Full|
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP |
-				   SUPPORTED_Pause);
-		ecmd->advertising = ADVERTISED_TP;
+		supported = (SUPPORTED_10baseT_Half |
+			     SUPPORTED_10baseT_Full |
+			     SUPPORTED_100baseT_Half |
+			     SUPPORTED_100baseT_Full |
+			     SUPPORTED_1000baseT_Full|
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_TP |
+			     SUPPORTED_Pause);
+		advertising = ADVERTISED_TP;
 
 		if (hw->mac.autoneg == 1) {
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 			/* the e1000 autoneg seems to match ethtool nicely */
-			ecmd->advertising |= hw->phy.autoneg_advertised;
+			advertising |= hw->phy.autoneg_advertised;
 		}
 
-		ecmd->port = PORT_TP;
-		ecmd->phy_address = hw->phy.addr;
-		ecmd->transceiver = XCVR_INTERNAL;
+		cmd->base.port = PORT_TP;
+		cmd->base.phy_address = hw->phy.addr;
 	} else {
-		ecmd->supported = (SUPPORTED_FIBRE |
-				   SUPPORTED_1000baseKX_Full |
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_Pause);
-		ecmd->advertising = (ADVERTISED_FIBRE |
-				     ADVERTISED_1000baseKX_Full);
+		supported = (SUPPORTED_FIBRE |
+			     SUPPORTED_1000baseKX_Full |
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_Pause);
+		advertising = (ADVERTISED_FIBRE |
+			       ADVERTISED_1000baseKX_Full);
 		if (hw->mac.type == e1000_i354) {
 			if ((hw->device_id ==
 			     E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) &&
 			    !(status & E1000_STATUS_2P5_SKU_OVER)) {
-				ecmd->supported |= SUPPORTED_2500baseX_Full;
-				ecmd->supported &=
-					~SUPPORTED_1000baseKX_Full;
-				ecmd->advertising |= ADVERTISED_2500baseX_Full;
-				ecmd->advertising &=
-					~ADVERTISED_1000baseKX_Full;
+				supported |= SUPPORTED_2500baseX_Full;
+				supported &= ~SUPPORTED_1000baseKX_Full;
+				advertising |= ADVERTISED_2500baseX_Full;
+				advertising &= ~ADVERTISED_1000baseKX_Full;
 			}
 		}
 		if (eth_flags->e100_base_fx) {
-			ecmd->supported |= SUPPORTED_100baseT_Full;
-			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			supported |= SUPPORTED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 		}
 		if (hw->mac.autoneg == 1)
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 
-		ecmd->port = PORT_FIBRE;
-		ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.port = PORT_FIBRE;
 	}
 	if (hw->mac.autoneg != 1)
-		ecmd->advertising &= ~(ADVERTISED_Pause |
-				       ADVERTISED_Asym_Pause);
+		advertising &= ~(ADVERTISED_Pause |
+				 ADVERTISED_Asym_Pause);
 
 	switch (hw->fc.requested_mode) {
 	case e1000_fc_full:
-		ecmd->advertising |= ADVERTISED_Pause;
+		advertising |= ADVERTISED_Pause;
 		break;
 	case e1000_fc_rx_pause:
-		ecmd->advertising |= (ADVERTISED_Pause |
-				      ADVERTISED_Asym_Pause);
+		advertising |= (ADVERTISED_Pause |
+				ADVERTISED_Asym_Pause);
 		break;
 	case e1000_fc_tx_pause:
-		ecmd->advertising |=  ADVERTISED_Asym_Pause;
+		advertising |=  ADVERTISED_Asym_Pause;
 		break;
 	default:
-		ecmd->advertising &= ~(ADVERTISED_Pause |
-				       ADVERTISED_Asym_Pause);
+		advertising &= ~(ADVERTISED_Pause |
+				 ADVERTISED_Asym_Pause);
 	}
 	if (status & E1000_STATUS_LU) {
 		if ((status & E1000_STATUS_2P5_SKU) &&
@@ -236,39 +241,46 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		}
 		if ((status & E1000_STATUS_FD) ||
 		    hw->phy.media_type != e1000_media_type_copper)
-			ecmd->duplex = DUPLEX_FULL;
+			cmd->base.duplex = DUPLEX_FULL;
 		else
-			ecmd->duplex = DUPLEX_HALF;
+			cmd->base.duplex = DUPLEX_HALF;
 	} else {
 		speed = SPEED_UNKNOWN;
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
-	ethtool_cmd_speed_set(ecmd, speed);
+	cmd->base.speed = speed;
 	if ((hw->phy.media_type == e1000_media_type_fiber) ||
 	    hw->mac.autoneg)
-		ecmd->autoneg = AUTONEG_ENABLE;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 	else
-		ecmd->autoneg = AUTONEG_DISABLE;
+		cmd->base.autoneg = AUTONEG_DISABLE;
 
 	/* MDI-X => 2; MDI =>1; Invalid =>0 */
 	if (hw->phy.media_type == e1000_media_type_copper)
-		ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+		cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
 						      ETH_TP_MDI;
 	else
-		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
 
 	if (hw->phy.mdix == AUTO_ALL_MODES)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
 	else
-		ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+		cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int igb_set_link_ksettings(struct net_device *netdev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 advertising;
 
 	/* When SoL/IDER sessions are active, autoneg/speed/duplex
 	 * cannot be changed
@@ -283,12 +295,12 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	 * some hardware doesn't allow MDI setting when speed or
 	 * duplex is forced.
 	 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (hw->phy.media_type != e1000_media_type_copper)
 			return -EOPNOTSUPP;
 
-		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
-		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			return -EINVAL;
 		}
@@ -297,10 +309,13 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
+
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		hw->mac.autoneg = 1;
 		if (hw->phy.media_type == e1000_media_type_fiber) {
-			hw->phy.autoneg_advertised = ecmd->advertising |
+			hw->phy.autoneg_advertised = advertising |
 						     ADVERTISED_FIBRE |
 						     ADVERTISED_Autoneg;
 			switch (adapter->link_speed) {
@@ -320,31 +335,31 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 				break;
 			}
 		} else {
-			hw->phy.autoneg_advertised = ecmd->advertising |
+			hw->phy.autoneg_advertised = advertising |
 						     ADVERTISED_TP |
 						     ADVERTISED_Autoneg;
 		}
-		ecmd->advertising = hw->phy.autoneg_advertised;
+		advertising = hw->phy.autoneg_advertised;
 		if (adapter->fc_autoneg)
 			hw->fc.requested_mode = e1000_fc_default;
 	} else {
-		u32 speed = ethtool_cmd_speed(ecmd);
+		u32 speed = cmd->base.speed;
 		/* calling this overrides forced MDI setting */
-		if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+		if (igb_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
 			clear_bit(__IGB_RESETTING, &adapter->state);
 			return -EINVAL;
 		}
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		/* fix up the value for auto (3 => 0) as zero is mapped
 		 * internally to auto
 		 */
-		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
 			hw->phy.mdix = AUTO_ALL_MODES;
 		else
-			hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+			hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
 	}
 
 	/* reset the link */
@@ -852,6 +867,8 @@ static void igb_get_drvinfo(struct net_device *netdev,
 		sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
+
+	drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN;
 }
 
 static void igb_get_ringparam(struct net_device *netdev,
@@ -1811,14 +1828,14 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 	tx_ntc = tx_ring->next_to_clean;
 	rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
 
-	while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) {
+	while (rx_desc->wb.upper.length) {
 		/* check Rx buffer */
 		rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
 
 		/* sync Rx buffer for CPU read */
 		dma_sync_single_for_cpu(rx_ring->dev,
 					rx_buffer_info->dma,
-					IGB_RX_BUFSZ,
+					size,
 					DMA_FROM_DEVICE);
 
 		/* verify contents of skb */
@@ -1828,12 +1845,21 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 		/* sync Rx buffer for device write */
 		dma_sync_single_for_device(rx_ring->dev,
 					   rx_buffer_info->dma,
-					   IGB_RX_BUFSZ,
+					   size,
 					   DMA_FROM_DEVICE);
 
 		/* unmap buffer on Tx side */
 		tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
-		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
+
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer_info->skb);
+
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer_info, dma),
+				 dma_unmap_len(tx_buffer_info, len),
+				 DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer_info, len, 0);
 
 		/* increment Rx/Tx next to clean counters */
 		rx_ntc++;
@@ -2271,6 +2297,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset)
 		return IGB_STATS_LEN;
 	case ETH_SS_TEST:
 		return IGB_TEST_LEN;
+	case ETH_SS_PRIV_FLAGS:
+		return IGB_PRIV_FLAGS_STR_LEN;
 	default:
 		return -ENOTSUPP;
 	}
@@ -2376,6 +2404,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 		}
 		/* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, igb_priv_flags_strings,
+		       IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+		break;
 	}
 }
 
@@ -3388,9 +3420,38 @@ static int igb_set_channels(struct net_device *netdev,
 	return 0;
 }
 
+static u32 igb_get_priv_flags(struct net_device *netdev)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	u32 priv_flags = 0;
+
+	if (adapter->flags & IGB_FLAG_RX_LEGACY)
+		priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX;
+
+	return priv_flags;
+}
+
+static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	unsigned int flags = adapter->flags;
+
+	flags &= ~IGB_FLAG_RX_LEGACY;
+	if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX)
+		flags |= IGB_FLAG_RX_LEGACY;
+
+	if (flags != adapter->flags) {
+		adapter->flags = flags;
+
+		/* reset interface to repopulate queues */
+		if (netif_running(netdev))
+			igb_reinit_locked(adapter);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops igb_ethtool_ops = {
-	.get_settings		= igb_get_settings,
-	.set_settings		= igb_set_settings,
 	.get_drvinfo		= igb_get_drvinfo,
 	.get_regs_len		= igb_get_regs_len,
 	.get_regs		= igb_get_regs,
@@ -3426,8 +3487,12 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.set_rxfh		= igb_set_rxfh,
 	.get_channels		= igb_get_channels,
 	.set_channels		= igb_set_channels,
+	.get_priv_flags		= igb_get_priv_flags,
+	.set_priv_flags		= igb_set_priv_flags,
 	.begin			= igb_ethtool_begin,
 	.complete		= igb_ethtool_complete,
+	.get_link_ksettings	= igb_get_link_ksettings,
+	.set_link_ksettings	= igb_set_link_ksettings,
 };
 
 void igb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index be456bae8169..1cf74aa4ebd9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -161,11 +161,16 @@ static void igb_vlan_mode(struct net_device *netdev,
 static int igb_vlan_rx_add_vid(struct net_device *, __be16, u16);
 static int igb_vlan_rx_kill_vid(struct net_device *, __be16, u16);
 static void igb_restore_vlan(struct igb_adapter *);
-static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8);
+static void igb_rar_set_index(struct igb_adapter *, u32);
 static void igb_ping_all_vfs(struct igb_adapter *);
 static void igb_msg_task(struct igb_adapter *);
 static void igb_vmm_control(struct igb_adapter *);
 static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *);
+static void igb_flush_mac_table(struct igb_adapter *);
+static int igb_available_rars(struct igb_adapter *, u8);
+static void igb_set_default_mac_filter(struct igb_adapter *);
+static int igb_uc_sync(struct net_device *, const unsigned char *);
+static int igb_uc_unsync(struct net_device *, const unsigned char *);
 static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
 static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac);
 static int igb_ndo_set_vf_vlan(struct net_device *netdev,
@@ -554,7 +559,7 @@ rx_ring_summary:
 					  16, 1,
 					  page_address(buffer_info->page) +
 						      buffer_info->page_offset,
-					  IGB_RX_BUFSZ, true);
+					  igb_rx_bufsz(rx_ring), true);
 				}
 			}
 		}
@@ -1153,6 +1158,8 @@ msi_only:
 		pci_disable_sriov(adapter->pdev);
 		msleep(500);
 
+		kfree(adapter->vf_mac_list);
+		adapter->vf_mac_list = NULL;
 		kfree(adapter->vf_data);
 		adapter->vf_data = NULL;
 		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
@@ -1987,6 +1994,13 @@ void igb_reset(struct igb_adapter *adapter)
 	if (hw->mac.ops.init_hw(hw))
 		dev_err(&pdev->dev, "Hardware Error\n");
 
+	/* RAR registers were cleared during init_hw, clear mac table */
+	igb_flush_mac_table(adapter);
+	__dev_uc_unsync(adapter->netdev, NULL);
+
+	/* Recover default RAR entry */
+	igb_set_default_mac_filter(adapter);
+
 	/* Flow control settings reset on hardware reset, so guarantee flow
 	 * control is off when forcing speed.
 	 */
@@ -2095,11 +2109,9 @@ static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
 		struct igb_adapter *adapter = netdev_priv(dev);
-		struct e1000_hw *hw = &adapter->hw;
 		int vfn = adapter->vfs_allocated_count;
-		int rar_entries = hw->mac.rar_entry_count - (vfn + 1);
 
-		if (netdev_uc_count(dev) >= rar_entries)
+		if (netdev_uc_count(dev) >= igb_available_rars(adapter, vfn))
 			return -ENOMEM;
 	}
 
@@ -2517,6 +2529,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_eeprom;
 	}
 
+	igb_set_default_mac_filter(adapter);
+
 	/* get firmware version for ethtool -i */
 	igb_set_fw_version(adapter);
 
@@ -2761,6 +2775,7 @@ err_eeprom:
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
 err_sw_init:
+	kfree(adapter->mac_table);
 	kfree(adapter->shadow_vfta);
 	igb_clear_interrupt_scheme(adapter);
 #ifdef CONFIG_PCI_IOV
@@ -2796,6 +2811,8 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 			msleep(500);
 		}
 
+		kfree(adapter->vf_mac_list);
+		adapter->vf_mac_list = NULL;
 		kfree(adapter->vf_data);
 		adapter->vf_data = NULL;
 		adapter->vfs_allocated_count = 0;
@@ -2816,8 +2833,9 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int old_vfs = pci_num_vf(pdev);
+	struct vf_mac_filter *mac_list;
 	int err = 0;
-	int i;
+	int num_vf_mac_filters, i;
 
 	if (!(adapter->flags & IGB_FLAG_HAS_MSIX) || num_vfs > 7) {
 		err = -EPERM;
@@ -2845,6 +2863,38 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs)
 		goto out;
 	}
 
+	/* Due to the limited number of RAR entries calculate potential
+	 * number of MAC filters available for the VFs. Reserve entries
+	 * for PF default MAC, PF MAC filters and at least one RAR entry
+	 * for each VF for VF MAC.
+	 */
+	num_vf_mac_filters = adapter->hw.mac.rar_entry_count -
+			     (1 + IGB_PF_MAC_FILTERS_RESERVED +
+			      adapter->vfs_allocated_count);
+
+	adapter->vf_mac_list = kcalloc(num_vf_mac_filters,
+				       sizeof(struct vf_mac_filter),
+				       GFP_KERNEL);
+
+	mac_list = adapter->vf_mac_list;
+	INIT_LIST_HEAD(&adapter->vf_macs.l);
+
+	if (adapter->vf_mac_list) {
+		/* Initialize list of VF MAC filters */
+		for (i = 0; i < num_vf_mac_filters; i++) {
+			mac_list->vf = -1;
+			mac_list->free = true;
+			list_add(&mac_list->l, &adapter->vf_macs.l);
+			mac_list++;
+		}
+	} else {
+		/* If we could not allocate memory for the VF MAC filters
+		 * we can continue without this feature but warn user.
+		 */
+		dev_err(&pdev->dev,
+			"Unable to allocate memory for VF MAC filter list\n");
+	}
+
 	/* only call pci_enable_sriov() if no VFs are allocated already */
 	if (!old_vfs) {
 		err = pci_enable_sriov(pdev, adapter->vfs_allocated_count);
@@ -2861,6 +2911,8 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs)
 	goto out;
 
 err_out:
+	kfree(adapter->vf_mac_list);
+	adapter->vf_mac_list = NULL;
 	kfree(adapter->vf_data);
 	adapter->vf_data = NULL;
 	adapter->vfs_allocated_count = 0;
@@ -2937,6 +2989,7 @@ static void igb_remove(struct pci_dev *pdev)
 		iounmap(hw->flash_address);
 	pci_release_mem_regions(pdev);
 
+	kfree(adapter->mac_table);
 	kfree(adapter->shadow_vfta);
 	free_netdev(netdev);
 
@@ -3099,6 +3152,11 @@ static int igb_sw_init(struct igb_adapter *adapter)
 	/* Assume MSI-X interrupts, will be checked during IRQ allocation */
 	adapter->flags |= IGB_FLAG_HAS_MSIX;
 
+	adapter->mac_table = kzalloc(sizeof(struct igb_mac_addr) *
+				     hw->mac.rar_entry_count, GFP_ATOMIC);
+	if (!adapter->mac_table)
+		return -ENOMEM;
+
 	igb_probe_vfs(adapter);
 
 	igb_init_queue_configuration(adapter);
@@ -3293,7 +3351,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
 
 	size = sizeof(struct igb_tx_buffer) * tx_ring->count;
 
-	tx_ring->tx_buffer_info = vzalloc(size);
+	tx_ring->tx_buffer_info = vmalloc(size);
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
@@ -3404,6 +3462,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 	txdctl |= IGB_TX_HTHRESH << 8;
 	txdctl |= IGB_TX_WTHRESH << 16;
 
+	/* reinitialize tx_buffer_info */
+	memset(ring->tx_buffer_info, 0,
+	       sizeof(struct igb_tx_buffer) * ring->count);
+
 	txdctl |= E1000_TXDCTL_QUEUE_ENABLE;
 	wr32(E1000_TXDCTL(reg_idx), txdctl);
 }
@@ -3435,7 +3497,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 
 	size = sizeof(struct igb_rx_buffer) * rx_ring->count;
 
-	rx_ring->rx_buffer_info = vzalloc(size);
+	rx_ring->rx_buffer_info = vmalloc(size);
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
@@ -3720,6 +3782,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 			   struct igb_ring *ring)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	union e1000_adv_rx_desc *rx_desc;
 	u64 rdba = ring->dma;
 	int reg_idx = ring->reg_idx;
 	u32 srrctl = 0, rxdctl = 0;
@@ -3741,7 +3804,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 
 	/* set descriptor configuration */
 	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	if (ring_uses_large_buffer(ring))
+		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	else
+		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
 	if (hw->mac.type >= e1000_82580)
 		srrctl |= E1000_SRRCTL_TIMESTAMP;
@@ -3758,11 +3824,39 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	rxdctl |= IGB_RX_HTHRESH << 8;
 	rxdctl |= IGB_RX_WTHRESH << 16;
 
+	/* initialize rx_buffer_info */
+	memset(ring->rx_buffer_info, 0,
+	       sizeof(struct igb_rx_buffer) * ring->count);
+
+	/* initialize Rx descriptor 0 */
+	rx_desc = IGB_RX_DESC(ring, 0);
+	rx_desc->wb.upper.length = 0;
+
 	/* enable receive descriptor fetching */
 	rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
 	wr32(E1000_RXDCTL(reg_idx), rxdctl);
 }
 
+static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
+				  struct igb_ring *rx_ring)
+{
+	/* set build_skb and buffer size flags */
+	clear_ring_build_skb_enabled(rx_ring);
+	clear_ring_uses_large_buffer(rx_ring);
+
+	if (adapter->flags & IGB_FLAG_RX_LEGACY)
+		return;
+
+	set_ring_build_skb_enabled(rx_ring);
+
+#if (PAGE_SIZE < 8192)
+	if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+		return;
+
+	set_ring_uses_large_buffer(rx_ring);
+#endif
+}
+
 /**
  *  igb_configure_rx - Configure receive Unit after Reset
  *  @adapter: board private structure
@@ -3774,14 +3868,17 @@ static void igb_configure_rx(struct igb_adapter *adapter)
 	int i;
 
 	/* set the correct pool for the PF default MAC address in entry 0 */
-	igb_rar_set_qsel(adapter, adapter->hw.mac.addr, 0,
-			 adapter->vfs_allocated_count);
+	igb_set_default_mac_filter(adapter);
 
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
 	 * the Base and Length of the Rx Descriptor Ring
 	 */
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		igb_configure_rx_ring(adapter, adapter->rx_ring[i]);
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igb_ring *rx_ring = adapter->rx_ring[i];
+
+		igb_set_rx_buffer_len(adapter, rx_ring);
+		igb_configure_rx_ring(adapter, rx_ring);
+	}
 }
 
 /**
@@ -3822,55 +3919,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter)
 			igb_free_tx_resources(adapter->tx_ring[i]);
 }
 
-void igb_unmap_and_free_tx_resource(struct igb_ring *ring,
-				    struct igb_tx_buffer *tx_buffer)
-{
-	if (tx_buffer->skb) {
-		dev_kfree_skb_any(tx_buffer->skb);
-		if (dma_unmap_len(tx_buffer, len))
-			dma_unmap_single(ring->dev,
-					 dma_unmap_addr(tx_buffer, dma),
-					 dma_unmap_len(tx_buffer, len),
-					 DMA_TO_DEVICE);
-	} else if (dma_unmap_len(tx_buffer, len)) {
-		dma_unmap_page(ring->dev,
-			       dma_unmap_addr(tx_buffer, dma),
-			       dma_unmap_len(tx_buffer, len),
-			       DMA_TO_DEVICE);
-	}
-	tx_buffer->next_to_watch = NULL;
-	tx_buffer->skb = NULL;
-	dma_unmap_len_set(tx_buffer, len, 0);
-	/* buffer_info must be completely set up in the transmit path */
-}
-
 /**
  *  igb_clean_tx_ring - Free Tx Buffers
  *  @tx_ring: ring to be cleaned
  **/
 static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 {
-	struct igb_tx_buffer *buffer_info;
-	unsigned long size;
-	u16 i;
+	u16 i = tx_ring->next_to_clean;
+	struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
 
-	if (!tx_ring->tx_buffer_info)
-		return;
-	/* Free all the Tx ring sk_buffs */
+	while (i != tx_ring->next_to_use) {
+		union e1000_adv_tx_desc *eop_desc, *tx_desc;
 
-	for (i = 0; i < tx_ring->count; i++) {
-		buffer_info = &tx_ring->tx_buffer_info[i];
-		igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
-	}
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer->skb);
 
-	netdev_tx_reset_queue(txring_txq(tx_ring));
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
 
-	size = sizeof(struct igb_tx_buffer) * tx_ring->count;
-	memset(tx_ring->tx_buffer_info, 0, size);
+		/* check for eop_desc to determine the end of the packet */
+		eop_desc = tx_buffer->next_to_watch;
+		tx_desc = IGB_TX_DESC(tx_ring, i);
+
+		/* unmap remaining buffers */
+		while (tx_desc != eop_desc) {
+			tx_buffer++;
+			tx_desc++;
+			i++;
+			if (unlikely(i == tx_ring->count)) {
+				i = 0;
+				tx_buffer = tx_ring->tx_buffer_info;
+				tx_desc = IGB_TX_DESC(tx_ring, 0);
+			}
 
-	/* Zero out the descriptor ring */
-	memset(tx_ring->desc, 0, tx_ring->size);
+			/* unmap any remaining paged data */
+			if (dma_unmap_len(tx_buffer, len))
+				dma_unmap_page(tx_ring->dev,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
+					       DMA_TO_DEVICE);
+		}
 
+		/* move us one more past the eop_desc for start of next pkt */
+		tx_buffer++;
+		i++;
+		if (unlikely(i == tx_ring->count)) {
+			i = 0;
+			tx_buffer = tx_ring->tx_buffer_info;
+		}
+	}
+
+	/* reset BQL for queue */
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
 }
@@ -3932,50 +4037,39 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)
  **/
 static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 {
-	unsigned long size;
-	u16 i;
+	u16 i = rx_ring->next_to_clean;
 
 	if (rx_ring->skb)
 		dev_kfree_skb(rx_ring->skb);
 	rx_ring->skb = NULL;
 
-	if (!rx_ring->rx_buffer_info)
-		return;
-
 	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
+	while (i != rx_ring->next_to_alloc) {
 		struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
 
-		if (!buffer_info->page)
-			continue;
-
 		/* Invalidate cache lines that may have been written to by
 		 * device so that we avoid corrupting memory.
 		 */
 		dma_sync_single_range_for_cpu(rx_ring->dev,
 					      buffer_info->dma,
 					      buffer_info->page_offset,
-					      IGB_RX_BUFSZ,
+					      igb_rx_bufsz(rx_ring),
 					      DMA_FROM_DEVICE);
 
 		/* free resources associated with mapping */
 		dma_unmap_page_attrs(rx_ring->dev,
 				     buffer_info->dma,
-				     PAGE_SIZE,
+				     igb_rx_pg_size(rx_ring),
 				     DMA_FROM_DEVICE,
-				     DMA_ATTR_SKIP_CPU_SYNC);
+				     IGB_RX_DMA_ATTR);
 		__page_frag_cache_drain(buffer_info->page,
 					buffer_info->pagecnt_bias);
 
-		buffer_info->page = NULL;
+		i++;
+		if (i == rx_ring->count)
+			i = 0;
 	}
 
-	size = sizeof(struct igb_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_buffer_info, 0, size);
-
-	/* Zero out the descriptor ring */
-	memset(rx_ring->desc, 0, rx_ring->size);
-
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -4014,8 +4108,7 @@ static int igb_set_mac(struct net_device *netdev, void *p)
 	memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
 
 	/* set the correct pool for the new PF MAC address in entry 0 */
-	igb_rar_set_qsel(adapter, hw->mac.addr, 0,
-			 adapter->vfs_allocated_count);
+	igb_set_default_mac_filter(adapter);
 
 	return 0;
 }
@@ -4059,49 +4152,6 @@ static int igb_write_mc_addr_list(struct net_device *netdev)
 	return netdev_mc_count(netdev);
 }
 
-/**
- *  igb_write_uc_addr_list - write unicast addresses to RAR table
- *  @netdev: network interface device structure
- *
- *  Writes unicast address list to the RAR table.
- *  Returns: -ENOMEM on failure/insufficient address space
- *           0 on no addresses written
- *           X on writing X addresses to the RAR table
- **/
-static int igb_write_uc_addr_list(struct net_device *netdev)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct e1000_hw *hw = &adapter->hw;
-	unsigned int vfn = adapter->vfs_allocated_count;
-	unsigned int rar_entries = hw->mac.rar_entry_count - (vfn + 1);
-	int count = 0;
-
-	/* return ENOMEM indicating insufficient memory for addresses */
-	if (netdev_uc_count(netdev) > rar_entries)
-		return -ENOMEM;
-
-	if (!netdev_uc_empty(netdev) && rar_entries) {
-		struct netdev_hw_addr *ha;
-
-		netdev_for_each_uc_addr(ha, netdev) {
-			if (!rar_entries)
-				break;
-			igb_rar_set_qsel(adapter, ha->addr,
-					 rar_entries--,
-					 vfn);
-			count++;
-		}
-	}
-	/* write the addresses in reverse order to avoid write combining */
-	for (; rar_entries > 0 ; rar_entries--) {
-		wr32(E1000_RAH(rar_entries), 0);
-		wr32(E1000_RAL(rar_entries), 0);
-	}
-	wrfl();
-
-	return count;
-}
-
 static int igb_vlan_promisc_enable(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
@@ -4240,7 +4290,7 @@ static void igb_set_rx_mode(struct net_device *netdev)
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	unsigned int vfn = adapter->vfs_allocated_count;
-	u32 rctl = 0, vmolr = 0;
+	u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE;
 	int count;
 
 	/* Check for Promiscuous and All Multicast modes */
@@ -4274,8 +4324,7 @@ static void igb_set_rx_mode(struct net_device *netdev)
 	 * sufficient space to store all the addresses then enable
 	 * unicast promiscuous mode
 	 */
-	count = igb_write_uc_addr_list(netdev);
-	if (count < 0) {
+	if (__dev_uc_sync(netdev, igb_uc_sync, igb_uc_unsync)) {
 		rctl |= E1000_RCTL_UPE;
 		vmolr |= E1000_VMOLR_ROPE;
 	}
@@ -4298,6 +4347,14 @@ static void igb_set_rx_mode(struct net_device *netdev)
 				     E1000_RCTL_VFE);
 	wr32(E1000_RCTL, rctl);
 
+#if (PAGE_SIZE < 8192)
+	if (!adapter->vfs_allocated_count) {
+		if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+			rlpml = IGB_MAX_FRAME_BUILD_SKB;
+	}
+#endif
+	wr32(E1000_RLPML, rlpml);
+
 	/* In order to support SR-IOV and eventually VMDq it is necessary to set
 	 * the VMOLR to enable the appropriate modes.  Without this workaround
 	 * we will have issues with VLAN tag stripping not being done for frames
@@ -4312,12 +4369,17 @@ static void igb_set_rx_mode(struct net_device *netdev)
 	vmolr |= rd32(E1000_VMOLR(vfn)) &
 		 ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE);
 
-	/* enable Rx jumbo frames, no need for restriction */
+	/* enable Rx jumbo frames, restrict as needed to support build_skb */
 	vmolr &= ~E1000_VMOLR_RLPML_MASK;
-	vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE;
+#if (PAGE_SIZE < 8192)
+	if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+		vmolr |= IGB_MAX_FRAME_BUILD_SKB;
+	else
+#endif
+		vmolr |= MAX_JUMBO_FRAME_SIZE;
+	vmolr |= E1000_VMOLR_LPE;
 
 	wr32(E1000_VMOLR(vfn), vmolr);
-	wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE);
 
 	igb_restore_vf_multicasts(adapter);
 }
@@ -5256,18 +5318,32 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
+	tx_buffer = &tx_ring->tx_buffer_info[i];
 
 	/* clear dma mappings for failed tx_buffer_info map */
-	for (;;) {
+	while (tx_buffer != first) {
+		if (dma_unmap_len(tx_buffer, len))
+			dma_unmap_page(tx_ring->dev,
+				       dma_unmap_addr(tx_buffer, dma),
+				       dma_unmap_len(tx_buffer, len),
+				       DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		if (i--)
+			i += tx_ring->count;
 		tx_buffer = &tx_ring->tx_buffer_info[i];
-		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer);
-		if (tx_buffer == first)
-			break;
-		if (i == 0)
-			i = tx_ring->count;
-		i--;
 	}
 
+	if (dma_unmap_len(tx_buffer, len))
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_buffer, len, 0);
+
+	dev_kfree_skb_any(tx_buffer->skb);
+	tx_buffer->skb = NULL;
+
 	tx_ring->next_to_use = i;
 }
 
@@ -5339,7 +5415,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 out_drop:
-	igb_unmap_and_free_tx_resource(tx_ring, first);
+	dev_kfree_skb_any(first->skb);
+	first->skb = NULL;
 
 	return NETDEV_TX_OK;
 }
@@ -6304,7 +6381,6 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses;
-	int rar_entry = hw->mac.rar_entry_count - (vf + 1);
 	u32 reg, msgbuf[3];
 	u8 *addr = (u8 *)(&msgbuf[1]);
 
@@ -6312,7 +6388,7 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 	igb_vf_reset(adapter, vf);
 
 	/* set vf mac address */
-	igb_rar_set_qsel(adapter, vf_mac, rar_entry, vf);
+	igb_set_vf_mac(adapter, vf, vf_mac);
 
 	/* enable transmit and receive for vf */
 	reg = rd32(E1000_VFTE);
@@ -6332,18 +6408,238 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 	igb_write_mbx(hw, msgbuf, 3, vf);
 }
 
+static void igb_flush_mac_table(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int i;
+
+	for (i = 0; i < hw->mac.rar_entry_count; i++) {
+		adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE;
+		memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+		adapter->mac_table[i].queue = 0;
+		igb_rar_set_index(adapter, i);
+	}
+}
+
+static int igb_available_rars(struct igb_adapter *adapter, u8 queue)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	/* do not count rar entries reserved for VFs MAC addresses */
+	int rar_entries = hw->mac.rar_entry_count -
+			  adapter->vfs_allocated_count;
+	int i, count = 0;
+
+	for (i = 0; i < rar_entries; i++) {
+		/* do not count default entries */
+		if (adapter->mac_table[i].state & IGB_MAC_STATE_DEFAULT)
+			continue;
+
+		/* do not count "in use" entries for different queues */
+		if ((adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE) &&
+		    (adapter->mac_table[i].queue != queue))
+			continue;
+
+		count++;
+	}
+
+	return count;
+}
+
+/* Set default MAC address for the PF in the first RAR entry */
+static void igb_set_default_mac_filter(struct igb_adapter *adapter)
+{
+	struct igb_mac_addr *mac_table = &adapter->mac_table[0];
+
+	ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
+	mac_table->queue = adapter->vfs_allocated_count;
+	mac_table->state = IGB_MAC_STATE_DEFAULT | IGB_MAC_STATE_IN_USE;
+
+	igb_rar_set_index(adapter, 0);
+}
+
+int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr,
+		       const u8 queue)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int rar_entries = hw->mac.rar_entry_count -
+			  adapter->vfs_allocated_count;
+	int i;
+
+	if (is_zero_ether_addr(addr))
+		return -EINVAL;
+
+	/* Search for the first empty entry in the MAC table.
+	 * Do not touch entries at the end of the table reserved for the VF MAC
+	 * addresses.
+	 */
+	for (i = 0; i < rar_entries; i++) {
+		if (adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE)
+			continue;
+
+		ether_addr_copy(adapter->mac_table[i].addr, addr);
+		adapter->mac_table[i].queue = queue;
+		adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE;
+
+		igb_rar_set_index(adapter, i);
+		return i;
+	}
+
+	return -ENOSPC;
+}
+
+int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr,
+		       const u8 queue)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int rar_entries = hw->mac.rar_entry_count -
+			  adapter->vfs_allocated_count;
+	int i;
+
+	if (is_zero_ether_addr(addr))
+		return -EINVAL;
+
+	/* Search for matching entry in the MAC table based on given address
+	 * and queue. Do not touch entries at the end of the table reserved
+	 * for the VF MAC addresses.
+	 */
+	for (i = 0; i < rar_entries; i++) {
+		if (!(adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE))
+			continue;
+		if (adapter->mac_table[i].queue != queue)
+			continue;
+		if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
+			continue;
+
+		adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE;
+		memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+		adapter->mac_table[i].queue = 0;
+
+		igb_rar_set_index(adapter, i);
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int igb_uc_sync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	int ret;
+
+	ret = igb_add_mac_filter(adapter, addr, adapter->vfs_allocated_count);
+
+	return min_t(int, ret, 0);
+}
+
+static int igb_uc_unsync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+
+	igb_del_mac_filter(adapter, addr, adapter->vfs_allocated_count);
+
+	return 0;
+}
+
+int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
+			  const u32 info, const u8 *addr)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
+	struct list_head *pos;
+	struct vf_mac_filter *entry = NULL;
+	int ret = 0;
+
+	switch (info) {
+	case E1000_VF_MAC_FILTER_CLR:
+		/* remove all unicast MAC filters related to the current VF */
+		list_for_each(pos, &adapter->vf_macs.l) {
+			entry = list_entry(pos, struct vf_mac_filter, l);
+			if (entry->vf == vf) {
+				entry->vf = -1;
+				entry->free = true;
+				igb_del_mac_filter(adapter, entry->vf_mac, vf);
+			}
+		}
+		break;
+	case E1000_VF_MAC_FILTER_ADD:
+		if (vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) {
+			dev_warn(&pdev->dev,
+				 "VF %d requested MAC filter but is administratively denied\n",
+				 vf);
+			return -EINVAL;
+		}
+
+		if (!is_valid_ether_addr(addr)) {
+			dev_warn(&pdev->dev,
+				 "VF %d attempted to set invalid MAC filter\n",
+				 vf);
+			return -EINVAL;
+		}
+
+		/* try to find empty slot in the list */
+		list_for_each(pos, &adapter->vf_macs.l) {
+			entry = list_entry(pos, struct vf_mac_filter, l);
+			if (entry->free)
+				break;
+		}
+
+		if (entry && entry->free) {
+			entry->free = false;
+			entry->vf = vf;
+			ether_addr_copy(entry->vf_mac, addr);
+
+			ret = igb_add_mac_filter(adapter, addr, vf);
+			ret = min_t(int, ret, 0);
+		} else {
+			ret = -ENOSPC;
+		}
+
+		if (ret == -ENOSPC)
+			dev_warn(&pdev->dev,
+				 "VF %d has requested MAC filter but there is no space for it\n",
+				 vf);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf)
 {
+	struct pci_dev *pdev = adapter->pdev;
+	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
+	u32 info = msg[0] & E1000_VT_MSGINFO_MASK;
+
 	/* The VF MAC Address is stored in a packed array of bytes
 	 * starting at the second 32 bit word of the msg array
 	 */
-	unsigned char *addr = (char *)&msg[1];
-	int err = -1;
+	unsigned char *addr = (unsigned char *)&msg[1];
+	int ret = 0;
 
-	if (is_valid_ether_addr(addr))
-		err = igb_set_vf_mac(adapter, vf, addr);
+	if (!info) {
+		if (vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) {
+			dev_warn(&pdev->dev,
+				 "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n",
+				 vf);
+			return -EINVAL;
+		}
 
-	return err;
+		if (!is_valid_ether_addr(addr)) {
+			dev_warn(&pdev->dev,
+				 "VF %d attempted to set invalid MAC\n",
+				 vf);
+			return -EINVAL;
+		}
+
+		ret = igb_set_vf_mac(adapter, vf, addr);
+	} else {
+		ret = igb_set_vf_mac_filter(adapter, vf, info, addr);
+	}
+
+	return ret;
 }
 
 static void igb_rcv_ack_from_vf(struct igb_adapter *adapter, u32 vf)
@@ -6400,13 +6696,7 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
 
 	switch ((msgbuf[0] & 0xFFFF)) {
 	case E1000_VF_SET_MAC_ADDR:
-		retval = -EINVAL;
-		if (!(vf_data->flags & IGB_VF_FLAG_PF_SET_MAC))
-			retval = igb_set_vf_mac_addr(adapter, msgbuf, vf);
-		else
-			dev_warn(&pdev->dev,
-				 "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n",
-				 vf);
+		retval = igb_set_vf_mac_addr(adapter, msgbuf, vf);
 		break;
 	case E1000_VF_SET_PROMISC:
 		retval = igb_set_vf_promisc(adapter, msgbuf, vf);
@@ -6686,7 +6976,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 				 DMA_TO_DEVICE);
 
 		/* clear tx_buffer data */
-		tx_buffer->skb = NULL;
 		dma_unmap_len_set(tx_buffer, len, 0);
 
 		/* clear last DMA location and unmap remaining buffers */
@@ -6822,8 +7111,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 	nta++;
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
-	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	/* Transfer page from old buffer to new buffer.
+	 * Move each member individually to avoid possible store
+	 * forwarding stalls.
+	 */
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 static inline bool igb_page_is_reserved(struct page *page)
@@ -6831,11 +7126,10 @@ static inline bool igb_page_is_reserved(struct page *page)
 	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
-static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
-				  struct page *page,
-				  unsigned int truesize)
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
 {
-	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--;
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* avoid re-using remote pages */
 	if (unlikely(igb_page_is_reserved(page)))
@@ -6843,16 +7137,13 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_ref_count(page) != pagecnt_bias))
+	if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
+#define IGB_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048)
 
-	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
+	if (rx_buffer->page_offset > IGB_LAST_OFFSET)
 		return false;
 #endif
 
@@ -6860,7 +7151,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 	 * the pagecnt_bias and page count so that we fully restock the
 	 * number of references the driver holds.
 	 */
-	if (unlikely(pagecnt_bias == 1)) {
+	if (unlikely(!pagecnt_bias)) {
 		page_ref_add(page, USHRT_MAX);
 		rx_buffer->pagecnt_bias = USHRT_MAX;
 	}
@@ -6872,34 +7163,56 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
  *  igb_add_rx_frag - Add contents of Rx buffer to sk_buff
  *  @rx_ring: rx descriptor ring to transact packets on
  *  @rx_buffer: buffer containing page to add
- *  @rx_desc: descriptor containing length of buffer written by hardware
  *  @skb: sk_buff to place the data into
+ *  @size: size of buffer to be added
  *
  *  This function will add the data contained in rx_buffer->page to the skb.
- *  This is done either through a direct copy if the data in the buffer is
- *  less than the skb header size, otherwise it will just attach the page as
- *  a frag to the skb.
- *
- *  The function will then update the page offset if necessary and return
- *  true if the buffer can be reused by the adapter.
  **/
-static bool igb_add_rx_frag(struct igb_ring *rx_ring,
+static void igb_add_rx_frag(struct igb_ring *rx_ring,
 			    struct igb_rx_buffer *rx_buffer,
-			    unsigned int size,
-			    union e1000_adv_rx_desc *rx_desc,
-			    struct sk_buff *skb)
+			    struct sk_buff *skb,
+			    unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = IGB_RX_BUFSZ;
+	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+				SKB_DATA_ALIGN(IGB_SKB_PAD + size) :
+				SKB_DATA_ALIGN(size);
+#endif
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
+static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
+					 struct igb_rx_buffer *rx_buffer,
+					 union e1000_adv_rx_desc *rx_desc,
+					 unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
-	unsigned int pull_len;
+	unsigned int headlen;
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
 
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
+	/* allocate a skb to store the frags */
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
+	if (unlikely(!skb))
+		return NULL;
 
 	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
 		igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
@@ -6907,95 +7220,73 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 		size -= IGB_TS_HDR_LEN;
 	}
 
-	if (likely(size <= IGB_RX_HDR_LEN)) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
-		/* page is not reserved, we can reuse buffer as-is */
-		if (likely(!igb_page_is_reserved(page)))
-			return true;
-
-		/* this page cannot be reused so discard it */
-		return false;
-	}
-
-	/* we need the header to contain the greater of either ETH_HLEN or
-	 * 60 bytes if the skb->len is less than 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN);
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > IGB_RX_HDR_LEN)
+		headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
 
 	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
-
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				(va + headlen) - page_address(rx_buffer->page),
+				size, truesize);
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		rx_buffer->pagecnt_bias++;
+	}
 
-	return igb_can_reuse_rx_page(rx_buffer, page, truesize);
+	return skb;
 }
 
-static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
-					   union e1000_adv_rx_desc *rx_desc,
-					   struct sk_buff *skb)
+static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
+				     struct igb_rx_buffer *rx_buffer,
+				     union e1000_adv_rx_desc *rx_desc,
+				     unsigned int size)
 {
-	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
-	struct igb_rx_buffer *rx_buffer;
-	struct page *page;
-
-	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
-
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) +
-				  rx_buffer->page_offset;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+				SKB_DATA_ALIGN(IGB_SKB_PAD + size);
+#endif
+	struct sk_buff *skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
 
-		/* allocate a skb to store the frags */
-		skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_failed++;
-			return NULL;
-		}
+	/* build an skb around the page buffer */
+	skb = build_skb(va - IGB_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
-	}
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, IGB_SKB_PAD);
+	__skb_put(skb, size);
 
-	/* pull page into skb */
-	if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) {
-		/* hand second half of page back to the ring */
-		igb_reuse_rx_page(rx_ring, rx_buffer);
-	} else {
-		/* We are not reusing the buffer so unmap it and free
-		 * any references we are holding to it
-		 */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
-				     PAGE_SIZE, DMA_FROM_DEVICE,
-				     DMA_ATTR_SKIP_CPU_SYNC);
-		__page_frag_cache_drain(page, rx_buffer->pagecnt_bias);
+	/* pull timestamp out of packet data */
+	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+		igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
+		__skb_pull(skb, IGB_TS_HDR_LEN);
 	}
 
-	/* clear contents of rx_buffer */
-	rx_buffer->page = NULL;
+	/* update buffer offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
 
 	return skb;
 }
@@ -7154,6 +7445,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
+static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
+					       const unsigned int size)
+{
+	struct igb_rx_buffer *rx_buffer;
+
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
+
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
+
+	rx_buffer->pagecnt_bias--;
+
+	return rx_buffer;
+}
+
+static void igb_put_rx_buffer(struct igb_ring *rx_ring,
+			      struct igb_rx_buffer *rx_buffer)
+{
+	if (igb_can_reuse_rx_page(rx_buffer)) {
+		/* hand second half of page back to the ring */
+		igb_reuse_rx_page(rx_ring, rx_buffer);
+	} else {
+		/* We are not reusing the buffer so unmap it and free
+		 * any references we are holding to it
+		 */
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
+				     IGB_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
+	}
+
+	/* clear contents of rx_buffer */
+	rx_buffer->page = NULL;
+}
+
 static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
 	struct igb_ring *rx_ring = q_vector->rx.ring;
@@ -7163,6 +7495,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 
 	while (likely(total_packets < budget)) {
 		union e1000_adv_rx_desc *rx_desc;
+		struct igb_rx_buffer *rx_buffer;
+		unsigned int size;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
@@ -7171,8 +7505,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		}
 
 		rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean);
-
-		if (!rx_desc->wb.upper.status_error)
+		size = le16_to_cpu(rx_desc->wb.upper.length);
+		if (!size)
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -7181,13 +7515,25 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		 */
 		dma_rmb();
 
+		rx_buffer = igb_get_rx_buffer(rx_ring, size);
+
 		/* retrieve a buffer from the ring */
-		skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
+		if (skb)
+			igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size);
+		else
+			skb = igb_construct_skb(rx_ring, rx_buffer,
+						rx_desc, size);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb)
+		if (!skb) {
+			rx_ring->rx_stats.alloc_failed++;
+			rx_buffer->pagecnt_bias++;
 			break;
+		}
 
+		igb_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		/* fetch next buffer in frame if non-eop */
@@ -7231,6 +7577,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	return total_packets;
 }
 
+static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0;
+}
+
 static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 				  struct igb_rx_buffer *bi)
 {
@@ -7242,21 +7593,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		return true;
 
 	/* alloc new page for storage */
-	page = dev_alloc_page();
+	page = dev_alloc_pages(igb_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_failed++;
 		return false;
 	}
 
 	/* map page for use */
-	dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
-				 DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 igb_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 IGB_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
 	 */
 	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_page(page);
+		__free_pages(page, igb_rx_pg_order(rx_ring));
 
 		rx_ring->rx_stats.alloc_failed++;
 		return false;
@@ -7264,7 +7617,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 
 	bi->dma = dma;
 	bi->page = page;
-	bi->page_offset = 0;
+	bi->page_offset = igb_rx_offset(rx_ring);
 	bi->pagecnt_bias = 1;
 
 	return true;
@@ -7279,6 +7632,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 	union e1000_adv_rx_desc *rx_desc;
 	struct igb_rx_buffer *bi;
 	u16 i = rx_ring->next_to_use;
+	u16 bufsz;
 
 	/* nothing to do */
 	if (!cleaned_count)
@@ -7288,14 +7642,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 	bi = &rx_ring->rx_buffer_info[i];
 	i -= rx_ring->count;
 
+	bufsz = igb_rx_bufsz(rx_ring);
+
 	do {
 		if (!igb_alloc_mapped_page(rx_ring, bi))
 			break;
 
 		/* sync the buffer for use by the device */
 		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 IGB_RX_BUFSZ,
+						 bi->page_offset, bufsz,
 						 DMA_FROM_DEVICE);
 
 		/* Refresh the desc even if buffer_addrs didn't change
@@ -7312,8 +7667,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 			i -= rx_ring->count;
 		}
 
-		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.upper.status_error = 0;
+		/* clear the length for the next_to_use descriptor */
+		rx_desc->wb.upper.length = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
@@ -7630,6 +7985,36 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	return 0;
 }
 
+static void igb_deliver_wake_packet(struct net_device *netdev)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct sk_buff *skb;
+	u32 wupl;
+
+	wupl = rd32(E1000_WUPL) & E1000_WUPL_MASK;
+
+	/* WUPM stores only the first 128 bytes of the wake packet.
+	 * Read the packet only if we have the whole thing.
+	 */
+	if ((wupl == 0) || (wupl > E1000_WUPM_BYTES))
+		return;
+
+	skb = netdev_alloc_skb_ip_align(netdev, E1000_WUPM_BYTES);
+	if (!skb)
+		return;
+
+	skb_put(skb, wupl);
+
+	/* Ensure reads are 32-bit aligned */
+	wupl = roundup(wupl, 4);
+
+	memcpy_fromio(skb->data, hw->hw_addr + E1000_WUPM_REG(0), wupl);
+
+	skb->protocol = eth_type_trans(skb, netdev);
+	netif_rx(skb);
+}
+
 #ifdef CONFIG_PM
 #ifdef CONFIG_PM_SLEEP
 static int igb_suspend(struct device *dev)
@@ -7659,7 +8044,7 @@ static int igb_resume(struct device *dev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 err;
+	u32 err, val;
 
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
@@ -7690,6 +8075,10 @@ static int igb_resume(struct device *dev)
 	 */
 	igb_get_hw_control(adapter);
 
+	val = rd32(E1000_WUS);
+	if (val & WAKE_PKT_WUS)
+		igb_deliver_wake_packet(netdev);
+
 	wr32(E1000_WUS, ~0);
 
 	rtnl_lock();
@@ -7948,11 +8337,16 @@ static void igb_io_resume(struct pci_dev *pdev)
 	igb_get_hw_control(adapter);
 }
 
-static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index,
-			     u8 qsel)
+/**
+ *  igb_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
+ *  @adapter: Pointer to adapter structure
+ *  @index: Index of the RAR entry which need to be synced with MAC table
+ **/
+static void igb_rar_set_index(struct igb_adapter *adapter, u32 index)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 rar_low, rar_high;
+	u8 *addr = adapter->mac_table[index].addr;
 
 	/* HW expects these to be in network order when they are plugged
 	 * into the registers which are little endian.  In order to guarantee
@@ -7963,12 +8357,16 @@ static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index,
 	rar_high = le16_to_cpup((__le16 *)(addr + 4));
 
 	/* Indicate to hardware the Address is Valid. */
-	rar_high |= E1000_RAH_AV;
+	if (adapter->mac_table[index].state & IGB_MAC_STATE_IN_USE) {
+		rar_high |= E1000_RAH_AV;
 
-	if (hw->mac.type == e1000_82575)
-		rar_high |= E1000_RAH_POOL_1 * qsel;
-	else
-		rar_high |= E1000_RAH_POOL_1 << qsel;
+		if (hw->mac.type == e1000_82575)
+			rar_high |= E1000_RAH_POOL_1 *
+				    adapter->mac_table[index].queue;
+		else
+			rar_high |= E1000_RAH_POOL_1 <<
+				    adapter->mac_table[index].queue;
+	}
 
 	wr32(E1000_RAL(index), rar_low);
 	wrfl();
@@ -7984,10 +8382,13 @@ static int igb_set_vf_mac(struct igb_adapter *adapter,
 	 * towards the first, as a result a collision should not be possible
 	 */
 	int rar_entry = hw->mac.rar_entry_count - (vf + 1);
+	unsigned char *vf_mac_addr = adapter->vf_data[vf].vf_mac_addresses;
 
-	memcpy(adapter->vf_data[vf].vf_mac_addresses, mac_addr, ETH_ALEN);
-
-	igb_rar_set_qsel(adapter, mac_addr, rar_entry, vf);
+	ether_addr_copy(vf_mac_addr, mac_addr);
+	ether_addr_copy(adapter->mac_table[rar_entry].addr, mac_addr);
+	adapter->mac_table[rar_entry].queue = vf;
+	adapter->mac_table[rar_entry].state |= IGB_MAC_STATE_IN_USE;
+	igb_rar_set_index(adapter, rar_entry);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index c4477552ce9e..7a3fd4d74592 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
  * incoming frame.  The value is stored in little endian format starting on
  * byte 8.
  **/
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector,
-			 unsigned char *va,
+void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			 struct sk_buff *skb)
 {
 	__le64 *regval = (__le64 *)va;
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index 8dea1b1367ef..34faa113a8a0 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -71,45 +71,45 @@ static const char igbvf_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define IGBVF_TEST_LEN ARRAY_SIZE(igbvf_gstrings_test)
 
-static int igbvf_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int igbvf_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	u32 status;
 
-	ecmd->supported   = SUPPORTED_1000baseT_Full;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
 
-	ecmd->advertising = ADVERTISED_1000baseT_Full;
-
-	ecmd->port = -1;
-	ecmd->transceiver = XCVR_DUMMY1;
+	cmd->base.port = -1;
 
 	status = er32(STATUS);
 	if (status & E1000_STATUS_LU) {
 		if (status & E1000_STATUS_SPEED_1000)
-			ethtool_cmd_speed_set(ecmd, SPEED_1000);
+			cmd->base.speed = SPEED_1000;
 		else if (status & E1000_STATUS_SPEED_100)
-			ethtool_cmd_speed_set(ecmd, SPEED_100);
+			cmd->base.speed = SPEED_100;
 		else
-			ethtool_cmd_speed_set(ecmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 
 		if (status & E1000_STATUS_FD)
-			ecmd->duplex = DUPLEX_FULL;
+			cmd->base.duplex = DUPLEX_FULL;
 		else
-			ecmd->duplex = DUPLEX_HALF;
+			cmd->base.duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = AUTONEG_DISABLE;
+	cmd->base.autoneg = AUTONEG_DISABLE;
 
 	return 0;
 }
 
-static int igbvf_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int igbvf_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	return -EOPNOTSUPP;
 }
@@ -443,8 +443,6 @@ static void igbvf_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 static const struct ethtool_ops igbvf_ethtool_ops = {
-	.get_settings		= igbvf_get_settings,
-	.set_settings		= igbvf_set_settings,
 	.get_drvinfo		= igbvf_get_drvinfo,
 	.get_regs_len		= igbvf_get_regs_len,
 	.get_regs		= igbvf_get_regs,
@@ -467,6 +465,8 @@ static const struct ethtool_ops igbvf_ethtool_ops = {
 	.get_ethtool_stats	= igbvf_get_ethtool_stats,
 	.get_coalesce		= igbvf_get_coalesce,
 	.set_coalesce		= igbvf_set_coalesce,
+	.get_link_ksettings	= igbvf_get_link_ksettings,
+	.set_link_ksettings	= igbvf_set_link_ksettings,
 };
 
 void igbvf_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h
index 6f4290d6dc9f..bf69f01f8467 100644
--- a/drivers/net/ethernet/intel/igbvf/igbvf.h
+++ b/drivers/net/ethernet/intel/igbvf/igbvf.h
@@ -101,6 +101,8 @@ enum latency_range {
 
 #define IGBVF_MNG_VLAN_NONE	(-1)
 
+#define IGBVF_MAX_MAC_FILTERS	3
+
 /* Number of packet split data buffers (not including the header buffer) */
 #define PS_PAGE_BUFFERS		(MAX_PS_BUFFERS - 1)
 
@@ -241,7 +243,6 @@ struct igbvf_adapter {
 	/* OS defined structs */
 	struct net_device *netdev;
 	struct pci_dev *pdev;
-	struct net_device_stats net_stats;
 	spinlock_t stats_lock; /* prevent concurrent stats updates */
 
 	/* structs defined in e1000_hw.h */
diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h
index f800bf8eedae..30d58c4a444e 100644
--- a/drivers/net/ethernet/intel/igbvf/mbx.h
+++ b/drivers/net/ethernet/intel/igbvf/mbx.h
@@ -62,6 +62,10 @@
 
 #define E1000_VF_RESET		0x01 /* VF requests reset */
 #define E1000_VF_SET_MAC_ADDR	0x02 /* VF requests PF to set MAC addr */
+/* VF requests PF to clear all unicast MAC filters */
+#define E1000_VF_MAC_FILTER_CLR (0x01 << E1000_VT_MSGINFO_SHIFT)
+/* VF requests PF to add unicast MAC filter */
+#define E1000_VF_MAC_FILTER_ADD (0x02 << E1000_VT_MSGINFO_SHIFT)
 #define E1000_VF_SET_MULTICAST	0x03 /* VF requests PF to set MC addr */
 #define E1000_VF_SET_VLAN	0x04 /* VF requests PF to set VLAN */
 #define E1000_VF_SET_LPE	0x05 /* VF requests PF to set VMOLR.LPE */
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 839ba110f7fb..1b9cbbe88f6f 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -400,8 +400,8 @@ next_desc:
 
 	adapter->total_rx_packets += total_packets;
 	adapter->total_rx_bytes += total_bytes;
-	adapter->net_stats.rx_bytes += total_bytes;
-	adapter->net_stats.rx_packets += total_packets;
+	netdev->stats.rx_bytes += total_bytes;
+	netdev->stats.rx_packets += total_packets;
 	return cleaned;
 }
 
@@ -864,8 +864,8 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring)
 		}
 	}
 
-	adapter->net_stats.tx_bytes += total_bytes;
-	adapter->net_stats.tx_packets += total_packets;
+	netdev->stats.tx_bytes += total_bytes;
+	netdev->stats.tx_packets += total_packets;
 	return count < tx_ring->count;
 }
 
@@ -1433,12 +1433,52 @@ static void igbvf_set_multi(struct net_device *netdev)
 }
 
 /**
+ * igbvf_set_uni - Configure unicast MAC filters
+ * @netdev: network interface device structure
+ *
+ * This routine is responsible for configuring the hardware for proper
+ * unicast filters.
+ **/
+static int igbvf_set_uni(struct net_device *netdev)
+{
+	struct igbvf_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+
+	if (netdev_uc_count(netdev) > IGBVF_MAX_MAC_FILTERS) {
+		pr_err("Too many unicast filters - No Space\n");
+		return -ENOSPC;
+	}
+
+	/* Clear all unicast MAC filters */
+	hw->mac.ops.set_uc_addr(hw, E1000_VF_MAC_FILTER_CLR, NULL);
+
+	if (!netdev_uc_empty(netdev)) {
+		struct netdev_hw_addr *ha;
+
+		/* Add MAC filters one by one */
+		netdev_for_each_uc_addr(ha, netdev) {
+			hw->mac.ops.set_uc_addr(hw, E1000_VF_MAC_FILTER_ADD,
+						ha->addr);
+			udelay(200);
+		}
+	}
+
+	return 0;
+}
+
+static void igbvf_set_rx_mode(struct net_device *netdev)
+{
+	igbvf_set_multi(netdev);
+	igbvf_set_uni(netdev);
+}
+
+/**
  * igbvf_configure - configure the hardware for Rx and Tx
  * @adapter: private board structure
  **/
 static void igbvf_configure(struct igbvf_adapter *adapter)
 {
-	igbvf_set_multi(adapter->netdev);
+	igbvf_set_rx_mode(adapter->netdev);
 
 	igbvf_restore_vlan(adapter);
 
@@ -1798,7 +1838,7 @@ void igbvf_update_stats(struct igbvf_adapter *adapter)
 	UPDATE_VF_COUNTER(VFGPRLBC, gprlbc);
 
 	/* Fill out the OS statistics structure */
-	adapter->net_stats.multicast = adapter->stats.mprc;
+	adapter->netdev->stats.multicast = adapter->stats.mprc;
 }
 
 static void igbvf_print_link_info(struct igbvf_adapter *adapter)
@@ -2334,21 +2374,6 @@ static void igbvf_reset_task(struct work_struct *work)
 }
 
 /**
- * igbvf_get_stats - Get System Network Statistics
- * @netdev: network interface device structure
- *
- * Returns the address of the device statistics structure.
- * The statistics are actually updated from the timer callback.
- **/
-static struct net_device_stats *igbvf_get_stats(struct net_device *netdev)
-{
-	struct igbvf_adapter *adapter = netdev_priv(netdev);
-
-	/* only return the current stats */
-	return &adapter->net_stats;
-}
-
-/**
  * igbvf_change_mtu - Change the Maximum Transfer Unit
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
@@ -2635,8 +2660,7 @@ static const struct net_device_ops igbvf_netdev_ops = {
 	.ndo_open		= igbvf_open,
 	.ndo_stop		= igbvf_close,
 	.ndo_start_xmit		= igbvf_xmit_frame,
-	.ndo_get_stats		= igbvf_get_stats,
-	.ndo_set_rx_mode	= igbvf_set_multi,
+	.ndo_set_rx_mode	= igbvf_set_rx_mode,
 	.ndo_set_mac_address	= igbvf_set_mac,
 	.ndo_change_mtu		= igbvf_change_mtu,
 	.ndo_do_ioctl		= igbvf_ioctl,
diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c
index 335ba6642145..528be116184e 100644
--- a/drivers/net/ethernet/intel/igbvf/vf.c
+++ b/drivers/net/ethernet/intel/igbvf/vf.c
@@ -36,6 +36,7 @@ static void e1000_update_mc_addr_list_vf(struct e1000_hw *hw, u8 *,
 					 u32, u32, u32);
 static void e1000_rar_set_vf(struct e1000_hw *, u8 *, u32);
 static s32 e1000_read_mac_addr_vf(struct e1000_hw *);
+static s32 e1000_set_uc_addr_vf(struct e1000_hw *hw, u32 subcmd, u8 *addr);
 static s32 e1000_set_vfta_vf(struct e1000_hw *, u16, bool);
 
 /**
@@ -66,6 +67,8 @@ static s32 e1000_init_mac_params_vf(struct e1000_hw *hw)
 	mac->ops.rar_set = e1000_rar_set_vf;
 	/* read mac address */
 	mac->ops.read_mac_addr = e1000_read_mac_addr_vf;
+	/* set mac filter */
+	mac->ops.set_uc_addr = e1000_set_uc_addr_vf;
 	/* set vlan filter table array */
 	mac->ops.set_vfta = e1000_set_vfta_vf;
 
@@ -338,6 +341,44 @@ static s32 e1000_read_mac_addr_vf(struct e1000_hw *hw)
 }
 
 /**
+ *  e1000_set_uc_addr_vf - Set or clear unicast filters
+ *  @hw: pointer to the HW structure
+ *  @sub_cmd: add or clear filters
+ *  @addr: pointer to the filter MAC address
+ **/
+static s32 e1000_set_uc_addr_vf(struct e1000_hw *hw, u32 sub_cmd, u8 *addr)
+{
+	struct e1000_mbx_info *mbx = &hw->mbx;
+	u32 msgbuf[3], msgbuf_chk;
+	u8 *msg_addr = (u8 *)(&msgbuf[1]);
+	s32 ret_val;
+
+	memset(msgbuf, 0, sizeof(msgbuf));
+	msgbuf[0] |= sub_cmd;
+	msgbuf[0] |= E1000_VF_SET_MAC_ADDR;
+	msgbuf_chk = msgbuf[0];
+
+	if (addr)
+		memcpy(msg_addr, addr, ETH_ALEN);
+
+	ret_val = mbx->ops.write_posted(hw, msgbuf, 3);
+
+	if (!ret_val)
+		ret_val = mbx->ops.read_posted(hw, msgbuf, 3);
+
+	msgbuf[0] &= ~E1000_VT_MSGTYPE_CTS;
+
+	if (!ret_val) {
+		msgbuf[0] &= ~E1000_VT_MSGTYPE_CTS;
+
+		if (msgbuf[0] == (msgbuf_chk | E1000_VT_MSGTYPE_NACK))
+			return -ENOSPC;
+	}
+
+	return ret_val;
+}
+
+/**
  *  e1000_check_for_link_vf - Check for link for a virtual interface
  *  @hw: pointer to the HW structure
  *
diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h
index f00a41d9a1ca..4cf78b0dec50 100644
--- a/drivers/net/ethernet/intel/igbvf/vf.h
+++ b/drivers/net/ethernet/intel/igbvf/vf.h
@@ -179,6 +179,7 @@ struct e1000_mac_operations {
 	s32  (*get_bus_info)(struct e1000_hw *);
 	s32  (*get_link_up_info)(struct e1000_hw *, u16 *, u16 *);
 	void (*update_mc_addr_list)(struct e1000_hw *, u8 *, u32, u32, u32);
+	s32  (*set_uc_addr)(struct e1000_hw *, u32, u8 *);
 	s32  (*reset_hw)(struct e1000_hw *);
 	s32  (*init_hw)(struct e1000_hw *);
 	s32  (*setup_link)(struct e1000_hw *);
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index e5d72559cca9..d10a0d242dda 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -94,24 +94,30 @@ static struct ixgb_stats ixgb_gstrings_stats[] = {
 #define IXGB_STATS_LEN	ARRAY_SIZE(ixgb_gstrings_stats)
 
 static int
-ixgb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+ixgb_get_link_ksettings(struct net_device *netdev,
+			struct ethtool_link_ksettings *cmd)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
 
-	ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-	ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-	ecmd->port = PORT_FIBRE;
-	ecmd->transceiver = XCVR_EXTERNAL;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+
+	cmd->base.port = PORT_FIBRE;
 
 	if (netif_carrier_ok(adapter->netdev)) {
-		ethtool_cmd_speed_set(ecmd, SPEED_10000);
-		ecmd->duplex = DUPLEX_FULL;
+		cmd->base.speed = SPEED_10000;
+		cmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = AUTONEG_DISABLE;
+	cmd->base.autoneg = AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -126,13 +132,14 @@ void ixgb_set_speed_duplex(struct net_device *netdev)
 }
 
 static int
-ixgb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+ixgb_set_link_ksettings(struct net_device *netdev,
+			const struct ethtool_link_ksettings *cmd)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
-	u32 speed = ethtool_cmd_speed(ecmd);
+	u32 speed = cmd->base.speed;
 
-	if (ecmd->autoneg == AUTONEG_ENABLE ||
-	    (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL))
+	if (cmd->base.autoneg == AUTONEG_ENABLE ||
+	    (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL))
 		return -EINVAL;
 
 	if (netif_running(adapter->netdev)) {
@@ -630,8 +637,6 @@ ixgb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 }
 
 static const struct ethtool_ops ixgb_ethtool_ops = {
-	.get_settings = ixgb_get_settings,
-	.set_settings = ixgb_set_settings,
 	.get_drvinfo = ixgb_get_drvinfo,
 	.get_regs_len = ixgb_get_regs_len,
 	.get_regs = ixgb_get_regs,
@@ -649,6 +654,8 @@ static const struct ethtool_ops ixgb_ethtool_ops = {
 	.set_phys_id = ixgb_set_phys_id,
 	.get_sset_count = ixgb_get_sset_count,
 	.get_ethtool_stats = ixgb_get_ethtool_stats,
+	.get_link_ksettings = ixgb_get_link_ksettings,
+	.set_link_ksettings = ixgb_set_link_ksettings,
 };
 
 void ixgb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index fbd220d137b3..5a713199653c 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -86,7 +86,6 @@ static void ixgb_set_multi(struct net_device *netdev);
 static void ixgb_watchdog(unsigned long data);
 static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb,
 				   struct net_device *netdev);
-static struct net_device_stats *ixgb_get_stats(struct net_device *netdev);
 static int ixgb_change_mtu(struct net_device *netdev, int new_mtu);
 static int ixgb_set_mac(struct net_device *netdev, void *p);
 static irqreturn_t ixgb_intr(int irq, void *data);
@@ -367,7 +366,6 @@ static const struct net_device_ops ixgb_netdev_ops = {
 	.ndo_open 		= ixgb_open,
 	.ndo_stop		= ixgb_close,
 	.ndo_start_xmit		= ixgb_xmit_frame,
-	.ndo_get_stats		= ixgb_get_stats,
 	.ndo_set_rx_mode	= ixgb_set_multi,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgb_set_mac,
@@ -1597,20 +1595,6 @@ ixgb_tx_timeout_task(struct work_struct *work)
 }
 
 /**
- * ixgb_get_stats - Get System Network Statistics
- * @netdev: network interface device structure
- *
- * Returns the address of the device statistics structure.
- * The statistics are actually updated from the timer callback.
- **/
-
-static struct net_device_stats *
-ixgb_get_stats(struct net_device *netdev)
-{
-	return &netdev->stats;
-}
-
-/**
  * ixgb_change_mtu - Change the Maximum Transfer Unit
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index b1ecc2627a5a..76263762bea1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -86,17 +86,62 @@
 
 /* Supported Rx Buffer Sizes */
 #define IXGBE_RXBUFFER_256    256  /* Used for skb receive header */
+#define IXGBE_RXBUFFER_1536  1536
 #define IXGBE_RXBUFFER_2K    2048
 #define IXGBE_RXBUFFER_3K    3072
 #define IXGBE_RXBUFFER_4K    4096
 #define IXGBE_MAX_RXBUFFER  16384  /* largest size for a single descriptor */
 
-#define IXGBE_SKB_PAD		(NET_SKB_PAD + NET_IP_ALIGN)
+/* Attempt to maximize the headroom available for incoming frames.  We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame.  This leaves us with 512 bytes of room.  From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ *	 up negative.  In these cases we should fall back to the 3K
+ *	 buffers.
+ */
 #if (PAGE_SIZE < 8192)
-#define IXGBE_MAX_FRAME_BUILD_SKB \
-	(SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K) - IXGBE_SKB_PAD)
+#define IXGBE_MAX_2K_FRAME_BUILD_SKB (IXGBE_RXBUFFER_1536 - NET_IP_ALIGN)
+#define IXGBE_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + IXGBE_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K))
+
+static inline int ixgbe_compute_pad(int rx_buf_len)
+{
+	int page_size, pad_size;
+
+	page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+	pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+	return pad_size;
+}
+
+static inline int ixgbe_skb_pad(void)
+{
+	int rx_buf_len;
+
+	/* If a 2K buffer cannot handle a standard Ethernet frame then
+	 * optimize padding for a 3K buffer instead of a 1.5K buffer.
+	 *
+	 * For a 3K buffer we need to add enough padding to allow for
+	 * tailroom due to NET_IP_ALIGN possibly shifting us out of
+	 * cache-line alignment.
+	 */
+	if (IXGBE_2K_TOO_SMALL_WITH_PADDING)
+		rx_buf_len = IXGBE_RXBUFFER_3K + SKB_DATA_ALIGN(NET_IP_ALIGN);
+	else
+		rx_buf_len = IXGBE_RXBUFFER_1536;
+
+	/* if needed make room for NET_IP_ALIGN */
+	rx_buf_len -= NET_IP_ALIGN;
+
+	return ixgbe_compute_pad(rx_buf_len);
+}
+
+#define IXGBE_SKB_PAD	ixgbe_skb_pad()
 #else
-#define IXGBE_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K
+#define IXGBE_SKB_PAD	(NET_SKB_PAD + NET_IP_ALIGN)
 #endif
 
 /*
@@ -190,7 +235,11 @@ struct vf_macvlans {
 struct ixgbe_tx_buffer {
 	union ixgbe_adv_tx_desc *next_to_watch;
 	unsigned long time_stamp;
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		/* XDP uses address ptr on irq_clean */
+		void *data;
+	};
 	unsigned int bytecount;
 	unsigned short gso_segs;
 	__be16 protocol;
@@ -243,6 +292,7 @@ enum ixgbe_ring_state_t {
 	__IXGBE_TX_XPS_INIT_DONE,
 	__IXGBE_TX_DETECT_HANG,
 	__IXGBE_HANG_CHECK_ARMED,
+	__IXGBE_TX_XDP_RING,
 };
 
 #define ring_uses_build_skb(ring) \
@@ -269,10 +319,17 @@ struct ixgbe_fwd_adapter {
 	set_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state)
 #define clear_ring_rsc_enabled(ring) \
 	clear_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state)
+#define ring_is_xdp(ring) \
+	test_bit(__IXGBE_TX_XDP_RING, &(ring)->state)
+#define set_ring_xdp(ring) \
+	set_bit(__IXGBE_TX_XDP_RING, &(ring)->state)
+#define clear_ring_xdp(ring) \
+	clear_bit(__IXGBE_TX_XDP_RING, &(ring)->state)
 struct ixgbe_ring {
 	struct ixgbe_ring *next;	/* pointer to next ring in q_vector */
 	struct ixgbe_q_vector *q_vector; /* backpointer to host q_vector */
 	struct net_device *netdev;	/* netdev ring belongs to */
+	struct bpf_prog *xdp_prog;
 	struct device *dev;		/* device for DMA mapping */
 	struct ixgbe_fwd_adapter *l2_accel_priv;
 	void *desc;			/* descriptor ring memory */
@@ -334,6 +391,7 @@ enum ixgbe_ring_f_enum {
 #define IXGBE_MAX_FCOE_INDICES		8
 #define MAX_RX_QUEUES			(IXGBE_MAX_FDIR_INDICES + 1)
 #define MAX_TX_QUEUES			(IXGBE_MAX_FDIR_INDICES + 1)
+#define MAX_XDP_QUEUES			(IXGBE_MAX_FDIR_INDICES + 1)
 #define IXGBE_MAX_L2A_QUEUES		4
 #define IXGBE_BAD_L2A_QUEUE		3
 #define IXGBE_MAX_MACVLANS		31
@@ -361,7 +419,7 @@ static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring)
 		return IXGBE_RXBUFFER_3K;
 #if (PAGE_SIZE < 8192)
 	if (ring_uses_build_skb(ring))
-		return IXGBE_MAX_FRAME_BUILD_SKB;
+		return IXGBE_MAX_2K_FRAME_BUILD_SKB;
 #endif
 	return IXGBE_RXBUFFER_2K;
 }
@@ -510,6 +568,7 @@ struct ixgbe_adapter {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	/* OS defined structs */
 	struct net_device *netdev;
+	struct bpf_prog *xdp_prog;
 	struct pci_dev *pdev;
 
 	unsigned long state;
@@ -576,6 +635,10 @@ struct ixgbe_adapter {
 	__be16 vxlan_port;
 	__be16 geneve_port;
 
+	/* XDP */
+	int num_xdp_queues;
+	struct ixgbe_ring *xdp_ring[MAX_XDP_QUEUES];
+
 	/* TX */
 	struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp;
 
@@ -622,6 +685,7 @@ struct ixgbe_adapter {
 
 	u64 tx_busy;
 	unsigned int tx_ring_count;
+	unsigned int xdp_ring_count;
 	unsigned int rx_ring_count;
 
 	u32 link_speed;
@@ -705,7 +769,7 @@ struct ixgbe_adapter {
 	u8 rss_indir_tbl[IXGBE_MAX_RETA_ENTRIES];
 
 #define IXGBE_RSS_KEY_SIZE     40  /* size of RSS Hash Key in bytes */
-	u32 rss_key[IXGBE_RSS_KEY_SIZE / sizeof(u32)];
+	u32 *rss_key;
 };
 
 static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
@@ -762,6 +826,7 @@ enum ixgbe_boards {
 	board_X540,
 	board_X550,
 	board_X550EM_x,
+	board_x550em_x_fw,
 	board_x550em_a,
 	board_x550em_a_fw,
 };
@@ -771,6 +836,7 @@ extern const struct ixgbe_info ixgbe_82599_info;
 extern const struct ixgbe_info ixgbe_X540_info;
 extern const struct ixgbe_info ixgbe_X550_info;
 extern const struct ixgbe_info ixgbe_X550EM_x_info;
+extern const struct ixgbe_info ixgbe_x550em_x_fw_info;
 extern const struct ixgbe_info ixgbe_x550em_a_info;
 extern const struct ixgbe_info ixgbe_x550em_a_fw_info;
 #ifdef CONFIG_IXGBE_DCB
@@ -790,7 +856,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter);
 void ixgbe_reinit_locked(struct ixgbe_adapter *adapter);
 void ixgbe_reset(struct ixgbe_adapter *adapter);
 void ixgbe_set_ethtool_ops(struct net_device *netdev);
-int ixgbe_setup_rx_resources(struct ixgbe_ring *);
+int ixgbe_setup_rx_resources(struct ixgbe_adapter *, struct ixgbe_ring *);
 int ixgbe_setup_tx_resources(struct ixgbe_ring *);
 void ixgbe_free_rx_resources(struct ixgbe_ring *);
 void ixgbe_free_tx_resources(struct ixgbe_ring *);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 90fa5bf23d1b..7e5e336d7dcc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -179,6 +179,7 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw)
 	case IXGBE_DEV_ID_82598_BX:
 	case IXGBE_DEV_ID_82599_KR:
 	case IXGBE_DEV_ID_X550EM_X_KR:
+	case IXGBE_DEV_ID_X550EM_X_XFI:
 		return SUPPORTED_10000baseKR_Full;
 	default:
 		return SUPPORTED_10000baseKX4_Full |
@@ -186,60 +187,62 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw)
 	}
 }
 
-static int ixgbe_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int ixgbe_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	ixgbe_link_speed supported_link;
 	bool autoneg = false;
+	u32 supported, advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
 
 	hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg);
 
 	/* set the supported link speeds */
 	if (supported_link & IXGBE_LINK_SPEED_10GB_FULL)
-		ecmd->supported |= ixgbe_get_supported_10gtypes(hw);
+		supported |= ixgbe_get_supported_10gtypes(hw);
 	if (supported_link & IXGBE_LINK_SPEED_1GB_FULL)
-		ecmd->supported |= (ixgbe_isbackplane(hw->phy.media_type)) ?
+		supported |= (ixgbe_isbackplane(hw->phy.media_type)) ?
 				   SUPPORTED_1000baseKX_Full :
 				   SUPPORTED_1000baseT_Full;
 	if (supported_link & IXGBE_LINK_SPEED_100_FULL)
-		ecmd->supported |= SUPPORTED_100baseT_Full;
+		supported |= SUPPORTED_100baseT_Full;
 	if (supported_link & IXGBE_LINK_SPEED_10_FULL)
-		ecmd->supported |= SUPPORTED_10baseT_Full;
+		supported |= SUPPORTED_10baseT_Full;
 
 	/* default advertised speed if phy.autoneg_advertised isn't set */
-	ecmd->advertising = ecmd->supported;
+	advertising = supported;
 	/* set the advertised speeds */
 	if (hw->phy.autoneg_advertised) {
-		ecmd->advertising = 0;
+		advertising = 0;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL)
-			ecmd->advertising |= ADVERTISED_10baseT_Full;
+			advertising |= ADVERTISED_10baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL)
-			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
-			ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G;
+			advertising |= supported & ADVRTSD_MSK_10G;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) {
-			if (ecmd->supported & SUPPORTED_1000baseKX_Full)
-				ecmd->advertising |= ADVERTISED_1000baseKX_Full;
+			if (supported & SUPPORTED_1000baseKX_Full)
+				advertising |= ADVERTISED_1000baseKX_Full;
 			else
-				ecmd->advertising |= ADVERTISED_1000baseT_Full;
+				advertising |= ADVERTISED_1000baseT_Full;
 		}
 	} else {
 		if (hw->phy.multispeed_fiber && !autoneg) {
 			if (supported_link & IXGBE_LINK_SPEED_10GB_FULL)
-				ecmd->advertising = ADVERTISED_10000baseT_Full;
+				advertising = ADVERTISED_10000baseT_Full;
 		}
 	}
 
 	if (autoneg) {
-		ecmd->supported |= SUPPORTED_Autoneg;
-		ecmd->advertising |= ADVERTISED_Autoneg;
-		ecmd->autoneg = AUTONEG_ENABLE;
+		supported |= SUPPORTED_Autoneg;
+		advertising |= ADVERTISED_Autoneg;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 	} else
-		ecmd->autoneg = AUTONEG_DISABLE;
-
-	ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.autoneg = AUTONEG_DISABLE;
 
 	/* Determine the remaining settings based on the PHY type. */
 	switch (adapter->hw.phy.type) {
@@ -248,14 +251,14 @@ static int ixgbe_get_settings(struct net_device *netdev,
 	case ixgbe_phy_x550em_ext_t:
 	case ixgbe_phy_fw:
 	case ixgbe_phy_cu_unknown:
-		ecmd->supported |= SUPPORTED_TP;
-		ecmd->advertising |= ADVERTISED_TP;
-		ecmd->port = PORT_TP;
+		supported |= SUPPORTED_TP;
+		advertising |= ADVERTISED_TP;
+		cmd->base.port = PORT_TP;
 		break;
 	case ixgbe_phy_qt:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_FIBRE;
+		supported |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_FIBRE;
 		break;
 	case ixgbe_phy_nl:
 	case ixgbe_phy_sfp_passive_tyco:
@@ -273,9 +276,9 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		case ixgbe_sfp_type_da_cu:
 		case ixgbe_sfp_type_da_cu_core0:
 		case ixgbe_sfp_type_da_cu_core1:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_DA;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_DA;
 			break;
 		case ixgbe_sfp_type_sr:
 		case ixgbe_sfp_type_lr:
@@ -285,102 +288,113 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		case ixgbe_sfp_type_1g_sx_core1:
 		case ixgbe_sfp_type_1g_lx_core0:
 		case ixgbe_sfp_type_1g_lx_core1:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_FIBRE;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_FIBRE;
 			break;
 		case ixgbe_sfp_type_not_present:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_NONE;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_NONE;
 			break;
 		case ixgbe_sfp_type_1g_cu_core0:
 		case ixgbe_sfp_type_1g_cu_core1:
-			ecmd->supported |= SUPPORTED_TP;
-			ecmd->advertising |= ADVERTISED_TP;
-			ecmd->port = PORT_TP;
+			supported |= SUPPORTED_TP;
+			advertising |= ADVERTISED_TP;
+			cmd->base.port = PORT_TP;
 			break;
 		case ixgbe_sfp_type_unknown:
 		default:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_OTHER;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_OTHER;
 			break;
 		}
 		break;
 	case ixgbe_phy_xaui:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_NONE;
+		supported |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_NONE;
 		break;
 	case ixgbe_phy_unknown:
 	case ixgbe_phy_generic:
 	case ixgbe_phy_sfp_unsupported:
 	default:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_OTHER;
+		supported |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_OTHER;
 		break;
 	}
 
 	/* Indicate pause support */
-	ecmd->supported |= SUPPORTED_Pause;
+	supported |= SUPPORTED_Pause;
 
 	switch (hw->fc.requested_mode) {
 	case ixgbe_fc_full:
-		ecmd->advertising |= ADVERTISED_Pause;
+		advertising |= ADVERTISED_Pause;
 		break;
 	case ixgbe_fc_rx_pause:
-		ecmd->advertising |= ADVERTISED_Pause |
+		advertising |= ADVERTISED_Pause |
 				     ADVERTISED_Asym_Pause;
 		break;
 	case ixgbe_fc_tx_pause:
-		ecmd->advertising |= ADVERTISED_Asym_Pause;
+		advertising |= ADVERTISED_Asym_Pause;
 		break;
 	default:
-		ecmd->advertising &= ~(ADVERTISED_Pause |
+		advertising &= ~(ADVERTISED_Pause |
 				       ADVERTISED_Asym_Pause);
 	}
 
 	if (netif_carrier_ok(netdev)) {
 		switch (adapter->link_speed) {
 		case IXGBE_LINK_SPEED_10GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_10000);
+			cmd->base.speed = SPEED_10000;
 			break;
 		case IXGBE_LINK_SPEED_5GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_5000);
+			cmd->base.speed = SPEED_5000;
 			break;
 		case IXGBE_LINK_SPEED_2_5GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_2500);
+			cmd->base.speed = SPEED_2500;
 			break;
 		case IXGBE_LINK_SPEED_1GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_1000);
+			cmd->base.speed = SPEED_1000;
 			break;
 		case IXGBE_LINK_SPEED_100_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_100);
+			cmd->base.speed = SPEED_100;
 			break;
 		case IXGBE_LINK_SPEED_10_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 			break;
 		default:
 			break;
 		}
-		ecmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
+
 	return 0;
 }
 
-static int ixgbe_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int ixgbe_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 advertised, old;
 	s32 err = 0;
+	u32 supported, advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	if ((hw->phy.media_type == ixgbe_media_type_copper) ||
 	    (hw->phy.multispeed_fiber)) {
@@ -388,12 +402,12 @@ static int ixgbe_set_settings(struct net_device *netdev,
 		 * this function does not support duplex forcing, but can
 		 * limit the advertising of the adapter to the specified speed
 		 */
-		if (ecmd->advertising & ~ecmd->supported)
+		if (advertising & ~supported)
 			return -EINVAL;
 
 		/* only allow one speed at a time if no autoneg */
-		if (!ecmd->autoneg && hw->phy.multispeed_fiber) {
-			if (ecmd->advertising ==
+		if (!cmd->base.autoneg && hw->phy.multispeed_fiber) {
+			if (advertising ==
 			    (ADVERTISED_10000baseT_Full |
 			     ADVERTISED_1000baseT_Full))
 				return -EINVAL;
@@ -401,16 +415,16 @@ static int ixgbe_set_settings(struct net_device *netdev,
 
 		old = hw->phy.autoneg_advertised;
 		advertised = 0;
-		if (ecmd->advertising & ADVERTISED_10000baseT_Full)
+		if (advertising & ADVERTISED_10000baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_10GB_FULL;
 
-		if (ecmd->advertising & ADVERTISED_1000baseT_Full)
+		if (advertising & ADVERTISED_1000baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_1GB_FULL;
 
-		if (ecmd->advertising & ADVERTISED_100baseT_Full)
+		if (advertising & ADVERTISED_100baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_100_FULL;
 
-		if (ecmd->advertising & ADVERTISED_10baseT_Full)
+		if (advertising & ADVERTISED_10baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_10_FULL;
 
 		if (old == advertised)
@@ -428,10 +442,11 @@ static int ixgbe_set_settings(struct net_device *netdev,
 		clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
 	} else {
 		/* in this case we currently only support 10Gb/FULL */
-		u32 speed = ethtool_cmd_speed(ecmd);
-		if ((ecmd->autoneg == AUTONEG_ENABLE) ||
-		    (ecmd->advertising != ADVERTISED_10000baseT_Full) ||
-		    (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL))
+		u32 speed = cmd->base.speed;
+
+		if ((cmd->base.autoneg == AUTONEG_ENABLE) ||
+		    (advertising != ADVERTISED_10000baseT_Full) ||
+		    (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL))
 			return -EINVAL;
 	}
 
@@ -1056,15 +1071,19 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 	if (!netif_running(adapter->netdev)) {
 		for (i = 0; i < adapter->num_tx_queues; i++)
 			adapter->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < adapter->num_xdp_queues; i++)
+			adapter->xdp_ring[i]->count = new_tx_count;
 		for (i = 0; i < adapter->num_rx_queues; i++)
 			adapter->rx_ring[i]->count = new_rx_count;
 		adapter->tx_ring_count = new_tx_count;
+		adapter->xdp_ring_count = new_tx_count;
 		adapter->rx_ring_count = new_rx_count;
 		goto clear_reset;
 	}
 
 	/* allocate temporary buffer to store rings in */
 	i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues);
+	i = max_t(int, i, adapter->num_xdp_queues);
 	temp_ring = vmalloc(i * sizeof(struct ixgbe_ring));
 
 	if (!temp_ring) {
@@ -1096,12 +1115,33 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 			}
 		}
 
+		for (i = 0; i < adapter->num_xdp_queues; i++) {
+			memcpy(&temp_ring[i], adapter->xdp_ring[i],
+			       sizeof(struct ixgbe_ring));
+
+			temp_ring[i].count = new_tx_count;
+			err = ixgbe_setup_tx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					ixgbe_free_tx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
 		for (i = 0; i < adapter->num_tx_queues; i++) {
 			ixgbe_free_tx_resources(adapter->tx_ring[i]);
 
 			memcpy(adapter->tx_ring[i], &temp_ring[i],
 			       sizeof(struct ixgbe_ring));
 		}
+		for (i = 0; i < adapter->num_xdp_queues; i++) {
+			ixgbe_free_tx_resources(adapter->xdp_ring[i]);
+
+			memcpy(adapter->xdp_ring[i], &temp_ring[i],
+			       sizeof(struct ixgbe_ring));
+		}
 
 		adapter->tx_ring_count = new_tx_count;
 	}
@@ -1113,7 +1153,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 			       sizeof(struct ixgbe_ring));
 
 			temp_ring[i].count = new_rx_count;
-			err = ixgbe_setup_rx_resources(&temp_ring[i]);
+			err = ixgbe_setup_rx_resources(adapter, &temp_ring[i]);
 			if (err) {
 				while (i) {
 					i--;
@@ -1746,7 +1786,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
 	rx_ring->netdev = adapter->netdev;
 	rx_ring->reg_idx = adapter->rx_ring[0]->reg_idx;
 
-	err = ixgbe_setup_rx_resources(rx_ring);
+	err = ixgbe_setup_rx_resources(adapter, rx_ring);
 	if (err) {
 		ret_val = 4;
 		goto err_nomem;
@@ -2927,9 +2967,7 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter)
 
 static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-
-	return sizeof(adapter->rss_key);
+	return IXGBE_RSS_KEY_SIZE;
 }
 
 static u32 ixgbe_rss_indir_size(struct net_device *netdev)
@@ -3402,8 +3440,6 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 }
 
 static const struct ethtool_ops ixgbe_ethtool_ops = {
-	.get_settings           = ixgbe_get_settings,
-	.set_settings           = ixgbe_set_settings,
 	.get_drvinfo            = ixgbe_get_drvinfo,
 	.get_regs_len           = ixgbe_get_regs_len,
 	.get_regs               = ixgbe_get_regs,
@@ -3442,6 +3478,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.get_ts_info		= ixgbe_get_ts_info,
 	.get_module_info	= ixgbe_get_module_info,
 	.get_module_eeprom	= ixgbe_get_module_eeprom,
+	.get_link_ksettings     = ixgbe_get_link_ksettings,
+	.set_link_ksettings     = ixgbe_set_link_ksettings,
 };
 
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 1b8be7d813bd..b45fdc98033d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -267,12 +267,14 @@ static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter)
  **/
 static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter)
 {
-	int i;
+	int i, reg_idx;
 
 	for (i = 0; i < adapter->num_rx_queues; i++)
 		adapter->rx_ring[i]->reg_idx = i;
-	for (i = 0; i < adapter->num_tx_queues; i++)
-		adapter->tx_ring[i]->reg_idx = i;
+	for (i = 0, reg_idx = 0; i < adapter->num_tx_queues; i++, reg_idx++)
+		adapter->tx_ring[i]->reg_idx = reg_idx;
+	for (i = 0; i < adapter->num_xdp_queues; i++, reg_idx++)
+		adapter->xdp_ring[i]->reg_idx = reg_idx;
 
 	return true;
 }
@@ -308,6 +310,11 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter)
 	ixgbe_cache_ring_rss(adapter);
 }
 
+static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter)
+{
+	return adapter->xdp_prog ? nr_cpu_ids : 0;
+}
+
 #define IXGBE_RSS_64Q_MASK	0x3F
 #define IXGBE_RSS_16Q_MASK	0xF
 #define IXGBE_RSS_8Q_MASK	0x7
@@ -382,6 +389,7 @@ static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter)
 	adapter->num_rx_queues_per_pool = tcs;
 
 	adapter->num_tx_queues = vmdq_i * tcs;
+	adapter->num_xdp_queues = 0;
 	adapter->num_rx_queues = vmdq_i * tcs;
 
 #ifdef IXGBE_FCOE
@@ -479,6 +487,7 @@ static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter)
 		netdev_set_tc_queue(dev, i, rss_i, rss_i * i);
 
 	adapter->num_tx_queues = rss_i * tcs;
+	adapter->num_xdp_queues = 0;
 	adapter->num_rx_queues = rss_i * tcs;
 
 	return true;
@@ -549,6 +558,7 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
 
 	adapter->num_rx_queues = vmdq_i * rss_i;
 	adapter->num_tx_queues = vmdq_i * rss_i;
+	adapter->num_xdp_queues = 0;
 
 	/* disable ATR as it is not supported when VMDq is enabled */
 	adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
@@ -669,6 +679,7 @@ static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter)
 #endif /* IXGBE_FCOE */
 	adapter->num_rx_queues = rss_i;
 	adapter->num_tx_queues = rss_i;
+	adapter->num_xdp_queues = ixgbe_xdp_queues(adapter);
 
 	return true;
 }
@@ -689,6 +700,7 @@ static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter)
 	/* Start with base case */
 	adapter->num_rx_queues = 1;
 	adapter->num_tx_queues = 1;
+	adapter->num_xdp_queues = 0;
 	adapter->num_rx_pools = adapter->num_rx_queues;
 	adapter->num_rx_queues_per_pool = 1;
 
@@ -719,8 +731,11 @@ static int ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter)
 	struct ixgbe_hw *hw = &adapter->hw;
 	int i, vectors, vector_threshold;
 
-	/* We start by asking for one vector per queue pair */
+	/* We start by asking for one vector per queue pair with XDP queues
+	 * being stacked with TX queues.
+	 */
 	vectors = max(adapter->num_rx_queues, adapter->num_tx_queues);
+	vectors = max(vectors, adapter->num_xdp_queues);
 
 	/* It is easy to be greedy for MSI-X vectors. However, it really
 	 * doesn't do much good if we have a lot more vectors than CPUs. We'll
@@ -800,6 +815,8 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring,
  * @v_idx: index of vector in adapter struct
  * @txr_count: total number of Tx rings to allocate
  * @txr_idx: index of first Tx ring to allocate
+ * @xdp_count: total number of XDP rings to allocate
+ * @xdp_idx: index of first XDP ring to allocate
  * @rxr_count: total number of Rx rings to allocate
  * @rxr_idx: index of first Rx ring to allocate
  *
@@ -808,6 +825,7 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring,
 static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 				int v_count, int v_idx,
 				int txr_count, int txr_idx,
+				int xdp_count, int xdp_idx,
 				int rxr_count, int rxr_idx)
 {
 	struct ixgbe_q_vector *q_vector;
@@ -817,7 +835,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	int ring_count, size;
 	u8 tcs = netdev_get_num_tc(adapter->netdev);
 
-	ring_count = txr_count + rxr_count;
+	ring_count = txr_count + rxr_count + xdp_count;
 	size = sizeof(struct ixgbe_q_vector) +
 	       (sizeof(struct ixgbe_ring) * ring_count);
 
@@ -909,6 +927,33 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		ring++;
 	}
 
+	while (xdp_count) {
+		/* assign generic ring traits */
+		ring->dev = &adapter->pdev->dev;
+		ring->netdev = adapter->netdev;
+
+		/* configure backlink on ring */
+		ring->q_vector = q_vector;
+
+		/* update q_vector Tx values */
+		ixgbe_add_ring(ring, &q_vector->tx);
+
+		/* apply Tx specific ring traits */
+		ring->count = adapter->tx_ring_count;
+		ring->queue_index = xdp_idx;
+		set_ring_xdp(ring);
+
+		/* assign ring to adapter */
+		adapter->xdp_ring[xdp_idx] = ring;
+
+		/* update count and index */
+		xdp_count--;
+		xdp_idx++;
+
+		/* push pointer to next ring */
+		ring++;
+	}
+
 	while (rxr_count) {
 		/* assign generic ring traits */
 		ring->dev = &adapter->pdev->dev;
@@ -1002,17 +1047,18 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
 	int q_vectors = adapter->num_q_vectors;
 	int rxr_remaining = adapter->num_rx_queues;
 	int txr_remaining = adapter->num_tx_queues;
-	int rxr_idx = 0, txr_idx = 0, v_idx = 0;
+	int xdp_remaining = adapter->num_xdp_queues;
+	int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0;
 	int err;
 
 	/* only one q_vector if MSI-X is disabled. */
 	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
 		q_vectors = 1;
 
-	if (q_vectors >= (rxr_remaining + txr_remaining)) {
+	if (q_vectors >= (rxr_remaining + txr_remaining + xdp_remaining)) {
 		for (; rxr_remaining; v_idx++) {
 			err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx,
-						   0, 0, 1, rxr_idx);
+						   0, 0, 0, 0, 1, rxr_idx);
 
 			if (err)
 				goto err_out;
@@ -1026,8 +1072,11 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
 	for (; v_idx < q_vectors; v_idx++) {
 		int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
 		int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
+		int xqpv = DIV_ROUND_UP(xdp_remaining, q_vectors - v_idx);
+
 		err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx,
 					   tqpv, txr_idx,
+					   xqpv, xdp_idx,
 					   rqpv, rxr_idx);
 
 		if (err)
@@ -1036,14 +1085,17 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
 		/* update counts and index */
 		rxr_remaining -= rqpv;
 		txr_remaining -= tqpv;
+		xdp_remaining -= xqpv;
 		rxr_idx++;
 		txr_idx++;
+		xdp_idx += xqpv;
 	}
 
 	return 0;
 
 err_out:
 	adapter->num_tx_queues = 0;
+	adapter->num_xdp_queues = 0;
 	adapter->num_rx_queues = 0;
 	adapter->num_q_vectors = 0;
 
@@ -1066,6 +1118,7 @@ static void ixgbe_free_q_vectors(struct ixgbe_adapter *adapter)
 	int v_idx = adapter->num_q_vectors;
 
 	adapter->num_tx_queues = 0;
+	adapter->num_xdp_queues = 0;
 	adapter->num_rx_queues = 0;
 	adapter->num_q_vectors = 0;
 
@@ -1172,9 +1225,10 @@ int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter)
 
 	ixgbe_cache_ring_register(adapter);
 
-	e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\n",
+	e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u XDP Queue count = %u\n",
 		   (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled",
-		   adapter->num_rx_queues, adapter->num_tx_queues);
+		   adapter->num_rx_queues, adapter->num_tx_queues,
+		   adapter->num_xdp_queues);
 
 	set_bit(__IXGBE_DOWN, &adapter->state);
 
@@ -1195,6 +1249,7 @@ err_alloc_q_vectors:
 void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter)
 {
 	adapter->num_tx_queues = 0;
+	adapter->num_xdp_queues = 0;
 	adapter->num_rx_queues = 0;
 
 	ixgbe_free_q_vectors(adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a7a430a7be2c..22a29df1d29e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -49,6 +49,9 @@
 #include <linux/if_macvlan.h>
 #include <linux/if_bridge.h>
 #include <linux/prefetch.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/atomic.h>
 #include <scsi/fc/fc_fcoe.h>
 #include <net/udp_tunnel.h>
 #include <net/pkt_cls.h>
@@ -85,6 +88,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = {
 	[board_X540]		= &ixgbe_X540_info,
 	[board_X550]		= &ixgbe_X550_info,
 	[board_X550EM_x]	= &ixgbe_X550EM_x_info,
+	[board_x550em_x_fw]	= &ixgbe_x550em_x_fw_info,
 	[board_x550em_a]	= &ixgbe_x550em_a_info,
 	[board_x550em_a_fw]	= &ixgbe_x550em_a_fw_info,
 };
@@ -131,9 +135,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_1G_T), board_x550em_x_fw},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR), board_x550em_a },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR_L), board_x550em_a },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP_N), board_x550em_a },
@@ -508,7 +514,7 @@ static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {
  */
 static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
 {
-	int i = 0, j = 0;
+	int i;
 	char rname[16];
 	u32 regs[64];
 
@@ -570,21 +576,38 @@ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
 			regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i));
 		break;
 	default:
-		pr_info("%-15s %08x\n", reginfo->name,
-			IXGBE_READ_REG(hw, reginfo->ofs));
+		pr_info("%-15s %08x\n",
+			reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs));
 		return;
 	}
 
-	for (i = 0; i < 8; i++) {
-		snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7);
-		pr_err("%-15s", rname);
+	i = 0;
+	while (i < 64) {
+		int j;
+		char buf[9 * 8 + 1];
+		char *p = buf;
+
+		snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7);
 		for (j = 0; j < 8; j++)
-			pr_cont(" %08x", regs[i*8+j]);
-		pr_cont("\n");
+			p += sprintf(p, " %08x", regs[i++]);
+		pr_err("%-15s%s\n", rname, buf);
 	}
 
 }
 
+static void ixgbe_print_buffer(struct ixgbe_ring *ring, int n)
+{
+	struct ixgbe_tx_buffer *tx_buffer;
+
+	tx_buffer = &ring->tx_buffer_info[ring->next_to_clean];
+	pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n",
+		n, ring->next_to_use, ring->next_to_clean,
+		(u64)dma_unmap_addr(tx_buffer, dma),
+		dma_unmap_len(tx_buffer, len),
+		tx_buffer->next_to_watch,
+		(u64)tx_buffer->time_stamp);
+}
+
 /*
  * ixgbe_dump - Print registers, tx-rings and rx-rings
  */
@@ -594,14 +617,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_reg_info *reginfo;
 	int n = 0;
-	struct ixgbe_ring *tx_ring;
+	struct ixgbe_ring *ring;
 	struct ixgbe_tx_buffer *tx_buffer;
 	union ixgbe_adv_tx_desc *tx_desc;
 	struct my_u0 { u64 a; u64 b; } *u0;
 	struct ixgbe_ring *rx_ring;
 	union ixgbe_adv_rx_desc *rx_desc;
 	struct ixgbe_rx_buffer *rx_buffer_info;
-	u32 staterr;
 	int i = 0;
 
 	if (!netif_msg_hw(adapter))
@@ -635,14 +657,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 		"Queue [NTU] [NTC] [bi(ntc)->dma  ]",
 		"leng", "ntw", "timestamp");
 	for (n = 0; n < adapter->num_tx_queues; n++) {
-		tx_ring = adapter->tx_ring[n];
-		tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
-		pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n",
-			   n, tx_ring->next_to_use, tx_ring->next_to_clean,
-			   (u64)dma_unmap_addr(tx_buffer, dma),
-			   dma_unmap_len(tx_buffer, len),
-			   tx_buffer->next_to_watch,
-			   (u64)tx_buffer->time_stamp);
+		ring = adapter->tx_ring[n];
+		ixgbe_print_buffer(ring, n);
+	}
+
+	for (n = 0; n < adapter->num_xdp_queues; n++) {
+		ring = adapter->xdp_ring[n];
+		ixgbe_print_buffer(ring, n);
 	}
 
 	/* Print TX Rings */
@@ -687,21 +708,32 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 	 */
 
 	for (n = 0; n < adapter->num_tx_queues; n++) {
-		tx_ring = adapter->tx_ring[n];
+		ring = adapter->tx_ring[n];
 		pr_info("------------------------------------\n");
-		pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
+		pr_info("TX QUEUE INDEX = %d\n", ring->queue_index);
 		pr_info("------------------------------------\n");
 		pr_info("%s%s    %s              %s        %s          %s\n",
 			"T [desc]     [address 63:0  ] ",
 			"[PlPOIdStDDt Ln] [bi->dma       ] ",
 			"leng", "ntw", "timestamp", "bi->skb");
 
-		for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
-			tx_desc = IXGBE_TX_DESC(tx_ring, i);
-			tx_buffer = &tx_ring->tx_buffer_info[i];
+		for (i = 0; ring->desc && (i < ring->count); i++) {
+			tx_desc = IXGBE_TX_DESC(ring, i);
+			tx_buffer = &ring->tx_buffer_info[i];
 			u0 = (struct my_u0 *)tx_desc;
 			if (dma_unmap_len(tx_buffer, len) > 0) {
-				pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p",
+				const char *ring_desc;
+
+				if (i == ring->next_to_use &&
+				    i == ring->next_to_clean)
+					ring_desc = " NTC/U";
+				else if (i == ring->next_to_use)
+					ring_desc = " NTU";
+				else if (i == ring->next_to_clean)
+					ring_desc = " NTC";
+				else
+					ring_desc = "";
+				pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p%s",
 					i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
@@ -709,16 +741,8 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 					dma_unmap_len(tx_buffer, len),
 					tx_buffer->next_to_watch,
 					(u64)tx_buffer->time_stamp,
-					tx_buffer->skb);
-				if (i == tx_ring->next_to_use &&
-					i == tx_ring->next_to_clean)
-					pr_cont(" NTC/U\n");
-				else if (i == tx_ring->next_to_use)
-					pr_cont(" NTU\n");
-				else if (i == tx_ring->next_to_clean)
-					pr_cont(" NTC\n");
-				else
-					pr_cont("\n");
+					tx_buffer->skb,
+					ring_desc);
 
 				if (netif_msg_pktdata(adapter) &&
 				    tx_buffer->skb)
@@ -797,34 +821,44 @@ rx_ring_summary:
 		pr_info("------------------------------------\n");
 		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
 		pr_info("------------------------------------\n");
-		pr_info("%s%s%s",
+		pr_info("%s%s%s\n",
 			"R  [desc]      [ PktBuf     A0] ",
 			"[  HeadBuf   DD] [bi->dma       ] [bi->skb       ] ",
-			"<-- Adv Rx Read format\n");
-		pr_info("%s%s%s",
+			"<-- Adv Rx Read format");
+		pr_info("%s%s%s\n",
 			"RWB[desc]      [PcsmIpSHl PtRs] ",
 			"[vl er S cks ln] ---------------- [bi->skb       ] ",
-			"<-- Adv Rx Write-Back format\n");
+			"<-- Adv Rx Write-Back format");
 
 		for (i = 0; i < rx_ring->count; i++) {
+			const char *ring_desc;
+
+			if (i == rx_ring->next_to_use)
+				ring_desc = " NTU";
+			else if (i == rx_ring->next_to_clean)
+				ring_desc = " NTC";
+			else
+				ring_desc = "";
+
 			rx_buffer_info = &rx_ring->rx_buffer_info[i];
 			rx_desc = IXGBE_RX_DESC(rx_ring, i);
 			u0 = (struct my_u0 *)rx_desc;
-			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
-			if (staterr & IXGBE_RXD_STAT_DD) {
+			if (rx_desc->wb.upper.length) {
 				/* Descriptor Done */
-				pr_info("RWB[0x%03X]     %016llX "
-					"%016llX ---------------- %p", i,
+				pr_info("RWB[0x%03X]     %016llX %016llX ---------------- %p%s\n",
+					i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
-					rx_buffer_info->skb);
+					rx_buffer_info->skb,
+					ring_desc);
 			} else {
-				pr_info("R  [0x%03X]     %016llX "
-					"%016llX %016llX %p", i,
+				pr_info("R  [0x%03X]     %016llX %016llX %016llX %p%s\n",
+					i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
 					(u64)rx_buffer_info->dma,
-					rx_buffer_info->skb);
+					rx_buffer_info->skb,
+					ring_desc);
 
 				if (netif_msg_pktdata(adapter) &&
 				    rx_buffer_info->dma) {
@@ -835,14 +869,6 @@ rx_ring_summary:
 					   ixgbe_rx_bufsz(rx_ring), true);
 				}
 			}
-
-			if (i == rx_ring->next_to_use)
-				pr_cont(" NTU\n");
-			else if (i == rx_ring->next_to_clean)
-				pr_cont(" NTC\n");
-			else
-				pr_cont("\n");
-
 		}
 	}
 }
@@ -972,6 +998,10 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		clear_bit(__IXGBE_HANG_CHECK_ARMED,
 			  &adapter->tx_ring[i]->state);
+
+	for (i = 0; i < adapter->num_xdp_queues; i++)
+		clear_bit(__IXGBE_HANG_CHECK_ARMED,
+			  &adapter->xdp_ring[i]->state);
 }
 
 static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
@@ -1016,6 +1046,14 @@ static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
 		if (xoff[tc])
 			clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
 	}
+
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
+
+		tc = xdp_ring->dcb_tc;
+		if (xoff[tc])
+			clear_bit(__IXGBE_HANG_CHECK_ARMED, &xdp_ring->state);
+	}
 }
 
 static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
@@ -1167,7 +1205,10 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		total_packets += tx_buffer->gso_segs;
 
 		/* free the skb */
-		napi_consume_skb(tx_buffer->skb, napi_budget);
+		if (ring_is_xdp(tx_ring))
+			page_frag_free(tx_buffer->data);
+		else
+			napi_consume_skb(tx_buffer->skb, napi_budget);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -1228,7 +1269,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 	if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
 		/* schedule immediate reset if we believe we hung */
 		struct ixgbe_hw *hw = &adapter->hw;
-		e_err(drv, "Detected Tx Unit Hang\n"
+		e_err(drv, "Detected Tx Unit Hang %s\n"
 			"  Tx Queue             <%d>\n"
 			"  TDH, TDT             <%x>, <%x>\n"
 			"  next_to_use          <%x>\n"
@@ -1236,13 +1277,16 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 			"tx_buffer_info[next_to_clean]\n"
 			"  time_stamp           <%lx>\n"
 			"  jiffies              <%lx>\n",
+			ring_is_xdp(tx_ring) ? "(XDP)" : "",
 			tx_ring->queue_index,
 			IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
 			IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
 			tx_ring->next_to_use, i,
 			tx_ring->tx_buffer_info[i].time_stamp, jiffies);
 
-		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+		if (!ring_is_xdp(tx_ring))
+			netif_stop_subqueue(tx_ring->netdev,
+					    tx_ring->queue_index);
 
 		e_info(probe,
 		       "tx hang %d detected on queue %d, resetting adapter\n",
@@ -1255,6 +1299,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		return true;
 	}
 
+	if (ring_is_xdp(tx_ring))
+		return !!budget;
+
 	netdev_tx_completed_queue(txring_txq(tx_ring),
 				  total_packets, total_bytes);
 
@@ -1846,6 +1893,10 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being fixed
  *
+ * Check if the skb is valid in the XDP case it will be an error pointer.
+ * Return true in this case to abort processing and advance to next
+ * descriptor.
+ *
  * Check for corrupted packet headers caused by senders on the local L2
  * embedded NIC switch not setting up their Tx Descriptors right.  These
  * should be very rare.
@@ -1864,6 +1915,10 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 {
 	struct net_device *netdev = rx_ring->netdev;
 
+	/* XDP packets use error pointer so abort at this point */
+	if (IS_ERR(skb))
+		return true;
+
 	/* verify that the packet does not have any known errors */
 	if (unlikely(ixgbe_test_staterr(rx_desc,
 					IXGBE_RXDADV_ERR_FRAME_ERR_MASK) &&
@@ -2039,7 +2094,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
-		if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
+		if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) {
 			/* the page has been released from the ring */
 			IXGBE_CB(skb)->page_released = true;
 		} else {
@@ -2060,21 +2115,22 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
 
 static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 					   struct ixgbe_rx_buffer *rx_buffer,
-					   union ixgbe_adv_rx_desc *rx_desc,
-					   unsigned int size)
+					   struct xdp_buff *xdp,
+					   union ixgbe_adv_rx_desc *rx_desc)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+	unsigned int size = xdp->data_end - xdp->data;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = SKB_DATA_ALIGN(size);
+	unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end -
+					       xdp->data_hard_start);
 #endif
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
+	prefetch(xdp->data);
 #if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
+	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
 
 	/* allocate a skb to store the frags */
@@ -2087,7 +2143,7 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 			IXGBE_CB(skb)->dma = rx_buffer->dma;
 
 		skb_add_rx_frag(skb, 0, rx_buffer->page,
-				rx_buffer->page_offset,
+				xdp->data - page_address(rx_buffer->page),
 				size, truesize);
 #if (PAGE_SIZE < 8192)
 		rx_buffer->page_offset ^= truesize;
@@ -2095,7 +2151,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 		rx_buffer->page_offset += truesize;
 #endif
 	} else {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+		memcpy(__skb_put(skb, size),
+		       xdp->data, ALIGN(size, sizeof(long)));
 		rx_buffer->pagecnt_bias++;
 	}
 
@@ -2104,32 +2161,32 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 
 static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 				       struct ixgbe_rx_buffer *rx_buffer,
-				       union ixgbe_adv_rx_desc *rx_desc,
-				       unsigned int size)
+				       struct xdp_buff *xdp,
+				       union ixgbe_adv_rx_desc *rx_desc)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size);
+				SKB_DATA_ALIGN(xdp->data_end -
+					       xdp->data_hard_start);
 #endif
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
+	prefetch(xdp->data);
 #if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
+	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
 
 	/* build an skb to around the page buffer */
-	skb = build_skb(va - IXGBE_SKB_PAD, truesize);
+	skb = build_skb(xdp->data_hard_start, truesize);
 	if (unlikely(!skb))
 		return NULL;
 
 	/* update pointers within the skb to store the data */
-	skb_reserve(skb, IXGBE_SKB_PAD);
-	__skb_put(skb, size);
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	__skb_put(skb, xdp->data_end - xdp->data);
 
 	/* record DMA address if this is the start of a chain of buffers */
 	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
@@ -2145,6 +2202,65 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
+#define IXGBE_XDP_PASS 0
+#define IXGBE_XDP_CONSUMED 1
+#define IXGBE_XDP_TX 2
+
+static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
+			       struct xdp_buff *xdp);
+
+static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
+				     struct ixgbe_ring *rx_ring,
+				     struct xdp_buff *xdp)
+{
+	int result = IXGBE_XDP_PASS;
+	struct bpf_prog *xdp_prog;
+	u32 act;
+
+	rcu_read_lock();
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
+	if (!xdp_prog)
+		goto xdp_out;
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		result = ixgbe_xmit_xdp_ring(adapter, xdp);
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	case XDP_ABORTED:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+		/* fallthrough -- handle aborts by dropping packet */
+	case XDP_DROP:
+		result = IXGBE_XDP_CONSUMED;
+		break;
+	}
+xdp_out:
+	rcu_read_unlock();
+	return ERR_PTR(-result);
+}
+
+static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
+				 struct ixgbe_rx_buffer *rx_buffer,
+				 unsigned int size)
+{
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
+
+	rx_buffer->page_offset ^= truesize;
+#else
+	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) :
+				SKB_DATA_ALIGN(size);
+
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
 /**
  * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @q_vector: structure containing interrupt and ring information
@@ -2163,17 +2279,19 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			       const int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-#ifdef IXGBE_FCOE
 	struct ixgbe_adapter *adapter = q_vector->adapter;
+#ifdef IXGBE_FCOE
 	int ddp_bytes;
 	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
+	bool xdp_xmit = false;
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
 		struct ixgbe_rx_buffer *rx_buffer;
 		struct sk_buff *skb;
+		struct xdp_buff xdp;
 		unsigned int size;
 
 		/* return some buffers to hardware, one at a time is too slow */
@@ -2196,14 +2314,34 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size);
 
 		/* retrieve a buffer from the ring */
-		if (skb)
+		if (!skb) {
+			xdp.data = page_address(rx_buffer->page) +
+				   rx_buffer->page_offset;
+			xdp.data_hard_start = xdp.data -
+					      ixgbe_rx_offset(rx_ring);
+			xdp.data_end = xdp.data + size;
+
+			skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
+		}
+
+		if (IS_ERR(skb)) {
+			if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
+				xdp_xmit = true;
+				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
+			} else {
+				rx_buffer->pagecnt_bias++;
+			}
+			total_rx_packets++;
+			total_rx_bytes += size;
+		} else if (skb) {
 			ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size);
-		else if (ring_uses_build_skb(rx_ring))
+		} else if (ring_uses_build_skb(rx_ring)) {
 			skb = ixgbe_build_skb(rx_ring, rx_buffer,
-					      rx_desc, size);
-		else
+					      &xdp, rx_desc);
+		} else {
 			skb = ixgbe_construct_skb(rx_ring, rx_buffer,
-						  rx_desc, size);
+						  &xdp, rx_desc);
+		}
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -2260,6 +2398,16 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		total_rx_packets++;
 	}
 
+	if (xdp_xmit) {
+		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.
+		 */
+		wmb();
+		writel(ring->next_to_use, ring->tail);
+	}
+
 	u64_stats_update_begin(&rx_ring->syncp);
 	rx_ring->stats.packets += total_rx_packets;
 	rx_ring->stats.bytes += total_rx_bytes;
@@ -3364,6 +3512,8 @@ static void ixgbe_configure_tx(struct ixgbe_adapter *adapter)
 	/* Setup the HW Tx Head and Tail descriptor pointers */
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]);
+	for (i = 0; i < adapter->num_xdp_queues; i++)
+		ixgbe_configure_tx_ring(adapter, adapter->xdp_ring[i]);
 }
 
 static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter,
@@ -3489,6 +3639,28 @@ void ixgbe_store_key(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_init_rss_key - Initialize adapter RSS key
+ * @adapter: device handle
+ *
+ * Allocates and initializes the RSS key if it is not allocated.
+ **/
+static inline int ixgbe_init_rss_key(struct ixgbe_adapter *adapter)
+{
+	u32 *rss_key;
+
+	if (!adapter->rss_key) {
+		rss_key = kzalloc(IXGBE_RSS_KEY_SIZE, GFP_KERNEL);
+		if (unlikely(!rss_key))
+			return -ENOMEM;
+
+		netdev_rss_key_fill(rss_key, IXGBE_RSS_KEY_SIZE);
+		adapter->rss_key = rss_key;
+	}
+
+	return 0;
+}
+
+/**
  * ixgbe_store_reta - Write the RETA table to HW
  * @adapter: device handle
  *
@@ -3590,7 +3762,7 @@ static void ixgbe_setup_vfreta(struct ixgbe_adapter *adapter)
 	/* Fill out hash function seeds */
 	for (i = 0; i < 10; i++)
 		IXGBE_WRITE_REG(hw, IXGBE_PFVFRSSRK(i, pf_pool),
-				adapter->rss_key[i]);
+				*(adapter->rss_key + i));
 
 	/* Fill out the redirection table */
 	for (i = 0, j = 0; i < 64; i++, j++) {
@@ -3651,7 +3823,6 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
 	if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP)
 		rss_field |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP;
 
-	netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key));
 	if ((hw->mac.type >= ixgbe_mac_X550) &&
 	    (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) {
 		unsigned int pf_pool = adapter->num_vfs;
@@ -3802,7 +3973,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 		/* Limit the maximum frame size so we don't overrun the skb */
 		if (ring_uses_build_skb(ring) &&
 		    !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state))
-			rxdctl |= IXGBE_MAX_FRAME_BUILD_SKB |
+			rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB |
 				  IXGBE_RXDCTL_RLPML_EN;
 #endif
 	}
@@ -3972,8 +4143,8 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 
-		if ((max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)) ||
-		    (max_frame > IXGBE_MAX_FRAME_BUILD_SKB))
+		if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
+		    (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 #endif
 	}
@@ -5505,7 +5676,10 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
 		union ixgbe_adv_tx_desc *eop_desc, *tx_desc;
 
 		/* Free all the Tx ring sk_buffs */
-		dev_kfree_skb_any(tx_buffer->skb);
+		if (ring_is_xdp(tx_ring))
+			page_frag_free(tx_buffer->data);
+		else
+			dev_kfree_skb_any(tx_buffer->skb);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -5546,7 +5720,8 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
 	}
 
 	/* reset BQL for queue */
-	netdev_tx_reset_queue(txring_txq(tx_ring));
+	if (!ring_is_xdp(tx_ring))
+		netdev_tx_reset_queue(txring_txq(tx_ring));
 
 	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
@@ -5575,6 +5750,8 @@ static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter)
 
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		ixgbe_clean_tx_ring(adapter->tx_ring[i]);
+	for (i = 0; i < adapter->num_xdp_queues; i++)
+		ixgbe_clean_tx_ring(adapter->xdp_ring[i]);
 }
 
 static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter)
@@ -5669,6 +5846,11 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 		u8 reg_idx = adapter->tx_ring[i]->reg_idx;
 		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
 	}
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		u8 reg_idx = adapter->xdp_ring[i]->reg_idx;
+
+		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+	}
 
 	/* Disable the Tx DMA engine on 82599 and later MAC */
 	switch (hw->mac.type) {
@@ -5854,6 +6036,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	if (!adapter->mac_table)
 		return -ENOMEM;
 
+	if (ixgbe_init_rss_key(adapter))
+		return -ENOMEM;
+
 	/* Set MAC specific capability flags and exceptions */
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
@@ -5944,10 +6129,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	/* assign number of SR-IOV VFs */
 	if (hw->mac.type != ixgbe_mac_82598EB) {
 		if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) {
-			adapter->num_vfs = 0;
+			max_vfs = 0;
 			e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n");
-		} else {
-			adapter->num_vfs = max_vfs;
 		}
 	}
 #endif /* CONFIG_PCI_IOV */
@@ -6041,7 +6224,7 @@ err:
  **/
 static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter)
 {
-	int i, err = 0;
+	int i, j = 0, err = 0;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		err = ixgbe_setup_tx_resources(adapter->tx_ring[i]);
@@ -6051,10 +6234,20 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter)
 		e_err(probe, "Allocation for Tx Queue %u failed\n", i);
 		goto err_setup_tx;
 	}
+	for (j = 0; j < adapter->num_xdp_queues; j++) {
+		err = ixgbe_setup_tx_resources(adapter->xdp_ring[j]);
+		if (!err)
+			continue;
+
+		e_err(probe, "Allocation for Tx Queue %u failed\n", j);
+		goto err_setup_tx;
+	}
 
 	return 0;
 err_setup_tx:
 	/* rewind the index freeing the rings as we go */
+	while (j--)
+		ixgbe_free_tx_resources(adapter->xdp_ring[j]);
 	while (i--)
 		ixgbe_free_tx_resources(adapter->tx_ring[i]);
 	return err;
@@ -6066,7 +6259,8 @@ err_setup_tx:
  *
  * Returns 0 on success, negative on failure
  **/
-int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
+int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
+			     struct ixgbe_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
 	int orig_node = dev_to_node(dev);
@@ -6105,6 +6299,8 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 
+	rx_ring->xdp_prog = adapter->xdp_prog;
+
 	return 0;
 err:
 	vfree(rx_ring->rx_buffer_info);
@@ -6128,7 +6324,7 @@ static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter)
 	int i, err = 0;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		err = ixgbe_setup_rx_resources(adapter->rx_ring[i]);
+		err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]);
 		if (!err)
 			continue;
 
@@ -6184,6 +6380,9 @@ static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		if (adapter->tx_ring[i]->desc)
 			ixgbe_free_tx_resources(adapter->tx_ring[i]);
+	for (i = 0; i < adapter->num_xdp_queues; i++)
+		if (adapter->xdp_ring[i]->desc)
+			ixgbe_free_tx_resources(adapter->xdp_ring[i]);
 }
 
 /**
@@ -6196,6 +6395,7 @@ void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring)
 {
 	ixgbe_clean_rx_ring(rx_ring);
 
+	rx_ring->xdp_prog = NULL;
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
 
@@ -6602,6 +6802,14 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 		bytes += tx_ring->stats.bytes;
 		packets += tx_ring->stats.packets;
 	}
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
+
+		restart_queue += xdp_ring->tx_stats.restart_queue;
+		tx_busy += xdp_ring->tx_stats.tx_busy;
+		bytes += xdp_ring->stats.bytes;
+		packets += xdp_ring->stats.packets;
+	}
 	adapter->restart_queue = restart_queue;
 	adapter->tx_busy = tx_busy;
 	netdev->stats.tx_bytes = bytes;
@@ -6795,6 +7003,9 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter)
 		for (i = 0; i < adapter->num_tx_queues; i++)
 			set_bit(__IXGBE_TX_FDIR_INIT_DONE,
 				&(adapter->tx_ring[i]->state));
+		for (i = 0; i < adapter->num_xdp_queues; i++)
+			set_bit(__IXGBE_TX_FDIR_INIT_DONE,
+				&adapter->xdp_ring[i]->state);
 		/* re-enable flow director interrupts */
 		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR);
 	} else {
@@ -6828,6 +7039,8 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter)
 	if (netif_carrier_ok(adapter->netdev)) {
 		for (i = 0; i < adapter->num_tx_queues; i++)
 			set_check_for_tx_hang(adapter->tx_ring[i]);
+		for (i = 0; i < adapter->num_xdp_queues; i++)
+			set_check_for_tx_hang(adapter->xdp_ring[i]);
 	}
 
 	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
@@ -7058,6 +7271,13 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter)
 			return true;
 	}
 
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		struct ixgbe_ring *ring = adapter->xdp_ring[i];
+
+		if (ring->next_to_use != ring->next_to_clean)
+			return true;
+	}
+
 	return false;
 }
 
@@ -8015,6 +8235,62 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 #endif
 }
 
+static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
+			       struct xdp_buff *xdp)
+{
+	struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
+	struct ixgbe_tx_buffer *tx_buffer;
+	union ixgbe_adv_tx_desc *tx_desc;
+	u32 len, cmd_type;
+	dma_addr_t dma;
+	u16 i;
+
+	len = xdp->data_end - xdp->data;
+
+	if (unlikely(!ixgbe_desc_unused(ring)))
+		return IXGBE_XDP_CONSUMED;
+
+	dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(ring->dev, dma))
+		return IXGBE_XDP_CONSUMED;
+
+	/* record the location of the first descriptor for this packet */
+	tx_buffer = &ring->tx_buffer_info[ring->next_to_use];
+	tx_buffer->bytecount = len;
+	tx_buffer->gso_segs = 1;
+	tx_buffer->protocol = 0;
+
+	i = ring->next_to_use;
+	tx_desc = IXGBE_TX_DESC(ring, i);
+
+	dma_unmap_len_set(tx_buffer, len, len);
+	dma_unmap_addr_set(tx_buffer, dma, dma);
+	tx_buffer->data = xdp->data;
+	tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+	/* put descriptor type bits */
+	cmd_type = IXGBE_ADVTXD_DTYP_DATA |
+		   IXGBE_ADVTXD_DCMD_DEXT |
+		   IXGBE_ADVTXD_DCMD_IFCS;
+	cmd_type |= len | IXGBE_TXD_CMD;
+	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+	tx_desc->read.olinfo_status =
+		cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT);
+
+	/* Avoid any potential race with xdp_xmit and cleanup */
+	smp_wmb();
+
+	/* set next_to_watch value indicating a packet is present */
+	i++;
+	if (i == ring->count)
+		i = 0;
+
+	tx_buffer->next_to_watch = tx_desc;
+	ring->next_to_use = i;
+
+	return IXGBE_XDP_TX;
+}
+
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 			  struct ixgbe_adapter *adapter,
 			  struct ixgbe_ring *tx_ring)
@@ -8306,6 +8582,23 @@ static void ixgbe_netpoll(struct net_device *netdev)
 
 #endif
 
+static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats,
+				   struct ixgbe_ring *ring)
+{
+	u64 bytes, packets;
+	unsigned int start;
+
+	if (ring) {
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
+			packets = ring->stats.packets;
+			bytes   = ring->stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
+		stats->tx_packets += packets;
+		stats->tx_bytes   += bytes;
+	}
+}
+
 static void ixgbe_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
@@ -8331,18 +8624,13 @@ static void ixgbe_get_stats64(struct net_device *netdev,
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct ixgbe_ring *ring = ACCESS_ONCE(adapter->tx_ring[i]);
-		u64 bytes, packets;
-		unsigned int start;
 
-		if (ring) {
-			do {
-				start = u64_stats_fetch_begin_irq(&ring->syncp);
-				packets = ring->stats.packets;
-				bytes   = ring->stats.bytes;
-			} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
-			stats->tx_packets += packets;
-			stats->tx_bytes   += bytes;
-		}
+		ixgbe_get_ring_stats64(stats, ring);
+	}
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		struct ixgbe_ring *ring = ACCESS_ONCE(adapter->xdp_ring[i]);
+
+		ixgbe_get_ring_stats64(stats, ring);
 	}
 	rcu_read_unlock();
 
@@ -8948,7 +9236,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return ixgbe_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return ixgbe_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 #ifdef CONFIG_PCI_IOV
@@ -9459,6 +9749,68 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
+static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
+{
+	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct bpf_prog *old_prog;
+
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+		return -EINVAL;
+
+	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
+		return -EINVAL;
+
+	/* verify ixgbe ring attributes are sufficient for XDP */
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct ixgbe_ring *ring = adapter->rx_ring[i];
+
+		if (ring_is_rsc_enabled(ring))
+			return -EINVAL;
+
+		if (frame_size > ixgbe_rx_bufsz(ring))
+			return -EINVAL;
+	}
+
+	if (nr_cpu_ids > MAX_XDP_QUEUES)
+		return -ENOMEM;
+
+	old_prog = xchg(&adapter->xdp_prog, prog);
+
+	/* If transitioning XDP modes reconfigure rings */
+	if (!!prog != !!old_prog) {
+		int err = ixgbe_setup_tc(dev, netdev_get_num_tc(dev));
+
+		if (err) {
+			rcu_assign_pointer(adapter->xdp_prog, old_prog);
+			return -EINVAL;
+		}
+	} else {
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog);
+	}
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	return 0;
+}
+
+static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return ixgbe_xdp_setup(dev, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = !!(adapter->xdp_prog);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
@@ -9504,6 +9856,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_udp_tunnel_add	= ixgbe_add_udp_tunnel_port,
 	.ndo_udp_tunnel_del	= ixgbe_del_udp_tunnel_port,
 	.ndo_features_check	= ixgbe_features_check,
+	.ndo_xdp		= ixgbe_xdp,
 };
 
 /**
@@ -9808,7 +10161,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ixgbe_init_mbx_params_pf(hw);
 	hw->mbx.ops = ii->mbx_ops;
 	pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT);
-	ixgbe_enable_sriov(adapter);
+	ixgbe_enable_sriov(adapter, max_vfs);
 skip_sriov:
 
 #endif
@@ -9934,6 +10287,9 @@ skip_sriov:
 	if (err)
 		goto err_sw_init;
 
+	for (i = 0; i < adapter->num_xdp_queues; i++)
+		u64_stats_init(&adapter->xdp_ring[i]->syncp);
+
 	/* WOL not supported for all devices */
 	adapter->wol = 0;
 	hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap);
@@ -10059,6 +10415,7 @@ err_sw_init:
 	iounmap(adapter->io_addr);
 	kfree(adapter->jump_tables[0]);
 	kfree(adapter->mac_table);
+	kfree(adapter->rss_key);
 err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
@@ -10143,6 +10500,7 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	}
 
 	kfree(adapter->mac_table);
+	kfree(adapter->rss_key);
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index e55b2602f371..654a402f0e9e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -792,7 +792,8 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
 		hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10_FULL;
 
 	/* Setup link based on the new speed settings */
-	hw->phy.ops.setup_link(hw);
+	if (hw->phy.ops.setup_link)
+		hw->phy.ops.setup_link(hw);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 044cb44747cf..8baf298a8516 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -46,88 +46,96 @@
 #include "ixgbe_sriov.h"
 
 #ifdef CONFIG_PCI_IOV
-static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
+static inline void ixgbe_alloc_vf_macvlans(struct ixgbe_adapter *adapter,
+					   unsigned int num_vfs)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
-	int num_vf_macvlans, i;
 	struct vf_macvlans *mv_list;
-
-	adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;
-	e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs);
-
-	/* Enable VMDq flag so device will be set in VM mode */
-	adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED;
-	if (!adapter->ring_feature[RING_F_VMDQ].limit)
-		adapter->ring_feature[RING_F_VMDQ].limit = 1;
-	adapter->ring_feature[RING_F_VMDQ].offset = adapter->num_vfs;
+	int num_vf_macvlans, i;
 
 	num_vf_macvlans = hw->mac.num_rar_entries -
-	(IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs);
+			  (IXGBE_MAX_PF_MACVLANS + 1 + num_vfs);
+	if (!num_vf_macvlans)
+		return;
 
-	adapter->mv_list = mv_list = kcalloc(num_vf_macvlans,
-					     sizeof(struct vf_macvlans),
-					     GFP_KERNEL);
+	mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans),
+			  GFP_KERNEL);
 	if (mv_list) {
 		/* Initialize list of VF macvlans */
 		INIT_LIST_HEAD(&adapter->vf_mvs.l);
 		for (i = 0; i < num_vf_macvlans; i++) {
-			mv_list->vf = -1;
-			mv_list->free = true;
-			list_add(&mv_list->l, &adapter->vf_mvs.l);
-			mv_list++;
+			mv_list[i].vf = -1;
+			mv_list[i].free = true;
+			list_add(&mv_list[i].l, &adapter->vf_mvs.l);
 		}
+		adapter->mv_list = mv_list;
 	}
+}
+
+static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
+				unsigned int num_vfs)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i;
+
+	adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;
+
+	/* Enable VMDq flag so device will be set in VM mode */
+	adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED;
+	if (!adapter->ring_feature[RING_F_VMDQ].limit)
+		adapter->ring_feature[RING_F_VMDQ].limit = 1;
+
+	/* Allocate memory for per VF control structures */
+	adapter->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage),
+				  GFP_KERNEL);
+	if (!adapter->vfinfo)
+		return -ENOMEM;
+
+	adapter->num_vfs = num_vfs;
+
+	ixgbe_alloc_vf_macvlans(adapter, num_vfs);
+	adapter->ring_feature[RING_F_VMDQ].offset = num_vfs;
 
 	/* Initialize default switching mode VEB */
 	IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
 	adapter->bridge_mode = BRIDGE_MODE_VEB;
 
-	/* If call to enable VFs succeeded then allocate memory
-	 * for per VF control structures.
-	 */
-	adapter->vfinfo =
-		kcalloc(adapter->num_vfs,
-			sizeof(struct vf_data_storage), GFP_KERNEL);
-	if (adapter->vfinfo) {
-		/* limit trafffic classes based on VFs enabled */
-		if ((adapter->hw.mac.type == ixgbe_mac_82599EB) &&
-		    (adapter->num_vfs < 16)) {
-			adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS;
-			adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS;
-		} else if (adapter->num_vfs < 32) {
-			adapter->dcb_cfg.num_tcs.pg_tcs = 4;
-			adapter->dcb_cfg.num_tcs.pfc_tcs = 4;
-		} else {
-			adapter->dcb_cfg.num_tcs.pg_tcs = 1;
-			adapter->dcb_cfg.num_tcs.pfc_tcs = 1;
-		}
-
-		/* Disable RSC when in SR-IOV mode */
-		adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE |
-				     IXGBE_FLAG2_RSC_ENABLED);
+	/* limit trafffic classes based on VFs enabled */
+	if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && (num_vfs < 16)) {
+		adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS;
+		adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS;
+	} else if (num_vfs < 32) {
+		adapter->dcb_cfg.num_tcs.pg_tcs = 4;
+		adapter->dcb_cfg.num_tcs.pfc_tcs = 4;
+	} else {
+		adapter->dcb_cfg.num_tcs.pg_tcs = 1;
+		adapter->dcb_cfg.num_tcs.pfc_tcs = 1;
+	}
 
-		for (i = 0; i < adapter->num_vfs; i++) {
-			/* enable spoof checking for all VFs */
-			adapter->vfinfo[i].spoofchk_enabled = true;
+	/* Disable RSC when in SR-IOV mode */
+	adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE |
+			     IXGBE_FLAG2_RSC_ENABLED);
 
-			/* We support VF RSS querying only for 82599 and x540
-			 * devices at the moment. These devices share RSS
-			 * indirection table and RSS hash key with PF therefore
-			 * we want to disable the querying by default.
-			 */
-			adapter->vfinfo[i].rss_query_enabled = 0;
+	for (i = 0; i < num_vfs; i++) {
+		/* enable spoof checking for all VFs */
+		adapter->vfinfo[i].spoofchk_enabled = true;
 
-			/* Untrust all VFs */
-			adapter->vfinfo[i].trusted = false;
+		/* We support VF RSS querying only for 82599 and x540
+		 * devices at the moment. These devices share RSS
+		 * indirection table and RSS hash key with PF therefore
+		 * we want to disable the querying by default.
+		 */
+		adapter->vfinfo[i].rss_query_enabled = 0;
 
-			/* set the default xcast mode */
-			adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE;
-		}
+		/* Untrust all VFs */
+		adapter->vfinfo[i].trusted = false;
 
-		return 0;
+		/* set the default xcast mode */
+		adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE;
 	}
 
-	return -ENOMEM;
+	e_info(probe, "SR-IOV enabled with %d VFs\n", num_vfs);
+	return 0;
 }
 
 /**
@@ -165,12 +173,13 @@ static void ixgbe_get_vfs(struct ixgbe_adapter *adapter)
 /* Note this function is called when the user wants to enable SR-IOV
  * VFs using the now deprecated module parameter
  */
-void ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
+void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs)
 {
 	int pre_existing_vfs = 0;
+	unsigned int num_vfs;
 
 	pre_existing_vfs = pci_num_vf(adapter->pdev);
-	if (!pre_existing_vfs && !adapter->num_vfs)
+	if (!pre_existing_vfs && !max_vfs)
 		return;
 
 	/* If there are pre-existing VFs then we have to force
@@ -180,7 +189,7 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
 	 * have been created via the new PCI SR-IOV sysfs interface.
 	 */
 	if (pre_existing_vfs) {
-		adapter->num_vfs = pre_existing_vfs;
+		num_vfs = pre_existing_vfs;
 		dev_warn(&adapter->pdev->dev,
 			 "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n");
 	} else {
@@ -192,17 +201,16 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
 		 * physical function.  If the user requests greater than
 		 * 63 VFs then it is an error - reset to default of zero.
 		 */
-		adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, IXGBE_MAX_VFS_DRV_LIMIT);
+		num_vfs = min_t(unsigned int, max_vfs, IXGBE_MAX_VFS_DRV_LIMIT);
 
-		err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
+		err = pci_enable_sriov(adapter->pdev, num_vfs);
 		if (err) {
 			e_err(probe, "Failed to enable PCI sriov: %d\n", err);
-			adapter->num_vfs = 0;
 			return;
 		}
 	}
 
-	if (!__ixgbe_enable_sriov(adapter)) {
+	if (!__ixgbe_enable_sriov(adapter, num_vfs)) {
 		ixgbe_get_vfs(adapter);
 		return;
 	}
@@ -298,6 +306,7 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs)
 #ifdef CONFIG_PCI_IOV
 	struct ixgbe_adapter *adapter = pci_get_drvdata(dev);
 	int err = 0;
+	u8 num_tc;
 	int i;
 	int pre_existing_vfs = pci_num_vf(dev);
 
@@ -310,23 +319,41 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs)
 		return err;
 
 	/* While the SR-IOV capability structure reports total VFs to be 64,
-	 * we have to limit the actual number allocated based on two factors.
+	 * we limit the actual number allocated as below based on two factors.
+	 *    Num_TCs	MAX_VFs
+	 *	1	  63
+	 *	<=4	  31
+	 *	>4	  15
 	 * First, we reserve some transmit/receive resources for the PF.
 	 * Second, VMDQ also uses the same pools that SR-IOV does. We need to
 	 * account for this, so that we don't accidentally allocate more VFs
 	 * than we have available pools. The PCI bus driver already checks for
 	 * other values out of range.
 	 */
-	if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VF_FUNCTIONS)
-		return -EPERM;
+	num_tc = netdev_get_num_tc(adapter->netdev);
 
-	adapter->num_vfs = num_vfs;
+	if (num_tc > 4) {
+		if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_8TC) {
+			e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_8TC);
+			return -EPERM;
+		}
+	} else if ((num_tc > 1) && (num_tc <= 4)) {
+		if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_4TC) {
+			e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_4TC);
+			return -EPERM;
+		}
+	} else {
+		if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_1TC) {
+			e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_1TC);
+			return -EPERM;
+		}
+	}
 
-	err = __ixgbe_enable_sriov(adapter);
+	err = __ixgbe_enable_sriov(adapter, num_vfs);
 	if (err)
 		return  err;
 
-	for (i = 0; i < adapter->num_vfs; i++)
+	for (i = 0; i < num_vfs; i++)
 		ixgbe_vf_configuration(dev, (i | 0x10000000));
 
 	/* reset before enabling SRIOV to avoid mailbox issues */
@@ -650,58 +677,6 @@ update_vlvfb:
 	}
 }
 
-static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
-	u8 num_tcs = netdev_get_num_tc(adapter->netdev);
-
-	/* remove VLAN filters beloning to this VF */
-	ixgbe_clear_vf_vlans(adapter, vf);
-
-	/* add back PF assigned VLAN or VLAN 0 */
-	ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf);
-
-	/* reset offloads to defaults */
-	ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan);
-
-	/* set outgoing tags for VFs */
-	if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) {
-		ixgbe_clear_vmvir(adapter, vf);
-	} else {
-		if (vfinfo->pf_qos || !num_tcs)
-			ixgbe_set_vmvir(adapter, vfinfo->pf_vlan,
-					vfinfo->pf_qos, vf);
-		else
-			ixgbe_set_vmvir(adapter, vfinfo->pf_vlan,
-					adapter->default_up, vf);
-
-		if (vfinfo->spoofchk_enabled)
-			hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);
-	}
-
-	/* reset multicast table array for vf */
-	adapter->vfinfo[vf].num_vf_mc_hashes = 0;
-
-	/* Flush and reset the mta with the new values */
-	ixgbe_set_rx_mode(adapter->netdev);
-
-	ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
-
-	/* reset VF api back to unknown */
-	adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10;
-}
-
-static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
-			    int vf, unsigned char *mac_addr)
-{
-	ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
-	memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN);
-	ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
-
-	return 0;
-}
-
 static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 				int vf, int index, unsigned char *mac_addr)
 {
@@ -757,6 +732,59 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
+static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
+	u8 num_tcs = netdev_get_num_tc(adapter->netdev);
+
+	/* remove VLAN filters beloning to this VF */
+	ixgbe_clear_vf_vlans(adapter, vf);
+
+	/* add back PF assigned VLAN or VLAN 0 */
+	ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf);
+
+	/* reset offloads to defaults */
+	ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan);
+
+	/* set outgoing tags for VFs */
+	if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) {
+		ixgbe_clear_vmvir(adapter, vf);
+	} else {
+		if (vfinfo->pf_qos || !num_tcs)
+			ixgbe_set_vmvir(adapter, vfinfo->pf_vlan,
+					vfinfo->pf_qos, vf);
+		else
+			ixgbe_set_vmvir(adapter, vfinfo->pf_vlan,
+					adapter->default_up, vf);
+
+		if (vfinfo->spoofchk_enabled)
+			hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);
+	}
+
+	/* reset multicast table array for vf */
+	adapter->vfinfo[vf].num_vf_mc_hashes = 0;
+
+	/* Flush and reset the mta with the new values */
+	ixgbe_set_rx_mode(adapter->netdev);
+
+	ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
+	ixgbe_set_vf_macvlan(adapter, vf, 0, NULL);
+
+	/* reset VF api back to unknown */
+	adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10;
+}
+
+static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
+			    int vf, unsigned char *mac_addr)
+{
+	ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
+	memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN);
+	ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
+
+	return 0;
+}
+
 int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask)
 {
 	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
@@ -1085,7 +1113,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,
 		return -EOPNOTSUPP;
 	}
 
-	memcpy(rss_key, adapter->rss_key, sizeof(adapter->rss_key));
+	memcpy(rss_key, adapter->rss_key, IXGBE_RSS_KEY_SIZE);
 
 	return 0;
 }
@@ -1319,18 +1347,26 @@ void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter)
 int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	if (!is_valid_ether_addr(mac) || (vf >= adapter->num_vfs))
+
+	if (vf >= adapter->num_vfs)
+		return -EINVAL;
+
+	if (is_zero_ether_addr(mac)) {
+		adapter->vfinfo[vf].pf_set_mac = false;
+		dev_info(&adapter->pdev->dev, "removing MAC on VF %d\n", vf);
+	} else if (is_valid_ether_addr(mac)) {
+		adapter->vfinfo[vf].pf_set_mac = true;
+		dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n",
+			 mac, vf);
+		dev_info(&adapter->pdev->dev, "Reload the VF driver to make this change effective.");
+		if (test_bit(__IXGBE_DOWN, &adapter->state)) {
+			dev_warn(&adapter->pdev->dev, "The VF MAC address has been set, but the PF device is not up.\n");
+			dev_warn(&adapter->pdev->dev, "Bring the PF device up before attempting to use the VF device.\n");
+		}
+	} else {
 		return -EINVAL;
-	adapter->vfinfo[vf].pf_set_mac = true;
-	dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf);
-	dev_info(&adapter->pdev->dev, "Reload the VF driver to make this"
-				      " change effective.");
-	if (test_bit(__IXGBE_DOWN, &adapter->state)) {
-		dev_warn(&adapter->pdev->dev, "The VF MAC address has been set,"
-			 " but the PF device is not up.\n");
-		dev_warn(&adapter->pdev->dev, "Bring the PF device up before"
-			 " attempting to use the VF device.\n");
 	}
+
 	return ixgbe_set_vf_mac(adapter, vf, mac);
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index 0c7977d27b71..cf67b9b18ed7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -33,6 +33,9 @@
  *  63 (IXGBE_MAX_VF_FUNCTIONS - 1)
  */
 #define IXGBE_MAX_VFS_DRV_LIMIT  (IXGBE_MAX_VF_FUNCTIONS - 1)
+#define IXGBE_MAX_VFS_1TC		IXGBE_MAX_VF_FUNCTIONS
+#define IXGBE_MAX_VFS_4TC		32
+#define IXGBE_MAX_VFS_8TC		16
 
 #ifdef CONFIG_PCI_IOV
 void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter);
@@ -56,7 +59,7 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter);
 int ixgbe_disable_sriov(struct ixgbe_adapter *adapter);
 #ifdef CONFIG_PCI_IOV
-void ixgbe_enable_sriov(struct ixgbe_adapter *adapter);
+void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs);
 #endif
 int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 1d07f2ead914..9c2460c5ef1b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -85,6 +85,7 @@
 #define IXGBE_DEV_ID_X550EM_X_SFP	0x15AC
 #define IXGBE_DEV_ID_X550EM_X_10G_T	0x15AD
 #define IXGBE_DEV_ID_X550EM_X_1G_T	0x15AE
+#define IXGBE_DEV_ID_X550EM_X_XFI	0x15B0
 #define IXGBE_DEV_ID_X550EM_A_KR	0x15C2
 #define IXGBE_DEV_ID_X550EM_A_KR_L	0x15C3
 #define IXGBE_DEV_ID_X550EM_A_SFP_N	0x15C4
@@ -1387,9 +1388,6 @@ struct ixgbe_thermal_sensor_data {
 #define ATH_PHY_ID       0x03429050
 #define AQ_FW_REV        0x20
 
-/* PHY Types */
-#define IXGBE_M88E1145_E_PHY_ID  0x01410CD0
-
 /* Special PHY Init Routine */
 #define IXGBE_PHY_INIT_OFFSET_NL 0x002B
 #define IXGBE_PHY_INIT_END_NL    0xFFFF
@@ -3128,7 +3126,9 @@ enum ixgbe_phy_type {
 	ixgbe_phy_aq,
 	ixgbe_phy_x550em_kr,
 	ixgbe_phy_x550em_kx4,
+	ixgbe_phy_x550em_xfi,
 	ixgbe_phy_x550em_ext_t,
+	ixgbe_phy_ext_1g_t,
 	ixgbe_phy_cu_unknown,
 	ixgbe_phy_qt,
 	ixgbe_phy_xaui,
@@ -3754,15 +3754,6 @@ struct ixgbe_info {
 #define IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN		BIT(3)
 #define IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN		BIT(31)
 
-#define IXGBE_KX4_LINK_CNTL_1				0x4C
-#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX		BIT(16)
-#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4		BIT(17)
-#define IXGBE_KX4_LINK_CNTL_1_TETH_EEE_CAP_KX		BIT(24)
-#define IXGBE_KX4_LINK_CNTL_1_TETH_EEE_CAP_KX4		BIT(25)
-#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_ENABLE		BIT(29)
-#define IXGBE_KX4_LINK_CNTL_1_TETH_FORCE_LINK_UP	BIT(30)
-#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_RESTART		BIT(31)
-
 #define IXGBE_SB_IOSF_INDIRECT_CTRL		0x00011144
 #define IXGBE_SB_IOSF_INDIRECT_DATA		0x00011148
 
@@ -3779,12 +3770,14 @@ struct ixgbe_info {
 #define IXGBE_SB_IOSF_CTRL_BUSY_SHIFT		31
 #define IXGBE_SB_IOSF_CTRL_BUSY		BIT(IXGBE_SB_IOSF_CTRL_BUSY_SHIFT)
 #define IXGBE_SB_IOSF_TARGET_KR_PHY	0
-#define IXGBE_SB_IOSF_TARGET_KX4_UNIPHY	1
-#define IXGBE_SB_IOSF_TARGET_KX4_PCS0	2
-#define IXGBE_SB_IOSF_TARGET_KX4_PCS1	3
 
 #define IXGBE_NW_MNG_IF_SEL		0x00011178
 #define IXGBE_NW_MNG_IF_SEL_MDIO_ACT		BIT(1)
+#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10M	BIT(17)
+#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_100M	BIT(18)
+#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_1G	BIT(19)
+#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G	BIT(20)
+#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10G	BIT(21)
 #define IXGBE_NW_MNG_IF_SEL_ENABLE_10_100M	BIT(23)
 #define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE	BIT(24)
 #define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT	3
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 84a467a8ed3d..6ea0d6a5fb90 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -95,6 +95,7 @@ s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw)
 {
 	s32 status;
 	u32 ctrl, i;
+	u32 swfw_mask = hw->phy.phy_semaphore_mask;
 
 	/* Call adapter stop to disable tx/rx and clear interrupts */
 	status = hw->mac.ops.stop_adapter(hw);
@@ -105,10 +106,17 @@ s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw)
 	ixgbe_clear_tx_pending(hw);
 
 mac_reset_top:
+	status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask);
+	if (status) {
+		hw_dbg(hw, "semaphore failed with %d", status);
+		return IXGBE_ERR_SWFW_SYNC;
+	}
+
 	ctrl = IXGBE_CTRL_RST;
 	ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL);
 	IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl);
 	IXGBE_WRITE_FLUSH(hw);
+	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
 	usleep_range(1000, 1200);
 
 	/* Poll for reset bit to self-clear indicating reset is complete */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 200f847fd8f3..2ba024b575ea 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -49,6 +49,18 @@ static s32 ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw)
 	return 0;
 }
 
+static s32 ixgbe_get_invariants_X550_x_fw(struct ixgbe_hw *hw)
+{
+	struct ixgbe_phy_info *phy = &hw->phy;
+
+	/* Start with X540 invariants, since so similar */
+	ixgbe_get_invariants_X540(hw);
+
+	phy->ops.set_phy_power = NULL;
+
+	return 0;
+}
+
 static s32 ixgbe_get_invariants_X550_a(struct ixgbe_hw *hw)
 {
 	struct ixgbe_mac_info *mac = &hw->mac;
@@ -320,6 +332,9 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw)
 	case IXGBE_DEV_ID_X550EM_X_KX4:
 		hw->phy.type = ixgbe_phy_x550em_kx4;
 		break;
+	case IXGBE_DEV_ID_X550EM_X_XFI:
+		hw->phy.type = ixgbe_phy_x550em_xfi;
+		break;
 	case IXGBE_DEV_ID_X550EM_X_KR:
 	case IXGBE_DEV_ID_X550EM_A_KR:
 	case IXGBE_DEV_ID_X550EM_A_KR_L:
@@ -331,9 +346,21 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw)
 		else
 			hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM;
 		/* Fallthrough */
-	case IXGBE_DEV_ID_X550EM_X_1G_T:
 	case IXGBE_DEV_ID_X550EM_X_10G_T:
 		return ixgbe_identify_phy_generic(hw);
+	case IXGBE_DEV_ID_X550EM_X_1G_T:
+		hw->phy.type = ixgbe_phy_ext_1g_t;
+		break;
+	case IXGBE_DEV_ID_X550EM_A_1G_T:
+	case IXGBE_DEV_ID_X550EM_A_1G_T_L:
+		hw->phy.type = ixgbe_phy_fw;
+		hw->phy.ops.read_reg = NULL;
+		hw->phy.ops.write_reg = NULL;
+		if (hw->bus.lan_id)
+			hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY1_SM;
+		else
+			hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY0_SM;
+		break;
 	default:
 		break;
 	}
@@ -2145,6 +2172,8 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw)
 					ixgbe_set_soft_rate_select_speed;
 		break;
 	case ixgbe_media_type_copper:
+		if (hw->device_id == IXGBE_DEV_ID_X550EM_X_1G_T)
+			break;
 		mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em;
 		mac->ops.setup_fc = ixgbe_setup_fc_generic;
 		mac->ops.check_link = ixgbe_check_link_t_X550em;
@@ -2215,8 +2244,39 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
 		else
 			*speed = IXGBE_LINK_SPEED_10GB_FULL;
 	} else {
-		*speed = IXGBE_LINK_SPEED_10GB_FULL |
-			 IXGBE_LINK_SPEED_1GB_FULL;
+		switch (hw->phy.type) {
+		case ixgbe_phy_x550em_kx4:
+			*speed = IXGBE_LINK_SPEED_1GB_FULL |
+				 IXGBE_LINK_SPEED_2_5GB_FULL |
+				 IXGBE_LINK_SPEED_10GB_FULL;
+			break;
+		case ixgbe_phy_x550em_xfi:
+			*speed = IXGBE_LINK_SPEED_1GB_FULL |
+				 IXGBE_LINK_SPEED_10GB_FULL;
+			break;
+		case ixgbe_phy_ext_1g_t:
+		case ixgbe_phy_sgmii:
+			*speed = IXGBE_LINK_SPEED_1GB_FULL;
+			break;
+		case ixgbe_phy_x550em_kr:
+			if (hw->mac.type == ixgbe_mac_x550em_a) {
+				/* check different backplane modes */
+				if (hw->phy.nw_mng_if_sel &
+				    IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G) {
+					*speed = IXGBE_LINK_SPEED_2_5GB_FULL;
+					break;
+				} else if (hw->device_id ==
+					   IXGBE_DEV_ID_X550EM_A_KR_L) {
+					*speed = IXGBE_LINK_SPEED_1GB_FULL;
+					break;
+				}
+			}
+			/* fall through */
+		default:
+			*speed = IXGBE_LINK_SPEED_10GB_FULL |
+				 IXGBE_LINK_SPEED_1GB_FULL;
+			break;
+		}
 		*autoneg = true;
 	}
 	return 0;
@@ -2473,44 +2533,6 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw,
 	return ixgbe_restart_an_internal_phy_x550em(hw);
 }
 
-/** ixgbe_setup_kx4_x550em - Configure the KX4 PHY.
- *  @hw: pointer to hardware structure
- *
- *   Configures the integrated KX4 PHY.
- **/
-static s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw)
-{
-	s32 status;
-	u32 reg_val;
-
-	status = hw->mac.ops.read_iosf_sb_reg(hw, IXGBE_KX4_LINK_CNTL_1,
-					      IXGBE_SB_IOSF_TARGET_KX4_PCS0 +
-					      hw->bus.lan_id, &reg_val);
-	if (status)
-		return status;
-
-	reg_val &= ~(IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4 |
-		     IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX);
-
-	reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_ENABLE;
-
-	/* Advertise 10G support. */
-	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
-		reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4;
-
-	/* Advertise 1G support. */
-	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL)
-		reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX;
-
-	/* Restart auto-negotiation. */
-	reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_RESTART;
-	status = hw->mac.ops.write_iosf_sb_reg(hw, IXGBE_KX4_LINK_CNTL_1,
-					       IXGBE_SB_IOSF_TARGET_KX4_PCS0 +
-					       hw->bus.lan_id, reg_val);
-
-	return status;
-}
-
 /**
  * ixgbe_setup_kr_x550em - Configure the KR PHY
  * @hw: pointer to hardware structure
@@ -2521,6 +2543,9 @@ static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw)
 	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL)
 		return 0;
 
+	if (ixgbe_check_reset_blocked(hw))
+		return 0;
+
 	return ixgbe_setup_kr_speed_x550em(hw, hw->phy.autoneg_advertised);
 }
 
@@ -3134,7 +3159,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 	/* Set functions pointers based on phy type */
 	switch (hw->phy.type) {
 	case ixgbe_phy_x550em_kx4:
-		phy->ops.setup_link = ixgbe_setup_kx4_x550em;
+		phy->ops.setup_link = NULL;
 		phy->ops.read_reg = ixgbe_read_phy_reg_x550em;
 		phy->ops.write_reg = ixgbe_write_phy_reg_x550em;
 		break;
@@ -3143,6 +3168,12 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 		phy->ops.read_reg = ixgbe_read_phy_reg_x550em;
 		phy->ops.write_reg = ixgbe_write_phy_reg_x550em;
 		break;
+	case ixgbe_phy_x550em_xfi:
+		/* link is managed by HW */
+		phy->ops.setup_link = NULL;
+		phy->ops.read_reg = ixgbe_read_phy_reg_x550em;
+		phy->ops.write_reg = ixgbe_write_phy_reg_x550em;
+		break;
 	case ixgbe_phy_x550em_ext_t:
 		/* Save NW management interface connected on board. This is used
 		 * to determine internal PHY mode
@@ -3164,10 +3195,18 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 		phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em;
 		phy->ops.reset = ixgbe_reset_phy_t_X550em;
 		break;
+	case ixgbe_phy_sgmii:
+		phy->ops.setup_link = NULL;
+		break;
 	case ixgbe_phy_fw:
 		phy->ops.setup_link = ixgbe_setup_fw_link;
 		phy->ops.reset = ixgbe_reset_phy_fw;
 		break;
+	case ixgbe_phy_ext_1g_t:
+		phy->ops.setup_link = NULL;
+		phy->ops.read_reg = NULL;
+		phy->ops.write_reg = NULL;
+		break;
 	default:
 		break;
 	}
@@ -3193,6 +3232,7 @@ static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw)
 		/* Fallthrough */
 	case IXGBE_DEV_ID_X550EM_X_KR:
 	case IXGBE_DEV_ID_X550EM_X_KX4:
+	case IXGBE_DEV_ID_X550EM_X_XFI:
 	case IXGBE_DEV_ID_X550EM_A_KR:
 	case IXGBE_DEV_ID_X550EM_A_KR_L:
 		media_type = ixgbe_media_type_backplane;
@@ -3300,6 +3340,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 	u32 ctrl = 0;
 	u32 i;
 	bool link_up = false;
+	u32 swfw_mask = hw->phy.phy_semaphore_mask;
 
 	/* Call adapter stop to disable Tx/Rx and clear interrupts */
 	status = hw->mac.ops.stop_adapter(hw);
@@ -3345,9 +3386,16 @@ mac_reset_top:
 			ctrl = IXGBE_CTRL_RST;
 	}
 
+	status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask);
+	if (status) {
+		hw_dbg(hw, "semaphore failed with %d", status);
+		return IXGBE_ERR_SWFW_SYNC;
+	}
+
 	ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL);
 	IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl);
 	IXGBE_WRITE_FLUSH(hw);
+	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
 	usleep_range(1000, 1200);
 
 	/* Poll for reset bit to self-clear meaning reset is complete */
@@ -3780,7 +3828,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = {
 	.get_media_type		= ixgbe_get_media_type_X550em,
 	.get_san_mac_addr	= NULL,
 	.get_wwn_prefix		= NULL,
-	.setup_link		= NULL, /* defined later */
+	.setup_link		= &ixgbe_setup_mac_link_X540,
 	.get_link_capabilities	= ixgbe_get_link_capabilities_X550em,
 	.get_bus_info		= ixgbe_get_bus_info_X550em,
 	.setup_sfp		= ixgbe_setup_sfp_modules_X550em,
@@ -3862,6 +3910,17 @@ static const struct ixgbe_phy_operations phy_ops_X550EM_x = {
 	.write_reg		= &ixgbe_write_phy_reg_generic,
 };
 
+static const struct ixgbe_phy_operations phy_ops_x550em_x_fw = {
+	X550_COMMON_PHY
+	.check_overtemp		= NULL,
+	.init			= ixgbe_init_phy_ops_X550em,
+	.identify		= ixgbe_identify_phy_x550em,
+	.read_reg		= NULL,
+	.write_reg		= NULL,
+	.read_reg_mdi		= NULL,
+	.write_reg_mdi		= NULL,
+};
+
 static const struct ixgbe_phy_operations phy_ops_x550em_a = {
 	X550_COMMON_PHY
 	.check_overtemp		= &ixgbe_tn_check_overtemp,
@@ -3924,6 +3983,16 @@ const struct ixgbe_info ixgbe_X550EM_x_info = {
 	.link_ops		= &link_ops_x550em_x,
 };
 
+const struct ixgbe_info ixgbe_x550em_x_fw_info = {
+	.mac			= ixgbe_mac_X550EM_x,
+	.get_invariants		= ixgbe_get_invariants_X550_x_fw,
+	.mac_ops		= &mac_ops_X550EM_x,
+	.eeprom_ops		= &eeprom_ops_X550EM_x,
+	.phy_ops		= &phy_ops_x550em_x_fw,
+	.mbx_ops		= &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_X550EM_x,
+};
+
 const struct ixgbe_info ixgbe_x550em_a_info = {
 	.mac			= ixgbe_mac_x550em_a,
 	.get_invariants		= &ixgbe_get_invariants_X550_a,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 1f6c0ecd50bb..ff9d05f308ee 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -80,7 +80,7 @@ static struct ixgbe_stats ixgbevf_gstrings_stats[] = {
 #define IXGBEVF_QUEUE_STATS_LEN ( \
 	(((struct ixgbevf_adapter *)netdev_priv(netdev))->num_tx_queues + \
 	 ((struct ixgbevf_adapter *)netdev_priv(netdev))->num_rx_queues) * \
-	 (sizeof(struct ixgbe_stats) / sizeof(u64)))
+	 (sizeof(struct ixgbevf_stats) / sizeof(u64)))
 #define IXGBEVF_GLOBAL_STATS_LEN ARRAY_SIZE(ixgbevf_gstrings_stats)
 
 #define IXGBEVF_STATS_LEN (IXGBEVF_GLOBAL_STATS_LEN + IXGBEVF_QUEUE_STATS_LEN)
@@ -91,18 +91,18 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define IXGBEVF_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN)
 
-static int ixgbevf_get_settings(struct net_device *netdev,
-				struct ethtool_cmd *ecmd)
+static int ixgbevf_get_link_ksettings(struct net_device *netdev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 link_speed = 0;
 	bool link_up;
 
-	ecmd->supported = SUPPORTED_10000baseT_Full;
-	ecmd->autoneg = AUTONEG_DISABLE;
-	ecmd->transceiver = XCVR_DUMMY1;
-	ecmd->port = -1;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full);
+	cmd->base.autoneg = AUTONEG_DISABLE;
+	cmd->base.port = -1;
 
 	hw->mac.get_link_status = 1;
 	hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
@@ -122,11 +122,11 @@ static int ixgbevf_get_settings(struct net_device *netdev,
 			break;
 		}
 
-		ethtool_cmd_speed_set(ecmd, speed);
-		ecmd->duplex = DUPLEX_FULL;
+		cmd->base.speed = speed;
+		cmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
 	return 0;
@@ -855,7 +855,8 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 
 	if (adapter->hw.mac.type >= ixgbe_mac_X550_vf) {
 		if (key)
-			memcpy(key, adapter->rss_key, sizeof(adapter->rss_key));
+			memcpy(key, adapter->rss_key,
+			       ixgbevf_get_rxfh_key_size(netdev));
 
 		if (indir) {
 			int i;
@@ -885,7 +886,6 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 }
 
 static const struct ethtool_ops ixgbevf_ethtool_ops = {
-	.get_settings		= ixgbevf_get_settings,
 	.get_drvinfo		= ixgbevf_get_drvinfo,
 	.get_regs_len		= ixgbevf_get_regs_len,
 	.get_regs		= ixgbevf_get_regs,
@@ -905,6 +905,7 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = {
 	.get_rxfh_indir_size	= ixgbevf_get_rxfh_indir_size,
 	.get_rxfh_key_size	= ixgbevf_get_rxfh_key_size,
 	.get_rxfh		= ixgbevf_get_rxfh,
+	.get_link_ksettings	= ixgbevf_get_link_ksettings,
 };
 
 void ixgbevf_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index a8cbc2dda0dd..581f44bbd7b3 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -319,7 +319,7 @@ struct ixgbevf_adapter {
 	spinlock_t mbx_lock;
 	unsigned long last_reset;
 
-	u32 rss_key[IXGBEVF_VFRSSRK_REGS];
+	u32 *rss_key;
 	u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE];
 };
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 80bab261a0ec..eee29bddddc1 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1660,6 +1660,28 @@ static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter,
 		       reg_idx);
 }
 
+/**
+ * ixgbevf_init_rss_key - Initialize adapter RSS key
+ * @adapter: device handle
+ *
+ * Allocates and initializes the RSS key if it is not allocated.
+ **/
+static inline int ixgbevf_init_rss_key(struct ixgbevf_adapter *adapter)
+{
+	u32 *rss_key;
+
+	if (!adapter->rss_key) {
+		rss_key = kzalloc(IXGBEVF_RSS_HASH_KEY_SIZE, GFP_KERNEL);
+		if (unlikely(!rss_key))
+			return -ENOMEM;
+
+		netdev_rss_key_fill(rss_key, IXGBEVF_RSS_HASH_KEY_SIZE);
+		adapter->rss_key = rss_key;
+	}
+
+	return 0;
+}
+
 static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -1668,9 +1690,8 @@ static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter)
 	u8 i, j;
 
 	/* Fill out hash function seeds */
-	netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key));
 	for (i = 0; i < IXGBEVF_VFRSSRK_REGS; i++)
-		IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), adapter->rss_key[i]);
+		IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), *(adapter->rss_key + i));
 
 	for (i = 0, j = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++, j++) {
 		if (j == rss_i)
@@ -2611,6 +2632,12 @@ static int ixgbevf_sw_init(struct ixgbevf_adapter *adapter)
 
 	hw->mbx.ops.init_params(hw);
 
+	if (hw->mac.type >= ixgbe_mac_X550_vf) {
+		err = ixgbevf_init_rss_key(adapter);
+		if (err)
+			goto out;
+	}
+
 	/* assume legacy case in which PF would only give VF 2 queues */
 	hw->mac.max_tx_queues = 2;
 	hw->mac.max_rx_queues = 2;
@@ -4127,6 +4154,7 @@ err_register:
 err_sw_init:
 	ixgbevf_reset_interrupt_capability(adapter);
 	iounmap(adapter->io_addr);
+	kfree(adapter->rss_key);
 err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state);
 	free_netdev(netdev);
@@ -4173,6 +4201,7 @@ static void ixgbevf_remove(struct pci_dev *pdev)
 
 	hw_dbg(&adapter->hw, "Remove complete\n");
 
+	kfree(adapter->rss_key);
 	disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state);
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 8a5db9d7219d..b6d0c01eab10 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -333,7 +333,7 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues)
 	switch (hw->api_version) {
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_12:
-		if (hw->mac.type >= ixgbe_mac_X550_vf)
+		if (hw->mac.type < ixgbe_mac_X550_vf)
 			break;
 	default:
 		return -EOPNOTSUPP;
@@ -399,7 +399,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key)
 	switch (hw->api_version) {
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_12:
-		if (hw->mac.type >= ixgbe_mac_X550_vf)
+		if (hw->mac.type < ixgbe_mac_X550_vf)
 			break;
 	default:
 		return -EOPNOTSUPP;
@@ -419,7 +419,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key)
 	msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS;
 
 	/* If the operation has been refused by a PF return -EPERM */
-	if (msgbuf[0] == (IXGBE_VF_GET_RETA | IXGBE_VT_MSGTYPE_NACK))
+	if (msgbuf[0] == (IXGBE_VF_GET_RSS_KEY | IXGBE_VT_MSGTYPE_NACK))
 		return -EPERM;
 
 	/* If we didn't get an ACK there must have been
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index d2555e8b947e..da6fb825afea 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -82,13 +82,13 @@ config MVNETA_BM
 	  that all dependencies are met.
 
 config MVPP2
-	tristate "Marvell Armada 375 network interface support"
+	tristate "Marvell Armada 375/7K/8K network interface support"
 	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on HAS_DMA
 	select MVMDIO
 	---help---
 	  This driver supports the network interface units in the
-	  Marvell ARMADA 375 SoC.
+	  Marvell ARMADA 375, 7K and 8K SoCs.
 
 config PXA168_ETH
 	tristate "Marvell pxa168 ethernet support"
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index a0d1b084ecec..90a60b98c28e 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -53,7 +53,7 @@
 struct orion_mdio_dev {
 	struct mutex lock;
 	void __iomem *regs;
-	struct clk *clk;
+	struct clk *clk[3];
 	/*
 	 * If we have access to the error interrupt pin (which is
 	 * somewhat misnamed as it not only reflects internal errors
@@ -187,7 +187,7 @@ static int orion_mdio_probe(struct platform_device *pdev)
 	struct resource *r;
 	struct mii_bus *bus;
 	struct orion_mdio_dev *dev;
-	int ret;
+	int i, ret;
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!r) {
@@ -216,11 +216,20 @@ static int orion_mdio_probe(struct platform_device *pdev)
 
 	init_waitqueue_head(&dev->smi_busy_wait);
 
-	dev->clk = devm_clk_get(&pdev->dev, NULL);
-	if (!IS_ERR(dev->clk))
-		clk_prepare_enable(dev->clk);
+	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+		dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+		if (IS_ERR(dev->clk[i]))
+			break;
+		clk_prepare_enable(dev->clk[i]);
+	}
 
 	dev->err_interrupt = platform_get_irq(pdev, 0);
+	if (dev->err_interrupt > 0 &&
+	    resource_size(r) < MVMDIO_ERR_INT_MASK + 4) {
+		dev_err(&pdev->dev,
+			"disabling interrupt, resource size is too small\n");
+		dev->err_interrupt = 0;
+	}
 	if (dev->err_interrupt > 0) {
 		ret = devm_request_irq(&pdev->dev, dev->err_interrupt,
 					orion_mdio_err_irq,
@@ -251,8 +260,16 @@ static int orion_mdio_probe(struct platform_device *pdev)
 	return 0;
 
 out_mdio:
-	if (!IS_ERR(dev->clk))
-		clk_disable_unprepare(dev->clk);
+	if (dev->err_interrupt > 0)
+		writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
+
+	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+		if (IS_ERR(dev->clk[i]))
+			break;
+		clk_disable_unprepare(dev->clk[i]);
+		clk_put(dev->clk[i]);
+	}
+
 	return ret;
 }
 
@@ -260,11 +277,18 @@ static int orion_mdio_remove(struct platform_device *pdev)
 {
 	struct mii_bus *bus = platform_get_drvdata(pdev);
 	struct orion_mdio_dev *dev = bus->priv;
+	int i;
 
-	writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
+	if (dev->err_interrupt > 0)
+		writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
 	mdiobus_unregister(bus);
-	if (!IS_ERR(dev->clk))
-		clk_disable_unprepare(dev->clk);
+
+	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+		if (IS_ERR(dev->clk[i]))
+			break;
+		clk_disable_unprepare(dev->clk[i]);
+		clk_put(dev->clk[i]);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61dd4462411c..d297011b535d 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -431,6 +431,7 @@ struct mvneta_port {
 	/* Flags for special SoC configurations */
 	bool neta_armada3700;
 	u16 rx_offset_correction;
+	const struct mbus_dram_target_info *dram_target_info;
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -1106,7 +1107,7 @@ static void mvneta_port_up(struct mvneta_port *pp)
 	q_map = 0;
 	for (queue = 0; queue < txq_number; queue++) {
 		struct mvneta_tx_queue *txq = &pp->txqs[queue];
-		if (txq->descs != NULL)
+		if (txq->descs)
 			q_map |= (1 << queue);
 	}
 	mvreg_write(pp, MVNETA_TXQ_CMD, q_map);
@@ -1115,7 +1116,7 @@ static void mvneta_port_up(struct mvneta_port *pp)
 	for (queue = 0; queue < rxq_number; queue++) {
 		struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
 
-		if (rxq->descs != NULL)
+		if (rxq->descs)
 			q_map |= (1 << queue);
 	}
 	mvreg_write(pp, MVNETA_RXQ_CMD, q_map);
@@ -2849,7 +2850,7 @@ static int mvneta_rxq_init(struct mvneta_port *pp,
 	rxq->descs = dma_alloc_coherent(pp->dev->dev.parent,
 					rxq->size * MVNETA_DESC_ALIGNED_SIZE,
 					&rxq->descs_phys, GFP_KERNEL);
-	if (rxq->descs == NULL)
+	if (!rxq->descs)
 		return -ENOMEM;
 
 	rxq->last_desc = rxq->size - 1;
@@ -2919,7 +2920,7 @@ static int mvneta_txq_init(struct mvneta_port *pp,
 	txq->descs = dma_alloc_coherent(pp->dev->dev.parent,
 					txq->size * MVNETA_DESC_ALIGNED_SIZE,
 					&txq->descs_phys, GFP_KERNEL);
-	if (txq->descs == NULL)
+	if (!txq->descs)
 		return -ENOMEM;
 
 	txq->last_desc = txq->size - 1;
@@ -2932,8 +2933,9 @@ static int mvneta_txq_init(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), txq->descs_phys);
 	mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), txq->size);
 
-	txq->tx_skb = kmalloc(txq->size * sizeof(*txq->tx_skb), GFP_KERNEL);
-	if (txq->tx_skb == NULL) {
+	txq->tx_skb = kmalloc_array(txq->size, sizeof(*txq->tx_skb),
+				    GFP_KERNEL);
+	if (!txq->tx_skb) {
 		dma_free_coherent(pp->dev->dev.parent,
 				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
 				  txq->descs, txq->descs_phys);
@@ -2944,7 +2946,7 @@ static int mvneta_txq_init(struct mvneta_port *pp,
 	txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent,
 					   txq->size * TSO_HEADER_SIZE,
 					   &txq->tso_hdrs_phys, GFP_KERNEL);
-	if (txq->tso_hdrs == NULL) {
+	if (!txq->tso_hdrs) {
 		kfree(txq->tx_skb);
 		dma_free_coherent(pp->dev->dev.parent,
 				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
@@ -3317,6 +3319,7 @@ static void mvneta_adjust_link(struct net_device *ndev)
 static int mvneta_mdio_probe(struct mvneta_port *pp)
 {
 	struct phy_device *phy_dev;
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
 
 	phy_dev = of_phy_connect(pp->dev, pp->phy_node, mvneta_adjust_link, 0,
 				 pp->phy_interface);
@@ -3325,6 +3328,9 @@ static int mvneta_mdio_probe(struct mvneta_port *pp)
 		return -ENODEV;
 	}
 
+	phy_ethtool_get_wol(phy_dev, &wol);
+	device_set_wakeup_capable(&pp->dev->dev, !!wol.supported);
+
 	phy_dev->supported &= PHY_GBIT_FEATURES;
 	phy_dev->advertising = phy_dev->supported;
 
@@ -3941,10 +3947,16 @@ static void mvneta_ethtool_get_wol(struct net_device *dev,
 static int mvneta_ethtool_set_wol(struct net_device *dev,
 				  struct ethtool_wolinfo *wol)
 {
+	int ret;
+
 	if (!dev->phydev)
 		return -EOPNOTSUPP;
 
-	return phy_ethtool_set_wol(dev->phydev, wol);
+	ret = phy_ethtool_set_wol(dev->phydev, wol);
+	if (!ret)
+		device_set_wakeup_enable(&dev->dev, !!wol->wolopts);
+
+	return ret;
 }
 
 static const struct net_device_ops mvneta_netdev_ops = {
@@ -3991,8 +4003,7 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp)
 	/* Set port default values */
 	mvneta_defaults_set(pp);
 
-	pp->txqs = devm_kcalloc(dev, txq_number, sizeof(struct mvneta_tx_queue),
-				GFP_KERNEL);
+	pp->txqs = devm_kcalloc(dev, txq_number, sizeof(*pp->txqs), GFP_KERNEL);
 	if (!pp->txqs)
 		return -ENOMEM;
 
@@ -4004,8 +4015,7 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp)
 		txq->done_pkts_coal = MVNETA_TXDONE_COAL_PKTS;
 	}
 
-	pp->rxqs = devm_kcalloc(dev, rxq_number, sizeof(struct mvneta_rx_queue),
-				GFP_KERNEL);
+	pp->rxqs = devm_kcalloc(dev, rxq_number, sizeof(*pp->rxqs), GFP_KERNEL);
 	if (!pp->rxqs)
 		return -ENOMEM;
 
@@ -4016,9 +4026,11 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp)
 		rxq->size = pp->rx_ring_size;
 		rxq->pkts_coal = MVNETA_RX_COAL_PKTS;
 		rxq->time_coal = MVNETA_RX_COAL_USEC;
-		rxq->buf_virt_addr = devm_kmalloc(pp->dev->dev.parent,
-						  rxq->size * sizeof(void *),
-						  GFP_KERNEL);
+		rxq->buf_virt_addr
+			= devm_kmalloc_array(pp->dev->dev.parent,
+					     rxq->size,
+					     sizeof(*rxq->buf_virt_addr),
+					     GFP_KERNEL);
 		if (!rxq->buf_virt_addr)
 			return -ENOMEM;
 	}
@@ -4098,6 +4110,8 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		ctrl |= MVNETA_GMAC2_PORT_RGMII;
 		break;
 	default:
@@ -4118,7 +4132,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 /* Device initialization routine */
 static int mvneta_probe(struct platform_device *pdev)
 {
-	const struct mbus_dram_target_info *dram_target_info;
 	struct resource *res;
 	struct device_node *dn = pdev->dev.of_node;
 	struct device_node *phy_node;
@@ -4267,13 +4280,13 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp->tx_csum_limit = tx_csum_limit;
 
-	dram_target_info = mv_mbus_dram_info();
+	pp->dram_target_info = mv_mbus_dram_info();
 	/* Armada3700 requires setting default configuration of Mbus
 	 * windows, however without using filled mbus_dram_target_info
 	 * structure.
 	 */
-	if (dram_target_info || pp->neta_armada3700)
-		mvneta_conf_mbus_windows(pp, dram_target_info);
+	if (pp->dram_target_info || pp->neta_armada3700)
+		mvneta_conf_mbus_windows(pp, pp->dram_target_info);
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -4405,6 +4418,61 @@ static int mvneta_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int mvneta_suspend(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (netif_running(dev))
+		mvneta_stop(dev);
+	netif_device_detach(dev);
+	clk_disable_unprepare(pp->clk_bus);
+	clk_disable_unprepare(pp->clk);
+	return 0;
+}
+
+static int mvneta_resume(struct device *device)
+{
+	struct platform_device *pdev = to_platform_device(device);
+	struct net_device *dev = dev_get_drvdata(device);
+	struct mvneta_port *pp = netdev_priv(dev);
+	int err;
+
+	clk_prepare_enable(pp->clk);
+	if (!IS_ERR(pp->clk_bus))
+		clk_prepare_enable(pp->clk_bus);
+	if (pp->dram_target_info || pp->neta_armada3700)
+		mvneta_conf_mbus_windows(pp, pp->dram_target_info);
+	if (pp->bm_priv) {
+		err = mvneta_bm_port_init(pdev, pp);
+		if (err < 0) {
+			dev_info(&pdev->dev, "use SW buffer management\n");
+			pp->bm_priv = NULL;
+		}
+	}
+	mvneta_defaults_set(pp);
+	err = mvneta_port_power_up(pp, pp->phy_interface);
+	if (err < 0) {
+		dev_err(device, "can't power up port\n");
+		return err;
+	}
+
+	if (pp->use_inband_status)
+		mvneta_fixed_link_update(pp, dev->phydev);
+
+	netif_device_attach(dev);
+	if (netif_running(dev)) {
+		mvneta_open(dev);
+		mvneta_set_rx_mode(dev);
+	}
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mvneta_pm_ops, mvneta_suspend, mvneta_resume);
+
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
 	{ .compatible = "marvell,armada-xp-neta" },
@@ -4419,6 +4487,7 @@ static struct platform_driver mvneta_driver = {
 	.driver = {
 		.name = MVNETA_DRIVER_NAME,
 		.of_match_table = mvneta_match,
+		.pm = &mvneta_pm_ops,
 	},
 };
 
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index d00421b9ffea..9b875d776b29 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -25,6 +25,7 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_address.h>
+#include <linux/of_device.h>
 #include <linux/phy.h>
 #include <linux/clk.h>
 #include <linux/hrtimer.h>
@@ -49,9 +50,11 @@
 #define     MVPP2_SNOOP_PKT_SIZE_MASK		0x1ff
 #define     MVPP2_SNOOP_BUF_HDR_MASK		BIT(9)
 #define     MVPP2_RXQ_POOL_SHORT_OFFS		20
-#define     MVPP2_RXQ_POOL_SHORT_MASK		0x700000
+#define     MVPP21_RXQ_POOL_SHORT_MASK		0x700000
+#define     MVPP22_RXQ_POOL_SHORT_MASK		0xf00000
 #define     MVPP2_RXQ_POOL_LONG_OFFS		24
-#define     MVPP2_RXQ_POOL_LONG_MASK		0x7000000
+#define     MVPP21_RXQ_POOL_LONG_MASK		0x7000000
+#define     MVPP22_RXQ_POOL_LONG_MASK		0xf000000
 #define     MVPP2_RXQ_PACKET_OFFSET_OFFS	28
 #define     MVPP2_RXQ_PACKET_OFFSET_MASK	0x70000000
 #define     MVPP2_RXQ_DISABLE_MASK		BIT(31)
@@ -99,6 +102,7 @@
 /* Descriptor Manager Top Registers */
 #define MVPP2_RXQ_NUM_REG			0x2040
 #define MVPP2_RXQ_DESC_ADDR_REG			0x2044
+#define     MVPP22_DESC_ADDR_OFFS		8
 #define MVPP2_RXQ_DESC_SIZE_REG			0x2048
 #define     MVPP2_RXQ_DESC_SIZE_MASK		0x3ff0
 #define MVPP2_RXQ_STATUS_UPDATE_REG(rxq)	(0x3000 + 4 * (rxq))
@@ -117,9 +121,6 @@
 #define MVPP2_TXQ_DESC_SIZE_REG			0x2088
 #define     MVPP2_TXQ_DESC_SIZE_MASK		0x3ff0
 #define MVPP2_AGGR_TXQ_UPDATE_REG		0x2090
-#define MVPP2_TXQ_THRESH_REG			0x2094
-#define     MVPP2_TRANSMITTED_THRESH_OFFSET	16
-#define     MVPP2_TRANSMITTED_THRESH_MASK	0x3fff0000
 #define MVPP2_TXQ_INDEX_REG			0x2098
 #define MVPP2_TXQ_PREF_BUF_REG			0x209c
 #define     MVPP2_PREF_BUF_PTR(desc)		((desc) & 0xfff)
@@ -140,6 +141,7 @@
 #define MVPP2_TXQ_RSVD_CLR_REG			0x20b8
 #define     MVPP2_TXQ_RSVD_CLR_OFFSET		16
 #define MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu)	(0x2100 + 4 * (cpu))
+#define     MVPP22_AGGR_TXQ_DESC_ADDR_OFFS	8
 #define MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu)	(0x2140 + 4 * (cpu))
 #define     MVPP2_AGGR_TXQ_DESC_SIZE_MASK	0x3ff0
 #define MVPP2_AGGR_TXQ_STATUS_REG(cpu)		(0x2180 + 4 * (cpu))
@@ -152,10 +154,52 @@
 #define MVPP2_WIN_REMAP(w)			(0x4040 + ((w) << 2))
 #define MVPP2_BASE_ADDR_ENABLE			0x4060
 
+/* AXI Bridge Registers */
+#define MVPP22_AXI_BM_WR_ATTR_REG		0x4100
+#define MVPP22_AXI_BM_RD_ATTR_REG		0x4104
+#define MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG	0x4110
+#define MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG	0x4114
+#define MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG	0x4118
+#define MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG	0x411c
+#define MVPP22_AXI_RX_DATA_WR_ATTR_REG		0x4120
+#define MVPP22_AXI_TX_DATA_RD_ATTR_REG		0x4130
+#define MVPP22_AXI_RD_NORMAL_CODE_REG		0x4150
+#define MVPP22_AXI_RD_SNOOP_CODE_REG		0x4154
+#define MVPP22_AXI_WR_NORMAL_CODE_REG		0x4160
+#define MVPP22_AXI_WR_SNOOP_CODE_REG		0x4164
+
+/* Values for AXI Bridge registers */
+#define MVPP22_AXI_ATTR_CACHE_OFFS		0
+#define MVPP22_AXI_ATTR_DOMAIN_OFFS		12
+
+#define MVPP22_AXI_CODE_CACHE_OFFS		0
+#define MVPP22_AXI_CODE_DOMAIN_OFFS		4
+
+#define MVPP22_AXI_CODE_CACHE_NON_CACHE		0x3
+#define MVPP22_AXI_CODE_CACHE_WR_CACHE		0x7
+#define MVPP22_AXI_CODE_CACHE_RD_CACHE		0xb
+
+#define MVPP22_AXI_CODE_DOMAIN_OUTER_DOM	2
+#define MVPP22_AXI_CODE_DOMAIN_SYSTEM		3
+
 /* Interrupt Cause and Mask registers */
 #define MVPP2_ISR_RX_THRESHOLD_REG(rxq)		(0x5200 + 4 * (rxq))
 #define     MVPP2_MAX_ISR_RX_THRESHOLD		0xfffff0
-#define MVPP2_ISR_RXQ_GROUP_REG(rxq)		(0x5400 + 4 * (rxq))
+#define MVPP21_ISR_RXQ_GROUP_REG(rxq)		(0x5400 + 4 * (rxq))
+
+#define MVPP22_ISR_RXQ_GROUP_INDEX_REG          0x5400
+#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK   0x380
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7
+
+#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK   0x380
+
+#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG     0x5404
+#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK    0x1f
+#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK      0xf00
+#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET    8
+
 #define MVPP2_ISR_ENABLE_REG(port)		(0x5420 + 4 * (port))
 #define     MVPP2_ISR_ENABLE_INTERRUPT(mask)	((mask) & 0xffff)
 #define     MVPP2_ISR_DISABLE_INTERRUPT(mask)	(((mask) << 16) & 0xffff0000)
@@ -210,14 +254,19 @@
 #define MVPP2_BM_PHY_ALLOC_REG(pool)		(0x6400 + ((pool) * 4))
 #define     MVPP2_BM_PHY_ALLOC_GRNTD_MASK	BIT(0)
 #define MVPP2_BM_VIRT_ALLOC_REG			0x6440
+#define MVPP22_BM_ADDR_HIGH_ALLOC		0x6444
+#define     MVPP22_BM_ADDR_HIGH_PHYS_MASK	0xff
+#define     MVPP22_BM_ADDR_HIGH_VIRT_MASK	0xff00
+#define     MVPP22_BM_ADDR_HIGH_VIRT_SHIFT	8
 #define MVPP2_BM_PHY_RLS_REG(pool)		(0x6480 + ((pool) * 4))
 #define     MVPP2_BM_PHY_RLS_MC_BUFF_MASK	BIT(0)
 #define     MVPP2_BM_PHY_RLS_PRIO_EN_MASK	BIT(1)
 #define     MVPP2_BM_PHY_RLS_GRNTD_MASK		BIT(2)
 #define MVPP2_BM_VIRT_RLS_REG			0x64c0
-#define MVPP2_BM_MC_RLS_REG			0x64c4
-#define     MVPP2_BM_MC_ID_MASK			0xfff
-#define     MVPP2_BM_FORCE_RELEASE_MASK		BIT(12)
+#define MVPP22_BM_ADDR_HIGH_RLS_REG		0x64c4
+#define     MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK	0xff
+#define	    MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK	0xff00
+#define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT	8
 
 /* TX Scheduler registers */
 #define MVPP2_TXP_SCHED_PORT_INDEX_REG		0x8000
@@ -287,6 +336,24 @@
 #define      MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK	0x1fc0
 #define      MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v)	(((v) << 6) & \
 					MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK)
+#define MVPP22_GMAC_CTRL_4_REG			0x90
+#define      MVPP22_CTRL4_EXT_PIN_GMII_SEL	BIT(0)
+#define      MVPP22_CTRL4_DP_CLK_SEL		BIT(5)
+#define      MVPP22_CTRL4_SYNC_BYPASS		BIT(6)
+#define      MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE	BIT(7)
+
+/* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0,
+ * relative to port->base.
+ */
+#define MVPP22_XLG_CTRL3_REG			0x11c
+#define      MVPP22_XLG_CTRL3_MACMODESELECT_MASK	(7 << 13)
+#define      MVPP22_XLG_CTRL3_MACMODESELECT_GMAC	(0 << 13)
+
+/* SMI registers. PPv2.2 only, relative to priv->iface_base. */
+#define MVPP22_SMI_MISC_CFG_REG			0x1204
+#define      MVPP22_SMI_POLLING_EN		BIT(10)
+
+#define MVPP22_GMAC_BASE(port)		(0x7000 + (port) * 0x1000 + 0xe00)
 
 #define MVPP2_CAUSE_TXQ_SENT_DESC_ALL_MASK	0xff
 
@@ -335,15 +402,9 @@
 /* Maximum number of TXQs used by single port */
 #define MVPP2_MAX_TXQ			8
 
-/* Maximum number of RXQs used by single port */
-#define MVPP2_MAX_RXQ			8
-
 /* Dfault number of RXQs in use */
 #define MVPP2_DEFAULT_RXQ		4
 
-/* Total number of RXQs available to all ports */
-#define MVPP2_RXQ_TOTAL_NUM		(MVPP2_MAX_PORTS * MVPP2_MAX_RXQ)
-
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD			128
 
@@ -615,6 +676,11 @@ enum mvpp2_prs_l3_cast {
  */
 #define MVPP2_BM_SHORT_PKT_SIZE		MVPP2_RX_MAX_PKT_SIZE(512)
 
+#define MVPP21_ADDR_SPACE_SZ		0
+#define MVPP22_ADDR_SPACE_SZ		SZ_64K
+
+#define MVPP2_MAX_CPUS			4
+
 enum mvpp2_bm_type {
 	MVPP2_BM_FREE,
 	MVPP2_BM_SWF_LONG,
@@ -626,12 +692,19 @@ enum mvpp2_bm_type {
 /* Shared Packet Processor resources */
 struct mvpp2 {
 	/* Shared registers' base addresses */
-	void __iomem *base;
 	void __iomem *lms_base;
+	void __iomem *iface_base;
+
+	/* On PPv2.2, each CPU can access the base register through a
+	 * separate address space, each 64 KB apart from each
+	 * other.
+	 */
+	void __iomem *cpu_base[MVPP2_MAX_CPUS];
 
 	/* Common clocks */
 	struct clk *pp_clk;
 	struct clk *gop_clk;
+	struct clk *mg_clk;
 
 	/* List of pointers to port structures */
 	struct mvpp2_port **port_list;
@@ -649,6 +722,12 @@ struct mvpp2 {
 
 	/* Tclk value */
 	u32 tclk;
+
+	/* HW version */
+	enum { MVPP21, MVPP22 } hw_version;
+
+	/* Maximum number of RXQs per port */
+	unsigned int max_port_rxqs;
 };
 
 struct mvpp2_pcpu_stats {
@@ -670,6 +749,11 @@ struct mvpp2_port_pcpu {
 struct mvpp2_port {
 	u8 id;
 
+	/* Index of the port from the "group of ports" complex point
+	 * of view
+	 */
+	int gop_id;
+
 	int irq;
 
 	struct mvpp2 *priv;
@@ -741,22 +825,24 @@ struct mvpp2_port {
 #define MVPP2_RXD_L3_IP6		BIT(30)
 #define MVPP2_RXD_BUF_HDR		BIT(31)
 
-struct mvpp2_tx_desc {
+/* HW TX descriptor for PPv2.1 */
+struct mvpp21_tx_desc {
 	u32 command;		/* Options used by HW for packet transmitting.*/
 	u8  packet_offset;	/* the offset from the buffer beginning	*/
 	u8  phys_txq;		/* destination queue ID			*/
 	u16 data_size;		/* data size of transmitted packet in bytes */
-	u32 buf_phys_addr;	/* physical addr of transmitted buffer	*/
+	u32 buf_dma_addr;	/* physical addr of transmitted buffer	*/
 	u32 buf_cookie;		/* cookie for access to TX buffer in tx path */
 	u32 reserved1[3];	/* hw_cmd (for future use, BM, PON, PNC) */
 	u32 reserved2;		/* reserved (for future use)		*/
 };
 
-struct mvpp2_rx_desc {
+/* HW RX descriptor for PPv2.1 */
+struct mvpp21_rx_desc {
 	u32 status;		/* info about received packet		*/
 	u16 reserved1;		/* parser_info (for future use, PnC)	*/
 	u16 data_size;		/* size of received packet in bytes	*/
-	u32 buf_phys_addr;	/* physical address of the buffer	*/
+	u32 buf_dma_addr;	/* physical address of the buffer	*/
 	u32 buf_cookie;		/* cookie for access to RX buffer in rx path */
 	u16 reserved2;		/* gem_port_id (for future use, PON)	*/
 	u16 reserved3;		/* csum_l4 (for future use, PnC)	*/
@@ -767,12 +853,51 @@ struct mvpp2_rx_desc {
 	u32 reserved8;
 };
 
+/* HW TX descriptor for PPv2.2 */
+struct mvpp22_tx_desc {
+	u32 command;
+	u8  packet_offset;
+	u8  phys_txq;
+	u16 data_size;
+	u64 reserved1;
+	u64 buf_dma_addr_ptp;
+	u64 buf_cookie_misc;
+};
+
+/* HW RX descriptor for PPv2.2 */
+struct mvpp22_rx_desc {
+	u32 status;
+	u16 reserved1;
+	u16 data_size;
+	u32 reserved2;
+	u32 reserved3;
+	u64 buf_dma_addr_key_hash;
+	u64 buf_cookie_misc;
+};
+
+/* Opaque type used by the driver to manipulate the HW TX and RX
+ * descriptors
+ */
+struct mvpp2_tx_desc {
+	union {
+		struct mvpp21_tx_desc pp21;
+		struct mvpp22_tx_desc pp22;
+	};
+};
+
+struct mvpp2_rx_desc {
+	union {
+		struct mvpp21_rx_desc pp21;
+		struct mvpp22_rx_desc pp22;
+	};
+};
+
 struct mvpp2_txq_pcpu_buf {
 	/* Transmitted SKB */
 	struct sk_buff *skb;
 
 	/* Physical address of transmitted buffer */
-	dma_addr_t phys;
+	dma_addr_t dma;
 
 	/* Size transmitted */
 	size_t size;
@@ -825,7 +950,7 @@ struct mvpp2_tx_queue {
 	struct mvpp2_tx_desc *descs;
 
 	/* DMA address of the Tx DMA descriptors array */
-	dma_addr_t descs_phys;
+	dma_addr_t descs_dma;
 
 	/* Index of the last Tx DMA descriptor */
 	int last_desc;
@@ -848,7 +973,7 @@ struct mvpp2_rx_queue {
 	struct mvpp2_rx_desc *descs;
 
 	/* DMA address of the RX DMA descriptors array */
-	dma_addr_t descs_phys;
+	dma_addr_t descs_dma;
 
 	/* Index of the last RX DMA descriptor */
 	int last_desc;
@@ -912,6 +1037,8 @@ struct mvpp2_bm_pool {
 
 	/* Buffer Pointers Pool External (BPPE) size */
 	int size;
+	/* BPPE size in bytes */
+	int size_bytes;
 	/* Number of buffers for this pool */
 	int buf_num;
 	/* Pool buffer size */
@@ -922,29 +1049,13 @@ struct mvpp2_bm_pool {
 
 	/* BPPE virtual base address */
 	u32 *virt_addr;
-	/* BPPE physical base address */
-	dma_addr_t phys_addr;
+	/* BPPE DMA base address */
+	dma_addr_t dma_addr;
 
 	/* Ports using BM pool */
 	u32 port_map;
 };
 
-struct mvpp2_buff_hdr {
-	u32 next_buff_phys_addr;
-	u32 next_buff_virt_addr;
-	u16 byte_count;
-	u16 info;
-	u8  reserved1;		/* bm_qset (for future use, BM)		*/
-};
-
-/* Buffer header info bits */
-#define MVPP2_B_HDR_INFO_MC_ID_MASK	0xfff
-#define MVPP2_B_HDR_INFO_MC_ID(info)	((info) & MVPP2_B_HDR_INFO_MC_ID_MASK)
-#define MVPP2_B_HDR_INFO_LAST_OFFS	12
-#define MVPP2_B_HDR_INFO_LAST_MASK	BIT(12)
-#define MVPP2_B_HDR_INFO_IS_LAST(info) \
-	   ((info & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS)
-
 /* Static declaractions */
 
 /* Number of RXQs used by single port */
@@ -959,12 +1070,177 @@ static int txq_number = MVPP2_MAX_TXQ;
 
 static void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data)
 {
-	writel(data, priv->base + offset);
+	writel(data, priv->cpu_base[0] + offset);
 }
 
 static u32 mvpp2_read(struct mvpp2 *priv, u32 offset)
 {
-	return readl(priv->base + offset);
+	return readl(priv->cpu_base[0] + offset);
+}
+
+/* These accessors should be used to access:
+ *
+ * - per-CPU registers, where each CPU has its own copy of the
+ *   register.
+ *
+ *   MVPP2_BM_VIRT_ALLOC_REG
+ *   MVPP2_BM_ADDR_HIGH_ALLOC
+ *   MVPP22_BM_ADDR_HIGH_RLS_REG
+ *   MVPP2_BM_VIRT_RLS_REG
+ *   MVPP2_ISR_RX_TX_CAUSE_REG
+ *   MVPP2_ISR_RX_TX_MASK_REG
+ *   MVPP2_TXQ_NUM_REG
+ *   MVPP2_AGGR_TXQ_UPDATE_REG
+ *   MVPP2_TXQ_RSVD_REQ_REG
+ *   MVPP2_TXQ_RSVD_RSLT_REG
+ *   MVPP2_TXQ_SENT_REG
+ *   MVPP2_RXQ_NUM_REG
+ *
+ * - global registers that must be accessed through a specific CPU
+ *   window, because they are related to an access to a per-CPU
+ *   register
+ *
+ *   MVPP2_BM_PHY_ALLOC_REG    (related to MVPP2_BM_VIRT_ALLOC_REG)
+ *   MVPP2_BM_PHY_RLS_REG      (related to MVPP2_BM_VIRT_RLS_REG)
+ *   MVPP2_RXQ_THRESH_REG      (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_RXQ_DESC_ADDR_REG   (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_RXQ_DESC_SIZE_REG   (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_RXQ_INDEX_REG       (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_TXQ_PENDING_REG     (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_DESC_ADDR_REG   (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_DESC_SIZE_REG   (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_INDEX_REG       (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_PENDING_REG     (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_PREF_BUF_REG    (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_PREF_BUF_REG    (related to MVPP2_TXQ_NUM_REG)
+ */
+static void mvpp2_percpu_write(struct mvpp2 *priv, int cpu,
+			       u32 offset, u32 data)
+{
+	writel(data, priv->cpu_base[cpu] + offset);
+}
+
+static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu,
+			     u32 offset)
+{
+	return readl(priv->cpu_base[cpu] + offset);
+}
+
+static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
+					    struct mvpp2_tx_desc *tx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return tx_desc->pp21.buf_dma_addr;
+	else
+		return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+}
+
+static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
+				      struct mvpp2_tx_desc *tx_desc,
+				      dma_addr_t dma_addr)
+{
+	if (port->priv->hw_version == MVPP21) {
+		tx_desc->pp21.buf_dma_addr = dma_addr;
+	} else {
+		u64 val = (u64)dma_addr;
+
+		tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+		tx_desc->pp22.buf_dma_addr_ptp |= val;
+	}
+}
+
+static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port,
+				    struct mvpp2_tx_desc *tx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return tx_desc->pp21.data_size;
+	else
+		return tx_desc->pp22.data_size;
+}
+
+static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
+				  struct mvpp2_tx_desc *tx_desc,
+				  size_t size)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.data_size = size;
+	else
+		tx_desc->pp22.data_size = size;
+}
+
+static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
+				 struct mvpp2_tx_desc *tx_desc,
+				 unsigned int txq)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.phys_txq = txq;
+	else
+		tx_desc->pp22.phys_txq = txq;
+}
+
+static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
+				 struct mvpp2_tx_desc *tx_desc,
+				 unsigned int command)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.command = command;
+	else
+		tx_desc->pp22.command = command;
+}
+
+static void mvpp2_txdesc_offset_set(struct mvpp2_port *port,
+				    struct mvpp2_tx_desc *tx_desc,
+				    unsigned int offset)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.packet_offset = offset;
+	else
+		tx_desc->pp22.packet_offset = offset;
+}
+
+static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
+					    struct mvpp2_tx_desc *tx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return tx_desc->pp21.packet_offset;
+	else
+		return tx_desc->pp22.packet_offset;
+}
+
+static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
+					    struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.buf_dma_addr;
+	else
+		return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+}
+
+static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
+					     struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.buf_cookie;
+	else
+		return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+}
+
+static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
+				    struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.data_size;
+	else
+		return rx_desc->pp22.data_size;
+}
+
+static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
+				   struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.status;
+	else
+		return rx_desc->pp22.status;
 }
 
 static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
@@ -974,15 +1250,17 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
 		txq_pcpu->txq_get_index = 0;
 }
 
-static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
+static void mvpp2_txq_inc_put(struct mvpp2_port *port,
+			      struct mvpp2_txq_pcpu *txq_pcpu,
 			      struct sk_buff *skb,
 			      struct mvpp2_tx_desc *tx_desc)
 {
 	struct mvpp2_txq_pcpu_buf *tx_buf =
 		txq_pcpu->buffs + txq_pcpu->txq_put_index;
 	tx_buf->skb = skb;
-	tx_buf->size = tx_desc->data_size;
-	tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset;
+	tx_buf->size = mvpp2_txdesc_size_get(port, tx_desc);
+	tx_buf->dma = mvpp2_txdesc_dma_addr_get(port, tx_desc) +
+		mvpp2_txdesc_offset_get(port, tx_desc);
 	txq_pcpu->txq_put_index++;
 	if (txq_pcpu->txq_put_index == txq_pcpu->size)
 		txq_pcpu->txq_put_index = 0;
@@ -1411,7 +1689,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 		mvpp2_prs_hw_read(priv, &pe);
 	} else {
 		/* Entry doesn't exist - create new */
-		memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
 		pe.index = MVPP2_PE_DROP_ALL;
 
@@ -1448,7 +1726,7 @@ static void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, bool add)
 		mvpp2_prs_hw_read(priv, &pe);
 	} else {
 		/* Entry doesn't exist - create new */
-		memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
 		pe.index = MVPP2_PE_MAC_PROMISCUOUS;
 
@@ -1494,7 +1772,7 @@ static void mvpp2_prs_mac_multi_set(struct mvpp2 *priv, int port, int index,
 		mvpp2_prs_hw_read(priv, &pe);
 	} else {
 		/* Entry doesn't exist - create new */
-		memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
 		pe.index = index;
 
@@ -1546,7 +1824,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 		mvpp2_prs_hw_read(priv, &pe);
 	} else {
 		/* Entry doesn't exist - create new */
-		memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA);
 		pe.index = tid;
 
@@ -1609,7 +1887,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port,
 		mvpp2_prs_hw_read(priv, &pe);
 	} else {
 		/* Entry doesn't exist - create new */
-		memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA);
 		pe.index = tid;
 
@@ -1743,10 +2021,10 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 
 		if (tid <= tid_aux) {
 			ret = -EINVAL;
-			goto error;
+			goto free_pe;
 		}
 
-		memset(pe, 0 , sizeof(struct mvpp2_prs_entry));
+		memset(pe, 0, sizeof(*pe));
 		mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_VLAN);
 		pe->index = tid;
 
@@ -1775,8 +2053,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 	mvpp2_prs_tcam_port_map_set(pe, port_map);
 
 	mvpp2_prs_hw_write(priv, pe);
-
-error:
+free_pe:
 	kfree(pe);
 
 	return ret;
@@ -1861,7 +2138,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 		ai = mvpp2_prs_double_vlan_ai_free_get(priv);
 		if (ai < 0) {
 			ret = ai;
-			goto error;
+			goto free_pe;
 		}
 
 		/* Get first single/triple vlan tid */
@@ -1884,10 +2161,10 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 
 		if (tid >= tid_aux) {
 			ret = -ERANGE;
-			goto error;
+			goto free_pe;
 		}
 
-		memset(pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(pe, 0, sizeof(*pe));
 		mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_VLAN);
 		pe->index = tid;
 
@@ -1911,8 +2188,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 	/* Update ports' mask */
 	mvpp2_prs_tcam_port_map_set(pe, port_map);
 	mvpp2_prs_hw_write(priv, pe);
-
-error:
+free_pe:
 	kfree(pe);
 	return ret;
 }
@@ -1934,7 +2210,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = tid;
 
@@ -1992,7 +2268,7 @@ static int mvpp2_prs_ip4_cast(struct mvpp2 *priv, unsigned short l3_cast)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = tid;
 
@@ -2048,7 +2324,7 @@ static int mvpp2_prs_ip6_proto(struct mvpp2 *priv, unsigned short proto,
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6);
 	pe.index = tid;
 
@@ -2087,7 +2363,7 @@ static int mvpp2_prs_ip6_cast(struct mvpp2 *priv, unsigned short l3_cast)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6);
 	pe.index = tid;
 
@@ -2147,7 +2423,7 @@ static void mvpp2_prs_def_flow_init(struct mvpp2 *priv)
 	int port;
 
 	for (port = 0; port < MVPP2_MAX_PORTS; port++) {
-		memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
 		pe.index = MVPP2_PE_FIRST_DEFAULT_FLOW - port;
 
@@ -2169,7 +2445,7 @@ static void mvpp2_prs_mh_init(struct mvpp2 *priv)
 {
 	struct mvpp2_prs_entry pe;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 
 	pe.index = MVPP2_PE_MH_DEFAULT;
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MH);
@@ -2192,7 +2468,7 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv)
 {
 	struct mvpp2_prs_entry pe;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 
 	/* Non-promiscuous mode for all ports - DROP unknown packets */
 	pe.index = MVPP2_PE_MAC_NON_PROMISCUOUS;
@@ -2253,7 +2529,7 @@ static void mvpp2_prs_dsa_init(struct mvpp2 *priv)
 					MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
 
 	/* Set default entry, in case DSA or EDSA tag not found */
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA);
 	pe.index = MVPP2_PE_DSA_DEFAULT;
 	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_VLAN);
@@ -2283,7 +2559,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2);
 	pe.index = tid;
 
@@ -2309,7 +2585,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2);
 	pe.index = tid;
 
@@ -2339,7 +2615,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2);
 	pe.index = tid;
 
@@ -2373,7 +2649,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2);
 	pe.index = tid;
 
@@ -2438,7 +2714,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2);
 	pe.index = tid;
 
@@ -2535,7 +2811,7 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv)
 		return err;
 
 	/* Set default double vlan entry */
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VLAN);
 	pe.index = MVPP2_PE_VLAN_DBL;
 
@@ -2555,7 +2831,7 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv)
 	mvpp2_prs_hw_write(priv, &pe);
 
 	/* Set default vlan none entry */
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VLAN);
 	pe.index = MVPP2_PE_VLAN_NONE;
 
@@ -2585,7 +2861,7 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE);
 	pe.index = tid;
 
@@ -2635,7 +2911,7 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE);
 	pe.index = tid;
 
@@ -2662,7 +2938,7 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE);
 	pe.index = tid;
 
@@ -2720,7 +2996,7 @@ static int mvpp2_prs_ip4_init(struct mvpp2 *priv)
 		return err;
 
 	/* Default IPv4 entry for unknown protocols */
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = MVPP2_PE_IP4_PROTO_UN;
 
@@ -2745,7 +3021,7 @@ static int mvpp2_prs_ip4_init(struct mvpp2 *priv)
 	mvpp2_prs_hw_write(priv, &pe);
 
 	/* Default IPv4 entry for unicast address */
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = MVPP2_PE_IP4_ADDR_UN;
 
@@ -2813,7 +3089,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv)
 	if (tid < 0)
 		return tid;
 
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6);
 	pe.index = tid;
 
@@ -2834,7 +3110,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv)
 	mvpp2_prs_hw_write(priv, &pe);
 
 	/* Default IPv6 entry for unknown protocols */
-	memset(&pe, 0, sizeof(struct mvpp2_prs_entry));
+	memset(&pe, 0, sizeof(pe));
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6);
 	pe.index = MVPP2_PE_IP6_PROTO_UN;
 
@@ -2927,7 +3203,7 @@ static int mvpp2_prs_default_init(struct platform_device *pdev,
 		mvpp2_prs_hw_inv(priv, index);
 
 	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
-					sizeof(struct mvpp2_prs_shadow),
+					sizeof(*priv->prs_shadow),
 					GFP_KERNEL);
 	if (!priv->prs_shadow)
 		return -ENOMEM;
@@ -3378,27 +3654,39 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev,
 				struct mvpp2 *priv,
 				struct mvpp2_bm_pool *bm_pool, int size)
 {
-	int size_bytes;
 	u32 val;
 
-	size_bytes = sizeof(u32) * size;
-	bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes,
-						&bm_pool->phys_addr,
+	/* Number of buffer pointers must be a multiple of 16, as per
+	 * hardware constraints
+	 */
+	if (!IS_ALIGNED(size, 16))
+		return -EINVAL;
+
+	/* PPv2.1 needs 8 bytes per buffer pointer, PPv2.2 needs 16
+	 * bytes per buffer pointer
+	 */
+	if (priv->hw_version == MVPP21)
+		bm_pool->size_bytes = 2 * sizeof(u32) * size;
+	else
+		bm_pool->size_bytes = 2 * sizeof(u64) * size;
+
+	bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, bm_pool->size_bytes,
+						&bm_pool->dma_addr,
 						GFP_KERNEL);
 	if (!bm_pool->virt_addr)
 		return -ENOMEM;
 
 	if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr,
 			MVPP2_BM_POOL_PTR_ALIGN)) {
-		dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
-				  bm_pool->phys_addr);
+		dma_free_coherent(&pdev->dev, bm_pool->size_bytes,
+				  bm_pool->virt_addr, bm_pool->dma_addr);
 		dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n",
 			bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN);
 		return -ENOMEM;
 	}
 
 	mvpp2_write(priv, MVPP2_BM_POOL_BASE_REG(bm_pool->id),
-		    bm_pool->phys_addr);
+		    lower_32_bits(bm_pool->dma_addr));
 	mvpp2_write(priv, MVPP2_BM_POOL_SIZE_REG(bm_pool->id), size);
 
 	val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id));
@@ -3426,6 +3714,34 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_POOL_BUF_SIZE_REG(bm_pool->id), val);
 }
 
+static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv,
+				    struct mvpp2_bm_pool *bm_pool,
+				    dma_addr_t *dma_addr,
+				    phys_addr_t *phys_addr)
+{
+	int cpu = smp_processor_id();
+
+	*dma_addr = mvpp2_percpu_read(priv, cpu,
+				      MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
+	*phys_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_VIRT_ALLOC_REG);
+
+	if (priv->hw_version == MVPP22) {
+		u32 val;
+		u32 dma_addr_highbits, phys_addr_highbits;
+
+		val = mvpp2_percpu_read(priv, cpu, MVPP22_BM_ADDR_HIGH_ALLOC);
+		dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK);
+		phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >>
+			MVPP22_BM_ADDR_HIGH_VIRT_SHIFT;
+
+		if (sizeof(dma_addr_t) == 8)
+			*dma_addr |= (u64)dma_addr_highbits << 32;
+
+		if (sizeof(phys_addr_t) == 8)
+			*phys_addr |= (u64)phys_addr_highbits << 32;
+	}
+}
+
 /* Free all buffers from the pool */
 static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
 			       struct mvpp2_bm_pool *bm_pool)
@@ -3433,21 +3749,21 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
 	int i;
 
 	for (i = 0; i < bm_pool->buf_num; i++) {
-		dma_addr_t buf_phys_addr;
-		unsigned long vaddr;
+		dma_addr_t buf_dma_addr;
+		phys_addr_t buf_phys_addr;
+		void *data;
 
-		/* Get buffer virtual address (indirect access) */
-		buf_phys_addr = mvpp2_read(priv,
-					   MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
-		vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG);
+		mvpp2_bm_bufs_get_addrs(dev, priv, bm_pool,
+					&buf_dma_addr, &buf_phys_addr);
 
-		dma_unmap_single(dev, buf_phys_addr,
+		dma_unmap_single(dev, buf_dma_addr,
 				 bm_pool->buf_size, DMA_FROM_DEVICE);
 
-		if (!vaddr)
+		data = (void *)phys_to_virt(buf_phys_addr);
+		if (!data)
 			break;
 
-		mvpp2_frag_free(bm_pool, (void *)vaddr);
+		mvpp2_frag_free(bm_pool, data);
 	}
 
 	/* Update BM driver with number of buffers removed from pool */
@@ -3471,9 +3787,9 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev,
 	val |= MVPP2_BM_STOP_MASK;
 	mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val);
 
-	dma_free_coherent(&pdev->dev, sizeof(u32) * bm_pool->size,
+	dma_free_coherent(&pdev->dev, bm_pool->size_bytes,
 			  bm_pool->virt_addr,
-			  bm_pool->phys_addr);
+			  bm_pool->dma_addr);
 	return 0;
 }
 
@@ -3515,7 +3831,7 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv)
 
 	/* Allocate and initialize BM pools */
 	priv->bm_pools = devm_kcalloc(&pdev->dev, MVPP2_BM_POOLS_NUM,
-				     sizeof(struct mvpp2_bm_pool), GFP_KERNEL);
+				      sizeof(*priv->bm_pools), GFP_KERNEL);
 	if (!priv->bm_pools)
 		return -ENOMEM;
 
@@ -3529,17 +3845,20 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv)
 static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port,
 				    int lrxq, int long_pool)
 {
-	u32 val;
+	u32 val, mask;
 	int prxq;
 
 	/* Get queue physical ID */
 	prxq = port->rxqs[lrxq]->id;
 
-	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
-	val &= ~MVPP2_RXQ_POOL_LONG_MASK;
-	val |= ((long_pool << MVPP2_RXQ_POOL_LONG_OFFS) &
-		    MVPP2_RXQ_POOL_LONG_MASK);
+	if (port->priv->hw_version == MVPP21)
+		mask = MVPP21_RXQ_POOL_LONG_MASK;
+	else
+		mask = MVPP22_RXQ_POOL_LONG_MASK;
 
+	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
+	val &= ~mask;
+	val |= (long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & mask;
 	mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val);
 }
 
@@ -3547,40 +3866,45 @@ static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port,
 static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port,
 				     int lrxq, int short_pool)
 {
-	u32 val;
+	u32 val, mask;
 	int prxq;
 
 	/* Get queue physical ID */
 	prxq = port->rxqs[lrxq]->id;
 
-	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
-	val &= ~MVPP2_RXQ_POOL_SHORT_MASK;
-	val |= ((short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) &
-		    MVPP2_RXQ_POOL_SHORT_MASK);
+	if (port->priv->hw_version == MVPP21)
+		mask = MVPP21_RXQ_POOL_SHORT_MASK;
+	else
+		mask = MVPP22_RXQ_POOL_SHORT_MASK;
 
+	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
+	val &= ~mask;
+	val |= (short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & mask;
 	mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val);
 }
 
 static void *mvpp2_buf_alloc(struct mvpp2_port *port,
 			     struct mvpp2_bm_pool *bm_pool,
-			     dma_addr_t *buf_phys_addr,
+			     dma_addr_t *buf_dma_addr,
+			     phys_addr_t *buf_phys_addr,
 			     gfp_t gfp_mask)
 {
-	dma_addr_t phys_addr;
+	dma_addr_t dma_addr;
 	void *data;
 
 	data = mvpp2_frag_alloc(bm_pool);
 	if (!data)
 		return NULL;
 
-	phys_addr = dma_map_single(port->dev->dev.parent, data,
-				   MVPP2_RX_BUF_SIZE(bm_pool->pkt_size),
-				    DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(port->dev->dev.parent, phys_addr))) {
+	dma_addr = dma_map_single(port->dev->dev.parent, data,
+				  MVPP2_RX_BUF_SIZE(bm_pool->pkt_size),
+				  DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(port->dev->dev.parent, dma_addr))) {
 		mvpp2_frag_free(bm_pool, data);
 		return NULL;
 	}
-	*buf_phys_addr = phys_addr;
+	*buf_dma_addr = dma_addr;
+	*buf_phys_addr = virt_to_phys(data);
 
 	return data;
 }
@@ -3604,37 +3928,46 @@ static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie)
 
 /* Release buffer to BM */
 static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool,
-				     dma_addr_t buf_phys_addr,
-				     unsigned long buf_virt_addr)
+				     dma_addr_t buf_dma_addr,
+				     phys_addr_t buf_phys_addr)
 {
-	mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_virt_addr);
-	mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_phys_addr);
-}
+	int cpu = smp_processor_id();
 
-/* Release multicast buffer */
-static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool,
-				 dma_addr_t buf_phys_addr,
-				 unsigned long buf_virt_addr,
-				 int mc_id)
-{
-	u32 val = 0;
+	if (port->priv->hw_version == MVPP22) {
+		u32 val = 0;
+
+		if (sizeof(dma_addr_t) == 8)
+			val |= upper_32_bits(buf_dma_addr) &
+				MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK;
 
-	val |= (mc_id & MVPP2_BM_MC_ID_MASK);
-	mvpp2_write(port->priv, MVPP2_BM_MC_RLS_REG, val);
+		if (sizeof(phys_addr_t) == 8)
+			val |= (upper_32_bits(buf_phys_addr)
+				<< MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) &
+				MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK;
 
-	mvpp2_bm_pool_put(port, pool,
-			  buf_phys_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK,
-			  buf_virt_addr);
+		mvpp2_percpu_write(port->priv, cpu,
+				   MVPP22_BM_ADDR_HIGH_RLS_REG, val);
+	}
+
+	/* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply
+	 * returned in the "cookie" field of the RX
+	 * descriptor. Instead of storing the virtual address, we
+	 * store the physical address
+	 */
+	mvpp2_percpu_write(port->priv, cpu,
+			   MVPP2_BM_VIRT_RLS_REG, buf_phys_addr);
+	mvpp2_percpu_write(port->priv, cpu,
+			   MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr);
 }
 
 /* Refill BM pool */
 static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm,
-			      dma_addr_t phys_addr,
-			      unsigned long cookie)
+			      dma_addr_t dma_addr,
+			      phys_addr_t phys_addr)
 {
 	int pool = mvpp2_bm_cookie_pool_get(bm);
 
-	mvpp2_bm_pool_put(port, pool, phys_addr, cookie);
+	mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr);
 }
 
 /* Allocate buffers for the pool */
@@ -3642,7 +3975,8 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port,
 			     struct mvpp2_bm_pool *bm_pool, int buf_num)
 {
 	int i, buf_size, total_size;
-	dma_addr_t phys_addr;
+	dma_addr_t dma_addr;
+	phys_addr_t phys_addr;
 	void *buf;
 
 	buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size);
@@ -3657,12 +3991,13 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port,
 	}
 
 	for (i = 0; i < buf_num; i++) {
-		buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_KERNEL);
+		buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr,
+				      &phys_addr, GFP_KERNEL);
 		if (!buf)
 			break;
 
-		mvpp2_bm_pool_put(port, bm_pool->id, phys_addr,
-				  (unsigned long)buf);
+		mvpp2_bm_pool_put(port, bm_pool->id, dma_addr,
+				  phys_addr);
 	}
 
 	/* Update BM driver with number of buffers added to pool */
@@ -3830,7 +4165,8 @@ static void mvpp2_interrupts_mask(void *arg)
 {
 	struct mvpp2_port *port = arg;
 
-	mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), 0);
+	mvpp2_percpu_write(port->priv, smp_processor_id(),
+			   MVPP2_ISR_RX_TX_MASK_REG(port->id), 0);
 }
 
 /* Unmask the current CPU's Rx/Tx interrupts */
@@ -3838,17 +4174,46 @@ static void mvpp2_interrupts_unmask(void *arg)
 {
 	struct mvpp2_port *port = arg;
 
-	mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id),
-		    (MVPP2_CAUSE_MISC_SUM_MASK |
-		     MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
+	mvpp2_percpu_write(port->priv, smp_processor_id(),
+			   MVPP2_ISR_RX_TX_MASK_REG(port->id),
+			   (MVPP2_CAUSE_MISC_SUM_MASK |
+			    MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
 }
 
 /* Port configuration routines */
 
+static void mvpp22_port_mii_set(struct mvpp2_port *port)
+{
+	u32 val;
+
+	return;
+
+	/* Only GOP port 0 has an XLG MAC */
+	if (port->gop_id == 0) {
+		val = readl(port->base + MVPP22_XLG_CTRL3_REG);
+		val &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
+		val |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
+		writel(val, port->base + MVPP22_XLG_CTRL3_REG);
+	}
+
+	val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
+	if (port->phy_interface == PHY_INTERFACE_MODE_RGMII)
+		val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+	else
+		val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+	val &= ~MVPP22_CTRL4_DP_CLK_SEL;
+	val |= MVPP22_CTRL4_SYNC_BYPASS;
+	val |= MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+	writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
+}
+
 static void mvpp2_port_mii_set(struct mvpp2_port *port)
 {
 	u32 val;
 
+	if (port->priv->hw_version == MVPP22)
+		mvpp22_port_mii_set(port);
+
 	val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
 
 	switch (port->phy_interface) {
@@ -3952,16 +4317,18 @@ static void mvpp2_defaults_set(struct mvpp2_port *port)
 {
 	int tx_port_num, val, queue, ptxq, lrxq;
 
-	/* Configure port to loopback if needed */
-	if (port->flags & MVPP2_F_LOOPBACK)
-		mvpp2_port_loopback_set(port);
+	if (port->priv->hw_version == MVPP21) {
+		/* Configure port to loopback if needed */
+		if (port->flags & MVPP2_F_LOOPBACK)
+			mvpp2_port_loopback_set(port);
 
-	/* Update TX FIFO MIN Threshold */
-	val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
-	val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
-	/* Min. TX threshold must be less than minimal packet length */
-	val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2);
-	writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+		/* Update TX FIFO MIN Threshold */
+		val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+		val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
+		/* Min. TX threshold must be less than minimal packet length */
+		val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2);
+		writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+	}
 
 	/* Disable Legacy WRR, Disable EJP, Release from reset */
 	tx_port_num = mvpp2_egress_port(port);
@@ -4048,7 +4415,7 @@ static void mvpp2_egress_enable(struct mvpp2_port *port)
 	for (queue = 0; queue < txq_number; queue++) {
 		struct mvpp2_tx_queue *txq = port->txqs[queue];
 
-		if (txq->descs != NULL)
+		if (txq->descs)
 			qmap |= (1 << queue);
 	}
 
@@ -4149,11 +4516,15 @@ static void mvpp2_rxq_offset_set(struct mvpp2_port *port,
 }
 
 /* Obtain BM cookie information from descriptor */
-static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc)
+static u32 mvpp2_bm_cookie_build(struct mvpp2_port *port,
+				 struct mvpp2_rx_desc *rx_desc)
 {
-	int pool = (rx_desc->status & MVPP2_RXD_BM_POOL_ID_MASK) >>
-		   MVPP2_RXD_BM_POOL_ID_OFFS;
 	int cpu = smp_processor_id();
+	int pool;
+
+	pool = (mvpp2_rxdesc_status_get(port, rx_desc) &
+		MVPP2_RXD_BM_POOL_ID_MASK) >>
+		MVPP2_RXD_BM_POOL_ID_OFFS;
 
 	return ((pool & 0xFF) << MVPP2_BM_COOKIE_POOL_OFFS) |
 	       ((cpu & 0xFF) << MVPP2_BM_COOKIE_CPU_OFFS);
@@ -4161,18 +4532,6 @@ static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc)
 
 /* Tx descriptors helper methods */
 
-/* Get number of Tx descriptors waiting to be transmitted by HW */
-static int mvpp2_txq_pend_desc_num_get(struct mvpp2_port *port,
-				       struct mvpp2_tx_queue *txq)
-{
-	u32 val;
-
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG);
-
-	return val & MVPP2_TXQ_PENDING_MASK;
-}
-
 /* Get pointer to next Tx descriptor to be processed (send) by HW */
 static struct mvpp2_tx_desc *
 mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq)
@@ -4187,7 +4546,8 @@ mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq)
 static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending)
 {
 	/* aggregated access - relevant TXQ number is written in TX desc */
-	mvpp2_write(port->priv, MVPP2_AGGR_TXQ_UPDATE_REG, pending);
+	mvpp2_percpu_write(port->priv, smp_processor_id(),
+			   MVPP2_AGGR_TXQ_UPDATE_REG, pending);
 }
 
 
@@ -4216,11 +4576,12 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv,
 					 struct mvpp2_tx_queue *txq, int num)
 {
 	u32 val;
+	int cpu = smp_processor_id();
 
 	val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num;
-	mvpp2_write(priv, MVPP2_TXQ_RSVD_REQ_REG, val);
+	mvpp2_percpu_write(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val);
 
-	val = mvpp2_read(priv, MVPP2_TXQ_RSVD_RSLT_REG);
+	val = mvpp2_percpu_read(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG);
 
 	return val & MVPP2_TXQ_RSVD_RSLT_MASK;
 }
@@ -4321,7 +4682,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port,
 	u32 val;
 
 	/* Reading status reg resets transmitted descriptor counter */
-	val = mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(txq->id));
+	val = mvpp2_percpu_read(port->priv, smp_processor_id(),
+				MVPP2_TXQ_SENT_REG(txq->id));
 
 	return (val & MVPP2_TRANSMITTED_COUNT_MASK) >>
 		MVPP2_TRANSMITTED_COUNT_OFFSET;
@@ -4335,7 +4697,8 @@ static void mvpp2_txq_sent_counter_clear(void *arg)
 	for (queue = 0; queue < txq_number; queue++) {
 		int id = port->txqs[queue]->id;
 
-		mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(id));
+		mvpp2_percpu_read(port->priv, smp_processor_id(),
+				  MVPP2_TXQ_SENT_REG(id));
 	}
 }
 
@@ -4394,12 +4757,14 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port)
 static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port,
 				   struct mvpp2_rx_queue *rxq)
 {
+	int cpu = smp_processor_id();
+
 	if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK)
 		rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK;
 
-	mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
-	mvpp2_write(port->priv, MVPP2_RXQ_THRESH_REG,
-		    rxq->pkts_coal);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG,
+			   rxq->pkts_coal);
 }
 
 static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz)
@@ -4449,7 +4814,7 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 		struct mvpp2_txq_pcpu_buf *tx_buf =
 			txq_pcpu->buffs + txq_pcpu->txq_get_index;
 
-		dma_unmap_single(port->dev->dev.parent, tx_buf->phys,
+		dma_unmap_single(port->dev->dev.parent, tx_buf->dma,
 				 tx_buf->size, DMA_TO_DEVICE);
 		if (tx_buf->skb)
 			dev_kfree_skb_any(tx_buf->skb);
@@ -4527,10 +4892,12 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 			       int desc_num, int cpu,
 			       struct mvpp2 *priv)
 {
+	u32 txq_dma;
+
 	/* Allocate memory for TX descriptors */
 	aggr_txq->descs = dma_alloc_coherent(&pdev->dev,
 				desc_num * MVPP2_DESC_ALIGNED_SIZE,
-				&aggr_txq->descs_phys, GFP_KERNEL);
+				&aggr_txq->descs_dma, GFP_KERNEL);
 	if (!aggr_txq->descs)
 		return -ENOMEM;
 
@@ -4540,10 +4907,16 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 	aggr_txq->next_desc_to_proc = mvpp2_read(priv,
 						 MVPP2_AGGR_TXQ_INDEX_REG(cpu));
 
-	/* Set Tx descriptors queue starting address */
-	/* indirect access */
-	mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu),
-		    aggr_txq->descs_phys);
+	/* Set Tx descriptors queue starting address indirect
+	 * access
+	 */
+	if (priv->hw_version == MVPP21)
+		txq_dma = aggr_txq->descs_dma;
+	else
+		txq_dma = aggr_txq->descs_dma >>
+			MVPP22_AGGR_TXQ_DESC_ADDR_OFFS;
+
+	mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma);
 	mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num);
 
 	return 0;
@@ -4554,12 +4927,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
 			  struct mvpp2_rx_queue *rxq)
 
 {
+	u32 rxq_dma;
+	int cpu;
+
 	rxq->size = port->rx_ring_size;
 
 	/* Allocate memory for RX descriptors */
 	rxq->descs = dma_alloc_coherent(port->dev->dev.parent,
 					rxq->size * MVPP2_DESC_ALIGNED_SIZE,
-					&rxq->descs_phys, GFP_KERNEL);
+					&rxq->descs_dma, GFP_KERNEL);
 	if (!rxq->descs)
 		return -ENOMEM;
 
@@ -4569,10 +4945,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
 	mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0);
 
 	/* Set Rx descriptors queue starting address - indirect access */
-	mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_phys);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size);
-	mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+	if (port->priv->hw_version == MVPP21)
+		rxq_dma = rxq->descs_dma;
+	else
+		rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS;
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0);
 
 	/* Set Offset */
 	mvpp2_rxq_offset_set(port, rxq->id, NET_SKB_PAD);
@@ -4599,10 +4980,11 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port,
 
 	for (i = 0; i < rx_received; i++) {
 		struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
-		u32 bm = mvpp2_bm_cookie_build(rx_desc);
+		u32 bm = mvpp2_bm_cookie_build(port, rx_desc);
 
-		mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
-				  rx_desc->buf_cookie);
+		mvpp2_pool_refill(port, bm,
+				  mvpp2_rxdesc_dma_addr_get(port, rx_desc),
+				  mvpp2_rxdesc_cookie_get(port, rx_desc));
 	}
 	mvpp2_rxq_status_update(port, rxq->id, rx_received, rx_received);
 }
@@ -4611,26 +4993,29 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port,
 static void mvpp2_rxq_deinit(struct mvpp2_port *port,
 			     struct mvpp2_rx_queue *rxq)
 {
+	int cpu;
+
 	mvpp2_rxq_drop_pkts(port, rxq);
 
 	if (rxq->descs)
 		dma_free_coherent(port->dev->dev.parent,
 				  rxq->size * MVPP2_DESC_ALIGNED_SIZE,
 				  rxq->descs,
-				  rxq->descs_phys);
+				  rxq->descs_dma);
 
 	rxq->descs             = NULL;
 	rxq->last_desc         = 0;
 	rxq->next_desc_to_proc = 0;
-	rxq->descs_phys        = 0;
+	rxq->descs_dma         = 0;
 
 	/* Clear Rx descriptors queue starting address and size;
 	 * free descriptor number
 	 */
 	mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0);
-	mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, 0);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, 0);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0);
 }
 
 /* Create and initialize a Tx queue */
@@ -4646,23 +5031,25 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	/* Allocate memory for Tx descriptors */
 	txq->descs = dma_alloc_coherent(port->dev->dev.parent,
 				txq->size * MVPP2_DESC_ALIGNED_SIZE,
-				&txq->descs_phys, GFP_KERNEL);
+				&txq->descs_dma, GFP_KERNEL);
 	if (!txq->descs)
 		return -ENOMEM;
 
 	txq->last_desc = txq->size - 1;
 
 	/* Set Tx descriptors queue starting address - indirect access */
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_phys);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, txq->size &
-					     MVPP2_TXQ_DESC_SIZE_MASK);
-	mvpp2_write(port->priv, MVPP2_TXQ_INDEX_REG, 0);
-	mvpp2_write(port->priv, MVPP2_TXQ_RSVD_CLR_REG,
-		    txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET);
-	val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG,
+			   txq->descs_dma);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG,
+			   txq->size & MVPP2_TXQ_DESC_SIZE_MASK);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_INDEX_REG, 0);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_RSVD_CLR_REG,
+			   txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET);
+	val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PENDING_REG);
 	val &= ~MVPP2_TXQ_PENDING_MASK;
-	mvpp2_write(port->priv, MVPP2_TXQ_PENDING_REG, val);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PENDING_REG, val);
 
 	/* Calculate base address in prefetch buffer. We reserve 16 descriptors
 	 * for each existing TXQ.
@@ -4673,9 +5060,9 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) +
 	       (txq->log_id * desc_per_txq);
 
-	mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG,
-		    MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 |
-		    MVPP2_PREF_BUF_THRESH(desc_per_txq/2));
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG,
+			   MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 |
+			   MVPP2_PREF_BUF_THRESH(desc_per_txq / 2));
 
 	/* WRR / EJP configuration - indirect access */
 	tx_port_num = mvpp2_egress_port(port);
@@ -4694,11 +5081,11 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
 		txq_pcpu->size = txq->size;
-		txq_pcpu->buffs = kmalloc(txq_pcpu->size *
-					  sizeof(struct mvpp2_txq_pcpu_buf),
-					  GFP_KERNEL);
+		txq_pcpu->buffs = kmalloc_array(txq_pcpu->size,
+						sizeof(*txq_pcpu->buffs),
+						GFP_KERNEL);
 		if (!txq_pcpu->buffs)
-			goto error;
+			goto cleanup;
 
 		txq_pcpu->count = 0;
 		txq_pcpu->reserved_num = 0;
@@ -4707,8 +5094,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	}
 
 	return 0;
-
-error:
+cleanup:
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
 		kfree(txq_pcpu->buffs);
@@ -4716,7 +5102,7 @@ error:
 
 	dma_free_coherent(port->dev->dev.parent,
 			  txq->size * MVPP2_DESC_ALIGNED_SIZE,
-			  txq->descs, txq->descs_phys);
+			  txq->descs, txq->descs_dma);
 
 	return -ENOMEM;
 }
@@ -4736,20 +5122,21 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
 	if (txq->descs)
 		dma_free_coherent(port->dev->dev.parent,
 				  txq->size * MVPP2_DESC_ALIGNED_SIZE,
-				  txq->descs, txq->descs_phys);
+				  txq->descs, txq->descs_dma);
 
 	txq->descs             = NULL;
 	txq->last_desc         = 0;
 	txq->next_desc_to_proc = 0;
-	txq->descs_phys        = 0;
+	txq->descs_dma         = 0;
 
 	/* Set minimum bandwidth for disabled TXQs */
 	mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0);
 
 	/* Set Tx descriptors queue starting address and size */
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, 0);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, 0);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0);
 }
 
 /* Cleanup Tx ports */
@@ -4759,10 +5146,11 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq)
 	int delay, pending, cpu;
 	u32 val;
 
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	val = mvpp2_read(port->priv, MVPP2_TXQ_PREF_BUF_REG);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+	val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG);
 	val |= MVPP2_TXQ_DRAIN_EN_MASK;
-	mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val);
 
 	/* The napi queue has been stopped so wait for all packets
 	 * to be transmitted.
@@ -4778,11 +5166,13 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq)
 		mdelay(1);
 		delay++;
 
-		pending = mvpp2_txq_pend_desc_num_get(port, txq);
+		pending = mvpp2_percpu_read(port->priv, cpu,
+					    MVPP2_TXQ_PENDING_REG);
+		pending &= MVPP2_TXQ_PENDING_MASK;
 	} while (pending);
 
 	val &= ~MVPP2_TXQ_DRAIN_EN_MASK;
-	mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val);
 
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
@@ -4991,20 +5381,21 @@ static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
 static void mvpp2_rx_error(struct mvpp2_port *port,
 			   struct mvpp2_rx_desc *rx_desc)
 {
-	u32 status = rx_desc->status;
+	u32 status = mvpp2_rxdesc_status_get(port, rx_desc);
+	size_t sz = mvpp2_rxdesc_size_get(port, rx_desc);
 
 	switch (status & MVPP2_RXD_ERR_CODE_MASK) {
 	case MVPP2_RXD_ERR_CRC:
-		netdev_err(port->dev, "bad rx status %08x (crc error), size=%d\n",
-			   status, rx_desc->data_size);
+		netdev_err(port->dev, "bad rx status %08x (crc error), size=%zu\n",
+			   status, sz);
 		break;
 	case MVPP2_RXD_ERR_OVERRUN:
-		netdev_err(port->dev, "bad rx status %08x (overrun error), size=%d\n",
-			   status, rx_desc->data_size);
+		netdev_err(port->dev, "bad rx status %08x (overrun error), size=%zu\n",
+			   status, sz);
 		break;
 	case MVPP2_RXD_ERR_RESOURCE:
-		netdev_err(port->dev, "bad rx status %08x (resource error), size=%d\n",
-			   status, rx_desc->data_size);
+		netdev_err(port->dev, "bad rx status %08x (resource error), size=%zu\n",
+			   status, sz);
 		break;
 	}
 }
@@ -5031,15 +5422,17 @@ static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status,
 static int mvpp2_rx_refill(struct mvpp2_port *port,
 			   struct mvpp2_bm_pool *bm_pool, u32 bm)
 {
-	dma_addr_t phys_addr;
+	dma_addr_t dma_addr;
+	phys_addr_t phys_addr;
 	void *buf;
 
 	/* No recycle or too many buffers are in use, so allocate a new skb */
-	buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_ATOMIC);
+	buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, &phys_addr,
+			      GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
-	mvpp2_pool_refill(port, bm, phys_addr, (unsigned long)buf);
+	mvpp2_pool_refill(port, bm, dma_addr, phys_addr);
 
 	return 0;
 }
@@ -5075,43 +5468,6 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb)
 	return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE;
 }
 
-static void mvpp2_buff_hdr_rx(struct mvpp2_port *port,
-			      struct mvpp2_rx_desc *rx_desc)
-{
-	struct mvpp2_buff_hdr *buff_hdr;
-	struct sk_buff *skb;
-	u32 rx_status = rx_desc->status;
-	dma_addr_t buff_phys_addr;
-	unsigned long buff_virt_addr;
-	dma_addr_t buff_phys_addr_next;
-	unsigned long buff_virt_addr_next;
-	int mc_id;
-	int pool_id;
-
-	pool_id = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >>
-		   MVPP2_RXD_BM_POOL_ID_OFFS;
-	buff_phys_addr = rx_desc->buf_phys_addr;
-	buff_virt_addr = rx_desc->buf_cookie;
-
-	do {
-		skb = (struct sk_buff *)buff_virt_addr;
-		buff_hdr = (struct mvpp2_buff_hdr *)skb->head;
-
-		mc_id = MVPP2_B_HDR_INFO_MC_ID(buff_hdr->info);
-
-		buff_phys_addr_next = buff_hdr->next_buff_phys_addr;
-		buff_virt_addr_next = buff_hdr->next_buff_virt_addr;
-
-		/* Release buffer */
-		mvpp2_bm_pool_mc_put(port, pool_id, buff_phys_addr,
-				     buff_virt_addr, mc_id);
-
-		buff_phys_addr = buff_phys_addr_next;
-		buff_virt_addr = buff_virt_addr_next;
-
-	} while (!MVPP2_B_HDR_INFO_IS_LAST(buff_hdr->info));
-}
-
 /* Main rx processing */
 static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		    struct mvpp2_rx_queue *rxq)
@@ -5132,25 +5488,23 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		struct mvpp2_bm_pool *bm_pool;
 		struct sk_buff *skb;
 		unsigned int frag_size;
-		dma_addr_t phys_addr;
+		dma_addr_t dma_addr;
+		phys_addr_t phys_addr;
 		u32 bm, rx_status;
 		int pool, rx_bytes, err;
 		void *data;
 
 		rx_done++;
-		rx_status = rx_desc->status;
-		rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE;
-		phys_addr = rx_desc->buf_phys_addr;
-		data = (void *)(uintptr_t)rx_desc->buf_cookie;
-
-		bm = mvpp2_bm_cookie_build(rx_desc);
+		rx_status = mvpp2_rxdesc_status_get(port, rx_desc);
+		rx_bytes = mvpp2_rxdesc_size_get(port, rx_desc);
+		rx_bytes -= MVPP2_MH_SIZE;
+		dma_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc);
+		phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc);
+		data = (void *)phys_to_virt(phys_addr);
+
+		bm = mvpp2_bm_cookie_build(port, rx_desc);
 		pool = mvpp2_bm_cookie_pool_get(bm);
 		bm_pool = &port->priv->bm_pools[pool];
-		/* Check if buffer header is used */
-		if (rx_status & MVPP2_RXD_BUF_HDR) {
-			mvpp2_buff_hdr_rx(port, rx_desc);
-			continue;
-		}
 
 		/* In case of an error, release the requested buffer pointer
 		 * to the Buffer Manager. This request process is controlled
@@ -5158,13 +5512,11 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		 * comprised by the RX descriptor.
 		 */
 		if (rx_status & MVPP2_RXD_ERR_SUMMARY) {
-		err_drop_frame:
+err_drop_frame:
 			dev->stats.rx_errors++;
 			mvpp2_rx_error(port, rx_desc);
 			/* Return the buffer to the pool */
-
-			mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
-					  rx_desc->buf_cookie);
+			mvpp2_pool_refill(port, bm, dma_addr, phys_addr);
 			continue;
 		}
 
@@ -5185,7 +5537,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 			goto err_drop_frame;
 		}
 
-		dma_unmap_single(dev->dev.parent, phys_addr,
+		dma_unmap_single(dev->dev.parent, dma_addr,
 				 bm_pool->buf_size, DMA_FROM_DEVICE);
 
 		rcvd_pkts++;
@@ -5216,11 +5568,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 }
 
 static inline void
-tx_desc_unmap_put(struct device *dev, struct mvpp2_tx_queue *txq,
+tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq,
 		  struct mvpp2_tx_desc *desc)
 {
-	dma_unmap_single(dev, desc->buf_phys_addr,
-			 desc->data_size, DMA_TO_DEVICE);
+	dma_addr_t buf_dma_addr =
+		mvpp2_txdesc_dma_addr_get(port, desc);
+	size_t buf_sz =
+		mvpp2_txdesc_size_get(port, desc);
+	dma_unmap_single(port->dev->dev.parent, buf_dma_addr,
+			 buf_sz, DMA_TO_DEVICE);
 	mvpp2_txq_desc_put(txq);
 }
 
@@ -5232,47 +5588,49 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb,
 	struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu);
 	struct mvpp2_tx_desc *tx_desc;
 	int i;
-	dma_addr_t buf_phys_addr;
+	dma_addr_t buf_dma_addr;
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		void *addr = page_address(frag->page.p) + frag->page_offset;
 
 		tx_desc = mvpp2_txq_next_desc_get(aggr_txq);
-		tx_desc->phys_txq = txq->id;
-		tx_desc->data_size = frag->size;
+		mvpp2_txdesc_txq_set(port, tx_desc, txq->id);
+		mvpp2_txdesc_size_set(port, tx_desc, frag->size);
 
-		buf_phys_addr = dma_map_single(port->dev->dev.parent, addr,
-					       tx_desc->data_size,
+		buf_dma_addr = dma_map_single(port->dev->dev.parent, addr,
+					       frag->size,
 					       DMA_TO_DEVICE);
-		if (dma_mapping_error(port->dev->dev.parent, buf_phys_addr)) {
+		if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) {
 			mvpp2_txq_desc_put(txq);
-			goto error;
+			goto cleanup;
 		}
 
-		tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN;
-		tx_desc->buf_phys_addr = buf_phys_addr & (~MVPP2_TX_DESC_ALIGN);
+		mvpp2_txdesc_offset_set(port, tx_desc,
+					buf_dma_addr & MVPP2_TX_DESC_ALIGN);
+		mvpp2_txdesc_dma_addr_set(port, tx_desc,
+					  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
 
 		if (i == (skb_shinfo(skb)->nr_frags - 1)) {
 			/* Last descriptor */
-			tx_desc->command = MVPP2_TXD_L_DESC;
-			mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
+			mvpp2_txdesc_cmd_set(port, tx_desc,
+					     MVPP2_TXD_L_DESC);
+			mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc);
 		} else {
 			/* Descriptor in the middle: Not First, Not Last */
-			tx_desc->command = 0;
-			mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
+			mvpp2_txdesc_cmd_set(port, tx_desc, 0);
+			mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc);
 		}
 	}
 
 	return 0;
-
-error:
+cleanup:
 	/* Release all descriptors that were used to map fragments of
 	 * this packet, as well as the corresponding DMA mappings
 	 */
 	for (i = i - 1; i >= 0; i--) {
 		tx_desc = txq->descs + i;
-		tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc);
+		tx_desc_unmap_put(port, txq, tx_desc);
 	}
 
 	return -ENOMEM;
@@ -5285,7 +5643,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
 	struct mvpp2_tx_queue *txq, *aggr_txq;
 	struct mvpp2_txq_pcpu *txq_pcpu;
 	struct mvpp2_tx_desc *tx_desc;
-	dma_addr_t buf_phys_addr;
+	dma_addr_t buf_dma_addr;
 	int frags = 0;
 	u16 txq_id;
 	u32 tx_cmd;
@@ -5307,35 +5665,38 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
 
 	/* Get a descriptor for the first part of the packet */
 	tx_desc = mvpp2_txq_next_desc_get(aggr_txq);
-	tx_desc->phys_txq = txq->id;
-	tx_desc->data_size = skb_headlen(skb);
+	mvpp2_txdesc_txq_set(port, tx_desc, txq->id);
+	mvpp2_txdesc_size_set(port, tx_desc, skb_headlen(skb));
 
-	buf_phys_addr = dma_map_single(dev->dev.parent, skb->data,
-				       tx_desc->data_size, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(dev->dev.parent, buf_phys_addr))) {
+	buf_dma_addr = dma_map_single(dev->dev.parent, skb->data,
+				      skb_headlen(skb), DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) {
 		mvpp2_txq_desc_put(txq);
 		frags = 0;
 		goto out;
 	}
-	tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN;
-	tx_desc->buf_phys_addr = buf_phys_addr & ~MVPP2_TX_DESC_ALIGN;
+
+	mvpp2_txdesc_offset_set(port, tx_desc,
+				buf_dma_addr & MVPP2_TX_DESC_ALIGN);
+	mvpp2_txdesc_dma_addr_set(port, tx_desc,
+				  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
 
 	tx_cmd = mvpp2_skb_tx_csum(port, skb);
 
 	if (frags == 1) {
 		/* First and Last descriptor */
 		tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC;
-		tx_desc->command = tx_cmd;
-		mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
+		mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd);
+		mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc);
 	} else {
 		/* First but not Last */
 		tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE;
-		tx_desc->command = tx_cmd;
-		mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
+		mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd);
+		mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc);
 
 		/* Continue with other skb fragments */
 		if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
-			tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc);
+			tx_desc_unmap_put(port, txq, tx_desc);
 			frags = 0;
 			goto out;
 		}
@@ -5396,6 +5757,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 	u32 cause_rx_tx, cause_rx, cause_misc;
 	int rx_done = 0;
 	struct mvpp2_port *port = netdev_priv(napi->dev);
+	int cpu = smp_processor_id();
 
 	/* Rx/Tx cause register
 	 *
@@ -5407,8 +5769,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 	 *
 	 * Each CPU has its own Rx/Tx cause register
 	 */
-	cause_rx_tx = mvpp2_read(port->priv,
-				 MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
+	cause_rx_tx = mvpp2_percpu_read(port->priv, cpu,
+					MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
 	cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
 	cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK;
 
@@ -5417,8 +5779,9 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 
 		/* Clear the cause register */
 		mvpp2_write(port->priv, MVPP2_ISR_MISC_CAUSE_REG, 0);
-		mvpp2_write(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id),
-			    cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
+		mvpp2_percpu_write(port->priv, cpu,
+				   MVPP2_ISR_RX_TX_CAUSE_REG(port->id),
+				   cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
 	}
 
 	cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK;
@@ -5530,7 +5893,7 @@ static int mvpp2_check_ringparam_valid(struct net_device *dev,
 	return 0;
 }
 
-static void mvpp2_get_mac_address(struct mvpp2_port *port, unsigned char *addr)
+static void mvpp21_get_mac_address(struct mvpp2_port *port, unsigned char *addr)
 {
 	u32 mac_addr_l, mac_addr_m, mac_addr_h;
 
@@ -5698,7 +6061,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p)
 
 	if (!is_valid_ether_addr(addr->sa_data)) {
 		err = -EADDRNOTAVAIL;
-		goto error;
+		goto log_error;
 	}
 
 	if (!netif_running(dev)) {
@@ -5708,7 +6071,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p)
 		/* Reconfigure parser to accept the original MAC address */
 		err = mvpp2_prs_update_mac_da(dev, dev->dev_addr);
 		if (err)
-			goto error;
+			goto log_error;
 	}
 
 	mvpp2_stop_dev(port);
@@ -5720,15 +6083,14 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p)
 	/* Reconfigure parser accept the original MAC address */
 	err = mvpp2_prs_update_mac_da(dev, dev->dev_addr);
 	if (err)
-		goto error;
+		goto log_error;
 out_start:
 	mvpp2_start_dev(port);
 	mvpp2_egress_enable(port);
 	mvpp2_ingress_enable(port);
 	return 0;
-
-error:
-	netdev_err(dev, "fail to change MAC address\n");
+log_error:
+	netdev_err(dev, "failed to change MAC address\n");
 	return err;
 }
 
@@ -5753,7 +6115,7 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 		/* Reconfigure BM to the original MTU */
 		err = mvpp2_bm_update_mtu(dev, dev->mtu);
 		if (err)
-			goto error;
+			goto log_error;
 	}
 
 	mvpp2_stop_dev(port);
@@ -5767,7 +6129,7 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 	/* Reconfigure BM to the original MTU */
 	err = mvpp2_bm_update_mtu(dev, dev->mtu);
 	if (err)
-		goto error;
+		goto log_error;
 
 out_start:
 	mvpp2_start_dev(port);
@@ -5775,9 +6137,8 @@ out_start:
 	mvpp2_ingress_enable(port);
 
 	return 0;
-
-error:
-	netdev_err(dev, "fail to change MTU\n");
+log_error:
+	netdev_err(dev, "failed to change MTU\n");
 	return err;
 }
 
@@ -5946,7 +6307,7 @@ static int mvpp2_ethtool_set_ringparam(struct net_device *dev,
 err_clean_rxqs:
 	mvpp2_cleanup_rxqs(port);
 err_out:
-	netdev_err(dev, "fail to change ring parameters");
+	netdev_err(dev, "failed to change ring parameters");
 	return err;
 }
 
@@ -5975,16 +6336,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
-/* Driver initialization */
-
-static void mvpp2_port_power_up(struct mvpp2_port *port)
-{
-	mvpp2_port_mii_set(port);
-	mvpp2_port_periodic_xon_disable(port);
-	mvpp2_port_fc_adv_enable(port);
-	mvpp2_port_reset(port);
-}
-
 /* Initialize port HW */
 static int mvpp2_port_init(struct mvpp2_port *port)
 {
@@ -5993,7 +6344,8 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	struct mvpp2_txq_pcpu *txq_pcpu;
 	int queue, cpu, err;
 
-	if (port->first_rxq + rxq_number > MVPP2_RXQ_TOTAL_NUM)
+	if (port->first_rxq + rxq_number >
+	    MVPP2_MAX_PORTS * priv->max_port_rxqs)
 		return -EINVAL;
 
 	/* Disable port */
@@ -6061,7 +6413,18 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	}
 
 	/* Configure Rx queue group interrupt for this port */
-	mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(port->id), rxq_number);
+	if (priv->hw_version == MVPP21) {
+		mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id),
+			    rxq_number);
+	} else {
+		u32 val;
+
+		val = (port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET);
+		mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val);
+
+		val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET);
+		mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val);
+	}
 
 	/* Create Rx descriptor rings */
 	for (queue = 0; queue < rxq_number; queue++) {
@@ -6103,8 +6466,7 @@ err_free_percpu:
 /* Ports initialization */
 static int mvpp2_port_probe(struct platform_device *pdev,
 			    struct device_node *port_node,
-			    struct mvpp2 *priv,
-			    int *next_first_rxq)
+			    struct mvpp2 *priv)
 {
 	struct device_node *phy_node;
 	struct mvpp2_port *port;
@@ -6117,11 +6479,9 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	u32 id;
 	int features;
 	int phy_mode;
-	int priv_common_regs_num = 2;
 	int err, i, cpu;
 
-	dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number,
-				 rxq_number);
+	dev = alloc_etherdev_mqs(sizeof(*port), txq_number, rxq_number);
 	if (!dev)
 		return -ENOMEM;
 
@@ -6163,16 +6523,30 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	port->priv = priv;
 	port->id = id;
-	port->first_rxq = *next_first_rxq;
+	if (priv->hw_version == MVPP21)
+		port->first_rxq = port->id * rxq_number;
+	else
+		port->first_rxq = port->id * priv->max_port_rxqs;
+
 	port->phy_node = phy_node;
 	port->phy_interface = phy_mode;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM,
-				    priv_common_regs_num + id);
-	port->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(port->base)) {
-		err = PTR_ERR(port->base);
-		goto err_free_irq;
+	if (priv->hw_version == MVPP21) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id);
+		port->base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(port->base)) {
+			err = PTR_ERR(port->base);
+			goto err_free_irq;
+		}
+	} else {
+		if (of_property_read_u32(port_node, "gop-port-id",
+					 &port->gop_id)) {
+			err = -EINVAL;
+			dev_err(&pdev->dev, "missing gop-port-id value\n");
+			goto err_free_irq;
+		}
+
+		port->base = priv->iface_base + MVPP22_GMAC_BASE(port->gop_id);
 	}
 
 	/* Alloc per-cpu stats */
@@ -6187,7 +6561,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		mac_from = "device tree";
 		ether_addr_copy(dev->dev_addr, dt_mac_addr);
 	} else {
-		mvpp2_get_mac_address(port, hw_mac_addr);
+		if (priv->hw_version == MVPP21)
+			mvpp21_get_mac_address(port, hw_mac_addr);
 		if (is_valid_ether_addr(hw_mac_addr)) {
 			mac_from = "hardware";
 			ether_addr_copy(dev->dev_addr, hw_mac_addr);
@@ -6207,7 +6582,14 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		dev_err(&pdev->dev, "failed to init port %d\n", id);
 		goto err_free_stats;
 	}
-	mvpp2_port_power_up(port);
+
+	mvpp2_port_mii_set(port);
+	mvpp2_port_periodic_xon_disable(port);
+
+	if (priv->hw_version == MVPP21)
+		mvpp2_port_fc_adv_enable(port);
+
+	mvpp2_port_reset(port);
 
 	port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
 	if (!port->pcpu) {
@@ -6245,8 +6627,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	}
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
 
-	/* Increment the first Rx queue number to be used by the next port */
-	*next_first_rxq += rxq_number;
 	priv->port_list[id] = port;
 	return 0;
 
@@ -6330,6 +6710,60 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv)
 	mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
 }
 
+static void mvpp2_axi_init(struct mvpp2 *priv)
+{
+	u32 val, rdval, wrval;
+
+	mvpp2_write(priv, MVPP22_BM_ADDR_HIGH_RLS_REG, 0x0);
+
+	/* AXI Bridge Configuration */
+
+	rdval = MVPP22_AXI_CODE_CACHE_RD_CACHE
+		<< MVPP22_AXI_ATTR_CACHE_OFFS;
+	rdval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_ATTR_DOMAIN_OFFS;
+
+	wrval = MVPP22_AXI_CODE_CACHE_WR_CACHE
+		<< MVPP22_AXI_ATTR_CACHE_OFFS;
+	wrval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_ATTR_DOMAIN_OFFS;
+
+	/* BM */
+	mvpp2_write(priv, MVPP22_AXI_BM_WR_ATTR_REG, wrval);
+	mvpp2_write(priv, MVPP22_AXI_BM_RD_ATTR_REG, rdval);
+
+	/* Descriptors */
+	mvpp2_write(priv, MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG, rdval);
+	mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG, wrval);
+	mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG, rdval);
+	mvpp2_write(priv, MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG, wrval);
+
+	/* Buffer Data */
+	mvpp2_write(priv, MVPP22_AXI_TX_DATA_RD_ATTR_REG, rdval);
+	mvpp2_write(priv, MVPP22_AXI_RX_DATA_WR_ATTR_REG, wrval);
+
+	val = MVPP22_AXI_CODE_CACHE_NON_CACHE
+		<< MVPP22_AXI_CODE_CACHE_OFFS;
+	val |= MVPP22_AXI_CODE_DOMAIN_SYSTEM
+		<< MVPP22_AXI_CODE_DOMAIN_OFFS;
+	mvpp2_write(priv, MVPP22_AXI_RD_NORMAL_CODE_REG, val);
+	mvpp2_write(priv, MVPP22_AXI_WR_NORMAL_CODE_REG, val);
+
+	val = MVPP22_AXI_CODE_CACHE_RD_CACHE
+		<< MVPP22_AXI_CODE_CACHE_OFFS;
+	val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_CODE_DOMAIN_OFFS;
+
+	mvpp2_write(priv, MVPP22_AXI_RD_SNOOP_CODE_REG, val);
+
+	val = MVPP22_AXI_CODE_CACHE_WR_CACHE
+		<< MVPP22_AXI_CODE_CACHE_OFFS;
+	val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_CODE_DOMAIN_OFFS;
+
+	mvpp2_write(priv, MVPP22_AXI_WR_SNOOP_CODE_REG, val);
+}
+
 /* Initialize network controller common part HW */
 static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 {
@@ -6338,7 +6772,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 	u32 val;
 
 	/* Checks for hardware constraints */
-	if (rxq_number % 4 || (rxq_number > MVPP2_MAX_RXQ) ||
+	if (rxq_number % 4 || (rxq_number > priv->max_port_rxqs) ||
 	    (txq_number > MVPP2_MAX_TXQ)) {
 		dev_err(&pdev->dev, "invalid queue size parameter\n");
 		return -EINVAL;
@@ -6349,14 +6783,23 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 	if (dram_target_info)
 		mvpp2_conf_mbus_windows(dram_target_info, priv);
 
+	if (priv->hw_version == MVPP22)
+		mvpp2_axi_init(priv);
+
 	/* Disable HW PHY polling */
-	val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
-	val |= MVPP2_PHY_AN_STOP_SMI0_MASK;
-	writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+	if (priv->hw_version == MVPP21) {
+		val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+		val |= MVPP2_PHY_AN_STOP_SMI0_MASK;
+		writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+	} else {
+		val = readl(priv->iface_base + MVPP22_SMI_MISC_CFG_REG);
+		val &= ~MVPP22_SMI_POLLING_EN;
+		writel(val, priv->iface_base + MVPP22_SMI_MISC_CFG_REG);
+	}
 
 	/* Allocate and initialize aggregated TXQs */
 	priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(),
-				       sizeof(struct mvpp2_tx_queue),
+				       sizeof(*priv->aggr_txqs),
 				       GFP_KERNEL);
 	if (!priv->aggr_txqs)
 		return -ENOMEM;
@@ -6374,11 +6817,25 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 	mvpp2_rx_fifo_init(priv);
 
 	/* Reset Rx queue group interrupt configuration */
-	for (i = 0; i < MVPP2_MAX_PORTS; i++)
-		mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(i), rxq_number);
+	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+		if (priv->hw_version == MVPP21) {
+			mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(i),
+				    rxq_number);
+			continue;
+		} else {
+			u32 val;
+
+			val = (i << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET);
+			mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val);
+
+			val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET);
+			mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val);
+		}
+	}
 
-	writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
-	       priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG);
+	if (priv->hw_version == MVPP21)
+		writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
+		       priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG);
 
 	/* Allow cache snoop when transmiting packets */
 	mvpp2_write(priv, MVPP2_TX_SNOOP_REG, 0x1);
@@ -6405,22 +6862,46 @@ static int mvpp2_probe(struct platform_device *pdev)
 	struct device_node *port_node;
 	struct mvpp2 *priv;
 	struct resource *res;
-	int port_count, first_rxq;
+	void __iomem *base;
+	int port_count, cpu;
 	int err;
 
-	priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL);
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
+	priv->hw_version =
+		(unsigned long)of_device_get_match_data(&pdev->dev);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(priv->base))
-		return PTR_ERR(priv->base);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	if (priv->hw_version == MVPP21) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		priv->lms_base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(priv->lms_base))
+			return PTR_ERR(priv->lms_base);
+	} else {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		priv->iface_base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(priv->iface_base))
+			return PTR_ERR(priv->iface_base);
+	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	priv->lms_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(priv->lms_base))
-		return PTR_ERR(priv->lms_base);
+	for_each_present_cpu(cpu) {
+		u32 addr_space_sz;
+
+		addr_space_sz = (priv->hw_version == MVPP21 ?
+				 MVPP21_ADDR_SPACE_SZ : MVPP22_ADDR_SPACE_SZ);
+		priv->cpu_base[cpu] = base + cpu * addr_space_sz;
+	}
+
+	if (priv->hw_version == MVPP21)
+		priv->max_port_rxqs = 8;
+	else
+		priv->max_port_rxqs = 32;
 
 	priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk");
 	if (IS_ERR(priv->pp_clk))
@@ -6438,42 +6919,70 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (err < 0)
 		goto err_pp_clk;
 
+	if (priv->hw_version == MVPP22) {
+		priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk");
+		if (IS_ERR(priv->mg_clk)) {
+			err = PTR_ERR(priv->mg_clk);
+			goto err_gop_clk;
+		}
+
+		err = clk_prepare_enable(priv->mg_clk);
+		if (err < 0)
+			goto err_gop_clk;
+	}
+
 	/* Get system's tclk rate */
 	priv->tclk = clk_get_rate(priv->pp_clk);
 
+	if (priv->hw_version == MVPP22) {
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+		if (err)
+			goto err_mg_clk;
+		/* Sadly, the BM pools all share the same register to
+		 * store the high 32 bits of their address. So they
+		 * must all have the same high 32 bits, which forces
+		 * us to restrict coherent memory to DMA_BIT_MASK(32).
+		 */
+		err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+		if (err)
+			goto err_mg_clk;
+	}
+
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to initialize controller\n");
-		goto err_gop_clk;
+		goto err_mg_clk;
 	}
 
 	port_count = of_get_available_child_count(dn);
 	if (port_count == 0) {
 		dev_err(&pdev->dev, "no ports enabled\n");
 		err = -ENODEV;
-		goto err_gop_clk;
+		goto err_mg_clk;
 	}
 
 	priv->port_list = devm_kcalloc(&pdev->dev, port_count,
-				      sizeof(struct mvpp2_port *),
-				      GFP_KERNEL);
+				       sizeof(*priv->port_list),
+				       GFP_KERNEL);
 	if (!priv->port_list) {
 		err = -ENOMEM;
-		goto err_gop_clk;
+		goto err_mg_clk;
 	}
 
 	/* Initialize ports */
-	first_rxq = 0;
 	for_each_available_child_of_node(dn, port_node) {
-		err = mvpp2_port_probe(pdev, port_node, priv, &first_rxq);
+		err = mvpp2_port_probe(pdev, port_node, priv);
 		if (err < 0)
-			goto err_gop_clk;
+			goto err_mg_clk;
 	}
 
 	platform_set_drvdata(pdev, priv);
 	return 0;
 
+err_mg_clk:
+	if (priv->hw_version == MVPP22)
+		clk_disable_unprepare(priv->mg_clk);
 err_gop_clk:
 	clk_disable_unprepare(priv->gop_clk);
 err_pp_clk:
@@ -6506,9 +7015,10 @@ static int mvpp2_remove(struct platform_device *pdev)
 		dma_free_coherent(&pdev->dev,
 				  MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
 				  aggr_txq->descs,
-				  aggr_txq->descs_phys);
+				  aggr_txq->descs_dma);
 	}
 
+	clk_disable_unprepare(priv->mg_clk);
 	clk_disable_unprepare(priv->pp_clk);
 	clk_disable_unprepare(priv->gop_clk);
 
@@ -6516,7 +7026,14 @@ static int mvpp2_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id mvpp2_match[] = {
-	{ .compatible = "marvell,armada-375-pp2" },
+	{
+		.compatible = "marvell,armada-375-pp2",
+		.data = (void *)MVPP21,
+	},
+	{
+		.compatible = "marvell,armada-7k-pp22",
+		.data = (void *)MVPP22,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvpp2_match);
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 28cb36d9e50a..993724959a7c 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -556,11 +556,11 @@ static int init_hash_table(struct pxa168_eth_private *pep)
 	 * function.Driver can dynamically switch to them if the 1/2kB hash
 	 * table is full.
 	 */
-	if (pep->htpr == NULL) {
+	if (!pep->htpr) {
 		pep->htpr = dma_zalloc_coherent(pep->dev->dev.parent,
 						HASH_ADDR_TABLE_SIZE,
 						&pep->htpr_dma, GFP_KERNEL);
-		if (pep->htpr == NULL)
+		if (!pep->htpr)
 			return -ENOMEM;
 	} else {
 		memset(pep->htpr, 0, HASH_ADDR_TABLE_SIZE);
@@ -1036,8 +1036,7 @@ static int rxq_init(struct net_device *dev)
 	int rx_desc_num = pep->rx_ring_size;
 
 	/* Allocate RX skb rings */
-	pep->rx_skb = kzalloc(sizeof(*pep->rx_skb) * pep->rx_ring_size,
-			     GFP_KERNEL);
+	pep->rx_skb = kcalloc(rx_desc_num, sizeof(*pep->rx_skb), GFP_KERNEL);
 	if (!pep->rx_skb)
 		return -ENOMEM;
 
@@ -1096,8 +1095,7 @@ static int txq_init(struct net_device *dev)
 	int size = 0, i = 0;
 	int tx_desc_num = pep->tx_ring_size;
 
-	pep->tx_skb = kzalloc(sizeof(*pep->tx_skb) * pep->tx_ring_size,
-			     GFP_KERNEL);
+	pep->tx_skb = kcalloc(tx_desc_num, sizeof(*pep->tx_skb), GFP_KERNEL);
 	if (!pep->tx_skb)
 		return -ENOMEM;
 
@@ -1358,7 +1356,7 @@ static int pxa168_smi_write(struct mii_bus *bus, int phy_addr, int regnum,
 static int pxa168_eth_do_ioctl(struct net_device *dev, struct ifreq *ifr,
 			       int cmd)
 {
-	if (dev->phydev != NULL)
+	if (dev->phydev)
 		return phy_mii_ioctl(dev->phydev, ifr, cmd);
 
 	return -EOPNOTSUPP;
@@ -1503,7 +1501,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	pep->timeout.data = (unsigned long)pep;
 
 	pep->smi_bus = mdiobus_alloc();
-	if (pep->smi_bus == NULL) {
+	if (!pep->smi_bus) {
 		err = -ENOMEM;
 		goto err_netdev;
 	}
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index edb95271a4f2..5d7d94de4e00 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -2657,7 +2657,7 @@ static int skge_down(struct net_device *dev)
 	struct skge_hw *hw = skge->hw;
 	int port = skge->port;
 
-	if (skge->mem == NULL)
+	if (!skge->mem)
 		return 0;
 
 	netif_info(skge, ifdown, skge->netdev, "disabling interface\n");
@@ -3718,7 +3718,7 @@ static int skge_debug_show(struct seq_file *seq, void *v)
 			   t->csum_offs, t->csum_write, t->csum_start);
 	}
 
-	seq_printf(seq, "\nRx Ring:\n");
+	seq_puts(seq, "\nRx Ring:\n");
 	for (e = skge->rx_ring.to_clean; ; e = e->next) {
 		const struct skge_rx_desc *r = e->desc;
 
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 2b2cc3f3ca10..1145cde2274a 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4544,7 +4544,7 @@ static int sky2_debug_show(struct seq_file *seq, void *v)
 		   sky2_read32(hw, B0_Y2_SP_ICR));
 
 	if (!netif_running(dev)) {
-		seq_printf(seq, "network not running\n");
+		seq_puts(seq, "network not running\n");
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 9e757684816d..16f97552ae98 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -613,7 +613,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
 	struct mtk_tx_dma *itxd, *txd;
-	struct mtk_tx_buf *tx_buf;
+	struct mtk_tx_buf *itx_buf, *tx_buf;
 	dma_addr_t mapped_addr;
 	unsigned int nr_frags;
 	int i, n_desc = 1;
@@ -627,8 +627,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT;
 	txd4 |= fport;
 
-	tx_buf = mtk_desc_to_tx_buf(ring, itxd);
-	memset(tx_buf, 0, sizeof(*tx_buf));
+	itx_buf = mtk_desc_to_tx_buf(ring, itxd);
+	memset(itx_buf, 0, sizeof(*itx_buf));
 
 	if (gso)
 		txd4 |= TX_DMA_TSO;
@@ -647,9 +647,11 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 		return -ENOMEM;
 
 	WRITE_ONCE(itxd->txd1, mapped_addr);
-	tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
-	dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
-	dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
+	itx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
+	itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
+			  MTK_TX_FLAGS_FPORT1;
+	dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr);
+	dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb));
 
 	/* TX SG offload */
 	txd = itxd;
@@ -685,11 +687,13 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 					       last_frag * TX_DMA_LS0));
 			WRITE_ONCE(txd->txd4, fport);
 
-			tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
 			tx_buf = mtk_desc_to_tx_buf(ring, txd);
 			memset(tx_buf, 0, sizeof(*tx_buf));
-
+			tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
 			tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
+			tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
+					 MTK_TX_FLAGS_FPORT1;
+
 			dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
 			dma_unmap_len_set(tx_buf, dma_len0, frag_map_size);
 			frag_size -= frag_map_size;
@@ -698,7 +702,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	/* store skb to cleanup */
-	tx_buf->skb = skb;
+	itx_buf->skb = skb;
 
 	WRITE_ONCE(itxd->txd4, txd4);
 	WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) |
@@ -1012,17 +1016,16 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget)
 
 	while ((cpu != dma) && budget) {
 		u32 next_cpu = desc->txd2;
-		int mac;
+		int mac = 0;
 
 		desc = mtk_qdma_phys_to_virt(ring, desc->txd2);
 		if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0)
 			break;
 
-		mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) &
-		       TX_DMA_FPORT_MASK;
-		mac--;
-
 		tx_buf = mtk_desc_to_tx_buf(ring, desc);
+		if (tx_buf->flags & MTK_TX_FLAGS_FPORT1)
+			mac = 1;
+
 		skb = tx_buf->skb;
 		if (!skb) {
 			condition = 1;
@@ -1846,6 +1849,12 @@ static int mtk_hw_init(struct mtk_eth *eth)
 	/* GE2, Force 1000M/FD, FC ON */
 	mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1));
 
+	/* Indicates CDM to parse the MTK special tag from CPU
+	 * which also is working out for untag packets.
+	 */
+	val = mtk_r32(eth, MTK_CDMQ_IG_CTRL);
+	mtk_w32(eth, val | MTK_CDMQ_STAG_EN, MTK_CDMQ_IG_CTRL);
+
 	/* Enable RX VLan Offloading */
 	mtk_w32(eth, 1, MTK_CDMP_EG_CTRL);
 
@@ -1908,10 +1917,9 @@ static int __init mtk_init(struct net_device *dev)
 
 	/* If the mac address is invalid, use random mac address  */
 	if (!is_valid_ether_addr(dev->dev_addr)) {
-		random_ether_addr(dev->dev_addr);
+		eth_hw_addr_random(dev);
 		dev_err(eth->dev, "generated random MAC address %pM\n",
 			dev->dev_addr);
-		dev->addr_assign_type = NET_ADDR_RANDOM;
 	}
 
 	return mtk_phy_connect(dev);
@@ -2317,6 +2325,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops;
 
 	eth->netdev[id]->irq = eth->irq[0];
+	eth->netdev[id]->dev.of_node = np;
+
 	return 0;
 
 free_netdev:
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 99b1c8e9f16f..3c46a3b613b9 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -70,6 +70,10 @@
 /* Frame Engine Interrupt Grouping Register */
 #define MTK_FE_INT_GRP		0x20
 
+/* CDMP Ingress Control Register */
+#define MTK_CDMQ_IG_CTRL	0x1400
+#define MTK_CDMQ_STAG_EN	BIT(0)
+
 /* CDMP Exgress Control Register */
 #define MTK_CDMP_EG_CTRL	0x404
 
@@ -406,12 +410,18 @@ struct mtk_hw_stats {
 	struct u64_stats_sync	syncp;
 };
 
-/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how
- * memory was allocated so that it can be freed properly
- */
 enum mtk_tx_flags {
+	/* PDMA descriptor can point at 1-2 segments. This enum allows us to
+	 * track how memory was allocated so that it can be freed properly.
+	 */
 	MTK_TX_FLAGS_SINGLE0	= 0x01,
 	MTK_TX_FLAGS_PAGE0	= 0x02,
+
+	/* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted
+	 * SKB out instead of looking up through hardware TX descriptor.
+	 */
+	MTK_TX_FLAGS_FPORT0	= 0x04,
+	MTK_TX_FLAGS_FPORT1	= 0x08,
 };
 
 /* This enum allows us to identify how the clock is defined on the array of the
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e8c105164931..0e0fa7030565 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2305,6 +2305,17 @@ static int sync_toggles(struct mlx4_dev *dev)
 		rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read));
 		if (wr_toggle == 0xffffffff || rd_toggle == 0xffffffff) {
 			/* PCI might be offline */
+
+			/* If device removal has been requested,
+			 * do not continue retrying.
+			 */
+			if (dev->persist->interface_state &
+			    MLX4_INTERFACE_STATE_NOWAIT) {
+				mlx4_warn(dev,
+					  "communication channel is offline\n");
+				return -EIO;
+			}
+
 			msleep(100);
 			wr_toggle = swab32(readl(&priv->mfunc.comm->
 					   slave_write));
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c4d714fcc7da..ffbcb27c05e5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -117,7 +117,7 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
 	/* port statistics */
 	"tso_packets",
 	"xmit_more",
-	"queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed",
+	"queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_pages",
 	"rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload",
 
 	/* pf statistics */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 61420473fe5f..94fab20ef146 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -92,7 +92,9 @@ static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return mlx4_en_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return mlx4_en_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 #ifdef CONFIG_RFS_ACCEL
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 9166d90e7328..e0eb695318e6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -213,6 +213,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	priv->port_stats.rx_chksum_good = 0;
 	priv->port_stats.rx_chksum_none = 0;
 	priv->port_stats.rx_chksum_complete = 0;
+	priv->port_stats.rx_alloc_pages = 0;
 	priv->xdp_stats.rx_xdp_drop    = 0;
 	priv->xdp_stats.rx_xdp_tx      = 0;
 	priv->xdp_stats.rx_xdp_tx_full = 0;
@@ -223,6 +224,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		priv->port_stats.rx_chksum_good += READ_ONCE(ring->csum_ok);
 		priv->port_stats.rx_chksum_none += READ_ONCE(ring->csum_none);
 		priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete);
+		priv->port_stats.rx_alloc_pages += READ_ONCE(ring->rx_alloc_pages);
 		priv->xdp_stats.rx_xdp_drop	+= READ_ONCE(ring->xdp_drop);
 		priv->xdp_stats.rx_xdp_tx	+= READ_ONCE(ring->xdp_tx);
 		priv->xdp_stats.rx_xdp_tx_full	+= READ_ONCE(ring->xdp_tx_full);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 867292880c07..aa074e57ce06 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -50,173 +50,62 @@
 
 #include "mlx4_en.h"
 
-static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
-			    struct mlx4_en_rx_alloc *page_alloc,
-			    const struct mlx4_en_frag_info *frag_info,
-			    gfp_t _gfp)
+static int mlx4_alloc_page(struct mlx4_en_priv *priv,
+			   struct mlx4_en_rx_alloc *frag,
+			   gfp_t gfp)
 {
-	int order;
 	struct page *page;
 	dma_addr_t dma;
 
-	for (order = frag_info->order; ;) {
-		gfp_t gfp = _gfp;
-
-		if (order)
-			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NOMEMALLOC;
-		page = alloc_pages(gfp, order);
-		if (likely(page))
-			break;
-		if (--order < 0 ||
-		    ((PAGE_SIZE << order) < frag_info->frag_size))
-			return -ENOMEM;
-	}
-	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order,
-			   frag_info->dma_dir);
+	page = alloc_page(gfp);
+	if (unlikely(!page))
+		return -ENOMEM;
+	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir);
 	if (unlikely(dma_mapping_error(priv->ddev, dma))) {
-		put_page(page);
+		__free_page(page);
 		return -ENOMEM;
 	}
-	page_alloc->page_size = PAGE_SIZE << order;
-	page_alloc->page = page;
-	page_alloc->dma = dma;
-	page_alloc->page_offset = 0;
-	/* Not doing get_page() for each frag is a big win
-	 * on asymetric workloads. Note we can not use atomic_set().
-	 */
-	page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1);
+	frag->page = page;
+	frag->dma = dma;
+	frag->page_offset = priv->rx_headroom;
 	return 0;
 }
 
 static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
+			       struct mlx4_en_rx_ring *ring,
 			       struct mlx4_en_rx_desc *rx_desc,
 			       struct mlx4_en_rx_alloc *frags,
-			       struct mlx4_en_rx_alloc *ring_alloc,
 			       gfp_t gfp)
 {
-	struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
-	const struct mlx4_en_frag_info *frag_info;
-	struct page *page;
 	int i;
 
-	for (i = 0; i < priv->num_frags; i++) {
-		frag_info = &priv->frag_info[i];
-		page_alloc[i] = ring_alloc[i];
-		page_alloc[i].page_offset += frag_info->frag_stride;
-
-		if (page_alloc[i].page_offset + frag_info->frag_stride <=
-		    ring_alloc[i].page_size)
-			continue;
-
-		if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i],
-					      frag_info, gfp)))
-			goto out;
-	}
-
-	for (i = 0; i < priv->num_frags; i++) {
-		frags[i] = ring_alloc[i];
-		frags[i].page_offset += priv->frag_info[i].rx_headroom;
-		rx_desc->data[i].addr = cpu_to_be64(frags[i].dma +
-						    frags[i].page_offset);
-		ring_alloc[i] = page_alloc[i];
-	}
-
-	return 0;
-
-out:
-	while (i--) {
-		if (page_alloc[i].page != ring_alloc[i].page) {
-			dma_unmap_page(priv->ddev, page_alloc[i].dma,
-				page_alloc[i].page_size,
-				priv->frag_info[i].dma_dir);
-			page = page_alloc[i].page;
-			/* Revert changes done by mlx4_alloc_pages */
-			page_ref_sub(page, page_alloc[i].page_size /
-					   priv->frag_info[i].frag_stride - 1);
-			put_page(page);
+	for (i = 0; i < priv->num_frags; i++, frags++) {
+		if (!frags->page) {
+			if (mlx4_alloc_page(priv, frags, gfp))
+				return -ENOMEM;
+			ring->rx_alloc_pages++;
 		}
-	}
-	return -ENOMEM;
-}
-
-static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
-			      struct mlx4_en_rx_alloc *frags,
-			      int i)
-{
-	const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-	u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride;
-
-
-	if (next_frag_end > frags[i].page_size)
-		dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size,
-			       frag_info->dma_dir);
-
-	if (frags[i].page)
-		put_page(frags[i].page);
-}
-
-static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
-				  struct mlx4_en_rx_ring *ring)
-{
-	int i;
-	struct mlx4_en_rx_alloc *page_alloc;
-
-	for (i = 0; i < priv->num_frags; i++) {
-		const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-
-		if (mlx4_alloc_pages(priv, &ring->page_alloc[i],
-				     frag_info, GFP_KERNEL | __GFP_COLD))
-			goto out;
-
-		en_dbg(DRV, priv, "  frag %d allocator: - size:%d frags:%d\n",
-		       i, ring->page_alloc[i].page_size,
-		       page_ref_count(ring->page_alloc[i].page));
+		rx_desc->data[i].addr = cpu_to_be64(frags->dma +
+						    frags->page_offset);
 	}
 	return 0;
-
-out:
-	while (i--) {
-		struct page *page;
-
-		page_alloc = &ring->page_alloc[i];
-		dma_unmap_page(priv->ddev, page_alloc->dma,
-			       page_alloc->page_size,
-			       priv->frag_info[i].dma_dir);
-		page = page_alloc->page;
-		/* Revert changes done by mlx4_alloc_pages */
-		page_ref_sub(page, page_alloc->page_size /
-				   priv->frag_info[i].frag_stride - 1);
-		put_page(page);
-		page_alloc->page = NULL;
-	}
-	return -ENOMEM;
 }
 
-static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv,
-				      struct mlx4_en_rx_ring *ring)
+static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
+			      struct mlx4_en_rx_alloc *frag)
 {
-	struct mlx4_en_rx_alloc *page_alloc;
-	int i;
-
-	for (i = 0; i < priv->num_frags; i++) {
-		const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-
-		page_alloc = &ring->page_alloc[i];
-		en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n",
-		       i, page_count(page_alloc->page));
-
-		dma_unmap_page(priv->ddev, page_alloc->dma,
-				page_alloc->page_size, frag_info->dma_dir);
-		while (page_alloc->page_offset + frag_info->frag_stride <
-		       page_alloc->page_size) {
-			put_page(page_alloc->page);
-			page_alloc->page_offset += frag_info->frag_stride;
-		}
-		page_alloc->page = NULL;
+	if (frag->page) {
+		dma_unmap_page(priv->ddev, frag->dma,
+			       PAGE_SIZE, priv->dma_dir);
+		__free_page(frag->page);
 	}
+	/* We need to clear all fields, otherwise a change of priv->log_rx_info
+	 * could lead to see garbage later in frag->page.
+	 */
+	memset(frag, 0, sizeof(*frag));
 }
 
-static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv,
+static void mlx4_en_init_rx_desc(const struct mlx4_en_priv *priv,
 				 struct mlx4_en_rx_ring *ring, int index)
 {
 	struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index;
@@ -248,18 +137,23 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride);
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
-
 	if (ring->page_cache.index > 0) {
-		frags[0] = ring->page_cache.buf[--ring->page_cache.index];
-		rx_desc->data[0].addr = cpu_to_be64(frags[0].dma +
-						    frags[0].page_offset);
+		/* XDP uses a single page per frame */
+		if (!frags->page) {
+			ring->page_cache.index--;
+			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
+			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
+		}
+		frags->page_offset = XDP_PACKET_HEADROOM;
+		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
+						    XDP_PACKET_HEADROOM);
 		return 0;
 	}
 
-	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
+	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
 }
 
-static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+static bool mlx4_en_is_ring_empty(const struct mlx4_en_rx_ring *ring)
 {
 	return ring->prod == ring->cons;
 }
@@ -269,7 +163,8 @@ static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
 	*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
 }
 
-static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
+/* slow path */
+static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
 				 struct mlx4_en_rx_ring *ring,
 				 int index)
 {
@@ -279,7 +174,7 @@ static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
 	frags = ring->rx_info + (index << priv->log_rx_info);
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
-		mlx4_en_free_frag(priv, frags, nr);
+		mlx4_en_free_frag(priv, frags + nr);
 	}
 }
 
@@ -335,12 +230,12 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 	       ring->cons, ring->prod);
 
 	/* Unmap and free Rx buffers */
-	while (!mlx4_en_is_ring_empty(ring)) {
-		index = ring->cons & ring->size_mask;
+	for (index = 0; index < ring->size; index++) {
 		en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
 		mlx4_en_free_rx_desc(priv, ring, index);
-		++ring->cons;
 	}
+	ring->cons = 0;
+	ring->prod = 0;
 }
 
 void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
@@ -392,9 +287,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
-	ring->rx_info = vmalloc_node(tmp, node);
+	ring->rx_info = vzalloc_node(tmp, node);
 	if (!ring->rx_info) {
-		ring->rx_info = vmalloc(tmp);
+		ring->rx_info = vzalloc(tmp);
 		if (!ring->rx_info) {
 			err = -ENOMEM;
 			goto err_ring;
@@ -464,16 +359,6 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
 		/* Initialize all descriptors */
 		for (i = 0; i < ring->size; i++)
 			mlx4_en_init_rx_desc(priv, ring, i);
-
-		/* Initialize page allocators */
-		err = mlx4_en_init_allocator(priv, ring);
-		if (err) {
-			en_err(priv, "Failed initializing ring allocator\n");
-			if (ring->stride <= TXBB_SIZE)
-				ring->buf -= TXBB_SIZE;
-			ring_ind--;
-			goto err_allocator;
-		}
 	}
 	err = mlx4_en_fill_rx_buffers(priv);
 	if (err)
@@ -493,11 +378,9 @@ err_buffers:
 		mlx4_en_free_rx_buf(priv, priv->rx_ring[ring_ind]);
 
 	ring_ind = priv->rx_ring_num - 1;
-err_allocator:
 	while (ring_ind >= 0) {
 		if (priv->rx_ring[ring_ind]->stride <= TXBB_SIZE)
 			priv->rx_ring[ring_ind]->buf -= TXBB_SIZE;
-		mlx4_en_destroy_allocator(priv, priv->rx_ring[ring_ind]);
 		ring_ind--;
 	}
 	return err;
@@ -537,7 +420,9 @@ bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
 	if (cache->index >= MLX4_EN_CACHE_SIZE)
 		return false;
 
-	cache->buf[cache->index++] = *frame;
+	cache->buf[cache->index].page = frame->page;
+	cache->buf[cache->index].dma = frame->dma;
+	cache->index++;
 	return true;
 }
 
@@ -567,136 +452,91 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 	int i;
 
 	for (i = 0; i < ring->page_cache.index; i++) {
-		struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i];
-
-		dma_unmap_page(priv->ddev, frame->dma, frame->page_size,
-			       priv->frag_info[0].dma_dir);
-		put_page(frame->page);
+		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
+			       PAGE_SIZE, priv->dma_dir);
+		put_page(ring->page_cache.buf[i].page);
 	}
 	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
-	mlx4_en_destroy_allocator(priv, ring);
 }
 
 
 static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
-				    struct mlx4_en_rx_desc *rx_desc,
 				    struct mlx4_en_rx_alloc *frags,
 				    struct sk_buff *skb,
 				    int length)
 {
-	struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags;
-	struct mlx4_en_frag_info *frag_info;
-	int nr;
+	const struct mlx4_en_frag_info *frag_info = priv->frag_info;
+	unsigned int truesize = 0;
+	int nr, frag_size;
+	struct page *page;
 	dma_addr_t dma;
+	bool release;
 
 	/* Collect used fragments while replacing them in the HW descriptors */
-	for (nr = 0; nr < priv->num_frags; nr++) {
-		frag_info = &priv->frag_info[nr];
-		if (length <= frag_info->frag_prefix_size)
-			break;
-		if (unlikely(!frags[nr].page))
+	for (nr = 0;; frags++) {
+		frag_size = min_t(int, length, frag_info->frag_size);
+
+		page = frags->page;
+		if (unlikely(!page))
 			goto fail;
 
-		dma = be64_to_cpu(rx_desc->data[nr].addr);
-		dma_sync_single_for_cpu(priv->ddev, dma, frag_info->frag_size,
-					DMA_FROM_DEVICE);
+		dma = frags->dma;
+		dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset,
+					      frag_size, priv->dma_dir);
+
+		__skb_fill_page_desc(skb, nr, page, frags->page_offset,
+				     frag_size);
 
-		__skb_fill_page_desc(skb, nr, frags[nr].page,
-				     frags[nr].page_offset,
-				     frag_info->frag_size);
+		truesize += frag_info->frag_stride;
+		if (frag_info->frag_stride == PAGE_SIZE / 2) {
+			frags->page_offset ^= PAGE_SIZE / 2;
+			release = page_count(page) != 1 ||
+				  page_is_pfmemalloc(page) ||
+				  page_to_nid(page) != numa_mem_id();
+		} else {
+			u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
 
-		skb->truesize += frag_info->frag_stride;
-		frags[nr].page = NULL;
+			frags->page_offset += sz_align;
+			release = frags->page_offset + frag_info->frag_size > PAGE_SIZE;
+		}
+		if (release) {
+			dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
+			frags->page = NULL;
+		} else {
+			page_ref_inc(page);
+		}
+
+		nr++;
+		length -= frag_size;
+		if (!length)
+			break;
+		frag_info++;
 	}
-	/* Adjust size of last fragment to match actual length */
-	if (nr > 0)
-		skb_frag_size_set(&skb_frags_rx[nr - 1],
-			length - priv->frag_info[nr - 1].frag_prefix_size);
+	skb->truesize += truesize;
 	return nr;
 
 fail:
 	while (nr > 0) {
 		nr--;
-		__skb_frag_unref(&skb_frags_rx[nr]);
+		__skb_frag_unref(skb_shinfo(skb)->frags + nr);
 	}
 	return 0;
 }
 
-
-static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
-				      struct mlx4_en_rx_desc *rx_desc,
-				      struct mlx4_en_rx_alloc *frags,
-				      unsigned int length)
-{
-	struct sk_buff *skb;
-	void *va;
-	int used_frags;
-	dma_addr_t dma;
-
-	skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN);
-	if (unlikely(!skb)) {
-		en_dbg(RX_ERR, priv, "Failed allocating skb\n");
-		return NULL;
-	}
-	skb_reserve(skb, NET_IP_ALIGN);
-	skb->len = length;
-
-	/* Get pointer to first fragment so we could copy the headers into the
-	 * (linear part of the) skb */
-	va = page_address(frags[0].page) + frags[0].page_offset;
-
-	if (length <= SMALL_PACKET_SIZE) {
-		/* We are copying all relevant data to the skb - temporarily
-		 * sync buffers for the copy */
-		dma = be64_to_cpu(rx_desc->data[0].addr);
-		dma_sync_single_for_cpu(priv->ddev, dma, length,
-					DMA_FROM_DEVICE);
-		skb_copy_to_linear_data(skb, va, length);
-		skb->tail += length;
-	} else {
-		unsigned int pull_len;
-
-		/* Move relevant fragments to skb */
-		used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, frags,
-							skb, length);
-		if (unlikely(!used_frags)) {
-			kfree_skb(skb);
-			return NULL;
-		}
-		skb_shinfo(skb)->nr_frags = used_frags;
-
-		pull_len = eth_get_headlen(va, SMALL_PACKET_SIZE);
-		/* Copy headers into the skb linear buffer */
-		memcpy(skb->data, va, pull_len);
-		skb->tail += pull_len;
-
-		/* Skip headers in first fragment */
-		skb_shinfo(skb)->frags[0].page_offset += pull_len;
-
-		/* Adjust size of first fragment */
-		skb_frag_size_sub(&skb_shinfo(skb)->frags[0], pull_len);
-		skb->data_len = length - pull_len;
-	}
-	return skb;
-}
-
-static void validate_loopback(struct mlx4_en_priv *priv, struct sk_buff *skb)
+static void validate_loopback(struct mlx4_en_priv *priv, void *va)
 {
+	const unsigned char *data = va + ETH_HLEN;
 	int i;
-	int offset = ETH_HLEN;
 
-	for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++, offset++) {
-		if (*(skb->data + offset) != (unsigned char) (i & 0xff))
-			goto out_loopback;
+	for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++) {
+		if (data[i] != (unsigned char)i)
+			return;
 	}
 	/* Loopback found */
 	priv->loopback_ok = 1;
-
-out_loopback:
-	dev_kfree_skb_any(skb);
 }
 
 static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
@@ -801,7 +641,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	struct mlx4_cqe *cqe;
 	struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
 	struct mlx4_en_rx_alloc *frags;
-	struct mlx4_en_rx_desc *rx_desc;
 	struct bpf_prog *xdp_prog;
 	int doorbell_pending;
 	struct sk_buff *skb;
@@ -834,10 +673,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	/* Process all completed CQEs */
 	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
 		    cq->mcq.cons_index & cq->size)) {
+		void *va;
 
 		frags = ring->rx_info + (index << priv->log_rx_info);
-		rx_desc = ring->buf + (index << ring->log_stride);
-
+		va = page_address(frags[0].page) + frags[0].page_offset;
 		/*
 		 * make sure we read the CQE after we read the ownership bit
 		 */
@@ -860,16 +699,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		 * and not performing the selftest or flb disabled
 		 */
 		if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) {
-			struct ethhdr *ethh;
+			const struct ethhdr *ethh = va;
 			dma_addr_t dma;
 			/* Get pointer to first fragment since we haven't
 			 * skb yet and cast it to ethhdr struct
 			 */
-			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma = frags[0].dma + frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
 						DMA_FROM_DEVICE);
-			ethh = (struct ethhdr *)(page_address(frags[0].page) +
-						 frags[0].page_offset);
 
 			if (is_multicast_ether_addr(ethh->h_dest)) {
 				struct mlx4_mac_entry *entry;
@@ -887,13 +724,16 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			}
 		}
 
+		if (unlikely(priv->validate_loopback)) {
+			validate_loopback(priv, va);
+			goto next;
+		}
+
 		/*
 		 * Packet is OK - process it.
 		 */
 		length = be32_to_cpu(cqe->byte_cnt);
 		length -= ring->fcs_del;
-		l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
-			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
 
 		/* A bpf program gets first chance to drop the packet. It may
 		 * read bytes but not past the end of the frag.
@@ -904,13 +744,13 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			void *orig_data;
 			u32 act;
 
-			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma = frags[0].dma + frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma,
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
 
-			xdp.data_hard_start = page_address(frags[0].page);
-			xdp.data = xdp.data_hard_start + frags[0].page_offset;
+			xdp.data_hard_start = va - frags[0].page_offset;
+			xdp.data = va;
 			xdp.data_end = xdp.data + length;
 			orig_data = xdp.data;
 
@@ -920,6 +760,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				length = xdp.data_end - xdp.data;
 				frags[0].page_offset = xdp.data -
 					xdp.data_hard_start;
+				va = xdp.data;
 			}
 
 			switch (act) {
@@ -928,8 +769,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_TX:
 				if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
 							length, cq->ring,
-							&doorbell_pending)))
-					goto consumed;
+							&doorbell_pending))) {
+					frags[0].page = NULL;
+					goto next;
+				}
 				trace_xdp_exception(dev, xdp_prog, act);
 				goto xdp_drop_no_cnt; /* Drop on xmit failure */
 			default:
@@ -939,8 +782,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_DROP:
 				ring->xdp_drop++;
 xdp_drop_no_cnt:
-				if (likely(mlx4_en_rx_recycle(ring, frags)))
-					goto consumed;
 				goto next;
 			}
 		}
@@ -948,129 +789,51 @@ xdp_drop_no_cnt:
 		ring->bytes += length;
 		ring->packets++;
 
+		skb = napi_get_frags(&cq->napi);
+		if (!skb)
+			goto next;
+
+		if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
+			timestamp = mlx4_en_get_cqe_ts(cqe);
+			mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
+					       timestamp);
+		}
+		skb_record_rx_queue(skb, cq->ring);
+
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
 			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						      MLX4_CQE_STATUS_UDP)) {
 				if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
 				    cqe->checksum == cpu_to_be16(0xffff)) {
 					ip_summed = CHECKSUM_UNNECESSARY;
+					l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
+						(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
+					if (l2_tunnel)
+						skb->csum_level = 1;
 					ring->csum_ok++;
 				} else {
-					ip_summed = CHECKSUM_NONE;
-					ring->csum_none++;
+					goto csum_none;
 				}
 			} else {
 				if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP &&
 				    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 |
 							       MLX4_CQE_STATUS_IPV6))) {
-					ip_summed = CHECKSUM_COMPLETE;
-					ring->csum_complete++;
+					if (check_csum(cqe, skb, va, dev->features)) {
+						goto csum_none;
+					} else {
+						ip_summed = CHECKSUM_COMPLETE;
+						ring->csum_complete++;
+					}
 				} else {
-					ip_summed = CHECKSUM_NONE;
-					ring->csum_none++;
+					goto csum_none;
 				}
 			}
 		} else {
+csum_none:
 			ip_summed = CHECKSUM_NONE;
 			ring->csum_none++;
 		}
-
-		/* This packet is eligible for GRO if it is:
-		 * - DIX Ethernet (type interpretation)
-		 * - TCP/IP (v4)
-		 * - without IP options
-		 * - not an IP fragment
-		 */
-		if (dev->features & NETIF_F_GRO) {
-			struct sk_buff *gro_skb = napi_get_frags(&cq->napi);
-			if (!gro_skb)
-				goto next;
-
-			nr = mlx4_en_complete_rx_desc(priv,
-				rx_desc, frags, gro_skb,
-				length);
-			if (!nr)
-				goto next;
-
-			if (ip_summed == CHECKSUM_COMPLETE) {
-				void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
-				if (check_csum(cqe, gro_skb, va,
-					       dev->features)) {
-					ip_summed = CHECKSUM_NONE;
-					ring->csum_none++;
-					ring->csum_complete--;
-				}
-			}
-
-			skb_shinfo(gro_skb)->nr_frags = nr;
-			gro_skb->len = length;
-			gro_skb->data_len = length;
-			gro_skb->ip_summed = ip_summed;
-
-			if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
-				gro_skb->csum_level = 1;
-
-			if ((cqe->vlan_my_qpn &
-			    cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
-			    (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
-				u16 vid = be16_to_cpu(cqe->sl_vid);
-
-				__vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid);
-			} else if ((be32_to_cpu(cqe->vlan_my_qpn) &
-				  MLX4_CQE_SVLAN_PRESENT_MASK) &&
-				 (dev->features & NETIF_F_HW_VLAN_STAG_RX)) {
-				__vlan_hwaccel_put_tag(gro_skb,
-						       htons(ETH_P_8021AD),
-						       be16_to_cpu(cqe->sl_vid));
-			}
-
-			if (dev->features & NETIF_F_RXHASH)
-				skb_set_hash(gro_skb,
-					     be32_to_cpu(cqe->immed_rss_invalid),
-					     (ip_summed == CHECKSUM_UNNECESSARY) ?
-						PKT_HASH_TYPE_L4 :
-						PKT_HASH_TYPE_L3);
-
-			skb_record_rx_queue(gro_skb, cq->ring);
-
-			if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
-				timestamp = mlx4_en_get_cqe_ts(cqe);
-				mlx4_en_fill_hwtstamps(mdev,
-						       skb_hwtstamps(gro_skb),
-						       timestamp);
-			}
-
-			napi_gro_frags(&cq->napi);
-			goto next;
-		}
-
-		/* GRO not possible, complete processing here */
-		skb = mlx4_en_rx_skb(priv, rx_desc, frags, length);
-		if (unlikely(!skb)) {
-			ring->dropped++;
-			goto next;
-		}
-
-		if (unlikely(priv->validate_loopback)) {
-			validate_loopback(priv, skb);
-			goto next;
-		}
-
-		if (ip_summed == CHECKSUM_COMPLETE) {
-			if (check_csum(cqe, skb, skb->data, dev->features)) {
-				ip_summed = CHECKSUM_NONE;
-				ring->csum_complete--;
-				ring->csum_none++;
-			}
-		}
-
 		skb->ip_summed = ip_summed;
-		skb->protocol = eth_type_trans(skb, dev);
-		skb_record_rx_queue(skb, cq->ring);
-
-		if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
-			skb->csum_level = 1;
-
 		if (dev->features & NETIF_F_RXHASH)
 			skb_set_hash(skb,
 				     be32_to_cpu(cqe->immed_rss_invalid),
@@ -1078,36 +841,36 @@ xdp_drop_no_cnt:
 					PKT_HASH_TYPE_L4 :
 					PKT_HASH_TYPE_L3);
 
-		if ((be32_to_cpu(cqe->vlan_my_qpn) &
-		    MLX4_CQE_CVLAN_PRESENT_MASK) &&
+
+		if ((cqe->vlan_my_qpn &
+		     cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
 		    (dev->features & NETIF_F_HW_VLAN_CTAG_RX))
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid));
-		else if ((be32_to_cpu(cqe->vlan_my_qpn) &
-			  MLX4_CQE_SVLAN_PRESENT_MASK) &&
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       be16_to_cpu(cqe->sl_vid));
+		else if ((cqe->vlan_my_qpn &
+			  cpu_to_be32(MLX4_CQE_SVLAN_PRESENT_MASK)) &&
 			 (dev->features & NETIF_F_HW_VLAN_STAG_RX))
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD),
 					       be16_to_cpu(cqe->sl_vid));
 
-		if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
-			timestamp = mlx4_en_get_cqe_ts(cqe);
-			mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
-					       timestamp);
+		nr = mlx4_en_complete_rx_desc(priv, frags, skb, length);
+		if (likely(nr)) {
+			skb_shinfo(skb)->nr_frags = nr;
+			skb->len = length;
+			skb->data_len = length;
+			napi_gro_frags(&cq->napi);
+		} else {
+			skb->vlan_tci = 0;
+			skb_clear_hash(skb);
 		}
-
-		napi_gro_receive(&cq->napi, skb);
 next:
-		for (nr = 0; nr < priv->num_frags; nr++)
-			mlx4_en_free_frag(priv, frags, nr);
-
-consumed:
 		++cq->mcq.cons_index;
 		index = (cq->mcq.cons_index) & ring->size_mask;
 		cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor;
 		if (++polled == budget)
-			goto out;
+			break;
 	}
 
-out:
 	rcu_read_unlock();
 
 	if (polled) {
@@ -1178,13 +941,6 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 	return done;
 }
 
-static const int frag_sizes[] = {
-	FRAG_SZ0,
-	FRAG_SZ1,
-	FRAG_SZ2,
-	FRAG_SZ3
-};
-
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -1195,33 +951,43 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 	 * This only works when num_frags == 1.
 	 */
 	if (priv->tx_ring_num[TX_XDP]) {
-		priv->frag_info[0].order = 0;
 		priv->frag_info[0].frag_size = eff_mtu;
-		priv->frag_info[0].frag_prefix_size = 0;
 		/* This will gain efficient xdp frame recycling at the
 		 * expense of more costly truesize accounting
 		 */
 		priv->frag_info[0].frag_stride = PAGE_SIZE;
-		priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL;
-		priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM;
+		priv->dma_dir = PCI_DMA_BIDIRECTIONAL;
+		priv->rx_headroom = XDP_PACKET_HEADROOM;
 		i = 1;
 	} else {
-		int buf_size = 0;
+		int frag_size_max = 2048, buf_size = 0;
+
+		/* should not happen, right ? */
+		if (eff_mtu > PAGE_SIZE + (MLX4_EN_MAX_RX_FRAGS - 1) * 2048)
+			frag_size_max = PAGE_SIZE;
 
 		while (buf_size < eff_mtu) {
-			priv->frag_info[i].order = MLX4_EN_ALLOC_PREFER_ORDER;
-			priv->frag_info[i].frag_size =
-				(eff_mtu > buf_size + frag_sizes[i]) ?
-					frag_sizes[i] : eff_mtu - buf_size;
-			priv->frag_info[i].frag_prefix_size = buf_size;
-			priv->frag_info[i].frag_stride =
-				ALIGN(priv->frag_info[i].frag_size,
-				      SMP_CACHE_BYTES);
-			priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE;
-			priv->frag_info[i].rx_headroom = 0;
-			buf_size += priv->frag_info[i].frag_size;
+			int frag_stride, frag_size = eff_mtu - buf_size;
+			int pad, nb;
+
+			if (i < MLX4_EN_MAX_RX_FRAGS - 1)
+				frag_size = min(frag_size, frag_size_max);
+
+			priv->frag_info[i].frag_size = frag_size;
+			frag_stride = ALIGN(frag_size, SMP_CACHE_BYTES);
+			/* We can only pack 2 1536-bytes frames in on 4K page
+			 * Therefore, each frame would consume more bytes (truesize)
+			 */
+			nb = PAGE_SIZE / frag_stride;
+			pad = (PAGE_SIZE - nb * frag_stride) / nb;
+			pad &= ~(SMP_CACHE_BYTES - 1);
+			priv->frag_info[i].frag_stride = frag_stride + pad;
+
+			buf_size += frag_size;
 			i++;
 		}
+		priv->dma_dir = PCI_DMA_FROMDEVICE;
+		priv->rx_headroom = 0;
 	}
 
 	priv->num_frags = i;
@@ -1232,10 +998,9 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 	       eff_mtu, priv->num_frags);
 	for (i = 0; i < priv->num_frags; i++) {
 		en_err(priv,
-		       "  frag:%d - size:%d prefix:%d stride:%d\n",
+		       "  frag:%d - size:%d stride:%d\n",
 		       i,
 		       priv->frag_info[i].frag_size,
-		       priv->frag_info[i].frag_prefix_size,
 		       priv->frag_info[i].frag_stride);
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 95290e1fc9fe..17112faafbcc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -81,14 +81,11 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
 {
 	u32 loopback_ok = 0;
 	int i;
-	bool gro_enabled;
 
         priv->loopback_ok = 0;
 	priv->validate_loopback = 1;
-	gro_enabled = priv->dev->features & NETIF_F_GRO;
 
 	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
-	priv->dev->features &= ~NETIF_F_GRO;
 
 	/* xmit */
 	if (mlx4_en_test_loopback_xmit(priv)) {
@@ -111,9 +108,6 @@ mlx4_en_test_loopback_exit:
 
 	priv->validate_loopback = 0;
 
-	if (gro_enabled)
-		priv->dev->features |= NETIF_F_GRO;
-
 	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
 	return !loopback_ok;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 3ed42199d3f1..3ba89bc43d74 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -354,13 +354,11 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_alloc frame = {
 		.page = tx_info->page,
 		.dma = tx_info->map0_dma,
-		.page_offset = XDP_PACKET_HEADROOM,
-		.page_size = PAGE_SIZE,
 	};
 
 	if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
 		dma_unmap_page(priv->ddev, tx_info->map0_dma,
-			       PAGE_SIZE, priv->frag_info[0].dma_dir);
+			       PAGE_SIZE, priv->dma_dir);
 		put_page(tx_info->page);
 	}
 
@@ -980,8 +978,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		ring->tso_packets++;
 
-		i = ((skb->len - lso_header_size) / shinfo->gso_size) +
-			!!((skb->len - lso_header_size) % shinfo->gso_size);
+		i = shinfo->gso_segs;
 		tx_info->nr_bytes = skb->len + (i - 1) * lso_header_size;
 		ring->packets += i;
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 21377c315083..703205475524 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1940,6 +1940,14 @@ static int mlx4_comm_check_offline(struct mlx4_dev *dev)
 			       (u32)(1 << COMM_CHAN_OFFLINE_OFFSET));
 		if (!offline_bit)
 			return 0;
+
+		/* If device removal has been requested,
+		 * do not continue retrying.
+		 */
+		if (dev->persist->interface_state &
+		    MLX4_INTERFACE_STATE_NOWAIT)
+			break;
+
 		/* There are cases as part of AER/Reset flow that PF needs
 		 * around 100 msec to load. We therefore sleep for 100 msec
 		 * to allow other tasks to make use of that CPU during this
@@ -3955,6 +3963,9 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct devlink *devlink = priv_to_devlink(priv);
 	int active_vfs = 0;
 
+	if (mlx4_is_slave(dev))
+		persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT;
+
 	mutex_lock(&persist->interface_state_mutex);
 	persist->interface_state |= MLX4_INTERFACE_STATE_DELETION;
 	mutex_unlock(&persist->interface_state_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3629ce11a68b..39f401aa3047 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -102,17 +102,6 @@
 /* Use the maximum between 16384 and a single page */
 #define MLX4_EN_ALLOC_SIZE	PAGE_ALIGN(16384)
 
-#define MLX4_EN_ALLOC_PREFER_ORDER min_t(int, get_order(32768),		\
-					 PAGE_ALLOC_COSTLY_ORDER)
-
-/* Receive fragment sizes; we use at most 3 fragments (for 9600 byte MTU
- * and 4K allocations) */
-enum {
-	FRAG_SZ0 = 1536 - NET_IP_ALIGN,
-	FRAG_SZ1 = 4096,
-	FRAG_SZ2 = 4096,
-	FRAG_SZ3 = MLX4_EN_ALLOC_SIZE
-};
 #define MLX4_EN_MAX_RX_FRAGS	4
 
 /* Maximum ring sizes */
@@ -264,13 +253,16 @@ struct mlx4_en_rx_alloc {
 	struct page	*page;
 	dma_addr_t	dma;
 	u32		page_offset;
-	u32		page_size;
 };
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
+
 struct mlx4_en_page_cache {
 	u32 index;
-	struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE];
+	struct {
+		struct page	*page;
+		dma_addr_t	dma;
+	} buf[MLX4_EN_CACHE_SIZE];
 };
 
 struct mlx4_en_priv;
@@ -335,7 +327,6 @@ struct mlx4_en_rx_desc {
 
 struct mlx4_en_rx_ring {
 	struct mlx4_hwq_resources wqres;
-	struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
 	u32 size ;	/* number of Rx descs*/
 	u32 actual_size;
 	u32 size_mask;
@@ -355,6 +346,7 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	unsigned long csum_complete;
+	unsigned long rx_alloc_pages;
 	unsigned long xdp_drop;
 	unsigned long xdp_tx;
 	unsigned long xdp_tx_full;
@@ -472,11 +464,7 @@ struct mlx4_en_mc_list {
 
 struct mlx4_en_frag_info {
 	u16 frag_size;
-	u16 frag_prefix_size;
 	u32 frag_stride;
-	enum dma_data_direction dma_dir;
-	u16 order;
-	u16 rx_headroom;
 };
 
 #ifdef CONFIG_MLX4_EN_DCB
@@ -584,8 +572,10 @@ struct mlx4_en_priv {
 	u32 rx_ring_num;
 	u32 rx_skb_size;
 	struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS];
-	u16 num_frags;
-	u16 log_rx_info;
+	u8 num_frags;
+	u8 log_rx_info;
+	u8 dma_dir;
+	u16 rx_headroom;
 
 	struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES];
 	struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
index 48641cb0367f..926f3c3f3665 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
@@ -37,7 +37,7 @@ struct mlx4_en_port_stats {
 	unsigned long queue_stopped;
 	unsigned long wake_queue;
 	unsigned long tx_timeout;
-	unsigned long rx_alloc_failed;
+	unsigned long rx_alloc_pages;
 	unsigned long rx_chksum_good;
 	unsigned long rx_chksum_none;
 	unsigned long rx_chksum_complete;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index d8d5d161b8c7..4aa29ee93013 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2749,7 +2749,7 @@ int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	int index = vhcr->in_modifier;
 	struct res_mtt *mtt;
-	struct res_mpt *mpt;
+	struct res_mpt *mpt = NULL;
 	int mtt_base = mr_get_mtt_addr(inbox->buf) / dev->caps.mtt_entry_sz;
 	int phys;
 	int id;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index ddb4ca4ff930..a84b652f9b54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -14,6 +14,7 @@ config MLX5_CORE
 config MLX5_CORE_EN
 	bool "Mellanox Technologies ConnectX-4 Ethernet support"
 	depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+	depends on IPV6=y || IPV6=n || MLX5_CORE=m
 	imply PTP_1588_CLOCK
 	default n
 	---help---
@@ -30,3 +31,10 @@ config MLX5_CORE_EN_DCB
 	  This flag is depended on the kernel's DCB support.
 
 	  If unsure, set to Y
+
+config MLX5_CORE_IPOIB
+	bool "Mellanox Technologies ConnectX-4 IPoIB offloads support"
+	depends on MLX5_CORE_EN
+	default y
+	---help---
+	  MLX5 IPoIB offloads & acceleration support.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9f43beb86250..9e644615f07a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -11,3 +11,5 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o eswitch_offloads.o \
 		en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o
+
+mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index caa837e5e2b9..5bdaf3d545b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -279,6 +279,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_XRC_SRQ:
 	case MLX5_CMD_OP_DESTROY_DCT:
 	case MLX5_CMD_OP_DEALLOC_Q_COUNTER:
+	case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
 	case MLX5_CMD_OP_DEALLOC_PD:
 	case MLX5_CMD_OP_DEALLOC_UAR:
 	case MLX5_CMD_OP_DETACH_FROM_MCG:
@@ -305,8 +307,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 	case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
-	case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
+	case MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -361,6 +362,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
+	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
+	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
 	case MLX5_CMD_OP_ALLOC_PD:
 	case MLX5_CMD_OP_ALLOC_UAR:
 	case MLX5_CMD_OP_CONFIG_INT_MODERATION:
@@ -412,10 +419,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
 	case MLX5_CMD_OP_ALLOC_ENCAP_HEADER:
-	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
+	case MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
 		return -EIO;
@@ -497,6 +501,14 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
+	MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
 	MLX5_COMMAND_STR_CASE(ALLOC_PD);
 	MLX5_COMMAND_STR_CASE(DEALLOC_PD);
 	MLX5_COMMAND_STR_CASE(ALLOC_UAR);
@@ -572,12 +584,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
 	MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER);
-	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
-	MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
+	MLX5_COMMAND_STR_CASE(ALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_COMMAND_STR_CASE(DEALLOC_MODIFY_HEADER_CONTEXT);
 	default: return "unknown command opcode";
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f6a6ded204f6..0099a3e397bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -37,6 +37,7 @@
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
+#include <linux/crash_dump.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/qp.h>
 #include <linux/mlx5/cq.h>
@@ -90,7 +91,7 @@
 #define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
 
 #define MLX5_UMR_ALIGN				(2048)
-#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(128)
+#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
@@ -111,18 +112,13 @@
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
 #define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
-#define MLX5E_SQ_BF_BUDGET             16
 
 #define MLX5E_ICOSQ_MAX_WQEBBS \
 	(DIV_ROUND_UP(sizeof(struct mlx5e_umr_wqe), MLX5_SEND_WQE_BB))
 
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_IHS_DS_COUNT \
-	DIV_ROUND_UP(MLX5E_XDP_MIN_INLINE - 2, MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT \
 	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
-#define MLX5E_XDP_TX_WQEBBS \
-	DIV_ROUND_UP(MLX5E_XDP_TX_DS_COUNT, MLX5_SEND_WQEBB_NUM_DS)
 
 #define MLX5E_NUM_MAIN_GROUPS 9
 
@@ -158,6 +154,14 @@ static inline int mlx5_max_log_rq_size(int wq_type)
 	}
 }
 
+static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
+{
+	return is_kdump_kernel() ?
+		MLX5E_MIN_NUM_CHANNELS :
+		min_t(int, mdev->priv.eq_table.num_comp_vectors,
+		      MLX5E_MAX_NUM_CHANNELS);
+}
+
 struct mlx5e_tx_wqe {
 	struct mlx5_wqe_ctrl_seg ctrl;
 	struct mlx5_wqe_eth_seg  eth;
@@ -187,15 +191,15 @@ enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 1),
 };
 
-#define MLX5E_SET_PFLAG(priv, pflag, enable)			\
+#define MLX5E_SET_PFLAG(params, pflag, enable)			\
 	do {							\
 		if (enable)					\
-			(priv)->params.pflags |= (pflag);	\
+			(params)->pflags |= (pflag);		\
 		else						\
-			(priv)->params.pflags &= ~(pflag);	\
+			(params)->pflags &= ~(pflag);		\
 	} while (0)
 
-#define MLX5E_GET_PFLAG(priv, pflag) (!!((priv)->params.pflags & (pflag)))
+#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (pflag)))
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
@@ -218,7 +222,6 @@ struct mlx5e_params {
 	bool rx_cqe_compress_def;
 	struct mlx5e_cq_moder rx_cq_moderation;
 	struct mlx5e_cq_moder tx_cq_moderation;
-	u16 min_rx_wqes;
 	bool lro_en;
 	u32 lro_wqe_sz;
 	u16 tx_max_inline;
@@ -227,9 +230,11 @@ struct mlx5e_params {
 	u8  toeplitz_hash_key[40];
 	u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE];
 	bool vlan_strip_disable;
+	bool scatter_fcs_en;
 	bool rx_am_enabled;
 	u32 lro_timeout;
 	u32 pflags;
+	struct bpf_prog *xdp_prog;
 };
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -285,7 +290,6 @@ struct mlx5e_cq {
 	struct napi_struct        *napi;
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
-	struct mlx5e_priv         *priv;
 
 	/* cqe decompression */
 	struct mlx5_cqe64          title;
@@ -295,22 +299,163 @@ struct mlx5e_cq {
 	u16                        decmprs_wqe_counter;
 
 	/* control */
+	struct mlx5_core_dev      *mdev;
 	struct mlx5_frag_wq_ctrl   wq_ctrl;
 } ____cacheline_aligned_in_smp;
 
-struct mlx5e_rq;
-typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
-				       struct mlx5_cqe64 *cqe);
-typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
-				  u16 ix);
+struct mlx5e_tx_wqe_info {
+	struct sk_buff *skb;
+	u32 num_bytes;
+	u8  num_wqebbs;
+	u8  num_dma;
+};
+
+enum mlx5e_dma_map_type {
+	MLX5E_DMA_MAP_SINGLE,
+	MLX5E_DMA_MAP_PAGE
+};
+
+struct mlx5e_sq_dma {
+	dma_addr_t              addr;
+	u32                     size;
+	enum mlx5e_dma_map_type type;
+};
+
+enum {
+	MLX5E_SQ_STATE_ENABLED,
+};
+
+struct mlx5e_sq_wqe_info {
+	u8  opcode;
+	u8  num_wqebbs;
+};
+
+struct mlx5e_txqsq {
+	/* data path */
+
+	/* dirtied @completion */
+	u16                        cc;
+	u32                        dma_fifo_cc;
+
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        dma_fifo_pc;
+	struct mlx5e_sq_stats      stats;
+
+	struct mlx5e_cq            cq;
+
+	/* write@xmit, read@completion */
+	struct {
+		struct mlx5e_sq_dma       *dma_fifo;
+		struct mlx5e_tx_wqe_info  *wqe_info;
+	} db;
+
+	/* read only */
+	struct mlx5_wq_cyc         wq;
+	u32                        dma_fifo_mask;
+	void __iomem              *uar_map;
+	struct netdev_queue       *txq;
+	u32                        sqn;
+	u16                        max_inline;
+	u8                         min_inline_mode;
+	u16                        edge;
+	struct device             *pdev;
+	struct mlx5e_tstamp       *tstamp;
+	__be32                     mkey_be;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5e_channel      *channel;
+	int                        txq_ix;
+	u32                        rate_limit;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_xdpsq {
+	/* data path */
+
+	/* dirtied @rx completion */
+	u16                        cc;
+	u16                        pc;
+
+	struct mlx5e_cq            cq;
+
+	/* write@xmit, read@completion */
+	struct {
+		struct mlx5e_dma_info     *di;
+		bool                       doorbell;
+	} db;
+
+	/* read only */
+	struct mlx5_wq_cyc         wq;
+	void __iomem              *uar_map;
+	u32                        sqn;
+	struct device             *pdev;
+	__be32                     mkey_be;
+	u8                         min_inline_mode;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5e_channel      *channel;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_icosq {
+	/* data path */
+
+	/* dirtied @completion */
+	u16                        cc;
+
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        dma_fifo_pc;
+	u16                        prev_cc;
 
-typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+	struct mlx5e_cq            cq;
+
+	/* write@xmit, read@completion */
+	struct {
+		struct mlx5e_sq_wqe_info *ico_wqe;
+	} db;
+
+	/* read only */
+	struct mlx5_wq_cyc         wq;
+	void __iomem              *uar_map;
+	u32                        sqn;
+	u16                        edge;
+	struct device             *pdev;
+	__be32                     mkey_be;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5e_channel      *channel;
+} ____cacheline_aligned_in_smp;
+
+static inline bool
+mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
+{
+	return (((wq->sz_m1 & (cc - pc)) >= n) || (cc == pc));
+}
 
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
 };
 
+struct mlx5e_umr_dma_info {
+	__be64                *mtt;
+	dma_addr_t             mtt_addr;
+	struct mlx5e_dma_info  dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
+	struct mlx5e_umr_wqe   wqe;
+};
+
+struct mlx5e_mpw_info {
+	struct mlx5e_umr_dma_info umr;
+	u16 consumed_strides;
+	u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
+};
+
 struct mlx5e_rx_am_stats {
 	int ppms; /* packets per msec */
 	int epms; /* events per msec */
@@ -347,6 +492,11 @@ struct mlx5e_page_cache {
 	struct mlx5e_dma_info page_cache[MLX5E_CACHE_SIZE];
 };
 
+struct mlx5e_rq;
+typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
+typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq*, struct mlx5e_rx_wqe*, u16);
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
+
 struct mlx5e_rq {
 	/* data path */
 	struct mlx5_wq_ll      wq;
@@ -381,7 +531,10 @@ struct mlx5e_rq {
 	u16                    rx_headroom;
 
 	struct mlx5e_rx_am     am; /* Adaptive Moderation */
+
+	/* XDP */
 	struct bpf_prog       *xdp_prog;
+	struct mlx5e_xdpsq     xdpsq;
 
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
@@ -390,118 +543,10 @@ struct mlx5e_rq {
 	u32                    mpwqe_num_strides;
 	u32                    rqn;
 	struct mlx5e_channel  *channel;
-	struct mlx5e_priv     *priv;
+	struct mlx5_core_dev  *mdev;
 	struct mlx5_core_mkey  umr_mkey;
 } ____cacheline_aligned_in_smp;
 
-struct mlx5e_umr_dma_info {
-	__be64                *mtt;
-	dma_addr_t             mtt_addr;
-	struct mlx5e_dma_info  dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
-	struct mlx5e_umr_wqe   wqe;
-};
-
-struct mlx5e_mpw_info {
-	struct mlx5e_umr_dma_info umr;
-	u16 consumed_strides;
-	u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
-};
-
-struct mlx5e_tx_wqe_info {
-	u32 num_bytes;
-	u8  num_wqebbs;
-	u8  num_dma;
-};
-
-enum mlx5e_dma_map_type {
-	MLX5E_DMA_MAP_SINGLE,
-	MLX5E_DMA_MAP_PAGE
-};
-
-struct mlx5e_sq_dma {
-	dma_addr_t              addr;
-	u32                     size;
-	enum mlx5e_dma_map_type type;
-};
-
-enum {
-	MLX5E_SQ_STATE_ENABLED,
-	MLX5E_SQ_STATE_BF_ENABLE,
-};
-
-struct mlx5e_sq_wqe_info {
-	u8  opcode;
-	u8  num_wqebbs;
-};
-
-enum mlx5e_sq_type {
-	MLX5E_SQ_TXQ,
-	MLX5E_SQ_ICO,
-	MLX5E_SQ_XDP
-};
-
-struct mlx5e_sq {
-	/* data path */
-
-	/* dirtied @completion */
-	u16                        cc;
-	u32                        dma_fifo_cc;
-
-	/* dirtied @xmit */
-	u16                        pc ____cacheline_aligned_in_smp;
-	u32                        dma_fifo_pc;
-	u16                        bf_offset;
-	u16                        prev_cc;
-	u8                         bf_budget;
-	struct mlx5e_sq_stats      stats;
-
-	struct mlx5e_cq            cq;
-
-	/* pointers to per tx element info: write@xmit, read@completion */
-	union {
-		struct {
-			struct sk_buff           **skb;
-			struct mlx5e_sq_dma       *dma_fifo;
-			struct mlx5e_tx_wqe_info  *wqe_info;
-		} txq;
-		struct mlx5e_sq_wqe_info *ico_wqe;
-		struct {
-			struct mlx5e_sq_wqe_info  *wqe_info;
-			struct mlx5e_dma_info     *di;
-			bool                       doorbell;
-		} xdp;
-	} db;
-
-	/* read only */
-	struct mlx5_wq_cyc         wq;
-	u32                        dma_fifo_mask;
-	void __iomem              *uar_map;
-	struct netdev_queue       *txq;
-	u32                        sqn;
-	u16                        bf_buf_size;
-	u16                        max_inline;
-	u8                         min_inline_mode;
-	u16                        edge;
-	struct device             *pdev;
-	struct mlx5e_tstamp       *tstamp;
-	__be32                     mkey_be;
-	unsigned long              state;
-
-	/* control path */
-	struct mlx5_wq_ctrl        wq_ctrl;
-	struct mlx5_sq_bfreg	   bfreg;
-	struct mlx5e_channel      *channel;
-	int                        tc;
-	u32                        rate_limit;
-	u8                         type;
-} ____cacheline_aligned_in_smp;
-
-static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n)
-{
-	return (((sq->wq.sz_m1 & (sq->cc - sq->pc)) >= n) ||
-		(sq->cc  == sq->pc));
-}
-
 enum channel_flags {
 	MLX5E_CHANNEL_NAPI_SCHED = 1,
 };
@@ -509,9 +554,8 @@ enum channel_flags {
 struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
-	struct mlx5e_sq            xdp_sq;
-	struct mlx5e_sq            sq[MLX5E_MAX_NUM_TC];
-	struct mlx5e_sq            icosq;   /* internal control operations */
+	struct mlx5e_txqsq         sq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_icosq         icosq;   /* internal control operations */
 	bool                       xdp;
 	struct napi_struct         napi;
 	struct device             *pdev;
@@ -522,10 +566,18 @@ struct mlx5e_channel {
 
 	/* control */
 	struct mlx5e_priv         *priv;
+	struct mlx5_core_dev      *mdev;
+	struct mlx5e_tstamp       *tstamp;
 	int                        ix;
 	int                        cpu;
 };
 
+struct mlx5e_channels {
+	struct mlx5e_channel **c;
+	unsigned int           num;
+	struct mlx5e_params    params;
+};
+
 enum mlx5e_traffic_types {
 	MLX5E_TT_IPV4_TCP,
 	MLX5E_TT_IPV6_TCP,
@@ -675,34 +727,17 @@ enum {
 	MLX5E_NIC_PRIO
 };
 
-struct mlx5e_profile {
-	void	(*init)(struct mlx5_core_dev *mdev,
-			struct net_device *netdev,
-			const struct mlx5e_profile *profile, void *ppriv);
-	void	(*cleanup)(struct mlx5e_priv *priv);
-	int	(*init_rx)(struct mlx5e_priv *priv);
-	void	(*cleanup_rx)(struct mlx5e_priv *priv);
-	int	(*init_tx)(struct mlx5e_priv *priv);
-	void	(*cleanup_tx)(struct mlx5e_priv *priv);
-	void	(*enable)(struct mlx5e_priv *priv);
-	void	(*disable)(struct mlx5e_priv *priv);
-	void	(*update_stats)(struct mlx5e_priv *priv);
-	int	(*max_nch)(struct mlx5_core_dev *mdev);
-	int	max_tc;
-};
-
 struct mlx5e_priv {
 	/* priv data path fields - start */
-	struct mlx5e_sq            **txq_to_sq_map;
-	int channeltc_to_txq_map[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
-	struct bpf_prog *xdp_prog;
+	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
+	int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
 	/* priv data path fields - end */
 
 	unsigned long              state;
 	struct mutex               state_lock; /* Protects Interface state */
 	struct mlx5e_rq            drop_rq;
 
-	struct mlx5e_channel     **channel;
+	struct mlx5e_channels      channels;
 	u32                        tisn[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rqt           indir_rqt;
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
@@ -712,7 +747,6 @@ struct mlx5e_priv {
 	struct mlx5e_flow_steering fs;
 	struct mlx5e_vxlan_db      vxlan;
 
-	struct mlx5e_params        params;
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
@@ -732,9 +766,28 @@ struct mlx5e_priv {
 	void                      *ppriv;
 };
 
+struct mlx5e_profile {
+	void	(*init)(struct mlx5_core_dev *mdev,
+			struct net_device *netdev,
+			const struct mlx5e_profile *profile, void *ppriv);
+	void	(*cleanup)(struct mlx5e_priv *priv);
+	int	(*init_rx)(struct mlx5e_priv *priv);
+	void	(*cleanup_rx)(struct mlx5e_priv *priv);
+	int	(*init_tx)(struct mlx5e_priv *priv);
+	void	(*cleanup_tx)(struct mlx5e_priv *priv);
+	void	(*enable)(struct mlx5e_priv *priv);
+	void	(*disable)(struct mlx5e_priv *priv);
+	void	(*update_stats)(struct mlx5e_priv *priv);
+	int	(*max_nch)(struct mlx5_core_dev *mdev);
+	struct {
+		mlx5e_fp_handle_rx_cqe handle_rx_cqe;
+		mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
+	} rx_handlers;
+	int	max_tc;
+};
+
 void mlx5e_build_ptys2ethtool_map(void);
 
-void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw);
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       void *accel_priv, select_queue_fallback_t fallback);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
@@ -744,7 +797,9 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
-void mlx5e_free_sq_descs(struct mlx5e_sq *sq);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
+void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 
 void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 			bool recycle);
@@ -792,7 +847,7 @@ void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 			     struct ptp_clock_event *event);
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr);
 int mlx5e_hwstamp_get(struct net_device *dev, struct ifreq *ifr);
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
 			  u16 vid);
@@ -801,14 +856,40 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
+struct mlx5e_redirect_rqt_param {
+	bool is_rss;
+	union {
+		u32 rqn; /* Direct RQN (Non-RSS) */
+		struct {
+			u8 hfunc;
+			struct mlx5e_channels *channels;
+		} rss; /* RSS data */
+	};
+};
 
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
-				    enum mlx5e_traffic_types tt);
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+		       struct mlx5e_redirect_rqt_param rrp);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+				    enum mlx5e_traffic_types tt,
+				    void *tirc);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
+
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+			struct mlx5e_channels *chs);
+void mlx5e_close_channels(struct mlx5e_channels *chs);
+
+/* Function pointer to be used to modify WH settings while
+ * switching channels
+ */
+typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				struct mlx5e_channels *new_chs,
+				mlx5e_fp_hw_modify hw_modify);
+void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
+void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
+
 void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
 				   u32 *indirection_rqt, int len,
 				   int num_channels);
@@ -816,30 +897,43 @@ int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 				 u8 cq_period_mode);
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type);
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+			      struct mlx5e_params *params, u8 rq_type);
 
-static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
-				      struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz)
+static inline
+struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
 {
-	u16 ofst = sq->bf_offset;
+	u16                         pi   = *pc & wq->sz_m1;
+	struct mlx5e_tx_wqe        *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	struct mlx5_wqe_ctrl_seg   *cseg = &wqe->ctrl;
+
+	memset(cseg, 0, sizeof(*cseg));
+
+	cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
+	cseg->qpn_ds           = cpu_to_be32((sqn << 8) | 0x01);
 
+	(*pc)++;
+
+	return wqe;
+}
+
+static inline
+void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
+		     void __iomem *uar_map,
+		     struct mlx5_wqe_ctrl_seg *ctrl)
+{
+	ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
 	/* ensure wqe is visible to device before updating doorbell record */
 	dma_wmb();
 
-	*sq->wq.db = cpu_to_be32(sq->pc);
+	*wq->db = cpu_to_be32(pc);
 
 	/* ensure doorbell record is visible to device before ringing the
 	 * doorbell
 	 */
 	wmb();
-	if (bf_sz)
-		__iowrite64_copy(sq->uar_map + ofst, ctrl, bf_sz);
-	else
-		mlx5_write64((__be32 *)ctrl, sq->uar_map + ofst, NULL);
-	/* flush the write-combining mapped buffer */
-	wmb();
 
-	sq->bf_offset ^= sq->bf_buf_size;
+	mlx5_write64((__be32 *)ctrl, uar_map, NULL);
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
@@ -895,48 +989,43 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
-				     bool enable_uc_lb);
-
-struct mlx5_eswitch_rep;
-int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,
-			 struct mlx5_eswitch_rep *rep);
-void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw,
-			    struct mlx5_eswitch_rep *rep);
-int mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep);
-void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
-			  struct mlx5_eswitch_rep *rep);
-int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
-void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
-int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
-void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
-void mlx5e_update_hw_rep_counters(struct mlx5e_priv *priv);
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb);
+
+/* common netdev helpers */
+int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
+
+int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv);
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv);
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
-void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv);
 int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
+void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv);
+
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
+		     u32 underlay_qpn, u32 *tisn);
+void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
+
 int mlx5e_create_tises(struct mlx5e_priv *priv);
 void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
 void mlx5e_update_stats_work(struct work_struct *work);
-struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
-				       const struct mlx5e_profile *profile,
-				       void *ppriv);
-void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv);
-int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
-void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
 u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
-void mlx5e_add_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti);
-void mlx5e_del_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti);
 
-int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
-			    void *sp);
-bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id);
+/* mlx5e generic netdev management API */
+struct net_device*
+mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
+		    void *ppriv);
+int mlx5e_attach_netdev(struct mlx5e_priv *priv);
+void mlx5e_detach_netdev(struct mlx5e_priv *priv);
+void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
+void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_params *params,
+			    u16 max_channels);
 
-bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
-bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv);
 #endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 68419a01db36..c8a005326e30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -174,13 +174,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 				 enum arfs_type type)
 {
 	struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type];
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
-	struct mlx5_flow_destination dest;
 	struct mlx5e_tir *tir = priv->indir_tir;
+	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_spec *spec;
 	int err = 0;
 
@@ -325,10 +321,16 @@ static int arfs_create_table(struct mlx5e_priv *priv,
 {
 	struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
 	struct mlx5e_flow_table *ft = &arfs->arfs_tables[type].ft;
+	struct mlx5_flow_table_attr ft_attr = {};
 	int err;
 
-	ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
-				       MLX5E_ARFS_TABLE_SIZE, MLX5E_ARFS_FT_LEVEL, 0);
+	ft->num_groups = 0;
+
+	ft_attr.max_fte = MLX5E_ARFS_TABLE_SIZE;
+	ft_attr.level = MLX5E_ARFS_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
 	if (IS_ERR(ft->t)) {
 		err = PTR_ERR(ft->t);
 		ft->t = NULL;
@@ -469,15 +471,11 @@ static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
 static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 					      struct arfs_rule *arfs_rule)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
 	struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
 	struct arfs_tuple *tuple = &arfs_rule->tuple;
 	struct mlx5_flow_handle *rule = NULL;
 	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct arfs_table *arfs_table;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_table *ft;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 37e66eef6fb5..e706a87fc8b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -90,6 +90,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
+	int err;
 
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
 		return -EOPNOTSUPP;
@@ -111,7 +112,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	switch (config.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		/* Reset CQE compression to Admin default */
-		mlx5e_modify_rx_cqe_compression_locked(priv, priv->params.rx_cqe_compress_def);
+		mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def);
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
@@ -129,7 +130,12 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		/* Disable CQE compression */
 		netdev_warn(dev, "Disabling cqe compression");
-		mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		if (err) {
+			netdev_err(dev, "Failed disabling cqe compression err=%d\n", err);
+			mutex_unlock(&priv->state_lock);
+			return err;
+		}
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index bd898d8deda0..f1f17f7a3cd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -107,10 +107,18 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_dealloc_transport_domain;
 	}
 
+	err = mlx5_alloc_bfreg(mdev, &res->bfreg, false, false);
+	if (err) {
+		mlx5_core_err(mdev, "alloc bfreg failed, %d\n", err);
+		goto err_destroy_mkey;
+	}
+
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
 
 	return 0;
 
+err_destroy_mkey:
+	mlx5_core_destroy_mkey(mdev, &res->mkey);
 err_dealloc_transport_domain:
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 err_dealloc_pd:
@@ -122,23 +130,26 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 {
 	struct mlx5e_resources *res = &mdev->mlx5e_res;
 
+	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, &res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
 }
 
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
-				     bool enable_uc_lb)
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	void *in;
+	int err  = -ENOMEM;
+	u32 tirn = 0;
 	int inlen;
-	int err = 0;
+	void *in;
+
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = mlx5_vzalloc(inlen);
 	if (!in)
-		return -ENOMEM;
+		goto out;
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -147,13 +158,16 @@ int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
-		err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
+		tirn = tir->tirn;
+		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
 		if (err)
 			goto out;
 	}
 
 out:
 	kvfree(in);
+	if (err)
+		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 0523ed47f597..8fa23f6a1f67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -302,6 +302,9 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_dcbx *dcbx = &priv->dcbx;
 
+	if (mode & DCB_CAP_DCBX_LLD_MANAGED)
+		return 1;
+
 	if ((!mode) && MLX5_CAP_GEN(priv->mdev, dcbx)) {
 		if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_AUTO)
 			return 0;
@@ -315,13 +318,10 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 		return 1;
 	}
 
-	if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
+	if (!(mode & DCB_CAP_DCBX_HOST))
 		return 1;
 
-	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
-	    !(mode & DCB_CAP_DCBX_VER_CEE) ||
-	    !(mode & DCB_CAP_DCBX_VER_IEEE) ||
-	    !(mode & DCB_CAP_DCBX_HOST))
+	if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
 		return 1;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a004a5a1a4c2..ce7b09d72ff6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -42,8 +42,9 @@ static void mlx5e_get_drvinfo(struct net_device *dev,
 	strlcpy(drvinfo->version, DRIVER_VERSION " (" DRIVER_RELDATE ")",
 		sizeof(drvinfo->version));
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		 "%d.%d.%d",
-		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev));
+		 "%d.%d.%04d (%.16s)",
+		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
+		 mdev->board_id);
 	strlcpy(drvinfo->bus_info, pci_name(mdev->pdev),
 		sizeof(drvinfo->bus_info));
 }
@@ -152,12 +153,9 @@ static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv)
 }
 
 #define MLX5E_NUM_Q_CNTRS(priv) (NUM_Q_COUNTERS * (!!priv->q_counter))
-#define MLX5E_NUM_RQ_STATS(priv) \
-	(NUM_RQ_STATS * priv->params.num_channels * \
-	 test_bit(MLX5E_STATE_OPENED, &priv->state))
+#define MLX5E_NUM_RQ_STATS(priv) (NUM_RQ_STATS * (priv)->channels.num)
 #define MLX5E_NUM_SQ_STATS(priv) \
-	(NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \
-	 test_bit(MLX5E_STATE_OPENED, &priv->state))
+	(NUM_SQ_STATS * (priv)->channels.num * (priv)->channels.params.num_tc)
 #define MLX5E_NUM_PFC_COUNTERS(priv) \
 	((mlx5e_query_global_pause_combined(priv) + hweight8(mlx5e_query_pfc_combined(priv))) * \
 	  NUM_PPORT_PER_PRIO_PFC_COUNTERS)
@@ -262,17 +260,17 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 		return;
 
 	/* per channel counters */
-	for (i = 0; i < priv->params.num_channels; i++)
+	for (i = 0; i < priv->channels.num; i++)
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				rq_stats_desc[j].format, i);
 
-	for (tc = 0; tc < priv->params.num_tc; tc++)
-		for (i = 0; i < priv->params.num_channels; i++)
+	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+		for (i = 0; i < priv->channels.num; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				sprintf(data + (idx++) * ETH_GSTRING_LEN,
 					sq_stats_desc[j].format,
-					priv->channeltc_to_txq_map[i][tc]);
+					priv->channel_tc2txq[i][tc]);
 }
 
 static void mlx5e_get_strings(struct net_device *dev,
@@ -303,6 +301,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 				    struct ethtool_stats *stats, u64 *data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *channels;
 	struct mlx5_priv *mlx5_priv;
 	int i, j, tc, prio, idx = 0;
 	unsigned long pfc_combined;
@@ -313,6 +312,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 	mutex_lock(&priv->state_lock);
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_update_stats(priv);
+	channels = &priv->channels;
 	mutex_unlock(&priv->state_lock);
 
 	for (i = 0; i < NUM_SW_COUNTERS; i++)
@@ -382,16 +382,16 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 		return;
 
 	/* per channel counters */
-	for (i = 0; i < priv->params.num_channels; i++)
+	for (i = 0; i < channels->num; i++)
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			data[idx++] =
-			       MLX5E_READ_CTR64_CPU(&priv->channel[i]->rq.stats,
+			       MLX5E_READ_CTR64_CPU(&channels->c[i]->rq.stats,
 						    rq_stats_desc, j);
 
-	for (tc = 0; tc < priv->params.num_tc; tc++)
-		for (i = 0; i < priv->params.num_channels; i++)
+	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+		for (i = 0; i < channels->num; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
-				data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel[i]->sq[tc].stats,
+				data[idx++] = MLX5E_READ_CTR64_CPU(&channels->c[i]->sq[tc].stats,
 								   sq_stats_desc, j);
 }
 
@@ -406,8 +406,8 @@ static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
 	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		return num_wqe;
 
-	stride_size = 1 << priv->params.mpwqe_log_stride_sz;
-	num_strides = 1 << priv->params.mpwqe_log_num_strides;
+	stride_size = 1 << priv->channels.params.mpwqe_log_stride_sz;
+	num_strides = 1 << priv->channels.params.mpwqe_log_num_strides;
 	wqe_size = stride_size * num_strides;
 
 	packets_per_wqe = wqe_size /
@@ -427,8 +427,8 @@ static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
 	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		return num_packets;
 
-	stride_size = 1 << priv->params.mpwqe_log_stride_sz;
-	num_strides = 1 << priv->params.mpwqe_log_num_strides;
+	stride_size = 1 << priv->channels.params.mpwqe_log_stride_sz;
+	num_strides = 1 << priv->channels.params.mpwqe_log_num_strides;
 	wqe_size = stride_size * num_strides;
 
 	num_packets = (1 << order_base_2(num_packets));
@@ -443,26 +443,25 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 				struct ethtool_ringparam *param)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int rq_wq_type = priv->params.rq_wq_type;
+	int rq_wq_type = priv->channels.params.rq_wq_type;
 
 	param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
 							 1 << mlx5_max_log_rq_size(rq_wq_type));
 	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
 	param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-						     1 << priv->params.log_rq_size);
-	param->tx_pending     = 1 << priv->params.log_sq_size;
+						     1 << priv->channels.params.log_rq_size);
+	param->tx_pending     = 1 << priv->channels.params.log_sq_size;
 }
 
 static int mlx5e_set_ringparam(struct net_device *dev,
 			       struct ethtool_ringparam *param)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	bool was_opened;
-	int rq_wq_type = priv->params.rq_wq_type;
+	int rq_wq_type = priv->channels.params.rq_wq_type;
+	struct mlx5e_channels new_channels = {};
 	u32 rx_pending_wqes;
 	u32 min_rq_size;
 	u32 max_rq_size;
-	u16 min_rx_wqes;
 	u8 log_rq_size;
 	u8 log_sq_size;
 	u32 num_mtts;
@@ -500,7 +499,7 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 	}
 
 	num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
-	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+	if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
 	    !MLX5E_VALID_NUM_MTTS(num_mtts)) {
 		netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
 			    __func__, param->rx_pending);
@@ -522,26 +521,29 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 
 	log_rq_size = order_base_2(rx_pending_wqes);
 	log_sq_size = order_base_2(param->tx_pending);
-	min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes);
 
-	if (log_rq_size == priv->params.log_rq_size &&
-	    log_sq_size == priv->params.log_sq_size &&
-	    min_rx_wqes == priv->params.min_rx_wqes)
+	if (log_rq_size == priv->channels.params.log_rq_size &&
+	    log_sq_size == priv->channels.params.log_sq_size)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(dev);
+	new_channels.params = priv->channels.params;
+	new_channels.params.log_rq_size = log_rq_size;
+	new_channels.params.log_sq_size = log_sq_size;
 
-	priv->params.log_rq_size = log_rq_size;
-	priv->params.log_sq_size = log_sq_size;
-	priv->params.min_rx_wqes = min_rx_wqes;
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto unlock;
+	}
+
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto unlock;
 
-	if (was_opened)
-		err = mlx5e_open_locked(dev);
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
+unlock:
 	mutex_unlock(&priv->state_lock);
 
 	return err;
@@ -553,7 +555,7 @@ static void mlx5e_get_channels(struct net_device *dev,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
 	ch->max_combined   = priv->profile->max_nch(priv->mdev);
-	ch->combined_count = priv->params.num_channels;
+	ch->combined_count = priv->channels.params.num_channels;
 }
 
 static int mlx5e_set_channels(struct net_device *dev,
@@ -561,8 +563,8 @@ static int mlx5e_set_channels(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	unsigned int count = ch->combined_count;
+	struct mlx5e_channels new_channels = {};
 	bool arfs_enabled;
-	bool was_opened;
 	int err = 0;
 
 	if (!count) {
@@ -571,27 +573,32 @@ static int mlx5e_set_channels(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	if (priv->params.num_channels == count)
+	if (priv->channels.params.num_channels == count)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(dev);
+	new_channels.params = priv->channels.params;
+	new_channels.params.num_channels = count;
+	mlx5e_build_default_indir_rqt(priv->mdev, new_channels.params.indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, count);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+
+	/* Create fresh channels with new parameters */
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
 
 	arfs_enabled = dev->features & NETIF_F_NTUPLE;
 	if (arfs_enabled)
 		mlx5e_arfs_disable(priv);
 
-	priv->params.num_channels = count;
-	mlx5e_build_default_indir_rqt(priv->mdev, priv->params.indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, count);
-
-	if (was_opened)
-		err = mlx5e_open_locked(dev);
-	if (err)
-		goto out;
+	/* Switch to new channels, set new parameters and close old ones */
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
 	if (arfs_enabled) {
 		err = mlx5e_arfs_enable(priv);
@@ -614,49 +621,24 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
 		return -EOPNOTSUPP;
 
-	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation.usec;
-	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts;
-	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation.usec;
-	coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation.pkts;
-	coal->use_adaptive_rx_coalesce = priv->params.rx_am_enabled;
+	coal->rx_coalesce_usecs       = priv->channels.params.rx_cq_moderation.usec;
+	coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts;
+	coal->tx_coalesce_usecs       = priv->channels.params.tx_cq_moderation.usec;
+	coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts;
+	coal->use_adaptive_rx_coalesce = priv->channels.params.rx_am_enabled;
 
 	return 0;
 }
 
-static int mlx5e_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+static void
+mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_channel *c;
-	bool restart =
-		!!coal->use_adaptive_rx_coalesce != priv->params.rx_am_enabled;
-	bool was_opened;
-	int err = 0;
 	int tc;
 	int i;
 
-	if (!MLX5_CAP_GEN(mdev, cq_moderation))
-		return -EOPNOTSUPP;
-
-	mutex_lock(&priv->state_lock);
-
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened && restart) {
-		mlx5e_close_locked(netdev);
-		priv->params.rx_am_enabled = !!coal->use_adaptive_rx_coalesce;
-	}
-
-	priv->params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
-	priv->params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
-	priv->params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
-	priv->params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
-
-	if (!was_opened || restart)
-		goto out;
-
-	for (i = 0; i < priv->params.num_channels; ++i) {
-		c = priv->channel[i];
+	for (i = 0; i < priv->channels.num; ++i) {
+		struct mlx5e_channel *c = priv->channels.c[i];
 
 		for (tc = 0; tc < c->num_tc; tc++) {
 			mlx5_core_modify_cq_moderation(mdev,
@@ -669,11 +651,50 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 					       coal->rx_coalesce_usecs,
 					       coal->rx_max_coalesced_frames);
 	}
+}
 
-out:
-	if (was_opened && restart)
-		err = mlx5e_open_locked(netdev);
+static int mlx5e_set_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv    = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channels new_channels = {};
+	int err = 0;
+	bool reset;
+
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&priv->state_lock);
+	new_channels.params = priv->channels.params;
+
+	new_channels.params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
+	new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
+	new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
+	new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
+	new_channels.params.rx_am_enabled         = !!coal->use_adaptive_rx_coalesce;
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+	/* we are opened */
+
+	reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_am_enabled;
+	if (!reset) {
+		mlx5e_set_priv_channels_coalesce(priv, coal);
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+
+	/* open fresh channels with new coal parameters */
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
+
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
+out:
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
@@ -968,7 +989,7 @@ static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	return sizeof(priv->params.toeplitz_hash_key);
+	return sizeof(priv->channels.params.toeplitz_hash_key);
 }
 
 static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
@@ -982,15 +1003,15 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 	if (indir)
-		memcpy(indir, priv->params.indirection_rqt,
-		       sizeof(priv->params.indirection_rqt));
+		memcpy(indir, priv->channels.params.indirection_rqt,
+		       sizeof(priv->channels.params.indirection_rqt));
 
 	if (key)
-		memcpy(key, priv->params.toeplitz_hash_key,
-		       sizeof(priv->params.toeplitz_hash_key));
+		memcpy(key, priv->channels.params.toeplitz_hash_key,
+		       sizeof(priv->channels.params.toeplitz_hash_key));
 
 	if (hfunc)
-		*hfunc = priv->params.rss_hfunc;
+		*hfunc = priv->channels.params.rss_hfunc;
 
 	return 0;
 }
@@ -1006,7 +1027,7 @@ static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 }
@@ -1030,25 +1051,37 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 
 	mutex_lock(&priv->state_lock);
 
-	if (indir) {
-		u32 rqtn = priv->indir_rqt.rqtn;
-
-		memcpy(priv->params.indirection_rqt, indir,
-		       sizeof(priv->params.indirection_rqt));
-		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
-	}
-
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    hfunc != priv->params.rss_hfunc) {
-		priv->params.rss_hfunc = hfunc;
+	    hfunc != priv->channels.params.rss_hfunc) {
+		priv->channels.params.rss_hfunc = hfunc;
 		hash_changed = true;
 	}
 
+	if (indir) {
+		memcpy(priv->channels.params.indirection_rqt, indir,
+		       sizeof(priv->channels.params.indirection_rqt));
+
+		if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+			u32 rqtn = priv->indir_rqt.rqtn;
+			struct mlx5e_redirect_rqt_param rrp = {
+				.is_rss = true,
+				{
+					.rss = {
+						.hfunc = priv->channels.params.rss_hfunc,
+						.channels  = &priv->channels,
+					},
+				},
+			};
+
+			mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
+		}
+	}
+
 	if (key) {
-		memcpy(priv->params.toeplitz_hash_key, key,
-		       sizeof(priv->params.toeplitz_hash_key));
+		memcpy(priv->channels.params.toeplitz_hash_key, key,
+		       sizeof(priv->channels.params.toeplitz_hash_key));
 		hash_changed = hash_changed ||
-			       priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+			       priv->channels.params.rss_hfunc == ETH_RSS_HASH_TOP;
 	}
 
 	if (hash_changed)
@@ -1069,7 +1102,7 @@ static int mlx5e_get_rxnfc(struct net_device *netdev,
 
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
-		info->data = priv->params.num_channels;
+		info->data = priv->channels.params.num_channels;
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
@@ -1097,7 +1130,7 @@ static int mlx5e_get_tunable(struct net_device *dev,
 
 	switch (tuna->id) {
 	case ETHTOOL_TX_COPYBREAK:
-		*(u32 *)data = priv->params.tx_max_inline;
+		*(u32 *)data = priv->channels.params.tx_max_inline;
 		break;
 	default:
 		err = -EINVAL;
@@ -1113,9 +1146,11 @@ static int mlx5e_set_tunable(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	bool was_opened;
-	u32 val;
+	struct mlx5e_channels new_channels = {};
 	int err = 0;
+	u32 val;
+
+	mutex_lock(&priv->state_lock);
 
 	switch (tuna->id) {
 	case ETHTOOL_TX_COPYBREAK:
@@ -1125,24 +1160,26 @@ static int mlx5e_set_tunable(struct net_device *dev,
 			break;
 		}
 
-		mutex_lock(&priv->state_lock);
+		new_channels.params = priv->channels.params;
+		new_channels.params.tx_max_inline = val;
 
-		was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-		if (was_opened)
-			mlx5e_close_locked(dev);
-
-		priv->params.tx_max_inline = val;
+		if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+			priv->channels.params = new_channels.params;
+			break;
+		}
 
-		if (was_opened)
-			err = mlx5e_open_locked(dev);
+		err = mlx5e_open_channels(priv, &new_channels);
+		if (err)
+			break;
+		mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
-		mutex_unlock(&priv->state_lock);
 		break;
 	default:
 		err = -EINVAL;
 		break;
 	}
 
+	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
@@ -1442,15 +1479,15 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channels new_channels = {};
 	bool rx_mode_changed;
 	u8 rx_cq_period_mode;
 	int err = 0;
-	bool reset;
 
 	rx_cq_period_mode = enable ?
 		MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 		MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
-	rx_mode_changed = rx_cq_period_mode != priv->params.rx_cq_period_mode;
+	rx_mode_changed = rx_cq_period_mode != priv->channels.params.rx_cq_period_mode;
 
 	if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE &&
 	    !MLX5_CAP_GEN(mdev, cq_period_start_from_cqe))
@@ -1459,16 +1496,51 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
 	if (!rx_mode_changed)
 		return 0;
 
-	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (reset)
-		mlx5e_close_locked(netdev);
+	new_channels.params = priv->channels.params;
+	mlx5e_set_rx_cq_mode_params(&new_channels.params, rx_cq_period_mode);
 
-	mlx5e_set_rx_cq_mode_params(&priv->params, rx_cq_period_mode);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		return 0;
+	}
 
-	if (reset)
-		err = mlx5e_open_locked(netdev);
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		return err;
 
-	return err;
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	return 0;
+}
+
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val)
+{
+	bool curr_val = MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS);
+	struct mlx5e_channels new_channels = {};
+	int err = 0;
+
+	if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
+		return new_val ? -EOPNOTSUPP : 0;
+
+	if (curr_val == new_val)
+		return 0;
+
+	new_channels.params = priv->channels.params;
+	MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val);
+
+	mlx5e_set_rq_type_params(priv->mdev, &new_channels.params,
+				 new_channels.params.rq_wq_type);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		return 0;
+	}
+
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		return err;
+
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	return 0;
 }
 
 static int set_pflag_rx_cqe_compress(struct net_device *netdev,
@@ -1486,8 +1558,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 	}
 
 	mlx5e_modify_rx_cqe_compression_locked(priv, enable);
-	priv->params.rx_cqe_compress_def = enable;
-	mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
+	priv->channels.params.rx_cqe_compress_def = enable;
 
 	return 0;
 }
@@ -1499,7 +1570,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	bool enable = !!(wanted_flags & flag);
-	u32 changes = wanted_flags ^ priv->params.pflags;
+	u32 changes = wanted_flags ^ priv->channels.params.pflags;
 	int err;
 
 	if (!(changes & flag))
@@ -1512,7 +1583,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
 		return err;
 	}
 
-	MLX5E_SET_PFLAG(priv, flag, enable);
+	MLX5E_SET_PFLAG(&priv->channels.params, flag, enable);
 	return 0;
 }
 
@@ -1541,7 +1612,7 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	return priv->params.pflags;
+	return priv->channels.params.pflags;
 }
 
 static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index f2762e45c8ae..576d6787b484 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -159,14 +159,10 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
 				 enum mlx5e_vlan_rule_type rule_type,
 				 u16 vid, struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
 	struct mlx5_flow_table *ft = priv->fs.vlan.ft.t;
 	struct mlx5_flow_destination dest;
 	struct mlx5_flow_handle **rule_p;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	int err = 0;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -659,11 +655,7 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 			u16 etype,
 			u8 proto)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	int err = 0;
@@ -800,7 +792,7 @@ err:
 	return err;
 }
 
-static void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
 {
 	struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
 
@@ -808,14 +800,19 @@ static void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
 	mlx5e_destroy_flow_table(&ttc->ft);
 }
 
-static int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn)
 {
 	struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
+	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5e_flow_table *ft = &ttc->ft;
 	int err;
 
-	ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
-				       MLX5E_TTC_TABLE_SIZE, MLX5E_TTC_FT_LEVEL, 0);
+	ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE;
+	ft_attr.level = MLX5E_TTC_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.underlay_qpn = underlay_qpn;
+
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
 	if (IS_ERR(ft->t)) {
 		err = PTR_ERR(ft->t);
 		ft->t = NULL;
@@ -848,13 +845,9 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
 static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 				  struct mlx5e_l2_rule *ai, int type)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
 	struct mlx5_flow_table *ft = priv->fs.l2.ft.t;
 	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_spec *spec;
 	int err = 0;
 	u8 *mc_dmac;
@@ -985,12 +978,16 @@ static int mlx5e_create_l2_table(struct mlx5e_priv *priv)
 {
 	struct mlx5e_l2_table *l2_table = &priv->fs.l2;
 	struct mlx5e_flow_table *ft = &l2_table->ft;
+	struct mlx5_flow_table_attr ft_attr = {};
 	int err;
 
 	ft->num_groups = 0;
-	ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
-				       MLX5E_L2_TABLE_SIZE, MLX5E_L2_FT_LEVEL, 0);
 
+	ft_attr.max_fte = MLX5E_L2_TABLE_SIZE;
+	ft_attr.level = MLX5E_L2_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
 	if (IS_ERR(ft->t)) {
 		err = PTR_ERR(ft->t);
 		ft->t = NULL;
@@ -1088,11 +1085,16 @@ static int mlx5e_create_vlan_table_groups(struct mlx5e_flow_table *ft)
 static int mlx5e_create_vlan_table(struct mlx5e_priv *priv)
 {
 	struct mlx5e_flow_table *ft = &priv->fs.vlan.ft;
+	struct mlx5_flow_table_attr ft_attr = {};
 	int err;
 
 	ft->num_groups = 0;
-	ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
-				       MLX5E_VLAN_TABLE_SIZE, MLX5E_VLAN_FT_LEVEL, 0);
+
+	ft_attr.max_fte = MLX5E_VLAN_TABLE_SIZE;
+	ft_attr.level = MLX5E_VLAN_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
 
 	if (IS_ERR(ft->t)) {
 		err = PTR_ERR(ft->t);
@@ -1145,7 +1147,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 		priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
 	}
 
-	err = mlx5e_create_ttc_table(priv);
+	err = mlx5e_create_ttc_table(priv, 0);
 	if (err) {
 		netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
 			   err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d55fff0ba388..85bf4a389295 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -390,7 +390,7 @@ static int validate_flow(struct mlx5e_priv *priv,
 	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
 		return -EINVAL;
 
-	if (fs->ring_cookie >= priv->params.num_channels &&
+	if (fs->ring_cookie >= priv->channels.params.num_channels &&
 	    fs->ring_cookie != RX_CLS_FLOW_DISC)
 		return -EINVAL;
 
@@ -564,6 +564,7 @@ int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *i
 	int idx = 0;
 	int err = 0;
 
+	info->data = MAX_NUM_OF_ETHTOOL_RULES;
 	while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
 		err = mlx5e_ethtool_get_flow(priv, info, location);
 		if (!err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8ef64c4db2c2..a61b71b6fff3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -31,28 +31,24 @@
  */
 
 #include <net/tc_act/tc_gact.h>
-#include <linux/crash_dump.h>
 #include <net/pkt_cls.h>
 #include <linux/mlx5/fs.h>
 #include <net/vxlan.h>
 #include <linux/bpf.h>
+#include "eswitch.h"
 #include "en.h"
 #include "en_tc.h"
-#include "eswitch.h"
+#include "en_rep.h"
 #include "vxlan.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param	wq;
-	bool			am_enabled;
 };
 
 struct mlx5e_sq_param {
 	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
 	struct mlx5_wq_param       wq;
-	u16                        max_inline;
-	u8                         min_inline_mode;
-	enum mlx5e_sq_type         type;
 };
 
 struct mlx5e_cq_param {
@@ -79,49 +75,47 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 		MLX5_CAP_ETH(mdev, reg_umr_sq);
 }
 
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+			      struct mlx5e_params *params, u8 rq_type)
 {
-	priv->params.rq_wq_type = rq_type;
-	priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
-	switch (priv->params.rq_wq_type) {
+	params->rq_wq_type = rq_type;
+	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		priv->params.log_rq_size = is_kdump_kernel() ?
+		params->log_rq_size = is_kdump_kernel() ?
 			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
 			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
-		priv->params.mpwqe_log_stride_sz =
-			MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
-			MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(priv->mdev) :
-			MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(priv->mdev);
-		priv->params.mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
-			priv->params.mpwqe_log_stride_sz;
+		params->mpwqe_log_stride_sz =
+			MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
+			MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) :
+			MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
+		params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
+			params->mpwqe_log_stride_sz;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		priv->params.log_rq_size = is_kdump_kernel() ?
+		params->log_rq_size = is_kdump_kernel() ?
 			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
 
 		/* Extra room needed for build_skb */
-		priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM +
+		params->lro_wqe_sz -= MLX5_RX_HEADROOM +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	}
-	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
-					       BIT(priv->params.log_rq_size));
 
-	mlx5_core_info(priv->mdev,
-		       "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
-		       priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
-		       BIT(priv->params.log_rq_size),
-		       BIT(priv->params.mpwqe_log_stride_sz),
-		       MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS));
+	mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
+		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
+		       BIT(params->log_rq_size),
+		       BIT(params->mpwqe_log_stride_sz),
+		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
-static void mlx5e_set_rq_priv_params(struct mlx5e_priv *priv)
+static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
-	u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(priv->mdev) &&
-		    !priv->xdp_prog ?
+	u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) &&
+		    !params->xdp_prog ?
 		    MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
 		    MLX5_WQ_TYPE_LINKED_LIST;
-	mlx5e_set_rq_type_params(priv, rq_type);
+	mlx5e_set_rq_type_params(mdev, params, rq_type);
 }
 
 static void mlx5e_update_carrier(struct mlx5e_priv *priv)
@@ -174,15 +168,17 @@ unlock:
 
 static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 {
-	struct mlx5e_sw_stats *s = &priv->stats.sw;
+	struct mlx5e_sw_stats temp, *s = &temp;
 	struct mlx5e_rq_stats *rq_stats;
 	struct mlx5e_sq_stats *sq_stats;
 	u64 tx_offload_none = 0;
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->params.num_channels; i++) {
-		rq_stats = &priv->channel[i]->rq.stats;
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
+
+		rq_stats = &c->rq.stats;
 
 		s->rx_packets	+= rq_stats->packets;
 		s->rx_bytes	+= rq_stats->bytes;
@@ -204,8 +200,8 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 
-		for (j = 0; j < priv->params.num_tc; j++) {
-			sq_stats = &priv->channel[i]->sq[j].stats;
+		for (j = 0; j < priv->channels.params.num_tc; j++) {
+			sq_stats = &c->sq[j].stats;
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
@@ -229,6 +225,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
 				priv->stats.pport.phy_counters,
 				counter_set.phys_layer_cntrs.link_down_events);
+	memcpy(&priv->stats.sw, s, sizeof(*s));
 }
 
 static void mlx5e_update_vport_counters(struct mlx5e_priv *priv)
@@ -243,7 +240,6 @@ static void mlx5e_update_vport_counters(struct mlx5e_priv *priv)
 	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
 	MLX5_SET(query_vport_counter_in, in, other_vport, 0);
 
-	memset(out, 0, outlen);
 	mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
 }
 
@@ -402,8 +398,10 @@ static inline int mlx5e_get_wqe_mtt_sz(void)
 		     MLX5_UMR_MTT_ALIGNMENT);
 }
 
-static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5e_sq *sq,
-				       struct mlx5e_umr_wqe *wqe, u16 ix)
+static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
+				       struct mlx5e_icosq *sq,
+				       struct mlx5e_umr_wqe *wqe,
+				       u16 ix)
 {
 	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->ctrl;
 	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
@@ -493,11 +491,10 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
 	kfree(rq->mpwqe.info);
 }
 
-static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
+static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 				 u64 npages, u8 page_shift,
 				 struct mlx5_core_mkey *umr_mkey)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	void *mkc;
 	u32 *in;
@@ -531,21 +528,20 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
 	return err;
 }
 
-static int mlx5e_create_rq_umr_mkey(struct mlx5e_rq *rq)
+static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq)
 {
-	struct mlx5e_priv *priv = rq->priv;
-	u64 num_mtts = MLX5E_REQUIRED_MTTS(BIT(priv->params.log_rq_size));
+	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->wq));
 
-	return mlx5e_create_umr_mkey(priv, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
 }
 
-static int mlx5e_create_rq(struct mlx5e_channel *c,
-			   struct mlx5e_rq_param *param,
-			   struct mlx5e_rq *rq)
+static int mlx5e_alloc_rq(struct mlx5e_channel *c,
+			  struct mlx5e_params *params,
+			  struct mlx5e_rq_param *rqp,
+			  struct mlx5e_rq *rq)
 {
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	void *rqc = param->rqc;
+	struct mlx5_core_dev *mdev = c->mdev;
+	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
 	u32 byte_count;
 	u32 frag_sz;
@@ -554,9 +550,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
 
-	err = mlx5_wq_ll_create(mdev, &param->wq, rqc_wq, &rq->wq,
+	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
 				&rq->wq_ctrl);
 	if (err)
 		return err;
@@ -565,15 +561,15 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 
 	wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 
-	rq->wq_type = priv->params.rq_wq_type;
+	rq->wq_type = params->rq_wq_type;
 	rq->pdev    = c->pdev;
 	rq->netdev  = c->netdev;
-	rq->tstamp  = &priv->tstamp;
+	rq->tstamp  = c->tstamp;
 	rq->channel = c;
 	rq->ix      = c->ix;
-	rq->priv    = c->priv;
+	rq->mdev    = mdev;
 
-	rq->xdp_prog = priv->xdp_prog ? bpf_prog_inc(priv->xdp_prog) : NULL;
+	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
 	if (IS_ERR(rq->xdp_prog)) {
 		err = PTR_ERR(rq->xdp_prog);
 		rq->xdp_prog = NULL;
@@ -588,24 +584,26 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		rq->rx_headroom = MLX5_RX_HEADROOM;
 	}
 
-	switch (priv->params.rq_wq_type) {
+	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		if (mlx5e_is_vf_vport_rep(priv)) {
-			err = -EINVAL;
-			goto err_rq_wq_destroy;
-		}
 
-		rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
-		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
-		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
+		rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe;
+		if (!rq->handle_rx_cqe) {
+			err = -EINVAL;
+			netdev_err(c->netdev, "RX handler of MPWQE RQ is not set, err %d\n", err);
+			goto err_rq_wq_destroy;
+		}
+
+		rq->mpwqe_stride_sz = BIT(params->mpwqe_log_stride_sz);
+		rq->mpwqe_num_strides = BIT(params->mpwqe_log_num_strides);
 
 		rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
 		byte_count = rq->buff.wqe_sz;
 
-		err = mlx5e_create_rq_umr_mkey(rq);
+		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_wq_destroy;
 		rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
@@ -621,18 +619,20 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 			err = -ENOMEM;
 			goto err_rq_wq_destroy;
 		}
-
-		if (mlx5e_is_vf_vport_rep(priv))
-			rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep;
-		else
-			rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
-
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
-		rq->buff.wqe_sz = (priv->params.lro_en) ?
-				priv->params.lro_wqe_sz :
-				MLX5E_SW2HW_MTU(priv->netdev->mtu);
+		rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe;
+		if (!rq->handle_rx_cqe) {
+			kfree(rq->dma_info);
+			err = -EINVAL;
+			netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err);
+			goto err_rq_wq_destroy;
+		}
+
+		rq->buff.wqe_sz = params->lro_en  ?
+				params->lro_wqe_sz :
+				MLX5E_SW2HW_MTU(c->netdev->mtu);
 		byte_count = rq->buff.wqe_sz;
 
 		/* calc the required page order */
@@ -656,8 +656,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 	}
 
 	INIT_WORK(&rq->am.work, mlx5e_rx_am_work);
-	rq->am.mode = priv->params.rx_cq_period_mode;
-
+	rq->am.mode = params->rx_cq_period_mode;
 	rq->page_cache.head = 0;
 	rq->page_cache.tail = 0;
 
@@ -674,7 +673,7 @@ err_rq_wq_destroy:
 	return err;
 }
 
-static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
+static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
 	int i;
 
@@ -684,7 +683,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		mlx5e_rq_free_mpwqe_info(rq);
-		mlx5_core_destroy_mkey(rq->priv->mdev, &rq->umr_mkey);
+		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		kfree(rq->dma_info);
@@ -699,10 +698,10 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 
-static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
+static int mlx5e_create_rq(struct mlx5e_rq *rq,
+			   struct mlx5e_rq_param *param)
 {
-	struct mlx5e_priv *priv = rq->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_dev *mdev = rq->mdev;
 
 	void *in;
 	void *rqc;
@@ -723,7 +722,6 @@ static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
 
 	MLX5_SET(rqc,  rqc, cqn,		rq->cq.mcq.cqn);
 	MLX5_SET(rqc,  rqc, state,		MLX5_RQC_STATE_RST);
-	MLX5_SET(rqc,  rqc, vsd, priv->params.vlan_strip_disable);
 	MLX5_SET(wq,   wq,  log_wq_pg_sz,	rq->wq_ctrl.buf.page_shift -
 						MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
@@ -742,8 +740,7 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
 				 int next_state)
 {
 	struct mlx5e_channel *c = rq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_dev *mdev = c->mdev;
 
 	void *in;
 	void *rqc;
@@ -767,7 +764,7 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
 	return err;
 }
 
-static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
+static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable)
 {
 	struct mlx5e_channel *c = rq->channel;
 	struct mlx5e_priv *priv = c->priv;
@@ -787,6 +784,35 @@ static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
 
 	MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY);
 	MLX5_SET64(modify_rq_in, in, modify_bitmask,
+		   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS);
+	MLX5_SET(rqc, rqc, scatter_fcs, enable);
+	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
+
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+
+	kvfree(in);
+
+	return err;
+}
+
+static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
+{
+	struct mlx5e_channel *c = rq->channel;
+	struct mlx5_core_dev *mdev = c->mdev;
+	void *in;
+	void *rqc;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_rq_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
+
+	MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY);
+	MLX5_SET64(modify_rq_in, in, modify_bitmask,
 		   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD);
 	MLX5_SET(rqc, rqc, vsd, vsd);
 	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
@@ -798,25 +824,28 @@ static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
 	return err;
 }
 
-static void mlx5e_disable_rq(struct mlx5e_rq *rq)
+static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 {
-	mlx5_core_destroy_rq(rq->priv->mdev, rq->rqn);
+	mlx5_core_destroy_rq(rq->mdev, rq->rqn);
 }
 
 static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq)
 {
 	unsigned long exp_time = jiffies + msecs_to_jiffies(20000);
 	struct mlx5e_channel *c = rq->channel;
-	struct mlx5e_priv *priv = c->priv;
+
 	struct mlx5_wq_ll *wq = &rq->wq;
+	u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
 
 	while (time_before(jiffies, exp_time)) {
-		if (wq->cur_sz >= priv->params.min_rx_wqes)
+		if (wq->cur_sz >= min_wqes)
 			return 0;
 
 		msleep(20);
 	}
 
+	netdev_warn(c->netdev, "Failed to get min RX wqes on RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
+		    rq->rqn, wq->cur_sz, min_wqes);
 	return -ETIMEDOUT;
 }
 
@@ -842,83 +871,128 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 }
 
 static int mlx5e_open_rq(struct mlx5e_channel *c,
+			 struct mlx5e_params *params,
 			 struct mlx5e_rq_param *param,
 			 struct mlx5e_rq *rq)
 {
-	struct mlx5e_sq *sq = &c->icosq;
-	u16 pi = sq->pc & sq->wq.sz_m1;
 	int err;
 
-	err = mlx5e_create_rq(c, param, rq);
+	err = mlx5e_alloc_rq(c, params, param, rq);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_rq(rq, param);
+	err = mlx5e_create_rq(rq, param);
 	if (err)
-		goto err_destroy_rq;
+		goto err_free_rq;
 
-	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
 	if (err)
-		goto err_disable_rq;
+		goto err_destroy_rq;
 
-	if (param->am_enabled)
+	if (params->rx_am_enabled)
 		set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
-	sq->db.ico_wqe[pi].num_wqebbs = 1;
-	mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
-
 	return 0;
 
-err_disable_rq:
-	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	mlx5e_disable_rq(rq);
 err_destroy_rq:
 	mlx5e_destroy_rq(rq);
+err_free_rq:
+	mlx5e_free_rq(rq);
 
 	return err;
 }
 
-static void mlx5e_close_rq(struct mlx5e_rq *rq)
+static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+{
+	struct mlx5e_icosq *sq = &rq->channel->icosq;
+	u16 pi = sq->pc & sq->wq.sz_m1;
+	struct mlx5e_tx_wqe *nopwqe;
+
+	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
+	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
+	sq->db.ico_wqe[pi].num_wqebbs = 1;
+	nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+}
+
+static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
-	cancel_work_sync(&rq->am.work);
+}
 
-	mlx5e_disable_rq(rq);
-	mlx5e_free_rx_descs(rq);
+static void mlx5e_close_rq(struct mlx5e_rq *rq)
+{
+	cancel_work_sync(&rq->am.work);
 	mlx5e_destroy_rq(rq);
+	mlx5e_free_rx_descs(rq);
+	mlx5e_free_rq(rq);
 }
 
-static void mlx5e_free_sq_xdp_db(struct mlx5e_sq *sq)
+static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kfree(sq->db.xdp.di);
-	kfree(sq->db.xdp.wqe_info);
+	kfree(sq->db.di);
 }
 
-static int mlx5e_alloc_sq_xdp_db(struct mlx5e_sq *sq, int numa)
+static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.xdp.di = kzalloc_node(sizeof(*sq->db.xdp.di) * wq_sz,
+	sq->db.di = kzalloc_node(sizeof(*sq->db.di) * wq_sz,
 				     GFP_KERNEL, numa);
-	sq->db.xdp.wqe_info = kzalloc_node(sizeof(*sq->db.xdp.wqe_info) * wq_sz,
-					   GFP_KERNEL, numa);
-	if (!sq->db.xdp.di || !sq->db.xdp.wqe_info) {
-		mlx5e_free_sq_xdp_db(sq);
+	if (!sq->db.di) {
+		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
 	}
 
 	return 0;
 }
 
-static void mlx5e_free_sq_ico_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param,
+			     struct mlx5e_xdpsq *sq)
+{
+	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
+	struct mlx5_core_dev *mdev = c->mdev;
+	int err;
+
+	sq->pdev      = c->pdev;
+	sq->mkey_be   = c->mkey_be;
+	sq->channel   = c;
+	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
+	sq->min_inline_mode = params->tx_min_inline_mode;
+
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	if (err)
+		return err;
+	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
+
+	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
+	if (err)
+		goto err_sq_wq_destroy;
+
+	return 0;
+
+err_sq_wq_destroy:
+	mlx5_wq_destroy(&sq->wq_ctrl);
+
+	return err;
+}
+
+static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
+{
+	mlx5e_free_xdpsq_db(sq);
+	mlx5_wq_destroy(&sq->wq_ctrl);
+}
+
+static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
 	kfree(sq->db.ico_wqe);
 }
 
-static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
+static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
@@ -930,155 +1004,128 @@ static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
 	return 0;
 }
 
-static void mlx5e_free_sq_txq_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
+			     struct mlx5e_sq_param *param,
+			     struct mlx5e_icosq *sq)
 {
-	kfree(sq->db.txq.wqe_info);
-	kfree(sq->db.txq.dma_fifo);
-	kfree(sq->db.txq.skb);
-}
+	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
+	struct mlx5_core_dev *mdev = c->mdev;
+	int err;
 
-static int mlx5e_alloc_sq_txq_db(struct mlx5e_sq *sq, int numa)
-{
-	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
-	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+	sq->pdev      = c->pdev;
+	sq->mkey_be   = c->mkey_be;
+	sq->channel   = c;
+	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
-	sq->db.txq.skb = kzalloc_node(wq_sz * sizeof(*sq->db.txq.skb),
-				      GFP_KERNEL, numa);
-	sq->db.txq.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.txq.dma_fifo),
-					   GFP_KERNEL, numa);
-	sq->db.txq.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.txq.wqe_info),
-					   GFP_KERNEL, numa);
-	if (!sq->db.txq.skb || !sq->db.txq.dma_fifo || !sq->db.txq.wqe_info) {
-		mlx5e_free_sq_txq_db(sq);
-		return -ENOMEM;
-	}
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	if (err)
+		return err;
+	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	sq->dma_fifo_mask = df_sz - 1;
+	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
+	if (err)
+		goto err_sq_wq_destroy;
+
+	sq->edge = (sq->wq.sz_m1 + 1) - MLX5E_ICOSQ_MAX_WQEBBS;
 
 	return 0;
+
+err_sq_wq_destroy:
+	mlx5_wq_destroy(&sq->wq_ctrl);
+
+	return err;
 }
 
-static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
+static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 {
-	switch (sq->type) {
-	case MLX5E_SQ_TXQ:
-		mlx5e_free_sq_txq_db(sq);
-		break;
-	case MLX5E_SQ_ICO:
-		mlx5e_free_sq_ico_db(sq);
-		break;
-	case MLX5E_SQ_XDP:
-		mlx5e_free_sq_xdp_db(sq);
-		break;
-	}
+	mlx5e_free_icosq_db(sq);
+	mlx5_wq_destroy(&sq->wq_ctrl);
 }
 
-static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
+static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
-	switch (sq->type) {
-	case MLX5E_SQ_TXQ:
-		return mlx5e_alloc_sq_txq_db(sq, numa);
-	case MLX5E_SQ_ICO:
-		return mlx5e_alloc_sq_ico_db(sq, numa);
-	case MLX5E_SQ_XDP:
-		return mlx5e_alloc_sq_xdp_db(sq, numa);
-	}
-
-	return 0;
+	kfree(sq->db.wqe_info);
+	kfree(sq->db.dma_fifo);
 }
 
-static int mlx5e_sq_get_max_wqebbs(u8 sq_type)
+static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 {
-	switch (sq_type) {
-	case MLX5E_SQ_ICO:
-		return MLX5E_ICOSQ_MAX_WQEBBS;
-	case MLX5E_SQ_XDP:
-		return MLX5E_XDP_TX_WQEBBS;
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+	sq->db.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.dma_fifo),
+					   GFP_KERNEL, numa);
+	sq->db.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.wqe_info),
+					   GFP_KERNEL, numa);
+	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
+		mlx5e_free_txqsq_db(sq);
+		return -ENOMEM;
 	}
-	return MLX5_SEND_WQE_MAX_WQEBBS;
+
+	sq->dma_fifo_mask = df_sz - 1;
+
+	return 0;
 }
 
-static int mlx5e_create_sq(struct mlx5e_channel *c,
-			   int tc,
-			   struct mlx5e_sq_param *param,
-			   struct mlx5e_sq *sq)
+static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
+			     int txq_ix,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param,
+			     struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	void *sqc = param->sqc;
-	void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
+	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
+	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
 
-	sq->type      = param->type;
 	sq->pdev      = c->pdev;
-	sq->tstamp    = &priv->tstamp;
+	sq->tstamp    = c->tstamp;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
-	sq->tc        = tc;
-
-	err = mlx5_alloc_bfreg(mdev, &sq->bfreg, MLX5_CAP_GEN(mdev, bf), false);
-	if (err)
-		return err;
+	sq->txq_ix    = txq_ix;
+	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
+	sq->max_inline      = params->tx_max_inline;
+	sq->min_inline_mode = params->tx_min_inline_mode;
 
-	sq->uar_map = sq->bfreg.map;
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
-
-	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq,
-				 &sq->wq_ctrl);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
-		goto err_unmap_free_uar;
-
-	sq->wq.db       = &sq->wq.db[MLX5_SND_DBR];
-	if (sq->bfreg.wc)
-		set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state);
-
-	sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
-	sq->max_inline  = param->max_inline;
-	sq->min_inline_mode = param->min_inline_mode;
+		return err;
+	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
-	if (sq->type == MLX5E_SQ_TXQ) {
-		int txq_ix;
-
-		txq_ix = c->ix + tc * priv->params.num_channels;
-		sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix);
-		priv->txq_to_sq_map[txq_ix] = sq;
-	}
-
-	sq->edge = (sq->wq.sz_m1 + 1) - mlx5e_sq_get_max_wqebbs(sq->type);
-	sq->bf_budget = MLX5E_SQ_BF_BUDGET;
+	sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
 
 	return 0;
 
 err_sq_wq_destroy:
 	mlx5_wq_destroy(&sq->wq_ctrl);
 
-err_unmap_free_uar:
-	mlx5_free_bfreg(mdev, &sq->bfreg);
-
 	return err;
 }
 
-static void mlx5e_destroy_sq(struct mlx5e_sq *sq)
+static void mlx5e_free_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-
-	mlx5e_free_sq_db(sq);
+	mlx5e_free_txqsq_db(sq);
 	mlx5_wq_destroy(&sq->wq_ctrl);
-	mlx5_free_bfreg(priv->mdev, &sq->bfreg);
 }
 
-static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
-{
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+struct mlx5e_create_sq_param {
+	struct mlx5_wq_ctrl        *wq_ctrl;
+	u32                         cqn;
+	u32                         tisn;
+	u8                          tis_lst_sz;
+	u8                          min_inline_mode;
+};
 
+static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
+			   struct mlx5e_sq_param *param,
+			   struct mlx5e_create_sq_param *csp,
+			   u32 *sqn)
+{
 	void *in;
 	void *sqc;
 	void *wq;
@@ -1086,7 +1133,7 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
 	int err;
 
 	inlen = MLX5_ST_SZ_BYTES(create_sq_in) +
-		sizeof(u64) * sq->wq_ctrl.buf.npages;
+		sizeof(u64) * csp->wq_ctrl->buf.npages;
 	in = mlx5_vzalloc(inlen);
 	if (!in)
 		return -ENOMEM;
@@ -1095,40 +1142,40 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
 	wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	memcpy(sqc, param->sqc, sizeof(param->sqc));
-
-	MLX5_SET(sqc,  sqc, tis_num_0, param->type == MLX5E_SQ_ICO ?
-				       0 : priv->tisn[sq->tc]);
-	MLX5_SET(sqc,  sqc, cqn,		sq->cq.mcq.cqn);
+	MLX5_SET(sqc,  sqc, tis_lst_sz, csp->tis_lst_sz);
+	MLX5_SET(sqc,  sqc, tis_num_0, csp->tisn);
+	MLX5_SET(sqc,  sqc, cqn, csp->cqn);
 
 	if (MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		MLX5_SET(sqc,  sqc, min_wqe_inline_mode, sq->min_inline_mode);
+		MLX5_SET(sqc,  sqc, min_wqe_inline_mode, csp->min_inline_mode);
 
-	MLX5_SET(sqc,  sqc, state,		MLX5_SQC_STATE_RST);
-	MLX5_SET(sqc,  sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1);
+	MLX5_SET(sqc,  sqc, state, MLX5_SQC_STATE_RST);
 
 	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq,   wq, uar_page,      sq->bfreg.index);
-	MLX5_SET(wq,   wq, log_wq_pg_sz,  sq->wq_ctrl.buf.page_shift -
+	MLX5_SET(wq,   wq, uar_page,      mdev->mlx5e_res.bfreg.index);
+	MLX5_SET(wq,   wq, log_wq_pg_sz,  csp->wq_ctrl->buf.page_shift -
 					  MLX5_ADAPTER_PAGE_SHIFT);
-	MLX5_SET64(wq, wq, dbr_addr,      sq->wq_ctrl.db.dma);
+	MLX5_SET64(wq, wq, dbr_addr,      csp->wq_ctrl->db.dma);
 
-	mlx5_fill_page_array(&sq->wq_ctrl.buf,
-			     (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+	mlx5_fill_page_array(&csp->wq_ctrl->buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
 
-	err = mlx5_core_create_sq(mdev, in, inlen, &sq->sqn);
+	err = mlx5_core_create_sq(mdev, in, inlen, sqn);
 
 	kvfree(in);
 
 	return err;
 }
 
-static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
-			   int next_state, bool update_rl, int rl_index)
-{
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+struct mlx5e_modify_sq_param {
+	int curr_state;
+	int next_state;
+	bool rl_update;
+	int rl_index;
+};
 
+static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+			   struct mlx5e_modify_sq_param *p)
+{
 	void *in;
 	void *sqc;
 	int inlen;
@@ -1141,68 +1188,94 @@ static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
 
 	sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
 
-	MLX5_SET(modify_sq_in, in, sq_state, curr_state);
-	MLX5_SET(sqc, sqc, state, next_state);
-	if (update_rl && next_state == MLX5_SQC_STATE_RDY) {
+	MLX5_SET(modify_sq_in, in, sq_state, p->curr_state);
+	MLX5_SET(sqc, sqc, state, p->next_state);
+	if (p->rl_update && p->next_state == MLX5_SQC_STATE_RDY) {
 		MLX5_SET64(modify_sq_in, in, modify_bitmask, 1);
-		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, rl_index);
+		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, p->rl_index);
 	}
 
-	err = mlx5_core_modify_sq(mdev, sq->sqn, in, inlen);
+	err = mlx5_core_modify_sq(mdev, sqn, in, inlen);
 
 	kvfree(in);
 
 	return err;
 }
 
-static void mlx5e_disable_sq(struct mlx5e_sq *sq)
+static void mlx5e_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn)
 {
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	mlx5_core_destroy_sq(mdev, sq->sqn);
-	if (sq->rate_limit)
-		mlx5_rl_remove_rate(mdev, sq->rate_limit);
+	mlx5_core_destroy_sq(mdev, sqn);
 }
 
-static int mlx5e_open_sq(struct mlx5e_channel *c,
-			 int tc,
-			 struct mlx5e_sq_param *param,
-			 struct mlx5e_sq *sq)
+static int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev,
+			       struct mlx5e_sq_param *param,
+			       struct mlx5e_create_sq_param *csp,
+			       u32 *sqn)
 {
+	struct mlx5e_modify_sq_param msp = {0};
 	int err;
 
-	err = mlx5e_create_sq(c, tc, param, sq);
+	err = mlx5e_create_sq(mdev, param, csp, sqn);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_sq(sq, param);
+	msp.curr_state = MLX5_SQC_STATE_RST;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+	err = mlx5e_modify_sq(mdev, *sqn, &msp);
 	if (err)
-		goto err_destroy_sq;
+		mlx5e_destroy_sq(mdev, *sqn);
 
-	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY,
-			      false, 0);
+	return err;
+}
+
+static int mlx5e_set_sq_maxrate(struct net_device *dev,
+				struct mlx5e_txqsq *sq, u32 rate);
+
+static int mlx5e_open_txqsq(struct mlx5e_channel *c,
+			    u32 tisn,
+			    int txq_ix,
+			    struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param,
+			    struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_create_sq_param csp = {};
+	u32 tx_rate;
+	int err;
+
+	err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq);
 	if (err)
-		goto err_disable_sq;
+		return err;
 
-	if (sq->txq) {
-		netdev_tx_reset_queue(sq->txq);
-		netif_tx_start_queue(sq->txq);
-	}
+	csp.tisn            = tisn;
+	csp.tis_lst_sz      = 1;
+	csp.cqn             = sq->cq.mcq.cqn;
+	csp.wq_ctrl         = &sq->wq_ctrl;
+	csp.min_inline_mode = sq->min_inline_mode;
+	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+	if (err)
+		goto err_free_txqsq;
+
+	tx_rate = c->priv->tx_rates[sq->txq_ix];
+	if (tx_rate)
+		mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate);
 
 	return 0;
 
-err_disable_sq:
+err_free_txqsq:
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	mlx5e_disable_sq(sq);
-err_destroy_sq:
-	mlx5e_destroy_sq(sq);
+	mlx5e_free_txqsq(sq);
 
 	return err;
 }
 
+static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+{
+	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
+	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	netdev_tx_reset_queue(sq->txq);
+	netif_tx_start_queue(sq->txq);
+}
+
 static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
@@ -1210,43 +1283,153 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 	__netif_tx_unlock_bh(txq);
 }
 
-static void mlx5e_close_sq(struct mlx5e_sq *sq)
+static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
+	struct mlx5e_channel *c = sq->channel;
+
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&sq->channel->napi);
+	napi_synchronize(&c->napi);
 
-	if (sq->txq) {
-		netif_tx_disable_queue(sq->txq);
+	netif_tx_disable_queue(sq->txq);
 
-		/* last doorbell out, godspeed .. */
-		if (mlx5e_sq_has_room_for(sq, 1)) {
-			sq->db.txq.skb[(sq->pc & sq->wq.sz_m1)] = NULL;
-			mlx5e_send_nop(sq, true);
-		}
+	/* last doorbell out, godspeed .. */
+	if (mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1)) {
+		struct mlx5e_tx_wqe *nop;
+
+		sq->db.wqe_info[(sq->pc & sq->wq.sz_m1)].skb = NULL;
+		nop = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
+}
+
+static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+	struct mlx5_core_dev *mdev = c->mdev;
 
-	mlx5e_disable_sq(sq);
-	mlx5e_free_sq_descs(sq);
-	mlx5e_destroy_sq(sq);
+	mlx5e_destroy_sq(mdev, sq->sqn);
+	if (sq->rate_limit)
+		mlx5_rl_remove_rate(mdev, sq->rate_limit);
+	mlx5e_free_txqsq_descs(sq);
+	mlx5e_free_txqsq(sq);
 }
 
-static int mlx5e_create_cq(struct mlx5e_channel *c,
-			   struct mlx5e_cq_param *param,
-			   struct mlx5e_cq *cq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c,
+			    struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param,
+			    struct mlx5e_icosq *sq)
+{
+	struct mlx5e_create_sq_param csp = {};
+	int err;
+
+	err = mlx5e_alloc_icosq(c, param, sq);
+	if (err)
+		return err;
+
+	csp.cqn             = sq->cq.mcq.cqn;
+	csp.wq_ctrl         = &sq->wq_ctrl;
+	csp.min_inline_mode = params->tx_min_inline_mode;
+	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+	if (err)
+		goto err_free_icosq;
+
+	return 0;
+
+err_free_icosq:
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	mlx5e_free_icosq(sq);
+
+	return err;
+}
+
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	napi_synchronize(&c->napi);
+
+	mlx5e_destroy_sq(c->mdev, sq->sqn);
+	mlx5e_free_icosq(sq);
+}
+
+static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
+			    struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param,
+			    struct mlx5e_xdpsq *sq)
+{
+	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
+	struct mlx5e_create_sq_param csp = {};
+	unsigned int inline_hdr_sz = 0;
+	int err;
+	int i;
+
+	err = mlx5e_alloc_xdpsq(c, params, param, sq);
+	if (err)
+		return err;
+
+	csp.tis_lst_sz      = 1;
+	csp.tisn            = c->priv->tisn[0]; /* tc = 0 */
+	csp.cqn             = sq->cq.mcq.cqn;
+	csp.wq_ctrl         = &sq->wq_ctrl;
+	csp.min_inline_mode = sq->min_inline_mode;
+	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+	if (err)
+		goto err_free_xdpsq;
+
+	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+		inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
+		ds_cnt++;
+	}
+
+	/* Pre initialize fixed WQE fields */
+	for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+		struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
+		struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+		struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+		struct mlx5_wqe_data_seg *dseg;
+
+		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+
+		dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
+		dseg->lkey = sq->mkey_be;
+	}
+
+	return 0;
+
+err_free_xdpsq:
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	mlx5e_free_xdpsq(sq);
+
+	return err;
+}
+
+static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	napi_synchronize(&c->napi);
+
+	mlx5e_destroy_sq(c->mdev, sq->sqn);
+	mlx5e_free_xdpsq_descs(sq);
+	mlx5e_free_xdpsq(sq);
+}
+
+static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
+				 struct mlx5e_cq_param *param,
+				 struct mlx5e_cq *cq)
 {
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
 	unsigned int irqn;
 	int err;
 	u32 i;
 
-	param->wq.buf_numa_node = cpu_to_node(c->cpu);
-	param->wq.db_numa_node  = cpu_to_node(c->cpu);
-	param->eq_ix   = c->ix;
-
 	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
 			       &cq->wq_ctrl);
 	if (err)
@@ -1254,8 +1437,6 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 
 	mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
 
-	cq->napi        = &c->napi;
-
 	mcq->cqe_sz     = 64;
 	mcq->set_ci_db  = cq->wq_ctrl.db.db;
 	mcq->arm_db     = cq->wq_ctrl.db.db + 1;
@@ -1272,21 +1453,38 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 		cqe->op_own = 0xf1;
 	}
 
-	cq->channel = c;
-	cq->priv = priv;
+	cq->mdev = mdev;
 
 	return 0;
 }
 
-static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
+static int mlx5e_alloc_cq(struct mlx5e_channel *c,
+			  struct mlx5e_cq_param *param,
+			  struct mlx5e_cq *cq)
+{
+	struct mlx5_core_dev *mdev = c->priv->mdev;
+	int err;
+
+	param->wq.buf_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node  = cpu_to_node(c->cpu);
+	param->eq_ix   = c->ix;
+
+	err = mlx5e_alloc_cq_common(mdev, param, cq);
+
+	cq->napi    = &c->napi;
+	cq->channel = c;
+
+	return err;
+}
+
+static void mlx5e_free_cq(struct mlx5e_cq *cq)
 {
 	mlx5_cqwq_destroy(&cq->wq_ctrl);
 }
 
-static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
+static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 {
-	struct mlx5e_priv *priv = cq->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_dev *mdev = cq->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 
 	void *in;
@@ -1330,47 +1528,41 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	return 0;
 }
 
-static void mlx5e_disable_cq(struct mlx5e_cq *cq)
+static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
 {
-	struct mlx5e_priv *priv = cq->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	mlx5_core_destroy_cq(mdev, &cq->mcq);
+	mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
 }
 
 static int mlx5e_open_cq(struct mlx5e_channel *c,
+			 struct mlx5e_cq_moder moder,
 			 struct mlx5e_cq_param *param,
-			 struct mlx5e_cq *cq,
-			 struct mlx5e_cq_moder moderation)
+			 struct mlx5e_cq *cq)
 {
+	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
 
-	err = mlx5e_create_cq(c, param, cq);
+	err = mlx5e_alloc_cq(c, param, cq);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_cq(cq, param);
+	err = mlx5e_create_cq(cq, param);
 	if (err)
-		goto err_destroy_cq;
+		goto err_free_cq;
 
 	if (MLX5_CAP_GEN(mdev, cq_moderation))
-		mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
-					       moderation.usec,
-					       moderation.pkts);
+		mlx5_core_modify_cq_moderation(mdev, &cq->mcq, moder.usec, moder.pkts);
 	return 0;
 
-err_destroy_cq:
-	mlx5e_destroy_cq(cq);
+err_free_cq:
+	mlx5e_free_cq(cq);
 
 	return err;
 }
 
 static void mlx5e_close_cq(struct mlx5e_cq *cq)
 {
-	mlx5e_disable_cq(cq);
 	mlx5e_destroy_cq(cq);
+	mlx5e_free_cq(cq);
 }
 
 static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
@@ -1379,15 +1571,15 @@ static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
 }
 
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
+			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
 {
-	struct mlx5e_priv *priv = c->priv;
 	int err;
 	int tc;
 
 	for (tc = 0; tc < c->num_tc; tc++) {
-		err = mlx5e_open_cq(c, &cparam->tx_cq, &c->sq[tc].cq,
-				    priv->params.tx_cq_moderation);
+		err = mlx5e_open_cq(c, params->tx_cq_moderation,
+				    &cparam->tx_cq, &c->sq[tc].cq);
 		if (err)
 			goto err_close_tx_cqs;
 	}
@@ -1410,13 +1602,17 @@ static void mlx5e_close_tx_cqs(struct mlx5e_channel *c)
 }
 
 static int mlx5e_open_sqs(struct mlx5e_channel *c,
+			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
 {
 	int err;
 	int tc;
 
-	for (tc = 0; tc < c->num_tc; tc++) {
-		err = mlx5e_open_sq(c, tc, &cparam->sq, &c->sq[tc]);
+	for (tc = 0; tc < params->num_tc; tc++) {
+		int txq_ix = c->ix + tc * params->num_channels;
+
+		err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
+				       params, &cparam->sq, &c->sq[tc]);
 		if (err)
 			goto err_close_sqs;
 	}
@@ -1425,7 +1621,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 
 err_close_sqs:
 	for (tc--; tc >= 0; tc--)
-		mlx5e_close_sq(&c->sq[tc]);
+		mlx5e_close_txqsq(&c->sq[tc]);
 
 	return err;
 }
@@ -1435,23 +1631,15 @@ static void mlx5e_close_sqs(struct mlx5e_channel *c)
 	int tc;
 
 	for (tc = 0; tc < c->num_tc; tc++)
-		mlx5e_close_sq(&c->sq[tc]);
-}
-
-static void mlx5e_build_channeltc_to_txq_map(struct mlx5e_priv *priv, int ix)
-{
-	int i;
-
-	for (i = 0; i < priv->profile->max_tc; i++)
-		priv->channeltc_to_txq_map[ix][i] =
-			ix + i * priv->params.num_channels;
+		mlx5e_close_txqsq(&c->sq[tc]);
 }
 
 static int mlx5e_set_sq_maxrate(struct net_device *dev,
-				struct mlx5e_sq *sq, u32 rate)
+				struct mlx5e_txqsq *sq, u32 rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_modify_sq_param msp = {0};
 	u16 rl_index = 0;
 	int err;
 
@@ -1474,8 +1662,11 @@ static int mlx5e_set_sq_maxrate(struct net_device *dev,
 		}
 	}
 
-	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
-			      MLX5_SQC_STATE_RDY, true, rl_index);
+	msp.curr_state = MLX5_SQC_STATE_RDY;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+	msp.rl_index   = rl_index;
+	msp.rl_update  = true;
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
 	if (err) {
 		netdev_err(dev, "Failed configuring rate %u: %d\n",
 			   rate, err);
@@ -1493,7 +1684,7 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_sq *sq = priv->txq_to_sq_map[index];
+	struct mlx5e_txqsq *sq = priv->txq2sq[index];
 	int err = 0;
 
 	if (!mlx5_rl_is_supported(mdev)) {
@@ -1520,114 +1711,87 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	return err;
 }
 
-static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
-{
-	return is_kdump_kernel() ?
-		MLX5E_MIN_NUM_CHANNELS :
-		min_t(int, mdev->priv.eq_table.num_comp_vectors,
-		      MLX5E_MAX_NUM_CHANNELS);
-}
-
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+			      struct mlx5e_params *params,
 			      struct mlx5e_channel_param *cparam,
 			      struct mlx5e_channel **cp)
 {
-	struct mlx5e_cq_moder icosq_cq_moder = {0, 0};
+	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	struct mlx5e_cq_moder rx_cq_profile;
 	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
-	struct mlx5e_sq *sq;
 	int err;
-	int i;
 
 	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
 	c->priv     = priv;
+	c->mdev     = priv->mdev;
+	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
 	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
-	c->num_tc   = priv->params.num_tc;
-	c->xdp      = !!priv->xdp_prog;
-
-	if (priv->params.rx_am_enabled)
-		rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode);
-	else
-		rx_cq_profile = priv->params.rx_cq_moderation;
-
-	mlx5e_build_channeltc_to_txq_map(priv, ix);
+	c->num_tc   = params->num_tc;
+	c->xdp      = !!params->xdp_prog;
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
-	err = mlx5e_open_cq(c, &cparam->icosq_cq, &c->icosq.cq, icosq_cq_moder);
+	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
 	if (err)
 		goto err_napi_del;
 
-	err = mlx5e_open_tx_cqs(c, cparam);
+	err = mlx5e_open_tx_cqs(c, params, cparam);
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq,
-			    rx_cq_profile);
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
 	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
-	err = c->xdp ? mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq,
-				     priv->params.tx_cq_moderation) : 0;
+	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
+				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
 	if (err)
 		goto err_close_rx_cq;
 
 	napi_enable(&c->napi);
 
-	err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq);
+	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
 	if (err)
 		goto err_disable_napi;
 
-	err = mlx5e_open_sqs(c, cparam);
+	err = mlx5e_open_sqs(c, params, cparam);
 	if (err)
 		goto err_close_icosq;
 
-	for (i = 0; i < priv->params.num_tc; i++) {
-		u32 txq_ix = priv->channeltc_to_txq_map[ix][i];
-
-		if (priv->tx_rates[txq_ix]) {
-			sq = priv->txq_to_sq_map[txq_ix];
-			mlx5e_set_sq_maxrate(priv->netdev, sq,
-					     priv->tx_rates[txq_ix]);
-		}
-	}
-
-	err = c->xdp ? mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq) : 0;
+	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0;
 	if (err)
 		goto err_close_sqs;
 
-	err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
+	err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq);
 	if (err)
 		goto err_close_xdp_sq;
 
-	netif_set_xps_queue(netdev, get_cpu_mask(c->cpu), ix);
 	*cp = c;
 
 	return 0;
 err_close_xdp_sq:
 	if (c->xdp)
-		mlx5e_close_sq(&c->xdp_sq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq);
 
 err_close_sqs:
 	mlx5e_close_sqs(c);
 
 err_close_icosq:
-	mlx5e_close_sq(&c->icosq);
+	mlx5e_close_icosq(&c->icosq);
 
 err_disable_napi:
 	napi_disable(&c->napi);
 	if (c->xdp)
-		mlx5e_close_cq(&c->xdp_sq.cq);
+		mlx5e_close_cq(&c->rq.xdpsq.cq);
 
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
@@ -1645,16 +1809,35 @@ err_napi_del:
 	return err;
 }
 
+static void mlx5e_activate_channel(struct mlx5e_channel *c)
+{
+	int tc;
+
+	for (tc = 0; tc < c->num_tc; tc++)
+		mlx5e_activate_txqsq(&c->sq[tc]);
+	mlx5e_activate_rq(&c->rq);
+	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+}
+
+static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
+{
+	int tc;
+
+	mlx5e_deactivate_rq(&c->rq);
+	for (tc = 0; tc < c->num_tc; tc++)
+		mlx5e_deactivate_txqsq(&c->sq[tc]);
+}
+
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
-		mlx5e_close_sq(&c->xdp_sq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq);
 	mlx5e_close_sqs(c);
-	mlx5e_close_sq(&c->icosq);
+	mlx5e_close_icosq(&c->icosq);
 	napi_disable(&c->napi);
 	if (c->xdp)
-		mlx5e_close_cq(&c->xdp_sq.cq);
+		mlx5e_close_cq(&c->rq.xdpsq.cq);
 	mlx5e_close_cq(&c->rq.cq);
 	mlx5e_close_tx_cqs(c);
 	mlx5e_close_cq(&c->icosq.cq);
@@ -1664,17 +1847,16 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 }
 
 static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+				 struct mlx5e_params *params,
 				 struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
 
-	switch (priv->params.rq_wq_type) {
+	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		MLX5_SET(wq, wq, log_wqe_num_of_strides,
-			 priv->params.mpwqe_log_num_strides - 9);
-		MLX5_SET(wq, wq, log_wqe_stride_size,
-			 priv->params.mpwqe_log_stride_sz - 6);
+		MLX5_SET(wq, wq, log_wqe_num_of_strides, params->mpwqe_log_num_strides - 9);
+		MLX5_SET(wq, wq, log_wqe_stride_size, params->mpwqe_log_stride_sz - 6);
 		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
@@ -1683,14 +1865,14 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 
 	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
-	MLX5_SET(wq, wq, log_wq_sz,        priv->params.log_rq_size);
+	MLX5_SET(wq, wq, log_wq_sz,        params->log_rq_size);
 	MLX5_SET(wq, wq, pd,               priv->mdev->mlx5e_res.pdn);
 	MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
+	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
+	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
 	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
 	param->wq.linear = 1;
-
-	param->am_enabled = priv->params.rx_am_enabled;
 }
 
 static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
@@ -1715,17 +1897,14 @@ static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
+				 struct mlx5e_params *params,
 				 struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	mlx5e_build_sq_param_common(priv, param);
-	MLX5_SET(wq, wq, log_wq_sz,     priv->params.log_sq_size);
-
-	param->max_inline = priv->params.tx_max_inline;
-	param->min_inline_mode = priv->params.tx_min_inline_mode;
-	param->type = MLX5E_SQ_TXQ;
+	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 }
 
 static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
@@ -1737,37 +1916,36 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_params *params,
 				    struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
-	switch (priv->params.rq_wq_type) {
+	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		log_cq_size = priv->params.log_rq_size +
-			priv->params.mpwqe_log_num_strides;
+		log_cq_size = params->log_rq_size + params->mpwqe_log_num_strides;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		log_cq_size = priv->params.log_rq_size;
+		log_cq_size = params->log_rq_size;
 	}
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
-	if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
 		MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM);
 		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
 	}
 
 	mlx5e_build_common_cq_param(priv, param);
-
-	param->cq_period_mode = priv->params.rx_cq_period_mode;
 }
 
 static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_params *params,
 				    struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
-	MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size);
+	MLX5_SET(cqc, cqc, log_cq_size, params->log_sq_size);
 
 	mlx5e_build_common_cq_param(priv, param);
 
@@ -1775,8 +1953,8 @@ static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
-				     struct mlx5e_cq_param *param,
-				     u8 log_wq_size)
+				     u8 log_wq_size,
+				     struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
@@ -1788,8 +1966,8 @@ static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_sq_param *param,
-				    u8 log_wq_size)
+				    u8 log_wq_size,
+				    struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -1798,162 +1976,119 @@ static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
 
 	MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
 	MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
-
-	param->type = MLX5E_SQ_ICO;
 }
 
 static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_params *params,
 				    struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	mlx5e_build_sq_param_common(priv, param);
-	MLX5_SET(wq, wq, log_wq_sz,     priv->params.log_sq_size);
-
-	param->max_inline = priv->params.tx_max_inline;
-	param->min_inline_mode = priv->params.tx_min_inline_mode;
-	param->type = MLX5E_SQ_XDP;
+	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 }
 
-static void mlx5e_build_channel_param(struct mlx5e_priv *priv, struct mlx5e_channel_param *cparam)
+static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
+				      struct mlx5e_params *params,
+				      struct mlx5e_channel_param *cparam)
 {
 	u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 
-	mlx5e_build_rq_param(priv, &cparam->rq);
-	mlx5e_build_sq_param(priv, &cparam->sq);
-	mlx5e_build_xdpsq_param(priv, &cparam->xdp_sq);
-	mlx5e_build_icosq_param(priv, &cparam->icosq, icosq_log_wq_sz);
-	mlx5e_build_rx_cq_param(priv, &cparam->rx_cq);
-	mlx5e_build_tx_cq_param(priv, &cparam->tx_cq);
-	mlx5e_build_ico_cq_param(priv, &cparam->icosq_cq, icosq_log_wq_sz);
+	mlx5e_build_rq_param(priv, params, &cparam->rq);
+	mlx5e_build_sq_param(priv, params, &cparam->sq);
+	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
+	mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
+	mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq);
+	mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
+	mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq);
 }
 
-static int mlx5e_open_channels(struct mlx5e_priv *priv)
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+			struct mlx5e_channels *chs)
 {
 	struct mlx5e_channel_param *cparam;
-	int nch = priv->params.num_channels;
 	int err = -ENOMEM;
 	int i;
-	int j;
-
-	priv->channel = kcalloc(nch, sizeof(struct mlx5e_channel *),
-				GFP_KERNEL);
 
-	priv->txq_to_sq_map = kcalloc(nch * priv->params.num_tc,
-				      sizeof(struct mlx5e_sq *), GFP_KERNEL);
+	chs->num = chs->params.num_channels;
 
+	chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
 	cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+	if (!chs->c || !cparam)
+		goto err_free;
 
-	if (!priv->channel || !priv->txq_to_sq_map || !cparam)
-		goto err_free_txq_to_sq_map;
-
-	mlx5e_build_channel_param(priv, cparam);
-
-	for (i = 0; i < nch; i++) {
-		err = mlx5e_open_channel(priv, i, cparam, &priv->channel[i]);
-		if (err)
-			goto err_close_channels;
-	}
-
-	for (j = 0; j < nch; j++) {
-		err = mlx5e_wait_for_min_rx_wqes(&priv->channel[j]->rq);
+	mlx5e_build_channel_param(priv, &chs->params, cparam);
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]);
 		if (err)
 			goto err_close_channels;
 	}
 
-	/* FIXME: This is a W/A for tx timeout watch dog false alarm when
-	 * polling for inactive tx queues.
-	 */
-	netif_tx_start_all_queues(priv->netdev);
-
 	kfree(cparam);
 	return 0;
 
 err_close_channels:
 	for (i--; i >= 0; i--)
-		mlx5e_close_channel(priv->channel[i]);
+		mlx5e_close_channel(chs->c[i]);
 
-err_free_txq_to_sq_map:
-	kfree(priv->txq_to_sq_map);
-	kfree(priv->channel);
+err_free:
+	kfree(chs->c);
 	kfree(cparam);
-
+	chs->num = 0;
 	return err;
 }
 
-static void mlx5e_close_channels(struct mlx5e_priv *priv)
+static void mlx5e_activate_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
-	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
-	 * polling for inactive tx queues.
-	 */
-	netif_tx_stop_all_queues(priv->netdev);
-	netif_tx_disable(priv->netdev);
-
-	for (i = 0; i < priv->params.num_channels; i++)
-		mlx5e_close_channel(priv->channel[i]);
-
-	kfree(priv->txq_to_sq_map);
-	kfree(priv->channel);
+	for (i = 0; i < chs->num; i++)
+		mlx5e_activate_channel(chs->c[i]);
 }
 
-static int mlx5e_rx_hash_fn(int hfunc)
+static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
 {
-	return (hfunc == ETH_RSS_HASH_TOP) ?
-	       MLX5_RX_HASH_FN_TOEPLITZ :
-	       MLX5_RX_HASH_FN_INVERTED_XOR8;
-}
-
-static int mlx5e_bits_invert(unsigned long a, int size)
-{
-	int inv = 0;
+	int err = 0;
 	int i;
 
-	for (i = 0; i < size; i++)
-		inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i;
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq);
+		if (err)
+			break;
+	}
 
-	return inv;
+	return err;
 }
 
-static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc)
+static void mlx5e_deactivate_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
-	for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) {
-		int ix = i;
-		u32 rqn;
-
-		if (priv->params.rss_hfunc == ETH_RSS_HASH_XOR)
-			ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE);
-
-		ix = priv->params.indirection_rqt[ix];
-		rqn = test_bit(MLX5E_STATE_OPENED, &priv->state) ?
-				priv->channel[ix]->rq.rqn :
-				priv->drop_rq.rqn;
-		MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
-	}
+	for (i = 0; i < chs->num; i++)
+		mlx5e_deactivate_channel(chs->c[i]);
 }
 
-static void mlx5e_fill_direct_rqt_rqn(struct mlx5e_priv *priv, void *rqtc,
-				      int ix)
+void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
-	u32 rqn = test_bit(MLX5E_STATE_OPENED, &priv->state) ?
-			priv->channel[ix]->rq.rqn :
-			priv->drop_rq.rqn;
+	int i;
 
-	MLX5_SET(rqtc, rqtc, rq_num[0], rqn);
+	for (i = 0; i < chs->num; i++)
+		mlx5e_close_channel(chs->c[i]);
+
+	kfree(chs->c);
+	chs->num = 0;
 }
 
-static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz,
-			    int ix, struct mlx5e_rqt *rqt)
+static int
+mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, struct mlx5e_rqt *rqt)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqtc;
 	int inlen;
 	int err;
 	u32 *in;
+	int i;
 
 	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
 	in = mlx5_vzalloc(inlen);
@@ -1965,10 +2100,8 @@ static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz,
 	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
 	MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
 
-	if (sz > 1) /* RSS */
-		mlx5e_fill_indir_rqt_rqns(priv, rqtc);
-	else
-		mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
+	for (i = 0; i < sz; i++)
+		MLX5_SET(rqtc, rqtc, rq_num[i], priv->drop_rq.rqn);
 
 	err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn);
 	if (!err)
@@ -1984,11 +2117,15 @@ void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt)
 	mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn);
 }
 
-static int mlx5e_create_indirect_rqts(struct mlx5e_priv *priv)
+int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rqt *rqt = &priv->indir_rqt;
+	int err;
 
-	return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, 0, rqt);
+	err = mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt);
+	if (err)
+		mlx5_core_warn(priv->mdev, "create indirect rqts failed, %d\n", err);
+	return err;
 }
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
@@ -1999,7 +2136,7 @@ int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
 
 	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
 		rqt = &priv->direct_tir[ix].rqt;
-		err = mlx5e_create_rqt(priv, 1 /*size */, ix, rqt);
+		err = mlx5e_create_rqt(priv, 1 /*size */, rqt);
 		if (err)
 			goto err_destroy_rqts;
 	}
@@ -2007,13 +2144,64 @@ int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
 	return 0;
 
 err_destroy_rqts:
+	mlx5_core_warn(priv->mdev, "create direct rqts failed, %d\n", err);
 	for (ix--; ix >= 0; ix--)
 		mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
 
 	return err;
 }
 
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++)
+		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+}
+
+static int mlx5e_rx_hash_fn(int hfunc)
+{
+	return (hfunc == ETH_RSS_HASH_TOP) ?
+	       MLX5_RX_HASH_FN_TOEPLITZ :
+	       MLX5_RX_HASH_FN_INVERTED_XOR8;
+}
+
+static int mlx5e_bits_invert(unsigned long a, int size)
+{
+	int inv = 0;
+	int i;
+
+	for (i = 0; i < size; i++)
+		inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i;
+
+	return inv;
+}
+
+static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz,
+				struct mlx5e_redirect_rqt_param rrp, void *rqtc)
+{
+	int i;
+
+	for (i = 0; i < sz; i++) {
+		u32 rqn;
+
+		if (rrp.is_rss) {
+			int ix = i;
+
+			if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
+				ix = mlx5e_bits_invert(i, ilog2(sz));
+
+			ix = priv->channels.params.indirection_rqt[ix];
+			rqn = rrp.rss.channels->c[ix]->rq.rqn;
+		} else {
+			rqn = rrp.rqn;
+		}
+		MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
+	}
+}
+
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+		       struct mlx5e_redirect_rqt_param rrp)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqtc;
@@ -2029,41 +2217,86 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
 	rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx);
 
 	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
-	if (sz > 1) /* RSS */
-		mlx5e_fill_indir_rqt_rqns(priv, rqtc);
-	else
-		mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
-
 	MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1);
-
+	mlx5e_fill_rqt_rqns(priv, sz, rrp, rqtc);
 	err = mlx5_core_modify_rqt(mdev, rqtn, in, inlen);
 
 	kvfree(in);
-
 	return err;
 }
 
-static void mlx5e_redirect_rqts(struct mlx5e_priv *priv)
+static u32 mlx5e_get_direct_rqn(struct mlx5e_priv *priv, int ix,
+				struct mlx5e_redirect_rqt_param rrp)
+{
+	if (!rrp.is_rss)
+		return rrp.rqn;
+
+	if (ix >= rrp.rss.channels->num)
+		return priv->drop_rq.rqn;
+
+	return rrp.rss.channels->c[ix]->rq.rqn;
+}
+
+static void mlx5e_redirect_rqts(struct mlx5e_priv *priv,
+				struct mlx5e_redirect_rqt_param rrp)
 {
 	u32 rqtn;
 	int ix;
 
 	if (priv->indir_rqt.enabled) {
+		/* RSS RQ table */
 		rqtn = priv->indir_rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
+		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
 	}
 
-	for (ix = 0; ix < priv->params.num_channels; ix++) {
+	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
+		struct mlx5e_redirect_rqt_param direct_rrp = {
+			.is_rss = false,
+			{
+				.rqn    = mlx5e_get_direct_rqn(priv, ix, rrp)
+			},
+		};
+
+		/* Direct RQ Tables */
 		if (!priv->direct_tir[ix].rqt.enabled)
 			continue;
+
 		rqtn = priv->direct_tir[ix].rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, 1, ix);
+		mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
 	}
 }
 
-static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
+static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv,
+					    struct mlx5e_channels *chs)
+{
+	struct mlx5e_redirect_rqt_param rrp = {
+		.is_rss        = true,
+		{
+			.rss = {
+				.channels  = chs,
+				.hfunc     = chs->params.rss_hfunc,
+			}
+		},
+	};
+
+	mlx5e_redirect_rqts(priv, rrp);
+}
+
+static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv)
+{
+	struct mlx5e_redirect_rqt_param drop_rrp = {
+		.is_rss = false,
+		{
+			.rqn = priv->drop_rq.rqn,
+		},
+	};
+
+	mlx5e_redirect_rqts(priv, drop_rrp);
+}
+
+static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 {
-	if (!priv->params.lro_en)
+	if (!params->lro_en)
 		return;
 
 #define ROUGH_MAX_L2_L3_HDR_SZ 256
@@ -2072,13 +2305,13 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
-		 (priv->params.lro_wqe_sz -
-		  ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
-	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
+		 (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
-				    enum mlx5e_traffic_types tt)
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+				    enum mlx5e_traffic_types tt,
+				    void *tirc)
 {
 	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
@@ -2094,16 +2327,15 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
 				 MLX5_HASH_FIELD_SEL_DST_IP   |\
 				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
 
-	MLX5_SET(tirc, tirc, rx_hash_fn,
-		 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
-	if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
+	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
+	if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
 					     rx_hash_toeplitz_key);
 		size_t len = MLX5_FLD_SZ_BYTES(tirc,
 					       rx_hash_toeplitz_key);
 
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-		memcpy(rss_key, priv->params.toeplitz_hash_key, len);
+		memcpy(rss_key, params->toeplitz_hash_key, len);
 	}
 
 	switch (tt) {
@@ -2208,7 +2440,7 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 	MLX5_SET(modify_tir_in, in, bitmask.lro, 1);
 	tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
 
-	mlx5e_build_tir_ctx_lro(tirc, priv);
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in,
@@ -2258,9 +2490,9 @@ static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
 	*mtu = MLX5E_HW2SW_MTU(hw_mtu);
 }
 
-static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
+static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct net_device *netdev = priv->netdev;
 	u16 mtu;
 	int err;
 
@@ -2280,8 +2512,8 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
 static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int nch = priv->params.num_channels;
-	int ntc = priv->params.num_tc;
+	int nch = priv->channels.params.num_channels;
+	int ntc = priv->channels.params.num_tc;
 	int tc;
 
 	netdev_reset_tc(netdev);
@@ -2298,53 +2530,116 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
+static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channel *c;
+	struct mlx5e_txqsq *sq;
+	int i, tc;
+
+	for (i = 0; i < priv->channels.num; i++)
+		for (tc = 0; tc < priv->profile->max_tc; tc++)
+			priv->channel_tc2txq[i][tc] = i + tc * priv->channels.num;
+
+	for (i = 0; i < priv->channels.num; i++) {
+		c = priv->channels.c[i];
+		for (tc = 0; tc < c->num_tc; tc++) {
+			sq = &c->sq[tc];
+			priv->txq2sq[sq->txq_ix] = sq;
+		}
+	}
+}
+
+static bool mlx5e_is_eswitch_vport_mngr(struct mlx5_core_dev *mdev)
+{
+	return (MLX5_CAP_GEN(mdev, vport_group_manager) &&
+		MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH);
+}
+
+void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
+{
+	int num_txqs = priv->channels.num * priv->channels.params.num_tc;
+	struct net_device *netdev = priv->netdev;
+
+	mlx5e_netdev_set_tcs(netdev);
+	netif_set_real_num_tx_queues(netdev, num_txqs);
+	netif_set_real_num_rx_queues(netdev, priv->channels.num);
+
+	mlx5e_build_channels_tx_maps(priv);
+	mlx5e_activate_channels(&priv->channels);
+	netif_tx_start_all_queues(priv->netdev);
+
+	if (mlx5e_is_eswitch_vport_mngr(priv->mdev))
+		mlx5e_add_sqs_fwd_rules(priv);
+
+	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
+	mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
+}
+
+void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
+{
+	mlx5e_redirect_rqts_to_drop(priv);
+
+	if (mlx5e_is_eswitch_vport_mngr(priv->mdev))
+		mlx5e_remove_sqs_fwd_rules(priv);
+
+	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
+	 * polling for inactive tx queues.
+	 */
+	netif_tx_stop_all_queues(priv->netdev);
+	netif_tx_disable(priv->netdev);
+	mlx5e_deactivate_channels(&priv->channels);
+}
+
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				struct mlx5e_channels *new_chs,
+				mlx5e_fp_hw_modify hw_modify)
+{
+	struct net_device *netdev = priv->netdev;
+	int new_num_txqs;
+
+	new_num_txqs = new_chs->num * new_chs->params.num_tc;
+
+	netif_carrier_off(netdev);
+
+	if (new_num_txqs < netdev->real_num_tx_queues)
+		netif_set_real_num_tx_queues(netdev, new_num_txqs);
+
+	mlx5e_deactivate_priv_channels(priv);
+	mlx5e_close_channels(&priv->channels);
+
+	priv->channels = *new_chs;
+
+	/* New channels are ready to roll, modify HW settings if needed */
+	if (hw_modify)
+		hw_modify(priv);
+
+	mlx5e_refresh_tirs(priv, false);
+	mlx5e_activate_priv_channels(priv);
+
+	mlx5e_update_carrier(priv);
+}
+
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int num_txqs;
 	int err;
 
 	set_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	mlx5e_netdev_set_tcs(netdev);
-
-	num_txqs = priv->params.num_channels * priv->params.num_tc;
-	netif_set_real_num_tx_queues(netdev, num_txqs);
-	netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
-
-	err = mlx5e_open_channels(priv);
-	if (err) {
-		netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
-			   __func__, err);
+	err = mlx5e_open_channels(priv, &priv->channels);
+	if (err)
 		goto err_clear_state_opened_flag;
-	}
-
-	err = mlx5e_refresh_tirs_self_loopback(priv->mdev, false);
-	if (err) {
-		netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n",
-			   __func__, err);
-		goto err_close_channels;
-	}
 
-	mlx5e_redirect_rqts(priv);
+	mlx5e_refresh_tirs(priv, false);
+	mlx5e_activate_priv_channels(priv);
 	mlx5e_update_carrier(priv);
 	mlx5e_timestamp_init(priv);
-#ifdef CONFIG_RFS_ACCEL
-	priv->netdev->rx_cpu_rmap = priv->mdev->rmap;
-#endif
+
 	if (priv->profile->update_stats)
 		queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
-		err = mlx5e_add_sqs_fwd_rules(priv);
-		if (err)
-			goto err_close_channels;
-	}
 	return 0;
 
-err_close_channels:
-	mlx5e_close_channels(priv);
 err_clear_state_opened_flag:
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 	return err;
@@ -2365,7 +2660,6 @@ int mlx5e_open(struct net_device *netdev)
 int mlx5e_close_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
 
 	/* May already be CLOSED in case a previous configuration operation
 	 * (e.g RX/TX queue size change) that involves close&open failed.
@@ -2375,13 +2669,10 @@ int mlx5e_close_locked(struct net_device *netdev)
 
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager))
-		mlx5e_remove_sqs_fwd_rules(priv);
-
 	mlx5e_timestamp_cleanup(priv);
 	netif_carrier_off(priv->netdev);
-	mlx5e_redirect_rqts(priv);
-	mlx5e_close_channels(priv);
+	mlx5e_deactivate_priv_channels(priv);
+	mlx5e_close_channels(&priv->channels);
 
 	return 0;
 }
@@ -2401,11 +2692,10 @@ int mlx5e_close(struct net_device *netdev)
 	return err;
 }
 
-static int mlx5e_create_drop_rq(struct mlx5e_priv *priv,
-				struct mlx5e_rq *rq,
-				struct mlx5e_rq_param *param)
+static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev,
+			       struct mlx5e_rq *rq,
+			       struct mlx5e_rq_param *param)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqc = param->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
 	int err;
@@ -2417,111 +2707,85 @@ static int mlx5e_create_drop_rq(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	rq->priv = priv;
+	rq->mdev = mdev;
 
 	return 0;
 }
 
-static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
-				struct mlx5e_cq *cq,
-				struct mlx5e_cq_param *param)
+static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
+			       struct mlx5e_cq *cq,
+			       struct mlx5e_cq_param *param)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_core_cq *mcq = &cq->mcq;
-	int eqn_not_used;
-	unsigned int irqn;
-	int err;
-
-	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
-			       &cq->wq_ctrl);
-	if (err)
-		return err;
-
-	mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
-
-	mcq->cqe_sz     = 64;
-	mcq->set_ci_db  = cq->wq_ctrl.db.db;
-	mcq->arm_db     = cq->wq_ctrl.db.db + 1;
-	*mcq->set_ci_db = 0;
-	*mcq->arm_db    = 0;
-	mcq->vector     = param->eq_ix;
-	mcq->comp       = mlx5e_completion_event;
-	mcq->event      = mlx5e_cq_error_event;
-	mcq->irqn       = irqn;
-
-	cq->priv = priv;
-
-	return 0;
+	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
 
-static int mlx5e_open_drop_rq(struct mlx5e_priv *priv)
+static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
+			      struct mlx5e_rq *drop_rq)
 {
-	struct mlx5e_cq_param cq_param;
-	struct mlx5e_rq_param rq_param;
-	struct mlx5e_rq *rq = &priv->drop_rq;
-	struct mlx5e_cq *cq = &priv->drop_rq.cq;
+	struct mlx5e_cq_param cq_param = {};
+	struct mlx5e_rq_param rq_param = {};
+	struct mlx5e_cq *cq = &drop_rq->cq;
 	int err;
 
-	memset(&cq_param, 0, sizeof(cq_param));
-	memset(&rq_param, 0, sizeof(rq_param));
 	mlx5e_build_drop_rq_param(&rq_param);
 
-	err = mlx5e_create_drop_cq(priv, cq, &cq_param);
+	err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_cq(cq, &cq_param);
+	err = mlx5e_create_cq(cq, &cq_param);
 	if (err)
-		goto err_destroy_cq;
+		goto err_free_cq;
 
-	err = mlx5e_create_drop_rq(priv, rq, &rq_param);
+	err = mlx5e_alloc_drop_rq(mdev, drop_rq, &rq_param);
 	if (err)
-		goto err_disable_cq;
+		goto err_destroy_cq;
 
-	err = mlx5e_enable_rq(rq, &rq_param);
+	err = mlx5e_create_rq(drop_rq, &rq_param);
 	if (err)
-		goto err_destroy_rq;
+		goto err_free_rq;
 
 	return 0;
 
-err_destroy_rq:
-	mlx5e_destroy_rq(&priv->drop_rq);
-
-err_disable_cq:
-	mlx5e_disable_cq(&priv->drop_rq.cq);
+err_free_rq:
+	mlx5e_free_rq(drop_rq);
 
 err_destroy_cq:
-	mlx5e_destroy_cq(&priv->drop_rq.cq);
+	mlx5e_destroy_cq(cq);
+
+err_free_cq:
+	mlx5e_free_cq(cq);
 
 	return err;
 }
 
-static void mlx5e_close_drop_rq(struct mlx5e_priv *priv)
+static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
 {
-	mlx5e_disable_rq(&priv->drop_rq);
-	mlx5e_destroy_rq(&priv->drop_rq);
-	mlx5e_disable_cq(&priv->drop_rq.cq);
-	mlx5e_destroy_cq(&priv->drop_rq.cq);
+	mlx5e_destroy_rq(drop_rq);
+	mlx5e_free_rq(drop_rq);
+	mlx5e_destroy_cq(&drop_rq->cq);
+	mlx5e_free_cq(&drop_rq->cq);
 }
 
-static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc)
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
+		     u32 underlay_qpn, u32 *tisn)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0};
 	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
 
 	MLX5_SET(tisc, tisc, prio, tc << 1);
+	MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn);
 	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn);
 
 	if (mlx5_lag_is_lacp_owner(mdev))
 		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
 
-	return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]);
+	return mlx5_core_create_tis(mdev, in, sizeof(in), tisn);
 }
 
-static void mlx5e_destroy_tis(struct mlx5e_priv *priv, int tc)
+void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
 {
-	mlx5_core_destroy_tis(priv->mdev, priv->tisn[tc]);
+	mlx5_core_destroy_tis(mdev, tisn);
 }
 
 int mlx5e_create_tises(struct mlx5e_priv *priv)
@@ -2530,7 +2794,7 @@ int mlx5e_create_tises(struct mlx5e_priv *priv)
 	int tc;
 
 	for (tc = 0; tc < priv->profile->max_tc; tc++) {
-		err = mlx5e_create_tis(priv, tc);
+		err = mlx5e_create_tis(priv->mdev, tc, 0, &priv->tisn[tc]);
 		if (err)
 			goto err_close_tises;
 	}
@@ -2539,7 +2803,7 @@ int mlx5e_create_tises(struct mlx5e_priv *priv)
 
 err_close_tises:
 	for (tc--; tc >= 0; tc--)
-		mlx5e_destroy_tis(priv, tc);
+		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 
 	return err;
 }
@@ -2549,34 +2813,34 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 	int tc;
 
 	for (tc = 0; tc < priv->profile->max_tc; tc++)
-		mlx5e_destroy_tis(priv, tc);
+		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 }
 
-static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
-				      enum mlx5e_traffic_types tt)
+static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
+				      enum mlx5e_traffic_types tt,
+				      u32 *tirc)
 {
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
-	mlx5e_build_tir_ctx_lro(tirc, priv);
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
 }
 
-static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
-				       u32 rqtn)
+static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
 {
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
-	mlx5e_build_tir_ctx_lro(tirc, priv);
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, rqtn);
 	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
 }
 
-static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
+int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tir *tir;
 	void *tirc;
@@ -2594,7 +2858,7 @@ static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 		memset(in, 0, inlen);
 		tir = &priv->indir_tir[tt];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_indir_tir_ctx(priv, tirc, tt);
+		mlx5e_build_indir_tir_ctx(priv, tt, tirc);
 		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
 		if (err)
 			goto err_destroy_tirs;
@@ -2605,6 +2869,7 @@ static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 	return 0;
 
 err_destroy_tirs:
+	mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err);
 	for (tt--; tt >= 0; tt--)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]);
 
@@ -2632,8 +2897,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
 		memset(in, 0, inlen);
 		tir = &priv->direct_tir[ix];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_direct_tir_ctx(priv, tirc,
-					   priv->direct_tir[ix].rqt.rqtn);
+		mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc);
 		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
 		if (err)
 			goto err_destroy_ch_tirs;
@@ -2644,6 +2908,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
 	return 0;
 
 err_destroy_ch_tirs:
+	mlx5_core_warn(priv->mdev, "create direct tirs failed, %d\n", err);
 	for (ix--; ix >= 0; ix--)
 		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]);
 
@@ -2652,7 +2917,7 @@ err_destroy_ch_tirs:
 	return err;
 }
 
-static void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 {
 	int i;
 
@@ -2669,16 +2934,27 @@ void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
 		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
 }
 
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
+static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
 {
 	int err = 0;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return 0;
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable);
+		if (err)
+			return err;
+	}
 
-	for (i = 0; i < priv->params.num_channels; i++) {
-		err = mlx5e_modify_rq_vsd(&priv->channel[i]->rq, vsd);
+	return 0;
+}
+
+static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
+{
+	int err = 0;
+	int i;
+
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd);
 		if (err)
 			return err;
 	}
@@ -2689,7 +2965,7 @@ int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
 static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool was_opened;
+	struct mlx5e_channels new_channels = {};
 	int err = 0;
 
 	if (tc && tc != MLX5E_MAX_NUM_TC)
@@ -2697,17 +2973,21 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
 
 	mutex_lock(&priv->state_lock);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(priv->netdev);
+	new_channels.params = priv->channels.params;
+	new_channels.params.num_tc = tc ? tc : 1;
 
-	priv->params.num_tc = tc ? tc : 1;
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
 
-	if (was_opened)
-		err = mlx5e_open_locked(priv->netdev);
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
 
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+out:
 	mutex_unlock(&priv->state_lock);
-
 	return err;
 }
 
@@ -2737,7 +3017,9 @@ mqprio:
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return mlx5e_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return mlx5e_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 static void
@@ -2822,26 +3104,31 @@ typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable);
 static int set_feature_lro(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	int err;
+	struct mlx5e_channels new_channels = {};
+	int err = 0;
+	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	if (was_opened && (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST))
-		mlx5e_close_locked(priv->netdev);
+	reset = (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST);
+	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	priv->params.lro_en = enable;
-	err = mlx5e_modify_tirs_lro(priv);
-	if (err) {
-		netdev_err(netdev, "lro modify failed, %d\n", err);
-		priv->params.lro_en = !enable;
+	new_channels.params = priv->channels.params;
+	new_channels.params.lro_en = enable;
+
+	if (!reset) {
+		priv->channels.params = new_channels.params;
+		err = mlx5e_modify_tirs_lro(priv);
+		goto out;
 	}
 
-	if (was_opened && (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST))
-		mlx5e_open_locked(priv->netdev);
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
 
+	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+out:
 	mutex_unlock(&priv->state_lock);
-
 	return err;
 }
 
@@ -2878,23 +3165,44 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable)
 	return mlx5_set_port_fcs(mdev, !enable);
 }
 
-static int set_feature_rx_vlan(struct net_device *netdev, bool enable)
+static int set_feature_rx_fcs(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
 	mutex_lock(&priv->state_lock);
 
-	priv->params.vlan_strip_disable = !enable;
-	err = mlx5e_modify_rqs_vsd(priv, !enable);
+	priv->channels.params.scatter_fcs_en = enable;
+	err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable);
 	if (err)
-		priv->params.vlan_strip_disable = enable;
+		priv->channels.params.scatter_fcs_en = !enable;
 
 	mutex_unlock(&priv->state_lock);
 
 	return err;
 }
 
+static int set_feature_rx_vlan(struct net_device *netdev, bool enable)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int err = 0;
+
+	mutex_lock(&priv->state_lock);
+
+	priv->channels.params.vlan_strip_disable = !enable;
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	err = mlx5e_modify_channels_vsd(&priv->channels, !enable);
+	if (err)
+		priv->channels.params.vlan_strip_disable = enable;
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
 #ifdef CONFIG_RFS_ACCEL
 static int set_feature_arfs(struct net_device *netdev, bool enable)
 {
@@ -2947,6 +3255,8 @@ static int mlx5e_set_features(struct net_device *netdev,
 				    set_feature_tc_num_filters);
 	err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL,
 				    set_feature_rx_all);
+	err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS,
+				    set_feature_rx_fcs);
 	err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX,
 				    set_feature_rx_vlan);
 #ifdef CONFIG_RFS_ACCEL
@@ -2960,28 +3270,38 @@ static int mlx5e_set_features(struct net_device *netdev,
 static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool was_opened;
+	struct mlx5e_channels new_channels = {};
+	int curr_mtu;
 	int err = 0;
 	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	reset = !priv->params.lro_en &&
-		(priv->params.rq_wq_type !=
+	reset = !priv->channels.params.lro_en &&
+		(priv->channels.params.rq_wq_type !=
 		 MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened && reset)
-		mlx5e_close_locked(netdev);
+	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
 
+	curr_mtu    = netdev->mtu;
 	netdev->mtu = new_mtu;
-	mlx5e_set_dev_port_mtu(netdev);
 
-	if (was_opened && reset)
-		err = mlx5e_open_locked(netdev);
+	if (!reset) {
+		mlx5e_set_dev_port_mtu(priv);
+		goto out;
+	}
 
-	mutex_unlock(&priv->state_lock);
+	new_channels.params = priv->channels.params;
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err) {
+		netdev->mtu = curr_mtu;
+		goto out;
+	}
+
+	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
 
+out:
+	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
@@ -3100,8 +3420,8 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 					    vf_stats);
 }
 
-void mlx5e_add_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti)
+static void mlx5e_add_vxlan_port(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -3114,8 +3434,8 @@ void mlx5e_add_vxlan_port(struct net_device *netdev,
 	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
 }
 
-void mlx5e_del_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti)
+static void mlx5e_del_vxlan_port(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -3186,8 +3506,8 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 
 	netdev_err(dev, "TX timeout detected\n");
 
-	for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
-		struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
+		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
 			continue;
@@ -3219,7 +3539,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 
 	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
 	/* no need for full reset when exchanging programs */
-	reset = (!priv->xdp_prog || !prog);
+	reset = (!priv->channels.params.xdp_prog || !prog);
 
 	if (was_opened && reset)
 		mlx5e_close_locked(netdev);
@@ -3227,7 +3547,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
 		 */
-		prog = bpf_prog_add(prog, priv->params.num_channels);
+		prog = bpf_prog_add(prog, priv->channels.num);
 		if (IS_ERR(prog)) {
 			err = PTR_ERR(prog);
 			goto unlock;
@@ -3237,12 +3557,12 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* exchange programs, extra prog reference we got from caller
 	 * as long as we don't fail from this point onwards.
 	 */
-	old_prog = xchg(&priv->xdp_prog, prog);
+	old_prog = xchg(&priv->channels.params.xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
 	if (reset) /* change RQ type according to priv->xdp_prog */
-		mlx5e_set_rq_priv_params(priv);
+		mlx5e_set_rq_params(priv->mdev, &priv->channels.params);
 
 	if (was_opened && reset)
 		mlx5e_open_locked(netdev);
@@ -3253,8 +3573,8 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* exchanging programs w/o reset, we update ref counts on behalf
 	 * of the channels RQs here.
 	 */
-	for (i = 0; i < priv->params.num_channels; i++) {
-		struct mlx5e_channel *c = priv->channel[i];
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
 
 		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
 		napi_synchronize(&c->napi);
@@ -3280,7 +3600,7 @@ static bool mlx5e_xdp_attached(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	return !!priv->xdp_prog;
+	return !!priv->channels.params.xdp_prog;
 }
 
 static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
@@ -3303,10 +3623,12 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
 static void mlx5e_netpoll(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *chs = &priv->channels;
+
 	int i;
 
-	for (i = 0; i < priv->params.num_channels; i++)
-		napi_schedule(&priv->channel[i]->napi);
+	for (i = 0; i < chs->num; i++)
+		napi_schedule(&chs->c[i]->napi);
 }
 #endif
 
@@ -3463,6 +3785,12 @@ static bool cqe_compress_heuristic(u32 link_speed, u32 pci_bw)
 		(pci_bw < 40000) && (pci_bw < link_speed));
 }
 
+static bool hw_lro_heuristic(u32 link_speed, u32 pci_bw)
+{
+	return !(link_speed && pci_bw &&
+		 (pci_bw <= 16000) && (pci_bw < link_speed));
+}
+
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 {
 	params->rx_cq_period_mode = cq_period_mode;
@@ -3475,6 +3803,13 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
 		params->rx_cq_moderation.usec =
 			MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
+
+	if (params->rx_am_enabled)
+		params->rx_cq_moderation =
+			mlx5e_am_get_def_profile(params->rx_cq_period_mode);
+
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
+			params->rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
 }
 
 u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
@@ -3489,75 +3824,81 @@ u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
 	return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
 }
 
-static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
-					struct net_device *netdev,
-					const struct mlx5e_profile *profile,
-					void *ppriv)
+void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_params *params,
+			    u16 max_channels)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u8 cq_period_mode = 0;
 	u32 link_speed = 0;
 	u32 pci_bw = 0;
-	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
-					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
-					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	priv->mdev                         = mdev;
-	priv->netdev                       = netdev;
-	priv->params.num_channels          = profile->max_nch(mdev);
-	priv->profile                      = profile;
-	priv->ppriv                        = ppriv;
+	params->num_channels = max_channels;
+	params->num_tc       = 1;
 
-	priv->params.lro_timeout =
-		mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+	mlx5e_get_max_linkspeed(mdev, &link_speed);
+	mlx5e_get_pci_bw(mdev, &pci_bw);
+	mlx5_core_dbg(mdev, "Max link speed = %d, PCI BW = %d\n",
+		      link_speed, pci_bw);
 
-	priv->params.log_sq_size = is_kdump_kernel() ?
+	/* SQ */
+	params->log_sq_size = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 
 	/* set CQE compression */
-	priv->params.rx_cqe_compress_def = false;
+	params->rx_cqe_compress_def = false;
 	if (MLX5_CAP_GEN(mdev, cqe_compression) &&
-	    MLX5_CAP_GEN(mdev, vport_group_manager)) {
-		mlx5e_get_max_linkspeed(mdev, &link_speed);
-		mlx5e_get_pci_bw(mdev, &pci_bw);
-		mlx5_core_dbg(mdev, "Max link speed = %d, PCI BW = %d\n",
-			      link_speed, pci_bw);
-		priv->params.rx_cqe_compress_def =
-			cqe_compress_heuristic(link_speed, pci_bw);
-	}
-
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS,
-			priv->params.rx_cqe_compress_def);
-
-	mlx5e_set_rq_priv_params(priv);
-	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		priv->params.lro_en = true;
-
-	priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
-
-	priv->params.tx_cq_moderation.usec =
-		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
-	priv->params.tx_cq_moderation.pkts =
-		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
-	priv->params.tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
-	mlx5_query_min_inline(mdev, &priv->params.tx_min_inline_mode);
-	if (priv->params.tx_min_inline_mode == MLX5_INLINE_MODE_NONE &&
+	     MLX5_CAP_GEN(mdev, vport_group_manager))
+		params->rx_cqe_compress_def = cqe_compress_heuristic(link_speed, pci_bw);
+
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
+
+	/* RQ */
+	mlx5e_set_rq_params(mdev, params);
+
+	/* HW LRO */
+	/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
+	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		params->lro_en = hw_lro_heuristic(link_speed, pci_bw);
+	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+
+	/* CQ moderation params */
+	cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
+
+	params->tx_cq_moderation.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+	params->tx_cq_moderation.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
+
+	/* TX inline */
+	params->tx_max_inline = mlx5e_get_max_inline_cap(mdev);
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
+	if (params->tx_min_inline_mode == MLX5_INLINE_MODE_NONE &&
 	    !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		priv->params.tx_min_inline_mode = MLX5_INLINE_MODE_L2;
+		params->tx_min_inline_mode = MLX5_INLINE_MODE_L2;
 
-	priv->params.num_tc                = 1;
-	priv->params.rss_hfunc             = ETH_RSS_HASH_XOR;
+	/* RSS */
+	params->rss_hfunc = ETH_RSS_HASH_XOR;
+	netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
+	mlx5e_build_default_indir_rqt(mdev, params->indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, max_channels);
+}
 
-	netdev_rss_key_fill(priv->params.toeplitz_hash_key,
-			    sizeof(priv->params.toeplitz_hash_key));
+static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
+					struct net_device *netdev,
+					const struct mlx5e_profile *profile,
+					void *ppriv)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
+	priv->mdev        = mdev;
+	priv->netdev      = netdev;
+	priv->profile     = profile;
+	priv->ppriv       = ppriv;
 
-	/* Initialize pflags */
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
-			priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
+	mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
 
 	mutex_init(&priv->state_lock);
 
@@ -3642,13 +3983,19 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	if (fcs_supported)
 		netdev->hw_features |= NETIF_F_RXALL;
 
+	if (MLX5_CAP_ETH(mdev, scatter_fcs))
+		netdev->hw_features |= NETIF_F_RXFCS;
+
 	netdev->features          = netdev->hw_features;
-	if (!priv->params.lro_en)
+	if (!priv->channels.params.lro_en)
 		netdev->features  &= ~NETIF_F_LRO;
 
 	if (fcs_enabled)
 		netdev->features  &= ~NETIF_F_RXALL;
 
+	if (!priv->channels.params.scatter_fcs_en)
+		netdev->features  &= ~NETIF_F_RXFCS;
+
 #define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f)
 	if (FT_CAP(flow_modify_en) &&
 	    FT_CAP(modify_root) &&
@@ -3708,39 +4055,30 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_vxlan_cleanup(priv);
 
-	if (priv->xdp_prog)
-		bpf_prog_put(priv->xdp_prog);
+	if (priv->channels.params.xdp_prog)
+		bpf_prog_put(priv->channels.params.xdp_prog);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
-	int i;
 
-	err = mlx5e_create_indirect_rqts(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create indirect rqts failed, %d\n", err);
+	err = mlx5e_create_indirect_rqt(priv);
+	if (err)
 		return err;
-	}
 
 	err = mlx5e_create_direct_rqts(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create direct rqts failed, %d\n", err);
+	if (err)
 		goto err_destroy_indirect_rqts;
-	}
 
 	err = mlx5e_create_indirect_tirs(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create indirect tirs failed, %d\n", err);
+	if (err)
 		goto err_destroy_direct_rqts;
-	}
 
 	err = mlx5e_create_direct_tirs(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create direct tirs failed, %d\n", err);
+	if (err)
 		goto err_destroy_indirect_tirs;
-	}
 
 	err = mlx5e_create_flow_steering(priv);
 	if (err) {
@@ -3761,8 +4099,7 @@ err_destroy_direct_tirs:
 err_destroy_indirect_tirs:
 	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
-	for (i = 0; i < priv->profile->max_nch(mdev); i++)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	mlx5e_destroy_direct_rqts(priv);
 err_destroy_indirect_rqts:
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	return err;
@@ -3770,14 +4107,11 @@ err_destroy_indirect_rqts:
 
 static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 {
-	int i;
-
 	mlx5e_tc_cleanup(priv);
 	mlx5e_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_indirect_tirs(priv);
-	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	mlx5e_destroy_direct_rqts(priv);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 }
 
@@ -3801,21 +4135,22 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep rep;
+	u16 max_mtu;
+
+	mlx5e_init_l2_addr(priv);
+
+	/* MTU range: 68 - hw-specific max */
+	netdev->min_mtu = ETH_MIN_MTU;
+	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu);
+	mlx5e_set_dev_port_mtu(priv);
 
 	mlx5_lag_add(mdev, netdev);
 
 	mlx5e_enable_async_events(priv);
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
-		mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
-		rep.load = mlx5e_nic_rep_load;
-		rep.unload = mlx5e_nic_rep_unload;
-		rep.vport = FDB_UPLINK_VPORT;
-		rep.netdev = netdev;
-		mlx5_eswitch_register_vport_rep(esw, 0, &rep);
-	}
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		mlx5e_register_vport_reps(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
@@ -3828,16 +4163,29 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	}
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
+
+	rtnl_lock();
+	if (netif_running(netdev))
+		mlx5e_open(netdev);
+	netif_device_attach(netdev);
+	rtnl_unlock();
 }
 
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+
+	rtnl_lock();
+	if (netif_running(priv->netdev))
+		mlx5e_close(priv->netdev);
+	netif_device_detach(priv->netdev);
+	rtnl_unlock();
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
+
 	if (MLX5_CAP_GEN(mdev, vport_group_manager))
-		mlx5_eswitch_unregister_vport_rep(esw, 0);
+		mlx5e_unregister_vport_reps(priv);
+
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove(mdev);
 }
@@ -3853,9 +4201,13 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.disable	   = mlx5e_nic_disable,
 	.update_stats	   = mlx5e_update_stats,
 	.max_nch	   = mlx5e_get_max_num_channels,
+	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe,
+	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
 	.max_tc		   = MLX5E_MAX_NUM_TC,
 };
 
+/* mlx5e generic netdev management API (move to en_common.c) */
+
 struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 				       const struct mlx5e_profile *profile,
 				       void *ppriv)
@@ -3872,6 +4224,10 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 		return NULL;
 	}
 
+#ifdef CONFIG_RFS_ACCEL
+	netdev->rx_cpu_rmap = mdev->rmap;
+#endif
+
 	profile->init(mdev, netdev, profile, ppriv);
 
 	netif_carrier_off(netdev);
@@ -3891,14 +4247,12 @@ err_cleanup_nic:
 	return NULL;
 }
 
-int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
+int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	const struct mlx5e_profile *profile;
-	struct mlx5e_priv *priv;
-	u16 max_mtu;
 	int err;
 
-	priv = netdev_priv(netdev);
 	profile = priv->profile;
 	clear_bit(MLX5E_STATE_DESTROYING, &priv->state);
 
@@ -3906,7 +4260,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	if (err)
 		goto out;
 
-	err = mlx5e_open_drop_rq(priv);
+	err = mlx5e_open_drop_rq(mdev, &priv->drop_rq);
 	if (err) {
 		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
 		goto err_cleanup_tx;
@@ -3918,28 +4272,13 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 
 	mlx5e_create_q_counter(priv);
 
-	mlx5e_init_l2_addr(priv);
-
-	/* MTU range: 68 - hw-specific max */
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu);
-
-	mlx5e_set_dev_port_mtu(netdev);
-
 	if (profile->enable)
 		profile->enable(priv);
 
-	rtnl_lock();
-	if (netif_running(netdev))
-		mlx5e_open(netdev);
-	netif_device_attach(netdev);
-	rtnl_unlock();
-
 	return 0;
 
 err_close_drop_rq:
-	mlx5e_close_drop_rq(priv);
+	mlx5e_close_drop_rq(&priv->drop_rq);
 
 err_cleanup_tx:
 	profile->cleanup_tx(priv);
@@ -3948,66 +4287,34 @@ out:
 	return err;
 }
 
-static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
-	u8 mac[ETH_ALEN];
-
-	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
-		return;
-
-	mlx5_query_nic_vport_mac_address(mdev, 0, mac);
-
-	for (vport = 1; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep rep;
-
-		rep.load = mlx5e_vport_rep_load;
-		rep.unload = mlx5e_vport_rep_unload;
-		rep.vport = vport;
-		ether_addr_copy(rep.hw_id, mac);
-		mlx5_eswitch_register_vport_rep(esw, vport, &rep);
-	}
-}
-
-static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
-
-	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
-		return;
-
-	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport);
-}
-
-void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
+void mlx5e_detach_netdev(struct mlx5e_priv *priv)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	const struct mlx5e_profile *profile = priv->profile;
 
 	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
 
-	rtnl_lock();
-	if (netif_running(netdev))
-		mlx5e_close(netdev);
-	netif_device_detach(netdev);
-	rtnl_unlock();
-
 	if (profile->disable)
 		profile->disable(priv);
 	flush_workqueue(priv->wq);
 
 	mlx5e_destroy_q_counter(priv);
 	profile->cleanup_rx(priv);
-	mlx5e_close_drop_rq(priv);
+	mlx5e_close_drop_rq(&priv->drop_rq);
 	profile->cleanup_tx(priv);
 	cancel_delayed_work_sync(&priv->update_stats_work);
 }
 
+void mlx5e_destroy_netdev(struct mlx5e_priv *priv)
+{
+	const struct mlx5e_profile *profile = priv->profile;
+	struct net_device *netdev = priv->netdev;
+
+	destroy_workqueue(priv->wq);
+	if (profile->cleanup)
+		profile->cleanup(priv);
+	free_netdev(netdev);
+}
+
 /* mlx5e_attach and mlx5e_detach scope should be only creating/destroying
  * hardware contexts and to connect it to the current netdev.
  */
@@ -4024,13 +4331,12 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv)
 	if (err)
 		return err;
 
-	err = mlx5e_attach_netdev(mdev, netdev);
+	err = mlx5e_attach_netdev(priv);
 	if (err) {
 		mlx5e_destroy_mdev_resources(mdev);
 		return err;
 	}
 
-	mlx5e_register_vport_rep(mdev);
 	return 0;
 }
 
@@ -4042,8 +4348,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 	if (!netif_device_present(netdev))
 		return;
 
-	mlx5e_unregister_vport_rep(mdev);
-	mlx5e_detach_netdev(mdev, netdev);
+	mlx5e_detach_netdev(priv);
 	mlx5e_destroy_mdev_resources(mdev);
 }
 
@@ -4051,7 +4356,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	void *ppriv = NULL;
+	struct mlx5e_rep_priv *rpriv = NULL;
 	void *priv;
 	int vport;
 	int err;
@@ -4061,10 +4366,17 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 	if (err)
 		return NULL;
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager))
-		ppriv = &esw->offloads.vport_reps[0];
+	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
+		rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
+		if (!rpriv) {
+			mlx5_core_warn(mdev,
+				       "Not creating net device, Failed to alloc rep priv data\n");
+			return NULL;
+		}
+		rpriv->rep = &esw->offloads.vport_reps[0];
+	}
 
-	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, ppriv);
+	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, rpriv);
 	if (!netdev) {
 		mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
 		goto err_unregister_reps;
@@ -4090,33 +4402,25 @@ err_detach:
 	mlx5e_detach(mdev, priv);
 
 err_destroy_netdev:
-	mlx5e_destroy_netdev(mdev, priv);
+	mlx5e_destroy_netdev(priv);
 
 err_unregister_reps:
 	for (vport = 1; vport < total_vfs; vport++)
 		mlx5_eswitch_unregister_vport_rep(esw, vport);
 
+	kfree(rpriv);
 	return NULL;
 }
 
-void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
-{
-	const struct mlx5e_profile *profile = priv->profile;
-	struct net_device *netdev = priv->netdev;
-
-	destroy_workqueue(priv->wq);
-	if (profile->cleanup)
-		profile->cleanup(priv);
-	free_netdev(netdev);
-}
-
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
 	struct mlx5e_priv *priv = vpriv;
+	void *ppriv = priv->ppriv;
 
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
-	mlx5e_destroy_netdev(mdev, priv);
+	mlx5e_destroy_netdev(priv);
+	kfree(ppriv);
 }
 
 static void *mlx5e_get_netdev(void *vpriv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2c864574a9d5..79462c0368a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -34,10 +34,14 @@
 #include <linux/mlx5/fs.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
+#include <net/netevent.h>
+#include <net/arp.h>
 
 #include "eswitch.h"
 #include "en.h"
+#include "en_rep.h"
 #include "en_tc.h"
+#include "fs_core.h"
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
@@ -75,7 +79,8 @@ static void mlx5e_rep_get_strings(struct net_device *dev,
 static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct rtnl_link_stats64 *vport_stats;
 	struct ifla_vf_stats vf_stats;
 	int err;
@@ -102,14 +107,16 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->params.num_channels; i++) {
-		rq_stats = &priv->channel[i]->rq.stats;
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
+
+		rq_stats = &c->rq.stats;
 
 		s->rx_packets	+= rq_stats->packets;
 		s->rx_bytes	+= rq_stats->bytes;
 
-		for (j = 0; j < priv->params.num_tc; j++) {
-			sq_stats = &priv->channel[i]->sq[j].stats;
+		for (j = 0; j < priv->channels.params.num_tc; j++) {
+			sq_stats = &c->sq[j].stats;
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
@@ -163,7 +170,8 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 
 	if (esw->mode == SRIOV_NONE)
@@ -182,66 +190,426 @@ int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 }
 
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
-
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5e_channel *c;
-	int n, tc, err, num_sqs = 0;
+	int n, tc, num_sqs = 0;
+	int err = -ENOMEM;
 	u16 *sqs;
 
-	sqs = kcalloc(priv->params.num_channels * priv->params.num_tc, sizeof(u16), GFP_KERNEL);
+	sqs = kcalloc(priv->channels.num * priv->channels.params.num_tc, sizeof(u16), GFP_KERNEL);
 	if (!sqs)
-		return -ENOMEM;
+		goto out;
 
-	for (n = 0; n < priv->params.num_channels; n++) {
-		c = priv->channel[n];
+	for (n = 0; n < priv->channels.num; n++) {
+		c = priv->channels.c[n];
 		for (tc = 0; tc < c->num_tc; tc++)
 			sqs[num_sqs++] = c->sq[tc].sqn;
 	}
 
 	err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
-
 	kfree(sqs);
+
+out:
+	if (err)
+		netdev_warn(priv->netdev, "Failed to add SQs FWD rules %d\n", err);
 	return err;
 }
 
-int mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
 {
-	struct net_device *netdev = rep->netdev;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+
+	mlx5_eswitch_sqs2vport_stop(esw, rep);
+}
+
+static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	unsigned long ipv6_interval = NEIGH_VAR(&ipv6_stub->nd_tbl->parms,
+						DELAY_PROBE_TIME);
+#else
+	unsigned long ipv6_interval = ~0UL;
+#endif
+	unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms,
+						DELAY_PROBE_TIME);
+	struct net_device *netdev = rpriv->rep->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return mlx5e_add_sqs_fwd_rules(priv);
-	return 0;
+	rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval);
+	mlx5_fc_update_sampling_interval(priv->mdev, rpriv->neigh_update.min_interval);
 }
 
-void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
+void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv)
 {
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
 
-	mlx5_eswitch_sqs2vport_stop(esw, rep);
+	mlx5_fc_queue_stats_work(priv->mdev,
+				 &neigh_update->neigh_stats_work,
+				 neigh_update->min_interval);
 }
 
-void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
-			  struct mlx5_eswitch_rep *rep)
+static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
 {
-	struct net_device *netdev = rep->netdev;
+	struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
+						    neigh_update.neigh_stats_work.work);
+	struct net_device *netdev = rpriv->rep->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_neigh_hash_entry *nhe;
 
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-		mlx5e_remove_sqs_fwd_rules(priv);
+	rtnl_lock();
+	if (!list_empty(&rpriv->neigh_update.neigh_list))
+		mlx5e_rep_queue_neigh_stats_work(priv);
 
-	/* clean (and re-init) existing uplink offloaded TC rules */
-	mlx5e_tc_cleanup(priv);
-	mlx5e_tc_init(priv);
+	list_for_each_entry(nhe, &rpriv->neigh_update.neigh_list, neigh_list)
+		mlx5e_tc_update_neigh_used_value(nhe);
+
+	rtnl_unlock();
+}
+
+static void mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe)
+{
+	refcount_inc(&nhe->refcnt);
+}
+
+static void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe)
+{
+	if (refcount_dec_and_test(&nhe->refcnt))
+		kfree(nhe);
+}
+
+static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
+				   struct mlx5e_encap_entry *e,
+				   bool neigh_connected,
+				   unsigned char ha[ETH_ALEN])
+{
+	struct ethhdr *eth = (struct ethhdr *)e->encap_header;
+
+	ASSERT_RTNL();
+
+	if ((!neigh_connected && (e->flags & MLX5_ENCAP_ENTRY_VALID)) ||
+	    !ether_addr_equal(e->h_dest, ha))
+		mlx5e_tc_encap_flows_del(priv, e);
+
+	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
+		ether_addr_copy(e->h_dest, ha);
+		ether_addr_copy(eth->h_dest, ha);
+
+		mlx5e_tc_encap_flows_add(priv, e);
+	}
+}
+
+static void mlx5e_rep_neigh_update(struct work_struct *work)
+{
+	struct mlx5e_neigh_hash_entry *nhe =
+		container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work);
+	struct neighbour *n = nhe->n;
+	struct mlx5e_encap_entry *e;
+	unsigned char ha[ETH_ALEN];
+	struct mlx5e_priv *priv;
+	bool neigh_connected;
+	bool encap_connected;
+	u8 nud_state, dead;
+
+	rtnl_lock();
+
+	/* If these parameters are changed after we release the lock,
+	 * we'll receive another event letting us know about it.
+	 * We use this lock to avoid inconsistency between the neigh validity
+	 * and it's hw address.
+	 */
+	read_lock_bh(&n->lock);
+	memcpy(ha, n->ha, ETH_ALEN);
+	nud_state = n->nud_state;
+	dead = n->dead;
+	read_unlock_bh(&n->lock);
+
+	neigh_connected = (nud_state & NUD_VALID) && !dead;
+
+	list_for_each_entry(e, &nhe->encap_list, encap_list) {
+		encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
+		priv = netdev_priv(e->out_dev);
+
+		if (encap_connected != neigh_connected ||
+		    !ether_addr_equal(e->h_dest, ha))
+			mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
+	}
+	mlx5e_rep_neigh_entry_release(nhe);
+	rtnl_unlock();
+	neigh_release(n);
+}
+
+static struct mlx5e_neigh_hash_entry *
+mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
+			     struct mlx5e_neigh *m_neigh);
+
+static int mlx5e_rep_netevent_event(struct notifier_block *nb,
+				    unsigned long event, void *ptr)
+{
+	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
+						    neigh_update.netevent_nb);
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	struct net_device *netdev = rpriv->rep->netdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_neigh_hash_entry *nhe = NULL;
+	struct mlx5e_neigh m_neigh = {};
+	struct neigh_parms *p;
+	struct neighbour *n;
+	bool found = false;
+
+	switch (event) {
+	case NETEVENT_NEIGH_UPDATE:
+		n = ptr;
+#if IS_ENABLED(CONFIG_IPV6)
+		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+#else
+		if (n->tbl != &arp_tbl)
+#endif
+			return NOTIFY_DONE;
+
+		m_neigh.dev = n->dev;
+		m_neigh.family = n->ops->family;
+		memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+
+		/* We are in atomic context and can't take RTNL mutex, so use
+		 * spin_lock_bh to lookup the neigh table. bh is used since
+		 * netevent can be called from a softirq context.
+		 */
+		spin_lock_bh(&neigh_update->encap_lock);
+		nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
+		if (!nhe) {
+			spin_unlock_bh(&neigh_update->encap_lock);
+			return NOTIFY_DONE;
+		}
+
+		/* This assignment is valid as long as the the neigh reference
+		 * is taken
+		 */
+		nhe->n = n;
+
+		/* Take a reference to ensure the neighbour and mlx5 encap
+		 * entry won't be destructed until we drop the reference in
+		 * delayed work.
+		 */
+		neigh_hold(n);
+		mlx5e_rep_neigh_entry_hold(nhe);
+
+		if (!queue_work(priv->wq, &nhe->neigh_update_work)) {
+			mlx5e_rep_neigh_entry_release(nhe);
+			neigh_release(n);
+		}
+		spin_unlock_bh(&neigh_update->encap_lock);
+		break;
+
+	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
+		p = ptr;
+
+		/* We check the device is present since we don't care about
+		 * changes in the default table, we only care about changes
+		 * done per device delay prob time parameter.
+		 */
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
+#else
+		if (!p->dev || p->tbl != &arp_tbl)
+#endif
+			return NOTIFY_DONE;
+
+		/* We are in atomic context and can't take RTNL mutex,
+		 * so use spin_lock_bh to walk the neigh list and look for
+		 * the relevant device. bh is used since netevent can be
+		 * called from a softirq context.
+		 */
+		spin_lock_bh(&neigh_update->encap_lock);
+		list_for_each_entry(nhe, &neigh_update->neigh_list, neigh_list) {
+			if (p->dev == nhe->m_neigh.dev) {
+				found = true;
+				break;
+			}
+		}
+		spin_unlock_bh(&neigh_update->encap_lock);
+		if (!found)
+			return NOTIFY_DONE;
+
+		neigh_update->min_interval = min_t(unsigned long,
+						   NEIGH_VAR(p, DELAY_PROBE_TIME),
+						   neigh_update->min_interval);
+		mlx5_fc_update_sampling_interval(priv->mdev,
+						 neigh_update->min_interval);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static const struct rhashtable_params mlx5e_neigh_ht_params = {
+	.head_offset = offsetof(struct mlx5e_neigh_hash_entry, rhash_node),
+	.key_offset = offsetof(struct mlx5e_neigh_hash_entry, m_neigh),
+	.key_len = sizeof(struct mlx5e_neigh),
+	.automatic_shrinking = true,
+};
+
+static int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	int err;
+
+	err = rhashtable_init(&neigh_update->neigh_ht, &mlx5e_neigh_ht_params);
+	if (err)
+		return err;
+
+	INIT_LIST_HEAD(&neigh_update->neigh_list);
+	spin_lock_init(&neigh_update->encap_lock);
+	INIT_DELAYED_WORK(&neigh_update->neigh_stats_work,
+			  mlx5e_rep_neigh_stats_work);
+	mlx5e_rep_neigh_update_init_interval(rpriv);
+
+	rpriv->neigh_update.netevent_nb.notifier_call = mlx5e_rep_netevent_event;
+	err = register_netevent_notifier(&rpriv->neigh_update.netevent_nb);
+	if (err)
+		goto out_err;
+	return 0;
+
+out_err:
+	rhashtable_destroy(&neigh_update->neigh_ht);
+	return err;
+}
+
+static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	struct mlx5e_priv *priv = netdev_priv(rpriv->rep->netdev);
+
+	unregister_netevent_notifier(&neigh_update->netevent_nb);
+
+	flush_workqueue(priv->wq); /* flush neigh update works */
+
+	cancel_delayed_work_sync(&rpriv->neigh_update.neigh_stats_work);
+
+	rhashtable_destroy(&neigh_update->neigh_ht);
+}
+
+static int mlx5e_rep_neigh_entry_insert(struct mlx5e_priv *priv,
+					struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	int err;
+
+	err = rhashtable_insert_fast(&rpriv->neigh_update.neigh_ht,
+				     &nhe->rhash_node,
+				     mlx5e_neigh_ht_params);
+	if (err)
+		return err;
+
+	list_add(&nhe->neigh_list, &rpriv->neigh_update.neigh_list);
+
+	return err;
+}
+
+static void mlx5e_rep_neigh_entry_remove(struct mlx5e_priv *priv,
+					 struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	spin_lock_bh(&rpriv->neigh_update.encap_lock);
+
+	list_del(&nhe->neigh_list);
+
+	rhashtable_remove_fast(&rpriv->neigh_update.neigh_ht,
+			       &nhe->rhash_node,
+			       mlx5e_neigh_ht_params);
+	spin_unlock_bh(&rpriv->neigh_update.encap_lock);
+}
+
+/* This function must only be called under RTNL lock or under the
+ * representor's encap_lock in case RTNL mutex can't be held.
+ */
+static struct mlx5e_neigh_hash_entry *
+mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
+			     struct mlx5e_neigh *m_neigh)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+
+	return rhashtable_lookup_fast(&neigh_update->neigh_ht, m_neigh,
+				      mlx5e_neigh_ht_params);
+}
+
+static int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
+					struct mlx5e_encap_entry *e,
+					struct mlx5e_neigh_hash_entry **nhe)
+{
+	int err;
+
+	*nhe = kzalloc(sizeof(**nhe), GFP_KERNEL);
+	if (!*nhe)
+		return -ENOMEM;
+
+	memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh));
+	INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update);
+	INIT_LIST_HEAD(&(*nhe)->encap_list);
+	refcount_set(&(*nhe)->refcnt, 1);
+
+	err = mlx5e_rep_neigh_entry_insert(priv, *nhe);
+	if (err)
+		goto out_free;
+	return 0;
+
+out_free:
+	kfree(*nhe);
+	return err;
+}
+
+static void mlx5e_rep_neigh_entry_destroy(struct mlx5e_priv *priv,
+					  struct mlx5e_neigh_hash_entry *nhe)
+{
+	/* The neigh hash entry must be removed from the hash table regardless
+	 * of the reference count value, so it won't be found by the next
+	 * neigh notification call. The neigh hash entry reference count is
+	 * incremented only during creation and neigh notification calls and
+	 * protects from freeing the nhe struct.
+	 */
+	mlx5e_rep_neigh_entry_remove(priv, nhe);
+	mlx5e_rep_neigh_entry_release(nhe);
+}
+
+int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e)
+{
+	struct mlx5e_neigh_hash_entry *nhe;
+	int err;
+
+	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
+	if (!nhe) {
+		err = mlx5e_rep_neigh_entry_create(priv, e, &nhe);
+		if (err)
+			return err;
+	}
+	list_add(&e->encap_list, &nhe->encap_list);
+	return 0;
+}
+
+void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
+				  struct mlx5e_encap_entry *e)
+{
+	struct mlx5e_neigh_hash_entry *nhe;
+
+	list_del(&e->encap_list);
+	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
+
+	if (list_empty(&nhe->encap_list))
+		mlx5e_rep_neigh_entry_destroy(priv, nhe);
 }
 
 static int mlx5e_rep_open(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int err;
 
@@ -259,7 +627,8 @@ static int mlx5e_rep_open(struct net_device *dev)
 static int mlx5e_rep_close(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 
 	(void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
@@ -271,7 +640,8 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
 					char *buf, size_t len)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	int ret;
 
 	ret = snprintf(buf, len, "%d", rep->vport - 1);
@@ -314,18 +684,25 @@ static int mlx5e_rep_ndo_setup_tc(struct net_device *dev, u32 handle,
 
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 {
-	struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep;
 
-	if (rep && rep->vport == FDB_UPLINK_VPORT && esw->mode == SRIOV_OFFLOADS)
+	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+		return false;
+
+	rep = rpriv->rep;
+	if (esw->mode == SRIOV_OFFLOADS &&
+	    rep && rep->vport == FDB_UPLINK_VPORT)
 		return true;
 
 	return false;
 }
 
-bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
+static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 {
-	struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 
 	if (rep && rep->vport != FDB_UPLINK_VPORT)
 		return true;
@@ -393,48 +770,27 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_ndo_setup_tc,
 	.ndo_get_stats64         = mlx5e_rep_get_stats,
-	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
-	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
 	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
 };
 
-static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
-					struct net_device *netdev,
-					const struct mlx5e_profile *profile,
-					void *ppriv)
+static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	priv->params.log_sq_size           =
-		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
-	priv->params.rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
-	priv->params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
-
-	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
-					    BIT(priv->params.log_rq_size));
-
-	priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
-
-	priv->params.tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
-	priv->params.num_tc                = 1;
-
-	priv->params.lro_wqe_sz            =
-		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
-
-	priv->mdev                         = mdev;
-	priv->netdev                       = netdev;
-	priv->params.num_channels          = profile->max_nch(mdev);
-	priv->profile                      = profile;
-	priv->ppriv                        = ppriv;
+	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
+	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 
-	mutex_init(&priv->state_lock);
+	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
 
-	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+	params->tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
+	params->num_tc                = 1;
+	params->lro_wqe_sz            = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 }
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
@@ -460,30 +816,39 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
 			   const struct mlx5e_profile *profile,
 			   void *ppriv)
 {
-	mlx5e_build_rep_netdev_priv(mdev, netdev, profile, ppriv);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	priv->mdev                         = mdev;
+	priv->netdev                       = netdev;
+	priv->profile                      = profile;
+	priv->ppriv                        = ppriv;
+
+	mutex_init(&priv->state_lock);
+
+	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+
+	priv->channels.params.num_channels = profile->max_nch(mdev);
+	mlx5e_build_rep_params(mdev, &priv->channels.params);
 	mlx5e_build_rep_netdev(netdev);
 }
 
 static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_flow_handle *flow_rule;
 	int err;
-	int i;
+
+	mlx5e_init_l2_addr(priv);
 
 	err = mlx5e_create_direct_rqts(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create direct rqts failed, %d\n", err);
+	if (err)
 		return err;
-	}
 
 	err = mlx5e_create_direct_tirs(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create direct tirs failed, %d\n", err);
+	if (err)
 		goto err_destroy_direct_rqts;
-	}
 
 	flow_rule = mlx5_eswitch_create_vport_rx_rule(esw,
 						      rep->vport,
@@ -505,21 +870,19 @@ err_del_flow_rule:
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_direct_rqts:
-	for (i = 0; i < priv->params.num_channels; i++)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	mlx5e_destroy_direct_rqts(priv);
 	return err;
 }
 
 static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 {
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
-	int i;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 
 	mlx5e_tc_cleanup(priv);
 	mlx5_del_flow_rules(rep->vport_rx_rule);
 	mlx5e_destroy_direct_tirs(priv);
-	for (i = 0; i < priv->params.num_channels; i++)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	mlx5e_destroy_direct_rqts(priv);
 }
 
 static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
@@ -548,56 +911,181 @@ static struct mlx5e_profile mlx5e_rep_profile = {
 	.cleanup_tx		= mlx5e_cleanup_nic_tx,
 	.update_stats           = mlx5e_rep_update_stats,
 	.max_nch		= mlx5e_get_rep_max_num_channels,
+	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
+	.rx_handlers.handle_rx_cqe_mpwqe = NULL /* Not supported */,
 	.max_tc			= 1,
 };
 
-int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,
-			 struct mlx5_eswitch_rep *rep)
+/* e-Switch vport representors */
+
+static int
+mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	int err;
+
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		err = mlx5e_add_sqs_fwd_rules(priv);
+		if (err)
+			return err;
+	}
+
+	err = mlx5e_rep_neigh_init(rpriv);
+	if (err)
+		goto err_remove_sqs;
+
+	return 0;
+
+err_remove_sqs:
+	mlx5e_remove_sqs_fwd_rules(priv);
+	return err;
+}
+
+static void
+mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 {
+	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_remove_sqs_fwd_rules(priv);
+
+	/* clean (and re-init) existing uplink offloaded TC rules */
+	mlx5e_tc_cleanup(priv);
+	mlx5e_tc_init(priv);
+
+	mlx5e_rep_neigh_cleanup(rpriv);
+}
+
+static int
+mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_rep_priv *rpriv;
 	struct net_device *netdev;
 	int err;
 
-	netdev = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rep);
+	rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
+	if (!rpriv)
+		return -ENOMEM;
+
+	netdev = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rpriv);
 	if (!netdev) {
 		pr_warn("Failed to create representor netdev for vport %d\n",
 			rep->vport);
+		kfree(rpriv);
 		return -EINVAL;
 	}
 
 	rep->netdev = netdev;
+	rpriv->rep = rep;
 
-	err = mlx5e_attach_netdev(esw->dev, netdev);
+	err = mlx5e_attach_netdev(netdev_priv(netdev));
 	if (err) {
 		pr_warn("Failed to attach representor netdev for vport %d\n",
 			rep->vport);
 		goto err_destroy_netdev;
 	}
 
+	err = mlx5e_rep_neigh_init(rpriv);
+	if (err) {
+		pr_warn("Failed to initialized neighbours handling for vport %d\n",
+			rep->vport);
+		goto err_detach_netdev;
+	}
+
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
 			rep->vport);
-		goto err_detach_netdev;
+		goto err_neigh_cleanup;
 	}
 
 	return 0;
 
+err_neigh_cleanup:
+	mlx5e_rep_neigh_cleanup(rpriv);
+
 err_detach_netdev:
-	mlx5e_detach_netdev(esw->dev, netdev);
+	mlx5e_detach_netdev(netdev_priv(netdev));
 
 err_destroy_netdev:
-	mlx5e_destroy_netdev(esw->dev, netdev_priv(netdev));
-
+	mlx5e_destroy_netdev(netdev_priv(netdev));
+	kfree(rpriv);
 	return err;
 
 }
 
-void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw,
-			    struct mlx5_eswitch_rep *rep)
+static void
+mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 {
 	struct net_device *netdev = rep->netdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	void *ppriv = priv->ppriv;
+
+	unregister_netdev(rep->netdev);
+
+	mlx5e_rep_neigh_cleanup(rpriv);
+	mlx5e_detach_netdev(priv);
+	mlx5e_destroy_netdev(priv);
+	kfree(ppriv); /* mlx5e_rep_priv */
+}
+
+static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	int vport;
+	u8 mac[ETH_ALEN];
+
+	mlx5_query_nic_vport_mac_address(mdev, 0, mac);
+
+	for (vport = 1; vport < total_vfs; vport++) {
+		struct mlx5_eswitch_rep rep;
+
+		rep.load = mlx5e_vport_rep_load;
+		rep.unload = mlx5e_vport_rep_unload;
+		rep.vport = vport;
+		ether_addr_copy(rep.hw_id, mac);
+		mlx5_eswitch_register_vport_rep(esw, vport, &rep);
+	}
+}
+
+static void mlx5e_rep_unregister_vf_vports(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	int vport;
+
+	for (vport = 1; vport < total_vfs; vport++)
+		mlx5_eswitch_unregister_vport_rep(esw, vport);
+}
+
+void mlx5e_register_vport_reps(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
+	struct mlx5_eswitch_rep rep;
+
+	mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
+	rep.load = mlx5e_nic_rep_load;
+	rep.unload = mlx5e_nic_rep_unload;
+	rep.vport = FDB_UPLINK_VPORT;
+	rep.netdev = priv->netdev;
+	mlx5_eswitch_register_vport_rep(esw, 0, &rep); /* UPLINK PF vport*/
+
+	mlx5e_rep_register_vf_vports(priv); /* VFs vports */
+}
+
+void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
 
-	unregister_netdev(netdev);
-	mlx5e_detach_netdev(esw->dev, netdev);
-	mlx5e_destroy_netdev(esw->dev, netdev_priv(netdev));
+	mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
+	mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
new file mode 100644
index 000000000000..a0a1a7a1d6c0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -0,0 +1,145 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __MLX5E_REP_H__
+#define __MLX5E_REP_H__
+
+#include <net/ip_tunnels.h>
+#include <linux/rhashtable.h>
+#include "eswitch.h"
+#include "en.h"
+
+struct mlx5e_neigh_update_table {
+	struct rhashtable       neigh_ht;
+	/* Save the neigh hash entries in a list in addition to the hash table
+	 * (neigh_ht). In order to iterate easily over the neigh entries.
+	 * Used for stats query.
+	 */
+	struct list_head	neigh_list;
+	/* protect lookup/remove operations */
+	spinlock_t              encap_lock;
+	struct notifier_block   netevent_nb;
+	struct delayed_work     neigh_stats_work;
+	unsigned long           min_interval; /* jiffies */
+};
+
+struct mlx5e_rep_priv {
+	struct mlx5_eswitch_rep *rep;
+	struct mlx5e_neigh_update_table neigh_update;
+};
+
+struct mlx5e_neigh {
+	struct net_device *dev;
+	union {
+		__be32	v4;
+		struct in6_addr v6;
+	} dst_ip;
+	int family;
+};
+
+struct mlx5e_neigh_hash_entry {
+	struct rhash_head rhash_node;
+	struct mlx5e_neigh m_neigh;
+
+	/* Save the neigh hash entry in a list on the representor in
+	 * addition to the hash table. In order to iterate easily over the
+	 * neighbour entries. Used for stats query.
+	 */
+	struct list_head neigh_list;
+
+	/* encap list sharing the same neigh */
+	struct list_head encap_list;
+
+	/* valid only when the neigh reference is taken during
+	 * neigh_update_work workqueue callback.
+	 */
+	struct neighbour *n;
+	struct work_struct neigh_update_work;
+
+	/* neigh hash entry can be deleted only when the refcount is zero.
+	 * refcount is needed to avoid neigh hash entry removal by TC, while
+	 * it's used by the neigh notification call.
+	 */
+	refcount_t refcnt;
+
+	/* Save the last reported time offloaded trafic pass over one of the
+	 * neigh hash entry flows. Use it to periodically update the neigh
+	 * 'used' value and avoid neigh deleting by the kernel.
+	 */
+	unsigned long reported_lastuse;
+};
+
+enum {
+	/* set when the encap entry is successfully offloaded into HW */
+	MLX5_ENCAP_ENTRY_VALID     = BIT(0),
+};
+
+struct mlx5e_encap_entry {
+	/* neigh hash entry list of encaps sharing the same neigh */
+	struct list_head encap_list;
+	struct mlx5e_neigh m_neigh;
+	/* a node of the eswitch encap hash table which keeping all the encap
+	 * entries
+	 */
+	struct hlist_node encap_hlist;
+	struct list_head flows;
+	u32 encap_id;
+	struct ip_tunnel_info tun_info;
+	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
+
+	struct net_device *out_dev;
+	int tunnel_type;
+	u8 flags;
+	char *encap_header;
+	int encap_size;
+};
+
+void mlx5e_register_vport_reps(struct mlx5e_priv *priv);
+void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv);
+bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
+int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
+void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
+
+int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, void *sp);
+bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id);
+
+int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
+void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
+
+int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e);
+void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
+				  struct mlx5e_encap_entry *e);
+
+void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
+
+#endif /* __MLX5E_REP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 3d371688fbbb..7b1566f0ae58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -39,6 +39,8 @@
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
+#include "en_rep.h"
+#include "ipoib.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
 {
@@ -156,28 +158,6 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 	return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
 }
 
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val)
-{
-	bool was_opened;
-
-	if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
-		return;
-
-	if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) == val)
-		return;
-
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(priv->netdev);
-
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val);
-	mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
-
-	if (was_opened)
-		mlx5e_open_locked(priv->netdev);
-
-}
-
 #define RQ_PAGE_SIZE(rq) ((1 << rq->buff.page_order) << PAGE_SHIFT)
 
 static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
@@ -331,7 +311,7 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-	struct mlx5e_sq *sq = &rq->channel->icosq;
+	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *wqe;
 	u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
@@ -341,7 +321,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 	while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
 		sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
 		sq->db.ico_wqe[pi].num_wqebbs = 1;
-		mlx5e_send_nop(sq, false);
+		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
 
 	wqe = mlx5_wq_cyc_get_wqe(wq, pi);
@@ -353,7 +333,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs;
 	sq->pc += num_wqebbs;
-	mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
 }
 
 static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
@@ -601,6 +581,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		/* Subtract one since we already counted this as one
+		 * "regular" packet in mlx5e_complete_rx_cqe()
+		 */
+		rq->stats.packets += lro_num_seg - 1;
 		rq->stats.lro_packets++;
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
@@ -633,37 +617,36 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
 }
 
-static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_sq *sq)
+static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_tx_wqe *wqe;
-	u16 pi = (sq->pc - MLX5E_XDP_TX_WQEBBS) & wq->sz_m1; /* last pi */
+	u16 pi = (sq->pc - 1) & wq->sz_m1; /* last pi */
 
 	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
 
-	wqe->ctrl.fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-	mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
 }
 
 static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
 					struct mlx5e_dma_info *di,
 					const struct xdp_buff *xdp)
 {
-	struct mlx5e_sq          *sq   = &rq->channel->xdp_sq;
+	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
-	u16                      pi    = sq->pc & wq->sz_m1;
+	u16                       pi   = sq->pc & wq->sz_m1;
 	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-	struct mlx5e_sq_wqe_info *wi   = &sq->db.xdp.wqe_info[pi];
 
 	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
 	struct mlx5_wqe_data_seg *dseg;
-	u8 ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 
 	ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
 	dma_addr_t dma_addr  = di->addr + data_offset;
 	unsigned int dma_len = xdp->data_end - xdp->data;
 
+	prefetchw(wqe);
+
 	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE ||
 		     MLX5E_SW2HW_MTU(rq->netdev->mtu) < dma_len)) {
 		rq->stats.xdp_drop++;
@@ -671,48 +654,42 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
 		return false;
 	}
 
-	if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_XDP_TX_WQEBBS))) {
-		if (sq->db.xdp.doorbell) {
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
+		if (sq->db.doorbell) {
 			/* SQ is full, ring doorbell */
 			mlx5e_xmit_xdp_doorbell(sq);
-			sq->db.xdp.doorbell = false;
+			sq->db.doorbell = false;
 		}
 		rq->stats.xdp_tx_full++;
 		mlx5e_page_release(rq, di, true);
 		return false;
 	}
 
-	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len,
-				   PCI_DMA_TODEVICE);
+	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
 
-	memset(wqe, 0, sizeof(*wqe));
+	cseg->fm_ce_se = 0;
 
 	dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
+
 	/* copy the inline part if required */
 	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
 		memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
 		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
 		dma_len  -= MLX5E_XDP_MIN_INLINE;
 		dma_addr += MLX5E_XDP_MIN_INLINE;
-
-		ds_cnt   += MLX5E_XDP_IHS_DS_COUNT;
 		dseg++;
 	}
 
 	/* write the dma part */
 	dseg->addr       = cpu_to_be64(dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
-	dseg->lkey       = sq->mkey_be;
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
-	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-	sq->db.xdp.di[pi] = *di;
-	wi->opcode     = MLX5_OPCODE_SEND;
-	wi->num_wqebbs = MLX5E_XDP_TX_WQEBBS;
-	sq->pc += MLX5E_XDP_TX_WQEBBS;
+	sq->db.di[pi] = *di;
+	sq->pc++;
 
-	sq->db.xdp.doorbell = true;
+	sq->db.doorbell = true;
 	rq->stats.xdp_tx++;
 	return true;
 }
@@ -833,7 +810,8 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	struct net_device *netdev = rq->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv  = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5e_rx_wqe *wqe;
 	struct sk_buff *skb;
 	__be16 wqe_counter_be;
@@ -928,7 +906,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto mpwrq_cqe_out;
 	}
 
-	prefetch(skb->data);
+	prefetchw(skb->data);
 	cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
 
 	mlx5e_mpwqe_fill_rx_skb(rq, cqe, wi, cqe_bcnt, skb);
@@ -946,7 +924,7 @@ mpwrq_cqe_out:
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
-	struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq;
+	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
 	int work_done = 0;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
@@ -973,9 +951,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		rq->handle_rx_cqe(rq, cqe);
 	}
 
-	if (xdp_sq->db.xdp.doorbell) {
-		mlx5e_xmit_xdp_doorbell(xdp_sq);
-		xdp_sq->db.xdp.doorbell = false;
+	if (xdpsq->db.doorbell) {
+		mlx5e_xmit_xdp_doorbell(xdpsq);
+		xdpsq->db.doorbell = false;
 	}
 
 	mlx5_cqwq_update_db_record(&cq->wq);
@@ -985,3 +963,152 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 
 	return work_done;
 }
+
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+{
+	struct mlx5e_xdpsq *sq;
+	struct mlx5e_rq *rq;
+	u16 sqcc;
+	int i;
+
+	sq = container_of(cq, struct mlx5e_xdpsq, cq);
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return false;
+
+	rq = container_of(sq, struct mlx5e_rq, xdpsq);
+
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
+		struct mlx5_cqe64 *cqe;
+		u16 wqe_counter;
+		bool last_wqe;
+
+		cqe = mlx5e_get_cqe(cq);
+		if (!cqe)
+			break;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		do {
+			struct mlx5e_dma_info *di;
+			u16 ci;
+
+			last_wqe = (sqcc == wqe_counter);
+
+			ci = sqcc & sq->wq.sz_m1;
+			di = &sq->db.di[ci];
+
+			sqcc++;
+			/* Recycle RX page */
+			mlx5e_page_release(rq, di, true);
+		} while (!last_wqe);
+	}
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	sq->cc = sqcc;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
+}
+
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
+	struct mlx5e_dma_info *di;
+	u16 ci;
+
+	while (sq->cc != sq->pc) {
+		ci = sq->cc & sq->wq.sz_m1;
+		di = &sq->db.di[ci];
+		sq->cc++;
+
+		mlx5e_page_release(rq, di, false);
+	}
+}
+
+#ifdef CONFIG_MLX5_CORE_IPOIB
+
+#define MLX5_IB_GRH_DGID_OFFSET 24
+#define MLX5_IB_GRH_BYTES       40
+#define MLX5_IPOIB_ENCAP_LEN    4
+#define MLX5_GID_SIZE           16
+
+static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
+					 struct mlx5_cqe64 *cqe,
+					 u32 cqe_bcnt,
+					 struct sk_buff *skb)
+{
+	struct net_device *netdev = rq->netdev;
+	u8 *dgid;
+	u8 g;
+
+	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
+	dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET;
+	if ((!g) || dgid[0] != 0xff)
+		skb->pkt_type = PACKET_HOST;
+	else if (memcmp(dgid, netdev->broadcast + 4, MLX5_GID_SIZE) == 0)
+		skb->pkt_type = PACKET_BROADCAST;
+	else
+		skb->pkt_type = PACKET_MULTICAST;
+
+	/* TODO: IB/ipoib: Allow mcast packets from other VFs
+	 * 68996a6e760e5c74654723eeb57bf65628ae87f4
+	 */
+
+	skb_pull(skb, MLX5_IB_GRH_BYTES);
+
+	skb->protocol = *((__be16 *)(skb->data));
+
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+
+	skb_record_rx_queue(skb, rq->ix);
+
+	if (likely(netdev->features & NETIF_F_RXHASH))
+		mlx5e_skb_set_hash(cqe, skb);
+
+	skb_reset_mac_header(skb);
+	skb_pull(skb, MLX5_IPOIB_ENCAP_LEN);
+
+	skb->dev = netdev;
+
+	rq->stats.csum_complete++;
+	rq->stats.packets++;
+	rq->stats.bytes += cqe_bcnt;
+}
+
+void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	struct mlx5e_rx_wqe *wqe;
+	__be16 wqe_counter_be;
+	struct sk_buff *skb;
+	u16 wqe_counter;
+	u32 cqe_bcnt;
+
+	wqe_counter_be = cqe->wqe_counter;
+	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
+
+	skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
+	if (!skb)
+		goto wq_ll_pop;
+
+	mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	napi_gro_receive(rq->cq.napi, skb);
+
+wq_ll_pop:
+	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+		       &wqe->next.next_wqe_index);
+}
+
+#endif /* CONFIG_MLX5_CORE_IPOIB */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index cbfac06b7ffd..02dd3a95ed8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -293,7 +293,7 @@ void mlx5e_rx_am_work(struct work_struct *work)
 	struct mlx5e_rq *rq = container_of(am, struct mlx5e_rq, am);
 	struct mlx5e_cq_moder cur_profile = profile[am->mode][am->profile_ix];
 
-	mlx5_core_modify_cq_moderation(rq->priv->mdev, &rq->cq.mcq,
+	mlx5_core_modify_cq_moderation(rq->mdev, &rq->cq.mcq,
 				       cur_profile.usec, cur_profile.pkts);
 
 	am->state = MLX5E_AM_START_MEASURE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 31e3cb7ee5fe..5225f2226a67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -204,9 +204,6 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	struct iphdr *iph;
 
 	/* We are only going to peek, no need to clone the SKB */
-	if (skb->protocol != htons(ETH_P_IP))
-		goto out;
-
 	if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
 		goto out;
 
@@ -239,17 +236,14 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 {
 	int err = 0;
 
-	err = mlx5e_refresh_tirs_self_loopback(priv->mdev, true);
-	if (err) {
-		netdev_err(priv->netdev,
-			   "\tFailed to enable UC loopback err(%d)\n", err);
+	err = mlx5e_refresh_tirs(priv, true);
+	if (err)
 		return err;
-	}
 
 	lbtp->loopback_ok = false;
 	init_completion(&lbtp->comp);
 
-	lbtp->pt.type = htons(ETH_P_ALL);
+	lbtp->pt.type = htons(ETH_P_IP);
 	lbtp->pt.func = mlx5e_test_loopback_validate;
 	lbtp->pt.dev = priv->netdev;
 	lbtp->pt.af_packet_priv = lbtp;
@@ -261,7 +255,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 					struct mlx5e_lbt_priv *lbtp)
 {
 	dev_remove_pack(&lbtp->pt);
-	mlx5e_refresh_tirs_self_loopback(priv->mdev, false);
+	mlx5e_refresh_tirs(priv, false);
 }
 
 #define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 44406a5ec15d..11c27e4fadf6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -42,18 +42,43 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
+#include <net/tc_act/tc_pedit.h>
 #include <net/vxlan.h>
+#include <net/arp.h>
 #include "en.h"
+#include "en_rep.h"
 #include "en_tc.h"
 #include "eswitch.h"
 #include "vxlan.h"
 
+struct mlx5_nic_flow_attr {
+	u32 action;
+	u32 flow_tag;
+	u32 mod_hdr_id;
+};
+
+enum {
+	MLX5E_TC_FLOW_ESWITCH	= BIT(0),
+	MLX5E_TC_FLOW_NIC	= BIT(1),
+	MLX5E_TC_FLOW_OFFLOADED	= BIT(2),
+};
+
 struct mlx5e_tc_flow {
 	struct rhash_head	node;
 	u64			cookie;
+	u8			flags;
 	struct mlx5_flow_handle *rule;
 	struct list_head	encap; /* flows sharing the same encap */
-	struct mlx5_esw_flow_attr *attr;
+	union {
+		struct mlx5_esw_flow_attr esw_attr[0];
+		struct mlx5_nic_flow_attr nic_attr[0];
+	};
+};
+
+struct mlx5e_tc_flow_parse_attr {
+	struct mlx5_flow_spec spec;
+	int num_mod_hdr_actions;
+	void *mod_hdr_actions;
 };
 
 enum {
@@ -66,24 +91,26 @@ enum {
 
 static struct mlx5_flow_handle *
 mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
-		      struct mlx5_flow_spec *spec,
-		      u32 action, u32 flow_tag)
+		      struct mlx5e_tc_flow_parse_attr *parse_attr,
+		      struct mlx5e_tc_flow *flow)
 {
+	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	struct mlx5_core_dev *dev = priv->mdev;
-	struct mlx5_flow_destination dest = { 0 };
+	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {
-		.action = action,
-		.flow_tag = flow_tag,
+		.action = attr->action,
+		.flow_tag = attr->flow_tag,
 		.encap_id = 0,
 	};
 	struct mlx5_fc *counter = NULL;
 	struct mlx5_flow_handle *rule;
 	bool table_created = false;
+	int err;
 
-	if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 		dest.ft = priv->fs.vlan.ft.t;
-	} else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+	} else if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		counter = mlx5_fc_create(dev, true);
 		if (IS_ERR(counter))
 			return ERR_CAST(counter);
@@ -92,6 +119,19 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		dest.counter = counter;
 	}
 
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+		err = mlx5_modify_header_alloc(dev, MLX5_FLOW_NAMESPACE_KERNEL,
+					       parse_attr->num_mod_hdr_actions,
+					       parse_attr->mod_hdr_actions,
+					       &attr->mod_hdr_id);
+		flow_act.modify_id = attr->mod_hdr_id;
+		kfree(parse_attr->mod_hdr_actions);
+		if (err) {
+			rule = ERR_PTR(err);
+			goto err_create_mod_hdr_id;
+		}
+	}
+
 	if (IS_ERR_OR_NULL(priv->fs.tc.t)) {
 		priv->fs.tc.t =
 			mlx5_create_auto_grouped_flow_table(priv->fs.ns,
@@ -109,8 +149,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		table_created = true;
 	}
 
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	rule = mlx5_add_flow_rules(priv->fs.tc.t, spec, &flow_act, &dest, 1);
+	parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	rule = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
+				   &flow_act, &dest, 1);
 
 	if (IS_ERR(rule))
 		goto err_add_rule;
@@ -123,70 +164,239 @@ err_add_rule:
 		priv->fs.tc.t = NULL;
 	}
 err_create_ft:
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   attr->mod_hdr_id);
+err_create_mod_hdr_id:
 	mlx5_fc_destroy(dev, counter);
 
 	return rule;
 }
 
+static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
+				  struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_fc *counter = NULL;
+
+	counter = mlx5_flow_rule_counter(flow->rule);
+	mlx5_del_flow_rules(flow->rule);
+	mlx5_fc_destroy(priv->mdev, counter);
+
+	if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
+		mlx5_destroy_flow_table(priv->fs.tc.t);
+		priv->fs.tc.t = NULL;
+	}
+
+	if (flow->nic_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   flow->nic_attr->mod_hdr_id);
+}
+
+static void mlx5e_detach_encap(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow);
+
 static struct mlx5_flow_handle *
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
-		      struct mlx5_flow_spec *spec,
-		      struct mlx5_esw_flow_attr *attr)
+		      struct mlx5e_tc_flow_parse_attr *parse_attr,
+		      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5_flow_handle *rule;
 	int err;
 
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
-	if (err)
-		return ERR_PTR(err);
+	if (err) {
+		rule = ERR_PTR(err);
+		goto err_add_vlan;
+	}
+
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+		err = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_FDB,
+					       parse_attr->num_mod_hdr_actions,
+					       parse_attr->mod_hdr_actions,
+					       &attr->mod_hdr_id);
+		kfree(parse_attr->mod_hdr_actions);
+		if (err) {
+			rule = ERR_PTR(err);
+			goto err_mod_hdr;
+		}
+	}
+
+	rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
+	if (IS_ERR(rule))
+		goto err_add_rule;
 
-	return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
+	return rule;
+
+err_add_rule:
+	if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   attr->mod_hdr_id);
+err_mod_hdr:
+	mlx5_eswitch_del_vlan_action(esw, attr);
+err_add_vlan:
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+		mlx5e_detach_encap(priv, flow);
+	return rule;
+}
+
+static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
+				  struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+
+	if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
+		flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED;
+		mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr);
+	}
+
+	mlx5_eswitch_del_vlan_action(esw, flow->esw_attr);
+
+	if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) {
+		mlx5e_detach_encap(priv, flow);
+		kvfree(flow->esw_attr->parse_attr);
+	}
+
+	if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   attr->mod_hdr_id);
+}
+
+void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
+			      struct mlx5e_encap_entry *e)
+{
+	struct mlx5e_tc_flow *flow;
+	int err;
+
+	err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
+			       e->encap_size, e->encap_header,
+			       &e->encap_id);
+	if (err) {
+		mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n",
+			       err);
+		return;
+	}
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(priv);
+
+	list_for_each_entry(flow, &e->flows, encap) {
+		flow->esw_attr->encap_id = e->encap_id;
+		flow->rule = mlx5e_tc_add_fdb_flow(priv,
+						   flow->esw_attr->parse_attr,
+						   flow);
+		if (IS_ERR(flow->rule)) {
+			err = PTR_ERR(flow->rule);
+			mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n",
+				       err);
+			continue;
+		}
+		flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
+	}
+}
+
+void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
+			      struct mlx5e_encap_entry *e)
+{
+	struct mlx5e_tc_flow *flow;
+	struct mlx5_fc *counter;
+
+	list_for_each_entry(flow, &e->flows, encap) {
+		if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
+			flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED;
+			counter = mlx5_flow_rule_counter(flow->rule);
+			mlx5_del_flow_rules(flow->rule);
+			mlx5_fc_destroy(priv->mdev, counter);
+		}
+	}
+
+	if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
+		e->flags &= ~MLX5_ENCAP_ENTRY_VALID;
+		mlx5_encap_dealloc(priv->mdev, e->encap_id);
+	}
+}
+
+void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
+	u64 bytes, packets, lastuse = 0;
+	struct mlx5e_tc_flow *flow;
+	struct mlx5e_encap_entry *e;
+	struct mlx5_fc *counter;
+	struct neigh_table *tbl;
+	bool neigh_used = false;
+	struct neighbour *n;
+
+	if (m_neigh->family == AF_INET)
+		tbl = &arp_tbl;
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (m_neigh->family == AF_INET6)
+		tbl = ipv6_stub->nd_tbl;
+#endif
+	else
+		return;
+
+	list_for_each_entry(e, &nhe->encap_list, encap_list) {
+		if (!(e->flags & MLX5_ENCAP_ENTRY_VALID))
+			continue;
+		list_for_each_entry(flow, &e->flows, encap) {
+			if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
+				counter = mlx5_flow_rule_counter(flow->rule);
+				mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+				if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) {
+					neigh_used = true;
+					break;
+				}
+			}
+		}
+	}
+
+	if (neigh_used) {
+		nhe->reported_lastuse = jiffies;
+
+		/* find the relevant neigh according to the cached device and
+		 * dst ip pair
+		 */
+		n = neigh_lookup(tbl, &m_neigh->dst_ip, m_neigh->dev);
+		if (!n) {
+			WARN(1, "The neighbour already freed\n");
+			return;
+		}
+
+		neigh_event_send(n, NULL);
+		neigh_release(n);
+	}
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow) {
+			       struct mlx5e_tc_flow *flow)
+{
 	struct list_head *next = flow->encap.next;
 
 	list_del(&flow->encap);
 	if (list_empty(next)) {
-		struct mlx5_encap_entry *e;
+		struct mlx5e_encap_entry *e;
+
+		e = list_entry(next, struct mlx5e_encap_entry, flows);
+		mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 
-		e = list_entry(next, struct mlx5_encap_entry, flows);
-		if (e->n) {
+		if (e->flags & MLX5_ENCAP_ENTRY_VALID)
 			mlx5_encap_dealloc(priv->mdev, e->encap_id);
-			neigh_release(e->n);
-		}
+
 		hlist_del_rcu(&e->encap_hlist);
+		kfree(e->encap_header);
 		kfree(e);
 	}
 }
 
-/* we get here also when setting rule to the FW failed, etc. It means that the
- * flow rule itself might not exist, but some offloading related to the actions
- * should be cleaned.
- */
 static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_fc *counter = NULL;
-
-	if (!IS_ERR(flow->rule)) {
-		counter = mlx5_flow_rule_counter(flow->rule);
-		mlx5_del_flow_rules(flow->rule);
-		mlx5_fc_destroy(priv->mdev, counter);
-	}
-
-	if (esw && esw->mode == SRIOV_OFFLOADS) {
-		mlx5_eswitch_del_vlan_action(esw, flow->attr);
-		if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
-			mlx5e_detach_encap(priv, flow);
-	}
-
-	if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
-		mlx5_destroy_flow_table(priv->fs.tc.t);
-		priv->fs.tc.t = NULL;
-	}
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+		mlx5e_tc_del_fdb_flow(priv, flow);
+	else
+		mlx5e_tc_del_nic_flow(priv, flow);
 }
 
 static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
@@ -243,12 +453,15 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_PORTS,
 						  f->mask);
+		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+		struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw);
+		struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 
 		/* Full udp dst port must be given */
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) &&
+		if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -598,20 +811,24 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 }
 
 static int parse_cls_flower(struct mlx5e_priv *priv,
+			    struct mlx5e_tc_flow *flow,
 			    struct mlx5_flow_spec *spec,
 			    struct tc_cls_flower_offload *f)
 {
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
-	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep;
 	u8 min_inline;
 	int err;
 
 	err = __parse_cls_flower(priv, spec, f, &min_inline);
 
-	if (!err && esw->mode == SRIOV_OFFLOADS &&
-	    rep->vport != FDB_UPLINK_VPORT) {
-		if (min_inline > esw->offloads.inline_mode) {
+	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
+		rep = rpriv->rep;
+		if (rep->vport != FDB_UPLINK_VPORT &&
+		    (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
+		    esw->offloads.inline_mode < min_inline)) {
 			netdev_warn(priv->netdev,
 				    "Flow is not offloaded due to min inline setting, required %d actual %d\n",
 				    min_inline, esw->offloads.inline_mode);
@@ -622,29 +839,313 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 	return err;
 }
 
+struct pedit_headers {
+	struct ethhdr  eth;
+	struct iphdr   ip4;
+	struct ipv6hdr ip6;
+	struct tcphdr  tcp;
+	struct udphdr  udp;
+};
+
+static int pedit_header_offsets[] = {
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
+};
+
+#define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype])
+
+static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset,
+			 struct pedit_headers *masks,
+			 struct pedit_headers *vals)
+{
+	u32 *curr_pmask, *curr_pval;
+
+	if (hdr_type >= __PEDIT_HDR_TYPE_MAX)
+		goto out_err;
+
+	curr_pmask = (u32 *)(pedit_header(masks, hdr_type) + offset);
+	curr_pval  = (u32 *)(pedit_header(vals, hdr_type) + offset);
+
+	if (*curr_pmask & mask)  /* disallow acting twice on the same location */
+		goto out_err;
+
+	*curr_pmask |= mask;
+	*curr_pval  |= (val & mask);
+
+	return 0;
+
+out_err:
+	return -EOPNOTSUPP;
+}
+
+struct mlx5_fields {
+	u8  field;
+	u8  size;
+	u32 offset;
+};
+
+static struct mlx5_fields fields[] = {
+	{MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16, 4, offsetof(struct pedit_headers, eth.h_dest[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0,  2, offsetof(struct pedit_headers, eth.h_dest[4])},
+	{MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16, 4, offsetof(struct pedit_headers, eth.h_source[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0,  2, offsetof(struct pedit_headers, eth.h_source[4])},
+	{MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE,  2, offsetof(struct pedit_headers, eth.h_proto)},
+
+	{MLX5_ACTION_IN_FIELD_OUT_IP_DSCP, 1, offsetof(struct pedit_headers, ip4.tos)},
+	{MLX5_ACTION_IN_FIELD_OUT_IP_TTL,  1, offsetof(struct pedit_headers, ip4.ttl)},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV4,   4, offsetof(struct pedit_headers, ip4.saddr)},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV4,   4, offsetof(struct pedit_headers, ip4.daddr)},
+
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96, 4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64,  4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[1])},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32,  4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[2])},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0,   4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[3])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96, 4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64,  4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[1])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32,  4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[2])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0,   4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[3])},
+
+	{MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT, 2, offsetof(struct pedit_headers, tcp.source)},
+	{MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT, 2, offsetof(struct pedit_headers, tcp.dest)},
+	{MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS, 1, offsetof(struct pedit_headers, tcp.ack_seq) + 5},
+
+	{MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT, 2, offsetof(struct pedit_headers, udp.source)},
+	{MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT, 2, offsetof(struct pedit_headers, udp.dest)},
+};
+
+/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, it says how many HW actions were
+ * actually parsed.
+ */
+static int offload_pedit_fields(struct pedit_headers *masks,
+				struct pedit_headers *vals,
+				struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+	int i, action_size, nactions, max_actions, first, last;
+	void *s_masks_p, *a_masks_p, *vals_p;
+	u32 s_mask, a_mask, val;
+	struct mlx5_fields *f;
+	u8 cmd, field_bsize;
+	unsigned long mask;
+	void *action;
+
+	set_masks = &masks[TCA_PEDIT_KEY_EX_CMD_SET];
+	add_masks = &masks[TCA_PEDIT_KEY_EX_CMD_ADD];
+	set_vals = &vals[TCA_PEDIT_KEY_EX_CMD_SET];
+	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
+
+	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+	action = parse_attr->mod_hdr_actions;
+	max_actions = parse_attr->num_mod_hdr_actions;
+	nactions = 0;
+
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		f = &fields[i];
+		/* avoid seeing bits set from previous iterations */
+		s_mask = a_mask = mask = val = 0;
+
+		s_masks_p = (void *)set_masks + f->offset;
+		a_masks_p = (void *)add_masks + f->offset;
+
+		memcpy(&s_mask, s_masks_p, f->size);
+		memcpy(&a_mask, a_masks_p, f->size);
+
+		if (!s_mask && !a_mask) /* nothing to offload here */
+			continue;
+
+		if (s_mask && a_mask) {
+			printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field);
+			return -EOPNOTSUPP;
+		}
+
+		if (nactions == max_actions) {
+			printk(KERN_WARNING "mlx5: parsed %d pedit actions, can't do more\n", nactions);
+			return -EOPNOTSUPP;
+		}
+
+		if (s_mask) {
+			cmd  = MLX5_ACTION_TYPE_SET;
+			mask = s_mask;
+			vals_p = (void *)set_vals + f->offset;
+			/* clear to denote we consumed this field */
+			memset(s_masks_p, 0, f->size);
+		} else {
+			cmd  = MLX5_ACTION_TYPE_ADD;
+			mask = a_mask;
+			vals_p = (void *)add_vals + f->offset;
+			/* clear to denote we consumed this field */
+			memset(a_masks_p, 0, f->size);
+		}
+
+		memcpy(&val, vals_p, f->size);
+
+		field_bsize = f->size * BITS_PER_BYTE;
+		first = find_first_bit(&mask, field_bsize);
+		last  = find_last_bit(&mask, field_bsize);
+		if (first > 0 || last != (field_bsize - 1)) {
+			printk(KERN_WARNING "mlx5: partial rewrite (mask %lx) is currently not offloaded\n",
+			       mask);
+			return -EOPNOTSUPP;
+		}
+
+		MLX5_SET(set_action_in, action, action_type, cmd);
+		MLX5_SET(set_action_in, action, field, f->field);
+
+		if (cmd == MLX5_ACTION_TYPE_SET) {
+			MLX5_SET(set_action_in, action, offset, 0);
+			/* length is num of bits to be written, zero means length of 32 */
+			MLX5_SET(set_action_in, action, length, field_bsize);
+		}
+
+		if (field_bsize == 32)
+			MLX5_SET(set_action_in, action, data, ntohl(val));
+		else if (field_bsize == 16)
+			MLX5_SET(set_action_in, action, data, ntohs(val));
+		else if (field_bsize == 8)
+			MLX5_SET(set_action_in, action, data, val);
+
+		action += action_size;
+		nactions++;
+	}
+
+	parse_attr->num_mod_hdr_actions = nactions;
+	return 0;
+}
+
+static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
+				 const struct tc_action *a, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+	int nkeys, action_size, max_actions;
+
+	nkeys = tcf_pedit_nkeys(a);
+	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+
+	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
+		max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, max_modify_header_actions);
+	else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
+		max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, max_modify_header_actions);
+
+	/* can get up to crazingly 16 HW actions in 32 bits pedit SW key */
+	max_actions = min(max_actions, nkeys * 16);
+
+	parse_attr->mod_hdr_actions = kcalloc(max_actions, action_size, GFP_KERNEL);
+	if (!parse_attr->mod_hdr_actions)
+		return -ENOMEM;
+
+	parse_attr->num_mod_hdr_actions = max_actions;
+	return 0;
+}
+
+static const struct pedit_headers zero_masks = {};
+
+static int parse_tc_pedit_action(struct mlx5e_priv *priv,
+				 const struct tc_action *a, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+	struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks;
+	int nkeys, i, err = -EOPNOTSUPP;
+	u32 mask, val, offset;
+	u8 cmd, htype;
+
+	nkeys = tcf_pedit_nkeys(a);
+
+	memset(masks, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+	memset(vals,  0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+
+	for (i = 0; i < nkeys; i++) {
+		htype = tcf_pedit_htype(a, i);
+		cmd = tcf_pedit_cmd(a, i);
+		err = -EOPNOTSUPP; /* can't be all optimistic */
+
+		if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
+			printk(KERN_WARNING "mlx5: legacy pedit isn't offloaded\n");
+			goto out_err;
+		}
+
+		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
+			printk(KERN_WARNING "mlx5: pedit cmd %d isn't offloaded\n", cmd);
+			goto out_err;
+		}
+
+		mask = tcf_pedit_mask(a, i);
+		val = tcf_pedit_val(a, i);
+		offset = tcf_pedit_offset(a, i);
+
+		err = set_pedit_val(htype, ~mask, val, offset, &masks[cmd], &vals[cmd]);
+		if (err)
+			goto out_err;
+	}
+
+	err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+	if (err)
+		goto out_err;
+
+	err = offload_pedit_fields(masks, vals, parse_attr);
+	if (err < 0)
+		goto out_dealloc_parsed_actions;
+
+	for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
+		cmd_masks = &masks[cmd];
+		if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
+			printk(KERN_WARNING "mlx5: attempt to offload an unsupported field (cmd %d)\n",
+			       cmd);
+			print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS,
+				       16, 1, cmd_masks, sizeof(zero_masks), true);
+			err = -EOPNOTSUPP;
+			goto out_dealloc_parsed_actions;
+		}
+	}
+
+	return 0;
+
+out_dealloc_parsed_actions:
+	kfree(parse_attr->mod_hdr_actions);
+out_err:
+	return err;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
-				u32 *action, u32 *flow_tag)
+				struct mlx5e_tc_flow_parse_attr *parse_attr,
+				struct mlx5e_tc_flow *flow)
 {
+	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	const struct tc_action *a;
 	LIST_HEAD(actions);
+	int err;
 
 	if (tc_no_actions(exts))
 		return -EINVAL;
 
-	*flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
-	*action = 0;
+	attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+	attr->action = 0;
 
 	tcf_exts_to_list(exts, &actions);
 	list_for_each_entry(a, &actions, list) {
 		/* Only support a single action per rule */
-		if (*action)
+		if (attr->action)
 			return -EINVAL;
 
 		if (is_tcf_gact_shot(a)) {
-			*action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
 			if (MLX5_CAP_FLOWTABLE(priv->mdev,
 					       flow_table_properties_nic_receive.flow_counter))
-				*action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+				attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+			continue;
+		}
+
+		if (is_tcf_pedit(a)) {
+			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL,
+						    parse_attr);
+			if (err)
+				return err;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
+					MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			continue;
 		}
 
@@ -657,8 +1158,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				return -EINVAL;
 			}
 
-			*flow_tag = mark;
-			*action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+			attr->flow_tag = mark;
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			continue;
 		}
 
@@ -757,16 +1258,15 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int gen_vxlan_header_ipv4(struct net_device *out_dev,
-				 char buf[],
-				 unsigned char h_dest[ETH_ALEN],
-				 int ttl,
-				 __be32 daddr,
-				 __be32 saddr,
-				 __be16 udp_dst_port,
-				 __be32 vx_vni)
+static void gen_vxlan_header_ipv4(struct net_device *out_dev,
+				  char buf[], int encap_size,
+				  unsigned char h_dest[ETH_ALEN],
+				  int ttl,
+				  __be32 daddr,
+				  __be32 saddr,
+				  __be16 udp_dst_port,
+				  __be32 vx_vni)
 {
-	int encap_size = VXLAN_HLEN + sizeof(struct iphdr) + ETH_HLEN;
 	struct ethhdr *eth = (struct ethhdr *)buf;
 	struct iphdr  *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
 	struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr));
@@ -789,20 +1289,17 @@ static int gen_vxlan_header_ipv4(struct net_device *out_dev,
 	udp->dest = udp_dst_port;
 	vxh->vx_flags = VXLAN_HF_VNI;
 	vxh->vx_vni = vxlan_vni_field(vx_vni);
-
-	return encap_size;
 }
 
-static int gen_vxlan_header_ipv6(struct net_device *out_dev,
-				 char buf[],
-				 unsigned char h_dest[ETH_ALEN],
-				 int ttl,
-				 struct in6_addr *daddr,
-				 struct in6_addr *saddr,
-				 __be16 udp_dst_port,
-				 __be32 vx_vni)
+static void gen_vxlan_header_ipv6(struct net_device *out_dev,
+				  char buf[], int encap_size,
+				  unsigned char h_dest[ETH_ALEN],
+				  int ttl,
+				  struct in6_addr *daddr,
+				  struct in6_addr *saddr,
+				  __be16 udp_dst_port,
+				  __be32 vx_vni)
 {
-	int encap_size = VXLAN_HLEN + sizeof(struct ipv6hdr) + ETH_HLEN;
 	struct ethhdr *eth = (struct ethhdr *)buf;
 	struct ipv6hdr *ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
 	struct udphdr *udp = (struct udphdr *)((char *)ip6h + sizeof(struct ipv6hdr));
@@ -824,23 +1321,29 @@ static int gen_vxlan_header_ipv6(struct net_device *out_dev,
 	udp->dest = udp_dst_port;
 	vxh->vx_flags = VXLAN_HF_VNI;
 	vxh->vx_vni = vxlan_vni_field(vx_vni);
-
-	return encap_size;
 }
 
 static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 					  struct net_device *mirred_dev,
-					  struct mlx5_encap_entry *e,
-					  struct net_device **out_dev)
+					  struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	int ipv4_encap_size = ETH_HLEN + sizeof(struct iphdr) + VXLAN_HLEN;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	int encap_size, ttl, err;
+	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
 	char *encap_header;
+	int ttl, err;
+	u8 nud_state;
+
+	if (max_encap_size < ipv4_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv4_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
 
-	encap_header = kzalloc(max_encap_size, GFP_KERNEL);
+	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
 	if (!encap_header)
 		return -ENOMEM;
 
@@ -857,58 +1360,94 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	fl4.daddr = tun_key->u.ipv4.dst;
 	fl4.saddr = tun_key->u.ipv4.src;
 
-	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, out_dev,
+	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
 				      &fl4, &n, &ttl);
 	if (err)
 		goto out;
 
-	if (!(n->nud_state & NUD_VALID)) {
-		pr_warn("%s: can't offload, neighbour to %pI4 invalid\n", __func__, &fl4.daddr);
-		err = -EOPNOTSUPP;
+	/* used by mlx5e_detach_encap to lookup a neigh hash table
+	 * entry in the neigh hash table when a user deletes a rule
+	 */
+	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
+	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+	e->out_dev = out_dev;
+
+	/* It's importent to add the neigh to the hash table before checking
+	 * the neigh validity state. So if we'll get a notification, in case the
+	 * neigh changes it's validity state, we would find the relevant neigh
+	 * in the hash.
+	 */
+	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
+	if (err)
 		goto out;
-	}
-
-	e->n = n;
-	e->out_dev = *out_dev;
 
-	neigh_ha_snapshot(e->h_dest, n, *out_dev);
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(e->h_dest, n->ha);
+	read_unlock_bh(&n->lock);
 
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
-		encap_size = gen_vxlan_header_ipv4(*out_dev, encap_header,
-						   e->h_dest, ttl,
-						   fl4.daddr,
-						   fl4.saddr, tun_key->tp_dst,
-						   tunnel_id_to_key32(tun_key->tun_id));
+		gen_vxlan_header_ipv4(out_dev, encap_header,
+				      ipv4_encap_size, e->h_dest, ttl,
+				      fl4.daddr,
+				      fl4.saddr, tun_key->tp_dst,
+				      tunnel_id_to_key32(tun_key->tun_id));
 		break;
 	default:
 		err = -EOPNOTSUPP;
-		goto out;
+		goto destroy_neigh_entry;
+	}
+	e->encap_size = ipv4_encap_size;
+	e->encap_header = encap_header;
+
+	if (!(nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+		neigh_release(n);
+		return -EAGAIN;
 	}
 
 	err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
-			       encap_size, encap_header, &e->encap_id);
+			       ipv4_encap_size, encap_header, &e->encap_id);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
+	neigh_release(n);
+	return err;
+
+destroy_neigh_entry:
+	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 out:
-	if (err && n)
-		neigh_release(n);
 	kfree(encap_header);
+	if (n)
+		neigh_release(n);
 	return err;
 }
 
 static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 					  struct net_device *mirred_dev,
-					  struct mlx5_encap_entry *e,
-					  struct net_device **out_dev)
-
+					  struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	int ipv6_encap_size = ETH_HLEN + sizeof(struct ipv6hdr) + VXLAN_HLEN;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	int encap_size, err, ttl = 0;
+	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
 	char *encap_header;
+	int err, ttl = 0;
+	u8 nud_state;
+
+	if (max_encap_size < ipv6_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv6_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
 
-	encap_header = kzalloc(max_encap_size, GFP_KERNEL);
+	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
 	if (!encap_header)
 		return -ENOMEM;
 
@@ -926,55 +1465,88 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
 
-	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, out_dev,
+	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
 				      &fl6, &n, &ttl);
 	if (err)
 		goto out;
 
-	if (!(n->nud_state & NUD_VALID)) {
-		pr_warn("%s: can't offload, neighbour to %pI6 invalid\n", __func__, &fl6.daddr);
-		err = -EOPNOTSUPP;
+	/* used by mlx5e_detach_encap to lookup a neigh hash table
+	 * entry in the neigh hash table when a user deletes a rule
+	 */
+	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
+	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+	e->out_dev = out_dev;
+
+	/* It's importent to add the neigh to the hash table before checking
+	 * the neigh validity state. So if we'll get a notification, in case the
+	 * neigh changes it's validity state, we would find the relevant neigh
+	 * in the hash.
+	 */
+	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
+	if (err)
 		goto out;
-	}
-
-	e->n = n;
-	e->out_dev = *out_dev;
 
-	neigh_ha_snapshot(e->h_dest, n, *out_dev);
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(e->h_dest, n->ha);
+	read_unlock_bh(&n->lock);
 
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
-		encap_size = gen_vxlan_header_ipv6(*out_dev, encap_header,
-						   e->h_dest, ttl,
-						   &fl6.daddr,
-						   &fl6.saddr, tun_key->tp_dst,
-						   tunnel_id_to_key32(tun_key->tun_id));
+		gen_vxlan_header_ipv6(out_dev, encap_header,
+				      ipv6_encap_size, e->h_dest, ttl,
+				      &fl6.daddr,
+				      &fl6.saddr, tun_key->tp_dst,
+				      tunnel_id_to_key32(tun_key->tun_id));
 		break;
 	default:
 		err = -EOPNOTSUPP;
-		goto out;
+		goto destroy_neigh_entry;
+	}
+
+	e->encap_size = ipv6_encap_size;
+	e->encap_header = encap_header;
+
+	if (!(nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+		neigh_release(n);
+		return -EAGAIN;
 	}
 
 	err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
-			       encap_size, encap_header, &e->encap_id);
+			       ipv6_encap_size, encap_header, &e->encap_id);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
+	neigh_release(n);
+	return err;
+
+destroy_neigh_entry:
+	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 out:
-	if (err && n)
-		neigh_release(n);
 	kfree(encap_header);
+	if (n)
+		neigh_release(n);
 	return err;
 }
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct ip_tunnel_info *tun_info,
 			      struct net_device *mirred_dev,
-			      struct mlx5_esw_flow_attr *attr)
+			      struct net_device **encap_dev,
+			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw);
 	unsigned short family = ip_tunnel_info_af(tun_info);
+	struct mlx5e_priv *up_priv = netdev_priv(up_dev);
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct ip_tunnel_key *key = &tun_info->key;
-	struct mlx5_encap_entry *e;
-	struct net_device *out_dev;
-	int tunnel_type, err = -EOPNOTSUPP;
+	struct mlx5e_encap_entry *e;
+	int tunnel_type, err = 0;
 	uintptr_t hash_key;
 	bool found = false;
 
@@ -990,7 +1562,7 @@ vxlan_encap_offload_err:
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
@@ -1009,10 +1581,8 @@ vxlan_encap_offload_err:
 		}
 	}
 
-	if (found) {
-		attr->encap = e;
-		return 0;
-	}
+	if (found)
+		goto attach_flow;
 
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
 	if (!e)
@@ -1023,16 +1593,21 @@ vxlan_encap_offload_err:
 	INIT_LIST_HEAD(&e->flows);
 
 	if (family == AF_INET)
-		err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e, &out_dev);
+		err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e);
 	else if (family == AF_INET6)
-		err = mlx5e_create_encap_header_ipv6(priv, mirred_dev, e, &out_dev);
+		err = mlx5e_create_encap_header_ipv6(priv, mirred_dev, e);
 
-	if (err)
+	if (err && err != -EAGAIN)
 		goto out_err;
 
-	attr->encap = e;
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 
+attach_flow:
+	list_add(&flow->encap, &e->flows);
+	*encap_dev = e->out_dev;
+	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
+		attr->encap_id = e->encap_id;
+
 	return err;
 
 out_err:
@@ -1041,20 +1616,22 @@ out_err:
 }
 
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
 {
-	struct mlx5_esw_flow_attr *attr = flow->attr;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct ip_tunnel_info *info = NULL;
 	const struct tc_action *a;
 	LIST_HEAD(actions);
 	bool encap = false;
-	int err;
+	int err = 0;
 
 	if (tc_no_actions(exts))
 		return -EINVAL;
 
 	memset(attr, 0, sizeof(*attr));
-	attr->in_rep = priv->ppriv;
+	attr->in_rep = rpriv->rep;
 
 	tcf_exts_to_list(exts, &actions);
 	list_for_each_entry(a, &actions, list) {
@@ -1064,9 +1641,19 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			continue;
 		}
 
+		if (is_tcf_pedit(a)) {
+			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
+						    parse_attr);
+			if (err)
+				return err;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+			continue;
+		}
+
 		if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
-			struct net_device *out_dev;
+			struct net_device *out_dev, *encap_dev = NULL;
 			struct mlx5e_priv *out_priv;
 
 			out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex);
@@ -1076,18 +1663,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					MLX5_FLOW_CONTEXT_ACTION_COUNT;
 				out_priv = netdev_priv(out_dev);
-				attr->out_rep = out_priv->ppriv;
+				rpriv = out_priv->ppriv;
+				attr->out_rep = rpriv->rep;
 			} else if (encap) {
 				err = mlx5e_attach_encap(priv, info,
-							 out_dev, attr);
-				if (err)
+							 out_dev, &encap_dev, flow);
+				if (err && err != -EAGAIN)
 					return err;
-				list_add(&flow->encap, &attr->encap->flows);
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
 					MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					MLX5_FLOW_CONTEXT_ACTION_COUNT;
-				out_priv = netdev_priv(attr->encap->out_dev);
-				attr->out_rep = out_priv->ppriv;
+				out_priv = netdev_priv(encap_dev);
+				rpriv = out_priv->ppriv;
+				attr->out_rep = rpriv->rep;
+				attr->parse_attr = parse_attr;
 			} else {
 				pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
 				       priv->netdev->name, out_dev->name);
@@ -1106,14 +1695,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == VLAN_F_POP) {
+			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == VLAN_F_PUSH) {
+			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
 				if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q))
 					return -EOPNOTSUPP;
 
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 				attr->vlan = tcf_vlan_push_vid(a);
+			} else { /* action is TCA_VLAN_ACT_MODIFY */
+				return -EOPNOTSUPP;
 			}
 			continue;
 		}
@@ -1125,74 +1716,85 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 		return -EINVAL;
 	}
-	return 0;
+	return err;
 }
 
 int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 			   struct tc_cls_flower_offload *f)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
-	int err = 0;
-	bool fdb_flow = false;
-	u32 flow_tag, action;
 	struct mlx5e_tc_flow *flow;
-	struct mlx5_flow_spec *spec;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-
-	if (esw && esw->mode == SRIOV_OFFLOADS)
-		fdb_flow = true;
+	int attr_size, err = 0;
+	u8 flow_flags = 0;
 
-	if (fdb_flow)
-		flow = kzalloc(sizeof(*flow) +
-			       sizeof(struct mlx5_esw_flow_attr),
-			       GFP_KERNEL);
-	else
-		flow = kzalloc(sizeof(*flow), GFP_KERNEL);
+	if (esw && esw->mode == SRIOV_OFFLOADS) {
+		flow_flags = MLX5E_TC_FLOW_ESWITCH;
+		attr_size  = sizeof(struct mlx5_esw_flow_attr);
+	} else {
+		flow_flags = MLX5E_TC_FLOW_NIC;
+		attr_size  = sizeof(struct mlx5_nic_flow_attr);
+	}
 
-	spec = mlx5_vzalloc(sizeof(*spec));
-	if (!spec || !flow) {
+	flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL);
+	parse_attr = mlx5_vzalloc(sizeof(*parse_attr));
+	if (!parse_attr || !flow) {
 		err = -ENOMEM;
 		goto err_free;
 	}
 
 	flow->cookie = f->cookie;
+	flow->flags = flow_flags;
 
-	err = parse_cls_flower(priv, spec, f);
+	err = parse_cls_flower(priv, flow, &parse_attr->spec, f);
 	if (err < 0)
 		goto err_free;
 
-	if (fdb_flow) {
-		flow->attr  = (struct mlx5_esw_flow_attr *)(flow + 1);
-		err = parse_tc_fdb_actions(priv, f->exts, flow);
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
+		err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow);
 		if (err < 0)
-			goto err_free;
-		flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, flow->attr);
+			goto err_handle_encap_flow;
+		flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow);
 	} else {
-		err = parse_tc_nic_actions(priv, f->exts, &action, &flow_tag);
+		err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow);
 		if (err < 0)
 			goto err_free;
-		flow->rule = mlx5e_tc_add_nic_flow(priv, spec, action, flow_tag);
+		flow->rule = mlx5e_tc_add_nic_flow(priv, parse_attr, flow);
 	}
 
 	if (IS_ERR(flow->rule)) {
 		err = PTR_ERR(flow->rule);
-		goto err_del_rule;
+		goto err_free;
 	}
 
+	flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
 				     tc->ht_params);
 	if (err)
 		goto err_del_rule;
 
-	goto out;
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH &&
+	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
+		kvfree(parse_attr);
+	return err;
 
 err_del_rule:
 	mlx5e_tc_del_flow(priv, flow);
 
+err_handle_encap_flow:
+	if (err == -EAGAIN) {
+		err = rhashtable_insert_fast(&tc->ht, &flow->node,
+					     tc->ht_params);
+		if (err)
+			mlx5e_tc_del_flow(priv, flow);
+		else
+			return 0;
+	}
+
 err_free:
+	kvfree(parse_attr);
 	kfree(flow);
-out:
-	kvfree(spec);
 	return err;
 }
 
@@ -1211,7 +1813,6 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
 
 	mlx5e_tc_del_flow(priv, flow);
 
-
 	kfree(flow);
 
 	return 0;
@@ -1234,6 +1835,9 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv,
 	if (!flow)
 		return -EINVAL;
 
+	if (!(flow->flags & MLX5E_TC_FLOW_OFFLOADED))
+		return 0;
+
 	counter = mlx5_flow_rule_counter(flow->rule);
 	if (!counter)
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 34bf903fc886..ecbe30d808ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -46,6 +46,15 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
 int mlx5e_stats_flower(struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f);
 
+struct mlx5e_encap_entry;
+void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
+			      struct mlx5e_encap_entry *e);
+void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
+			      struct mlx5e_encap_entry *e);
+
+struct mlx5e_neigh_hash_entry;
+void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
+
 static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv)
 {
 	return atomic_read(&priv->fs.tc.ht.nelems);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f193128bac4b..ab3bb026ff9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -33,34 +33,12 @@
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
 #include "en.h"
+#include "ipoib.h"
 
 #define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
 #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
 			    MLX5E_SQ_NOPS_ROOM)
 
-void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw)
-{
-	struct mlx5_wq_cyc                *wq  = &sq->wq;
-
-	u16 pi = sq->pc & wq->sz_m1;
-	struct mlx5e_tx_wqe              *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	struct mlx5_wqe_ctrl_seg         *cseg = &wqe->ctrl;
-
-	memset(cseg, 0, sizeof(*cseg));
-
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_NOP);
-	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | 0x01);
-
-	sq->pc++;
-	sq->stats.nop++;
-
-	if (notify_hw) {
-		cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-		mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
-	}
-}
-
 static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 				      struct mlx5e_sq_dma *dma)
 {
@@ -76,25 +54,25 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 	}
 }
 
-static inline void mlx5e_dma_push(struct mlx5e_sq *sq,
+static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
 				  dma_addr_t addr,
 				  u32 size,
 				  enum mlx5e_dma_map_type map_type)
 {
 	u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask;
 
-	sq->db.txq.dma_fifo[i].addr = addr;
-	sq->db.txq.dma_fifo[i].size = size;
-	sq->db.txq.dma_fifo[i].type = map_type;
+	sq->db.dma_fifo[i].addr = addr;
+	sq->db.dma_fifo[i].size = size;
+	sq->db.dma_fifo[i].type = map_type;
 	sq->dma_fifo_pc++;
 }
 
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i)
+static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
 {
-	return &sq->db.txq.dma_fifo[i & sq->dma_fifo_mask];
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
 }
 
-static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, u8 num_dma)
+static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
 {
 	int i;
 
@@ -111,6 +89,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
+	u16 num_channels;
 	int up = 0;
 
 	if (!netdev_get_num_tc(dev))
@@ -122,11 +101,11 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 	/* channel_ix can be larger than num_channels since
 	 * dev->num_real_tx_queues = num_channels * num_tc
 	 */
-	if (channel_ix >= priv->params.num_channels)
-		channel_ix = reciprocal_scale(channel_ix,
-					      priv->params.num_channels);
+	num_channels = priv->channels.params.num_channels;
+	if (channel_ix >= num_channels)
+		channel_ix = reciprocal_scale(channel_ix, num_channels);
 
-	return priv->channeltc_to_txq_map[channel_ix][up];
+	return priv->channel_tc2txq[channel_ix][up];
 }
 
 static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
@@ -175,25 +154,6 @@ static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	}
 }
 
-static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
-					    struct sk_buff *skb, bool bf)
-{
-	/* Some NIC TX decisions, e.g loopback, are based on the packet
-	 * headers and occur before the data gather.
-	 * Therefore these headers must be copied into the WQE
-	 */
-	if (bf) {
-		u16 ihs = skb_headlen(skb);
-
-		if (skb_vlan_tag_present(skb))
-			ihs += VLAN_HLEN;
-
-		if (ihs <= sq->max_inline)
-			return skb_headlen(skb);
-	}
-	return mlx5e_calc_min_inline(sq->min_inline_mode, skb);
-}
-
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
 					    unsigned int *skb_len,
 					    unsigned int len)
@@ -218,31 +178,9 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs,
 	mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz);
 }
 
-static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
+static inline void
+mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
 {
-	struct mlx5_wq_cyc       *wq   = &sq->wq;
-
-	u16 pi = sq->pc & wq->sz_m1;
-	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-	struct mlx5e_tx_wqe_info *wi   = &sq->db.txq.wqe_info[pi];
-
-	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-	struct mlx5_wqe_data_seg *dseg;
-
-	unsigned char *skb_data = skb->data;
-	unsigned int skb_len = skb->len;
-	u8  opcode = MLX5_OPCODE_SEND;
-	dma_addr_t dma_addr = 0;
-	unsigned int num_bytes;
-	bool bf = false;
-	u16 headlen;
-	u16 ds_cnt;
-	u16 ihs;
-	int i;
-
-	memset(wqe, 0, sizeof(*wqe));
-
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
 		if (skb->encapsulation) {
@@ -254,71 +192,51 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		}
 	} else
 		sq->stats.csum_none++;
+}
 
-	if (sq->cc != sq->prev_cc) {
-		sq->prev_cc = sq->cc;
-		sq->bf_budget = (sq->cc == sq->pc) ? MLX5E_SQ_BF_BUDGET : 0;
-	}
-
-	if (skb_is_gso(skb)) {
-		eseg->mss    = cpu_to_be16(skb_shinfo(skb)->gso_size);
-		opcode       = MLX5_OPCODE_LSO;
+static inline u16
+mlx5e_txwqe_build_eseg_gso(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+			   struct mlx5_wqe_eth_seg *eseg, unsigned int *num_bytes)
+{
+	u16 ihs;
 
-		if (skb->encapsulation) {
-			ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
-			sq->stats.tso_inner_packets++;
-			sq->stats.tso_inner_bytes += skb->len - ihs;
-		} else {
-			ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
-			sq->stats.tso_packets++;
-			sq->stats.tso_bytes += skb->len - ihs;
-		}
+	eseg->mss    = cpu_to_be16(skb_shinfo(skb)->gso_size);
 
-		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
+	if (skb->encapsulation) {
+		ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
+		sq->stats.tso_inner_packets++;
+		sq->stats.tso_inner_bytes += skb->len - ihs;
 	} else {
-		bf = sq->bf_budget &&
-		     !skb->xmit_more &&
-		     !skb_shinfo(skb)->nr_frags;
-		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
-		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		sq->stats.tso_packets++;
+		sq->stats.tso_bytes += skb->len - ihs;
 	}
 
-	wi->num_bytes = num_bytes;
-
-	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
-	if (ihs) {
-		if (skb_vlan_tag_present(skb)) {
-			mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs, &skb_data, &skb_len);
-			ihs += VLAN_HLEN;
-		} else {
-			memcpy(eseg->inline_hdr.start, skb_data, ihs);
-			mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs);
-		}
-		eseg->inline_hdr.sz = cpu_to_be16(ihs);
-		ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS);
-	} else if (skb_vlan_tag_present(skb)) {
-		eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
-		eseg->insert.vlan_tci = cpu_to_be16(skb_vlan_tag_get(skb));
-	}
-
-	dseg = (struct mlx5_wqe_data_seg *)cseg + ds_cnt;
+	*num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
+	return ihs;
+}
 
-	wi->num_dma = 0;
+static inline int
+mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+			unsigned char *skb_data, u16 headlen,
+			struct mlx5_wqe_data_seg *dseg)
+{
+	dma_addr_t dma_addr = 0;
+	u8 num_dma          = 0;
+	int i;
 
-	headlen = skb_len - skb->data_len;
 	if (headlen) {
 		dma_addr = dma_map_single(sq->pdev, skb_data, headlen,
 					  DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			goto dma_unmap_wqe_err;
+			return -ENOMEM;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
 		dseg->byte_count = cpu_to_be32(headlen);
 
 		mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE);
-		wi->num_dma++;
-
+		num_dma++;
 		dseg++;
 	}
 
@@ -327,62 +245,121 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		int fsz = skb_frag_size(frag);
 
 		dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
-					    DMA_TO_DEVICE);
+				     DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			goto dma_unmap_wqe_err;
+			return -ENOMEM;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
 		dseg->byte_count = cpu_to_be32(fsz);
 
 		mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
-		wi->num_dma++;
-
+		num_dma++;
 		dseg++;
 	}
 
-	ds_cnt += wi->num_dma;
-
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
-	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+	return num_dma;
+}
 
-	sq->db.txq.skb[pi] = skb;
+static inline void
+mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		     u8 opcode, u16 ds_cnt, u32 num_bytes, u8 num_dma,
+		     struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi;
 
+	wi->num_bytes = num_bytes;
+	wi->num_dma = num_dma;
 	wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	sq->pc += wi->num_wqebbs;
+	wi->skb = skb;
 
-	netdev_tx_sent_queue(sq->txq, wi->num_bytes);
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
+	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+
+	netdev_tx_sent_queue(sq->txq, num_bytes);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
-	if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM))) {
+	sq->pc += wi->num_wqebbs;
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM))) {
 		netif_tx_stop_queue(sq->txq);
 		sq->stats.stopped++;
 	}
 
-	sq->stats.xmit_more += skb->xmit_more;
-	if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
-		int bf_sz = 0;
-
-		if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state))
-			bf_sz = wi->num_wqebbs << 3;
-
-		cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-		mlx5e_tx_notify_hw(sq, &wqe->ctrl, bf_sz);
-	}
+	if (!skb->xmit_more || netif_xmit_stopped(sq->txq))
+		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
 
 	/* fill sq edge with nops to avoid wqe wrap around */
 	while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
-		sq->db.txq.skb[pi] = NULL;
-		mlx5e_send_nop(sq, false);
+		sq->db.wqe_info[pi].skb = NULL;
+		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+		sq->stats.nop++;
 	}
+}
 
-	if (bf)
-		sq->bf_budget--;
+static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb)
+{
+	struct mlx5_wq_cyc       *wq   = &sq->wq;
 
-	sq->stats.packets++;
+	u16 pi = sq->pc & wq->sz_m1;
+	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	struct mlx5e_tx_wqe_info *wi   = &sq->db.wqe_info[pi];
+
+	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+
+	unsigned char *skb_data = skb->data;
+	unsigned int skb_len = skb->len;
+	u8  opcode = MLX5_OPCODE_SEND;
+	unsigned int num_bytes;
+	int num_dma;
+	u16 headlen;
+	u16 ds_cnt;
+	u16 ihs;
+
+	memset(wqe, 0, sizeof(*wqe));
+
+	mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
+
+	if (skb_is_gso(skb)) {
+		opcode = MLX5_OPCODE_LSO;
+		ihs = mlx5e_txwqe_build_eseg_gso(sq, skb, eseg, &num_bytes);
+		sq->stats.packets += skb_shinfo(skb)->gso_segs;
+	} else {
+		ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		sq->stats.packets++;
+	}
 	sq->stats.bytes += num_bytes;
+	sq->stats.xmit_more += skb->xmit_more;
+
+	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
+	if (ihs) {
+		if (skb_vlan_tag_present(skb)) {
+			mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs, &skb_data, &skb_len);
+			ihs += VLAN_HLEN;
+		} else {
+			memcpy(eseg->inline_hdr.start, skb_data, ihs);
+			mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs);
+		}
+		eseg->inline_hdr.sz = cpu_to_be16(ihs);
+		ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS);
+	} else if (skb_vlan_tag_present(skb)) {
+		eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
+		eseg->insert.vlan_tci = cpu_to_be16(skb_vlan_tag_get(skb));
+	}
+
+	headlen = skb_len - skb->data_len;
+	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
+					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
+	if (unlikely(num_dma < 0))
+		goto dma_unmap_wqe_err;
+
+	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
+			     num_bytes, num_dma, wi, cseg);
+
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
@@ -397,21 +374,21 @@ dma_unmap_wqe_err:
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sq *sq = priv->txq_to_sq_map[skb_get_queue_mapping(skb)];
+	struct mlx5e_txqsq *sq = priv->txq2sq[skb_get_queue_mapping(skb)];
 
 	return mlx5e_sq_xmit(sq, skb);
 }
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
-	struct mlx5e_sq *sq;
+	struct mlx5e_txqsq *sq;
 	u32 dma_fifo_cc;
 	u32 nbytes;
 	u16 npkts;
 	u16 sqcc;
 	int i;
 
-	sq = container_of(cq, struct mlx5e_sq, cq);
+	sq = container_of(cq, struct mlx5e_txqsq, cq);
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
 		return false;
@@ -449,8 +426,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			last_wqe = (sqcc == wqe_counter);
 
 			ci = sqcc & sq->wq.sz_m1;
-			skb = sq->db.txq.skb[ci];
-			wi = &sq->db.txq.wqe_info[ci];
+			wi = &sq->db.wqe_info[ci];
+			skb = wi->skb;
 
 			if (unlikely(!skb)) { /* nop */
 				sqcc++;
@@ -491,7 +468,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 
 	if (netif_tx_queue_stopped(sq->txq) &&
-	    mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) {
+	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM)) {
 		netif_tx_wake_queue(sq->txq);
 		sq->stats.wake++;
 	}
@@ -499,7 +476,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
-static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
+void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
 	struct sk_buff *skb;
@@ -508,8 +485,8 @@ static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
 
 	while (sq->cc != sq->pc) {
 		ci = sq->cc & sq->wq.sz_m1;
-		skb = sq->db.txq.skb[ci];
-		wi = &sq->db.txq.wqe_info[ci];
+		wi = &sq->db.wqe_info[ci];
+		skb = wi->skb;
 
 		if (!skb) { /* nop */
 			sq->cc++;
@@ -528,36 +505,89 @@ static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
 	}
 }
 
-static void mlx5e_free_xdp_sq_descs(struct mlx5e_sq *sq)
+#ifdef CONFIG_MLX5_CORE_IPOIB
+
+struct mlx5_wqe_eth_pad {
+	u8 rsvd0[16];
+};
+
+struct mlx5i_tx_wqe {
+	struct mlx5_wqe_ctrl_seg     ctrl;
+	struct mlx5_wqe_datagram_seg datagram;
+	struct mlx5_wqe_eth_pad      pad;
+	struct mlx5_wqe_eth_seg      eth;
+};
+
+static inline void
+mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey,
+			   struct mlx5_wqe_datagram_seg *dseg)
 {
-	struct mlx5e_sq_wqe_info *wi;
-	struct mlx5e_dma_info *di;
-	u16 ci;
+	memcpy(&dseg->av, av, sizeof(struct mlx5_av));
+	dseg->av.dqp_dct = cpu_to_be32(dqpn | MLX5_EXTENDED_UD_AV);
+	dseg->av.key.qkey.qkey = cpu_to_be32(dqkey);
+}
 
-	while (sq->cc != sq->pc) {
-		ci = sq->cc & sq->wq.sz_m1;
-		di = &sq->db.xdp.di[ci];
-		wi = &sq->db.xdp.wqe_info[ci];
+netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+			  struct mlx5_av *av, u32 dqpn, u32 dqkey)
+{
+	struct mlx5_wq_cyc       *wq   = &sq->wq;
+	u16                       pi   = sq->pc & wq->sz_m1;
+	struct mlx5i_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	struct mlx5e_tx_wqe_info *wi   = &sq->db.wqe_info[pi];
 
-		if (wi->opcode == MLX5_OPCODE_NOP) {
-			sq->cc++;
-			continue;
-		}
+	struct mlx5_wqe_ctrl_seg     *cseg = &wqe->ctrl;
+	struct mlx5_wqe_datagram_seg *datagram = &wqe->datagram;
+	struct mlx5_wqe_eth_seg      *eseg = &wqe->eth;
 
-		sq->cc += wi->num_wqebbs;
+	unsigned char *skb_data = skb->data;
+	unsigned int skb_len = skb->len;
+	u8  opcode = MLX5_OPCODE_SEND;
+	unsigned int num_bytes;
+	int num_dma;
+	u16 headlen;
+	u16 ds_cnt;
+	u16 ihs;
+
+	memset(wqe, 0, sizeof(*wqe));
 
-		mlx5e_page_release(&sq->channel->rq, di, false);
+	mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram);
+
+	mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
+
+	if (skb_is_gso(skb)) {
+		opcode = MLX5_OPCODE_LSO;
+		ihs = mlx5e_txwqe_build_eseg_gso(sq, skb, eseg, &num_bytes);
+	} else {
+		ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
-}
 
-void mlx5e_free_sq_descs(struct mlx5e_sq *sq)
-{
-	switch (sq->type) {
-	case MLX5E_SQ_TXQ:
-		mlx5e_free_txq_sq_descs(sq);
-		break;
-	case MLX5E_SQ_XDP:
-		mlx5e_free_xdp_sq_descs(sq);
-		break;
+	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
+	if (ihs) {
+		memcpy(eseg->inline_hdr.start, skb_data, ihs);
+		mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs);
+		eseg->inline_hdr.sz = cpu_to_be16(ihs);
+		ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS);
 	}
+
+	headlen = skb_len - skb->data_len;
+	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
+					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
+	if (unlikely(num_dma < 0))
+		goto dma_unmap_wqe_err;
+
+	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
+			     num_bytes, num_dma, wi, cseg);
+
+	return NETDEV_TX_OK;
+
+dma_unmap_wqe_err:
+	sq->stats.dropped++;
+	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
+
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
 }
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index e5c12a732aa1..5ca6714e3e02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -37,124 +37,69 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq)
 	struct mlx5_cqwq *wq = &cq->wq;
 	u32 ci = mlx5_cqwq_get_ci(wq);
 	struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci);
-	int cqe_ownership_bit = cqe->op_own & MLX5_CQE_OWNER_MASK;
-	int sw_ownership_val = mlx5_cqwq_get_wrap_cnt(wq) & 1;
+	u8 cqe_ownership_bit = cqe->op_own & MLX5_CQE_OWNER_MASK;
+	u8 sw_ownership_val = mlx5_cqwq_get_wrap_cnt(wq) & 1;
 
 	if (cqe_ownership_bit != sw_ownership_val)
 		return NULL;
 
 	/* ensure cqe content is read after cqe ownership bit */
-	rmb();
+	dma_rmb();
 
 	return cqe;
 }
 
-static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
+static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
+					     struct mlx5e_icosq *sq,
+					     struct mlx5_cqe64 *cqe,
+					     u16 *sqcc)
 {
-	struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq);
-	struct mlx5_wq_cyc *wq;
-	struct mlx5_cqe64 *cqe;
-	u16 sqcc;
-
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1;
+	struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci];
+	struct mlx5e_rq *rq = &sq->channel->rq;
+
+	prefetch(rq);
+	mlx5_cqwq_pop(&cq->wq);
+	*sqcc += icowi->num_wqebbs;
+
+	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
+		WARN_ONCE(true, "mlx5e: Bad OP in ICOSQ CQE: 0x%x\n",
+			  cqe->op_own);
 		return;
+	}
 
-	cqe = mlx5e_get_cqe(cq);
-	if (likely(!cqe))
+	if (likely(icowi->opcode == MLX5_OPCODE_UMR)) {
+		mlx5e_post_rx_mpwqe(rq);
 		return;
+	}
 
-	wq = &sq->wq;
-
-	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
-	 * otherwise a cq overrun may occur
-	 */
-	sqcc = sq->cc;
-
-	do {
-		u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1;
-		struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci];
-
-		mlx5_cqwq_pop(&cq->wq);
-		sqcc += icowi->num_wqebbs;
-
-		if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
-			WARN_ONCE(true, "mlx5e: Bad OP in ICOSQ CQE: 0x%x\n",
-				  cqe->op_own);
-			break;
-		}
-
-		switch (icowi->opcode) {
-		case MLX5_OPCODE_NOP:
-			break;
-		case MLX5_OPCODE_UMR:
-			mlx5e_post_rx_mpwqe(&sq->channel->rq);
-			break;
-		default:
-			WARN_ONCE(true,
-				  "mlx5e: Bad OPCODE in ICOSQ WQE info: 0x%x\n",
-				  icowi->opcode);
-		}
-
-	} while ((cqe = mlx5e_get_cqe(cq)));
-
-	mlx5_cqwq_update_db_record(&cq->wq);
-
-	/* ensure cq space is freed before enabling more cqes */
-	wmb();
-
-	sq->cc = sqcc;
+	if (unlikely(icowi->opcode != MLX5_OPCODE_NOP))
+		WARN_ONCE(true,
+			  "mlx5e: Bad OPCODE in ICOSQ WQE info: 0x%x\n",
+			  icowi->opcode);
 }
 
-static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq)
+static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 {
-	struct mlx5e_sq *sq;
+	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
+	struct mlx5_cqe64 *cqe;
 	u16 sqcc;
-	int i;
-
-	sq = container_of(cq, struct mlx5e_sq, cq);
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return false;
+		return;
+
+	cqe = mlx5e_get_cqe(cq);
+	if (likely(!cqe))
+		return;
 
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
 	 * otherwise a cq overrun may occur
 	 */
 	sqcc = sq->cc;
 
-	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
-		struct mlx5_cqe64 *cqe;
-		u16 wqe_counter;
-		bool last_wqe;
-
-		cqe = mlx5e_get_cqe(cq);
-		if (!cqe)
-			break;
-
-		mlx5_cqwq_pop(&cq->wq);
-
-		wqe_counter = be16_to_cpu(cqe->wqe_counter);
-
-		do {
-			struct mlx5e_sq_wqe_info *wi;
-			struct mlx5e_dma_info *di;
-			u16 ci;
-
-			last_wqe = (sqcc == wqe_counter);
-
-			ci = sqcc & sq->wq.sz_m1;
-			di = &sq->db.xdp.di[ci];
-			wi = &sq->db.xdp.wqe_info[ci];
-
-			if (unlikely(wi->opcode == MLX5_OPCODE_NOP)) {
-				sqcc++;
-				continue;
-			}
-
-			sqcc += wi->num_wqebbs;
-			/* Recycle RX page */
-			mlx5e_page_release(&sq->channel->rq, di, true);
-		} while (!last_wqe);
-	}
+	/* by design, there's only a single cqe */
+	mlx5e_poll_ico_single_cqe(cq, sq, cqe, &sqcc);
 
 	mlx5_cqwq_update_db_record(&cq->wq);
 
@@ -162,7 +107,6 @@ static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq)
 	wmb();
 
 	sq->cc = sqcc;
-	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
@@ -178,12 +122,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
+	if (c->xdp)
+		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
+
 	work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
 	busy |= work_done == budget;
 
-	if (c->xdp)
-		busy |= mlx5e_poll_xdp_tx_cq(&c->xdp_sq.cq);
-
 	mlx5e_poll_ico_cq(&c->icosq.cq);
 
 	busy |= mlx5e_post_rx_wqes(&c->rq);
@@ -224,8 +168,7 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 	struct mlx5e_channel *c = cq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct net_device *netdev = priv->netdev;
+	struct net_device *netdev = c->netdev;
 
 	netdev_err(netdev, "%s: cqn=0x%.6x event=0x%.2x\n",
 		   __func__, mcq->cqn, event);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index fcd5bc7e31db..2e34d95ea776 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -53,13 +53,6 @@ struct esw_uc_addr {
 	u32                vport;
 };
 
-/* E-Switch MC FDB table hash node */
-struct esw_mc_addr { /* SRIOV only */
-	struct l2addr_node     node;
-	struct mlx5_flow_handle *uplink_rule; /* Forward to uplink rule */
-	u32                    refcnt;
-};
-
 /* Vport UC/MC hash node */
 struct vport_addr {
 	struct l2addr_node     node;
@@ -337,6 +330,7 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *root_ns;
 	struct mlx5_flow_table *fdb;
@@ -362,7 +356,9 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	memset(flow_group_in, 0, inlen);
 
 	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
-	fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0, 0);
+
+	ft_attr.max_fte = table_size;
+	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
 		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
@@ -814,7 +810,7 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
 static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
 				    bool promisc, bool mc_promisc)
 {
-	struct esw_mc_addr *allmulti_addr = esw->mc_promisc;
+	struct esw_mc_addr *allmulti_addr = &esw->mc_promisc;
 	struct mlx5_vport *vport = &esw->vports[vport_num];
 
 	if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc)
@@ -1685,7 +1681,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n",
 		 esw->enabled_vports, esw->mode);
 
-	mc_promisc = esw->mc_promisc;
+	mc_promisc = &esw->mc_promisc;
 	nvports = esw->enabled_vports;
 
 	for (i = 0; i < esw->total_vports; i++)
@@ -1729,7 +1725,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 {
 	int l2_table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
 	int total_vports = MLX5_TOTAL_VPORTS(dev);
-	struct esw_mc_addr *mc_promisc;
 	struct mlx5_eswitch *esw;
 	int vport_num;
 	int err;
@@ -1758,13 +1753,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	}
 	esw->l2_table.size = l2_table_size;
 
-	mc_promisc = kzalloc(sizeof(*mc_promisc), GFP_KERNEL);
-	if (!mc_promisc) {
-		err = -ENOMEM;
-		goto abort;
-	}
-	esw->mc_promisc = mc_promisc;
-
 	esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
 	if (!esw->work_queue) {
 		err = -ENOMEM;
@@ -1803,6 +1791,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	esw->enabled_vports = 0;
 	esw->mode = SRIOV_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+	else
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	return 0;
@@ -1827,7 +1820,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	esw->dev->priv.eswitch = NULL;
 	destroy_workqueue(esw->work_queue);
 	kfree(esw->l2_table.bitmap);
-	kfree(esw->mc_promisc);
 	kfree(esw->offloads.vport_reps);
 	kfree(esw->vports);
 	kfree(esw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 5b78883d5654..b746f62c8c79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -36,7 +36,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_link.h>
 #include <net/devlink.h>
-#include <net/ip_tunnels.h>
 #include <linux/mlx5/device.h>
 
 #define MLX5_MAX_UC_PER_VPORT(dev) \
@@ -209,6 +208,15 @@ struct mlx5_esw_offload {
 	struct mlx5_eswitch_rep *vport_reps;
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	u8 inline_mode;
+	u64 num_flows;
+	u8 encap;
+};
+
+/* E-Switch MC FDB table hash node */
+struct esw_mc_addr { /* SRIOV only */
+	struct l2addr_node     node;
+	struct mlx5_flow_handle *uplink_rule; /* Forward to uplink rule */
+	u32                    refcnt;
 };
 
 struct mlx5_eswitch {
@@ -224,7 +232,7 @@ struct mlx5_eswitch {
 	 * and async SRIOV admin state changes
 	 */
 	struct mutex            state_lock;
-	struct esw_mc_addr      *mc_promisc;
+	struct esw_mc_addr	mc_promisc;
 
 	struct {
 		bool            enabled;
@@ -271,6 +279,11 @@ struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_spec *spec,
 				struct mlx5_esw_flow_attr *attr);
+void
+mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
+				struct mlx5_flow_handle *rule,
+				struct mlx5_esw_flow_attr *attr);
+
 struct mlx5_flow_handle *
 mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
 
@@ -279,20 +292,8 @@ enum {
 	SET_VLAN_INSERT	= BIT(1)
 };
 
-#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP  0x40
-#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x80
-
-struct mlx5_encap_entry {
-	struct hlist_node encap_hlist;
-	struct list_head flows;
-	u32 encap_id;
-	struct neighbour *n;
-	struct ip_tunnel_info tun_info;
-	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
-
-	struct net_device *out_dev;
-	int tunnel_type;
-};
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP  0x4000
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x8000
 
 struct mlx5_esw_flow_attr {
 	struct mlx5_eswitch_rep *in_rep;
@@ -301,7 +302,9 @@ struct mlx5_esw_flow_attr {
 	int	action;
 	u16	vlan;
 	bool	vlan_handled;
-	struct mlx5_encap_entry *encap;
+	u32	encap_id;
+	u32	mod_hdr_id;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
 };
 
 int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
@@ -315,6 +318,8 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode);
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode);
 int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode);
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap);
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap);
 void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
 				     int vport_index,
 				     struct mlx5_eswitch_rep *rep);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4f5b0d47d5f3..f991f669047e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -68,8 +68,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	}
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		counter = mlx5_fc_create(esw->dev, true);
-		if (IS_ERR(counter))
-			return ERR_CAST(counter);
+		if (IS_ERR(counter)) {
+			rule = ERR_CAST(counter);
+			goto err_counter_alloc;
+		}
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 		dest[i].counter = counter;
 		i++;
@@ -86,17 +88,40 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
 		spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
 
-	if (attr->encap)
-		flow_act.encap_id = attr->encap->encap_id;
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		flow_act.modify_id = attr->mod_hdr_id;
+
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+		flow_act.encap_id = attr->encap_id;
 
 	rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb,
 				   spec, &flow_act, dest, i);
 	if (IS_ERR(rule))
-		mlx5_fc_destroy(esw->dev, counter);
+		goto err_add_rule;
+	else
+		esw->offloads.num_flows++;
+
+	return rule;
 
+err_add_rule:
+	mlx5_fc_destroy(esw->dev, counter);
+err_counter_alloc:
 	return rule;
 }
 
+void
+mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
+				struct mlx5_flow_handle *rule,
+				struct mlx5_esw_flow_attr *attr)
+{
+	struct mlx5_fc *counter = NULL;
+
+	counter = mlx5_flow_rule_counter(rule);
+	mlx5_del_flow_rules(rule);
+	mlx5_fc_destroy(esw->dev, counter);
+	esw->offloads.num_flows--;
+}
+
 static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 {
 	struct mlx5_eswitch_rep *rep;
@@ -401,30 +426,21 @@ out:
 	return err;
 }
 
-#define MAX_PF_SQ 256
 #define ESW_OFFLOADS_NUM_GROUPS  4
 
-static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw)
 {
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	int table_size, ix, esw_size, err = 0;
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *root_ns;
 	struct mlx5_flow_table *fdb = NULL;
-	struct mlx5_flow_group *g;
-	u32 *flow_group_in;
-	void *match_criteria;
+	int esw_size, err = 0;
 	u32 flags = 0;
 
-	flow_group_in = mlx5_vzalloc(inlen);
-	if (!flow_group_in)
-		return -ENOMEM;
-
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get FDB flow namespace\n");
 		err = -EOPNOTSUPP;
-		goto ns_err;
+		goto out;
 	}
 
 	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d)*groups(%d))\n",
@@ -434,8 +450,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	esw_size = min_t(int, MLX5_CAP_GEN(dev, max_flow_counter) * ESW_OFFLOADS_NUM_GROUPS,
 			 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
 
-	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
 		flags |= MLX5_FLOW_TABLE_TUNNEL_EN;
 
 	fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH,
@@ -445,12 +460,55 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
 		esw_warn(dev, "Failed to create Fast path FDB Table err %d\n", err);
-		goto fast_fdb_err;
+		goto out;
 	}
 	esw->fdb_table.fdb = fdb;
 
+out:
+	return err;
+}
+
+static void esw_destroy_offloads_fast_fdb_table(struct mlx5_eswitch *esw)
+{
+	mlx5_destroy_flow_table(esw->fdb_table.fdb);
+}
+
+#define MAX_PF_SQ 256
+
+static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *fdb = NULL;
+	int table_size, ix, err = 0;
+	struct mlx5_flow_group *g;
+	void *match_criteria;
+	u32 *flow_group_in;
+
+	esw_debug(esw->dev, "Create offloads FDB Tables\n");
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		err = -EOPNOTSUPP;
+		goto ns_err;
+	}
+
+	err = esw_create_offloads_fast_fdb_table(esw);
+	if (err)
+		goto fast_fdb_err;
+
 	table_size = nvports + MAX_PF_SQ + 1;
-	fdb = mlx5_create_flow_table(root_ns, FDB_SLOW_PATH, table_size, 0, 0);
+
+	ft_attr.max_fte = table_size;
+	ft_attr.prio = FDB_SLOW_PATH;
+
+	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
 		esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err);
@@ -515,25 +573,26 @@ ns_err:
 	return err;
 }
 
-static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 {
 	if (!esw->fdb_table.fdb)
 		return;
 
-	esw_debug(esw->dev, "Destroy offloads FDB Table\n");
+	esw_debug(esw->dev, "Destroy offloads FDB Tables\n");
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.fdb);
-	mlx5_destroy_flow_table(esw->fdb_table.fdb);
+	esw_destroy_offloads_fast_fdb_table(esw);
 }
 
 static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 {
-	struct mlx5_flow_namespace *ns;
-	struct mlx5_flow_table *ft_offloads;
+	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_table *ft_offloads;
+	struct mlx5_flow_namespace *ns;
 	int err = 0;
 
 	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
@@ -542,7 +601,9 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 		return -EOPNOTSUPP;
 	}
 
-	ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0);
+	ft_attr.max_fte = dev->priv.sriov.num_vfs + 2;
+
+	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft_offloads)) {
 		err = PTR_ERR(ft_offloads);
 		esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err);
@@ -683,7 +744,7 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 	mlx5_dev_list_unlock();
 
-	err = esw_create_offloads_fdb_table(esw, nvports);
+	err = esw_create_offloads_fdb_tables(esw, nvports);
 	if (err)
 		goto create_fdb_err;
 
@@ -720,7 +781,7 @@ create_fg_err:
 	esw_destroy_offloads_table(esw);
 
 create_ft_err:
-	esw_destroy_offloads_fdb_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
 
 create_fdb_err:
 	/* enable back PF RoCE */
@@ -766,7 +827,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
 
 	esw_destroy_vport_rx_group(esw);
 	esw_destroy_offloads_table(esw);
-	esw_destroy_offloads_fdb_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -894,8 +955,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	int num_vports = esw->enabled_vports;
-	int err;
-	int vport;
+	int err, vport;
 	u8 mlx5_mode;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
@@ -904,9 +964,22 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
-	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
+	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
+	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+		if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
+			return 0;
+		/* fall through */
+	case MLX5_CAP_INLINE_MODE_L2:
+		esw_warn(dev, "Inline mode can't be set\n");
+		return -EOPNOTSUPP;
+	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+		break;
+	}
+
+	if (esw->offloads.num_flows > 0) {
+		esw_warn(dev, "Can't set inline mode when flows are configured\n");
 		return -EOPNOTSUPP;
+	}
 
 	err = esw_inline_mode_from_devlink(mode, &mlx5_mode);
 	if (err)
@@ -944,18 +1017,14 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
-	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		return -EOPNOTSUPP;
-
 	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
 int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 {
+	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 	struct mlx5_core_dev *dev = esw->dev;
 	int vport;
-	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
 		return -EOPNOTSUPP;
@@ -963,10 +1032,18 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
-	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		return -EOPNOTSUPP;
+	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
+	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+		mlx5_mode = MLX5_INLINE_MODE_NONE;
+		goto out;
+	case MLX5_CAP_INLINE_MODE_L2:
+		mlx5_mode = MLX5_INLINE_MODE_L2;
+		goto out;
+	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+		goto query_vports;
+	}
 
+query_vports:
 	for (vport = 1; vport <= nvfs; vport++) {
 		mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
 		if (vport > 1 && prev_mlx5_mode != mlx5_mode)
@@ -974,10 +1051,71 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 		prev_mlx5_mode = mlx5_mode;
 	}
 
+out:
 	*mode = mlx5_mode;
 	return 0;
 }
 
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+		return -EOPNOTSUPP;
+
+	if (esw->mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	if (encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE &&
+	    (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) ||
+	     !MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)))
+		return -EOPNOTSUPP;
+
+	if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
+		return -EOPNOTSUPP;
+
+	if (esw->mode == SRIOV_LEGACY) {
+		esw->offloads.encap = encap;
+		return 0;
+	}
+
+	if (esw->offloads.encap == encap)
+		return 0;
+
+	if (esw->offloads.num_flows > 0) {
+		esw_warn(dev, "Can't set encapsulation when flows are configured\n");
+		return -EOPNOTSUPP;
+	}
+
+	esw_destroy_offloads_fast_fdb_table(esw);
+
+	esw->offloads.encap = encap;
+	err = esw_create_offloads_fast_fdb_table(esw);
+	if (err) {
+		esw_warn(esw->dev, "Failed re-creating fast FDB table, err %d\n", err);
+		esw->offloads.encap = !encap;
+		(void) esw_create_offloads_fast_fdb_table(esw);
+	}
+	return err;
+}
+
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+		return -EOPNOTSUPP;
+
+	if (esw->mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	*encap = esw->offloads.encap;
+	return 0;
+}
+
 void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
 				     int vport_index,
 				     struct mlx5_eswitch_rep *__rep)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index b64a781c7e85..19e3d2fc2099 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -45,6 +45,10 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
 	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0};
 
+	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
+	    ft->underlay_qpn == 0)
+		return 0;
+
 	MLX5_SET(set_flow_table_root_in, in, opcode,
 		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
 	MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
@@ -54,6 +58,10 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
 		MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
 	}
 
+	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
+	    ft->underlay_qpn != 0)
+		MLX5_SET(set_flow_table_root_in, in, underlay_qpn, ft->underlay_qpn);
+
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
@@ -249,6 +257,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, flow_tag, fte->flow_tag);
 	MLX5_SET(flow_context, in_flow_context, action, fte->action);
 	MLX5_SET(flow_context, in_flow_context, encap_id, fte->encap_id);
+	MLX5_SET(flow_context, in_flow_context, modify_header_id, fte->modify_id);
 	in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
 				      match_value);
 	memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param));
@@ -515,3 +524,69 @@ void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id)
 
 	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
+
+int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+			     u8 namespace, u8 num_actions,
+			     void *modify_actions, u32 *modify_header_id)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)];
+	int max_actions, actions_size, inlen, err;
+	void *actions_in;
+	u8 table_type;
+	u32 *in;
+
+	switch (namespace) {
+	case MLX5_FLOW_NAMESPACE_FDB:
+		max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, max_modify_header_actions);
+		table_type = FS_FT_FDB;
+		break;
+	case MLX5_FLOW_NAMESPACE_KERNEL:
+		max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(dev, max_modify_header_actions);
+		table_type = FS_FT_NIC_RX;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (num_actions > max_actions) {
+		mlx5_core_warn(dev, "too many modify header actions %d, max supported %d\n",
+			       num_actions, max_actions);
+		return -EOPNOTSUPP;
+	}
+
+	actions_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) * num_actions;
+	inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) + actions_size;
+
+	in = kzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(alloc_modify_header_context_in, in, opcode,
+		 MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type);
+	MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_actions);
+
+	actions_in = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions);
+	memcpy(actions_in, modify_actions, actions_size);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+
+	*modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
+	kfree(in);
+	return err;
+}
+
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)];
+	u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)];
+
+	memset(in, 0, sizeof(in));
+	MLX5_SET(dealloc_modify_header_context_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
+		 modify_header_id);
+
+	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 2478516a61e2..b8a176503d38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -476,6 +476,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act,
 	fte->index = index;
 	fte->action = flow_act->action;
 	fte->encap_id = flow_act->encap_id;
+	fte->modify_id = flow_act->modify_id;
 
 	return fte;
 }
@@ -777,18 +778,16 @@ static void list_add_flow_table(struct mlx5_flow_table *ft,
 }
 
 static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
+							struct mlx5_flow_table_attr *ft_attr,
 							enum fs_flow_table_op_mod op_mod,
-							u16 vport, int prio,
-							int max_fte, u32 level,
-							u32 flags)
+							u16 vport)
 {
+	struct mlx5_flow_root_namespace *root = find_root(&ns->node);
 	struct mlx5_flow_table *next_ft = NULL;
+	struct fs_prio *fs_prio = NULL;
 	struct mlx5_flow_table *ft;
-	int err;
 	int log_table_sz;
-	struct mlx5_flow_root_namespace *root =
-		find_root(&ns->node);
-	struct fs_prio *fs_prio = NULL;
+	int err;
 
 	if (!root) {
 		pr_err("mlx5: flow steering failed to find root of namespace\n");
@@ -796,29 +795,31 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	}
 
 	mutex_lock(&root->chain_lock);
-	fs_prio = find_prio(ns, prio);
+	fs_prio = find_prio(ns, ft_attr->prio);
 	if (!fs_prio) {
 		err = -EINVAL;
 		goto unlock_root;
 	}
-	if (level >= fs_prio->num_levels) {
+	if (ft_attr->level >= fs_prio->num_levels) {
 		err = -ENOSPC;
 		goto unlock_root;
 	}
 	/* The level is related to the
 	 * priority level range.
 	 */
-	level += fs_prio->start_level;
-	ft = alloc_flow_table(level,
+	ft_attr->level += fs_prio->start_level;
+	ft = alloc_flow_table(ft_attr->level,
 			      vport,
-			      max_fte ? roundup_pow_of_two(max_fte) : 0,
+			      ft_attr->max_fte ? roundup_pow_of_two(ft_attr->max_fte) : 0,
 			      root->table_type,
-			      op_mod, flags);
+			      op_mod, ft_attr->flags);
 	if (!ft) {
 		err = -ENOMEM;
 		goto unlock_root;
 	}
 
+	ft->underlay_qpn = ft_attr->underlay_qpn;
+
 	tree_init_node(&ft->node, 1, del_flow_table);
 	log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
 	next_ft = find_next_chained_ft(fs_prio);
@@ -848,44 +849,56 @@ unlock_root:
 }
 
 struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
-					       int prio, int max_fte,
-					       u32 level,
-					       u32 flags)
+					       struct mlx5_flow_table_attr *ft_attr)
 {
-	return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, 0, prio,
-					max_fte, level, flags);
+	return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, 0);
 }
 
 struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
 						     int prio, int max_fte,
 						     u32 level, u16 vport)
 {
-	return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, vport, prio,
-					max_fte, level, 0);
+	struct mlx5_flow_table_attr ft_attr = {};
+
+	ft_attr.max_fte = max_fte;
+	ft_attr.level   = level;
+	ft_attr.prio    = prio;
+
+	return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, 0);
 }
 
-struct mlx5_flow_table *mlx5_create_lag_demux_flow_table(
-					       struct mlx5_flow_namespace *ns,
-					       int prio, u32 level)
+struct mlx5_flow_table*
+mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns,
+				 int prio, u32 level)
 {
-	return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_LAG_DEMUX, 0, prio, 0,
-					level, 0);
+	struct mlx5_flow_table_attr ft_attr = {};
+
+	ft_attr.level = level;
+	ft_attr.prio  = prio;
+	return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0);
 }
 EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table);
 
-struct mlx5_flow_table *mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
-							    int prio,
-							    int num_flow_table_entries,
-							    int max_num_groups,
-							    u32 level,
-							    u32 flags)
+struct mlx5_flow_table*
+mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
+				    int prio,
+				    int num_flow_table_entries,
+				    int max_num_groups,
+				    u32 level,
+				    u32 flags)
 {
+	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_table *ft;
 
 	if (max_num_groups > num_flow_table_entries)
 		return ERR_PTR(-EINVAL);
 
-	ft = mlx5_create_flow_table(ns, prio, num_flow_table_entries, level, flags);
+	ft_attr.max_fte = num_flow_table_entries;
+	ft_attr.prio    = prio;
+	ft_attr.level   = level;
+	ft_attr.flags   = flags;
+
+	ft = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft))
 		return ft;
 
@@ -1136,7 +1149,7 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
 						u32 *match_criteria)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct list_head *prev = ft->node.children.prev;
+	struct list_head *prev = &ft->node.children;
 	unsigned int candidate_index = 0;
 	struct mlx5_flow_group *fg;
 	void *match_criteria_addr;
@@ -1827,12 +1840,18 @@ static void set_prio_attrs(struct mlx5_flow_root_namespace *root_ns)
 static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
 {
 	struct mlx5_flow_namespace *ns = NULL;
+	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_table *ft;
 
 	ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR);
 	if (WARN_ON(!ns))
 		return -EINVAL;
-	ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0);
+
+	ft_attr.max_fte = ANCHOR_SIZE;
+	ft_attr.level   = ANCHOR_LEVEL;
+	ft_attr.prio    = ANCHOR_PRIO;
+
+	ft = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft)) {
 		mlx5_core_err(steering->dev, "Failed to create last anchor flow table");
 		return PTR_ERR(ft);
@@ -1886,9 +1905,6 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
 
-	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
-		return;
-
 	cleanup_root_ns(steering->root_ns);
 	cleanup_root_ns(steering->esw_egress_root_ns);
 	cleanup_root_ns(steering->esw_ingress_root_ns);
@@ -1991,9 +2007,6 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 	struct mlx5_flow_steering *steering;
 	int err = 0;
 
-	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
-		return 0;
-
 	err = mlx5_init_fc_stats(dev);
 	if (err)
 		return err;
@@ -2004,7 +2017,10 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 	steering->dev = dev;
 	dev->priv.steering = steering;
 
-	if (MLX5_CAP_GEN(dev, nic_flow_table) &&
+	if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
+	      (MLX5_CAP_GEN(dev, nic_flow_table))) ||
+	     ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
+	      MLX5_CAP_GEN(dev, ipoib_enhanced_offloads))) &&
 	    MLX5_CAP_FLOWTABLE_NIC_RX(dev, ft_support)) {
 		err = init_root_ns(steering);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 8e668c63f69e..81eafc7b9dd9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -118,6 +118,7 @@ struct mlx5_flow_table {
 	/* FWD rules that point on this flow table */
 	struct list_head		fwd_rules;
 	u32				flags;
+	u32				underlay_qpn;
 };
 
 struct mlx5_fc_cache {
@@ -152,6 +153,7 @@ struct fs_fte {
 	u32				index;
 	u32				action;
 	u32				encap_id;
+	u32				modify_id;
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
 };
@@ -197,6 +199,11 @@ struct mlx5_flow_root_namespace {
 
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
 void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev);
+void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
+			      struct delayed_work *dwork,
+			      unsigned long delay);
+void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
+				      unsigned long interval);
 
 int mlx5_init_fs(struct mlx5_core_dev *dev);
 void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 7431f633de31..6507d8acc54d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -165,7 +165,8 @@ static void mlx5_fc_stats_work(struct work_struct *work)
 	list_splice_tail_init(&fc_stats->addlist, &tmplist);
 
 	if (!list_empty(&tmplist) || !RB_EMPTY_ROOT(&fc_stats->counters))
-		queue_delayed_work(fc_stats->wq, &fc_stats->work, MLX5_FC_STATS_PERIOD);
+		queue_delayed_work(fc_stats->wq, &fc_stats->work,
+				   fc_stats->sampling_interval);
 
 	spin_unlock(&fc_stats->addlist_lock);
 
@@ -200,7 +201,7 @@ static void mlx5_fc_stats_work(struct work_struct *work)
 		node = mlx5_fc_stats_query(dev, counter, last->id);
 	}
 
-	fc_stats->next_query = now + MLX5_FC_STATS_PERIOD;
+	fc_stats->next_query = now + fc_stats->sampling_interval;
 }
 
 struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
@@ -265,6 +266,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 	if (!fc_stats->wq)
 		return -ENOMEM;
 
+	fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD;
 	INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work);
 
 	return 0;
@@ -317,3 +319,21 @@ void mlx5_fc_query_cached(struct mlx5_fc *counter,
 	counter->lastbytes = c.bytes;
 	counter->lastpackets = c.packets;
 }
+
+void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
+			      struct delayed_work *dwork,
+			      unsigned long delay)
+{
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+
+	queue_delayed_work(fc_stats->wq, dwork, delay);
+}
+
+void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
+				      unsigned long interval)
+{
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+
+	fc_stats->sampling_interval = min_t(unsigned long, interval,
+					    fc_stats->sampling_interval);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index d0bbefa08af7..1bc14d0fded8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -137,7 +137,8 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, nic_flow_table)) {
+	if (MLX5_CAP_GEN(dev, nic_flow_table) ||
+	    MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
new file mode 100644
index 000000000000..3c84e36af018
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
@@ -0,0 +1,498 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/mlx5/fs.h>
+#include "en.h"
+#include "ipoib.h"
+
+#define IB_DEFAULT_Q_KEY   0xb1b
+
+static int mlx5i_open(struct net_device *netdev);
+static int mlx5i_close(struct net_device *netdev);
+static int  mlx5i_dev_init(struct net_device *dev);
+static void mlx5i_dev_cleanup(struct net_device *dev);
+
+static const struct net_device_ops mlx5i_netdev_ops = {
+	.ndo_open                = mlx5i_open,
+	.ndo_stop                = mlx5i_close,
+	.ndo_init                = mlx5i_dev_init,
+	.ndo_uninit              = mlx5i_dev_cleanup,
+};
+
+/* IPoIB mlx5 netdev profile */
+
+/* Called directly after IPoIB netdevice was created to initialize SW structs */
+static void mlx5i_init(struct mlx5_core_dev *mdev,
+		       struct net_device *netdev,
+		       const struct mlx5e_profile *profile,
+		       void *ppriv)
+{
+	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
+
+	priv->mdev        = mdev;
+	priv->netdev      = netdev;
+	priv->profile     = profile;
+	priv->ppriv       = ppriv;
+
+	mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+
+	mutex_init(&priv->state_lock);
+
+	netdev->hw_features    |= NETIF_F_SG;
+	netdev->hw_features    |= NETIF_F_IP_CSUM;
+	netdev->hw_features    |= NETIF_F_IPV6_CSUM;
+	netdev->hw_features    |= NETIF_F_GRO;
+	netdev->hw_features    |= NETIF_F_TSO;
+	netdev->hw_features    |= NETIF_F_TSO6;
+	netdev->hw_features    |= NETIF_F_RXCSUM;
+	netdev->hw_features    |= NETIF_F_RXHASH;
+
+	netdev->netdev_ops = &mlx5i_netdev_ops;
+}
+
+/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */
+static void mlx5i_cleanup(struct mlx5e_priv *priv)
+{
+	/* Do nothing .. */
+}
+
+#define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2
+
+static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
+{
+	struct mlx5_qp_context *context = NULL;
+	u32 *in = NULL;
+	void *addr_path;
+	int ret = 0;
+	int inlen;
+	void *qpc;
+
+	inlen = MLX5_ST_SZ_BYTES(create_qp_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD);
+	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+	MLX5_SET(qpc, qpc, ulp_stateless_offload_mode,
+		 MLX5_QP_ENHANCED_ULP_STATELESS_MODE);
+
+	addr_path = MLX5_ADDR_OF(qpc, qpc, primary_address_path);
+	MLX5_SET(ads, addr_path, port, 1);
+	MLX5_SET(ads, addr_path, grh, 1);
+
+	ret = mlx5_core_create_qp(mdev, qp, in, inlen);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed creating IPoIB QP err : %d\n", ret);
+		goto out;
+	}
+
+	/* QP states */
+	context = kzalloc(sizeof(*context), GFP_KERNEL);
+	if (!context) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11);
+	context->pri_path.port = 1;
+	context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY);
+
+	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret);
+		goto out;
+	}
+	memset(context, 0, sizeof(*context));
+
+	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret);
+		goto out;
+	}
+
+	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret);
+		goto out;
+	}
+
+out:
+	kfree(context);
+	kvfree(in);
+	return ret;
+}
+
+static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
+{
+	mlx5_core_destroy_qp(mdev, qp);
+}
+
+static int mlx5i_init_tx(struct mlx5e_priv *priv)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	int err;
+
+	err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp);
+	if (err) {
+		mlx5_core_warn(priv->mdev, "create underlay QP failed, %d\n", err);
+		return err;
+	}
+
+	err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
+	if (err) {
+		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+
+	mlx5e_destroy_tis(priv->mdev, priv->tisn[0]);
+	mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp);
+}
+
+static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	int err;
+
+	priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
+					       MLX5_FLOW_NAMESPACE_KERNEL);
+
+	if (!priv->fs.ns)
+		return -EINVAL;
+
+	err = mlx5e_arfs_create_tables(priv);
+	if (err) {
+		netdev_err(priv->netdev, "Failed to create arfs tables, err=%d\n",
+			   err);
+		priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
+	}
+
+	err = mlx5e_create_ttc_table(priv, ipriv->qp.qpn);
+	if (err) {
+		netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
+			   err);
+		goto err_destroy_arfs_tables;
+	}
+
+	return 0;
+
+err_destroy_arfs_tables:
+	mlx5e_arfs_destroy_tables(priv);
+
+	return err;
+}
+
+static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
+{
+	mlx5e_destroy_ttc_table(priv);
+	mlx5e_arfs_destroy_tables(priv);
+}
+
+static int mlx5i_init_rx(struct mlx5e_priv *priv)
+{
+	int err;
+
+	err = mlx5e_create_indirect_rqt(priv);
+	if (err)
+		return err;
+
+	err = mlx5e_create_direct_rqts(priv);
+	if (err)
+		goto err_destroy_indirect_rqts;
+
+	err = mlx5e_create_indirect_tirs(priv);
+	if (err)
+		goto err_destroy_direct_rqts;
+
+	err = mlx5e_create_direct_tirs(priv);
+	if (err)
+		goto err_destroy_indirect_tirs;
+
+	err = mlx5i_create_flow_steering(priv);
+	if (err)
+		goto err_destroy_direct_tirs;
+
+	return 0;
+
+err_destroy_direct_tirs:
+	mlx5e_destroy_direct_tirs(priv);
+err_destroy_indirect_tirs:
+	mlx5e_destroy_indirect_tirs(priv);
+err_destroy_direct_rqts:
+	mlx5e_destroy_direct_rqts(priv);
+err_destroy_indirect_rqts:
+	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	return err;
+}
+
+static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
+{
+	mlx5i_destroy_flow_steering(priv);
+	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_indirect_tirs(priv);
+	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+}
+
+static const struct mlx5e_profile mlx5i_nic_profile = {
+	.init		   = mlx5i_init,
+	.cleanup	   = mlx5i_cleanup,
+	.init_tx	   = mlx5i_init_tx,
+	.cleanup_tx	   = mlx5i_cleanup_tx,
+	.init_rx	   = mlx5i_init_rx,
+	.cleanup_rx	   = mlx5i_cleanup_rx,
+	.enable		   = NULL, /* mlx5i_enable */
+	.disable	   = NULL, /* mlx5i_disable */
+	.update_stats	   = NULL, /* mlx5i_update_stats */
+	.max_nch	   = mlx5e_get_max_num_channels,
+	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
+	.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
+	.max_tc		   = MLX5I_MAX_NUM_TC,
+};
+
+/* mlx5i netdev NDos */
+
+static int mlx5i_dev_init(struct net_device *dev)
+{
+	struct mlx5e_priv    *priv   = mlx5i_epriv(dev);
+	struct mlx5i_priv    *ipriv  = priv->ppriv;
+
+	/* Set dev address using underlay QP */
+	dev->dev_addr[1] = (ipriv->qp.qpn >> 16) & 0xff;
+	dev->dev_addr[2] = (ipriv->qp.qpn >>  8) & 0xff;
+	dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff;
+
+	return 0;
+}
+
+static void mlx5i_dev_cleanup(struct net_device *dev)
+{
+	struct mlx5e_priv    *priv   = mlx5i_epriv(dev);
+	struct mlx5_core_dev *mdev   = priv->mdev;
+	struct mlx5i_priv    *ipriv  = priv->ppriv;
+	struct mlx5_qp_context context;
+
+	/* detach qp from flow-steering by reset it */
+	mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, &ipriv->qp);
+}
+
+static int mlx5i_open(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	int err;
+
+	mutex_lock(&priv->state_lock);
+
+	set_bit(MLX5E_STATE_OPENED, &priv->state);
+
+	err = mlx5e_open_channels(priv, &priv->channels);
+	if (err)
+		goto err_clear_state_opened_flag;
+
+	mlx5e_refresh_tirs(priv, false);
+	mlx5e_activate_priv_channels(priv);
+	mutex_unlock(&priv->state_lock);
+	return 0;
+
+err_clear_state_opened_flag:
+	clear_bit(MLX5E_STATE_OPENED, &priv->state);
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static int mlx5i_close(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+
+	/* May already be CLOSED in case a previous configuration operation
+	 * (e.g RX/TX queue size change) that involves close&open failed.
+	 */
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	clear_bit(MLX5E_STATE_OPENED, &priv->state);
+
+	netif_carrier_off(priv->netdev);
+	mlx5e_deactivate_priv_channels(priv);
+	mlx5e_close_channels(&priv->channels);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return 0;
+}
+
+#ifdef notusedyet
+/* IPoIB RDMA netdev callbacks */
+static int mlx5i_attach_mcast(struct net_device *netdev, struct ib_device *hca,
+			      union ib_gid *gid, u16 lid, int set_qkey)
+{
+	struct mlx5e_priv    *epriv = mlx5i_epriv(netdev);
+	struct mlx5_core_dev *mdev  = epriv->mdev;
+	struct mlx5i_priv    *ipriv = epriv->ppriv;
+	int err;
+
+	mlx5_core_dbg(mdev, "attaching QPN 0x%x, MGID %pI6\n", ipriv->qp.qpn, gid->raw);
+	err = mlx5_core_attach_mcg(mdev, gid, ipriv->qp.qpn);
+	if (err)
+		mlx5_core_warn(mdev, "failed attaching QPN 0x%x, MGID %pI6\n",
+			       ipriv->qp.qpn, gid->raw);
+
+	return err;
+}
+
+static int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
+			      union ib_gid *gid, u16 lid)
+{
+	struct mlx5e_priv    *epriv = mlx5i_epriv(netdev);
+	struct mlx5_core_dev *mdev  = epriv->mdev;
+	struct mlx5i_priv    *ipriv = epriv->ppriv;
+	int err;
+
+	mlx5_core_dbg(mdev, "detaching QPN 0x%x, MGID %pI6\n", ipriv->qp.qpn, gid->raw);
+
+	err = mlx5_core_detach_mcg(mdev, gid, ipriv->qp.qpn);
+	if (err)
+		mlx5_core_dbg(mdev, "failed dettaching QPN 0x%x, MGID %pI6\n",
+			      ipriv->qp.qpn, gid->raw);
+
+	return err;
+}
+
+static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
+	       struct ib_ah *address, u32 dqpn, u32 dqkey)
+{
+	struct mlx5e_priv *epriv = mlx5i_epriv(dev);
+	struct mlx5e_txqsq *sq   = epriv->txq2sq[skb_get_queue_mapping(skb)];
+	struct mlx5_ib_ah *mah   = to_mah(address);
+
+	return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, dqkey);
+}
+#endif
+
+static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev)
+{
+	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_IB)
+		return -EOPNOTSUPP;
+
+	if (!MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads)) {
+		mlx5_core_warn(mdev, "IPoIB enhanced offloads are not supported\n");
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+static struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
+						 struct ib_device *ibdev,
+						 const char *name,
+						 void (*setup)(struct net_device *))
+{
+	const struct mlx5e_profile *profile = &mlx5i_nic_profile;
+	int nch = profile->max_nch(mdev);
+	struct net_device *netdev;
+	struct mlx5i_priv *ipriv;
+	struct mlx5e_priv *epriv;
+	int err;
+
+	if (mlx5i_check_required_hca_cap(mdev)) {
+		mlx5_core_warn(mdev, "Accelerated mode is not supported\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	/* This function should only be called once per mdev */
+	err = mlx5e_create_mdev_resources(mdev);
+	if (err)
+		return NULL;
+
+	netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv),
+				  name, NET_NAME_UNKNOWN,
+				  setup,
+				  nch * MLX5E_MAX_NUM_TC,
+				  nch);
+	if (!netdev) {
+		mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n");
+		goto free_mdev_resources;
+	}
+
+	ipriv = netdev_priv(netdev);
+	epriv = mlx5i_epriv(netdev);
+
+	epriv->wq = create_singlethread_workqueue("mlx5i");
+	if (!epriv->wq)
+		goto err_free_netdev;
+
+	profile->init(mdev, netdev, profile, ipriv);
+
+	mlx5e_attach_netdev(epriv);
+	netif_carrier_off(netdev);
+
+	/* TODO: set rdma_netdev func pointers
+	 * rn = &ipriv->rn;
+	 * rn->hca  = ibdev;
+	 * rn->send = mlx5i_xmit;
+	 * rn->attach_mcast = mlx5i_attach_mcast;
+	 * rn->detach_mcast = mlx5i_detach_mcast;
+	 */
+	return netdev;
+
+err_free_netdev:
+	free_netdev(netdev);
+free_mdev_resources:
+	mlx5e_destroy_mdev_resources(mdev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mlx5_rdma_netdev_alloc);
+
+static void mlx5_rdma_netdev_free(struct net_device *netdev)
+{
+	struct mlx5e_priv          *priv    = mlx5i_epriv(netdev);
+	const struct mlx5e_profile *profile = priv->profile;
+
+	mlx5e_detach_netdev(priv);
+	profile->cleanup(priv);
+	destroy_workqueue(priv->wq);
+	free_netdev(netdev);
+
+	mlx5e_destroy_mdev_resources(priv->mdev);
+}
+EXPORT_SYMBOL(mlx5_rdma_netdev_free);
+
diff --git a/drivers/infiniband/hw/qedr/qedr_hsi.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.h
index 66d27521373f..bae0a5cbc8ad 100644
--- a/drivers/infiniband/hw/qedr/qedr_hsi.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.h
@@ -1,5 +1,5 @@
-/* QLogic qedr NIC Driver
- * Copyright (c) 2015-2016  QLogic Corporation
+/*
+ * Copyright (c) 2017, Mellanox Technologies. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -17,7 +17,7 @@
  *
  *      - Redistributions in binary form must reproduce the above
  *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
+ *        disclaimer in the documentation and/or other materials
  *        provided with the distribution.
  *
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
@@ -29,28 +29,26 @@
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef __QED_HSI_ROCE__
-#define __QED_HSI_ROCE__
 
-#include <linux/qed/common_hsi.h>
-#include <linux/qed/roce_common.h>
-#include "qedr_hsi_rdma.h"
+#ifndef __MLX5E_IPOB_H__
+#define __MLX5E_IPOB_H__
 
-/* Affiliated asynchronous events / errors enumeration */
-enum roce_async_events_type {
-	ROCE_ASYNC_EVENT_NONE = 0,
-	ROCE_ASYNC_EVENT_COMM_EST = 1,
-	ROCE_ASYNC_EVENT_SQ_DRAINED,
-	ROCE_ASYNC_EVENT_SRQ_LIMIT,
-	ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
-	ROCE_ASYNC_EVENT_CQ_ERR,
-	ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
-	ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
-	ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
-	ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
-	ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
-	ROCE_ASYNC_EVENT_SRQ_EMPTY,
-	MAX_ROCE_ASYNC_EVENTS_TYPE
+#include <linux/mlx5/fs.h>
+#include "en.h"
+
+#define MLX5I_MAX_NUM_TC 1
+
+/* ipoib rdma netdev's private data structure */
+struct mlx5i_priv {
+	struct mlx5_core_qp qp;
+	char  *mlx5e_priv[0];
 };
 
-#endif /* __QED_HSI_ROCE__ */
+/* Extract mlx5e_priv from IPoIB netdev */
+#define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv))
+
+netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+			  struct mlx5_av *av, u32 dqpn, u32 dqkey);
+void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
+
+#endif /* __MLX5E_IPOB_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 55957246c0e8..b5d5519542e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 					 struct netdev_notifier_changeupper_info *info)
 {
 	struct net_device *upper = info->upper_dev, *ndev_tmp;
-	struct netdev_lag_upper_info *lag_upper_info;
+	struct netdev_lag_upper_info *lag_upper_info = NULL;
 	bool is_bonded;
 	int bond_status = 0;
 	int num_slaves = 0;
@@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	if (!netif_is_lag_master(upper))
 		return 0;
 
-	lag_upper_info = info->upper_info;
+	if (info->linking)
+		lag_upper_info = info->upper_info;
 
 	/* The event may still be of interest if the slave does not belong to
 	 * us, but is enslaved to a master which has one or more of our netdevs
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c4242a4e8130..0c123d571b4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -87,7 +87,7 @@ static struct mlx5_profile profile[] = {
 	[2] = {
 		.mask		= MLX5_PROF_MASK_QP_SIZE |
 				  MLX5_PROF_MASK_MR_CACHE,
-		.log_max_qp	= 17,
+		.log_max_qp	= 18,
 		.mr_cache[0]	= {
 			.size	= 500,
 			.limit	= 250
@@ -1029,7 +1029,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (err) {
 		dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
 			FW_INIT_TIMEOUT_MILI);
-		goto out_err;
+		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_enable_hca(dev, 0);
@@ -1280,6 +1280,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
 	.eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set,
 	.eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get,
+	.eswitch_encap_mode_set = mlx5_devlink_eswitch_encap_mode_set,
+	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
 #endif
 };
 
@@ -1352,6 +1354,7 @@ static int init_one(struct pci_dev *pdev,
 	if (err)
 		goto clean_load;
 
+	pci_save_state(pdev);
 	return 0;
 
 clean_load:
@@ -1407,9 +1410,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call save the pci state and drain the health wq */
+	/* In case of kernel call drain the health wq */
 	if (state) {
-		pci_save_state(pdev);
 		mlx5_drain_health_wq(dev);
 		mlx5_pci_disable_device(dev);
 	}
@@ -1461,6 +1463,7 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
+	pci_save_state(pdev);
 
 	if (wait_vital(pdev)) {
 		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
@@ -1513,8 +1516,10 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF},	/* ConnectX-4LX VF */
 	{ PCI_VDEVICE(MELLANOX, 0x1017) },			/* ConnectX-5, PCIe 3.0 */
 	{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 VF */
-	{ PCI_VDEVICE(MELLANOX, 0x1019) },			/* ConnectX-5, PCIe 4.0 */
-	{ PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5, PCIe 4.0 VF */
+	{ PCI_VDEVICE(MELLANOX, 0x1019) },			/* ConnectX-5 Ex */
+	{ PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 Ex VF */
+	{ PCI_VDEVICE(MELLANOX, 0x101b) },			/* ConnectX-6 */
+	{ PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF},	/* ConnectX-6 VF */
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b3dabe6e8836..fbc6e9e9e305 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -141,6 +141,11 @@ int mlx5_encap_alloc(struct mlx5_core_dev *dev,
 		     u32 *encap_id);
 void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id);
 
+int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+			     u8 namespace, u8 num_actions,
+			     void *modify_actions, u32 *modify_header_id);
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id);
+
 bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv);
 
 int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 2e6b0f290ddc..222b25908d01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -87,6 +87,7 @@ static void up_rel_func(struct kref *kref)
 	struct mlx5_uars_page *up = container_of(kref, struct mlx5_uars_page, ref_count);
 
 	list_del(&up->list);
+	iounmap(up->map);
 	if (mlx5_cmd_free_uar(up->mdev, up->index))
 		mlx5_core_warn(up->mdev, "failed to free uar index %d\n", up->index);
 	kfree(up->reg_bitmap);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 6b6c30deee83..2fb8c6585ac7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -15,7 +15,8 @@ obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
 				   spectrum_kvdl.o spectrum_acl_tcam.o \
-				   spectrum_acl.o spectrum_flower.o
+				   spectrum_acl.o spectrum_flower.o \
+				   spectrum_cnt.o spectrum_dpipe.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
 obj-$(CONFIG_MLXSW_MINIMAL)	+= mlxsw_minimal.o
 mlxsw_minimal-objs		:= minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index a1b48421648a..479511cf79bc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -1043,13 +1043,6 @@ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4);
  */
 MLXSW_ITEM32(cmd_mbox, sw2hw_cq, c_eqn, 0x00, 24, 1);
 
-/* cmd_mbox_sw2hw_cq_oi
- * When set, overrun ignore is enabled. When set, updates of
- * CQ consumer counter (poll for completion) or Request completion
- * notifications (Arm CQ) DoorBells should not be rung on that CQ.
- */
-MLXSW_ITEM32(cmd_mbox, sw2hw_cq, oi, 0x00, 12, 1);
-
 /* cmd_mbox_sw2hw_cq_st
  * Event delivery state machine
  * 0x0 - FIRED
@@ -1132,11 +1125,6 @@ static inline int mlxsw_cmd_sw2hw_eq(struct mlxsw_core *mlxsw_core,
  */
 MLXSW_ITEM32(cmd_mbox, sw2hw_eq, int_msix, 0x00, 24, 1);
 
-/* cmd_mbox_sw2hw_eq_oi
- * When set, overrun ignore is enabled.
- */
-MLXSW_ITEM32(cmd_mbox, sw2hw_eq, oi, 0x00, 12, 1);
-
 /* cmd_mbox_sw2hw_eq_st
  * Event delivery state machine
  * 0x0 - FIRED
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index a4c07841aaf6..affe84eb4bff 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -40,9 +40,6 @@
 #include <linux/export.h>
 #include <linux/err.h>
 #include <linux/if_link.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <linux/u64_stats_sync.h>
 #include <linux/netdevice.h>
 #include <linux/completion.h>
 #include <linux/skbuff.h>
@@ -74,23 +71,9 @@ static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock);
 
 static const char mlxsw_core_driver_name[] = "mlxsw_core";
 
-static struct dentry *mlxsw_core_dbg_root;
-
 static struct workqueue_struct *mlxsw_wq;
 static struct workqueue_struct *mlxsw_owq;
 
-struct mlxsw_core_pcpu_stats {
-	u64			trap_rx_packets[MLXSW_TRAP_ID_MAX];
-	u64			trap_rx_bytes[MLXSW_TRAP_ID_MAX];
-	u64			port_rx_packets[MLXSW_PORT_MAX_PORTS];
-	u64			port_rx_bytes[MLXSW_PORT_MAX_PORTS];
-	struct u64_stats_sync	syncp;
-	u32			trap_rx_dropped[MLXSW_TRAP_ID_MAX];
-	u32			port_rx_dropped[MLXSW_PORT_MAX_PORTS];
-	u32			trap_rx_invalid;
-	u32			port_rx_invalid;
-};
-
 struct mlxsw_core_port {
 	struct devlink_port devlink_port;
 	void *port_driver_priv;
@@ -121,23 +104,48 @@ struct mlxsw_core {
 		spinlock_t trans_list_lock; /* protects trans_list writes */
 		bool use_emad;
 	} emad;
-	struct mlxsw_core_pcpu_stats __percpu *pcpu_stats;
-	struct dentry *dbg_dir;
-	struct {
-		struct debugfs_blob_wrapper vsd_blob;
-		struct debugfs_blob_wrapper psid_blob;
-	} dbg;
 	struct {
 		u8 *mapping; /* lag_id+port_index to local_port mapping */
 	} lag;
 	struct mlxsw_res res;
 	struct mlxsw_hwmon *hwmon;
 	struct mlxsw_thermal *thermal;
-	struct mlxsw_core_port ports[MLXSW_PORT_MAX_PORTS];
+	struct mlxsw_core_port *ports;
+	unsigned int max_ports;
 	unsigned long driver_priv[0];
 	/* driver_priv has to be always the last item */
 };
 
+#define MLXSW_PORT_MAX_PORTS_DEFAULT	0x40
+
+static int mlxsw_ports_init(struct mlxsw_core *mlxsw_core)
+{
+	/* Switch ports are numbered from 1 to queried value */
+	if (MLXSW_CORE_RES_VALID(mlxsw_core, MAX_SYSTEM_PORT))
+		mlxsw_core->max_ports = MLXSW_CORE_RES_GET(mlxsw_core,
+							   MAX_SYSTEM_PORT) + 1;
+	else
+		mlxsw_core->max_ports = MLXSW_PORT_MAX_PORTS_DEFAULT + 1;
+
+	mlxsw_core->ports = kcalloc(mlxsw_core->max_ports,
+				    sizeof(struct mlxsw_core_port), GFP_KERNEL);
+	if (!mlxsw_core->ports)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mlxsw_ports_fini(struct mlxsw_core *mlxsw_core)
+{
+	kfree(mlxsw_core->ports);
+}
+
+unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->max_ports;
+}
+EXPORT_SYMBOL(mlxsw_core_max_ports);
+
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
 {
 	return mlxsw_core->driver_priv;
@@ -703,91 +711,6 @@ err_out:
  * Core functions
  *****************/
 
-static int mlxsw_core_rx_stats_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_core *mlxsw_core = file->private;
-	struct mlxsw_core_pcpu_stats *p;
-	u64 rx_packets, rx_bytes;
-	u64 tmp_rx_packets, tmp_rx_bytes;
-	u32 rx_dropped, rx_invalid;
-	unsigned int start;
-	int i;
-	int j;
-	static const char hdr[] =
-		"     NUM   RX_PACKETS     RX_BYTES RX_DROPPED\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < MLXSW_TRAP_ID_MAX; i++) {
-		rx_packets = 0;
-		rx_bytes = 0;
-		rx_dropped = 0;
-		for_each_possible_cpu(j) {
-			p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-			do {
-				start = u64_stats_fetch_begin(&p->syncp);
-				tmp_rx_packets = p->trap_rx_packets[i];
-				tmp_rx_bytes = p->trap_rx_bytes[i];
-			} while (u64_stats_fetch_retry(&p->syncp, start));
-
-			rx_packets += tmp_rx_packets;
-			rx_bytes += tmp_rx_bytes;
-			rx_dropped += p->trap_rx_dropped[i];
-		}
-		seq_printf(file, "trap %3d %12llu %12llu %10u\n",
-			   i, rx_packets, rx_bytes, rx_dropped);
-	}
-	rx_invalid = 0;
-	for_each_possible_cpu(j) {
-		p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-		rx_invalid += p->trap_rx_invalid;
-	}
-	seq_printf(file, "trap INV                           %10u\n",
-		   rx_invalid);
-
-	for (i = 0; i < MLXSW_PORT_MAX_PORTS; i++) {
-		rx_packets = 0;
-		rx_bytes = 0;
-		rx_dropped = 0;
-		for_each_possible_cpu(j) {
-			p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-			do {
-				start = u64_stats_fetch_begin(&p->syncp);
-				tmp_rx_packets = p->port_rx_packets[i];
-				tmp_rx_bytes = p->port_rx_bytes[i];
-			} while (u64_stats_fetch_retry(&p->syncp, start));
-
-			rx_packets += tmp_rx_packets;
-			rx_bytes += tmp_rx_bytes;
-			rx_dropped += p->port_rx_dropped[i];
-		}
-		seq_printf(file, "port %3d %12llu %12llu %10u\n",
-			   i, rx_packets, rx_bytes, rx_dropped);
-	}
-	rx_invalid = 0;
-	for_each_possible_cpu(j) {
-		p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-		rx_invalid += p->port_rx_invalid;
-	}
-	seq_printf(file, "port INV                           %10u\n",
-		   rx_invalid);
-	return 0;
-}
-
-static int mlxsw_core_rx_stats_dbg_open(struct inode *inode, struct file *f)
-{
-	struct mlxsw_core *mlxsw_core = inode->i_private;
-
-	return single_open(f, mlxsw_core_rx_stats_dbg_read, mlxsw_core);
-}
-
-static const struct file_operations mlxsw_core_rx_stats_dbg_ops = {
-	.owner = THIS_MODULE,
-	.open = mlxsw_core_rx_stats_dbg_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
-
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver)
 {
 	spin_lock(&mlxsw_core_driver_list_lock);
@@ -835,39 +758,13 @@ static void mlxsw_core_driver_put(const char *kind)
 	spin_unlock(&mlxsw_core_driver_list_lock);
 }
 
-static int mlxsw_core_debugfs_init(struct mlxsw_core *mlxsw_core)
-{
-	const struct mlxsw_bus_info *bus_info = mlxsw_core->bus_info;
-
-	mlxsw_core->dbg_dir = debugfs_create_dir(bus_info->device_name,
-						 mlxsw_core_dbg_root);
-	if (!mlxsw_core->dbg_dir)
-		return -ENOMEM;
-	debugfs_create_file("rx_stats", S_IRUGO, mlxsw_core->dbg_dir,
-			    mlxsw_core, &mlxsw_core_rx_stats_dbg_ops);
-	mlxsw_core->dbg.vsd_blob.data = (void *) &bus_info->vsd;
-	mlxsw_core->dbg.vsd_blob.size = sizeof(bus_info->vsd);
-	debugfs_create_blob("vsd", S_IRUGO, mlxsw_core->dbg_dir,
-			    &mlxsw_core->dbg.vsd_blob);
-	mlxsw_core->dbg.psid_blob.data = (void *) &bus_info->psid;
-	mlxsw_core->dbg.psid_blob.size = sizeof(bus_info->psid);
-	debugfs_create_blob("psid", S_IRUGO, mlxsw_core->dbg_dir,
-			    &mlxsw_core->dbg.psid_blob);
-	return 0;
-}
-
-static void mlxsw_core_debugfs_fini(struct mlxsw_core *mlxsw_core)
-{
-	debugfs_remove_recursive(mlxsw_core->dbg_dir);
-}
-
 static int mlxsw_devlink_port_split(struct devlink *devlink,
 				    unsigned int port_index,
 				    unsigned int count)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
-	if (port_index >= MLXSW_PORT_MAX_PORTS)
+	if (port_index >= mlxsw_core->max_ports)
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_split)
 		return -EOPNOTSUPP;
@@ -879,7 +776,7 @@ static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
-	if (port_index >= MLXSW_PORT_MAX_PORTS)
+	if (port_index >= mlxsw_core->max_ports)
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_unsplit)
 		return -EOPNOTSUPP;
@@ -1101,18 +998,15 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	mlxsw_core->bus_priv = bus_priv;
 	mlxsw_core->bus_info = mlxsw_bus_info;
 
-	mlxsw_core->pcpu_stats =
-		netdev_alloc_pcpu_stats(struct mlxsw_core_pcpu_stats);
-	if (!mlxsw_core->pcpu_stats) {
-		err = -ENOMEM;
-		goto err_alloc_stats;
-	}
-
 	err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile,
 			      &mlxsw_core->res);
 	if (err)
 		goto err_bus_init;
 
+	err = mlxsw_ports_init(mlxsw_core);
+	if (err)
+		goto err_ports_init;
+
 	if (MLXSW_CORE_RES_VALID(mlxsw_core, MAX_LAG) &&
 	    MLXSW_CORE_RES_VALID(mlxsw_core, MAX_LAG_MEMBERS)) {
 		alloc_size = sizeof(u8) *
@@ -1148,15 +1042,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 			goto err_driver_init;
 	}
 
-	err = mlxsw_core_debugfs_init(mlxsw_core);
-	if (err)
-		goto err_debugfs_init;
-
 	return 0;
 
-err_debugfs_init:
-	if (mlxsw_core->driver->fini)
-		mlxsw_core->driver->fini(mlxsw_core);
 err_driver_init:
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
@@ -1167,10 +1054,10 @@ err_devlink_register:
 err_emad_init:
 	kfree(mlxsw_core->lag.mapping);
 err_alloc_lag_mapping:
+	mlxsw_ports_fini(mlxsw_core);
+err_ports_init:
 	mlxsw_bus->fini(bus_priv);
 err_bus_init:
-	free_percpu(mlxsw_core->pcpu_stats);
-err_alloc_stats:
 	devlink_free(devlink);
 err_devlink_alloc:
 	mlxsw_core_driver_put(device_kind);
@@ -1183,15 +1070,14 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 	const char *device_kind = mlxsw_core->bus_info->device_kind;
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
-	mlxsw_core_debugfs_fini(mlxsw_core);
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
 	kfree(mlxsw_core->lag.mapping);
+	mlxsw_ports_fini(mlxsw_core);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
-	free_percpu(mlxsw_core->pcpu_stats);
 	devlink_free(devlink);
 	mlxsw_core_driver_put(device_kind);
 }
@@ -1639,7 +1525,6 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 {
 	struct mlxsw_rx_listener_item *rxl_item;
 	const struct mlxsw_rx_listener *rxl;
-	struct mlxsw_core_pcpu_stats *pcpu_stats;
 	u8 local_port;
 	bool found = false;
 
@@ -1661,7 +1546,7 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    __func__, local_port, rx_info->trap_id);
 
 	if ((rx_info->trap_id >= MLXSW_TRAP_ID_MAX) ||
-	    (local_port >= MLXSW_PORT_MAX_PORTS))
+	    (local_port >= mlxsw_core->max_ports))
 		goto drop;
 
 	rcu_read_lock();
@@ -1678,26 +1563,10 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 	if (!found)
 		goto drop;
 
-	pcpu_stats = this_cpu_ptr(mlxsw_core->pcpu_stats);
-	u64_stats_update_begin(&pcpu_stats->syncp);
-	pcpu_stats->port_rx_packets[local_port]++;
-	pcpu_stats->port_rx_bytes[local_port] += skb->len;
-	pcpu_stats->trap_rx_packets[rx_info->trap_id]++;
-	pcpu_stats->trap_rx_bytes[rx_info->trap_id] += skb->len;
-	u64_stats_update_end(&pcpu_stats->syncp);
-
 	rxl->func(skb, local_port, rxl_item->priv);
 	return;
 
 drop:
-	if (rx_info->trap_id >= MLXSW_TRAP_ID_MAX)
-		this_cpu_inc(mlxsw_core->pcpu_stats->trap_rx_invalid);
-	else
-		this_cpu_inc(mlxsw_core->pcpu_stats->trap_rx_dropped[rx_info->trap_id]);
-	if (local_port >= MLXSW_PORT_MAX_PORTS)
-		this_cpu_inc(mlxsw_core->pcpu_stats->port_rx_invalid);
-	else
-		this_cpu_inc(mlxsw_core->pcpu_stats->port_rx_dropped[local_port]);
 	dev_kfree_skb(skb);
 }
 EXPORT_SYMBOL(mlxsw_core_skb_receive);
@@ -1926,15 +1795,8 @@ static int __init mlxsw_core_module_init(void)
 		err = -ENOMEM;
 		goto err_alloc_ordered_workqueue;
 	}
-	mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
-	if (!mlxsw_core_dbg_root) {
-		err = -ENOMEM;
-		goto err_debugfs_create_dir;
-	}
 	return 0;
 
-err_debugfs_create_dir:
-	destroy_workqueue(mlxsw_owq);
 err_alloc_ordered_workqueue:
 	destroy_workqueue(mlxsw_wq);
 	return err;
@@ -1942,7 +1804,6 @@ err_alloc_ordered_workqueue:
 
 static void __exit mlxsw_core_module_exit(void)
 {
-	debugfs_remove_recursive(mlxsw_core_dbg_root);
 	destroy_workqueue(mlxsw_owq);
 	destroy_workqueue(mlxsw_wq);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index cf38cf9027f8..7fb35395adf5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -57,6 +57,8 @@ struct mlxsw_driver;
 struct mlxsw_bus;
 struct mlxsw_bus_info;
 
+unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core);
+
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 5f337715a4da..46304ffb9449 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -567,6 +567,89 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 	return oneact + MLXSW_AFA_PAYLOAD_OFFSET;
 }
 
+/* VLAN Action
+ * -----------
+ * VLAN action is used for manipulating VLANs. It can be used to implement QinQ,
+ * VLAN translation, change of PCP bits of the VLAN tag, push, pop as swap VLANs
+ * and more.
+ */
+
+#define MLXSW_AFA_VLAN_CODE 0x02
+#define MLXSW_AFA_VLAN_SIZE 1
+
+enum mlxsw_afa_vlan_vlan_tag_cmd {
+	MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
+	MLXSW_AFA_VLAN_VLAN_TAG_CMD_PUSH_TAG,
+	MLXSW_AFA_VLAN_VLAN_TAG_CMD_POP_TAG,
+};
+
+enum mlxsw_afa_vlan_cmd {
+	MLXSW_AFA_VLAN_CMD_NOP,
+	MLXSW_AFA_VLAN_CMD_SET_OUTER,
+	MLXSW_AFA_VLAN_CMD_SET_INNER,
+	MLXSW_AFA_VLAN_CMD_COPY_OUTER_TO_INNER,
+	MLXSW_AFA_VLAN_CMD_COPY_INNER_TO_OUTER,
+	MLXSW_AFA_VLAN_CMD_SWAP,
+};
+
+/* afa_vlan_vlan_tag_cmd
+ * Tag command: push, pop, nop VLAN header.
+ */
+MLXSW_ITEM32(afa, vlan, vlan_tag_cmd, 0x00, 29, 3);
+
+/* afa_vlan_vid_cmd */
+MLXSW_ITEM32(afa, vlan, vid_cmd, 0x04, 29, 3);
+
+/* afa_vlan_vid */
+MLXSW_ITEM32(afa, vlan, vid, 0x04, 0, 12);
+
+/* afa_vlan_ethertype_cmd */
+MLXSW_ITEM32(afa, vlan, ethertype_cmd, 0x08, 29, 3);
+
+/* afa_vlan_ethertype
+ * Index to EtherTypes in Switch VLAN EtherType Register (SVER).
+ */
+MLXSW_ITEM32(afa, vlan, ethertype, 0x08, 24, 3);
+
+/* afa_vlan_pcp_cmd */
+MLXSW_ITEM32(afa, vlan, pcp_cmd, 0x08, 13, 3);
+
+/* afa_vlan_pcp */
+MLXSW_ITEM32(afa, vlan, pcp, 0x08, 8, 3);
+
+static inline void
+mlxsw_afa_vlan_pack(char *payload,
+		    enum mlxsw_afa_vlan_vlan_tag_cmd vlan_tag_cmd,
+		    enum mlxsw_afa_vlan_cmd vid_cmd, u16 vid,
+		    enum mlxsw_afa_vlan_cmd pcp_cmd, u8 pcp,
+		    enum mlxsw_afa_vlan_cmd ethertype_cmd, u8 ethertype)
+{
+	mlxsw_afa_vlan_vlan_tag_cmd_set(payload, vlan_tag_cmd);
+	mlxsw_afa_vlan_vid_cmd_set(payload, vid_cmd);
+	mlxsw_afa_vlan_vid_set(payload, vid);
+	mlxsw_afa_vlan_pcp_cmd_set(payload, pcp_cmd);
+	mlxsw_afa_vlan_pcp_set(payload, pcp);
+	mlxsw_afa_vlan_ethertype_cmd_set(payload, ethertype_cmd);
+	mlxsw_afa_vlan_ethertype_set(payload, ethertype);
+}
+
+int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
+				       u16 vid, u8 pcp, u8 et)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_VLAN_CODE,
+						  MLXSW_AFA_VLAN_SIZE);
+
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
+			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
+			    MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
+			    MLXSW_AFA_VLAN_CMD_SET_OUTER, et);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify);
+
 /* Trap / Discard Action
  * ---------------------
  * The Trap / Discard action enables trapping / mirroring packets to the CPU
@@ -677,3 +760,98 @@ err_append_action:
 	return err;
 }
 EXPORT_SYMBOL(mlxsw_afa_block_append_fwd);
+
+/* Policing and Counting Action
+ * ----------------------------
+ * Policing and Counting action is used for binding policer and counter
+ * to ACL rules.
+ */
+
+#define MLXSW_AFA_POLCNT_CODE 0x08
+#define MLXSW_AFA_POLCNT_SIZE 1
+
+enum mlxsw_afa_polcnt_counter_set_type {
+	/* No count */
+	MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+	/* Count packets and bytes */
+	MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+	/* Count only packets */
+	MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* afa_polcnt_counter_set_type
+ * Counter set type for flow counters.
+ */
+MLXSW_ITEM32(afa, polcnt, counter_set_type, 0x04, 24, 8);
+
+/* afa_polcnt_counter_index
+ * Counter index for flow counters.
+ */
+MLXSW_ITEM32(afa, polcnt, counter_index, 0x04, 0, 24);
+
+static inline void
+mlxsw_afa_polcnt_pack(char *payload,
+		      enum mlxsw_afa_polcnt_counter_set_type set_type,
+		      u32 counter_index)
+{
+	mlxsw_afa_polcnt_counter_set_type_set(payload, set_type);
+	mlxsw_afa_polcnt_counter_index_set(payload, counter_index);
+}
+
+int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
+				   u32 counter_index)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_POLCNT_CODE,
+						  MLXSW_AFA_POLCNT_SIZE);
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
+			      counter_index);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_counter);
+
+/* Virtual Router and Forwarding Domain Action
+ * -------------------------------------------
+ * Virtual Switch action is used for manipulate the Virtual Router (VR),
+ * MPLS label space and the Forwarding Identifier (FID).
+ */
+
+#define MLXSW_AFA_VIRFWD_CODE 0x0E
+#define MLXSW_AFA_VIRFWD_SIZE 1
+
+enum mlxsw_afa_virfwd_fid_cmd {
+	/* Do nothing */
+	MLXSW_AFA_VIRFWD_FID_CMD_NOOP,
+	/* Set the Forwarding Identifier (FID) to fid */
+	MLXSW_AFA_VIRFWD_FID_CMD_SET,
+};
+
+/* afa_virfwd_fid_cmd */
+MLXSW_ITEM32(afa, virfwd, fid_cmd, 0x08, 29, 3);
+
+/* afa_virfwd_fid
+ * The FID value.
+ */
+MLXSW_ITEM32(afa, virfwd, fid, 0x08, 0, 16);
+
+static inline void mlxsw_afa_virfwd_pack(char *payload,
+					 enum mlxsw_afa_virfwd_fid_cmd fid_cmd,
+					 u16 fid)
+{
+	mlxsw_afa_virfwd_fid_cmd_set(payload, fid_cmd);
+	mlxsw_afa_virfwd_fid_set(payload, fid);
+}
+
+int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_VIRFWD_CODE,
+						  MLXSW_AFA_VIRFWD_SIZE);
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_fid_set);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 43f78dcfe394..bd8b91d02880 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -62,5 +62,10 @@ void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
 int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 			       u8 local_port, bool in_port);
+int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
+				       u16 vid, u8 pcp, u8 et);
+int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
+				   u32 counter_index);
+int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index e4fcba7c2af2..c75e9141e3ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -54,6 +54,8 @@ enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_DST_IP6_LO,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
+	MLXSW_AFK_ELEMENT_VID,
+	MLXSW_AFK_ELEMENT_PCP,
 	MLXSW_AFK_ELEMENT_MAX,
 };
 
@@ -88,7 +90,7 @@ struct mlxsw_afk_element_info {
 	MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF,			\
 			       _element, _offset, 0, _size)
 
-/* For the purpose of the driver, define a internal storage scratchpad
+/* For the purpose of the driver, define an internal storage scratchpad
  * that will be used to store key/mask values. For each defined element type
  * define an internal storage geometry.
  */
@@ -98,6 +100,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6),
 	MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8),
+	MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12),
+	MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3),
 	MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32),
 	MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index a223c85dfde0..23f7d828cf67 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -44,8 +44,6 @@
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
 #include <linux/log2.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
 #include <linux/string.h>
 
 #include "pci_hw.h"
@@ -57,8 +55,6 @@
 
 static const char mlxsw_pci_driver_name[] = "mlxsw_pci";
 
-static struct dentry *mlxsw_pci_dbg_root;
-
 #define mlxsw_pci_write32(mlxsw_pci, reg, val) \
 	iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
 #define mlxsw_pci_read32(mlxsw_pci, reg) \
@@ -71,21 +67,6 @@ enum mlxsw_pci_queue_type {
 	MLXSW_PCI_QUEUE_TYPE_EQ,
 };
 
-static const char *mlxsw_pci_queue_type_str(enum mlxsw_pci_queue_type q_type)
-{
-	switch (q_type) {
-	case MLXSW_PCI_QUEUE_TYPE_SDQ:
-		return "sdq";
-	case MLXSW_PCI_QUEUE_TYPE_RDQ:
-		return "rdq";
-	case MLXSW_PCI_QUEUE_TYPE_CQ:
-		return "cq";
-	case MLXSW_PCI_QUEUE_TYPE_EQ:
-		return "eq";
-	}
-	BUG();
-}
-
 #define MLXSW_PCI_QUEUE_TYPE_COUNT	4
 
 static const u16 mlxsw_pci_doorbell_type_offset[] = {
@@ -155,7 +136,6 @@ struct mlxsw_pci {
 	u8 __iomem *hw_addr;
 	struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT];
 	u32 doorbell_offset;
-	struct msix_entry msix_entry;
 	struct mlxsw_core *core;
 	struct {
 		struct mlxsw_pci_mem_item *items;
@@ -174,7 +154,6 @@ struct mlxsw_pci {
 		} comp;
 	} cmd;
 	struct mlxsw_bus_info bus_info;
-	struct dentry *dbg_dir;
 };
 
 static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
@@ -261,21 +240,11 @@ static u8 mlxsw_pci_sdq_count(struct mlxsw_pci *mlxsw_pci)
 	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_SDQ);
 }
 
-static u8 mlxsw_pci_rdq_count(struct mlxsw_pci *mlxsw_pci)
-{
-	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_RDQ);
-}
-
 static u8 mlxsw_pci_cq_count(struct mlxsw_pci *mlxsw_pci)
 {
 	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_CQ);
 }
 
-static u8 mlxsw_pci_eq_count(struct mlxsw_pci *mlxsw_pci)
-{
-	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_EQ);
-}
-
 static struct mlxsw_pci_queue *
 __mlxsw_pci_queue_get(struct mlxsw_pci *mlxsw_pci,
 		      enum mlxsw_pci_queue_type q_type, u8 q_num)
@@ -390,26 +359,6 @@ static void mlxsw_pci_sdq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_sdq(mlxsw_pci->core, q->num);
 }
 
-static int mlxsw_pci_sdq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM PROD_COUNT CONS_COUNT COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_sdq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_sdq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %5d\n",
-			   i, q->producer_counter, q->consumer_counter,
-			   q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe,
 				  int index, char *frag_data, size_t frag_len,
 				  int direction)
@@ -544,26 +493,6 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci,
 	}
 }
 
-static int mlxsw_pci_rdq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM PROD_COUNT CONS_COUNT COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_rdq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_rdq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %5d\n",
-			   i, q->producer_counter, q->consumer_counter,
-			   q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			     struct mlxsw_pci_queue *q)
 {
@@ -580,7 +509,6 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 
 	mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */
 	mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
-	mlxsw_cmd_mbox_sw2hw_cq_oi_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
@@ -602,27 +530,6 @@ static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
 }
 
-static int mlxsw_pci_cq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM CONS_INDEX  SDQ_COUNT  RDQ_COUNT COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_cq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_cq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %10d %5d\n",
-			   i, q->consumer_counter, q->u.cq.comp_sdq_count,
-			   q->u.cq.comp_rdq_count, q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 				     struct mlxsw_pci_queue *q,
 				     u16 consumer_counter_limit,
@@ -755,7 +662,6 @@ static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	}
 
 	mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */
-	mlxsw_cmd_mbox_sw2hw_eq_oi_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */
 	mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count));
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
@@ -777,27 +683,6 @@ static void mlxsw_pci_eq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_eq(mlxsw_pci->core, q->num);
 }
 
-static int mlxsw_pci_eq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM CONS_COUNT     EV_CMD    EV_COMP   EV_OTHER COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_eq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_eq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %10d %10d %5d\n",
-			   i, q->consumer_counter, q->u.eq.ev_cmd_count,
-			   q->u.eq.ev_comp_count, q->u.eq.ev_other_count,
-			   q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe)
 {
 	mlxsw_pci->cmd.comp.status = mlxsw_pci_eqe_cmd_status_get(eqe);
@@ -868,7 +753,6 @@ struct mlxsw_pci_queue_ops {
 	void (*fini)(struct mlxsw_pci *mlxsw_pci,
 		     struct mlxsw_pci_queue *q);
 	void (*tasklet)(unsigned long data);
-	int (*dbg_read)(struct seq_file *s, void *data);
 	u16 elem_count;
 	u8 elem_size;
 };
@@ -877,7 +761,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_sdq_ops = {
 	.type		= MLXSW_PCI_QUEUE_TYPE_SDQ,
 	.init		= mlxsw_pci_sdq_init,
 	.fini		= mlxsw_pci_sdq_fini,
-	.dbg_read	= mlxsw_pci_sdq_dbg_read,
 	.elem_count	= MLXSW_PCI_WQE_COUNT,
 	.elem_size	= MLXSW_PCI_WQE_SIZE,
 };
@@ -886,7 +769,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_rdq_ops = {
 	.type		= MLXSW_PCI_QUEUE_TYPE_RDQ,
 	.init		= mlxsw_pci_rdq_init,
 	.fini		= mlxsw_pci_rdq_fini,
-	.dbg_read	= mlxsw_pci_rdq_dbg_read,
 	.elem_count	= MLXSW_PCI_WQE_COUNT,
 	.elem_size	= MLXSW_PCI_WQE_SIZE
 };
@@ -896,7 +778,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
 	.init		= mlxsw_pci_cq_init,
 	.fini		= mlxsw_pci_cq_fini,
 	.tasklet	= mlxsw_pci_cq_tasklet,
-	.dbg_read	= mlxsw_pci_cq_dbg_read,
 	.elem_count	= MLXSW_PCI_CQE_COUNT,
 	.elem_size	= MLXSW_PCI_CQE_SIZE
 };
@@ -906,7 +787,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = {
 	.init		= mlxsw_pci_eq_init,
 	.fini		= mlxsw_pci_eq_fini,
 	.tasklet	= mlxsw_pci_eq_tasklet,
-	.dbg_read	= mlxsw_pci_eq_dbg_read,
 	.elem_count	= MLXSW_PCI_EQE_COUNT,
 	.elem_size	= MLXSW_PCI_EQE_SIZE
 };
@@ -984,9 +864,7 @@ static int mlxsw_pci_queue_group_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 				      const struct mlxsw_pci_queue_ops *q_ops,
 				      u8 num_qs)
 {
-	struct pci_dev *pdev = mlxsw_pci->pdev;
 	struct mlxsw_pci_queue_type_group *queue_group;
-	char tmp[16];
 	int i;
 	int err;
 
@@ -1003,10 +881,6 @@ static int mlxsw_pci_queue_group_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	}
 	queue_group->count = num_qs;
 
-	sprintf(tmp, "%s_stats", mlxsw_pci_queue_type_str(q_ops->type));
-	debugfs_create_devm_seqfile(&pdev->dev, tmp, mlxsw_pci->dbg_dir,
-				    q_ops->dbg_read);
-
 	return 0;
 
 err_queue_init:
@@ -1534,7 +1408,7 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_aqs_init;
 
-	err = request_irq(mlxsw_pci->msix_entry.vector,
+	err = request_irq(pci_irq_vector(pdev, 0),
 			  mlxsw_pci_eq_irq_handler, 0,
 			  mlxsw_pci->bus_info.device_kind, mlxsw_pci);
 	if (err) {
@@ -1567,7 +1441,7 @@ static void mlxsw_pci_fini(void *bus_priv)
 {
 	struct mlxsw_pci *mlxsw_pci = bus_priv;
 
-	free_irq(mlxsw_pci->msix_entry.vector, mlxsw_pci);
+	free_irq(pci_irq_vector(mlxsw_pci->pdev, 0), mlxsw_pci);
 	mlxsw_pci_aqs_fini(mlxsw_pci);
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
 	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
@@ -1842,8 +1716,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_sw_reset;
 	}
 
-	err = pci_enable_msix_exact(pdev, &mlxsw_pci->msix_entry, 1);
-	if (err) {
+	err = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
+	if (err < 0) {
 		dev_err(&pdev->dev, "MSI-X init failed\n");
 		goto err_msix_init;
 	}
@@ -1852,14 +1726,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
 	mlxsw_pci->bus_info.dev = &pdev->dev;
 
-	mlxsw_pci->dbg_dir = debugfs_create_dir(mlxsw_pci->bus_info.device_name,
-						mlxsw_pci_dbg_root);
-	if (!mlxsw_pci->dbg_dir) {
-		dev_err(&pdev->dev, "Failed to create debugfs dir\n");
-		err = -ENOMEM;
-		goto err_dbg_create_dir;
-	}
-
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
 					     &mlxsw_pci_bus, mlxsw_pci);
 	if (err) {
@@ -1870,9 +1736,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err_bus_device_register:
-	debugfs_remove_recursive(mlxsw_pci->dbg_dir);
-err_dbg_create_dir:
-	pci_disable_msix(mlxsw_pci->pdev);
+	pci_free_irq_vectors(mlxsw_pci->pdev);
 err_msix_init:
 err_sw_reset:
 	iounmap(mlxsw_pci->hw_addr);
@@ -1892,8 +1756,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
 	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
 
 	mlxsw_core_bus_device_unregister(mlxsw_pci->core);
-	debugfs_remove_recursive(mlxsw_pci->dbg_dir);
-	pci_disable_msix(mlxsw_pci->pdev);
+	pci_free_irq_vectors(mlxsw_pci->pdev);
 	iounmap(mlxsw_pci->hw_addr);
 	pci_release_regions(mlxsw_pci->pdev);
 	pci_disable_device(mlxsw_pci->pdev);
@@ -1916,15 +1779,11 @@ EXPORT_SYMBOL(mlxsw_pci_driver_unregister);
 
 static int __init mlxsw_pci_module_init(void)
 {
-	mlxsw_pci_dbg_root = debugfs_create_dir(mlxsw_pci_driver_name, NULL);
-	if (!mlxsw_pci_dbg_root)
-		return -ENOMEM;
 	return 0;
 }
 
 static void __exit mlxsw_pci_module_exit(void)
 {
-	debugfs_remove_recursive(mlxsw_pci_dbg_root);
 }
 
 module_init(mlxsw_pci_module_init);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index 3d42146473b3..c580abba8d34 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -49,20 +49,12 @@
 
 #define MLXSW_PORT_MID			0xd000
 
-#define MLXSW_PORT_MAX_PHY_PORTS	0x40
-#define MLXSW_PORT_MAX_PORTS		(MLXSW_PORT_MAX_PHY_PORTS + 1)
-
 #define MLXSW_PORT_MAX_IB_PHY_PORTS	36
 #define MLXSW_PORT_MAX_IB_PORTS		(MLXSW_PORT_MAX_IB_PHY_PORTS + 1)
 
-#define MLXSW_PORT_DEVID_BITS_OFFSET	10
-#define MLXSW_PORT_PHY_BITS_OFFSET	4
-#define MLXSW_PORT_PHY_BITS_MASK	(MLXSW_PORT_MAX_PHY_PORTS - 1)
-
 #define MLXSW_PORT_CPU_PORT		0x0
-#define MLXSW_PORT_ROUTER_PORT		(MLXSW_PORT_MAX_PHY_PORTS + 2)
 
-#define MLXSW_PORT_DONT_CARE		(MLXSW_PORT_MAX_PORTS)
+#define MLXSW_PORT_DONT_CARE		0xFF
 
 #define MLXSW_PORT_MODULE_MAX_WIDTH	4
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 0899e2d310e2..83b277c8090e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -769,7 +769,7 @@ static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid)
 #define MLXSW_REG_SPVM_ID 0x200F
 #define MLXSW_REG_SPVM_BASE_LEN 0x04 /* base length, without records */
 #define MLXSW_REG_SPVM_REC_LEN 0x04 /* record length */
-#define MLXSW_REG_SPVM_REC_MAX_COUNT 256
+#define MLXSW_REG_SPVM_REC_MAX_COUNT 255
 #define MLXSW_REG_SPVM_LEN (MLXSW_REG_SPVM_BASE_LEN +	\
 		    MLXSW_REG_SPVM_REC_LEN * MLXSW_REG_SPVM_REC_MAX_COUNT)
 
@@ -1702,7 +1702,7 @@ static inline void mlxsw_reg_sfmr_pack(char *payload,
 #define MLXSW_REG_SPVMLR_ID 0x2020
 #define MLXSW_REG_SPVMLR_BASE_LEN 0x04 /* base length, without records */
 #define MLXSW_REG_SPVMLR_REC_LEN 0x04 /* record length */
-#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 256
+#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 255
 #define MLXSW_REG_SPVMLR_LEN (MLXSW_REG_SPVMLR_BASE_LEN + \
 			      MLXSW_REG_SPVMLR_REC_LEN * \
 			      MLXSW_REG_SPVMLR_REC_MAX_COUNT)
@@ -4125,6 +4125,60 @@ MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16);
  */
 MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12);
 
+/* Shared between ingress/egress */
+enum mlxsw_reg_ritr_counter_set_type {
+	/* No Count. */
+	MLXSW_REG_RITR_COUNTER_SET_TYPE_NO_COUNT = 0x0,
+	/* Basic. Used for router interfaces, counting the following:
+	 *	- Error and Discard counters.
+	 *	- Unicast, Multicast and Broadcast counters. Sharing the
+	 *	  same set of counters for the different type of traffic
+	 *	  (IPv4, IPv6 and mpls).
+	 */
+	MLXSW_REG_RITR_COUNTER_SET_TYPE_BASIC = 0x9,
+};
+
+/* reg_ritr_ingress_counter_index
+ * Counter Index for flow counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ingress_counter_index, 0x38, 0, 24);
+
+/* reg_ritr_ingress_counter_set_type
+ * Igress Counter Set Type for router interface counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ingress_counter_set_type, 0x38, 24, 8);
+
+/* reg_ritr_egress_counter_index
+ * Counter Index for flow counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, egress_counter_index, 0x3C, 0, 24);
+
+/* reg_ritr_egress_counter_set_type
+ * Egress Counter Set Type for router interface counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, egress_counter_set_type, 0x3C, 24, 8);
+
+static inline void mlxsw_reg_ritr_counter_pack(char *payload, u32 index,
+					       bool enable, bool egress)
+{
+	enum mlxsw_reg_ritr_counter_set_type set_type;
+
+	if (enable)
+		set_type = MLXSW_REG_RITR_COUNTER_SET_TYPE_BASIC;
+	else
+		set_type = MLXSW_REG_RITR_COUNTER_SET_TYPE_NO_COUNT;
+	mlxsw_reg_ritr_egress_counter_set_type_set(payload, set_type);
+
+	if (egress)
+		mlxsw_reg_ritr_egress_counter_index_set(payload, index);
+	else
+		mlxsw_reg_ritr_ingress_counter_index_set(payload, index);
+}
+
 static inline void mlxsw_reg_ritr_rif_pack(char *payload, u16 rif)
 {
 	MLXSW_REG_ZERO(ritr, payload);
@@ -4141,7 +4195,8 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag,
 
 static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
 				       enum mlxsw_reg_ritr_if_type type,
-				       u16 rif, u16 mtu, const char *mac)
+				       u16 rif, u16 vr_id, u16 mtu,
+				       const char *mac)
 {
 	bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL;
 
@@ -4153,6 +4208,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
 	mlxsw_reg_ritr_rif_set(payload, rif);
 	mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
 	mlxsw_reg_ritr_lb_en_set(payload, 1);
+	mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
 	mlxsw_reg_ritr_mtu_set(payload, mtu);
 	mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
 }
@@ -4285,6 +4341,129 @@ static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload,
 	mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac);
 }
 
+/* RICNT - Router Interface Counter Register
+ * -----------------------------------------
+ * The RICNT register retrieves per port performance counters
+ */
+#define MLXSW_REG_RICNT_ID 0x800B
+#define MLXSW_REG_RICNT_LEN 0x100
+
+MLXSW_REG_DEFINE(ricnt, MLXSW_REG_RICNT_ID, MLXSW_REG_RICNT_LEN);
+
+/* reg_ricnt_counter_index
+ * Counter index
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, counter_index, 0x04, 0, 24);
+
+enum mlxsw_reg_ricnt_counter_set_type {
+	/* No Count. */
+	MLXSW_REG_RICNT_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+	/* Basic. Used for router interfaces, counting the following:
+	 *	- Error and Discard counters.
+	 *	- Unicast, Multicast and Broadcast counters. Sharing the
+	 *	  same set of counters for the different type of traffic
+	 *	  (IPv4, IPv6 and mpls).
+	 */
+	MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC = 0x09,
+};
+
+/* reg_ricnt_counter_set_type
+ * Counter Set Type for router interface counter
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, counter_set_type, 0x04, 24, 8);
+
+enum mlxsw_reg_ricnt_opcode {
+	/* Nop. Supported only for read access*/
+	MLXSW_REG_RICNT_OPCODE_NOP = 0x00,
+	/* Clear. Setting the clr bit will reset the counter value for
+	 * all counters of the specified Router Interface.
+	 */
+	MLXSW_REG_RICNT_OPCODE_CLEAR = 0x08,
+};
+
+/* reg_ricnt_opcode
+ * Opcode
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, op, 0x00, 28, 4);
+
+/* reg_ricnt_good_unicast_packets
+ * good unicast packets.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_unicast_packets, 0x08, 0, 64);
+
+/* reg_ricnt_good_multicast_packets
+ * good multicast packets.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_multicast_packets, 0x10, 0, 64);
+
+/* reg_ricnt_good_broadcast_packets
+ * good broadcast packets
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_broadcast_packets, 0x18, 0, 64);
+
+/* reg_ricnt_good_unicast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good unicast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_unicast_bytes, 0x20, 0, 64);
+
+/* reg_ricnt_good_multicast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good multicast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_multicast_bytes, 0x28, 0, 64);
+
+/* reg_ritr_good_broadcast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good broadcast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_broadcast_bytes, 0x30, 0, 64);
+
+/* reg_ricnt_error_packets
+ * A count of errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, error_packets, 0x38, 0, 64);
+
+/* reg_ricnt_discrad_packets
+ * A count of non-errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, discard_packets, 0x40, 0, 64);
+
+/* reg_ricnt_error_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for errored frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, error_bytes, 0x48, 0, 64);
+
+/* reg_ricnt_discard_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for non-errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, discard_bytes, 0x50, 0, 64);
+
+static inline void mlxsw_reg_ricnt_pack(char *payload, u32 index,
+					enum mlxsw_reg_ricnt_opcode op)
+{
+	MLXSW_REG_ZERO(ricnt, payload);
+	mlxsw_reg_ricnt_op_set(payload, op);
+	mlxsw_reg_ricnt_counter_index_set(payload, index);
+	mlxsw_reg_ricnt_counter_set_type_set(payload,
+					     MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC);
+}
+
 /* RALTA - Router Algorithmic LPM Tree Allocation Register
  * -------------------------------------------------------
  * RALTA is used to allocate the LPM trees of the SHSPM method.
@@ -5504,6 +5683,70 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e,
 	mlxsw_reg_mpsc_rate_set(payload, rate);
 }
 
+/* MGPC - Monitoring General Purpose Counter Set Register
+ * The MGPC register retrieves and sets the General Purpose Counter Set.
+ */
+#define MLXSW_REG_MGPC_ID 0x9081
+#define MLXSW_REG_MGPC_LEN 0x18
+
+MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN);
+
+enum mlxsw_reg_mgpc_counter_set_type {
+	/* No count */
+	MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00,
+	/* Count packets and bytes */
+	MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+	/* Count only packets */
+	MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* reg_mgpc_counter_set_type
+ * Counter set type.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mgpc, counter_set_type, 0x00, 24, 8);
+
+/* reg_mgpc_counter_index
+ * Counter index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mgpc, counter_index, 0x00, 0, 24);
+
+enum mlxsw_reg_mgpc_opcode {
+	/* Nop */
+	MLXSW_REG_MGPC_OPCODE_NOP = 0x00,
+	/* Clear counters */
+	MLXSW_REG_MGPC_OPCODE_CLEAR = 0x08,
+};
+
+/* reg_mgpc_opcode
+ * Opcode.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mgpc, opcode, 0x04, 28, 4);
+
+/* reg_mgpc_byte_counter
+ * Byte counter value.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mgpc, byte_counter, 0x08, 0, 64);
+
+/* reg_mgpc_packet_counter
+ * Packet counter value.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64);
+
+static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index,
+				       enum mlxsw_reg_mgpc_opcode opcode,
+				       enum mlxsw_reg_mgpc_counter_set_type set_type)
+{
+	MLXSW_REG_ZERO(mgpc, payload);
+	mlxsw_reg_mgpc_counter_index_set(payload, counter_index);
+	mlxsw_reg_mgpc_counter_set_type_set(payload, set_type);
+	mlxsw_reg_mgpc_opcode_set(payload, opcode);
+}
+
 /* SBPR - Shared Buffer Pools Register
  * -----------------------------------
  * The SBPR configures and retrieves the shared buffer pools and configuration.
@@ -5960,6 +6203,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(rgcr),
 	MLXSW_REG(ritr),
 	MLXSW_REG(ratr),
+	MLXSW_REG(ricnt),
 	MLXSW_REG(ralta),
 	MLXSW_REG(ralst),
 	MLXSW_REG(raltb),
@@ -5977,6 +6221,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mpar),
 	MLXSW_REG(mlcr),
 	MLXSW_REG(mpsc),
+	MLXSW_REG(mgpc),
 	MLXSW_REG(sbpr),
 	MLXSW_REG(sbcm),
 	MLXSW_REG(sbpm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index bce8c2e00630..9556d934714b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -43,11 +43,15 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
 	MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
 	MLXSW_RES_ID_MAX_TRAP_GROUPS,
+	MLXSW_RES_ID_COUNTER_POOL_SIZE,
 	MLXSW_RES_ID_MAX_SPAN,
+	MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES,
+	MLXSW_RES_ID_COUNTER_SIZE_ROUTER_BASIC,
 	MLXSW_RES_ID_MAX_SYSTEM_PORT,
 	MLXSW_RES_ID_MAX_LAG,
 	MLXSW_RES_ID_MAX_LAG_MEMBERS,
 	MLXSW_RES_ID_MAX_BUFFER_SIZE,
+	MLXSW_RES_ID_CELL_SIZE,
 	MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS,
 	MLXSW_RES_ID_ACL_MAX_TCAM_RULES,
 	MLXSW_RES_ID_ACL_MAX_REGIONS,
@@ -59,6 +63,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
+	MLXSW_RES_ID_MAX_LPM_TREES,
 
 	/* Internal resources.
 	 * Determined by the SW, not queried from the HW.
@@ -75,11 +80,15 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
 	[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
 	[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
+	[MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410,
 	[MLXSW_RES_ID_MAX_SPAN] = 0x2420,
+	[MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443,
+	[MLXSW_RES_ID_COUNTER_SIZE_ROUTER_BASIC] = 0x2449,
 	[MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502,
 	[MLXSW_RES_ID_MAX_LAG] = 0x2520,
 	[MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521,
 	[MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802,	/* Bytes */
+	[MLXSW_RES_ID_CELL_SIZE] = 0x2803,	/* Bytes */
 	[MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901,
 	[MLXSW_RES_ID_ACL_MAX_TCAM_RULES] = 0x2902,
 	[MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903,
@@ -91,6 +100,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
+	[MLXSW_RES_ID_MAX_LPM_TREES] = 0x2C30,
 };
 
 struct mlxsw_res {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 16484f24b7db..88357cee7679 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -66,6 +66,8 @@
 #include "port.h"
 #include "trap.h"
 #include "txheader.h"
+#include "spectrum_cnt.h"
+#include "spectrum_dpipe.h"
 
 static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
 static const char mlxsw_sp_driver_version[] = "1.0";
@@ -138,6 +140,60 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16);
  */
 MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
 
+int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
+			      unsigned int counter_index, u64 *packets,
+			      u64 *bytes)
+{
+	char mgpc_pl[MLXSW_REG_MGPC_LEN];
+	int err;
+
+	mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP,
+			    MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
+	if (err)
+		return err;
+	*packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl);
+	*bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl);
+	return 0;
+}
+
+static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp,
+				       unsigned int counter_index)
+{
+	char mgpc_pl[MLXSW_REG_MGPC_LEN];
+
+	mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR,
+			    MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
+}
+
+int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				unsigned int *p_counter_index)
+{
+	int err;
+
+	err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+				     p_counter_index);
+	if (err)
+		return err;
+	err = mlxsw_sp_flow_counter_clear(mlxsw_sp, *p_counter_index);
+	if (err)
+		goto err_counter_clear;
+	return 0;
+
+err_counter_clear:
+	mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+			      *p_counter_index);
+	return err;
+}
+
+void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
+				unsigned int counter_index)
+{
+	 mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+			       counter_index);
+}
+
 static void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
 				     const struct mlxsw_tx_info *tx_info)
 {
@@ -304,9 +360,10 @@ static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port)
 	return false;
 }
 
-static int mlxsw_sp_span_mtu_to_buffsize(int mtu)
+static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp,
+					 int mtu)
 {
-	return MLXSW_SP_BYTES_TO_CELLS(mtu * 5 / 2) + 1;
+	return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1;
 }
 
 static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
@@ -319,8 +376,9 @@ static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
 	 * updated according to the mtu value
 	 */
 	if (mlxsw_sp_span_is_egress_mirror(port)) {
-		mlxsw_reg_sbib_pack(sbib_pl, port->local_port,
-				    mlxsw_sp_span_mtu_to_buffsize(mtu));
+		u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu);
+
+		mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 		if (err) {
 			netdev_err(port->dev, "Could not update shared buffer for mirroring\n");
@@ -357,8 +415,10 @@ mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port,
 
 	/* if it is an egress SPAN, bind a shared buffer to it */
 	if (type == MLXSW_SP_SPAN_EGRESS) {
-		mlxsw_reg_sbib_pack(sbib_pl, port->local_port,
-				    mlxsw_sp_span_mtu_to_buffsize(port->dev->mtu));
+		u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp,
+							     port->dev->mtu);
+
+		mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 		if (err) {
 			netdev_err(port->dev, "Could not create shared buffer for mirroring\n");
@@ -745,19 +805,47 @@ static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p)
 	return 0;
 }
 
-static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int pg_index, int mtu,
-				 bool pause_en, bool pfc_en, u16 delay)
+static u16 mlxsw_sp_pg_buf_threshold_get(const struct mlxsw_sp *mlxsw_sp,
+					 int mtu)
 {
-	u16 pg_size = 2 * MLXSW_SP_BYTES_TO_CELLS(mtu);
+	return 2 * mlxsw_sp_bytes_cells(mlxsw_sp, mtu);
+}
 
-	delay = pfc_en ? mlxsw_sp_pfc_delay_get(mtu, delay) :
-			 MLXSW_SP_PAUSE_DELAY;
+#define MLXSW_SP_CELL_FACTOR 2	/* 2 * cell_size / (IPG + cell_size + 1) */
+
+static u16 mlxsw_sp_pfc_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
+				  u16 delay)
+{
+	delay = mlxsw_sp_bytes_cells(mlxsw_sp, DIV_ROUND_UP(delay,
+							    BITS_PER_BYTE));
+	return MLXSW_SP_CELL_FACTOR * delay + mlxsw_sp_bytes_cells(mlxsw_sp,
+								   mtu);
+}
+
+/* Maximum delay buffer needed in case of PAUSE frames, in bytes.
+ * Assumes 100m cable and maximum MTU.
+ */
+#define MLXSW_SP_PAUSE_DELAY 58752
 
-	if (pause_en || pfc_en)
-		mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, pg_index,
-						    pg_size + delay, pg_size);
+static u16 mlxsw_sp_pg_buf_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
+				     u16 delay, bool pfc, bool pause)
+{
+	if (pfc)
+		return mlxsw_sp_pfc_delay_get(mlxsw_sp, mtu, delay);
+	else if (pause)
+		return mlxsw_sp_bytes_cells(mlxsw_sp, MLXSW_SP_PAUSE_DELAY);
+	else
+		return 0;
+}
+
+static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int index, u16 size, u16 thres,
+				 bool lossy)
+{
+	if (lossy)
+		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, index, size);
 	else
-		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pg_index, pg_size);
+		mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, index, size,
+						    thres);
 }
 
 int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
@@ -778,6 +866,8 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		bool configure = false;
 		bool pfc = false;
+		bool lossy;
+		u16 thres;
 
 		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
 			if (prio_tc[j] == i) {
@@ -789,7 +879,12 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 
 		if (!configure)
 			continue;
-		mlxsw_sp_pg_buf_pack(pbmc_pl, i, mtu, pause_en, pfc, delay);
+
+		lossy = !(pfc || pause_en);
+		thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+		delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
+						  pause_en);
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
@@ -966,8 +1061,9 @@ mlxsw_sp_port_get_stats64(struct net_device *dev,
 	memcpy(stats, mlxsw_sp_port->hw_stats.cache, sizeof(*stats));
 }
 
-int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
-			   u16 vid_end, bool is_member, bool untagged)
+static int __mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 vid_begin, u16 vid_end,
+				    bool is_member, bool untagged)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char *spvm_pl;
@@ -984,6 +1080,26 @@ int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 	return err;
 }
 
+int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
+			   u16 vid_end, bool is_member, bool untagged)
+{
+	u16 vid, vid_e;
+	int err;
+
+	for (vid = vid_begin; vid <= vid_end;
+	     vid += MLXSW_REG_SPVM_REC_MAX_COUNT) {
+		vid_e = min((u16) (vid + MLXSW_REG_SPVM_REC_MAX_COUNT - 1),
+			    vid_end);
+
+		err = __mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid_e,
+					       is_member, untagged);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_port_vp_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
@@ -1368,7 +1484,7 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle,
 						       tc->cls_mall);
 			return 0;
 		default:
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		}
 	case TC_SETUP_CLSFLOWER:
 		switch (tc->cls_flower->command) {
@@ -1379,6 +1495,9 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle,
 			mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress,
 						tc->cls_flower);
 			return 0;
+		case TC_CLSFLOWER_STATS:
+			return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress,
+						     tc->cls_flower);
 		default:
 			return -EOPNOTSUPP;
 		}
@@ -1492,6 +1611,7 @@ err_port_pause_configure:
 struct mlxsw_sp_port_hw_stats {
 	char str[ETH_GSTRING_LEN];
 	u64 (*getter)(const char *payload);
+	bool cells_bytes;
 };
 
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
@@ -1612,17 +1732,11 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
 
 #define MLXSW_SP_PORT_HW_PRIO_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_prio_stats)
 
-static u64 mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get(const char *ppcnt_pl)
-{
-	u64 transmit_queue = mlxsw_reg_ppcnt_tc_transmit_queue_get(ppcnt_pl);
-
-	return MLXSW_SP_CELLS_TO_BYTES(transmit_queue);
-}
-
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 	{
 		.str = "tc_transmit_queue_tc",
-		.getter = mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get,
+		.getter = mlxsw_reg_ppcnt_tc_transmit_queue_get,
+		.cells_bytes = true,
 	},
 	{
 		.str = "tc_no_buffer_discard_uc_tc",
@@ -1734,6 +1848,8 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 				      enum mlxsw_reg_ppcnt_grp grp, int prio,
 				      u64 *data, int data_index)
 {
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port_hw_stats *hw_stats;
 	char ppcnt_pl[MLXSW_REG_PPCNT_LEN];
 	int i, len;
@@ -1743,8 +1859,13 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 	if (err)
 		return;
 	mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
-	for (i = 0; i < len; i++)
+	for (i = 0; i < len; i++) {
 		data[data_index + i] = hw_stats[i].getter(ppcnt_pl);
+		if (!hw_stats[i].cells_bytes)
+			continue;
+		data[data_index + i] = mlxsw_sp_cells_bytes(mlxsw_sp,
+							    data[data_index + i]);
+	}
 }
 
 static void mlxsw_sp_port_get_stats(struct net_device *dev,
@@ -2537,25 +2658,33 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 {
 	int i;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+	for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
 		if (mlxsw_sp_port_created(mlxsw_sp, i))
 			mlxsw_sp_port_remove(mlxsw_sp, i);
+	kfree(mlxsw_sp->port_to_module);
 	kfree(mlxsw_sp->ports);
 }
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	u8 module, width, lane;
 	size_t alloc_size;
 	int i;
 	int err;
 
-	alloc_size = sizeof(struct mlxsw_sp_port *) * MLXSW_PORT_MAX_PORTS;
+	alloc_size = sizeof(struct mlxsw_sp_port *) * max_ports;
 	mlxsw_sp->ports = kzalloc(alloc_size, GFP_KERNEL);
 	if (!mlxsw_sp->ports)
 		return -ENOMEM;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
+	mlxsw_sp->port_to_module = kcalloc(max_ports, sizeof(u8), GFP_KERNEL);
+	if (!mlxsw_sp->port_to_module) {
+		err = -ENOMEM;
+		goto err_port_to_module_alloc;
+	}
+
+	for (i = 1; i < max_ports; i++) {
 		err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
 						    &width, &lane);
 		if (err)
@@ -2575,6 +2704,8 @@ err_port_module_info_get:
 	for (i--; i >= 1; i--)
 		if (mlxsw_sp_port_created(mlxsw_sp, i))
 			mlxsw_sp_port_remove(mlxsw_sp, i);
+	kfree(mlxsw_sp->port_to_module);
+err_port_to_module_alloc:
 	kfree(mlxsw_sp->ports);
 	return err;
 }
@@ -2877,6 +3008,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, IGMP, false),
 	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, ARP, false),
+	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false),
 	/* L3 traps */
 	MLXSW_SP_RXL_NO_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_NO_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false),
@@ -3158,6 +3290,18 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
 }
 
+static int mlxsw_sp_vfid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create);
+
+static int mlxsw_sp_dummy_fid_init(struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_sp_vfid_op(mlxsw_sp, MLXSW_SP_DUMMY_FID, true);
+}
+
+static void mlxsw_sp_dummy_fid_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp_vfid_op(mlxsw_sp, MLXSW_SP_DUMMY_FID, false);
+}
+
 static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
@@ -3224,6 +3368,24 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_acl_init;
 	}
 
+	err = mlxsw_sp_counter_pool_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
+		goto err_counter_pool_init;
+	}
+
+	err = mlxsw_sp_dpipe_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
+		goto err_dpipe_init;
+	}
+
+	err = mlxsw_sp_dummy_fid_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to init dummy FID\n");
+		goto err_dummy_fid_init;
+	}
+
 	err = mlxsw_sp_ports_create(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n");
@@ -3233,6 +3395,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	return 0;
 
 err_ports_create:
+	mlxsw_sp_dummy_fid_fini(mlxsw_sp);
+err_dummy_fid_init:
+	mlxsw_sp_dpipe_fini(mlxsw_sp);
+err_dpipe_init:
+	mlxsw_sp_counter_pool_fini(mlxsw_sp);
+err_counter_pool_init:
 	mlxsw_sp_acl_fini(mlxsw_sp);
 err_acl_init:
 	mlxsw_sp_span_fini(mlxsw_sp);
@@ -3255,6 +3423,9 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 
 	mlxsw_sp_ports_remove(mlxsw_sp);
+	mlxsw_sp_dummy_fid_fini(mlxsw_sp);
+	mlxsw_sp_dpipe_fini(mlxsw_sp);
+	mlxsw_sp_counter_pool_fini(mlxsw_sp);
 	mlxsw_sp_acl_fini(mlxsw_sp);
 	mlxsw_sp_span_fini(mlxsw_sp);
 	mlxsw_sp_router_fini(mlxsw_sp);
@@ -3326,13 +3497,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev)
 	return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
 }
 
-static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
+static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data)
 {
-	struct mlxsw_sp_port **port = data;
+	struct mlxsw_sp_port **p_mlxsw_sp_port = data;
 	int ret = 0;
 
 	if (mlxsw_sp_port_dev_check(lower_dev)) {
-		*port = netdev_priv(lower_dev);
+		*p_mlxsw_sp_port = netdev_priv(lower_dev);
 		ret = 1;
 	}
 
@@ -3341,18 +3512,18 @@ static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
 
 static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
 {
-	struct mlxsw_sp_port *port;
+	struct mlxsw_sp_port *mlxsw_sp_port;
 
 	if (mlxsw_sp_port_dev_check(dev))
 		return netdev_priv(dev);
 
-	port = NULL;
-	netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port);
+	mlxsw_sp_port = NULL;
+	netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port);
 
-	return port;
+	return mlxsw_sp_port;
 }
 
-static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
+struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port;
 
@@ -3362,15 +3533,16 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
 
 static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
 {
-	struct mlxsw_sp_port *port;
+	struct mlxsw_sp_port *mlxsw_sp_port;
 
 	if (mlxsw_sp_port_dev_check(dev))
 		return netdev_priv(dev);
 
-	port = NULL;
-	netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port);
+	mlxsw_sp_port = NULL;
+	netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk,
+				      &mlxsw_sp_port);
 
-	return port;
+	return mlxsw_sp_port;
 }
 
 struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
@@ -3390,546 +3562,6 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
 	dev_put(mlxsw_sp_port->dev);
 }
 
-static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r,
-				       unsigned long event)
-{
-	switch (event) {
-	case NETDEV_UP:
-		if (!r)
-			return true;
-		r->ref_count++;
-		return false;
-	case NETDEV_DOWN:
-		if (r && --r->ref_count == 0)
-			return true;
-		/* It is possible we already removed the RIF ourselves
-		 * if it was assigned to a netdev that is now a bridge
-		 * or LAG slave.
-		 */
-		return false;
-	}
-
-	return false;
-}
-
-static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
-{
-	int i;
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
-		if (!mlxsw_sp->rifs[i])
-			return i;
-
-	return MLXSW_SP_INVALID_RIF;
-}
-
-static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
-					   bool *p_lagged, u16 *p_system_port)
-{
-	u8 local_port = mlxsw_sp_vport->local_port;
-
-	*p_lagged = mlxsw_sp_vport->lagged;
-	*p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
-}
-
-static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
-				    struct net_device *l3_dev, u16 rif,
-				    bool create)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	bool lagged = mlxsw_sp_vport->lagged;
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	u16 system_port;
-
-	mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif,
-			    l3_dev->mtu, l3_dev->dev_addr);
-
-	mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
-	mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
-				  mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
-
-static struct mlxsw_sp_fid *
-mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
-{
-	struct mlxsw_sp_fid *f;
-
-	f = kzalloc(sizeof(*f), GFP_KERNEL);
-	if (!f)
-		return NULL;
-
-	f->leave = mlxsw_sp_vport_rif_sp_leave;
-	f->ref_count = 0;
-	f->dev = l3_dev;
-	f->fid = fid;
-
-	return f;
-}
-
-static struct mlxsw_sp_rif *
-mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f)
-{
-	struct mlxsw_sp_rif *r;
-
-	r = kzalloc(sizeof(*r), GFP_KERNEL);
-	if (!r)
-		return NULL;
-
-	INIT_LIST_HEAD(&r->nexthop_list);
-	INIT_LIST_HEAD(&r->neigh_list);
-	ether_addr_copy(r->addr, l3_dev->dev_addr);
-	r->mtu = l3_dev->mtu;
-	r->ref_count = 1;
-	r->dev = l3_dev;
-	r->rif = rif;
-	r->f = f;
-
-	return r;
-}
-
-static struct mlxsw_sp_rif *
-mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
-			     struct net_device *l3_dev)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	struct mlxsw_sp_fid *f;
-	struct mlxsw_sp_rif *r;
-	u16 fid, rif;
-	int err;
-
-	rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
-	if (rif == MLXSW_SP_INVALID_RIF)
-		return ERR_PTR(-ERANGE);
-
-	err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true);
-	if (err)
-		return ERR_PTR(err);
-
-	fid = mlxsw_sp_rif_sp_to_fid(rif);
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
-	if (err)
-		goto err_rif_fdb_op;
-
-	f = mlxsw_sp_rfid_alloc(fid, l3_dev);
-	if (!f) {
-		err = -ENOMEM;
-		goto err_rfid_alloc;
-	}
-
-	r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
-	if (!r) {
-		err = -ENOMEM;
-		goto err_rif_alloc;
-	}
-
-	f->r = r;
-	mlxsw_sp->rifs[rif] = r;
-
-	return r;
-
-err_rif_alloc:
-	kfree(f);
-err_rfid_alloc:
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
-err_rif_fdb_op:
-	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
-	return ERR_PTR(err);
-}
-
-static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
-					  struct mlxsw_sp_rif *r)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	struct net_device *l3_dev = r->dev;
-	struct mlxsw_sp_fid *f = r->f;
-	u16 fid = f->fid;
-	u16 rif = r->rif;
-
-	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r);
-
-	mlxsw_sp->rifs[rif] = NULL;
-	f->r = NULL;
-
-	kfree(r);
-
-	kfree(f);
-
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
-
-	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
-}
-
-static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
-				      struct net_device *l3_dev)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	struct mlxsw_sp_rif *r;
-
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
-	if (!r) {
-		r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
-		if (IS_ERR(r))
-			return PTR_ERR(r);
-	}
-
-	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f);
-	r->f->ref_count++;
-
-	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid);
-
-	return 0;
-}
-
-static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
-{
-	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
-
-	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
-
-	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
-	if (--f->ref_count == 0)
-		mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r);
-}
-
-static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
-					 struct net_device *port_dev,
-					 unsigned long event, u16 vid)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
-	struct mlxsw_sp_port *mlxsw_sp_vport;
-
-	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
-	if (WARN_ON(!mlxsw_sp_vport))
-		return -EINVAL;
-
-	switch (event) {
-	case NETDEV_UP:
-		return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
-	case NETDEV_DOWN:
-		mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
-		break;
-	}
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
-					unsigned long event)
-{
-	if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev))
-		return 0;
-
-	return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
-}
-
-static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
-					 struct net_device *lag_dev,
-					 unsigned long event, u16 vid)
-{
-	struct net_device *port_dev;
-	struct list_head *iter;
-	int err;
-
-	netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
-		if (mlxsw_sp_port_dev_check(port_dev)) {
-			err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
-							    event, vid);
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
-				       unsigned long event)
-{
-	if (netif_is_bridge_port(lag_dev))
-		return 0;
-
-	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
-}
-
-static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
-						    struct net_device *l3_dev)
-{
-	u16 fid;
-
-	if (is_vlan_dev(l3_dev))
-		fid = vlan_dev_vlan_id(l3_dev);
-	else if (mlxsw_sp->master_bridge.dev == l3_dev)
-		fid = 1;
-	else
-		return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
-
-	return mlxsw_sp_fid_find(mlxsw_sp, fid);
-}
-
-static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
-{
-	return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
-	       MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
-}
-
-static u16 mlxsw_sp_flood_table_index_get(u16 fid)
-{
-	return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
-}
-
-static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
-					  bool set)
-{
-	enum mlxsw_flood_table_type table_type;
-	char *sftr_pl;
-	u16 index;
-	int err;
-
-	sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
-	if (!sftr_pl)
-		return -ENOMEM;
-
-	table_type = mlxsw_sp_flood_table_type_get(fid);
-	index = mlxsw_sp_flood_table_index_get(fid);
-	mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type,
-			    1, MLXSW_PORT_ROUTER_PORT, set);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
-
-	kfree(sftr_pl);
-	return err;
-}
-
-static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
-{
-	if (mlxsw_sp_fid_is_vfid(fid))
-		return MLXSW_REG_RITR_FID_IF;
-	else
-		return MLXSW_REG_RITR_VLAN_IF;
-}
-
-static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp,
-				  struct net_device *l3_dev,
-				  u16 fid, u16 rif,
-				  bool create)
-{
-	enum mlxsw_reg_ritr_if_type rif_type;
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-
-	rif_type = mlxsw_sp_rif_type_get(fid);
-	mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu,
-			    l3_dev->dev_addr);
-	mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
-				      struct net_device *l3_dev,
-				      struct mlxsw_sp_fid *f)
-{
-	struct mlxsw_sp_rif *r;
-	u16 rif;
-	int err;
-
-	rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
-	if (rif == MLXSW_SP_INVALID_RIF)
-		return -ERANGE;
-
-	err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
-	if (err)
-		return err;
-
-	err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
-	if (err)
-		goto err_rif_bridge_op;
-
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
-	if (err)
-		goto err_rif_fdb_op;
-
-	r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
-	if (!r) {
-		err = -ENOMEM;
-		goto err_rif_alloc;
-	}
-
-	f->r = r;
-	mlxsw_sp->rifs[rif] = r;
-
-	netdev_dbg(l3_dev, "RIF=%d created\n", rif);
-
-	return 0;
-
-err_rif_alloc:
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
-err_rif_fdb_op:
-	mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
-err_rif_bridge_op:
-	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
-	return err;
-}
-
-void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_rif *r)
-{
-	struct net_device *l3_dev = r->dev;
-	struct mlxsw_sp_fid *f = r->f;
-	u16 rif = r->rif;
-
-	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r);
-
-	mlxsw_sp->rifs[rif] = NULL;
-	f->r = NULL;
-
-	kfree(r);
-
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
-
-	mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
-
-	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
-
-	netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif);
-}
-
-static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
-					  struct net_device *br_dev,
-					  unsigned long event)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
-	struct mlxsw_sp_fid *f;
-
-	/* FID can either be an actual FID if the L3 device is the
-	 * VLAN-aware bridge or a VLAN device on top. Otherwise, the
-	 * L3 device is a VLAN-unaware bridge and we get a vFID.
-	 */
-	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
-	if (WARN_ON(!f))
-		return -EINVAL;
-
-	switch (event) {
-	case NETDEV_UP:
-		return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
-	case NETDEV_DOWN:
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
-		break;
-	}
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
-					unsigned long event)
-{
-	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
-	u16 vid = vlan_dev_vlan_id(vlan_dev);
-
-	if (mlxsw_sp_port_dev_check(real_dev))
-		return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
-						     vid);
-	else if (netif_is_lag_master(real_dev))
-		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
-						     vid);
-	else if (netif_is_bridge_master(real_dev) &&
-		 mlxsw_sp->master_bridge.dev == real_dev)
-		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
-						      event);
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-				   unsigned long event, void *ptr)
-{
-	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
-	struct net_device *dev = ifa->ifa_dev->dev;
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_rif *r;
-	int err = 0;
-
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
-
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!mlxsw_sp_rif_should_config(r, event))
-		goto out;
-
-	if (mlxsw_sp_port_dev_check(dev))
-		err = mlxsw_sp_inetaddr_port_event(dev, event);
-	else if (netif_is_lag_master(dev))
-		err = mlxsw_sp_inetaddr_lag_event(dev, event);
-	else if (netif_is_bridge_master(dev))
-		err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
-	else if (is_vlan_dev(dev))
-		err = mlxsw_sp_inetaddr_vlan_event(dev, event);
-
-out:
-	return notifier_from_errno(err);
-}
-
-static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif,
-			     const char *mac, int mtu)
-{
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	int err;
-
-	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
-	mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
-	mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
-{
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_rif *r;
-	int err;
-
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		return 0;
-
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!r)
-		return 0;
-
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false);
-	if (err)
-		return err;
-
-	err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu);
-	if (err)
-		goto err_rif_edit;
-
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true);
-	if (err)
-		goto err_rif_fdb_op;
-
-	ether_addr_copy(r->addr, dev->dev_addr);
-	r->mtu = dev->mtu;
-
-	netdev_dbg(dev, "Updated RIF=%d\n", r->rif);
-
-	return 0;
-
-err_rif_fdb_op:
-	mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu);
-err_rif_edit:
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true);
-	return err;
-}
-
 static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port,
 					 u16 fid)
 {
@@ -4220,7 +3852,7 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp,
 
 static void
 mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
-				  u16 lag_id)
+				  struct net_device *lag_dev, u16 lag_id)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 	struct mlxsw_sp_fid *f;
@@ -4238,6 +3870,7 @@ mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	mlxsw_sp_vport->lag_id = lag_id;
 	mlxsw_sp_vport->lagged = 1;
+	mlxsw_sp_vport->dev = lag_dev;
 }
 
 static void
@@ -4254,6 +3887,7 @@ mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port)
 	if (f)
 		f->leave(mlxsw_sp_vport);
 
+	mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
 	mlxsw_sp_vport->lagged = 0;
 }
 
@@ -4293,7 +3927,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 1;
 	lag->ref_count++;
 
-	mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id);
+	mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_dev, lag_id);
 
 	return 0;
 
@@ -4403,6 +4037,56 @@ static void mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
 }
 
+static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				 bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	enum mlxsw_reg_spms_state spms_state;
+	char *spms_pl;
+	u16 vid;
+	int err;
+
+	spms_state = enable ? MLXSW_REG_SPMS_STATE_FORWARDING :
+			      MLXSW_REG_SPMS_STATE_DISCARDING;
+
+	spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL);
+	if (!spms_pl)
+		return -ENOMEM;
+	mlxsw_reg_spms_pack(spms_pl, mlxsw_sp_port->local_port);
+
+	for (vid = 0; vid < VLAN_N_VID; vid++)
+		mlxsw_reg_spms_vid_pack(spms_pl, vid, spms_state);
+
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spms), spms_pl);
+	kfree(spms_pl);
+	return err;
+}
+
+static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err;
+
+	err = mlxsw_sp_port_stp_set(mlxsw_sp_port, true);
+	if (err)
+		return err;
+	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
+				     true, false);
+	if (err)
+		goto err_port_vlan_set;
+	return 0;
+
+err_port_vlan_set:
+	mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
+	return err;
+}
+
+static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
+			       false, false);
+	mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
+}
+
 static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 					       unsigned long event, void *ptr)
 {
@@ -4421,7 +4105,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 		upper_dev = info->upper_dev;
 		if (!is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(upper_dev) &&
-		    !netif_is_bridge_master(upper_dev))
+		    !netif_is_bridge_master(upper_dev) &&
+		    !netif_is_ovs_master(upper_dev))
 			return -EINVAL;
 		if (!info->linking)
 			break;
@@ -4438,6 +4123,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
 			return -EINVAL;
+		if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev))
+			return -EINVAL;
+		if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -4446,8 +4135,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 				err = mlxsw_sp_port_vlan_link(mlxsw_sp_port,
 							      upper_dev);
 			else
-				 mlxsw_sp_port_vlan_unlink(mlxsw_sp_port,
-							   upper_dev);
+				mlxsw_sp_port_vlan_unlink(mlxsw_sp_port,
+							  upper_dev);
 		} else if (netif_is_bridge_master(upper_dev)) {
 			if (info->linking)
 				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
@@ -4461,6 +4150,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 			else
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
+		} else if (netif_is_ovs_master(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
+			else
+				mlxsw_sp_port_ovs_leave(mlxsw_sp_port);
 		} else {
 			err = -EINVAL;
 			WARN_ON(1);
@@ -4552,8 +4246,8 @@ static void mlxsw_sp_master_bridge_vlan_unlink(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_fid *f;
 
 	f = mlxsw_sp_fid_find(mlxsw_sp, fid);
-	if (f && f->r)
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f && f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
 	if (f && --f->ref_count == 0)
 		mlxsw_sp_fid_destroy(mlxsw_sp, f);
 }
@@ -4564,33 +4258,40 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
 	struct netdev_notifier_changeupper_info *info;
 	struct net_device *upper_dev;
 	struct mlxsw_sp *mlxsw_sp;
-	int err;
+	int err = 0;
 
 	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
 	if (!mlxsw_sp)
 		return 0;
-	if (br_dev != mlxsw_sp->master_bridge.dev)
-		return 0;
 
 	info = ptr;
 
 	switch (event) {
-	case NETDEV_CHANGEUPPER:
+	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
 		if (!is_vlan_dev(upper_dev))
-			break;
-		if (info->linking) {
-			err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
-							       upper_dev);
-			if (err)
-				return err;
+			return -EINVAL;
+		if (is_vlan_dev(upper_dev) &&
+		    br_dev != mlxsw_sp->master_bridge.dev)
+			return -EINVAL;
+		break;
+	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (is_vlan_dev(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
+								       upper_dev);
+			else
+				mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp,
+								   upper_dev);
 		} else {
-			mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev);
+			err = -EINVAL;
+			WARN_ON(1);
 		}
 		break;
 	}
 
-	return 0;
+	return err;
 }
 
 static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp)
@@ -4657,8 +4358,8 @@ static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
 	clear_bit(vfid, mlxsw_sp->vfids.mapped);
 	list_del(&f->list);
 
-	if (f->r)
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
 
 	kfree(f);
 
@@ -4810,6 +4511,8 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev,
 	int err = 0;
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+	if (!mlxsw_sp_vport)
+		return 0;
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
@@ -4821,22 +4524,24 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev,
 		/* We can't have multiple VLAN interfaces configured on
 		 * the same port and being members in the same bridge.
 		 */
-		if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
+		if (netif_is_bridge_master(upper_dev) &&
+		    !mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
 						       upper_dev))
 			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (info->linking) {
-			if (WARN_ON(!mlxsw_sp_vport))
-				return -EINVAL;
-			err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
-							 upper_dev);
+		if (netif_is_bridge_master(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
+								 upper_dev);
+			else
+				mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
 		} else {
-			if (!mlxsw_sp_vport)
-				return 0;
-			mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
+			err = -EINVAL;
+			WARN_ON(1);
 		}
+		break;
 	}
 
 	return err;
@@ -4878,6 +4583,15 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr)
+{
+	struct netdev_notifier_changeupper_info *info = ptr;
+
+	if (event != NETDEV_PRECHANGEUPPER && event != NETDEV_CHANGEUPPER)
+		return false;
+	return netif_is_l3_master(info->upper_dev);
+}
+
 static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				    unsigned long event, void *ptr)
 {
@@ -4886,6 +4600,8 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 
 	if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
 		err = mlxsw_sp_netdevice_router_port_event(dev);
+	else if (mlxsw_sp_is_vrf_event(event, ptr))
+		err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr);
 	else if (mlxsw_sp_port_dev_check(dev))
 		err = mlxsw_sp_netdevice_port_event(dev, event, ptr);
 	else if (netif_is_lag_master(dev))
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 13ec85e7c392..0c23bc1e946d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -57,41 +57,21 @@
 #define MLXSW_SP_VFID_BASE VLAN_N_VID
 #define MLXSW_SP_VFID_MAX 1024	/* Bridged VLAN interfaces */
 
+#define MLXSW_SP_DUMMY_FID 15359
+
 #define MLXSW_SP_RFID_BASE 15360
-#define MLXSW_SP_INVALID_RIF 0xffff
 
 #define MLXSW_SP_MID_MAX 7000
 
 #define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
 
-#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
-#define MLXSW_SP_LPM_TREE_MAX 22
-#define MLXSW_SP_LPM_TREE_COUNT (MLXSW_SP_LPM_TREE_MAX - MLXSW_SP_LPM_TREE_MIN)
-
 #define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
 
-#define MLXSW_SP_BYTES_PER_CELL 96
-
-#define MLXSW_SP_BYTES_TO_CELLS(b) DIV_ROUND_UP(b, MLXSW_SP_BYTES_PER_CELL)
-#define MLXSW_SP_CELLS_TO_BYTES(c) (c * MLXSW_SP_BYTES_PER_CELL)
-
 #define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */
 #define MLXSW_SP_KVD_GRANULARITY 128
 
-/* Maximum delay buffer needed in case of PAUSE frames, in cells.
- * Assumes 100m cable and maximum MTU.
- */
-#define MLXSW_SP_PAUSE_DELAY 612
-
-#define MLXSW_SP_CELL_FACTOR 2	/* 2 * cell_size / (IPG + cell_size + 1) */
-
-static inline u16 mlxsw_sp_pfc_delay_get(int mtu, u16 delay)
-{
-	delay = MLXSW_SP_BYTES_TO_CELLS(DIV_ROUND_UP(delay, BITS_PER_BYTE));
-	return MLXSW_SP_CELL_FACTOR * delay + MLXSW_SP_BYTES_TO_CELLS(mtu);
-}
-
 struct mlxsw_sp_port;
+struct mlxsw_sp_rif;
 
 struct mlxsw_sp_upper {
 	struct net_device *dev;
@@ -103,21 +83,10 @@ struct mlxsw_sp_fid {
 	struct list_head list;
 	unsigned int ref_count;
 	struct net_device *dev;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	u16 fid;
 };
 
-struct mlxsw_sp_rif {
-	struct list_head nexthop_list;
-	struct list_head neigh_list;
-	struct net_device *dev;
-	unsigned int ref_count;
-	struct mlxsw_sp_fid *f;
-	unsigned char addr[ETH_ALEN];
-	int mtu;
-	u16 rif;
-};
-
 struct mlxsw_sp_mid {
 	struct list_head list;
 	unsigned char addr[ETH_ALEN];
@@ -138,17 +107,7 @@ static inline u16 mlxsw_sp_fid_to_vfid(u16 fid)
 
 static inline bool mlxsw_sp_fid_is_vfid(u16 fid)
 {
-	return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE;
-}
-
-static inline bool mlxsw_sp_fid_is_rfid(u16 fid)
-{
-	return fid >= MLXSW_SP_RFID_BASE;
-}
-
-static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif)
-{
-	return MLXSW_SP_RFID_BASE + rif;
+	return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_DUMMY_FID;
 }
 
 struct mlxsw_sp_sb_pr {
@@ -177,12 +136,15 @@ struct mlxsw_sp_sb_pm {
 #define MLXSW_SP_SB_POOL_COUNT	4
 #define MLXSW_SP_SB_TC_COUNT	8
 
+struct mlxsw_sp_sb_port {
+	struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
+	struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
+};
+
 struct mlxsw_sp_sb {
 	struct mlxsw_sp_sb_pr prs[2][MLXSW_SP_SB_POOL_COUNT];
-	struct {
-		struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
-		struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
-	} ports[MLXSW_PORT_MAX_PORTS];
+	struct mlxsw_sp_sb_port *ports;
+	u32 cell_size;
 };
 
 #define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE)
@@ -207,11 +169,9 @@ struct mlxsw_sp_fib;
 
 struct mlxsw_sp_vr {
 	u16 id; /* virtual router ID */
-	bool used;
-	enum mlxsw_sp_l3proto proto;
 	u32 tb_id; /* kernel fib table id */
-	struct mlxsw_sp_lpm_tree *lpm_tree;
-	struct mlxsw_sp_fib *fib;
+	unsigned int rif_count;
+	struct mlxsw_sp_fib *fib4;
 };
 
 enum mlxsw_sp_span_type {
@@ -253,12 +213,15 @@ struct mlxsw_sp_port_mall_tc_entry {
 };
 
 struct mlxsw_sp_router {
-	struct mlxsw_sp_lpm_tree lpm_trees[MLXSW_SP_LPM_TREE_COUNT];
 	struct mlxsw_sp_vr *vrs;
 	struct rhashtable neigh_ht;
 	struct rhashtable nexthop_group_ht;
 	struct rhashtable nexthop_ht;
 	struct {
+		struct mlxsw_sp_lpm_tree *trees;
+		unsigned int tree_count;
+	} lpm;
+	struct {
 		struct delayed_work dw;
 		unsigned long interval;	/* ms */
 	} neighs_update;
@@ -269,6 +232,7 @@ struct mlxsw_sp_router {
 };
 
 struct mlxsw_sp_acl;
+struct mlxsw_sp_counter_pool;
 
 struct mlxsw_sp {
 	struct {
@@ -296,7 +260,7 @@ struct mlxsw_sp {
 	u32 ageing_time;
 	struct mlxsw_sp_upper master_bridge;
 	struct mlxsw_sp_upper *lags;
-	u8 port_to_module[MLXSW_PORT_MAX_PORTS];
+	u8 *port_to_module;
 	struct mlxsw_sp_sb sb;
 	struct mlxsw_sp_router router;
 	struct mlxsw_sp_acl *acl;
@@ -304,6 +268,7 @@ struct mlxsw_sp {
 		DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE);
 	} kvdl;
 
+	struct mlxsw_sp_counter_pool *counter_pool;
 	struct {
 		struct mlxsw_sp_span_entry *entries;
 		int entries_count;
@@ -317,6 +282,18 @@ mlxsw_sp_lag_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 	return &mlxsw_sp->lags[lag_id];
 }
 
+static inline u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp,
+				       u32 cells)
+{
+	return mlxsw_sp->sb.cell_size * cells;
+}
+
+static inline u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp,
+				       u32 bytes)
+{
+	return DIV_ROUND_UP(bytes, mlxsw_sp->sb.cell_size);
+}
+
 struct mlxsw_sp_port_pcpu_stats {
 	u64			rx_packets;
 	u64			rx_bytes;
@@ -386,6 +363,7 @@ struct mlxsw_sp_port {
 };
 
 bool mlxsw_sp_port_dev_check(const struct net_device *dev);
+struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev);
 void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port);
 
@@ -497,19 +475,6 @@ mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-static inline struct mlxsw_sp_rif *
-mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev)
-{
-	int i;
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
-		if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
-			return mlxsw_sp->rifs[i];
-
-	return NULL;
-}
-
 enum mlxsw_sp_flood_table {
 	MLXSW_SP_FLOOD_TABLE_UC,
 	MLXSW_SP_FLOOD_TABLE_BC,
@@ -570,8 +535,6 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
 			bool adding);
 struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid);
 void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f);
-void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_rif *r);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
 			  bool dwrr, u8 dwrr_weight);
@@ -608,10 +571,16 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
 				   unsigned long event, void *ptr);
-void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_rif *r);
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr);
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_rif *rif);
+int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
+				 struct netdev_notifier_changeupper_info *info);
 
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count);
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
+			u32 *p_entry_index);
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
@@ -620,6 +589,8 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
 	struct mlxsw_afk_element_values values;
 	struct mlxsw_afa_block *act_block;
+	unsigned int counter_index;
+	bool counter_valid;
 };
 
 enum mlxsw_sp_acl_profile {
@@ -639,6 +610,8 @@ struct mlxsw_sp_acl_profile_ops {
 			void *ruleset_priv, void *rule_priv,
 			struct mlxsw_sp_acl_rule_info *rulei);
 	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+				 bool *activity);
 };
 
 struct mlxsw_sp_acl_ops {
@@ -679,6 +652,14 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule_info *rulei,
 			       struct net_device *out_dev);
+int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei,
+				u32 action, u16 vid, u16 proto, u8 prio);
+int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_rule_info *rulei);
+int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_rule_info *rulei,
+				   u16 fid);
 
 struct mlxsw_sp_acl_rule;
 
@@ -698,6 +679,9 @@ mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
 			 unsigned long cookie);
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule);
+int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule *rule,
+				u64 *packets, u64 *bytes, u64 *last_use);
 
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
@@ -708,5 +692,14 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
 			    __be16 protocol, struct tc_cls_flower_offload *f);
 void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
 			     struct tc_cls_flower_offload *f);
+int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
+			  struct tc_cls_flower_offload *f);
+int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
+			      unsigned int counter_index, u64 *packets,
+			      u64 *bytes);
+int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				unsigned int *p_counter_index);
+void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
+				unsigned int counter_index);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 8a18b3aa70dc..317f7b14627f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -39,6 +39,7 @@
 #include <linux/string.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <net/tc_act/tc_vlan.h>
 
 #include "reg.h"
 #include "core.h"
@@ -49,10 +50,17 @@
 #include "spectrum_acl_flex_keys.h"
 
 struct mlxsw_sp_acl {
+	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_afk *afk;
 	struct mlxsw_afa *afa;
 	const struct mlxsw_sp_acl_ops *ops;
 	struct rhashtable ruleset_ht;
+	struct list_head rules;
+	struct {
+		struct delayed_work dw;
+		unsigned long interval;	/* ms */
+#define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000
+	} rule_activity_update;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
@@ -79,9 +87,13 @@ struct mlxsw_sp_acl_ruleset {
 
 struct mlxsw_sp_acl_rule {
 	struct rhash_head ht_node; /* Member of rule HT */
+	struct list_head list;
 	unsigned long cookie; /* HT key */
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule_info *rulei;
+	u64 last_used;
+	u64 last_packets;
+	u64 last_bytes;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
@@ -237,6 +249,27 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
 }
 
+static int
+mlxsw_sp_acl_rulei_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &rulei->counter_index);
+	if (err)
+		return err;
+	rulei->counter_valid = true;
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_rulei_counter_free(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei)
+{
+	rulei->counter_valid = false;
+	mlxsw_sp_flow_counter_free(mlxsw_sp, rulei->counter_index);
+}
+
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
 {
@@ -335,6 +368,48 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 					  local_port, in_port);
 }
 
+int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei,
+				u32 action, u16 vid, u16 proto, u8 prio)
+{
+	u8 ethertype;
+
+	if (action == TCA_VLAN_ACT_MODIFY) {
+		switch (proto) {
+		case ETH_P_8021Q:
+			ethertype = 0;
+			break;
+		case ETH_P_8021AD:
+			ethertype = 1;
+			break;
+		default:
+			dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n",
+				proto);
+			return -EINVAL;
+		}
+
+		return mlxsw_afa_block_append_vlan_modify(rulei->act_block,
+							  vid, prio, ethertype);
+	} else {
+		dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n");
+		return -EINVAL;
+	}
+}
+
+int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return mlxsw_afa_block_append_counter(rulei->act_block,
+					      rulei->counter_index);
+}
+
+int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_rule_info *rulei,
+				   u16 fid)
+{
+	return mlxsw_afa_block_append_fid_set(rulei->act_block, fid);
+}
+
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
@@ -358,8 +433,14 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 		err = PTR_ERR(rule->rulei);
 		goto err_rulei_create;
 	}
+
+	err = mlxsw_sp_acl_rulei_counter_alloc(mlxsw_sp, rule->rulei);
+	if (err)
+		goto err_counter_alloc;
 	return rule;
 
+err_counter_alloc:
+	mlxsw_sp_acl_rulei_destroy(rule->rulei);
 err_rulei_create:
 	kfree(rule);
 err_alloc:
@@ -372,6 +453,7 @@ void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 
+	mlxsw_sp_acl_rulei_counter_free(mlxsw_sp, rule->rulei);
 	mlxsw_sp_acl_rulei_destroy(rule->rulei);
 	kfree(rule);
 	mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
@@ -393,6 +475,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_insert;
 
+	list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
 	return 0;
 
 err_rhashtable_insert:
@@ -406,6 +489,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
 
+	list_del(&rule->list);
 	rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node,
 			       mlxsw_sp_acl_rule_ht_params);
 	ops->rule_del(mlxsw_sp, rule->priv);
@@ -426,6 +510,90 @@ mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule)
 	return rule->rulei;
 }
 
+static int mlxsw_sp_acl_rule_activity_update(struct mlxsw_sp *mlxsw_sp,
+					     struct mlxsw_sp_acl_rule *rule)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
+	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
+	bool active;
+	int err;
+
+	err = ops->rule_activity_get(mlxsw_sp, rule->priv, &active);
+	if (err)
+		return err;
+	if (active)
+		rule->last_used = jiffies;
+	return 0;
+}
+
+static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
+{
+	struct mlxsw_sp_acl_rule *rule;
+	int err;
+
+	/* Protect internal structures from changes */
+	rtnl_lock();
+	list_for_each_entry(rule, &acl->rules, list) {
+		err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
+							rule);
+		if (err)
+			goto err_rule_update;
+	}
+	rtnl_unlock();
+	return 0;
+
+err_rule_update:
+	rtnl_unlock();
+	return err;
+}
+
+static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl)
+{
+	unsigned long interval = acl->rule_activity_update.interval;
+
+	mlxsw_core_schedule_dw(&acl->rule_activity_update.dw,
+			       msecs_to_jiffies(interval));
+}
+
+static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work)
+{
+	struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl,
+						rule_activity_update.dw.work);
+	int err;
+
+	err = mlxsw_sp_acl_rules_activity_update(acl);
+	if (err)
+		dev_err(acl->mlxsw_sp->bus_info->dev, "Could not update acl activity");
+
+	mlxsw_sp_acl_rule_activity_work_schedule(acl);
+}
+
+int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule *rule,
+				u64 *packets, u64 *bytes, u64 *last_use)
+
+{
+	struct mlxsw_sp_acl_rule_info *rulei;
+	u64 current_packets;
+	u64 current_bytes;
+	int err;
+
+	rulei = mlxsw_sp_acl_rule_rulei(rule);
+	err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index,
+					&current_packets, &current_bytes);
+	if (err)
+		return err;
+
+	*packets = current_packets - rule->last_packets;
+	*bytes = current_bytes - rule->last_bytes;
+	*last_use = rule->last_used;
+
+	rule->last_bytes = current_bytes;
+	rule->last_packets = current_packets;
+
+	return 0;
+}
+
 #define MLXSW_SP_KDVL_ACT_EXT_SIZE 1
 
 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
@@ -434,7 +602,6 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	struct mlxsw_sp *mlxsw_sp = priv;
 	char pefa_pl[MLXSW_REG_PEFA_LEN];
 	u32 kvdl_index;
-	int ret;
 	int err;
 
 	/* The first action set of a TCAM entry is stored directly in TCAM,
@@ -443,10 +610,10 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	if (is_first)
 		return 0;
 
-	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE);
-	if (ret < 0)
-		return ret;
-	kvdl_index = ret;
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE,
+				  &kvdl_index);
+	if (err)
+		return err;
 	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
 	if (err)
@@ -475,13 +642,11 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 	struct mlxsw_sp *mlxsw_sp = priv;
 	char ppbs_pl[MLXSW_REG_PPBS_LEN];
 	u32 kvdl_index;
-	int ret;
 	int err;
 
-	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1);
-	if (ret < 0)
-		return ret;
-	kvdl_index = ret;
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+	if (err)
+		return err;
 	mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
 	if (err)
@@ -518,7 +683,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	if (!acl)
 		return -ENOMEM;
 	mlxsw_sp->acl = acl;
-
+	acl->mlxsw_sp = mlxsw_sp;
 	acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						       ACL_FLEX_KEYS),
 				    mlxsw_sp_afk_blocks,
@@ -541,11 +706,18 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_rhashtable_init;
 
+	INIT_LIST_HEAD(&acl->rules);
 	err = acl_ops->init(mlxsw_sp, acl->priv);
 	if (err)
 		goto err_acl_ops_init;
 
 	acl->ops = acl_ops;
+
+	/* Create the delayed work for the rule activity_update */
+	INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
+			  mlxsw_sp_acl_rul_activity_update_work);
+	acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS;
+	mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0);
 	return 0;
 
 err_acl_ops_init:
@@ -564,7 +736,9 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	const struct mlxsw_sp_acl_ops *acl_ops = acl->ops;
 
+	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
 	acl_ops->fini(mlxsw_sp, acl->priv);
+	WARN_ON(!list_empty(&acl->rules));
 	rhashtable_destroy(&acl->ruleset_ht);
 	mlxsw_afa_destroy(acl->afa);
 	mlxsw_afk_destroy(acl->afk);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
index 82b81cf7f4a7..af7b7bad48df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
@@ -39,11 +39,15 @@
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
@@ -65,6 +69,8 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
 	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 7382832215fa..3a24289979d9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -561,6 +561,24 @@ mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
 }
 
+static int
+mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_tcam_region *region,
+					    unsigned int offset,
+					    bool *activity)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	int err;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
+			     region->tcam_region_info, offset);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	if (err)
+		return err;
+	*activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
+	return 0;
+}
+
 #define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
 
 static int
@@ -940,6 +958,19 @@ static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 }
 
+static int
+mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_entry *entry,
+				     bool *activity)
+{
+	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
+	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+
+	return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region,
+							   entry->parman_item.index,
+							   activity);
+}
+
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
 	MLXSW_AFK_ELEMENT_DMAC,
@@ -950,6 +981,8 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_DST_IP4,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
+	MLXSW_AFK_ELEMENT_VID,
+	MLXSW_AFK_ELEMENT_PCP,
 };
 
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = {
@@ -1046,6 +1079,16 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
 }
 
+static int
+mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
+					   void *rule_priv, bool *activity)
+{
+	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
+						    activity);
+}
+
 static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.ruleset_priv_size	= sizeof(struct mlxsw_sp_acl_tcam_flower_ruleset),
 	.ruleset_add		= mlxsw_sp_acl_tcam_flower_ruleset_add,
@@ -1055,6 +1098,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
+	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
 };
 
 static const struct mlxsw_sp_acl_profile_ops *
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index a7468262f118..997189cfe7fd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -162,8 +162,8 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 }
 
 static const u16 mlxsw_sp_pbs[] = {
-	[0] = 2 * MLXSW_SP_BYTES_TO_CELLS(ETH_FRAME_LEN),
-	[9] = 2 * MLXSW_SP_BYTES_TO_CELLS(MLXSW_PORT_MAX_MTU),
+	[0] = 2 * ETH_FRAME_LEN,
+	[9] = 2 * MLXSW_PORT_MAX_MTU,
 };
 
 #define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs)
@@ -171,20 +171,22 @@ static const u16 mlxsw_sp_pbs[] = {
 
 static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
 	int i;
 
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port,
 			    0xffff, 0xffff / 2);
 	for (i = 0; i < MLXSW_SP_PBS_LEN; i++) {
+		u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp_pbs[i]);
+
 		if (i == MLXSW_SP_PB_UNUSED)
 			continue;
-		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, mlxsw_sp_pbs[i]);
+		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size);
 	}
 	mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
 					 MLXSW_REG_PBMC_PORT_SHARED_BUF_IDX, 0);
-	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core,
-			       MLXSW_REG(pbmc), pbmc_pl);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
 }
 
 static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -209,11 +211,25 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port);
 }
 
-#define MLXSW_SP_SB_PR_INGRESS_SIZE				\
-	(15000000 - (2 * 20000 * MLXSW_PORT_MAX_PORTS))
+static int mlxsw_sp_sb_ports_init(struct mlxsw_sp *mlxsw_sp)
+{
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+
+	mlxsw_sp->sb.ports = kcalloc(max_ports, sizeof(struct mlxsw_sp_sb_port),
+				     GFP_KERNEL);
+	if (!mlxsw_sp->sb.ports)
+		return -ENOMEM;
+	return 0;
+}
+
+static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	kfree(mlxsw_sp->sb.ports);
+}
+
+#define MLXSW_SP_SB_PR_INGRESS_SIZE	12440000
 #define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
-#define MLXSW_SP_SB_PR_EGRESS_SIZE				\
-	(14000000 - (8 * 1500 * MLXSW_PORT_MAX_PORTS))
+#define MLXSW_SP_SB_PR_EGRESS_SIZE	13232000
 
 #define MLXSW_SP_SB_PR(_mode, _size)	\
 	{				\
@@ -223,18 +239,17 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_ingress[] = {
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_SIZE)),
+		       MLXSW_SP_SB_PR_INGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_MNG_SIZE)),
+		       MLXSW_SP_SB_PR_INGRESS_MNG_SIZE),
 };
 
 #define MLXSW_SP_SB_PRS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_ingress)
 
 static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_egress[] = {
-	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_EGRESS_SIZE)),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
@@ -251,11 +266,9 @@ static int __mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	for (i = 0; i < prs_len; i++) {
-		const struct mlxsw_sp_sb_pr *pr;
+		u32 size = mlxsw_sp_bytes_cells(mlxsw_sp, prs[i].size);
 
-		pr = &prs[i];
-		err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir,
-					   pr->mode, pr->size);
+		err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir, prs[i].mode, size);
 		if (err)
 			return err;
 	}
@@ -284,7 +297,7 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp)
 	}
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 8, 0),
+	MLXSW_SP_SB_CM(10000, 8, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
@@ -293,20 +306,20 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(20000), 1, 3),
+	MLXSW_SP_SB_CM(20000, 1, 3),
 };
 
 #define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress)
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
 	MLXSW_SP_SB_CM(0, 0, 0),
 	MLXSW_SP_SB_CM(0, 0, 0),
 	MLXSW_SP_SB_CM(0, 0, 0),
@@ -330,7 +343,7 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 0, 0),
+	MLXSW_SP_SB_CM(10000, 0, 0),
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
@@ -370,13 +383,17 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 	for (i = 0; i < cms_len; i++) {
 		const struct mlxsw_sp_sb_cm *cm;
+		u32 min_buff;
 
 		if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS)
 			continue; /* PG number 8 does not exist, skip it */
 		cm = &cms[i];
+		/* All pools are initialized using dynamic thresholds,
+		 * therefore 'max_buff' isn't specified in cells.
+		 */
+		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff);
 		err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, dir,
-					   cm->min_buff, cm->max_buff,
-					   cm->pool);
+					   min_buff, cm->max_buff, cm->pool);
 		if (err)
 			return err;
 	}
@@ -484,21 +501,21 @@ struct mlxsw_sp_sb_mm {
 	}
 
 static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = {
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
 };
 
 #define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms)
@@ -511,10 +528,15 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 
 	for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) {
 		const struct mlxsw_sp_sb_mm *mc;
+		u32 min_buff;
 
 		mc = &mlxsw_sp_sb_mms[i];
-		mlxsw_reg_sbmm_pack(sbmm_pl, i, mc->min_buff,
-				    mc->max_buff, mc->pool);
+		/* All pools are initialized using dynamic thresholds,
+		 * therefore 'max_buff' isn't specified in cells.
+		 */
+		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, mc->min_buff);
+		mlxsw_reg_sbmm_pack(sbmm_pl, i, min_buff, mc->max_buff,
+				    mc->pool);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbmm), sbmm_pl);
 		if (err)
 			return err;
@@ -522,32 +544,53 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
-#define MLXSW_SP_SB_SIZE (16 * 1024 * 1024)
-
 int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 {
+	u64 sb_size;
 	int err;
 
-	err = mlxsw_sp_sb_prs_init(mlxsw_sp);
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, CELL_SIZE))
+		return -EIO;
+	mlxsw_sp->sb.cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE);
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE))
+		return -EIO;
+	sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE);
+
+	err = mlxsw_sp_sb_ports_init(mlxsw_sp);
 	if (err)
 		return err;
+	err = mlxsw_sp_sb_prs_init(mlxsw_sp);
+	if (err)
+		goto err_sb_prs_init;
 	err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp);
 	if (err)
-		return err;
+		goto err_sb_cpu_port_sb_cms_init;
 	err = mlxsw_sp_sb_mms_init(mlxsw_sp);
 	if (err)
-		return err;
-	return devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0,
-				   MLXSW_SP_SB_SIZE,
-				   MLXSW_SP_SB_POOL_COUNT,
-				   MLXSW_SP_SB_POOL_COUNT,
-				   MLXSW_SP_SB_TC_COUNT,
-				   MLXSW_SP_SB_TC_COUNT);
+		goto err_sb_mms_init;
+	err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0, sb_size,
+				  MLXSW_SP_SB_POOL_COUNT,
+				  MLXSW_SP_SB_POOL_COUNT,
+				  MLXSW_SP_SB_TC_COUNT,
+				  MLXSW_SP_SB_TC_COUNT);
+	if (err)
+		goto err_devlink_sb_register;
+
+	return 0;
+
+err_devlink_sb_register:
+err_sb_mms_init:
+err_sb_cpu_port_sb_cms_init:
+err_sb_prs_init:
+	mlxsw_sp_sb_ports_fini(mlxsw_sp);
+	return err;
 }
 
 void mlxsw_sp_buffers_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	devlink_sb_unregister(priv_to_devlink(mlxsw_sp->core), 0);
+	mlxsw_sp_sb_ports_fini(mlxsw_sp);
 }
 
 int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -596,7 +639,7 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
 
 	pool_info->pool_type = (enum devlink_sb_pool_type) dir;
-	pool_info->size = MLXSW_SP_CELLS_TO_BYTES(pr->size);
+	pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size);
 	pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode;
 	return 0;
 }
@@ -606,9 +649,9 @@ int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
 			 enum devlink_sb_threshold_type threshold_type)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	u32 pool_size = mlxsw_sp_bytes_cells(mlxsw_sp, size);
 	u8 pool = pool_get(pool_index);
 	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
-	u32 pool_size = MLXSW_SP_BYTES_TO_CELLS(size);
 	enum mlxsw_reg_sbpr_mode mode;
 
 	if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE))
@@ -627,7 +670,7 @@ static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u8 pool,
 
 	if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC)
 		return max_buff - MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET;
-	return MLXSW_SP_CELLS_TO_BYTES(max_buff);
+	return mlxsw_sp_cells_bytes(mlxsw_sp, max_buff);
 }
 
 static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
@@ -645,7 +688,7 @@ static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
 			return -EINVAL;
 		*p_max_buff = val;
 	} else {
-		*p_max_buff = MLXSW_SP_BYTES_TO_CELLS(threshold);
+		*p_max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, threshold);
 	}
 	return 0;
 }
@@ -761,7 +804,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
 
 	masked_count = 0;
 	for (local_port = cb_ctx.local_port_1;
-	     local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	     local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
@@ -775,7 +818,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
 	}
 	masked_count = 0;
 	for (local_port = cb_ctx.local_port_1;
-	     local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	     local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
@@ -817,7 +860,7 @@ next_batch:
 		mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
 		mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
 	}
-	for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
@@ -847,7 +890,7 @@ do_query:
 				    cb_priv);
 	if (err)
 		goto out;
-	if (local_port < MLXSW_PORT_MAX_PORTS)
+	if (local_port < mlxsw_core_max_ports(mlxsw_core))
 		goto next_batch;
 
 out:
@@ -882,7 +925,7 @@ next_batch:
 		mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
 		mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
 	}
-	for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
@@ -908,7 +951,7 @@ do_query:
 				    &bulk_list, NULL, 0);
 	if (err)
 		goto out;
-	if (local_port < MLXSW_PORT_MAX_PORTS)
+	if (local_port < mlxsw_core_max_ports(mlxsw_core))
 		goto next_batch;
 
 out:
@@ -932,8 +975,8 @@ int mlxsw_sp_sb_occ_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
 	struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port,
 						       pool, dir);
 
-	*p_cur = MLXSW_SP_CELLS_TO_BYTES(pm->occ.cur);
-	*p_max = MLXSW_SP_CELLS_TO_BYTES(pm->occ.max);
+	*p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.cur);
+	*p_max = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.max);
 	return 0;
 }
 
@@ -951,7 +994,7 @@ int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 	struct mlxsw_sp_sb_cm *cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port,
 						       pg_buff, dir);
 
-	*p_cur = MLXSW_SP_CELLS_TO_BYTES(cm->occ.cur);
-	*p_max = MLXSW_SP_CELLS_TO_BYTES(cm->occ.max);
+	*p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, cm->occ.cur);
+	*p_max = mlxsw_sp_cells_bytes(mlxsw_sp, cm->occ.max);
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
new file mode 100644
index 000000000000..0f46775e0307
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
@@ -0,0 +1,207 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum_cnt.h"
+
+#define MLXSW_SP_COUNTER_POOL_BANK_SIZE 4096
+
+struct mlxsw_sp_counter_sub_pool {
+	unsigned int base_index;
+	unsigned int size;
+	unsigned int entry_size;
+	unsigned int bank_count;
+};
+
+struct mlxsw_sp_counter_pool {
+	unsigned int pool_size;
+	unsigned long *usage; /* Usage bitmap */
+	struct mlxsw_sp_counter_sub_pool *sub_pools;
+};
+
+static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = {
+	[MLXSW_SP_COUNTER_SUB_POOL_FLOW] = {
+		.bank_count = 6,
+	},
+	[MLXSW_SP_COUNTER_SUB_POOL_RIF] = {
+		.bank_count = 2,
+	}
+};
+
+static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp)
+{
+	unsigned int total_bank_config = 0;
+	unsigned int pool_size;
+	int i;
+
+	pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE);
+	/* Check config is valid, no bank over subscription */
+	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++)
+		total_bank_config += mlxsw_sp_counter_sub_pools[i].bank_count;
+	if (total_bank_config > pool_size / MLXSW_SP_COUNTER_POOL_BANK_SIZE + 1)
+		return -EINVAL;
+	return 0;
+}
+
+static int mlxsw_sp_counter_sub_pools_prepare(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+
+	/* Prepare generic flow pool*/
+	sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_FLOW];
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_PACKETS_BYTES))
+		return -EIO;
+	sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						  COUNTER_SIZE_PACKETS_BYTES);
+	/* Prepare erif pool*/
+	sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_RIF];
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_ROUTER_BASIC))
+		return -EIO;
+	sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						  COUNTER_SIZE_ROUTER_BASIC);
+	return 0;
+}
+
+int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+	struct mlxsw_sp_counter_pool *pool;
+	unsigned int base_index;
+	unsigned int map_size;
+	int i;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_POOL_SIZE))
+		return -EIO;
+
+	err = mlxsw_sp_counter_pool_validate(mlxsw_sp);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_counter_sub_pools_prepare(mlxsw_sp);
+	if (err)
+		return err;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return -ENOMEM;
+
+	pool->pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE);
+	map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long);
+
+	pool->usage = kzalloc(map_size, GFP_KERNEL);
+	if (!pool->usage) {
+		err = -ENOMEM;
+		goto err_usage_alloc;
+	}
+
+	pool->sub_pools = mlxsw_sp_counter_sub_pools;
+	/* Allocation is based on bank count which should be
+	 * specified for each sub pool statically.
+	 */
+	base_index = 0;
+	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) {
+		sub_pool = &pool->sub_pools[i];
+		sub_pool->size = sub_pool->bank_count *
+				 MLXSW_SP_COUNTER_POOL_BANK_SIZE;
+		sub_pool->base_index = base_index;
+		base_index += sub_pool->size;
+		/* The last bank can't be fully used */
+		if (sub_pool->base_index + sub_pool->size > pool->pool_size)
+			sub_pool->size = pool->pool_size - sub_pool->base_index;
+	}
+
+	mlxsw_sp->counter_pool = pool;
+	return 0;
+
+err_usage_alloc:
+	kfree(pool);
+	return err;
+}
+
+void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+
+	WARN_ON(find_first_bit(pool->usage, pool->pool_size) !=
+			       pool->pool_size);
+	kfree(pool->usage);
+	kfree(pool);
+}
+
+int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int *p_counter_index)
+{
+	struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+	unsigned int entry_index;
+	unsigned int stop_index;
+	int i;
+
+	sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id];
+	stop_index = sub_pool->base_index + sub_pool->size;
+	entry_index = sub_pool->base_index;
+
+	entry_index = find_next_zero_bit(pool->usage, stop_index, entry_index);
+	if (entry_index == stop_index)
+		return -ENOBUFS;
+	/* The sub-pools can contain non-integer number of entries
+	 * so we must check for overflow
+	 */
+	if (entry_index + sub_pool->entry_size > stop_index)
+		return -ENOBUFS;
+	for (i = 0; i < sub_pool->entry_size; i++)
+		__set_bit(entry_index + i, pool->usage);
+
+	*p_counter_index = entry_index;
+	return 0;
+}
+
+void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int counter_index)
+{
+	struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+	int i;
+
+	if (WARN_ON(counter_index >= pool->pool_size))
+		return;
+	sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id];
+	for (i = 0; i < sub_pool->entry_size; i++)
+		__clear_bit(counter_index + i, pool->usage);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
new file mode 100644
index 000000000000..fd34d0a01073
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
@@ -0,0 +1,54 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkdis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_CNT_H
+#define _MLXSW_SPECTRUM_CNT_H
+
+#include "spectrum.h"
+
+enum mlxsw_sp_counter_sub_pool_id {
+	MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+	MLXSW_SP_COUNTER_SUB_POOL_RIF,
+};
+
+int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int *p_counter_index);
+void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int counter_index);
+int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
new file mode 100644
index 000000000000..ea56f6ade6b4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -0,0 +1,351 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arakdis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <net/devlink.h>
+
+#include "spectrum.h"
+#include "spectrum_dpipe.h"
+#include "spectrum_router.h"
+
+enum mlxsw_sp_field_metadata_id {
+	MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+	MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+	MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+};
+
+static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = {
+	{ .name = "erif_port",
+	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+	  .bitwidth = 32,
+	  .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+	},
+	{ .name = "l3_forward",
+	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+	  .bitwidth = 1,
+	},
+	{ .name = "l3_drop",
+	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+	  .bitwidth = 1,
+	},
+};
+
+enum mlxsw_sp_dpipe_header_id {
+	MLXSW_SP_DPIPE_HEADER_METADATA,
+};
+
+static struct devlink_dpipe_header mlxsw_sp_dpipe_header_metadata = {
+	.name = "mlxsw_meta",
+	.id = MLXSW_SP_DPIPE_HEADER_METADATA,
+	.fields = mlxsw_sp_dpipe_fields_metadata,
+	.fields_count = ARRAY_SIZE(mlxsw_sp_dpipe_fields_metadata),
+};
+
+static struct devlink_dpipe_header *mlxsw_dpipe_headers[] = {
+	&mlxsw_sp_dpipe_header_metadata,
+};
+
+static struct devlink_dpipe_headers mlxsw_sp_dpipe_headers = {
+	.headers = mlxsw_dpipe_headers,
+	.headers_count = ARRAY_SIZE(mlxsw_dpipe_headers),
+};
+
+static int mlxsw_sp_dpipe_table_erif_actions_dump(void *priv,
+						  struct sk_buff *skb)
+{
+	struct devlink_dpipe_action action = {0};
+	int err;
+
+	action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action.header = &mlxsw_sp_dpipe_header_metadata;
+	action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD;
+
+	err = devlink_dpipe_action_put(skb, &action);
+	if (err)
+		return err;
+
+	action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action.header = &mlxsw_sp_dpipe_header_metadata;
+	action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP;
+
+	return devlink_dpipe_action_put(skb, &action);
+}
+
+static int mlxsw_sp_dpipe_table_erif_matches_dump(void *priv,
+						  struct sk_buff *skb)
+{
+	struct devlink_dpipe_match match = {0};
+
+	match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match.header = &mlxsw_sp_dpipe_header_metadata;
+	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+
+	return devlink_dpipe_match_put(skb, &match);
+}
+
+static void mlxsw_sp_erif_entry_clear(struct devlink_dpipe_entry *entry)
+{
+	unsigned int value_count, value_index;
+	struct devlink_dpipe_value *value;
+
+	value = entry->action_values;
+	value_count = entry->action_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+
+	value = entry->match_values;
+	value_count = entry->match_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+}
+
+static void
+mlxsw_sp_erif_match_action_prepare(struct devlink_dpipe_match *match,
+				   struct devlink_dpipe_action *action)
+{
+	action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action->header = &mlxsw_sp_dpipe_header_metadata;
+	action->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD;
+
+	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match->header = &mlxsw_sp_dpipe_header_metadata;
+	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+}
+
+static int mlxsw_sp_erif_entry_prepare(struct devlink_dpipe_entry *entry,
+				       struct devlink_dpipe_value *match_value,
+				       struct devlink_dpipe_match *match,
+				       struct devlink_dpipe_value *action_value,
+				       struct devlink_dpipe_action *action)
+{
+	entry->match_values = match_value;
+	entry->match_values_count = 1;
+
+	entry->action_values = action_value;
+	entry->action_values_count = 1;
+
+	match_value->match = match;
+	match_value->value_size = sizeof(u32);
+	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+	if (!match_value->value)
+		return -ENOMEM;
+
+	action_value->action = action;
+	action_value->value_size = sizeof(u32);
+	action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+	if (!action_value->value)
+		goto err_action_alloc;
+	return 0;
+
+err_action_alloc:
+	kfree(match_value->value);
+	return -ENOMEM;
+}
+
+static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp,
+				   struct devlink_dpipe_entry *entry,
+				   struct mlxsw_sp_rif *rif,
+				   bool counters_enabled)
+{
+	u32 *action_value;
+	u32 *rif_value;
+	u64 cnt;
+	int err;
+
+	/* Set Match RIF index */
+	rif_value = entry->match_values->value;
+	*rif_value = mlxsw_sp_rif_index(rif);
+	entry->match_values->mapping_value = mlxsw_sp_rif_dev_ifindex(rif);
+	entry->match_values->mapping_valid = true;
+
+	/* Set Action Forwarding */
+	action_value = entry->action_values->value;
+	*action_value = 1;
+
+	entry->counter_valid = false;
+	entry->counter = 0;
+	if (!counters_enabled)
+		return 0;
+
+	entry->index = mlxsw_sp_rif_index(rif);
+	err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif,
+					     MLXSW_SP_RIF_COUNTER_EGRESS,
+					     &cnt);
+	if (!err) {
+		entry->counter = cnt;
+		entry->counter_valid = true;
+	}
+	return 0;
+}
+
+static int
+mlxsw_sp_table_erif_entries_dump(void *priv, bool counters_enabled,
+				 struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink_dpipe_value match_value = {{0}}, action_value = {{0}};
+	struct devlink_dpipe_action action = {0};
+	struct devlink_dpipe_match match = {0};
+	struct devlink_dpipe_entry entry = {0};
+	struct mlxsw_sp *mlxsw_sp = priv;
+	unsigned int rif_count;
+	int i, j;
+	int err;
+
+	mlxsw_sp_erif_match_action_prepare(&match, &action);
+	err = mlxsw_sp_erif_entry_prepare(&entry, &match_value, &match,
+					  &action_value, &action);
+	if (err)
+		return err;
+
+	rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	rtnl_lock();
+	i = 0;
+start_again:
+	err = devlink_dpipe_entry_ctx_prepare(dump_ctx);
+	if (err)
+		return err;
+	j = 0;
+	for (; i < rif_count; i++) {
+		if (!mlxsw_sp->rifs[i])
+			continue;
+		err = mlxsw_sp_erif_entry_get(mlxsw_sp, &entry,
+					      mlxsw_sp->rifs[i],
+					      counters_enabled);
+		if (err)
+			goto err_entry_get;
+		err = devlink_dpipe_entry_ctx_append(dump_ctx, &entry);
+		if (err) {
+			if (err == -EMSGSIZE) {
+				if (!j)
+					goto err_entry_append;
+				break;
+			}
+			goto err_entry_append;
+		}
+		j++;
+	}
+
+	devlink_dpipe_entry_ctx_close(dump_ctx);
+	if (i != rif_count)
+		goto start_again;
+	rtnl_unlock();
+
+	mlxsw_sp_erif_entry_clear(&entry);
+	return 0;
+err_entry_append:
+err_entry_get:
+	rtnl_unlock();
+	mlxsw_sp_erif_entry_clear(&entry);
+	return err;
+}
+
+static int mlxsw_sp_table_erif_counters_update(void *priv, bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	int i;
+
+	rtnl_lock();
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
+		if (!mlxsw_sp->rifs[i])
+			continue;
+		if (enable)
+			mlxsw_sp_rif_counter_alloc(mlxsw_sp,
+						   mlxsw_sp->rifs[i],
+						   MLXSW_SP_RIF_COUNTER_EGRESS);
+		else
+			mlxsw_sp_rif_counter_free(mlxsw_sp,
+						  mlxsw_sp->rifs[i],
+						  MLXSW_SP_RIF_COUNTER_EGRESS);
+	}
+	rtnl_unlock();
+	return 0;
+}
+
+static struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
+	.matches_dump = mlxsw_sp_dpipe_table_erif_matches_dump,
+	.actions_dump = mlxsw_sp_dpipe_table_erif_actions_dump,
+	.entries_dump = mlxsw_sp_table_erif_entries_dump,
+	.counters_set_update = mlxsw_sp_table_erif_counters_update,
+};
+
+static int mlxsw_sp_dpipe_erif_table_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	u64 table_size;
+
+	table_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	return devlink_dpipe_table_register(devlink,
+					    MLXSW_SP_DPIPE_TABLE_NAME_ERIF,
+					    &mlxsw_sp_erif_ops,
+					    mlxsw_sp, table_size,
+					    false);
+}
+
+static void mlxsw_sp_dpipe_erif_table_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+	devlink_dpipe_table_unregister(devlink, MLXSW_SP_DPIPE_TABLE_NAME_ERIF);
+}
+
+int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	int err;
+
+	err = devlink_dpipe_headers_register(devlink,
+					     &mlxsw_sp_dpipe_headers);
+	if (err)
+		return err;
+	err = mlxsw_sp_dpipe_erif_table_init(mlxsw_sp);
+	if (err)
+		goto err_erif_register;
+	return 0;
+
+err_erif_register:
+	devlink_dpipe_headers_unregister(priv_to_devlink(mlxsw_sp->core));
+	return err;
+}
+
+void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+	mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp);
+	devlink_dpipe_headers_unregister(devlink);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
new file mode 100644
index 000000000000..d2089298cba3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -0,0 +1,43 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_PIPELINE_H_
+#define _MLXSW_PIPELINE_H_
+
+int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp);
+
+#define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
+
+#endif /* _MLXSW_PIPELINE_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 22ab42925377..7d87e23578a3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -39,6 +39,7 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
 
 #include "spectrum.h"
 #include "core_acl_flex_keys.h"
@@ -55,6 +56,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	if (tc_no_actions(exts))
 		return 0;
 
+	/* Count action is inserted first */
+	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei);
+	if (err)
+		return err;
+
 	tcf_exts_to_list(exts, &actions);
 	list_for_each_entry(a, &actions, list) {
 		if (is_tcf_gact_shot(a)) {
@@ -65,6 +71,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			int ifindex = tcf_mirred_ifindex(a);
 			struct net_device *out_dev;
 
+			err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei,
+							     MLXSW_SP_DUMMY_FID);
+			if (err)
+				return err;
+
 			out_dev = __dev_get_by_index(dev_net(dev), ifindex);
 			if (out_dev == dev)
 				out_dev = NULL;
@@ -73,6 +84,15 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 							 out_dev);
 			if (err)
 				return err;
+		} else if (is_tcf_vlan(a)) {
+			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
+			u32 action = tcf_vlan_action(a);
+			u8 prio = tcf_vlan_push_prio(a);
+			u16 vid = tcf_vlan_push_vid(a);
+
+			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
+							   action, vid,
+							   proto, prio);
 		} else {
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
@@ -173,7 +193,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n");
 		return -EOPNOTSUPP;
 	}
@@ -234,6 +255,27 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 					       sizeof(key->src));
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_VLAN,
+						  f->key);
+		struct flow_dissector_key_vlan *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_VLAN,
+						  f->mask);
+		if (mask->vlan_id != 0)
+			mlxsw_sp_acl_rulei_keymask_u32(rulei,
+						       MLXSW_AFK_ELEMENT_VID,
+						       key->vlan_id,
+						       mask->vlan_id);
+		if (mask->vlan_priority != 0)
+			mlxsw_sp_acl_rulei_keymask_u32(rulei,
+						       MLXSW_AFK_ELEMENT_PCP,
+						       key->vlan_priority,
+						       mask->vlan_priority);
+	}
+
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS)
 		mlxsw_sp_flower_parse_ipv4(rulei, f);
 
@@ -303,14 +345,58 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev,
 					   ingress,
 					   MLXSW_SP_ACL_PROFILE_FLOWER);
-	if (WARN_ON(IS_ERR(ruleset)))
+	if (IS_ERR(ruleset))
 		return;
 
 	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
-	if (!WARN_ON(!rule)) {
+	if (rule) {
 		mlxsw_sp_acl_rule_del(mlxsw_sp, rule);
 		mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
 	}
 
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 }
+
+int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
+			  struct tc_cls_flower_offload *f)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+	struct tc_action *a;
+	LIST_HEAD(actions);
+	u64 packets;
+	u64 lastuse;
+	u64 bytes;
+	int err;
+
+	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev,
+					   ingress,
+					   MLXSW_SP_ACL_PROFILE_FLOWER);
+	if (WARN_ON(IS_ERR(ruleset)))
+		return -EINVAL;
+
+	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
+	if (!rule)
+		return -EINVAL;
+
+	err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes,
+					  &lastuse);
+	if (err)
+		goto err_rule_get_stats;
+
+	preempt_disable();
+
+	tcf_exts_to_list(f->exts, &actions);
+	list_for_each_entry(a, &actions, list)
+		tcf_action_stats_update(a, bytes, packets, lastuse);
+
+	preempt_enable();
+
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+	return 0;
+
+err_rule_get_stats:
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index ac321e8e5c1a..26c26cd30c3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -45,7 +45,8 @@
 	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE)
 #define MLXSW_SP_CHUNK_MAX 32
 
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
+			u32 *p_entry_index)
 {
 	int entry_index;
 	int size;
@@ -72,7 +73,8 @@ int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
 
 		for (i = 0; i < type_entries; i++)
 			set_bit(entry_index + i, mlxsw_sp->kvdl.usage);
-		return entry_index;
+		*p_entry_index = entry_index;
+		return 0;
 	}
 	return -ENOBUFS;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index bd8de6b9be71..33cec1cc1642 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -41,14 +41,184 @@
 #include <linux/in6.h>
 #include <linux/notifier.h>
 #include <linux/inetdevice.h>
+#include <linux/netdevice.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
 #include <net/ip_fib.h>
+#include <net/fib_rules.h>
+#include <net/l3mdev.h>
 
 #include "spectrum.h"
 #include "core.h"
 #include "reg.h"
+#include "spectrum_cnt.h"
+#include "spectrum_dpipe.h"
+#include "spectrum_router.h"
+
+struct mlxsw_sp_rif {
+	struct list_head nexthop_list;
+	struct list_head neigh_list;
+	struct net_device *dev;
+	struct mlxsw_sp_fid *f;
+	unsigned char addr[ETH_ALEN];
+	int mtu;
+	u16 rif_index;
+	u16 vr_id;
+	unsigned int counter_ingress;
+	bool counter_ingress_valid;
+	unsigned int counter_egress;
+	bool counter_egress_valid;
+};
+
+static unsigned int *
+mlxsw_sp_rif_p_counter_get(struct mlxsw_sp_rif *rif,
+			   enum mlxsw_sp_rif_counter_dir dir)
+{
+	switch (dir) {
+	case MLXSW_SP_RIF_COUNTER_EGRESS:
+		return &rif->counter_egress;
+	case MLXSW_SP_RIF_COUNTER_INGRESS:
+		return &rif->counter_ingress;
+	}
+	return NULL;
+}
+
+static bool
+mlxsw_sp_rif_counter_valid_get(struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir)
+{
+	switch (dir) {
+	case MLXSW_SP_RIF_COUNTER_EGRESS:
+		return rif->counter_egress_valid;
+	case MLXSW_SP_RIF_COUNTER_INGRESS:
+		return rif->counter_ingress_valid;
+	}
+	return false;
+}
+
+static void
+mlxsw_sp_rif_counter_valid_set(struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir,
+			       bool valid)
+{
+	switch (dir) {
+	case MLXSW_SP_RIF_COUNTER_EGRESS:
+		rif->counter_egress_valid = valid;
+		break;
+	case MLXSW_SP_RIF_COUNTER_INGRESS:
+		rif->counter_ingress_valid = valid;
+		break;
+	}
+}
+
+static int mlxsw_sp_rif_counter_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+				     unsigned int counter_index, bool enable,
+				     enum mlxsw_sp_rif_counter_dir dir)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	bool is_egress = false;
+	int err;
+
+	if (dir == MLXSW_SP_RIF_COUNTER_EGRESS)
+		is_egress = true;
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_ritr_counter_pack(ritr_pl, counter_index, enable,
+				    is_egress);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_rif *rif,
+				   enum mlxsw_sp_rif_counter_dir dir, u64 *cnt)
+{
+	char ricnt_pl[MLXSW_REG_RICNT_LEN];
+	unsigned int *p_counter_index;
+	bool valid;
+	int err;
+
+	valid = mlxsw_sp_rif_counter_valid_get(rif, dir);
+	if (!valid)
+		return -EINVAL;
+
+	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+	if (!p_counter_index)
+		return -EINVAL;
+	mlxsw_reg_ricnt_pack(ricnt_pl, *p_counter_index,
+			     MLXSW_REG_RICNT_OPCODE_NOP);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl);
+	if (err)
+		return err;
+	*cnt = mlxsw_reg_ricnt_good_unicast_packets_get(ricnt_pl);
+	return 0;
+}
+
+static int mlxsw_sp_rif_counter_clear(struct mlxsw_sp *mlxsw_sp,
+				      unsigned int counter_index)
+{
+	char ricnt_pl[MLXSW_REG_RICNT_LEN];
+
+	mlxsw_reg_ricnt_pack(ricnt_pl, counter_index,
+			     MLXSW_REG_RICNT_OPCODE_CLEAR);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl);
+}
+
+int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir)
+{
+	unsigned int *p_counter_index;
+	int err;
+
+	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+	if (!p_counter_index)
+		return -EINVAL;
+	err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+				     p_counter_index);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_counter_clear(mlxsw_sp, *p_counter_index);
+	if (err)
+		goto err_counter_clear;
+
+	err = mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index,
+					*p_counter_index, true, dir);
+	if (err)
+		goto err_counter_edit;
+	mlxsw_sp_rif_counter_valid_set(rif, dir, true);
+	return 0;
+
+err_counter_edit:
+err_counter_clear:
+	mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+			      *p_counter_index);
+	return err;
+}
+
+void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir)
+{
+	unsigned int *p_counter_index;
+
+	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+	if (WARN_ON(!p_counter_index))
+		return;
+	mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index,
+				  *p_counter_index, false, dir);
+	mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+			      *p_counter_index);
+	mlxsw_sp_rif_counter_valid_set(rif, dir, false);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+			 const struct net_device *dev);
 
 #define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \
 	for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT)
@@ -89,12 +259,6 @@ mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1,
 }
 
 static void
-mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage)
-{
-	memset(prefix_usage, 0, sizeof(*prefix_usage));
-}
-
-static void
 mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage,
 			  unsigned char prefix_len)
 {
@@ -125,7 +289,7 @@ struct mlxsw_sp_fib_node {
 	struct list_head entry_list;
 	struct list_head list;
 	struct rhash_head ht_node;
-	struct mlxsw_sp_vr *vr;
+	struct mlxsw_sp_fib *fib;
 	struct mlxsw_sp_fib_key key;
 };
 
@@ -149,13 +313,17 @@ struct mlxsw_sp_fib_entry {
 struct mlxsw_sp_fib {
 	struct rhashtable ht;
 	struct list_head node_list;
+	struct mlxsw_sp_vr *vr;
+	struct mlxsw_sp_lpm_tree *lpm_tree;
 	unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT];
 	struct mlxsw_sp_prefix_usage prefix_usage;
+	enum mlxsw_sp_l3proto proto;
 };
 
 static const struct rhashtable_params mlxsw_sp_fib_ht_params;
 
-static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
+static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr,
+						enum mlxsw_sp_l3proto proto)
 {
 	struct mlxsw_sp_fib *fib;
 	int err;
@@ -167,6 +335,8 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
 	if (err)
 		goto err_rhashtable_init;
 	INIT_LIST_HEAD(&fib->node_list);
+	fib->proto = proto;
+	fib->vr = vr;
 	return fib;
 
 err_rhashtable_init:
@@ -177,24 +347,21 @@ err_rhashtable_init:
 static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib)
 {
 	WARN_ON(!list_empty(&fib->node_list));
+	WARN_ON(fib->lpm_tree);
 	rhashtable_destroy(&fib->ht);
 	kfree(fib);
 }
 
 static struct mlxsw_sp_lpm_tree *
-mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved)
+mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp)
 {
 	static struct mlxsw_sp_lpm_tree *lpm_tree;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
-		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
-		if (lpm_tree->ref_count == 0) {
-			if (one_reserved)
-				one_reserved = false;
-			else
-				return lpm_tree;
-		}
+	for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm.trees[i];
+		if (lpm_tree->ref_count == 0)
+			return lpm_tree;
 	}
 	return NULL;
 }
@@ -248,12 +415,12 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_lpm_tree *
 mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_prefix_usage *prefix_usage,
-			 enum mlxsw_sp_l3proto proto, bool one_reserved)
+			 enum mlxsw_sp_l3proto proto)
 {
 	struct mlxsw_sp_lpm_tree *lpm_tree;
 	int err;
 
-	lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved);
+	lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp);
 	if (!lpm_tree)
 		return ERR_PTR(-EBUSY);
 	lpm_tree->proto = proto;
@@ -283,13 +450,13 @@ static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_lpm_tree *
 mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
 		      struct mlxsw_sp_prefix_usage *prefix_usage,
-		      enum mlxsw_sp_l3proto proto, bool one_reserved)
+		      enum mlxsw_sp_l3proto proto)
 {
 	struct mlxsw_sp_lpm_tree *lpm_tree;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
-		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+	for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm.trees[i];
 		if (lpm_tree->ref_count != 0 &&
 		    lpm_tree->proto == proto &&
 		    mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
@@ -297,7 +464,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
 			goto inc_ref_count;
 	}
 	lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage,
-					    proto, one_reserved);
+					    proto);
 	if (IS_ERR(lpm_tree))
 		return lpm_tree;
 
@@ -314,15 +481,41 @@ static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
+#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
+
+static int mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_lpm_tree *lpm_tree;
+	u64 max_trees;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
-		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_LPM_TREES))
+		return -EIO;
+
+	max_trees = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_LPM_TREES);
+	mlxsw_sp->router.lpm.tree_count = max_trees - MLXSW_SP_LPM_TREE_MIN;
+	mlxsw_sp->router.lpm.trees = kcalloc(mlxsw_sp->router.lpm.tree_count,
+					     sizeof(struct mlxsw_sp_lpm_tree),
+					     GFP_KERNEL);
+	if (!mlxsw_sp->router.lpm.trees)
+		return -ENOMEM;
+
+	for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm.trees[i];
 		lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN;
 	}
+
+	return 0;
+}
+
+static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	kfree(mlxsw_sp->router.lpm.trees);
+}
+
+static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr)
+{
+	return !!vr->fib4;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
@@ -332,31 +525,31 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
 		vr = &mlxsw_sp->router.vrs[i];
-		if (!vr->used)
+		if (!mlxsw_sp_vr_is_used(vr))
 			return vr;
 	}
 	return NULL;
 }
 
 static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp,
-				     struct mlxsw_sp_vr *vr)
+				     const struct mlxsw_sp_fib *fib)
 {
 	char raltb_pl[MLXSW_REG_RALTB_LEN];
 
-	mlxsw_reg_raltb_pack(raltb_pl, vr->id,
-			     (enum mlxsw_reg_ralxx_protocol) vr->proto,
-			     vr->lpm_tree->id);
+	mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
+			     (enum mlxsw_reg_ralxx_protocol) fib->proto,
+			     fib->lpm_tree->id);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
 }
 
 static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_vr *vr)
+				       const struct mlxsw_sp_fib *fib)
 {
 	char raltb_pl[MLXSW_REG_RALTB_LEN];
 
 	/* Bind to tree 0 which is default */
-	mlxsw_reg_raltb_pack(raltb_pl, vr->id,
-			     (enum mlxsw_reg_ralxx_protocol) vr->proto, 0);
+	mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
+			     (enum mlxsw_reg_ralxx_protocol) fib->proto, 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
 }
 
@@ -369,8 +562,7 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
-					    u32 tb_id,
-					    enum mlxsw_sp_l3proto proto)
+					    u32 tb_id)
 {
 	struct mlxsw_sp_vr *vr;
 	int i;
@@ -379,69 +571,50 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
 		vr = &mlxsw_sp->router.vrs[i];
-		if (vr->used && vr->proto == proto && vr->tb_id == tb_id)
+		if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id)
 			return vr;
 	}
 	return NULL;
 }
 
+static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr,
+					    enum mlxsw_sp_l3proto proto)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return vr->fib4;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		BUG_ON(1);
+	}
+	return NULL;
+}
+
 static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
-					      unsigned char prefix_len,
-					      u32 tb_id,
-					      enum mlxsw_sp_l3proto proto)
+					      u32 tb_id)
 {
-	struct mlxsw_sp_prefix_usage req_prefix_usage;
-	struct mlxsw_sp_lpm_tree *lpm_tree;
 	struct mlxsw_sp_vr *vr;
-	int err;
 
 	vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
 	if (!vr)
 		return ERR_PTR(-EBUSY);
-	vr->fib = mlxsw_sp_fib_create();
-	if (IS_ERR(vr->fib))
-		return ERR_CAST(vr->fib);
-
-	vr->proto = proto;
+	vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(vr->fib4))
+		return ERR_CAST(vr->fib4);
 	vr->tb_id = tb_id;
-	mlxsw_sp_prefix_usage_zero(&req_prefix_usage);
-	mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
-					 proto, true);
-	if (IS_ERR(lpm_tree)) {
-		err = PTR_ERR(lpm_tree);
-		goto err_tree_get;
-	}
-	vr->lpm_tree = lpm_tree;
-	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
-	if (err)
-		goto err_tree_bind;
-
-	vr->used = true;
 	return vr;
-
-err_tree_bind:
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
-err_tree_get:
-	mlxsw_sp_fib_destroy(vr->fib);
-
-	return ERR_PTR(err);
 }
 
-static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_vr *vr)
+static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr)
 {
-	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
-	mlxsw_sp_fib_destroy(vr->fib);
-	vr->used = false;
+	mlxsw_sp_fib_destroy(vr->fib4);
+	vr->fib4 = NULL;
 }
 
 static int
-mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
+mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib,
 			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
 {
-	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+	struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree;
 	struct mlxsw_sp_lpm_tree *new_tree;
 	int err;
 
@@ -449,7 +622,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 		return 0;
 
 	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
-					 vr->proto, false);
+					 fib->proto);
 	if (IS_ERR(new_tree)) {
 		/* We failed to get a tree according to the required
 		 * prefix usage. However, the current tree might be still good
@@ -463,8 +636,8 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 	}
 
 	/* Prevent packet loss by overwriting existing binding */
-	vr->lpm_tree = new_tree;
-	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	fib->lpm_tree = new_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib);
 	if (err)
 		goto err_tree_bind;
 	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
@@ -472,53 +645,26 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 	return 0;
 
 err_tree_bind:
-	vr->lpm_tree = lpm_tree;
+	fib->lpm_tree = lpm_tree;
 	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
 	return err;
 }
 
-static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
-					   unsigned char prefix_len,
-					   u32 tb_id,
-					   enum mlxsw_sp_l3proto proto)
+static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id)
 {
 	struct mlxsw_sp_vr *vr;
-	int err;
 
 	tb_id = mlxsw_sp_fix_tb_id(tb_id);
-	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto);
-	if (!vr) {
-		vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto);
-		if (IS_ERR(vr))
-			return vr;
-	} else {
-		struct mlxsw_sp_prefix_usage req_prefix_usage;
-
-		mlxsw_sp_prefix_usage_cpy(&req_prefix_usage,
-					  &vr->fib->prefix_usage);
-		mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
-		/* Need to replace LPM tree in case new prefix is required. */
-		err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
-						 &req_prefix_usage);
-		if (err)
-			return ERR_PTR(err);
-	}
+	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id);
+	if (!vr)
+		vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id);
 	return vr;
 }
 
-static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr)
+static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr)
 {
-	/* Destroy virtual router entity in case the associated FIB is empty
-	 * and allow it to be used for other tables in future. Otherwise,
-	 * check if some prefix usage did not disappear and change tree if
-	 * that is the case. Note that in case new, smaller tree cannot be
-	 * allocated, the original one will be kept being used.
-	 */
-	if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage))
-		mlxsw_sp_vr_destroy(mlxsw_sp, vr);
-	else
-		mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
-					   &vr->fib->prefix_usage);
+	if (!vr->rif_count && list_empty(&vr->fib4->node_list))
+		mlxsw_sp_vr_destroy(vr);
 }
 
 static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp)
@@ -627,14 +773,14 @@ static struct mlxsw_sp_neigh_entry *
 mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	int err;
 
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
-	if (!r)
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
+	if (!rif)
 		return ERR_PTR(-EINVAL);
 
-	neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, r->rif);
+	neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, rif->rif_index);
 	if (!neigh_entry)
 		return ERR_PTR(-ENOMEM);
 
@@ -642,7 +788,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
 	if (err)
 		goto err_neigh_entry_insert;
 
-	list_add(&neigh_entry->rif_list_node, &r->neigh_list);
+	list_add(&neigh_entry->rif_list_node, &rif->neigh_list);
 
 	return neigh_entry;
 
@@ -1050,22 +1196,22 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
 }
 
 static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp,
-				    const struct mlxsw_sp_rif *r)
+				    const struct mlxsw_sp_rif *rif)
 {
 	char rauht_pl[MLXSW_REG_RAUHT_LEN];
 
 	mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL,
-			     r->rif, r->addr);
+			     rif->rif_index, rif->addr);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
 }
 
 static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-					 struct mlxsw_sp_rif *r)
+					 struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry, *tmp;
 
-	mlxsw_sp_neigh_rif_flush(mlxsw_sp, r);
-	list_for_each_entry_safe(neigh_entry, tmp, &r->neigh_list,
+	mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif);
+	list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list,
 				 rif_list_node)
 		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
 }
@@ -1082,7 +1228,7 @@ struct mlxsw_sp_nexthop {
 						*/
 	struct rhash_head ht_node;
 	struct mlxsw_sp_nexthop_key key;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	u8 should_offload:1, /* set indicates this neigh is connected and
 			      * should be put to KVD linear area of this group.
 			      */
@@ -1109,7 +1255,7 @@ struct mlxsw_sp_nexthop_group {
 	u16 ecmp_size;
 	u16 count;
 	struct mlxsw_sp_nexthop nexthops[0];
-#define nh_rif	nexthops[0].r
+#define nh_rif	nexthops[0].rif
 };
 
 static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = {
@@ -1171,7 +1317,7 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
-					     struct mlxsw_sp_vr *vr,
+					     const struct mlxsw_sp_fib *fib,
 					     u32 adj_index, u16 ecmp_size,
 					     u32 new_adj_index,
 					     u16 new_ecmp_size)
@@ -1179,8 +1325,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
 	char raleu_pl[MLXSW_REG_RALEU_LEN];
 
 	mlxsw_reg_raleu_pack(raleu_pl,
-			     (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id,
-			     adj_index, ecmp_size, new_adj_index,
+			     (enum mlxsw_reg_ralxx_protocol) fib->proto,
+			     fib->vr->id, adj_index, ecmp_size, new_adj_index,
 			     new_ecmp_size);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl);
 }
@@ -1190,14 +1336,14 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
 					  u32 old_adj_index, u16 old_ecmp_size)
 {
 	struct mlxsw_sp_fib_entry *fib_entry;
-	struct mlxsw_sp_vr *vr = NULL;
+	struct mlxsw_sp_fib *fib = NULL;
 	int err;
 
 	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
-		if (vr == fib_entry->fib_node->vr)
+		if (fib == fib_entry->fib_node->fib)
 			continue;
-		vr = fib_entry->fib_node->vr;
-		err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr,
+		fib = fib_entry->fib_node->fib;
+		err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib,
 							old_adj_index,
 							old_ecmp_size,
 							nh_grp->adj_index,
@@ -1280,7 +1426,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	bool old_adj_index_valid;
 	u32 old_adj_index;
 	u16 old_ecmp_size;
-	int ret;
 	int i;
 	int err;
 
@@ -1318,15 +1463,14 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		 */
 		goto set_trap;
 
-	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size);
-	if (ret < 0) {
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
+	if (err) {
 		/* We ran out of KVD linear space, just set the
 		 * trap and let everything flow through kernel.
 		 */
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n");
 		goto set_trap;
 	}
-	adj_index = ret;
 	old_adj_index_valid = nh_grp->adj_index_valid;
 	old_adj_index = nh_grp->adj_index;
 	old_ecmp_size = nh_grp->ecmp_size;
@@ -1399,22 +1543,22 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 }
 
 static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh,
-				      struct mlxsw_sp_rif *r)
+				      struct mlxsw_sp_rif *rif)
 {
-	if (nh->r)
+	if (nh->rif)
 		return;
 
-	nh->r = r;
-	list_add(&nh->rif_list_node, &r->nexthop_list);
+	nh->rif = rif;
+	list_add(&nh->rif_list_node, &rif->nexthop_list);
 }
 
 static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh)
 {
-	if (!nh->r)
+	if (!nh->rif)
 		return;
 
 	list_del(&nh->rif_list_node);
-	nh->r = NULL;
+	nh->rif = NULL;
 }
 
 static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp,
@@ -1505,7 +1649,7 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
 {
 	struct net_device *dev = fib_nh->nh_dev;
 	struct in_device *in_dev;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	int err;
 
 	nh->nh_grp = nh_grp;
@@ -1514,15 +1658,18 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
+	if (!dev)
+		return 0;
+
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 	    fib_nh->nh_flags & RTNH_F_LINKDOWN)
 		return 0;
 
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!r)
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
 		return 0;
-	mlxsw_sp_nexthop_rif_init(nh, r);
+	mlxsw_sp_nexthop_rif_init(nh, rif);
 
 	err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
 	if (err)
@@ -1548,7 +1695,7 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_nexthop_key key;
 	struct mlxsw_sp_nexthop *nh;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 
 	if (mlxsw_sp->router.aborted)
 		return;
@@ -1558,13 +1705,13 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
 	if (WARN_ON_ONCE(!nh))
 		return;
 
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
-	if (!r)
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
+	if (!rif)
 		return;
 
 	switch (event) {
 	case FIB_EVENT_NH_ADD:
-		mlxsw_sp_nexthop_rif_init(nh, r);
+		mlxsw_sp_nexthop_rif_init(nh, rif);
 		mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
 		break;
 	case FIB_EVENT_NH_DEL:
@@ -1577,11 +1724,11 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
 }
 
 static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-					   struct mlxsw_sp_rif *r)
+					   struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_nexthop *nh, *tmp;
 
-	list_for_each_entry_safe(nh, tmp, &r->nexthop_list, rif_list_node) {
+	list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) {
 		mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
 		mlxsw_sp_nexthop_rif_fini(nh);
 		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
@@ -1699,7 +1846,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 {
 	fib_entry->offloaded = true;
 
-	switch (fib_entry->fib_node->vr->proto) {
+	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		fib_info_offload_inc(fib_entry->nh_group->key.fi);
 		break;
@@ -1711,7 +1858,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 static void
 mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 {
-	switch (fib_entry->fib_node->vr->proto) {
+	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		fib_info_offload_dec(fib_entry->nh_group->key.fi);
 		break;
@@ -1751,8 +1898,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
 					 enum mlxsw_reg_ralue_op op)
 {
 	char ralue_pl[MLXSW_REG_RALUE_LEN];
+	struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
 	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
-	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
 	enum mlxsw_reg_ralue_trap_action trap_action;
 	u16 trap_id = 0;
 	u32 adjacency_index = 0;
@@ -1772,8 +1919,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_reg_ralue_pack4(ralue_pl,
-			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
-			      vr->id, fib_entry->fib_node->key.prefix_len,
+			      (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+			      fib->vr->id, fib_entry->fib_node->key.prefix_len,
 			      *p_dip);
 	mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id,
 					adjacency_index, ecmp_size);
@@ -1784,27 +1931,28 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp_fib_entry *fib_entry,
 					enum mlxsw_reg_ralue_op op)
 {
-	struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif;
+	struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif;
+	struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
 	enum mlxsw_reg_ralue_trap_action trap_action;
 	char ralue_pl[MLXSW_REG_RALUE_LEN];
 	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
-	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
 	u16 trap_id = 0;
-	u16 rif = 0;
+	u16 rif_index = 0;
 
 	if (mlxsw_sp_fib_entry_should_offload(fib_entry)) {
 		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
-		rif = r->rif;
+		rif_index = rif->rif_index;
 	} else {
 		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
 		trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
 	}
 
 	mlxsw_reg_ralue_pack4(ralue_pl,
-			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
-			      vr->id, fib_entry->fib_node->key.prefix_len,
+			      (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+			      fib->vr->id, fib_entry->fib_node->key.prefix_len,
 			      *p_dip);
-	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif);
+	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id,
+				       rif_index);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
 }
 
@@ -1812,13 +1960,13 @@ static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_fib_entry *fib_entry,
 				       enum mlxsw_reg_ralue_op op)
 {
+	struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
 	char ralue_pl[MLXSW_REG_RALUE_LEN];
 	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
-	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
 
 	mlxsw_reg_ralue_pack4(ralue_pl,
-			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
-			      vr->id, fib_entry->fib_node->key.prefix_len,
+			      (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+			      fib->vr->id, fib_entry->fib_node->key.prefix_len,
 			      *p_dip);
 	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
@@ -1845,7 +1993,7 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
 {
 	int err = -EINVAL;
 
-	switch (fib_entry->fib_node->vr->proto) {
+	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op);
 		break;
@@ -1877,17 +2025,29 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 {
 	struct fib_info *fi = fen_info->fi;
 
-	if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) {
+	switch (fen_info->type) {
+	case RTN_BROADCAST: /* fall through */
+	case RTN_LOCAL:
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
 		return 0;
-	}
-	if (fen_info->type != RTN_UNICAST)
-		return -EINVAL;
-	if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
+	case RTN_UNREACHABLE: /* fall through */
+	case RTN_BLACKHOLE: /* fall through */
+	case RTN_PROHIBIT:
+		/* Packets hitting these routes need to be trapped, but
+		 * can do so with a lower priority than packets directed
+		 * at the host, so use action type local instead of trap.
+		 */
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
-	else
-		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
-	return 0;
+		return 0;
+	case RTN_UNICAST:
+		if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
+			fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
+		else
+			fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
+		return 0;
+	default:
+		return -EINVAL;
+	}
 }
 
 static struct mlxsw_sp_fib_entry *
@@ -1996,7 +2156,7 @@ mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr,
 }
 
 static struct mlxsw_sp_fib_node *
-mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
+mlxsw_sp_fib_node_create(struct mlxsw_sp_fib *fib, const void *addr,
 			 size_t addr_len, unsigned char prefix_len)
 {
 	struct mlxsw_sp_fib_node *fib_node;
@@ -2006,18 +2166,15 @@ mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
 		return NULL;
 
 	INIT_LIST_HEAD(&fib_node->entry_list);
-	list_add(&fib_node->list, &vr->fib->node_list);
+	list_add(&fib_node->list, &fib->node_list);
 	memcpy(fib_node->key.addr, addr, addr_len);
 	fib_node->key.prefix_len = prefix_len;
-	mlxsw_sp_fib_node_insert(vr->fib, fib_node);
-	fib_node->vr = vr;
 
 	return fib_node;
 }
 
 static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node)
 {
-	mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node);
 	list_del(&fib_node->list);
 	WARN_ON(!list_empty(&fib_node->entry_list));
 	kfree(fib_node);
@@ -2034,7 +2191,7 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node,
 static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
 {
 	unsigned char prefix_len = fib_node->key.prefix_len;
-	struct mlxsw_sp_fib *fib = fib_node->vr->fib;
+	struct mlxsw_sp_fib *fib = fib_node->fib;
 
 	if (fib->prefix_ref_count[prefix_len]++ == 0)
 		mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len);
@@ -2043,32 +2200,98 @@ static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
 static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node)
 {
 	unsigned char prefix_len = fib_node->key.prefix_len;
-	struct mlxsw_sp_fib *fib = fib_node->vr->fib;
+	struct mlxsw_sp_fib *fib = fib_node->fib;
 
 	if (--fib->prefix_ref_count[prefix_len] == 0)
 		mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len);
 }
 
+static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_fib_node *fib_node,
+				  struct mlxsw_sp_fib *fib)
+{
+	struct mlxsw_sp_prefix_usage req_prefix_usage;
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	int err;
+
+	err = mlxsw_sp_fib_node_insert(fib, fib_node);
+	if (err)
+		return err;
+	fib_node->fib = fib;
+
+	mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage);
+	mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len);
+
+	if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) {
+		err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib,
+						 &req_prefix_usage);
+		if (err)
+			goto err_tree_check;
+	} else {
+		lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
+						 fib->proto);
+		if (IS_ERR(lpm_tree))
+			return PTR_ERR(lpm_tree);
+		fib->lpm_tree = lpm_tree;
+		err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib);
+		if (err)
+			goto err_tree_bind;
+	}
+
+	mlxsw_sp_fib_node_prefix_inc(fib_node);
+
+	return 0;
+
+err_tree_bind:
+	fib->lpm_tree = NULL;
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+err_tree_check:
+	fib_node->fib = NULL;
+	mlxsw_sp_fib_node_remove(fib, fib_node);
+	return err;
+}
+
+static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_fib_node *fib_node)
+{
+	struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree;
+	struct mlxsw_sp_fib *fib = fib_node->fib;
+
+	mlxsw_sp_fib_node_prefix_dec(fib_node);
+
+	if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) {
+		mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib);
+		fib->lpm_tree = NULL;
+		mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+	} else {
+		mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage);
+	}
+
+	fib_node->fib = NULL;
+	mlxsw_sp_fib_node_remove(fib, fib_node);
+}
+
 static struct mlxsw_sp_fib_node *
 mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
 		       const struct fib_entry_notifier_info *fen_info)
 {
 	struct mlxsw_sp_fib_node *fib_node;
+	struct mlxsw_sp_fib *fib;
 	struct mlxsw_sp_vr *vr;
 	int err;
 
-	vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id,
-			     MLXSW_SP_L3_PROTO_IPV4);
+	vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id);
 	if (IS_ERR(vr))
 		return ERR_CAST(vr);
+	fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4);
 
-	fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst,
+	fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst,
 					    sizeof(fen_info->dst),
 					    fen_info->dst_len);
 	if (fib_node)
 		return fib_node;
 
-	fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst,
+	fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst,
 					    sizeof(fen_info->dst),
 					    fen_info->dst_len);
 	if (!fib_node) {
@@ -2076,22 +2299,29 @@ mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
 		goto err_fib_node_create;
 	}
 
+	err = mlxsw_sp_fib_node_init(mlxsw_sp, fib_node, fib);
+	if (err)
+		goto err_fib_node_init;
+
 	return fib_node;
 
+err_fib_node_init:
+	mlxsw_sp_fib_node_destroy(fib_node);
 err_fib_node_create:
-	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	mlxsw_sp_vr_put(vr);
 	return ERR_PTR(err);
 }
 
 static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_fib_node *fib_node)
 {
-	struct mlxsw_sp_vr *vr = fib_node->vr;
+	struct mlxsw_sp_vr *vr = fib_node->fib->vr;
 
 	if (!list_empty(&fib_node->entry_list))
 		return;
+	mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node);
 	mlxsw_sp_fib_node_destroy(fib_node);
-	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	mlxsw_sp_vr_put(vr);
 }
 
 static struct mlxsw_sp_fib_entry *
@@ -2236,8 +2466,6 @@ static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_fib4_node_entry_add;
 
-	mlxsw_sp_fib_node_prefix_inc(fib_node);
-
 	return 0;
 
 err_fib4_node_entry_add:
@@ -2251,7 +2479,6 @@ mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
 
-	mlxsw_sp_fib_node_prefix_dec(fib_node);
 	mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry);
 	mlxsw_sp_fib4_node_list_remove(fib_entry);
 }
@@ -2340,9 +2567,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 {
 	char ralta_pl[MLXSW_REG_RALTA_LEN];
 	char ralst_pl[MLXSW_REG_RALST_LEN];
-	char raltb_pl[MLXSW_REG_RALTB_LEN];
-	char ralue_pl[MLXSW_REG_RALUE_LEN];
-	int err;
+	int i, err;
 
 	mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4,
 			     MLXSW_SP_LPM_TREE_MIN);
@@ -2355,16 +2580,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		return err;
 
-	mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4,
-			     MLXSW_SP_LPM_TREE_MIN);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
-	if (err)
-		return err;
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
+		struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i];
+		char raltb_pl[MLXSW_REG_RALTB_LEN];
+		char ralue_pl[MLXSW_REG_RALUE_LEN];
 
-	mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
-			      MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0);
-	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+		if (!mlxsw_sp_vr_is_used(vr))
+			continue;
+
+		mlxsw_reg_raltb_pack(raltb_pl, vr->id,
+				     MLXSW_REG_RALXX_PROTOCOL_IPV4,
+				     MLXSW_SP_LPM_TREE_MIN);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb),
+				      raltb_pl);
+		if (err)
+			return err;
+
+		mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
+				      MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0,
+				      0);
+		mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue),
+				      ralue_pl);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
@@ -2390,7 +2632,7 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
 static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
 				    struct mlxsw_sp_fib_node *fib_node)
 {
-	switch (fib_node->vr->proto) {
+	switch (fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node);
 		break;
@@ -2400,26 +2642,32 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
-static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
+static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_vr *vr,
+				  enum mlxsw_sp_l3proto proto)
 {
+	struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto);
 	struct mlxsw_sp_fib_node *fib_node, *tmp;
-	struct mlxsw_sp_vr *vr;
+
+	list_for_each_entry_safe(fib_node, tmp, &fib->node_list, list) {
+		bool do_break = &tmp->list == &fib->node_list;
+
+		mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
+		if (do_break)
+			break;
+	}
+}
+
+static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
+{
 	int i;
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
-		vr = &mlxsw_sp->router.vrs[i];
+		struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i];
 
-		if (!vr->used)
+		if (!mlxsw_sp_vr_is_used(vr))
 			continue;
-
-		list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list,
-					 list) {
-			bool do_break = &tmp->list == &vr->fib->node_list;
-
-			mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
-			if (do_break)
-				break;
-		}
+		mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4);
 	}
 }
 
@@ -2437,74 +2685,11 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
 }
 
-static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
-{
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	int err;
-
-	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-	if (WARN_ON_ONCE(err))
-		return err;
-
-	mlxsw_reg_ritr_enable_set(ritr_pl, false);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_rif *r)
-{
-	mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif);
-	mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r);
-	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r);
-}
-
-static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
-{
-	char rgcr_pl[MLXSW_REG_RGCR_LEN];
-	u64 max_rifs;
-	int err;
-
-	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
-		return -EIO;
-
-	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
-	mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *),
-				 GFP_KERNEL);
-	if (!mlxsw_sp->rifs)
-		return -ENOMEM;
-
-	mlxsw_reg_rgcr_pack(rgcr_pl, true);
-	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
-	if (err)
-		goto err_rgcr_fail;
-
-	return 0;
-
-err_rgcr_fail:
-	kfree(mlxsw_sp->rifs);
-	return err;
-}
-
-static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	char rgcr_pl[MLXSW_REG_RGCR_LEN];
-	int i;
-
-	mlxsw_reg_rgcr_pack(rgcr_pl, false);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
-		WARN_ON_ONCE(mlxsw_sp->rifs[i]);
-
-	kfree(mlxsw_sp->rifs);
-}
-
 struct mlxsw_sp_fib_event_work {
 	struct work_struct work;
 	union {
 		struct fib_entry_notifier_info fen_info;
+		struct fib_rule_notifier_info fr_info;
 		struct fib_nh_notifier_info fnh_info;
 	};
 	struct mlxsw_sp *mlxsw_sp;
@@ -2516,6 +2701,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
 	struct mlxsw_sp_fib_event_work *fib_work =
 		container_of(work, struct mlxsw_sp_fib_event_work, work);
 	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
+	struct fib_rule *rule;
 	bool replace, append;
 	int err;
 
@@ -2539,7 +2725,10 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
 		break;
 	case FIB_EVENT_RULE_ADD: /* fall through */
 	case FIB_EVENT_RULE_DEL:
-		mlxsw_sp_router_fib4_abort(mlxsw_sp);
+		rule = fib_work->fr_info.rule;
+		if (!fib4_rule_default(rule) && !rule->l3mdev)
+			mlxsw_sp_router_fib4_abort(mlxsw_sp);
+		fib_rule_put(rule);
 		break;
 	case FIB_EVENT_NH_ADD: /* fall through */
 	case FIB_EVENT_NH_DEL:
@@ -2582,6 +2771,11 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
+	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_DEL:
+		memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
+		fib_rule_get(fib_work->fr_info.rule);
+		break;
 	case FIB_EVENT_NH_ADD: /* fall through */
 	case FIB_EVENT_NH_DEL:
 		memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info));
@@ -2594,6 +2788,707 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+			 const struct net_device *dev)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+		if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
+			return mlxsw_sp->rifs[i];
+
+	return NULL;
+}
+
+static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	int err;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (WARN_ON_ONCE(err))
+		return err;
+
+	mlxsw_reg_ritr_enable_set(ritr_pl, false);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_rif *rif)
+{
+	mlxsw_sp_router_rif_disable(mlxsw_sp, rif->rif_index);
+	mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, rif);
+	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif);
+}
+
+static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif,
+				       const struct in_device *in_dev,
+				       unsigned long event)
+{
+	switch (event) {
+	case NETDEV_UP:
+		if (!rif)
+			return true;
+		return false;
+	case NETDEV_DOWN:
+		if (rif && !in_dev->ifa_list &&
+		    !netif_is_l3_slave(rif->dev))
+			return true;
+		/* It is possible we already removed the RIF ourselves
+		 * if it was assigned to a netdev that is now a bridge
+		 * or LAG slave.
+		 */
+		return false;
+	}
+
+	return false;
+}
+
+#define MLXSW_SP_INVALID_INDEX_RIF 0xffff
+static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+		if (!mlxsw_sp->rifs[i])
+			return i;
+
+	return MLXSW_SP_INVALID_INDEX_RIF;
+}
+
+static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
+					   bool *p_lagged, u16 *p_system_port)
+{
+	u8 local_port = mlxsw_sp_vport->local_port;
+
+	*p_lagged = mlxsw_sp_vport->lagged;
+	*p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
+}
+
+static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
+				    u16 vr_id, struct net_device *l3_dev,
+				    u16 rif_index, bool create)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	bool lagged = mlxsw_sp_vport->lagged;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	u16 system_port;
+
+	mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif_index,
+			    vr_id, l3_dev->mtu, l3_dev->dev_addr);
+
+	mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
+	mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
+				  mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+
+static u16 mlxsw_sp_rif_sp_to_fid(u16 rif_index)
+{
+	return MLXSW_SP_RFID_BASE + rif_index;
+}
+
+static struct mlxsw_sp_fid *
+mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	f->leave = mlxsw_sp_vport_rif_sp_leave;
+	f->ref_count = 0;
+	f->dev = l3_dev;
+	f->fid = fid;
+
+	return f;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_alloc(u16 rif_index, u16 vr_id, struct net_device *l3_dev,
+		   struct mlxsw_sp_fid *f)
+{
+	struct mlxsw_sp_rif *rif;
+
+	rif = kzalloc(sizeof(*rif), GFP_KERNEL);
+	if (!rif)
+		return NULL;
+
+	INIT_LIST_HEAD(&rif->nexthop_list);
+	INIT_LIST_HEAD(&rif->neigh_list);
+	ether_addr_copy(rif->addr, l3_dev->dev_addr);
+	rif->mtu = l3_dev->mtu;
+	rif->vr_id = vr_id;
+	rif->dev = l3_dev;
+	rif->rif_index = rif_index;
+	rif->f = f;
+
+	return rif;
+}
+
+u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif)
+{
+	return rif->rif_index;
+}
+
+int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
+{
+	return rif->dev->ifindex;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
+			     struct net_device *l3_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	u32 tb_id = l3mdev_fib_table(l3_dev);
+	struct mlxsw_sp_vr *vr;
+	struct mlxsw_sp_fid *f;
+	struct mlxsw_sp_rif *rif;
+	u16 fid, rif_index;
+	int err;
+
+	rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp);
+	if (rif_index == MLXSW_SP_INVALID_INDEX_RIF)
+		return ERR_PTR(-ERANGE);
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+	if (IS_ERR(vr))
+		return ERR_CAST(vr);
+
+	err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev,
+				       rif_index, true);
+	if (err)
+		goto err_vport_rif_sp_op;
+
+	fid = mlxsw_sp_rif_sp_to_fid(rif_index);
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	f = mlxsw_sp_rfid_alloc(fid, l3_dev);
+	if (!f) {
+		err = -ENOMEM;
+		goto err_rfid_alloc;
+	}
+
+	rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f);
+	if (!rif) {
+		err = -ENOMEM;
+		goto err_rif_alloc;
+	}
+
+	if (devlink_dpipe_table_counter_enabled(priv_to_devlink(mlxsw_sp->core),
+						MLXSW_SP_DPIPE_TABLE_NAME_ERIF)) {
+		err = mlxsw_sp_rif_counter_alloc(mlxsw_sp, rif,
+						 MLXSW_SP_RIF_COUNTER_EGRESS);
+		if (err)
+			netdev_dbg(mlxsw_sp_vport->dev,
+				   "Counter alloc Failed err=%d\n", err);
+	}
+
+	f->rif = rif;
+	mlxsw_sp->rifs[rif_index] = rif;
+	vr->rif_count++;
+
+	return rif;
+
+err_rif_alloc:
+	kfree(f);
+err_rfid_alloc:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+err_rif_fdb_op:
+	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index,
+				 false);
+err_vport_rif_sp_op:
+	mlxsw_sp_vr_put(vr);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
+					  struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id];
+	struct net_device *l3_dev = rif->dev;
+	struct mlxsw_sp_fid *f = rif->f;
+	u16 rif_index = rif->rif_index;
+	u16 fid = f->fid;
+
+	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+
+	mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS);
+	mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_INGRESS);
+
+	vr->rif_count--;
+	mlxsw_sp->rifs[rif_index] = NULL;
+	f->rif = NULL;
+
+	kfree(rif);
+
+	kfree(f);
+
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+
+	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index,
+				 false);
+	mlxsw_sp_vr_put(vr);
+}
+
+static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
+				      struct net_device *l3_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
+	if (!rif) {
+		rif = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
+		if (IS_ERR(rif))
+			return PTR_ERR(rif);
+	}
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, rif->f);
+	rif->f->ref_count++;
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", rif->f->fid);
+
+	return 0;
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+	if (--f->ref_count == 0)
+		mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->rif);
+}
+
+static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
+					 struct net_device *port_dev,
+					 unsigned long event, u16 vid)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return -EINVAL;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
+	case NETDEV_DOWN:
+		mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
+					unsigned long event)
+{
+	if (netif_is_bridge_port(port_dev) ||
+	    netif_is_lag_port(port_dev) ||
+	    netif_is_ovs_port(port_dev))
+		return 0;
+
+	return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
+}
+
+static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
+					 struct net_device *lag_dev,
+					 unsigned long event, u16 vid)
+{
+	struct net_device *port_dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
+		if (mlxsw_sp_port_dev_check(port_dev)) {
+			err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
+							    event, vid);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
+				       unsigned long event)
+{
+	if (netif_is_bridge_port(lag_dev))
+		return 0;
+
+	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+						    struct net_device *l3_dev)
+{
+	u16 fid;
+
+	if (is_vlan_dev(l3_dev))
+		fid = vlan_dev_vlan_id(l3_dev);
+	else if (mlxsw_sp->master_bridge.dev == l3_dev)
+		fid = 1;
+	else
+		return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
+
+	return mlxsw_sp_fid_find(mlxsw_sp, fid);
+}
+
+static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_core_max_ports(mlxsw_sp->core) + 1;
+}
+
+static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
+{
+	return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
+	       MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
+}
+
+static u16 mlxsw_sp_flood_table_index_get(u16 fid)
+{
+	return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
+}
+
+static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
+					  bool set)
+{
+	u8 router_port = mlxsw_sp_router_port(mlxsw_sp);
+	enum mlxsw_flood_table_type table_type;
+	char *sftr_pl;
+	u16 index;
+	int err;
+
+	sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
+	if (!sftr_pl)
+		return -ENOMEM;
+
+	table_type = mlxsw_sp_flood_table_type_get(fid);
+	index = mlxsw_sp_flood_table_index_get(fid);
+	mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type,
+			    1, router_port, set);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
+
+	kfree(sftr_pl);
+	return err;
+}
+
+static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
+{
+	if (mlxsw_sp_fid_is_vfid(fid))
+		return MLXSW_REG_RITR_FID_IF;
+	else
+		return MLXSW_REG_RITR_VLAN_IF;
+}
+
+static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, u16 vr_id,
+				  struct net_device *l3_dev,
+				  u16 fid, u16 rif,
+				  bool create)
+{
+	enum mlxsw_reg_ritr_if_type rif_type;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+
+	rif_type = mlxsw_sp_rif_type_get(fid);
+	mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, vr_id, l3_dev->mtu,
+			    l3_dev->dev_addr);
+	mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
+				      struct net_device *l3_dev,
+				      struct mlxsw_sp_fid *f)
+{
+	u32 tb_id = l3mdev_fib_table(l3_dev);
+	struct mlxsw_sp_rif *rif;
+	struct mlxsw_sp_vr *vr;
+	u16 rif_index;
+	int err;
+
+	rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp);
+	if (rif_index == MLXSW_SP_INVALID_INDEX_RIF)
+		return -ERANGE;
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+	if (IS_ERR(vr))
+		return PTR_ERR(vr);
+
+	err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
+	if (err)
+		goto err_port_flood_set;
+
+	err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid,
+				     rif_index, true);
+	if (err)
+		goto err_rif_bridge_op;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f);
+	if (!rif) {
+		err = -ENOMEM;
+		goto err_rif_alloc;
+	}
+
+	f->rif = rif;
+	mlxsw_sp->rifs[rif_index] = rif;
+	vr->rif_count++;
+
+	netdev_dbg(l3_dev, "RIF=%d created\n", rif_index);
+
+	return 0;
+
+err_rif_alloc:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+err_rif_fdb_op:
+	mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index,
+			       false);
+err_rif_bridge_op:
+	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+err_port_flood_set:
+	mlxsw_sp_vr_put(vr);
+	return err;
+}
+
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id];
+	struct net_device *l3_dev = rif->dev;
+	struct mlxsw_sp_fid *f = rif->f;
+	u16 rif_index = rif->rif_index;
+
+	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+
+	vr->rif_count--;
+	mlxsw_sp->rifs[rif_index] = NULL;
+	f->rif = NULL;
+
+	kfree(rif);
+
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+
+	mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index,
+			       false);
+
+	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+
+	mlxsw_sp_vr_put(vr);
+
+	netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif_index);
+}
+
+static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+					  struct net_device *br_dev,
+					  unsigned long event)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
+	struct mlxsw_sp_fid *f;
+
+	/* FID can either be an actual FID if the L3 device is the
+	 * VLAN-aware bridge or a VLAN device on top. Otherwise, the
+	 * L3 device is a VLAN-unaware bridge and we get a vFID.
+	 */
+	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+	if (WARN_ON(!f))
+		return -EINVAL;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
+	case NETDEV_DOWN:
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+					unsigned long event)
+{
+	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	u16 vid = vlan_dev_vlan_id(vlan_dev);
+
+	if (mlxsw_sp_port_dev_check(real_dev))
+		return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
+						     vid);
+	else if (netif_is_lag_master(real_dev))
+		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
+						     vid);
+	else if (netif_is_bridge_master(real_dev) &&
+		 mlxsw_sp->master_bridge.dev == real_dev)
+		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
+						      event);
+
+	return 0;
+}
+
+static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
+				     unsigned long event)
+{
+	if (mlxsw_sp_port_dev_check(dev))
+		return mlxsw_sp_inetaddr_port_event(dev, event);
+	else if (netif_is_lag_master(dev))
+		return mlxsw_sp_inetaddr_lag_event(dev, event);
+	else if (netif_is_bridge_master(dev))
+		return mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
+	else if (is_vlan_dev(dev))
+		return mlxsw_sp_inetaddr_vlan_event(dev, event);
+	else
+		return 0;
+}
+
+int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
+	struct net_device *dev = ifa->ifa_dev->dev;
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err = 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		goto out;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!mlxsw_sp_rif_should_config(rif, ifa->ifa_dev, event))
+		goto out;
+
+	err = __mlxsw_sp_inetaddr_event(dev, event);
+out:
+	return notifier_from_errno(err);
+}
+
+static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+			     const char *mac, int mtu)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	int err;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
+	mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
+	mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
+{
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
+		return 0;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, false);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, dev->dev_addr,
+				dev->mtu);
+	if (err)
+		goto err_rif_edit;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, rif->f->fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	ether_addr_copy(rif->addr, dev->dev_addr);
+	rif->mtu = dev->mtu;
+
+	netdev_dbg(dev, "Updated RIF=%d\n", rif->rif_index);
+
+	return 0;
+
+err_rif_fdb_op:
+	mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu);
+err_rif_edit:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, true);
+	return err;
+}
+
+static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
+				  struct net_device *l3_dev)
+{
+	struct mlxsw_sp_rif *rif;
+
+	/* If netdev is already associated with a RIF, then we need to
+	 * destroy it and create a new one with the new virtual router ID.
+	 */
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
+	if (rif)
+		__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN);
+
+	return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP);
+}
+
+static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
+				    struct net_device *l3_dev)
+{
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
+	if (!rif)
+		return;
+	__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN);
+}
+
+int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
+				 struct netdev_notifier_changeupper_info *info)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
+	int err = 0;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		return 0;
+	case NETDEV_CHANGEUPPER:
+		if (info->linking)
+			err = mlxsw_sp_port_vrf_join(mlxsw_sp, l3_dev);
+		else
+			mlxsw_sp_port_vrf_leave(mlxsw_sp, l3_dev);
+		break;
+	}
+
+	return err;
+}
+
 static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
 {
 	struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
@@ -2606,6 +3501,48 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
 	mlxsw_sp_router_fib_flush(mlxsw_sp);
 }
 
+static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
+{
+	char rgcr_pl[MLXSW_REG_RGCR_LEN];
+	u64 max_rifs;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
+		return -EIO;
+
+	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *),
+				 GFP_KERNEL);
+	if (!mlxsw_sp->rifs)
+		return -ENOMEM;
+
+	mlxsw_reg_rgcr_pack(rgcr_pl, true);
+	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
+	if (err)
+		goto err_rgcr_fail;
+
+	return 0;
+
+err_rgcr_fail:
+	kfree(mlxsw_sp->rifs);
+	return err;
+}
+
+static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	char rgcr_pl[MLXSW_REG_RGCR_LEN];
+	int i;
+
+	mlxsw_reg_rgcr_pack(rgcr_pl, false);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+		WARN_ON_ONCE(mlxsw_sp->rifs[i]);
+
+	kfree(mlxsw_sp->rifs);
+}
+
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
 	int err;
@@ -2625,7 +3562,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_nexthop_group_ht_init;
 
-	mlxsw_sp_lpm_init(mlxsw_sp);
+	err = mlxsw_sp_lpm_init(mlxsw_sp);
+	if (err)
+		goto err_lpm_init;
+
 	err = mlxsw_sp_vrs_init(mlxsw_sp);
 	if (err)
 		goto err_vrs_init;
@@ -2647,6 +3587,8 @@ err_register_fib_notifier:
 err_neigh_init:
 	mlxsw_sp_vrs_fini(mlxsw_sp);
 err_vrs_init:
+	mlxsw_sp_lpm_fini(mlxsw_sp);
+err_lpm_init:
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
 err_nexthop_group_ht_init:
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
@@ -2660,6 +3602,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 	unregister_fib_notifier(&mlxsw_sp->fib_nb);
 	mlxsw_sp_neigh_fini(mlxsw_sp);
 	mlxsw_sp_vrs_fini(mlxsw_sp);
+	mlxsw_sp_lpm_fini(mlxsw_sp);
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
 	__mlxsw_sp_router_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
new file mode 100644
index 000000000000..c3095fef6697
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -0,0 +1,58 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_ROUTER_H_
+#define _MLXSW_ROUTER_H_
+
+#include "spectrum.h"
+
+enum mlxsw_sp_rif_counter_dir {
+	MLXSW_SP_RIF_COUNTER_INGRESS,
+	MLXSW_SP_RIF_COUNTER_EGRESS,
+};
+
+u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_rif *rif,
+				   enum mlxsw_sp_rif_counter_dir dir,
+				   u64 *cnt);
+void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir);
+int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir);
+
+#endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 598727d578c1..0d8411f1f954 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -568,8 +568,8 @@ void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f)
 
 	list_del(&f->list);
 
-	if (f->r)
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
 
 	kfree(f);
 
@@ -745,27 +745,6 @@ err_port_allow_untagged_set:
 	return err;
 }
 
-static int __mlxsw_sp_port_vlans_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				     u16 vid_begin, u16 vid_end, bool is_member,
-				     bool untagged)
-{
-	u16 vid, vid_e;
-	int err;
-
-	for (vid = vid_begin; vid <= vid_end;
-	     vid += MLXSW_REG_SPVM_REC_MAX_COUNT) {
-		vid_e = min((u16) (vid + MLXSW_REG_SPVM_REC_MAX_COUNT - 1),
-			    vid_end);
-
-		err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid_e,
-					     is_member, untagged);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 static int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port,
 					  u16 vid_begin, u16 vid_end,
 					  bool learn_enable)
@@ -804,8 +783,8 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		return err;
 	}
 
-	err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end,
-					true, flag_untagged);
+	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid_begin, vid_end,
+				     true, flag_untagged);
 	if (err) {
 		netdev_err(dev, "Unable to add VIDs %d-%d\n", vid_begin,
 			   vid_end);
@@ -863,8 +842,8 @@ err_port_vid_learning_set:
 	if (old_pvid != mlxsw_sp_port->pvid)
 		mlxsw_sp_port_pvid_set(mlxsw_sp_port, old_pvid);
 err_port_pvid_set:
-	__mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false,
-				  false);
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid_begin, vid_end,
+			       false, false);
 err_port_vlans_set:
 	mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
 	return err;
@@ -1012,7 +991,7 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
 
 	mlxsw_reg_smid_pack(smid_pl, mid, mlxsw_sp_port->local_port, add);
 	if (clear_all_ports) {
-		for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+		for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
 			if (mlxsw_sp->ports[i])
 				mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
 	}
@@ -1171,8 +1150,8 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (pvid >= vid_begin && pvid <= vid_end)
 		mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0);
 
-	__mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false,
-				  false);
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid_begin, vid_end,
+			       false, false);
 
 	mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index ec1e886d4566..3b0f72455681 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1321,7 +1321,7 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
 {
 	int i;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+	for (i = 1; i < mlxsw_core_max_ports(mlxsw_sx->core); i++)
 		if (mlxsw_sx_port_created(mlxsw_sx, i))
 			mlxsw_sx_port_remove(mlxsw_sx, i);
 	kfree(mlxsw_sx->ports);
@@ -1329,17 +1329,18 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
 
 static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sx->core);
 	size_t alloc_size;
 	u8 module, width;
 	int i;
 	int err;
 
-	alloc_size = sizeof(struct mlxsw_sx_port *) * MLXSW_PORT_MAX_PORTS;
+	alloc_size = sizeof(struct mlxsw_sx_port *) * max_ports;
 	mlxsw_sx->ports = kzalloc(alloc_size, GFP_KERNEL);
 	if (!mlxsw_sx->ports)
 		return -ENOMEM;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
+	for (i = 1; i < max_ports; i++) {
 		err = mlxsw_sx_port_module_info_get(mlxsw_sx, i, &module,
 						    &width);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 02ea48b15eb5..e008fdbed20f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -55,6 +55,7 @@ enum {
 	MLXSW_TRAP_ID_IGMP_V2_LEAVE = 0x33,
 	MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34,
 	MLXSW_TRAP_ID_PKT_SAMPLE = 0x38,
+	MLXSW_TRAP_ID_FID_MISS = 0x3D,
 	MLXSW_TRAP_ID_ARPBC = 0x50,
 	MLXSW_TRAP_ID_ARPUC = 0x51,
 	MLXSW_TRAP_ID_MTUERROR = 0x52,
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 279ee4612981..20358f87de57 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -212,25 +212,6 @@ static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val)
 }
 
 /**
- * ks8851_rx_1msg - select whether to use one or two messages for spi read
- * @ks: The device structure
- *
- * Return whether to generate a single message with a tx and rx buffer
- * supplied to spi_sync(), or alternatively send the tx and rx buffers
- * as separate messages.
- *
- * Depending on the hardware in use, a single message may be more efficient
- * on interrupts or work done by the driver.
- *
- * This currently always returns true until we add some per-device data passed
- * from the platform code to specify which mode is better.
- */
-static inline bool ks8851_rx_1msg(struct ks8851_net *ks)
-{
-	return true;
-}
-
-/**
  * ks8851_rdreg - issue read register command and return the data
  * @ks: The device state
  * @op: The register address and byte enables in message format.
@@ -251,14 +232,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 
 	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
 
-	if (ks8851_rx_1msg(ks)) {
-		msg = &ks->spi_msg1;
-		xfer = &ks->spi_xfer1;
-
-		xfer->tx_buf = txb;
-		xfer->rx_buf = trx;
-		xfer->len = rxl + 2;
-	} else {
+	if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
 		msg = &ks->spi_msg2;
 		xfer = ks->spi_xfer2;
 
@@ -270,15 +244,22 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 		xfer->tx_buf = NULL;
 		xfer->rx_buf = trx;
 		xfer->len = rxl;
+	} else {
+		msg = &ks->spi_msg1;
+		xfer = &ks->spi_xfer1;
+
+		xfer->tx_buf = txb;
+		xfer->rx_buf = trx;
+		xfer->len = rxl + 2;
 	}
 
 	ret = spi_sync(ks->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "read: spi_sync() failed\n");
-	else if (ks8851_rx_1msg(ks))
-		memcpy(rxb, trx + 2, rxl);
-	else
+	else if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
 		memcpy(rxb, trx, rxl);
+	else
+		memcpy(rxb, trx + 2, rxl);
 }
 
 /**
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 06c9f4100cb9..c0d7d5eec7e7 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -25,6 +25,7 @@
 #include <linux/of_irq.h>
 #include <linux/crc32.h>
 #include <linux/crc32c.h>
+#include <linux/circ_buf.h>
 
 #include "moxart_ether.h"
 
@@ -227,8 +228,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 		if (desc0 & (RX_DESC0_ERR | RX_DESC0_CRC_ERR | RX_DESC0_FTL |
 			     RX_DESC0_RUNT | RX_DESC0_ODD_NB)) {
 			net_dbg_ratelimited("packet error\n");
-			priv->stats.rx_dropped++;
-			priv->stats.rx_errors++;
+			ndev->stats.rx_dropped++;
+			ndev->stats.rx_errors++;
 			goto rx_next;
 		}
 
@@ -244,8 +245,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 
 		if (unlikely(!skb)) {
 			net_dbg_ratelimited("netdev_alloc_skb_ip_align failed\n");
-			priv->stats.rx_dropped++;
-			priv->stats.rx_errors++;
+			ndev->stats.rx_dropped++;
+			ndev->stats.rx_errors++;
 			goto rx_next;
 		}
 
@@ -255,10 +256,10 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 		napi_gro_receive(&priv->napi, skb);
 		rx++;
 
-		priv->stats.rx_packets++;
-		priv->stats.rx_bytes += len;
+		ndev->stats.rx_packets++;
+		ndev->stats.rx_bytes += len;
 		if (desc0 & RX_DESC0_MULTICAST)
-			priv->stats.multicast++;
+			ndev->stats.multicast++;
 
 rx_next:
 		wmb(); /* prevent setting ownership back too early */
@@ -278,6 +279,13 @@ rx_next:
 	return rx;
 }
 
+static int moxart_tx_queue_space(struct net_device *ndev)
+{
+	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+
+	return CIRC_SPACE(priv->tx_head, priv->tx_tail, TX_DESC_NUM);
+}
+
 static void moxart_tx_finished(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
@@ -288,8 +296,8 @@ static void moxart_tx_finished(struct net_device *ndev)
 		dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail],
 				 priv->tx_len[tx_tail], DMA_TO_DEVICE);
 
-		priv->stats.tx_packets++;
-		priv->stats.tx_bytes += priv->tx_skb[tx_tail]->len;
+		ndev->stats.tx_packets++;
+		ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len;
 
 		dev_kfree_skb_irq(priv->tx_skb[tx_tail]);
 		priv->tx_skb[tx_tail] = NULL;
@@ -297,6 +305,9 @@ static void moxart_tx_finished(struct net_device *ndev)
 		tx_tail = TX_NEXT(tx_tail);
 	}
 	priv->tx_tail = tx_tail;
+	if (netif_queue_stopped(ndev) &&
+	    moxart_tx_queue_space(ndev) >= TX_WAKE_THRESHOLD)
+		netif_wake_queue(ndev);
 }
 
 static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id)
@@ -324,16 +335,21 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
 	void *desc;
 	unsigned int len;
-	unsigned int tx_head = priv->tx_head;
+	unsigned int tx_head;
 	u32 txdes1;
 	int ret = NETDEV_TX_BUSY;
 
+	spin_lock_irq(&priv->txlock);
+
+	tx_head = priv->tx_head;
 	desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head);
 
-	spin_lock_irq(&priv->txlock);
+	if (moxart_tx_queue_space(ndev) == 1)
+		netif_stop_queue(ndev);
+
 	if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) {
 		net_dbg_ratelimited("no TX space for packet\n");
-		priv->stats.tx_dropped++;
+		ndev->stats.tx_dropped++;
 		goto out_unlock;
 	}
 	rmb(); /* ensure data is only read that had TX_DESC0_DMA_OWN cleared */
@@ -384,13 +400,6 @@ out_unlock:
 	return ret;
 }
 
-static struct net_device_stats *moxart_mac_get_stats(struct net_device *ndev)
-{
-	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
-
-	return &priv->stats;
-}
-
 static void moxart_mac_setmulticast(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
@@ -440,7 +449,6 @@ static const struct net_device_ops moxart_netdev_ops = {
 	.ndo_open		= moxart_mac_open,
 	.ndo_stop		= moxart_mac_stop,
 	.ndo_start_xmit		= moxart_mac_start_xmit,
-	.ndo_get_stats		= moxart_mac_get_stats,
 	.ndo_set_rx_mode	= moxart_mac_set_rx_mode,
 	.ndo_set_mac_address	= moxart_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h
index 93a9563ac7c6..686b8957d5cf 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.h
+++ b/drivers/net/ethernet/moxa/moxart_ether.h
@@ -59,6 +59,7 @@
 #define TX_NEXT(N)		(((N) + 1) & (TX_DESC_NUM_MASK))
 #define TX_BUF_SIZE		1600
 #define TX_BUF_SIZE_MAX		(TX_DESC1_BUF_SIZE_MASK+1)
+#define TX_WAKE_THRESHOLD	16
 
 #define RX_DESC_NUM		64
 #define RX_DESC_NUM_MASK	(RX_DESC_NUM-1)
@@ -292,7 +293,6 @@
 
 struct moxart_mac_priv_t {
 	void __iomem *base;
-	struct net_device_stats stats;
 	unsigned int reg_maccr;
 	unsigned int reg_imr;
 	struct napi_struct napi;
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 6933afa69df2..4b15f0f496aa 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -6,8 +6,10 @@ nfp-objs := \
 	    nfpcore/nfp_cpplib.o \
 	    nfpcore/nfp_hwinfo.o \
 	    nfpcore/nfp_mip.o \
+	    nfpcore/nfp_mutex.o \
 	    nfpcore/nfp_nffw.o \
 	    nfpcore/nfp_nsp.o \
+	    nfpcore/nfp_nsp_cmds.o \
 	    nfpcore/nfp_nsp_eth.o \
 	    nfpcore/nfp_resource.o \
 	    nfpcore/nfp_rtsym.o \
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c b/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
index 335beb8b8b45..97a8f00674d0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
@@ -798,7 +798,7 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	const struct bpf_insn *insn = &meta->insn;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2, alu_op,
 			 insn->src_reg * 2, br_mask, insn->off);
@@ -818,7 +818,7 @@ wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u32 tmp_reg;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
 	if (!swap)
@@ -847,7 +847,7 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u8 areg = insn->src_reg * 2, breg = insn->dst_reg * 2;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (swap) {
 		areg ^= breg;
@@ -1132,7 +1132,7 @@ static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		emit_alu(nfp_prog, reg_both(meta->insn.dst_reg * 2),
 			 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_LEN);
 	else
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	return 0;
 }
@@ -1143,7 +1143,7 @@ static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 	if (meta->insn.off != offsetof(struct xdp_md, data) &&
 	    meta->insn.off != offsetof(struct xdp_md, data_end))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT);
 
@@ -1174,12 +1174,12 @@ static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	if (meta->insn.off == offsetof(struct sk_buff, mark))
 		return wrp_set_mark(nfp_prog, meta->insn.src_reg * 2);
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int mem_stx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -1192,7 +1192,7 @@ static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 static int jump(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	if (meta->insn.off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	emit_br(nfp_prog, BR_UNC, meta->insn.off, 0);
 
 	return 0;
@@ -1206,7 +1206,7 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u32 tmp_reg;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (imm & ~0U) {
 		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
@@ -1245,7 +1245,7 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u32 tmp_reg;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (!imm) {
 		meta->skip = true;
@@ -1276,7 +1276,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u32 tmp_reg;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (!imm) {
 		emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
@@ -1302,7 +1302,7 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	const struct bpf_insn *insn = &meta->insn;
 
 	if (insn->off < 0) /* TODO */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	emit_alu(nfp_prog, imm_a(nfp_prog), reg_a(insn->dst_reg * 2),
 		 ALU_OP_XOR, reg_b(insn->src_reg * 2));
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index dedac720fb29..dde35dae35c5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -48,7 +48,7 @@
 #include "nfpcore/nfp.h"
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nffw.h"
-#include "nfpcore/nfp_nsp_eth.h"
+#include "nfpcore/nfp_nsp.h"
 
 #include "nfpcore/nfp6000_pcie.h"
 
@@ -253,6 +253,7 @@ exit_release_fw:
 
 static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
 {
+	struct nfp_nsp_identify *nspi;
 	struct nfp_nsp *nsp;
 	int err;
 
@@ -269,6 +270,12 @@ static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
 
 	pf->eth_tbl = __nfp_eth_read_ports(pf->cpp, nsp);
 
+	nspi = __nfp_nsp_identify(nsp);
+	if (nspi) {
+		dev_info(&pdev->dev, "BSP: %s\n", nspi->version);
+		kfree(nspi);
+	}
+
 	err = nfp_fw_load(pdev, pf, nsp);
 	if (err < 0) {
 		kfree(pf->eth_tbl);
@@ -385,8 +392,7 @@ static void nfp_pci_remove(struct pci_dev *pdev)
 {
 	struct nfp_pf *pf = pci_get_drvdata(pdev);
 
-	if (!list_empty(&pf->ports))
-		nfp_net_pci_remove(pf);
+	nfp_net_pci_remove(pf);
 
 	nfp_pcie_sriov_disable(pdev);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index 39105d0435e9..b57de047b002 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -42,7 +42,9 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/msi.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/workqueue.h>
 
 struct dentry;
 struct pci_dev;
@@ -64,8 +66,11 @@ struct nfp_eth_table;
  * @fw_loaded:		Is the firmware loaded?
  * @eth_tbl:		NSP ETH table
  * @ddir:		Per-device debugfs directory
- * @num_ports:		Number of adapter ports
+ * @num_ports:		Number of adapter ports app firmware supports
+ * @num_netdevs:	Number of netdevs spawned
  * @ports:		Linked list of port structures (struct nfp_net)
+ * @port_lock:		Protects @ports, @num_ports, @num_netdevs
+ * @port_refresh_work:	Work entry for taking netdevs out
  */
 struct nfp_pf {
 	struct pci_dev *pdev;
@@ -88,7 +93,11 @@ struct nfp_pf {
 	struct dentry *ddir;
 
 	unsigned int num_ports;
+	unsigned int num_netdevs;
+
 	struct list_head ports;
+	struct work_struct port_refresh_work;
+	struct mutex port_lock;
 };
 
 extern struct pci_driver nfp_netvf_pci_driver;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index e614a376b595..fcf81b3be830 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -50,14 +50,14 @@
 
 #include "nfp_net_ctrl.h"
 
-#define nn_err(nn, fmt, args...)  netdev_err((nn)->netdev, fmt, ## args)
-#define nn_warn(nn, fmt, args...) netdev_warn((nn)->netdev, fmt, ## args)
-#define nn_info(nn, fmt, args...) netdev_info((nn)->netdev, fmt, ## args)
-#define nn_dbg(nn, fmt, args...)  netdev_dbg((nn)->netdev, fmt, ## args)
-#define nn_warn_ratelimit(nn, fmt, args...)				\
+#define nn_err(nn, fmt, args...)  netdev_err((nn)->dp.netdev, fmt, ## args)
+#define nn_warn(nn, fmt, args...) netdev_warn((nn)->dp.netdev, fmt, ## args)
+#define nn_info(nn, fmt, args...) netdev_info((nn)->dp.netdev, fmt, ## args)
+#define nn_dbg(nn, fmt, args...)  netdev_dbg((nn)->dp.netdev, fmt, ## args)
+#define nn_dp_warn(dp, fmt, args...)					\
 	do {								\
 		if (unlikely(net_ratelimit()))				\
-			netdev_warn((nn)->netdev, fmt, ## args);	\
+			netdev_warn((dp)->netdev, fmt, ## args);	\
 	} while (0)
 
 /* Max time to wait for NFP to respond on updates (in seconds) */
@@ -112,6 +112,7 @@
 
 /* Forward declarations */
 struct nfp_cpp;
+struct nfp_eth_table_port;
 struct nfp_net;
 struct nfp_net_r_vector;
 
@@ -200,6 +201,7 @@ struct nfp_net_tx_buf {
  * @txds:       Virtual address of TX ring in host memory
  * @dma:        DMA address of the TX ring
  * @size:       Size, in bytes, of the TX ring (needed to free)
+ * @is_xdp:	Is this a XDP TX ring?
  */
 struct nfp_net_tx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -220,6 +222,7 @@ struct nfp_net_tx_ring {
 
 	dma_addr_t dma;
 	unsigned int size;
+	bool is_xdp;
 } ____cacheline_aligned;
 
 /* RX and freelist descriptor format */
@@ -283,6 +286,12 @@ struct nfp_net_rx_desc {
 
 #define NFP_NET_META_FIELD_MASK GENMASK(NFP_NET_META_FIELD_SIZE - 1, 0)
 
+struct nfp_meta_parsed {
+	u32 hash_type;
+	u32 hash;
+	u32 mark;
+};
+
 struct nfp_net_rx_hash {
 	__be32 hash_type;
 	__be32 hash;
@@ -306,17 +315,13 @@ struct nfp_net_rx_buf {
  * @rd_p:       FL/RX ring read pointer (free running)
  * @idx:        Ring index from Linux's perspective
  * @fl_qcidx:   Queue Controller Peripheral (QCP) queue index for the freelist
- * @rx_qcidx:   Queue Controller Peripheral (QCP) queue index for the RX queue
  * @qcp_fl:     Pointer to base of the QCP freelist queue
- * @qcp_rx:     Pointer to base of the QCP RX queue
  * @wr_ptr_add: Accumulated number of buffers to add to QCP write pointer
  *              (used for free list batching)
  * @rxbufs:     Array of transmitted FL/RX buffers
  * @rxds:       Virtual address of FL/RX ring in host memory
  * @dma:        DMA address of the FL/RX ring
  * @size:       Size, in bytes, of the FL/RX ring (needed to free)
- * @bufsz:	Buffer allocation size for convenience of management routines
- *		(NOTE: this is in second cache line, do not use on fast path!)
  */
 struct nfp_net_rx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -325,20 +330,17 @@ struct nfp_net_rx_ring {
 	u32 wr_p;
 	u32 rd_p;
 
-	u16 idx;
-	u16 wr_ptr_add;
+	u32 idx;
+	u32 wr_ptr_add;
 
 	int fl_qcidx;
-	int rx_qcidx;
 	u8 __iomem *qcp_fl;
-	u8 __iomem *qcp_rx;
 
 	struct nfp_net_rx_buf *rxbufs;
 	struct nfp_net_rx_desc *rxds;
 
 	dma_addr_t dma;
 	unsigned int size;
-	unsigned int bufsz;
 } ____cacheline_aligned;
 
 /**
@@ -433,19 +435,76 @@ struct nfp_stat_pair {
 };
 
 /**
- * struct nfp_net - NFP network device structure
- * @pdev:               Backpointer to PCI device
- * @netdev:             Backpointer to net_device structure
- * @is_vf:              Is the driver attached to a VF?
+ * struct nfp_net_dp - NFP network device datapath data structure
+ * @dev:		Backpointer to struct device
+ * @netdev:		Backpointer to net_device structure
+ * @is_vf:		Is the driver attached to a VF?
  * @bpf_offload_skip_sw:  Offloaded BPF program will not be rerun by cls_bpf
  * @bpf_offload_xdp:	Offloaded BPF program is XDP
- * @ctrl:               Local copy of the control register/word.
- * @fl_bufsz:           Currently configured size of the freelist buffers
+ * @chained_metadata_format:  Firemware will use new metadata format
+ * @rx_dma_dir:		Mapping direction for RX buffers
+ * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
  * @rx_offset:		Offset in the RX buffers where packet data starts
+ * @ctrl:		Local copy of the control register/word.
+ * @fl_bufsz:		Currently configured size of the freelist buffers
  * @xdp_prog:		Installed XDP program
- * @fw_ver:             Firmware version
+ * @tx_rings:		Array of pre-allocated TX ring structures
+ * @rx_rings:		Array of pre-allocated RX ring structures
+ * @ctrl_bar:		Pointer to mapped control BAR
+ *
+ * @txd_cnt:		Size of the TX ring in number of descriptors
+ * @rxd_cnt:		Size of the RX ring in number of descriptors
+ * @num_r_vecs:		Number of used ring vectors
+ * @num_tx_rings:	Currently configured number of TX rings
+ * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
+ * @num_rx_rings:	Currently configured number of RX rings
+ * @mtu:		Device MTU
+ */
+struct nfp_net_dp {
+	struct device *dev;
+	struct net_device *netdev;
+
+	u8 is_vf:1;
+	u8 bpf_offload_skip_sw:1;
+	u8 bpf_offload_xdp:1;
+	u8 chained_metadata_format:1;
+
+	u8 rx_dma_dir;
+	u8 rx_offset;
+
+	u32 rx_dma_off;
+
+	u32 ctrl;
+	u32 fl_bufsz;
+
+	struct bpf_prog *xdp_prog;
+
+	struct nfp_net_tx_ring *tx_rings;
+	struct nfp_net_rx_ring *rx_rings;
+
+	u8 __iomem *ctrl_bar;
+
+	/* Cold data follows */
+
+	unsigned int txd_cnt;
+	unsigned int rxd_cnt;
+
+	unsigned int num_r_vecs;
+
+	unsigned int num_tx_rings;
+	unsigned int num_stack_tx_rings;
+	unsigned int num_rx_rings;
+
+	unsigned int mtu;
+};
+
+/**
+ * struct nfp_net - NFP network device structure
+ * @dp:			Datapath structure
+ * @fw_ver:		Firmware version
  * @cap:                Capabilities advertised by the Firmware
  * @max_mtu:            Maximum support MTU advertised by the Firmware
+ * @rss_hfunc:		RSS selected hash function
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
@@ -454,17 +513,9 @@ struct nfp_stat_pair {
  * @rx_filter_change:	Jiffies when statistics last changed
  * @rx_filter_stats_timer:  Timer for polling filter offload statistics
  * @rx_filter_lock:	Lock protecting timer state changes (teardown)
+ * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
- * @num_tx_rings:       Currently configured number of TX rings
- * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
- * @num_rx_rings:       Currently configured number of RX rings
- * @txd_cnt:            Size of the TX ring in number of descriptors
- * @rxd_cnt:            Size of the RX ring in number of descriptors
- * @tx_rings:           Array of pre-allocated TX ring structures
- * @rx_rings:           Array of pre-allocated RX ring structures
- * @max_r_vecs:	        Number of allocated interrupt vectors for RX/TX
- * @num_r_vecs:         Number of used ring vectors
  * @r_vecs:             Pre-allocated array of ring vectors
  * @irq_entries:        Pre-allocated array of MSI-X entries
  * @lsc_handler:        Handler for Link State Change interrupt
@@ -480,7 +531,8 @@ struct nfp_stat_pair {
  * @reconfig_sync_present:  Some thread is performing synchronous reconfig
  * @reconfig_timer:	Timer for async reading of reconfig results
  * @link_up:            Is the link up?
- * @link_status_lock:	Protects @link_up and ensures atomicity with BAR reading
+ * @link_changed:	Has link state changes since last port refresh?
+ * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
  * @rx_coalesce_max_frames: RX interrupt moderation frame count parameter
  * @tx_coalesce_usecs:      TX interrupt moderation usecs delay parameter
@@ -488,36 +540,24 @@ struct nfp_stat_pair {
  * @vxlan_ports:	VXLAN ports for RX inner csum offload communicated to HW
  * @vxlan_usecnt:	IPv4/IPv6 VXLAN port use counts
  * @qcp_cfg:            Pointer to QCP queue used for configuration notification
- * @ctrl_bar:           Pointer to mapped control BAR
  * @tx_bar:             Pointer to mapped TX queues
  * @rx_bar:             Pointer to mapped FL/RX queues
  * @debugfs_dir:	Device directory in debugfs
  * @ethtool_dump_flag:	Ethtool dump flag
  * @port_list:		Entry on device port list
+ * @pdev:		Backpointer to PCI device
  * @cpp:		CPP device handle if available
+ * @eth_port:		Translated ETH Table port entry
  */
 struct nfp_net {
-	struct pci_dev *pdev;
-	struct net_device *netdev;
-
-	unsigned is_vf:1;
-	unsigned bpf_offload_skip_sw:1;
-	unsigned bpf_offload_xdp:1;
-
-	u32 ctrl;
-	u32 fl_bufsz;
-
-	u32 rx_offset;
-
-	struct bpf_prog *xdp_prog;
-
-	struct nfp_net_tx_ring *tx_rings;
-	struct nfp_net_rx_ring *rx_rings;
+	struct nfp_net_dp dp;
 
 	struct nfp_net_fw_version fw_ver;
+
 	u32 cap;
 	u32 max_mtu;
 
+	u8 rss_hfunc;
 	u32 rss_cfg;
 	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
@@ -530,18 +570,10 @@ struct nfp_net {
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
 
-	unsigned int num_tx_rings;
-	unsigned int num_stack_tx_rings;
-	unsigned int num_rx_rings;
-
 	int stride_tx;
 	int stride_rx;
 
-	int txd_cnt;
-	int rxd_cnt;
-
 	unsigned int max_r_vecs;
-	unsigned int num_r_vecs;
 	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
 	struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
 
@@ -557,6 +589,7 @@ struct nfp_net {
 	u32 me_freq_mhz;
 
 	bool link_up;
+	bool link_changed;
 	spinlock_t link_status_lock;
 
 	spinlock_t reconfig_lock;
@@ -575,7 +608,6 @@ struct nfp_net {
 
 	u8 __iomem *qcp_cfg;
 
-	u8 __iomem *ctrl_bar;
 	u8 __iomem *tx_bar;
 	u8 __iomem *rx_bar;
 
@@ -584,14 +616,10 @@ struct nfp_net {
 
 	struct list_head port_list;
 
+	struct pci_dev *pdev;
 	struct nfp_cpp *cpp;
-};
 
-struct nfp_net_ring_set {
-	unsigned int n_rings;
-	unsigned int mtu;
-	unsigned int dcnt;
-	void *rings;
+	struct nfp_eth_table_port *eth_port;
 };
 
 /* Functions to read/write from/to a BAR
@@ -599,42 +627,42 @@ struct nfp_net_ring_set {
  */
 static inline u16 nn_readb(struct nfp_net *nn, int off)
 {
-	return readb(nn->ctrl_bar + off);
+	return readb(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
 {
-	writeb(val, nn->ctrl_bar + off);
+	writeb(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u16 nn_readw(struct nfp_net *nn, int off)
 {
-	return readw(nn->ctrl_bar + off);
+	return readw(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
 {
-	writew(val, nn->ctrl_bar + off);
+	writew(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u32 nn_readl(struct nfp_net *nn, int off)
 {
-	return readl(nn->ctrl_bar + off);
+	return readl(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writel(struct nfp_net *nn, int off, u32 val)
 {
-	writel(val, nn->ctrl_bar + off);
+	writel(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u64 nn_readq(struct nfp_net *nn, int off)
 {
-	return readq(nn->ctrl_bar + off);
+	return readq(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writeq(struct nfp_net *nn, int off, u64 val)
 {
-	writeq(val, nn->ctrl_bar + off);
+	writeq(val, nn->dp.ctrl_bar + off);
 }
 
 /* Flush posted PCI writes by reading something without side effects */
@@ -776,6 +804,7 @@ void nfp_net_netdev_clean(struct net_device *netdev);
 void nfp_net_set_ethtool_ops(struct net_device *netdev);
 void nfp_net_info(struct nfp_net *nn);
 int nfp_net_reconfig(struct nfp_net *nn, u32 update);
+unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
 void nfp_net_rss_write_itbl(struct nfp_net *nn);
 void nfp_net_rss_write_key(struct nfp_net *nn);
 void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
@@ -787,9 +816,14 @@ void nfp_net_irqs_disable(struct pci_dev *pdev);
 void
 nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
 		    unsigned int n);
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-		      struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx);
+
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn);
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new,
+			  struct netlink_ext_ack *extack);
+
+bool nfp_net_link_changed_read_clear(struct nfp_net *nn);
+int nfp_net_refresh_eth_port(struct nfp_net *nn);
+void nfp_net_refresh_port_table(struct nfp_net *nn);
 
 #ifdef CONFIG_NFP_DEBUG
 void nfp_net_debugfs_create(void);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 9179a99563af..db20376260f5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -41,6 +41,7 @@
  *          Chris Telfer <chris.telfer@netronome.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/module.h>
@@ -66,6 +67,7 @@
 #include <net/pkt_cls.h>
 #include <net/vxlan.h>
 
+#include "nfpcore/nfp_nsp.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net.h"
 
@@ -83,20 +85,33 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 	put_unaligned_le32(reg, fw_ver);
 }
 
-static dma_addr_t
-nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz,
-		   int direction)
+static dma_addr_t nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag)
 {
-	return dma_map_single(&nn->pdev->dev, frag + NFP_NET_RX_BUF_HEADROOM,
-			      bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+	return dma_map_single_attrs(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM,
+				    dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+				    dp->rx_dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
 }
 
 static void
-nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr,
-		     unsigned int bufsz, int direction)
+nfp_net_dma_sync_dev_rx(const struct nfp_net_dp *dp, dma_addr_t dma_addr)
 {
-	dma_unmap_single(&nn->pdev->dev, dma_addr,
-			 bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+	dma_sync_single_for_device(dp->dev, dma_addr,
+				   dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+				   dp->rx_dma_dir);
+}
+
+static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr)
+{
+	dma_unmap_single_attrs(dp->dev, dma_addr,
+			       dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+			       dp->rx_dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
+}
+
+static void nfp_net_dma_sync_cpu_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr,
+				    unsigned int len)
+{
+	dma_sync_single_for_cpu(dp->dev, dma_addr - NFP_NET_RX_BUF_HEADROOM,
+				len, dp->rx_dma_dir);
 }
 
 /* Firmware reconfig
@@ -327,19 +342,22 @@ void
 nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
 		    unsigned int n)
 {
+	struct nfp_net_dp *dp = &nn->dp;
+
 	nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS;
-	nn->num_r_vecs = nn->max_r_vecs;
+	dp->num_r_vecs = nn->max_r_vecs;
 
 	memcpy(nn->irq_entries, irq_entries, sizeof(*irq_entries) * n);
 
-	if (nn->num_rx_rings > nn->num_r_vecs ||
-	    nn->num_tx_rings > nn->num_r_vecs)
-		nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n",
-			nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs);
+	if (dp->num_rx_rings > dp->num_r_vecs ||
+	    dp->num_tx_rings > dp->num_r_vecs)
+		dev_warn(nn->dp.dev, "More rings (%d,%d) than vectors (%d).\n",
+			 dp->num_rx_rings, dp->num_tx_rings,
+			 dp->num_r_vecs);
 
-	nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings);
-	nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings);
-	nn->num_stack_tx_rings = nn->num_tx_rings;
+	dp->num_rx_rings = min(dp->num_r_vecs, dp->num_rx_rings);
+	dp->num_tx_rings = min(dp->num_r_vecs, dp->num_tx_rings);
+	dp->num_stack_tx_rings = dp->num_tx_rings;
 }
 
 /**
@@ -373,6 +391,19 @@ static irqreturn_t nfp_net_irq_rxtx(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+bool nfp_net_link_changed_read_clear(struct nfp_net *nn)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&nn->link_status_lock, flags);
+	ret = nn->link_changed;
+	nn->link_changed = false;
+	spin_unlock_irqrestore(&nn->link_status_lock, flags);
+
+	return ret;
+}
+
 /**
  * nfp_net_read_link_status() - Reread link status from control BAR
  * @nn:       NFP Network structure
@@ -392,13 +423,14 @@ static void nfp_net_read_link_status(struct nfp_net *nn)
 		goto out;
 
 	nn->link_up = link_up;
+	nn->link_changed = true;
 
 	if (nn->link_up) {
-		netif_carrier_on(nn->netdev);
-		netdev_info(nn->netdev, "NIC Link is Up\n");
+		netif_carrier_on(nn->dp.netdev);
+		netdev_info(nn->dp.netdev, "NIC Link is Up\n");
 	} else {
-		netif_carrier_off(nn->netdev);
-		netdev_info(nn->netdev, "NIC Link is Down\n");
+		netif_carrier_off(nn->dp.netdev);
+		netdev_info(nn->dp.netdev, "NIC Link is Down\n");
 	}
 out:
 	spin_unlock_irqrestore(&nn->link_status_lock, flags);
@@ -446,15 +478,18 @@ static irqreturn_t nfp_net_irq_exn(int irq, void *data)
  * @tx_ring:  TX ring structure
  * @r_vec:    IRQ vector servicing this ring
  * @idx:      Ring index
+ * @is_xdp:   Is this an XDP TX ring?
  */
 static void
 nfp_net_tx_ring_init(struct nfp_net_tx_ring *tx_ring,
-		     struct nfp_net_r_vector *r_vec, unsigned int idx)
+		     struct nfp_net_r_vector *r_vec, unsigned int idx,
+		     bool is_xdp)
 {
 	struct nfp_net *nn = r_vec->nfp_net;
 
 	tx_ring->idx = idx;
 	tx_ring->r_vec = r_vec;
+	tx_ring->is_xdp = is_xdp;
 
 	tx_ring->qcidx = tx_ring->idx * nn->stride_tx;
 	tx_ring->qcp_q = nn->tx_bar + NFP_QCP_QUEUE_OFF(tx_ring->qcidx);
@@ -476,10 +511,7 @@ nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring,
 	rx_ring->r_vec = r_vec;
 
 	rx_ring->fl_qcidx = rx_ring->idx * nn->stride_rx;
-	rx_ring->rx_qcidx = rx_ring->fl_qcidx + (nn->stride_rx - 1);
-
 	rx_ring->qcp_fl = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->fl_qcidx);
-	rx_ring->qcp_rx = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->rx_qcidx);
 }
 
 /**
@@ -530,7 +562,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset,
 
 	entry = &nn->irq_entries[vector_idx];
 
-	snprintf(name, name_sz, format, netdev_name(nn->netdev));
+	snprintf(name, name_sz, format, netdev_name(nn->dp.netdev));
 	err = request_irq(entry->vector, handler, 0, name, nn);
 	if (err) {
 		nn_err(nn, "Failed to request IRQ %d (err=%d).\n",
@@ -617,7 +649,6 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
 
 /**
  * nfp_net_tx_tso() - Set up Tx descriptor for LSO
- * @nn:  NFP Net device
  * @r_vec: per-ring structure
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to HW TX descriptor
@@ -626,7 +657,7 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
  * Set up Tx descriptor for LSO, do nothing for non-LSO skbs.
  * Return error on packet header greater than maximum supported LSO header size.
  */
-static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 			   struct nfp_net_tx_buf *txbuf,
 			   struct nfp_net_tx_desc *txd, struct sk_buff *skb)
 {
@@ -657,7 +688,7 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 
 /**
  * nfp_net_tx_csum() - Set TX CSUM offload flags in TX descriptor
- * @nn:  NFP Net device
+ * @dp:  NFP Net data path struct
  * @r_vec: per-ring structure
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to TX descriptor
@@ -666,7 +697,8 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
  * This function sets the TX checksum flags in the TX descriptor based
  * on the configuration and the protocol of the packet to be transmitted.
  */
-static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_csum(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec,
 			    struct nfp_net_tx_buf *txbuf,
 			    struct nfp_net_tx_desc *txd, struct sk_buff *skb)
 {
@@ -674,7 +706,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	struct iphdr *iph;
 	u8 l4_hdr;
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
+	if (!(dp->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
 		return;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -693,8 +725,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	} else if (ipv6h->version == 6) {
 		l4_hdr = ipv6h->nexthdr;
 	} else {
-		nn_warn_ratelimit(nn, "partial checksum but ipv=%x!\n",
-				  iph->version);
+		nn_dp_warn(dp, "partial checksum but ipv=%x!\n", iph->version);
 		return;
 	}
 
@@ -706,8 +737,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 		txd->flags |= PCIE_DESC_TX_UDP_CSUM;
 		break;
 	default:
-		nn_warn_ratelimit(nn, "partial checksum but l4 proto=%x!\n",
-				  l4_hdr);
+		nn_dp_warn(dp, "partial checksum but l4 proto=%x!\n", l4_hdr);
 		return;
 	}
 
@@ -737,28 +767,31 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	const struct skb_frag_struct *frag;
-	struct nfp_net_r_vector *r_vec;
 	struct nfp_net_tx_desc *txd, txdg;
-	struct nfp_net_tx_buf *txbuf;
 	struct nfp_net_tx_ring *tx_ring;
+	struct nfp_net_r_vector *r_vec;
+	struct nfp_net_tx_buf *txbuf;
 	struct netdev_queue *nd_q;
+	struct nfp_net_dp *dp;
 	dma_addr_t dma_addr;
 	unsigned int fsize;
 	int f, nr_frags;
 	int wr_idx;
 	u16 qidx;
 
+	dp = &nn->dp;
 	qidx = skb_get_queue_mapping(skb);
-	tx_ring = &nn->tx_rings[qidx];
+	tx_ring = &dp->tx_rings[qidx];
 	r_vec = tx_ring->r_vec;
-	nd_q = netdev_get_tx_queue(nn->netdev, qidx);
+	nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) {
-		nn_warn_ratelimit(nn, "TX ring %d busy. wrp=%u rdp=%u\n",
-				  qidx, tx_ring->wr_p, tx_ring->rd_p);
+		nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n",
+			   qidx, tx_ring->wr_p, tx_ring->rd_p);
 		netif_tx_stop_queue(nd_q);
+		nfp_net_tx_xmit_more_flush(tx_ring);
 		u64_stats_update_begin(&r_vec->tx_sync);
 		r_vec->tx_busy++;
 		u64_stats_update_end(&r_vec->tx_sync);
@@ -766,9 +799,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	/* Start with the head skbuf */
-	dma_addr = dma_map_single(&nn->pdev->dev, skb->data, skb_headlen(skb),
+	dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb),
 				  DMA_TO_DEVICE);
-	if (dma_mapping_error(&nn->pdev->dev, dma_addr))
+	if (dma_mapping_error(dp->dev, dma_addr))
 		goto err_free;
 
 	wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
@@ -792,11 +825,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	txd->mss = 0;
 	txd->l4_offset = 0;
 
-	nfp_net_tx_tso(nn, r_vec, txbuf, txd, skb);
+	nfp_net_tx_tso(r_vec, txbuf, txd, skb);
 
-	nfp_net_tx_csum(nn, r_vec, txbuf, txd, skb);
+	nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb);
 
-	if (skb_vlan_tag_present(skb) && nn->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
+	if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
 		txd->flags |= PCIE_DESC_TX_VLAN;
 		txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb));
 	}
@@ -810,9 +843,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 			frag = &skb_shinfo(skb)->frags[f];
 			fsize = skb_frag_size(frag);
 
-			dma_addr = skb_frag_dma_map(&nn->pdev->dev, frag, 0,
+			dma_addr = skb_frag_dma_map(dp->dev, frag, 0,
 						    fsize, DMA_TO_DEVICE);
-			if (dma_mapping_error(&nn->pdev->dev, dma_addr))
+			if (dma_mapping_error(dp->dev, dma_addr))
 				goto err_unmap;
 
 			wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1);
@@ -851,8 +884,7 @@ err_unmap:
 	--f;
 	while (f >= 0) {
 		frag = &skb_shinfo(skb)->frags[f];
-		dma_unmap_page(&nn->pdev->dev,
-			       tx_ring->txbufs[wr_idx].dma_addr,
+		dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		tx_ring->txbufs[wr_idx].skb = NULL;
 		tx_ring->txbufs[wr_idx].dma_addr = 0;
@@ -861,13 +893,14 @@ err_unmap:
 		if (wr_idx < 0)
 			wr_idx += tx_ring->cnt;
 	}
-	dma_unmap_single(&nn->pdev->dev, tx_ring->txbufs[wr_idx].dma_addr,
+	dma_unmap_single(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			 skb_headlen(skb), DMA_TO_DEVICE);
 	tx_ring->txbufs[wr_idx].skb = NULL;
 	tx_ring->txbufs[wr_idx].dma_addr = 0;
 	tx_ring->txbufs[wr_idx].fidx = -2;
 err_free:
-	nn_warn_ratelimit(nn, "Failed to map DMA TX buffer\n");
+	nn_dp_warn(dp, "Failed to map DMA TX buffer\n");
+	nfp_net_tx_xmit_more_flush(tx_ring);
 	u64_stats_update_begin(&r_vec->tx_sync);
 	r_vec->tx_errors++;
 	u64_stats_update_end(&r_vec->tx_sync);
@@ -884,7 +917,7 @@ err_free:
 static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	const struct skb_frag_struct *frag;
 	struct netdev_queue *nd_q;
 	u32 done_pkts = 0, done_bytes = 0;
@@ -894,6 +927,9 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 	int fidx;
 	int idx;
 
+	if (tx_ring->wr_p == tx_ring->rd_p)
+		return;
+
 	/* Work out how many descriptors have been transmitted */
 	qcp_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q);
 
@@ -918,8 +954,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 
 		if (fidx == -1) {
 			/* unmap head */
-			dma_unmap_single(&nn->pdev->dev,
-					 tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr,
 					 skb_headlen(skb), DMA_TO_DEVICE);
 
 			done_pkts += tx_ring->txbufs[idx].pkt_cnt;
@@ -927,8 +962,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 		} else {
 			/* unmap fragment */
 			frag = &skb_shinfo(skb)->frags[fidx];
-			dma_unmap_page(&nn->pdev->dev,
-				       tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr,
 				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
@@ -948,7 +982,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 	r_vec->tx_pkts += done_pkts;
 	u64_stats_update_end(&r_vec->tx_sync);
 
-	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_completed_queue(nd_q, done_pkts, done_bytes);
 	if (nfp_net_tx_ring_should_wake(tx_ring)) {
 		/* Make sure TX thread will see updated tx_ring->rd_p */
@@ -966,11 +1000,13 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
 	u32 done_pkts = 0, done_bytes = 0;
 	int idx, todo;
 	u32 qcp_rd_p;
 
+	if (tx_ring->wr_p == tx_ring->rd_p)
+		return;
+
 	/* Work out how many descriptors have been transmitted */
 	qcp_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q);
 
@@ -982,23 +1018,12 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 	else
 		todo = qcp_rd_p + tx_ring->cnt - tx_ring->qcp_rd_p;
 
+	done_pkts = todo;
 	while (todo--) {
 		idx = tx_ring->rd_p & (tx_ring->cnt - 1);
 		tx_ring->rd_p++;
 
-		if (!tx_ring->txbufs[idx].frag)
-			continue;
-
-		nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr,
-				     nn->fl_bufsz, DMA_BIDIRECTIONAL);
-		__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
-
-		done_pkts++;
 		done_bytes += tx_ring->txbufs[idx].real_len;
-
-		tx_ring->txbufs[idx].dma_addr = 0;
-		tx_ring->txbufs[idx].frag = NULL;
-		tx_ring->txbufs[idx].fidx = -2;
 	}
 
 	tx_ring->qcp_rd_p = qcp_rd_p;
@@ -1015,52 +1040,43 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 
 /**
  * nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @tx_ring:	TX ring structure
  *
  * Assumes that the device is stopped
  */
 static void
-nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
+nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 {
-	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	const struct skb_frag_struct *frag;
-	struct pci_dev *pdev = nn->pdev;
 	struct netdev_queue *nd_q;
 
-	while (tx_ring->rd_p != tx_ring->wr_p) {
+	while (!tx_ring->is_xdp && tx_ring->rd_p != tx_ring->wr_p) {
 		struct nfp_net_tx_buf *tx_buf;
-		int idx;
+		struct sk_buff *skb;
+		int idx, nr_frags;
 
 		idx = tx_ring->rd_p & (tx_ring->cnt - 1);
 		tx_buf = &tx_ring->txbufs[idx];
 
-		if (tx_ring == r_vec->xdp_ring) {
-			nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr,
-					     nn->fl_bufsz, DMA_BIDIRECTIONAL);
-			__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
-		} else {
-			struct sk_buff *skb = tx_ring->txbufs[idx].skb;
-			int nr_frags = skb_shinfo(skb)->nr_frags;
-
-			if (tx_buf->fidx == -1) {
-				/* unmap head */
-				dma_unmap_single(&pdev->dev, tx_buf->dma_addr,
-						 skb_headlen(skb),
-						 DMA_TO_DEVICE);
-			} else {
-				/* unmap fragment */
-				frag = &skb_shinfo(skb)->frags[tx_buf->fidx];
-				dma_unmap_page(&pdev->dev, tx_buf->dma_addr,
-					       skb_frag_size(frag),
-					       DMA_TO_DEVICE);
-			}
+		skb = tx_ring->txbufs[idx].skb;
+		nr_frags = skb_shinfo(skb)->nr_frags;
 
-			/* check for last gather fragment */
-			if (tx_buf->fidx == nr_frags - 1)
-				dev_kfree_skb_any(skb);
+		if (tx_buf->fidx == -1) {
+			/* unmap head */
+			dma_unmap_single(dp->dev, tx_buf->dma_addr,
+					 skb_headlen(skb), DMA_TO_DEVICE);
+		} else {
+			/* unmap fragment */
+			frag = &skb_shinfo(skb)->frags[tx_buf->fidx];
+			dma_unmap_page(dp->dev, tx_buf->dma_addr,
+				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
+		/* check for last gather fragment */
+		if (tx_buf->fidx == nr_frags - 1)
+			dev_kfree_skb_any(skb);
+
 		tx_buf->dma_addr = 0;
 		tx_buf->skb = NULL;
 		tx_buf->fidx = -2;
@@ -1075,10 +1091,10 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 	tx_ring->qcp_rd_p = 0;
 	tx_ring->wr_ptr_add = 0;
 
-	if (tx_ring == r_vec->xdp_ring)
+	if (tx_ring->is_xdp)
 		return;
 
-	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_reset_queue(nd_q);
 }
 
@@ -1087,7 +1103,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
-	for (i = 0; i < nn->netdev->real_num_tx_queues; i++) {
+	for (i = 0; i < nn->dp.netdev->real_num_tx_queues; i++) {
 		if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i)))
 			continue;
 		nn_warn(nn, "TX timeout on ring: %d\n", i);
@@ -1098,16 +1114,17 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
 /* Receive processing
  */
 static unsigned int
-nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu)
+nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp)
 {
 	unsigned int fl_bufsz;
 
 	fl_bufsz = NFP_NET_RX_BUF_HEADROOM;
-	if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+	fl_bufsz += dp->rx_dma_off;
+	if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
 		fl_bufsz += NFP_NET_MAX_PREPEND;
 	else
-		fl_bufsz += nn->rx_offset;
-	fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu;
+		fl_bufsz += dp->rx_offset;
+	fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + dp->mtu;
 
 	fl_bufsz = SKB_DATA_ALIGN(fl_bufsz);
 	fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -1126,62 +1143,53 @@ nfp_net_free_frag(void *frag, bool xdp)
 
 /**
  * nfp_net_rx_alloc_one() - Allocate and map page frag for RX
- * @rx_ring:	RX ring structure of the skb
+ * @dp:		NFP Net data path struct
  * @dma_addr:	Pointer to storage for DMA address (output param)
- * @fl_bufsz:	size of freelist buffers
- * @xdp:	Whether XDP is enabled
  *
  * This function will allcate a new page frag, map it for DMA.
  *
  * Return: allocated page frag or NULL on failure.
  */
-static void *
-nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr,
-		     unsigned int fl_bufsz, bool xdp)
+static void *nfp_net_rx_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 {
-	struct nfp_net *nn = rx_ring->r_vec->nfp_net;
-	int direction;
 	void *frag;
 
-	if (!xdp)
-		frag = netdev_alloc_frag(fl_bufsz);
+	if (!dp->xdp_prog)
+		frag = netdev_alloc_frag(dp->fl_bufsz);
 	else
 		frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD));
 	if (!frag) {
-		nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
 	}
 
-	direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-
-	*dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction);
-	if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
-		nfp_net_free_frag(frag, xdp);
-		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+	*dma_addr = nfp_net_dma_map_rx(dp, frag);
+	if (dma_mapping_error(dp->dev, *dma_addr)) {
+		nfp_net_free_frag(frag, dp->xdp_prog);
+		nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
 		return NULL;
 	}
 
 	return frag;
 }
 
-static void *
-nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
+static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 {
 	void *frag;
 
-	if (!nn->xdp_prog)
-		frag = napi_alloc_frag(nn->fl_bufsz);
+	if (!dp->xdp_prog)
+		frag = napi_alloc_frag(dp->fl_bufsz);
 	else
 		frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD));
 	if (!frag) {
-		nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
 	}
 
-	*dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction);
-	if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
-		nfp_net_free_frag(frag, nn->xdp_prog);
-		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+	*dma_addr = nfp_net_dma_map_rx(dp, frag);
+	if (dma_mapping_error(dp->dev, *dma_addr)) {
+		nfp_net_free_frag(frag, dp->xdp_prog);
+		nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
 		return NULL;
 	}
 
@@ -1190,17 +1198,21 @@ nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
 
 /**
  * nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring structure
  * @frag:	page fragment buffer
  * @dma_addr:	DMA address of skb mapping
  */
-static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
+static void nfp_net_rx_give_one(const struct nfp_net_dp *dp,
+				struct nfp_net_rx_ring *rx_ring,
 				void *frag, dma_addr_t dma_addr)
 {
 	unsigned int wr_idx;
 
 	wr_idx = rx_ring->wr_p & (rx_ring->cnt - 1);
 
+	nfp_net_dma_sync_dev_rx(dp, dma_addr);
+
 	/* Stash SKB and DMA address away */
 	rx_ring->rxbufs[wr_idx].frag = frag;
 	rx_ring->rxbufs[wr_idx].dma_addr = dma_addr;
@@ -1208,7 +1220,8 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
 	/* Fill freelist descriptor */
 	rx_ring->rxds[wr_idx].fld.reserved = 0;
 	rx_ring->rxds[wr_idx].fld.meta_len_dd = 0;
-	nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, dma_addr);
+	nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld,
+			      dma_addr + dp->rx_dma_off);
 
 	rx_ring->wr_p++;
 	rx_ring->wr_ptr_add++;
@@ -1249,19 +1262,17 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 
 /**
  * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring to remove buffers from
- * @xdp:	Whether XDP is enabled
  *
  * Assumes that the device is stopped and buffers are in [0, ring->cnt - 1)
  * entries.  After device is disabled nfp_net_rx_ring_reset() must be called
  * to restore required ring geometry.
  */
 static void
-nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
-			  bool xdp)
+nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp,
+			  struct nfp_net_rx_ring *rx_ring)
 {
-	int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	unsigned int i;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
@@ -1272,9 +1283,8 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 		if (!rx_ring->rxbufs[i].frag)
 			continue;
 
-		nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr,
-				     rx_ring->bufsz, direction);
-		nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp);
+		nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr);
+		nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog);
 		rx_ring->rxbufs[i].dma_addr = 0;
 		rx_ring->rxbufs[i].frag = NULL;
 	}
@@ -1282,13 +1292,12 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 /**
  * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW)
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring to remove buffers from
- * @xdp:	Whether XDP is enabled
  */
 static int
-nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
-			   bool xdp)
+nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp,
+			   struct nfp_net_rx_ring *rx_ring)
 {
 	struct nfp_net_rx_buf *rxbufs;
 	unsigned int i;
@@ -1296,11 +1305,9 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 	rxbufs = rx_ring->rxbufs;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
-		rxbufs[i].frag =
-			nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr,
-					     rx_ring->bufsz, xdp);
+		rxbufs[i].frag = nfp_net_rx_alloc_one(dp, &rxbufs[i].dma_addr);
 		if (!rxbufs[i].frag) {
-			nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp);
+			nfp_net_rx_ring_bufs_free(dp, rx_ring);
 			return -ENOMEM;
 		}
 	}
@@ -1310,14 +1317,17 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 /**
  * nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW
+ * @dp:	     NFP Net data path struct
  * @rx_ring: RX ring to fill
  */
-static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring)
+static void
+nfp_net_rx_ring_fill_freelist(struct nfp_net_dp *dp,
+			      struct nfp_net_rx_ring *rx_ring)
 {
 	unsigned int i;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++)
-		nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag,
+		nfp_net_rx_give_one(dp, rx_ring, rx_ring->rxbufs[i].frag,
 				    rx_ring->rxbufs[i].dma_addr);
 }
 
@@ -1337,17 +1347,18 @@ static int nfp_net_rx_csum_has_errors(u16 flags)
 
 /**
  * nfp_net_rx_csum() - set SKB checksum field based on RX descriptor flags
- * @nn:  NFP Net device
+ * @dp:  NFP Net data path struct
  * @r_vec: per-ring structure
  * @rxd: Pointer to RX descriptor
  * @skb: Pointer to SKB
  */
-static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_rx_csum(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec,
 			    struct nfp_net_rx_desc *rxd, struct sk_buff *skb)
 {
 	skb_checksum_none_assert(skb);
 
-	if (!(nn->netdev->features & NETIF_F_RXCSUM))
+	if (!(dp->netdev->features & NETIF_F_RXCSUM))
 		return;
 
 	if (nfp_net_rx_csum_has_errors(le16_to_cpu(rxd->rxd.flags))) {
@@ -1378,8 +1389,9 @@ static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	}
 }
 
-static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb,
-			     unsigned int type, __be32 *hash)
+static void
+nfp_net_set_hash(struct net_device *netdev, struct nfp_meta_parsed *meta,
+		 unsigned int type, __be32 *hash)
 {
 	if (!(netdev->features & NETIF_F_RXHASH))
 		return;
@@ -1388,34 +1400,33 @@ static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb,
 	case NFP_NET_RSS_IPV4:
 	case NFP_NET_RSS_IPV6:
 	case NFP_NET_RSS_IPV6_EX:
-		skb_set_hash(skb, get_unaligned_be32(hash), PKT_HASH_TYPE_L3);
+		meta->hash_type = PKT_HASH_TYPE_L3;
 		break;
 	default:
-		skb_set_hash(skb, get_unaligned_be32(hash), PKT_HASH_TYPE_L4);
+		meta->hash_type = PKT_HASH_TYPE_L4;
 		break;
 	}
+
+	meta->hash = get_unaligned_be32(hash);
 }
 
 static void
-nfp_net_set_hash_desc(struct net_device *netdev, struct sk_buff *skb,
-		      struct nfp_net_rx_desc *rxd)
+nfp_net_set_hash_desc(struct net_device *netdev, struct nfp_meta_parsed *meta,
+		      void *data, struct nfp_net_rx_desc *rxd)
 {
-	struct nfp_net_rx_hash *rx_hash;
+	struct nfp_net_rx_hash *rx_hash = data;
 
 	if (!(rxd->rxd.flags & PCIE_DESC_RX_RSS))
 		return;
 
-	rx_hash = (struct nfp_net_rx_hash *)(skb->data - sizeof(*rx_hash));
-
-	nfp_net_set_hash(netdev, skb, get_unaligned_be32(&rx_hash->hash_type),
+	nfp_net_set_hash(netdev, meta, get_unaligned_be32(&rx_hash->hash_type),
 			 &rx_hash->hash);
 }
 
 static void *
-nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
-		   int meta_len)
+nfp_net_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta,
+		   void *data, int meta_len)
 {
-	u8 *data = skb->data - meta_len;
 	u32 meta_info;
 
 	meta_info = get_unaligned_be32(data);
@@ -1425,13 +1436,13 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
 		switch (meta_info & NFP_NET_META_FIELD_MASK) {
 		case NFP_NET_META_HASH:
 			meta_info >>= NFP_NET_META_FIELD_SIZE;
-			nfp_net_set_hash(netdev, skb,
+			nfp_net_set_hash(netdev, meta,
 					 meta_info & NFP_NET_META_FIELD_MASK,
 					 (__be32 *)data);
 			data += 4;
 			break;
 		case NFP_NET_META_MARK:
-			skb->mark = get_unaligned_be32(data);
+			meta->mark = get_unaligned_be32(data);
 			data += 4;
 			break;
 		default:
@@ -1445,8 +1456,9 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
 }
 
 static void
-nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
-		struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb)
+nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
+		struct nfp_net_rx_ring *rx_ring, struct nfp_net_rx_buf *rxbuf,
+		struct sk_buff *skb)
 {
 	u64_stats_update_begin(&r_vec->rx_sync);
 	r_vec->rx_drops++;
@@ -1458,53 +1470,47 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
 	if (skb && rxbuf && skb->head == rxbuf->frag)
 		page_ref_inc(virt_to_head_page(rxbuf->frag));
 	if (rxbuf)
-		nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr);
+		nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr);
 	if (skb)
 		dev_kfree_skb_any(skb);
 }
 
 static bool
-nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
+nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
 		   struct nfp_net_tx_ring *tx_ring,
-		   struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off,
+		   struct nfp_net_rx_buf *rxbuf, unsigned int dma_off,
 		   unsigned int pkt_len)
 {
 	struct nfp_net_tx_buf *txbuf;
 	struct nfp_net_tx_desc *txd;
-	dma_addr_t new_dma_addr;
-	void *new_frag;
 	int wr_idx;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, 1))) {
-		nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
-		return false;
-	}
-
-	new_frag = nfp_net_napi_alloc_one(nn, DMA_BIDIRECTIONAL, &new_dma_addr);
-	if (unlikely(!new_frag)) {
-		nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+		nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL);
 		return false;
 	}
-	nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
 
 	wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
 
 	/* Stash the soft descriptor of the head then initialize it */
 	txbuf = &tx_ring->txbufs[wr_idx];
+
+	nfp_net_rx_give_one(dp, rx_ring, txbuf->frag, txbuf->dma_addr);
+
 	txbuf->frag = rxbuf->frag;
 	txbuf->dma_addr = rxbuf->dma_addr;
 	txbuf->fidx = -1;
 	txbuf->pkt_cnt = 1;
 	txbuf->real_len = pkt_len;
 
-	dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off,
+	dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + dma_off,
 				   pkt_len, DMA_BIDIRECTIONAL);
 
 	/* Build TX descriptor */
 	txd = &tx_ring->txds[wr_idx];
 	txd->offset_eop = PCIE_DESC_TX_EOP;
 	txd->dma_len = cpu_to_le16(pkt_len);
-	nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + pkt_off);
+	nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + dma_off);
 	txd->data_len = cpu_to_le16(pkt_len);
 
 	txd->flags = 0;
@@ -1516,14 +1522,24 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 	return true;
 }
 
-static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
+static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start,
+			   unsigned int *off, unsigned int *len)
 {
 	struct xdp_buff xdp;
+	void *orig_data;
+	int ret;
 
-	xdp.data = data;
-	xdp.data_end = data + len;
+	xdp.data_hard_start = hard_start;
+	xdp.data = data + *off;
+	xdp.data_end = data + *off + *len;
 
-	return bpf_prog_run_xdp(prog, &xdp);
+	orig_data = xdp.data;
+	ret = bpf_prog_run_xdp(prog, &xdp);
+
+	*len -= xdp.data - orig_data;
+	*off += xdp.data - orig_data;
+
+	return ret;
 }
 
 /**
@@ -1540,25 +1556,24 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
 static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 {
 	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	struct nfp_net_tx_ring *tx_ring;
 	struct bpf_prog *xdp_prog;
 	unsigned int true_bufsz;
 	struct sk_buff *skb;
 	int pkts_polled = 0;
-	int rx_dma_map_dir;
 	int idx;
 
 	rcu_read_lock();
-	xdp_prog = READ_ONCE(nn->xdp_prog);
-	rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-	true_bufsz = xdp_prog ? PAGE_SIZE : nn->fl_bufsz;
+	xdp_prog = READ_ONCE(dp->xdp_prog);
+	true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
 	tx_ring = r_vec->xdp_ring;
 
 	while (pkts_polled < budget) {
-		unsigned int meta_len, data_len, data_off, pkt_len, pkt_off;
+		unsigned int meta_len, data_len, meta_off, pkt_len, pkt_off;
 		struct nfp_net_rx_buf *rxbuf;
 		struct nfp_net_rx_desc *rxd;
+		struct nfp_meta_parsed meta;
 		dma_addr_t new_dma_addr;
 		void *new_frag;
 
@@ -1573,6 +1588,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		memset(&meta, 0, sizeof(meta));
+
 		rx_ring->rd_p++;
 		pkts_polled++;
 
@@ -1593,11 +1610,12 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		data_len = le16_to_cpu(rxd->rxd.data_len);
 		pkt_len = data_len - meta_len;
 
-		if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
-			pkt_off = meta_len;
+		pkt_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_dma_off;
+		if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+			pkt_off += meta_len;
 		else
-			pkt_off = nn->rx_offset;
-		data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off;
+			pkt_off += dp->rx_offset;
+		meta_off = pkt_off - meta_len;
 
 		/* Stats update */
 		u64_stats_update_begin(&r_vec->rx_sync);
@@ -1605,30 +1623,62 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		r_vec->rx_bytes += pkt_len;
 		u64_stats_update_end(&r_vec->rx_sync);
 
+		if (unlikely(meta_len > NFP_NET_MAX_PREPEND ||
+			     (dp->rx_offset && meta_len > dp->rx_offset))) {
+			nn_dp_warn(dp, "oversized RX packet metadata %u\n",
+				   meta_len);
+			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
+			continue;
+		}
+
+		nfp_net_dma_sync_cpu_rx(dp, rxbuf->dma_addr + meta_off,
+					data_len);
+
+		if (!dp->chained_metadata_format) {
+			nfp_net_set_hash_desc(dp->netdev, &meta,
+					      rxbuf->frag + meta_off, rxd);
+		} else if (meta_len) {
+			void *end;
+
+			end = nfp_net_parse_meta(dp->netdev, &meta,
+						 rxbuf->frag + meta_off,
+						 meta_len);
+			if (unlikely(end != rxbuf->frag + pkt_off)) {
+				nn_dp_warn(dp, "invalid RX packet metadata\n");
+				nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf,
+						NULL);
+				continue;
+			}
+		}
+
 		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
-				  nn->bpf_offload_xdp)) {
+				  dp->bpf_offload_xdp)) {
+			unsigned int dma_off;
+			void *hard_start;
 			int act;
 
-			dma_sync_single_for_cpu(&nn->pdev->dev,
-						rxbuf->dma_addr + pkt_off,
-						pkt_len, DMA_BIDIRECTIONAL);
-			act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off,
-					      pkt_len);
+			hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+
+			act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start,
+					      &pkt_off, &pkt_len);
 			switch (act) {
 			case XDP_PASS:
 				break;
 			case XDP_TX:
-				if (unlikely(!nfp_net_tx_xdp_buf(nn, rx_ring,
+				dma_off = pkt_off - NFP_NET_RX_BUF_HEADROOM;
+				if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring,
 								 tx_ring, rxbuf,
-								 pkt_off, pkt_len)))
-					trace_xdp_exception(nn->netdev, xdp_prog, act);
+								 dma_off,
+								 pkt_len)))
+					trace_xdp_exception(dp->netdev,
+							    xdp_prog, act);
 				continue;
 			default:
 				bpf_warn_invalid_xdp_action(act);
 			case XDP_ABORTED:
-				trace_xdp_exception(nn->netdev, xdp_prog, act);
+				trace_xdp_exception(dp->netdev, xdp_prog, act);
 			case XDP_DROP:
-				nfp_net_rx_give_one(rx_ring, rxbuf->frag,
+				nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag,
 						    rxbuf->dma_addr);
 				continue;
 			}
@@ -1636,41 +1686,29 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		skb = build_skb(rxbuf->frag, true_bufsz);
 		if (unlikely(!skb)) {
-			nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL);
+			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
 			continue;
 		}
-		new_frag = nfp_net_napi_alloc_one(nn, rx_dma_map_dir,
-						  &new_dma_addr);
+		new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr);
 		if (unlikely(!new_frag)) {
-			nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb);
+			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb);
 			continue;
 		}
 
-		nfp_net_dma_unmap_rx(nn, rxbuf->dma_addr, nn->fl_bufsz,
-				     rx_dma_map_dir);
+		nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr);
 
-		nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+		nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
 
-		skb_reserve(skb, data_off);
+		skb_reserve(skb, pkt_off);
 		skb_put(skb, pkt_len);
 
-		if (nn->fw_ver.major <= 3) {
-			nfp_net_set_hash_desc(nn->netdev, skb, rxd);
-		} else if (meta_len) {
-			void *end;
-
-			end = nfp_net_parse_meta(nn->netdev, skb, meta_len);
-			if (unlikely(end != skb->data)) {
-				nn_warn_ratelimit(nn, "invalid RX packet metadata\n");
-				nfp_net_rx_drop(r_vec, rx_ring, NULL, skb);
-				continue;
-			}
-		}
+		skb->mark = meta.mark;
+		skb_set_hash(skb, meta.hash, meta.hash_type);
 
 		skb_record_rx_queue(skb, rx_ring->idx);
-		skb->protocol = eth_type_trans(skb, nn->netdev);
+		skb->protocol = eth_type_trans(skb, dp->netdev);
 
-		nfp_net_rx_csum(nn, r_vec, rxd, skb);
+		nfp_net_rx_csum(dp, r_vec, rxd, skb);
 
 		if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
@@ -1707,10 +1745,9 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 			nfp_net_xdp_complete(r_vec->xdp_ring);
 	}
 
-	if (pkts_polled < budget) {
-		napi_complete_done(napi, pkts_polled);
-		nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
-	}
+	if (pkts_polled < budget)
+		if (napi_complete_done(napi, pkts_polled))
+			nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
 
 	return pkts_polled;
 }
@@ -1725,13 +1762,12 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 
 	kfree(tx_ring->txbufs);
 
 	if (tx_ring->txds)
-		dma_free_coherent(&pdev->dev, tx_ring->size,
+		dma_free_coherent(dp->dev, tx_ring->size,
 				  tx_ring->txds, tx_ring->dma);
 
 	tx_ring->cnt = 0;
@@ -1743,24 +1779,21 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 
 /**
  * nfp_net_tx_ring_alloc() - Allocate resource for a TX ring
+ * @dp:        NFP Net data path struct
  * @tx_ring:   TX Ring structure to allocate
- * @cnt:       Ring buffer count
- * @is_xdp:    True if ring will be used for XDP
  *
  * Return: 0 on success, negative errno otherwise.
  */
 static int
-nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
+nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
 	int sz;
 
-	tx_ring->cnt = cnt;
+	tx_ring->cnt = dp->txd_cnt;
 
 	tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt;
-	tx_ring->txds = dma_zalloc_coherent(&pdev->dev, tx_ring->size,
+	tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size,
 					    &tx_ring->dma, GFP_KERNEL);
 	if (!tx_ring->txds)
 		goto err_alloc;
@@ -1770,15 +1803,10 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
 	if (!tx_ring->txbufs)
 		goto err_alloc;
 
-	if (!is_xdp)
-		netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask,
+	if (!tx_ring->is_xdp)
+		netif_set_xps_queue(dp->netdev, &r_vec->affinity_mask,
 				    tx_ring->idx);
 
-	nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p %s\n",
-	       tx_ring->idx, tx_ring->qcidx,
-	       tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds,
-	       is_xdp ? "XDP" : "");
-
 	return 0;
 
 err_alloc:
@@ -1786,62 +1814,92 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static struct nfp_net_tx_ring *
-nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
-			    unsigned int num_stack_tx_rings)
+static void
+nfp_net_tx_ring_bufs_free(struct nfp_net_dp *dp,
+			  struct nfp_net_tx_ring *tx_ring)
 {
-	struct nfp_net_tx_ring *rings;
-	unsigned int r;
+	unsigned int i;
 
-	rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
-	if (!rings)
-		return NULL;
+	if (!tx_ring->is_xdp)
+		return;
 
-	for (r = 0; r < s->n_rings; r++) {
-		int bias = 0;
+	for (i = 0; i < tx_ring->cnt; i++) {
+		if (!tx_ring->txbufs[i].frag)
+			return;
 
-		if (r >= num_stack_tx_rings)
-			bias = num_stack_tx_rings;
+		nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[i].dma_addr);
+		__free_page(virt_to_page(tx_ring->txbufs[i].frag));
+	}
+}
 
-		nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r);
+static int
+nfp_net_tx_ring_bufs_alloc(struct nfp_net_dp *dp,
+			   struct nfp_net_tx_ring *tx_ring)
+{
+	struct nfp_net_tx_buf *txbufs = tx_ring->txbufs;
+	unsigned int i;
 
-		if (nfp_net_tx_ring_alloc(&rings[r], s->dcnt, bias))
-			goto err_free_prev;
-	}
+	if (!tx_ring->is_xdp)
+		return 0;
 
-	return s->rings = rings;
+	for (i = 0; i < tx_ring->cnt; i++) {
+		txbufs[i].frag = nfp_net_rx_alloc_one(dp, &txbufs[i].dma_addr);
+		if (!txbufs[i].frag) {
+			nfp_net_tx_ring_bufs_free(dp, tx_ring);
+			return -ENOMEM;
+		}
+	}
 
-err_free_prev:
-	while (r--)
-		nfp_net_tx_ring_free(&rings[r]);
-	kfree(rings);
-	return NULL;
+	return 0;
 }
 
-static void
-nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
+static int nfp_net_tx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
-	struct nfp_net_ring_set new = *s;
+	unsigned int r;
+
+	dp->tx_rings = kcalloc(dp->num_tx_rings, sizeof(*dp->tx_rings),
+			       GFP_KERNEL);
+	if (!dp->tx_rings)
+		return -ENOMEM;
+
+	for (r = 0; r < dp->num_tx_rings; r++) {
+		int bias = 0;
+
+		if (r >= dp->num_stack_tx_rings)
+			bias = dp->num_stack_tx_rings;
 
-	s->dcnt = nn->txd_cnt;
-	s->rings = nn->tx_rings;
-	s->n_rings = nn->num_tx_rings;
+		nfp_net_tx_ring_init(&dp->tx_rings[r], &nn->r_vecs[r - bias],
+				     r, bias);
+
+		if (nfp_net_tx_ring_alloc(dp, &dp->tx_rings[r]))
+			goto err_free_prev;
 
-	nn->txd_cnt = new.dcnt;
-	nn->tx_rings = new.rings;
-	nn->num_tx_rings = new.n_rings;
+		if (nfp_net_tx_ring_bufs_alloc(dp, &dp->tx_rings[r]))
+			goto err_free_ring;
+	}
+
+	return 0;
+
+err_free_prev:
+	while (r--) {
+		nfp_net_tx_ring_bufs_free(dp, &dp->tx_rings[r]);
+err_free_ring:
+		nfp_net_tx_ring_free(&dp->tx_rings[r]);
+	}
+	kfree(dp->tx_rings);
+	return -ENOMEM;
 }
 
-static void
-nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
+static void nfp_net_tx_rings_free(struct nfp_net_dp *dp)
 {
-	struct nfp_net_tx_ring *rings = s->rings;
 	unsigned int r;
 
-	for (r = 0; r < s->n_rings; r++)
-		nfp_net_tx_ring_free(&rings[r]);
+	for (r = 0; r < dp->num_tx_rings; r++) {
+		nfp_net_tx_ring_bufs_free(dp, &dp->tx_rings[r]);
+		nfp_net_tx_ring_free(&dp->tx_rings[r]);
+	}
 
-	kfree(rings);
+	kfree(dp->tx_rings);
 }
 
 /**
@@ -1851,13 +1909,12 @@ nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
 static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 {
 	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 
 	kfree(rx_ring->rxbufs);
 
 	if (rx_ring->rxds)
-		dma_free_coherent(&pdev->dev, rx_ring->size,
+		dma_free_coherent(dp->dev, rx_ring->size,
 				  rx_ring->rxds, rx_ring->dma);
 
 	rx_ring->cnt = 0;
@@ -1869,26 +1926,19 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 
 /**
  * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring
+ * @dp:	      NFP Net data path struct
  * @rx_ring:  RX ring to allocate
- * @fl_bufsz: Size of buffers to allocate
- * @cnt:      Ring buffer count
  *
  * Return: 0 on success, negative errno otherwise.
  */
 static int
-nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
-		      u32 cnt)
+nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 {
-	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
 	int sz;
 
-	rx_ring->cnt = cnt;
-	rx_ring->bufsz = fl_bufsz;
-
+	rx_ring->cnt = dp->rxd_cnt;
 	rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
-	rx_ring->rxds = dma_zalloc_coherent(&pdev->dev, rx_ring->size,
+	rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size,
 					    &rx_ring->dma, GFP_KERNEL);
 	if (!rx_ring->rxds)
 		goto err_alloc;
@@ -1898,10 +1948,6 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
 	if (!rx_ring->rxbufs)
 		goto err_alloc;
 
-	nn_dbg(nn, "RxQ%02d: FlQCidx=%02d RxQCidx=%02d cnt=%d dma=%#llx host=%p\n",
-	       rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx,
-	       rx_ring->cnt, (unsigned long long)rx_ring->dma, rx_ring->rxds);
-
 	return 0;
 
 err_alloc:
@@ -1909,82 +1955,59 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static struct nfp_net_rx_ring *
-nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
-			    bool xdp)
+static int nfp_net_rx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
-	unsigned int fl_bufsz =	nfp_net_calc_fl_bufsz(nn, s->mtu);
-	struct nfp_net_rx_ring *rings;
 	unsigned int r;
 
-	rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
-	if (!rings)
-		return NULL;
+	dp->rx_rings = kcalloc(dp->num_rx_rings, sizeof(*dp->rx_rings),
+			       GFP_KERNEL);
+	if (!dp->rx_rings)
+		return -ENOMEM;
 
-	for (r = 0; r < s->n_rings; r++) {
-		nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r);
+	for (r = 0; r < dp->num_rx_rings; r++) {
+		nfp_net_rx_ring_init(&dp->rx_rings[r], &nn->r_vecs[r], r);
 
-		if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt))
+		if (nfp_net_rx_ring_alloc(dp, &dp->rx_rings[r]))
 			goto err_free_prev;
 
-		if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r], xdp))
+		if (nfp_net_rx_ring_bufs_alloc(dp, &dp->rx_rings[r]))
 			goto err_free_ring;
 	}
 
-	return s->rings = rings;
+	return 0;
 
 err_free_prev:
 	while (r--) {
-		nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
+		nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]);
 err_free_ring:
-		nfp_net_rx_ring_free(&rings[r]);
+		nfp_net_rx_ring_free(&dp->rx_rings[r]);
 	}
-	kfree(rings);
-	return NULL;
-}
-
-static void
-nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
-{
-	struct nfp_net_ring_set new = *s;
-
-	s->mtu = nn->netdev->mtu;
-	s->dcnt = nn->rxd_cnt;
-	s->rings = nn->rx_rings;
-	s->n_rings = nn->num_rx_rings;
-
-	nn->netdev->mtu = new.mtu;
-	nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, new.mtu);
-	nn->rxd_cnt = new.dcnt;
-	nn->rx_rings = new.rings;
-	nn->num_rx_rings = new.n_rings;
+	kfree(dp->rx_rings);
+	return -ENOMEM;
 }
 
-static void
-nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s,
-			 bool xdp)
+static void nfp_net_rx_rings_free(struct nfp_net_dp *dp)
 {
-	struct nfp_net_rx_ring *rings = s->rings;
 	unsigned int r;
 
-	for (r = 0; r < s->n_rings; r++) {
-		nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
-		nfp_net_rx_ring_free(&rings[r]);
+	for (r = 0; r < dp->num_rx_rings; r++) {
+		nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]);
+		nfp_net_rx_ring_free(&dp->rx_rings[r]);
 	}
 
-	kfree(rings);
+	kfree(dp->rx_rings);
 }
 
 static void
-nfp_net_vector_assign_rings(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
-			    int idx)
+nfp_net_vector_assign_rings(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec, int idx)
 {
-	r_vec->rx_ring = idx < nn->num_rx_rings ? &nn->rx_rings[idx] : NULL;
+	r_vec->rx_ring = idx < dp->num_rx_rings ? &dp->rx_rings[idx] : NULL;
 	r_vec->tx_ring =
-		idx < nn->num_stack_tx_rings ? &nn->tx_rings[idx] : NULL;
+		idx < dp->num_stack_tx_rings ? &dp->tx_rings[idx] : NULL;
 
-	r_vec->xdp_ring = idx < nn->num_tx_rings - nn->num_stack_tx_rings ?
-		&nn->tx_rings[nn->num_stack_tx_rings + idx] : NULL;
+	r_vec->xdp_ring = idx < dp->num_tx_rings - dp->num_stack_tx_rings ?
+		&dp->tx_rings[dp->num_stack_tx_rings + idx] : NULL;
 }
 
 static int
@@ -1994,11 +2017,11 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	int err;
 
 	/* Setup NAPI */
-	netif_napi_add(nn->netdev, &r_vec->napi,
+	netif_napi_add(nn->dp.netdev, &r_vec->napi,
 		       nfp_net_poll, NAPI_POLL_WEIGHT);
 
 	snprintf(r_vec->name, sizeof(r_vec->name),
-		 "%s-rxtx-%d", nn->netdev->name, idx);
+		 "%s-rxtx-%d", nn->dp.netdev->name, idx);
 	err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name,
 			  r_vec);
 	if (err) {
@@ -2045,7 +2068,7 @@ void nfp_net_rss_write_key(struct nfp_net *nn)
 {
 	int i;
 
-	for (i = 0; i < NFP_NET_CFG_RSS_KEY_SZ; i += 4)
+	for (i = 0; i < nfp_net_rss_key_sz(nn); i += 4)
 		nn_writel(nn, NFP_NET_CFG_RSS_KEY + i,
 			  get_unaligned_le32(nn->rss_key + i));
 }
@@ -2069,13 +2092,13 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
 	/* copy RX interrupt coalesce parameters */
 	value = (nn->rx_coalesce_max_frames << 16) |
 		(factor * nn->rx_coalesce_usecs);
-	for (i = 0; i < nn->num_rx_rings; i++)
+	for (i = 0; i < nn->dp.num_rx_rings; i++)
 		nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(i), value);
 
 	/* copy TX interrupt coalesce parameters */
 	value = (nn->tx_coalesce_max_frames << 16) |
 		(factor * nn->tx_coalesce_usecs);
-	for (i = 0; i < nn->num_tx_rings; i++)
+	for (i = 0; i < nn->dp.num_tx_rings; i++)
 		nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(i), value);
 }
 
@@ -2090,9 +2113,9 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
 static void nfp_net_write_mac_addr(struct nfp_net *nn)
 {
 	nn_writel(nn, NFP_NET_CFG_MACADDR + 0,
-		  get_unaligned_be32(nn->netdev->dev_addr));
+		  get_unaligned_be32(nn->dp.netdev->dev_addr));
 	nn_writew(nn, NFP_NET_CFG_MACADDR + 6,
-		  get_unaligned_be16(nn->netdev->dev_addr + 4));
+		  get_unaligned_be16(nn->dp.netdev->dev_addr + 4));
 }
 
 static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
@@ -2116,7 +2139,7 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 	unsigned int r;
 	int err;
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 	new_ctrl &= ~NFP_NET_CFG_CTRL_ENABLE;
 	update = NFP_NET_CFG_UPDATE_GEN;
 	update |= NFP_NET_CFG_UPDATE_MSIX;
@@ -2133,14 +2156,14 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 	if (err)
 		nn_err(nn, "Could not disable device: %d\n", err);
 
-	for (r = 0; r < nn->num_rx_rings; r++)
-		nfp_net_rx_ring_reset(&nn->rx_rings[r]);
-	for (r = 0; r < nn->num_tx_rings; r++)
-		nfp_net_tx_ring_reset(nn, &nn->tx_rings[r]);
-	for (r = 0; r < nn->num_r_vecs; r++)
+	for (r = 0; r < nn->dp.num_rx_rings; r++)
+		nfp_net_rx_ring_reset(&nn->dp.rx_rings[r]);
+	for (r = 0; r < nn->dp.num_tx_rings; r++)
+		nfp_net_tx_ring_reset(&nn->dp, &nn->dp.tx_rings[r]);
+	for (r = 0; r < nn->dp.num_r_vecs; r++)
 		nfp_net_vec_clear_ring_data(nn, r);
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 }
 
 static void
@@ -2162,13 +2185,17 @@ nfp_net_tx_ring_hw_cfg_write(struct nfp_net *nn,
 	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), tx_ring->r_vec->irq_entry);
 }
 
-static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
+/**
+ * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
+ * @nn:      NFP Net device to reconfigure
+ */
+static int nfp_net_set_config_and_enable(struct nfp_net *nn)
 {
-	u32 new_ctrl, update = 0;
+	u32 bufsz, new_ctrl, update = 0;
 	unsigned int r;
 	int err;
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 
 	if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
 		nfp_net_rss_write_key(nn);
@@ -2184,22 +2211,23 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 		update |= NFP_NET_CFG_UPDATE_IRQMOD;
 	}
 
-	for (r = 0; r < nn->num_tx_rings; r++)
-		nfp_net_tx_ring_hw_cfg_write(nn, &nn->tx_rings[r], r);
-	for (r = 0; r < nn->num_rx_rings; r++)
-		nfp_net_rx_ring_hw_cfg_write(nn, &nn->rx_rings[r], r);
+	for (r = 0; r < nn->dp.num_tx_rings; r++)
+		nfp_net_tx_ring_hw_cfg_write(nn, &nn->dp.tx_rings[r], r);
+	for (r = 0; r < nn->dp.num_rx_rings; r++)
+		nfp_net_rx_ring_hw_cfg_write(nn, &nn->dp.rx_rings[r], r);
 
-	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
-		  0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
+	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->dp.num_tx_rings == 64 ?
+		  0xffffffffffffffffULL : ((u64)1 << nn->dp.num_tx_rings) - 1);
 
-	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ?
-		  0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1);
+	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->dp.num_rx_rings == 64 ?
+		  0xffffffffffffffffULL : ((u64)1 << nn->dp.num_rx_rings) - 1);
 
 	nfp_net_write_mac_addr(nn);
 
-	nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu);
-	nn_writel(nn, NFP_NET_CFG_FLBUFSZ,
-		  nn->fl_bufsz - NFP_NET_RX_BUF_NON_DATA);
+	nn_writel(nn, NFP_NET_CFG_MTU, nn->dp.netdev->mtu);
+
+	bufsz = nn->dp.fl_bufsz - nn->dp.rx_dma_off - NFP_NET_RX_BUF_NON_DATA;
+	nn_writel(nn, NFP_NET_CFG_FLBUFSZ, bufsz);
 
 	/* Enable device */
 	new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
@@ -2211,37 +2239,26 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	err = nfp_net_reconfig(nn, update);
+	if (err) {
+		nfp_net_clear_config_and_disable(nn);
+		return err;
+	}
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 
-	for (r = 0; r < nn->num_rx_rings; r++)
-		nfp_net_rx_ring_fill_freelist(&nn->rx_rings[r]);
+	for (r = 0; r < nn->dp.num_rx_rings; r++)
+		nfp_net_rx_ring_fill_freelist(&nn->dp, &nn->dp.rx_rings[r]);
 
 	/* Since reconfiguration requests while NFP is down are ignored we
 	 * have to wipe the entire VXLAN configuration and reinitialize it.
 	 */
-	if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
+	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN) {
 		memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
 		memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
-		udp_tunnel_get_rx_info(nn->netdev);
+		udp_tunnel_get_rx_info(nn->dp.netdev);
 	}
 
-	return err;
-}
-
-/**
- * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
- * @nn:      NFP Net device to reconfigure
- */
-static int nfp_net_set_config_and_enable(struct nfp_net *nn)
-{
-	int err;
-
-	err = __nfp_net_set_config_and_enable(nn);
-	if (err)
-		nfp_net_clear_config_and_disable(nn);
-
-	return err;
+	return 0;
 }
 
 /**
@@ -2252,12 +2269,12 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		napi_enable(&nn->r_vecs[r].napi);
 		enable_irq(nn->r_vecs[r].irq_vector);
 	}
 
-	netif_tx_wake_all_queues(nn->netdev);
+	netif_tx_wake_all_queues(nn->dp.netdev);
 
 	enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 	nfp_net_read_link_status(nn);
@@ -2266,22 +2283,8 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 static int nfp_net_netdev_open(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = nn->netdev->mtu,
-		.dcnt = nn->rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = nn->num_tx_rings,
-		.dcnt = nn->txd_cnt,
-	};
 	int err, r;
 
-	if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) {
-		nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->ctrl);
-		return -EBUSY;
-	}
-
 	/* Step 1: Allocate resources for rings and the like
 	 * - Request interrupts
 	 * - Allocate RX and TX ring resources
@@ -2299,33 +2302,28 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		goto err_free_exn;
 	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
 		if (err)
 			goto err_cleanup_vec_p;
 	}
 
-	nn->rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->xdp_prog);
-	if (!nn->rx_rings) {
-		err = -ENOMEM;
+	err = nfp_net_rx_rings_prepare(nn, &nn->dp);
+	if (err)
 		goto err_cleanup_vec;
-	}
 
-	nn->tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx,
-						   nn->num_stack_tx_rings);
-	if (!nn->tx_rings) {
-		err = -ENOMEM;
+	err = nfp_net_tx_rings_prepare(nn, &nn->dp);
+	if (err)
 		goto err_free_rx_rings;
-	}
 
 	for (r = 0; r < nn->max_r_vecs; r++)
-		nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
+		nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
 
-	err = netif_set_real_num_tx_queues(netdev, nn->num_stack_tx_rings);
+	err = netif_set_real_num_tx_queues(netdev, nn->dp.num_stack_tx_rings);
 	if (err)
 		goto err_free_rings;
 
-	err = netif_set_real_num_rx_queues(netdev, nn->num_rx_rings);
+	err = netif_set_real_num_rx_queues(netdev, nn->dp.num_rx_rings);
 	if (err)
 		goto err_free_rings;
 
@@ -2351,11 +2349,11 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	return 0;
 
 err_free_rings:
-	nfp_net_tx_ring_set_free(nn, &tx);
+	nfp_net_tx_rings_free(&nn->dp);
 err_free_rx_rings:
-	nfp_net_rx_ring_set_free(nn, &rx, nn->xdp_prog);
+	nfp_net_rx_rings_free(&nn->dp);
 err_cleanup_vec:
-	r = nn->num_r_vecs;
+	r = nn->dp.num_r_vecs;
 err_cleanup_vec_p:
 	while (r--)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
@@ -2374,15 +2372,15 @@ static void nfp_net_close_stack(struct nfp_net *nn)
 	unsigned int r;
 
 	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
-	netif_carrier_off(nn->netdev);
+	netif_carrier_off(nn->dp.netdev);
 	nn->link_up = false;
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		disable_irq(nn->r_vecs[r].irq_vector);
 		napi_disable(&nn->r_vecs[r].napi);
 	}
 
-	netif_tx_disable(nn->netdev);
+	netif_tx_disable(nn->dp.netdev);
 }
 
 /**
@@ -2393,17 +2391,19 @@ static void nfp_net_close_free_all(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	for (r = 0; r < nn->num_rx_rings; r++) {
-		nfp_net_rx_ring_bufs_free(nn, &nn->rx_rings[r], nn->xdp_prog);
-		nfp_net_rx_ring_free(&nn->rx_rings[r]);
+	for (r = 0; r < nn->dp.num_rx_rings; r++) {
+		nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r]);
+		nfp_net_rx_ring_free(&nn->dp.rx_rings[r]);
+	}
+	for (r = 0; r < nn->dp.num_tx_rings; r++) {
+		nfp_net_tx_ring_bufs_free(&nn->dp, &nn->dp.tx_rings[r]);
+		nfp_net_tx_ring_free(&nn->dp.tx_rings[r]);
 	}
-	for (r = 0; r < nn->num_tx_rings; r++)
-		nfp_net_tx_ring_free(&nn->tx_rings[r]);
-	for (r = 0; r < nn->num_r_vecs; r++)
+	for (r = 0; r < nn->dp.num_r_vecs; r++)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 
-	kfree(nn->rx_rings);
-	kfree(nn->tx_rings);
+	kfree(nn->dp.rx_rings);
+	kfree(nn->dp.tx_rings);
 
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
@@ -2417,11 +2417,6 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) {
-		nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl);
-		return 0;
-	}
-
 	/* Step 1: Disable RX and TX rings from the Linux kernel perspective
 	 */
 	nfp_net_close_stack(nn);
@@ -2443,7 +2438,7 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	u32 new_ctrl;
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 
 	if (netdev->flags & IFF_PROMISC) {
 		if (nn->cap & NFP_NET_CFG_CTRL_PROMISC)
@@ -2454,13 +2449,13 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
 		new_ctrl &= ~NFP_NET_CFG_CTRL_PROMISC;
 	}
 
-	if (new_ctrl == nn->ctrl)
+	if (new_ctrl == nn->dp.ctrl)
 		return;
 
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_GEN);
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 }
 
 static void nfp_net_rss_init_itbl(struct nfp_net *nn)
@@ -2469,181 +2464,174 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn)
 
 	for (i = 0; i < sizeof(nn->rss_itbl); i++)
 		nn->rss_itbl[i] =
-			ethtool_rxfh_indir_default(i, nn->num_rx_rings);
+			ethtool_rxfh_indir_default(i, nn->dp.num_rx_rings);
 }
 
-static int
-nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs,
-			 unsigned int *stack_tx_rings,
-			 struct bpf_prog **xdp_prog,
-			 struct nfp_net_ring_set *rx,
-			 struct nfp_net_ring_set *tx)
+static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp)
+{
+	struct nfp_net_dp new_dp = *dp;
+
+	*dp = nn->dp;
+	nn->dp = new_dp;
+
+	nn->dp.netdev->mtu = new_dp.mtu;
+
+	if (!netif_is_rxfh_configured(nn->dp.netdev))
+		nfp_net_rss_init_itbl(nn);
+}
+
+static int nfp_net_dp_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
 	unsigned int r;
 	int err;
 
-	if (rx)
-		nfp_net_rx_ring_set_swap(nn, rx);
-	if (tx)
-		nfp_net_tx_ring_set_swap(nn, tx);
-
-	swap(*num_vecs, nn->num_r_vecs);
-	swap(*stack_tx_rings, nn->num_stack_tx_rings);
-	*xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
+	nfp_net_dp_swap(nn, dp);
 
 	for (r = 0; r <	nn->max_r_vecs; r++)
-		nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
+		nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
 
-	if (!netif_is_rxfh_configured(nn->netdev))
-		nfp_net_rss_init_itbl(nn);
-
-	err = netif_set_real_num_rx_queues(nn->netdev,
-					   nn->num_rx_rings);
+	err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings);
 	if (err)
 		return err;
 
-	if (nn->netdev->real_num_tx_queues != nn->num_stack_tx_rings) {
-		err = netif_set_real_num_tx_queues(nn->netdev,
-						   nn->num_stack_tx_rings);
+	if (nn->dp.netdev->real_num_tx_queues != nn->dp.num_stack_tx_rings) {
+		err = netif_set_real_num_tx_queues(nn->dp.netdev,
+						   nn->dp.num_stack_tx_rings);
 		if (err)
 			return err;
 	}
 
-	return __nfp_net_set_config_and_enable(nn);
+	return nfp_net_set_config_and_enable(nn);
+}
+
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn)
+{
+	struct nfp_net_dp *new;
+
+	new = kmalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	*new = nn->dp;
+
+	/* Clear things which need to be recomputed */
+	new->fl_bufsz = 0;
+	new->tx_rings = NULL;
+	new->rx_rings = NULL;
+	new->num_r_vecs = 0;
+	new->num_stack_tx_rings = 0;
+
+	return new;
 }
 
 static int
-nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog,
-		     struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp,
+		     struct netlink_ext_ack *extack)
 {
 	/* XDP-enabled tests */
-	if (!xdp_prog)
+	if (!dp->xdp_prog)
 		return 0;
-	if (rx && nfp_net_calc_fl_bufsz(nn, rx->mtu) > PAGE_SIZE) {
-		nn_warn(nn, "MTU too large w/ XDP enabled\n");
+	if (dp->fl_bufsz > PAGE_SIZE) {
+		NL_MOD_TRY_SET_ERR_MSG(extack, "MTU too large w/ XDP enabled");
 		return -EINVAL;
 	}
-	if (tx && tx->n_rings > nn->max_tx_rings) {
-		nn_warn(nn, "Insufficient number of TX rings w/ XDP enabled\n");
+	if (dp->num_tx_rings > nn->max_tx_rings) {
+		NL_MOD_TRY_SET_ERR_MSG(extack, "Insufficient number of TX rings w/ XDP enabled");
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
-static void
-nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-			   struct nfp_net_ring_set *rx,
-			   struct nfp_net_ring_set *tx,
-			   unsigned int stack_tx_rings, unsigned int num_vecs)
-{
-	nn->netdev->mtu = rx ? rx->mtu : nn->netdev->mtu;
-	nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, nn->netdev->mtu);
-	nn->rxd_cnt = rx ? rx->dcnt : nn->rxd_cnt;
-	nn->txd_cnt = tx ? tx->dcnt : nn->txd_cnt;
-	nn->num_rx_rings = rx ? rx->n_rings : nn->num_rx_rings;
-	nn->num_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
-	nn->num_stack_tx_rings = stack_tx_rings;
-	nn->num_r_vecs = num_vecs;
-	*xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
-
-	if (!netif_is_rxfh_configured(nn->netdev))
-		nfp_net_rss_init_itbl(nn);
-}
-
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-		      struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp,
+			  struct netlink_ext_ack *extack)
 {
-	unsigned int stack_tx_rings, num_vecs, r;
-	int err;
+	int r, err;
 
-	stack_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
-	if (*xdp_prog)
-		stack_tx_rings -= rx ? rx->n_rings : nn->num_rx_rings;
+	dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp);
 
-	num_vecs = max(rx ? rx->n_rings : nn->num_rx_rings, stack_tx_rings);
+	dp->num_stack_tx_rings = dp->num_tx_rings;
+	if (dp->xdp_prog)
+		dp->num_stack_tx_rings -= dp->num_rx_rings;
 
-	err = nfp_net_check_config(nn, *xdp_prog, rx, tx);
+	dp->num_r_vecs = max(dp->num_rx_rings, dp->num_stack_tx_rings);
+
+	err = nfp_net_check_config(nn, dp, extack);
 	if (err)
-		return err;
+		goto exit_free_dp;
 
-	if (!netif_running(nn->netdev)) {
-		nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx,
-					   stack_tx_rings, num_vecs);
-		return 0;
+	if (!netif_running(dp->netdev)) {
+		nfp_net_dp_swap(nn, dp);
+		err = 0;
+		goto exit_free_dp;
 	}
 
 	/* Prepare new rings */
-	for (r = nn->num_r_vecs; r < num_vecs; r++) {
+	for (r = nn->dp.num_r_vecs; r < dp->num_r_vecs; r++) {
 		err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
 		if (err) {
-			num_vecs = r;
-			goto err_cleanup_vecs;
-		}
-	}
-	if (rx) {
-		if (!nfp_net_rx_ring_set_prepare(nn, rx, *xdp_prog)) {
-			err = -ENOMEM;
+			dp->num_r_vecs = r;
 			goto err_cleanup_vecs;
 		}
 	}
-	if (tx) {
-		if (!nfp_net_tx_ring_set_prepare(nn, tx, stack_tx_rings)) {
-			err = -ENOMEM;
-			goto err_free_rx;
-		}
-	}
+
+	err = nfp_net_rx_rings_prepare(nn, dp);
+	if (err)
+		goto err_cleanup_vecs;
+
+	err = nfp_net_tx_rings_prepare(nn, dp);
+	if (err)
+		goto err_free_rx;
 
 	/* Stop device, swap in new rings, try to start the firmware */
 	nfp_net_close_stack(nn);
 	nfp_net_clear_config_and_disable(nn);
 
-	err = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
-				       xdp_prog, rx, tx);
+	err = nfp_net_dp_swap_enable(nn, dp);
 	if (err) {
 		int err2;
 
 		nfp_net_clear_config_and_disable(nn);
 
 		/* Try with old configuration and old rings */
-		err2 = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
-						xdp_prog, rx, tx);
+		err2 = nfp_net_dp_swap_enable(nn, dp);
 		if (err2)
 			nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n",
 			       err, err2);
 	}
-	for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+	for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 
-	if (rx)
-		nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
-	if (tx)
-		nfp_net_tx_ring_set_free(nn, tx);
+	nfp_net_rx_rings_free(dp);
+	nfp_net_tx_rings_free(dp);
 
 	nfp_net_open_stack(nn);
+exit_free_dp:
+	kfree(dp);
 
 	return err;
 
 err_free_rx:
-	if (rx)
-		nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
+	nfp_net_rx_rings_free(dp);
 err_cleanup_vecs:
-	for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+	for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
+	kfree(dp);
 	return err;
 }
 
 static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = new_mtu,
-		.dcnt = nn->rxd_cnt,
-	};
+	struct nfp_net_dp *dp;
+
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
 
-	return nfp_net_ring_reconfig(nn, &nn->xdp_prog, &rx, NULL);
+	dp->mtu = new_mtu;
+
+	return nfp_net_ring_reconfig(nn, dp, NULL);
 }
 
 static void nfp_net_stat64(struct net_device *netdev,
@@ -2652,7 +2640,7 @@ static void nfp_net_stat64(struct net_device *netdev,
 	struct nfp_net *nn = netdev_priv(netdev);
 	int r;
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		struct nfp_net_r_vector *r_vec = &nn->r_vecs[r];
 		u64 data[3];
 		unsigned int start;
@@ -2694,12 +2682,12 @@ nfp_net_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 	struct nfp_net *nn = netdev_priv(netdev);
 
 	if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	if (proto != htons(ETH_P_ALL))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) {
-		if (!nn->bpf_offload_xdp)
+		if (!nn->dp.bpf_offload_xdp)
 			return nfp_net_bpf_offload(nn, tc->cls_bpf);
 		else
 			return -EBUSY;
@@ -2718,7 +2706,7 @@ static int nfp_net_set_features(struct net_device *netdev,
 
 	/* Assume this is not called with features we have not advertised */
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 
 	if (changed & NETIF_F_RXCSUM) {
 		if (features & NETIF_F_RXCSUM)
@@ -2762,7 +2750,7 @@ static int nfp_net_set_features(struct net_device *netdev,
 			new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER;
 	}
 
-	if (changed & NETIF_F_HW_TC && nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
+	if (changed & NETIF_F_HW_TC && nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) {
 		nn_err(nn, "Cannot disable HW TC offload while in use\n");
 		return -EBUSY;
 	}
@@ -2770,16 +2758,16 @@ static int nfp_net_set_features(struct net_device *netdev,
 	nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n",
 	       netdev->features, features, changed);
 
-	if (new_ctrl == nn->ctrl)
+	if (new_ctrl == nn->dp.ctrl)
 		return 0;
 
-	nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->ctrl, new_ctrl);
+	nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->dp.ctrl, new_ctrl);
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 	if (err)
 		return err;
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 
 	return 0;
 }
@@ -2830,6 +2818,26 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
+static int
+nfp_net_get_phys_port_name(struct net_device *netdev, char *name, size_t len)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	int err;
+
+	if (!nn->eth_port)
+		return -EOPNOTSUPP;
+
+	if (!nn->eth_port->is_split)
+		err = snprintf(name, len, "p%d", nn->eth_port->label_port);
+	else
+		err = snprintf(name, len, "p%ds%d", nn->eth_port->label_port,
+			       nn->eth_port->label_subport);
+	if (err >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * nfp_net_set_vxlan_port() - set vxlan port in SW and reconfigure HW
  * @nn:   NFP Net device to reconfigure
@@ -2842,7 +2850,7 @@ static void nfp_net_set_vxlan_port(struct nfp_net *nn, int idx, __be16 port)
 
 	nn->vxlan_ports[idx] = port;
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_VXLAN))
+	if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN))
 		return;
 
 	BUILD_BUG_ON(NFP_NET_N_VXLAN_PORTS & 1);
@@ -2921,8 +2929,8 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
 	if (!nfp_net_ebpf_capable(nn))
 		return -EINVAL;
 
-	if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
-		if (!nn->bpf_offload_xdp)
+	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) {
+		if (!nn->dp.bpf_offload_xdp)
 			return prog ? -EBUSY : 0;
 		cmd.command = prog ? TC_CLSBPF_REPLACE : TC_CLSBPF_DESTROY;
 	} else {
@@ -2935,48 +2943,44 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
 	/* Stop offload if replace not possible */
 	if (ret && cmd.command == TC_CLSBPF_REPLACE)
 		nfp_net_xdp_offload(nn, NULL);
-	nn->bpf_offload_xdp = prog && !ret;
+	nn->dp.bpf_offload_xdp = prog && !ret;
 	return ret;
 }
 
-static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog)
+static int nfp_net_xdp_setup(struct nfp_net *nn, struct netdev_xdp *xdp)
 {
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = nn->netdev->mtu,
-		.dcnt = nn->rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = nn->num_tx_rings,
-		.dcnt = nn->txd_cnt,
-	};
+	struct bpf_prog *old_prog = nn->dp.xdp_prog;
+	struct bpf_prog *prog = xdp->prog;
+	struct nfp_net_dp *dp;
 	int err;
 
-	if (prog && prog->xdp_adjust_head) {
-		nn_err(nn, "Does not support bpf_xdp_adjust_head()\n");
-		return -EOPNOTSUPP;
-	}
-	if (!prog && !nn->xdp_prog)
+	if (!prog && !nn->dp.xdp_prog)
 		return 0;
-	if (prog && nn->xdp_prog) {
-		prog = xchg(&nn->xdp_prog, prog);
+	if (prog && nn->dp.xdp_prog) {
+		prog = xchg(&nn->dp.xdp_prog, prog);
 		bpf_prog_put(prog);
-		nfp_net_xdp_offload(nn, nn->xdp_prog);
+		nfp_net_xdp_offload(nn, nn->dp.xdp_prog);
 		return 0;
 	}
 
-	tx.n_rings += prog ? nn->num_rx_rings : -nn->num_rx_rings;
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
+
+	dp->xdp_prog = prog;
+	dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings;
+	dp->rx_dma_dir = prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	dp->rx_dma_off = prog ? XDP_PACKET_HEADROOM - nn->dp.rx_offset : 0;
 
 	/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
-	err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx);
+	err = nfp_net_ring_reconfig(nn, dp, xdp->extack);
 	if (err)
 		return err;
 
-	/* @prog got swapped and is now the old one */
-	if (prog)
-		bpf_prog_put(prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
-	nfp_net_xdp_offload(nn, nn->xdp_prog);
+	nfp_net_xdp_offload(nn, nn->dp.xdp_prog);
 
 	return 0;
 }
@@ -2987,9 +2991,9 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
-		return nfp_net_xdp_setup(nn, xdp->prog);
+		return nfp_net_xdp_setup(nn, xdp);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nn->xdp_prog;
+		xdp->prog_attached = !!nn->dp.xdp_prog;
 		return 0;
 	default:
 		return -EINVAL;
@@ -3008,6 +3012,7 @@ static const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_set_features	= nfp_net_set_features,
 	.ndo_features_check	= nfp_net_features_check,
+	.ndo_get_phys_port_name	= nfp_net_get_phys_port_name,
 	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
 	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 	.ndo_xdp		= nfp_net_xdp,
@@ -3020,9 +3025,9 @@ static const struct net_device_ops nfp_net_netdev_ops = {
 void nfp_net_info(struct nfp_net *nn)
 {
 	nn_info(nn, "Netronome NFP-6xxx %sNetdev: TxQs=%d/%d RxQs=%d/%d\n",
-		nn->is_vf ? "VF " : "",
-		nn->num_tx_rings, nn->max_tx_rings,
-		nn->num_rx_rings, nn->max_rx_rings);
+		nn->dp.is_vf ? "VF " : "",
+		nn->dp.num_tx_rings, nn->max_tx_rings,
+		nn->dp.num_rx_rings, nn->max_rx_rings);
 	nn_info(nn, "VER: %d.%d.%d.%d, Maximum supported MTU: %d\n",
 		nn->fw_ver.resv, nn->fw_ver.class,
 		nn->fw_ver.major, nn->fw_ver.minor,
@@ -3074,21 +3079,24 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	nn = netdev_priv(netdev);
 
-	nn->netdev = netdev;
+	nn->dp.netdev = netdev;
+	nn->dp.dev = &pdev->dev;
 	nn->pdev = pdev;
 
 	nn->max_tx_rings = max_tx_rings;
 	nn->max_rx_rings = max_rx_rings;
 
-	nn->num_tx_rings = min_t(unsigned int, max_tx_rings, num_online_cpus());
-	nn->num_rx_rings = min_t(unsigned int, max_rx_rings,
+	nn->dp.num_tx_rings = min_t(unsigned int,
+				    max_tx_rings, num_online_cpus());
+	nn->dp.num_rx_rings = min_t(unsigned int, max_rx_rings,
 				 netif_get_num_default_rss_queues());
 
-	nn->num_r_vecs = max(nn->num_tx_rings, nn->num_rx_rings);
-	nn->num_r_vecs = min_t(unsigned int, nn->num_r_vecs, num_online_cpus());
+	nn->dp.num_r_vecs = max(nn->dp.num_tx_rings, nn->dp.num_rx_rings);
+	nn->dp.num_r_vecs = min_t(unsigned int,
+				  nn->dp.num_r_vecs, num_online_cpus());
 
-	nn->txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
-	nn->rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
+	nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
+	nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
 
 	spin_lock_init(&nn->reconfig_lock);
 	spin_lock_init(&nn->rx_filter_lock);
@@ -3108,7 +3116,28 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
  */
 void nfp_net_netdev_free(struct nfp_net *nn)
 {
-	free_netdev(nn->netdev);
+	free_netdev(nn->dp.netdev);
+}
+
+/**
+ * nfp_net_rss_key_sz() - Get current size of the RSS key
+ * @nn:		NFP Net device instance
+ *
+ * Return: size of the RSS key for currently selected hash function.
+ */
+unsigned int nfp_net_rss_key_sz(struct nfp_net *nn)
+{
+	switch (nn->rss_hfunc) {
+	case ETH_RSS_HASH_TOP:
+		return NFP_NET_CFG_RSS_KEY_SZ;
+	case ETH_RSS_HASH_XOR:
+		return 0;
+	case ETH_RSS_HASH_CRC32:
+		return 4;
+	}
+
+	nn_warn(nn, "Unknown hash function: %u\n", nn->rss_hfunc);
+	return 0;
 }
 
 /**
@@ -3117,14 +3146,32 @@ void nfp_net_netdev_free(struct nfp_net *nn)
  */
 static void nfp_net_rss_init(struct nfp_net *nn)
 {
-	netdev_rss_key_fill(nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
+	unsigned long func_bit, rss_cap_hfunc;
+	u32 reg;
+
+	/* Read the RSS function capability and select first supported func */
+	reg = nn_readl(nn, NFP_NET_CFG_RSS_CAP);
+	rss_cap_hfunc =	FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, reg);
+	if (!rss_cap_hfunc)
+		rss_cap_hfunc =	FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC,
+					  NFP_NET_CFG_RSS_TOEPLITZ);
+
+	func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS);
+	if (func_bit == NFP_NET_CFG_RSS_HFUNCS) {
+		dev_warn(nn->dp.dev,
+			 "Bad RSS config, defaulting to Toeplitz hash\n");
+		func_bit = ETH_RSS_HASH_TOP_BIT;
+	}
+	nn->rss_hfunc = 1 << func_bit;
+
+	netdev_rss_key_fill(nn->rss_key, nfp_net_rss_key_sz(nn));
 
 	nfp_net_rss_init_itbl(nn);
 
 	/* Enable IPv4/IPv6 TCP by default */
 	nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP |
 		      NFP_NET_CFG_RSS_IPV6_TCP |
-		      NFP_NET_CFG_RSS_TOEPLITZ |
+		      FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc) |
 		      NFP_NET_CFG_RSS_MASK;
 }
 
@@ -3151,6 +3198,10 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int err;
 
+	nn->dp.chained_metadata_format = nn->fw_ver.major > 3;
+
+	nn->dp.rx_dma_dir = DMA_FROM_DEVICE;
+
 	/* Get some of the read-only fields from the BAR */
 	nn->cap = nn_readl(nn, NFP_NET_CFG_CAP);
 	nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU);
@@ -3158,17 +3209,26 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	nfp_net_write_mac_addr(nn);
 
 	/* Determine RX packet/metadata boundary offset */
-	if (nn->fw_ver.major >= 2)
-		nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
-	else
-		nn->rx_offset = NFP_NET_RX_OFFSET;
+	if (nn->fw_ver.major >= 2) {
+		u32 reg;
+
+		reg = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
+		if (reg > NFP_NET_MAX_PREPEND) {
+			nn_err(nn, "Invalid rx offset: %d\n", reg);
+			return -EINVAL;
+		}
+		nn->dp.rx_offset = reg;
+	} else {
+		nn->dp.rx_offset = NFP_NET_RX_OFFSET;
+	}
 
 	/* Set default MTU and Freelist buffer size */
 	if (nn->max_mtu < NFP_NET_DEFAULT_MTU)
 		netdev->mtu = nn->max_mtu;
 	else
 		netdev->mtu = NFP_NET_DEFAULT_MTU;
-	nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, netdev->mtu);
+	nn->dp.mtu = netdev->mtu;
+	nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp);
 
 	/* Advertise/enable offloads based on capabilities
 	 *
@@ -3179,31 +3239,31 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	netdev->hw_features = NETIF_F_HIGHDMA;
 	if (nn->cap & NFP_NET_CFG_CTRL_RXCSUM) {
 		netdev->hw_features |= NETIF_F_RXCSUM;
-		nn->ctrl |= NFP_NET_CFG_CTRL_RXCSUM;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXCSUM;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_TXCSUM) {
 		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-		nn->ctrl |= NFP_NET_CFG_CTRL_TXCSUM;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXCSUM;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_GATHER) {
 		netdev->hw_features |= NETIF_F_SG;
-		nn->ctrl |= NFP_NET_CFG_CTRL_GATHER;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_GATHER;
 	}
 	if ((nn->cap & NFP_NET_CFG_CTRL_LSO) && nn->fw_ver.major > 2) {
 		netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
-		nn->ctrl |= NFP_NET_CFG_CTRL_LSO;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_LSO;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
 		netdev->hw_features |= NETIF_F_RXHASH;
 		nfp_net_rss_init(nn);
-		nn->ctrl |= NFP_NET_CFG_CTRL_RSS;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_RSS;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_VXLAN &&
 	    nn->cap & NFP_NET_CFG_CTRL_NVGRE) {
 		if (nn->cap & NFP_NET_CFG_CTRL_LSO)
 			netdev->hw_features |= NETIF_F_GSO_GRE |
 					       NETIF_F_GSO_UDP_TUNNEL;
-		nn->ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE;
 
 		netdev->hw_enc_features = netdev->hw_features;
 	}
@@ -3212,11 +3272,11 @@ int nfp_net_netdev_init(struct net_device *netdev)
 
 	if (nn->cap & NFP_NET_CFG_CTRL_RXVLAN) {
 		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
-		nn->ctrl |= NFP_NET_CFG_CTRL_RXVLAN;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXVLAN;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_TXVLAN) {
 		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
-		nn->ctrl |= NFP_NET_CFG_CTRL_TXVLAN;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXVLAN;
 	}
 
 	netdev->features = netdev->hw_features;
@@ -3229,14 +3289,14 @@ int nfp_net_netdev_init(struct net_device *netdev)
 
 	/* Allow L2 Broadcast and Multicast through by default, if supported */
 	if (nn->cap & NFP_NET_CFG_CTRL_L2BC)
-		nn->ctrl |= NFP_NET_CFG_CTRL_L2BC;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2BC;
 	if (nn->cap & NFP_NET_CFG_CTRL_L2MC)
-		nn->ctrl |= NFP_NET_CFG_CTRL_L2MC;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2MC;
 
 	/* Allow IRQ moderation, if supported */
 	if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) {
 		nfp_net_irqmod_init(nn);
-		nn->ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
 	}
 
 	/* Stash the re-configuration queue away.  First odd queue in TX Bar */
@@ -3275,9 +3335,10 @@ void nfp_net_netdev_clean(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-	if (nn->bpf_offload_xdp)
+	unregister_netdev(nn->dp.netdev);
+
+	if (nn->dp.xdp_prog)
+		bpf_prog_put(nn->dp.xdp_prog);
+	if (nn->dp.bpf_offload_xdp)
 		nfp_net_xdp_offload(nn, NULL);
-	unregister_netdev(nn->netdev);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 385ba355c965..d04ccc9f6116 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Netronome Systems, Inc.
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -177,6 +177,19 @@
 #define   NFP_NET_CFG_VERSION_MINOR(x)    (((x) & 0xff) <<  0)
 #define NFP_NET_CFG_STS                 0x0034
 #define   NFP_NET_CFG_STS_LINK            (0x1 << 0) /* Link up or down */
+/* Link rate */
+#define   NFP_NET_CFG_STS_LINK_RATE_SHIFT 1
+#define   NFP_NET_CFG_STS_LINK_RATE_MASK  0xF
+#define   NFP_NET_CFG_STS_LINK_RATE       \
+	(NFP_NET_CFG_STS_LINK_RATE_MASK << NFP_NET_CFG_STS_LINK_RATE_SHIFT)
+#define   NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED   0
+#define   NFP_NET_CFG_STS_LINK_RATE_UNKNOWN       1
+#define   NFP_NET_CFG_STS_LINK_RATE_1G            2
+#define   NFP_NET_CFG_STS_LINK_RATE_10G           3
+#define   NFP_NET_CFG_STS_LINK_RATE_25G           4
+#define   NFP_NET_CFG_STS_LINK_RATE_40G           5
+#define   NFP_NET_CFG_STS_LINK_RATE_50G           6
+#define   NFP_NET_CFG_STS_LINK_RATE_100G          7
 #define NFP_NET_CFG_CAP                 0x0038
 #define NFP_NET_CFG_MAX_TXRINGS         0x003c
 #define NFP_NET_CFG_MAX_RXRINGS         0x0040
@@ -192,6 +205,14 @@
 #define NFP_NET_CFG_RX_OFFSET_DYNAMIC		0	/* Prepend mode */
 
 /**
+ * RSS capabilities
+ * @NFP_NET_CFG_RSS_CAP_HFUNC:	supported hash functions (same bits as
+ *				@NFP_NET_CFG_RSS_HFUNC)
+ */
+#define NFP_NET_CFG_RSS_CAP		0x0054
+#define   NFP_NET_CFG_RSS_CAP_HFUNC	  0xff000000
+
+/**
  * VXLAN/UDP encap configuration
  * @NFP_NET_CFG_VXLAN_PORT:	Base address of table of tunnels' UDP dst ports
  * @NFP_NET_CFG_VXLAN_SZ:	Size of the UDP port table in bytes
@@ -249,7 +270,11 @@
 #define   NFP_NET_CFG_RSS_IPV4_UDP        (1 << 11) /* RSS for IPv4/UDP */
 #define   NFP_NET_CFG_RSS_IPV6_TCP        (1 << 12) /* RSS for IPv6/TCP */
 #define   NFP_NET_CFG_RSS_IPV6_UDP        (1 << 13) /* RSS for IPv6/UDP */
+#define   NFP_NET_CFG_RSS_HFUNC		  0xff000000
 #define   NFP_NET_CFG_RSS_TOEPLITZ        (1 << 24) /* Use Toeplitz hash */
+#define   NFP_NET_CFG_RSS_XOR		  (1 << 25) /* Use XOR as hash */
+#define   NFP_NET_CFG_RSS_CRC32		  (1 << 26) /* Use CRC32 as hash */
+#define   NFP_NET_CFG_RSS_HFUNCS	  3
 #define NFP_NET_CFG_RSS_KEY             (NFP_NET_CFG_RSS_BASE + 0x4)
 #define NFP_NET_CFG_RSS_KEY_SZ          0x28
 #define NFP_NET_CFG_RSS_ITBL            (NFP_NET_CFG_RSS_BASE + 0x4 + \
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index 6e9372a18375..4077c59bf782 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -40,9 +40,9 @@ static struct dentry *nfp_dir;
 
 static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 {
-	int fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p, rxd_cnt;
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_rx_ring *rx_ring;
+	int fl_rd_p, fl_wr_p, rxd_cnt;
 	struct nfp_net_rx_desc *rxd;
 	struct nfp_net *nn;
 	void *frag;
@@ -54,19 +54,18 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 		goto out;
 	nn = r_vec->nfp_net;
 	rx_ring = r_vec->rx_ring;
-	if (!netif_running(nn->netdev))
+	if (!netif_running(nn->dp.netdev))
 		goto out;
 
 	rxd_cnt = rx_ring->cnt;
 
 	fl_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_fl);
 	fl_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_fl);
-	rx_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_rx);
-	rx_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_rx);
 
-	seq_printf(file, "RX[%02d]: H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n",
-		   rx_ring->idx, rx_ring->rd_p, rx_ring->wr_p,
-		   fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p);
+	seq_printf(file, "RX[%02d,%02d]: cnt=%d dma=%pad host=%p   H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d\n",
+		   rx_ring->idx, rx_ring->fl_qcidx,
+		   rx_ring->cnt, &rx_ring->dma, rx_ring->rxds,
+		   rx_ring->rd_p, rx_ring->wr_p, fl_rd_p, fl_wr_p);
 
 	for (i = 0; i < rxd_cnt; i++) {
 		rxd = &rx_ring->rxds[i];
@@ -89,10 +88,6 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 			seq_puts(file, " FL_RD");
 		if (i == fl_wr_p % rxd_cnt)
 			seq_puts(file, " FL_WR");
-		if (i == rx_rd_p % rxd_cnt)
-			seq_puts(file, " RX_RD");
-		if (i == rx_wr_p % rxd_cnt)
-			seq_puts(file, " RX_WR");
 
 		seq_putc(file, '\n');
 	}
@@ -143,7 +138,7 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
 	if (!r_vec->nfp_net || !tx_ring)
 		goto out;
 	nn = r_vec->nfp_net;
-	if (!netif_running(nn->netdev))
+	if (!netif_running(nn->dp.netdev))
 		goto out;
 
 	txd_cnt = tx_ring->cnt;
@@ -151,8 +146,11 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
 	d_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q);
 	d_wr_p = nfp_qcp_wr_ptr_read(tx_ring->qcp_q);
 
-	seq_printf(file, "TX[%02d]: H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n",
-		   tx_ring->idx, tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p);
+	seq_printf(file, "TX[%02d,%02d%s]: cnt=%d dma=%pad host=%p   H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n",
+		   tx_ring->idx, tx_ring->qcidx,
+		   tx_ring == r_vec->tx_ring ? "" : "xdp",
+		   tx_ring->cnt, &tx_ring->dma, tx_ring->txds,
+		   tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p);
 
 	for (i = 0; i < txd_cnt; i++) {
 		txd = &tx_ring->txds[i];
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 2649f7523c81..abbb47e60cc3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -40,6 +40,7 @@
  *          Brad Petrus <brad.petrus@netronome.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -48,6 +49,7 @@
 #include <linux/ethtool.h>
 
 #include "nfpcore/nfp.h"
+#include "nfpcore/nfp_nsp.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net.h"
 
@@ -126,9 +128,9 @@ static const struct _nfp_net_et_stats nfp_net_et_stats[] = {
 };
 
 #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats)
-#define NN_ET_RVEC_STATS_LEN (nn->num_r_vecs * 3)
+#define NN_ET_RVEC_STATS_LEN (nn->dp.num_r_vecs * 3)
 #define NN_ET_RVEC_GATHER_STATS 7
-#define NN_ET_QUEUE_STATS_LEN ((nn->num_tx_rings + nn->num_rx_rings) * 2)
+#define NN_ET_QUEUE_STATS_LEN ((nn->dp.num_tx_rings + nn->dp.num_rx_rings) * 2)
 #define NN_ET_STATS_LEN (NN_ET_GLOBAL_STATS_LEN + NN_ET_RVEC_GATHER_STATS + \
 			 NN_ET_RVEC_STATS_LEN + NN_ET_QUEUE_STATS_LEN)
 
@@ -172,6 +174,119 @@ static void nfp_net_get_drvinfo(struct net_device *netdev,
 	drvinfo->regdump_len = NFP_NET_CFG_BAR_SZ;
 }
 
+/**
+ * nfp_net_get_link_ksettings - Get Link Speed settings
+ * @netdev:	network interface device structure
+ * @cmd:	ethtool command
+ *
+ * Reports speed settings based on info in the BAR provided by the fw.
+ */
+static int
+nfp_net_get_link_ksettings(struct net_device *netdev,
+			   struct ethtool_link_ksettings *cmd)
+{
+	static const u32 ls_to_ethtool[] = {
+		[NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED]	= 0,
+		[NFP_NET_CFG_STS_LINK_RATE_UNKNOWN]	= SPEED_UNKNOWN,
+		[NFP_NET_CFG_STS_LINK_RATE_1G]		= SPEED_1000,
+		[NFP_NET_CFG_STS_LINK_RATE_10G]		= SPEED_10000,
+		[NFP_NET_CFG_STS_LINK_RATE_25G]		= SPEED_25000,
+		[NFP_NET_CFG_STS_LINK_RATE_40G]		= SPEED_40000,
+		[NFP_NET_CFG_STS_LINK_RATE_50G]		= SPEED_50000,
+		[NFP_NET_CFG_STS_LINK_RATE_100G]	= SPEED_100000,
+	};
+	struct nfp_net *nn = netdev_priv(netdev);
+	u32 sts, ls;
+
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+	cmd->base.port = PORT_OTHER;
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
+
+	if (nn->eth_port)
+		cmd->base.autoneg = nn->eth_port->aneg != NFP_ANEG_DISABLED ?
+			AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+	if (!netif_carrier_ok(netdev))
+		return 0;
+
+	/* Use link speed from ETH table if available, otherwise try the BAR */
+	if (nn->eth_port) {
+		int err;
+
+		if (nfp_net_link_changed_read_clear(nn)) {
+			err = nfp_net_refresh_eth_port(nn);
+			if (err)
+				return err;
+		}
+
+		cmd->base.port = nn->eth_port->port_type;
+		cmd->base.speed = nn->eth_port->speed;
+		cmd->base.duplex = DUPLEX_FULL;
+		return 0;
+	}
+
+	sts = nn_readl(nn, NFP_NET_CFG_STS);
+
+	ls = FIELD_GET(NFP_NET_CFG_STS_LINK_RATE, sts);
+	if (ls == NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED)
+		return -EOPNOTSUPP;
+
+	if (ls == NFP_NET_CFG_STS_LINK_RATE_UNKNOWN ||
+	    ls >= ARRAY_SIZE(ls_to_ethtool))
+		return 0;
+
+	cmd->base.speed = ls_to_ethtool[sts];
+	cmd->base.duplex = DUPLEX_FULL;
+
+	return 0;
+}
+
+static int
+nfp_net_set_link_ksettings(struct net_device *netdev,
+			   const struct ethtool_link_ksettings *cmd)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_nsp *nsp;
+	int err;
+
+	if (!nn->eth_port)
+		return -EOPNOTSUPP;
+
+	if (netif_running(netdev)) {
+		nn_warn(nn, "Changing settings not allowed on an active interface. It may cause the port to be disabled until reboot.\n");
+		return -EBUSY;
+	}
+
+	nsp = nfp_eth_config_start(nn->cpp, nn->eth_port->index);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	err = __nfp_eth_set_aneg(nsp, cmd->base.autoneg == AUTONEG_ENABLE ?
+				 NFP_ANEG_AUTO : NFP_ANEG_DISABLED);
+	if (err)
+		goto err_bad_set;
+	if (cmd->base.speed != SPEED_UNKNOWN) {
+		u32 speed = cmd->base.speed / nn->eth_port->lanes;
+
+		err = __nfp_eth_set_speed(nsp, speed);
+		if (err)
+			goto err_bad_set;
+	}
+
+	err = nfp_eth_config_commit_end(nsp);
+	if (err > 0)
+		return 0; /* no change */
+
+	nfp_net_refresh_port_table(nn);
+
+	return err;
+
+err_bad_set:
+	nfp_eth_config_cleanup_end(nsp);
+	return err;
+}
+
 static void nfp_net_get_ringparam(struct net_device *netdev,
 				  struct ethtool_ringparam *ring)
 {
@@ -179,30 +294,22 @@ static void nfp_net_get_ringparam(struct net_device *netdev,
 
 	ring->rx_max_pending = NFP_NET_MAX_RX_DESCS;
 	ring->tx_max_pending = NFP_NET_MAX_TX_DESCS;
-	ring->rx_pending = nn->rxd_cnt;
-	ring->tx_pending = nn->txd_cnt;
+	ring->rx_pending = nn->dp.rxd_cnt;
+	ring->tx_pending = nn->dp.txd_cnt;
 }
 
 static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
 {
-	struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = nn->netdev->mtu,
-		.dcnt = rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = nn->num_tx_rings,
-		.dcnt = txd_cnt,
-	};
+	struct nfp_net_dp *dp;
 
-	if (nn->rxd_cnt != rxd_cnt)
-		reconfig_rx = &rx;
-	if (nn->txd_cnt != txd_cnt)
-		reconfig_tx = &tx;
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
 
-	return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
-				     reconfig_rx, reconfig_tx);
+	dp->rxd_cnt = rxd_cnt;
+	dp->txd_cnt = txd_cnt;
+
+	return nfp_net_ring_reconfig(nn, dp, NULL);
 }
 
 static int nfp_net_set_ringparam(struct net_device *netdev,
@@ -223,11 +330,11 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
 	    txd_cnt < NFP_NET_MIN_TX_DESCS || txd_cnt > NFP_NET_MAX_TX_DESCS)
 		return -EINVAL;
 
-	if (nn->rxd_cnt == rxd_cnt && nn->txd_cnt == txd_cnt)
+	if (nn->dp.rxd_cnt == rxd_cnt && nn->dp.txd_cnt == txd_cnt)
 		return 0;
 
 	nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n",
-	       nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt);
+	       nn->dp.rxd_cnt, rxd_cnt, nn->dp.txd_cnt, txd_cnt);
 
 	return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt);
 }
@@ -245,7 +352,7 @@ static void nfp_net_get_strings(struct net_device *netdev,
 			memcpy(p, nfp_net_et_stats[i].name, ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < nn->num_r_vecs; i++) {
+		for (i = 0; i < nn->dp.num_r_vecs; i++) {
 			sprintf(p, "rvec_%u_rx_pkts", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "rvec_%u_tx_pkts", i);
@@ -267,13 +374,13 @@ static void nfp_net_get_strings(struct net_device *netdev,
 		p += ETH_GSTRING_LEN;
 		strncpy(p, "tx_lso", ETH_GSTRING_LEN);
 		p += ETH_GSTRING_LEN;
-		for (i = 0; i < nn->num_tx_rings; i++) {
+		for (i = 0; i < nn->dp.num_tx_rings; i++) {
 			sprintf(p, "txq_%u_pkts", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "txq_%u_bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < nn->num_rx_rings; i++) {
+		for (i = 0; i < nn->dp.num_rx_rings; i++) {
 			sprintf(p, "rxq_%u_pkts", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "rxq_%u_bytes", i);
@@ -306,12 +413,12 @@ static void nfp_net_get_stats(struct net_device *netdev,
 			break;
 
 		case NFP_NET_DEV_ET_STATS:
-			io_p = nn->ctrl_bar + nfp_net_et_stats[i].off;
+			io_p = nn->dp.ctrl_bar + nfp_net_et_stats[i].off;
 			data[i] = readq(io_p);
 			break;
 		}
 	}
-	for (j = 0; j < nn->num_r_vecs; j++) {
+	for (j = 0; j < nn->dp.num_r_vecs; j++) {
 		unsigned int start;
 
 		do {
@@ -337,16 +444,16 @@ static void nfp_net_get_stats(struct net_device *netdev,
 	}
 	for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++)
 		data[i++] = gathered_stats[j];
-	for (j = 0; j < nn->num_tx_rings; j++) {
-		io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j);
+	for (j = 0; j < nn->dp.num_tx_rings; j++) {
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j);
 		data[i++] = readq(io_p);
-		io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8;
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8;
 		data[i++] = readq(io_p);
 	}
-	for (j = 0; j < nn->num_rx_rings; j++) {
-		io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j);
+	for (j = 0; j < nn->dp.num_rx_rings; j++) {
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j);
 		data[i++] = readq(io_p);
-		io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8;
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8;
 		data[i++] = readq(io_p);
 	}
 }
@@ -410,7 +517,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev,
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
-		cmd->data = nn->num_rx_rings;
+		cmd->data = nn->dp.num_rx_rings;
 		return 0;
 	case ETHTOOL_GRXFH:
 		return nfp_net_get_rss_hash_opts(nn, cmd);
@@ -454,13 +561,13 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn,
 		return -EINVAL;
 	}
 
-	new_rss_cfg |= NFP_NET_CFG_RSS_TOEPLITZ;
+	new_rss_cfg |= FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc);
 	new_rss_cfg |= NFP_NET_CFG_RSS_MASK;
 
 	if (new_rss_cfg == nn->rss_cfg)
 		return 0;
 
-	writel(new_rss_cfg, nn->ctrl_bar + NFP_NET_CFG_RSS_CTRL);
+	writel(new_rss_cfg, nn->dp.ctrl_bar + NFP_NET_CFG_RSS_CTRL);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_RSS);
 	if (err)
 		return err;
@@ -496,7 +603,12 @@ static u32 nfp_net_get_rxfh_indir_size(struct net_device *netdev)
 
 static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev)
 {
-	return NFP_NET_CFG_RSS_KEY_SZ;
+	struct nfp_net *nn = netdev_priv(netdev);
+
+	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS))
+		return -EOPNOTSUPP;
+
+	return nfp_net_rss_key_sz(nn);
 }
 
 static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
@@ -512,9 +624,12 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
 			indir[i] = nn->rss_itbl[i];
 	if (key)
-		memcpy(key, nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+		memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn));
+	if (hfunc) {
+		*hfunc = nn->rss_hfunc;
+		if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
+			*hfunc = ETH_RSS_HASH_UNKNOWN;
+	}
 
 	return 0;
 }
@@ -527,14 +642,14 @@ static int nfp_net_set_rxfh(struct net_device *netdev,
 	int i;
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS) ||
-	    !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == ETH_RSS_HASH_TOP))
+	    !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc))
 		return -EOPNOTSUPP;
 
 	if (!key && !indir)
 		return 0;
 
 	if (key) {
-		memcpy(nn->rss_key, key, NFP_NET_CFG_RSS_KEY_SZ);
+		memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn));
 		nfp_net_rss_write_key(nn);
 	}
 	if (indir) {
@@ -564,7 +679,7 @@ static void nfp_net_get_regs(struct net_device *netdev,
 	regs->version = nn_readl(nn, NFP_NET_CFG_VERSION);
 
 	for (i = 0; i < NFP_NET_CFG_BAR_SZ / sizeof(u32); i++)
-		regs_buf[i] = readl(nn->ctrl_bar + (i * sizeof(u32)));
+		regs_buf[i] = readl(nn->dp.ctrl_bar + (i * sizeof(u32)));
 }
 
 static int nfp_net_get_coalesce(struct net_device *netdev,
@@ -676,7 +791,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
 	    ec->tx_coalesce_usecs_high ||
 	    ec->tx_max_coalesced_frames_high ||
 	    ec->rate_sample_interval)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* Compute factor used to convert coalesce '_usecs' parameters to
 	 * ME timestamp ticks.  There are 16 ME clock cycles for each timestamp
@@ -736,16 +851,16 @@ static void nfp_net_get_channels(struct net_device *netdev,
 	struct nfp_net *nn = netdev_priv(netdev);
 	unsigned int num_tx_rings;
 
-	num_tx_rings = nn->num_tx_rings;
-	if (nn->xdp_prog)
-		num_tx_rings -= nn->num_rx_rings;
+	num_tx_rings = nn->dp.num_tx_rings;
+	if (nn->dp.xdp_prog)
+		num_tx_rings -= nn->dp.num_rx_rings;
 
 	channel->max_rx = min(nn->max_rx_rings, nn->max_r_vecs);
 	channel->max_tx = min(nn->max_tx_rings, nn->max_r_vecs);
 	channel->max_combined = min(channel->max_rx, channel->max_tx);
 	channel->max_other = NFP_NET_NON_Q_VECTORS;
-	channel->combined_count = min(nn->num_rx_rings, num_tx_rings);
-	channel->rx_count = nn->num_rx_rings - channel->combined_count;
+	channel->combined_count = min(nn->dp.num_rx_rings, num_tx_rings);
+	channel->rx_count = nn->dp.num_rx_rings - channel->combined_count;
 	channel->tx_count = num_tx_rings - channel->combined_count;
 	channel->other_count = NFP_NET_NON_Q_VECTORS;
 }
@@ -753,29 +868,19 @@ static void nfp_net_get_channels(struct net_device *netdev,
 static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx,
 				 unsigned int total_tx)
 {
-	struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
-	struct nfp_net_ring_set rx = {
-		.n_rings = total_rx,
-		.mtu = nn->netdev->mtu,
-		.dcnt = nn->rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = total_tx,
-		.dcnt = nn->txd_cnt,
-	};
+	struct nfp_net_dp *dp;
 
-	if (nn->num_rx_rings != total_rx)
-		reconfig_rx = &rx;
-	if (nn->num_stack_tx_rings != total_tx ||
-	    (nn->xdp_prog && reconfig_rx))
-		reconfig_tx = &tx;
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
 
-	/* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */
-	if (nn->xdp_prog)
-		tx.n_rings += total_rx;
+	dp->num_rx_rings = total_rx;
+	dp->num_tx_rings = total_tx;
+	/* nfp_net_check_config() will catch num_tx_rings > nn->max_tx_rings */
+	if (dp->xdp_prog)
+		dp->num_tx_rings += total_rx;
 
-	return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
-				     reconfig_rx, reconfig_tx);
+	return nfp_net_ring_reconfig(nn, dp, NULL);
 }
 
 static int nfp_net_set_channels(struct net_device *netdev,
@@ -823,6 +928,8 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.set_coalesce           = nfp_net_set_coalesce,
 	.get_channels		= nfp_net_get_channels,
 	.set_channels		= nfp_net_set_channels,
+	.get_link_ksettings	= nfp_net_get_link_ksettings,
+	.set_link_ksettings	= nfp_net_set_link_ksettings,
 };
 
 void nfp_net_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 3afcdc11480c..8cb87cbe1120 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -47,11 +47,12 @@
 #include <linux/pci_regs.h>
 #include <linux/msi.h>
 #include <linux/random.h>
+#include <linux/rtnetlink.h>
 
 #include "nfpcore/nfp.h"
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nffw.h"
-#include "nfpcore/nfp_nsp_eth.h"
+#include "nfpcore/nfp_nsp.h"
 #include "nfpcore/nfp6000_pcie.h"
 
 #include "nfp_net_ctrl.h"
@@ -129,61 +130,61 @@ err_area:
 	return (u8 __iomem *)ERR_PTR(err);
 }
 
+/**
+ * nfp_net_get_mac_addr() - Get the MAC address.
+ * @nn:       NFP Network structure
+ * @cpp:      NFP CPP handle
+ * @id:	      NFP port id
+ *
+ * First try to get the MAC address from NSP ETH table. If that
+ * fails try HWInfo.  As a last resort generate a random address.
+ */
 static void
-nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp,
-			    unsigned int id)
+nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_cpp *cpp, unsigned int id)
 {
+	struct nfp_net_dp *dp = &nn->dp;
 	u8 mac_addr[ETH_ALEN];
 	const char *mac_str;
 	char name[32];
 
+	if (nn->eth_port) {
+		ether_addr_copy(dp->netdev->dev_addr, nn->eth_port->mac_addr);
+		ether_addr_copy(dp->netdev->perm_addr, nn->eth_port->mac_addr);
+		return;
+	}
+
 	snprintf(name, sizeof(name), "eth%d.mac", id);
 
 	mac_str = nfp_hwinfo_lookup(cpp, name);
 	if (!mac_str) {
-		dev_warn(&nn->pdev->dev,
-			 "Can't lookup MAC address. Generate\n");
-		eth_hw_addr_random(nn->netdev);
+		dev_warn(dp->dev, "Can't lookup MAC address. Generate\n");
+		eth_hw_addr_random(dp->netdev);
 		return;
 	}
 
 	if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
 		   &mac_addr[0], &mac_addr[1], &mac_addr[2],
 		   &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) {
-		dev_warn(&nn->pdev->dev,
+		dev_warn(dp->dev,
 			 "Can't parse MAC address (%s). Generate.\n", mac_str);
-		eth_hw_addr_random(nn->netdev);
+		eth_hw_addr_random(dp->netdev);
 		return;
 	}
 
-	ether_addr_copy(nn->netdev->dev_addr, mac_addr);
-	ether_addr_copy(nn->netdev->perm_addr, mac_addr);
+	ether_addr_copy(dp->netdev->dev_addr, mac_addr);
+	ether_addr_copy(dp->netdev->perm_addr, mac_addr);
 }
 
-/**
- * nfp_net_get_mac_addr() - Get the MAC address.
- * @nn:       NFP Network structure
- * @pf:	      NFP PF device structure
- * @id:	      NFP port id
- *
- * First try to get the MAC address from NSP ETH table. If that
- * fails try HWInfo.  As a last resort generate a random address.
- */
-static void
-nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id)
+static struct nfp_eth_table_port *
+nfp_net_find_port(struct nfp_eth_table *eth_tbl, unsigned int id)
 {
 	int i;
 
-	for (i = 0; pf->eth_tbl && i < pf->eth_tbl->count; i++)
-		if (pf->eth_tbl->ports[i].eth_index == id) {
-			const u8 *mac_addr = pf->eth_tbl->ports[i].mac_addr;
+	for (i = 0; eth_tbl && i < eth_tbl->count; i++)
+		if (eth_tbl->ports[i].eth_index == id)
+			return &eth_tbl->ports[i];
 
-			ether_addr_copy(nn->netdev->dev_addr, mac_addr);
-			ether_addr_copy(nn->netdev->perm_addr, mac_addr);
-			return;
-		}
-
-	nfp_net_get_mac_addr_hwinfo(nn, pf->cpp, id);
+	return NULL;
 }
 
 static unsigned int nfp_net_pf_get_num_ports(struct nfp_pf *pf)
@@ -282,6 +283,7 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf)
 	while (!list_empty(&pf->ports)) {
 		nn = list_first_entry(&pf->ports, struct nfp_net, port_list);
 		list_del(&nn->port_list);
+		pf->num_netdevs--;
 
 		nfp_net_netdev_free(nn);
 	}
@@ -290,7 +292,8 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf)
 static struct nfp_net *
 nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar,
 			     void __iomem *tx_bar, void __iomem *rx_bar,
-			     int stride, struct nfp_net_fw_version *fw_ver)
+			     int stride, struct nfp_net_fw_version *fw_ver,
+			     struct nfp_eth_table_port *eth_port)
 {
 	u32 n_tx_rings, n_rx_rings;
 	struct nfp_net *nn;
@@ -305,12 +308,13 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar,
 
 	nn->cpp = pf->cpp;
 	nn->fw_ver = *fw_ver;
-	nn->ctrl_bar = ctrl_bar;
+	nn->dp.ctrl_bar = ctrl_bar;
 	nn->tx_bar = tx_bar;
 	nn->rx_bar = rx_bar;
-	nn->is_vf = 0;
+	nn->dp.is_vf = 0;
 	nn->stride_rx = stride;
 	nn->stride_tx = stride;
+	nn->eth_port = eth_port;
 
 	return nn;
 }
@@ -322,7 +326,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn,
 	int err;
 
 	/* Get MAC address */
-	nfp_net_get_mac_addr(nn, pf, id);
+	nfp_net_get_mac_addr(nn, pf->cpp, id);
 
 	/* Get ME clock frequency from ctrl BAR
 	 * XXX for now frequency is hardcoded until we figure out how
@@ -330,7 +334,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn,
 	 */
 	nn->me_freq_mhz = 1200;
 
-	err = nfp_net_netdev_init(nn->netdev);
+	err = nfp_net_netdev_init(nn->dp.netdev);
 	if (err)
 		return err;
 
@@ -347,6 +351,7 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar,
 			 int stride, struct nfp_net_fw_version *fw_ver)
 {
 	u32 prev_tx_base, prev_rx_base, tgt_tx_base, tgt_rx_base;
+	struct nfp_eth_table_port *eth_port;
 	struct nfp_net *nn;
 	unsigned int i;
 	int err;
@@ -362,17 +367,27 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar,
 		prev_tx_base = tgt_tx_base;
 		prev_rx_base = tgt_rx_base;
 
-		nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar, rx_bar,
-						  stride, fw_ver);
-		if (IS_ERR(nn)) {
-			err = PTR_ERR(nn);
-			goto err_free_prev;
+		eth_port = nfp_net_find_port(pf->eth_tbl, i);
+		if (eth_port && eth_port->override_changed) {
+			nfp_warn(pf->cpp, "Config changed for port #%d, reboot required before port will be operational\n", i);
+		} else {
+			nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar,
+							  rx_bar, stride,
+							  fw_ver, eth_port);
+			if (IS_ERR(nn)) {
+				err = PTR_ERR(nn);
+				goto err_free_prev;
+			}
+			list_add_tail(&nn->port_list, &pf->ports);
+			pf->num_netdevs++;
 		}
-		list_add_tail(&nn->port_list, &pf->ports);
 
 		ctrl_bar += NFP_PF_CSR_SLICE_SIZE;
 	}
 
+	if (list_empty(&pf->ports))
+		return -ENODEV;
+
 	return 0;
 
 err_free_prev:
@@ -399,7 +414,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 	/* Get MSI-X vectors */
 	wanted_irqs = 0;
 	list_for_each_entry(nn, &pf->ports, port_list)
-		wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->num_r_vecs;
+		wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->dp.num_r_vecs;
 	pf->irq_entries = kcalloc(wanted_irqs, sizeof(*pf->irq_entries),
 				  GFP_KERNEL);
 	if (!pf->irq_entries) {
@@ -408,7 +423,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 	}
 
 	num_irqs = nfp_net_irqs_alloc(pf->pdev, pf->irq_entries,
-				      NFP_NET_MIN_PORT_IRQS * pf->num_ports,
+				      NFP_NET_MIN_PORT_IRQS * pf->num_netdevs,
 				      wanted_irqs);
 	if (!num_irqs) {
 		nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n");
@@ -418,7 +433,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 
 	/* Distribute IRQs to ports */
 	irqs_left = num_irqs;
-	ports_left = pf->num_ports;
+	ports_left = pf->num_netdevs;
 	list_for_each_entry(nn, &pf->ports, port_list) {
 		unsigned int n;
 
@@ -444,7 +459,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 err_prev_deinit:
 	list_for_each_entry_continue_reverse(nn, &pf->ports, port_list) {
 		nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
-		nfp_net_netdev_clean(nn->netdev);
+		nfp_net_netdev_clean(nn->dp.netdev);
 	}
 	nfp_net_irqs_disable(pf->pdev);
 err_vec_free:
@@ -454,6 +469,108 @@ err_nn_free:
 	return err;
 }
 
+static void nfp_net_pci_remove_finish(struct nfp_pf *pf)
+{
+	nfp_net_debugfs_dir_clean(&pf->ddir);
+
+	nfp_net_irqs_disable(pf->pdev);
+	kfree(pf->irq_entries);
+
+	nfp_cpp_area_release_free(pf->rx_area);
+	nfp_cpp_area_release_free(pf->tx_area);
+	nfp_cpp_area_release_free(pf->ctrl_area);
+}
+
+static void nfp_net_refresh_netdevs(struct work_struct *work)
+{
+	struct nfp_pf *pf = container_of(work, struct nfp_pf,
+					 port_refresh_work);
+	struct nfp_eth_table *eth_table;
+	struct nfp_net *nn, *next;
+
+	mutex_lock(&pf->port_lock);
+
+	/* Check for nfp_net_pci_remove() racing against us */
+	if (list_empty(&pf->ports))
+		goto out;
+
+	list_for_each_entry(nn, &pf->ports, port_list)
+		nfp_net_link_changed_read_clear(nn);
+
+	eth_table = nfp_eth_read_ports(pf->cpp);
+	if (!eth_table) {
+		nfp_err(pf->cpp, "Error refreshing port config!\n");
+		goto out;
+	}
+
+	rtnl_lock();
+	list_for_each_entry(nn, &pf->ports, port_list) {
+		if (!nn->eth_port)
+			continue;
+		nn->eth_port = nfp_net_find_port(eth_table,
+						 nn->eth_port->eth_index);
+	}
+	rtnl_unlock();
+
+	kfree(pf->eth_tbl);
+	pf->eth_tbl = eth_table;
+
+	list_for_each_entry_safe(nn, next, &pf->ports, port_list) {
+		if (!nn->eth_port) {
+			nfp_warn(pf->cpp, "Warning: port not present after reconfig\n");
+			continue;
+		}
+		if (!nn->eth_port->override_changed)
+			continue;
+
+		nn_warn(nn, "Port config changed, unregistering. Reboot required before port will be operational again.\n");
+
+		nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
+		nfp_net_netdev_clean(nn->dp.netdev);
+
+		list_del(&nn->port_list);
+		pf->num_netdevs--;
+		nfp_net_netdev_free(nn);
+	}
+
+	if (list_empty(&pf->ports))
+		nfp_net_pci_remove_finish(pf);
+out:
+	mutex_unlock(&pf->port_lock);
+}
+
+void nfp_net_refresh_port_table(struct nfp_net *nn)
+{
+	struct nfp_pf *pf = pci_get_drvdata(nn->pdev);
+
+	schedule_work(&pf->port_refresh_work);
+}
+
+int nfp_net_refresh_eth_port(struct nfp_net *nn)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_eth_table *eth_table;
+
+	eth_table = nfp_eth_read_ports(nn->cpp);
+	if (!eth_table) {
+		nn_err(nn, "Error refreshing port state table!\n");
+		return -EIO;
+	}
+
+	eth_port = nfp_net_find_port(eth_table, nn->eth_port->eth_index);
+	if (!eth_port) {
+		nn_err(nn, "Error finding state of the port!\n");
+		kfree(eth_table);
+		return -EIO;
+	}
+
+	memcpy(nn->eth_port, eth_port, sizeof(*eth_port));
+
+	kfree(eth_table);
+
+	return 0;
+}
+
 /*
  * PCI device functions
  */
@@ -467,17 +584,23 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 	int stride;
 	int err;
 
+	INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_netdevs);
+	mutex_init(&pf->port_lock);
+
 	/* Verify that the board has completed initialization */
 	if (!nfp_is_ready(pf->cpp)) {
 		nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n");
 		return -EINVAL;
 	}
 
+	mutex_lock(&pf->port_lock);
 	pf->num_ports = nfp_net_pf_get_num_ports(pf);
 
 	ctrl_bar = nfp_net_pf_map_ctrl_bar(pf);
-	if (!ctrl_bar)
-		return pf->fw_loaded ? -EINVAL : -EPROBE_DEFER;
+	if (!ctrl_bar) {
+		err = pf->fw_loaded ? -EINVAL : -EPROBE_DEFER;
+		goto err_unlock;
+	}
 
 	nfp_net_get_fw_version(&fw_ver, ctrl_bar);
 	if (fw_ver.resv || fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
@@ -551,6 +674,8 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 	if (err)
 		goto err_clean_ddir;
 
+	mutex_unlock(&pf->port_lock);
+
 	return 0;
 
 err_clean_ddir:
@@ -560,6 +685,8 @@ err_unmap_tx:
 	nfp_cpp_area_release_free(pf->tx_area);
 err_ctrl_unmap:
 	nfp_cpp_area_release_free(pf->ctrl_area);
+err_unlock:
+	mutex_unlock(&pf->port_lock);
 	return err;
 }
 
@@ -567,20 +694,21 @@ void nfp_net_pci_remove(struct nfp_pf *pf)
 {
 	struct nfp_net *nn;
 
+	mutex_lock(&pf->port_lock);
+	if (list_empty(&pf->ports))
+		goto out;
+
 	list_for_each_entry(nn, &pf->ports, port_list) {
 		nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
 
-		nfp_net_netdev_clean(nn->netdev);
+		nfp_net_netdev_clean(nn->dp.netdev);
 	}
 
 	nfp_net_pf_free_netdevs(pf);
 
-	nfp_net_debugfs_dir_clean(&pf->ddir);
-
-	nfp_net_irqs_disable(pf->pdev);
-	kfree(pf->irq_entries);
+	nfp_net_pci_remove_finish(pf);
+out:
+	mutex_unlock(&pf->port_lock);
 
-	nfp_cpp_area_release_free(pf->rx_area);
-	nfp_cpp_area_release_free(pf->tx_area);
-	nfp_cpp_area_release_free(pf->ctrl_area);
+	cancel_work_sync(&pf->port_refresh_work);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
index 18a851eb3508..cc823df12c8a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
@@ -58,7 +58,7 @@ void nfp_net_filter_stats_timer(unsigned long data)
 
 	spin_lock_bh(&nn->rx_filter_lock);
 
-	if (nn->ctrl & NFP_NET_CFG_CTRL_BPF)
+	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
 		mod_timer(&nn->rx_filter_stats_timer,
 			  jiffies + NFP_NET_STAT_POLL_IVL);
 
@@ -119,12 +119,12 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 		if (tc_no_actions(cls_bpf->exts))
 			return NN_ACT_DIRECT;
 
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	/* TC legacy mode */
 	if (!tc_single_action(cls_bpf->exts))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	tcf_exts_to_list(cls_bpf->exts, &actions);
 	list_for_each_entry(a, &actions, list) {
@@ -132,11 +132,11 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 			return NN_ACT_TC_DROP;
 
 		if (is_tcf_mirred_egress_redirect(a) &&
-		    tcf_mirred_ifindex(a) == nn->netdev->ifindex)
+		    tcf_mirred_ifindex(a) == nn->dp.netdev->ifindex)
 			return NN_ACT_TC_REDIR;
 	}
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int
@@ -152,7 +152,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_BPF_SYSCALL))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	ret = nfp_net_bpf_get_act(nn, cls_bpf);
 	if (ret < 0)
@@ -160,16 +160,15 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	act = ret;
 
 	max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
-	if (max_mtu < nn->netdev->mtu) {
+	if (max_mtu < nn->dp.netdev->mtu) {
 		nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	start_off = nn_readw(nn, NFP_NET_CFG_BPF_START);
 	done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE);
 
-	*code = dma_zalloc_coherent(&nn->pdev->dev, code_sz, dma_addr,
-				    GFP_KERNEL);
+	*code = dma_zalloc_coherent(nn->dp.dev, code_sz, dma_addr, GFP_KERNEL);
 	if (!*code)
 		return -ENOMEM;
 
@@ -181,7 +180,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	return 0;
 
 out:
-	dma_free_coherent(&nn->pdev->dev, code_sz, *code, *dma_addr);
+	dma_free_coherent(nn->dp.dev, code_sz, *code, *dma_addr);
 	return ret;
 }
 
@@ -194,7 +193,7 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
 	u64 bpf_addr = dma_addr;
 	int err;
 
-	nn->bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW);
+	nn->dp.bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW);
 
 	if (dense_mode)
 		bpf_addr |= NFP_NET_CFG_BPF_CFG_8CTX;
@@ -208,13 +207,13 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
 		nn_err(nn, "FW command error while loading BPF: %d\n", err);
 
 	/* Enable passing packets through BPF function */
-	nn->ctrl |= NFP_NET_CFG_CTRL_BPF;
-	nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl);
+	nn->dp.ctrl |= NFP_NET_CFG_CTRL_BPF;
+	nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 	if (err)
 		nn_err(nn, "FW command error while enabling BPF: %d\n", err);
 
-	dma_free_coherent(&nn->pdev->dev, code_sz, code, dma_addr);
+	dma_free_coherent(nn->dp.dev, code_sz, code, dma_addr);
 
 	nfp_net_bpf_stats_reset(nn);
 	mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL);
@@ -222,16 +221,16 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
 
 static int nfp_net_bpf_stop(struct nfp_net *nn)
 {
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_BPF))
+	if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF))
 		return 0;
 
 	spin_lock_bh(&nn->rx_filter_lock);
-	nn->ctrl &= ~NFP_NET_CFG_CTRL_BPF;
+	nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_BPF;
 	spin_unlock_bh(&nn->rx_filter_lock);
-	nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl);
+	nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
 
 	del_timer_sync(&nn->rx_filter_stats_timer);
-	nn->bpf_offload_skip_sw = 0;
+	nn->dp.bpf_offload_skip_sw = 0;
 
 	return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 }
@@ -255,7 +254,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 		 * frames which didn't have BPF applied in the hardware should
 		 * be fine if software fallback is available, though.
 		 */
-		if (nn->bpf_offload_skip_sw)
+		if (nn->dp.bpf_offload_skip_sw)
 			return -EBUSY;
 
 		err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code,
@@ -270,7 +269,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 		return 0;
 
 	case TC_CLSBPF_ADD:
-		if (nn->ctrl & NFP_NET_CFG_CTRL_BPF)
+		if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
 			return -EBUSY;
 
 		err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code,
@@ -290,6 +289,6 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 		return nfp_net_bpf_stats_update(nn, cls_bpf);
 
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index 39407f7cc586..86e61be6f35c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -84,12 +84,12 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn)
 	put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]);
 
 	if (!is_valid_ether_addr(mac_addr)) {
-		eth_hw_addr_random(nn->netdev);
+		eth_hw_addr_random(nn->dp.netdev);
 		return;
 	}
 
-	ether_addr_copy(nn->netdev->dev_addr, mac_addr);
-	ether_addr_copy(nn->netdev->perm_addr, mac_addr);
+	ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr);
+	ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr);
 }
 
 static int nfp_netvf_pci_probe(struct pci_dev *pdev,
@@ -210,8 +210,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	vf->nn = nn;
 
 	nn->fw_ver = fw_ver;
-	nn->ctrl_bar = ctrl_bar;
-	nn->is_vf = 1;
+	nn->dp.ctrl_bar = ctrl_bar;
+	nn->dp.is_vf = 1;
 	nn->stride_tx = stride;
 	nn->stride_rx = stride;
 
@@ -268,7 +268,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 
 	num_irqs = nfp_net_irqs_alloc(pdev, vf->irq_entries,
 				      NFP_NET_MIN_PORT_IRQS,
-				      NFP_NET_NON_Q_VECTORS + nn->num_r_vecs);
+				      NFP_NET_NON_Q_VECTORS +
+				      nn->dp.num_r_vecs);
 	if (!num_irqs) {
 		nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n");
 		err = -EIO;
@@ -282,7 +283,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	 */
 	nn->me_freq_mhz = 1200;
 
-	err = nfp_net_netdev_init(nn->netdev);
+	err = nfp_net_netdev_init(nn->dp.netdev);
 	if (err)
 		goto err_irqs_disable;
 
@@ -327,7 +328,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev)
 	nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
 	nfp_net_debugfs_dir_clean(&vf->ddir);
 
-	nfp_net_netdev_clean(nn->netdev);
+	nfp_net_netdev_clean(nn->dp.netdev);
 
 	nfp_net_irqs_disable(pdev);
 
@@ -337,7 +338,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev)
 	} else {
 		iounmap(vf->q_bar);
 	}
-	iounmap(nn->ctrl_bar);
+	iounmap(nn->dp.ctrl_bar);
 
 	nfp_net_netdev_free(nn);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
index 42cb720b696d..4df2ce261b3f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
@@ -48,32 +48,26 @@
 
 const char *nfp_hwinfo_lookup(struct nfp_cpp *cpp, const char *lookup);
 
-/* Implemented in nfp_nsp.c */
+/* Implemented in nfp_nsp.c, low level functions */
 
 struct nfp_nsp;
-struct firmware;
-
-struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp);
-void nfp_nsp_close(struct nfp_nsp *state);
-u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state);
-u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state);
-int nfp_nsp_wait(struct nfp_nsp *state);
-int nfp_nsp_device_soft_reset(struct nfp_nsp *state);
-int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw);
+
+struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state);
+bool nfp_nsp_config_modified(struct nfp_nsp *state);
+void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified);
+void *nfp_nsp_config_entries(struct nfp_nsp *state);
+unsigned int nfp_nsp_config_idx(struct nfp_nsp *state);
+void nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries,
+			      unsigned int idx);
+void nfp_nsp_config_clear_state(struct nfp_nsp *state);
 int nfp_nsp_read_eth_table(struct nfp_nsp *state, void *buf, unsigned int size);
 int nfp_nsp_write_eth_table(struct nfp_nsp *state,
 			    const void *buf, unsigned int size);
+int nfp_nsp_read_identify(struct nfp_nsp *state, void *buf, unsigned int size);
 
 /* Implemented in nfp_resource.c */
 
-#define NFP_RESOURCE_TBL_TARGET		NFP_CPP_TARGET_MU
-#define NFP_RESOURCE_TBL_BASE		0x8100000000ULL
-
-/* NFP Resource Table self-identifier */
-#define NFP_RESOURCE_TBL_NAME		"nfp.res"
-#define NFP_RESOURCE_TBL_KEY		0x00000000 /* Special key for entry 0 */
-
-/* All other keys are CRC32-POSIX of the 8-byte identification string */
+/* All keys are CRC32-POSIX of the 8-byte identification string */
 
 /* ARM/PCI vNIC Interfaces 0..3 */
 #define NFP_RESOURCE_VNIC_PCI_0		"vnic.p0"
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 15cc3e77cf6a..43dc68e01274 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -217,7 +217,7 @@ static resource_size_t nfp_bar_resource_start(struct nfp_bar *bar)
 #define TARGET_WIDTH_64    8
 
 static int
-compute_bar(struct nfp6000_pcie *nfp, struct nfp_bar *bar,
+compute_bar(const struct nfp6000_pcie *nfp, const struct nfp_bar *bar,
 	    u32 *bar_config, u64 *bar_base,
 	    int tgt, int act, int tok, u64 offset, size_t size, int width)
 {
@@ -410,35 +410,36 @@ find_matching_bar(struct nfp6000_pcie *nfp,
 
 /* Return EAGAIN if no resource is available */
 static int
-find_unused_bar_noblock(struct nfp6000_pcie *nfp,
+find_unused_bar_noblock(const struct nfp6000_pcie *nfp,
 			int tgt, int act, int tok,
 			u64 offset, size_t size, int width)
 {
-	int n, invalid = 0;
+	int n, busy = 0;
 
 	for (n = 0; n < nfp->bars; n++) {
-		struct nfp_bar *bar = &nfp->bar[n];
+		const struct nfp_bar *bar = &nfp->bar[n];
 		int err;
 
-		if (bar->bitsize == 0) {
-			invalid++;
-			continue;
-		}
-
-		if (atomic_read(&bar->refcnt) != 0)
+		if (!bar->bitsize)
 			continue;
 
 		/* Just check to see if we can make it fit... */
 		err = compute_bar(nfp, bar, NULL, NULL,
 				  tgt, act, tok, offset, size, width);
+		if (err)
+			continue;
 
-		if (err < 0)
-			invalid++;
-		else
+		if (!atomic_read(&bar->refcnt))
 			return n;
+
+		busy++;
 	}
 
-	return (n == invalid) ? -EINVAL : -EAGAIN;
+	if (WARN(!busy, "No suitable BAR found for request tgt:0x%x act:0x%x tok:0x%x off:0x%llx size:%zd width:%d\n",
+		 tgt, act, tok, offset, size, width))
+		return -EINVAL;
+
+	return -EAGAIN;
 }
 
 static int
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index 40108e66c654..e2abba4c3a3f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -65,39 +65,49 @@ struct nfp_cpp_resource {
 	u64 end;
 };
 
-struct nfp_cpp_mutex {
-	struct list_head list;
-	struct nfp_cpp *cpp;
-	int target;
-	u16 usage;
-	u16 depth;
-	unsigned long long address;
-	u32 key;
-};
-
+/**
+ * struct nfp_cpp - main nfpcore device structure
+ * Following fields are read-only after probe() exits or netdevs are spawned.
+ * @dev:		embedded device structure
+ * @op:			low-level implementation ops
+ * @priv:		private data of the low-level implementation
+ * @model:		chip model
+ * @interface:		chip interface id we are using to reach it
+ * @serial:		chip serial number
+ * @imb_cat_table:	CPP Mapping Table
+ *
+ * Following fields can be used only in probe() or with rtnl held:
+ * @hwinfo:		HWInfo database fetched from the device
+ * @rtsym:		firmware run time symbols
+ *
+ * Following fields use explicit locking:
+ * @resource_list:	NFP CPP resource list
+ * @resource_lock:	protects @resource_list
+ *
+ * @area_cache_list:	cached areas for cpp/xpb read/write speed up
+ * @area_cache_mutex:	protects @area_cache_list
+ *
+ * @waitq:		area wait queue
+ */
 struct nfp_cpp {
 	struct device dev;
 
-	void *priv; /* Private data of the low-level implementation */
+	void *priv;
 
 	u32 model;
 	u16 interface;
 	u8 serial[NFP_SERIAL_LEN];
 
 	const struct nfp_cpp_operations *op;
-	struct list_head resource_list;	/* NFP CPP resource list */
-	struct list_head mutex_cache;	/* Mutex cache */
+	struct list_head resource_list;
 	rwlock_t resource_lock;
 	wait_queue_head_t waitq;
 
-	/* NFP6000 CPP Mapping Table */
 	u32 imb_cat_table[16];
 
-	/* Cached areas for cpp/xpb readl/writel speedups */
-	struct mutex area_cache_mutex;  /* Lock for the area cache */
+	struct mutex area_cache_mutex;
 	struct list_head area_cache_list;
 
-	/* Cached information */
 	void *hwinfo;
 	void *rtsym;
 };
@@ -187,24 +197,6 @@ void nfp_cpp_free(struct nfp_cpp *cpp)
 {
 	struct nfp_cpp_area_cache *cache, *ctmp;
 	struct nfp_cpp_resource *res, *rtmp;
-	struct nfp_cpp_mutex *mutex, *mtmp;
-
-	/* There should be no mutexes in the cache at this point. */
-	WARN_ON(!list_empty(&cpp->mutex_cache));
-	/* .. but if there are, unlock them and complain. */
-	list_for_each_entry_safe(mutex, mtmp, &cpp->mutex_cache, list) {
-		dev_err(cpp->dev.parent, "Dangling mutex: @%d::0x%llx, %d locks held by %d owners\n",
-			mutex->target, (unsigned long long)mutex->address,
-			mutex->depth, mutex->usage);
-
-		/* Forcing an unlock */
-		mutex->depth = 1;
-		nfp_cpp_mutex_unlock(mutex);
-
-		/* Forcing a free */
-		mutex->usage = 1;
-		nfp_cpp_mutex_free(mutex);
-	}
 
 	/* Remove all caches */
 	list_for_each_entry_safe(cache, ctmp, &cpp->area_cache_list, entry) {
@@ -419,9 +411,43 @@ nfp_cpp_area_alloc(struct nfp_cpp *cpp, u32 dest,
  */
 void nfp_cpp_area_free(struct nfp_cpp_area *area)
 {
+	if (atomic_read(&area->refcount))
+		nfp_warn(area->cpp, "Warning: freeing busy area\n");
 	nfp_cpp_area_put(area);
 }
 
+static bool nfp_cpp_area_acquire_try(struct nfp_cpp_area *area, int *status)
+{
+	*status = area->cpp->op->area_acquire(area);
+
+	return *status != -EAGAIN;
+}
+
+static int __nfp_cpp_area_acquire(struct nfp_cpp_area *area)
+{
+	int err, status;
+
+	if (atomic_inc_return(&area->refcount) > 1)
+		return 0;
+
+	if (!area->cpp->op->area_acquire)
+		return 0;
+
+	err = wait_event_interruptible(area->cpp->waitq,
+				       nfp_cpp_area_acquire_try(area, &status));
+	if (!err)
+		err = status;
+	if (err) {
+		nfp_warn(area->cpp, "Warning: area wait failed: %d\n", err);
+		atomic_dec(&area->refcount);
+		return err;
+	}
+
+	nfp_cpp_area_get(area);
+
+	return 0;
+}
+
 /**
  * nfp_cpp_area_acquire() - lock down a CPP area for access
  * @area:	CPP area handle
@@ -433,27 +459,13 @@ void nfp_cpp_area_free(struct nfp_cpp_area *area)
  */
 int nfp_cpp_area_acquire(struct nfp_cpp_area *area)
 {
-	mutex_lock(&area->mutex);
-	if (atomic_inc_return(&area->refcount) == 1) {
-		int (*a_a)(struct nfp_cpp_area *);
-
-		a_a = area->cpp->op->area_acquire;
-		if (a_a) {
-			int err;
+	int ret;
 
-			wait_event_interruptible(area->cpp->waitq,
-						 (err = a_a(area)) != -EAGAIN);
-			if (err < 0) {
-				atomic_dec(&area->refcount);
-				mutex_unlock(&area->mutex);
-				return err;
-			}
-		}
-	}
+	mutex_lock(&area->mutex);
+	ret = __nfp_cpp_area_acquire(area);
 	mutex_unlock(&area->mutex);
 
-	nfp_cpp_area_get(area);
-	return 0;
+	return ret;
 }
 
 /**
@@ -829,10 +841,7 @@ area_cache_get(struct nfp_cpp *cpp, u32 id,
 	 * the need for special case code below when
 	 * checking against available cache size.
 	 */
-	if (length == 0)
-		return NULL;
-
-	if (list_empty(&cpp->area_cache_list) || id == 0)
+	if (length == 0 || id == 0)
 		return NULL;
 
 	/* Remap from cpp_island to cpp_target */
@@ -840,10 +849,15 @@ area_cache_get(struct nfp_cpp *cpp, u32 id,
 	if (err < 0)
 		return NULL;
 
-	addr += *offset;
-
 	mutex_lock(&cpp->area_cache_mutex);
 
+	if (list_empty(&cpp->area_cache_list)) {
+		mutex_unlock(&cpp->area_cache_mutex);
+		return NULL;
+	}
+
+	addr += *offset;
+
 	/* See if we have a match */
 	list_for_each_entry(cache, &cpp->area_cache_list, entry) {
 		if (id == cache->id &&
@@ -937,12 +951,14 @@ int nfp_cpp_read(struct nfp_cpp *cpp, u32 destination,
 			return -ENOMEM;
 
 		err = nfp_cpp_area_acquire(area);
-		if (err)
-			goto out;
+		if (err) {
+			nfp_cpp_area_free(area);
+			return err;
+		}
 	}
 
 	err = nfp_cpp_area_read(area, offset, kernel_vaddr, length);
-out:
+
 	if (cache)
 		area_cache_put(cpp, cache);
 	else
@@ -979,13 +995,14 @@ int nfp_cpp_write(struct nfp_cpp *cpp, u32 destination,
 			return -ENOMEM;
 
 		err = nfp_cpp_area_acquire(area);
-		if (err)
-			goto out;
+		if (err) {
+			nfp_cpp_area_free(area);
+			return err;
+		}
 	}
 
 	err = nfp_cpp_area_write(area, offset, kernel_vaddr, length);
 
-out:
 	if (cache)
 		area_cache_put(cpp, cache);
 	else
@@ -1127,7 +1144,6 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 	rwlock_init(&cpp->resource_lock);
 	init_waitqueue_head(&cpp->waitq);
 	lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key);
-	INIT_LIST_HEAD(&cpp->mutex_cache);
 	INIT_LIST_HEAD(&cpp->resource_list);
 	INIT_LIST_HEAD(&cpp->area_cache_list);
 	mutex_init(&cpp->area_cache_mutex);
@@ -1425,322 +1441,3 @@ void *nfp_cpp_explicit_priv(struct nfp_cpp_explicit *cpp_explicit)
 {
 	return &cpp_explicit[1];
 }
-
-/* THIS FUNCTION IS NOT EXPORTED */
-static u32 nfp_mutex_locked(u16 interface)
-{
-	return (u32)interface << 16 | 0x000f;
-}
-
-static u32 nfp_mutex_unlocked(u16 interface)
-{
-	return (u32)interface << 16 | 0x0000;
-}
-
-static bool nfp_mutex_is_locked(u32 val)
-{
-	return (val & 0xffff) == 0x000f;
-}
-
-static bool nfp_mutex_is_unlocked(u32 val)
-{
-	return (val & 0xffff) == 0000;
-}
-
-/* If you need more than 65536 recursive locks, please rethink your code. */
-#define MUTEX_DEPTH_MAX         0xffff
-
-static int
-nfp_cpp_mutex_validate(u16 interface, int *target, unsigned long long address)
-{
-	/* Not permitted on invalid interfaces */
-	if (NFP_CPP_INTERFACE_TYPE_of(interface) ==
-	    NFP_CPP_INTERFACE_TYPE_INVALID)
-		return -EINVAL;
-
-	/* Address must be 64-bit aligned */
-	if (address & 7)
-		return -EINVAL;
-
-	if (*target != NFP_CPP_TARGET_MU)
-		return -EINVAL;
-
-	return 0;
-}
-
-/**
- * nfp_cpp_mutex_init() - Initialize a mutex location
- * @cpp:	NFP CPP handle
- * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
- * @address:	Offset into the address space of the NFP CPP target ID
- * @key:	Unique 32-bit value for this mutex
- *
- * The CPP target:address must point to a 64-bit aligned location, and
- * will initialize 64 bits of data at the location.
- *
- * This creates the initial mutex state, as locked by this
- * nfp_cpp_interface().
- *
- * This function should only be called when setting up
- * the initial lock state upon boot-up of the system.
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_init(struct nfp_cpp *cpp,
-		       int target, unsigned long long address, u32 key)
-{
-	const u32 muw = NFP_CPP_ID(target, 4, 0);    /* atomic_write */
-	u16 interface = nfp_cpp_interface(cpp);
-	int err;
-
-	err = nfp_cpp_mutex_validate(interface, &target, address);
-	if (err)
-		return err;
-
-	err = nfp_cpp_writel(cpp, muw, address + 4, key);
-	if (err)
-		return err;
-
-	err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_locked(interface));
-	if (err)
-		return err;
-
-	return 0;
-}
-
-/**
- * nfp_cpp_mutex_alloc() - Create a mutex handle
- * @cpp:	NFP CPP handle
- * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
- * @address:	Offset into the address space of the NFP CPP target ID
- * @key:	32-bit unique key (must match the key at this location)
- *
- * The CPP target:address must point to a 64-bit aligned location, and
- * reserve 64 bits of data at the location for use by the handle.
- *
- * Only target/address pairs that point to entities that support the
- * MU Atomic Engine's CmpAndSwap32 command are supported.
- *
- * Return:	A non-NULL struct nfp_cpp_mutex * on success, NULL on failure.
- */
-struct nfp_cpp_mutex *nfp_cpp_mutex_alloc(struct nfp_cpp *cpp, int target,
-					  unsigned long long address, u32 key)
-{
-	const u32 mur = NFP_CPP_ID(target, 3, 0);    /* atomic_read */
-	u16 interface = nfp_cpp_interface(cpp);
-	struct nfp_cpp_mutex *mutex;
-	int err;
-	u32 tmp;
-
-	err = nfp_cpp_mutex_validate(interface, &target, address);
-	if (err)
-		return NULL;
-
-	/* Look for mutex on cache list */
-	list_for_each_entry(mutex, &cpp->mutex_cache, list) {
-		if (mutex->target == target && mutex->address == address) {
-			mutex->usage++;
-			return mutex;
-		}
-	}
-
-	err = nfp_cpp_readl(cpp, mur, address + 4, &tmp);
-	if (err < 0)
-		return NULL;
-
-	if (tmp != key)
-		return NULL;
-
-	mutex = kzalloc(sizeof(*mutex), GFP_KERNEL);
-	if (!mutex)
-		return NULL;
-
-	mutex->cpp = cpp;
-	mutex->target = target;
-	mutex->address = address;
-	mutex->key = key;
-	mutex->depth = 0;
-	mutex->usage = 1;
-
-	/* Add mutex to cache list */
-	list_add(&mutex->list, &cpp->mutex_cache);
-
-	return mutex;
-}
-
-/**
- * nfp_cpp_mutex_free() - Free a mutex handle - does not alter the lock state
- * @mutex:	NFP CPP Mutex handle
- */
-void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex)
-{
-	if (--mutex->usage)
-		return;
-
-	/* Remove mutex from cache */
-	list_del(&mutex->list);
-	kfree(mutex);
-}
-
-/**
- * nfp_cpp_mutex_lock() - Lock a mutex handle, using the NFP MU Atomic Engine
- * @mutex:	NFP CPP Mutex handle
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
-{
-	unsigned long warn_at = jiffies + 15 * HZ;
-	unsigned int timeout_ms = 1;
-	int err;
-
-	/* We can't use a waitqueue here, because the unlocker
-	 * might be on a separate CPU.
-	 *
-	 * So just wait for now.
-	 */
-	for (;;) {
-		err = nfp_cpp_mutex_trylock(mutex);
-		if (err != -EBUSY)
-			break;
-
-		err = msleep_interruptible(timeout_ms);
-		if (err != 0)
-			return -ERESTARTSYS;
-
-		if (time_is_before_eq_jiffies(warn_at)) {
-			warn_at = jiffies + 60 * HZ;
-			dev_warn(mutex->cpp->dev.parent,
-				 "Warning: waiting for NFP mutex [usage:%hd depth:%hd target:%d addr:%llx key:%08x]\n",
-				 mutex->usage, mutex->depth,
-				 mutex->target, mutex->address, mutex->key);
-		}
-	}
-
-	return err;
-}
-
-/**
- * nfp_cpp_mutex_unlock() - Unlock a mutex handle, using the MU Atomic Engine
- * @mutex:	NFP CPP Mutex handle
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex)
-{
-	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
-	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
-	struct nfp_cpp *cpp = mutex->cpp;
-	u32 key, value;
-	u16 interface;
-	int err;
-
-	interface = nfp_cpp_interface(cpp);
-
-	if (mutex->depth > 1) {
-		mutex->depth--;
-		return 0;
-	}
-
-	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address + 4, &key);
-	if (err < 0)
-		return err;
-
-	if (key != mutex->key)
-		return -EPERM;
-
-	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address, &value);
-	if (err < 0)
-		return err;
-
-	if (value != nfp_mutex_locked(interface))
-		return -EACCES;
-
-	err = nfp_cpp_writel(cpp, muw, mutex->address,
-			     nfp_mutex_unlocked(interface));
-	if (err < 0)
-		return err;
-
-	mutex->depth = 0;
-	return 0;
-}
-
-/**
- * nfp_cpp_mutex_trylock() - Attempt to lock a mutex handle
- * @mutex:	NFP CPP Mutex handle
- *
- * Return:      0 if the lock succeeded, -errno on failure
- */
-int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex)
-{
-	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
-	const u32 mus = NFP_CPP_ID(mutex->target, 5, 3);    /* test_set_imm */
-	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
-	struct nfp_cpp *cpp = mutex->cpp;
-	u32 key, value, tmp;
-	int err;
-
-	if (mutex->depth > 0) {
-		if (mutex->depth == MUTEX_DEPTH_MAX)
-			return -E2BIG;
-		mutex->depth++;
-		return 0;
-	}
-
-	/* Verify that the lock marker is not damaged */
-	err = nfp_cpp_readl(cpp, mur, mutex->address + 4, &key);
-	if (err < 0)
-		return err;
-
-	if (key != mutex->key)
-		return -EPERM;
-
-	/* Compare against the unlocked state, and if true,
-	 * write the interface id into the top 16 bits, and
-	 * mark as locked.
-	 */
-	value = nfp_mutex_locked(nfp_cpp_interface(cpp));
-
-	/* We use test_set_imm here, as it implies a read
-	 * of the current state, and sets the bits in the
-	 * bytemask of the command to 1s. Since the mutex
-	 * is guaranteed to be 64-bit aligned, the bytemask
-	 * of this 32-bit command is ensured to be 8'b00001111,
-	 * which implies that the lower 4 bits will be set to
-	 * ones regardless of the initial state.
-	 *
-	 * Since this is a 'Readback' operation, with no Pull
-	 * data, we can treat this as a normal Push (read)
-	 * atomic, which returns the original value.
-	 */
-	err = nfp_cpp_readl(cpp, mus, mutex->address, &tmp);
-	if (err < 0)
-		return err;
-
-	/* Was it unlocked? */
-	if (nfp_mutex_is_unlocked(tmp)) {
-		/* The read value can only be 0x....0000 in the unlocked state.
-		 * If there was another contending for this lock, then
-		 * the lock state would be 0x....000f
-		 */
-
-		/* Write our owner ID into the lock
-		 * While not strictly necessary, this helps with
-		 * debug and bookkeeping.
-		 */
-		err = nfp_cpp_writel(cpp, muw, mutex->address, value);
-		if (err < 0)
-			return err;
-
-		mutex->depth = 1;
-		return 0;
-	}
-
-	/* Already locked by us? Success! */
-	if (tmp == value) {
-		mutex->depth = 1;
-		return 0;
-	}
-
-	return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
-}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
new file mode 100644
index 000000000000..8a99c189efa8
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
@@ -0,0 +1,345 @@
+/*
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+
+#include "nfp_cpp.h"
+#include "nfp6000/nfp6000.h"
+
+struct nfp_cpp_mutex {
+	struct nfp_cpp *cpp;
+	int target;
+	u16 depth;
+	unsigned long long address;
+	u32 key;
+};
+
+static u32 nfp_mutex_locked(u16 interface)
+{
+	return (u32)interface << 16 | 0x000f;
+}
+
+static u32 nfp_mutex_unlocked(u16 interface)
+{
+	return (u32)interface << 16 | 0x0000;
+}
+
+static bool nfp_mutex_is_locked(u32 val)
+{
+	return (val & 0xffff) == 0x000f;
+}
+
+static bool nfp_mutex_is_unlocked(u32 val)
+{
+	return (val & 0xffff) == 0000;
+}
+
+/* If you need more than 65536 recursive locks, please rethink your code. */
+#define NFP_MUTEX_DEPTH_MAX         0xffff
+
+static int
+nfp_cpp_mutex_validate(u16 interface, int *target, unsigned long long address)
+{
+	/* Not permitted on invalid interfaces */
+	if (NFP_CPP_INTERFACE_TYPE_of(interface) ==
+	    NFP_CPP_INTERFACE_TYPE_INVALID)
+		return -EINVAL;
+
+	/* Address must be 64-bit aligned */
+	if (address & 7)
+		return -EINVAL;
+
+	if (*target != NFP_CPP_TARGET_MU)
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * nfp_cpp_mutex_init() - Initialize a mutex location
+ * @cpp:	NFP CPP handle
+ * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address:	Offset into the address space of the NFP CPP target ID
+ * @key:	Unique 32-bit value for this mutex
+ *
+ * The CPP target:address must point to a 64-bit aligned location, and
+ * will initialize 64 bits of data at the location.
+ *
+ * This creates the initial mutex state, as locked by this
+ * nfp_cpp_interface().
+ *
+ * This function should only be called when setting up
+ * the initial lock state upon boot-up of the system.
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_init(struct nfp_cpp *cpp,
+		       int target, unsigned long long address, u32 key)
+{
+	const u32 muw = NFP_CPP_ID(target, 4, 0);    /* atomic_write */
+	u16 interface = nfp_cpp_interface(cpp);
+	int err;
+
+	err = nfp_cpp_mutex_validate(interface, &target, address);
+	if (err)
+		return err;
+
+	err = nfp_cpp_writel(cpp, muw, address + 4, key);
+	if (err)
+		return err;
+
+	err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_locked(interface));
+	if (err)
+		return err;
+
+	return 0;
+}
+
+/**
+ * nfp_cpp_mutex_alloc() - Create a mutex handle
+ * @cpp:	NFP CPP handle
+ * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address:	Offset into the address space of the NFP CPP target ID
+ * @key:	32-bit unique key (must match the key at this location)
+ *
+ * The CPP target:address must point to a 64-bit aligned location, and
+ * reserve 64 bits of data at the location for use by the handle.
+ *
+ * Only target/address pairs that point to entities that support the
+ * MU Atomic Engine's CmpAndSwap32 command are supported.
+ *
+ * Return:	A non-NULL struct nfp_cpp_mutex * on success, NULL on failure.
+ */
+struct nfp_cpp_mutex *nfp_cpp_mutex_alloc(struct nfp_cpp *cpp, int target,
+					  unsigned long long address, u32 key)
+{
+	const u32 mur = NFP_CPP_ID(target, 3, 0);    /* atomic_read */
+	u16 interface = nfp_cpp_interface(cpp);
+	struct nfp_cpp_mutex *mutex;
+	int err;
+	u32 tmp;
+
+	err = nfp_cpp_mutex_validate(interface, &target, address);
+	if (err)
+		return NULL;
+
+	err = nfp_cpp_readl(cpp, mur, address + 4, &tmp);
+	if (err < 0)
+		return NULL;
+
+	if (tmp != key)
+		return NULL;
+
+	mutex = kzalloc(sizeof(*mutex), GFP_KERNEL);
+	if (!mutex)
+		return NULL;
+
+	mutex->cpp = cpp;
+	mutex->target = target;
+	mutex->address = address;
+	mutex->key = key;
+	mutex->depth = 0;
+
+	return mutex;
+}
+
+/**
+ * nfp_cpp_mutex_free() - Free a mutex handle - does not alter the lock state
+ * @mutex:	NFP CPP Mutex handle
+ */
+void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex)
+{
+	kfree(mutex);
+}
+
+/**
+ * nfp_cpp_mutex_lock() - Lock a mutex handle, using the NFP MU Atomic Engine
+ * @mutex:	NFP CPP Mutex handle
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
+{
+	unsigned long warn_at = jiffies + 15 * HZ;
+	unsigned int timeout_ms = 1;
+	int err;
+
+	/* We can't use a waitqueue here, because the unlocker
+	 * might be on a separate CPU.
+	 *
+	 * So just wait for now.
+	 */
+	for (;;) {
+		err = nfp_cpp_mutex_trylock(mutex);
+		if (err != -EBUSY)
+			break;
+
+		err = msleep_interruptible(timeout_ms);
+		if (err != 0)
+			return -ERESTARTSYS;
+
+		if (time_is_before_eq_jiffies(warn_at)) {
+			warn_at = jiffies + 60 * HZ;
+			nfp_warn(mutex->cpp,
+				 "Warning: waiting for NFP mutex [depth:%hd target:%d addr:%llx key:%08x]\n",
+				 mutex->depth,
+				 mutex->target, mutex->address, mutex->key);
+		}
+	}
+
+	return err;
+}
+
+/**
+ * nfp_cpp_mutex_unlock() - Unlock a mutex handle, using the MU Atomic Engine
+ * @mutex:	NFP CPP Mutex handle
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex)
+{
+	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
+	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
+	struct nfp_cpp *cpp = mutex->cpp;
+	u32 key, value;
+	u16 interface;
+	int err;
+
+	interface = nfp_cpp_interface(cpp);
+
+	if (mutex->depth > 1) {
+		mutex->depth--;
+		return 0;
+	}
+
+	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address + 4, &key);
+	if (err < 0)
+		return err;
+
+	if (key != mutex->key)
+		return -EPERM;
+
+	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address, &value);
+	if (err < 0)
+		return err;
+
+	if (value != nfp_mutex_locked(interface))
+		return -EACCES;
+
+	err = nfp_cpp_writel(cpp, muw, mutex->address,
+			     nfp_mutex_unlocked(interface));
+	if (err < 0)
+		return err;
+
+	mutex->depth = 0;
+	return 0;
+}
+
+/**
+ * nfp_cpp_mutex_trylock() - Attempt to lock a mutex handle
+ * @mutex:	NFP CPP Mutex handle
+ *
+ * Return:      0 if the lock succeeded, -errno on failure
+ */
+int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex)
+{
+	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
+	const u32 mus = NFP_CPP_ID(mutex->target, 5, 3);    /* test_set_imm */
+	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
+	struct nfp_cpp *cpp = mutex->cpp;
+	u32 key, value, tmp;
+	int err;
+
+	if (mutex->depth > 0) {
+		if (mutex->depth == NFP_MUTEX_DEPTH_MAX)
+			return -E2BIG;
+		mutex->depth++;
+		return 0;
+	}
+
+	/* Verify that the lock marker is not damaged */
+	err = nfp_cpp_readl(cpp, mur, mutex->address + 4, &key);
+	if (err < 0)
+		return err;
+
+	if (key != mutex->key)
+		return -EPERM;
+
+	/* Compare against the unlocked state, and if true,
+	 * write the interface id into the top 16 bits, and
+	 * mark as locked.
+	 */
+	value = nfp_mutex_locked(nfp_cpp_interface(cpp));
+
+	/* We use test_set_imm here, as it implies a read
+	 * of the current state, and sets the bits in the
+	 * bytemask of the command to 1s. Since the mutex
+	 * is guaranteed to be 64-bit aligned, the bytemask
+	 * of this 32-bit command is ensured to be 8'b00001111,
+	 * which implies that the lower 4 bits will be set to
+	 * ones regardless of the initial state.
+	 *
+	 * Since this is a 'Readback' operation, with no Pull
+	 * data, we can treat this as a normal Push (read)
+	 * atomic, which returns the original value.
+	 */
+	err = nfp_cpp_readl(cpp, mus, mutex->address, &tmp);
+	if (err < 0)
+		return err;
+
+	/* Was it unlocked? */
+	if (nfp_mutex_is_unlocked(tmp)) {
+		/* The read value can only be 0x....0000 in the unlocked state.
+		 * If there was another contending for this lock, then
+		 * the lock state would be 0x....000f
+		 */
+
+		/* Write our owner ID into the lock
+		 * While not strictly necessary, this helps with
+		 * debug and bookkeeping.
+		 */
+		err = nfp_cpp_writel(cpp, muw, mutex->address, value);
+		if (err < 0)
+			return err;
+
+		mutex->depth = 1;
+		return 0;
+	}
+
+	return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 34c50987c377..2fa9247bb23d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -49,6 +49,7 @@
 
 #include "nfp.h"
 #include "nfp_cpp.h"
+#include "nfp_nsp.h"
 
 /* Offsets relative to the CSR base */
 #define NSP_STATUS		0x00
@@ -77,7 +78,7 @@
 
 #define NSP_MAGIC		0xab10
 #define NSP_MAJOR		0
-#define NSP_MINOR		(__MAX_SPCODE - 1)
+#define NSP_MINOR		8
 
 #define NSP_CODE_MAJOR		GENMASK(15, 12)
 #define NSP_CODE_MINOR		GENMASK(11, 0)
@@ -92,8 +93,18 @@ enum nfp_nsp_cmd {
 	SPCODE_FW_LOAD		= 6, /* Load fw from buffer, len in option */
 	SPCODE_ETH_RESCAN	= 7, /* Rescan ETHs, write ETH_TABLE to buf */
 	SPCODE_ETH_CONTROL	= 8, /* Update media config from buffer */
+	SPCODE_NSP_IDENTIFY	= 13, /* Read NSP version */
+};
 
-	__MAX_SPCODE,
+static const struct {
+	int code;
+	const char *msg;
+} nsp_errors[] = {
+	{ 6010, "could not map to phy for port" },
+	{ 6011, "not an allowed rate/lanes for port" },
+	{ 6012, "not an allowed rate/lanes for port" },
+	{ 6013, "high/low error, change other port first" },
+	{ 6014, "config not found in flash" },
 };
 
 struct nfp_nsp {
@@ -103,8 +114,63 @@ struct nfp_nsp {
 		u16 major;
 		u16 minor;
 	} ver;
+
+	/* Eth table config state */
+	bool modified;
+	unsigned int idx;
+	void *entries;
 };
 
+struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state)
+{
+	return state->cpp;
+}
+
+bool nfp_nsp_config_modified(struct nfp_nsp *state)
+{
+	return state->modified;
+}
+
+void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified)
+{
+	state->modified = modified;
+}
+
+void *nfp_nsp_config_entries(struct nfp_nsp *state)
+{
+	return state->entries;
+}
+
+unsigned int nfp_nsp_config_idx(struct nfp_nsp *state)
+{
+	return state->idx;
+}
+
+void
+nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries, unsigned int idx)
+{
+	state->entries = entries;
+	state->idx = idx;
+}
+
+void nfp_nsp_config_clear_state(struct nfp_nsp *state)
+{
+	state->entries = NULL;
+	state->idx = 0;
+}
+
+static void nfp_nsp_print_extended_error(struct nfp_nsp *state, u32 ret_val)
+{
+	int i;
+
+	if (!ret_val)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(nsp_errors); i++)
+		if (ret_val == nsp_errors[i].code)
+			nfp_err(state->cpp, "err msg: %s\n", nsp_errors[i].msg);
+}
+
 static int nfp_nsp_check(struct nfp_nsp *state)
 {
 	struct nfp_cpp *cpp = state->cpp;
@@ -209,9 +275,8 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
 		if ((*reg & mask) == val)
 			return 0;
 
-		err = msleep_interruptible(100);
-		if (err)
-			return err;
+		if (msleep_interruptible(25))
+			return -ERESTARTSYS;
 
 		if (time_after(start_time, wait_until))
 			return -ETIMEDOUT;
@@ -228,7 +293,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
  *
  * Return: 0 for success with no result
  *
- *	 1..255 for NSP completion with a result code
+ *	 positive value for NSP completion with a result code
  *
  *	-EAGAIN if the NSP is not yet present
  *	-ENODEV if the NSP is not a supported model
@@ -239,7 +304,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
 static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option,
 			   u32 buff_cpp, u64 buff_addr)
 {
-	u64 reg, nsp_base, nsp_buffer, nsp_status, nsp_command;
+	u64 reg, ret_val, nsp_base, nsp_buffer, nsp_status, nsp_command;
 	struct nfp_cpp *cpp = state->cpp;
 	u32 nsp_cpp;
 	int err;
@@ -292,18 +357,20 @@ static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option,
 		return err;
 	}
 
+	err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, &ret_val);
+	if (err < 0)
+		return err;
+	ret_val = FIELD_GET(NSP_COMMAND_OPTION, ret_val);
+
 	err = FIELD_GET(NSP_STATUS_RESULT, reg);
 	if (err) {
-		nfp_warn(cpp, "Result (error) code set: %d command: %d\n",
-			 -err, code);
+		nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n",
+			 -err, (int)ret_val, code);
+		nfp_nsp_print_extended_error(state, ret_val);
 		return -err;
 	}
 
-	err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, &reg);
-	if (err < 0)
-		return err;
-
-	return FIELD_GET(NSP_COMMAND_OPTION, reg);
+	return ret_val;
 }
 
 static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
@@ -380,9 +447,10 @@ int nfp_nsp_wait(struct nfp_nsp *state)
 		if (err != -EAGAIN)
 			break;
 
-		err = msleep_interruptible(100);
-		if (err)
+		if (msleep_interruptible(25)) {
+			err = -ERESTARTSYS;
 			break;
+		}
 
 		if (time_after(start_time, wait_until)) {
 			err = -ETIMEDOUT;
@@ -424,3 +492,9 @@ int nfp_nsp_write_eth_table(struct nfp_nsp *state,
 	return nfp_nsp_command_buf(state, SPCODE_ETH_CONTROL, size, buf, size,
 				   NULL, 0);
 }
+
+int nfp_nsp_read_identify(struct nfp_nsp *state, void *buf, unsigned int size)
+{
+	return nfp_nsp_command_buf(state, SPCODE_NSP_IDENTIFY, size, NULL, 0,
+				   buf, size);
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
new file mode 100644
index 000000000000..36b21e4dc56d
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
@@ -0,0 +1,174 @@
+/*
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef NSP_NSP_H
+#define NSP_NSP_H 1
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+struct firmware;
+struct nfp_cpp;
+struct nfp_nsp;
+
+struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp);
+void nfp_nsp_close(struct nfp_nsp *state);
+u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state);
+u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state);
+int nfp_nsp_wait(struct nfp_nsp *state);
+int nfp_nsp_device_soft_reset(struct nfp_nsp *state);
+int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw);
+
+enum nfp_eth_interface {
+	NFP_INTERFACE_NONE	= 0,
+	NFP_INTERFACE_SFP	= 1,
+	NFP_INTERFACE_SFPP	= 10,
+	NFP_INTERFACE_SFP28	= 28,
+	NFP_INTERFACE_QSFP	= 40,
+	NFP_INTERFACE_CXP	= 100,
+	NFP_INTERFACE_QSFP28	= 112,
+};
+
+enum nfp_eth_media {
+	NFP_MEDIA_DAC_PASSIVE = 0,
+	NFP_MEDIA_DAC_ACTIVE,
+	NFP_MEDIA_FIBRE,
+};
+
+enum nfp_eth_aneg {
+	NFP_ANEG_AUTO = 0,
+	NFP_ANEG_SEARCH,
+	NFP_ANEG_25G_CONSORTIUM,
+	NFP_ANEG_25G_IEEE,
+	NFP_ANEG_DISABLED,
+};
+
+/**
+ * struct nfp_eth_table - ETH table information
+ * @count:	number of table entries
+ * @ports:	table of ports
+ *
+ * @eth_index:	port index according to legacy ethX numbering
+ * @index:	chip-wide first channel index
+ * @nbi:	NBI index
+ * @base:	first channel index (within NBI)
+ * @lanes:	number of channels
+ * @speed:	interface speed (in Mbps)
+ * @interface:	interface (module) plugged in
+ * @media:	media type of the @interface
+ * @aneg:	auto negotiation mode
+ * @mac_addr:	interface MAC address
+ * @label_port:	port id
+ * @label_subport:  id of interface within port (for split ports)
+ * @enabled:	is enabled?
+ * @tx_enabled:	is TX enabled?
+ * @rx_enabled:	is RX enabled?
+ * @override_changed: is media reconfig pending?
+ *
+ * @port_type:	one of %PORT_* defines for ethtool
+ * @is_split:	is interface part of a split port
+ */
+struct nfp_eth_table {
+	unsigned int count;
+	struct nfp_eth_table_port {
+		unsigned int eth_index;
+		unsigned int index;
+		unsigned int nbi;
+		unsigned int base;
+		unsigned int lanes;
+		unsigned int speed;
+
+		unsigned int interface;
+		enum nfp_eth_media media;
+
+		enum nfp_eth_aneg aneg;
+
+		u8 mac_addr[ETH_ALEN];
+
+		u8 label_port;
+		u8 label_subport;
+
+		bool enabled;
+		bool tx_enabled;
+		bool rx_enabled;
+
+		bool override_changed;
+
+		/* Computed fields */
+		u8 port_type;
+
+		bool is_split;
+	} ports[0];
+};
+
+struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp);
+struct nfp_eth_table *
+__nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp);
+
+int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable);
+int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx,
+			   bool configed);
+
+struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx);
+int nfp_eth_config_commit_end(struct nfp_nsp *nsp);
+void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp);
+
+int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode);
+int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed);
+int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes);
+
+/**
+ * struct nfp_nsp_identify - NSP static information
+ * @version:      opaque version string
+ * @flags:        version flags
+ * @br_primary:   branch id of primary bootloader
+ * @br_secondary: branch id of secondary bootloader
+ * @br_nsp:       branch id of NSP
+ * @primary:      version of primarary bootloader
+ * @secondary:    version id of secondary bootloader
+ * @nsp:          version id of NSP
+ */
+struct nfp_nsp_identify {
+	char version[40];
+	u8 flags;
+	u8 br_primary;
+	u8 br_secondary;
+	u8 br_nsp;
+	u16 primary;
+	u16 secondary;
+	u16 nsp;
+};
+
+struct nfp_nsp_identify *__nfp_nsp_identify(struct nfp_nsp *nsp);
+
+#endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_cmds.c
index edf703d319c8..e7a263de3731 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_cmds.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-2017 Netronome Systems, Inc.
+ * Copyright (C) 2017 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -31,51 +31,59 @@
  * SOFTWARE.
  */
 
-#ifndef NSP_NSP_ETH_H
-#define NSP_NSP_ETH_H 1
+#include <linux/kernel.h>
+#include <linux/slab.h>
 
-#include <linux/types.h>
-#include <linux/if_ether.h>
+#include "nfp.h"
+#include "nfp_nsp.h"
 
-/**
- * struct nfp_eth_table - ETH table information
- * @count:	number of table entries
- * @ports:	table of ports
- *
- * @eth_index:	port index according to legacy ethX numbering
- * @index:	chip-wide first channel index
- * @nbi:	NBI index
- * @base:	first channel index (within NBI)
- * @lanes:	number of channels
- * @speed:	interface speed (in Mbps)
- * @mac_addr:	interface MAC address
- * @label:	interface id string
- * @enabled:	is enabled?
- * @tx_enabled:	is TX enabled?
- * @rx_enabled:	is RX enabled?
- */
-struct nfp_eth_table {
-	unsigned int count;
-	struct nfp_eth_table_port {
-		unsigned int eth_index;
-		unsigned int index;
-		unsigned int nbi;
-		unsigned int base;
-		unsigned int lanes;
-		unsigned int speed;
+struct nsp_identify {
+	u8 version[40];
+	u8 flags;
+	u8 br_primary;
+	u8 br_secondary;
+	u8 br_nsp;
+	__le16 primary;
+	__le16 secondary;
+	__le16 nsp;
+	__le16 reserved;
+};
 
-		u8 mac_addr[ETH_ALEN];
-		char label[8];
+struct nfp_nsp_identify *__nfp_nsp_identify(struct nfp_nsp *nsp)
+{
+	struct nfp_nsp_identify *nspi = NULL;
+	struct nsp_identify *ni;
+	int ret;
 
-		bool enabled;
-		bool tx_enabled;
-		bool rx_enabled;
-	} ports[0];
-};
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 15)
+		return NULL;
+
+	ni = kzalloc(sizeof(*ni), GFP_KERNEL);
+	if (!ni)
+		return NULL;
+
+	ret = nfp_nsp_read_identify(nsp, ni, sizeof(*ni));
+	if (ret < 0) {
+		nfp_err(nfp_nsp_cpp(nsp), "reading bsp version failed %d\n",
+			ret);
+		goto exit_free;
+	}
+
+	nspi = kzalloc(sizeof(*nspi), GFP_KERNEL);
+	if (!nspi)
+		goto exit_free;
 
-struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp);
-struct nfp_eth_table *
-__nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp);
-int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable);
+	memcpy(nspi->version, ni->version, sizeof(nspi->version));
+	nspi->version[sizeof(nspi->version) - 1] = '\0';
+	nspi->flags = ni->flags;
+	nspi->br_primary = ni->br_primary;
+	nspi->br_secondary = ni->br_secondary;
+	nspi->br_nsp = ni->br_nsp;
+	nspi->primary = le16_to_cpu(ni->primary);
+	nspi->secondary = le16_to_cpu(ni->secondary);
+	nspi->nsp = le16_to_cpu(ni->nsp);
 
-#endif
+exit_free:
+	kfree(ni);
+	return nspi;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index 1ece1f8ae4b3..639438d8313a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -43,13 +43,13 @@
 #include <linux/module.h>
 
 #include "nfp.h"
-#include "nfp_nsp_eth.h"
+#include "nfp_nsp.h"
 #include "nfp6000/nfp6000.h"
 
 #define NSP_ETH_NBI_PORT_COUNT		24
 #define NSP_ETH_MAX_COUNT		(2 * NSP_ETH_NBI_PORT_COUNT)
 #define NSP_ETH_TABLE_SIZE		(NSP_ETH_MAX_COUNT *		\
-					 sizeof(struct eth_table_entry))
+					 sizeof(union eth_table_entry))
 
 #define NSP_ETH_PORT_LANES		GENMASK_ULL(3, 0)
 #define NSP_ETH_PORT_INDEX		GENMASK_ULL(15, 8)
@@ -58,14 +58,32 @@
 
 #define NSP_ETH_PORT_LANES_MASK		cpu_to_le64(NSP_ETH_PORT_LANES)
 
+#define NSP_ETH_STATE_CONFIGURED	BIT_ULL(0)
 #define NSP_ETH_STATE_ENABLED		BIT_ULL(1)
 #define NSP_ETH_STATE_TX_ENABLED	BIT_ULL(2)
 #define NSP_ETH_STATE_RX_ENABLED	BIT_ULL(3)
 #define NSP_ETH_STATE_RATE		GENMASK_ULL(11, 8)
+#define NSP_ETH_STATE_INTERFACE		GENMASK_ULL(19, 12)
+#define NSP_ETH_STATE_MEDIA		GENMASK_ULL(21, 20)
+#define NSP_ETH_STATE_OVRD_CHNG		BIT_ULL(22)
+#define NSP_ETH_STATE_ANEG		GENMASK_ULL(25, 23)
 
+#define NSP_ETH_CTRL_CONFIGURED		BIT_ULL(0)
 #define NSP_ETH_CTRL_ENABLED		BIT_ULL(1)
 #define NSP_ETH_CTRL_TX_ENABLED		BIT_ULL(2)
 #define NSP_ETH_CTRL_RX_ENABLED		BIT_ULL(3)
+#define NSP_ETH_CTRL_SET_RATE		BIT_ULL(4)
+#define NSP_ETH_CTRL_SET_LANES		BIT_ULL(5)
+#define NSP_ETH_CTRL_SET_ANEG		BIT_ULL(6)
+
+enum nfp_eth_raw {
+	NSP_ETH_RAW_PORT = 0,
+	NSP_ETH_RAW_STATE,
+	NSP_ETH_RAW_MAC,
+	NSP_ETH_RAW_CONTROL,
+
+	NSP_ETH_NUM_RAW
+};
 
 enum nfp_eth_rate {
 	RATE_INVALID = 0,
@@ -76,29 +94,49 @@ enum nfp_eth_rate {
 	RATE_25G,
 };
 
-struct eth_table_entry {
-	__le64 port;
-	__le64 state;
-	u8 mac_addr[6];
-	u8 resv[2];
-	__le64 control;
+union eth_table_entry {
+	struct {
+		__le64 port;
+		__le64 state;
+		u8 mac_addr[6];
+		u8 resv[2];
+		__le64 control;
+	};
+	__le64 raw[NSP_ETH_NUM_RAW];
+};
+
+static const struct {
+	enum nfp_eth_rate rate;
+	unsigned int speed;
+} nsp_eth_rate_tbl[] = {
+	{ RATE_INVALID,	0, },
+	{ RATE_10M,	SPEED_10, },
+	{ RATE_100M,	SPEED_100, },
+	{ RATE_1G,	SPEED_1000, },
+	{ RATE_10G,	SPEED_10000, },
+	{ RATE_25G,	SPEED_25000, },
 };
 
-static unsigned int nfp_eth_rate(enum nfp_eth_rate rate)
+static unsigned int nfp_eth_rate2speed(enum nfp_eth_rate rate)
 {
-	unsigned int rate_xlate[] = {
-		[RATE_INVALID]		= 0,
-		[RATE_10M]		= SPEED_10,
-		[RATE_100M]		= SPEED_100,
-		[RATE_1G]		= SPEED_1000,
-		[RATE_10G]		= SPEED_10000,
-		[RATE_25G]		= SPEED_25000,
-	};
+	int i;
 
-	if (rate >= ARRAY_SIZE(rate_xlate))
-		return 0;
+	for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++)
+		if (nsp_eth_rate_tbl[i].rate == rate)
+			return nsp_eth_rate_tbl[i].speed;
+
+	return 0;
+}
+
+static unsigned int nfp_eth_speed2rate(unsigned int speed)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++)
+		if (nsp_eth_rate_tbl[i].speed == speed)
+			return nsp_eth_rate_tbl[i].rate;
 
-	return rate_xlate[rate];
+	return RATE_INVALID;
 }
 
 static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src)
@@ -110,8 +148,8 @@ static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src)
 }
 
 static void
-nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index,
-		       struct nfp_eth_table_port *dst)
+nfp_eth_port_translate(struct nfp_nsp *nsp, const union eth_table_entry *src,
+		       unsigned int index, struct nfp_eth_table_port *dst)
 {
 	unsigned int rate;
 	u64 port, state;
@@ -129,14 +167,60 @@ nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index,
 	dst->tx_enabled = FIELD_GET(NSP_ETH_STATE_TX_ENABLED, state);
 	dst->rx_enabled = FIELD_GET(NSP_ETH_STATE_RX_ENABLED, state);
 
-	rate = nfp_eth_rate(FIELD_GET(NSP_ETH_STATE_RATE, state));
+	rate = nfp_eth_rate2speed(FIELD_GET(NSP_ETH_STATE_RATE, state));
 	dst->speed = dst->lanes * rate;
 
+	dst->interface = FIELD_GET(NSP_ETH_STATE_INTERFACE, state);
+	dst->media = FIELD_GET(NSP_ETH_STATE_MEDIA, state);
+
 	nfp_eth_copy_mac_reverse(dst->mac_addr, src->mac_addr);
 
-	snprintf(dst->label, sizeof(dst->label) - 1, "%llu.%llu",
-		 FIELD_GET(NSP_ETH_PORT_PHYLABEL, port),
-		 FIELD_GET(NSP_ETH_PORT_LABEL, port));
+	dst->label_port = FIELD_GET(NSP_ETH_PORT_PHYLABEL, port);
+	dst->label_subport = FIELD_GET(NSP_ETH_PORT_LABEL, port);
+
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 17)
+		return;
+
+	dst->override_changed = FIELD_GET(NSP_ETH_STATE_OVRD_CHNG, state);
+	dst->aneg = FIELD_GET(NSP_ETH_STATE_ANEG, state);
+}
+
+static void
+nfp_eth_mark_split_ports(struct nfp_cpp *cpp, struct nfp_eth_table *table)
+{
+	unsigned int i, j;
+
+	for (i = 0; i < table->count; i++)
+		for (j = 0; j < table->count; j++) {
+			if (i == j)
+				continue;
+			if (table->ports[i].label_port !=
+			    table->ports[j].label_port)
+				continue;
+			if (table->ports[i].label_subport ==
+			    table->ports[j].label_subport)
+				nfp_warn(cpp,
+					 "Port %d subport %d is a duplicate\n",
+					 table->ports[i].label_port,
+					 table->ports[i].label_subport);
+
+			table->ports[i].is_split = true;
+			break;
+		}
+}
+
+static void
+nfp_eth_calc_port_type(struct nfp_cpp *cpp, struct nfp_eth_table_port *entry)
+{
+	if (entry->interface == NFP_INTERFACE_NONE) {
+		entry->port_type = PORT_NONE;
+		return;
+	}
+
+	if (entry->media == NFP_MEDIA_FIBRE)
+		entry->port_type = PORT_FIBRE;
+	else
+		entry->port_type = PORT_DA;
 }
 
 /**
@@ -166,10 +250,9 @@ struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp)
 struct nfp_eth_table *
 __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
 {
-	struct eth_table_entry *entries;
+	union eth_table_entry *entries;
 	struct nfp_eth_table *table;
-	unsigned int cnt;
-	int i, j, ret;
+	int i, j, ret, cnt = 0;
 
 	entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
 	if (!entries)
@@ -178,93 +261,288 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
 	ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
 	if (ret < 0) {
 		nfp_err(cpp, "reading port table failed %d\n", ret);
-		kfree(entries);
-		return NULL;
+		goto err;
 	}
 
-	/* Some versions of flash will give us 0 instead of port count */
-	cnt = ret;
-	if (!cnt) {
-		for (i = 0; i < NSP_ETH_MAX_COUNT; i++)
-			if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
-				cnt++;
+	for (i = 0; i < NSP_ETH_MAX_COUNT; i++)
+		if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
+			cnt++;
+
+	/* Some versions of flash will give us 0 instead of port count.
+	 * For those that give a port count, verify it against the value
+	 * calculated above.
+	 */
+	if (ret && ret != cnt) {
+		nfp_err(cpp, "table entry count reported (%d) does not match entries present (%d)\n",
+			ret, cnt);
+		goto err;
 	}
 
 	table = kzalloc(sizeof(*table) +
 			sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL);
-	if (!table) {
-		kfree(entries);
-		return NULL;
-	}
+	if (!table)
+		goto err;
 
 	table->count = cnt;
 	for (i = 0, j = 0; i < NSP_ETH_MAX_COUNT; i++)
 		if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
-			nfp_eth_port_translate(&entries[i], i,
+			nfp_eth_port_translate(nsp, &entries[i], i,
 					       &table->ports[j++]);
 
+	nfp_eth_mark_split_ports(cpp, table);
+	for (i = 0; i < table->count; i++)
+		nfp_eth_calc_port_type(cpp, &table->ports[i]);
+
 	kfree(entries);
 
 	return table;
+
+err:
+	kfree(entries);
+	return NULL;
 }
 
-/**
- * nfp_eth_set_mod_enable() - set PHY module enable control bit
- * @cpp:	NFP CPP handle
- * @idx:	NFP chip-wide port index
- * @enable:	Desired state
- *
- * Enable or disable PHY module (this usually means setting the TX lanes
- * disable bits).
- *
- * Return: 0 or -ERRNO.
- */
-int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable)
+struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx)
 {
-	struct eth_table_entry *entries;
+	union eth_table_entry *entries;
 	struct nfp_nsp *nsp;
-	u64 reg;
 	int ret;
 
 	entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
 	if (!entries)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	nsp = nfp_nsp_open(cpp);
 	if (IS_ERR(nsp)) {
 		kfree(entries);
-		return PTR_ERR(nsp);
+		return nsp;
 	}
 
 	ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
 	if (ret < 0) {
 		nfp_err(cpp, "reading port table failed %d\n", ret);
-		goto exit_close_nsp;
+		goto err;
 	}
 
 	if (!(entries[idx].port & NSP_ETH_PORT_LANES_MASK)) {
 		nfp_warn(cpp, "trying to set port state on disabled port %d\n",
 			 idx);
-		ret = -EINVAL;
-		goto exit_close_nsp;
+		goto err;
+	}
+
+	nfp_nsp_config_set_state(nsp, entries, idx);
+	return nsp;
+
+err:
+	nfp_nsp_close(nsp);
+	kfree(entries);
+	return ERR_PTR(-EIO);
+}
+
+void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp)
+{
+	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+
+	nfp_nsp_config_set_modified(nsp, false);
+	nfp_nsp_config_clear_state(nsp);
+	nfp_nsp_close(nsp);
+	kfree(entries);
+}
+
+/**
+ * nfp_eth_config_commit_end() - perform recorded configuration changes
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ *
+ * Perform the configuration which was requested with __nfp_eth_set_*()
+ * helpers and recorded in @nsp state.  If device was already configured
+ * as requested or no __nfp_eth_set_*() operations were made no NSP command
+ * will be performed.
+ *
+ * Return:
+ * 0 - configuration successful;
+ * 1 - no changes were needed;
+ * -ERRNO - configuration failed.
+ */
+int nfp_eth_config_commit_end(struct nfp_nsp *nsp)
+{
+	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+	int ret = 1;
+
+	if (nfp_nsp_config_modified(nsp)) {
+		ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
+		ret = ret < 0 ? ret : 0;
+	}
+
+	nfp_eth_config_cleanup_end(nsp);
+
+	return ret;
+}
+
+/**
+ * nfp_eth_set_mod_enable() - set PHY module enable control bit
+ * @cpp:	NFP CPP handle
+ * @idx:	NFP chip-wide port index
+ * @enable:	Desired state
+ *
+ * Enable or disable PHY module (this usually means setting the TX lanes
+ * disable bits).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable)
+{
+	union eth_table_entry *entries;
+	struct nfp_nsp *nsp;
+	u64 reg;
+
+	nsp = nfp_eth_config_start(cpp, idx);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	entries = nfp_nsp_config_entries(nsp);
+
+	/* Check if we are already in requested state */
+	reg = le64_to_cpu(entries[idx].state);
+	if (enable != FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) {
+		reg = le64_to_cpu(entries[idx].control);
+		reg &= ~NSP_ETH_CTRL_ENABLED;
+		reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable);
+		entries[idx].control = cpu_to_le64(reg);
+
+		nfp_nsp_config_set_modified(nsp, true);
 	}
 
+	return nfp_eth_config_commit_end(nsp);
+}
+
+/**
+ * nfp_eth_set_configured() - set PHY module configured control bit
+ * @cpp:	NFP CPP handle
+ * @idx:	NFP chip-wide port index
+ * @configed:	Desired state
+ *
+ * Set the ifup/ifdown state on the PHY.
+ *
+ * Return: 0 or -ERRNO.
+ */
+int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed)
+{
+	union eth_table_entry *entries;
+	struct nfp_nsp *nsp;
+	u64 reg;
+
+	nsp = nfp_eth_config_start(cpp, idx);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	entries = nfp_nsp_config_entries(nsp);
+
 	/* Check if we are already in requested state */
 	reg = le64_to_cpu(entries[idx].state);
-	if (enable == FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) {
-		ret = 0;
-		goto exit_close_nsp;
+	if (configed != FIELD_GET(NSP_ETH_STATE_CONFIGURED, reg)) {
+		reg = le64_to_cpu(entries[idx].control);
+		reg &= ~NSP_ETH_CTRL_CONFIGURED;
+		reg |= FIELD_PREP(NSP_ETH_CTRL_CONFIGURED, configed);
+		entries[idx].control = cpu_to_le64(reg);
+
+		nfp_nsp_config_set_modified(nsp, true);
 	}
 
-	reg = le64_to_cpu(entries[idx].control);
-	reg &= ~NSP_ETH_CTRL_ENABLED;
-	reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable);
-	entries[idx].control = cpu_to_le64(reg);
+	return nfp_eth_config_commit_end(nsp);
+}
 
-	ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
-exit_close_nsp:
-	nfp_nsp_close(nsp);
-	kfree(entries);
+/* Force inline, FIELD_* macroes require masks to be compilation-time known */
+static __always_inline int
+nfp_eth_set_bit_config(struct nfp_nsp *nsp, unsigned int raw_idx,
+		       const u64 mask, unsigned int val, const u64 ctrl_bit)
+{
+	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+	unsigned int idx = nfp_nsp_config_idx(nsp);
+	u64 reg;
+
+	/* Note: set features were added in ABI 0.14 but the error
+	 *	 codes were initially not populated correctly.
+	 */
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 17) {
+		nfp_err(nfp_nsp_cpp(nsp),
+			"set operations not supported, please update flash\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Check if we are already in requested state */
+	reg = le64_to_cpu(entries[idx].raw[raw_idx]);
+	if (val == FIELD_GET(mask, reg))
+		return 0;
 
-	return ret < 0 ? ret : 0;
+	reg &= ~mask;
+	reg |= FIELD_PREP(mask, val);
+	entries[idx].raw[raw_idx] = cpu_to_le64(reg);
+
+	entries[idx].control |= cpu_to_le64(ctrl_bit);
+
+	nfp_nsp_config_set_modified(nsp, true);
+
+	return 0;
+}
+
+/**
+ * __nfp_eth_set_aneg() - set PHY autonegotiation control bit
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @mode:	Desired autonegotiation mode
+ *
+ * Allow/disallow PHY module to advertise/perform autonegotiation.
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode)
+{
+	return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE,
+				      NSP_ETH_STATE_ANEG, mode,
+				      NSP_ETH_CTRL_SET_ANEG);
+}
+
+/**
+ * __nfp_eth_set_speed() - set interface speed/rate
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @speed:	Desired speed (per lane)
+ *
+ * Set lane speed.  Provided @speed value should be subport speed divided
+ * by number of lanes this subport is spanning (i.e. 10000 for 40G, 25000 for
+ * 50G, etc.)
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed)
+{
+	enum nfp_eth_rate rate;
+
+	rate = nfp_eth_speed2rate(speed);
+	if (rate == RATE_INVALID) {
+		nfp_warn(nfp_nsp_cpp(nsp),
+			 "could not find matching lane rate for speed %u\n",
+			 speed);
+		return -EINVAL;
+	}
+
+	return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE,
+				      NSP_ETH_STATE_RATE, rate,
+				      NSP_ETH_CTRL_SET_RATE);
+}
+
+/**
+ * __nfp_eth_set_split() - set interface lane split
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @lanes:	Desired lanes per port
+ *
+ * Set number of lanes in the port.
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes)
+{
+	return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_PORT, NSP_ETH_PORT_LANES,
+				      lanes, NSP_ETH_CTRL_SET_LANES);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
index a2850344f8b4..2d15a7c9d0de 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
@@ -45,6 +45,13 @@
 #include "nfp_cpp.h"
 #include "nfp6000/nfp6000.h"
 
+#define NFP_RESOURCE_TBL_TARGET		NFP_CPP_TARGET_MU
+#define NFP_RESOURCE_TBL_BASE		0x8100000000ULL
+
+/* NFP Resource Table self-identifier */
+#define NFP_RESOURCE_TBL_NAME		"nfp.res"
+#define NFP_RESOURCE_TBL_KEY		0x00000000 /* Special key for entry 0 */
+
 #define NFP_RESOURCE_ENTRY_NAME_SZ	8
 
 /**
@@ -100,9 +107,11 @@ static int nfp_cpp_resource_find(struct nfp_cpp *cpp, struct nfp_resource *res)
 	strncpy(name_pad, res->name, sizeof(name_pad));
 
 	/* Search for a matching entry */
-	key = NFP_RESOURCE_TBL_KEY;
-	if (memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8))
-		key = crc32_posix(name_pad, sizeof(name_pad));
+	if (!memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8)) {
+		nfp_err(cpp, "Grabbing device lock not supported\n");
+		return -EOPNOTSUPP;
+	}
+	key = crc32_posix(name_pad, sizeof(name_pad));
 
 	for (i = 0; i < NFP_RESOURCE_TBL_ENTRIES; i++) {
 		u64 addr = NFP_RESOURCE_TBL_BASE +
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index 9709c8ca0774..159564d8dcdb 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -152,7 +152,6 @@ struct  w90p910_ether {
 	struct tran_pdesc *tdesc;
 	dma_addr_t rdesc_phys;
 	dma_addr_t tdesc_phys;
-	struct net_device_stats stats;
 	struct platform_device *pdev;
 	struct resource *res;
 	struct sk_buff *skb;
@@ -584,15 +583,6 @@ static int w90p910_ether_close(struct net_device *dev)
 	return 0;
 }
 
-static struct net_device_stats *w90p910_ether_stats(struct net_device *dev)
-{
-	struct w90p910_ether *ether;
-
-	ether = netdev_priv(dev);
-
-	return &ether->stats;
-}
-
 static int w90p910_send_frame(struct net_device *dev,
 					unsigned char *data, int length)
 {
@@ -671,10 +661,10 @@ static irqreturn_t w90p910_tx_interrupt(int irq, void *dev_id)
 			ether->finish_tx = 0;
 
 		if (txbd->sl & TXDS_TXCP) {
-			ether->stats.tx_packets++;
-			ether->stats.tx_bytes += txbd->sl & 0xFFFF;
+			dev->stats.tx_packets++;
+			dev->stats.tx_bytes += txbd->sl & 0xFFFF;
 		} else {
-			ether->stats.tx_errors++;
+			dev->stats.tx_errors++;
 		}
 
 		txbd->sl = 0x0;
@@ -730,7 +720,7 @@ static void netdev_rx(struct net_device *dev)
 			data = ether->rdesc->recv_buf[ether->cur_rx];
 			skb = netdev_alloc_skb(dev, length + 2);
 			if (!skb) {
-				ether->stats.rx_dropped++;
+				dev->stats.rx_dropped++;
 				return;
 			}
 
@@ -738,24 +728,24 @@ static void netdev_rx(struct net_device *dev)
 			skb_put(skb, length);
 			skb_copy_to_linear_data(skb, data, length);
 			skb->protocol = eth_type_trans(skb, dev);
-			ether->stats.rx_packets++;
-			ether->stats.rx_bytes += length;
+			dev->stats.rx_packets++;
+			dev->stats.rx_bytes += length;
 			netif_rx(skb);
 		} else {
-			ether->stats.rx_errors++;
+			dev->stats.rx_errors++;
 
 			if (status & RXDS_RP) {
 				dev_err(&pdev->dev, "rx runt err\n");
-				ether->stats.rx_length_errors++;
+				dev->stats.rx_length_errors++;
 			} else if (status & RXDS_CRCE) {
 				dev_err(&pdev->dev, "rx crc err\n");
-				ether->stats.rx_crc_errors++;
+				dev->stats.rx_crc_errors++;
 			} else if (status & RXDS_ALIE) {
 				dev_err(&pdev->dev, "rx alignment err\n");
-				ether->stats.rx_frame_errors++;
+				dev->stats.rx_frame_errors++;
 			} else if (status & RXDS_PTLE) {
 				dev_err(&pdev->dev, "rx longer err\n");
-				ether->stats.rx_over_errors++;
+				dev->stats.rx_over_errors++;
 			}
 		}
 
@@ -912,7 +902,6 @@ static const struct net_device_ops w90p910_ether_netdev_ops = {
 	.ndo_open		= w90p910_ether_open,
 	.ndo_stop		= w90p910_ether_close,
 	.ndo_start_xmit		= w90p910_ether_start_xmit,
-	.ndo_get_stats		= w90p910_ether_stats,
 	.ndo_set_rx_mode	= w90p910_ether_set_multicast_list,
 	.ndo_set_mac_address	= w90p910_set_mac_address,
 	.ndo_do_ioctl		= w90p910_ether_ioctl,
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 7b43a3b4abdc..3dd973475125 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1375,13 +1375,8 @@ netxen_receive_peg_ready(struct netxen_adapter *adapter)
 
 	} while (--retries);
 
-	if (!retries) {
-		printk(KERN_ERR "Receive Peg initialization not "
-			      "complete, state: 0x%x.\n", val);
-		return -EIO;
-	}
-
-	return 0;
+	pr_err("Receive Peg initialization not complete, state: 0x%x.\n", val);
+	return -EIO;
 }
 
 int netxen_init_firmware(struct netxen_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 00c17fa6545b..2ab1aab7c3fe 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -51,7 +51,19 @@
 #include "qed_hsi.h"
 
 extern const struct qed_common_ops qed_common_ops_pass;
-#define DRV_MODULE_VERSION "8.10.10.20"
+
+#define QED_MAJOR_VERSION               8
+#define QED_MINOR_VERSION               10
+#define QED_REVISION_VERSION            10
+#define QED_ENGINEERING_VERSION 21
+
+#define QED_VERSION						 \
+	((QED_MAJOR_VERSION << 24) | (QED_MINOR_VERSION << 16) | \
+	 (QED_REVISION_VERSION << 8) | QED_ENGINEERING_VERSION)
+
+#define STORM_FW_VERSION				       \
+	((FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | \
+	 (FW_REVISION_VERSION << 8) | FW_ENGINEERING_VERSION)
 
 #define MAX_HWFNS_PER_DEVICE    (4)
 #define NAME_SIZE 16
@@ -59,9 +71,8 @@ extern const struct qed_common_ops qed_common_ops_pass;
 
 #define QED_WFQ_UNIT	100
 
-#define ISCSI_BDQ_ID(_port_id) (_port_id)
-#define FCOE_BDQ_ID(_port_id) ((_port_id) + 2)
 #define QED_WID_SIZE            (1024)
+#define QED_MIN_WIDS		(4)
 #define QED_PF_DEMS_SIZE        (4)
 
 /* cau states */
@@ -76,6 +87,15 @@ union qed_mcp_protocol_stats;
 enum qed_mcp_protocol_type;
 
 /* helpers */
+#define QED_MFW_GET_FIELD(name, field) \
+	(((name) & (field ## _MASK)) >> (field ## _SHIFT))
+
+#define QED_MFW_SET_FIELD(name, field, value)				       \
+	do {								       \
+		(name)	&= ~((field ## _MASK) << (field ## _SHIFT));	       \
+		(name)	|= (((value) << (field ## _SHIFT)) & (field ## _MASK));\
+	} while (0)
+
 static inline u32 qed_db_addr(u32 cid, u32 DEMS)
 {
 	u32 db_addr = FIELD_VALUE(DB_LEGACY_ADDR_DEMS, DEMS) |
@@ -130,9 +150,35 @@ enum qed_tunn_clss {
 	QED_TUNN_CLSS_MAC_VNI,
 	QED_TUNN_CLSS_INNER_MAC_VLAN,
 	QED_TUNN_CLSS_INNER_MAC_VNI,
+	QED_TUNN_CLSS_MAC_VLAN_DUAL_STAGE,
 	MAX_QED_TUNN_CLSS,
 };
 
+struct qed_tunn_update_type {
+	bool b_update_mode;
+	bool b_mode_enabled;
+	enum qed_tunn_clss tun_cls;
+};
+
+struct qed_tunn_update_udp_port {
+	bool b_update_port;
+	u16 port;
+};
+
+struct qed_tunnel_info {
+	struct qed_tunn_update_type vxlan;
+	struct qed_tunn_update_type l2_geneve;
+	struct qed_tunn_update_type ip_geneve;
+	struct qed_tunn_update_type l2_gre;
+	struct qed_tunn_update_type ip_gre;
+
+	struct qed_tunn_update_udp_port vxlan_port;
+	struct qed_tunn_update_udp_port geneve_port;
+
+	bool b_update_rx_cls;
+	bool b_update_tx_cls;
+};
+
 struct qed_tunn_start_params {
 	unsigned long	tunn_mode;
 	u16		vxlan_udp_port;
@@ -198,6 +244,7 @@ enum qed_resources {
 	QED_LL2_QUEUE,
 	QED_CMDQS_CQS,
 	QED_RDMA_STATS_QUEUE,
+	QED_BDQ,
 	QED_MAX_RESC,
 };
 
@@ -205,8 +252,9 @@ enum QED_FEATURE {
 	QED_PF_L2_QUE,
 	QED_VF,
 	QED_RDMA_CNQ,
-	QED_VF_L2_QUE,
+	QED_ISCSI_CQ,
 	QED_FCOE_CQ,
+	QED_VF_L2_QUE,
 	QED_MAX_FEATURES,
 };
 
@@ -219,7 +267,9 @@ enum QED_PORT_MODE {
 	QED_PORT_MODE_DE_4X20G,
 	QED_PORT_MODE_DE_1X40G,
 	QED_PORT_MODE_DE_2X25G,
-	QED_PORT_MODE_DE_1X25G
+	QED_PORT_MODE_DE_1X25G,
+	QED_PORT_MODE_DE_4X25G,
+	QED_PORT_MODE_DE_2X10G,
 };
 
 enum qed_dev_cap {
@@ -249,9 +299,14 @@ struct qed_hw_info {
 				 RESC_NUM(_p_hwfn, resc))
 #define FEAT_NUM(_p_hwfn, resc) ((_p_hwfn)->hw_info.feat_num[resc])
 
-	u8				num_tc;
+	/* Amount of traffic classes HW supports */
+	u8 num_hw_tc;
+
+	/* Amount of TCs which should be active according to DCBx or upper
+	 * layer driver configuration.
+	 */
+	u8 num_active_tc;
 	u8				offload_tc;
-	u8				non_offload_tc;
 
 	u32				concrete_fid;
 	u16				opaque_fid;
@@ -314,15 +369,19 @@ struct qed_qm_info {
 	struct init_qm_port_params	*qm_port_params;
 	u16				start_pq;
 	u8				start_vport;
-	u8				pure_lb_pq;
-	u8				offload_pq;
-	u8				pure_ack_pq;
-	u8 ooo_pq;
-	u8				vf_queues_offset;
+	u16				 pure_lb_pq;
+	u16				offload_pq;
+	u16				low_latency_pq;
+	u16				pure_ack_pq;
+	u16				ooo_pq;
+	u16				first_vf_pq;
+	u16				first_mcos_pq;
+	u16				first_rl_pq;
 	u16				num_pqs;
 	u16				num_vf_pqs;
 	u8				num_vports;
 	u8				max_phys_tcs_per_port;
+	u8				ooo_tc;
 	bool				pf_rl_en;
 	bool				pf_wfq_en;
 	bool				vport_rl_en;
@@ -353,6 +412,12 @@ struct qed_fw_data {
 	u32			init_ops_size;
 };
 
+#define DRV_MODULE_VERSION		      \
+	__stringify(QED_MAJOR_VERSION) "."    \
+	__stringify(QED_MINOR_VERSION) "."    \
+	__stringify(QED_REVISION_VERSION) "." \
+	__stringify(QED_ENGINEERING_VERSION)
+
 struct qed_simd_fp_handler {
 	void	*token;
 	void	(*func)(void *);
@@ -364,7 +429,8 @@ struct qed_hwfn {
 #define IS_LEAD_HWFN(edev)              (!((edev)->my_id))
 	u8				rel_pf_id;      /* Relative to engine*/
 	u8				abs_pf_id;
-#define QED_PATH_ID(_p_hwfn)		((_p_hwfn)->abs_pf_id & 1)
+#define QED_PATH_ID(_p_hwfn) \
+	(QED_IS_K2((_p_hwfn)->cdev) ? 0 : ((_p_hwfn)->abs_pf_id & 1))
 	u8				port_id;
 	bool				b_active;
 
@@ -409,6 +475,11 @@ struct qed_hwfn {
 	struct qed_ptt			*p_main_ptt;
 	struct qed_ptt			*p_dpc_ptt;
 
+	/* PTP will be used only by the leading function.
+	 * Usage of all PTP-apis should be synchronized as result.
+	 */
+	struct qed_ptt *p_ptp_ptt;
+
 	struct qed_sb_sp_info		*p_sp_sb;
 	struct qed_sb_attn_info		*p_sb_attn;
 
@@ -455,6 +526,7 @@ struct qed_hwfn {
 	struct dbg_tools_data		dbg_info;
 
 	/* PWM region specific data */
+	u16				wid_count;
 	u32				dpi_size;
 	u32				dpi_count;
 
@@ -465,8 +537,8 @@ struct qed_hwfn {
 	u8 dcbx_no_edpm;
 	u8 db_bar_no_edpm;
 
-	/* p_ptp_ptt is valid for leading HWFN only */
-	struct qed_ptt *p_ptp_ptt;
+	struct qed_ptt *p_arfs_ptt;
+
 	struct qed_simd_fp_handler	simd_proto_handler[64];
 
 #ifdef CONFIG_QED_SRIOV
@@ -523,9 +595,7 @@ struct qed_dev {
 	u8	dp_level;
 	char	name[NAME_SIZE];
 
-	u8	type;
-#define QED_DEV_TYPE_BB (0 << 0)
-#define QED_DEV_TYPE_AH BIT(0)
+	enum	qed_dev_type type;
 /* Translate type/revision combo into the proper conditions */
 #define QED_IS_BB(dev)  ((dev)->type == QED_DEV_TYPE_BB)
 #define QED_IS_BB_A0(dev)       (QED_IS_BB(dev) && \
@@ -540,6 +610,9 @@ struct qed_dev {
 
 	u16	vendor_id;
 	u16	device_id;
+#define QED_DEV_ID_MASK		0xff00
+#define QED_DEV_ID_MASK_BB	0x1600
+#define QED_DEV_ID_MASK_AH	0x8000
 
 	u16	chip_num;
 #define CHIP_NUM_MASK                   0xffff
@@ -606,9 +679,7 @@ struct qed_dev {
 	/* SRIOV */
 	struct qed_hw_sriov_info *p_iov_info;
 #define IS_QED_SRIOV(cdev)              (!!(cdev)->p_iov_info)
-
-	unsigned long			tunn_mode;
-
+	struct qed_tunnel_info		tunnel;
 	bool				b_is_vf;
 	u32				drv_type;
 	struct qed_eth_stats		*reset_stats;
@@ -652,12 +723,19 @@ struct qed_dev {
 	u32 rdma_max_sge;
 	u32 rdma_max_inline;
 	u32 rdma_max_srq_sge;
+	u16 tunn_feature_mask;
 };
 
-#define NUM_OF_VFS(dev)         MAX_NUM_VFS_BB
-#define NUM_OF_L2_QUEUES(dev)	MAX_NUM_L2_QUEUES_BB
-#define NUM_OF_SBS(dev)         MAX_SB_PER_PATH_BB
-#define NUM_OF_ENG_PFS(dev)     MAX_NUM_PFS_BB
+#define NUM_OF_VFS(dev)         (QED_IS_BB(dev) ? MAX_NUM_VFS_BB \
+						: MAX_NUM_VFS_K2)
+#define NUM_OF_L2_QUEUES(dev)   (QED_IS_BB(dev) ? MAX_NUM_L2_QUEUES_BB \
+						: MAX_NUM_L2_QUEUES_K2)
+#define NUM_OF_PORTS(dev)       (QED_IS_BB(dev) ? MAX_NUM_PORTS_BB \
+						: MAX_NUM_PORTS_K2)
+#define NUM_OF_SBS(dev)         (QED_IS_BB(dev) ? MAX_SB_PER_PATH_BB \
+						: MAX_SB_PER_PATH_K2)
+#define NUM_OF_ENG_PFS(dev)     (QED_IS_BB(dev) ? MAX_NUM_PFS_BB \
+						: MAX_NUM_PFS_K2)
 
 /**
  * @brief qed_concrete_to_sw_fid - get the sw function id from
@@ -693,6 +771,26 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev,
 					 u32 min_pf_rate);
 
 void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+int qed_device_num_engines(struct qed_dev *cdev);
+int qed_device_get_port_id(struct qed_dev *cdev);
+
+#define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
+
+/* Flags for indication of required queues */
+#define PQ_FLAGS_RLS    (BIT(0))
+#define PQ_FLAGS_MCOS   (BIT(1))
+#define PQ_FLAGS_LB     (BIT(2))
+#define PQ_FLAGS_OOO    (BIT(3))
+#define PQ_FLAGS_ACK    (BIT(4))
+#define PQ_FLAGS_OFLD   (BIT(5))
+#define PQ_FLAGS_VFS    (BIT(6))
+#define PQ_FLAGS_LLT    (BIT(7))
+
+/* physical queue index for cm context intialization */
+u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
+u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
 /* Other Linux specific common definitions */
@@ -721,5 +819,6 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);
 int qed_slowpath_irq_req(struct qed_hwfn *hwfn);
+void qed_slowpath_irq_sync(struct qed_hwfn *p_hwfn);
 
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index d42d03df751a..b3aaa985956e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -71,8 +71,7 @@
 #define TM_ALIGN        BIT(TM_SHIFT)
 #define TM_ELEM_SIZE    4
 
-/* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */
-#define ILT_DEFAULT_HW_P_SIZE	(IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3)
+#define ILT_DEFAULT_HW_P_SIZE	4
 
 #define ILT_PAGE_IN_BYTES(hw_p_size)	(1U << ((hw_p_size) + 12))
 #define ILT_CFG_REG(cli, reg)	PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
@@ -220,9 +219,6 @@ struct qed_cxt_mngr {
 	 */
 	u32				vf_count;
 
-	/* total number of SRQ's for this hwfn */
-	u32 srq_count;
-
 	/* Acquired CIDs */
 	struct qed_cid_acquired_map	acquired[MAX_CONN_TYPES];
 
@@ -238,12 +234,17 @@ struct qed_cxt_mngr {
 	u32 t2_num_pages;
 	u64 first_free;
 	u64 last_free;
+
+	/* total number of SRQ's for this hwfn */
+	u32 srq_count;
+
+	/* Maximal number of L2 steering filters */
+	u32 arfs_count;
 };
 static bool src_proto(enum protocol_type type)
 {
 	return type == PROTOCOLID_ISCSI ||
-	       type == PROTOCOLID_FCOE ||
-	       type == PROTOCOLID_ROCE;
+	       type == PROTOCOLID_FCOE;
 }
 
 static bool tm_cid_proto(enum protocol_type type)
@@ -293,6 +294,9 @@ static void qed_cxt_src_iids(struct qed_cxt_mngr *p_mngr,
 		iids->pf_cids += p_mngr->conn_cfg[i].cid_count;
 		iids->per_vf_cids += p_mngr->conn_cfg[i].cids_per_vf;
 	}
+
+	/* Add L2 filtering filters in addition */
+	iids->pf_cids += p_mngr->arfs_count;
 }
 
 /* counts the iids for the Timers block configuration */
@@ -304,16 +308,34 @@ struct qed_tm_iids {
 	u32 per_vf_tids;
 };
 
-static void qed_cxt_tm_iids(struct qed_cxt_mngr *p_mngr,
+static void qed_cxt_tm_iids(struct qed_hwfn *p_hwfn,
+			    struct qed_cxt_mngr *p_mngr,
 			    struct qed_tm_iids *iids)
 {
-	u32 i, j;
-
-	for (i = 0; i < MAX_CONN_TYPES; i++) {
+	bool tm_vf_required = false;
+	bool tm_required = false;
+	int i, j;
+
+	/* Timers is a special case -> we don't count how many cids require
+	 * timers but what's the max cid that will be used by the timer block.
+	 * therefore we traverse in reverse order, and once we hit a protocol
+	 * that requires the timers memory, we'll sum all the protocols up
+	 * to that one.
+	 */
+	for (i = MAX_CONN_TYPES - 1; i >= 0; i--) {
 		struct qed_conn_type_cfg *p_cfg = &p_mngr->conn_cfg[i];
 
-		if (tm_cid_proto(i)) {
+		if (tm_cid_proto(i) || tm_required) {
+			if (p_cfg->cid_count)
+				tm_required = true;
+
 			iids->pf_cids += p_cfg->cid_count;
+		}
+
+		if (tm_cid_proto(i) || tm_vf_required) {
+			if (p_cfg->cids_per_vf)
+				tm_vf_required = true;
+
 			iids->per_vf_cids += p_cfg->cids_per_vf;
 		}
 
@@ -422,8 +444,9 @@ static void qed_cxt_set_proto_cid_count(struct qed_hwfn *p_hwfn,
 		u32 page_sz = p_mgr->clients[ILT_CLI_CDUC].p_size.val;
 		u32 cxt_size = CONN_CXT_SIZE(p_hwfn);
 		u32 elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
+		u32 align = elems_per_page * DQ_RANGE_ALIGN;
 
-		p_conn->cid_count = roundup(p_conn->cid_count, elems_per_page);
+		p_conn->cid_count = roundup(p_conn->cid_count, align);
 	}
 }
 
@@ -526,7 +549,22 @@ static u32 qed_ilt_get_dynamic_line_cnt(struct qed_hwfn *p_hwfn,
 	return lines_to_skip;
 }
 
-int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
+static struct qed_ilt_client_cfg *qed_cxt_set_cli(struct qed_ilt_client_cfg
+						  *p_cli)
+{
+	p_cli->active = false;
+	p_cli->first.val = 0;
+	p_cli->last.val = 0;
+	return p_cli;
+}
+
+static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk)
+{
+	p_blk->total_size = 0;
+	return p_blk;
+}
+
+int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 {
 	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
 	u32 curr_line, total, i, task_size, line;
@@ -550,7 +588,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		   p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);
 
 	/* CDUC */
-	p_cli = &p_mngr->clients[ILT_CLI_CDUC];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUC]);
+
 	curr_line = p_mngr->pf_start_line;
 
 	/* CDUC PF */
@@ -559,7 +598,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	/* get the counters for the CDUC and QM clients  */
 	qed_cxt_cdu_iids(p_mngr, &cdu_iids);
 
-	p_blk = &p_cli->pf_blks[CDUC_BLK];
+	p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUC_BLK]);
 
 	total = cdu_iids.pf_cids * CONN_CXT_SIZE(p_hwfn);
 
@@ -573,7 +612,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 							       ILT_CLI_CDUC);
 
 	/* CDUC VF */
-	p_blk = &p_cli->vf_blks[CDUC_BLK];
+	p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUC_BLK]);
 	total = cdu_iids.per_vf_cids * CONN_CXT_SIZE(p_hwfn);
 
 	qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
@@ -587,7 +626,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 				     ILT_CLI_CDUC);
 
 	/* CDUT PF */
-	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUT]);
 	p_cli->first.val = curr_line;
 
 	/* first the 'working' task memory */
@@ -596,7 +635,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		if (!p_seg || p_seg->count == 0)
 			continue;
 
-		p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(i)];
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUT_SEG_BLK(i)]);
 		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total,
 				     p_mngr->task_type_size[p_seg->type]);
@@ -611,7 +650,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		if (!p_seg || p_seg->count == 0)
 			continue;
 
-		p_blk = &p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)];
+		p_blk =
+		    qed_cxt_set_blk(&p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)]);
 
 		if (!p_seg->has_fl_mem) {
 			/* The segment is active (total size pf 'working'
@@ -656,7 +696,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		/* 'working' memory */
 		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
 
-		p_blk = &p_cli->vf_blks[CDUT_SEG_BLK(0)];
+		p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUT_SEG_BLK(0)]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk,
 				     curr_line, total,
 				     p_mngr->task_type_size[p_seg->type]);
@@ -665,7 +705,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 				     ILT_CLI_CDUT);
 
 		/* 'init' memory */
-		p_blk = &p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)];
+		p_blk =
+		    qed_cxt_set_blk(&p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)]);
 		if (!p_seg->has_fl_mem) {
 			/* see comment above */
 			line = p_cli->vf_blks[CDUT_SEG_BLK(0)].start_line;
@@ -693,8 +734,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	}
 
 	/* QM */
-	p_cli = &p_mngr->clients[ILT_CLI_QM];
-	p_blk = &p_cli->pf_blks[0];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_QM]);
+	p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
 
 	qed_cxt_qm_iids(p_hwfn, &qm_iids);
 	total = qed_qm_pf_mem_size(p_hwfn->rel_pf_id, qm_iids.cids,
@@ -718,7 +759,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	p_cli->pf_total_lines = curr_line - p_blk->start_line;
 
 	/* SRC */
-	p_cli = &p_mngr->clients[ILT_CLI_SRC];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_SRC]);
 	qed_cxt_src_iids(p_mngr, &src_iids);
 
 	/* Both the PF and VFs searcher connections are stored in the per PF
@@ -732,7 +773,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 
 		total = roundup_pow_of_two(local_max);
 
-		p_blk = &p_cli->pf_blks[0];
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * sizeof(struct src_ent),
 				     sizeof(struct src_ent));
@@ -743,11 +784,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	}
 
 	/* TM PF */
-	p_cli = &p_mngr->clients[ILT_CLI_TM];
-	qed_cxt_tm_iids(p_mngr, &tm_iids);
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TM]);
+	qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
 	total = tm_iids.pf_cids + tm_iids.pf_tids_total;
 	if (total) {
-		p_blk = &p_cli->pf_blks[0];
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * TM_ELEM_SIZE, TM_ELEM_SIZE);
 
@@ -759,14 +800,14 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	/* TM VF */
 	total = tm_iids.per_vf_cids + tm_iids.per_vf_tids;
 	if (total) {
-		p_blk = &p_cli->vf_blks[0];
+		p_blk = qed_cxt_set_blk(&p_cli->vf_blks[0]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * TM_ELEM_SIZE, TM_ELEM_SIZE);
 
 		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
 				     ILT_CLI_TM);
-		p_cli->pf_total_lines = curr_line - p_blk->start_line;
 
+		p_cli->vf_total_lines = curr_line - p_blk->start_line;
 		for (i = 1; i < p_mngr->vf_count; i++)
 			qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
 					     ILT_CLI_TM);
@@ -776,8 +817,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	total = qed_cxt_get_srq_count(p_hwfn);
 
 	if (total) {
-		p_cli = &p_mngr->clients[ILT_CLI_TSDM];
-		p_blk = &p_cli->pf_blks[SRQ_BLK];
+		p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TSDM]);
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[SRQ_BLK]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * SRQ_CXT_SIZE, SRQ_CXT_SIZE);
 
@@ -786,13 +827,50 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		p_cli->pf_total_lines = curr_line - p_blk->start_line;
 	}
 
+	*line_count = curr_line - p_hwfn->p_cxt_mngr->pf_start_line;
+
 	if (curr_line - p_hwfn->p_cxt_mngr->pf_start_line >
-	    RESC_NUM(p_hwfn, QED_ILT)) {
-		DP_ERR(p_hwfn, "too many ilt lines...#lines=%d\n",
-		       curr_line - p_hwfn->p_cxt_mngr->pf_start_line);
+	    RESC_NUM(p_hwfn, QED_ILT))
 		return -EINVAL;
+
+	return 0;
+}
+
+u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines)
+{
+	struct qed_ilt_client_cfg *p_cli;
+	u32 excess_lines, available_lines;
+	struct qed_cxt_mngr *p_mngr;
+	u32 ilt_page_size, elem_size;
+	struct qed_tid_seg *p_seg;
+	int i;
+
+	available_lines = RESC_NUM(p_hwfn, QED_ILT);
+	excess_lines = used_lines - available_lines;
+
+	if (!excess_lines)
+		return 0;
+
+	if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+		return 0;
+
+	p_mngr = p_hwfn->p_cxt_mngr;
+	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
+	ilt_page_size = ILT_PAGE_IN_BYTES(p_cli->p_size.val);
+
+	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
+		p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
+		if (!p_seg || p_seg->count == 0)
+			continue;
+
+		elem_size = p_mngr->task_type_size[p_seg->type];
+		if (!elem_size)
+			continue;
+
+		return (ilt_page_size / elem_size) * excess_lines;
 	}
 
+	DP_NOTICE(p_hwfn, "failed computing excess ILT lines\n");
 	return 0;
 }
 
@@ -1126,7 +1204,7 @@ int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn)
 	clients[ILT_CLI_TSDM].first.reg = ILT_CFG_REG(TSDM, FIRST_ILT);
 	clients[ILT_CLI_TSDM].last.reg = ILT_CFG_REG(TSDM, LAST_ILT);
 	clients[ILT_CLI_TSDM].p_size.reg = ILT_CFG_REG(TSDM, P_SIZE);
-	/* default ILT page size for all clients is 32K */
+	/* default ILT page size for all clients is 64K */
 	for (i = 0; i < ILT_CLI_MAX; i++)
 		p_mngr->clients[i].p_size.val = ILT_DEFAULT_HW_P_SIZE;
 
@@ -1366,7 +1444,7 @@ static void qed_cdu_init_pf(struct qed_hwfn *p_hwfn)
 	}
 }
 
-void qed_qm_init_pf(struct qed_hwfn *p_hwfn)
+void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_qm_pf_rt_init_params params;
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
@@ -1392,22 +1470,15 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn)
 	params.pq_params = qm_info->qm_pq_params;
 	params.vport_params = qm_info->qm_vport_params;
 
-	qed_qm_pf_rt_init(p_hwfn, p_hwfn->p_main_ptt, &params);
+	qed_qm_pf_rt_init(p_hwfn, p_ptt, &params);
 }
 
 /* CM PF */
-static int qed_cm_init_pf(struct qed_hwfn *p_hwfn)
+void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
 {
-	union qed_qm_pq_params pq_params;
-	u16 pq;
-
 	/* XCM pure-LB queue */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = LB_TC;
-	pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
-	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET, pq);
-
-	return 0;
+	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET,
+		     qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB));
 }
 
 /* DQ PF */
@@ -1639,7 +1710,7 @@ static void qed_tm_init_pf(struct qed_hwfn *p_hwfn)
 	u8 i;
 
 	memset(&tm_iids, 0, sizeof(tm_iids));
-	qed_cxt_tm_iids(p_mngr, &tm_iids);
+	qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
 
 	/* @@@TBD No pre-scan for now */
 
@@ -1757,9 +1828,9 @@ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn)
 	qed_prs_init_common(p_hwfn);
 }
 
-void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn)
+void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	qed_qm_init_pf(p_hwfn);
+	qed_qm_init_pf(p_hwfn, p_ptt);
 	qed_cm_init_pf(p_hwfn);
 	qed_dq_init_pf(p_hwfn);
 	qed_cdu_init_pf(p_hwfn);
@@ -1883,13 +1954,12 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info)
 }
 
 static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
-				   struct qed_rdma_pf_params *p_params)
+				   struct qed_rdma_pf_params *p_params,
+				   u32 num_tasks)
 {
-	u32 num_cons, num_tasks, num_qps, num_mrs, num_srqs;
+	u32 num_cons, num_qps, num_srqs;
 	enum protocol_type proto;
 
-	num_mrs = min_t(u32, RDMA_MAX_TIDS, p_params->num_mrs);
-	num_tasks = num_mrs;	/* each mr uses a single task id */
 	num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs);
 
 	switch (p_hwfn->hw_info.personality) {
@@ -1918,7 +1988,7 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 	}
 }
 
-int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
+int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 {
 	/* Set the number of required CORE connections */
 	u32 core_cids = 1; /* SPQ */
@@ -1930,9 +2000,10 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
 	switch (p_hwfn->hw_info.personality) {
 	case QED_PCI_ETH_ROCE:
 	{
-		qed_rdma_set_pf_params(p_hwfn,
-				       &p_hwfn->
-				       pf_params.rdma_pf_params);
+			qed_rdma_set_pf_params(p_hwfn,
+					       &p_hwfn->
+					       pf_params.rdma_pf_params,
+					       rdma_tasks);
 		/* no need for break since RoCE coexist with Ethernet */
 	}
 	case QED_PCI_ETH:
@@ -1942,6 +2013,7 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
 
 		qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
 					    p_params->num_cons, 1);
+		p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters;
 		break;
 	}
 	case QED_PCI_FCOE:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index 8b010324268a..53ad532dc212 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -105,19 +105,28 @@ u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn,
  * @brief qed_cxt_set_pf_params - Set the PF params for cxt init
  *
  * @param p_hwfn
- *
+ * @param rdma_tasks - requested maximum
  * @return int
  */
-int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn);
+int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks);
 
 /**
  * @brief qed_cxt_cfg_ilt_compute - compute ILT init parameters
  *
  * @param p_hwfn
+ * @param last_line
  *
  * @return int
  */
-int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn);
+int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *last_line);
+
+/**
+ * @brief qed_cxt_cfg_ilt_compute_excess - how many lines can be decreased
+ *
+ * @param p_hwfn
+ * @param used_lines
+ */
+u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines);
 
 /**
  * @brief qed_cxt_mngr_alloc - Allocate and init the context manager struct
@@ -163,19 +172,18 @@ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn);
 /**
  * @brief qed_cxt_hw_init_pf - Initailze ILT and DQ, PF phase, per path.
  *
- *
- *
  * @param p_hwfn
+ * @param p_ptt
  */
-void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn);
+void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
 /**
  * @brief qed_qm_init_pf - Initailze the QM PF phase, per path
  *
  * @param p_hwfn
+ * @param p_ptt
  */
-
-void qed_qm_init_pf(struct qed_hwfn *p_hwfn);
+void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
 /**
  * @brief Reconfigures QM pf on the fly
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 5bd36a4a8fcd..d883ad5bec6d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -64,11 +64,11 @@
 	((u32)(prio_tc_tbl >> ((7 - prio) * 4)) & 0x7)
 
 static const struct qed_dcbx_app_metadata qed_dcbx_app_update[] = {
-	{DCBX_PROTOCOL_ISCSI, "ISCSI", QED_PCI_DEFAULT},
-	{DCBX_PROTOCOL_FCOE, "FCOE", QED_PCI_DEFAULT},
-	{DCBX_PROTOCOL_ROCE, "ROCE", QED_PCI_DEFAULT},
-	{DCBX_PROTOCOL_ROCE_V2, "ROCE_V2", QED_PCI_DEFAULT},
-	{DCBX_PROTOCOL_ETH, "ETH", QED_PCI_ETH}
+	{DCBX_PROTOCOL_ISCSI, "ISCSI", QED_PCI_ISCSI},
+	{DCBX_PROTOCOL_FCOE, "FCOE", QED_PCI_FCOE},
+	{DCBX_PROTOCOL_ROCE, "ROCE", QED_PCI_ETH_ROCE},
+	{DCBX_PROTOCOL_ROCE_V2, "ROCE_V2", QED_PCI_ETH_ROCE},
+	{DCBX_PROTOCOL_ETH, "ETH", QED_PCI_ETH},
 };
 
 static bool qed_dcbx_app_ethtype(u32 app_info_bitmap)
@@ -183,7 +183,7 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data)
 			   "%s info: update %d, enable %d, prio %d, tc %d, num_tc %d\n",
 			   qed_dcbx_app_update[i].name, p_data->arr[id].update,
 			   p_data->arr[id].enable, p_data->arr[id].priority,
-			   p_data->arr[id].tc, p_hwfn->hw_info.num_tc);
+			   p_data->arr[id].tc, p_hwfn->hw_info.num_active_tc);
 	}
 }
 
@@ -204,12 +204,8 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 	p_data->arr[type].tc = tc;
 
 	/* QM reconf data */
-	if (p_info->personality == personality) {
-		if (personality == QED_PCI_ETH)
-			p_info->non_offload_tc = tc;
-		else
-			p_info->offload_tc = tc;
-	}
+	if (p_info->personality == personality)
+		p_info->offload_tc = tc;
 }
 
 /* Update app protocol data and hw_info fields with the TLV info */
@@ -275,8 +271,8 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
 		     struct dcbx_app_priority_entry *p_tbl,
 		     u32 pri_tc_tbl, int count, u8 dcbx_version)
 {
-	u8 tc, priority_map;
 	enum dcbx_protocol_type type;
+	u8 tc, priority_map;
 	bool enable, ieee;
 	u16 protocol_id;
 	int priority;
@@ -376,7 +372,9 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn)
 	if (rc)
 		return rc;
 
-	p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS);
+	p_info->num_active_tc = QED_MFW_GET_FIELD(p_ets->flags,
+						  DCBX_ETS_MAX_TCS);
+	p_hwfn->qm_info.ooo_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_OOO_TC);
 	data.pf_id = p_hwfn->rel_pf_id;
 	data.dcbx_enabled = !!dcbx_version;
 
@@ -558,8 +556,9 @@ qed_dcbx_get_pfc_data(struct qed_hwfn *p_hwfn,
 	p_params->pfc.prio[7] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_7);
 
 	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
-		   "PFC params: willing %d, pfc_bitmap %d\n",
-		   p_params->pfc.willing, pfc_map);
+		   "PFC params: willing %d, pfc_bitmap %u max_tc = %u enabled = %d\n",
+		   p_params->pfc.willing, pfc_map, p_params->pfc.max_tc,
+		   p_params->pfc.enabled);
 }
 
 static void
@@ -578,10 +577,17 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn,
 	p_params->max_ets_tc = QED_MFW_GET_FIELD(p_ets->flags,
 						 DCBX_ETS_MAX_TCS);
 	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
-		   "ETS params: willing %d, ets_cbs %d pri_tc_tbl_0 %x max_ets_tc %d\n",
-		   p_params->ets_willing,
-		   p_params->ets_cbs,
-		   p_ets->pri_tc_tbl[0], p_params->max_ets_tc);
+		   "ETS params: willing %d, enabled = %d ets_cbs %d pri_tc_tbl_0 %x max_ets_tc %d\n",
+		   p_params->ets_willing, p_params->ets_enabled,
+		   p_params->ets_cbs, p_ets->pri_tc_tbl[0],
+		   p_params->max_ets_tc);
+
+	if (p_params->ets_enabled && !p_params->max_ets_tc) {
+		p_params->max_ets_tc = QED_MAX_PFC_PRIORITIES;
+		DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+			   "ETS params: max_ets_tc is forced to %d\n",
+		p_params->max_ets_tc);
+	}
 
 	/* 8 bit tsa and bw data corresponding to each of the 8 TC's are
 	 * encoded in a type u32 array of size 2.
@@ -615,8 +621,7 @@ qed_dcbx_get_common_params(struct qed_hwfn *p_hwfn,
 }
 
 static void
-qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt, struct qed_dcbx_get *params)
+qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn, struct qed_dcbx_get *params)
 {
 	struct dcbx_features *p_feat;
 
@@ -628,8 +633,7 @@ qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn,
 }
 
 static void
-qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn,
-			   struct qed_ptt *p_ptt, struct qed_dcbx_get *params)
+qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn, struct qed_dcbx_get *params)
 {
 	struct dcbx_features *p_feat;
 
@@ -642,7 +646,6 @@ qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn,
 
 static void
 qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
-				struct qed_ptt *p_ptt,
 				struct qed_dcbx_get *params)
 {
 	struct qed_dcbx_operational_params *p_operational;
@@ -663,6 +666,7 @@ qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
 	if (!enabled) {
 		p_operational->enabled = enabled;
 		p_operational->valid = false;
+		DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Dcbx is disabled\n");
 		return;
 	}
 
@@ -676,8 +680,14 @@ qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
 		 DCBX_CONFIG_VERSION_CEE);
 	p_operational->cee = val;
 
-	DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Version support: ieee %d, cee %d\n",
-		   p_operational->ieee, p_operational->cee);
+	val = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) ==
+		 DCBX_CONFIG_VERSION_STATIC);
+	p_operational->local = val;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "Version support: ieee %d, cee %d, static %d\n",
+		   p_operational->ieee, p_operational->cee,
+		   p_operational->local);
 
 	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
 				   p_feat->app.app_pri_tbl, &p_feat->ets,
@@ -692,7 +702,6 @@ qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
 
 static void
 qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt,
 			       struct qed_dcbx_get *params)
 {
 	struct lldp_config_params_s *p_local;
@@ -707,7 +716,6 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
 
 static void
 qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
-				struct qed_ptt *p_ptt,
 				struct qed_dcbx_get *params)
 {
 	struct lldp_status_params_s *p_remote;
@@ -721,25 +729,24 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
 }
 
 static int
-qed_dcbx_get_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
-		    struct qed_dcbx_get *p_params,
+qed_dcbx_get_params(struct qed_hwfn *p_hwfn, struct qed_dcbx_get *p_params,
 		    enum qed_mib_read_type type)
 {
 	switch (type) {
 	case QED_DCBX_REMOTE_MIB:
-		qed_dcbx_get_remote_params(p_hwfn, p_ptt, p_params);
+		qed_dcbx_get_remote_params(p_hwfn, p_params);
 		break;
 	case QED_DCBX_LOCAL_MIB:
-		qed_dcbx_get_local_params(p_hwfn, p_ptt, p_params);
+		qed_dcbx_get_local_params(p_hwfn, p_params);
 		break;
 	case QED_DCBX_OPERATIONAL_MIB:
-		qed_dcbx_get_operational_params(p_hwfn, p_ptt, p_params);
+		qed_dcbx_get_operational_params(p_hwfn, p_params);
 		break;
 	case QED_DCBX_REMOTE_LLDP_MIB:
-		qed_dcbx_get_remote_lldp_params(p_hwfn, p_ptt, p_params);
+		qed_dcbx_get_remote_lldp_params(p_hwfn, p_params);
 		break;
 	case QED_DCBX_LOCAL_LLDP_MIB:
-		qed_dcbx_get_local_lldp_params(p_hwfn, p_ptt, p_params);
+		qed_dcbx_get_local_lldp_params(p_hwfn, p_params);
 		break;
 	default:
 		DP_ERR(p_hwfn, "MIB read err, unknown mib type %d\n", type);
@@ -897,7 +904,8 @@ qed_dcbx_mib_update_event(struct qed_hwfn *p_hwfn,
 			qed_sp_pf_update(p_hwfn);
 		}
 	}
-	qed_dcbx_get_params(p_hwfn, p_ptt, &p_hwfn->p_dcbx_info->get, type);
+
+	qed_dcbx_get_params(p_hwfn, &p_hwfn->p_dcbx_info->get, type);
 	qed_dcbx_aen(p_hwfn, type);
 
 	return rc;
@@ -905,17 +913,14 @@ qed_dcbx_mib_update_event(struct qed_hwfn *p_hwfn,
 
 int qed_dcbx_info_alloc(struct qed_hwfn *p_hwfn)
 {
-	int rc = 0;
-
 	p_hwfn->p_dcbx_info = kzalloc(sizeof(*p_hwfn->p_dcbx_info), GFP_KERNEL);
 	if (!p_hwfn->p_dcbx_info)
-		rc = -ENOMEM;
+		return -ENOMEM;
 
-	return rc;
+	return 0;
 }
 
-void qed_dcbx_info_free(struct qed_hwfn *p_hwfn,
-			struct qed_dcbx_info *p_dcbx_info)
+void qed_dcbx_info_free(struct qed_hwfn *p_hwfn)
 {
 	kfree(p_hwfn->p_dcbx_info);
 }
@@ -954,14 +959,9 @@ void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 	p_dcb_data = &p_dest->fcoe_dcb_data;
 	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_FCOE);
 	p_dcb_data = &p_dest->roce_dcb_data;
-
-	if (p_src->arr[DCBX_PROTOCOL_ROCE].update)
-		qed_dcbx_update_protocol_data(p_dcb_data, p_src,
-					      DCBX_PROTOCOL_ROCE);
-	if (p_src->arr[DCBX_PROTOCOL_ROCE_V2].update)
-		qed_dcbx_update_protocol_data(p_dcb_data, p_src,
-					      DCBX_PROTOCOL_ROCE_V2);
-
+	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ROCE);
+	p_dcb_data = &p_dest->rroce_dcb_data;
+	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ROCE_V2);
 	p_dcb_data = &p_dest->iscsi_dcb_data;
 	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ISCSI);
 	p_dcb_data = &p_dest->eth_dcb_data;
@@ -987,7 +987,7 @@ static int qed_dcbx_query_params(struct qed_hwfn *p_hwfn,
 	if (rc)
 		goto out;
 
-	rc = qed_dcbx_get_params(p_hwfn, p_ptt, p_get, type);
+	rc = qed_dcbx_get_params(p_hwfn, p_get, type);
 
 out:
 	qed_ptt_release(p_hwfn, p_ptt);
@@ -1001,6 +1001,8 @@ qed_dcbx_set_pfc_data(struct qed_hwfn *p_hwfn,
 	u8 pfc_map = 0;
 	int i;
 
+	*pfc &= ~DCBX_PFC_ERROR_MASK;
+
 	if (p_params->pfc.willing)
 		*pfc |= DCBX_PFC_WILLING_MASK;
 	else
@@ -1160,6 +1162,9 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn,
 		local_admin->config = DCBX_CONFIG_VERSION_DISABLED;
 	}
 
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Dcbx version = %d\n",
+		   local_admin->config);
+
 	if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG)
 		qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc,
 				      &params->config.params);
@@ -1236,6 +1241,8 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
 		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_CEE;
 	if (dcbx_info->operational.ieee)
 		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_IEEE;
+	if (dcbx_info->operational.local)
+		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC;
 
 	p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled;
 	memcpy(&p_hwfn->p_dcbx_info->set.config.params,
@@ -1255,7 +1262,7 @@ static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn,
 {
 	struct qed_dcbx_get *dcbx_info;
 
-	dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL);
+	dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_ATOMIC);
 	if (!dcbx_info)
 		return NULL;
 
@@ -1785,8 +1792,9 @@ static u8 qed_dcbnl_setdcbx(struct qed_dev *cdev, u8 mode)
 
 	DP_VERBOSE(hwfn, QED_MSG_DCB, "new mode = %x\n", mode);
 
-	if (!(mode & DCB_CAP_DCBX_VER_IEEE) && !(mode & DCB_CAP_DCBX_VER_CEE)) {
-		DP_INFO(hwfn, "Allowed mode is cee, ieee or both\n");
+	if (!(mode & DCB_CAP_DCBX_VER_IEEE) &&
+	    !(mode & DCB_CAP_DCBX_VER_CEE) && !(mode & DCB_CAP_DCBX_STATIC)) {
+		DP_INFO(hwfn, "Allowed modes are cee, ieee or static\n");
 		return 1;
 	}
 
@@ -1806,6 +1814,11 @@ static u8 qed_dcbnl_setdcbx(struct qed_dev *cdev, u8 mode)
 		dcbx_set.enabled = true;
 	}
 
+	if (mode & DCB_CAP_DCBX_STATIC) {
+		dcbx_set.ver_num |= DCBX_CONFIG_VERSION_STATIC;
+		dcbx_set.enabled = true;
+	}
+
 	ptt = qed_ptt_acquire(hwfn);
 	if (!ptt)
 		return 1;
@@ -1814,7 +1827,7 @@ static u8 qed_dcbnl_setdcbx(struct qed_dev *cdev, u8 mode)
 
 	qed_ptt_release(hwfn, ptt);
 
-	return 0;
+	return rc;
 }
 
 static u8 qed_dcbnl_getfeatcfg(struct qed_dev *cdev, int featid, u8 *flags)
@@ -2073,6 +2086,8 @@ static int qed_dcbnl_ieee_setpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
 	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
 		dcbx_set.config.params.pfc.prio[i] = !!(pfc->pfc_en & BIT(i));
 
+	dcbx_set.config.params.pfc.max_tc = pfc->pfc_cap;
+
 	ptt = qed_ptt_acquire(hwfn);
 	if (!ptt)
 		return -EINVAL;
@@ -2191,15 +2206,46 @@ qed_dcbnl_ieee_peer_getpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
 	return qed_dcbnl_get_ieee_pfc(cdev, pfc, true);
 }
 
+static int qed_get_sf_ieee_value(u8 selector, u8 *sf_ieee)
+{
+	switch (selector) {
+	case IEEE_8021QAZ_APP_SEL_ETHERTYPE:
+		*sf_ieee = QED_DCBX_SF_IEEE_ETHTYPE;
+		break;
+	case IEEE_8021QAZ_APP_SEL_STREAM:
+		*sf_ieee = QED_DCBX_SF_IEEE_TCP_PORT;
+		break;
+	case IEEE_8021QAZ_APP_SEL_DGRAM:
+		*sf_ieee = QED_DCBX_SF_IEEE_UDP_PORT;
+		break;
+	case IEEE_8021QAZ_APP_SEL_ANY:
+		*sf_ieee = QED_DCBX_SF_IEEE_TCP_UDP_PORT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int qed_dcbnl_ieee_getapp(struct qed_dev *cdev, struct dcb_app *app)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_dcbx_get *dcbx_info;
 	struct qed_app_entry *entry;
-	bool ethtype;
 	u8 prio = 0;
+	u8 sf_ieee;
 	int i;
 
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "selector = %d protocol = %d\n",
+		   app->selector, app->protocol);
+
+	if (qed_get_sf_ieee_value(app->selector, &sf_ieee)) {
+		DP_INFO(cdev, "Invalid selector field value %d\n",
+			app->selector);
+		return -EINVAL;
+	}
+
 	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
 	if (!dcbx_info)
 		return -EINVAL;
@@ -2210,11 +2256,9 @@ static int qed_dcbnl_ieee_getapp(struct qed_dev *cdev, struct dcb_app *app)
 		return -EINVAL;
 	}
 
-	/* ieee defines the selector field value for ethertype to be 1 */
-	ethtype = !!((app->selector - 1) == DCB_APP_IDTYPE_ETHTYPE);
 	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
 		entry = &dcbx_info->operational.params.app_entry[i];
-		if ((entry->ethtype == ethtype) &&
+		if ((entry->sf_ieee == sf_ieee) &&
 		    (entry->proto_id == app->protocol)) {
 			prio = entry->prio;
 			break;
@@ -2242,14 +2286,22 @@ static int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app)
 	struct qed_dcbx_set dcbx_set;
 	struct qed_app_entry *entry;
 	struct qed_ptt *ptt;
-	bool ethtype;
+	u8 sf_ieee;
 	int rc, i;
 
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "selector = %d protocol = %d pri = %d\n",
+		   app->selector, app->protocol, app->priority);
 	if (app->priority < 0 || app->priority >= QED_MAX_PFC_PRIORITIES) {
 		DP_INFO(hwfn, "Invalid priority %d\n", app->priority);
 		return -EINVAL;
 	}
 
+	if (qed_get_sf_ieee_value(app->selector, &sf_ieee)) {
+		DP_INFO(cdev, "Invalid selector field value %d\n",
+			app->selector);
+		return -EINVAL;
+	}
+
 	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
 	if (!dcbx_info)
 		return -EINVAL;
@@ -2267,11 +2319,9 @@ static int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app)
 	if (rc)
 		return -EINVAL;
 
-	/* ieee defines the selector field value for ethertype to be 1 */
-	ethtype = !!((app->selector - 1) == DCB_APP_IDTYPE_ETHTYPE);
 	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
 		entry = &dcbx_set.config.params.app_entry[i];
-		if ((entry->ethtype == ethtype) &&
+		if ((entry->sf_ieee == sf_ieee) &&
 		    (entry->proto_id == app->protocol))
 			break;
 		/* First empty slot */
@@ -2287,7 +2337,7 @@ static int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app)
 	}
 
 	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
-	dcbx_set.config.params.app_entry[i].ethtype = ethtype;
+	dcbx_set.config.params.app_entry[i].sf_ieee = sf_ieee;
 	dcbx_set.config.params.app_entry[i].proto_id = app->protocol;
 	dcbx_set.config.params.app_entry[i].prio = BIT(app->priority);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 0fabe97f998d..414e26268f3a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -85,9 +85,6 @@ struct qed_dcbx_app_metadata {
 	enum qed_pci_personality personality;
 };
 
-#define QED_MFW_GET_FIELD(name, field) \
-	(((name) & (field ## _MASK)) >> (field ## _SHIFT))
-
 struct qed_dcbx_info {
 	struct lldp_status_params_s lldp_remote[LLDP_MAX_LLDP_AGENTS];
 	struct lldp_config_params_s lldp_local[LLDP_MAX_LLDP_AGENTS];
@@ -122,7 +119,7 @@ qed_dcbx_mib_update_event(struct qed_hwfn *,
 			  struct qed_ptt *, enum qed_mib_read_type);
 
 int qed_dcbx_info_alloc(struct qed_hwfn *p_hwfn);
-void qed_dcbx_info_free(struct qed_hwfn *, struct qed_dcbx_info *);
+void qed_dcbx_info_free(struct qed_hwfn *p_hwfn);
 void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 				   struct pf_update_ramrod_data *p_dest);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 68f19ca57f96..483241b4b05d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -17,7 +17,6 @@
 
 /* Chip IDs enum */
 enum chip_ids {
-	CHIP_RESERVED,
 	CHIP_BB_B0,
 	CHIP_K2,
 	MAX_CHIP_IDS
@@ -40,6 +39,7 @@ enum mem_groups {
 	MEM_GROUP_BTB_RAM,
 	MEM_GROUP_RDIF_CTX,
 	MEM_GROUP_TDIF_CTX,
+	MEM_GROUP_CFC_MEM,
 	MEM_GROUP_CONN_CFC_MEM,
 	MEM_GROUP_TASK_CFC_MEM,
 	MEM_GROUP_CAU_PI,
@@ -72,6 +72,7 @@ static const char * const s_mem_group_names[] = {
 	"BTB_RAM",
 	"RDIF_CTX",
 	"TDIF_CTX",
+	"CFC_MEM",
 	"CONN_CFC_MEM",
 	"TASK_CFC_MEM",
 	"CAU_PI",
@@ -185,13 +186,16 @@ struct dbg_array {
 	u32 size_in_dwords;
 };
 
+struct chip_platform_defs {
+	u8 num_ports;
+	u8 num_pfs;
+	u8 num_vfs;
+};
+
 /* Chip constant definitions */
 struct chip_defs {
 	const char *name;
-	struct {
-		u8 num_ports;
-		u8 num_pfs;
-	} per_platform[MAX_PLATFORM_IDS];
+	struct chip_platform_defs per_platform[MAX_PLATFORM_IDS];
 };
 
 /* Platform constant definitions */
@@ -405,22 +409,23 @@ struct phy_defs {
 /***************************** Constant Arrays *******************************/
 
 /* Debug arrays */
-static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} };
+static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} };
 
 /* Chip constant definitions array */
 static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = {
-	{ "reserved", { {0, 0}, {0, 0}, {0, 0}, {0, 0} } },
 	{ "bb_b0",
-	  { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB}, {0, 0}, {0, 0}, {0, 0} } },
-	{ "k2", { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2}, {0, 0}, {0, 0}, {0, 0} } }
+	  { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB, MAX_NUM_VFS_BB}, {0, 0, 0},
+	    {0, 0, 0}, {0, 0, 0} } },
+	{ "k2",
+	  { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2, MAX_NUM_VFS_K2}, {0, 0, 0},
+	    {0, 0, 0}, {0, 0, 0} } }
 };
 
 /* Storm constant definitions array */
 static struct storm_defs s_storm_defs[] = {
 	/* Tstorm */
 	{'T', BLOCK_TSEM,
-	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT,
-	  DBG_BUS_CLIENT_RBCT}, true,
+	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, true,
 	 TSEM_REG_FAST_MEMORY,
 	 TSEM_REG_DBG_FRAME_MODE, TSEM_REG_SLOW_DBG_ACTIVE,
 	 TSEM_REG_SLOW_DBG_MODE, TSEM_REG_DBG_MODE1_CFG,
@@ -432,8 +437,7 @@ static struct storm_defs s_storm_defs[] = {
 	 4, TCM_REG_SM_TASK_CTX},
 	/* Mstorm */
 	{'M', BLOCK_MSEM,
-	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT,
-	  DBG_BUS_CLIENT_RBCM}, false,
+	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, false,
 	 MSEM_REG_FAST_MEMORY,
 	 MSEM_REG_DBG_FRAME_MODE, MSEM_REG_SLOW_DBG_ACTIVE,
 	 MSEM_REG_SLOW_DBG_MODE, MSEM_REG_DBG_MODE1_CFG,
@@ -445,8 +449,7 @@ static struct storm_defs s_storm_defs[] = {
 	 7, MCM_REG_SM_TASK_CTX},
 	/* Ustorm */
 	{'U', BLOCK_USEM,
-	 {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU,
-	  DBG_BUS_CLIENT_RBCU}, false,
+	 {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, false,
 	 USEM_REG_FAST_MEMORY,
 	 USEM_REG_DBG_FRAME_MODE, USEM_REG_SLOW_DBG_ACTIVE,
 	 USEM_REG_SLOW_DBG_MODE, USEM_REG_DBG_MODE1_CFG,
@@ -458,8 +461,7 @@ static struct storm_defs s_storm_defs[] = {
 	 3, UCM_REG_SM_TASK_CTX},
 	/* Xstorm */
 	{'X', BLOCK_XSEM,
-	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX,
-	  DBG_BUS_CLIENT_RBCX}, false,
+	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, false,
 	 XSEM_REG_FAST_MEMORY,
 	 XSEM_REG_DBG_FRAME_MODE, XSEM_REG_SLOW_DBG_ACTIVE,
 	 XSEM_REG_SLOW_DBG_MODE, XSEM_REG_DBG_MODE1_CFG,
@@ -471,8 +473,7 @@ static struct storm_defs s_storm_defs[] = {
 	 0, 0},
 	/* Ystorm */
 	{'Y', BLOCK_YSEM,
-	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX,
-	  DBG_BUS_CLIENT_RBCY}, false,
+	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, false,
 	 YSEM_REG_FAST_MEMORY,
 	 YSEM_REG_DBG_FRAME_MODE, YSEM_REG_SLOW_DBG_ACTIVE,
 	 YSEM_REG_SLOW_DBG_MODE, YSEM_REG_DBG_MODE1_CFG,
@@ -484,8 +485,7 @@ static struct storm_defs s_storm_defs[] = {
 	 12, YCM_REG_SM_TASK_CTX},
 	/* Pstorm */
 	{'P', BLOCK_PSEM,
-	 {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS,
-	  DBG_BUS_CLIENT_RBCS}, true,
+	 {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, true,
 	 PSEM_REG_FAST_MEMORY,
 	 PSEM_REG_DBG_FRAME_MODE, PSEM_REG_SLOW_DBG_ACTIVE,
 	 PSEM_REG_SLOW_DBG_MODE, PSEM_REG_DBG_MODE1_CFG,
@@ -499,8 +499,9 @@ static struct storm_defs s_storm_defs[] = {
 
 /* Block definitions array */
 static struct block_defs block_grc_defs = {
-	"grc", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
+	"grc",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
 	GRC_REG_DBG_SELECT, GRC_REG_DBG_DWORD_ENABLE,
 	GRC_REG_DBG_SHIFT, GRC_REG_DBG_FORCE_VALID,
 	GRC_REG_DBG_FORCE_FRAME,
@@ -508,29 +509,30 @@ static struct block_defs block_grc_defs = {
 };
 
 static struct block_defs block_miscs_defs = {
-	"miscs", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"miscs", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_misc_defs = {
-	"misc", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"misc", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_dbu_defs = {
-	"dbu", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"dbu", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_pglue_b_defs = {
-	"pglue_b", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH},
+	"pglue_b",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH},
 	PGLUE_B_REG_DBG_SELECT, PGLUE_B_REG_DBG_DWORD_ENABLE,
 	PGLUE_B_REG_DBG_SHIFT, PGLUE_B_REG_DBG_FORCE_VALID,
 	PGLUE_B_REG_DBG_FORCE_FRAME,
@@ -538,8 +540,9 @@ static struct block_defs block_pglue_b_defs = {
 };
 
 static struct block_defs block_cnig_defs = {
-	"cnig", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+	"cnig",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
 	CNIG_REG_DBG_SELECT_K2, CNIG_REG_DBG_DWORD_ENABLE_K2,
 	CNIG_REG_DBG_SHIFT_K2, CNIG_REG_DBG_FORCE_VALID_K2,
 	CNIG_REG_DBG_FORCE_FRAME_K2,
@@ -547,15 +550,16 @@ static struct block_defs block_cnig_defs = {
 };
 
 static struct block_defs block_cpmu_defs = {
-	"cpmu", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"cpmu", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 8
 };
 
 static struct block_defs block_ncsi_defs = {
-	"ncsi", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
+	"ncsi",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
 	NCSI_REG_DBG_SELECT, NCSI_REG_DBG_DWORD_ENABLE,
 	NCSI_REG_DBG_SHIFT, NCSI_REG_DBG_FORCE_VALID,
 	NCSI_REG_DBG_FORCE_FRAME,
@@ -563,15 +567,16 @@ static struct block_defs block_ncsi_defs = {
 };
 
 static struct block_defs block_opte_defs = {
-	"opte", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"opte", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 4
 };
 
 static struct block_defs block_bmb_defs = {
-	"bmb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB},
+	"bmb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB},
 	BMB_REG_DBG_SELECT, BMB_REG_DBG_DWORD_ENABLE,
 	BMB_REG_DBG_SHIFT, BMB_REG_DBG_FORCE_VALID,
 	BMB_REG_DBG_FORCE_FRAME,
@@ -579,8 +584,9 @@ static struct block_defs block_bmb_defs = {
 };
 
 static struct block_defs block_pcie_defs = {
-	"pcie", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+	"pcie",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
 	PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE,
 	PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID,
 	PCIE_REG_DBG_COMMON_FORCE_FRAME,
@@ -588,15 +594,16 @@ static struct block_defs block_pcie_defs = {
 };
 
 static struct block_defs block_mcp_defs = {
-	"mcp", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"mcp", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_mcp2_defs = {
-	"mcp2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
+	"mcp2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
 	MCP2_REG_DBG_SELECT, MCP2_REG_DBG_DWORD_ENABLE,
 	MCP2_REG_DBG_SHIFT, MCP2_REG_DBG_FORCE_VALID,
 	MCP2_REG_DBG_FORCE_FRAME,
@@ -604,8 +611,9 @@ static struct block_defs block_mcp2_defs = {
 };
 
 static struct block_defs block_pswhst_defs = {
-	"pswhst", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswhst",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWHST_REG_DBG_SELECT, PSWHST_REG_DBG_DWORD_ENABLE,
 	PSWHST_REG_DBG_SHIFT, PSWHST_REG_DBG_FORCE_VALID,
 	PSWHST_REG_DBG_FORCE_FRAME,
@@ -613,8 +621,9 @@ static struct block_defs block_pswhst_defs = {
 };
 
 static struct block_defs block_pswhst2_defs = {
-	"pswhst2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswhst2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWHST2_REG_DBG_SELECT, PSWHST2_REG_DBG_DWORD_ENABLE,
 	PSWHST2_REG_DBG_SHIFT, PSWHST2_REG_DBG_FORCE_VALID,
 	PSWHST2_REG_DBG_FORCE_FRAME,
@@ -622,8 +631,9 @@ static struct block_defs block_pswhst2_defs = {
 };
 
 static struct block_defs block_pswrd_defs = {
-	"pswrd", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrd",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRD_REG_DBG_SELECT, PSWRD_REG_DBG_DWORD_ENABLE,
 	PSWRD_REG_DBG_SHIFT, PSWRD_REG_DBG_FORCE_VALID,
 	PSWRD_REG_DBG_FORCE_FRAME,
@@ -631,8 +641,9 @@ static struct block_defs block_pswrd_defs = {
 };
 
 static struct block_defs block_pswrd2_defs = {
-	"pswrd2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrd2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRD2_REG_DBG_SELECT, PSWRD2_REG_DBG_DWORD_ENABLE,
 	PSWRD2_REG_DBG_SHIFT, PSWRD2_REG_DBG_FORCE_VALID,
 	PSWRD2_REG_DBG_FORCE_FRAME,
@@ -640,8 +651,9 @@ static struct block_defs block_pswrd2_defs = {
 };
 
 static struct block_defs block_pswwr_defs = {
-	"pswwr", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswwr",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWWR_REG_DBG_SELECT, PSWWR_REG_DBG_DWORD_ENABLE,
 	PSWWR_REG_DBG_SHIFT, PSWWR_REG_DBG_FORCE_VALID,
 	PSWWR_REG_DBG_FORCE_FRAME,
@@ -649,15 +661,16 @@ static struct block_defs block_pswwr_defs = {
 };
 
 static struct block_defs block_pswwr2_defs = {
-	"pswwr2", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"pswwr2", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISC_PL_HV, 3
 };
 
 static struct block_defs block_pswrq_defs = {
-	"pswrq", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrq",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRQ_REG_DBG_SELECT, PSWRQ_REG_DBG_DWORD_ENABLE,
 	PSWRQ_REG_DBG_SHIFT, PSWRQ_REG_DBG_FORCE_VALID,
 	PSWRQ_REG_DBG_FORCE_FRAME,
@@ -665,8 +678,9 @@ static struct block_defs block_pswrq_defs = {
 };
 
 static struct block_defs block_pswrq2_defs = {
-	"pswrq2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrq2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRQ2_REG_DBG_SELECT, PSWRQ2_REG_DBG_DWORD_ENABLE,
 	PSWRQ2_REG_DBG_SHIFT, PSWRQ2_REG_DBG_FORCE_VALID,
 	PSWRQ2_REG_DBG_FORCE_FRAME,
@@ -674,8 +688,9 @@ static struct block_defs block_pswrq2_defs = {
 };
 
 static struct block_defs block_pglcs_defs = {
-	"pglcs", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+	"pglcs",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
 	PGLCS_REG_DBG_SELECT, PGLCS_REG_DBG_DWORD_ENABLE,
 	PGLCS_REG_DBG_SHIFT, PGLCS_REG_DBG_FORCE_VALID,
 	PGLCS_REG_DBG_FORCE_FRAME,
@@ -683,8 +698,9 @@ static struct block_defs block_pglcs_defs = {
 };
 
 static struct block_defs block_ptu_defs = {
-	"ptu", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"ptu",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PTU_REG_DBG_SELECT, PTU_REG_DBG_DWORD_ENABLE,
 	PTU_REG_DBG_SHIFT, PTU_REG_DBG_FORCE_VALID,
 	PTU_REG_DBG_FORCE_FRAME,
@@ -692,8 +708,9 @@ static struct block_defs block_ptu_defs = {
 };
 
 static struct block_defs block_dmae_defs = {
-	"dmae", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"dmae",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	DMAE_REG_DBG_SELECT, DMAE_REG_DBG_DWORD_ENABLE,
 	DMAE_REG_DBG_SHIFT, DMAE_REG_DBG_FORCE_VALID,
 	DMAE_REG_DBG_FORCE_FRAME,
@@ -701,8 +718,9 @@ static struct block_defs block_dmae_defs = {
 };
 
 static struct block_defs block_tcm_defs = {
-	"tcm", {true, true, true}, true, DBG_TSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"tcm",
+	{true, true}, true, DBG_TSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	TCM_REG_DBG_SELECT, TCM_REG_DBG_DWORD_ENABLE,
 	TCM_REG_DBG_SHIFT, TCM_REG_DBG_FORCE_VALID,
 	TCM_REG_DBG_FORCE_FRAME,
@@ -710,8 +728,9 @@ static struct block_defs block_tcm_defs = {
 };
 
 static struct block_defs block_mcm_defs = {
-	"mcm", {true, true, true}, true, DBG_MSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"mcm",
+	{true, true}, true, DBG_MSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	MCM_REG_DBG_SELECT, MCM_REG_DBG_DWORD_ENABLE,
 	MCM_REG_DBG_SHIFT, MCM_REG_DBG_FORCE_VALID,
 	MCM_REG_DBG_FORCE_FRAME,
@@ -719,8 +738,9 @@ static struct block_defs block_mcm_defs = {
 };
 
 static struct block_defs block_ucm_defs = {
-	"ucm", {true, true, true}, true, DBG_USTORM_ID,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"ucm",
+	{true, true}, true, DBG_USTORM_ID,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	UCM_REG_DBG_SELECT, UCM_REG_DBG_DWORD_ENABLE,
 	UCM_REG_DBG_SHIFT, UCM_REG_DBG_FORCE_VALID,
 	UCM_REG_DBG_FORCE_FRAME,
@@ -728,8 +748,9 @@ static struct block_defs block_ucm_defs = {
 };
 
 static struct block_defs block_xcm_defs = {
-	"xcm", {true, true, true}, true, DBG_XSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xcm",
+	{true, true}, true, DBG_XSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XCM_REG_DBG_SELECT, XCM_REG_DBG_DWORD_ENABLE,
 	XCM_REG_DBG_SHIFT, XCM_REG_DBG_FORCE_VALID,
 	XCM_REG_DBG_FORCE_FRAME,
@@ -737,8 +758,9 @@ static struct block_defs block_xcm_defs = {
 };
 
 static struct block_defs block_ycm_defs = {
-	"ycm", {true, true, true}, true, DBG_YSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"ycm",
+	{true, true}, true, DBG_YSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	YCM_REG_DBG_SELECT, YCM_REG_DBG_DWORD_ENABLE,
 	YCM_REG_DBG_SHIFT, YCM_REG_DBG_FORCE_VALID,
 	YCM_REG_DBG_FORCE_FRAME,
@@ -746,8 +768,9 @@ static struct block_defs block_ycm_defs = {
 };
 
 static struct block_defs block_pcm_defs = {
-	"pcm", {true, true, true}, true, DBG_PSTORM_ID,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"pcm",
+	{true, true}, true, DBG_PSTORM_ID,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	PCM_REG_DBG_SELECT, PCM_REG_DBG_DWORD_ENABLE,
 	PCM_REG_DBG_SHIFT, PCM_REG_DBG_FORCE_VALID,
 	PCM_REG_DBG_FORCE_FRAME,
@@ -755,8 +778,9 @@ static struct block_defs block_pcm_defs = {
 };
 
 static struct block_defs block_qm_defs = {
-	"qm", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ},
+	"qm",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ},
 	QM_REG_DBG_SELECT, QM_REG_DBG_DWORD_ENABLE,
 	QM_REG_DBG_SHIFT, QM_REG_DBG_FORCE_VALID,
 	QM_REG_DBG_FORCE_FRAME,
@@ -764,8 +788,9 @@ static struct block_defs block_qm_defs = {
 };
 
 static struct block_defs block_tm_defs = {
-	"tm", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"tm",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	TM_REG_DBG_SELECT, TM_REG_DBG_DWORD_ENABLE,
 	TM_REG_DBG_SHIFT, TM_REG_DBG_FORCE_VALID,
 	TM_REG_DBG_FORCE_FRAME,
@@ -773,8 +798,9 @@ static struct block_defs block_tm_defs = {
 };
 
 static struct block_defs block_dorq_defs = {
-	"dorq", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"dorq",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	DORQ_REG_DBG_SELECT, DORQ_REG_DBG_DWORD_ENABLE,
 	DORQ_REG_DBG_SHIFT, DORQ_REG_DBG_FORCE_VALID,
 	DORQ_REG_DBG_FORCE_FRAME,
@@ -782,8 +808,9 @@ static struct block_defs block_dorq_defs = {
 };
 
 static struct block_defs block_brb_defs = {
-	"brb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
+	"brb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
 	BRB_REG_DBG_SELECT, BRB_REG_DBG_DWORD_ENABLE,
 	BRB_REG_DBG_SHIFT, BRB_REG_DBG_FORCE_VALID,
 	BRB_REG_DBG_FORCE_FRAME,
@@ -791,8 +818,9 @@ static struct block_defs block_brb_defs = {
 };
 
 static struct block_defs block_src_defs = {
-	"src", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"src",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	SRC_REG_DBG_SELECT, SRC_REG_DBG_DWORD_ENABLE,
 	SRC_REG_DBG_SHIFT, SRC_REG_DBG_FORCE_VALID,
 	SRC_REG_DBG_FORCE_FRAME,
@@ -800,8 +828,9 @@ static struct block_defs block_src_defs = {
 };
 
 static struct block_defs block_prs_defs = {
-	"prs", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
+	"prs",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
 	PRS_REG_DBG_SELECT, PRS_REG_DBG_DWORD_ENABLE,
 	PRS_REG_DBG_SHIFT, PRS_REG_DBG_FORCE_VALID,
 	PRS_REG_DBG_FORCE_FRAME,
@@ -809,8 +838,9 @@ static struct block_defs block_prs_defs = {
 };
 
 static struct block_defs block_tsdm_defs = {
-	"tsdm", {true, true, true}, true, DBG_TSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"tsdm",
+	{true, true}, true, DBG_TSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	TSDM_REG_DBG_SELECT, TSDM_REG_DBG_DWORD_ENABLE,
 	TSDM_REG_DBG_SHIFT, TSDM_REG_DBG_FORCE_VALID,
 	TSDM_REG_DBG_FORCE_FRAME,
@@ -818,8 +848,9 @@ static struct block_defs block_tsdm_defs = {
 };
 
 static struct block_defs block_msdm_defs = {
-	"msdm", {true, true, true}, true, DBG_MSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"msdm",
+	{true, true}, true, DBG_MSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	MSDM_REG_DBG_SELECT, MSDM_REG_DBG_DWORD_ENABLE,
 	MSDM_REG_DBG_SHIFT, MSDM_REG_DBG_FORCE_VALID,
 	MSDM_REG_DBG_FORCE_FRAME,
@@ -827,8 +858,9 @@ static struct block_defs block_msdm_defs = {
 };
 
 static struct block_defs block_usdm_defs = {
-	"usdm", {true, true, true}, true, DBG_USTORM_ID,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"usdm",
+	{true, true}, true, DBG_USTORM_ID,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	USDM_REG_DBG_SELECT, USDM_REG_DBG_DWORD_ENABLE,
 	USDM_REG_DBG_SHIFT, USDM_REG_DBG_FORCE_VALID,
 	USDM_REG_DBG_FORCE_FRAME,
@@ -836,8 +868,9 @@ static struct block_defs block_usdm_defs = {
 };
 
 static struct block_defs block_xsdm_defs = {
-	"xsdm", {true, true, true}, true, DBG_XSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xsdm",
+	{true, true}, true, DBG_XSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XSDM_REG_DBG_SELECT, XSDM_REG_DBG_DWORD_ENABLE,
 	XSDM_REG_DBG_SHIFT, XSDM_REG_DBG_FORCE_VALID,
 	XSDM_REG_DBG_FORCE_FRAME,
@@ -845,8 +878,9 @@ static struct block_defs block_xsdm_defs = {
 };
 
 static struct block_defs block_ysdm_defs = {
-	"ysdm", {true, true, true}, true, DBG_YSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"ysdm",
+	{true, true}, true, DBG_YSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	YSDM_REG_DBG_SELECT, YSDM_REG_DBG_DWORD_ENABLE,
 	YSDM_REG_DBG_SHIFT, YSDM_REG_DBG_FORCE_VALID,
 	YSDM_REG_DBG_FORCE_FRAME,
@@ -854,8 +888,9 @@ static struct block_defs block_ysdm_defs = {
 };
 
 static struct block_defs block_psdm_defs = {
-	"psdm", {true, true, true}, true, DBG_PSTORM_ID,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"psdm",
+	{true, true}, true, DBG_PSTORM_ID,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	PSDM_REG_DBG_SELECT, PSDM_REG_DBG_DWORD_ENABLE,
 	PSDM_REG_DBG_SHIFT, PSDM_REG_DBG_FORCE_VALID,
 	PSDM_REG_DBG_FORCE_FRAME,
@@ -863,8 +898,9 @@ static struct block_defs block_psdm_defs = {
 };
 
 static struct block_defs block_tsem_defs = {
-	"tsem", {true, true, true}, true, DBG_TSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"tsem",
+	{true, true}, true, DBG_TSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	TSEM_REG_DBG_SELECT, TSEM_REG_DBG_DWORD_ENABLE,
 	TSEM_REG_DBG_SHIFT, TSEM_REG_DBG_FORCE_VALID,
 	TSEM_REG_DBG_FORCE_FRAME,
@@ -872,8 +908,9 @@ static struct block_defs block_tsem_defs = {
 };
 
 static struct block_defs block_msem_defs = {
-	"msem", {true, true, true}, true, DBG_MSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"msem",
+	{true, true}, true, DBG_MSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	MSEM_REG_DBG_SELECT, MSEM_REG_DBG_DWORD_ENABLE,
 	MSEM_REG_DBG_SHIFT, MSEM_REG_DBG_FORCE_VALID,
 	MSEM_REG_DBG_FORCE_FRAME,
@@ -881,8 +918,9 @@ static struct block_defs block_msem_defs = {
 };
 
 static struct block_defs block_usem_defs = {
-	"usem", {true, true, true}, true, DBG_USTORM_ID,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"usem",
+	{true, true}, true, DBG_USTORM_ID,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	USEM_REG_DBG_SELECT, USEM_REG_DBG_DWORD_ENABLE,
 	USEM_REG_DBG_SHIFT, USEM_REG_DBG_FORCE_VALID,
 	USEM_REG_DBG_FORCE_FRAME,
@@ -890,8 +928,9 @@ static struct block_defs block_usem_defs = {
 };
 
 static struct block_defs block_xsem_defs = {
-	"xsem", {true, true, true}, true, DBG_XSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xsem",
+	{true, true}, true, DBG_XSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XSEM_REG_DBG_SELECT, XSEM_REG_DBG_DWORD_ENABLE,
 	XSEM_REG_DBG_SHIFT, XSEM_REG_DBG_FORCE_VALID,
 	XSEM_REG_DBG_FORCE_FRAME,
@@ -899,8 +938,9 @@ static struct block_defs block_xsem_defs = {
 };
 
 static struct block_defs block_ysem_defs = {
-	"ysem", {true, true, true}, true, DBG_YSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"ysem",
+	{true, true}, true, DBG_YSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	YSEM_REG_DBG_SELECT, YSEM_REG_DBG_DWORD_ENABLE,
 	YSEM_REG_DBG_SHIFT, YSEM_REG_DBG_FORCE_VALID,
 	YSEM_REG_DBG_FORCE_FRAME,
@@ -908,8 +948,9 @@ static struct block_defs block_ysem_defs = {
 };
 
 static struct block_defs block_psem_defs = {
-	"psem", {true, true, true}, true, DBG_PSTORM_ID,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"psem",
+	{true, true}, true, DBG_PSTORM_ID,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	PSEM_REG_DBG_SELECT, PSEM_REG_DBG_DWORD_ENABLE,
 	PSEM_REG_DBG_SHIFT, PSEM_REG_DBG_FORCE_VALID,
 	PSEM_REG_DBG_FORCE_FRAME,
@@ -917,8 +958,9 @@ static struct block_defs block_psem_defs = {
 };
 
 static struct block_defs block_rss_defs = {
-	"rss", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"rss",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	RSS_REG_DBG_SELECT, RSS_REG_DBG_DWORD_ENABLE,
 	RSS_REG_DBG_SHIFT, RSS_REG_DBG_FORCE_VALID,
 	RSS_REG_DBG_FORCE_FRAME,
@@ -926,8 +968,9 @@ static struct block_defs block_rss_defs = {
 };
 
 static struct block_defs block_tmld_defs = {
-	"tmld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"tmld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	TMLD_REG_DBG_SELECT, TMLD_REG_DBG_DWORD_ENABLE,
 	TMLD_REG_DBG_SHIFT, TMLD_REG_DBG_FORCE_VALID,
 	TMLD_REG_DBG_FORCE_FRAME,
@@ -935,8 +978,9 @@ static struct block_defs block_tmld_defs = {
 };
 
 static struct block_defs block_muld_defs = {
-	"muld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"muld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	MULD_REG_DBG_SELECT, MULD_REG_DBG_DWORD_ENABLE,
 	MULD_REG_DBG_SHIFT, MULD_REG_DBG_FORCE_VALID,
 	MULD_REG_DBG_FORCE_FRAME,
@@ -944,8 +988,9 @@ static struct block_defs block_muld_defs = {
 };
 
 static struct block_defs block_yuld_defs = {
-	"yuld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"yuld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	YULD_REG_DBG_SELECT, YULD_REG_DBG_DWORD_ENABLE,
 	YULD_REG_DBG_SHIFT, YULD_REG_DBG_FORCE_VALID,
 	YULD_REG_DBG_FORCE_FRAME,
@@ -953,8 +998,9 @@ static struct block_defs block_yuld_defs = {
 };
 
 static struct block_defs block_xyld_defs = {
-	"xyld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xyld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XYLD_REG_DBG_SELECT, XYLD_REG_DBG_DWORD_ENABLE,
 	XYLD_REG_DBG_SHIFT, XYLD_REG_DBG_FORCE_VALID,
 	XYLD_REG_DBG_FORCE_FRAME,
@@ -962,8 +1008,9 @@ static struct block_defs block_xyld_defs = {
 };
 
 static struct block_defs block_prm_defs = {
-	"prm", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"prm",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	PRM_REG_DBG_SELECT, PRM_REG_DBG_DWORD_ENABLE,
 	PRM_REG_DBG_SHIFT, PRM_REG_DBG_FORCE_VALID,
 	PRM_REG_DBG_FORCE_FRAME,
@@ -971,8 +1018,9 @@ static struct block_defs block_prm_defs = {
 };
 
 static struct block_defs block_pbf_pb1_defs = {
-	"pbf_pb1", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+	"pbf_pb1",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
 	PBF_PB1_REG_DBG_SELECT, PBF_PB1_REG_DBG_DWORD_ENABLE,
 	PBF_PB1_REG_DBG_SHIFT, PBF_PB1_REG_DBG_FORCE_VALID,
 	PBF_PB1_REG_DBG_FORCE_FRAME,
@@ -981,8 +1029,9 @@ static struct block_defs block_pbf_pb1_defs = {
 };
 
 static struct block_defs block_pbf_pb2_defs = {
-	"pbf_pb2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+	"pbf_pb2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
 	PBF_PB2_REG_DBG_SELECT, PBF_PB2_REG_DBG_DWORD_ENABLE,
 	PBF_PB2_REG_DBG_SHIFT, PBF_PB2_REG_DBG_FORCE_VALID,
 	PBF_PB2_REG_DBG_FORCE_FRAME,
@@ -991,8 +1040,9 @@ static struct block_defs block_pbf_pb2_defs = {
 };
 
 static struct block_defs block_rpb_defs = {
-	"rpb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"rpb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	RPB_REG_DBG_SELECT, RPB_REG_DBG_DWORD_ENABLE,
 	RPB_REG_DBG_SHIFT, RPB_REG_DBG_FORCE_VALID,
 	RPB_REG_DBG_FORCE_FRAME,
@@ -1000,8 +1050,9 @@ static struct block_defs block_rpb_defs = {
 };
 
 static struct block_defs block_btb_defs = {
-	"btb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV},
+	"btb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV},
 	BTB_REG_DBG_SELECT, BTB_REG_DBG_DWORD_ENABLE,
 	BTB_REG_DBG_SHIFT, BTB_REG_DBG_FORCE_VALID,
 	BTB_REG_DBG_FORCE_FRAME,
@@ -1009,8 +1060,9 @@ static struct block_defs block_btb_defs = {
 };
 
 static struct block_defs block_pbf_defs = {
-	"pbf", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+	"pbf",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
 	PBF_REG_DBG_SELECT, PBF_REG_DBG_DWORD_ENABLE,
 	PBF_REG_DBG_SHIFT, PBF_REG_DBG_FORCE_VALID,
 	PBF_REG_DBG_FORCE_FRAME,
@@ -1018,8 +1070,9 @@ static struct block_defs block_pbf_defs = {
 };
 
 static struct block_defs block_rdif_defs = {
-	"rdif", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"rdif",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	RDIF_REG_DBG_SELECT, RDIF_REG_DBG_DWORD_ENABLE,
 	RDIF_REG_DBG_SHIFT, RDIF_REG_DBG_FORCE_VALID,
 	RDIF_REG_DBG_FORCE_FRAME,
@@ -1027,8 +1080,9 @@ static struct block_defs block_rdif_defs = {
 };
 
 static struct block_defs block_tdif_defs = {
-	"tdif", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"tdif",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	TDIF_REG_DBG_SELECT, TDIF_REG_DBG_DWORD_ENABLE,
 	TDIF_REG_DBG_SHIFT, TDIF_REG_DBG_FORCE_VALID,
 	TDIF_REG_DBG_FORCE_FRAME,
@@ -1036,8 +1090,9 @@ static struct block_defs block_tdif_defs = {
 };
 
 static struct block_defs block_cdu_defs = {
-	"cdu", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"cdu",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	CDU_REG_DBG_SELECT, CDU_REG_DBG_DWORD_ENABLE,
 	CDU_REG_DBG_SHIFT, CDU_REG_DBG_FORCE_VALID,
 	CDU_REG_DBG_FORCE_FRAME,
@@ -1045,8 +1100,9 @@ static struct block_defs block_cdu_defs = {
 };
 
 static struct block_defs block_ccfc_defs = {
-	"ccfc", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"ccfc",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	CCFC_REG_DBG_SELECT, CCFC_REG_DBG_DWORD_ENABLE,
 	CCFC_REG_DBG_SHIFT, CCFC_REG_DBG_FORCE_VALID,
 	CCFC_REG_DBG_FORCE_FRAME,
@@ -1054,8 +1110,9 @@ static struct block_defs block_ccfc_defs = {
 };
 
 static struct block_defs block_tcfc_defs = {
-	"tcfc", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"tcfc",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	TCFC_REG_DBG_SELECT, TCFC_REG_DBG_DWORD_ENABLE,
 	TCFC_REG_DBG_SHIFT, TCFC_REG_DBG_FORCE_VALID,
 	TCFC_REG_DBG_FORCE_FRAME,
@@ -1063,8 +1120,9 @@ static struct block_defs block_tcfc_defs = {
 };
 
 static struct block_defs block_igu_defs = {
-	"igu", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"igu",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	IGU_REG_DBG_SELECT, IGU_REG_DBG_DWORD_ENABLE,
 	IGU_REG_DBG_SHIFT, IGU_REG_DBG_FORCE_VALID,
 	IGU_REG_DBG_FORCE_FRAME,
@@ -1072,8 +1130,9 @@ static struct block_defs block_igu_defs = {
 };
 
 static struct block_defs block_cau_defs = {
-	"cau", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"cau",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	CAU_REG_DBG_SELECT, CAU_REG_DBG_DWORD_ENABLE,
 	CAU_REG_DBG_SHIFT, CAU_REG_DBG_FORCE_VALID,
 	CAU_REG_DBG_FORCE_FRAME,
@@ -1081,8 +1140,9 @@ static struct block_defs block_cau_defs = {
 };
 
 static struct block_defs block_umac_defs = {
-	"umac", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+	"umac",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
 	UMAC_REG_DBG_SELECT, UMAC_REG_DBG_DWORD_ENABLE,
 	UMAC_REG_DBG_SHIFT, UMAC_REG_DBG_FORCE_VALID,
 	UMAC_REG_DBG_FORCE_FRAME,
@@ -1090,22 +1150,23 @@ static struct block_defs block_umac_defs = {
 };
 
 static struct block_defs block_xmac_defs = {
-	"xmac", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"xmac", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_dbg_defs = {
-	"dbg", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"dbg", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 3
 };
 
 static struct block_defs block_nig_defs = {
-	"nig", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
+	"nig",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
 	NIG_REG_DBG_SELECT, NIG_REG_DBG_DWORD_ENABLE,
 	NIG_REG_DBG_SHIFT, NIG_REG_DBG_FORCE_VALID,
 	NIG_REG_DBG_FORCE_FRAME,
@@ -1113,8 +1174,9 @@ static struct block_defs block_nig_defs = {
 };
 
 static struct block_defs block_wol_defs = {
-	"wol", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+	"wol",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
 	WOL_REG_DBG_SELECT, WOL_REG_DBG_DWORD_ENABLE,
 	WOL_REG_DBG_SHIFT, WOL_REG_DBG_FORCE_VALID,
 	WOL_REG_DBG_FORCE_FRAME,
@@ -1122,8 +1184,9 @@ static struct block_defs block_wol_defs = {
 };
 
 static struct block_defs block_bmbn_defs = {
-	"bmbn", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB},
+	"bmbn",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB},
 	BMBN_REG_DBG_SELECT, BMBN_REG_DBG_DWORD_ENABLE,
 	BMBN_REG_DBG_SHIFT, BMBN_REG_DBG_FORCE_VALID,
 	BMBN_REG_DBG_FORCE_FRAME,
@@ -1131,15 +1194,16 @@ static struct block_defs block_bmbn_defs = {
 };
 
 static struct block_defs block_ipc_defs = {
-	"ipc", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"ipc", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISCS_PL_UA, 8
 };
 
 static struct block_defs block_nwm_defs = {
-	"nwm", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+	"nwm",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
 	NWM_REG_DBG_SELECT, NWM_REG_DBG_DWORD_ENABLE,
 	NWM_REG_DBG_SHIFT, NWM_REG_DBG_FORCE_VALID,
 	NWM_REG_DBG_FORCE_FRAME,
@@ -1147,22 +1211,29 @@ static struct block_defs block_nwm_defs = {
 };
 
 static struct block_defs block_nws_defs = {
-	"nws", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
-	0, 0, 0, 0, 0,
+	"nws",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+	NWS_REG_DBG_SELECT, NWS_REG_DBG_DWORD_ENABLE,
+	NWS_REG_DBG_SHIFT, NWS_REG_DBG_FORCE_VALID,
+	NWS_REG_DBG_FORCE_FRAME,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 12
 };
 
 static struct block_defs block_ms_defs = {
-	"ms", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
-	0, 0, 0, 0, 0,
+	"ms",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+	MS_REG_DBG_SELECT, MS_REG_DBG_DWORD_ENABLE,
+	MS_REG_DBG_SHIFT, MS_REG_DBG_FORCE_VALID,
+	MS_REG_DBG_FORCE_FRAME,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 13
 };
 
 static struct block_defs block_phy_pcie_defs = {
-	"phy_pcie", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+	"phy_pcie",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
 	PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE,
 	PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID,
 	PCIE_REG_DBG_COMMON_FORCE_FRAME,
@@ -1170,22 +1241,57 @@ static struct block_defs block_phy_pcie_defs = {
 };
 
 static struct block_defs block_led_defs = {
-	"led", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"led", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	true, false, DBG_RESET_REG_MISCS_PL_HV, 14
+};
+
+static struct block_defs block_avs_wrap_defs = {
+	"avs_wrap", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	true, false, DBG_RESET_REG_MISCS_PL_UA, 11
+};
+
+static struct block_defs block_rgfs_defs = {
+	"rgfs", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
-	true, true, DBG_RESET_REG_MISCS_PL_HV, 14
+	false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_tgfs_defs = {
+	"tgfs", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_ptld_defs = {
+	"ptld", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_ypld_defs = {
+	"ypld", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_misc_aeu_defs = {
-	"misc_aeu", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"misc_aeu", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_bar0_map_defs = {
-	"bar0_map", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"bar0_map", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
@@ -1269,6 +1375,11 @@ static struct block_defs *s_block_defs[MAX_BLOCK_ID] = {
 	&block_ms_defs,
 	&block_phy_pcie_defs,
 	&block_led_defs,
+	&block_avs_wrap_defs,
+	&block_rgfs_defs,
+	&block_tgfs_defs,
+	&block_ptld_defs,
+	&block_ypld_defs,
 	&block_misc_aeu_defs,
 	&block_bar0_map_defs,
 };
@@ -1281,65 +1392,67 @@ static struct platform_defs s_platform_defs[] = {
 };
 
 static struct grc_param_defs s_grc_param_defs[] = {
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_TSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_MSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_USTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_XSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_YSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_PSTORM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_REGS */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RAM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PBUF */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IOR */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_VFC */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM_CTX */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_ILT */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RSS */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CAU */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_QM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MCP */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_RESERVED */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CFC */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IGU */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BRB */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BTB */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BMB */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_NIG */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MULD */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PRS */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DMAE */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_TM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_SDM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DIF */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_STATIC */
-	{{0, 0, 0}, 0, 1, false, 0, 0},	/* DBG_GRC_PARAM_UNSTALL */
-	{{MAX_LCIDS, MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS,
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_TSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_MSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_USTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_XSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_YSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_PSTORM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_REGS */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RAM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PBUF */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IOR */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_VFC */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM_CTX */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_ILT */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RSS */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CAU */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_QM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MCP */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_RESERVED */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CFC */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IGU */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BRB */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BTB */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BMB */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_NIG */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MULD */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PRS */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DMAE */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_TM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_SDM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DIF */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_STATIC */
+	{{0, 0}, 0, 1, false, 0, 0},	/* DBG_GRC_PARAM_UNSTALL */
+	{{MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS,
 	 MAX_LCIDS},			/* DBG_GRC_PARAM_NUM_LCIDS */
-	{{MAX_LTIDS, MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS,
+	{{MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS,
 	 MAX_LTIDS},			/* DBG_GRC_PARAM_NUM_LTIDS */
-	{{0, 0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_EXCLUDE_ALL */
-	{{0, 0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_CRASH */
-	{{0, 0, 0}, 0, 1, false, 1, 0},	/* DBG_GRC_PARAM_PARITY_SAFE */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM */
-	{{1, 1, 1}, 0, 1, false, 0, 1}	/* DBG_GRC_PARAM_DUMP_PHY */
+	{{0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_EXCLUDE_ALL */
+	{{0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_CRASH */
+	{{0, 0}, 0, 1, false, 1, 0},	/* DBG_GRC_PARAM_PARITY_SAFE */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PHY */
+	{{0, 0}, 0, 1, false, 0, 0},	/* DBG_GRC_PARAM_NO_MCP */
+	{{0, 0}, 0, 1, false, 0, 0}	/* DBG_GRC_PARAM_NO_FW_VER */
 };
 
 static struct rss_mem_defs s_rss_mem_defs[] = {
 	{ "rss_mem_cid", "rss_cid", 0,
-	  {256, 256, 320},
-	  {32, 32, 32} },
+	  {256, 320},
+	  {32, 32} },
 	{ "rss_mem_key_msb", "rss_key", 1024,
-	  {128, 128, 208},
-	  {256, 256, 256} },
+	  {128, 208},
+	  {256, 256} },
 	{ "rss_mem_key_lsb", "rss_key", 2048,
-	  {128, 128, 208},
-	  {64, 64, 64} },
+	  {128, 208},
+	  {64, 64} },
 	{ "rss_mem_info", "rss_info", 3072,
-	  {128, 128, 208},
-	  {16, 16, 16} },
+	  {128, 208},
+	  {16, 16} },
 	{ "rss_mem_ind", "rss_ind", 4096,
-	  {(128 * 128), (128 * 128), (128 * 208)},
-	  {16, 16, 16} }
+	  {(128 * 128), (128 * 208)},
+	  {16, 16} }
 };
 
 static struct vfc_ram_defs s_vfc_ram_defs[] = {
@@ -1352,32 +1465,32 @@ static struct vfc_ram_defs s_vfc_ram_defs[] = {
 static struct big_ram_defs s_big_ram_defs[] = {
 	{ "BRB", MEM_GROUP_BRB_MEM, MEM_GROUP_BRB_RAM, DBG_GRC_PARAM_DUMP_BRB,
 	  BRB_REG_BIG_RAM_ADDRESS, BRB_REG_BIG_RAM_DATA,
-	  {4800, 4800, 5632} },
+	  {4800, 5632} },
 	{ "BTB", MEM_GROUP_BTB_MEM, MEM_GROUP_BTB_RAM, DBG_GRC_PARAM_DUMP_BTB,
 	  BTB_REG_BIG_RAM_ADDRESS, BTB_REG_BIG_RAM_DATA,
-	  {2880, 2880, 3680} },
+	  {2880, 3680} },
 	{ "BMB", MEM_GROUP_BMB_MEM, MEM_GROUP_BMB_RAM, DBG_GRC_PARAM_DUMP_BMB,
 	  BMB_REG_BIG_RAM_ADDRESS, BMB_REG_BIG_RAM_DATA,
-	  {1152, 1152, 1152} }
+	  {1152, 1152} }
 };
 
 static struct reset_reg_defs s_reset_regs_defs[] = {
 	{ MISCS_REG_RESET_PL_UA, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISCS_PL_UA */
+	  {true, true} },		/* DBG_RESET_REG_MISCS_PL_UA */
 	{ MISCS_REG_RESET_PL_HV, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISCS_PL_HV */
+	  {true, true} },		/* DBG_RESET_REG_MISCS_PL_HV */
 	{ MISCS_REG_RESET_PL_HV_2, 0x0,
-	  {false, false, true} },	/* DBG_RESET_REG_MISCS_PL_HV_2 */
+	  {false, true} },	/* DBG_RESET_REG_MISCS_PL_HV_2 */
 	{ MISC_REG_RESET_PL_UA, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_UA */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_UA */
 	{ MISC_REG_RESET_PL_HV, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_HV */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_HV */
 	{ MISC_REG_RESET_PL_PDA_VMAIN_1, 0x4404040,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */
 	{ MISC_REG_RESET_PL_PDA_VMAIN_2, 0x7c00007,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */
 	{ MISC_REG_RESET_PL_PDA_VAUX, 0x2,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VAUX */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VAUX */
 };
 
 static struct phy_defs s_phy_defs[] = {
@@ -1410,6 +1523,26 @@ static u32 qed_read_unaligned_dword(u8 *buf)
 	return dword;
 }
 
+/* Returns the value of the specified GRC param */
+static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn,
+			     enum dbg_grc_params grc_param)
+{
+	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+
+	return dev_data->grc.param_val[grc_param];
+}
+
+/* Initializes the GRC parameters */
+static void qed_dbg_grc_init_params(struct qed_hwfn *p_hwfn)
+{
+	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+
+	if (!dev_data->grc.params_initialized) {
+		qed_dbg_grc_set_params_default(p_hwfn);
+		dev_data->grc.params_initialized = 1;
+	}
+}
+
 /* Initializes debug data for the specified device */
 static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn,
 					struct qed_ptt *p_ptt)
@@ -1424,13 +1557,17 @@ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn,
 		dev_data->mode_enable[MODE_K2] = 1;
 	} else if (QED_IS_BB_B0(p_hwfn->cdev)) {
 		dev_data->chip_id = CHIP_BB_B0;
-		dev_data->mode_enable[MODE_BB_B0] = 1;
+		dev_data->mode_enable[MODE_BB] = 1;
 	} else {
 		return DBG_STATUS_UNKNOWN_CHIP;
 	}
 
 	dev_data->platform_id = PLATFORM_ASIC;
 	dev_data->mode_enable[MODE_ASIC] = 1;
+
+	/* Initializes the GRC parameters */
+	qed_dbg_grc_init_params(p_hwfn);
+
 	dev_data->initialized = true;
 	return DBG_STATUS_OK;
 }
@@ -1561,7 +1698,7 @@ static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn,
 	int printed_chars;
 	u32 offset = 0;
 
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) {
 		/* Read FW image/version from PRAM in a non-reset SEMI */
 		bool found = false;
 		u8 storm_id;
@@ -1622,7 +1759,7 @@ static u32 qed_dump_mfw_ver_param(struct qed_hwfn *p_hwfn,
 {
 	char mfw_ver_str[16] = EMPTY_FW_VERSION_STR;
 
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) {
 		u32 global_section_offsize, global_section_addr, mfw_ver;
 		u32 public_data_addr, global_section_offsize_addr;
 		int printed_chars;
@@ -1683,15 +1820,13 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn,
 					 bool dump,
 					 u8 num_specific_global_params)
 {
+	u8 num_params = NUM_COMMON_GLOBAL_PARAMS + num_specific_global_params;
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
 	u32 offset = 0;
 
 	/* Find platform string and dump global params section header */
 	offset += qed_dump_section_hdr(dump_buf + offset,
-				       dump,
-				       "global_params",
-				       NUM_COMMON_GLOBAL_PARAMS +
-				       num_specific_global_params);
+				       dump, "global_params", num_params);
 
 	/* Store params */
 	offset += qed_dump_fw_ver_param(p_hwfn, p_ptt, dump_buf + offset, dump);
@@ -1815,37 +1950,6 @@ static bool qed_is_mode_match(struct qed_hwfn *p_hwfn, u16 *modes_buf_offset)
 	}
 }
 
-/* Returns the value of the specified GRC param */
-static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn,
-			     enum dbg_grc_params grc_param)
-{
-	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-
-	return dev_data->grc.param_val[grc_param];
-}
-
-/* Clear all GRC params */
-static void qed_dbg_grc_clear_params(struct qed_hwfn *p_hwfn)
-{
-	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-	u32 i;
-
-	for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
-		dev_data->grc.param_set_by_user[i] = 0;
-}
-
-/* Assign default GRC param values */
-static void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn)
-{
-	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-	u32 i;
-
-	for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
-		if (!dev_data->grc.param_set_by_user[i])
-			dev_data->grc.param_val[i] =
-			    s_grc_param_defs[i].default_val[dev_data->chip_id];
-}
-
 /* Returns true if the specified entity (indicated by GRC param) should be
  * included in the dump, false otherwise.
  */
@@ -1971,7 +2075,7 @@ static void qed_grc_unreset_blocks(struct qed_hwfn *p_hwfn,
 	}
 }
 
-/* Returns the attention name offsets of the specified block */
+/* Returns the attention block data of the specified block */
 static const struct dbg_attn_block_type_data *
 qed_get_block_attn_data(enum block_id block_id, enum dbg_attn_type attn_type)
 {
@@ -2040,7 +2144,7 @@ static void qed_grc_clear_all_prty(struct qed_hwfn *p_hwfn,
  * The following parameters are dumped:
  * - 'count' = num_dumped_entries
  * - 'split' = split_type
- * - 'id'i = split_id (dumped only if split_id >= 0)
+ * - 'id' = split_id (dumped only if split_id >= 0)
  * - 'param_name' = param_val (user param, dumped only if param_name != NULL and
  *	param_val != NULL)
  */
@@ -2069,21 +2173,81 @@ static u32 qed_grc_dump_regs_hdr(u32 *dump_buf,
 	return offset;
 }
 
-/* Dumps GRC register/memory. Returns the dumped size in dwords. */
+/* Dumps the GRC registers in the specified address range.
+ * Returns the dumped size in dwords.
+ */
+static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt, u32 *dump_buf,
+				   bool dump, u32 addr, u32 len)
+{
+	u32 byte_addr = DWORDS_TO_BYTES(addr), offset = 0, i;
+
+	if (dump)
+		for (i = 0; i < len; i++, byte_addr += BYTES_IN_DWORD, offset++)
+			*(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr);
+	else
+		offset += len;
+	return offset;
+}
+
+/* Dumps GRC registers sequence header. Returns the dumped size in dwords. */
+static u32 qed_grc_dump_reg_entry_hdr(u32 *dump_buf, bool dump, u32 addr,
+				      u32 len)
+{
+	if (dump)
+		*dump_buf = addr | (len << REG_DUMP_LEN_SHIFT);
+	return 1;
+}
+
+/* Dumps GRC registers sequence. Returns the dumped size in dwords. */
 static u32 qed_grc_dump_reg_entry(struct qed_hwfn *p_hwfn,
 				  struct qed_ptt *p_ptt, u32 *dump_buf,
 				  bool dump, u32 addr, u32 len)
 {
-	u32 offset = 0, i;
+	u32 offset = 0;
+
+	offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, len);
+	offset += qed_grc_dump_addr_range(p_hwfn,
+					  p_ptt,
+					  dump_buf + offset, dump, addr, len);
+	return offset;
+}
+
+/* Dumps GRC registers sequence with skip cycle.
+ * Returns the dumped size in dwords.
+ */
+static u32 qed_grc_dump_reg_entry_skip(struct qed_hwfn *p_hwfn,
+				       struct qed_ptt *p_ptt, u32 *dump_buf,
+				       bool dump, u32 addr, u32 total_len,
+				       u32 read_len, u32 skip_len)
+{
+	u32 offset = 0, reg_offset = 0;
 
+	offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, total_len);
 	if (dump) {
-		*(dump_buf + offset++) = addr | (len << REG_DUMP_LEN_SHIFT);
-		for (i = 0; i < len; i++, addr++, offset++)
-			*(dump_buf + offset) = qed_rd(p_hwfn,
-						      p_ptt,
-						      DWORDS_TO_BYTES(addr));
+		while (reg_offset < total_len) {
+			u32 curr_len = min_t(u32,
+					     read_len,
+					     total_len - reg_offset);
+			offset += qed_grc_dump_addr_range(p_hwfn,
+							  p_ptt,
+							  dump_buf + offset,
+							  dump, addr, curr_len);
+			reg_offset += curr_len;
+			addr += curr_len;
+			if (reg_offset < total_len) {
+				curr_len = min_t(u32,
+						 skip_len,
+						 total_len - skip_len);
+				memset(dump_buf + offset, 0,
+				       DWORDS_TO_BYTES(curr_len));
+				offset += curr_len;
+				reg_offset += curr_len;
+				addr += curr_len;
+			}
+		}
 	} else {
-		offset += len + 1;
+		offset += total_len;
 	}
 
 	return offset;
@@ -2124,14 +2288,17 @@ static u32 qed_grc_dump_regs_entries(struct qed_hwfn *p_hwfn,
 				const struct dbg_dump_reg *reg =
 				    (const struct dbg_dump_reg *)
 				    &input_regs_arr.ptr[input_offset];
+				u32 addr, len;
 
+				addr = GET_FIELD(reg->data,
+						 DBG_DUMP_REG_ADDRESS);
+				len = GET_FIELD(reg->data, DBG_DUMP_REG_LENGTH);
 				offset +=
-					qed_grc_dump_reg_entry(p_hwfn, p_ptt,
-						    dump_buf + offset, dump,
-						    GET_FIELD(reg->data,
-							DBG_DUMP_REG_ADDRESS),
-						    GET_FIELD(reg->data,
-							DBG_DUMP_REG_LENGTH));
+				    qed_grc_dump_reg_entry(p_hwfn, p_ptt,
+							   dump_buf + offset,
+							   dump,
+							   addr,
+							   len);
 				(*num_dumped_reg_entries)++;
 			}
 		} else {
@@ -2194,8 +2361,14 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 				  const char *param_name, const char *param_val)
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	struct chip_platform_defs *p_platform_defs;
 	u32 offset = 0, input_offset = 0;
-	u8 port_id, pf_id;
+	struct chip_defs *p_chip_defs;
+	u8 port_id, pf_id, vf_id;
+	u16 fid;
+
+	p_chip_defs = &s_chip_defs[dev_data->chip_id];
+	p_platform_defs = &p_chip_defs->per_platform[dev_data->platform_id];
 
 	if (dump)
 		DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping registers...\n");
@@ -2214,7 +2387,6 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 
 		switch (split_type_id) {
 		case SPLIT_TYPE_NONE:
-		case SPLIT_TYPE_VF:
 			offset += qed_grc_dump_split_data(p_hwfn,
 							  p_ptt,
 							  curr_input_regs_arr,
@@ -2227,10 +2399,7 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 							  param_val);
 			break;
 		case SPLIT_TYPE_PORT:
-			for (port_id = 0;
-			     port_id <
-			     s_chip_defs[dev_data->chip_id].
-			     per_platform[dev_data->platform_id].num_ports;
+			for (port_id = 0; port_id < p_platform_defs->num_ports;
 			     port_id++) {
 				if (dump)
 					qed_port_pretend(p_hwfn, p_ptt,
@@ -2247,20 +2416,48 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 			break;
 		case SPLIT_TYPE_PF:
 		case SPLIT_TYPE_PORT_PF:
-			for (pf_id = 0;
-			     pf_id <
-			     s_chip_defs[dev_data->chip_id].
-			     per_platform[dev_data->platform_id].num_pfs;
+			for (pf_id = 0; pf_id < p_platform_defs->num_pfs;
 			     pf_id++) {
-				if (dump)
-					qed_fid_pretend(p_hwfn, p_ptt, pf_id);
-				offset += qed_grc_dump_split_data(p_hwfn,
-							p_ptt,
-							curr_input_regs_arr,
-							dump_buf + offset,
-							dump, block_enable,
-							"pf", pf_id, param_name,
-							param_val);
+				u8 pfid_shift =
+					PXP_PRETEND_CONCRETE_FID_PFID_SHIFT;
+
+				if (dump) {
+					fid = pf_id << pfid_shift;
+					qed_fid_pretend(p_hwfn, p_ptt, fid);
+				}
+
+				offset +=
+				    qed_grc_dump_split_data(p_hwfn, p_ptt,
+							    curr_input_regs_arr,
+							    dump_buf + offset,
+							    dump, block_enable,
+							    "pf", pf_id,
+							    param_name,
+							    param_val);
+			}
+			break;
+		case SPLIT_TYPE_VF:
+			for (vf_id = 0; vf_id < p_platform_defs->num_vfs;
+			     vf_id++) {
+				u8 vfvalid_shift =
+					PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT;
+				u8 vfid_shift =
+					PXP_PRETEND_CONCRETE_FID_VFID_SHIFT;
+
+				if (dump) {
+					fid = BIT(vfvalid_shift) |
+					      (vf_id << vfid_shift);
+					qed_fid_pretend(p_hwfn, p_ptt, fid);
+				}
+
+				offset +=
+				    qed_grc_dump_split_data(p_hwfn, p_ptt,
+							    curr_input_regs_arr,
+							    dump_buf + offset,
+							    dump, block_enable,
+							    "vf", vf_id,
+							    param_name,
+							    param_val);
 			}
 			break;
 		default:
@@ -2271,8 +2468,11 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Pretend to original PF */
-	if (dump)
-		qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
+	if (dump) {
+		fid = p_hwfn->rel_pf_id << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT;
+		qed_fid_pretend(p_hwfn, p_ptt, fid);
+	}
+
 	return offset;
 }
 
@@ -2291,13 +2491,14 @@ static u32 qed_grc_dump_reset_regs(struct qed_hwfn *p_hwfn,
 	/* Write reset registers */
 	for (i = 0; i < MAX_DBG_RESET_REGS; i++) {
 		if (s_reset_regs_defs[i].exists[dev_data->chip_id]) {
+			u32 addr = BYTES_TO_DWORDS(s_reset_regs_defs[i].addr);
+
 			offset += qed_grc_dump_reg_entry(p_hwfn,
 							 p_ptt,
 							 dump_buf + offset,
 							 dump,
-							 BYTES_TO_DWORDS
-							 (s_reset_regs_defs
-							  [i].addr), 1);
+							 addr,
+							 1);
 			num_regs++;
 		}
 	}
@@ -2339,6 +2540,7 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 				&attn_reg_arr[reg_idx];
 			u16 modes_buf_offset;
 			bool eval_mode;
+			u32 addr;
 
 			/* Check mode */
 			eval_mode = GET_FIELD(reg_data->mode.data,
@@ -2349,19 +2551,23 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 			if (!eval_mode ||
 			    qed_is_mode_match(p_hwfn, &modes_buf_offset)) {
 				/* Mode match - read and dump registers */
-				offset += qed_grc_dump_reg_entry(p_hwfn,
-							p_ptt,
-							dump_buf + offset,
-							dump,
-							reg_data->mask_address,
-							1);
-				offset += qed_grc_dump_reg_entry(p_hwfn,
-						p_ptt,
-						dump_buf + offset,
-						dump,
-						GET_FIELD(reg_data->data,
-						    DBG_ATTN_REG_STS_ADDRESS),
-						1);
+				addr = reg_data->mask_address;
+				offset +=
+				    qed_grc_dump_reg_entry(p_hwfn,
+							   p_ptt,
+							   dump_buf + offset,
+							   dump,
+							   addr,
+							   1);
+				addr = GET_FIELD(reg_data->data,
+						 DBG_ATTN_REG_STS_ADDRESS);
+				offset +=
+				    qed_grc_dump_reg_entry(p_hwfn,
+							   p_ptt,
+							   dump_buf + offset,
+							   dump,
+							   addr,
+							   1);
 				num_reg_entries += 2;
 			}
 		}
@@ -2369,18 +2575,21 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 
 	/* Write storm stall status registers */
 	for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
+		u32 addr;
+
 		if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id] &&
 		    dump)
 			continue;
 
+		addr =
+		    BYTES_TO_DWORDS(s_storm_defs[storm_id].sem_fast_mem_addr +
+				    SEM_FAST_REG_STALLED);
 		offset += qed_grc_dump_reg_entry(p_hwfn,
-					p_ptt,
-					dump_buf + offset,
-					dump,
-					BYTES_TO_DWORDS(s_storm_defs[storm_id].
-							sem_fast_mem_addr +
-							SEM_FAST_REG_STALLED),
-					1);
+						 p_ptt,
+						 dump_buf + offset,
+						 dump,
+						 addr,
+						 1);
 		num_reg_entries++;
 	}
 
@@ -2392,11 +2601,47 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 	return offset;
 }
 
+/* Dumps registers that can't be represented in the debug arrays */
+static u32 qed_grc_dump_special_regs(struct qed_hwfn *p_hwfn,
+				     struct qed_ptt *p_ptt,
+				     u32 *dump_buf, bool dump)
+{
+	u32 offset = 0, addr;
+
+	offset += qed_grc_dump_regs_hdr(dump_buf,
+					dump, 2, "eng", -1, NULL, NULL);
+
+	/* Dump R/TDIF_REG_DEBUG_ERROR_INFO_SIZE (every 8'th register should be
+	 * skipped).
+	 */
+	addr = BYTES_TO_DWORDS(RDIF_REG_DEBUG_ERROR_INFO);
+	offset += qed_grc_dump_reg_entry_skip(p_hwfn,
+					      p_ptt,
+					      dump_buf + offset,
+					      dump,
+					      addr,
+					      RDIF_REG_DEBUG_ERROR_INFO_SIZE,
+					      7,
+					      1);
+	addr = BYTES_TO_DWORDS(TDIF_REG_DEBUG_ERROR_INFO);
+	offset +=
+	    qed_grc_dump_reg_entry_skip(p_hwfn,
+					p_ptt,
+					dump_buf + offset,
+					dump,
+					addr,
+					TDIF_REG_DEBUG_ERROR_INFO_SIZE,
+					7,
+					1);
+
+	return offset;
+}
+
 /* Dumps a GRC memory header (section and params).
  * The following parameters are dumped:
  * name - name is dumped only if it's not NULL.
- * addr - byte_addr is dumped only if name is NULL.
- * len - dword_len is always dumped.
+ * addr - addr is dumped only if name is NULL.
+ * len - len is always dumped.
  * width - bit_width is dumped if it's not zero.
  * packed - packed=1 is dumped if it's not false.
  * mem_group - mem_group is always dumped.
@@ -2408,8 +2653,8 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
 				u32 *dump_buf,
 				bool dump,
 				const char *name,
-				u32 byte_addr,
-				u32 dword_len,
+				u32 addr,
+				u32 len,
 				u32 bit_width,
 				bool packed,
 				const char *mem_group,
@@ -2419,7 +2664,7 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
 	u32 offset = 0;
 	char buf[64];
 
-	if (!dword_len)
+	if (!len)
 		DP_NOTICE(p_hwfn,
 			  "Unexpected GRC Dump error: dumped memory size must be non-zero\n");
 	if (bit_width)
@@ -2446,20 +2691,21 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_DEBUG,
 				   "Dumping %d registers from %s...\n",
-				   dword_len, buf);
+				   len, buf);
 	} else {
 		/* Dump address */
 		offset += qed_dump_num_param(dump_buf + offset,
-					     dump, "addr", byte_addr);
-		if (dump && dword_len > 64)
+					     dump, "addr",
+					     DWORDS_TO_BYTES(addr));
+		if (dump && len > 64)
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_DEBUG,
 				   "Dumping %d registers from address 0x%x...\n",
-				   dword_len, byte_addr);
+				   len, (u32)DWORDS_TO_BYTES(addr));
 	}
 
 	/* Dump len */
-	offset += qed_dump_num_param(dump_buf + offset, dump, "len", dword_len);
+	offset += qed_dump_num_param(dump_buf + offset, dump, "len", len);
 
 	/* Dump bit width */
 	if (bit_width)
@@ -2492,8 +2738,8 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn,
 			    u32 *dump_buf,
 			    bool dump,
 			    const char *name,
-			    u32 byte_addr,
-			    u32 dword_len,
+			    u32 addr,
+			    u32 len,
 			    u32 bit_width,
 			    bool packed,
 			    const char *mem_group,
@@ -2505,21 +2751,14 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn,
 				       dump_buf + offset,
 				       dump,
 				       name,
-				       byte_addr,
-				       dword_len,
+				       addr,
+				       len,
 				       bit_width,
 				       packed,
 				       mem_group, is_storm, storm_letter);
-	if (dump) {
-		u32 i;
-
-		for (i = 0; i < dword_len;
-		     i++, byte_addr += BYTES_IN_DWORD, offset++)
-			*(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr);
-	} else {
-		offset += dword_len;
-	}
-
+	offset += qed_grc_dump_addr_range(p_hwfn,
+					  p_ptt,
+					  dump_buf + offset, dump, addr, len);
 	return offset;
 }
 
@@ -2575,25 +2814,41 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn,
 			if (qed_grc_is_mem_included(p_hwfn,
 					(enum block_id)cond_hdr->block_id,
 					mem_group_id)) {
-				u32 mem_byte_addr =
-					DWORDS_TO_BYTES(GET_FIELD(mem->dword0,
-							DBG_DUMP_MEM_ADDRESS));
+				u32 mem_addr = GET_FIELD(mem->dword0,
+							 DBG_DUMP_MEM_ADDRESS);
 				u32 mem_len = GET_FIELD(mem->dword1,
 							DBG_DUMP_MEM_LENGTH);
+				enum dbg_grc_params grc_param;
 				char storm_letter = 'a';
 				bool is_storm = false;
 
 				/* Update memory length for CCFC/TCFC memories
 				 * according to number of LCIDs/LTIDs.
 				 */
-				if (mem_group_id == MEM_GROUP_CONN_CFC_MEM)
+				if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) {
+					if (mem_len % MAX_LCIDS != 0) {
+						DP_NOTICE(p_hwfn,
+							  "Invalid CCFC connection memory size\n");
+						return 0;
+					}
+
+					grc_param = DBG_GRC_PARAM_NUM_LCIDS;
 					mem_len = qed_grc_get_param(p_hwfn,
-							DBG_GRC_PARAM_NUM_LCIDS)
-							* (mem_len / MAX_LCIDS);
-				else if (mem_group_id == MEM_GROUP_TASK_CFC_MEM)
+								    grc_param) *
+						  (mem_len / MAX_LCIDS);
+				} else if (mem_group_id ==
+					   MEM_GROUP_TASK_CFC_MEM) {
+					if (mem_len % MAX_LTIDS != 0) {
+						DP_NOTICE(p_hwfn,
+							  "Invalid TCFC task memory size\n");
+						return 0;
+					}
+
+					grc_param = DBG_GRC_PARAM_NUM_LTIDS;
 					mem_len = qed_grc_get_param(p_hwfn,
-							DBG_GRC_PARAM_NUM_LTIDS)
-							* (mem_len / MAX_LTIDS);
+								    grc_param) *
+						  (mem_len / MAX_LTIDS);
+				}
 
 				/* If memory is associated with Storm, update
 				 * Storm details.
@@ -2610,7 +2865,7 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn,
 				/* Dump memory */
 				offset += qed_grc_dump_mem(p_hwfn, p_ptt,
 						dump_buf + offset, dump, NULL,
-						mem_byte_addr, mem_len, 0,
+						mem_addr, mem_len, 0,
 						false,
 						s_mem_group_names[mem_group_id],
 						is_storm, storm_letter);
@@ -2799,29 +3054,31 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn,
 	u32 offset = 0;
 
 	for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
-		if (qed_grc_is_storm_included(p_hwfn,
-					      (enum dbg_storms)storm_id)) {
-			for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) {
-				u32 addr =
-				    s_storm_defs[storm_id].sem_fast_mem_addr +
-				    SEM_FAST_REG_STORM_REG_FILE +
-				    DWORDS_TO_BYTES(IOR_SET_OFFSET(set_id));
+		struct storm_defs *storm = &s_storm_defs[storm_id];
 
-				buf[strlen(buf) - 1] = '0' + set_id;
-				offset += qed_grc_dump_mem(p_hwfn,
-							   p_ptt,
-							   dump_buf + offset,
-							   dump,
-							   buf,
-							   addr,
-							   IORS_PER_SET,
-							   32,
-							   false,
-							   "ior",
-							   true,
-							   s_storm_defs
-							   [storm_id].letter);
-			}
+		if (!qed_grc_is_storm_included(p_hwfn,
+					       (enum dbg_storms)storm_id))
+			continue;
+
+		for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) {
+			u32 dwords, addr;
+
+			dwords = storm->sem_fast_mem_addr +
+				 SEM_FAST_REG_STORM_REG_FILE;
+			addr = BYTES_TO_DWORDS(dwords) + IOR_SET_OFFSET(set_id);
+			buf[strlen(buf) - 1] = '0' + set_id;
+			offset += qed_grc_dump_mem(p_hwfn,
+						   p_ptt,
+						   dump_buf + offset,
+						   dump,
+						   buf,
+						   addr,
+						   IORS_PER_SET,
+						   32,
+						   false,
+						   "ior",
+						   true,
+						   storm->letter);
 		}
 	}
 
@@ -2990,34 +3247,39 @@ static u32 qed_grc_dump_rss(struct qed_hwfn *p_hwfn,
 		struct rss_mem_defs *rss_defs = &s_rss_mem_defs[rss_mem_id];
 		u32 num_entries = rss_defs->num_entries[dev_data->chip_id];
 		u32 entry_width = rss_defs->entry_width[dev_data->chip_id];
-		u32 total_size = (num_entries * entry_width) / 32;
+		u32 total_dwords = (num_entries * entry_width) / 32;
+		u32 size = RSS_REG_RSS_RAM_DATA_SIZE;
 		bool packed = (entry_width == 16);
-		u32 addr = rss_defs->addr;
-		u32 i, j;
+		u32 rss_addr = rss_defs->addr;
+		u32 i, addr;
 
 		offset += qed_grc_dump_mem_hdr(p_hwfn,
 					       dump_buf + offset,
 					       dump,
 					       rss_defs->mem_name,
-					       addr,
-					       total_size,
+					       0,
+					       total_dwords,
 					       entry_width,
 					       packed,
 					       rss_defs->type_name, false, 0);
 
 		if (!dump) {
-			offset += total_size;
+			offset += total_dwords;
 			continue;
 		}
 
 		/* Dump RSS data */
-		for (i = 0; i < BYTES_TO_DWORDS(total_size); i++, addr++) {
-			qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, addr);
-			for (j = 0; j < BYTES_IN_DWORD; j++, offset++)
-				*(dump_buf + offset) =
-					qed_rd(p_hwfn, p_ptt,
-					       RSS_REG_RSS_RAM_DATA +
-					       DWORDS_TO_BYTES(j));
+		for (i = 0; i < total_dwords;
+		     i += RSS_REG_RSS_RAM_DATA_SIZE, rss_addr++) {
+			addr = BYTES_TO_DWORDS(RSS_REG_RSS_RAM_DATA);
+			qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, rss_addr);
+				offset += qed_grc_dump_addr_range(p_hwfn,
+								  p_ptt,
+								  dump_buf +
+								  offset,
+								  dump,
+								  addr,
+								  size);
 		}
 	}
 
@@ -3030,19 +3292,19 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn,
 				u32 *dump_buf, bool dump, u8 big_ram_id)
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	u32 total_blocks, ram_size, offset = 0, i;
 	char mem_name[12] = "???_BIG_RAM";
 	char type_name[8] = "???_RAM";
-	u32 ram_size, total_blocks;
-	u32 offset = 0, i, j;
+	struct big_ram_defs *big_ram;
 
-	total_blocks =
-		s_big_ram_defs[big_ram_id].num_of_blocks[dev_data->chip_id];
+	big_ram = &s_big_ram_defs[big_ram_id];
+	total_blocks = big_ram->num_of_blocks[dev_data->chip_id];
 	ram_size = total_blocks * BIG_RAM_BLOCK_SIZE_DWORDS;
 
-	strncpy(type_name, s_big_ram_defs[big_ram_id].instance_name,
-		strlen(s_big_ram_defs[big_ram_id].instance_name));
-	strncpy(mem_name, s_big_ram_defs[big_ram_id].instance_name,
-		strlen(s_big_ram_defs[big_ram_id].instance_name));
+	strncpy(type_name, big_ram->instance_name,
+		strlen(big_ram->instance_name));
+	strncpy(mem_name, big_ram->instance_name,
+		strlen(big_ram->instance_name));
 
 	/* Dump memory header */
 	offset += qed_grc_dump_mem_hdr(p_hwfn,
@@ -3059,13 +3321,17 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn,
 
 	/* Read and dump Big RAM data */
 	for (i = 0; i < total_blocks / 2; i++) {
-		qed_wr(p_hwfn, p_ptt, s_big_ram_defs[big_ram_id].addr_reg_addr,
-		       i);
-		for (j = 0; j < 2 * BIG_RAM_BLOCK_SIZE_DWORDS; j++, offset++)
-			*(dump_buf + offset) = qed_rd(p_hwfn, p_ptt,
-						s_big_ram_defs[big_ram_id].
-							data_reg_addr +
-						DWORDS_TO_BYTES(j));
+		u32 addr, len;
+
+		qed_wr(p_hwfn, p_ptt, big_ram->addr_reg_addr, i);
+		addr = BYTES_TO_DWORDS(big_ram->data_reg_addr);
+		len = 2 * BIG_RAM_BLOCK_SIZE_DWORDS;
+		offset += qed_grc_dump_addr_range(p_hwfn,
+						  p_ptt,
+						  dump_buf + offset,
+						  dump,
+						  addr,
+						  len);
 	}
 
 	return offset;
@@ -3075,11 +3341,11 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 			    struct qed_ptt *p_ptt, u32 *dump_buf, bool dump)
 {
 	bool block_enable[MAX_BLOCK_ID] = { 0 };
+	u32 offset = 0, addr;
 	bool halted = false;
-	u32 offset = 0;
 
 	/* Halt MCP */
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) {
 		halted = !qed_mcp_halt(p_hwfn, p_ptt);
 		if (!halted)
 			DP_NOTICE(p_hwfn, "MCP halt failed!\n");
@@ -3091,7 +3357,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 				   dump_buf + offset,
 				   dump,
 				   NULL,
-				   MCP_REG_SCRATCH,
+				   BYTES_TO_DWORDS(MCP_REG_SCRATCH),
 				   MCP_REG_SCRATCH_SIZE,
 				   0, false, "MCP", false, 0);
 
@@ -3101,7 +3367,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 				   dump_buf + offset,
 				   dump,
 				   NULL,
-				   MCP_REG_CPU_REG_FILE,
+				   BYTES_TO_DWORDS(MCP_REG_CPU_REG_FILE),
 				   MCP_REG_CPU_REG_FILE_SIZE,
 				   0, false, "MCP", false, 0);
 
@@ -3115,12 +3381,13 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 	/* Dump required non-MCP registers */
 	offset += qed_grc_dump_regs_hdr(dump_buf + offset,
 					dump, 1, "eng", -1, "block", "MCP");
+	addr = BYTES_TO_DWORDS(MISC_REG_SHARED_MEM_ADDR);
 	offset += qed_grc_dump_reg_entry(p_hwfn,
 					 p_ptt,
 					 dump_buf + offset,
 					 dump,
-					 BYTES_TO_DWORDS
-					 (MISC_REG_SHARED_MEM_ADDR), 1);
+					 addr,
+					 1);
 
 	/* Release MCP */
 	if (halted && qed_mcp_resume(p_hwfn, p_ptt))
@@ -3212,7 +3479,7 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
 {
 	u32 block_dwords = NUM_DBG_BUS_LINES * STATIC_DEBUG_LINE_DWORDS;
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-	u32 offset = 0, block_id, line_id, addr, i;
+	u32 offset = 0, block_id, line_id;
 	struct block_defs *p_block_defs;
 
 	if (dump) {
@@ -3255,6 +3522,8 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
 		if (dump && !dev_data->block_in_reset[block_id]) {
 			u8 dbg_client_id =
 				p_block_defs->dbg_client_id[dev_data->chip_id];
+			u32 addr = BYTES_TO_DWORDS(DBG_REG_CALENDAR_OUT_DATA);
+			u32 len = STATIC_DEBUG_LINE_DWORDS;
 
 			/* Enable block's client */
 			qed_bus_enable_clients(p_hwfn, p_ptt,
@@ -3270,11 +3539,13 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
 						    0xf, 0, 0, 0);
 
 				/* Read debug line info */
-				for (i = 0, addr = DBG_REG_CALENDAR_OUT_DATA;
-				     i < STATIC_DEBUG_LINE_DWORDS;
-				     i++, offset++, addr += BYTES_IN_DWORD)
-					dump_buf[offset] = qed_rd(p_hwfn, p_ptt,
-								  addr);
+				offset +=
+				    qed_grc_dump_addr_range(p_hwfn,
+							    p_ptt,
+							    dump_buf + offset,
+							    dump,
+							    addr,
+							    len);
 			}
 
 			/* Disable block's client and debug output */
@@ -3311,14 +3582,8 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
 	u8 i, port_mode = 0;
 	u32 offset = 0;
 
-	/* Check if emulation platform */
 	*num_dumped_dwords = 0;
 
-	/* Fill GRC parameters that were not set by the user with their default
-	 * value.
-	 */
-	qed_dbg_grc_set_params_default(p_hwfn);
-
 	/* Find port mode */
 	if (dump) {
 		switch (qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE)) {
@@ -3370,15 +3635,14 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Disable all parities using MFW command */
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) {
 		parities_masked = !qed_mcp_mask_parities(p_hwfn, p_ptt, 1);
 		if (!parities_masked) {
+			DP_NOTICE(p_hwfn,
+				  "Failed to mask parities using MFW\n");
 			if (qed_grc_get_param
 			    (p_hwfn, DBG_GRC_PARAM_PARITY_SAFE))
 				return DBG_STATUS_MCP_COULD_NOT_MASK_PRTY;
-			else
-				DP_NOTICE(p_hwfn,
-					  "Failed to mask parities using MFW\n");
 		}
 	}
 
@@ -3409,6 +3673,11 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
 						 offset,
 						 dump,
 						 block_enable, NULL, NULL);
+
+		/* Dump special registers */
+		offset += qed_grc_dump_special_regs(p_hwfn,
+						    p_ptt,
+						    dump_buf + offset, dump);
 	}
 
 	/* Dump memories */
@@ -3583,9 +3852,9 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn,
 			}
 
 			if (mode_match) {
-				u32 grc_addr =
-					DWORDS_TO_BYTES(GET_FIELD(reg->data,
-						DBG_IDLE_CHK_INFO_REG_ADDRESS));
+				u32 addr =
+				    GET_FIELD(reg->data,
+					      DBG_IDLE_CHK_INFO_REG_ADDRESS);
 
 				/* Write register header */
 				struct dbg_idle_chk_result_reg_hdr *reg_hdr =
@@ -3597,16 +3866,19 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn,
 				memset(reg_hdr, 0, sizeof(*reg_hdr));
 				reg_hdr->size = reg->size;
 				SET_FIELD(reg_hdr->data,
-					DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID,
-					rule->num_cond_regs + reg_id);
+					  DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID,
+					  rule->num_cond_regs + reg_id);
 
 				/* Write register values */
-				for (i = 0; i < reg->size;
-				     i++, offset++, grc_addr += 4)
-					dump_buf[offset] =
-						qed_rd(p_hwfn, p_ptt, grc_addr);
-				}
+				offset +=
+				    qed_grc_dump_addr_range(p_hwfn,
+							    p_ptt,
+							    dump_buf + offset,
+							    dump,
+							    addr,
+							    reg->size);
 			}
+		}
 	}
 
 	return offset;
@@ -3621,7 +3893,7 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
 	u32 cond_reg_values[IDLE_CHK_MAX_ENTRIES_SIZE];
-	u32 i, j, offset = 0;
+	u32 i, offset = 0;
 	u16 entry_id;
 	u8 reg_id;
 
@@ -3664,73 +3936,83 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		if (!check_rule && dump)
 			continue;
 
+		if (!dump) {
+			u32 entry_dump_size =
+				qed_idle_chk_dump_failure(p_hwfn,
+							  p_ptt,
+							  dump_buf + offset,
+							  false,
+							  rule->rule_id,
+							  rule,
+							  0,
+							  NULL);
+
+			offset += num_reg_entries * entry_dump_size;
+			(*num_failing_rules) += num_reg_entries;
+			continue;
+		}
+
 		/* Go over all register entries (number of entries is the same
 		 * for all condition registers).
 		 */
 		for (entry_id = 0; entry_id < num_reg_entries; entry_id++) {
 			/* Read current entry of all condition registers */
-			if (dump) {
-				u32 next_reg_offset = 0;
-
-				for (reg_id = 0;
-				     reg_id < rule->num_cond_regs;
-				     reg_id++) {
-					const struct dbg_idle_chk_cond_reg
-						*reg = &cond_regs[reg_id];
-
-					/* Find GRC address (if it's a memory,
-					 * the address of the specific entry is
-					 * calculated).
-					 */
-					u32 grc_addr =
-					   DWORDS_TO_BYTES(
-						GET_FIELD(reg->data,
-						    DBG_IDLE_CHK_COND_REG_ADDRESS));
-
-					if (reg->num_entries > 1 ||
-					    reg->start_entry > 0) {
-						u32 padded_entry_size =
-							reg->entry_size > 1 ?
-							roundup_pow_of_two
-							(reg->entry_size) : 1;
-
-						grc_addr +=
-							DWORDS_TO_BYTES(
-								(reg->start_entry +
-								entry_id)
-								* padded_entry_size);
-					}
+			u32 next_reg_offset = 0;
 
-					/* Read registers */
-					if (next_reg_offset + reg->entry_size >=
-					    IDLE_CHK_MAX_ENTRIES_SIZE) {
-						DP_NOTICE(p_hwfn,
-							  "idle check registers entry is too large\n");
-						return 0;
-					}
+			for (reg_id = 0; reg_id < rule->num_cond_regs;
+			     reg_id++) {
+				const struct dbg_idle_chk_cond_reg *reg =
+					&cond_regs[reg_id];
 
-					for (j = 0; j < reg->entry_size;
-					     j++, next_reg_offset++,
-					     grc_addr += 4)
-					     cond_reg_values[next_reg_offset] =
-						qed_rd(p_hwfn, p_ptt, grc_addr);
+				/* Find GRC address (if it's a memory,the
+				 * address of the specific entry is calculated).
+				 */
+				u32 addr =
+				    GET_FIELD(reg->data,
+					      DBG_IDLE_CHK_COND_REG_ADDRESS);
+
+				if (reg->num_entries > 1 ||
+				    reg->start_entry > 0) {
+					u32 padded_entry_size =
+					   reg->entry_size > 1 ?
+					   roundup_pow_of_two(reg->entry_size) :
+					   1;
+
+					addr += (reg->start_entry + entry_id) *
+						padded_entry_size;
 				}
+
+				/* Read registers */
+				if (next_reg_offset + reg->entry_size >=
+				    IDLE_CHK_MAX_ENTRIES_SIZE) {
+					DP_NOTICE(p_hwfn,
+						  "idle check registers entry is too large\n");
+					return 0;
+				}
+
+				next_reg_offset +=
+				    qed_grc_dump_addr_range(p_hwfn,
+							    p_ptt,
+							    cond_reg_values +
+							    next_reg_offset,
+							    dump, addr,
+							    reg->entry_size);
 			}
 
 			/* Call rule's condition function - a return value of
 			 * true indicates failure.
 			 */
 			if ((*cond_arr[rule->cond_id])(cond_reg_values,
-						       imm_values) || !dump) {
+						       imm_values)) {
 				offset +=
-					qed_idle_chk_dump_failure(p_hwfn,
-							p_ptt,
-							dump_buf + offset,
-							dump,
-							rule->rule_id,
-							rule,
-							entry_id,
-							cond_reg_values);
+				    qed_idle_chk_dump_failure(p_hwfn,
+							      p_ptt,
+							      dump_buf + offset,
+							      dump,
+							      rule->rule_id,
+							      rule,
+							      entry_id,
+							      cond_reg_values);
 				(*num_failing_rules)++;
 				break;
 			}
@@ -3818,13 +4100,18 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
 	struct mcp_file_att file_att;
 
 	/* Call NVRAM get file command */
-	if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_GET_FILE_ATT,
-			       image_type, &ret_mcp_resp, &ret_mcp_param,
-			       &ret_txn_size, (u32 *)&file_att) != 0)
-		return DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
+	int nvm_result = qed_mcp_nvm_rd_cmd(p_hwfn,
+					    p_ptt,
+					    DRV_MSG_CODE_NVM_GET_FILE_ATT,
+					    image_type,
+					    &ret_mcp_resp,
+					    &ret_mcp_param,
+					    &ret_txn_size,
+					    (u32 *)&file_att);
 
 	/* Check response */
-	if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK)
+	if (nvm_result ||
+	    (ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK)
 		return DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
 
 	/* Update return values */
@@ -3944,7 +4231,6 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
 	u32 running_mfw_addr =
 		MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize) +
 		QED_SECTION_SIZE(spad_trace_offsize) + trace_data_size_bytes;
-	enum dbg_status status;
 	u32 nvram_image_type;
 
 	*running_bundle_id = qed_rd(p_hwfn, p_ptt, running_mfw_addr);
@@ -3955,30 +4241,12 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
 	nvram_image_type =
 	    (*running_bundle_id ==
 	     DIR_ID_1) ? NVM_TYPE_MFW_TRACE1 : NVM_TYPE_MFW_TRACE2;
-	status = qed_find_nvram_image(p_hwfn,
-				      p_ptt,
-				      nvram_image_type,
-				      trace_meta_offset_bytes,
-				      trace_meta_size_bytes);
-
-	return status;
-}
-
-/* Reads the MCP Trace data from the specified GRC address into the specified
- * buffer.
- */
-static void qed_mcp_trace_read_data(struct qed_hwfn *p_hwfn,
-				    struct qed_ptt *p_ptt,
-				    u32 grc_addr, u32 size_in_dwords, u32 *buf)
-{
-	u32 i;
 
-	DP_VERBOSE(p_hwfn,
-		   QED_MSG_DEBUG,
-		   "mcp_trace_read_data: reading trace data of size %d dwords from GRC address 0x%x\n",
-		   size_in_dwords, grc_addr);
-	for (i = 0; i < size_in_dwords; i++, grc_addr += BYTES_IN_DWORD)
-		buf[i] = qed_rd(p_hwfn, p_ptt, grc_addr);
+	return qed_find_nvram_image(p_hwfn,
+				    p_ptt,
+				    nvram_image_type,
+				    trace_meta_offset_bytes,
+				    trace_meta_size_bytes);
 }
 
 /* Reads the MCP Trace meta data (from NVRAM or buffer) into the specified
@@ -4034,11 +4302,14 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 					  bool dump, u32 *num_dumped_dwords)
 {
 	u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords;
-	u32 trace_meta_size_dwords, running_bundle_id, offset = 0;
-	u32 trace_meta_offset_bytes, trace_meta_size_bytes;
+	u32 trace_meta_size_dwords = 0, running_bundle_id, offset = 0;
+	u32 trace_meta_offset_bytes = 0, trace_meta_size_bytes = 0;
 	enum dbg_status status;
+	bool mcp_access;
 	int halted = 0;
 
+	mcp_access = !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP);
+
 	*num_dumped_dwords = 0;
 
 	/* Get trace data info */
@@ -4060,7 +4331,7 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 	 * consistent if halt fails, MCP trace is taken anyway, with a small
 	 * risk that it may be corrupt.
 	 */
-	if (dump) {
+	if (dump && mcp_access) {
 		halted = !qed_mcp_halt(p_hwfn, p_ptt);
 		if (!halted)
 			DP_NOTICE(p_hwfn, "MCP halt failed!\n");
@@ -4078,13 +4349,12 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 				     dump, "size", trace_data_size_dwords);
 
 	/* Read trace data from scratchpad into dump buffer */
-	if (dump)
-		qed_mcp_trace_read_data(p_hwfn,
-					p_ptt,
-					trace_data_grc_addr,
-					trace_data_size_dwords,
-					dump_buf + offset);
-	offset += trace_data_size_dwords;
+	offset += qed_grc_dump_addr_range(p_hwfn,
+					  p_ptt,
+					  dump_buf + offset,
+					  dump,
+					  BYTES_TO_DWORDS(trace_data_grc_addr),
+					  trace_data_size_dwords);
 
 	/* Resume MCP (only if halt succeeded) */
 	if (halted && qed_mcp_resume(p_hwfn, p_ptt) != 0)
@@ -4095,38 +4365,38 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 				       dump, "mcp_trace_meta", 1);
 
 	/* Read trace meta info */
-	status = qed_mcp_trace_get_meta_info(p_hwfn,
-					     p_ptt,
-					     trace_data_size_bytes,
-					     &running_bundle_id,
-					     &trace_meta_offset_bytes,
-					     &trace_meta_size_bytes);
-	if (status != DBG_STATUS_OK)
-		return status;
+	if (mcp_access) {
+		status = qed_mcp_trace_get_meta_info(p_hwfn,
+						     p_ptt,
+						     trace_data_size_bytes,
+						     &running_bundle_id,
+						     &trace_meta_offset_bytes,
+						     &trace_meta_size_bytes);
+		if (status == DBG_STATUS_OK)
+			trace_meta_size_dwords =
+				BYTES_TO_DWORDS(trace_meta_size_bytes);
+	}
 
-	/* Dump trace meta size param (trace_meta_size_bytes is always
-	 * dword-aligned).
-	 */
-	trace_meta_size_dwords = BYTES_TO_DWORDS(trace_meta_size_bytes);
-	offset += qed_dump_num_param(dump_buf + offset,	dump, "size",
-				     trace_meta_size_dwords);
+	/* Dump trace meta size param */
+	offset += qed_dump_num_param(dump_buf + offset,
+				     dump, "size", trace_meta_size_dwords);
 
 	/* Read trace meta image into dump buffer */
-	if (dump) {
+	if (dump && trace_meta_size_dwords)
 		status = qed_mcp_trace_read_meta(p_hwfn,
-						p_ptt,
-						trace_meta_offset_bytes,
-						trace_meta_size_bytes,
-						dump_buf + offset);
-		if (status != DBG_STATUS_OK)
-			return status;
-	}
-
-	offset += trace_meta_size_dwords;
+						 p_ptt,
+						 trace_meta_offset_bytes,
+						 trace_meta_size_bytes,
+						 dump_buf + offset);
+	if (status == DBG_STATUS_OK)
+		offset += trace_meta_size_dwords;
 
 	*num_dumped_dwords = offset;
 
-	return DBG_STATUS_OK;
+	/* If no mcp access, indicate that the dump doesn't contain the meta
+	 * data from NVRAM.
+	 */
+	return mcp_access ? status : DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
 }
 
 /* Dump GRC FIFO */
@@ -4311,9 +4581,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 			       struct qed_ptt *p_ptt, u32 *dump_buf, bool dump)
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	struct fw_asserts_ram_section *asserts;
 	char storm_letter_str[2] = "?";
 	struct fw_info fw_info;
-	u32 offset = 0, i;
+	u32 offset = 0;
 	u8 storm_id;
 
 	/* Dump global params */
@@ -4323,8 +4594,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 	offset += qed_dump_str_param(dump_buf + offset,
 				     dump, "dump-type", "fw-asserts");
 	for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
-		u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx,
-			last_list_idx, element_addr;
+		u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx;
+		u32 last_list_idx, addr;
 
 		if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id])
 			continue;
@@ -4332,6 +4603,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 		/* Read FW info for the current Storm */
 		qed_read_fw_info(p_hwfn, p_ptt, storm_id, &fw_info);
 
+		asserts = &fw_info.fw_asserts_section;
+
 		/* Dump FW Asserts section header and params */
 		storm_letter_str[0] = s_storm_defs[storm_id].letter;
 		offset += qed_dump_section_hdr(dump_buf + offset, dump,
@@ -4339,12 +4612,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 		offset += qed_dump_str_param(dump_buf + offset, dump, "storm",
 					     storm_letter_str);
 		offset += qed_dump_num_param(dump_buf + offset, dump, "size",
-					     fw_info.fw_asserts_section.
-					     list_element_dword_size);
+					     asserts->list_element_dword_size);
 
 		if (!dump) {
-			offset += fw_info.fw_asserts_section.
-				  list_element_dword_size;
+			offset += asserts->list_element_dword_size;
 			continue;
 		}
 
@@ -4352,28 +4623,22 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 		fw_asserts_section_addr =
 			s_storm_defs[storm_id].sem_fast_mem_addr +
 			SEM_FAST_REG_INT_RAM +
-			RAM_LINES_TO_BYTES(fw_info.fw_asserts_section.
-					   section_ram_line_offset);
+			RAM_LINES_TO_BYTES(asserts->section_ram_line_offset);
 		next_list_idx_addr =
 			fw_asserts_section_addr +
-			DWORDS_TO_BYTES(fw_info.fw_asserts_section.
-					list_next_index_dword_offset);
+			DWORDS_TO_BYTES(asserts->list_next_index_dword_offset);
 		next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr);
 		last_list_idx = (next_list_idx > 0
 				 ? next_list_idx
-				 : fw_info.fw_asserts_section.list_num_elements)
-				- 1;
-		element_addr =
-			fw_asserts_section_addr +
-			DWORDS_TO_BYTES(fw_info.fw_asserts_section.
-					list_dword_offset) +
-			last_list_idx *
-			DWORDS_TO_BYTES(fw_info.fw_asserts_section.
-					list_element_dword_size);
-		for (i = 0;
-		     i < fw_info.fw_asserts_section.list_element_dword_size;
-		     i++, offset++, element_addr += BYTES_IN_DWORD)
-			dump_buf[offset] = qed_rd(p_hwfn, p_ptt, element_addr);
+				 : asserts->list_num_elements) - 1;
+		addr = BYTES_TO_DWORDS(fw_asserts_section_addr) +
+		       asserts->list_dword_offset +
+		       last_list_idx * asserts->list_element_dword_size;
+		offset +=
+		    qed_grc_dump_addr_range(p_hwfn, p_ptt,
+					    dump_buf + offset,
+					    dump, addr,
+					    asserts->list_element_dword_size);
 	}
 
 	/* Dump last section */
@@ -4386,13 +4651,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr)
 {
 	/* Convert binary data to debug arrays */
-	u32 num_of_buffers = *(u32 *)bin_ptr;
-	struct bin_buffer_hdr *buf_array;
+	struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr;
 	u8 buf_id;
 
-	buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1);
-
-	for (buf_id = 0; buf_id < num_of_buffers; buf_id++) {
+	for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) {
 		s_dbg_arrays[buf_id].ptr =
 		    (u32 *)(bin_ptr + buf_array[buf_id].offset);
 		s_dbg_arrays[buf_id].size_in_dwords =
@@ -4402,6 +4664,17 @@ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr)
 	return DBG_STATUS_OK;
 }
 
+/* Assign default GRC param values */
+void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn)
+{
+	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	u32 i;
+
+	for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
+		dev_data->grc.param_val[i] =
+		    s_grc_param_defs[i].default_val[dev_data->chip_id];
+}
+
 enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn,
 					      struct qed_ptt *p_ptt,
 					      u32 *buf_size)
@@ -4441,8 +4714,9 @@ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn,
 	/* GRC Dump */
 	status = qed_grc_dump(p_hwfn, p_ptt, dump_buf, true, num_dumped_dwords);
 
-	/* Clear all GRC params */
-	qed_dbg_grc_clear_params(p_hwfn);
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
 	return status;
 }
 
@@ -4495,6 +4769,10 @@ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn,
 
 	/* Idle Check Dump */
 	*num_dumped_dwords = qed_idle_chk_dump(p_hwfn, p_ptt, dump_buf, true);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
 	return DBG_STATUS_OK;
 }
 
@@ -4519,11 +4797,15 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 	u32 needed_buf_size_in_dwords;
 	enum dbg_status status;
 
-	status = qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt,
+	/* validate buffer size */
+	status =
+	    qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt,
 						&needed_buf_size_in_dwords);
 
-	if (status != DBG_STATUS_OK)
+	if (status != DBG_STATUS_OK &&
+	    status != DBG_STATUS_NVRAM_GET_IMAGE_FAILED)
 		return status;
+
 	if (buf_size_in_dwords < needed_buf_size_in_dwords)
 		return DBG_STATUS_DUMP_BUF_TOO_SMALL;
 
@@ -4531,8 +4813,13 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
 
 	/* Perform dump */
-	return qed_mcp_trace_dump(p_hwfn,
-				  p_ptt, dump_buf, true, num_dumped_dwords);
+	status = qed_mcp_trace_dump(p_hwfn,
+				    p_ptt, dump_buf, true, num_dumped_dwords);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -4567,8 +4854,14 @@ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn,
 
 	/* Update reset state */
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
-	return qed_reg_fifo_dump(p_hwfn,
-				 p_ptt, dump_buf, true, num_dumped_dwords);
+
+	status = qed_reg_fifo_dump(p_hwfn,
+				   p_ptt, dump_buf, true, num_dumped_dwords);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -4603,8 +4896,13 @@ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn,
 
 	/* Update reset state */
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
-	return qed_igu_fifo_dump(p_hwfn,
-				 p_ptt, dump_buf, true, num_dumped_dwords);
+
+	status = qed_igu_fifo_dump(p_hwfn,
+				   p_ptt, dump_buf, true, num_dumped_dwords);
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status
@@ -4641,9 +4939,16 @@ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn,
 
 	/* Update reset state */
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
-	return qed_protection_override_dump(p_hwfn,
-					    p_ptt,
-					    dump_buf, true, num_dumped_dwords);
+
+	status = qed_protection_override_dump(p_hwfn,
+					      p_ptt,
+					      dump_buf,
+					      true, num_dumped_dwords);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -5045,13 +5350,10 @@ static char s_temp_buf[MAX_MSG_LEN];
 enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr)
 {
 	/* Convert binary data to debug arrays */
-	u32 num_of_buffers = *(u32 *)bin_ptr;
-	struct bin_buffer_hdr *buf_array;
+	struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr;
 	u8 buf_id;
 
-	buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1);
-
-	for (buf_id = 0; buf_id < num_of_buffers; buf_id++) {
+	for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) {
 		s_dbg_arrays[buf_id].ptr =
 		    (u32 *)(bin_ptr + buf_array[buf_id].offset);
 		s_dbg_arrays[buf_id].size_in_dwords =
@@ -5874,16 +6176,16 @@ static enum dbg_status qed_parse_reg_fifo_dump(struct qed_hwfn *p_hwfn,
 		results_offset +=
 		    sprintf(qed_get_buf_ptr(results_buf,
 					    results_offset),
-			    "raw: 0x%016llx, address: 0x%07llx, access: %-5s, pf: %2lld, vf: %s, port: %lld, privilege: %-3s, protection: %-12s, master: %-4s, errors: ",
+			    "raw: 0x%016llx, address: 0x%07x, access: %-5s, pf: %2d, vf: %s, port: %d, privilege: %-3s, protection: %-12s, master: %-4s, errors: ",
 			    elements[i].data,
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      REG_FIFO_ELEMENT_ADDRESS) *
 				      REG_FIFO_ELEMENT_ADDR_FACTOR,
 				      s_access_strs[GET_FIELD(elements[i].data,
 						    REG_FIFO_ELEMENT_ACCESS)],
-			    GET_FIELD(elements[i].data,
-				      REG_FIFO_ELEMENT_PF), vf_str,
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
+					   REG_FIFO_ELEMENT_PF), vf_str,
+			    (u32)GET_FIELD(elements[i].data,
 				      REG_FIFO_ELEMENT_PORT),
 				      s_privilege_strs[GET_FIELD(elements[i].
 				      data,
@@ -6189,13 +6491,13 @@ qed_parse_protection_override_dump(struct qed_hwfn *p_hwfn,
 		results_offset +=
 		    sprintf(qed_get_buf_ptr(results_buf,
 					    results_offset),
-			    "window %2d, address: 0x%07x, size: %7lld regs, read: %lld, write: %lld, read protection: %-12s, write protection: %-12s\n",
+			    "window %2d, address: 0x%07x, size: %7d regs, read: %d, write: %d, read protection: %-12s, write protection: %-12s\n",
 			    i, address,
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE),
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      PROTECTION_OVERRIDE_ELEMENT_READ),
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      PROTECTION_OVERRIDE_ELEMENT_WRITE),
 			    s_protection_strs[GET_FIELD(elements[i].data,
 				PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION)],
@@ -6508,7 +6810,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
 	 */
 	rc = qed_features_lookup[feature_idx].get_size(p_hwfn, p_ptt,
 						       &buf_size_dwords);
-	if (rc != DBG_STATUS_OK)
+	if (rc != DBG_STATUS_OK && rc != DBG_STATUS_NVRAM_GET_IMAGE_FAILED)
 		return rc;
 	feature->buf_size = buf_size_dwords * sizeof(u32);
 	feature->dump_buf = vmalloc(feature->buf_size);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index e2a081ceaf52..5f31140d0b77 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -75,7 +75,8 @@ enum BAR_ID {
 	BAR_ID_1        /* Used for doorbells */
 };
 
-static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id)
+static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn,
+			   struct qed_ptt *p_ptt, enum BAR_ID bar_id)
 {
 	u32 bar_reg = (bar_id == BAR_ID_0 ?
 		       PGLUE_B_REG_PF_BAR0_SIZE : PGLUE_B_REG_PF_BAR1_SIZE);
@@ -84,7 +85,7 @@ static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id)
 	if (IS_VF(p_hwfn->cdev))
 		return 1 << 17;
 
-	val = qed_rd(p_hwfn, p_hwfn->p_main_ptt, bar_reg);
+	val = qed_rd(p_hwfn, p_ptt, bar_reg);
 	if (val)
 		return 1 << (val + 15);
 
@@ -182,199 +183,573 @@ void qed_resc_free(struct qed_dev *cdev)
 		}
 		qed_iov_free(p_hwfn);
 		qed_dmae_info_free(p_hwfn);
-		qed_dcbx_info_free(p_hwfn, p_hwfn->p_dcbx_info);
+		qed_dcbx_info_free(p_hwfn);
 	}
 }
 
-static int qed_init_qm_info(struct qed_hwfn *p_hwfn, bool b_sleepable)
+/******************** QM initialization *******************/
+#define ACTIVE_TCS_BMAP 0x9f
+#define ACTIVE_TCS_BMAP_4PORT_K2 0xf
+
+/* determines the physical queue flags for a given PF. */
+static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 {
-	u8 num_vports, vf_offset = 0, i, vport_id, num_ports, curr_queue = 0;
-	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
-	struct init_qm_port_params *p_qm_port;
-	bool init_rdma_offload_pq = false;
-	bool init_pure_ack_pq = false;
-	bool init_ooo_pq = false;
-	u16 num_pqs, multi_cos_tcs = 1;
-	u8 pf_wfq = qm_info->pf_wfq;
-	u32 pf_rl = qm_info->pf_rl;
-	u16 num_pf_rls = 0;
-	u16 num_vfs = 0;
-
-#ifdef CONFIG_QED_SRIOV
-	if (p_hwfn->cdev->p_iov_info)
-		num_vfs = p_hwfn->cdev->p_iov_info->total_vfs;
-#endif
-	memset(qm_info, 0, sizeof(*qm_info));
+	u32 flags;
 
-	num_pqs = multi_cos_tcs + num_vfs + 1;	/* The '1' is for pure-LB */
-	num_vports = (u8)RESC_NUM(p_hwfn, QED_VPORT);
+	/* common flags */
+	flags = PQ_FLAGS_LB;
 
-	if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
-		num_pqs++;	/* for RoCE queue */
-		init_rdma_offload_pq = true;
-		/* we subtract num_vfs because each require a rate limiter,
-		 * and one default rate limiter
-		 */
-		if (p_hwfn->pf_params.rdma_pf_params.enable_dcqcn)
-			num_pf_rls = RESC_NUM(p_hwfn, QED_RL) - num_vfs - 1;
+	/* feature flags */
+	if (IS_QED_SRIOV(p_hwfn->cdev))
+		flags |= PQ_FLAGS_VFS;
 
-		num_pqs += num_pf_rls;
-		qm_info->num_pf_rls = (u8) num_pf_rls;
+	/* protocol flags */
+	switch (p_hwfn->hw_info.personality) {
+	case QED_PCI_ETH:
+		flags |= PQ_FLAGS_MCOS;
+		break;
+	case QED_PCI_FCOE:
+		flags |= PQ_FLAGS_OFLD;
+		break;
+	case QED_PCI_ISCSI:
+		flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD;
+		break;
+	case QED_PCI_ETH_ROCE:
+		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+		break;
+	default:
+		DP_ERR(p_hwfn,
+		       "unknown personality %d\n", p_hwfn->hw_info.personality);
+		return 0;
 	}
 
-	if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
-		num_pqs += 2;	/* for iSCSI pure-ACK / OOO queue */
-		init_pure_ack_pq = true;
-		init_ooo_pq = true;
-	}
+	return flags;
+}
 
-	/* Sanity checking that setup requires legal number of resources */
-	if (num_pqs > RESC_NUM(p_hwfn, QED_PQ)) {
-		DP_ERR(p_hwfn,
-		       "Need too many Physical queues - 0x%04x when only %04x are available\n",
-		       num_pqs, RESC_NUM(p_hwfn, QED_PQ));
-		return -EINVAL;
-	}
+/* Getters for resource amounts necessary for qm initialization */
+u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
+{
+	return p_hwfn->hw_info.num_hw_tc;
+}
 
-	/* PQs will be arranged as follows: First per-TC PQ then pure-LB quete.
-	 */
-	qm_info->qm_pq_params = kcalloc(num_pqs,
-					sizeof(struct init_qm_pq_params),
-					b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
-	if (!qm_info->qm_pq_params)
-		goto alloc_err;
+u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
+{
+	return IS_QED_SRIOV(p_hwfn->cdev) ?
+	       p_hwfn->cdev->p_iov_info->total_vfs : 0;
+}
 
-	qm_info->qm_vport_params = kcalloc(num_vports,
-					   sizeof(struct init_qm_vport_params),
-					   b_sleepable ? GFP_KERNEL
-						       : GFP_ATOMIC);
-	if (!qm_info->qm_vport_params)
-		goto alloc_err;
+#define NUM_DEFAULT_RLS 1
 
-	qm_info->qm_port_params = kcalloc(MAX_NUM_PORTS,
-					  sizeof(struct init_qm_port_params),
-					  b_sleepable ? GFP_KERNEL
-						      : GFP_ATOMIC);
-	if (!qm_info->qm_port_params)
-		goto alloc_err;
+u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
+{
+	u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
 
-	qm_info->wfq_data = kcalloc(num_vports, sizeof(struct qed_wfq_data),
-				    b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
-	if (!qm_info->wfq_data)
-		goto alloc_err;
+	/* num RLs can't exceed resource amount of rls or vports */
+	num_pf_rls = (u16) min_t(u32, RESC_NUM(p_hwfn, QED_RL),
+				 RESC_NUM(p_hwfn, QED_VPORT));
+
+	/* Make sure after we reserve there's something left */
+	if (num_pf_rls < num_vfs + NUM_DEFAULT_RLS)
+		return 0;
 
-	vport_id = (u8)RESC_START(p_hwfn, QED_VPORT);
+	/* subtract rls necessary for VFs and one default one for the PF */
+	num_pf_rls -= num_vfs + NUM_DEFAULT_RLS;
 
-	/* First init rate limited queues */
-	for (curr_queue = 0; curr_queue < num_pf_rls; curr_queue++) {
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id++;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.non_offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		qm_info->qm_pq_params[curr_queue].rl_valid = 1;
-	}
+	return num_pf_rls;
+}
 
-	/* First init per-TC PQs */
-	for (i = 0; i < multi_cos_tcs; i++) {
-		struct init_qm_pq_params *params =
-		    &qm_info->qm_pq_params[curr_queue++];
+u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
-		if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE ||
-		    p_hwfn->hw_info.personality == QED_PCI_ETH) {
-			params->vport_id = vport_id;
-			params->tc_id = p_hwfn->hw_info.non_offload_tc;
-			params->wrr_group = 1;
-		} else {
-			params->vport_id = vport_id;
-			params->tc_id = p_hwfn->hw_info.offload_tc;
-			params->wrr_group = 1;
-		}
-	}
+	/* all pqs share the same vport, except for vfs and pf_rl pqs */
+	return (!!(PQ_FLAGS_RLS & pq_flags)) *
+	       qed_init_qm_get_num_pf_rls(p_hwfn) +
+	       (!!(PQ_FLAGS_VFS & pq_flags)) *
+	       qed_init_qm_get_num_vfs(p_hwfn) + 1;
+}
 
-	/* Then init pure-LB PQ */
-	qm_info->pure_lb_pq = curr_queue;
-	qm_info->qm_pq_params[curr_queue].vport_id =
-	    (u8) RESC_START(p_hwfn, QED_VPORT);
-	qm_info->qm_pq_params[curr_queue].tc_id = PURE_LB_TC;
-	qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-	curr_queue++;
-
-	qm_info->offload_pq = 0;
-	if (init_rdma_offload_pq) {
-		qm_info->offload_pq = curr_queue;
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		curr_queue++;
-	}
-
-	if (init_pure_ack_pq) {
-		qm_info->pure_ack_pq = curr_queue;
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		curr_queue++;
-	}
-
-	if (init_ooo_pq) {
-		qm_info->ooo_pq = curr_queue;
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
-		qm_info->qm_pq_params[curr_queue].tc_id = DCBX_ISCSI_OOO_TC;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		curr_queue++;
-	}
-
-	/* Then init per-VF PQs */
-	vf_offset = curr_queue;
-	for (i = 0; i < num_vfs; i++) {
-		/* First vport is used by the PF */
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id + i + 1;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.non_offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		qm_info->qm_pq_params[curr_queue].rl_valid = 1;
-		curr_queue++;
-	}
-
-	qm_info->vf_queues_offset = vf_offset;
-	qm_info->num_pqs = num_pqs;
-	qm_info->num_vports = num_vports;
+/* calc amount of PQs according to the requested flags */
+u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
+	return (!!(PQ_FLAGS_RLS & pq_flags)) *
+	       qed_init_qm_get_num_pf_rls(p_hwfn) +
+	       (!!(PQ_FLAGS_MCOS & pq_flags)) *
+	       qed_init_qm_get_num_tcs(p_hwfn) +
+	       (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
+	       (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
+	       (!!(PQ_FLAGS_LLT & pq_flags)) +
+	       (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
+}
+
+/* initialize the top level QM params */
+static void qed_init_qm_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	bool four_port;
+
+	/* pq and vport bases for this PF */
+	qm_info->start_pq = (u16) RESC_START(p_hwfn, QED_PQ);
+	qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT);
+
+	/* rate limiting and weighted fair queueing are always enabled */
+	qm_info->vport_rl_en = 1;
+	qm_info->vport_wfq_en = 1;
+
+	/* TC config is different for AH 4 port */
+	four_port = p_hwfn->cdev->num_ports_in_engines == MAX_NUM_PORTS_K2;
+
+	/* in AH 4 port we have fewer TCs per port */
+	qm_info->max_phys_tcs_per_port = four_port ? NUM_PHYS_TCS_4PORT_K2 :
+						     NUM_OF_PHYS_TCS;
+
+	/* unless MFW indicated otherwise, ooo_tc == 3 for
+	 * AH 4-port and 4 otherwise.
+	 */
+	if (!qm_info->ooo_tc)
+		qm_info->ooo_tc = four_port ? DCBX_TCP_OOO_K2_4PORT_TC :
+					      DCBX_TCP_OOO_TC;
+}
+
+/* initialize qm vport params */
+static void qed_init_qm_vport_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 i;
+
+	/* all vports participate in weighted fair queueing */
+	for (i = 0; i < qed_init_qm_get_num_vports(p_hwfn); i++)
+		qm_info->qm_vport_params[i].vport_wfq = 1;
+}
+
+/* initialize qm port params */
+static void qed_init_qm_port_params(struct qed_hwfn *p_hwfn)
+{
 	/* Initialize qm port parameters */
-	num_ports = p_hwfn->cdev->num_ports_in_engines;
+	u8 i, active_phys_tcs, num_ports = p_hwfn->cdev->num_ports_in_engines;
+
+	/* indicate how ooo and high pri traffic is dealt with */
+	active_phys_tcs = num_ports == MAX_NUM_PORTS_K2 ?
+			  ACTIVE_TCS_BMAP_4PORT_K2 :
+			  ACTIVE_TCS_BMAP;
+
 	for (i = 0; i < num_ports; i++) {
-		p_qm_port = &qm_info->qm_port_params[i];
+		struct init_qm_port_params *p_qm_port =
+		    &p_hwfn->qm_info.qm_port_params[i];
+
 		p_qm_port->active = 1;
-		if (num_ports == 4)
-			p_qm_port->active_phys_tcs = 0x7;
-		else
-			p_qm_port->active_phys_tcs = 0x9f;
+		p_qm_port->active_phys_tcs = active_phys_tcs;
 		p_qm_port->num_pbf_cmd_lines = PBF_MAX_CMD_LINES / num_ports;
 		p_qm_port->num_btb_blocks = BTB_MAX_BLOCKS / num_ports;
 	}
+}
+
+/* Reset the params which must be reset for qm init. QM init may be called as
+ * a result of flows other than driver load (e.g. dcbx renegotiation). Other
+ * params may be affected by the init but would simply recalculate to the same
+ * values. The allocations made for QM init, ports, vports, pqs and vfqs are not
+ * affected as these amounts stay the same.
+ */
+static void qed_init_qm_reset_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	qm_info->num_pqs = 0;
+	qm_info->num_vports = 0;
+	qm_info->num_pf_rls = 0;
+	qm_info->num_vf_pqs = 0;
+	qm_info->first_vf_pq = 0;
+	qm_info->first_mcos_pq = 0;
+	qm_info->first_rl_pq = 0;
+}
+
+static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	qm_info->num_vports++;
+
+	if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn))
+		DP_ERR(p_hwfn,
+		       "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n",
+		       qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn));
+}
+
+/* initialize a single pq and manage qm_info resources accounting.
+ * The pq_init_flags param determines whether the PQ is rate limited
+ * (for VF or PF) and whether a new vport is allocated to the pq or not
+ * (i.e. vport will be shared).
+ */
+
+/* flags for pq init */
+#define PQ_INIT_SHARE_VPORT     (1 << 0)
+#define PQ_INIT_PF_RL           (1 << 1)
+#define PQ_INIT_VF_RL           (1 << 2)
+
+/* defines for pq init */
+#define PQ_INIT_DEFAULT_WRR_GROUP       1
+#define PQ_INIT_DEFAULT_TC              0
+#define PQ_INIT_OFLD_TC                 (p_hwfn->hw_info.offload_tc)
+
+static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
+			   struct qed_qm_info *qm_info,
+			   u8 tc, u32 pq_init_flags)
+{
+	u16 pq_idx = qm_info->num_pqs, max_pq = qed_init_qm_get_num_pqs(p_hwfn);
+
+	if (pq_idx > max_pq)
+		DP_ERR(p_hwfn,
+		       "pq overflow! pq %d, max pq %d\n", pq_idx, max_pq);
+
+	/* init pq params */
+	qm_info->qm_pq_params[pq_idx].vport_id = qm_info->start_vport +
+	    qm_info->num_vports;
+	qm_info->qm_pq_params[pq_idx].tc_id = tc;
+	qm_info->qm_pq_params[pq_idx].wrr_group = PQ_INIT_DEFAULT_WRR_GROUP;
+	qm_info->qm_pq_params[pq_idx].rl_valid =
+	    (pq_init_flags & PQ_INIT_PF_RL || pq_init_flags & PQ_INIT_VF_RL);
+
+	/* qm params accounting */
+	qm_info->num_pqs++;
+	if (!(pq_init_flags & PQ_INIT_SHARE_VPORT))
+		qm_info->num_vports++;
+
+	if (pq_init_flags & PQ_INIT_PF_RL)
+		qm_info->num_pf_rls++;
+
+	if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn))
+		DP_ERR(p_hwfn,
+		       "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n",
+		       qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn));
+
+	if (qm_info->num_pf_rls > qed_init_qm_get_num_pf_rls(p_hwfn))
+		DP_ERR(p_hwfn,
+		       "rl overflow! qm_info->num_pf_rls %d, qm_init_get_num_pf_rls() %d\n",
+		       qm_info->num_pf_rls, qed_init_qm_get_num_pf_rls(p_hwfn));
+}
+
+/* get pq index according to PQ_FLAGS */
+static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
+					   u32 pq_flags)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	/* Can't have multiple flags set here */
+	if (bitmap_weight((unsigned long *)&pq_flags, sizeof(pq_flags)) > 1)
+		goto err;
+
+	switch (pq_flags) {
+	case PQ_FLAGS_RLS:
+		return &qm_info->first_rl_pq;
+	case PQ_FLAGS_MCOS:
+		return &qm_info->first_mcos_pq;
+	case PQ_FLAGS_LB:
+		return &qm_info->pure_lb_pq;
+	case PQ_FLAGS_OOO:
+		return &qm_info->ooo_pq;
+	case PQ_FLAGS_ACK:
+		return &qm_info->pure_ack_pq;
+	case PQ_FLAGS_OFLD:
+		return &qm_info->offload_pq;
+	case PQ_FLAGS_LLT:
+		return &qm_info->low_latency_pq;
+	case PQ_FLAGS_VFS:
+		return &qm_info->first_vf_pq;
+	default:
+		goto err;
+	}
+
+err:
+	DP_ERR(p_hwfn, "BAD pq flags %d\n", pq_flags);
+	return NULL;
+}
+
+/* save pq index in qm info */
+static void qed_init_qm_set_idx(struct qed_hwfn *p_hwfn,
+				u32 pq_flags, u16 pq_val)
+{
+	u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags);
+
+	*base_pq_idx = p_hwfn->qm_info.start_pq + pq_val;
+}
+
+/* get tx pq index, with the PQ TX base already set (ready for context init) */
+u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags)
+{
+	u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags);
+
+	return *base_pq_idx + CM_TX_PQ_BASE;
+}
+
+u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u8 max_tc = qed_init_qm_get_num_tcs(p_hwfn);
+
+	if (tc > max_tc)
+		DP_ERR(p_hwfn, "tc %d must be smaller than %d\n", tc, max_tc);
+
+	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_MCOS) + tc;
+}
+
+u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
+{
+	u16 max_vf = qed_init_qm_get_num_vfs(p_hwfn);
+
+	if (vf > max_vf)
+		DP_ERR(p_hwfn, "vf %d must be smaller than %d\n", vf, max_vf);
+
+	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
+}
+
+u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl)
+{
+	u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn);
+
+	if (rl > max_rl)
+		DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl);
+
+	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl;
+}
+
+/* Functions for creating specific types of pqs */
+static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LB))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LB, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PURE_LB_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_ooo_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OOO))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OOO, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, qm_info->ooo_tc, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_ACK))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OFLD))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LLT))
+		return;
 
-	qm_info->max_phys_tcs_per_port = NUM_OF_PHYS_TCS;
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 tc_idx;
 
-	qm_info->start_pq = (u16)RESC_START(p_hwfn, QED_PQ);
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_MCOS))
+		return;
 
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_MCOS, qm_info->num_pqs);
+	for (tc_idx = 0; tc_idx < qed_init_qm_get_num_tcs(p_hwfn); tc_idx++)
+		qed_init_qm_pq(p_hwfn, qm_info, tc_idx, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_vf_pqs(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u16 vf_idx, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_VFS))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_VFS, qm_info->num_pqs);
 	qm_info->num_vf_pqs = num_vfs;
-	qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT);
+	for (vf_idx = 0; vf_idx < num_vfs; vf_idx++)
+		qed_init_qm_pq(p_hwfn,
+			       qm_info, PQ_INIT_DEFAULT_TC, PQ_INIT_VF_RL);
+}
 
-	for (i = 0; i < qm_info->num_vports; i++)
-		qm_info->qm_vport_params[i].vport_wfq = 1;
+static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn)
+{
+	u16 pf_rls_idx, num_pf_rls = qed_init_qm_get_num_pf_rls(p_hwfn);
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 
-	qm_info->vport_rl_en = 1;
-	qm_info->vport_wfq_en = 1;
-	qm_info->pf_rl = pf_rl;
-	qm_info->pf_wfq = pf_wfq;
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_RLS))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs);
+	for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++)
+		qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL);
+}
+
+static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn)
+{
+	/* rate limited pqs, must come first (FW assumption) */
+	qed_init_qm_rl_pqs(p_hwfn);
+
+	/* pqs for multi cos */
+	qed_init_qm_mcos_pqs(p_hwfn);
+
+	/* pure loopback pq */
+	qed_init_qm_lb_pq(p_hwfn);
+
+	/* out of order pq */
+	qed_init_qm_ooo_pq(p_hwfn);
+
+	/* pure ack pq */
+	qed_init_qm_pure_ack_pq(p_hwfn);
+
+	/* pq for offloaded protocol */
+	qed_init_qm_offload_pq(p_hwfn);
+
+	/* low latency pq */
+	qed_init_qm_low_latency_pq(p_hwfn);
+
+	/* done sharing vports */
+	qed_init_qm_advance_vport(p_hwfn);
+
+	/* pqs for vfs */
+	qed_init_qm_vf_pqs(p_hwfn);
+}
+
+/* compare values of getters against resources amounts */
+static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
+{
+	if (qed_init_qm_get_num_vports(p_hwfn) > RESC_NUM(p_hwfn, QED_VPORT)) {
+		DP_ERR(p_hwfn, "requested amount of vports exceeds resource\n");
+		return -EINVAL;
+	}
+
+	if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
+		DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+		return -EINVAL;
+	}
 
 	return 0;
+}
 
-alloc_err:
-	qed_qm_info_free(p_hwfn);
-	return -ENOMEM;
+static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	struct init_qm_vport_params *vport;
+	struct init_qm_port_params *port;
+	struct init_qm_pq_params *pq;
+	int i, tc;
+
+	/* top level params */
+	DP_VERBOSE(p_hwfn,
+		   NETIF_MSG_HW,
+		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+		   qm_info->start_pq,
+		   qm_info->start_vport,
+		   qm_info->pure_lb_pq,
+		   qm_info->offload_pq, qm_info->pure_ack_pq);
+	DP_VERBOSE(p_hwfn,
+		   NETIF_MSG_HW,
+		   "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
+		   qm_info->ooo_pq,
+		   qm_info->first_vf_pq,
+		   qm_info->num_pqs,
+		   qm_info->num_vf_pqs,
+		   qm_info->num_vports, qm_info->max_phys_tcs_per_port);
+	DP_VERBOSE(p_hwfn,
+		   NETIF_MSG_HW,
+		   "pf_rl_en %d, pf_wfq_en %d, vport_rl_en %d, vport_wfq_en %d, pf_wfq %d, pf_rl %d, num_pf_rls %d, pq_flags %x\n",
+		   qm_info->pf_rl_en,
+		   qm_info->pf_wfq_en,
+		   qm_info->vport_rl_en,
+		   qm_info->vport_wfq_en,
+		   qm_info->pf_wfq,
+		   qm_info->pf_rl,
+		   qm_info->num_pf_rls, qed_get_pq_flags(p_hwfn));
+
+	/* port table */
+	for (i = 0; i < p_hwfn->cdev->num_ports_in_engines; i++) {
+		port = &(qm_info->qm_port_params[i]);
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "port idx %d, active %d, active_phys_tcs %d, num_pbf_cmd_lines %d, num_btb_blocks %d, reserved %d\n",
+			   i,
+			   port->active,
+			   port->active_phys_tcs,
+			   port->num_pbf_cmd_lines,
+			   port->num_btb_blocks, port->reserved);
+	}
+
+	/* vport table */
+	for (i = 0; i < qm_info->num_vports; i++) {
+		vport = &(qm_info->qm_vport_params[i]);
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "vport idx %d, vport_rl %d, wfq %d, first_tx_pq_id [ ",
+			   qm_info->start_vport + i,
+			   vport->vport_rl, vport->vport_wfq);
+		for (tc = 0; tc < NUM_OF_TCS; tc++)
+			DP_VERBOSE(p_hwfn,
+				   NETIF_MSG_HW,
+				   "%d ", vport->first_tx_pq_id[tc]);
+		DP_VERBOSE(p_hwfn, NETIF_MSG_HW, "]\n");
+	}
+
+	/* pq table */
+	for (i = 0; i < qm_info->num_pqs; i++) {
+		pq = &(qm_info->qm_pq_params[i]);
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "pq idx %d, vport_id %d, tc %d, wrr_grp %d, rl_valid %d\n",
+			   qm_info->start_pq + i,
+			   pq->vport_id,
+			   pq->tc_id, pq->wrr_group, pq->rl_valid);
+	}
+}
+
+static void qed_init_qm_info(struct qed_hwfn *p_hwfn)
+{
+	/* reset params required for init run */
+	qed_init_qm_reset_params(p_hwfn);
+
+	/* init QM top level params */
+	qed_init_qm_params(p_hwfn);
+
+	/* init QM port params */
+	qed_init_qm_port_params(p_hwfn);
+
+	/* init QM vport params */
+	qed_init_qm_vport_params(p_hwfn);
+
+	/* init QM physical queue params */
+	qed_init_qm_pq_params(p_hwfn);
+
+	/* display all that init */
+	qed_dp_init_qm_params(p_hwfn);
 }
 
 /* This function reconfigures the QM pf on the fly.
@@ -391,17 +766,8 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	bool b_rc;
 	int rc;
 
-	/* qm_info is allocated in qed_init_qm_info() which is already called
-	 * from qed_resc_alloc() or previous call of qed_qm_reconf().
-	 * The allocated size may change each init, so we free it before next
-	 * allocation.
-	 */
-	qed_qm_info_free(p_hwfn);
-
 	/* initialize qed's qm data structure */
-	rc = qed_init_qm_info(p_hwfn, false);
-	if (rc)
-		return rc;
+	qed_init_qm_info(p_hwfn);
 
 	/* stop PF's qm queues */
 	spin_lock_bh(&qm_lock);
@@ -415,7 +781,7 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	qed_init_clear_rt_data(p_hwfn);
 
 	/* prepare QM portion of runtime array */
-	qed_qm_init_pf(p_hwfn);
+	qed_qm_init_pf(p_hwfn, p_ptt);
 
 	/* activate init tool on runtime array */
 	rc = qed_init_run(p_hwfn, p_ptt, PHASE_QM_PF, p_hwfn->rel_pf_id,
@@ -434,6 +800,47 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return 0;
 }
 
+static int qed_alloc_qm_data(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	int rc;
+
+	rc = qed_init_qm_sanity(p_hwfn);
+	if (rc)
+		goto alloc_err;
+
+	qm_info->qm_pq_params = kzalloc(sizeof(*qm_info->qm_pq_params) *
+					qed_init_qm_get_num_pqs(p_hwfn),
+					GFP_KERNEL);
+	if (!qm_info->qm_pq_params)
+		goto alloc_err;
+
+	qm_info->qm_vport_params = kzalloc(sizeof(*qm_info->qm_vport_params) *
+					   qed_init_qm_get_num_vports(p_hwfn),
+					   GFP_KERNEL);
+	if (!qm_info->qm_vport_params)
+		goto alloc_err;
+
+	qm_info->qm_port_params = kzalloc(sizeof(*qm_info->qm_port_params) *
+					  p_hwfn->cdev->num_ports_in_engines,
+					  GFP_KERNEL);
+	if (!qm_info->qm_port_params)
+		goto alloc_err;
+
+	qm_info->wfq_data = kzalloc(sizeof(*qm_info->wfq_data) *
+				    qed_init_qm_get_num_vports(p_hwfn),
+				    GFP_KERNEL);
+	if (!qm_info->wfq_data)
+		goto alloc_err;
+
+	return 0;
+
+alloc_err:
+	DP_NOTICE(p_hwfn, "Failed to allocate memory for QM params\n");
+	qed_qm_info_free(p_hwfn);
+	return -ENOMEM;
+}
+
 int qed_resc_alloc(struct qed_dev *cdev)
 {
 	struct qed_iscsi_info *p_iscsi_info;
@@ -442,8 +849,10 @@ int qed_resc_alloc(struct qed_dev *cdev)
 #ifdef CONFIG_QED_LL2
 	struct qed_ll2_info *p_ll2_info;
 #endif
+	u32 rdma_tasks, excess_tasks;
 	struct qed_consq *p_consq;
 	struct qed_eq *p_eq;
+	u32 line_count;
 	int i, rc = 0;
 
 	if (IS_VF(cdev))
@@ -465,19 +874,44 @@ int qed_resc_alloc(struct qed_dev *cdev)
 		/* Set the HW cid/tid numbers (in the contest manager)
 		 * Must be done prior to any further computations.
 		 */
-		rc = qed_cxt_set_pf_params(p_hwfn);
+		rc = qed_cxt_set_pf_params(p_hwfn, RDMA_MAX_TIDS);
 		if (rc)
 			goto alloc_err;
 
-		/* Prepare and process QM requirements */
-		rc = qed_init_qm_info(p_hwfn, true);
+		rc = qed_alloc_qm_data(p_hwfn);
 		if (rc)
 			goto alloc_err;
 
+		/* init qm info */
+		qed_init_qm_info(p_hwfn);
+
 		/* Compute the ILT client partition */
-		rc = qed_cxt_cfg_ilt_compute(p_hwfn);
-		if (rc)
-			goto alloc_err;
+		rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "too many ILT lines; re-computing with less lines\n");
+			/* In case there are not enough ILT lines we reduce the
+			 * number of RDMA tasks and re-compute.
+			 */
+			excess_tasks =
+			    qed_cxt_cfg_ilt_compute_excess(p_hwfn, line_count);
+			if (!excess_tasks)
+				goto alloc_err;
+
+			rdma_tasks = RDMA_MAX_TIDS - excess_tasks;
+			rc = qed_cxt_set_pf_params(p_hwfn, rdma_tasks);
+			if (rc)
+				goto alloc_err;
+
+			rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count);
+			if (rc) {
+				DP_ERR(p_hwfn,
+				       "failed ILT compute. Requested too many lines: %u\n",
+				       line_count);
+
+				goto alloc_err;
+			}
+		}
 
 		/* CID map / ILT shadow table / T2
 		 * The talbes sizes are determined by the computations above
@@ -674,11 +1108,19 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
+static int qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
 {
 	int hw_mode = 0;
 
-	hw_mode = (1 << MODE_BB_B0);
+	if (QED_IS_BB_B0(p_hwfn->cdev)) {
+		hw_mode |= 1 << MODE_BB;
+	} else if (QED_IS_AH(p_hwfn->cdev)) {
+		hw_mode |= 1 << MODE_K2;
+	} else {
+		DP_NOTICE(p_hwfn, "Unknown chip type %#x\n",
+			  p_hwfn->cdev->type);
+		return -EINVAL;
+	}
 
 	switch (p_hwfn->cdev->num_ports_in_engines) {
 	case 1:
@@ -693,7 +1135,7 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
 	default:
 		DP_NOTICE(p_hwfn, "num_ports_in_engine = %d not supported\n",
 			  p_hwfn->cdev->num_ports_in_engines);
-		return;
+		return -EINVAL;
 	}
 
 	switch (p_hwfn->cdev->mf_mode) {
@@ -719,6 +1161,8 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
 	DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP),
 		   "Configuring function for hw_mode: 0x%08x\n",
 		   p_hwfn->hw_info.hw_mode);
+
+	return 0;
 }
 
 /* Init run time data for all PFs on an engine. */
@@ -748,16 +1192,67 @@ static void qed_init_cau_rt_data(struct qed_dev *cdev)
 	}
 }
 
+static void qed_init_cache_line_size(struct qed_hwfn *p_hwfn,
+				     struct qed_ptt *p_ptt)
+{
+	u32 val, wr_mbs, cache_line_size;
+
+	val = qed_rd(p_hwfn, p_ptt, PSWRQ2_REG_WR_MBS0);
+	switch (val) {
+	case 0:
+		wr_mbs = 128;
+		break;
+	case 1:
+		wr_mbs = 256;
+		break;
+	case 2:
+		wr_mbs = 512;
+		break;
+	default:
+		DP_INFO(p_hwfn,
+			"Unexpected value of PSWRQ2_REG_WR_MBS0 [0x%x]. Avoid configuring PGLUE_B_REG_CACHE_LINE_SIZE.\n",
+			val);
+		return;
+	}
+
+	cache_line_size = min_t(u32, L1_CACHE_BYTES, wr_mbs);
+	switch (cache_line_size) {
+	case 32:
+		val = 0;
+		break;
+	case 64:
+		val = 1;
+		break;
+	case 128:
+		val = 2;
+		break;
+	case 256:
+		val = 3;
+		break;
+	default:
+		DP_INFO(p_hwfn,
+			"Unexpected value of cache line size [0x%x]. Avoid configuring PGLUE_B_REG_CACHE_LINE_SIZE.\n",
+			cache_line_size);
+	}
+
+	if (L1_CACHE_BYTES > wr_mbs)
+		DP_INFO(p_hwfn,
+			"The cache line size for padding is suboptimal for performance [OS cache line size 0x%x, wr mbs 0x%x]\n",
+			L1_CACHE_BYTES, wr_mbs);
+
+	STORE_RT_REG(p_hwfn, PGLUE_REG_B_CACHE_LINE_SIZE_RT_OFFSET, val);
+}
+
 static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
 			      struct qed_ptt *p_ptt, int hw_mode)
 {
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 	struct qed_qm_common_rt_init_params params;
 	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 vf_id, max_num_vfs;
 	u16 num_pfs, pf_id;
 	u32 concrete_fid;
 	int rc = 0;
-	u8 vf_id;
 
 	qed_init_cau_rt_data(cdev);
 
@@ -784,17 +1279,7 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
 
 	qed_cxt_hw_init_common(p_hwfn);
 
-	/* Close gate from NIG to BRB/Storm; By default they are open, but
-	 * we close them to prevent NIG from passing data to reset blocks.
-	 * Should have been done in the ENGINE phase, but init-tool lacks
-	 * proper port-pretend capabilities.
-	 */
-	qed_wr(p_hwfn, p_ptt, NIG_REG_RX_BRB_OUT_EN, 0);
-	qed_wr(p_hwfn, p_ptt, NIG_REG_STORM_OUT_EN, 0);
-	qed_port_pretend(p_hwfn, p_ptt, p_hwfn->port_id ^ 1);
-	qed_wr(p_hwfn, p_ptt, NIG_REG_RX_BRB_OUT_EN, 0);
-	qed_wr(p_hwfn, p_ptt, NIG_REG_STORM_OUT_EN, 0);
-	qed_port_unpretend(p_hwfn, p_ptt);
+	qed_init_cache_line_size(p_hwfn, p_ptt);
 
 	rc = qed_init_run(p_hwfn, p_ptt, PHASE_ENGINE, ANY_PHASE_ID, hw_mode);
 	if (rc)
@@ -814,7 +1299,8 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
 		qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
 	}
 
-	for (vf_id = 0; vf_id < MAX_NUM_VFS_BB; vf_id++) {
+	max_num_vfs = QED_IS_AH(cdev) ? MAX_NUM_VFS_K2 : MAX_NUM_VFS_BB;
+	for (vf_id = 0; vf_id < max_num_vfs; vf_id++) {
 		concrete_fid = qed_vfid_to_concrete(p_hwfn, vf_id);
 		qed_fid_pretend(p_hwfn, p_ptt, (u16) concrete_fid);
 		qed_wr(p_hwfn, p_ptt, CCFC_REG_STRONG_ENABLE_VF, 0x1);
@@ -832,17 +1318,15 @@ static int
 qed_hw_init_dpi_size(struct qed_hwfn *p_hwfn,
 		     struct qed_ptt *p_ptt, u32 pwm_region_size, u32 n_cpus)
 {
-	u32 dpi_page_size_1, dpi_page_size_2, dpi_page_size;
-	u32 dpi_bit_shift, dpi_count;
+	u32 dpi_bit_shift, dpi_count, dpi_page_size;
 	u32 min_dpis;
+	u32 n_wids;
 
 	/* Calculate DPI size */
-	dpi_page_size_1 = QED_WID_SIZE * n_cpus;
-	dpi_page_size_2 = max_t(u32, QED_WID_SIZE, PAGE_SIZE);
-	dpi_page_size = max_t(u32, dpi_page_size_1, dpi_page_size_2);
-	dpi_page_size = roundup_pow_of_two(dpi_page_size);
+	n_wids = max_t(u32, QED_MIN_WIDS, n_cpus);
+	dpi_page_size = QED_WID_SIZE * roundup_pow_of_two(n_wids);
+	dpi_page_size = (dpi_page_size + PAGE_SIZE - 1) & ~(PAGE_SIZE - 1);
 	dpi_bit_shift = ilog2(dpi_page_size / 4096);
-
 	dpi_count = pwm_region_size / dpi_page_size;
 
 	min_dpis = p_hwfn->pf_params.rdma_pf_params.min_dpis;
@@ -870,13 +1354,13 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u32 pwm_regsize, norm_regsize;
 	u32 non_pwm_conn, min_addr_reg1;
-	u32 db_bar_size, n_cpus;
+	u32 db_bar_size, n_cpus = 1;
 	u32 roce_edpm_mode;
 	u32 pf_dems_shift;
 	int rc = 0;
 	u8 cond;
 
-	db_bar_size = qed_hw_bar_size(p_hwfn, BAR_ID_1);
+	db_bar_size = qed_hw_bar_size(p_hwfn, p_ptt, BAR_ID_1);
 	if (p_hwfn->cdev->num_hwfns > 1)
 		db_bar_size /= 2;
 
@@ -931,6 +1415,8 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 			qed_rdma_dpm_bar(p_hwfn, p_ptt);
 	}
 
+	p_hwfn->wid_count = (u16) n_cpus;
+
 	DP_INFO(p_hwfn,
 		"doorbell bar: normal_region_size=%d, pwm_region_size=%d, dpi_size=%d, dpi_count=%d, roce_edpm=%s\n",
 		norm_regsize,
@@ -967,7 +1453,7 @@ static int qed_hw_init_port(struct qed_hwfn *p_hwfn,
 
 static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt,
-			  struct qed_tunn_start_params *p_tunn,
+			  struct qed_tunnel_info *p_tunn,
 			  int hw_mode,
 			  bool b_hw_start,
 			  enum qed_int_mode int_mode,
@@ -987,7 +1473,7 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 		p_hwfn->qm_info.pf_rl = 100000;
 	}
 
-	qed_cxt_hw_init_pf(p_hwfn);
+	qed_cxt_hw_init_pf(p_hwfn, p_ptt);
 
 	qed_int_igu_init_rt(p_hwfn);
 
@@ -1095,25 +1581,47 @@ static void qed_reset_mb_shadow(struct qed_hwfn *p_hwfn,
 	       p_hwfn->mcp_info->mfw_mb_cur, p_hwfn->mcp_info->mfw_mb_length);
 }
 
-int qed_hw_init(struct qed_dev *cdev,
-		struct qed_tunn_start_params *p_tunn,
-		bool b_hw_start,
-		enum qed_int_mode int_mode,
-		bool allow_npar_tx_switch,
-		const u8 *bin_fw_data)
+static void
+qed_fill_load_req_params(struct qed_load_req_params *p_load_req,
+			 struct qed_drv_load_params *p_drv_load)
+{
+	memset(p_load_req, 0, sizeof(*p_load_req));
+
+	p_load_req->drv_role = p_drv_load->is_crash_kernel ?
+			       QED_DRV_ROLE_KDUMP : QED_DRV_ROLE_OS;
+	p_load_req->timeout_val = p_drv_load->mfw_timeout_val;
+	p_load_req->avoid_eng_reset = p_drv_load->avoid_eng_reset;
+	p_load_req->override_force_load = p_drv_load->override_force_load;
+}
+
+static int qed_vf_start(struct qed_hwfn *p_hwfn,
+			struct qed_hw_init_params *p_params)
 {
+	if (p_params->p_tunn) {
+		qed_vf_set_vf_start_tunn_update_param(p_params->p_tunn);
+		qed_vf_pf_tunnel_param_update(p_hwfn, p_params->p_tunn);
+	}
+
+	p_hwfn->b_int_enabled = 1;
+
+	return 0;
+}
+
+int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
+{
+	struct qed_load_req_params load_req_params;
 	u32 load_code, param, drv_mb_param;
 	bool b_default_mtu = true;
 	struct qed_hwfn *p_hwfn;
 	int rc = 0, mfw_rc, i;
 
-	if ((int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
+	if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
 		DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n");
 		return -EINVAL;
 	}
 
 	if (IS_PF(cdev)) {
-		rc = qed_init_fw_data(cdev, bin_fw_data);
+		rc = qed_init_fw_data(cdev, p_params->bin_fw_data);
 		if (rc)
 			return rc;
 	}
@@ -1128,26 +1636,32 @@ int qed_hw_init(struct qed_dev *cdev,
 		}
 
 		if (IS_VF(cdev)) {
-			p_hwfn->b_int_enabled = 1;
+			qed_vf_start(p_hwfn, p_params);
 			continue;
 		}
 
 		/* Enable DMAE in PXP */
 		rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
 
-		qed_calc_hw_mode(p_hwfn);
+		rc = qed_calc_hw_mode(p_hwfn);
+		if (rc)
+			return rc;
 
-		rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt, &load_code);
+		qed_fill_load_req_params(&load_req_params,
+					 p_params->p_drv_load_params);
+		rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt,
+				      &load_req_params);
 		if (rc) {
-			DP_NOTICE(p_hwfn, "Failed sending LOAD_REQ command\n");
+			DP_NOTICE(p_hwfn, "Failed sending a LOAD_REQ command\n");
 			return rc;
 		}
 
-		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
-
+		load_code = load_req_params.load_code;
 		DP_VERBOSE(p_hwfn, QED_MSG_SP,
-			   "Load request was sent. Resp:0x%x, Load code: 0x%x\n",
-			   rc, load_code);
+			   "Load request was sent. Load code: 0x%x\n",
+			   load_code);
+
+		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
 
 		p_hwfn->first_on_engine = (load_code ==
 					   FW_MSG_CODE_DRV_LOAD_ENGINE);
@@ -1168,11 +1682,15 @@ int qed_hw_init(struct qed_dev *cdev,
 		/* Fall into */
 		case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 			rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt,
-					    p_tunn, p_hwfn->hw_info.hw_mode,
-					    b_hw_start, int_mode,
-					    allow_npar_tx_switch);
+					    p_params->p_tunn,
+					    p_hwfn->hw_info.hw_mode,
+					    p_params->b_hw_start,
+					    p_params->int_mode,
+					    p_params->allow_npar_tx_switch);
 			break;
 		default:
+			DP_NOTICE(p_hwfn,
+				  "Unexpected load code [0x%08x]", load_code);
 			rc = -EINVAL;
 			break;
 		}
@@ -1212,10 +1730,7 @@ int qed_hw_init(struct qed_dev *cdev,
 
 	if (IS_PF(cdev)) {
 		p_hwfn = QED_LEADING_HWFN(cdev);
-		drv_mb_param = (FW_MAJOR_VERSION << 24) |
-			       (FW_MINOR_VERSION << 16) |
-			       (FW_REVISION_VERSION << 8) |
-			       (FW_ENGINEERING_VERSION);
+		drv_mb_param = STORM_FW_VERSION;
 		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
 				 DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER,
 				 drv_mb_param, &load_code, &param);
@@ -1290,27 +1805,53 @@ void qed_hw_timers_stop_all(struct qed_dev *cdev)
 
 int qed_hw_stop(struct qed_dev *cdev)
 {
-	int rc = 0, t_rc;
+	struct qed_hwfn *p_hwfn;
+	struct qed_ptt *p_ptt;
+	int rc, rc2 = 0;
 	int j;
 
 	for_each_hwfn(cdev, j) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[j];
-		struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+		p_hwfn = &cdev->hwfns[j];
+		p_ptt = p_hwfn->p_main_ptt;
 
 		DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Stopping hw/fw\n");
 
 		if (IS_VF(cdev)) {
 			qed_vf_pf_int_cleanup(p_hwfn);
+			rc = qed_vf_pf_reset(p_hwfn);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "qed_vf_pf_reset failed. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 			continue;
 		}
 
 		/* mark the hw as uninitialized... */
 		p_hwfn->hw_init_done = false;
 
+		/* Send unload command to MCP */
+		rc = qed_mcp_unload_req(p_hwfn, p_ptt);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
+				  rc);
+			rc2 = -EINVAL;
+		}
+
+		qed_slowpath_irq_sync(p_hwfn);
+
+		/* After this point no MFW attentions are expected, e.g. prevent
+		 * race between pf stop and dcbx pf update.
+		 */
 		rc = qed_sp_pf_stop(p_hwfn);
-		if (rc)
+		if (rc) {
 			DP_NOTICE(p_hwfn,
-				  "Failed to close PF against FW. Continue to stop HW to prevent illegal host access by the device\n");
+				  "Failed to close PF against FW [rc = %d]. Continue to stop HW to prevent illegal host access by the device.\n",
+				  rc);
+			rc2 = -EINVAL;
+		}
 
 		qed_wr(p_hwfn, p_ptt,
 		       NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x1);
@@ -1333,34 +1874,54 @@ int qed_hw_stop(struct qed_dev *cdev)
 
 		/* Need to wait 1ms to guarantee SBs are cleared */
 		usleep_range(1000, 2000);
+
+		/* Disable PF in HW blocks */
+		qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0);
+		qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0);
+
+		qed_mcp_unload_done(p_hwfn, p_ptt);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
+				  rc);
+			rc2 = -EINVAL;
+		}
 	}
 
 	if (IS_PF(cdev)) {
+		p_hwfn = QED_LEADING_HWFN(cdev);
+		p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
+
 		/* Disable DMAE in PXP - in CMT, this should only be done for
 		 * first hw-function, and only after all transactions have
 		 * stopped for all active hw-functions.
 		 */
-		t_rc = qed_change_pci_hwfn(&cdev->hwfns[0],
-					   cdev->hwfns[0].p_main_ptt, false);
-		if (t_rc != 0)
-			rc = t_rc;
+		rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "qed_change_pci_hwfn failed. rc = %d.\n", rc);
+			rc2 = -EINVAL;
+		}
 	}
 
-	return rc;
+	return rc2;
 }
 
-void qed_hw_stop_fastpath(struct qed_dev *cdev)
+int qed_hw_stop_fastpath(struct qed_dev *cdev)
 {
 	int j;
 
 	for_each_hwfn(cdev, j) {
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[j];
-		struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+		struct qed_ptt *p_ptt;
 
 		if (IS_VF(cdev)) {
 			qed_vf_pf_int_cleanup(p_hwfn);
 			continue;
 		}
+		p_ptt = qed_ptt_acquire(p_hwfn);
+		if (!p_ptt)
+			return -EAGAIN;
 
 		DP_VERBOSE(p_hwfn,
 			   NETIF_MSG_IFDOWN, "Shutting down the fastpath\n");
@@ -1378,100 +1939,28 @@ void qed_hw_stop_fastpath(struct qed_dev *cdev)
 
 		/* Need to wait 1ms to guarantee SBs are cleared */
 		usleep_range(1000, 2000);
-	}
-}
-
-void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn)
-{
-	if (IS_VF(p_hwfn->cdev))
-		return;
-
-	/* Re-open incoming traffic */
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-	       NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0);
-}
-
-static int qed_reg_assert(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt, u32 reg, bool expected)
-{
-	u32 assert_val = qed_rd(p_hwfn, p_ptt, reg);
-
-	if (assert_val != expected) {
-		DP_NOTICE(p_hwfn, "Value at address 0x%08x != 0x%08x\n",
-			  reg, expected);
-		return -EINVAL;
+		qed_ptt_release(p_hwfn, p_ptt);
 	}
 
 	return 0;
 }
 
-int qed_hw_reset(struct qed_dev *cdev)
+int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn)
 {
-	int rc = 0;
-	u32 unload_resp, unload_param;
-	u32 wol_param;
-	int i;
-
-	switch (cdev->wol_config) {
-	case QED_OV_WOL_DISABLED:
-		wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
-		break;
-	case QED_OV_WOL_ENABLED:
-		wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
-		break;
-	default:
-		DP_NOTICE(cdev,
-			  "Unknown WoL configuration %02x\n", cdev->wol_config);
-		/* Fallthrough */
-	case QED_OV_WOL_DEFAULT:
-		wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
-	}
-
-	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+	struct qed_ptt *p_ptt;
 
-		if (IS_VF(cdev)) {
-			rc = qed_vf_pf_reset(p_hwfn);
-			if (rc)
-				return rc;
-			continue;
-		}
-
-		DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Resetting hw/fw\n");
-
-		/* Check for incorrect states */
-		qed_reg_assert(p_hwfn, p_hwfn->p_main_ptt,
-			       QM_REG_USG_CNT_PF_TX, 0);
-		qed_reg_assert(p_hwfn, p_hwfn->p_main_ptt,
-			       QM_REG_USG_CNT_PF_OTHER, 0);
-
-		/* Disable PF in HW blocks */
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt, DORQ_REG_PF_DB_ENABLE, 0);
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt, QM_REG_PF_EN, 0);
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-		       TCFC_REG_STRONG_ENABLE_PF, 0);
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-		       CCFC_REG_STRONG_ENABLE_PF, 0);
+	if (IS_VF(p_hwfn->cdev))
+		return 0;
 
-		/* Send unload command to MCP */
-		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				 DRV_MSG_CODE_UNLOAD_REQ, wol_param,
-				 &unload_resp, &unload_param);
-		if (rc) {
-			DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_REQ failed\n");
-			unload_resp = FW_MSG_CODE_DRV_UNLOAD_ENGINE;
-		}
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EAGAIN;
 
-		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				 DRV_MSG_CODE_UNLOAD_DONE,
-				 0, &unload_resp, &unload_param);
-		if (rc) {
-			DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_DONE failed\n");
-			return rc;
-		}
-	}
+	/* Re-open incoming traffic */
+	qed_wr(p_hwfn, p_ptt, NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0);
+	qed_ptt_release(p_hwfn, p_ptt);
 
-	return rc;
+	return 0;
 }
 
 /* Free hwfn memory and resources acquired in hw_hwfn_prepare */
@@ -1485,10 +1974,25 @@ static void qed_hw_hwfn_free(struct qed_hwfn *p_hwfn)
 static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
 {
 	/* clear indirect access */
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_88_F0, 0);
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_8C_F0, 0);
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_90_F0, 0);
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_94_F0, 0);
+	if (QED_IS_AH(p_hwfn->cdev)) {
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_E8_F0_K2, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_EC_F0_K2, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_F0_F0_K2, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_F4_F0_K2, 0);
+	} else {
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_88_F0_BB, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_8C_F0_BB, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_90_F0_BB, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
+	}
 
 	/* Clean Previous errors if such exist */
 	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
@@ -1522,7 +2026,7 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
 {
 	u32 *feat_num = p_hwfn->hw_info.feat_num;
 	struct qed_sb_cnt_info sb_cnt_info;
-	int num_features = 1;
+	u32 non_l2_sbs = 0;
 
 	if (IS_ENABLED(CONFIG_QED_RDMA) &&
 	    p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
@@ -1530,204 +2034,260 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
 		 * the status blocks equally between L2 / RoCE but with
 		 * consideration as to how many l2 queues / cnqs we have.
 		 */
-		num_features++;
-
 		feat_num[QED_RDMA_CNQ] =
-			min_t(u32, RESC_NUM(p_hwfn, QED_SB) / num_features,
+			min_t(u32, RESC_NUM(p_hwfn, QED_SB) / 2,
 			      RESC_NUM(p_hwfn, QED_RDMA_CNQ_RAM));
-	}
 
-	feat_num[QED_PF_L2_QUE] = min_t(u32, RESC_NUM(p_hwfn, QED_SB) /
-						num_features,
-					RESC_NUM(p_hwfn, QED_L2_QUEUE));
-
-	memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
-	qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
-	feat_num[QED_VF_L2_QUE] =
-	    min_t(u32,
-		  RESC_NUM(p_hwfn, QED_L2_QUEUE) -
-		  FEAT_NUM(p_hwfn, QED_PF_L2_QUE), sb_cnt_info.sb_iov_cnt);
+		non_l2_sbs = feat_num[QED_RDMA_CNQ];
+	}
 
+	if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE ||
+	    p_hwfn->hw_info.personality == QED_PCI_ETH) {
+		/* Start by allocating VF queues, then PF's */
+		memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+		qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+		feat_num[QED_VF_L2_QUE] = min_t(u32,
+						RESC_NUM(p_hwfn, QED_L2_QUEUE),
+						sb_cnt_info.sb_iov_cnt);
+		feat_num[QED_PF_L2_QUE] = min_t(u32,
+						RESC_NUM(p_hwfn, QED_SB) -
+						non_l2_sbs,
+						RESC_NUM(p_hwfn,
+							 QED_L2_QUEUE) -
+						FEAT_NUM(p_hwfn,
+							 QED_VF_L2_QUE));
+	}
+
+	if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
+		feat_num[QED_ISCSI_CQ] = min_t(u32, RESC_NUM(p_hwfn, QED_SB),
+					       RESC_NUM(p_hwfn,
+							QED_CMDQS_CQS));
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_PROBE,
-		   "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d #SBS=%d num_features=%d\n",
+		   "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d ISCSI_CQ=%d #SBS=%d\n",
 		   (int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE),
 		   (int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE),
 		   (int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ),
-		   RESC_NUM(p_hwfn, QED_SB), num_features);
+		   (int)FEAT_NUM(p_hwfn, QED_ISCSI_CQ),
+		   RESC_NUM(p_hwfn, QED_SB));
 }
 
-static enum resource_id_enum qed_hw_get_mfw_res_id(enum qed_resources res_id)
+const char *qed_hw_get_resc_name(enum qed_resources res_id)
 {
-	enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
-
 	switch (res_id) {
-	case QED_SB:
-		mfw_res_id = RESOURCE_NUM_SB_E;
-		break;
 	case QED_L2_QUEUE:
-		mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
-		break;
+		return "L2_QUEUE";
 	case QED_VPORT:
-		mfw_res_id = RESOURCE_NUM_VPORT_E;
-		break;
+		return "VPORT";
 	case QED_RSS_ENG:
-		mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
-		break;
+		return "RSS_ENG";
 	case QED_PQ:
-		mfw_res_id = RESOURCE_NUM_PQ_E;
-		break;
+		return "PQ";
 	case QED_RL:
-		mfw_res_id = RESOURCE_NUM_RL_E;
-		break;
+		return "RL";
 	case QED_MAC:
+		return "MAC";
 	case QED_VLAN:
-		/* Each VFC resource can accommodate both a MAC and a VLAN */
-		mfw_res_id = RESOURCE_VFC_FILTER_E;
-		break;
+		return "VLAN";
+	case QED_RDMA_CNQ_RAM:
+		return "RDMA_CNQ_RAM";
 	case QED_ILT:
-		mfw_res_id = RESOURCE_ILT_E;
-		break;
+		return "ILT";
 	case QED_LL2_QUEUE:
-		mfw_res_id = RESOURCE_LL2_QUEUE_E;
-		break;
-	case QED_RDMA_CNQ_RAM:
+		return "LL2_QUEUE";
 	case QED_CMDQS_CQS:
-		/* CNQ/CMDQS are the same resource */
-		mfw_res_id = RESOURCE_CQS_E;
-		break;
+		return "CMDQS_CQS";
 	case QED_RDMA_STATS_QUEUE:
-		mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
-		break;
+		return "RDMA_STATS_QUEUE";
+	case QED_BDQ:
+		return "BDQ";
+	case QED_SB:
+		return "SB";
 	default:
-		break;
+		return "UNKNOWN_RESOURCE";
+	}
+}
+
+static int
+__qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt,
+			    enum qed_resources res_id,
+			    u32 resc_max_val, u32 *p_mcp_resp)
+{
+	int rc;
+
+	rc = qed_mcp_set_resc_max_val(p_hwfn, p_ptt, res_id,
+				      resc_max_val, p_mcp_resp);
+	if (rc) {
+		DP_NOTICE(p_hwfn,
+			  "MFW response failure for a max value setting of resource %d [%s]\n",
+			  res_id, qed_hw_get_resc_name(res_id));
+		return rc;
+	}
+
+	if (*p_mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK)
+		DP_INFO(p_hwfn,
+			"Failed to set the max value of resource %d [%s]. mcp_resp = 0x%08x.\n",
+			res_id, qed_hw_get_resc_name(res_id), *p_mcp_resp);
+
+	return 0;
+}
+
+static int
+qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	bool b_ah = QED_IS_AH(p_hwfn->cdev);
+	u32 resc_max_val, mcp_resp;
+	u8 res_id;
+	int rc;
+
+	for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
+		switch (res_id) {
+		case QED_LL2_QUEUE:
+			resc_max_val = MAX_NUM_LL2_RX_QUEUES;
+			break;
+		case QED_RDMA_CNQ_RAM:
+			/* No need for a case for QED_CMDQS_CQS since
+			 * CNQ/CMDQS are the same resource.
+			 */
+			resc_max_val = NUM_OF_CMDQS_CQS;
+			break;
+		case QED_RDMA_STATS_QUEUE:
+			resc_max_val = b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2
+			    : RDMA_NUM_STATISTIC_COUNTERS_BB;
+			break;
+		case QED_BDQ:
+			resc_max_val = BDQ_NUM_RESOURCES;
+			break;
+		default:
+			continue;
+		}
+
+		rc = __qed_hw_set_soft_resc_size(p_hwfn, p_ptt, res_id,
+						 resc_max_val, &mcp_resp);
+		if (rc)
+			return rc;
+
+		/* There's no point to continue to the next resource if the
+		 * command is not supported by the MFW.
+		 * We do continue if the command is supported but the resource
+		 * is unknown to the MFW. Such a resource will be later
+		 * configured with the default allocation values.
+		 */
+		if (mcp_resp == FW_MSG_CODE_UNSUPPORTED)
+			return -EINVAL;
 	}
 
-	return mfw_res_id;
+	return 0;
 }
 
-static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn,
-				    enum qed_resources res_id)
+static
+int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn,
+			 enum qed_resources res_id,
+			 u32 *p_resc_num, u32 *p_resc_start)
 {
 	u8 num_funcs = p_hwfn->num_funcs_on_engine;
+	bool b_ah = QED_IS_AH(p_hwfn->cdev);
 	struct qed_sb_cnt_info sb_cnt_info;
-	u32 dflt_resc_num = 0;
 
 	switch (res_id) {
-	case QED_SB:
-		memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
-		qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
-		dflt_resc_num = sb_cnt_info.sb_cnt;
-		break;
 	case QED_L2_QUEUE:
-		dflt_resc_num = MAX_NUM_L2_QUEUES_BB / num_funcs;
+		*p_resc_num = (b_ah ? MAX_NUM_L2_QUEUES_K2 :
+			       MAX_NUM_L2_QUEUES_BB) / num_funcs;
 		break;
 	case QED_VPORT:
-		dflt_resc_num = MAX_NUM_VPORTS_BB / num_funcs;
+		*p_resc_num = (b_ah ? MAX_NUM_VPORTS_K2 :
+			       MAX_NUM_VPORTS_BB) / num_funcs;
 		break;
 	case QED_RSS_ENG:
-		dflt_resc_num = ETH_RSS_ENGINE_NUM_BB / num_funcs;
+		*p_resc_num = (b_ah ? ETH_RSS_ENGINE_NUM_K2 :
+			       ETH_RSS_ENGINE_NUM_BB) / num_funcs;
 		break;
 	case QED_PQ:
-		/* The granularity of the PQs is 8 */
-		dflt_resc_num = MAX_QM_TX_QUEUES_BB / num_funcs;
-		dflt_resc_num &= ~0x7;
+		*p_resc_num = (b_ah ? MAX_QM_TX_QUEUES_K2 :
+			       MAX_QM_TX_QUEUES_BB) / num_funcs;
+		*p_resc_num &= ~0x7;	/* The granularity of the PQs is 8 */
 		break;
 	case QED_RL:
-		dflt_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
+		*p_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
 		break;
 	case QED_MAC:
 	case QED_VLAN:
 		/* Each VFC resource can accommodate both a MAC and a VLAN */
-		dflt_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
+		*p_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
 		break;
 	case QED_ILT:
-		dflt_resc_num = PXP_NUM_ILT_RECORDS_BB / num_funcs;
+		*p_resc_num = (b_ah ? PXP_NUM_ILT_RECORDS_K2 :
+			       PXP_NUM_ILT_RECORDS_BB) / num_funcs;
 		break;
 	case QED_LL2_QUEUE:
-		dflt_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
+		*p_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
 		break;
 	case QED_RDMA_CNQ_RAM:
 	case QED_CMDQS_CQS:
 		/* CNQ/CMDQS are the same resource */
-		dflt_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
+		*p_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
 		break;
 	case QED_RDMA_STATS_QUEUE:
-		dflt_resc_num = RDMA_NUM_STATISTIC_COUNTERS_BB / num_funcs;
+		*p_resc_num = (b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2 :
+			       RDMA_NUM_STATISTIC_COUNTERS_BB) / num_funcs;
 		break;
-	default:
+	case QED_BDQ:
+		if (p_hwfn->hw_info.personality != QED_PCI_ISCSI &&
+		    p_hwfn->hw_info.personality != QED_PCI_FCOE)
+			*p_resc_num = 0;
+		else
+			*p_resc_num = 1;
 		break;
+	case QED_SB:
+		memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+		qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+		*p_resc_num = sb_cnt_info.sb_cnt;
+		break;
+	default:
+		return -EINVAL;
 	}
 
-	return dflt_resc_num;
-}
-
-static const char *qed_hw_get_resc_name(enum qed_resources res_id)
-{
 	switch (res_id) {
-	case QED_SB:
-		return "SB";
-	case QED_L2_QUEUE:
-		return "L2_QUEUE";
-	case QED_VPORT:
-		return "VPORT";
-	case QED_RSS_ENG:
-		return "RSS_ENG";
-	case QED_PQ:
-		return "PQ";
-	case QED_RL:
-		return "RL";
-	case QED_MAC:
-		return "MAC";
-	case QED_VLAN:
-		return "VLAN";
-	case QED_RDMA_CNQ_RAM:
-		return "RDMA_CNQ_RAM";
-	case QED_ILT:
-		return "ILT";
-	case QED_LL2_QUEUE:
-		return "LL2_QUEUE";
-	case QED_CMDQS_CQS:
-		return "CMDQS_CQS";
-	case QED_RDMA_STATS_QUEUE:
-		return "RDMA_STATS_QUEUE";
+	case QED_BDQ:
+		if (!*p_resc_num)
+			*p_resc_start = 0;
+		else if (p_hwfn->cdev->num_ports_in_engines == 4)
+			*p_resc_start = p_hwfn->port_id;
+		else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
+			*p_resc_start = p_hwfn->port_id;
+		else if (p_hwfn->hw_info.personality == QED_PCI_FCOE)
+			*p_resc_start = p_hwfn->port_id + 2;
+		break;
 	default:
-		return "UNKNOWN_RESOURCE";
+		*p_resc_start = *p_resc_num * p_hwfn->enabled_func_idx;
+		break;
 	}
+
+	return 0;
 }
 
-static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
-				enum qed_resources res_id)
+static int __qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
+				  enum qed_resources res_id)
 {
-	u32 dflt_resc_num = 0, dflt_resc_start = 0, mcp_resp, mcp_param;
-	u32 *p_resc_num, *p_resc_start;
-	struct resource_info resc_info;
+	u32 dflt_resc_num = 0, dflt_resc_start = 0;
+	u32 mcp_resp, *p_resc_num, *p_resc_start;
 	int rc;
 
 	p_resc_num = &RESC_NUM(p_hwfn, res_id);
 	p_resc_start = &RESC_START(p_hwfn, res_id);
 
-	/* Default values assumes that each function received equal share */
-	dflt_resc_num = qed_hw_get_dflt_resc_num(p_hwfn, res_id);
-	if (!dflt_resc_num) {
+	rc = qed_hw_get_dflt_resc(p_hwfn, res_id, &dflt_resc_num,
+				  &dflt_resc_start);
+	if (rc) {
 		DP_ERR(p_hwfn,
 		       "Failed to get default amount for resource %d [%s]\n",
 		       res_id, qed_hw_get_resc_name(res_id));
-		return -EINVAL;
-	}
-	dflt_resc_start = dflt_resc_num * p_hwfn->enabled_func_idx;
-
-	memset(&resc_info, 0, sizeof(resc_info));
-	resc_info.res_id = qed_hw_get_mfw_res_id(res_id);
-	if (resc_info.res_id == RESOURCE_NUM_INVALID) {
-		DP_ERR(p_hwfn,
-		       "Failed to match resource %d [%s] with the MFW resources\n",
-		       res_id, qed_hw_get_resc_name(res_id));
-		return -EINVAL;
+		return rc;
 	}
 
-	rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, &resc_info,
-				   &mcp_resp, &mcp_param);
+	rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, res_id,
+				   &mcp_resp, p_resc_num, p_resc_start);
 	if (rc) {
 		DP_NOTICE(p_hwfn,
 			  "MFW response failure for an allocation request for resource %d [%s]\n",
@@ -1740,13 +2300,12 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
 	 * - There is an internal error in the MFW while processing the request
 	 * - The resource ID is unknown to the MFW
 	 */
-	if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK &&
-	    mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_DEPRECATED) {
-		DP_NOTICE(p_hwfn,
-			  "Resource %d [%s]: No allocation info was received [mcp_resp 0x%x]. Applying default values [num %d, start %d].\n",
-			  res_id,
-			  qed_hw_get_resc_name(res_id),
-			  mcp_resp, dflt_resc_num, dflt_resc_start);
+	if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK) {
+		DP_INFO(p_hwfn,
+			"Failed to receive allocation info for resource %d [%s]. mcp_resp = 0x%x. Applying default values [%d,%d].\n",
+			res_id,
+			qed_hw_get_resc_name(res_id),
+			mcp_resp, dflt_resc_num, dflt_resc_start);
 		*p_resc_num = dflt_resc_num;
 		*p_resc_start = dflt_resc_start;
 		goto out;
@@ -1754,13 +2313,9 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
 
 	/* Special handling for status blocks; Would be revised in future */
 	if (res_id == QED_SB) {
-		resc_info.size -= 1;
-		resc_info.offset -= p_hwfn->enabled_func_idx;
+		*p_resc_num -= 1;
+		*p_resc_start -= p_hwfn->enabled_func_idx;
 	}
-
-	*p_resc_num = resc_info.size;
-	*p_resc_start = resc_info.offset;
-
 out:
 	/* PQs have to divide by 8 [that's the HW granularity].
 	 * Reduce number so it would fit.
@@ -1778,19 +2333,80 @@ out:
 	return 0;
 }
 
-static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
+static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn)
 {
-	u8 res_id;
 	int rc;
+	u8 res_id;
 
 	for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
-		rc = qed_hw_set_resc_info(p_hwfn, res_id);
+		rc = __qed_hw_set_resc_info(p_hwfn, res_id);
 		if (rc)
 			return rc;
 	}
 
+	return 0;
+}
+
+static int qed_hw_get_resc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_resc_unlock_params resc_unlock_params;
+	struct qed_resc_lock_params resc_lock_params;
+	bool b_ah = QED_IS_AH(p_hwfn->cdev);
+	u8 res_id;
+	int rc;
+
+	/* Setting the max values of the soft resources and the following
+	 * resources allocation queries should be atomic. Since several PFs can
+	 * run in parallel - a resource lock is needed.
+	 * If either the resource lock or resource set value commands are not
+	 * supported - skip the the max values setting, release the lock if
+	 * needed, and proceed to the queries. Other failures, including a
+	 * failure to acquire the lock, will cause this function to fail.
+	 */
+	qed_mcp_resc_lock_default_init(&resc_lock_params, &resc_unlock_params,
+				       QED_RESC_LOCK_RESC_ALLOC, false);
+
+	rc = qed_mcp_resc_lock(p_hwfn, p_ptt, &resc_lock_params);
+	if (rc && rc != -EINVAL) {
+		return rc;
+	} else if (rc == -EINVAL) {
+		DP_INFO(p_hwfn,
+			"Skip the max values setting of the soft resources since the resource lock is not supported by the MFW\n");
+	} else if (!rc && !resc_lock_params.b_granted) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to acquire the resource lock for the resource allocation commands\n");
+		return -EBUSY;
+	} else {
+		rc = qed_hw_set_soft_resc_size(p_hwfn, p_ptt);
+		if (rc && rc != -EINVAL) {
+			DP_NOTICE(p_hwfn,
+				  "Failed to set the max values of the soft resources\n");
+			goto unlock_and_exit;
+		} else if (rc == -EINVAL) {
+			DP_INFO(p_hwfn,
+				"Skip the max values setting of the soft resources since it is not supported by the MFW\n");
+			rc = qed_mcp_resc_unlock(p_hwfn, p_ptt,
+						 &resc_unlock_params);
+			if (rc)
+				DP_INFO(p_hwfn,
+					"Failed to release the resource lock for the resource allocation commands\n");
+		}
+	}
+
+	rc = qed_hw_set_resc_info(p_hwfn);
+	if (rc)
+		goto unlock_and_exit;
+
+	if (resc_lock_params.b_granted && !resc_unlock_params.b_released) {
+		rc = qed_mcp_resc_unlock(p_hwfn, p_ptt, &resc_unlock_params);
+		if (rc)
+			DP_INFO(p_hwfn,
+				"Failed to release the resource lock for the resource allocation commands\n");
+	}
+
 	/* Sanity for ILT */
-	if ((RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB)) {
+	if ((b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_K2)) ||
+	    (!b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB))) {
 		DP_NOTICE(p_hwfn, "Can't assign ILT pages [%08x,...,%08x]\n",
 			  RESC_START(p_hwfn, QED_ILT),
 			  RESC_END(p_hwfn, QED_ILT) - 1);
@@ -1799,8 +2415,6 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
 
 	qed_hw_set_feat(p_hwfn);
 
-	DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE,
-		   "The numbers for each resource are:\n");
 	for (res_id = 0; res_id < QED_MAX_RESC; res_id++)
 		DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, "%s = %d start = %d\n",
 			   qed_hw_get_resc_name(res_id),
@@ -1808,6 +2422,11 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
 			   RESC_START(p_hwfn, res_id));
 
 	return 0;
+
+unlock_and_exit:
+	if (resc_lock_params.b_granted && !resc_unlock_params.b_released)
+		qed_mcp_resc_unlock(p_hwfn, p_ptt, &resc_unlock_params);
+	return rc;
 }
 
 static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
@@ -1860,9 +2479,15 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G:
 		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X25G;
 		break;
+	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G:
+		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X10G;
+		break;
 	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G:
 		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_1X25G;
 		break;
+	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G:
+		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_4X25G;
+		break;
 	default:
 		DP_NOTICE(p_hwfn, "Unknown port mode in 0x%08x\n", core_cfg);
 		break;
@@ -1976,8 +2601,9 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u8 num_funcs, enabled_func_idx = p_hwfn->rel_pf_id;
 	u32 reg_function_hide, tmp, eng_mask, low_pfs_mask;
+	struct qed_dev *cdev = p_hwfn->cdev;
 
-	num_funcs = MAX_NUM_PFS_BB;
+	num_funcs = QED_IS_AH(cdev) ? MAX_NUM_PFS_K2 : MAX_NUM_PFS_BB;
 
 	/* Bit 0 of MISCS_REG_FUNCTION_HIDE indicates whether the bypass values
 	 * in the other bits are selected.
@@ -1990,12 +2616,17 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	reg_function_hide = qed_rd(p_hwfn, p_ptt, MISCS_REG_FUNCTION_HIDE);
 
 	if (reg_function_hide & 0x1) {
-		if (QED_PATH_ID(p_hwfn) && p_hwfn->cdev->num_hwfns == 1) {
-			num_funcs = 0;
-			eng_mask = 0xaaaa;
+		if (QED_IS_BB(cdev)) {
+			if (QED_PATH_ID(p_hwfn) && cdev->num_hwfns == 1) {
+				num_funcs = 0;
+				eng_mask = 0xaaaa;
+			} else {
+				num_funcs = 1;
+				eng_mask = 0x5554;
+			}
 		} else {
 			num_funcs = 1;
-			eng_mask = 0x5554;
+			eng_mask = 0xfffe;
 		}
 
 		/* Get the number of the enabled functions on the engine */
@@ -2027,24 +2658,12 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		   p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine);
 }
 
-static int
-qed_get_hw_info(struct qed_hwfn *p_hwfn,
-		struct qed_ptt *p_ptt,
-		enum qed_pci_personality personality)
+static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt)
 {
 	u32 port_mode;
-	int rc;
-
-	/* Since all information is common, only first hwfns should do this */
-	if (IS_LEAD_HWFN(p_hwfn)) {
-		rc = qed_iov_hw_info(p_hwfn);
-		if (rc)
-			return rc;
-	}
 
-	/* Read the port mode */
-	port_mode = qed_rd(p_hwfn, p_ptt,
-			   CNIG_REG_NW_PORT_MODE_BB_B0);
+	port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB_B0);
 
 	if (port_mode < 3) {
 		p_hwfn->cdev->num_ports_in_engines = 1;
@@ -2057,6 +2676,54 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		/* Default num_ports_in_engines to something */
 		p_hwfn->cdev->num_ports_in_engines = 1;
 	}
+}
+
+static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt)
+{
+	u32 port;
+	int i;
+
+	p_hwfn->cdev->num_ports_in_engines = 0;
+
+	for (i = 0; i < MAX_NUM_PORTS_K2; i++) {
+		port = qed_rd(p_hwfn, p_ptt,
+			      CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4));
+		if (port & 1)
+			p_hwfn->cdev->num_ports_in_engines++;
+	}
+
+	if (!p_hwfn->cdev->num_ports_in_engines) {
+		DP_NOTICE(p_hwfn, "All NIG ports are inactive\n");
+
+		/* Default num_ports_in_engine to something */
+		p_hwfn->cdev->num_ports_in_engines = 1;
+	}
+}
+
+static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	if (QED_IS_BB(p_hwfn->cdev))
+		qed_hw_info_port_num_bb(p_hwfn, p_ptt);
+	else
+		qed_hw_info_port_num_ah(p_hwfn, p_ptt);
+}
+
+static int
+qed_get_hw_info(struct qed_hwfn *p_hwfn,
+		struct qed_ptt *p_ptt,
+		enum qed_pci_personality personality)
+{
+	int rc;
+
+	/* Since all information is common, only first hwfns should do this */
+	if (IS_LEAD_HWFN(p_hwfn)) {
+		rc = qed_iov_hw_info(p_hwfn);
+		if (rc)
+			return rc;
+	}
+
+	qed_hw_info_port_num(p_hwfn, p_ptt);
 
 	qed_hw_get_nvm_info(p_hwfn, p_ptt);
 
@@ -2085,33 +2752,48 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		p_hwfn->hw_info.personality = protocol;
 	}
 
+	p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
+	p_hwfn->hw_info.num_active_tc = 1;
+
 	qed_get_num_funcs(p_hwfn, p_ptt);
 
 	if (qed_mcp_is_init(p_hwfn))
 		p_hwfn->hw_info.mtu = p_hwfn->mcp_info->func_info.mtu;
 
-	return qed_hw_get_resc(p_hwfn);
+	return qed_hw_get_resc(p_hwfn, p_ptt);
 }
 
-static int qed_get_dev_info(struct qed_dev *cdev)
+static int qed_get_dev_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u16 device_id_mask;
 	u32 tmp;
 
 	/* Read Vendor Id / Device Id */
 	pci_read_config_word(cdev->pdev, PCI_VENDOR_ID, &cdev->vendor_id);
 	pci_read_config_word(cdev->pdev, PCI_DEVICE_ID, &cdev->device_id);
 
-	cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
-				     MISCS_REG_CHIP_NUM);
-	cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
-				     MISCS_REG_CHIP_REV);
+	/* Determine type */
+	device_id_mask = cdev->device_id & QED_DEV_ID_MASK;
+	switch (device_id_mask) {
+	case QED_DEV_ID_MASK_BB:
+		cdev->type = QED_DEV_TYPE_BB;
+		break;
+	case QED_DEV_ID_MASK_AH:
+		cdev->type = QED_DEV_TYPE_AH;
+		break;
+	default:
+		DP_NOTICE(p_hwfn, "Unknown device id 0x%x\n", cdev->device_id);
+		return -EBUSY;
+	}
+
+	cdev->chip_num = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_NUM);
+	cdev->chip_rev = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_REV);
+
 	MASK_FIELD(CHIP_REV, cdev->chip_rev);
 
-	cdev->type = QED_DEV_TYPE_BB;
 	/* Learn number of HW-functions */
-	tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt,
-		     MISCS_REG_CMT_ENABLED_FOR_PAIR);
+	tmp = qed_rd(p_hwfn, p_ptt, MISCS_REG_CMT_ENABLED_FOR_PAIR);
 
 	if (tmp & (1 << p_hwfn->rel_pf_id)) {
 		DP_NOTICE(cdev->hwfns, "device in CMT mode\n");
@@ -2120,15 +2802,17 @@ static int qed_get_dev_info(struct qed_dev *cdev)
 		cdev->num_hwfns = 1;
 	}
 
-	cdev->chip_bond_id = qed_rd(p_hwfn, p_hwfn->p_main_ptt,
+	cdev->chip_bond_id = qed_rd(p_hwfn, p_ptt,
 				    MISCS_REG_CHIP_TEST_REG) >> 4;
 	MASK_FIELD(CHIP_BOND_ID, cdev->chip_bond_id);
-	cdev->chip_metal = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
-				       MISCS_REG_CHIP_METAL);
+	cdev->chip_metal = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_METAL);
 	MASK_FIELD(CHIP_METAL, cdev->chip_metal);
 
 	DP_INFO(cdev->hwfns,
-		"Chip details - Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n",
+		"Chip details - %s %c%d, Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n",
+		QED_IS_BB(cdev) ? "BB" : "AH",
+		'A' + cdev->chip_rev,
+		(int)cdev->chip_metal,
 		cdev->chip_num, cdev->chip_rev,
 		cdev->chip_bond_id, cdev->chip_metal);
 
@@ -2174,7 +2858,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 
 	/* First hwfn learns basic information, e.g., number of hwfns */
 	if (!p_hwfn->my_id) {
-		rc = qed_get_dev_info(p_hwfn->cdev);
+		rc = qed_get_dev_info(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			goto err1;
 	}
@@ -2195,6 +2879,15 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 		goto err2;
 	}
 
+	/* Sending a mailbox to the MFW should be done after qed_get_hw_info()
+	 * is called as it sets the ports number in an engine.
+	 */
+	if (IS_LEAD_HWFN(p_hwfn)) {
+		rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt);
+		if (rc)
+			DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n");
+	}
+
 	/* Allocate the init RT array and initialize the init-ops engine */
 	rc = qed_init_alloc(p_hwfn);
 	if (rc)
@@ -2236,11 +2929,14 @@ int qed_hw_prepare(struct qed_dev *cdev,
 		u8 __iomem *addr;
 
 		/* adjust bar offset for second engine */
-		addr = cdev->regview + qed_hw_bar_size(p_hwfn, BAR_ID_0) / 2;
+		addr = cdev->regview +
+		       qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+				       BAR_ID_0) / 2;
 		p_regview = addr;
 
-		/* adjust doorbell bar offset for second engine */
-		addr = cdev->doorbells + qed_hw_bar_size(p_hwfn, BAR_ID_1) / 2;
+		addr = cdev->doorbells +
+		       qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+				       BAR_ID_1) / 2;
 		p_doorbell = addr;
 
 		/* prepare second hw function */
@@ -2389,9 +3085,8 @@ qed_chain_alloc_sanity_check(struct qed_dev *cdev,
 	 * size/capacity fields are of a u32 type.
 	 */
 	if ((cnt_type == QED_CHAIN_CNT_TYPE_U16 &&
-	     chain_size > 0x10000) ||
-	    (cnt_type == QED_CHAIN_CNT_TYPE_U32 &&
-	     chain_size > 0x100000000ULL)) {
+	     chain_size > ((u32)U16_MAX + 1)) ||
+	    (cnt_type == QED_CHAIN_CNT_TYPE_U32 && chain_size > U32_MAX)) {
 		DP_NOTICE(cdev,
 			  "The actual chain size (0x%llx) is larger than the maximal possible value\n",
 			  chain_size);
@@ -3364,3 +4059,22 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	memset(p_hwfn->qm_info.wfq_data, 0,
 	       sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports);
 }
+
+int qed_device_num_engines(struct qed_dev *cdev)
+{
+	return QED_IS_BB(cdev) ? 2 : 1;
+}
+
+static int qed_device_num_ports(struct qed_dev *cdev)
+{
+	/* in CMT always only one port */
+	if (cdev->num_hwfns > 1)
+		return 1;
+
+	return cdev->num_ports_in_engines * qed_device_num_engines(cdev);
+}
+
+int qed_device_get_port_id(struct qed_dev *cdev)
+{
+	return (QED_LEADING_HWFN(cdev)->abs_pf_id) % qed_device_num_ports(cdev);
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index 6812003411cd..cefe3ee9064a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -82,26 +82,63 @@ int qed_resc_alloc(struct qed_dev *cdev);
  */
 void qed_resc_setup(struct qed_dev *cdev);
 
+enum qed_override_force_load {
+	QED_OVERRIDE_FORCE_LOAD_NONE,
+	QED_OVERRIDE_FORCE_LOAD_ALWAYS,
+	QED_OVERRIDE_FORCE_LOAD_NEVER,
+};
+
+struct qed_drv_load_params {
+	/* Indicates whether the driver is running over a crash kernel.
+	 * As part of the load request, this will be used for providing the
+	 * driver role to the MFW.
+	 * In case of a crash kernel over PDA - this should be set to false.
+	 */
+	bool is_crash_kernel;
+
+	/* The timeout value that the MFW should use when locking the engine for
+	 * the driver load process.
+	 * A value of '0' means the default value, and '255' means no timeout.
+	 */
+	u8 mfw_timeout_val;
+#define QED_LOAD_REQ_LOCK_TO_DEFAULT    0
+#define QED_LOAD_REQ_LOCK_TO_NONE       255
+
+	/* Avoid engine reset when first PF loads on it */
+	bool avoid_eng_reset;
+
+	/* Allow overriding the default force load behavior */
+	enum qed_override_force_load override_force_load;
+};
+
+struct qed_hw_init_params {
+	/* Tunneling parameters */
+	struct qed_tunnel_info *p_tunn;
+
+	bool b_hw_start;
+
+	/* Interrupt mode [msix, inta, etc.] to use */
+	enum qed_int_mode int_mode;
+
+	/* NPAR tx switching to be used for vports for tx-switching */
+	bool allow_npar_tx_switch;
+
+	/* Binary fw data pointer in binary fw file */
+	const u8 *bin_fw_data;
+
+	/* Driver load parameters */
+	struct qed_drv_load_params *p_drv_load_params;
+};
+
 /**
  * @brief qed_hw_init -
  *
  * @param cdev
- * @param p_tunn
- * @param b_hw_start
- * @param int_mode - interrupt mode [msix, inta, etc.] to use.
- * @param allow_npar_tx_switch - npar tx switching to be used
- *	  for vports configured for tx-switching.
- * @param bin_fw_data - binary fw data pointer in binary fw file.
- *			Pass NULL if not using binary fw file.
+ * @param p_params
  *
  * @return int
  */
-int qed_hw_init(struct qed_dev *cdev,
-		struct qed_tunn_start_params *p_tunn,
-		bool b_hw_start,
-		enum qed_int_mode int_mode,
-		bool allow_npar_tx_switch,
-		const u8 *bin_fw_data);
+int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params);
 
 /**
  * @brief qed_hw_timers_stop_all - stop the timers HW block
@@ -128,26 +165,20 @@ int qed_hw_stop(struct qed_dev *cdev);
  *
  * @param cdev
  *
+ * @return int
  */
-void qed_hw_stop_fastpath(struct qed_dev *cdev);
+int qed_hw_stop_fastpath(struct qed_dev *cdev);
 
 /**
  * @brief qed_hw_start_fastpath -restart fastpath traffic,
  *		only if hw_stop_fastpath was called
  *
- * @param cdev
- *
- */
-void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn);
-
-/**
- * @brief qed_hw_reset -
- *
- * @param cdev
+ * @param p_hwfn
  *
  * @return int
  */
-int qed_hw_reset(struct qed_dev *cdev);
+int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn);
+
 
 /**
  * @brief qed_hw_prepare -
@@ -441,4 +472,6 @@ int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
  */
 int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 			 u16 coalesce, u8 qid, u16 sb_id);
+
+const char *qed_hw_get_resc_name(enum qed_resources res_id);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index cbc81412174f..21a58fffd02b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -191,7 +191,7 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn,
 	p_data->q_params.cq_sb_pi = fcoe_pf_params->gl_rq_pi;
 	p_data->q_params.cmdq_sb_pi = fcoe_pf_params->gl_cmd_pi;
 
-	p_data->q_params.bdq_resource_id = FCOE_BDQ_ID(p_hwfn->port_id);
+	p_data->q_params.bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
 
 	DMA_REGPAIR_LE(p_data->q_params.bdq_pbl_base_address[BDQ_ID_RQ],
 		       fcoe_pf_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
@@ -241,7 +241,7 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
 	struct fcoe_conn_offload_ramrod_data *p_data;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	u16 pq_id = 0, tmp;
+	u16 physical_q0, tmp;
 	int rc;
 
 	/* Get SPQ entry */
@@ -261,9 +261,9 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
 	p_data = &p_ramrod->offload_ramrod_data;
 
 	/* Transmission PQ is the first of the PF */
-	pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_FCOE, NULL);
-	p_conn->physical_q0 = cpu_to_le16(pq_id);
-	p_data->physical_q0 = cpu_to_le16(pq_id);
+	physical_q0 = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	p_conn->physical_q0 = cpu_to_le16(physical_q0);
+	p_data->physical_q0 = cpu_to_le16(physical_q0);
 
 	p_data->conn_id = cpu_to_le16(p_conn->conn_id);
 	DMA_REGPAIR_LE(p_data->sq_pbl_addr, p_conn->sq_pbl_addr);
@@ -340,10 +340,10 @@ qed_sp_fcoe_conn_destroy(struct qed_hwfn *p_hwfn,
 
 static int
 qed_sp_fcoe_func_stop(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt,
 		      enum spq_mode comp_mode,
 		      struct qed_spq_comp_cb *p_comp_addr)
 {
-	struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	u32 active_segs = 0;
@@ -512,19 +512,31 @@ static void __iomem *qed_fcoe_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
 static void __iomem *qed_fcoe_get_primary_bdq_prod(struct qed_hwfn *p_hwfn,
 						   u8 bdq_id)
 {
-	u8 bdq_function_id = FCOE_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_MSDM_RAM +
-	       MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id, bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_MSDM_RAM +
+		       MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 static void __iomem *qed_fcoe_get_secondary_bdq_prod(struct qed_hwfn *p_hwfn,
 						     u8 bdq_id)
 {
-	u8 bdq_function_id = FCOE_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_TSDM_RAM +
-	       TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id, bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_TSDM_RAM +
+		       TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 struct qed_fcoe_info *qed_fcoe_alloc(struct qed_hwfn *p_hwfn)
@@ -753,6 +765,7 @@ static struct qed_hash_fcoe_con *qed_fcoe_get_hash(struct qed_dev *cdev,
 
 static int qed_fcoe_stop(struct qed_dev *cdev)
 {
+	struct qed_ptt *p_ptt;
 	int rc;
 
 	if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) {
@@ -766,10 +779,15 @@ static int qed_fcoe_stop(struct qed_dev *cdev)
 		return -EINVAL;
 	}
 
+	p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
+	if (!p_ptt)
+		return -EAGAIN;
+
 	/* Stop the fcoe */
-	rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev),
+	rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev), p_ptt,
 				   QED_SPQ_MODE_EBLOCK, NULL);
 	cdev->flags &= ~QED_FLAG_STORAGE_STARTED;
+	qed_ptt_release(QED_LEADING_HWFN(cdev), p_ptt);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 37c2bfb663bb..858a57a73589 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -574,6 +574,7 @@ enum core_event_opcode {
 	CORE_EVENT_TX_QUEUE_STOP,
 	CORE_EVENT_RX_QUEUE_START,
 	CORE_EVENT_RX_QUEUE_STOP,
+	CORE_EVENT_RX_QUEUE_FLUSH,
 	MAX_CORE_EVENT_OPCODE
 };
 
@@ -625,6 +626,7 @@ enum core_ramrod_cmd_id {
 	CORE_RAMROD_TX_QUEUE_START,
 	CORE_RAMROD_RX_QUEUE_STOP,
 	CORE_RAMROD_TX_QUEUE_STOP,
+	CORE_RAMROD_RX_QUEUE_FLUSH,
 	MAX_CORE_RAMROD_CMD_ID
 };
 
@@ -698,7 +700,8 @@ struct core_rx_slow_path_cqe {
 	u8 type;
 	u8 ramrod_cmd_id;
 	__le16 echo;
-	__le32 reserved1[7];
+	struct core_rx_cqe_opaque_data opaque_data;
+	__le32 reserved1[5];
 };
 
 union core_rx_cqe_union {
@@ -735,45 +738,46 @@ struct core_rx_stop_ramrod_data {
 	__le16 reserved2[2];
 };
 
-struct core_tx_bd_flags {
-	u8 as_bitfield;
-#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_MASK	0x1
-#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_SHIFT	0
-#define CORE_TX_BD_FLAGS_VLAN_INSERTION_MASK	0x1
-#define CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT	1
-#define CORE_TX_BD_FLAGS_START_BD_MASK	0x1
-#define CORE_TX_BD_FLAGS_START_BD_SHIFT	2
-#define CORE_TX_BD_FLAGS_IP_CSUM_MASK	0x1
-#define CORE_TX_BD_FLAGS_IP_CSUM_SHIFT	3
-#define CORE_TX_BD_FLAGS_L4_CSUM_MASK	0x1
-#define CORE_TX_BD_FLAGS_L4_CSUM_SHIFT	4
-#define CORE_TX_BD_FLAGS_IPV6_EXT_MASK	0x1
-#define CORE_TX_BD_FLAGS_IPV6_EXT_SHIFT	5
-#define CORE_TX_BD_FLAGS_L4_PROTOCOL_MASK	0x1
-#define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT	6
-#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK	0x1
-#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7
+struct core_tx_bd_data {
+	__le16 as_bitfield;
+#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_MASK	0x1
+#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_SHIFT     0
+#define CORE_TX_BD_DATA_VLAN_INSERTION_MASK	0x1
+#define CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT      1
+#define CORE_TX_BD_DATA_START_BD_MASK	0x1
+#define CORE_TX_BD_DATA_START_BD_SHIFT            2
+#define CORE_TX_BD_DATA_IP_CSUM_MASK	0x1
+#define CORE_TX_BD_DATA_IP_CSUM_SHIFT             3
+#define CORE_TX_BD_DATA_L4_CSUM_MASK	0x1
+#define CORE_TX_BD_DATA_L4_CSUM_SHIFT             4
+#define CORE_TX_BD_DATA_IPV6_EXT_MASK	0x1
+#define CORE_TX_BD_DATA_IPV6_EXT_SHIFT            5
+#define CORE_TX_BD_DATA_L4_PROTOCOL_MASK	0x1
+#define CORE_TX_BD_DATA_L4_PROTOCOL_SHIFT         6
+#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_MASK	0x1
+#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_SHIFT 7
+#define CORE_TX_BD_DATA_NBDS_MASK	0xF
+#define CORE_TX_BD_DATA_NBDS_SHIFT                8
+#define CORE_TX_BD_DATA_ROCE_FLAV_MASK	0x1
+#define CORE_TX_BD_DATA_ROCE_FLAV_SHIFT           12
+#define CORE_TX_BD_DATA_IP_LEN_MASK	0x1
+#define CORE_TX_BD_DATA_IP_LEN_SHIFT              13
+#define CORE_TX_BD_DATA_RESERVED0_MASK            0x3
+#define CORE_TX_BD_DATA_RESERVED0_SHIFT           14
 };
 
 struct core_tx_bd {
 	struct regpair addr;
 	__le16 nbytes;
 	__le16 nw_vlan_or_lb_echo;
-	u8 bitfield0;
-#define CORE_TX_BD_NBDS_MASK	0xF
-#define CORE_TX_BD_NBDS_SHIFT	0
-#define CORE_TX_BD_ROCE_FLAV_MASK	0x1
-#define CORE_TX_BD_ROCE_FLAV_SHIFT	4
-#define CORE_TX_BD_RESERVED0_MASK	0x7
-#define CORE_TX_BD_RESERVED0_SHIFT	5
-	struct core_tx_bd_flags bd_flags;
+	struct core_tx_bd_data bd_data;
 	__le16 bitfield1;
 #define CORE_TX_BD_L4_HDR_OFFSET_W_MASK	0x3FFF
 #define CORE_TX_BD_L4_HDR_OFFSET_W_SHIFT 0
 #define CORE_TX_BD_TX_DST_MASK	0x1
 #define CORE_TX_BD_TX_DST_SHIFT	14
-#define CORE_TX_BD_RESERVED1_MASK	0x1
-#define CORE_TX_BD_RESERVED1_SHIFT	15
+#define CORE_TX_BD_RESERVED_MASK         0x1
+#define CORE_TX_BD_RESERVED_SHIFT        15
 };
 
 enum core_tx_dest {
@@ -800,6 +804,14 @@ struct core_tx_stop_ramrod_data {
 	__le32 reserved0[2];
 };
 
+enum dcb_dhcp_update_flag {
+	DONT_UPDATE_DCB_DHCP,
+	UPDATE_DCB,
+	UPDATE_DSCP,
+	UPDATE_DCB_DSCP,
+	MAX_DCB_DHCP_UPDATE_FLAG
+};
+
 struct eth_mstorm_per_pf_stat {
 	struct regpair gre_discard_pkts;
 	struct regpair vxlan_discard_pkts;
@@ -893,6 +905,12 @@ union event_ring_element {
 	struct event_ring_next_addr next_addr;
 };
 
+enum fw_flow_ctrl_mode {
+	flow_ctrl_pause,
+	flow_ctrl_pfc,
+	MAX_FW_FLOW_CTRL_MODE
+};
+
 /* Major and Minor hsi Versions */
 struct hsi_fp_ver_struct {
 	u8 minor_ver_arr[2];
@@ -921,6 +939,7 @@ enum malicious_vf_error_id {
 	ETH_EDPM_OUT_OF_SYNC,
 	ETH_TUNN_IPV6_EXT_NBD_ERR,
 	ETH_CONTROL_PACKET_VIOLATION,
+	ETH_ANTI_SPOOFING_ERR,
 	MAX_MALICIOUS_VF_ERROR_ID
 };
 
@@ -1106,8 +1125,9 @@ struct tstorm_per_port_stat {
 	struct regpair ll2_mac_filter_discard;
 	struct regpair ll2_conn_disabled_discard;
 	struct regpair iscsi_irregular_pkt;
-	struct regpair reserved;
+	struct regpair fcoe_irregular_pkt;
 	struct regpair roce_irregular_pkt;
+	struct regpair reserved;
 	struct regpair eth_irregular_pkt;
 	struct regpair reserved1;
 	struct regpair preroce_irregular_pkt;
@@ -1648,6 +1668,11 @@ enum block_addr {
 	GRCBASE_MS = 0x6a0000,
 	GRCBASE_PHY_PCIE = 0x620000,
 	GRCBASE_LED = 0x6b8000,
+	GRCBASE_AVS_WRAP = 0x6b0000,
+	GRCBASE_RGFS = 0x19d0000,
+	GRCBASE_TGFS = 0x19e0000,
+	GRCBASE_PTLD = 0x19f0000,
+	GRCBASE_YPLD = 0x1a10000,
 	GRCBASE_MISC_AEU = 0x8000,
 	GRCBASE_BAR0_MAP = 0x1c00000,
 	MAX_BLOCK_ADDR
@@ -1732,6 +1757,11 @@ enum block_id {
 	BLOCK_MS,
 	BLOCK_PHY_PCIE,
 	BLOCK_LED,
+	BLOCK_AVS_WRAP,
+	BLOCK_RGFS,
+	BLOCK_TGFS,
+	BLOCK_PTLD,
+	BLOCK_YPLD,
 	BLOCK_MISC_AEU,
 	BLOCK_BAR0_MAP,
 	MAX_BLOCK_ID
@@ -1783,9 +1813,9 @@ struct dbg_attn_reg_result {
 	__le32 data;
 #define DBG_ATTN_REG_RESULT_STS_ADDRESS_MASK	0xFFFFFF
 #define DBG_ATTN_REG_RESULT_STS_ADDRESS_SHIFT	0
-#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_MASK	0xFF
-#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_SHIFT	24
-	__le16 attn_idx_offset;
+#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_MASK	0xFF
+#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_SHIFT	24
+	__le16 block_attn_offset;
 	__le16 reserved;
 	__le32 sts_val;
 	__le32 mask_val;
@@ -1815,12 +1845,12 @@ struct dbg_mode_hdr {
 /* Attention register */
 struct dbg_attn_reg {
 	struct dbg_mode_hdr mode;
-	__le16 attn_idx_offset;
+	__le16 block_attn_offset;
 	__le32 data;
 #define DBG_ATTN_REG_STS_ADDRESS_MASK	0xFFFFFF
 #define DBG_ATTN_REG_STS_ADDRESS_SHIFT	0
-#define DBG_ATTN_REG_NUM_ATTN_IDX_MASK	0xFF
-#define DBG_ATTN_REG_NUM_ATTN_IDX_SHIFT	24
+#define DBG_ATTN_REG_NUM_REG_ATTN_MASK	0xFF
+#define DBG_ATTN_REG_NUM_REG_ATTN_SHIFT 24
 	__le32 sts_clr_address;
 	__le32 mask_address;
 };
@@ -2001,6 +2031,20 @@ enum dbg_bus_clients {
 	MAX_DBG_BUS_CLIENTS
 };
 
+enum dbg_bus_constraint_ops {
+	DBG_BUS_CONSTRAINT_OP_EQ,
+	DBG_BUS_CONSTRAINT_OP_NE,
+	DBG_BUS_CONSTRAINT_OP_LT,
+	DBG_BUS_CONSTRAINT_OP_LTC,
+	DBG_BUS_CONSTRAINT_OP_LE,
+	DBG_BUS_CONSTRAINT_OP_LEC,
+	DBG_BUS_CONSTRAINT_OP_GT,
+	DBG_BUS_CONSTRAINT_OP_GTC,
+	DBG_BUS_CONSTRAINT_OP_GE,
+	DBG_BUS_CONSTRAINT_OP_GEC,
+	MAX_DBG_BUS_CONSTRAINT_OPS
+};
+
 /* Debug Bus memory address */
 struct dbg_bus_mem_addr {
 	__le32 lo;
@@ -2092,10 +2136,18 @@ struct dbg_bus_data {
 					      * DBG_BUS_TARGET_ID_PCI.
 					      */
 	__le16 reserved;
-	struct dbg_bus_block_data blocks[80];/* Debug Bus data for each block */
+	struct dbg_bus_block_data blocks[88];/* Debug Bus data for each block */
 	struct dbg_bus_storm_data storms[6]; /* Debug Bus data for each block */
 };
 
+enum dbg_bus_filter_types {
+	DBG_BUS_FILTER_TYPE_OFF,
+	DBG_BUS_FILTER_TYPE_PRE,
+	DBG_BUS_FILTER_TYPE_POST,
+	DBG_BUS_FILTER_TYPE_ON,
+	MAX_DBG_BUS_FILTER_TYPES
+};
+
 /* Debug bus frame modes */
 enum dbg_bus_frame_modes {
 	DBG_BUS_FRAME_MODE_0HW_4ST = 0, /* 0 HW dwords, 4 Storm dwords */
@@ -2104,6 +2156,40 @@ enum dbg_bus_frame_modes {
 	MAX_DBG_BUS_FRAME_MODES
 };
 
+enum dbg_bus_input_types {
+	DBG_BUS_INPUT_TYPE_STORM,
+	DBG_BUS_INPUT_TYPE_BLOCK,
+	MAX_DBG_BUS_INPUT_TYPES
+};
+
+enum dbg_bus_other_engine_modes {
+	DBG_BUS_OTHER_ENGINE_MODE_NONE,
+	DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_TX,
+	DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_RX,
+	DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_TX,
+	DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_RX,
+	MAX_DBG_BUS_OTHER_ENGINE_MODES
+};
+
+enum dbg_bus_post_trigger_types {
+	DBG_BUS_POST_TRIGGER_RECORD,
+	DBG_BUS_POST_TRIGGER_DROP,
+	MAX_DBG_BUS_POST_TRIGGER_TYPES
+};
+
+enum dbg_bus_pre_trigger_types {
+	DBG_BUS_PRE_TRIGGER_START_FROM_ZERO,
+	DBG_BUS_PRE_TRIGGER_NUM_CHUNKS,
+	DBG_BUS_PRE_TRIGGER_DROP,
+	MAX_DBG_BUS_PRE_TRIGGER_TYPES
+};
+
+enum dbg_bus_semi_frame_modes {
+	DBG_BUS_SEMI_FRAME_MODE_0SLOW_4FAST = 0,
+	DBG_BUS_SEMI_FRAME_MODE_4SLOW_0FAST = 3,
+	MAX_DBG_BUS_SEMI_FRAME_MODES
+};
+
 /* Debug bus states */
 enum dbg_bus_states {
 	DBG_BUS_STATE_IDLE, /* debug bus idle state (not recording) */
@@ -2115,6 +2201,19 @@ enum dbg_bus_states {
 	MAX_DBG_BUS_STATES
 };
 
+enum dbg_bus_storm_modes {
+	DBG_BUS_STORM_MODE_PRINTF,
+	DBG_BUS_STORM_MODE_PRAM_ADDR,
+	DBG_BUS_STORM_MODE_DRA_RW,
+	DBG_BUS_STORM_MODE_DRA_W,
+	DBG_BUS_STORM_MODE_LD_ST_ADDR,
+	DBG_BUS_STORM_MODE_DRA_FSM,
+	DBG_BUS_STORM_MODE_RH,
+	DBG_BUS_STORM_MODE_FOC,
+	DBG_BUS_STORM_MODE_EXT_STORE,
+	MAX_DBG_BUS_STORM_MODES
+};
+
 /* Debug bus target IDs */
 enum dbg_bus_targets {
 	/* records debug bus to DBG block internal buffer */
@@ -2128,13 +2227,10 @@ enum dbg_bus_targets {
 
 /* GRC Dump data */
 struct dbg_grc_data {
-	__le32 param_val[40]; /* Value of each GRC parameter. Array size must
-			       * match the enum dbg_grc_params.
-			       */
-	u8 param_set_by_user[40]; /* Indicates for each GRC parameter if it was
-				   * set by the user (0/1). Array size must
-				   * match the enum dbg_grc_params.
-				   */
+	u8 params_initialized;
+	u8 reserved1;
+	__le16 reserved2;
+	__le32 param_val[48];
 };
 
 /* Debug GRC params */
@@ -2181,6 +2277,8 @@ enum dbg_grc_params {
 	DBG_GRC_PARAM_PARITY_SAFE,
 	DBG_GRC_PARAM_DUMP_CM, /* dump CM memories (0/1) */
 	DBG_GRC_PARAM_DUMP_PHY, /* dump PHY memories (0/1) */
+	DBG_GRC_PARAM_NO_MCP,
+	DBG_GRC_PARAM_NO_FW_VER,
 	MAX_DBG_GRC_PARAMS
 };
 
@@ -2280,7 +2378,7 @@ struct dbg_tools_data {
 	struct dbg_bus_data bus; /* Debug Bus data */
 	struct idle_chk_data idle_chk; /* Idle Check data */
 	u8 mode_enable[40]; /* Indicates if a mode is enabled (0/1) */
-	u8 block_in_reset[80]; /* Indicates if a block is in reset state (0/1).
+	u8 block_in_reset[88]; /* Indicates if a block is in reset state (0/1).
 				*/
 	u8 chip_id; /* Chip ID (from enum chip_ids) */
 	u8 platform_id; /* Platform ID (from enum platform_ids) */
@@ -2404,7 +2502,7 @@ struct fw_info_location {
 
 enum init_modes {
 	MODE_RESERVED,
-	MODE_BB_B0,
+	MODE_BB,
 	MODE_K2,
 	MODE_ASIC,
 	MODE_RESERVED2,
@@ -2418,7 +2516,6 @@ enum init_modes {
 	MODE_PORTS_PER_ENG_2,
 	MODE_PORTS_PER_ENG_4,
 	MODE_100G,
-	MODE_40G,
 	MODE_RESERVED6,
 	MAX_INIT_MODES
 };
@@ -2686,6 +2783,13 @@ struct iro {
  */
 enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr);
 /**
+ * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their
+ *	default value.
+ *
+ * @param p_hwfn		- HW device data
+ */
+void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn);
+/**
  * @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for
  *	GRC Dump.
  *
@@ -3369,6 +3473,11 @@ void qed_set_geneve_dest_port(struct qed_hwfn *p_hwfn,
 void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 			   struct qed_ptt *p_ptt,
 			   bool eth_geneve_enable, bool ip_geneve_enable);
+void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn,
+			      struct qed_ptt *p_ptt, u16 pf_id);
+void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			     u16 pf_id, bool tcp, bool udp,
+			     bool ipv4, bool ipv6);
 
 #define	YSTORM_FLOW_CONTROL_MODE_OFFSET			(IRO[0].base)
 #define	YSTORM_FLOW_CONTROL_MODE_SIZE			(IRO[0].size)
@@ -3418,7 +3527,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 #define	MSTORM_TPA_TIMEOUT_US_SIZE			(IRO[21].size)
 #define	MSTORM_ETH_PF_STAT_OFFSET(pf_id) \
 	(IRO[22].base + ((pf_id) * IRO[22].m1))
-#define	MSTORM_ETH_PF_STAT_SIZE				(IRO[21].size)
+#define	MSTORM_ETH_PF_STAT_SIZE				(IRO[22].size)
 #define	USTORM_QUEUE_STAT_OFFSET(stat_counter_id) \
 	(IRO[23].base + ((stat_counter_id) * IRO[23].m1))
 #define	USTORM_QUEUE_STAT_SIZE				(IRO[23].size)
@@ -3482,7 +3591,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 
 static const struct iro iro_arr[47] = {
 	{0x0, 0x0, 0x0, 0x0, 0x8},
-	{0x4cb0, 0x78, 0x0, 0x0, 0x78},
+	{0x4cb0, 0x80, 0x0, 0x0, 0x80},
 	{0x6318, 0x20, 0x0, 0x0, 0x20},
 	{0xb00, 0x8, 0x0, 0x0, 0x4},
 	{0xa80, 0x8, 0x0, 0x0, 0x4},
@@ -3521,13 +3630,13 @@ static const struct iro iro_arr[47] = {
 	{0xd888, 0x38, 0x0, 0x0, 0x24},
 	{0x12c38, 0x10, 0x0, 0x0, 0x8},
 	{0x11aa0, 0x38, 0x0, 0x0, 0x18},
-	{0xa8c0, 0x30, 0x0, 0x0, 0x10},
-	{0x86f8, 0x28, 0x0, 0x0, 0x18},
+	{0xa8c0, 0x38, 0x0, 0x0, 0x10},
+	{0x86f8, 0x30, 0x0, 0x0, 0x18},
 	{0x101f8, 0x10, 0x0, 0x0, 0x10},
 	{0xdd08, 0x48, 0x0, 0x0, 0x38},
 	{0x10660, 0x20, 0x0, 0x0, 0x20},
 	{0x2b80, 0x80, 0x0, 0x0, 0x10},
-	{0x5000, 0x10, 0x0, 0x0, 0x10},
+	{0x5020, 0x10, 0x0, 0x0, 0x10},
 };
 
 /* Runtime array offsets */
@@ -4595,6 +4704,12 @@ enum eth_ipv4_frag_type {
 	MAX_ETH_IPV4_FRAG_TYPE
 };
 
+enum eth_ip_type {
+	ETH_IPV4,
+	ETH_IPV6,
+	MAX_ETH_IP_TYPE
+};
+
 enum eth_ramrod_cmd_id {
 	ETH_RAMROD_UNUSED,
 	ETH_RAMROD_VPORT_START,
@@ -4752,6 +4867,18 @@ struct eth_vport_tx_mode {
 	__le16 reserved2[3];
 };
 
+enum gft_filter_update_action {
+	GFT_ADD_FILTER,
+	GFT_DELETE_FILTER,
+	MAX_GFT_FILTER_UPDATE_ACTION
+};
+
+enum gft_logic_filter_type {
+	GFT_FILTER_TYPE,
+	RFS_FILTER_TYPE,
+	MAX_GFT_LOGIC_FILTER_TYPE
+};
+
 /* Ramrod data for rx queue start ramrod */
 struct rx_queue_start_ramrod_data {
 	__le16 rx_queue_id;
@@ -4822,6 +4949,16 @@ struct rx_udp_filter_data {
 	__le32 tenant_id;
 };
 
+struct rx_update_gft_filter_data {
+	struct regpair pkt_hdr_addr;
+	__le16 pkt_hdr_length;
+	__le16 rx_qid_or_action_icid;
+	u8 vport_id;
+	u8 filter_type;
+	u8 filter_action;
+	u8 reserved;
+};
+
 /* Ramrod data for rx queue start ramrod */
 struct tx_queue_start_ramrod_data {
 	__le16 sb_id;
@@ -4944,7 +5081,10 @@ struct vport_update_ramrod_data_cmn {
 	u8 update_mtu_flg;
 
 	__le16 mtu;
-	u8 reserved[2];
+	u8 update_ctl_frame_checks_en_flg;
+	u8 ctl_frame_mac_check_en;
+	u8 ctl_frame_ethtype_check_en;
+	u8 reserved[15];
 };
 
 struct vport_update_ramrod_mcast {
@@ -4962,6 +5102,652 @@ struct vport_update_ramrod_data {
 	struct eth_vport_rss_config rss_config;
 };
 
+struct gft_cam_line {
+	__le32 camline;
+#define GFT_CAM_LINE_VALID_MASK		0x1
+#define GFT_CAM_LINE_VALID_SHIFT	0
+#define GFT_CAM_LINE_DATA_MASK		0x3FFF
+#define GFT_CAM_LINE_DATA_SHIFT		1
+#define GFT_CAM_LINE_MASK_BITS_MASK	0x3FFF
+#define GFT_CAM_LINE_MASK_BITS_SHIFT	15
+#define GFT_CAM_LINE_RESERVED1_MASK	0x7
+#define GFT_CAM_LINE_RESERVED1_SHIFT	29
+};
+
+struct gft_cam_line_mapped {
+	__le32 camline;
+#define GFT_CAM_LINE_MAPPED_VALID_MASK				0x1
+#define GFT_CAM_LINE_MAPPED_VALID_SHIFT				0
+#define GFT_CAM_LINE_MAPPED_IP_VERSION_MASK			0x1
+#define GFT_CAM_LINE_MAPPED_IP_VERSION_SHIFT			1
+#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_MASK		0x1
+#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_SHIFT		2
+#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK		0xF
+#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_SHIFT		3
+#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_MASK			0xF
+#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_SHIFT			7
+#define GFT_CAM_LINE_MAPPED_PF_ID_MASK				0xF
+#define GFT_CAM_LINE_MAPPED_PF_ID_SHIFT				11
+#define GFT_CAM_LINE_MAPPED_IP_VERSION_MASK_MASK		0x1
+#define GFT_CAM_LINE_MAPPED_IP_VERSION_MASK_SHIFT		15
+#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_MASK_MASK		0x1
+#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_MASK_SHIFT	16
+#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK_MASK	0xF
+#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK_SHIFT	17
+#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_MASK_MASK		0xF
+#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_MASK_SHIFT		21
+#define GFT_CAM_LINE_MAPPED_PF_ID_MASK_MASK			0xF
+#define GFT_CAM_LINE_MAPPED_PF_ID_MASK_SHIFT			25
+#define GFT_CAM_LINE_MAPPED_RESERVED1_MASK			0x7
+#define GFT_CAM_LINE_MAPPED_RESERVED1_SHIFT			29
+};
+
+union gft_cam_line_union {
+	struct gft_cam_line cam_line;
+	struct gft_cam_line_mapped cam_line_mapped;
+};
+
+enum gft_profile_ip_version {
+	GFT_PROFILE_IPV4 = 0,
+	GFT_PROFILE_IPV6 = 1,
+	MAX_GFT_PROFILE_IP_VERSION
+};
+
+enum gft_profile_upper_protocol_type {
+	GFT_PROFILE_ROCE_PROTOCOL = 0,
+	GFT_PROFILE_RROCE_PROTOCOL = 1,
+	GFT_PROFILE_FCOE_PROTOCOL = 2,
+	GFT_PROFILE_ICMP_PROTOCOL = 3,
+	GFT_PROFILE_ARP_PROTOCOL = 4,
+	GFT_PROFILE_USER_TCP_SRC_PORT_1_INNER = 5,
+	GFT_PROFILE_USER_TCP_DST_PORT_1_INNER = 6,
+	GFT_PROFILE_TCP_PROTOCOL = 7,
+	GFT_PROFILE_USER_UDP_DST_PORT_1_INNER = 8,
+	GFT_PROFILE_USER_UDP_DST_PORT_2_OUTER = 9,
+	GFT_PROFILE_UDP_PROTOCOL = 10,
+	GFT_PROFILE_USER_IP_1_INNER = 11,
+	GFT_PROFILE_USER_IP_2_OUTER = 12,
+	GFT_PROFILE_USER_ETH_1_INNER = 13,
+	GFT_PROFILE_USER_ETH_2_OUTER = 14,
+	GFT_PROFILE_RAW = 15,
+	MAX_GFT_PROFILE_UPPER_PROTOCOL_TYPE
+};
+
+struct gft_ram_line {
+	__le32 low32bits;
+#define GFT_RAM_LINE_VLAN_SELECT_MASK			0x3
+#define GFT_RAM_LINE_VLAN_SELECT_SHIFT			0
+#define GFT_RAM_LINE_TUNNEL_ENTROPHY_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_ENTROPHY_SHIFT		2
+#define GFT_RAM_LINE_TUNNEL_TTL_EQUAL_ONE_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_TTL_EQUAL_ONE_SHIFT		3
+#define GFT_RAM_LINE_TUNNEL_TTL_MASK			0x1
+#define GFT_RAM_LINE_TUNNEL_TTL_SHIFT			4
+#define GFT_RAM_LINE_TUNNEL_ETHERTYPE_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_ETHERTYPE_SHIFT		5
+#define GFT_RAM_LINE_TUNNEL_DST_PORT_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_DST_PORT_SHIFT		6
+#define GFT_RAM_LINE_TUNNEL_SRC_PORT_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_SRC_PORT_SHIFT		7
+#define GFT_RAM_LINE_TUNNEL_DSCP_MASK			0x1
+#define GFT_RAM_LINE_TUNNEL_DSCP_SHIFT			8
+#define GFT_RAM_LINE_TUNNEL_OVER_IP_PROTOCOL_MASK	0x1
+#define GFT_RAM_LINE_TUNNEL_OVER_IP_PROTOCOL_SHIFT	9
+#define GFT_RAM_LINE_TUNNEL_DST_IP_MASK			0x1
+#define GFT_RAM_LINE_TUNNEL_DST_IP_SHIFT		10
+#define GFT_RAM_LINE_TUNNEL_SRC_IP_MASK			0x1
+#define GFT_RAM_LINE_TUNNEL_SRC_IP_SHIFT		11
+#define GFT_RAM_LINE_TUNNEL_PRIORITY_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_PRIORITY_SHIFT		12
+#define GFT_RAM_LINE_TUNNEL_PROVIDER_VLAN_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_PROVIDER_VLAN_SHIFT		13
+#define GFT_RAM_LINE_TUNNEL_VLAN_MASK			0x1
+#define GFT_RAM_LINE_TUNNEL_VLAN_SHIFT			14
+#define GFT_RAM_LINE_TUNNEL_DST_MAC_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_DST_MAC_SHIFT		15
+#define GFT_RAM_LINE_TUNNEL_SRC_MAC_MASK		0x1
+#define GFT_RAM_LINE_TUNNEL_SRC_MAC_SHIFT		16
+#define GFT_RAM_LINE_TTL_EQUAL_ONE_MASK			0x1
+#define GFT_RAM_LINE_TTL_EQUAL_ONE_SHIFT		17
+#define GFT_RAM_LINE_TTL_MASK				0x1
+#define GFT_RAM_LINE_TTL_SHIFT				18
+#define GFT_RAM_LINE_ETHERTYPE_MASK			0x1
+#define GFT_RAM_LINE_ETHERTYPE_SHIFT			19
+#define GFT_RAM_LINE_RESERVED0_MASK			0x1
+#define GFT_RAM_LINE_RESERVED0_SHIFT			20
+#define GFT_RAM_LINE_TCP_FLAG_FIN_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_FIN_SHIFT			21
+#define GFT_RAM_LINE_TCP_FLAG_SYN_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_SYN_SHIFT			22
+#define GFT_RAM_LINE_TCP_FLAG_RST_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_RST_SHIFT			23
+#define GFT_RAM_LINE_TCP_FLAG_PSH_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_PSH_SHIFT			24
+#define GFT_RAM_LINE_TCP_FLAG_ACK_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_ACK_SHIFT			25
+#define GFT_RAM_LINE_TCP_FLAG_URG_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_URG_SHIFT			26
+#define GFT_RAM_LINE_TCP_FLAG_ECE_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_ECE_SHIFT			27
+#define GFT_RAM_LINE_TCP_FLAG_CWR_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_CWR_SHIFT			28
+#define GFT_RAM_LINE_TCP_FLAG_NS_MASK			0x1
+#define GFT_RAM_LINE_TCP_FLAG_NS_SHIFT			29
+#define GFT_RAM_LINE_DST_PORT_MASK			0x1
+#define GFT_RAM_LINE_DST_PORT_SHIFT			30
+#define GFT_RAM_LINE_SRC_PORT_MASK			0x1
+#define GFT_RAM_LINE_SRC_PORT_SHIFT			31
+	__le32 high32bits;
+#define GFT_RAM_LINE_DSCP_MASK				0x1
+#define GFT_RAM_LINE_DSCP_SHIFT				0
+#define GFT_RAM_LINE_OVER_IP_PROTOCOL_MASK		0x1
+#define GFT_RAM_LINE_OVER_IP_PROTOCOL_SHIFT		1
+#define GFT_RAM_LINE_DST_IP_MASK			0x1
+#define GFT_RAM_LINE_DST_IP_SHIFT			2
+#define GFT_RAM_LINE_SRC_IP_MASK			0x1
+#define GFT_RAM_LINE_SRC_IP_SHIFT			3
+#define GFT_RAM_LINE_PRIORITY_MASK			0x1
+#define GFT_RAM_LINE_PRIORITY_SHIFT			4
+#define GFT_RAM_LINE_PROVIDER_VLAN_MASK			0x1
+#define GFT_RAM_LINE_PROVIDER_VLAN_SHIFT		5
+#define GFT_RAM_LINE_VLAN_MASK				0x1
+#define GFT_RAM_LINE_VLAN_SHIFT				6
+#define GFT_RAM_LINE_DST_MAC_MASK			0x1
+#define GFT_RAM_LINE_DST_MAC_SHIFT			7
+#define GFT_RAM_LINE_SRC_MAC_MASK			0x1
+#define GFT_RAM_LINE_SRC_MAC_SHIFT			8
+#define GFT_RAM_LINE_TENANT_ID_MASK			0x1
+#define GFT_RAM_LINE_TENANT_ID_SHIFT			9
+#define GFT_RAM_LINE_RESERVED1_MASK			0x3FFFFF
+#define GFT_RAM_LINE_RESERVED1_SHIFT			10
+};
+
+struct mstorm_eth_conn_ag_ctx {
+	u8 byte0;
+	u8 byte1;
+	u8 flags0;
+#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0
+#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT         1
+#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK	0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT          2
+#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK	0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT          4
+#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK	0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT          6
+	u8 flags1;
+#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT        0
+#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT        1
+#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT        2
+#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT      3
+#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT      4
+#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT      5
+#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT      6
+#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT      7
+	__le16 word0;
+	__le16 word1;
+	__le32 reg0;
+	__le32 reg1;
+};
+
+struct xstorm_eth_conn_agctxdq_ext_ldpart {
+	u8 reserved0;
+	u8 eth_state;
+	u8 flags0;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_SHIFT           0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_SHIFT              1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_SHIFT              2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_SHIFT           3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_SHIFT              4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_SHIFT              5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_SHIFT              6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_SHIFT              7
+	u8 flags1;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_SHIFT              0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_SHIFT              1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_SHIFT              2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_SHIFT                  3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_SHIFT                  4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_SHIFT                  5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_SHIFT         6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_SHIFT           7
+	u8 flags2;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_SHIFT                    0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_SHIFT                    2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_SHIFT                    4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_SHIFT                    6
+	u8 flags3;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_SHIFT                    0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_SHIFT                    2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_SHIFT                    4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_SHIFT                    6
+	u8 flags4;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_SHIFT                    0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_SHIFT                    2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_SHIFT                   4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_SHIFT                   6
+	u8 flags5;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_SHIFT                   0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_SHIFT                   2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_SHIFT                   4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_SHIFT                   6
+	u8 flags6;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_SHIFT       0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_SHIFT       2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_SHIFT                  4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_SHIFT           6
+	u8 flags7;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_SHIFT             2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_SHIFT              4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_SHIFT                  6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_SHIFT                  7
+	u8 flags8;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_SHIFT                  0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_SHIFT                  1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_SHIFT                  2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_SHIFT                  3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_SHIFT                  4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_SHIFT                  5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_SHIFT                  6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_SHIFT                  7
+	u8 flags9;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_SHIFT                 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_SHIFT                 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_SHIFT                 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_SHIFT                 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_SHIFT                 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_SHIFT                 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_SHIFT    6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_SHIFT    7
+	u8 flags10;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_SHIFT        1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_SHIFT            2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_SHIFT             3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_SHIFT           4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_SHIFT             6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_SHIFT             7
+	u8 flags11;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_SHIFT             0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_SHIFT             1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_SHIFT         2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_SHIFT                3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_SHIFT                4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_SHIFT                5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_SHIFT           6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_SHIFT                7
+	u8 flags12;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_SHIFT               1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_SHIFT           2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_SHIFT           3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_SHIFT               4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_SHIFT               5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_SHIFT               6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_SHIFT               7
+	u8 flags13;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_SHIFT               1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_SHIFT           2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_SHIFT           3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_SHIFT           4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_SHIFT           5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_SHIFT           6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_SHIFT           7
+	u8 flags14;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_SHIFT       0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_SHIFT     1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_SHIFT   2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_SHIFT   3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_SHIFT         4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_SHIFT       5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_SHIFT             6
+	u8 edpm_event_id;
+	__le16 physical_q0;
+	__le16 quota;
+	__le16 edpm_num_bds;
+	__le16 tx_bd_cons;
+	__le16 tx_bd_prod;
+	__le16 tx_class;
+	__le16 conn_dpi;
+	u8 byte3;
+	u8 byte4;
+	u8 byte5;
+	u8 byte6;
+	__le32 reg0;
+	__le32 reg1;
+	__le32 reg2;
+	__le32 reg3;
+	__le32 reg4;
+};
+
+struct xstorm_eth_hw_conn_ag_ctx {
+	u8 reserved0;
+	u8 eth_state;
+	u8 flags0;
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT           0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT              1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT              2
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT           3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT              4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT              5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT              6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT              7
+	u8 flags1;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT              0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT              1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT              2
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT                  3
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_SHIFT                  4
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_SHIFT                  5
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT         6
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT           7
+	u8 flags2;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT                    0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT                    2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT                    4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT                    6
+	u8 flags3;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT                    0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT                    2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT                    4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT                    6
+	u8 flags4;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT                    0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT                    2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT                   4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT                   6
+	u8 flags5;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT                   0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT                   2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT                   4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT                   6
+	u8 flags6;
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT       0
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT       2
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT                  4
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT           6
+	u8 flags7;
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT             2
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT              4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT                  6
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT                  7
+	u8 flags8;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT                  0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT                  1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT                  2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT                  3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT                  4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT                  5
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT                  6
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT                  7
+	u8 flags9;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT                 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT                 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT                 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT                 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT                 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT                 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT    6
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT    7
+	u8 flags10;
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT        1
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT            2
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT             3
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT           4
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT             6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT             7
+	u8 flags11;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT             0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT             1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT         2
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT                3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT                4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT                5
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT           6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT                7
+	u8 flags12;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT               1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT           2
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT           3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT               4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT               5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT               6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT               7
+	u8 flags13;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT               1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT           2
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT           3
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT           4
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT           5
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT           6
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT           7
+	u8 flags14;
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT       0
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT     1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT   2
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT   3
+#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT         4
+#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT       5
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT             6
+	u8 edpm_event_id;
+	__le16 physical_q0;
+	__le16 quota;
+	__le16 edpm_num_bds;
+	__le16 tx_bd_cons;
+	__le16 tx_bd_prod;
+	__le16 tx_class;
+	__le16 conn_dpi;
+};
+
 struct mstorm_rdma_task_st_ctx {
 	struct regpair temp[4];
 };
@@ -6165,7 +6951,7 @@ struct ystorm_roce_conn_st_ctx {
 };
 
 struct xstorm_roce_conn_st_ctx {
-	struct regpair temp[22];
+	struct regpair temp[24];
 };
 
 struct tstorm_roce_conn_st_ctx {
@@ -6220,7 +7006,7 @@ struct roce_create_qp_req_ramrod_data {
 	__le16 mtu;
 	__le16 pd;
 	__le16 sq_num_pages;
-	__le16 reseved2;
+	__le16 low_latency_phy_queue;
 	struct regpair sq_pbl_addr;
 	struct regpair orq_pbl_addr;
 	__le16 local_mac_addr[3];
@@ -6234,7 +7020,7 @@ struct roce_create_qp_req_ramrod_data {
 	u8 stats_counter_id;
 	u8 reserved3[7];
 	__le32 cq_cid;
-	__le16 physical_queue0;
+	__le16 regular_latency_phy_queue;
 	__le16 dpi;
 };
 
@@ -6282,15 +7068,16 @@ struct roce_create_qp_resp_ramrod_data {
 	__le32 dst_gid[4];
 	struct regpair qp_handle_for_cqe;
 	struct regpair qp_handle_for_async;
-	__le32 reserved2[2];
+	__le16 low_latency_phy_queue;
+	u8 reserved2[6];
 	__le32 cq_cid;
-	__le16 physical_queue0;
+	__le16 regular_latency_phy_queue;
 	__le16 dpi;
 };
 
 struct roce_destroy_qp_req_output_params {
 	__le32 num_bound_mw;
-	__le32 reserved;
+	__le32 cq_prod;
 };
 
 struct roce_destroy_qp_req_ramrod_data {
@@ -6299,7 +7086,7 @@ struct roce_destroy_qp_req_ramrod_data {
 
 struct roce_destroy_qp_resp_output_params {
 	__le32 num_invalidated_mw;
-	__le32 reserved;
+	__le32 cq_prod;
 };
 
 struct roce_destroy_qp_resp_ramrod_data {
@@ -7426,6 +8213,7 @@ struct ystorm_fcoe_conn_st_ctx {
 	u8 fcp_rsp_size;
 	__le16 mss;
 	struct regpair reserved;
+	__le16 min_frame_size;
 	u8 protection_info_flags;
 #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_MASK  0x1
 #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_SHIFT 0
@@ -7444,7 +8232,6 @@ struct ystorm_fcoe_conn_st_ctx {
 #define YSTORM_FCOE_CONN_ST_CTX_RSRV_MASK                0x3F
 #define YSTORM_FCOE_CONN_ST_CTX_RSRV_SHIFT               2
 	u8 fcp_xfer_size;
-	u8 reserved3[2];
 };
 
 struct fcoe_vlan_fields {
@@ -8273,10 +9060,10 @@ struct xstorm_iscsi_conn_ag_ctx {
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK                    0x3
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT                   6
 	u8 flags7;
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK                    0x3
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT                   0
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_MASK                    0x3
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_SHIFT                   2
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK	0x3
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT        0
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK	0x3
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT        2
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK                   0x3
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT                  4
 #define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK                       0x1
@@ -8322,10 +9109,10 @@ struct xstorm_iscsi_conn_ag_ctx {
 #define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT                     0
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK                 0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT                1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK                 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT                2
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_MASK                 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT                3
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK	0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT     2
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK	0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT     3
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK                0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT               4
 #define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK        0x1
@@ -8335,8 +9122,8 @@ struct xstorm_iscsi_conn_ag_ctx {
 #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK    0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT   7
 	u8 flags11;
-#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK                     0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT                    0
+#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK	0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT              0
 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK                     0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT                    1
 #define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK                   0x1
@@ -8440,7 +9227,7 @@ struct xstorm_iscsi_conn_ag_ctx {
 	__le32 reg10;
 	__le32 reg11;
 	__le32 exp_stat_sn;
-	__le32 reg13;
+	__le32 ongoing_fast_rxmit_seq;
 	__le32 reg14;
 	__le32 reg15;
 	__le32 reg16;
@@ -8466,10 +9253,10 @@ struct tstorm_iscsi_conn_ag_ctx {
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK                0x3
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT               6
 	u8 flags1;
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1_MASK                0x3
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT               0
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2_MASK                0x3
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT               2
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK	0x3
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT      0
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK	0x3
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT      2
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK     0x3
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT    4
 #define TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK                0x3
@@ -8490,10 +9277,10 @@ struct tstorm_iscsi_conn_ag_ctx {
 #define TSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT              2
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK              0x1
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT             4
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK              0x1
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT             5
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK              0x1
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT             6
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK	0x1
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT   5
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK	0x1
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT   6
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK  0x1
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7
 	u8 flags4;
@@ -8539,7 +9326,7 @@ struct tstorm_iscsi_conn_ag_ctx {
 	__le32 reg6;
 	__le32 reg7;
 	__le32 reg8;
-	u8 byte2;
+	u8 cid_offload_cnt;
 	u8 byte3;
 	__le16 word0;
 };
@@ -8831,11 +9618,24 @@ struct eth_stats {
 	u64 r511;
 	u64 r1023;
 	u64 r1518;
-	u64 r1522;
-	u64 r2047;
-	u64 r4095;
-	u64 r9216;
-	u64 r16383;
+
+	union {
+		struct {
+			u64 r1522;
+			u64 r2047;
+			u64 r4095;
+			u64 r9216;
+			u64 r16383;
+		} bb0;
+		struct {
+			u64 unused1;
+			u64 r1519_to_max;
+			u64 unused2;
+			u64 unused3;
+			u64 unused4;
+		} ah0;
+	} u0;
+
 	u64 rfcs;
 	u64 rxcf;
 	u64 rxpf;
@@ -8852,14 +9652,36 @@ struct eth_stats {
 	u64 t511;
 	u64 t1023;
 	u64 t1518;
-	u64 t2047;
-	u64 t4095;
-	u64 t9216;
-	u64 t16383;
+
+	union {
+		struct {
+			u64 t2047;
+			u64 t4095;
+			u64 t9216;
+			u64 t16383;
+		} bb1;
+		struct {
+			u64 t1519_to_max;
+			u64 unused6;
+			u64 unused7;
+			u64 unused8;
+		} ah1;
+	} u1;
+
 	u64 txpf;
 	u64 txpp;
-	u64 tlpiec;
-	u64 tncl;
+
+	union {
+		struct {
+			u64 tlpiec;
+			u64 tncl;
+		} bb2;
+		struct {
+			u64 unused9;
+			u64 unused10;
+		} ah2;
+	} u2;
+
 	u64 rbyte;
 	u64 rxuca;
 	u64 rxmca;
@@ -8943,12 +9765,12 @@ struct dcbx_ets_feature {
 #define DCBX_ETS_CBS_SHIFT	3
 #define DCBX_ETS_MAX_TCS_MASK	0x000000f0
 #define DCBX_ETS_MAX_TCS_SHIFT	4
-#define DCBX_ISCSI_OOO_TC_MASK	0x00000f00
-#define DCBX_ISCSI_OOO_TC_SHIFT	8
+#define DCBX_OOO_TC_MASK	0x00000f00
+#define DCBX_OOO_TC_SHIFT	8
 	u32 pri_tc_tbl[1];
-#define DCBX_ISCSI_OOO_TC	(4)
+#define DCBX_TCP_OOO_TC		(4)
 
-#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET	(DCBX_ISCSI_OOO_TC + 1)
+#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET	(DCBX_TCP_OOO_TC + 1)
 #define DCBX_CEE_STRICT_PRIORITY	0xf
 	u32 tc_bw_tbl[2];
 	u32 tc_tsa_tbl[2];
@@ -8957,6 +9779,9 @@ struct dcbx_ets_feature {
 #define DCBX_ETS_TSA_ETS	2
 };
 
+#define DCBX_TCP_OOO_TC			(4)
+#define DCBX_TCP_OOO_K2_4PORT_TC	(3)
+
 struct dcbx_app_priority_entry {
 	u32 entry;
 #define DCBX_APP_PRI_MAP_MASK		0x000000ff
@@ -9067,6 +9892,10 @@ struct dcb_dscp_map {
 struct public_global {
 	u32 max_path;
 	u32 max_ports;
+#define MODE_1P 1
+#define MODE_2P 2
+#define MODE_3P 3
+#define MODE_4P 4
 	u32 debug_mb_offset;
 	u32 phymod_dbg_mb_offset;
 	struct couple_mode_teaming cmt;
@@ -9248,9 +10077,11 @@ struct public_func {
 #define DRV_ID_PDA_COMP_VER_MASK	0x0000ffff
 #define DRV_ID_PDA_COMP_VER_SHIFT	0
 
+#define LOAD_REQ_HSI_VERSION		2
 #define DRV_ID_MCP_HSI_VER_MASK		0x00ff0000
 #define DRV_ID_MCP_HSI_VER_SHIFT	16
-#define DRV_ID_MCP_HSI_VER_CURRENT	(1 << DRV_ID_MCP_HSI_VER_SHIFT)
+#define DRV_ID_MCP_HSI_VER_CURRENT	(LOAD_REQ_HSI_VERSION << \
+					 DRV_ID_MCP_HSI_VER_SHIFT)
 
 #define DRV_ID_DRV_TYPE_MASK		0x7f000000
 #define DRV_ID_DRV_TYPE_SHIFT		24
@@ -9345,6 +10176,7 @@ enum resource_id_enum {
 	RESOURCE_NUM_RSS_ENGINES_E = 14,
 	RESOURCE_LL2_QUEUE_E = 15,
 	RESOURCE_RDMA_STATS_QUEUE_E = 16,
+	RESOURCE_BDQ_E = 17,
 	RESOURCE_MAX_NUM,
 	RESOURCE_NUM_INVALID = 0xFFFFFFFF
 };
@@ -9362,6 +10194,46 @@ struct resource_info {
 #define RESOURCE_ELEMENT_STRICT (1 << 0)
 };
 
+#define DRV_ROLE_NONE           0
+#define DRV_ROLE_PREBOOT        1
+#define DRV_ROLE_OS             2
+#define DRV_ROLE_KDUMP          3
+
+struct load_req_stc {
+	u32 drv_ver_0;
+	u32 drv_ver_1;
+	u32 fw_ver;
+	u32 misc0;
+#define LOAD_REQ_ROLE_MASK              0x000000FF
+#define LOAD_REQ_ROLE_SHIFT             0
+#define LOAD_REQ_LOCK_TO_MASK           0x0000FF00
+#define LOAD_REQ_LOCK_TO_SHIFT          8
+#define LOAD_REQ_LOCK_TO_DEFAULT        0
+#define LOAD_REQ_LOCK_TO_NONE           255
+#define LOAD_REQ_FORCE_MASK             0x000F0000
+#define LOAD_REQ_FORCE_SHIFT            16
+#define LOAD_REQ_FORCE_NONE             0
+#define LOAD_REQ_FORCE_PF               1
+#define LOAD_REQ_FORCE_ALL              2
+#define LOAD_REQ_FLAGS0_MASK            0x00F00000
+#define LOAD_REQ_FLAGS0_SHIFT           20
+#define LOAD_REQ_FLAGS0_AVOID_RESET     (0x1 << 0)
+};
+
+struct load_rsp_stc {
+	u32 drv_ver_0;
+	u32 drv_ver_1;
+	u32 fw_ver;
+	u32 misc0;
+#define LOAD_RSP_ROLE_MASK              0x000000FF
+#define LOAD_RSP_ROLE_SHIFT             0
+#define LOAD_RSP_HSI_MASK               0x0000FF00
+#define LOAD_RSP_HSI_SHIFT              8
+#define LOAD_RSP_FLAGS0_MASK            0x000F0000
+#define LOAD_RSP_FLAGS0_SHIFT           16
+#define LOAD_RSP_FLAGS0_DRV_EXISTS      (0x1 << 0)
+};
+
 union drv_union_data {
 	u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
 	struct mcp_mac wol_mac;
@@ -9393,6 +10265,7 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_LOAD_REQ			0x10000000
 #define DRV_MSG_CODE_LOAD_DONE			0x11000000
 #define DRV_MSG_CODE_INIT_HW			0x12000000
+#define DRV_MSG_CODE_CANCEL_LOAD_REQ            0x13000000
 #define DRV_MSG_CODE_UNLOAD_REQ			0x20000000
 #define DRV_MSG_CODE_UNLOAD_DONE		0x21000000
 #define DRV_MSG_CODE_INIT_PHY			0x22000000
@@ -9405,12 +10278,14 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE     0x31000000
 #define DRV_MSG_CODE_BW_UPDATE_ACK              0x32000000
 #define DRV_MSG_CODE_OV_UPDATE_MTU              0x33000000
+#define DRV_MSG_GET_RESOURCE_ALLOC_MSG		0x34000000
+#define DRV_MSG_SET_RESOURCE_VALUE_MSG		0x35000000
 #define DRV_MSG_CODE_OV_UPDATE_WOL              0x38000000
 #define DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE     0x39000000
 
 #define DRV_MSG_CODE_BW_UPDATE_ACK		0x32000000
 #define DRV_MSG_CODE_NIG_DRAIN			0x30000000
-#define DRV_MSG_GET_RESOURCE_ALLOC_MSG          0x34000000
+#define DRV_MSG_CODE_INITIATE_PF_FLR            0x02010000
 #define DRV_MSG_CODE_VF_DISABLED_DONE		0xc0000000
 #define DRV_MSG_CODE_CFG_VF_MSIX		0xc0010000
 #define DRV_MSG_CODE_NVM_GET_FILE_ATT		0x00030000
@@ -9436,6 +10311,33 @@ struct public_drv_mb {
 
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
 #define DRV_MSG_CODE_SET_LED_MODE		0x00200000
+#define DRV_MSG_CODE_RESOURCE_CMD	0x00230000
+
+#define RESOURCE_CMD_REQ_RESC_MASK		0x0000001F
+#define RESOURCE_CMD_REQ_RESC_SHIFT		0
+#define RESOURCE_CMD_REQ_OPCODE_MASK		0x000000E0
+#define RESOURCE_CMD_REQ_OPCODE_SHIFT		5
+#define RESOURCE_OPCODE_REQ			1
+#define RESOURCE_OPCODE_REQ_WO_AGING		2
+#define RESOURCE_OPCODE_REQ_W_AGING		3
+#define RESOURCE_OPCODE_RELEASE			4
+#define RESOURCE_OPCODE_FORCE_RELEASE		5
+#define RESOURCE_CMD_REQ_AGE_MASK		0x0000FF00
+#define RESOURCE_CMD_REQ_AGE_SHIFT		8
+
+#define RESOURCE_CMD_RSP_OWNER_MASK		0x000000FF
+#define RESOURCE_CMD_RSP_OWNER_SHIFT		0
+#define RESOURCE_CMD_RSP_OPCODE_MASK		0x00000700
+#define RESOURCE_CMD_RSP_OPCODE_SHIFT		8
+#define RESOURCE_OPCODE_GNT			1
+#define RESOURCE_OPCODE_BUSY			2
+#define RESOURCE_OPCODE_RELEASED		3
+#define RESOURCE_OPCODE_RELEASED_PREVIOUS	4
+#define RESOURCE_OPCODE_WRONG_OWNER		5
+#define RESOURCE_OPCODE_UNKNOWN_CMD		255
+
+#define RESOURCE_DUMP				0
+
 #define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL	0x002b0000
 #define DRV_MSG_CODE_OS_WOL			0x002e0000
 
@@ -9524,12 +10426,16 @@ struct public_drv_mb {
 
 	u32 fw_mb_header;
 #define FW_MSG_CODE_MASK			0xffff0000
+#define FW_MSG_CODE_UNSUPPORTED                 0x00000000
 #define FW_MSG_CODE_DRV_LOAD_ENGINE		0x10100000
 #define FW_MSG_CODE_DRV_LOAD_PORT		0x10110000
 #define FW_MSG_CODE_DRV_LOAD_FUNCTION		0x10120000
 #define FW_MSG_CODE_DRV_LOAD_REFUSED_PDA	0x10200000
-#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI	0x10210000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1	0x10210000
 #define FW_MSG_CODE_DRV_LOAD_REFUSED_DIAG	0x10220000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI        0x10230000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_REQUIRES_FORCE 0x10300000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_REJECT     0x10310000
 #define FW_MSG_CODE_DRV_LOAD_DONE		0x11100000
 #define FW_MSG_CODE_DRV_UNLOAD_ENGINE		0x20110000
 #define FW_MSG_CODE_DRV_UNLOAD_PORT		0x20120000
@@ -9549,6 +10455,10 @@ struct public_drv_mb {
 #define FW_MSG_SEQ_NUMBER_MASK			0x0000ffff
 
 	u32 fw_mb_param;
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_MASK	0x0000FFFF
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT	0
 
 	/* get pf rdma protocol command responce */
 #define FW_MB_PARAM_GET_PF_RDMA_NONE		0x0
@@ -9659,6 +10569,8 @@ struct nvm_cfg1_glob {
 #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G		0xC
 #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G		0xD
 #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G		0xE
+#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G		0xF
+
 	u32 e_lane_cfg1;
 	u32 e_lane_cfg2;
 	u32 f_lane_cfg1;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 899cad7f97ea..a05feb38c6ee 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -58,6 +58,7 @@ struct qed_ptt {
 	struct list_head	list_entry;
 	unsigned int		idx;
 	struct pxp_ptt_entry	pxp;
+	u8			hwfn_id;
 };
 
 struct qed_ptt_pool {
@@ -79,6 +80,7 @@ int qed_ptt_pool_alloc(struct qed_hwfn *p_hwfn)
 		p_pool->ptts[i].idx = i;
 		p_pool->ptts[i].pxp.offset = QED_BAR_INVALID_OFFSET;
 		p_pool->ptts[i].pxp.pretend.control = 0;
+		p_pool->ptts[i].hwfn_id = p_hwfn->my_id;
 		if (i >= RESERVED_PTT_MAX)
 			list_add(&p_pool->ptts[i].list_entry,
 				 &p_pool->free_list);
@@ -193,6 +195,11 @@ static u32 qed_set_ptt(struct qed_hwfn *p_hwfn,
 
 	offset = hw_addr - win_hw_addr;
 
+	if (p_ptt->hwfn_id != p_hwfn->my_id)
+		DP_NOTICE(p_hwfn,
+			  "ptt[%d] of hwfn[%02x] is used by hwfn[%02x]!\n",
+			  p_ptt->idx, p_ptt->hwfn_id, p_hwfn->my_id);
+
 	/* Verify the address is within the window */
 	if (hw_addr < win_hw_addr ||
 	    offset >= PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE) {
@@ -800,55 +807,3 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn,
-		  enum protocol_type proto, union qed_qm_pq_params *p_params)
-{
-	u16 pq_id = 0;
-
-	if ((proto == PROTOCOLID_CORE ||
-	     proto == PROTOCOLID_ETH ||
-	     proto == PROTOCOLID_ISCSI ||
-	     proto == PROTOCOLID_ROCE) && !p_params) {
-		DP_NOTICE(p_hwfn,
-			  "Protocol %d received NULL PQ params\n", proto);
-		return 0;
-	}
-
-	switch (proto) {
-	case PROTOCOLID_CORE:
-		if (p_params->core.tc == LB_TC)
-			pq_id = p_hwfn->qm_info.pure_lb_pq;
-		else if (p_params->core.tc == OOO_LB_TC)
-			pq_id = p_hwfn->qm_info.ooo_pq;
-		else
-			pq_id = p_hwfn->qm_info.offload_pq;
-		break;
-	case PROTOCOLID_ETH:
-		pq_id = p_params->eth.tc;
-		if (p_params->eth.is_vf)
-			pq_id += p_hwfn->qm_info.vf_queues_offset +
-				 p_params->eth.vf_id;
-		break;
-	case PROTOCOLID_ISCSI:
-		if (p_params->iscsi.q_idx == 1)
-			pq_id = p_hwfn->qm_info.pure_ack_pq;
-		break;
-	case PROTOCOLID_ROCE:
-		if (p_params->roce.dcqcn)
-			pq_id = p_params->roce.qpid;
-		else
-			pq_id = p_hwfn->qm_info.offload_pq;
-		if (pq_id > p_hwfn->qm_info.num_pf_rls)
-			pq_id = p_hwfn->qm_info.offload_pq;
-		break;
-	case PROTOCOLID_FCOE:
-		pq_id = p_hwfn->qm_info.offload_pq;
-		break;
-	default:
-		pq_id = 0;
-	}
-
-	pq_id = CM_TX_PQ_BASE + pq_id + RESC_START(p_hwfn, QED_PQ);
-
-	return pq_id;
-}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index 9277264d2e65..f2505c691c26 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -297,9 +297,6 @@ union qed_qm_pq_params {
 	} roce;
 };
 
-u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn,
-		  enum protocol_type proto, union qed_qm_pq_params *params);
-
 int qed_init_fw_data(struct qed_dev *cdev,
 		     const u8 *fw_data);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index d891a6852695..67200c5498ab 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -215,13 +215,6 @@ static void qed_cmdq_lines_voq_rt_init(struct qed_hwfn *p_hwfn,
 {
 	u32 qm_line_crd;
 
-	/* In A0 - Limit the size of pbf queue so that only 511 commands with
-	 * the minimum size of 4 (FCoE minimum size)
-	 */
-	bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev);
-
-	if (is_bb_a0)
-		cmdq_lines = min_t(u32, cmdq_lines, 1022);
 	qm_line_crd = QM_VOQ_LINE_CRD(cmdq_lines);
 	OVERWRITE_RT_REG(p_hwfn, PBF_CMDQ_LINES_RT_OFFSET(voq),
 			 (u32)cmdq_lines);
@@ -343,13 +336,11 @@ static void qed_tx_pq_map_rt_init(
 	u16 first_pq_group = p_params->start_pq / QM_PF_QUEUE_GROUP_SIZE;
 	u16 last_pq_group = (p_params->start_pq + num_pqs - 1) /
 			    QM_PF_QUEUE_GROUP_SIZE;
-	bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev);
 	u16 i, pq_id, pq_group;
 
 	/* a bit per Tx PQ indicating if the PQ is associated with a VF */
 	u32 tx_pq_vf_mask[MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE] = { 0 };
-	u32 tx_pq_vf_mask_width = is_bb_a0 ? 32 : QM_PF_QUEUE_GROUP_SIZE;
-	u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / tx_pq_vf_mask_width;
+	u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE;
 	u32 pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_pf_cids);
 	u32 vport_pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_vf_cids);
 	u32 mem_addr_4kb = base_mem_addr_4kb;
@@ -371,6 +362,10 @@ static void qed_tx_pq_map_rt_init(
 		bool is_vf_pq = (i >= p_params->num_pf_pqs);
 		struct qm_rf_pq_map tx_pq_map;
 
+		bool rl_valid = p_params->pq_params[i].rl_valid &&
+				(p_params->pq_params[i].vport_id <
+				 MAX_QM_GLOBAL_RLS);
+
 		/* update first Tx PQ of VPORT/TC */
 		u8 vport_id_in_pf = p_params->pq_params[i].vport_id -
 				    p_params->start_vport;
@@ -389,14 +384,18 @@ static void qed_tx_pq_map_rt_init(
 				     (p_params->pf_id <<
 				      QM_WFQ_VP_PQ_PF_SHIFT));
 		}
+
+		if (p_params->pq_params[i].rl_valid && !rl_valid)
+			DP_NOTICE(p_hwfn,
+				  "Invalid VPORT ID for rate limiter configuration");
 		/* fill PQ map entry */
 		memset(&tx_pq_map, 0, sizeof(tx_pq_map));
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_PQ_VALID, 1);
-		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_VALID,
-			  p_params->pq_params[i].rl_valid ? 1 : 0);
+		SET_FIELD(tx_pq_map.reg,
+			  QM_RF_PQ_MAP_RL_VALID, rl_valid ? 1 : 0);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VP_PQ_ID, first_tx_pq_id);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_ID,
-			  p_params->pq_params[i].rl_valid ?
+			  rl_valid ?
 			  p_params->pq_params[i].vport_id : 0);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VOQ, voq);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_WRR_WEIGHT_GROUP,
@@ -413,8 +412,9 @@ static void qed_tx_pq_map_rt_init(
 			/* if PQ is associated with a VF, add indication
 			 * to PQ VF mask
 			 */
-			tx_pq_vf_mask[pq_id / tx_pq_vf_mask_width] |=
-				(1 << (pq_id % tx_pq_vf_mask_width));
+			tx_pq_vf_mask[pq_id /
+				      QM_PF_QUEUE_GROUP_SIZE] |=
+			    BIT((pq_id % QM_PF_QUEUE_GROUP_SIZE));
 			mem_addr_4kb += vport_pq_mem_4kb;
 		} else {
 			mem_addr_4kb += pq_mem_4kb;
@@ -480,8 +480,8 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn,
 	if (p_params->pf_id < MAX_NUM_PFS_BB)
 		crd_reg_offset = QM_REG_WFQPFCRD_RT_OFFSET;
 	else
-		crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET +
-				 (p_params->pf_id % MAX_NUM_PFS_BB);
+		crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET;
+	crd_reg_offset += p_params->pf_id % MAX_NUM_PFS_BB;
 
 	inc_val = QM_WFQ_INC_VAL(p_params->pf_wfq);
 	if (!inc_val || inc_val > QM_WFQ_MAX_INC_VAL) {
@@ -498,11 +498,11 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn,
 				 QM_WFQ_CRD_REG_SIGN_BIT);
 	}
 
-	STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id,
-		     inc_val);
 	STORE_RT_REG(p_hwfn,
 		     QM_REG_WFQPFUPPERBOUND_RT_OFFSET + p_params->pf_id,
 		     QM_WFQ_UPPER_BOUND | QM_WFQ_CRD_REG_SIGN_BIT);
+	STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id,
+		     inc_val);
 	return 0;
 }
 
@@ -576,6 +576,12 @@ static int qed_vport_rl_rt_init(struct qed_hwfn *p_hwfn,
 {
 	u8 i, vport_id;
 
+	if (start_vport + num_vports >= MAX_QM_GLOBAL_RLS) {
+		DP_NOTICE(p_hwfn,
+			  "Invalid VPORT ID for rate limiter configuration");
+		return -1;
+	}
+
 	/* go over all PF VPORTs */
 	for (i = 0, vport_id = start_vport; i < num_vports; i++, vport_id++) {
 		u32 inc_val = QM_RL_INC_VAL(vport_params[i].vport_rl);
@@ -785,6 +791,12 @@ int qed_init_vport_rl(struct qed_hwfn *p_hwfn,
 {
 	u32 inc_val = QM_RL_INC_VAL(vport_rl);
 
+	if (vport_id >= MAX_QM_GLOBAL_RLS) {
+		DP_NOTICE(p_hwfn,
+			  "Invalid VPORT ID for rate limiter configuration");
+		return -1;
+	}
+
 	if (inc_val > QM_RL_MAX_INC_VAL) {
 		DP_NOTICE(p_hwfn, "Invalid VPORT rate-limit configuration");
 		return -1;
@@ -940,12 +952,6 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 	       eth_geneve_enable ? 1 : 0);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_IP_ENABLE, ip_geneve_enable ? 1 : 0);
 
-	/* comp ver */
-	reg_val = (ip_geneve_enable || eth_geneve_enable) ? 1 : 0;
-	qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_COMP_VER, reg_val);
-	qed_wr(p_hwfn, p_ptt, PBF_REG_NGE_COMP_VER, reg_val);
-	qed_wr(p_hwfn, p_ptt, PRS_REG_NGE_COMP_VER, reg_val);
-
 	/* EDPM with geneve tunnel not supported in BB_B0 */
 	if (QED_IS_BB_B0(p_hwfn->cdev))
 		return;
@@ -955,3 +961,132 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, DORQ_REG_L2_EDPM_TUNNEL_NGE_IP_EN,
 	       ip_geneve_enable ? 1 : 0);
 }
+
+#define T_ETH_PACKET_MATCH_RFS_EVENTID 25
+#define PARSER_ETH_CONN_CM_HDR (0x0)
+#define CAM_LINE_SIZE sizeof(u32)
+#define RAM_LINE_SIZE sizeof(u64)
+#define REG_SIZE sizeof(u32)
+
+void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn,
+			      struct qed_ptt *p_ptt, u16 pf_id)
+{
+	union gft_cam_line_union camline;
+	struct gft_ram_line ramline;
+	u32 *p_ramline, i;
+
+	p_ramline = (u32 *)&ramline;
+
+	/*stop using gft logic */
+	qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 0);
+	qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, 0x0);
+	memset(&camline, 0, sizeof(union gft_cam_line_union));
+	qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id,
+	       camline.cam_line_mapped.camline);
+	memset(&ramline, 0, sizeof(union gft_cam_line_union));
+
+	for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) {
+		u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM;
+
+		hw_addr += (RAM_LINE_SIZE * pf_id + i * REG_SIZE);
+
+		qed_wr(p_hwfn, p_ptt, hw_addr, *(p_ramline + i));
+	}
+}
+
+void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			     u16 pf_id, bool tcp, bool udp,
+			     bool ipv4, bool ipv6)
+{
+	u32 rfs_cm_hdr_event_id, *p_ramline;
+	union gft_cam_line_union camline;
+	struct gft_ram_line ramline;
+	int i;
+
+	rfs_cm_hdr_event_id = qed_rd(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT);
+	p_ramline = (u32 *)&ramline;
+
+	if (!ipv6 && !ipv4)
+		DP_NOTICE(p_hwfn,
+			  "set_rfs_mode_enable: must accept at least on of - ipv4 or ipv6");
+	if (!tcp && !udp)
+		DP_NOTICE(p_hwfn,
+			  "set_rfs_mode_enable: must accept at least on of - udp or tcp");
+
+	rfs_cm_hdr_event_id |= T_ETH_PACKET_MATCH_RFS_EVENTID <<
+					PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT;
+	rfs_cm_hdr_event_id |= PARSER_ETH_CONN_CM_HDR <<
+					PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT;
+	qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, rfs_cm_hdr_event_id);
+
+	/* Configure Registers for RFS mode */
+	qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 1);
+	qed_wr(p_hwfn, p_ptt, PRS_REG_LOAD_L2_FILTER, 0);
+	camline.cam_line_mapped.camline = 0;
+
+	/* cam line is now valid!! */
+	SET_FIELD(camline.cam_line_mapped.camline,
+		  GFT_CAM_LINE_MAPPED_VALID, 1);
+
+	/* filters are per PF!! */
+	SET_FIELD(camline.cam_line_mapped.camline,
+		  GFT_CAM_LINE_MAPPED_PF_ID_MASK, 1);
+	SET_FIELD(camline.cam_line_mapped.camline,
+		  GFT_CAM_LINE_MAPPED_PF_ID, pf_id);
+	if (!(tcp && udp)) {
+		SET_FIELD(camline.cam_line_mapped.camline,
+			  GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK, 1);
+		if (tcp)
+			SET_FIELD(camline.cam_line_mapped.camline,
+				  GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE,
+				  GFT_PROFILE_TCP_PROTOCOL);
+		else
+			SET_FIELD(camline.cam_line_mapped.camline,
+				  GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE,
+				  GFT_PROFILE_UDP_PROTOCOL);
+	}
+
+	if (!(ipv4 && ipv6)) {
+		SET_FIELD(camline.cam_line_mapped.camline,
+			  GFT_CAM_LINE_MAPPED_IP_VERSION_MASK, 1);
+		if (ipv4)
+			SET_FIELD(camline.cam_line_mapped.camline,
+				  GFT_CAM_LINE_MAPPED_IP_VERSION,
+				  GFT_PROFILE_IPV4);
+		else
+			SET_FIELD(camline.cam_line_mapped.camline,
+				  GFT_CAM_LINE_MAPPED_IP_VERSION,
+				  GFT_PROFILE_IPV6);
+	}
+
+	/* write characteristics to cam */
+	qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id,
+	       camline.cam_line_mapped.camline);
+	camline.cam_line_mapped.camline = qed_rd(p_hwfn, p_ptt,
+						 PRS_REG_GFT_CAM +
+						 CAM_LINE_SIZE * pf_id);
+
+	/* write line to RAM - compare to filter 4 tuple */
+	ramline.low32bits = 0;
+	ramline.high32bits = 0;
+	SET_FIELD(ramline.high32bits, GFT_RAM_LINE_DST_IP, 1);
+	SET_FIELD(ramline.high32bits, GFT_RAM_LINE_SRC_IP, 1);
+	SET_FIELD(ramline.low32bits, GFT_RAM_LINE_SRC_PORT, 1);
+	SET_FIELD(ramline.low32bits, GFT_RAM_LINE_DST_PORT, 1);
+
+	/* each iteration write to reg */
+	for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++)
+		qed_wr(p_hwfn, p_ptt,
+		       PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * pf_id +
+		       i * REG_SIZE, *(p_ramline + i));
+
+	/* set default profile so that no filter match will happen */
+	ramline.low32bits = 0xffff;
+	ramline.high32bits = 0xffff;
+
+	for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++)
+		qed_wr(p_hwfn, p_ptt,
+		       PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE *
+		       PRS_GFT_CAM_LINES_NO_MATCH + i * REG_SIZE,
+		       *(p_ramline + i));
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
index 243b64e0d4dc..4a2e7be5bf72 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
@@ -554,7 +554,7 @@ int qed_init_fw_data(struct qed_dev *cdev, const u8 *data)
 	}
 
 	/* First Dword contains metadata and should be skipped */
-	buf_hdr = (struct bin_buffer_hdr *)(data + sizeof(u32));
+	buf_hdr = (struct bin_buffer_hdr *)data;
 
 	offset = buf_hdr[BIN_BUF_INIT_FW_VER_INFO].offset;
 	fw->fw_ver_info = (struct fw_ver_info *)(data + offset);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 84310b60849b..0ed24d6e6c65 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -2500,8 +2500,9 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn,
 
 	/* Configure pi coalescing if set */
 	if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) {
+		u8 num_tc = p_hwfn->hw_info.num_hw_tc;
 		u8 timeset, timer_res;
-		u8 num_tc = 1, i;
+		u8 i;
 
 		/* timeset = (coalesce >> timer-res), timeset is 7bit wide */
 		if (p_hwfn->cdev->rx_coalesce_usecs <= 0x7F)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 3a44d6b395fa..339c91dfa658 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -181,6 +181,15 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
 	p_params = &p_hwfn->pf_params.iscsi_pf_params;
 	p_queue = &p_init->q_params;
 
+	/* Sanity */
+	if (p_params->num_queues > p_hwfn->hw_info.feat_num[QED_ISCSI_CQ]) {
+		DP_ERR(p_hwfn,
+		       "Cannot satisfy CQ amount. Queues requested %d, CQs available %d. Aborting function start\n",
+		       p_params->num_queues,
+		       p_hwfn->hw_info.resc_num[QED_ISCSI_CQ]);
+		return -EINVAL;
+	}
+
 	SET_FIELD(p_init->hdr.flags,
 		  ISCSI_SLOW_PATH_HDR_LAYER_CODE, ISCSI_SLOW_PATH_LAYER_CODE);
 	p_init->hdr.op_code = ISCSI_RAMROD_CMD_ID_INIT_FUNC;
@@ -190,6 +199,9 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
 	p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring;
 	p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring;
 	p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring;
+	p_init->ooo_enable = p_params->ooo_enable;
+	p_init->ll2_rx_queue_id = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] +
+				  p_params->ll2_ooo_queue_id;
 	p_init->func_params.log_page_size = p_params->log_page_size;
 	val = p_params->num_tasks;
 	p_init->func_params.num_tasks = cpu_to_le16(val);
@@ -213,7 +225,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
 		p_queue->cq_cmdq_sb_num_arr[i] = cpu_to_le16(val);
 	}
 
-	p_queue->bdq_resource_id = ISCSI_BDQ_ID(p_hwfn->port_id);
+	p_queue->bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
 
 	DMA_REGPAIR_LE(p_queue->bdq_pbl_base_address[BDQ_ID_RQ],
 		       p_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
@@ -267,11 +279,10 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 	struct tcp_offload_params *p_tcp = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params pq_params;
-	u16 pq0_id = 0, pq1_id = 0;
 	dma_addr_t r2tq_pbl_addr;
 	dma_addr_t xhq_pbl_addr;
 	dma_addr_t uhq_pbl_addr;
+	u16 physical_q;
 	int rc = 0;
 	u32 dval;
 	u16 wval;
@@ -294,16 +305,14 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 	p_ramrod = &p_ent->ramrod.iscsi_conn_offload;
 
 	/* Transmission PQ is the first of the PF */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq0_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params);
-	p_conn->physical_q0 = cpu_to_le16(pq0_id);
-	p_ramrod->iscsi.physical_q0 = cpu_to_le16(pq0_id);
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	p_conn->physical_q0 = cpu_to_le16(physical_q);
+	p_ramrod->iscsi.physical_q0 = cpu_to_le16(physical_q);
 
 	/* iSCSI Pure-ACK PQ */
-	pq_params.iscsi.q_idx = 1;
-	pq1_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params);
-	p_conn->physical_q1 = cpu_to_le16(pq1_id);
-	p_ramrod->iscsi.physical_q1 = cpu_to_le16(pq1_id);
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK);
+	p_conn->physical_q1 = cpu_to_le16(physical_q);
+	p_ramrod->iscsi.physical_q1 = cpu_to_le16(physical_q);
 
 	p_ramrod->hdr.op_code = ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN;
 	SET_FIELD(p_ramrod->hdr.flags, ISCSI_SLOW_PATH_HDR_LAYER_CODE,
@@ -590,21 +599,31 @@ static void __iomem *qed_iscsi_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
 static void __iomem *qed_iscsi_get_primary_bdq_prod(struct qed_hwfn *p_hwfn,
 						    u8 bdq_id)
 {
-	u8 bdq_function_id = ISCSI_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_MSDM_RAM +
-			     MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id,
-							     bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_MSDM_RAM +
+		       MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 static void __iomem *qed_iscsi_get_secondary_bdq_prod(struct qed_hwfn *p_hwfn,
 						      u8 bdq_id)
 {
-	u8 bdq_function_id = ISCSI_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_TSDM_RAM +
-			     TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id,
-							     bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_TSDM_RAM +
+		       TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 static int qed_iscsi_setup_connection(struct qed_hwfn *p_hwfn,
@@ -786,6 +805,23 @@ static void qed_iscsi_release_connection(struct qed_hwfn *p_hwfn,
 	spin_unlock_bh(&p_hwfn->p_iscsi_info->lock);
 }
 
+void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
+			       struct qed_iscsi_conn *p_conn)
+{
+	qed_chain_free(p_hwfn->cdev, &p_conn->xhq);
+	qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
+	qed_chain_free(p_hwfn->cdev, &p_conn->r2tq);
+	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+			  sizeof(struct tcp_upload_params),
+			  p_conn->tcp_upload_params_virt_addr,
+			  p_conn->tcp_upload_params_phys_addr);
+	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+			  sizeof(struct scsi_terminate_extra_params),
+			  p_conn->queue_cnts_virt_addr,
+			  p_conn->queue_cnts_phys_addr);
+	kfree(p_conn);
+}
+
 struct qed_iscsi_info *qed_iscsi_alloc(struct qed_hwfn *p_hwfn)
 {
 	struct qed_iscsi_info *p_iscsi_info;
@@ -807,6 +843,17 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn,
 void qed_iscsi_free(struct qed_hwfn *p_hwfn,
 		    struct qed_iscsi_info *p_iscsi_info)
 {
+	struct qed_iscsi_conn *p_conn = NULL;
+
+	while (!list_empty(&p_hwfn->p_iscsi_info->free_list)) {
+		p_conn = list_first_entry(&p_hwfn->p_iscsi_info->free_list,
+					  struct qed_iscsi_conn, list_entry);
+		if (p_conn) {
+			list_del(&p_conn->list_entry);
+			qed_iscsi_free_connection(p_hwfn, p_conn);
+		}
+	}
+
 	kfree(p_iscsi_info);
 }
 
@@ -826,6 +873,8 @@ static void _qed_iscsi_get_tstats(struct qed_hwfn *p_hwfn,
 	    HILO_64_REGPAIR(tstats.iscsi_rx_bytes_cnt);
 	p_stats->iscsi_rx_packet_cnt =
 	    HILO_64_REGPAIR(tstats.iscsi_rx_packet_cnt);
+	p_stats->iscsi_rx_new_ooo_isle_events_cnt =
+	    HILO_64_REGPAIR(tstats.iscsi_rx_new_ooo_isle_events_cnt);
 	p_stats->iscsi_cmdq_threshold_cnt =
 	    le32_to_cpu(tstats.iscsi_cmdq_threshold_cnt);
 	p_stats->iscsi_rq_threshold_cnt =
@@ -972,6 +1021,8 @@ static int qed_fill_iscsi_dev_info(struct qed_dev *cdev,
 	info->secondary_bdq_rq_addr =
 	    qed_iscsi_get_secondary_bdq_prod(hwfn, BDQ_ID_RQ);
 
+	info->num_cqs = FEAT_NUM(hwfn, QED_ISCSI_CQ);
+
 	return rc;
 }
 
@@ -1273,6 +1324,26 @@ static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats)
 	return qed_iscsi_get_stats(QED_LEADING_HWFN(cdev), stats);
 }
 
+void qed_get_protocol_stats_iscsi(struct qed_dev *cdev,
+				  struct qed_mcp_iscsi_stats *stats)
+{
+	struct qed_iscsi_stats proto_stats;
+
+	/* Retrieve FW statistics */
+	memset(&proto_stats, 0, sizeof(proto_stats));
+	if (qed_iscsi_stats(cdev, &proto_stats)) {
+		DP_VERBOSE(cdev, QED_MSG_STORAGE,
+			   "Failed to collect ISCSI statistics\n");
+		return;
+	}
+
+	/* Translate FW statistics into struct */
+	stats->rx_pdus = proto_stats.iscsi_rx_total_pdu_cnt;
+	stats->tx_pdus = proto_stats.iscsi_tx_total_pdu_cnt;
+	stats->rx_bytes = proto_stats.iscsi_rx_bytes_cnt;
+	stats->tx_bytes = proto_stats.iscsi_tx_bytes_cnt;
+}
+
 static const struct qed_iscsi_ops qed_iscsi_ops_pass = {
 	.common = &qed_common_ops_pass,
 	.ll2 = &qed_ll2_ops_pass,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
index 20c187f4ed0b..ae98f772cbc0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
@@ -64,13 +64,25 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn,
 
 void qed_iscsi_free(struct qed_hwfn *p_hwfn,
 		    struct qed_iscsi_info *p_iscsi_info);
+
+/**
+ * @brief - Fills provided statistics struct with statistics.
+ *
+ * @param cdev
+ * @param stats - points to struct that will be filled with statistics.
+ */
+void qed_get_protocol_stats_iscsi(struct qed_dev *cdev,
+				  struct qed_mcp_iscsi_stats *stats);
 #else /* IS_ENABLED(CONFIG_QED_ISCSI) */
 static inline struct qed_iscsi_info *qed_iscsi_alloc(
 		struct qed_hwfn *p_hwfn) { return NULL; }
 static inline void qed_iscsi_setup(struct qed_hwfn *p_hwfn,
 				   struct qed_iscsi_info *p_iscsi_info) {}
 static inline void qed_iscsi_free(struct qed_hwfn *p_hwfn,
-				  struct qed_iscsi_info *p_iscsi_info) {}
+				 struct qed_iscsi_info *p_iscsi_info) {}
+static inline void
+qed_get_protocol_stats_iscsi(struct qed_dev *cdev,
+			     struct qed_mcp_iscsi_stats *stats) {}
 #endif /* IS_ENABLED(CONFIG_QED_ISCSI) */
 
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index df932be5a4e5..746fed4099c8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -938,15 +938,12 @@ qed_eth_pf_tx_queue_start(struct qed_hwfn *p_hwfn,
 			  dma_addr_t pbl_addr,
 			  u16 pbl_size, void __iomem **pp_doorbell)
 {
-	union qed_qm_pq_params pq_params;
 	int rc;
 
-	memset(&pq_params, 0, sizeof(pq_params));
 
 	rc = qed_eth_txq_start_ramrod(p_hwfn, p_cid,
 				      pbl_addr, pbl_size,
-				      qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH,
-						    &pq_params));
+				      qed_get_cm_pq_idx_mcos(p_hwfn, tc));
 	if (rc)
 		return rc;
 
@@ -1470,13 +1467,20 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn,
 	memset(&pstats, 0, sizeof(pstats));
 	qed_memcpy_from(p_hwfn, p_ptt, &pstats, pstats_addr, pstats_len);
 
-	p_stats->tx_ucast_bytes += HILO_64_REGPAIR(pstats.sent_ucast_bytes);
-	p_stats->tx_mcast_bytes += HILO_64_REGPAIR(pstats.sent_mcast_bytes);
-	p_stats->tx_bcast_bytes += HILO_64_REGPAIR(pstats.sent_bcast_bytes);
-	p_stats->tx_ucast_pkts += HILO_64_REGPAIR(pstats.sent_ucast_pkts);
-	p_stats->tx_mcast_pkts += HILO_64_REGPAIR(pstats.sent_mcast_pkts);
-	p_stats->tx_bcast_pkts += HILO_64_REGPAIR(pstats.sent_bcast_pkts);
-	p_stats->tx_err_drop_pkts += HILO_64_REGPAIR(pstats.error_drop_pkts);
+	p_stats->common.tx_ucast_bytes +=
+	    HILO_64_REGPAIR(pstats.sent_ucast_bytes);
+	p_stats->common.tx_mcast_bytes +=
+	    HILO_64_REGPAIR(pstats.sent_mcast_bytes);
+	p_stats->common.tx_bcast_bytes +=
+	    HILO_64_REGPAIR(pstats.sent_bcast_bytes);
+	p_stats->common.tx_ucast_pkts +=
+	    HILO_64_REGPAIR(pstats.sent_ucast_pkts);
+	p_stats->common.tx_mcast_pkts +=
+	    HILO_64_REGPAIR(pstats.sent_mcast_pkts);
+	p_stats->common.tx_bcast_pkts +=
+	    HILO_64_REGPAIR(pstats.sent_bcast_pkts);
+	p_stats->common.tx_err_drop_pkts +=
+	    HILO_64_REGPAIR(pstats.error_drop_pkts);
 }
 
 static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
@@ -1502,10 +1506,10 @@ static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
 	memset(&tstats, 0, sizeof(tstats));
 	qed_memcpy_from(p_hwfn, p_ptt, &tstats, tstats_addr, tstats_len);
 
-	p_stats->mftag_filter_discards +=
-		HILO_64_REGPAIR(tstats.mftag_filter_discard);
-	p_stats->mac_filter_discards +=
-		HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
+	p_stats->common.mftag_filter_discards +=
+	    HILO_64_REGPAIR(tstats.mftag_filter_discard);
+	p_stats->common.mac_filter_discards +=
+	    HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
 }
 
 static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn,
@@ -1539,12 +1543,15 @@ static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn,
 	memset(&ustats, 0, sizeof(ustats));
 	qed_memcpy_from(p_hwfn, p_ptt, &ustats, ustats_addr, ustats_len);
 
-	p_stats->rx_ucast_bytes += HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
-	p_stats->rx_mcast_bytes += HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
-	p_stats->rx_bcast_bytes += HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
-	p_stats->rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
-	p_stats->rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
-	p_stats->rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
+	p_stats->common.rx_ucast_bytes +=
+	    HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
+	p_stats->common.rx_mcast_bytes +=
+	    HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
+	p_stats->common.rx_bcast_bytes +=
+	    HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
+	p_stats->common.rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
+	p_stats->common.rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
+	p_stats->common.rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
 }
 
 static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn,
@@ -1578,23 +1585,26 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn,
 	memset(&mstats, 0, sizeof(mstats));
 	qed_memcpy_from(p_hwfn, p_ptt, &mstats, mstats_addr, mstats_len);
 
-	p_stats->no_buff_discards += HILO_64_REGPAIR(mstats.no_buff_discard);
-	p_stats->packet_too_big_discard +=
-		HILO_64_REGPAIR(mstats.packet_too_big_discard);
-	p_stats->ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard);
-	p_stats->tpa_coalesced_pkts +=
-		HILO_64_REGPAIR(mstats.tpa_coalesced_pkts);
-	p_stats->tpa_coalesced_events +=
-		HILO_64_REGPAIR(mstats.tpa_coalesced_events);
-	p_stats->tpa_aborts_num += HILO_64_REGPAIR(mstats.tpa_aborts_num);
-	p_stats->tpa_coalesced_bytes +=
-		HILO_64_REGPAIR(mstats.tpa_coalesced_bytes);
+	p_stats->common.no_buff_discards +=
+	    HILO_64_REGPAIR(mstats.no_buff_discard);
+	p_stats->common.packet_too_big_discard +=
+	    HILO_64_REGPAIR(mstats.packet_too_big_discard);
+	p_stats->common.ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard);
+	p_stats->common.tpa_coalesced_pkts +=
+	    HILO_64_REGPAIR(mstats.tpa_coalesced_pkts);
+	p_stats->common.tpa_coalesced_events +=
+	    HILO_64_REGPAIR(mstats.tpa_coalesced_events);
+	p_stats->common.tpa_aborts_num +=
+	    HILO_64_REGPAIR(mstats.tpa_aborts_num);
+	p_stats->common.tpa_coalesced_bytes +=
+	    HILO_64_REGPAIR(mstats.tpa_coalesced_bytes);
 }
 
 static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn,
 				       struct qed_ptt *p_ptt,
 				       struct qed_eth_stats *p_stats)
 {
+	struct qed_eth_stats_common *p_common = &p_stats->common;
 	struct port_stats port_stats;
 	int j;
 
@@ -1605,54 +1615,75 @@ static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn,
 			offsetof(struct public_port, stats),
 			sizeof(port_stats));
 
-	p_stats->rx_64_byte_packets		+= port_stats.eth.r64;
-	p_stats->rx_65_to_127_byte_packets	+= port_stats.eth.r127;
-	p_stats->rx_128_to_255_byte_packets	+= port_stats.eth.r255;
-	p_stats->rx_256_to_511_byte_packets	+= port_stats.eth.r511;
-	p_stats->rx_512_to_1023_byte_packets	+= port_stats.eth.r1023;
-	p_stats->rx_1024_to_1518_byte_packets	+= port_stats.eth.r1518;
-	p_stats->rx_1519_to_1522_byte_packets	+= port_stats.eth.r1522;
-	p_stats->rx_1519_to_2047_byte_packets	+= port_stats.eth.r2047;
-	p_stats->rx_2048_to_4095_byte_packets	+= port_stats.eth.r4095;
-	p_stats->rx_4096_to_9216_byte_packets	+= port_stats.eth.r9216;
-	p_stats->rx_9217_to_16383_byte_packets	+= port_stats.eth.r16383;
-	p_stats->rx_crc_errors			+= port_stats.eth.rfcs;
-	p_stats->rx_mac_crtl_frames		+= port_stats.eth.rxcf;
-	p_stats->rx_pause_frames		+= port_stats.eth.rxpf;
-	p_stats->rx_pfc_frames			+= port_stats.eth.rxpp;
-	p_stats->rx_align_errors		+= port_stats.eth.raln;
-	p_stats->rx_carrier_errors		+= port_stats.eth.rfcr;
-	p_stats->rx_oversize_packets		+= port_stats.eth.rovr;
-	p_stats->rx_jabbers			+= port_stats.eth.rjbr;
-	p_stats->rx_undersize_packets		+= port_stats.eth.rund;
-	p_stats->rx_fragments			+= port_stats.eth.rfrg;
-	p_stats->tx_64_byte_packets		+= port_stats.eth.t64;
-	p_stats->tx_65_to_127_byte_packets	+= port_stats.eth.t127;
-	p_stats->tx_128_to_255_byte_packets	+= port_stats.eth.t255;
-	p_stats->tx_256_to_511_byte_packets	+= port_stats.eth.t511;
-	p_stats->tx_512_to_1023_byte_packets	+= port_stats.eth.t1023;
-	p_stats->tx_1024_to_1518_byte_packets	+= port_stats.eth.t1518;
-	p_stats->tx_1519_to_2047_byte_packets	+= port_stats.eth.t2047;
-	p_stats->tx_2048_to_4095_byte_packets	+= port_stats.eth.t4095;
-	p_stats->tx_4096_to_9216_byte_packets	+= port_stats.eth.t9216;
-	p_stats->tx_9217_to_16383_byte_packets	+= port_stats.eth.t16383;
-	p_stats->tx_pause_frames		+= port_stats.eth.txpf;
-	p_stats->tx_pfc_frames			+= port_stats.eth.txpp;
-	p_stats->tx_lpi_entry_count		+= port_stats.eth.tlpiec;
-	p_stats->tx_total_collisions		+= port_stats.eth.tncl;
-	p_stats->rx_mac_bytes			+= port_stats.eth.rbyte;
-	p_stats->rx_mac_uc_packets		+= port_stats.eth.rxuca;
-	p_stats->rx_mac_mc_packets		+= port_stats.eth.rxmca;
-	p_stats->rx_mac_bc_packets		+= port_stats.eth.rxbca;
-	p_stats->rx_mac_frames_ok		+= port_stats.eth.rxpok;
-	p_stats->tx_mac_bytes			+= port_stats.eth.tbyte;
-	p_stats->tx_mac_uc_packets		+= port_stats.eth.txuca;
-	p_stats->tx_mac_mc_packets		+= port_stats.eth.txmca;
-	p_stats->tx_mac_bc_packets		+= port_stats.eth.txbca;
-	p_stats->tx_mac_ctrl_frames		+= port_stats.eth.txcf;
+	p_common->rx_64_byte_packets += port_stats.eth.r64;
+	p_common->rx_65_to_127_byte_packets += port_stats.eth.r127;
+	p_common->rx_128_to_255_byte_packets += port_stats.eth.r255;
+	p_common->rx_256_to_511_byte_packets += port_stats.eth.r511;
+	p_common->rx_512_to_1023_byte_packets += port_stats.eth.r1023;
+	p_common->rx_1024_to_1518_byte_packets += port_stats.eth.r1518;
+	p_common->rx_crc_errors += port_stats.eth.rfcs;
+	p_common->rx_mac_crtl_frames += port_stats.eth.rxcf;
+	p_common->rx_pause_frames += port_stats.eth.rxpf;
+	p_common->rx_pfc_frames += port_stats.eth.rxpp;
+	p_common->rx_align_errors += port_stats.eth.raln;
+	p_common->rx_carrier_errors += port_stats.eth.rfcr;
+	p_common->rx_oversize_packets += port_stats.eth.rovr;
+	p_common->rx_jabbers += port_stats.eth.rjbr;
+	p_common->rx_undersize_packets += port_stats.eth.rund;
+	p_common->rx_fragments += port_stats.eth.rfrg;
+	p_common->tx_64_byte_packets += port_stats.eth.t64;
+	p_common->tx_65_to_127_byte_packets += port_stats.eth.t127;
+	p_common->tx_128_to_255_byte_packets += port_stats.eth.t255;
+	p_common->tx_256_to_511_byte_packets += port_stats.eth.t511;
+	p_common->tx_512_to_1023_byte_packets += port_stats.eth.t1023;
+	p_common->tx_1024_to_1518_byte_packets += port_stats.eth.t1518;
+	p_common->tx_pause_frames += port_stats.eth.txpf;
+	p_common->tx_pfc_frames += port_stats.eth.txpp;
+	p_common->rx_mac_bytes += port_stats.eth.rbyte;
+	p_common->rx_mac_uc_packets += port_stats.eth.rxuca;
+	p_common->rx_mac_mc_packets += port_stats.eth.rxmca;
+	p_common->rx_mac_bc_packets += port_stats.eth.rxbca;
+	p_common->rx_mac_frames_ok += port_stats.eth.rxpok;
+	p_common->tx_mac_bytes += port_stats.eth.tbyte;
+	p_common->tx_mac_uc_packets += port_stats.eth.txuca;
+	p_common->tx_mac_mc_packets += port_stats.eth.txmca;
+	p_common->tx_mac_bc_packets += port_stats.eth.txbca;
+	p_common->tx_mac_ctrl_frames += port_stats.eth.txcf;
 	for (j = 0; j < 8; j++) {
-		p_stats->brb_truncates	+= port_stats.brb.brb_truncate[j];
-		p_stats->brb_discards	+= port_stats.brb.brb_discard[j];
+		p_common->brb_truncates += port_stats.brb.brb_truncate[j];
+		p_common->brb_discards += port_stats.brb.brb_discard[j];
+	}
+
+	if (QED_IS_BB(p_hwfn->cdev)) {
+		struct qed_eth_stats_bb *p_bb = &p_stats->bb;
+
+		p_bb->rx_1519_to_1522_byte_packets +=
+		    port_stats.eth.u0.bb0.r1522;
+		p_bb->rx_1519_to_2047_byte_packets +=
+		    port_stats.eth.u0.bb0.r2047;
+		p_bb->rx_2048_to_4095_byte_packets +=
+		    port_stats.eth.u0.bb0.r4095;
+		p_bb->rx_4096_to_9216_byte_packets +=
+		    port_stats.eth.u0.bb0.r9216;
+		p_bb->rx_9217_to_16383_byte_packets +=
+		    port_stats.eth.u0.bb0.r16383;
+		p_bb->tx_1519_to_2047_byte_packets +=
+		    port_stats.eth.u1.bb1.t2047;
+		p_bb->tx_2048_to_4095_byte_packets +=
+		    port_stats.eth.u1.bb1.t4095;
+		p_bb->tx_4096_to_9216_byte_packets +=
+		    port_stats.eth.u1.bb1.t9216;
+		p_bb->tx_9217_to_16383_byte_packets +=
+		    port_stats.eth.u1.bb1.t16383;
+		p_bb->tx_lpi_entry_count += port_stats.eth.u2.bb2.tlpiec;
+		p_bb->tx_total_collisions += port_stats.eth.u2.bb2.tncl;
+	} else {
+		struct qed_eth_stats_ah *p_ah = &p_stats->ah;
+
+		p_ah->rx_1519_to_max_byte_packets +=
+		    port_stats.eth.u0.ah0.r1519_to_max;
+		p_ah->tx_1519_to_max_byte_packets =
+		    port_stats.eth.u1.ah1.t1519_to_max;
 	}
 }
 
@@ -1768,6 +1799,84 @@ void qed_reset_vport_stats(struct qed_dev *cdev)
 		_qed_get_vport_stats(cdev, cdev->reset_stats);
 }
 
+static void
+qed_arfs_mode_configure(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			struct qed_arfs_config_params *p_cfg_params)
+{
+	if (p_cfg_params->arfs_enable) {
+		qed_set_rfs_mode_enable(p_hwfn, p_ptt, p_hwfn->rel_pf_id,
+					p_cfg_params->tcp, p_cfg_params->udp,
+					p_cfg_params->ipv4, p_cfg_params->ipv6);
+		DP_VERBOSE(p_hwfn, QED_MSG_SP,
+			   "tcp = %s, udp = %s, ipv4 = %s, ipv6 =%s\n",
+			   p_cfg_params->tcp ? "Enable" : "Disable",
+			   p_cfg_params->udp ? "Enable" : "Disable",
+			   p_cfg_params->ipv4 ? "Enable" : "Disable",
+			   p_cfg_params->ipv6 ? "Enable" : "Disable");
+	} else {
+		qed_set_rfs_mode_disable(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP, "Configured ARFS mode : %s\n",
+		   p_cfg_params->arfs_enable ? "Enable" : "Disable");
+}
+
+static int
+qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+				struct qed_spq_comp_cb *p_cb,
+				dma_addr_t p_addr, u16 length, u16 qid,
+				u8 vport_id, bool b_is_add)
+{
+	struct rx_update_gft_filter_data *p_ramrod = NULL;
+	struct qed_spq_entry *p_ent = NULL;
+	struct qed_sp_init_data init_data;
+	u16 abs_rx_q_id = 0;
+	u8 abs_vport_id = 0;
+	int rc = -EINVAL;
+
+	rc = qed_fw_vport(p_hwfn, vport_id, &abs_vport_id);
+	if (rc)
+		return rc;
+
+	rc = qed_fw_l2_queue(p_hwfn, qid, &abs_rx_q_id);
+	if (rc)
+		return rc;
+
+	/* Get SPQ entry */
+	memset(&init_data, 0, sizeof(init_data));
+	init_data.cid = qed_spq_get_cid(p_hwfn);
+
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+
+	if (p_cb) {
+		init_data.comp_mode = QED_SPQ_MODE_CB;
+		init_data.p_comp_data = p_cb;
+	} else {
+		init_data.comp_mode = QED_SPQ_MODE_EBLOCK;
+	}
+
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 ETH_RAMROD_GFT_UPDATE_FILTER,
+				 PROTOCOLID_ETH, &init_data);
+	if (rc)
+		return rc;
+
+	p_ramrod = &p_ent->ramrod.rx_update_gft;
+	DMA_REGPAIR_LE(p_ramrod->pkt_hdr_addr, p_addr);
+	p_ramrod->pkt_hdr_length = cpu_to_le16(length);
+	p_ramrod->rx_qid_or_action_icid = cpu_to_le16(abs_rx_q_id);
+	p_ramrod->vport_id = abs_vport_id;
+	p_ramrod->filter_type = RFS_FILTER_TYPE;
+	p_ramrod->filter_action = b_is_add ? GFT_ADD_FILTER : GFT_DELETE_FILTER;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "V[%0x], Q[%04x] - %s filter from 0x%llx [length %04xb]\n",
+		   abs_vport_id, abs_rx_q_id,
+		   b_is_add ? "Adding" : "Removing", (u64)p_addr, length);
+
+	return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
 static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 				 struct qed_dev_eth_info *info)
 {
@@ -1898,7 +2007,11 @@ static int qed_start_vport(struct qed_dev *cdev,
 			return rc;
 		}
 
-		qed_hw_start_fastpath(p_hwfn);
+		rc = qed_hw_start_fastpath(p_hwfn);
+		if (rc) {
+			DP_ERR(cdev, "Failed to start VPORT fastpath\n");
+			return rc;
+		}
 
 		DP_VERBOSE(cdev, (QED_MSG_SPQ | NETIF_MSG_IFUP),
 			   "Started V-PORT %d with MTU %d\n",
@@ -2141,7 +2254,13 @@ static int qed_start_txq(struct qed_dev *cdev,
 #define QED_HW_STOP_RETRY_LIMIT (10)
 static int qed_fastpath_stop(struct qed_dev *cdev)
 {
-	qed_hw_stop_fastpath(cdev);
+	int rc;
+
+	rc = qed_hw_stop_fastpath(cdev);
+	if (rc) {
+		DP_ERR(cdev, "Failed to stop Fastpath\n");
+		return rc;
+	}
 
 	return 0;
 }
@@ -2166,31 +2285,46 @@ static int qed_stop_txq(struct qed_dev *cdev, u8 rss_id, void *handle)
 static int qed_tunn_configure(struct qed_dev *cdev,
 			      struct qed_tunn_params *tunn_params)
 {
-	struct qed_tunn_update_params tunn_info;
+	struct qed_tunnel_info tunn_info;
 	int i, rc;
 
-	if (IS_VF(cdev))
-		return 0;
-
 	memset(&tunn_info, 0, sizeof(tunn_info));
-	if (tunn_params->update_vxlan_port == 1) {
-		tunn_info.update_vxlan_udp_port = 1;
-		tunn_info.vxlan_udp_port = tunn_params->vxlan_port;
+	if (tunn_params->update_vxlan_port) {
+		tunn_info.vxlan_port.b_update_port = true;
+		tunn_info.vxlan_port.port = tunn_params->vxlan_port;
 	}
 
-	if (tunn_params->update_geneve_port == 1) {
-		tunn_info.update_geneve_udp_port = 1;
-		tunn_info.geneve_udp_port = tunn_params->geneve_port;
+	if (tunn_params->update_geneve_port) {
+		tunn_info.geneve_port.b_update_port = true;
+		tunn_info.geneve_port.port = tunn_params->geneve_port;
 	}
 
 	for_each_hwfn(cdev, i) {
 		struct qed_hwfn *hwfn = &cdev->hwfns[i];
+		struct qed_tunnel_info *tun;
+
+		tun = &hwfn->cdev->tunnel;
 
 		rc = qed_sp_pf_update_tunn_cfg(hwfn, &tunn_info,
 					       QED_SPQ_MODE_EBLOCK, NULL);
-
 		if (rc)
 			return rc;
+
+		if (IS_PF_SRIOV(hwfn)) {
+			u16 vxlan_port, geneve_port;
+			int j;
+
+			vxlan_port = tun->vxlan_port.port;
+			geneve_port = tun->geneve_port.port;
+
+			qed_for_each_vf(hwfn, j) {
+				qed_iov_bulletin_set_udp_ports(hwfn, j,
+							       vxlan_port,
+							       geneve_port);
+			}
+
+			qed_schedule_iov(hwfn, QED_IOV_WQ_BULLETIN_UPDATE_FLAG);
+		}
 	}
 
 	return 0;
@@ -2315,6 +2449,59 @@ static int qed_configure_filter(struct qed_dev *cdev,
 	}
 }
 
+static int qed_configure_arfs_searcher(struct qed_dev *cdev, bool en_searcher)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_arfs_config_params arfs_config_params;
+
+	memset(&arfs_config_params, 0, sizeof(arfs_config_params));
+	arfs_config_params.tcp = true;
+	arfs_config_params.udp = true;
+	arfs_config_params.ipv4 = true;
+	arfs_config_params.ipv6 = true;
+	arfs_config_params.arfs_enable = en_searcher;
+
+	qed_arfs_mode_configure(p_hwfn, p_hwfn->p_arfs_ptt,
+				&arfs_config_params);
+	return 0;
+}
+
+static void
+qed_arfs_sp_response_handler(struct qed_hwfn *p_hwfn,
+			     void *cookie, union event_ring_data *data,
+			     u8 fw_return_code)
+{
+	struct qed_common_cb_ops *op = p_hwfn->cdev->protocol_ops.common;
+	void *dev = p_hwfn->cdev->ops_cookie;
+
+	op->arfs_filter_op(dev, cookie, fw_return_code);
+}
+
+static int qed_ntuple_arfs_filter_config(struct qed_dev *cdev, void *cookie,
+					 dma_addr_t mapping, u16 length,
+					 u16 vport_id, u16 rx_queue_id,
+					 bool add_filter)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_spq_comp_cb cb;
+	int rc = -EINVAL;
+
+	cb.function = qed_arfs_sp_response_handler;
+	cb.cookie = cookie;
+
+	rc = qed_configure_rfs_ntuple_filter(p_hwfn, p_hwfn->p_arfs_ptt,
+					     &cb, mapping, length, rx_queue_id,
+					     vport_id, add_filter);
+	if (rc)
+		DP_NOTICE(p_hwfn,
+			  "Failed to issue a-RFS filter configuration\n");
+	else
+		DP_VERBOSE(p_hwfn, NETIF_MSG_DRV,
+			   "Successfully issued a-RFS filter configuration\n");
+
+	return rc;
+}
+
 static int qed_fp_cqe_completion(struct qed_dev *dev,
 				 u8 rss_id, struct eth_slow_path_rx_cqe *cqe)
 {
@@ -2356,6 +2543,8 @@ static const struct qed_eth_ops qed_eth_ops_pass = {
 	.eth_cqe_completion = &qed_fp_cqe_completion,
 	.get_vport_stats = &qed_get_vport_stats,
 	.tunn_config = &qed_tunn_configure,
+	.ntuple_filter_config = &qed_ntuple_arfs_filter_config,
+	.configure_arfs_searcher = &qed_configure_arfs_searcher,
 };
 
 const struct qed_eth_ops *qed_get_eth_ops(void)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index e763abd334f6..6f44229899eb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -185,6 +185,14 @@ struct qed_filter_accept_flags {
 #define QED_ACCEPT_BCAST                0x20
 };
 
+struct qed_arfs_config_params {
+	bool tcp;
+	bool udp;
+	bool ipv4;
+	bool ipv6;
+	bool arfs_enable;
+};
+
 struct qed_sp_vport_update_params {
 	u16				opaque_fid;
 	u8				vport_id;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 9a0b9af10a57..09c86411918c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -211,6 +211,8 @@ static void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn,
 	/* If need to reuse or there's no replacement buffer, repost this */
 	if (rc)
 		goto out_post;
+	dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr,
+			 cdev->ll2->rx_size, DMA_FROM_DEVICE);
 
 	skb = build_skb(buffer->data, 0);
 	if (!skb) {
@@ -474,7 +476,7 @@ qed_ll2_rxq_completion_gsi(struct qed_hwfn *p_hwfn,
 static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn,
 				      struct qed_ll2_info *p_ll2_conn,
 				      union core_rx_cqe_union *p_cqe,
-				      unsigned long lock_flags,
+				      unsigned long *p_lock_flags,
 				      bool b_last_cqe)
 {
 	struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue;
@@ -495,10 +497,10 @@ static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn,
 			  "Mismatch between active_descq and the LL2 Rx chain\n");
 	list_add_tail(&p_pkt->list_entry, &p_rx->free_descq);
 
-	spin_unlock_irqrestore(&p_rx->lock, lock_flags);
+	spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags);
 	qed_ll2b_complete_rx_packet(p_hwfn, p_ll2_conn->my_id,
 				    p_pkt, &p_cqe->rx_cqe_fp, b_last_cqe);
-	spin_lock_irqsave(&p_rx->lock, lock_flags);
+	spin_lock_irqsave(&p_rx->lock, *p_lock_flags);
 
 	return 0;
 }
@@ -538,7 +540,8 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie)
 			break;
 		case CORE_RX_CQE_TYPE_REGULAR:
 			rc = qed_ll2_rxq_completion_reg(p_hwfn, p_ll2_conn,
-							cqe, flags, b_last_cqe);
+							cqe, &flags,
+							b_last_cqe);
 			break;
 		default:
 			rc = -EIO;
@@ -594,7 +597,7 @@ static u8 qed_ll2_convert_rx_parse_to_tx_flags(u16 parse_flags)
 	u8 bd_flags = 0;
 
 	if (GET_FIELD(parse_flags, PARSING_AND_ERR_FLAGS_TAG8021QEXIST))
-		SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_VLAN_INSERTION, 1);
+		SET_FIELD(bd_flags, CORE_TX_BD_DATA_VLAN_INSERTION, 1);
 
 	return bd_flags;
 }
@@ -755,8 +758,8 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn,
 			     p_buffer->placement_offset;
 		parse_flags = p_buffer->parse_flags;
 		bd_flags = qed_ll2_convert_rx_parse_to_tx_flags(parse_flags);
-		SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_FORCE_VLAN_MODE, 1);
-		SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_L4_PROTOCOL, 1);
+		SET_FIELD(bd_flags, CORE_TX_BD_DATA_FORCE_VLAN_MODE, 1);
+		SET_FIELD(bd_flags, CORE_TX_BD_DATA_L4_PROTOCOL, 1);
 
 		rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1,
 					       p_buffer->vlan, bd_flags,
@@ -968,7 +971,7 @@ static int qed_ll2_start_ooo(struct qed_dev *cdev,
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
-	struct qed_ll2_conn ll2_info;
+	struct qed_ll2_conn ll2_info = { 0 };
 	int rc;
 
 	ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO;
@@ -1087,7 +1090,6 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	struct core_tx_start_ramrod_data *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params pq_params;
 	u16 pq_id = 0, pbl_size;
 	int rc = -EINVAL;
 
@@ -1124,9 +1126,18 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	pbl_size = qed_chain_get_page_cnt(&p_tx->txq_chain);
 	p_ramrod->pbl_size = cpu_to_le16(pbl_size);
 
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = p_ll2_conn->conn.tx_tc;
-	pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
+	switch (p_ll2_conn->conn.tx_tc) {
+	case LB_TC:
+		pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB);
+		break;
+	case OOO_LB_TC:
+		pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OOO);
+		break;
+	default:
+		pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+		break;
+	}
+
 	p_ramrod->qm_pq_id = cpu_to_le16(pq_id);
 
 	switch (conn_type) {
@@ -1397,13 +1408,21 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
 	struct qed_ll2_info *p_ll2_conn;
 	struct qed_ll2_rx_queue *p_rx;
 	struct qed_ll2_tx_queue *p_tx;
+	struct qed_ptt *p_ptt;
 	int rc = -EINVAL;
 	u32 i, capacity;
 	u8 qid;
 
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EAGAIN;
+
 	p_ll2_conn = qed_ll2_handle_sanity_lock(p_hwfn, connection_handle);
-	if (!p_ll2_conn)
-		return -EINVAL;
+	if (!p_ll2_conn) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	p_rx = &p_ll2_conn->rx_queue;
 	p_tx = &p_ll2_conn->tx_queue;
 
@@ -1436,7 +1455,9 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
 	p_tx->cur_completing_frag_num = 0;
 	*p_tx->p_fw_cons = 0;
 
-	qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_ll2_conn->cid);
+	rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_ll2_conn->cid);
+	if (rc)
+		goto out;
 
 	qid = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] + connection_handle;
 	p_ll2_conn->queue_id = qid;
@@ -1450,26 +1471,28 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
 
 	rc = qed_ll2_establish_connection_rx(p_hwfn, p_ll2_conn);
 	if (rc)
-		return rc;
+		goto out;
 
 	rc = qed_sp_ll2_tx_queue_start(p_hwfn, p_ll2_conn);
 	if (rc)
-		return rc;
+		goto out;
 
 	if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt, PRS_REG_USE_LIGHT_L2, 1);
+		qed_wr(p_hwfn, p_ptt, PRS_REG_USE_LIGHT_L2, 1);
 
 	qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn);
 
 	if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_FCOE) {
-		qed_llh_add_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+		qed_llh_add_protocol_filter(p_hwfn, p_ptt,
 					    0x8906, 0,
 					    QED_LLH_FILTER_ETHERTYPE);
-		qed_llh_add_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+		qed_llh_add_protocol_filter(p_hwfn, p_ptt,
 					    0x8914, 0,
 					    QED_LLH_FILTER_ETHERTYPE);
 	}
 
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
 	return rc;
 }
 
@@ -1588,33 +1611,34 @@ static void qed_ll2_prepare_tx_packet_set(struct qed_hwfn *p_hwfn,
 	p_tx->cur_send_frag_num++;
 }
 
-static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
-					     struct qed_ll2_info *p_ll2,
-					     struct qed_ll2_tx_packet *p_curp,
-					     u8 num_of_bds,
-					     enum core_tx_dest tx_dest,
-					     u16 vlan,
-					     u8 bd_flags,
-					     u16 l4_hdr_offset_w,
-					     enum core_roce_flavor_type type,
-					     dma_addr_t first_frag,
-					     u16 first_frag_len)
+static void
+qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
+				 struct qed_ll2_info *p_ll2,
+				 struct qed_ll2_tx_packet *p_curp,
+				 u8 num_of_bds,
+				 enum core_tx_dest tx_dest,
+				 u16 vlan,
+				 u8 bd_flags,
+				 u16 l4_hdr_offset_w,
+				 enum core_roce_flavor_type roce_flavor,
+				 dma_addr_t first_frag,
+				 u16 first_frag_len)
 {
 	struct qed_chain *p_tx_chain = &p_ll2->tx_queue.txq_chain;
 	u16 prod_idx = qed_chain_get_prod_idx(p_tx_chain);
 	struct core_tx_bd *start_bd = NULL;
-	u16 frag_idx;
+	u16 bd_data = 0, frag_idx;
 
 	start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
 	start_bd->nw_vlan_or_lb_echo = cpu_to_le16(vlan);
 	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W,
 		  cpu_to_le16(l4_hdr_offset_w));
 	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest);
-	start_bd->bd_flags.as_bitfield = bd_flags;
-	start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK <<
-	    CORE_TX_BD_FLAGS_START_BD_SHIFT;
-	SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds);
-	SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type);
+	bd_data |= bd_flags;
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1);
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, num_of_bds);
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor);
+	start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data);
 	DMA_REGPAIR_LE(start_bd->addr, first_frag);
 	start_bd->nbytes = cpu_to_le16(first_frag_len);
 
@@ -1639,9 +1663,8 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 		struct core_tx_bd **p_bd = &p_curp->bds_set[frag_idx].txq_bd;
 
 		*p_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
-		(*p_bd)->bd_flags.as_bitfield = 0;
+		(*p_bd)->bd_data.as_bitfield = 0;
 		(*p_bd)->bitfield1 = 0;
-		(*p_bd)->bitfield0 = 0;
 		p_curp->bds_set[frag_idx].tx_frag = 0;
 		p_curp->bds_set[frag_idx].frag_len = 0;
 	}
@@ -1820,23 +1843,30 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
 {
 	struct qed_ll2_info *p_ll2_conn = NULL;
 	int rc = -EINVAL;
+	struct qed_ptt *p_ptt;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EAGAIN;
 
 	p_ll2_conn = qed_ll2_handle_sanity_lock(p_hwfn, connection_handle);
-	if (!p_ll2_conn)
-		return -EINVAL;
+	if (!p_ll2_conn) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	/* Stop Tx & Rx of connection, if needed */
 	if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
 		rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn);
 		if (rc)
-			return rc;
+			goto out;
 		qed_ll2_txq_flush(p_hwfn, connection_handle);
 	}
 
 	if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
 		rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn);
 		if (rc)
-			return rc;
+			goto out;
 		qed_ll2_rxq_flush(p_hwfn, connection_handle);
 	}
 
@@ -1844,14 +1874,16 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
 		qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
 
 	if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_FCOE) {
-		qed_llh_remove_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+		qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
 					       0x8906, 0,
 					       QED_LLH_FILTER_ETHERTYPE);
-		qed_llh_remove_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+		qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
 					       0x8914, 0,
 					       QED_LLH_FILTER_ETHERTYPE);
 	}
 
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
 	return rc;
 }
 
@@ -2238,11 +2270,11 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
 	/* Request HW to calculate IP csum */
 	if (!((vlan_get_protocol(skb) == htons(ETH_P_IPV6)) &&
 	      ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6))
-		flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT);
+		flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT);
 
 	if (skb_vlan_tag_present(skb)) {
 		vlan = skb_vlan_tag_get(skb);
-		flags |= BIT(CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT);
+		flags |= BIT(CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT);
 	}
 
 	rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev),
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index eef30a598b40..59992cf20d42 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -45,6 +45,7 @@
 #include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_ll2_if.h>
 
@@ -54,6 +55,8 @@
 #include "qed_dev_api.h"
 #include "qed_ll2.h"
 #include "qed_fcoe.h"
+#include "qed_iscsi.h"
+
 #include "qed_mcp.h"
 #include "qed_hw.h"
 #include "qed_selftest.h"
@@ -227,10 +230,25 @@ err0:
 int qed_fill_dev_info(struct qed_dev *cdev,
 		      struct qed_dev_info *dev_info)
 {
+	struct qed_tunnel_info *tun = &cdev->tunnel;
 	struct qed_ptt  *ptt;
 
 	memset(dev_info, 0, sizeof(struct qed_dev_info));
 
+	if (tun->vxlan.tun_cls == QED_TUNN_CLSS_MAC_VLAN &&
+	    tun->vxlan.b_mode_enabled)
+		dev_info->vxlan_enable = true;
+
+	if (tun->l2_gre.b_mode_enabled && tun->ip_gre.b_mode_enabled &&
+	    tun->l2_gre.tun_cls == QED_TUNN_CLSS_MAC_VLAN &&
+	    tun->ip_gre.tun_cls == QED_TUNN_CLSS_MAC_VLAN)
+		dev_info->gre_enable = true;
+
+	if (tun->l2_geneve.b_mode_enabled && tun->ip_geneve.b_mode_enabled &&
+	    tun->l2_geneve.tun_cls == QED_TUNN_CLSS_MAC_VLAN &&
+	    tun->ip_geneve.tun_cls == QED_TUNN_CLSS_MAC_VLAN)
+		dev_info->geneve_enable = true;
+
 	dev_info->num_hwfns = cdev->num_hwfns;
 	dev_info->pci_mem_start = cdev->pci_params.mem_start;
 	dev_info->pci_mem_end = cdev->pci_params.mem_end;
@@ -238,6 +256,7 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 	dev_info->rdma_supported = (cdev->hwfns[0].hw_info.personality ==
 				    QED_PCI_ETH_ROCE);
 	dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]);
+	dev_info->dev_type = cdev->type;
 	ether_addr_copy(dev_info->hw_mac, cdev->hwfns[0].hw_info.hw_mac_addr);
 
 	if (IS_PF(cdev)) {
@@ -588,6 +607,19 @@ int qed_slowpath_irq_req(struct qed_hwfn *hwfn)
 	return rc;
 }
 
+void qed_slowpath_irq_sync(struct qed_hwfn *p_hwfn)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 id = p_hwfn->my_id;
+	u32 int_mode;
+
+	int_mode = cdev->int_params.out.int_mode;
+	if (int_mode == QED_INT_MODE_MSIX)
+		synchronize_irq(cdev->int_params.msix_table[id].vector);
+	else
+		synchronize_irq(cdev->pdev->irq);
+}
+
 static void qed_slowpath_irq_free(struct qed_dev *cdev)
 {
 	int i;
@@ -630,19 +662,6 @@ static int qed_nic_stop(struct qed_dev *cdev)
 	return rc;
 }
 
-static int qed_nic_reset(struct qed_dev *cdev)
-{
-	int rc;
-
-	rc = qed_hw_reset(cdev);
-	if (rc)
-		return rc;
-
-	qed_resc_free(cdev);
-
-	return 0;
-}
-
 static int qed_nic_setup(struct qed_dev *cdev)
 {
 	int rc, i;
@@ -743,7 +762,8 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	cdev->int_params.fp_msix_cnt = cdev->int_params.out.num_vectors -
 				       cdev->num_hwfns;
 
-	if (!IS_ENABLED(CONFIG_QED_RDMA))
+	if (!IS_ENABLED(CONFIG_QED_RDMA) ||
+	    QED_LEADING_HWFN(cdev)->hw_info.personality != QED_PCI_ETH_ROCE)
 		return 0;
 
 	for_each_hwfn(cdev, i)
@@ -875,10 +895,12 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 		params->rdma_pf_params.num_qps = QED_ROCE_QPS;
 		params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
 		/* divide by 3 the MRs to avoid MF ILT overflow */
-		params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
 		params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
 	}
 
+	if (cdev->num_hwfns > 1 || IS_VF(cdev))
+		params->eth_pf_params.num_arfs_filters = 0;
+
 	/* In case we might support RDMA, don't allow qede to be greedy
 	 * with the L2 contexts. Allow for 64 queues [rx, tx, xdp] per hwfn.
 	 */
@@ -900,11 +922,15 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 static int qed_slowpath_start(struct qed_dev *cdev,
 			      struct qed_slowpath_params *params)
 {
-	struct qed_tunn_start_params tunn_info;
+	struct qed_drv_load_params drv_load_params;
+	struct qed_hw_init_params hw_init_params;
 	struct qed_mcp_drv_version drv_version;
+	struct qed_tunnel_info tunn_info;
 	const u8 *data = NULL;
 	struct qed_hwfn *hwfn;
+#ifdef CONFIG_RFS_ACCEL
 	struct qed_ptt *p_ptt;
+#endif
 	int rc = -EINVAL;
 
 	if (qed_iov_wq_start(cdev))
@@ -920,13 +946,18 @@ static int qed_slowpath_start(struct qed_dev *cdev,
 			goto err;
 		}
 
-		p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
-		if (p_ptt) {
-			QED_LEADING_HWFN(cdev)->p_ptp_ptt = p_ptt;
-		} else {
-			DP_NOTICE(cdev, "Failed to acquire PTT for PTP\n");
-			goto err;
+#ifdef CONFIG_RFS_ACCEL
+		if (cdev->num_hwfns == 1) {
+			p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
+			if (p_ptt) {
+				QED_LEADING_HWFN(cdev)->p_arfs_ptt = p_ptt;
+			} else {
+				DP_NOTICE(cdev,
+					  "Failed to acquire PTT for aRFS\n");
+				goto err;
+			}
 		}
+#endif
 	}
 
 	cdev->rx_coalesce_usecs = QED_DEFAULT_RX_USECS;
@@ -953,27 +984,47 @@ static int qed_slowpath_start(struct qed_dev *cdev,
 		qed_dbg_pf_init(cdev);
 	}
 
-	memset(&tunn_info, 0, sizeof(tunn_info));
-	tunn_info.tunn_mode |=  1 << QED_MODE_VXLAN_TUNN |
-				1 << QED_MODE_L2GRE_TUNN |
-				1 << QED_MODE_IPGRE_TUNN |
-				1 << QED_MODE_L2GENEVE_TUNN |
-				1 << QED_MODE_IPGENEVE_TUNN;
-
-	tunn_info.tunn_clss_vxlan = QED_TUNN_CLSS_MAC_VLAN;
-	tunn_info.tunn_clss_l2gre = QED_TUNN_CLSS_MAC_VLAN;
-	tunn_info.tunn_clss_ipgre = QED_TUNN_CLSS_MAC_VLAN;
-
 	/* Start the slowpath */
-	rc = qed_hw_init(cdev, &tunn_info, true,
-			 cdev->int_params.out.int_mode,
-			 true, data);
+	memset(&hw_init_params, 0, sizeof(hw_init_params));
+	memset(&tunn_info, 0, sizeof(tunn_info));
+	tunn_info.vxlan.b_mode_enabled = true;
+	tunn_info.l2_gre.b_mode_enabled = true;
+	tunn_info.ip_gre.b_mode_enabled = true;
+	tunn_info.l2_geneve.b_mode_enabled = true;
+	tunn_info.ip_geneve.b_mode_enabled = true;
+	tunn_info.vxlan.tun_cls = QED_TUNN_CLSS_MAC_VLAN;
+	tunn_info.l2_gre.tun_cls = QED_TUNN_CLSS_MAC_VLAN;
+	tunn_info.ip_gre.tun_cls = QED_TUNN_CLSS_MAC_VLAN;
+	tunn_info.l2_geneve.tun_cls = QED_TUNN_CLSS_MAC_VLAN;
+	tunn_info.ip_geneve.tun_cls = QED_TUNN_CLSS_MAC_VLAN;
+	hw_init_params.p_tunn = &tunn_info;
+	hw_init_params.b_hw_start = true;
+	hw_init_params.int_mode = cdev->int_params.out.int_mode;
+	hw_init_params.allow_npar_tx_switch = true;
+	hw_init_params.bin_fw_data = data;
+
+	memset(&drv_load_params, 0, sizeof(drv_load_params));
+	drv_load_params.is_crash_kernel = is_kdump_kernel();
+	drv_load_params.mfw_timeout_val = QED_LOAD_REQ_LOCK_TO_DEFAULT;
+	drv_load_params.avoid_eng_reset = false;
+	drv_load_params.override_force_load = QED_OVERRIDE_FORCE_LOAD_NONE;
+	hw_init_params.p_drv_load_params = &drv_load_params;
+
+	rc = qed_hw_init(cdev, &hw_init_params);
 	if (rc)
 		goto err2;
 
 	DP_INFO(cdev,
 		"HW initialization and function start completed successfully\n");
 
+	if (IS_PF(cdev)) {
+		cdev->tunn_feature_mask = (BIT(QED_MODE_VXLAN_TUNN) |
+					   BIT(QED_MODE_L2GENEVE_TUNN) |
+					   BIT(QED_MODE_IPGENEVE_TUNN) |
+					   BIT(QED_MODE_L2GRE_TUNN) |
+					   BIT(QED_MODE_IPGRE_TUNN));
+	}
+
 	/* Allocate LL2 interface if needed */
 	if (QED_LEADING_HWFN(cdev)->using_ll2) {
 		rc = qed_ll2_alloc_if(cdev);
@@ -1014,9 +1065,12 @@ err:
 	if (IS_PF(cdev))
 		release_firmware(cdev->firmware);
 
-	if (IS_PF(cdev) && QED_LEADING_HWFN(cdev)->p_ptp_ptt)
+#ifdef CONFIG_RFS_ACCEL
+	if (IS_PF(cdev) && (cdev->num_hwfns == 1) &&
+	    QED_LEADING_HWFN(cdev)->p_arfs_ptt)
 		qed_ptt_release(QED_LEADING_HWFN(cdev),
-				QED_LEADING_HWFN(cdev)->p_ptp_ptt);
+				QED_LEADING_HWFN(cdev)->p_arfs_ptt);
+#endif
 
 	qed_iov_wq_stop(cdev, false);
 
@@ -1031,8 +1085,11 @@ static int qed_slowpath_stop(struct qed_dev *cdev)
 	qed_ll2_dealloc_if(cdev);
 
 	if (IS_PF(cdev)) {
-		qed_ptt_release(QED_LEADING_HWFN(cdev),
-				QED_LEADING_HWFN(cdev)->p_ptp_ptt);
+#ifdef CONFIG_RFS_ACCEL
+		if (cdev->num_hwfns == 1)
+			qed_ptt_release(QED_LEADING_HWFN(cdev),
+					QED_LEADING_HWFN(cdev)->p_arfs_ptt);
+#endif
 		qed_free_stream_mem(cdev);
 		if (IS_QED_ETH_IF(cdev))
 			qed_sriov_disable(cdev, true);
@@ -1042,7 +1099,8 @@ static int qed_slowpath_stop(struct qed_dev *cdev)
 	}
 
 	qed_disable_msix(cdev);
-	qed_nic_reset(cdev);
+
+	qed_resc_free(cdev);
 
 	qed_iov_wq_stop(cdev, true);
 
@@ -1653,13 +1711,18 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
 	switch (type) {
 	case QED_MCP_LAN_STATS:
 		qed_get_vport_stats(cdev, &eth_stats);
-		stats->lan_stats.ucast_rx_pkts = eth_stats.rx_ucast_pkts;
-		stats->lan_stats.ucast_tx_pkts = eth_stats.tx_ucast_pkts;
+		stats->lan_stats.ucast_rx_pkts =
+					eth_stats.common.rx_ucast_pkts;
+		stats->lan_stats.ucast_tx_pkts =
+					eth_stats.common.tx_ucast_pkts;
 		stats->lan_stats.fcs_err = -1;
 		break;
 	case QED_MCP_FCOE_STATS:
 		qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats);
 		break;
+	case QED_MCP_ISCSI_STATS:
+		qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats);
+		break;
 	default:
 		DP_ERR(cdev, "Invalid protocol type = %d\n", type);
 		return;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 87fde205149f..7266b36a2655 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -111,12 +111,71 @@ void qed_mcp_read_mb(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	}
 }
 
+struct qed_mcp_cmd_elem {
+	struct list_head list;
+	struct qed_mcp_mb_params *p_mb_params;
+	u16 expected_seq_num;
+	bool b_is_completed;
+};
+
+/* Must be called while cmd_lock is acquired */
+static struct qed_mcp_cmd_elem *
+qed_mcp_cmd_add_elem(struct qed_hwfn *p_hwfn,
+		     struct qed_mcp_mb_params *p_mb_params,
+		     u16 expected_seq_num)
+{
+	struct qed_mcp_cmd_elem *p_cmd_elem = NULL;
+
+	p_cmd_elem = kzalloc(sizeof(*p_cmd_elem), GFP_ATOMIC);
+	if (!p_cmd_elem)
+		goto out;
+
+	p_cmd_elem->p_mb_params = p_mb_params;
+	p_cmd_elem->expected_seq_num = expected_seq_num;
+	list_add(&p_cmd_elem->list, &p_hwfn->mcp_info->cmd_list);
+out:
+	return p_cmd_elem;
+}
+
+/* Must be called while cmd_lock is acquired */
+static void qed_mcp_cmd_del_elem(struct qed_hwfn *p_hwfn,
+				 struct qed_mcp_cmd_elem *p_cmd_elem)
+{
+	list_del(&p_cmd_elem->list);
+	kfree(p_cmd_elem);
+}
+
+/* Must be called while cmd_lock is acquired */
+static struct qed_mcp_cmd_elem *qed_mcp_cmd_get_elem(struct qed_hwfn *p_hwfn,
+						     u16 seq_num)
+{
+	struct qed_mcp_cmd_elem *p_cmd_elem = NULL;
+
+	list_for_each_entry(p_cmd_elem, &p_hwfn->mcp_info->cmd_list, list) {
+		if (p_cmd_elem->expected_seq_num == seq_num)
+			return p_cmd_elem;
+	}
+
+	return NULL;
+}
+
 int qed_mcp_free(struct qed_hwfn *p_hwfn)
 {
 	if (p_hwfn->mcp_info) {
+		struct qed_mcp_cmd_elem *p_cmd_elem, *p_tmp;
+
 		kfree(p_hwfn->mcp_info->mfw_mb_cur);
 		kfree(p_hwfn->mcp_info->mfw_mb_shadow);
+
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+		list_for_each_entry_safe(p_cmd_elem,
+					 p_tmp,
+					 &p_hwfn->mcp_info->cmd_list, list) {
+			qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+		}
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 	}
+
 	kfree(p_hwfn->mcp_info);
 
 	return 0;
@@ -160,7 +219,7 @@ static int qed_load_mcp_offsets(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	p_info->drv_pulse_seq = DRV_MB_RD(p_hwfn, p_ptt, drv_pulse_mb) &
 				DRV_PULSE_SEQ_MASK;
 
-	p_info->mcp_hist = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
+	p_info->mcp_hist = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
 
 	return 0;
 }
@@ -176,6 +235,12 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		goto err;
 	p_info = p_hwfn->mcp_info;
 
+	/* Initialize the MFW spinlock */
+	spin_lock_init(&p_info->cmd_lock);
+	spin_lock_init(&p_info->link_lock);
+
+	INIT_LIST_HEAD(&p_info->cmd_list);
+
 	if (qed_load_mcp_offsets(p_hwfn, p_ptt) != 0) {
 		DP_NOTICE(p_hwfn, "MCP is not initialized\n");
 		/* Do not free mcp_info here, since public_base indicate that
@@ -190,10 +255,6 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	if (!p_info->mfw_mb_shadow || !p_info->mfw_mb_addr)
 		goto err;
 
-	/* Initialize the MFW spinlock */
-	spin_lock_init(&p_info->lock);
-	spin_lock_init(&p_info->link_lock);
-
 	return 0;
 
 err:
@@ -201,68 +262,39 @@ err:
 	return -ENOMEM;
 }
 
-/* Locks the MFW mailbox of a PF to ensure a single access.
- * The lock is achieved in most cases by holding a spinlock, causing other
- * threads to wait till a previous access is done.
- * In some cases (currently when a [UN]LOAD_REQ commands are sent), the single
- * access is achieved by setting a blocking flag, which will fail other
- * competing contexts to send their mailboxes.
- */
-static int qed_mcp_mb_lock(struct qed_hwfn *p_hwfn, u32 cmd)
+static void qed_mcp_reread_offsets(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt)
 {
-	spin_lock_bh(&p_hwfn->mcp_info->lock);
+	u32 generic_por_0 = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
 
-	/* The spinlock shouldn't be acquired when the mailbox command is
-	 * [UN]LOAD_REQ, since the engine is locked by the MFW, and a parallel
-	 * pending [UN]LOAD_REQ command of another PF together with a spinlock
-	 * (i.e. interrupts are disabled) - can lead to a deadlock.
-	 * It is assumed that for a single PF, no other mailbox commands can be
-	 * sent from another context while sending LOAD_REQ, and that any
-	 * parallel commands to UNLOAD_REQ can be cancelled.
+	/* Use MCP history register to check if MCP reset occurred between init
+	 * time and now.
 	 */
-	if (cmd == DRV_MSG_CODE_LOAD_DONE || cmd == DRV_MSG_CODE_UNLOAD_DONE)
-		p_hwfn->mcp_info->block_mb_sending = false;
-
-	if (p_hwfn->mcp_info->block_mb_sending) {
-		DP_NOTICE(p_hwfn,
-			  "Trying to send a MFW mailbox command [0x%x] in parallel to [UN]LOAD_REQ. Aborting.\n",
-			  cmd);
-		spin_unlock_bh(&p_hwfn->mcp_info->lock);
-		return -EBUSY;
-	}
+	if (p_hwfn->mcp_info->mcp_hist != generic_por_0) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SP,
+			   "Rereading MCP offsets [mcp_hist 0x%08x, generic_por_0 0x%08x]\n",
+			   p_hwfn->mcp_info->mcp_hist, generic_por_0);
 
-	if (cmd == DRV_MSG_CODE_LOAD_REQ || cmd == DRV_MSG_CODE_UNLOAD_REQ) {
-		p_hwfn->mcp_info->block_mb_sending = true;
-		spin_unlock_bh(&p_hwfn->mcp_info->lock);
+		qed_load_mcp_offsets(p_hwfn, p_ptt);
+		qed_mcp_cmd_port_init(p_hwfn, p_ptt);
 	}
-
-	return 0;
-}
-
-static void qed_mcp_mb_unlock(struct qed_hwfn *p_hwfn, u32 cmd)
-{
-	if (cmd != DRV_MSG_CODE_LOAD_REQ && cmd != DRV_MSG_CODE_UNLOAD_REQ)
-		spin_unlock_bh(&p_hwfn->mcp_info->lock);
 }
 
 int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 seq = ++p_hwfn->mcp_info->drv_mb_seq;
-	u8 delay = CHIP_MCP_RESP_ITER_US;
-	u32 org_mcp_reset_seq, cnt = 0;
+	u32 org_mcp_reset_seq, seq, delay = CHIP_MCP_RESP_ITER_US, cnt = 0;
 	int rc = 0;
 
-	/* Ensure that only a single thread is accessing the mailbox at a
-	 * certain time.
-	 */
-	rc = qed_mcp_mb_lock(p_hwfn, DRV_MSG_CODE_MCP_RESET);
-	if (rc != 0)
-		return rc;
+	/* Ensure that only a single thread is accessing the mailbox */
+	spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
 
-	/* Set drv command along with the updated sequence */
 	org_mcp_reset_seq = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
-	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header,
-		  (DRV_MSG_CODE_MCP_RESET | seq));
+
+	/* Set drv command along with the updated sequence */
+	qed_mcp_reread_offsets(p_hwfn, p_ptt);
+	seq = ++p_hwfn->mcp_info->drv_mb_seq;
+	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (DRV_MSG_CODE_MCP_RESET | seq));
 
 	do {
 		/* Wait for MFW response */
@@ -281,72 +313,207 @@ int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		rc = -EAGAIN;
 	}
 
-	qed_mcp_mb_unlock(p_hwfn, DRV_MSG_CODE_MCP_RESET);
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 
 	return rc;
 }
 
-static int qed_do_mcp_cmd(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt,
-			  u32 cmd,
-			  u32 param,
-			  u32 *o_mcp_resp,
-			  u32 *o_mcp_param)
+/* Must be called while cmd_lock is acquired */
+static bool qed_mcp_has_pending_cmd(struct qed_hwfn *p_hwfn)
 {
-	u8 delay = CHIP_MCP_RESP_ITER_US;
-	u32 seq, cnt = 1, actual_mb_seq;
-	int rc = 0;
-
-	/* Get actual driver mailbox sequence */
-	actual_mb_seq = DRV_MB_RD(p_hwfn, p_ptt, drv_mb_header) &
-			DRV_MSG_SEQ_NUMBER_MASK;
+	struct qed_mcp_cmd_elem *p_cmd_elem;
 
-	/* Use MCP history register to check if MCP reset occurred between
-	 * init time and now.
+	/* There is at most one pending command at a certain time, and if it
+	 * exists - it is placed at the HEAD of the list.
 	 */
-	if (p_hwfn->mcp_info->mcp_hist !=
-	    qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0)) {
-		DP_VERBOSE(p_hwfn, QED_MSG_SP, "Rereading MCP offsets\n");
-		qed_load_mcp_offsets(p_hwfn, p_ptt);
-		qed_mcp_cmd_port_init(p_hwfn, p_ptt);
+	if (!list_empty(&p_hwfn->mcp_info->cmd_list)) {
+		p_cmd_elem = list_first_entry(&p_hwfn->mcp_info->cmd_list,
+					      struct qed_mcp_cmd_elem, list);
+		return !p_cmd_elem->b_is_completed;
 	}
-	seq = ++p_hwfn->mcp_info->drv_mb_seq;
 
-	/* Set drv param */
-	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_param, param);
+	return false;
+}
 
-	/* Set drv command along with the updated sequence */
-	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (cmd | seq));
+/* Must be called while cmd_lock is acquired */
+static int
+qed_mcp_update_pending_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mcp_mb_params *p_mb_params;
+	struct qed_mcp_cmd_elem *p_cmd_elem;
+	u32 mcp_resp;
+	u16 seq_num;
+
+	mcp_resp = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_header);
+	seq_num = (u16)(mcp_resp & FW_MSG_SEQ_NUMBER_MASK);
+
+	/* Return if no new non-handled response has been received */
+	if (seq_num != p_hwfn->mcp_info->drv_mb_seq)
+		return -EAGAIN;
+
+	p_cmd_elem = qed_mcp_cmd_get_elem(p_hwfn, seq_num);
+	if (!p_cmd_elem) {
+		DP_ERR(p_hwfn,
+		       "Failed to find a pending mailbox cmd that expects sequence number %d\n",
+		       seq_num);
+		return -EINVAL;
+	}
+
+	p_mb_params = p_cmd_elem->p_mb_params;
+
+	/* Get the MFW response along with the sequence number */
+	p_mb_params->mcp_resp = mcp_resp;
+
+	/* Get the MFW param */
+	p_mb_params->mcp_param = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_param);
+
+	/* Get the union data */
+	if (p_mb_params->p_data_dst != NULL && p_mb_params->data_dst_size) {
+		u32 union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
+				      offsetof(struct public_drv_mb,
+					       union_data);
+		qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst,
+				union_data_addr, p_mb_params->data_dst_size);
+	}
+
+	p_cmd_elem->b_is_completed = true;
+
+	return 0;
+}
+
+/* Must be called while cmd_lock is acquired */
+static void __qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt,
+				    struct qed_mcp_mb_params *p_mb_params,
+				    u16 seq_num)
+{
+	union drv_union_data union_data;
+	u32 union_data_addr;
+
+	/* Set the union data */
+	union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
+			  offsetof(struct public_drv_mb, union_data);
+	memset(&union_data, 0, sizeof(union_data));
+	if (p_mb_params->p_data_src != NULL && p_mb_params->data_src_size)
+		memcpy(&union_data, p_mb_params->p_data_src,
+		       p_mb_params->data_src_size);
+	qed_memcpy_to(p_hwfn, p_ptt, union_data_addr, &union_data,
+		      sizeof(union_data));
+
+	/* Set the drv param */
+	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_param, p_mb_params->param);
+
+	/* Set the drv command along with the sequence number */
+	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (p_mb_params->cmd | seq_num));
 
 	DP_VERBOSE(p_hwfn, QED_MSG_SP,
-		   "wrote command (%x) to MFW MB param 0x%08x\n",
-		   (cmd | seq), param);
+		   "MFW mailbox: command 0x%08x param 0x%08x\n",
+		   (p_mb_params->cmd | seq_num), p_mb_params->param);
+}
 
+static int
+_qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       struct qed_mcp_mb_params *p_mb_params,
+		       u32 max_retries, u32 delay)
+{
+	struct qed_mcp_cmd_elem *p_cmd_elem;
+	u32 cnt = 0;
+	u16 seq_num;
+	int rc = 0;
+
+	/* Wait until the mailbox is non-occupied */
 	do {
-		/* Wait for MFW response */
+		/* Exit the loop if there is no pending command, or if the
+		 * pending command is completed during this iteration.
+		 * The spinlock stays locked until the command is sent.
+		 */
+
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+		if (!qed_mcp_has_pending_cmd(p_hwfn))
+			break;
+
+		rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
+		if (!rc)
+			break;
+		else if (rc != -EAGAIN)
+			goto err;
+
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 		udelay(delay);
-		*o_mcp_resp = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_header);
+	} while (++cnt < max_retries);
 
-		/* Give the FW up to 5 second (500*10ms) */
-	} while ((seq != (*o_mcp_resp & FW_MSG_SEQ_NUMBER_MASK)) &&
-		 (cnt++ < QED_DRV_MB_MAX_RETRIES));
+	if (cnt >= max_retries) {
+		DP_NOTICE(p_hwfn,
+			  "The MFW mailbox is occupied by an uncompleted command. Failed to send command 0x%08x [param 0x%08x].\n",
+			  p_mb_params->cmd, p_mb_params->param);
+		return -EAGAIN;
+	}
 
-	DP_VERBOSE(p_hwfn, QED_MSG_SP,
-		   "[after %d ms] read (%x) seq is (%x) from FW MB\n",
-		   cnt * delay, *o_mcp_resp, seq);
-
-	/* Is this a reply to our command? */
-	if (seq == (*o_mcp_resp & FW_MSG_SEQ_NUMBER_MASK)) {
-		*o_mcp_resp &= FW_MSG_CODE_MASK;
-		/* Get the MCP param */
-		*o_mcp_param = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_param);
-	} else {
-		/* FW BUG! */
-		DP_ERR(p_hwfn, "MFW failed to respond [cmd 0x%x param 0x%x]\n",
-		       cmd, param);
-		*o_mcp_resp = 0;
-		rc = -EAGAIN;
+	/* Send the mailbox command */
+	qed_mcp_reread_offsets(p_hwfn, p_ptt);
+	seq_num = ++p_hwfn->mcp_info->drv_mb_seq;
+	p_cmd_elem = qed_mcp_cmd_add_elem(p_hwfn, p_mb_params, seq_num);
+	if (!p_cmd_elem) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	__qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, seq_num);
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+	/* Wait for the MFW response */
+	do {
+		/* Exit the loop if the command is already completed, or if the
+		 * command is completed during this iteration.
+		 * The spinlock stays locked until the list element is removed.
+		 */
+
+		udelay(delay);
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+		if (p_cmd_elem->b_is_completed)
+			break;
+
+		rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
+		if (!rc)
+			break;
+		else if (rc != -EAGAIN)
+			goto err;
+
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+	} while (++cnt < max_retries);
+
+	if (cnt >= max_retries) {
+		DP_NOTICE(p_hwfn,
+			  "The MFW failed to respond to command 0x%08x [param 0x%08x].\n",
+			  p_mb_params->cmd, p_mb_params->param);
+
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+		qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+		return -EAGAIN;
 	}
+
+	qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "MFW mailbox: response 0x%08x param 0x%08x [after %d.%03d ms]\n",
+		   p_mb_params->mcp_resp,
+		   p_mb_params->mcp_param,
+		   (cnt * delay) / 1000, (cnt * delay) % 1000);
+
+	/* Clear the sequence number from the MFW response */
+	p_mb_params->mcp_resp &= FW_MSG_CODE_MASK;
+
+	return 0;
+
+err:
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 	return rc;
 }
 
@@ -354,9 +521,9 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
 				 struct qed_ptt *p_ptt,
 				 struct qed_mcp_mb_params *p_mb_params)
 {
-	u32 union_data_addr;
-
-	int rc;
+	size_t union_data_size = sizeof(union drv_union_data);
+	u32 max_retries = QED_DRV_MB_MAX_RETRIES;
+	u32 delay = CHIP_MCP_RESP_ITER_US;
 
 	/* MCP not initialized */
 	if (!qed_mcp_is_init(p_hwfn)) {
@@ -364,33 +531,17 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
 		return -EBUSY;
 	}
 
-	union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
-			  offsetof(struct public_drv_mb, union_data);
-
-	/* Ensure that only a single thread is accessing the mailbox at a
-	 * certain time.
-	 */
-	rc = qed_mcp_mb_lock(p_hwfn, p_mb_params->cmd);
-	if (rc)
-		return rc;
-
-	if (p_mb_params->p_data_src != NULL)
-		qed_memcpy_to(p_hwfn, p_ptt, union_data_addr,
-			      p_mb_params->p_data_src,
-			      sizeof(*p_mb_params->p_data_src));
-
-	rc = qed_do_mcp_cmd(p_hwfn, p_ptt, p_mb_params->cmd,
-			    p_mb_params->param, &p_mb_params->mcp_resp,
-			    &p_mb_params->mcp_param);
-
-	if (p_mb_params->p_data_dst != NULL)
-		qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst,
-				union_data_addr,
-				sizeof(*p_mb_params->p_data_dst));
-
-	qed_mcp_mb_unlock(p_hwfn, p_mb_params->cmd);
+	if (p_mb_params->data_src_size > union_data_size ||
+	    p_mb_params->data_dst_size > union_data_size) {
+		DP_ERR(p_hwfn,
+		       "The provided size is larger than the union data size [src_size %u, dst_size %u, union_data_size %zu]\n",
+		       p_mb_params->data_src_size,
+		       p_mb_params->data_dst_size, union_data_size);
+		return -EINVAL;
+	}
 
-	return rc;
+	return _qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, max_retries,
+				      delay);
 }
 
 int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
@@ -401,32 +552,12 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
 		u32 *o_mcp_param)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data data_src;
 	int rc;
 
 	memset(&mb_params, 0, sizeof(mb_params));
-	memset(&data_src, 0, sizeof(data_src));
 	mb_params.cmd = cmd;
 	mb_params.param = param;
 
-	/* In case of UNLOAD_DONE, set the primary MAC */
-	if ((cmd == DRV_MSG_CODE_UNLOAD_DONE) &&
-	    (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED)) {
-		u8 *p_mac = p_hwfn->cdev->wol_mac;
-
-		data_src.wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
-		data_src.wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
-					     p_mac[4] << 8 | p_mac[5];
-
-		DP_VERBOSE(p_hwfn,
-			   (QED_MSG_SP | NETIF_MSG_IFDOWN),
-			   "Setting WoL MAC: %pM --> [%08x,%08x]\n",
-			   p_mac, data_src.wol_mac.mac_upper,
-			   data_src.wol_mac.mac_lower);
-
-		mb_params.p_data_src = &data_src;
-	}
-
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		return rc;
@@ -445,13 +576,17 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
 		       u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	u8 raw_data[MCP_DRV_NVM_BUF_LEN];
 	int rc;
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = cmd;
 	mb_params.param = param;
-	mb_params.p_data_dst = &union_data;
+	mb_params.p_data_dst = raw_data;
+
+	/* Use the maximal value since the actual one is part of the response */
+	mb_params.data_dst_size = MCP_DRV_NVM_BUF_LEN;
+
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		return rc;
@@ -460,55 +595,413 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
 	*o_mcp_param = mb_params.mcp_param;
 
 	*o_txn_size = *o_mcp_param;
-	memcpy(o_buf, &union_data.raw_data, *o_txn_size);
+	memcpy(o_buf, raw_data, *o_txn_size);
 
 	return 0;
 }
 
-int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
-		     struct qed_ptt *p_ptt, u32 *p_load_code)
+static bool
+qed_mcp_can_force_load(u8 drv_role,
+		       u8 exist_drv_role,
+		       enum qed_override_force_load override_force_load)
+{
+	bool can_force_load = false;
+
+	switch (override_force_load) {
+	case QED_OVERRIDE_FORCE_LOAD_ALWAYS:
+		can_force_load = true;
+		break;
+	case QED_OVERRIDE_FORCE_LOAD_NEVER:
+		can_force_load = false;
+		break;
+	default:
+		can_force_load = (drv_role == DRV_ROLE_OS &&
+				  exist_drv_role == DRV_ROLE_PREBOOT) ||
+				 (drv_role == DRV_ROLE_KDUMP &&
+				  exist_drv_role == DRV_ROLE_OS);
+		break;
+	}
+
+	return can_force_load;
+}
+
+static int qed_mcp_cancel_load_req(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt)
+{
+	u32 resp = 0, param = 0;
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_CANCEL_LOAD_REQ, 0,
+			 &resp, &param);
+	if (rc)
+		DP_NOTICE(p_hwfn,
+			  "Failed to send cancel load request, rc = %d\n", rc);
+
+	return rc;
+}
+
+#define CONFIG_QEDE_BITMAP_IDX		BIT(0)
+#define CONFIG_QED_SRIOV_BITMAP_IDX	BIT(1)
+#define CONFIG_QEDR_BITMAP_IDX		BIT(2)
+#define CONFIG_QEDF_BITMAP_IDX		BIT(4)
+#define CONFIG_QEDI_BITMAP_IDX		BIT(5)
+#define CONFIG_QED_LL2_BITMAP_IDX	BIT(6)
+
+static u32 qed_get_config_bitmap(void)
+{
+	u32 config_bitmap = 0x0;
+
+	if (IS_ENABLED(CONFIG_QEDE))
+		config_bitmap |= CONFIG_QEDE_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_SRIOV))
+		config_bitmap |= CONFIG_QED_SRIOV_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_RDMA))
+		config_bitmap |= CONFIG_QEDR_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_FCOE))
+		config_bitmap |= CONFIG_QEDF_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_ISCSI))
+		config_bitmap |= CONFIG_QEDI_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_LL2))
+		config_bitmap |= CONFIG_QED_LL2_BITMAP_IDX;
+
+	return config_bitmap;
+}
+
+struct qed_load_req_in_params {
+	u8 hsi_ver;
+#define QED_LOAD_REQ_HSI_VER_DEFAULT	0
+#define QED_LOAD_REQ_HSI_VER_1		1
+	u32 drv_ver_0;
+	u32 drv_ver_1;
+	u32 fw_ver;
+	u8 drv_role;
+	u8 timeout_val;
+	u8 force_cmd;
+	bool avoid_eng_reset;
+};
+
+struct qed_load_req_out_params {
+	u32 load_code;
+	u32 exist_drv_ver_0;
+	u32 exist_drv_ver_1;
+	u32 exist_fw_ver;
+	u8 exist_drv_role;
+	u8 mfw_hsi_ver;
+	bool drv_exists;
+};
+
+static int
+__qed_mcp_load_req(struct qed_hwfn *p_hwfn,
+		   struct qed_ptt *p_ptt,
+		   struct qed_load_req_in_params *p_in_params,
+		   struct qed_load_req_out_params *p_out_params)
 {
-	struct qed_dev *cdev = p_hwfn->cdev;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	struct load_req_stc load_req;
+	struct load_rsp_stc load_rsp;
+	u32 hsi_ver;
 	int rc;
 
+	memset(&load_req, 0, sizeof(load_req));
+	load_req.drv_ver_0 = p_in_params->drv_ver_0;
+	load_req.drv_ver_1 = p_in_params->drv_ver_1;
+	load_req.fw_ver = p_in_params->fw_ver;
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_ROLE, p_in_params->drv_role);
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_LOCK_TO,
+			  p_in_params->timeout_val);
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_FORCE,
+			  p_in_params->force_cmd);
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_FLAGS0,
+			  p_in_params->avoid_eng_reset);
+
+	hsi_ver = (p_in_params->hsi_ver == QED_LOAD_REQ_HSI_VER_DEFAULT) ?
+		  DRV_ID_MCP_HSI_VER_CURRENT :
+		  (p_in_params->hsi_ver << DRV_ID_MCP_HSI_VER_SHIFT);
+
 	memset(&mb_params, 0, sizeof(mb_params));
-	/* Load Request */
 	mb_params.cmd = DRV_MSG_CODE_LOAD_REQ;
-	mb_params.param = PDA_COMP | DRV_ID_MCP_HSI_VER_CURRENT |
-			  cdev->drv_type;
-	memcpy(&union_data.ver_str, cdev->ver_str, MCP_DRV_VER_STR_SIZE);
-	mb_params.p_data_src = &union_data;
-	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	mb_params.param = PDA_COMP | hsi_ver | p_hwfn->cdev->drv_type;
+	mb_params.p_data_src = &load_req;
+	mb_params.data_src_size = sizeof(load_req);
+	mb_params.p_data_dst = &load_rsp;
+	mb_params.data_dst_size = sizeof(load_rsp);
 
-	/* if mcp fails to respond we must abort */
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Load Request: param 0x%08x [init_hw %d, drv_type %d, hsi_ver %d, pda 0x%04x]\n",
+		   mb_params.param,
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_DRV_INIT_HW),
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_DRV_TYPE),
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_MCP_HSI_VER),
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_PDA_COMP_VER));
+
+	if (p_in_params->hsi_ver != QED_LOAD_REQ_HSI_VER_1) {
+		DP_VERBOSE(p_hwfn, QED_MSG_SP,
+			   "Load Request: drv_ver 0x%08x_0x%08x, fw_ver 0x%08x, misc0 0x%08x [role %d, timeout %d, force %d, flags0 0x%x]\n",
+			   load_req.drv_ver_0,
+			   load_req.drv_ver_1,
+			   load_req.fw_ver,
+			   load_req.misc0,
+			   QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_ROLE),
+			   QED_MFW_GET_FIELD(load_req.misc0,
+					     LOAD_REQ_LOCK_TO),
+			   QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_FORCE),
+			   QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_FLAGS0));
+	}
+
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc) {
-		DP_ERR(p_hwfn, "MCP response failure, aborting\n");
+		DP_NOTICE(p_hwfn, "Failed to send load request, rc = %d\n", rc);
 		return rc;
 	}
 
-	*p_load_code = mb_params.mcp_resp;
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Load Response: resp 0x%08x\n", mb_params.mcp_resp);
+	p_out_params->load_code = mb_params.mcp_resp;
+
+	if (p_in_params->hsi_ver != QED_LOAD_REQ_HSI_VER_1 &&
+	    p_out_params->load_code != FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SP,
+			   "Load Response: exist_drv_ver 0x%08x_0x%08x, exist_fw_ver 0x%08x, misc0 0x%08x [exist_role %d, mfw_hsi %d, flags0 0x%x]\n",
+			   load_rsp.drv_ver_0,
+			   load_rsp.drv_ver_1,
+			   load_rsp.fw_ver,
+			   load_rsp.misc0,
+			   QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_ROLE),
+			   QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_HSI),
+			   QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_FLAGS0));
+
+		p_out_params->exist_drv_ver_0 = load_rsp.drv_ver_0;
+		p_out_params->exist_drv_ver_1 = load_rsp.drv_ver_1;
+		p_out_params->exist_fw_ver = load_rsp.fw_ver;
+		p_out_params->exist_drv_role =
+		    QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_ROLE);
+		p_out_params->mfw_hsi_ver =
+		    QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_HSI);
+		p_out_params->drv_exists =
+		    QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_FLAGS0) &
+		    LOAD_RSP_FLAGS0_DRV_EXISTS;
+	}
+
+	return 0;
+}
+
+static int eocre_get_mfw_drv_role(struct qed_hwfn *p_hwfn,
+				  enum qed_drv_role drv_role,
+				  u8 *p_mfw_drv_role)
+{
+	switch (drv_role) {
+	case QED_DRV_ROLE_OS:
+		*p_mfw_drv_role = DRV_ROLE_OS;
+		break;
+	case QED_DRV_ROLE_KDUMP:
+		*p_mfw_drv_role = DRV_ROLE_KDUMP;
+		break;
+	default:
+		DP_ERR(p_hwfn, "Unexpected driver role %d\n", drv_role);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum qed_load_req_force {
+	QED_LOAD_REQ_FORCE_NONE,
+	QED_LOAD_REQ_FORCE_PF,
+	QED_LOAD_REQ_FORCE_ALL,
+};
+
+static void qed_get_mfw_force_cmd(struct qed_hwfn *p_hwfn,
+
+				  enum qed_load_req_force force_cmd,
+				  u8 *p_mfw_force_cmd)
+{
+	switch (force_cmd) {
+	case QED_LOAD_REQ_FORCE_NONE:
+		*p_mfw_force_cmd = LOAD_REQ_FORCE_NONE;
+		break;
+	case QED_LOAD_REQ_FORCE_PF:
+		*p_mfw_force_cmd = LOAD_REQ_FORCE_PF;
+		break;
+	case QED_LOAD_REQ_FORCE_ALL:
+		*p_mfw_force_cmd = LOAD_REQ_FORCE_ALL;
+		break;
+	}
+}
+
+int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
+		     struct qed_ptt *p_ptt,
+		     struct qed_load_req_params *p_params)
+{
+	struct qed_load_req_out_params out_params;
+	struct qed_load_req_in_params in_params;
+	u8 mfw_drv_role, mfw_force_cmd;
+	int rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_DEFAULT;
+	in_params.drv_ver_0 = QED_VERSION;
+	in_params.drv_ver_1 = qed_get_config_bitmap();
+	in_params.fw_ver = STORM_FW_VERSION;
+	rc = eocre_get_mfw_drv_role(p_hwfn, p_params->drv_role, &mfw_drv_role);
+	if (rc)
+		return rc;
+
+	in_params.drv_role = mfw_drv_role;
+	in_params.timeout_val = p_params->timeout_val;
+	qed_get_mfw_force_cmd(p_hwfn,
+			      QED_LOAD_REQ_FORCE_NONE, &mfw_force_cmd);
+
+	in_params.force_cmd = mfw_force_cmd;
+	in_params.avoid_eng_reset = p_params->avoid_eng_reset;
 
-	/* If MFW refused (e.g. other port is in diagnostic mode) we
-	 * must abort. This can happen in the following cases:
-	 * - Other port is in diagnostic mode
-	 * - Previously loaded function on the engine is not compliant with
-	 *   the requester.
-	 * - MFW cannot cope with the requester's DRV_MFW_HSI_VERSION.
-	 *      -
+	memset(&out_params, 0, sizeof(out_params));
+	rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params, &out_params);
+	if (rc)
+		return rc;
+
+	/* First handle cases where another load request should/might be sent:
+	 * - MFW expects the old interface [HSI version = 1]
+	 * - MFW responds that a force load request is required
 	 */
-	if (!(*p_load_code) ||
-	    ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_HSI) ||
-	    ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_PDA) ||
-	    ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_DIAG)) {
-		DP_ERR(p_hwfn, "MCP refused load request, aborting\n");
+	if (out_params.load_code == FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1) {
+		DP_INFO(p_hwfn,
+			"MFW refused a load request due to HSI > 1. Resending with HSI = 1\n");
+
+		in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_1;
+		memset(&out_params, 0, sizeof(out_params));
+		rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params, &out_params);
+		if (rc)
+			return rc;
+	} else if (out_params.load_code ==
+		   FW_MSG_CODE_DRV_LOAD_REFUSED_REQUIRES_FORCE) {
+		if (qed_mcp_can_force_load(in_params.drv_role,
+					   out_params.exist_drv_role,
+					   p_params->override_force_load)) {
+			DP_INFO(p_hwfn,
+				"A force load is required [{role, fw_ver, drv_ver}: loading={%d, 0x%08x, x%08x_0x%08x}, existing={%d, 0x%08x, 0x%08x_0x%08x}]\n",
+				in_params.drv_role, in_params.fw_ver,
+				in_params.drv_ver_0, in_params.drv_ver_1,
+				out_params.exist_drv_role,
+				out_params.exist_fw_ver,
+				out_params.exist_drv_ver_0,
+				out_params.exist_drv_ver_1);
+
+			qed_get_mfw_force_cmd(p_hwfn,
+					      QED_LOAD_REQ_FORCE_ALL,
+					      &mfw_force_cmd);
+
+			in_params.force_cmd = mfw_force_cmd;
+			memset(&out_params, 0, sizeof(out_params));
+			rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params,
+						&out_params);
+			if (rc)
+				return rc;
+		} else {
+			DP_NOTICE(p_hwfn,
+				  "A force load is required [{role, fw_ver, drv_ver}: loading={%d, 0x%08x, x%08x_0x%08x}, existing={%d, 0x%08x, 0x%08x_0x%08x}] - Avoid\n",
+				  in_params.drv_role, in_params.fw_ver,
+				  in_params.drv_ver_0, in_params.drv_ver_1,
+				  out_params.exist_drv_role,
+				  out_params.exist_fw_ver,
+				  out_params.exist_drv_ver_0,
+				  out_params.exist_drv_ver_1);
+			DP_NOTICE(p_hwfn,
+				  "Avoid sending a force load request to prevent disruption of active PFs\n");
+
+			qed_mcp_cancel_load_req(p_hwfn, p_ptt);
+			return -EBUSY;
+		}
+	}
+
+	/* Now handle the other types of responses.
+	 * The "REFUSED_HSI_1" and "REFUSED_REQUIRES_FORCE" responses are not
+	 * expected here after the additional revised load requests were sent.
+	 */
+	switch (out_params.load_code) {
+	case FW_MSG_CODE_DRV_LOAD_ENGINE:
+	case FW_MSG_CODE_DRV_LOAD_PORT:
+	case FW_MSG_CODE_DRV_LOAD_FUNCTION:
+		if (out_params.mfw_hsi_ver != QED_LOAD_REQ_HSI_VER_1 &&
+		    out_params.drv_exists) {
+			/* The role and fw/driver version match, but the PF is
+			 * already loaded and has not been unloaded gracefully.
+			 */
+			DP_NOTICE(p_hwfn,
+				  "PF is already loaded\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unexpected refusal to load request [resp 0x%08x]. Aborting.\n",
+			  out_params.load_code);
 		return -EBUSY;
 	}
 
+	p_params->load_code = out_params.load_code;
+
 	return 0;
 }
 
+int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 wol_param, mcp_resp, mcp_param;
+
+	switch (p_hwfn->cdev->wol_config) {
+	case QED_OV_WOL_DISABLED:
+		wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
+		break;
+	case QED_OV_WOL_ENABLED:
+		wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unknown WoL configuration %02x\n",
+			  p_hwfn->cdev->wol_config);
+		/* Fallthrough */
+	case QED_OV_WOL_DEFAULT:
+		wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
+	}
+
+	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_UNLOAD_REQ, wol_param,
+			   &mcp_resp, &mcp_param);
+}
+
+int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mcp_mb_params mb_params;
+	struct mcp_mac wol_mac;
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_UNLOAD_DONE;
+
+	/* Set the primary MAC if WoL is enabled */
+	if (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED) {
+		u8 *p_mac = p_hwfn->cdev->wol_mac;
+
+		memset(&wol_mac, 0, sizeof(wol_mac));
+		wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
+		wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
+				    p_mac[4] << 8 | p_mac[5];
+
+		DP_VERBOSE(p_hwfn,
+			   (QED_MSG_SP | NETIF_MSG_IFDOWN),
+			   "Setting WoL MAC: %pM --> [%08x,%08x]\n",
+			   p_mac, wol_mac.mac_upper, wol_mac.mac_lower);
+
+		mb_params.p_data_src = &wol_mac;
+		mb_params.data_src_size = sizeof(wol_mac);
+	}
+
+	return qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+}
+
 static void qed_mcp_handle_vf_flr(struct qed_hwfn *p_hwfn,
 				  struct qed_ptt *p_ptt)
 {
@@ -549,7 +1042,6 @@ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn,
 	u32 func_addr = SECTION_ADDR(mfw_func_offsize,
 				     MCP_PF_ID(p_hwfn));
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
 	int rc;
 	int i;
 
@@ -560,8 +1052,8 @@ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn,
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = DRV_MSG_CODE_VF_DISABLED_DONE;
-	memcpy(&union_data.ack_vf_disabled, vfs_to_ack, VF_MAX_STATIC / 8);
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = vfs_to_ack;
+	mb_params.data_src_size = VF_MAX_STATIC / 8;
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc) {
 		DP_NOTICE(p_hwfn, "Failed to pass ACK for VF flr to MFW\n");
@@ -744,33 +1236,31 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 {
 	struct qed_mcp_link_params *params = &p_hwfn->mcp_info->link_input;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
-	struct eth_phy_cfg *phy_cfg;
+	struct eth_phy_cfg phy_cfg;
 	int rc = 0;
 	u32 cmd;
 
 	/* Set the shmem configuration according to params */
-	phy_cfg = &union_data.drv_phy_cfg;
-	memset(phy_cfg, 0, sizeof(*phy_cfg));
+	memset(&phy_cfg, 0, sizeof(phy_cfg));
 	cmd = b_up ? DRV_MSG_CODE_INIT_PHY : DRV_MSG_CODE_LINK_RESET;
 	if (!params->speed.autoneg)
-		phy_cfg->speed = params->speed.forced_speed;
-	phy_cfg->pause |= (params->pause.autoneg) ? ETH_PAUSE_AUTONEG : 0;
-	phy_cfg->pause |= (params->pause.forced_rx) ? ETH_PAUSE_RX : 0;
-	phy_cfg->pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
-	phy_cfg->adv_speed = params->speed.advertised_speeds;
-	phy_cfg->loopback_mode = params->loopback_mode;
+		phy_cfg.speed = params->speed.forced_speed;
+	phy_cfg.pause |= (params->pause.autoneg) ? ETH_PAUSE_AUTONEG : 0;
+	phy_cfg.pause |= (params->pause.forced_rx) ? ETH_PAUSE_RX : 0;
+	phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
+	phy_cfg.adv_speed = params->speed.advertised_speeds;
+	phy_cfg.loopback_mode = params->loopback_mode;
 
 	p_hwfn->b_drv_link_init = b_up;
 
 	if (b_up) {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
 			   "Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, features 0x%08x\n",
-			   phy_cfg->speed,
-			   phy_cfg->pause,
-			   phy_cfg->adv_speed,
-			   phy_cfg->loopback_mode,
-			   phy_cfg->feature_config_flags);
+			   phy_cfg.speed,
+			   phy_cfg.pause,
+			   phy_cfg.adv_speed,
+			   phy_cfg.loopback_mode,
+			   phy_cfg.feature_config_flags);
 	} else {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
 			   "Resetting link\n");
@@ -778,7 +1268,8 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = cmd;
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = &phy_cfg;
+	mb_params.data_src_size = sizeof(phy_cfg);
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 
 	/* if mcp fails to respond we must abort */
@@ -805,7 +1296,6 @@ static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 	enum qed_mcp_protocol_type stats_type;
 	union qed_mcp_protocol_stats stats;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
 	u32 hsi_param;
 
 	switch (type) {
@@ -835,8 +1325,8 @@ static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = DRV_MSG_CODE_GET_STATS;
 	mb_params.param = hsi_param;
-	memcpy(&union_data, &stats, sizeof(stats));
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = &stats;
+	mb_params.data_src_size = sizeof(stats);
 	qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 }
 
@@ -963,7 +1453,7 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 			qed_mcp_update_bw(p_hwfn, p_ptt);
 			break;
 		default:
-			DP_NOTICE(p_hwfn, "Unimplemented MFW message %d\n", i);
+			DP_INFO(p_hwfn, "Unimplemented MFW message %d\n", i);
 			rc = -EINVAL;
 		}
 	}
@@ -1316,24 +1806,23 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
 			 struct qed_ptt *p_ptt,
 			 struct qed_mcp_drv_version *p_ver)
 {
-	struct drv_version_stc *p_drv_version;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	struct drv_version_stc drv_version;
 	__be32 val;
 	u32 i;
 	int rc;
 
-	p_drv_version = &union_data.drv_version;
-	p_drv_version->version = p_ver->version;
-
+	memset(&drv_version, 0, sizeof(drv_version));
+	drv_version.version = p_ver->version;
 	for (i = 0; i < (MCP_DRV_VER_STR_SIZE - 4) / sizeof(u32); i++) {
 		val = cpu_to_be32(*((u32 *)&p_ver->name[i * sizeof(u32)]));
-		*(__be32 *)&p_drv_version->name[i * sizeof(u32)] = val;
+		*(__be32 *)&drv_version.name[i * sizeof(u32)] = val;
 	}
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = DRV_MSG_CODE_SET_VERSION;
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = &drv_version;
+	mb_params.data_src_size = sizeof(drv_version);
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		DP_ERR(p_hwfn, "MCP response failure, aborting\n");
@@ -1450,7 +1939,7 @@ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u8 *mac)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	u32 mfw_mac[2];
 	int rc;
 
 	memset(&mb_params, 0, sizeof(mb_params));
@@ -1458,8 +1947,17 @@ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
 	mb_params.param = DRV_MSG_CODE_VMAC_TYPE_MAC <<
 			  DRV_MSG_CODE_VMAC_TYPE_SHIFT;
 	mb_params.param |= MCP_PF_ID(p_hwfn);
-	ether_addr_copy(&union_data.raw_data[0], mac);
-	mb_params.p_data_src = &union_data;
+
+	/* MCP is BE, and on LE platforms PCI would swap access to SHMEM
+	 * in 32-bit granularity.
+	 * So the MAC has to be set in native order [and not byte order],
+	 * otherwise it would be read incorrectly by MFW after swap.
+	 */
+	mfw_mac[0] = mac[0] << 24 | mac[1] << 16 | mac[2] << 8 | mac[3];
+	mfw_mac[1] = mac[4] << 24 | mac[5] << 16;
+
+	mb_params.p_data_src = (u8 *)mfw_mac;
+	mb_params.data_src_size = 8;
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		DP_ERR(p_hwfn, "Failed to send mac address, rc = %d\n", rc);
@@ -1724,52 +2222,426 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-#define QED_RESC_ALLOC_VERSION_MAJOR    1
+static enum resource_id_enum qed_mcp_get_mfw_res_id(enum qed_resources res_id)
+{
+	enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
+
+	switch (res_id) {
+	case QED_SB:
+		mfw_res_id = RESOURCE_NUM_SB_E;
+		break;
+	case QED_L2_QUEUE:
+		mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
+		break;
+	case QED_VPORT:
+		mfw_res_id = RESOURCE_NUM_VPORT_E;
+		break;
+	case QED_RSS_ENG:
+		mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
+		break;
+	case QED_PQ:
+		mfw_res_id = RESOURCE_NUM_PQ_E;
+		break;
+	case QED_RL:
+		mfw_res_id = RESOURCE_NUM_RL_E;
+		break;
+	case QED_MAC:
+	case QED_VLAN:
+		/* Each VFC resource can accommodate both a MAC and a VLAN */
+		mfw_res_id = RESOURCE_VFC_FILTER_E;
+		break;
+	case QED_ILT:
+		mfw_res_id = RESOURCE_ILT_E;
+		break;
+	case QED_LL2_QUEUE:
+		mfw_res_id = RESOURCE_LL2_QUEUE_E;
+		break;
+	case QED_RDMA_CNQ_RAM:
+	case QED_CMDQS_CQS:
+		/* CNQ/CMDQS are the same resource */
+		mfw_res_id = RESOURCE_CQS_E;
+		break;
+	case QED_RDMA_STATS_QUEUE:
+		mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
+		break;
+	case QED_BDQ:
+		mfw_res_id = RESOURCE_BDQ_E;
+		break;
+	default:
+		break;
+	}
+
+	return mfw_res_id;
+}
+
+#define QED_RESC_ALLOC_VERSION_MAJOR    2
 #define QED_RESC_ALLOC_VERSION_MINOR    0
 #define QED_RESC_ALLOC_VERSION				     \
 	((QED_RESC_ALLOC_VERSION_MAJOR <<		     \
 	  DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT) | \
 	 (QED_RESC_ALLOC_VERSION_MINOR <<		     \
 	  DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT))
-int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt,
-			  struct resource_info *p_resc_info,
-			  u32 *p_mcp_resp, u32 *p_mcp_param)
+
+struct qed_resc_alloc_in_params {
+	u32 cmd;
+	enum qed_resources res_id;
+	u32 resc_max_val;
+};
+
+struct qed_resc_alloc_out_params {
+	u32 mcp_resp;
+	u32 mcp_param;
+	u32 resc_num;
+	u32 resc_start;
+	u32 vf_resc_num;
+	u32 vf_resc_start;
+	u32 flags;
+};
+
+static int
+qed_mcp_resc_allocation_msg(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt,
+			    struct qed_resc_alloc_in_params *p_in_params,
+			    struct qed_resc_alloc_out_params *p_out_params)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	struct resource_info mfw_resc_info;
 	int rc;
 
+	memset(&mfw_resc_info, 0, sizeof(mfw_resc_info));
+
+	mfw_resc_info.res_id = qed_mcp_get_mfw_res_id(p_in_params->res_id);
+	if (mfw_resc_info.res_id == RESOURCE_NUM_INVALID) {
+		DP_ERR(p_hwfn,
+		       "Failed to match resource %d [%s] with the MFW resources\n",
+		       p_in_params->res_id,
+		       qed_hw_get_resc_name(p_in_params->res_id));
+		return -EINVAL;
+	}
+
+	switch (p_in_params->cmd) {
+	case DRV_MSG_SET_RESOURCE_VALUE_MSG:
+		mfw_resc_info.size = p_in_params->resc_max_val;
+		/* Fallthrough */
+	case DRV_MSG_GET_RESOURCE_ALLOC_MSG:
+		break;
+	default:
+		DP_ERR(p_hwfn, "Unexpected resource alloc command [0x%08x]\n",
+		       p_in_params->cmd);
+		return -EINVAL;
+	}
+
 	memset(&mb_params, 0, sizeof(mb_params));
-	memset(&union_data, 0, sizeof(union_data));
-	mb_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+	mb_params.cmd = p_in_params->cmd;
 	mb_params.param = QED_RESC_ALLOC_VERSION;
+	mb_params.p_data_src = &mfw_resc_info;
+	mb_params.data_src_size = sizeof(mfw_resc_info);
+	mb_params.p_data_dst = mb_params.p_data_src;
+	mb_params.data_dst_size = mb_params.data_src_size;
 
-	/* Need to have a sufficient large struct, as the cmd_and_union
-	 * is going to do memcpy from and to it.
-	 */
-	memcpy(&union_data.resource, p_resc_info, sizeof(*p_resc_info));
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "Resource message request: cmd 0x%08x, res_id %d [%s], hsi_version %d.%d, val 0x%x\n",
+		   p_in_params->cmd,
+		   p_in_params->res_id,
+		   qed_hw_get_resc_name(p_in_params->res_id),
+		   QED_MFW_GET_FIELD(mb_params.param,
+				     DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR),
+		   QED_MFW_GET_FIELD(mb_params.param,
+				     DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR),
+		   p_in_params->resc_max_val);
 
-	mb_params.p_data_src = &union_data;
-	mb_params.p_data_dst = &union_data;
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		return rc;
 
-	/* Copy the data back */
-	memcpy(p_resc_info, &union_data.resource, sizeof(*p_resc_info));
-	*p_mcp_resp = mb_params.mcp_resp;
-	*p_mcp_param = mb_params.mcp_param;
+	p_out_params->mcp_resp = mb_params.mcp_resp;
+	p_out_params->mcp_param = mb_params.mcp_param;
+	p_out_params->resc_num = mfw_resc_info.size;
+	p_out_params->resc_start = mfw_resc_info.offset;
+	p_out_params->vf_resc_num = mfw_resc_info.vf_size;
+	p_out_params->vf_resc_start = mfw_resc_info.vf_offset;
+	p_out_params->flags = mfw_resc_info.flags;
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "Resource message response: mfw_hsi_version %d.%d, num 0x%x, start 0x%x, vf_num 0x%x, vf_start 0x%x, flags 0x%08x\n",
+		   QED_MFW_GET_FIELD(p_out_params->mcp_param,
+				     FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR),
+		   QED_MFW_GET_FIELD(p_out_params->mcp_param,
+				     FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR),
+		   p_out_params->resc_num,
+		   p_out_params->resc_start,
+		   p_out_params->vf_resc_num,
+		   p_out_params->vf_resc_start, p_out_params->flags);
+
+	return 0;
+}
+
+int
+qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 enum qed_resources res_id,
+			 u32 resc_max_val, u32 *p_mcp_resp)
+{
+	struct qed_resc_alloc_out_params out_params;
+	struct qed_resc_alloc_in_params in_params;
+	int rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	in_params.cmd = DRV_MSG_SET_RESOURCE_VALUE_MSG;
+	in_params.res_id = res_id;
+	in_params.resc_max_val = resc_max_val;
+	memset(&out_params, 0, sizeof(out_params));
+	rc = qed_mcp_resc_allocation_msg(p_hwfn, p_ptt, &in_params,
+					 &out_params);
+	if (rc)
+		return rc;
+
+	*p_mcp_resp = out_params.mcp_resp;
+
+	return 0;
+}
+
+int
+qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt,
+		      enum qed_resources res_id,
+		      u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start)
+{
+	struct qed_resc_alloc_out_params out_params;
+	struct qed_resc_alloc_in_params in_params;
+	int rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	in_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+	in_params.res_id = res_id;
+	memset(&out_params, 0, sizeof(out_params));
+	rc = qed_mcp_resc_allocation_msg(p_hwfn, p_ptt, &in_params,
+					 &out_params);
+	if (rc)
+		return rc;
+
+	*p_mcp_resp = out_params.mcp_resp;
+
+	if (*p_mcp_resp == FW_MSG_CODE_RESOURCE_ALLOC_OK) {
+		*p_resc_num = out_params.resc_num;
+		*p_resc_start = out_params.resc_start;
+	}
+
+	return 0;
+}
+
+int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 mcp_resp, mcp_param;
+
+	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_INITIATE_PF_FLR, 0,
+			   &mcp_resp, &mcp_param);
+}
+
+static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt,
+				u32 param, u32 *p_mcp_resp, u32 *p_mcp_param)
+{
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, param,
+			 p_mcp_resp, p_mcp_param);
+	if (rc)
+		return rc;
+
+	if (*p_mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The resource command is unsupported by the MFW\n");
+		return -EINVAL;
+	}
+
+	if (*p_mcp_param == RESOURCE_OPCODE_UNKNOWN_CMD) {
+		u8 opcode = QED_MFW_GET_FIELD(param, RESOURCE_CMD_REQ_OPCODE);
+
+		DP_NOTICE(p_hwfn,
+			  "The resource command is unknown to the MFW [param 0x%08x, opcode %d]\n",
+			  param, opcode);
+		return -EINVAL;
+	}
+
+	return rc;
+}
+
+int
+__qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+		    struct qed_ptt *p_ptt,
+		    struct qed_resc_lock_params *p_params)
+{
+	u32 param = 0, mcp_resp, mcp_param;
+	u8 opcode;
+	int rc;
+
+	switch (p_params->timeout) {
+	case QED_MCP_RESC_LOCK_TO_DEFAULT:
+		opcode = RESOURCE_OPCODE_REQ;
+		p_params->timeout = 0;
+		break;
+	case QED_MCP_RESC_LOCK_TO_NONE:
+		opcode = RESOURCE_OPCODE_REQ_WO_AGING;
+		p_params->timeout = 0;
+		break;
+	default:
+		opcode = RESOURCE_OPCODE_REQ_W_AGING;
+		break;
+	}
+
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_RESC, p_params->resource);
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_OPCODE, opcode);
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_AGE, p_params->timeout);
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "Resource lock request: param 0x%08x [age %d, opcode %d, resource %d]\n",
+		   param, p_params->timeout, opcode, p_params->resource);
+
+	/* Attempt to acquire the resource */
+	rc = qed_mcp_resource_cmd(p_hwfn, p_ptt, param, &mcp_resp, &mcp_param);
+	if (rc)
+		return rc;
+
+	/* Analyze the response */
+	p_params->owner = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OWNER);
+	opcode = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OPCODE);
 
 	DP_VERBOSE(p_hwfn,
 		   QED_MSG_SP,
-		   "MFW resource_info: version 0x%x, res_id 0x%x, size 0x%x, offset 0x%x, vf_size 0x%x, vf_offset 0x%x, flags 0x%x\n",
-		   *p_mcp_param,
-		   p_resc_info->res_id,
-		   p_resc_info->size,
-		   p_resc_info->offset,
-		   p_resc_info->vf_size,
-		   p_resc_info->vf_offset, p_resc_info->flags);
+		   "Resource lock response: mcp_param 0x%08x [opcode %d, owner %d]\n",
+		   mcp_param, opcode, p_params->owner);
+
+	switch (opcode) {
+	case RESOURCE_OPCODE_GNT:
+		p_params->b_granted = true;
+		break;
+	case RESOURCE_OPCODE_BUSY:
+		p_params->b_granted = false;
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unexpected opcode in resource lock response [mcp_param 0x%08x, opcode %d]\n",
+			  mcp_param, opcode);
+		return -EINVAL;
+	}
 
 	return 0;
 }
+
+int
+qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params)
+{
+	u32 retry_cnt = 0;
+	int rc;
+
+	do {
+		/* No need for an interval before the first iteration */
+		if (retry_cnt) {
+			if (p_params->sleep_b4_retry) {
+				u16 retry_interval_in_ms =
+				    DIV_ROUND_UP(p_params->retry_interval,
+						 1000);
+
+				msleep(retry_interval_in_ms);
+			} else {
+				udelay(p_params->retry_interval);
+			}
+		}
+
+		rc = __qed_mcp_resc_lock(p_hwfn, p_ptt, p_params);
+		if (rc)
+			return rc;
+
+		if (p_params->b_granted)
+			break;
+	} while (retry_cnt++ < p_params->retry_num);
+
+	return 0;
+}
+
+int
+qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
+		    struct qed_ptt *p_ptt,
+		    struct qed_resc_unlock_params *p_params)
+{
+	u32 param = 0, mcp_resp, mcp_param;
+	u8 opcode;
+	int rc;
+
+	opcode = p_params->b_force ? RESOURCE_OPCODE_FORCE_RELEASE
+				   : RESOURCE_OPCODE_RELEASE;
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_RESC, p_params->resource);
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_OPCODE, opcode);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Resource unlock request: param 0x%08x [opcode %d, resource %d]\n",
+		   param, opcode, p_params->resource);
+
+	/* Attempt to release the resource */
+	rc = qed_mcp_resource_cmd(p_hwfn, p_ptt, param, &mcp_resp, &mcp_param);
+	if (rc)
+		return rc;
+
+	/* Analyze the response */
+	opcode = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OPCODE);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Resource unlock response: mcp_param 0x%08x [opcode %d]\n",
+		   mcp_param, opcode);
+
+	switch (opcode) {
+	case RESOURCE_OPCODE_RELEASED_PREVIOUS:
+		DP_INFO(p_hwfn,
+			"Resource unlock request for an already released resource [%d]\n",
+			p_params->resource);
+		/* Fallthrough */
+	case RESOURCE_OPCODE_RELEASED:
+		p_params->b_released = true;
+		break;
+	case RESOURCE_OPCODE_WRONG_OWNER:
+		p_params->b_released = false;
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unexpected opcode in resource unlock response [mcp_param 0x%08x, opcode %d]\n",
+			  mcp_param, opcode);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock,
+				    struct qed_resc_unlock_params *p_unlock,
+				    enum qed_resc_lock
+				    resource, bool b_is_permanent)
+{
+	if (p_lock) {
+		memset(p_lock, 0, sizeof(*p_lock));
+
+		/* Permanent resources don't require aging, and there's no
+		 * point in trying to acquire them more than once since it's
+		 * unexpected another entity would release them.
+		 */
+		if (b_is_permanent) {
+			p_lock->timeout = QED_MCP_RESC_LOCK_TO_NONE;
+		} else {
+			p_lock->retry_num = QED_MCP_RESC_LOCK_RETRY_CNT_DFLT;
+			p_lock->retry_interval =
+			    QED_MCP_RESC_LOCK_RETRY_VAL_DFLT;
+			p_lock->sleep_b4_retry = true;
+		}
+
+		p_lock->resource = resource;
+	}
+
+	if (p_unlock) {
+		memset(p_unlock, 0, sizeof(*p_unlock));
+		p_unlock->resource = resource;
+	}
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 368e88de146c..5ae35d6cc7d1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -39,6 +39,7 @@
 #include <linux/spinlock.h>
 #include <linux/qed/qed_fcoe_if.h>
 #include "qed_hsi.h"
+#include "qed_dev_api.h"
 
 struct qed_mcp_link_speed_params {
 	bool    autoneg;
@@ -479,14 +480,18 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
 					    rel_pfid)
 #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id)
 
-/* TODO - this is only correct as long as only BB is supported, and
- * no port-swapping is implemented; Afterwards we'll need to fix it.
- */
-#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %	\
-				 ((_p_hwfn)->cdev->num_ports_in_engines * 2))
+#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %			  \
+				 ((_p_hwfn)->cdev->num_ports_in_engines * \
+				  qed_device_num_engines((_p_hwfn)->cdev)))
+
 struct qed_mcp_info {
-	/* Spinlock used for protecting the access to the MFW mailbox */
-	spinlock_t				lock;
+	/* List for mailbox commands which were sent and wait for a response */
+	struct list_head			cmd_list;
+
+	/* Spinlock used for protecting the access to the mailbox commands list
+	 * and the sending of the commands.
+	 */
+	spinlock_t				cmd_lock;
 
 	/* Spinlock used for syncing SW link-changes and link-changes
 	 * originating from attention context.
@@ -506,14 +511,16 @@ struct qed_mcp_info {
 	u8					*mfw_mb_cur;
 	u8					*mfw_mb_shadow;
 	u16					mfw_mb_length;
-	u16					mcp_hist;
+	u32					mcp_hist;
 };
 
 struct qed_mcp_mb_params {
 	u32			cmd;
 	u32			param;
-	union drv_union_data	*p_data_src;
-	union drv_union_data	*p_data_dst;
+	void			*p_data_src;
+	u8			data_src_size;
+	void			*p_data_dst;
+	u8			data_dst_size;
 	u32			mcp_resp;
 	u32			mcp_param;
 };
@@ -564,27 +571,55 @@ int qed_mcp_free(struct qed_hwfn *p_hwfn);
 int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt);
 
+enum qed_drv_role {
+	QED_DRV_ROLE_OS,
+	QED_DRV_ROLE_KDUMP,
+};
+
+struct qed_load_req_params {
+	/* Input params */
+	enum qed_drv_role drv_role;
+	u8 timeout_val;
+	bool avoid_eng_reset;
+	enum qed_override_force_load override_force_load;
+
+	/* Output params */
+	u32 load_code;
+};
+
 /**
- * @brief Sends a LOAD_REQ to the MFW, and in case operation
- *        succeed, returns whether this PF is the first on the
- *        chip/engine/port or function. This function should be
- *        called when driver is ready to accept MFW events after
- *        Storms initializations are done.
+ * @brief Sends a LOAD_REQ to the MFW, and in case the operation succeeds,
+ *        returns whether this PF is the first on the engine/port or function.
  *
- * @param p_hwfn       - hw function
- * @param p_ptt        - PTT required for register access
- * @param p_load_code  - The MCP response param containing one
- *      of the following:
- *      FW_MSG_CODE_DRV_LOAD_ENGINE
- *      FW_MSG_CODE_DRV_LOAD_PORT
- *      FW_MSG_CODE_DRV_LOAD_FUNCTION
- * @return int -
- *      0 - Operation was successul.
- *      -EBUSY - Operation failed
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_params
+ *
+ * @return int - 0 - Operation was successful.
  */
 int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 		     struct qed_ptt *p_ptt,
-		     u32 *p_load_code);
+		     struct qed_load_req_params *p_params);
+
+/**
+ * @brief Sends a UNLOAD_REQ message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief Sends a UNLOAD_DONE message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
 /**
  * @brief Read the MFW mailbox into Current buffer.
@@ -708,6 +743,41 @@ int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u32 mask_parities);
 
 /**
+ * @brief - Sets the MFW's max value for the given resource
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param res_id
+ *  @param resc_max_val
+ *  @param p_mcp_resp
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 enum qed_resources res_id,
+			 u32 resc_max_val, u32 *p_mcp_resp);
+
+/**
+ * @brief - Gets the MFW allocation info for the given resource
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param res_id
+ *  @param p_mcp_resp
+ *  @param p_resc_num
+ *  @param p_resc_start
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt,
+		      enum qed_resources res_id,
+		      u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start);
+
+/**
  * @brief Send eswitch mode to MFW
  *
  *  @param p_hwfn
@@ -720,19 +790,106 @@ int qed_mcp_ov_update_eswitch(struct qed_hwfn *p_hwfn,
 			      struct qed_ptt *p_ptt,
 			      enum qed_ov_eswitch eswitch);
 
+#define QED_MCP_RESC_LOCK_MIN_VAL       RESOURCE_DUMP
+#define QED_MCP_RESC_LOCK_MAX_VAL       31
+
+enum qed_resc_lock {
+	QED_RESC_LOCK_DBG_DUMP = QED_MCP_RESC_LOCK_MIN_VAL,
+	QED_RESC_LOCK_PTP_PORT0,
+	QED_RESC_LOCK_PTP_PORT1,
+	QED_RESC_LOCK_PTP_PORT2,
+	QED_RESC_LOCK_PTP_PORT3,
+	QED_RESC_LOCK_RESC_ALLOC = QED_MCP_RESC_LOCK_MAX_VAL,
+	QED_RESC_LOCK_RESC_INVALID
+};
+
 /**
- * @brief - Gets the MFW allocation info for the given resource
+ * @brief - Initiates PF FLR
  *
  *  @param p_hwfn
  *  @param p_ptt
- *  @param p_resc_info - descriptor of requested resource
- *  @param p_mcp_resp
- *  @param p_mcp_param
  *
  * @return int - 0 - operation was successful.
  */
-int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt,
-			  struct resource_info *p_resc_info,
-			  u32 *p_mcp_resp, u32 *p_mcp_param);
+int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+struct qed_resc_lock_params {
+	/* Resource number [valid values are 0..31] */
+	u8 resource;
+
+	/* Lock timeout value in seconds [default, none or 1..254] */
+	u8 timeout;
+#define QED_MCP_RESC_LOCK_TO_DEFAULT    0
+#define QED_MCP_RESC_LOCK_TO_NONE       255
+
+	/* Number of times to retry locking */
+	u8 retry_num;
+#define QED_MCP_RESC_LOCK_RETRY_CNT_DFLT        10
+
+	/* The interval in usec between retries */
+	u16 retry_interval;
+#define QED_MCP_RESC_LOCK_RETRY_VAL_DFLT        10000
+
+	/* Use sleep or delay between retries */
+	bool sleep_b4_retry;
+
+	/* Will be set as true if the resource is free and granted */
+	bool b_granted;
+
+	/* Will be filled with the resource owner.
+	 * [0..15 = PF0-15, 16 = MFW]
+	 */
+	u8 owner;
+};
+
+/**
+ * @brief Acquires MFW generic resource lock
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param p_params
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params);
+
+struct qed_resc_unlock_params {
+	/* Resource number [valid values are 0..31] */
+	u8 resource;
+
+	/* Allow to release a resource even if belongs to another PF */
+	bool b_force;
+
+	/* Will be set as true if the resource is released */
+	bool b_released;
+};
+
+/**
+ * @brief Releases MFW generic resource lock
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param p_params
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
+		    struct qed_ptt *p_ptt,
+		    struct qed_resc_unlock_params *p_params);
+
+/**
+ * @brief - default initialization for lock/unlock resource structs
+ *
+ * @param p_lock - lock params struct to be initialized; Can be NULL
+ * @param p_unlock - unlock params struct to be initialized; Can be NULL
+ * @param resource - the requested resource
+ * @paral b_is_permanent - disable retries & aging when set
+ */
+void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock,
+				    struct qed_resc_unlock_params *p_unlock,
+				    enum qed_resc_lock
+				    resource, bool b_is_permanent);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index 7d731c6cb892..db96670192c7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -41,6 +41,7 @@
 #include "qed_iscsi.h"
 #include "qed_ll2.h"
 #include "qed_ooo.h"
+#include "qed_cxt.h"
 
 static struct qed_ooo_archipelago
 *qed_ooo_seek_archipelago(struct qed_hwfn *p_hwfn,
@@ -48,15 +49,18 @@ static struct qed_ooo_archipelago
 			  *p_ooo_info,
 			  u32 cid)
 {
-	struct qed_ooo_archipelago *p_archipelago = NULL;
+	u32 idx = (cid & 0xffff) - p_ooo_info->cid_base;
+	struct qed_ooo_archipelago *p_archipelago;
 
-	list_for_each_entry(p_archipelago,
-			    &p_ooo_info->archipelagos_list, list_entry) {
-		if (p_archipelago->cid == cid)
-			return p_archipelago;
-	}
+	if (idx >= p_ooo_info->max_num_archipelagos)
+		return NULL;
 
-	return NULL;
+	p_archipelago = &p_ooo_info->p_archipelagos_mem[idx];
+
+	if (list_empty(&p_archipelago->isles_list))
+		return NULL;
+
+	return p_archipelago;
 }
 
 static struct qed_ooo_isle *qed_ooo_seek_isle(struct qed_hwfn *p_hwfn,
@@ -97,8 +101,8 @@ void qed_ooo_save_history_entry(struct qed_hwfn *p_hwfn,
 
 struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 {
+	u16 max_num_archipelagos = 0, cid_base;
 	struct qed_ooo_info *p_ooo_info;
-	u16 max_num_archipelagos = 0;
 	u16 max_num_isles = 0;
 	u32 i;
 
@@ -110,6 +114,7 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 
 	max_num_archipelagos = p_hwfn->pf_params.iscsi_pf_params.num_cons;
 	max_num_isles = QED_MAX_NUM_ISLES + max_num_archipelagos;
+	cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_ISCSI);
 
 	if (!max_num_archipelagos) {
 		DP_NOTICE(p_hwfn,
@@ -121,11 +126,12 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 	if (!p_ooo_info)
 		return NULL;
 
+	p_ooo_info->cid_base = cid_base;
+	p_ooo_info->max_num_archipelagos = max_num_archipelagos;
+
 	INIT_LIST_HEAD(&p_ooo_info->free_buffers_list);
 	INIT_LIST_HEAD(&p_ooo_info->ready_buffers_list);
 	INIT_LIST_HEAD(&p_ooo_info->free_isles_list);
-	INIT_LIST_HEAD(&p_ooo_info->free_archipelagos_list);
-	INIT_LIST_HEAD(&p_ooo_info->archipelagos_list);
 
 	p_ooo_info->p_isles_mem = kcalloc(max_num_isles,
 					  sizeof(struct qed_ooo_isle),
@@ -146,11 +152,8 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 	if (!p_ooo_info->p_archipelagos_mem)
 		goto no_archipelagos_mem;
 
-	for (i = 0; i < max_num_archipelagos; i++) {
+	for (i = 0; i < max_num_archipelagos; i++)
 		INIT_LIST_HEAD(&p_ooo_info->p_archipelagos_mem[i].isles_list);
-		list_add_tail(&p_ooo_info->p_archipelagos_mem[i].list_entry,
-			      &p_ooo_info->free_archipelagos_list);
-	}
 
 	p_ooo_info->ooo_history.p_cqes =
 				kcalloc(QED_MAX_NUM_OOO_HISTORY_ENTRIES,
@@ -159,6 +162,8 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 	if (!p_ooo_info->ooo_history.p_cqes)
 		goto no_history_mem;
 
+	p_ooo_info->ooo_history.num_of_cqes = QED_MAX_NUM_OOO_HISTORY_ENTRIES;
+
 	return p_ooo_info;
 
 no_history_mem:
@@ -176,21 +181,9 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn,
 	struct qed_ooo_archipelago *p_archipelago;
 	struct qed_ooo_buffer *p_buffer;
 	struct qed_ooo_isle *p_isle;
-	bool b_found = false;
-
-	if (list_empty(&p_ooo_info->archipelagos_list))
-		return;
-
-	list_for_each_entry(p_archipelago,
-			    &p_ooo_info->archipelagos_list, list_entry) {
-		if (p_archipelago->cid == cid) {
-			list_del(&p_archipelago->list_entry);
-			b_found = true;
-			break;
-		}
-	}
 
-	if (!b_found)
+	p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid);
+	if (!p_archipelago)
 		return;
 
 	while (!list_empty(&p_archipelago->isles_list)) {
@@ -214,27 +207,21 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn,
 		list_add_tail(&p_isle->list_entry,
 			      &p_ooo_info->free_isles_list);
 	}
-
-	list_add_tail(&p_archipelago->list_entry,
-		      &p_ooo_info->free_archipelagos_list);
 }
 
 void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn,
 			       struct qed_ooo_info *p_ooo_info)
 {
-	struct qed_ooo_archipelago *p_arch;
+	struct qed_ooo_archipelago *p_archipelago;
 	struct qed_ooo_buffer *p_buffer;
 	struct qed_ooo_isle *p_isle;
+	u32 i;
 
-	while (!list_empty(&p_ooo_info->archipelagos_list)) {
-		p_arch = list_first_entry(&p_ooo_info->archipelagos_list,
-					  struct qed_ooo_archipelago,
-					  list_entry);
-
-		list_del(&p_arch->list_entry);
+	for (i = 0; i < p_ooo_info->max_num_archipelagos; i++) {
+		p_archipelago = &(p_ooo_info->p_archipelagos_mem[i]);
 
-		while (!list_empty(&p_arch->isles_list)) {
-			p_isle = list_first_entry(&p_arch->isles_list,
+		while (!list_empty(&p_archipelago->isles_list)) {
+			p_isle = list_first_entry(&p_archipelago->isles_list,
 						  struct qed_ooo_isle,
 						  list_entry);
 
@@ -256,8 +243,6 @@ void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn,
 			list_add_tail(&p_isle->list_entry,
 				      &p_ooo_info->free_isles_list);
 		}
-		list_add_tail(&p_arch->list_entry,
-			      &p_ooo_info->free_archipelagos_list);
 	}
 	if (!list_empty(&p_ooo_info->ready_buffers_list))
 		list_splice_tail_init(&p_ooo_info->ready_buffers_list,
@@ -376,12 +361,6 @@ void qed_ooo_delete_isles(struct qed_hwfn *p_hwfn,
 		p_ooo_info->cur_isles_number--;
 		list_add(&p_isle->list_entry, &p_ooo_info->free_isles_list);
 	}
-
-	if (list_empty(&p_archipelago->isles_list)) {
-		list_del(&p_archipelago->list_entry);
-		list_add(&p_archipelago->list_entry,
-			 &p_ooo_info->free_archipelagos_list);
-	}
 }
 
 void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn,
@@ -424,28 +403,10 @@ void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn,
 		return;
 	}
 
-	if (!p_archipelago &&
-	    !list_empty(&p_ooo_info->free_archipelagos_list)) {
-		p_archipelago =
-		    list_first_entry(&p_ooo_info->free_archipelagos_list,
-				     struct qed_ooo_archipelago, list_entry);
+	if (!p_archipelago) {
+		u32 idx = (cid & 0xffff) - p_ooo_info->cid_base;
 
-		list_del(&p_archipelago->list_entry);
-		if (!list_empty(&p_archipelago->isles_list)) {
-			DP_NOTICE(p_hwfn,
-				  "Free OOO connection is not empty\n");
-			INIT_LIST_HEAD(&p_archipelago->isles_list);
-		}
-		p_archipelago->cid = cid;
-		list_add(&p_archipelago->list_entry,
-			 &p_ooo_info->archipelagos_list);
-	} else if (!p_archipelago) {
-		DP_NOTICE(p_hwfn, "No more free OOO connections\n");
-		list_add(&p_isle->list_entry,
-			 &p_ooo_info->free_isles_list);
-		list_add(&p_buffer->list_entry,
-			 &p_ooo_info->free_buffers_list);
-		return;
+		p_archipelago = &p_ooo_info->p_archipelagos_mem[idx];
 	}
 
 	list_add(&p_buffer->list_entry, &p_isle->buffers_list);
@@ -515,11 +476,6 @@ void qed_ooo_join_isles(struct qed_hwfn *p_hwfn,
 	} else {
 		list_splice_tail_init(&p_right_isle->buffers_list,
 				      &p_ooo_info->ready_buffers_list);
-		if (list_empty(&p_archipelago->isles_list)) {
-			list_del(&p_archipelago->list_entry);
-			list_add(&p_archipelago->list_entry,
-				 &p_ooo_info->free_archipelagos_list);
-		}
 	}
 	list_add_tail(&p_right_isle->list_entry, &p_ooo_info->free_isles_list);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
index 4f138fb5f533..791ad0f8b759 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
@@ -60,9 +60,7 @@ struct qed_ooo_isle {
 };
 
 struct qed_ooo_archipelago {
-	struct list_head list_entry;
 	struct list_head isles_list;
-	u32 cid;
 };
 
 struct qed_ooo_history {
@@ -75,14 +73,14 @@ struct qed_ooo_info {
 	struct list_head free_buffers_list;
 	struct list_head ready_buffers_list;
 	struct list_head free_isles_list;
-	struct list_head free_archipelagos_list;
-	struct list_head archipelagos_list;
 	struct qed_ooo_archipelago *p_archipelagos_mem;
 	struct qed_ooo_isle *p_isles_mem;
 	struct qed_ooo_history ooo_history;
 	u32 cur_isles_number;
 	u32 max_isles_number;
 	u32 gen_isles_number;
+	u16 max_num_archipelagos;
+	u16 cid_base;
 };
 
 #if IS_ENABLED(CONFIG_QED_ISCSI)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index d27aa85da23c..434a164a76ed 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -34,7 +34,7 @@
 #include "qed_dev_api.h"
 #include "qed_hw.h"
 #include "qed_l2.h"
-#include "qed_ptp.h"
+#include "qed_mcp.h"
 #include "qed_reg_addr.h"
 
 /* 16 nano second time quantas to wait before making a Drift adjustment */
@@ -45,6 +45,82 @@
 #define QED_DRIFT_CNTR_DIRECTION_SHIFT		31
 #define QED_TIMESTAMP_MASK			BIT(16)
 
+static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn)
+{
+	switch (qed_device_get_port_id(p_hwfn->cdev)) {
+	case 0:
+		return QED_RESC_LOCK_PTP_PORT0;
+	case 1:
+		return QED_RESC_LOCK_PTP_PORT1;
+	case 2:
+		return QED_RESC_LOCK_PTP_PORT2;
+	case 3:
+		return QED_RESC_LOCK_PTP_PORT3;
+	default:
+		return QED_RESC_LOCK_RESC_INVALID;
+	}
+}
+
+static int qed_ptp_res_lock(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_resc_lock_params params;
+	enum qed_resc_lock resource;
+	int rc;
+
+	resource = qed_ptcdev_to_resc(p_hwfn);
+	if (resource == QED_RESC_LOCK_RESC_INVALID)
+		return -EINVAL;
+
+	qed_mcp_resc_lock_default_init(&params, NULL, resource, true);
+
+	rc = qed_mcp_resc_lock(p_hwfn, p_ptt, &params);
+	if (rc && rc != -EINVAL) {
+		return rc;
+	} else if (rc == -EINVAL) {
+		/* MFW doesn't support resource locking, first PF on the port
+		 * has lock ownership.
+		 */
+		if (p_hwfn->abs_pf_id < p_hwfn->cdev->num_ports_in_engines)
+			return 0;
+
+		DP_INFO(p_hwfn, "PF doesn't have lock ownership\n");
+		return -EBUSY;
+	} else if (!rc && !params.b_granted) {
+		DP_INFO(p_hwfn, "Failed to acquire ptp resource lock\n");
+		return -EBUSY;
+	}
+
+	return rc;
+}
+
+static int qed_ptp_res_unlock(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_resc_unlock_params params;
+	enum qed_resc_lock resource;
+	int rc;
+
+	resource = qed_ptcdev_to_resc(p_hwfn);
+	if (resource == QED_RESC_LOCK_RESC_INVALID)
+		return -EINVAL;
+
+	qed_mcp_resc_lock_default_init(NULL, &params, resource, true);
+
+	rc = qed_mcp_resc_unlock(p_hwfn, p_ptt, &params);
+	if (rc == -EINVAL) {
+		/* MFW doesn't support locking, first PF has lock ownership */
+		if (p_hwfn->abs_pf_id < p_hwfn->cdev->num_ports_in_engines) {
+			rc = 0;
+		} else {
+			DP_INFO(p_hwfn, "PF doesn't have lock ownership\n");
+			return -EINVAL;
+		}
+	} else if (rc) {
+		DP_INFO(p_hwfn, "Failed to release the ptp resource lock\n");
+	}
+
+	return rc;
+}
+
 /* Read Rx timestamp */
 static int qed_ptp_hw_read_rx_ts(struct qed_dev *cdev, u64 *timestamp)
 {
@@ -112,39 +188,73 @@ static int qed_ptp_hw_read_cc(struct qed_dev *cdev, u64 *phc_cycles)
 }
 
 /* Filter PTP protocol packets that need to be timestamped */
-static int qed_ptp_hw_cfg_rx_filters(struct qed_dev *cdev,
-				     enum qed_ptp_filter_type type)
+static int qed_ptp_hw_cfg_filters(struct qed_dev *cdev,
+				  enum qed_ptp_filter_type rx_type,
+				  enum qed_ptp_hwtstamp_tx_type tx_type)
 {
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_ptt *p_ptt = p_hwfn->p_ptp_ptt;
-	u32 rule_mask, parm_mask;
+	u32 rule_mask, enable_cfg = 0x0;
 
-	switch (type) {
-	case QED_PTP_FILTER_L2_IPV4_IPV6:
-		parm_mask = 0x6AA;
-		rule_mask = 0x3EEE;
+	switch (rx_type) {
+	case QED_PTP_FILTER_NONE:
+		enable_cfg = 0x0;
+		rule_mask = 0x3FFF;
 		break;
-	case QED_PTP_FILTER_L2:
-		parm_mask = 0x6BF;
-		rule_mask = 0x3EFF;
+	case QED_PTP_FILTER_ALL:
+		enable_cfg = 0x7;
+		rule_mask = 0x3CAA;
 		break;
-	case QED_PTP_FILTER_IPV4_IPV6:
-		parm_mask = 0x7EA;
-		rule_mask = 0x3FFE;
+	case QED_PTP_FILTER_V1_L4_EVENT:
+		enable_cfg = 0x3;
+		rule_mask = 0x3FFA;
 		break;
-	case QED_PTP_FILTER_IPV4:
-		parm_mask = 0x7EE;
+	case QED_PTP_FILTER_V1_L4_GEN:
+		enable_cfg = 0x3;
 		rule_mask = 0x3FFE;
 		break;
+	case QED_PTP_FILTER_V2_L4_EVENT:
+		enable_cfg = 0x5;
+		rule_mask = 0x3FAA;
+		break;
+	case QED_PTP_FILTER_V2_L4_GEN:
+		enable_cfg = 0x5;
+		rule_mask = 0x3FEE;
+		break;
+	case QED_PTP_FILTER_V2_L2_EVENT:
+		enable_cfg = 0x5;
+		rule_mask = 0x3CFF;
+		break;
+	case QED_PTP_FILTER_V2_L2_GEN:
+		enable_cfg = 0x5;
+		rule_mask = 0x3EFF;
+		break;
+	case QED_PTP_FILTER_V2_EVENT:
+		enable_cfg = 0x5;
+		rule_mask = 0x3CAA;
+		break;
+	case QED_PTP_FILTER_V2_GEN:
+		enable_cfg = 0x5;
+		rule_mask = 0x3EEE;
+		break;
 	default:
-		DP_INFO(p_hwfn, "Invalid PTP filter type %d\n", type);
+		DP_INFO(p_hwfn, "Invalid PTP filter type %d\n", rx_type);
 		return -EINVAL;
 	}
 
-	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_PARAM_MASK, parm_mask);
+	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_PARAM_MASK, 0);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_RULE_MASK, rule_mask);
+	qed_wr(p_hwfn, p_ptt, NIG_REG_RX_PTP_EN, enable_cfg);
 
-	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_TO_HOST, 0x1);
+	if (tx_type == QED_PTP_HWTSTAMP_TX_OFF) {
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_PTP_EN, 0x0);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_PARAM_MASK, 0x7FF);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_RULE_MASK, 0x3FFF);
+	} else {
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_PTP_EN, enable_cfg);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_PARAM_MASK, 0);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_RULE_MASK, rule_mask);
+	}
 
 	/* Reset possibly old timestamps */
 	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_HOST_BUF_SEQID,
@@ -248,7 +358,25 @@ static int qed_ptp_hw_adjfreq(struct qed_dev *cdev, s32 ppb)
 static int qed_ptp_hw_enable(struct qed_dev *cdev)
 {
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
-	struct qed_ptt *p_ptt = p_hwfn->p_ptp_ptt;
+	struct qed_ptt *p_ptt;
+	int rc;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt) {
+		DP_NOTICE(p_hwfn, "Failed to acquire PTT for PTP\n");
+		return -EBUSY;
+	}
+
+	p_hwfn->p_ptp_ptt = p_ptt;
+
+	rc = qed_ptp_res_lock(p_hwfn, p_ptt);
+	if (rc) {
+		DP_INFO(p_hwfn,
+			"Couldn't acquire the resource lock, skip ptp enable for this PF\n");
+		qed_ptt_release(p_hwfn, p_ptt);
+		p_hwfn->p_ptp_ptt = NULL;
+		return rc;
+	}
 
 	/* Reset PTP event detection rules - will be configured in the IOCTL */
 	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_PARAM_MASK, 0x7FF);
@@ -262,12 +390,20 @@ static int qed_ptp_hw_enable(struct qed_dev *cdev)
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TS_OUTPUT_ENABLE_PDA, 0x1);
 
 	/* Pause free running counter */
-	qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2);
+	if (QED_IS_BB_B0(p_hwfn->cdev))
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2);
+	if (QED_IS_AH(p_hwfn->cdev))
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 2);
 
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_LSB, 0);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_MSB, 0);
 	/* Resume free running counter */
-	qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4);
+	if (QED_IS_BB_B0(p_hwfn->cdev))
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4);
+	if (QED_IS_AH(p_hwfn->cdev)) {
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 4);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_PTP_LATCH_OSTS_PKT_TIME, 1);
+	}
 
 	/* Disable drift register */
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_DRIFT_CNTR_CONF, 0x0);
@@ -281,22 +417,13 @@ static int qed_ptp_hw_enable(struct qed_dev *cdev)
 	return 0;
 }
 
-static int qed_ptp_hw_hwtstamp_tx_on(struct qed_dev *cdev)
-{
-	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
-	struct qed_ptt *p_ptt = p_hwfn->p_ptp_ptt;
-
-	qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_PARAM_MASK, 0x6AA);
-	qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_RULE_MASK, 0x3EEE);
-
-	return 0;
-}
-
 static int qed_ptp_hw_disable(struct qed_dev *cdev)
 {
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_ptt *p_ptt = p_hwfn->p_ptp_ptt;
 
+	qed_ptp_res_unlock(p_hwfn, p_ptt);
+
 	/* Reset PTP event detection rules */
 	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_PARAM_MASK, 0x7FF);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_RULE_MASK, 0x3FFF);
@@ -308,12 +435,14 @@ static int qed_ptp_hw_disable(struct qed_dev *cdev)
 	qed_wr(p_hwfn, p_ptt, NIG_REG_RX_PTP_EN, 0x0);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TX_PTP_EN, 0x0);
 
+	qed_ptt_release(p_hwfn, p_ptt);
+	p_hwfn->p_ptp_ptt = NULL;
+
 	return 0;
 }
 
 const struct qed_eth_ptp_ops qed_ptp_ops_pass = {
-	.hwtstamp_tx_on = qed_ptp_hw_hwtstamp_tx_on,
-	.cfg_rx_filters = qed_ptp_hw_cfg_rx_filters,
+	.cfg_filters = qed_ptp_hw_cfg_filters,
 	.read_rx_ts = qed_ptp_hw_read_rx_ts,
 	.read_tx_ts = qed_ptp_hw_read_tx_ts,
 	.read_cc = qed_ptp_hw_read_cc,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.h b/drivers/net/ethernet/qlogic/qed/qed_ptp.h
deleted file mode 100644
index 63c666d0b739..000000000000
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* QLogic qed NIC Driver
- * Copyright (c) 2015-2017  QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and /or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-#ifndef _QED_PTP_H
-#define _QED_PTP_H
-#include <linux/types.h>
-
-int qed_ptp_hwtstamp_tx_on(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-int qed_ptp_cfg_rx_filters(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
-			   enum qed_ptp_filter_type type);
-int qed_ptp_read_rx_ts(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u64 *ts);
-int qed_ptp_read_tx_ts(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u64 *ts);
-int qed_ptp_read_cc(struct qed_hwfn *p_hwfn,
-		    struct qed_ptt *p_ptt, u64 *cycles);
-int qed_ptp_adjfreq(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, s32 ppb);
-int qed_ptp_disable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-int qed_ptp_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-
-#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index d59d9df60cd2..1ae73b2d6d1e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -160,13 +160,13 @@
 	0x2e0704UL
 #define  CCFC_REG_STRONG_ENABLE_PF \
 	0x2e0708UL
-#define  PGLUE_B_REG_PGL_ADDR_88_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_88_F0_BB \
 	0x2aa404UL
-#define  PGLUE_B_REG_PGL_ADDR_8C_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_8C_F0_BB \
 	0x2aa408UL
-#define  PGLUE_B_REG_PGL_ADDR_90_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_90_F0_BB \
 	0x2aa40cUL
-#define  PGLUE_B_REG_PGL_ADDR_94_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_94_F0_BB \
 	0x2aa410UL
 #define  PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR \
 	0x2aa138UL
@@ -356,6 +356,10 @@
 	0x238804UL
 #define  RDIF_REG_STOP_ON_ERROR \
 	0x300040UL
+#define RDIF_REG_DEBUG_ERROR_INFO \
+	0x300400UL
+#define RDIF_REG_DEBUG_ERROR_INFO_SIZE \
+	64
 #define  SRC_REG_SOFT_RST \
 	0x23874cUL
 #define  TCFC_REG_ACTIVITY_COUNTER \
@@ -370,6 +374,10 @@
 	0x1700004UL
 #define  TDIF_REG_STOP_ON_ERROR \
 	0x310040UL
+#define TDIF_REG_DEBUG_ERROR_INFO \
+	0x310400UL
+#define TDIF_REG_DEBUG_ERROR_INFO_SIZE \
+	64
 #define  UCM_REG_INIT \
 	0x1280000UL
 #define  UMAC_REG_IPG_HD_BKP_CNTL_BB_B0 \
@@ -1236,6 +1244,26 @@
 	0x1901534UL
 #define USEM_REG_DBG_FORCE_FRAME \
 	0x1901538UL
+#define NWS_REG_DBG_SELECT \
+	0x700128UL
+#define NWS_REG_DBG_DWORD_ENABLE \
+	0x70012cUL
+#define NWS_REG_DBG_SHIFT \
+	0x700130UL
+#define NWS_REG_DBG_FORCE_VALID	\
+	0x700134UL
+#define NWS_REG_DBG_FORCE_FRAME	\
+	0x700138UL
+#define MS_REG_DBG_SELECT \
+	0x6a0228UL
+#define MS_REG_DBG_DWORD_ENABLE \
+	0x6a022cUL
+#define MS_REG_DBG_SHIFT \
+	0x6a0230UL
+#define MS_REG_DBG_FORCE_VALID \
+	0x6a0234UL
+#define MS_REG_DBG_FORCE_FRAME \
+	0x6a0238UL
 #define PCIE_REG_DBG_COMMON_SELECT \
 	0x054398UL
 #define PCIE_REG_DBG_COMMON_DWORD_ENABLE \
@@ -1448,6 +1476,8 @@
 	0x000b48UL
 #define RSS_REG_RSS_RAM_DATA \
 	0x238c20UL
+#define RSS_REG_RSS_RAM_DATA_SIZE \
+	4
 #define MISC_REG_BLOCK_256B_EN \
 	0x008c14UL
 #define NWS_REG_NWS_CMU	\
@@ -1520,4 +1550,22 @@
 #define NIG_REG_TIMESYNC_GEN_REG_BB 0x500d00UL
 #define NIG_REG_TSGEN_FREE_CNT_VALUE_LSB 0x5088a8UL
 #define NIG_REG_TSGEN_FREE_CNT_VALUE_MSB 0x5088acUL
+#define NIG_REG_PTP_LATCH_OSTS_PKT_TIME 0x509040UL
+#define PSWRQ2_REG_WR_MBS0 0x240400UL
+
+#define PGLUE_B_REG_PGL_ADDR_E8_F0_K2 0x2aaf98UL
+#define PGLUE_B_REG_PGL_ADDR_EC_F0_K2 0x2aaf9cUL
+#define PGLUE_B_REG_PGL_ADDR_F0_F0_K2 0x2aafa0UL
+#define PGLUE_B_REG_PGL_ADDR_F4_F0_K2 0x2aafa4UL
+#define NIG_REG_TSGEN_FREECNT_UPDATE_K2 0x509008UL
+#define CNIG_REG_NIG_PORT0_CONF_K2 0x218200UL
+
+#define PRS_REG_SEARCH_GFT 0x1f11bcUL
+#define PRS_REG_CM_HDR_GFT 0x1f11c8UL
+#define PRS_REG_GFT_CAM 0x1f1100UL
+#define PRS_REG_GFT_PROFILE_MASK_RAM 0x1f1000UL
+#define PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT 0
+#define PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT 8
+#define PRS_REG_LOAD_L2_FILTER 0x1f0198UL
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index d9ff6b28591c..56289d7cd306 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -66,17 +66,31 @@
 #include "qed_roce.h"
 #include "qed_ll2.h"
 
-void qed_async_roce_event(struct qed_hwfn *p_hwfn,
-			  struct event_ring_entry *p_eqe)
+static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid);
+
+void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+			  u8 fw_event_code, union rdma_eqe_data *rdma_data)
 {
-	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+	if (fw_event_code == ROCE_ASYNC_EVENT_DESTROY_QP_DONE) {
+		u16 icid =
+		    (u16)le32_to_cpu(rdma_data->rdma_destroy_qp_data.cid);
+
+		/* icid release in this async event can occur only if the icid
+		 * was offloaded to the FW. In case it wasn't offloaded this is
+		 * handled in qed_roce_sp_destroy_qp.
+		 */
+		qed_roce_free_real_icid(p_hwfn, icid);
+	} else {
+		struct qed_rdma_events *events = &p_hwfn->p_rdma_info->events;
 
-	p_rdma_info->events.affiliated_event(p_rdma_info->events.context,
-					     p_eqe->opcode, &p_eqe->data);
+		events->affiliated_event(p_hwfn->p_rdma_info->events.context,
+					 fw_event_code,
+					 &rdma_data->async_handle);
+	}
 }
 
 static int qed_rdma_bmap_alloc(struct qed_hwfn *p_hwfn,
-			       struct qed_bmap *bmap, u32 max_count)
+			       struct qed_bmap *bmap, u32 max_count, char *name)
 {
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "max_count = %08x\n", max_count);
 
@@ -90,43 +104,62 @@ static int qed_rdma_bmap_alloc(struct qed_hwfn *p_hwfn,
 		return -ENOMEM;
 	}
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocated bitmap %p\n",
-		   bmap->bitmap);
+	snprintf(bmap->name, QED_RDMA_MAX_BMAP_NAME, "%s", name);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "0\n");
 	return 0;
 }
 
 static int qed_rdma_bmap_alloc_id(struct qed_hwfn *p_hwfn,
 				  struct qed_bmap *bmap, u32 *id_num)
 {
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "bmap = %p\n", bmap);
-
 	*id_num = find_first_zero_bit(bmap->bitmap, bmap->max_count);
-
-	if (*id_num >= bmap->max_count) {
-		DP_NOTICE(p_hwfn, "no id available max_count=%d\n",
-			  bmap->max_count);
+	if (*id_num >= bmap->max_count)
 		return -EINVAL;
-	}
 
 	__set_bit(*id_num, bmap->bitmap);
 
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "%s bitmap: allocated id %d\n",
+		   bmap->name, *id_num);
+
 	return 0;
 }
 
+static void qed_bmap_set_id(struct qed_hwfn *p_hwfn,
+			    struct qed_bmap *bmap, u32 id_num)
+{
+	if (id_num >= bmap->max_count)
+		return;
+
+	__set_bit(id_num, bmap->bitmap);
+}
+
 static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
 				struct qed_bmap *bmap, u32 id_num)
 {
 	bool b_acquired;
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "id_num = %08x", id_num);
 	if (id_num >= bmap->max_count)
 		return;
 
 	b_acquired = test_and_clear_bit(id_num, bmap->bitmap);
 	if (!b_acquired) {
-		DP_NOTICE(p_hwfn, "ID %d already released\n", id_num);
+		DP_NOTICE(p_hwfn, "%s bitmap: id %d already released\n",
+			  bmap->name, id_num);
 		return;
 	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "%s bitmap: released id %d\n",
+		   bmap->name, id_num);
+}
+
+static int qed_bmap_test_id(struct qed_hwfn *p_hwfn,
+			    struct qed_bmap *bmap, u32 id_num)
+{
+	if (id_num >= bmap->max_count)
+		return -1;
+
+	return test_bit(id_num, bmap->bitmap);
 }
 
 static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
@@ -170,7 +203,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	/* Queue zone lines are shared between RoCE and L2 in such a way that
 	 * they can be used by each without obstructing the other.
 	 */
-	p_rdma_info->queue_zone_base = (u16)FEAT_NUM(p_hwfn, QED_L2_QUEUE);
+	p_rdma_info->queue_zone_base = (u16)RESC_START(p_hwfn, QED_L2_QUEUE);
+	p_rdma_info->max_queue_zones = (u16)RESC_NUM(p_hwfn, QED_L2_QUEUE);
 
 	/* Allocate a struct with device params and fill it */
 	p_rdma_info->dev = kzalloc(sizeof(*p_rdma_info->dev), GFP_KERNEL);
@@ -191,7 +225,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Allocate bit map for pd's */
-	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->pd_map, RDMA_MAX_PDS);
+	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->pd_map, RDMA_MAX_PDS,
+				 "PD");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate pd_map, rc = %d\n",
@@ -201,7 +236,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 
 	/* Allocate DPI bitmap */
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->dpi_map,
-				 p_hwfn->dpi_count);
+				 p_hwfn->dpi_count, "DPI");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate DPI bitmap, rc = %d\n", rc);
@@ -212,7 +247,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	 * twice the number of QPs.
 	 */
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map,
-				 p_rdma_info->num_qps * 2);
+				 p_rdma_info->num_qps * 2, "CQ");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate cq bitmap, rc = %d\n", rc);
@@ -224,7 +259,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	 * The maximum number of CQs is bounded to  twice the number of QPs.
 	 */
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->toggle_bits,
-				 p_rdma_info->num_qps * 2);
+				 p_rdma_info->num_qps * 2, "Toggle");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate toogle bits, rc = %d\n", rc);
@@ -233,7 +268,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 
 	/* Allocate bitmap for itids */
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->tid_map,
-				 p_rdma_info->num_mrs);
+				 p_rdma_info->num_mrs, "MR");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate itids bitmaps, rc = %d\n", rc);
@@ -241,16 +276,27 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Allocate bitmap for cids used for qps. */
-	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cid_map, num_cons);
+	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cid_map, num_cons,
+				 "CID");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate cid bitmap, rc = %d\n", rc);
 		goto free_tid_map;
 	}
 
+	/* Allocate bitmap for cids used for responders/requesters. */
+	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->real_cid_map, num_cons,
+				 "REAL_CID");
+	if (rc) {
+		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+			   "Failed to allocate real cid bitmap, rc = %d\n", rc);
+		goto free_cid_map;
+	}
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocation successful\n");
 	return 0;
 
+free_cid_map:
+	kfree(p_rdma_info->cid_map.bitmap);
 free_tid_map:
 	kfree(p_rdma_info->tid_map.bitmap);
 free_toggle_map:
@@ -271,16 +317,79 @@ free_rdma_info:
 	return rc;
 }
 
+static void qed_rdma_bmap_free(struct qed_hwfn *p_hwfn,
+			       struct qed_bmap *bmap, bool check)
+{
+	int weight = bitmap_weight(bmap->bitmap, bmap->max_count);
+	int last_line = bmap->max_count / (64 * 8);
+	int last_item = last_line * 8 +
+	    DIV_ROUND_UP(bmap->max_count % (64 * 8), 64);
+	u64 *pmap = (u64 *)bmap->bitmap;
+	int line, item, offset;
+	u8 str_last_line[200] = { 0 };
+
+	if (!weight || !check)
+		goto end;
+
+	DP_NOTICE(p_hwfn,
+		  "%s bitmap not free - size=%d, weight=%d, 512 bits per line\n",
+		  bmap->name, bmap->max_count, weight);
+
+	/* print aligned non-zero lines, if any */
+	for (item = 0, line = 0; line < last_line; line++, item += 8)
+		if (bitmap_weight((unsigned long *)&pmap[item], 64 * 8))
+			DP_NOTICE(p_hwfn,
+				  "line 0x%04x: 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
+				  line,
+				  pmap[item],
+				  pmap[item + 1],
+				  pmap[item + 2],
+				  pmap[item + 3],
+				  pmap[item + 4],
+				  pmap[item + 5],
+				  pmap[item + 6], pmap[item + 7]);
+
+	/* print last unaligned non-zero line, if any */
+	if ((bmap->max_count % (64 * 8)) &&
+	    (bitmap_weight((unsigned long *)&pmap[item],
+			   bmap->max_count - item * 64))) {
+		offset = sprintf(str_last_line, "line 0x%04x: ", line);
+		for (; item < last_item; item++)
+			offset += sprintf(str_last_line + offset,
+					  "0x%016llx ", pmap[item]);
+		DP_NOTICE(p_hwfn, "%s\n", str_last_line);
+	}
+
+end:
+	kfree(bmap->bitmap);
+	bmap->bitmap = NULL;
+}
+
 static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
 {
+	struct qed_bmap *rcid_map = &p_hwfn->p_rdma_info->real_cid_map;
 	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+	int wait_count = 0;
 
-	kfree(p_rdma_info->cid_map.bitmap);
-	kfree(p_rdma_info->tid_map.bitmap);
-	kfree(p_rdma_info->toggle_bits.bitmap);
-	kfree(p_rdma_info->cq_map.bitmap);
-	kfree(p_rdma_info->dpi_map.bitmap);
-	kfree(p_rdma_info->pd_map.bitmap);
+	/* when destroying a_RoCE QP the control is returned to the user after
+	 * the synchronous part. The asynchronous part may take a little longer.
+	 * We delay for a short while if an async destroy QP is still expected.
+	 * Beyond the added delay we clear the bitmap anyway.
+	 */
+	while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) {
+		msleep(100);
+		if (wait_count++ > 20) {
+			DP_NOTICE(p_hwfn, "cid bitmap wait timed out\n");
+			break;
+		}
+	}
+
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->cid_map, 1);
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->pd_map, 1);
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->dpi_map, 1);
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->cq_map, 1);
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->toggle_bits, 0);
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tid_map, 1);
 
 	kfree(p_rdma_info->port);
 	kfree(p_rdma_info->dev);
@@ -675,6 +784,7 @@ static int qed_rdma_add_user(void *rdma_cxt,
 				    ((out_params->dpi) * p_hwfn->dpi_size);
 
 	out_params->dpi_size = p_hwfn->dpi_size;
+	out_params->wid_count = p_hwfn->wid_count;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Adding user - done, rc = %d\n", rc);
 	return rc;
@@ -693,6 +803,8 @@ static struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
 
 	p_port->link_speed = p_hwfn->mcp_info->link_output.speed;
 
+	p_port->max_msg_size = RDMA_MAX_DATA_SIZE_IN_WQE;
+
 	return p_port;
 }
 
@@ -724,6 +836,14 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
 	u32 addr;
 
 	p_hwfn = (struct qed_hwfn *)rdma_cxt;
+
+	if (qz_offset > p_hwfn->p_rdma_info->max_queue_zones) {
+		DP_NOTICE(p_hwfn,
+			  "queue zone offset %d is too large (max is %d)\n",
+			  qz_offset, p_hwfn->p_rdma_info->max_queue_zones);
+		return;
+	}
+
 	qz_num = p_hwfn->p_rdma_info->queue_zone_base + qz_offset;
 	addr = GTT_BAR0_MAP_REG_USDM_RAM +
 	       USTORM_COMMON_QUEUE_CONS_OFFSET(qz_num);
@@ -737,9 +857,12 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
 static int qed_fill_rdma_dev_info(struct qed_dev *cdev,
 				  struct qed_dev_rdma_info *info)
 {
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+
 	memset(info, 0, sizeof(*info));
 
 	info->rdma_type = QED_RDMA_TYPE_ROCE;
+	info->user_dpm_enabled = (p_hwfn->db_bar_no_edpm == 0);
 
 	qed_fill_dev_info(cdev, &info->common);
 
@@ -887,8 +1010,7 @@ static int qed_rdma_create_cq(void *rdma_cxt,
 
 	/* Allocate icid */
 	spin_lock_bh(&p_info->lock);
-	rc = qed_rdma_bmap_alloc_id(p_hwfn,
-				    &p_info->cq_map, &returned_id);
+	rc = qed_rdma_bmap_alloc_id(p_hwfn, &p_info->cq_map, &returned_id);
 	spin_unlock_bh(&p_info->lock);
 
 	if (rc) {
@@ -1080,6 +1202,14 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
 	return flavor;
 }
 
+void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
+{
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid);
+	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid + 1);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
 {
 	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
@@ -1139,15 +1269,22 @@ err:
 	return rc;
 }
 
+static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
+{
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	qed_bmap_set_id(p_hwfn, &p_hwfn->p_rdma_info->real_cid_map, cid);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_resp_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params qm_params;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 physical_queue0 = 0;
+	u16 regular_latency_queue;
+	enum protocol_type proto;
 	int rc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -1229,15 +1366,16 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
 	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
 	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
-	p_ramrod->stats_counter_id = p_hwfn->rel_pf_id;
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
 
-	memset(&qm_params, 0, sizeof(qm_params));
-	qm_params.roce.qpid = qp->icid >> 1;
-	physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params);
+	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+
+	p_ramrod->regular_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
+	p_ramrod->low_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
 
-	p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0);
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
 	qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
@@ -1253,13 +1391,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d physical_queue0 = 0x%x\n",
-		   rc, physical_queue0);
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+		   "rc = %d regular physical queue = 0x%x\n", rc,
+		   regular_latency_queue);
 
 	if (rc)
 		goto err;
 
 	qp->resp_offloaded = true;
+	qp->cq_prod = 0;
+
+	proto = p_hwfn->p_rdma_info->proto;
+	qed_roce_set_real_cid(p_hwfn, qp->icid -
+			      qed_cxt_get_proto_cid_start(p_hwfn, proto));
 
 	return rc;
 
@@ -1277,10 +1421,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 {
 	struct roce_create_qp_req_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params qm_params;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 physical_queue0 = 0;
+	u16 regular_latency_queue;
+	enum protocol_type proto;
 	int rc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -1351,15 +1495,16 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
 	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
 	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
-	p_ramrod->stats_counter_id = p_hwfn->rel_pf_id;
-	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
-				       qp->sq_cq_id);
+	p_ramrod->cq_cid =
+	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
 
-	memset(&qm_params, 0, sizeof(qm_params));
-	qm_params.roce.qpid = qp->icid >> 1;
-	physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params);
+	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+
+	p_ramrod->regular_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
+	p_ramrod->low_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
 
-	p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0);
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
 	qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
@@ -1378,6 +1523,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 		goto err;
 
 	qp->req_offloaded = true;
+	proto = p_hwfn->p_rdma_info->proto;
+	qed_roce_set_real_cid(p_hwfn,
+			      qp->icid + 1 -
+			      qed_cxt_get_proto_cid_start(p_hwfn, proto));
 
 	return rc;
 
@@ -1577,7 +1726,8 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn,
 
 static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 					    struct qed_rdma_qp *qp,
-					    u32 *num_invalidated_mw)
+					    u32 *num_invalidated_mw,
+					    u32 *cq_prod)
 {
 	struct roce_destroy_qp_resp_output_params *p_ramrod_res;
 	struct roce_destroy_qp_resp_ramrod_data *p_ramrod;
@@ -1588,8 +1738,22 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
-	if (!qp->resp_offloaded)
+	*num_invalidated_mw = 0;
+	*cq_prod = qp->cq_prod;
+
+	if (!qp->resp_offloaded) {
+		/* If a responder was never offload, we need to free the cids
+		 * allocated in create_qp as a FW async event will never arrive
+		 */
+		u32 cid;
+
+		cid = qp->icid -
+		      qed_cxt_get_proto_cid_start(p_hwfn,
+						  p_hwfn->p_rdma_info->proto);
+		qed_roce_free_cid_pair(p_hwfn, (u16)cid);
+
 		return 0;
+	}
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
@@ -1624,6 +1788,8 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 		goto err;
 
 	*num_invalidated_mw = le32_to_cpu(p_ramrod_res->num_invalidated_mw);
+	*cq_prod = le32_to_cpu(p_ramrod_res->cq_prod);
+	qp->cq_prod = *cq_prod;
 
 	/* Free IRQ - only if ramrod succeeded, in case FW is still using it */
 	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
@@ -1827,10 +1993,8 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
 
 	out_params->draining = false;
 
-	if (rq_err_state)
+	if (rq_err_state || sq_err_state)
 		qp->cur_state = QED_ROCE_QP_STATE_ERR;
-	else if (sq_err_state)
-		qp->cur_state = QED_ROCE_QP_STATE_SQE;
 	else if (sq_draining)
 		out_params->draining = true;
 	out_params->state = qp->cur_state;
@@ -1849,10 +2013,9 @@ err_resp:
 
 static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 {
-	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
 	u32 num_invalidated_mw = 0;
 	u32 num_bound_mw = 0;
-	u32 start_cid;
+	u32 cq_prod;
 	int rc;
 
 	/* Destroys the specified QP */
@@ -1866,7 +2029,8 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 
 	if (qp->cur_state != QED_ROCE_QP_STATE_RESET) {
 		rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp,
-						      &num_invalidated_mw);
+						      &num_invalidated_mw,
+						      &cq_prod);
 		if (rc)
 			return rc;
 
@@ -1881,21 +2045,6 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 				  "number of invalidate memory windows is different from bounded ones\n");
 			return -EINVAL;
 		}
-
-		spin_lock_bh(&p_rdma_info->lock);
-
-		start_cid = qed_cxt_get_proto_cid_start(p_hwfn,
-							p_rdma_info->proto);
-
-		/* Release responder's icid */
-		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map,
-				    qp->icid - start_cid);
-
-		/* Release requester's icid */
-		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map,
-				    qp->icid + 1 - start_cid);
-
-		spin_unlock_bh(&p_rdma_info->lock);
 	}
 
 	return 0;
@@ -2097,8 +2246,7 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn,
 						  params->modify_flags);
 
 		return rc;
-	} else if (qp->cur_state == QED_ROCE_QP_STATE_ERR ||
-		   qp->cur_state == QED_ROCE_QP_STATE_SQE) {
+	} else if (qp->cur_state == QED_ROCE_QP_STATE_ERR) {
 		/* ->ERR */
 		rc = qed_roce_sp_modify_responder(p_hwfn, qp, true,
 						  params->modify_flags);
@@ -2110,12 +2258,19 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn,
 		return rc;
 	} else if (qp->cur_state == QED_ROCE_QP_STATE_RESET) {
 		/* Any state -> RESET */
+		u32 cq_prod;
+
+		/* Send destroy responder ramrod */
+		rc = qed_roce_sp_destroy_qp_responder(p_hwfn,
+						      qp,
+						      &num_invalidated_mw,
+						      &cq_prod);
 
-		rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp,
-						      &num_invalidated_mw);
 		if (rc)
 			return rc;
 
+		qp->cq_prod = cq_prod;
+
 		rc = qed_roce_sp_destroy_qp_requester(p_hwfn, qp,
 						      &num_bound_mw);
 
@@ -2357,6 +2512,8 @@ qed_rdma_register_tid(void *rdma_cxt,
 	}
 
 	rc = qed_spq_post(p_hwfn, p_ent, &fw_return_code);
+	if (rc)
+		return rc;
 
 	if (fw_return_code != RDMA_RETURN_OK) {
 		DP_NOTICE(p_hwfn, "fw_return_code = %d\n", fw_return_code);
@@ -2454,6 +2611,31 @@ static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
 	return rc;
 }
 
+static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid)
+{
+	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+	u32 start_cid, cid, xcid;
+
+	/* an even icid belongs to a responder while an odd icid belongs to a
+	 * requester. The 'cid' received as an input can be either. We calculate
+	 * the "partner" icid and call it xcid. Only if both are free then the
+	 * "cid" map can be cleared.
+	 */
+	start_cid = qed_cxt_get_proto_cid_start(p_hwfn, p_rdma_info->proto);
+	cid = icid - start_cid;
+	xcid = cid ^ 1;
+
+	spin_lock_bh(&p_rdma_info->lock);
+
+	qed_bmap_release_id(p_hwfn, &p_rdma_info->real_cid_map, cid);
+	if (qed_bmap_test_id(p_hwfn, &p_rdma_info->real_cid_map, xcid) == 0) {
+		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, cid);
+		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, xcid);
+	}
+
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev)
 {
 	return QED_LEADING_HWFN(cdev);
@@ -2773,7 +2955,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev,
 						      : QED_LL2_RROCE;
 
 	if (pkt->roce_mode == ROCE_V2_IPV4)
-		flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT);
+		flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT);
 
 	/* Tx header */
 	rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), roce_ll2->handle,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index 36cf4b2ab7fa..9742af516183 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -67,9 +67,11 @@ enum qed_rdma_toggle_bit {
 	QED_RDMA_TOGGLE_BIT_SET = 1
 };
 
+#define QED_RDMA_MAX_BMAP_NAME	(10)
 struct qed_bmap {
 	unsigned long *bitmap;
 	u32 max_count;
+	char name[QED_RDMA_MAX_BMAP_NAME];
 };
 
 struct qed_rdma_info {
@@ -82,6 +84,7 @@ struct qed_rdma_info {
 	struct qed_bmap qp_map;
 	struct qed_bmap srq_map;
 	struct qed_bmap cid_map;
+	struct qed_bmap real_cid_map;
 	struct qed_bmap dpi_map;
 	struct qed_bmap toggle_bits;
 	struct qed_rdma_events events;
@@ -92,6 +95,7 @@ struct qed_rdma_info {
 	u32 num_qps;
 	u32 num_mrs;
 	u16 queue_zone_base;
+	u16 max_queue_zones;
 	enum protocol_type proto;
 };
 
@@ -153,6 +157,7 @@ struct qed_rdma_qp {
 	dma_addr_t irq_phys_addr;
 	u8 irq_num_pages;
 	bool resp_offloaded;
+	u32 cq_prod;
 
 	u8 remote_mac_addr[6];
 	u8 local_mac_addr[6];
@@ -163,8 +168,8 @@ struct qed_rdma_qp {
 
 #if IS_ENABLED(CONFIG_QED_RDMA)
 void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-void qed_async_roce_event(struct qed_hwfn *p_hwfn,
-			  struct event_ring_entry *p_eqe);
+void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+			  u8 fw_event_code, union rdma_eqe_data *rdma_data);
 void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
 				     u8 connection_handle,
 				     void *cookie,
@@ -187,7 +192,9 @@ void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
 				     u16 src_mac_addr_lo, bool b_last_packet);
 #else
 static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
-static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {}
+static inline void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+					u8 fw_event_code,
+					union rdma_eqe_data *rdma_data) {}
 static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
 						   u8 connection_handle,
 						   void *cookie,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 30393ffaa8e5..3357bbefa445 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -84,6 +84,7 @@ union ramrod_data {
 	struct tx_queue_stop_ramrod_data tx_queue_stop;
 	struct vport_start_ramrod_data vport_start;
 	struct vport_stop_ramrod_data vport_stop;
+	struct rx_update_gft_filter_data rx_update_gft;
 	struct vport_update_ramrod_data vport_update;
 	struct core_rx_start_ramrod_data core_rx_queue_start;
 	struct core_rx_stop_ramrod_data core_rx_queue_stop;
@@ -408,7 +409,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn,
  */
 
 int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
-		    struct qed_tunn_start_params *p_tunn,
+		    struct qed_tunnel_info *p_tunn,
 		    enum qed_mf_mode mode, bool allow_npar_tx_switch);
 
 /**
@@ -441,7 +442,7 @@ int qed_sp_pf_update(struct qed_hwfn *p_hwfn);
 int qed_sp_pf_stop(struct qed_hwfn *p_hwfn);
 
 int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn,
-			      struct qed_tunn_update_params *p_tunn,
+			      struct qed_tunnel_info *p_tunn,
 			      enum spq_mode comp_mode,
 			      struct qed_spq_comp_cb *p_comp_data);
 /**
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 6fb80f9ef446..bc3694e91b85 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -111,7 +111,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
-static enum tunnel_clss qed_tunn_get_clss_type(u8 type)
+static enum tunnel_clss qed_tunn_clss_to_fw_clss(u8 type)
 {
 	switch (type) {
 	case QED_TUNN_CLSS_MAC_VLAN:
@@ -122,206 +122,201 @@ static enum tunnel_clss qed_tunn_get_clss_type(u8 type)
 		return TUNNEL_CLSS_INNER_MAC_VLAN;
 	case QED_TUNN_CLSS_INNER_MAC_VNI:
 		return TUNNEL_CLSS_INNER_MAC_VNI;
+	case QED_TUNN_CLSS_MAC_VLAN_DUAL_STAGE:
+		return TUNNEL_CLSS_MAC_VLAN_DUAL_STAGE;
 	default:
 		return TUNNEL_CLSS_MAC_VLAN;
 	}
 }
 
 static void
-qed_tunn_set_pf_fix_tunn_mode(struct qed_hwfn *p_hwfn,
-			      struct qed_tunn_update_params *p_src,
-			      struct pf_update_tunnel_config *p_tunn_cfg)
+qed_set_pf_update_tunn_mode(struct qed_tunnel_info *p_tun,
+			    struct qed_tunnel_info *p_src, bool b_pf_start)
 {
-	unsigned long cached_tunn_mode = p_hwfn->cdev->tunn_mode;
-	unsigned long update_mask = p_src->tunn_mode_update_mask;
-	unsigned long tunn_mode = p_src->tunn_mode;
-	unsigned long new_tunn_mode = 0;
-
-	if (test_bit(QED_MODE_L2GRE_TUNN, &update_mask)) {
-		if (test_bit(QED_MODE_L2GRE_TUNN, &tunn_mode))
-			__set_bit(QED_MODE_L2GRE_TUNN, &new_tunn_mode);
-	} else {
-		if (test_bit(QED_MODE_L2GRE_TUNN, &cached_tunn_mode))
-			__set_bit(QED_MODE_L2GRE_TUNN, &new_tunn_mode);
-	}
-
-	if (test_bit(QED_MODE_IPGRE_TUNN, &update_mask)) {
-		if (test_bit(QED_MODE_IPGRE_TUNN, &tunn_mode))
-			__set_bit(QED_MODE_IPGRE_TUNN, &new_tunn_mode);
-	} else {
-		if (test_bit(QED_MODE_IPGRE_TUNN, &cached_tunn_mode))
-			__set_bit(QED_MODE_IPGRE_TUNN, &new_tunn_mode);
-	}
+	if (p_src->vxlan.b_update_mode || b_pf_start)
+		p_tun->vxlan.b_mode_enabled = p_src->vxlan.b_mode_enabled;
 
-	if (test_bit(QED_MODE_VXLAN_TUNN, &update_mask)) {
-		if (test_bit(QED_MODE_VXLAN_TUNN, &tunn_mode))
-			__set_bit(QED_MODE_VXLAN_TUNN, &new_tunn_mode);
-	} else {
-		if (test_bit(QED_MODE_VXLAN_TUNN, &cached_tunn_mode))
-			__set_bit(QED_MODE_VXLAN_TUNN, &new_tunn_mode);
-	}
-
-	if (p_src->update_geneve_udp_port) {
-		p_tunn_cfg->set_geneve_udp_port_flg = 1;
-		p_tunn_cfg->geneve_udp_port =
-				cpu_to_le16(p_src->geneve_udp_port);
-	}
+	if (p_src->l2_gre.b_update_mode || b_pf_start)
+		p_tun->l2_gre.b_mode_enabled = p_src->l2_gre.b_mode_enabled;
 
-	if (test_bit(QED_MODE_L2GENEVE_TUNN, &update_mask)) {
-		if (test_bit(QED_MODE_L2GENEVE_TUNN, &tunn_mode))
-			__set_bit(QED_MODE_L2GENEVE_TUNN, &new_tunn_mode);
-	} else {
-		if (test_bit(QED_MODE_L2GENEVE_TUNN, &cached_tunn_mode))
-			__set_bit(QED_MODE_L2GENEVE_TUNN, &new_tunn_mode);
-	}
+	if (p_src->ip_gre.b_update_mode || b_pf_start)
+		p_tun->ip_gre.b_mode_enabled = p_src->ip_gre.b_mode_enabled;
 
-	if (test_bit(QED_MODE_IPGENEVE_TUNN, &update_mask)) {
-		if (test_bit(QED_MODE_IPGENEVE_TUNN, &tunn_mode))
-			__set_bit(QED_MODE_IPGENEVE_TUNN, &new_tunn_mode);
-	} else {
-		if (test_bit(QED_MODE_IPGENEVE_TUNN, &cached_tunn_mode))
-			__set_bit(QED_MODE_IPGENEVE_TUNN, &new_tunn_mode);
-	}
+	if (p_src->l2_geneve.b_update_mode || b_pf_start)
+		p_tun->l2_geneve.b_mode_enabled =
+		    p_src->l2_geneve.b_mode_enabled;
 
-	p_src->tunn_mode = new_tunn_mode;
+	if (p_src->ip_geneve.b_update_mode || b_pf_start)
+		p_tun->ip_geneve.b_mode_enabled =
+		    p_src->ip_geneve.b_mode_enabled;
 }
 
-static void
-qed_tunn_set_pf_update_params(struct qed_hwfn *p_hwfn,
-			      struct qed_tunn_update_params *p_src,
-			      struct pf_update_tunnel_config *p_tunn_cfg)
+static void qed_set_tunn_cls_info(struct qed_tunnel_info *p_tun,
+				  struct qed_tunnel_info *p_src)
 {
-	unsigned long tunn_mode = p_src->tunn_mode;
 	enum tunnel_clss type;
 
-	qed_tunn_set_pf_fix_tunn_mode(p_hwfn, p_src, p_tunn_cfg);
-	p_tunn_cfg->update_rx_pf_clss = p_src->update_rx_pf_clss;
-	p_tunn_cfg->update_tx_pf_clss = p_src->update_tx_pf_clss;
-
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_vxlan);
-	p_tunn_cfg->tunnel_clss_vxlan  = type;
-
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_l2gre);
-	p_tunn_cfg->tunnel_clss_l2gre = type;
+	p_tun->b_update_rx_cls = p_src->b_update_rx_cls;
+	p_tun->b_update_tx_cls = p_src->b_update_tx_cls;
+
+	type = qed_tunn_clss_to_fw_clss(p_src->vxlan.tun_cls);
+	p_tun->vxlan.tun_cls = type;
+	type = qed_tunn_clss_to_fw_clss(p_src->l2_gre.tun_cls);
+	p_tun->l2_gre.tun_cls = type;
+	type = qed_tunn_clss_to_fw_clss(p_src->ip_gre.tun_cls);
+	p_tun->ip_gre.tun_cls = type;
+	type = qed_tunn_clss_to_fw_clss(p_src->l2_geneve.tun_cls);
+	p_tun->l2_geneve.tun_cls = type;
+	type = qed_tunn_clss_to_fw_clss(p_src->ip_geneve.tun_cls);
+	p_tun->ip_geneve.tun_cls = type;
+}
 
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_ipgre);
-	p_tunn_cfg->tunnel_clss_ipgre = type;
+static void qed_set_tunn_ports(struct qed_tunnel_info *p_tun,
+			       struct qed_tunnel_info *p_src)
+{
+	p_tun->geneve_port.b_update_port = p_src->geneve_port.b_update_port;
+	p_tun->vxlan_port.b_update_port = p_src->vxlan_port.b_update_port;
 
-	if (p_src->update_vxlan_udp_port) {
-		p_tunn_cfg->set_vxlan_udp_port_flg = 1;
-		p_tunn_cfg->vxlan_udp_port = cpu_to_le16(p_src->vxlan_udp_port);
-	}
+	if (p_src->geneve_port.b_update_port)
+		p_tun->geneve_port.port = p_src->geneve_port.port;
 
-	if (test_bit(QED_MODE_L2GRE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_l2gre = 1;
+	if (p_src->vxlan_port.b_update_port)
+		p_tun->vxlan_port.port = p_src->vxlan_port.port;
+}
 
-	if (test_bit(QED_MODE_IPGRE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_ipgre = 1;
+static void
+__qed_set_ramrod_tunnel_param(u8 *p_tunn_cls, u8 *p_enable_tx_clas,
+			      struct qed_tunn_update_type *tun_type)
+{
+	*p_tunn_cls = tun_type->tun_cls;
 
-	if (test_bit(QED_MODE_VXLAN_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_vxlan = 1;
+	if (tun_type->b_mode_enabled)
+		*p_enable_tx_clas = 1;
+}
 
-	if (p_src->update_geneve_udp_port) {
-		p_tunn_cfg->set_geneve_udp_port_flg = 1;
-		p_tunn_cfg->geneve_udp_port =
-				cpu_to_le16(p_src->geneve_udp_port);
+static void
+qed_set_ramrod_tunnel_param(u8 *p_tunn_cls, u8 *p_enable_tx_clas,
+			    struct qed_tunn_update_type *tun_type,
+			    u8 *p_update_port, __le16 *p_port,
+			    struct qed_tunn_update_udp_port *p_udp_port)
+{
+	__qed_set_ramrod_tunnel_param(p_tunn_cls, p_enable_tx_clas, tun_type);
+	if (p_udp_port->b_update_port) {
+		*p_update_port = 1;
+		*p_port = cpu_to_le16(p_udp_port->port);
 	}
+}
 
-	if (test_bit(QED_MODE_L2GENEVE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_l2geneve = 1;
-
-	if (test_bit(QED_MODE_IPGENEVE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_ipgeneve = 1;
-
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_l2geneve);
-	p_tunn_cfg->tunnel_clss_l2geneve = type;
-
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_ipgeneve);
-	p_tunn_cfg->tunnel_clss_ipgeneve = type;
+static void
+qed_tunn_set_pf_update_params(struct qed_hwfn *p_hwfn,
+			      struct qed_tunnel_info *p_src,
+			      struct pf_update_tunnel_config *p_tunn_cfg)
+{
+	struct qed_tunnel_info *p_tun = &p_hwfn->cdev->tunnel;
+
+	qed_set_pf_update_tunn_mode(p_tun, p_src, false);
+	qed_set_tunn_cls_info(p_tun, p_src);
+	qed_set_tunn_ports(p_tun, p_src);
+
+	qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_vxlan,
+				    &p_tunn_cfg->tx_enable_vxlan,
+				    &p_tun->vxlan,
+				    &p_tunn_cfg->set_vxlan_udp_port_flg,
+				    &p_tunn_cfg->vxlan_udp_port,
+				    &p_tun->vxlan_port);
+
+	qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_l2geneve,
+				    &p_tunn_cfg->tx_enable_l2geneve,
+				    &p_tun->l2_geneve,
+				    &p_tunn_cfg->set_geneve_udp_port_flg,
+				    &p_tunn_cfg->geneve_udp_port,
+				    &p_tun->geneve_port);
+
+	__qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_ipgeneve,
+				      &p_tunn_cfg->tx_enable_ipgeneve,
+				      &p_tun->ip_geneve);
+
+	__qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_l2gre,
+				      &p_tunn_cfg->tx_enable_l2gre,
+				      &p_tun->l2_gre);
+
+	__qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_ipgre,
+				      &p_tunn_cfg->tx_enable_ipgre,
+				      &p_tun->ip_gre);
+
+	p_tunn_cfg->update_rx_pf_clss = p_tun->b_update_rx_cls;
+	p_tunn_cfg->update_tx_pf_clss = p_tun->b_update_tx_cls;
 }
 
 static void qed_set_hw_tunn_mode(struct qed_hwfn *p_hwfn,
 				 struct qed_ptt *p_ptt,
-				 unsigned long tunn_mode)
+				 struct qed_tunnel_info *p_tun)
 {
-	u8 l2gre_enable = 0, ipgre_enable = 0, vxlan_enable = 0;
-	u8 l2geneve_enable = 0, ipgeneve_enable = 0;
-
-	if (test_bit(QED_MODE_L2GRE_TUNN, &tunn_mode))
-		l2gre_enable = 1;
+	qed_set_gre_enable(p_hwfn, p_ptt, p_tun->l2_gre.b_mode_enabled,
+			   p_tun->ip_gre.b_mode_enabled);
+	qed_set_vxlan_enable(p_hwfn, p_ptt, p_tun->vxlan.b_mode_enabled);
 
-	if (test_bit(QED_MODE_IPGRE_TUNN, &tunn_mode))
-		ipgre_enable = 1;
-
-	if (test_bit(QED_MODE_VXLAN_TUNN, &tunn_mode))
-		vxlan_enable = 1;
-
-	qed_set_gre_enable(p_hwfn, p_ptt, l2gre_enable, ipgre_enable);
-	qed_set_vxlan_enable(p_hwfn, p_ptt, vxlan_enable);
+	qed_set_geneve_enable(p_hwfn, p_ptt, p_tun->l2_geneve.b_mode_enabled,
+			      p_tun->ip_geneve.b_mode_enabled);
+}
 
-	if (test_bit(QED_MODE_L2GENEVE_TUNN, &tunn_mode))
-		l2geneve_enable = 1;
+static void qed_set_hw_tunn_mode_port(struct qed_hwfn *p_hwfn,
+				      struct qed_tunnel_info *p_tunn)
+{
+	if (p_tunn->vxlan_port.b_update_port)
+		qed_set_vxlan_dest_port(p_hwfn, p_hwfn->p_main_ptt,
+					p_tunn->vxlan_port.port);
 
-	if (test_bit(QED_MODE_IPGENEVE_TUNN, &tunn_mode))
-		ipgeneve_enable = 1;
+	if (p_tunn->geneve_port.b_update_port)
+		qed_set_geneve_dest_port(p_hwfn, p_hwfn->p_main_ptt,
+					 p_tunn->geneve_port.port);
 
-	qed_set_geneve_enable(p_hwfn, p_ptt, l2geneve_enable,
-			      ipgeneve_enable);
+	qed_set_hw_tunn_mode(p_hwfn, p_hwfn->p_main_ptt, p_tunn);
 }
 
 static void
 qed_tunn_set_pf_start_params(struct qed_hwfn *p_hwfn,
-			     struct qed_tunn_start_params *p_src,
+			     struct qed_tunnel_info *p_src,
 			     struct pf_start_tunnel_config *p_tunn_cfg)
 {
-	unsigned long tunn_mode;
-	enum tunnel_clss type;
+	struct qed_tunnel_info *p_tun = &p_hwfn->cdev->tunnel;
 
 	if (!p_src)
 		return;
 
-	tunn_mode = p_src->tunn_mode;
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_vxlan);
-	p_tunn_cfg->tunnel_clss_vxlan = type;
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_l2gre);
-	p_tunn_cfg->tunnel_clss_l2gre = type;
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_ipgre);
-	p_tunn_cfg->tunnel_clss_ipgre = type;
-
-	if (p_src->update_vxlan_udp_port) {
-		p_tunn_cfg->set_vxlan_udp_port_flg = 1;
-		p_tunn_cfg->vxlan_udp_port = cpu_to_le16(p_src->vxlan_udp_port);
-	}
-
-	if (test_bit(QED_MODE_L2GRE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_l2gre = 1;
-
-	if (test_bit(QED_MODE_IPGRE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_ipgre = 1;
-
-	if (test_bit(QED_MODE_VXLAN_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_vxlan = 1;
-
-	if (p_src->update_geneve_udp_port) {
-		p_tunn_cfg->set_geneve_udp_port_flg = 1;
-		p_tunn_cfg->geneve_udp_port =
-				cpu_to_le16(p_src->geneve_udp_port);
-	}
-
-	if (test_bit(QED_MODE_L2GENEVE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_l2geneve = 1;
-
-	if (test_bit(QED_MODE_IPGENEVE_TUNN, &tunn_mode))
-		p_tunn_cfg->tx_enable_ipgeneve = 1;
-
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_l2geneve);
-	p_tunn_cfg->tunnel_clss_l2geneve = type;
-	type = qed_tunn_get_clss_type(p_src->tunn_clss_ipgeneve);
-	p_tunn_cfg->tunnel_clss_ipgeneve = type;
+	qed_set_pf_update_tunn_mode(p_tun, p_src, true);
+	qed_set_tunn_cls_info(p_tun, p_src);
+	qed_set_tunn_ports(p_tun, p_src);
+
+	qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_vxlan,
+				    &p_tunn_cfg->tx_enable_vxlan,
+				    &p_tun->vxlan,
+				    &p_tunn_cfg->set_vxlan_udp_port_flg,
+				    &p_tunn_cfg->vxlan_udp_port,
+				    &p_tun->vxlan_port);
+
+	qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_l2geneve,
+				    &p_tunn_cfg->tx_enable_l2geneve,
+				    &p_tun->l2_geneve,
+				    &p_tunn_cfg->set_geneve_udp_port_flg,
+				    &p_tunn_cfg->geneve_udp_port,
+				    &p_tun->geneve_port);
+
+	__qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_ipgeneve,
+				      &p_tunn_cfg->tx_enable_ipgeneve,
+				      &p_tun->ip_geneve);
+
+	__qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_l2gre,
+				      &p_tunn_cfg->tx_enable_l2gre,
+				      &p_tun->l2_gre);
+
+	__qed_set_ramrod_tunnel_param(&p_tunn_cfg->tunnel_clss_ipgre,
+				      &p_tunn_cfg->tx_enable_ipgre,
+				      &p_tun->ip_gre);
 }
 
 int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
-		    struct qed_tunn_start_params *p_tunn,
+		    struct qed_tunnel_info *p_tunn,
 		    enum qed_mf_mode mode, bool allow_npar_tx_switch)
 {
 	struct pf_start_ramrod_data *p_ramrod = NULL;
@@ -416,11 +411,8 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
 
-	if (p_tunn) {
-		qed_set_hw_tunn_mode(p_hwfn, p_hwfn->p_main_ptt,
-				     p_tunn->tunn_mode);
-		p_hwfn->cdev->tunn_mode = p_tunn->tunn_mode;
-	}
+	if (p_tunn)
+		qed_set_hw_tunn_mode_port(p_hwfn, &p_hwfn->cdev->tunnel);
 
 	return rc;
 }
@@ -451,7 +443,7 @@ int qed_sp_pf_update(struct qed_hwfn *p_hwfn)
 
 /* Set pf update ramrod command params */
 int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn,
-			      struct qed_tunn_update_params *p_tunn,
+			      struct qed_tunnel_info *p_tunn,
 			      enum spq_mode comp_mode,
 			      struct qed_spq_comp_cb *p_comp_data)
 {
@@ -459,6 +451,12 @@ int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn,
 	struct qed_sp_init_data init_data;
 	int rc = -EINVAL;
 
+	if (IS_VF(p_hwfn->cdev))
+		return qed_vf_pf_tunnel_param_update(p_hwfn, p_tunn);
+
+	if (!p_tunn)
+		return -EINVAL;
+
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
 	init_data.cid = qed_spq_get_cid(p_hwfn);
@@ -479,15 +477,7 @@ int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn,
 	if (rc)
 		return rc;
 
-	if (p_tunn->update_vxlan_udp_port)
-		qed_set_vxlan_dest_port(p_hwfn, p_hwfn->p_main_ptt,
-					p_tunn->vxlan_udp_port);
-	if (p_tunn->update_geneve_udp_port)
-		qed_set_geneve_dest_port(p_hwfn, p_hwfn->p_main_ptt,
-					 p_tunn->geneve_udp_port);
-
-	qed_set_hw_tunn_mode(p_hwfn, p_hwfn->p_main_ptt, p_tunn->tunn_mode);
-	p_hwfn->cdev->tunn_mode = p_tunn->tunn_mode;
+	qed_set_hw_tunn_mode_port(p_hwfn, &p_hwfn->cdev->tunnel);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 645328a9f0cf..f6423a139ca0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -119,6 +119,7 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
 			 u8 *p_fw_ret, bool skip_quick_poll)
 {
 	struct qed_spq_comp_done *comp_done;
+	struct qed_ptt *p_ptt;
 	int rc;
 
 	/* A relatively short polling period w/o sleeping, to allow the FW to
@@ -135,8 +136,14 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
 	if (!rc)
 		return 0;
 
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt) {
+		DP_NOTICE(p_hwfn, "ptt, failed to acquire\n");
+		return -EAGAIN;
+	}
+
 	DP_INFO(p_hwfn, "Ramrod is stuck, requesting MCP drain\n");
-	rc = qed_mcp_drain(p_hwfn, p_hwfn->p_main_ptt);
+	rc = qed_mcp_drain(p_hwfn, p_ptt);
 	if (rc) {
 		DP_NOTICE(p_hwfn, "MCP drain failed\n");
 		goto err;
@@ -145,15 +152,18 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
 	/* Retry after drain */
 	rc = __qed_spq_block(p_hwfn, p_ent, p_fw_ret, true);
 	if (!rc)
-		return 0;
+		goto out;
 
 	comp_done = (struct qed_spq_comp_done *)p_ent->comp_cb.cookie;
-	if (comp_done->done == 1) {
+	if (comp_done->done == 1)
 		if (p_fw_ret)
 			*p_fw_ret = comp_done->fw_return_code;
-		return 0;
-	}
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+	return 0;
+
 err:
+	qed_ptt_release(p_hwfn, p_ptt);
 	DP_NOTICE(p_hwfn,
 		  "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n",
 		  le32_to_cpu(p_ent->elem.hdr.cid),
@@ -205,11 +215,10 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn,
 static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn,
 				  struct qed_spq *p_spq)
 {
-	u16				pq;
-	struct qed_cxt_info		cxt_info;
-	struct core_conn_context	*p_cxt;
-	union qed_qm_pq_params		pq_params;
-	int				rc;
+	struct core_conn_context *p_cxt;
+	struct qed_cxt_info cxt_info;
+	u16 physical_q;
+	int rc;
 
 	cxt_info.iid = p_spq->cid;
 
@@ -231,10 +240,8 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn,
 		  XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN, 1);
 
 	/* QM physical queue */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = LB_TC;
-	pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
-	p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(pq);
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB);
+	p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(physical_q);
 
 	p_cxt->xstorm_st_context.spq_base_lo =
 		DMA_LO_LE(p_spq->chain.p_phys_addr);
@@ -296,9 +303,12 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
 			   struct event_ring_entry *p_eqe)
 {
 	switch (p_eqe->protocol_id) {
+#if IS_ENABLED(CONFIG_QED_RDMA)
 	case PROTOCOLID_ROCE:
-		qed_async_roce_event(p_hwfn, p_eqe);
+		qed_roce_async_event(p_hwfn, p_eqe->opcode,
+				     &p_eqe->data.rdma_data);
 		return 0;
+#endif
 	case PROTOCOLID_COMMON:
 		return qed_sriov_eqe_event(p_hwfn,
 					   p_eqe->opcode,
@@ -306,14 +316,6 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
 	case PROTOCOLID_ISCSI:
 		if (!IS_ENABLED(CONFIG_QED_ISCSI))
 			return -EINVAL;
-		if (p_eqe->opcode == ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES) {
-			u32 cid = le32_to_cpu(p_eqe->data.iscsi_info.cid);
-
-			qed_ooo_release_connection_isles(p_hwfn,
-							 p_hwfn->p_ooo_info,
-							 cid);
-			return 0;
-		}
 
 		if (p_hwfn->p_iscsi_info->event_cb) {
 			struct qed_iscsi_info *p_iscsi = p_hwfn->p_iscsi_info;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 253c2bbe1e4e..d5df29f787c5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -178,26 +178,59 @@ static struct qed_vf_info *qed_iov_get_vf_info(struct qed_hwfn *p_hwfn,
 	return vf;
 }
 
+enum qed_iov_validate_q_mode {
+	QED_IOV_VALIDATE_Q_NA,
+	QED_IOV_VALIDATE_Q_ENABLE,
+	QED_IOV_VALIDATE_Q_DISABLE,
+};
+
+static bool qed_iov_validate_queue_mode(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf,
+					u16 qid,
+					enum qed_iov_validate_q_mode mode,
+					bool b_is_tx)
+{
+	if (mode == QED_IOV_VALIDATE_Q_NA)
+		return true;
+
+	if ((b_is_tx && p_vf->vf_queues[qid].p_tx_cid) ||
+	    (!b_is_tx && p_vf->vf_queues[qid].p_rx_cid))
+		return mode == QED_IOV_VALIDATE_Q_ENABLE;
+
+	/* In case we haven't found any valid cid, then its disabled */
+	return mode == QED_IOV_VALIDATE_Q_DISABLE;
+}
+
 static bool qed_iov_validate_rxq(struct qed_hwfn *p_hwfn,
-				 struct qed_vf_info *p_vf, u16 rx_qid)
+				 struct qed_vf_info *p_vf,
+				 u16 rx_qid,
+				 enum qed_iov_validate_q_mode mode)
 {
-	if (rx_qid >= p_vf->num_rxqs)
+	if (rx_qid >= p_vf->num_rxqs) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
 			   "VF[0x%02x] - can't touch Rx queue[%04x]; Only 0x%04x are allocated\n",
 			   p_vf->abs_vf_id, rx_qid, p_vf->num_rxqs);
-	return rx_qid < p_vf->num_rxqs;
+		return false;
+	}
+
+	return qed_iov_validate_queue_mode(p_hwfn, p_vf, rx_qid, mode, false);
 }
 
 static bool qed_iov_validate_txq(struct qed_hwfn *p_hwfn,
-				 struct qed_vf_info *p_vf, u16 tx_qid)
+				 struct qed_vf_info *p_vf,
+				 u16 tx_qid,
+				 enum qed_iov_validate_q_mode mode)
 {
-	if (tx_qid >= p_vf->num_txqs)
+	if (tx_qid >= p_vf->num_txqs) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
 			   "VF[0x%02x] - can't touch Tx queue[%04x]; Only 0x%04x are allocated\n",
 			   p_vf->abs_vf_id, tx_qid, p_vf->num_txqs);
-	return tx_qid < p_vf->num_txqs;
+		return false;
+	}
+
+	return qed_iov_validate_queue_mode(p_hwfn, p_vf, tx_qid, mode, true);
 }
 
 static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
@@ -217,6 +250,34 @@ static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
 	return false;
 }
 
+static bool qed_iov_validate_active_rxq(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf)
+{
+	u8 i;
+
+	for (i = 0; i < p_vf->num_rxqs; i++)
+		if (qed_iov_validate_queue_mode(p_hwfn, p_vf, i,
+						QED_IOV_VALIDATE_Q_ENABLE,
+						false))
+			return true;
+
+	return false;
+}
+
+static bool qed_iov_validate_active_txq(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf)
+{
+	u8 i;
+
+	for (i = 0; i < p_vf->num_txqs; i++)
+		if (qed_iov_validate_queue_mode(p_hwfn, p_vf, i,
+						QED_IOV_VALIDATE_Q_ENABLE,
+						true))
+			return true;
+
+	return false;
+}
+
 static int qed_iov_post_vf_bulletin(struct qed_hwfn *p_hwfn,
 				    int vfid, struct qed_ptt *p_ptt)
 {
@@ -557,14 +618,30 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
 		return 0;
 	}
 
-	/* Calculate the first VF index - this is a bit tricky; Basically,
-	 * VFs start at offset 16 relative to PF0, and 2nd engine VFs begin
-	 * after the first engine's VFs.
+	/* First VF index based on offset is tricky:
+	 *  - If ARI is supported [likely], offset - (16 - pf_id) would
+	 *    provide the number for eng0. 2nd engine Vfs would begin
+	 *    after the first engine's VFs.
+	 *  - If !ARI, VFs would start on next device.
+	 *    so offset - (256 - pf_id) would provide the number.
+	 * Utilize the fact that (256 - pf_id) is achieved only by later
+	 * to diffrentiate between the two.
 	 */
-	cdev->p_iov_info->first_vf_in_pf = p_hwfn->cdev->p_iov_info->offset +
-					   p_hwfn->abs_pf_id - 16;
-	if (QED_PATH_ID(p_hwfn))
-		cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+
+	if (p_hwfn->cdev->p_iov_info->offset < (256 - p_hwfn->abs_pf_id)) {
+		u32 first = p_hwfn->cdev->p_iov_info->offset +
+			    p_hwfn->abs_pf_id - 16;
+
+		cdev->p_iov_info->first_vf_in_pf = first;
+
+		if (QED_PATH_ID(p_hwfn))
+			cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+	} else {
+		u32 first = p_hwfn->cdev->p_iov_info->offset +
+			    p_hwfn->abs_pf_id - 256;
+
+		cdev->p_iov_info->first_vf_in_pf = first;
+	}
 
 	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
 		   "First VF in hwfn 0x%08x\n",
@@ -677,6 +754,11 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
 	u32 igu_vf_conf = IGU_VF_CONF_FUNC_EN;
 	int rc;
 
+	/* It's possible VF was previously considered malicious -
+	 * clear the indication even if we're only going to disable VF.
+	 */
+	vf->b_malicious = false;
+
 	if (vf->to_disable)
 		return 0;
 
@@ -689,9 +771,6 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
 
 	qed_iov_vf_igu_reset(p_hwfn, p_ptt, vf);
 
-	/* It's possible VF was previously considered malicious */
-	vf->b_malicious = false;
-
 	rc = qed_mcp_config_vf_msix(p_hwfn, p_ptt, vf->abs_vf_id, vf->num_sbs);
 	if (rc)
 		return rc;
@@ -1118,13 +1197,17 @@ static void qed_iov_send_response(struct qed_hwfn *p_hwfn,
 			   (sizeof(union pfvf_tlvs) - sizeof(u64)) / 4,
 			   &params);
 
-	qed_dmae_host2host(p_hwfn, p_ptt, mbx->reply_phys,
-			   mbx->req_virt->first_tlv.reply_address,
-			   sizeof(u64) / 4, &params);
-
+	/* Once PF copies the rc to the VF, the latter can continue
+	 * and send an additional message. So we have to make sure the
+	 * channel would be re-set to ready prior to that.
+	 */
 	REG_WR(p_hwfn,
 	       GTT_BAR0_MAP_REG_USDM_RAM +
 	       USTORM_VF_PF_CHANNEL_READY_OFFSET(eng_vf_id), 1);
+
+	qed_dmae_host2host(p_hwfn, p_ptt, mbx->reply_phys,
+			   mbx->req_virt->first_tlv.reply_address,
+			   sizeof(u64) / 4, &params);
 }
 
 static u16 qed_iov_vport_to_tlv(struct qed_hwfn *p_hwfn,
@@ -1733,6 +1816,8 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
 	vf->state = VF_ENABLED;
 	start = &mbx->req_virt->start_vport;
 
+	qed_iov_enable_vf_traffic(p_hwfn, p_ptt, vf);
+
 	/* Initialize Status block in CAU */
 	for (sb_id = 0; sb_id < vf->num_sbs; sb_id++) {
 		if (!start->sb_addr[sb_id]) {
@@ -1746,7 +1831,6 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
 				    start->sb_addr[sb_id],
 				    vf->igu_sbs[sb_id], vf->abs_vf_id, 1);
 	}
-	qed_iov_enable_vf_traffic(p_hwfn, p_ptt, vf);
 
 	vf->mtu = start->mtu;
 	vf->shadow_config.inner_vlan_removal = start->inner_vlan_removal;
@@ -1803,6 +1887,16 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
 	vf->vport_instance--;
 	vf->spoof_chk = false;
 
+	if ((qed_iov_validate_active_rxq(p_hwfn, vf)) ||
+	    (qed_iov_validate_active_txq(p_hwfn, vf))) {
+		vf->b_malicious = true;
+		DP_NOTICE(p_hwfn,
+			  "VF [%02x] - considered malicious; Unable to stop RX/TX queuess\n",
+			  vf->abs_vf_id);
+		status = PFVF_STATUS_MALICIOUS;
+		goto out;
+	}
+
 	rc = qed_sp_vport_stop(p_hwfn, vf->opaque_fid, vf->vport_id);
 	if (rc) {
 		DP_ERR(p_hwfn, "qed_iov_vf_mbx_stop_vport returned error %d\n",
@@ -1814,6 +1908,7 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
 	vf->configured_features = 0;
 	memset(&vf->shadow_config, 0, sizeof(vf->shadow_config));
 
+out:
 	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_VPORT_TEARDOWN,
 			     sizeof(struct pfvf_def_resp_tlv), status);
 }
@@ -1870,7 +1965,8 @@ static void qed_iov_vf_mbx_start_rxq(struct qed_hwfn *p_hwfn,
 
 	req = &mbx->req_virt->start_rxq;
 
-	if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid) ||
+	if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid,
+				  QED_IOV_VALIDATE_Q_DISABLE) ||
 	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
 		goto out;
 
@@ -1923,6 +2019,220 @@ out:
 	qed_iov_vf_mbx_start_rxq_resp(p_hwfn, p_ptt, vf, status, b_legacy_vf);
 }
 
+static void
+qed_iov_pf_update_tun_response(struct pfvf_update_tunn_param_tlv *p_resp,
+			       struct qed_tunnel_info *p_tun,
+			       u16 tunn_feature_mask)
+{
+	p_resp->tunn_feature_mask = tunn_feature_mask;
+	p_resp->vxlan_mode = p_tun->vxlan.b_mode_enabled;
+	p_resp->l2geneve_mode = p_tun->l2_geneve.b_mode_enabled;
+	p_resp->ipgeneve_mode = p_tun->ip_geneve.b_mode_enabled;
+	p_resp->l2gre_mode = p_tun->l2_gre.b_mode_enabled;
+	p_resp->ipgre_mode = p_tun->l2_gre.b_mode_enabled;
+	p_resp->vxlan_clss = p_tun->vxlan.tun_cls;
+	p_resp->l2gre_clss = p_tun->l2_gre.tun_cls;
+	p_resp->ipgre_clss = p_tun->ip_gre.tun_cls;
+	p_resp->l2geneve_clss = p_tun->l2_geneve.tun_cls;
+	p_resp->ipgeneve_clss = p_tun->ip_geneve.tun_cls;
+	p_resp->geneve_udp_port = p_tun->geneve_port.port;
+	p_resp->vxlan_udp_port = p_tun->vxlan_port.port;
+}
+
+static void
+__qed_iov_pf_update_tun_param(struct vfpf_update_tunn_param_tlv *p_req,
+			      struct qed_tunn_update_type *p_tun,
+			      enum qed_tunn_mode mask, u8 tun_cls)
+{
+	if (p_req->tun_mode_update_mask & BIT(mask)) {
+		p_tun->b_update_mode = true;
+
+		if (p_req->tunn_mode & BIT(mask))
+			p_tun->b_mode_enabled = true;
+	}
+
+	p_tun->tun_cls = tun_cls;
+}
+
+static void
+qed_iov_pf_update_tun_param(struct vfpf_update_tunn_param_tlv *p_req,
+			    struct qed_tunn_update_type *p_tun,
+			    struct qed_tunn_update_udp_port *p_port,
+			    enum qed_tunn_mode mask,
+			    u8 tun_cls, u8 update_port, u16 port)
+{
+	if (update_port) {
+		p_port->b_update_port = true;
+		p_port->port = port;
+	}
+
+	__qed_iov_pf_update_tun_param(p_req, p_tun, mask, tun_cls);
+}
+
+static bool
+qed_iov_pf_validate_tunn_param(struct vfpf_update_tunn_param_tlv *p_req)
+{
+	bool b_update_requested = false;
+
+	if (p_req->tun_mode_update_mask || p_req->update_tun_cls ||
+	    p_req->update_geneve_port || p_req->update_vxlan_port)
+		b_update_requested = true;
+
+	return b_update_requested;
+}
+
+static void qed_pf_validate_tunn_mode(struct qed_tunn_update_type *tun, int *rc)
+{
+	if (tun->b_update_mode && !tun->b_mode_enabled) {
+		tun->b_update_mode = false;
+		*rc = -EINVAL;
+	}
+}
+
+static int
+qed_pf_validate_modify_tunn_config(struct qed_hwfn *p_hwfn,
+				   u16 *tun_features, bool *update,
+				   struct qed_tunnel_info *tun_src)
+{
+	struct qed_eth_cb_ops *ops = p_hwfn->cdev->protocol_ops.eth;
+	struct qed_tunnel_info *tun = &p_hwfn->cdev->tunnel;
+	u16 bultn_vxlan_port, bultn_geneve_port;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+	int i, rc = 0;
+
+	*tun_features = p_hwfn->cdev->tunn_feature_mask;
+	bultn_vxlan_port = tun->vxlan_port.port;
+	bultn_geneve_port = tun->geneve_port.port;
+	qed_pf_validate_tunn_mode(&tun_src->vxlan, &rc);
+	qed_pf_validate_tunn_mode(&tun_src->l2_geneve, &rc);
+	qed_pf_validate_tunn_mode(&tun_src->ip_geneve, &rc);
+	qed_pf_validate_tunn_mode(&tun_src->l2_gre, &rc);
+	qed_pf_validate_tunn_mode(&tun_src->ip_gre, &rc);
+
+	if ((tun_src->b_update_rx_cls || tun_src->b_update_tx_cls) &&
+	    (tun_src->vxlan.tun_cls != QED_TUNN_CLSS_MAC_VLAN ||
+	     tun_src->l2_geneve.tun_cls != QED_TUNN_CLSS_MAC_VLAN ||
+	     tun_src->ip_geneve.tun_cls != QED_TUNN_CLSS_MAC_VLAN ||
+	     tun_src->l2_gre.tun_cls != QED_TUNN_CLSS_MAC_VLAN ||
+	     tun_src->ip_gre.tun_cls != QED_TUNN_CLSS_MAC_VLAN)) {
+		tun_src->b_update_rx_cls = false;
+		tun_src->b_update_tx_cls = false;
+		rc = -EINVAL;
+	}
+
+	if (tun_src->vxlan_port.b_update_port) {
+		if (tun_src->vxlan_port.port == tun->vxlan_port.port) {
+			tun_src->vxlan_port.b_update_port = false;
+		} else {
+			*update = true;
+			bultn_vxlan_port = tun_src->vxlan_port.port;
+		}
+	}
+
+	if (tun_src->geneve_port.b_update_port) {
+		if (tun_src->geneve_port.port == tun->geneve_port.port) {
+			tun_src->geneve_port.b_update_port = false;
+		} else {
+			*update = true;
+			bultn_geneve_port = tun_src->geneve_port.port;
+		}
+	}
+
+	qed_for_each_vf(p_hwfn, i) {
+		qed_iov_bulletin_set_udp_ports(p_hwfn, i, bultn_vxlan_port,
+					       bultn_geneve_port);
+	}
+
+	qed_schedule_iov(p_hwfn, QED_IOV_WQ_BULLETIN_UPDATE_FLAG);
+	ops->ports_update(cookie, bultn_vxlan_port, bultn_geneve_port);
+
+	return rc;
+}
+
+static void qed_iov_vf_mbx_update_tunn_param(struct qed_hwfn *p_hwfn,
+					     struct qed_ptt *p_ptt,
+					     struct qed_vf_info *p_vf)
+{
+	struct qed_tunnel_info *p_tun = &p_hwfn->cdev->tunnel;
+	struct qed_iov_vf_mbx *mbx = &p_vf->vf_mbx;
+	struct pfvf_update_tunn_param_tlv *p_resp;
+	struct vfpf_update_tunn_param_tlv *p_req;
+	u8 status = PFVF_STATUS_SUCCESS;
+	bool b_update_required = false;
+	struct qed_tunnel_info tunn;
+	u16 tunn_feature_mask = 0;
+	int i, rc = 0;
+
+	mbx->offset = (u8 *)mbx->reply_virt;
+
+	memset(&tunn, 0, sizeof(tunn));
+	p_req = &mbx->req_virt->tunn_param_update;
+
+	if (!qed_iov_pf_validate_tunn_param(p_req)) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "No tunnel update requested by VF\n");
+		status = PFVF_STATUS_FAILURE;
+		goto send_resp;
+	}
+
+	tunn.b_update_rx_cls = p_req->update_tun_cls;
+	tunn.b_update_tx_cls = p_req->update_tun_cls;
+
+	qed_iov_pf_update_tun_param(p_req, &tunn.vxlan, &tunn.vxlan_port,
+				    QED_MODE_VXLAN_TUNN, p_req->vxlan_clss,
+				    p_req->update_vxlan_port,
+				    p_req->vxlan_port);
+	qed_iov_pf_update_tun_param(p_req, &tunn.l2_geneve, &tunn.geneve_port,
+				    QED_MODE_L2GENEVE_TUNN,
+				    p_req->l2geneve_clss,
+				    p_req->update_geneve_port,
+				    p_req->geneve_port);
+	__qed_iov_pf_update_tun_param(p_req, &tunn.ip_geneve,
+				      QED_MODE_IPGENEVE_TUNN,
+				      p_req->ipgeneve_clss);
+	__qed_iov_pf_update_tun_param(p_req, &tunn.l2_gre,
+				      QED_MODE_L2GRE_TUNN, p_req->l2gre_clss);
+	__qed_iov_pf_update_tun_param(p_req, &tunn.ip_gre,
+				      QED_MODE_IPGRE_TUNN, p_req->ipgre_clss);
+
+	/* If PF modifies VF's req then it should
+	 * still return an error in case of partial configuration
+	 * or modified configuration as opposed to requested one.
+	 */
+	rc = qed_pf_validate_modify_tunn_config(p_hwfn, &tunn_feature_mask,
+						&b_update_required, &tunn);
+
+	if (rc)
+		status = PFVF_STATUS_FAILURE;
+
+	/* If QED client is willing to update anything ? */
+	if (b_update_required) {
+		u16 geneve_port;
+
+		rc = qed_sp_pf_update_tunn_cfg(p_hwfn, &tunn,
+					       QED_SPQ_MODE_EBLOCK, NULL);
+		if (rc)
+			status = PFVF_STATUS_FAILURE;
+
+		geneve_port = p_tun->geneve_port.port;
+		qed_for_each_vf(p_hwfn, i) {
+			qed_iov_bulletin_set_udp_ports(p_hwfn, i,
+						       p_tun->vxlan_port.port,
+						       geneve_port);
+		}
+	}
+
+send_resp:
+	p_resp = qed_add_tlv(p_hwfn, &mbx->offset,
+			     CHANNEL_TLV_UPDATE_TUNN_PARAM, sizeof(*p_resp));
+
+	qed_iov_pf_update_tun_response(p_resp, p_tun, tunn_feature_mask);
+	qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_LIST_END,
+		    sizeof(struct channel_list_end_tlv));
+
+	qed_iov_send_response(p_hwfn, p_ptt, p_vf, sizeof(*p_resp), status);
+}
+
 static void qed_iov_vf_mbx_start_txq_resp(struct qed_hwfn *p_hwfn,
 					  struct qed_ptt *p_ptt,
 					  struct qed_vf_info *p_vf, u8 status)
@@ -1970,21 +2280,16 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 	struct qed_queue_start_common_params params;
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
 	u8 status = PFVF_STATUS_NO_RESOURCE;
-	union qed_qm_pq_params pq_params;
 	struct vfpf_start_txq_tlv *req;
 	struct qed_vf_q_info *p_queue;
 	int rc;
 	u16 pq;
 
-	/* Prepare the parameters which would choose the right PQ */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.eth.is_vf = 1;
-	pq_params.eth.vf_id = vf->relative_vf_id;
-
 	memset(&params, 0, sizeof(params));
 	req = &mbx->req_virt->start_txq;
 
-	if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid) ||
+	if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid,
+				  QED_IOV_VALIDATE_Q_DISABLE) ||
 	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
 		goto out;
 
@@ -2004,7 +2309,7 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 	if (!p_queue->p_tx_cid)
 		goto out;
 
-	pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, &pq_params);
+	pq = qed_get_cm_pq_idx_vf(p_hwfn, vf->relative_vf_id);
 	rc = qed_eth_txq_start_ramrod(p_hwfn, p_queue->p_tx_cid,
 				      req->pbl_addr, req->pbl_size, pq);
 	if (rc) {
@@ -2021,57 +2326,53 @@ out:
 
 static int qed_iov_vf_stop_rxqs(struct qed_hwfn *p_hwfn,
 				struct qed_vf_info *vf,
-				u16 rxq_id, u8 num_rxqs, bool cqe_completion)
+				u16 rxq_id, bool cqe_completion)
 {
 	struct qed_vf_q_info *p_queue;
 	int rc = 0;
-	int qid;
 
-	if (rxq_id + num_rxqs > ARRAY_SIZE(vf->vf_queues))
+	if (!qed_iov_validate_rxq(p_hwfn, vf, rxq_id,
+				  QED_IOV_VALIDATE_Q_ENABLE)) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[%d] Tried Closing Rx 0x%04x which is inactive\n",
+			   vf->relative_vf_id, rxq_id);
 		return -EINVAL;
+	}
 
-	for (qid = rxq_id; qid < rxq_id + num_rxqs; qid++) {
-		p_queue = &vf->vf_queues[qid];
+	p_queue = &vf->vf_queues[rxq_id];
 
-		if (!p_queue->p_rx_cid)
-			continue;
-
-		rc = qed_eth_rx_queue_stop(p_hwfn,
-					   p_queue->p_rx_cid,
-					   false, cqe_completion);
-		if (rc)
-			return rc;
+	rc = qed_eth_rx_queue_stop(p_hwfn,
+				   p_queue->p_rx_cid,
+				   false, cqe_completion);
+	if (rc)
+		return rc;
 
-		vf->vf_queues[qid].p_rx_cid = NULL;
-		vf->num_active_rxqs--;
-	}
+	p_queue->p_rx_cid = NULL;
+	vf->num_active_rxqs--;
 
-	return rc;
+	return 0;
 }
 
 static int qed_iov_vf_stop_txqs(struct qed_hwfn *p_hwfn,
-				struct qed_vf_info *vf, u16 txq_id, u8 num_txqs)
+				struct qed_vf_info *vf, u16 txq_id)
 {
-	int rc = 0;
 	struct qed_vf_q_info *p_queue;
-	int qid;
+	int rc = 0;
 
-	if (txq_id + num_txqs > ARRAY_SIZE(vf->vf_queues))
+	if (!qed_iov_validate_txq(p_hwfn, vf, txq_id,
+				  QED_IOV_VALIDATE_Q_ENABLE))
 		return -EINVAL;
 
-	for (qid = txq_id; qid < txq_id + num_txqs; qid++) {
-		p_queue = &vf->vf_queues[qid];
-		if (!p_queue->p_tx_cid)
-			continue;
+	p_queue = &vf->vf_queues[txq_id];
 
-		rc = qed_eth_tx_queue_stop(p_hwfn, p_queue->p_tx_cid);
-		if (rc)
-			return rc;
+	rc = qed_eth_tx_queue_stop(p_hwfn, p_queue->p_tx_cid);
+	if (rc)
+		return rc;
 
-		p_queue->p_tx_cid = NULL;
-	}
+	p_queue->p_tx_cid = NULL;
 
-	return rc;
+	return 0;
 }
 
 static void qed_iov_vf_mbx_stop_rxqs(struct qed_hwfn *p_hwfn,
@@ -2080,20 +2381,28 @@ static void qed_iov_vf_mbx_stop_rxqs(struct qed_hwfn *p_hwfn,
 {
 	u16 length = sizeof(struct pfvf_def_resp_tlv);
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
-	u8 status = PFVF_STATUS_SUCCESS;
+	u8 status = PFVF_STATUS_FAILURE;
 	struct vfpf_stop_rxqs_tlv *req;
 	int rc;
 
-	/* We give the option of starting from qid != 0, in this case we
-	 * need to make sure that qid + num_qs doesn't exceed the actual
-	 * amount of queues that exist.
+	/* There has never been an official driver that used this interface
+	 * for stopping multiple queues, and it is now considered deprecated.
+	 * Validate this isn't used here.
 	 */
 	req = &mbx->req_virt->stop_rxqs;
-	rc = qed_iov_vf_stop_rxqs(p_hwfn, vf, req->rx_qid,
-				  req->num_rxqs, req->cqe_completion);
-	if (rc)
-		status = PFVF_STATUS_FAILURE;
+	if (req->num_rxqs != 1) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Odd; VF[%d] tried stopping multiple Rx queues\n",
+			   vf->relative_vf_id);
+		status = PFVF_STATUS_NOT_SUPPORTED;
+		goto out;
+	}
 
+	rc = qed_iov_vf_stop_rxqs(p_hwfn, vf, req->rx_qid,
+				  req->cqe_completion);
+	if (!rc)
+		status = PFVF_STATUS_SUCCESS;
+out:
 	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_STOP_RXQS,
 			     length, status);
 }
@@ -2104,19 +2413,27 @@ static void qed_iov_vf_mbx_stop_txqs(struct qed_hwfn *p_hwfn,
 {
 	u16 length = sizeof(struct pfvf_def_resp_tlv);
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
-	u8 status = PFVF_STATUS_SUCCESS;
+	u8 status = PFVF_STATUS_FAILURE;
 	struct vfpf_stop_txqs_tlv *req;
 	int rc;
 
-	/* We give the option of starting from qid != 0, in this case we
-	 * need to make sure that qid + num_qs doesn't exceed the actual
-	 * amount of queues that exist.
+	/* There has never been an official driver that used this interface
+	 * for stopping multiple queues, and it is now considered deprecated.
+	 * Validate this isn't used here.
 	 */
 	req = &mbx->req_virt->stop_txqs;
-	rc = qed_iov_vf_stop_txqs(p_hwfn, vf, req->tx_qid, req->num_txqs);
-	if (rc)
-		status = PFVF_STATUS_FAILURE;
+	if (req->num_txqs != 1) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Odd; VF[%d] tried stopping multiple Tx queues\n",
+			   vf->relative_vf_id);
+		status = PFVF_STATUS_NOT_SUPPORTED;
+		goto out;
+	}
+	rc = qed_iov_vf_stop_txqs(p_hwfn, vf, req->tx_qid);
+	if (!rc)
+		status = PFVF_STATUS_SUCCESS;
 
+out:
 	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_STOP_TXQS,
 			     length, status);
 }
@@ -2141,22 +2458,17 @@ static void qed_iov_vf_mbx_update_rxqs(struct qed_hwfn *p_hwfn,
 	complete_event_flg = !!(req->flags & VFPF_RXQ_UPD_COMPLETE_EVENT_FLAG);
 
 	/* Validate inputs */
-	if (req->num_rxqs + req->rx_qid > QED_MAX_VF_CHAINS_PER_PF ||
-	    !qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid)) {
-		DP_INFO(p_hwfn, "VF[%d]: Incorrect Rxqs [%04x, %02x]\n",
-			vf->relative_vf_id, req->rx_qid, req->num_rxqs);
-		goto out;
-	}
-
-	for (i = 0; i < req->num_rxqs; i++) {
-		qid = req->rx_qid + i;
-		if (!vf->vf_queues[qid].p_rx_cid) {
-			DP_INFO(p_hwfn,
-				"VF[%d] rx_qid = %d isn`t active!\n",
-				vf->relative_vf_id, qid);
+	for (i = req->rx_qid; i < req->rx_qid + req->num_rxqs; i++)
+		if (!qed_iov_validate_rxq(p_hwfn, vf, i,
+					  QED_IOV_VALIDATE_Q_ENABLE)) {
+			DP_INFO(p_hwfn, "VF[%d]: Incorrect Rxqs [%04x, %02x]\n",
+				vf->relative_vf_id, req->rx_qid, req->num_rxqs);
 			goto out;
 		}
 
+	/* Prepare the handlers */
+	for (i = 0; i < req->num_rxqs; i++) {
+		qid = req->rx_qid + i;
 		handlers[i] = vf->vf_queues[qid].p_rx_cid;
 	}
 
@@ -2372,7 +2684,8 @@ qed_iov_vp_update_rss_param(struct qed_hwfn *p_hwfn,
 
 	for (i = 0; i < table_size; i++) {
 		q_idx = p_rss_tlv->rss_ind_table[i];
-		if (!qed_iov_validate_rxq(p_hwfn, vf, q_idx)) {
+		if (!qed_iov_validate_rxq(p_hwfn, vf, q_idx,
+					  QED_IOV_VALIDATE_Q_ENABLE)) {
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_IOV,
 				   "VF[%d]: Omitting RSS due to wrong queue %04x\n",
@@ -2381,15 +2694,6 @@ qed_iov_vp_update_rss_param(struct qed_hwfn *p_hwfn,
 			goto out;
 		}
 
-		if (!vf->vf_queues[q_idx].p_rx_cid) {
-			DP_VERBOSE(p_hwfn,
-				   QED_MSG_IOV,
-				   "VF[%d]: Omitting RSS due to inactive queue %08x\n",
-				   vf->relative_vf_id, q_idx);
-			b_reject = true;
-			goto out;
-		}
-
 		p_rss->rss_ind_table[i] = vf->vf_queues[q_idx].p_rx_cid;
 	}
 
@@ -3042,9 +3346,10 @@ qed_iov_vf_flr_cleanup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return rc;
 }
 
-int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
+bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
 {
-	u16 i, found = 0;
+	bool found = false;
+	u16 i;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_IOV, "Marking FLR-ed VFs\n");
 	for (i = 0; i < (VF_MAX_STATIC / 32); i++)
@@ -3054,7 +3359,7 @@ int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
 
 	if (!p_hwfn->cdev->p_iov_info) {
 		DP_NOTICE(p_hwfn, "VF flr but no IOV\n");
-		return 0;
+		return false;
 	}
 
 	/* Mark VFs */
@@ -3083,7 +3388,7 @@ int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
 			 * VF flr until ACKs, we're safe.
 			 */
 			p_flr[rel_vf_id / 64] |= 1ULL << (rel_vf_id % 64);
-			found = 1;
+			found = true;
 		}
 	}
 
@@ -3184,6 +3489,9 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn,
 		case CHANNEL_TLV_RELEASE:
 			qed_iov_vf_mbx_release(p_hwfn, p_ptt, p_vf);
 			break;
+		case CHANNEL_TLV_UPDATE_TUNN_PARAM:
+			qed_iov_vf_mbx_update_tunn_param(p_hwfn, p_ptt, p_vf);
+			break;
 		}
 	} else if (qed_iov_tlv_supported(mbx->first_tlv.tl.type)) {
 		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
@@ -3289,11 +3597,17 @@ static void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn,
 	if (!p_vf)
 		return;
 
-	DP_INFO(p_hwfn,
-		"VF [%d] - Malicious behavior [%02x]\n",
-		p_vf->abs_vf_id, p_data->err_id);
+	if (!p_vf->b_malicious) {
+		DP_NOTICE(p_hwfn,
+			  "VF [%d] - Malicious behavior [%02x]\n",
+			  p_vf->abs_vf_id, p_data->err_id);
 
-	p_vf->b_malicious = true;
+		p_vf->b_malicious = true;
+	} else {
+		DP_INFO(p_hwfn,
+			"VF [%d] - Malicious behavior [%02x]\n",
+			p_vf->abs_vf_id, p_data->err_id);
+	}
 }
 
 int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
@@ -3414,6 +3728,29 @@ static void qed_iov_bulletin_set_forced_vlan(struct qed_hwfn *p_hwfn,
 	qed_iov_configure_vport_forced(p_hwfn, vf_info, feature);
 }
 
+void qed_iov_bulletin_set_udp_ports(struct qed_hwfn *p_hwfn,
+				    int vfid, u16 vxlan_port, u16 geneve_port)
+{
+	struct qed_vf_info *vf_info;
+
+	vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true);
+	if (!vf_info) {
+		DP_NOTICE(p_hwfn->cdev,
+			  "Can not set udp ports, invalid vfid [%d]\n", vfid);
+		return;
+	}
+
+	if (vf_info->b_malicious) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Can not set udp ports to malicious VF [%d]\n",
+			   vfid);
+		return;
+	}
+
+	vf_info->bulletin.p_virt->vxlan_udp_port = vxlan_port;
+	vf_info->bulletin.p_virt->geneve_udp_port = geneve_port;
+}
+
 static bool qed_iov_vf_has_vport_instance(struct qed_hwfn *p_hwfn, int vfid)
 {
 	struct qed_vf_info *p_vf_info;
@@ -3842,6 +4179,7 @@ static int qed_get_vf_config(struct qed_dev *cdev,
 
 void qed_inform_vf_link_state(struct qed_hwfn *hwfn)
 {
+	struct qed_hwfn *lead_hwfn = QED_LEADING_HWFN(hwfn->cdev);
 	struct qed_mcp_link_capabilities caps;
 	struct qed_mcp_link_params params;
 	struct qed_mcp_link_state link;
@@ -3858,9 +4196,15 @@ void qed_inform_vf_link_state(struct qed_hwfn *hwfn)
 		if (!vf_info)
 			continue;
 
-		memcpy(&params, qed_mcp_get_link_params(hwfn), sizeof(params));
-		memcpy(&link, qed_mcp_get_link_state(hwfn), sizeof(link));
-		memcpy(&caps, qed_mcp_get_link_capabilities(hwfn),
+		/* Only hwfn0 is actually interested in the link speed.
+		 * But since only it would receive an MFW indication of link,
+		 * need to take configuration from it - otherwise things like
+		 * rate limiting for hwfn1 VF would not work.
+		 */
+		memcpy(&params, qed_mcp_get_link_params(lead_hwfn),
+		       sizeof(params));
+		memcpy(&link, qed_mcp_get_link_state(lead_hwfn), sizeof(link));
+		memcpy(&caps, qed_mcp_get_link_capabilities(lead_hwfn),
 		       sizeof(caps));
 
 		/* Modify link according to the VF's configured link state */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index a89605821522..81a497ce6585 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -270,6 +270,9 @@ enum qed_iov_wq_flag {
  */
 u16 qed_iov_get_next_active_vf(struct qed_hwfn *p_hwfn, u16 rel_vf_id);
 
+void qed_iov_bulletin_set_udp_ports(struct qed_hwfn *p_hwfn,
+				    int vfid, u16 vxlan_port, u16 geneve_port);
+
 /**
  * @brief Read sriov related information and allocated resources
  *  reads from configuraiton space, shmem, etc.
@@ -348,9 +351,9 @@ int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
  * @param p_hwfn
  * @param disabled_vfs - bitmask of all VFs on path that were FLRed
  *
- * @return 1 iff one of the PF's vfs got FLRed. 0 otherwise.
+ * @return true iff one of the PF's vfs got FLRed. false otherwise.
  */
-int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs);
+bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs);
 
 /**
  * @brief Search extended TLVs in request/reply buffer.
@@ -378,6 +381,12 @@ static inline u16 qed_iov_get_next_active_vf(struct qed_hwfn *p_hwfn,
 	return MAX_NUM_VFS;
 }
 
+static inline void
+qed_iov_bulletin_set_udp_ports(struct qed_hwfn *p_hwfn, int vfid,
+			       u16 vxlan_port, u16 geneve_port)
+{
+}
+
 static inline int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
 {
 	return 0;
@@ -407,10 +416,10 @@ static inline int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
 	return -EINVAL;
 }
 
-static inline int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn,
-				      u32 *disabled_vfs)
+static inline bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn,
+				       u32 *disabled_vfs)
 {
-	return 0;
+	return false;
 }
 
 static inline void qed_iov_wq_stop(struct qed_dev *cdev, bool schedule_first)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 15d2855ec563..11d71e5eea14 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -134,14 +134,20 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	}
 
 	if (!*done) {
-		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
-			   "VF <-- PF Timeout [Type %d]\n",
-			   p_req->first_tlv.tl.type);
+		DP_NOTICE(p_hwfn,
+			  "VF <-- PF Timeout [Type %d]\n",
+			  p_req->first_tlv.tl.type);
 		rc = -EBUSY;
 	} else {
-		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
-			   "PF response: %d [Type %d]\n",
-			   *done, p_req->first_tlv.tl.type);
+		if ((*done != PFVF_STATUS_SUCCESS) &&
+		    (*done != PFVF_STATUS_NO_RESOURCE))
+			DP_NOTICE(p_hwfn,
+				  "PF response: %d [Type %d]\n",
+				  *done, p_req->first_tlv.tl.type);
+		else
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "PF response: %d [Type %d]\n",
+				   *done, p_req->first_tlv.tl.type);
 	}
 
 	return rc;
@@ -228,7 +234,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 		/* send acquire request */
 		rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
 		if (rc)
-			return rc;
+			goto exit;
 
 		/* copy acquire response from buffer to p_hwfn */
 		memcpy(&p_iov->acquire_resp, resp, sizeof(p_iov->acquire_resp));
@@ -412,6 +418,155 @@ free_p_iov:
 #define MSTORM_QZONE_START(dev)   (TSTORM_QZONE_START +	\
 				   (TSTORM_QZONE_SIZE * NUM_OF_L2_QUEUES(dev)))
 
+static void
+__qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req,
+			   struct qed_tunn_update_type *p_src,
+			   enum qed_tunn_clss mask, u8 *p_cls)
+{
+	if (p_src->b_update_mode) {
+		p_req->tun_mode_update_mask |= BIT(mask);
+
+		if (p_src->b_mode_enabled)
+			p_req->tunn_mode |= BIT(mask);
+	}
+
+	*p_cls = p_src->tun_cls;
+}
+
+static void
+qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req,
+			 struct qed_tunn_update_type *p_src,
+			 enum qed_tunn_clss mask,
+			 u8 *p_cls, struct qed_tunn_update_udp_port *p_port,
+			 u8 *p_update_port, u16 *p_udp_port)
+{
+	if (p_port->b_update_port) {
+		*p_update_port = 1;
+		*p_udp_port = p_port->port;
+	}
+
+	__qed_vf_prep_tunn_req_tlv(p_req, p_src, mask, p_cls);
+}
+
+void qed_vf_set_vf_start_tunn_update_param(struct qed_tunnel_info *p_tun)
+{
+	if (p_tun->vxlan.b_mode_enabled)
+		p_tun->vxlan.b_update_mode = true;
+	if (p_tun->l2_geneve.b_mode_enabled)
+		p_tun->l2_geneve.b_update_mode = true;
+	if (p_tun->ip_geneve.b_mode_enabled)
+		p_tun->ip_geneve.b_update_mode = true;
+	if (p_tun->l2_gre.b_mode_enabled)
+		p_tun->l2_gre.b_update_mode = true;
+	if (p_tun->ip_gre.b_mode_enabled)
+		p_tun->ip_gre.b_update_mode = true;
+
+	p_tun->b_update_rx_cls = true;
+	p_tun->b_update_tx_cls = true;
+}
+
+static void
+__qed_vf_update_tunn_param(struct qed_tunn_update_type *p_tun,
+			   u16 feature_mask, u8 tunn_mode,
+			   u8 tunn_cls, enum qed_tunn_mode val)
+{
+	if (feature_mask & BIT(val)) {
+		p_tun->b_mode_enabled = tunn_mode;
+		p_tun->tun_cls = tunn_cls;
+	} else {
+		p_tun->b_mode_enabled = false;
+	}
+}
+
+static void qed_vf_update_tunn_param(struct qed_hwfn *p_hwfn,
+				     struct qed_tunnel_info *p_tun,
+				     struct pfvf_update_tunn_param_tlv *p_resp)
+{
+	/* Update mode and classes provided by PF */
+	u16 feat_mask = p_resp->tunn_feature_mask;
+
+	__qed_vf_update_tunn_param(&p_tun->vxlan, feat_mask,
+				   p_resp->vxlan_mode, p_resp->vxlan_clss,
+				   QED_MODE_VXLAN_TUNN);
+	__qed_vf_update_tunn_param(&p_tun->l2_geneve, feat_mask,
+				   p_resp->l2geneve_mode,
+				   p_resp->l2geneve_clss,
+				   QED_MODE_L2GENEVE_TUNN);
+	__qed_vf_update_tunn_param(&p_tun->ip_geneve, feat_mask,
+				   p_resp->ipgeneve_mode,
+				   p_resp->ipgeneve_clss,
+				   QED_MODE_IPGENEVE_TUNN);
+	__qed_vf_update_tunn_param(&p_tun->l2_gre, feat_mask,
+				   p_resp->l2gre_mode, p_resp->l2gre_clss,
+				   QED_MODE_L2GRE_TUNN);
+	__qed_vf_update_tunn_param(&p_tun->ip_gre, feat_mask,
+				   p_resp->ipgre_mode, p_resp->ipgre_clss,
+				   QED_MODE_IPGRE_TUNN);
+	p_tun->geneve_port.port = p_resp->geneve_udp_port;
+	p_tun->vxlan_port.port = p_resp->vxlan_udp_port;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "tunn mode: vxlan=0x%x, l2geneve=0x%x, ipgeneve=0x%x, l2gre=0x%x, ipgre=0x%x",
+		   p_tun->vxlan.b_mode_enabled, p_tun->l2_geneve.b_mode_enabled,
+		   p_tun->ip_geneve.b_mode_enabled,
+		   p_tun->l2_gre.b_mode_enabled, p_tun->ip_gre.b_mode_enabled);
+}
+
+int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn,
+				  struct qed_tunnel_info *p_src)
+{
+	struct qed_tunnel_info *p_tun = &p_hwfn->cdev->tunnel;
+	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
+	struct pfvf_update_tunn_param_tlv *p_resp;
+	struct vfpf_update_tunn_param_tlv *p_req;
+	int rc;
+
+	p_req = qed_vf_pf_prep(p_hwfn, CHANNEL_TLV_UPDATE_TUNN_PARAM,
+			       sizeof(*p_req));
+
+	if (p_src->b_update_rx_cls && p_src->b_update_tx_cls)
+		p_req->update_tun_cls = 1;
+
+	qed_vf_prep_tunn_req_tlv(p_req, &p_src->vxlan, QED_MODE_VXLAN_TUNN,
+				 &p_req->vxlan_clss, &p_src->vxlan_port,
+				 &p_req->update_vxlan_port,
+				 &p_req->vxlan_port);
+	qed_vf_prep_tunn_req_tlv(p_req, &p_src->l2_geneve,
+				 QED_MODE_L2GENEVE_TUNN,
+				 &p_req->l2geneve_clss, &p_src->geneve_port,
+				 &p_req->update_geneve_port,
+				 &p_req->geneve_port);
+	__qed_vf_prep_tunn_req_tlv(p_req, &p_src->ip_geneve,
+				   QED_MODE_IPGENEVE_TUNN,
+				   &p_req->ipgeneve_clss);
+	__qed_vf_prep_tunn_req_tlv(p_req, &p_src->l2_gre,
+				   QED_MODE_L2GRE_TUNN, &p_req->l2gre_clss);
+	__qed_vf_prep_tunn_req_tlv(p_req, &p_src->ip_gre,
+				   QED_MODE_IPGRE_TUNN, &p_req->ipgre_clss);
+
+	/* add list termination tlv */
+	qed_add_tlv(p_hwfn, &p_iov->offset,
+		    CHANNEL_TLV_LIST_END,
+		    sizeof(struct channel_list_end_tlv));
+
+	p_resp = &p_iov->pf2vf_reply->tunn_param_resp;
+	rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status, sizeof(*p_resp));
+
+	if (rc)
+		goto exit;
+
+	if (p_resp->hdr.status != PFVF_STATUS_SUCCESS) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Failed to update tunnel parameters\n");
+		rc = -EINVAL;
+	}
+
+	qed_vf_update_tunn_param(p_hwfn, p_tun, p_resp);
+exit:
+	qed_vf_pf_req_end(p_hwfn, rc);
+	return rc;
+}
+
 int
 qed_vf_pf_rxq_start(struct qed_hwfn *p_hwfn,
 		    struct qed_queue_cid *p_cid,
@@ -1245,6 +1400,18 @@ static bool qed_vf_bulletin_get_forced_mac(struct qed_hwfn *hwfn,
 	return true;
 }
 
+static void
+qed_vf_bulletin_get_udp_ports(struct qed_hwfn *p_hwfn,
+			      u16 *p_vxlan_port, u16 *p_geneve_port)
+{
+	struct qed_bulletin_content *p_bulletin;
+
+	p_bulletin = &p_hwfn->vf_iov_info->bulletin_shadow;
+
+	*p_vxlan_port = p_bulletin->vxlan_udp_port;
+	*p_geneve_port = p_bulletin->geneve_udp_port;
+}
+
 void qed_vf_get_fw_version(struct qed_hwfn *p_hwfn,
 			   u16 *fw_major, u16 *fw_minor,
 			   u16 *fw_rev, u16 *fw_eng)
@@ -1264,12 +1431,16 @@ static void qed_handle_bulletin_change(struct qed_hwfn *hwfn)
 	struct qed_eth_cb_ops *ops = hwfn->cdev->protocol_ops.eth;
 	u8 mac[ETH_ALEN], is_mac_exist, is_mac_forced;
 	void *cookie = hwfn->cdev->ops_cookie;
+	u16 vxlan_port, geneve_port;
 
+	qed_vf_bulletin_get_udp_ports(hwfn, &vxlan_port, &geneve_port);
 	is_mac_exist = qed_vf_bulletin_get_forced_mac(hwfn, mac,
 						      &is_mac_forced);
 	if (is_mac_exist && cookie)
 		ops->force_mac(cookie, mac, !!is_mac_forced);
 
+	ops->ports_update(cookie, vxlan_port, geneve_port);
+
 	/* Always update link configuration according to bulletin */
 	qed_link_update(hwfn);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 7da0b165d8bc..34ac70b0e5fe 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -275,6 +275,8 @@ struct vfpf_stop_rxqs_tlv {
 	struct vfpf_first_tlv first_tlv;
 
 	u16 rx_qid;
+
+	/* this field is deprecated and should *always* be set to '1' */
 	u8 num_rxqs;
 	u8 cqe_completion;
 	u8 padding[4];
@@ -285,6 +287,8 @@ struct vfpf_stop_txqs_tlv {
 	struct vfpf_first_tlv first_tlv;
 
 	u16 tx_qid;
+
+	/* this field is deprecated and should *always* be set to '1' */
 	u8 num_txqs;
 	u8 padding[5];
 };
@@ -425,6 +429,43 @@ struct vfpf_ucast_filter_tlv {
 	u16 padding[3];
 };
 
+/* tunnel update param tlv */
+struct vfpf_update_tunn_param_tlv {
+	struct vfpf_first_tlv first_tlv;
+
+	u8 tun_mode_update_mask;
+	u8 tunn_mode;
+	u8 update_tun_cls;
+	u8 vxlan_clss;
+	u8 l2gre_clss;
+	u8 ipgre_clss;
+	u8 l2geneve_clss;
+	u8 ipgeneve_clss;
+	u8 update_geneve_port;
+	u8 update_vxlan_port;
+	u16 geneve_port;
+	u16 vxlan_port;
+	u8 padding[2];
+};
+
+struct pfvf_update_tunn_param_tlv {
+	struct pfvf_tlv hdr;
+
+	u16 tunn_feature_mask;
+	u8 vxlan_mode;
+	u8 l2geneve_mode;
+	u8 ipgeneve_mode;
+	u8 l2gre_mode;
+	u8 ipgre_mode;
+	u8 vxlan_clss;
+	u8 l2gre_clss;
+	u8 ipgre_clss;
+	u8 l2geneve_clss;
+	u8 ipgeneve_clss;
+	u16 vxlan_udp_port;
+	u16 geneve_udp_port;
+};
+
 struct tlv_buffer_size {
 	u8 tlv_buffer[TLV_BUFFER_SIZE];
 };
@@ -440,6 +481,7 @@ union vfpf_tlvs {
 	struct vfpf_vport_start_tlv start_vport;
 	struct vfpf_vport_update_tlv vport_update;
 	struct vfpf_ucast_filter_tlv ucast_filter;
+	struct vfpf_update_tunn_param_tlv tunn_param_update;
 	struct channel_list_end_tlv list_end;
 	struct tlv_buffer_size tlv_buf_size;
 };
@@ -449,6 +491,7 @@ union pfvf_tlvs {
 	struct pfvf_acquire_resp_tlv acquire_resp;
 	struct tlv_buffer_size tlv_buf_size;
 	struct pfvf_start_queue_resp_tlv queue_start;
+	struct pfvf_update_tunn_param_tlv tunn_param_resp;
 };
 
 enum qed_bulletin_bit {
@@ -509,7 +552,9 @@ struct qed_bulletin_content {
 	u8 partner_rx_flow_ctrl_en;
 	u8 partner_adv_pause;
 	u8 sfp_tx_fault;
-	u8 padding4[6];
+	u16 vxlan_udp_port;
+	u16 geneve_udp_port;
+	u8 padding4[2];
 
 	u32 speed;
 	u32 partner_adv_speed;
@@ -551,6 +596,7 @@ enum {
 	CHANNEL_TLV_VPORT_UPDATE_RSS,
 	CHANNEL_TLV_VPORT_UPDATE_ACCEPT_ANY_VLAN,
 	CHANNEL_TLV_VPORT_UPDATE_SGE_TPA,
+	CHANNEL_TLV_UPDATE_TUNN_PARAM,
 	CHANNEL_TLV_MAX,
 
 	/* Required for iterating over vport-update tlvs.
@@ -868,6 +914,9 @@ void __qed_vf_get_link_caps(struct qed_hwfn *p_hwfn,
 			    struct qed_bulletin_content *p_bulletin);
 
 void qed_iov_vf_task(struct work_struct *work);
+void qed_vf_set_vf_start_tunn_update_param(struct qed_tunnel_info *p_tun);
+int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn,
+				  struct qed_tunnel_info *p_tunn);
 #else
 static inline void qed_vf_get_link_params(struct qed_hwfn *p_hwfn,
 					  struct qed_mcp_link_params *params)
@@ -1029,6 +1078,17 @@ __qed_vf_get_link_caps(struct qed_hwfn *p_hwfn,
 static inline void qed_iov_vf_task(struct work_struct *work)
 {
 }
+
+static inline void
+qed_vf_set_vf_start_tunn_update_param(struct qed_tunnel_info *p_tun)
+{
+}
+
+static inline int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn,
+						struct qed_tunnel_info *p_tunn)
+{
+	return -EINVAL;
+}
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index f2aaef2cfb86..9b4f08b6f9b9 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -41,6 +41,9 @@
 #include <linux/mutex.h>
 #include <linux/bpf.h>
 #include <linux/io.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
 #include <linux/qed/common_hsi.h>
 #include <linux/qed/eth_common.h>
 #include <linux/qed/qed_if.h>
@@ -50,7 +53,7 @@
 #define QEDE_MAJOR_VERSION		8
 #define QEDE_MINOR_VERSION		10
 #define QEDE_REVISION_VERSION		10
-#define QEDE_ENGINEERING_VERSION	20
+#define QEDE_ENGINEERING_VERSION	21
 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "."	\
 		__stringify(QEDE_MINOR_VERSION) "."		\
 		__stringify(QEDE_REVISION_VERSION) "."		\
@@ -58,7 +61,7 @@
 
 #define DRV_MODULE_SYM		qede
 
-struct qede_stats {
+struct qede_stats_common {
 	u64 no_buff_discards;
 	u64 packet_too_big_discard;
 	u64 ttl0_discard;
@@ -90,11 +93,6 @@ struct qede_stats {
 	u64 rx_256_to_511_byte_packets;
 	u64 rx_512_to_1023_byte_packets;
 	u64 rx_1024_to_1518_byte_packets;
-	u64 rx_1519_to_1522_byte_packets;
-	u64 rx_1519_to_2047_byte_packets;
-	u64 rx_2048_to_4095_byte_packets;
-	u64 rx_4096_to_9216_byte_packets;
-	u64 rx_9217_to_16383_byte_packets;
 	u64 rx_crc_errors;
 	u64 rx_mac_crtl_frames;
 	u64 rx_pause_frames;
@@ -111,17 +109,39 @@ struct qede_stats {
 	u64 tx_256_to_511_byte_packets;
 	u64 tx_512_to_1023_byte_packets;
 	u64 tx_1024_to_1518_byte_packets;
+	u64 tx_pause_frames;
+	u64 tx_pfc_frames;
+	u64 brb_truncates;
+	u64 brb_discards;
+	u64 tx_mac_ctrl_frames;
+};
+
+struct qede_stats_bb {
+	u64 rx_1519_to_1522_byte_packets;
+	u64 rx_1519_to_2047_byte_packets;
+	u64 rx_2048_to_4095_byte_packets;
+	u64 rx_4096_to_9216_byte_packets;
+	u64 rx_9217_to_16383_byte_packets;
 	u64 tx_1519_to_2047_byte_packets;
 	u64 tx_2048_to_4095_byte_packets;
 	u64 tx_4096_to_9216_byte_packets;
 	u64 tx_9217_to_16383_byte_packets;
-	u64 tx_pause_frames;
-	u64 tx_pfc_frames;
 	u64 tx_lpi_entry_count;
 	u64 tx_total_collisions;
-	u64 brb_truncates;
-	u64 brb_discards;
-	u64 tx_mac_ctrl_frames;
+};
+
+struct qede_stats_ah {
+	u64 rx_1519_to_max_byte_packets;
+	u64 tx_1519_to_max_byte_packets;
+};
+
+struct qede_stats {
+	struct qede_stats_common common;
+
+	union {
+		struct qede_stats_bb bb;
+		struct qede_stats_ah ah;
+	};
 };
 
 struct qede_vlan {
@@ -147,10 +167,11 @@ struct qede_dev {
 	u32				dp_module;
 	u8				dp_level;
 
-	u32 flags;
-#define QEDE_FLAG_IS_VF	BIT(0)
+	unsigned long flags;
+#define QEDE_FLAG_IS_VF			BIT(0)
 #define IS_VF(edev)	(!!((edev)->flags & QEDE_FLAG_IS_VF))
 #define QEDE_TX_TIMESTAMPING_EN		BIT(1)
+#define QEDE_FLAGS_PTP_TX_IN_PRORGESS	BIT(2)
 
 	const struct qed_eth_ops	*ops;
 	struct qede_ptp			*ptp;
@@ -158,6 +179,10 @@ struct qede_dev {
 	struct qed_dev_eth_info dev_info;
 #define QEDE_MAX_RSS_CNT(edev)	((edev)->dev_info.num_queues)
 #define QEDE_MAX_TSS_CNT(edev)	((edev)->dev_info.num_queues)
+#define QEDE_IS_BB(edev) \
+	((edev)->dev_info.common.dev_type == QED_DEV_TYPE_BB)
+#define QEDE_IS_AH(edev) \
+	((edev)->dev_info.common.dev_type == QED_DEV_TYPE_AH)
 
 	struct qede_fastpath		*fp_array;
 	u8				req_num_tx;
@@ -216,7 +241,10 @@ struct qede_dev {
 	u16				vxlan_dst_port;
 	u16				geneve_dst_port;
 
-	bool wol_enabled;
+#ifdef CONFIG_RFS_ACCEL
+	struct qede_arfs		*arfs;
+#endif
+	bool				wol_enabled;
 
 	struct qede_rdma_dev		rdma_info;
 
@@ -292,21 +320,24 @@ struct qede_rx_queue {
 	u8 data_direction;
 	u8 rxq_id;
 
+	/* Used once per each NAPI run */
+	u16 num_rx_buffers;
+
+	u16 rx_headroom;
+
 	u32 rx_buf_size;
 	u32 rx_buf_seg_size;
 
-	u64 rcv_pkts;
-
 	struct sw_rx_data *sw_rx_ring;
 	struct qed_chain rx_bd_ring;
 	struct qed_chain rx_comp_ring ____cacheline_aligned;
 
-	/* Used once per each NAPI run */
-	u16 num_rx_buffers;
-
 	/* GRO */
 	struct qede_agg_info tpa_info[ETH_TPA_MAX_AGGS_NUM];
 
+	/* Used once per each NAPI run */
+	u64 rcv_pkts;
+
 	u64 rx_hw_errors;
 	u64 rx_alloc_errors;
 	u64 rx_ip_frags;
@@ -328,6 +359,11 @@ struct sw_tx_bd {
 #define QEDE_TSO_SPLIT_BD		BIT(0)
 };
 
+struct sw_tx_xdp {
+	struct page *page;
+	dma_addr_t mapping;
+};
+
 struct qede_tx_queue {
 	u8 is_xdp;
 	bool is_legacy;
@@ -351,11 +387,11 @@ struct qede_tx_queue {
 #define QEDE_TXQ_IDX_TO_XDP(edev, idx)	((idx) + QEDE_MAX_TSS_CNT(edev))
 
 	/* Regular Tx requires skb + metadata for release purpose,
-	 * while XDP requires only the pages themselves.
+	 * while XDP requires the pages and the mapped address.
 	 */
 	union {
 		struct sw_tx_bd *skbs;
-		struct page **pages;
+		struct sw_tx_xdp *xdp;
 	} sw_tx_ring;
 
 	struct qed_chain tx_pbl;
@@ -407,8 +443,20 @@ struct qede_fastpath {
 #define QEDE_TUNN_CSUM_UNNECESSARY	BIT(2)
 
 #define QEDE_SP_RX_MODE			1
-#define QEDE_SP_VXLAN_PORT_CONFIG	2
-#define QEDE_SP_GENEVE_PORT_CONFIG	3
+
+#ifdef CONFIG_RFS_ACCEL
+int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+		       u16 rxq_index, u32 flow_id);
+void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr);
+void qede_poll_for_freeing_arfs_filters(struct qede_dev *edev);
+void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc);
+void qede_free_arfs(struct qede_dev *edev);
+int qede_alloc_arfs(struct qede_dev *edev);
+
+#define QEDE_SP_ARFS_CONFIG	4
+#define QEDE_SP_TASK_POLL_DELAY	(5 * HZ)
+#define QEDE_RFS_MAX_FLTR	256
+#endif
 
 struct qede_reload_args {
 	void (*func)(struct qede_dev *edev, struct qede_reload_args *args);
@@ -433,6 +481,7 @@ irqreturn_t qede_msix_fp_int(int irq, void *fp_cookie);
 
 /* Filtering function definitions */
 void qede_force_mac(void *dev, u8 *mac, bool forced);
+void qede_udp_ports_update(void *dev, u16 vxlan_port, u16 geneve_port);
 int qede_set_mac_addr(struct net_device *ndev, void *p);
 
 int qede_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
index 03e8c0212433..a9e7379313db 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
@@ -281,6 +281,11 @@ static int qede_dcbnl_ieee_setapp(struct net_device *netdev,
 				  struct dcb_app *app)
 {
 	struct qede_dev *edev = netdev_priv(netdev);
+	int err;
+
+	err = dcb_ieee_setapp(netdev, app);
+	if (err)
+		return err;
 
 	return edev->ops->dcb->ieee_setapp(edev->cdev, app);
 }
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 897953133245..4dcfe9614731 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -75,16 +75,33 @@ static const struct {
 	QEDE_TQSTAT(stopped_cnt),
 };
 
-#define QEDE_STAT_OFFSET(stat_name) (offsetof(struct qede_stats, stat_name))
-#define QEDE_STAT_STRING(stat_name) (#stat_name)
-#define _QEDE_STAT(stat_name, pf_only) \
-	 {QEDE_STAT_OFFSET(stat_name), QEDE_STAT_STRING(stat_name), pf_only}
-#define QEDE_PF_STAT(stat_name)	_QEDE_STAT(stat_name, true)
-#define QEDE_STAT(stat_name)	_QEDE_STAT(stat_name, false)
+#define QEDE_STAT_OFFSET(stat_name, type, base) \
+	(offsetof(type, stat_name) + (base))
+#define QEDE_STAT_STRING(stat_name)	(#stat_name)
+#define _QEDE_STAT(stat_name, type, base, attr) \
+	{QEDE_STAT_OFFSET(stat_name, type, base), \
+	 QEDE_STAT_STRING(stat_name), \
+	 attr}
+#define QEDE_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_common, 0, 0x0)
+#define QEDE_PF_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_common, 0, \
+		   BIT(QEDE_STAT_PF_ONLY))
+#define QEDE_PF_BB_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_bb, \
+		   offsetof(struct qede_stats, bb), \
+		   BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_BB_ONLY))
+#define QEDE_PF_AH_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_ah, \
+		   offsetof(struct qede_stats, ah), \
+		   BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_AH_ONLY))
 static const struct {
 	u64 offset;
 	char string[ETH_GSTRING_LEN];
-	bool pf_only;
+	unsigned long attr;
+#define QEDE_STAT_PF_ONLY	0
+#define QEDE_STAT_BB_ONLY	1
+#define QEDE_STAT_AH_ONLY	2
 } qede_stats_arr[] = {
 	QEDE_STAT(rx_ucast_bytes),
 	QEDE_STAT(rx_mcast_bytes),
@@ -106,22 +123,23 @@ static const struct {
 	QEDE_PF_STAT(rx_256_to_511_byte_packets),
 	QEDE_PF_STAT(rx_512_to_1023_byte_packets),
 	QEDE_PF_STAT(rx_1024_to_1518_byte_packets),
-	QEDE_PF_STAT(rx_1519_to_1522_byte_packets),
-	QEDE_PF_STAT(rx_1519_to_2047_byte_packets),
-	QEDE_PF_STAT(rx_2048_to_4095_byte_packets),
-	QEDE_PF_STAT(rx_4096_to_9216_byte_packets),
-	QEDE_PF_STAT(rx_9217_to_16383_byte_packets),
+	QEDE_PF_BB_STAT(rx_1519_to_1522_byte_packets),
+	QEDE_PF_BB_STAT(rx_1519_to_2047_byte_packets),
+	QEDE_PF_BB_STAT(rx_2048_to_4095_byte_packets),
+	QEDE_PF_BB_STAT(rx_4096_to_9216_byte_packets),
+	QEDE_PF_BB_STAT(rx_9217_to_16383_byte_packets),
+	QEDE_PF_AH_STAT(rx_1519_to_max_byte_packets),
 	QEDE_PF_STAT(tx_64_byte_packets),
 	QEDE_PF_STAT(tx_65_to_127_byte_packets),
 	QEDE_PF_STAT(tx_128_to_255_byte_packets),
 	QEDE_PF_STAT(tx_256_to_511_byte_packets),
 	QEDE_PF_STAT(tx_512_to_1023_byte_packets),
 	QEDE_PF_STAT(tx_1024_to_1518_byte_packets),
-	QEDE_PF_STAT(tx_1519_to_2047_byte_packets),
-	QEDE_PF_STAT(tx_2048_to_4095_byte_packets),
-	QEDE_PF_STAT(tx_4096_to_9216_byte_packets),
-	QEDE_PF_STAT(tx_9217_to_16383_byte_packets),
-
+	QEDE_PF_BB_STAT(tx_1519_to_2047_byte_packets),
+	QEDE_PF_BB_STAT(tx_2048_to_4095_byte_packets),
+	QEDE_PF_BB_STAT(tx_4096_to_9216_byte_packets),
+	QEDE_PF_BB_STAT(tx_9217_to_16383_byte_packets),
+	QEDE_PF_AH_STAT(tx_1519_to_max_byte_packets),
 	QEDE_PF_STAT(rx_mac_crtl_frames),
 	QEDE_PF_STAT(tx_mac_ctrl_frames),
 	QEDE_PF_STAT(rx_pause_frames),
@@ -136,8 +154,8 @@ static const struct {
 	QEDE_PF_STAT(rx_jabbers),
 	QEDE_PF_STAT(rx_undersize_packets),
 	QEDE_PF_STAT(rx_fragments),
-	QEDE_PF_STAT(tx_lpi_entry_count),
-	QEDE_PF_STAT(tx_total_collisions),
+	QEDE_PF_BB_STAT(tx_lpi_entry_count),
+	QEDE_PF_BB_STAT(tx_total_collisions),
 	QEDE_PF_STAT(brb_truncates),
 	QEDE_PF_STAT(brb_discards),
 	QEDE_STAT(no_buff_discards),
@@ -155,6 +173,12 @@ static const struct {
 };
 
 #define QEDE_NUM_STATS	ARRAY_SIZE(qede_stats_arr)
+#define QEDE_STAT_IS_PF_ONLY(i) \
+	test_bit(QEDE_STAT_PF_ONLY, &qede_stats_arr[i].attr)
+#define QEDE_STAT_IS_BB_ONLY(i) \
+	test_bit(QEDE_STAT_BB_ONLY, &qede_stats_arr[i].attr)
+#define QEDE_STAT_IS_AH_ONLY(i) \
+	test_bit(QEDE_STAT_AH_ONLY, &qede_stats_arr[i].attr)
 
 enum {
 	QEDE_PRI_FLAG_CMT,
@@ -213,6 +237,13 @@ static void qede_get_strings_stats_rxq(struct qede_dev *edev,
 	}
 }
 
+static bool qede_is_irrelevant_stat(struct qede_dev *edev, int stat_index)
+{
+	return (IS_VF(edev) && QEDE_STAT_IS_PF_ONLY(stat_index)) ||
+	       (QEDE_IS_BB(edev) && QEDE_STAT_IS_AH_ONLY(stat_index)) ||
+	       (QEDE_IS_AH(edev) && QEDE_STAT_IS_BB_ONLY(stat_index));
+}
+
 static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 {
 	struct qede_fastpath *fp;
@@ -234,7 +265,7 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 
 	/* Account for non-queue statistics */
 	for (i = 0; i < QEDE_NUM_STATS; i++) {
-		if (IS_VF(edev) && qede_stats_arr[i].pf_only)
+		if (qede_is_irrelevant_stat(edev, i))
 			continue;
 		strcpy(buf, qede_stats_arr[i].string);
 		buf += ETH_GSTRING_LEN;
@@ -309,7 +340,7 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 	}
 
 	for (i = 0; i < QEDE_NUM_STATS; i++) {
-		if (IS_VF(edev) && qede_stats_arr[i].pf_only)
+		if (qede_is_irrelevant_stat(edev, i))
 			continue;
 		*buf = *((u64 *)(((void *)&edev->stats) +
 				 qede_stats_arr[i].offset));
@@ -323,17 +354,13 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 static int qede_get_sset_count(struct net_device *dev, int stringset)
 {
 	struct qede_dev *edev = netdev_priv(dev);
-	int num_stats = QEDE_NUM_STATS;
+	int num_stats = QEDE_NUM_STATS, i;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		if (IS_VF(edev)) {
-			int i;
-
-			for (i = 0; i < QEDE_NUM_STATS; i++)
-				if (qede_stats_arr[i].pf_only)
-					num_stats--;
-		}
+		for (i = 0; i < QEDE_NUM_STATS; i++)
+			if (qede_is_irrelevant_stat(edev, i))
+				num_stats--;
 
 		/* Account for the Regular Tx statistics */
 		num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index 107c3fda4792..eb5652073ca8 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -38,6 +38,459 @@
 #include <linux/qed/qed_if.h>
 #include "qede.h"
 
+#ifdef CONFIG_RFS_ACCEL
+struct qede_arfs_tuple {
+	union {
+		__be32 src_ipv4;
+		struct in6_addr src_ipv6;
+	};
+	union {
+		__be32 dst_ipv4;
+		struct in6_addr dst_ipv6;
+	};
+	__be16  src_port;
+	__be16  dst_port;
+	__be16  eth_proto;
+	u8      ip_proto;
+};
+
+struct qede_arfs_fltr_node {
+#define QEDE_FLTR_VALID	 0
+	unsigned long state;
+
+	/* pointer to aRFS packet buffer */
+	void *data;
+
+	/* dma map address of aRFS packet buffer */
+	dma_addr_t mapping;
+
+	/* length of aRFS packet buffer */
+	int buf_len;
+
+	/* tuples to hold from aRFS packet buffer */
+	struct qede_arfs_tuple tuple;
+
+	u32 flow_id;
+	u16 sw_id;
+	u16 rxq_id;
+	u16 next_rxq_id;
+	bool filter_op;
+	bool used;
+	struct hlist_node node;
+};
+
+struct qede_arfs {
+#define QEDE_ARFS_POLL_COUNT	100
+#define QEDE_RFS_FLW_BITSHIFT	(4)
+#define QEDE_RFS_FLW_MASK	((1 << QEDE_RFS_FLW_BITSHIFT) - 1)
+	struct hlist_head	arfs_hl_head[1 << QEDE_RFS_FLW_BITSHIFT];
+
+	/* lock for filter list access */
+	spinlock_t		arfs_list_lock;
+	unsigned long		*arfs_fltr_bmap;
+	int			filter_count;
+	bool			enable;
+};
+
+static void qede_configure_arfs_fltr(struct qede_dev *edev,
+				     struct qede_arfs_fltr_node *n,
+				     u16 rxq_id, bool add_fltr)
+{
+	const struct qed_eth_ops *op = edev->ops;
+
+	if (n->used)
+		return;
+
+	DP_VERBOSE(edev, NETIF_MSG_RX_STATUS,
+		   "%s arfs filter flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n",
+		   add_fltr ? "Adding" : "Deleting",
+		   n->flow_id, n->sw_id, ntohs(n->tuple.src_port),
+		   ntohs(n->tuple.dst_port), rxq_id);
+
+	n->used = true;
+	n->filter_op = add_fltr;
+	op->ntuple_filter_config(edev->cdev, n, n->mapping, n->buf_len, 0,
+				 rxq_id, add_fltr);
+}
+
+static void
+qede_free_arfs_filter(struct qede_dev *edev,  struct qede_arfs_fltr_node *fltr)
+{
+	kfree(fltr->data);
+	clear_bit(fltr->sw_id, edev->arfs->arfs_fltr_bmap);
+	kfree(fltr);
+}
+
+void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc)
+{
+	struct qede_arfs_fltr_node *fltr = filter;
+	struct qede_dev *edev = dev;
+
+	if (fw_rc) {
+		DP_NOTICE(edev,
+			  "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n",
+			  fw_rc, fltr->flow_id, fltr->sw_id,
+			  ntohs(fltr->tuple.src_port),
+			  ntohs(fltr->tuple.dst_port), fltr->rxq_id);
+
+		spin_lock_bh(&edev->arfs->arfs_list_lock);
+
+		fltr->used = false;
+		clear_bit(QEDE_FLTR_VALID, &fltr->state);
+
+		spin_unlock_bh(&edev->arfs->arfs_list_lock);
+		return;
+	}
+
+	spin_lock_bh(&edev->arfs->arfs_list_lock);
+
+	fltr->used = false;
+
+	if (fltr->filter_op) {
+		set_bit(QEDE_FLTR_VALID, &fltr->state);
+		if (fltr->rxq_id != fltr->next_rxq_id)
+			qede_configure_arfs_fltr(edev, fltr, fltr->rxq_id,
+						 false);
+	} else {
+		clear_bit(QEDE_FLTR_VALID, &fltr->state);
+		if (fltr->rxq_id != fltr->next_rxq_id) {
+			fltr->rxq_id = fltr->next_rxq_id;
+			qede_configure_arfs_fltr(edev, fltr,
+						 fltr->rxq_id, true);
+		}
+	}
+
+	spin_unlock_bh(&edev->arfs->arfs_list_lock);
+}
+
+/* Should be called while qede_lock is held */
+void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr)
+{
+	int i;
+
+	for (i = 0; i <= QEDE_RFS_FLW_MASK; i++) {
+		struct hlist_node *temp;
+		struct hlist_head *head;
+		struct qede_arfs_fltr_node *fltr;
+
+		head = &edev->arfs->arfs_hl_head[i];
+
+		hlist_for_each_entry_safe(fltr, temp, head, node) {
+			bool del = false;
+
+			if (edev->state != QEDE_STATE_OPEN)
+				del = true;
+
+			spin_lock_bh(&edev->arfs->arfs_list_lock);
+
+			if ((!test_bit(QEDE_FLTR_VALID, &fltr->state) &&
+			     !fltr->used) || free_fltr) {
+				hlist_del(&fltr->node);
+				dma_unmap_single(&edev->pdev->dev,
+						 fltr->mapping,
+						 fltr->buf_len, DMA_TO_DEVICE);
+				qede_free_arfs_filter(edev, fltr);
+				edev->arfs->filter_count--;
+			} else {
+				if ((rps_may_expire_flow(edev->ndev,
+							 fltr->rxq_id,
+							 fltr->flow_id,
+							 fltr->sw_id) || del) &&
+							 !free_fltr)
+					qede_configure_arfs_fltr(edev, fltr,
+								 fltr->rxq_id,
+								 false);
+			}
+
+			spin_unlock_bh(&edev->arfs->arfs_list_lock);
+		}
+	}
+
+	spin_lock_bh(&edev->arfs->arfs_list_lock);
+
+	if (!edev->arfs->filter_count) {
+		if (edev->arfs->enable) {
+			edev->arfs->enable = false;
+			edev->ops->configure_arfs_searcher(edev->cdev, false);
+		}
+	} else {
+		set_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags);
+		schedule_delayed_work(&edev->sp_task,
+				      QEDE_SP_TASK_POLL_DELAY);
+	}
+
+	spin_unlock_bh(&edev->arfs->arfs_list_lock);
+}
+
+/* This function waits until all aRFS filters get deleted and freed.
+ * On timeout it frees all filters forcefully.
+ */
+void qede_poll_for_freeing_arfs_filters(struct qede_dev *edev)
+{
+	int count = QEDE_ARFS_POLL_COUNT;
+
+	while (count) {
+		qede_process_arfs_filters(edev, false);
+
+		if (!edev->arfs->filter_count)
+			break;
+
+		msleep(100);
+		count--;
+	}
+
+	if (!count) {
+		DP_NOTICE(edev, "Timeout in polling for arfs filter free\n");
+
+		/* Something is terribly wrong, free forcefully */
+		qede_process_arfs_filters(edev, true);
+	}
+}
+
+int qede_alloc_arfs(struct qede_dev *edev)
+{
+	int i;
+
+	edev->arfs = vzalloc(sizeof(*edev->arfs));
+	if (!edev->arfs)
+		return -ENOMEM;
+
+	spin_lock_init(&edev->arfs->arfs_list_lock);
+
+	for (i = 0; i <= QEDE_RFS_FLW_MASK; i++)
+		INIT_HLIST_HEAD(&edev->arfs->arfs_hl_head[i]);
+
+	edev->ndev->rx_cpu_rmap = alloc_irq_cpu_rmap(QEDE_RSS_COUNT(edev));
+	if (!edev->ndev->rx_cpu_rmap) {
+		vfree(edev->arfs);
+		edev->arfs = NULL;
+		return -ENOMEM;
+	}
+
+	edev->arfs->arfs_fltr_bmap = vzalloc(BITS_TO_LONGS(QEDE_RFS_MAX_FLTR) *
+					     sizeof(long));
+	if (!edev->arfs->arfs_fltr_bmap) {
+		free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap);
+		edev->ndev->rx_cpu_rmap = NULL;
+		vfree(edev->arfs);
+		edev->arfs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void qede_free_arfs(struct qede_dev *edev)
+{
+	if (!edev->arfs)
+		return;
+
+	if (edev->ndev->rx_cpu_rmap)
+		free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap);
+
+	edev->ndev->rx_cpu_rmap = NULL;
+	vfree(edev->arfs->arfs_fltr_bmap);
+	edev->arfs->arfs_fltr_bmap = NULL;
+	vfree(edev->arfs);
+	edev->arfs = NULL;
+}
+
+static bool qede_compare_ip_addr(struct qede_arfs_fltr_node *tpos,
+				 const struct sk_buff *skb)
+{
+	if (skb->protocol == htons(ETH_P_IP)) {
+		if (tpos->tuple.src_ipv4 == ip_hdr(skb)->saddr &&
+		    tpos->tuple.dst_ipv4 == ip_hdr(skb)->daddr)
+			return true;
+		else
+			return false;
+	} else {
+		struct in6_addr *src = &tpos->tuple.src_ipv6;
+		u8 size = sizeof(struct in6_addr);
+
+		if (!memcmp(src, &ipv6_hdr(skb)->saddr, size) &&
+		    !memcmp(&tpos->tuple.dst_ipv6, &ipv6_hdr(skb)->daddr, size))
+			return true;
+		else
+			return false;
+	}
+}
+
+static struct qede_arfs_fltr_node *
+qede_arfs_htbl_key_search(struct hlist_head *h, const struct sk_buff *skb,
+			  __be16 src_port, __be16 dst_port, u8 ip_proto)
+{
+	struct qede_arfs_fltr_node *tpos;
+
+	hlist_for_each_entry(tpos, h, node)
+		if (tpos->tuple.ip_proto == ip_proto &&
+		    tpos->tuple.eth_proto == skb->protocol &&
+		    qede_compare_ip_addr(tpos, skb) &&
+		    tpos->tuple.src_port == src_port &&
+		    tpos->tuple.dst_port == dst_port)
+			return tpos;
+
+	return NULL;
+}
+
+static struct qede_arfs_fltr_node *
+qede_alloc_filter(struct qede_dev *edev, int min_hlen)
+{
+	struct qede_arfs_fltr_node *n;
+	int bit_id;
+
+	bit_id = find_first_zero_bit(edev->arfs->arfs_fltr_bmap,
+				     QEDE_RFS_MAX_FLTR);
+
+	if (bit_id >= QEDE_RFS_MAX_FLTR)
+		return NULL;
+
+	n = kzalloc(sizeof(*n), GFP_ATOMIC);
+	if (!n)
+		return NULL;
+
+	n->data = kzalloc(min_hlen, GFP_ATOMIC);
+	if (!n->data) {
+		kfree(n);
+		return NULL;
+	}
+
+	n->sw_id = (u16)bit_id;
+	set_bit(bit_id, edev->arfs->arfs_fltr_bmap);
+	return n;
+}
+
+int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+		       u16 rxq_index, u32 flow_id)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	struct qede_arfs_fltr_node *n;
+	int min_hlen, rc, tp_offset;
+	struct ethhdr *eth;
+	__be16 *ports;
+	u16 tbl_idx;
+	u8 ip_proto;
+
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
+	if (skb->protocol != htons(ETH_P_IP) &&
+	    skb->protocol != htons(ETH_P_IPV6))
+		return -EPROTONOSUPPORT;
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		ip_proto = ip_hdr(skb)->protocol;
+		tp_offset = sizeof(struct iphdr);
+	} else {
+		ip_proto = ipv6_hdr(skb)->nexthdr;
+		tp_offset = sizeof(struct ipv6hdr);
+	}
+
+	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP)
+		return -EPROTONOSUPPORT;
+
+	ports = (__be16 *)(skb->data + tp_offset);
+	tbl_idx = skb_get_hash_raw(skb) & QEDE_RFS_FLW_MASK;
+
+	spin_lock_bh(&edev->arfs->arfs_list_lock);
+
+	n = qede_arfs_htbl_key_search(&edev->arfs->arfs_hl_head[tbl_idx],
+				      skb, ports[0], ports[1], ip_proto);
+
+	if (n) {
+		/* Filter match */
+		n->next_rxq_id = rxq_index;
+
+		if (test_bit(QEDE_FLTR_VALID, &n->state)) {
+			if (n->rxq_id != rxq_index)
+				qede_configure_arfs_fltr(edev, n, n->rxq_id,
+							 false);
+		} else {
+			if (!n->used) {
+				n->rxq_id = rxq_index;
+				qede_configure_arfs_fltr(edev, n, n->rxq_id,
+							 true);
+			}
+		}
+
+		rc = n->sw_id;
+		goto ret_unlock;
+	}
+
+	min_hlen = ETH_HLEN + skb_headlen(skb);
+
+	n = qede_alloc_filter(edev, min_hlen);
+	if (!n) {
+		rc = -ENOMEM;
+		goto ret_unlock;
+	}
+
+	n->buf_len = min_hlen;
+	n->rxq_id = rxq_index;
+	n->next_rxq_id = rxq_index;
+	n->tuple.src_port = ports[0];
+	n->tuple.dst_port = ports[1];
+	n->flow_id = flow_id;
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		n->tuple.src_ipv4 = ip_hdr(skb)->saddr;
+		n->tuple.dst_ipv4 = ip_hdr(skb)->daddr;
+	} else {
+		memcpy(&n->tuple.src_ipv6, &ipv6_hdr(skb)->saddr,
+		       sizeof(struct in6_addr));
+		memcpy(&n->tuple.dst_ipv6, &ipv6_hdr(skb)->daddr,
+		       sizeof(struct in6_addr));
+	}
+
+	eth = (struct ethhdr *)n->data;
+	eth->h_proto = skb->protocol;
+	n->tuple.eth_proto = skb->protocol;
+	n->tuple.ip_proto = ip_proto;
+	memcpy(n->data + ETH_HLEN, skb->data, skb_headlen(skb));
+
+	n->mapping = dma_map_single(&edev->pdev->dev, n->data,
+				    n->buf_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&edev->pdev->dev, n->mapping)) {
+		DP_NOTICE(edev, "Failed to map DMA memory for arfs\n");
+		qede_free_arfs_filter(edev, n);
+		rc = -ENOMEM;
+		goto ret_unlock;
+	}
+
+	INIT_HLIST_NODE(&n->node);
+	hlist_add_head(&n->node, &edev->arfs->arfs_hl_head[tbl_idx]);
+	edev->arfs->filter_count++;
+
+	if (edev->arfs->filter_count == 1 && !edev->arfs->enable) {
+		edev->ops->configure_arfs_searcher(edev->cdev, true);
+		edev->arfs->enable = true;
+	}
+
+	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
+
+	spin_unlock_bh(&edev->arfs->arfs_list_lock);
+
+	set_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+	return n->sw_id;
+
+ret_unlock:
+	spin_unlock_bh(&edev->arfs->arfs_list_lock);
+	return rc;
+}
+#endif
+
+void qede_udp_ports_update(void *dev, u16 vxlan_port, u16 geneve_port)
+{
+	struct qede_dev *edev = dev;
+
+	if (edev->vxlan_dst_port != vxlan_port)
+		edev->vxlan_dst_port = 0;
+
+	if (edev->geneve_dst_port != geneve_port)
+		edev->geneve_dst_port = 0;
+}
+
 void qede_force_mac(void *dev, u8 *mac, bool forced)
 {
 	struct qede_dev *edev = dev;
@@ -441,69 +894,112 @@ int qede_set_features(struct net_device *dev, netdev_features_t features)
 void qede_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti)
 {
 	struct qede_dev *edev = netdev_priv(dev);
+	struct qed_tunn_params tunn_params;
 	u16 t_port = ntohs(ti->port);
+	int rc;
+
+	memset(&tunn_params, 0, sizeof(tunn_params));
 
 	switch (ti->type) {
 	case UDP_TUNNEL_TYPE_VXLAN:
+		if (!edev->dev_info.common.vxlan_enable)
+			return;
+
 		if (edev->vxlan_dst_port)
 			return;
 
-		edev->vxlan_dst_port = t_port;
+		tunn_params.update_vxlan_port = 1;
+		tunn_params.vxlan_port = t_port;
 
-		DP_VERBOSE(edev, QED_MSG_DEBUG, "Added vxlan port=%d\n",
-			   t_port);
+		__qede_lock(edev);
+		rc = edev->ops->tunn_config(edev->cdev, &tunn_params);
+		__qede_unlock(edev);
+
+		if (!rc) {
+			edev->vxlan_dst_port = t_port;
+			DP_VERBOSE(edev, QED_MSG_DEBUG, "Added vxlan port=%d\n",
+				   t_port);
+		} else {
+			DP_NOTICE(edev, "Failed to add vxlan UDP port=%d\n",
+				  t_port);
+		}
 
-		set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
+		if (!edev->dev_info.common.geneve_enable)
+			return;
+
 		if (edev->geneve_dst_port)
 			return;
 
-		edev->geneve_dst_port = t_port;
+		tunn_params.update_geneve_port = 1;
+		tunn_params.geneve_port = t_port;
+
+		__qede_lock(edev);
+		rc = edev->ops->tunn_config(edev->cdev, &tunn_params);
+		__qede_unlock(edev);
+
+		if (!rc) {
+			edev->geneve_dst_port = t_port;
+			DP_VERBOSE(edev, QED_MSG_DEBUG,
+				   "Added geneve port=%d\n", t_port);
+		} else {
+			DP_NOTICE(edev, "Failed to add geneve UDP port=%d\n",
+				  t_port);
+		}
 
-		DP_VERBOSE(edev, QED_MSG_DEBUG, "Added geneve port=%d\n",
-			   t_port);
-		set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
 		break;
 	default:
 		return;
 	}
-
-	schedule_delayed_work(&edev->sp_task, 0);
 }
 
-void qede_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti)
+void qede_udp_tunnel_del(struct net_device *dev,
+			 struct udp_tunnel_info *ti)
 {
 	struct qede_dev *edev = netdev_priv(dev);
+	struct qed_tunn_params tunn_params;
 	u16 t_port = ntohs(ti->port);
 
+	memset(&tunn_params, 0, sizeof(tunn_params));
+
 	switch (ti->type) {
 	case UDP_TUNNEL_TYPE_VXLAN:
 		if (t_port != edev->vxlan_dst_port)
 			return;
 
+		tunn_params.update_vxlan_port = 1;
+		tunn_params.vxlan_port = 0;
+
+		__qede_lock(edev);
+		edev->ops->tunn_config(edev->cdev, &tunn_params);
+		__qede_unlock(edev);
+
 		edev->vxlan_dst_port = 0;
 
 		DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted vxlan port=%d\n",
 			   t_port);
 
-		set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
 		if (t_port != edev->geneve_dst_port)
 			return;
 
+		tunn_params.update_geneve_port = 1;
+		tunn_params.geneve_port = 0;
+
+		__qede_lock(edev);
+		edev->ops->tunn_config(edev->cdev, &tunn_params);
+		__qede_unlock(edev);
+
 		edev->geneve_dst_port = 0;
 
 		DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted geneve port=%d\n",
 			   t_port);
-		set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
 		break;
 	default:
 		return;
 	}
-
-	schedule_delayed_work(&edev->sp_task, 0);
 }
 
 static void qede_xdp_reload_func(struct qede_dev *edev,
@@ -520,11 +1016,6 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog)
 {
 	struct qede_reload_args args;
 
-	if (prog && prog->xdp_adjust_head) {
-		DP_ERR(edev, "Does not support bpf_xdp_adjust_head()\n");
-		return -EOPNOTSUPP;
-	}
-
 	/* If we're called, there was already a bpf reference increment */
 	args.func = &qede_xdp_reload_func;
 	args.u.new_prog = prog;
@@ -537,6 +1028,11 @@ int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 
+	if (IS_VF(edev)) {
+		DP_NOTICE(edev, "VFs don't support XDP\n");
+		return -EOPNOTSUPP;
+	}
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 1e65038c8fc0..7b6f41d06245 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -87,7 +87,8 @@ int qede_alloc_rx_buffer(struct qede_rx_queue *rxq, bool allow_lazy)
 	rx_bd = (struct eth_rx_bd *)qed_chain_produce(&rxq->rx_bd_ring);
 	WARN_ON(!rx_bd);
 	rx_bd->addr.hi = cpu_to_le32(upper_32_bits(mapping));
-	rx_bd->addr.lo = cpu_to_le32(lower_32_bits(mapping));
+	rx_bd->addr.lo = cpu_to_le32(lower_32_bits(mapping) +
+				     rxq->rx_headroom);
 
 	rxq->sw_rx_prod++;
 	rxq->filled_buffers++;
@@ -360,7 +361,8 @@ static int qede_xdp_xmit(struct qede_dev *edev, struct qede_fastpath *fp,
 				   metadata->mapping + padding,
 				   length, PCI_DMA_TODEVICE);
 
-	txq->sw_tx_ring.pages[idx] = metadata->data;
+	txq->sw_tx_ring.xdp[idx].page = metadata->data;
+	txq->sw_tx_ring.xdp[idx].mapping = metadata->mapping;
 	txq->sw_tx_prod++;
 
 	/* Mark the fastpath for future XDP doorbell */
@@ -384,19 +386,19 @@ int qede_txq_has_work(struct qede_tx_queue *txq)
 
 static void qede_xdp_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
-	struct eth_tx_1st_bd *bd;
-	u16 hw_bd_cons;
+	u16 hw_bd_cons, idx;
 
 	hw_bd_cons = le16_to_cpu(*txq->hw_cons_ptr);
 	barrier();
 
 	while (hw_bd_cons != qed_chain_get_cons_idx(&txq->tx_pbl)) {
-		bd = (struct eth_tx_1st_bd *)qed_chain_consume(&txq->tx_pbl);
+		qed_chain_consume(&txq->tx_pbl);
+		idx = txq->sw_tx_cons & NUM_TX_BDS_MAX;
 
-		dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(bd),
-				 PAGE_SIZE, DMA_BIDIRECTIONAL);
-		__free_page(txq->sw_tx_ring.pages[txq->sw_tx_cons &
-						  NUM_TX_BDS_MAX]);
+		dma_unmap_page(&edev->pdev->dev,
+			       txq->sw_tx_ring.xdp[idx].mapping,
+			       PAGE_SIZE, DMA_BIDIRECTIONAL);
+		__free_page(txq->sw_tx_ring.xdp[idx].page);
 
 		txq->sw_tx_cons++;
 		txq->xmit_pkts++;
@@ -508,7 +510,8 @@ static inline void qede_reuse_page(struct qede_rx_queue *rxq,
 	new_mapping = curr_prod->mapping + curr_prod->page_offset;
 
 	rx_bd_prod->addr.hi = cpu_to_le32(upper_32_bits(new_mapping));
-	rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping));
+	rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping) +
+					  rxq->rx_headroom);
 
 	rxq->sw_rx_prod++;
 	curr_cons->data = NULL;
@@ -624,7 +627,6 @@ static inline void qede_skb_receive(struct qede_dev *edev,
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
 
 	napi_gro_receive(&fp->napi, skb);
-	rxq->rcv_pkts++;
 }
 
 static void qede_set_gro_params(struct qede_dev *edev,
@@ -884,9 +886,9 @@ static inline void qede_tpa_cont(struct qede_dev *edev,
 		       "Strange - TPA cont with more than a single len_list entry\n");
 }
 
-static void qede_tpa_end(struct qede_dev *edev,
-			 struct qede_fastpath *fp,
-			 struct eth_fast_path_rx_tpa_end_cqe *cqe)
+static int qede_tpa_end(struct qede_dev *edev,
+			struct qede_fastpath *fp,
+			struct eth_fast_path_rx_tpa_end_cqe *cqe)
 {
 	struct qede_rx_queue *rxq = fp->rxq;
 	struct qede_agg_info *tpa_info;
@@ -934,11 +936,12 @@ static void qede_tpa_end(struct qede_dev *edev,
 
 	tpa_info->state = QEDE_AGG_STATE_NONE;
 
-	return;
+	return 1;
 err:
 	tpa_info->state = QEDE_AGG_STATE_NONE;
 	dev_kfree_skb_any(tpa_info->skb);
 	tpa_info->skb = NULL;
+	return 0;
 }
 
 static u8 qede_check_notunn_csum(u16 flag)
@@ -990,14 +993,15 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 			struct qede_rx_queue *rxq,
 			struct bpf_prog *prog,
 			struct sw_rx_data *bd,
-			struct eth_fast_path_rx_reg_cqe *cqe)
+			struct eth_fast_path_rx_reg_cqe *cqe,
+			u16 *data_offset, u16 *len)
 {
-	u16 len = le16_to_cpu(cqe->len_on_first_bd);
 	struct xdp_buff xdp;
 	enum xdp_action act;
 
-	xdp.data = page_address(bd->data) + cqe->placement_offset;
-	xdp.data_end = xdp.data + len;
+	xdp.data_hard_start = page_address(bd->data);
+	xdp.data = xdp.data_hard_start + *data_offset;
+	xdp.data_end = xdp.data + *len;
 
 	/* Queues always have a full reset currently, so for the time
 	 * being until there's atomic program replace just mark read
@@ -1007,6 +1011,10 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 	act = bpf_prog_run_xdp(prog, &xdp);
 	rcu_read_unlock();
 
+	/* Recalculate, as XDP might have changed the headers */
+	*data_offset = xdp.data - xdp.data_hard_start;
+	*len = xdp.data_end - xdp.data;
+
 	if (act == XDP_PASS)
 		return true;
 
@@ -1025,7 +1033,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 		/* Now if there's a transmission problem, we'd still have to
 		 * throw current buffer, as replacement was already allocated.
 		 */
-		if (qede_xdp_xmit(edev, fp, bd, cqe->placement_offset, len)) {
+		if (qede_xdp_xmit(edev, fp, bd, *data_offset, *len)) {
 			dma_unmap_page(rxq->dev, bd->mapping,
 				       PAGE_SIZE, DMA_BIDIRECTIONAL);
 			__free_page(bd->data);
@@ -1052,7 +1060,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
 					    struct sw_rx_data *bd, u16 len,
 					    u16 pad)
 {
-	unsigned int offset = bd->page_offset;
+	unsigned int offset = bd->page_offset + pad;
 	struct skb_frag_struct *frag;
 	struct page *page = bd->data;
 	unsigned int pull_len;
@@ -1069,7 +1077,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
 	 */
 	if (len + pad <= edev->rx_copybreak) {
 		memcpy(skb_put(skb, len),
-		       page_address(page) + pad + offset, len);
+		       page_address(page) + offset, len);
 		qede_reuse_page(rxq, bd);
 		goto out;
 	}
@@ -1077,7 +1085,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
 	frag = &skb_shinfo(skb)->frags[0];
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-			page, pad + offset, len, rxq->rx_buf_seg_size);
+			page, offset, len, rxq->rx_buf_seg_size);
 
 	va = skb_frag_address(frag);
 	pull_len = eth_get_headlen(va, QEDE_RX_HDR_SIZE);
@@ -1178,8 +1186,7 @@ static int qede_rx_process_tpa_cqe(struct qede_dev *edev,
 		qede_tpa_cont(edev, rxq, &cqe->fast_path_tpa_cont);
 		return 0;
 	case ETH_RX_CQE_TYPE_TPA_END:
-		qede_tpa_end(edev, fp, &cqe->fast_path_tpa_end);
-		return 1;
+		return qede_tpa_end(edev, fp, &cqe->fast_path_tpa_end);
 	default:
 		return 0;
 	}
@@ -1224,12 +1231,13 @@ static int qede_rx_process_cqe(struct qede_dev *edev,
 
 	fp_cqe = &cqe->fast_path_regular;
 	len = le16_to_cpu(fp_cqe->len_on_first_bd);
-	pad = fp_cqe->placement_offset;
+	pad = fp_cqe->placement_offset + rxq->rx_headroom;
 
 	/* Run eBPF program if one is attached */
 	if (xdp_prog)
-		if (!qede_rx_xdp(edev, fp, rxq, xdp_prog, bd, fp_cqe))
-			return 1;
+		if (!qede_rx_xdp(edev, fp, rxq, xdp_prog, bd, fp_cqe,
+				 &pad, &len))
+			return 0;
 
 	/* If this is an error packet then drop it */
 	flags = cqe->fast_path_regular.pars_flags.flags;
@@ -1290,8 +1298,8 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
 {
 	struct qede_rx_queue *rxq = fp->rxq;
 	struct qede_dev *edev = fp->edev;
+	int work_done = 0, rcv_pkts = 0;
 	u16 hw_comp_cons, sw_comp_cons;
-	int work_done = 0;
 
 	hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
 	sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
@@ -1305,12 +1313,14 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
 
 	/* Loop to complete all indicated BDs */
 	while ((sw_comp_cons != hw_comp_cons) && (work_done < budget)) {
-		qede_rx_process_cqe(edev, fp, rxq);
+		rcv_pkts += qede_rx_process_cqe(edev, fp, rxq);
 		qed_chain_recycle_consumed(&rxq->rx_comp_ring);
 		sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
 		work_done++;
 	}
 
+	rxq->rcv_pkts += rcv_pkts;
+
 	/* Allocate replacement buffers */
 	while (rxq->num_rx_buffers - rxq->filled_buffers)
 		if (qede_alloc_rx_buffer(rxq, false))
@@ -1687,13 +1697,24 @@ netdev_features_t qede_features_check(struct sk_buff *skb,
 		}
 
 		/* Disable offloads for geneve tunnels, as HW can't parse
-		 * the geneve header which has option length greater than 32B.
+		 * the geneve header which has option length greater than 32b
+		 * and disable offloads for the ports which are not offloaded.
 		 */
-		if ((l4_proto == IPPROTO_UDP) &&
-		    ((skb_inner_mac_header(skb) -
-		      skb_transport_header(skb)) > QEDE_MAX_TUN_HDR_LEN))
-			return features & ~(NETIF_F_CSUM_MASK |
-					    NETIF_F_GSO_MASK);
+		if (l4_proto == IPPROTO_UDP) {
+			struct qede_dev *edev = netdev_priv(dev);
+			u16 hdrlen, vxln_port, gnv_port;
+
+			hdrlen = QEDE_MAX_TUN_HDR_LEN;
+			vxln_port = edev->vxlan_dst_port;
+			gnv_port = edev->geneve_dst_port;
+
+			if ((skb_inner_mac_header(skb) -
+			     skb_transport_header(skb)) > hdrlen ||
+			     (ntohs(udp_hdr(skb)->dest) != vxln_port &&
+			      ntohs(udp_hdr(skb)->dest) != gnv_port))
+				return features & ~(NETIF_F_CSUM_MASK |
+						    NETIF_F_GSO_MASK);
+		}
 	}
 
 	return features;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 3a78c3f25157..b9ba23d71c61 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -84,6 +84,8 @@ static const struct qed_eth_ops *qed_ops;
 #define CHIP_NUM_57980S_50		0x1654
 #define CHIP_NUM_57980S_25		0x1656
 #define CHIP_NUM_57980S_IOV		0x1664
+#define CHIP_NUM_AH			0x8070
+#define CHIP_NUM_AH_IOV			0x8090
 
 #ifndef PCI_DEVICE_ID_NX2_57980E
 #define PCI_DEVICE_ID_57980S_40		CHIP_NUM_57980S_40
@@ -93,6 +95,9 @@ static const struct qed_eth_ops *qed_ops;
 #define PCI_DEVICE_ID_57980S_50		CHIP_NUM_57980S_50
 #define PCI_DEVICE_ID_57980S_25		CHIP_NUM_57980S_25
 #define PCI_DEVICE_ID_57980S_IOV	CHIP_NUM_57980S_IOV
+#define PCI_DEVICE_ID_AH		CHIP_NUM_AH
+#define PCI_DEVICE_ID_AH_IOV		CHIP_NUM_AH_IOV
+
 #endif
 
 enum qede_pci_private {
@@ -110,6 +115,10 @@ static const struct pci_device_id qede_pci_tbl[] = {
 #ifdef CONFIG_QED_SRIOV
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF},
 #endif
+	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH), QEDE_PRIVATE_PF},
+#ifdef CONFIG_QED_SRIOV
+	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH_IOV), QEDE_PRIVATE_VF},
+#endif
 	{ 0 }
 };
 
@@ -216,9 +225,13 @@ static struct pci_driver qede_pci_driver = {
 
 static struct qed_eth_cb_ops qede_ll_ops = {
 	{
+#ifdef CONFIG_RFS_ACCEL
+		.arfs_filter_op = qede_arfs_filter_op,
+#endif
 		.link_update = qede_link_update,
 	},
 	.force_mac = qede_force_mac,
+	.ports_update = qede_udp_ports_update,
 };
 
 static int qede_netdev_event(struct notifier_block *this, unsigned long event,
@@ -314,122 +327,135 @@ static int qede_close(struct net_device *ndev);
 
 void qede_fill_by_demand_stats(struct qede_dev *edev)
 {
+	struct qede_stats_common *p_common = &edev->stats.common;
 	struct qed_eth_stats stats;
 
 	edev->ops->get_vport_stats(edev->cdev, &stats);
-	edev->stats.no_buff_discards = stats.no_buff_discards;
-	edev->stats.packet_too_big_discard = stats.packet_too_big_discard;
-	edev->stats.ttl0_discard = stats.ttl0_discard;
-	edev->stats.rx_ucast_bytes = stats.rx_ucast_bytes;
-	edev->stats.rx_mcast_bytes = stats.rx_mcast_bytes;
-	edev->stats.rx_bcast_bytes = stats.rx_bcast_bytes;
-	edev->stats.rx_ucast_pkts = stats.rx_ucast_pkts;
-	edev->stats.rx_mcast_pkts = stats.rx_mcast_pkts;
-	edev->stats.rx_bcast_pkts = stats.rx_bcast_pkts;
-	edev->stats.mftag_filter_discards = stats.mftag_filter_discards;
-	edev->stats.mac_filter_discards = stats.mac_filter_discards;
-
-	edev->stats.tx_ucast_bytes = stats.tx_ucast_bytes;
-	edev->stats.tx_mcast_bytes = stats.tx_mcast_bytes;
-	edev->stats.tx_bcast_bytes = stats.tx_bcast_bytes;
-	edev->stats.tx_ucast_pkts = stats.tx_ucast_pkts;
-	edev->stats.tx_mcast_pkts = stats.tx_mcast_pkts;
-	edev->stats.tx_bcast_pkts = stats.tx_bcast_pkts;
-	edev->stats.tx_err_drop_pkts = stats.tx_err_drop_pkts;
-	edev->stats.coalesced_pkts = stats.tpa_coalesced_pkts;
-	edev->stats.coalesced_events = stats.tpa_coalesced_events;
-	edev->stats.coalesced_aborts_num = stats.tpa_aborts_num;
-	edev->stats.non_coalesced_pkts = stats.tpa_not_coalesced_pkts;
-	edev->stats.coalesced_bytes = stats.tpa_coalesced_bytes;
-
-	edev->stats.rx_64_byte_packets = stats.rx_64_byte_packets;
-	edev->stats.rx_65_to_127_byte_packets = stats.rx_65_to_127_byte_packets;
-	edev->stats.rx_128_to_255_byte_packets =
-				stats.rx_128_to_255_byte_packets;
-	edev->stats.rx_256_to_511_byte_packets =
-				stats.rx_256_to_511_byte_packets;
-	edev->stats.rx_512_to_1023_byte_packets =
-				stats.rx_512_to_1023_byte_packets;
-	edev->stats.rx_1024_to_1518_byte_packets =
-				stats.rx_1024_to_1518_byte_packets;
-	edev->stats.rx_1519_to_1522_byte_packets =
-				stats.rx_1519_to_1522_byte_packets;
-	edev->stats.rx_1519_to_2047_byte_packets =
-				stats.rx_1519_to_2047_byte_packets;
-	edev->stats.rx_2048_to_4095_byte_packets =
-				stats.rx_2048_to_4095_byte_packets;
-	edev->stats.rx_4096_to_9216_byte_packets =
-				stats.rx_4096_to_9216_byte_packets;
-	edev->stats.rx_9217_to_16383_byte_packets =
-				stats.rx_9217_to_16383_byte_packets;
-	edev->stats.rx_crc_errors = stats.rx_crc_errors;
-	edev->stats.rx_mac_crtl_frames = stats.rx_mac_crtl_frames;
-	edev->stats.rx_pause_frames = stats.rx_pause_frames;
-	edev->stats.rx_pfc_frames = stats.rx_pfc_frames;
-	edev->stats.rx_align_errors = stats.rx_align_errors;
-	edev->stats.rx_carrier_errors = stats.rx_carrier_errors;
-	edev->stats.rx_oversize_packets = stats.rx_oversize_packets;
-	edev->stats.rx_jabbers = stats.rx_jabbers;
-	edev->stats.rx_undersize_packets = stats.rx_undersize_packets;
-	edev->stats.rx_fragments = stats.rx_fragments;
-	edev->stats.tx_64_byte_packets = stats.tx_64_byte_packets;
-	edev->stats.tx_65_to_127_byte_packets = stats.tx_65_to_127_byte_packets;
-	edev->stats.tx_128_to_255_byte_packets =
-				stats.tx_128_to_255_byte_packets;
-	edev->stats.tx_256_to_511_byte_packets =
-				stats.tx_256_to_511_byte_packets;
-	edev->stats.tx_512_to_1023_byte_packets =
-				stats.tx_512_to_1023_byte_packets;
-	edev->stats.tx_1024_to_1518_byte_packets =
-				stats.tx_1024_to_1518_byte_packets;
-	edev->stats.tx_1519_to_2047_byte_packets =
-				stats.tx_1519_to_2047_byte_packets;
-	edev->stats.tx_2048_to_4095_byte_packets =
-				stats.tx_2048_to_4095_byte_packets;
-	edev->stats.tx_4096_to_9216_byte_packets =
-				stats.tx_4096_to_9216_byte_packets;
-	edev->stats.tx_9217_to_16383_byte_packets =
-				stats.tx_9217_to_16383_byte_packets;
-	edev->stats.tx_pause_frames = stats.tx_pause_frames;
-	edev->stats.tx_pfc_frames = stats.tx_pfc_frames;
-	edev->stats.tx_lpi_entry_count = stats.tx_lpi_entry_count;
-	edev->stats.tx_total_collisions = stats.tx_total_collisions;
-	edev->stats.brb_truncates = stats.brb_truncates;
-	edev->stats.brb_discards = stats.brb_discards;
-	edev->stats.tx_mac_ctrl_frames = stats.tx_mac_ctrl_frames;
+
+	p_common->no_buff_discards = stats.common.no_buff_discards;
+	p_common->packet_too_big_discard = stats.common.packet_too_big_discard;
+	p_common->ttl0_discard = stats.common.ttl0_discard;
+	p_common->rx_ucast_bytes = stats.common.rx_ucast_bytes;
+	p_common->rx_mcast_bytes = stats.common.rx_mcast_bytes;
+	p_common->rx_bcast_bytes = stats.common.rx_bcast_bytes;
+	p_common->rx_ucast_pkts = stats.common.rx_ucast_pkts;
+	p_common->rx_mcast_pkts = stats.common.rx_mcast_pkts;
+	p_common->rx_bcast_pkts = stats.common.rx_bcast_pkts;
+	p_common->mftag_filter_discards = stats.common.mftag_filter_discards;
+	p_common->mac_filter_discards = stats.common.mac_filter_discards;
+
+	p_common->tx_ucast_bytes = stats.common.tx_ucast_bytes;
+	p_common->tx_mcast_bytes = stats.common.tx_mcast_bytes;
+	p_common->tx_bcast_bytes = stats.common.tx_bcast_bytes;
+	p_common->tx_ucast_pkts = stats.common.tx_ucast_pkts;
+	p_common->tx_mcast_pkts = stats.common.tx_mcast_pkts;
+	p_common->tx_bcast_pkts = stats.common.tx_bcast_pkts;
+	p_common->tx_err_drop_pkts = stats.common.tx_err_drop_pkts;
+	p_common->coalesced_pkts = stats.common.tpa_coalesced_pkts;
+	p_common->coalesced_events = stats.common.tpa_coalesced_events;
+	p_common->coalesced_aborts_num = stats.common.tpa_aborts_num;
+	p_common->non_coalesced_pkts = stats.common.tpa_not_coalesced_pkts;
+	p_common->coalesced_bytes = stats.common.tpa_coalesced_bytes;
+
+	p_common->rx_64_byte_packets = stats.common.rx_64_byte_packets;
+	p_common->rx_65_to_127_byte_packets =
+	    stats.common.rx_65_to_127_byte_packets;
+	p_common->rx_128_to_255_byte_packets =
+	    stats.common.rx_128_to_255_byte_packets;
+	p_common->rx_256_to_511_byte_packets =
+	    stats.common.rx_256_to_511_byte_packets;
+	p_common->rx_512_to_1023_byte_packets =
+	    stats.common.rx_512_to_1023_byte_packets;
+	p_common->rx_1024_to_1518_byte_packets =
+	    stats.common.rx_1024_to_1518_byte_packets;
+	p_common->rx_crc_errors = stats.common.rx_crc_errors;
+	p_common->rx_mac_crtl_frames = stats.common.rx_mac_crtl_frames;
+	p_common->rx_pause_frames = stats.common.rx_pause_frames;
+	p_common->rx_pfc_frames = stats.common.rx_pfc_frames;
+	p_common->rx_align_errors = stats.common.rx_align_errors;
+	p_common->rx_carrier_errors = stats.common.rx_carrier_errors;
+	p_common->rx_oversize_packets = stats.common.rx_oversize_packets;
+	p_common->rx_jabbers = stats.common.rx_jabbers;
+	p_common->rx_undersize_packets = stats.common.rx_undersize_packets;
+	p_common->rx_fragments = stats.common.rx_fragments;
+	p_common->tx_64_byte_packets = stats.common.tx_64_byte_packets;
+	p_common->tx_65_to_127_byte_packets =
+	    stats.common.tx_65_to_127_byte_packets;
+	p_common->tx_128_to_255_byte_packets =
+	    stats.common.tx_128_to_255_byte_packets;
+	p_common->tx_256_to_511_byte_packets =
+	    stats.common.tx_256_to_511_byte_packets;
+	p_common->tx_512_to_1023_byte_packets =
+	    stats.common.tx_512_to_1023_byte_packets;
+	p_common->tx_1024_to_1518_byte_packets =
+	    stats.common.tx_1024_to_1518_byte_packets;
+	p_common->tx_pause_frames = stats.common.tx_pause_frames;
+	p_common->tx_pfc_frames = stats.common.tx_pfc_frames;
+	p_common->brb_truncates = stats.common.brb_truncates;
+	p_common->brb_discards = stats.common.brb_discards;
+	p_common->tx_mac_ctrl_frames = stats.common.tx_mac_ctrl_frames;
+
+	if (QEDE_IS_BB(edev)) {
+		struct qede_stats_bb *p_bb = &edev->stats.bb;
+
+		p_bb->rx_1519_to_1522_byte_packets =
+		    stats.bb.rx_1519_to_1522_byte_packets;
+		p_bb->rx_1519_to_2047_byte_packets =
+		    stats.bb.rx_1519_to_2047_byte_packets;
+		p_bb->rx_2048_to_4095_byte_packets =
+		    stats.bb.rx_2048_to_4095_byte_packets;
+		p_bb->rx_4096_to_9216_byte_packets =
+		    stats.bb.rx_4096_to_9216_byte_packets;
+		p_bb->rx_9217_to_16383_byte_packets =
+		    stats.bb.rx_9217_to_16383_byte_packets;
+		p_bb->tx_1519_to_2047_byte_packets =
+		    stats.bb.tx_1519_to_2047_byte_packets;
+		p_bb->tx_2048_to_4095_byte_packets =
+		    stats.bb.tx_2048_to_4095_byte_packets;
+		p_bb->tx_4096_to_9216_byte_packets =
+		    stats.bb.tx_4096_to_9216_byte_packets;
+		p_bb->tx_9217_to_16383_byte_packets =
+		    stats.bb.tx_9217_to_16383_byte_packets;
+		p_bb->tx_lpi_entry_count = stats.bb.tx_lpi_entry_count;
+		p_bb->tx_total_collisions = stats.bb.tx_total_collisions;
+	} else {
+		struct qede_stats_ah *p_ah = &edev->stats.ah;
+
+		p_ah->rx_1519_to_max_byte_packets =
+		    stats.ah.rx_1519_to_max_byte_packets;
+		p_ah->tx_1519_to_max_byte_packets =
+		    stats.ah.tx_1519_to_max_byte_packets;
+	}
 }
 
 static void qede_get_stats64(struct net_device *dev,
 			     struct rtnl_link_stats64 *stats)
 {
 	struct qede_dev *edev = netdev_priv(dev);
+	struct qede_stats_common *p_common;
 
 	qede_fill_by_demand_stats(edev);
+	p_common = &edev->stats.common;
 
-	stats->rx_packets = edev->stats.rx_ucast_pkts +
-			    edev->stats.rx_mcast_pkts +
-			    edev->stats.rx_bcast_pkts;
-	stats->tx_packets = edev->stats.tx_ucast_pkts +
-			    edev->stats.tx_mcast_pkts +
-			    edev->stats.tx_bcast_pkts;
-
-	stats->rx_bytes = edev->stats.rx_ucast_bytes +
-			  edev->stats.rx_mcast_bytes +
-			  edev->stats.rx_bcast_bytes;
+	stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts +
+			    p_common->rx_bcast_pkts;
+	stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts +
+			    p_common->tx_bcast_pkts;
 
-	stats->tx_bytes = edev->stats.tx_ucast_bytes +
-			  edev->stats.tx_mcast_bytes +
-			  edev->stats.tx_bcast_bytes;
+	stats->rx_bytes = p_common->rx_ucast_bytes + p_common->rx_mcast_bytes +
+			  p_common->rx_bcast_bytes;
+	stats->tx_bytes = p_common->tx_ucast_bytes + p_common->tx_mcast_bytes +
+			  p_common->tx_bcast_bytes;
 
-	stats->tx_errors = edev->stats.tx_err_drop_pkts;
-	stats->multicast = edev->stats.rx_mcast_pkts +
-			   edev->stats.rx_bcast_pkts;
+	stats->tx_errors = p_common->tx_err_drop_pkts;
+	stats->multicast = p_common->rx_mcast_pkts + p_common->rx_bcast_pkts;
 
-	stats->rx_fifo_errors = edev->stats.no_buff_discards;
+	stats->rx_fifo_errors = p_common->no_buff_discards;
 
-	stats->collisions = edev->stats.tx_total_collisions;
-	stats->rx_crc_errors = edev->stats.rx_crc_errors;
-	stats->rx_frame_errors = edev->stats.rx_align_errors;
+	if (QEDE_IS_BB(edev))
+		stats->collisions = edev->stats.bb.tx_total_collisions;
+	stats->rx_crc_errors = p_common->rx_crc_errors;
+	stats->rx_frame_errors = p_common->rx_align_errors;
 }
 
 #ifdef CONFIG_QED_SRIOV
@@ -532,6 +558,9 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_udp_tunnel_del = qede_udp_tunnel_del,
 	.ndo_features_check = qede_features_check,
 	.ndo_xdp = qede_xdp,
+#ifdef CONFIG_RFS_ACCEL
+	.ndo_rx_flow_steer = qede_rx_flow_steer,
+#endif
 };
 
 /* -------------------------------------------------------------------------
@@ -581,7 +610,8 @@ static void qede_init_ndev(struct qede_dev *edev)
 {
 	struct net_device *ndev = edev->ndev;
 	struct pci_dev *pdev = edev->pdev;
-	u32 hw_features;
+	bool udp_tunnel_enable = false;
+	netdev_features_t hw_features;
 
 	pci_set_drvdata(pdev, ndev);
 
@@ -603,16 +633,33 @@ static void qede_init_ndev(struct qede_dev *edev)
 		      NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		      NETIF_F_TSO | NETIF_F_TSO6;
 
-	/* Encap features*/
-	hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL |
-		       NETIF_F_TSO_ECN | NETIF_F_GSO_UDP_TUNNEL_CSUM |
-		       NETIF_F_GSO_GRE_CSUM;
-	ndev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-				NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO_ECN |
-				NETIF_F_TSO6 | NETIF_F_GSO_GRE |
-				NETIF_F_GSO_UDP_TUNNEL | NETIF_F_RXCSUM |
-				NETIF_F_GSO_UDP_TUNNEL_CSUM |
-				NETIF_F_GSO_GRE_CSUM;
+	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1)
+		hw_features |= NETIF_F_NTUPLE;
+
+	if (edev->dev_info.common.vxlan_enable ||
+	    edev->dev_info.common.geneve_enable)
+		udp_tunnel_enable = true;
+
+	if (udp_tunnel_enable || edev->dev_info.common.gre_enable) {
+		hw_features |= NETIF_F_TSO_ECN;
+		ndev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+					NETIF_F_SG | NETIF_F_TSO |
+					NETIF_F_TSO_ECN | NETIF_F_TSO6 |
+					NETIF_F_RXCSUM;
+	}
+
+	if (udp_tunnel_enable) {
+		hw_features |= (NETIF_F_GSO_UDP_TUNNEL |
+				NETIF_F_GSO_UDP_TUNNEL_CSUM);
+		ndev->hw_enc_features |= (NETIF_F_GSO_UDP_TUNNEL |
+					  NETIF_F_GSO_UDP_TUNNEL_CSUM);
+	}
+
+	if (edev->dev_info.common.gre_enable) {
+		hw_features |= (NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM);
+		ndev->hw_enc_features |= (NETIF_F_GSO_GRE |
+					  NETIF_F_GSO_GRE_CSUM);
+	}
 
 	ndev->vlan_features = hw_features | NETIF_F_RXHASH | NETIF_F_RXCSUM |
 			      NETIF_F_HIGHDMA;
@@ -750,7 +797,6 @@ static void qede_sp_task(struct work_struct *work)
 {
 	struct qede_dev *edev = container_of(work, struct qede_dev,
 					     sp_task.work);
-	struct qed_dev *cdev = edev->cdev;
 
 	__qede_lock(edev);
 
@@ -758,24 +804,12 @@ static void qede_sp_task(struct work_struct *work)
 		if (edev->state == QEDE_STATE_OPEN)
 			qede_config_rx_mode(edev->ndev);
 
-	if (test_and_clear_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags)) {
-		struct qed_tunn_params tunn_params;
-
-		memset(&tunn_params, 0, sizeof(tunn_params));
-		tunn_params.update_vxlan_port = 1;
-		tunn_params.vxlan_port = edev->vxlan_dst_port;
-		qed_ops->tunn_config(cdev, &tunn_params);
-	}
-
-	if (test_and_clear_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags)) {
-		struct qed_tunn_params tunn_params;
-
-		memset(&tunn_params, 0, sizeof(tunn_params));
-		tunn_params.update_geneve_port = 1;
-		tunn_params.geneve_port = edev->geneve_dst_port;
-		qed_ops->tunn_config(cdev, &tunn_params);
+#ifdef CONFIG_RFS_ACCEL
+	if (test_and_clear_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags)) {
+		if (edev->state == QEDE_STATE_OPEN)
+			qede_process_arfs_filters(edev, false);
 	}
-
+#endif
 	__qede_unlock(edev);
 }
 
@@ -786,6 +820,9 @@ static void qede_update_pf_params(struct qed_dev *cdev)
 	/* 64 rx + 64 tx + 64 XDP */
 	memset(&pf_params, 0, sizeof(struct qed_pf_params));
 	pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * 3;
+#ifdef CONFIG_RFS_ACCEL
+	pf_params.eth_pf_params.num_arfs_filters = QEDE_RFS_MAX_FLTR;
+#endif
 	qed_ops->common->update_pf_params(cdev, &pf_params);
 }
 
@@ -870,13 +907,8 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	edev->ops->common->set_id(cdev, edev->ndev->name, DRV_MODULE_VERSION);
 
 	/* PTP not supported on VFs */
-	if (!is_vf) {
-		rc = qede_ptp_register_phc(edev);
-		if (rc) {
-			DP_NOTICE(edev, "Cannot register PHC\n");
-			goto err5;
-		}
-	}
+	if (!is_vf)
+		qede_ptp_enable(edev, true);
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
@@ -891,8 +923,6 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 
 	return 0;
 
-err5:
-	unregister_netdev(edev->ndev);
 err4:
 	qede_roce_dev_remove(edev);
 err3:
@@ -940,11 +970,10 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
-	cancel_delayed_work_sync(&edev->sp_task);
-
 	unregister_netdev(ndev);
+	cancel_delayed_work_sync(&edev->sp_task);
 
-	qede_ptp_remove(edev);
+	qede_ptp_disable(edev);
 
 	qede_roce_dev_remove(edev);
 
@@ -1165,9 +1194,11 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 	rxq->num_rx_buffers = edev->q_num_rx_buffers;
 
 	rxq->rx_buf_size = NET_IP_ALIGN + ETH_OVERHEAD + edev->ndev->mtu;
+	rxq->rx_headroom = edev->xdp_prog ? XDP_PACKET_HEADROOM : 0;
 
-	if (rxq->rx_buf_size > PAGE_SIZE)
-		rxq->rx_buf_size = PAGE_SIZE;
+	/* Make sure that the headroom and  payload fit in a single page */
+	if (rxq->rx_buf_size + rxq->rx_headroom > PAGE_SIZE)
+		rxq->rx_buf_size = PAGE_SIZE - rxq->rx_headroom;
 
 	/* Segment size to spilt a page in multiple equal parts,
 	 * unless XDP is used in which case we'd use the entire page.
@@ -1229,7 +1260,7 @@ static void qede_free_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	/* Free the parallel SW ring */
 	if (txq->is_xdp)
-		kfree(txq->sw_tx_ring.pages);
+		kfree(txq->sw_tx_ring.xdp);
 	else
 		kfree(txq->sw_tx_ring.skbs);
 
@@ -1247,9 +1278,9 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 
 	/* Allocate the parallel driver ring for Tx buffers */
 	if (txq->is_xdp) {
-		size = sizeof(*txq->sw_tx_ring.pages) * TX_RING_SIZE;
-		txq->sw_tx_ring.pages = kzalloc(size, GFP_KERNEL);
-		if (!txq->sw_tx_ring.pages)
+		size = sizeof(*txq->sw_tx_ring.xdp) * TX_RING_SIZE;
+		txq->sw_tx_ring.xdp = kzalloc(size, GFP_KERNEL);
+		if (!txq->sw_tx_ring.xdp)
 			goto err;
 	} else {
 		size = sizeof(*txq->sw_tx_ring.skbs) * TX_RING_SIZE;
@@ -1466,6 +1497,18 @@ static int qede_req_msix_irqs(struct qede_dev *edev)
 	}
 
 	for (i = 0; i < QEDE_QUEUE_CNT(edev); i++) {
+#ifdef CONFIG_RFS_ACCEL
+		struct qede_fastpath *fp = &edev->fp_array[i];
+
+		if (edev->ndev->rx_cpu_rmap && (fp->type & QEDE_FASTPATH_RX)) {
+			rc = irq_cpu_rmap_add(edev->ndev->rx_cpu_rmap,
+					      edev->int_info.msix[i].vector);
+			if (rc) {
+				DP_ERR(edev, "Failed to add CPU rmap\n");
+				qede_free_arfs(edev);
+			}
+		}
+#endif
 		rc = request_irq(edev->int_info.msix[i].vector,
 				 qede_msix_fp_int, 0, edev->fp_array[i].name,
 				 &edev->fp_array[i]);
@@ -1827,8 +1870,6 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	qede_roce_dev_event_close(edev);
 	edev->state = QEDE_STATE_CLOSED;
 
-	qede_ptp_stop(edev);
-
 	/* Close OS Tx */
 	netif_tx_disable(edev->ndev);
 	netif_carrier_off(edev->ndev);
@@ -1847,7 +1888,12 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 
 	qede_vlan_mark_nonconfigured(edev);
 	edev->ops->fastpath_stop(edev->cdev);
-
+#ifdef CONFIG_RFS_ACCEL
+	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) {
+		qede_poll_for_freeing_arfs_filters(edev);
+		qede_free_arfs(edev);
+	}
+#endif
 	/* Release the interrupts */
 	qede_sync_free_irqs(edev);
 	edev->ops->common->set_fp_int(edev->cdev, 0);
@@ -1899,6 +1945,13 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	if (rc)
 		goto err2;
 
+#ifdef CONFIG_RFS_ACCEL
+	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) {
+		rc = qede_alloc_arfs(edev);
+		if (rc)
+			DP_NOTICE(edev, "aRFS memory allocation failed\n");
+	}
+#endif
 	qede_napi_add_enable(edev);
 	DP_INFO(edev, "Napi added and enabled\n");
 
@@ -1925,13 +1978,10 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 
 	qede_roce_dev_event_open(edev);
 
-	qede_ptp_start(edev, (mode == QEDE_LOAD_NORMAL));
-
 	edev->state = QEDE_STATE_OPEN;
 
 	DP_INFO(edev, "Ending successfully qede load\n");
 
-
 	goto out;
 err4:
 	qede_sync_free_irqs(edev);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 2e62dec09bd7..24f06e2ef43e 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -181,6 +181,7 @@ static void qede_ptp_task(struct work_struct *work)
 	skb_tstamp_tx(ptp->tx_skb, &shhwtstamps);
 	dev_kfree_skb_any(ptp->tx_skb);
 	ptp->tx_skb = NULL;
+	clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags);
 
 	DP_VERBOSE(edev, QED_MSG_DEBUG,
 		   "Tx timestamp, timestamp cycles = %llu, ns = %llu\n",
@@ -206,23 +207,10 @@ static u64 qede_ptp_read_cc(const struct cyclecounter *cc)
 	return phc_cycles;
 }
 
-static void qede_ptp_init_cc(struct qede_dev *edev)
-{
-	struct qede_ptp *ptp;
-
-	ptp = edev->ptp;
-	if (!ptp)
-		return;
-
-	memset(&ptp->cc, 0, sizeof(ptp->cc));
-	ptp->cc.read = qede_ptp_read_cc;
-	ptp->cc.mask = CYCLECOUNTER_MASK(64);
-	ptp->cc.shift = 0;
-	ptp->cc.mult = 1;
-}
-
 static int qede_ptp_cfg_filters(struct qede_dev *edev)
 {
+	enum qed_ptp_hwtstamp_tx_type tx_type = QED_PTP_HWTSTAMP_TX_ON;
+	enum qed_ptp_filter_type rx_filter = QED_PTP_FILTER_NONE;
 	struct qede_ptp *ptp = edev->ptp;
 
 	if (!ptp)
@@ -236,7 +224,12 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev)
 	switch (ptp->tx_type) {
 	case HWTSTAMP_TX_ON:
 		edev->flags |= QEDE_TX_TIMESTAMPING_EN;
-		ptp->ops->hwtstamp_tx_on(edev->cdev);
+		tx_type = QED_PTP_HWTSTAMP_TX_ON;
+		break;
+
+	case HWTSTAMP_TX_OFF:
+		edev->flags &= ~QEDE_TX_TIMESTAMPING_EN;
+		tx_type = QED_PTP_HWTSTAMP_TX_OFF;
 		break;
 
 	case HWTSTAMP_TX_ONESTEP_SYNC:
@@ -247,42 +240,57 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev)
 	spin_lock_bh(&ptp->lock);
 	switch (ptp->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
+		rx_filter = QED_PTP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
 		ptp->rx_filter = HWTSTAMP_FILTER_NONE;
+		rx_filter = QED_PTP_FILTER_ALL;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		rx_filter = QED_PTP_FILTER_V1_L4_EVENT;
+		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		/* Initialize PTP detection for UDP/IPv4 events */
-		ptp->ops->cfg_rx_filters(edev->cdev, QED_PTP_FILTER_IPV4);
+		rx_filter = QED_PTP_FILTER_V1_L4_GEN;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		rx_filter = QED_PTP_FILTER_V2_L4_EVENT;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		/* Initialize PTP detection for UDP/IPv4 or UDP/IPv6 events */
-		ptp->ops->cfg_rx_filters(edev->cdev, QED_PTP_FILTER_IPV4_IPV6);
+		rx_filter = QED_PTP_FILTER_V2_L4_GEN;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		rx_filter = QED_PTP_FILTER_V2_L2_EVENT;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
 		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		/* Initialize PTP detection L2 events */
-		ptp->ops->cfg_rx_filters(edev->cdev, QED_PTP_FILTER_L2);
+		rx_filter = QED_PTP_FILTER_V2_L2_GEN;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		rx_filter = QED_PTP_FILTER_V2_EVENT;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		/* Initialize PTP detection L2, UDP/IPv4 or UDP/IPv6 events */
-		ptp->ops->cfg_rx_filters(edev->cdev,
-					 QED_PTP_FILTER_L2_IPV4_IPV6);
+		rx_filter = QED_PTP_FILTER_V2_GEN;
 		break;
 	}
 
+	ptp->ops->cfg_filters(edev->cdev, rx_filter, tx_type);
+
 	spin_unlock_bh(&ptp->lock);
 
 	return 0;
@@ -324,61 +332,6 @@ int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *ifr)
 			    sizeof(config)) ? -EFAULT : 0;
 }
 
-/* Called during load, to initialize PTP-related stuff */
-static void qede_ptp_init(struct qede_dev *edev, bool init_tc)
-{
-	struct qede_ptp *ptp;
-	int rc;
-
-	ptp = edev->ptp;
-	if (!ptp)
-		return;
-
-	spin_lock_init(&ptp->lock);
-
-	/* Configure PTP in HW */
-	rc = ptp->ops->enable(edev->cdev);
-	if (rc) {
-		DP_ERR(edev, "Stopping PTP initialization\n");
-		return;
-	}
-
-	/* Init work queue for Tx timestamping */
-	INIT_WORK(&ptp->work, qede_ptp_task);
-
-	/* Init cyclecounter and timecounter. This is done only in the first
-	 * load. If done in every load, PTP application will fail when doing
-	 * unload / load (e.g. MTU change) while it is running.
-	 */
-	if (init_tc) {
-		qede_ptp_init_cc(edev);
-		timecounter_init(&ptp->tc, &ptp->cc,
-				 ktime_to_ns(ktime_get_real()));
-	}
-
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "PTP initialization is successful\n");
-}
-
-void qede_ptp_start(struct qede_dev *edev, bool init_tc)
-{
-	qede_ptp_init(edev, init_tc);
-	qede_ptp_cfg_filters(edev);
-}
-
-void qede_ptp_remove(struct qede_dev *edev)
-{
-	struct qede_ptp *ptp;
-
-	ptp = edev->ptp;
-	if (ptp && ptp->clock) {
-		ptp_clock_unregister(ptp->clock);
-		ptp->clock = NULL;
-	}
-
-	kfree(ptp);
-	edev->ptp = NULL;
-}
-
 int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info)
 {
 	struct qede_ptp *ptp = edev->ptp;
@@ -417,8 +370,7 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info)
 	return 0;
 }
 
-/* Called during unload, to stop PTP-related stuff */
-void qede_ptp_stop(struct qede_dev *edev)
+void qede_ptp_disable(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 
@@ -426,6 +378,11 @@ void qede_ptp_stop(struct qede_dev *edev)
 	if (!ptp)
 		return;
 
+	if (ptp->clock) {
+		ptp_clock_unregister(ptp->clock);
+		ptp->clock = NULL;
+	}
+
 	/* Cancel PTP work queue. Should be done after the Tx queues are
 	 * drained to prevent additional scheduling.
 	 */
@@ -439,11 +396,54 @@ void qede_ptp_stop(struct qede_dev *edev)
 	spin_lock_bh(&ptp->lock);
 	ptp->ops->disable(edev->cdev);
 	spin_unlock_bh(&ptp->lock);
+
+	kfree(ptp);
+	edev->ptp = NULL;
+}
+
+static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
+{
+	struct qede_ptp *ptp;
+	int rc;
+
+	ptp = edev->ptp;
+	if (!ptp)
+		return -EINVAL;
+
+	spin_lock_init(&ptp->lock);
+
+	/* Configure PTP in HW */
+	rc = ptp->ops->enable(edev->cdev);
+	if (rc) {
+		DP_INFO(edev, "PTP HW enable failed\n");
+		return rc;
+	}
+
+	/* Init work queue for Tx timestamping */
+	INIT_WORK(&ptp->work, qede_ptp_task);
+
+	/* Init cyclecounter and timecounter. This is done only in the first
+	 * load. If done in every load, PTP application will fail when doing
+	 * unload / load (e.g. MTU change) while it is running.
+	 */
+	if (init_tc) {
+		memset(&ptp->cc, 0, sizeof(ptp->cc));
+		ptp->cc.read = qede_ptp_read_cc;
+		ptp->cc.mask = CYCLECOUNTER_MASK(64);
+		ptp->cc.shift = 0;
+		ptp->cc.mult = 1;
+
+		timecounter_init(&ptp->tc, &ptp->cc,
+				 ktime_to_ns(ktime_get_real()));
+	}
+
+	return rc;
 }
 
-int qede_ptp_register_phc(struct qede_dev *edev)
+int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 {
 	struct qede_ptp *ptp;
+	int rc;
 
 	ptp = kzalloc(sizeof(*ptp), GFP_KERNEL);
 	if (!ptp) {
@@ -454,14 +454,19 @@ int qede_ptp_register_phc(struct qede_dev *edev)
 	ptp->edev = edev;
 	ptp->ops = edev->ops->ptp;
 	if (!ptp->ops) {
-		kfree(ptp);
-		edev->ptp = NULL;
-		DP_ERR(edev, "PTP clock registeration failed\n");
-		return -EIO;
+		DP_INFO(edev, "PTP enable failed\n");
+		rc = -EIO;
+		goto err1;
 	}
 
 	edev->ptp = ptp;
 
+	rc = qede_ptp_init(edev, init_tc);
+	if (rc)
+		goto err1;
+
+	qede_ptp_cfg_filters(edev);
+
 	/* Fill the ptp_clock_info struct and register PTP clock */
 	ptp->clock_info.owner = THIS_MODULE;
 	snprintf(ptp->clock_info.name, 16, "%s", edev->ndev->name);
@@ -478,13 +483,21 @@ int qede_ptp_register_phc(struct qede_dev *edev)
 
 	ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
-		ptp->clock = NULL;
-		kfree(ptp);
-		edev->ptp = NULL;
+		rc = -EINVAL;
 		DP_ERR(edev, "PTP clock registeration failed\n");
+		goto err2;
 	}
 
 	return 0;
+
+err2:
+	qede_ptp_disable(edev);
+	ptp->clock = NULL;
+err1:
+	kfree(ptp);
+	edev->ptp = NULL;
+
+	return rc;
 }
 
 void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb)
@@ -495,6 +508,9 @@ void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb)
 	if (!ptp)
 		return;
 
+	if (test_and_set_bit_lock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags))
+		return;
+
 	if (unlikely(!(edev->flags & QEDE_TX_TIMESTAMPING_EN))) {
 		DP_NOTICE(edev,
 			  "Tx timestamping was not enabled, this packet will not be timestamped\n");
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.h b/drivers/net/ethernet/qlogic/qede/qede_ptp.h
index f328f9bba53a..691a14c4b2c5 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.h
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.h
@@ -40,10 +40,8 @@
 void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb);
 void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb);
 int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req);
-void qede_ptp_start(struct qede_dev *edev, bool init_tc);
-void qede_ptp_stop(struct qede_dev *edev);
-void qede_ptp_remove(struct qede_dev *edev);
-int qede_ptp_register_phc(struct qede_dev *edev);
+void qede_ptp_disable(struct qede_dev *edev);
+int qede_ptp_enable(struct qede_dev *edev, bool init_tc);
 int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *ts);
 
 static inline void qede_ptp_record_rx_ts(struct qede_dev *edev,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index d7107055ec60..2f656f395f39 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -128,6 +128,8 @@ static int qlcnic_sriov_virtid_fn(struct qlcnic_adapter *adapter, int vf_id)
 		return 0;
 
 	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV);
+	if (!pos)
+		return 0;
 	pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &offset);
 	pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &stride);
 
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 6d31f92ef2b6..84ac50f92c9c 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -1162,8 +1162,8 @@ struct ob_mac_tso_iocb_rsp {
 struct ib_mac_iocb_rsp {
 	u8 opcode;		/* 0x20 */
 	u8 flags1;
-#define IB_MAC_IOCB_RSP_OI	0x01	/* Overide intr delay */
-#define IB_MAC_IOCB_RSP_I	0x02	/* Disble Intr Generation */
+#define IB_MAC_IOCB_RSP_OI	0x01	/* Override intr delay */
+#define IB_MAC_IOCB_RSP_I	0x02	/* Disable Intr Generation */
 #define IB_MAC_CSUM_ERR_MASK 0x1c	/* A mask to use for csum errs */
 #define IB_MAC_IOCB_RSP_TE	0x04	/* Checksum error */
 #define IB_MAC_IOCB_RSP_NU	0x08	/* No checksum rcvd */
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index e9e647072596..1188d420fe53 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -4686,7 +4686,8 @@ static int ql_init_device(struct pci_dev *pdev, struct net_device *ndev,
 	/*
 	 * Set up the operating parameters.
 	 */
-	qdev->workqueue = alloc_ordered_workqueue(ndev->name, WQ_MEM_RECLAIM);
+	qdev->workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+						  ndev->name);
 	INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
index f62c215be779..7116be485e61 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
@@ -26,6 +26,7 @@
 
 /* SGMII digital lane registers */
 #define EMAC_SGMII_LN_DRVR_CTRL0		0x000C
+#define EMAC_SGMII_LN_DRVR_CTRL1		0x0010
 #define EMAC_SGMII_LN_DRVR_TAP_EN		0x0018
 #define EMAC_SGMII_LN_TX_MARGINING		0x001C
 #define EMAC_SGMII_LN_TX_PRE			0x0020
@@ -48,6 +49,7 @@
 #define EMAC_SGMII_LN_RX_EN_SIGNAL		0x02AC
 #define EMAC_SGMII_LN_RX_MISC_CNTRL0		0x02B8
 #define EMAC_SGMII_LN_DRVR_LOGIC_CLKDIV		0x02C8
+#define EMAC_SGMII_LN_RX_RESECODE_OFFSET	0x02CC
 
 /* SGMII digital lane register values */
 #define UCDR_STEP_BY_TWO_MODE0			BIT(7)
@@ -73,6 +75,8 @@
 #define CML_GEAR_MODE(x)			(((x) & 7) << 3)
 #define CML2CMOS_IBOOST_MODE(x)			((x) & 7)
 
+#define RESCODE_OFFSET(x)			((x) & 0x1f)
+
 #define MIXER_LOADB_MODE(x)			(((x) & 0xf) << 2)
 #define MIXER_DATARATE_MODE(x)			((x) & 3)
 
@@ -159,6 +163,8 @@ static const struct emac_reg_write sgmii_laned[] = {
 	{EMAC_SGMII_LN_PARALLEL_RATE, PARALLEL_RATE_MODE0(1)},
 	{EMAC_SGMII_LN_TX_BAND_MODE, BAND_MODE0(1)},
 	{EMAC_SGMII_LN_RX_BAND, BAND_MODE0(2)},
+	{EMAC_SGMII_LN_DRVR_CTRL1, RESCODE_OFFSET(7)},
+	{EMAC_SGMII_LN_RX_RESECODE_OFFSET, RESCODE_OFFSET(9)},
 	{EMAC_SGMII_LN_LANE_MODE, LANE_MODE(26)},
 	{EMAC_SGMII_LN_RX_RCVR_PATH1_MODE0, CDR_PD_SEL_MODE0(2) |
 		EN_DLL_MODE0 | EN_IQ_DCC_MODE0 | EN_IQCAL_MODE0},
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index 040b28977ee7..18c184ee1f3c 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -13,6 +13,7 @@
 /* Qualcomm Technologies, Inc. EMAC SGMII Controller driver.
  */
 
+#include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/acpi.h>
 #include <linux/of_device.h>
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 672f6b696069..72233ab9474b 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -1406,27 +1406,29 @@ static int cp_get_sset_count (struct net_device *dev, int sset)
 	}
 }
 
-static int cp_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cp_get_link_ksettings(struct net_device *dev,
+				 struct ethtool_link_ksettings *cmd)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	int rc;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cp->lock, flags);
-	rc = mii_ethtool_gset(&cp->mii_if, cmd);
+	rc = mii_ethtool_get_link_ksettings(&cp->mii_if, cmd);
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	return rc;
 }
 
-static int cp_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cp_set_link_ksettings(struct net_device *dev,
+				 const struct ethtool_link_ksettings *cmd)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	int rc;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cp->lock, flags);
-	rc = mii_ethtool_sset(&cp->mii_if, cmd);
+	rc = mii_ethtool_set_link_ksettings(&cp->mii_if, cmd);
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	return rc;
@@ -1578,8 +1580,6 @@ static const struct ethtool_ops cp_ethtool_ops = {
 	.get_drvinfo		= cp_get_drvinfo,
 	.get_regs_len		= cp_get_regs_len,
 	.get_sset_count		= cp_get_sset_count,
-	.get_settings		= cp_get_settings,
-	.set_settings		= cp_set_settings,
 	.nway_reset		= cp_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_msglevel		= cp_get_msglevel,
@@ -1593,6 +1593,8 @@ static const struct ethtool_ops cp_ethtool_ops = {
 	.get_eeprom		= cp_get_eeprom,
 	.set_eeprom		= cp_set_eeprom,
 	.get_ringparam		= cp_get_ringparam,
+	.get_link_ksettings	= cp_get_link_ksettings,
+	.set_link_ksettings	= cp_set_link_ksettings,
 };
 
 static int cp_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 89631753e799..ca22f2898664 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2384,21 +2384,23 @@ static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 }
 
-static int rtl8139_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8139_get_link_ksettings(struct net_device *dev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
 	spin_lock_irq(&tp->lock);
-	mii_ethtool_gset(&tp->mii, cmd);
+	mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 	spin_unlock_irq(&tp->lock);
 	return 0;
 }
 
-static int rtl8139_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8139_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
 	int rc;
 	spin_lock_irq(&tp->lock);
-	rc = mii_ethtool_sset(&tp->mii, cmd);
+	rc = mii_ethtool_set_link_ksettings(&tp->mii, cmd);
 	spin_unlock_irq(&tp->lock);
 	return rc;
 }
@@ -2480,8 +2482,6 @@ static void rtl8139_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 
 static const struct ethtool_ops rtl8139_ethtool_ops = {
 	.get_drvinfo		= rtl8139_get_drvinfo,
-	.get_settings		= rtl8139_get_settings,
-	.set_settings		= rtl8139_set_settings,
 	.get_regs_len		= rtl8139_get_regs_len,
 	.get_regs		= rtl8139_get_regs,
 	.nway_reset		= rtl8139_nway_reset,
@@ -2493,6 +2493,8 @@ static const struct ethtool_ops rtl8139_ethtool_ops = {
 	.get_strings		= rtl8139_get_strings,
 	.get_sset_count		= rtl8139_get_sset_count,
 	.get_ethtool_stats	= rtl8139_get_ethtool_stats,
+	.get_link_ksettings	= rtl8139_get_link_ksettings,
+	.set_link_ksettings	= rtl8139_set_link_ksettings,
 };
 
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 81f18a833527..0a8f2817ea60 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -817,7 +817,8 @@ struct rtl8169_private {
 	} csi_ops;
 
 	int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
-	int (*get_settings)(struct net_device *, struct ethtool_cmd *);
+	int (*get_link_ksettings)(struct net_device *,
+				  struct ethtool_link_ksettings *);
 	void (*phy_reset_enable)(struct rtl8169_private *tp);
 	void (*hw_start)(struct net_device *);
 	unsigned int (*phy_reset_pending)(struct rtl8169_private *tp);
@@ -2115,41 +2116,49 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
 }
 
-static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8169_get_link_ksettings_tbi(struct net_device *dev,
+					  struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
 	u32 status;
+	u32 supported, advertising;
 
-	cmd->supported =
+	supported =
 		SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE;
-	cmd->port = PORT_FIBRE;
-	cmd->transceiver = XCVR_INTERNAL;
+	cmd->base.port = PORT_FIBRE;
 
 	status = RTL_R32(TBICSR);
-	cmd->advertising = (status & TBINwEnable) ?  ADVERTISED_Autoneg : 0;
-	cmd->autoneg = !!(status & TBINwEnable);
+	advertising = (status & TBINwEnable) ?  ADVERTISED_Autoneg : 0;
+	cmd->base.autoneg = !!(status & TBINwEnable);
 
-	ethtool_cmd_speed_set(cmd, SPEED_1000);
-	cmd->duplex = DUPLEX_FULL; /* Always set */
+	cmd->base.speed = SPEED_1000;
+	cmd->base.duplex = DUPLEX_FULL; /* Always set */
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int rtl8169_gset_xmii(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8169_get_link_ksettings_xmii(struct net_device *dev,
+					   struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	return mii_ethtool_gset(&tp->mii, cmd);
+	return mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 }
 
-static int rtl8169_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8169_get_link_ksettings(struct net_device *dev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	int rc;
 
 	rtl_lock_work(tp);
-	rc = tp->get_settings(dev, cmd);
+	rc = tp->get_link_ksettings(dev, cmd);
 	rtl_unlock_work(tp);
 
 	return rc;
@@ -2356,7 +2365,6 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_drvinfo		= rtl8169_get_drvinfo,
 	.get_regs_len		= rtl8169_get_regs_len,
 	.get_link		= ethtool_op_get_link,
-	.get_settings		= rtl8169_get_settings,
 	.set_settings		= rtl8169_set_settings,
 	.get_msglevel		= rtl8169_get_msglevel,
 	.set_msglevel		= rtl8169_set_msglevel,
@@ -2368,6 +2376,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.nway_reset		= rtl8169_nway_reset,
+	.get_link_ksettings	= rtl8169_get_link_ksettings,
 };
 
 static void rtl8169_get_mac_version(struct rtl8169_private *tp,
@@ -8351,14 +8360,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (rtl_tbi_enabled(tp)) {
 		tp->set_speed = rtl8169_set_speed_tbi;
-		tp->get_settings = rtl8169_gset_tbi;
+		tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi;
 		tp->phy_reset_enable = rtl8169_tbi_reset_enable;
 		tp->phy_reset_pending = rtl8169_tbi_reset_pending;
 		tp->link_ok = rtl8169_tbi_link_ok;
 		tp->do_ioctl = rtl_tbi_ioctl;
 	} else {
 		tp->set_speed = rtl8169_set_speed_xmii;
-		tp->get_settings = rtl8169_gset_xmii;
+		tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii;
 		tp->phy_reset_enable = rtl8169_xmii_reset_enable;
 		tp->phy_reset_pending = rtl8169_xmii_reset_pending;
 		tp->link_ok = rtl8169_xmii_link_ok;
@@ -8444,9 +8453,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
 		~(RxBOVF | RxFOVF) : ~0;
 
-	init_timer(&tp->timer);
-	tp->timer.data = (unsigned long) dev;
-	tp->timer.function = rtl8169_phy_timer;
+	setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev);
 
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 8cfc4a54f2dc..3cd7989c007d 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1516,11 +1516,12 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		spin_unlock_irqrestore(&priv->lock, flags);
 		return NETDEV_TX_BUSY;
 	}
-	entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC);
-	priv->tx_skb[q][entry / NUM_TX_DESC] = skb;
 
 	if (skb_put_padto(skb, ETH_ZLEN))
-		goto drop;
+		goto exit;
+
+	entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC);
+	priv->tx_skb[q][entry / NUM_TX_DESC] = skb;
 
 	buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) +
 		 entry / NUM_TX_DESC * DPTR_ALIGN;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 54248775f227..f68c4db656ed 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1127,12 +1127,70 @@ static struct mdiobb_ops bb_ops = {
 	.get_mdio_data = sh_get_mdio,
 };
 
+/* free Tx skb function */
+static int sh_eth_tx_free(struct net_device *ndev, bool sent_only)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	struct sh_eth_txdesc *txdesc;
+	int free_num = 0;
+	int entry;
+	bool sent;
+
+	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
+		entry = mdp->dirty_tx % mdp->num_tx_ring;
+		txdesc = &mdp->tx_ring[entry];
+		sent = !(txdesc->status & cpu_to_le32(TD_TACT));
+		if (sent_only && !sent)
+			break;
+		/* TACT bit must be checked before all the following reads */
+		dma_rmb();
+		netif_info(mdp, tx_done, ndev,
+			   "tx entry %d status 0x%08x\n",
+			   entry, le32_to_cpu(txdesc->status));
+		/* Free the original skb. */
+		if (mdp->tx_skbuff[entry]) {
+			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
+					 le32_to_cpu(txdesc->len) >> 16,
+					 DMA_TO_DEVICE);
+			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
+			mdp->tx_skbuff[entry] = NULL;
+			free_num++;
+		}
+		txdesc->status = cpu_to_le32(TD_TFP);
+		if (entry >= mdp->num_tx_ring - 1)
+			txdesc->status |= cpu_to_le32(TD_TDLE);
+
+		if (sent) {
+			ndev->stats.tx_packets++;
+			ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
+		}
+	}
+	return free_num;
+}
+
 /* free skb and descriptor buffer */
 static void sh_eth_ring_free(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	int ringsize, i;
 
+	if (mdp->rx_ring) {
+		for (i = 0; i < mdp->num_rx_ring; i++) {
+			if (mdp->rx_skbuff[i]) {
+				struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i];
+
+				dma_unmap_single(&ndev->dev,
+						 le32_to_cpu(rxdesc->addr),
+						 ALIGN(mdp->rx_buf_sz, 32),
+						 DMA_FROM_DEVICE);
+			}
+		}
+		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
+		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
+				  mdp->rx_desc_dma);
+		mdp->rx_ring = NULL;
+	}
+
 	/* Free Rx skb ringbuffer */
 	if (mdp->rx_skbuff) {
 		for (i = 0; i < mdp->num_rx_ring; i++)
@@ -1141,27 +1199,18 @@ static void sh_eth_ring_free(struct net_device *ndev)
 	kfree(mdp->rx_skbuff);
 	mdp->rx_skbuff = NULL;
 
-	/* Free Tx skb ringbuffer */
-	if (mdp->tx_skbuff) {
-		for (i = 0; i < mdp->num_tx_ring; i++)
-			dev_kfree_skb(mdp->tx_skbuff[i]);
-	}
-	kfree(mdp->tx_skbuff);
-	mdp->tx_skbuff = NULL;
-
-	if (mdp->rx_ring) {
-		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
-		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
-				  mdp->rx_desc_dma);
-		mdp->rx_ring = NULL;
-	}
-
 	if (mdp->tx_ring) {
+		sh_eth_tx_free(ndev, false);
+
 		ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring;
 		dma_free_coherent(NULL, ringsize, mdp->tx_ring,
 				  mdp->tx_desc_dma);
 		mdp->tx_ring = NULL;
 	}
+
+	/* Free Tx skb ringbuffer */
+	kfree(mdp->tx_skbuff);
+	mdp->tx_skbuff = NULL;
 }
 
 /* format skb and descriptor buffer */
@@ -1409,43 +1458,6 @@ static void sh_eth_dev_exit(struct net_device *ndev)
 	update_mac_address(ndev);
 }
 
-/* free Tx skb function */
-static int sh_eth_txfree(struct net_device *ndev)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	struct sh_eth_txdesc *txdesc;
-	int free_num = 0;
-	int entry;
-
-	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
-		entry = mdp->dirty_tx % mdp->num_tx_ring;
-		txdesc = &mdp->tx_ring[entry];
-		if (txdesc->status & cpu_to_le32(TD_TACT))
-			break;
-		/* TACT bit must be checked before all the following reads */
-		dma_rmb();
-		netif_info(mdp, tx_done, ndev,
-			   "tx entry %d status 0x%08x\n",
-			   entry, le32_to_cpu(txdesc->status));
-		/* Free the original skb. */
-		if (mdp->tx_skbuff[entry]) {
-			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
-					 le32_to_cpu(txdesc->len) >> 16,
-					 DMA_TO_DEVICE);
-			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
-			mdp->tx_skbuff[entry] = NULL;
-			free_num++;
-		}
-		txdesc->status = cpu_to_le32(TD_TFP);
-		if (entry >= mdp->num_tx_ring - 1)
-			txdesc->status |= cpu_to_le32(TD_TDLE);
-
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
-	}
-	return free_num;
-}
-
 /* Packet receive function */
 static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 {
@@ -1690,7 +1702,7 @@ static void sh_eth_error(struct net_device *ndev, u32 intr_status)
 			   intr_status, mdp->cur_tx, mdp->dirty_tx,
 			   (u32)ndev->state, edtrr);
 		/* dirty buffer free */
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 
 		/* SH7712 BUG */
 		if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) {
@@ -1751,7 +1763,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev)
 		/* Clear Tx interrupts */
 		sh_eth_write(ndev, intr_status & cd->tx_check, EESR);
 
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 		netif_wake_queue(ndev);
 	}
 
@@ -2412,7 +2424,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	spin_lock_irqsave(&mdp->lock, flags);
 	if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) {
-		if (!sh_eth_txfree(ndev)) {
+		if (!sh_eth_tx_free(ndev, true)) {
 			netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n");
 			netif_stop_queue(ndev);
 			spin_unlock_irqrestore(&mdp->lock, flags);
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 0f63a44a955d..bab13613b138 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -33,6 +33,7 @@
 #include <net/rtnetlink.h>
 #include <net/netevent.h>
 #include <net/arp.h>
+#include <net/fib_rules.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <generated/utsrelease.h>
 
@@ -1115,7 +1116,7 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port,
 					  const struct rocker_desc_info *desc_info,
 					  void *priv)
 {
-	struct ethtool_cmd *ecmd = priv;
+	struct ethtool_link_ksettings *ecmd = priv;
 	const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
 	const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
 	u32 speed;
@@ -1137,13 +1138,14 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port,
 	duplex = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX]);
 	autoneg = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG]);
 
-	ecmd->transceiver = XCVR_INTERNAL;
-	ecmd->supported = SUPPORTED_TP;
-	ecmd->phy_address = 0xff;
-	ecmd->port = PORT_TP;
-	ethtool_cmd_speed_set(ecmd, speed);
-	ecmd->duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF;
-	ecmd->autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, TP);
+
+	ecmd->base.phy_address = 0xff;
+	ecmd->base.port = PORT_TP;
+	ecmd->base.speed = speed;
+	ecmd->base.duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF;
+	ecmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
 
 	return 0;
 }
@@ -1250,7 +1252,7 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port,
 					  struct rocker_desc_info *desc_info,
 					  void *priv)
 {
-	struct ethtool_cmd *ecmd = priv;
+	struct ethtool_link_ksettings *ecmd = priv;
 	struct rocker_tlv *cmd_info;
 
 	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
@@ -1263,13 +1265,13 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port,
 			       rocker_port->pport))
 		return -EMSGSIZE;
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_SPEED,
-			       ethtool_cmd_speed(ecmd)))
+			       ecmd->base.speed))
 		return -EMSGSIZE;
 	if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX,
-			      ecmd->duplex))
+			      ecmd->base.duplex))
 		return -EMSGSIZE;
 	if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG,
-			      ecmd->autoneg))
+			      ecmd->base.autoneg))
 		return -EMSGSIZE;
 	rocker_tlv_nest_end(desc_info, cmd_info);
 	return 0;
@@ -1347,8 +1349,9 @@ rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port,
 	return 0;
 }
 
-static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port,
-						struct ethtool_cmd *ecmd)
+static int
+rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port,
+				     struct ethtool_link_ksettings *ecmd)
 {
 	return rocker_cmd_exec(rocker_port, false,
 			       rocker_cmd_get_port_settings_prep, NULL,
@@ -1373,12 +1376,17 @@ static int rocker_cmd_get_port_settings_mode(struct rocker_port *rocker_port,
 			       rocker_cmd_get_port_settings_mode_proc, p_mode);
 }
 
-static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port,
-						struct ethtool_cmd *ecmd)
+static int
+rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port,
+				     const struct ethtool_link_ksettings *ecmd)
 {
+	struct ethtool_link_ksettings copy_ecmd;
+
+	memcpy(&copy_ecmd, ecmd, sizeof(copy_ecmd));
+
 	return rocker_cmd_exec(rocker_port, false,
 			       rocker_cmd_set_port_settings_ethtool_prep,
-			       ecmd, NULL, NULL);
+			       &copy_ecmd, NULL, NULL);
 }
 
 static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port,
@@ -2168,7 +2176,10 @@ static const struct switchdev_ops rocker_port_switchdev_ops = {
 
 struct rocker_fib_event_work {
 	struct work_struct work;
-	struct fib_entry_notifier_info fen_info;
+	union {
+		struct fib_entry_notifier_info fen_info;
+		struct fib_rule_notifier_info fr_info;
+	};
 	struct rocker *rocker;
 	unsigned long event;
 };
@@ -2178,6 +2189,7 @@ static void rocker_router_fib_event_work(struct work_struct *work)
 	struct rocker_fib_event_work *fib_work =
 		container_of(work, struct rocker_fib_event_work, work);
 	struct rocker *rocker = fib_work->rocker;
+	struct fib_rule *rule;
 	int err;
 
 	/* Protect internal structures from changes */
@@ -2195,7 +2207,10 @@ static void rocker_router_fib_event_work(struct work_struct *work)
 		break;
 	case FIB_EVENT_RULE_ADD: /* fall through */
 	case FIB_EVENT_RULE_DEL:
-		rocker_world_fib4_abort(rocker);
+		rule = fib_work->fr_info.rule;
+		if (!fib4_rule_default(rule))
+			rocker_world_fib4_abort(rocker);
+		fib_rule_put(rule);
 		break;
 	}
 	rtnl_unlock();
@@ -2226,6 +2241,11 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
+	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_DEL:
+		memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
+		fib_rule_get(fib_work->fr_info.rule);
+		break;
 	}
 
 	queue_work(rocker->rocker_owq, &fib_work->work);
@@ -2237,16 +2257,18 @@ static int rocker_router_fib_event(struct notifier_block *nb,
  * ethtool interface
  ********************/
 
-static int rocker_port_get_settings(struct net_device *dev,
-				    struct ethtool_cmd *ecmd)
+static int
+rocker_port_get_link_ksettings(struct net_device *dev,
+			       struct ethtool_link_ksettings *ecmd)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
 
 	return rocker_cmd_get_port_settings_ethtool(rocker_port, ecmd);
 }
 
-static int rocker_port_set_settings(struct net_device *dev,
-				    struct ethtool_cmd *ecmd)
+static int
+rocker_port_set_link_ksettings(struct net_device *dev,
+			       const struct ethtool_link_ksettings *ecmd)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
 
@@ -2388,13 +2410,13 @@ static int rocker_port_get_sset_count(struct net_device *netdev, int sset)
 }
 
 static const struct ethtool_ops rocker_port_ethtool_ops = {
-	.get_settings		= rocker_port_get_settings,
-	.set_settings		= rocker_port_set_settings,
 	.get_drvinfo		= rocker_port_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_strings		= rocker_port_get_strings,
 	.get_ethtool_stats	= rocker_port_get_stats,
 	.get_sset_count		= rocker_port_get_sset_count,
+	.get_link_ksettings	= rocker_port_get_link_ksettings,
+	.set_link_ksettings	= rocker_port_set_link_ksettings,
 };
 
 /*****************
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 7cd76b6b5cb9..2ae852454780 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -2216,18 +2216,15 @@ static int ofdpa_port_stp_update(struct ofdpa_port *ofdpa_port,
 {
 	bool want[OFDPA_CTRL_MAX] = { 0, };
 	bool prev_ctrls[OFDPA_CTRL_MAX];
-	u8 uninitialized_var(prev_state);
+	u8 prev_state;
 	int err;
 	int i;
 
-	if (switchdev_trans_ph_prepare(trans)) {
-		memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
-		prev_state = ofdpa_port->stp_state;
-	}
-
-	if (ofdpa_port->stp_state == state)
+	prev_state = ofdpa_port->stp_state;
+	if (prev_state == state)
 		return 0;
 
+	memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
 	ofdpa_port->stp_state = state;
 
 	switch (state) {
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c60c2d4c646a..78efb2822b86 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -119,6 +119,7 @@ struct efx_ef10_filter_table {
 	bool mc_promisc;
 /* Whether in multicast promiscuous mode when last changed */
 	bool mc_promisc_last;
+	bool mc_overflow; /* Too many MC addrs; should always imply mc_promisc */
 	bool vlan_filter;
 	struct list_head vlan_list;
 };
@@ -5058,6 +5059,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 	struct netdev_hw_addr *mc;
 	unsigned int i, addr_count;
 
+	table->mc_overflow = false;
 	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
 	addr_count = netdev_mc_count(net_dev);
@@ -5065,6 +5067,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
 			table->mc_promisc = true;
+			table->mc_overflow = true;
 			break;
 		}
 		ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
@@ -5469,12 +5472,15 @@ static void efx_ef10_filter_vlan_sync_rx_mode(struct efx_nic *efx,
 			}
 		} else {
 			/* If we failed to insert promiscuous filters, don't
-			 * rollback.  Regardless, also insert the mc_list
+			 * rollback.  Regardless, also insert the mc_list,
+			 * unless it's incomplete due to overflow
 			 */
 			efx_ef10_filter_insert_def(efx, vlan,
 						   EFX_ENCAP_TYPE_NONE,
 						   true, false);
-			efx_ef10_filter_insert_addr_list(efx, vlan, true, false);
+			if (!table->mc_overflow)
+				efx_ef10_filter_insert_addr_list(efx, vlan,
+								 true, false);
 		}
 	} else {
 		/* If any filters failed to insert, rollback and fall back to
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 334bcc6df6b2..b9cb697b2818 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1371,6 +1371,13 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 		free_cpumask_var(thread_mask);
 	}
 
+	if (count > EFX_MAX_RX_QUEUES) {
+		netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+			       "Reducing number of rx queues from %u to %u.\n",
+			       count, EFX_MAX_RX_QUEUES);
+		count = EFX_MAX_RX_QUEUES;
+	}
+
 	/* If RSS is requested for the PF *and* VFs then we can't write RSS
 	 * table entries that are inaccessible to VFs
 	 */
@@ -2404,7 +2411,7 @@ static void efx_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *t
 	tnl.type = (u16)efx_tunnel_type;
 	tnl.port = ti->port;
 
-	if (efx->type->udp_tnl_add_port)
+	if (efx->type->udp_tnl_del_port)
 		(void)efx->type->udp_tnl_del_port(efx, tnl);
 }
 
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index ee14662415c5..a0c52e328102 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -74,7 +74,10 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
 #define EFX_RXQ_MIN_ENT		128U
 #define EFX_TXQ_MIN_ENT(efx)	(2 * efx_tx_max_skb_descs(efx))
 
-#define EFX_TXQ_MAX_ENT(efx)	(EFX_WORKAROUND_35388(efx) ? \
+/* All EF10 architecture NICs steal one bit of the DMAQ size for various
+ * other purposes when counting TxQ entries, so we halve the queue size.
+ */
+#define EFX_TXQ_MAX_ENT(efx)	(EFX_WORKAROUND_EF10(efx) ? \
 				 EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE)
 
 static inline bool efx_rss_enabled(struct efx_nic *efx)
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index f5e5cd1659a1..29614da91cbf 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -1354,6 +1354,13 @@ static unsigned int ef4_wanted_parallelism(struct ef4_nic *efx)
 		free_cpumask_var(thread_mask);
 	}
 
+	if (count > EF4_MAX_RX_QUEUES) {
+		netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+			       "Reducing number of rx queues from %u to %u.\n",
+			       count, EF4_MAX_RX_QUEUES);
+		count = EF4_MAX_RX_QUEUES;
+	}
+
 	return count;
 }
 
diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c
index 104fb15a73f2..f6daf09b8627 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.c
+++ b/drivers/net/ethernet/sfc/falcon/tx.c
@@ -437,11 +437,13 @@ int ef4_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	num_tc = ntc->tc;
+	num_tc = ntc->mqprio->num_tc;
 
 	if (ef4_nic_rev(efx) < EF4_REV_FALCON_B0 || num_tc > EF4_MAX_TX_TC)
 		return -EINVAL;
 
+	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
 	if (num_tc == net_dev->num_tc)
 		return 0;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index ff88d60aa6d5..3bdf87f31087 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -665,11 +665,13 @@ int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	num_tc = ntc->tc;
+	num_tc = ntc->mqprio->num_tc;
 
 	if (num_tc > EFX_MAX_TX_TC)
 		return -EINVAL;
 
+	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
 	if (num_tc == net_dev->num_tc)
 		return 0;
 
diff --git a/drivers/net/ethernet/sfc/workarounds.h b/drivers/net/ethernet/sfc/workarounds.h
index 103f827a1623..c67fa18b8121 100644
--- a/drivers/net/ethernet/sfc/workarounds.h
+++ b/drivers/net/ethernet/sfc/workarounds.h
@@ -16,6 +16,7 @@
  */
 
 #define EFX_WORKAROUND_SIENA(efx) (efx_nic_rev(efx) == EFX_REV_SIENA_A0)
+#define EFX_WORKAROUND_EF10(efx) (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
 #define EFX_WORKAROUND_10G(efx) 1
 
 /* Bit-bashed I2C reads cause performance drop */
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 57e6cef81ebe..52ead5524de7 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -1558,25 +1558,27 @@ static void ioc3_get_drvinfo (struct net_device *dev,
 	strlcpy(info->bus_info, pci_name(ip->pdev), sizeof(info->bus_info));
 }
 
-static int ioc3_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ioc3_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct ioc3_private *ip = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&ip->ioc3_lock);
-	rc = mii_ethtool_gset(&ip->mii, cmd);
+	rc = mii_ethtool_get_link_ksettings(&ip->mii, cmd);
 	spin_unlock_irq(&ip->ioc3_lock);
 
 	return rc;
 }
 
-static int ioc3_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ioc3_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct ioc3_private *ip = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&ip->ioc3_lock);
-	rc = mii_ethtool_sset(&ip->mii, cmd);
+	rc = mii_ethtool_set_link_ksettings(&ip->mii, cmd);
 	spin_unlock_irq(&ip->ioc3_lock);
 
 	return rc;
@@ -1608,10 +1610,10 @@ static u32 ioc3_get_link(struct net_device *dev)
 
 static const struct ethtool_ops ioc3_ethtool_ops = {
 	.get_drvinfo		= ioc3_get_drvinfo,
-	.get_settings		= ioc3_get_settings,
-	.set_settings		= ioc3_set_settings,
 	.nway_reset		= ioc3_nway_reset,
 	.get_link		= ioc3_get_link,
+	.get_link_ksettings	= ioc3_get_link_ksettings,
+	.set_link_ksettings	= ioc3_set_link_ksettings,
 };
 
 static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
index 6c2e2b311c16..751c81848f35 100644
--- a/drivers/net/ethernet/silan/sc92031.c
+++ b/drivers/net/ethernet/silan/sc92031.c
@@ -1122,14 +1122,16 @@ static void sc92031_poll_controller(struct net_device *dev)
 }
 #endif
 
-static int sc92031_ethtool_get_settings(struct net_device *dev,
-		struct ethtool_cmd *cmd)
+static int
+sc92031_ethtool_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct sc92031_priv *priv = netdev_priv(dev);
 	void __iomem *port_base = priv->port_base;
 	u8 phy_address;
 	u32 phy_ctrl;
 	u16 output_status;
+	u32 supported, advertising;
 
 	spin_lock_bh(&priv->lock);
 
@@ -1142,68 +1144,77 @@ static int sc92031_ethtool_get_settings(struct net_device *dev,
 
 	spin_unlock_bh(&priv->lock);
 
-	cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full
+	supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full
 			| SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full
 			| SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII;
 
-	cmd->advertising = ADVERTISED_TP | ADVERTISED_MII;
+	advertising = ADVERTISED_TP | ADVERTISED_MII;
 
 	if ((phy_ctrl & (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10))
 			== (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10))
-		cmd->advertising |= ADVERTISED_Autoneg;
+		advertising |= ADVERTISED_Autoneg;
 
 	if ((phy_ctrl & PhyCtrlSpd10) == PhyCtrlSpd10)
-		cmd->advertising |= ADVERTISED_10baseT_Half;
+		advertising |= ADVERTISED_10baseT_Half;
 
 	if ((phy_ctrl & (PhyCtrlSpd10 | PhyCtrlDux))
 			== (PhyCtrlSpd10 | PhyCtrlDux))
-		cmd->advertising |= ADVERTISED_10baseT_Full;
+		advertising |= ADVERTISED_10baseT_Full;
 
 	if ((phy_ctrl & PhyCtrlSpd100) == PhyCtrlSpd100)
-		cmd->advertising |= ADVERTISED_100baseT_Half;
+		advertising |= ADVERTISED_100baseT_Half;
 
 	if ((phy_ctrl & (PhyCtrlSpd100 | PhyCtrlDux))
 			== (PhyCtrlSpd100 | PhyCtrlDux))
-		cmd->advertising |= ADVERTISED_100baseT_Full;
+		advertising |= ADVERTISED_100baseT_Full;
 
 	if (phy_ctrl & PhyCtrlAne)
-		cmd->advertising |= ADVERTISED_Autoneg;
+		advertising |= ADVERTISED_Autoneg;
 
-	ethtool_cmd_speed_set(cmd,
-			      (output_status & 0x2) ? SPEED_100 : SPEED_10);
-	cmd->duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF;
-	cmd->port = PORT_MII;
-	cmd->phy_address = phy_address;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->autoneg = (phy_ctrl & PhyCtrlAne) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+	cmd->base.speed = (output_status & 0x2) ? SPEED_100 : SPEED_10;
+	cmd->base.duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF;
+	cmd->base.port = PORT_MII;
+	cmd->base.phy_address = phy_address;
+	cmd->base.autoneg = (phy_ctrl & PhyCtrlAne) ?
+		AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int sc92031_ethtool_set_settings(struct net_device *dev,
-		struct ethtool_cmd *cmd)
+static int
+sc92031_ethtool_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct sc92031_priv *priv = netdev_priv(dev);
 	void __iomem *port_base = priv->port_base;
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
 	u32 phy_ctrl;
 	u32 old_phy_ctrl;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	if (!(speed == SPEED_10 || speed == SPEED_100))
 		return -EINVAL;
-	if (!(cmd->duplex == DUPLEX_HALF || cmd->duplex == DUPLEX_FULL))
-		return -EINVAL;
-	if (!(cmd->port == PORT_MII))
+	if (!(cmd->base.duplex == DUPLEX_HALF ||
+	      cmd->base.duplex == DUPLEX_FULL))
 		return -EINVAL;
-	if (!(cmd->phy_address == 0x1f))
+	if (!(cmd->base.port == PORT_MII))
 		return -EINVAL;
-	if (!(cmd->transceiver == XCVR_INTERNAL))
+	if (!(cmd->base.phy_address == 0x1f))
 		return -EINVAL;
-	if (!(cmd->autoneg == AUTONEG_DISABLE || cmd->autoneg == AUTONEG_ENABLE))
+	if (!(cmd->base.autoneg == AUTONEG_DISABLE ||
+	      cmd->base.autoneg == AUTONEG_ENABLE))
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_ENABLE) {
-		if (!(cmd->advertising & (ADVERTISED_Autoneg
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
+		if (!(advertising & (ADVERTISED_Autoneg
 				| ADVERTISED_100baseT_Full
 				| ADVERTISED_100baseT_Half
 				| ADVERTISED_10baseT_Full
@@ -1213,15 +1224,15 @@ static int sc92031_ethtool_set_settings(struct net_device *dev,
 		phy_ctrl = PhyCtrlAne;
 
 		// FIXME: I'm not sure what the original code was trying to do
-		if (cmd->advertising & ADVERTISED_Autoneg)
+		if (advertising & ADVERTISED_Autoneg)
 			phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10;
-		if (cmd->advertising & ADVERTISED_100baseT_Full)
+		if (advertising & ADVERTISED_100baseT_Full)
 			phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100;
-		if (cmd->advertising & ADVERTISED_100baseT_Half)
+		if (advertising & ADVERTISED_100baseT_Half)
 			phy_ctrl |= PhyCtrlSpd100;
-		if (cmd->advertising & ADVERTISED_10baseT_Full)
+		if (advertising & ADVERTISED_10baseT_Full)
 			phy_ctrl |= PhyCtrlSpd10 | PhyCtrlDux;
-		if (cmd->advertising & ADVERTISED_10baseT_Half)
+		if (advertising & ADVERTISED_10baseT_Half)
 			phy_ctrl |= PhyCtrlSpd10;
 	} else {
 		// FIXME: Whole branch guessed
@@ -1232,7 +1243,7 @@ static int sc92031_ethtool_set_settings(struct net_device *dev,
 		else /* cmd->speed == SPEED_100 */
 			phy_ctrl |= PhyCtrlSpd100;
 
-		if (cmd->duplex == DUPLEX_FULL)
+		if (cmd->base.duplex == DUPLEX_FULL)
 			phy_ctrl |= PhyCtrlDux;
 	}
 
@@ -1368,8 +1379,6 @@ static void sc92031_ethtool_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops sc92031_ethtool_ops = {
-	.get_settings		= sc92031_ethtool_get_settings,
-	.set_settings		= sc92031_ethtool_set_settings,
 	.get_wol		= sc92031_ethtool_get_wol,
 	.set_wol		= sc92031_ethtool_set_wol,
 	.nway_reset		= sc92031_ethtool_nway_reset,
@@ -1377,6 +1386,8 @@ static const struct ethtool_ops sc92031_ethtool_ops = {
 	.get_strings		= sc92031_ethtool_get_strings,
 	.get_sset_count		= sc92031_ethtool_get_sset_count,
 	.get_ethtool_stats	= sc92031_ethtool_get_ethtool_stats,
+	.get_link_ksettings	= sc92031_ethtool_get_link_ksettings,
+	.set_link_ksettings	= sc92031_ethtool_set_link_ksettings,
 };
 
 
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index 210e35d079dd..02da106c6e04 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -1734,18 +1734,20 @@ static void sis190_set_speed_auto(struct net_device *dev)
 		   BMCR_ANENABLE | BMCR_ANRESTART | BMCR_RESET);
 }
 
-static int sis190_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int sis190_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct sis190_private *tp = netdev_priv(dev);
 
-	return mii_ethtool_gset(&tp->mii_if, cmd);
+	return mii_ethtool_get_link_ksettings(&tp->mii_if, cmd);
 }
 
-static int sis190_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int sis190_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct sis190_private *tp = netdev_priv(dev);
 
-	return mii_ethtool_sset(&tp->mii_if, cmd);
+	return mii_ethtool_set_link_ksettings(&tp->mii_if, cmd);
 }
 
 static void sis190_get_drvinfo(struct net_device *dev,
@@ -1797,8 +1799,6 @@ static void sis190_set_msglevel(struct net_device *dev, u32 value)
 }
 
 static const struct ethtool_ops sis190_ethtool_ops = {
-	.get_settings	= sis190_get_settings,
-	.set_settings	= sis190_set_settings,
 	.get_drvinfo	= sis190_get_drvinfo,
 	.get_regs_len	= sis190_get_regs_len,
 	.get_regs	= sis190_get_regs,
@@ -1806,6 +1806,8 @@ static const struct ethtool_ops sis190_ethtool_ops = {
 	.get_msglevel	= sis190_get_msglevel,
 	.set_msglevel	= sis190_set_msglevel,
 	.nway_reset	= sis190_nway_reset,
+	.get_link_ksettings = sis190_get_link_ksettings,
+	.set_link_ksettings = sis190_set_link_ksettings,
 };
 
 static int sis190_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 1b6f6171d078..40bd88362e3d 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -2035,23 +2035,23 @@ static u32 sis900_get_link(struct net_device *net_dev)
 	return mii_link_ok(&sis_priv->mii_info);
 }
 
-static int sis900_get_settings(struct net_device *net_dev,
-				struct ethtool_cmd *cmd)
+static int sis900_get_link_ksettings(struct net_device *net_dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct sis900_private *sis_priv = netdev_priv(net_dev);
 	spin_lock_irq(&sis_priv->lock);
-	mii_ethtool_gset(&sis_priv->mii_info, cmd);
+	mii_ethtool_get_link_ksettings(&sis_priv->mii_info, cmd);
 	spin_unlock_irq(&sis_priv->lock);
 	return 0;
 }
 
-static int sis900_set_settings(struct net_device *net_dev,
-				struct ethtool_cmd *cmd)
+static int sis900_set_link_ksettings(struct net_device *net_dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct sis900_private *sis_priv = netdev_priv(net_dev);
 	int rt;
 	spin_lock_irq(&sis_priv->lock);
-	rt = mii_ethtool_sset(&sis_priv->mii_info, cmd);
+	rt = mii_ethtool_set_link_ksettings(&sis_priv->mii_info, cmd);
 	spin_unlock_irq(&sis_priv->lock);
 	return rt;
 }
@@ -2129,11 +2129,11 @@ static const struct ethtool_ops sis900_ethtool_ops = {
 	.get_msglevel	= sis900_get_msglevel,
 	.set_msglevel	= sis900_set_msglevel,
 	.get_link	= sis900_get_link,
-	.get_settings	= sis900_get_settings,
-	.set_settings	= sis900_set_settings,
 	.nway_reset	= sis900_nway_reset,
 	.get_wol	= sis900_get_wol,
-	.set_wol	= sis900_set_wol
+	.set_wol	= sis900_set_wol,
+	.get_link_ksettings = sis900_get_link_ksettings,
+	.set_link_ksettings = sis900_set_link_ksettings,
 };
 
 /**
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 5f2737189c72..db6dcb06193d 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1387,25 +1387,27 @@ static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *
 	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
-static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct epic_private *np = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&np->lock);
-	rc = mii_ethtool_gset(&np->mii, cmd);
+	rc = mii_ethtool_get_link_ksettings(&np->mii, cmd);
 	spin_unlock_irq(&np->lock);
 
 	return rc;
 }
 
-static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct epic_private *np = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&np->lock);
-	rc = mii_ethtool_sset(&np->mii, cmd);
+	rc = mii_ethtool_set_link_ksettings(&np->mii, cmd);
 	spin_unlock_irq(&np->lock);
 
 	return rc;
@@ -1460,14 +1462,14 @@ static void ethtool_complete(struct net_device *dev)
 
 static const struct ethtool_ops netdev_ethtool_ops = {
 	.get_drvinfo		= netdev_get_drvinfo,
-	.get_settings		= netdev_get_settings,
-	.set_settings		= netdev_set_settings,
 	.nway_reset		= netdev_nway_reset,
 	.get_link		= netdev_get_link,
 	.get_msglevel		= netdev_get_msglevel,
 	.set_msglevel		= netdev_set_msglevel,
 	.begin			= ethtool_begin,
-	.complete		= ethtool_complete
+	.complete		= ethtool_complete,
+	.get_link_ksettings	= netdev_get_link_ksettings,
+	.set_link_ksettings	= netdev_set_link_ksettings,
 };
 
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 4f19c6166182..36307d34f641 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1446,40 +1446,40 @@ static int smc911x_close(struct net_device *dev)
  * Ethtool support
  */
 static int
-smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc911x_ethtool_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct smc911x_local *lp = netdev_priv(dev);
 	int ret, status;
 	unsigned long flags;
+	u32 supported;
 
 	DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__);
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
 
 	if (lp->phy_type != 0) {
 		spin_lock_irqsave(&lp->lock, flags);
-		ret = mii_ethtool_gset(&lp->mii, cmd);
+		ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irqrestore(&lp->lock, flags);
 	} else {
-		cmd->supported = SUPPORTED_10baseT_Half |
+		supported = SUPPORTED_10baseT_Half |
 				SUPPORTED_10baseT_Full |
 				SUPPORTED_TP | SUPPORTED_AUI;
 
 		if (lp->ctl_rspeed == 10)
-			ethtool_cmd_speed_set(cmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 		else if (lp->ctl_rspeed == 100)
-			ethtool_cmd_speed_set(cmd, SPEED_100);
-
-		cmd->autoneg = AUTONEG_DISABLE;
-		if (lp->mii.phy_id==1)
-			cmd->transceiver = XCVR_INTERNAL;
-		else
-			cmd->transceiver = XCVR_EXTERNAL;
-		cmd->port = 0;
+			cmd->base.speed = SPEED_100;
+
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		cmd->base.port = 0;
 		SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status);
-		cmd->duplex =
+		cmd->base.duplex =
 			(status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ?
 				DUPLEX_FULL : DUPLEX_HALF;
+
+		ethtool_convert_legacy_u32_to_link_mode(
+			cmd->link_modes.supported, supported);
+
 		ret = 0;
 	}
 
@@ -1487,7 +1487,8 @@ smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
 }
 
 static int
-smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc911x_ethtool_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct smc911x_local *lp = netdev_priv(dev);
 	int ret;
@@ -1495,16 +1496,18 @@ smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
 
 	if (lp->phy_type != 0) {
 		spin_lock_irqsave(&lp->lock, flags);
-		ret = mii_ethtool_sset(&lp->mii, cmd);
+		ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irqrestore(&lp->lock, flags);
 	} else {
-		if (cmd->autoneg != AUTONEG_DISABLE ||
-			cmd->speed != SPEED_10 ||
-			(cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) ||
-			(cmd->port != PORT_TP && cmd->port != PORT_AUI))
+		if (cmd->base.autoneg != AUTONEG_DISABLE ||
+		    cmd->base.speed != SPEED_10 ||
+		    (cmd->base.duplex != DUPLEX_HALF &&
+		     cmd->base.duplex != DUPLEX_FULL) ||
+		    (cmd->base.port != PORT_TP &&
+		     cmd->base.port != PORT_AUI))
 			return -EINVAL;
 
-		lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL;
+		lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
 
 		ret = 0;
 	}
@@ -1686,8 +1689,6 @@ static int smc911x_ethtool_geteeprom_len(struct net_device *dev)
 }
 
 static const struct ethtool_ops smc911x_ethtool_ops = {
-	.get_settings	 = smc911x_ethtool_getsettings,
-	.set_settings	 = smc911x_ethtool_setsettings,
 	.get_drvinfo	 = smc911x_ethtool_getdrvinfo,
 	.get_msglevel	 = smc911x_ethtool_getmsglevel,
 	.set_msglevel	 = smc911x_ethtool_setmsglevel,
@@ -1698,6 +1699,8 @@ static const struct ethtool_ops smc911x_ethtool_ops = {
 	.get_eeprom_len = smc911x_ethtool_geteeprom_len,
 	.get_eeprom = smc911x_ethtool_geteeprom,
 	.set_eeprom = smc911x_ethtool_seteeprom,
+	.get_link_ksettings	 = smc911x_ethtool_get_link_ksettings,
+	.set_link_ksettings	 = smc911x_ethtool_set_link_ksettings,
 };
 
 /*
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index 97280daba27f..976aa876789a 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -1843,56 +1843,60 @@ static int smc_link_ok(struct net_device *dev)
     }
 }
 
-static int smc_netdev_get_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_netdev_get_ecmd(struct net_device *dev,
+			       struct ethtool_link_ksettings *ecmd)
 {
-    u16 tmp;
-    unsigned int ioaddr = dev->base_addr;
+	u16 tmp;
+	unsigned int ioaddr = dev->base_addr;
+	u32 supported;
 
-    ecmd->supported = (SUPPORTED_TP | SUPPORTED_AUI |
-	SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full);
-		
-    SMC_SELECT_BANK(1);
-    tmp = inw(ioaddr + CONFIG);
-    ecmd->port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP;
-    ecmd->transceiver = XCVR_INTERNAL;
-    ethtool_cmd_speed_set(ecmd, SPEED_10);
-    ecmd->phy_address = ioaddr + MGMT;
+	supported = (SUPPORTED_TP | SUPPORTED_AUI |
+		     SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full);
 
-    SMC_SELECT_BANK(0);
-    tmp = inw(ioaddr + TCR);
-    ecmd->duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF;
+	SMC_SELECT_BANK(1);
+	tmp = inw(ioaddr + CONFIG);
+	ecmd->base.port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP;
+	ecmd->base.speed = SPEED_10;
+	ecmd->base.phy_address = ioaddr + MGMT;
 
-    return 0;
+	SMC_SELECT_BANK(0);
+	tmp = inw(ioaddr + TCR);
+	ecmd->base.duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF;
+
+	ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported,
+						supported);
+
+	return 0;
 }
 
-static int smc_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_netdev_set_ecmd(struct net_device *dev,
+			       const struct ethtool_link_ksettings *ecmd)
 {
-    u16 tmp;
-    unsigned int ioaddr = dev->base_addr;
+	u16 tmp;
+	unsigned int ioaddr = dev->base_addr;
 
-    if (ethtool_cmd_speed(ecmd) != SPEED_10)
-	return -EINVAL;
-    if (ecmd->duplex != DUPLEX_HALF && ecmd->duplex != DUPLEX_FULL)
-    	return -EINVAL;
-    if (ecmd->port != PORT_TP && ecmd->port != PORT_AUI)
-	return -EINVAL;
-    if (ecmd->transceiver != XCVR_INTERNAL)
-    	return -EINVAL;
+	if (ecmd->base.speed != SPEED_10)
+		return -EINVAL;
+	if (ecmd->base.duplex != DUPLEX_HALF &&
+	    ecmd->base.duplex != DUPLEX_FULL)
+		return -EINVAL;
+	if (ecmd->base.port != PORT_TP && ecmd->base.port != PORT_AUI)
+		return -EINVAL;
 
-    if (ecmd->port == PORT_AUI)
-	smc_set_xcvr(dev, 1);
-    else
-	smc_set_xcvr(dev, 0);
+	if (ecmd->base.port == PORT_AUI)
+		smc_set_xcvr(dev, 1);
+	else
+		smc_set_xcvr(dev, 0);
 
-    SMC_SELECT_BANK(0);
-    tmp = inw(ioaddr + TCR);
-    if (ecmd->duplex == DUPLEX_FULL)
-	tmp |= TCR_FDUPLX;
-    else
-	tmp &= ~TCR_FDUPLX;
-    outw(tmp, ioaddr + TCR);
-	
-    return 0;
+	SMC_SELECT_BANK(0);
+	tmp = inw(ioaddr + TCR);
+	if (ecmd->base.duplex == DUPLEX_FULL)
+		tmp |= TCR_FDUPLX;
+	else
+		tmp &= ~TCR_FDUPLX;
+	outw(tmp, ioaddr + TCR);
+
+	return 0;
 }
 
 static int check_if_running(struct net_device *dev)
@@ -1908,7 +1912,8 @@ static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
-static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *ecmd)
 {
 	struct smc_private *smc = netdev_priv(dev);
 	unsigned int ioaddr = dev->base_addr;
@@ -1919,7 +1924,7 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 	spin_lock_irqsave(&smc->lock, flags);
 	SMC_SELECT_BANK(3);
 	if (smc->cfg & CFG_MII_SELECT)
-		ret = mii_ethtool_gset(&smc->mii_if, ecmd);
+		ret = mii_ethtool_get_link_ksettings(&smc->mii_if, ecmd);
 	else
 		ret = smc_netdev_get_ecmd(dev, ecmd);
 	SMC_SELECT_BANK(saved_bank);
@@ -1927,7 +1932,8 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 	return ret;
 }
 
-static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *ecmd)
 {
 	struct smc_private *smc = netdev_priv(dev);
 	unsigned int ioaddr = dev->base_addr;
@@ -1938,7 +1944,7 @@ static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 	spin_lock_irqsave(&smc->lock, flags);
 	SMC_SELECT_BANK(3);
 	if (smc->cfg & CFG_MII_SELECT)
-		ret = mii_ethtool_sset(&smc->mii_if, ecmd);
+		ret = mii_ethtool_set_link_ksettings(&smc->mii_if, ecmd);
 	else
 		ret = smc_netdev_set_ecmd(dev, ecmd);
 	SMC_SELECT_BANK(saved_bank);
@@ -1982,10 +1988,10 @@ static int smc_nway_reset(struct net_device *dev)
 static const struct ethtool_ops ethtool_ops = {
 	.begin = check_if_running,
 	.get_drvinfo = smc_get_drvinfo,
-	.get_settings = smc_get_settings,
-	.set_settings = smc_set_settings,
 	.get_link = smc_get_link,
 	.nway_reset = smc_nway_reset,
+	.get_link_ksettings = smc_get_link_ksettings,
+	.set_link_ksettings = smc_set_link_ksettings,
 };
 
 static int smc_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 65077c77082a..91e9bd7159ab 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1535,32 +1535,33 @@ static int smc_close(struct net_device *dev)
  * Ethtool support
  */
 static int
-smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc_ethtool_get_link_ksettings(struct net_device *dev,
+			       struct ethtool_link_ksettings *cmd)
 {
 	struct smc_local *lp = netdev_priv(dev);
 	int ret;
 
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
-
 	if (lp->phy_type != 0) {
 		spin_lock_irq(&lp->lock);
-		ret = mii_ethtool_gset(&lp->mii, cmd);
+		ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irq(&lp->lock);
 	} else {
-		cmd->supported = SUPPORTED_10baseT_Half |
+		u32 supported = SUPPORTED_10baseT_Half |
 				 SUPPORTED_10baseT_Full |
 				 SUPPORTED_TP | SUPPORTED_AUI;
 
 		if (lp->ctl_rspeed == 10)
-			ethtool_cmd_speed_set(cmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 		else if (lp->ctl_rspeed == 100)
-			ethtool_cmd_speed_set(cmd, SPEED_100);
+			cmd->base.speed = SPEED_100;
+
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		cmd->base.port = 0;
+		cmd->base.duplex = lp->tcr_cur_mode & TCR_SWFDUP ?
+			DUPLEX_FULL : DUPLEX_HALF;
 
-		cmd->autoneg = AUTONEG_DISABLE;
-		cmd->transceiver = XCVR_INTERNAL;
-		cmd->port = 0;
-		cmd->duplex = lp->tcr_cur_mode & TCR_SWFDUP ? DUPLEX_FULL : DUPLEX_HALF;
+		ethtool_convert_legacy_u32_to_link_mode(
+			cmd->link_modes.supported, supported);
 
 		ret = 0;
 	}
@@ -1569,24 +1570,26 @@ smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
 }
 
 static int
-smc_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc_ethtool_set_link_ksettings(struct net_device *dev,
+			       const struct ethtool_link_ksettings *cmd)
 {
 	struct smc_local *lp = netdev_priv(dev);
 	int ret;
 
 	if (lp->phy_type != 0) {
 		spin_lock_irq(&lp->lock);
-		ret = mii_ethtool_sset(&lp->mii, cmd);
+		ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irq(&lp->lock);
 	} else {
-		if (cmd->autoneg != AUTONEG_DISABLE ||
-		    cmd->speed != SPEED_10 ||
-		    (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) ||
-		    (cmd->port != PORT_TP && cmd->port != PORT_AUI))
+		if (cmd->base.autoneg != AUTONEG_DISABLE ||
+		    cmd->base.speed != SPEED_10 ||
+		    (cmd->base.duplex != DUPLEX_HALF &&
+		     cmd->base.duplex != DUPLEX_FULL) ||
+		    (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI))
 			return -EINVAL;
 
-//		lp->port = cmd->port;
-		lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL;
+//		lp->port = cmd->base.port;
+		lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
 
 //		if (netif_running(dev))
 //			smc_set_port(dev);
@@ -1744,8 +1747,6 @@ static int smc_ethtool_seteeprom(struct net_device *dev,
 
 
 static const struct ethtool_ops smc_ethtool_ops = {
-	.get_settings	= smc_ethtool_getsettings,
-	.set_settings	= smc_ethtool_setsettings,
 	.get_drvinfo	= smc_ethtool_getdrvinfo,
 
 	.get_msglevel	= smc_ethtool_getmsglevel,
@@ -1755,6 +1756,8 @@ static const struct ethtool_ops smc_ethtool_ops = {
 	.get_eeprom_len = smc_ethtool_geteeprom_len,
 	.get_eeprom	= smc_ethtool_geteeprom,
 	.set_eeprom	= smc_ethtool_seteeprom,
+	.get_link_ksettings	= smc_ethtool_get_link_ksettings,
+	.set_link_ksettings	= smc_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops smc_netdev_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index 01a8c020d6db..e93c40b4631e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -26,12 +26,15 @@
 
 static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)p;
-	unsigned int entry = priv->cur_tx;
-	struct dma_desc *desc = priv->dma_tx + entry;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p;
 	unsigned int nopaged_len = skb_headlen(skb);
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->cur_tx;
 	unsigned int bmax, des2;
 	unsigned int i = 1, len;
+	struct dma_desc *desc;
+
+	desc = tx_q->dma_tx + entry;
 
 	if (priv->plat->enh_desc)
 		bmax = BUF_SIZE_8KiB;
@@ -45,16 +48,16 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 	desc->des2 = cpu_to_le32(des2);
 	if (dma_mapping_error(priv->device, des2))
 		return -1;
-	priv->tx_skbuff_dma[entry].buf = des2;
-	priv->tx_skbuff_dma[entry].len = bmax;
+	tx_q->tx_skbuff_dma[entry].buf = des2;
+	tx_q->tx_skbuff_dma[entry].len = bmax;
 	/* do not close the descriptor and do not set own bit */
 	priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
-					0, false);
+					0, false, skb->len);
 
 	while (len != 0) {
-		priv->tx_skbuff[entry] = NULL;
+		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
-		desc = priv->dma_tx + entry;
+		desc = tx_q->dma_tx + entry;
 
 		if (len > bmax) {
 			des2 = dma_map_single(priv->device,
@@ -63,11 +66,11 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 			desc->des2 = cpu_to_le32(des2);
 			if (dma_mapping_error(priv->device, des2))
 				return -1;
-			priv->tx_skbuff_dma[entry].buf = des2;
-			priv->tx_skbuff_dma[entry].len = bmax;
+			tx_q->tx_skbuff_dma[entry].buf = des2;
+			tx_q->tx_skbuff_dma[entry].len = bmax;
 			priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum,
 							STMMAC_CHAIN_MODE, 1,
-							false);
+							false, skb->len);
 			len -= bmax;
 			i++;
 		} else {
@@ -77,17 +80,17 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 			desc->des2 = cpu_to_le32(des2);
 			if (dma_mapping_error(priv->device, des2))
 				return -1;
-			priv->tx_skbuff_dma[entry].buf = des2;
-			priv->tx_skbuff_dma[entry].len = len;
+			tx_q->tx_skbuff_dma[entry].buf = des2;
+			tx_q->tx_skbuff_dma[entry].len = len;
 			/* last descriptor can be set now */
 			priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
 							STMMAC_CHAIN_MODE, 1,
-							true);
+							true, skb->len);
 			len = 0;
 		}
 	}
 
-	priv->cur_tx = entry;
+	tx_q->cur_tx = entry;
 
 	return entry;
 }
@@ -136,32 +139,34 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr,
 
 static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	if (priv->hwts_rx_en && !priv->extend_desc)
 		/* NOTE: Device will overwrite des3 with timestamp value if
 		 * 1588-2002 time stamping is enabled, hence reinitialize it
 		 * to keep explicit chaining in the descriptor.
 		 */
-		p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy +
-				      (((priv->dirty_rx) + 1) %
+		p->des3 = cpu_to_le32((unsigned int)(rx_q->dma_rx_phy +
+				      (((rx_q->dirty_rx) + 1) %
 				       DMA_RX_SIZE) *
 				      sizeof(struct dma_desc)));
 }
 
 static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
-	unsigned int entry = priv->dirty_tx;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr;
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->dirty_tx;
 
-	if (priv->tx_skbuff_dma[entry].last_segment && !priv->extend_desc &&
+	if (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc &&
 	    priv->hwts_tx_en)
 		/* NOTE: Device will overwrite des3 with timestamp value if
 		 * 1588-2002 time stamping is enabled, hence reinitialize it
 		 * to keep explicit chaining in the descriptor.
 		 */
-		p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy +
-				      ((priv->dirty_tx + 1) % DMA_TX_SIZE))
+		p->des3 = cpu_to_le32((unsigned int)((tx_q->dma_tx_phy +
+				      ((tx_q->dirty_tx + 1) % DMA_TX_SIZE))
 				      * sizeof(struct dma_desc)));
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 04d9245b7149..b7ce3fbb5375 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -246,6 +246,15 @@ struct stmmac_extra_stats {
 #define STMMAC_TX_MAX_FRAMES	256
 #define STMMAC_TX_FRAMES	64
 
+/* Packets types */
+enum packets_types {
+	PACKET_AVCPQ = 0x1, /* AV Untagged Control packets */
+	PACKET_PTPQ = 0x2, /* PTP Packets */
+	PACKET_DCBCPQ = 0x3, /* DCB Control Packets */
+	PACKET_UPQ = 0x4, /* Untagged Packets */
+	PACKET_MCBCQ = 0x5, /* Multicast & Broadcast Packets */
+};
+
 /* Rx IPC status */
 enum rx_frame_status {
 	good_frame = 0x0,
@@ -324,6 +333,9 @@ struct dma_features {
 	unsigned int number_tx_queues;
 	/* Alternate (enhanced) DESC mode */
 	unsigned int enh_desc;
+	/* TX and RX FIFO sizes */
+	unsigned int tx_fifo_size;
+	unsigned int rx_fifo_size;
 };
 
 /* GMAC TX FIFO is 8K, Rx FIFO is 16K */
@@ -361,7 +373,7 @@ struct stmmac_desc_ops {
 	/* Invoked by the xmit function to prepare the tx descriptor */
 	void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len,
 				 bool csum_flag, int mode, bool tx_own,
-				 bool ls);
+				 bool ls, unsigned int tot_pkt_len);
 	void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1,
 				    int len2, bool tx_own, bool ls,
 				    unsigned int tcphdrlen,
@@ -413,6 +425,14 @@ struct stmmac_dma_ops {
 	int (*reset)(void __iomem *ioaddr);
 	void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
 		     u32 dma_tx, u32 dma_rx, int atds);
+	void (*init_chan)(void __iomem *ioaddr,
+			  struct stmmac_dma_cfg *dma_cfg, u32 chan);
+	void (*init_rx_chan)(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_rx_phy, u32 chan);
+	void (*init_tx_chan)(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_tx_phy, u32 chan);
 	/* Configure the AXI Bus Mode Register */
 	void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
 	/* Dump DMA registers */
@@ -421,25 +441,28 @@ struct stmmac_dma_ops {
 	 * An invalid value enables the store-and-forward mode */
 	void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
 			 int rxfifosz);
+	void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
+			    int fifosz);
+	void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel);
 	/* To track extra statistic (if supported) */
 	void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x,
 				   void __iomem *ioaddr);
 	void (*enable_dma_transmission) (void __iomem *ioaddr);
-	void (*enable_dma_irq) (void __iomem *ioaddr);
-	void (*disable_dma_irq) (void __iomem *ioaddr);
-	void (*start_tx) (void __iomem *ioaddr);
-	void (*stop_tx) (void __iomem *ioaddr);
-	void (*start_rx) (void __iomem *ioaddr);
-	void (*stop_rx) (void __iomem *ioaddr);
+	void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan);
+	void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan);
+	void (*start_tx)(void __iomem *ioaddr, u32 chan);
+	void (*stop_tx)(void __iomem *ioaddr, u32 chan);
+	void (*start_rx)(void __iomem *ioaddr, u32 chan);
+	void (*stop_rx)(void __iomem *ioaddr, u32 chan);
 	int (*dma_interrupt) (void __iomem *ioaddr,
-			      struct stmmac_extra_stats *x);
+			      struct stmmac_extra_stats *x, u32 chan);
 	/* If supported then get the optional core features */
 	void (*get_hw_feature)(void __iomem *ioaddr,
 			       struct dma_features *dma_cap);
 	/* Program the HW RX Watchdog */
-	void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt);
-	void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len);
-	void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len);
+	void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan);
+	void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
+	void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
@@ -451,20 +474,44 @@ struct mac_device_info;
 struct stmmac_ops {
 	/* MAC core initialization */
 	void (*core_init)(struct mac_device_info *hw, int mtu);
+	/* Enable the MAC RX/TX */
+	void (*set_mac)(void __iomem *ioaddr, bool enable);
 	/* Enable and verify that the IPC module is supported */
 	int (*rx_ipc)(struct mac_device_info *hw);
 	/* Enable RX Queues */
-	void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue);
+	void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue);
+	/* RX Queues Priority */
+	void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+	/* TX Queues Priority */
+	void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+	/* RX Queues Routing */
+	void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet,
+				 u32 queue);
+	/* Program RX Algorithms */
+	void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg);
+	/* Program TX Algorithms */
+	void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg);
+	/* Set MTL TX queues weight */
+	void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw,
+					u32 weight, u32 queue);
+	/* RX MTL queue to RX dma mapping */
+	void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan);
+	/* Configure AV Algorithm */
+	void (*config_cbs)(struct mac_device_info *hw, u32 send_slope,
+			   u32 idle_slope, u32 high_credit, u32 low_credit,
+			   u32 queue);
 	/* Dump MAC registers */
 	void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space);
 	/* Handle extra events on specific interrupts hw dependent */
 	int (*host_irq_status)(struct mac_device_info *hw,
 			       struct stmmac_extra_stats *x);
+	/* Handle MTL interrupts */
+	int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan);
 	/* Multicast filter setting */
 	void (*set_filter)(struct mac_device_info *hw, struct net_device *dev);
 	/* Flow control setting */
 	void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex,
-			  unsigned int fc, unsigned int pause_time);
+			  unsigned int fc, unsigned int pause_time, u32 tx_cnt);
 	/* Set power management mode (e.g. magic frame) */
 	void (*pmt)(struct mac_device_info *hw, unsigned long mode);
 	/* Set/Get Unicast MAC addresses */
@@ -477,7 +524,8 @@ struct stmmac_ops {
 	void (*reset_eee_mode)(struct mac_device_info *hw);
 	void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
 	void (*set_eee_pls)(struct mac_device_info *hw, int link);
-	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+		      u32 rx_queues, u32 tx_queues);
 	/* PCS calls */
 	void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral,
 			     bool loopback);
@@ -547,6 +595,11 @@ struct mac_device_info {
 	unsigned int ps;
 };
 
+struct stmmac_rx_routing {
+	u32 reg_mask;
+	u32 reg_shift;
+};
+
 struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
 					int perfect_uc_entries,
 					int *synopsys_id);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 1a3fa3d9f855..dd6a2f9791cc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -14,16 +14,34 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/device.h>
+#include <linux/gpio/consumer.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
+#include <linux/reset.h>
 #include <linux/stmmac.h>
 
 #include "stmmac_platform.h"
+#include "dwmac4.h"
+
+struct tegra_eqos {
+	struct device *dev;
+	void __iomem *regs;
+
+	struct reset_control *rst;
+	struct clk *clk_master;
+	struct clk *clk_slave;
+	struct clk *clk_tx;
+	struct clk *clk_rx;
+
+	struct gpio_desc *reset;
+};
 
 static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 				   struct plat_stmmacenet_data *plat_dat)
@@ -106,13 +124,309 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 	return 0;
 }
 
+static void *dwc_qos_probe(struct platform_device *pdev,
+			   struct plat_stmmacenet_data *plat_dat,
+			   struct stmmac_resources *stmmac_res)
+{
+	int err;
+
+	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
+	if (IS_ERR(plat_dat->stmmac_clk)) {
+		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
+		return ERR_CAST(plat_dat->stmmac_clk);
+	}
+
+	err = clk_prepare_enable(plat_dat->stmmac_clk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
+			err);
+		return ERR_PTR(err);
+	}
+
+	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
+	if (IS_ERR(plat_dat->pclk)) {
+		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
+		err = PTR_ERR(plat_dat->pclk);
+		goto disable;
+	}
+
+	err = clk_prepare_enable(plat_dat->pclk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n",
+			err);
+		goto disable;
+	}
+
+	return NULL;
+
+disable:
+	clk_disable_unprepare(plat_dat->stmmac_clk);
+	return ERR_PTR(err);
+}
+
+static int dwc_qos_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	clk_disable_unprepare(priv->plat->pclk);
+	clk_disable_unprepare(priv->plat->stmmac_clk);
+
+	return 0;
+}
+
+#define SDMEMCOMPPADCTRL 0x8800
+#define  SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD BIT(31)
+
+#define AUTO_CAL_CONFIG 0x8804
+#define  AUTO_CAL_CONFIG_START BIT(31)
+#define  AUTO_CAL_CONFIG_ENABLE BIT(29)
+
+#define AUTO_CAL_STATUS 0x880c
+#define  AUTO_CAL_STATUS_ACTIVE BIT(31)
+
+static void tegra_eqos_fix_speed(void *priv, unsigned int speed)
+{
+	struct tegra_eqos *eqos = priv;
+	unsigned long rate = 125000000;
+	bool needs_calibration = false;
+	u32 value;
+	int err;
+
+	switch (speed) {
+	case SPEED_1000:
+		needs_calibration = true;
+		rate = 125000000;
+		break;
+
+	case SPEED_100:
+		needs_calibration = true;
+		rate = 25000000;
+		break;
+
+	case SPEED_10:
+		rate = 2500000;
+		break;
+
+	default:
+		dev_err(eqos->dev, "invalid speed %u\n", speed);
+		break;
+	}
+
+	if (needs_calibration) {
+		/* calibrate */
+		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+		value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+
+		udelay(1);
+
+		value = readl(eqos->regs + AUTO_CAL_CONFIG);
+		value |= AUTO_CAL_CONFIG_START | AUTO_CAL_CONFIG_ENABLE;
+		writel(value, eqos->regs + AUTO_CAL_CONFIG);
+
+		err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+						value,
+						value & AUTO_CAL_STATUS_ACTIVE,
+						1, 10);
+		if (err < 0) {
+			dev_err(eqos->dev, "calibration did not start\n");
+			goto failed;
+		}
+
+		err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+						value,
+						(value & AUTO_CAL_STATUS_ACTIVE) == 0,
+						20, 200);
+		if (err < 0) {
+			dev_err(eqos->dev, "calibration didn't finish\n");
+			goto failed;
+		}
+
+	failed:
+		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+		value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+	} else {
+		value = readl(eqos->regs + AUTO_CAL_CONFIG);
+		value &= ~AUTO_CAL_CONFIG_ENABLE;
+		writel(value, eqos->regs + AUTO_CAL_CONFIG);
+	}
+
+	err = clk_set_rate(eqos->clk_tx, rate);
+	if (err < 0)
+		dev_err(eqos->dev, "failed to set TX rate: %d\n", err);
+}
+
+static int tegra_eqos_init(struct platform_device *pdev, void *priv)
+{
+	struct tegra_eqos *eqos = priv;
+	unsigned long rate;
+	u32 value;
+
+	rate = clk_get_rate(eqos->clk_slave);
+
+	value = (rate / 1000000) - 1;
+	writel(value, eqos->regs + GMAC_1US_TIC_COUNTER);
+
+	return 0;
+}
+
+static void *tegra_eqos_probe(struct platform_device *pdev,
+			      struct plat_stmmacenet_data *data,
+			      struct stmmac_resources *res)
+{
+	struct tegra_eqos *eqos;
+	int err;
+
+	eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL);
+	if (!eqos) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	eqos->dev = &pdev->dev;
+	eqos->regs = res->addr;
+
+	eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus");
+	if (IS_ERR(eqos->clk_master)) {
+		err = PTR_ERR(eqos->clk_master);
+		goto error;
+	}
+
+	err = clk_prepare_enable(eqos->clk_master);
+	if (err < 0)
+		goto error;
+
+	eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus");
+	if (IS_ERR(eqos->clk_slave)) {
+		err = PTR_ERR(eqos->clk_slave);
+		goto disable_master;
+	}
+
+	data->stmmac_clk = eqos->clk_slave;
+
+	err = clk_prepare_enable(eqos->clk_slave);
+	if (err < 0)
+		goto disable_master;
+
+	eqos->clk_rx = devm_clk_get(&pdev->dev, "rx");
+	if (IS_ERR(eqos->clk_rx)) {
+		err = PTR_ERR(eqos->clk_rx);
+		goto disable_slave;
+	}
+
+	err = clk_prepare_enable(eqos->clk_rx);
+	if (err < 0)
+		goto disable_slave;
+
+	eqos->clk_tx = devm_clk_get(&pdev->dev, "tx");
+	if (IS_ERR(eqos->clk_tx)) {
+		err = PTR_ERR(eqos->clk_tx);
+		goto disable_rx;
+	}
+
+	err = clk_prepare_enable(eqos->clk_tx);
+	if (err < 0)
+		goto disable_rx;
+
+	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(eqos->reset)) {
+		err = PTR_ERR(eqos->reset);
+		goto disable_tx;
+	}
+
+	usleep_range(2000, 4000);
+	gpiod_set_value(eqos->reset, 0);
+
+	eqos->rst = devm_reset_control_get(&pdev->dev, "eqos");
+	if (IS_ERR(eqos->rst)) {
+		err = PTR_ERR(eqos->rst);
+		goto reset_phy;
+	}
+
+	err = reset_control_assert(eqos->rst);
+	if (err < 0)
+		goto reset_phy;
+
+	usleep_range(2000, 4000);
+
+	err = reset_control_deassert(eqos->rst);
+	if (err < 0)
+		goto reset_phy;
+
+	usleep_range(2000, 4000);
+
+	data->fix_mac_speed = tegra_eqos_fix_speed;
+	data->init = tegra_eqos_init;
+	data->bsp_priv = eqos;
+
+	err = tegra_eqos_init(pdev, eqos);
+	if (err < 0)
+		goto reset;
+
+out:
+	return eqos;
+
+reset:
+	reset_control_assert(eqos->rst);
+reset_phy:
+	gpiod_set_value(eqos->reset, 1);
+disable_tx:
+	clk_disable_unprepare(eqos->clk_tx);
+disable_rx:
+	clk_disable_unprepare(eqos->clk_rx);
+disable_slave:
+	clk_disable_unprepare(eqos->clk_slave);
+disable_master:
+	clk_disable_unprepare(eqos->clk_master);
+error:
+	eqos = ERR_PTR(err);
+	goto out;
+}
+
+static int tegra_eqos_remove(struct platform_device *pdev)
+{
+	struct tegra_eqos *eqos = get_stmmac_bsp_priv(&pdev->dev);
+
+	reset_control_assert(eqos->rst);
+	gpiod_set_value(eqos->reset, 1);
+	clk_disable_unprepare(eqos->clk_tx);
+	clk_disable_unprepare(eqos->clk_rx);
+	clk_disable_unprepare(eqos->clk_slave);
+	clk_disable_unprepare(eqos->clk_master);
+
+	return 0;
+}
+
+struct dwc_eth_dwmac_data {
+	void *(*probe)(struct platform_device *pdev,
+		       struct plat_stmmacenet_data *data,
+		       struct stmmac_resources *res);
+	int (*remove)(struct platform_device *pdev);
+};
+
+static const struct dwc_eth_dwmac_data dwc_qos_data = {
+	.probe = dwc_qos_probe,
+	.remove = dwc_qos_remove,
+};
+
+static const struct dwc_eth_dwmac_data tegra_eqos_data = {
+	.probe = tegra_eqos_probe,
+	.remove = tegra_eqos_remove,
+};
+
 static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 {
+	const struct dwc_eth_dwmac_data *data;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
 	struct resource *res;
+	void *priv;
 	int ret;
 
+	data = of_device_get_match_data(&pdev->dev);
+
 	memset(&stmmac_res, 0, sizeof(struct stmmac_resources));
 
 	/**
@@ -138,39 +452,26 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
-	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
-	if (IS_ERR(plat_dat->stmmac_clk)) {
-		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
-		ret = PTR_ERR(plat_dat->stmmac_clk);
-		plat_dat->stmmac_clk = NULL;
-		goto err_remove_config_dt;
-	}
-	clk_prepare_enable(plat_dat->stmmac_clk);
-
-	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
-	if (IS_ERR(plat_dat->pclk)) {
-		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
-		ret = PTR_ERR(plat_dat->pclk);
-		plat_dat->pclk = NULL;
-		goto err_out_clk_dis_phy;
+	priv = data->probe(pdev, plat_dat, &stmmac_res);
+	if (IS_ERR(priv)) {
+		ret = PTR_ERR(priv);
+		dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret);
+		goto remove_config;
 	}
-	clk_prepare_enable(plat_dat->pclk);
 
 	ret = dwc_eth_dwmac_config_dt(pdev, plat_dat);
 	if (ret)
-		goto err_out_clk_dis_aper;
+		goto remove;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_out_clk_dis_aper;
+		goto remove;
 
-	return 0;
+	return ret;
 
-err_out_clk_dis_aper:
-	clk_disable_unprepare(plat_dat->pclk);
-err_out_clk_dis_phy:
-	clk_disable_unprepare(plat_dat->stmmac_clk);
-err_remove_config_dt:
+remove:
+	data->remove(pdev);
+remove_config:
 	stmmac_remove_config_dt(pdev, plat_dat);
 
 	return ret;
@@ -178,11 +479,29 @@ err_remove_config_dt:
 
 static int dwc_eth_dwmac_remove(struct platform_device *pdev)
 {
-	return stmmac_pltfr_remove(pdev);
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	const struct dwc_eth_dwmac_data *data;
+	int err;
+
+	data = of_device_get_match_data(&pdev->dev);
+
+	err = stmmac_dvr_remove(&pdev->dev);
+	if (err < 0)
+		dev_err(&pdev->dev, "failed to remove platform: %d\n", err);
+
+	err = data->remove(pdev);
+	if (err < 0)
+		dev_err(&pdev->dev, "failed to remove subdriver: %d\n", err);
+
+	stmmac_remove_config_dt(pdev, priv->plat);
+
+	return err;
 }
 
 static const struct of_device_id dwc_eth_dwmac_match[] = {
-	{ .compatible = "snps,dwc-qos-ethernet-4.10", },
+	{ .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data },
+	{ .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index e5db6ac36235..f0df5193f047 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -74,6 +74,10 @@ struct rk_priv_data {
 #define GRF_BIT(nr)	(BIT(nr) | BIT(nr+16))
 #define GRF_CLR_BIT(nr)	(BIT(nr+16))
 
+#define DELAY_ENABLE(soc, tx, rx) \
+	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
+	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
+
 #define RK3228_GRF_MAC_CON0	0x0900
 #define RK3228_GRF_MAC_CON1	0x0904
 
@@ -115,8 +119,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3228_GMAC_RMII_MODE_CLR |
-		     RK3228_GMAC_RXCLK_DLY_ENABLE |
-		     RK3228_GMAC_TXCLK_DLY_ENABLE);
+		     DELAY_ENABLE(RK3228, tx_delay, rx_delay));
 
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON0,
 		     RK3228_GMAC_CLK_RX_DL_CFG(rx_delay) |
@@ -232,8 +235,7 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3288_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3288_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3,
-		     RK3288_GMAC_RXCLK_DLY_ENABLE |
-		     RK3288_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3288, tx_delay, rx_delay) |
 		     RK3288_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3288_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -460,8 +462,7 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3366_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3366_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON7,
-		     RK3366_GMAC_RXCLK_DLY_ENABLE |
-		     RK3366_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3366, tx_delay, rx_delay) |
 		     RK3366_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3366_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -572,8 +573,7 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3368_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3368_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16,
-		     RK3368_GMAC_RXCLK_DLY_ENABLE |
-		     RK3368_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3368, tx_delay, rx_delay) |
 		     RK3368_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3368_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -684,8 +684,7 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3399_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3399_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON6,
-		     RK3399_GMAC_RXCLK_DLY_ENABLE |
-		     RK3399_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3399, tx_delay, rx_delay) |
 		     RK3399_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3399_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -985,14 +984,29 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 		return ret;
 
 	/*rmii or rgmii*/
-	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII) {
+	switch (bsp_priv->phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
 		dev_info(dev, "init for RGMII\n");
 		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay,
 					    bsp_priv->rx_delay);
-	} else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) {
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		dev_info(dev, "init for RGMII_ID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, 0, 0);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		dev_info(dev, "init for RGMII_RXID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay, 0);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		dev_info(dev, "init for RGMII_TXID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, 0, bsp_priv->rx_delay);
+		break;
+	case PHY_INTERFACE_MODE_RMII:
 		dev_info(dev, "init for RMII\n");
 		bsp_priv->ops->set_to_rmii(bsp_priv);
-	} else {
+		break;
+	default:
 		dev_err(dev, "NO interface defined!\n");
 	}
 
@@ -1022,12 +1036,19 @@ static void rk_fix_speed(void *priv, unsigned int speed)
 	struct rk_priv_data *bsp_priv = priv;
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII)
+	switch (bsp_priv->phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		bsp_priv->ops->set_rgmii_speed(bsp_priv, speed);
-	else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
+		break;
+	case PHY_INTERFACE_MODE_RMII:
 		bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
-	else
+		break;
+	default:
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
+	}
 }
 
 static int rk_gmac_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 19b9b3087099..f3d9305e5f70 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 
 
 static void dwmac1000_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-				unsigned int fc, unsigned int pause_time)
+				unsigned int fc, unsigned int pause_time,
+				u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	/* Set flow such that DZPQ in Mac Register 6 is 0,
@@ -412,7 +413,8 @@ static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
 	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
 }
 
-static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			    u32 rx_queues, u32 tx_queues)
 {
 	u32 value = readl(ioaddr + GMAC_DEBUG);
 
@@ -488,6 +490,7 @@ static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 
 static const struct stmmac_ops dwmac1000_ops = {
 	.core_init = dwmac1000_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac1000_rx_ipc_enable,
 	.dump_regs = dwmac1000_dump_regs,
 	.host_irq_status = dwmac1000_irq_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index d3654a447046..471a9aa6ac94 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -247,7 +247,8 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
 }
 
-static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
+				  u32 number_chan)
 {
 	writel(riwt, ioaddr + DMA_RX_WATCHDOG);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index e370ccec6176..1b3609105484 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct mac_device_info *hw,
 }
 
 static void dwmac100_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-			       unsigned int fc, unsigned int pause_time)
+			       unsigned int fc, unsigned int pause_time,
+			       u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	unsigned int flow = MAC_FLOW_CTRL_ENABLE;
@@ -149,6 +150,7 @@ static void dwmac100_pmt(struct mac_device_info *hw, unsigned long mode)
 
 static const struct stmmac_ops dwmac100_ops = {
 	.core_init = dwmac100_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac100_rx_ipc_enable,
 	.dump_regs = dwmac100_dump_mac_regs,
 	.host_irq_status = dwmac100_irq_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index db45134fddf0..d74cedf2a397 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -22,9 +22,15 @@
 #define GMAC_HASH_TAB_32_63		0x00000014
 #define GMAC_RX_FLOW_CTRL		0x00000090
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
+#define GMAC_TXQ_PRTY_MAP0		0x98
+#define GMAC_TXQ_PRTY_MAP1		0x9C
 #define GMAC_RXQ_CTRL0			0x000000a0
+#define GMAC_RXQ_CTRL1			0x000000a4
+#define GMAC_RXQ_CTRL2			0x000000a8
+#define GMAC_RXQ_CTRL3			0x000000ac
 #define GMAC_INT_STATUS			0x000000b0
 #define GMAC_INT_EN			0x000000b4
+#define GMAC_1US_TIC_COUNTER		0x000000dc
 #define GMAC_PCS_BASE			0x000000e0
 #define GMAC_PHYIF_CONTROL_STATUS	0x000000f8
 #define GMAC_PMT			0x000000c0
@@ -38,6 +44,22 @@
 #define GMAC_ADDR_HIGH(reg)		(0x300 + reg * 8)
 #define GMAC_ADDR_LOW(reg)		(0x304 + reg * 8)
 
+/* RX Queues Routing */
+#define GMAC_RXQCTRL_AVCPQ_MASK		GENMASK(2, 0)
+#define GMAC_RXQCTRL_AVCPQ_SHIFT	0
+#define GMAC_RXQCTRL_PTPQ_MASK		GENMASK(6, 4)
+#define GMAC_RXQCTRL_PTPQ_SHIFT		4
+#define GMAC_RXQCTRL_DCBCPQ_MASK	GENMASK(10, 8)
+#define GMAC_RXQCTRL_DCBCPQ_SHIFT	8
+#define GMAC_RXQCTRL_UPQ_MASK		GENMASK(14, 12)
+#define GMAC_RXQCTRL_UPQ_SHIFT		12
+#define GMAC_RXQCTRL_MCBCQ_MASK		GENMASK(18, 16)
+#define GMAC_RXQCTRL_MCBCQ_SHIFT	16
+#define GMAC_RXQCTRL_MCBCQEN		BIT(20)
+#define GMAC_RXQCTRL_MCBCQEN_SHIFT	20
+#define GMAC_RXQCTRL_TACPQE		BIT(21)
+#define GMAC_RXQCTRL_TACPQE_SHIFT	21
+
 /* MAC Packet Filtering */
 #define GMAC_PACKET_FILTER_PR		BIT(0)
 #define GMAC_PACKET_FILTER_HMC		BIT(2)
@@ -53,6 +75,14 @@
 /* MAC Flow Control RX */
 #define GMAC_RX_FLOW_CTRL_RFE		BIT(0)
 
+/* RX Queues Priorities */
+#define GMAC_RXQCTRL_PSRQX_MASK(x)	GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_RXQCTRL_PSRQX_SHIFT(x)	((x) * 8)
+
+/* TX Queues Priorities */
+#define GMAC_TXQCTRL_PSTQX_MASK(x)	GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_TXQCTRL_PSTQX_SHIFT(x)	((x) * 8)
+
 /* MAC Flow Control TX */
 #define GMAC_TX_FLOW_CTRL_TFE		BIT(1)
 #define GMAC_TX_FLOW_CTRL_PT_SHIFT	16
@@ -148,6 +178,8 @@ enum power_event {
 /* MAC HW features1 bitmap */
 #define GMAC_HW_FEAT_AVSEL		BIT(20)
 #define GMAC_HW_TSOEN			BIT(18)
+#define GMAC_HW_TXFIFOSIZE		GENMASK(10, 6)
+#define GMAC_HW_RXFIFOSIZE		GENMASK(4, 0)
 
 /* MAC HW features2 bitmap */
 #define GMAC_HW_FEAT_TXCHCNT		GENMASK(21, 18)
@@ -161,8 +193,25 @@ enum power_event {
 #define GMAC_HI_REG_AE			BIT(31)
 
 /*  MTL registers */
+#define MTL_OPERATION_MODE		0x00000c00
+#define MTL_OPERATION_SCHALG_MASK	GENMASK(6, 5)
+#define MTL_OPERATION_SCHALG_WRR	(0x0 << 5)
+#define MTL_OPERATION_SCHALG_WFQ	(0x1 << 5)
+#define MTL_OPERATION_SCHALG_DWRR	(0x2 << 5)
+#define MTL_OPERATION_SCHALG_SP		(0x3 << 5)
+#define MTL_OPERATION_RAA		BIT(2)
+#define MTL_OPERATION_RAA_SP		(0x0 << 2)
+#define MTL_OPERATION_RAA_WSP		(0x1 << 2)
+
 #define MTL_INT_STATUS			0x00000c20
-#define MTL_INT_Q0			BIT(0)
+#define MTL_INT_QX(x)			BIT(x)
+
+#define MTL_RXQ_DMA_MAP0		0x00000c30 /* queue 0 to 3 */
+#define MTL_RXQ_DMA_MAP1		0x00000c34 /* queue 4 to 7 */
+#define MTL_RXQ_DMA_Q04MDMACH_MASK	GENMASK(3, 0)
+#define MTL_RXQ_DMA_Q04MDMACH(x)	((x) << 0)
+#define MTL_RXQ_DMA_QXMDMACH_MASK(x)	GENMASK(11 + (8 * ((x) - 1)), 8 * (x))
+#define MTL_RXQ_DMA_QXMDMACH(chan, q)	((chan) << (8 * (q)))
 
 #define MTL_CHAN_BASE_ADDR		0x00000d00
 #define MTL_CHAN_BASE_OFFSET		0x40
@@ -180,6 +229,7 @@ enum power_event {
 #define MTL_OP_MODE_TSF			BIT(1)
 
 #define MTL_OP_MODE_TQS_MASK		GENMASK(24, 16)
+#define MTL_OP_MODE_TQS_SHIFT		16
 
 #define MTL_OP_MODE_TTC_MASK		0x70
 #define MTL_OP_MODE_TTC_SHIFT		4
@@ -193,6 +243,17 @@ enum power_event {
 #define MTL_OP_MODE_TTC_384		(6 << MTL_OP_MODE_TTC_SHIFT)
 #define MTL_OP_MODE_TTC_512		(7 << MTL_OP_MODE_TTC_SHIFT)
 
+#define MTL_OP_MODE_RQS_MASK		GENMASK(29, 20)
+#define MTL_OP_MODE_RQS_SHIFT		20
+
+#define MTL_OP_MODE_RFD_MASK		GENMASK(19, 14)
+#define MTL_OP_MODE_RFD_SHIFT		14
+
+#define MTL_OP_MODE_RFA_MASK		GENMASK(13, 8)
+#define MTL_OP_MODE_RFA_SHIFT		8
+
+#define MTL_OP_MODE_EHFC		BIT(7)
+
 #define MTL_OP_MODE_RTC_MASK		0x18
 #define MTL_OP_MODE_RTC_SHIFT		3
 
@@ -201,6 +262,46 @@ enum power_event {
 #define MTL_OP_MODE_RTC_96		(2 << MTL_OP_MODE_RTC_SHIFT)
 #define MTL_OP_MODE_RTC_128		(3 << MTL_OP_MODE_RTC_SHIFT)
 
+/* MTL ETS Control register */
+#define MTL_ETS_CTRL_BASE_ADDR		0x00000d10
+#define MTL_ETS_CTRL_BASE_OFFSET	0x40
+#define MTL_ETSX_CTRL_BASE_ADDR(x)	(MTL_ETS_CTRL_BASE_ADDR + \
+					((x) * MTL_ETS_CTRL_BASE_OFFSET))
+
+#define MTL_ETS_CTRL_CC			BIT(3)
+#define MTL_ETS_CTRL_AVALG		BIT(2)
+
+/* MTL Queue Quantum Weight */
+#define MTL_TXQ_WEIGHT_BASE_ADDR	0x00000d18
+#define MTL_TXQ_WEIGHT_BASE_OFFSET	0x40
+#define MTL_TXQX_WEIGHT_BASE_ADDR(x)	(MTL_TXQ_WEIGHT_BASE_ADDR + \
+					((x) * MTL_TXQ_WEIGHT_BASE_OFFSET))
+#define MTL_TXQ_WEIGHT_ISCQW_MASK	GENMASK(20, 0)
+
+/* MTL sendSlopeCredit register */
+#define MTL_SEND_SLP_CRED_BASE_ADDR	0x00000d1c
+#define MTL_SEND_SLP_CRED_OFFSET	0x40
+#define MTL_SEND_SLP_CREDX_BASE_ADDR(x)	(MTL_SEND_SLP_CRED_BASE_ADDR + \
+					((x) * MTL_SEND_SLP_CRED_OFFSET))
+
+#define MTL_SEND_SLP_CRED_SSC_MASK	GENMASK(13, 0)
+
+/* MTL hiCredit register */
+#define MTL_HIGH_CRED_BASE_ADDR		0x00000d20
+#define MTL_HIGH_CRED_OFFSET		0x40
+#define MTL_HIGH_CREDX_BASE_ADDR(x)	(MTL_HIGH_CRED_BASE_ADDR + \
+					((x) * MTL_HIGH_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_HC_MASK		GENMASK(28, 0)
+
+/* MTL loCredit register */
+#define MTL_LOW_CRED_BASE_ADDR		0x00000d24
+#define MTL_LOW_CRED_OFFSET		0x40
+#define MTL_LOW_CREDX_BASE_ADDR(x)	(MTL_LOW_CRED_BASE_ADDR + \
+					((x) * MTL_LOW_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_LC_MASK		GENMASK(28, 0)
+
 /*  MTL debug */
 #define MTL_DEBUG_TXSTSFSTS		BIT(5)
 #define MTL_DEBUG_TXFSTS		BIT(4)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 1e79e6529c4a..48793f2e9307 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -59,17 +59,211 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
 	writel(value, ioaddr + GMAC_INT_EN);
 }
 
-static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue)
+static void dwmac4_rx_queue_enable(struct mac_device_info *hw,
+				   u8 mode, u32 queue)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_RXQ_CTRL0);
 
 	value &= GMAC_RX_QUEUE_CLEAR(queue);
-	value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+	if (mode == MTL_QUEUE_AVB)
+		value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+	else if (mode == MTL_QUEUE_DCB)
+		value |= GMAC_RX_DCB_QUEUE_ENABLE(queue);
 
 	writel(value, ioaddr + GMAC_RXQ_CTRL0);
 }
 
+static void dwmac4_rx_queue_priority(struct mac_device_info *hw,
+				     u32 prio, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 base_register;
+	u32 value;
+
+	base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
+
+	value = readl(ioaddr + base_register);
+
+	value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue);
+	value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+						GMAC_RXQCTRL_PSRQX_MASK(queue);
+	writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_priority(struct mac_device_info *hw,
+				     u32 prio, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 base_register;
+	u32 value;
+
+	base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1;
+
+	value = readl(ioaddr + base_register);
+
+	value &= ~GMAC_TXQCTRL_PSTQX_MASK(queue);
+	value |= (prio << GMAC_TXQCTRL_PSTQX_SHIFT(queue)) &
+						GMAC_TXQCTRL_PSTQX_MASK(queue);
+
+	writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_routing(struct mac_device_info *hw,
+				    u8 packet, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	const struct stmmac_rx_routing route_possibilities[] = {
+		{ GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT },
+		{ GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT },
+		{ GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT },
+		{ GMAC_RXQCTRL_UPQ_MASK, GMAC_RXQCTRL_UPQ_SHIFT },
+		{ GMAC_RXQCTRL_MCBCQ_MASK, GMAC_RXQCTRL_MCBCQ_SHIFT },
+	};
+
+	value = readl(ioaddr + GMAC_RXQ_CTRL1);
+
+	/* routing configuration */
+	value &= ~route_possibilities[packet - 1].reg_mask;
+	value |= (queue << route_possibilities[packet-1].reg_shift) &
+		 route_possibilities[packet - 1].reg_mask;
+
+	/* some packets require extra ops */
+	if (packet == PACKET_AVCPQ) {
+		value &= ~GMAC_RXQCTRL_TACPQE;
+		value |= 0x1 << GMAC_RXQCTRL_TACPQE_SHIFT;
+	} else if (packet == PACKET_MCBCQ) {
+		value &= ~GMAC_RXQCTRL_MCBCQEN;
+		value |= 0x1 << GMAC_RXQCTRL_MCBCQEN_SHIFT;
+	}
+
+	writel(value, ioaddr + GMAC_RXQ_CTRL1);
+}
+
+static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw,
+					  u32 rx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+	value &= ~MTL_OPERATION_RAA;
+	switch (rx_alg) {
+	case MTL_RX_ALGORITHM_SP:
+		value |= MTL_OPERATION_RAA_SP;
+		break;
+	case MTL_RX_ALGORITHM_WSP:
+		value |= MTL_OPERATION_RAA_WSP;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + MTL_OPERATION_MODE);
+}
+
+static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw,
+					  u32 tx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+	value &= ~MTL_OPERATION_SCHALG_MASK;
+	switch (tx_alg) {
+	case MTL_TX_ALGORITHM_WRR:
+		value |= MTL_OPERATION_SCHALG_WRR;
+		break;
+	case MTL_TX_ALGORITHM_WFQ:
+		value |= MTL_OPERATION_SCHALG_WFQ;
+		break;
+	case MTL_TX_ALGORITHM_DWRR:
+		value |= MTL_OPERATION_SCHALG_DWRR;
+		break;
+	case MTL_TX_ALGORITHM_SP:
+		value |= MTL_OPERATION_SCHALG_SP;
+		break;
+	default:
+		break;
+	}
+}
+
+static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw,
+					   u32 weight, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+
+	value &= ~MTL_TXQ_WEIGHT_ISCQW_MASK;
+	value |= weight & MTL_TXQ_WEIGHT_ISCQW_MASK;
+	writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+}
+
+static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	if (queue < 4)
+		value = readl(ioaddr + MTL_RXQ_DMA_MAP0);
+	else
+		value = readl(ioaddr + MTL_RXQ_DMA_MAP1);
+
+	if (queue == 0 || queue == 4) {
+		value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK;
+		value |= MTL_RXQ_DMA_Q04MDMACH(chan);
+	} else {
+		value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue);
+		value |= MTL_RXQ_DMA_QXMDMACH(chan, queue);
+	}
+
+	if (queue < 4)
+		writel(value, ioaddr + MTL_RXQ_DMA_MAP0);
+	else
+		writel(value, ioaddr + MTL_RXQ_DMA_MAP1);
+}
+
+static void dwmac4_config_cbs(struct mac_device_info *hw,
+			      u32 send_slope, u32 idle_slope,
+			      u32 high_credit, u32 low_credit, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	pr_debug("Queue %d configured as AVB. Parameters:\n", queue);
+	pr_debug("\tsend_slope: 0x%08x\n", send_slope);
+	pr_debug("\tidle_slope: 0x%08x\n", idle_slope);
+	pr_debug("\thigh_credit: 0x%08x\n", high_credit);
+	pr_debug("\tlow_credit: 0x%08x\n", low_credit);
+
+	/* enable AV algorithm */
+	value = readl(ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+	value |= MTL_ETS_CTRL_AVALG;
+	value |= MTL_ETS_CTRL_CC;
+	writel(value, ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+
+	/* configure send slope */
+	value = readl(ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_SEND_SLP_CRED_SSC_MASK;
+	value |= send_slope & MTL_SEND_SLP_CRED_SSC_MASK;
+	writel(value, ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+
+	/* configure idle slope (same register as tx weight) */
+	dwmac4_set_mtl_tx_queue_weight(hw, idle_slope, queue);
+
+	/* configure high credit */
+	value = readl(ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_HIGH_CRED_HC_MASK;
+	value |= high_credit & MTL_HIGH_CRED_HC_MASK;
+	writel(value, ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+
+	/* configure high credit */
+	value = readl(ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_HIGH_CRED_LC_MASK;
+	value |= low_credit & MTL_HIGH_CRED_LC_MASK;
+	writel(value, ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+}
+
 static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -251,11 +445,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 }
 
 static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-			     unsigned int fc, unsigned int pause_time)
+			     unsigned int fc, unsigned int pause_time,
+			     u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 channel = STMMAC_CHAN0;	/* FIXME */
 	unsigned int flow = 0;
+	u32 queue = 0;
 
 	pr_debug("GMAC Flow-Control:\n");
 	if (fc & FLOW_RX) {
@@ -265,13 +460,18 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 	}
 	if (fc & FLOW_TX) {
 		pr_debug("\tTransmit Flow-Control ON\n");
-		flow |= GMAC_TX_FLOW_CTRL_TFE;
-		writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
 
-		if (duplex) {
+		if (duplex)
 			pr_debug("\tduplex mode: PAUSE %d\n", pause_time);
-			flow |= (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
-			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
+
+		for (queue = 0; queue < tx_cnt; queue++) {
+			flow |= GMAC_TX_FLOW_CTRL_TFE;
+
+			if (duplex)
+				flow |=
+				(pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
+
+			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
 		}
 	}
 }
@@ -325,11 +525,34 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 	}
 }
 
+static int dwmac4_irq_mtl_status(struct mac_device_info *hw, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 mtl_int_qx_status;
+	int ret = 0;
+
+	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
+
+	/* Check MTL Interrupt */
+	if (mtl_int_qx_status & MTL_INT_QX(chan)) {
+		/* read Queue x Interrupt status */
+		u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(chan));
+
+		if (status & MTL_RX_OVERFLOW_INT) {
+			/*  clear Interrupt */
+			writel(status | MTL_RX_OVERFLOW_INT,
+			       ioaddr + MTL_CHAN_INT_CTRL(chan));
+			ret = CORE_IRQ_MTL_RX_OVERFLOW;
+		}
+	}
+
+	return ret;
+}
+
 static int dwmac4_irq_status(struct mac_device_info *hw,
 			     struct stmmac_extra_stats *x)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 mtl_int_qx_status;
 	u32 intr_status;
 	int ret = 0;
 
@@ -348,20 +571,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		x->irq_receive_pmt_irq_n++;
 	}
 
-	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
-	/* Check MTL Interrupt: Currently only one queue is used: Q0. */
-	if (mtl_int_qx_status & MTL_INT_Q0) {
-		/* read Queue 0 Interrupt status */
-		u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-
-		if (status & MTL_RX_OVERFLOW_INT) {
-			/*  clear Interrupt */
-			writel(status | MTL_RX_OVERFLOW_INT,
-			       ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-			ret = CORE_IRQ_MTL_RX_OVERFLOW;
-		}
-	}
-
 	dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x);
 	if (intr_status & PCS_RGSMIIIS_IRQ)
 		dwmac4_phystatus(ioaddr, x);
@@ -369,64 +578,69 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 	return ret;
 }
 
-static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			 u32 rx_queues, u32 tx_queues)
 {
 	u32 value;
-
-	/*  Currently only channel 0 is supported */
-	value = readl(ioaddr + MTL_CHAN_TX_DEBUG(STMMAC_CHAN0));
-
-	if (value & MTL_DEBUG_TXSTSFSTS)
-		x->mtl_tx_status_fifo_full++;
-	if (value & MTL_DEBUG_TXFSTS)
-		x->mtl_tx_fifo_not_empty++;
-	if (value & MTL_DEBUG_TWCSTS)
-		x->mmtl_fifo_ctrl++;
-	if (value & MTL_DEBUG_TRCSTS_MASK) {
-		u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
-			     >> MTL_DEBUG_TRCSTS_SHIFT;
-		if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
-			x->mtl_tx_fifo_read_ctrl_write++;
-		else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
-			x->mtl_tx_fifo_read_ctrl_wait++;
-		else if (trcsts == MTL_DEBUG_TRCSTS_READ)
-			x->mtl_tx_fifo_read_ctrl_read++;
-		else
-			x->mtl_tx_fifo_read_ctrl_idle++;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues; queue++) {
+		value = readl(ioaddr + MTL_CHAN_TX_DEBUG(queue));
+
+		if (value & MTL_DEBUG_TXSTSFSTS)
+			x->mtl_tx_status_fifo_full++;
+		if (value & MTL_DEBUG_TXFSTS)
+			x->mtl_tx_fifo_not_empty++;
+		if (value & MTL_DEBUG_TWCSTS)
+			x->mmtl_fifo_ctrl++;
+		if (value & MTL_DEBUG_TRCSTS_MASK) {
+			u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
+				     >> MTL_DEBUG_TRCSTS_SHIFT;
+			if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
+				x->mtl_tx_fifo_read_ctrl_write++;
+			else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
+				x->mtl_tx_fifo_read_ctrl_wait++;
+			else if (trcsts == MTL_DEBUG_TRCSTS_READ)
+				x->mtl_tx_fifo_read_ctrl_read++;
+			else
+				x->mtl_tx_fifo_read_ctrl_idle++;
+		}
+		if (value & MTL_DEBUG_TXPAUSED)
+			x->mac_tx_in_pause++;
 	}
-	if (value & MTL_DEBUG_TXPAUSED)
-		x->mac_tx_in_pause++;
 
-	value = readl(ioaddr + MTL_CHAN_RX_DEBUG(STMMAC_CHAN0));
+	for (queue = 0; queue < rx_queues; queue++) {
+		value = readl(ioaddr + MTL_CHAN_RX_DEBUG(queue));
 
-	if (value & MTL_DEBUG_RXFSTS_MASK) {
-		u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
-			     >> MTL_DEBUG_RRCSTS_SHIFT;
+		if (value & MTL_DEBUG_RXFSTS_MASK) {
+			u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
+				     >> MTL_DEBUG_RRCSTS_SHIFT;
 
-		if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
-			x->mtl_rx_fifo_fill_level_full++;
-		else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
-			x->mtl_rx_fifo_fill_above_thresh++;
-		else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
-			x->mtl_rx_fifo_fill_below_thresh++;
-		else
-			x->mtl_rx_fifo_fill_level_empty++;
-	}
-	if (value & MTL_DEBUG_RRCSTS_MASK) {
-		u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
-			     MTL_DEBUG_RRCSTS_SHIFT;
-
-		if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
-			x->mtl_rx_fifo_read_ctrl_flush++;
-		else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
-			x->mtl_rx_fifo_read_ctrl_read_data++;
-		else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
-			x->mtl_rx_fifo_read_ctrl_status++;
-		else
-			x->mtl_rx_fifo_read_ctrl_idle++;
+			if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
+				x->mtl_rx_fifo_fill_level_full++;
+			else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
+				x->mtl_rx_fifo_fill_above_thresh++;
+			else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
+				x->mtl_rx_fifo_fill_below_thresh++;
+			else
+				x->mtl_rx_fifo_fill_level_empty++;
+		}
+		if (value & MTL_DEBUG_RRCSTS_MASK) {
+			u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
+				     MTL_DEBUG_RRCSTS_SHIFT;
+
+			if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
+				x->mtl_rx_fifo_read_ctrl_flush++;
+			else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
+				x->mtl_rx_fifo_read_ctrl_read_data++;
+			else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
+				x->mtl_rx_fifo_read_ctrl_status++;
+			else
+				x->mtl_rx_fifo_read_ctrl_idle++;
+		}
+		if (value & MTL_DEBUG_RWCSTS)
+			x->mtl_rx_fifo_ctrl_active++;
 	}
-	if (value & MTL_DEBUG_RWCSTS)
-		x->mtl_rx_fifo_ctrl_active++;
 
 	/* GMAC debug */
 	value = readl(ioaddr + GMAC_DEBUG);
@@ -455,10 +669,51 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 
 static const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.rx_queue_prio = dwmac4_rx_queue_priority,
+	.tx_queue_prio = dwmac4_tx_queue_priority,
+	.rx_queue_routing = dwmac4_tx_queue_routing,
+	.prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+	.map_mtl_to_dma = dwmac4_map_mtl_dma,
+	.config_cbs = dwmac4_config_cbs,
 	.dump_regs = dwmac4_dump_regs,
 	.host_irq_status = dwmac4_irq_status,
+	.host_mtl_irq_status = dwmac4_irq_mtl_status,
+	.flow_ctrl = dwmac4_flow_ctrl,
+	.pmt = dwmac4_pmt,
+	.set_umac_addr = dwmac4_set_umac_addr,
+	.get_umac_addr = dwmac4_get_umac_addr,
+	.set_eee_mode = dwmac4_set_eee_mode,
+	.reset_eee_mode = dwmac4_reset_eee_mode,
+	.set_eee_timer = dwmac4_set_eee_timer,
+	.set_eee_pls = dwmac4_set_eee_pls,
+	.pcs_ctrl_ane = dwmac4_ctrl_ane,
+	.pcs_rane = dwmac4_rane,
+	.pcs_get_adv_lp = dwmac4_get_adv_lp,
+	.debug = dwmac4_debug,
+	.set_filter = dwmac4_set_filter,
+};
+
+static const struct stmmac_ops dwmac410_ops = {
+	.core_init = dwmac4_core_init,
+	.set_mac = stmmac_dwmac4_set_mac,
+	.rx_ipc = dwmac4_rx_ipc_enable,
+	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.rx_queue_prio = dwmac4_rx_queue_priority,
+	.tx_queue_prio = dwmac4_tx_queue_priority,
+	.rx_queue_routing = dwmac4_tx_queue_routing,
+	.prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+	.map_mtl_to_dma = dwmac4_map_mtl_dma,
+	.config_cbs = dwmac4_config_cbs,
+	.dump_regs = dwmac4_dump_regs,
+	.host_irq_status = dwmac4_irq_status,
+	.host_mtl_irq_status = dwmac4_irq_mtl_status,
 	.flow_ctrl = dwmac4_flow_ctrl,
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
@@ -492,8 +747,6 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
 	if (mac->multicast_filter_bins)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
-	mac->mac = &dwmac4_ops;
-
 	mac->link.port = GMAC_CONFIG_PS;
 	mac->link.duplex = GMAC_CONFIG_DM;
 	mac->link.speed = GMAC_CONFIG_FES;
@@ -514,5 +767,10 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
 	else
 		mac->dma = &dwmac4_dma_ops;
 
+	if (*synopsys_id >= DWMAC_CORE_4_00)
+		mac->mac = &dwmac410_ops;
+	else
+		mac->mac = &dwmac4_ops;
+
 	return mac;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 843ec69222ea..aa6476439aee 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -304,12 +304,13 @@ static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end)
 
 static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				      bool csum_flag, int mode, bool tx_own,
-				      bool ls)
+				      bool ls, unsigned int tot_pkt_len)
 {
 	unsigned int tdes3 = le32_to_cpu(p->des3);
 
 	p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK);
 
+	tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK;
 	if (is_fs)
 		tdes3 |= TDES3_FIRST_DESCRIPTOR;
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index f97b0d5d9987..eec8463057fd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -71,36 +71,48 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 	writel(value, ioaddr + DMA_SYS_BUS_MODE);
 }
 
-static void dwmac4_dma_init_channel(void __iomem *ioaddr,
-				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 dma_rx_phy,
-				    u32 channel)
+void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_rx_phy, u32 chan)
 {
 	u32 value;
-	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
-	int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
 
-	/* set PBL for each channels. Currently we affect same configuration
-	 * on each channel
-	 */
-	value = readl(ioaddr + DMA_CHAN_CONTROL(channel));
-	if (dma_cfg->pblx8)
-		value = value | DMA_BUS_MODE_PBL;
-	writel(value, ioaddr + DMA_CHAN_CONTROL(channel));
+	value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
+}
 
-	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(channel));
+void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_tx_phy, u32 chan)
+{
+	u32 value;
+	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+
+	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 	value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(channel));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
-	value = readl(ioaddr + DMA_CHAN_RX_CONTROL(channel));
-	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(channel));
+	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+}
 
-	/* Mask interrupts by writing to CSR7 */
-	writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(channel));
+void dwmac4_dma_init_channel(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+	u32 value;
+
+	/* common channel control register config */
+	value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
+	if (dma_cfg->pblx8)
+		value = value | DMA_BUS_MODE_PBL;
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(channel));
-	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(channel));
+	/* Mask interrupts by writing to CSR7 */
+	writel(DMA_CHAN_INTR_DEFAULT_MASK,
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 static void dwmac4_dma_init(void __iomem *ioaddr,
@@ -108,7 +120,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
 			    u32 dma_tx, u32 dma_rx, int atds)
 {
 	u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
-	int i;
 
 	/* Set the Fixed burst mode */
 	if (dma_cfg->fixed_burst)
@@ -122,9 +133,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
 		value |= DMA_SYS_BUS_AAL;
 
 	writel(value, ioaddr + DMA_SYS_BUS_MODE);
-
-	for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
-		dwmac4_dma_init_channel(ioaddr, dma_cfg, dma_tx, dma_rx, i);
 }
 
 static void _dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 channel,
@@ -174,46 +182,121 @@ static void dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space)
 		_dwmac4_dump_dma_regs(ioaddr, i, reg_space);
 }
 
-static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan)
 {
-	int i;
+	u32 chan;
 
-	for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
-		writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i));
+	for (chan = 0; chan < number_chan; chan++)
+		writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan));
 }
 
-static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
-				    int rxmode, u32 channel)
+static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
+				       u32 channel, int fifosz)
 {
-	u32 mtl_tx_op, mtl_rx_op, mtl_rx_int;
+	unsigned int rqs = fifosz / 256 - 1;
+	u32 mtl_rx_op, mtl_rx_int;
 
-	/* Following code only done for channel 0, other channels not yet
-	 * supported.
-	 */
-	mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+	if (mode == SF_DMA_MODE) {
+		pr_debug("GMAC: enable RX store and forward mode\n");
+		mtl_rx_op |= MTL_OP_MODE_RSF;
+	} else {
+		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode);
+		mtl_rx_op &= ~MTL_OP_MODE_RSF;
+		mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
+		if (mode <= 32)
+			mtl_rx_op |= MTL_OP_MODE_RTC_32;
+		else if (mode <= 64)
+			mtl_rx_op |= MTL_OP_MODE_RTC_64;
+		else if (mode <= 96)
+			mtl_rx_op |= MTL_OP_MODE_RTC_96;
+		else
+			mtl_rx_op |= MTL_OP_MODE_RTC_128;
+	}
+
+	mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK;
+	mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT;
+
+	/* enable flow control only if each channel gets 4 KiB or more FIFO */
+	if (fifosz >= 4096) {
+		unsigned int rfd, rfa;
+
+		mtl_rx_op |= MTL_OP_MODE_EHFC;
+
+		/* Set Threshold for Activating Flow Control to min 2 frames,
+		 * i.e. 1500 * 2 = 3000 bytes.
+		 *
+		 * Set Threshold for Deactivating Flow Control to min 1 frame,
+		 * i.e. 1500 bytes.
+		 */
+		switch (fifosz) {
+		case 4096:
+			/* This violates the above formula because of FIFO size
+			 * limit therefore overflow may occur in spite of this.
+			 */
+			rfd = 0x03; /* Full-2.5K */
+			rfa = 0x01; /* Full-1.5K */
+			break;
+
+		case 8192:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x0a; /* Full-6K */
+			break;
+
+		case 16384:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x12; /* Full-10K */
+			break;
+
+		default:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x1e; /* Full-16K */
+			break;
+		}
+
+		mtl_rx_op &= ~MTL_OP_MODE_RFD_MASK;
+		mtl_rx_op |= rfd << MTL_OP_MODE_RFD_SHIFT;
 
-	if (txmode == SF_DMA_MODE) {
+		mtl_rx_op &= ~MTL_OP_MODE_RFA_MASK;
+		mtl_rx_op |= rfa << MTL_OP_MODE_RFA_SHIFT;
+	}
+
+	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+	/* Enable MTL RX overflow */
+	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
+	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
+	       ioaddr + MTL_CHAN_INT_CTRL(channel));
+}
+
+static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
+				       u32 channel)
+{
+	u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable TX store and forward mode\n");
 		/* Transmit COE type 2 cannot be done in cut-through mode. */
 		mtl_tx_op |= MTL_OP_MODE_TSF;
 	} else {
-		pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode);
+		pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode);
 		mtl_tx_op &= ~MTL_OP_MODE_TSF;
 		mtl_tx_op &= MTL_OP_MODE_TTC_MASK;
 		/* Set the transmit threshold */
-		if (txmode <= 32)
+		if (mode <= 32)
 			mtl_tx_op |= MTL_OP_MODE_TTC_32;
-		else if (txmode <= 64)
+		else if (mode <= 64)
 			mtl_tx_op |= MTL_OP_MODE_TTC_64;
-		else if (txmode <= 96)
+		else if (mode <= 96)
 			mtl_tx_op |= MTL_OP_MODE_TTC_96;
-		else if (txmode <= 128)
+		else if (mode <= 128)
 			mtl_tx_op |= MTL_OP_MODE_TTC_128;
-		else if (txmode <= 192)
+		else if (mode <= 192)
 			mtl_tx_op |= MTL_OP_MODE_TTC_192;
-		else if (txmode <= 256)
+		else if (mode <= 256)
 			mtl_tx_op |= MTL_OP_MODE_TTC_256;
-		else if (txmode <= 384)
+		else if (mode <= 384)
 			mtl_tx_op |= MTL_OP_MODE_TTC_384;
 		else
 			mtl_tx_op |= MTL_OP_MODE_TTC_512;
@@ -230,39 +313,6 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
 	 */
 	mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK;
 	writel(mtl_tx_op, ioaddr +  MTL_CHAN_TX_OP_MODE(channel));
-
-	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	if (rxmode == SF_DMA_MODE) {
-		pr_debug("GMAC: enable RX store and forward mode\n");
-		mtl_rx_op |= MTL_OP_MODE_RSF;
-	} else {
-		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode);
-		mtl_rx_op &= ~MTL_OP_MODE_RSF;
-		mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
-		if (rxmode <= 32)
-			mtl_rx_op |= MTL_OP_MODE_RTC_32;
-		else if (rxmode <= 64)
-			mtl_rx_op |= MTL_OP_MODE_RTC_64;
-		else if (rxmode <= 96)
-			mtl_rx_op |= MTL_OP_MODE_RTC_96;
-		else
-			mtl_rx_op |= MTL_OP_MODE_RTC_128;
-	}
-
-	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	/* Enable MTL RX overflow */
-	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
-	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
-	       ioaddr + MTL_CHAN_INT_CTRL(channel));
-}
-
-static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode,
-				      int rxmode, int rxfifosz)
-{
-	/* Only Channel 0 is actually configured and used */
-	dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0);
 }
 
 static void dwmac4_get_hw_feature(void __iomem *ioaddr,
@@ -294,6 +344,11 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE1);
 	dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20;
 	dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18;
+	/* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by
+	 * shifting and store the sizes in bytes.
+	 */
+	dma_cap->tx_fifo_size = 128 << ((hw_cap & GMAC_HW_TXFIFOSIZE) >> 6);
+	dma_cap->rx_fifo_size = 128 << ((hw_cap & GMAC_HW_RXFIFOSIZE) >> 0);
 	/* MAC HW feature2 */
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE2);
 	/* TX and RX number of channels */
@@ -332,9 +387,13 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
+	.init_chan = dwmac4_dma_init_channel,
+	.init_rx_chan = dwmac4_dma_init_rx_chan,
+	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,
 	.dump_regs = dwmac4_dump_dma_regs,
-	.dma_mode = dwmac4_dma_operation_mode,
+	.dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+	.dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
 	.enable_dma_irq = dwmac4_enable_dma_irq,
 	.disable_dma_irq = dwmac4_disable_dma_irq,
 	.start_tx = dwmac4_dma_start_tx,
@@ -354,9 +413,13 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
+	.init_chan = dwmac4_dma_init_channel,
+	.init_rx_chan = dwmac4_dma_init_rx_chan,
+	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,
 	.dump_regs = dwmac4_dump_dma_regs,
-	.dma_mode = dwmac4_dma_operation_mode,
+	.dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+	.dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
 	.enable_dma_irq = dwmac410_enable_dma_irq,
 	.disable_dma_irq = dwmac4_disable_dma_irq,
 	.start_tx = dwmac4_dma_start_tx,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 1b06df749e2b..8474bf961dd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -185,17 +185,17 @@
 
 int dwmac4_dma_reset(void __iomem *ioaddr);
 void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr);
-void dwmac4_enable_dma_irq(void __iomem *ioaddr);
-void dwmac410_enable_dma_irq(void __iomem *ioaddr);
-void dwmac4_disable_dma_irq(void __iomem *ioaddr);
-void dwmac4_dma_start_tx(void __iomem *ioaddr);
-void dwmac4_dma_stop_tx(void __iomem *ioaddr);
-void dwmac4_dma_start_rx(void __iomem *ioaddr);
-void dwmac4_dma_stop_rx(void __iomem *ioaddr);
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan);
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
-			 struct stmmac_extra_stats *x);
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len);
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len);
+			 struct stmmac_extra_stats *x, u32 chan);
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
 void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index c7326d5b2f43..49f5687879df 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -37,96 +37,96 @@ int dwmac4_dma_reset(void __iomem *ioaddr)
 
 void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
 {
-	writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(0));
+	writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(chan));
 }
 
 void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
 {
-	writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0));
+	writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(chan));
 }
 
-void dwmac4_dma_start_tx(void __iomem *ioaddr)
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value |= DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value |= GMAC_CONFIG_TE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_stop_tx(void __iomem *ioaddr)
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value &= ~DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value &= ~GMAC_CONFIG_TE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_start_rx(void __iomem *ioaddr)
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value |= DMA_CONTROL_SR;
 
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value |= GMAC_CONFIG_RE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_stop_rx(void __iomem *ioaddr)
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value &= ~DMA_CONTROL_SR;
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value &= ~GMAC_CONFIG_RE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
 {
-	writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(STMMAC_CHAN0));
+	writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(chan));
 }
 
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
 {
-	writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0));
+	writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(chan));
 }
 
-void dwmac4_enable_dma_irq(void __iomem *ioaddr)
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr +
-	       DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	       DMA_CHAN_INTR_ENA(chan));
 }
 
-void dwmac410_enable_dma_irq(void __iomem *ioaddr)
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10,
-	       ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
-void dwmac4_disable_dma_irq(void __iomem *ioaddr)
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
-	writel(0, ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	writel(0, ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
-			 struct stmmac_extra_stats *x)
+			 struct stmmac_extra_stats *x, u32 chan)
 {
 	int ret = 0;
 
-	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(0));
+	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
 
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
@@ -153,7 +153,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 		if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
 			u32 value;
 
-			value = readl(ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+			value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
 			/* to schedule NAPI on real RIE event. */
 			if (likely(value & DMA_CHAN_INTR_ENA_RIE)) {
 				x->rx_normal_irq_n++;
@@ -172,7 +172,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 	 * status [21-0] expect reserved bits [5-3]
 	 */
 	writel((intr_status & 0x3fffc7),
-	       ioaddr + DMA_CHAN_STATUS(STMMAC_CHAN0));
+	       ioaddr + DMA_CHAN_STATUS(chan));
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 56e485f79077..9091df86723a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -137,13 +137,14 @@
 #define DMA_CONTROL_FTF		0x00100000	/* Flush transmit FIFO */
 
 void dwmac_enable_dma_transmission(void __iomem *ioaddr);
-void dwmac_enable_dma_irq(void __iomem *ioaddr);
-void dwmac_disable_dma_irq(void __iomem *ioaddr);
-void dwmac_dma_start_tx(void __iomem *ioaddr);
-void dwmac_dma_stop_tx(void __iomem *ioaddr);
-void dwmac_dma_start_rx(void __iomem *ioaddr);
-void dwmac_dma_stop_rx(void __iomem *ioaddr);
-int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan);
+int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			u32 chan);
 int dwmac_dma_reset(void __iomem *ioaddr);
 
 #endif /* __DWMAC_DMA_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index e60bfca2a763..38f94305aab5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -47,38 +47,38 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr)
 	writel(1, ioaddr + DMA_XMT_POLL_DEMAND);
 }
 
-void dwmac_enable_dma_irq(void __iomem *ioaddr)
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
 }
 
-void dwmac_disable_dma_irq(void __iomem *ioaddr)
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(0, ioaddr + DMA_INTR_ENA);
 }
 
-void dwmac_dma_start_tx(void __iomem *ioaddr)
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value |= DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_stop_tx(void __iomem *ioaddr)
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value &= ~DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_start_rx(void __iomem *ioaddr)
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value |= DMA_CONTROL_SR;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_stop_rx(void __iomem *ioaddr)
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value &= ~DMA_CONTROL_SR;
@@ -156,7 +156,7 @@ static void show_rx_process_state(unsigned int status)
 #endif
 
 int dwmac_dma_interrupt(void __iomem *ioaddr,
-			struct stmmac_extra_stats *x)
+			struct stmmac_extra_stats *x, u32 chan)
 {
 	int ret = 0;
 	/* read the status register (CSR5) */
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 323b59ec74a3..7546b3664113 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(struct dma_desc *p, int mode)
 
 static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				     bool csum_flag, int mode, bool tx_own,
-				     bool ls)
+				     bool ls, unsigned int tot_pkt_len)
 {
 	unsigned int tdes0 = le32_to_cpu(p->des0);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index efb818ebd55e..f817f8f36569 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct dma_desc *p, int mode)
 
 static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				  bool csum_flag, int mode, bool tx_own,
-				  bool ls)
+				  bool ls, unsigned int tot_pkt_len)
 {
 	unsigned int tdes1 = le32_to_cpu(p->des1);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index 452f256ff03f..28e4b5d50ce6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -26,16 +26,17 @@
 
 static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)p;
-	unsigned int entry = priv->cur_tx;
-	struct dma_desc *desc;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p;
 	unsigned int nopaged_len = skb_headlen(skb);
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->cur_tx;
 	unsigned int bmax, len, des2;
+	struct dma_desc *desc;
 
 	if (priv->extend_desc)
-		desc = (struct dma_desc *)(priv->dma_etx + entry);
+		desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 	else
-		desc = priv->dma_tx + entry;
+		desc = tx_q->dma_tx + entry;
 
 	if (priv->plat->enh_desc)
 		bmax = BUF_SIZE_8KiB;
@@ -52,48 +53,51 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		if (dma_mapping_error(priv->device, des2))
 			return -1;
 
-		priv->tx_skbuff_dma[entry].buf = des2;
-		priv->tx_skbuff_dma[entry].len = bmax;
-		priv->tx_skbuff_dma[entry].is_jumbo = true;
+		tx_q->tx_skbuff_dma[entry].buf = des2;
+		tx_q->tx_skbuff_dma[entry].len = bmax;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum,
-						STMMAC_RING_MODE, 0, false);
-		priv->tx_skbuff[entry] = NULL;
+						STMMAC_RING_MODE, 0,
+						false, skb->len);
+		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
 		if (priv->extend_desc)
-			desc = (struct dma_desc *)(priv->dma_etx + entry);
+			desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 		else
-			desc = priv->dma_tx + entry;
+			desc = tx_q->dma_tx + entry;
 
 		des2 = dma_map_single(priv->device, skb->data + bmax, len,
 				      DMA_TO_DEVICE);
 		desc->des2 = cpu_to_le32(des2);
 		if (dma_mapping_error(priv->device, des2))
 			return -1;
-		priv->tx_skbuff_dma[entry].buf = des2;
-		priv->tx_skbuff_dma[entry].len = len;
-		priv->tx_skbuff_dma[entry].is_jumbo = true;
+		tx_q->tx_skbuff_dma[entry].buf = des2;
+		tx_q->tx_skbuff_dma[entry].len = len;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
-						STMMAC_RING_MODE, 1, true);
+						STMMAC_RING_MODE, 1,
+						true, skb->len);
 	} else {
 		des2 = dma_map_single(priv->device, skb->data,
 				      nopaged_len, DMA_TO_DEVICE);
 		desc->des2 = cpu_to_le32(des2);
 		if (dma_mapping_error(priv->device, des2))
 			return -1;
-		priv->tx_skbuff_dma[entry].buf = des2;
-		priv->tx_skbuff_dma[entry].len = nopaged_len;
-		priv->tx_skbuff_dma[entry].is_jumbo = true;
+		tx_q->tx_skbuff_dma[entry].buf = des2;
+		tx_q->tx_skbuff_dma[entry].len = nopaged_len;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum,
-						STMMAC_RING_MODE, 0, true);
+						STMMAC_RING_MODE, 0,
+						true, skb->len);
 	}
 
-	priv->cur_tx = entry;
+	tx_q->cur_tx = entry;
 
 	return entry;
 }
@@ -125,12 +129,13 @@ static void stmmac_init_desc3(struct dma_desc *p)
 
 static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
-	unsigned int entry = priv->dirty_tx;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr;
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->dirty_tx;
 
 	/* des3 is only used for jumbo frames tx or time stamping */
-	if (unlikely(priv->tx_skbuff_dma[entry].is_jumbo ||
-		     (priv->tx_skbuff_dma[entry].last_segment &&
+	if (unlikely(tx_q->tx_skbuff_dma[entry].is_jumbo ||
+		     (tx_q->tx_skbuff_dma[entry].last_segment &&
 		      !priv->extend_desc && priv->hwts_tx_en)))
 		p->des3 = 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index cd8fb619b1e9..33efe7038cab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -46,38 +46,51 @@ struct stmmac_tx_info {
 	bool is_jumbo;
 };
 
-struct stmmac_priv {
-	/* Frequently used values are kept adjacent for cache effect */
+/* Frequently used values are kept adjacent for cache effect */
+struct stmmac_tx_queue {
+	u32 queue_index;
+	struct stmmac_priv *priv_data;
 	struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
 	struct dma_desc *dma_tx;
 	struct sk_buff **tx_skbuff;
+	struct stmmac_tx_info *tx_skbuff_dma;
 	unsigned int cur_tx;
 	unsigned int dirty_tx;
+	dma_addr_t dma_tx_phy;
+	u32 tx_tail_addr;
+};
+
+struct stmmac_rx_queue {
+	u32 queue_index;
+	struct stmmac_priv *priv_data;
+	struct dma_extended_desc *dma_erx;
+	struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
+	struct sk_buff **rx_skbuff;
+	dma_addr_t *rx_skbuff_dma;
+	unsigned int cur_rx;
+	unsigned int dirty_rx;
+	u32 rx_zeroc_thresh;
+	dma_addr_t dma_rx_phy;
+	u32 rx_tail_addr;
+	struct napi_struct napi ____cacheline_aligned_in_smp;
+};
+
+struct stmmac_priv {
+	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
-	struct stmmac_tx_info *tx_skbuff_dma;
-	dma_addr_t dma_tx_phy;
+
 	int tx_coalesce;
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
 	struct timer_list txtimer;
 	bool tso;
 
-	struct dma_desc *dma_rx	____cacheline_aligned_in_smp;
-	struct dma_extended_desc *dma_erx;
-	struct sk_buff **rx_skbuff;
-	unsigned int cur_rx;
-	unsigned int dirty_rx;
 	unsigned int dma_buf_sz;
 	unsigned int rx_copybreak;
-	unsigned int rx_zeroc_thresh;
 	u32 rx_riwt;
 	int hwts_rx_en;
-	dma_addr_t *rx_skbuff_dma;
-	dma_addr_t dma_rx_phy;
-
-	struct napi_struct napi ____cacheline_aligned_in_smp;
 
 	void __iomem *ioaddr;
 	struct net_device *dev;
@@ -85,6 +98,12 @@ struct stmmac_priv {
 	struct mac_device_info *hw;
 	spinlock_t lock;
 
+	/* RX Queue */
+	struct stmmac_rx_queue rx_queue[MTL_MAX_RX_QUEUES];
+
+	/* TX Queue */
+	struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES];
+
 	int oldlink;
 	int speed;
 	int oldduplex;
@@ -119,8 +138,6 @@ struct stmmac_priv {
 	spinlock_t ptp_lock;
 	void __iomem *mmcaddr;
 	void __iomem *ptpaddr;
-	u32 rx_tail_addr;
-	u32 tx_tail_addr;
 	u32 mss;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 85d64114e159..16808e48ca1c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
 		      struct ethtool_pauseparam *pause)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	struct phy_device *phy = netdev->phydev;
 	int new_pause = FLOW_OFF;
 
@@ -511,7 +512,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	}
 
 	priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl,
-				 priv->pause);
+				 priv->pause, tx_cnt);
 	return 0;
 }
 
@@ -519,6 +520,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 				 struct ethtool_stats *dummy, u64 *data)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
 	int i, j = 0;
 
 	/* Update the DMA HW counters for dwmac10/100 */
@@ -549,7 +552,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 		if ((priv->hw->mac->debug) &&
 		    (priv->synopsys_id >= DWMAC_CORE_3_50))
 			priv->hw->mac->debug(priv->ioaddr,
-					     (void *)&priv->xstats);
+					     (void *)&priv->xstats,
+					     rx_queues_count, tx_queues_count);
 	}
 	for (i = 0; i < STMMAC_STATS_LEN; i++) {
 		char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset;
@@ -726,6 +730,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 			       struct ethtool_coalesce *ec)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int rx_riwt;
 
 	/* Check not supported parameters  */
@@ -764,7 +769,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 	priv->tx_coal_frames = ec->tx_max_coalesced_frames;
 	priv->tx_coal_timer = ec->tx_coalesce_usecs;
 	priv->rx_riwt = rx_riwt;
-	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt);
+	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4498a3861aa3..cd8c60132390 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -139,6 +139,64 @@ static void stmmac_verify_args(void)
 }
 
 /**
+ * stmmac_disable_all_queues - Disable all queues
+ * @priv: driver private structure
+ */
+static void stmmac_disable_all_queues(struct stmmac_priv *priv)
+{
+	u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < rx_queues_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		napi_disable(&rx_q->napi);
+	}
+}
+
+/**
+ * stmmac_enable_all_queues - Enable all queues
+ * @priv: driver private structure
+ */
+static void stmmac_enable_all_queues(struct stmmac_priv *priv)
+{
+	u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < rx_queues_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		napi_enable(&rx_q->napi);
+	}
+}
+
+/**
+ * stmmac_stop_all_queues - Stop all queues
+ * @priv: driver private structure
+ */
+static void stmmac_stop_all_queues(struct stmmac_priv *priv)
+{
+	u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_cnt; queue++)
+		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
+}
+
+/**
+ * stmmac_start_all_queues - Start all queues
+ * @priv: driver private structure
+ */
+static void stmmac_start_all_queues(struct stmmac_priv *priv)
+{
+	u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_cnt; queue++)
+		netif_tx_start_queue(netdev_get_tx_queue(priv->dev, queue));
+}
+
+/**
  * stmmac_clk_csr_set - dynamically set the MDC clock
  * @priv: driver private structure
  * Description: this is to dynamically set the MDC clock according to the csr
@@ -185,26 +243,33 @@ static void print_pkt(unsigned char *buf, int len)
 	print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, buf, len);
 }
 
-static inline u32 stmmac_tx_avail(struct stmmac_priv *priv)
+static inline u32 stmmac_tx_avail(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	u32 avail;
 
-	if (priv->dirty_tx > priv->cur_tx)
-		avail = priv->dirty_tx - priv->cur_tx - 1;
+	if (tx_q->dirty_tx > tx_q->cur_tx)
+		avail = tx_q->dirty_tx - tx_q->cur_tx - 1;
 	else
-		avail = DMA_TX_SIZE - priv->cur_tx + priv->dirty_tx - 1;
+		avail = DMA_TX_SIZE - tx_q->cur_tx + tx_q->dirty_tx - 1;
 
 	return avail;
 }
 
-static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv)
+/**
+ * stmmac_rx_dirty - Get RX queue dirty
+ * @priv: driver private structure
+ * @queue: RX queue index
+ */
+static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	u32 dirty;
 
-	if (priv->dirty_rx <= priv->cur_rx)
-		dirty = priv->cur_rx - priv->dirty_rx;
+	if (rx_q->dirty_rx <= rx_q->cur_rx)
+		dirty = rx_q->cur_rx - rx_q->dirty_rx;
 	else
-		dirty = DMA_RX_SIZE - priv->dirty_rx + priv->cur_rx;
+		dirty = DMA_RX_SIZE - rx_q->dirty_rx + rx_q->cur_rx;
 
 	return dirty;
 }
@@ -232,9 +297,19 @@ static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv)
  */
 static void stmmac_enable_eee_mode(struct stmmac_priv *priv)
 {
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	/* check if all TX queues have the work finished */
+	for (queue = 0; queue < tx_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		if (tx_q->dirty_tx != tx_q->cur_tx)
+			return; /* still unfinished work */
+	}
+
 	/* Check and enter in LPI mode */
-	if ((priv->dirty_tx == priv->cur_tx) &&
-	    (priv->tx_path_in_lpi_mode == false))
+	if (!priv->tx_path_in_lpi_mode)
 		priv->hw->mac->set_eee_mode(priv->hw,
 					    priv->plat->en_tx_lpi_clockgating);
 }
@@ -673,6 +748,19 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
 }
 
 /**
+ *  stmmac_mac_flow_ctrl - Configure flow control in all queues
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the flow control in all queues
+ */
+static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+
+	priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl,
+				 priv->pause, tx_cnt);
+}
+
+/**
  * stmmac_adjust_link - adjusts the link parameters
  * @dev: net device structure
  * Description: this is the helper called by the physical abstraction layer
@@ -687,7 +775,6 @@ static void stmmac_adjust_link(struct net_device *dev)
 	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	int new_state = 0;
-	unsigned int fc = priv->flow_ctrl, pause_time = priv->pause;
 
 	if (!phydev)
 		return;
@@ -709,8 +796,7 @@ static void stmmac_adjust_link(struct net_device *dev)
 		}
 		/* Flow Control operation */
 		if (phydev->pause)
-			priv->hw->mac->flow_ctrl(priv->hw, phydev->duplex,
-						 fc, pause_time);
+			stmmac_mac_flow_ctrl(priv, phydev->duplex);
 
 		if (phydev->speed != priv->speed) {
 			new_state = 1;
@@ -878,22 +964,56 @@ static int stmmac_init_phy(struct net_device *dev)
 	return 0;
 }
 
-static void stmmac_display_rings(struct stmmac_priv *priv)
+static void stmmac_display_rx_rings(struct stmmac_priv *priv)
 {
-	void *head_rx, *head_tx;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	void *head_rx;
+	u32 queue;
 
-	if (priv->extend_desc) {
-		head_rx = (void *)priv->dma_erx;
-		head_tx = (void *)priv->dma_etx;
-	} else {
-		head_rx = (void *)priv->dma_rx;
-		head_tx = (void *)priv->dma_tx;
+	/* Display RX rings */
+	for (queue = 0; queue < rx_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		pr_info("\tRX Queue %u rings\n", queue);
+
+		if (priv->extend_desc)
+			head_rx = (void *)rx_q->dma_erx;
+		else
+			head_rx = (void *)rx_q->dma_rx;
+
+		/* Display RX ring */
+		priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
+	}
+}
+
+static void stmmac_display_tx_rings(struct stmmac_priv *priv)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	void *head_tx;
+	u32 queue;
+
+	/* Display TX rings */
+	for (queue = 0; queue < tx_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		pr_info("\tTX Queue %d rings\n", queue);
+
+		if (priv->extend_desc)
+			head_tx = (void *)tx_q->dma_etx;
+		else
+			head_tx = (void *)tx_q->dma_tx;
+
+		priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
 	}
+}
+
+static void stmmac_display_rings(struct stmmac_priv *priv)
+{
+	/* Display RX ring */
+	stmmac_display_rx_rings(priv);
 
-	/* Display Rx ring */
-	priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
-	/* Display Tx ring */
-	priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
+	/* Display TX ring */
+	stmmac_display_tx_rings(priv);
 }
 
 static int stmmac_set_bfsize(int mtu, int bufsize)
@@ -913,48 +1033,88 @@ static int stmmac_set_bfsize(int mtu, int bufsize)
 }
 
 /**
- * stmmac_clear_descriptors - clear descriptors
+ * stmmac_clear_rx_descriptors - clear RX descriptors
  * @priv: driver private structure
- * Description: this function is called to clear the tx and rx descriptors
+ * @queue: RX queue index
+ * Description: this function is called to clear the RX descriptors
  * in case of both basic and extended descriptors are used.
  */
-static void stmmac_clear_descriptors(struct stmmac_priv *priv)
+static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	int i;
 
-	/* Clear the Rx/Tx descriptors */
+	/* Clear the RX descriptors */
 	for (i = 0; i < DMA_RX_SIZE; i++)
 		if (priv->extend_desc)
-			priv->hw->desc->init_rx_desc(&priv->dma_erx[i].basic,
+			priv->hw->desc->init_rx_desc(&rx_q->dma_erx[i].basic,
 						     priv->use_riwt, priv->mode,
 						     (i == DMA_RX_SIZE - 1));
 		else
-			priv->hw->desc->init_rx_desc(&priv->dma_rx[i],
+			priv->hw->desc->init_rx_desc(&rx_q->dma_rx[i],
 						     priv->use_riwt, priv->mode,
 						     (i == DMA_RX_SIZE - 1));
+}
+
+/**
+ * stmmac_clear_tx_descriptors - clear tx descriptors
+ * @priv: driver private structure
+ * @queue: TX queue index.
+ * Description: this function is called to clear the TX descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue)
+{
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+	int i;
+
+	/* Clear the TX descriptors */
 	for (i = 0; i < DMA_TX_SIZE; i++)
 		if (priv->extend_desc)
-			priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic,
+			priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic,
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
 		else
-			priv->hw->desc->init_tx_desc(&priv->dma_tx[i],
+			priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i],
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
 }
 
 /**
+ * stmmac_clear_descriptors - clear descriptors
+ * @priv: driver private structure
+ * Description: this function is called to clear the TX and RX descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void stmmac_clear_descriptors(struct stmmac_priv *priv)
+{
+	u32 rx_queue_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_queue_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	/* Clear the RX descriptors */
+	for (queue = 0; queue < rx_queue_cnt; queue++)
+		stmmac_clear_rx_descriptors(priv, queue);
+
+	/* Clear the TX descriptors */
+	for (queue = 0; queue < tx_queue_cnt; queue++)
+		stmmac_clear_tx_descriptors(priv, queue);
+}
+
+/**
  * stmmac_init_rx_buffers - init the RX descriptor buffer.
  * @priv: driver private structure
  * @p: descriptor pointer
  * @i: descriptor index
- * @flags: gfp flag.
+ * @flags: gfp flag
+ * @queue: RX queue index
  * Description: this function is called to allocate a receive buffer, perform
  * the DMA mapping and init the descriptor.
  */
 static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
-				  int i, gfp_t flags)
+				  int i, gfp_t flags, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct sk_buff *skb;
 
 	skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
@@ -963,20 +1123,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 			   "%s: Rx init fails; skb is NULL\n", __func__);
 		return -ENOMEM;
 	}
-	priv->rx_skbuff[i] = skb;
-	priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
+	rx_q->rx_skbuff[i] = skb;
+	rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
 						priv->dma_buf_sz,
 						DMA_FROM_DEVICE);
-	if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) {
+	if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) {
 		netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
 		dev_kfree_skb_any(skb);
 		return -EINVAL;
 	}
 
 	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]);
+		p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
 	else
-		p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]);
+		p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
 
 	if ((priv->hw->mode->init_desc3) &&
 	    (priv->dma_buf_sz == BUF_SIZE_16KiB))
@@ -985,30 +1145,71 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 	return 0;
 }
 
-static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i)
+/**
+ * stmmac_free_rx_buffer - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ * @i: buffer index.
+ */
+static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i)
 {
-	if (priv->rx_skbuff[i]) {
-		dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+	if (rx_q->rx_skbuff[i]) {
+		dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i],
 				 priv->dma_buf_sz, DMA_FROM_DEVICE);
-		dev_kfree_skb_any(priv->rx_skbuff[i]);
+		dev_kfree_skb_any(rx_q->rx_skbuff[i]);
 	}
-	priv->rx_skbuff[i] = NULL;
+	rx_q->rx_skbuff[i] = NULL;
 }
 
 /**
- * init_dma_desc_rings - init the RX/TX descriptor rings
+ * stmmac_free_tx_buffer - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ * @i: buffer index.
+ */
+static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i)
+{
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+	if (tx_q->tx_skbuff_dma[i].buf) {
+		if (tx_q->tx_skbuff_dma[i].map_as_page)
+			dma_unmap_page(priv->device,
+				       tx_q->tx_skbuff_dma[i].buf,
+				       tx_q->tx_skbuff_dma[i].len,
+				       DMA_TO_DEVICE);
+		else
+			dma_unmap_single(priv->device,
+					 tx_q->tx_skbuff_dma[i].buf,
+					 tx_q->tx_skbuff_dma[i].len,
+					 DMA_TO_DEVICE);
+	}
+
+	if (tx_q->tx_skbuff[i]) {
+		dev_kfree_skb_any(tx_q->tx_skbuff[i]);
+		tx_q->tx_skbuff[i] = NULL;
+		tx_q->tx_skbuff_dma[i].buf = 0;
+		tx_q->tx_skbuff_dma[i].map_as_page = false;
+	}
+}
+
+/**
+ * init_dma_rx_desc_rings - init the RX descriptor rings
  * @dev: net device structure
  * @flags: gfp flag.
- * Description: this function initializes the DMA RX/TX descriptors
+ * Description: this function initializes the DMA RX descriptors
  * and allocates the socket buffers. It supports the chained and ring
  * modes.
  */
-static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
+static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
 {
-	int i;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_count = priv->plat->rx_queues_to_use;
 	unsigned int bfsize = 0;
 	int ret = -ENOMEM;
+	u32 queue;
+	int i;
 
 	if (priv->hw->mode->set_16kib_bfsize)
 		bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
@@ -1018,235 +1219,409 @@ static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
 
 	priv->dma_buf_sz = bfsize;
 
-	netif_dbg(priv, probe, priv->dev,
-		  "(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n",
-		  __func__, (u32)priv->dma_rx_phy, (u32)priv->dma_tx_phy);
-
 	/* RX INITIALIZATION */
 	netif_dbg(priv, probe, priv->dev,
 		  "SKB addresses:\nskb\t\tskb data\tdma data\n");
 
-	for (i = 0; i < DMA_RX_SIZE; i++) {
-		struct dma_desc *p;
-		if (priv->extend_desc)
-			p = &((priv->dma_erx + i)->basic);
-		else
-			p = priv->dma_rx + i;
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 
-		ret = stmmac_init_rx_buffers(priv, p, i, flags);
-		if (ret)
-			goto err_init_rx_buffers;
+		netif_dbg(priv, probe, priv->dev,
+			  "(%s) dma_rx_phy=0x%08x\n", __func__,
+			  (u32)rx_q->dma_rx_phy);
 
-		netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
-			  priv->rx_skbuff[i], priv->rx_skbuff[i]->data,
-			  (unsigned int)priv->rx_skbuff_dma[i]);
+		for (i = 0; i < DMA_RX_SIZE; i++) {
+			struct dma_desc *p;
+
+			if (priv->extend_desc)
+				p = &((rx_q->dma_erx + i)->basic);
+			else
+				p = rx_q->dma_rx + i;
+
+			ret = stmmac_init_rx_buffers(priv, p, i, flags,
+						     queue);
+			if (ret)
+				goto err_init_rx_buffers;
+
+			netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
+				  rx_q->rx_skbuff[i], rx_q->rx_skbuff[i]->data,
+				  (unsigned int)rx_q->rx_skbuff_dma[i]);
+		}
+
+		rx_q->cur_rx = 0;
+		rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
+
+		stmmac_clear_rx_descriptors(priv, queue);
+
+		/* Setup the chained descriptor addresses */
+		if (priv->mode == STMMAC_CHAIN_MODE) {
+			if (priv->extend_desc)
+				priv->hw->mode->init(rx_q->dma_erx,
+						     rx_q->dma_rx_phy,
+						     DMA_RX_SIZE, 1);
+			else
+				priv->hw->mode->init(rx_q->dma_rx,
+						     rx_q->dma_rx_phy,
+						     DMA_RX_SIZE, 0);
+		}
 	}
-	priv->cur_rx = 0;
-	priv->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
+
 	buf_sz = bfsize;
 
-	/* Setup the chained descriptor addresses */
-	if (priv->mode == STMMAC_CHAIN_MODE) {
-		if (priv->extend_desc) {
-			priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy,
-					     DMA_RX_SIZE, 1);
-			priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy,
-					     DMA_TX_SIZE, 1);
-		} else {
-			priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy,
-					     DMA_RX_SIZE, 0);
-			priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy,
-					     DMA_TX_SIZE, 0);
-		}
+	return 0;
+
+err_init_rx_buffers:
+	while (queue >= 0) {
+		while (--i >= 0)
+			stmmac_free_rx_buffer(priv, queue, i);
+
+		if (queue == 0)
+			break;
+
+		i = DMA_RX_SIZE;
+		queue--;
 	}
 
-	/* TX INITIALIZATION */
-	for (i = 0; i < DMA_TX_SIZE; i++) {
-		struct dma_desc *p;
-		if (priv->extend_desc)
-			p = &((priv->dma_etx + i)->basic);
-		else
-			p = priv->dma_tx + i;
+	return ret;
+}
 
-		if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-			p->des0 = 0;
-			p->des1 = 0;
-			p->des2 = 0;
-			p->des3 = 0;
-		} else {
-			p->des2 = 0;
+/**
+ * init_dma_tx_desc_rings - init the TX descriptor rings
+ * @dev: net device structure.
+ * Description: this function initializes the DMA TX descriptors
+ * and allocates the socket buffers. It supports the chained and ring
+ * modes.
+ */
+static int init_dma_tx_desc_rings(struct net_device *dev)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_queue_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+	int i;
+
+	for (queue = 0; queue < tx_queue_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		netif_dbg(priv, probe, priv->dev,
+			  "(%s) dma_tx_phy=0x%08x\n", __func__,
+			 (u32)tx_q->dma_tx_phy);
+
+		/* Setup the chained descriptor addresses */
+		if (priv->mode == STMMAC_CHAIN_MODE) {
+			if (priv->extend_desc)
+				priv->hw->mode->init(tx_q->dma_etx,
+						     tx_q->dma_tx_phy,
+						     DMA_TX_SIZE, 1);
+			else
+				priv->hw->mode->init(tx_q->dma_tx,
+						     tx_q->dma_tx_phy,
+						     DMA_TX_SIZE, 0);
+		}
+
+		for (i = 0; i < DMA_TX_SIZE; i++) {
+			struct dma_desc *p;
+			if (priv->extend_desc)
+				p = &((tx_q->dma_etx + i)->basic);
+			else
+				p = tx_q->dma_tx + i;
+
+			if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+				p->des0 = 0;
+				p->des1 = 0;
+				p->des2 = 0;
+				p->des3 = 0;
+			} else {
+				p->des2 = 0;
+			}
+
+			tx_q->tx_skbuff_dma[i].buf = 0;
+			tx_q->tx_skbuff_dma[i].map_as_page = false;
+			tx_q->tx_skbuff_dma[i].len = 0;
+			tx_q->tx_skbuff_dma[i].last_segment = false;
+			tx_q->tx_skbuff[i] = NULL;
 		}
 
-		priv->tx_skbuff_dma[i].buf = 0;
-		priv->tx_skbuff_dma[i].map_as_page = false;
-		priv->tx_skbuff_dma[i].len = 0;
-		priv->tx_skbuff_dma[i].last_segment = false;
-		priv->tx_skbuff[i] = NULL;
+		tx_q->dirty_tx = 0;
+		tx_q->cur_tx = 0;
+
+		netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	priv->dirty_tx = 0;
-	priv->cur_tx = 0;
-	netdev_reset_queue(priv->dev);
+	return 0;
+}
+
+/**
+ * init_dma_desc_rings - init the RX/TX descriptor rings
+ * @dev: net device structure
+ * @flags: gfp flag.
+ * Description: this function initializes the DMA RX/TX descriptors
+ * and allocates the socket buffers. It supports the chained and ring
+ * modes.
+ */
+static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	int ret;
+
+	ret = init_dma_rx_desc_rings(dev, flags);
+	if (ret)
+		return ret;
+
+	ret = init_dma_tx_desc_rings(dev);
 
 	stmmac_clear_descriptors(priv);
 
 	if (netif_msg_hw(priv))
 		stmmac_display_rings(priv);
 
-	return 0;
-err_init_rx_buffers:
-	while (--i >= 0)
-		stmmac_free_rx_buffers(priv, i);
 	return ret;
 }
 
-static void dma_free_rx_skbufs(struct stmmac_priv *priv)
+/**
+ * dma_free_rx_skbufs - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ */
+static void dma_free_rx_skbufs(struct stmmac_priv *priv, u32 queue)
 {
 	int i;
 
 	for (i = 0; i < DMA_RX_SIZE; i++)
-		stmmac_free_rx_buffers(priv, i);
+		stmmac_free_rx_buffer(priv, queue, i);
 }
 
-static void dma_free_tx_skbufs(struct stmmac_priv *priv)
+/**
+ * dma_free_tx_skbufs - free TX dma buffers
+ * @priv: private structure
+ * @queue: TX queue index
+ */
+static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue)
 {
 	int i;
 
-	for (i = 0; i < DMA_TX_SIZE; i++) {
-		if (priv->tx_skbuff_dma[i].buf) {
-			if (priv->tx_skbuff_dma[i].map_as_page)
-				dma_unmap_page(priv->device,
-					       priv->tx_skbuff_dma[i].buf,
-					       priv->tx_skbuff_dma[i].len,
-					       DMA_TO_DEVICE);
-			else
-				dma_unmap_single(priv->device,
-						 priv->tx_skbuff_dma[i].buf,
-						 priv->tx_skbuff_dma[i].len,
-						 DMA_TO_DEVICE);
-		}
+	for (i = 0; i < DMA_TX_SIZE; i++)
+		stmmac_free_tx_buffer(priv, queue, i);
+}
 
-		if (priv->tx_skbuff[i]) {
-			dev_kfree_skb_any(priv->tx_skbuff[i]);
-			priv->tx_skbuff[i] = NULL;
-			priv->tx_skbuff_dma[i].buf = 0;
-			priv->tx_skbuff_dma[i].map_as_page = false;
-		}
+/**
+ * free_dma_rx_desc_resources - free RX dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
+{
+	u32 rx_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+
+	/* Free RX queue resources */
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		/* Release the DMA RX socket buffers */
+		dma_free_rx_skbufs(priv, queue);
+
+		/* Free DMA regions of consistent memory previously allocated */
+		if (!priv->extend_desc)
+			dma_free_coherent(priv->device,
+					  DMA_RX_SIZE * sizeof(struct dma_desc),
+					  rx_q->dma_rx, rx_q->dma_rx_phy);
+		else
+			dma_free_coherent(priv->device, DMA_RX_SIZE *
+					  sizeof(struct dma_extended_desc),
+					  rx_q->dma_erx, rx_q->dma_rx_phy);
+
+		kfree(rx_q->rx_skbuff_dma);
+		kfree(rx_q->rx_skbuff);
 	}
 }
 
 /**
- * alloc_dma_desc_resources - alloc TX/RX resources.
+ * free_dma_tx_desc_resources - free TX dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_tx_desc_resources(struct stmmac_priv *priv)
+{
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 queue = 0;
+
+	/* Free TX queue resources */
+	for (queue = 0; queue < tx_count; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		/* Release the DMA TX socket buffers */
+		dma_free_tx_skbufs(priv, queue);
+
+		/* Free DMA regions of consistent memory previously allocated */
+		if (!priv->extend_desc)
+			dma_free_coherent(priv->device,
+					  DMA_TX_SIZE * sizeof(struct dma_desc),
+					  tx_q->dma_tx, tx_q->dma_tx_phy);
+		else
+			dma_free_coherent(priv->device, DMA_TX_SIZE *
+					  sizeof(struct dma_extended_desc),
+					  tx_q->dma_etx, tx_q->dma_tx_phy);
+
+		kfree(tx_q->tx_skbuff_dma);
+		kfree(tx_q->tx_skbuff);
+	}
+}
+
+/**
+ * alloc_dma_rx_desc_resources - alloc RX resources.
  * @priv: private structure
  * Description: according to which descriptor can be used (extend or basic)
  * this function allocates the resources for TX and RX paths. In case of
  * reception, for example, it pre-allocated the RX socket buffer in order to
  * allow zero-copy mechanism.
  */
-static int alloc_dma_desc_resources(struct stmmac_priv *priv)
+static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
 {
+	u32 rx_count = priv->plat->rx_queues_to_use;
 	int ret = -ENOMEM;
+	u32 queue;
 
-	priv->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, sizeof(dma_addr_t),
-					    GFP_KERNEL);
-	if (!priv->rx_skbuff_dma)
-		return -ENOMEM;
+	/* RX queues buffers and DMA */
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 
-	priv->rx_skbuff = kmalloc_array(DMA_RX_SIZE, sizeof(struct sk_buff *),
-					GFP_KERNEL);
-	if (!priv->rx_skbuff)
-		goto err_rx_skbuff;
-
-	priv->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
-					    sizeof(*priv->tx_skbuff_dma),
-					    GFP_KERNEL);
-	if (!priv->tx_skbuff_dma)
-		goto err_tx_skbuff_dma;
-
-	priv->tx_skbuff = kmalloc_array(DMA_TX_SIZE, sizeof(struct sk_buff *),
-					GFP_KERNEL);
-	if (!priv->tx_skbuff)
-		goto err_tx_skbuff;
-
-	if (priv->extend_desc) {
-		priv->dma_erx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE *
-						    sizeof(struct
-							   dma_extended_desc),
-						    &priv->dma_rx_phy,
-						    GFP_KERNEL);
-		if (!priv->dma_erx)
-			goto err_dma;
+		rx_q->queue_index = queue;
+		rx_q->priv_data = priv;
 
-		priv->dma_etx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE *
-						    sizeof(struct
-							   dma_extended_desc),
-						    &priv->dma_tx_phy,
+		rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE,
+						    sizeof(dma_addr_t),
 						    GFP_KERNEL);
-		if (!priv->dma_etx) {
-			dma_free_coherent(priv->device, DMA_RX_SIZE *
-					  sizeof(struct dma_extended_desc),
-					  priv->dma_erx, priv->dma_rx_phy);
-			goto err_dma;
-		}
-	} else {
-		priv->dma_rx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE *
-						   sizeof(struct dma_desc),
-						   &priv->dma_rx_phy,
-						   GFP_KERNEL);
-		if (!priv->dma_rx)
-			goto err_dma;
+		if (!rx_q->rx_skbuff_dma)
+			return -ENOMEM;
 
-		priv->dma_tx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE *
-						   sizeof(struct dma_desc),
-						   &priv->dma_tx_phy,
-						   GFP_KERNEL);
-		if (!priv->dma_tx) {
-			dma_free_coherent(priv->device, DMA_RX_SIZE *
-					  sizeof(struct dma_desc),
-					  priv->dma_rx, priv->dma_rx_phy);
+		rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE,
+						sizeof(struct sk_buff *),
+						GFP_KERNEL);
+		if (!rx_q->rx_skbuff)
 			goto err_dma;
+
+		if (priv->extend_desc) {
+			rx_q->dma_erx = dma_zalloc_coherent(priv->device,
+							    DMA_RX_SIZE *
+							    sizeof(struct
+							    dma_extended_desc),
+							    &rx_q->dma_rx_phy,
+							    GFP_KERNEL);
+			if (!rx_q->dma_erx)
+				goto err_dma;
+
+		} else {
+			rx_q->dma_rx = dma_zalloc_coherent(priv->device,
+							   DMA_RX_SIZE *
+							   sizeof(struct
+							   dma_desc),
+							   &rx_q->dma_rx_phy,
+							   GFP_KERNEL);
+			if (!rx_q->dma_rx)
+				goto err_dma;
 		}
 	}
 
 	return 0;
 
 err_dma:
-	kfree(priv->tx_skbuff);
-err_tx_skbuff:
-	kfree(priv->tx_skbuff_dma);
-err_tx_skbuff_dma:
-	kfree(priv->rx_skbuff);
-err_rx_skbuff:
-	kfree(priv->rx_skbuff_dma);
+	free_dma_rx_desc_resources(priv);
+
 	return ret;
 }
 
-static void free_dma_desc_resources(struct stmmac_priv *priv)
+/**
+ * alloc_dma_tx_desc_resources - alloc TX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv)
 {
-	/* Release the DMA TX/RX socket buffers */
-	dma_free_rx_skbufs(priv);
-	dma_free_tx_skbufs(priv);
-
-	/* Free DMA regions of consistent memory previously allocated */
-	if (!priv->extend_desc) {
-		dma_free_coherent(priv->device,
-				  DMA_TX_SIZE * sizeof(struct dma_desc),
-				  priv->dma_tx, priv->dma_tx_phy);
-		dma_free_coherent(priv->device,
-				  DMA_RX_SIZE * sizeof(struct dma_desc),
-				  priv->dma_rx, priv->dma_rx_phy);
-	} else {
-		dma_free_coherent(priv->device, DMA_TX_SIZE *
-				  sizeof(struct dma_extended_desc),
-				  priv->dma_etx, priv->dma_tx_phy);
-		dma_free_coherent(priv->device, DMA_RX_SIZE *
-				  sizeof(struct dma_extended_desc),
-				  priv->dma_erx, priv->dma_rx_phy);
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	int ret = -ENOMEM;
+	u32 queue;
+
+	/* TX queues buffers and DMA */
+	for (queue = 0; queue < tx_count; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		tx_q->queue_index = queue;
+		tx_q->priv_data = priv;
+
+		tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
+						    sizeof(*tx_q->tx_skbuff_dma),
+						    GFP_KERNEL);
+		if (!tx_q->tx_skbuff_dma)
+			return -ENOMEM;
+
+		tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE,
+						sizeof(struct sk_buff *),
+						GFP_KERNEL);
+		if (!tx_q->tx_skbuff)
+			goto err_dma_buffers;
+
+		if (priv->extend_desc) {
+			tx_q->dma_etx = dma_zalloc_coherent(priv->device,
+							    DMA_TX_SIZE *
+							    sizeof(struct
+							    dma_extended_desc),
+							    &tx_q->dma_tx_phy,
+							    GFP_KERNEL);
+			if (!tx_q->dma_etx)
+				goto err_dma_buffers;
+		} else {
+			tx_q->dma_tx = dma_zalloc_coherent(priv->device,
+							   DMA_TX_SIZE *
+							   sizeof(struct
+								  dma_desc),
+							   &tx_q->dma_tx_phy,
+							   GFP_KERNEL);
+			if (!tx_q->dma_tx)
+				goto err_dma_buffers;
+		}
 	}
-	kfree(priv->rx_skbuff_dma);
-	kfree(priv->rx_skbuff);
-	kfree(priv->tx_skbuff_dma);
-	kfree(priv->tx_skbuff);
+
+	return 0;
+
+err_dma_buffers:
+	free_dma_tx_desc_resources(priv);
+
+	return ret;
+}
+
+/**
+ * alloc_dma_desc_resources - alloc TX/RX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_desc_resources(struct stmmac_priv *priv)
+{
+	/* RX Allocation */
+	int ret = alloc_dma_rx_desc_resources(priv);
+
+	if (ret)
+		return ret;
+
+	ret = alloc_dma_tx_desc_resources(priv);
+
+	return ret;
+}
+
+/**
+ * free_dma_desc_resources - free dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_desc_resources(struct stmmac_priv *priv)
+{
+	/* Release the DMA RX socket buffers */
+	free_dma_rx_desc_resources(priv);
+
+	/* Release the DMA TX socket buffers */
+	free_dma_tx_desc_resources(priv);
 }
 
 /**
@@ -1256,19 +1631,104 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
  */
 static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
 {
-	int rx_count = priv->dma_cap.number_rx_queues;
-	int queue = 0;
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	int queue;
+	u8 mode;
 
-	/* If GMAC does not have multiple queues, then this is not necessary*/
-	if (rx_count == 1)
-		return;
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		mode = priv->plat->rx_queues_cfg[queue].mode_to_use;
+		priv->hw->mac->rx_queue_enable(priv->hw, mode, queue);
+	}
+}
 
-	/**
-	 *  If the core is synthesized with multiple rx queues / multiple
-	 *  dma channels, then rx queues will be disabled by default.
-	 *  For now only rx queue 0 is enabled.
-	 */
-	priv->hw->mac->rx_queue_enable(priv->hw, queue);
+/**
+ * stmmac_start_rx_dma - start RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This starts a RX DMA channel
+ */
+static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan);
+	priv->hw->dma->start_rx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_start_tx_dma - start TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This starts a TX DMA channel
+ */
+static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan);
+	priv->hw->dma->start_tx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_stop_rx_dma - stop RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This stops a RX DMA channel
+ */
+static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan);
+	priv->hw->dma->stop_rx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_stop_tx_dma - stop TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This stops a TX DMA channel
+ */
+static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan);
+	priv->hw->dma->stop_tx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_start_all_dma - start all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This starts all the RX and TX DMA channels
+ */
+static void stmmac_start_all_dma(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan = 0;
+
+	for (chan = 0; chan < rx_channels_count; chan++)
+		stmmac_start_rx_dma(priv, chan);
+
+	for (chan = 0; chan < tx_channels_count; chan++)
+		stmmac_start_tx_dma(priv, chan);
+}
+
+/**
+ * stmmac_stop_all_dma - stop all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This stops the RX and TX DMA channels
+ */
+static void stmmac_stop_all_dma(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan = 0;
+
+	for (chan = 0; chan < rx_channels_count; chan++)
+		stmmac_stop_rx_dma(priv, chan);
+
+	for (chan = 0; chan < tx_channels_count; chan++)
+		stmmac_stop_tx_dma(priv, chan);
 }
 
 /**
@@ -1279,11 +1739,20 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
  */
 static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 {
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
 	int rxfifosz = priv->plat->rx_fifo_size;
+	u32 txmode = 0;
+	u32 rxmode = 0;
+	u32 chan = 0;
 
-	if (priv->plat->force_thresh_dma_mode)
-		priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz);
-	else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
+	if (rxfifosz == 0)
+		rxfifosz = priv->dma_cap.rx_fifo_size;
+
+	if (priv->plat->force_thresh_dma_mode) {
+		txmode = tc;
+		rxmode = tc;
+	} else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
 		/*
 		 * In case of GMAC, SF mode can be enabled
 		 * to perform the TX COE in HW. This depends on:
@@ -1291,37 +1760,53 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 		 * 2) There is no bugged Jumbo frame support
 		 *    that needs to not insert csum in the TDES.
 		 */
-		priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE,
-					rxfifosz);
+		txmode = SF_DMA_MODE;
+		rxmode = SF_DMA_MODE;
 		priv->xstats.threshold = SF_DMA_MODE;
-	} else
-		priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE,
+	} else {
+		txmode = tc;
+		rxmode = SF_DMA_MODE;
+	}
+
+	/* configure all channels */
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		for (chan = 0; chan < rx_channels_count; chan++)
+			priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+						   rxfifosz);
+
+		for (chan = 0; chan < tx_channels_count; chan++)
+			priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+	} else {
+		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
 					rxfifosz);
+	}
 }
 
 /**
  * stmmac_tx_clean - to manage the transmission completion
  * @priv: driver private structure
+ * @queue: TX queue index
  * Description: it reclaims the transmit resources after transmission completes.
  */
-static void stmmac_tx_clean(struct stmmac_priv *priv)
+static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	unsigned int bytes_compl = 0, pkts_compl = 0;
-	unsigned int entry = priv->dirty_tx;
+	unsigned int entry = tx_q->dirty_tx;
 
 	netif_tx_lock(priv->dev);
 
 	priv->xstats.tx_clean++;
 
-	while (entry != priv->cur_tx) {
-		struct sk_buff *skb = priv->tx_skbuff[entry];
+	while (entry != tx_q->cur_tx) {
+		struct sk_buff *skb = tx_q->tx_skbuff[entry];
 		struct dma_desc *p;
 		int status;
 
 		if (priv->extend_desc)
-			p = (struct dma_desc *)(priv->dma_etx + entry);
+			p = (struct dma_desc *)(tx_q->dma_etx + entry);
 		else
-			p = priv->dma_tx + entry;
+			p = tx_q->dma_tx + entry;
 
 		status = priv->hw->desc->tx_status(&priv->dev->stats,
 						      &priv->xstats, p,
@@ -1342,48 +1827,51 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
 			stmmac_get_tx_hwtstamp(priv, p, skb);
 		}
 
-		if (likely(priv->tx_skbuff_dma[entry].buf)) {
-			if (priv->tx_skbuff_dma[entry].map_as_page)
+		if (likely(tx_q->tx_skbuff_dma[entry].buf)) {
+			if (tx_q->tx_skbuff_dma[entry].map_as_page)
 				dma_unmap_page(priv->device,
-					       priv->tx_skbuff_dma[entry].buf,
-					       priv->tx_skbuff_dma[entry].len,
+					       tx_q->tx_skbuff_dma[entry].buf,
+					       tx_q->tx_skbuff_dma[entry].len,
 					       DMA_TO_DEVICE);
 			else
 				dma_unmap_single(priv->device,
-						 priv->tx_skbuff_dma[entry].buf,
-						 priv->tx_skbuff_dma[entry].len,
+						 tx_q->tx_skbuff_dma[entry].buf,
+						 tx_q->tx_skbuff_dma[entry].len,
 						 DMA_TO_DEVICE);
-			priv->tx_skbuff_dma[entry].buf = 0;
-			priv->tx_skbuff_dma[entry].len = 0;
-			priv->tx_skbuff_dma[entry].map_as_page = false;
+			tx_q->tx_skbuff_dma[entry].buf = 0;
+			tx_q->tx_skbuff_dma[entry].len = 0;
+			tx_q->tx_skbuff_dma[entry].map_as_page = false;
 		}
 
 		if (priv->hw->mode->clean_desc3)
-			priv->hw->mode->clean_desc3(priv, p);
+			priv->hw->mode->clean_desc3(tx_q, p);
 
-		priv->tx_skbuff_dma[entry].last_segment = false;
-		priv->tx_skbuff_dma[entry].is_jumbo = false;
+		tx_q->tx_skbuff_dma[entry].last_segment = false;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = false;
 
 		if (likely(skb != NULL)) {
 			pkts_compl++;
 			bytes_compl += skb->len;
 			dev_consume_skb_any(skb);
-			priv->tx_skbuff[entry] = NULL;
+			tx_q->tx_skbuff[entry] = NULL;
 		}
 
 		priv->hw->desc->release_tx_desc(p, priv->mode);
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 	}
-	priv->dirty_tx = entry;
+	tx_q->dirty_tx = entry;
 
-	netdev_completed_queue(priv->dev, pkts_compl, bytes_compl);
+	netdev_tx_completed_queue(netdev_get_tx_queue(priv->dev, queue),
+				  pkts_compl, bytes_compl);
+
+	if (unlikely(netif_tx_queue_stopped(netdev_get_tx_queue(priv->dev,
+								queue))) &&
+	    stmmac_tx_avail(priv, queue) > STMMAC_TX_THRESH) {
 
-	if (unlikely(netif_queue_stopped(priv->dev) &&
-	    stmmac_tx_avail(priv) > STMMAC_TX_THRESH)) {
 		netif_dbg(priv, tx_done, priv->dev,
 			  "%s: restart transmit\n", __func__);
-		netif_wake_queue(priv->dev);
+		netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
 	if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
@@ -1393,45 +1881,76 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
 	netif_tx_unlock(priv->dev);
 }
 
-static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan)
 {
-	priv->hw->dma->enable_dma_irq(priv->ioaddr);
+	priv->hw->dma->enable_dma_irq(priv->ioaddr, chan);
 }
 
-static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan)
 {
-	priv->hw->dma->disable_dma_irq(priv->ioaddr);
+	priv->hw->dma->disable_dma_irq(priv->ioaddr, chan);
 }
 
 /**
  * stmmac_tx_err - to manage the tx error
  * @priv: driver private structure
+ * @chan: channel index
  * Description: it cleans the descriptors and restarts the transmission
  * in case of transmission errors.
  */
-static void stmmac_tx_err(struct stmmac_priv *priv)
+static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
 	int i;
-	netif_stop_queue(priv->dev);
 
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	dma_free_tx_skbufs(priv);
+	netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, chan));
+
+	stmmac_stop_tx_dma(priv, chan);
+	dma_free_tx_skbufs(priv, chan);
 	for (i = 0; i < DMA_TX_SIZE; i++)
 		if (priv->extend_desc)
-			priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic,
+			priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic,
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
 		else
-			priv->hw->desc->init_tx_desc(&priv->dma_tx[i],
+			priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i],
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
-	priv->dirty_tx = 0;
-	priv->cur_tx = 0;
-	netdev_reset_queue(priv->dev);
-	priv->hw->dma->start_tx(priv->ioaddr);
+	tx_q->dirty_tx = 0;
+	tx_q->cur_tx = 0;
+	netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, chan));
+	stmmac_start_tx_dma(priv, chan);
 
 	priv->dev->stats.tx_errors++;
-	netif_wake_queue(priv->dev);
+	netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, chan));
+}
+
+/**
+ *  stmmac_set_dma_operation_mode - Set DMA operation mode by channel
+ *  @priv: driver private structure
+ *  @txmode: TX operating mode
+ *  @rxmode: RX operating mode
+ *  @chan: channel index
+ *  Description: it is used for configuring of the DMA operation mode in
+ *  runtime in order to program the tx/rx DMA thresholds or Store-And-Forward
+ *  mode.
+ */
+static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
+					  u32 rxmode, u32 chan)
+{
+	int rxfifosz = priv->plat->rx_fifo_size;
+
+	if (rxfifosz == 0)
+		rxfifosz = priv->dma_cap.rx_fifo_size;
+
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+					   rxfifosz);
+		priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+	} else {
+		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
+					rxfifosz);
+	}
 }
 
 /**
@@ -1443,31 +1962,43 @@ static void stmmac_tx_err(struct stmmac_priv *priv)
  */
 static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 {
+	u32 tx_channel_count = priv->plat->tx_queues_to_use;
 	int status;
-	int rxfifosz = priv->plat->rx_fifo_size;
+	u32 chan;
 
-	status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats);
-	if (likely((status & handle_rx)) || (status & handle_tx)) {
-		if (likely(napi_schedule_prep(&priv->napi))) {
-			stmmac_disable_dma_irq(priv);
-			__napi_schedule(&priv->napi);
+	for (chan = 0; chan < tx_channel_count; chan++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];
+
+		status = priv->hw->dma->dma_interrupt(priv->ioaddr,
+						      &priv->xstats, chan);
+		if (likely((status & handle_rx)) || (status & handle_tx)) {
+			if (likely(napi_schedule_prep(&rx_q->napi))) {
+				stmmac_disable_dma_irq(priv, chan);
+				__napi_schedule(&rx_q->napi);
+			}
 		}
-	}
-	if (unlikely(status & tx_hard_error_bump_tc)) {
-		/* Try to bump up the dma threshold on this failure */
-		if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
-		    (tc <= 256)) {
-			tc += 64;
-			if (priv->plat->force_thresh_dma_mode)
-				priv->hw->dma->dma_mode(priv->ioaddr, tc, tc,
-							rxfifosz);
-			else
-				priv->hw->dma->dma_mode(priv->ioaddr, tc,
-							SF_DMA_MODE, rxfifosz);
-			priv->xstats.threshold = tc;
+
+		if (unlikely(status & tx_hard_error_bump_tc)) {
+			/* Try to bump up the dma threshold on this failure */
+			if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
+			    (tc <= 256)) {
+				tc += 64;
+				if (priv->plat->force_thresh_dma_mode)
+					stmmac_set_dma_operation_mode(priv,
+								      tc,
+								      tc,
+								      chan);
+				else
+					stmmac_set_dma_operation_mode(priv,
+								    tc,
+								    SF_DMA_MODE,
+								    chan);
+				priv->xstats.threshold = tc;
+			}
+		} else if (unlikely(status == tx_hard_error)) {
+			stmmac_tx_err(priv, chan);
 		}
-	} else if (unlikely(status == tx_hard_error))
-		stmmac_tx_err(priv);
+	}
 }
 
 /**
@@ -1574,6 +2105,13 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv)
  */
 static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 {
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	struct stmmac_rx_queue *rx_q;
+	struct stmmac_tx_queue *tx_q;
+	u32 dummy_dma_rx_phy = 0;
+	u32 dummy_dma_tx_phy = 0;
+	u32 chan = 0;
 	int atds = 0;
 	int ret = 0;
 
@@ -1591,19 +2129,49 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 		return ret;
 	}
 
-	priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
-			    priv->dma_tx_phy, priv->dma_rx_phy, atds);
-
 	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		priv->rx_tail_addr = priv->dma_rx_phy +
-			    (DMA_RX_SIZE * sizeof(struct dma_desc));
-		priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr,
-					       STMMAC_CHAN0);
+		/* DMA Configuration */
+		priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+				    dummy_dma_tx_phy, dummy_dma_rx_phy, atds);
+
+		/* DMA RX Channel Configuration */
+		for (chan = 0; chan < rx_channels_count; chan++) {
+			rx_q = &priv->rx_queue[chan];
+
+			priv->hw->dma->init_rx_chan(priv->ioaddr,
+						    priv->plat->dma_cfg,
+						    rx_q->dma_rx_phy, chan);
+
+			rx_q->rx_tail_addr = rx_q->dma_rx_phy +
+				    (DMA_RX_SIZE * sizeof(struct dma_desc));
+			priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+						       rx_q->rx_tail_addr,
+						       chan);
+		}
+
+		/* DMA TX Channel Configuration */
+		for (chan = 0; chan < tx_channels_count; chan++) {
+			tx_q = &priv->tx_queue[chan];
+
+			priv->hw->dma->init_chan(priv->ioaddr,
+						 priv->plat->dma_cfg,
+						 chan);
+
+			priv->hw->dma->init_tx_chan(priv->ioaddr,
+						    priv->plat->dma_cfg,
+						    tx_q->dma_tx_phy, chan);
 
-		priv->tx_tail_addr = priv->dma_tx_phy +
-			    (DMA_TX_SIZE * sizeof(struct dma_desc));
-		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-					       STMMAC_CHAN0);
+			tx_q->tx_tail_addr = tx_q->dma_tx_phy +
+				    (DMA_TX_SIZE * sizeof(struct dma_desc));
+			priv->hw->dma->set_tx_tail_ptr(priv->ioaddr,
+						       tx_q->tx_tail_addr,
+						       chan);
+		}
+	} else {
+		rx_q = &priv->rx_queue[chan];
+		tx_q = &priv->tx_queue[chan];
+		priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+				    tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds);
 	}
 
 	if (priv->plat->axi && priv->hw->dma->axi)
@@ -1621,8 +2189,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 static void stmmac_tx_timer(unsigned long data)
 {
 	struct stmmac_priv *priv = (struct stmmac_priv *)data;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue;
 
-	stmmac_tx_clean(priv);
+	/* let's scan all the tx queues */
+	for (queue = 0; queue < tx_queues_count; queue++)
+		stmmac_tx_clean(priv, queue);
 }
 
 /**
@@ -1644,6 +2216,196 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 	add_timer(&priv->txtimer);
 }
 
+static void stmmac_set_rings_length(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan;
+
+	/* set TX ring length */
+	if (priv->hw->dma->set_tx_ring_len) {
+		for (chan = 0; chan < tx_channels_count; chan++)
+			priv->hw->dma->set_tx_ring_len(priv->ioaddr,
+						       (DMA_TX_SIZE - 1), chan);
+	}
+
+	/* set RX ring length */
+	if (priv->hw->dma->set_rx_ring_len) {
+		for (chan = 0; chan < rx_channels_count; chan++)
+			priv->hw->dma->set_rx_ring_len(priv->ioaddr,
+						       (DMA_RX_SIZE - 1), chan);
+	}
+}
+
+/**
+ *  stmmac_set_tx_queue_weight - Set TX queue weight
+ *  @priv: driver private structure
+ *  Description: It is used for setting TX queues weight
+ */
+static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 weight;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_count; queue++) {
+		weight = priv->plat->tx_queues_cfg[queue].weight;
+		priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue);
+	}
+}
+
+/**
+ *  stmmac_configure_cbs - Configure CBS in TX queue
+ *  @priv: driver private structure
+ *  Description: It is used for configuring CBS in AVB TX queues
+ */
+static void stmmac_configure_cbs(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 mode_to_use;
+	u32 queue;
+
+	/* queue 0 is reserved for legacy traffic */
+	for (queue = 1; queue < tx_queues_count; queue++) {
+		mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+		if (mode_to_use == MTL_QUEUE_DCB)
+			continue;
+
+		priv->hw->mac->config_cbs(priv->hw,
+				priv->plat->tx_queues_cfg[queue].send_slope,
+				priv->plat->tx_queues_cfg[queue].idle_slope,
+				priv->plat->tx_queues_cfg[queue].high_credit,
+				priv->plat->tx_queues_cfg[queue].low_credit,
+				queue);
+	}
+}
+
+/**
+ *  stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel
+ *  @priv: driver private structure
+ *  Description: It is used for mapping RX queues to RX dma channels
+ */
+static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u32 chan;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		chan = priv->plat->rx_queues_cfg[queue].chan;
+		priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan);
+	}
+}
+
+/**
+ *  stmmac_mac_config_rx_queues_prio - Configure RX Queue priority
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the RX Queue Priority
+ */
+static void stmmac_mac_config_rx_queues_prio(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u32 prio;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		if (!priv->plat->rx_queues_cfg[queue].use_prio)
+			continue;
+
+		prio = priv->plat->rx_queues_cfg[queue].prio;
+		priv->hw->mac->rx_queue_prio(priv->hw, prio, queue);
+	}
+}
+
+/**
+ *  stmmac_mac_config_tx_queues_prio - Configure TX Queue priority
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the TX Queue Priority
+ */
+static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue;
+	u32 prio;
+
+	for (queue = 0; queue < tx_queues_count; queue++) {
+		if (!priv->plat->tx_queues_cfg[queue].use_prio)
+			continue;
+
+		prio = priv->plat->tx_queues_cfg[queue].prio;
+		priv->hw->mac->tx_queue_prio(priv->hw, prio, queue);
+	}
+}
+
+/**
+ *  stmmac_mac_config_rx_queues_routing - Configure RX Queue Routing
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the RX queue routing
+ */
+static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u8 packet;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		/* no specific packet type routing specified for the queue */
+		if (priv->plat->rx_queues_cfg[queue].pkt_route == 0x0)
+			continue;
+
+		packet = priv->plat->rx_queues_cfg[queue].pkt_route;
+		priv->hw->mac->rx_queue_prio(priv->hw, packet, queue);
+	}
+}
+
+/**
+ *  stmmac_mtl_configuration - Configure MTL
+ *  @priv: driver private structure
+ *  Description: It is used for configurring MTL
+ */
+static void stmmac_mtl_configuration(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+
+	if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight)
+		stmmac_set_tx_queue_weight(priv);
+
+	/* Configure MTL RX algorithms */
+	if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms)
+		priv->hw->mac->prog_mtl_rx_algorithms(priv->hw,
+						priv->plat->rx_sched_algorithm);
+
+	/* Configure MTL TX algorithms */
+	if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms)
+		priv->hw->mac->prog_mtl_tx_algorithms(priv->hw,
+						priv->plat->tx_sched_algorithm);
+
+	/* Configure CBS in AVB TX queues */
+	if (tx_queues_count > 1 && priv->hw->mac->config_cbs)
+		stmmac_configure_cbs(priv);
+
+	/* Map RX MTL to DMA channels */
+	if (priv->hw->mac->map_mtl_to_dma)
+		stmmac_rx_queue_dma_chan_map(priv);
+
+	/* Enable MAC RX Queues */
+	if (priv->hw->mac->rx_queue_enable)
+		stmmac_mac_enable_rx_queues(priv);
+
+	/* Set RX priorities */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_prio)
+		stmmac_mac_config_rx_queues_prio(priv);
+
+	/* Set TX priorities */
+	if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio)
+		stmmac_mac_config_tx_queues_prio(priv);
+
+	/* Set RX routing */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_routing)
+		stmmac_mac_config_rx_queues_routing(priv);
+}
+
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
@@ -1659,6 +2421,9 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 chan;
 	int ret;
 
 	/* DMA initialization and SW reset */
@@ -1688,9 +2453,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	/* Initialize the MAC Core */
 	priv->hw->mac->core_init(priv->hw, dev->mtu);
 
-	/* Initialize MAC RX Queues */
-	if (priv->hw->mac->rx_queue_enable)
-		stmmac_mac_enable_rx_queues(priv);
+	/* Initialize MTL*/
+	if (priv->synopsys_id >= DWMAC_CORE_4_00)
+		stmmac_mtl_configuration(priv);
 
 	ret = priv->hw->mac->rx_ipc(priv->hw);
 	if (!ret) {
@@ -1700,10 +2465,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	}
 
 	/* Enable the MAC Rx/Tx */
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		stmmac_dwmac4_set_mac(priv->ioaddr, true);
-	else
-		stmmac_set_mac(priv->ioaddr, true);
+	priv->hw->mac->set_mac(priv->ioaddr, true);
 
 	/* Set the HW DMA mode and the COE */
 	stmmac_dma_operation_mode(priv);
@@ -1711,6 +2473,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	stmmac_mmc_setup(priv);
 
 	if (init_ptp) {
+		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+		if (ret < 0)
+			netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret);
+
 		ret = stmmac_init_ptp(priv);
 		if (ret == -EOPNOTSUPP)
 			netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -1725,35 +2491,37 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 			    __func__);
 #endif
 	/* Start the ball rolling... */
-	netdev_dbg(priv->dev, "DMA RX/TX processes started...\n");
-	priv->hw->dma->start_tx(priv->ioaddr);
-	priv->hw->dma->start_rx(priv->ioaddr);
+	stmmac_start_all_dma(priv);
 
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
 		priv->rx_riwt = MAX_DMA_RIWT;
-		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT);
+		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt);
 	}
 
 	if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane)
 		priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0);
 
-	/*  set TX ring length */
-	if (priv->hw->dma->set_tx_ring_len)
-		priv->hw->dma->set_tx_ring_len(priv->ioaddr,
-					       (DMA_TX_SIZE - 1));
-	/*  set RX ring length */
-	if (priv->hw->dma->set_rx_ring_len)
-		priv->hw->dma->set_rx_ring_len(priv->ioaddr,
-					       (DMA_RX_SIZE - 1));
+	/* set TX and RX rings length */
+	stmmac_set_rings_length(priv);
+
 	/* Enable TSO */
-	if (priv->tso)
-		priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0);
+	if (priv->tso) {
+		for (chan = 0; chan < tx_cnt; chan++)
+			priv->hw->dma->enable_tso(priv->ioaddr, 1, chan);
+	}
 
 	return 0;
 }
 
+static void stmmac_hw_teardown(struct net_device *dev)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+
+	clk_disable_unprepare(priv->plat->clk_ptp_ref);
+}
+
 /**
  *  stmmac_open - open entry point of the driver
  *  @dev : pointer to the device structure.
@@ -1821,7 +2589,7 @@ static int stmmac_open(struct net_device *dev)
 		netdev_err(priv->dev,
 			   "%s: ERROR: allocating the IRQ %d (error: %d)\n",
 			   __func__, dev->irq, ret);
-		goto init_error;
+		goto irq_error;
 	}
 
 	/* Request the Wake IRQ in case of another line is used for WoL */
@@ -1848,8 +2616,8 @@ static int stmmac_open(struct net_device *dev)
 		}
 	}
 
-	napi_enable(&priv->napi);
-	netif_start_queue(dev);
+	stmmac_enable_all_queues(priv);
+	stmmac_start_all_queues(priv);
 
 	return 0;
 
@@ -1858,7 +2626,12 @@ lpiirq_error:
 		free_irq(priv->wol_irq, dev);
 wolirq_error:
 	free_irq(dev->irq, dev);
+irq_error:
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
+	del_timer_sync(&priv->txtimer);
+	stmmac_hw_teardown(dev);
 init_error:
 	free_dma_desc_resources(priv);
 dma_desc_error:
@@ -1887,9 +2660,9 @@ static int stmmac_release(struct net_device *dev)
 		phy_disconnect(dev->phydev);
 	}
 
-	netif_stop_queue(dev);
+	stmmac_stop_all_queues(priv);
 
-	napi_disable(&priv->napi);
+	stmmac_disable_all_queues(priv);
 
 	del_timer_sync(&priv->txtimer);
 
@@ -1901,14 +2674,13 @@ static int stmmac_release(struct net_device *dev)
 		free_irq(priv->lpi_irq, dev);
 
 	/* Stop TX/RX DMA and clear the descriptors */
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	priv->hw->dma->stop_rx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
 	/* Release and free the Rx/Tx resources */
 	free_dma_desc_resources(priv);
 
 	/* Disable the MAC Rx/Tx */
-	stmmac_set_mac(priv->ioaddr, false);
+	priv->hw->mac->set_mac(priv->ioaddr, false);
 
 	netif_carrier_off(dev);
 
@@ -1927,22 +2699,24 @@ static int stmmac_release(struct net_device *dev)
  *  @des: buffer start address
  *  @total_len: total length to fill in descriptors
  *  @last_segmant: condition for the last descriptor
+ *  @queue: TX queue index
  *  Description:
  *  This function fills descriptor and request new descriptors according to
  *  buffer length to fill
  */
 static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
-				 int total_len, bool last_segment)
+				 int total_len, bool last_segment, u32 queue)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	struct dma_desc *desc;
-	int tmp_len;
 	u32 buff_size;
+	int tmp_len;
 
 	tmp_len = total_len;
 
 	while (tmp_len > 0) {
-		priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
-		desc = priv->dma_tx + priv->cur_tx;
+		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
+		desc = tx_q->dma_tx + tx_q->cur_tx;
 
 		desc->des0 = cpu_to_le32(des + (total_len - tmp_len));
 		buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
@@ -1986,23 +2760,28 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
  */
 static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	u32 pay_len, mss;
-	int tmp_pay_len = 0;
+	struct dma_desc *desc, *first, *mss_desc = NULL;
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int nfrags = skb_shinfo(skb)->nr_frags;
+	u32 queue = skb_get_queue_mapping(skb);
 	unsigned int first_entry, des;
-	struct dma_desc *desc, *first, *mss_desc = NULL;
+	struct stmmac_tx_queue *tx_q;
+	int tmp_pay_len = 0;
+	u32 pay_len, mss;
 	u8 proto_hdr_len;
 	int i;
 
+	tx_q = &priv->tx_queue[queue];
+
 	/* Compute header lengths */
 	proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 
 	/* Desc availability based on threshold should be enough safe */
-	if (unlikely(stmmac_tx_avail(priv) <
+	if (unlikely(stmmac_tx_avail(priv, queue) <
 		(((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) {
-		if (!netif_queue_stopped(dev)) {
-			netif_stop_queue(dev);
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
+			netif_tx_stop_queue(netdev_get_tx_queue(priv->dev,
+								queue));
 			/* This is a hard error, log it. */
 			netdev_err(priv->dev,
 				   "%s: Tx Ring full when queue awake\n",
@@ -2017,10 +2796,10 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* set new MSS value if needed */
 	if (mss != priv->mss) {
-		mss_desc = priv->dma_tx + priv->cur_tx;
+		mss_desc = tx_q->dma_tx + tx_q->cur_tx;
 		priv->hw->desc->set_mss(mss_desc, mss);
 		priv->mss = mss;
-		priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
+		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
 	}
 
 	if (netif_msg_tx_queued(priv)) {
@@ -2030,9 +2809,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 			skb->data_len);
 	}
 
-	first_entry = priv->cur_tx;
+	first_entry = tx_q->cur_tx;
 
-	desc = priv->dma_tx + first_entry;
+	desc = tx_q->dma_tx + first_entry;
 	first = desc;
 
 	/* first descriptor: fill Headers on Buf1 */
@@ -2041,9 +2820,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (dma_mapping_error(priv->device, des))
 		goto dma_map_err;
 
-	priv->tx_skbuff_dma[first_entry].buf = des;
-	priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
-	priv->tx_skbuff[first_entry] = skb;
+	tx_q->tx_skbuff_dma[first_entry].buf = des;
+	tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
+	tx_q->tx_skbuff[first_entry] = skb;
 
 	first->des0 = cpu_to_le32(des);
 
@@ -2054,7 +2833,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* If needed take extra descriptors to fill the remaining payload */
 	tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
 
-	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0));
+	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
 
 	/* Prepare fragments */
 	for (i = 0; i < nfrags; i++) {
@@ -2063,24 +2842,26 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		des = skb_frag_dma_map(priv->device, frag, 0,
 				       skb_frag_size(frag),
 				       DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->device, des))
+			goto dma_map_err;
 
 		stmmac_tso_allocator(priv, des, skb_frag_size(frag),
-				     (i == nfrags - 1));
+				     (i == nfrags - 1), queue);
 
-		priv->tx_skbuff_dma[priv->cur_tx].buf = des;
-		priv->tx_skbuff_dma[priv->cur_tx].len = skb_frag_size(frag);
-		priv->tx_skbuff[priv->cur_tx] = NULL;
-		priv->tx_skbuff_dma[priv->cur_tx].map_as_page = true;
+		tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des;
+		tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag);
+		tx_q->tx_skbuff[tx_q->cur_tx] = NULL;
+		tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true;
 	}
 
-	priv->tx_skbuff_dma[priv->cur_tx].last_segment = true;
+	tx_q->tx_skbuff_dma[tx_q->cur_tx].last_segment = true;
 
-	priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
+	tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
 
-	if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
+	if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) {
 		netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
 			  __func__);
-		netif_stop_queue(dev);
+		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
 	dev->stats.tx_bytes += skb->len;
@@ -2112,7 +2893,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	priv->hw->desc->prepare_tso_tx_desc(first, 1,
 			proto_hdr_len,
 			pay_len,
-			1, priv->tx_skbuff_dma[first_entry].last_segment,
+			1, tx_q->tx_skbuff_dma[first_entry].last_segment,
 			tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len));
 
 	/* If context desc is used to change MSS */
@@ -2127,20 +2908,20 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (netif_msg_pktdata(priv)) {
 		pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n",
-			__func__, priv->cur_tx, priv->dirty_tx, first_entry,
-			priv->cur_tx, first, nfrags);
+			__func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
+			tx_q->cur_tx, first, nfrags);
 
-		priv->hw->desc->display_ring((void *)priv->dma_tx, DMA_TX_SIZE,
+		priv->hw->desc->display_ring((void *)tx_q->dma_tx, DMA_TX_SIZE,
 					     0);
 
 		pr_info(">>> frame to be transmitted: ");
 		print_pkt(skb->data, skb_headlen(skb));
 	}
 
-	netdev_sent_queue(dev, skb->len);
+	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
-	priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-				       STMMAC_CHAN0);
+	priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr,
+				       queue);
 
 	return NETDEV_TX_OK;
 
@@ -2164,21 +2945,26 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_priv *priv = netdev_priv(dev);
 	unsigned int nopaged_len = skb_headlen(skb);
 	int i, csum_insertion = 0, is_jumbo = 0;
+	u32 queue = skb_get_queue_mapping(skb);
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	unsigned int entry, first_entry;
 	struct dma_desc *desc, *first;
+	struct stmmac_tx_queue *tx_q;
 	unsigned int enh_desc;
 	unsigned int des;
 
+	tx_q = &priv->tx_queue[queue];
+
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
 		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
 			return stmmac_tso_xmit(skb, dev);
 	}
 
-	if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
-		if (!netif_queue_stopped(dev)) {
-			netif_stop_queue(dev);
+	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
+			netif_tx_stop_queue(netdev_get_tx_queue(priv->dev,
+								queue));
 			/* This is a hard error, log it. */
 			netdev_err(priv->dev,
 				   "%s: Tx Ring full when queue awake\n",
@@ -2190,19 +2976,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->tx_path_in_lpi_mode)
 		stmmac_disable_eee_mode(priv);
 
-	entry = priv->cur_tx;
+	entry = tx_q->cur_tx;
 	first_entry = entry;
 
 	csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL);
 
 	if (likely(priv->extend_desc))
-		desc = (struct dma_desc *)(priv->dma_etx + entry);
+		desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 	else
-		desc = priv->dma_tx + entry;
+		desc = tx_q->dma_tx + entry;
 
 	first = desc;
 
-	priv->tx_skbuff[first_entry] = skb;
+	tx_q->tx_skbuff[first_entry] = skb;
 
 	enh_desc = priv->plat->enh_desc;
 	/* To program the descriptors according to the size of the frame */
@@ -2211,7 +2997,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(is_jumbo) && likely(priv->synopsys_id <
 					 DWMAC_CORE_4_00)) {
-		entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
+		entry = priv->hw->mode->jumbo_frm(tx_q, skb, csum_insertion);
 		if (unlikely(entry < 0))
 			goto dma_map_err;
 	}
@@ -2224,48 +3010,49 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
 		if (likely(priv->extend_desc))
-			desc = (struct dma_desc *)(priv->dma_etx + entry);
+			desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 		else
-			desc = priv->dma_tx + entry;
+			desc = tx_q->dma_tx + entry;
 
 		des = skb_frag_dma_map(priv->device, frag, 0, len,
 				       DMA_TO_DEVICE);
 		if (dma_mapping_error(priv->device, des))
 			goto dma_map_err; /* should reuse desc w/o issues */
 
-		priv->tx_skbuff[entry] = NULL;
+		tx_q->tx_skbuff[entry] = NULL;
 
-		priv->tx_skbuff_dma[entry].buf = des;
+		tx_q->tx_skbuff_dma[entry].buf = des;
 		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
 			desc->des0 = cpu_to_le32(des);
 		else
 			desc->des2 = cpu_to_le32(des);
 
-		priv->tx_skbuff_dma[entry].map_as_page = true;
-		priv->tx_skbuff_dma[entry].len = len;
-		priv->tx_skbuff_dma[entry].last_segment = last_segment;
+		tx_q->tx_skbuff_dma[entry].map_as_page = true;
+		tx_q->tx_skbuff_dma[entry].len = len;
+		tx_q->tx_skbuff_dma[entry].last_segment = last_segment;
 
 		/* Prepare the descriptor and set the own bit too */
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion,
-						priv->mode, 1, last_segment);
+						priv->mode, 1, last_segment,
+						skb->len);
 	}
 
 	entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
-	priv->cur_tx = entry;
+	tx_q->cur_tx = entry;
 
 	if (netif_msg_pktdata(priv)) {
 		void *tx_head;
 
 		netdev_dbg(priv->dev,
 			   "%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
-			   __func__, priv->cur_tx, priv->dirty_tx, first_entry,
+			   __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
 			   entry, first, nfrags);
 
 		if (priv->extend_desc)
-			tx_head = (void *)priv->dma_etx;
+			tx_head = (void *)tx_q->dma_etx;
 		else
-			tx_head = (void *)priv->dma_tx;
+			tx_head = (void *)tx_q->dma_tx;
 
 		priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false);
 
@@ -2273,10 +3060,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		print_pkt(skb->data, skb->len);
 	}
 
-	if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
+	if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) {
 		netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
 			  __func__);
-		netif_stop_queue(dev);
+		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
 	dev->stats.tx_bytes += skb->len;
@@ -2311,14 +3098,14 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (dma_mapping_error(priv->device, des))
 			goto dma_map_err;
 
-		priv->tx_skbuff_dma[first_entry].buf = des;
+		tx_q->tx_skbuff_dma[first_entry].buf = des;
 		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
 			first->des0 = cpu_to_le32(des);
 		else
 			first->des2 = cpu_to_le32(des);
 
-		priv->tx_skbuff_dma[first_entry].len = nopaged_len;
-		priv->tx_skbuff_dma[first_entry].last_segment = last_segment;
+		tx_q->tx_skbuff_dma[first_entry].len = nopaged_len;
+		tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment;
 
 		if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 			     priv->hwts_tx_en)) {
@@ -2330,7 +3117,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* Prepare the first descriptor setting the OWN bit too */
 		priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len,
 						csum_insertion, priv->mode, 1,
-						last_segment);
+						last_segment, skb->len);
 
 		/* The own bit must be the latest setting done when prepare the
 		 * descriptor and then barrier is needed to make sure that
@@ -2339,13 +3126,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		dma_wmb();
 	}
 
-	netdev_sent_queue(dev, skb->len);
+	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	if (priv->synopsys_id < DWMAC_CORE_4_00)
 		priv->hw->dma->enable_dma_transmission(priv->ioaddr);
 	else
-		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-					       STMMAC_CHAN0);
+		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr,
+					       queue);
 
 	return NETDEV_TX_OK;
 
@@ -2373,9 +3160,9 @@ static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb)
 }
 
 
-static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv)
+static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q)
 {
-	if (priv->rx_zeroc_thresh < STMMAC_RX_THRESH)
+	if (rx_q->rx_zeroc_thresh < STMMAC_RX_THRESH)
 		return 0;
 
 	return 1;
@@ -2384,30 +3171,33 @@ static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv)
 /**
  * stmmac_rx_refill - refill used skb preallocated buffers
  * @priv: driver private structure
+ * @queue: RX queue index
  * Description : this is to reallocate the skb for the reception process
  * that is based on zero-copy.
  */
-static inline void stmmac_rx_refill(struct stmmac_priv *priv)
+static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	int dirty = stmmac_rx_dirty(priv, queue);
+	unsigned int entry = rx_q->dirty_rx;
+
 	int bfsize = priv->dma_buf_sz;
-	unsigned int entry = priv->dirty_rx;
-	int dirty = stmmac_rx_dirty(priv);
 
 	while (dirty-- > 0) {
 		struct dma_desc *p;
 
 		if (priv->extend_desc)
-			p = (struct dma_desc *)(priv->dma_erx + entry);
+			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
-			p = priv->dma_rx + entry;
+			p = rx_q->dma_rx + entry;
 
-		if (likely(priv->rx_skbuff[entry] == NULL)) {
+		if (likely(!rx_q->rx_skbuff[entry])) {
 			struct sk_buff *skb;
 
 			skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
 			if (unlikely(!skb)) {
 				/* so for a while no zero-copy! */
-				priv->rx_zeroc_thresh = STMMAC_RX_THRESH;
+				rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH;
 				if (unlikely(net_ratelimit()))
 					dev_err(priv->device,
 						"fail to alloc skb entry %d\n",
@@ -2415,28 +3205,28 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
 				break;
 			}
 
-			priv->rx_skbuff[entry] = skb;
-			priv->rx_skbuff_dma[entry] =
+			rx_q->rx_skbuff[entry] = skb;
+			rx_q->rx_skbuff_dma[entry] =
 			    dma_map_single(priv->device, skb->data, bfsize,
 					   DMA_FROM_DEVICE);
 			if (dma_mapping_error(priv->device,
-					      priv->rx_skbuff_dma[entry])) {
+					      rx_q->rx_skbuff_dma[entry])) {
 				netdev_err(priv->dev, "Rx DMA map failed\n");
 				dev_kfree_skb(skb);
 				break;
 			}
 
 			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
-				p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
+				p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
 				p->des1 = 0;
 			} else {
-				p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
+				p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
 			}
 			if (priv->hw->mode->refill_desc3)
-				priv->hw->mode->refill_desc3(priv, p);
+				priv->hw->mode->refill_desc3(rx_q, p);
 
-			if (priv->rx_zeroc_thresh > 0)
-				priv->rx_zeroc_thresh--;
+			if (rx_q->rx_zeroc_thresh > 0)
+				rx_q->rx_zeroc_thresh--;
 
 			netif_dbg(priv, rx_status, priv->dev,
 				  "refill entry #%d\n", entry);
@@ -2452,31 +3242,33 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
 	}
-	priv->dirty_rx = entry;
+	rx_q->dirty_rx = entry;
 }
 
 /**
  * stmmac_rx - manage the receive process
  * @priv: driver private structure
- * @limit: napi bugget.
+ * @limit: napi bugget
+ * @queue: RX queue index.
  * Description :  this the function called by the napi poll method.
  * It gets all the frames inside the ring.
  */
-static int stmmac_rx(struct stmmac_priv *priv, int limit)
+static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
-	unsigned int entry = priv->cur_rx;
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	unsigned int entry = rx_q->cur_rx;
+	int coe = priv->hw->rx_csum;
 	unsigned int next_entry;
 	unsigned int count = 0;
-	int coe = priv->hw->rx_csum;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
 
 		netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__);
 		if (priv->extend_desc)
-			rx_head = (void *)priv->dma_erx;
+			rx_head = (void *)rx_q->dma_erx;
 		else
-			rx_head = (void *)priv->dma_rx;
+			rx_head = (void *)rx_q->dma_rx;
 
 		priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true);
 	}
@@ -2486,9 +3278,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 		struct dma_desc *np;
 
 		if (priv->extend_desc)
-			p = (struct dma_desc *)(priv->dma_erx + entry);
+			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
-			p = priv->dma_rx + entry;
+			p = rx_q->dma_rx + entry;
 
 		/* read the status of the incoming frame */
 		status = priv->hw->desc->rx_status(&priv->dev->stats,
@@ -2499,20 +3291,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 
 		count++;
 
-		priv->cur_rx = STMMAC_GET_ENTRY(priv->cur_rx, DMA_RX_SIZE);
-		next_entry = priv->cur_rx;
+		rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE);
+		next_entry = rx_q->cur_rx;
 
 		if (priv->extend_desc)
-			np = (struct dma_desc *)(priv->dma_erx + next_entry);
+			np = (struct dma_desc *)(rx_q->dma_erx + next_entry);
 		else
-			np = priv->dma_rx + next_entry;
+			np = rx_q->dma_rx + next_entry;
 
 		prefetch(np);
 
 		if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status))
 			priv->hw->desc->rx_extended_status(&priv->dev->stats,
 							   &priv->xstats,
-							   priv->dma_erx +
+							   rx_q->dma_erx +
 							   entry);
 		if (unlikely(status == discard_frame)) {
 			priv->dev->stats.rx_errors++;
@@ -2522,9 +3314,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 				 * them in stmmac_rx_refill() function so that
 				 * device can reuse it.
 				 */
-				priv->rx_skbuff[entry] = NULL;
+				rx_q->rx_skbuff[entry] = NULL;
 				dma_unmap_single(priv->device,
-						 priv->rx_skbuff_dma[entry],
+						 rx_q->rx_skbuff_dma[entry],
 						 priv->dma_buf_sz,
 						 DMA_FROM_DEVICE);
 			}
@@ -2572,7 +3364,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 			 */
 			if (unlikely(!priv->plat->has_gmac4 &&
 				     ((frame_len < priv->rx_copybreak) ||
-				     stmmac_rx_threshold_count(priv)))) {
+				     stmmac_rx_threshold_count(rx_q)))) {
 				skb = netdev_alloc_skb_ip_align(priv->dev,
 								frame_len);
 				if (unlikely(!skb)) {
@@ -2584,21 +3376,21 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 				}
 
 				dma_sync_single_for_cpu(priv->device,
-							priv->rx_skbuff_dma
+							rx_q->rx_skbuff_dma
 							[entry], frame_len,
 							DMA_FROM_DEVICE);
 				skb_copy_to_linear_data(skb,
-							priv->
+							rx_q->
 							rx_skbuff[entry]->data,
 							frame_len);
 
 				skb_put(skb, frame_len);
 				dma_sync_single_for_device(priv->device,
-							   priv->rx_skbuff_dma
+							   rx_q->rx_skbuff_dma
 							   [entry], frame_len,
 							   DMA_FROM_DEVICE);
 			} else {
-				skb = priv->rx_skbuff[entry];
+				skb = rx_q->rx_skbuff[entry];
 				if (unlikely(!skb)) {
 					netdev_err(priv->dev,
 						   "%s: Inconsistent Rx chain\n",
@@ -2607,12 +3399,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 					break;
 				}
 				prefetch(skb->data - NET_IP_ALIGN);
-				priv->rx_skbuff[entry] = NULL;
-				priv->rx_zeroc_thresh++;
+				rx_q->rx_skbuff[entry] = NULL;
+				rx_q->rx_zeroc_thresh++;
 
 				skb_put(skb, frame_len);
 				dma_unmap_single(priv->device,
-						 priv->rx_skbuff_dma[entry],
+						 rx_q->rx_skbuff_dma[entry],
 						 priv->dma_buf_sz,
 						 DMA_FROM_DEVICE);
 			}
@@ -2634,7 +3426,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 			else
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-			napi_gro_receive(&priv->napi, skb);
+			napi_gro_receive(&rx_q->napi, skb);
 
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
@@ -2642,7 +3434,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 		entry = next_entry;
 	}
 
-	stmmac_rx_refill(priv);
+	stmmac_rx_refill(priv, queue);
 
 	priv->xstats.rx_pkt_n += count;
 
@@ -2659,16 +3451,24 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
  */
 static int stmmac_poll(struct napi_struct *napi, int budget)
 {
-	struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi);
+	struct stmmac_rx_queue *rx_q =
+		container_of(napi, struct stmmac_rx_queue, napi);
+	struct stmmac_priv *priv = rx_q->priv_data;
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 chan = rx_q->queue_index;
 	int work_done = 0;
+	u32 queue;
 
 	priv->xstats.napi_poll++;
-	stmmac_tx_clean(priv);
 
-	work_done = stmmac_rx(priv, budget);
+	/* check all the queues */
+	for (queue = 0; queue < tx_count; queue++)
+		stmmac_tx_clean(priv, queue);
+
+	work_done = stmmac_rx(priv, budget, rx_q->queue_index);
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-		stmmac_enable_dma_irq(priv);
+		stmmac_enable_dma_irq(priv, chan);
 	}
 	return work_done;
 }
@@ -2684,9 +3484,12 @@ static int stmmac_poll(struct napi_struct *napi, int budget)
 static void stmmac_tx_timeout(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 chan;
 
 	/* Clear Tx resources and restart transmitting again */
-	stmmac_tx_err(priv);
+	for (chan = 0; chan < tx_count; chan++)
+		stmmac_tx_err(priv, chan);
 }
 
 /**
@@ -2795,6 +3598,12 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 {
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queues_count;
+	u32 queue;
+
+	queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt;
 
 	if (priv->irq_wake)
 		pm_wakeup_event(priv->device, 0);
@@ -2808,16 +3617,30 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
 		int status = priv->hw->mac->host_irq_status(priv->hw,
 							    &priv->xstats);
+
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
 			if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
-				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
-							priv->rx_tail_addr,
-							STMMAC_CHAN0);
+		}
+
+		if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+			for (queue = 0; queue < queues_count; queue++) {
+				struct stmmac_rx_queue *rx_q =
+				&priv->rx_queue[queue];
+
+				status |=
+				priv->hw->mac->host_mtl_irq_status(priv->hw,
+								   queue);
+
+				if (status & CORE_IRQ_MTL_RX_OVERFLOW &&
+				    priv->hw->dma->set_rx_tail_ptr)
+					priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+								rx_q->rx_tail_addr,
+								queue);
+			}
 		}
 
 		/* PCS link status */
@@ -2915,17 +3738,40 @@ static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v)
 {
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_count = priv->plat->rx_queues_to_use;
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 queue;
 
-	if (priv->extend_desc) {
-		seq_printf(seq, "Extended RX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_erx, DMA_RX_SIZE, 1, seq);
-		seq_printf(seq, "Extended TX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_etx, DMA_TX_SIZE, 1, seq);
-	} else {
-		seq_printf(seq, "RX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_rx, DMA_RX_SIZE, 0, seq);
-		seq_printf(seq, "TX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_tx, DMA_TX_SIZE, 0, seq);
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		seq_printf(seq, "RX Queue %d:\n", queue);
+
+		if (priv->extend_desc) {
+			seq_printf(seq, "Extended descriptor ring:\n");
+			sysfs_display_ring((void *)rx_q->dma_erx,
+					   DMA_RX_SIZE, 1, seq);
+		} else {
+			seq_printf(seq, "Descriptor ring:\n");
+			sysfs_display_ring((void *)rx_q->dma_rx,
+					   DMA_RX_SIZE, 0, seq);
+		}
+	}
+
+	for (queue = 0; queue < tx_count; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		seq_printf(seq, "TX Queue %d:\n", queue);
+
+		if (priv->extend_desc) {
+			seq_printf(seq, "Extended descriptor ring:\n");
+			sysfs_display_ring((void *)tx_q->dma_etx,
+					   DMA_TX_SIZE, 1, seq);
+		} else {
+			seq_printf(seq, "Descriptor ring:\n");
+			sysfs_display_ring((void *)tx_q->dma_tx,
+					   DMA_TX_SIZE, 0, seq);
+		}
 	}
 
 	return 0;
@@ -3208,11 +4054,14 @@ int stmmac_dvr_probe(struct device *device,
 		     struct plat_stmmacenet_data *plat_dat,
 		     struct stmmac_resources *res)
 {
-	int ret = 0;
 	struct net_device *ndev = NULL;
 	struct stmmac_priv *priv;
+	int ret = 0;
+	u32 queue;
 
-	ndev = alloc_etherdev(sizeof(struct stmmac_priv));
+	ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv),
+				  MTL_MAX_TX_QUEUES,
+				  MTL_MAX_RX_QUEUES);
 	if (!ndev)
 		return -ENOMEM;
 
@@ -3254,6 +4103,10 @@ int stmmac_dvr_probe(struct device *device,
 	if (ret)
 		goto error_hw_init;
 
+	/* Configure real RX and TX queues */
+	netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
+	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
+
 	ndev->netdev_ops = &stmmac_netdev_ops;
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -3303,7 +4156,12 @@ int stmmac_dvr_probe(struct device *device,
 			 "Enable RX Mitigation via HW Watchdog Timer\n");
 	}
 
-	netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
+	for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		netif_napi_add(ndev, &rx_q->napi, stmmac_poll,
+			       (8 * priv->plat->rx_queues_to_use));
+	}
 
 	spin_lock_init(&priv->lock);
 
@@ -3348,7 +4206,11 @@ error_netdev_register:
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
 		stmmac_mdio_unregister(ndev);
 error_mdio_register:
-	netif_napi_del(&priv->napi);
+	for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		netif_napi_del(&rx_q->napi);
+	}
 error_hw_init:
 	free_netdev(ndev);
 
@@ -3369,10 +4231,9 @@ int stmmac_dvr_remove(struct device *dev)
 
 	netdev_info(priv->dev, "%s: removing driver", __func__);
 
-	priv->hw->dma->stop_rx(priv->ioaddr);
-	priv->hw->dma->stop_tx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
-	stmmac_set_mac(priv->ioaddr, false);
+	priv->hw->mac->set_mac(priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
 	if (priv->plat->stmmac_rst)
@@ -3411,20 +4272,19 @@ int stmmac_suspend(struct device *dev)
 	spin_lock_irqsave(&priv->lock, flags);
 
 	netif_device_detach(ndev);
-	netif_stop_queue(ndev);
+	stmmac_stop_all_queues(priv);
 
-	napi_disable(&priv->napi);
+	stmmac_disable_all_queues(priv);
 
 	/* Stop TX/RX DMA */
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	priv->hw->dma->stop_rx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
 	/* Enable Power down mode by programming the PMT regs */
 	if (device_may_wakeup(priv->device)) {
 		priv->hw->mac->pmt(priv->hw, priv->wolopts);
 		priv->irq_wake = 1;
 	} else {
-		stmmac_set_mac(priv->ioaddr, false);
+		priv->hw->mac->set_mac(priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
 		clk_disable(priv->plat->pclk);
@@ -3440,6 +4300,31 @@ int stmmac_suspend(struct device *dev)
 EXPORT_SYMBOL_GPL(stmmac_suspend);
 
 /**
+ * stmmac_reset_queues_param - reset queue parameters
+ * @dev: device pointer
+ */
+static void stmmac_reset_queues_param(struct stmmac_priv *priv)
+{
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < rx_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		rx_q->cur_rx = 0;
+		rx_q->dirty_rx = 0;
+	}
+
+	for (queue = 0; queue < tx_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		tx_q->cur_tx = 0;
+		tx_q->dirty_tx = 0;
+	}
+}
+
+/**
  * stmmac_resume - resume callback
  * @dev: device pointer
  * Description: when resume this function is invoked to setup the DMA and CORE
@@ -3479,10 +4364,8 @@ int stmmac_resume(struct device *dev)
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	priv->cur_rx = 0;
-	priv->dirty_rx = 0;
-	priv->dirty_tx = 0;
-	priv->cur_tx = 0;
+	stmmac_reset_queues_param(priv);
+
 	/* reset private mss value to force mss context settings at
 	 * next tso xmit (only used for gmac4).
 	 */
@@ -3494,9 +4377,9 @@ int stmmac_resume(struct device *dev)
 	stmmac_init_tx_coalesce(priv);
 	stmmac_set_rx_mode(ndev);
 
-	napi_enable(&priv->napi);
+	stmmac_enable_all_queues(priv);
 
-	netif_start_queue(ndev);
+	stmmac_start_all_queues(priv);
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 5c9e462276b9..39be96779145 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -32,6 +32,7 @@
  */
 struct stmmac_pci_dmi_data {
 	const char *name;
+	const char *asset_tag;
 	unsigned int func;
 	int phy_addr;
 };
@@ -46,6 +47,7 @@ struct stmmac_pci_info {
 static int stmmac_pci_find_phy_addr(struct stmmac_pci_info *info)
 {
 	const char *name = dmi_get_system_info(DMI_BOARD_NAME);
+	const char *asset_tag = dmi_get_system_info(DMI_BOARD_ASSET_TAG);
 	unsigned int func = PCI_FUNC(info->pdev->devfn);
 	struct stmmac_pci_dmi_data *dmi;
 
@@ -57,8 +59,12 @@ static int stmmac_pci_find_phy_addr(struct stmmac_pci_info *info)
 		return 1;
 
 	for (dmi = info->dmi; dmi->name && *dmi->name; dmi++) {
-		if (!strcmp(dmi->name, name) && dmi->func == func)
+		if (!strcmp(dmi->name, name) && dmi->func == func) {
+			/* If asset tag is provided, match on it as well. */
+			if (dmi->asset_tag && strcmp(dmi->asset_tag, asset_tag))
+				continue;
 			return dmi->phy_addr;
+		}
 	}
 
 	return -ENODEV;
@@ -88,6 +94,17 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat)
 
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
+
+	/* Set default number of RX and TX queues to use */
+	plat->tx_queues_to_use = 1;
+	plat->rx_queues_to_use = 1;
+
+	/* Disable Priority config by default */
+	plat->tx_queues_cfg[0].use_prio = false;
+	plat->rx_queues_cfg[0].use_prio = false;
+
+	/* Disable RX queues routing by default */
+	plat->rx_queues_cfg[0].pkt_route = 0x0;
 }
 
 static int quark_default_data(struct plat_stmmacenet_data *plat,
@@ -142,6 +159,24 @@ static struct stmmac_pci_dmi_data quark_pci_dmi_data[] = {
 		.func = 6,
 		.phy_addr = 1,
 	},
+	{
+		.name = "SIMATIC IOT2000",
+		.asset_tag = "6ES7647-0AA00-0YA2",
+		.func = 6,
+		.phy_addr = 1,
+	},
+	{
+		.name = "SIMATIC IOT2000",
+		.asset_tag = "6ES7647-0AA00-1YA2",
+		.func = 6,
+		.phy_addr = 1,
+	},
+	{
+		.name = "SIMATIC IOT2000",
+		.asset_tag = "6ES7647-0AA00-1YA2",
+		.func = 7,
+		.phy_addr = 1,
+	},
 	{}
 };
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 433a84239a68..7fc3a1ef395a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -108,7 +108,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
 	if (!np)
 		return NULL;
 
-	axi = kzalloc(sizeof(*axi), GFP_KERNEL);
+	axi = devm_kzalloc(&pdev->dev, sizeof(*axi), GFP_KERNEL);
 	if (!axi) {
 		of_node_put(np);
 		return ERR_PTR(-ENOMEM);
@@ -132,6 +132,155 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
 }
 
 /**
+ * stmmac_mtl_setup - parse DT parameters for multiple queues configuration
+ * @pdev: platform device
+ */
+static void stmmac_mtl_setup(struct platform_device *pdev,
+			     struct plat_stmmacenet_data *plat)
+{
+	struct device_node *q_node;
+	struct device_node *rx_node;
+	struct device_node *tx_node;
+	u8 queue = 0;
+
+	/* For backwards-compatibility with device trees that don't have any
+	 * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back
+	 * to one RX and TX queues each.
+	 */
+	plat->rx_queues_to_use = 1;
+	plat->tx_queues_to_use = 1;
+
+	rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0);
+	if (!rx_node)
+		return;
+
+	tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0);
+	if (!tx_node) {
+		of_node_put(rx_node);
+		return;
+	}
+
+	/* Processing RX queues common config */
+	if (of_property_read_u8(rx_node, "snps,rx-queues-to-use",
+				&plat->rx_queues_to_use))
+		plat->rx_queues_to_use = 1;
+
+	if (of_property_read_bool(rx_node, "snps,rx-sched-sp"))
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+	else if (of_property_read_bool(rx_node, "snps,rx-sched-wsp"))
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_WSP;
+	else
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+
+	/* Processing individual RX queue config */
+	for_each_child_of_node(rx_node, q_node) {
+		if (queue >= plat->rx_queues_to_use)
+			break;
+
+		if (of_property_read_bool(q_node, "snps,dcb-algorithm"))
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		else if (of_property_read_bool(q_node, "snps,avb-algorithm"))
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+		else
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+
+		if (of_property_read_u8(q_node, "snps,map-to-dma-channel",
+					&plat->rx_queues_cfg[queue].chan))
+			plat->rx_queues_cfg[queue].chan = queue;
+		/* TODO: Dynamic mapping to be included in the future */
+
+		if (of_property_read_u32(q_node, "snps,priority",
+					&plat->rx_queues_cfg[queue].prio)) {
+			plat->rx_queues_cfg[queue].prio = 0;
+			plat->rx_queues_cfg[queue].use_prio = false;
+		} else {
+			plat->rx_queues_cfg[queue].use_prio = true;
+		}
+
+		/* RX queue specific packet type routing */
+		if (of_property_read_bool(q_node, "snps,route-avcp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_AVCPQ;
+		else if (of_property_read_bool(q_node, "snps,route-ptp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_PTPQ;
+		else if (of_property_read_bool(q_node, "snps,route-dcbcp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_DCBCPQ;
+		else if (of_property_read_bool(q_node, "snps,route-up"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ;
+		else if (of_property_read_bool(q_node, "snps,route-multi-broad"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ;
+		else
+			plat->rx_queues_cfg[queue].pkt_route = 0x0;
+
+		queue++;
+	}
+
+	/* Processing TX queues common config */
+	if (of_property_read_u8(tx_node, "snps,tx-queues-to-use",
+				&plat->tx_queues_to_use))
+		plat->tx_queues_to_use = 1;
+
+	if (of_property_read_bool(tx_node, "snps,tx-sched-wrr"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-sp"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+	else
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+
+	queue = 0;
+
+	/* Processing individual TX queue config */
+	for_each_child_of_node(tx_node, q_node) {
+		if (queue >= plat->tx_queues_to_use)
+			break;
+
+		if (of_property_read_u8(q_node, "snps,weight",
+					&plat->tx_queues_cfg[queue].weight))
+			plat->tx_queues_cfg[queue].weight = 0x10 + queue;
+
+		if (of_property_read_bool(q_node, "snps,dcb-algorithm")) {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		} else if (of_property_read_bool(q_node,
+						 "snps,avb-algorithm")) {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+
+			/* Credit Base Shaper parameters used by AVB */
+			if (of_property_read_u32(q_node, "snps,send_slope",
+				&plat->tx_queues_cfg[queue].send_slope))
+				plat->tx_queues_cfg[queue].send_slope = 0x0;
+			if (of_property_read_u32(q_node, "snps,idle_slope",
+				&plat->tx_queues_cfg[queue].idle_slope))
+				plat->tx_queues_cfg[queue].idle_slope = 0x0;
+			if (of_property_read_u32(q_node, "snps,high_credit",
+				&plat->tx_queues_cfg[queue].high_credit))
+				plat->tx_queues_cfg[queue].high_credit = 0x0;
+			if (of_property_read_u32(q_node, "snps,low_credit",
+				&plat->tx_queues_cfg[queue].low_credit))
+				plat->tx_queues_cfg[queue].low_credit = 0x0;
+		} else {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		}
+
+		if (of_property_read_u32(q_node, "snps,priority",
+					&plat->tx_queues_cfg[queue].prio)) {
+			plat->tx_queues_cfg[queue].prio = 0;
+			plat->tx_queues_cfg[queue].use_prio = false;
+		} else {
+			plat->tx_queues_cfg[queue].use_prio = true;
+		}
+
+		queue++;
+	}
+
+	of_node_put(rx_node);
+	of_node_put(tx_node);
+	of_node_put(q_node);
+}
+
+/**
  * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
  * @plat: driver data platform structure
  * @np: device tree node
@@ -340,6 +489,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 
 	plat->axi = stmmac_axi_setup(pdev);
 
+	stmmac_mtl_setup(pdev, plat);
+
 	/* clock setup */
 	plat->stmmac_clk = devm_clk_get(&pdev->dev,
 					STMMAC_RESOURCE_NAME);
@@ -359,13 +510,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	clk_prepare_enable(plat->pclk);
 
 	/* Fall-back to main clock in case of no PTP ref is passed */
-	plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "clk_ptp_ref");
+	plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref");
 	if (IS_ERR(plat->clk_ptp_ref)) {
 		plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk);
 		plat->clk_ptp_ref = NULL;
 		dev_warn(&pdev->dev, "PTP uses main clock\n");
 	} else {
-		clk_prepare_enable(plat->clk_ptp_ref);
 		plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref);
 		dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate);
 	}
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 0e8e89f17dbb..382993c1561c 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -691,7 +691,8 @@ static void cas_mif_poll(struct cas *cp, const int enable)
 }
 
 /* Must be invoked under cp->lock */
-static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep)
+static void cas_begin_auto_negotiation(struct cas *cp,
+				       const struct ethtool_link_ksettings *ep)
 {
 	u16 ctl;
 #if 1
@@ -704,16 +705,16 @@ static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep)
 	if (!ep)
 		goto start_aneg;
 	lcntl = cp->link_cntl;
-	if (ep->autoneg == AUTONEG_ENABLE)
+	if (ep->base.autoneg == AUTONEG_ENABLE) {
 		cp->link_cntl = BMCR_ANENABLE;
-	else {
-		u32 speed = ethtool_cmd_speed(ep);
+	} else {
+		u32 speed = ep->base.speed;
 		cp->link_cntl = 0;
 		if (speed == SPEED_100)
 			cp->link_cntl |= BMCR_SPEED100;
 		else if (speed == SPEED_1000)
 			cp->link_cntl |= CAS_BMCR_SPEED1000;
-		if (ep->duplex == DUPLEX_FULL)
+		if (ep->base.duplex == DUPLEX_FULL)
 			cp->link_cntl |= BMCR_FULLDPLX;
 	}
 #if 1
@@ -4528,19 +4529,21 @@ static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 	strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
 }
 
-static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cas_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct cas *cp = netdev_priv(dev);
 	u16 bmcr;
 	int full_duplex, speed, pause;
 	unsigned long flags;
 	enum link_state linkstate = link_up;
+	u32 supported, advertising;
 
-	cmd->advertising = 0;
-	cmd->supported = SUPPORTED_Autoneg;
+	advertising = 0;
+	supported = SUPPORTED_Autoneg;
 	if (cp->cas_flags & CAS_FLAG_1000MB_CAP) {
-		cmd->supported |= SUPPORTED_1000baseT_Full;
-		cmd->advertising |= ADVERTISED_1000baseT_Full;
+		supported |= SUPPORTED_1000baseT_Full;
+		advertising |= ADVERTISED_1000baseT_Full;
 	}
 
 	/* Record PHY settings if HW is on. */
@@ -4548,17 +4551,15 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	bmcr = 0;
 	linkstate = cp->lstate;
 	if (CAS_PHY_MII(cp->phy_type)) {
-		cmd->port = PORT_MII;
-		cmd->transceiver = (cp->cas_flags & CAS_FLAG_SATURN) ?
-			XCVR_INTERNAL : XCVR_EXTERNAL;
-		cmd->phy_address = cp->phy_addr;
-		cmd->advertising |= ADVERTISED_TP | ADVERTISED_MII |
+		cmd->base.port = PORT_MII;
+		cmd->base.phy_address = cp->phy_addr;
+		advertising |= ADVERTISED_TP | ADVERTISED_MII |
 			ADVERTISED_10baseT_Half |
 			ADVERTISED_10baseT_Full |
 			ADVERTISED_100baseT_Half |
 			ADVERTISED_100baseT_Full;
 
-		cmd->supported |=
+		supported |=
 			(SUPPORTED_10baseT_Half |
 			 SUPPORTED_10baseT_Full |
 			 SUPPORTED_100baseT_Half |
@@ -4574,11 +4575,10 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		}
 
 	} else {
-		cmd->port = PORT_FIBRE;
-		cmd->transceiver = XCVR_INTERNAL;
-		cmd->phy_address = 0;
-		cmd->supported   |= SUPPORTED_FIBRE;
-		cmd->advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_FIBRE;
+		cmd->base.phy_address = 0;
+		supported   |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
 
 		if (cp->hw_running) {
 			/* pcs uses the same bits as mii */
@@ -4590,21 +4590,20 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	if (bmcr & BMCR_ANENABLE) {
-		cmd->advertising |= ADVERTISED_Autoneg;
-		cmd->autoneg = AUTONEG_ENABLE;
-		ethtool_cmd_speed_set(cmd, ((speed == 10) ?
+		advertising |= ADVERTISED_Autoneg;
+		cmd->base.autoneg = AUTONEG_ENABLE;
+		cmd->base.speed =  ((speed == 10) ?
 					    SPEED_10 :
 					    ((speed == 1000) ?
-					     SPEED_1000 : SPEED_100)));
-		cmd->duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
+					     SPEED_1000 : SPEED_100));
+		cmd->base.duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
-		ethtool_cmd_speed_set(cmd, ((bmcr & CAS_BMCR_SPEED1000) ?
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		cmd->base.speed = ((bmcr & CAS_BMCR_SPEED1000) ?
 					    SPEED_1000 :
 					    ((bmcr & BMCR_SPEED100) ?
-					     SPEED_100 : SPEED_10)));
-		cmd->duplex =
-			(bmcr & BMCR_FULLDPLX) ?
+					     SPEED_100 : SPEED_10));
+		cmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
 			DUPLEX_FULL : DUPLEX_HALF;
 	}
 	if (linkstate != link_up) {
@@ -4619,39 +4618,46 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		 * settings that we configured.
 		 */
 		if (cp->link_cntl & BMCR_ANENABLE) {
-			ethtool_cmd_speed_set(cmd, 0);
-			cmd->duplex = 0xff;
+			cmd->base.speed = 0;
+			cmd->base.duplex = 0xff;
 		} else {
-			ethtool_cmd_speed_set(cmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 			if (cp->link_cntl & BMCR_SPEED100) {
-				ethtool_cmd_speed_set(cmd, SPEED_100);
+				cmd->base.speed = SPEED_100;
 			} else if (cp->link_cntl & CAS_BMCR_SPEED1000) {
-				ethtool_cmd_speed_set(cmd, SPEED_1000);
+				cmd->base.speed = SPEED_1000;
 			}
-			cmd->duplex = (cp->link_cntl & BMCR_FULLDPLX)?
+			cmd->base.duplex = (cp->link_cntl & BMCR_FULLDPLX) ?
 				DUPLEX_FULL : DUPLEX_HALF;
 		}
 	}
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
+
 	return 0;
 }
 
-static int cas_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cas_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct cas *cp = netdev_priv(dev);
 	unsigned long flags;
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
 
 	/* Verify the settings we care about. */
-	if (cmd->autoneg != AUTONEG_ENABLE &&
-	    cmd->autoneg != AUTONEG_DISABLE)
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_DISABLE &&
+	if (cmd->base.autoneg == AUTONEG_DISABLE &&
 	    ((speed != SPEED_1000 &&
 	      speed != SPEED_100 &&
 	      speed != SPEED_10) ||
-	     (cmd->duplex != DUPLEX_HALF &&
-	      cmd->duplex != DUPLEX_FULL)))
+	     (cmd->base.duplex != DUPLEX_HALF &&
+	      cmd->base.duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
 	/* Apply settings and restart link process. */
@@ -4753,8 +4759,6 @@ static void cas_get_ethtool_stats(struct net_device *dev,
 
 static const struct ethtool_ops cas_ethtool_ops = {
 	.get_drvinfo		= cas_get_drvinfo,
-	.get_settings		= cas_get_settings,
-	.set_settings		= cas_set_settings,
 	.nway_reset		= cas_nway_reset,
 	.get_link		= cas_get_link,
 	.get_msglevel		= cas_get_msglevel,
@@ -4764,6 +4768,8 @@ static const struct ethtool_ops cas_ethtool_ops = {
 	.get_sset_count		= cas_get_sset_count,
 	.get_strings		= cas_get_strings,
 	.get_ethtool_stats	= cas_get_ethtool_stats,
+	.get_link_ksettings	= cas_get_link_ksettings,
+	.set_link_ksettings	= cas_set_link_ksettings,
 };
 
 static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 89952deae47f..5a90fed06260 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -1,6 +1,6 @@
 /* ldmvsw.c: Sun4v LDOM Virtual Switch Driver.
  *
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -41,8 +41,8 @@
 static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
 
 #define DRV_MODULE_NAME		"ldmvsw"
-#define DRV_MODULE_VERSION	"1.1"
-#define DRV_MODULE_RELDATE	"February 3, 2017"
+#define DRV_MODULE_VERSION	"1.2"
+#define DRV_MODULE_RELDATE	"March 4, 2017"
 
 static char version[] =
 	DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")";
@@ -123,6 +123,20 @@ static void vsw_set_rx_mode(struct net_device *dev)
 	return sunvnet_set_rx_mode_common(dev, port->vp);
 }
 
+int ldmvsw_open(struct net_device *dev)
+{
+	struct vnet_port *port = netdev_priv(dev);
+	struct vio_driver_state *vio = &port->vio;
+
+	/* reset the channel */
+	vio_link_state_change(vio, LDC_EVENT_RESET);
+	vnet_port_reset(port);
+	vio_port_up(vio);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ldmvsw_open);
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void vsw_poll_controller(struct net_device *dev)
 {
@@ -133,7 +147,7 @@ static void vsw_poll_controller(struct net_device *dev)
 #endif
 
 static const struct net_device_ops vsw_ops = {
-	.ndo_open		= sunvnet_open_common,
+	.ndo_open		= ldmvsw_open,
 	.ndo_stop		= sunvnet_close_common,
 	.ndo_set_rx_mode	= vsw_set_rx_mode,
 	.ndo_set_mac_address	= sunvnet_set_mac_addr_common,
@@ -365,6 +379,11 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	napi_enable(&port->napi);
 	vio_port_up(&port->vio);
 
+	/* assure no carrier until we receive an LDC_EVENT_UP,
+	 * even if the vsw config script tries to force us up
+	 */
+	netif_carrier_off(dev);
+
 	netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr);
 
 	pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name,
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 57978056b336..2dcca249eb9c 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6813,7 +6813,8 @@ static void niu_get_drvinfo(struct net_device *dev,
 			sizeof(info->bus_info));
 }
 
-static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int niu_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct niu *np = netdev_priv(dev);
 	struct niu_link_config *lp;
@@ -6821,28 +6822,30 @@ static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	lp = &np->link_config;
 
 	memset(cmd, 0, sizeof(*cmd));
-	cmd->phy_address = np->phy_addr;
-	cmd->supported = lp->supported;
-	cmd->advertising = lp->active_advertising;
-	cmd->autoneg = lp->active_autoneg;
-	ethtool_cmd_speed_set(cmd, lp->active_speed);
-	cmd->duplex = lp->active_duplex;
-	cmd->port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP;
-	cmd->transceiver = (np->flags & NIU_FLAGS_XCVR_SERDES) ?
-		XCVR_EXTERNAL : XCVR_INTERNAL;
+	cmd->base.phy_address = np->phy_addr;
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						lp->supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						lp->active_advertising);
+	cmd->base.autoneg = lp->active_autoneg;
+	cmd->base.speed = lp->active_speed;
+	cmd->base.duplex = lp->active_duplex;
+	cmd->base.port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP;
 
 	return 0;
 }
 
-static int niu_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int niu_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct niu *np = netdev_priv(dev);
 	struct niu_link_config *lp = &np->link_config;
 
-	lp->advertising = cmd->advertising;
-	lp->speed = ethtool_cmd_speed(cmd);
-	lp->duplex = cmd->duplex;
-	lp->autoneg = cmd->autoneg;
+	ethtool_convert_link_mode_to_legacy_u32(&lp->advertising,
+						cmd->link_modes.advertising);
+	lp->speed = cmd->base.speed;
+	lp->duplex = cmd->base.duplex;
+	lp->autoneg = cmd->base.autoneg;
 	return niu_init_link(np);
 }
 
@@ -7902,14 +7905,14 @@ static const struct ethtool_ops niu_ethtool_ops = {
 	.nway_reset		= niu_nway_reset,
 	.get_eeprom_len		= niu_get_eeprom_len,
 	.get_eeprom		= niu_get_eeprom,
-	.get_settings		= niu_get_settings,
-	.set_settings		= niu_set_settings,
 	.get_strings		= niu_get_strings,
 	.get_sset_count		= niu_get_sset_count,
 	.get_ethtool_stats	= niu_get_ethtool_stats,
 	.set_phys_id		= niu_set_phys_id,
 	.get_rxnfc		= niu_get_nfc,
 	.set_rxnfc		= niu_set_nfc,
+	.get_link_ksettings	= niu_get_link_ksettings,
+	.set_link_ksettings	= niu_set_link_ksettings,
 };
 
 static int niu_ldg_assign_ldn(struct niu *np, struct niu_parent *parent,
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index c4caf486cbef..3189722110c2 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -169,7 +169,7 @@ static void bigmac_stop(struct bigmac *bp)
 
 static void bigmac_get_counters(struct bigmac *bp, void __iomem *bregs)
 {
-	struct net_device_stats *stats = &bp->enet_stats;
+	struct net_device_stats *stats = &bp->dev->stats;
 
 	stats->rx_crc_errors += sbus_readl(bregs + BMAC_RCRCECTR);
 	sbus_writel(0, bregs + BMAC_RCRCECTR);
@@ -774,8 +774,8 @@ static void bigmac_tx(struct bigmac *bp)
 		if (this->tx_flags & TXD_OWN)
 			break;
 		skb = bp->tx_skbs[elem];
-		bp->enet_stats.tx_packets++;
-		bp->enet_stats.tx_bytes += skb->len;
+		dev->stats.tx_packets++;
+		dev->stats.tx_bytes += skb->len;
 		dma_unmap_single(&bp->bigmac_op->dev,
 				 this->tx_addr, skb->len,
 				 DMA_TO_DEVICE);
@@ -811,12 +811,12 @@ static void bigmac_rx(struct bigmac *bp)
 
 		/* Check for errors. */
 		if (len < ETH_ZLEN) {
-			bp->enet_stats.rx_errors++;
-			bp->enet_stats.rx_length_errors++;
+			bp->dev->stats.rx_errors++;
+			bp->dev->stats.rx_length_errors++;
 
 	drop_it:
 			/* Return it to the BigMAC. */
-			bp->enet_stats.rx_dropped++;
+			bp->dev->stats.rx_dropped++;
 			this->rx_flags =
 				(RXD_OWN | ((RX_BUF_ALLOC_SIZE - 34) & RXD_LENGTH));
 			goto next;
@@ -875,8 +875,8 @@ static void bigmac_rx(struct bigmac *bp)
 		/* No checksums done by the BigMAC ;-( */
 		skb->protocol = eth_type_trans(skb, bp->dev);
 		netif_rx(skb);
-		bp->enet_stats.rx_packets++;
-		bp->enet_stats.rx_bytes += len;
+		bp->dev->stats.rx_packets++;
+		bp->dev->stats.rx_bytes += len;
 	next:
 		elem = NEXT_RX(elem);
 		this = &rxbase[elem];
@@ -987,7 +987,7 @@ static struct net_device_stats *bigmac_get_stats(struct net_device *dev)
 	struct bigmac *bp = netdev_priv(dev);
 
 	bigmac_get_counters(bp, bp->bregs);
-	return &bp->enet_stats;
+	return &dev->stats;
 }
 
 static void bigmac_set_multicast(struct net_device *dev)
diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h
index 532fc56830cf..ee56930475a8 100644
--- a/drivers/net/ethernet/sun/sunbmac.h
+++ b/drivers/net/ethernet/sun/sunbmac.h
@@ -311,7 +311,6 @@ struct bigmac {
 	enum bigmac_timer_state	timer_state;
 	unsigned int		timer_ticks;
 
-	struct net_device_stats	enet_stats;
 	struct platform_device	*qec_op;
 	struct platform_device	*bigmac_op;
 	struct net_device	*dev;
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 5c5952e782cd..fa607d062cb3 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -1250,12 +1250,18 @@ static void gem_stop_dma(struct gem *gp)
 
 
 // XXX dbl check what that function should do when called on PCS PHY
-static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep)
+static void gem_begin_auto_negotiation(struct gem *gp,
+				       const struct ethtool_link_ksettings *ep)
 {
 	u32 advertise, features;
 	int autoneg;
 	int speed;
 	int duplex;
+	u32 advertising;
+
+	if (ep)
+		ethtool_convert_link_mode_to_legacy_u32(
+			&advertising, ep->link_modes.advertising);
 
 	if (gp->phy_type != phy_mii_mdio0 &&
      	    gp->phy_type != phy_mii_mdio1)
@@ -1278,13 +1284,13 @@ static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep)
 	/* Setup link parameters */
 	if (!ep)
 		goto start_aneg;
-	if (ep->autoneg == AUTONEG_ENABLE) {
-		advertise = ep->advertising;
+	if (ep->base.autoneg == AUTONEG_ENABLE) {
+		advertise = advertising;
 		autoneg = 1;
 	} else {
 		autoneg = 0;
-		speed = ethtool_cmd_speed(ep);
-		duplex = ep->duplex;
+		speed = ep->base.speed;
+		duplex = ep->base.duplex;
 	}
 
 start_aneg:
@@ -2515,85 +2521,96 @@ static void gem_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 	strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info));
 }
 
-static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int gem_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct gem *gp = netdev_priv(dev);
+	u32 supported, advertising;
 
 	if (gp->phy_type == phy_mii_mdio0 ||
 	    gp->phy_type == phy_mii_mdio1) {
 		if (gp->phy_mii.def)
-			cmd->supported = gp->phy_mii.def->features;
+			supported = gp->phy_mii.def->features;
 		else
-			cmd->supported = (SUPPORTED_10baseT_Half |
+			supported = (SUPPORTED_10baseT_Half |
 					  SUPPORTED_10baseT_Full);
 
 		/* XXX hardcoded stuff for now */
-		cmd->port = PORT_MII;
-		cmd->transceiver = XCVR_EXTERNAL;
-		cmd->phy_address = 0; /* XXX fixed PHYAD */
+		cmd->base.port = PORT_MII;
+		cmd->base.phy_address = 0; /* XXX fixed PHYAD */
 
 		/* Return current PHY settings */
-		cmd->autoneg = gp->want_autoneg;
-		ethtool_cmd_speed_set(cmd, gp->phy_mii.speed);
-		cmd->duplex = gp->phy_mii.duplex;
-		cmd->advertising = gp->phy_mii.advertising;
+		cmd->base.autoneg = gp->want_autoneg;
+		cmd->base.speed = gp->phy_mii.speed;
+		cmd->base.duplex = gp->phy_mii.duplex;
+		advertising = gp->phy_mii.advertising;
 
 		/* If we started with a forced mode, we don't have a default
 		 * advertise set, we need to return something sensible so
 		 * userland can re-enable autoneg properly.
 		 */
-		if (cmd->advertising == 0)
-			cmd->advertising = cmd->supported;
+		if (advertising == 0)
+			advertising = supported;
 	} else { // XXX PCS ?
-		cmd->supported =
+		supported =
 			(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
 			 SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
 			 SUPPORTED_Autoneg);
-		cmd->advertising = cmd->supported;
-		ethtool_cmd_speed_set(cmd, 0);
-		cmd->duplex = cmd->port = cmd->phy_address =
-			cmd->transceiver = cmd->autoneg = 0;
+		advertising = supported;
+		cmd->base.speed = 0;
+		cmd->base.duplex = 0;
+		cmd->base.port = 0;
+		cmd->base.phy_address = 0;
+		cmd->base.autoneg = 0;
 
 		/* serdes means usually a Fibre connector, with most fixed */
 		if (gp->phy_type == phy_serdes) {
-			cmd->port = PORT_FIBRE;
-			cmd->supported = (SUPPORTED_1000baseT_Half |
+			cmd->base.port = PORT_FIBRE;
+			supported = (SUPPORTED_1000baseT_Half |
 				SUPPORTED_1000baseT_Full |
 				SUPPORTED_FIBRE | SUPPORTED_Autoneg |
 				SUPPORTED_Pause | SUPPORTED_Asym_Pause);
-			cmd->advertising = cmd->supported;
-			cmd->transceiver = XCVR_INTERNAL;
+			advertising = supported;
 			if (gp->lstate == link_up)
-				ethtool_cmd_speed_set(cmd, SPEED_1000);
-			cmd->duplex = DUPLEX_FULL;
-			cmd->autoneg = 1;
+				cmd->base.speed = SPEED_1000;
+			cmd->base.duplex = DUPLEX_FULL;
+			cmd->base.autoneg = 1;
 		}
 	}
-	cmd->maxtxpkt = cmd->maxrxpkt = 0;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int gem_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int gem_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct gem *gp = netdev_priv(dev);
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	/* Verify the settings we care about. */
-	if (cmd->autoneg != AUTONEG_ENABLE &&
-	    cmd->autoneg != AUTONEG_DISABLE)
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_ENABLE &&
-	    cmd->advertising == 0)
+	if (cmd->base.autoneg == AUTONEG_ENABLE &&
+	    advertising == 0)
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_DISABLE &&
+	if (cmd->base.autoneg == AUTONEG_DISABLE &&
 	    ((speed != SPEED_1000 &&
 	      speed != SPEED_100 &&
 	      speed != SPEED_10) ||
-	     (cmd->duplex != DUPLEX_HALF &&
-	      cmd->duplex != DUPLEX_FULL)))
+	     (cmd->base.duplex != DUPLEX_HALF &&
+	      cmd->base.duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
 	/* Apply settings and restart link process. */
@@ -2666,13 +2683,13 @@ static int gem_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 static const struct ethtool_ops gem_ethtool_ops = {
 	.get_drvinfo		= gem_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
-	.get_settings		= gem_get_settings,
-	.set_settings		= gem_set_settings,
 	.nway_reset		= gem_nway_reset,
 	.get_msglevel		= gem_get_msglevel,
 	.set_msglevel		= gem_set_msglevel,
 	.get_wol		= gem_get_wol,
 	.set_wol		= gem_set_wol,
+	.get_link_ksettings	= gem_get_link_ksettings,
+	.set_link_ksettings	= gem_set_link_ksettings,
 };
 
 static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 72ff05cd3ed8..9e983e1d8249 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -933,7 +933,7 @@ static void happy_meal_stop(struct happy_meal *hp, void __iomem *gregs)
 /* hp->happy_lock must be held */
 static void happy_meal_get_counters(struct happy_meal *hp, void __iomem *bregs)
 {
-	struct net_device_stats *stats = &hp->net_stats;
+	struct net_device_stats *stats = &hp->dev->stats;
 
 	stats->rx_crc_errors += hme_read32(hp, bregs + BMAC_RCRCECTR);
 	hme_write32(hp, bregs + BMAC_RCRCECTR, 0);
@@ -1294,9 +1294,10 @@ static void happy_meal_init_rings(struct happy_meal *hp)
 }
 
 /* hp->happy_lock must be held */
-static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
-					      void __iomem *tregs,
-					      struct ethtool_cmd *ep)
+static void
+happy_meal_begin_auto_negotiation(struct happy_meal *hp,
+				  void __iomem *tregs,
+				  const struct ethtool_link_ksettings *ep)
 {
 	int timeout;
 
@@ -1309,7 +1310,7 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
 	/* XXX Check BMSR_ANEGCAPABLE, should not be necessary though. */
 
 	hp->sw_advertise = happy_meal_tcvr_read(hp, tregs, MII_ADVERTISE);
-	if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) {
+	if (!ep || ep->base.autoneg == AUTONEG_ENABLE) {
 		/* Advertise everything we can support. */
 		if (hp->sw_bmsr & BMSR_10HALF)
 			hp->sw_advertise |= (ADVERTISE_10HALF);
@@ -1384,14 +1385,14 @@ force_link:
 		/* Disable auto-negotiation in BMCR, enable the duplex and
 		 * speed setting, init the timer state machine, and fire it off.
 		 */
-		if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) {
+		if (!ep || ep->base.autoneg == AUTONEG_ENABLE) {
 			hp->sw_bmcr = BMCR_SPEED100;
 		} else {
-			if (ethtool_cmd_speed(ep) == SPEED_100)
+			if (ep->base.speed == SPEED_100)
 				hp->sw_bmcr = BMCR_SPEED100;
 			else
 				hp->sw_bmcr = 0;
-			if (ep->duplex == DUPLEX_FULL)
+			if (ep->base.duplex == DUPLEX_FULL)
 				hp->sw_bmcr |= BMCR_FULLDPLX;
 		}
 		happy_meal_tcvr_write(hp, tregs, MII_BMCR, hp->sw_bmcr);
@@ -1856,7 +1857,7 @@ static int happy_meal_is_not_so_happy(struct happy_meal *hp, u32 status)
 		if (status & GREG_STAT_TXLERR)
 			printk("LateError ");
 		if (status & GREG_STAT_TXPERR)
-			printk("ParityErro ");
+			printk("ParityError ");
 		if (status & GREG_STAT_TXTERR)
 			printk("TagBotch ");
 		printk("]\n");
@@ -1946,7 +1947,7 @@ static void happy_meal_tx(struct happy_meal *hp)
 				break;
 		}
 		hp->tx_skbs[elem] = NULL;
-		hp->net_stats.tx_bytes += skb->len;
+		dev->stats.tx_bytes += skb->len;
 
 		for (frag = 0; frag <= skb_shinfo(skb)->nr_frags; frag++) {
 			dma_addr = hme_read_desc32(hp, &this->tx_addr);
@@ -1963,7 +1964,7 @@ static void happy_meal_tx(struct happy_meal *hp)
 		}
 
 		dev_kfree_skb_irq(skb);
-		hp->net_stats.tx_packets++;
+		dev->stats.tx_packets++;
 	}
 	hp->tx_old = elem;
 	TXD((">"));
@@ -2008,17 +2009,17 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
 		/* Check for errors. */
 		if ((len < ETH_ZLEN) || (flags & RXFLAG_OVERFLOW)) {
 			RXD(("ERR(%08x)]", flags));
-			hp->net_stats.rx_errors++;
+			dev->stats.rx_errors++;
 			if (len < ETH_ZLEN)
-				hp->net_stats.rx_length_errors++;
+				dev->stats.rx_length_errors++;
 			if (len & (RXFLAG_OVERFLOW >> 16)) {
-				hp->net_stats.rx_over_errors++;
-				hp->net_stats.rx_fifo_errors++;
+				dev->stats.rx_over_errors++;
+				dev->stats.rx_fifo_errors++;
 			}
 
 			/* Return it to the Happy meal. */
 	drop_it:
-			hp->net_stats.rx_dropped++;
+			dev->stats.rx_dropped++;
 			hme_write_rxd(hp, this,
 				      (RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)),
 				      dma_addr);
@@ -2083,8 +2084,8 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
 		skb->protocol = eth_type_trans(skb, dev);
 		netif_rx(skb);
 
-		hp->net_stats.rx_packets++;
-		hp->net_stats.rx_bytes += len;
+		dev->stats.rx_packets++;
+		dev->stats.rx_bytes += len;
 	next:
 		elem = NEXT_RX(elem);
 		this = &rxbase[elem];
@@ -2395,7 +2396,7 @@ static struct net_device_stats *happy_meal_get_stats(struct net_device *dev)
 	happy_meal_get_counters(hp, hp->bigmacregs);
 	spin_unlock_irq(&hp->happy_lock);
 
-	return &hp->net_stats;
+	return &dev->stats;
 }
 
 static void happy_meal_set_multicast(struct net_device *dev)
@@ -2434,20 +2435,21 @@ static void happy_meal_set_multicast(struct net_device *dev)
 }
 
 /* Ethtool support... */
-static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int hme_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct happy_meal *hp = netdev_priv(dev);
 	u32 speed;
+	u32 supported;
 
-	cmd->supported =
+	supported =
 		(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
 		 SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
 		 SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII);
 
 	/* XXX hardcoded stuff for now */
-	cmd->port = PORT_TP; /* XXX no MII support */
-	cmd->transceiver = XCVR_INTERNAL; /* XXX no external xcvr support */
-	cmd->phy_address = 0; /* XXX fixed PHYAD */
+	cmd->base.port = PORT_TP; /* XXX no MII support */
+	cmd->base.phy_address = 0; /* XXX fixed PHYAD */
 
 	/* Record PHY settings. */
 	spin_lock_irq(&hp->happy_lock);
@@ -2456,41 +2458,45 @@ static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	spin_unlock_irq(&hp->happy_lock);
 
 	if (hp->sw_bmcr & BMCR_ANENABLE) {
-		cmd->autoneg = AUTONEG_ENABLE;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 		speed = ((hp->sw_lpa & (LPA_100HALF | LPA_100FULL)) ?
 			 SPEED_100 : SPEED_10);
 		if (speed == SPEED_100)
-			cmd->duplex =
+			cmd->base.duplex =
 				(hp->sw_lpa & (LPA_100FULL)) ?
 				DUPLEX_FULL : DUPLEX_HALF;
 		else
-			cmd->duplex =
+			cmd->base.duplex =
 				(hp->sw_lpa & (LPA_10FULL)) ?
 				DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
+		cmd->base.autoneg = AUTONEG_DISABLE;
 		speed = (hp->sw_bmcr & BMCR_SPEED100) ? SPEED_100 : SPEED_10;
-		cmd->duplex =
+		cmd->base.duplex =
 			(hp->sw_bmcr & BMCR_FULLDPLX) ?
 			DUPLEX_FULL : DUPLEX_HALF;
 	}
-	ethtool_cmd_speed_set(cmd, speed);
+	cmd->base.speed = speed;
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+
 	return 0;
 }
 
-static int hme_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int hme_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct happy_meal *hp = netdev_priv(dev);
 
 	/* Verify the settings we care about. */
-	if (cmd->autoneg != AUTONEG_ENABLE &&
-	    cmd->autoneg != AUTONEG_DISABLE)
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
-	if (cmd->autoneg == AUTONEG_DISABLE &&
-	    ((ethtool_cmd_speed(cmd) != SPEED_100 &&
-	      ethtool_cmd_speed(cmd) != SPEED_10) ||
-	     (cmd->duplex != DUPLEX_HALF &&
-	      cmd->duplex != DUPLEX_FULL)))
+	if (cmd->base.autoneg == AUTONEG_DISABLE &&
+	    ((cmd->base.speed != SPEED_100 &&
+	      cmd->base.speed != SPEED_10) ||
+	     (cmd->base.duplex != DUPLEX_HALF &&
+	      cmd->base.duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
 	/* Ok, do it to it. */
@@ -2537,10 +2543,10 @@ static u32 hme_get_link(struct net_device *dev)
 }
 
 static const struct ethtool_ops hme_ethtool_ops = {
-	.get_settings		= hme_get_settings,
-	.set_settings		= hme_set_settings,
 	.get_drvinfo		= hme_get_drvinfo,
 	.get_link		= hme_get_link,
+	.get_link_ksettings	= hme_get_link_ksettings,
+	.set_link_ksettings	= hme_set_link_ksettings,
 };
 
 static int hme_version_printed;
diff --git a/drivers/net/ethernet/sun/sunhme.h b/drivers/net/ethernet/sun/sunhme.h
index 4a8d5b18dfd5..3af540adb3c5 100644
--- a/drivers/net/ethernet/sun/sunhme.h
+++ b/drivers/net/ethernet/sun/sunhme.h
@@ -418,8 +418,6 @@ struct happy_meal {
 
 	int rx_new, tx_new, rx_old, tx_old;
 
-	struct net_device_stats	  net_stats;      /* Statistical counters              */
-
 #if defined(CONFIG_SBUS) && defined(CONFIG_PCI)
 	u32 (*read32)(void __iomem *);
 	void (*write32)(void __iomem *, u32);
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 4cc2571f71c6..0b95105f7060 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1,7 +1,7 @@
 /* sunvnet.c: Sun LDOM Virtual Network Driver.
  *
  * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -77,11 +77,125 @@ static void vnet_set_msglevel(struct net_device *dev, u32 value)
 	vp->msg_enable = value;
 }
 
+static const struct {
+	const char string[ETH_GSTRING_LEN];
+} ethtool_stats_keys[] = {
+	{ "rx_packets" },
+	{ "tx_packets" },
+	{ "rx_bytes" },
+	{ "tx_bytes" },
+	{ "rx_errors" },
+	{ "tx_errors" },
+	{ "rx_dropped" },
+	{ "tx_dropped" },
+	{ "multicast" },
+	{ "rx_length_errors" },
+	{ "rx_frame_errors" },
+	{ "rx_missed_errors" },
+	{ "tx_carrier_errors" },
+	{ "nports" },
+};
+
+static int vnet_get_sset_count(struct net_device *dev, int sset)
+{
+	struct vnet *vp = (struct vnet *)netdev_priv(dev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(ethtool_stats_keys)
+			+ (NUM_VNET_PORT_STATS * vp->nports);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
+{
+	struct vnet *vp = (struct vnet *)netdev_priv(dev);
+	struct vnet_port *port;
+	char *p = (char *)buf;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(buf, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
+		p += sizeof(ethtool_stats_keys);
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(port, &vp->port_list, list) {
+			snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM",
+				 port->q_index, port->switch_port ? "s" : "q",
+				 port->raddr);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.event_up",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+		}
+		rcu_read_unlock();
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static void vnet_get_ethtool_stats(struct net_device *dev,
+				   struct ethtool_stats *estats, u64 *data)
+{
+	struct vnet *vp = (struct vnet *)netdev_priv(dev);
+	struct vnet_port *port;
+	int i = 0;
+
+	data[i++] = dev->stats.rx_packets;
+	data[i++] = dev->stats.tx_packets;
+	data[i++] = dev->stats.rx_bytes;
+	data[i++] = dev->stats.tx_bytes;
+	data[i++] = dev->stats.rx_errors;
+	data[i++] = dev->stats.tx_errors;
+	data[i++] = dev->stats.rx_dropped;
+	data[i++] = dev->stats.tx_dropped;
+	data[i++] = dev->stats.multicast;
+	data[i++] = dev->stats.rx_length_errors;
+	data[i++] = dev->stats.rx_frame_errors;
+	data[i++] = dev->stats.rx_missed_errors;
+	data[i++] = dev->stats.tx_carrier_errors;
+	data[i++] = vp->nports;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &vp->port_list, list) {
+		data[i++] = port->q_index;
+		data[i++] = port->stats.rx_packets;
+		data[i++] = port->stats.tx_packets;
+		data[i++] = port->stats.rx_bytes;
+		data[i++] = port->stats.tx_bytes;
+		data[i++] = port->stats.event_up;
+		data[i++] = port->stats.event_reset;
+	}
+	rcu_read_unlock();
+}
+
 static const struct ethtool_ops vnet_ethtool_ops = {
 	.get_drvinfo		= vnet_get_drvinfo,
 	.get_msglevel		= vnet_get_msglevel,
 	.set_msglevel		= vnet_set_msglevel,
 	.get_link		= ethtool_op_get_link,
+	.get_sset_count		= vnet_get_sset_count,
+	.get_strings		= vnet_get_strings,
+	.get_ethtool_stats	= vnet_get_ethtool_stats,
 };
 
 static LIST_HEAD(vnet_list);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index fa2d11ca9b81..9e86833249d4 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1,7 +1,7 @@
 /* sunvnet.c: Sun LDOM Virtual Network Driver.
  *
  * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -43,7 +43,6 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION("1.1");
 
 static int __vnet_tx_trigger(struct vnet_port *port, u32 start);
-static void vnet_port_reset(struct vnet_port *port);
 
 static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr)
 {
@@ -410,8 +409,12 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc)
 
 	skb->ip_summed = port->switch_port ? CHECKSUM_NONE : CHECKSUM_PARTIAL;
 
+	if (unlikely(is_multicast_ether_addr(eth_hdr(skb)->h_dest)))
+		dev->stats.multicast++;
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += len;
+	port->stats.rx_packets++;
+	port->stats.rx_bytes += len;
 	napi_gro_receive(&port->napi, skb);
 	return 0;
 
@@ -747,6 +750,13 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
 
 	/* RESET takes precedent over any other event */
 	if (port->rx_event & LDC_EVENT_RESET) {
+		/* a link went down */
+
+		if (port->vsw == 1) {
+			netif_tx_stop_all_queues(dev);
+			netif_carrier_off(dev);
+		}
+
 		vio_link_state_change(vio, LDC_EVENT_RESET);
 		vnet_port_reset(port);
 		vio_port_up(vio);
@@ -762,12 +772,21 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
 			maybe_tx_wakeup(port);
 
 		port->rx_event = 0;
+		port->stats.event_reset++;
 		return 0;
 	}
 
 	if (port->rx_event & LDC_EVENT_UP) {
+		/* a link came up */
+
+		if (port->vsw == 1) {
+			netif_carrier_on(port->dev);
+			netif_tx_start_all_queues(port->dev);
+		}
+
 		vio_link_state_change(vio, LDC_EVENT_UP);
 		port->rx_event = 0;
+		port->stats.event_up++;
 		return 0;
 	}
 
@@ -1417,6 +1436,8 @@ ldc_start_done:
 
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += port->tx_bufs[txi].skb->len;
+	port->stats.tx_packets++;
+	port->stats.tx_bytes += port->tx_bufs[txi].skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
 	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
@@ -1631,7 +1652,7 @@ void sunvnet_port_free_tx_bufs_common(struct vnet_port *port)
 }
 EXPORT_SYMBOL_GPL(sunvnet_port_free_tx_bufs_common);
 
-static void vnet_port_reset(struct vnet_port *port)
+void vnet_port_reset(struct vnet_port *port)
 {
 	del_timer(&port->clean_timer);
 	sunvnet_port_free_tx_bufs_common(port);
@@ -1639,6 +1660,7 @@ static void vnet_port_reset(struct vnet_port *port)
 	port->tso = (port->vsw == 0);  /* no tso in vsw, misbehaves in bridge */
 	port->tsolen = 0;
 }
+EXPORT_SYMBOL_GPL(vnet_port_reset);
 
 static int vnet_port_alloc_tx_ring(struct vnet_port *port)
 {
@@ -1708,20 +1730,32 @@ EXPORT_SYMBOL_GPL(sunvnet_poll_controller_common);
 void sunvnet_port_add_txq_common(struct vnet_port *port)
 {
 	struct vnet *vp = port->vp;
-	int n;
+	int smallest = 0;
+	int i;
+
+	/* find the first least-used q
+	 * When there are more ldoms than q's, we start to
+	 * double up on ports per queue.
+	 */
+	for (i = 0; i < VNET_MAX_TXQS; i++) {
+		if (vp->q_used[i] == 0) {
+			smallest = i;
+			break;
+		}
+		if (vp->q_used[i] < vp->q_used[smallest])
+			smallest = i;
+	}
 
-	n = vp->nports++;
-	n = n & (VNET_MAX_TXQS - 1);
-	port->q_index = n;
-	netif_tx_wake_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port),
-						port->q_index));
+	vp->nports++;
+	vp->q_used[smallest]++;
+	port->q_index = smallest;
 }
 EXPORT_SYMBOL_GPL(sunvnet_port_add_txq_common);
 
 void sunvnet_port_rm_txq_common(struct vnet_port *port)
 {
 	port->vp->nports--;
-	netif_tx_stop_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port),
-						port->q_index));
+	port->vp->q_used[port->q_index]--;
+	port->q_index = 0;
 }
 EXPORT_SYMBOL_GPL(sunvnet_port_rm_txq_common);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h
index ce5c824128a3..b20d6fa7ef25 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.h
+++ b/drivers/net/ethernet/sun/sunvnet_common.h
@@ -35,6 +35,19 @@ struct vnet_tx_entry {
 
 struct vnet;
 
+struct vnet_port_stats {
+	/* keep them all the same size */
+	u32 rx_bytes;
+	u32 tx_bytes;
+	u32 rx_packets;
+	u32 tx_packets;
+	u32 event_up;
+	u32 event_reset;
+	u32 q_placeholder;
+};
+
+#define NUM_VNET_PORT_STATS  (sizeof(struct vnet_port_stats) / sizeof(u32))
+
 /* Structure to describe a vnet-port or vsw-port in the MD.
  * If the vsw bit is set, this structure represents a vswitch
  * port, and the net_device can be found from ->dev. If the
@@ -44,6 +57,8 @@ struct vnet;
 struct vnet_port {
 	struct vio_driver_state	vio;
 
+	struct vnet_port_stats stats;
+
 	struct hlist_node	hash;
 	u8			raddr[ETH_ALEN];
 	unsigned		switch_port:1;
@@ -97,22 +112,15 @@ struct vnet_mcast_entry {
 };
 
 struct vnet {
-	/* Protects port_list and port_hash.  */
-	spinlock_t		lock;
-
+	spinlock_t		lock; /* Protects port_list and port_hash.  */
 	struct net_device	*dev;
-
 	u32			msg_enable;
-
+	u8			q_used[VNET_MAX_TXQS];
 	struct list_head	port_list;
-
 	struct hlist_head	port_hash[VNET_PORT_HASH_SIZE];
-
 	struct vnet_mcast_entry	*mcast_list;
-
 	struct list_head	list;
 	u64			local_mac;
-
 	int			nports;
 };
 
@@ -139,6 +147,7 @@ int sunvnet_handle_attr_common(struct vio_driver_state *vio, void *arg);
 void sunvnet_handshake_complete_common(struct vio_driver_state *vio);
 int sunvnet_poll_common(struct napi_struct *napi, int budget);
 void sunvnet_port_free_tx_bufs_common(struct vnet_port *port);
+void vnet_port_reset(struct vnet_port *port);
 bool sunvnet_port_is_up_common(struct vnet_port *vnet);
 void sunvnet_port_add_txq_common(struct vnet_port *port);
 void sunvnet_port_rm_txq_common(struct vnet_port *port);
diff --git a/drivers/net/ethernet/synopsys/Kconfig b/drivers/net/ethernet/synopsys/Kconfig
new file mode 100644
index 000000000000..a9503884e1c2
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/Kconfig
@@ -0,0 +1,41 @@
+#
+# Synopsys network device configuration
+#
+
+config NET_VENDOR_SYNOPSYS
+	bool "Synopsys devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) device belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Synopsys devices. If you say Y, you will be asked
+	  for your specific device in the following questions.
+
+if NET_VENDOR_SYNOPSYS
+
+config DWC_XLGMAC
+	tristate "Synopsys DWC Enterprise Ethernet (XLGMAC) driver support"
+	depends on HAS_IOMEM && HAS_DMA
+	select BITREVERSE
+	select CRC32
+	---help---
+	  This driver supports the Synopsys DesignWare Cores Enterprise
+	  Ethernet (dwc-xlgmac).
+
+if DWC_XLGMAC
+
+config DWC_XLGMAC_PCI
+	tristate "XLGMAC PCI bus support"
+	depends on DWC_XLGMAC && PCI
+	---help---
+	  This selects the pci bus support for the dwc-xlgmac driver.
+	  This driver was tested on Synopsys XLGMAC IP Prototyping Kit.
+
+	  If you have a controller with this interface, say Y or M here.
+	  If unsure, say N.
+
+endif # DWC_XLGMAC
+
+endif # NET_VENDOR_SYNOPSYS
diff --git a/drivers/net/ethernet/synopsys/Makefile b/drivers/net/ethernet/synopsys/Makefile
new file mode 100644
index 000000000000..0ad01916f11e
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the Synopsys network device drivers.
+#
+
+obj-$(CONFIG_DWC_XLGMAC) += dwc-xlgmac.o
+dwc-xlgmac-objs := dwc-xlgmac-net.o dwc-xlgmac-desc.o \
+		   dwc-xlgmac-hw.o dwc-xlgmac-common.o \
+		   dwc-xlgmac-ethtool.o
+
+dwc-xlgmac-$(CONFIG_DWC_XLGMAC_PCI) += dwc-xlgmac-pci.o
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
new file mode 100644
index 000000000000..d655a4261e98
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
@@ -0,0 +1,737 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+MODULE_LICENSE("Dual BSD/GPL");
+
+static int debug = -1;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "DWC ethernet debug level (0=none,...,16=all)");
+static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
+				      NETIF_MSG_IFUP);
+
+static unsigned char dev_addr[6] = {0, 0x55, 0x7b, 0xb5, 0x7d, 0xf7};
+
+static void xlgmac_read_mac_addr(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+
+	/* Currently it uses a static mac address for test */
+	memcpy(pdata->mac_addr, dev_addr, netdev->addr_len);
+}
+
+static void xlgmac_default_config(struct xlgmac_pdata *pdata)
+{
+	pdata->tx_osp_mode = DMA_OSP_ENABLE;
+	pdata->tx_sf_mode = MTL_TSF_ENABLE;
+	pdata->rx_sf_mode = MTL_RSF_DISABLE;
+	pdata->pblx8 = DMA_PBL_X8_ENABLE;
+	pdata->tx_pbl = DMA_PBL_32;
+	pdata->rx_pbl = DMA_PBL_32;
+	pdata->tx_threshold = MTL_TX_THRESHOLD_128;
+	pdata->rx_threshold = MTL_RX_THRESHOLD_128;
+	pdata->tx_pause = 1;
+	pdata->rx_pause = 1;
+	pdata->phy_speed = SPEED_25000;
+	pdata->sysclk_rate = XLGMAC_SYSCLOCK;
+
+	strlcpy(pdata->drv_name, XLGMAC_DRV_NAME, sizeof(pdata->drv_name));
+	strlcpy(pdata->drv_ver, XLGMAC_DRV_VERSION, sizeof(pdata->drv_ver));
+}
+
+static void xlgmac_init_all_ops(struct xlgmac_pdata *pdata)
+{
+	xlgmac_init_desc_ops(&pdata->desc_ops);
+	xlgmac_init_hw_ops(&pdata->hw_ops);
+}
+
+static int xlgmac_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct net_device *netdev = pdata->netdev;
+	unsigned int i;
+	int ret;
+
+	/* Set default configuration data */
+	xlgmac_default_config(pdata);
+
+	/* Set irq, base_addr, MAC address, */
+	netdev->irq = pdata->dev_irq;
+	netdev->base_addr = (unsigned long)pdata->mac_regs;
+	xlgmac_read_mac_addr(pdata);
+	memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len);
+
+	/* Set all the function pointers */
+	xlgmac_init_all_ops(pdata);
+
+	/* Issue software reset to device */
+	hw_ops->exit(pdata);
+
+	/* Populate the hardware features */
+	xlgmac_get_all_hw_features(pdata);
+	xlgmac_print_all_hw_features(pdata);
+
+	/* TODO: Set the PHY mode to XLGMII */
+
+	/* Set the DMA mask */
+	ret = dma_set_mask_and_coherent(pdata->dev,
+					DMA_BIT_MASK(pdata->hw_feat.dma_width));
+	if (ret) {
+		dev_err(pdata->dev, "dma_set_mask_and_coherent failed\n");
+		return ret;
+	}
+
+	/* Channel and ring params initializtion
+	 *  pdata->channel_count;
+	 *  pdata->tx_ring_count;
+	 *  pdata->rx_ring_count;
+	 *  pdata->tx_desc_count;
+	 *  pdata->rx_desc_count;
+	 */
+	BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_TX_DESC_CNT);
+	pdata->tx_desc_count = XLGMAC_TX_DESC_CNT;
+	if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) {
+		dev_err(pdata->dev, "tx descriptor count (%d) is not valid\n",
+			pdata->tx_desc_count);
+		ret = -EINVAL;
+		return ret;
+	}
+	BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_RX_DESC_CNT);
+	pdata->rx_desc_count = XLGMAC_RX_DESC_CNT;
+	if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) {
+		dev_err(pdata->dev, "rx descriptor count (%d) is not valid\n",
+			pdata->rx_desc_count);
+		ret = -EINVAL;
+		return ret;
+	}
+
+	pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(),
+				     pdata->hw_feat.tx_ch_cnt);
+	pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count,
+				     pdata->hw_feat.tx_q_cnt);
+	pdata->tx_q_count = pdata->tx_ring_count;
+	ret = netif_set_real_num_tx_queues(netdev, pdata->tx_q_count);
+	if (ret) {
+		dev_err(pdata->dev, "error setting real tx queue count\n");
+		return ret;
+	}
+
+	pdata->rx_ring_count = min_t(unsigned int,
+				     netif_get_num_default_rss_queues(),
+				     pdata->hw_feat.rx_ch_cnt);
+	pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count,
+				     pdata->hw_feat.rx_q_cnt);
+	pdata->rx_q_count = pdata->rx_ring_count;
+	ret = netif_set_real_num_rx_queues(netdev, pdata->rx_q_count);
+	if (ret) {
+		dev_err(pdata->dev, "error setting real rx queue count\n");
+		return ret;
+	}
+
+	pdata->channel_count =
+		max_t(unsigned int, pdata->tx_ring_count, pdata->rx_ring_count);
+
+	/* Initialize RSS hash key and lookup table */
+	netdev_rss_key_fill(pdata->rss_key, sizeof(pdata->rss_key));
+
+	for (i = 0; i < XLGMAC_RSS_MAX_TABLE_SIZE; i++)
+		pdata->rss_table[i] = XLGMAC_SET_REG_BITS(
+					pdata->rss_table[i],
+					MAC_RSSDR_DMCH_POS,
+					MAC_RSSDR_DMCH_LEN,
+					i % pdata->rx_ring_count);
+
+	pdata->rss_options = XLGMAC_SET_REG_BITS(
+				pdata->rss_options,
+				MAC_RSSCR_IP2TE_POS,
+				MAC_RSSCR_IP2TE_LEN, 1);
+	pdata->rss_options = XLGMAC_SET_REG_BITS(
+				pdata->rss_options,
+				MAC_RSSCR_TCP4TE_POS,
+				MAC_RSSCR_TCP4TE_LEN, 1);
+	pdata->rss_options = XLGMAC_SET_REG_BITS(
+				pdata->rss_options,
+				MAC_RSSCR_UDP4TE_POS,
+				MAC_RSSCR_UDP4TE_LEN, 1);
+
+	/* Set device operations */
+	netdev->netdev_ops = xlgmac_get_netdev_ops();
+	netdev->ethtool_ops = xlgmac_get_ethtool_ops();
+
+	/* Set device features */
+	if (pdata->hw_feat.tso) {
+		netdev->hw_features = NETIF_F_TSO;
+		netdev->hw_features |= NETIF_F_TSO6;
+		netdev->hw_features |= NETIF_F_SG;
+		netdev->hw_features |= NETIF_F_IP_CSUM;
+		netdev->hw_features |= NETIF_F_IPV6_CSUM;
+	} else if (pdata->hw_feat.tx_coe) {
+		netdev->hw_features = NETIF_F_IP_CSUM;
+		netdev->hw_features |= NETIF_F_IPV6_CSUM;
+	}
+
+	if (pdata->hw_feat.rx_coe) {
+		netdev->hw_features |= NETIF_F_RXCSUM;
+		netdev->hw_features |= NETIF_F_GRO;
+	}
+
+	if (pdata->hw_feat.rss)
+		netdev->hw_features |= NETIF_F_RXHASH;
+
+	netdev->vlan_features |= netdev->hw_features;
+
+	netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	if (pdata->hw_feat.sa_vlan_ins)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+	if (pdata->hw_feat.vlhash)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	netdev->features |= netdev->hw_features;
+	pdata->netdev_features = netdev->features;
+
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* Use default watchdog timeout */
+	netdev->watchdog_timeo = 0;
+
+	/* Tx coalesce parameters initialization */
+	pdata->tx_usecs = XLGMAC_INIT_DMA_TX_USECS;
+	pdata->tx_frames = XLGMAC_INIT_DMA_TX_FRAMES;
+
+	/* Rx coalesce parameters initialization */
+	pdata->rx_riwt = hw_ops->usec_to_riwt(pdata, XLGMAC_INIT_DMA_RX_USECS);
+	pdata->rx_usecs = XLGMAC_INIT_DMA_RX_USECS;
+	pdata->rx_frames = XLGMAC_INIT_DMA_RX_FRAMES;
+
+	return 0;
+}
+
+int xlgmac_drv_probe(struct device *dev, struct xlgmac_resources *res)
+{
+	struct xlgmac_pdata *pdata;
+	struct net_device *netdev;
+	int ret;
+
+	netdev = alloc_etherdev_mq(sizeof(struct xlgmac_pdata),
+				   XLGMAC_MAX_DMA_CHANNELS);
+
+	if (!netdev) {
+		dev_err(dev, "alloc_etherdev failed\n");
+		return -ENOMEM;
+	}
+
+	SET_NETDEV_DEV(netdev, dev);
+	dev_set_drvdata(dev, netdev);
+	pdata = netdev_priv(netdev);
+	pdata->dev = dev;
+	pdata->netdev = netdev;
+
+	pdata->dev_irq = res->irq;
+	pdata->mac_regs = res->addr;
+
+	mutex_init(&pdata->rss_mutex);
+	pdata->msg_enable = netif_msg_init(debug, default_msg_level);
+
+	ret = xlgmac_init(pdata);
+	if (ret) {
+		dev_err(dev, "xlgmac init failed\n");
+		goto err_free_netdev;
+	}
+
+	ret = register_netdev(netdev);
+	if (ret) {
+		dev_err(dev, "net device registration failed\n");
+		goto err_free_netdev;
+	}
+
+	return 0;
+
+err_free_netdev:
+	free_netdev(netdev);
+
+	return ret;
+}
+
+int xlgmac_drv_remove(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+
+	unregister_netdev(netdev);
+	free_netdev(netdev);
+
+	return 0;
+}
+
+void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx,
+			 unsigned int count,
+			 unsigned int flag)
+{
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+
+	while (count--) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, idx);
+		dma_desc = desc_data->dma_desc;
+
+		netdev_dbg(pdata->netdev, "TX: dma_desc=%p, dma_desc_addr=%pad\n",
+			   desc_data->dma_desc, &desc_data->dma_desc_addr);
+		netdev_dbg(pdata->netdev,
+			   "TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx,
+			   (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE",
+			   le32_to_cpu(dma_desc->desc0),
+			   le32_to_cpu(dma_desc->desc1),
+			   le32_to_cpu(dma_desc->desc2),
+			   le32_to_cpu(dma_desc->desc3));
+
+		idx++;
+	}
+}
+
+void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx)
+{
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, idx);
+	dma_desc = desc_data->dma_desc;
+
+	netdev_dbg(pdata->netdev, "RX: dma_desc=%p, dma_desc_addr=%pad\n",
+		   desc_data->dma_desc, &desc_data->dma_desc_addr);
+	netdev_dbg(pdata->netdev,
+		   "RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n",
+		   idx,
+		   le32_to_cpu(dma_desc->desc0),
+		   le32_to_cpu(dma_desc->desc1),
+		   le32_to_cpu(dma_desc->desc2),
+		   le32_to_cpu(dma_desc->desc3));
+}
+
+void xlgmac_print_pkt(struct net_device *netdev,
+		      struct sk_buff *skb, bool tx_rx)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb->data;
+	unsigned char *buf = skb->data;
+	unsigned char buffer[128];
+	unsigned int i, j;
+
+	netdev_dbg(netdev, "\n************** SKB dump ****************\n");
+
+	netdev_dbg(netdev, "%s packet of %d bytes\n",
+		   (tx_rx ? "TX" : "RX"), skb->len);
+
+	netdev_dbg(netdev, "Dst MAC addr: %pM\n", eth->h_dest);
+	netdev_dbg(netdev, "Src MAC addr: %pM\n", eth->h_source);
+	netdev_dbg(netdev, "Protocol: %#06hx\n", ntohs(eth->h_proto));
+
+	for (i = 0, j = 0; i < skb->len;) {
+		j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx",
+			      buf[i++]);
+
+		if ((i % 32) == 0) {
+			netdev_dbg(netdev, "  %#06x: %s\n", i - 32, buffer);
+			j = 0;
+		} else if ((i % 16) == 0) {
+			buffer[j++] = ' ';
+			buffer[j++] = ' ';
+		} else if ((i % 4) == 0) {
+			buffer[j++] = ' ';
+		}
+	}
+	if (i % 32)
+		netdev_dbg(netdev, "  %#06x: %s\n", i - (i % 32), buffer);
+
+	netdev_dbg(netdev, "\n************** SKB dump ****************\n");
+}
+
+void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_features *hw_feat = &pdata->hw_feat;
+	unsigned int mac_hfr0, mac_hfr1, mac_hfr2;
+
+	mac_hfr0 = readl(pdata->mac_regs + MAC_HWF0R);
+	mac_hfr1 = readl(pdata->mac_regs + MAC_HWF1R);
+	mac_hfr2 = readl(pdata->mac_regs + MAC_HWF2R);
+
+	memset(hw_feat, 0, sizeof(*hw_feat));
+
+	hw_feat->version = readl(pdata->mac_regs + MAC_VR);
+
+	/* Hardware feature register 0 */
+	hw_feat->phyifsel    = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_PHYIFSEL_POS,
+						MAC_HWF0R_PHYIFSEL_LEN);
+	hw_feat->vlhash      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_VLHASH_POS,
+						MAC_HWF0R_VLHASH_LEN);
+	hw_feat->sma         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_SMASEL_POS,
+						MAC_HWF0R_SMASEL_LEN);
+	hw_feat->rwk         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_RWKSEL_POS,
+						MAC_HWF0R_RWKSEL_LEN);
+	hw_feat->mgk         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_MGKSEL_POS,
+						MAC_HWF0R_MGKSEL_LEN);
+	hw_feat->mmc         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_MMCSEL_POS,
+						MAC_HWF0R_MMCSEL_LEN);
+	hw_feat->aoe         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_ARPOFFSEL_POS,
+						MAC_HWF0R_ARPOFFSEL_LEN);
+	hw_feat->ts          = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_TSSEL_POS,
+						MAC_HWF0R_TSSEL_LEN);
+	hw_feat->eee         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_EEESEL_POS,
+						MAC_HWF0R_EEESEL_LEN);
+	hw_feat->tx_coe      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_TXCOESEL_POS,
+						MAC_HWF0R_TXCOESEL_LEN);
+	hw_feat->rx_coe      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_RXCOESEL_POS,
+						MAC_HWF0R_RXCOESEL_LEN);
+	hw_feat->addn_mac    = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_ADDMACADRSEL_POS,
+						MAC_HWF0R_ADDMACADRSEL_LEN);
+	hw_feat->ts_src      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_TSSTSSEL_POS,
+						MAC_HWF0R_TSSTSSEL_LEN);
+	hw_feat->sa_vlan_ins = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_SAVLANINS_POS,
+						MAC_HWF0R_SAVLANINS_LEN);
+
+	/* Hardware feature register 1 */
+	hw_feat->rx_fifo_size  = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_RXFIFOSIZE_POS,
+						MAC_HWF1R_RXFIFOSIZE_LEN);
+	hw_feat->tx_fifo_size  = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_TXFIFOSIZE_POS,
+						MAC_HWF1R_TXFIFOSIZE_LEN);
+	hw_feat->adv_ts_hi     = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_ADVTHWORD_POS,
+						MAC_HWF1R_ADVTHWORD_LEN);
+	hw_feat->dma_width     = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_ADDR64_POS,
+						MAC_HWF1R_ADDR64_LEN);
+	hw_feat->dcb           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_DCBEN_POS,
+						MAC_HWF1R_DCBEN_LEN);
+	hw_feat->sph           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_SPHEN_POS,
+						MAC_HWF1R_SPHEN_LEN);
+	hw_feat->tso           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_TSOEN_POS,
+						MAC_HWF1R_TSOEN_LEN);
+	hw_feat->dma_debug     = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_DBGMEMA_POS,
+						MAC_HWF1R_DBGMEMA_LEN);
+	hw_feat->rss           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_RSSEN_POS,
+						MAC_HWF1R_RSSEN_LEN);
+	hw_feat->tc_cnt	       = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_NUMTC_POS,
+						MAC_HWF1R_NUMTC_LEN);
+	hw_feat->hash_table_size = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_HASHTBLSZ_POS,
+						MAC_HWF1R_HASHTBLSZ_LEN);
+	hw_feat->l3l4_filter_num = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_L3L4FNUM_POS,
+						MAC_HWF1R_L3L4FNUM_LEN);
+
+	/* Hardware feature register 2 */
+	hw_feat->rx_q_cnt     = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_RXQCNT_POS,
+						MAC_HWF2R_RXQCNT_LEN);
+	hw_feat->tx_q_cnt     = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_TXQCNT_POS,
+						MAC_HWF2R_TXQCNT_LEN);
+	hw_feat->rx_ch_cnt    = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_RXCHCNT_POS,
+						MAC_HWF2R_RXCHCNT_LEN);
+	hw_feat->tx_ch_cnt    = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_TXCHCNT_POS,
+						MAC_HWF2R_TXCHCNT_LEN);
+	hw_feat->pps_out_num  = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_PPSOUTNUM_POS,
+						MAC_HWF2R_PPSOUTNUM_LEN);
+	hw_feat->aux_snap_num = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_AUXSNAPNUM_POS,
+						MAC_HWF2R_AUXSNAPNUM_LEN);
+
+	/* Translate the Hash Table size into actual number */
+	switch (hw_feat->hash_table_size) {
+	case 0:
+		break;
+	case 1:
+		hw_feat->hash_table_size = 64;
+		break;
+	case 2:
+		hw_feat->hash_table_size = 128;
+		break;
+	case 3:
+		hw_feat->hash_table_size = 256;
+		break;
+	}
+
+	/* Translate the address width setting into actual number */
+	switch (hw_feat->dma_width) {
+	case 0:
+		hw_feat->dma_width = 32;
+		break;
+	case 1:
+		hw_feat->dma_width = 40;
+		break;
+	case 2:
+		hw_feat->dma_width = 48;
+		break;
+	default:
+		hw_feat->dma_width = 32;
+	}
+
+	/* The Queue, Channel and TC counts are zero based so increment them
+	 * to get the actual number
+	 */
+	hw_feat->rx_q_cnt++;
+	hw_feat->tx_q_cnt++;
+	hw_feat->rx_ch_cnt++;
+	hw_feat->tx_ch_cnt++;
+	hw_feat->tc_cnt++;
+}
+
+void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata)
+{
+	char *str = NULL;
+
+	XLGMAC_PR("\n");
+	XLGMAC_PR("=====================================================\n");
+	XLGMAC_PR("\n");
+	XLGMAC_PR("HW support following features\n");
+	XLGMAC_PR("\n");
+	/* HW Feature Register0 */
+	XLGMAC_PR("VLAN Hash Filter Selected                   : %s\n",
+		  pdata->hw_feat.vlhash ? "YES" : "NO");
+	XLGMAC_PR("SMA (MDIO) Interface                        : %s\n",
+		  pdata->hw_feat.sma ? "YES" : "NO");
+	XLGMAC_PR("PMT Remote Wake-up Packet Enable            : %s\n",
+		  pdata->hw_feat.rwk ? "YES" : "NO");
+	XLGMAC_PR("PMT Magic Packet Enable                     : %s\n",
+		  pdata->hw_feat.mgk ? "YES" : "NO");
+	XLGMAC_PR("RMON/MMC Module Enable                      : %s\n",
+		  pdata->hw_feat.mmc ? "YES" : "NO");
+	XLGMAC_PR("ARP Offload Enabled                         : %s\n",
+		  pdata->hw_feat.aoe ? "YES" : "NO");
+	XLGMAC_PR("IEEE 1588-2008 Timestamp Enabled            : %s\n",
+		  pdata->hw_feat.ts ? "YES" : "NO");
+	XLGMAC_PR("Energy Efficient Ethernet Enabled           : %s\n",
+		  pdata->hw_feat.eee ? "YES" : "NO");
+	XLGMAC_PR("Transmit Checksum Offload Enabled           : %s\n",
+		  pdata->hw_feat.tx_coe ? "YES" : "NO");
+	XLGMAC_PR("Receive Checksum Offload Enabled            : %s\n",
+		  pdata->hw_feat.rx_coe ? "YES" : "NO");
+	XLGMAC_PR("Additional MAC Addresses 1-31 Selected      : %s\n",
+		  pdata->hw_feat.addn_mac ? "YES" : "NO");
+
+	switch (pdata->hw_feat.ts_src) {
+	case 0:
+		str = "RESERVED";
+		break;
+	case 1:
+		str = "INTERNAL";
+		break;
+	case 2:
+		str = "EXTERNAL";
+		break;
+	case 3:
+		str = "BOTH";
+		break;
+	}
+	XLGMAC_PR("Timestamp System Time Source                : %s\n", str);
+
+	XLGMAC_PR("Source Address or VLAN Insertion Enable     : %s\n",
+		  pdata->hw_feat.sa_vlan_ins ? "YES" : "NO");
+
+	/* HW Feature Register1 */
+	switch (pdata->hw_feat.rx_fifo_size) {
+	case 0:
+		str = "128 bytes";
+		break;
+	case 1:
+		str = "256 bytes";
+		break;
+	case 2:
+		str = "512 bytes";
+		break;
+	case 3:
+		str = "1 KBytes";
+		break;
+	case 4:
+		str = "2 KBytes";
+		break;
+	case 5:
+		str = "4 KBytes";
+		break;
+	case 6:
+		str = "8 KBytes";
+		break;
+	case 7:
+		str = "16 KBytes";
+		break;
+	case 8:
+		str = "32 kBytes";
+		break;
+	case 9:
+		str = "64 KBytes";
+		break;
+	case 10:
+		str = "128 KBytes";
+		break;
+	case 11:
+		str = "256 KBytes";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("MTL Receive FIFO Size                       : %s\n", str);
+
+	switch (pdata->hw_feat.tx_fifo_size) {
+	case 0:
+		str = "128 bytes";
+		break;
+	case 1:
+		str = "256 bytes";
+		break;
+	case 2:
+		str = "512 bytes";
+		break;
+	case 3:
+		str = "1 KBytes";
+		break;
+	case 4:
+		str = "2 KBytes";
+		break;
+	case 5:
+		str = "4 KBytes";
+		break;
+	case 6:
+		str = "8 KBytes";
+		break;
+	case 7:
+		str = "16 KBytes";
+		break;
+	case 8:
+		str = "32 kBytes";
+		break;
+	case 9:
+		str = "64 KBytes";
+		break;
+	case 10:
+		str = "128 KBytes";
+		break;
+	case 11:
+		str = "256 KBytes";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("MTL Transmit FIFO Size                      : %s\n", str);
+
+	XLGMAC_PR("IEEE 1588 High Word Register Enable         : %s\n",
+		  pdata->hw_feat.adv_ts_hi ? "YES" : "NO");
+	XLGMAC_PR("Address width                               : %u\n",
+		  pdata->hw_feat.dma_width);
+	XLGMAC_PR("DCB Feature Enable                          : %s\n",
+		  pdata->hw_feat.dcb ? "YES" : "NO");
+	XLGMAC_PR("Split Header Feature Enable                 : %s\n",
+		  pdata->hw_feat.sph ? "YES" : "NO");
+	XLGMAC_PR("TCP Segmentation Offload Enable             : %s\n",
+		  pdata->hw_feat.tso ? "YES" : "NO");
+	XLGMAC_PR("DMA Debug Registers Enabled                 : %s\n",
+		  pdata->hw_feat.dma_debug ? "YES" : "NO");
+	XLGMAC_PR("RSS Feature Enabled                         : %s\n",
+		  pdata->hw_feat.rss ? "YES" : "NO");
+	XLGMAC_PR("Number of Traffic classes                   : %u\n",
+		  (pdata->hw_feat.tc_cnt));
+	XLGMAC_PR("Hash Table Size                             : %u\n",
+		  pdata->hw_feat.hash_table_size);
+	XLGMAC_PR("Total number of L3 or L4 Filters            : %u\n",
+		  pdata->hw_feat.l3l4_filter_num);
+
+	/* HW Feature Register2 */
+	XLGMAC_PR("Number of MTL Receive Queues                : %u\n",
+		  pdata->hw_feat.rx_q_cnt);
+	XLGMAC_PR("Number of MTL Transmit Queues               : %u\n",
+		  pdata->hw_feat.tx_q_cnt);
+	XLGMAC_PR("Number of DMA Receive Channels              : %u\n",
+		  pdata->hw_feat.rx_ch_cnt);
+	XLGMAC_PR("Number of DMA Transmit Channels             : %u\n",
+		  pdata->hw_feat.tx_ch_cnt);
+
+	switch (pdata->hw_feat.pps_out_num) {
+	case 0:
+		str = "No PPS output";
+		break;
+	case 1:
+		str = "1 PPS output";
+		break;
+	case 2:
+		str = "2 PPS output";
+		break;
+	case 3:
+		str = "3 PPS output";
+		break;
+	case 4:
+		str = "4 PPS output";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("Number of PPS Outputs                       : %s\n", str);
+
+	switch (pdata->hw_feat.aux_snap_num) {
+	case 0:
+		str = "No auxiliary input";
+		break;
+	case 1:
+		str = "1 auxiliary input";
+		break;
+	case 2:
+		str = "2 auxiliary input";
+		break;
+	case 3:
+		str = "3 auxiliary input";
+		break;
+	case 4:
+		str = "4 auxiliary input";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("Number of Auxiliary Snapshot Inputs         : %s", str);
+
+	XLGMAC_PR("\n");
+	XLGMAC_PR("=====================================================\n");
+	XLGMAC_PR("\n");
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
new file mode 100644
index 000000000000..e9672b1f9968
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
@@ -0,0 +1,644 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static void xlgmac_unmap_desc_data(struct xlgmac_pdata *pdata,
+				   struct xlgmac_desc_data *desc_data)
+{
+	if (desc_data->skb_dma) {
+		if (desc_data->mapped_as_page) {
+			dma_unmap_page(pdata->dev, desc_data->skb_dma,
+				       desc_data->skb_dma_len, DMA_TO_DEVICE);
+		} else {
+			dma_unmap_single(pdata->dev, desc_data->skb_dma,
+					 desc_data->skb_dma_len, DMA_TO_DEVICE);
+		}
+		desc_data->skb_dma = 0;
+		desc_data->skb_dma_len = 0;
+	}
+
+	if (desc_data->skb) {
+		dev_kfree_skb_any(desc_data->skb);
+		desc_data->skb = NULL;
+	}
+
+	if (desc_data->rx.hdr.pa.pages)
+		put_page(desc_data->rx.hdr.pa.pages);
+
+	if (desc_data->rx.hdr.pa_unmap.pages) {
+		dma_unmap_page(pdata->dev, desc_data->rx.hdr.pa_unmap.pages_dma,
+			       desc_data->rx.hdr.pa_unmap.pages_len,
+			       DMA_FROM_DEVICE);
+		put_page(desc_data->rx.hdr.pa_unmap.pages);
+	}
+
+	if (desc_data->rx.buf.pa.pages)
+		put_page(desc_data->rx.buf.pa.pages);
+
+	if (desc_data->rx.buf.pa_unmap.pages) {
+		dma_unmap_page(pdata->dev, desc_data->rx.buf.pa_unmap.pages_dma,
+			       desc_data->rx.buf.pa_unmap.pages_len,
+			       DMA_FROM_DEVICE);
+		put_page(desc_data->rx.buf.pa_unmap.pages);
+	}
+
+	memset(&desc_data->tx, 0, sizeof(desc_data->tx));
+	memset(&desc_data->rx, 0, sizeof(desc_data->rx));
+
+	desc_data->mapped_as_page = 0;
+
+	if (desc_data->state_saved) {
+		desc_data->state_saved = 0;
+		desc_data->state.skb = NULL;
+		desc_data->state.len = 0;
+		desc_data->state.error = 0;
+	}
+}
+
+static void xlgmac_free_ring(struct xlgmac_pdata *pdata,
+			     struct xlgmac_ring *ring)
+{
+	struct xlgmac_desc_data *desc_data;
+	unsigned int i;
+
+	if (!ring)
+		return;
+
+	if (ring->desc_data_head) {
+		for (i = 0; i < ring->dma_desc_count; i++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+			xlgmac_unmap_desc_data(pdata, desc_data);
+		}
+
+		kfree(ring->desc_data_head);
+		ring->desc_data_head = NULL;
+	}
+
+	if (ring->rx_hdr_pa.pages) {
+		dma_unmap_page(pdata->dev, ring->rx_hdr_pa.pages_dma,
+			       ring->rx_hdr_pa.pages_len, DMA_FROM_DEVICE);
+		put_page(ring->rx_hdr_pa.pages);
+
+		ring->rx_hdr_pa.pages = NULL;
+		ring->rx_hdr_pa.pages_len = 0;
+		ring->rx_hdr_pa.pages_offset = 0;
+		ring->rx_hdr_pa.pages_dma = 0;
+	}
+
+	if (ring->rx_buf_pa.pages) {
+		dma_unmap_page(pdata->dev, ring->rx_buf_pa.pages_dma,
+			       ring->rx_buf_pa.pages_len, DMA_FROM_DEVICE);
+		put_page(ring->rx_buf_pa.pages);
+
+		ring->rx_buf_pa.pages = NULL;
+		ring->rx_buf_pa.pages_len = 0;
+		ring->rx_buf_pa.pages_offset = 0;
+		ring->rx_buf_pa.pages_dma = 0;
+	}
+
+	if (ring->dma_desc_head) {
+		dma_free_coherent(pdata->dev,
+				  (sizeof(struct xlgmac_dma_desc) *
+				  ring->dma_desc_count),
+				  ring->dma_desc_head,
+				  ring->dma_desc_head_addr);
+		ring->dma_desc_head = NULL;
+	}
+}
+
+static int xlgmac_init_ring(struct xlgmac_pdata *pdata,
+			    struct xlgmac_ring *ring,
+			    unsigned int dma_desc_count)
+{
+	if (!ring)
+		return 0;
+
+	/* Descriptors */
+	ring->dma_desc_count = dma_desc_count;
+	ring->dma_desc_head = dma_alloc_coherent(pdata->dev,
+					(sizeof(struct xlgmac_dma_desc) *
+					 dma_desc_count),
+					&ring->dma_desc_head_addr,
+					GFP_KERNEL);
+	if (!ring->dma_desc_head)
+		return -ENOMEM;
+
+	/* Array of descriptor data */
+	ring->desc_data_head = kcalloc(dma_desc_count,
+					sizeof(struct xlgmac_desc_data),
+					GFP_KERNEL);
+	if (!ring->desc_data_head)
+		return -ENOMEM;
+
+	netif_dbg(pdata, drv, pdata->netdev,
+		  "dma_desc_head=%p, dma_desc_head_addr=%pad, desc_data_head=%p\n",
+		ring->dma_desc_head,
+		&ring->dma_desc_head_addr,
+		ring->desc_data_head);
+
+	return 0;
+}
+
+static void xlgmac_free_rings(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (!pdata->channel_head)
+		return;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		xlgmac_free_ring(pdata, channel->tx_ring);
+		xlgmac_free_ring(pdata, channel->rx_ring);
+	}
+}
+
+static int xlgmac_alloc_rings(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	int ret;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n",
+			  channel->name);
+
+		ret = xlgmac_init_ring(pdata, channel->tx_ring,
+				       pdata->tx_desc_count);
+
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Tx ring");
+			goto err_init_ring;
+		}
+
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n",
+			  channel->name);
+
+		ret = xlgmac_init_ring(pdata, channel->rx_ring,
+				       pdata->rx_desc_count);
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Rx ring\n");
+			goto err_init_ring;
+		}
+	}
+
+	return 0;
+
+err_init_ring:
+	xlgmac_free_rings(pdata);
+
+	return ret;
+}
+
+static void xlgmac_free_channels(struct xlgmac_pdata *pdata)
+{
+	if (!pdata->channel_head)
+		return;
+
+	kfree(pdata->channel_head->tx_ring);
+	pdata->channel_head->tx_ring = NULL;
+
+	kfree(pdata->channel_head->rx_ring);
+	pdata->channel_head->rx_ring = NULL;
+
+	kfree(pdata->channel_head);
+
+	pdata->channel_head = NULL;
+	pdata->channel_count = 0;
+}
+
+static int xlgmac_alloc_channels(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel_head, *channel;
+	struct xlgmac_ring *tx_ring, *rx_ring;
+	int ret = -ENOMEM;
+	unsigned int i;
+
+	channel_head = kcalloc(pdata->channel_count,
+			       sizeof(struct xlgmac_channel), GFP_KERNEL);
+	if (!channel_head)
+		return ret;
+
+	netif_dbg(pdata, drv, pdata->netdev,
+		  "channel_head=%p\n", channel_head);
+
+	tx_ring = kcalloc(pdata->tx_ring_count, sizeof(struct xlgmac_ring),
+			  GFP_KERNEL);
+	if (!tx_ring)
+		goto err_tx_ring;
+
+	rx_ring = kcalloc(pdata->rx_ring_count, sizeof(struct xlgmac_ring),
+			  GFP_KERNEL);
+	if (!rx_ring)
+		goto err_rx_ring;
+
+	for (i = 0, channel = channel_head; i < pdata->channel_count;
+		i++, channel++) {
+		snprintf(channel->name, sizeof(channel->name), "channel-%u", i);
+		channel->pdata = pdata;
+		channel->queue_index = i;
+		channel->dma_regs = pdata->mac_regs + DMA_CH_BASE +
+				    (DMA_CH_INC * i);
+
+		if (pdata->per_channel_irq) {
+			/* Get the per DMA interrupt */
+			ret = pdata->channel_irq[i];
+			if (ret < 0) {
+				netdev_err(pdata->netdev,
+					   "get_irq %u failed\n",
+					   i + 1);
+				goto err_irq;
+			}
+			channel->dma_irq = ret;
+		}
+
+		if (i < pdata->tx_ring_count)
+			channel->tx_ring = tx_ring++;
+
+		if (i < pdata->rx_ring_count)
+			channel->rx_ring = rx_ring++;
+
+		netif_dbg(pdata, drv, pdata->netdev,
+			  "%s: dma_regs=%p, tx_ring=%p, rx_ring=%p\n",
+			  channel->name, channel->dma_regs,
+			  channel->tx_ring, channel->rx_ring);
+	}
+
+	pdata->channel_head = channel_head;
+
+	return 0;
+
+err_irq:
+	kfree(rx_ring);
+
+err_rx_ring:
+	kfree(tx_ring);
+
+err_tx_ring:
+	kfree(channel_head);
+
+	return ret;
+}
+
+static void xlgmac_free_channels_and_rings(struct xlgmac_pdata *pdata)
+{
+	xlgmac_free_rings(pdata);
+
+	xlgmac_free_channels(pdata);
+}
+
+static int xlgmac_alloc_channels_and_rings(struct xlgmac_pdata *pdata)
+{
+	int ret;
+
+	ret = xlgmac_alloc_channels(pdata);
+	if (ret)
+		goto err_alloc;
+
+	ret = xlgmac_alloc_rings(pdata);
+	if (ret)
+		goto err_alloc;
+
+	return 0;
+
+err_alloc:
+	xlgmac_free_channels_and_rings(pdata);
+
+	return ret;
+}
+
+static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata,
+			      struct xlgmac_page_alloc *pa,
+			      gfp_t gfp, int order)
+{
+	struct page *pages = NULL;
+	dma_addr_t pages_dma;
+
+	/* Try to obtain pages, decreasing order if necessary */
+	gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
+	while (order >= 0) {
+		pages = alloc_pages(gfp, order);
+		if (pages)
+			break;
+
+		order--;
+	}
+	if (!pages)
+		return -ENOMEM;
+
+	/* Map the pages */
+	pages_dma = dma_map_page(pdata->dev, pages, 0,
+				 PAGE_SIZE << order, DMA_FROM_DEVICE);
+	if (dma_mapping_error(pdata->dev, pages_dma)) {
+		put_page(pages);
+		return -ENOMEM;
+	}
+
+	pa->pages = pages;
+	pa->pages_len = PAGE_SIZE << order;
+	pa->pages_offset = 0;
+	pa->pages_dma = pages_dma;
+
+	return 0;
+}
+
+static void xlgmac_set_buffer_data(struct xlgmac_buffer_data *bd,
+				   struct xlgmac_page_alloc *pa,
+				   unsigned int len)
+{
+	get_page(pa->pages);
+	bd->pa = *pa;
+
+	bd->dma_base = pa->pages_dma;
+	bd->dma_off = pa->pages_offset;
+	bd->dma_len = len;
+
+	pa->pages_offset += len;
+	if ((pa->pages_offset + len) > pa->pages_len) {
+		/* This data descriptor is responsible for unmapping page(s) */
+		bd->pa_unmap = *pa;
+
+		/* Get a new allocation next time */
+		pa->pages = NULL;
+		pa->pages_len = 0;
+		pa->pages_offset = 0;
+		pa->pages_dma = 0;
+	}
+}
+
+static int xlgmac_map_rx_buffer(struct xlgmac_pdata *pdata,
+				struct xlgmac_ring *ring,
+				struct xlgmac_desc_data *desc_data)
+{
+	int order, ret;
+
+	if (!ring->rx_hdr_pa.pages) {
+		ret = xlgmac_alloc_pages(pdata, &ring->rx_hdr_pa,
+					 GFP_ATOMIC, 0);
+		if (ret)
+			return ret;
+	}
+
+	if (!ring->rx_buf_pa.pages) {
+		order = max_t(int, PAGE_ALLOC_COSTLY_ORDER - 1, 0);
+		ret = xlgmac_alloc_pages(pdata, &ring->rx_buf_pa,
+					 GFP_ATOMIC, order);
+		if (ret)
+			return ret;
+	}
+
+	/* Set up the header page info */
+	xlgmac_set_buffer_data(&desc_data->rx.hdr, &ring->rx_hdr_pa,
+			       XLGMAC_SKB_ALLOC_SIZE);
+
+	/* Set up the buffer page info */
+	xlgmac_set_buffer_data(&desc_data->rx.buf, &ring->rx_buf_pa,
+			       pdata->rx_buf_size);
+
+	return 0;
+}
+
+static void xlgmac_tx_desc_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	dma_addr_t dma_desc_addr;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		dma_desc = ring->dma_desc_head;
+		dma_desc_addr = ring->dma_desc_head_addr;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+
+			desc_data->dma_desc = dma_desc;
+			desc_data->dma_desc_addr = dma_desc_addr;
+
+			dma_desc++;
+			dma_desc_addr += sizeof(struct xlgmac_dma_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+		memset(&ring->tx, 0, sizeof(ring->tx));
+
+		hw_ops->tx_desc_init(channel);
+	}
+}
+
+static void xlgmac_rx_desc_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	dma_addr_t dma_desc_addr;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		dma_desc = ring->dma_desc_head;
+		dma_desc_addr = ring->dma_desc_head_addr;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+
+			desc_data->dma_desc = dma_desc;
+			desc_data->dma_desc_addr = dma_desc_addr;
+
+			if (xlgmac_map_rx_buffer(pdata, ring, desc_data))
+				break;
+
+			dma_desc++;
+			dma_desc_addr += sizeof(struct xlgmac_dma_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+
+		hw_ops->rx_desc_init(channel);
+	}
+}
+
+static int xlgmac_map_tx_skb(struct xlgmac_channel *channel,
+			     struct sk_buff *skb)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->tx_ring;
+	unsigned int start_index, cur_index;
+	struct xlgmac_desc_data *desc_data;
+	unsigned int offset, datalen, len;
+	struct xlgmac_pkt_info *pkt_info;
+	struct skb_frag_struct *frag;
+	unsigned int tso, vlan;
+	dma_addr_t skb_dma;
+	unsigned int i;
+
+	offset = 0;
+	start_index = ring->cur;
+	cur_index = ring->cur;
+
+	pkt_info = &ring->pkt_info;
+	pkt_info->desc_count = 0;
+	pkt_info->length = 0;
+
+	tso = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				  TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+				  TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN);
+	vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				   TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+				   TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN);
+
+	/* Save space for a context descriptor if needed */
+	if ((tso && (pkt_info->mss != ring->tx.cur_mss)) ||
+	    (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag)))
+		cur_index++;
+	desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+
+	if (tso) {
+		/* Map the TSO header */
+		skb_dma = dma_map_single(pdata->dev, skb->data,
+					 pkt_info->header_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		desc_data->skb_dma = skb_dma;
+		desc_data->skb_dma_len = pkt_info->header_len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb header: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, pkt_info->header_len);
+
+		offset = pkt_info->header_len;
+
+		pkt_info->length += pkt_info->header_len;
+
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+	}
+
+	/* Map the (remainder of the) packet */
+	for (datalen = skb_headlen(skb) - offset; datalen; ) {
+		len = min_t(unsigned int, datalen, XLGMAC_TX_MAX_BUF_SIZE);
+
+		skb_dma = dma_map_single(pdata->dev, skb->data + offset, len,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		desc_data->skb_dma = skb_dma;
+		desc_data->skb_dma_len = len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb data: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, len);
+
+		datalen -= len;
+		offset += len;
+
+		pkt_info->length += len;
+
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "mapping frag %u\n", i);
+
+		frag = &skb_shinfo(skb)->frags[i];
+		offset = 0;
+
+		for (datalen = skb_frag_size(frag); datalen; ) {
+			len = min_t(unsigned int, datalen,
+				    XLGMAC_TX_MAX_BUF_SIZE);
+
+			skb_dma = skb_frag_dma_map(pdata->dev, frag, offset,
+						   len, DMA_TO_DEVICE);
+			if (dma_mapping_error(pdata->dev, skb_dma)) {
+				netdev_alert(pdata->netdev,
+					     "skb_frag_dma_map failed\n");
+				goto err_out;
+			}
+			desc_data->skb_dma = skb_dma;
+			desc_data->skb_dma_len = len;
+			desc_data->mapped_as_page = 1;
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "skb frag: index=%u, dma=%pad, len=%u\n",
+				  cur_index, &skb_dma, len);
+
+			datalen -= len;
+			offset += len;
+
+			pkt_info->length += len;
+
+			cur_index++;
+			desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+		}
+	}
+
+	/* Save the skb address in the last entry. We always have some data
+	 * that has been mapped so desc_data is always advanced past the last
+	 * piece of mapped data - use the entry pointed to by cur_index - 1.
+	 */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index - 1);
+	desc_data->skb = skb;
+
+	/* Save the number of descriptor entries used */
+	pkt_info->desc_count = cur_index - start_index;
+
+	return pkt_info->desc_count;
+
+err_out:
+	while (start_index < cur_index) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, start_index++);
+		xlgmac_unmap_desc_data(pdata, desc_data);
+	}
+
+	return 0;
+}
+
+void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops)
+{
+	desc_ops->alloc_channles_and_rings = xlgmac_alloc_channels_and_rings;
+	desc_ops->free_channels_and_rings = xlgmac_free_channels_and_rings;
+	desc_ops->map_tx_skb = xlgmac_map_tx_skb;
+	desc_ops->map_rx_buffer = xlgmac_map_rx_buffer;
+	desc_ops->unmap_desc_data = xlgmac_unmap_desc_data;
+	desc_ops->tx_desc_init = xlgmac_tx_desc_init;
+	desc_ops->rx_desc_init = xlgmac_rx_desc_init;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c
new file mode 100644
index 000000000000..fde722136869
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c
@@ -0,0 +1,275 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/ethtool.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+struct xlgmac_stats_desc {
+	char stat_string[ETH_GSTRING_LEN];
+	int stat_offset;
+};
+
+#define XLGMAC_STAT(str, var)					\
+	{							\
+		str,						\
+		offsetof(struct xlgmac_pdata, stats.var),	\
+	}
+
+static const struct xlgmac_stats_desc xlgmac_gstring_stats[] = {
+	/* MMC TX counters */
+	XLGMAC_STAT("tx_bytes", txoctetcount_gb),
+	XLGMAC_STAT("tx_bytes_good", txoctetcount_g),
+	XLGMAC_STAT("tx_packets", txframecount_gb),
+	XLGMAC_STAT("tx_packets_good", txframecount_g),
+	XLGMAC_STAT("tx_unicast_packets", txunicastframes_gb),
+	XLGMAC_STAT("tx_broadcast_packets", txbroadcastframes_gb),
+	XLGMAC_STAT("tx_broadcast_packets_good", txbroadcastframes_g),
+	XLGMAC_STAT("tx_multicast_packets", txmulticastframes_gb),
+	XLGMAC_STAT("tx_multicast_packets_good", txmulticastframes_g),
+	XLGMAC_STAT("tx_vlan_packets_good", txvlanframes_g),
+	XLGMAC_STAT("tx_64_byte_packets", tx64octets_gb),
+	XLGMAC_STAT("tx_65_to_127_byte_packets", tx65to127octets_gb),
+	XLGMAC_STAT("tx_128_to_255_byte_packets", tx128to255octets_gb),
+	XLGMAC_STAT("tx_256_to_511_byte_packets", tx256to511octets_gb),
+	XLGMAC_STAT("tx_512_to_1023_byte_packets", tx512to1023octets_gb),
+	XLGMAC_STAT("tx_1024_to_max_byte_packets", tx1024tomaxoctets_gb),
+	XLGMAC_STAT("tx_underflow_errors", txunderflowerror),
+	XLGMAC_STAT("tx_pause_frames", txpauseframes),
+
+	/* MMC RX counters */
+	XLGMAC_STAT("rx_bytes", rxoctetcount_gb),
+	XLGMAC_STAT("rx_bytes_good", rxoctetcount_g),
+	XLGMAC_STAT("rx_packets", rxframecount_gb),
+	XLGMAC_STAT("rx_unicast_packets_good", rxunicastframes_g),
+	XLGMAC_STAT("rx_broadcast_packets_good", rxbroadcastframes_g),
+	XLGMAC_STAT("rx_multicast_packets_good", rxmulticastframes_g),
+	XLGMAC_STAT("rx_vlan_packets", rxvlanframes_gb),
+	XLGMAC_STAT("rx_64_byte_packets", rx64octets_gb),
+	XLGMAC_STAT("rx_65_to_127_byte_packets", rx65to127octets_gb),
+	XLGMAC_STAT("rx_128_to_255_byte_packets", rx128to255octets_gb),
+	XLGMAC_STAT("rx_256_to_511_byte_packets", rx256to511octets_gb),
+	XLGMAC_STAT("rx_512_to_1023_byte_packets", rx512to1023octets_gb),
+	XLGMAC_STAT("rx_1024_to_max_byte_packets", rx1024tomaxoctets_gb),
+	XLGMAC_STAT("rx_undersize_packets_good", rxundersize_g),
+	XLGMAC_STAT("rx_oversize_packets_good", rxoversize_g),
+	XLGMAC_STAT("rx_crc_errors", rxcrcerror),
+	XLGMAC_STAT("rx_crc_errors_small_packets", rxrunterror),
+	XLGMAC_STAT("rx_crc_errors_giant_packets", rxjabbererror),
+	XLGMAC_STAT("rx_length_errors", rxlengtherror),
+	XLGMAC_STAT("rx_out_of_range_errors", rxoutofrangetype),
+	XLGMAC_STAT("rx_fifo_overflow_errors", rxfifooverflow),
+	XLGMAC_STAT("rx_watchdog_errors", rxwatchdogerror),
+	XLGMAC_STAT("rx_pause_frames", rxpauseframes),
+
+	/* Extra counters */
+	XLGMAC_STAT("tx_tso_packets", tx_tso_packets),
+	XLGMAC_STAT("rx_split_header_packets", rx_split_header_packets),
+	XLGMAC_STAT("tx_process_stopped", tx_process_stopped),
+	XLGMAC_STAT("rx_process_stopped", rx_process_stopped),
+	XLGMAC_STAT("tx_buffer_unavailable", tx_buffer_unavailable),
+	XLGMAC_STAT("rx_buffer_unavailable", rx_buffer_unavailable),
+	XLGMAC_STAT("fatal_bus_error", fatal_bus_error),
+	XLGMAC_STAT("tx_vlan_packets", tx_vlan_packets),
+	XLGMAC_STAT("rx_vlan_packets", rx_vlan_packets),
+	XLGMAC_STAT("napi_poll_isr", napi_poll_isr),
+	XLGMAC_STAT("napi_poll_txtimer", napi_poll_txtimer),
+};
+
+#define XLGMAC_STATS_COUNT	ARRAY_SIZE(xlgmac_gstring_stats)
+
+static void xlgmac_ethtool_get_drvinfo(struct net_device *netdev,
+				       struct ethtool_drvinfo *drvinfo)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	u32 ver = pdata->hw_feat.version;
+	u32 snpsver, devid, userver;
+
+	strlcpy(drvinfo->driver, pdata->drv_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, pdata->drv_ver, sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, dev_name(pdata->dev),
+		sizeof(drvinfo->bus_info));
+	/* S|SNPSVER: Synopsys-defined Version
+	 * D|DEVID: Indicates the Device family
+	 * U|USERVER: User-defined Version
+	 */
+	snpsver = XLGMAC_GET_REG_BITS(ver, MAC_VR_SNPSVER_POS,
+				      MAC_VR_SNPSVER_LEN);
+	devid = XLGMAC_GET_REG_BITS(ver, MAC_VR_DEVID_POS,
+				    MAC_VR_DEVID_LEN);
+	userver = XLGMAC_GET_REG_BITS(ver, MAC_VR_USERVER_POS,
+				      MAC_VR_USERVER_LEN);
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "S.D.U: %x.%x.%x", snpsver, devid, userver);
+}
+
+static u32 xlgmac_ethtool_get_msglevel(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+	return pdata->msg_enable;
+}
+
+static void xlgmac_ethtool_set_msglevel(struct net_device *netdev,
+					u32 msglevel)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+	pdata->msg_enable = msglevel;
+}
+
+static void xlgmac_ethtool_get_channels(struct net_device *netdev,
+					struct ethtool_channels *channel)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+	channel->max_rx = XLGMAC_MAX_DMA_CHANNELS;
+	channel->max_tx = XLGMAC_MAX_DMA_CHANNELS;
+	channel->rx_count = pdata->rx_q_count;
+	channel->tx_count = pdata->tx_q_count;
+}
+
+static int xlgmac_ethtool_get_coalesce(struct net_device *netdev,
+				       struct ethtool_coalesce *ec)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+	memset(ec, 0, sizeof(struct ethtool_coalesce));
+	ec->rx_coalesce_usecs = pdata->rx_usecs;
+	ec->rx_max_coalesced_frames = pdata->rx_frames;
+	ec->tx_max_coalesced_frames = pdata->tx_frames;
+
+	return 0;
+}
+
+static int xlgmac_ethtool_set_coalesce(struct net_device *netdev,
+				       struct ethtool_coalesce *ec)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	unsigned int rx_frames, rx_riwt, rx_usecs;
+	unsigned int tx_frames;
+
+	/* Check for not supported parameters */
+	if ((ec->rx_coalesce_usecs_irq) || (ec->rx_max_coalesced_frames_irq) ||
+	    (ec->tx_coalesce_usecs) || (ec->tx_coalesce_usecs_high) ||
+	    (ec->tx_max_coalesced_frames_irq) || (ec->tx_coalesce_usecs_irq) ||
+	    (ec->stats_block_coalesce_usecs) ||  (ec->pkt_rate_low) ||
+	    (ec->use_adaptive_rx_coalesce) || (ec->use_adaptive_tx_coalesce) ||
+	    (ec->rx_max_coalesced_frames_low) || (ec->rx_coalesce_usecs_low) ||
+	    (ec->tx_coalesce_usecs_low) || (ec->tx_max_coalesced_frames_low) ||
+	    (ec->pkt_rate_high) || (ec->rx_coalesce_usecs_high) ||
+	    (ec->rx_max_coalesced_frames_high) ||
+	    (ec->tx_max_coalesced_frames_high) ||
+	    (ec->rate_sample_interval))
+		return -EOPNOTSUPP;
+
+	rx_usecs = ec->rx_coalesce_usecs;
+	rx_riwt = hw_ops->usec_to_riwt(pdata, rx_usecs);
+	rx_frames = ec->rx_max_coalesced_frames;
+	tx_frames = ec->tx_max_coalesced_frames;
+
+	if ((rx_riwt > XLGMAC_MAX_DMA_RIWT) ||
+	    (rx_riwt < XLGMAC_MIN_DMA_RIWT) ||
+	    (rx_frames > pdata->rx_desc_count))
+		return -EINVAL;
+
+	if (tx_frames > pdata->tx_desc_count)
+		return -EINVAL;
+
+	pdata->rx_riwt = rx_riwt;
+	pdata->rx_usecs = rx_usecs;
+	pdata->rx_frames = rx_frames;
+	hw_ops->config_rx_coalesce(pdata);
+
+	pdata->tx_frames = tx_frames;
+	hw_ops->config_tx_coalesce(pdata);
+
+	return 0;
+}
+
+static void xlgmac_ethtool_get_strings(struct net_device *netdev,
+				       u32 stringset, u8 *data)
+{
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < XLGMAC_STATS_COUNT; i++) {
+			memcpy(data, xlgmac_gstring_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			data += ETH_GSTRING_LEN;
+		}
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static int xlgmac_ethtool_get_sset_count(struct net_device *netdev,
+					 int stringset)
+{
+	int ret;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		ret = XLGMAC_STATS_COUNT;
+		break;
+
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static void xlgmac_ethtool_get_ethtool_stats(struct net_device *netdev,
+					     struct ethtool_stats *stats,
+					     u64 *data)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	u8 *stat;
+	int i;
+
+	pdata->hw_ops.read_mmc_stats(pdata);
+	for (i = 0; i < XLGMAC_STATS_COUNT; i++) {
+		stat = (u8 *)pdata + xlgmac_gstring_stats[i].stat_offset;
+		*data++ = *(u64 *)stat;
+	}
+}
+
+static const struct ethtool_ops xlgmac_ethtool_ops = {
+	.get_drvinfo = xlgmac_ethtool_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_msglevel = xlgmac_ethtool_get_msglevel,
+	.set_msglevel = xlgmac_ethtool_set_msglevel,
+	.get_channels = xlgmac_ethtool_get_channels,
+	.get_coalesce = xlgmac_ethtool_get_coalesce,
+	.set_coalesce = xlgmac_ethtool_set_coalesce,
+	.get_strings = xlgmac_ethtool_get_strings,
+	.get_sset_count = xlgmac_ethtool_get_sset_count,
+	.get_ethtool_stats = xlgmac_ethtool_get_ethtool_stats,
+};
+
+const struct ethtool_ops *xlgmac_get_ethtool_ops(void)
+{
+	return &xlgmac_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
new file mode 100644
index 000000000000..458a7844260a
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -0,0 +1,3147 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/phy.h>
+#include <linux/mdio.h>
+#include <linux/clk.h>
+#include <linux/bitrev.h>
+#include <linux/crc32.h>
+#include <linux/dcbnl.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_tx_complete(struct xlgmac_dma_desc *dma_desc)
+{
+	return !XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				TX_NORMAL_DESC3_OWN_POS,
+				TX_NORMAL_DESC3_OWN_LEN);
+}
+
+static int xlgmac_disable_rx_csum(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS,
+				     MAC_RCR_IPC_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+
+	return 0;
+}
+
+static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS,
+				     MAC_RCR_IPC_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+
+	return 0;
+}
+
+static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr)
+{
+	unsigned int mac_addr_hi, mac_addr_lo;
+
+	mac_addr_hi = (addr[5] <<  8) | (addr[4] <<  0);
+	mac_addr_lo = (addr[3] << 24) | (addr[2] << 16) |
+		      (addr[1] <<  8) | (addr[0] <<  0);
+
+	writel(mac_addr_hi, pdata->mac_regs + MAC_MACA0HR);
+	writel(mac_addr_lo, pdata->mac_regs + MAC_MACA0LR);
+
+	return 0;
+}
+
+static void xlgmac_set_mac_reg(struct xlgmac_pdata *pdata,
+			       struct netdev_hw_addr *ha,
+			       unsigned int *mac_reg)
+{
+	unsigned int mac_addr_hi, mac_addr_lo;
+	u8 *mac_addr;
+
+	mac_addr_lo = 0;
+	mac_addr_hi = 0;
+
+	if (ha) {
+		mac_addr = (u8 *)&mac_addr_lo;
+		mac_addr[0] = ha->addr[0];
+		mac_addr[1] = ha->addr[1];
+		mac_addr[2] = ha->addr[2];
+		mac_addr[3] = ha->addr[3];
+		mac_addr = (u8 *)&mac_addr_hi;
+		mac_addr[0] = ha->addr[4];
+		mac_addr[1] = ha->addr[5];
+
+		netif_dbg(pdata, drv, pdata->netdev,
+			  "adding mac address %pM at %#x\n",
+			  ha->addr, *mac_reg);
+
+		mac_addr_hi = XLGMAC_SET_REG_BITS(mac_addr_hi,
+						  MAC_MACA1HR_AE_POS,
+						MAC_MACA1HR_AE_LEN,
+						1);
+	}
+
+	writel(mac_addr_hi, pdata->mac_regs + *mac_reg);
+	*mac_reg += MAC_MACA_INC;
+	writel(mac_addr_lo, pdata->mac_regs + *mac_reg);
+	*mac_reg += MAC_MACA_INC;
+}
+
+static int xlgmac_enable_rx_vlan_stripping(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_VLANTR);
+	/* Put the VLAN tag in the Rx descriptor */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLRXS_POS,
+				     MAC_VLANTR_EVLRXS_LEN, 1);
+	/* Don't check the VLAN type */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_DOVLTC_POS,
+				     MAC_VLANTR_DOVLTC_LEN, 1);
+	/* Check only C-TAG (0x8100) packets */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ERSVLM_POS,
+				     MAC_VLANTR_ERSVLM_LEN, 0);
+	/* Don't consider an S-TAG (0x88A8) packet as a VLAN packet */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ESVL_POS,
+				     MAC_VLANTR_ESVL_LEN, 0);
+	/* Enable VLAN tag stripping */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS,
+				     MAC_VLANTR_EVLS_LEN, 0x3);
+	writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+	return 0;
+}
+
+static int xlgmac_disable_rx_vlan_stripping(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_VLANTR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS,
+				     MAC_VLANTR_EVLS_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+	return 0;
+}
+
+static int xlgmac_enable_rx_vlan_filtering(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	/* Enable VLAN filtering */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS,
+				     MAC_PFR_VTFE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	regval = readl(pdata->mac_regs + MAC_VLANTR);
+	/* Enable VLAN Hash Table filtering */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTHM_POS,
+				     MAC_VLANTR_VTHM_LEN, 1);
+	/* Disable VLAN tag inverse matching */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTIM_POS,
+				     MAC_VLANTR_VTIM_LEN, 0);
+	/* Only filter on the lower 12-bits of the VLAN tag */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ETV_POS,
+				     MAC_VLANTR_ETV_LEN, 1);
+	/* In order for the VLAN Hash Table filtering to be effective,
+	 * the VLAN tag identifier in the VLAN Tag Register must not
+	 * be zero.  Set the VLAN tag identifier to "1" to enable the
+	 * VLAN Hash Table filtering.  This implies that a VLAN tag of
+	 * 1 will always pass filtering.
+	 */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VL_POS,
+				     MAC_VLANTR_VL_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+	return 0;
+}
+
+static int xlgmac_disable_rx_vlan_filtering(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	/* Disable VLAN filtering */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS,
+				     MAC_PFR_VTFE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	return 0;
+}
+
+static u32 xlgmac_vid_crc32_le(__le16 vid_le)
+{
+	unsigned char *data = (unsigned char *)&vid_le;
+	unsigned char data_byte = 0;
+	u32 poly = 0xedb88320;
+	u32 crc = ~0;
+	u32 temp = 0;
+	int i, bits;
+
+	bits = get_bitmask_order(VLAN_VID_MASK);
+	for (i = 0; i < bits; i++) {
+		if ((i % 8) == 0)
+			data_byte = data[i / 8];
+
+		temp = ((crc & 1) ^ data_byte) & 1;
+		crc >>= 1;
+		data_byte >>= 1;
+
+		if (temp)
+			crc ^= poly;
+	}
+
+	return crc;
+}
+
+static int xlgmac_update_vlan_hash_table(struct xlgmac_pdata *pdata)
+{
+	u16 vlan_hash_table = 0;
+	__le16 vid_le;
+	u32 regval;
+	u32 crc;
+	u16 vid;
+
+	/* Generate the VLAN Hash Table value */
+	for_each_set_bit(vid, pdata->active_vlans, VLAN_N_VID) {
+		/* Get the CRC32 value of the VLAN ID */
+		vid_le = cpu_to_le16(vid);
+		crc = bitrev32(~xlgmac_vid_crc32_le(vid_le)) >> 28;
+
+		vlan_hash_table |= (1 << crc);
+	}
+
+	regval = readl(pdata->mac_regs + MAC_VLANHTR);
+	/* Set the VLAN Hash Table filtering register */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANHTR_VLHT_POS,
+				     MAC_VLANHTR_VLHT_LEN, vlan_hash_table);
+	writel(regval, pdata->mac_regs + MAC_VLANHTR);
+
+	return 0;
+}
+
+static int xlgmac_set_promiscuous_mode(struct xlgmac_pdata *pdata,
+				       unsigned int enable)
+{
+	unsigned int val = enable ? 1 : 0;
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR),
+				     MAC_PFR_PR_POS, MAC_PFR_PR_LEN);
+	if (regval == val)
+		return 0;
+
+	netif_dbg(pdata, drv, pdata->netdev, "%s promiscuous mode\n",
+		  enable ? "entering" : "leaving");
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PR_POS,
+				     MAC_PFR_PR_LEN, val);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	/* Hardware will still perform VLAN filtering in promiscuous mode */
+	if (enable) {
+		xlgmac_disable_rx_vlan_filtering(pdata);
+	} else {
+		if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+			xlgmac_enable_rx_vlan_filtering(pdata);
+	}
+
+	return 0;
+}
+
+static int xlgmac_set_all_multicast_mode(struct xlgmac_pdata *pdata,
+					 unsigned int enable)
+{
+	unsigned int val = enable ? 1 : 0;
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR),
+				     MAC_PFR_PM_POS, MAC_PFR_PM_LEN);
+	if (regval == val)
+		return 0;
+
+	netif_dbg(pdata, drv, pdata->netdev, "%s allmulti mode\n",
+		  enable ? "entering" : "leaving");
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PM_POS,
+				     MAC_PFR_PM_LEN, val);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	return 0;
+}
+
+static void xlgmac_set_mac_addn_addrs(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	struct netdev_hw_addr *ha;
+	unsigned int addn_macs;
+	unsigned int mac_reg;
+
+	mac_reg = MAC_MACA1HR;
+	addn_macs = pdata->hw_feat.addn_mac;
+
+	if (netdev_uc_count(netdev) > addn_macs) {
+		xlgmac_set_promiscuous_mode(pdata, 1);
+	} else {
+		netdev_for_each_uc_addr(ha, netdev) {
+			xlgmac_set_mac_reg(pdata, ha, &mac_reg);
+			addn_macs--;
+		}
+
+		if (netdev_mc_count(netdev) > addn_macs) {
+			xlgmac_set_all_multicast_mode(pdata, 1);
+		} else {
+			netdev_for_each_mc_addr(ha, netdev) {
+				xlgmac_set_mac_reg(pdata, ha, &mac_reg);
+				addn_macs--;
+			}
+		}
+	}
+
+	/* Clear remaining additional MAC address entries */
+	while (addn_macs--)
+		xlgmac_set_mac_reg(pdata, NULL, &mac_reg);
+}
+
+static void xlgmac_set_mac_hash_table(struct xlgmac_pdata *pdata)
+{
+	unsigned int hash_table_shift, hash_table_count;
+	u32 hash_table[XLGMAC_MAC_HASH_TABLE_SIZE];
+	struct net_device *netdev = pdata->netdev;
+	struct netdev_hw_addr *ha;
+	unsigned int hash_reg;
+	unsigned int i;
+	u32 crc;
+
+	hash_table_shift = 26 - (pdata->hw_feat.hash_table_size >> 7);
+	hash_table_count = pdata->hw_feat.hash_table_size / 32;
+	memset(hash_table, 0, sizeof(hash_table));
+
+	/* Build the MAC Hash Table register values */
+	netdev_for_each_uc_addr(ha, netdev) {
+		crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN));
+		crc >>= hash_table_shift;
+		hash_table[crc >> 5] |= (1 << (crc & 0x1f));
+	}
+
+	netdev_for_each_mc_addr(ha, netdev) {
+		crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN));
+		crc >>= hash_table_shift;
+		hash_table[crc >> 5] |= (1 << (crc & 0x1f));
+	}
+
+	/* Set the MAC Hash Table registers */
+	hash_reg = MAC_HTR0;
+	for (i = 0; i < hash_table_count; i++) {
+		writel(hash_table[i], pdata->mac_regs + hash_reg);
+		hash_reg += MAC_HTR_INC;
+	}
+}
+
+static int xlgmac_add_mac_addresses(struct xlgmac_pdata *pdata)
+{
+	if (pdata->hw_feat.hash_table_size)
+		xlgmac_set_mac_hash_table(pdata);
+	else
+		xlgmac_set_mac_addn_addrs(pdata);
+
+	return 0;
+}
+
+static void xlgmac_config_mac_address(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	xlgmac_set_mac_address(pdata, pdata->netdev->dev_addr);
+
+	/* Filtering is done using perfect filtering and hash filtering */
+	if (pdata->hw_feat.hash_table_size) {
+		regval = readl(pdata->mac_regs + MAC_PFR);
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HPF_POS,
+					     MAC_PFR_HPF_LEN, 1);
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HUC_POS,
+					     MAC_PFR_HUC_LEN, 1);
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HMC_POS,
+					     MAC_PFR_HMC_LEN, 1);
+		writel(regval, pdata->mac_regs + MAC_PFR);
+	}
+}
+
+static void xlgmac_config_jumbo_enable(struct xlgmac_pdata *pdata)
+{
+	unsigned int val;
+	u32 regval;
+
+	val = (pdata->netdev->mtu > XLGMAC_STD_PACKET_MTU) ? 1 : 0;
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_JE_POS,
+				     MAC_RCR_JE_LEN, val);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static void xlgmac_config_checksum_offload(struct xlgmac_pdata *pdata)
+{
+	if (pdata->netdev->features & NETIF_F_RXCSUM)
+		xlgmac_enable_rx_csum(pdata);
+	else
+		xlgmac_disable_rx_csum(pdata);
+}
+
+static void xlgmac_config_vlan_support(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_VLANIR);
+	/* Indicate that VLAN Tx CTAGs come from context descriptors */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_CSVL_POS,
+				     MAC_VLANIR_CSVL_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_VLTI_POS,
+				     MAC_VLANIR_VLTI_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_VLANIR);
+
+	/* Set the current VLAN Hash Table register value */
+	xlgmac_update_vlan_hash_table(pdata);
+
+	if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		xlgmac_enable_rx_vlan_filtering(pdata);
+	else
+		xlgmac_disable_rx_vlan_filtering(pdata);
+
+	if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		xlgmac_enable_rx_vlan_stripping(pdata);
+	else
+		xlgmac_disable_rx_vlan_stripping(pdata);
+}
+
+static int xlgmac_config_rx_mode(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	unsigned int pr_mode, am_mode;
+
+	pr_mode = ((netdev->flags & IFF_PROMISC) != 0);
+	am_mode = ((netdev->flags & IFF_ALLMULTI) != 0);
+
+	xlgmac_set_promiscuous_mode(pdata, pr_mode);
+	xlgmac_set_all_multicast_mode(pdata, am_mode);
+
+	xlgmac_add_mac_addresses(pdata);
+
+	return 0;
+}
+
+static void xlgmac_prepare_tx_stop(struct xlgmac_pdata *pdata,
+				   struct xlgmac_channel *channel)
+{
+	unsigned int tx_dsr, tx_pos, tx_qidx;
+	unsigned long tx_timeout;
+	unsigned int tx_status;
+
+	/* Calculate the status register to read and the position within */
+	if (channel->queue_index < DMA_DSRX_FIRST_QUEUE) {
+		tx_dsr = DMA_DSR0;
+		tx_pos = (channel->queue_index * DMA_DSR_Q_LEN) +
+			 DMA_DSR0_TPS_START;
+	} else {
+		tx_qidx = channel->queue_index - DMA_DSRX_FIRST_QUEUE;
+
+		tx_dsr = DMA_DSR1 + ((tx_qidx / DMA_DSRX_QPR) * DMA_DSRX_INC);
+		tx_pos = ((tx_qidx % DMA_DSRX_QPR) * DMA_DSR_Q_LEN) +
+			 DMA_DSRX_TPS_START;
+	}
+
+	/* The Tx engine cannot be stopped if it is actively processing
+	 * descriptors. Wait for the Tx engine to enter the stopped or
+	 * suspended state.  Don't wait forever though...
+	 */
+	tx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ);
+	while (time_before(jiffies, tx_timeout)) {
+		tx_status = readl(pdata->mac_regs + tx_dsr);
+		tx_status = XLGMAC_GET_REG_BITS(tx_status, tx_pos,
+						DMA_DSR_TPS_LEN);
+		if ((tx_status == DMA_TPS_STOPPED) ||
+		    (tx_status == DMA_TPS_SUSPENDED))
+			break;
+
+		usleep_range(500, 1000);
+	}
+
+	if (!time_before(jiffies, tx_timeout))
+		netdev_info(pdata->netdev,
+			    "timed out waiting for Tx DMA channel %u to stop\n",
+			    channel->queue_index);
+}
+
+static void xlgmac_enable_tx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	/* Enable each Tx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS,
+					     DMA_CH_TCR_ST_LEN, 1);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+
+	/* Enable each Tx queue */
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS,
+					     MTL_Q_TQOMR_TXQEN_LEN,
+					MTL_Q_ENABLED);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	/* Enable MAC Tx */
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS,
+				     MAC_TCR_TE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+}
+
+static void xlgmac_disable_tx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	/* Prepare for Tx DMA channel stop */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		xlgmac_prepare_tx_stop(pdata, channel);
+	}
+
+	/* Disable MAC Tx */
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS,
+				     MAC_TCR_TE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	/* Disable each Tx queue */
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS,
+					     MTL_Q_TQOMR_TXQEN_LEN, 0);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	/* Disable each Tx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS,
+					     DMA_CH_TCR_ST_LEN, 0);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+}
+
+static void xlgmac_prepare_rx_stop(struct xlgmac_pdata *pdata,
+				   unsigned int queue)
+{
+	unsigned int rx_status, prxq, rxqsts;
+	unsigned long rx_timeout;
+
+	/* The Rx engine cannot be stopped if it is actively processing
+	 * packets. Wait for the Rx queue to empty the Rx fifo.  Don't
+	 * wait forever though...
+	 */
+	rx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ);
+	while (time_before(jiffies, rx_timeout)) {
+		rx_status = readl(XLGMAC_MTL_REG(pdata, queue, MTL_Q_RQDR));
+		prxq = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_PRXQ_POS,
+					   MTL_Q_RQDR_PRXQ_LEN);
+		rxqsts = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_RXQSTS_POS,
+					     MTL_Q_RQDR_RXQSTS_LEN);
+		if ((prxq == 0) && (rxqsts == 0))
+			break;
+
+		usleep_range(500, 1000);
+	}
+
+	if (!time_before(jiffies, rx_timeout))
+		netdev_info(pdata->netdev,
+			    "timed out waiting for Rx queue %u to empty\n",
+			    queue);
+}
+
+static void xlgmac_enable_rx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int regval, i;
+
+	/* Enable each Rx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS,
+					     DMA_CH_RCR_SR_LEN, 1);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+
+	/* Enable each Rx queue */
+	regval = 0;
+	for (i = 0; i < pdata->rx_q_count; i++)
+		regval |= (0x02 << (i << 1));
+	writel(regval, pdata->mac_regs + MAC_RQC0R);
+
+	/* Enable MAC Rx */
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS,
+				     MAC_RCR_DCRCC_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS,
+				     MAC_RCR_CST_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS,
+				     MAC_RCR_ACS_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS,
+				     MAC_RCR_RE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static void xlgmac_disable_rx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	/* Disable MAC Rx */
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS,
+				     MAC_RCR_DCRCC_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS,
+				     MAC_RCR_CST_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS,
+				     MAC_RCR_ACS_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS,
+				     MAC_RCR_RE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+
+	/* Prepare for Rx DMA channel stop */
+	for (i = 0; i < pdata->rx_q_count; i++)
+		xlgmac_prepare_rx_stop(pdata, i);
+
+	/* Disable each Rx queue */
+	writel(0, pdata->mac_regs + MAC_RQC0R);
+
+	/* Disable each Rx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS,
+					     DMA_CH_RCR_SR_LEN, 0);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+}
+
+static void xlgmac_tx_start_xmit(struct xlgmac_channel *channel,
+				 struct xlgmac_ring *ring)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_desc_data *desc_data;
+
+	/* Make sure everything is written before the register write */
+	wmb();
+
+	/* Issue a poll command to Tx DMA by writing address
+	 * of next immediate free descriptor
+	 */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_TDTR_LO));
+
+	/* Start the Tx timer */
+	if (pdata->tx_usecs && !channel->tx_timer_active) {
+		channel->tx_timer_active = 1;
+		mod_timer(&channel->tx_timer,
+			  jiffies + usecs_to_jiffies(pdata->tx_usecs));
+	}
+
+	ring->tx.xmit_more = 0;
+}
+
+static void xlgmac_dev_xmit(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->tx_ring;
+	unsigned int tso_context, vlan_context;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_pkt_info *pkt_info;
+	unsigned int csum, tso, vlan;
+	int start_index = ring->cur;
+	int cur_index = ring->cur;
+	unsigned int tx_set_ic;
+	int i;
+
+	pkt_info = &ring->pkt_info;
+	csum = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				   TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+				TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN);
+	tso = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				  TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+				TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN);
+	vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				   TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+				TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN);
+
+	if (tso && (pkt_info->mss != ring->tx.cur_mss))
+		tso_context = 1;
+	else
+		tso_context = 0;
+
+	if (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag))
+		vlan_context = 1;
+	else
+		vlan_context = 0;
+
+	/* Determine if an interrupt should be generated for this Tx:
+	 *   Interrupt:
+	 *     - Tx frame count exceeds the frame count setting
+	 *     - Addition of Tx frame count to the frame count since the
+	 *       last interrupt was set exceeds the frame count setting
+	 *   No interrupt:
+	 *     - No frame count setting specified (ethtool -C ethX tx-frames 0)
+	 *     - Addition of Tx frame count to the frame count since the
+	 *       last interrupt was set does not exceed the frame count setting
+	 */
+	ring->coalesce_count += pkt_info->tx_packets;
+	if (!pdata->tx_frames)
+		tx_set_ic = 0;
+	else if (pkt_info->tx_packets > pdata->tx_frames)
+		tx_set_ic = 1;
+	else if ((ring->coalesce_count % pdata->tx_frames) <
+		 pkt_info->tx_packets)
+		tx_set_ic = 1;
+	else
+		tx_set_ic = 0;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+	dma_desc = desc_data->dma_desc;
+
+	/* Create a context descriptor if this is a TSO pkt_info */
+	if (tso_context || vlan_context) {
+		if (tso_context) {
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "TSO context descriptor, mss=%u\n",
+				  pkt_info->mss);
+
+			/* Set the MSS size */
+			dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc2,
+						TX_CONTEXT_DESC2_MSS_POS,
+						TX_CONTEXT_DESC2_MSS_LEN,
+						pkt_info->mss);
+
+			/* Mark it as a CONTEXT descriptor */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_CTXT_POS,
+						TX_CONTEXT_DESC3_CTXT_LEN,
+						1);
+
+			/* Indicate this descriptor contains the MSS */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_TCMSSV_POS,
+						TX_CONTEXT_DESC3_TCMSSV_LEN,
+						1);
+
+			ring->tx.cur_mss = pkt_info->mss;
+		}
+
+		if (vlan_context) {
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "VLAN context descriptor, ctag=%u\n",
+				  pkt_info->vlan_ctag);
+
+			/* Mark it as a CONTEXT descriptor */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_CTXT_POS,
+						TX_CONTEXT_DESC3_CTXT_LEN,
+						1);
+
+			/* Set the VLAN tag */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_VT_POS,
+						TX_CONTEXT_DESC3_VT_LEN,
+						pkt_info->vlan_ctag);
+
+			/* Indicate this descriptor contains the VLAN tag */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_VLTV_POS,
+						TX_CONTEXT_DESC3_VLTV_LEN,
+						1);
+
+			ring->tx.cur_vlan_ctag = pkt_info->vlan_ctag;
+		}
+
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+		dma_desc = desc_data->dma_desc;
+	}
+
+	/* Update buffer address (for TSO this is the header) */
+	dma_desc->desc0 =  cpu_to_le32(lower_32_bits(desc_data->skb_dma));
+	dma_desc->desc1 =  cpu_to_le32(upper_32_bits(desc_data->skb_dma));
+
+	/* Update the buffer length */
+	dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc2,
+				TX_NORMAL_DESC2_HL_B1L_POS,
+				TX_NORMAL_DESC2_HL_B1L_LEN,
+				desc_data->skb_dma_len);
+
+	/* VLAN tag insertion check */
+	if (vlan) {
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_VTIR_POS,
+					TX_NORMAL_DESC2_VTIR_LEN,
+					TX_NORMAL_DESC2_VLAN_INSERT);
+		pdata->stats.tx_vlan_packets++;
+	}
+
+	/* Timestamp enablement check */
+	if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				TX_PACKET_ATTRIBUTES_PTP_POS,
+				TX_PACKET_ATTRIBUTES_PTP_LEN))
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_TTSE_POS,
+					TX_NORMAL_DESC2_TTSE_LEN,
+					1);
+
+	/* Mark it as First Descriptor */
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_FD_POS,
+				TX_NORMAL_DESC3_FD_LEN,
+				1);
+
+	/* Mark it as a NORMAL descriptor */
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_CTXT_POS,
+				TX_NORMAL_DESC3_CTXT_LEN,
+				0);
+
+	/* Set OWN bit if not the first descriptor */
+	if (cur_index != start_index)
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_OWN_POS,
+					TX_NORMAL_DESC3_OWN_LEN,
+					1);
+
+	if (tso) {
+		/* Enable TSO */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_TSE_POS,
+					TX_NORMAL_DESC3_TSE_LEN, 1);
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_TCPPL_POS,
+					TX_NORMAL_DESC3_TCPPL_LEN,
+					pkt_info->tcp_payload_len);
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_TCPHDRLEN_POS,
+					TX_NORMAL_DESC3_TCPHDRLEN_LEN,
+					pkt_info->tcp_header_len / 4);
+
+		pdata->stats.tx_tso_packets++;
+	} else {
+		/* Enable CRC and Pad Insertion */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_CPC_POS,
+					TX_NORMAL_DESC3_CPC_LEN, 0);
+
+		/* Enable HW CSUM */
+		if (csum)
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_NORMAL_DESC3_CIC_POS,
+						TX_NORMAL_DESC3_CIC_LEN,
+						0x3);
+
+		/* Set the total length to be transmitted */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_FL_POS,
+					TX_NORMAL_DESC3_FL_LEN,
+					pkt_info->length);
+	}
+
+	for (i = cur_index - start_index + 1; i < pkt_info->desc_count; i++) {
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+		dma_desc = desc_data->dma_desc;
+
+		/* Update buffer address */
+		dma_desc->desc0 =
+			cpu_to_le32(lower_32_bits(desc_data->skb_dma));
+		dma_desc->desc1 =
+			cpu_to_le32(upper_32_bits(desc_data->skb_dma));
+
+		/* Update the buffer length */
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_HL_B1L_POS,
+					TX_NORMAL_DESC2_HL_B1L_LEN,
+					desc_data->skb_dma_len);
+
+		/* Set OWN bit */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_OWN_POS,
+					TX_NORMAL_DESC3_OWN_LEN, 1);
+
+		/* Mark it as NORMAL descriptor */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_CTXT_POS,
+					TX_NORMAL_DESC3_CTXT_LEN, 0);
+
+		/* Enable HW CSUM */
+		if (csum)
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_NORMAL_DESC3_CIC_POS,
+						TX_NORMAL_DESC3_CIC_LEN,
+						0x3);
+	}
+
+	/* Set LAST bit for the last descriptor */
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_LD_POS,
+				TX_NORMAL_DESC3_LD_LEN, 1);
+
+	/* Set IC bit based on Tx coalescing settings */
+	if (tx_set_ic)
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_IC_POS,
+					TX_NORMAL_DESC2_IC_LEN, 1);
+
+	/* Save the Tx info to report back during cleanup */
+	desc_data->tx.packets = pkt_info->tx_packets;
+	desc_data->tx.bytes = pkt_info->tx_bytes;
+
+	/* In case the Tx DMA engine is running, make sure everything
+	 * is written to the descriptor(s) before setting the OWN bit
+	 * for the first descriptor
+	 */
+	dma_wmb();
+
+	/* Set OWN bit for the first descriptor */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+	dma_desc = desc_data->dma_desc;
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_OWN_POS,
+				TX_NORMAL_DESC3_OWN_LEN, 1);
+
+	if (netif_msg_tx_queued(pdata))
+		xlgmac_dump_tx_desc(pdata, ring, start_index,
+				    pkt_info->desc_count, 1);
+
+	/* Make sure ownership is written to the descriptor */
+	smp_wmb();
+
+	ring->cur = cur_index + 1;
+	if (!pkt_info->skb->xmit_more ||
+	    netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
+						   channel->queue_index)))
+		xlgmac_tx_start_xmit(channel, ring);
+	else
+		ring->tx.xmit_more = 1;
+
+	XLGMAC_PR("%s: descriptors %u to %u written\n",
+		  channel->name, start_index & (ring->dma_desc_count - 1),
+		  (ring->cur - 1) & (ring->dma_desc_count - 1));
+}
+
+static void xlgmac_get_rx_tstamp(struct xlgmac_pkt_info *pkt_info,
+				 struct xlgmac_dma_desc *dma_desc)
+{
+	u32 tsa, tsd;
+	u64 nsec;
+
+	tsa = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				     RX_CONTEXT_DESC3_TSA_POS,
+				RX_CONTEXT_DESC3_TSA_LEN);
+	tsd = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				     RX_CONTEXT_DESC3_TSD_POS,
+				RX_CONTEXT_DESC3_TSD_LEN);
+	if (tsa && !tsd) {
+		nsec = le32_to_cpu(dma_desc->desc1);
+		nsec <<= 32;
+		nsec |= le32_to_cpu(dma_desc->desc0);
+		if (nsec != 0xffffffffffffffffULL) {
+			pkt_info->rx_tstamp = nsec;
+			pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS,
+					RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN,
+					1);
+		}
+	}
+}
+
+static void xlgmac_tx_desc_reset(struct xlgmac_desc_data *desc_data)
+{
+	struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc;
+
+	/* Reset the Tx descriptor
+	 *   Set buffer 1 (lo) address to zero
+	 *   Set buffer 1 (hi) address to zero
+	 *   Reset all other control bits (IC, TTSE, B2L & B1L)
+	 *   Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC, etc)
+	 */
+	dma_desc->desc0 = 0;
+	dma_desc->desc1 = 0;
+	dma_desc->desc2 = 0;
+	dma_desc->desc3 = 0;
+
+	/* Make sure ownership is written to the descriptor */
+	dma_wmb();
+}
+
+static void xlgmac_tx_desc_init(struct xlgmac_channel *channel)
+{
+	struct xlgmac_ring *ring = channel->tx_ring;
+	struct xlgmac_desc_data *desc_data;
+	int start_index = ring->cur;
+	int i;
+
+	/* Initialze all descriptors */
+	for (i = 0; i < ring->dma_desc_count; i++) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+
+		/* Initialize Tx descriptor */
+		xlgmac_tx_desc_reset(desc_data);
+	}
+
+	/* Update the total number of Tx descriptors */
+	writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_TDRLR));
+
+	/* Update the starting address of descriptor ring */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+	writel(upper_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_TDLR_HI));
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_TDLR_LO));
+}
+
+static void xlgmac_rx_desc_reset(struct xlgmac_pdata *pdata,
+				 struct xlgmac_desc_data *desc_data,
+				 unsigned int index)
+{
+	struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc;
+	unsigned int rx_frames = pdata->rx_frames;
+	unsigned int rx_usecs = pdata->rx_usecs;
+	dma_addr_t hdr_dma, buf_dma;
+	unsigned int inte;
+
+	if (!rx_usecs && !rx_frames) {
+		/* No coalescing, interrupt for every descriptor */
+		inte = 1;
+	} else {
+		/* Set interrupt based on Rx frame coalescing setting */
+		if (rx_frames && !((index + 1) % rx_frames))
+			inte = 1;
+		else
+			inte = 0;
+	}
+
+	/* Reset the Rx descriptor
+	 *   Set buffer 1 (lo) address to header dma address (lo)
+	 *   Set buffer 1 (hi) address to header dma address (hi)
+	 *   Set buffer 2 (lo) address to buffer dma address (lo)
+	 *   Set buffer 2 (hi) address to buffer dma address (hi) and
+	 *     set control bits OWN and INTE
+	 */
+	hdr_dma = desc_data->rx.hdr.dma_base + desc_data->rx.hdr.dma_off;
+	buf_dma = desc_data->rx.buf.dma_base + desc_data->rx.buf.dma_off;
+	dma_desc->desc0 = cpu_to_le32(lower_32_bits(hdr_dma));
+	dma_desc->desc1 = cpu_to_le32(upper_32_bits(hdr_dma));
+	dma_desc->desc2 = cpu_to_le32(lower_32_bits(buf_dma));
+	dma_desc->desc3 = cpu_to_le32(upper_32_bits(buf_dma));
+
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				RX_NORMAL_DESC3_INTE_POS,
+				RX_NORMAL_DESC3_INTE_LEN,
+				inte);
+
+	/* Since the Rx DMA engine is likely running, make sure everything
+	 * is written to the descriptor(s) before setting the OWN bit
+	 * for the descriptor
+	 */
+	dma_wmb();
+
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				RX_NORMAL_DESC3_OWN_POS,
+				RX_NORMAL_DESC3_OWN_LEN,
+				1);
+
+	/* Make sure ownership is written to the descriptor */
+	dma_wmb();
+}
+
+static void xlgmac_rx_desc_init(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	unsigned int start_index = ring->cur;
+	struct xlgmac_desc_data *desc_data;
+	unsigned int i;
+
+	/* Initialize all descriptors */
+	for (i = 0; i < ring->dma_desc_count; i++) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+
+		/* Initialize Rx descriptor */
+		xlgmac_rx_desc_reset(pdata, desc_data, i);
+	}
+
+	/* Update the total number of Rx descriptors */
+	writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_RDRLR));
+
+	/* Update the starting address of descriptor ring */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+	writel(upper_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDLR_HI));
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDLR_LO));
+
+	/* Update the Rx Descriptor Tail Pointer */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index +
+					  ring->dma_desc_count - 1);
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO));
+}
+
+static int xlgmac_is_context_desc(struct xlgmac_dma_desc *dma_desc)
+{
+	/* Rx and Tx share CTXT bit, so check TDES3.CTXT bit */
+	return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				TX_NORMAL_DESC3_CTXT_POS,
+				TX_NORMAL_DESC3_CTXT_LEN);
+}
+
+static int xlgmac_is_last_desc(struct xlgmac_dma_desc *dma_desc)
+{
+	/* Rx and Tx share LD bit, so check TDES3.LD bit */
+	return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				TX_NORMAL_DESC3_LD_POS,
+				TX_NORMAL_DESC3_LD_LEN);
+}
+
+static int xlgmac_disable_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+	unsigned int max_q_count, q_count;
+	unsigned int reg, regval;
+	unsigned int i;
+
+	/* Clear MTL flow control */
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS,
+					     MTL_Q_RQOMR_EHFC_LEN, 0);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	/* Clear MAC flow control */
+	max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES;
+	q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+	reg = MAC_Q0TFCR;
+	for (i = 0; i < q_count; i++) {
+		regval = readl(pdata->mac_regs + reg);
+		regval = XLGMAC_SET_REG_BITS(regval,
+					     MAC_Q0TFCR_TFE_POS,
+					MAC_Q0TFCR_TFE_LEN,
+					0);
+		writel(regval, pdata->mac_regs + reg);
+
+		reg += MAC_QTFCR_INC;
+	}
+
+	return 0;
+}
+
+static int xlgmac_enable_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+	unsigned int max_q_count, q_count;
+	unsigned int reg, regval;
+	unsigned int i;
+
+	/* Set MTL flow control */
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS,
+					     MTL_Q_RQOMR_EHFC_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	/* Set MAC flow control */
+	max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES;
+	q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+	reg = MAC_Q0TFCR;
+	for (i = 0; i < q_count; i++) {
+		regval = readl(pdata->mac_regs + reg);
+
+		/* Enable transmit flow control */
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_TFE_POS,
+					     MAC_Q0TFCR_TFE_LEN, 1);
+		/* Set pause time */
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_PT_POS,
+					     MAC_Q0TFCR_PT_LEN, 0xffff);
+
+		writel(regval, pdata->mac_regs + reg);
+
+		reg += MAC_QTFCR_INC;
+	}
+
+	return 0;
+}
+
+static int xlgmac_disable_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RFCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS,
+				     MAC_RFCR_RFE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RFCR);
+
+	return 0;
+}
+
+static int xlgmac_enable_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RFCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS,
+				     MAC_RFCR_RFE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RFCR);
+
+	return 0;
+}
+
+static int xlgmac_config_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+	if (pdata->tx_pause)
+		xlgmac_enable_tx_flow_control(pdata);
+	else
+		xlgmac_disable_tx_flow_control(pdata);
+
+	return 0;
+}
+
+static int xlgmac_config_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+	if (pdata->rx_pause)
+		xlgmac_enable_rx_flow_control(pdata);
+	else
+		xlgmac_disable_rx_flow_control(pdata);
+
+	return 0;
+}
+
+static int xlgmac_config_rx_coalesce(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RIWT));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RIWT_RWT_POS,
+					     DMA_CH_RIWT_RWT_LEN,
+					     pdata->rx_riwt);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RIWT));
+	}
+
+	return 0;
+}
+
+static void xlgmac_config_flow_control(struct xlgmac_pdata *pdata)
+{
+	xlgmac_config_tx_flow_control(pdata);
+	xlgmac_config_rx_flow_control(pdata);
+}
+
+static void xlgmac_config_rx_fep_enable(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FEP_POS,
+					     MTL_Q_RQOMR_FEP_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+}
+
+static void xlgmac_config_rx_fup_enable(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FUP_POS,
+					     MTL_Q_RQOMR_FUP_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+}
+
+static int xlgmac_config_tx_coalesce(struct xlgmac_pdata *pdata)
+{
+	return 0;
+}
+
+static void xlgmac_config_rx_buffer_size(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_RBSZ_POS,
+					     DMA_CH_RCR_RBSZ_LEN,
+					pdata->rx_buf_size);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+}
+
+static void xlgmac_config_tso_mode(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		if (pdata->hw_feat.tso) {
+			regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+			regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_TSE_POS,
+						     DMA_CH_TCR_TSE_LEN, 1);
+			writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		}
+	}
+}
+
+static void xlgmac_config_sph_mode(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_SPH_POS,
+					     DMA_CH_CR_SPH_LEN, 1);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR));
+	}
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_HDSMS_POS,
+				     MAC_RCR_HDSMS_LEN,
+				XLGMAC_SPH_HDSMS_SIZE);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static unsigned int xlgmac_usec_to_riwt(struct xlgmac_pdata *pdata,
+					unsigned int usec)
+{
+	unsigned long rate;
+	unsigned int ret;
+
+	rate = pdata->sysclk_rate;
+
+	/* Convert the input usec value to the watchdog timer value. Each
+	 * watchdog timer value is equivalent to 256 clock cycles.
+	 * Calculate the required value as:
+	 *   ( usec * ( system_clock_mhz / 10^6 ) / 256
+	 */
+	ret = (usec * (rate / 1000000)) / 256;
+
+	return ret;
+}
+
+static unsigned int xlgmac_riwt_to_usec(struct xlgmac_pdata *pdata,
+					unsigned int riwt)
+{
+	unsigned long rate;
+	unsigned int ret;
+
+	rate = pdata->sysclk_rate;
+
+	/* Convert the input watchdog timer value to the usec value. Each
+	 * watchdog timer value is equivalent to 256 clock cycles.
+	 * Calculate the required value as:
+	 *   ( riwt * 256 ) / ( system_clock_mhz / 10^6 )
+	 */
+	ret = (riwt * 256) / (rate / 1000000);
+
+	return ret;
+}
+
+static int xlgmac_config_rx_threshold(struct xlgmac_pdata *pdata,
+				      unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RTC_POS,
+					     MTL_Q_RQOMR_RTC_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	return 0;
+}
+
+static void xlgmac_config_mtl_mode(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	/* Set Tx to weighted round robin scheduling algorithm */
+	regval = readl(pdata->mac_regs + MTL_OMR);
+	regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_ETSALG_POS,
+				     MTL_OMR_ETSALG_LEN, MTL_ETSALG_WRR);
+	writel(regval, pdata->mac_regs + MTL_OMR);
+
+	/* Set Tx traffic classes to use WRR algorithm with equal weights */
+	for (i = 0; i < pdata->hw_feat.tc_cnt; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_ETSCR_TSA_POS,
+					     MTL_TC_ETSCR_TSA_LEN, MTL_TSA_ETS);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR));
+
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_QWR_QW_POS,
+					     MTL_TC_QWR_QW_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR));
+	}
+
+	/* Set Rx to strict priority algorithm */
+	regval = readl(pdata->mac_regs + MTL_OMR);
+	regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_RAA_POS,
+				     MTL_OMR_RAA_LEN, MTL_RAA_SP);
+	writel(regval, pdata->mac_regs + MTL_OMR);
+}
+
+static void xlgmac_config_queue_mapping(struct xlgmac_pdata *pdata)
+{
+	unsigned int ppq, ppq_extra, prio, prio_queues;
+	unsigned int qptc, qptc_extra, queue;
+	unsigned int reg, regval;
+	unsigned int mask;
+	unsigned int i, j;
+
+	/* Map the MTL Tx Queues to Traffic Classes
+	 *   Note: Tx Queues >= Traffic Classes
+	 */
+	qptc = pdata->tx_q_count / pdata->hw_feat.tc_cnt;
+	qptc_extra = pdata->tx_q_count % pdata->hw_feat.tc_cnt;
+
+	for (i = 0, queue = 0; i < pdata->hw_feat.tc_cnt; i++) {
+		for (j = 0; j < qptc; j++) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TXq%u mapped to TC%u\n", queue, i);
+			regval = readl(XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			regval = XLGMAC_SET_REG_BITS(regval,
+						     MTL_Q_TQOMR_Q2TCMAP_POS,
+						     MTL_Q_TQOMR_Q2TCMAP_LEN,
+						     i);
+			writel(regval, XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			queue++;
+		}
+
+		if (i < qptc_extra) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TXq%u mapped to TC%u\n", queue, i);
+			regval = readl(XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			regval = XLGMAC_SET_REG_BITS(regval,
+						     MTL_Q_TQOMR_Q2TCMAP_POS,
+						     MTL_Q_TQOMR_Q2TCMAP_LEN,
+						     i);
+			writel(regval, XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			queue++;
+		}
+	}
+
+	/* Map the 8 VLAN priority values to available MTL Rx queues */
+	prio_queues = min_t(unsigned int, IEEE_8021QAZ_MAX_TCS,
+			    pdata->rx_q_count);
+	ppq = IEEE_8021QAZ_MAX_TCS / prio_queues;
+	ppq_extra = IEEE_8021QAZ_MAX_TCS % prio_queues;
+
+	reg = MAC_RQC2R;
+	regval = 0;
+	for (i = 0, prio = 0; i < prio_queues;) {
+		mask = 0;
+		for (j = 0; j < ppq; j++) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "PRIO%u mapped to RXq%u\n", prio, i);
+			mask |= (1 << prio);
+			prio++;
+		}
+
+		if (i < ppq_extra) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "PRIO%u mapped to RXq%u\n", prio, i);
+			mask |= (1 << prio);
+			prio++;
+		}
+
+		regval |= (mask << ((i++ % MAC_RQC2_Q_PER_REG) << 3));
+
+		if ((i % MAC_RQC2_Q_PER_REG) && (i != prio_queues))
+			continue;
+
+		writel(regval, pdata->mac_regs + reg);
+		reg += MAC_RQC2_INC;
+		regval = 0;
+	}
+
+	/* Configure one to one, MTL Rx queue to DMA Rx channel mapping
+	 *  ie Q0 <--> CH0, Q1 <--> CH1 ... Q11 <--> CH11
+	 */
+	reg = MTL_RQDCM0R;
+	regval = readl(pdata->mac_regs + reg);
+	regval |= (MTL_RQDCM0R_Q0MDMACH | MTL_RQDCM0R_Q1MDMACH |
+		    MTL_RQDCM0R_Q2MDMACH | MTL_RQDCM0R_Q3MDMACH);
+	writel(regval, pdata->mac_regs + reg);
+
+	reg += MTL_RQDCM_INC;
+	regval = readl(pdata->mac_regs + reg);
+	regval |= (MTL_RQDCM1R_Q4MDMACH | MTL_RQDCM1R_Q5MDMACH |
+		    MTL_RQDCM1R_Q6MDMACH | MTL_RQDCM1R_Q7MDMACH);
+	writel(regval, pdata->mac_regs + reg);
+
+	reg += MTL_RQDCM_INC;
+	regval = readl(pdata->mac_regs + reg);
+	regval |= (MTL_RQDCM2R_Q8MDMACH | MTL_RQDCM2R_Q9MDMACH |
+		    MTL_RQDCM2R_Q10MDMACH | MTL_RQDCM2R_Q11MDMACH);
+	writel(regval, pdata->mac_regs + reg);
+}
+
+static unsigned int xlgmac_calculate_per_queue_fifo(
+					unsigned int fifo_size,
+					unsigned int queue_count)
+{
+	unsigned int q_fifo_size;
+	unsigned int p_fifo;
+
+	/* Calculate the configured fifo size */
+	q_fifo_size = 1 << (fifo_size + 7);
+
+	/* The configured value may not be the actual amount of fifo RAM */
+	q_fifo_size = min_t(unsigned int, XLGMAC_MAX_FIFO, q_fifo_size);
+
+	q_fifo_size = q_fifo_size / queue_count;
+
+	/* Each increment in the queue fifo size represents 256 bytes of
+	 * fifo, with 0 representing 256 bytes. Distribute the fifo equally
+	 * between the queues.
+	 */
+	p_fifo = q_fifo_size / 256;
+	if (p_fifo)
+		p_fifo--;
+
+	return p_fifo;
+}
+
+static void xlgmac_config_tx_fifo_size(struct xlgmac_pdata *pdata)
+{
+	unsigned int fifo_size;
+	unsigned int i;
+	u32 regval;
+
+	fifo_size = xlgmac_calculate_per_queue_fifo(
+				pdata->hw_feat.tx_fifo_size,
+				pdata->tx_q_count);
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TQS_POS,
+					     MTL_Q_TQOMR_TQS_LEN, fifo_size);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	netif_info(pdata, drv, pdata->netdev,
+		   "%d Tx hardware queues, %d byte fifo per queue\n",
+		   pdata->tx_q_count, ((fifo_size + 1) * 256));
+}
+
+static void xlgmac_config_rx_fifo_size(struct xlgmac_pdata *pdata)
+{
+	unsigned int fifo_size;
+	unsigned int i;
+	u32 regval;
+
+	fifo_size = xlgmac_calculate_per_queue_fifo(
+					pdata->hw_feat.rx_fifo_size,
+					pdata->rx_q_count);
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RQS_POS,
+					     MTL_Q_RQOMR_RQS_LEN, fifo_size);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	netif_info(pdata, drv, pdata->netdev,
+		   "%d Rx hardware queues, %d byte fifo per queue\n",
+		   pdata->rx_q_count, ((fifo_size + 1) * 256));
+}
+
+static void xlgmac_config_flow_control_threshold(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR));
+		/* Activate flow control when less than 4k left in fifo */
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFA_POS,
+					     MTL_Q_RQFCR_RFA_LEN, 2);
+		/* De-activate flow control when more than 6k left in fifo */
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFD_POS,
+					     MTL_Q_RQFCR_RFD_LEN, 4);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR));
+	}
+}
+
+static int xlgmac_config_tx_threshold(struct xlgmac_pdata *pdata,
+				      unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TTC_POS,
+					     MTL_Q_TQOMR_TTC_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_rsf_mode(struct xlgmac_pdata *pdata,
+				  unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RSF_POS,
+					     MTL_Q_RQOMR_RSF_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_tsf_mode(struct xlgmac_pdata *pdata,
+				  unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TSF_POS,
+					     MTL_Q_TQOMR_TSF_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_osp_mode(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_OSP_POS,
+					     DMA_CH_TCR_OSP_LEN,
+					pdata->tx_osp_mode);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_pblx8(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_PBLX8_POS,
+					     DMA_CH_CR_PBLX8_LEN,
+					pdata->pblx8);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_get_tx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_TCR));
+	regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_TCR_PBL_POS,
+				     DMA_CH_TCR_PBL_LEN);
+	return regval;
+}
+
+static int xlgmac_config_tx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_PBL_POS,
+					     DMA_CH_TCR_PBL_LEN,
+					pdata->tx_pbl);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_get_rx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_RCR));
+	regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_RCR_PBL_POS,
+				     DMA_CH_RCR_PBL_LEN);
+	return regval;
+}
+
+static int xlgmac_config_rx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_PBL_POS,
+					     DMA_CH_RCR_PBL_LEN,
+					pdata->rx_pbl);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+
+	return 0;
+}
+
+static u64 xlgmac_mmc_read(struct xlgmac_pdata *pdata, unsigned int reg_lo)
+{
+	bool read_hi;
+	u64 val;
+
+	switch (reg_lo) {
+	/* These registers are always 64 bit */
+	case MMC_TXOCTETCOUNT_GB_LO:
+	case MMC_TXOCTETCOUNT_G_LO:
+	case MMC_RXOCTETCOUNT_GB_LO:
+	case MMC_RXOCTETCOUNT_G_LO:
+		read_hi = true;
+		break;
+
+	default:
+		read_hi = false;
+	}
+
+	val = (u64)readl(pdata->mac_regs + reg_lo);
+
+	if (read_hi)
+		val |= ((u64)readl(pdata->mac_regs + reg_lo + 4) << 32);
+
+	return val;
+}
+
+static void xlgmac_tx_mmc_int(struct xlgmac_pdata *pdata)
+{
+	unsigned int mmc_isr = readl(pdata->mac_regs + MMC_TISR);
+	struct xlgmac_stats *stats = &pdata->stats;
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXOCTETCOUNT_GB_POS,
+				MMC_TISR_TXOCTETCOUNT_GB_LEN))
+		stats->txoctetcount_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXFRAMECOUNT_GB_POS,
+				MMC_TISR_TXFRAMECOUNT_GB_LEN))
+		stats->txframecount_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXBROADCASTFRAMES_G_POS,
+				MMC_TISR_TXBROADCASTFRAMES_G_LEN))
+		stats->txbroadcastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXMULTICASTFRAMES_G_POS,
+				MMC_TISR_TXMULTICASTFRAMES_G_LEN))
+		stats->txmulticastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX64OCTETS_GB_POS,
+				MMC_TISR_TX64OCTETS_GB_LEN))
+		stats->tx64octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX65TO127OCTETS_GB_POS,
+				MMC_TISR_TX65TO127OCTETS_GB_LEN))
+		stats->tx65to127octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX128TO255OCTETS_GB_POS,
+				MMC_TISR_TX128TO255OCTETS_GB_LEN))
+		stats->tx128to255octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX256TO511OCTETS_GB_POS,
+				MMC_TISR_TX256TO511OCTETS_GB_LEN))
+		stats->tx256to511octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX512TO1023OCTETS_GB_POS,
+				MMC_TISR_TX512TO1023OCTETS_GB_LEN))
+		stats->tx512to1023octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX1024TOMAXOCTETS_GB_POS,
+				MMC_TISR_TX1024TOMAXOCTETS_GB_LEN))
+		stats->tx1024tomaxoctets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXUNICASTFRAMES_GB_POS,
+				MMC_TISR_TXUNICASTFRAMES_GB_LEN))
+		stats->txunicastframes_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXMULTICASTFRAMES_GB_POS,
+				MMC_TISR_TXMULTICASTFRAMES_GB_LEN))
+		stats->txmulticastframes_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXBROADCASTFRAMES_GB_POS,
+				MMC_TISR_TXBROADCASTFRAMES_GB_LEN))
+		stats->txbroadcastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXUNDERFLOWERROR_POS,
+				MMC_TISR_TXUNDERFLOWERROR_LEN))
+		stats->txunderflowerror +=
+			xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXOCTETCOUNT_G_POS,
+				MMC_TISR_TXOCTETCOUNT_G_LEN))
+		stats->txoctetcount_g +=
+			xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXFRAMECOUNT_G_POS,
+				MMC_TISR_TXFRAMECOUNT_G_LEN))
+		stats->txframecount_g +=
+			xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXPAUSEFRAMES_POS,
+				MMC_TISR_TXPAUSEFRAMES_LEN))
+		stats->txpauseframes +=
+			xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXVLANFRAMES_G_POS,
+				MMC_TISR_TXVLANFRAMES_G_LEN))
+		stats->txvlanframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO);
+}
+
+static void xlgmac_rx_mmc_int(struct xlgmac_pdata *pdata)
+{
+	unsigned int mmc_isr = readl(pdata->mac_regs + MMC_RISR);
+	struct xlgmac_stats *stats = &pdata->stats;
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXFRAMECOUNT_GB_POS,
+				MMC_RISR_RXFRAMECOUNT_GB_LEN))
+		stats->rxframecount_gb +=
+			xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOCTETCOUNT_GB_POS,
+				MMC_RISR_RXOCTETCOUNT_GB_LEN))
+		stats->rxoctetcount_gb +=
+			xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOCTETCOUNT_G_POS,
+				MMC_RISR_RXOCTETCOUNT_G_LEN))
+		stats->rxoctetcount_g +=
+			xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXBROADCASTFRAMES_G_POS,
+				MMC_RISR_RXBROADCASTFRAMES_G_LEN))
+		stats->rxbroadcastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXMULTICASTFRAMES_G_POS,
+				MMC_RISR_RXMULTICASTFRAMES_G_LEN))
+		stats->rxmulticastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXCRCERROR_POS,
+				MMC_RISR_RXCRCERROR_LEN))
+		stats->rxcrcerror +=
+			xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXRUNTERROR_POS,
+				MMC_RISR_RXRUNTERROR_LEN))
+		stats->rxrunterror +=
+			xlgmac_mmc_read(pdata, MMC_RXRUNTERROR);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXJABBERERROR_POS,
+				MMC_RISR_RXJABBERERROR_LEN))
+		stats->rxjabbererror +=
+			xlgmac_mmc_read(pdata, MMC_RXJABBERERROR);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXUNDERSIZE_G_POS,
+				MMC_RISR_RXUNDERSIZE_G_LEN))
+		stats->rxundersize_g +=
+			xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOVERSIZE_G_POS,
+				MMC_RISR_RXOVERSIZE_G_LEN))
+		stats->rxoversize_g +=
+			xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX64OCTETS_GB_POS,
+				MMC_RISR_RX64OCTETS_GB_LEN))
+		stats->rx64octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX65TO127OCTETS_GB_POS,
+				MMC_RISR_RX65TO127OCTETS_GB_LEN))
+		stats->rx65to127octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX128TO255OCTETS_GB_POS,
+				MMC_RISR_RX128TO255OCTETS_GB_LEN))
+		stats->rx128to255octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX256TO511OCTETS_GB_POS,
+				MMC_RISR_RX256TO511OCTETS_GB_LEN))
+		stats->rx256to511octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX512TO1023OCTETS_GB_POS,
+				MMC_RISR_RX512TO1023OCTETS_GB_LEN))
+		stats->rx512to1023octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX1024TOMAXOCTETS_GB_POS,
+				MMC_RISR_RX1024TOMAXOCTETS_GB_LEN))
+		stats->rx1024tomaxoctets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXUNICASTFRAMES_G_POS,
+				MMC_RISR_RXUNICASTFRAMES_G_LEN))
+		stats->rxunicastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXLENGTHERROR_POS,
+				MMC_RISR_RXLENGTHERROR_LEN))
+		stats->rxlengtherror +=
+			xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOUTOFRANGETYPE_POS,
+				MMC_RISR_RXOUTOFRANGETYPE_LEN))
+		stats->rxoutofrangetype +=
+			xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXPAUSEFRAMES_POS,
+				MMC_RISR_RXPAUSEFRAMES_LEN))
+		stats->rxpauseframes +=
+			xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXFIFOOVERFLOW_POS,
+				MMC_RISR_RXFIFOOVERFLOW_LEN))
+		stats->rxfifooverflow +=
+			xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXVLANFRAMES_GB_POS,
+				MMC_RISR_RXVLANFRAMES_GB_LEN))
+		stats->rxvlanframes_gb +=
+			xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXWATCHDOGERROR_POS,
+				MMC_RISR_RXWATCHDOGERROR_LEN))
+		stats->rxwatchdogerror +=
+			xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR);
+}
+
+static void xlgmac_read_mmc_stats(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_stats *stats = &pdata->stats;
+	u32 regval;
+
+	/* Freeze counters */
+	regval = readl(pdata->mac_regs + MMC_CR);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS,
+				     MMC_CR_MCF_LEN, 1);
+	writel(regval, pdata->mac_regs + MMC_CR);
+
+	stats->txoctetcount_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+	stats->txframecount_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+	stats->txbroadcastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+	stats->txmulticastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+	stats->tx64octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO);
+
+	stats->tx65to127octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+	stats->tx128to255octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+	stats->tx256to511octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+	stats->tx512to1023octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+	stats->tx1024tomaxoctets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+	stats->txunicastframes_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+	stats->txmulticastframes_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+	stats->txbroadcastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+	stats->txunderflowerror +=
+		xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+	stats->txoctetcount_g +=
+		xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+	stats->txframecount_g +=
+		xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+	stats->txpauseframes +=
+		xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO);
+
+	stats->txvlanframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO);
+
+	stats->rxframecount_gb +=
+		xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+	stats->rxoctetcount_gb +=
+		xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+	stats->rxoctetcount_g +=
+		xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+	stats->rxbroadcastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+	stats->rxmulticastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+	stats->rxcrcerror +=
+		xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO);
+
+	stats->rxrunterror +=
+		xlgmac_mmc_read(pdata, MMC_RXRUNTERROR);
+
+	stats->rxjabbererror +=
+		xlgmac_mmc_read(pdata, MMC_RXJABBERERROR);
+
+	stats->rxundersize_g +=
+		xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G);
+
+	stats->rxoversize_g +=
+		xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G);
+
+	stats->rx64octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO);
+
+	stats->rx65to127octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+	stats->rx128to255octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+	stats->rx256to511octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+	stats->rx512to1023octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+	stats->rx1024tomaxoctets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+	stats->rxunicastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+	stats->rxlengtherror +=
+		xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO);
+
+	stats->rxoutofrangetype +=
+		xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+	stats->rxpauseframes +=
+		xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO);
+
+	stats->rxfifooverflow +=
+		xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+	stats->rxvlanframes_gb +=
+		xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+	stats->rxwatchdogerror +=
+		xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR);
+
+	/* Un-freeze counters */
+	regval = readl(pdata->mac_regs + MMC_CR);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS,
+				     MMC_CR_MCF_LEN, 0);
+	writel(regval, pdata->mac_regs + MMC_CR);
+}
+
+static void xlgmac_config_mmc(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MMC_CR);
+	/* Set counters to reset on read */
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_ROR_POS,
+				     MMC_CR_ROR_LEN, 1);
+	/* Reset the counters */
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_CR_POS,
+				     MMC_CR_CR_LEN, 1);
+	writel(regval, pdata->mac_regs + MMC_CR);
+}
+
+static int xlgmac_write_rss_reg(struct xlgmac_pdata *pdata, unsigned int type,
+				unsigned int index, unsigned int val)
+{
+	unsigned int wait;
+	int ret = 0;
+	u32 regval;
+
+	mutex_lock(&pdata->rss_mutex);
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR),
+				     MAC_RSSAR_OB_POS, MAC_RSSAR_OB_LEN);
+	if (regval) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	writel(val, pdata->mac_regs + MAC_RSSDR);
+
+	regval = readl(pdata->mac_regs + MAC_RSSAR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_RSSIA_POS,
+				     MAC_RSSAR_RSSIA_LEN, index);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_ADDRT_POS,
+				     MAC_RSSAR_ADDRT_LEN, type);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_CT_POS,
+				     MAC_RSSAR_CT_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_OB_POS,
+				     MAC_RSSAR_OB_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RSSAR);
+
+	wait = 1000;
+	while (wait--) {
+		regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR),
+					     MAC_RSSAR_OB_POS,
+					     MAC_RSSAR_OB_LEN);
+		if (!regval)
+			goto unlock;
+
+		usleep_range(1000, 1500);
+	}
+
+	ret = -EBUSY;
+
+unlock:
+	mutex_unlock(&pdata->rss_mutex);
+
+	return ret;
+}
+
+static int xlgmac_write_rss_hash_key(struct xlgmac_pdata *pdata)
+{
+	unsigned int key_regs = sizeof(pdata->rss_key) / sizeof(u32);
+	unsigned int *key = (unsigned int *)&pdata->rss_key;
+	int ret;
+
+	while (key_regs--) {
+		ret = xlgmac_write_rss_reg(pdata, XLGMAC_RSS_HASH_KEY_TYPE,
+					   key_regs, *key++);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int xlgmac_write_rss_lookup_table(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) {
+		ret = xlgmac_write_rss_reg(pdata,
+					   XLGMAC_RSS_LOOKUP_TABLE_TYPE, i,
+					   pdata->rss_table[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int xlgmac_set_rss_hash_key(struct xlgmac_pdata *pdata, const u8 *key)
+{
+	memcpy(pdata->rss_key, key, sizeof(pdata->rss_key));
+
+	return xlgmac_write_rss_hash_key(pdata);
+}
+
+static int xlgmac_set_rss_lookup_table(struct xlgmac_pdata *pdata,
+				       const u32 *table)
+{
+	unsigned int i;
+	u32 tval;
+
+	for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) {
+		tval = table[i];
+		pdata->rss_table[i] = XLGMAC_SET_REG_BITS(
+						pdata->rss_table[i],
+						MAC_RSSDR_DMCH_POS,
+						MAC_RSSDR_DMCH_LEN,
+						tval);
+	}
+
+	return xlgmac_write_rss_lookup_table(pdata);
+}
+
+static int xlgmac_enable_rss(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+	int ret;
+
+	if (!pdata->hw_feat.rss)
+		return -EOPNOTSUPP;
+
+	/* Program the hash key */
+	ret = xlgmac_write_rss_hash_key(pdata);
+	if (ret)
+		return ret;
+
+	/* Program the lookup table */
+	ret = xlgmac_write_rss_lookup_table(pdata);
+	if (ret)
+		return ret;
+
+	/* Set the RSS options */
+	writel(pdata->rss_options, pdata->mac_regs + MAC_RSSCR);
+
+	/* Enable RSS */
+	regval = readl(pdata->mac_regs + MAC_RSSCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS,
+				     MAC_RSSCR_RSSE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RSSCR);
+
+	return 0;
+}
+
+static int xlgmac_disable_rss(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	if (!pdata->hw_feat.rss)
+		return -EOPNOTSUPP;
+
+	regval = readl(pdata->mac_regs + MAC_RSSCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS,
+				     MAC_RSSCR_RSSE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RSSCR);
+
+	return 0;
+}
+
+static void xlgmac_config_rss(struct xlgmac_pdata *pdata)
+{
+	int ret;
+
+	if (!pdata->hw_feat.rss)
+		return;
+
+	if (pdata->netdev->features & NETIF_F_RXHASH)
+		ret = xlgmac_enable_rss(pdata);
+	else
+		ret = xlgmac_disable_rss(pdata);
+
+	if (ret)
+		netdev_err(pdata->netdev,
+			   "error configuring RSS, RSS disabled\n");
+}
+
+static void xlgmac_enable_dma_interrupts(struct xlgmac_pdata *pdata)
+{
+	unsigned int dma_ch_isr, dma_ch_ier;
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		/* Clear all the interrupts which are set */
+		dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR));
+		writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR));
+
+		/* Clear all interrupt enable bits */
+		dma_ch_ier = 0;
+
+		/* Enable following interrupts
+		 *   NIE  - Normal Interrupt Summary Enable
+		 *   AIE  - Abnormal Interrupt Summary Enable
+		 *   FBEE - Fatal Bus Error Enable
+		 */
+		dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+						 DMA_CH_IER_NIE_POS,
+					DMA_CH_IER_NIE_LEN, 1);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+						 DMA_CH_IER_AIE_POS,
+					DMA_CH_IER_AIE_LEN, 1);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+						 DMA_CH_IER_FBEE_POS,
+					DMA_CH_IER_FBEE_LEN, 1);
+
+		if (channel->tx_ring) {
+			/* Enable the following Tx interrupts
+			 *   TIE  - Transmit Interrupt Enable (unless using
+			 *          per channel interrupts)
+			 */
+			if (!pdata->per_channel_irq)
+				dma_ch_ier = XLGMAC_SET_REG_BITS(
+						dma_ch_ier,
+						DMA_CH_IER_TIE_POS,
+						DMA_CH_IER_TIE_LEN,
+						1);
+		}
+		if (channel->rx_ring) {
+			/* Enable following Rx interrupts
+			 *   RBUE - Receive Buffer Unavailable Enable
+			 *   RIE  - Receive Interrupt Enable (unless using
+			 *          per channel interrupts)
+			 */
+			dma_ch_ier = XLGMAC_SET_REG_BITS(
+					dma_ch_ier,
+					DMA_CH_IER_RBUE_POS,
+					DMA_CH_IER_RBUE_LEN,
+					1);
+			if (!pdata->per_channel_irq)
+				dma_ch_ier = XLGMAC_SET_REG_BITS(
+						dma_ch_ier,
+						DMA_CH_IER_RIE_POS,
+						DMA_CH_IER_RIE_LEN,
+						1);
+		}
+
+		writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+	}
+}
+
+static void xlgmac_enable_mtl_interrupts(struct xlgmac_pdata *pdata)
+{
+	unsigned int q_count, i;
+	unsigned int mtl_q_isr;
+
+	q_count = max(pdata->hw_feat.tx_q_cnt, pdata->hw_feat.rx_q_cnt);
+	for (i = 0; i < q_count; i++) {
+		/* Clear all the interrupts which are set */
+		mtl_q_isr = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR));
+		writel(mtl_q_isr, XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR));
+
+		/* No MTL interrupts to be enabled */
+		writel(0, XLGMAC_MTL_REG(pdata, i, MTL_Q_IER));
+	}
+}
+
+static void xlgmac_enable_mac_interrupts(struct xlgmac_pdata *pdata)
+{
+	unsigned int mac_ier = 0;
+	u32 regval;
+
+	/* Enable Timestamp interrupt */
+	mac_ier = XLGMAC_SET_REG_BITS(mac_ier, MAC_IER_TSIE_POS,
+				      MAC_IER_TSIE_LEN, 1);
+
+	writel(mac_ier, pdata->mac_regs + MAC_IER);
+
+	/* Enable all counter interrupts */
+	regval = readl(pdata->mac_regs + MMC_RIER);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_RIER_ALL_INTERRUPTS_POS,
+				     MMC_RIER_ALL_INTERRUPTS_LEN, 0xffffffff);
+	writel(regval, pdata->mac_regs + MMC_RIER);
+	regval = readl(pdata->mac_regs + MMC_TIER);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_TIER_ALL_INTERRUPTS_POS,
+				     MMC_TIER_ALL_INTERRUPTS_LEN, 0xffffffff);
+	writel(regval, pdata->mac_regs + MMC_TIER);
+}
+
+static int xlgmac_set_xlgmii_25000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0x1)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0x1);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static int xlgmac_set_xlgmii_40000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static int xlgmac_set_xlgmii_50000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0x2)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0x2);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static int xlgmac_set_xlgmii_100000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0x3)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0x3);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static void xlgmac_config_mac_speed(struct xlgmac_pdata *pdata)
+{
+	switch (pdata->phy_speed) {
+	case SPEED_100000:
+		xlgmac_set_xlgmii_100000_speed(pdata);
+		break;
+
+	case SPEED_50000:
+		xlgmac_set_xlgmii_50000_speed(pdata);
+		break;
+
+	case SPEED_40000:
+		xlgmac_set_xlgmii_40000_speed(pdata);
+		break;
+
+	case SPEED_25000:
+		xlgmac_set_xlgmii_25000_speed(pdata);
+		break;
+	}
+}
+
+static int xlgmac_dev_read(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	struct net_device *netdev = pdata->netdev;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_pkt_info *pkt_info;
+	unsigned int err, etlt, l34t;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+	dma_desc = desc_data->dma_desc;
+	pkt_info = &ring->pkt_info;
+
+	/* Check for data availability */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_OWN_POS,
+				   RX_NORMAL_DESC3_OWN_LEN))
+		return 1;
+
+	/* Make sure descriptor fields are read after reading the OWN bit */
+	dma_rmb();
+
+	if (netif_msg_rx_status(pdata))
+		xlgmac_dump_rx_desc(pdata, ring, ring->cur);
+
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_CTXT_POS,
+				   RX_NORMAL_DESC3_CTXT_LEN)) {
+		/* Timestamp Context Descriptor */
+		xlgmac_get_rx_tstamp(pkt_info, dma_desc);
+
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+					RX_PACKET_ATTRIBUTES_CONTEXT_LEN,
+					1);
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN,
+				0);
+		return 0;
+	}
+
+	/* Normal Descriptor, be sure Context Descriptor bit is off */
+	pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+				RX_PACKET_ATTRIBUTES_CONTEXT_LEN,
+				0);
+
+	/* Indicate if a Context Descriptor is next */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_CDA_POS,
+				   RX_NORMAL_DESC3_CDA_LEN))
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN,
+				1);
+
+	/* Get the header length */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_FD_POS,
+				   RX_NORMAL_DESC3_FD_LEN)) {
+		desc_data->rx.hdr_len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc2,
+							RX_NORMAL_DESC2_HL_POS,
+							RX_NORMAL_DESC2_HL_LEN);
+		if (desc_data->rx.hdr_len)
+			pdata->stats.rx_split_header_packets++;
+	}
+
+	/* Get the RSS hash */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_RSV_POS,
+				   RX_NORMAL_DESC3_RSV_LEN)) {
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_RSS_HASH_POS,
+				RX_PACKET_ATTRIBUTES_RSS_HASH_LEN,
+				1);
+
+		pkt_info->rss_hash = le32_to_cpu(dma_desc->desc1);
+
+		l34t = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+					      RX_NORMAL_DESC3_L34T_POS,
+					  RX_NORMAL_DESC3_L34T_LEN);
+		switch (l34t) {
+		case RX_DESC3_L34T_IPV4_TCP:
+		case RX_DESC3_L34T_IPV4_UDP:
+		case RX_DESC3_L34T_IPV6_TCP:
+		case RX_DESC3_L34T_IPV6_UDP:
+			pkt_info->rss_hash_type = PKT_HASH_TYPE_L4;
+			break;
+		default:
+			pkt_info->rss_hash_type = PKT_HASH_TYPE_L3;
+		}
+	}
+
+	/* Get the pkt_info length */
+	desc_data->rx.len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+					RX_NORMAL_DESC3_PL_POS,
+					RX_NORMAL_DESC3_PL_LEN);
+
+	if (!XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				    RX_NORMAL_DESC3_LD_POS,
+				    RX_NORMAL_DESC3_LD_LEN)) {
+		/* Not all the data has been transferred for this pkt_info */
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+				RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN,
+				1);
+		return 0;
+	}
+
+	/* This is the last of the data for this pkt_info */
+	pkt_info->attributes = XLGMAC_SET_REG_BITS(
+			pkt_info->attributes,
+			RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+			RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN,
+			0);
+
+	/* Set checksum done indicator as appropriate */
+	if (netdev->features & NETIF_F_RXCSUM)
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+				RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN,
+				1);
+
+	/* Check for errors (only valid in last descriptor) */
+	err = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				     RX_NORMAL_DESC3_ES_POS,
+				     RX_NORMAL_DESC3_ES_LEN);
+	etlt = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				      RX_NORMAL_DESC3_ETLT_POS,
+				      RX_NORMAL_DESC3_ETLT_LEN);
+	netif_dbg(pdata, rx_status, netdev, "err=%u, etlt=%#x\n", err, etlt);
+
+	if (!err || !etlt) {
+		/* No error if err is 0 or etlt is 0 */
+		if ((etlt == 0x09) &&
+		    (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
+			pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+					RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN,
+					1);
+			pkt_info->vlan_ctag =
+				XLGMAC_GET_REG_BITS_LE(dma_desc->desc0,
+						       RX_NORMAL_DESC0_OVT_POS,
+						   RX_NORMAL_DESC0_OVT_LEN);
+			netif_dbg(pdata, rx_status, netdev, "vlan-ctag=%#06x\n",
+				  pkt_info->vlan_ctag);
+		}
+	} else {
+		if ((etlt == 0x05) || (etlt == 0x06))
+			pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+					RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN,
+					0);
+		else
+			pkt_info->errors = XLGMAC_SET_REG_BITS(
+					pkt_info->errors,
+					RX_PACKET_ERRORS_FRAME_POS,
+					RX_PACKET_ERRORS_FRAME_LEN,
+					1);
+	}
+
+	XLGMAC_PR("%s - descriptor=%u (cur=%d)\n", channel->name,
+		  ring->cur & (ring->dma_desc_count - 1), ring->cur);
+
+	return 0;
+}
+
+static int xlgmac_enable_int(struct xlgmac_channel *channel,
+			     enum xlgmac_int int_id)
+{
+	unsigned int dma_ch_ier;
+
+	dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	switch (int_id) {
+	case XLGMAC_INT_DMA_CH_SR_TI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TXSE_POS,
+				DMA_CH_IER_TXSE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TBUE_POS,
+				DMA_CH_IER_TBUE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RBUE_POS,
+				DMA_CH_IER_RBUE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RSE_POS,
+				DMA_CH_IER_RSE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TI_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 1);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_FBE:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_FBEE_POS,
+				DMA_CH_IER_FBEE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_ALL:
+		dma_ch_ier |= channel->saved_ier;
+		break;
+	default:
+		return -1;
+	}
+
+	writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	return 0;
+}
+
+static int xlgmac_disable_int(struct xlgmac_channel *channel,
+			      enum xlgmac_int int_id)
+{
+	unsigned int dma_ch_ier;
+
+	dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	switch (int_id) {
+	case XLGMAC_INT_DMA_CH_SR_TI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TXSE_POS,
+				DMA_CH_IER_TXSE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TBUE_POS,
+				DMA_CH_IER_TBUE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RBUE_POS,
+				DMA_CH_IER_RBUE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RSE_POS,
+				DMA_CH_IER_RSE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TI_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 0);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_FBE:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_FBEE_POS,
+				DMA_CH_IER_FBEE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_ALL:
+		channel->saved_ier = dma_ch_ier & XLGMAC_DMA_INTERRUPT_MASK;
+		dma_ch_ier &= ~XLGMAC_DMA_INTERRUPT_MASK;
+		break;
+	default:
+		return -1;
+	}
+
+	writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	return 0;
+}
+
+static int xlgmac_flush_tx_queues(struct xlgmac_pdata *pdata)
+{
+	unsigned int i, count;
+	u32 regval;
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS,
+					     MTL_Q_TQOMR_FTQ_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	/* Poll Until Poll Condition */
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		count = 2000;
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_GET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS,
+					     MTL_Q_TQOMR_FTQ_LEN);
+		while (--count && regval)
+			usleep_range(500, 600);
+
+		if (!count)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void xlgmac_config_dma_bus(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + DMA_SBMR);
+	/* Set enhanced addressing mode */
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_EAME_POS,
+				     DMA_SBMR_EAME_LEN, 1);
+	/* Set the System Bus mode */
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_UNDEF_POS,
+				     DMA_SBMR_UNDEF_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_BLEN_256_POS,
+				     DMA_SBMR_BLEN_256_LEN, 1);
+	writel(regval, pdata->mac_regs + DMA_SBMR);
+}
+
+static int xlgmac_hw_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+	int ret;
+
+	/* Flush Tx queues */
+	ret = xlgmac_flush_tx_queues(pdata);
+	if (ret)
+		return ret;
+
+	/* Initialize DMA related features */
+	xlgmac_config_dma_bus(pdata);
+	xlgmac_config_osp_mode(pdata);
+	xlgmac_config_pblx8(pdata);
+	xlgmac_config_tx_pbl_val(pdata);
+	xlgmac_config_rx_pbl_val(pdata);
+	xlgmac_config_rx_coalesce(pdata);
+	xlgmac_config_tx_coalesce(pdata);
+	xlgmac_config_rx_buffer_size(pdata);
+	xlgmac_config_tso_mode(pdata);
+	xlgmac_config_sph_mode(pdata);
+	xlgmac_config_rss(pdata);
+	desc_ops->tx_desc_init(pdata);
+	desc_ops->rx_desc_init(pdata);
+	xlgmac_enable_dma_interrupts(pdata);
+
+	/* Initialize MTL related features */
+	xlgmac_config_mtl_mode(pdata);
+	xlgmac_config_queue_mapping(pdata);
+	xlgmac_config_tsf_mode(pdata, pdata->tx_sf_mode);
+	xlgmac_config_rsf_mode(pdata, pdata->rx_sf_mode);
+	xlgmac_config_tx_threshold(pdata, pdata->tx_threshold);
+	xlgmac_config_rx_threshold(pdata, pdata->rx_threshold);
+	xlgmac_config_tx_fifo_size(pdata);
+	xlgmac_config_rx_fifo_size(pdata);
+	xlgmac_config_flow_control_threshold(pdata);
+	xlgmac_config_rx_fep_enable(pdata);
+	xlgmac_config_rx_fup_enable(pdata);
+	xlgmac_enable_mtl_interrupts(pdata);
+
+	/* Initialize MAC related features */
+	xlgmac_config_mac_address(pdata);
+	xlgmac_config_rx_mode(pdata);
+	xlgmac_config_jumbo_enable(pdata);
+	xlgmac_config_flow_control(pdata);
+	xlgmac_config_mac_speed(pdata);
+	xlgmac_config_checksum_offload(pdata);
+	xlgmac_config_vlan_support(pdata);
+	xlgmac_config_mmc(pdata);
+	xlgmac_enable_mac_interrupts(pdata);
+
+	return 0;
+}
+
+static int xlgmac_hw_exit(struct xlgmac_pdata *pdata)
+{
+	unsigned int count = 2000;
+	u32 regval;
+
+	/* Issue a software reset */
+	regval = readl(pdata->mac_regs + DMA_MR);
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_MR_SWR_POS,
+				     DMA_MR_SWR_LEN, 1);
+	writel(regval, pdata->mac_regs + DMA_MR);
+	usleep_range(10, 15);
+
+	/* Poll Until Poll Condition */
+	while (--count &&
+	       XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + DMA_MR),
+				   DMA_MR_SWR_POS, DMA_MR_SWR_LEN))
+		usleep_range(500, 600);
+
+	if (!count)
+		return -EBUSY;
+
+	return 0;
+}
+
+void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops)
+{
+	hw_ops->init = xlgmac_hw_init;
+	hw_ops->exit = xlgmac_hw_exit;
+
+	hw_ops->tx_complete = xlgmac_tx_complete;
+
+	hw_ops->enable_tx = xlgmac_enable_tx;
+	hw_ops->disable_tx = xlgmac_disable_tx;
+	hw_ops->enable_rx = xlgmac_enable_rx;
+	hw_ops->disable_rx = xlgmac_disable_rx;
+
+	hw_ops->dev_xmit = xlgmac_dev_xmit;
+	hw_ops->dev_read = xlgmac_dev_read;
+	hw_ops->enable_int = xlgmac_enable_int;
+	hw_ops->disable_int = xlgmac_disable_int;
+
+	hw_ops->set_mac_address = xlgmac_set_mac_address;
+	hw_ops->config_rx_mode = xlgmac_config_rx_mode;
+	hw_ops->enable_rx_csum = xlgmac_enable_rx_csum;
+	hw_ops->disable_rx_csum = xlgmac_disable_rx_csum;
+
+	/* For MII speed configuration */
+	hw_ops->set_xlgmii_25000_speed = xlgmac_set_xlgmii_25000_speed;
+	hw_ops->set_xlgmii_40000_speed = xlgmac_set_xlgmii_40000_speed;
+	hw_ops->set_xlgmii_50000_speed = xlgmac_set_xlgmii_50000_speed;
+	hw_ops->set_xlgmii_100000_speed = xlgmac_set_xlgmii_100000_speed;
+
+	/* For descriptor related operation */
+	hw_ops->tx_desc_init = xlgmac_tx_desc_init;
+	hw_ops->rx_desc_init = xlgmac_rx_desc_init;
+	hw_ops->tx_desc_reset = xlgmac_tx_desc_reset;
+	hw_ops->rx_desc_reset = xlgmac_rx_desc_reset;
+	hw_ops->is_last_desc = xlgmac_is_last_desc;
+	hw_ops->is_context_desc = xlgmac_is_context_desc;
+	hw_ops->tx_start_xmit = xlgmac_tx_start_xmit;
+
+	/* For Flow Control */
+	hw_ops->config_tx_flow_control = xlgmac_config_tx_flow_control;
+	hw_ops->config_rx_flow_control = xlgmac_config_rx_flow_control;
+
+	/* For Vlan related config */
+	hw_ops->enable_rx_vlan_stripping = xlgmac_enable_rx_vlan_stripping;
+	hw_ops->disable_rx_vlan_stripping = xlgmac_disable_rx_vlan_stripping;
+	hw_ops->enable_rx_vlan_filtering = xlgmac_enable_rx_vlan_filtering;
+	hw_ops->disable_rx_vlan_filtering = xlgmac_disable_rx_vlan_filtering;
+	hw_ops->update_vlan_hash_table = xlgmac_update_vlan_hash_table;
+
+	/* For RX coalescing */
+	hw_ops->config_rx_coalesce = xlgmac_config_rx_coalesce;
+	hw_ops->config_tx_coalesce = xlgmac_config_tx_coalesce;
+	hw_ops->usec_to_riwt = xlgmac_usec_to_riwt;
+	hw_ops->riwt_to_usec = xlgmac_riwt_to_usec;
+
+	/* For RX and TX threshold config */
+	hw_ops->config_rx_threshold = xlgmac_config_rx_threshold;
+	hw_ops->config_tx_threshold = xlgmac_config_tx_threshold;
+
+	/* For RX and TX Store and Forward Mode config */
+	hw_ops->config_rsf_mode = xlgmac_config_rsf_mode;
+	hw_ops->config_tsf_mode = xlgmac_config_tsf_mode;
+
+	/* For TX DMA Operating on Second Frame config */
+	hw_ops->config_osp_mode = xlgmac_config_osp_mode;
+
+	/* For RX and TX PBL config */
+	hw_ops->config_rx_pbl_val = xlgmac_config_rx_pbl_val;
+	hw_ops->get_rx_pbl_val = xlgmac_get_rx_pbl_val;
+	hw_ops->config_tx_pbl_val = xlgmac_config_tx_pbl_val;
+	hw_ops->get_tx_pbl_val = xlgmac_get_tx_pbl_val;
+	hw_ops->config_pblx8 = xlgmac_config_pblx8;
+
+	/* For MMC statistics support */
+	hw_ops->tx_mmc_int = xlgmac_tx_mmc_int;
+	hw_ops->rx_mmc_int = xlgmac_rx_mmc_int;
+	hw_ops->read_mmc_stats = xlgmac_read_mmc_stats;
+
+	/* For Receive Side Scaling */
+	hw_ops->enable_rss = xlgmac_enable_rss;
+	hw_ops->disable_rss = xlgmac_disable_rss;
+	hw_ops->set_rss_hash_key = xlgmac_set_rss_hash_key;
+	hw_ops->set_rss_lookup_table = xlgmac_set_rss_lookup_table;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
new file mode 100644
index 000000000000..3b91257683bc
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
@@ -0,0 +1,1350 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/tcp.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_one_poll(struct napi_struct *, int);
+static int xlgmac_all_poll(struct napi_struct *, int);
+
+static inline unsigned int xlgmac_tx_avail_desc(struct xlgmac_ring *ring)
+{
+	return (ring->dma_desc_count - (ring->cur - ring->dirty));
+}
+
+static inline unsigned int xlgmac_rx_dirty_desc(struct xlgmac_ring *ring)
+{
+	return (ring->cur - ring->dirty);
+}
+
+static int xlgmac_maybe_stop_tx_queue(
+			struct xlgmac_channel *channel,
+			struct xlgmac_ring *ring,
+			unsigned int count)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+
+	if (count > xlgmac_tx_avail_desc(ring)) {
+		netif_info(pdata, drv, pdata->netdev,
+			   "Tx queue stopped, not enough descriptors available\n");
+		netif_stop_subqueue(pdata->netdev, channel->queue_index);
+		ring->tx.queue_stopped = 1;
+
+		/* If we haven't notified the hardware because of xmit_more
+		 * support, tell it now
+		 */
+		if (ring->tx.xmit_more)
+			pdata->hw_ops.tx_start_xmit(channel, ring);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	return 0;
+}
+
+static void xlgmac_prep_vlan(struct sk_buff *skb,
+			     struct xlgmac_pkt_info *pkt_info)
+{
+	if (skb_vlan_tag_present(skb))
+		pkt_info->vlan_ctag = skb_vlan_tag_get(skb);
+}
+
+static int xlgmac_prep_tso(struct sk_buff *skb,
+			   struct xlgmac_pkt_info *pkt_info)
+{
+	int ret;
+
+	if (!XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				 TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+				 TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN))
+		return 0;
+
+	ret = skb_cow_head(skb, 0);
+	if (ret)
+		return ret;
+
+	pkt_info->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	pkt_info->tcp_header_len = tcp_hdrlen(skb);
+	pkt_info->tcp_payload_len = skb->len - pkt_info->header_len;
+	pkt_info->mss = skb_shinfo(skb)->gso_size;
+
+	XLGMAC_PR("header_len=%u\n", pkt_info->header_len);
+	XLGMAC_PR("tcp_header_len=%u, tcp_payload_len=%u\n",
+		  pkt_info->tcp_header_len, pkt_info->tcp_payload_len);
+	XLGMAC_PR("mss=%u\n", pkt_info->mss);
+
+	/* Update the number of packets that will ultimately be transmitted
+	 * along with the extra bytes for each extra packet
+	 */
+	pkt_info->tx_packets = skb_shinfo(skb)->gso_segs;
+	pkt_info->tx_bytes += (pkt_info->tx_packets - 1) * pkt_info->header_len;
+
+	return 0;
+}
+
+static int xlgmac_is_tso(struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	return 1;
+}
+
+static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata,
+			       struct xlgmac_ring *ring,
+			       struct sk_buff *skb,
+			       struct xlgmac_pkt_info *pkt_info)
+{
+	struct skb_frag_struct *frag;
+	unsigned int context_desc;
+	unsigned int len;
+	unsigned int i;
+
+	pkt_info->skb = skb;
+
+	context_desc = 0;
+	pkt_info->desc_count = 0;
+
+	pkt_info->tx_packets = 1;
+	pkt_info->tx_bytes = skb->len;
+
+	if (xlgmac_is_tso(skb)) {
+		/* TSO requires an extra descriptor if mss is different */
+		if (skb_shinfo(skb)->gso_size != ring->tx.cur_mss) {
+			context_desc = 1;
+			pkt_info->desc_count++;
+		}
+
+		/* TSO requires an extra descriptor for TSO header */
+		pkt_info->desc_count++;
+
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+					TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN,
+					1);
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN,
+					1);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL)
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN,
+					1);
+
+	if (skb_vlan_tag_present(skb)) {
+		/* VLAN requires an extra descriptor if tag is different */
+		if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag)
+			/* We can share with the TSO context descriptor */
+			if (!context_desc) {
+				context_desc = 1;
+				pkt_info->desc_count++;
+			}
+
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+					TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN,
+					1);
+	}
+
+	for (len = skb_headlen(skb); len;) {
+		pkt_info->desc_count++;
+		len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		frag = &skb_shinfo(skb)->frags[i];
+		for (len = skb_frag_size(frag); len; ) {
+			pkt_info->desc_count++;
+			len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE);
+		}
+	}
+}
+
+static int xlgmac_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu)
+{
+	unsigned int rx_buf_size;
+
+	if (mtu > XLGMAC_JUMBO_PACKET_MTU) {
+		netdev_alert(netdev, "MTU exceeds maximum supported value\n");
+		return -EINVAL;
+	}
+
+	rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	rx_buf_size = clamp_val(rx_buf_size, XLGMAC_RX_MIN_BUF_SIZE, PAGE_SIZE);
+
+	rx_buf_size = (rx_buf_size + XLGMAC_RX_BUF_ALIGN - 1) &
+		      ~(XLGMAC_RX_BUF_ALIGN - 1);
+
+	return rx_buf_size;
+}
+
+static void xlgmac_enable_rx_tx_ints(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_channel *channel;
+	enum xlgmac_int int_id;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (channel->tx_ring && channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI_RI;
+		else if (channel->tx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI;
+		else if (channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_RI;
+		else
+			continue;
+
+		hw_ops->enable_int(channel, int_id);
+	}
+}
+
+static void xlgmac_disable_rx_tx_ints(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_channel *channel;
+	enum xlgmac_int int_id;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (channel->tx_ring && channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI_RI;
+		else if (channel->tx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI;
+		else if (channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_RI;
+		else
+			continue;
+
+		hw_ops->disable_int(channel, int_id);
+	}
+}
+
+static irqreturn_t xlgmac_isr(int irq, void *data)
+{
+	unsigned int dma_isr, dma_ch_isr, mac_isr;
+	struct xlgmac_pdata *pdata = data;
+	struct xlgmac_channel *channel;
+	struct xlgmac_hw_ops *hw_ops;
+	unsigned int i, ti, ri;
+
+	hw_ops = &pdata->hw_ops;
+
+	/* The DMA interrupt status register also reports MAC and MTL
+	 * interrupts. So for polling mode, we just need to check for
+	 * this register to be non-zero
+	 */
+	dma_isr = readl(pdata->mac_regs + DMA_ISR);
+	if (!dma_isr)
+		return IRQ_HANDLED;
+
+	netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr);
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!(dma_isr & (1 << i)))
+			continue;
+
+		channel = pdata->channel_head + i;
+
+		dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR));
+		netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n",
+			  i, dma_ch_isr);
+
+		/* The TI or RI interrupt bits may still be set even if using
+		 * per channel DMA interrupts. Check to be sure those are not
+		 * enabled before using the private data napi structure.
+		 */
+		ti = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TI_POS,
+					 DMA_CH_SR_TI_LEN);
+		ri = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RI_POS,
+					 DMA_CH_SR_RI_LEN);
+		if (!pdata->per_channel_irq && (ti || ri)) {
+			if (napi_schedule_prep(&pdata->napi)) {
+				/* Disable Tx and Rx interrupts */
+				xlgmac_disable_rx_tx_ints(pdata);
+
+				pdata->stats.napi_poll_isr++;
+				/* Turn on polling */
+				__napi_schedule_irqoff(&pdata->napi);
+			}
+		}
+
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TPS_POS,
+					DMA_CH_SR_TPS_LEN))
+			pdata->stats.tx_process_stopped++;
+
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RPS_POS,
+					DMA_CH_SR_RPS_LEN))
+			pdata->stats.rx_process_stopped++;
+
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TBU_POS,
+					DMA_CH_SR_TBU_LEN))
+			pdata->stats.tx_buffer_unavailable++;
+
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RBU_POS,
+					DMA_CH_SR_RBU_LEN))
+			pdata->stats.rx_buffer_unavailable++;
+
+		/* Restart the device on a Fatal Bus Error */
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_FBE_POS,
+					DMA_CH_SR_FBE_LEN)) {
+			pdata->stats.fatal_bus_error++;
+			schedule_work(&pdata->restart_work);
+		}
+
+		/* Clear all interrupt signals */
+		writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR));
+	}
+
+	if (XLGMAC_GET_REG_BITS(dma_isr, DMA_ISR_MACIS_POS,
+				DMA_ISR_MACIS_LEN)) {
+		mac_isr = readl(pdata->mac_regs + MAC_ISR);
+
+		if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCTXIS_POS,
+					MAC_ISR_MMCTXIS_LEN))
+			hw_ops->tx_mmc_int(pdata);
+
+		if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCRXIS_POS,
+					MAC_ISR_MMCRXIS_LEN))
+			hw_ops->rx_mmc_int(pdata);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t xlgmac_dma_isr(int irq, void *data)
+{
+	struct xlgmac_channel *channel = data;
+
+	/* Per channel DMA interrupts are enabled, so we use the per
+	 * channel napi structure and not the private data napi structure
+	 */
+	if (napi_schedule_prep(&channel->napi)) {
+		/* Disable Tx and Rx interrupts */
+		disable_irq_nosync(channel->dma_irq);
+
+		/* Turn on polling */
+		__napi_schedule_irqoff(&channel->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void xlgmac_tx_timer(unsigned long data)
+{
+	struct xlgmac_channel *channel = (struct xlgmac_channel *)data;
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct napi_struct *napi;
+
+	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
+
+	if (napi_schedule_prep(napi)) {
+		/* Disable Tx and Rx interrupts */
+		if (pdata->per_channel_irq)
+			disable_irq_nosync(channel->dma_irq);
+		else
+			xlgmac_disable_rx_tx_ints(pdata);
+
+		pdata->stats.napi_poll_txtimer++;
+		/* Turn on polling */
+		__napi_schedule(napi);
+	}
+
+	channel->tx_timer_active = 0;
+}
+
+static void xlgmac_init_timers(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		setup_timer(&channel->tx_timer, xlgmac_tx_timer,
+			    (unsigned long)channel);
+	}
+}
+
+static void xlgmac_stop_timers(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		del_timer_sync(&channel->tx_timer);
+	}
+}
+
+static void xlgmac_napi_enable(struct xlgmac_pdata *pdata, unsigned int add)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (pdata->per_channel_irq) {
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++) {
+			if (add)
+				netif_napi_add(pdata->netdev, &channel->napi,
+					       xlgmac_one_poll,
+					       NAPI_POLL_WEIGHT);
+
+			napi_enable(&channel->napi);
+		}
+	} else {
+		if (add)
+			netif_napi_add(pdata->netdev, &pdata->napi,
+				       xlgmac_all_poll, NAPI_POLL_WEIGHT);
+
+		napi_enable(&pdata->napi);
+	}
+}
+
+static void xlgmac_napi_disable(struct xlgmac_pdata *pdata, unsigned int del)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (pdata->per_channel_irq) {
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++) {
+			napi_disable(&channel->napi);
+
+			if (del)
+				netif_napi_del(&channel->napi);
+		}
+	} else {
+		napi_disable(&pdata->napi);
+
+		if (del)
+			netif_napi_del(&pdata->napi);
+	}
+}
+
+static int xlgmac_request_irqs(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	int ret;
+
+	ret = devm_request_irq(pdata->dev, pdata->dev_irq, xlgmac_isr,
+			       IRQF_SHARED, netdev->name, pdata);
+	if (ret) {
+		netdev_alert(netdev, "error requesting irq %d\n",
+			     pdata->dev_irq);
+		return ret;
+	}
+
+	if (!pdata->per_channel_irq)
+		return 0;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		snprintf(channel->dma_irq_name,
+			 sizeof(channel->dma_irq_name) - 1,
+			 "%s-TxRx-%u", netdev_name(netdev),
+			 channel->queue_index);
+
+		ret = devm_request_irq(pdata->dev, channel->dma_irq,
+				       xlgmac_dma_isr, 0,
+				       channel->dma_irq_name, channel);
+		if (ret) {
+			netdev_alert(netdev, "error requesting irq %d\n",
+				     channel->dma_irq);
+			goto err_irq;
+		}
+	}
+
+	return 0;
+
+err_irq:
+	/* Using an unsigned int, 'i' will go to UINT_MAX and exit */
+	for (i--, channel--; i < pdata->channel_count; i--, channel--)
+		devm_free_irq(pdata->dev, channel->dma_irq, channel);
+
+	devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+
+	return ret;
+}
+
+static void xlgmac_free_irqs(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+
+	if (!pdata->per_channel_irq)
+		return;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++)
+		devm_free_irq(pdata->dev, channel->dma_irq, channel);
+}
+
+static void xlgmac_free_tx_data(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+			desc_ops->unmap_desc_data(pdata, desc_data);
+		}
+	}
+}
+
+static void xlgmac_free_rx_data(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+			desc_ops->unmap_desc_data(pdata, desc_data);
+		}
+	}
+}
+
+static int xlgmac_start(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct net_device *netdev = pdata->netdev;
+	int ret;
+
+	hw_ops->init(pdata);
+	xlgmac_napi_enable(pdata, 1);
+
+	ret = xlgmac_request_irqs(pdata);
+	if (ret)
+		goto err_napi;
+
+	hw_ops->enable_tx(pdata);
+	hw_ops->enable_rx(pdata);
+	netif_tx_start_all_queues(netdev);
+
+	return 0;
+
+err_napi:
+	xlgmac_napi_disable(pdata, 1);
+	hw_ops->exit(pdata);
+
+	return ret;
+}
+
+static void xlgmac_stop(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct net_device *netdev = pdata->netdev;
+	struct xlgmac_channel *channel;
+	struct netdev_queue *txq;
+	unsigned int i;
+
+	netif_tx_stop_all_queues(netdev);
+	xlgmac_stop_timers(pdata);
+	hw_ops->disable_tx(pdata);
+	hw_ops->disable_rx(pdata);
+	xlgmac_free_irqs(pdata);
+	xlgmac_napi_disable(pdata, 1);
+	hw_ops->exit(pdata);
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			continue;
+
+		txq = netdev_get_tx_queue(netdev, channel->queue_index);
+		netdev_tx_reset_queue(txq);
+	}
+}
+
+static void xlgmac_restart_dev(struct xlgmac_pdata *pdata)
+{
+	/* If not running, "restart" will happen on open */
+	if (!netif_running(pdata->netdev))
+		return;
+
+	xlgmac_stop(pdata);
+
+	xlgmac_free_tx_data(pdata);
+	xlgmac_free_rx_data(pdata);
+
+	xlgmac_start(pdata);
+}
+
+static void xlgmac_restart(struct work_struct *work)
+{
+	struct xlgmac_pdata *pdata = container_of(work,
+						   struct xlgmac_pdata,
+						   restart_work);
+
+	rtnl_lock();
+
+	xlgmac_restart_dev(pdata);
+
+	rtnl_unlock();
+}
+
+static int xlgmac_open(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_desc_ops *desc_ops;
+	int ret;
+
+	desc_ops = &pdata->desc_ops;
+
+	/* TODO: Initialize the phy */
+
+	/* Calculate the Rx buffer size before allocating rings */
+	ret = xlgmac_calc_rx_buf_size(netdev, netdev->mtu);
+	if (ret < 0)
+		return ret;
+	pdata->rx_buf_size = ret;
+
+	/* Allocate the channels and rings */
+	ret = desc_ops->alloc_channles_and_rings(pdata);
+	if (ret)
+		return ret;
+
+	INIT_WORK(&pdata->restart_work, xlgmac_restart);
+	xlgmac_init_timers(pdata);
+
+	ret = xlgmac_start(pdata);
+	if (ret)
+		goto err_channels_and_rings;
+
+	return 0;
+
+err_channels_and_rings:
+	desc_ops->free_channels_and_rings(pdata);
+
+	return ret;
+}
+
+static int xlgmac_close(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_desc_ops *desc_ops;
+
+	desc_ops = &pdata->desc_ops;
+
+	/* Stop the device */
+	xlgmac_stop(pdata);
+
+	/* Free the channels and rings */
+	desc_ops->free_channels_and_rings(pdata);
+
+	return 0;
+}
+
+static void xlgmac_tx_timeout(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+	netdev_warn(netdev, "tx timeout, device restarting\n");
+	schedule_work(&pdata->restart_work);
+}
+
+static int xlgmac_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_pkt_info *tx_pkt_info;
+	struct xlgmac_desc_ops *desc_ops;
+	struct xlgmac_channel *channel;
+	struct xlgmac_hw_ops *hw_ops;
+	struct netdev_queue *txq;
+	struct xlgmac_ring *ring;
+	int ret;
+
+	desc_ops = &pdata->desc_ops;
+	hw_ops = &pdata->hw_ops;
+
+	XLGMAC_PR("skb->len = %d\n", skb->len);
+
+	channel = pdata->channel_head + skb->queue_mapping;
+	txq = netdev_get_tx_queue(netdev, channel->queue_index);
+	ring = channel->tx_ring;
+	tx_pkt_info = &ring->pkt_info;
+
+	if (skb->len == 0) {
+		netif_err(pdata, tx_err, netdev,
+			  "empty skb received from stack\n");
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Prepare preliminary packet info for TX */
+	memset(tx_pkt_info, 0, sizeof(*tx_pkt_info));
+	xlgmac_prep_tx_pkt(pdata, ring, skb, tx_pkt_info);
+
+	/* Check that there are enough descriptors available */
+	ret = xlgmac_maybe_stop_tx_queue(channel, ring,
+					 tx_pkt_info->desc_count);
+	if (ret)
+		return ret;
+
+	ret = xlgmac_prep_tso(skb, tx_pkt_info);
+	if (ret) {
+		netif_err(pdata, tx_err, netdev,
+			  "error processing TSO packet\n");
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+	xlgmac_prep_vlan(skb, tx_pkt_info);
+
+	if (!desc_ops->map_tx_skb(channel, skb)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Report on the actual number of bytes (to be) sent */
+	netdev_tx_sent_queue(txq, tx_pkt_info->tx_bytes);
+
+	/* Configure required descriptor fields for transmission */
+	hw_ops->dev_xmit(channel);
+
+	if (netif_msg_pktdata(pdata))
+		xlgmac_print_pkt(netdev, skb, true);
+
+	/* Stop the queue in advance if there may not be enough descriptors */
+	xlgmac_maybe_stop_tx_queue(channel, ring, XLGMAC_TX_MAX_DESC_NR);
+
+	return NETDEV_TX_OK;
+}
+
+static void xlgmac_get_stats64(struct net_device *netdev,
+			       struct rtnl_link_stats64 *s)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_stats *pstats = &pdata->stats;
+
+	pdata->hw_ops.read_mmc_stats(pdata);
+
+	s->rx_packets = pstats->rxframecount_gb;
+	s->rx_bytes = pstats->rxoctetcount_gb;
+	s->rx_errors = pstats->rxframecount_gb -
+		       pstats->rxbroadcastframes_g -
+		       pstats->rxmulticastframes_g -
+		       pstats->rxunicastframes_g;
+	s->multicast = pstats->rxmulticastframes_g;
+	s->rx_length_errors = pstats->rxlengtherror;
+	s->rx_crc_errors = pstats->rxcrcerror;
+	s->rx_fifo_errors = pstats->rxfifooverflow;
+
+	s->tx_packets = pstats->txframecount_gb;
+	s->tx_bytes = pstats->txoctetcount_gb;
+	s->tx_errors = pstats->txframecount_gb - pstats->txframecount_g;
+	s->tx_dropped = netdev->stats.tx_dropped;
+}
+
+static int xlgmac_set_mac_address(struct net_device *netdev, void *addr)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(netdev->dev_addr, saddr->sa_data, netdev->addr_len);
+
+	hw_ops->set_mac_address(pdata, netdev->dev_addr);
+
+	return 0;
+}
+
+static int xlgmac_ioctl(struct net_device *netdev,
+			struct ifreq *ifreq, int cmd)
+{
+	if (!netif_running(netdev))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int xlgmac_change_mtu(struct net_device *netdev, int mtu)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	int ret;
+
+	ret = xlgmac_calc_rx_buf_size(netdev, mtu);
+	if (ret < 0)
+		return ret;
+
+	pdata->rx_buf_size = ret;
+	netdev->mtu = mtu;
+
+	xlgmac_restart_dev(pdata);
+
+	return 0;
+}
+
+static int xlgmac_vlan_rx_add_vid(struct net_device *netdev,
+				  __be16 proto,
+				  u16 vid)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+	set_bit(vid, pdata->active_vlans);
+	hw_ops->update_vlan_hash_table(pdata);
+
+	return 0;
+}
+
+static int xlgmac_vlan_rx_kill_vid(struct net_device *netdev,
+				   __be16 proto,
+				   u16 vid)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+	clear_bit(vid, pdata->active_vlans);
+	hw_ops->update_vlan_hash_table(pdata);
+
+	return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void xlgmac_poll_controller(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (pdata->per_channel_irq) {
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++)
+			xlgmac_dma_isr(channel->dma_irq, channel);
+	} else {
+		disable_irq(pdata->dev_irq);
+		xlgmac_isr(pdata->dev_irq, pdata);
+		enable_irq(pdata->dev_irq);
+	}
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
+static int xlgmac_set_features(struct net_device *netdev,
+			       netdev_features_t features)
+{
+	netdev_features_t rxhash, rxcsum, rxvlan, rxvlan_filter;
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	int ret = 0;
+
+	rxhash = pdata->netdev_features & NETIF_F_RXHASH;
+	rxcsum = pdata->netdev_features & NETIF_F_RXCSUM;
+	rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX;
+	rxvlan_filter = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	if ((features & NETIF_F_RXHASH) && !rxhash)
+		ret = hw_ops->enable_rss(pdata);
+	else if (!(features & NETIF_F_RXHASH) && rxhash)
+		ret = hw_ops->disable_rss(pdata);
+	if (ret)
+		return ret;
+
+	if ((features & NETIF_F_RXCSUM) && !rxcsum)
+		hw_ops->enable_rx_csum(pdata);
+	else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+		hw_ops->disable_rx_csum(pdata);
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
+		hw_ops->enable_rx_vlan_stripping(pdata);
+	else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && rxvlan)
+		hw_ops->disable_rx_vlan_stripping(pdata);
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && !rxvlan_filter)
+		hw_ops->enable_rx_vlan_filtering(pdata);
+	else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && rxvlan_filter)
+		hw_ops->disable_rx_vlan_filtering(pdata);
+
+	pdata->netdev_features = features;
+
+	return 0;
+}
+
+static void xlgmac_set_rx_mode(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+	hw_ops->config_rx_mode(pdata);
+}
+
+static const struct net_device_ops xlgmac_netdev_ops = {
+	.ndo_open		= xlgmac_open,
+	.ndo_stop		= xlgmac_close,
+	.ndo_start_xmit		= xlgmac_xmit,
+	.ndo_tx_timeout		= xlgmac_tx_timeout,
+	.ndo_get_stats64	= xlgmac_get_stats64,
+	.ndo_change_mtu		= xlgmac_change_mtu,
+	.ndo_set_mac_address	= xlgmac_set_mac_address,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_do_ioctl		= xlgmac_ioctl,
+	.ndo_vlan_rx_add_vid	= xlgmac_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= xlgmac_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= xlgmac_poll_controller,
+#endif
+	.ndo_set_features	= xlgmac_set_features,
+	.ndo_set_rx_mode	= xlgmac_set_rx_mode,
+};
+
+const struct net_device_ops *xlgmac_get_netdev_ops(void)
+{
+	return &xlgmac_netdev_ops;
+}
+
+static void xlgmac_rx_refresh(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_desc_ops *desc_ops;
+	struct xlgmac_hw_ops *hw_ops;
+
+	desc_ops = &pdata->desc_ops;
+	hw_ops = &pdata->hw_ops;
+
+	while (ring->dirty != ring->cur) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty);
+
+		/* Reset desc_data values */
+		desc_ops->unmap_desc_data(pdata, desc_data);
+
+		if (desc_ops->map_rx_buffer(pdata, ring, desc_data))
+			break;
+
+		hw_ops->rx_desc_reset(pdata, desc_data, ring->dirty);
+
+		ring->dirty++;
+	}
+
+	/* Make sure everything is written before the register write */
+	wmb();
+
+	/* Update the Rx Tail Pointer Register with address of
+	 * the last cleaned entry
+	 */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty - 1);
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO));
+}
+
+static struct sk_buff *xlgmac_create_skb(struct xlgmac_pdata *pdata,
+					 struct napi_struct *napi,
+					 struct xlgmac_desc_data *desc_data,
+					 unsigned int len)
+{
+	unsigned int copy_len;
+	struct sk_buff *skb;
+	u8 *packet;
+
+	skb = napi_alloc_skb(napi, desc_data->rx.hdr.dma_len);
+	if (!skb)
+		return NULL;
+
+	/* Start with the header buffer which may contain just the header
+	 * or the header plus data
+	 */
+	dma_sync_single_range_for_cpu(pdata->dev, desc_data->rx.hdr.dma_base,
+				      desc_data->rx.hdr.dma_off,
+				      desc_data->rx.hdr.dma_len,
+				      DMA_FROM_DEVICE);
+
+	packet = page_address(desc_data->rx.hdr.pa.pages) +
+		 desc_data->rx.hdr.pa.pages_offset;
+	copy_len = (desc_data->rx.hdr_len) ? desc_data->rx.hdr_len : len;
+	copy_len = min(desc_data->rx.hdr.dma_len, copy_len);
+	skb_copy_to_linear_data(skb, packet, copy_len);
+	skb_put(skb, copy_len);
+
+	len -= copy_len;
+	if (len) {
+		/* Add the remaining data as a frag */
+		dma_sync_single_range_for_cpu(pdata->dev,
+					      desc_data->rx.buf.dma_base,
+					      desc_data->rx.buf.dma_off,
+					      desc_data->rx.buf.dma_len,
+					      DMA_FROM_DEVICE);
+
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				desc_data->rx.buf.pa.pages,
+				desc_data->rx.buf.pa.pages_offset,
+				len, desc_data->rx.buf.dma_len);
+		desc_data->rx.buf.pa.pages = NULL;
+	}
+
+	return skb;
+}
+
+static int xlgmac_tx_poll(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->tx_ring;
+	struct net_device *netdev = pdata->netdev;
+	unsigned int tx_packets = 0, tx_bytes = 0;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_desc_ops *desc_ops;
+	struct xlgmac_hw_ops *hw_ops;
+	struct netdev_queue *txq;
+	int processed = 0;
+	unsigned int cur;
+
+	desc_ops = &pdata->desc_ops;
+	hw_ops = &pdata->hw_ops;
+
+	/* Nothing to do if there isn't a Tx ring for this channel */
+	if (!ring)
+		return 0;
+
+	cur = ring->cur;
+
+	/* Be sure we get ring->cur before accessing descriptor data */
+	smp_rmb();
+
+	txq = netdev_get_tx_queue(netdev, channel->queue_index);
+
+	while ((processed < XLGMAC_TX_DESC_MAX_PROC) &&
+	       (ring->dirty != cur)) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty);
+		dma_desc = desc_data->dma_desc;
+
+		if (!hw_ops->tx_complete(dma_desc))
+			break;
+
+		/* Make sure descriptor fields are read after reading
+		 * the OWN bit
+		 */
+		dma_rmb();
+
+		if (netif_msg_tx_done(pdata))
+			xlgmac_dump_tx_desc(pdata, ring, ring->dirty, 1, 0);
+
+		if (hw_ops->is_last_desc(dma_desc)) {
+			tx_packets += desc_data->tx.packets;
+			tx_bytes += desc_data->tx.bytes;
+		}
+
+		/* Free the SKB and reset the descriptor for re-use */
+		desc_ops->unmap_desc_data(pdata, desc_data);
+		hw_ops->tx_desc_reset(desc_data);
+
+		processed++;
+		ring->dirty++;
+	}
+
+	if (!processed)
+		return 0;
+
+	netdev_tx_completed_queue(txq, tx_packets, tx_bytes);
+
+	if ((ring->tx.queue_stopped == 1) &&
+	    (xlgmac_tx_avail_desc(ring) > XLGMAC_TX_DESC_MIN_FREE)) {
+		ring->tx.queue_stopped = 0;
+		netif_tx_wake_queue(txq);
+	}
+
+	XLGMAC_PR("processed=%d\n", processed);
+
+	return processed;
+}
+
+static int xlgmac_rx_poll(struct xlgmac_channel *channel, int budget)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	struct net_device *netdev = pdata->netdev;
+	unsigned int len, dma_desc_len, max_len;
+	unsigned int context_next, context;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_pkt_info *pkt_info;
+	unsigned int incomplete, error;
+	struct xlgmac_hw_ops *hw_ops;
+	unsigned int received = 0;
+	struct napi_struct *napi;
+	struct sk_buff *skb;
+	int packet_count = 0;
+
+	hw_ops = &pdata->hw_ops;
+
+	/* Nothing to do if there isn't a Rx ring for this channel */
+	if (!ring)
+		return 0;
+
+	incomplete = 0;
+	context_next = 0;
+
+	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+	pkt_info = &ring->pkt_info;
+	while (packet_count < budget) {
+		/* First time in loop see if we need to restore state */
+		if (!received && desc_data->state_saved) {
+			skb = desc_data->state.skb;
+			error = desc_data->state.error;
+			len = desc_data->state.len;
+		} else {
+			memset(pkt_info, 0, sizeof(*pkt_info));
+			skb = NULL;
+			error = 0;
+			len = 0;
+		}
+
+read_again:
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+
+		if (xlgmac_rx_dirty_desc(ring) > XLGMAC_RX_DESC_MAX_DIRTY)
+			xlgmac_rx_refresh(channel);
+
+		if (hw_ops->dev_read(channel))
+			break;
+
+		received++;
+		ring->cur++;
+
+		incomplete = XLGMAC_GET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+					RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN);
+		context_next = XLGMAC_GET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+					RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN);
+		context = XLGMAC_GET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+					RX_PACKET_ATTRIBUTES_CONTEXT_LEN);
+
+		/* Earlier error, just drain the remaining data */
+		if ((incomplete || context_next) && error)
+			goto read_again;
+
+		if (error || pkt_info->errors) {
+			if (pkt_info->errors)
+				netif_err(pdata, rx_err, netdev,
+					  "error in received packet\n");
+			dev_kfree_skb(skb);
+			goto next_packet;
+		}
+
+		if (!context) {
+			/* Length is cumulative, get this descriptor's length */
+			dma_desc_len = desc_data->rx.len - len;
+			len += dma_desc_len;
+
+			if (dma_desc_len && !skb) {
+				skb = xlgmac_create_skb(pdata, napi, desc_data,
+							dma_desc_len);
+				if (!skb)
+					error = 1;
+			} else if (dma_desc_len) {
+				dma_sync_single_range_for_cpu(
+						pdata->dev,
+						desc_data->rx.buf.dma_base,
+						desc_data->rx.buf.dma_off,
+						desc_data->rx.buf.dma_len,
+						DMA_FROM_DEVICE);
+
+				skb_add_rx_frag(
+					skb, skb_shinfo(skb)->nr_frags,
+					desc_data->rx.buf.pa.pages,
+					desc_data->rx.buf.pa.pages_offset,
+					dma_desc_len,
+					desc_data->rx.buf.dma_len);
+				desc_data->rx.buf.pa.pages = NULL;
+			}
+		}
+
+		if (incomplete || context_next)
+			goto read_again;
+
+		if (!skb)
+			goto next_packet;
+
+		/* Be sure we don't exceed the configured MTU */
+		max_len = netdev->mtu + ETH_HLEN;
+		if (!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    (skb->protocol == htons(ETH_P_8021Q)))
+			max_len += VLAN_HLEN;
+
+		if (skb->len > max_len) {
+			netif_err(pdata, rx_err, netdev,
+				  "packet length exceeds configured MTU\n");
+			dev_kfree_skb(skb);
+			goto next_packet;
+		}
+
+		if (netif_msg_pktdata(pdata))
+			xlgmac_print_pkt(netdev, skb, false);
+
+		skb_checksum_none_assert(skb);
+		if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+				    RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+				    RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN)) {
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       pkt_info->vlan_ctag);
+			pdata->stats.rx_vlan_packets++;
+		}
+
+		if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_RSS_HASH_POS,
+				    RX_PACKET_ATTRIBUTES_RSS_HASH_LEN))
+			skb_set_hash(skb, pkt_info->rss_hash,
+				     pkt_info->rss_hash_type);
+
+		skb->dev = netdev;
+		skb->protocol = eth_type_trans(skb, netdev);
+		skb_record_rx_queue(skb, channel->queue_index);
+
+		napi_gro_receive(napi, skb);
+
+next_packet:
+		packet_count++;
+	}
+
+	/* Check if we need to save state before leaving */
+	if (received && (incomplete || context_next)) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+		desc_data->state_saved = 1;
+		desc_data->state.skb = skb;
+		desc_data->state.len = len;
+		desc_data->state.error = error;
+	}
+
+	XLGMAC_PR("packet_count = %d\n", packet_count);
+
+	return packet_count;
+}
+
+static int xlgmac_one_poll(struct napi_struct *napi, int budget)
+{
+	struct xlgmac_channel *channel = container_of(napi,
+						struct xlgmac_channel,
+						napi);
+	int processed = 0;
+
+	XLGMAC_PR("budget=%d\n", budget);
+
+	/* Cleanup Tx ring first */
+	xlgmac_tx_poll(channel);
+
+	/* Process Rx ring next */
+	processed = xlgmac_rx_poll(channel, budget);
+
+	/* If we processed everything, we are done */
+	if (processed < budget) {
+		/* Turn off polling */
+		napi_complete_done(napi, processed);
+
+		/* Enable Tx and Rx interrupts */
+		enable_irq(channel->dma_irq);
+	}
+
+	XLGMAC_PR("received = %d\n", processed);
+
+	return processed;
+}
+
+static int xlgmac_all_poll(struct napi_struct *napi, int budget)
+{
+	struct xlgmac_pdata *pdata = container_of(napi,
+						   struct xlgmac_pdata,
+						   napi);
+	struct xlgmac_channel *channel;
+	int processed, last_processed;
+	int ring_budget;
+	unsigned int i;
+
+	XLGMAC_PR("budget=%d\n", budget);
+
+	processed = 0;
+	ring_budget = budget / pdata->rx_ring_count;
+	do {
+		last_processed = processed;
+
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++) {
+			/* Cleanup Tx ring first */
+			xlgmac_tx_poll(channel);
+
+			/* Process Rx ring next */
+			if (ring_budget > (budget - processed))
+				ring_budget = budget - processed;
+			processed += xlgmac_rx_poll(channel, ring_budget);
+		}
+	} while ((processed < budget) && (processed != last_processed));
+
+	/* If we processed everything, we are done */
+	if (processed < budget) {
+		/* Turn off polling */
+		napi_complete_done(napi, processed);
+
+		/* Enable Tx and Rx interrupts */
+		xlgmac_enable_rx_tx_ints(pdata);
+	}
+
+	XLGMAC_PR("received = %d\n", processed);
+
+	return processed;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c
new file mode 100644
index 000000000000..386bafe74c3f
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c
@@ -0,0 +1,78 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id)
+{
+	struct device *dev = &pcidev->dev;
+	struct xlgmac_resources res;
+	int i, ret;
+
+	ret = pcim_enable_device(pcidev);
+	if (ret) {
+		dev_err(dev, "ERROR: failed to enable device\n");
+		return ret;
+	}
+
+	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+		if (pci_resource_len(pcidev, i) == 0)
+			continue;
+		ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME);
+		if (ret)
+			return ret;
+		break;
+	}
+
+	pci_set_master(pcidev);
+
+	memset(&res, 0, sizeof(res));
+	res.irq = pcidev->irq;
+	res.addr = pcim_iomap_table(pcidev)[i];
+
+	return xlgmac_drv_probe(&pcidev->dev, &res);
+}
+
+static void xlgmac_remove(struct pci_dev *pcidev)
+{
+	xlgmac_drv_remove(&pcidev->dev);
+}
+
+static const struct pci_device_id xlgmac_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS, 0x7302) },
+	{ 0 }
+};
+MODULE_DEVICE_TABLE(pci, xlgmac_pci_tbl);
+
+static struct pci_driver xlgmac_pci_driver = {
+	.name		= XLGMAC_DRV_NAME,
+	.id_table	= xlgmac_pci_tbl,
+	.probe		= xlgmac_probe,
+	.remove		= xlgmac_remove,
+};
+
+module_pci_driver(xlgmac_pci_driver);
+
+MODULE_DESCRIPTION(XLGMAC_DRV_DESC);
+MODULE_VERSION(XLGMAC_DRV_VERSION);
+MODULE_AUTHOR("Jie Deng <jiedeng@synopsys.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h
new file mode 100644
index 000000000000..3754f220567d
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h
@@ -0,0 +1,744 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#ifndef __DWC_XLGMAC_REG_H__
+#define __DWC_XLGMAC_REG_H__
+
+/* MAC register offsets */
+#define MAC_TCR				0x0000
+#define MAC_RCR				0x0004
+#define MAC_PFR				0x0008
+#define MAC_HTR0			0x0010
+#define MAC_VLANTR			0x0050
+#define MAC_VLANHTR			0x0058
+#define MAC_VLANIR			0x0060
+#define MAC_Q0TFCR			0x0070
+#define MAC_RFCR			0x0090
+#define MAC_RQC0R			0x00a0
+#define MAC_RQC1R			0x00a4
+#define MAC_RQC2R			0x00a8
+#define MAC_RQC3R			0x00ac
+#define MAC_ISR				0x00b0
+#define MAC_IER				0x00b4
+#define MAC_VR				0x0110
+#define MAC_HWF0R			0x011c
+#define MAC_HWF1R			0x0120
+#define MAC_HWF2R			0x0124
+#define MAC_MACA0HR			0x0300
+#define MAC_MACA0LR			0x0304
+#define MAC_MACA1HR			0x0308
+#define MAC_MACA1LR			0x030c
+#define MAC_RSSCR			0x0c80
+#define MAC_RSSAR			0x0c88
+#define MAC_RSSDR			0x0c8c
+
+#define MAC_QTFCR_INC			4
+#define MAC_MACA_INC			4
+#define MAC_HTR_INC			4
+#define MAC_RQC2_INC			4
+#define MAC_RQC2_Q_PER_REG		4
+
+/* MAC register entry bit positions and sizes */
+#define MAC_HWF0R_ADDMACADRSEL_POS	18
+#define MAC_HWF0R_ADDMACADRSEL_LEN	5
+#define MAC_HWF0R_ARPOFFSEL_POS		9
+#define MAC_HWF0R_ARPOFFSEL_LEN		1
+#define MAC_HWF0R_EEESEL_POS		13
+#define MAC_HWF0R_EEESEL_LEN		1
+#define MAC_HWF0R_PHYIFSEL_POS		1
+#define MAC_HWF0R_PHYIFSEL_LEN		2
+#define MAC_HWF0R_MGKSEL_POS		7
+#define MAC_HWF0R_MGKSEL_LEN		1
+#define MAC_HWF0R_MMCSEL_POS		8
+#define MAC_HWF0R_MMCSEL_LEN		1
+#define MAC_HWF0R_RWKSEL_POS		6
+#define MAC_HWF0R_RWKSEL_LEN		1
+#define MAC_HWF0R_RXCOESEL_POS		16
+#define MAC_HWF0R_RXCOESEL_LEN		1
+#define MAC_HWF0R_SAVLANINS_POS		27
+#define MAC_HWF0R_SAVLANINS_LEN		1
+#define MAC_HWF0R_SMASEL_POS		5
+#define MAC_HWF0R_SMASEL_LEN		1
+#define MAC_HWF0R_TSSEL_POS		12
+#define MAC_HWF0R_TSSEL_LEN		1
+#define MAC_HWF0R_TSSTSSEL_POS		25
+#define MAC_HWF0R_TSSTSSEL_LEN		2
+#define MAC_HWF0R_TXCOESEL_POS		14
+#define MAC_HWF0R_TXCOESEL_LEN		1
+#define MAC_HWF0R_VLHASH_POS		4
+#define MAC_HWF0R_VLHASH_LEN		1
+#define MAC_HWF1R_ADDR64_POS		14
+#define MAC_HWF1R_ADDR64_LEN		2
+#define MAC_HWF1R_ADVTHWORD_POS		13
+#define MAC_HWF1R_ADVTHWORD_LEN		1
+#define MAC_HWF1R_DBGMEMA_POS		19
+#define MAC_HWF1R_DBGMEMA_LEN		1
+#define MAC_HWF1R_DCBEN_POS		16
+#define MAC_HWF1R_DCBEN_LEN		1
+#define MAC_HWF1R_HASHTBLSZ_POS		24
+#define MAC_HWF1R_HASHTBLSZ_LEN		3
+#define MAC_HWF1R_L3L4FNUM_POS		27
+#define MAC_HWF1R_L3L4FNUM_LEN		4
+#define MAC_HWF1R_NUMTC_POS		21
+#define MAC_HWF1R_NUMTC_LEN		3
+#define MAC_HWF1R_RSSEN_POS		20
+#define MAC_HWF1R_RSSEN_LEN		1
+#define MAC_HWF1R_RXFIFOSIZE_POS	0
+#define MAC_HWF1R_RXFIFOSIZE_LEN	5
+#define MAC_HWF1R_SPHEN_POS		17
+#define MAC_HWF1R_SPHEN_LEN		1
+#define MAC_HWF1R_TSOEN_POS		18
+#define MAC_HWF1R_TSOEN_LEN		1
+#define MAC_HWF1R_TXFIFOSIZE_POS	6
+#define MAC_HWF1R_TXFIFOSIZE_LEN	5
+#define MAC_HWF2R_AUXSNAPNUM_POS	28
+#define MAC_HWF2R_AUXSNAPNUM_LEN	3
+#define MAC_HWF2R_PPSOUTNUM_POS		24
+#define MAC_HWF2R_PPSOUTNUM_LEN		3
+#define MAC_HWF2R_RXCHCNT_POS		12
+#define MAC_HWF2R_RXCHCNT_LEN		4
+#define MAC_HWF2R_RXQCNT_POS		0
+#define MAC_HWF2R_RXQCNT_LEN		4
+#define MAC_HWF2R_TXCHCNT_POS		18
+#define MAC_HWF2R_TXCHCNT_LEN		4
+#define MAC_HWF2R_TXQCNT_POS		6
+#define MAC_HWF2R_TXQCNT_LEN		4
+#define MAC_IER_TSIE_POS		12
+#define MAC_IER_TSIE_LEN		1
+#define MAC_ISR_MMCRXIS_POS		9
+#define MAC_ISR_MMCRXIS_LEN		1
+#define MAC_ISR_MMCTXIS_POS		10
+#define MAC_ISR_MMCTXIS_LEN		1
+#define MAC_ISR_PMTIS_POS		4
+#define MAC_ISR_PMTIS_LEN		1
+#define MAC_ISR_TSIS_POS		12
+#define MAC_ISR_TSIS_LEN		1
+#define MAC_MACA1HR_AE_POS		31
+#define MAC_MACA1HR_AE_LEN		1
+#define MAC_PFR_HMC_POS			2
+#define MAC_PFR_HMC_LEN			1
+#define MAC_PFR_HPF_POS			10
+#define MAC_PFR_HPF_LEN			1
+#define MAC_PFR_HUC_POS			1
+#define MAC_PFR_HUC_LEN			1
+#define MAC_PFR_PM_POS			4
+#define MAC_PFR_PM_LEN			1
+#define MAC_PFR_PR_POS			0
+#define MAC_PFR_PR_LEN			1
+#define MAC_PFR_VTFE_POS		16
+#define MAC_PFR_VTFE_LEN		1
+#define MAC_Q0TFCR_PT_POS		16
+#define MAC_Q0TFCR_PT_LEN		16
+#define MAC_Q0TFCR_TFE_POS		1
+#define MAC_Q0TFCR_TFE_LEN		1
+#define MAC_RCR_ACS_POS			1
+#define MAC_RCR_ACS_LEN			1
+#define MAC_RCR_CST_POS			2
+#define MAC_RCR_CST_LEN			1
+#define MAC_RCR_DCRCC_POS		3
+#define MAC_RCR_DCRCC_LEN		1
+#define MAC_RCR_HDSMS_POS		12
+#define MAC_RCR_HDSMS_LEN		3
+#define MAC_RCR_IPC_POS			9
+#define MAC_RCR_IPC_LEN			1
+#define MAC_RCR_JE_POS			8
+#define MAC_RCR_JE_LEN			1
+#define MAC_RCR_LM_POS			10
+#define MAC_RCR_LM_LEN			1
+#define MAC_RCR_RE_POS			0
+#define MAC_RCR_RE_LEN			1
+#define MAC_RFCR_PFCE_POS		8
+#define MAC_RFCR_PFCE_LEN		1
+#define MAC_RFCR_RFE_POS		0
+#define MAC_RFCR_RFE_LEN		1
+#define MAC_RFCR_UP_POS			1
+#define MAC_RFCR_UP_LEN			1
+#define MAC_RQC0R_RXQ0EN_POS		0
+#define MAC_RQC0R_RXQ0EN_LEN		2
+#define MAC_RSSAR_ADDRT_POS		2
+#define MAC_RSSAR_ADDRT_LEN		1
+#define MAC_RSSAR_CT_POS		1
+#define MAC_RSSAR_CT_LEN		1
+#define MAC_RSSAR_OB_POS		0
+#define MAC_RSSAR_OB_LEN		1
+#define MAC_RSSAR_RSSIA_POS		8
+#define MAC_RSSAR_RSSIA_LEN		8
+#define MAC_RSSCR_IP2TE_POS		1
+#define MAC_RSSCR_IP2TE_LEN		1
+#define MAC_RSSCR_RSSE_POS		0
+#define MAC_RSSCR_RSSE_LEN		1
+#define MAC_RSSCR_TCP4TE_POS		2
+#define MAC_RSSCR_TCP4TE_LEN		1
+#define MAC_RSSCR_UDP4TE_POS		3
+#define MAC_RSSCR_UDP4TE_LEN		1
+#define MAC_RSSDR_DMCH_POS		0
+#define MAC_RSSDR_DMCH_LEN		4
+#define MAC_TCR_SS_POS			28
+#define MAC_TCR_SS_LEN			3
+#define MAC_TCR_TE_POS			0
+#define MAC_TCR_TE_LEN			1
+#define MAC_VLANHTR_VLHT_POS		0
+#define MAC_VLANHTR_VLHT_LEN		16
+#define MAC_VLANIR_VLTI_POS		20
+#define MAC_VLANIR_VLTI_LEN		1
+#define MAC_VLANIR_CSVL_POS		19
+#define MAC_VLANIR_CSVL_LEN		1
+#define MAC_VLANTR_DOVLTC_POS		20
+#define MAC_VLANTR_DOVLTC_LEN		1
+#define MAC_VLANTR_ERSVLM_POS		19
+#define MAC_VLANTR_ERSVLM_LEN		1
+#define MAC_VLANTR_ESVL_POS		18
+#define MAC_VLANTR_ESVL_LEN		1
+#define MAC_VLANTR_ETV_POS		16
+#define MAC_VLANTR_ETV_LEN		1
+#define MAC_VLANTR_EVLS_POS		21
+#define MAC_VLANTR_EVLS_LEN		2
+#define MAC_VLANTR_EVLRXS_POS		24
+#define MAC_VLANTR_EVLRXS_LEN		1
+#define MAC_VLANTR_VL_POS		0
+#define MAC_VLANTR_VL_LEN		16
+#define MAC_VLANTR_VTHM_POS		25
+#define MAC_VLANTR_VTHM_LEN		1
+#define MAC_VLANTR_VTIM_POS		17
+#define MAC_VLANTR_VTIM_LEN		1
+#define MAC_VR_DEVID_POS		8
+#define MAC_VR_DEVID_LEN		8
+#define MAC_VR_SNPSVER_POS		0
+#define MAC_VR_SNPSVER_LEN		8
+#define MAC_VR_USERVER_POS		16
+#define MAC_VR_USERVER_LEN		8
+
+/* MMC register offsets */
+#define MMC_CR				0x0800
+#define MMC_RISR			0x0804
+#define MMC_TISR			0x0808
+#define MMC_RIER			0x080c
+#define MMC_TIER			0x0810
+#define MMC_TXOCTETCOUNT_GB_LO		0x0814
+#define MMC_TXFRAMECOUNT_GB_LO		0x081c
+#define MMC_TXBROADCASTFRAMES_G_LO	0x0824
+#define MMC_TXMULTICASTFRAMES_G_LO	0x082c
+#define MMC_TX64OCTETS_GB_LO		0x0834
+#define MMC_TX65TO127OCTETS_GB_LO	0x083c
+#define MMC_TX128TO255OCTETS_GB_LO	0x0844
+#define MMC_TX256TO511OCTETS_GB_LO	0x084c
+#define MMC_TX512TO1023OCTETS_GB_LO	0x0854
+#define MMC_TX1024TOMAXOCTETS_GB_LO	0x085c
+#define MMC_TXUNICASTFRAMES_GB_LO	0x0864
+#define MMC_TXMULTICASTFRAMES_GB_LO	0x086c
+#define MMC_TXBROADCASTFRAMES_GB_LO	0x0874
+#define MMC_TXUNDERFLOWERROR_LO		0x087c
+#define MMC_TXOCTETCOUNT_G_LO		0x0884
+#define MMC_TXFRAMECOUNT_G_LO		0x088c
+#define MMC_TXPAUSEFRAMES_LO		0x0894
+#define MMC_TXVLANFRAMES_G_LO		0x089c
+#define MMC_RXFRAMECOUNT_GB_LO		0x0900
+#define MMC_RXOCTETCOUNT_GB_LO		0x0908
+#define MMC_RXOCTETCOUNT_G_LO		0x0910
+#define MMC_RXBROADCASTFRAMES_G_LO	0x0918
+#define MMC_RXMULTICASTFRAMES_G_LO	0x0920
+#define MMC_RXCRCERROR_LO		0x0928
+#define MMC_RXRUNTERROR			0x0930
+#define MMC_RXJABBERERROR		0x0934
+#define MMC_RXUNDERSIZE_G		0x0938
+#define MMC_RXOVERSIZE_G		0x093c
+#define MMC_RX64OCTETS_GB_LO		0x0940
+#define MMC_RX65TO127OCTETS_GB_LO	0x0948
+#define MMC_RX128TO255OCTETS_GB_LO	0x0950
+#define MMC_RX256TO511OCTETS_GB_LO	0x0958
+#define MMC_RX512TO1023OCTETS_GB_LO	0x0960
+#define MMC_RX1024TOMAXOCTETS_GB_LO	0x0968
+#define MMC_RXUNICASTFRAMES_G_LO	0x0970
+#define MMC_RXLENGTHERROR_LO		0x0978
+#define MMC_RXOUTOFRANGETYPE_LO		0x0980
+#define MMC_RXPAUSEFRAMES_LO		0x0988
+#define MMC_RXFIFOOVERFLOW_LO		0x0990
+#define MMC_RXVLANFRAMES_GB_LO		0x0998
+#define MMC_RXWATCHDOGERROR		0x09a0
+
+/* MMC register entry bit positions and sizes */
+#define MMC_CR_CR_POS				0
+#define MMC_CR_CR_LEN				1
+#define MMC_CR_CSR_POS				1
+#define MMC_CR_CSR_LEN				1
+#define MMC_CR_ROR_POS				2
+#define MMC_CR_ROR_LEN				1
+#define MMC_CR_MCF_POS				3
+#define MMC_CR_MCF_LEN				1
+#define MMC_CR_MCT_POS				4
+#define MMC_CR_MCT_LEN				2
+#define MMC_RIER_ALL_INTERRUPTS_POS		0
+#define MMC_RIER_ALL_INTERRUPTS_LEN		23
+#define MMC_RISR_RXFRAMECOUNT_GB_POS		0
+#define MMC_RISR_RXFRAMECOUNT_GB_LEN		1
+#define MMC_RISR_RXOCTETCOUNT_GB_POS		1
+#define MMC_RISR_RXOCTETCOUNT_GB_LEN		1
+#define MMC_RISR_RXOCTETCOUNT_G_POS		2
+#define MMC_RISR_RXOCTETCOUNT_G_LEN		1
+#define MMC_RISR_RXBROADCASTFRAMES_G_POS	3
+#define MMC_RISR_RXBROADCASTFRAMES_G_LEN	1
+#define MMC_RISR_RXMULTICASTFRAMES_G_POS	4
+#define MMC_RISR_RXMULTICASTFRAMES_G_LEN	1
+#define MMC_RISR_RXCRCERROR_POS			5
+#define MMC_RISR_RXCRCERROR_LEN			1
+#define MMC_RISR_RXRUNTERROR_POS		6
+#define MMC_RISR_RXRUNTERROR_LEN		1
+#define MMC_RISR_RXJABBERERROR_POS		7
+#define MMC_RISR_RXJABBERERROR_LEN		1
+#define MMC_RISR_RXUNDERSIZE_G_POS		8
+#define MMC_RISR_RXUNDERSIZE_G_LEN		1
+#define MMC_RISR_RXOVERSIZE_G_POS		9
+#define MMC_RISR_RXOVERSIZE_G_LEN		1
+#define MMC_RISR_RX64OCTETS_GB_POS		10
+#define MMC_RISR_RX64OCTETS_GB_LEN		1
+#define MMC_RISR_RX65TO127OCTETS_GB_POS		11
+#define MMC_RISR_RX65TO127OCTETS_GB_LEN		1
+#define MMC_RISR_RX128TO255OCTETS_GB_POS	12
+#define MMC_RISR_RX128TO255OCTETS_GB_LEN	1
+#define MMC_RISR_RX256TO511OCTETS_GB_POS	13
+#define MMC_RISR_RX256TO511OCTETS_GB_LEN	1
+#define MMC_RISR_RX512TO1023OCTETS_GB_POS	14
+#define MMC_RISR_RX512TO1023OCTETS_GB_LEN	1
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_POS	15
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_LEN	1
+#define MMC_RISR_RXUNICASTFRAMES_G_POS		16
+#define MMC_RISR_RXUNICASTFRAMES_G_LEN		1
+#define MMC_RISR_RXLENGTHERROR_POS		17
+#define MMC_RISR_RXLENGTHERROR_LEN		1
+#define MMC_RISR_RXOUTOFRANGETYPE_POS		18
+#define MMC_RISR_RXOUTOFRANGETYPE_LEN		1
+#define MMC_RISR_RXPAUSEFRAMES_POS		19
+#define MMC_RISR_RXPAUSEFRAMES_LEN		1
+#define MMC_RISR_RXFIFOOVERFLOW_POS		20
+#define MMC_RISR_RXFIFOOVERFLOW_LEN		1
+#define MMC_RISR_RXVLANFRAMES_GB_POS		21
+#define MMC_RISR_RXVLANFRAMES_GB_LEN		1
+#define MMC_RISR_RXWATCHDOGERROR_POS		22
+#define MMC_RISR_RXWATCHDOGERROR_LEN		1
+#define MMC_TIER_ALL_INTERRUPTS_POS		0
+#define MMC_TIER_ALL_INTERRUPTS_LEN		18
+#define MMC_TISR_TXOCTETCOUNT_GB_POS		0
+#define MMC_TISR_TXOCTETCOUNT_GB_LEN		1
+#define MMC_TISR_TXFRAMECOUNT_GB_POS		1
+#define MMC_TISR_TXFRAMECOUNT_GB_LEN		1
+#define MMC_TISR_TXBROADCASTFRAMES_G_POS	2
+#define MMC_TISR_TXBROADCASTFRAMES_G_LEN	1
+#define MMC_TISR_TXMULTICASTFRAMES_G_POS	3
+#define MMC_TISR_TXMULTICASTFRAMES_G_LEN	1
+#define MMC_TISR_TX64OCTETS_GB_POS		4
+#define MMC_TISR_TX64OCTETS_GB_LEN		1
+#define MMC_TISR_TX65TO127OCTETS_GB_POS		5
+#define MMC_TISR_TX65TO127OCTETS_GB_LEN		1
+#define MMC_TISR_TX128TO255OCTETS_GB_POS	6
+#define MMC_TISR_TX128TO255OCTETS_GB_LEN	1
+#define MMC_TISR_TX256TO511OCTETS_GB_POS	7
+#define MMC_TISR_TX256TO511OCTETS_GB_LEN	1
+#define MMC_TISR_TX512TO1023OCTETS_GB_POS	8
+#define MMC_TISR_TX512TO1023OCTETS_GB_LEN	1
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_POS	9
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_LEN	1
+#define MMC_TISR_TXUNICASTFRAMES_GB_POS		10
+#define MMC_TISR_TXUNICASTFRAMES_GB_LEN		1
+#define MMC_TISR_TXMULTICASTFRAMES_GB_POS	11
+#define MMC_TISR_TXMULTICASTFRAMES_GB_LEN	1
+#define MMC_TISR_TXBROADCASTFRAMES_GB_POS	12
+#define MMC_TISR_TXBROADCASTFRAMES_GB_LEN	1
+#define MMC_TISR_TXUNDERFLOWERROR_POS		13
+#define MMC_TISR_TXUNDERFLOWERROR_LEN		1
+#define MMC_TISR_TXOCTETCOUNT_G_POS		14
+#define MMC_TISR_TXOCTETCOUNT_G_LEN		1
+#define MMC_TISR_TXFRAMECOUNT_G_POS		15
+#define MMC_TISR_TXFRAMECOUNT_G_LEN		1
+#define MMC_TISR_TXPAUSEFRAMES_POS		16
+#define MMC_TISR_TXPAUSEFRAMES_LEN		1
+#define MMC_TISR_TXVLANFRAMES_G_POS		17
+#define MMC_TISR_TXVLANFRAMES_G_LEN		1
+
+/* MTL register offsets */
+#define MTL_OMR				0x1000
+#define MTL_FDDR			0x1010
+#define MTL_RQDCM0R			0x1030
+
+#define MTL_RQDCM_INC			4
+#define MTL_RQDCM_Q_PER_REG		4
+
+/* MTL register entry bit positions and sizes */
+#define MTL_OMR_ETSALG_POS		5
+#define MTL_OMR_ETSALG_LEN		2
+#define MTL_OMR_RAA_POS			2
+#define MTL_OMR_RAA_LEN			1
+
+/* MTL queue register offsets
+ *   Multiple queues can be active.  The first queue has registers
+ *   that begin at 0x1100.  Each subsequent queue has registers that
+ *   are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_Q_BASE			0x1100
+#define MTL_Q_INC			0x80
+
+#define MTL_Q_TQOMR			0x00
+#define MTL_Q_RQOMR			0x40
+#define MTL_Q_RQDR			0x48
+#define MTL_Q_RQFCR			0x50
+#define MTL_Q_IER			0x70
+#define MTL_Q_ISR			0x74
+
+/* MTL queue register entry bit positions and sizes */
+#define MTL_Q_RQDR_PRXQ_POS		16
+#define MTL_Q_RQDR_PRXQ_LEN		14
+#define MTL_Q_RQDR_RXQSTS_POS		4
+#define MTL_Q_RQDR_RXQSTS_LEN		2
+#define MTL_Q_RQFCR_RFA_POS		1
+#define MTL_Q_RQFCR_RFA_LEN		6
+#define MTL_Q_RQFCR_RFD_POS		17
+#define MTL_Q_RQFCR_RFD_LEN		6
+#define MTL_Q_RQOMR_EHFC_POS		7
+#define MTL_Q_RQOMR_EHFC_LEN		1
+#define MTL_Q_RQOMR_RQS_POS		16
+#define MTL_Q_RQOMR_RQS_LEN		9
+#define MTL_Q_RQOMR_RSF_POS		5
+#define MTL_Q_RQOMR_RSF_LEN		1
+#define MTL_Q_RQOMR_FEP_POS		4
+#define MTL_Q_RQOMR_FEP_LEN		1
+#define MTL_Q_RQOMR_FUP_POS		3
+#define MTL_Q_RQOMR_FUP_LEN		1
+#define MTL_Q_RQOMR_RTC_POS		0
+#define MTL_Q_RQOMR_RTC_LEN		2
+#define MTL_Q_TQOMR_FTQ_POS		0
+#define MTL_Q_TQOMR_FTQ_LEN		1
+#define MTL_Q_TQOMR_Q2TCMAP_POS		8
+#define MTL_Q_TQOMR_Q2TCMAP_LEN		3
+#define MTL_Q_TQOMR_TQS_POS		16
+#define MTL_Q_TQOMR_TQS_LEN		10
+#define MTL_Q_TQOMR_TSF_POS		1
+#define MTL_Q_TQOMR_TSF_LEN		1
+#define MTL_Q_TQOMR_TTC_POS		4
+#define MTL_Q_TQOMR_TTC_LEN		3
+#define MTL_Q_TQOMR_TXQEN_POS		2
+#define MTL_Q_TQOMR_TXQEN_LEN		2
+
+/* MTL queue register value */
+#define MTL_RSF_DISABLE			0x00
+#define MTL_RSF_ENABLE			0x01
+#define MTL_TSF_DISABLE			0x00
+#define MTL_TSF_ENABLE			0x01
+
+#define MTL_RX_THRESHOLD_64		0x00
+#define MTL_RX_THRESHOLD_96		0x02
+#define MTL_RX_THRESHOLD_128		0x03
+#define MTL_TX_THRESHOLD_64		0x00
+#define MTL_TX_THRESHOLD_96		0x02
+#define MTL_TX_THRESHOLD_128		0x03
+#define MTL_TX_THRESHOLD_192		0x04
+#define MTL_TX_THRESHOLD_256		0x05
+#define MTL_TX_THRESHOLD_384		0x06
+#define MTL_TX_THRESHOLD_512		0x07
+
+#define MTL_ETSALG_WRR			0x00
+#define MTL_ETSALG_WFQ			0x01
+#define MTL_ETSALG_DWRR			0x02
+#define MTL_RAA_SP			0x00
+#define MTL_RAA_WSP			0x01
+
+#define MTL_Q_DISABLED			0x00
+#define MTL_Q_ENABLED			0x02
+
+#define MTL_RQDCM0R_Q0MDMACH		0x0
+#define MTL_RQDCM0R_Q1MDMACH		0x00000100
+#define MTL_RQDCM0R_Q2MDMACH		0x00020000
+#define MTL_RQDCM0R_Q3MDMACH		0x03000000
+#define MTL_RQDCM1R_Q4MDMACH		0x00000004
+#define MTL_RQDCM1R_Q5MDMACH		0x00000500
+#define MTL_RQDCM1R_Q6MDMACH		0x00060000
+#define MTL_RQDCM1R_Q7MDMACH		0x07000000
+#define MTL_RQDCM2R_Q8MDMACH		0x00000008
+#define MTL_RQDCM2R_Q9MDMACH		0x00000900
+#define MTL_RQDCM2R_Q10MDMACH		0x000A0000
+#define MTL_RQDCM2R_Q11MDMACH		0x0B000000
+
+/* MTL traffic class register offsets
+ *   Multiple traffic classes can be active.  The first class has registers
+ *   that begin at 0x1100.  Each subsequent queue has registers that
+ *   are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_TC_BASE			MTL_Q_BASE
+#define MTL_TC_INC			MTL_Q_INC
+
+#define MTL_TC_ETSCR			0x10
+#define MTL_TC_ETSSR			0x14
+#define MTL_TC_QWR			0x18
+
+/* MTL traffic class register entry bit positions and sizes */
+#define MTL_TC_ETSCR_TSA_POS		0
+#define MTL_TC_ETSCR_TSA_LEN		2
+#define MTL_TC_QWR_QW_POS		0
+#define MTL_TC_QWR_QW_LEN		21
+
+/* MTL traffic class register value */
+#define MTL_TSA_SP			0x00
+#define MTL_TSA_ETS			0x02
+
+/* DMA register offsets */
+#define DMA_MR				0x3000
+#define DMA_SBMR			0x3004
+#define DMA_ISR				0x3008
+#define DMA_DSR0			0x3020
+#define DMA_DSR1			0x3024
+
+/* DMA register entry bit positions and sizes */
+#define DMA_ISR_MACIS_POS		17
+#define DMA_ISR_MACIS_LEN		1
+#define DMA_ISR_MTLIS_POS		16
+#define DMA_ISR_MTLIS_LEN		1
+#define DMA_MR_SWR_POS			0
+#define DMA_MR_SWR_LEN			1
+#define DMA_SBMR_EAME_POS		11
+#define DMA_SBMR_EAME_LEN		1
+#define DMA_SBMR_BLEN_64_POS		5
+#define DMA_SBMR_BLEN_64_LEN		1
+#define DMA_SBMR_BLEN_128_POS		6
+#define DMA_SBMR_BLEN_128_LEN		1
+#define DMA_SBMR_BLEN_256_POS		7
+#define DMA_SBMR_BLEN_256_LEN		1
+#define DMA_SBMR_UNDEF_POS		0
+#define DMA_SBMR_UNDEF_LEN		1
+
+/* DMA register values */
+#define DMA_DSR_RPS_LEN			4
+#define DMA_DSR_TPS_LEN			4
+#define DMA_DSR_Q_LEN			(DMA_DSR_RPS_LEN + DMA_DSR_TPS_LEN)
+#define DMA_DSR0_TPS_START		12
+#define DMA_DSRX_FIRST_QUEUE		3
+#define DMA_DSRX_INC			4
+#define DMA_DSRX_QPR			4
+#define DMA_DSRX_TPS_START		4
+#define DMA_TPS_STOPPED			0x00
+#define DMA_TPS_SUSPENDED		0x06
+
+/* DMA channel register offsets
+ *   Multiple channels can be active.  The first channel has registers
+ *   that begin at 0x3100.  Each subsequent channel has registers that
+ *   are accessed using an offset of 0x80 from the previous channel.
+ */
+#define DMA_CH_BASE			0x3100
+#define DMA_CH_INC			0x80
+
+#define DMA_CH_CR			0x00
+#define DMA_CH_TCR			0x04
+#define DMA_CH_RCR			0x08
+#define DMA_CH_TDLR_HI			0x10
+#define DMA_CH_TDLR_LO			0x14
+#define DMA_CH_RDLR_HI			0x18
+#define DMA_CH_RDLR_LO			0x1c
+#define DMA_CH_TDTR_LO			0x24
+#define DMA_CH_RDTR_LO			0x2c
+#define DMA_CH_TDRLR			0x30
+#define DMA_CH_RDRLR			0x34
+#define DMA_CH_IER			0x38
+#define DMA_CH_RIWT			0x3c
+#define DMA_CH_SR			0x60
+
+/* DMA channel register entry bit positions and sizes */
+#define DMA_CH_CR_PBLX8_POS		16
+#define DMA_CH_CR_PBLX8_LEN		1
+#define DMA_CH_CR_SPH_POS		24
+#define DMA_CH_CR_SPH_LEN		1
+#define DMA_CH_IER_AIE_POS		15
+#define DMA_CH_IER_AIE_LEN		1
+#define DMA_CH_IER_FBEE_POS		12
+#define DMA_CH_IER_FBEE_LEN		1
+#define DMA_CH_IER_NIE_POS		16
+#define DMA_CH_IER_NIE_LEN		1
+#define DMA_CH_IER_RBUE_POS		7
+#define DMA_CH_IER_RBUE_LEN		1
+#define DMA_CH_IER_RIE_POS		6
+#define DMA_CH_IER_RIE_LEN		1
+#define DMA_CH_IER_RSE_POS		8
+#define DMA_CH_IER_RSE_LEN		1
+#define DMA_CH_IER_TBUE_POS		2
+#define DMA_CH_IER_TBUE_LEN		1
+#define DMA_CH_IER_TIE_POS		0
+#define DMA_CH_IER_TIE_LEN		1
+#define DMA_CH_IER_TXSE_POS		1
+#define DMA_CH_IER_TXSE_LEN		1
+#define DMA_CH_RCR_PBL_POS		16
+#define DMA_CH_RCR_PBL_LEN		6
+#define DMA_CH_RCR_RBSZ_POS		1
+#define DMA_CH_RCR_RBSZ_LEN		14
+#define DMA_CH_RCR_SR_POS		0
+#define DMA_CH_RCR_SR_LEN		1
+#define DMA_CH_RIWT_RWT_POS		0
+#define DMA_CH_RIWT_RWT_LEN		8
+#define DMA_CH_SR_FBE_POS		12
+#define DMA_CH_SR_FBE_LEN		1
+#define DMA_CH_SR_RBU_POS		7
+#define DMA_CH_SR_RBU_LEN		1
+#define DMA_CH_SR_RI_POS		6
+#define DMA_CH_SR_RI_LEN		1
+#define DMA_CH_SR_RPS_POS		8
+#define DMA_CH_SR_RPS_LEN		1
+#define DMA_CH_SR_TBU_POS		2
+#define DMA_CH_SR_TBU_LEN		1
+#define DMA_CH_SR_TI_POS		0
+#define DMA_CH_SR_TI_LEN		1
+#define DMA_CH_SR_TPS_POS		1
+#define DMA_CH_SR_TPS_LEN		1
+#define DMA_CH_TCR_OSP_POS		4
+#define DMA_CH_TCR_OSP_LEN		1
+#define DMA_CH_TCR_PBL_POS		16
+#define DMA_CH_TCR_PBL_LEN		6
+#define DMA_CH_TCR_ST_POS		0
+#define DMA_CH_TCR_ST_LEN		1
+#define DMA_CH_TCR_TSE_POS		12
+#define DMA_CH_TCR_TSE_LEN		1
+
+/* DMA channel register values */
+#define DMA_OSP_DISABLE			0x00
+#define DMA_OSP_ENABLE			0x01
+#define DMA_PBL_1			1
+#define DMA_PBL_2			2
+#define DMA_PBL_4			4
+#define DMA_PBL_8			8
+#define DMA_PBL_16			16
+#define DMA_PBL_32			32
+#define DMA_PBL_64			64
+#define DMA_PBL_128			128
+#define DMA_PBL_256			256
+#define DMA_PBL_X8_DISABLE		0x00
+#define DMA_PBL_X8_ENABLE		0x01
+
+/* Descriptor/Packet entry bit positions and sizes */
+#define RX_PACKET_ERRORS_CRC_POS		2
+#define RX_PACKET_ERRORS_CRC_LEN		1
+#define RX_PACKET_ERRORS_FRAME_POS		3
+#define RX_PACKET_ERRORS_FRAME_LEN		1
+#define RX_PACKET_ERRORS_LENGTH_POS		0
+#define RX_PACKET_ERRORS_LENGTH_LEN		1
+#define RX_PACKET_ERRORS_OVERRUN_POS		1
+#define RX_PACKET_ERRORS_OVERRUN_LEN		1
+
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_POS	0
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN	1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS	1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN	1
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_POS	2
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN	1
+#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS	3
+#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN	1
+#define RX_PACKET_ATTRIBUTES_CONTEXT_POS	4
+#define RX_PACKET_ATTRIBUTES_CONTEXT_LEN	1
+#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS	5
+#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN	1
+#define RX_PACKET_ATTRIBUTES_RSS_HASH_POS	6
+#define RX_PACKET_ATTRIBUTES_RSS_HASH_LEN	1
+
+#define RX_NORMAL_DESC0_OVT_POS			0
+#define RX_NORMAL_DESC0_OVT_LEN			16
+#define RX_NORMAL_DESC2_HL_POS			0
+#define RX_NORMAL_DESC2_HL_LEN			10
+#define RX_NORMAL_DESC3_CDA_POS			27
+#define RX_NORMAL_DESC3_CDA_LEN			1
+#define RX_NORMAL_DESC3_CTXT_POS		30
+#define RX_NORMAL_DESC3_CTXT_LEN		1
+#define RX_NORMAL_DESC3_ES_POS			15
+#define RX_NORMAL_DESC3_ES_LEN			1
+#define RX_NORMAL_DESC3_ETLT_POS		16
+#define RX_NORMAL_DESC3_ETLT_LEN		4
+#define RX_NORMAL_DESC3_FD_POS			29
+#define RX_NORMAL_DESC3_FD_LEN			1
+#define RX_NORMAL_DESC3_INTE_POS		30
+#define RX_NORMAL_DESC3_INTE_LEN		1
+#define RX_NORMAL_DESC3_L34T_POS		20
+#define RX_NORMAL_DESC3_L34T_LEN		4
+#define RX_NORMAL_DESC3_LD_POS			28
+#define RX_NORMAL_DESC3_LD_LEN			1
+#define RX_NORMAL_DESC3_OWN_POS			31
+#define RX_NORMAL_DESC3_OWN_LEN			1
+#define RX_NORMAL_DESC3_PL_POS			0
+#define RX_NORMAL_DESC3_PL_LEN			14
+#define RX_NORMAL_DESC3_RSV_POS			26
+#define RX_NORMAL_DESC3_RSV_LEN			1
+
+#define RX_DESC3_L34T_IPV4_TCP			1
+#define RX_DESC3_L34T_IPV4_UDP			2
+#define RX_DESC3_L34T_IPV4_ICMP			3
+#define RX_DESC3_L34T_IPV6_TCP			9
+#define RX_DESC3_L34T_IPV6_UDP			10
+#define RX_DESC3_L34T_IPV6_ICMP			11
+
+#define RX_CONTEXT_DESC3_TSA_POS		4
+#define RX_CONTEXT_DESC3_TSA_LEN		1
+#define RX_CONTEXT_DESC3_TSD_POS		6
+#define RX_CONTEXT_DESC3_TSD_LEN		1
+
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS	0
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN	1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS	1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN	1
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS	2
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN	1
+#define TX_PACKET_ATTRIBUTES_PTP_POS		3
+#define TX_PACKET_ATTRIBUTES_PTP_LEN		1
+
+#define TX_CONTEXT_DESC2_MSS_POS		0
+#define TX_CONTEXT_DESC2_MSS_LEN		15
+#define TX_CONTEXT_DESC3_CTXT_POS		30
+#define TX_CONTEXT_DESC3_CTXT_LEN		1
+#define TX_CONTEXT_DESC3_TCMSSV_POS		26
+#define TX_CONTEXT_DESC3_TCMSSV_LEN		1
+#define TX_CONTEXT_DESC3_VLTV_POS		16
+#define TX_CONTEXT_DESC3_VLTV_LEN		1
+#define TX_CONTEXT_DESC3_VT_POS			0
+#define TX_CONTEXT_DESC3_VT_LEN			16
+
+#define TX_NORMAL_DESC2_HL_B1L_POS		0
+#define TX_NORMAL_DESC2_HL_B1L_LEN		14
+#define TX_NORMAL_DESC2_IC_POS			31
+#define TX_NORMAL_DESC2_IC_LEN			1
+#define TX_NORMAL_DESC2_TTSE_POS		30
+#define TX_NORMAL_DESC2_TTSE_LEN		1
+#define TX_NORMAL_DESC2_VTIR_POS		14
+#define TX_NORMAL_DESC2_VTIR_LEN		2
+#define TX_NORMAL_DESC3_CIC_POS			16
+#define TX_NORMAL_DESC3_CIC_LEN			2
+#define TX_NORMAL_DESC3_CPC_POS			26
+#define TX_NORMAL_DESC3_CPC_LEN			2
+#define TX_NORMAL_DESC3_CTXT_POS		30
+#define TX_NORMAL_DESC3_CTXT_LEN		1
+#define TX_NORMAL_DESC3_FD_POS			29
+#define TX_NORMAL_DESC3_FD_LEN			1
+#define TX_NORMAL_DESC3_FL_POS			0
+#define TX_NORMAL_DESC3_FL_LEN			15
+#define TX_NORMAL_DESC3_LD_POS			28
+#define TX_NORMAL_DESC3_LD_LEN			1
+#define TX_NORMAL_DESC3_OWN_POS			31
+#define TX_NORMAL_DESC3_OWN_LEN			1
+#define TX_NORMAL_DESC3_TCPHDRLEN_POS		19
+#define TX_NORMAL_DESC3_TCPHDRLEN_LEN		4
+#define TX_NORMAL_DESC3_TCPPL_POS		0
+#define TX_NORMAL_DESC3_TCPPL_LEN		18
+#define TX_NORMAL_DESC3_TSE_POS			18
+#define TX_NORMAL_DESC3_TSE_LEN			1
+
+#define TX_NORMAL_DESC2_VLAN_INSERT		0x2
+
+#define XLGMAC_MTL_REG(pdata, n, reg)					\
+	((pdata)->mac_regs + MTL_Q_BASE + ((n) * MTL_Q_INC) + (reg))
+
+#define XLGMAC_DMA_REG(channel, reg)	((channel)->dma_regs + (reg))
+
+#endif /* __DWC_XLGMAC_REG_H__ */
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
new file mode 100644
index 000000000000..cab3e40a86b9
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
@@ -0,0 +1,660 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#ifndef __DWC_XLGMAC_H__
+#define __DWC_XLGMAC_H__
+
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <linux/phy.h>
+#include <linux/if_vlan.h>
+#include <linux/bitops.h>
+#include <linux/timecounter.h>
+
+#define XLGMAC_DRV_NAME			"dwc-xlgmac"
+#define XLGMAC_DRV_VERSION		"1.0.0"
+#define XLGMAC_DRV_DESC			"Synopsys DWC XLGMAC Driver"
+
+/* Descriptor related parameters */
+#define XLGMAC_TX_DESC_CNT		1024
+#define XLGMAC_TX_DESC_MIN_FREE		(XLGMAC_TX_DESC_CNT >> 3)
+#define XLGMAC_TX_DESC_MAX_PROC		(XLGMAC_TX_DESC_CNT >> 1)
+#define XLGMAC_RX_DESC_CNT		1024
+#define XLGMAC_RX_DESC_MAX_DIRTY	(XLGMAC_RX_DESC_CNT >> 3)
+
+/* Descriptors required for maximum contiguous TSO/GSO packet */
+#define XLGMAC_TX_MAX_SPLIT	((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
+
+/* Maximum possible descriptors needed for a SKB */
+#define XLGMAC_TX_MAX_DESC_NR	(MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2)
+
+#define XLGMAC_TX_MAX_BUF_SIZE	(0x3fff & ~(64 - 1))
+#define XLGMAC_RX_MIN_BUF_SIZE	(ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN)
+#define XLGMAC_RX_BUF_ALIGN	64
+
+/* Maximum Size for Splitting the Header Data
+ * Keep in sync with SKB_ALLOC_SIZE
+ * 3'b000: 64 bytes, 3'b001: 128 bytes
+ * 3'b010: 256 bytes, 3'b011: 512 bytes
+ * 3'b100: 1023 bytes ,   3'b101'3'b111: Reserved
+ */
+#define XLGMAC_SPH_HDSMS_SIZE		3
+#define XLGMAC_SKB_ALLOC_SIZE		512
+
+#define XLGMAC_MAX_FIFO			81920
+
+#define XLGMAC_MAX_DMA_CHANNELS		16
+#define XLGMAC_DMA_STOP_TIMEOUT		5
+#define XLGMAC_DMA_INTERRUPT_MASK	0x31c7
+
+/* Default coalescing parameters */
+#define XLGMAC_INIT_DMA_TX_USECS	1000
+#define XLGMAC_INIT_DMA_TX_FRAMES	25
+#define XLGMAC_INIT_DMA_RX_USECS	30
+#define XLGMAC_INIT_DMA_RX_FRAMES	25
+#define XLGMAC_MAX_DMA_RIWT		0xff
+#define XLGMAC_MIN_DMA_RIWT		0x01
+
+/* Flow control queue count */
+#define XLGMAC_MAX_FLOW_CONTROL_QUEUES	8
+
+/* System clock is 125 MHz */
+#define XLGMAC_SYSCLOCK			125000000
+
+/* Maximum MAC address hash table size (256 bits = 8 bytes) */
+#define XLGMAC_MAC_HASH_TABLE_SIZE	8
+
+/* Receive Side Scaling */
+#define XLGMAC_RSS_HASH_KEY_SIZE	40
+#define XLGMAC_RSS_MAX_TABLE_SIZE	256
+#define XLGMAC_RSS_LOOKUP_TABLE_TYPE	0
+#define XLGMAC_RSS_HASH_KEY_TYPE	1
+
+#define XLGMAC_STD_PACKET_MTU		1500
+#define XLGMAC_JUMBO_PACKET_MTU		9000
+
+/* Helper macro for descriptor handling
+ *  Always use XLGMAC_GET_DESC_DATA to access the descriptor data
+ */
+#define XLGMAC_GET_DESC_DATA(ring, idx) ({				\
+	typeof(ring) _ring = (ring);					\
+	((_ring)->desc_data_head +					\
+	 ((idx) & ((_ring)->dma_desc_count - 1)));			\
+})
+
+#define XLGMAC_GET_REG_BITS(var, pos, len) ({				\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	((var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos);		\
+})
+
+#define XLGMAC_GET_REG_BITS_LE(var, pos, len) ({			\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	typeof(var) _var = le32_to_cpu((var));				\
+	((_var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos);		\
+})
+
+#define XLGMAC_SET_REG_BITS(var, pos, len, val) ({			\
+	typeof(var) _var = (var);					\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	typeof(val) _val = (val);					\
+	_val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos);		\
+	_var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val;		\
+})
+
+#define XLGMAC_SET_REG_BITS_LE(var, pos, len, val) ({			\
+	typeof(var) _var = (var);					\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	typeof(val) _val = (val);					\
+	_val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos);		\
+	_var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val;		\
+	cpu_to_le32(_var);						\
+})
+
+struct xlgmac_pdata;
+
+enum xlgmac_int {
+	XLGMAC_INT_DMA_CH_SR_TI,
+	XLGMAC_INT_DMA_CH_SR_TPS,
+	XLGMAC_INT_DMA_CH_SR_TBU,
+	XLGMAC_INT_DMA_CH_SR_RI,
+	XLGMAC_INT_DMA_CH_SR_RBU,
+	XLGMAC_INT_DMA_CH_SR_RPS,
+	XLGMAC_INT_DMA_CH_SR_TI_RI,
+	XLGMAC_INT_DMA_CH_SR_FBE,
+	XLGMAC_INT_DMA_ALL,
+};
+
+struct xlgmac_stats {
+	/* MMC TX counters */
+	u64 txoctetcount_gb;
+	u64 txframecount_gb;
+	u64 txbroadcastframes_g;
+	u64 txmulticastframes_g;
+	u64 tx64octets_gb;
+	u64 tx65to127octets_gb;
+	u64 tx128to255octets_gb;
+	u64 tx256to511octets_gb;
+	u64 tx512to1023octets_gb;
+	u64 tx1024tomaxoctets_gb;
+	u64 txunicastframes_gb;
+	u64 txmulticastframes_gb;
+	u64 txbroadcastframes_gb;
+	u64 txunderflowerror;
+	u64 txoctetcount_g;
+	u64 txframecount_g;
+	u64 txpauseframes;
+	u64 txvlanframes_g;
+
+	/* MMC RX counters */
+	u64 rxframecount_gb;
+	u64 rxoctetcount_gb;
+	u64 rxoctetcount_g;
+	u64 rxbroadcastframes_g;
+	u64 rxmulticastframes_g;
+	u64 rxcrcerror;
+	u64 rxrunterror;
+	u64 rxjabbererror;
+	u64 rxundersize_g;
+	u64 rxoversize_g;
+	u64 rx64octets_gb;
+	u64 rx65to127octets_gb;
+	u64 rx128to255octets_gb;
+	u64 rx256to511octets_gb;
+	u64 rx512to1023octets_gb;
+	u64 rx1024tomaxoctets_gb;
+	u64 rxunicastframes_g;
+	u64 rxlengtherror;
+	u64 rxoutofrangetype;
+	u64 rxpauseframes;
+	u64 rxfifooverflow;
+	u64 rxvlanframes_gb;
+	u64 rxwatchdogerror;
+
+	/* Extra counters */
+	u64 tx_tso_packets;
+	u64 rx_split_header_packets;
+	u64 tx_process_stopped;
+	u64 rx_process_stopped;
+	u64 tx_buffer_unavailable;
+	u64 rx_buffer_unavailable;
+	u64 fatal_bus_error;
+	u64 tx_vlan_packets;
+	u64 rx_vlan_packets;
+	u64 napi_poll_isr;
+	u64 napi_poll_txtimer;
+};
+
+struct xlgmac_ring_buf {
+	struct sk_buff *skb;
+	dma_addr_t skb_dma;
+	unsigned int skb_len;
+};
+
+/* Common Tx and Rx DMA hardware descriptor */
+struct xlgmac_dma_desc {
+	__le32 desc0;
+	__le32 desc1;
+	__le32 desc2;
+	__le32 desc3;
+};
+
+/* Page allocation related values */
+struct xlgmac_page_alloc {
+	struct page *pages;
+	unsigned int pages_len;
+	unsigned int pages_offset;
+
+	dma_addr_t pages_dma;
+};
+
+/* Ring entry buffer data */
+struct xlgmac_buffer_data {
+	struct xlgmac_page_alloc pa;
+	struct xlgmac_page_alloc pa_unmap;
+
+	dma_addr_t dma_base;
+	unsigned long dma_off;
+	unsigned int dma_len;
+};
+
+/* Tx-related desc data */
+struct xlgmac_tx_desc_data {
+	unsigned int packets;		/* BQL packet count */
+	unsigned int bytes;		/* BQL byte count */
+};
+
+/* Rx-related desc data */
+struct xlgmac_rx_desc_data {
+	struct xlgmac_buffer_data hdr;	/* Header locations */
+	struct xlgmac_buffer_data buf;	/* Payload locations */
+
+	unsigned short hdr_len;		/* Length of received header */
+	unsigned short len;		/* Length of received packet */
+};
+
+struct xlgmac_pkt_info {
+	struct sk_buff *skb;
+
+	unsigned int attributes;
+
+	unsigned int errors;
+
+	/* descriptors needed for this packet */
+	unsigned int desc_count;
+	unsigned int length;
+
+	unsigned int tx_packets;
+	unsigned int tx_bytes;
+
+	unsigned int header_len;
+	unsigned int tcp_header_len;
+	unsigned int tcp_payload_len;
+	unsigned short mss;
+
+	unsigned short vlan_ctag;
+
+	u64 rx_tstamp;
+
+	u32 rss_hash;
+	enum pkt_hash_types rss_hash_type;
+};
+
+struct xlgmac_desc_data {
+	/* dma_desc: Virtual address of descriptor
+	 *  dma_desc_addr: DMA address of descriptor
+	 */
+	struct xlgmac_dma_desc *dma_desc;
+	dma_addr_t dma_desc_addr;
+
+	/* skb: Virtual address of SKB
+	 *  skb_dma: DMA address of SKB data
+	 *  skb_dma_len: Length of SKB DMA area
+	 */
+	struct sk_buff *skb;
+	dma_addr_t skb_dma;
+	unsigned int skb_dma_len;
+
+	/* Tx/Rx -related data */
+	struct xlgmac_tx_desc_data tx;
+	struct xlgmac_rx_desc_data rx;
+
+	unsigned int mapped_as_page;
+
+	/* Incomplete receive save location.  If the budget is exhausted
+	 * or the last descriptor (last normal descriptor or a following
+	 * context descriptor) has not been DMA'd yet the current state
+	 * of the receive processing needs to be saved.
+	 */
+	unsigned int state_saved;
+	struct {
+		struct sk_buff *skb;
+		unsigned int len;
+		unsigned int error;
+	} state;
+};
+
+struct xlgmac_ring {
+	/* Per packet related information */
+	struct xlgmac_pkt_info pkt_info;
+
+	/* Virtual/DMA addresses of DMA descriptor list and the total count */
+	struct xlgmac_dma_desc *dma_desc_head;
+	dma_addr_t dma_desc_head_addr;
+	unsigned int dma_desc_count;
+
+	/* Array of descriptor data corresponding the DMA descriptor
+	 * (always use the XLGMAC_GET_DESC_DATA macro to access this data)
+	 */
+	struct xlgmac_desc_data *desc_data_head;
+
+	/* Page allocation for RX buffers */
+	struct xlgmac_page_alloc rx_hdr_pa;
+	struct xlgmac_page_alloc rx_buf_pa;
+
+	/* Ring index values
+	 *  cur   - Tx: index of descriptor to be used for current transfer
+	 *          Rx: index of descriptor to check for packet availability
+	 *  dirty - Tx: index of descriptor to check for transfer complete
+	 *          Rx: index of descriptor to check for buffer reallocation
+	 */
+	unsigned int cur;
+	unsigned int dirty;
+
+	/* Coalesce frame count used for interrupt bit setting */
+	unsigned int coalesce_count;
+
+	union {
+		struct {
+			unsigned int xmit_more;
+			unsigned int queue_stopped;
+			unsigned short cur_mss;
+			unsigned short cur_vlan_ctag;
+		} tx;
+	};
+} ____cacheline_aligned;
+
+struct xlgmac_channel {
+	char name[16];
+
+	/* Address of private data area for device */
+	struct xlgmac_pdata *pdata;
+
+	/* Queue index and base address of queue's DMA registers */
+	unsigned int queue_index;
+	void __iomem *dma_regs;
+
+	/* Per channel interrupt irq number */
+	int dma_irq;
+	char dma_irq_name[IFNAMSIZ + 32];
+
+	/* Netdev related settings */
+	struct napi_struct napi;
+
+	unsigned int saved_ier;
+
+	unsigned int tx_timer_active;
+	struct timer_list tx_timer;
+
+	struct xlgmac_ring *tx_ring;
+	struct xlgmac_ring *rx_ring;
+} ____cacheline_aligned;
+
+struct xlgmac_desc_ops {
+	int (*alloc_channles_and_rings)(struct xlgmac_pdata *pdata);
+	void (*free_channels_and_rings)(struct xlgmac_pdata *pdata);
+	int (*map_tx_skb)(struct xlgmac_channel *channel,
+			  struct sk_buff *skb);
+	int (*map_rx_buffer)(struct xlgmac_pdata *pdata,
+			     struct xlgmac_ring *ring,
+			struct xlgmac_desc_data *desc_data);
+	void (*unmap_desc_data)(struct xlgmac_pdata *pdata,
+				struct xlgmac_desc_data *desc_data);
+	void (*tx_desc_init)(struct xlgmac_pdata *pdata);
+	void (*rx_desc_init)(struct xlgmac_pdata *pdata);
+};
+
+struct xlgmac_hw_ops {
+	int (*init)(struct xlgmac_pdata *pdata);
+	int (*exit)(struct xlgmac_pdata *pdata);
+
+	int (*tx_complete)(struct xlgmac_dma_desc *dma_desc);
+
+	void (*enable_tx)(struct xlgmac_pdata *pdata);
+	void (*disable_tx)(struct xlgmac_pdata *pdata);
+	void (*enable_rx)(struct xlgmac_pdata *pdata);
+	void (*disable_rx)(struct xlgmac_pdata *pdata);
+
+	int (*enable_int)(struct xlgmac_channel *channel,
+			  enum xlgmac_int int_id);
+	int (*disable_int)(struct xlgmac_channel *channel,
+			   enum xlgmac_int int_id);
+	void (*dev_xmit)(struct xlgmac_channel *channel);
+	int (*dev_read)(struct xlgmac_channel *channel);
+
+	int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr);
+	int (*config_rx_mode)(struct xlgmac_pdata *pdata);
+	int (*enable_rx_csum)(struct xlgmac_pdata *pdata);
+	int (*disable_rx_csum)(struct xlgmac_pdata *pdata);
+
+	/* For MII speed configuration */
+	int (*set_xlgmii_25000_speed)(struct xlgmac_pdata *pdata);
+	int (*set_xlgmii_40000_speed)(struct xlgmac_pdata *pdata);
+	int (*set_xlgmii_50000_speed)(struct xlgmac_pdata *pdata);
+	int (*set_xlgmii_100000_speed)(struct xlgmac_pdata *pdata);
+
+	/* For descriptor related operation */
+	void (*tx_desc_init)(struct xlgmac_channel *channel);
+	void (*rx_desc_init)(struct xlgmac_channel *channel);
+	void (*tx_desc_reset)(struct xlgmac_desc_data *desc_data);
+	void (*rx_desc_reset)(struct xlgmac_pdata *pdata,
+			      struct xlgmac_desc_data *desc_data,
+			unsigned int index);
+	int (*is_last_desc)(struct xlgmac_dma_desc *dma_desc);
+	int (*is_context_desc)(struct xlgmac_dma_desc *dma_desc);
+	void (*tx_start_xmit)(struct xlgmac_channel *channel,
+			      struct xlgmac_ring *ring);
+
+	/* For Flow Control */
+	int (*config_tx_flow_control)(struct xlgmac_pdata *pdata);
+	int (*config_rx_flow_control)(struct xlgmac_pdata *pdata);
+
+	/* For Vlan related config */
+	int (*enable_rx_vlan_stripping)(struct xlgmac_pdata *pdata);
+	int (*disable_rx_vlan_stripping)(struct xlgmac_pdata *pdata);
+	int (*enable_rx_vlan_filtering)(struct xlgmac_pdata *pdata);
+	int (*disable_rx_vlan_filtering)(struct xlgmac_pdata *pdata);
+	int (*update_vlan_hash_table)(struct xlgmac_pdata *pdata);
+
+	/* For RX coalescing */
+	int (*config_rx_coalesce)(struct xlgmac_pdata *pdata);
+	int (*config_tx_coalesce)(struct xlgmac_pdata *pdata);
+	unsigned int (*usec_to_riwt)(struct xlgmac_pdata *pdata,
+				     unsigned int usec);
+	unsigned int (*riwt_to_usec)(struct xlgmac_pdata *pdata,
+				     unsigned int riwt);
+
+	/* For RX and TX threshold config */
+	int (*config_rx_threshold)(struct xlgmac_pdata *pdata,
+				   unsigned int val);
+	int (*config_tx_threshold)(struct xlgmac_pdata *pdata,
+				   unsigned int val);
+
+	/* For RX and TX Store and Forward Mode config */
+	int (*config_rsf_mode)(struct xlgmac_pdata *pdata,
+			       unsigned int val);
+	int (*config_tsf_mode)(struct xlgmac_pdata *pdata,
+			       unsigned int val);
+
+	/* For TX DMA Operate on Second Frame config */
+	int (*config_osp_mode)(struct xlgmac_pdata *pdata);
+
+	/* For RX and TX PBL config */
+	int (*config_rx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*get_rx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*config_tx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*get_tx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*config_pblx8)(struct xlgmac_pdata *pdata);
+
+	/* For MMC statistics */
+	void (*rx_mmc_int)(struct xlgmac_pdata *pdata);
+	void (*tx_mmc_int)(struct xlgmac_pdata *pdata);
+	void (*read_mmc_stats)(struct xlgmac_pdata *pdata);
+
+	/* For Receive Side Scaling */
+	int (*enable_rss)(struct xlgmac_pdata *pdata);
+	int (*disable_rss)(struct xlgmac_pdata *pdata);
+	int (*set_rss_hash_key)(struct xlgmac_pdata *pdata,
+				const u8 *key);
+	int (*set_rss_lookup_table)(struct xlgmac_pdata *pdata,
+				    const u32 *table);
+};
+
+/* This structure contains flags that indicate what hardware features
+ * or configurations are present in the device.
+ */
+struct xlgmac_hw_features {
+	/* HW Version */
+	unsigned int version;
+
+	/* HW Feature Register0 */
+	unsigned int phyifsel;		/* PHY interface support */
+	unsigned int vlhash;		/* VLAN Hash Filter */
+	unsigned int sma;		/* SMA(MDIO) Interface */
+	unsigned int rwk;		/* PMT remote wake-up packet */
+	unsigned int mgk;		/* PMT magic packet */
+	unsigned int mmc;		/* RMON module */
+	unsigned int aoe;		/* ARP Offload */
+	unsigned int ts;		/* IEEE 1588-2008 Advanced Timestamp */
+	unsigned int eee;		/* Energy Efficient Ethernet */
+	unsigned int tx_coe;		/* Tx Checksum Offload */
+	unsigned int rx_coe;		/* Rx Checksum Offload */
+	unsigned int addn_mac;		/* Additional MAC Addresses */
+	unsigned int ts_src;		/* Timestamp Source */
+	unsigned int sa_vlan_ins;	/* Source Address or VLAN Insertion */
+
+	/* HW Feature Register1 */
+	unsigned int rx_fifo_size;	/* MTL Receive FIFO Size */
+	unsigned int tx_fifo_size;	/* MTL Transmit FIFO Size */
+	unsigned int adv_ts_hi;		/* Advance Timestamping High Word */
+	unsigned int dma_width;		/* DMA width */
+	unsigned int dcb;		/* DCB Feature */
+	unsigned int sph;		/* Split Header Feature */
+	unsigned int tso;		/* TCP Segmentation Offload */
+	unsigned int dma_debug;		/* DMA Debug Registers */
+	unsigned int rss;		/* Receive Side Scaling */
+	unsigned int tc_cnt;		/* Number of Traffic Classes */
+	unsigned int hash_table_size;	/* Hash Table Size */
+	unsigned int l3l4_filter_num;	/* Number of L3-L4 Filters */
+
+	/* HW Feature Register2 */
+	unsigned int rx_q_cnt;		/* Number of MTL Receive Queues */
+	unsigned int tx_q_cnt;		/* Number of MTL Transmit Queues */
+	unsigned int rx_ch_cnt;		/* Number of DMA Receive Channels */
+	unsigned int tx_ch_cnt;		/* Number of DMA Transmit Channels */
+	unsigned int pps_out_num;	/* Number of PPS outputs */
+	unsigned int aux_snap_num;	/* Number of Aux snapshot inputs */
+};
+
+struct xlgmac_resources {
+	void __iomem *addr;
+	int irq;
+};
+
+struct xlgmac_pdata {
+	struct net_device *netdev;
+	struct device *dev;
+
+	struct xlgmac_hw_ops hw_ops;
+	struct xlgmac_desc_ops desc_ops;
+
+	/* Device statistics */
+	struct xlgmac_stats stats;
+
+	u32 msg_enable;
+
+	/* MAC registers base */
+	void __iomem *mac_regs;
+
+	/* Hardware features of the device */
+	struct xlgmac_hw_features hw_feat;
+
+	struct work_struct restart_work;
+
+	/* Rings for Tx/Rx on a DMA channel */
+	struct xlgmac_channel *channel_head;
+	unsigned int channel_count;
+	unsigned int tx_ring_count;
+	unsigned int rx_ring_count;
+	unsigned int tx_desc_count;
+	unsigned int rx_desc_count;
+	unsigned int tx_q_count;
+	unsigned int rx_q_count;
+
+	/* Tx/Rx common settings */
+	unsigned int pblx8;
+
+	/* Tx settings */
+	unsigned int tx_sf_mode;
+	unsigned int tx_threshold;
+	unsigned int tx_pbl;
+	unsigned int tx_osp_mode;
+
+	/* Rx settings */
+	unsigned int rx_sf_mode;
+	unsigned int rx_threshold;
+	unsigned int rx_pbl;
+
+	/* Tx coalescing settings */
+	unsigned int tx_usecs;
+	unsigned int tx_frames;
+
+	/* Rx coalescing settings */
+	unsigned int rx_riwt;
+	unsigned int rx_usecs;
+	unsigned int rx_frames;
+
+	/* Current Rx buffer size */
+	unsigned int rx_buf_size;
+
+	/* Flow control settings */
+	unsigned int tx_pause;
+	unsigned int rx_pause;
+
+	/* Device interrupt number */
+	int dev_irq;
+	unsigned int per_channel_irq;
+	int channel_irq[XLGMAC_MAX_DMA_CHANNELS];
+
+	/* Netdev related settings */
+	unsigned char mac_addr[ETH_ALEN];
+	netdev_features_t netdev_features;
+	struct napi_struct napi;
+
+	/* Filtering support */
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+
+	/* Device clocks */
+	unsigned long sysclk_rate;
+
+	/* RSS addressing mutex */
+	struct mutex rss_mutex;
+
+	/* Receive Side Scaling settings */
+	u8 rss_key[XLGMAC_RSS_HASH_KEY_SIZE];
+	u32 rss_table[XLGMAC_RSS_MAX_TABLE_SIZE];
+	u32 rss_options;
+
+	int phy_speed;
+
+	char drv_name[32];
+	char drv_ver[32];
+};
+
+void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops);
+void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops);
+const struct net_device_ops *xlgmac_get_netdev_ops(void);
+const struct ethtool_ops *xlgmac_get_ethtool_ops(void);
+void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx,
+			 unsigned int count,
+			 unsigned int flag);
+void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx);
+void xlgmac_print_pkt(struct net_device *netdev,
+		      struct sk_buff *skb, bool tx_rx);
+void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata);
+void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata);
+int xlgmac_drv_probe(struct device *dev,
+		     struct xlgmac_resources *res);
+int xlgmac_drv_remove(struct device *dev);
+
+/* For debug prints */
+#ifdef XLGMAC_DEBUG
+#define XLGMAC_PR(fmt, args...) \
+	pr_alert("[%s,%d]:" fmt, __func__, __LINE__, ## args)
+#else
+#define XLGMAC_PR(x...)		do { } while (0)
+#endif
+
+#endif /* __DWC_XLGMAC_H__ */
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index f864fd0663db..711fbbbc4b1f 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2124,33 +2124,26 @@ static const char
 };
 
 /*
- * bdx_get_settings - get device-specific settings
+ * bdx_get_link_ksettings - get device-specific settings
  * @netdev
  * @ecmd
  */
-static int bdx_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
-{
-	u32 rdintcm;
-	u32 tdintcm;
-	struct bdx_priv *priv = netdev_priv(netdev);
-
-	rdintcm = priv->rdintcm;
-	tdintcm = priv->tdintcm;
-
-	ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-	ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-	ethtool_cmd_speed_set(ecmd, SPEED_10000);
-	ecmd->duplex = DUPLEX_FULL;
-	ecmd->port = PORT_FIBRE;
-	ecmd->transceiver = XCVR_EXTERNAL;	/* what does it mean? */
-	ecmd->autoneg = AUTONEG_DISABLE;
-
-	/* PCK_TH measures in multiples of FIFO bytes
-	   We translate to packets */
-	ecmd->maxtxpkt =
-	    ((GET_PCK_TH(tdintcm) * PCK_TH_MULT) / BDX_TXF_DESC_SZ);
-	ecmd->maxrxpkt =
-	    ((GET_PCK_TH(rdintcm) * PCK_TH_MULT) / sizeof(struct rxf_desc));
+static int bdx_get_link_ksettings(struct net_device *netdev,
+				  struct ethtool_link_ksettings *ecmd)
+{
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising, FIBRE);
+
+	ecmd->base.speed = SPEED_10000;
+	ecmd->base.duplex = DUPLEX_FULL;
+	ecmd->base.port = PORT_FIBRE;
+	ecmd->base.autoneg = AUTONEG_DISABLE;
 
 	return 0;
 }
@@ -2384,7 +2377,6 @@ static void bdx_get_ethtool_stats(struct net_device *netdev,
 static void bdx_set_ethtool_ops(struct net_device *netdev)
 {
 	static const struct ethtool_ops bdx_ethtool_ops = {
-		.get_settings = bdx_get_settings,
 		.get_drvinfo = bdx_get_drvinfo,
 		.get_link = ethtool_op_get_link,
 		.get_coalesce = bdx_get_coalesce,
@@ -2394,6 +2386,7 @@ static void bdx_set_ethtool_ops(struct net_device *netdev)
 		.get_strings = bdx_get_strings,
 		.get_sset_count = bdx_get_sset_count,
 		.get_ethtool_stats = bdx_get_ethtool_stats,
+		.get_link_ksettings = bdx_get_link_ksettings,
 	};
 
 	netdev->ethtool_ops = &bdx_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 296c8efd0038..48a541eb0af2 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -74,15 +74,23 @@ config TI_CPSW
 	  will be called cpsw.
 
 config TI_CPTS
-	tristate "TI Common Platform Time Sync (CPTS) Support"
+	bool "TI Common Platform Time Sync (CPTS) Support"
 	depends on TI_CPSW || TI_KEYSTONE_NETCP
-	imply PTP_1588_CLOCK
+	depends on POSIX_TIMERS
 	---help---
 	  This driver supports the Common Platform Time Sync unit of
 	  the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem.
 	  The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the
 	  driver offers a PTP Hardware Clock.
 
+config TI_CPTS_MOD
+	tristate
+	depends on TI_CPTS
+	default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y
+	select NET_PTP_CLASSIFY
+	imply PTP_1588_CLOCK
+	default m
+
 config TI_KEYSTONE_NETCP
 	tristate "TI Keystone NETCP Core Support"
 	select TI_CPSW_ALE
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 1e7c10bf8713..10e6b0ce51ba 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o
 obj-$(CONFIG_TI_DAVINCI_CPDMA) += davinci_cpdma.o
 obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o
 obj-$(CONFIG_TI_CPSW_ALE) += cpsw_ale.o
-obj-$(CONFIG_TI_CPTS) += cpts.o
+obj-$(CONFIG_TI_CPTS_MOD) += cpts.o
 obj-$(CONFIG_TI_CPSW) += ti_cpsw.o
 ti_cpsw-y := cpsw.o
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 9f3d9c67e3fe..fa674a8bda0c 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1267,6 +1267,7 @@ static void soft_reset_slave(struct cpsw_slave *slave)
 static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 {
 	u32 slave_port;
+	struct phy_device *phy;
 	struct cpsw_common *cpsw = priv->cpsw;
 
 	soft_reset_slave(slave);
@@ -1300,27 +1301,28 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 				   1 << slave_port, 0, 0, ALE_MCAST_FWD_2);
 
 	if (slave->data->phy_node) {
-		slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node,
+		phy = of_phy_connect(priv->ndev, slave->data->phy_node,
 				 &cpsw_adjust_link, 0, slave->data->phy_if);
-		if (!slave->phy) {
+		if (!phy) {
 			dev_err(priv->dev, "phy \"%s\" not found on slave %d\n",
 				slave->data->phy_node->full_name,
 				slave->slave_num);
 			return;
 		}
 	} else {
-		slave->phy = phy_connect(priv->ndev, slave->data->phy_id,
+		phy = phy_connect(priv->ndev, slave->data->phy_id,
 				 &cpsw_adjust_link, slave->data->phy_if);
-		if (IS_ERR(slave->phy)) {
+		if (IS_ERR(phy)) {
 			dev_err(priv->dev,
 				"phy \"%s\" not found on slave %d, err %ld\n",
 				slave->data->phy_id, slave->slave_num,
-				PTR_ERR(slave->phy));
-			slave->phy = NULL;
+				PTR_ERR(phy));
 			return;
 		}
 	}
 
+	slave->phy = phy;
+
 	phy_attached_info(slave->phy);
 
 	phy_start(slave->phy);
@@ -1817,6 +1819,8 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev)
 	}
 
 	cpsw_intr_enable(cpsw);
+	netif_trans_update(ndev);
+	netif_tx_wake_all_queues(ndev);
 }
 
 static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 7c7ae0890e90..729a7da90b5b 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1134,7 +1134,6 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp)
 		u32 buf_len = skb_frag_size(frag);
 		dma_addr_t desc_dma;
 		u32 desc_dma_32;
-		u32 pkt_info;
 
 		dma_addr = dma_map_page(dev, page, page_offset, buf_len,
 					DMA_TO_DEVICE);
@@ -1151,9 +1150,6 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp)
 		}
 
 		desc_dma = knav_pool_desc_virt_to_dma(netcp->tx_pool, ndesc);
-		pkt_info =
-			(netcp->tx_compl_qid & KNAV_DMA_DESC_RETQ_MASK) <<
-				KNAV_DMA_DESC_RETQ_SHIFT;
 		set_pkt_info(dma_addr, buf_len, 0, ndesc);
 		desc_dma_32 = (u32)desc_dma;
 		set_words(&desc_dma_32, 1, &pdesc->next_desc);
@@ -1882,6 +1878,7 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
 static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 			  struct tc_to_netdev *tc)
 {
+	u8 num_tc;
 	int i;
 
 	/* setup tc must be called under rtnl lock */
@@ -1890,15 +1887,18 @@ static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_tc = tc->mqprio->num_tc;
+
 	/* Sanity-check the number of traffic classes requested */
 	if ((dev->real_num_tx_queues <= 1) ||
-	    (dev->real_num_tx_queues < tc->tc))
+	    (dev->real_num_tx_queues < num_tc))
 		return -EINVAL;
 
 	/* Configure traffic class to queue mappings */
-	if (tc->tc) {
-		netdev_set_num_tc(dev, tc->tc);
-		for (i = 0; i < tc->tc; i++)
+	if (num_tc) {
+		netdev_set_num_tc(dev, num_tc);
+		for (i = 0; i < num_tc; i++)
 			netdev_set_tc_queue(dev, i, 1, i);
 	} else {
 		netdev_reset_tc(dev);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index eece3e2eec14..897176fc5043 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3048,8 +3048,7 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev,
 	for_each_child_of_node(node, port) {
 		slave = devm_kzalloc(dev, sizeof(*slave), GFP_KERNEL);
 		if (!slave) {
-			dev_err(dev,
-				"memomry alloc failed for secondary port(%s), skipping...\n",
+			dev_err(dev, "memory alloc failed for secondary port(%s), skipping...\n",
 				port->name);
 			continue;
 		}
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index 72013314bba8..fa6a06571187 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1206,61 +1206,68 @@ void gelic_net_get_drvinfo(struct net_device *netdev,
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
-static int gelic_ether_get_settings(struct net_device *netdev,
-				    struct ethtool_cmd *cmd)
+static int gelic_ether_get_link_ksettings(struct net_device *netdev,
+					  struct ethtool_link_ksettings *cmd)
 {
 	struct gelic_card *card = netdev_card(netdev);
+	u32 supported, advertising;
 
 	gelic_card_get_ether_port_status(card, 0);
 
 	if (card->ether_port_status & GELIC_LV1_ETHER_FULL_DUPLEX)
-		cmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 	else
-		cmd->duplex = DUPLEX_HALF;
+		cmd->base.duplex = DUPLEX_HALF;
 
 	switch (card->ether_port_status & GELIC_LV1_ETHER_SPEED_MASK) {
 	case GELIC_LV1_ETHER_SPEED_10:
-		ethtool_cmd_speed_set(cmd, SPEED_10);
+		cmd->base.speed = SPEED_10;
 		break;
 	case GELIC_LV1_ETHER_SPEED_100:
-		ethtool_cmd_speed_set(cmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 		break;
 	case GELIC_LV1_ETHER_SPEED_1000:
-		ethtool_cmd_speed_set(cmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 		break;
 	default:
 		pr_info("%s: speed unknown\n", __func__);
-		ethtool_cmd_speed_set(cmd, SPEED_10);
+		cmd->base.speed = SPEED_10;
 		break;
 	}
 
-	cmd->supported = SUPPORTED_TP | SUPPORTED_Autoneg |
+	supported = SUPPORTED_TP | SUPPORTED_Autoneg |
 			SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
 			SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
 			SUPPORTED_1000baseT_Full;
-	cmd->advertising = cmd->supported;
+	advertising = supported;
 	if (card->link_mode & GELIC_LV1_ETHER_AUTO_NEG) {
-		cmd->autoneg = AUTONEG_ENABLE;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
-		cmd->advertising &= ~ADVERTISED_Autoneg;
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		advertising &= ~ADVERTISED_Autoneg;
 	}
-	cmd->port = PORT_TP;
+	cmd->base.port = PORT_TP;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int gelic_ether_set_settings(struct net_device *netdev,
-				    struct ethtool_cmd *cmd)
+static int
+gelic_ether_set_link_ksettings(struct net_device *netdev,
+			       const struct ethtool_link_ksettings *cmd)
 {
 	struct gelic_card *card = netdev_card(netdev);
 	u64 mode;
 	int ret;
 
-	if (cmd->autoneg == AUTONEG_ENABLE) {
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		mode = GELIC_LV1_ETHER_AUTO_NEG;
 	} else {
-		switch (cmd->speed) {
+		switch (cmd->base.speed) {
 		case SPEED_10:
 			mode = GELIC_LV1_ETHER_SPEED_10;
 			break;
@@ -1273,9 +1280,9 @@ static int gelic_ether_set_settings(struct net_device *netdev,
 		default:
 			return -EINVAL;
 		}
-		if (cmd->duplex == DUPLEX_FULL)
+		if (cmd->base.duplex == DUPLEX_FULL) {
 			mode |= GELIC_LV1_ETHER_FULL_DUPLEX;
-		else if (cmd->speed == SPEED_1000) {
+		} else if (cmd->base.speed == SPEED_1000) {
 			pr_info("1000 half duplex is not supported.\n");
 			return -EINVAL;
 		}
@@ -1370,11 +1377,11 @@ done:
 
 static const struct ethtool_ops gelic_ether_ethtool_ops = {
 	.get_drvinfo	= gelic_net_get_drvinfo,
-	.get_settings	= gelic_ether_get_settings,
-	.set_settings	= gelic_ether_set_settings,
 	.get_link	= ethtool_op_get_link,
 	.get_wol	= gelic_net_get_wol,
 	.set_wol	= gelic_net_set_wol,
+	.get_link_ksettings = gelic_ether_get_link_ksettings,
+	.set_link_ksettings = gelic_ether_set_link_ksettings,
 };
 
 /**
diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
index ffe519382e11..16bd036d0682 100644
--- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c
+++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
@@ -47,19 +47,23 @@ static struct {
 };
 
 static int
-spider_net_ethtool_get_settings(struct net_device *netdev,
-			       struct ethtool_cmd *cmd)
+spider_net_ethtool_get_link_ksettings(struct net_device *netdev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct spider_net_card *card;
 	card = netdev_priv(netdev);
 
-	cmd->supported   = (SUPPORTED_1000baseT_Full |
-			     SUPPORTED_FIBRE);
-	cmd->advertising = (ADVERTISED_1000baseT_Full |
-			     ADVERTISED_FIBRE);
-	cmd->port = PORT_FIBRE;
-	ethtool_cmd_speed_set(cmd, card->phy.speed);
-	cmd->duplex = DUPLEX_FULL;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+
+	cmd->base.port = PORT_FIBRE;
+	cmd->base.speed = card->phy.speed;
+	cmd->base.duplex = DUPLEX_FULL;
 
 	return 0;
 }
@@ -166,7 +170,6 @@ static void spider_net_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 const struct ethtool_ops spider_net_ethtool_ops = {
-	.get_settings		= spider_net_ethtool_get_settings,
 	.get_drvinfo		= spider_net_ethtool_get_drvinfo,
 	.get_wol		= spider_net_ethtool_get_wol,
 	.get_msglevel		= spider_net_ethtool_get_msglevel,
@@ -177,5 +180,6 @@ const struct ethtool_ops spider_net_ethtool_ops = {
 	.get_strings		= spider_net_get_strings,
 	.get_sset_count		= spider_net_get_sset_count,
 	.get_ethtool_stats	= spider_net_get_ethtool_stats,
+	.get_link_ksettings	= spider_net_ethtool_get_link_ksettings,
 };
 
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index a45f98fa4aa7..3dadee1080b9 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -1017,8 +1017,8 @@ tc35815_free_queues(struct net_device *dev)
 			BUG_ON(lp->tx_skbs[i].skb != skb);
 #endif
 			if (skb) {
-				dev_kfree_skb(skb);
 				pci_unmap_single(lp->pci_dev, lp->tx_skbs[i].skb_dma, skb->len, PCI_DMA_TODEVICE);
+				dev_kfree_skb(skb);
 				lp->tx_skbs[i].skb = NULL;
 				lp->tx_skbs[i].skb_dma = 0;
 			}
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index c5583991da4a..5ac6eaa9e785 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1499,27 +1499,29 @@ static void tsi108_init_mac(struct net_device *dev)
 	TSI_WRITE(TSI108_EC_INTMASK, ~0);
 }
 
-static int tsi108_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tsi108_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct tsi108_prv_data *data = netdev_priv(dev);
 	unsigned long flags;
 	int rc;
 
 	spin_lock_irqsave(&data->txlock, flags);
-	rc = mii_ethtool_gset(&data->mii_if, cmd);
+	rc = mii_ethtool_get_link_ksettings(&data->mii_if, cmd);
 	spin_unlock_irqrestore(&data->txlock, flags);
 
 	return rc;
 }
 
-static int tsi108_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tsi108_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct tsi108_prv_data *data = netdev_priv(dev);
 	unsigned long flags;
 	int rc;
 
 	spin_lock_irqsave(&data->txlock, flags);
-	rc = mii_ethtool_sset(&data->mii_if, cmd);
+	rc = mii_ethtool_set_link_ksettings(&data->mii_if, cmd);
 	spin_unlock_irqrestore(&data->txlock, flags);
 
 	return rc;
@@ -1535,8 +1537,8 @@ static int tsi108_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 static const struct ethtool_ops tsi108_ethtool_ops = {
 	.get_link 	= ethtool_op_get_link,
-	.get_settings	= tsi108_get_settings,
-	.set_settings	= tsi108_set_settings,
+	.get_link_ksettings	= tsi108_get_link_ksettings,
+	.set_link_ksettings	= tsi108_set_link_ksettings,
 };
 
 static const struct net_device_ops tsi108_netdev_ops = {
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index c068c58428f7..4cf41f779d0e 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -2303,25 +2303,27 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i
 	strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info));
 }
 
-static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	int rc;
 
 	mutex_lock(&rp->task_lock);
-	rc = mii_ethtool_gset(&rp->mii_if, cmd);
+	rc = mii_ethtool_get_link_ksettings(&rp->mii_if, cmd);
 	mutex_unlock(&rp->task_lock);
 
 	return rc;
 }
 
-static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	int rc;
 
 	mutex_lock(&rp->task_lock);
-	rc = mii_ethtool_sset(&rp->mii_if, cmd);
+	rc = mii_ethtool_set_link_ksettings(&rp->mii_if, cmd);
 	rhine_set_carrier(&rp->mii_if);
 	mutex_unlock(&rp->task_lock);
 
@@ -2391,14 +2393,14 @@ static int rhine_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 static const struct ethtool_ops netdev_ethtool_ops = {
 	.get_drvinfo		= netdev_get_drvinfo,
-	.get_settings		= netdev_get_settings,
-	.set_settings		= netdev_set_settings,
 	.nway_reset		= netdev_nway_reset,
 	.get_link		= netdev_get_link,
 	.get_msglevel		= netdev_get_msglevel,
 	.set_msglevel		= netdev_set_msglevel,
 	.get_wol		= rhine_get_wol,
 	.set_wol		= rhine_set_wol,
+	.get_link_ksettings	= netdev_get_link_ksettings,
+	.set_link_ksettings	= netdev_set_link_ksettings,
 };
 
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index d088788b27a7..ef9538ee53d0 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -3291,15 +3291,17 @@ static void velocity_ethtool_down(struct net_device *dev)
 		velocity_set_power_state(vptr, PCI_D3hot);
 }
 
-static int velocity_get_settings(struct net_device *dev,
-				 struct ethtool_cmd *cmd)
+static int velocity_get_link_ksettings(struct net_device *dev,
+				       struct ethtool_link_ksettings *cmd)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
 	struct mac_regs __iomem *regs = vptr->mac_regs;
 	u32 status;
+	u32 supported, advertising;
+
 	status = check_connection_type(vptr->mac_regs);
 
-	cmd->supported = SUPPORTED_TP |
+	supported = SUPPORTED_TP |
 			SUPPORTED_Autoneg |
 			SUPPORTED_10baseT_Half |
 			SUPPORTED_10baseT_Full |
@@ -3308,9 +3310,9 @@ static int velocity_get_settings(struct net_device *dev,
 			SUPPORTED_1000baseT_Half |
 			SUPPORTED_1000baseT_Full;
 
-	cmd->advertising = ADVERTISED_TP | ADVERTISED_Autoneg;
+	advertising = ADVERTISED_TP | ADVERTISED_Autoneg;
 	if (vptr->options.spd_dpx == SPD_DPX_AUTO) {
-		cmd->advertising |=
+		advertising |=
 			ADVERTISED_10baseT_Half |
 			ADVERTISED_10baseT_Full |
 			ADVERTISED_100baseT_Half |
@@ -3320,19 +3322,19 @@ static int velocity_get_settings(struct net_device *dev,
 	} else {
 		switch (vptr->options.spd_dpx) {
 		case SPD_DPX_1000_FULL:
-			cmd->advertising |= ADVERTISED_1000baseT_Full;
+			advertising |= ADVERTISED_1000baseT_Full;
 			break;
 		case SPD_DPX_100_HALF:
-			cmd->advertising |= ADVERTISED_100baseT_Half;
+			advertising |= ADVERTISED_100baseT_Half;
 			break;
 		case SPD_DPX_100_FULL:
-			cmd->advertising |= ADVERTISED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 			break;
 		case SPD_DPX_10_HALF:
-			cmd->advertising |= ADVERTISED_10baseT_Half;
+			advertising |= ADVERTISED_10baseT_Half;
 			break;
 		case SPD_DPX_10_FULL:
-			cmd->advertising |= ADVERTISED_10baseT_Full;
+			advertising |= ADVERTISED_10baseT_Full;
 			break;
 		default:
 			break;
@@ -3340,30 +3342,35 @@ static int velocity_get_settings(struct net_device *dev,
 	}
 
 	if (status & VELOCITY_SPEED_1000)
-		ethtool_cmd_speed_set(cmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 	else if (status & VELOCITY_SPEED_100)
-		ethtool_cmd_speed_set(cmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 	else
-		ethtool_cmd_speed_set(cmd, SPEED_10);
+		cmd->base.speed = SPEED_10;
 
-	cmd->autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
-	cmd->port = PORT_TP;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->phy_address = readb(&regs->MIIADR) & 0x1F;
+	cmd->base.autoneg = (status & VELOCITY_AUTONEG_ENABLE) ?
+		AUTONEG_ENABLE : AUTONEG_DISABLE;
+	cmd->base.port = PORT_TP;
+	cmd->base.phy_address = readb(&regs->MIIADR) & 0x1F;
 
 	if (status & VELOCITY_DUPLEX_FULL)
-		cmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 	else
-		cmd->duplex = DUPLEX_HALF;
+		cmd->base.duplex = DUPLEX_HALF;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int velocity_set_settings(struct net_device *dev,
-				 struct ethtool_cmd *cmd)
+static int velocity_set_link_ksettings(struct net_device *dev,
+				       const struct ethtool_link_ksettings *cmd)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
 	u32 curr_status;
 	u32 new_status = 0;
 	int ret = 0;
@@ -3371,11 +3378,12 @@ static int velocity_set_settings(struct net_device *dev,
 	curr_status = check_connection_type(vptr->mac_regs);
 	curr_status &= (~VELOCITY_LINK_FAIL);
 
-	new_status |= ((cmd->autoneg) ? VELOCITY_AUTONEG_ENABLE : 0);
+	new_status |= ((cmd->base.autoneg) ? VELOCITY_AUTONEG_ENABLE : 0);
 	new_status |= ((speed == SPEED_1000) ? VELOCITY_SPEED_1000 : 0);
 	new_status |= ((speed == SPEED_100) ? VELOCITY_SPEED_100 : 0);
 	new_status |= ((speed == SPEED_10) ? VELOCITY_SPEED_10 : 0);
-	new_status |= ((cmd->duplex == DUPLEX_FULL) ? VELOCITY_DUPLEX_FULL : 0);
+	new_status |= ((cmd->base.duplex == DUPLEX_FULL) ?
+		       VELOCITY_DUPLEX_FULL : 0);
 
 	if ((new_status & VELOCITY_AUTONEG_ENABLE) &&
 	    (new_status != (curr_status | VELOCITY_AUTONEG_ENABLE))) {
@@ -3644,8 +3652,6 @@ static void velocity_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops velocity_ethtool_ops = {
-	.get_settings		= velocity_get_settings,
-	.set_settings		= velocity_set_settings,
 	.get_drvinfo		= velocity_get_drvinfo,
 	.get_wol		= velocity_ethtool_get_wol,
 	.set_wol		= velocity_ethtool_set_wol,
@@ -3658,7 +3664,9 @@ static const struct ethtool_ops velocity_ethtool_ops = {
 	.get_coalesce		= velocity_get_coalesce,
 	.set_coalesce		= velocity_set_coalesce,
 	.begin			= velocity_ethtool_up,
-	.complete		= velocity_ethtool_down
+	.complete		= velocity_ethtool_down,
+	.get_link_ksettings	= velocity_get_link_ksettings,
+	.set_link_ksettings	= velocity_set_link_ksettings,
 };
 
 #if defined(CONFIG_PM) && defined(CONFIG_INET)
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index f90267f0519f..2bdfb39215e9 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -1152,7 +1152,8 @@ int w5100_probe(struct device *dev, const struct w5100_ops *ops,
 	if (err < 0)
 		goto err_register;
 
-	priv->xfer_wq = alloc_workqueue(netdev_name(ndev), WQ_MEM_RECLAIM, 0);
+	priv->xfer_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+					netdev_name(ndev));
 	if (!priv->xfer_wq) {
 		err = -ENOMEM;
 		goto err_wq;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index b96e96919e31..33c595f4691d 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -301,7 +301,7 @@ static void axienet_set_mac_address(struct net_device *ndev,
 	if (address)
 		memcpy(ndev->dev_addr, address, ETH_ALEN);
 	if (!is_valid_ether_addr(ndev->dev_addr))
-		eth_random_addr(ndev->dev_addr);
+		eth_hw_addr_random(ndev);
 
 	/* Set up unicast MAC address filter set its mac address */
 	axienet_iow(lp, XAE_UAW0_OFFSET,
diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c
index 6575f880f1be..7d101714c2ef 100644
--- a/drivers/net/fjes/fjes_ethtool.c
+++ b/drivers/net/fjes/fjes_ethtool.c
@@ -175,16 +175,15 @@ static void fjes_get_drvinfo(struct net_device *netdev,
 		 "platform:%s", plat_dev->name);
 }
 
-static int fjes_get_settings(struct net_device *netdev,
-			     struct ethtool_cmd *ecmd)
+static int fjes_get_link_ksettings(struct net_device *netdev,
+				   struct ethtool_link_ksettings *ecmd)
 {
-	ecmd->supported = 0;
-	ecmd->advertising = 0;
-	ecmd->duplex = DUPLEX_FULL;
-	ecmd->autoneg = AUTONEG_DISABLE;
-	ecmd->transceiver = XCVR_DUMMY1;
-	ecmd->port = PORT_NONE;
-	ethtool_cmd_speed_set(ecmd, 20000);	/* 20Gb/s */
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ecmd->base.duplex = DUPLEX_FULL;
+	ecmd->base.autoneg = AUTONEG_DISABLE;
+	ecmd->base.port = PORT_NONE;
+	ecmd->base.speed = 20000;	/* 20Gb/s */
 
 	return 0;
 }
@@ -296,7 +295,6 @@ static int fjes_get_dump_data(struct net_device *netdev,
 }
 
 static const struct ethtool_ops fjes_ethtool_ops = {
-		.get_settings		= fjes_get_settings,
 		.get_drvinfo		= fjes_get_drvinfo,
 		.get_ethtool_stats = fjes_get_ethtool_stats,
 		.get_strings      = fjes_get_strings,
@@ -306,6 +304,7 @@ static const struct ethtool_ops fjes_ethtool_ops = {
 		.set_dump		= fjes_set_dump,
 		.get_dump_flag		= fjes_get_dump_flag,
 		.get_dump_data		= fjes_get_dump_data,
+		.get_link_ksettings	= fjes_get_link_ksettings,
 };
 
 void fjes_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index b75d9cdcfb0c..ae48c809bac9 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -45,6 +45,8 @@ MODULE_DESCRIPTION("FUJITSU Extended Socket Network Device Driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
+#define ACPI_MOTHERBOARD_RESOURCE_HID "PNP0C02"
+
 static int fjes_request_irq(struct fjes_adapter *);
 static void fjes_free_irq(struct fjes_adapter *);
 
@@ -78,7 +80,7 @@ static void fjes_rx_irq(struct fjes_adapter *, int);
 static int fjes_poll(struct napi_struct *, int);
 
 static const struct acpi_device_id fjes_acpi_ids[] = {
-	{"PNP0C02", 0},
+	{ACPI_MOTHERBOARD_RESOURCE_HID, 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, fjes_acpi_ids);
@@ -115,18 +117,17 @@ static struct resource fjes_resource[] = {
 	},
 };
 
-static int fjes_acpi_add(struct acpi_device *device)
+static bool is_extended_socket_device(struct acpi_device *device)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
 	char str_buf[sizeof(FJES_ACPI_SYMBOL) + 1];
-	struct platform_device *plat_dev;
 	union acpi_object *str;
 	acpi_status status;
 	int result;
 
 	status = acpi_evaluate_object(device->handle, "_STR", NULL, &buffer);
 	if (ACPI_FAILURE(status))
-		return -ENODEV;
+		return false;
 
 	str = buffer.pointer;
 	result = utf16s_to_utf8s((wchar_t *)str->string.pointer,
@@ -136,10 +137,42 @@ static int fjes_acpi_add(struct acpi_device *device)
 
 	if (strncmp(FJES_ACPI_SYMBOL, str_buf, strlen(FJES_ACPI_SYMBOL)) != 0) {
 		kfree(buffer.pointer);
-		return -ENODEV;
+		return false;
 	}
 	kfree(buffer.pointer);
 
+	return true;
+}
+
+static int acpi_check_extended_socket_status(struct acpi_device *device)
+{
+	unsigned long long sta;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(device->handle, "_STA", NULL, &sta);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	if (!((sta & ACPI_STA_DEVICE_PRESENT) &&
+	      (sta & ACPI_STA_DEVICE_ENABLED) &&
+	      (sta & ACPI_STA_DEVICE_UI) &&
+	      (sta & ACPI_STA_DEVICE_FUNCTIONING)))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int fjes_acpi_add(struct acpi_device *device)
+{
+	struct platform_device *plat_dev;
+	acpi_status status;
+
+	if (!is_extended_socket_device(device))
+		return -ENODEV;
+
+	if (acpi_check_extended_socket_status(device))
+		return -ENODEV;
+
 	status = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
 				     fjes_get_acpi_resource, fjes_resource);
 	if (ACPI_FAILURE(status))
@@ -1316,7 +1349,7 @@ static void fjes_netdev_setup(struct net_device *netdev)
 	netdev->min_mtu = fjes_support_mtu[0];
 	netdev->max_mtu = fjes_support_mtu[3];
 	netdev->flags |= IFF_BROADCAST;
-	netdev->features |= NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_FILTER;
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 }
 
 static void fjes_irq_watch_task(struct work_struct *work)
@@ -1473,11 +1506,44 @@ static void fjes_watch_unshare_task(struct work_struct *work)
 	}
 }
 
+static acpi_status
+acpi_find_extended_socket_device(acpi_handle obj_handle, u32 level,
+				 void *context, void **return_value)
+{
+	struct acpi_device *device;
+	bool *found = context;
+	int result;
+
+	result = acpi_bus_get_device(obj_handle, &device);
+	if (result)
+		return AE_OK;
+
+	if (strcmp(acpi_device_hid(device), ACPI_MOTHERBOARD_RESOURCE_HID))
+		return AE_OK;
+
+	if (!is_extended_socket_device(device))
+		return AE_OK;
+
+	if (acpi_check_extended_socket_status(device))
+		return AE_OK;
+
+	*found = true;
+	return AE_CTRL_TERMINATE;
+}
+
 /* fjes_init_module - Driver Registration Routine */
 static int __init fjes_init_module(void)
 {
+	bool found = false;
 	int result;
 
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
+			    acpi_find_extended_socket_device, NULL, &found,
+			    NULL);
+
+	if (!found)
+		return -ENODEV;
+
 	pr_info("%s - version %s - %s\n",
 		fjes_driver_string, fjes_driver_version, fjes_copyright);
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 7074b40ebd7f..dec5d563ab19 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1244,7 +1244,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 		metadata = true;
 
 	if (data[IFLA_GENEVE_UDP_CSUM] &&
-	    !nla_get_u8(data[IFLA_GENEVE_UDP_CSUM]))
+	    nla_get_u8(data[IFLA_GENEVE_UDP_CSUM]))
 		info.key.tun_flags |= TUNNEL_CSUM;
 
 	if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX] &&
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 89698741682f..4fea1b3dfbb4 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -56,7 +56,10 @@ struct pdp_ctx {
 	u16			af;
 
 	struct in_addr		ms_addr_ip4;
-	struct in_addr		sgsn_addr_ip4;
+	struct in_addr		peer_addr_ip4;
+
+	struct sock		*sk;
+	struct net_device       *dev;
 
 	atomic_t		tx_seq;
 	struct rcu_head		rcu_head;
@@ -66,11 +69,12 @@ struct pdp_ctx {
 struct gtp_dev {
 	struct list_head	list;
 
-	struct socket		*sock0;
-	struct socket		*sock1u;
+	struct sock		*sk0;
+	struct sock		*sk1u;
 
 	struct net_device	*dev;
 
+	unsigned int		role;
 	unsigned int		hash_size;
 	struct hlist_head	*tid_hash;
 	struct hlist_head	*addr_hash;
@@ -84,6 +88,8 @@ struct gtp_net {
 
 static u32 gtp_h_initval;
 
+static void pdp_context_delete(struct pdp_ctx *pctx);
+
 static inline u32 gtp0_hashfn(u64 tid)
 {
 	u32 *tid32 = (u32 *) &tid;
@@ -149,8 +155,8 @@ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
 	return NULL;
 }
 
-static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
-				  unsigned int hdrlen)
+static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
+				  unsigned int hdrlen, unsigned int role)
 {
 	struct iphdr *iph;
 
@@ -159,25 +165,62 @@ static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
 
 	iph = (struct iphdr *)(skb->data + hdrlen);
 
-	return iph->saddr == pctx->ms_addr_ip4.s_addr;
+	if (role == GTP_ROLE_SGSN)
+		return iph->daddr == pctx->ms_addr_ip4.s_addr;
+	else
+		return iph->saddr == pctx->ms_addr_ip4.s_addr;
 }
 
-/* Check if the inner IP source address in this packet is assigned to any
+/* Check if the inner IP address in this packet is assigned to any
  * existing mobile subscriber.
  */
-static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
-			     unsigned int hdrlen)
+static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
+			     unsigned int hdrlen, unsigned int role)
 {
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP:
-		return gtp_check_src_ms_ipv4(skb, pctx, hdrlen);
+		return gtp_check_ms_ipv4(skb, pctx, hdrlen, role);
 	}
 	return false;
 }
 
+static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
+			unsigned int hdrlen, unsigned int role)
+{
+	struct pcpu_sw_netstats *stats;
+
+	if (!gtp_check_ms(skb, pctx, hdrlen, role)) {
+		netdev_dbg(pctx->dev, "No PDP ctx for this MS\n");
+		return 1;
+	}
+
+	/* Get rid of the GTP + UDP headers. */
+	if (iptunnel_pull_header(skb, hdrlen, skb->protocol,
+				 !net_eq(sock_net(pctx->sk), dev_net(pctx->dev))))
+		return -1;
+
+	netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n");
+
+	/* Now that the UDP and the GTP header have been removed, set up the
+	 * new network header. This is required by the upper layer to
+	 * calculate the transport header.
+	 */
+	skb_reset_network_header(skb);
+
+	skb->dev = pctx->dev;
+
+	stats = this_cpu_ptr(pctx->dev->tstats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	netif_rx(skb);
+	return 0;
+}
+
 /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
-static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
-			       bool xnet)
+static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
 {
 	unsigned int hdrlen = sizeof(struct udphdr) +
 			      sizeof(struct gtp0_header);
@@ -201,17 +244,10 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
 		return 1;
 	}
 
-	if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
-		netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
-		return 1;
-	}
-
-	/* Get rid of the GTP + UDP headers. */
-	return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+	return gtp_rx(pctx, skb, hdrlen, gtp->role);
 }
 
-static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
-				bool xnet)
+static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
 {
 	unsigned int hdrlen = sizeof(struct udphdr) +
 			      sizeof(struct gtp1_header);
@@ -250,37 +286,33 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
 		return 1;
 	}
 
-	if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
-		netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
-		return 1;
-	}
-
-	/* Get rid of the GTP + UDP headers. */
-	return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+	return gtp_rx(pctx, skb, hdrlen, gtp->role);
 }
 
-static void gtp_encap_disable(struct gtp_dev *gtp)
+static void gtp_encap_destroy(struct sock *sk)
 {
-	if (gtp->sock0 && gtp->sock0->sk) {
-		udp_sk(gtp->sock0->sk)->encap_type = 0;
-		rcu_assign_sk_user_data(gtp->sock0->sk, NULL);
-	}
-	if (gtp->sock1u && gtp->sock1u->sk) {
-		udp_sk(gtp->sock1u->sk)->encap_type = 0;
-		rcu_assign_sk_user_data(gtp->sock1u->sk, NULL);
-	}
+	struct gtp_dev *gtp;
 
-	gtp->sock0 = NULL;
-	gtp->sock1u = NULL;
+	gtp = rcu_dereference_sk_user_data(sk);
+	if (gtp) {
+		udp_sk(sk)->encap_type = 0;
+		rcu_assign_sk_user_data(sk, NULL);
+		sock_put(sk);
+	}
 }
 
-static void gtp_encap_destroy(struct sock *sk)
+static void gtp_encap_disable_sock(struct sock *sk)
 {
-	struct gtp_dev *gtp;
+	if (!sk)
+		return;
 
-	gtp = rcu_dereference_sk_user_data(sk);
-	if (gtp)
-		gtp_encap_disable(gtp);
+	gtp_encap_destroy(sk);
+}
+
+static void gtp_encap_disable(struct gtp_dev *gtp)
+{
+	gtp_encap_disable_sock(gtp->sk0);
+	gtp_encap_disable_sock(gtp->sk1u);
 }
 
 /* UDP encapsulation receive handler. See net/ipv4/udp.c.
@@ -288,10 +320,8 @@ static void gtp_encap_destroy(struct sock *sk)
  */
 static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
-	struct pcpu_sw_netstats *stats;
 	struct gtp_dev *gtp;
-	bool xnet;
-	int ret;
+	int ret = 0;
 
 	gtp = rcu_dereference_sk_user_data(sk);
 	if (!gtp)
@@ -299,16 +329,14 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
 
-	xnet = !net_eq(sock_net(sk), dev_net(gtp->dev));
-
 	switch (udp_sk(sk)->encap_type) {
 	case UDP_ENCAP_GTP0:
 		netdev_dbg(gtp->dev, "received GTP0 packet\n");
-		ret = gtp0_udp_encap_recv(gtp, skb, xnet);
+		ret = gtp0_udp_encap_recv(gtp, skb);
 		break;
 	case UDP_ENCAP_GTP1U:
 		netdev_dbg(gtp->dev, "received GTP1U packet\n");
-		ret = gtp1u_udp_encap_recv(gtp, skb, xnet);
+		ret = gtp1u_udp_encap_recv(gtp, skb);
 		break;
 	default:
 		ret = -1; /* Shouldn't happen. */
@@ -317,33 +345,17 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	switch (ret) {
 	case 1:
 		netdev_dbg(gtp->dev, "pass up to the process\n");
-		return 1;
+		break;
 	case 0:
-		netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n");
 		break;
 	case -1:
 		netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
 		kfree_skb(skb);
-		return 0;
+		ret = 0;
+		break;
 	}
 
-	/* Now that the UDP and the GTP header have been removed, set up the
-	 * new network header. This is required by the upper layer to
-	 * calculate the transport header.
-	 */
-	skb_reset_network_header(skb);
-
-	skb->dev = gtp->dev;
-
-	stats = this_cpu_ptr(gtp->dev->tstats);
-	u64_stats_update_begin(&stats->syncp);
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len;
-	u64_stats_update_end(&stats->syncp);
-
-	netif_rx(skb);
-
-	return 0;
+	return ret;
 }
 
 static int gtp_dev_init(struct net_device *dev)
@@ -367,8 +379,9 @@ static void gtp_dev_uninit(struct net_device *dev)
 	free_percpu(dev->tstats);
 }
 
-static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
-					   const struct sock *sk, __be32 daddr)
+static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
+					   const struct sock *sk,
+					   __be32 daddr)
 {
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_oif		= sk->sk_bound_dev_if;
@@ -377,7 +390,7 @@ static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
 	fl4->flowi4_tos		= RT_CONN_FLAGS(sk);
 	fl4->flowi4_proto	= sk->sk_protocol;
 
-	return ip_route_output_key(net, fl4);
+	return ip_route_output_key(sock_net(sk), fl4);
 }
 
 static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
@@ -466,7 +479,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 	struct rtable *rt;
 	struct flowi4 fl4;
 	struct iphdr *iph;
-	struct sock *sk;
 	__be16 df;
 	int mtu;
 
@@ -474,7 +486,11 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 	 * Prepend PDP header with TEI/TID from PDP ctx.
 	 */
 	iph = ip_hdr(skb);
-	pctx = ipv4_pdp_find(gtp, iph->daddr);
+	if (gtp->role == GTP_ROLE_SGSN)
+		pctx = ipv4_pdp_find(gtp, iph->saddr);
+	else
+		pctx = ipv4_pdp_find(gtp, iph->daddr);
+
 	if (!pctx) {
 		netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
 			   &iph->daddr);
@@ -482,40 +498,17 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 	}
 	netdev_dbg(dev, "found PDP context %p\n", pctx);
 
-	switch (pctx->gtp_version) {
-	case GTP_V0:
-		if (gtp->sock0)
-			sk = gtp->sock0->sk;
-		else
-			sk = NULL;
-		break;
-	case GTP_V1:
-		if (gtp->sock1u)
-			sk = gtp->sock1u->sk;
-		else
-			sk = NULL;
-		break;
-	default:
-		return -ENOENT;
-	}
-
-	if (!sk) {
-		netdev_dbg(dev, "no userspace socket is available, skip\n");
-		return -ENOENT;
-	}
-
-	rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk,
-				  pctx->sgsn_addr_ip4.s_addr);
+	rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr);
 	if (IS_ERR(rt)) {
 		netdev_dbg(dev, "no route to SSGN %pI4\n",
-			   &pctx->sgsn_addr_ip4.s_addr);
+			   &pctx->peer_addr_ip4.s_addr);
 		dev->stats.tx_carrier_errors++;
 		goto err;
 	}
 
 	if (rt->dst.dev == dev) {
 		netdev_dbg(dev, "circular route to SSGN %pI4\n",
-			   &pctx->sgsn_addr_ip4.s_addr);
+			   &pctx->peer_addr_ip4.s_addr);
 		dev->stats.collisions++;
 		goto err_rt;
 	}
@@ -550,7 +543,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		goto err_rt;
 	}
 
-	gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
+	gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev);
 	gtp_push_header(skb, pktinfo);
 
 	return 0;
@@ -640,27 +633,23 @@ static void gtp_link_setup(struct net_device *dev)
 
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
 static void gtp_hashtable_free(struct gtp_dev *gtp);
-static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
-			    int fd_gtp0, int fd_gtp1);
+static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);
 
 static int gtp_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[])
 {
-	int hashsize, err, fd0, fd1;
 	struct gtp_dev *gtp;
 	struct gtp_net *gn;
+	int hashsize, err;
 
-	if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1])
+	if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1])
 		return -EINVAL;
 
 	gtp = netdev_priv(dev);
 
-	fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
-	fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
-
-	err = gtp_encap_enable(dev, gtp, fd0, fd1);
+	err = gtp_encap_enable(gtp, data);
 	if (err < 0)
-		goto out_err;
+		return err;
 
 	if (!data[IFLA_GTP_PDP_HASHSIZE])
 		hashsize = 1024;
@@ -688,7 +677,6 @@ out_hashtable:
 	gtp_hashtable_free(gtp);
 out_encap:
 	gtp_encap_disable(gtp);
-out_err:
 	return err;
 }
 
@@ -706,6 +694,7 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = {
 	[IFLA_GTP_FD0]			= { .type = NLA_U32 },
 	[IFLA_GTP_FD1]			= { .type = NLA_U32 },
 	[IFLA_GTP_PDP_HASHSIZE]		= { .type = NLA_U32 },
+	[IFLA_GTP_ROLE]			= { .type = NLA_U32 },
 };
 
 static int gtp_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -747,21 +736,6 @@ static struct rtnl_link_ops gtp_link_ops __read_mostly = {
 	.fill_info	= gtp_fill_info,
 };
 
-static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[])
-{
-	struct net *net;
-
-	/* Examine the link attributes and figure out which network namespace
-	 * we are talking about.
-	 */
-	if (tb[GTPA_NET_NS_FD])
-		net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD]));
-	else
-		net = get_net(src_net);
-
-	return net;
-}
-
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 {
 	int i;
@@ -791,93 +765,127 @@ static void gtp_hashtable_free(struct gtp_dev *gtp)
 	struct pdp_ctx *pctx;
 	int i;
 
-	for (i = 0; i < gtp->hash_size; i++) {
-		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid) {
-			hlist_del_rcu(&pctx->hlist_tid);
-			hlist_del_rcu(&pctx->hlist_addr);
-			kfree_rcu(pctx, rcu_head);
-		}
-	}
+	for (i = 0; i < gtp->hash_size; i++)
+		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
+			pdp_context_delete(pctx);
+
 	synchronize_rcu();
 	kfree(gtp->addr_hash);
 	kfree(gtp->tid_hash);
 }
 
-static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
-			    int fd_gtp0, int fd_gtp1)
+static struct sock *gtp_encap_enable_socket(int fd, int type,
+					    struct gtp_dev *gtp)
 {
 	struct udp_tunnel_sock_cfg tuncfg = {NULL};
-	struct socket *sock0, *sock1u;
+	struct socket *sock;
+	struct sock *sk;
 	int err;
 
-	netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1);
-
-	sock0 = sockfd_lookup(fd_gtp0, &err);
-	if (sock0 == NULL) {
-		netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0);
-		return -ENOENT;
-	}
+	pr_debug("enable gtp on %d, %d\n", fd, type);
 
-	if (sock0->sk->sk_protocol != IPPROTO_UDP) {
-		netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0);
-		err = -EINVAL;
-		goto err1;
+	sock = sockfd_lookup(fd, &err);
+	if (!sock) {
+		pr_debug("gtp socket fd=%d not found\n", fd);
+		return NULL;
 	}
 
-	sock1u = sockfd_lookup(fd_gtp1, &err);
-	if (sock1u == NULL) {
-		netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1);
-		err = -ENOENT;
-		goto err1;
+	if (sock->sk->sk_protocol != IPPROTO_UDP) {
+		pr_debug("socket fd=%d not UDP\n", fd);
+		sk = ERR_PTR(-EINVAL);
+		goto out_sock;
 	}
 
-	if (sock1u->sk->sk_protocol != IPPROTO_UDP) {
-		netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1);
-		err = -EINVAL;
-		goto err2;
+	if (rcu_dereference_sk_user_data(sock->sk)) {
+		sk = ERR_PTR(-EBUSY);
+		goto out_sock;
 	}
 
-	netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u);
-
-	gtp->sock0 = sock0;
-	gtp->sock1u = sock1u;
+	sk = sock->sk;
+	sock_hold(sk);
 
 	tuncfg.sk_user_data = gtp;
+	tuncfg.encap_type = type;
 	tuncfg.encap_rcv = gtp_encap_recv;
 	tuncfg.encap_destroy = gtp_encap_destroy;
 
-	tuncfg.encap_type = UDP_ENCAP_GTP0;
-	setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg);
-
-	tuncfg.encap_type = UDP_ENCAP_GTP1U;
-	setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg);
+	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
 
-	err = 0;
-err2:
-	sockfd_put(sock1u);
-err1:
-	sockfd_put(sock0);
-	return err;
+out_sock:
+	sockfd_put(sock);
+	return sk;
 }
 
-static struct net_device *gtp_find_dev(struct net *net, int ifindex)
+static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
 {
-	struct gtp_net *gn = net_generic(net, gtp_net_id);
-	struct gtp_dev *gtp;
+	struct sock *sk1u = NULL;
+	struct sock *sk0 = NULL;
+	unsigned int role = GTP_ROLE_GGSN;
 
-	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
-		if (ifindex == gtp->dev->ifindex)
-			return gtp->dev;
+	if (data[IFLA_GTP_FD0]) {
+		u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
+
+		sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp);
+		if (IS_ERR(sk0))
+			return PTR_ERR(sk0);
 	}
-	return NULL;
+
+	if (data[IFLA_GTP_FD1]) {
+		u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
+
+		sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
+		if (IS_ERR(sk1u)) {
+			if (sk0)
+				gtp_encap_disable_sock(sk0);
+			return PTR_ERR(sk1u);
+		}
+	}
+
+	if (data[IFLA_GTP_ROLE]) {
+		role = nla_get_u32(data[IFLA_GTP_ROLE]);
+		if (role > GTP_ROLE_SGSN)
+			return -EINVAL;
+	}
+
+	gtp->sk0 = sk0;
+	gtp->sk1u = sk1u;
+	gtp->role = role;
+
+	return 0;
+}
+
+static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
+{
+	struct gtp_dev *gtp = NULL;
+	struct net_device *dev;
+	struct net *net;
+
+	/* Examine the link attributes and figure out which network namespace
+	 * we are talking about.
+	 */
+	if (nla[GTPA_NET_NS_FD])
+		net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD]));
+	else
+		net = get_net(src_net);
+
+	if (IS_ERR(net))
+		return NULL;
+
+	/* Check if there's an existing gtpX device to configure */
+	dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK]));
+	if (dev->netdev_ops == &gtp_netdev_ops)
+		gtp = netdev_priv(dev);
+
+	put_net(net);
+	return gtp;
 }
 
 static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 {
 	pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
 	pctx->af = AF_INET;
-	pctx->sgsn_addr_ip4.s_addr =
-		nla_get_be32(info->attrs[GTPA_SGSN_ADDRESS]);
+	pctx->peer_addr_ip4.s_addr =
+		nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]);
 	pctx->ms_addr_ip4.s_addr =
 		nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
 
@@ -899,9 +907,10 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 	}
 }
 
-static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
+static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+			struct genl_info *info)
 {
-	struct gtp_dev *gtp = netdev_priv(dev);
+	struct net_device *dev = gtp->dev;
 	u32 hash_ms, hash_tid = 0;
 	struct pdp_ctx *pctx;
 	bool found = false;
@@ -940,6 +949,9 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
 	if (pctx == NULL)
 		return -ENOMEM;
 
+	sock_hold(sk);
+	pctx->sk = sk;
+	pctx->dev = gtp->dev;
 	ipv4_pdp_fill(pctx, info);
 	atomic_set(&pctx->tx_seq, 0);
 
@@ -963,31 +975,50 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
 	switch (pctx->gtp_version) {
 	case GTP_V0:
 		netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
-			   pctx->u.v0.tid, &pctx->sgsn_addr_ip4,
+			   pctx->u.v0.tid, &pctx->peer_addr_ip4,
 			   &pctx->ms_addr_ip4, pctx);
 		break;
 	case GTP_V1:
 		netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
 			   pctx->u.v1.i_tei, pctx->u.v1.o_tei,
-			   &pctx->sgsn_addr_ip4, &pctx->ms_addr_ip4, pctx);
+			   &pctx->peer_addr_ip4, &pctx->ms_addr_ip4, pctx);
 		break;
 	}
 
 	return 0;
 }
 
+static void pdp_context_free(struct rcu_head *head)
+{
+	struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head);
+
+	sock_put(pctx->sk);
+	kfree(pctx);
+}
+
+static void pdp_context_delete(struct pdp_ctx *pctx)
+{
+	hlist_del_rcu(&pctx->hlist_tid);
+	hlist_del_rcu(&pctx->hlist_addr);
+	call_rcu(&pctx->rcu_head, pdp_context_free);
+}
+
 static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 {
-	struct net_device *dev;
-	struct net *net;
+	unsigned int version;
+	struct gtp_dev *gtp;
+	struct sock *sk;
+	int err;
 
 	if (!info->attrs[GTPA_VERSION] ||
 	    !info->attrs[GTPA_LINK] ||
-	    !info->attrs[GTPA_SGSN_ADDRESS] ||
+	    !info->attrs[GTPA_PEER_ADDRESS] ||
 	    !info->attrs[GTPA_MS_ADDRESS])
 		return -EINVAL;
 
-	switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+	version = nla_get_u32(info->attrs[GTPA_VERSION]);
+
+	switch (version) {
 	case GTP_V0:
 		if (!info->attrs[GTPA_TID] ||
 		    !info->attrs[GTPA_FLOW])
@@ -1003,77 +1034,101 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
+	rcu_read_lock();
 
-	/* Check if there's an existing gtpX device to configure */
-	dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
-	if (dev == NULL) {
-		put_net(net);
-		return -ENODEV;
+	gtp = gtp_find_dev(sock_net(skb->sk), info->attrs);
+	if (!gtp) {
+		err = -ENODEV;
+		goto out_unlock;
 	}
-	put_net(net);
 
-	return ipv4_pdp_add(dev, info);
+	if (version == GTP_V0)
+		sk = gtp->sk0;
+	else if (version == GTP_V1)
+		sk = gtp->sk1u;
+	else
+		sk = NULL;
+
+	if (!sk) {
+		err = -ENODEV;
+		goto out_unlock;
+	}
+
+	err = ipv4_pdp_add(gtp, sk, info);
+
+out_unlock:
+	rcu_read_unlock();
+	return err;
 }
 
-static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
+static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net,
+					    struct nlattr *nla[])
 {
-	struct net_device *dev;
-	struct pdp_ctx *pctx;
 	struct gtp_dev *gtp;
-	struct net *net;
 
-	if (!info->attrs[GTPA_VERSION] ||
-	    !info->attrs[GTPA_LINK])
-		return -EINVAL;
+	gtp = gtp_find_dev(net, nla);
+	if (!gtp)
+		return ERR_PTR(-ENODEV);
 
-	net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
+	if (nla[GTPA_MS_ADDRESS]) {
+		__be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]);
 
-	/* Check if there's an existing gtpX device to configure */
-	dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
-	if (dev == NULL) {
-		put_net(net);
-		return -ENODEV;
+		return ipv4_pdp_find(gtp, ip);
+	} else if (nla[GTPA_VERSION]) {
+		u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]);
+
+		if (gtp_version == GTP_V0 && nla[GTPA_TID])
+			return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID]));
+		else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI])
+			return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI]));
 	}
-	put_net(net);
 
-	gtp = netdev_priv(dev);
+	return ERR_PTR(-EINVAL);
+}
 
-	switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
-	case GTP_V0:
-		if (!info->attrs[GTPA_TID])
-			return -EINVAL;
-		pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID]));
-		break;
-	case GTP_V1:
-		if (!info->attrs[GTPA_I_TEI])
-			return -EINVAL;
-		pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI]));
-		break;
+static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[])
+{
+	struct pdp_ctx *pctx;
 
-	default:
+	if (nla[GTPA_LINK])
+		pctx = gtp_find_pdp_by_link(net, nla);
+	else
+		pctx = ERR_PTR(-EINVAL);
+
+	if (!pctx)
+		pctx = ERR_PTR(-ENOENT);
+
+	return pctx;
+}
+
+static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pdp_ctx *pctx;
+	int err = 0;
+
+	if (!info->attrs[GTPA_VERSION])
 		return -EINVAL;
-	}
 
-	if (pctx == NULL)
-		return -ENOENT;
+	rcu_read_lock();
+
+	pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
+	if (IS_ERR(pctx)) {
+		err = PTR_ERR(pctx);
+		goto out_unlock;
+	}
 
 	if (pctx->gtp_version == GTP_V0)
-		netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
+		netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
 			   pctx->u.v0.tid, pctx);
 	else if (pctx->gtp_version == GTP_V1)
-		netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
+		netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
 			   pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
 
-	hlist_del_rcu(&pctx->hlist_tid);
-	hlist_del_rcu(&pctx->hlist_addr);
-	kfree_rcu(pctx, rcu_head);
+	pdp_context_delete(pctx);
 
-	return 0;
+out_unlock:
+	rcu_read_unlock();
+	return err;
 }
 
 static struct genl_family gtp_genl_family;
@@ -1089,7 +1144,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
 		goto nlmsg_failure;
 
 	if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
-	    nla_put_be32(skb, GTPA_SGSN_ADDRESS, pctx->sgsn_addr_ip4.s_addr) ||
+	    nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
 	    nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
 		goto nla_put_failure;
 
@@ -1117,59 +1172,17 @@ nla_put_failure:
 static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
 {
 	struct pdp_ctx *pctx = NULL;
-	struct net_device *dev;
 	struct sk_buff *skb2;
-	struct gtp_dev *gtp;
-	u32 gtp_version;
-	struct net *net;
 	int err;
 
-	if (!info->attrs[GTPA_VERSION] ||
-	    !info->attrs[GTPA_LINK])
-		return -EINVAL;
-
-	gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
-	switch (gtp_version) {
-	case GTP_V0:
-	case GTP_V1:
-		break;
-	default:
+	if (!info->attrs[GTPA_VERSION])
 		return -EINVAL;
-	}
-
-	net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-
-	/* Check if there's an existing gtpX device to configure */
-	dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
-	if (dev == NULL) {
-		put_net(net);
-		return -ENODEV;
-	}
-	put_net(net);
-
-	gtp = netdev_priv(dev);
 
 	rcu_read_lock();
-	if (gtp_version == GTP_V0 &&
-	    info->attrs[GTPA_TID]) {
-		u64 tid = nla_get_u64(info->attrs[GTPA_TID]);
-
-		pctx = gtp0_pdp_find(gtp, tid);
-	} else if (gtp_version == GTP_V1 &&
-		 info->attrs[GTPA_I_TEI]) {
-		u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]);
-
-		pctx = gtp1_pdp_find(gtp, tid);
-	} else if (info->attrs[GTPA_MS_ADDRESS]) {
-		__be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
-
-		pctx = ipv4_pdp_find(gtp, ip);
-	}
 
-	if (pctx == NULL) {
-		err = -ENOENT;
+	pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
+	if (IS_ERR(pctx)) {
+		err = PTR_ERR(pctx);
 		goto err_unlock;
 	}
 
@@ -1242,7 +1255,7 @@ static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
 	[GTPA_LINK]		= { .type = NLA_U32, },
 	[GTPA_VERSION]		= { .type = NLA_U32, },
 	[GTPA_TID]		= { .type = NLA_U64, },
-	[GTPA_SGSN_ADDRESS]	= { .type = NLA_U32, },
+	[GTPA_PEER_ADDRESS]	= { .type = NLA_U32, },
 	[GTPA_MS_ADDRESS]	= { .type = NLA_U32, },
 	[GTPA_FLOW]		= { .type = NLA_U16, },
 	[GTPA_NET_NS_FD]	= { .type = NLA_U32, },
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index d3e73ac158ae..262b2ea576a3 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -196,6 +196,7 @@ int netvsc_recv_callback(struct net_device *net,
 			 const struct ndis_tcp_ip_checksum_info *csum_info,
 			 const struct ndis_pkt_8021q_info *vlan);
 void netvsc_channel_cb(void *context);
+int netvsc_poll(struct napi_struct *napi, int budget);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 int rndis_filter_device_add(struct hv_device *dev,
@@ -632,7 +633,7 @@ struct nvsp_message {
 
 #define NETVSC_PACKET_SIZE                      4096
 
-#define VRSS_SEND_TAB_SIZE 16
+#define VRSS_SEND_TAB_SIZE 16  /* must be power of 2 */
 #define VRSS_CHANNEL_MAX 64
 #define VRSS_CHANNEL_DEFAULT 8
 
@@ -685,7 +686,7 @@ struct net_device_context {
 	/* point back to our device context */
 	struct hv_device *device_ctx;
 	/* netvsc_device */
-	struct netvsc_device *nvdev;
+	struct netvsc_device __rcu *nvdev;
 	/* reconfigure work */
 	struct delayed_work dwork;
 	/* last reconfig time */
@@ -700,14 +701,13 @@ struct net_device_context {
 
 	u32 tx_checksum_mask;
 
+	u32 tx_send_table[VRSS_SEND_TAB_SIZE];
+
 	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
 	struct netvsc_ethtool_stats eth_stats;
 
-	/* the device is going away */
-	bool start_remove;
-
 	/* State to manage the associated VF interface. */
 	struct net_device __rcu *vf_netdev;
 
@@ -720,6 +720,8 @@ struct net_device_context {
 /* Per channel data */
 struct netvsc_channel {
 	struct vmbus_channel *channel;
+	const struct vmpacket_descriptor *desc;
+	struct napi_struct napi;
 	struct multi_send_data msd;
 	struct multi_recv_comp mrc;
 	atomic_t queue_sends;
@@ -749,7 +751,6 @@ struct netvsc_device {
 	u32 send_section_cnt;
 	u32 send_section_size;
 	unsigned long *send_section_map;
-	int map_words;
 
 	/* Used for NetVSP initialization protocol */
 	struct completion channel_init_wait;
@@ -757,11 +758,10 @@ struct netvsc_device {
 
 	struct nvsp_message revoke_packet;
 
-	u32 send_table[VRSS_SEND_TAB_SIZE];
 	u32 max_chn;
 	u32 num_chn;
-	spinlock_t sc_lock; /* Protects num_sc_offered variable */
-	u32 num_sc_offered;
+
+	refcount_t sc_offered;
 
 	/* Holds rndis device info */
 	void *extension;
@@ -776,6 +776,8 @@ struct netvsc_device {
 	atomic_t open_cnt;
 
 	struct netvsc_channel chan_table[VRSS_CHANNEL_MAX];
+
+	struct rcu_head rcu;
 };
 
 static inline struct netvsc_device *
@@ -1424,9 +1426,6 @@ struct rndis_message {
 	((void *) rndis_msg)
 
 
-#define __struct_bcount(x)
-
-
 
 #define RNDIS_HEADER_SIZE	(sizeof(struct rndis_message) - \
 				 sizeof(union rndis_message_container))
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d35ebd993b38..15749d359e60 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -80,8 +80,10 @@ static struct netvsc_device *alloc_net_device(void)
 	return net_device;
 }
 
-static void free_netvsc_device(struct netvsc_device *nvdev)
+static void free_netvsc_device(struct rcu_head *head)
 {
+	struct netvsc_device *nvdev
+		= container_of(head, struct netvsc_device, rcu);
 	int i;
 
 	for (i = 0; i < VRSS_CHANNEL_MAX; i++)
@@ -90,14 +92,9 @@ static void free_netvsc_device(struct netvsc_device *nvdev)
 	kfree(nvdev);
 }
 
-
-static inline bool netvsc_channel_idle(const struct netvsc_device *net_device,
-				       u16 q_idx)
+static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
 {
-	const struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
-
-	return atomic_read(&net_device->num_outstanding_recvs) == 0 &&
-		atomic_read(&nvchan->queue_sends) == 0;
+	call_rcu(&nvdev->rcu, free_netvsc_device);
 }
 
 static struct netvsc_device *get_outbound_net_device(struct hv_device *device)
@@ -138,6 +135,13 @@ static void netvsc_destroy_buf(struct hv_device *device)
 				       sizeof(struct nvsp_message),
 				       (unsigned long)revoke_packet,
 				       VM_PKT_DATA_INBAND, 0);
+		/* If the failure is because the channel is rescinded;
+		 * ignore the failure since we cannot send on a rescinded
+		 * channel. This would allow us to properly cleanup
+		 * even when the channel is rescinded.
+		 */
+		if (device->channel->rescind)
+			ret = 0;
 		/*
 		 * If we failed here, we might as well return and
 		 * have a leak rather than continue and a bugchk
@@ -198,6 +202,15 @@ static void netvsc_destroy_buf(struct hv_device *device)
 				       sizeof(struct nvsp_message),
 				       (unsigned long)revoke_packet,
 				       VM_PKT_DATA_INBAND, 0);
+
+		/* If the failure is because the channel is rescinded;
+		 * ignore the failure since we cannot send on a rescinded
+		 * channel. This would allow us to properly cleanup
+		 * even when the channel is rescinded.
+		 */
+		if (device->channel->rescind)
+			ret = 0;
+
 		/* If we failed here, we might as well return and
 		 * have a leak rather than continue and a bugchk
 		 */
@@ -236,6 +249,7 @@ static int netvsc_init_buf(struct hv_device *device)
 	struct netvsc_device *net_device;
 	struct nvsp_message *init_packet;
 	struct net_device *ndev;
+	size_t map_words;
 	int node;
 
 	net_device = get_outbound_net_device(device);
@@ -401,11 +415,9 @@ static int netvsc_init_buf(struct hv_device *device)
 		   net_device->send_section_size, net_device->send_section_cnt);
 
 	/* Setup state for managing the send buffer. */
-	net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt,
-					     BITS_PER_LONG);
+	map_words = DIV_ROUND_UP(net_device->send_section_cnt, BITS_PER_LONG);
 
-	net_device->send_section_map = kcalloc(net_device->map_words,
-					       sizeof(ulong), GFP_KERNEL);
+	net_device->send_section_map = kcalloc(map_words, sizeof(ulong), GFP_KERNEL);
 	if (net_device->send_section_map == NULL) {
 		ret = -ENOMEM;
 		goto cleanup;
@@ -556,10 +568,11 @@ void netvsc_device_remove(struct hv_device *device)
 	struct net_device *ndev = hv_get_drvdata(device);
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	int i;
 
 	netvsc_disconnect_vsp(device);
 
-	net_device_ctx->nvdev = NULL;
+	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
 
 	/*
 	 * At this point, no one should be accessing net_device
@@ -570,8 +583,12 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
+	/* And dissassociate NAPI context from device */
+	for (i = 0; i < net_device->num_chn; i++)
+		netif_napi_del(&net_device->chan_table[i].napi);
+
 	/* Release all resources */
-	free_netvsc_device(net_device);
+	free_netvsc_device_rcu(net_device);
 }
 
 #define RING_AVAIL_PERCENT_HIWATER 20
@@ -600,11 +617,11 @@ static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
 static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 				    struct vmbus_channel *incoming_channel,
 				    struct hv_device *device,
-				    struct vmpacket_descriptor *packet)
+				    const struct vmpacket_descriptor *desc,
+				    int budget)
 {
-	struct sk_buff *skb = (struct sk_buff *)(unsigned long)packet->trans_id;
+	struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
 	struct net_device *ndev = hv_get_drvdata(device);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	struct vmbus_channel *channel = device->channel;
 	u16 q_idx = 0;
 	int queue_sends;
@@ -628,7 +645,7 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 		tx_stats->bytes += packet->total_bytes;
 		u64_stats_update_end(&tx_stats->syncp);
 
-		dev_consume_skb_any(skb);
+		napi_consume_skb(skb, budget);
 	}
 
 	queue_sends =
@@ -638,7 +655,6 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 		wake_up(&net_device->wait_drain);
 
 	if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
-	    !net_device_ctx->start_remove &&
 	    (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
 	     queue_sends < 1))
 		netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
@@ -647,14 +663,12 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 static void netvsc_send_completion(struct netvsc_device *net_device,
 				   struct vmbus_channel *incoming_channel,
 				   struct hv_device *device,
-				   struct vmpacket_descriptor *packet)
+				   const struct vmpacket_descriptor *desc,
+				   int budget)
 {
-	struct nvsp_message *nvsp_packet;
+	struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
 	struct net_device *ndev = hv_get_drvdata(device);
 
-	nvsp_packet = (struct nvsp_message *)((unsigned long)packet +
-					      (packet->offset8 << 3));
-
 	switch (nvsp_packet->hdr.msg_type) {
 	case NVSP_MSG_TYPE_INIT_COMPLETE:
 	case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE:
@@ -668,7 +682,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 
 	case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE:
 		netvsc_send_tx_complete(net_device, incoming_channel,
-					device, packet);
+					device, desc, budget);
 		break;
 
 	default:
@@ -683,7 +697,7 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
 	unsigned long *map_addr = net_device->send_section_map;
 	unsigned int i;
 
-	for_each_clear_bit(i, map_addr, net_device->map_words) {
+	for_each_clear_bit(i, map_addr, net_device->send_section_cnt) {
 		if (sync_test_and_set_bit(i, map_addr) == 0)
 			return i;
 	}
@@ -710,8 +724,7 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		packet->page_buf_cnt;
 
 	/* Add padding */
-	if (skb && skb->xmit_more && remain &&
-	    !packet->cp_partial) {
+	if (skb->xmit_more && remain && !packet->cp_partial) {
 		padding = net_device->pkt_align - remain;
 		rndis_msg->msg_len += padding;
 		packet->total_data_buflen += padding;
@@ -869,9 +882,7 @@ int netvsc_send(struct hv_device *device,
 	if (msdp->pkt)
 		msd_len = msdp->pkt->total_data_buflen;
 
-	try_batch = (skb != NULL) && msd_len > 0 && msdp->count <
-		    net_device->max_pkt;
-
+	try_batch =  msd_len > 0 && msdp->count < net_device->max_pkt;
 	if (try_batch && msd_len + pktlen + net_device->pkt_align <
 	    net_device->send_section_size) {
 		section_index = msdp->pkt->send_buf_index;
@@ -881,7 +892,7 @@ int netvsc_send(struct hv_device *device,
 		section_index = msdp->pkt->send_buf_index;
 		packet->cp_partial = true;
 
-	} else if ((skb != NULL) && pktlen + net_device->pkt_align <
+	} else if (pktlen + net_device->pkt_align <
 		   net_device->send_section_size) {
 		section_index = netvsc_get_next_send_section(net_device);
 		if (section_index != NETVSC_INVALID_INDEX) {
@@ -1066,28 +1077,29 @@ static inline struct recv_comp_data *get_recv_comp_slot(
 	return rcd;
 }
 
-static void netvsc_receive(struct net_device *ndev,
+static int netvsc_receive(struct net_device *ndev,
 		   struct netvsc_device *net_device,
 		   struct net_device_context *net_device_ctx,
 		   struct hv_device *device,
 		   struct vmbus_channel *channel,
-		   struct vmtransfer_page_packet_header *vmxferpage_packet,
+		   const struct vmpacket_descriptor *desc,
 		   struct nvsp_message *nvsp)
 {
+	const struct vmtransfer_page_packet_header *vmxferpage_packet
+		= container_of(desc, const struct vmtransfer_page_packet_header, d);
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 	char *recv_buf = net_device->recv_buf;
 	u32 status = NVSP_STAT_SUCCESS;
 	int i;
 	int count = 0;
 	int ret;
-	struct recv_comp_data *rcd;
-	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 
 	/* Make sure this is a valid nvsp packet */
 	if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) {
 		netif_err(net_device_ctx, rx_err, ndev,
 			  "Unknown nvsp packet type received %u\n",
 			  nvsp->hdr.msg_type);
-		return;
+		return 0;
 	}
 
 	if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) {
@@ -1095,7 +1107,7 @@ static void netvsc_receive(struct net_device *ndev,
 			  "Invalid xfer page set id - expecting %x got %x\n",
 			  NETVSC_RECEIVE_BUFFER_ID,
 			  vmxferpage_packet->xfer_pageset_id);
-		return;
+		return 0;
 	}
 
 	count = vmxferpage_packet->range_cnt;
@@ -1111,40 +1123,36 @@ static void netvsc_receive(struct net_device *ndev,
 					      channel, data, buflen);
 	}
 
-	if (!net_device->chan_table[q_idx].mrc.buf) {
+	if (net_device->chan_table[q_idx].mrc.buf) {
+		struct recv_comp_data *rcd;
+
+		rcd = get_recv_comp_slot(net_device, channel, q_idx);
+		if (rcd) {
+			rcd->tid = vmxferpage_packet->d.trans_id;
+			rcd->status = status;
+		} else {
+			netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n",
+				   q_idx, vmxferpage_packet->d.trans_id);
+		}
+	} else {
 		ret = netvsc_send_recv_completion(channel,
 						  vmxferpage_packet->d.trans_id,
 						  status);
 		if (ret)
 			netdev_err(ndev, "Recv_comp q:%hd, tid:%llx, err:%d\n",
 				   q_idx, vmxferpage_packet->d.trans_id, ret);
-		return;
 	}
-
-	rcd = get_recv_comp_slot(net_device, channel, q_idx);
-
-	if (!rcd) {
-		netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n",
-			   q_idx, vmxferpage_packet->d.trans_id);
-		return;
-	}
-
-	rcd->tid = vmxferpage_packet->d.trans_id;
-	rcd->status = status;
+	return count;
 }
 
 static void netvsc_send_table(struct hv_device *hdev,
 			      struct nvsp_message *nvmsg)
 {
-	struct netvsc_device *nvscdev;
 	struct net_device *ndev = hv_get_drvdata(hdev);
+	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	int i;
 	u32 count, *tab;
 
-	nvscdev = get_outbound_net_device(hdev);
-	if (!nvscdev)
-		return;
-
 	count = nvmsg->msg.v5_msg.send_table.count;
 	if (count != VRSS_SEND_TAB_SIZE) {
 		netdev_err(ndev, "Received wrong send-table size:%u\n", count);
@@ -1155,7 +1163,7 @@ static void netvsc_send_table(struct hv_device *hdev,
 		      nvmsg->msg.v5_msg.send_table.offset);
 
 	for (i = 0; i < count; i++)
-		nvscdev->send_table[i] = tab[i];
+		net_device_ctx->tx_send_table[i] = tab[i];
 }
 
 static void netvsc_send_vf(struct net_device_context *net_device_ctx,
@@ -1180,28 +1188,25 @@ static inline void netvsc_receive_inband(struct hv_device *hdev,
 	}
 }
 
-static void netvsc_process_raw_pkt(struct hv_device *device,
-				   struct vmbus_channel *channel,
-				   struct netvsc_device *net_device,
-				   struct net_device *ndev,
-				   u64 request_id,
-				   struct vmpacket_descriptor *desc)
+static int netvsc_process_raw_pkt(struct hv_device *device,
+				  struct vmbus_channel *channel,
+				  struct netvsc_device *net_device,
+				  struct net_device *ndev,
+				  const struct vmpacket_descriptor *desc,
+				  int budget)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct nvsp_message *nvmsg
-		= (struct nvsp_message *)((unsigned long)desc
-					  + (desc->offset8 << 3));
+	struct nvsp_message *nvmsg = hv_pkt_data(desc);
 
 	switch (desc->type) {
 	case VM_PKT_COMP:
-		netvsc_send_completion(net_device, channel, device, desc);
+		netvsc_send_completion(net_device, channel, device,
+				       desc, budget);
 		break;
 
 	case VM_PKT_DATA_USING_XFER_PAGES:
-		netvsc_receive(ndev, net_device, net_device_ctx,
-			       device, channel,
-			       (struct vmtransfer_page_packet_header *)desc,
-			       nvmsg);
+		return netvsc_receive(ndev, net_device, net_device_ctx,
+				      device, channel, desc, nvmsg);
 		break;
 
 	case VM_PKT_DATA_INBAND:
@@ -1210,50 +1215,74 @@ static void netvsc_process_raw_pkt(struct hv_device *device,
 
 	default:
 		netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
-			   desc->type, request_id);
+			   desc->type, desc->trans_id);
 		break;
 	}
+
+	return 0;
 }
 
-void netvsc_channel_cb(void *context)
+static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel)
+{
+	struct vmbus_channel *primary = channel->primary_channel;
+
+	return primary ? primary->device_obj : channel->device_obj;
+}
+
+/* Network processing softirq
+ * Process data in incoming ring buffer from host
+ * Stops when ring is empty or budget is met or exceeded.
+ */
+int netvsc_poll(struct napi_struct *napi, int budget)
 {
-	struct vmbus_channel *channel = context;
+	struct netvsc_channel *nvchan
+		= container_of(napi, struct netvsc_channel, napi);
+	struct vmbus_channel *channel = nvchan->channel;
+	struct hv_device *device = netvsc_channel_to_device(channel);
 	u16 q_idx = channel->offermsg.offer.sub_channel_index;
-	struct hv_device *device;
-	struct netvsc_device *net_device;
-	struct vmpacket_descriptor *desc;
-	struct net_device *ndev;
-	bool need_to_commit = false;
+	struct net_device *ndev = hv_get_drvdata(device);
+	struct netvsc_device *net_device = net_device_to_netvsc_device(ndev);
+	int work_done = 0;
 
-	if (channel->primary_channel != NULL)
-		device = channel->primary_channel->device_obj;
-	else
-		device = channel->device_obj;
+	/* If starting a new interval */
+	if (!nvchan->desc)
+		nvchan->desc = hv_pkt_iter_first(channel);
 
-	ndev = hv_get_drvdata(device);
-	if (unlikely(!ndev))
-		return;
+	while (nvchan->desc && work_done < budget) {
+		work_done += netvsc_process_raw_pkt(device, channel, net_device,
+						    ndev, nvchan->desc, budget);
+		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
+	}
 
-	net_device = net_device_to_netvsc_device(ndev);
-	if (unlikely(net_device->destroy) &&
-	    netvsc_channel_idle(net_device, q_idx))
-		return;
+	/* If receive ring was exhausted
+	 * and not doing busy poll
+	 * then re-enable host interrupts
+	 *  and reschedule if ring is not empty.
+	 */
+	if (work_done < budget &&
+	    napi_complete_done(napi, work_done) &&
+	    hv_end_read(&channel->inbound) != 0)
+		napi_reschedule(napi);
 
-	/* commit_rd_index() -> hv_signal_on_read() needs this. */
-	init_cached_read_index(channel);
+	netvsc_chk_recv_comp(net_device, channel, q_idx);
 
-	while ((desc = get_next_pkt_raw(channel)) != NULL) {
-		netvsc_process_raw_pkt(device, channel, net_device,
-				       ndev, desc->trans_id, desc);
+	/* Driver may overshoot since multiple packets per descriptor */
+	return min(work_done, budget);
+}
 
-		put_pkt_raw(channel, desc);
-		need_to_commit = true;
-	}
+/* Call back when data is available in host ring buffer.
+ * Processing is deferred until network softirq (NAPI)
+ */
+void netvsc_channel_cb(void *context)
+{
+	struct netvsc_channel *nvchan = context;
 
-	if (need_to_commit)
-		commit_rd_index(channel);
+	if (napi_schedule_prep(&nvchan->napi)) {
+		/* disable interupts from host */
+		hv_begin_read(&nvchan->channel->inbound);
 
-	netvsc_chk_recv_comp(net_device, channel, q_idx);
+		__napi_schedule(&nvchan->napi);
+	}
 }
 
 /*
@@ -1275,10 +1304,29 @@ int netvsc_device_add(struct hv_device *device,
 
 	net_device->ring_size = ring_size;
 
+	/* Because the device uses NAPI, all the interrupt batching and
+	 * control is done via Net softirq, not the channel handling
+	 */
+	set_channel_read_mode(device->channel, HV_CALL_ISR);
+
+	/* If we're reopening the device we may have multiple queues, fill the
+	 * chn_table with the default channel to use it before subchannels are
+	 * opened.
+	 * Initialize the channel state before we open;
+	 * we can be interrupted as soon as we open the channel.
+	 */
+
+	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
+		struct netvsc_channel *nvchan = &net_device->chan_table[i];
+
+		nvchan->channel = device->channel;
+	}
+
 	/* Open the channel */
 	ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
 			 ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb, device->channel);
+			 netvsc_channel_cb,
+			 net_device->chan_table);
 
 	if (ret != 0) {
 		netdev_err(ndev, "unable to open channel: %d\n", ret);
@@ -1288,19 +1336,15 @@ int netvsc_device_add(struct hv_device *device,
 	/* Channel is opened */
 	netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");
 
-	/* If we're reopening the device we may have multiple queues, fill the
-	 * chn_table with the default channel to use it before subchannels are
-	 * opened.
-	 */
-	for (i = 0; i < VRSS_CHANNEL_MAX; i++)
-		net_device->chan_table[i].channel = device->channel;
+	/* Enable NAPI handler for init callbacks */
+	netif_napi_add(ndev, &net_device->chan_table[0].napi,
+		       netvsc_poll, NAPI_POLL_WEIGHT);
+	napi_enable(&net_device->chan_table[0].napi);
 
 	/* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is
 	 * populated.
 	 */
-	wmb();
-
-	net_device_ctx->nvdev = net_device;
+	rcu_assign_pointer(net_device_ctx->nvdev, net_device);
 
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device);
@@ -1313,11 +1357,13 @@ int netvsc_device_add(struct hv_device *device,
 	return ret;
 
 close:
+	netif_napi_del(&net_device->chan_table[0].napi);
+
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
 cleanup:
-	free_netvsc_device(net_device);
+	free_netvsc_device(&net_device->rcu);
 
 	return ret;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index bc05c895d958..4421a6d00375 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -62,7 +62,7 @@ static void do_set_multicast(struct work_struct *w)
 		container_of(w, struct net_device_context, work);
 	struct hv_device *device_obj = ndevctx->device_ctx;
 	struct net_device *ndev = hv_get_drvdata(device_obj);
-	struct netvsc_device *nvdev = ndevctx->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndevctx->nvdev);
 	struct rndis_device *rdev;
 
 	if (!nvdev)
@@ -116,7 +116,7 @@ static int netvsc_open(struct net_device *net)
 static int netvsc_close(struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	int ret;
 	u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
 	struct vmbus_channel *chn;
@@ -191,6 +191,54 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 	return ppi;
 }
 
+/* Azure hosts don't support non-TCP port numbers in hashing yet. We compute
+ * hash for non-TCP traffic with only IP numbers.
+ */
+static inline u32 netvsc_get_hash(struct sk_buff *skb, struct sock *sk)
+{
+	struct flow_keys flow;
+	u32 hash;
+	static u32 hashrnd __read_mostly;
+
+	net_get_random_once(&hashrnd, sizeof(hashrnd));
+
+	if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
+		return 0;
+
+	if (flow.basic.ip_proto == IPPROTO_TCP) {
+		return skb_get_hash(skb);
+	} else {
+		if (flow.basic.n_proto == htons(ETH_P_IP))
+			hash = jhash2((u32 *)&flow.addrs.v4addrs, 2, hashrnd);
+		else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+			hash = jhash2((u32 *)&flow.addrs.v6addrs, 8, hashrnd);
+		else
+			hash = 0;
+
+		skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
+	}
+
+	return hash;
+}
+
+static inline int netvsc_get_tx_queue(struct net_device *ndev,
+				      struct sk_buff *skb, int old_idx)
+{
+	const struct net_device_context *ndc = netdev_priv(ndev);
+	struct sock *sk = skb->sk;
+	int q_idx;
+
+	q_idx = ndc->tx_send_table[netvsc_get_hash(skb, sk) &
+				   (VRSS_SEND_TAB_SIZE - 1)];
+
+	/* If queue index changed record the new value */
+	if (q_idx != old_idx &&
+	    sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
+		sk_tx_queue_set(sk, q_idx);
+
+	return q_idx;
+}
+
 /*
  * Select queue for transmit.
  *
@@ -205,28 +253,21 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 			void *accel_priv, select_queue_fallback_t fallback)
 {
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *nvsc_dev = net_device_ctx->nvdev;
-	struct sock *sk = skb->sk;
-	int q_idx = sk_tx_queue_get(sk);
-
-	if (q_idx < 0 || skb->ooo_okay ||
-	    q_idx >= ndev->real_num_tx_queues) {
-		u16 hash = __skb_tx_hash(ndev, skb, VRSS_SEND_TAB_SIZE);
-		int new_idx;
-
-		new_idx = nvsc_dev->send_table[hash]
-			% nvsc_dev->num_chn;
+	unsigned int num_tx_queues = ndev->real_num_tx_queues;
+	int q_idx = sk_tx_queue_get(skb->sk);
 
-		if (q_idx != new_idx && sk &&
-		    sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
-			sk_tx_queue_set(sk, new_idx);
-
-		q_idx = new_idx;
+	if (q_idx < 0 || skb->ooo_okay) {
+		/* If forwarding a packet, we use the recorded queue when
+		 * available for better cache locality.
+		 */
+		if (skb_rx_queue_recorded(skb))
+			q_idx = skb_get_rx_queue(skb);
+		else
+			q_idx = netvsc_get_tx_queue(ndev, skb, q_idx);
 	}
 
-	if (unlikely(!nvsc_dev->chan_table[q_idx].channel))
-		q_idx = 0;
+	while (unlikely(q_idx >= num_tx_queues))
+		q_idx -= num_tx_queues;
 
 	return q_idx;
 }
@@ -589,13 +630,14 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
 }
 
 static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
+					     struct napi_struct *napi,
 					     const struct ndis_tcp_ip_checksum_info *csum_info,
 					     const struct ndis_pkt_8021q_info *vlan,
 					     void *data, u32 buflen)
 {
 	struct sk_buff *skb;
 
-	skb = netdev_alloc_skb_ip_align(net, buflen);
+	skb = napi_alloc_skb(napi, buflen);
 	if (!skb)
 		return skb;
 
@@ -641,12 +683,12 @@ int netvsc_recv_callback(struct net_device *net,
 			 const struct ndis_pkt_8021q_info *vlan)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	struct netvsc_device *net_device;
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
+	struct netvsc_channel *nvchan;
 	struct net_device *vf_netdev;
 	struct sk_buff *skb;
 	struct netvsc_stats *rx_stats;
-	u16 q_idx = channel->offermsg.offer.sub_channel_index;
-
 
 	if (net->reg_state != NETREG_REGISTERED)
 		return NVSP_STAT_FAIL;
@@ -659,13 +701,20 @@ int netvsc_recv_callback(struct net_device *net,
 	 * interface in the guest.
 	 */
 	rcu_read_lock();
+	net_device = rcu_dereference(net_device_ctx->nvdev);
+	if (unlikely(!net_device))
+		goto drop;
+
+	nvchan = &net_device->chan_table[q_idx];
 	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
 	if (vf_netdev && (vf_netdev->flags & IFF_UP))
 		net = vf_netdev;
 
 	/* Allocate a skb - TODO direct I/O to pages? */
-	skb = netvsc_alloc_recv_skb(net, csum_info, vlan, data, len);
+	skb = netvsc_alloc_recv_skb(net, &nvchan->napi,
+				    csum_info, vlan, data, len);
 	if (unlikely(!skb)) {
+drop:
 		++net->stats.rx_dropped;
 		rcu_read_unlock();
 		return NVSP_STAT_FAIL;
@@ -679,7 +728,7 @@ int netvsc_recv_callback(struct net_device *net,
 	 * on the synthetic device because modifying the VF device
 	 * statistics will not work correctly.
 	 */
-	rx_stats = &net_device->chan_table[q_idx].rx_stats;
+	rx_stats = &nvchan->rx_stats;
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->packets++;
 	rx_stats->bytes += len;
@@ -690,12 +739,7 @@ int netvsc_recv_callback(struct net_device *net,
 		++rx_stats->multicast;
 	u64_stats_update_end(&rx_stats->syncp);
 
-	/*
-	 * Pass the skb back up. Network stack will deallocate the skb when it
-	 * is done.
-	 * TODO - use NAPI?
-	 */
-	netif_receive_skb(skb);
+	napi_gro_receive(&nvchan->napi, skb);
 	rcu_read_unlock();
 
 	return 0;
@@ -712,7 +756,7 @@ static void netvsc_get_channels(struct net_device *net,
 				struct ethtool_channels *channel)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 
 	if (nvdev) {
 		channel->max_combined	= nvdev->max_chn;
@@ -749,8 +793,9 @@ static int netvsc_set_channels(struct net_device *net,
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct hv_device *dev = net_device_ctx->device_ctx;
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	unsigned int count = channels->combined_count;
+	bool was_running;
 	int ret;
 
 	/* We do not support separate count for rx, tx, or other */
@@ -761,7 +806,7 @@ static int netvsc_set_channels(struct net_device *net,
 	if (count > net->num_tx_queues || count > net->num_rx_queues)
 		return -EINVAL;
 
-	if (net_device_ctx->start_remove || !nvdev || nvdev->destroy)
+	if (!nvdev || nvdev->destroy)
 		return -ENODEV;
 
 	if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5)
@@ -770,11 +815,13 @@ static int netvsc_set_channels(struct net_device *net,
 	if (count > nvdev->max_chn)
 		return -EINVAL;
 
-	ret = netvsc_close(net);
-	if (ret)
-		return ret;
+	was_running = netif_running(net);
+	if (was_running) {
+		ret = netvsc_close(net);
+		if (ret)
+			return ret;
+	}
 
-	net_device_ctx->start_remove = true;
 	rndis_filter_device_remove(dev, nvdev);
 
 	ret = netvsc_set_queues(net, dev, count);
@@ -783,8 +830,8 @@ static int netvsc_set_channels(struct net_device *net,
 	else
 		netvsc_set_queues(net, dev, nvdev->num_chn);
 
-	netvsc_open(net);
-	net_device_ctx->start_remove = false;
+	if (was_running)
+		ret = netvsc_open(net);
 
 	/* We may have missed link change notifications */
 	schedule_delayed_work(&net_device_ctx->dwork, 0);
@@ -792,18 +839,19 @@ static int netvsc_set_channels(struct net_device *net,
 	return ret;
 }
 
-static bool netvsc_validate_ethtool_ss_cmd(const struct ethtool_cmd *cmd)
+static bool
+netvsc_validate_ethtool_ss_cmd(const struct ethtool_link_ksettings *cmd)
 {
-	struct ethtool_cmd diff1 = *cmd;
-	struct ethtool_cmd diff2 = {};
+	struct ethtool_link_ksettings diff1 = *cmd;
+	struct ethtool_link_ksettings diff2 = {};
 
-	ethtool_cmd_speed_set(&diff1, 0);
-	diff1.duplex = 0;
+	diff1.base.speed = 0;
+	diff1.base.duplex = 0;
 	/* advertising and cmd are usually set */
-	diff1.advertising = 0;
-	diff1.cmd = 0;
+	ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
+	diff1.base.cmd = 0;
 	/* We set port to PORT_OTHER */
-	diff2.port = PORT_OTHER;
+	diff2.base.port = PORT_OTHER;
 
 	return !memcmp(&diff1, &diff2, sizeof(diff1));
 }
@@ -813,33 +861,35 @@ static void netvsc_init_settings(struct net_device *dev)
 	struct net_device_context *ndc = netdev_priv(dev);
 
 	ndc->speed = SPEED_UNKNOWN;
-	ndc->duplex = DUPLEX_UNKNOWN;
+	ndc->duplex = DUPLEX_FULL;
 }
 
-static int netvsc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netvsc_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 
-	ethtool_cmd_speed_set(cmd, ndc->speed);
-	cmd->duplex = ndc->duplex;
-	cmd->port = PORT_OTHER;
+	cmd->base.speed = ndc->speed;
+	cmd->base.duplex = ndc->duplex;
+	cmd->base.port = PORT_OTHER;
 
 	return 0;
 }
 
-static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netvsc_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	u32 speed;
 
-	speed = ethtool_cmd_speed(cmd);
+	speed = cmd->base.speed;
 	if (!ethtool_validate_speed(speed) ||
-	    !ethtool_validate_duplex(cmd->duplex) ||
+	    !ethtool_validate_duplex(cmd->base.duplex) ||
 	    !netvsc_validate_ethtool_ss_cmd(cmd))
 		return -EINVAL;
 
 	ndc->speed = speed;
-	ndc->duplex = cmd->duplex;
+	ndc->duplex = cmd->base.duplex;
 
 	return 0;
 }
@@ -847,24 +897,27 @@ static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 {
 	struct net_device_context *ndevctx = netdev_priv(ndev);
-	struct netvsc_device *nvdev = ndevctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
 	struct hv_device *hdev = ndevctx->device_ctx;
 	struct netvsc_device_info device_info;
-	int ret;
+	bool was_running;
+	int ret = 0;
 
-	if (ndevctx->start_remove || !nvdev || nvdev->destroy)
+	if (!nvdev || nvdev->destroy)
 		return -ENODEV;
 
-	ret = netvsc_close(ndev);
-	if (ret)
-		goto out;
+	was_running = netif_running(ndev);
+	if (was_running) {
+		ret = netvsc_close(ndev);
+		if (ret)
+			return ret;
+	}
 
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
 	device_info.num_chn = nvdev->num_chn;
 	device_info.max_num_vrss_chns = nvdev->num_chn;
 
-	ndevctx->start_remove = true;
 	rndis_filter_device_remove(hdev, nvdev);
 
 	/* 'nvdev' has been freed in rndis_filter_device_remove() ->
@@ -877,9 +930,8 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 
 	rndis_filter_device_add(hdev, &device_info);
 
-out:
-	netvsc_open(ndev);
-	ndevctx->start_remove = false;
+	if (was_running)
+		ret = netvsc_open(ndev);
 
 	/* We may have missed link change notifications */
 	schedule_delayed_work(&ndevctx->dwork, 0);
@@ -891,7 +943,7 @@ static void netvsc_get_stats64(struct net_device *net,
 			       struct rtnl_link_stats64 *t)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = ndev_ctx->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
 	int i;
 
 	if (!nvdev)
@@ -976,7 +1028,10 @@ static const struct {
 static int netvsc_get_sset_count(struct net_device *dev, int string_set)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+
+	if (!nvdev)
+		return -ENODEV;
 
 	switch (string_set) {
 	case ETH_SS_STATS:
@@ -990,13 +1045,16 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 				     struct ethtool_stats *stats, u64 *data)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
 	const void *nds = &ndc->eth_stats;
 	const struct netvsc_stats *qstats;
 	unsigned int start;
 	u64 packets, bytes;
 	int i, j;
 
+	if (!nvdev)
+		return;
+
 	for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
 		data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);
 
@@ -1025,10 +1083,13 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
 	u8 *p = data;
 	int i;
 
+	if (!nvdev)
+		return;
+
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
@@ -1080,7 +1141,10 @@ netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 		 u32 *rules)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+
+	if (!nvdev)
+		return -ENODEV;
 
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
@@ -1116,13 +1180,17 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 			   u8 *hfunc)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *ndev = ndc->nvdev;
-	struct rndis_device *rndis_dev = ndev->extension;
+	struct netvsc_device *ndev = rcu_dereference(ndc->nvdev);
+	struct rndis_device *rndis_dev;
 	int i;
 
+	if (!ndev)
+		return -ENODEV;
+
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */
 
+	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
 			indir[i] = rndis_dev->ind_table[i];
@@ -1138,13 +1206,17 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
 			   const u8 *key, const u8 hfunc)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *ndev = ndc->nvdev;
-	struct rndis_device *rndis_dev = ndev->extension;
+	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
+	struct rndis_device *rndis_dev;
 	int i;
 
+	if (!ndev)
+		return -ENODEV;
+
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
+	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
 			if (indir[i] >= dev->num_rx_queues)
@@ -1173,13 +1245,13 @@ static const struct ethtool_ops ethtool_ops = {
 	.get_channels   = netvsc_get_channels,
 	.set_channels   = netvsc_set_channels,
 	.get_ts_info	= ethtool_op_get_ts_info,
-	.get_settings	= netvsc_get_settings,
-	.set_settings	= netvsc_set_settings,
 	.get_rxnfc	= netvsc_get_rxnfc,
 	.get_rxfh_key_size = netvsc_get_rxfh_key_size,
 	.get_rxfh_indir_size = netvsc_rss_indir_size,
 	.get_rxfh	= netvsc_get_rxfh,
 	.set_rxfh	= netvsc_set_rxfh,
+	.get_link_ksettings = netvsc_get_link_ksettings,
+	.set_link_ksettings = netvsc_set_link_ksettings,
 };
 
 static const struct net_device_ops device_ops = {
@@ -1215,10 +1287,10 @@ static void netvsc_link_change(struct work_struct *w)
 	unsigned long flags, next_reconfig, delay;
 
 	rtnl_lock();
-	if (ndev_ctx->start_remove)
+	net_device = rtnl_dereference(ndev_ctx->nvdev);
+	if (!net_device)
 		goto out_unlock;
 
-	net_device = ndev_ctx->nvdev;
 	rdev = net_device->extension;
 
 	next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
@@ -1359,7 +1431,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
-	netvsc_dev = net_device_ctx->nvdev;
+	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
 		return NOTIFY_DONE;
 
@@ -1385,7 +1457,7 @@ static int netvsc_vf_up(struct net_device *vf_netdev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
-	netvsc_dev = net_device_ctx->nvdev;
+	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 
 	netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
 
@@ -1419,7 +1491,7 @@ static int netvsc_vf_down(struct net_device *vf_netdev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
-	netvsc_dev = net_device_ctx->nvdev;
+	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 
 	netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
 	netvsc_switch_datapath(ndev, false);
@@ -1479,8 +1551,6 @@ static int netvsc_probe(struct hv_device *dev,
 
 	hv_set_drvdata(dev, net);
 
-	net_device_ctx->start_remove = false;
-
 	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
 
@@ -1497,8 +1567,7 @@ static int netvsc_probe(struct hv_device *dev,
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
-	device_info.max_num_vrss_chns = min_t(u32, VRSS_CHANNEL_DEFAULT,
-					      num_online_cpus());
+	device_info.num_chn = VRSS_CHANNEL_DEFAULT;
 	ret = rndis_filter_device_add(dev, &device_info);
 	if (ret != 0) {
 		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
@@ -1514,6 +1583,7 @@ static int netvsc_probe(struct hv_device *dev,
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 	net->vlan_features = net->features;
 
+	/* RCU not necessary here, device not registered */
 	nvdev = net_device_ctx->nvdev;
 	netif_set_real_num_tx_queues(net, nvdev->num_chn);
 	netif_set_real_num_rx_queues(net, nvdev->num_chn);
@@ -1549,26 +1619,20 @@ static int netvsc_remove(struct hv_device *dev)
 
 	ndev_ctx = netdev_priv(net);
 
-	/* Avoid racing with netvsc_change_mtu()/netvsc_set_channels()
-	 * removing the device.
-	 */
-	rtnl_lock();
-	ndev_ctx->start_remove = true;
-	rtnl_unlock();
+	netif_device_detach(net);
 
 	cancel_delayed_work_sync(&ndev_ctx->dwork);
 	cancel_work_sync(&ndev_ctx->work);
 
-	/* Stop outbound asap */
-	netif_tx_disable(net);
-
-	unregister_netdev(net);
-
 	/*
 	 * Call to the vsc driver to let it know that the device is being
-	 * removed
+	 * removed. Also blocks mtu and channel changes.
 	 */
+	rtnl_lock();
 	rndis_filter_device_remove(dev, ndev_ctx->nvdev);
+	rtnl_unlock();
+
+	unregister_netdev(net);
 
 	hv_set_drvdata(dev, NULL);
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 19356f56b7b1..ab92c3c95951 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -819,16 +819,14 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
 {
 	struct rndis_request *request;
 	struct rndis_set_request *set;
-	struct rndis_set_complete *set_complete;
 	int ret;
 
 	request = get_rndis_request(dev, RNDIS_MSG_SET,
 			RNDIS_MESSAGE_SIZE(struct rndis_set_request) +
 			sizeof(u32));
-	if (!request) {
-		ret = -ENOMEM;
-		goto cleanup;
-	}
+	if (!request)
+		return -ENOMEM;
+
 
 	/* Setup the rndis set */
 	set = &request->request_msg.msg.set_req;
@@ -840,15 +838,11 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
 	       &new_filter, sizeof(u32));
 
 	ret = rndis_filter_send_request(dev, request);
-	if (ret != 0)
-		goto cleanup;
+	if (ret == 0)
+		wait_for_completion(&request->wait_event);
 
-	wait_for_completion(&request->wait_event);
+	put_rndis_request(dev, request);
 
-	set_complete = &request->response_msg.msg.set_complete;
-cleanup:
-	if (request)
-		put_rndis_request(dev, request);
 	return ret;
 }
 
@@ -926,8 +920,6 @@ static void rndis_filter_halt_device(struct rndis_device *dev)
 	struct rndis_halt_request *halt;
 	struct net_device_context *net_device_ctx = netdev_priv(dev->ndev);
 	struct netvsc_device *nvdev = net_device_ctx->nvdev;
-	struct hv_device *hdev = net_device_ctx->device_ctx;
-	ulong flags;
 
 	/* Attempt to do a rndis device halt */
 	request = get_rndis_request(dev, RNDIS_MSG_HALT,
@@ -945,9 +937,10 @@ static void rndis_filter_halt_device(struct rndis_device *dev)
 	dev->state = RNDIS_DEV_UNINITIALIZED;
 
 cleanup:
-	spin_lock_irqsave(&hdev->channel->inbound_lock, flags);
 	nvdev->destroy = true;
-	spin_unlock_irqrestore(&hdev->channel->inbound_lock, flags);
+
+	/* Force flag to be ordered before waiting */
+	wmb();
 
 	/* Wait for all send completions */
 	wait_event(nvdev->wait_drain, netvsc_device_idle(nvdev));
@@ -996,26 +989,38 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 		hv_get_drvdata(new_sc->primary_channel->device_obj);
 	struct netvsc_device *nvscdev = net_device_to_netvsc_device(ndev);
 	u16 chn_index = new_sc->offermsg.offer.sub_channel_index;
+	struct netvsc_channel *nvchan;
 	int ret;
-	unsigned long flags;
 
 	if (chn_index >= nvscdev->num_chn)
 		return;
 
-	nvscdev->chan_table[chn_index].mrc.buf
+	nvchan = nvscdev->chan_table + chn_index;
+	nvchan->mrc.buf
 		= vzalloc(NETVSC_RECVSLOT_MAX * sizeof(struct recv_comp_data));
 
+	if (!nvchan->mrc.buf)
+		return;
+
+	/* Because the device uses NAPI, all the interrupt batching and
+	 * control is done via Net softirq, not the channel handling
+	 */
+	set_channel_read_mode(new_sc, HV_CALL_ISR);
+
+	/* Set the channel before opening.*/
+	nvchan->channel = new_sc;
+	netif_napi_add(ndev, &nvchan->napi,
+		       netvsc_poll, NAPI_POLL_WEIGHT);
+
 	ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
 			 nvscdev->ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb, new_sc);
-
+			 netvsc_channel_cb, nvchan);
 	if (ret == 0)
-		nvscdev->chan_table[chn_index].channel = new_sc;
+		napi_enable(&nvchan->napi);
+	else
+		netdev_err(ndev, "sub channel open failed (%d)\n", ret);
 
-	spin_lock_irqsave(&nvscdev->sc_lock, flags);
-	nvscdev->num_sc_offered--;
-	spin_unlock_irqrestore(&nvscdev->sc_lock, flags);
-	if (nvscdev->num_sc_offered == 0)
+	if (refcount_dec_and_test(&nvscdev->sc_offered))
 		complete(&nvscdev->channel_init_wait);
 }
 
@@ -1032,12 +1037,9 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	unsigned int gso_max_size = GSO_MAX_SIZE;
-	u32 mtu, size;
-	u32 num_rss_qs;
-	u32 sc_delta;
+	u32 mtu, size, num_rss_qs;
 	const struct cpumask *node_cpu_mask;
 	u32 num_possible_rss_qs;
-	unsigned long flags;
 	int i, ret;
 
 	rndis_device = get_rndis_device();
@@ -1060,7 +1062,7 @@ int rndis_filter_device_add(struct hv_device *dev,
 	net_device->max_chn = 1;
 	net_device->num_chn = 1;
 
-	spin_lock_init(&net_device->sc_lock);
+	refcount_set(&net_device->sc_offered, 0);
 
 	net_device->extension = rndis_device;
 	rndis_device->ndev = net;
@@ -1174,34 +1176,30 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
-	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, rsscap.num_recv_que);
-
-	num_rss_qs = min(device_info->max_num_vrss_chns, net_device->max_chn);
-
 	/*
 	 * We will limit the VRSS channels to the number CPUs in the NUMA node
 	 * the primary channel is currently bound to.
+	 *
+	 * This also guarantees that num_possible_rss_qs <= num_online_cpus
 	 */
 	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
-	num_possible_rss_qs = cpumask_weight(node_cpu_mask);
+	num_possible_rss_qs = min_t(u32, cpumask_weight(node_cpu_mask),
+				    rsscap.num_recv_que);
 
-	/* We will use the given number of channels if available. */
-	if (device_info->num_chn && device_info->num_chn < net_device->max_chn)
-		net_device->num_chn = device_info->num_chn;
-	else
-		net_device->num_chn = min(num_possible_rss_qs, num_rss_qs);
+	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs);
 
-	num_rss_qs = net_device->num_chn - 1;
+	/* We will use the given number of channels if available. */
+	net_device->num_chn = min(net_device->max_chn, device_info->num_chn);
 
 	for (i = 0; i < ITAB_NUM; i++)
 		rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i,
 							net_device->num_chn);
 
-	net_device->num_sc_offered = num_rss_qs;
-
-	if (net_device->num_chn == 1)
-		goto out;
+	num_rss_qs = net_device->num_chn - 1;
+	if (num_rss_qs == 0)
+		return 0;
 
+	refcount_set(&net_device->sc_offered, num_rss_qs);
 	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
 
 	init_packet = &net_device->channel_init_pkt;
@@ -1217,32 +1215,23 @@ int rndis_filter_device_add(struct hv_device *dev,
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret)
 		goto out;
-	wait_for_completion(&net_device->channel_init_wait);
 
-	if (init_packet->msg.v5_msg.subchn_comp.status !=
-	    NVSP_STAT_SUCCESS) {
+	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
 		ret = -ENODEV;
 		goto out;
 	}
+	wait_for_completion(&net_device->channel_init_wait);
+
 	net_device->num_chn = 1 +
 		init_packet->msg.v5_msg.subchn_comp.num_subchannels;
 
-	ret = rndis_filter_set_rss_param(rndis_device, netvsc_hash_key,
-					 net_device->num_chn);
-
-	/*
-	 * Set the number of sub-channels to be received.
-	 */
-	spin_lock_irqsave(&net_device->sc_lock, flags);
-	sc_delta = num_rss_qs - (net_device->num_chn - 1);
-	net_device->num_sc_offered -= sc_delta;
-	spin_unlock_irqrestore(&net_device->sc_lock, flags);
-
+	/* ignore failues from setting rss parameters, still have channels */
+	rndis_filter_set_rss_param(rndis_device, netvsc_hash_key,
+				   net_device->num_chn);
 out:
 	if (ret) {
 		net_device->max_chn = 1;
 		net_device->num_chn = 1;
-		net_device->num_sc_offered = 0;
 	}
 
 	return 0; /* return 0 because primary channel can be used alone */
@@ -1257,12 +1246,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
 {
 	struct rndis_device *rndis_dev = net_dev->extension;
 
-	/* If not all subchannel offers are complete, wait for them until
-	 * completion to avoid race.
-	 */
-	if (net_dev->num_sc_offered > 0)
-		wait_for_completion(&net_dev->channel_init_wait);
-
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(rndis_dev);
 
diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig
index 3057a8df4ce9..303ba4133920 100644
--- a/drivers/net/ieee802154/Kconfig
+++ b/drivers/net/ieee802154/Kconfig
@@ -82,3 +82,25 @@ config IEEE802154_ADF7242
 
 	  This driver can also be built as a module. To do so, say M here.
 	  the module will be called 'adf7242'.
+
+config IEEE802154_CA8210
+	tristate "Cascoda CA8210 transceiver driver"
+	depends on IEEE802154_DRIVERS && MAC802154
+	depends on COMMON_CLK
+	depends on SPI
+	---help---
+	  Say Y here to enable the CA8210 SPI 802.15.4 wireless
+	  controller.
+
+	  This driver can also be built as a module. To do so, say M here.
+	  the module will be called 'ca8210'.
+
+config IEEE802154_CA8210_DEBUGFS
+	bool "CA8210 debugfs interface"
+	depends on IEEE802154_CA8210
+	depends on DEBUG_FS
+	---help---
+	  This option compiles debugfs code for the ca8210 driver. This
+	  exposes a debugfs node for each CA8210 instance which allows
+	  direct use of the Cascoda API, exposing the 802.15.4 MAC
+	  management entities.
diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile
index 3a923d339497..8374bb44a145 100644
--- a/drivers/net/ieee802154/Makefile
+++ b/drivers/net/ieee802154/Makefile
@@ -4,3 +4,4 @@ obj-$(CONFIG_IEEE802154_MRF24J40) += mrf24j40.o
 obj-$(CONFIG_IEEE802154_CC2520) += cc2520.o
 obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o
 obj-$(CONFIG_IEEE802154_ADF7242) += adf7242.o
+obj-$(CONFIG_IEEE802154_CA8210) += ca8210.o
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
new file mode 100644
index 000000000000..25fd3b04b3c0
--- /dev/null
+++ b/drivers/net/ieee802154/ca8210.c
@@ -0,0 +1,3242 @@
+/*
+ * http://www.cascoda.com/products/ca-821x/
+ * Copyright (c) 2016, Cascoda, Ltd.
+ * All rights reserved.
+ *
+ * This code is dual-licensed under both GPLv2 and 3-clause BSD. What follows is
+ * the license notice for both respectively.
+ *
+ *******************************************************************************
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ *******************************************************************************
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * 3. Neither the name of the copyright holder nor the names of its contributors
+ * may be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/cdev.h>
+#include <linux/clk-provider.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/ieee802154.h>
+#include <linux/kfifo.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/poll.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
+
+#include <net/ieee802154_netdev.h>
+#include <net/mac802154.h>
+
+#define DRIVER_NAME "ca8210"
+
+/* external clock frequencies */
+#define ONE_MHZ      1000000
+#define TWO_MHZ      (2 * ONE_MHZ)
+#define FOUR_MHZ     (4 * ONE_MHZ)
+#define EIGHT_MHZ    (8 * ONE_MHZ)
+#define SIXTEEN_MHZ  (16 * ONE_MHZ)
+
+/* spi constants */
+#define CA8210_SPI_BUF_SIZE 256
+#define CA8210_SYNC_TIMEOUT 1000     /* Timeout for synchronous commands [ms] */
+
+/* test interface constants */
+#define CA8210_TEST_INT_FILE_NAME "ca8210_test"
+#define CA8210_TEST_INT_FIFO_SIZE 256
+
+/* MAC status enumerations */
+#define MAC_SUCCESS                     (0x00)
+#define MAC_ERROR                       (0x01)
+#define MAC_CANCELLED                   (0x02)
+#define MAC_READY_FOR_POLL              (0x03)
+#define MAC_COUNTER_ERROR               (0xDB)
+#define MAC_IMPROPER_KEY_TYPE           (0xDC)
+#define MAC_IMPROPER_SECURITY_LEVEL     (0xDD)
+#define MAC_UNSUPPORTED_LEGACY          (0xDE)
+#define MAC_UNSUPPORTED_SECURITY        (0xDF)
+#define MAC_BEACON_LOST                 (0xE0)
+#define MAC_CHANNEL_ACCESS_FAILURE      (0xE1)
+#define MAC_DENIED                      (0xE2)
+#define MAC_DISABLE_TRX_FAILURE         (0xE3)
+#define MAC_SECURITY_ERROR              (0xE4)
+#define MAC_FRAME_TOO_LONG              (0xE5)
+#define MAC_INVALID_GTS                 (0xE6)
+#define MAC_INVALID_HANDLE              (0xE7)
+#define MAC_INVALID_PARAMETER           (0xE8)
+#define MAC_NO_ACK                      (0xE9)
+#define MAC_NO_BEACON                   (0xEA)
+#define MAC_NO_DATA                     (0xEB)
+#define MAC_NO_SHORT_ADDRESS            (0xEC)
+#define MAC_OUT_OF_CAP                  (0xED)
+#define MAC_PAN_ID_CONFLICT             (0xEE)
+#define MAC_REALIGNMENT                 (0xEF)
+#define MAC_TRANSACTION_EXPIRED         (0xF0)
+#define MAC_TRANSACTION_OVERFLOW        (0xF1)
+#define MAC_TX_ACTIVE                   (0xF2)
+#define MAC_UNAVAILABLE_KEY             (0xF3)
+#define MAC_UNSUPPORTED_ATTRIBUTE       (0xF4)
+#define MAC_INVALID_ADDRESS             (0xF5)
+#define MAC_ON_TIME_TOO_LONG            (0xF6)
+#define MAC_PAST_TIME                   (0xF7)
+#define MAC_TRACKING_OFF                (0xF8)
+#define MAC_INVALID_INDEX               (0xF9)
+#define MAC_LIMIT_REACHED               (0xFA)
+#define MAC_READ_ONLY                   (0xFB)
+#define MAC_SCAN_IN_PROGRESS            (0xFC)
+#define MAC_SUPERFRAME_OVERLAP          (0xFD)
+#define MAC_SYSTEM_ERROR                (0xFF)
+
+/* HWME attribute IDs */
+#define HWME_EDTHRESHOLD       (0x04)
+#define HWME_EDVALUE           (0x06)
+#define HWME_SYSCLKOUT         (0x0F)
+#define HWME_LQILIMIT          (0x11)
+
+/* TDME attribute IDs */
+#define TDME_CHANNEL          (0x00)
+#define TDME_ATM_CONFIG       (0x06)
+
+#define MAX_HWME_ATTRIBUTE_SIZE  16
+#define MAX_TDME_ATTRIBUTE_SIZE  2
+
+/* PHY/MAC PIB Attribute Enumerations */
+#define PHY_CURRENT_CHANNEL               (0x00)
+#define PHY_TRANSMIT_POWER                (0x02)
+#define PHY_CCA_MODE                      (0x03)
+#define MAC_ASSOCIATION_PERMIT            (0x41)
+#define MAC_AUTO_REQUEST                  (0x42)
+#define MAC_BATT_LIFE_EXT                 (0x43)
+#define MAC_BATT_LIFE_EXT_PERIODS         (0x44)
+#define MAC_BEACON_PAYLOAD                (0x45)
+#define MAC_BEACON_PAYLOAD_LENGTH         (0x46)
+#define MAC_BEACON_ORDER                  (0x47)
+#define MAC_GTS_PERMIT                    (0x4d)
+#define MAC_MAX_CSMA_BACKOFFS             (0x4e)
+#define MAC_MIN_BE                        (0x4f)
+#define MAC_PAN_ID                        (0x50)
+#define MAC_PROMISCUOUS_MODE              (0x51)
+#define MAC_RX_ON_WHEN_IDLE               (0x52)
+#define MAC_SHORT_ADDRESS                 (0x53)
+#define MAC_SUPERFRAME_ORDER              (0x54)
+#define MAC_ASSOCIATED_PAN_COORD          (0x56)
+#define MAC_MAX_BE                        (0x57)
+#define MAC_MAX_FRAME_RETRIES             (0x59)
+#define MAC_RESPONSE_WAIT_TIME            (0x5A)
+#define MAC_SECURITY_ENABLED              (0x5D)
+
+#define MAC_AUTO_REQUEST_SECURITY_LEVEL   (0x78)
+#define MAC_AUTO_REQUEST_KEY_ID_MODE      (0x79)
+
+#define NS_IEEE_ADDRESS                   (0xFF) /* Non-standard IEEE address */
+
+/* MAC Address Mode Definitions */
+#define MAC_MODE_NO_ADDR                (0x00)
+#define MAC_MODE_SHORT_ADDR             (0x02)
+#define MAC_MODE_LONG_ADDR              (0x03)
+
+/* MAC constants */
+#define MAX_BEACON_OVERHEAD        (75)
+#define MAX_BEACON_PAYLOAD_LENGTH  (IEEE802154_MTU - MAX_BEACON_OVERHEAD)
+
+#define MAX_ATTRIBUTE_SIZE              (122)
+#define MAX_DATA_SIZE                   (114)
+
+#define CA8210_VALID_CHANNELS                 (0x07FFF800)
+
+/* MAC workarounds for V1.1 and MPW silicon (V0.x) */
+#define CA8210_MAC_WORKAROUNDS (0)
+#define CA8210_MAC_MPW         (0)
+
+/* memory manipulation macros */
+#define LS_BYTE(x)     ((u8)((x) & 0xFF))
+#define MS_BYTE(x)     ((u8)(((x) >> 8) & 0xFF))
+
+/* message ID codes in SPI commands */
+/* downstream */
+#define MCPS_DATA_REQUEST                     (0x00)
+#define MLME_ASSOCIATE_REQUEST                (0x02)
+#define MLME_ASSOCIATE_RESPONSE               (0x03)
+#define MLME_DISASSOCIATE_REQUEST             (0x04)
+#define MLME_GET_REQUEST                      (0x05)
+#define MLME_ORPHAN_RESPONSE                  (0x06)
+#define MLME_RESET_REQUEST                    (0x07)
+#define MLME_RX_ENABLE_REQUEST                (0x08)
+#define MLME_SCAN_REQUEST                     (0x09)
+#define MLME_SET_REQUEST                      (0x0A)
+#define MLME_START_REQUEST                    (0x0B)
+#define MLME_POLL_REQUEST                     (0x0D)
+#define HWME_SET_REQUEST                      (0x0E)
+#define HWME_GET_REQUEST                      (0x0F)
+#define TDME_SETSFR_REQUEST                   (0x11)
+#define TDME_GETSFR_REQUEST                   (0x12)
+#define TDME_SET_REQUEST                      (0x14)
+/* upstream */
+#define MCPS_DATA_INDICATION                  (0x00)
+#define MCPS_DATA_CONFIRM                     (0x01)
+#define MLME_RESET_CONFIRM                    (0x0A)
+#define MLME_SET_CONFIRM                      (0x0E)
+#define MLME_START_CONFIRM                    (0x0F)
+#define HWME_SET_CONFIRM                      (0x12)
+#define HWME_GET_CONFIRM                      (0x13)
+#define HWME_WAKEUP_INDICATION		      (0x15)
+#define TDME_SETSFR_CONFIRM                   (0x17)
+
+/* SPI command IDs */
+/* bit indicating a confirm or indication from slave to master */
+#define SPI_S2M                            (0x20)
+/* bit indicating a synchronous message */
+#define SPI_SYN                            (0x40)
+
+/* SPI command definitions */
+#define SPI_IDLE                           (0xFF)
+#define SPI_NACK                           (0xF0)
+
+#define SPI_MCPS_DATA_REQUEST          (MCPS_DATA_REQUEST)
+#define SPI_MCPS_DATA_INDICATION       (MCPS_DATA_INDICATION + SPI_S2M)
+#define SPI_MCPS_DATA_CONFIRM          (MCPS_DATA_CONFIRM + SPI_S2M)
+
+#define SPI_MLME_ASSOCIATE_REQUEST     (MLME_ASSOCIATE_REQUEST)
+#define SPI_MLME_RESET_REQUEST         (MLME_RESET_REQUEST + SPI_SYN)
+#define SPI_MLME_SET_REQUEST           (MLME_SET_REQUEST + SPI_SYN)
+#define SPI_MLME_START_REQUEST         (MLME_START_REQUEST + SPI_SYN)
+#define SPI_MLME_RESET_CONFIRM         (MLME_RESET_CONFIRM + SPI_S2M + SPI_SYN)
+#define SPI_MLME_SET_CONFIRM           (MLME_SET_CONFIRM + SPI_S2M + SPI_SYN)
+#define SPI_MLME_START_CONFIRM         (MLME_START_CONFIRM + SPI_S2M + SPI_SYN)
+
+#define SPI_HWME_SET_REQUEST           (HWME_SET_REQUEST + SPI_SYN)
+#define SPI_HWME_GET_REQUEST           (HWME_GET_REQUEST + SPI_SYN)
+#define SPI_HWME_SET_CONFIRM           (HWME_SET_CONFIRM + SPI_S2M + SPI_SYN)
+#define SPI_HWME_GET_CONFIRM           (HWME_GET_CONFIRM + SPI_S2M + SPI_SYN)
+#define SPI_HWME_WAKEUP_INDICATION     (HWME_WAKEUP_INDICATION + SPI_S2M)
+
+#define SPI_TDME_SETSFR_REQUEST        (TDME_SETSFR_REQUEST + SPI_SYN)
+#define SPI_TDME_SET_REQUEST           (TDME_SET_REQUEST + SPI_SYN)
+#define SPI_TDME_SETSFR_CONFIRM        (TDME_SETSFR_CONFIRM + SPI_S2M + SPI_SYN)
+
+/* TDME SFR addresses */
+/* Page 0 */
+#define CA8210_SFR_PACFG                   (0xB1)
+#define CA8210_SFR_MACCON                  (0xD8)
+#define CA8210_SFR_PACFGIB                 (0xFE)
+/* Page 1 */
+#define CA8210_SFR_LOTXCAL                 (0xBF)
+#define CA8210_SFR_PTHRH                   (0xD1)
+#define CA8210_SFR_PRECFG                  (0xD3)
+#define CA8210_SFR_LNAGX40                 (0xE1)
+#define CA8210_SFR_LNAGX41                 (0xE2)
+#define CA8210_SFR_LNAGX42                 (0xE3)
+#define CA8210_SFR_LNAGX43                 (0xE4)
+#define CA8210_SFR_LNAGX44                 (0xE5)
+#define CA8210_SFR_LNAGX45                 (0xE6)
+#define CA8210_SFR_LNAGX46                 (0xE7)
+#define CA8210_SFR_LNAGX47                 (0xE9)
+
+#define PACFGIB_DEFAULT_CURRENT            (0x3F)
+#define PTHRH_DEFAULT_THRESHOLD            (0x5A)
+#define LNAGX40_DEFAULT_GAIN               (0x29) /* 10dB */
+#define LNAGX41_DEFAULT_GAIN               (0x54) /* 21dB */
+#define LNAGX42_DEFAULT_GAIN               (0x6C) /* 27dB */
+#define LNAGX43_DEFAULT_GAIN               (0x7A) /* 30dB */
+#define LNAGX44_DEFAULT_GAIN               (0x84) /* 33dB */
+#define LNAGX45_DEFAULT_GAIN               (0x8B) /* 34dB */
+#define LNAGX46_DEFAULT_GAIN               (0x92) /* 36dB */
+#define LNAGX47_DEFAULT_GAIN               (0x96) /* 37dB */
+
+#define CA8210_IOCTL_HARD_RESET            (0x00)
+
+/* Structs/Enums */
+
+/**
+ * struct cas_control - spi transfer structure
+ * @msg:                  spi_message for each exchange
+ * @transfer:             spi_transfer for each exchange
+ * @tx_buf:               source array for transmission
+ * @tx_in_buf:            array storing bytes received during transmission
+ * @priv:                 pointer to private data
+ *
+ * This structure stores all the necessary data passed around during a single
+ * spi exchange.
+ */
+struct cas_control {
+	struct spi_message msg;
+	struct spi_transfer transfer;
+
+	u8 tx_buf[CA8210_SPI_BUF_SIZE];
+	u8 tx_in_buf[CA8210_SPI_BUF_SIZE];
+
+	struct ca8210_priv *priv;
+};
+
+/**
+ * struct ca8210_test - ca8210 test interface structure
+ * @ca8210_dfs_spi_int: pointer to the entry in the debug fs for this device
+ * @up_fifo:            fifo for upstream messages
+ *
+ * This structure stores all the data pertaining to the debug interface
+ */
+struct ca8210_test {
+	struct dentry *ca8210_dfs_spi_int;
+	struct kfifo up_fifo;
+	wait_queue_head_t readq;
+};
+
+/**
+ * struct ca8210_priv - ca8210 private data structure
+ * @spi:                    pointer to the ca8210 spi device object
+ * @hw:                     pointer to the ca8210 ieee802154_hw object
+ * @hw_registered:          true if hw has been registered with ieee802154
+ * @lock:                   spinlock protecting the private data area
+ * @mlme_workqueue:           workqueue for triggering MLME Reset
+ * @irq_workqueue:          workqueue for irq processing
+ * @tx_skb:                 current socket buffer to transmit
+ * @nextmsduhandle:         msdu handle to pass to the 15.4 MAC layer for the
+ *                           next transmission
+ * @clk:                    external clock provided by the ca8210
+ * @last_dsn:               sequence number of last data packet received, for
+ *                           resend detection
+ * @test:                   test interface data section for this instance
+ * @async_tx_pending:       true if an asynchronous transmission was started and
+ *                           is not complete
+ * @sync_command_response:  pointer to buffer to fill with sync response
+ * @ca8210_is_awake:        nonzero if ca8210 is initialised, ready for comms
+ * @sync_down:              counts number of downstream synchronous commands
+ * @sync_up:                counts number of upstream synchronous commands
+ * @spi_transfer_complete   completion object for a single spi_transfer
+ * @sync_exchange_complete  completion object for a complete synchronous API
+ *                           exchange
+ * @promiscuous             whether the ca8210 is in promiscuous mode or not
+ * @retries:                records how many times the current pending spi
+ *                           transfer has been retried
+ */
+struct ca8210_priv {
+	struct spi_device *spi;
+	struct ieee802154_hw *hw;
+	bool hw_registered;
+	spinlock_t lock;
+	struct workqueue_struct *mlme_workqueue;
+	struct workqueue_struct *irq_workqueue;
+	struct sk_buff *tx_skb;
+	u8 nextmsduhandle;
+	struct clk *clk;
+	int last_dsn;
+	struct ca8210_test test;
+	bool async_tx_pending;
+	u8 *sync_command_response;
+	struct completion ca8210_is_awake;
+	int sync_down, sync_up;
+	struct completion spi_transfer_complete, sync_exchange_complete;
+	bool promiscuous;
+	int retries;
+};
+
+/**
+ * struct work_priv_container - link between a work object and the relevant
+ *                              device's private data
+ * @work: work object being executed
+ * @priv: device's private data section
+ *
+ */
+struct work_priv_container {
+	struct work_struct work;
+	struct ca8210_priv *priv;
+};
+
+/**
+ * struct ca8210_platform_data - ca8210 platform data structure
+ * @extclockenable: true if the external clock is to be enabled
+ * @extclockfreq:   frequency of the external clock
+ * @extclockgpio:   ca8210 output gpio of the external clock
+ * @gpio_reset:     gpio number of ca8210 reset line
+ * @gpio_irq:       gpio number of ca8210 interrupt line
+ * @irq_id:         identifier for the ca8210 irq
+ *
+ */
+struct ca8210_platform_data {
+	bool extclockenable;
+	unsigned int extclockfreq;
+	unsigned int extclockgpio;
+	int gpio_reset;
+	int gpio_irq;
+	int irq_id;
+};
+
+/**
+ * struct fulladdr - full MAC addressing information structure
+ * @mode:    address mode (none, short, extended)
+ * @pan_id:  16-bit LE pan id
+ * @address: LE address, variable length as specified by mode
+ *
+ */
+struct fulladdr {
+	u8         mode;
+	u8         pan_id[2];
+	u8         address[8];
+};
+
+/**
+ * union macaddr: generic MAC address container
+ * @short_addr:   16-bit short address
+ * @ieee_address: 64-bit extended address as LE byte array
+ *
+ */
+union macaddr {
+	u16        short_address;
+	u8         ieee_address[8];
+};
+
+/**
+ * struct secspec: security specification for SAP commands
+ * @security_level: 0-7, controls level of authentication & encryption
+ * @key_id_mode:    0-3, specifies how to obtain key
+ * @key_source:     extended key retrieval data
+ * @key_index:      single-byte key identifier
+ *
+ */
+struct secspec {
+	u8         security_level;
+	u8         key_id_mode;
+	u8         key_source[8];
+	u8         key_index;
+};
+
+/* downlink functions parameter set definitions */
+struct mcps_data_request_pset {
+	u8              src_addr_mode;
+	struct fulladdr dst;
+	u8              msdu_length;
+	u8              msdu_handle;
+	u8              tx_options;
+	u8              msdu[MAX_DATA_SIZE];
+};
+
+struct mlme_set_request_pset {
+	u8         pib_attribute;
+	u8         pib_attribute_index;
+	u8         pib_attribute_length;
+	u8         pib_attribute_value[MAX_ATTRIBUTE_SIZE];
+};
+
+struct hwme_set_request_pset {
+	u8         hw_attribute;
+	u8         hw_attribute_length;
+	u8         hw_attribute_value[MAX_HWME_ATTRIBUTE_SIZE];
+};
+
+struct hwme_get_request_pset {
+	u8         hw_attribute;
+};
+
+struct tdme_setsfr_request_pset {
+	u8         sfr_page;
+	u8         sfr_address;
+	u8         sfr_value;
+};
+
+/* uplink functions parameter set definitions */
+struct hwme_set_confirm_pset {
+	u8         status;
+	u8         hw_attribute;
+};
+
+struct hwme_get_confirm_pset {
+	u8         status;
+	u8         hw_attribute;
+	u8         hw_attribute_length;
+	u8         hw_attribute_value[MAX_HWME_ATTRIBUTE_SIZE];
+};
+
+struct tdme_setsfr_confirm_pset {
+	u8         status;
+	u8         sfr_page;
+	u8         sfr_address;
+};
+
+struct mac_message {
+	u8      command_id;
+	u8      length;
+	union {
+		struct mcps_data_request_pset       data_req;
+		struct mlme_set_request_pset        set_req;
+		struct hwme_set_request_pset        hwme_set_req;
+		struct hwme_get_request_pset        hwme_get_req;
+		struct tdme_setsfr_request_pset     tdme_set_sfr_req;
+		struct hwme_set_confirm_pset        hwme_set_cnf;
+		struct hwme_get_confirm_pset        hwme_get_cnf;
+		struct tdme_setsfr_confirm_pset     tdme_set_sfr_cnf;
+		u8                                  u8param;
+		u8                                  status;
+		u8                                  payload[148];
+	} pdata;
+};
+
+union pa_cfg_sfr {
+	struct {
+		u8 bias_current_trim     : 3;
+		u8 /* reserved */        : 1;
+		u8 buffer_capacitor_trim : 3;
+		u8 boost                 : 1;
+	};
+	u8 paib;
+};
+
+struct preamble_cfg_sfr {
+	u8 timeout_symbols      : 3;
+	u8 acquisition_symbols  : 3;
+	u8 search_symbols       : 2;
+};
+
+static int (*cascoda_api_upstream)(
+	const u8 *buf,
+	size_t len,
+	void *device_ref
+);
+
+/**
+ * link_to_linux_err() - Translates an 802.15.4 return code into the closest
+ *                       linux error
+ * @link_status:  802.15.4 status code
+ *
+ * Return: 0 or Linux error code
+ */
+static int link_to_linux_err(int link_status)
+{
+	if (link_status < 0) {
+		/* status is already a Linux code */
+		return link_status;
+	}
+	switch (link_status) {
+	case MAC_SUCCESS:
+	case MAC_REALIGNMENT:
+		return 0;
+	case MAC_IMPROPER_KEY_TYPE:
+		return -EKEYREJECTED;
+	case MAC_IMPROPER_SECURITY_LEVEL:
+	case MAC_UNSUPPORTED_LEGACY:
+	case MAC_DENIED:
+		return -EACCES;
+	case MAC_BEACON_LOST:
+	case MAC_NO_ACK:
+	case MAC_NO_BEACON:
+		return -ENETUNREACH;
+	case MAC_CHANNEL_ACCESS_FAILURE:
+	case MAC_TX_ACTIVE:
+	case MAC_SCAN_IN_PROGRESS:
+		return -EBUSY;
+	case MAC_DISABLE_TRX_FAILURE:
+	case MAC_OUT_OF_CAP:
+		return -EAGAIN;
+	case MAC_FRAME_TOO_LONG:
+		return -EMSGSIZE;
+	case MAC_INVALID_GTS:
+	case MAC_PAST_TIME:
+		return -EBADSLT;
+	case MAC_INVALID_HANDLE:
+		return -EBADMSG;
+	case MAC_INVALID_PARAMETER:
+	case MAC_UNSUPPORTED_ATTRIBUTE:
+	case MAC_ON_TIME_TOO_LONG:
+	case MAC_INVALID_INDEX:
+		return -EINVAL;
+	case MAC_NO_DATA:
+		return -ENODATA;
+	case MAC_NO_SHORT_ADDRESS:
+		return -EFAULT;
+	case MAC_PAN_ID_CONFLICT:
+		return -EADDRINUSE;
+	case MAC_TRANSACTION_EXPIRED:
+		return -ETIME;
+	case MAC_TRANSACTION_OVERFLOW:
+		return -ENOBUFS;
+	case MAC_UNAVAILABLE_KEY:
+		return -ENOKEY;
+	case MAC_INVALID_ADDRESS:
+		return -ENXIO;
+	case MAC_TRACKING_OFF:
+	case MAC_SUPERFRAME_OVERLAP:
+		return -EREMOTEIO;
+	case MAC_LIMIT_REACHED:
+		return -EDQUOT;
+	case MAC_READ_ONLY:
+		return -EROFS;
+	default:
+		return -EPROTO;
+	}
+}
+
+/**
+ * ca8210_test_int_driver_write() - Writes a message to the test interface to be
+ *                                  read by the userspace
+ * @buf:  Buffer containing upstream message
+ * @len:  length of message to write
+ * @spi:  SPI device of message originator
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_test_int_driver_write(
+	const u8       *buf,
+	size_t          len,
+	void           *spi
+)
+{
+	struct ca8210_priv *priv = spi_get_drvdata(spi);
+	struct ca8210_test *test = &priv->test;
+	char *fifo_buffer;
+	int i;
+
+	dev_dbg(
+		&priv->spi->dev,
+		"test_interface: Buffering upstream message:\n"
+	);
+	for (i = 0; i < len; i++)
+		dev_dbg(&priv->spi->dev, "%#03x\n", buf[i]);
+
+	fifo_buffer = kmalloc(len, GFP_KERNEL);
+	if (!fifo_buffer)
+		return -ENOMEM;
+	memcpy(fifo_buffer, buf, len);
+	kfifo_in(&test->up_fifo, &fifo_buffer, 4);
+	wake_up_interruptible(&priv->test.readq);
+
+	return 0;
+}
+
+/* SPI Operation */
+
+static int ca8210_net_rx(
+	struct ieee802154_hw  *hw,
+	u8                    *command,
+	size_t                 len
+);
+static u8 mlme_reset_request_sync(
+	u8       set_default_pib,
+	void    *device_ref
+);
+static int ca8210_spi_transfer(
+	struct spi_device *spi,
+	const u8          *buf,
+	size_t             len
+);
+
+/**
+ * ca8210_reset_send() - Hard resets the ca8210 for a given time
+ * @spi:  Pointer to target ca8210 spi device
+ * @ms:   Milliseconds to hold the reset line low for
+ */
+static void ca8210_reset_send(struct spi_device *spi, unsigned int ms)
+{
+	struct ca8210_platform_data *pdata = spi->dev.platform_data;
+	struct ca8210_priv *priv = spi_get_drvdata(spi);
+	long status;
+
+	gpio_set_value(pdata->gpio_reset, 0);
+	reinit_completion(&priv->ca8210_is_awake);
+	msleep(ms);
+	gpio_set_value(pdata->gpio_reset, 1);
+	priv->promiscuous = false;
+
+	/* Wait until wakeup indication seen */
+	status = wait_for_completion_interruptible_timeout(
+		&priv->ca8210_is_awake,
+		msecs_to_jiffies(CA8210_SYNC_TIMEOUT)
+	);
+	if (status == 0) {
+		dev_crit(
+			&spi->dev,
+			"Fatal: No wakeup from ca8210 after reset!\n"
+		);
+	}
+
+	dev_dbg(&spi->dev, "Reset the device\n");
+}
+
+/**
+ * ca8210_mlme_reset_worker() - Resets the MLME, Called when the MAC OVERFLOW
+ *                              condition happens.
+ * @work:  Pointer to work being executed
+ */
+static void ca8210_mlme_reset_worker(struct work_struct *work)
+{
+	struct work_priv_container *wpc = container_of(
+		work,
+		struct work_priv_container,
+		work
+	);
+	struct ca8210_priv *priv = wpc->priv;
+
+	mlme_reset_request_sync(0, priv->spi);
+	kfree(wpc);
+}
+
+/**
+ * ca8210_rx_done() - Calls various message dispatches responding to a received
+ *                    command
+ * @arg:  Pointer to the cas_control object for the relevant spi transfer
+ *
+ * Presents a received SAP command from the ca8210 to the Cascoda EVBME, test
+ * interface and network driver.
+ */
+static void ca8210_rx_done(struct cas_control *cas_ctl)
+{
+	u8 *buf;
+	u8 len;
+	struct work_priv_container *mlme_reset_wpc;
+	struct ca8210_priv *priv = cas_ctl->priv;
+
+	buf = cas_ctl->tx_in_buf;
+	len = buf[1] + 2;
+	if (len > CA8210_SPI_BUF_SIZE) {
+		dev_crit(
+			&priv->spi->dev,
+			"Received packet len (%d) erroneously long\n",
+			len
+		);
+		goto finish;
+	}
+
+	if (buf[0] & SPI_SYN) {
+		if (priv->sync_command_response) {
+			memcpy(priv->sync_command_response, buf, len);
+			complete(&priv->sync_exchange_complete);
+		} else {
+			if (cascoda_api_upstream)
+				cascoda_api_upstream(buf, len, priv->spi);
+			priv->sync_up++;
+		}
+	} else {
+		if (cascoda_api_upstream)
+			cascoda_api_upstream(buf, len, priv->spi);
+	}
+
+	ca8210_net_rx(priv->hw, buf, len);
+	if (buf[0] == SPI_MCPS_DATA_CONFIRM) {
+		if (buf[3] == MAC_TRANSACTION_OVERFLOW) {
+			dev_info(
+				&priv->spi->dev,
+				"Waiting for transaction overflow to stabilise...\n");
+			msleep(2000);
+			dev_info(
+				&priv->spi->dev,
+				"Resetting MAC...\n");
+
+			mlme_reset_wpc = kmalloc(sizeof(*mlme_reset_wpc),
+						 GFP_KERNEL);
+			if (!mlme_reset_wpc)
+				goto finish;
+			INIT_WORK(
+				&mlme_reset_wpc->work,
+				ca8210_mlme_reset_worker
+			);
+			mlme_reset_wpc->priv = priv;
+			queue_work(priv->mlme_workqueue, &mlme_reset_wpc->work);
+		}
+	} else if (buf[0] == SPI_HWME_WAKEUP_INDICATION) {
+		dev_notice(
+			&priv->spi->dev,
+			"Wakeup indication received, reason:\n"
+		);
+		switch (buf[2]) {
+		case 0:
+			dev_notice(
+				&priv->spi->dev,
+				"Transceiver woken up from Power Up / System Reset\n"
+			);
+			break;
+		case 1:
+			dev_notice(
+				&priv->spi->dev,
+				"Watchdog Timer Time-Out\n"
+			);
+			break;
+		case 2:
+			dev_notice(
+				&priv->spi->dev,
+				"Transceiver woken up from Power-Off by Sleep Timer Time-Out\n");
+			break;
+		case 3:
+			dev_notice(
+				&priv->spi->dev,
+				"Transceiver woken up from Power-Off by GPIO Activity\n"
+			);
+			break;
+		case 4:
+			dev_notice(
+				&priv->spi->dev,
+				"Transceiver woken up from Standby by Sleep Timer Time-Out\n"
+			);
+			break;
+		case 5:
+			dev_notice(
+				&priv->spi->dev,
+				"Transceiver woken up from Standby by GPIO Activity\n"
+			);
+			break;
+		case 6:
+			dev_notice(
+				&priv->spi->dev,
+				"Sleep-Timer Time-Out in Active Mode\n"
+			);
+			break;
+		default:
+			dev_warn(&priv->spi->dev, "Wakeup reason unknown\n");
+			break;
+		}
+		complete(&priv->ca8210_is_awake);
+	}
+
+finish:;
+}
+
+static int ca8210_remove(struct spi_device *spi_device);
+
+/**
+ * ca8210_spi_transfer_complete() - Called when a single spi transfer has
+ *                                  completed
+ * @context:  Pointer to the cas_control object for the finished transfer
+ */
+static void ca8210_spi_transfer_complete(void *context)
+{
+	struct cas_control *cas_ctl = context;
+	struct ca8210_priv *priv = cas_ctl->priv;
+	bool duplex_rx = false;
+	int i;
+	u8 retry_buffer[CA8210_SPI_BUF_SIZE];
+
+	if (
+		cas_ctl->tx_in_buf[0] == SPI_NACK ||
+		(cas_ctl->tx_in_buf[0] == SPI_IDLE &&
+		cas_ctl->tx_in_buf[1] == SPI_NACK)
+	) {
+		/* ca8210 is busy */
+		dev_info(&priv->spi->dev, "ca8210 was busy during attempted write\n");
+		if (cas_ctl->tx_buf[0] == SPI_IDLE) {
+			dev_warn(
+				&priv->spi->dev,
+				"IRQ servicing NACKd, dropping transfer\n"
+			);
+			kfree(cas_ctl);
+			return;
+		}
+		if (priv->retries > 3) {
+			dev_err(&priv->spi->dev, "too many retries!\n");
+			kfree(cas_ctl);
+			ca8210_remove(priv->spi);
+			return;
+		}
+		memcpy(retry_buffer, cas_ctl->tx_buf, CA8210_SPI_BUF_SIZE);
+		kfree(cas_ctl);
+		ca8210_spi_transfer(
+			priv->spi,
+			retry_buffer,
+			CA8210_SPI_BUF_SIZE
+		);
+		priv->retries++;
+		dev_info(&priv->spi->dev, "retried spi write\n");
+		return;
+	} else if (
+			cas_ctl->tx_in_buf[0] != SPI_IDLE &&
+			cas_ctl->tx_in_buf[0] != SPI_NACK
+		) {
+		duplex_rx = true;
+	}
+
+	if (duplex_rx) {
+		dev_dbg(&priv->spi->dev, "READ CMD DURING TX\n");
+		for (i = 0; i < cas_ctl->tx_in_buf[1] + 2; i++)
+			dev_dbg(
+				&priv->spi->dev,
+				"%#03x\n",
+				cas_ctl->tx_in_buf[i]
+			);
+		ca8210_rx_done(cas_ctl);
+	}
+	complete(&priv->spi_transfer_complete);
+	kfree(cas_ctl);
+	priv->retries = 0;
+}
+
+/**
+ * ca8210_spi_transfer() - Initiate duplex spi transfer with ca8210
+ * @spi: Pointer to spi device for transfer
+ * @buf: Octet array to send
+ * @len: length of the buffer being sent
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_spi_transfer(
+	struct spi_device  *spi,
+	const u8           *buf,
+	size_t              len
+)
+{
+	int i, status = 0;
+	struct ca8210_priv *priv = spi_get_drvdata(spi);
+	struct cas_control *cas_ctl;
+
+	if (!spi) {
+		dev_crit(
+			&spi->dev,
+			"NULL spi device passed to ca8210_spi_transfer\n"
+		);
+		return -ENODEV;
+	}
+
+	reinit_completion(&priv->spi_transfer_complete);
+
+	dev_dbg(&spi->dev, "ca8210_spi_transfer called\n");
+
+	cas_ctl = kmalloc(sizeof(*cas_ctl), GFP_ATOMIC);
+	if (!cas_ctl)
+		return -ENOMEM;
+
+	cas_ctl->priv = priv;
+	memset(cas_ctl->tx_buf, SPI_IDLE, CA8210_SPI_BUF_SIZE);
+	memset(cas_ctl->tx_in_buf, SPI_IDLE, CA8210_SPI_BUF_SIZE);
+	memcpy(cas_ctl->tx_buf, buf, len);
+
+	for (i = 0; i < len; i++)
+		dev_dbg(&spi->dev, "%#03x\n", cas_ctl->tx_buf[i]);
+
+	spi_message_init(&cas_ctl->msg);
+
+	cas_ctl->transfer.tx_nbits = 1; /* 1 MOSI line */
+	cas_ctl->transfer.rx_nbits = 1; /* 1 MISO line */
+	cas_ctl->transfer.speed_hz = 0; /* Use device setting */
+	cas_ctl->transfer.bits_per_word = 0; /* Use device setting */
+	cas_ctl->transfer.tx_buf = cas_ctl->tx_buf;
+	cas_ctl->transfer.rx_buf = cas_ctl->tx_in_buf;
+	cas_ctl->transfer.delay_usecs = 0;
+	cas_ctl->transfer.cs_change = 0;
+	cas_ctl->transfer.len = sizeof(struct mac_message);
+	cas_ctl->msg.complete = ca8210_spi_transfer_complete;
+	cas_ctl->msg.context = cas_ctl;
+
+	spi_message_add_tail(
+		&cas_ctl->transfer,
+		&cas_ctl->msg
+	);
+
+	status = spi_async(spi, &cas_ctl->msg);
+	if (status < 0) {
+		dev_crit(
+			&spi->dev,
+			"status %d from spi_sync in write\n",
+			status
+		);
+	}
+
+	return status;
+}
+
+/**
+ * ca8210_spi_exchange() - Exchange API/SAP commands with the radio
+ * @buf:         Octet array of command being sent downstream
+ * @len:         length of buf
+ * @response:    buffer for storing synchronous response
+ * @device_ref:  spi_device pointer for ca8210
+ *
+ * Effectively calls ca8210_spi_transfer to write buf[] to the spi, then for
+ * synchronous commands waits for the corresponding response to be read from
+ * the spi before returning. The response is written to the response parameter.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_spi_exchange(
+	const u8 *buf,
+	size_t len,
+	u8 *response,
+	void *device_ref
+)
+{
+	int status = 0;
+	struct spi_device *spi = device_ref;
+	struct ca8210_priv *priv = spi->dev.driver_data;
+	long wait_remaining;
+
+	if ((buf[0] & SPI_SYN) && response) { /* if sync wait for confirm */
+		reinit_completion(&priv->sync_exchange_complete);
+		priv->sync_command_response = response;
+	}
+
+	do {
+		reinit_completion(&priv->spi_transfer_complete);
+		status = ca8210_spi_transfer(priv->spi, buf, len);
+		if (status) {
+			dev_warn(
+				&spi->dev,
+				"spi write failed, returned %d\n",
+				status
+			);
+			if (status == -EBUSY)
+				continue;
+			if (((buf[0] & SPI_SYN) && response))
+				complete(&priv->sync_exchange_complete);
+			goto cleanup;
+		}
+
+		wait_remaining = wait_for_completion_interruptible_timeout(
+			&priv->spi_transfer_complete,
+			msecs_to_jiffies(1000)
+		);
+		if (wait_remaining == -ERESTARTSYS) {
+			status = -ERESTARTSYS;
+		} else if (wait_remaining == 0) {
+			dev_err(
+				&spi->dev,
+				"SPI downstream transfer timed out!\n"
+			);
+			status = -ETIME;
+			goto cleanup;
+		}
+	} while (status < 0);
+
+	if (!((buf[0] & SPI_SYN) && response))
+		goto cleanup;
+
+	wait_remaining = wait_for_completion_interruptible_timeout(
+		&priv->sync_exchange_complete,
+		msecs_to_jiffies(CA8210_SYNC_TIMEOUT)
+	);
+	if (wait_remaining == -ERESTARTSYS) {
+		status = -ERESTARTSYS;
+	} else if (wait_remaining == 0) {
+		dev_err(
+			&spi->dev,
+			"Synchronous confirm timeout\n"
+		);
+		status = -ETIME;
+	}
+
+cleanup:
+	priv->sync_command_response = NULL;
+	return status;
+}
+
+/**
+ * ca8210_interrupt_handler() - Called when an irq is received from the ca8210
+ * @irq:     Id of the irq being handled
+ * @dev_id:  Pointer passed by the system, pointing to the ca8210's private data
+ *
+ * This function is called when the irq line from the ca8210 is asserted,
+ * signifying that the ca8210 has a message to send upstream to us. Starts the
+ * asynchronous spi read.
+ *
+ * Return: irq return code
+ */
+static irqreturn_t ca8210_interrupt_handler(int irq, void *dev_id)
+{
+	struct ca8210_priv *priv = dev_id;
+	int status;
+
+	dev_dbg(&priv->spi->dev, "irq: Interrupt occurred\n");
+	do {
+		status = ca8210_spi_transfer(priv->spi, NULL, 0);
+		if (status && (status != -EBUSY)) {
+			dev_warn(
+				&priv->spi->dev,
+				"spi read failed, returned %d\n",
+				status
+			);
+		}
+	} while (status == -EBUSY);
+	return IRQ_HANDLED;
+}
+
+static int (*cascoda_api_downstream)(
+	const u8 *buf,
+	size_t len,
+	u8 *response,
+	void *device_ref
+) = ca8210_spi_exchange;
+
+/* Cascoda API / 15.4 SAP Primitives */
+
+/**
+ * tdme_setsfr_request_sync() - TDME_SETSFR_request/confirm according to API
+ * @sfr_page:    SFR Page
+ * @sfr_address: SFR Address
+ * @sfr_value:   SFR Value
+ * @device_ref:  Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of TDME-SETSFR.confirm
+ */
+static u8 tdme_setsfr_request_sync(
+	u8            sfr_page,
+	u8            sfr_address,
+	u8            sfr_value,
+	void         *device_ref
+)
+{
+	int ret;
+	struct mac_message command, response;
+	struct spi_device *spi = device_ref;
+
+	command.command_id = SPI_TDME_SETSFR_REQUEST;
+	command.length = 3;
+	command.pdata.tdme_set_sfr_req.sfr_page    = sfr_page;
+	command.pdata.tdme_set_sfr_req.sfr_address = sfr_address;
+	command.pdata.tdme_set_sfr_req.sfr_value   = sfr_value;
+	response.command_id = SPI_IDLE;
+	ret = cascoda_api_downstream(
+		&command.command_id,
+		command.length + 2,
+		&response.command_id,
+		device_ref
+	);
+	if (ret) {
+		dev_crit(&spi->dev, "cascoda_api_downstream returned %d", ret);
+		return MAC_SYSTEM_ERROR;
+	}
+
+	if (response.command_id != SPI_TDME_SETSFR_CONFIRM) {
+		dev_crit(
+			&spi->dev,
+			"sync response to SPI_TDME_SETSFR_REQUEST was not SPI_TDME_SETSFR_CONFIRM, it was %d\n",
+			response.command_id
+		);
+		return MAC_SYSTEM_ERROR;
+	}
+
+	return response.pdata.tdme_set_sfr_cnf.status;
+}
+
+/**
+ * tdme_chipinit() - TDME Chip Register Default Initialisation Macro
+ * @device_ref: Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of API calls
+ */
+static u8 tdme_chipinit(void *device_ref)
+{
+	u8 status = MAC_SUCCESS;
+	u8 sfr_address;
+	struct spi_device *spi = device_ref;
+	struct preamble_cfg_sfr pre_cfg_value = {
+		.timeout_symbols     = 3,
+		.acquisition_symbols = 3,
+		.search_symbols      = 1,
+	};
+	/* LNA Gain Settings */
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX40),
+		LNAGX40_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX41),
+		LNAGX41_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX42),
+		LNAGX42_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX43),
+		LNAGX43_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX44),
+		LNAGX44_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX45),
+		LNAGX45_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX46),
+		LNAGX46_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_LNAGX47),
+		LNAGX47_DEFAULT_GAIN, device_ref);
+	if (status)
+		goto finish;
+	/* Preamble Timing Config */
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_PRECFG),
+		*((u8 *)&pre_cfg_value), device_ref);
+	if (status)
+		goto finish;
+	/* Preamble Threshold High */
+	status = tdme_setsfr_request_sync(
+		1, (sfr_address = CA8210_SFR_PTHRH),
+		PTHRH_DEFAULT_THRESHOLD, device_ref);
+	if (status)
+		goto finish;
+	/* Tx Output Power 8 dBm */
+	status = tdme_setsfr_request_sync(
+		0, (sfr_address = CA8210_SFR_PACFGIB),
+		PACFGIB_DEFAULT_CURRENT, device_ref);
+	if (status)
+		goto finish;
+
+finish:
+	if (status != MAC_SUCCESS) {
+		dev_err(
+			&spi->dev,
+			"failed to set sfr at %#03x, status = %#03x\n",
+			sfr_address,
+			status
+		);
+	}
+	return status;
+}
+
+/**
+ * tdme_channelinit() - TDME Channel Register Default Initialisation Macro (Tx)
+ * @channel:    802.15.4 channel to initialise chip for
+ * @device_ref: Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of API calls
+ */
+static u8 tdme_channelinit(u8 channel, void *device_ref)
+{
+	/* Transceiver front-end local oscillator tx two-point calibration
+	 * value. Tuned for the hardware.
+	 */
+	u8 txcalval;
+
+	if (channel >= 25)
+		txcalval = 0xA7;
+	else if (channel >= 23)
+		txcalval = 0xA8;
+	else if (channel >= 22)
+		txcalval = 0xA9;
+	else if (channel >= 20)
+		txcalval = 0xAA;
+	else if (channel >= 17)
+		txcalval = 0xAB;
+	else if (channel >= 16)
+		txcalval = 0xAC;
+	else if (channel >= 14)
+		txcalval = 0xAD;
+	else if (channel >= 12)
+		txcalval = 0xAE;
+	else
+		txcalval = 0xAF;
+
+	return tdme_setsfr_request_sync(
+		1,
+		CA8210_SFR_LOTXCAL,
+		txcalval,
+		device_ref
+	);  /* LO Tx Cal */
+}
+
+/**
+ * tdme_checkpibattribute() - Checks Attribute Values that are not checked in
+ *                            MAC
+ * @pib_attribute:        Attribute Number
+ * @pib_attribute_length: Attribute length
+ * @pib_attribute_value:  Pointer to Attribute Value
+ * @device_ref:           Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of checks
+ */
+static u8 tdme_checkpibattribute(
+	u8            pib_attribute,
+	u8            pib_attribute_length,
+	const void   *pib_attribute_value
+)
+{
+	u8 status = MAC_SUCCESS;
+	u8 value;
+
+	value  = *((u8 *)pib_attribute_value);
+
+	switch (pib_attribute) {
+	/* PHY */
+	case PHY_TRANSMIT_POWER:
+		if (value > 0x3F)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case PHY_CCA_MODE:
+		if (value > 0x03)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	/* MAC */
+	case MAC_BATT_LIFE_EXT_PERIODS:
+		if ((value < 6) || (value > 41))
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_BEACON_PAYLOAD:
+		if (pib_attribute_length > MAX_BEACON_PAYLOAD_LENGTH)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_BEACON_PAYLOAD_LENGTH:
+		if (value > MAX_BEACON_PAYLOAD_LENGTH)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_BEACON_ORDER:
+		if (value > 15)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_MAX_BE:
+		if ((value < 3) || (value > 8))
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_MAX_CSMA_BACKOFFS:
+		if (value > 5)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_MAX_FRAME_RETRIES:
+		if (value > 7)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_MIN_BE:
+		if (value > 8)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_RESPONSE_WAIT_TIME:
+		if ((value < 2) || (value > 64))
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_SUPERFRAME_ORDER:
+		if (value > 15)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	/* boolean */
+	case MAC_ASSOCIATED_PAN_COORD:
+	case MAC_ASSOCIATION_PERMIT:
+	case MAC_AUTO_REQUEST:
+	case MAC_BATT_LIFE_EXT:
+	case MAC_GTS_PERMIT:
+	case MAC_PROMISCUOUS_MODE:
+	case MAC_RX_ON_WHEN_IDLE:
+	case MAC_SECURITY_ENABLED:
+		if (value > 1)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	/* MAC SEC */
+	case MAC_AUTO_REQUEST_SECURITY_LEVEL:
+		if (value > 7)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	case MAC_AUTO_REQUEST_KEY_ID_MODE:
+		if (value > 3)
+			status = MAC_INVALID_PARAMETER;
+		break;
+	default:
+		break;
+	}
+
+	return status;
+}
+
+/**
+ * tdme_settxpower() - Sets the tx power for MLME_SET phyTransmitPower
+ * @txp:        Transmit Power
+ * @device_ref: Nondescript pointer to target device
+ *
+ * Normalised to 802.15.4 Definition (6-bit, signed):
+ * Bit 7-6: not used
+ * Bit 5-0: tx power (-32 - +31 dB)
+ *
+ * Return: 802.15.4 status code of api calls
+ */
+static u8 tdme_settxpower(u8 txp, void *device_ref)
+{
+	u8 status;
+	s8 txp_val;
+	u8 txp_ext;
+	union pa_cfg_sfr pa_cfg_val;
+
+	/* extend from 6 to 8 bit */
+	txp_ext = 0x3F & txp;
+	if (txp_ext & 0x20)
+		txp_ext += 0xC0;
+	txp_val = (s8)txp_ext;
+
+	if (CA8210_MAC_MPW) {
+		if (txp_val > 0) {
+			/* 8 dBm: ptrim = 5, itrim = +3 => +4 dBm */
+			pa_cfg_val.bias_current_trim     = 3;
+			pa_cfg_val.buffer_capacitor_trim = 5;
+			pa_cfg_val.boost                 = 1;
+		} else {
+			/* 0 dBm: ptrim = 7, itrim = +3 => -6 dBm */
+			pa_cfg_val.bias_current_trim     = 3;
+			pa_cfg_val.buffer_capacitor_trim = 7;
+			pa_cfg_val.boost                 = 0;
+		}
+		/* write PACFG */
+		status = tdme_setsfr_request_sync(
+			0,
+			CA8210_SFR_PACFG,
+			pa_cfg_val.paib,
+			device_ref
+		);
+	} else {
+		/* Look-Up Table for Setting Current and Frequency Trim values
+		 * for desired Output Power
+		 */
+		if (txp_val > 8) {
+			pa_cfg_val.paib = 0x3F;
+		} else if (txp_val == 8) {
+			pa_cfg_val.paib = 0x32;
+		} else if (txp_val == 7) {
+			pa_cfg_val.paib = 0x22;
+		} else if (txp_val == 6) {
+			pa_cfg_val.paib = 0x18;
+		} else if (txp_val == 5) {
+			pa_cfg_val.paib = 0x10;
+		} else if (txp_val == 4) {
+			pa_cfg_val.paib = 0x0C;
+		} else if (txp_val == 3) {
+			pa_cfg_val.paib = 0x08;
+		} else if (txp_val == 2) {
+			pa_cfg_val.paib = 0x05;
+		} else if (txp_val == 1) {
+			pa_cfg_val.paib = 0x03;
+		} else if (txp_val == 0) {
+			pa_cfg_val.paib = 0x01;
+		} else { /* < 0 */
+			pa_cfg_val.paib = 0x00;
+		}
+		/* write PACFGIB */
+		status = tdme_setsfr_request_sync(
+			0,
+			CA8210_SFR_PACFGIB,
+			pa_cfg_val.paib,
+			device_ref
+		);
+	}
+
+	return status;
+}
+
+/**
+ * mcps_data_request() - mcps_data_request (Send Data) according to API Spec
+ * @src_addr_mode:    Source Addressing Mode
+ * @dst_address_mode: Destination Addressing Mode
+ * @dst_pan_id:       Destination PAN ID
+ * @dst_addr:         Pointer to Destination Address
+ * @msdu_length:      length of Data
+ * @msdu:             Pointer to Data
+ * @msdu_handle:      Handle of Data
+ * @tx_options:       Tx Options Bit Field
+ * @security:         Pointer to Security Structure or NULL
+ * @device_ref:       Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of action
+ */
+static u8 mcps_data_request(
+	u8               src_addr_mode,
+	u8               dst_address_mode,
+	u16              dst_pan_id,
+	union macaddr   *dst_addr,
+	u8               msdu_length,
+	u8              *msdu,
+	u8               msdu_handle,
+	u8               tx_options,
+	struct secspec  *security,
+	void            *device_ref
+)
+{
+	struct secspec *psec;
+	struct mac_message command;
+
+	command.command_id = SPI_MCPS_DATA_REQUEST;
+	command.pdata.data_req.src_addr_mode = src_addr_mode;
+	command.pdata.data_req.dst.mode = dst_address_mode;
+	if (dst_address_mode != MAC_MODE_NO_ADDR) {
+		command.pdata.data_req.dst.pan_id[0] = LS_BYTE(dst_pan_id);
+		command.pdata.data_req.dst.pan_id[1] = MS_BYTE(dst_pan_id);
+		if (dst_address_mode == MAC_MODE_SHORT_ADDR) {
+			command.pdata.data_req.dst.address[0] = LS_BYTE(
+				dst_addr->short_address
+			);
+			command.pdata.data_req.dst.address[1] = MS_BYTE(
+				dst_addr->short_address
+			);
+		} else {   /* MAC_MODE_LONG_ADDR*/
+			memcpy(
+				command.pdata.data_req.dst.address,
+				dst_addr->ieee_address,
+				8
+			);
+		}
+	}
+	command.pdata.data_req.msdu_length = msdu_length;
+	command.pdata.data_req.msdu_handle = msdu_handle;
+	command.pdata.data_req.tx_options = tx_options;
+	memcpy(command.pdata.data_req.msdu, msdu, msdu_length);
+	psec = (struct secspec *)(command.pdata.data_req.msdu + msdu_length);
+	command.length = sizeof(struct mcps_data_request_pset) -
+		MAX_DATA_SIZE + msdu_length;
+	if (!security || (security->security_level == 0)) {
+		psec->security_level = 0;
+		command.length += 1;
+	} else {
+		*psec = *security;
+		command.length += sizeof(struct secspec);
+	}
+
+	if (ca8210_spi_transfer(device_ref, &command.command_id,
+				command.length + 2))
+		return MAC_SYSTEM_ERROR;
+
+	return MAC_SUCCESS;
+}
+
+/**
+ * mlme_reset_request_sync() - MLME_RESET_request/confirm according to API Spec
+ * @set_default_pib: Set defaults in PIB
+ * @device_ref:      Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of MLME-RESET.confirm
+ */
+static u8 mlme_reset_request_sync(
+	u8    set_default_pib,
+	void *device_ref
+)
+{
+	u8 status;
+	struct mac_message command, response;
+	struct spi_device *spi = device_ref;
+
+	command.command_id = SPI_MLME_RESET_REQUEST;
+	command.length = 1;
+	command.pdata.u8param = set_default_pib;
+
+	if (cascoda_api_downstream(
+		&command.command_id,
+		command.length + 2,
+		&response.command_id,
+		device_ref)) {
+		dev_err(&spi->dev, "cascoda_api_downstream failed\n");
+		return MAC_SYSTEM_ERROR;
+	}
+
+	if (response.command_id != SPI_MLME_RESET_CONFIRM)
+		return MAC_SYSTEM_ERROR;
+
+	status = response.pdata.status;
+
+	/* reset COORD Bit for Channel Filtering as Coordinator */
+	if (CA8210_MAC_WORKAROUNDS && set_default_pib && (!status)) {
+		status = tdme_setsfr_request_sync(
+			0,
+			CA8210_SFR_MACCON,
+			0,
+			device_ref
+		);
+	}
+
+	return status;
+}
+
+/**
+ * mlme_set_request_sync() - MLME_SET_request/confirm according to API Spec
+ * @pib_attribute:        Attribute Number
+ * @pib_attribute_index:  Index within Attribute if an Array
+ * @pib_attribute_length: Attribute length
+ * @pib_attribute_value:  Pointer to Attribute Value
+ * @device_ref:           Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of MLME-SET.confirm
+ */
+static u8 mlme_set_request_sync(
+	u8            pib_attribute,
+	u8            pib_attribute_index,
+	u8            pib_attribute_length,
+	const void   *pib_attribute_value,
+	void         *device_ref
+)
+{
+	u8 status;
+	struct mac_message command, response;
+
+	/* pre-check the validity of pib_attribute values that are not checked
+	 * in MAC
+	 */
+	if (tdme_checkpibattribute(
+		pib_attribute, pib_attribute_length, pib_attribute_value)) {
+		return MAC_INVALID_PARAMETER;
+	}
+
+	if (pib_attribute == PHY_CURRENT_CHANNEL) {
+		status = tdme_channelinit(
+			*((u8 *)pib_attribute_value),
+			device_ref
+		);
+		if (status)
+			return status;
+	}
+
+	if (pib_attribute == PHY_TRANSMIT_POWER) {
+		return tdme_settxpower(
+			*((u8 *)pib_attribute_value),
+			device_ref
+		);
+	}
+
+	command.command_id = SPI_MLME_SET_REQUEST;
+	command.length = sizeof(struct mlme_set_request_pset) -
+		MAX_ATTRIBUTE_SIZE + pib_attribute_length;
+	command.pdata.set_req.pib_attribute = pib_attribute;
+	command.pdata.set_req.pib_attribute_index = pib_attribute_index;
+	command.pdata.set_req.pib_attribute_length = pib_attribute_length;
+	memcpy(
+		command.pdata.set_req.pib_attribute_value,
+		pib_attribute_value,
+		pib_attribute_length
+	);
+
+	if (cascoda_api_downstream(
+		&command.command_id,
+		command.length + 2,
+		&response.command_id,
+		device_ref)) {
+		return MAC_SYSTEM_ERROR;
+	}
+
+	if (response.command_id != SPI_MLME_SET_CONFIRM)
+		return MAC_SYSTEM_ERROR;
+
+	return response.pdata.status;
+}
+
+/**
+ * hwme_set_request_sync() - HWME_SET_request/confirm according to API Spec
+ * @hw_attribute:        Attribute Number
+ * @hw_attribute_length: Attribute length
+ * @hw_attribute_value:  Pointer to Attribute Value
+ * @device_ref:          Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of HWME-SET.confirm
+ */
+static u8 hwme_set_request_sync(
+	u8           hw_attribute,
+	u8           hw_attribute_length,
+	u8          *hw_attribute_value,
+	void        *device_ref
+)
+{
+	struct mac_message command, response;
+
+	command.command_id = SPI_HWME_SET_REQUEST;
+	command.length = 2 + hw_attribute_length;
+	command.pdata.hwme_set_req.hw_attribute = hw_attribute;
+	command.pdata.hwme_set_req.hw_attribute_length = hw_attribute_length;
+	memcpy(
+		command.pdata.hwme_set_req.hw_attribute_value,
+		hw_attribute_value,
+		hw_attribute_length
+	);
+
+	if (cascoda_api_downstream(
+		&command.command_id,
+		command.length + 2,
+		&response.command_id,
+		device_ref)) {
+		return MAC_SYSTEM_ERROR;
+	}
+
+	if (response.command_id != SPI_HWME_SET_CONFIRM)
+		return MAC_SYSTEM_ERROR;
+
+	return response.pdata.hwme_set_cnf.status;
+}
+
+/**
+ * hwme_get_request_sync() - HWME_GET_request/confirm according to API Spec
+ * @hw_attribute:        Attribute Number
+ * @hw_attribute_length: Attribute length
+ * @hw_attribute_value:  Pointer to Attribute Value
+ * @device_ref:          Nondescript pointer to target device
+ *
+ * Return: 802.15.4 status code of HWME-GET.confirm
+ */
+static u8 hwme_get_request_sync(
+	u8           hw_attribute,
+	u8          *hw_attribute_length,
+	u8          *hw_attribute_value,
+	void        *device_ref
+)
+{
+	struct mac_message command, response;
+
+	command.command_id = SPI_HWME_GET_REQUEST;
+	command.length = 1;
+	command.pdata.hwme_get_req.hw_attribute = hw_attribute;
+
+	if (cascoda_api_downstream(
+		&command.command_id,
+		command.length + 2,
+		&response.command_id,
+		device_ref)) {
+		return MAC_SYSTEM_ERROR;
+	}
+
+	if (response.command_id != SPI_HWME_GET_CONFIRM)
+		return MAC_SYSTEM_ERROR;
+
+	if (response.pdata.hwme_get_cnf.status == MAC_SUCCESS) {
+		*hw_attribute_length =
+			response.pdata.hwme_get_cnf.hw_attribute_length;
+		memcpy(
+			hw_attribute_value,
+			response.pdata.hwme_get_cnf.hw_attribute_value,
+			*hw_attribute_length
+		);
+	}
+
+	return response.pdata.hwme_get_cnf.status;
+}
+
+/* Network driver operation */
+
+/**
+ * ca8210_async_xmit_complete() - Called to announce that an asynchronous
+ *                                transmission has finished
+ * @hw:          ieee802154_hw of ca8210 that has finished exchange
+ * @msduhandle:  Identifier of transmission that has completed
+ * @status:      Returned 802.15.4 status code of the transmission
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_async_xmit_complete(
+	struct ieee802154_hw  *hw,
+	u8                     msduhandle,
+	u8                     status)
+{
+	struct ca8210_priv *priv = hw->priv;
+
+	if (priv->nextmsduhandle != msduhandle) {
+		dev_err(
+			&priv->spi->dev,
+			"Unexpected msdu_handle on data confirm, Expected %d, got %d\n",
+			priv->nextmsduhandle,
+			msduhandle
+		);
+		return -EIO;
+	}
+
+	priv->async_tx_pending = false;
+	priv->nextmsduhandle++;
+
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"Link transmission unsuccessful, status = %d\n",
+			status
+		);
+		if (status != MAC_TRANSACTION_OVERFLOW) {
+			ieee802154_wake_queue(priv->hw);
+			return 0;
+		}
+	}
+	ieee802154_xmit_complete(priv->hw, priv->tx_skb, true);
+
+	return 0;
+}
+
+/**
+ * ca8210_skb_rx() - Contructs a properly framed socket buffer from a received
+ *                   MCPS_DATA_indication
+ * @hw:        ieee802154_hw that MCPS_DATA_indication was received by
+ * @len:       length of MCPS_DATA_indication
+ * @data_ind:  Octet array of MCPS_DATA_indication
+ *
+ * Called by the spi driver whenever a SAP command is received, this function
+ * will ascertain whether the command is of interest to the network driver and
+ * take necessary action.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_skb_rx(
+	struct ieee802154_hw  *hw,
+	size_t                 len,
+	u8                    *data_ind
+)
+{
+	struct ieee802154_hdr hdr;
+	int msdulen;
+	int hlen;
+	u8 mpdulinkquality = data_ind[23];
+	struct sk_buff *skb;
+	struct ca8210_priv *priv = hw->priv;
+
+	/* Allocate mtu size buffer for every rx packet */
+	skb = dev_alloc_skb(IEEE802154_MTU + sizeof(hdr));
+	if (!skb) {
+		dev_crit(&priv->spi->dev, "dev_alloc_skb failed\n");
+		return -ENOMEM;
+	}
+	skb_reserve(skb, sizeof(hdr));
+
+	msdulen = data_ind[22]; /* msdu_length */
+	if (msdulen > IEEE802154_MTU) {
+		dev_err(
+			&priv->spi->dev,
+			"received erroneously large msdu length!\n"
+		);
+		kfree_skb(skb);
+		return -EMSGSIZE;
+	}
+	dev_dbg(&priv->spi->dev, "skb buffer length = %d\n", msdulen);
+
+	if (priv->promiscuous)
+		goto copy_payload;
+
+	/* Populate hdr */
+	hdr.sec.level = data_ind[29 + msdulen];
+	dev_dbg(&priv->spi->dev, "security level: %#03x\n", hdr.sec.level);
+	if (hdr.sec.level > 0) {
+		hdr.sec.key_id_mode = data_ind[30 + msdulen];
+		memcpy(&hdr.sec.extended_src, &data_ind[31 + msdulen], 8);
+		hdr.sec.key_id = data_ind[39 + msdulen];
+	}
+	hdr.source.mode = data_ind[0];
+	dev_dbg(&priv->spi->dev, "srcAddrMode: %#03x\n", hdr.source.mode);
+	hdr.source.pan_id = *(u16 *)&data_ind[1];
+	dev_dbg(&priv->spi->dev, "srcPanId: %#06x\n", hdr.source.pan_id);
+	memcpy(&hdr.source.extended_addr, &data_ind[3], 8);
+	hdr.dest.mode = data_ind[11];
+	dev_dbg(&priv->spi->dev, "dstAddrMode: %#03x\n", hdr.dest.mode);
+	hdr.dest.pan_id = *(u16 *)&data_ind[12];
+	dev_dbg(&priv->spi->dev, "dstPanId: %#06x\n", hdr.dest.pan_id);
+	memcpy(&hdr.dest.extended_addr, &data_ind[14], 8);
+
+	/* Fill in FC implicitly */
+	hdr.fc.type = 1; /* Data frame */
+	if (hdr.sec.level)
+		hdr.fc.security_enabled = 1;
+	else
+		hdr.fc.security_enabled = 0;
+	if (data_ind[1] != data_ind[12] || data_ind[2] != data_ind[13])
+		hdr.fc.intra_pan = 1;
+	else
+		hdr.fc.intra_pan = 0;
+	hdr.fc.dest_addr_mode = hdr.dest.mode;
+	hdr.fc.source_addr_mode = hdr.source.mode;
+
+	/* Add hdr to front of buffer */
+	hlen = ieee802154_hdr_push(skb, &hdr);
+
+	if (hlen < 0) {
+		dev_crit(&priv->spi->dev, "failed to push mac hdr onto skb!\n");
+		kfree_skb(skb);
+		return hlen;
+	}
+
+	skb_reset_mac_header(skb);
+	skb->mac_len = hlen;
+
+copy_payload:
+	/* Add <msdulen> bytes of space to the back of the buffer */
+	/* Copy msdu to skb */
+	memcpy(skb_put(skb, msdulen), &data_ind[29], msdulen);
+
+	ieee802154_rx_irqsafe(hw, skb, mpdulinkquality);
+	return 0;
+}
+
+/**
+ * ca8210_net_rx() - Acts upon received SAP commands relevant to the network
+ *                   driver
+ * @hw:       ieee802154_hw that command was received by
+ * @command:  Octet array of received command
+ * @len:      length of the received command
+ *
+ * Called by the spi driver whenever a SAP command is received, this function
+ * will ascertain whether the command is of interest to the network driver and
+ * take necessary action.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_net_rx(struct ieee802154_hw *hw, u8 *command, size_t len)
+{
+	struct ca8210_priv *priv = hw->priv;
+	unsigned long flags;
+	u8 status;
+
+	dev_dbg(&priv->spi->dev, "ca8210_net_rx(), CmdID = %d\n", command[0]);
+
+	if (command[0] == SPI_MCPS_DATA_INDICATION) {
+		/* Received data */
+		spin_lock_irqsave(&priv->lock, flags);
+		if (command[26] == priv->last_dsn) {
+			dev_dbg(
+				&priv->spi->dev,
+				"DSN %d resend received, ignoring...\n",
+				command[26]
+			);
+			spin_unlock_irqrestore(&priv->lock, flags);
+			return 0;
+		}
+		priv->last_dsn = command[26];
+		spin_unlock_irqrestore(&priv->lock, flags);
+		return ca8210_skb_rx(hw, len - 2, command + 2);
+	} else if (command[0] == SPI_MCPS_DATA_CONFIRM) {
+		status = command[3];
+		if (priv->async_tx_pending) {
+			return ca8210_async_xmit_complete(
+				hw,
+				command[2],
+				status
+			);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ca8210_skb_tx() - Transmits a given socket buffer using the ca8210
+ * @skb:         Socket buffer to transmit
+ * @msduhandle:  Data identifier to pass to the 802.15.4 MAC
+ * @priv:        Pointer to private data section of target ca8210
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_skb_tx(
+	struct sk_buff      *skb,
+	u8                   msduhandle,
+	struct ca8210_priv  *priv
+)
+{
+	int status;
+	struct ieee802154_hdr header = { 0 };
+	struct secspec secspec;
+	unsigned int mac_len;
+
+	dev_dbg(&priv->spi->dev, "ca8210_skb_tx() called\n");
+
+	/* Get addressing info from skb - ieee802154 layer creates a full
+	 * packet
+	 */
+	mac_len = ieee802154_hdr_peek_addrs(skb, &header);
+
+	secspec.security_level = header.sec.level;
+	secspec.key_id_mode = header.sec.key_id_mode;
+	if (secspec.key_id_mode == 2)
+		memcpy(secspec.key_source, &header.sec.short_src, 4);
+	else if (secspec.key_id_mode == 3)
+		memcpy(secspec.key_source, &header.sec.extended_src, 8);
+	secspec.key_index = header.sec.key_id;
+
+	/* Pass to Cascoda API */
+	status =  mcps_data_request(
+		header.source.mode,
+		header.dest.mode,
+		header.dest.pan_id,
+		(union macaddr *)&header.dest.extended_addr,
+		skb->len - mac_len,
+		&skb->data[mac_len],
+		msduhandle,
+		header.fc.ack_request,
+		&secspec,
+		priv->spi
+	);
+	return link_to_linux_err(status);
+}
+
+/**
+ * ca8210_start() - Starts the network driver
+ * @hw:  ieee802154_hw of ca8210 being started
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_start(struct ieee802154_hw *hw)
+{
+	int status;
+	u8 rx_on_when_idle;
+	u8 lqi_threshold = 0;
+	struct ca8210_priv *priv = hw->priv;
+
+	priv->last_dsn = -1;
+	/* Turn receiver on when idle for now just to test rx */
+	rx_on_when_idle = 1;
+	status = mlme_set_request_sync(
+		MAC_RX_ON_WHEN_IDLE,
+		0,
+		1,
+		&rx_on_when_idle,
+		priv->spi
+	);
+	if (status) {
+		dev_crit(
+			&priv->spi->dev,
+			"Setting rx_on_when_idle failed, status = %d\n",
+			status
+		);
+		return link_to_linux_err(status);
+	}
+	status = hwme_set_request_sync(
+		HWME_LQILIMIT,
+		1,
+		&lqi_threshold,
+		priv->spi
+	);
+	if (status) {
+		dev_crit(
+			&priv->spi->dev,
+			"Setting lqilimit failed, status = %d\n",
+			status
+		);
+		return link_to_linux_err(status);
+	}
+
+	return 0;
+}
+
+/**
+ * ca8210_stop() - Stops the network driver
+ * @hw:  ieee802154_hw of ca8210 being stopped
+ *
+ * Return: 0 or linux error code
+ */
+static void ca8210_stop(struct ieee802154_hw *hw)
+{
+}
+
+/**
+ * ca8210_xmit_async() - Asynchronously transmits a given socket buffer using
+ *                       the ca8210
+ * @hw:   ieee802154_hw of ca8210 to transmit from
+ * @skb:  Socket buffer to transmit
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_xmit_async(struct ieee802154_hw *hw, struct sk_buff *skb)
+{
+	struct ca8210_priv *priv = hw->priv;
+	int status;
+
+	dev_dbg(&priv->spi->dev, "calling ca8210_xmit_async()\n");
+
+	priv->tx_skb = skb;
+	priv->async_tx_pending = true;
+	status = ca8210_skb_tx(skb, priv->nextmsduhandle, priv);
+	return status;
+}
+
+/**
+ * ca8210_get_ed() - Returns the measured energy on the current channel at this
+ *                   instant in time
+ * @hw:     ieee802154_hw of target ca8210
+ * @level:  Measured Energy Detect level
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_get_ed(struct ieee802154_hw *hw, u8 *level)
+{
+	u8 lenvar;
+	struct ca8210_priv *priv = hw->priv;
+
+	return link_to_linux_err(
+		hwme_get_request_sync(HWME_EDVALUE, &lenvar, level, priv->spi)
+	);
+}
+
+/**
+ * ca8210_set_channel() - Sets the current operating 802.15.4 channel of the
+ *                        ca8210
+ * @hw:       ieee802154_hw of target ca8210
+ * @page:     Channel page to set
+ * @channel:  Channel number to set
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_channel(
+	struct ieee802154_hw  *hw,
+	u8                     page,
+	u8                     channel
+)
+{
+	u8 status;
+	struct ca8210_priv *priv = hw->priv;
+
+	status = mlme_set_request_sync(
+		PHY_CURRENT_CHANNEL,
+		0,
+		1,
+		&channel,
+		priv->spi
+	);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting channel, MLME-SET.confirm status = %d\n",
+			status
+		);
+	}
+	return link_to_linux_err(status);
+}
+
+/**
+ * ca8210_set_hw_addr_filt() - Sets the address filtering parameters of the
+ *                             ca8210
+ * @hw:       ieee802154_hw of target ca8210
+ * @filt:     Filtering parameters
+ * @changed:  Bitmap representing which parameters to change
+ *
+ * Effectively just sets the actual addressing information identifying this node
+ * as all filtering is performed by the ca8210 as detailed in the IEEE 802.15.4
+ * 2006 specification.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_hw_addr_filt(
+	struct ieee802154_hw            *hw,
+	struct ieee802154_hw_addr_filt  *filt,
+	unsigned long                    changed
+)
+{
+	u8 status = 0;
+	struct ca8210_priv *priv = hw->priv;
+
+	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
+		status = mlme_set_request_sync(
+			MAC_PAN_ID,
+			0,
+			2,
+			&filt->pan_id, priv->spi
+		);
+		if (status) {
+			dev_err(
+				&priv->spi->dev,
+				"error setting pan id, MLME-SET.confirm status = %d",
+				status
+			);
+			return link_to_linux_err(status);
+		}
+	}
+	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
+		status = mlme_set_request_sync(
+			MAC_SHORT_ADDRESS,
+			0,
+			2,
+			&filt->short_addr, priv->spi
+		);
+		if (status) {
+			dev_err(
+				&priv->spi->dev,
+				"error setting short address, MLME-SET.confirm status = %d",
+				status
+			);
+			return link_to_linux_err(status);
+		}
+	}
+	if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) {
+		status = mlme_set_request_sync(
+			NS_IEEE_ADDRESS,
+			0,
+			8,
+			&filt->ieee_addr,
+			priv->spi
+		);
+		if (status) {
+			dev_err(
+				&priv->spi->dev,
+				"error setting ieee address, MLME-SET.confirm status = %d",
+				status
+			);
+			return link_to_linux_err(status);
+		}
+	}
+	/* TODO: Should use MLME_START to set coord bit? */
+	return 0;
+}
+
+/**
+ * ca8210_set_tx_power() - Sets the transmit power of the ca8210
+ * @hw:   ieee802154_hw of target ca8210
+ * @mbm:  Transmit power in mBm (dBm*100)
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_tx_power(struct ieee802154_hw *hw, s32 mbm)
+{
+	struct ca8210_priv *priv = hw->priv;
+
+	mbm /= 100;
+	return link_to_linux_err(
+		mlme_set_request_sync(PHY_TRANSMIT_POWER, 0, 1, &mbm, priv->spi)
+	);
+}
+
+/**
+ * ca8210_set_cca_mode() - Sets the clear channel assessment mode of the ca8210
+ * @hw:   ieee802154_hw of target ca8210
+ * @cca:  CCA mode to set
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_cca_mode(
+	struct ieee802154_hw       *hw,
+	const struct wpan_phy_cca  *cca
+)
+{
+	u8 status;
+	u8 cca_mode;
+	struct ca8210_priv *priv = hw->priv;
+
+	cca_mode = cca->mode & 3;
+	if (cca_mode == 3 && cca->opt == NL802154_CCA_OPT_ENERGY_CARRIER_OR) {
+		/* cca_mode 0 == CS OR ED, 3 == CS AND ED */
+		cca_mode = 0;
+	}
+	status = mlme_set_request_sync(
+		PHY_CCA_MODE,
+		0,
+		1,
+		&cca_mode,
+		priv->spi
+	);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting cca mode, MLME-SET.confirm status = %d",
+			status
+		);
+	}
+	return link_to_linux_err(status);
+}
+
+/**
+ * ca8210_set_cca_ed_level() - Sets the CCA ED level of the ca8210
+ * @hw:     ieee802154_hw of target ca8210
+ * @level:  ED level to set (in mbm)
+ *
+ * Sets the minimum threshold of measured energy above which the ca8210 will
+ * back off and retry a transmission.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_cca_ed_level(struct ieee802154_hw *hw, s32 level)
+{
+	u8 status;
+	u8 ed_threshold = (level / 100) * 2 + 256;
+	struct ca8210_priv *priv = hw->priv;
+
+	status = hwme_set_request_sync(
+		HWME_EDTHRESHOLD,
+		1,
+		&ed_threshold,
+		priv->spi
+	);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting ed threshold, HWME-SET.confirm status = %d",
+			status
+		);
+	}
+	return link_to_linux_err(status);
+}
+
+/**
+ * ca8210_set_csma_params() - Sets the CSMA parameters of the ca8210
+ * @hw:       ieee802154_hw of target ca8210
+ * @min_be:   Minimum backoff exponent when backing off a transmission
+ * @max_be:   Maximum backoff exponent when backing off a transmission
+ * @retries:  Number of times to retry after backing off
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_csma_params(
+	struct ieee802154_hw  *hw,
+	u8                     min_be,
+	u8                     max_be,
+	u8                     retries
+)
+{
+	u8 status;
+	struct ca8210_priv *priv = hw->priv;
+
+	status = mlme_set_request_sync(MAC_MIN_BE, 0, 1, &min_be, priv->spi);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting min be, MLME-SET.confirm status = %d",
+			status
+		);
+		return link_to_linux_err(status);
+	}
+	status = mlme_set_request_sync(MAC_MAX_BE, 0, 1, &max_be, priv->spi);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting max be, MLME-SET.confirm status = %d",
+			status
+		);
+		return link_to_linux_err(status);
+	}
+	status = mlme_set_request_sync(
+		MAC_MAX_CSMA_BACKOFFS,
+		0,
+		1,
+		&retries,
+		priv->spi
+	);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting max csma backoffs, MLME-SET.confirm status = %d",
+			status
+		);
+	}
+	return link_to_linux_err(status);
+}
+
+/**
+ * ca8210_set_frame_retries() - Sets the maximum frame retries of the ca8210
+ * @hw:       ieee802154_hw of target ca8210
+ * @retries:  Number of retries
+ *
+ * Sets the number of times to retry a transmission if no acknowledgment was
+ * was received from the other end when one was requested.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
+{
+	u8 status;
+	struct ca8210_priv *priv = hw->priv;
+
+	status = mlme_set_request_sync(
+		MAC_MAX_FRAME_RETRIES,
+		0,
+		1,
+		&retries,
+		priv->spi
+	);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting frame retries, MLME-SET.confirm status = %d",
+			status
+		);
+	}
+	return link_to_linux_err(status);
+}
+
+static int ca8210_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on)
+{
+	u8 status;
+	struct ca8210_priv *priv = hw->priv;
+
+	status = mlme_set_request_sync(
+		MAC_PROMISCUOUS_MODE,
+		0,
+		1,
+		(const void*)&on,
+		priv->spi
+	);
+	if (status) {
+		dev_err(
+			&priv->spi->dev,
+			"error setting promiscuous mode, MLME-SET.confirm status = %d",
+			status
+		);
+	} else {
+		priv->promiscuous = on;
+	}
+	return link_to_linux_err(status);
+}
+
+static const struct ieee802154_ops ca8210_phy_ops = {
+	.start = ca8210_start,
+	.stop = ca8210_stop,
+	.xmit_async = ca8210_xmit_async,
+	.ed = ca8210_get_ed,
+	.set_channel = ca8210_set_channel,
+	.set_hw_addr_filt = ca8210_set_hw_addr_filt,
+	.set_txpower = ca8210_set_tx_power,
+	.set_cca_mode = ca8210_set_cca_mode,
+	.set_cca_ed_level = ca8210_set_cca_ed_level,
+	.set_csma_params = ca8210_set_csma_params,
+	.set_frame_retries = ca8210_set_frame_retries,
+	.set_promiscuous_mode = ca8210_set_promiscuous_mode
+};
+
+/* Test/EVBME Interface */
+
+/**
+ * ca8210_test_int_open() - Opens the test interface to the userspace
+ * @inodp:  inode representation of file interface
+ * @filp:   file interface
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_test_int_open(struct inode *inodp, struct file *filp)
+{
+	struct ca8210_priv *priv = inodp->i_private;
+
+	filp->private_data = priv;
+	return 0;
+}
+
+/**
+ * ca8210_test_check_upstream() - Checks a command received from the upstream
+ *                                testing interface for required action
+ * @buf:        Buffer containing command to check
+ * @device_ref: Nondescript pointer to target device
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_test_check_upstream(u8 *buf, void *device_ref)
+{
+	int ret;
+	u8 response[CA8210_SPI_BUF_SIZE];
+
+	if (buf[0] == SPI_MLME_SET_REQUEST) {
+		ret = tdme_checkpibattribute(buf[2], buf[4], buf + 5);
+		if (ret) {
+			response[0]  = SPI_MLME_SET_CONFIRM;
+			response[1] = 3;
+			response[2] = MAC_INVALID_PARAMETER;
+			response[3] = buf[2];
+			response[4] = buf[3];
+			if (cascoda_api_upstream)
+				cascoda_api_upstream(response, 5, device_ref);
+			return ret;
+		}
+	}
+	if (buf[0] == SPI_MLME_ASSOCIATE_REQUEST) {
+		return tdme_channelinit(buf[2], device_ref);
+	} else if (buf[0] == SPI_MLME_START_REQUEST) {
+		return tdme_channelinit(buf[4], device_ref);
+	} else if (
+		(buf[0] == SPI_MLME_SET_REQUEST) &&
+		(buf[2] == PHY_CURRENT_CHANNEL)
+	) {
+		return tdme_channelinit(buf[5], device_ref);
+	} else if (
+		(buf[0] == SPI_TDME_SET_REQUEST) &&
+		(buf[2] == TDME_CHANNEL)
+	) {
+		return tdme_channelinit(buf[4], device_ref);
+	} else if (
+		(CA8210_MAC_WORKAROUNDS) &&
+		(buf[0] == SPI_MLME_RESET_REQUEST) &&
+		(buf[2] == 1)
+	) {
+		/* reset COORD Bit for Channel Filtering as Coordinator */
+		return tdme_setsfr_request_sync(
+			0,
+			CA8210_SFR_MACCON,
+			0,
+			device_ref
+		);
+	}
+	return 0;
+} /* End of EVBMECheckSerialCommand() */
+
+/**
+ * ca8210_test_int_user_write() - Called by a process in userspace to send a
+ *                                message to the ca8210 drivers
+ * @filp:    file interface
+ * @in_buf:  Buffer containing message to write
+ * @len:     length of message
+ * @off:     file offset
+ *
+ * Return: 0 or linux error code
+ */
+static ssize_t ca8210_test_int_user_write(
+	struct file        *filp,
+	const char __user  *in_buf,
+	size_t              len,
+	loff_t             *off
+)
+{
+	int ret;
+	struct ca8210_priv *priv = filp->private_data;
+	u8 command[CA8210_SPI_BUF_SIZE];
+
+	if (len > CA8210_SPI_BUF_SIZE) {
+		dev_warn(
+			&priv->spi->dev,
+			"userspace requested erroneously long write (%zu)\n",
+			len
+		);
+		return -EMSGSIZE;
+	}
+
+	ret = copy_from_user(command, in_buf, len);
+	if (ret) {
+		dev_err(
+			&priv->spi->dev,
+			"%d bytes could not be copied from userspace\n",
+			ret
+		);
+		return -EIO;
+	}
+
+	ret = ca8210_test_check_upstream(command, priv->spi);
+	if (ret == 0) {
+		ret = ca8210_spi_exchange(
+			command,
+			command[1] + 2,
+			NULL,
+			priv->spi
+		);
+		if (ret < 0) {
+			/* effectively 0 bytes were written successfully */
+			dev_err(
+				&priv->spi->dev,
+				"spi exchange failed\n"
+			);
+			return ret;
+		}
+		if (command[0] & SPI_SYN)
+			priv->sync_down++;
+	}
+
+	return len;
+}
+
+/**
+ * ca8210_test_int_user_read() - Called by a process in userspace to read a
+ *                               message from the ca8210 drivers
+ * @filp:  file interface
+ * @buf:   Buffer to write message to
+ * @len:   length of message to read (ignored)
+ * @offp:  file offset
+ *
+ * If the O_NONBLOCK flag was set when opening the file then this function will
+ * not block, i.e. it will return if the fifo is empty. Otherwise the function
+ * will block, i.e. wait until new data arrives.
+ *
+ * Return: number of bytes read
+ */
+static ssize_t ca8210_test_int_user_read(
+	struct file  *filp,
+	char __user  *buf,
+	size_t        len,
+	loff_t       *offp
+)
+{
+	int i, cmdlen;
+	struct ca8210_priv *priv = filp->private_data;
+	unsigned char *fifo_buffer;
+	unsigned long bytes_not_copied;
+
+	if (filp->f_flags & O_NONBLOCK) {
+		/* Non-blocking mode */
+		if (kfifo_is_empty(&priv->test.up_fifo))
+			return 0;
+	} else {
+		/* Blocking mode */
+		wait_event_interruptible(
+			priv->test.readq,
+			!kfifo_is_empty(&priv->test.up_fifo)
+		);
+	}
+
+	if (kfifo_out(&priv->test.up_fifo, &fifo_buffer, 4) != 4) {
+		dev_err(
+			&priv->spi->dev,
+			"test_interface: Wrong number of elements popped from upstream fifo\n"
+		);
+		return 0;
+	}
+	cmdlen = fifo_buffer[1];
+	bytes_not_copied = cmdlen + 2;
+
+	bytes_not_copied = copy_to_user(buf, fifo_buffer, bytes_not_copied);
+	if (bytes_not_copied > 0) {
+		dev_err(
+			&priv->spi->dev,
+			"%lu bytes could not be copied to user space!\n",
+			bytes_not_copied
+		);
+	}
+
+	dev_dbg(&priv->spi->dev, "test_interface: Cmd len = %d\n", cmdlen);
+
+	dev_dbg(&priv->spi->dev, "test_interface: Read\n");
+	for (i = 0; i < cmdlen + 2; i++)
+		dev_dbg(&priv->spi->dev, "%#03x\n", fifo_buffer[i]);
+
+	kfree(fifo_buffer);
+
+	return cmdlen + 2;
+}
+
+/**
+ * ca8210_test_int_ioctl() - Called by a process in userspace to enact an
+ *                           arbitrary action
+ * @filp:        file interface
+ * @ioctl_num:   which action to enact
+ * @ioctl_param: arbitrary parameter for the action
+ *
+ * Return: status
+ */
+static long ca8210_test_int_ioctl(
+	struct file *filp,
+	unsigned int ioctl_num,
+	unsigned long ioctl_param
+)
+{
+	struct ca8210_priv *priv = filp->private_data;
+
+	switch (ioctl_num) {
+	case CA8210_IOCTL_HARD_RESET:
+		ca8210_reset_send(priv->spi, ioctl_param);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/**
+ * ca8210_test_int_poll() - Called by a process in userspace to determine which
+ *                          actions are currently possible for the file
+ * @filp:   file interface
+ * @ptable: poll table
+ *
+ * Return: set of poll return flags
+ */
+static unsigned int ca8210_test_int_poll(
+	struct file *filp,
+	struct poll_table_struct *ptable
+)
+{
+	unsigned int return_flags = 0;
+	struct ca8210_priv *priv = filp->private_data;
+
+	poll_wait(filp, &priv->test.readq, ptable);
+	if (!kfifo_is_empty(&priv->test.up_fifo))
+		return_flags |= (POLLIN | POLLRDNORM);
+	if (wait_event_interruptible(
+		priv->test.readq,
+		!kfifo_is_empty(&priv->test.up_fifo))) {
+		return POLLERR;
+	}
+	return return_flags;
+}
+
+static const struct file_operations test_int_fops = {
+	.read =           ca8210_test_int_user_read,
+	.write =          ca8210_test_int_user_write,
+	.open =           ca8210_test_int_open,
+	.release =        NULL,
+	.unlocked_ioctl = ca8210_test_int_ioctl,
+	.poll =           ca8210_test_int_poll
+};
+
+/* Init/Deinit */
+
+/**
+ * ca8210_get_platform_data() - Populate a ca8210_platform_data object
+ * @spi_device:  Pointer to ca8210 spi device object to get data for
+ * @pdata:       Pointer to ca8210_platform_data object to populate
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_get_platform_data(
+	struct spi_device *spi_device,
+	struct ca8210_platform_data *pdata
+)
+{
+	int ret = 0;
+
+	if (!spi_device->dev.of_node)
+		return -EINVAL;
+
+	pdata->extclockenable = of_property_read_bool(
+		spi_device->dev.of_node,
+		"extclock-enable"
+	);
+	if (pdata->extclockenable) {
+		ret = of_property_read_u32(
+			spi_device->dev.of_node,
+			"extclock-freq",
+			&pdata->extclockfreq
+		);
+		if (ret < 0)
+			return ret;
+
+		ret = of_property_read_u32(
+			spi_device->dev.of_node,
+			"extclock-gpio",
+			&pdata->extclockgpio
+		);
+	}
+
+	return ret;
+}
+
+/**
+ * ca8210_config_extern_clk() - Configure the external clock provided by the
+ *                              ca8210
+ * @pdata:  Pointer to ca8210_platform_data containing clock parameters
+ * @spi:    Pointer to target ca8210 spi device
+ * @on:	    True to turn the clock on, false to turn off
+ *
+ * The external clock is configured with a frequency and output pin taken from
+ * the platform data.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_config_extern_clk(
+	struct ca8210_platform_data *pdata,
+	struct spi_device *spi,
+	bool on
+)
+{
+	u8 clkparam[2];
+
+	if (on) {
+		dev_info(&spi->dev, "Switching external clock on\n");
+		switch (pdata->extclockfreq) {
+		case SIXTEEN_MHZ:
+			clkparam[0] = 1;
+			break;
+		case EIGHT_MHZ:
+			clkparam[0] = 2;
+			break;
+		case FOUR_MHZ:
+			clkparam[0] = 3;
+			break;
+		case TWO_MHZ:
+			clkparam[0] = 4;
+			break;
+		case ONE_MHZ:
+			clkparam[0] = 5;
+			break;
+		default:
+			dev_crit(&spi->dev, "Invalid extclock-freq\n");
+			return -EINVAL;
+		}
+		clkparam[1] = pdata->extclockgpio;
+	} else {
+		dev_info(&spi->dev, "Switching external clock off\n");
+		clkparam[0] = 0; /* off */
+		clkparam[1] = 0;
+	}
+	return link_to_linux_err(
+		hwme_set_request_sync(HWME_SYSCLKOUT, 2, clkparam, spi)
+	);
+}
+
+/**
+ * ca8210_register_ext_clock() - Register ca8210's external clock with kernel
+ * @spi:  Pointer to target ca8210 spi device
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_register_ext_clock(struct spi_device *spi)
+{
+	struct device_node *np = spi->dev.of_node;
+	struct ca8210_priv *priv = spi_get_drvdata(spi);
+	struct ca8210_platform_data *pdata = spi->dev.platform_data;
+	int ret = 0;
+
+	if (!np)
+		return -EFAULT;
+
+	priv->clk = clk_register_fixed_rate(
+		&spi->dev,
+		np->name,
+		NULL,
+		0,
+		pdata->extclockfreq
+	);
+
+	if (IS_ERR(priv->clk)) {
+		dev_crit(&spi->dev, "Failed to register external clk\n");
+		return PTR_ERR(priv->clk);
+	}
+	ret = of_clk_add_provider(np, of_clk_src_simple_get, priv->clk);
+	if (ret) {
+		clk_unregister(priv->clk);
+		dev_crit(
+			&spi->dev,
+			"Failed to register external clock as clock provider\n"
+		);
+	} else {
+		dev_info(&spi->dev, "External clock set as clock provider\n");
+	}
+
+	return ret;
+}
+
+/**
+ * ca8210_unregister_ext_clock() - Unregister ca8210's external clock with
+ *                                 kernel
+ * @spi:  Pointer to target ca8210 spi device
+ */
+static void ca8210_unregister_ext_clock(struct spi_device *spi)
+{
+	struct ca8210_priv *priv = spi_get_drvdata(spi);
+
+	if (!priv->clk)
+		return
+
+	of_clk_del_provider(spi->dev.of_node);
+	clk_unregister(priv->clk);
+	dev_info(&spi->dev, "External clock unregistered\n");
+}
+
+/**
+ * ca8210_reset_init() - Initialise the reset input to the ca8210
+ * @spi:  Pointer to target ca8210 spi device
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_reset_init(struct spi_device *spi)
+{
+	int ret;
+	struct ca8210_platform_data *pdata = spi->dev.platform_data;
+
+	pdata->gpio_reset = of_get_named_gpio(
+		spi->dev.of_node,
+		"reset-gpio",
+		0
+	);
+
+	ret = gpio_direction_output(pdata->gpio_reset, 1);
+	if (ret < 0) {
+		dev_crit(
+			&spi->dev,
+			"Reset GPIO %d did not set to output mode\n",
+			pdata->gpio_reset
+		);
+	}
+
+	return ret;
+}
+
+/**
+ * ca8210_interrupt_init() - Initialise the irq output from the ca8210
+ * @spi:  Pointer to target ca8210 spi device
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_interrupt_init(struct spi_device *spi)
+{
+	int ret;
+	struct ca8210_platform_data *pdata = spi->dev.platform_data;
+
+	pdata->gpio_irq = of_get_named_gpio(
+		spi->dev.of_node,
+		"irq-gpio",
+		0
+	);
+
+	pdata->irq_id = gpio_to_irq(pdata->gpio_irq);
+	if (pdata->irq_id < 0) {
+		dev_crit(
+			&spi->dev,
+			"Could not get irq for gpio pin %d\n",
+			pdata->gpio_irq
+		);
+		gpio_free(pdata->gpio_irq);
+		return pdata->irq_id;
+	}
+
+	ret = request_irq(
+		pdata->irq_id,
+		ca8210_interrupt_handler,
+		IRQF_TRIGGER_FALLING,
+		"ca8210-irq",
+		spi_get_drvdata(spi)
+	);
+	if (ret) {
+		dev_crit(&spi->dev, "request_irq %d failed\n", pdata->irq_id);
+		gpio_unexport(pdata->gpio_irq);
+		gpio_free(pdata->gpio_irq);
+	}
+
+	return ret;
+}
+
+/**
+ * ca8210_dev_com_init() - Initialise the spi communication component
+ * @priv:  Pointer to private data structure
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_dev_com_init(struct ca8210_priv *priv)
+{
+	priv->mlme_workqueue = alloc_ordered_workqueue(
+		"MLME work queue",
+		WQ_UNBOUND
+	);
+	if (!priv->mlme_workqueue) {
+		dev_crit(&priv->spi->dev, "alloc of mlme_workqueue failed!\n");
+		return -ENOMEM;
+	}
+
+	priv->irq_workqueue = alloc_ordered_workqueue(
+		"ca8210 irq worker",
+		WQ_UNBOUND
+	);
+	if (!priv->irq_workqueue) {
+		dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * ca8210_dev_com_clear() - Deinitialise the spi communication component
+ * @priv:  Pointer to private data structure
+ */
+static void ca8210_dev_com_clear(struct ca8210_priv *priv)
+{
+	flush_workqueue(priv->mlme_workqueue);
+	destroy_workqueue(priv->mlme_workqueue);
+	flush_workqueue(priv->irq_workqueue);
+	destroy_workqueue(priv->irq_workqueue);
+}
+
+#define CA8210_MAX_TX_POWERS (9)
+static const s32 ca8210_tx_powers[CA8210_MAX_TX_POWERS] = {
+	800, 700, 600, 500, 400, 300, 200, 100, 0
+};
+
+#define CA8210_MAX_ED_LEVELS (21)
+static const s32 ca8210_ed_levels[CA8210_MAX_ED_LEVELS] = {
+	-10300, -10250, -10200, -10150, -10100, -10050, -10000, -9950, -9900,
+	-9850, -9800, -9750, -9700, -9650, -9600, -9550, -9500, -9450, -9400,
+	-9350, -9300
+};
+
+/**
+ * ca8210_hw_setup() - Populate the ieee802154_hw phy attributes with the
+ *                     ca8210's defaults
+ * @ca8210_hw:  Pointer to ieee802154_hw to populate
+ */
+static void ca8210_hw_setup(struct ieee802154_hw *ca8210_hw)
+{
+	/* Support channels 11-26 */
+	ca8210_hw->phy->supported.channels[0] = CA8210_VALID_CHANNELS;
+	ca8210_hw->phy->supported.tx_powers_size = CA8210_MAX_TX_POWERS;
+	ca8210_hw->phy->supported.tx_powers = ca8210_tx_powers;
+	ca8210_hw->phy->supported.cca_ed_levels_size = CA8210_MAX_ED_LEVELS;
+	ca8210_hw->phy->supported.cca_ed_levels = ca8210_ed_levels;
+	ca8210_hw->phy->current_channel = 18;
+	ca8210_hw->phy->current_page = 0;
+	ca8210_hw->phy->transmit_power = 800;
+	ca8210_hw->phy->cca.mode = NL802154_CCA_ENERGY_CARRIER;
+	ca8210_hw->phy->cca.opt = NL802154_CCA_OPT_ENERGY_CARRIER_AND;
+	ca8210_hw->phy->cca_ed_level = -9800;
+	ca8210_hw->phy->symbol_duration = 16;
+	ca8210_hw->phy->lifs_period = 40;
+	ca8210_hw->phy->sifs_period = 12;
+	ca8210_hw->flags =
+		IEEE802154_HW_AFILT |
+		IEEE802154_HW_OMIT_CKSUM |
+		IEEE802154_HW_FRAME_RETRIES |
+		IEEE802154_HW_PROMISCUOUS |
+		IEEE802154_HW_CSMA_PARAMS;
+	ca8210_hw->phy->flags =
+		WPAN_PHY_FLAG_TXPOWER |
+		WPAN_PHY_FLAG_CCA_ED_LEVEL |
+		WPAN_PHY_FLAG_CCA_MODE;
+}
+
+/**
+ * ca8210_test_interface_init() - Initialise the test file interface
+ * @priv:  Pointer to private data structure
+ *
+ * Provided as an alternative to the standard linux network interface, the test
+ * interface exposes a file in the filesystem (ca8210_test) that allows
+ * 802.15.4 SAP Commands and Cascoda EVBME commands to be sent directly to
+ * the stack.
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_test_interface_init(struct ca8210_priv *priv)
+{
+	struct ca8210_test *test = &priv->test;
+	char node_name[32];
+
+	snprintf(
+		node_name,
+		sizeof(node_name),
+		"ca8210@%d_%d",
+		priv->spi->master->bus_num,
+		priv->spi->chip_select
+	);
+
+	test->ca8210_dfs_spi_int = debugfs_create_file(
+		node_name,
+		0600, /* S_IRUSR | S_IWUSR */
+		NULL,
+		priv,
+		&test_int_fops
+	);
+	if (IS_ERR(test->ca8210_dfs_spi_int)) {
+		dev_err(
+			&priv->spi->dev,
+			"Error %ld when creating debugfs node\n",
+			PTR_ERR(test->ca8210_dfs_spi_int)
+		);
+		return PTR_ERR(test->ca8210_dfs_spi_int);
+	}
+	debugfs_create_symlink("ca8210", NULL, node_name);
+	init_waitqueue_head(&test->readq);
+	return kfifo_alloc(
+		&test->up_fifo,
+		CA8210_TEST_INT_FIFO_SIZE,
+		GFP_KERNEL
+	);
+}
+
+/**
+ * ca8210_test_interface_clear() - Deinitialise the test file interface
+ * @priv:  Pointer to private data structure
+ */
+static void ca8210_test_interface_clear(struct ca8210_priv *priv)
+{
+	struct ca8210_test *test = &priv->test;
+
+	if (!IS_ERR(test->ca8210_dfs_spi_int))
+		debugfs_remove(test->ca8210_dfs_spi_int);
+	kfifo_free(&test->up_fifo);
+	dev_info(&priv->spi->dev, "Test interface removed\n");
+}
+
+/**
+ * ca8210_remove() - Shut down a ca8210 upon being disconnected
+ * @priv:  Pointer to private data structure
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_remove(struct spi_device *spi_device)
+{
+	struct ca8210_priv *priv;
+	struct ca8210_platform_data *pdata;
+
+	dev_info(&spi_device->dev, "Removing ca8210\n");
+
+	pdata = spi_device->dev.platform_data;
+	if (pdata) {
+		if (pdata->extclockenable) {
+			ca8210_unregister_ext_clock(spi_device);
+			ca8210_config_extern_clk(pdata, spi_device, 0);
+		}
+		free_irq(pdata->irq_id, spi_device->dev.driver_data);
+		kfree(pdata);
+		spi_device->dev.platform_data = NULL;
+	}
+	/* get spi_device private data */
+	priv = spi_get_drvdata(spi_device);
+	if (priv) {
+		dev_info(
+			&spi_device->dev,
+			"sync_down = %d, sync_up = %d\n",
+			priv->sync_down,
+			priv->sync_up
+		);
+		ca8210_dev_com_clear(spi_device->dev.driver_data);
+		if (priv->hw) {
+			if (priv->hw_registered)
+				ieee802154_unregister_hw(priv->hw);
+			ieee802154_free_hw(priv->hw);
+			priv->hw = NULL;
+			dev_info(
+				&spi_device->dev,
+				"Unregistered & freed ieee802154_hw.\n"
+			);
+		}
+		if (IS_ENABLED(CONFIG_IEEE802154_CA8210_DEBUGFS))
+			ca8210_test_interface_clear(priv);
+	}
+
+	return 0;
+}
+
+/**
+ * ca8210_probe() - Set up a connected ca8210 upon being detected by the system
+ * @priv:  Pointer to private data structure
+ *
+ * Return: 0 or linux error code
+ */
+static int ca8210_probe(struct spi_device *spi_device)
+{
+	struct ca8210_priv *priv;
+	struct ieee802154_hw *hw;
+	struct ca8210_platform_data *pdata;
+	int ret;
+
+	dev_info(&spi_device->dev, "Inserting ca8210\n");
+
+	/* allocate ieee802154_hw and private data */
+	hw = ieee802154_alloc_hw(sizeof(struct ca8210_priv), &ca8210_phy_ops);
+	if (!hw) {
+		dev_crit(&spi_device->dev, "ieee802154_alloc_hw failed\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	priv = hw->priv;
+	priv->hw = hw;
+	priv->spi = spi_device;
+	hw->parent = &spi_device->dev;
+	spin_lock_init(&priv->lock);
+	priv->async_tx_pending = false;
+	priv->hw_registered = false;
+	priv->sync_up = 0;
+	priv->sync_down = 0;
+	priv->promiscuous = false;
+	priv->retries = 0;
+	init_completion(&priv->ca8210_is_awake);
+	init_completion(&priv->spi_transfer_complete);
+	init_completion(&priv->sync_exchange_complete);
+	spi_set_drvdata(priv->spi, priv);
+	if (IS_ENABLED(CONFIG_IEEE802154_CA8210_DEBUGFS)) {
+		cascoda_api_upstream = ca8210_test_int_driver_write;
+		ca8210_test_interface_init(priv);
+	} else {
+		cascoda_api_upstream = NULL;
+	}
+	ca8210_hw_setup(hw);
+	ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
+
+	pdata = kmalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		dev_crit(
+			&spi_device->dev,
+			"Could not allocate platform data\n"
+		);
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = ca8210_get_platform_data(priv->spi, pdata);
+	if (ret) {
+		dev_crit(&spi_device->dev, "ca8210_get_platform_data failed\n");
+		goto error;
+	}
+	priv->spi->dev.platform_data = pdata;
+
+	ret = ca8210_dev_com_init(priv);
+	if (ret) {
+		dev_crit(&spi_device->dev, "ca8210_dev_com_init failed\n");
+		goto error;
+	}
+	ret = ca8210_reset_init(priv->spi);
+	if (ret) {
+		dev_crit(&spi_device->dev, "ca8210_reset_init failed\n");
+		goto error;
+	}
+
+	ret = ca8210_interrupt_init(priv->spi);
+	if (ret) {
+		dev_crit(&spi_device->dev, "ca8210_interrupt_init failed\n");
+		goto error;
+	}
+
+	msleep(100);
+
+	ca8210_reset_send(priv->spi, 1);
+
+	ret = tdme_chipinit(priv->spi);
+	if (ret) {
+		dev_crit(&spi_device->dev, "tdme_chipinit failed\n");
+		goto error;
+	}
+
+	if (pdata->extclockenable) {
+		ret = ca8210_config_extern_clk(pdata, priv->spi, 1);
+		if (ret) {
+			dev_crit(
+				&spi_device->dev,
+				"ca8210_config_extern_clk failed\n"
+			);
+			goto error;
+		}
+		ret = ca8210_register_ext_clock(priv->spi);
+		if (ret) {
+			dev_crit(
+				&spi_device->dev,
+				"ca8210_register_ext_clock failed\n"
+			);
+			goto error;
+		}
+	}
+
+	ret = ieee802154_register_hw(hw);
+	if (ret) {
+		dev_crit(&spi_device->dev, "ieee802154_register_hw failed\n");
+		goto error;
+	}
+	priv->hw_registered = true;
+
+	return 0;
+error:
+	msleep(100); /* wait for pending spi transfers to complete */
+	ca8210_remove(spi_device);
+	return link_to_linux_err(ret);
+}
+
+static const struct of_device_id ca8210_of_ids[] = {
+	{.compatible = "cascoda,ca8210", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ca8210_of_ids);
+
+static struct spi_driver ca8210_spi_driver = {
+	.driver = {
+		.name =                 DRIVER_NAME,
+		.owner =                THIS_MODULE,
+		.of_match_table =       of_match_ptr(ca8210_of_ids),
+	},
+	.probe  =                       ca8210_probe,
+	.remove =                       ca8210_remove
+};
+
+module_spi_driver(ca8210_spi_driver);
+
+MODULE_AUTHOR("Harry Morris <h.morris@cascoda.com>");
+MODULE_DESCRIPTION("CA-8210 SoftMAC driver");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION("1.0");
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 7b131f8e4093..bd63289c55e8 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -18,6 +18,7 @@
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/ieee802154.h>
 #include <linux/irq.h>
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 800a46c8d26c..7919369c0a72 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -26,6 +26,7 @@
 #include <linux/netfilter.h>
 #include <net/ip.h>
 #include <net/ip6_route.h>
+#include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/route.h>
 #include <net/addrconf.h>
@@ -91,6 +92,7 @@ struct ipvl_addr {
 
 struct ipvl_port {
 	struct net_device	*dev;
+	possible_net_t		pnet;
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	struct list_head	ipvlans;
 	u16			mode;
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index aa8575ccbce3..618ed88fad0f 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -9,7 +9,11 @@
 
 #include "ipvlan.h"
 
-static u32 ipvl_nf_hook_refcnt = 0;
+static unsigned int ipvlan_netid __read_mostly;
+
+struct ipvlan_netns {
+	unsigned int ipvl_nf_hook_refcnt;
+};
 
 static struct nf_hook_ops ipvl_nfops[] __read_mostly = {
 	{
@@ -35,28 +39,34 @@ static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev)
 	ipvlan->dev->mtu = dev->mtu;
 }
 
-static int ipvlan_register_nf_hook(void)
+static int ipvlan_register_nf_hook(struct net *net)
 {
+	struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid);
 	int err = 0;
 
-	if (!ipvl_nf_hook_refcnt) {
-		err = _nf_register_hooks(ipvl_nfops, ARRAY_SIZE(ipvl_nfops));
+	if (!vnet->ipvl_nf_hook_refcnt) {
+		err = nf_register_net_hooks(net, ipvl_nfops,
+					    ARRAY_SIZE(ipvl_nfops));
 		if (!err)
-			ipvl_nf_hook_refcnt = 1;
+			vnet->ipvl_nf_hook_refcnt = 1;
 	} else {
-		ipvl_nf_hook_refcnt++;
+		vnet->ipvl_nf_hook_refcnt++;
 	}
 
 	return err;
 }
 
-static void ipvlan_unregister_nf_hook(void)
+static void ipvlan_unregister_nf_hook(struct net *net)
 {
-	WARN_ON(!ipvl_nf_hook_refcnt);
+	struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid);
+
+	if (WARN_ON(!vnet->ipvl_nf_hook_refcnt))
+		return;
 
-	ipvl_nf_hook_refcnt--;
-	if (!ipvl_nf_hook_refcnt)
-		_nf_unregister_hooks(ipvl_nfops, ARRAY_SIZE(ipvl_nfops));
+	vnet->ipvl_nf_hook_refcnt--;
+	if (!vnet->ipvl_nf_hook_refcnt)
+		nf_unregister_net_hooks(net, ipvl_nfops,
+					ARRAY_SIZE(ipvl_nfops));
 }
 
 static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
@@ -69,7 +79,7 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 	if (port->mode != nval) {
 		if (nval == IPVLAN_MODE_L3S) {
 			/* New mode is L3S */
-			err = ipvlan_register_nf_hook();
+			err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
 			if (!err) {
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
 				mdev->priv_flags |= IFF_L3MDEV_MASTER;
@@ -78,7 +88,7 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
 			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
-			ipvlan_unregister_nf_hook();
+			ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
 			mdev->l3mdev_ops = NULL;
 		}
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
@@ -111,6 +121,7 @@ static int ipvlan_port_create(struct net_device *dev)
 	if (!port)
 		return -ENOMEM;
 
+	write_pnet(&port->pnet, dev_net(dev));
 	port->dev = dev;
 	port->mode = IPVLAN_MODE_L3;
 	INIT_LIST_HEAD(&port->ipvlans);
@@ -142,7 +153,7 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	if (port->mode == IPVLAN_MODE_L3S) {
 		dev->priv_flags &= ~IFF_L3MDEV_MASTER;
-		ipvlan_unregister_nf_hook();
+		ipvlan_unregister_nf_hook(dev_net(dev));
 		dev->l3mdev_ops = NULL;
 	}
 	netdev_rx_handler_unregister(dev);
@@ -673,6 +684,24 @@ static int ipvlan_device_event(struct notifier_block *unused,
 							 ipvlan->dev);
 		break;
 
+	case NETDEV_REGISTER: {
+		struct net *oldnet, *newnet = dev_net(dev);
+		struct ipvlan_netns *old_vnet;
+
+		oldnet = read_pnet(&port->pnet);
+		if (net_eq(newnet, oldnet))
+			break;
+
+		write_pnet(&port->pnet, newnet);
+
+		old_vnet = net_generic(oldnet, ipvlan_netid);
+		if (!old_vnet->ipvl_nf_hook_refcnt)
+			break;
+
+		ipvlan_register_nf_hook(newnet);
+		ipvlan_unregister_nf_hook(oldnet);
+		break;
+	}
 	case NETDEV_UNREGISTER:
 		if (dev->reg_state != NETREG_UNREGISTERING)
 			break;
@@ -854,6 +883,23 @@ static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = {
 	.notifier_call = ipvlan_addr6_event,
 };
 
+static void ipvlan_ns_exit(struct net *net)
+{
+	struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid);
+
+	if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) {
+		vnet->ipvl_nf_hook_refcnt = 0;
+		nf_unregister_net_hooks(net, ipvl_nfops,
+					ARRAY_SIZE(ipvl_nfops));
+	}
+}
+
+static struct pernet_operations ipvlan_net_ops = {
+	.id = &ipvlan_netid,
+	.size = sizeof(struct ipvlan_netns),
+	.exit = ipvlan_ns_exit,
+};
+
 static int __init ipvlan_init_module(void)
 {
 	int err;
@@ -863,10 +909,16 @@ static int __init ipvlan_init_module(void)
 	register_inet6addr_notifier(&ipvlan_addr6_notifier_block);
 	register_inetaddr_notifier(&ipvlan_addr4_notifier_block);
 
-	err = ipvlan_link_register(&ipvlan_link_ops);
+	err = register_pernet_subsys(&ipvlan_net_ops);
 	if (err < 0)
 		goto error;
 
+	err = ipvlan_link_register(&ipvlan_link_ops);
+	if (err < 0) {
+		unregister_pernet_subsys(&ipvlan_net_ops);
+		goto error;
+	}
+
 	return 0;
 error:
 	unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
@@ -878,6 +930,7 @@ error:
 static void __exit ipvlan_cleanup_module(void)
 {
 	rtnl_link_unregister(&ipvlan_link_ops);
+	unregister_pernet_subsys(&ipvlan_net_ops);
 	unregister_netdevice_notifier(&ipvlan_notifier_block);
 	unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
 	unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
index ffedad2a360a..15b920086251 100644
--- a/drivers/net/irda/vlsi_ir.c
+++ b/drivers/net/irda/vlsi_ir.c
@@ -418,8 +418,9 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr
 		memset(rd, 0, sizeof(*rd));
 		rd->hw = hwmap + i;
 		rd->buf = kmalloc(len, GFP_KERNEL|GFP_DMA);
-		if (rd->buf == NULL ||
-		    !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) {
+		if (rd->buf)
+			busaddr = pci_map_single(pdev, rd->buf, len, dir);
+		if (rd->buf == NULL || pci_dma_mapping_error(pdev, busaddr)) {
 			if (rd->buf) {
 				net_err_ratelimited("%s: failed to create PCI-MAP for %p\n",
 						    __func__, rd->buf);
@@ -430,8 +431,7 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr
 				rd = r->rd + j;
 				busaddr = rd_get_addr(rd);
 				rd_set_addr_status(rd, 0, 0);
-				if (busaddr)
-					pci_unmap_single(pdev, busaddr, len, dir);
+				pci_unmap_single(pdev, busaddr, len, dir);
 				kfree(rd->buf);
 				rd->buf = NULL;
 			}
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b23b71981fd5..224f65cb576b 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -13,7 +13,7 @@
  *
  *		Alan Cox	:	Fixed oddments for NET3.014
  *		Alan Cox	:	Rejig for NET3.029 snap #3
- *		Alan Cox	: 	Fixed NET3.029 bugs and sped up
+ *		Alan Cox	:	Fixed NET3.029 bugs and sped up
  *		Larry McVoy	:	Tiny tweak to double performance
  *		Alan Cox	:	Backed out LMV's tweak - the linux mm
  *					can't take it...
@@ -41,7 +41,7 @@
 #include <linux/in.h>
 
 #include <linux/uaccess.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
@@ -55,6 +55,7 @@
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/percpu.h>
+#include <linux/net_tstamp.h>
 #include <net/net_namespace.h>
 #include <linux/u64_stats_sync.h>
 
@@ -64,8 +65,7 @@ struct pcpu_lstats {
 	struct u64_stats_sync	syncp;
 };
 
-/*
- * The higher levels take care of making this non-reentrant (it's
+/* The higher levels take care of making this non-reentrant (it's
  * called with bh's disabled).
  */
 static netdev_tx_t loopback_xmit(struct sk_buff *skb,
@@ -74,6 +74,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 	struct pcpu_lstats *lb_stats;
 	int len;
 
+	skb_tx_timestamp(skb);
 	skb_orphan(skb);
 
 	/* Before queueing this packet to netif_rx(),
@@ -129,8 +130,21 @@ static u32 always_on(struct net_device *dev)
 	return 1;
 }
 
+static int loopback_get_ts_info(struct net_device *netdev,
+				struct ethtool_ts_info *ts_info)
+{
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				   SOF_TIMESTAMPING_RX_SOFTWARE |
+				   SOF_TIMESTAMPING_SOFTWARE;
+
+	ts_info->phc_index = -1;
+
+	return 0;
+};
+
 static const struct ethtool_ops loopback_ethtool_ops = {
 	.get_link		= always_on,
+	.get_ts_info		= loopback_get_ts_info,
 };
 
 static int loopback_dev_init(struct net_device *dev)
@@ -149,14 +163,13 @@ static void loopback_dev_free(struct net_device *dev)
 }
 
 static const struct net_device_ops loopback_ops = {
-	.ndo_init      = loopback_dev_init,
-	.ndo_start_xmit= loopback_xmit,
+	.ndo_init        = loopback_dev_init,
+	.ndo_start_xmit  = loopback_xmit,
 	.ndo_get_stats64 = loopback_get_stats64,
 	.ndo_set_mac_address = eth_mac_addr,
 };
 
-/*
- * The loopback device is special. There is only one instance
+/* The loopback device is special. There is only one instance
  * per network namespace.
  */
 static void loopback_setup(struct net_device *dev)
@@ -170,7 +183,7 @@ static void loopback_setup(struct net_device *dev)
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
-	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
+	dev->features		= NETIF_F_SG | NETIF_F_FRAGLIST
 		| NETIF_F_GSO_SOFTWARE
 		| NETIF_F_HW_CSUM
 		| NETIF_F_RXCSUM
@@ -206,7 +219,6 @@ static __net_init int loopback_net_init(struct net *net)
 	net->loopback_dev = dev;
 	return 0;
 
-
 out_free_netdev:
 	free_netdev(dev);
 out:
@@ -217,5 +229,5 @@ out:
 
 /* Registered in net/core/dev.c */
 struct pernet_operations __net_initdata loopback_net_ops = {
-       .init = loopback_net_init,
+	.init = loopback_net_init,
 };
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index ff0a5ed3ca80..cdc347be68f2 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -617,7 +617,8 @@ static void macsec_encrypt_done(struct crypto_async_request *base, int err)
 
 static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
 					     unsigned char **iv,
-					     struct scatterlist **sg)
+					     struct scatterlist **sg,
+					     int num_frags)
 {
 	size_t size, iv_offset, sg_offset;
 	struct aead_request *req;
@@ -629,7 +630,7 @@ static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
 
 	size = ALIGN(size, __alignof__(struct scatterlist));
 	sg_offset = size;
-	size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1);
+	size += sizeof(struct scatterlist) * num_frags;
 
 	tmp = kmalloc(size, GFP_ATOMIC);
 	if (!tmp)
@@ -649,6 +650,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 {
 	int ret;
 	struct scatterlist *sg;
+	struct sk_buff *trailer;
 	unsigned char *iv;
 	struct ethhdr *eth;
 	struct macsec_eth_header *hh;
@@ -723,7 +725,14 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg);
+	ret = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(ret < 0)) {
+		macsec_txsa_put(tx_sa);
+		kfree_skb(skb);
+		return ERR_PTR(ret);
+	}
+
+	req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret);
 	if (!req) {
 		macsec_txsa_put(tx_sa);
 		kfree_skb(skb);
@@ -732,7 +741,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 
 	macsec_fill_iv(iv, secy->sci, pn);
 
-	sg_init_table(sg, MAX_SKB_FRAGS + 1);
+	sg_init_table(sg, ret);
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	if (tx_sc->encrypt) {
@@ -917,6 +926,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 {
 	int ret;
 	struct scatterlist *sg;
+	struct sk_buff *trailer;
 	unsigned char *iv;
 	struct aead_request *req;
 	struct macsec_eth_header *hdr;
@@ -927,7 +937,12 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg);
+	ret = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(ret < 0)) {
+		kfree_skb(skb);
+		return ERR_PTR(ret);
+	}
+	req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret);
 	if (!req) {
 		kfree_skb(skb);
 		return ERR_PTR(-ENOMEM);
@@ -936,7 +951,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	hdr = (struct macsec_eth_header *)skb->data;
 	macsec_fill_iv(iv, sci, ntohl(hdr->packet_number));
 
-	sg_init_table(sg, MAX_SKB_FRAGS + 1);
+	sg_init_table(sg, ret);
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	if (hdr->tci_an & MACSEC_TCI_E) {
@@ -1590,8 +1605,9 @@ static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa)
 	if (!attrs[MACSEC_ATTR_SA_CONFIG])
 		return -EINVAL;
 
-	if (nla_parse_nested(tb_sa, MACSEC_SA_ATTR_MAX, attrs[MACSEC_ATTR_SA_CONFIG],
-			     macsec_genl_sa_policy))
+	if (nla_parse_nested(tb_sa, MACSEC_SA_ATTR_MAX,
+			     attrs[MACSEC_ATTR_SA_CONFIG],
+			     macsec_genl_sa_policy, NULL))
 		return -EINVAL;
 
 	return 0;
@@ -1602,8 +1618,9 @@ static int parse_rxsc_config(struct nlattr **attrs, struct nlattr **tb_rxsc)
 	if (!attrs[MACSEC_ATTR_RXSC_CONFIG])
 		return -EINVAL;
 
-	if (nla_parse_nested(tb_rxsc, MACSEC_RXSC_ATTR_MAX, attrs[MACSEC_ATTR_RXSC_CONFIG],
-			     macsec_genl_rxsc_policy))
+	if (nla_parse_nested(tb_rxsc, MACSEC_RXSC_ATTR_MAX,
+			     attrs[MACSEC_ATTR_RXSC_CONFIG],
+			     macsec_genl_rxsc_policy, NULL))
 		return -EINVAL;
 
 	return 0;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 9261722960a7..b34eaaae03fd 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1139,6 +1139,7 @@ static int macvlan_port_create(struct net_device *dev)
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
@@ -1147,7 +1148,15 @@ static void macvlan_port_destroy(struct net_device *dev)
 	 * but we need to cancel it and purge left skbs if any.
 	 */
 	cancel_work_sync(&port->bc_work);
-	__skb_queue_purge(&port->bc_queue);
+
+	while ((skb = __skb_dequeue(&port->bc_queue))) {
+		const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+		if (src)
+			dev_put(src->dev);
+
+		kfree_skb(skb);
+	}
 
 	kfree(port);
 }
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 36877ba65516..4daf3d0926a8 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -372,18 +372,19 @@ static void ntb_get_drvinfo(struct net_device *ndev,
 	strlcpy(info->bus_info, pci_name(dev->pdev), sizeof(info->bus_info));
 }
 
-static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ntb_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
-	cmd->supported = SUPPORTED_Backplane;
-	cmd->advertising = ADVERTISED_Backplane;
-	ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
-	cmd->duplex = DUPLEX_FULL;
-	cmd->port = PORT_OTHER;
-	cmd->phy_address = 0;
-	cmd->transceiver = XCVR_DUMMY1;
-	cmd->autoneg = AUTONEG_ENABLE;
-	cmd->maxtxpkt = 0;
-	cmd->maxrxpkt = 0;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, Backplane);
+
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_FULL;
+	cmd->base.port = PORT_OTHER;
+	cmd->base.phy_address = 0;
+	cmd->base.autoneg = AUTONEG_ENABLE;
 
 	return 0;
 }
@@ -391,7 +392,7 @@ static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 static const struct ethtool_ops ntb_ethtool_ops = {
 	.get_drvinfo = ntb_get_drvinfo,
 	.get_link = ethtool_op_get_link,
-	.get_settings = ntb_get_settings,
+	.get_link_ksettings = ntb_get_link_ksettings,
 };
 
 static const struct ntb_queue_handlers ntb_netdev_handlers = {
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 8dbd59baa34d..60ffc9da6a28 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -2,33 +2,12 @@
 # PHY Layer Configuration
 #
 
-menuconfig PHYLIB
-	tristate "PHY Device support and infrastructure"
-	depends on NETDEVICES
+menuconfig MDIO_DEVICE
+	tristate "MDIO bus device drivers"
 	help
-	  Ethernet controllers are usually attached to PHY
-	  devices.  This option provides infrastructure for
-	  managing PHY devices.
-
-if PHYLIB
+	   MDIO devices and driver infrastructure code.
 
-config SWPHY
-	bool
-
-config LED_TRIGGER_PHY
-	bool "Support LED triggers for tracking link state"
-	depends on LEDS_TRIGGERS
-	---help---
-	  Adds support for a set of LED trigger events per-PHY.  Link
-	  state change will trigger the events, for consumption by an
-	  LED class driver.  There are triggers for each link speed currently
-	  supported by the phy, and are of the form:
-	       <mii bus id>:<phy>:<speed>
-
-	  Where speed is in the form:
-		<Speed in megabits>Mbps or <Speed in gigabits>Gbps
-
-comment "MDIO bus device drivers"
+if MDIO_DEVICE
 
 config MDIO_BCM_IPROC
 	tristate "Broadcom iProc MDIO bus controller"
@@ -40,7 +19,7 @@ config MDIO_BCM_IPROC
 
 config MDIO_BCM_UNIMAC
 	tristate "Broadcom UniMAC MDIO bus controller"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && OF_MDIO
 	help
 	  This module provides a driver for the Broadcom UniMAC MDIO busses.
 	  This hardware can be found in the Broadcom GENET Ethernet MAC
@@ -49,6 +28,7 @@ config MDIO_BCM_UNIMAC
 
 config MDIO_BITBANG
 	tristate "Bitbanged MDIO buses"
+	depends on !(MDIO_DEVICE=y && PHYLIB=m)
 	help
 	  This module implements the MDIO bus protocol in software,
 	  for use by low level drivers that export the ability to
@@ -160,6 +140,36 @@ config MDIO_XGENE
 	  This module provides a driver for the MDIO busses found in the
 	  APM X-Gene SoC's.
 
+endif
+
+menuconfig PHYLIB
+	tristate "PHY Device support and infrastructure"
+	depends on NETDEVICES
+	select MDIO_DEVICE
+	help
+	  Ethernet controllers are usually attached to PHY
+	  devices.  This option provides infrastructure for
+	  managing PHY devices.
+
+if PHYLIB
+
+config SWPHY
+	bool
+
+config LED_TRIGGER_PHY
+	bool "Support LED triggers for tracking link state"
+	depends on LEDS_TRIGGERS
+	---help---
+	  Adds support for a set of LED trigger events per-PHY.  Link
+	  state change will trigger the events, for consumption by an
+	  LED class driver.  There are triggers for each link speed currently
+	  supported by the phy, and are of the form:
+	       <mii bus id>:<phy>:<speed>
+
+	  Where speed is in the form:
+		<Speed in megabits>Mbps or <Speed in gigabits>Gbps
+
+
 comment "MII PHY device drivers"
 
 config AMD_PHY
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 407b0b601ea8..e36db9a2ba38 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -1,7 +1,20 @@
 # Makefile for Linux PHY drivers and MDIO bus drivers
 
-libphy-y			:= phy.o phy_device.o mdio_bus.o mdio_device.o \
-				   mdio-boardinfo.o
+libphy-y			:= phy.o phy-core.o phy_device.o
+mdio-bus-y			+= mdio_bus.o mdio_device.o
+
+ifdef CONFIG_MDIO_DEVICE
+obj-y				+= mdio-boardinfo.o
+endif
+
+# PHYLIB implies MDIO_DEVICE, in that case, we have a bunch of circular
+# dependencies that does not make it possible to split mdio-bus objects into a
+# dedicated loadable module, so we bundle them all together into libphy.ko
+ifdef CONFIG_PHYLIB
+libphy-y			+= $(mdio-bus-y)
+else
+obj-$(CONFIG_MDIO_DEVICE)	+= mdio-bus.o
+endif
 libphy-$(CONFIG_SWPHY)		+= swphy.o
 libphy-$(CONFIG_LED_TRIGGER_PHY)	+= phy_led_triggers.o
 
diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index ab9ad689617c..171010eb4d9c 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Broadcom Corporation
+ * Copyright (C) 2015-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -201,8 +201,7 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
 	int val;
 
 	/* Enable EEE at PHY level */
-	val = phy_read_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
-				    MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL);
 	if (val < 0)
 		return val;
 
@@ -211,22 +210,19 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
 	else
 		val &= ~(LPI_FEATURE_EN | LPI_FEATURE_EN_DIG1000X);
 
-	phy_write_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
-			       MDIO_MMD_AN, (u32)val);
+	phy_write_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL, (u32)val);
 
 	/* Advertise EEE */
-	val = phy_read_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV,
-				    MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV);
 	if (val < 0)
 		return val;
 
 	if (enable)
-		val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+		val |= (MDIO_EEE_100TX | MDIO_EEE_1000T);
 	else
-		val &= ~(MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+		val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T);
 
-	phy_write_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV,
-			       MDIO_MMD_AN, (u32)val);
+	phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val);
 
 	return 0;
 }
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index d1c2614dad3a..caa9f6e17f34 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom BCM7xxx internal transceivers support.
  *
- * Copyright (C) 2014, Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -19,7 +19,7 @@
 
 /* Broadcom BCM7xxx internal PHY registers */
 
-/* 40nm only register definitions */
+/* EPHY only register definitions */
 #define MII_BCM7XXX_100TX_AUX_CTL	0x10
 #define MII_BCM7XXX_100TX_FALSE_CAR	0x13
 #define MII_BCM7XXX_100TX_DISC		0x14
@@ -27,6 +27,19 @@
 #define  MII_BCM7XXX_64CLK_MDIO		BIT(12)
 #define MII_BCM7XXX_TEST		0x1f
 #define  MII_BCM7XXX_SHD_MODE_2		BIT(2)
+#define MII_BCM7XXX_SHD_2_ADDR_CTRL	0xe
+#define MII_BCM7XXX_SHD_2_CTRL_STAT	0xf
+#define MII_BCM7XXX_SHD_2_BIAS_TRIM	0x1a
+#define MII_BCM7XXX_SHD_3_AN_EEE_ADV	0x3
+#define MII_BCM7XXX_SHD_3_PCS_CTRL_2	0x6
+#define  MII_BCM7XXX_PCS_CTRL_2_DEF	0x4400
+#define MII_BCM7XXX_SHD_3_AN_STAT	0xb
+#define  MII_BCM7XXX_AN_NULL_MSG_EN	BIT(0)
+#define  MII_BCM7XXX_AN_EEE_EN		BIT(1)
+#define MII_BCM7XXX_SHD_3_EEE_THRESH	0xe
+#define  MII_BCM7XXX_EEE_THRESH_DEF	0x50
+#define MII_BCM7XXX_SHD_3_TL4		0x23
+#define  MII_BCM7XXX_TL4_RST_MSK	(BIT(2) | BIT(1))
 
 /* 28nm only register definitions */
 #define MISC_ADDR(base, channel)	base, channel
@@ -286,6 +299,181 @@ static int phy_set_clr_bits(struct phy_device *dev, int location,
 	return v;
 }
 
+static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* set shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+			       MII_BCM7XXX_SHD_MODE_2, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Set current trim values INT_trim = -1, Ext_trim =0 */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_BIAS_TRIM, 0x3BE0);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Cal reset */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_TL4);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			       MII_BCM7XXX_TL4_RST_MSK, 0);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Cal reset disable */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_TL4);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			       0, MII_BCM7XXX_TL4_RST_MSK);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+reset_shadow_mode:
+	/* reset shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+			       MII_BCM7XXX_SHD_MODE_2);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/* The 28nm EPHY does not support Clause 45 (MMD) used by bcm-phy-lib */
+static int bcm7xxx_28nm_ephy_apd_enable(struct phy_device *phydev)
+{
+	int ret;
+
+	/* set shadow mode 1 */
+	ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST,
+			       MII_BRCM_FET_BT_SRE, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Enable auto-power down */
+	ret = phy_set_clr_bits(phydev, MII_BRCM_FET_SHDW_AUXSTAT2,
+			       MII_BRCM_FET_SHDW_AS2_APDE, 0);
+	if (ret < 0)
+		return ret;
+
+	/* reset shadow mode 1 */
+	ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, 0,
+			       MII_BRCM_FET_BT_SRE);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int bcm7xxx_28nm_ephy_eee_enable(struct phy_device *phydev)
+{
+	int ret;
+
+	/* set shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+			       MII_BCM7XXX_SHD_MODE_2, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Advertise supported modes */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_AN_EEE_ADV);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			MDIO_EEE_100TX);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Restore Defaults */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_PCS_CTRL_2);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			MII_BCM7XXX_PCS_CTRL_2_DEF);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_EEE_THRESH);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			MII_BCM7XXX_EEE_THRESH_DEF);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Enable EEE autonegotiation */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_AN_STAT);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			(MII_BCM7XXX_AN_NULL_MSG_EN | MII_BCM7XXX_AN_EEE_EN));
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+reset_shadow_mode:
+	/* reset shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+			       MII_BCM7XXX_SHD_MODE_2);
+	if (ret < 0)
+		return ret;
+
+	/* Restart autoneg */
+	phy_write(phydev, MII_BMCR,
+		  (BMCR_SPEED100 | BMCR_ANENABLE | BMCR_ANRESTART));
+
+	return 0;
+}
+
+static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev)
+{
+	u8 rev = phydev->phy_id & ~phydev->drv->phy_id_mask;
+	int ret = 0;
+
+	pr_info_once("%s: %s PHY revision: 0x%02x\n",
+		     phydev_name(phydev), phydev->drv->name, rev);
+
+	/* Dummy read to a register to workaround a possible issue upon reset
+	 * where the internal inverter may not allow the first MDIO transaction
+	 * to pass the MDIO management controller and make us return 0xffff for
+	 * such reads.
+	 */
+	phy_read(phydev, MII_BMSR);
+
+	/* Apply AFE software work-around if necessary */
+	if (rev == 0x01) {
+		ret = bcm7xxx_28nm_ephy_01_afe_config_init(phydev);
+		if (ret)
+			return ret;
+	}
+
+	ret = bcm7xxx_28nm_ephy_eee_enable(phydev);
+	if (ret)
+		return ret;
+
+	return bcm7xxx_28nm_ephy_apd_enable(phydev);
+}
+
+static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Re-apply workarounds coming out suspend/resume */
+	ret = bcm7xxx_28nm_ephy_config_init(phydev);
+	if (ret)
+		return ret;
+
+	return genphy_config_aneg(phydev);
+}
+
 static int bcm7xxx_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -434,6 +622,23 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
 	.probe		= bcm7xxx_28nm_probe,				\
 }
 
+#define BCM7XXX_28NM_EPHY(_oui, _name)					\
+{									\
+	.phy_id		= (_oui),					\
+	.phy_id_mask	= 0xfffffff0,					\
+	.name		= _name,					\
+	.features	= PHY_BASIC_FEATURES,				\
+	.flags		= PHY_IS_INTERNAL,				\
+	.config_init	= bcm7xxx_28nm_ephy_config_init,		\
+	.config_aneg	= genphy_config_aneg,				\
+	.read_status	= genphy_read_status,				\
+	.resume		= bcm7xxx_28nm_ephy_resume,			\
+	.get_sset_count	= bcm_phy_get_sset_count,			\
+	.get_strings	= bcm_phy_get_strings,				\
+	.get_stats	= bcm7xxx_28nm_get_phy_stats,			\
+	.probe		= bcm7xxx_28nm_probe,				\
+}
+
 #define BCM7XXX_40NM_EPHY(_oui, _name)					\
 {									\
 	.phy_id         = (_oui),					\
@@ -450,6 +655,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
 
 static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7268, "Broadcom BCM7268"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7271, "Broadcom BCM7271"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"),
@@ -466,6 +674,9 @@ static struct phy_driver bcm7xxx_driver[] = {
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7250, 0xfffffff0, },
+	{ PHY_ID_BCM7260, 0xfffffff0, },
+	{ PHY_ID_BCM7268, 0xfffffff0, },
+	{ PHY_ID_BCM7271, 0xfffffff0, },
 	{ PHY_ID_BCM7278, 0xfffffff0, },
 	{ PHY_ID_BCM7364, 0xfffffff0, },
 	{ PHY_ID_BCM7366, 0xfffffff0, },
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 9cd8b27d1292..a32dc5d11e89 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -74,27 +74,40 @@ static int bcm54612e_config_init(struct phy_device *phydev)
 	return 0;
 }
 
-static int bcm54810_config(struct phy_device *phydev)
+static int bcm5481x_config(struct phy_device *phydev)
 {
 	int rc, val;
 
-	val = bcm_phy_read_exp(phydev, BCM54810_EXP_BROADREACH_LRE_MISC_CTL);
-	val &= ~BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN;
-	rc = bcm_phy_write_exp(phydev, BCM54810_EXP_BROADREACH_LRE_MISC_CTL,
-			       val);
-	if (rc < 0)
-		return rc;
-
+	/* handling PHY's internal RX clock delay */
 	val = bcm54xx_auxctl_read(phydev, MII_BCM54XX_AUXCTL_SHDWSEL_MISC);
-	val &= ~MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN;
 	val |= MII_BCM54XX_AUXCTL_MISC_WREN;
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII ||
+	    phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
+		/* Disable RGMII RXC-RXD skew */
+		val &= ~MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN;
+	}
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+	    phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
+		/* Enable RGMII RXC-RXD skew */
+		val |= MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN;
+	}
 	rc = bcm54xx_auxctl_write(phydev, MII_BCM54XX_AUXCTL_SHDWSEL_MISC,
 				  val);
 	if (rc < 0)
 		return rc;
 
+	/* handling PHY's internal TX clock delay */
 	val = bcm_phy_read_shadow(phydev, BCM54810_SHD_CLK_CTL);
-	val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN;
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII ||
+	    phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
+		/* Disable internal TX clock delay */
+		val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN;
+	}
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+	    phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
+		/* Enable internal TX clock delay */
+		val |= BCM54810_SHD_CLK_CTL_GTXCLK_EN;
+	}
 	rc = bcm_phy_write_shadow(phydev, BCM54810_SHD_CLK_CTL, val);
 	if (rc < 0)
 		return rc;
@@ -244,7 +257,7 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev)
 
 static int bcm54xx_config_init(struct phy_device *phydev)
 {
-	int reg, err;
+	int reg, err, val;
 
 	reg = phy_read(phydev, MII_BCM54XX_ECR);
 	if (reg < 0)
@@ -283,8 +296,14 @@ static int bcm54xx_config_init(struct phy_device *phydev)
 		if (err)
 			return err;
 	} else if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810) {
-		err = bcm54810_config(phydev);
-		if (err)
+		/* For BCM54810, we need to disable BroadR-Reach function */
+		val = bcm_phy_read_exp(phydev,
+				       BCM54810_EXP_BROADREACH_LRE_MISC_CTL);
+		val &= ~BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN;
+		err = bcm_phy_write_exp(phydev,
+					BCM54810_EXP_BROADREACH_LRE_MISC_CTL,
+					val);
+		if (err < 0)
 			return err;
 	}
 
@@ -392,29 +411,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev)
 	ret = genphy_config_aneg(phydev);
 
 	/* Then we can set up the delay. */
-	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
-		u16 reg;
-
-		/*
-		 * There is no BCM5481 specification available, so down
-		 * here is everything we know about "register 0x18". This
-		 * at least helps BCM5481 to successfully receive packets
-		 * on MPC8360E-RDK board. Peter Barada <peterb@logicpd.com>
-		 * says: "This sets delay between the RXD and RXC signals
-		 * instead of using trace lengths to achieve timing".
-		 */
-
-		/* Set RDX clk delay. */
-		reg = 0x7 | (0x7 << 12);
-		phy_write(phydev, 0x18, reg);
-
-		reg = phy_read(phydev, 0x18);
-		/* Set RDX-RXC skew. */
-		reg |= (1 << 8);
-		/* Write bits 14:0. */
-		reg |= (1 << 15);
-		phy_write(phydev, 0x18, reg);
-	}
+	bcm5481x_config(phydev);
 
 	if (of_property_read_bool(np, "enet-phy-lane-swap")) {
 		/* Lane Swap - Undocumented register...magic! */
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index e2460a57e4b1..ed0d10f54f26 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1438,8 +1438,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
 		skb_queue_tail(&dp83640->rx_queue, skb);
 		schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT);
-	} else {
-		netif_rx_ni(skb);
 	}
 
 	return true;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 19865530e0b1..b57f20e552ba 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -133,14 +133,14 @@ static int dp83867_config_port_mirroring(struct phy_device *phydev)
 		(struct dp83867_private *)phydev->priv;
 	u16 val;
 
-	val = phy_read_mmd_indirect(phydev, DP83867_CFG4, DP83867_DEVADDR);
+	val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4);
 
 	if (dp83867->port_mirroring == DP83867_PORT_MIRROING_EN)
 		val |= DP83867_CFG4_PORT_MIRROR_EN;
 	else
 		val &= ~DP83867_CFG4_PORT_MIRROR_EN;
 
-	phy_write_mmd_indirect(phydev, DP83867_CFG4, DP83867_DEVADDR, val);
+	phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, val);
 
 	return 0;
 }
@@ -231,8 +231,7 @@ static int dp83867_config_init(struct phy_device *phydev)
 		 * register's bit 11 (marked as RESERVED).
 		 */
 
-		bs = phy_read_mmd_indirect(phydev, DP83867_STRAP_STS1,
-					   DP83867_DEVADDR);
+		bs = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_STRAP_STS1);
 		if (bs & DP83867_STRAP_STS1_RESERVED)
 			val &= ~DP83867_PHYCR_RESERVED_MASK;
 
@@ -243,8 +242,7 @@ static int dp83867_config_init(struct phy_device *phydev)
 
 	if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) &&
 	    (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) {
-		val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL,
-					    DP83867_DEVADDR);
+		val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL);
 
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
 			val |= (DP83867_RGMII_TX_CLK_DELAY_EN | DP83867_RGMII_RX_CLK_DELAY_EN);
@@ -255,25 +253,24 @@ static int dp83867_config_init(struct phy_device *phydev)
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
 			val |= DP83867_RGMII_RX_CLK_DELAY_EN;
 
-		phy_write_mmd_indirect(phydev, DP83867_RGMIICTL,
-				       DP83867_DEVADDR, val);
+		phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL, val);
 
 		delay = (dp83867->rx_id_delay |
 			(dp83867->tx_id_delay << DP83867_RGMII_TX_CLK_DELAY_SHIFT));
 
-		phy_write_mmd_indirect(phydev, DP83867_RGMIIDCTL,
-				       DP83867_DEVADDR, delay);
+		phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL,
+			      delay);
 
 		if (dp83867->io_impedance >= 0) {
-			val = phy_read_mmd_indirect(phydev, DP83867_IO_MUX_CFG,
-						    DP83867_DEVADDR);
+			val = phy_read_mmd(phydev, DP83867_DEVADDR,
+					   DP83867_IO_MUX_CFG);
 
 			val &= ~DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL;
 			val |= dp83867->io_impedance &
 			       DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL;
 
-			phy_write_mmd_indirect(phydev, DP83867_IO_MUX_CFG,
-					       DP83867_DEVADDR, val);
+			phy_write_mmd(phydev, DP83867_DEVADDR,
+				      DP83867_IO_MUX_CFG, val);
 		}
 	}
 
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
index b1fd7bb0e4db..55f8c52dd2f1 100644
--- a/drivers/net/phy/intel-xway.c
+++ b/drivers/net/phy/intel-xway.c
@@ -166,13 +166,13 @@ static int xway_gphy_config_init(struct phy_device *phydev)
 	/* Clear all pending interrupts */
 	phy_read(phydev, XWAY_MDIO_ISTAT);
 
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCH, MDIO_MMD_VEND2,
-			       XWAY_MMD_LEDCH_NACS_NONE |
-			       XWAY_MMD_LEDCH_SBF_F02HZ |
-			       XWAY_MMD_LEDCH_FBF_F16HZ);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCL, MDIO_MMD_VEND2,
-			       XWAY_MMD_LEDCH_CBLINK_NONE |
-			       XWAY_MMD_LEDCH_SCAN_NONE);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LEDCH,
+		      XWAY_MMD_LEDCH_NACS_NONE |
+		      XWAY_MMD_LEDCH_SBF_F02HZ |
+		      XWAY_MMD_LEDCH_FBF_F16HZ);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LEDCL,
+		      XWAY_MMD_LEDCH_CBLINK_NONE |
+		      XWAY_MMD_LEDCH_SCAN_NONE);
 
 	/**
 	 * In most cases only one LED is connected to this phy, so
@@ -183,12 +183,12 @@ static int xway_gphy_config_init(struct phy_device *phydev)
 	ledxh = XWAY_MMD_LEDxH_BLINKF_NONE | XWAY_MMD_LEDxH_CON_LINK10XX;
 	ledxl = XWAY_MMD_LEDxL_PULSE_TXACT | XWAY_MMD_LEDxL_PULSE_RXACT |
 		XWAY_MMD_LEDxL_BLINKS_NONE;
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0H, MDIO_MMD_VEND2, ledxh);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0L, MDIO_MMD_VEND2, ledxl);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1H, MDIO_MMD_VEND2, ledxh);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1L, MDIO_MMD_VEND2, ledxl);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2H, MDIO_MMD_VEND2, ledxh);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2L, MDIO_MMD_VEND2, ledxl);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED0H, ledxh);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED0L, ledxl);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED1H, ledxh);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED1L, ledxl);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2H, ledxh);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2L, ledxl);
 
 	return 0;
 }
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index f9d0fa315a47..272b051a0199 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1883,17 +1883,6 @@ static int m88e1510_probe(struct phy_device *phydev)
 	return m88e1510_hwmon_probe(phydev);
 }
 
-static void marvell_remove(struct phy_device *phydev)
-{
-#ifdef CONFIG_HWMON
-
-	struct marvell_priv *priv = phydev->priv;
-
-	if (priv && priv->hwmon_dev)
-		hwmon_device_unregister(priv->hwmon_dev);
-#endif
-}
-
 static struct phy_driver marvell_drivers[] = {
 	{
 		.phy_id = MARVELL_PHY_ID_88E1101,
@@ -1974,7 +1963,6 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1121_probe,
-		.remove = &marvell_remove,
 		.config_init = &m88e1121_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
@@ -2087,7 +2075,6 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES | SUPPORTED_FIBRE,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1510_probe,
-		.remove = &marvell_remove,
 		.config_init = &m88e1510_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
@@ -2109,7 +2096,6 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = m88e1510_probe,
-		.remove = &marvell_remove,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
@@ -2127,7 +2113,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1545",
 		.probe = m88e1510_probe,
-		.remove = &marvell_remove,
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.config_init = &marvell_config_init,
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 8c73b2e771dd..34395230ce70 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom UniMAC MDIO bus controller driver
  *
- * Copyright (C) 2014, Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -228,6 +228,7 @@ static int unimac_mdio_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id unimac_mdio_ids[] = {
+	{ .compatible = "brcm,genet-mdio-v5", },
 	{ .compatible = "brcm,genet-mdio-v4", },
 	{ .compatible = "brcm,genet-mdio-v3", },
 	{ .compatible = "brcm,genet-mdio-v2", },
diff --git a/drivers/net/phy/mdio-boardinfo.c b/drivers/net/phy/mdio-boardinfo.c
index 6b988f77da08..1861f387820d 100644
--- a/drivers/net/phy/mdio-boardinfo.c
+++ b/drivers/net/phy/mdio-boardinfo.c
@@ -24,10 +24,12 @@ static DEFINE_MUTEX(mdio_board_lock);
  * @mdiodev: MDIO device pointer
  * Context: can sleep
  */
-void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus)
+void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus,
+					   int (*cb)
+					   (struct mii_bus *bus,
+					    struct mdio_board_info *bi))
 {
 	struct mdio_board_entry *be;
-	struct mdio_device *mdiodev;
 	struct mdio_board_info *bi;
 	int ret;
 
@@ -38,23 +40,14 @@ void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus)
 		if (strcmp(bus->id, bi->bus_id))
 			continue;
 
-		mdiodev = mdio_device_create(bus, bi->mdio_addr);
-		if (IS_ERR(mdiodev))
+		ret = cb(bus, bi);
+		if (ret)
 			continue;
 
-		strncpy(mdiodev->modalias, bi->modalias,
-			sizeof(mdiodev->modalias));
-		mdiodev->bus_match = mdio_device_bus_match;
-		mdiodev->dev.platform_data = (void *)bi->platform_data;
-
-		ret = mdio_device_register(mdiodev);
-		if (ret) {
-			mdio_device_free(mdiodev);
-			continue;
-		}
 	}
 	mutex_unlock(&mdio_board_lock);
 }
+EXPORT_SYMBOL(mdiobus_setup_mdiodev_from_board_info);
 
 /**
  * mdio_register_board_info - register MDIO devices for a given board
@@ -84,3 +77,4 @@ int mdiobus_register_board_info(const struct mdio_board_info *info,
 
 	return 0;
 }
+EXPORT_SYMBOL(mdiobus_register_board_info);
diff --git a/drivers/net/phy/mdio-boardinfo.h b/drivers/net/phy/mdio-boardinfo.h
index 00f98163e90e..3a7f143904e8 100644
--- a/drivers/net/phy/mdio-boardinfo.h
+++ b/drivers/net/phy/mdio-boardinfo.h
@@ -14,6 +14,9 @@ struct mdio_board_entry {
 	struct mdio_board_info	board_info;
 };
 
-void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus);
+void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus,
+					   int (*cb)
+					   (struct mii_bus *bus,
+					    struct mdio_board_info *bi));
 
 #endif /* __MDIO_BOARD_INFO_H */
diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c
index f095051beb54..3e2ac07b6e37 100644
--- a/drivers/net/phy/mdio-xgene.c
+++ b/drivers/net/phy/mdio-xgene.c
@@ -229,7 +229,7 @@ static int xgene_xfi_mdio_write(struct mii_bus *bus, int phy_id,
 
 	val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg) |
 	      SET_VAL(HSTMIIMWRDAT, data);
-	xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, data);
+	xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val);
 
 	val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_WRITE);
 	xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index fa7d51f14869..a898e5c4ef1b 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -22,8 +22,11 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of_device.h>
 #include <linux/of_mdio.h>
+#include <linux/of_gpio.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
@@ -290,6 +293,36 @@ static inline void of_mdiobus_link_mdiodev(struct mii_bus *mdio,
 #endif
 
 /**
+ * mdiobus_create_device_from_board_info - create a full MDIO device given
+ * a mdio_board_info structure
+ * @bus: MDIO bus to create the devices on
+ * @bi: mdio_board_info structure describing the devices
+ *
+ * Returns 0 on success or < 0 on error.
+ */
+static int mdiobus_create_device(struct mii_bus *bus,
+				 struct mdio_board_info *bi)
+{
+	struct mdio_device *mdiodev;
+	int ret = 0;
+
+	mdiodev = mdio_device_create(bus, bi->mdio_addr);
+	if (IS_ERR(mdiodev))
+		return -ENODEV;
+
+	strncpy(mdiodev->modalias, bi->modalias,
+		sizeof(mdiodev->modalias));
+	mdiodev->bus_match = mdio_device_bus_match;
+	mdiodev->dev.platform_data = (void *)bi->platform_data;
+
+	ret = mdio_device_register(mdiodev);
+	if (ret)
+		mdio_device_free(mdiodev);
+
+	return ret;
+}
+
+/**
  * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
  * @bus: target mii_bus
  * @owner: module containing bus accessor functions
@@ -307,6 +340,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 {
 	struct mdio_device *mdiodev;
 	int i, err;
+	struct gpio_desc *gpiod;
 
 	if (NULL == bus || NULL == bus->name ||
 	    NULL == bus->read || NULL == bus->write)
@@ -333,6 +367,35 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 	if (bus->reset)
 		bus->reset(bus);
 
+	/* de-assert bus level PHY GPIO resets */
+	if (bus->num_reset_gpios > 0) {
+		bus->reset_gpiod = devm_kcalloc(&bus->dev,
+						 bus->num_reset_gpios,
+						 sizeof(struct gpio_desc *),
+						 GFP_KERNEL);
+		if (!bus->reset_gpiod)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < bus->num_reset_gpios; i++) {
+		gpiod = devm_gpiod_get_index(&bus->dev, "reset", i,
+					     GPIOD_OUT_LOW);
+		if (IS_ERR(gpiod)) {
+			err = PTR_ERR(gpiod);
+			if (err != -ENOENT) {
+				dev_err(&bus->dev,
+					"mii_bus %s couldn't get reset GPIO\n",
+					bus->id);
+				return err;
+			}
+		} else {
+			bus->reset_gpiod[i] = gpiod;
+			gpiod_set_value_cansleep(gpiod, 1);
+			udelay(bus->reset_delay_us);
+			gpiod_set_value_cansleep(gpiod, 0);
+		}
+	}
+
 	for (i = 0; i < PHY_MAX_ADDR; i++) {
 		if ((bus->phy_mask & (1 << i)) == 0) {
 			struct phy_device *phydev;
@@ -345,7 +408,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 		}
 	}
 
-	mdiobus_setup_mdiodev_from_board_info(bus);
+	mdiobus_setup_mdiodev_from_board_info(bus, mdiobus_create_device);
 
 	bus->state = MDIOBUS_REGISTERED;
 	pr_info("%s: probed\n", bus->name);
@@ -360,6 +423,13 @@ error:
 		mdiodev->device_remove(mdiodev);
 		mdiodev->device_free(mdiodev);
 	}
+
+	/* Put PHYs in RESET to save power */
+	for (i = 0; i < bus->num_reset_gpios; i++) {
+		if (bus->reset_gpiod[i])
+			gpiod_set_value_cansleep(bus->reset_gpiod[i], 1);
+	}
+
 	device_del(&bus->dev);
 	return err;
 }
@@ -381,6 +451,13 @@ void mdiobus_unregister(struct mii_bus *bus)
 		mdiodev->device_remove(mdiodev);
 		mdiodev->device_free(mdiodev);
 	}
+
+	/* Put PHYs in RESET to save power */
+	for (i = 0; i < bus->num_reset_gpios; i++) {
+		if (bus->reset_gpiod[i])
+			gpiod_set_value_cansleep(bus->reset_gpiod[i], 1);
+	}
+
 	device_del(&bus->dev);
 }
 EXPORT_SYMBOL(mdiobus_unregister);
@@ -648,9 +725,18 @@ int __init mdio_bus_init(void)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mdio_bus_init);
 
+#if IS_ENABLED(CONFIG_PHYLIB)
 void mdio_bus_exit(void)
 {
 	class_unregister(&mdio_bus_class);
 	bus_unregister(&mdio_bus_type);
 }
+EXPORT_SYMBOL_GPL(mdio_bus_exit);
+#else
+module_init(mdio_bus_init);
+/* no module_exit, intentional */
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MDIO bus/device layer");
+#endif
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 6742070ca676..6a5fd18f062c 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -297,17 +297,6 @@ static int kszphy_config_init(struct phy_device *phydev)
 	if (priv->led_mode >= 0)
 		kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode);
 
-	if (phy_interrupt_is_valid(phydev)) {
-		int ctl = phy_read(phydev, MII_BMCR);
-
-		if (ctl < 0)
-			return ctl;
-
-		ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE);
-		if (ret < 0)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -637,8 +626,7 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev)
  * MMD extended PHY registers.
  */
 static int
-ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
-		      int regnum)
+ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum)
 {
 	return -1;
 }
@@ -646,10 +634,10 @@ ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
 /* This routine does nothing since the Micrel ksz9021 does not support
  * standard IEEE MMD extended PHY registers.
  */
-static void
-ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
-		      int regnum, u32 val)
+static int
+ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum, u16 val)
 {
+	return -1;
 }
 
 static int kszphy_get_sset_count(struct phy_device *phydev)
@@ -798,9 +786,6 @@ static struct phy_driver ksphy_driver[] = {
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -940,9 +925,6 @@ static struct phy_driver ksphy_driver[] = {
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -952,6 +934,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= PHY_GBIT_FEATURES,
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
+	.probe		= kszphy_probe,
 	.config_init	= ksz9021_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
@@ -962,8 +945,8 @@ static struct phy_driver ksphy_driver[] = {
 	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
-	.read_mmd_indirect = ksz9021_rd_mmd_phyreg,
-	.write_mmd_indirect = ksz9021_wr_mmd_phyreg,
+	.read_mmd	= ksz9021_rd_mmd_phyreg,
+	.write_mmd	= ksz9021_wr_mmd_phyreg,
 }, {
 	.phy_id		= PHY_ID_KSZ9031,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
@@ -971,6 +954,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= PHY_GBIT_FEATURES,
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
+	.probe		= kszphy_probe,
 	.config_init	= ksz9031_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= ksz9031_read_status,
@@ -989,9 +973,6 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -1003,9 +984,6 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= kszphy_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -1017,9 +995,6 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
-	.get_sset_count = kszphy_get_sset_count,
-	.get_strings	= kszphy_get_strings,
-	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 } };
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 324fbf6ad8ff..2b2f543cf9f0 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -78,9 +78,8 @@ static int lan88xx_probe(struct phy_device *phydev)
 	priv->wolopts = 0;
 
 	/* these values can be used to identify internal PHY */
-	priv->chip_id = phy_read_mmd_indirect(phydev, LAN88XX_MMD3_CHIP_ID, 3);
-	priv->chip_rev = phy_read_mmd_indirect(phydev, LAN88XX_MMD3_CHIP_REV,
-					       3);
+	priv->chip_id = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_ID);
+	priv->chip_rev = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_REV);
 
 	phydev->priv = priv;
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
new file mode 100644
index 000000000000..6739b738bbaf
--- /dev/null
+++ b/drivers/net/phy/phy-core.c
@@ -0,0 +1,101 @@
+/*
+ * Core PHY library, taken from phy.c
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/export.h>
+#include <linux/phy.h>
+
+static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad,
+			     u16 regnum)
+{
+	/* Write the desired MMD Devad */
+	bus->write(bus, phy_addr, MII_MMD_CTRL, devad);
+
+	/* Write the desired MMD register address */
+	bus->write(bus, phy_addr, MII_MMD_DATA, regnum);
+
+	/* Select the Function : DATA with no post increment */
+	bus->write(bus, phy_addr, MII_MMD_CTRL, devad | MII_MMD_CTRL_NOINCR);
+}
+
+/**
+ * phy_read_mmd - Convenience function for reading a register
+ * from an MMD on a given PHY.
+ * @phydev: The phy_device struct
+ * @devad: The MMD to read from (0..31)
+ * @regnum: The register on the MMD to read (0..65535)
+ *
+ * Same rules as for phy_read();
+ */
+int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
+{
+	int val;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	if (phydev->drv->read_mmd) {
+		val = phydev->drv->read_mmd(phydev, devad, regnum);
+	} else if (phydev->is_c45) {
+		u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+		val = mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr);
+	} else {
+		struct mii_bus *bus = phydev->mdio.bus;
+		int phy_addr = phydev->mdio.addr;
+
+		mutex_lock(&bus->mdio_lock);
+		mmd_phy_indirect(bus, phy_addr, devad, regnum);
+
+		/* Read the content of the MMD's selected register */
+		val = bus->read(bus, phy_addr, MII_MMD_DATA);
+		mutex_unlock(&bus->mdio_lock);
+	}
+	return val;
+}
+EXPORT_SYMBOL(phy_read_mmd);
+
+/**
+ * phy_write_mmd - Convenience function for writing a register
+ * on an MMD on a given PHY.
+ * @phydev: The phy_device struct
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ * @val: value to write to @regnum
+ *
+ * Same rules as for phy_write();
+ */
+int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
+{
+	int ret;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	if (phydev->drv->write_mmd) {
+		ret = phydev->drv->write_mmd(phydev, devad, regnum, val);
+	} else if (phydev->is_c45) {
+		u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+		ret = mdiobus_write(phydev->mdio.bus, phydev->mdio.addr,
+				    addr, val);
+	} else {
+		struct mii_bus *bus = phydev->mdio.bus;
+		int phy_addr = phydev->mdio.addr;
+
+		mutex_lock(&bus->mdio_lock);
+		mmd_phy_indirect(bus, phy_addr, devad, regnum);
+
+		/* Write the data into MMD's selected register */
+		bus->write(bus, phy_addr, MII_MMD_DATA, val);
+		mutex_unlock(&bus->mdio_lock);
+
+		ret = 0;
+	}
+	return ret;
+}
+EXPORT_SYMBOL(phy_write_mmd);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1be69d8bc909..82ab8fb82587 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -50,8 +50,22 @@ static const char *phy_speed_to_str(int speed)
 		return "1Gbps";
 	case SPEED_2500:
 		return "2.5Gbps";
+	case SPEED_5000:
+		return "5Gbps";
 	case SPEED_10000:
 		return "10Gbps";
+	case SPEED_20000:
+		return "20Gbps";
+	case SPEED_25000:
+		return "25Gbps";
+	case SPEED_40000:
+		return "40Gbps";
+	case SPEED_50000:
+		return "50Gbps";
+	case SPEED_56000:
+		return "56Gbps";
+	case SPEED_100000:
+		return "100Gbps";
 	case SPEED_UNKNOWN:
 		return "Unknown";
 	default:
@@ -162,7 +176,9 @@ struct phy_setting {
 	u32 setting;
 };
 
-/* A mapping of all SUPPORTED settings to speed/duplex */
+/* A mapping of all SUPPORTED settings to speed/duplex.  This table
+ * must be grouped by speed and sorted in descending match priority
+ * - iow, descending speed. */
 static const struct phy_setting settings[] = {
 	{
 		.speed = SPEED_10000,
@@ -221,45 +237,70 @@ static const struct phy_setting settings[] = {
 	},
 };
 
-#define MAX_NUM_SETTINGS ARRAY_SIZE(settings)
-
 /**
- * phy_find_setting - find a PHY settings array entry that matches speed & duplex
+ * phy_lookup_setting - lookup a PHY setting
  * @speed: speed to match
  * @duplex: duplex to match
+ * @feature: allowed link modes
+ * @exact: an exact match is required
+ *
+ * Search the settings array for a setting that matches the speed and
+ * duplex, and which is supported.
+ *
+ * If @exact is unset, either an exact match or %NULL for no match will
+ * be returned.
  *
- * Description: Searches the settings array for the setting which
- *   matches the desired speed and duplex, and returns the index
- *   of that setting.  Returns the index of the last setting if
- *   none of the others match.
+ * If @exact is set, an exact match, the fastest supported setting at
+ * or below the specified speed, the slowest supported setting, or if
+ * they all fail, %NULL will be returned.
  */
-static inline unsigned int phy_find_setting(int speed, int duplex)
+static const struct phy_setting *
+phy_lookup_setting(int speed, int duplex, u32 features, bool exact)
 {
-	unsigned int idx = 0;
+	const struct phy_setting *p, *match = NULL, *last = NULL;
+	int i;
+
+	for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) {
+		if (p->setting & features) {
+			last = p;
+			if (p->speed == speed && p->duplex == duplex) {
+				/* Exact match for speed and duplex */
+				match = p;
+				break;
+			} else if (!exact) {
+				if (!match && p->speed <= speed)
+					/* Candidate */
+					match = p;
+
+				if (p->speed < speed)
+					break;
+			}
+		}
+	}
 
-	while (idx < ARRAY_SIZE(settings) &&
-	       (settings[idx].speed != speed || settings[idx].duplex != duplex))
-		idx++;
+	if (!match && !exact)
+		match = last;
 
-	return idx < MAX_NUM_SETTINGS ? idx : MAX_NUM_SETTINGS - 1;
+	return match;
 }
 
 /**
- * phy_find_valid - find a PHY setting that matches the requested features mask
- * @idx: The first index in settings[] to search
- * @features: A mask of the valid settings
+ * phy_find_valid - find a PHY setting that matches the requested parameters
+ * @speed: desired speed
+ * @duplex: desired duplex
+ * @supported: mask of supported link modes
  *
- * Description: Returns the index of the first valid setting less
- *   than or equal to the one pointed to by idx, as determined by
- *   the mask in features.  Returns the index of the last setting
- *   if nothing else matches.
+ * Locate a supported phy setting that is, in priority order:
+ * - an exact match for the specified speed and duplex mode
+ * - a match for the specified speed, or slower speed
+ * - the slowest supported speed
+ * Returns the matched phy_setting entry, or %NULL if no supported phy
+ * settings were found.
  */
-static inline unsigned int phy_find_valid(unsigned int idx, u32 features)
+static const struct phy_setting *
+phy_find_valid(int speed, int duplex, u32 supported)
 {
-	while (idx < MAX_NUM_SETTINGS && !(settings[idx].setting & features))
-		idx++;
-
-	return idx < MAX_NUM_SETTINGS ? idx : MAX_NUM_SETTINGS - 1;
+	return phy_lookup_setting(speed, duplex, supported, false);
 }
 
 /**
@@ -279,20 +320,11 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
 	unsigned int count = 0;
 	unsigned int idx = 0;
 
-	while (idx < MAX_NUM_SETTINGS && count < size) {
-		idx = phy_find_valid(idx, phy->supported);
-
-		if (!(settings[idx].setting & phy->supported))
-			break;
-
+	for (idx = 0; idx < ARRAY_SIZE(settings) && count < size; idx++)
 		/* Assumes settings are grouped by speed */
-		if ((count == 0) ||
-		    (speeds[count - 1] != settings[idx].speed)) {
-			speeds[count] = settings[idx].speed;
-			count++;
-		}
-		idx++;
-	}
+		if ((settings[idx].setting & phy->supported) &&
+		    (count == 0 || speeds[count - 1] != settings[idx].speed))
+			speeds[count++] = settings[idx].speed;
 
 	return count;
 }
@@ -308,12 +340,7 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
  */
 static inline bool phy_check_valid(int speed, int duplex, u32 features)
 {
-	unsigned int idx;
-
-	idx = phy_find_valid(phy_find_setting(speed, duplex), features);
-
-	return settings[idx].speed == speed && settings[idx].duplex == duplex &&
-		(settings[idx].setting & features);
+	return !!phy_lookup_setting(speed, duplex, features, true);
 }
 
 /**
@@ -326,18 +353,22 @@ static inline bool phy_check_valid(int speed, int duplex, u32 features)
  */
 static void phy_sanitize_settings(struct phy_device *phydev)
 {
+	const struct phy_setting *setting;
 	u32 features = phydev->supported;
-	unsigned int idx;
 
 	/* Sanitize settings based on PHY capabilities */
 	if ((features & SUPPORTED_Autoneg) == 0)
 		phydev->autoneg = AUTONEG_DISABLE;
 
-	idx = phy_find_valid(phy_find_setting(phydev->speed, phydev->duplex),
-			features);
-
-	phydev->speed = settings[idx].speed;
-	phydev->duplex = settings[idx].duplex;
+	setting = phy_find_valid(phydev->speed, phydev->duplex, features);
+	if (setting) {
+		phydev->speed = setting->speed;
+		phydev->duplex = setting->duplex;
+	} else {
+		/* We failed to find anything (no supported speeds?) */
+		phydev->speed = SPEED_UNKNOWN;
+		phydev->duplex = DUPLEX_UNKNOWN;
+	}
 }
 
 /**
@@ -591,16 +622,18 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 EXPORT_SYMBOL(phy_mii_ioctl);
 
 /**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * phy_start_aneg_priv - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: Sanitizes the settings (if we're not autonegotiating
  *   them), and then calls the driver's config_aneg function.
  *   If the PHYCONTROL Layer is operating, we change the state to
  *   reflect the beginning of Auto-negotiation or forcing.
  */
-int phy_start_aneg(struct phy_device *phydev)
+static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 {
+	bool trigger = 0;
 	int err;
 
 	if (!phydev->drv)
@@ -628,10 +661,40 @@ int phy_start_aneg(struct phy_device *phydev)
 		}
 	}
 
+	/* Re-schedule a PHY state machine to check PHY status because
+	 * negotiation may already be done and aneg interrupt may not be
+	 * generated.
+	 */
+	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+		err = phy_aneg_done(phydev);
+		if (err > 0) {
+			trigger = true;
+			err = 0;
+		}
+	}
+
 out_unlock:
 	mutex_unlock(&phydev->lock);
+
+	if (trigger)
+		phy_trigger_machine(phydev, sync);
+
 	return err;
 }
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ *   them), and then calls the driver's config_aneg function.
+ *   If the PHYCONTROL Layer is operating, we change the state to
+ *   reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+	return phy_start_aneg_priv(phydev, true);
+}
 EXPORT_SYMBOL(phy_start_aneg);
 
 /**
@@ -659,7 +722,7 @@ void phy_start_machine(struct phy_device *phydev)
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev, bool sync)
+void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
 	if (sync)
 		cancel_delayed_work_sync(&phydev->state_queue);
@@ -681,7 +744,7 @@ void phy_stop_machine(struct phy_device *phydev)
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (phydev->state > PHY_UP)
+	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
 }
@@ -1154,7 +1217,7 @@ void phy_state_machine(struct work_struct *work)
 	mutex_unlock(&phydev->lock);
 
 	if (needs_aneg)
-		err = phy_start_aneg(phydev);
+		err = phy_start_aneg_priv(phydev, false);
 	else if (do_suspend)
 		phy_suspend(phydev);
 
@@ -1192,91 +1255,6 @@ void phy_mac_interrupt(struct phy_device *phydev, int new_link)
 }
 EXPORT_SYMBOL(phy_mac_interrupt);
 
-static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
-				    int addr)
-{
-	/* Write the desired MMD Devad */
-	bus->write(bus, addr, MII_MMD_CTRL, devad);
-
-	/* Write the desired MMD register address */
-	bus->write(bus, addr, MII_MMD_DATA, prtad);
-
-	/* Select the Function : DATA with no post increment */
-	bus->write(bus, addr, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
-}
-
-/**
- * phy_read_mmd_indirect - reads data from the MMD registers
- * @phydev: The PHY device bus
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- *
- * Description: it reads data from the MMD registers (clause 22 to access to
- * clause 45) of the specified phy address.
- * To read these register we have:
- * 1) Write reg 13 // DEVAD
- * 2) Write reg 14 // MMD Address
- * 3) Write reg 13 // MMD Data Command for MMD DEVAD
- * 3) Read  reg 14 // Read MMD data
- */
-int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad)
-{
-	struct phy_driver *phydrv = phydev->drv;
-	int addr = phydev->mdio.addr;
-	int value = -1;
-
-	if (!phydrv->read_mmd_indirect) {
-		struct mii_bus *bus = phydev->mdio.bus;
-
-		mutex_lock(&bus->mdio_lock);
-		mmd_phy_indirect(bus, prtad, devad, addr);
-
-		/* Read the content of the MMD's selected register */
-		value = bus->read(bus, addr, MII_MMD_DATA);
-		mutex_unlock(&bus->mdio_lock);
-	} else {
-		value = phydrv->read_mmd_indirect(phydev, prtad, devad, addr);
-	}
-	return value;
-}
-EXPORT_SYMBOL(phy_read_mmd_indirect);
-
-/**
- * phy_write_mmd_indirect - writes data to the MMD registers
- * @phydev: The PHY device
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- * @data: data to write in the MMD register
- *
- * Description: Write data from the MMD registers of the specified
- * phy address.
- * To write these register we have:
- * 1) Write reg 13 // DEVAD
- * 2) Write reg 14 // MMD Address
- * 3) Write reg 13 // MMD Data Command for MMD DEVAD
- * 3) Write reg 14 // Write MMD data
- */
-void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
-				   int devad, u32 data)
-{
-	struct phy_driver *phydrv = phydev->drv;
-	int addr = phydev->mdio.addr;
-
-	if (!phydrv->write_mmd_indirect) {
-		struct mii_bus *bus = phydev->mdio.bus;
-
-		mutex_lock(&bus->mdio_lock);
-		mmd_phy_indirect(bus, prtad, devad, addr);
-
-		/* Write the data into MMD's selected register */
-		bus->write(bus, addr, MII_MMD_DATA, data);
-		mutex_unlock(&bus->mdio_lock);
-	} else {
-		phydrv->write_mmd_indirect(phydev, prtad, devad, addr, data);
-	}
-}
-EXPORT_SYMBOL(phy_write_mmd_indirect);
-
 /**
  * phy_init_eee - init and check the EEE feature
  * @phydev: target phy_device struct
@@ -1293,15 +1271,8 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 		return -EIO;
 
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
-	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
-	 * should return an error if they do not support EEE.
 	 */
-	if ((phydev->duplex == DUPLEX_FULL) &&
-	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	     phy_interface_is_rgmii(phydev) ||
-	     phy_is_internal(phydev))) {
+	if (phydev->duplex == DUPLEX_FULL) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
 		int status;
@@ -1312,8 +1283,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 			return status;
 
 		/* First check if the EEE ability is supported */
-		eee_cap = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE,
-						MDIO_MMD_PCS);
+		eee_cap = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
 		if (eee_cap <= 0)
 			goto eee_exit_err;
 
@@ -1324,13 +1294,11 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 		/* Check which link settings negotiated and verify it in
 		 * the EEE advertising registers.
 		 */
-		eee_lp = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE,
-					       MDIO_MMD_AN);
+		eee_lp = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
 		if (eee_lp <= 0)
 			goto eee_exit_err;
 
-		eee_adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV,
-						MDIO_MMD_AN);
+		eee_adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
 		if (eee_adv <= 0)
 			goto eee_exit_err;
 
@@ -1343,14 +1311,12 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 			/* Configure the PHY to stop receiving xMII
 			 * clock while it is signaling LPI.
 			 */
-			int val = phy_read_mmd_indirect(phydev, MDIO_CTRL1,
-							MDIO_MMD_PCS);
+			int val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
 			if (val < 0)
 				return val;
 
 			val |= MDIO_PCS_CTRL1_CLKSTOP_EN;
-			phy_write_mmd_indirect(phydev, MDIO_CTRL1,
-					       MDIO_MMD_PCS, val);
+			phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, val);
 		}
 
 		return 0; /* EEE supported */
@@ -1372,7 +1338,7 @@ int phy_get_eee_err(struct phy_device *phydev)
 	if (!phydev->drv)
 		return -EIO;
 
-	return phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_WK_ERR, MDIO_MMD_PCS);
+	return phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_WK_ERR);
 }
 EXPORT_SYMBOL(phy_get_eee_err);
 
@@ -1392,19 +1358,19 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		return -EIO;
 
 	/* Get Supported EEE */
-	val = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE, MDIO_MMD_PCS);
+	val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
 	if (val < 0)
 		return val;
 	data->supported = mmd_eee_cap_to_ethtool_sup_t(val);
 
 	/* Get advertisement EEE */
-	val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
 	if (val < 0)
 		return val;
 	data->advertised = mmd_eee_adv_to_ethtool_adv_t(val);
 
 	/* Get LP advertisement EEE */
-	val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
 	if (val < 0)
 		return val;
 	data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(val);
@@ -1422,15 +1388,37 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
  */
 int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 {
-	int val = ethtool_adv_to_mmd_eee_adv_t(data->advertised);
+	int cap, old_adv, adv, ret;
 
 	if (!phydev->drv)
 		return -EIO;
 
+	/* Get Supported EEE */
+	cap = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
+	if (cap < 0)
+		return cap;
+
+	old_adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
+	if (old_adv < 0)
+		return old_adv;
+
+	adv = ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
+
 	/* Mask prohibited EEE modes */
-	val &= ~phydev->eee_broken_modes;
+	adv &= ~phydev->eee_broken_modes;
+
+	if (old_adv != adv) {
+		ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
+		if (ret < 0)
+			return ret;
 
-	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, val);
+		/* Restart autonegotiation so the new modes get sent to the
+		 * link partner.
+		 */
+		ret = genphy_restart_aneg(phydev);
+		if (ret < 0)
+			return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index daec6555f3b1..1219eeab69d1 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1217,7 +1217,7 @@ static int genphy_config_eee_advert(struct phy_device *phydev)
 	 * supported by the phy. If we read 0, EEE is not advertised
 	 * In both case, we don't need to continue
 	 */
-	adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+	adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
 	if (adv <= 0)
 		return 0;
 
@@ -1228,7 +1228,7 @@ static int genphy_config_eee_advert(struct phy_device *phydev)
 	if (old_adv == adv)
 		return 0;
 
-	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, adv);
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
 
 	return 1;
 }
@@ -1864,7 +1864,7 @@ static struct phy_driver genphy_driver[] = {
 	.phy_id		= 0xffffffff,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Generic PHY",
-	.soft_reset	= genphy_soft_reset,
+	.soft_reset	= genphy_no_soft_reset,
 	.config_init	= genphy_config_init,
 	.features	= PHY_GBIT_FEATURES | SUPPORTED_MII |
 			  SUPPORTED_AUI | SUPPORTED_FIBRE |
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index fb32eaf2255d..cef6967b0396 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/mii.h>
 #include <linux/ethtool.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
 #include <linux/smscphy.h>
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index 93ffedfa2994..1e2d4f1179da 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -491,13 +491,14 @@ static int ks8995_probe(struct spi_device *spi)
 	if (err)
 		return err;
 
-	ks->regs_attr.size = ks->chip->regs_size;
 	memcpy(&ks->regs_attr, &ks8995_registers_attr, sizeof(ks->regs_attr));
+	ks->regs_attr.size = ks->chip->regs_size;
 
 	err = ks8995_reset(ks);
 	if (err)
 		return err;
 
+	sysfs_attr_init(&ks->regs_attr.attr);
 	err = sysfs_create_bin_file(&spi->dev.kobj, &ks->regs_attr);
 	if (err) {
 		dev_err(&spi->dev, "unable to create sysfs file, err=%d\n",
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4a24b5d15f5a..6c5d5ef46f75 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -990,7 +990,7 @@ static void team_port_disable(struct team *team,
 #define TEAM_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
 
-static void ___team_compute_features(struct team *team)
+static void __team_compute_features(struct team *team)
 {
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
@@ -1023,16 +1023,10 @@ static void ___team_compute_features(struct team *team)
 		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
 }
 
-static void __team_compute_features(struct team *team)
-{
-	___team_compute_features(team);
-	netdev_change_features(team->dev);
-}
-
 static void team_compute_features(struct team *team)
 {
 	mutex_lock(&team->lock);
-	___team_compute_features(team);
+	__team_compute_features(team);
 	mutex_unlock(&team->lock);
 	netdev_change_features(team->dev);
 }
@@ -1641,6 +1635,7 @@ static void team_uninit(struct net_device *dev)
 	team_notify_peers_fini(team);
 	team_queue_override_fini(team);
 	mutex_unlock(&team->lock);
+	netdev_change_features(dev);
 }
 
 static void team_destructor(struct net_device *dev)
@@ -1928,6 +1923,10 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev)
 	mutex_lock(&team->lock);
 	err = team_port_add(team, port_dev);
 	mutex_unlock(&team->lock);
+
+	if (!err)
+		netdev_change_features(dev);
+
 	return err;
 }
 
@@ -1939,6 +1938,10 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 	mutex_lock(&team->lock);
 	err = team_port_del(team, port_dev);
 	mutex_unlock(&team->lock);
+
+	if (!err)
+		netdev_change_features(dev);
+
 	return err;
 }
 
@@ -2072,6 +2075,7 @@ static int team_dev_type_check_change(struct net_device *dev,
 static void team_setup(struct net_device *dev)
 {
 	ether_setup(dev);
+	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->netdev_ops = &team_netdev_ops;
 	dev->ethtool_ops = &team_ethtool_ops;
@@ -2357,8 +2361,10 @@ start_again:
 
 	hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI,
 			  TEAM_CMD_OPTIONS_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(skb);
 		return -EMSGSIZE;
+	}
 
 	if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex))
 		goto nla_put_failure;
@@ -2470,7 +2476,8 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			goto team_put;
 		}
 		err = nla_parse_nested(opt_attrs, TEAM_ATTR_OPTION_MAX,
-				       nl_option, team_nl_option_policy);
+				       nl_option, team_nl_option_policy,
+				       info->extack);
 		if (err)
 			goto team_put;
 		if (!opt_attrs[TEAM_ATTR_OPTION_NAME] ||
@@ -2630,8 +2637,10 @@ start_again:
 
 	hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI,
 			  TEAM_CMD_PORT_LIST_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(skb);
 		return -EMSGSIZE;
+	}
 
 	if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex))
 		goto nla_put_failure;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index dc1b1dd9157c..bbd707b9ef7a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -822,7 +822,18 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
+	struct tun_struct *tun = netdev_priv(dev);
+	int i;
+
 	netif_tx_start_all_queues(dev);
+
+	for (i = 0; i < tun->numqueues; i++) {
+		struct tun_file *tfile;
+
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		tfile->socket.sk->sk_write_space(tfile->socket.sk);
+	}
+
 	return 0;
 }
 
@@ -1103,9 +1114,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
-	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	     sock_writeable(sk)))
+	if (tun->dev->flags & IFF_UP &&
+	    (sock_writeable(sk) ||
+	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	      sock_writeable(sk))))
 		mask |= POLLOUT | POLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
@@ -1919,6 +1931,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 		return -EINVAL;
 
 	tun->set_features = features;
+	tun->dev->wanted_features &= ~TUN_USER_FEATURES;
+	tun->dev->wanted_features |= features;
 	netdev_update_features(tun->dev);
 
 	return 0;
@@ -2430,18 +2444,16 @@ static struct miscdevice tun_miscdev = {
 
 /* ethtool interface */
 
-static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	cmd->supported		= 0;
-	cmd->advertising	= 0;
-	ethtool_cmd_speed_set(cmd, SPEED_10);
-	cmd->duplex		= DUPLEX_FULL;
-	cmd->port		= PORT_TP;
-	cmd->phy_address	= 0;
-	cmd->transceiver	= XCVR_INTERNAL;
-	cmd->autoneg		= AUTONEG_DISABLE;
-	cmd->maxtxpkt		= 0;
-	cmd->maxrxpkt		= 0;
+static int tun_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	cmd->base.speed		= SPEED_10;
+	cmd->base.duplex	= DUPLEX_FULL;
+	cmd->base.port		= PORT_TP;
+	cmd->base.phy_address	= 0;
+	cmd->base.autoneg	= AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -2504,7 +2516,6 @@ static int tun_set_coalesce(struct net_device *dev,
 }
 
 static const struct ethtool_ops tun_ethtool_ops = {
-	.get_settings	= tun_get_settings,
 	.get_drvinfo	= tun_get_drvinfo,
 	.get_msglevel	= tun_get_msglevel,
 	.set_msglevel	= tun_set_msglevel,
@@ -2512,6 +2523,7 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.get_ts_info	= ethtool_op_get_ts_info,
 	.get_coalesce   = tun_get_coalesce,
 	.set_coalesce   = tun_set_coalesce,
+	.get_link_ksettings = tun_get_link_ksettings,
 };
 
 static int tun_queue_resize(struct tun_struct *tun)
@@ -2570,7 +2582,6 @@ static int __init tun_init(void)
 	int ret = 0;
 
 	pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
-	pr_info("%s\n", DRV_COPYRIGHT);
 
 	ret = rtnl_link_register(&tun_link_ops);
 	if (ret) {
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 3dd490f53e48..f28bd74ac275 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -369,7 +369,7 @@ config USB_NET_NET1080
 	  optionally with LEDs that indicate traffic
 
 config USB_NET_PLUSB
-	tristate "Prolific PL-2301/2302/25A1 based cables"
+	tristate "Prolific PL-2301/2302/25A1/27A1 based cables"
 	# if the handshake/init/reset problems, from original 'plusb',
 	# are ever resolved ... then remove "experimental"
 	depends on USB_USBNET
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 0dd510604118..a3aa0a27dfe5 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -136,9 +136,9 @@ static const struct ethtool_ops ax88172_ethtool_ops = {
 	.get_eeprom_len		= asix_get_eeprom_len,
 	.get_eeprom		= asix_get_eeprom,
 	.set_eeprom		= asix_set_eeprom,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static void ax88172_set_multicast(struct net_device *net)
@@ -206,6 +206,7 @@ static const struct net_device_ops ax88172_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= asix_ioctl,
@@ -301,9 +302,9 @@ static const struct ethtool_ops ax88772_ethtool_ops = {
 	.get_eeprom_len		= asix_get_eeprom_len,
 	.get_eeprom		= asix_get_eeprom,
 	.set_eeprom		= asix_set_eeprom,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int ax88772_link_reset(struct usbnet *dev)
@@ -591,6 +592,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= asix_ioctl,
@@ -775,9 +777,9 @@ static const struct ethtool_ops ax88178_ethtool_ops = {
 	.get_eeprom_len		= asix_get_eeprom_len,
 	.get_eeprom		= asix_get_eeprom,
 	.set_eeprom		= asix_set_eeprom,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int marvell_phy_init(struct usbnet *dev)
@@ -1044,6 +1046,7 @@ static const struct net_device_ops ax88178_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= asix_set_multicast,
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 6308386b09df..501576f53854 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -143,6 +143,7 @@ static const struct net_device_ops ax88172a_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= ax88172a_ioctl,
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index a3a7db0702d8..51cf60092a18 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -620,16 +620,18 @@ ax88179_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom,
 	return 0;
 }
 
-static int ax88179_get_settings(struct net_device *net, struct ethtool_cmd *cmd)
+static int ax88179_get_link_ksettings(struct net_device *net,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
-	return mii_ethtool_gset(&dev->mii, cmd);
+	return mii_ethtool_get_link_ksettings(&dev->mii, cmd);
 }
 
-static int ax88179_set_settings(struct net_device *net, struct ethtool_cmd *cmd)
+static int ax88179_set_link_ksettings(struct net_device *net,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
-	return mii_ethtool_sset(&dev->mii, cmd);
+	return mii_ethtool_set_link_ksettings(&dev->mii, cmd);
 }
 
 static int
@@ -826,11 +828,11 @@ static const struct ethtool_ops ax88179_ethtool_ops = {
 	.set_wol		= ax88179_set_wol,
 	.get_eeprom_len		= ax88179_get_eeprom_len,
 	.get_eeprom		= ax88179_get_eeprom,
-	.get_settings		= ax88179_get_settings,
-	.set_settings		= ax88179_set_settings,
 	.get_eee		= ax88179_get_eee,
 	.set_eee		= ax88179_set_eee,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= ax88179_get_link_ksettings,
+	.set_link_ksettings	= ax88179_set_link_ksettings,
 };
 
 static void ax88179_set_multicast(struct net_device *net)
@@ -957,6 +959,7 @@ static const struct net_device_ops ax88179_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_change_mtu		= ax88179_change_mtu,
 	.ndo_set_mac_address	= ax88179_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 0acc9b640419..fce92f0e5abd 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -688,29 +688,34 @@ static void catc_get_drvinfo(struct net_device *dev,
 	usb_make_path(catc->usbdev, info->bus_info, sizeof(info->bus_info));
 }
 
-static int catc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int catc_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct catc *catc = netdev_priv(dev);
 	if (!catc->is_f5u011)
 		return -EOPNOTSUPP;
 
-	cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_TP;
-	cmd->advertising = ADVERTISED_10baseT_Half | ADVERTISED_TP;
-	ethtool_cmd_speed_set(cmd, SPEED_10);
-	cmd->duplex = DUPLEX_HALF;
-	cmd->port = PORT_TP; 
-	cmd->phy_address = 0;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->autoneg = AUTONEG_DISABLE;
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+
+	cmd->base.speed = SPEED_10;
+	cmd->base.duplex = DUPLEX_HALF;
+	cmd->base.port = PORT_TP;
+	cmd->base.phy_address = 0;
+	cmd->base.autoneg = AUTONEG_DISABLE;
+
 	return 0;
 }
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = catc_get_drvinfo,
-	.get_settings = catc_get_settings,
-	.get_link = ethtool_op_get_link
+	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = catc_get_link_ksettings,
 };
 
 /*
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index f5552aaaa77a..f3ae88fdf332 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -532,6 +532,7 @@ static const struct driver_info wwan_info = {
 #define LENOVO_VENDOR_ID	0x17ef
 #define NVIDIA_VENDOR_ID	0x0955
 #define HP_VENDOR_ID		0x03f0
+#define MICROSOFT_VENDOR_ID	0x045e
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -761,6 +762,20 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* Microsoft Surface 2 dock (based on Realtek RTL8152) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07ab, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 3a98f3762a4c..a6b997cffd3b 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -100,6 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
 	.ndo_stop             = usbnet_stop,
 	.ndo_start_xmit       = usbnet_start_xmit,
 	.ndo_tx_timeout       = usbnet_tx_timeout,
+	.ndo_get_stats64      = usbnet_get_stats64,
 	.ndo_change_mtu       = cdc_ncm_change_mtu,
 	.ndo_set_mac_address  = eth_mac_addr,
 	.ndo_validate_addr    = eth_validate_addr,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index f317984f7536..bb3f71f9fbde 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -131,8 +131,6 @@ static void cdc_ncm_get_strings(struct net_device __always_unused *netdev, u32 s
 static void cdc_ncm_update_rxtx_max(struct usbnet *dev, u32 new_rx, u32 new_tx);
 
 static const struct ethtool_ops cdc_ncm_ethtool_ops = {
-	.get_settings      = usbnet_get_settings,
-	.set_settings      = usbnet_set_settings,
 	.get_link          = usbnet_get_link,
 	.nway_reset        = usbnet_nway_reset,
 	.get_drvinfo       = usbnet_get_drvinfo,
@@ -142,6 +140,8 @@ static const struct ethtool_ops cdc_ncm_ethtool_ops = {
 	.get_sset_count    = cdc_ncm_get_sset_count,
 	.get_strings       = cdc_ncm_get_strings,
 	.get_ethtool_stats = cdc_ncm_get_ethtool_stats,
+	.get_link_ksettings      = usbnet_get_link_ksettings,
+	.set_link_ksettings      = usbnet_set_link_ksettings,
 };
 
 static u32 cdc_ncm_check_rx_max(struct usbnet *dev, u32 new_rx)
@@ -753,6 +753,7 @@ static const struct net_device_ops cdc_ncm_netdev_ops = {
 	.ndo_stop	     = usbnet_stop,
 	.ndo_start_xmit	     = usbnet_start_xmit,
 	.ndo_tx_timeout	     = usbnet_tx_timeout,
+	.ndo_get_stats64     = usbnet_get_stats64,
 	.ndo_change_mtu	     = cdc_ncm_change_mtu,
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr   = eth_validate_addr,
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index 8a40202c0a17..c4f1c363e24b 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -254,14 +254,9 @@ static struct sk_buff *ch9200_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	tx_overhead = 0x40;
 
 	len = skb->len;
-	if (skb_headroom(skb) < tx_overhead) {
-		struct sk_buff *skb2;
-
-		skb2 = skb_copy_expand(skb, tx_overhead, 0, flags);
+	if (skb_cow_head(skb, tx_overhead)) {
 		dev_kfree_skb_any(skb);
-		skb = skb2;
-		if (!skb)
-			return NULL;
+		return NULL;
 	}
 
 	__skb_push(skb, tx_overhead);
diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c
index e221bfcee76b..947bea81d924 100644
--- a/drivers/net/usb/cx82310_eth.c
+++ b/drivers/net/usb/cx82310_eth.c
@@ -293,12 +293,9 @@ static struct sk_buff *cx82310_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 {
 	int len = skb->len;
 
-	if (skb_headroom(skb) < 2) {
-		struct sk_buff *skb2 = skb_copy_expand(skb, 2, 0, flags);
+	if (skb_cow_head(skb, 2)) {
 		dev_kfree_skb_any(skb);
-		skb = skb2;
-		if (!skb)
-			return NULL;
+		return NULL;
 	}
 	skb_push(skb, 2);
 
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 0b4bdd39106b..b91f92e4e5f2 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -281,9 +281,9 @@ static const struct ethtool_ops dm9601_ethtool_ops = {
 	.set_msglevel	= usbnet_set_msglevel,
 	.get_eeprom_len	= dm9601_get_eeprom_len,
 	.get_eeprom	= dm9601_get_eeprom,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.nway_reset	= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static void dm9601_set_multicast(struct net_device *net)
@@ -343,6 +343,7 @@ static const struct net_device_ops dm9601_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= dm9601_ioctl,
 	.ndo_set_rx_mode	= dm9601_set_multicast,
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 4f2e8141dbe2..00067a0c51ca 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2534,13 +2534,6 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 	SET_NETDEV_DEV(net, &interface->dev);
 	SET_NETDEV_DEVTYPE(net, &hso_type);
 
-	/* registering our net device */
-	result = register_netdev(net);
-	if (result) {
-		dev_err(&interface->dev, "Failed to register device\n");
-		goto exit;
-	}
-
 	/* start allocating */
 	for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
 		hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL);
@@ -2560,6 +2553,13 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 
 	add_net_device(hso_dev);
 
+	/* registering our net device */
+	result = register_netdev(net);
+	if (result) {
+		dev_err(&interface->dev, "Failed to register device\n");
+		goto exit;
+	}
+
 	hso_log_port(hso_dev);
 
 	hso_create_rfkill(hso_dev, interface);
@@ -3279,9 +3279,9 @@ static void __exit hso_exit(void)
 	pr_info("unloaded\n");
 
 	tty_unregister_driver(tty_drv);
-	put_tty_driver(tty_drv);
 	/* deregister the usb driver */
 	usb_deregister(&hso_driver);
+	put_tty_driver(tty_drv);
 }
 
 /* Module definitions */
diff --git a/drivers/net/usb/int51x1.c b/drivers/net/usb/int51x1.c
index 4ff70b22c6ee..5a43b77a6b9c 100644
--- a/drivers/net/usb/int51x1.c
+++ b/drivers/net/usb/int51x1.c
@@ -144,6 +144,7 @@ static const struct net_device_ops int51x1_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= int51x1_set_multicast,
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index 876f02f4945e..37fb621fde86 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -245,8 +245,6 @@ struct kaweth_device
 	__u16 packet_filter_bitmap;
 
 	struct kaweth_ethernet_configuration configuration;
-
-	struct net_device_stats stats;
 };
 
 /****************************************************************
@@ -598,7 +596,7 @@ static void kaweth_usb_receive(struct urb *urb)
 	struct sk_buff *skb;
 
 	if (unlikely(status == -EPIPE)) {
-		kaweth->stats.rx_errors++;
+		net->stats.rx_errors++;
 		kaweth->end = 1;
 		wake_up(&kaweth->term_wait);
 		dev_dbg(dev, "Status was -EPIPE.\n");
@@ -613,12 +611,12 @@ static void kaweth_usb_receive(struct urb *urb)
 	}
 	if (unlikely(status == -EPROTO || status == -ETIME ||
 		     status == -EILSEQ)) {
-		kaweth->stats.rx_errors++;
+		net->stats.rx_errors++;
 		dev_dbg(dev, "Status was -EPROTO, -ETIME, or -EILSEQ.\n");
 		return;
 	}
 	if (unlikely(status == -EOVERFLOW)) {
-		kaweth->stats.rx_errors++;
+		net->stats.rx_errors++;
 		dev_dbg(dev, "Status was -EOVERFLOW.\n");
 	}
 	spin_lock(&kaweth->device_lock);
@@ -663,8 +661,8 @@ static void kaweth_usb_receive(struct urb *urb)
 
 		netif_rx(skb);
 
-		kaweth->stats.rx_packets++;
-		kaweth->stats.rx_bytes += pkt_len;
+		net->stats.rx_packets++;
+		net->stats.rx_bytes += pkt_len;
 	}
 
 	kaweth_resubmit_rx_urb(kaweth, GFP_ATOMIC);
@@ -803,18 +801,12 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb,
 	}
 
 	/* We now decide whether we can put our special header into the sk_buff */
-	if (skb_cloned(skb) || skb_headroom(skb) < 2) {
-		/* no such luck - we make our own */
-		struct sk_buff *copied_skb;
-		copied_skb = skb_copy_expand(skb, 2, 0, GFP_ATOMIC);
-		dev_kfree_skb_irq(skb);
-		skb = copied_skb;
-		if (!copied_skb) {
-			kaweth->stats.tx_errors++;
-			netif_start_queue(net);
-			spin_unlock_irq(&kaweth->device_lock);
-			return NETDEV_TX_OK;
-		}
+	if (skb_cow_head(skb, 2)) {
+		net->stats.tx_errors++;
+		netif_start_queue(net);
+		spin_unlock_irq(&kaweth->device_lock);
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
 	}
 
 	private_header = (__le16 *)__skb_push(skb, 2);
@@ -834,15 +826,15 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb,
 	{
 		dev_warn(&net->dev, "kaweth failed tx_urb %d\n", res);
 skip:
-		kaweth->stats.tx_errors++;
+		net->stats.tx_errors++;
 
 		netif_start_queue(net);
 		dev_kfree_skb_irq(skb);
 	}
 	else
 	{
-		kaweth->stats.tx_packets++;
-		kaweth->stats.tx_bytes += skb->len;
+		net->stats.tx_packets++;
+		net->stats.tx_bytes += skb->len;
 	}
 
 	spin_unlock_irq(&kaweth->device_lock);
@@ -912,15 +904,6 @@ static void kaweth_async_set_rx_mode(struct kaweth_device *kaweth)
 }
 
 /****************************************************************
- *     kaweth_netdev_stats
- ****************************************************************/
-static struct net_device_stats *kaweth_netdev_stats(struct net_device *dev)
-{
-	struct kaweth_device *kaweth = netdev_priv(dev);
-	return &kaweth->stats;
-}
-
-/****************************************************************
  *     kaweth_tx_timeout
  ****************************************************************/
 static void kaweth_tx_timeout(struct net_device *net)
@@ -928,7 +911,7 @@ static void kaweth_tx_timeout(struct net_device *net)
 	struct kaweth_device *kaweth = netdev_priv(net);
 
 	dev_warn(&net->dev, "%s: Tx timed out. Resetting.\n", net->name);
-	kaweth->stats.tx_errors++;
+	net->stats.tx_errors++;
 	netif_trans_update(net);
 
 	usb_unlink_urb(kaweth->tx_urb);
@@ -981,7 +964,6 @@ static const struct net_device_ops kaweth_netdev_ops = {
 	.ndo_start_xmit =		kaweth_start_xmit,
 	.ndo_tx_timeout =		kaweth_tx_timeout,
 	.ndo_set_rx_mode =		kaweth_set_rx_mode,
-	.ndo_get_stats =		kaweth_netdev_stats,
 	.ndo_set_mac_address =		eth_mac_addr,
 	.ndo_validate_addr =		eth_validate_addr,
 };
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 9889a70ff4f6..9eff97a650ae 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -29,6 +29,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/mdio.h>
+#include <linux/phy.h>
 #include <net/ip6_checksum.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
@@ -1952,10 +1953,10 @@ static int lan8835_fixup(struct phy_device *phydev)
 	struct lan78xx_net *dev = netdev_priv(phydev->attached_dev);
 
 	/* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */
-	buf = phy_read_mmd_indirect(phydev, 0x8010, 3);
+	buf = phy_read_mmd(phydev, MDIO_MMD_PCS, 0x8010);
 	buf &= ~0x1800;
 	buf |= 0x0800;
-	phy_write_mmd_indirect(phydev, 0x8010, 3, buf);
+	phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf);
 
 	/* RGMII MAC TXC Delay Enable */
 	ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
@@ -1975,11 +1976,11 @@ static int ksz9031rnx_fixup(struct phy_device *phydev)
 
 	/* Micrel9301RNX PHY configuration */
 	/* RGMII Control Signal Pad Skew */
-	phy_write_mmd_indirect(phydev, 4, 2, 0x0077);
+	phy_write_mmd(phydev, MDIO_MMD_WIS, 4, 0x0077);
 	/* RGMII RX Data Pad Skew */
-	phy_write_mmd_indirect(phydev, 5, 2, 0x7777);
+	phy_write_mmd(phydev, MDIO_MMD_WIS, 5, 0x7777);
 	/* RGMII RX Clock Pad Skew */
-	phy_write_mmd_indirect(phydev, 8, 2, 0x1FF);
+	phy_write_mmd(phydev, MDIO_MMD_WIS, 8, 0x1FF);
 
 	dev->interface = PHY_INTERFACE_MODE_RGMII_RXID;
 
@@ -2607,14 +2608,9 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 {
 	u32 tx_cmd_a, tx_cmd_b;
 
-	if (skb_headroom(skb) < TX_OVERHEAD) {
-		struct sk_buff *skb2;
-
-		skb2 = skb_copy_expand(skb, TX_OVERHEAD, 0, flags);
+	if (skb_cow_head(skb, TX_OVERHEAD)) {
 		dev_kfree_skb_any(skb);
-		skb = skb2;
-		if (!skb)
-			return NULL;
+		return NULL;
 	}
 
 	if (lan78xx_linearize(skb) < 0)
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 4f345bd4e6e2..5a47e5510ca8 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -464,9 +464,9 @@ static const struct ethtool_ops mcs7830_ethtool_ops = {
 	.get_link		= usbnet_get_link,
 	.get_msglevel		= usbnet_get_msglevel,
 	.set_msglevel		= usbnet_set_msglevel,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static const struct net_device_ops mcs7830_netdev_ops = {
@@ -475,6 +475,7 @@ static const struct net_device_ops mcs7830_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= mcs7830_ioctl,
 	.ndo_set_rx_mode	= mcs7830_set_multicast,
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 36674484c6fb..6514c86f043e 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -501,13 +501,13 @@ static void read_bulk_callback(struct urb *urb)
 	if (rx_status & 0x1e) {
 		netif_dbg(pegasus, rx_err, net,
 			  "RX packet error %x\n", rx_status);
-		pegasus->stats.rx_errors++;
+		net->stats.rx_errors++;
 		if (rx_status & 0x06)	/* long or runt	*/
-			pegasus->stats.rx_length_errors++;
+			net->stats.rx_length_errors++;
 		if (rx_status & 0x08)
-			pegasus->stats.rx_crc_errors++;
+			net->stats.rx_crc_errors++;
 		if (rx_status & 0x10)	/* extra bits	*/
-			pegasus->stats.rx_frame_errors++;
+			net->stats.rx_frame_errors++;
 		goto goon;
 	}
 	if (pegasus->chip == 0x8513) {
@@ -535,8 +535,8 @@ static void read_bulk_callback(struct urb *urb)
 	skb_put(pegasus->rx_skb, pkt_len);
 	pegasus->rx_skb->protocol = eth_type_trans(pegasus->rx_skb, net);
 	netif_rx(pegasus->rx_skb);
-	pegasus->stats.rx_packets++;
-	pegasus->stats.rx_bytes += pkt_len;
+	net->stats.rx_packets++;
+	net->stats.rx_bytes += pkt_len;
 
 	if (pegasus->flags & PEGASUS_UNPLUG)
 		return;
@@ -670,13 +670,13 @@ static void intr_callback(struct urb *urb)
 		/* byte 0 == tx_status1, reg 2B */
 		if (d[0] & (TX_UNDERRUN|EXCESSIVE_COL
 					|LATE_COL|JABBER_TIMEOUT)) {
-			pegasus->stats.tx_errors++;
+			net->stats.tx_errors++;
 			if (d[0] & TX_UNDERRUN)
-				pegasus->stats.tx_fifo_errors++;
+				net->stats.tx_fifo_errors++;
 			if (d[0] & (EXCESSIVE_COL | JABBER_TIMEOUT))
-				pegasus->stats.tx_aborted_errors++;
+				net->stats.tx_aborted_errors++;
 			if (d[0] & LATE_COL)
-				pegasus->stats.tx_window_errors++;
+				net->stats.tx_window_errors++;
 		}
 
 		/* d[5].LINK_STATUS lies on some adapters.
@@ -685,7 +685,7 @@ static void intr_callback(struct urb *urb)
 		 */
 
 		/* bytes 3-4 == rx_lostpkt, reg 2E/2F */
-		pegasus->stats.rx_missed_errors += ((d[3] & 0x7f) << 8) | d[4];
+		net->stats.rx_missed_errors += ((d[3] & 0x7f) << 8) | d[4];
 	}
 
 	res = usb_submit_urb(urb, GFP_ATOMIC);
@@ -701,7 +701,7 @@ static void pegasus_tx_timeout(struct net_device *net)
 	pegasus_t *pegasus = netdev_priv(net);
 	netif_warn(pegasus, timer, net, "tx timeout\n");
 	usb_unlink_urb(pegasus->tx_urb);
-	pegasus->stats.tx_errors++;
+	net->stats.tx_errors++;
 }
 
 static netdev_tx_t pegasus_start_xmit(struct sk_buff *skb,
@@ -731,23 +731,18 @@ static netdev_tx_t pegasus_start_xmit(struct sk_buff *skb,
 			netif_device_detach(pegasus->net);
 			break;
 		default:
-			pegasus->stats.tx_errors++;
+			net->stats.tx_errors++;
 			netif_start_queue(net);
 		}
 	} else {
-		pegasus->stats.tx_packets++;
-		pegasus->stats.tx_bytes += skb->len;
+		net->stats.tx_packets++;
+		net->stats.tx_bytes += skb->len;
 	}
 	dev_kfree_skb(skb);
 
 	return NETDEV_TX_OK;
 }
 
-static struct net_device_stats *pegasus_netdev_stats(struct net_device *dev)
-{
-	return &((pegasus_t *) netdev_priv(dev))->stats;
-}
-
 static inline void disable_net_traffic(pegasus_t *pegasus)
 {
 	__le16 tmp = cpu_to_le16(0);
@@ -953,20 +948,22 @@ static inline void pegasus_reset_wol(struct net_device *dev)
 }
 
 static int
-pegasus_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+pegasus_get_link_ksettings(struct net_device *dev,
+			   struct ethtool_link_ksettings *ecmd)
 {
 	pegasus_t *pegasus;
 
 	pegasus = netdev_priv(dev);
-	mii_ethtool_gset(&pegasus->mii, ecmd);
+	mii_ethtool_get_link_ksettings(&pegasus->mii, ecmd);
 	return 0;
 }
 
 static int
-pegasus_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+pegasus_set_link_ksettings(struct net_device *dev,
+			   const struct ethtool_link_ksettings *ecmd)
 {
 	pegasus_t *pegasus = netdev_priv(dev);
-	return mii_ethtool_sset(&pegasus->mii, ecmd);
+	return mii_ethtool_set_link_ksettings(&pegasus->mii, ecmd);
 }
 
 static int pegasus_nway_reset(struct net_device *dev)
@@ -995,14 +992,14 @@ static void pegasus_set_msglevel(struct net_device *dev, u32 v)
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = pegasus_get_drvinfo,
-	.get_settings = pegasus_get_settings,
-	.set_settings = pegasus_set_settings,
 	.nway_reset = pegasus_nway_reset,
 	.get_link = pegasus_get_link,
 	.get_msglevel = pegasus_get_msglevel,
 	.set_msglevel = pegasus_set_msglevel,
 	.get_wol = pegasus_get_wol,
 	.set_wol = pegasus_set_wol,
+	.get_link_ksettings = pegasus_get_link_ksettings,
+	.set_link_ksettings = pegasus_set_link_ksettings,
 };
 
 static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
@@ -1292,7 +1289,6 @@ static const struct net_device_ops pegasus_netdev_ops = {
 	.ndo_do_ioctl =			pegasus_ioctl,
 	.ndo_start_xmit =		pegasus_start_xmit,
 	.ndo_set_rx_mode =		pegasus_set_multicast,
-	.ndo_get_stats =		pegasus_netdev_stats,
 	.ndo_tx_timeout =		pegasus_tx_timeout,
 	.ndo_set_mac_address =		eth_mac_addr,
 	.ndo_validate_addr =		eth_validate_addr,
diff --git a/drivers/net/usb/pegasus.h b/drivers/net/usb/pegasus.h
index d15646244fdf..9b7ea9c9167d 100644
--- a/drivers/net/usb/pegasus.h
+++ b/drivers/net/usb/pegasus.h
@@ -83,7 +83,6 @@ typedef struct pegasus {
 	struct usb_device	*usb;
 	struct usb_interface	*intf;
 	struct net_device	*net;
-	struct net_device_stats	stats;
 	struct mii_if_info	mii;
 	unsigned		flags;
 	unsigned		features;
diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c
index 22e1a9a99a7d..6fe59373cba9 100644
--- a/drivers/net/usb/plusb.c
+++ b/drivers/net/usb/plusb.c
@@ -102,7 +102,7 @@ static int pl_reset(struct usbnet *dev)
 }
 
 static const struct driver_info	prolific_info = {
-	.description =	"Prolific PL-2301/PL-2302/PL-25A1",
+	.description =	"Prolific PL-2301/PL-2302/PL-25A1/PL-27A1",
 	.flags =	FLAG_POINTTOPOINT | FLAG_NO_SETINT,
 		/* some PL-2302 versions seem to fail usb_set_interface() */
 	.reset =	pl_reset,
@@ -139,6 +139,17 @@ static const struct usb_device_id	products [] = {
 					 * Host-to-Host Cable
 					 */
 	.driver_info =  (unsigned long) &prolific_info,
+
+},
+
+/* super speed cables */
+{
+	USB_DEVICE(0x067b, 0x27a1),     /* PL-27A1, no eeprom
+					 * also: goobay Active USB 3.0
+					 * Data Link,
+					 * Unitek Y-3501
+					 */
+	.driver_info =  (unsigned long) &prolific_info,
 },
 
 	{ },		// END
@@ -158,5 +169,5 @@ static struct usb_driver plusb_driver = {
 module_usb_driver(plusb_driver);
 
 MODULE_AUTHOR("David Brownell");
-MODULE_DESCRIPTION("Prolific PL-2301/2302/25A1 USB Host to Host Link Driver");
+MODULE_DESCRIPTION("Prolific PL-2301/2302/25A1/27A1 USB Host to Host Link Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 805674550683..a3ed8115747c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -58,12 +58,198 @@ struct qmi_wwan_state {
 
 enum qmi_wwan_flags {
 	QMI_WWAN_FLAG_RAWIP = 1 << 0,
+	QMI_WWAN_FLAG_MUX = 1 << 1,
 };
 
 enum qmi_wwan_quirks {
 	QMI_WWAN_QUIRK_DTR = 1 << 0,	/* needs "set DTR" request */
 };
 
+struct qmimux_hdr {
+	u8 pad;
+	u8 mux_id;
+	__be16 pkt_len;
+};
+
+struct qmimux_priv {
+	struct net_device *real_dev;
+	u8 mux_id;
+};
+
+static int qmimux_open(struct net_device *dev)
+{
+	struct qmimux_priv *priv = netdev_priv(dev);
+	struct net_device *real_dev = priv->real_dev;
+
+	if (!(priv->real_dev->flags & IFF_UP))
+		return -ENETDOWN;
+
+	if (netif_carrier_ok(real_dev))
+		netif_carrier_on(dev);
+	return 0;
+}
+
+static int qmimux_stop(struct net_device *dev)
+{
+	netif_carrier_off(dev);
+	return 0;
+}
+
+static netdev_tx_t qmimux_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct qmimux_priv *priv = netdev_priv(dev);
+	unsigned int len = skb->len;
+	struct qmimux_hdr *hdr;
+
+	hdr = (struct qmimux_hdr *)skb_push(skb, sizeof(struct qmimux_hdr));
+	hdr->pad = 0;
+	hdr->mux_id = priv->mux_id;
+	hdr->pkt_len = cpu_to_be16(len);
+	skb->dev = priv->real_dev;
+	return dev_queue_xmit(skb);
+}
+
+static const struct net_device_ops qmimux_netdev_ops = {
+	.ndo_open       = qmimux_open,
+	.ndo_stop       = qmimux_stop,
+	.ndo_start_xmit = qmimux_start_xmit,
+};
+
+static void qmimux_setup(struct net_device *dev)
+{
+	dev->header_ops      = NULL;  /* No header */
+	dev->type            = ARPHRD_NONE;
+	dev->hard_header_len = 0;
+	dev->addr_len        = 0;
+	dev->flags           = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+	dev->netdev_ops      = &qmimux_netdev_ops;
+	dev->destructor      = free_netdev;
+}
+
+static struct net_device *qmimux_find_dev(struct usbnet *dev, u8 mux_id)
+{
+	struct qmimux_priv *priv;
+	struct list_head *iter;
+	struct net_device *ldev;
+
+	rcu_read_lock();
+	netdev_for_each_upper_dev_rcu(dev->net, ldev, iter) {
+		priv = netdev_priv(ldev);
+		if (priv->mux_id == mux_id) {
+			rcu_read_unlock();
+			return ldev;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
+static bool qmimux_has_slaves(struct usbnet *dev)
+{
+	return !list_empty(&dev->net->adj_list.upper);
+}
+
+static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	unsigned int len, offset = sizeof(struct qmimux_hdr);
+	struct qmimux_hdr *hdr;
+	struct net_device *net;
+	struct sk_buff *skbn;
+
+	while (offset < skb->len) {
+		hdr = (struct qmimux_hdr *)skb->data;
+		len = be16_to_cpu(hdr->pkt_len);
+
+		/* drop the packet, bogus length */
+		if (offset + len > skb->len)
+			return 0;
+
+		/* control packet, we do not know what to do */
+		if (hdr->pad & 0x80)
+			goto skip;
+
+		net = qmimux_find_dev(dev, hdr->mux_id);
+		if (!net)
+			goto skip;
+		skbn = netdev_alloc_skb(net, len);
+		if (!skbn)
+			return 0;
+		skbn->dev = net;
+
+		switch (skb->data[offset] & 0xf0) {
+		case 0x40:
+			skbn->protocol = htons(ETH_P_IP);
+			break;
+		case 0x60:
+			skbn->protocol = htons(ETH_P_IPV6);
+			break;
+		default:
+			/* not ip - do not know what to do */
+			goto skip;
+		}
+
+		memcpy(skb_put(skbn, len), skb->data + offset, len);
+		if (netif_rx(skbn) != NET_RX_SUCCESS)
+			return 0;
+
+skip:
+		offset += len + sizeof(struct qmimux_hdr);
+	}
+	return 1;
+}
+
+static int qmimux_register_device(struct net_device *real_dev, u8 mux_id)
+{
+	struct net_device *new_dev;
+	struct qmimux_priv *priv;
+	int err;
+
+	new_dev = alloc_netdev(sizeof(struct qmimux_priv),
+			       "qmimux%d", NET_NAME_UNKNOWN, qmimux_setup);
+	if (!new_dev)
+		return -ENOBUFS;
+
+	dev_net_set(new_dev, dev_net(real_dev));
+	priv = netdev_priv(new_dev);
+	priv->mux_id = mux_id;
+	priv->real_dev = real_dev;
+
+	err = register_netdevice(new_dev);
+	if (err < 0)
+		goto out_free_newdev;
+
+	/* Account for reference in struct qmimux_priv_priv */
+	dev_hold(real_dev);
+
+	err = netdev_upper_dev_link(real_dev, new_dev);
+	if (err)
+		goto out_unregister_netdev;
+
+	netif_stacked_transfer_operstate(real_dev, new_dev);
+
+	return 0;
+
+out_unregister_netdev:
+	unregister_netdevice(new_dev);
+	dev_put(real_dev);
+
+out_free_newdev:
+	free_netdev(new_dev);
+	return err;
+}
+
+static void qmimux_unregister_device(struct net_device *dev)
+{
+	struct qmimux_priv *priv = netdev_priv(dev);
+	struct net_device *real_dev = priv->real_dev;
+
+	netdev_upper_dev_unlink(real_dev, dev);
+	unregister_netdevice(dev);
+
+	/* Get rid of the reference to real_dev */
+	dev_put(real_dev);
+}
+
 static void qmi_wwan_netdev_setup(struct net_device *net)
 {
 	struct usbnet *dev = netdev_priv(net);
@@ -137,10 +323,114 @@ err:
 	return ret;
 }
 
+static ssize_t add_mux_show(struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_device *dev = to_net_dev(d);
+	struct qmimux_priv *priv;
+	struct list_head *iter;
+	struct net_device *ldev;
+	ssize_t count = 0;
+
+	rcu_read_lock();
+	netdev_for_each_upper_dev_rcu(dev, ldev, iter) {
+		priv = netdev_priv(ldev);
+		count += scnprintf(&buf[count], PAGE_SIZE - count,
+				   "0x%02x\n", priv->mux_id);
+	}
+	rcu_read_unlock();
+	return count;
+}
+
+static ssize_t add_mux_store(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct qmi_wwan_state *info = (void *)&dev->data;
+	u8 mux_id;
+	int ret;
+
+	if (kstrtou8(buf, 0, &mux_id))
+		return -EINVAL;
+
+	/* mux_id [1 - 0x7f] range empirically found */
+	if (mux_id < 1 || mux_id > 0x7f)
+		return -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (qmimux_find_dev(dev, mux_id)) {
+		netdev_err(dev->net, "mux_id already present\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* we don't want to modify a running netdev */
+	if (netif_running(dev->net)) {
+		netdev_err(dev->net, "Cannot change a running device\n");
+		ret = -EBUSY;
+		goto err;
+	}
+
+	ret = qmimux_register_device(dev->net, mux_id);
+	if (!ret) {
+		info->flags |= QMI_WWAN_FLAG_MUX;
+		ret = len;
+	}
+err:
+	rtnl_unlock();
+	return ret;
+}
+
+static ssize_t del_mux_show(struct device *d, struct device_attribute *attr, char *buf)
+{
+	return add_mux_show(d, attr, buf);
+}
+
+static ssize_t del_mux_store(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct qmi_wwan_state *info = (void *)&dev->data;
+	struct net_device *del_dev;
+	u8 mux_id;
+	int ret = 0;
+
+	if (kstrtou8(buf, 0, &mux_id))
+		return -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	/* we don't want to modify a running netdev */
+	if (netif_running(dev->net)) {
+		netdev_err(dev->net, "Cannot change a running device\n");
+		ret = -EBUSY;
+		goto err;
+	}
+
+	del_dev = qmimux_find_dev(dev, mux_id);
+	if (!del_dev) {
+		netdev_err(dev->net, "mux_id not present\n");
+		ret = -EINVAL;
+		goto err;
+	}
+	qmimux_unregister_device(del_dev);
+
+	if (!qmimux_has_slaves(dev))
+		info->flags &= ~QMI_WWAN_FLAG_MUX;
+	ret = len;
+err:
+	rtnl_unlock();
+	return ret;
+}
+
 static DEVICE_ATTR_RW(raw_ip);
+static DEVICE_ATTR_RW(add_mux);
+static DEVICE_ATTR_RW(del_mux);
 
 static struct attribute *qmi_wwan_sysfs_attrs[] = {
 	&dev_attr_raw_ip.attr,
+	&dev_attr_add_mux.attr,
+	&dev_attr_del_mux.attr,
 	NULL,
 };
 
@@ -184,6 +474,9 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	if (skb->len < dev->net->hard_header_len)
 		return 0;
 
+	if (info->flags & QMI_WWAN_FLAG_MUX)
+		return qmimux_rx_fixup(dev, skb);
+
 	switch (skb->data[0] & 0xf0) {
 	case 0x40:
 		proto = htons(ETH_P_IP);
@@ -249,6 +542,7 @@ static const struct net_device_ops qmi_wwan_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= qmi_wwan_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -580,6 +874,10 @@ static const struct usb_device_id products[] = {
 		USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x69),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* Motorola Mapphone devices with MDM6600 */
+		USB_VENDOR_AND_INTERFACE_INFO(0x22b8, USB_CLASS_VENDOR_SPEC, 0xfb, 0xff),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 
 	/* 2. Combined interface devices matching on class+protocol */
 	{	/* Huawei E367 and possibly others in "Windows mode" */
@@ -904,7 +1202,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
-	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
@@ -925,6 +1223,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
@@ -1030,11 +1330,33 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 	return usbnet_probe(intf, id);
 }
 
+static void qmi_wwan_disconnect(struct usb_interface *intf)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct qmi_wwan_state *info = (void *)&dev->data;
+	struct list_head *iter;
+	struct net_device *ldev;
+
+	if (info->flags & QMI_WWAN_FLAG_MUX) {
+		if (!rtnl_trylock()) {
+			restart_syscall();
+			return;
+		}
+		rcu_read_lock();
+		netdev_for_each_upper_dev_rcu(dev->net, ldev, iter)
+			qmimux_unregister_device(ldev);
+		rcu_read_unlock();
+		rtnl_unlock();
+		info->flags &= ~QMI_WWAN_FLAG_MUX;
+	}
+	usbnet_disconnect(intf);
+}
+
 static struct usb_driver qmi_wwan_driver = {
 	.name		      = "qmi_wwan",
 	.id_table	      = products,
 	.probe		      = qmi_wwan_probe,
-	.disconnect	      = usbnet_disconnect,
+	.disconnect	      = qmi_wwan_disconnect,
 	.suspend	      = qmi_wwan_suspend,
 	.resume		      =	qmi_wwan_resume,
 	.reset_resume         = qmi_wwan_resume,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 986243c932cc..ddc62cb69be8 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"8"
+#define NET_VERSION		"9"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -501,6 +501,8 @@ enum rtl_register_content {
 #define RTL8153_RMS		RTL8153_MAX_PACKET
 #define RTL8152_TX_TIMEOUT	(5 * HZ)
 #define RTL8152_NAPI_WEIGHT	64
+#define rx_reserved_size(x)	((x) + VLAN_ETH_HLEN + CRC_SIZE + \
+				 sizeof(struct rx_desc) + RX_ALIGN)
 
 /* rtl8152 flags */
 enum rtl8152_flags {
@@ -515,6 +517,7 @@ enum rtl8152_flags {
 
 /* Define these values to match your device */
 #define VENDOR_ID_REALTEK		0x0bda
+#define VENDOR_ID_MICROSOFT		0x045e
 #define VENDOR_ID_SAMSUNG		0x04e8
 #define VENDOR_ID_LENOVO		0x17ef
 #define VENDOR_ID_NVIDIA		0x0955
@@ -1292,6 +1295,7 @@ static void intr_callback(struct urb *urb)
 		}
 	} else {
 		if (netif_carrier_ok(tp->netdev)) {
+			netif_stop_queue(tp->netdev);
 			set_bit(RTL8152_LINK_CHG, &tp->flags);
 			schedule_delayed_work(&tp->schedule, 0);
 		}
@@ -1362,6 +1366,7 @@ static int alloc_all_mem(struct r8152 *tp)
 	spin_lock_init(&tp->rx_lock);
 	spin_lock_init(&tp->tx_lock);
 	INIT_LIST_HEAD(&tp->tx_free);
+	INIT_LIST_HEAD(&tp->rx_done);
 	skb_queue_head_init(&tp->tx_queue);
 	skb_queue_head_init(&tp->rx_queue);
 
@@ -1761,6 +1766,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 	unsigned long flags;
 	struct list_head *cursor, *next, rx_queue;
 	int ret = 0, work_done = 0;
+	struct napi_struct *napi = &tp->napi;
 
 	if (!skb_queue_empty(&tp->rx_queue)) {
 		while (work_done < budget) {
@@ -1773,7 +1779,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 				break;
 
 			pkt_len = skb->len;
-			napi_gro_receive(&tp->napi, skb);
+			napi_gro_receive(napi, skb);
 			work_done++;
 			stats->rx_packets++;
 			stats->rx_bytes += pkt_len;
@@ -1823,7 +1829,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 			pkt_len -= CRC_SIZE;
 			rx_data += sizeof(struct rx_desc);
 
-			skb = napi_alloc_skb(&tp->napi, pkt_len);
+			skb = napi_alloc_skb(napi, pkt_len);
 			if (!skb) {
 				stats->rx_dropped++;
 				goto find_next_rx;
@@ -1835,7 +1841,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 			skb->protocol = eth_type_trans(skb, netdev);
 			rtl_rx_vlan_tag(rx_desc, skb);
 			if (work_done < budget) {
-				napi_gro_receive(&tp->napi, skb);
+				napi_gro_receive(napi, skb);
 				work_done++;
 				stats->rx_packets++;
 				stats->rx_bytes += pkt_len;
@@ -2252,8 +2258,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp)
 
 static void r8153_set_rx_early_size(struct r8152 *tp)
 {
-	u32 mtu = tp->netdev->mtu;
-	u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 8;
+	u32 ocp_data = (agg_buf_sz - rx_reserved_size(tp->netdev->mtu)) / 4;
 
 	ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data);
 }
@@ -2898,7 +2903,8 @@ static void r8153_first_init(struct r8152 *tp)
 
 	rtl_rx_vlan_en(tp, tp->netdev->features & NETIF_F_HW_VLAN_CTAG_RX);
 
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8153_RMS);
+	ocp_data = tp->netdev->mtu + VLAN_ETH_HLEN + CRC_SIZE;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, ocp_data);
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_MTPS, MTPS_JUMBO);
 
 	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR0);
@@ -2950,7 +2956,8 @@ static void r8153_enter_oob(struct r8152 *tp)
 		usleep_range(1000, 2000);
 	}
 
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8153_RMS);
+	ocp_data = tp->netdev->mtu + VLAN_ETH_HLEN + CRC_SIZE;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, ocp_data);
 
 	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG);
 	ocp_data &= ~TEREDO_WAKE_MASK;
@@ -3150,6 +3157,7 @@ static bool rtl8153_in_nway(struct r8152 *tp)
 static void set_carrier(struct r8152 *tp)
 {
 	struct net_device *netdev = tp->netdev;
+	struct napi_struct *napi = &tp->napi;
 	u8 speed;
 
 	speed = rtl8152_get_speed(tp);
@@ -3159,19 +3167,22 @@ static void set_carrier(struct r8152 *tp)
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
 			netif_stop_queue(netdev);
-			napi_disable(&tp->napi);
+			napi_disable(napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
 			napi_enable(&tp->napi);
 			netif_wake_queue(netdev);
 			netif_info(tp, link, netdev, "carrier on\n");
+		} else if (netif_queue_stopped(netdev) &&
+			   skb_queue_len(&tp->tx_queue) < tp->tx_qlen) {
+			netif_wake_queue(netdev);
 		}
 	} else {
 		if (netif_carrier_ok(netdev)) {
 			netif_carrier_off(netdev);
-			napi_disable(&tp->napi);
+			napi_disable(napi);
 			tp->rtl_ops.disable(tp);
-			napi_enable(&tp->napi);
+			napi_enable(napi);
 			netif_info(tp, link, netdev, "carrier off\n");
 		}
 	}
@@ -3633,11 +3644,13 @@ static int rtl8152_runtime_suspend(struct r8152 *tp)
 		tp->rtl_ops.autosuspend_en(tp, true);
 
 		if (netif_carrier_ok(netdev)) {
-			napi_disable(&tp->napi);
+			struct napi_struct *napi = &tp->napi;
+
+			napi_disable(napi);
 			rtl_stop_rx(tp);
 			rxdy_gated_en(tp, false);
 			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
-			napi_enable(&tp->napi);
+			napi_enable(napi);
 		}
 	}
 
@@ -3653,12 +3666,14 @@ static int rtl8152_system_suspend(struct r8152 *tp)
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		struct napi_struct *napi = &tp->napi;
+
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
-		napi_disable(&tp->napi);
+		napi_disable(napi);
 		cancel_delayed_work_sync(&tp->schedule);
 		tp->rtl_ops.down(tp);
-		napi_enable(&tp->napi);
+		napi_enable(napi);
 	}
 
 	return ret;
@@ -3684,35 +3699,46 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
 static int rtl8152_resume(struct usb_interface *intf)
 {
 	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev = tp->netdev;
 
 	mutex_lock(&tp->control);
 
 	if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		tp->rtl_ops.init(tp);
 		queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
-		netif_device_attach(tp->netdev);
+		netif_device_attach(netdev);
 	}
 
-	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
+	if (netif_running(netdev) && netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+			struct napi_struct *napi = &tp->napi;
+
 			tp->rtl_ops.autosuspend_en(tp, false);
-			napi_disable(&tp->napi);
+			napi_disable(napi);
 			set_bit(WORK_ENABLE, &tp->flags);
-			if (netif_carrier_ok(tp->netdev))
-				rtl_start_rx(tp);
-			napi_enable(&tp->napi);
+			if (netif_carrier_ok(netdev)) {
+				if (rtl8152_get_speed(tp) & LINK_STATUS) {
+					rtl_start_rx(tp);
+				} else {
+					netif_carrier_off(netdev);
+					tp->rtl_ops.disable(tp);
+					netif_info(tp, link, netdev,
+						   "linking down\n");
+				}
+			}
+			napi_enable(napi);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 			smp_mb__after_atomic();
 			if (!list_empty(&tp->rx_done))
 				napi_schedule(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
-			netif_carrier_off(tp->netdev);
+			netif_carrier_off(netdev);
 			set_bit(WORK_ENABLE, &tp->flags);
 		}
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-		if (tp->netdev->flags & IFF_UP)
+		if (netdev->flags & IFF_UP)
 			tp->rtl_ops.autosuspend_en(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
@@ -3800,7 +3826,8 @@ static void rtl8152_get_drvinfo(struct net_device *netdev,
 }
 
 static
-int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
+int rtl8152_get_link_ksettings(struct net_device *netdev,
+			       struct ethtool_link_ksettings *cmd)
 {
 	struct r8152 *tp = netdev_priv(netdev);
 	int ret;
@@ -3814,7 +3841,7 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
 
 	mutex_lock(&tp->control);
 
-	ret = mii_ethtool_gset(&tp->mii, cmd);
+	ret = mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 
 	mutex_unlock(&tp->control);
 
@@ -3824,7 +3851,8 @@ out:
 	return ret;
 }
 
-static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8152_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct r8152 *tp = netdev_priv(dev);
 	int ret;
@@ -3835,11 +3863,12 @@ static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 
 	mutex_lock(&tp->control);
 
-	ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+	ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed,
+				cmd->base.duplex);
 	if (!ret) {
-		tp->autoneg = cmd->autoneg;
-		tp->speed = cmd->speed;
-		tp->duplex = cmd->duplex;
+		tp->autoneg = cmd->base.autoneg;
+		tp->speed = cmd->base.speed;
+		tp->duplex = cmd->base.duplex;
 	}
 
 	mutex_unlock(&tp->control);
@@ -4117,8 +4146,6 @@ static int rtl8152_set_coalesce(struct net_device *netdev,
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = rtl8152_get_drvinfo,
-	.get_settings = rtl8152_get_settings,
-	.set_settings = rtl8152_set_settings,
 	.get_link = ethtool_op_get_link,
 	.nway_reset = rtl8152_nway_reset,
 	.get_msglevel = rtl8152_get_msglevel,
@@ -4132,6 +4159,8 @@ static const struct ethtool_ops ops = {
 	.set_coalesce = rtl8152_set_coalesce,
 	.get_eee = rtl_ethtool_get_eee,
 	.set_eee = rtl_ethtool_set_eee,
+	.get_link_ksettings = rtl8152_get_link_ksettings,
+	.set_link_ksettings = rtl8152_set_link_ksettings,
 };
 
 static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -4200,8 +4229,14 @@ static int rtl8152_change_mtu(struct net_device *dev, int new_mtu)
 
 	dev->mtu = new_mtu;
 
-	if (netif_running(dev) && netif_carrier_ok(dev))
-		r8153_set_rx_early_size(tp);
+	if (netif_running(dev)) {
+		u32 rms = new_mtu + VLAN_ETH_HLEN + CRC_SIZE;
+
+		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, rms);
+
+		if (netif_carrier_ok(dev))
+			r8153_set_rx_early_size(tp);
+	}
 
 	mutex_unlock(&tp->control);
 
@@ -4224,44 +4259,6 @@ static const struct net_device_ops rtl8152_netdev_ops = {
 	.ndo_features_check	= rtl8152_features_check,
 };
 
-static void r8152b_get_version(struct r8152 *tp)
-{
-	u32	ocp_data;
-	u16	version;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR1);
-	version = (u16)(ocp_data & VERSION_MASK);
-
-	switch (version) {
-	case 0x4c00:
-		tp->version = RTL_VER_01;
-		break;
-	case 0x4c10:
-		tp->version = RTL_VER_02;
-		break;
-	case 0x5c00:
-		tp->version = RTL_VER_03;
-		tp->mii.supports_gmii = 1;
-		break;
-	case 0x5c10:
-		tp->version = RTL_VER_04;
-		tp->mii.supports_gmii = 1;
-		break;
-	case 0x5c20:
-		tp->version = RTL_VER_05;
-		tp->mii.supports_gmii = 1;
-		break;
-	case 0x5c30:
-		tp->version = RTL_VER_06;
-		tp->mii.supports_gmii = 1;
-		break;
-	default:
-		netif_info(tp, probe, tp->netdev,
-			   "Unknown version 0x%04x\n", version);
-		break;
-	}
-}
-
 static void rtl8152_unload(struct r8152 *tp)
 {
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
@@ -4326,14 +4323,66 @@ static int rtl_ops_init(struct r8152 *tp)
 	return ret;
 }
 
+static u8 rtl_get_version(struct usb_interface *intf)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	u32 ocp_data = 0;
+	__le32 *tmp;
+	u8 version;
+	int ret;
+
+	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return 0;
+
+	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
+			      RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
+			      PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
+	if (ret > 0)
+		ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK;
+
+	kfree(tmp);
+
+	switch (ocp_data) {
+	case 0x4c00:
+		version = RTL_VER_01;
+		break;
+	case 0x4c10:
+		version = RTL_VER_02;
+		break;
+	case 0x5c00:
+		version = RTL_VER_03;
+		break;
+	case 0x5c10:
+		version = RTL_VER_04;
+		break;
+	case 0x5c20:
+		version = RTL_VER_05;
+		break;
+	case 0x5c30:
+		version = RTL_VER_06;
+		break;
+	default:
+		version = RTL_VER_UNKNOWN;
+		dev_info(&intf->dev, "Unknown version 0x%04x\n", ocp_data);
+		break;
+	}
+
+	return version;
+}
+
 static int rtl8152_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
+	u8 version = rtl_get_version(intf);
 	struct r8152 *tp;
 	struct net_device *netdev;
 	int ret;
 
+	if (version == RTL_VER_UNKNOWN)
+		return -ENODEV;
+
 	if (udev->actconfig->desc.bConfigurationValue != 1) {
 		usb_driver_set_configuration(udev, 1);
 		return -ENODEV;
@@ -4353,8 +4402,18 @@ static int rtl8152_probe(struct usb_interface *intf,
 	tp->udev = udev;
 	tp->netdev = netdev;
 	tp->intf = intf;
+	tp->version = version;
+
+	switch (version) {
+	case RTL_VER_01:
+	case RTL_VER_02:
+		tp->mii.supports_gmii = 0;
+		break;
+	default:
+		tp->mii.supports_gmii = 1;
+		break;
+	}
 
-	r8152b_get_version(tp);
 	ret = rtl_ops_init(tp);
 	if (ret)
 		goto out;
@@ -4497,6 +4556,8 @@ static void rtl8152_disconnect(struct usb_interface *intf)
 static struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062)},
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index c5b21138b7eb..e96e2e5673d7 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -291,6 +291,7 @@ static const struct net_device_ops rndis_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index c81c79110cef..daaa88a66f40 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -791,47 +791,52 @@ static void rtl8150_get_drvinfo(struct net_device *netdev, struct ethtool_drvinf
 	usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info));
 }
 
-static int rtl8150_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int rtl8150_get_link_ksettings(struct net_device *netdev,
+				      struct ethtool_link_ksettings *ecmd)
 {
 	rtl8150_t *dev = netdev_priv(netdev);
 	short lpa, bmcr;
+	u32 supported;
 
-	ecmd->supported = (SUPPORTED_10baseT_Half |
+	supported = (SUPPORTED_10baseT_Half |
 			  SUPPORTED_10baseT_Full |
 			  SUPPORTED_100baseT_Half |
 			  SUPPORTED_100baseT_Full |
 			  SUPPORTED_Autoneg |
 			  SUPPORTED_TP | SUPPORTED_MII);
-	ecmd->port = PORT_TP;
-	ecmd->transceiver = XCVR_INTERNAL;
-	ecmd->phy_address = dev->phy;
+	ecmd->base.port = PORT_TP;
+	ecmd->base.phy_address = dev->phy;
 	get_registers(dev, BMCR, 2, &bmcr);
 	get_registers(dev, ANLP, 2, &lpa);
 	if (bmcr & BMCR_ANENABLE) {
 		u32 speed = ((lpa & (LPA_100HALF | LPA_100FULL)) ?
 			     SPEED_100 : SPEED_10);
-		ethtool_cmd_speed_set(ecmd, speed);
-		ecmd->autoneg = AUTONEG_ENABLE;
+		ecmd->base.speed = speed;
+		ecmd->base.autoneg = AUTONEG_ENABLE;
 		if (speed == SPEED_100)
-			ecmd->duplex = (lpa & LPA_100FULL) ?
+			ecmd->base.duplex = (lpa & LPA_100FULL) ?
 			    DUPLEX_FULL : DUPLEX_HALF;
 		else
-			ecmd->duplex = (lpa & LPA_10FULL) ?
+			ecmd->base.duplex = (lpa & LPA_10FULL) ?
 			    DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		ecmd->autoneg = AUTONEG_DISABLE;
-		ethtool_cmd_speed_set(ecmd, ((bmcr & BMCR_SPEED100) ?
-					     SPEED_100 : SPEED_10));
-		ecmd->duplex = (bmcr & BMCR_FULLDPLX) ?
+		ecmd->base.autoneg = AUTONEG_DISABLE;
+		ecmd->base.speed = ((bmcr & BMCR_SPEED100) ?
+					     SPEED_100 : SPEED_10);
+		ecmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
 		    DUPLEX_FULL : DUPLEX_HALF;
 	}
+
+	ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported,
+						supported);
+
 	return 0;
 }
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = rtl8150_get_drvinfo,
-	.get_settings = rtl8150_get_settings,
-	.get_link = ethtool_op_get_link
+	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = rtl8150_get_link_ksettings,
 };
 
 static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index ac69f28d92d2..2110ab3513f0 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -199,6 +199,7 @@ static const struct net_device_ops sierra_net_device_ops = {
 	.ndo_start_xmit         = usbnet_start_xmit,
 	.ndo_tx_timeout         = usbnet_tx_timeout,
 	.ndo_change_mtu         = usbnet_change_mtu,
+	.ndo_get_stats64        = usbnet_get_stats64,
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_validate_addr      = eth_validate_addr,
 };
@@ -648,9 +649,9 @@ static const struct ethtool_ops sierra_net_ethtool_ops = {
 	.get_link = sierra_net_get_link,
 	.get_msglevel = usbnet_get_msglevel,
 	.set_msglevel = usbnet_set_msglevel,
-	.get_settings = usbnet_get_settings,
-	.set_settings = usbnet_set_settings,
 	.nway_reset = usbnet_nway_reset,
+	.get_link_ksettings = usbnet_get_link_ksettings,
+	.set_link_ksettings = usbnet_set_link_ksettings,
 };
 
 static int sierra_net_get_fw_attr(struct usbnet *dev, u16 *datap)
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 0b17b40d7a4f..d0a113743195 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -743,13 +743,13 @@ static const struct ethtool_ops smsc75xx_ethtool_ops = {
 	.get_drvinfo	= usbnet_get_drvinfo,
 	.get_msglevel	= usbnet_get_msglevel,
 	.set_msglevel	= usbnet_set_msglevel,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.get_eeprom_len	= smsc75xx_ethtool_get_eeprom_len,
 	.get_eeprom	= smsc75xx_ethtool_get_eeprom,
 	.set_eeprom	= smsc75xx_ethtool_set_eeprom,
 	.get_wol	= smsc75xx_ethtool_get_wol,
 	.set_wol	= smsc75xx_ethtool_set_wol,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -1381,6 +1381,7 @@ static const struct net_device_ops smsc75xx_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_change_mtu		= smsc75xx_change_mtu,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
@@ -2203,13 +2204,9 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev,
 {
 	u32 tx_cmd_a, tx_cmd_b;
 
-	if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) {
-		struct sk_buff *skb2 =
-			skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags);
+	if (skb_cow_head(skb, SMSC75XX_TX_OVERHEAD)) {
 		dev_kfree_skb_any(skb);
-		skb = skb2;
-		if (!skb)
-			return NULL;
+		return NULL;
 	}
 
 	tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN) | TX_CMD_A_FCS;
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 831aa33d078a..765400b62168 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -33,7 +33,7 @@
 #include "smsc95xx.h"
 
 #define SMSC_CHIPNAME			"smsc95xx"
-#define SMSC_DRIVER_VERSION		"1.0.5"
+#define SMSC_DRIVER_VERSION		"1.0.6"
 #define HS_USB_PKT_SIZE			(512)
 #define FS_USB_PKT_SIZE			(64)
 #define DEFAULT_HS_BURST_CAP_SIZE	(16 * 1024 + 5 * HS_USB_PKT_SIZE)
@@ -853,32 +853,32 @@ static void set_mdix_status(struct net_device *net, __u8 mdix_ctrl)
 	pdata->mdix_ctrl = mdix_ctrl;
 }
 
-static int smsc95xx_get_settings(struct net_device *net,
-				 struct ethtool_cmd *cmd)
+static int smsc95xx_get_link_ksettings(struct net_device *net,
+				       struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 	int retval;
 
-	retval = usbnet_get_settings(net, cmd);
+	retval = usbnet_get_link_ksettings(net, cmd);
 
-	cmd->eth_tp_mdix = pdata->mdix_ctrl;
-	cmd->eth_tp_mdix_ctrl = pdata->mdix_ctrl;
+	cmd->base.eth_tp_mdix = pdata->mdix_ctrl;
+	cmd->base.eth_tp_mdix_ctrl = pdata->mdix_ctrl;
 
 	return retval;
 }
 
-static int smsc95xx_set_settings(struct net_device *net,
-				 struct ethtool_cmd *cmd)
+static int smsc95xx_set_link_ksettings(struct net_device *net,
+				       const struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 	int retval;
 
-	if (pdata->mdix_ctrl != cmd->eth_tp_mdix_ctrl)
-		set_mdix_status(net, cmd->eth_tp_mdix_ctrl);
+	if (pdata->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl)
+		set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl);
 
-	retval = usbnet_set_settings(net, cmd);
+	retval = usbnet_set_link_ksettings(net, cmd);
 
 	return retval;
 }
@@ -889,8 +889,6 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = {
 	.get_drvinfo	= usbnet_get_drvinfo,
 	.get_msglevel	= usbnet_get_msglevel,
 	.set_msglevel	= usbnet_set_msglevel,
-	.get_settings	= smsc95xx_get_settings,
-	.set_settings	= smsc95xx_set_settings,
 	.get_eeprom_len	= smsc95xx_ethtool_get_eeprom_len,
 	.get_eeprom	= smsc95xx_ethtool_get_eeprom,
 	.set_eeprom	= smsc95xx_ethtool_set_eeprom,
@@ -898,6 +896,8 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = {
 	.get_regs	= smsc95xx_ethtool_getregs,
 	.get_wol	= smsc95xx_ethtool_get_wol,
 	.set_wol	= smsc95xx_ethtool_set_wol,
+	.get_link_ksettings	= smsc95xx_get_link_ksettings,
+	.set_link_ksettings	= smsc95xx_set_link_ksettings,
 };
 
 static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -1248,6 +1248,7 @@ static const struct net_device_ops smsc95xx_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= smsc95xx_ioctl,
@@ -1498,7 +1499,7 @@ static int smsc95xx_enter_suspend3(struct usbnet *dev)
 	if (ret < 0)
 		return ret;
 
-	if (val & 0xFFFF) {
+	if (val & RX_FIFO_INF_USED_) {
 		netdev_info(dev->net, "rx fifo not empty in autosuspend\n");
 		return -EBUSY;
 	}
@@ -2001,13 +2002,13 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev,
 	/* We do not advertise SG, so skbs should be already linearized */
 	BUG_ON(skb_shinfo(skb)->nr_frags);
 
-	if (skb_headroom(skb) < overhead) {
-		struct sk_buff *skb2 = skb_copy_expand(skb,
-			overhead, 0, flags);
+	/* Make writable and expand header space by overhead if required */
+	if (skb_cow_head(skb, overhead)) {
+		/* Must deallocate here as returning NULL to indicate error
+		 * means the skb won't be deallocated in the caller.
+		 */
 		dev_kfree_skb_any(skb);
-		skb = skb2;
-		if (!skb)
-			return NULL;
+		return NULL;
 	}
 
 	if (csum) {
diff --git a/drivers/net/usb/smsc95xx.h b/drivers/net/usb/smsc95xx.h
index 29a4d9efce7c..cfc704f3a460 100644
--- a/drivers/net/usb/smsc95xx.h
+++ b/drivers/net/usb/smsc95xx.h
@@ -21,218 +21,280 @@
 #define _SMSC95XX_H
 
 /* Tx command words */
-#define TX_CMD_A_DATA_OFFSET_		(0x001F0000)
-#define TX_CMD_A_FIRST_SEG_		(0x00002000)
-#define TX_CMD_A_LAST_SEG_		(0x00001000)
-#define TX_CMD_A_BUF_SIZE_		(0x000007FF)
+#define TX_CMD_A_DATA_OFFSET_	(0x001F0000)	/* Data Start Offset */
+#define TX_CMD_A_FIRST_SEG_	(0x00002000)	/* First Segment */
+#define TX_CMD_A_LAST_SEG_	(0x00001000)	/* Last Segment */
+#define TX_CMD_A_BUF_SIZE_	(0x000007FF)	/* Buffer Size */
 
-#define TX_CMD_B_CSUM_ENABLE		(0x00004000)
-#define TX_CMD_B_ADD_CRC_DISABLE_	(0x00002000)
-#define TX_CMD_B_DISABLE_PADDING_	(0x00001000)
-#define TX_CMD_B_PKT_BYTE_LENGTH_	(0x000007FF)
+#define TX_CMD_B_CSUM_ENABLE	(0x00004000)	/* TX Checksum Enable */
+#define TX_CMD_B_ADD_CRC_DIS_	(0x00002000)	/* Add CRC Disable */
+#define TX_CMD_B_DIS_PADDING_	(0x00001000)	/* Disable Frame Padding */
+#define TX_CMD_B_FRAME_LENGTH_	(0x000007FF)	/* Frame Length (bytes) */
 
 /* Rx status word */
-#define RX_STS_FF_			(0x40000000)	/* Filter Fail */
-#define RX_STS_FL_			(0x3FFF0000)	/* Frame Length */
-#define RX_STS_ES_			(0x00008000)	/* Error Summary */
-#define RX_STS_BF_			(0x00002000)	/* Broadcast Frame */
-#define RX_STS_LE_			(0x00001000)	/* Length Error */
-#define RX_STS_RF_			(0x00000800)	/* Runt Frame */
-#define RX_STS_MF_			(0x00000400)	/* Multicast Frame */
-#define RX_STS_TL_			(0x00000080)	/* Frame too long */
-#define RX_STS_CS_			(0x00000040)	/* Collision Seen */
-#define RX_STS_FT_			(0x00000020)	/* Frame Type */
-#define RX_STS_RW_			(0x00000010)	/* Receive Watchdog */
-#define RX_STS_ME_			(0x00000008)	/* Mii Error */
-#define RX_STS_DB_			(0x00000004)	/* Dribbling */
-#define RX_STS_CRC_			(0x00000002)	/* CRC Error */
-
-/* SCSRs */
-#define ID_REV				(0x00)
-#define ID_REV_CHIP_ID_MASK_		(0xFFFF0000)
-#define ID_REV_CHIP_REV_MASK_		(0x0000FFFF)
-#define ID_REV_CHIP_ID_9500_		(0x9500)
-#define ID_REV_CHIP_ID_9500A_		(0x9E00)
-#define ID_REV_CHIP_ID_9512_		(0xEC00)
-#define ID_REV_CHIP_ID_9530_		(0x9530)
-#define ID_REV_CHIP_ID_89530_		(0x9E08)
-#define ID_REV_CHIP_ID_9730_		(0x9730)
-
-#define INT_STS				(0x08)
-#define INT_STS_TX_STOP_		(0x00020000)
-#define INT_STS_RX_STOP_		(0x00010000)
-#define INT_STS_PHY_INT_		(0x00008000)
-#define INT_STS_TXE_			(0x00004000)
-#define INT_STS_TDFU_			(0x00002000)
-#define INT_STS_TDFO_			(0x00001000)
-#define INT_STS_RXDF_			(0x00000800)
-#define INT_STS_GPIOS_			(0x000007FF)
-#define INT_STS_CLEAR_ALL_		(0xFFFFFFFF)
-
-#define RX_CFG				(0x0C)
-#define RX_FIFO_FLUSH_			(0x00000001)
-
-#define TX_CFG				(0x10)
-#define TX_CFG_ON_			(0x00000004)
-#define TX_CFG_STOP_			(0x00000002)
-#define TX_CFG_FIFO_FLUSH_		(0x00000001)
-
-#define HW_CFG				(0x14)
-#define HW_CFG_BIR_			(0x00001000)
-#define HW_CFG_LEDB_			(0x00000800)
-#define HW_CFG_RXDOFF_			(0x00000600)
-#define HW_CFG_DRP_			(0x00000040)
-#define HW_CFG_MEF_			(0x00000020)
-#define HW_CFG_LRST_			(0x00000008)
-#define HW_CFG_PSEL_			(0x00000004)
-#define HW_CFG_BCE_			(0x00000002)
-#define HW_CFG_SRST_			(0x00000001)
-
-#define RX_FIFO_INF			(0x18)
-
-#define PM_CTRL				(0x20)
-#define PM_CTL_RES_CLR_WKP_STS		(0x00000200)
-#define PM_CTL_DEV_RDY_			(0x00000080)
-#define PM_CTL_SUS_MODE_		(0x00000060)
-#define PM_CTL_SUS_MODE_0		(0x00000000)
-#define PM_CTL_SUS_MODE_1		(0x00000020)
-#define PM_CTL_SUS_MODE_2		(0x00000040)
-#define PM_CTL_SUS_MODE_3		(0x00000060)
-#define PM_CTL_PHY_RST_			(0x00000010)
-#define PM_CTL_WOL_EN_			(0x00000008)
-#define PM_CTL_ED_EN_			(0x00000004)
-#define PM_CTL_WUPS_			(0x00000003)
-#define PM_CTL_WUPS_NO_			(0x00000000)
-#define PM_CTL_WUPS_ED_			(0x00000001)
-#define PM_CTL_WUPS_WOL_		(0x00000002)
-#define PM_CTL_WUPS_MULTI_		(0x00000003)
-
-#define LED_GPIO_CFG			(0x24)
-#define LED_GPIO_CFG_SPD_LED		(0x01000000)
-#define LED_GPIO_CFG_LNK_LED		(0x00100000)
-#define LED_GPIO_CFG_FDX_LED		(0x00010000)
-
-#define GPIO_CFG			(0x28)
-
-#define AFC_CFG				(0x2C)
-
+#define RX_STS_FF_		(0x40000000)	/* Filter Fail */
+#define RX_STS_FL_		(0x3FFF0000)	/* Frame Length */
+#define RX_STS_ES_		(0x00008000)	/* Error Summary */
+#define RX_STS_BF_		(0x00002000)	/* Broadcast Frame */
+#define RX_STS_LE_		(0x00001000)	/* Length Error */
+#define RX_STS_RF_		(0x00000800)	/* Runt Frame */
+#define RX_STS_MF_		(0x00000400)	/* Multicast Frame */
+#define RX_STS_TL_		(0x00000080)	/* Frame too long */
+#define RX_STS_CS_		(0x00000040)	/* Collision Seen */
+#define RX_STS_FT_		(0x00000020)	/* Frame Type */
+#define RX_STS_RW_		(0x00000010)	/* Receive Watchdog */
+#define RX_STS_ME_		(0x00000008)	/* MII Error */
+#define RX_STS_DB_		(0x00000004)	/* Dribbling */
+#define RX_STS_CRC_		(0x00000002)	/* CRC Error */
+
+/* SCSRs - System Control and Status Registers */
+/* Device ID and Revision Register */
+#define ID_REV			(0x00)
+#define ID_REV_CHIP_ID_MASK_	(0xFFFF0000)
+#define ID_REV_CHIP_REV_MASK_	(0x0000FFFF)
+#define ID_REV_CHIP_ID_9500_	(0x9500)
+#define ID_REV_CHIP_ID_9500A_	(0x9E00)
+#define ID_REV_CHIP_ID_9512_	(0xEC00)
+#define ID_REV_CHIP_ID_9530_	(0x9530)
+#define ID_REV_CHIP_ID_89530_	(0x9E08)
+#define ID_REV_CHIP_ID_9730_	(0x9730)
+
+/* Interrupt Status Register */
+#define INT_STS			(0x08)
+#define INT_STS_MAC_RTO_	(0x00040000)	/* MAC Reset Time Out */
+#define INT_STS_TX_STOP_	(0x00020000)	/* TX Stopped */
+#define INT_STS_RX_STOP_	(0x00010000)	/* RX Stopped */
+#define INT_STS_PHY_INT_	(0x00008000)	/* PHY Interrupt */
+#define INT_STS_TXE_		(0x00004000)	/* Transmitter Error */
+#define INT_STS_TDFU_		(0x00002000)	/* TX Data FIFO Underrun */
+#define INT_STS_TDFO_		(0x00001000)	/* TX Data FIFO Overrun */
+#define INT_STS_RXDF_		(0x00000800)	/* RX Dropped Frame */
+#define INT_STS_GPIOS_		(0x000007FF)	/* GPIOs Interrupts */
+#define INT_STS_CLEAR_ALL_	(0xFFFFFFFF)
+
+/* Receive Configuration Register */
+#define RX_CFG			(0x0C)
+#define RX_FIFO_FLUSH_		(0x00000001)	/* Receive FIFO Flush */
+
+/* Transmit Configuration Register */
+#define TX_CFG			(0x10)
+#define TX_CFG_ON_		(0x00000004)	/* Transmitter Enable */
+#define TX_CFG_STOP_		(0x00000002)	/* Stop Transmitter */
+#define TX_CFG_FIFO_FLUSH_	(0x00000001)	/* Transmit FIFO Flush */
+
+/* Hardware Configuration Register */
+#define HW_CFG			(0x14)
+#define HW_CFG_BIR_		(0x00001000)	/* Bulk In Empty Response */
+#define HW_CFG_LEDB_		(0x00000800)	/* Activity LED 80ms Bypass */
+#define HW_CFG_RXDOFF_		(0x00000600)	/* RX Data Offset */
+#define HW_CFG_SBP_		(0x00000100)	/* Stall Bulk Out Pipe Dis. */
+#define HW_CFG_IME_		(0x00000080)	/* Internal MII Visi. Enable */
+#define HW_CFG_DRP_		(0x00000040)	/* Discard Errored RX Frame */
+#define HW_CFG_MEF_		(0x00000020)	/* Mult. ETH Frames/USB pkt */
+#define HW_CFG_ETC_		(0x00000010)	/* EEPROM Timeout Control */
+#define HW_CFG_LRST_		(0x00000008)	/* Soft Lite Reset */
+#define HW_CFG_PSEL_		(0x00000004)	/* External PHY Select */
+#define HW_CFG_BCE_		(0x00000002)	/* Burst Cap Enable */
+#define HW_CFG_SRST_		(0x00000001)	/* Soft Reset */
+
+/* Receive FIFO Information Register */
+#define RX_FIFO_INF		(0x18)
+#define RX_FIFO_INF_USED_	(0x0000FFFF)	/* RX Data FIFO Used Space */
+
+/* Transmit FIFO Information Register */
+#define TX_FIFO_INF		(0x1C)
+#define TX_FIFO_INF_FREE_	(0x0000FFFF)	/* TX Data FIFO Free Space */
+
+/* Power Management Control Register */
+#define PM_CTRL			(0x20)
+#define PM_CTL_RES_CLR_WKP_STS	(0x00000200)	/* Resume Clears Wakeup STS */
+#define PM_CTL_RES_CLR_WKP_EN	(0x00000100)	/* Resume Clears Wkp Enables */
+#define PM_CTL_DEV_RDY_		(0x00000080)	/* Device Ready */
+#define PM_CTL_SUS_MODE_	(0x00000060)	/* Suspend Mode */
+#define PM_CTL_SUS_MODE_0	(0x00000000)
+#define PM_CTL_SUS_MODE_1	(0x00000020)
+#define PM_CTL_SUS_MODE_2	(0x00000040)
+#define PM_CTL_SUS_MODE_3	(0x00000060)
+#define PM_CTL_PHY_RST_		(0x00000010)	/* PHY Reset */
+#define PM_CTL_WOL_EN_		(0x00000008)	/* Wake On Lan Enable */
+#define PM_CTL_ED_EN_		(0x00000004)	/* Energy Detect Enable */
+#define PM_CTL_WUPS_		(0x00000003)	/* Wake Up Status */
+#define PM_CTL_WUPS_NO_		(0x00000000)	/* No Wake Up Event Detected */
+#define PM_CTL_WUPS_ED_		(0x00000001)	/* Energy Detect */
+#define PM_CTL_WUPS_WOL_	(0x00000002)	/* Wake On Lan */
+#define PM_CTL_WUPS_MULTI_	(0x00000003)	/* Multiple Events Occurred */
+
+/* LED General Purpose IO Configuration Register */
+#define LED_GPIO_CFG		(0x24)
+#define LED_GPIO_CFG_SPD_LED	(0x01000000)	/* GPIOz as Speed LED */
+#define LED_GPIO_CFG_LNK_LED	(0x00100000)	/* GPIOy as Link LED */
+#define LED_GPIO_CFG_FDX_LED	(0x00010000)	/* GPIOx as Full Duplex LED */
+
+/* General Purpose IO Configuration Register */
+#define GPIO_CFG		(0x28)
+
+/* Automatic Flow Control Configuration Register */
+#define AFC_CFG			(0x2C)
+#define AFC_CFG_HI_		(0x00FF0000)	/* Auto Flow Ctrl High Level */
+#define AFC_CFG_LO_		(0x0000FF00)	/* Auto Flow Ctrl Low Level */
+#define AFC_CFG_BACK_DUR_	(0x000000F0)	/* Back Pressure Duration */
+#define AFC_CFG_FC_MULT_	(0x00000008)	/* Flow Ctrl on Mcast Frame */
+#define AFC_CFG_FC_BRD_		(0x00000004)	/* Flow Ctrl on Bcast Frame */
+#define AFC_CFG_FC_ADD_		(0x00000002)	/* Flow Ctrl on Addr. Decode */
+#define AFC_CFG_FC_ANY_		(0x00000001)	/* Flow Ctrl on Any Frame */
 /* Hi watermark = 15.5Kb (~10 mtu pkts) */
 /* low watermark = 3k (~2 mtu pkts) */
 /* backpressure duration = ~ 350us */
 /* Apply FC on any frame. */
-#define AFC_CFG_DEFAULT			(0x00F830A1)
-
-#define E2P_CMD				(0x30)
-#define E2P_CMD_BUSY_			(0x80000000)
-#define E2P_CMD_MASK_			(0x70000000)
-#define E2P_CMD_READ_			(0x00000000)
-#define E2P_CMD_EWDS_			(0x10000000)
-#define E2P_CMD_EWEN_			(0x20000000)
-#define E2P_CMD_WRITE_			(0x30000000)
-#define E2P_CMD_WRAL_			(0x40000000)
-#define E2P_CMD_ERASE_			(0x50000000)
-#define E2P_CMD_ERAL_			(0x60000000)
-#define E2P_CMD_RELOAD_			(0x70000000)
-#define E2P_CMD_TIMEOUT_		(0x00000400)
-#define E2P_CMD_LOADED_			(0x00000200)
-#define E2P_CMD_ADDR_			(0x000001FF)
-
-#define MAX_EEPROM_SIZE			(512)
-
-#define E2P_DATA			(0x34)
-#define E2P_DATA_MASK_			(0x000000FF)
-
-#define BURST_CAP			(0x38)
-
+#define AFC_CFG_DEFAULT		(0x00F830A1)
+
+/* EEPROM Command Register */
+#define E2P_CMD			(0x30)
+#define E2P_CMD_BUSY_		(0x80000000)	/* E2P Controller Busy */
+#define E2P_CMD_MASK_		(0x70000000)	/* Command Mask (see below) */
+#define E2P_CMD_READ_		(0x00000000)	/* Read Location */
+#define E2P_CMD_EWDS_		(0x10000000)	/* Erase/Write Disable */
+#define E2P_CMD_EWEN_		(0x20000000)	/* Erase/Write Enable */
+#define E2P_CMD_WRITE_		(0x30000000)	/* Write Location */
+#define E2P_CMD_WRAL_		(0x40000000)	/* Write All */
+#define E2P_CMD_ERASE_		(0x50000000)	/* Erase Location */
+#define E2P_CMD_ERAL_		(0x60000000)	/* Erase All */
+#define E2P_CMD_RELOAD_		(0x70000000)	/* Data Reload */
+#define E2P_CMD_TIMEOUT_	(0x00000400)	/* Set if no resp within 30ms */
+#define E2P_CMD_LOADED_		(0x00000200)	/* Valid EEPROM found */
+#define E2P_CMD_ADDR_		(0x000001FF)	/* Byte aligned address */
+
+#define MAX_EEPROM_SIZE		(512)
+
+/* EEPROM Data Register */
+#define E2P_DATA		(0x34)
+#define E2P_DATA_MASK_		(0x000000FF)	/* EEPROM Data Mask */
+
+/* Burst Cap Register */
+#define BURST_CAP		(0x38)
+#define BURST_CAP_MASK_		(0x000000FF)	/* Max burst sent by the UTX */
+
+/* Configuration Straps Status Register */
 #define	STRAP_STATUS			(0x3C)
-#define	STRAP_STATUS_PWR_SEL_		(0x00000020)
-#define	STRAP_STATUS_AMDIX_EN_		(0x00000010)
-#define	STRAP_STATUS_PORT_SWAP_		(0x00000008)
-#define	STRAP_STATUS_EEP_SIZE_		(0x00000004)
-#define	STRAP_STATUS_RMT_WKP_		(0x00000002)
-#define	STRAP_STATUS_EEP_DISABLE_	(0x00000001)
-
-#define GPIO_WAKE			(0x64)
-
-#define INT_EP_CTL			(0x68)
-#define INT_EP_CTL_INTEP_		(0x80000000)
-#define INT_EP_CTL_MACRTO_		(0x00080000)
-#define INT_EP_CTL_TX_STOP_		(0x00020000)
-#define INT_EP_CTL_RX_STOP_		(0x00010000)
-#define INT_EP_CTL_PHY_INT_		(0x00008000)
-#define INT_EP_CTL_TXE_			(0x00004000)
-#define INT_EP_CTL_TDFU_		(0x00002000)
-#define INT_EP_CTL_TDFO_		(0x00001000)
-#define INT_EP_CTL_RXDF_		(0x00000800)
-#define INT_EP_CTL_GPIOS_		(0x000007FF)
-
-#define BULK_IN_DLY			(0x6C)
-
-/* MAC CSRs */
-#define MAC_CR				(0x100)
-#define MAC_CR_RXALL_			(0x80000000)
-#define MAC_CR_RCVOWN_			(0x00800000)
-#define MAC_CR_LOOPBK_			(0x00200000)
-#define MAC_CR_FDPX_			(0x00100000)
-#define MAC_CR_MCPAS_			(0x00080000)
-#define MAC_CR_PRMS_			(0x00040000)
-#define MAC_CR_INVFILT_			(0x00020000)
-#define MAC_CR_PASSBAD_			(0x00010000)
-#define MAC_CR_HFILT_			(0x00008000)
-#define MAC_CR_HPFILT_			(0x00002000)
-#define MAC_CR_LCOLL_			(0x00001000)
-#define MAC_CR_BCAST_			(0x00000800)
-#define MAC_CR_DISRTY_			(0x00000400)
-#define MAC_CR_PADSTR_			(0x00000100)
-#define MAC_CR_BOLMT_MASK		(0x000000C0)
-#define MAC_CR_DFCHK_			(0x00000020)
-#define MAC_CR_TXEN_			(0x00000008)
-#define MAC_CR_RXEN_			(0x00000004)
-
-#define ADDRH				(0x104)
-
-#define ADDRL				(0x108)
-
-#define HASHH				(0x10C)
-
-#define HASHL				(0x110)
-
-#define MII_ADDR			(0x114)
-#define MII_WRITE_			(0x02)
-#define MII_BUSY_			(0x01)
-#define MII_READ_			(0x00) /* ~of MII Write bit */
-
-#define MII_DATA			(0x118)
-
-#define FLOW				(0x11C)
-#define FLOW_FCPT_			(0xFFFF0000)
-#define FLOW_FCPASS_			(0x00000004)
-#define FLOW_FCEN_			(0x00000002)
-#define FLOW_FCBSY_			(0x00000001)
-
-#define VLAN1				(0x120)
-
-#define VLAN2				(0x124)
-
-#define WUFF				(0x128)
-#define LAN9500_WUFF_NUM		(4)
-#define LAN9500A_WUFF_NUM		(8)
-
-#define WUCSR				(0x12C)
-#define WUCSR_WFF_PTR_RST_		(0x80000000)
-#define WUCSR_GUE_			(0x00000200)
-#define WUCSR_WUFR_			(0x00000040)
-#define WUCSR_MPR_			(0x00000020)
-#define WUCSR_WAKE_EN_			(0x00000004)
-#define WUCSR_MPEN_			(0x00000002)
-
-#define COE_CR				(0x130)
-#define Tx_COE_EN_			(0x00010000)
-#define Rx_COE_MODE_			(0x00000002)
-#define Rx_COE_EN_			(0x00000001)
-
-/* Vendor-specific PHY Definitions */
-
+#define	STRAP_STATUS_PWR_SEL_		(0x00000020) /* Device self-powered */
+#define	STRAP_STATUS_AMDIX_EN_		(0x00000010) /* Auto-MDIX Enabled */
+#define	STRAP_STATUS_PORT_SWAP_		(0x00000008) /* USBD+/USBD- Swapped */
+#define	STRAP_STATUS_EEP_SIZE_		(0x00000004) /* EEPROM Size */
+#define	STRAP_STATUS_RMT_WKP_		(0x00000002) /* Remote Wkp supported */
+#define	STRAP_STATUS_EEP_DISABLE_	(0x00000001) /* EEPROM Disabled */
+
+/* Data Port Select Register */
+#define DP_SEL			(0x40)
+
+/* Data Port Command Register */
+#define DP_CMD			(0x44)
+
+/* Data Port Address Register */
+#define DP_ADDR			(0x48)
+
+/* Data Port Data 0 Register */
+#define DP_DATA0		(0x4C)
+
+/* Data Port Data 1 Register */
+#define DP_DATA1		(0x50)
+
+/* General Purpose IO Wake Enable and Polarity Register */
+#define GPIO_WAKE		(0x64)
+
+/* Interrupt Endpoint Control Register */
+#define INT_EP_CTL		(0x68)
+#define INT_EP_CTL_INTEP_	(0x80000000)	/* Always TX Interrupt PKT */
+#define INT_EP_CTL_MAC_RTO_	(0x00080000)	/* MAC Reset Time Out */
+#define INT_EP_CTL_RX_FIFO_	(0x00040000)	/* RX FIFO Has Frame */
+#define INT_EP_CTL_TX_STOP_	(0x00020000)	/* TX Stopped */
+#define INT_EP_CTL_RX_STOP_	(0x00010000)	/* RX Stopped */
+#define INT_EP_CTL_PHY_INT_	(0x00008000)	/* PHY Interrupt */
+#define INT_EP_CTL_TXE_		(0x00004000)	/* TX Error */
+#define INT_EP_CTL_TDFU_	(0x00002000)	/* TX Data FIFO Underrun */
+#define INT_EP_CTL_TDFO_	(0x00001000)	/* TX Data FIFO Overrun */
+#define INT_EP_CTL_RXDF_	(0x00000800)	/* RX Dropped Frame */
+#define INT_EP_CTL_GPIOS_	(0x000007FF)	/* GPIOs Interrupt Enable */
+
+/* Bulk In Delay Register (units of 16.667ns, until ~1092µs) */
+#define BULK_IN_DLY		(0x6C)
+
+/* MAC CSRs - MAC Control and Status Registers */
+/* MAC Control Register */
+#define MAC_CR			(0x100)
+#define MAC_CR_RXALL_		(0x80000000)	/* Receive All Mode */
+#define MAC_CR_RCVOWN_		(0x00800000)	/* Disable Receive Own */
+#define MAC_CR_LOOPBK_		(0x00200000)	/* Loopback Operation Mode */
+#define MAC_CR_FDPX_		(0x00100000)	/* Full Duplex Mode */
+#define MAC_CR_MCPAS_		(0x00080000)	/* Pass All Multicast */
+#define MAC_CR_PRMS_		(0x00040000)	/* Promiscuous Mode */
+#define MAC_CR_INVFILT_		(0x00020000)	/* Inverse Filtering */
+#define MAC_CR_PASSBAD_		(0x00010000)	/* Pass Bad Frames */
+#define MAC_CR_HFILT_		(0x00008000)	/* Hash Only Filtering Mode */
+#define MAC_CR_HPFILT_		(0x00002000)	/* Hash/Perfect Filt. Mode */
+#define MAC_CR_LCOLL_		(0x00001000)	/* Late Collision Control */
+#define MAC_CR_BCAST_		(0x00000800)	/* Disable Broadcast Frames */
+#define MAC_CR_DISRTY_		(0x00000400)	/* Disable Retry */
+#define MAC_CR_PADSTR_		(0x00000100)	/* Automatic Pad Stripping */
+#define MAC_CR_BOLMT_MASK	(0x000000C0)	/* BackOff Limit */
+#define MAC_CR_DFCHK_		(0x00000020)	/* Deferral Check */
+#define MAC_CR_TXEN_		(0x00000008)	/* Transmitter Enable */
+#define MAC_CR_RXEN_		(0x00000004)	/* Receiver Enable */
+
+/* MAC Address High Register */
+#define ADDRH			(0x104)
+
+/* MAC Address Low Register */
+#define ADDRL			(0x108)
+
+/* Multicast Hash Table High Register */
+#define HASHH			(0x10C)
+
+/* Multicast Hash Table Low Register */
+#define HASHL			(0x110)
+
+/* MII Access Register */
+#define MII_ADDR		(0x114)
+#define MII_WRITE_		(0x02)
+#define MII_BUSY_		(0x01)
+#define MII_READ_		(0x00) /* ~of MII Write bit */
+
+/* MII Data Register */
+#define MII_DATA		(0x118)
+
+/* Flow Control Register */
+#define FLOW			(0x11C)
+#define FLOW_FCPT_		(0xFFFF0000)	/* Pause Time */
+#define FLOW_FCPASS_		(0x00000004)	/* Pass Control Frames */
+#define FLOW_FCEN_		(0x00000002)	/* Flow Control Enable */
+#define FLOW_FCBSY_		(0x00000001)	/* Flow Control Busy */
+
+/* VLAN1 Tag Register */
+#define VLAN1			(0x120)
+
+/* VLAN2 Tag Register */
+#define VLAN2			(0x124)
+
+/* Wake Up Frame Filter Register */
+#define WUFF			(0x128)
+#define LAN9500_WUFF_NUM	(4)
+#define LAN9500A_WUFF_NUM	(8)
+
+/* Wake Up Control and Status Register */
+#define WUCSR			(0x12C)
+#define WUCSR_WFF_PTR_RST_	(0x80000000)	/* WFrame Filter Pointer Rst */
+#define WUCSR_GUE_		(0x00000200)	/* Global Unicast Enable */
+#define WUCSR_WUFR_		(0x00000040)	/* Wakeup Frame Received */
+#define WUCSR_MPR_		(0x00000020)	/* Magic Packet Received */
+#define WUCSR_WAKE_EN_		(0x00000004)	/* Wakeup Frame Enable */
+#define WUCSR_MPEN_		(0x00000002)	/* Magic Packet Enable */
+
+/* Checksum Offload Engine Control Register */
+#define COE_CR			(0x130)
+#define Tx_COE_EN_		(0x00010000)	/* TX Csum Offload Enable */
+#define Rx_COE_MODE_		(0x00000002)	/* RX Csum Offload Mode */
+#define Rx_COE_EN_		(0x00000001)	/* RX Csum Offload Enable */
+
+/* Vendor-specific PHY Definitions (via MII access) */
 /* EDPD NLP / crossover time configuration (LAN9500A only) */
 #define PHY_EDPD_CONFIG			(16)
 #define PHY_EDPD_CONFIG_TX_NLP_EN_	((u16)0x8000)
@@ -255,17 +317,20 @@
 #define MODE_CTRL_STS_EDPWRDOWN_	((u16)0x2000)
 #define MODE_CTRL_STS_ENERGYON_		((u16)0x0002)
 
+/* Control/Status Indication Register */
 #define SPECIAL_CTRL_STS		(27)
 #define SPECIAL_CTRL_STS_OVRRD_AMDIX_	((u16)0x8000)
 #define SPECIAL_CTRL_STS_AMDIX_ENABLE_	((u16)0x4000)
 #define SPECIAL_CTRL_STS_AMDIX_STATE_	((u16)0x2000)
 
+/* Interrupt Source Register */
 #define PHY_INT_SRC			(29)
 #define PHY_INT_SRC_ENERGY_ON_		((u16)0x0080)
 #define PHY_INT_SRC_ANEG_COMP_		((u16)0x0040)
 #define PHY_INT_SRC_REMOTE_FAULT_	((u16)0x0020)
 #define PHY_INT_SRC_LINK_DOWN_		((u16)0x0010)
 
+/* Interrupt Mask Register */
 #define PHY_INT_MASK			(30)
 #define PHY_INT_MASK_ENERGY_ON_		((u16)0x0080)
 #define PHY_INT_MASK_ANEG_COMP_		((u16)0x0040)
@@ -273,7 +338,7 @@
 #define PHY_INT_MASK_LINK_DOWN_		((u16)0x0010)
 #define PHY_INT_MASK_DEFAULT_		(PHY_INT_MASK_ANEG_COMP_ | \
 					 PHY_INT_MASK_LINK_DOWN_)
-
+/* PHY Special Control/Status Register */
 #define PHY_SPECIAL			(31)
 #define PHY_SPECIAL_SPD_		((u16)0x001C)
 #define PHY_SPECIAL_SPD_10HALF_		((u16)0x0004)
@@ -287,12 +352,13 @@
 #define USB_VENDOR_REQUEST_GET_STATS		0xA2
 
 /* Interrupt Endpoint status word bitfields */
-#define INT_ENP_TX_STOP_		((u32)BIT(17))
-#define INT_ENP_RX_STOP_		((u32)BIT(16))
-#define INT_ENP_PHY_INT_		((u32)BIT(15))
-#define INT_ENP_TXE_			((u32)BIT(14))
-#define INT_ENP_TDFU_			((u32)BIT(13))
-#define INT_ENP_TDFO_			((u32)BIT(12))
-#define INT_ENP_RXDF_			((u32)BIT(11))
+#define INT_ENP_MAC_RTO_		((u32)BIT(18))	/* MAC Reset Time Out */
+#define INT_ENP_TX_STOP_		((u32)BIT(17))	/* TX Stopped */
+#define INT_ENP_RX_STOP_		((u32)BIT(16))	/* RX Stopped */
+#define INT_ENP_PHY_INT_		((u32)BIT(15))	/* PHY Interrupt */
+#define INT_ENP_TXE_			((u32)BIT(14))	/* TX Error */
+#define INT_ENP_TDFU_			((u32)BIT(13))	/* TX FIFO Underrun */
+#define INT_ENP_TDFO_			((u32)BIT(12))	/* TX FIFO Overrun */
+#define INT_ENP_RXDF_			((u32)BIT(11))	/* RX Dropped Frame */
 
 #endif /* _SMSC95XX_H */
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 4a1e9c489f1f..2d316c1b851b 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -249,9 +249,9 @@ static const struct ethtool_ops sr9700_ethtool_ops = {
 	.set_msglevel	= usbnet_set_msglevel,
 	.get_eeprom_len	= sr9700_get_eeprom_len,
 	.get_eeprom	= sr9700_get_eeprom,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.nway_reset	= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static void sr9700_set_multicast(struct net_device *netdev)
@@ -308,6 +308,7 @@ static const struct net_device_ops sr9700_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= sr9700_ioctl,
 	.ndo_set_rx_mode	= sr9700_set_multicast,
@@ -456,14 +457,9 @@ static struct sk_buff *sr9700_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 
 	len = skb->len;
 
-	if (skb_headroom(skb) < SR_TX_OVERHEAD) {
-		struct sk_buff *skb2;
-
-		skb2 = skb_copy_expand(skb, SR_TX_OVERHEAD, 0, flags);
+	if (skb_cow_head(skb, SR_TX_OVERHEAD)) {
 		dev_kfree_skb_any(skb);
-		skb = skb2;
-		if (!skb)
-			return NULL;
+		return NULL;
 	}
 
 	__skb_push(skb, SR_TX_OVERHEAD);
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index a50df0d8fb9a..9277a0f228df 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -524,9 +524,9 @@ static const struct ethtool_ops sr9800_ethtool_ops = {
 	.set_wol	= sr_set_wol,
 	.get_eeprom_len	= sr_get_eeprom_len,
 	.get_eeprom	= sr_get_eeprom,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.nway_reset	= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int sr9800_link_reset(struct usbnet *dev)
@@ -679,6 +679,7 @@ static const struct net_device_ops sr9800_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= sr_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= sr_ioctl,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3de65ea6531a..79048e72c1bd 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -82,8 +82,6 @@
 // randomly generated ethernet address
 static u8	node_id [ETH_ALEN];
 
-static const char driver_name [] = "usbnet";
-
 /* use ethtool to change the level for any given device */
 static int msg_level = -1;
 module_param (msg_level, int, 0);
@@ -316,6 +314,7 @@ static void __usbnet_status_stop_force(struct usbnet *dev)
  */
 void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
 {
+	struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
 	int	status;
 
 	if (test_bit(EVENT_RX_PAUSED, &dev->flags)) {
@@ -327,8 +326,10 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
 	if (skb->protocol == 0)
 		skb->protocol = eth_type_trans (skb, dev->net);
 
-	dev->net->stats.rx_packets++;
-	dev->net->stats.rx_bytes += skb->len;
+	u64_stats_update_begin(&stats64->syncp);
+	stats64->rx_packets++;
+	stats64->rx_bytes += skb->len;
+	u64_stats_update_end(&stats64->syncp);
 
 	netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n",
 		  skb->len + sizeof (struct ethhdr), skb->protocol);
@@ -947,18 +948,20 @@ EXPORT_SYMBOL_GPL(usbnet_open);
  * they'll probably want to use this base set.
  */
 
-int usbnet_get_settings (struct net_device *net, struct ethtool_cmd *cmd)
+int usbnet_get_link_ksettings(struct net_device *net,
+			      struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 
 	if (!dev->mii.mdio_read)
 		return -EOPNOTSUPP;
 
-	return mii_ethtool_gset(&dev->mii, cmd);
+	return mii_ethtool_get_link_ksettings(&dev->mii, cmd);
 }
-EXPORT_SYMBOL_GPL(usbnet_get_settings);
+EXPORT_SYMBOL_GPL(usbnet_get_link_ksettings);
 
-int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
+int usbnet_set_link_ksettings(struct net_device *net,
+			      const struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 	int retval;
@@ -966,7 +969,7 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
 	if (!dev->mii.mdio_write)
 		return -EOPNOTSUPP;
 
-	retval = mii_ethtool_sset(&dev->mii, cmd);
+	retval = mii_ethtool_set_link_ksettings(&dev->mii, cmd);
 
 	/* link speed/duplex might have changed */
 	if (dev->driver_info->link_reset)
@@ -976,9 +979,39 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
 	usbnet_update_max_qlen(dev);
 
 	return retval;
+}
+EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings);
 
+void usbnet_get_stats64(struct net_device *net, struct rtnl_link_stats64 *stats)
+{
+	struct usbnet *dev = netdev_priv(net);
+	unsigned int start;
+	int cpu;
+
+	netdev_stats_to_stats64(stats, &net->stats);
+
+	for_each_possible_cpu(cpu) {
+		struct pcpu_sw_netstats *stats64;
+		u64 rx_packets, rx_bytes;
+		u64 tx_packets, tx_bytes;
+
+		stats64 = per_cpu_ptr(dev->stats64, cpu);
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats64->syncp);
+			rx_packets = stats64->rx_packets;
+			rx_bytes = stats64->rx_bytes;
+			tx_packets = stats64->tx_packets;
+			tx_bytes = stats64->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats64->syncp, start));
+
+		stats->rx_packets += rx_packets;
+		stats->rx_bytes += rx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_bytes += tx_bytes;
+	}
 }
-EXPORT_SYMBOL_GPL(usbnet_set_settings);
+EXPORT_SYMBOL_GPL(usbnet_get_stats64);
 
 u32 usbnet_get_link (struct net_device *net)
 {
@@ -1038,14 +1071,14 @@ EXPORT_SYMBOL_GPL(usbnet_set_msglevel);
 
 /* drivers may override default ethtool_ops in their bind() routine */
 static const struct ethtool_ops usbnet_ethtool_ops = {
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.get_link		= usbnet_get_link,
 	.nway_reset		= usbnet_nway_reset,
 	.get_drvinfo		= usbnet_get_drvinfo,
 	.get_msglevel		= usbnet_get_msglevel,
 	.set_msglevel		= usbnet_set_msglevel,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 /*-------------------------------------------------------------------------*/
@@ -1211,8 +1244,12 @@ static void tx_complete (struct urb *urb)
 	struct usbnet		*dev = entry->dev;
 
 	if (urb->status == 0) {
-		dev->net->stats.tx_packets += entry->packets;
-		dev->net->stats.tx_bytes += entry->length;
+		struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+
+		u64_stats_update_begin(&stats64->syncp);
+		stats64->tx_packets += entry->packets;
+		stats64->tx_bytes += entry->length;
+		u64_stats_update_end(&stats64->syncp);
 	} else {
 		dev->net->stats.tx_errors++;
 
@@ -1569,6 +1606,7 @@ void usbnet_disconnect (struct usb_interface *intf)
 	usb_free_urb(dev->interrupt);
 	kfree(dev->padding_pkt);
 
+	free_percpu(dev->stats64);
 	free_netdev(net);
 }
 EXPORT_SYMBOL_GPL(usbnet_disconnect);
@@ -1580,6 +1618,7 @@ static const struct net_device_ops usbnet_netdev_ops = {
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_set_rx_mode	= usbnet_set_rx_mode,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -1641,6 +1680,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	dev->intf = udev;
 	dev->driver_info = info;
 	dev->driver_name = name;
+
+	dev->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->stats64)
+		goto out0;
+
 	dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
 				| NETIF_MSG_PROBE | NETIF_MSG_LINK);
 	init_waitqueue_head(&dev->wait);
@@ -1780,6 +1824,8 @@ out1:
 	 */
 	cancel_work_sync(&dev->kevent);
 	del_timer_sync(&dev->delay);
+	free_percpu(dev->stats64);
+out0:
 	free_netdev(net);
 out:
 	return status;
@@ -1929,7 +1975,7 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		   " value=0x%04x index=0x%04x size=%d\n",
 		   cmd, reqtype, value, index, size);
 
-	if (data) {
+	if (size) {
 		buf = kmalloc(size, GFP_KERNEL);
 		if (!buf)
 			goto out;
@@ -1938,8 +1984,13 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 	err = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
 			      cmd, reqtype, value, index, buf, size,
 			      USB_CTRL_GET_TIMEOUT);
-	if (err > 0 && err <= size)
-		memcpy(data, buf, err);
+	if (err > 0 && err <= size) {
+        if (data)
+            memcpy(data, buf, err);
+        else
+            netdev_dbg(dev->net,
+                "Huh? Data requested but thrown away.\n");
+    }
 	kfree(buf);
 out:
 	return err;
@@ -1960,7 +2011,13 @@ static int __usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		buf = kmemdup(data, size, GFP_KERNEL);
 		if (!buf)
 			goto out;
-	}
+	} else {
+        if (size) {
+            WARN_ON_ONCE(1);
+            err = -EINVAL;
+            goto out;
+        }
+    }
 
 	err = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
 			      cmd, reqtype, value, index, buf, size,
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8c39d6d690e5..38f0f03a29c8 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -45,18 +45,13 @@ static struct {
 	{ "peer_ifindex" },
 };
 
-static int veth_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int veth_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
-	cmd->supported		= 0;
-	cmd->advertising	= 0;
-	ethtool_cmd_speed_set(cmd, SPEED_10000);
-	cmd->duplex		= DUPLEX_FULL;
-	cmd->port		= PORT_TP;
-	cmd->phy_address	= 0;
-	cmd->transceiver	= XCVR_INTERNAL;
-	cmd->autoneg		= AUTONEG_DISABLE;
-	cmd->maxtxpkt		= 0;
-	cmd->maxrxpkt		= 0;
+	cmd->base.speed		= SPEED_10000;
+	cmd->base.duplex	= DUPLEX_FULL;
+	cmd->base.port		= PORT_TP;
+	cmd->base.autoneg	= AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -95,12 +90,12 @@ static void veth_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops veth_ethtool_ops = {
-	.get_settings		= veth_get_settings,
 	.get_drvinfo		= veth_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_strings		= veth_get_strings,
 	.get_sset_count		= veth_get_sset_count,
 	.get_ethtool_stats	= veth_get_ethtool_stats,
+	.get_link_ksettings	= veth_get_link_ksettings,
 };
 
 static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -373,7 +368,8 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		ifmp = nla_data(nla_peer);
 		err = rtnl_nla_parse_ifla(peer_tb,
 					  nla_data(nla_peer) + sizeof(struct ifinfomsg),
-					  nla_len(nla_peer) - sizeof(struct ifinfomsg));
+					  nla_len(nla_peer) - sizeof(struct ifinfomsg),
+					  NULL);
 		if (err < 0)
 			return err;
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ea9890d61967..3d0bc484b3d7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -33,9 +33,10 @@
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
 
-static bool csum = true, gso = true;
+static bool csum = true, gso = true, napi_tx;
 module_param(csum, bool, 0444);
 module_param(gso, bool, 0444);
+module_param(napi_tx, bool, 0644);
 
 /* FIXME: MTU in config. */
 #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
@@ -86,6 +87,8 @@ struct send_queue {
 
 	/* Name of the send queue: output.$index */
 	char name[40];
+
+	struct napi_struct napi;
 };
 
 /* Internal representation of a receive virtqueue */
@@ -239,15 +242,39 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void virtqueue_napi_schedule(struct napi_struct *napi,
+				    struct virtqueue *vq)
+{
+	if (napi_schedule_prep(napi)) {
+		virtqueue_disable_cb(vq);
+		__napi_schedule(napi);
+	}
+}
+
+static void virtqueue_napi_complete(struct napi_struct *napi,
+				    struct virtqueue *vq, int processed)
+{
+	int opaque;
+
+	opaque = virtqueue_enable_cb_prepare(vq);
+	if (napi_complete_done(napi, processed) &&
+	    unlikely(virtqueue_poll(vq, opaque)))
+		virtqueue_napi_schedule(napi, vq);
+}
+
 static void skb_xmit_done(struct virtqueue *vq)
 {
 	struct virtnet_info *vi = vq->vdev->priv;
+	struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi;
 
 	/* Suppress further interrupts. */
 	virtqueue_disable_cb(vq);
 
-	/* We were probably waiting for more output buffers. */
-	netif_wake_subqueue(vi->dev, vq2txq(vq));
+	if (napi->weight)
+		virtqueue_napi_schedule(napi, vq);
+	else
+		/* We were probably waiting for more output buffers. */
+		netif_wake_subqueue(vi->dev, vq2txq(vq));
 }
 
 static unsigned int mergeable_ctx_to_buf_truesize(unsigned long mrg_ctx)
@@ -936,27 +963,44 @@ static void skb_recv_done(struct virtqueue *rvq)
 	struct virtnet_info *vi = rvq->vdev->priv;
 	struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
 
-	/* Schedule NAPI, Suppress further interrupts if successful. */
-	if (napi_schedule_prep(&rq->napi)) {
-		virtqueue_disable_cb(rvq);
-		__napi_schedule(&rq->napi);
-	}
+	virtqueue_napi_schedule(&rq->napi, rvq);
 }
 
-static void virtnet_napi_enable(struct receive_queue *rq)
+static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
 {
-	napi_enable(&rq->napi);
+	napi_enable(napi);
 
 	/* If all buffers were filled by other side before we napi_enabled, we
-	 * won't get another interrupt, so process any outstanding packets
-	 * now.  virtnet_poll wants re-enable the queue, so we disable here.
-	 * We synchronize against interrupts via NAPI_STATE_SCHED */
-	if (napi_schedule_prep(&rq->napi)) {
-		virtqueue_disable_cb(rq->vq);
-		local_bh_disable();
-		__napi_schedule(&rq->napi);
-		local_bh_enable();
+	 * won't get another interrupt, so process any outstanding packets now.
+	 * Call local_bh_enable after to trigger softIRQ processing.
+	 */
+	local_bh_disable();
+	virtqueue_napi_schedule(napi, vq);
+	local_bh_enable();
+}
+
+static void virtnet_napi_tx_enable(struct virtnet_info *vi,
+				   struct virtqueue *vq,
+				   struct napi_struct *napi)
+{
+	if (!napi->weight)
+		return;
+
+	/* Tx napi touches cachelines on the cpu handling tx interrupts. Only
+	 * enable the feature if this is likely affine with the transmit path.
+	 */
+	if (!vi->affinity_hint_set) {
+		napi->weight = 0;
+		return;
 	}
+
+	return virtnet_napi_enable(vq, napi);
+}
+
+static void virtnet_napi_tx_disable(struct napi_struct *napi)
+{
+	if (napi->weight)
+		napi_disable(napi);
 }
 
 static void refill_work(struct work_struct *work)
@@ -971,7 +1015,7 @@ static void refill_work(struct work_struct *work)
 
 		napi_disable(&rq->napi);
 		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
-		virtnet_napi_enable(rq);
+		virtnet_napi_enable(rq->vq, &rq->napi);
 
 		/* In theory, this can happen: if we don't get any buffers in
 		 * we will *never* try to fill again.
@@ -1007,25 +1051,68 @@ static int virtnet_receive(struct receive_queue *rq, int budget)
 	return received;
 }
 
+static void free_old_xmit_skbs(struct send_queue *sq)
+{
+	struct sk_buff *skb;
+	unsigned int len;
+	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
+	unsigned int packets = 0;
+	unsigned int bytes = 0;
+
+	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		pr_debug("Sent skb %p\n", skb);
+
+		bytes += skb->len;
+		packets++;
+
+		dev_kfree_skb_any(skb);
+	}
+
+	/* Avoid overhead when no packets have been processed
+	 * happens when called speculatively from start_xmit.
+	 */
+	if (!packets)
+		return;
+
+	u64_stats_update_begin(&stats->tx_syncp);
+	stats->tx_bytes += bytes;
+	stats->tx_packets += packets;
+	u64_stats_update_end(&stats->tx_syncp);
+}
+
+static void virtnet_poll_cleantx(struct receive_queue *rq)
+{
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	unsigned int index = vq2rxq(rq->vq);
+	struct send_queue *sq = &vi->sq[index];
+	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
+
+	if (!sq->napi.weight)
+		return;
+
+	if (__netif_tx_trylock(txq)) {
+		free_old_xmit_skbs(sq);
+		__netif_tx_unlock(txq);
+	}
+
+	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
+		netif_tx_wake_queue(txq);
+}
+
 static int virtnet_poll(struct napi_struct *napi, int budget)
 {
 	struct receive_queue *rq =
 		container_of(napi, struct receive_queue, napi);
-	unsigned int r, received;
+	unsigned int received;
+
+	virtnet_poll_cleantx(rq);
 
 	received = virtnet_receive(rq, budget);
 
 	/* Out of packets? */
-	if (received < budget) {
-		r = virtqueue_enable_cb_prepare(rq->vq);
-		if (napi_complete_done(napi, received)) {
-			if (unlikely(virtqueue_poll(rq->vq, r)) &&
-			    napi_schedule_prep(napi)) {
-				virtqueue_disable_cb(rq->vq);
-				__napi_schedule(napi);
-			}
-		}
-	}
+	if (received < budget)
+		virtqueue_napi_complete(napi, rq->vq, received);
 
 	return received;
 }
@@ -1040,40 +1127,29 @@ static int virtnet_open(struct net_device *dev)
 			/* Make sure we have some buffers: if oom use wq. */
 			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
 				schedule_delayed_work(&vi->refill, 0);
-		virtnet_napi_enable(&vi->rq[i]);
+		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
 	}
 
 	return 0;
 }
 
-static void free_old_xmit_skbs(struct send_queue *sq)
+static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 {
-	struct sk_buff *skb;
-	unsigned int len;
+	struct send_queue *sq = container_of(napi, struct send_queue, napi);
 	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
-	unsigned int packets = 0;
-	unsigned int bytes = 0;
-
-	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		pr_debug("Sent skb %p\n", skb);
+	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq));
 
-		bytes += skb->len;
-		packets++;
+	__netif_tx_lock(txq, raw_smp_processor_id());
+	free_old_xmit_skbs(sq);
+	__netif_tx_unlock(txq);
 
-		dev_kfree_skb_any(skb);
-	}
+	virtqueue_napi_complete(napi, sq->vq, 0);
 
-	/* Avoid overhead when no packets have been processed
-	 * happens when called speculatively from start_xmit.
-	 */
-	if (!packets)
-		return;
+	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
+		netif_tx_wake_queue(txq);
 
-	u64_stats_update_begin(&stats->tx_syncp);
-	stats->tx_bytes += bytes;
-	stats->tx_packets += packets;
-	u64_stats_update_end(&stats->tx_syncp);
+	return 0;
 }
 
 static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
@@ -1125,10 +1201,14 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int err;
 	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
 	bool kick = !skb->xmit_more;
+	bool use_napi = sq->napi.weight;
 
 	/* Free up any pending old buffers before queueing new ones. */
 	free_old_xmit_skbs(sq);
 
+	if (use_napi && kick)
+		virtqueue_enable_cb_delayed(sq->vq);
+
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
 
@@ -1147,8 +1227,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* Don't wait up for transmitted skbs to be freed. */
-	skb_orphan(skb);
-	nf_reset(skb);
+	if (!use_napi) {
+		skb_orphan(skb);
+		nf_reset(skb);
+	}
 
 	/* If running out of space, stop queue to avoid getting packets that we
 	 * are then unable to transmit.
@@ -1162,7 +1244,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
 		netif_stop_subqueue(dev, qnum);
-		if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
+		if (!use_napi &&
+		    unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
 			free_old_xmit_skbs(sq);
 			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
@@ -1366,8 +1449,10 @@ static int virtnet_close(struct net_device *dev)
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
-	for (i = 0; i < vi->max_queue_pairs; i++)
+	for (i = 0; i < vi->max_queue_pairs; i++) {
 		napi_disable(&vi->rq[i].napi);
+		virtnet_napi_tx_disable(&vi->sq[i].napi);
+	}
 
 	return 0;
 }
@@ -1636,47 +1721,57 @@ static void virtnet_get_channels(struct net_device *dev,
 }
 
 /* Check if the user is trying to change anything besides speed/duplex */
-static bool virtnet_validate_ethtool_cmd(const struct ethtool_cmd *cmd)
+static bool
+virtnet_validate_ethtool_cmd(const struct ethtool_link_ksettings *cmd)
 {
-	struct ethtool_cmd diff1 = *cmd;
-	struct ethtool_cmd diff2 = {};
+	struct ethtool_link_ksettings diff1 = *cmd;
+	struct ethtool_link_ksettings diff2 = {};
 
 	/* cmd is always set so we need to clear it, validate the port type
 	 * and also without autonegotiation we can ignore advertising
 	 */
-	ethtool_cmd_speed_set(&diff1, 0);
-	diff2.port = PORT_OTHER;
-	diff1.advertising = 0;
-	diff1.duplex = 0;
-	diff1.cmd = 0;
+	diff1.base.speed = 0;
+	diff2.base.port = PORT_OTHER;
+	ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
+	diff1.base.duplex = 0;
+	diff1.base.cmd = 0;
+	diff1.base.link_mode_masks_nwords = 0;
 
-	return !memcmp(&diff1, &diff2, sizeof(diff1));
+	return !memcmp(&diff1.base, &diff2.base, sizeof(diff1.base)) &&
+		bitmap_empty(diff1.link_modes.supported,
+			     __ETHTOOL_LINK_MODE_MASK_NBITS) &&
+		bitmap_empty(diff1.link_modes.advertising,
+			     __ETHTOOL_LINK_MODE_MASK_NBITS) &&
+		bitmap_empty(diff1.link_modes.lp_advertising,
+			     __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static int virtnet_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int virtnet_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	u32 speed;
 
-	speed = ethtool_cmd_speed(cmd);
+	speed = cmd->base.speed;
 	/* don't allow custom speed and duplex */
 	if (!ethtool_validate_speed(speed) ||
-	    !ethtool_validate_duplex(cmd->duplex) ||
+	    !ethtool_validate_duplex(cmd->base.duplex) ||
 	    !virtnet_validate_ethtool_cmd(cmd))
 		return -EINVAL;
 	vi->speed = speed;
-	vi->duplex = cmd->duplex;
+	vi->duplex = cmd->base.duplex;
 
 	return 0;
 }
 
-static int virtnet_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int virtnet_get_link_ksettings(struct net_device *dev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	ethtool_cmd_speed_set(cmd, vi->speed);
-	cmd->duplex = vi->duplex;
-	cmd->port = PORT_OTHER;
+	cmd->base.speed = vi->speed;
+	cmd->base.duplex = vi->duplex;
+	cmd->base.port = PORT_OTHER;
 
 	return 0;
 }
@@ -1696,8 +1791,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 	.set_channels = virtnet_set_channels,
 	.get_channels = virtnet_get_channels,
 	.get_ts_info = ethtool_op_get_ts_info,
-	.get_settings = virtnet_get_settings,
-	.set_settings = virtnet_set_settings,
+	.get_link_ksettings = virtnet_get_link_ksettings,
+	.set_link_ksettings = virtnet_set_link_ksettings,
 };
 
 static void virtnet_freeze_down(struct virtio_device *vdev)
@@ -1712,8 +1807,10 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	cancel_delayed_work_sync(&vi->refill);
 
 	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++)
+		for (i = 0; i < vi->max_queue_pairs; i++) {
 			napi_disable(&vi->rq[i].napi);
+			virtnet_napi_tx_disable(&vi->sq[i].napi);
+		}
 	}
 }
 
@@ -1736,8 +1833,11 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
 				schedule_delayed_work(&vi->refill, 0);
 
-		for (i = 0; i < vi->max_queue_pairs; i++)
-			virtnet_napi_enable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
 	}
 
 	netif_device_attach(vi->dev);
@@ -1778,7 +1878,8 @@ err:
 	return ret;
 }
 
-static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
+static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+			   struct netlink_ext_ack *extack)
 {
 	unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -1790,16 +1891,17 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
 	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
 	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO)) {
-		netdev_warn(dev, "can't set XDP while host is implementing LRO, disable LRO first\n");
+		NL_SET_ERR_MSG(extack, "can't set XDP while host is implementing LRO, disable LRO first");
 		return -EOPNOTSUPP;
 	}
 
 	if (vi->mergeable_rx_bufs && !vi->any_header_sg) {
-		netdev_warn(dev, "XDP expects header/data in single page, any_header_sg required\n");
+		NL_SET_ERR_MSG(extack, "XDP expects header/data in single page, any_header_sg required");
 		return -EINVAL;
 	}
 
 	if (dev->mtu > max_sz) {
+		NL_SET_ERR_MSG(extack, "MTU too large to enable XDP");
 		netdev_warn(dev, "XDP requires MTU less than %lu\n", max_sz);
 		return -EINVAL;
 	}
@@ -1810,6 +1912,7 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 
 	/* XDP requires extra queues for XDP_TX */
 	if (curr_qp + xdp_qp > vi->max_queue_pairs) {
+		NL_SET_ERR_MSG(extack, "Too few free TX rings available");
 		netdev_warn(dev, "request %i queues but max is %i\n",
 			    curr_qp + xdp_qp, vi->max_queue_pairs);
 		return -ENOMEM;
@@ -1871,7 +1974,7 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
-		return virtnet_xdp_set(dev, xdp->prog);
+		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_attached = virtnet_xdp_query(dev);
 		return 0;
@@ -1942,6 +2045,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		napi_hash_del(&vi->rq[i].napi);
 		netif_napi_del(&vi->rq[i].napi);
+		netif_napi_del(&vi->sq[i].napi);
 	}
 
 	/* We called napi_hash_del() before netif_napi_del(),
@@ -2127,6 +2231,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 		vi->rq[i].pages = NULL;
 		netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
 			       napi_weight);
+		netif_tx_napi_add(vi->dev, &vi->sq[i].napi, virtnet_poll_tx,
+				  napi_tx ? napi_weight : 0);
 
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
@@ -2230,14 +2336,8 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
 #define MIN_MTU ETH_MIN_MTU
 #define MAX_MTU ETH_MAX_MTU
 
-static int virtnet_probe(struct virtio_device *vdev)
+static int virtnet_validate(struct virtio_device *vdev)
 {
-	int i, err;
-	struct net_device *dev;
-	struct virtnet_info *vi;
-	u16 max_queue_pairs;
-	int mtu;
-
 	if (!vdev->config->get) {
 		dev_err(&vdev->dev, "%s failure: config access disabled\n",
 			__func__);
@@ -2247,6 +2347,25 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (!virtnet_validate_features(vdev))
 		return -EINVAL;
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
+		int mtu = virtio_cread16(vdev,
+					 offsetof(struct virtio_net_config,
+						  mtu));
+		if (mtu < MIN_MTU)
+			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
+	}
+
+	return 0;
+}
+
+static int virtnet_probe(struct virtio_device *vdev)
+{
+	int i, err;
+	struct net_device *dev;
+	struct virtnet_info *vi;
+	u16 max_queue_pairs;
+	int mtu;
+
 	/* Find if host supports multiqueue virtio_net device */
 	err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ,
 				   struct virtio_net_config,
@@ -2362,11 +2481,20 @@ static int virtnet_probe(struct virtio_device *vdev)
 				     offsetof(struct virtio_net_config,
 					      mtu));
 		if (mtu < dev->min_mtu) {
-			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
-		} else {
-			dev->mtu = mtu;
-			dev->max_mtu = mtu;
+			/* Should never trigger: MTU was previously validated
+			 * in virtnet_validate.
+			 */
+			dev_err(&vdev->dev, "device MTU appears to have changed "
+				"it is now %d < %d", mtu, dev->min_mtu);
+			goto free_stats;
 		}
+
+		dev->mtu = mtu;
+		dev->max_mtu = mtu;
+
+		/* TODO: size buffers correctly in this case. */
+		if (dev->mtu > ETH_DATA_LEN)
+			vi->big_packets = true;
 	}
 
 	if (vi->any_header_sg)
@@ -2544,6 +2672,7 @@ static struct virtio_driver virtio_net_driver = {
 	.driver.name =	KBUILD_MODNAME,
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,
+	.validate =	virtnet_validate,
 	.probe =	virtnet_probe,
 	.remove =	virtnet_remove,
 	.config_changed = virtnet_config_changed,
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index f88ffafebfbf..2ff27314e047 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -471,22 +471,25 @@ vmxnet3_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 
 
 static int
-vmxnet3_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+vmxnet3_get_link_ksettings(struct net_device *netdev,
+			   struct ethtool_link_ksettings *ecmd)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
-	ecmd->supported = SUPPORTED_10000baseT_Full | SUPPORTED_1000baseT_Full |
-			  SUPPORTED_TP;
-	ecmd->advertising = ADVERTISED_TP;
-	ecmd->port = PORT_TP;
-	ecmd->transceiver = XCVR_INTERNAL;
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, 10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, TP);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising, TP);
+	ecmd->base.port = PORT_TP;
 
 	if (adapter->link_speed) {
-		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
-		ecmd->duplex = DUPLEX_FULL;
+		ecmd->base.speed = adapter->link_speed;
+		ecmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		ecmd->base.speed = SPEED_UNKNOWN;
+		ecmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 	return 0;
 }
@@ -880,7 +883,6 @@ done:
 }
 
 static const struct ethtool_ops vmxnet3_ethtool_ops = {
-	.get_settings      = vmxnet3_get_settings,
 	.get_drvinfo       = vmxnet3_get_drvinfo,
 	.get_regs_len      = vmxnet3_get_regs_len,
 	.get_regs          = vmxnet3_get_regs,
@@ -900,6 +902,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_rxfh          = vmxnet3_get_rss,
 	.set_rxfh          = vmxnet3_set_rss,
 #endif
+	.get_link_ksettings = vmxnet3_get_link_ksettings,
 };
 
 void vmxnet3_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 22379da63400..ceda5861da78 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -104,6 +104,23 @@ static void vrf_get_stats64(struct net_device *dev,
 	}
 }
 
+/* by default VRF devices do not have a qdisc and are expected
+ * to be created with only a single queue.
+ */
+static bool qdisc_tx_is_default(const struct net_device *dev)
+{
+	struct netdev_queue *txq;
+	struct Qdisc *qdisc;
+
+	if (dev->num_tx_queues > 1)
+		return false;
+
+	txq = netdev_get_tx_queue(dev, 0);
+	qdisc = rcu_access_pointer(txq->qdisc);
+
+	return !qdisc->enqueue;
+}
+
 /* Local traffic destined to local address. Reinsert the packet to rx
  * path, similar to loopback handling.
  */
@@ -340,6 +357,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
@@ -347,7 +365,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		u64_stats_update_begin(&dstats->syncp);
 		dstats->tx_pkts++;
-		dstats->tx_bytes += skb->len;
+		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
 		this_cpu_inc(dev->dstats->tx_drps);
@@ -356,6 +374,29 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static int vrf_finish_direct(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	struct net_device *vrf_dev = skb->dev;
+
+	if (!list_empty(&vrf_dev->ptype_all) &&
+	    likely(skb_headroom(skb) >= ETH_HLEN)) {
+		struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN);
+
+		ether_addr_copy(eth->h_source, vrf_dev->dev_addr);
+		eth_zero_addr(eth->h_dest);
+		eth->h_proto = skb->protocol;
+
+		rcu_read_lock_bh();
+		dev_queue_xmit_nit(skb, vrf_dev);
+		rcu_read_unlock_bh();
+
+		skb_pull(skb, ETH_HLEN);
+	}
+
+	return 1;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 /* modelled after ip6_finish_output2 */
 static int vrf_finish_output6(struct net *net, struct sock *sk,
@@ -404,18 +445,13 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
  * packet to go through device based features such as qdisc, netfilter
  * hooks and packet sockets with skb->dev set to vrf device.
  */
-static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
-				   struct sock *sk,
-				   struct sk_buff *skb)
+static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev,
+					    struct sk_buff *skb)
 {
 	struct net_vrf *vrf = netdev_priv(vrf_dev);
 	struct dst_entry *dst = NULL;
 	struct rt6_info *rt6;
 
-	/* don't divert link scope packets */
-	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
-		return skb;
-
 	rcu_read_lock();
 
 	rt6 = rcu_dereference(vrf->rt6);
@@ -437,6 +473,55 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	return skb;
 }
 
+static int vrf_output6_direct(struct net *net, struct sock *sk,
+			      struct sk_buff *skb)
+{
+	skb->protocol = htons(ETH_P_IPV6);
+
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+			    net, sk, skb, NULL, skb->dev,
+			    vrf_finish_direct,
+			    !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
+					  struct sock *sk,
+					  struct sk_buff *skb)
+{
+	struct net *net = dev_net(vrf_dev);
+	int err;
+
+	skb->dev = vrf_dev;
+
+	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
+		      skb, NULL, vrf_dev, vrf_output6_direct);
+
+	if (likely(err == 1))
+		err = vrf_output6_direct(net, sk, skb);
+
+	/* reset skb device */
+	if (likely(err == 1))
+		nf_reset(skb);
+	else
+		skb = NULL;
+
+	return skb;
+}
+
+static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
+				   struct sock *sk,
+				   struct sk_buff *skb)
+{
+	/* don't divert link scope packets */
+	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
+		return skb;
+
+	if (qdisc_tx_is_default(vrf_dev))
+		return vrf_ip6_out_direct(vrf_dev, sk, skb);
+
+	return vrf_ip6_out_redirect(vrf_dev, skb);
+}
+
 /* holding rtnl */
 static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
@@ -461,8 +546,10 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 	}
 
 	if (rt6_local) {
-		if (rt6_local->rt6i_idev)
+		if (rt6_local->rt6i_idev) {
 			in6_dev_put(rt6_local->rt6i_idev);
+			rt6_local->rt6i_idev = NULL;
+		}
 
 		dst = &rt6_local->dst;
 		dev_put(dst->dev);
@@ -606,18 +693,13 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
  * packet to go through device based features such as qdisc, netfilter
  * hooks and packet sockets with skb->dev set to vrf device.
  */
-static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
-				  struct sock *sk,
-				  struct sk_buff *skb)
+static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev,
+					   struct sk_buff *skb)
 {
 	struct net_vrf *vrf = netdev_priv(vrf_dev);
 	struct dst_entry *dst = NULL;
 	struct rtable *rth;
 
-	/* don't divert multicast */
-	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
-		return skb;
-
 	rcu_read_lock();
 
 	rth = rcu_dereference(vrf->rth);
@@ -639,6 +721,55 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	return skb;
 }
 
+static int vrf_output_direct(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	skb->protocol = htons(ETH_P_IP);
+
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+			    net, sk, skb, NULL, skb->dev,
+			    vrf_finish_direct,
+			    !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
+					 struct sock *sk,
+					 struct sk_buff *skb)
+{
+	struct net *net = dev_net(vrf_dev);
+	int err;
+
+	skb->dev = vrf_dev;
+
+	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
+		      skb, NULL, vrf_dev, vrf_output_direct);
+
+	if (likely(err == 1))
+		err = vrf_output_direct(net, sk, skb);
+
+	/* reset skb device */
+	if (likely(err == 1))
+		nf_reset(skb);
+	else
+		skb = NULL;
+
+	return skb;
+}
+
+static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
+				  struct sock *sk,
+				  struct sk_buff *skb)
+{
+	/* don't divert multicast */
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+		return skb;
+
+	if (qdisc_tx_is_default(vrf_dev))
+		return vrf_ip_out_direct(vrf_dev, sk, skb);
+
+	return vrf_ip_out_redirect(vrf_dev, skb);
+}
+
 /* called with rcu lock held */
 static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev,
 				  struct sock *sk,
@@ -746,14 +877,24 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 {
 	int ret;
 
+	/* do not allow loopback device to be enslaved to a VRF.
+	 * The vrf device acts as the loopback for the vrf.
+	 */
+	if (port_dev == dev_net(dev)->loopback_dev)
+		return -EOPNOTSUPP;
+
+	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
 	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
 	if (ret < 0)
-		return ret;
+		goto err;
 
-	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
 	cycle_netdev(port_dev);
 
 	return 0;
+
+err:
+	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
+	return ret;
 }
 
 static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
@@ -975,9 +1116,11 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
-		skb_push(skb, skb->mac_len);
-		dev_queue_xmit_nit(skb, vrf_dev);
-		skb_pull(skb, skb->mac_len);
+		if (!list_empty(&vrf_dev->ptype_all)) {
+			skb_push(skb, skb->mac_len);
+			dev_queue_xmit_nit(skb, vrf_dev);
+			skb_pull(skb, skb->mac_len);
+		}
 
 		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
 	}
@@ -1018,9 +1161,11 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 
 	vrf_rx_stats(vrf_dev, skb->len);
 
-	skb_push(skb, skb->mac_len);
-	dev_queue_xmit_nit(skb, vrf_dev);
-	skb_pull(skb, skb->mac_len);
+	if (!list_empty(&vrf_dev->ptype_all)) {
+		skb_push(skb, skb->mac_len);
+		dev_queue_xmit_nit(skb, vrf_dev);
+		skb_pull(skb, skb->mac_len);
+	}
 
 	skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev);
 out:
@@ -1125,7 +1270,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 		goto nla_put_failure;
 
 	/* rule only needs to appear once */
-	nlh->nlmsg_flags &= NLM_F_EXCL;
+	nlh->nlmsg_flags |= NLM_F_EXCL;
 
 	frh = nlmsg_data(nlh);
 	memset(frh, 0, sizeof(*frh));
@@ -1143,11 +1288,11 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
 	skb->sk = dev_net(dev)->rtnl;
 	if (add_it) {
-		err = fib_nl_newrule(skb, nlh);
+		err = fib_nl_newrule(skb, nlh, NULL);
 		if (err == -EEXIST)
 			err = 0;
 	} else {
-		err = fib_nl_delrule(skb, nlh);
+		err = fib_nl_delrule(skb, nlh, NULL);
 		if (err == -ENOENT)
 			err = 0;
 	}
diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c
new file mode 100644
index 000000000000..7f0136f2dd9d
--- /dev/null
+++ b/drivers/net/vsockmon.c
@@ -0,0 +1,170 @@
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/if_arp.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
+#include <net/af_vsock.h>
+#include <uapi/linux/vsockmon.h>
+#include <linux/virtio_vsock.h>
+
+/* Virtio transport max packet size plus header */
+#define DEFAULT_MTU (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + \
+		     sizeof(struct af_vsockmon_hdr))
+
+struct pcpu_lstats {
+	u64 rx_packets;
+	u64 rx_bytes;
+	struct u64_stats_sync syncp;
+};
+
+static int vsockmon_dev_init(struct net_device *dev)
+{
+	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
+	if (!dev->lstats)
+		return -ENOMEM;
+	return 0;
+}
+
+static void vsockmon_dev_uninit(struct net_device *dev)
+{
+	free_percpu(dev->lstats);
+}
+
+struct vsockmon {
+	struct vsock_tap vt;
+};
+
+static int vsockmon_open(struct net_device *dev)
+{
+	struct vsockmon *vsockmon = netdev_priv(dev);
+
+	vsockmon->vt.dev = dev;
+	vsockmon->vt.module = THIS_MODULE;
+	return vsock_add_tap(&vsockmon->vt);
+}
+
+static int vsockmon_close(struct net_device *dev)
+{
+	struct vsockmon *vsockmon = netdev_priv(dev);
+
+	return vsock_remove_tap(&vsockmon->vt);
+}
+
+static netdev_tx_t vsockmon_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	int len = skb->len;
+	struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats);
+
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_bytes += len;
+	stats->rx_packets++;
+	u64_stats_update_end(&stats->syncp);
+
+	dev_kfree_skb(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static void
+vsockmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	int i;
+	u64 bytes = 0, packets = 0;
+
+	for_each_possible_cpu(i) {
+		const struct pcpu_lstats *vstats;
+		u64 tbytes, tpackets;
+		unsigned int start;
+
+		vstats = per_cpu_ptr(dev->lstats, i);
+
+		do {
+			start = u64_stats_fetch_begin_irq(&vstats->syncp);
+			tbytes = vstats->rx_bytes;
+			tpackets = vstats->rx_packets;
+		} while (u64_stats_fetch_retry_irq(&vstats->syncp, start));
+
+		packets += tpackets;
+		bytes += tbytes;
+	}
+
+	stats->rx_packets = packets;
+	stats->tx_packets = 0;
+
+	stats->rx_bytes = bytes;
+	stats->tx_bytes = 0;
+}
+
+static int vsockmon_is_valid_mtu(int new_mtu)
+{
+	return new_mtu >= (int)sizeof(struct af_vsockmon_hdr);
+}
+
+static int vsockmon_change_mtu(struct net_device *dev, int new_mtu)
+{
+	if (!vsockmon_is_valid_mtu(new_mtu))
+		return -EINVAL;
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static const struct net_device_ops vsockmon_ops = {
+	.ndo_init = vsockmon_dev_init,
+	.ndo_uninit = vsockmon_dev_uninit,
+	.ndo_open = vsockmon_open,
+	.ndo_stop = vsockmon_close,
+	.ndo_start_xmit = vsockmon_xmit,
+	.ndo_get_stats64 = vsockmon_get_stats64,
+	.ndo_change_mtu = vsockmon_change_mtu,
+};
+
+static u32 always_on(struct net_device *dev)
+{
+	return 1;
+}
+
+static const struct ethtool_ops vsockmon_ethtool_ops = {
+	.get_link = always_on,
+};
+
+static void vsockmon_setup(struct net_device *dev)
+{
+	dev->type = ARPHRD_VSOCKMON;
+	dev->priv_flags |= IFF_NO_QUEUE;
+
+	dev->netdev_ops	= &vsockmon_ops;
+	dev->ethtool_ops = &vsockmon_ethtool_ops;
+	dev->destructor	= free_netdev;
+
+	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST |
+			NETIF_F_HIGHDMA | NETIF_F_LLTX;
+
+	dev->flags = IFF_NOARP;
+
+	dev->mtu = DEFAULT_MTU;
+}
+
+static struct rtnl_link_ops vsockmon_link_ops __read_mostly = {
+	.kind			= "vsockmon",
+	.priv_size		= sizeof(struct vsockmon),
+	.setup			= vsockmon_setup,
+};
+
+static __init int vsockmon_register(void)
+{
+	return rtnl_link_register(&vsockmon_link_ops);
+}
+
+static __exit void vsockmon_unregister(void)
+{
+	rtnl_link_unregister(&vsockmon_link_ops);
+}
+
+module_init(vsockmon_register);
+module_exit(vsockmon_unregister);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Gerard Garcia <ggarcia@deic.uab.cat>");
+MODULE_DESCRIPTION("Vsock monitoring device. Based on nlmon device.");
+MODULE_ALIAS_RTNL_LINK("vsockmon");
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e375560cc74e..328b4712683c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -276,9 +276,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	send_eth = send_ip = true;
 
 	if (type == RTM_GETNEIGH) {
-		ndm->ndm_family	= AF_INET;
 		send_ip = !vxlan_addr_any(&rdst->remote_ip);
 		send_eth = !is_zero_ether_addr(fdb->eth_addr);
+		ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET;
 	} else
 		ndm->ndm_family	= AF_BRIDGE;
 	ndm->ndm_state = fdb->state;
@@ -1515,7 +1515,7 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	int ns_olen;
 	int i, len;
 
-	if (dev == NULL)
+	if (dev == NULL || !pskb_may_pull(request, request->len))
 		return NULL;
 
 	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
@@ -1530,10 +1530,11 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	skb_push(reply, sizeof(struct ethhdr));
 	skb_reset_mac_header(reply);
 
-	ns = (struct nd_msg *)skb_transport_header(request);
+	ns = (struct nd_msg *)(ipv6_hdr(request) + 1);
 
 	daddr = eth_hdr(request)->h_source;
-	ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+	ns_olen = request->len - skb_network_offset(request) -
+		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
@@ -1604,10 +1605,13 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	if (!in6_dev)
 		goto out;
 
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
+		goto out;
+
 	iphdr = ipv6_hdr(skb);
 	daddr = &iphdr->daddr;
 
-	msg = (struct nd_msg *)skb_transport_header(skb);
+	msg = (struct nd_msg *)(iphdr + 1);
 	if (msg->icmph.icmp6_code != 0 ||
 	    msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
 		goto out;
@@ -2242,16 +2246,13 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (ntohs(eth->h_proto) == ETH_P_ARP)
 			return arp_reduce(dev, skb, vni);
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
-			 pskb_may_pull(skb, sizeof(struct ipv6hdr)
-				       + sizeof(struct nd_msg)) &&
-			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
-				struct nd_msg *msg;
-
-				msg = (struct nd_msg *)skb_transport_header(skb);
-				if (msg->icmph.icmp6_code == 0 &&
-				    msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
-					return neigh_reduce(dev, skb, vni);
+		else if (ntohs(eth->h_proto) == ETH_P_IPV6) {
+			struct ipv6hdr *hdr, _hdr;
+			if ((hdr = skb_header_pointer(skb,
+						      skb_network_offset(skb),
+						      sizeof(_hdr), &_hdr)) &&
+			    hdr->nexthdr == IPPROTO_ICMPV6)
+				return neigh_reduce(dev, skb, vni);
 		}
 #endif
 	}
@@ -2322,6 +2323,9 @@ static void vxlan_cleanup(unsigned long arg)
 			if (f->state & (NUD_PERMANENT | NUD_NOARP))
 				continue;
 
+			if (f->flags & NTF_EXT_LEARNED)
+				continue;
+
 			timeout = f->used + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
@@ -2754,8 +2758,6 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 
 	sock = vxlan_create_sock(net, ipv6, port, flags);
 	if (IS_ERR(sock)) {
-		pr_info("Cannot bind port %d, err=%ld\n", ntohs(port),
-			PTR_ERR(sock));
 		kfree(vs);
 		return ERR_CAST(sock);
 	}
@@ -2818,17 +2820,21 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 
 static int vxlan_sock_add(struct vxlan_dev *vxlan)
 {
-	bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
 	bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA;
+	bool ipv6 = vxlan->flags & VXLAN_F_IPV6 || metadata;
+	bool ipv4 = !ipv6 || metadata;
 	int ret = 0;
 
 	RCU_INIT_POINTER(vxlan->vn4_sock, NULL);
 #if IS_ENABLED(CONFIG_IPV6)
 	RCU_INIT_POINTER(vxlan->vn6_sock, NULL);
-	if (ipv6 || metadata)
+	if (ipv6) {
 		ret = __vxlan_sock_add(vxlan, true);
+		if (ret < 0 && ret != -EAFNOSUPPORT)
+			ipv4 = false;
+	}
 #endif
-	if (!ret && (!ipv6 || metadata))
+	if (ipv4)
 		ret = __vxlan_sock_add(vxlan, false);
 	if (ret < 0)
 		vxlan_sock_release(vxlan);
@@ -2923,6 +2929,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 	}
 
+	if (lowerdev) {
+		dev->gso_max_size = lowerdev->gso_max_size;
+		dev->gso_max_segs = lowerdev->gso_max_segs;
+	}
+
 	if (conf->mtu) {
 		int max_mtu = ETH_MAX_MTU;
 
@@ -2976,6 +2987,44 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	return 0;
 }
 
+static int __vxlan_dev_create(struct net *net, struct net_device *dev,
+			      struct vxlan_config *conf)
+{
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
+	err = vxlan_dev_configure(net, dev, conf, false);
+	if (err)
+		return err;
+
+	dev->ethtool_ops = &vxlan_ethtool_ops;
+
+	/* create an fdb entry for a valid default destination */
+	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+		err = vxlan_fdb_create(vxlan, all_zeros_mac,
+				       &vxlan->default_dst.remote_ip,
+				       NUD_REACHABLE | NUD_PERMANENT,
+				       NLM_F_EXCL | NLM_F_CREATE,
+				       vxlan->cfg.dst_port,
+				       vxlan->default_dst.remote_vni,
+				       vxlan->default_dst.remote_vni,
+				       vxlan->default_dst.remote_ifindex,
+				       NTF_SELF);
+		if (err)
+			return err;
+	}
+
+	err = register_netdevice(dev);
+	if (err) {
+		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
+		return err;
+	}
+
+	list_add(&vxlan->next, &vn->vxlan_list);
+	return 0;
+}
+
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 			 struct net_device *dev, struct vxlan_config *conf,
 			 bool changelink)
@@ -3172,8 +3221,6 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
-	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
-	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_config conf;
 	int err;
 
@@ -3181,36 +3228,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (err)
 		return err;
 
-	err = vxlan_dev_configure(src_net, dev, &conf, false);
-	if (err)
-		return err;
-
-	dev->ethtool_ops = &vxlan_ethtool_ops;
-
-	/* create an fdb entry for a valid default destination */
-	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
-				       &vxlan->default_dst.remote_ip,
-				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
-				       vxlan->cfg.dst_port,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
-		if (err)
-			return err;
-	}
-
-	err = register_netdevice(dev);
-	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
-	}
-
-	list_add(&vxlan->next, &vn->vxlan_list);
-
-	return 0;
+	return __vxlan_dev_create(src_net, dev, &conf);
 }
 
 static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
@@ -3440,7 +3458,7 @@ struct net_device *vxlan_dev_create(struct net *net, const char *name,
 	if (IS_ERR(dev))
 		return dev;
 
-	err = vxlan_dev_configure(net, dev, conf, false);
+	err = __vxlan_dev_create(net, dev, conf);
 	if (err < 0) {
 		free_netdev(dev);
 		return ERR_PTR(err);
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index a5045b5279d7..6742ae605660 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -381,8 +381,8 @@ static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev)
 	/* set bd status and length */
 	bd_status = (bd_status & T_W_S) | T_R_S | T_I_S | T_L_S | T_TC_S;
 
-	iowrite16be(bd_status, &bd->status);
 	iowrite16be(skb->len, &bd->length);
+	iowrite16be(bd_status, &bd->status);
 
 	/* Move to next BD in the ring */
 	if (!(bd_status & T_W_S))
@@ -457,7 +457,7 @@ static int hdlc_rx_done(struct ucc_hdlc_private *priv, int rx_work_limit)
 	struct sk_buff *skb;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	struct qe_bd *bd;
-	u32 bd_status;
+	u16 bd_status;
 	u16 length, howmany = 0;
 	u8 *bdbuffer;
 	int i;
diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c
index e1dd1ec18d64..b9b934b7713c 100644
--- a/drivers/net/wan/pc300too.c
+++ b/drivers/net/wan/pc300too.c
@@ -346,6 +346,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev,
 	    card->rambase == NULL) {
 		pr_err("ioremap() failed\n");
 		pc300_pci_remove_one(pdev);
+		return -ENOMEM;
 	}
 
 	/* PLX PCI 9050 workaround for local configuration register read bug */
diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c
index e7f5910a6519..f8eb66ef2944 100644
--- a/drivers/net/wimax/i2400m/usb.c
+++ b/drivers/net/wimax/i2400m/usb.c
@@ -467,6 +467,9 @@ int i2400mu_probe(struct usb_interface *iface,
 	struct i2400mu *i2400mu;
 	struct usb_device *usb_dev = interface_to_usbdev(iface);
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 4)
+		return -ENODEV;
+
 	if (usb_dev->speed != USB_SPEED_HIGH)
 		dev_err(dev, "device not connected as high speed\n");
 
diff --git a/drivers/net/wireless/admtek/adm8211.c b/drivers/net/wireless/admtek/adm8211.c
index 098c814e22c8..ed626f568b58 100644
--- a/drivers/net/wireless/admtek/adm8211.c
+++ b/drivers/net/wireless/admtek/adm8211.c
@@ -1917,6 +1917,8 @@ static int adm8211_probe(struct pci_dev *pdev,
 
 	dev->wiphy->bands[NL80211_BAND_2GHZ] = &priv->band;
 
+	wiphy_ext_feature_set(dev->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	err = ieee80211_register_hw(dev);
 	if (err) {
 		printk(KERN_ERR "%s (adm8211): Cannot register device\n",
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 7a60d2e652da..f2f4ccfdf8da 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1689,6 +1689,8 @@ static int ar5523_probe(struct usb_interface *intf,
 	if (error)
 		goto out_cancel_rx_cmd;
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	usb_set_intfdata(intf, hw);
 
 	error = ieee80211_register_hw(hw);
diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index 45226dbee5ce..da770af83036 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -640,6 +640,7 @@ static int ath10k_ahb_hif_start(struct ath10k *ar)
 {
 	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot ahb hif start\n");
 
+	napi_enable(&ar->napi);
 	ath10k_ce_enable_interrupts(ar);
 	ath10k_pci_enable_legacy_irq(ar);
 
@@ -692,7 +693,6 @@ static int ath10k_ahb_hif_power_up(struct ath10k *ar)
 		ath10k_err(ar, "could not wake up target CPU: %d\n", ret);
 		goto err_ce_deinit;
 	}
-	napi_enable(&ar->napi);
 
 	return 0;
 
diff --git a/drivers/net/wireless/ath/ath10k/bmi.c b/drivers/net/wireless/ath/ath10k/bmi.c
index 2872d347ea78..abeee200310b 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.c
+++ b/drivers/net/wireless/ath/ath10k/bmi.c
@@ -19,12 +19,21 @@
 #include "hif.h"
 #include "debug.h"
 #include "htc.h"
+#include "hw.h"
 
 void ath10k_bmi_start(struct ath10k *ar)
 {
+	int ret;
+
 	ath10k_dbg(ar, ATH10K_DBG_BMI, "bmi start\n");
 
 	ar->bmi.done_sent = false;
+
+	/* Enable hardware clock to speed up firmware download */
+	if (ar->hw_params.hw_ops->enable_pll_clk) {
+		ret = ar->hw_params.hw_ops->enable_pll_clk(ar);
+		ath10k_dbg(ar, ATH10K_DBG_BMI, "bmi enable pll ret %d\n", ret);
+	}
 }
 
 int ath10k_bmi_done(struct ath10k *ar)
@@ -129,6 +138,69 @@ int ath10k_bmi_read_memory(struct ath10k *ar,
 	return 0;
 }
 
+int ath10k_bmi_write_soc_reg(struct ath10k *ar, u32 address, u32 reg_val)
+{
+	struct bmi_cmd cmd;
+	u32 cmdlen = sizeof(cmd.id) + sizeof(cmd.write_soc_reg);
+	int ret;
+
+	ath10k_dbg(ar, ATH10K_DBG_BMI,
+		   "bmi write soc register 0x%08x val 0x%08x\n",
+		   address, reg_val);
+
+	if (ar->bmi.done_sent) {
+		ath10k_warn(ar, "bmi write soc register command in progress\n");
+		return -EBUSY;
+	}
+
+	cmd.id = __cpu_to_le32(BMI_WRITE_SOC_REGISTER);
+	cmd.write_soc_reg.addr = __cpu_to_le32(address);
+	cmd.write_soc_reg.value = __cpu_to_le32(reg_val);
+
+	ret = ath10k_hif_exchange_bmi_msg(ar, &cmd, cmdlen, NULL, NULL);
+	if (ret) {
+		ath10k_warn(ar, "Unable to write soc register to device: %d\n",
+			    ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath10k_bmi_read_soc_reg(struct ath10k *ar, u32 address, u32 *reg_val)
+{
+	struct bmi_cmd cmd;
+	union bmi_resp resp;
+	u32 cmdlen = sizeof(cmd.id) + sizeof(cmd.read_soc_reg);
+	u32 resplen = sizeof(resp.read_soc_reg);
+	int ret;
+
+	ath10k_dbg(ar, ATH10K_DBG_BMI, "bmi read soc register 0x%08x\n",
+		   address);
+
+	if (ar->bmi.done_sent) {
+		ath10k_warn(ar, "bmi read soc register command in progress\n");
+		return -EBUSY;
+	}
+
+	cmd.id = __cpu_to_le32(BMI_READ_SOC_REGISTER);
+	cmd.read_soc_reg.addr = __cpu_to_le32(address);
+
+	ret = ath10k_hif_exchange_bmi_msg(ar, &cmd, cmdlen, &resp, &resplen);
+	if (ret) {
+		ath10k_warn(ar, "Unable to read soc register from device: %d\n",
+			    ret);
+		return ret;
+	}
+
+	*reg_val = __le32_to_cpu(resp.read_soc_reg.value);
+
+	ath10k_dbg(ar, ATH10K_DBG_BMI, "bmi read soc register value 0x%08x\n",
+		   *reg_val);
+
+	return 0;
+}
+
 int ath10k_bmi_write_memory(struct ath10k *ar,
 			    u32 address, const void *buffer, u32 length)
 {
diff --git a/drivers/net/wireless/ath/ath10k/bmi.h b/drivers/net/wireless/ath/ath10k/bmi.h
index 7d3231acfb24..cc45b63ade15 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.h
+++ b/drivers/net/wireless/ath/ath10k/bmi.h
@@ -176,7 +176,8 @@ union bmi_resp {
 	} rompatch_uninstall;
 	struct {
 		/* 0 = nothing executed
-		 * otherwise = NVRAM segment return value */
+		 * otherwise = NVRAM segment return value
+		 */
 		__le32 result;
 	} nvram_process;
 	u8 payload[BMI_MAX_CMDBUF_SIZE];
@@ -232,4 +233,6 @@ int ath10k_bmi_lz_stream_start(struct ath10k *ar, u32 address);
 int ath10k_bmi_lz_data(struct ath10k *ar, const void *buffer, u32 length);
 int ath10k_bmi_fast_download(struct ath10k *ar, u32 address,
 			     const void *buffer, u32 length);
+int ath10k_bmi_read_soc_reg(struct ath10k *ar, u32 address, u32 *reg_val);
+int ath10k_bmi_write_soc_reg(struct ath10k *ar, u32 address, u32 reg_val);
 #endif /* _BMI_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index 4045657e0a6e..ee1090ca2eac 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -261,8 +261,7 @@ static inline void ath10k_ce_engine_int_status_clear(struct ath10k *ar,
 }
 
 /*
- * Guts of ath10k_ce_send, used by both ath10k_ce_send and
- * ath10k_ce_sendlist_send.
+ * Guts of ath10k_ce_send.
  * The caller takes responsibility for any needed locking.
  */
 int ath10k_ce_send_nolock(struct ath10k_ce_pipe *ce_state,
@@ -1052,7 +1051,7 @@ int ath10k_ce_alloc_pipe(struct ath10k *ar, int ce_id,
 	 */
 	BUILD_BUG_ON(2 * TARGET_NUM_MSDU_DESC >
 		     (CE_HTT_H2T_MSG_SRC_NENTRIES - 1));
-	BUILD_BUG_ON(2 * TARGET_10X_NUM_MSDU_DESC >
+	BUILD_BUG_ON(2 * TARGET_10_4_NUM_MSDU_DESC_PFC >
 		     (CE_HTT_H2T_MSG_SRC_NENTRIES - 1));
 	BUILD_BUG_ON(2 * TARGET_TLV_NUM_MSDU_DESC >
 		     (CE_HTT_H2T_MSG_SRC_NENTRIES - 1));
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 0a8e29e9a0eb..5a0638915874 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -71,6 +71,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA9887_HW_1_0_VERSION,
@@ -91,6 +92,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
@@ -110,6 +112,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
@@ -129,6 +132,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA6174_HW_3_0_VERSION,
@@ -148,6 +152,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA6174_HW_3_2_VERSION,
@@ -166,8 +171,11 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 			.board_size = QCA6174_BOARD_DATA_SZ,
 			.board_ext_size = QCA6174_BOARD_EXT_DATA_SZ,
 		},
-		.hw_ops = &qca988x_ops,
+		.hw_ops = &qca6174_ops,
+		.hw_clk = qca6174_clk,
+		.target_cpu_freq = 176000000,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA99X0_HW_2_0_DEV_VERSION,
@@ -193,6 +201,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.sw_decrypt_mcast_mgmt = true,
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
+		.spectral_bin_discard = 4,
 	},
 	{
 		.id = QCA9984_HW_1_0_DEV_VERSION,
@@ -219,6 +228,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.sw_decrypt_mcast_mgmt = true,
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
+		.spectral_bin_discard = 12,
 	},
 	{
 		.id = QCA9888_HW_2_0_DEV_VERSION,
@@ -244,6 +254,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.sw_decrypt_mcast_mgmt = true,
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
+		.spectral_bin_discard = 12,
 	},
 	{
 		.id = QCA9377_HW_1_0_DEV_VERSION,
@@ -263,6 +274,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA9377_HW_1_1_DEV_VERSION,
@@ -280,8 +292,11 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 			.board_size = QCA9377_BOARD_DATA_SZ,
 			.board_ext_size = QCA9377_BOARD_EXT_DATA_SZ,
 		},
-		.hw_ops = &qca988x_ops,
+		.hw_ops = &qca6174_ops,
+		.hw_clk = qca6174_clk,
+		.target_cpu_freq = 176000000,
 		.decap_align_bytes = 4,
+		.spectral_bin_discard = 0,
 	},
 	{
 		.id = QCA4019_HW_1_0_DEV_VERSION,
@@ -308,6 +323,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.sw_decrypt_mcast_mgmt = true,
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
+		.spectral_bin_discard = 4,
 	},
 };
 
@@ -1623,6 +1639,13 @@ static void ath10k_core_restart(struct work_struct *work)
 	wake_up(&ar->wmi.tx_credits_wq);
 	wake_up(&ar->peer_mapping_wq);
 
+	/* TODO: We can have one instance of cancelling coverage_class_work by
+	 * moving it to ath10k_halt(), so that both stop() and restart() would
+	 * call that but it takes conf_mutex() and if we call cancel_work_sync()
+	 * with conf_mutex it will deadlock.
+	 */
+	cancel_work_sync(&ar->set_coverage_class_work);
+
 	mutex_lock(&ar->conf_mutex);
 
 	switch (ar->state) {
@@ -1634,7 +1657,8 @@ static void ath10k_core_restart(struct work_struct *work)
 		break;
 	case ATH10K_STATE_OFF:
 		/* this can happen if driver is being unloaded
-		 * or if the crash happens during FW probing */
+		 * or if the crash happens during FW probing
+		 */
 		ath10k_warn(ar, "cannot restart a device that hasn't been started\n");
 		break;
 	case ATH10K_STATE_RESTARTING:
@@ -2162,7 +2186,8 @@ EXPORT_SYMBOL(ath10k_core_stop);
 /* mac80211 manages fw/hw initialization through start/stop hooks. However in
  * order to know what hw capabilities should be advertised to mac80211 it is
  * necessary to load the firmware (and tear it down immediately since start
- * hook will try to init it again) before registering */
+ * hook will try to init it again) before registering
+ */
 static int ath10k_core_probe_fw(struct ath10k *ar)
 {
 	struct bmi_target_info target_info;
@@ -2356,7 +2381,8 @@ void ath10k_core_unregister(struct ath10k *ar)
 
 	/* We must unregister from mac80211 before we stop HTC and HIF.
 	 * Otherwise we will fail to submit commands to FW and mac80211 will be
-	 * unhappy about callback failures. */
+	 * unhappy about callback failures.
+	 */
 	ath10k_mac_unregister(ar);
 
 	ath10k_testmode_destroy(ar);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 88d14be7fcce..bf091514ecc6 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -501,14 +501,16 @@ enum ath10k_state {
 	 * stopped in ath10k_core_restart() work holding conf_mutex. The state
 	 * RESTARTED means that the device is up and mac80211 has started hw
 	 * reconfiguration. Once mac80211 is done with the reconfiguration we
-	 * set the state to STATE_ON in reconfig_complete(). */
+	 * set the state to STATE_ON in reconfig_complete().
+	 */
 	ATH10K_STATE_RESTARTING,
 	ATH10K_STATE_RESTARTED,
 
 	/* The device has crashed while restarting hw. This state is like ON
 	 * but commands are blocked in HTC and -ECOMM response is given. This
 	 * prevents completion timeouts and makes the driver more responsive to
-	 * userspace commands. This is also prevents recursive recovery. */
+	 * userspace commands. This is also prevents recursive recovery.
+	 */
 	ATH10K_STATE_WEDGED,
 
 	/* factory tests */
@@ -775,6 +777,8 @@ struct ath10k {
 	u32 num_rf_chains;
 	u32 max_spatial_stream;
 	/* protected by conf_mutex */
+	u32 low_5ghz_chan;
+	u32 high_5ghz_chan;
 	bool ani_enabled;
 
 	bool p2p;
@@ -918,7 +922,8 @@ struct ath10k {
 	struct work_struct restart_work;
 
 	/* cycle count is reported twice for each visited channel during scan.
-	 * access protected by data_lock */
+	 * access protected by data_lock
+	 */
 	u32 survey_last_rx_clear_count;
 	u32 survey_last_cycle_count;
 	struct survey_info survey[ATH10K_NUM_CHANS];
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index fb0ade3adb07..4cd2a0fd49d6 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -249,9 +249,6 @@ static ssize_t ath10k_read_wmi_services(struct file *file,
 
 	mutex_lock(&ar->conf_mutex);
 
-	if (len > buf_len)
-		len = buf_len;
-
 	spin_lock_bh(&ar->data_lock);
 	for (i = 0; i < WMI_SERVICE_MAX; i++) {
 		enabled = test_bit(i, ar->wmi.svc_map);
@@ -1819,7 +1816,7 @@ static void ath10k_tpc_stats_fill(struct ath10k *ar,
 			 tpc_stats->num_tx_chain,
 			 tpc_stats->rate_max);
 
-	for (j = 0; j < tpc_stats->num_tx_chain ; j++) {
+	for (j = 0; j < WMI_TPC_FLAG; j++) {
 		switch (j) {
 		case WMI_TPC_TABLE_TYPE_CDD:
 			if (tpc_stats->flag[j] == ATH10K_TPC_TABLE_TYPE_FLAG) {
@@ -1985,7 +1982,8 @@ void ath10k_debug_stop(struct ath10k *ar)
 
 	/* Must not use _sync to avoid deadlock, we do that in
 	 * ath10k_debug_destroy(). The check for htt_stats_mask is to avoid
-	 * warning from del_timer(). */
+	 * warning from del_timer().
+	 */
 	if (ar->debug.htt_stats_mask != 0)
 		cancel_delayed_work(&ar->debug.htt_stats_dwork);
 
@@ -1997,6 +1995,15 @@ static ssize_t ath10k_write_simulate_radar(struct file *file,
 					   size_t count, loff_t *ppos)
 {
 	struct ath10k *ar = file->private_data;
+	struct ath10k_vif *arvif;
+
+	/* Just check for for the first vif alone, as all the vifs will be
+	 * sharing the same channel and if the channel is disabled, all the
+	 * vifs will share the same 'is_started' state.
+	 */
+	arvif = list_first_entry(&ar->arvifs, typeof(*arvif), list);
+	if (!arvif->is_started)
+		return -EINVAL;
 
 	ieee80211_radar_detected(ar->hw);
 
@@ -2437,86 +2444,82 @@ int ath10k_debug_register(struct ath10k *ar)
 	init_completion(&ar->debug.tpc_complete);
 	init_completion(&ar->debug.fw_stats_complete);
 
-	debugfs_create_file("fw_stats", S_IRUSR, ar->debug.debugfs_phy, ar,
+	debugfs_create_file("fw_stats", 0400, ar->debug.debugfs_phy, ar,
 			    &fops_fw_stats);
 
-	debugfs_create_file("fw_reset_stats", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_fw_reset_stats);
+	debugfs_create_file("fw_reset_stats", 0400, ar->debug.debugfs_phy, ar,
+			    &fops_fw_reset_stats);
 
-	debugfs_create_file("wmi_services", S_IRUSR, ar->debug.debugfs_phy, ar,
+	debugfs_create_file("wmi_services", 0400, ar->debug.debugfs_phy, ar,
 			    &fops_wmi_services);
 
-	debugfs_create_file("simulate_fw_crash", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_simulate_fw_crash);
+	debugfs_create_file("simulate_fw_crash", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_simulate_fw_crash);
 
-	debugfs_create_file("fw_crash_dump", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_fw_crash_dump);
+	debugfs_create_file("fw_crash_dump", 0400, ar->debug.debugfs_phy, ar,
+			    &fops_fw_crash_dump);
 
-	debugfs_create_file("reg_addr", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_reg_addr);
+	debugfs_create_file("reg_addr", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_reg_addr);
 
-	debugfs_create_file("reg_value", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_reg_value);
+	debugfs_create_file("reg_value", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_reg_value);
 
-	debugfs_create_file("mem_value", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_mem_value);
+	debugfs_create_file("mem_value", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_mem_value);
 
-	debugfs_create_file("chip_id", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_chip_id);
+	debugfs_create_file("chip_id", 0400, ar->debug.debugfs_phy, ar,
+			    &fops_chip_id);
 
-	debugfs_create_file("htt_stats_mask", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_htt_stats_mask);
+	debugfs_create_file("htt_stats_mask", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_htt_stats_mask);
 
-	debugfs_create_file("htt_max_amsdu_ampdu", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar,
+	debugfs_create_file("htt_max_amsdu_ampdu", 0600, ar->debug.debugfs_phy, ar,
 			    &fops_htt_max_amsdu_ampdu);
 
-	debugfs_create_file("fw_dbglog", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_fw_dbglog);
+	debugfs_create_file("fw_dbglog", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_fw_dbglog);
 
-	debugfs_create_file("cal_data", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_cal_data);
+	debugfs_create_file("cal_data", 0400, ar->debug.debugfs_phy, ar,
+			    &fops_cal_data);
 
-	debugfs_create_file("ani_enable", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_ani_enable);
+	debugfs_create_file("ani_enable", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_ani_enable);
 
-	debugfs_create_file("nf_cal_period", S_IRUSR | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_nf_cal_period);
+	debugfs_create_file("nf_cal_period", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_nf_cal_period);
 
 	if (IS_ENABLED(CONFIG_ATH10K_DFS_CERTIFIED)) {
-		debugfs_create_file("dfs_simulate_radar", S_IWUSR,
-				    ar->debug.debugfs_phy, ar,
-				    &fops_simulate_radar);
+		debugfs_create_file("dfs_simulate_radar", 0200, ar->debug.debugfs_phy,
+				    ar, &fops_simulate_radar);
 
-		debugfs_create_bool("dfs_block_radar_events", S_IWUSR,
+		debugfs_create_bool("dfs_block_radar_events", 0200,
 				    ar->debug.debugfs_phy,
 				    &ar->dfs_block_radar_events);
 
-		debugfs_create_file("dfs_stats", S_IRUSR,
-				    ar->debug.debugfs_phy, ar,
+		debugfs_create_file("dfs_stats", 0400, ar->debug.debugfs_phy, ar,
 				    &fops_dfs_stats);
 	}
 
-	debugfs_create_file("pktlog_filter", S_IRUGO | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_pktlog_filter);
+	debugfs_create_file("pktlog_filter", 0644, ar->debug.debugfs_phy, ar,
+			    &fops_pktlog_filter);
 
-	debugfs_create_file("quiet_period", S_IRUGO | S_IWUSR,
-			    ar->debug.debugfs_phy, ar, &fops_quiet_period);
+	debugfs_create_file("quiet_period", 0644, ar->debug.debugfs_phy, ar,
+			    &fops_quiet_period);
 
-	debugfs_create_file("tpc_stats", S_IRUSR,
-			    ar->debug.debugfs_phy, ar, &fops_tpc_stats);
+	debugfs_create_file("tpc_stats", 0400, ar->debug.debugfs_phy, ar,
+			    &fops_tpc_stats);
 
 	if (test_bit(WMI_SERVICE_COEX_GPIO, ar->wmi.svc_map))
-		debugfs_create_file("btcoex", S_IRUGO | S_IWUSR,
-				    ar->debug.debugfs_phy, ar, &fops_btcoex);
+		debugfs_create_file("btcoex", 0644, ar->debug.debugfs_phy, ar,
+				    &fops_btcoex);
 
 	if (test_bit(WMI_SERVICE_PEER_STATS, ar->wmi.svc_map))
-		debugfs_create_file("peer_stats", S_IRUGO | S_IWUSR,
-				    ar->debug.debugfs_phy, ar,
+		debugfs_create_file("peer_stats", 0644, ar->debug.debugfs_phy, ar,
 				    &fops_peer_stats);
 
-	debugfs_create_file("fw_checksums", S_IRUSR,
-			    ar->debug.debugfs_phy, ar, &fops_fw_checksums);
+	debugfs_create_file("fw_checksums", 0400, ar->debug.debugfs_phy, ar,
+			    &fops_fw_checksums);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath10k/debugfs_sta.c b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
index 7353e7ea88f1..d59ac6b83340 100644
--- a/drivers/net/wireless/ath/ath10k/debugfs_sta.c
+++ b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
@@ -372,11 +372,10 @@ static const struct file_operations fops_peer_debug_trigger = {
 void ath10k_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    struct ieee80211_sta *sta, struct dentry *dir)
 {
-	debugfs_create_file("aggr_mode", S_IRUGO | S_IWUSR, dir, sta,
-			    &fops_aggr_mode);
-	debugfs_create_file("addba", S_IWUSR, dir, sta, &fops_addba);
-	debugfs_create_file("addba_resp", S_IWUSR, dir, sta, &fops_addba_resp);
-	debugfs_create_file("delba", S_IWUSR, dir, sta, &fops_delba);
+	debugfs_create_file("aggr_mode", 0644, dir, sta, &fops_aggr_mode);
+	debugfs_create_file("addba", 0200, dir, sta, &fops_addba);
+	debugfs_create_file("addba_resp", 0200, dir, sta, &fops_addba_resp);
+	debugfs_create_file("delba", 0200, dir, sta, &fops_delba);
 	debugfs_create_file("peer_debug_trigger", 0600, dir, sta,
 			    &fops_peer_debug_trigger);
 }
diff --git a/drivers/net/wireless/ath/ath10k/hif.h b/drivers/net/wireless/ath/ath10k/hif.h
index b2566b06e1e1..6679dd9cfd12 100644
--- a/drivers/net/wireless/ath/ath10k/hif.h
+++ b/drivers/net/wireless/ath/ath10k/hif.h
@@ -54,7 +54,8 @@ struct ath10k_hif_ops {
 	int (*start)(struct ath10k *ar);
 
 	/* Clean up what start() did. This does not revert to BMI phase. If
-	 * desired so, call power_down() and power_up() */
+	 * desired so, call power_down() and power_up()
+	 */
 	void (*stop)(struct ath10k *ar);
 
 	int (*map_service_to_pipe)(struct ath10k *ar, u16 service_id,
@@ -82,7 +83,8 @@ struct ath10k_hif_ops {
 	int (*power_up)(struct ath10k *ar);
 
 	/* Power down the device and free up resources. stop() must be called
-	 * before this if start() was called earlier */
+	 * before this if start() was called earlier
+	 */
 	void (*power_down)(struct ath10k *ar);
 
 	int (*suspend)(struct ath10k *ar);
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 9f6a915f91bf..b7669b2e94aa 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -119,6 +119,9 @@ int ath10k_htc_send(struct ath10k_htc *htc,
 		credits = DIV_ROUND_UP(skb->len, htc->target_credit_size);
 		spin_lock_bh(&htc->tx_lock);
 		if (ep->tx_credits < credits) {
+			ath10k_dbg(ar, ATH10K_DBG_HTC,
+				   "htc insufficient credits ep %d required %d available %d\n",
+				   eid, credits, ep->tx_credits);
 			spin_unlock_bh(&htc->tx_lock);
 			ret = -EAGAIN;
 			goto err_pull;
@@ -419,7 +422,8 @@ static void ath10k_htc_control_rx_complete(struct ath10k *ar,
 					   struct sk_buff *skb)
 {
 	/* This is unexpected. FW is not supposed to send regular rx on this
-	 * endpoint. */
+	 * endpoint.
+	 */
 	ath10k_warn(ar, "unexpected htc rx\n");
 	kfree_skb(skb);
 }
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index 90c2f72666b8..6305308422c4 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -51,7 +51,8 @@ enum htt_h2t_msg_type { /* host-to-target */
 	HTT_H2T_MSG_TYPE_FRAG_DESC_BANK_CFG = 6,
 
 	/* This command is used for sending management frames in HTT < 3.0.
-	 * HTT >= 3.0 uses TX_FRM for everything. */
+	 * HTT >= 3.0 uses TX_FRM for everything.
+	 */
 	HTT_H2T_MSG_TYPE_MGMT_TX            = 7,
 	HTT_H2T_MSG_TYPE_TX_FETCH_RESP      = 11,
 
@@ -910,7 +911,8 @@ struct htt_rx_test {
 
 	/* payload consists of 2 lists:
 	 *  a) num_ints * sizeof(__le32)
-	 *  b) num_chars * sizeof(u8) aligned to 4bytes */
+	 *  b) num_chars * sizeof(u8) aligned to 4bytes
+	 */
 	u8 payload[0];
 } __packed;
 
@@ -1307,7 +1309,8 @@ struct htt_frag_desc_bank_id {
 } __packed;
 
 /* real is 16 but it wouldn't fit in the max htt message size
- * so we use a conservatively safe value for now */
+ * so we use a conservatively safe value for now
+ */
 #define HTT_FRAG_DESC_BANK_MAX 4
 
 #define HTT_FRAG_DESC_BANK_CFG_INFO_PDEV_ID_MASK		0x03
@@ -1684,12 +1687,14 @@ struct ath10k_htt {
 	DECLARE_KFIFO_PTR(txdone_fifo, struct htt_tx_done);
 
 	/* set if host-fw communication goes haywire
-	 * used to avoid further failures */
+	 * used to avoid further failures
+	 */
 	bool rx_confused;
 	atomic_t num_mpdus_ready;
 
 	/* This is used to group tx/rx completions separately and process them
-	 * in batches to reduce cache stalls */
+	 * in batches to reduce cache stalls
+	 */
 	struct sk_buff_head rx_compl_q;
 	struct sk_buff_head rx_in_ord_compl_q;
 	struct sk_buff_head tx_fetch_ind_q;
@@ -1725,11 +1730,13 @@ struct ath10k_htt {
 
 /* This structure layout is programmed via rx ring setup
  * so that FW knows how to transfer the rx descriptor to the host.
- * Buffers like this are placed on the rx ring. */
+ * Buffers like this are placed on the rx ring.
+ */
 struct htt_rx_desc {
 	union {
 		/* This field is filled on the host using the msdu buffer
-		 * from htt_rx_indication */
+		 * from htt_rx_indication
+		 */
 		struct fw_rx_desc_base fw_desc;
 		u32 pad;
 	} __packed;
@@ -1760,7 +1767,8 @@ struct htt_rx_desc {
 #define HTT_RX_MSDU_SIZE (HTT_RX_BUF_SIZE - (int)sizeof(struct htt_rx_desc))
 
 /* Refill a bunch of RX buffers for each refill round so that FW/HW can handle
- * aggregated traffic more nicely. */
+ * aggregated traffic more nicely.
+ */
 #define ATH10K_HTT_MAX_NUM_REFILL 100
 
 /*
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 02a3fc81fbe3..84b6067ff6e7 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -177,7 +177,8 @@ static void ath10k_htt_rx_msdu_buff_replenish(struct ath10k_htt *htt)
 	 * automatically balances load wrt to CPU power.
 	 *
 	 * This probably comes at a cost of lower maximum throughput but
-	 * improves the average and stability. */
+	 * improves the average and stability.
+	 */
 	spin_lock_bh(&htt->rx_ring.lock);
 	num_deficit = htt->rx_ring.fill_level - htt->rx_ring.fill_cnt;
 	num_to_fill = min(ATH10K_HTT_MAX_NUM_REFILL, num_deficit);
@@ -304,7 +305,8 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt,
 		rx_desc = (struct htt_rx_desc *)msdu->data;
 
 		/* FIXME: we must report msdu payload since this is what caller
-		 *        expects now */
+		 * expects now
+		 */
 		skb_put(msdu, offsetof(struct htt_rx_desc, msdu_payload));
 		skb_pull(msdu, offsetof(struct htt_rx_desc, msdu_payload));
 
@@ -630,16 +632,17 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar,
 		sgi = (info3 >> 7) & 1;
 
 		status->rate_idx = mcs;
-		status->flag |= RX_FLAG_HT;
+		status->encoding = RX_ENC_HT;
 		if (sgi)
-			status->flag |= RX_FLAG_SHORT_GI;
+			status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 		if (bw)
-			status->flag |= RX_FLAG_40MHZ;
+			status->bw = RATE_INFO_BW_40;
 		break;
 	case HTT_RX_VHT:
 	case HTT_RX_VHT_WITH_TXBF:
 		/* VHT-SIG-A1 in info2, VHT-SIG-A2 in info3
-		   TODO check this */
+		 * TODO check this
+		 */
 		bw = info2 & 3;
 		sgi = info3 & 1;
 		group_id = (info2 >> 4) & 0x3F;
@@ -686,10 +689,10 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar,
 		}
 
 		status->rate_idx = mcs;
-		status->vht_nss = nss;
+		status->nss = nss;
 
 		if (sgi)
-			status->flag |= RX_FLAG_SHORT_GI;
+			status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 		switch (bw) {
 		/* 20MHZ */
@@ -697,18 +700,18 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar,
 			break;
 		/* 40MHZ */
 		case 1:
-			status->flag |= RX_FLAG_40MHZ;
+			status->bw = RATE_INFO_BW_40;
 			break;
 		/* 80MHZ */
 		case 2:
-			status->vht_flag |= RX_VHT_FLAG_80MHZ;
+			status->bw = RATE_INFO_BW_80;
 			break;
 		case 3:
-			status->vht_flag |= RX_VHT_FLAG_160MHZ;
+			status->bw = RATE_INFO_BW_160;
 			break;
 		}
 
-		status->flag |= RX_FLAG_VHT;
+		status->encoding = RX_ENC_VHT;
 		break;
 	default:
 		break;
@@ -871,13 +874,10 @@ static void ath10k_htt_rx_h_ppdu(struct ath10k *ar,
 		/* New PPDU starts so clear out the old per-PPDU status. */
 		status->freq = 0;
 		status->rate_idx = 0;
-		status->vht_nss = 0;
-		status->vht_flag &= ~RX_VHT_FLAG_80MHZ;
-		status->flag &= ~(RX_FLAG_HT |
-				  RX_FLAG_VHT |
-				  RX_FLAG_SHORT_GI |
-				  RX_FLAG_40MHZ |
-				  RX_FLAG_MACTIME_END);
+		status->nss = 0;
+		status->encoding = RX_ENC_LEGACY;
+		status->bw = RATE_INFO_BW_20;
+		status->flag &= ~RX_FLAG_MACTIME_END;
 		status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 
 		ath10k_htt_rx_h_signal(ar, status, rxd);
@@ -930,7 +930,7 @@ static void ath10k_process_rx(struct ath10k *ar,
 	*status = *rx_status;
 
 	ath10k_dbg(ar, ATH10K_DBG_DATA,
-		   "rx skb %pK len %u peer %pM %s %s sn %u %s%s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%llx fcs-err %i mic-err %i amsdu-more %i\n",
+		   "rx skb %pK len %u peer %pM %s %s sn %u %s%s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
 		   skb,
 		   skb->len,
 		   ieee80211_get_SA(hdr),
@@ -938,16 +938,15 @@ static void ath10k_process_rx(struct ath10k *ar,
 		   is_multicast_ether_addr(ieee80211_get_DA(hdr)) ?
 							"mcast" : "ucast",
 		   (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4,
-		   (status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) == 0 ?
-							"legacy" : "",
-		   status->flag & RX_FLAG_HT ? "ht" : "",
-		   status->flag & RX_FLAG_VHT ? "vht" : "",
-		   status->flag & RX_FLAG_40MHZ ? "40" : "",
-		   status->vht_flag & RX_VHT_FLAG_80MHZ ? "80" : "",
-		   status->vht_flag & RX_VHT_FLAG_160MHZ ? "160" : "",
-		   status->flag & RX_FLAG_SHORT_GI ? "sgi " : "",
+		   (status->encoding == RX_ENC_LEGACY) ? "legacy" : "",
+		   (status->encoding == RX_ENC_HT) ? "ht" : "",
+		   (status->encoding == RX_ENC_VHT) ? "vht" : "",
+		   (status->bw == RATE_INFO_BW_40) ? "40" : "",
+		   (status->bw == RATE_INFO_BW_80) ? "80" : "",
+		   (status->bw == RATE_INFO_BW_160) ? "160" : "",
+		   status->enc_flags & RX_ENC_FLAG_SHORT_GI ? "sgi " : "",
 		   status->rate_idx,
-		   status->vht_nss,
+		   status->nss,
 		   status->freq,
 		   status->band, status->flag,
 		   !!(status->flag & RX_FLAG_FAILED_FCS_CRC),
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 86b427f5e2bc..685faac1368f 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -526,7 +526,8 @@ int ath10k_htt_h2t_stats_req(struct ath10k_htt *htt, u8 mask, u64 cookie)
 	memset(req, 0, sizeof(*req));
 
 	/* currently we support only max 8 bit masks so no need to worry
-	 * about endian support */
+	 * about endian support
+	 */
 	req->upload_types[0] = mask;
 	req->reset_types[0] = mask;
 	req->stat_type = HTT_STATS_REQ_CFG_STAT_TYPE_INVALID;
@@ -1008,7 +1009,8 @@ int ath10k_htt_tx(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txmode,
 	 * There is simply no point in pushing HTT TX_FRM through HTC tx path
 	 * as it's a waste of resources. By bypassing HTC it is possible to
 	 * avoid extra memory allocations, compress data structures and thus
-	 * improve performance. */
+	 * improve performance.
+	 */
 
 	txbuf->htc_hdr.eid = htt->eid;
 	txbuf->htc_hdr.len = __cpu_to_le16(sizeof(txbuf->cmd_hdr) +
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index 33fb26833cd0..c866ab524571 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -19,6 +19,7 @@
 #include "hw.h"
 #include "hif.h"
 #include "wmi-ops.h"
+#include "bmi.h"
 
 const struct ath10k_hw_regs qca988x_regs = {
 	.rtc_soc_base_address		= 0x00004000,
@@ -51,7 +52,7 @@ const struct ath10k_hw_regs qca6174_regs = {
 	.rtc_soc_base_address			= 0x00000800,
 	.rtc_wmac_base_address			= 0x00001000,
 	.soc_core_base_address			= 0x0003a000,
-	.wlan_mac_base_address			= 0x00020000,
+	.wlan_mac_base_address			= 0x00010000,
 	.ce_wrapper_base_address		= 0x00034000,
 	.ce0_base_address			= 0x00034400,
 	.ce1_base_address			= 0x00034800,
@@ -72,6 +73,9 @@ const struct ath10k_hw_regs qca6174_regs = {
 	.pcie_intr_fw_mask			= 0x00000400,
 	.pcie_intr_ce_mask_all			= 0x0007f800,
 	.pcie_intr_clr_address			= 0x00000014,
+	.cpu_pll_init_address			= 0x00404020,
+	.cpu_speed_address			= 0x00404024,
+	.core_clk_div_address			= 0x00404028,
 };
 
 const struct ath10k_hw_regs qca99x0_regs = {
@@ -187,6 +191,73 @@ const struct ath10k_hw_values qca4019_values = {
 	.ce_desc_meta_data_lsb          = 4,
 };
 
+const struct ath10k_hw_clk_params qca6174_clk[ATH10K_HW_REFCLK_COUNT] = {
+	{
+		.refclk = 48000000,
+		.div = 0xe,
+		.rnfrac = 0x2aaa8,
+		.settle_time = 2400,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 19200000,
+		.div = 0x24,
+		.rnfrac = 0x2aaa8,
+		.settle_time = 960,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 24000000,
+		.div = 0x1d,
+		.rnfrac = 0x15551,
+		.settle_time = 1200,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 26000000,
+		.div = 0x1b,
+		.rnfrac = 0x4ec4,
+		.settle_time = 1300,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 37400000,
+		.div = 0x12,
+		.rnfrac = 0x34b49,
+		.settle_time = 1870,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 38400000,
+		.div = 0x12,
+		.rnfrac = 0x15551,
+		.settle_time = 1920,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 40000000,
+		.div = 0x12,
+		.rnfrac = 0x26665,
+		.settle_time = 2000,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+	{
+		.refclk = 52000000,
+		.div = 0x1b,
+		.rnfrac = 0x4ec4,
+		.settle_time = 2600,
+		.refdiv = 0,
+		.outdiv = 1,
+	},
+};
+
 void ath10k_hw_fill_survey_time(struct ath10k *ar, struct survey_info *survey,
 				u32 cc, u32 rcc, u32 cc_prev, u32 rcc_prev)
 {
@@ -361,6 +432,195 @@ unlock:
 	mutex_unlock(&ar->conf_mutex);
 }
 
+/**
+ * ath10k_hw_qca6174_enable_pll_clock() - enable the qca6174 hw pll clock
+ * @ar: the ath10k blob
+ *
+ * This function is very hardware specific, the clock initialization
+ * steps is very sensitive and could lead to unknown crash, so they
+ * should be done in sequence.
+ *
+ * *** Be aware if you planned to refactor them. ***
+ *
+ * Return: 0 if successfully enable the pll, otherwise EINVAL
+ */
+static int ath10k_hw_qca6174_enable_pll_clock(struct ath10k *ar)
+{
+	int ret, wait_limit;
+	u32 clk_div_addr, pll_init_addr, speed_addr;
+	u32 addr, reg_val, mem_val;
+	struct ath10k_hw_params *hw;
+	const struct ath10k_hw_clk_params *hw_clk;
+
+	hw = &ar->hw_params;
+
+	if (ar->regs->core_clk_div_address == 0 ||
+	    ar->regs->cpu_pll_init_address == 0 ||
+	    ar->regs->cpu_speed_address == 0)
+		return -EINVAL;
+
+	clk_div_addr = ar->regs->core_clk_div_address;
+	pll_init_addr = ar->regs->cpu_pll_init_address;
+	speed_addr = ar->regs->cpu_speed_address;
+
+	/* Read efuse register to find out the right hw clock configuration */
+	addr = (RTC_SOC_BASE_ADDRESS | EFUSE_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* sanitize if the hw refclk index is out of the boundary */
+	if (MS(reg_val, EFUSE_XTAL_SEL) > ATH10K_HW_REFCLK_COUNT)
+		return -EINVAL;
+
+	hw_clk = &hw->hw_clk[MS(reg_val, EFUSE_XTAL_SEL)];
+
+	/* Set the rnfrac and outdiv params to bb_pll register */
+	addr = (RTC_SOC_BASE_ADDRESS | BB_PLL_CONFIG_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val &= ~(BB_PLL_CONFIG_FRAC_MASK | BB_PLL_CONFIG_OUTDIV_MASK);
+	reg_val |= (SM(hw_clk->rnfrac, BB_PLL_CONFIG_FRAC) |
+		    SM(hw_clk->outdiv, BB_PLL_CONFIG_OUTDIV));
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* Set the correct settle time value to pll_settle register */
+	addr = (RTC_WMAC_BASE_ADDRESS | WLAN_PLL_SETTLE_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val &= ~WLAN_PLL_SETTLE_TIME_MASK;
+	reg_val |= SM(hw_clk->settle_time, WLAN_PLL_SETTLE_TIME);
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* Set the clock_ctrl div to core_clk_ctrl register */
+	addr = (RTC_SOC_BASE_ADDRESS | SOC_CORE_CLK_CTRL_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val &= ~SOC_CORE_CLK_CTRL_DIV_MASK;
+	reg_val |= SM(1, SOC_CORE_CLK_CTRL_DIV);
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* Set the clock_div register */
+	mem_val = 1;
+	ret = ath10k_bmi_write_memory(ar, clk_div_addr, &mem_val,
+				      sizeof(mem_val));
+	if (ret)
+		return -EINVAL;
+
+	/* Configure the pll_control register */
+	addr = (RTC_WMAC_BASE_ADDRESS | WLAN_PLL_CONTROL_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val |= (SM(hw_clk->refdiv, WLAN_PLL_CONTROL_REFDIV) |
+		    SM(hw_clk->div, WLAN_PLL_CONTROL_DIV) |
+		    SM(1, WLAN_PLL_CONTROL_NOPWD));
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* busy wait (max 1s) the rtc_sync status register indicate ready */
+	wait_limit = 100000;
+	addr = (RTC_WMAC_BASE_ADDRESS | RTC_SYNC_STATUS_OFFSET);
+	do {
+		ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+		if (ret)
+			return -EINVAL;
+
+		if (!MS(reg_val, RTC_SYNC_STATUS_PLL_CHANGING))
+			break;
+
+		wait_limit--;
+		udelay(10);
+
+	} while (wait_limit > 0);
+
+	if (MS(reg_val, RTC_SYNC_STATUS_PLL_CHANGING))
+		return -EINVAL;
+
+	/* Unset the pll_bypass in pll_control register */
+	addr = (RTC_WMAC_BASE_ADDRESS | WLAN_PLL_CONTROL_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val &= ~WLAN_PLL_CONTROL_BYPASS_MASK;
+	reg_val |= SM(0, WLAN_PLL_CONTROL_BYPASS);
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* busy wait (max 1s) the rtc_sync status register indicate ready */
+	wait_limit = 100000;
+	addr = (RTC_WMAC_BASE_ADDRESS | RTC_SYNC_STATUS_OFFSET);
+	do {
+		ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+		if (ret)
+			return -EINVAL;
+
+		if (!MS(reg_val, RTC_SYNC_STATUS_PLL_CHANGING))
+			break;
+
+		wait_limit--;
+		udelay(10);
+
+	} while (wait_limit > 0);
+
+	if (MS(reg_val, RTC_SYNC_STATUS_PLL_CHANGING))
+		return -EINVAL;
+
+	/* Enable the hardware cpu clock register */
+	addr = (RTC_SOC_BASE_ADDRESS | SOC_CPU_CLOCK_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val &= ~SOC_CPU_CLOCK_STANDARD_MASK;
+	reg_val |= SM(1, SOC_CPU_CLOCK_STANDARD);
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* unset the nopwd from pll_control register */
+	addr = (RTC_WMAC_BASE_ADDRESS | WLAN_PLL_CONTROL_OFFSET);
+	ret = ath10k_bmi_read_soc_reg(ar, addr, &reg_val);
+	if (ret)
+		return -EINVAL;
+
+	reg_val &= ~WLAN_PLL_CONTROL_NOPWD_MASK;
+	ret = ath10k_bmi_write_soc_reg(ar, addr, reg_val);
+	if (ret)
+		return -EINVAL;
+
+	/* enable the pll_init register */
+	mem_val = 1;
+	ret = ath10k_bmi_write_memory(ar, pll_init_addr, &mem_val,
+				      sizeof(mem_val));
+	if (ret)
+		return -EINVAL;
+
+	/* set the target clock frequency to speed register */
+	ret = ath10k_bmi_write_memory(ar, speed_addr, &hw->target_cpu_freq,
+				      sizeof(hw->target_cpu_freq));
+	if (ret)
+		return -EINVAL;
+
+	return 0;
+}
+
 const struct ath10k_hw_ops qca988x_ops = {
 	.set_coverage_class = ath10k_hw_qca988x_set_coverage_class,
 };
@@ -374,3 +634,8 @@ static int ath10k_qca99x0_rx_desc_get_l3_pad_bytes(struct htt_rx_desc *rxd)
 const struct ath10k_hw_ops qca99x0_ops = {
 	.rx_desc_get_l3_pad_bytes = ath10k_qca99x0_rx_desc_get_l3_pad_bytes,
 };
+
+const struct ath10k_hw_ops qca6174_ops = {
+	.set_coverage_class = ath10k_hw_qca988x_set_coverage_class,
+	.enable_pll_clk = ath10k_hw_qca6174_enable_pll_clock,
+};
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index f0fda0f2b3b4..5b1e90bb2a4d 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -129,7 +129,7 @@ enum qca9377_chip_id_rev {
 #define QCA4019_HW_1_0_PATCH_LOAD_ADDR  0x1234
 
 #define ATH10K_FW_FILE_BASE		"firmware"
-#define ATH10K_FW_API_MAX		5
+#define ATH10K_FW_API_MAX		6
 #define ATH10K_FW_API_MIN		2
 
 #define ATH10K_FW_API2_FILE		"firmware-2.bin"
@@ -141,6 +141,9 @@ enum qca9377_chip_id_rev {
 /* HTT id conflict fix for management frames over HTT */
 #define ATH10K_FW_API5_FILE		"firmware-5.bin"
 
+/* the firmware-6.bin blob */
+#define ATH10K_FW_API6_FILE		"firmware-6.bin"
+
 #define ATH10K_FW_UTF_FILE		"utf.bin"
 #define ATH10K_FW_UTF_API2_FILE		"utf-2.bin"
 
@@ -255,6 +258,9 @@ struct ath10k_hw_regs {
 	u32 pcie_intr_fw_mask;
 	u32 pcie_intr_ce_mask_all;
 	u32 pcie_intr_clr_address;
+	u32 cpu_pll_init_address;
+	u32 cpu_speed_address;
+	u32 core_clk_div_address;
 };
 
 extern const struct ath10k_hw_regs qca988x_regs;
@@ -293,7 +299,8 @@ void ath10k_hw_fill_survey_time(struct ath10k *ar, struct survey_info *survey,
  *  - raw appears in nwifi decap, raw and nwifi appear in ethernet decap
  *  - raw have FCS, nwifi doesn't
  *  - ethernet frames have 802.11 header decapped and parts (base hdr, cipher
- *    param, llc/snap) are aligned to 4byte boundaries each */
+ *    param, llc/snap) are aligned to 4byte boundaries each
+ */
 enum ath10k_hw_txrx_mode {
 	ATH10K_HW_TXRX_RAW = 0,
 
@@ -363,6 +370,30 @@ enum ath10k_hw_cc_wraparound_type {
 	ATH10K_HW_CC_WRAP_SHIFTED_EACH = 2,
 };
 
+enum ath10k_hw_refclk_speed {
+	ATH10K_HW_REFCLK_UNKNOWN = -1,
+	ATH10K_HW_REFCLK_48_MHZ = 0,
+	ATH10K_HW_REFCLK_19_2_MHZ = 1,
+	ATH10K_HW_REFCLK_24_MHZ = 2,
+	ATH10K_HW_REFCLK_26_MHZ = 3,
+	ATH10K_HW_REFCLK_37_4_MHZ = 4,
+	ATH10K_HW_REFCLK_38_4_MHZ = 5,
+	ATH10K_HW_REFCLK_40_MHZ = 6,
+	ATH10K_HW_REFCLK_52_MHZ = 7,
+
+	/* must be the last one */
+	ATH10K_HW_REFCLK_COUNT,
+};
+
+struct ath10k_hw_clk_params {
+	u32 refclk;
+	u32 div;
+	u32 rnfrac;
+	u32 settle_time;
+	u32 refdiv;
+	u32 outdiv;
+};
+
 struct ath10k_hw_params {
 	u32 id;
 	u16 dev_id;
@@ -416,6 +447,13 @@ struct ath10k_hw_params {
 
 	/* Number of bytes used for alignment in rx_hdr_status of rx desc. */
 	int decap_align_bytes;
+
+	/* hw specific clock control parameters */
+	const struct ath10k_hw_clk_params *hw_clk;
+	int target_cpu_freq;
+
+	/* Number of bytes to be discarded for each FFT sample */
+	int spectral_bin_discard;
 };
 
 struct htt_rx_desc;
@@ -424,10 +462,14 @@ struct htt_rx_desc;
 struct ath10k_hw_ops {
 	int (*rx_desc_get_l3_pad_bytes)(struct htt_rx_desc *rxd);
 	void (*set_coverage_class)(struct ath10k *ar, s16 value);
+	int (*enable_pll_clk)(struct ath10k *ar);
 };
 
 extern const struct ath10k_hw_ops qca988x_ops;
 extern const struct ath10k_hw_ops qca99x0_ops;
+extern const struct ath10k_hw_ops qca6174_ops;
+
+extern const struct ath10k_hw_clk_params qca6174_clk[];
 
 static inline int
 ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw,
@@ -847,4 +889,38 @@ ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw,
 #define WAVE1_PHYCLK_USEC_MASK			0x0000007F
 #define WAVE1_PHYCLK_USEC_LSB			0
 
+/* qca6174 PLL offset/mask */
+#define SOC_CORE_CLK_CTRL_OFFSET		0x00000114
+#define SOC_CORE_CLK_CTRL_DIV_LSB		0
+#define SOC_CORE_CLK_CTRL_DIV_MASK		0x00000007
+
+#define EFUSE_OFFSET				0x0000032c
+#define EFUSE_XTAL_SEL_LSB			8
+#define EFUSE_XTAL_SEL_MASK			0x00000700
+
+#define BB_PLL_CONFIG_OFFSET			0x000002f4
+#define BB_PLL_CONFIG_FRAC_LSB			0
+#define BB_PLL_CONFIG_FRAC_MASK			0x0003ffff
+#define BB_PLL_CONFIG_OUTDIV_LSB		18
+#define BB_PLL_CONFIG_OUTDIV_MASK		0x001c0000
+
+#define WLAN_PLL_SETTLE_OFFSET			0x0018
+#define WLAN_PLL_SETTLE_TIME_LSB		0
+#define WLAN_PLL_SETTLE_TIME_MASK		0x000007ff
+
+#define WLAN_PLL_CONTROL_OFFSET			0x0014
+#define WLAN_PLL_CONTROL_DIV_LSB		0
+#define WLAN_PLL_CONTROL_DIV_MASK		0x000003ff
+#define WLAN_PLL_CONTROL_REFDIV_LSB		10
+#define WLAN_PLL_CONTROL_REFDIV_MASK		0x00003c00
+#define WLAN_PLL_CONTROL_BYPASS_LSB		16
+#define WLAN_PLL_CONTROL_BYPASS_MASK		0x00010000
+#define WLAN_PLL_CONTROL_NOPWD_LSB		18
+#define WLAN_PLL_CONTROL_NOPWD_MASK		0x00040000
+
+#define RTC_SYNC_STATUS_OFFSET			0x0244
+#define RTC_SYNC_STATUS_PLL_CHANGING_LSB	5
+#define RTC_SYNC_STATUS_PLL_CHANGING_MASK	0x00000020
+/* qca6174 PLL offset/mask end */
+
 #endif /* _HW_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 3029f257a19a..4674ff33d320 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -457,7 +457,8 @@ static int ath10k_clear_vdev_key(struct ath10k_vif *arvif,
 
 	for (;;) {
 		/* since ath10k_install_key we can't hold data_lock all the
-		 * time, so we try to remove the keys incrementally */
+		 * time, so we try to remove the keys incrementally
+		 */
 		spin_lock_bh(&ar->data_lock);
 		i = 0;
 		list_for_each_entry(peer, &ar->peers, list) {
@@ -609,7 +610,8 @@ static u8 ath10k_parse_mpdudensity(u8 mpdudensity)
 	case 2:
 	case 3:
 	/* Our lower layer calculations limit our precision to
-	   1 microsecond */
+	 * 1 microsecond
+	 */
 		return 1;
 	case 4:
 		return 2;
@@ -978,7 +980,8 @@ static int ath10k_monitor_vdev_start(struct ath10k *ar, int vdev_id)
 	arg.channel.band_center_freq2 = chandef->center_freq2;
 
 	/* TODO setup this dynamically, what in case we
-	   don't have any vifs? */
+	 * don't have any vifs?
+	 */
 	arg.channel.mode = chan_to_phymode(chandef);
 	arg.channel.chan_radar =
 			!!(channel->flags & IEEE80211_CHAN_RADAR);
@@ -2373,9 +2376,10 @@ static int ath10k_peer_assoc_qos_ap(struct ath10k *ar,
 		}
 
 		/* TODO setup this based on STA listen interval and
-		   beacon interval. Currently we don't know
-		   sta->listen_interval - mac80211 patch required.
-		   Currently use 10 seconds */
+		 * beacon interval. Currently we don't know
+		 * sta->listen_interval - mac80211 patch required.
+		 * Currently use 10 seconds
+		 */
 		ret = ath10k_wmi_set_ap_ps_param(ar, arvif->vdev_id, sta->addr,
 						 WMI_AP_PS_PEER_PARAM_AGEOUT_TIME,
 						 10);
@@ -2451,6 +2455,8 @@ static void ath10k_peer_assoc_h_vht(struct ath10k *ar,
 	enum nl80211_band band;
 	const u16 *vht_mcs_mask;
 	u8 ampdu_factor;
+	u8 max_nss, vht_mcs;
+	int i;
 
 	if (WARN_ON(ath10k_mac_vif_chan(vif, &def)))
 		return;
@@ -2478,7 +2484,8 @@ static void ath10k_peer_assoc_h_vht(struct ath10k *ar,
 	/* Workaround: Some Netgear/Linksys 11ac APs set Rx A-MPDU factor to
 	 * zero in VHT IE. Using it would result in degraded throughput.
 	 * arg->peer_max_mpdu at this point contains HT max_mpdu so keep
-	 * it if VHT max_mpdu is smaller. */
+	 * it if VHT max_mpdu is smaller.
+	 */
 	arg->peer_max_mpdu = max(arg->peer_max_mpdu,
 				 (1U << (IEEE80211_HT_MAX_AMPDU_FACTOR +
 					ampdu_factor)) - 1);
@@ -2489,6 +2496,18 @@ static void ath10k_peer_assoc_h_vht(struct ath10k *ar,
 	if (sta->bandwidth == IEEE80211_STA_RX_BW_160)
 		arg->peer_flags |= ar->wmi.peer_flags->bw160;
 
+	/* Calculate peer NSS capability from VHT capabilities if STA
+	 * supports VHT.
+	 */
+	for (i = 0, max_nss = 0, vht_mcs = 0; i < NL80211_VHT_NSS_MAX; i++) {
+		vht_mcs = __le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map) >>
+			  (2 * i) & 3;
+
+		if ((vht_mcs != IEEE80211_VHT_MCS_NOT_SUPPORTED) &&
+		    vht_mcs_mask[i])
+			max_nss = i + 1;
+	}
+	arg->peer_num_spatial_streams = min(sta->rx_nss, max_nss);
 	arg->peer_vht_rates.rx_max_rate =
 		__le16_to_cpu(vht_cap->vht_mcs.rx_highest);
 	arg->peer_vht_rates.rx_mcs_set =
@@ -2779,7 +2798,8 @@ static void ath10k_bss_assoc(struct ieee80211_hw *hw,
 	}
 
 	/* ap_sta must be accessed only within rcu section which must be left
-	 * before calling ath10k_setup_peer_smps() which might sleep. */
+	 * before calling ath10k_setup_peer_smps() which might sleep.
+	 */
 	ht_cap = ap_sta->ht_cap;
 	vht_cap = ap_sta->vht_cap;
 
@@ -3050,7 +3070,8 @@ static int ath10k_update_channel_list(struct ath10k *ar)
 
 			/* FIXME: why use only legacy modes, why not any
 			 * HT/VHT modes? Would that even make any
-			 * difference? */
+			 * difference?
+			 */
 			if (channel->band == NL80211_BAND_2GHZ)
 				ch->mode = MODE_11G;
 			else
@@ -3114,7 +3135,8 @@ static void ath10k_regd_update(struct ath10k *ar)
 	}
 
 	/* Target allows setting up per-band regdomain but ath_common provides
-	 * a combined one only */
+	 * a combined one only
+	 */
 	ret = ath10k_wmi_pdev_set_regdomain(ar,
 					    regpair->reg_domain,
 					    regpair->reg_domain, /* 2ghz */
@@ -3126,6 +3148,21 @@ static void ath10k_regd_update(struct ath10k *ar)
 		ath10k_warn(ar, "failed to set pdev regdomain: %d\n", ret);
 }
 
+static void ath10k_mac_update_channel_list(struct ath10k *ar,
+					   struct ieee80211_supported_band *band)
+{
+	int i;
+
+	if (ar->low_5ghz_chan && ar->high_5ghz_chan) {
+		for (i = 0; i < band->n_channels; i++) {
+			if (band->channels[i].center_freq < ar->low_5ghz_chan ||
+			    band->channels[i].center_freq > ar->high_5ghz_chan)
+				band->channels[i].flags |=
+					IEEE80211_CHAN_DISABLED;
+		}
+	}
+}
+
 static void ath10k_reg_notifier(struct wiphy *wiphy,
 				struct regulatory_request *request)
 {
@@ -3149,6 +3186,10 @@ static void ath10k_reg_notifier(struct wiphy *wiphy,
 	if (ar->state == ATH10K_STATE_ON)
 		ath10k_regd_update(ar);
 	mutex_unlock(&ar->conf_mutex);
+
+	if (ar->phy_capability & WHAL_WLAN_11A_CAPABILITY)
+		ath10k_mac_update_channel_list(ar,
+					       ar->hw->wiphy->bands[NL80211_BAND_5GHZ]);
 }
 
 /***************/
@@ -3644,7 +3685,8 @@ void ath10k_offchan_tx_work(struct work_struct *work)
 	 * never transmitted. We delete the peer upon tx completion.
 	 * It is unlikely that a peer for offchannel tx will already be
 	 * present. However it may be in some rare cases so account for that.
-	 * Otherwise we might remove a legitimate peer and break stuff. */
+	 * Otherwise we might remove a legitimate peer and break stuff.
+	 */
 
 	for (;;) {
 		skb = skb_dequeue(&ar->offchan_tx_queue);
@@ -4684,6 +4726,7 @@ static void ath10k_stop(struct ieee80211_hw *hw)
 	}
 	mutex_unlock(&ar->conf_mutex);
 
+	cancel_work_sync(&ar->set_coverage_class_work);
 	cancel_delayed_work_sync(&ar->scan.timeout);
 	cancel_work_sync(&ar->restart_work);
 }
@@ -5683,7 +5726,8 @@ static int ath10k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	}
 
 	/* the peer should not disappear in mid-way (unless FW goes awry) since
-	 * we already hold conf_mutex. we just make sure its there now. */
+	 * we already hold conf_mutex. we just make sure its there now.
+	 */
 	spin_lock_bh(&ar->data_lock);
 	peer = ath10k_peer_find(ar, arvif->vdev_id, peer_addr);
 	spin_unlock_bh(&ar->data_lock);
@@ -5695,8 +5739,7 @@ static int ath10k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			ret = -EOPNOTSUPP;
 			goto exit;
 		} else {
-			/* if the peer doesn't exist there is no key to disable
-			 * anymore */
+			/* if the peer doesn't exist there is no key to disable anymore */
 			goto exit;
 		}
 	}
@@ -6555,7 +6598,8 @@ static void ath10k_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	long time_left;
 
 	/* mac80211 doesn't care if we really xmit queued frames or not
-	 * we'll collect those frames either way if we stop/delete vdevs */
+	 * we'll collect those frames either way if we stop/delete vdevs
+	 */
 	if (drop)
 		return;
 
@@ -6606,7 +6650,8 @@ static void ath10k_reconfig_complete(struct ieee80211_hw *hw,
 	mutex_lock(&ar->conf_mutex);
 
 	/* If device failed to restart it will be in a different state, e.g.
-	 * ATH10K_STATE_WEDGED */
+	 * ATH10K_STATE_WEDGED
+	 */
 	if (ar->state == ATH10K_STATE_RESTARTED) {
 		ath10k_info(ar, "device successfully recovered\n");
 		ar->state = ATH10K_STATE_ON;
@@ -7129,7 +7174,7 @@ ath10k_mac_update_rx_channel(struct ath10k *ar,
 	lockdep_assert_held(&ar->data_lock);
 
 	WARN_ON(ctx && vifs);
-	WARN_ON(vifs && n_vifs != 1);
+	WARN_ON(vifs && !n_vifs);
 
 	/* FIXME: Sort of an optimization and a workaround. Peers and vifs are
 	 * on a linked list now. Doing a lookup peer -> vif -> chanctx for each
@@ -8248,6 +8293,8 @@ int ath10k_mac_register(struct ath10k *ar)
 	ar->hw->wiphy->cipher_suites = cipher_suites;
 	ar->hw->wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
 
+	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = ieee80211_register_hw(ar->hw);
 	if (ret) {
 		ath10k_err(ar, "failed to register ieee80211: %d\n", ret);
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 6094372307aa..1e9806f57ee4 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -720,14 +720,16 @@ void ath10k_pci_disable_and_clear_legacy_irq(struct ath10k *ar)
 {
 	/* IMPORTANT: INTR_CLR register has to be set after
 	 * INTR_ENABLE is set to 0, otherwise interrupt can not be
-	 * really cleared. */
+	 * really cleared.
+	 */
 	ath10k_pci_write32(ar, SOC_CORE_BASE_ADDRESS + PCIE_INTR_ENABLE_ADDRESS,
 			   0);
 	ath10k_pci_write32(ar, SOC_CORE_BASE_ADDRESS + PCIE_INTR_CLR_ADDRESS,
 			   PCIE_INTR_FIRMWARE_MASK | PCIE_INTR_CE_MASK_ALL);
 
 	/* IMPORTANT: this extra read transaction is required to
-	 * flush the posted write buffer. */
+	 * flush the posted write buffer.
+	 */
 	(void)ath10k_pci_read32(ar, SOC_CORE_BASE_ADDRESS +
 				PCIE_INTR_ENABLE_ADDRESS);
 }
@@ -739,7 +741,8 @@ void ath10k_pci_enable_legacy_irq(struct ath10k *ar)
 			   PCIE_INTR_FIRMWARE_MASK | PCIE_INTR_CE_MASK_ALL);
 
 	/* IMPORTANT: this extra read transaction is required to
-	 * flush the posted write buffer. */
+	 * flush the posted write buffer.
+	 */
 	(void)ath10k_pci_read32(ar, SOC_CORE_BASE_ADDRESS +
 				PCIE_INTR_ENABLE_ADDRESS);
 }
@@ -970,12 +973,6 @@ static int ath10k_pci_diag_read_mem(struct ath10k *ar, u32 address, void *data,
 		}
 
 		remaining_bytes -= nbytes;
-
-		if (ret) {
-			ath10k_warn(ar, "failed to read diag value at 0x%x: %d\n",
-				    address, ret);
-			break;
-		}
 		memcpy(data, data_buf, nbytes);
 
 		address += nbytes;
@@ -2914,7 +2911,8 @@ static int ath10k_pci_init_irq(struct ath10k *ar)
 	 * host won't know when target writes BAR to CORE_CTRL.
 	 * This write might get lost if target has NOT written BAR.
 	 * For now, fix the race by repeating the write in below
-	 * synchronization checking. */
+	 * synchronization checking.
+	 */
 	ar_pci->oper_irq_mode = ATH10K_PCI_IRQ_LEGACY;
 
 	ath10k_pci_write32(ar, SOC_CORE_BASE_ADDRESS + PCIE_INTR_ENABLE_ADDRESS,
@@ -3430,6 +3428,7 @@ MODULE_FIRMWARE(QCA6174_HW_2_1_FW_DIR "/" ATH10K_BOARD_API2_FILE);
 /* QCA6174 3.1 firmware files */
 MODULE_FIRMWARE(QCA6174_HW_3_0_FW_DIR "/" ATH10K_FW_API4_FILE);
 MODULE_FIRMWARE(QCA6174_HW_3_0_FW_DIR "/" ATH10K_FW_API5_FILE);
+MODULE_FIRMWARE(QCA6174_HW_3_0_FW_DIR "/" ATH10K_FW_API6_FILE);
 MODULE_FIRMWARE(QCA6174_HW_3_0_FW_DIR "/" QCA6174_HW_3_0_BOARD_DATA_FILE);
 MODULE_FIRMWARE(QCA6174_HW_3_0_FW_DIR "/" ATH10K_BOARD_API2_FILE);
 
diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h
index 034e7a54c5b2..c1022a1cf855 100644
--- a/drivers/net/wireless/ath/ath10k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath10k/rx_desc.h
@@ -439,19 +439,22 @@ struct rx_mpdu_end {
  *  c) A-MSDU subframe header (14 bytes) if appliable
  *  d) LLC/SNAP (RFC1042, 8 bytes)
  *
- * In case of A-MSDU only first frame in sequence contains (a) and (b). */
+ * In case of A-MSDU only first frame in sequence contains (a) and (b).
+ */
 enum rx_msdu_decap_format {
 	RX_MSDU_DECAP_RAW = 0,
 
 	/* Note: QoS frames are reported as non-QoS. The rx_hdr_status in
-	 * htt_rx_desc contains the original decapped 802.11 header. */
+	 * htt_rx_desc contains the original decapped 802.11 header.
+	 */
 	RX_MSDU_DECAP_NATIVE_WIFI = 1,
 
 	/* Payload contains an ethernet header (struct ethhdr). */
 	RX_MSDU_DECAP_ETHERNET2_DIX = 2,
 
 	/* Payload contains two 48-bit addresses and 2-byte length (14 bytes
-	 * total), followed by an RFC1042 header (8 bytes). */
+	 * total), followed by an RFC1042 header (8 bytes).
+	 */
 	RX_MSDU_DECAP_8023_SNAP_LLC = 3
 };
 
@@ -867,7 +870,7 @@ struct rx_ppdu_start {
  *
  * reserved_9
  *		Reserved: HW should fill with 0, FW should ignore.
-*/
+ */
 
 #define RX_PPDU_END_FLAGS_PHY_ERR             (1 << 0)
 #define RX_PPDU_END_FLAGS_RX_LOCATION         (1 << 1)
@@ -1207,7 +1210,7 @@ struct rx_ppdu_end {
  *		Every time HW sets this bit in memory FW/SW must clear this
  *		bit in memory.  FW will initialize all the ppdu_done dword
  *		to 0.
-*/
+ */
 
 #define FW_RX_DESC_INFO0_DISCARD  (1 << 0)
 #define FW_RX_DESC_INFO0_FORWARD  (1 << 1)
diff --git a/drivers/net/wireless/ath/ath10k/spectral.c b/drivers/net/wireless/ath/ath10k/spectral.c
index c061d6958bd1..dd9cc0939ea8 100644
--- a/drivers/net/wireless/ath/ath10k/spectral.c
+++ b/drivers/net/wireless/ath/ath10k/spectral.c
@@ -56,6 +56,21 @@ static uint8_t get_max_exp(s8 max_index, u16 max_magnitude, size_t bin_len,
 	return max_exp;
 }
 
+static inline size_t ath10k_spectral_fix_bin_size(struct ath10k *ar,
+						  size_t bin_len)
+{
+	/* some chipsets reports bin size as 2^n bytes + 'm' bytes in
+	 * report mode 2. First 2^n bytes carries inband tones and last
+	 * 'm' bytes carries band edge detection data mainly used in
+	 * radar detection purpose. Strip last 'm' bytes to make bin size
+	 * as a valid one. 'm' can take possible values of 4, 12.
+	 */
+	if (!is_power_of_2(bin_len))
+		bin_len -= ar->hw_params.spectral_bin_discard;
+
+	return bin_len;
+}
+
 int ath10k_spectral_process_fft(struct ath10k *ar,
 				struct wmi_phyerr_ev_arg *phyerr,
 				const struct phyerr_fft_report *fftr,
@@ -70,18 +85,11 @@ int ath10k_spectral_process_fft(struct ath10k *ar,
 
 	fft_sample = (struct fft_sample_ath10k *)&buf;
 
+	bin_len = ath10k_spectral_fix_bin_size(ar, bin_len);
+
 	if (bin_len < 64 || bin_len > SPECTRAL_ATH10K_MAX_NUM_BINS)
 		return -EINVAL;
 
-	/* qca99x0 reports bin size as 68 bytes (64 bytes + 4 bytes) in
-	 * report mode 2. First 64 bytes carries inband tones (-32 to +31)
-	 * and last 4 byte carries band edge detection data (+32) mainly
-	 * used in radar detection purpose. Strip last 4 byte to make bin
-	 * size is valid one.
-	 */
-	if (bin_len == 68)
-		bin_len -= 4;
-
 	reg0 = __le32_to_cpu(fftr->reg0);
 	reg1 = __le32_to_cpu(fftr->reg1);
 
@@ -536,15 +544,15 @@ int ath10k_spectral_create(struct ath10k *ar)
 						     1140, 2500,
 						     &rfs_spec_scan_cb, NULL);
 	debugfs_create_file("spectral_scan_ctl",
-			    S_IRUSR | S_IWUSR,
+			    0600,
 			    ar->debug.debugfs_phy, ar,
 			    &fops_spec_scan_ctl);
 	debugfs_create_file("spectral_count",
-			    S_IRUSR | S_IWUSR,
+			    0600,
 			    ar->debug.debugfs_phy, ar,
 			    &fops_spectral_count);
 	debugfs_create_file("spectral_bins",
-			    S_IRUSR | S_IWUSR,
+			    0600,
 			    ar->debug.debugfs_phy, ar,
 			    &fops_spectral_bins);
 
diff --git a/drivers/net/wireless/ath/ath10k/targaddrs.h b/drivers/net/wireless/ath/ath10k/targaddrs.h
index a47cab44d9c8..cbac9e4252d6 100644
--- a/drivers/net/wireless/ath/ath10k/targaddrs.h
+++ b/drivers/net/wireless/ath/ath10k/targaddrs.h
@@ -268,13 +268,13 @@ struct host_interest {
 #define HI_OPTION_FW_BRIDGE_SHIFT 0x04
 
 /*
-Fw Mode/SubMode Mask
-|-----------------------------------------------------------------------------|
-|  SUB   |   SUB   |   SUB   |  SUB    |         |         |         |        |
-|MODE[3] | MODE[2] | MODE[1] | MODE[0] | MODE[3] | MODE[2] | MODE[1] | MODE[0]|
-|  (2)   |   (2)   |   (2)   |   (2)   |   (2)   |   (2)   |   (2)   |   (2)  |
-|-----------------------------------------------------------------------------|
-*/
+ * Fw Mode/SubMode Mask
+ *-----------------------------------------------------------------------------
+ *  SUB   |   SUB   |   SUB   |  SUB    |         |         |         |
+ *MODE[3] | MODE[2] | MODE[1] | MODE[0] | MODE[3] | MODE[2] | MODE[1] | MODE[0]
+ *  (2)   |   (2)   |   (2)   |   (2)   |   (2)   |   (2)   |   (2)   |   (2)
+ *-----------------------------------------------------------------------------
+ */
 #define HI_OPTION_FW_MODE_BITS         0x2
 #define HI_OPTION_FW_MODE_MASK         0x3
 #define HI_OPTION_FW_MODE_SHIFT        0xC
@@ -428,8 +428,9 @@ Fw Mode/SubMode Mask
 #define HI_PWR_SAVE_LPL_ENABLED   0x1
 /*b1-b3 reserved*/
 /*b4-b5 : dev0 LPL type : 0 - none
-			  1- Reduce Pwr Search
-			  2- Reduce Pwr Listen*/
+ *			  1- Reduce Pwr Search
+ *			  2- Reduce Pwr Listen
+ */
 /*b6-b7 : dev1 LPL type and so on for Max 8 devices*/
 #define HI_PWR_SAVE_LPL_DEV0_LSB   4
 #define HI_PWR_SAVE_LPL_DEV_MASK   0x3
diff --git a/drivers/net/wireless/ath/ath10k/testmode.c b/drivers/net/wireless/ath/ath10k/testmode.c
index 8bb36c18a749..d8564624415c 100644
--- a/drivers/net/wireless/ath/ath10k/testmode.c
+++ b/drivers/net/wireless/ath/ath10k/testmode.c
@@ -420,8 +420,8 @@ int ath10k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct nlattr *tb[ATH10K_TM_ATTR_MAX + 1];
 	int ret;
 
-	ret = nla_parse(tb, ATH10K_TM_ATTR_MAX, data, len,
-			ath10k_tm_policy);
+	ret = nla_parse(tb, ATH10K_TM_ATTR_MAX, data, len, ath10k_tm_policy,
+			NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/ath/ath10k/thermal.c b/drivers/net/wireless/ath/ath10k/thermal.c
index 0a47269be289..87948aff1bd5 100644
--- a/drivers/net/wireless/ath/ath10k/thermal.c
+++ b/drivers/net/wireless/ath/ath10k/thermal.c
@@ -124,7 +124,7 @@ void ath10k_thermal_event_temperature(struct ath10k *ar, int temperature)
 	complete(&ar->thermal.wmi_sync);
 }
 
-static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, ath10k_thermal_show_temp,
+static SENSOR_DEVICE_ATTR(temp1_input, 0444, ath10k_thermal_show_temp,
 			  NULL, 0);
 
 static struct attribute *ath10k_hwmon_attrs[] = {
@@ -191,7 +191,8 @@ int ath10k_thermal_register(struct ath10k *ar)
 		return 0;
 
 	/* Avoid linking error on devm_hwmon_device_register_with_groups, I
-	 * guess linux/hwmon.h is missing proper stubs. */
+	 * guess linux/hwmon.h is missing proper stubs.
+	 */
 	if (!IS_REACHABLE(CONFIG_HWMON))
 		return 0;
 
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 9852c5d51139..d4986f626c35 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -34,7 +34,8 @@ static void ath10k_report_offchan_tx(struct ath10k *ar, struct sk_buff *skb)
 	/* If the original wait_for_completion() timed out before
 	 * {data,mgmt}_tx_completed() was called then we could complete
 	 * offchan_tx_completed for a different skb. Prevent this by using
-	 * offchan_tx_skb. */
+	 * offchan_tx_skb.
+	 */
 	spin_lock_bh(&ar->data_lock);
 	if (ar->offchan_tx_skb != skb) {
 		ath10k_warn(ar, "completed old offchannel frame\n");
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index c7956e181f80..2fc3f24ff1ca 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -390,7 +390,8 @@ ath10k_wmi_mgmt_tx(struct ath10k *ar, struct sk_buff *msdu)
 		return ret;
 
 	/* FIXME There's no ACK event for Management Tx. This probably
-	 * shouldn't be called here either. */
+	 * shouldn't be called here either.
+	 */
 	info->flags |= IEEE80211_TX_STAT_ACK;
 	ieee80211_tx_status_irqsafe(ar->hw, msdu);
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 2f1743e60fa1..6afc8d27f0d5 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -3210,7 +3210,8 @@ static void ath10k_wmi_update_tim(struct ath10k *ar,
 	tim_len = tim_info->tim_len ? __le32_to_cpu(tim_info->tim_len) : 1;
 
 	/* if next SWBA has no tim_changed the tim_bitmap is garbage.
-	 * we must copy the bitmap upon change and reuse it later */
+	 * we must copy the bitmap upon change and reuse it later
+	 */
 	if (__le32_to_cpu(tim_info->tim_changed)) {
 		int i;
 
@@ -3529,7 +3530,8 @@ void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 		 * before telling mac80211 to decrement CSA counter
 		 *
 		 * Once CSA counter is completed stop sending beacons until
-		 * actual channel switch is done */
+		 * actual channel switch is done
+		 */
 		if (arvif->vif->csa_active &&
 		    ieee80211_csa_is_complete(arvif->vif)) {
 			ieee80211_csa_finish(arvif->vif);
@@ -3643,6 +3645,11 @@ static void ath10k_dfs_radar_report(struct ath10k *ar,
 
 	spin_lock_bh(&ar->data_lock);
 	ch = ar->rx_channel;
+
+	/* fetch target operating channel during channel change */
+	if (!ch)
+		ch = ar->tgt_oper_chan;
+
 	spin_unlock_bh(&ar->data_lock);
 
 	if (!ch) {
@@ -3686,7 +3693,8 @@ radar_detected:
 	ATH10K_DFS_STAT_INC(ar, radar_detected);
 
 	/* Control radar events reporting in debugfs file
-	   dfs_block_radar_events */
+	 * dfs_block_radar_events
+	 */
 	if (ar->dfs_block_radar_events) {
 		ath10k_info(ar, "DFS Radar detected, but ignored as requested\n");
 		return;
@@ -4593,6 +4601,8 @@ ath10k_wmi_main_op_pull_svc_rdy_ev(struct ath10k *ar, struct sk_buff *skb,
 	arg->phy_capab = ev->phy_capability;
 	arg->num_rf_chains = ev->num_rf_chains;
 	arg->eeprom_rd = ev->hal_reg_capabilities.eeprom_rd;
+	arg->low_5ghz_chan = ev->hal_reg_capabilities.low_5ghz_chan;
+	arg->high_5ghz_chan = ev->hal_reg_capabilities.high_5ghz_chan;
 	arg->num_mem_reqs = ev->num_mem_reqs;
 	arg->service_map = ev->wmi_service_bitmap;
 	arg->service_map_len = sizeof(ev->wmi_service_bitmap);
@@ -4629,6 +4639,8 @@ ath10k_wmi_10x_op_pull_svc_rdy_ev(struct ath10k *ar, struct sk_buff *skb,
 	arg->phy_capab = ev->phy_capability;
 	arg->num_rf_chains = ev->num_rf_chains;
 	arg->eeprom_rd = ev->hal_reg_capabilities.eeprom_rd;
+	arg->low_5ghz_chan = ev->hal_reg_capabilities.low_5ghz_chan;
+	arg->high_5ghz_chan = ev->hal_reg_capabilities.high_5ghz_chan;
 	arg->num_mem_reqs = ev->num_mem_reqs;
 	arg->service_map = ev->wmi_service_bitmap;
 	arg->service_map_len = sizeof(ev->wmi_service_bitmap);
@@ -4682,6 +4694,8 @@ static void ath10k_wmi_event_service_ready_work(struct work_struct *work)
 	ar->phy_capability = __le32_to_cpu(arg.phy_capab);
 	ar->num_rf_chains = __le32_to_cpu(arg.num_rf_chains);
 	ar->hw_eeprom_rd = __le32_to_cpu(arg.eeprom_rd);
+	ar->low_5ghz_chan = __le32_to_cpu(arg.low_5ghz_chan);
+	ar->high_5ghz_chan = __le32_to_cpu(arg.high_5ghz_chan);
 
 	ath10k_dbg_dump(ar, ATH10K_DBG_WMI, NULL, "wmi svc: ",
 			arg.service_map, arg.service_map_len);
@@ -4758,9 +4772,10 @@ static void ath10k_wmi_event_service_ready_work(struct work_struct *work)
 				num_units = ar->max_num_peers + 1;
 		} else if (num_unit_info & NUM_UNITS_IS_NUM_PEERS) {
 			/* number of units to allocate is number of
-			 * peers, 1 extra for self peer on target */
-			/* this needs to be tied, host and target
-			 * can get out of sync */
+			 * peers, 1 extra for self peer on target
+			 * this needs to be tied, host and target
+			 * can get out of sync
+			 */
 			num_units = ar->max_num_peers + 1;
 		} else if (num_unit_info & NUM_UNITS_IS_NUM_VDEVS) {
 			num_units = ar->max_num_vdevs + 1;
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 386aa51435f1..1b4865a55595 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -1038,7 +1038,8 @@ enum wmi_cmd_id {
 	WMI_STA_UAPSD_AUTO_TRIG_CMDID,
 
 	/* STA Keep alive parameter configuration,
-	   Requires WMI_SERVICE_STA_KEEP_ALIVE */
+	 * Requires WMI_SERVICE_STA_KEEP_ALIVE
+	 */
 	WMI_STA_KEEPALIVE_CMD,
 
 	/* misc command group */
@@ -1774,7 +1775,8 @@ static inline const char *ath10k_wmi_phymode_str(enum wmi_phy_mode mode)
 		break;
 
 		/* no default handler to allow compiler to check that the
-		 * enum is fully handled */
+		 * enum is fully handled
+		 */
 	};
 
 	return "<unknown>";
@@ -2974,7 +2976,8 @@ struct wmi_start_scan_arg {
 /* When set, DFS channels will not be scanned */
 #define WMI_SCAN_BYPASS_DFS_CHN 0x40
 /* Different FW scan engine may choose to bail out on errors.
- * Allow the driver to have influence over that. */
+ * Allow the driver to have influence over that.
+ */
 #define WMI_SCAN_CONTINUE_ON_ERROR 0x80
 
 /* WMI_SCAN_CLASS_MASK must be the same value as IEEE80211_SCAN_CLASS_MASK */
@@ -3182,7 +3185,7 @@ struct wmi_10_4_phyerr_event {
 
 struct phyerr_radar_report {
 	__le32 reg0; /* RADAR_REPORT_REG0_* */
-	__le32 reg1; /* REDAR_REPORT_REG1_* */
+	__le32 reg1; /* RADAR_REPORT_REG1_* */
 } __packed;
 
 #define RADAR_REPORT_REG0_PULSE_IS_CHIRP_MASK		0x80000000
@@ -4447,14 +4450,16 @@ enum wmi_vdev_subtype_10_4 {
 /* values for vdev_start_request flags */
 /*
  * Indicates that AP VDEV uses hidden ssid. only valid for
- *  AP/GO */
+ *  AP/GO
+ */
 #define WMI_VDEV_START_HIDDEN_SSID  (1 << 0)
 /*
  * Indicates if robust management frame/management frame
  *  protection is enabled. For GO/AP vdevs, it indicates that
  *  it may support station/client associations with RMF enabled.
  *  For STA/client vdevs, it indicates that sta will
- *  associate with AP with RMF enabled. */
+ *  associate with AP with RMF enabled.
+ */
 #define WMI_VDEV_START_PMF_ENABLED  (1 << 1)
 
 struct wmi_p2p_noa_descriptor {
@@ -4814,7 +4819,8 @@ enum wmi_vdev_param {
 	 * An associated STA is considered unresponsive if there is no recent
 	 * TX/RX activity and downlink frames are buffered for it. Once a STA
 	 * exceeds the maximum unresponsive time, the AP will send a
-	 * WMI_STA_KICKOUT event to the host so the STA can be deleted. */
+	 * WMI_STA_KICKOUT event to the host so the STA can be deleted.
+	 */
 	WMI_VDEV_PARAM_AP_KEEPALIVE_MAX_UNRESPONSIVE_TIME_SECS,
 
 	/* Enable NAWDS : MCAST INSPECT Enable, NAWDS Flag set */
@@ -4941,7 +4947,8 @@ enum wmi_10x_vdev_param {
 	 * An associated STA is considered unresponsive if there is no recent
 	 * TX/RX activity and downlink frames are buffered for it. Once a STA
 	 * exceeds the maximum unresponsive time, the AP will send a
-	 * WMI_10X_STA_KICKOUT event to the host so the STA can be deleted. */
+	 * WMI_10X_STA_KICKOUT event to the host so the STA can be deleted.
+	 */
 	WMI_10X_VDEV_PARAM_AP_KEEPALIVE_MAX_UNRESPONSIVE_TIME_SECS,
 
 	/* Enable NAWDS : MCAST INSPECT Enable, NAWDS Flag set */
@@ -5605,12 +5612,14 @@ struct wmi_tim_info_arg {
 
 struct wmi_p2p_noa_info {
 	/* Bit 0 - Flag to indicate an update in NOA schedule
-	   Bits 7-1 - Reserved */
+	 * Bits 7-1 - Reserved
+	 */
 	u8 changed;
 	/* NOA index */
 	u8 index;
 	/* Bit 0 - Opp PS state of the AP
-	   Bits 1-7 - Ctwindow in TUs */
+	 * Bits 1-7 - Ctwindow in TUs
+	 */
 	u8 ctwindow_oppps;
 	/* Number of NOA descriptors */
 	u8 num_descriptors;
@@ -6000,7 +6009,8 @@ struct wmi_main_peer_assoc_complete_cmd {
 	struct wmi_common_peer_assoc_complete_cmd cmd;
 
 	/* HT Operation Element of the peer. Five bytes packed in 2
-	 *  INT32 array and filled from lsb to msb. */
+	 *  INT32 array and filled from lsb to msb.
+	 */
 	__le32 peer_ht_info[2];
 } __packed;
 
@@ -6335,6 +6345,8 @@ struct wmi_svc_rdy_ev_arg {
 	__le32 num_rf_chains;
 	__le32 eeprom_rd;
 	__le32 num_mem_reqs;
+	__le32 low_5ghz_chan;
+	__le32 high_5ghz_chan;
 	const __le32 *service_map;
 	size_t service_map_len;
 	const struct wlan_host_mem_req *mem_reqs[WMI_MAX_MEM_REQS];
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index d98fd421c7ec..527afcf39246 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -1414,10 +1414,10 @@ ath5k_receive_frame(struct ath5k_hw *ah, struct sk_buff *skb,
 	rxs->flag |= ath5k_rx_decrypted(ah, skb, rs);
 	switch (ah->ah_bwmode) {
 	case AR5K_BWMODE_5MHZ:
-		rxs->flag |= RX_FLAG_5MHZ;
+		rxs->bw = RATE_INFO_BW_5;
 		break;
 	case AR5K_BWMODE_10MHZ:
-		rxs->flag |= RX_FLAG_10MHZ;
+		rxs->bw = RATE_INFO_BW_10;
 		break;
 	default:
 		break;
@@ -1425,7 +1425,7 @@ ath5k_receive_frame(struct ath5k_hw *ah, struct sk_buff *skb,
 
 	if (rs->rs_rate ==
 	    ah->sbands[ah->curchan->band].bitrates[rxs->rate_idx].hw_value_short)
-		rxs->flag |= RX_FLAG_SHORTPRE;
+		rxs->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	trace_ath5k_rx(ah, skb);
 
@@ -2564,6 +2564,8 @@ ath5k_init_ah(struct ath5k_hw *ah, const struct ath_bus_ops *bus_ops)
 
 	hw->extra_tx_headroom = 2;
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	/*
 	 * Mark the device as detached to avoid processing
 	 * interrupts until setup is complete.
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 363b30a549c2..414b5b596efc 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -102,10 +102,8 @@ static struct ieee80211_channel ath6kl_2ghz_channels[] = {
 };
 
 static struct ieee80211_channel ath6kl_5ghz_a_channels[] = {
-	CHAN5G(34, 0), CHAN5G(36, 0),
-	CHAN5G(38, 0), CHAN5G(40, 0),
-	CHAN5G(42, 0), CHAN5G(44, 0),
-	CHAN5G(46, 0), CHAN5G(48, 0),
+	CHAN5G(36, 0), CHAN5G(40, 0),
+	CHAN5G(44, 0), CHAN5G(48, 0),
 	CHAN5G(52, 0), CHAN5G(56, 0),
 	CHAN5G(60, 0), CHAN5G(64, 0),
 	CHAN5G(100, 0), CHAN5G(104, 0),
@@ -171,7 +169,7 @@ static void ath6kl_cfg80211_sscan_disable(struct ath6kl_vif *vif)
 	if (!stopped)
 		return;
 
-	cfg80211_sched_scan_stopped(ar->wiphy);
+	cfg80211_sched_scan_stopped(ar->wiphy, 0);
 }
 
 static int ath6kl_set_wpa_version(struct ath6kl_vif *vif,
@@ -808,9 +806,15 @@ void ath6kl_cfg80211_connect_event(struct ath6kl_vif *vif, u16 channel,
 					WLAN_STATUS_SUCCESS, GFP_KERNEL);
 		cfg80211_put_bss(ar->wiphy, bss);
 	} else if (vif->sme_state == SME_CONNECTED) {
+		struct cfg80211_roam_info roam_info = {
+			.bss = bss,
+			.req_ie = assoc_req_ie,
+			.req_ie_len = assoc_req_len,
+			.resp_ie = assoc_resp_ie,
+			.resp_ie_len = assoc_resp_len,
+		};
 		/* inform roam event to cfg80211 */
-		cfg80211_roamed_bss(vif->ndev, bss, assoc_req_ie, assoc_req_len,
-				    assoc_resp_ie, assoc_resp_len, GFP_KERNEL);
+		cfg80211_roamed(vif->ndev, &roam_info, GFP_KERNEL);
 	}
 }
 
@@ -1505,7 +1509,6 @@ static struct wireless_dev *ath6kl_cfg80211_add_iface(struct wiphy *wiphy,
 						      const char *name,
 						      unsigned char name_assign_type,
 						      enum nl80211_iftype type,
-						      u32 *flags,
 						      struct vif_params *params)
 {
 	struct ath6kl *ar = wiphy_priv(wiphy);
@@ -1552,7 +1555,7 @@ static int ath6kl_cfg80211_del_iface(struct wiphy *wiphy,
 
 static int ath6kl_cfg80211_change_iface(struct wiphy *wiphy,
 					struct net_device *ndev,
-					enum nl80211_iftype type, u32 *flags,
+					enum nl80211_iftype type,
 					struct vif_params *params)
 {
 	struct ath6kl_vif *vif = netdev_priv(ndev);
@@ -3355,7 +3358,7 @@ static int ath6kl_cfg80211_sscan_start(struct wiphy *wiphy,
 }
 
 static int ath6kl_cfg80211_sscan_stop(struct wiphy *wiphy,
-				      struct net_device *dev)
+				      struct net_device *dev, u64 reqid)
 {
 	struct ath6kl_vif *vif = netdev_priv(dev);
 	bool stopped;
@@ -3976,7 +3979,7 @@ int ath6kl_cfg80211_init(struct ath6kl *ar)
 			    WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD;
 
 	if (test_bit(ATH6KL_FW_CAPABILITY_SCHED_SCAN_V2, ar->fw_capabilities))
-		ar->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
+		ar->wiphy->max_sched_scan_reqs = 1;
 
 	if (test_bit(ATH6KL_FW_CAPABILITY_INACTIVITY_TIMEOUT,
 		     ar->fw_capabilities))
diff --git a/drivers/net/wireless/ath/ath6kl/debug.h b/drivers/net/wireless/ath/ath6kl/debug.h
index 0614393dd7ae..94297572914f 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.h
+++ b/drivers/net/wireless/ath/ath6kl/debug.h
@@ -63,6 +63,7 @@ int ath6kl_read_tgt_stats(struct ath6kl *ar, struct ath6kl_vif *vif);
 
 #ifdef CONFIG_ATH6KL_DEBUG
 
+__printf(2, 3)
 void ath6kl_dbg(enum ATH6K_DEBUG_MASK mask, const char *fmt, ...);
 void ath6kl_dbg_dump(enum ATH6K_DEBUG_MASK mask,
 		     const char *msg, const char *prefix,
@@ -83,6 +84,7 @@ int ath6kl_debug_init_fs(struct ath6kl *ar);
 void ath6kl_debug_cleanup(struct ath6kl *ar);
 
 #else
+__printf(2, 3)
 static inline void ath6kl_dbg(enum ATH6K_DEBUG_MASK dbg_mask,
 			      const char *fmt, ...)
 {
diff --git a/drivers/net/wireless/ath/ath6kl/htc_pipe.c b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
index ca1a18c86c0d..d127a08d60df 100644
--- a/drivers/net/wireless/ath/ath6kl/htc_pipe.c
+++ b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
@@ -995,7 +995,7 @@ static int ath6kl_htc_pipe_rx_complete(struct ath6kl *ar, struct sk_buff *skb,
 
 	if (netlen < (payload_len + HTC_HDR_LENGTH)) {
 		ath6kl_dbg(ATH6KL_DBG_HTC,
-			   "HTC Rx: insufficient length, got:%d expected =%u\n",
+			   "HTC Rx: insufficient length, got:%d expected =%zu\n",
 			   netlen, payload_len + HTC_HDR_LENGTH);
 		status = -EINVAL;
 		goto free_skb;
diff --git a/drivers/net/wireless/ath/ath6kl/testmode.c b/drivers/net/wireless/ath/ath6kl/testmode.c
index d67170ea1038..d8dcacda9add 100644
--- a/drivers/net/wireless/ath/ath6kl/testmode.c
+++ b/drivers/net/wireless/ath/ath6kl/testmode.c
@@ -74,8 +74,8 @@ int ath6kl_tm_cmd(struct wiphy *wiphy, struct wireless_dev *wdev,
 	int err, buf_len;
 	void *buf;
 
-	err = nla_parse(tb, ATH6KL_TM_ATTR_MAX, data, len,
-			ath6kl_tm_policy);
+	err = nla_parse(tb, ATH6KL_TM_ATTR_MAX, data, len, ath6kl_tm_policy,
+			NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index 84a6d12c3f8a..bfc20b45b806 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -1082,7 +1082,7 @@ void ath6kl_wmi_sscan_timer(unsigned long ptr)
 {
 	struct ath6kl_vif *vif = (struct ath6kl_vif *) ptr;
 
-	cfg80211_sched_scan_results(vif->ar->wiphy);
+	cfg80211_sched_scan_results(vif->ar->wiphy, 0);
 }
 
 static int ath6kl_wmi_bssinfo_event_rx(struct wmi *wmi, u8 *datap, int len,
@@ -1596,7 +1596,7 @@ static int ath6kl_wmi_txe_notify_event_rx(struct wmi *wmi, u8 *datap, int len,
 	rate = le32_to_cpu(ev->rate);
 	pkts = le32_to_cpu(ev->pkts);
 
-	ath6kl_dbg(ATH6KL_DBG_WMI, "TXE notify event: peer %pM rate %d% pkts %d intvl %ds\n",
+	ath6kl_dbg(ATH6KL_DBG_WMI, "TXE notify event: peer %pM rate %d%% pkts %d intvl %ds\n",
 		   vif->bssid, rate, pkts, vif->txe_intvl);
 
 	cfg80211_cqm_txe_notify(vif->ndev, vif->bssid, pkts,
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c
index cc5bb0a76baf..68fcbe03bce2 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c
@@ -494,7 +494,8 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs,
 
 	rxs->rs_status = 0;
 	rxs->rs_flags =  0;
-	rxs->flag =  0;
+	rxs->enc_flags = 0;
+	rxs->bw = RATE_INFO_BW_20;
 
 	rxs->rs_datalen = rxsp->status2 & AR_DataLen;
 	rxs->rs_tstamp =  rxsp->status3;
@@ -520,8 +521,8 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs,
 	rxs->rs_isaggr = (rxsp->status11 & AR_RxAggr) ? 1 : 0;
 	rxs->rs_moreaggr = (rxsp->status11 & AR_RxMoreAggr) ? 1 : 0;
 	rxs->rs_antenna = (MS(rxsp->status4, AR_RxAntenna) & 0x7);
-	rxs->flag  |= (rxsp->status4 & AR_GI) ? RX_FLAG_SHORT_GI : 0;
-	rxs->flag  |= (rxsp->status4 & AR_2040) ? RX_FLAG_40MHZ : 0;
+	rxs->enc_flags |= (rxsp->status4 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0;
+	rxs->enc_flags |= (rxsp->status4 & AR_2040) ? RX_ENC_FLAG_40MHZ : 0;
 
 	rxs->evm0 = rxsp->status6;
 	rxs->evm1 = rxsp->status7;
diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c
index 0f71146b781d..13ab6bc46775 100644
--- a/drivers/net/wireless/ath/ath9k/calib.c
+++ b/drivers/net/wireless/ath/ath9k/calib.c
@@ -254,7 +254,9 @@ int ath9k_hw_loadnf(struct ath_hw *ah, struct ath9k_channel *chan)
 			if ((i >= AR5416_MAX_CHAINS) && !IS_CHAN_HT40(chan))
 				continue;
 
-			if (h)
+			if (ah->nf_override)
+				nfval = ah->nf_override;
+			else if (h)
 				nfval = h[i].privNF;
 			else
 				nfval = default_nf;
@@ -348,6 +350,7 @@ int ath9k_hw_loadnf(struct ath_hw *ah, struct ath9k_channel *chan)
 
 	return 0;
 }
+EXPORT_SYMBOL(ath9k_hw_loadnf);
 
 
 static void ath9k_hw_nf_sanitize(struct ath_hw *ah, s16 *nf)
diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c
index 0ffa23a61568..5e77fe1f5b0d 100644
--- a/drivers/net/wireless/ath/ath9k/common-spectral.c
+++ b/drivers/net/wireless/ath/ath9k/common-spectral.c
@@ -742,6 +742,9 @@ void ath9k_cmn_spectral_scan_trigger(struct ath_common *common,
 		return;
 	}
 
+	if (!spec_priv->spec_config.enabled)
+		return;
+
 	ath_ps_ops(common)->wakeup(common);
 	rxfilter = ath9k_hw_getrxfilter(ah);
 	ath9k_hw_setrxfilter(ah, rxfilter |
diff --git a/drivers/net/wireless/ath/ath9k/common.c b/drivers/net/wireless/ath/ath9k/common.c
index b80e08b13b74..c67d0e08bd4c 100644
--- a/drivers/net/wireless/ath/ath9k/common.c
+++ b/drivers/net/wireless/ath/ath9k/common.c
@@ -181,14 +181,15 @@ int ath9k_cmn_process_rate(struct ath_common *common,
 	sband = hw->wiphy->bands[band];
 
 	if (IS_CHAN_QUARTER_RATE(ah->curchan))
-		rxs->flag |= RX_FLAG_5MHZ;
+		rxs->bw = RATE_INFO_BW_5;
 	else if (IS_CHAN_HALF_RATE(ah->curchan))
-		rxs->flag |= RX_FLAG_10MHZ;
+		rxs->bw = RATE_INFO_BW_10;
 
 	if (rx_stats->rs_rate & 0x80) {
 		/* HT rate */
-		rxs->flag |= RX_FLAG_HT;
-		rxs->flag |= rx_stats->flag;
+		rxs->encoding = RX_ENC_HT;
+		rxs->enc_flags |= rx_stats->enc_flags;
+		rxs->bw = rx_stats->bw;
 		rxs->rate_idx = rx_stats->rs_rate & 0x7f;
 		return 0;
 	}
@@ -199,7 +200,7 @@ int ath9k_cmn_process_rate(struct ath_common *common,
 			return 0;
 		}
 		if (sband->bitrates[i].hw_value_short == rx_stats->rs_rate) {
-			rxs->flag |= RX_FLAG_SHORTPRE;
+			rxs->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 			rxs->rate_idx = i;
 			return 0;
 		}
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 43930c336987..2e64977a8ab6 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -1191,6 +1191,65 @@ static const struct file_operations fops_tpc = {
 	.llseek = default_llseek,
 };
 
+static ssize_t read_file_nf_override(struct file *file,
+				     char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	struct ath_softc *sc = file->private_data;
+	struct ath_hw *ah = sc->sc_ah;
+	char buf[32];
+	unsigned int len;
+
+	if (ah->nf_override == 0)
+		len = sprintf(buf, "off\n");
+	else
+		len = sprintf(buf, "%d\n", ah->nf_override);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t write_file_nf_override(struct file *file,
+				      const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	struct ath_softc *sc = file->private_data;
+	struct ath_hw *ah = sc->sc_ah;
+	long val;
+	char buf[32];
+	ssize_t len;
+
+	len = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, user_buf, len))
+		return -EFAULT;
+
+	buf[len] = '\0';
+	if (strncmp("off", buf, 3) == 0)
+		val = 0;
+	else if (kstrtol(buf, 0, &val))
+		return -EINVAL;
+
+	if (val > 0)
+		return -EINVAL;
+
+	if (val < -120)
+		return -EINVAL;
+
+	ah->nf_override = val;
+
+	if (ah->curchan)
+		ath9k_hw_loadnf(ah, ah->curchan);
+
+	return count;
+}
+
+static const struct file_operations fops_nf_override = {
+	.read = read_file_nf_override,
+	.write = write_file_nf_override,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 /* Ethtool support for get-stats */
 
 #define AMKSTR(nm) #nm "_BE", #nm "_BK", #nm "_VI", #nm "_VO"
@@ -1402,5 +1461,8 @@ int ath9k_init_debug(struct ath_hw *ah)
 	debugfs_create_u16("airtime_flags", S_IRUSR | S_IWUSR,
 			   sc->debug.debugfs_phy, &sc->airtime_flags);
 
+	debugfs_create_file("nf_override", S_IRUSR | S_IWUSR,
+			    sc->debug.debugfs_phy, sc, &fops_nf_override);
+
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath9k/debug_sta.c b/drivers/net/wireless/ath/ath9k/debug_sta.c
index 524cbf13ca9c..efc692ee67d4 100644
--- a/drivers/net/wireless/ath/ath9k/debug_sta.c
+++ b/drivers/net/wireless/ath/ath9k/debug_sta.c
@@ -116,12 +116,12 @@ void ath_debug_rate_stats(struct ath_softc *sc,
 		if (rxs->rate_idx >= ARRAY_SIZE(rstats->ht_stats))
 			goto exit;
 
-		if (rxs->flag & RX_FLAG_40MHZ)
+		if ((rxs->bw == RATE_INFO_BW_40))
 			rstats->ht_stats[rxs->rate_idx].ht40_cnt++;
 		else
 			rstats->ht_stats[rxs->rate_idx].ht20_cnt++;
 
-		if (rxs->flag & RX_FLAG_SHORT_GI)
+		if (rxs->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			rstats->ht_stats[rxs->rate_idx].sgi_cnt++;
 		else
 			rstats->ht_stats[rxs->rate_idx].lgi_cnt++;
@@ -130,7 +130,7 @@ void ath_debug_rate_stats(struct ath_softc *sc,
 	}
 
 	if (IS_CCK_RATE(rs->rs_rate)) {
-		if (rxs->flag & RX_FLAG_SHORTPRE)
+		if (rxs->enc_flags & RX_ENC_FLAG_SHORTPRE)
 			rstats->cck_stats[rxs->rate_idx].cck_sp_cnt++;
 		else
 			rstats->cck_stats[rxs->rate_idx].cck_lp_cnt++;
diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index fb80ec86e53d..6ccf24814514 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -112,7 +112,7 @@ void ath9k_hw_usb_gen_fill_eeprom(struct ath_hw *ah, u16 *eep_data,
 static bool ath9k_hw_nvram_read_array(u16 *blob, size_t blob_size,
 				      off_t offset, u16 *data)
 {
-	if (offset > blob_size)
+	if (offset >= blob_size)
 		return false;
 
 	*data =  blob[offset];
diff --git a/drivers/net/wireless/ath/ath9k/eeprom.h b/drivers/net/wireless/ath/ath9k/eeprom.h
index 30bf722e33ed..31390af6c33e 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.h
+++ b/drivers/net/wireless/ath/ath9k/eeprom.h
@@ -106,7 +106,7 @@
 #define AR9285_RDEXT_DEFAULT    0x1F
 
 #define ATH9K_POW_SM(_r, _s)	(((_r) & 0x3f) << (_s))
-#define FREQ2FBIN(x, y)		((y) ? ((x) - 2300) : (((x) - 4800) / 5))
+#define FREQ2FBIN(x, y)		(u8)((y) ? ((x) - 2300) : (((x) - 4800) / 5))
 #define FBIN2FREQ(x, y)		((y) ? (2300 + x) : (4800 + 5 * x))
 #define ath9k_hw_use_flash(_ah)	(!(_ah->ah_flags & AH_USE_EEPROM))
 
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index de2d212f39ec..12aa8abbcba4 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -37,6 +37,7 @@ static struct usb_device_id ath9k_hif_usb_ids[] = {
 	{ USB_DEVICE(0x0cf3, 0xb002) }, /* Ubiquiti WifiStation */
 	{ USB_DEVICE(0x057c, 0x8403) }, /* AVM FRITZ!WLAN 11N v2 USB */
 	{ USB_DEVICE(0x0471, 0x209e) }, /* Philips (or NXP) PTA01 */
+	{ USB_DEVICE(0x1eda, 0x2315) }, /* AirTies */
 
 	{ USB_DEVICE(0x0cf3, 0x7015),
 	  .driver_info = AR9287_USB },  /* Atheros */
@@ -1219,6 +1220,9 @@ static int send_eject_command(struct usb_interface *interface)
 	u8 bulk_out_ep;
 	int r;
 
+	if (iface_desc->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
 	/* Find bulk out endpoint */
 	for (r = 1; r >= 0; r--) {
 		endpoint = &iface_desc->endpoint[r].desc;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index b65c1b661ade..defacc6c9c99 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -780,6 +780,8 @@ static void ath9k_set_hw_capab(struct ath9k_htc_priv *priv,
 	}
 
 	SET_IEEE80211_PERM_ADDR(hw, common->macaddr);
+
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 }
 
 static int ath9k_init_firmware_version(struct ath9k_htc_priv *priv)
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index f333ef1e3e7b..b38a586ea59a 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -929,11 +929,12 @@ void ath9k_host_rx_init(struct ath9k_htc_priv *priv)
 static inline void convert_htc_flag(struct ath_rx_status *rx_stats,
 				   struct ath_htc_rx_status *rxstatus)
 {
-	rx_stats->flag = 0;
+	rx_stats->enc_flags = 0;
+	rx_stats->bw = RATE_INFO_BW_20;
 	if (rxstatus->rs_flags & ATH9K_RX_2040)
-		rx_stats->flag |= RX_FLAG_40MHZ;
+		rx_stats->bw = RATE_INFO_BW_40;
 	if (rxstatus->rs_flags & ATH9K_RX_GI)
-		rx_stats->flag |= RX_FLAG_SHORT_GI;
+		rx_stats->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 }
 
 static void rx_status_htc_to_ath(struct ath_rx_status *rx_stats,
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 9cbca1229bac..4ac70827d142 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -803,6 +803,7 @@ struct ath_hw {
 	u32 rfkill_gpio;
 	u32 rfkill_polarity;
 	u32 ah_flags;
+	s16 nf_override;
 
 	bool reset_power_on;
 	bool htc_reset_init;
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index fa4b3cc1ba22..fd9a61834c17 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -955,6 +955,8 @@ static void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
 	ath9k_cmn_reload_chainmask(ah);
 
 	SET_IEEE80211_PERM_ADDR(hw, common->macaddr);
+
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 }
 
 int ath9k_init_device(u16 devid, struct ath_softc *sc,
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index d937c39b3a0b..6128c2bb23d8 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -535,7 +535,8 @@ int ath9k_hw_rxprocdesc(struct ath_hw *ah, struct ath_desc *ds,
 
 	rs->rs_status = 0;
 	rs->rs_flags = 0;
-	rs->flag = 0;
+	rs->enc_flags = 0;
+	rs->bw = RATE_INFO_BW_20;
 
 	rs->rs_datalen = ads.ds_rxstatus1 & AR_DataLen;
 	rs->rs_tstamp = ads.AR_RcvTimestamp;
@@ -577,15 +578,15 @@ int ath9k_hw_rxprocdesc(struct ath_hw *ah, struct ath_desc *ds,
 	rs->rs_antenna = MS(ads.ds_rxstatus3, AR_RxAntenna);
 
 	/* directly mapped flags for ieee80211_rx_status */
-	rs->flag |=
-		(ads.ds_rxstatus3 & AR_GI) ? RX_FLAG_SHORT_GI : 0;
-	rs->flag |=
-		(ads.ds_rxstatus3 & AR_2040) ? RX_FLAG_40MHZ : 0;
+	rs->enc_flags |=
+		(ads.ds_rxstatus3 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0;
+	rs->enc_flags |=
+		(ads.ds_rxstatus3 & AR_2040) ? RX_ENC_FLAG_40MHZ : 0;
 	if (AR_SREV_9280_20_OR_LATER(ah))
-		rs->flag |=
+		rs->enc_flags |=
 			(ads.ds_rxstatus3 & AR_STBC) ?
 				/* we can only Nss=1 STBC */
-				(1 << RX_FLAG_STBC_SHIFT) : 0;
+				(1 << RX_ENC_FLAG_STBC_SHIFT) : 0;
 
 	if (ads.ds_rxstatus8 & AR_PreDelimCRCErr)
 		rs->rs_flags |= ATH9K_RX_DELIM_CRC_PRE;
diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index 770fc11b41d1..fd6aa49adadf 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -16,6 +16,7 @@
 
 #ifndef MAC_H
 #define MAC_H
+#include <net/cfg80211.h>
 
 #define set11nTries(_series, _index) \
 	(SM((_series)[_index].Tries, AR_XmitDataTries##_index))
@@ -143,7 +144,8 @@ struct ath_rx_status {
 	u32 evm2;
 	u32 evm3;
 	u32 evm4;
-	u32 flag; /* see enum mac80211_rx_flags */
+	u16 enc_flags;
+	enum rate_info_bw bw;
 };
 
 struct ath_htc_rx_status {
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index aff473dfa10d..7b7627f85d3a 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -383,6 +383,11 @@ static const struct pci_device_id ath_pci_id_table[] = {
 			 0x10CF, /* Fujitsu */
 			 0x1783),
 	  .driver_data = ATH9K_PCI_WOW },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+			 0x0034,
+			 PCI_VENDOR_ID_DELL,
+			 0x020B),
+	  .driver_data = ATH9K_PCI_WOW },
 
 	/* Killer Wireless (2x2) */
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index d79837fe333f..2197aee2bb72 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -1037,11 +1037,11 @@ static void ath_rx_count_airtime(struct ath_softc *sc,
 
 	rxs = IEEE80211_SKB_RXCB(skb);
 
-	is_sgi = !!(rxs->flag & RX_FLAG_SHORT_GI);
-	is_40 = !!(rxs->flag & RX_FLAG_40MHZ);
-	is_sp = !!(rxs->flag & RX_FLAG_SHORTPRE);
+	is_sgi = !!(rxs->enc_flags & RX_ENC_FLAG_SHORT_GI);
+	is_40 = !!(rxs->bw == RATE_INFO_BW_40);
+	is_sp = !!(rxs->enc_flags & RX_ENC_FLAG_SHORTPRE);
 
-	if (!!(rxs->flag & RX_FLAG_HT)) {
+	if (!!(rxs->encoding == RX_ENC_HT)) {
 		/* MCS rates */
 
 		airtime += ath_pkt_duration(sc, rxs->rate_idx, len,
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index ffb22a04beeb..988c8857d78c 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -1874,6 +1874,8 @@ void *carl9170_alloc(size_t priv_size)
 	for (i = 0; i < ARRAY_SIZE(ar->noise); i++)
 		ar->noise[i] = -95; /* ATH_DEFAULT_NOISE_FLOOR */
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	return ar;
 
 err_nomem:
diff --git a/drivers/net/wireless/ath/carl9170/rx.c b/drivers/net/wireless/ath/carl9170/rx.c
index 0c34c8729dc6..b2166726b05d 100644
--- a/drivers/net/wireless/ath/carl9170/rx.c
+++ b/drivers/net/wireless/ath/carl9170/rx.c
@@ -358,7 +358,7 @@ static int carl9170_rx_mac_status(struct ar9170 *ar,
 	switch (mac->status & AR9170_RX_STATUS_MODULATION) {
 	case AR9170_RX_STATUS_MODULATION_CCK:
 		if (mac->status & AR9170_RX_STATUS_SHORT_PREAMBLE)
-			status->flag |= RX_FLAG_SHORTPRE;
+			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 		switch (head->plcp[0]) {
 		case AR9170_RX_PHY_RATE_CCK_1M:
 			status->rate_idx = 0;
@@ -423,12 +423,12 @@ static int carl9170_rx_mac_status(struct ar9170 *ar,
 
 	case AR9170_RX_STATUS_MODULATION_HT:
 		if (head->plcp[3] & 0x80)
-			status->flag |= RX_FLAG_40MHZ;
+			status->bw = RATE_INFO_BW_40;
 		if (head->plcp[6] & 0x80)
-			status->flag |= RX_FLAG_SHORT_GI;
+			status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 		status->rate_idx = clamp(0, 75, head->plcp[3] & 0x7f);
-		status->flag |= RX_FLAG_HT;
+		status->encoding = RX_ENC_HT;
 		break;
 
 	default:
diff --git a/drivers/net/wireless/ath/regd.c b/drivers/net/wireless/ath/regd.c
index 43afa83a9f0c..e25bfdf78c2e 100644
--- a/drivers/net/wireless/ath/regd.c
+++ b/drivers/net/wireless/ath/regd.c
@@ -254,8 +254,12 @@ bool ath_is_49ghz_allowed(u16 regdomain)
 EXPORT_SYMBOL(ath_is_49ghz_allowed);
 
 /* Frequency is one where radar detection is required */
-static bool ath_is_radar_freq(u16 center_freq)
+static bool ath_is_radar_freq(u16 center_freq,
+			      struct ath_regulatory *reg)
+
 {
+	if (reg->country_code == CTRY_INDIA)
+		return (center_freq >= 5500 && center_freq <= 5700);
 	return (center_freq >= 5260 && center_freq <= 5700);
 }
 
@@ -306,7 +310,7 @@ __ath_reg_apply_beaconing_flags(struct wiphy *wiphy,
 				enum nl80211_reg_initiator initiator,
 				struct ieee80211_channel *ch)
 {
-	if (ath_is_radar_freq(ch->center_freq) ||
+	if (ath_is_radar_freq(ch->center_freq, reg) ||
 	    (ch->flags & IEEE80211_CHAN_RADAR))
 		return;
 
@@ -395,8 +399,9 @@ ath_reg_apply_ir_flags(struct wiphy *wiphy,
 	}
 }
 
-/* Always apply Radar/DFS rules on freq range 5260 MHz - 5700 MHz */
-static void ath_reg_apply_radar_flags(struct wiphy *wiphy)
+/* Always apply Radar/DFS rules on freq range 5500 MHz - 5700 MHz */
+static void ath_reg_apply_radar_flags(struct wiphy *wiphy,
+				      struct ath_regulatory *reg)
 {
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_channel *ch;
@@ -409,7 +414,7 @@ static void ath_reg_apply_radar_flags(struct wiphy *wiphy)
 
 	for (i = 0; i < sband->n_channels; i++) {
 		ch = &sband->channels[i];
-		if (!ath_is_radar_freq(ch->center_freq))
+		if (!ath_is_radar_freq(ch->center_freq, reg))
 			continue;
 		/* We always enable radar detection/DFS on this
 		 * frequency range. Additionally we also apply on
@@ -506,7 +511,7 @@ void ath_reg_notifier_apply(struct wiphy *wiphy,
 	struct ath_common *common = container_of(reg, struct ath_common,
 						 regulatory);
 	/* We always apply this */
-	ath_reg_apply_radar_flags(wiphy);
+	ath_reg_apply_radar_flags(wiphy, reg);
 
 	/*
 	 * This would happen when we have sent a custom regulatory request
@@ -654,7 +659,7 @@ ath_regd_init_wiphy(struct ath_regulatory *reg,
 	}
 
 	wiphy_apply_custom_regulatory(wiphy, regd);
-	ath_reg_apply_radar_flags(wiphy);
+	ath_reg_apply_radar_flags(wiphy, reg);
 	ath_reg_apply_world_flags(wiphy, NL80211_REGDOM_SET_BY_DRIVER, reg);
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/wcn36xx/Kconfig b/drivers/net/wireless/ath/wcn36xx/Kconfig
index 4b83e87f0b94..20bf967a70b9 100644
--- a/drivers/net/wireless/ath/wcn36xx/Kconfig
+++ b/drivers/net/wireless/ath/wcn36xx/Kconfig
@@ -2,7 +2,7 @@ config WCN36XX
 	tristate "Qualcomm Atheros WCN3660/3680 support"
 	depends on MAC80211 && HAS_DMA
 	depends on QCOM_WCNSS_CTRL || QCOM_WCNSS_CTRL=n
-	depends on QCOM_SMD || QCOM_SMD=n
+	depends on RPMSG || RPMSG=n
 	---help---
 	  This module adds support for wireless adapters based on
 	  Qualcomm Atheros WCN3660 and WCN3680 mobile chipsets.
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 7a0c2e7da7f6..d5e993dc9b23 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -22,7 +22,7 @@
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/smem_state.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
 #include "wcn36xx.h"
@@ -337,10 +337,10 @@ out_smd_stop:
 	wcn36xx_smd_stop(wcn);
 out_free_smd_buf:
 	kfree(wcn->hal_buf);
-out_free_dxe_pool:
-	wcn36xx_dxe_free_mem_pools(wcn);
 out_free_dxe_ctl:
 	wcn36xx_dxe_free_ctl_blks(wcn);
+out_free_dxe_pool:
+	wcn36xx_dxe_free_mem_pools(wcn);
 out_smd_close:
 	wcn36xx_smd_close(wcn);
 out_err:
@@ -1112,6 +1112,9 @@ static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 	wcn->hw->sta_data_size = sizeof(struct wcn36xx_sta);
 	wcn->hw->vif_data_size = sizeof(struct wcn36xx_vif);
 
+	wiphy_ext_feature_set(wcn->hw->wiphy,
+			      NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	return ret;
 }
 
@@ -1218,15 +1221,13 @@ static int wcn36xx_probe(struct platform_device *pdev)
 
 	INIT_WORK(&wcn->scan_work, wcn36xx_hw_scan_worker);
 
-	wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process);
+	wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process, hw);
 	if (IS_ERR(wcn->smd_channel)) {
 		wcn36xx_err("failed to open WLAN_CTRL channel\n");
 		ret = PTR_ERR(wcn->smd_channel);
 		goto out_wq;
 	}
 
-	qcom_smd_set_drvdata(wcn->smd_channel, hw);
-
 	addr = of_get_property(pdev->dev.of_node, "local-mac-address", &ret);
 	if (addr && ret != ETH_ALEN) {
 		wcn36xx_err("invalid local-mac-address\n");
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 1c2966f7db7a..9c6590d5348a 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -19,7 +19,7 @@
 #include <linux/etherdevice.h>
 #include <linux/firmware.h>
 #include <linux/bitops.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include "smd.h"
 
 struct wcn36xx_cfg_val {
@@ -254,7 +254,7 @@ static int wcn36xx_smd_send_and_wait(struct wcn36xx *wcn, size_t len)
 
 	init_completion(&wcn->hal_rsp_compl);
 	start = jiffies;
-	ret = qcom_smd_send(wcn->smd_channel, wcn->hal_buf, len);
+	ret = rpmsg_send(wcn->smd_channel, wcn->hal_buf, len);
 	if (ret) {
 		wcn36xx_err("HAL TX failed\n");
 		goto out;
@@ -2205,11 +2205,11 @@ out:
 	return ret;
 }
 
-int wcn36xx_smd_rsp_process(struct qcom_smd_channel *channel,
-			    const void *buf, size_t len)
+int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
+			    void *buf, int len, void *priv, u32 addr)
 {
 	const struct wcn36xx_hal_msg_header *msg_header = buf;
-	struct ieee80211_hw *hw = qcom_smd_get_drvdata(channel);
+	struct ieee80211_hw *hw = priv;
 	struct wcn36xx *wcn = hw->priv;
 	struct wcn36xx_hal_ind_msg *msg_ind;
 	wcn36xx_dbg_dump(WCN36XX_DBG_SMD_DUMP, "SMD <<< ", buf, len);
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.h b/drivers/net/wireless/ath/wcn36xx/smd.h
index 8892ccd67b14..013fc9546f56 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.h
+++ b/drivers/net/wireless/ath/wcn36xx/smd.h
@@ -51,7 +51,7 @@ struct wcn36xx_hal_ind_msg {
 };
 
 struct wcn36xx;
-struct qcom_smd_channel;
+struct rpmsg_device;
 
 int wcn36xx_smd_open(struct wcn36xx *wcn);
 void wcn36xx_smd_close(struct wcn36xx *wcn);
@@ -129,8 +129,8 @@ int wcn36xx_smd_trigger_ba(struct wcn36xx *wcn, u8 sta_index);
 
 int wcn36xx_smd_update_cfg(struct wcn36xx *wcn, u32 cfg_id, u32 value);
 
-int wcn36xx_smd_rsp_process(struct qcom_smd_channel *channel,
-			    const void *buf, size_t len);
+int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
+			    void *buf, int len, void *priv, u32 addr);
 
 int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
 			    struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/ath/wcn36xx/txrx.c b/drivers/net/wireless/ath/wcn36xx/txrx.c
index 8c387a0a3c09..22304edc5948 100644
--- a/drivers/net/wireless/ath/wcn36xx/txrx.c
+++ b/drivers/net/wireless/ath/wcn36xx/txrx.c
@@ -68,7 +68,7 @@ int wcn36xx_rx_skb(struct wcn36xx *wcn, struct sk_buff *skb)
 		       RX_FLAG_MMIC_STRIPPED |
 		       RX_FLAG_DECRYPTED;
 
-	wcn36xx_dbg(WCN36XX_DBG_RX, "status.flags=%llx\n", status.flag);
+	wcn36xx_dbg(WCN36XX_DBG_RX, "status.flags=%x\n", status.flag);
 
 	memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status));
 
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 7423998ddeb4..b52b4da9a967 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -195,7 +195,7 @@ struct wcn36xx {
 	void __iomem		*ccu_base;
 	void __iomem		*dxe_base;
 
-	struct qcom_smd_channel *smd_channel;
+	struct rpmsg_endpoint	*smd_channel;
 
 	struct qcom_smem_state  *tx_enable_state;
 	unsigned		tx_enable_state_bit;
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 83155b5ddbfb..fdaa99c541ac 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -178,9 +178,8 @@ int wil_cid_fill_sinfo(struct wil6210_priv *wil, int cid,
 			BIT(NL80211_STA_INFO_RX_DROP_MISC) |
 			BIT(NL80211_STA_INFO_TX_FAILED);
 
-	sinfo->txrate.flags = RATE_INFO_FLAGS_MCS | RATE_INFO_FLAGS_60G;
+	sinfo->txrate.flags = RATE_INFO_FLAGS_60G;
 	sinfo->txrate.mcs = le16_to_cpu(reply.evt.bf_mcs);
-	sinfo->rxrate.flags = RATE_INFO_FLAGS_MCS | RATE_INFO_FLAGS_60G;
 	sinfo->rxrate.mcs = stats->last_mcs_rx;
 	sinfo->rx_bytes = stats->rx_bytes;
 	sinfo->rx_packets = stats->rx_packets;
@@ -256,7 +255,7 @@ static struct wireless_dev *
 wil_cfg80211_add_iface(struct wiphy *wiphy, const char *name,
 		       unsigned char name_assign_type,
 		       enum nl80211_iftype type,
-		       u32 *flags, struct vif_params *params)
+		       struct vif_params *params)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 	struct net_device *ndev = wil_to_ndev(wil);
@@ -307,7 +306,7 @@ static int wil_cfg80211_del_iface(struct wiphy *wiphy,
 
 static int wil_cfg80211_change_iface(struct wiphy *wiphy,
 				     struct net_device *ndev,
-				     enum nl80211_iftype type, u32 *flags,
+				     enum nl80211_iftype type,
 				     struct vif_params *params)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
@@ -334,11 +333,8 @@ static int wil_cfg80211_change_iface(struct wiphy *wiphy,
 	case NL80211_IFTYPE_P2P_GO:
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		if (flags)
-			wil->monitor_flags = *flags;
-		else
-			wil->monitor_flags = 0;
-
+		if (params->flags)
+			wil->monitor_flags = params->flags;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -390,22 +386,23 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 	}
 	mutex_unlock(&wil->p2p_wdev_mutex);
 
-	/* social scan on P2P_DEVICE is handled as p2p search */
-	if (wdev->iftype == NL80211_IFTYPE_P2P_DEVICE &&
-	    wil_p2p_is_social_scan(request)) {
+	if (wdev->iftype == NL80211_IFTYPE_P2P_DEVICE) {
 		if (!wil->p2p.p2p_dev_started) {
 			wil_err(wil, "P2P search requested on stopped P2P device\n");
 			rc = -EIO;
 			goto out;
 		}
-		wil->scan_request = request;
-		wil->radio_wdev = wdev;
-		rc = wil_p2p_search(wil, request);
-		if (rc) {
-			wil->radio_wdev = wil_to_wdev(wil);
-			wil->scan_request = NULL;
+		/* social scan on P2P_DEVICE is handled as p2p search */
+		if (wil_p2p_is_social_scan(request)) {
+			wil->scan_request = request;
+			wil->radio_wdev = wdev;
+			rc = wil_p2p_search(wil, request);
+			if (rc) {
+				wil->radio_wdev = wil_to_wdev(wil);
+				wil->scan_request = NULL;
+			}
+			goto out;
 		}
-		goto out;
 	}
 
 	(void)wil_p2p_stop_discovery(wil);
@@ -415,9 +412,9 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 
 	for (i = 0; i < request->n_ssids; i++) {
 		wil_dbg_misc(wil, "SSID[%d]", i);
-		print_hex_dump_bytes("SSID ", DUMP_PREFIX_OFFSET,
-				     request->ssids[i].ssid,
-				     request->ssids[i].ssid_len);
+		wil_hex_dump_misc("SSID ", DUMP_PREFIX_OFFSET, 16, 1,
+				  request->ssids[i].ssid,
+				  request->ssids[i].ssid_len, true);
 	}
 
 	if (request->n_ssids)
@@ -454,8 +451,8 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 	}
 
 	if (request->ie_len)
-		print_hex_dump_bytes("Scan IE ", DUMP_PREFIX_OFFSET,
-				     request->ie, request->ie_len);
+		wil_hex_dump_misc("Scan IE ", DUMP_PREFIX_OFFSET, 16, 1,
+				  request->ie, request->ie_len, true);
 	else
 		wil_dbg_misc(wil, "Scan has no IE's\n");
 
@@ -679,6 +676,8 @@ static int wil_cfg80211_connect(struct wiphy *wiphy,
 	rc = wmi_send(wil, WMI_CONNECT_CMDID, &conn, sizeof(conn));
 	if (rc == 0) {
 		netif_carrier_on(ndev);
+		wil6210_bus_request(wil, WIL_MAX_BUS_REQUEST_KBPS);
+		wil->bss = bss;
 		/* Connect can take lots of time */
 		mod_timer(&wil->connect_timer,
 			  jiffies + msecs_to_jiffies(2000));
@@ -707,6 +706,7 @@ static int wil_cfg80211_disconnect(struct wiphy *wiphy,
 		return 0;
 	}
 
+	wil->locally_generated_disc = true;
 	rc = wmi_call(wil, WMI_DISCONNECT_CMDID, NULL, 0,
 		      WMI_DISCONNECT_EVENTID, NULL, 0,
 		      WIL6210_DISCONNECT_TO_MS);
@@ -760,7 +760,8 @@ int wil_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	 */
 
 	wil_dbg_misc(wil, "mgmt_tx\n");
-	print_hex_dump_bytes("mgmt tx frame ", DUMP_PREFIX_OFFSET, buf, len);
+	wil_hex_dump_misc("mgmt tx frame ", DUMP_PREFIX_OFFSET, 16, 1, buf,
+			  len, true);
 
 	cmd = kmalloc(sizeof(*cmd) + len, GFP_KERNEL);
 	if (!cmd) {
@@ -1093,18 +1094,18 @@ static int _wil_cfg80211_merge_extra_ies(const u8 *ies1, u16 ies1_len,
 
 static void wil_print_bcon_data(struct cfg80211_beacon_data *b)
 {
-	print_hex_dump_bytes("head     ", DUMP_PREFIX_OFFSET,
-			     b->head, b->head_len);
-	print_hex_dump_bytes("tail     ", DUMP_PREFIX_OFFSET,
-			     b->tail, b->tail_len);
-	print_hex_dump_bytes("BCON IE  ", DUMP_PREFIX_OFFSET,
-			     b->beacon_ies, b->beacon_ies_len);
-	print_hex_dump_bytes("PROBE    ", DUMP_PREFIX_OFFSET,
-			     b->probe_resp, b->probe_resp_len);
-	print_hex_dump_bytes("PROBE IE ", DUMP_PREFIX_OFFSET,
-			     b->proberesp_ies, b->proberesp_ies_len);
-	print_hex_dump_bytes("ASSOC IE ", DUMP_PREFIX_OFFSET,
-			     b->assocresp_ies, b->assocresp_ies_len);
+	wil_hex_dump_misc("head     ", DUMP_PREFIX_OFFSET, 16, 1,
+			  b->head, b->head_len, true);
+	wil_hex_dump_misc("tail     ", DUMP_PREFIX_OFFSET, 16, 1,
+			  b->tail, b->tail_len, true);
+	wil_hex_dump_misc("BCON IE  ", DUMP_PREFIX_OFFSET, 16, 1,
+			  b->beacon_ies, b->beacon_ies_len, true);
+	wil_hex_dump_misc("PROBE    ", DUMP_PREFIX_OFFSET, 16, 1,
+			  b->probe_resp, b->probe_resp_len, true);
+	wil_hex_dump_misc("PROBE IE ", DUMP_PREFIX_OFFSET, 16, 1,
+			  b->proberesp_ies, b->proberesp_ies_len, true);
+	wil_hex_dump_misc("ASSOC IE ", DUMP_PREFIX_OFFSET, 16, 1,
+			  b->assocresp_ies, b->assocresp_ies_len, true);
 }
 
 /* internal functions for device reset and starting AP */
@@ -1198,6 +1199,7 @@ static int _wil_cfg80211_start_ap(struct wiphy *wiphy,
 	wil->pbss = pbss;
 
 	netif_carrier_on(ndev);
+	wil6210_bus_request(wil, WIL_MAX_BUS_REQUEST_KBPS);
 
 	rc = wmi_pcp_start(wil, bi, wmi_nettype, chan, hidden_ssid, is_go);
 	if (rc)
@@ -1213,6 +1215,7 @@ err_bcast:
 	wmi_pcp_stop(wil);
 err_pcp_start:
 	netif_carrier_off(ndev);
+	wil6210_bus_request(wil, WIL_DEFAULT_BUS_REQUEST_KBPS);
 out:
 	mutex_unlock(&wil->mutex);
 	return rc;
@@ -1298,8 +1301,8 @@ static int wil_cfg80211_start_ap(struct wiphy *wiphy,
 	wil_dbg_misc(wil, "BI %d DTIM %d\n", info->beacon_interval,
 		     info->dtim_period);
 	wil_dbg_misc(wil, "PBSS %d\n", info->pbss);
-	print_hex_dump_bytes("SSID ", DUMP_PREFIX_OFFSET,
-			     info->ssid, info->ssid_len);
+	wil_hex_dump_misc("SSID ", DUMP_PREFIX_OFFSET, 16, 1,
+			  info->ssid, info->ssid_len, true);
 	wil_print_bcon_data(bcon);
 	wil_print_crypto(wil, crypto);
 
@@ -1319,6 +1322,7 @@ static int wil_cfg80211_stop_ap(struct wiphy *wiphy,
 	wil_dbg_misc(wil, "stop_ap\n");
 
 	netif_carrier_off(ndev);
+	wil6210_bus_request(wil, WIL_DEFAULT_BUS_REQUEST_KBPS);
 	wil_set_recovery_state(wil, fw_recovery_idle);
 
 	mutex_lock(&wil->mutex);
@@ -1555,12 +1559,6 @@ static int wil_cfg80211_set_power_mgmt(struct wiphy *wiphy,
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 	enum wmi_ps_profile_type ps_profile;
-	int rc;
-
-	if (!test_bit(WMI_FW_CAPABILITY_PS_CONFIG, wil->fw_capabilities)) {
-		wil_err(wil, "set_power_mgmt not supported\n");
-		return -EOPNOTSUPP;
-	}
 
 	wil_dbg_misc(wil, "enabled=%d, timeout=%d\n",
 		     enabled, timeout);
@@ -1570,11 +1568,7 @@ static int wil_cfg80211_set_power_mgmt(struct wiphy *wiphy,
 	else
 		ps_profile = WMI_PS_PROFILE_TYPE_PS_DISABLED;
 
-	rc  = wmi_ps_dev_profile_cfg(wil, ps_profile);
-	if (rc)
-		wil_err(wil, "wmi_ps_dev_profile_cfg failed (%d)\n", rc);
-
-	return rc;
+	return wil_ps_update(wil, ps_profile);
 }
 
 static const struct cfg80211_ops wil_cfg80211_ops = {
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 3e8cdf12feda..5648ebbd0e16 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -524,9 +524,8 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf,
 	if (!buf)
 		return -ENOMEM;
 
-	wil_memcpy_fromio_halp_vote(wil_blob->wil, buf,
-				    (const volatile void __iomem *)
-				    wil_blob->blob.data + pos, count);
+	wil_memcpy_fromio_32(buf, (const void __iomem *)
+			     wil_blob->blob.data + pos, count);
 
 	ret = copy_to_user(user_buf, buf, count);
 	kfree(buf);
diff --git a/drivers/net/wireless/ath/wil6210/fw_inc.c b/drivers/net/wireless/ath/wil6210/fw_inc.c
index f4901587c005..e01acac88825 100644
--- a/drivers/net/wireless/ath/wil6210/fw_inc.c
+++ b/drivers/net/wireless/ath/wil6210/fw_inc.c
@@ -554,5 +554,7 @@ bool wil_fw_verify_file_exists(struct wil6210_priv *wil, const char *name)
 	rc = request_firmware(&fw, name, wil_to_dev(wil));
 	if (!rc)
 		release_firmware(fw);
-	return rc != -ENOENT;
+	else
+		wil_dbg_fw(wil, "<%s> not available: %d\n", name, rc);
+	return !rc;
 }
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index efb1f59aafd9..32086792dfc3 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -30,8 +30,8 @@ bool debug_fw; /* = false; */
 module_param(debug_fw, bool, 0444);
 MODULE_PARM_DESC(debug_fw, " do not perform card reset. For FW debug");
 
-static bool oob_mode;
-module_param(oob_mode, bool, 0444);
+static u8 oob_mode;
+module_param(oob_mode, byte, 0444);
 MODULE_PARM_DESC(oob_mode,
 		 " enable out of the box (OOB) mode in FW, for diagnostics and certification");
 
@@ -130,17 +130,15 @@ void wil_memcpy_fromio_32(void *dst, const volatile void __iomem *src,
 	u32 *d = dst;
 	const volatile u32 __iomem *s = src;
 
-	/* size_t is unsigned, if (count%4 != 0) it will wrap */
-	for (count += 4; count > 4; count -= 4)
+	for (; count >= 4; count -= 4)
 		*d++ = __raw_readl(s++);
-}
 
-void wil_memcpy_fromio_halp_vote(struct wil6210_priv *wil, void *dst,
-				 const volatile void __iomem *src, size_t count)
-{
-	wil_halp_vote(wil);
-	wil_memcpy_fromio_32(dst, src, count);
-	wil_halp_unvote(wil);
+	if (unlikely(count)) {
+		/* count can be 1..3 */
+		u32 tmp = __raw_readl(s);
+
+		memcpy(d, &tmp, count);
+	}
 }
 
 void wil_memcpy_toio_32(volatile void __iomem *dst, const void *src,
@@ -149,17 +147,16 @@ void wil_memcpy_toio_32(volatile void __iomem *dst, const void *src,
 	volatile u32 __iomem *d = dst;
 	const u32 *s = src;
 
-	for (count += 4; count > 4; count -= 4)
+	for (; count >= 4; count -= 4)
 		__raw_writel(*s++, d++);
-}
 
-void wil_memcpy_toio_halp_vote(struct wil6210_priv *wil,
-			       volatile void __iomem *dst,
-			       const void *src, size_t count)
-{
-	wil_halp_vote(wil);
-	wil_memcpy_toio_32(dst, src, count);
-	wil_halp_unvote(wil);
+	if (unlikely(count)) {
+		/* count can be 1..3 */
+		u32 tmp = 0;
+
+		memcpy(&tmp, s, count);
+		__raw_writel(tmp, d);
+	}
 }
 
 static void wil_disconnect_cid(struct wil6210_priv *wil, int cid,
@@ -274,15 +271,20 @@ static void _wil6210_disconnect(struct wil6210_priv *wil, const u8 *bssid,
 		wil_bcast_fini(wil);
 		wil_update_net_queues_bh(wil, NULL, true);
 		netif_carrier_off(ndev);
+		wil6210_bus_request(wil, WIL_DEFAULT_BUS_REQUEST_KBPS);
 
 		if (test_bit(wil_status_fwconnected, wil->status)) {
 			clear_bit(wil_status_fwconnected, wil->status);
 			cfg80211_disconnected(ndev, reason_code,
-					      NULL, 0, false, GFP_KERNEL);
+					      NULL, 0,
+					      wil->locally_generated_disc,
+					      GFP_KERNEL);
+			wil->locally_generated_disc = false;
 		} else if (test_bit(wil_status_fwconnecting, wil->status)) {
 			cfg80211_connect_result(ndev, bssid, NULL, 0, NULL, 0,
 						WLAN_STATUS_UNSPECIFIED_FAILURE,
 						GFP_KERNEL);
+			wil->bss = NULL;
 		}
 		clear_bit(wil_status_fwconnecting, wil->status);
 		break;
@@ -304,10 +306,34 @@ static void wil_disconnect_worker(struct work_struct *work)
 {
 	struct wil6210_priv *wil = container_of(work,
 			struct wil6210_priv, disconnect_worker);
+	struct net_device *ndev = wil_to_ndev(wil);
+	int rc;
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_disconnect_event evt;
+	} __packed reply;
 
-	mutex_lock(&wil->mutex);
-	_wil6210_disconnect(wil, NULL, WLAN_REASON_UNSPECIFIED, false);
-	mutex_unlock(&wil->mutex);
+	if (test_bit(wil_status_fwconnected, wil->status))
+		/* connect succeeded after all */
+		return;
+
+	if (!test_bit(wil_status_fwconnecting, wil->status))
+		/* already disconnected */
+		return;
+
+	rc = wmi_call(wil, WMI_DISCONNECT_CMDID, NULL, 0,
+		      WMI_DISCONNECT_EVENTID, &reply, sizeof(reply),
+		      WIL6210_DISCONNECT_TO_MS);
+	if (rc) {
+		wil_err(wil, "disconnect error %d\n", rc);
+		return;
+	}
+
+	wil_update_net_queues_bh(wil, NULL, true);
+	netif_carrier_off(ndev);
+	cfg80211_connect_result(ndev, NULL, NULL, 0, NULL, 0,
+				WLAN_STATUS_UNSPECIFIED_FAILURE, GFP_KERNEL);
+	clear_bit(wil_status_fwconnecting, wil->status);
 }
 
 static void wil_connect_timer_fn(ulong x)
@@ -547,6 +573,9 @@ int wil_priv_init(struct wil6210_priv *wil)
 
 	if (rx_ring_overflow_thrsh == WIL6210_RX_HIGH_TRSH_INIT)
 		rx_ring_overflow_thrsh = WIL6210_RX_HIGH_TRSH_DEFAULT;
+
+	wil->ps_profile =  WMI_PS_PROFILE_TYPE_DEFAULT;
+
 	return 0;
 
 out_wmi_wq:
@@ -555,6 +584,12 @@ out_wmi_wq:
 	return -EAGAIN;
 }
 
+void wil6210_bus_request(struct wil6210_priv *wil, u32 kbps)
+{
+	if (wil->platform_ops.bus_request)
+		wil->platform_ops.bus_request(wil->platform_handle, kbps);
+}
+
 /**
  * wil6210_disconnect - disconnect one connection
  * @wil: driver context
@@ -607,13 +642,25 @@ static inline void wil_release_cpu(struct wil6210_priv *wil)
 	wil_w(wil, RGF_USER_USER_CPU_0, 1);
 }
 
-static void wil_set_oob_mode(struct wil6210_priv *wil, bool enable)
+static void wil_set_oob_mode(struct wil6210_priv *wil, u8 mode)
 {
-	wil_info(wil, "enable=%d\n", enable);
-	if (enable)
+	wil_info(wil, "oob_mode to %d\n", mode);
+	switch (mode) {
+	case 0:
+		wil_c(wil, RGF_USER_USAGE_6, BIT_USER_OOB_MODE |
+		      BIT_USER_OOB_R2_MODE);
+		break;
+	case 1:
+		wil_c(wil, RGF_USER_USAGE_6, BIT_USER_OOB_R2_MODE);
 		wil_s(wil, RGF_USER_USAGE_6, BIT_USER_OOB_MODE);
-	else
+		break;
+	case 2:
 		wil_c(wil, RGF_USER_USAGE_6, BIT_USER_OOB_MODE);
+		wil_s(wil, RGF_USER_USAGE_6, BIT_USER_OOB_R2_MODE);
+		break;
+	default:
+		wil_err(wil, "invalid oob_mode: %d\n", mode);
+	}
 }
 
 static int wil_target_reset(struct wil6210_priv *wil)
@@ -856,6 +903,24 @@ void wil_abort_scan(struct wil6210_priv *wil, bool sync)
 	}
 }
 
+int wil_ps_update(struct wil6210_priv *wil, enum wmi_ps_profile_type ps_profile)
+{
+	int rc;
+
+	if (!test_bit(WMI_FW_CAPABILITY_PS_CONFIG, wil->fw_capabilities)) {
+		wil_err(wil, "set_power_mgmt not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	rc  = wmi_ps_dev_profile_cfg(wil, ps_profile);
+	if (rc)
+		wil_err(wil, "wmi_ps_dev_profile_cfg failed (%d)\n", rc);
+	else
+		wil->ps_profile = ps_profile;
+
+	return rc;
+}
+
 /*
  * We reset all the structures, and we reset the UMAC.
  * After calling this routine, you're expected to reload
@@ -901,15 +966,15 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 	/* Disable device led before reset*/
 	wmi_led_cfg(wil, false);
 
+	mutex_lock(&wil->p2p_wdev_mutex);
+	wil_abort_scan(wil, false);
+	mutex_unlock(&wil->p2p_wdev_mutex);
+
 	/* prevent NAPI from being scheduled and prevent wmi commands */
 	mutex_lock(&wil->wmi_mutex);
 	bitmap_zero(wil->status, wil_status_last);
 	mutex_unlock(&wil->wmi_mutex);
 
-	mutex_lock(&wil->p2p_wdev_mutex);
-	wil_abort_scan(wil, false);
-	mutex_unlock(&wil->p2p_wdev_mutex);
-
 	wil_mask_irq(wil);
 
 	wmi_event_flush(wil);
@@ -986,6 +1051,9 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 			return rc;
 		}
 
+		if (wil->ps_profile != WMI_PS_PROFILE_TYPE_DEFAULT)
+			wil_ps_update(wil, wil->ps_profile);
+
 		wil_collect_fw_info(wil);
 
 		if (wil->platform_ops.notify) {
@@ -1066,9 +1134,7 @@ int __wil_up(struct wil6210_priv *wil)
 	napi_enable(&wil->napi_tx);
 	set_bit(wil_status_napi_en, wil->status);
 
-	if (wil->platform_ops.bus_request)
-		wil->platform_ops.bus_request(wil->platform_handle,
-					      WIL_MAX_BUS_REQUEST_KBPS);
+	wil6210_bus_request(wil, WIL_DEFAULT_BUS_REQUEST_KBPS);
 
 	return 0;
 }
@@ -1092,8 +1158,7 @@ int __wil_down(struct wil6210_priv *wil)
 
 	set_bit(wil_status_resetting, wil->status);
 
-	if (wil->platform_ops.bus_request)
-		wil->platform_ops.bus_request(wil->platform_handle, 0);
+	wil6210_bus_request(wil, 0);
 
 	wil_disable_irq(wil);
 	if (test_and_clear_bit(wil_status_napi_en, wil->status)) {
@@ -1154,6 +1219,7 @@ void wil_halp_vote(struct wil6210_priv *wil)
 		    wil->halp.ref_cnt);
 
 	if (++wil->halp.ref_cnt == 1) {
+		reinit_completion(&wil->halp.comp);
 		wil6210_set_halp(wil);
 		rc = wait_for_completion_timeout(&wil->halp.comp, to_jiffies);
 		if (!rc) {
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 874c787727fe..b38515fc7ce7 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -211,6 +211,7 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_err(dev, "wil_if_alloc failed: %d\n", rc);
 		return rc;
 	}
+
 	wil->pdev = pdev;
 	pci_set_drvdata(pdev, wil);
 	/* rollback to if_free */
@@ -224,6 +225,21 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 	/* rollback to err_plat */
 
+	/* device supports 48bit addresses */
+	rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (rc) {
+		dev_err(dev, "dma_set_mask_and_coherent(48) failed: %d\n", rc);
+		rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+		if (rc) {
+			dev_err(dev,
+				"dma_set_mask_and_coherent(32) failed: %d\n",
+				rc);
+			goto err_plat;
+		}
+	} else {
+		wil->use_extended_dma_addr = 1;
+	}
+
 	rc = pci_enable_device(pdev);
 	if (rc) {
 		wil_err(wil,
diff --git a/drivers/net/wireless/ath/wil6210/pm.c b/drivers/net/wireless/ath/wil6210/pm.c
index a0acb2d0cb79..2ae4fe85cc8c 100644
--- a/drivers/net/wireless/ath/wil6210/pm.c
+++ b/drivers/net/wireless/ath/wil6210/pm.c
@@ -71,6 +71,11 @@ int wil_suspend(struct wil6210_priv *wil, bool is_runtime)
 
 	wil_dbg_pm(wil, "suspend: %s\n", is_runtime ? "runtime" : "system");
 
+	if (test_bit(wil_status_suspended, wil->status)) {
+		wil_dbg_pm(wil, "trying to suspend while suspended\n");
+		return 0;
+	}
+
 	/* if netif up, hardware is alive, shut it down */
 	if (ndev->flags & IFF_UP) {
 		rc = wil_down(wil);
@@ -80,12 +85,24 @@ int wil_suspend(struct wil6210_priv *wil, bool is_runtime)
 		}
 	}
 
-	if (wil->platform_ops.suspend)
+	/* Disable PCIe IRQ to prevent sporadic IRQs when PCIe is suspending */
+	wil_dbg_pm(wil, "Disabling PCIe IRQ before suspending\n");
+	wil_disable_irq(wil);
+
+	if (wil->platform_ops.suspend) {
 		rc = wil->platform_ops.suspend(wil->platform_handle);
+		if (rc) {
+			wil_enable_irq(wil);
+			goto out;
+		}
+	}
+
+	set_bit(wil_status_suspended, wil->status);
 
 out:
 	wil_dbg_pm(wil, "suspend: %s => %d\n",
 		   is_runtime ? "runtime" : "system", rc);
+
 	return rc;
 }
 
@@ -104,12 +121,18 @@ int wil_resume(struct wil6210_priv *wil, bool is_runtime)
 		}
 	}
 
+	wil_dbg_pm(wil, "Enabling PCIe IRQ\n");
+	wil_enable_irq(wil);
+
 	/* if netif up, bring hardware up
 	 * During open(), IFF_UP set after actual device method
-	 * invocation. This prevent recursive call to wil_up()
+	 * invocation. This prevent recursive call to wil_up().
+	 * wil_status_suspended will be cleared in wil_reset
 	 */
 	if (ndev->flags & IFF_UP)
 		rc = wil_up(wil);
+	else
+		clear_bit(wil_status_suspended, wil->status);
 
 out:
 	wil_dbg_pm(wil, "resume: %s => %d\n",
diff --git a/drivers/net/wireless/ath/wil6210/pmc.c b/drivers/net/wireless/ath/wil6210/pmc.c
index 3ff4f4ce9fef..2e301b6b32a9 100644
--- a/drivers/net/wireless/ath/wil6210/pmc.c
+++ b/drivers/net/wireless/ath/wil6210/pmc.c
@@ -107,13 +107,28 @@ void wil_pmc_alloc(struct wil6210_priv *wil,
 
 	/* Allocate pring buffer and descriptors.
 	 * vring->va should be aligned on its size rounded up to power of 2
-	 * This is granted by the dma_alloc_coherent
+	 * This is granted by the dma_alloc_coherent.
+	 *
+	 * HW has limitation that all vrings addresses must share the same
+	 * upper 16 msb bits part of 48 bits address. To workaround that,
+	 * if we are using 48 bit addresses switch to 32 bit allocation
+	 * before allocating vring memory.
+	 *
+	 * There's no check for the return value of dma_set_mask_and_coherent,
+	 * since we assume if we were able to set the mask during
+	 * initialization in this system it will not fail if we set it again
 	 */
+	if (wil->use_extended_dma_addr)
+		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+
 	pmc->pring_va = dma_alloc_coherent(dev,
 			sizeof(struct vring_tx_desc) * num_descriptors,
 			&pmc->pring_pa,
 			GFP_KERNEL);
 
+	if (wil->use_extended_dma_addr)
+		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+
 	wil_dbg_misc(wil,
 		     "pmc_alloc: allocated pring %p => %pad. %zd x %d = total %zd bytes\n",
 		     pmc->pring_va, &pmc->pring_pa,
@@ -185,7 +200,7 @@ void wil_pmc_alloc(struct wil6210_priv *wil,
 
 release_pmc_skbs:
 	wil_err(wil, "exit on error: Releasing skbs...\n");
-	for (i = 0; pmc->descriptors[i].va && i < num_descriptors; i++) {
+	for (i = 0; i < num_descriptors && pmc->descriptors[i].va; i++) {
 		dma_free_coherent(dev,
 				  descriptor_size,
 				  pmc->descriptors[i].va,
@@ -268,7 +283,7 @@ void wil_pmc_free(struct wil6210_priv *wil, int send_pmc_cmd)
 		int i;
 
 		for (i = 0;
-		     pmc->descriptors[i].va && i < pmc->num_descriptors; i++) {
+		     i < pmc->num_descriptors && pmc->descriptors[i].va; i++) {
 			dma_free_coherent(dev,
 					  pmc->descriptor_size,
 					  pmc->descriptors[i].va,
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index 7404b6f39c6a..a43cffcf1bbf 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -343,8 +343,16 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 		wil_err(wil, "BACK requested unsupported ba_policy == 1\n");
 		status = WLAN_STATUS_INVALID_QOS_PARAM;
 	}
-	if (status == WLAN_STATUS_SUCCESS)
-		agg_wsize = wil_agg_size(wil, req_agg_wsize);
+	if (status == WLAN_STATUS_SUCCESS) {
+		if (req_agg_wsize == 0) {
+			wil_dbg_misc(wil, "Suggest BACK wsize %d\n",
+				     WIL_MAX_AGG_WSIZE);
+			agg_wsize = WIL_MAX_AGG_WSIZE;
+		} else {
+			agg_wsize = min_t(u16,
+					  WIL_MAX_AGG_WSIZE, req_agg_wsize);
+		}
+	}
 
 	rc = wmi_addba_rx_resp(wil, cid, tid, dialog_token, status,
 			       agg_amsdu, agg_wsize, agg_timeout);
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 072182e527e6..edab4c0a900f 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -37,6 +37,10 @@ bool rx_align_2;
 module_param(rx_align_2, bool, 0444);
 MODULE_PARM_DESC(rx_align_2, " align Rx buffers on 4*n+2, default - no");
 
+bool rx_large_buf;
+module_param(rx_large_buf, bool, 0444);
+MODULE_PARM_DESC(rx_large_buf, " allocate 8KB RX buffers, default - no");
+
 static inline uint wil_rx_snaplen(void)
 {
 	return rx_align_2 ? 6 : 0;
@@ -123,15 +127,32 @@ static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
 		vring->va = NULL;
 		return -ENOMEM;
 	}
+
 	/* vring->va should be aligned on its size rounded up to power of 2
-	 * This is granted by the dma_alloc_coherent
+	 * This is granted by the dma_alloc_coherent.
+	 *
+	 * HW has limitation that all vrings addresses must share the same
+	 * upper 16 msb bits part of 48 bits address. To workaround that,
+	 * if we are using 48 bit addresses switch to 32 bit allocation
+	 * before allocating vring memory.
+	 *
+	 * There's no check for the return value of dma_set_mask_and_coherent,
+	 * since we assume if we were able to set the mask during
+	 * initialization in this system it will not fail if we set it again
 	 */
+	if (wil->use_extended_dma_addr)
+		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+
 	vring->va = dma_alloc_coherent(dev, sz, &vring->pa, GFP_KERNEL);
 	if (!vring->va) {
 		kfree(vring->ctx);
 		vring->ctx = NULL;
 		return -ENOMEM;
 	}
+
+	if (wil->use_extended_dma_addr)
+		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+
 	/* initially, all descriptors are SW owned
 	 * For Tx and Rx, ownership bit is at the same location, thus
 	 * we can use any
@@ -238,7 +259,7 @@ static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct vring *vring,
 			       u32 i, int headroom)
 {
 	struct device *dev = wil_to_dev(wil);
-	unsigned int sz = mtu_max + ETH_HLEN + wil_rx_snaplen();
+	unsigned int sz = wil->rx_buf_len + ETH_HLEN + wil_rx_snaplen();
 	struct vring_rx_desc dd, *d = &dd;
 	volatile struct vring_rx_desc *_d = &vring->va[i].rx;
 	dma_addr_t pa;
@@ -402,7 +423,7 @@ static struct sk_buff *wil_vring_reap_rx(struct wil6210_priv *wil,
 	struct sk_buff *skb;
 	dma_addr_t pa;
 	unsigned int snaplen = wil_rx_snaplen();
-	unsigned int sz = mtu_max + ETH_HLEN + snaplen;
+	unsigned int sz = wil->rx_buf_len + ETH_HLEN + snaplen;
 	u16 dmalen;
 	u8 ftype;
 	int cid;
@@ -763,6 +784,20 @@ void wil_rx_handle(struct wil6210_priv *wil, int *quota)
 	wil_rx_refill(wil, v->size);
 }
 
+static void wil_rx_buf_len_init(struct wil6210_priv *wil)
+{
+	wil->rx_buf_len = rx_large_buf ?
+		WIL_MAX_ETH_MTU : TXRX_BUF_LEN_DEFAULT - WIL_MAX_MPDU_OVERHEAD;
+	if (mtu_max > wil->rx_buf_len) {
+		/* do not allow RX buffers to be smaller than mtu_max, for
+		 * backward compatibility (mtu_max parameter was also used
+		 * to support receiving large packets)
+		 */
+		wil_info(wil, "Override RX buffer to mtu_max(%d)\n", mtu_max);
+		wil->rx_buf_len = mtu_max;
+	}
+}
+
 int wil_rx_init(struct wil6210_priv *wil, u16 size)
 {
 	struct vring *vring = &wil->vring_rx;
@@ -775,6 +810,8 @@ int wil_rx_init(struct wil6210_priv *wil, u16 size)
 		return -EINVAL;
 	}
 
+	wil_rx_buf_len_init(wil);
+
 	vring->size = size;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 085a2dbfa21d..b00c803a1e83 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012-2016 Qualcomm Atheros, Inc.
+ * Copyright (c) 2012-2017 Qualcomm Atheros, Inc.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -32,6 +32,7 @@ extern unsigned short rx_ring_overflow_thrsh;
 extern int agg_wsize;
 extern u32 vring_idle_trsh;
 extern bool rx_align_2;
+extern bool rx_large_buf;
 extern bool debug_fw;
 extern bool disable_ap_sme;
 
@@ -40,6 +41,7 @@ extern bool disable_ap_sme;
 #define WIL_FW_NAME_SPARROW_PLUS "wil6210_sparrow_plus.fw" /* code Sparrow D0 */
 #define WIL_BOARD_FILE_NAME "wil6210.brd" /* board & radio parameters */
 
+#define WIL_DEFAULT_BUS_REQUEST_KBPS 128000 /* ~1Gbps */
 #define WIL_MAX_BUS_REQUEST_KBPS 800000 /* ~6.1Gbps */
 
 /**
@@ -139,6 +141,7 @@ struct RGF_ICR {
 #define RGF_USER_USAGE_1		(0x880004)
 #define RGF_USER_USAGE_6		(0x880018)
 	#define BIT_USER_OOB_MODE		BIT(31)
+	#define BIT_USER_OOB_R2_MODE		BIT(30)
 #define RGF_USER_HW_MACHINE_STATE	(0x8801dc)
 	#define HW_MACHINE_BOOT_DONE	(0x3fffffd)
 #define RGF_USER_USER_CPU_0		(0x8801e0)
@@ -409,6 +412,7 @@ enum { /* for wil6210_priv.status */
 	wil_status_irqen, /* FIXME: interrupts enabled - for debug */
 	wil_status_napi_en, /* NAPI enabled protected by wil->mutex */
 	wil_status_resetting, /* reset in progress */
+	wil_status_suspended, /* suspend completed, device is suspended */
 	wil_status_last /* keep last */
 };
 
@@ -612,6 +616,8 @@ struct wil6210_priv {
 	u16 channel; /* relevant in AP mode */
 	int sinfo_gen;
 	u32 ap_isolate; /* no intra-BSS communication */
+	struct cfg80211_bss *bss; /* connected bss, relevant in STA mode */
+	int locally_generated_disc; /* relevant in STA mode */
 	/* interrupt moderation */
 	u32 tx_max_burst_duration;
 	u32 tx_interframe_timeout;
@@ -652,11 +658,13 @@ struct wil6210_priv {
 	struct work_struct probe_client_worker;
 	/* DMA related */
 	struct vring vring_rx;
+	unsigned int rx_buf_len;
 	struct vring vring_tx[WIL6210_MAX_TX_RINGS];
 	struct vring_tx_data vring_tx_data[WIL6210_MAX_TX_RINGS];
 	u8 vring2cid_tid[WIL6210_MAX_TX_RINGS][2]; /* [0] - CID, [1] - TID */
 	struct wil_sta_info sta[WIL6210_MAX_CID];
 	int bcast_vring;
+	bool use_extended_dma_addr; /* indicates whether we are using 48 bits */
 	/* scan */
 	struct cfg80211_scan_request *scan_request;
 
@@ -686,6 +694,8 @@ struct wil6210_priv {
 	/* High Access Latency Policy voting */
 	struct wil_halp halp;
 
+	enum wmi_ps_profile_type ps_profile;
+
 #ifdef CONFIG_PM
 #ifdef CONFIG_PM_SLEEP
 	struct notifier_block pm_notify;
@@ -764,6 +774,12 @@ static inline void wil_c(struct wil6210_priv *wil, u32 reg, u32 val)
 			 print_hex_dump_debug("DBG[ WMI]" prefix_str,\
 					prefix_type, rowsize,	\
 					groupsize, buf, len, ascii)
+
+#define wil_hex_dump_misc(prefix_str, prefix_type, rowsize,	\
+			  groupsize, buf, len, ascii)		\
+			  print_hex_dump_debug("DBG[MISC]" prefix_str,\
+					prefix_type, rowsize,	\
+					groupsize, buf, len, ascii)
 #else /* defined(CONFIG_DYNAMIC_DEBUG) */
 static inline
 void wil_hex_dump_txrx(const char *prefix_str, int prefix_type, int rowsize,
@@ -776,18 +792,18 @@ void wil_hex_dump_wmi(const char *prefix_str, int prefix_type, int rowsize,
 		      int groupsize, const void *buf, size_t len, bool ascii)
 {
 }
+
+static inline
+void wil_hex_dump_misc(const char *prefix_str, int prefix_type, int rowsize,
+		       int groupsize, const void *buf, size_t len, bool ascii)
+{
+}
 #endif /* defined(CONFIG_DYNAMIC_DEBUG) */
 
 void wil_memcpy_fromio_32(void *dst, const volatile void __iomem *src,
 			  size_t count);
 void wil_memcpy_toio_32(volatile void __iomem *dst, const void *src,
 			size_t count);
-void wil_memcpy_fromio_halp_vote(struct wil6210_priv *wil, void *dst,
-				 const volatile void __iomem *src,
-				 size_t count);
-void wil_memcpy_toio_halp_vote(struct wil6210_priv *wil,
-			       volatile void __iomem *dst,
-			       const void *src, size_t count);
 
 void *wil_if_alloc(struct device *dev);
 void wil_if_free(struct wil6210_priv *wil);
@@ -795,6 +811,8 @@ int wil_if_add(struct wil6210_priv *wil);
 void wil_if_remove(struct wil6210_priv *wil);
 int wil_priv_init(struct wil6210_priv *wil);
 void wil_priv_deinit(struct wil6210_priv *wil);
+int wil_ps_update(struct wil6210_priv *wil,
+		  enum wmi_ps_profile_type ps_profile);
 int wil_reset(struct wil6210_priv *wil, bool no_fw);
 void wil_fw_error_recovery(struct wil6210_priv *wil);
 void wil_set_recovery_state(struct wil6210_priv *wil, int state);
@@ -899,7 +917,7 @@ int wmi_pcp_stop(struct wil6210_priv *wil);
 int wmi_led_cfg(struct wil6210_priv *wil, bool enable);
 int wmi_abort_scan(struct wil6210_priv *wil);
 void wil_abort_scan(struct wil6210_priv *wil, bool sync);
-
+void wil6210_bus_request(struct wil6210_priv *wil, u32 kbps);
 void wil6210_disconnect(struct wil6210_priv *wil, const u8 *bssid,
 			u16 reason_code, bool from_event);
 void wil_probe_client_flush(struct wil6210_priv *wil);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 1f22c19696b1..814c35645b73 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -518,16 +518,16 @@ static void wmi_evt_connect(struct wil6210_priv *wil, int id, void *d, int len)
 		assoc_resp_ielen = 0;
 	}
 
-	mutex_lock(&wil->mutex);
 	if (test_bit(wil_status_resetting, wil->status) ||
 	    !test_bit(wil_status_fwready, wil->status)) {
 		wil_err(wil, "status_resetting, cancel connect event, CID %d\n",
 			evt->cid);
-		mutex_unlock(&wil->mutex);
 		/* no need for cleanup, wil_reset will do that */
 		return;
 	}
 
+	mutex_lock(&wil->mutex);
+
 	if ((wdev->iftype == NL80211_IFTYPE_STATION) ||
 	    (wdev->iftype == NL80211_IFTYPE_P2P_CLIENT)) {
 		if (!test_bit(wil_status_fwconnecting, wil->status)) {
@@ -565,6 +565,7 @@ static void wmi_evt_connect(struct wil6210_priv *wil, int id, void *d, int len)
 	    (wdev->iftype == NL80211_IFTYPE_P2P_CLIENT)) {
 		if (rc) {
 			netif_carrier_off(ndev);
+			wil6210_bus_request(wil, WIL_DEFAULT_BUS_REQUEST_KBPS);
 			wil_err(wil, "cfg80211_connect_result with failure\n");
 			cfg80211_connect_result(ndev, evt->bssid, NULL, 0,
 						NULL, 0,
@@ -572,12 +573,16 @@ static void wmi_evt_connect(struct wil6210_priv *wil, int id, void *d, int len)
 						GFP_KERNEL);
 			goto out;
 		} else {
-			cfg80211_connect_result(ndev, evt->bssid,
-						assoc_req_ie, assoc_req_ielen,
-						assoc_resp_ie, assoc_resp_ielen,
-						WLAN_STATUS_SUCCESS,
-						GFP_KERNEL);
+			struct wiphy *wiphy = wil_to_wiphy(wil);
+
+			cfg80211_ref_bss(wiphy, wil->bss);
+			cfg80211_connect_bss(ndev, evt->bssid, wil->bss,
+					     assoc_req_ie, assoc_req_ielen,
+					     assoc_resp_ie, assoc_resp_ielen,
+					     WLAN_STATUS_SUCCESS, GFP_KERNEL,
+					     NL80211_TIMEOUT_UNSPECIFIED);
 		}
+		wil->bss = NULL;
 	} else if ((wdev->iftype == NL80211_IFTYPE_AP) ||
 		   (wdev->iftype == NL80211_IFTYPE_P2P_GO)) {
 		if (rc) {
@@ -626,6 +631,13 @@ static void wmi_evt_disconnect(struct wil6210_priv *wil, int id,
 
 	wil->sinfo_gen++;
 
+	if (test_bit(wil_status_resetting, wil->status) ||
+	    !test_bit(wil_status_fwready, wil->status)) {
+		wil_err(wil, "status_resetting, cancel disconnect event\n");
+		/* no need for cleanup, wil_reset will do that */
+		return;
+	}
+
 	mutex_lock(&wil->mutex);
 	wil6210_disconnect(wil, evt->bssid, reason_code, true);
 	mutex_unlock(&wil->mutex);
@@ -1393,7 +1405,8 @@ int wmi_rx_chain_add(struct wil6210_priv *wil, struct vring *vring)
 	struct wmi_cfg_rx_chain_cmd cmd = {
 		.action = WMI_RX_CHAIN_ADD,
 		.rx_sw_ring = {
-			.max_mpdu_size = cpu_to_le16(wil_mtu2macbuf(mtu_max)),
+			.max_mpdu_size = cpu_to_le16(
+				wil_mtu2macbuf(wil->rx_buf_len)),
 			.ring_mem_base = cpu_to_le64(vring->pa),
 			.ring_size = cpu_to_le16(vring->size),
 		},
@@ -1492,6 +1505,7 @@ int wmi_disconnect_sta(struct wil6210_priv *wil, const u8 *mac,
 
 	wil_dbg_wmi(wil, "disconnect_sta: (%pM, reason %d)\n", mac, reason);
 
+	wil->locally_generated_disc = true;
 	if (del_sta) {
 		ether_addr_copy(del_sta_cmd.dst_mac, mac);
 		rc = wmi_call(wil, WMI_DEL_STA_CMDID, &del_sta_cmd,
@@ -1733,14 +1747,19 @@ int wmi_new_sta(struct wil6210_priv *wil, const u8 *mac, u8 aid)
 
 void wmi_event_flush(struct wil6210_priv *wil)
 {
+	ulong flags;
 	struct pending_wmi_event *evt, *t;
 
 	wil_dbg_wmi(wil, "event_flush\n");
 
+	spin_lock_irqsave(&wil->wmi_ev_lock, flags);
+
 	list_for_each_entry_safe(evt, t, &wil->pending_wmi_ev, list) {
 		list_del(&evt->list);
 		kfree(evt);
 	}
+
+	spin_unlock_irqrestore(&wil->wmi_ev_lock, flags);
 }
 
 static bool wmi_evt_call_handler(struct wil6210_priv *wil, int id,
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index 7c9fee57aa91..f7f5f4f801e3 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -58,6 +58,7 @@ enum wmi_fw_capability {
 	WMI_FW_CAPABILITY_MGMT_RETRY_LIMIT	= 3,
 	WMI_FW_CAPABILITY_DISABLE_AP_SME	= 4,
 	WMI_FW_CAPABILITY_WMI_ONLY		= 5,
+	WMI_FW_CAPABILITY_THERMAL_THROTTLING	= 7,
 	WMI_FW_CAPABILITY_MAX,
 };
 
@@ -142,8 +143,6 @@ enum wmi_command_id {
 	WMI_MAINTAIN_RESUME_CMDID			= 0x851,
 	WMI_RS_MGMT_CMDID				= 0x852,
 	WMI_RF_MGMT_CMDID				= 0x853,
-	WMI_THERMAL_THROTTLING_CTRL_CMDID		= 0x854,
-	WMI_THERMAL_THROTTLING_GET_STATUS_CMDID		= 0x855,
 	WMI_OTP_READ_CMDID				= 0x856,
 	WMI_OTP_WRITE_CMDID				= 0x857,
 	WMI_LED_CFG_CMDID				= 0x858,
@@ -192,6 +191,8 @@ enum wmi_command_id {
 	WMI_GET_MGMT_RETRY_LIMIT_CMDID			= 0x931,
 	WMI_NEW_STA_CMDID				= 0x935,
 	WMI_DEL_STA_CMDID				= 0x936,
+	WMI_SET_THERMAL_THROTTLING_CFG_CMDID		= 0x940,
+	WMI_GET_THERMAL_THROTTLING_CFG_CMDID		= 0x941,
 	WMI_TOF_SESSION_START_CMDID			= 0x991,
 	WMI_TOF_GET_CAPABILITIES_CMDID			= 0x992,
 	WMI_TOF_SET_LCR_CMDID				= 0x993,
@@ -438,16 +439,6 @@ struct wmi_rf_mgmt_cmd {
 	__le32 rf_mgmt_type;
 } __packed;
 
-/* WMI_THERMAL_THROTTLING_CTRL_CMDID */
-#define THERMAL_THROTTLING_USE_DEFAULT_MAX_TXOP_LENGTH	(0xFFFFFFFF)
-
-/* WMI_THERMAL_THROTTLING_CTRL_CMDID */
-struct wmi_thermal_throttling_ctrl_cmd {
-	__le32 time_on_usec;
-	__le32 time_off_usec;
-	__le32 max_txop_length_usec;
-} __packed;
-
 /* WMI_RF_RX_TEST_CMDID */
 struct wmi_rf_rx_test_cmd {
 	__le32 sector;
@@ -549,7 +540,7 @@ struct wmi_pcp_start_cmd {
 	u8 hidden_ssid;
 	u8 is_go;
 	u8 reserved0[5];
-	/* abft_len override if non-0 */
+	/* A-BFT length override if non-0 */
 	u8 abft_len;
 	u8 disable_ap_sme;
 	u8 network_type;
@@ -910,6 +901,39 @@ struct wmi_set_mgmt_retry_limit_cmd {
 	u8 reserved[3];
 } __packed;
 
+/* Zones: HIGH, MAX, CRITICAL */
+#define WMI_NUM_OF_TT_ZONES	(3)
+
+struct wmi_tt_zone_limits {
+	/* Above this temperature this zone is active */
+	u8 temperature_high;
+	/* Below this temperature the adjacent lower zone is active */
+	u8 temperature_low;
+	u8 reserved[2];
+} __packed;
+
+/* Struct used for both configuration and status commands of thermal
+ * throttling
+ */
+struct wmi_tt_data {
+	/* Enable/Disable TT algorithm for baseband */
+	u8 bb_enabled;
+	u8 reserved0[3];
+	/* Define zones for baseband */
+	struct wmi_tt_zone_limits bb_zones[WMI_NUM_OF_TT_ZONES];
+	/* Enable/Disable TT algorithm for radio */
+	u8 rf_enabled;
+	u8 reserved1[3];
+	/* Define zones for all radio chips */
+	struct wmi_tt_zone_limits rf_zones[WMI_NUM_OF_TT_ZONES];
+} __packed;
+
+/* WMI_SET_THERMAL_THROTTLING_CFG_CMDID */
+struct wmi_set_thermal_throttling_cfg_cmd {
+	/* Command data */
+	struct wmi_tt_data tt_data;
+} __packed;
+
 /* WMI_NEW_STA_CMDID */
 struct wmi_new_sta_cmd {
 	u8 dst_mac[WMI_MAC_LEN];
@@ -1040,7 +1064,6 @@ enum wmi_event_id {
 	WMI_BF_RXSS_MGMT_DONE_EVENTID			= 0x1839,
 	WMI_RS_MGMT_DONE_EVENTID			= 0x1852,
 	WMI_RF_MGMT_STATUS_EVENTID			= 0x1853,
-	WMI_THERMAL_THROTTLING_STATUS_EVENTID		= 0x1855,
 	WMI_BF_SM_MGMT_DONE_EVENTID			= 0x1838,
 	WMI_RX_MGMT_PACKET_EVENTID			= 0x1840,
 	WMI_TX_MGMT_PACKET_EVENTID			= 0x1841,
@@ -1090,6 +1113,8 @@ enum wmi_event_id {
 	WMI_BRP_SET_ANT_LIMIT_EVENTID			= 0x1924,
 	WMI_SET_MGMT_RETRY_LIMIT_EVENTID		= 0x1930,
 	WMI_GET_MGMT_RETRY_LIMIT_EVENTID		= 0x1931,
+	WMI_SET_THERMAL_THROTTLING_CFG_EVENTID		= 0x1940,
+	WMI_GET_THERMAL_THROTTLING_CFG_EVENTID		= 0x1941,
 	WMI_TOF_SESSION_END_EVENTID			= 0x1991,
 	WMI_TOF_GET_CAPABILITIES_EVENTID		= 0x1992,
 	WMI_TOF_SET_LCR_EVENTID				= 0x1993,
@@ -1133,13 +1158,6 @@ struct wmi_rf_mgmt_status_event {
 	__le32 rf_status;
 } __packed;
 
-/* WMI_THERMAL_THROTTLING_STATUS_EVENTID */
-struct wmi_thermal_throttling_status_event {
-	__le32 time_on_usec;
-	__le32 time_off_usec;
-	__le32 max_txop_length_usec;
-} __packed;
-
 /* WMI_GET_STATUS_DONE_EVENTID */
 struct wmi_get_status_done_event {
 	__le32 is_associated;
@@ -2206,6 +2224,19 @@ struct wmi_tof_get_capabilities_event {
 	__le32 aoa_supported_types;
 } __packed;
 
+/* WMI_SET_THERMAL_THROTTLING_CFG_EVENTID */
+struct wmi_set_thermal_throttling_cfg_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_GET_THERMAL_THROTTLING_CFG_EVENTID */
+struct wmi_get_thermal_throttling_cfg_event {
+	/* Status data */
+	struct wmi_tt_data tt_data;
+} __packed;
+
 enum wmi_tof_session_end_status {
 	WMI_TOF_SESSION_END_NO_ERROR		= 0x00,
 	WMI_TOF_SESSION_END_FAIL		= 0x01,
diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c
index 0e180677c7fc..09defbcedd5e 100644
--- a/drivers/net/wireless/atmel/at76c50x-usb.c
+++ b/drivers/net/wireless/atmel/at76c50x-usb.c
@@ -2377,6 +2377,8 @@ static int at76_init_new_device(struct at76_priv *priv,
 
 	wiphy->hw_version = priv->board_type;
 
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = ieee80211_register_hw(priv->hw);
 	if (ret) {
 		printk(KERN_ERR "cannot register mac80211 hw (status %d)!\n",
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index e12f62356fd1..27b110dc8cc6 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -513,7 +513,7 @@ struct atmel_private {
 	} station_state;
 
 	int operating_mode, power_mode;
-	time_t last_qual;
+	unsigned long last_qual;
 	int beacons_this_sec;
 	int channel;
 	int reg_domain, config_reg_domain;
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 52f3541ecbcf..d23aac7503d3 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -5598,6 +5598,8 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev)
 
 	hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	wl->hw_registred = false;
 	hw->max_rates = 2;
 	SET_IEEE80211_DEV(hw, dev->dev);
diff --git a/drivers/net/wireless/broadcom/b43/xmit.c b/drivers/net/wireless/broadcom/b43/xmit.c
index b068d5aeee24..1b9c191e2a22 100644
--- a/drivers/net/wireless/broadcom/b43/xmit.c
+++ b/drivers/net/wireless/broadcom/b43/xmit.c
@@ -694,7 +694,7 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 	if (unlikely(phystat0 & (B43_RX_PHYST0_PLCPHCF | B43_RX_PHYST0_PLCPFV)))
 		status.flag |= RX_FLAG_FAILED_PLCP_CRC;
 	if (phystat0 & B43_RX_PHYST0_SHORTPRMBL)
-		status.flag |= RX_FLAG_SHORTPRE;
+		status.enc_flags |= RX_ENC_FLAG_SHORTPRE;
 	if (macstat & B43_RX_MAC_DECERR) {
 		/* Decryption with the given key failed.
 		 * Drop the packet. We also won't be able to decrypt it with
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index cdafebb9c936..f1e3dad57629 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -3850,6 +3850,8 @@ static int b43legacy_wireless_init(struct ssb_device *dev)
 	else
 		SET_IEEE80211_PERM_ADDR(hw, sprom->il0mac);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	/* Get and initialize struct b43legacy_wl */
 	wl = hw_to_b43legacy_wl(hw);
 	memset(wl, 0, sizeof(*wl));
diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig
index ab42b1fea03c..9d99eb42d917 100644
--- a/drivers/net/wireless/broadcom/brcm80211/Kconfig
+++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig
@@ -18,14 +18,14 @@ config BRCMSMAC
 	  module, the driver will be called brcmsmac.ko.
 
 config BRCMFMAC
-	tristate "Broadcom IEEE802.11n embedded FullMAC WLAN driver"
+	tristate "Broadcom FullMAC WLAN driver"
 	depends on CFG80211
 	select BRCMUTIL
 	---help---
-	  This module adds support for embedded wireless adapters based on
-	  Broadcom IEEE802.11n FullMAC chipsets. It has to work with at least
-	  one of the bus interface support. If you choose to build a module,
-	  it'll be called brcmfmac.ko.
+	  This module adds support for wireless adapters based on Broadcom
+	  FullMAC chipsets. It has to work with at least one of the bus
+	  interface support. If you choose to build a module, it'll be called
+	  brcmfmac.ko.
 
 config BRCMFMAC_PROTO_BCDC
 	bool
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
index 0383ba559edc..1f5a9b948abf 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
@@ -25,7 +25,6 @@ brcmfmac-objs += \
 		chip.o \
 		fwil.o \
 		fweh.o \
-		fwsignal.o \
 		p2p.o \
 		proto.o \
 		common.o \
@@ -36,7 +35,8 @@ brcmfmac-objs += \
 		vendor.o \
 		pno.o
 brcmfmac-$(CONFIG_BRCMFMAC_PROTO_BCDC) += \
-		bcdc.o
+		bcdc.o \
+		fwsignal.o
 brcmfmac-$(CONFIG_BRCMFMAC_PROTO_MSGBUF) += \
 		commonring.o \
 		flowring.o \
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c
index 384b1873e7e3..9f2d0b0cf6e5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c
@@ -103,9 +103,17 @@ struct brcmf_bcdc {
 	u8 bus_header[BUS_HEADER_LEN];
 	struct brcmf_proto_bcdc_dcmd msg;
 	unsigned char buf[BRCMF_DCMD_MAXLEN];
+	struct brcmf_fws_info *fws;
 };
 
 
+struct brcmf_fws_info *drvr_to_fws(struct brcmf_pub *drvr)
+{
+	struct brcmf_bcdc *bcdc = drvr->proto->pd;
+
+	return bcdc->fws;
+}
+
 static int
 brcmf_proto_bcdc_msg(struct brcmf_pub *drvr, int ifidx, uint cmd, void *buf,
 		     uint len, bool set)
@@ -330,8 +338,9 @@ static int brcmf_proto_bcdc_tx_queue_data(struct brcmf_pub *drvr, int ifidx,
 					  struct sk_buff *skb)
 {
 	struct brcmf_if *ifp = brcmf_get_ifp(drvr, ifidx);
+	struct brcmf_bcdc *bcdc = drvr->proto->pd;
 
-	if (!brcmf_fws_queue_skbs(drvr->fws))
+	if (!brcmf_fws_queue_skbs(bcdc->fws))
 		return brcmf_proto_txdata(drvr, ifidx, 0, skb);
 
 	return brcmf_fws_process_skb(ifp, skb);
@@ -345,6 +354,36 @@ brcmf_proto_bcdc_txdata(struct brcmf_pub *drvr, int ifidx, u8 offset,
 	return brcmf_bus_txdata(drvr->bus_if, pktbuf);
 }
 
+void brcmf_proto_bcdc_txflowblock(struct device *dev, bool state)
+{
+	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
+	struct brcmf_pub *drvr = bus_if->drvr;
+
+	brcmf_dbg(TRACE, "Enter\n");
+
+	brcmf_fws_bus_blocked(drvr, state);
+}
+
+void
+brcmf_proto_bcdc_txcomplete(struct device *dev, struct sk_buff *txp,
+			    bool success)
+{
+	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
+	struct brcmf_bcdc *bcdc = bus_if->drvr->proto->pd;
+	struct brcmf_if *ifp;
+
+	/* await txstatus signal for firmware if active */
+	if (brcmf_fws_fc_active(bcdc->fws)) {
+		if (!success)
+			brcmf_fws_bustxfail(bcdc->fws, txp);
+	} else {
+		if (brcmf_proto_bcdc_hdrpull(bus_if->drvr, false, txp, &ifp))
+			brcmu_pkt_buf_free_skb(txp);
+		else
+			brcmf_txfinalize(ifp, txp, success);
+	}
+}
+
 static void
 brcmf_proto_bcdc_configure_addr_mode(struct brcmf_pub *drvr, int ifidx,
 				     enum proto_addr_mode addr_mode)
@@ -369,6 +408,38 @@ static void brcmf_proto_bcdc_rxreorder(struct brcmf_if *ifp,
 	brcmf_fws_rxreorder(ifp, skb);
 }
 
+static void
+brcmf_proto_bcdc_add_if(struct brcmf_if *ifp)
+{
+	brcmf_fws_add_interface(ifp);
+}
+
+static void
+brcmf_proto_bcdc_del_if(struct brcmf_if *ifp)
+{
+	brcmf_fws_del_interface(ifp);
+}
+
+static void
+brcmf_proto_bcdc_reset_if(struct brcmf_if *ifp)
+{
+	brcmf_fws_reset_interface(ifp);
+}
+
+static int
+brcmf_proto_bcdc_init_done(struct brcmf_pub *drvr)
+{
+	struct brcmf_bcdc *bcdc = drvr->proto->pd;
+	struct brcmf_fws_info *fws;
+
+	fws = brcmf_fws_attach(drvr);
+	if (IS_ERR(fws))
+		return PTR_ERR(fws);
+
+	bcdc->fws = fws;
+	return 0;
+}
+
 int brcmf_proto_bcdc_attach(struct brcmf_pub *drvr)
 {
 	struct brcmf_bcdc *bcdc;
@@ -392,6 +463,10 @@ int brcmf_proto_bcdc_attach(struct brcmf_pub *drvr)
 	drvr->proto->delete_peer = brcmf_proto_bcdc_delete_peer;
 	drvr->proto->add_tdls_peer = brcmf_proto_bcdc_add_tdls_peer;
 	drvr->proto->rxreorder = brcmf_proto_bcdc_rxreorder;
+	drvr->proto->add_if = brcmf_proto_bcdc_add_if;
+	drvr->proto->del_if = brcmf_proto_bcdc_del_if;
+	drvr->proto->reset_if = brcmf_proto_bcdc_reset_if;
+	drvr->proto->init_done = brcmf_proto_bcdc_init_done;
 	drvr->proto->pd = bcdc;
 
 	drvr->hdrlen += BCDC_HEADER_LEN + BRCMF_PROT_FW_SIGNAL_MAX_TXBYTES;
@@ -406,6 +481,9 @@ fail:
 
 void brcmf_proto_bcdc_detach(struct brcmf_pub *drvr)
 {
-	kfree(drvr->proto->pd);
+	struct brcmf_bcdc *bcdc = drvr->proto->pd;
+
 	drvr->proto->pd = NULL;
+	brcmf_fws_detach(bcdc->fws);
+	kfree(bcdc);
 }
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.h
index 6003179c0ceb..3b0e9eff21b5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.h
@@ -19,6 +19,10 @@
 #ifdef CONFIG_BRCMFMAC_PROTO_BCDC
 int brcmf_proto_bcdc_attach(struct brcmf_pub *drvr);
 void brcmf_proto_bcdc_detach(struct brcmf_pub *drvr);
+void brcmf_proto_bcdc_txflowblock(struct device *dev, bool state);
+void brcmf_proto_bcdc_txcomplete(struct device *dev, struct sk_buff *txp,
+				 bool success);
+struct brcmf_fws_info *drvr_to_fws(struct brcmf_pub *drvr);
 #else
 static inline int brcmf_proto_bcdc_attach(struct brcmf_pub *drvr) { return 0; }
 static inline void brcmf_proto_bcdc_detach(struct brcmf_pub *drvr) {}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 5bc2ba214735..9b970dc2b922 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -21,6 +21,7 @@
 #include <linux/pci_ids.h>
 #include <linux/sched.h>
 #include <linux/completion.h>
+#include <linux/interrupt.h>
 #include <linux/scatterlist.h>
 #include <linux/mmc/sdio.h>
 #include <linux/mmc/core.h>
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
index 76693df34742..b55c3293c4b4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
@@ -229,11 +229,6 @@ int brcmf_attach(struct device *dev, struct brcmf_mp_device *settings);
 void brcmf_detach(struct device *dev);
 /* Indication from bus module that dongle should be reset */
 void brcmf_dev_reset(struct device *dev);
-/* Indication from bus module to change flow-control state */
-void brcmf_txflowblock(struct device *dev, bool state);
-
-/* Notify the bus has transferred the tx packet to firmware */
-void brcmf_txcomplete(struct device *dev, struct sk_buff *txp, bool success);
 
 /* Configure the "global" bus state used by upper layers */
 void brcmf_bus_change_state(struct brcmf_bus *bus, enum brcmf_bus_state state);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 944b83cfc519..cd1d6730eab7 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -575,12 +575,11 @@ static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp)
  *
  * @wiphy: wiphy device of new interface.
  * @name: name of the new interface.
- * @flags: not used.
  * @params: contains mac address for AP device.
  */
 static
 struct wireless_dev *brcmf_ap_add_vif(struct wiphy *wiphy, const char *name,
-				      u32 *flags, struct vif_params *params)
+				      struct vif_params *params)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
@@ -653,7 +652,6 @@ static struct wireless_dev *brcmf_cfg80211_add_iface(struct wiphy *wiphy,
 						     const char *name,
 						     unsigned char name_assign_type,
 						     enum nl80211_iftype type,
-						     u32 *flags,
 						     struct vif_params *params)
 {
 	struct wireless_dev *wdev;
@@ -674,12 +672,12 @@ static struct wireless_dev *brcmf_cfg80211_add_iface(struct wiphy *wiphy,
 	case NL80211_IFTYPE_MESH_POINT:
 		return ERR_PTR(-EOPNOTSUPP);
 	case NL80211_IFTYPE_AP:
-		wdev = brcmf_ap_add_vif(wiphy, name, flags, params);
+		wdev = brcmf_ap_add_vif(wiphy, name, params);
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_P2P_GO:
 	case NL80211_IFTYPE_P2P_DEVICE:
-		wdev = brcmf_p2p_add_vif(wiphy, name, name_assign_type, type, flags, params);
+		wdev = brcmf_p2p_add_vif(wiphy, name, name_assign_type, type, params);
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
 	default:
@@ -764,7 +762,7 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg,
 		brcmf_dbg(SCAN, "scheduled scan completed\n");
 		cfg->internal_escan = false;
 		if (!aborted)
-			cfg80211_sched_scan_results(cfg_to_wiphy(cfg));
+			cfg80211_sched_scan_results(cfg_to_wiphy(cfg), 0);
 	} else if (scan_request) {
 		struct cfg80211_scan_info info = {
 			.aborted = aborted,
@@ -858,7 +856,7 @@ int brcmf_cfg80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev)
 
 static s32
 brcmf_cfg80211_change_iface(struct wiphy *wiphy, struct net_device *ndev,
-			 enum nl80211_iftype type, u32 *flags,
+			 enum nl80211_iftype type,
 			 struct vif_params *params)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_priv(wiphy);
@@ -3097,6 +3095,9 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp,
 
 	status = e->status;
 
+	if (status == BRCMF_E_STATUS_ABORT)
+		goto exit;
+
 	if (!test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status)) {
 		brcmf_err("scan not ready, bsscfgidx=%d\n", ifp->bsscfgidx);
 		return -EPERM;
@@ -3213,7 +3214,7 @@ static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req,
 {
 	struct ieee80211_channel *chan;
 	enum nl80211_band band;
-	int freq;
+	int freq, i;
 
 	if (channel <= CH_MAX_2G_CHANNEL)
 		band = NL80211_BAND_2GHZ;
@@ -3228,10 +3229,22 @@ static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req,
 	if (!chan)
 		return -EINVAL;
 
-	req->channels[req->n_channels++] = chan;
-	memcpy(req->ssids[req->n_ssids].ssid, ssid, ssid_len);
-	req->ssids[req->n_ssids++].ssid_len = ssid_len;
+	for (i = 0; i < req->n_channels; i++) {
+		if (req->channels[i] == chan)
+			break;
+	}
+	if (i == req->n_channels)
+		req->channels[req->n_channels++] = chan;
 
+	for (i = 0; i < req->n_ssids; i++) {
+		if (req->ssids[i].ssid_len == ssid_len &&
+		    !memcmp(req->ssids[i].ssid, ssid, ssid_len))
+			break;
+	}
+	if (i == req->n_ssids) {
+		memcpy(req->ssids[req->n_ssids].ssid, ssid, ssid_len);
+		req->ssids[req->n_ssids++].ssid_len = ssid_len;
+	}
 	return 0;
 }
 
@@ -3297,6 +3310,7 @@ brcmf_notify_sched_scan_results(struct brcmf_if *ifp,
 	struct brcmf_pno_scanresults_le *pfn_result;
 	u32 result_count;
 	u32 status;
+	u32 datalen;
 
 	brcmf_dbg(SCAN, "Enter\n");
 
@@ -3323,6 +3337,14 @@ brcmf_notify_sched_scan_results(struct brcmf_if *ifp,
 		brcmf_err("FALSE PNO Event. (pfn_count == 0)\n");
 		goto out_err;
 	}
+
+	netinfo_start = brcmf_get_netinfo_array(pfn_result);
+	datalen = e->datalen - ((void *)netinfo_start - (void *)pfn_result);
+	if (datalen < result_count * sizeof(*netinfo)) {
+		brcmf_err("insufficient event data\n");
+		goto out_err;
+	}
+
 	request = brcmf_alloc_internal_escan_request(wiphy,
 						     result_count);
 	if (!request) {
@@ -3330,17 +3352,11 @@ brcmf_notify_sched_scan_results(struct brcmf_if *ifp,
 		goto out_err;
 	}
 
-	netinfo_start = brcmf_get_netinfo_array(pfn_result);
-
 	for (i = 0; i < result_count; i++) {
 		netinfo = &netinfo_start[i];
-		if (!netinfo) {
-			brcmf_err("Invalid netinfo ptr. index: %d\n",
-				  i);
-			err = -EINVAL;
-			goto out_err;
-		}
 
+		if (netinfo->SSID_len > IEEE80211_MAX_SSID_LEN)
+			netinfo->SSID_len = IEEE80211_MAX_SSID_LEN;
 		brcmf_dbg(SCAN, "SSID:%.32s Channel:%d\n",
 			  netinfo->SSID, netinfo->channel);
 		err = brcmf_internal_escan_add_info(request,
@@ -3356,7 +3372,7 @@ brcmf_notify_sched_scan_results(struct brcmf_if *ifp,
 		goto free_req;
 
 out_err:
-	cfg80211_sched_scan_stopped(wiphy);
+	cfg80211_sched_scan_stopped(wiphy, 0);
 free_req:
 	kfree(request);
 	return err;
@@ -3389,7 +3405,7 @@ brcmf_cfg80211_sched_scan_start(struct wiphy *wiphy,
 }
 
 static int brcmf_cfg80211_sched_scan_stop(struct wiphy *wiphy,
-					  struct net_device *ndev)
+					  struct net_device *ndev, u64 reqid)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_if *ifp = netdev_priv(ndev);
@@ -3591,7 +3607,7 @@ static s32 brcmf_cfg80211_resume(struct wiphy *wiphy)
 				      cfg->wowl.pre_pmmode);
 		cfg->wowl.active = false;
 		if (cfg->wowl.nd_enabled) {
-			brcmf_cfg80211_sched_scan_stop(cfg->wiphy, ifp->ndev);
+			brcmf_cfg80211_sched_scan_stop(cfg->wiphy, ifp->ndev, 0);
 			brcmf_fweh_unregister(cfg->pub, BRCMF_E_PFN_NET_FOUND);
 			brcmf_fweh_register(cfg->pub, BRCMF_E_PFN_NET_FOUND,
 					    brcmf_notify_sched_scan_results);
@@ -3675,7 +3691,7 @@ static s32 brcmf_cfg80211_suspend(struct wiphy *wiphy,
 
 	/* Stop scheduled scan */
 	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_PNO))
-		brcmf_cfg80211_sched_scan_stop(wiphy, ndev);
+		brcmf_cfg80211_sched_scan_stop(wiphy, ndev, 0);
 
 	/* end any scanning */
 	if (test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status))
@@ -5343,6 +5359,7 @@ brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg,
 	struct ieee80211_supported_band *band;
 	struct brcmf_bss_info_le *bi;
 	struct brcmu_chan ch;
+	struct cfg80211_roam_info roam_info = {};
 	u32 freq;
 	s32 err = 0;
 	u8 *buf;
@@ -5381,9 +5398,15 @@ brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg,
 
 done:
 	kfree(buf);
-	cfg80211_roamed(ndev, notify_channel, (u8 *)profile->bssid,
-			conn_info->req_ie, conn_info->req_ie_len,
-			conn_info->resp_ie, conn_info->resp_ie_len, GFP_KERNEL);
+
+	roam_info.channel = notify_channel;
+	roam_info.bssid = profile->bssid;
+	roam_info.req_ie = conn_info->req_ie;
+	roam_info.req_ie_len = conn_info->req_ie_len;
+	roam_info.resp_ie = conn_info->resp_ie;
+	roam_info.resp_ie_len = conn_info->resp_ie_len;
+
+	cfg80211_roamed(ndev, &roam_info, GFP_KERNEL);
 	brcmf_dbg(CONN, "Report roaming result\n");
 
 	set_bit(BRCMF_VIF_STATUS_CONNECTED, &ifp->vif->sme_state);
@@ -6358,11 +6381,11 @@ err:
 static void brcmf_wiphy_pno_params(struct wiphy *wiphy)
 {
 	/* scheduled scan settings */
+	wiphy->max_sched_scan_reqs = 1;
 	wiphy->max_sched_scan_ssids = BRCMF_PNO_MAX_PFN_COUNT;
 	wiphy->max_match_sets = BRCMF_PNO_MAX_PFN_COUNT;
 	wiphy->max_sched_scan_ie_len = BRCMF_SCAN_IE_LEN_MAX;
 	wiphy->max_sched_scan_plan_interval = BRCMF_PNO_SCHED_SCAN_MAX_PERIOD;
-	wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
 }
 
 #ifdef CONFIG_PM
@@ -6450,7 +6473,8 @@ static int brcmf_setup_wiphy(struct wiphy *wiphy, struct brcmf_if *ifp)
 				    BIT(NL80211_BSS_SELECT_ATTR_BAND_PREF) |
 				    BIT(NL80211_BSS_SELECT_ATTR_RSSI_ADJUST);
 
-	wiphy->flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT |
+	wiphy->flags |= WIPHY_FLAG_NETNS_OK |
+			WIPHY_FLAG_PS_ON_BY_DEFAULT |
 			WIPHY_FLAG_OFFCHAN_TX |
 			WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
 	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_TDLS))
@@ -6549,7 +6573,7 @@ static s32 brcmf_config_dongle(struct brcmf_cfg80211_info *cfg)
 	if (err)
 		goto default_conf_out;
 	err = brcmf_cfg80211_change_iface(wdev->wiphy, ndev, wdev->iftype,
-					  NULL, NULL);
+					  NULL);
 	if (err)
 		goto default_conf_out;
 
@@ -6736,6 +6760,10 @@ static void brcmf_cfg80211_reg_notifier(struct wiphy *wiphy,
 	s32 err;
 	int i;
 
+	/* The country code gets set to "00" by default at boot, ignore */
+	if (req->alpha2[0] == '0' && req->alpha2[1] == '0')
+		return;
+
 	/* ignore non-ISO3166 country codes */
 	for (i = 0; i < sizeof(req->alpha2); i++)
 		if (req->alpha2[i] < 'A' || req->alpha2[i] > 'Z') {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index 33b133f7e63a..7a2b49587b4d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -161,7 +161,7 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp)
 	strsep(&ptr, "\n");
 
 	/* Print fw version info */
-	brcmf_err("Firmware version = %s\n", buf);
+	brcmf_info("Firmware version = %s\n", buf);
 
 	/* locate firmware version number for ethtool */
 	ptr = strrchr(buf, ' ') + 1;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index 60da86a8d95b..a3d82368f1a9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -32,7 +32,6 @@
 #include "p2p.h"
 #include "cfg80211.h"
 #include "fwil.h"
-#include "fwsignal.h"
 #include "feature.h"
 #include "proto.h"
 #include "pcie.h"
@@ -198,7 +197,7 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 	int ret;
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_pub *drvr = ifp->drvr;
-	struct ethhdr *eh = (struct ethhdr *)(skb->data);
+	struct ethhdr *eh;
 
 	brcmf_dbg(DATA, "Enter, bsscfgidx=%d\n", ifp->bsscfgidx);
 
@@ -211,22 +210,13 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 		goto done;
 	}
 
-	/* Make sure there's enough room for any header */
-	if (skb_headroom(skb) < drvr->hdrlen) {
-		struct sk_buff *skb2;
-
-		brcmf_dbg(INFO, "%s: insufficient headroom\n",
+	/* Make sure there's enough writable headroom*/
+	ret = skb_cow_head(skb, drvr->hdrlen);
+	if (ret < 0) {
+		brcmf_err("%s: skb_cow_head failed\n",
 			  brcmf_ifname(ifp));
-		drvr->bus_if->tx_realloc++;
-		skb2 = skb_realloc_headroom(skb, drvr->hdrlen);
 		dev_kfree_skb(skb);
-		skb = skb2;
-		if (skb == NULL) {
-			brcmf_err("%s: skb_realloc_headroom failed\n",
-				  brcmf_ifname(ifp));
-			ret = -ENOMEM;
-			goto done;
-		}
+		goto done;
 	}
 
 	/* validate length for ether packet */
@@ -236,6 +226,8 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 		goto done;
 	}
 
+	eh = (struct ethhdr *)(skb->data);
+
 	if (eh->h_proto == htons(ETH_P_PAE))
 		atomic_inc(&ifp->pend_8021x_cnt);
 
@@ -283,16 +275,6 @@ void brcmf_txflowblock_if(struct brcmf_if *ifp,
 	spin_unlock_irqrestore(&ifp->netif_stop_lock, flags);
 }
 
-void brcmf_txflowblock(struct device *dev, bool state)
-{
-	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
-	struct brcmf_pub *drvr = bus_if->drvr;
-
-	brcmf_dbg(TRACE, "Enter\n");
-
-	brcmf_fws_bus_blocked(drvr, state);
-}
-
 void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb)
 {
 	if (skb->pkt_type == PACKET_MULTICAST)
@@ -393,24 +375,6 @@ void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success)
 	brcmu_pkt_buf_free_skb(txp);
 }
 
-void brcmf_txcomplete(struct device *dev, struct sk_buff *txp, bool success)
-{
-	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
-	struct brcmf_pub *drvr = bus_if->drvr;
-	struct brcmf_if *ifp;
-
-	/* await txstatus signal for firmware if active */
-	if (brcmf_fws_fc_active(drvr->fws)) {
-		if (!success)
-			brcmf_fws_bustxfail(drvr->fws, txp);
-	} else {
-		if (brcmf_proto_hdrpull(drvr, false, txp, &ifp))
-			brcmu_pkt_buf_free_skb(txp);
-		else
-			brcmf_txfinalize(ifp, txp, success);
-	}
-}
-
 static void brcmf_ethtool_get_drvinfo(struct net_device *ndev,
 				    struct ethtool_drvinfo *info)
 {
@@ -504,8 +468,9 @@ int brcmf_net_attach(struct brcmf_if *ifp, bool rtnl_locked)
 	ndev->needed_headroom += drvr->hdrlen;
 	ndev->ethtool_ops = &brcmf_ethtool_ops;
 
-	/* set the mac address */
+	/* set the mac address & netns */
 	memcpy(ndev->dev_addr, ifp->mac_addr, ETH_ALEN);
+	dev_net_set(ndev, wiphy_net(cfg_to_wiphy(drvr->config)));
 
 	INIT_WORK(&ifp->multicast_work, _brcmf_set_multicast_list);
 	INIT_WORK(&ifp->ndoffload_work, _brcmf_update_ndtable);
@@ -734,10 +699,28 @@ void brcmf_remove_interface(struct brcmf_if *ifp, bool rtnl_locked)
 		return;
 	brcmf_dbg(TRACE, "Enter, bsscfgidx=%d, ifidx=%d\n", ifp->bsscfgidx,
 		  ifp->ifidx);
-	brcmf_fws_del_interface(ifp);
+	brcmf_proto_del_if(ifp->drvr, ifp);
 	brcmf_del_if(ifp->drvr, ifp->bsscfgidx, rtnl_locked);
 }
 
+static int brcmf_psm_watchdog_notify(struct brcmf_if *ifp,
+				     const struct brcmf_event_msg *evtmsg,
+				     void *data)
+{
+	int err;
+
+	brcmf_dbg(TRACE, "enter: bsscfgidx=%d\n", ifp->bsscfgidx);
+
+	brcmf_err("PSM's watchdog has fired!\n");
+
+	err = brcmf_debug_create_memdump(ifp->drvr->bus_if, data,
+					 evtmsg->datalen);
+	if (err)
+		brcmf_err("Failed to get memory dump, %d\n", err);
+
+	return err;
+}
+
 #ifdef CONFIG_INET
 #define ARPOL_MAX_ENTRIES	8
 static int brcmf_inetaddr_changed(struct notifier_block *nb,
@@ -917,6 +900,10 @@ int brcmf_attach(struct device *dev, struct brcmf_mp_device *settings)
 		goto fail;
 	}
 
+	/* Attach to events important for core code */
+	brcmf_fweh_register(drvr, BRCMF_E_PSM_WATCHDOG,
+			    brcmf_psm_watchdog_notify);
+
 	/* attach firmware event handler */
 	brcmf_fweh_attach(drvr);
 
@@ -992,11 +979,11 @@ int brcmf_bus_started(struct device *dev)
 	}
 	brcmf_feat_attach(drvr);
 
-	ret = brcmf_fws_init(drvr);
+	ret = brcmf_proto_init_done(drvr);
 	if (ret < 0)
 		goto fail;
 
-	brcmf_fws_add_interface(ifp);
+	brcmf_proto_add_if(drvr, ifp);
 
 	drvr->config = brcmf_cfg80211_attach(drvr, bus_if->dev,
 					     drvr->settings->p2p_enable);
@@ -1040,10 +1027,6 @@ fail:
 		brcmf_cfg80211_detach(drvr->config);
 		drvr->config = NULL;
 	}
-	if (drvr->fws) {
-		brcmf_fws_del_interface(ifp);
-		brcmf_fws_deinit(drvr);
-	}
 	brcmf_net_detach(ifp->ndev, false);
 	if (p2p_ifp)
 		brcmf_net_detach(p2p_ifp->ndev, false);
@@ -1109,8 +1092,6 @@ void brcmf_detach(struct device *dev)
 
 	brcmf_cfg80211_detach(drvr->config);
 
-	brcmf_fws_deinit(drvr);
-
 	brcmf_bus_stop(drvr->bus_if);
 
 	brcmf_proto_detach(drvr);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
index 6aecd8dfd824..a4dd313140f3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
@@ -127,8 +127,6 @@ struct brcmf_pub {
 
 	struct brcmf_fweh_info fweh;
 
-	struct brcmf_fws_info *fws;
-
 	struct brcmf_ampdu_rx_reorder
 		*reorder_flows[BRCMF_AMPDU_RX_REORDER_MAXFLOWS];
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.c
index f4644cf371c7..1447a8352383 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.c
@@ -27,8 +27,8 @@
 
 static struct dentry *root_folder;
 
-static int brcmf_debug_create_memdump(struct brcmf_bus *bus, const void *data,
-				      size_t len)
+int brcmf_debug_create_memdump(struct brcmf_bus *bus, const void *data,
+			       size_t len)
 {
 	void *dump;
 	size_t ramsize;
@@ -54,24 +54,6 @@ static int brcmf_debug_create_memdump(struct brcmf_bus *bus, const void *data,
 	return 0;
 }
 
-static int brcmf_debug_psm_watchdog_notify(struct brcmf_if *ifp,
-					   const struct brcmf_event_msg *evtmsg,
-					   void *data)
-{
-	int err;
-
-	brcmf_dbg(TRACE, "enter: bsscfgidx=%d\n", ifp->bsscfgidx);
-
-	brcmf_err("PSM's watchdog has fired!\n");
-
-	err = brcmf_debug_create_memdump(ifp->drvr->bus_if, data,
-					 evtmsg->datalen);
-	if (err)
-		brcmf_err("Failed to get memory dump, %d\n", err);
-
-	return err;
-}
-
 void brcmf_debugfs_init(void)
 {
 	root_folder = debugfs_create_dir(KBUILD_MODNAME, NULL);
@@ -99,9 +81,7 @@ int brcmf_debug_attach(struct brcmf_pub *drvr)
 	if (IS_ERR(drvr->dbgfs_dir))
 		return PTR_ERR(drvr->dbgfs_dir);
 
-
-	return brcmf_fweh_register(drvr, BRCMF_E_PSM_WATCHDOG,
-				   brcmf_debug_psm_watchdog_notify);
+	return 0;
 }
 
 void brcmf_debug_detach(struct brcmf_pub *drvr)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h
index 066126123e96..fe264a5798f1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h
@@ -59,6 +59,10 @@ void __brcmf_err(const char *func, const char *fmt, ...);
 	} while (0)
 
 #if defined(DEBUG) || defined(CONFIG_BRCM_TRACING)
+
+/* For debug/tracing purposes treat info messages as errors */
+#define brcmf_info brcmf_err
+
 __printf(3, 4)
 void __brcmf_dbg(u32 level, const char *func, const char *fmt, ...);
 #define brcmf_dbg(level, fmt, ...)				\
@@ -77,6 +81,11 @@ do {								\
 
 #else /* defined(DEBUG) || defined(CONFIG_BRCM_TRACING) */
 
+#define brcmf_info(fmt, ...)						\
+	do {								\
+		pr_info("%s: " fmt, __func__, ##__VA_ARGS__);		\
+	} while (0)
+
 #define brcmf_dbg(level, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
 
 #define BRCMF_DATA_ON()		0
@@ -99,6 +108,7 @@ do {									\
 
 extern int brcmf_msg_level;
 
+struct brcmf_bus;
 struct brcmf_pub;
 #ifdef DEBUG
 void brcmf_debugfs_init(void);
@@ -108,6 +118,8 @@ void brcmf_debug_detach(struct brcmf_pub *drvr);
 struct dentry *brcmf_debugfs_get_devdir(struct brcmf_pub *drvr);
 int brcmf_debugfs_add_entry(struct brcmf_pub *drvr, const char *fn,
 			    int (*read_fn)(struct seq_file *seq, void *data));
+int brcmf_debug_create_memdump(struct brcmf_bus *bus, const void *data,
+			       size_t len);
 #else
 static inline void brcmf_debugfs_init(void)
 {
@@ -128,6 +140,12 @@ int brcmf_debugfs_add_entry(struct brcmf_pub *drvr, const char *fn,
 {
 	return 0;
 }
+static inline
+int brcmf_debug_create_memdump(struct brcmf_bus *bus, const void *data,
+			       size_t len)
+{
+	return 0;
+}
 #endif
 
 #endif /* BRCMFMAC_DEBUG_H */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
index c79306b57532..4eb1e1ce9ace 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
@@ -22,9 +22,9 @@
 #include "core.h"
 #include "debug.h"
 #include "tracepoint.h"
-#include "fwsignal.h"
 #include "fweh.h"
 #include "fwil.h"
+#include "proto.h"
 
 /**
  * struct brcmf_fweh_queue_item - event item on event queue.
@@ -172,14 +172,14 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr,
 		if (IS_ERR(ifp))
 			return;
 		if (!is_p2pdev)
-			brcmf_fws_add_interface(ifp);
+			brcmf_proto_add_if(drvr, ifp);
 		if (!drvr->fweh.evt_handler[BRCMF_E_IF])
 			if (brcmf_net_attach(ifp, false) < 0)
 				return;
 	}
 
 	if (ifp && ifevent->action == BRCMF_E_IF_CHANGE)
-		brcmf_fws_reset_interface(ifp);
+		brcmf_proto_reset_if(drvr, ifp);
 
 	err = brcmf_fweh_call_event_handler(ifp, emsg->event_code, emsg, data);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index 5f1a5929cb30..72373e59308e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -36,6 +36,7 @@
 #include "p2p.h"
 #include "cfg80211.h"
 #include "proto.h"
+#include "bcdc.h"
 #include "common.h"
 
 /**
@@ -1586,7 +1587,7 @@ static int brcmf_fws_notify_credit_map(struct brcmf_if *ifp,
 				       const struct brcmf_event_msg *e,
 				       void *data)
 {
-	struct brcmf_fws_info *fws = ifp->drvr->fws;
+	struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr);
 	int i;
 	u8 *credits = data;
 
@@ -1617,7 +1618,7 @@ static int brcmf_fws_notify_bcmc_credit_support(struct brcmf_if *ifp,
 						const struct brcmf_event_msg *e,
 						void *data)
 {
-	struct brcmf_fws_info *fws = ifp->drvr->fws;
+	struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr);
 
 	if (fws) {
 		brcmf_fws_lock(fws);
@@ -1826,7 +1827,7 @@ netif_rx:
 void brcmf_fws_hdrpull(struct brcmf_if *ifp, s16 siglen, struct sk_buff *skb)
 {
 	struct brcmf_skb_reorder_data *rd;
-	struct brcmf_fws_info *fws = ifp->drvr->fws;
+	struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr);
 	u8 *signal_data;
 	s16 data_len;
 	u8 type;
@@ -2091,8 +2092,7 @@ static int brcmf_fws_assign_htod(struct brcmf_fws_info *fws, struct sk_buff *p,
 
 int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 {
-	struct brcmf_pub *drvr = ifp->drvr;
-	struct brcmf_fws_info *fws = drvr->fws;
+	struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr);
 	struct brcmf_skbuff_cb *skcb = brcmf_skbcb(skb);
 	struct ethhdr *eh = (struct ethhdr *)(skb->data);
 	int fifo = BRCMF_FWS_FIFO_BCMC;
@@ -2142,10 +2142,10 @@ void brcmf_fws_reset_interface(struct brcmf_if *ifp)
 
 void brcmf_fws_add_interface(struct brcmf_if *ifp)
 {
-	struct brcmf_fws_info *fws = ifp->drvr->fws;
+	struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr);
 	struct brcmf_fws_mac_descriptor *entry;
 
-	if (!ifp->ndev)
+	if (!ifp->ndev || fws->fcmode == BRCMF_FWS_FCMODE_NONE)
 		return;
 
 	entry = &fws->desc.iface[ifp->ifidx];
@@ -2160,16 +2160,17 @@ void brcmf_fws_add_interface(struct brcmf_if *ifp)
 void brcmf_fws_del_interface(struct brcmf_if *ifp)
 {
 	struct brcmf_fws_mac_descriptor *entry = ifp->fws_desc;
+	struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr);
 
 	if (!entry)
 		return;
 
-	brcmf_fws_lock(ifp->drvr->fws);
+	brcmf_fws_lock(fws);
 	ifp->fws_desc = NULL;
 	brcmf_dbg(TRACE, "deleting %s\n", entry->name);
 	brcmf_fws_macdesc_deinit(entry);
-	brcmf_fws_cleanup(ifp->drvr->fws, ifp->ifidx);
-	brcmf_fws_unlock(ifp->drvr->fws);
+	brcmf_fws_cleanup(fws, ifp->ifidx);
+	brcmf_fws_unlock(fws);
 }
 
 static void brcmf_fws_dequeue_worker(struct work_struct *worker)
@@ -2243,7 +2244,7 @@ static void brcmf_fws_dequeue_worker(struct work_struct *worker)
 static int brcmf_debugfs_fws_stats_read(struct seq_file *seq, void *data)
 {
 	struct brcmf_bus *bus_if = dev_get_drvdata(seq->private);
-	struct brcmf_fws_stats *fwstats = &bus_if->drvr->fws->stats;
+	struct brcmf_fws_stats *fwstats = &(drvr_to_fws(bus_if->drvr)->stats);
 
 	seq_printf(seq,
 		   "header_pulls:      %u\n"
@@ -2308,7 +2309,7 @@ static int brcmf_debugfs_fws_stats_read(struct seq_file *seq, void *data)
 }
 #endif
 
-int brcmf_fws_init(struct brcmf_pub *drvr)
+struct brcmf_fws_info *brcmf_fws_attach(struct brcmf_pub *drvr)
 {
 	struct brcmf_fws_info *fws;
 	struct brcmf_if *ifp;
@@ -2316,17 +2317,15 @@ int brcmf_fws_init(struct brcmf_pub *drvr)
 	int rc;
 	u32 mode;
 
-	drvr->fws = kzalloc(sizeof(*(drvr->fws)), GFP_KERNEL);
-	if (!drvr->fws) {
+	fws = kzalloc(sizeof(*fws), GFP_KERNEL);
+	if (!fws) {
 		rc = -ENOMEM;
 		goto fail;
 	}
 
-	fws = drvr->fws;
-
 	spin_lock_init(&fws->spinlock);
 
-	/* set linkage back */
+	/* store drvr reference */
 	fws->drvr = drvr;
 	fws->fcmode = drvr->settings->fcmode;
 
@@ -2334,7 +2333,7 @@ int brcmf_fws_init(struct brcmf_pub *drvr)
 	    (fws->fcmode == BRCMF_FWS_FCMODE_NONE)) {
 		fws->avoid_queueing = true;
 		brcmf_dbg(INFO, "FWS queueing will be avoided\n");
-		return 0;
+		return fws;
 	}
 
 	fws->fws_wq = create_singlethread_workqueue("brcmf_fws_wq");
@@ -2396,6 +2395,7 @@ int brcmf_fws_init(struct brcmf_pub *drvr)
 	brcmf_fws_hanger_init(&fws->hanger);
 	brcmf_fws_macdesc_init(&fws->desc.other, NULL, 0);
 	brcmf_fws_macdesc_set_name(fws, &fws->desc.other);
+	brcmf_dbg(INFO, "added %s\n", fws->desc.other.name);
 	brcmu_pktq_init(&fws->desc.other.psq, BRCMF_FWS_PSQ_PREC_COUNT,
 			BRCMF_FWS_PSQ_LEN);
 
@@ -2405,27 +2405,24 @@ int brcmf_fws_init(struct brcmf_pub *drvr)
 
 	brcmf_dbg(INFO, "%s bdcv2 tlv signaling [%x]\n",
 		  fws->fw_signals ? "enabled" : "disabled", tlv);
-	return 0;
+	return fws;
 
 fail:
-	brcmf_fws_deinit(drvr);
-	return rc;
+	brcmf_fws_detach(fws);
+	return ERR_PTR(rc);
 }
 
-void brcmf_fws_deinit(struct brcmf_pub *drvr)
+void brcmf_fws_detach(struct brcmf_fws_info *fws)
 {
-	struct brcmf_fws_info *fws = drvr->fws;
-
 	if (!fws)
 		return;
 
-	if (drvr->fws->fws_wq)
-		destroy_workqueue(drvr->fws->fws_wq);
+	if (fws->fws_wq)
+		destroy_workqueue(fws->fws_wq);
 
 	/* cleanup */
 	brcmf_fws_lock(fws);
 	brcmf_fws_cleanup(fws, -1);
-	drvr->fws = NULL;
 	brcmf_fws_unlock(fws);
 
 	/* free top structure */
@@ -2461,7 +2458,7 @@ void brcmf_fws_bustxfail(struct brcmf_fws_info *fws, struct sk_buff *skb)
 
 void brcmf_fws_bus_blocked(struct brcmf_pub *drvr, bool flow_blocked)
 {
-	struct brcmf_fws_info *fws = drvr->fws;
+	struct brcmf_fws_info *fws = drvr_to_fws(drvr);
 	struct brcmf_if *ifp;
 	int i;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h
index 96df66073b2a..ba07bd972002 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h
@@ -18,8 +18,8 @@
 #ifndef FWSIGNAL_H_
 #define FWSIGNAL_H_
 
-int brcmf_fws_init(struct brcmf_pub *drvr);
-void brcmf_fws_deinit(struct brcmf_pub *drvr);
+struct brcmf_fws_info *brcmf_fws_attach(struct brcmf_pub *drvr);
+void brcmf_fws_detach(struct brcmf_fws_info *fws);
 bool brcmf_fws_queue_skbs(struct brcmf_fws_info *fws);
 bool brcmf_fws_fc_active(struct brcmf_fws_info *fws);
 void brcmf_fws_hdrpull(struct brcmf_if *ifp, s16 siglen, struct sk_buff *skb);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index de19c7c92bc6..aa299c47bfa2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2141,12 +2141,11 @@ fail:
  * @name: name of the new interface.
  * @name_assign_type: origin of the interface name
  * @type: nl80211 interface type.
- * @flags: not used.
  * @params: contains mac address for P2P device.
  */
 struct wireless_dev *brcmf_p2p_add_vif(struct wiphy *wiphy, const char *name,
 				       unsigned char name_assign_type,
-				       enum nl80211_iftype type, u32 *flags,
+				       enum nl80211_iftype type,
 				       struct vif_params *params)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
@@ -2238,14 +2237,16 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev)
 	struct brcmf_cfg80211_info *cfg = wiphy_priv(wiphy);
 	struct brcmf_p2p_info *p2p = &cfg->p2p;
 	struct brcmf_cfg80211_vif *vif;
+	enum nl80211_iftype iftype;
 	bool wait_for_disable = false;
 	int err;
 
 	brcmf_dbg(TRACE, "delete P2P vif\n");
 	vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev);
 
+	iftype = vif->wdev.iftype;
 	brcmf_cfg80211_arm_vif_event(cfg, vif);
-	switch (vif->wdev.iftype) {
+	switch (iftype) {
 	case NL80211_IFTYPE_P2P_CLIENT:
 		if (test_bit(BRCMF_VIF_STATUS_DISCONNECTING, &vif->sme_state))
 			wait_for_disable = true;
@@ -2275,7 +2276,7 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev)
 					    BRCMF_P2P_DISABLE_TIMEOUT);
 
 	err = 0;
-	if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE) {
+	if (iftype != NL80211_IFTYPE_P2P_DEVICE) {
 		brcmf_vif_clear_mgmt_ies(vif);
 		err = brcmf_p2p_release_p2p_if(vif);
 	}
@@ -2291,7 +2292,7 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev)
 	brcmf_remove_interface(vif->ifp, true);
 
 	brcmf_cfg80211_arm_vif_event(cfg, NULL);
-	if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE)
+	if (iftype != NL80211_IFTYPE_P2P_DEVICE)
 		p2p->bss_idx[P2PAPI_BSSCFG_CONNECTION].vif = NULL;
 
 	return err;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h
index 8ce9447533ef..0e8b34d2d85c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h
@@ -150,7 +150,7 @@ s32 brcmf_p2p_attach(struct brcmf_cfg80211_info *cfg, bool p2pdev_forced);
 void brcmf_p2p_detach(struct brcmf_p2p_info *p2p);
 struct wireless_dev *brcmf_p2p_add_vif(struct wiphy *wiphy, const char *name,
 				       unsigned char name_assign_type,
-				       enum nl80211_iftype type, u32 *flags,
+				       enum nl80211_iftype type,
 				       struct vif_params *params);
 int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev);
 int brcmf_p2p_ifchange(struct brcmf_cfg80211_info *cfg,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 6fae4cf3f6ab..f36b96dc6acd 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1877,6 +1877,7 @@ static int brcmf_pcie_pm_enter_D3(struct device *dev)
 			   BRCMF_PCIE_MBDATA_TIMEOUT);
 	if (!devinfo->mbdata_completed) {
 		brcmf_err("Timeout on response for entering D3 substate\n");
+		brcmf_bus_change_state(bus, BRCMF_BUS_UP);
 		return -EIO;
 	}
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c
index 9a25e79a46cf..6c3bde83d070 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c
@@ -182,7 +182,6 @@ int brcmf_pno_clean(struct brcmf_if *ifp)
 int brcmf_pno_start_sched_scan(struct brcmf_if *ifp,
 			       struct cfg80211_sched_scan_request *req)
 {
-	struct brcmu_d11inf *d11inf;
 	struct brcmf_pno_config_le pno_cfg;
 	struct cfg80211_ssid *ssid;
 	u16 chan;
@@ -209,7 +208,6 @@ int brcmf_pno_start_sched_scan(struct brcmf_if *ifp,
 	}
 
 	/* configure channels to use */
-	d11inf = &ifp->drvr->config->d11inf;
 	for (i = 0; i < req->n_channels; i++) {
 		chan = req->channels[i]->hw_value;
 		pno_cfg.channel_list[i] = cpu_to_le16(chan);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h
index 34b59feedeba..2404f8a7c31c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h
@@ -44,6 +44,10 @@ struct brcmf_proto {
 	void (*add_tdls_peer)(struct brcmf_pub *drvr, int ifidx,
 			      u8 peer[ETH_ALEN]);
 	void (*rxreorder)(struct brcmf_if *ifp, struct sk_buff *skb);
+	void (*add_if)(struct brcmf_if *ifp);
+	void (*del_if)(struct brcmf_if *ifp);
+	void (*reset_if)(struct brcmf_if *ifp);
+	int (*init_done)(struct brcmf_pub *drvr);
 	void *pd;
 };
 
@@ -118,4 +122,36 @@ brcmf_proto_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb)
 	ifp->drvr->proto->rxreorder(ifp, skb);
 }
 
+static inline void
+brcmf_proto_add_if(struct brcmf_pub *drvr, struct brcmf_if *ifp)
+{
+	if (!drvr->proto->add_if)
+		return;
+	drvr->proto->add_if(ifp);
+}
+
+static inline void
+brcmf_proto_del_if(struct brcmf_pub *drvr, struct brcmf_if *ifp)
+{
+	if (!drvr->proto->del_if)
+		return;
+	drvr->proto->del_if(ifp);
+}
+
+static inline void
+brcmf_proto_reset_if(struct brcmf_pub *drvr, struct brcmf_if *ifp)
+{
+	if (!drvr->proto->reset_if)
+		return;
+	drvr->proto->reset_if(ifp);
+}
+
+static inline int
+brcmf_proto_init_done(struct brcmf_pub *drvr)
+{
+	if (!drvr->proto->init_done)
+		return 0;
+	return drvr->proto->init_done(drvr);
+}
+
 #endif /* BRCMFMAC_PROTO_H */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 65689469c5a1..fc64b8913aa6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -44,6 +44,7 @@
 #include "firmware.h"
 #include "core.h"
 #include "common.h"
+#include "bcdc.h"
 
 #define DCMD_RESP_TIMEOUT	msecs_to_jiffies(2500)
 #define CTL_DONE_TIMEOUT	msecs_to_jiffies(2500)
@@ -539,7 +540,11 @@ static int qcount[NUMPRIO];
 /* Limit on rounding up frames */
 static const uint max_roundup = 512;
 
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+#define ALIGNMENT  8
+#else
 #define ALIGNMENT  4
+#endif
 
 enum brcmf_sdio_frmtype {
 	BRCMF_SDIO_FT_NORMAL,
@@ -2265,7 +2270,8 @@ done:
 		bus->tx_seq = (bus->tx_seq + pktq->qlen) % SDPCM_SEQ_WRAP;
 	skb_queue_walk_safe(pktq, pkt_next, tmp) {
 		__skb_unlink(pkt_next, pktq);
-		brcmf_txcomplete(bus->sdiodev->dev, pkt_next, ret == 0);
+		brcmf_proto_bcdc_txcomplete(bus->sdiodev->dev, pkt_next,
+					    ret == 0);
 	}
 	return ret;
 }
@@ -2328,7 +2334,7 @@ static uint brcmf_sdio_sendfromq(struct brcmf_sdio *bus, uint maxframes)
 	if ((bus->sdiodev->state == BRCMF_SDIOD_DATA) &&
 	    bus->txoff && (pktq_len(&bus->txq) < TXLOW)) {
 		bus->txoff = false;
-		brcmf_txflowblock(bus->sdiodev->dev, false);
+		brcmf_proto_bcdc_txflowblock(bus->sdiodev->dev, false);
 	}
 
 	return cnt;
@@ -2753,7 +2759,7 @@ static int brcmf_sdio_bus_txdata(struct device *dev, struct sk_buff *pkt)
 
 	if (pktq_len(&bus->txq) >= TXHI) {
 		bus->txoff = true;
-		brcmf_txflowblock(dev, true);
+		brcmf_proto_bcdc_txflowblock(dev, true);
 	}
 	spin_unlock_bh(&bus->txq_lock);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index d93ebbdc7737..e4d545f9edee 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -29,6 +29,7 @@
 #include "usb.h"
 #include "core.h"
 #include "common.h"
+#include "bcdc.h"
 
 
 #define IOCTL_RESP_TIMEOUT		msecs_to_jiffies(2000)
@@ -482,13 +483,13 @@ static void brcmf_usb_tx_complete(struct urb *urb)
 		  req->skb);
 	brcmf_usb_del_fromq(devinfo, req);
 
-	brcmf_txcomplete(devinfo->dev, req->skb, urb->status == 0);
+	brcmf_proto_bcdc_txcomplete(devinfo->dev, req->skb, urb->status == 0);
 	req->skb = NULL;
 	brcmf_usb_enq(devinfo, &devinfo->tx_freeq, req, &devinfo->tx_freecount);
 	spin_lock_irqsave(&devinfo->tx_flowblock_lock, flags);
 	if (devinfo->tx_freecount > devinfo->tx_high_watermark &&
 		devinfo->tx_flowblock) {
-		brcmf_txflowblock(devinfo->dev, false);
+		brcmf_proto_bcdc_txflowblock(devinfo->dev, false);
 		devinfo->tx_flowblock = false;
 	}
 	spin_unlock_irqrestore(&devinfo->tx_flowblock_lock, flags);
@@ -635,7 +636,7 @@ static int brcmf_usb_tx(struct device *dev, struct sk_buff *skb)
 	spin_lock_irqsave(&devinfo->tx_flowblock_lock, flags);
 	if (devinfo->tx_freecount < devinfo->tx_low_watermark &&
 	    !devinfo->tx_flowblock) {
-		brcmf_txflowblock(dev, true);
+		brcmf_proto_bcdc_txflowblock(dev, true);
 		devinfo->tx_flowblock = true;
 	}
 	spin_unlock_irqrestore(&devinfo->tx_flowblock_lock, flags);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 7c2a9a9bc372..ddfdfe177e24 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -1082,6 +1082,8 @@ static int ieee_hw_init(struct ieee80211_hw *hw)
 	 * hw->wiphy->flags |= WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD;
 	 */
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	hw->rate_control_algorithm = "minstrel_ht";
 
 	hw->sta_data_size = 0;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index c2a938b59044..0a14942b8216 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -7092,9 +7092,9 @@ prep_mac80211_status(struct brcms_c_info *wlc, struct d11rxhdr *rxh,
 	rspec = brcms_c_compute_rspec(rxh, plcp);
 	if (is_mcs_rate(rspec)) {
 		rx_status->rate_idx = rspec & RSPEC_RATE_MASK;
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 		if (rspec_is40mhz(rspec))
-			rx_status->flag |= RX_FLAG_40MHZ;
+			rx_status->bw = RATE_INFO_BW_40;
 	} else {
 		switch (rspec2rate(rspec)) {
 		case BRCM_RATE_1M:
@@ -7149,9 +7149,9 @@ prep_mac80211_status(struct brcms_c_info *wlc, struct d11rxhdr *rxh,
 		/* Determine short preamble and rate_idx */
 		if (is_cck_rate(rspec)) {
 			if (rxh->PhyRxStatus_0 & PRXS0_SHORTH)
-				rx_status->flag |= RX_FLAG_SHORTPRE;
+				rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 		} else if (is_ofdm_rate(rspec)) {
-			rx_status->flag |= RX_FLAG_SHORTPRE;
+			rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 		} else {
 			brcms_err(wlc->hw->d11core, "%s: Unknown modulation\n",
 				  __func__);
@@ -7159,7 +7159,7 @@ prep_mac80211_status(struct brcms_c_info *wlc, struct d11rxhdr *rxh,
 	}
 
 	if (plcp3_issgi(plcp[3]))
-		rx_status->flag |= RX_FLAG_SHORT_GI;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (rxh->RxStatus1 & RXS_DECERR) {
 		rx_status->flag |= RX_FLAG_FAILED_PLCP_CRC;
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index 5ef3c5cc47c5..bbc579b647b6 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -3539,9 +3539,6 @@ static int ipw_load(struct ipw_priv *priv)
 	fw_img = &fw->data[le32_to_cpu(fw->boot_size) +
 			   le32_to_cpu(fw->ucode_size)];
 
-	if (rc < 0)
-		goto error;
-
 	if (!priv->rxq)
 		priv->rxq = ipw_rx_queue_alloc(priv);
 	else
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
index e8e65115feba..38bf403bb1e1 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
@@ -3592,6 +3592,8 @@ il3945_setup_mac(struct il_priv *il)
 
 	il_leds_init(il);
 
+	wiphy_ext_feature_set(il->hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = ieee80211_register_hw(il->hw);
 	if (ret) {
 		IL_ERR("Failed to register hw (error %d)\n", ret);
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-rs.c b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
index 03ad9b8b55f4..b2f35dfbc01b 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
@@ -656,7 +656,7 @@ il3945_rs_get_rate(void *il_r, struct ieee80211_sta *sta, void *il_sta,
 	rate_mask = sta->supp_rates[sband->band];
 
 	/* get user max rate if set */
-	max_rate_idx = txrc->max_rate_idx;
+	max_rate_idx = fls(txrc->rate_idx_mask) - 1;
 	if (sband->band == NL80211_BAND_5GHZ && max_rate_idx != -1)
 		max_rate_idx += IL_FIRST_OFDM_RATE;
 	if (max_rate_idx < 0 || max_rate_idx >= RATE_COUNT)
diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index 4db327a95414..080ea8155b90 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -570,7 +570,7 @@ il3945_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 
 	/* set the preamble flag if appropriate */
 	if (rx_hdr->phy_flags & RX_RES_PHY_FLAGS_SHORT_PREAMBLE_MSK)
-		rx_status.flag |= RX_FLAG_SHORTPRE;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if ((unlikely(rx_stats->phy_count > 20))) {
 		D_DROP("dsp size out of range [0,20]: %d\n",
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 2781f5728d07..5d5faa3cad24 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -728,15 +728,15 @@ il4965_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 
 	/* set the preamble flag if appropriate */
 	if (phy_res->phy_flags & RX_RES_PHY_FLAGS_SHORT_PREAMBLE_MSK)
-		rx_status.flag |= RX_FLAG_SHORTPRE;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	/* Set up the HT phy flags */
 	if (rate_n_flags & RATE_MCS_HT_MSK)
-		rx_status.flag |= RX_FLAG_HT;
+		rx_status.encoding = RX_ENC_HT;
 	if (rate_n_flags & RATE_MCS_HT40_MSK)
-		rx_status.flag |= RX_FLAG_40MHZ;
+		rx_status.enc_flags |= RX_ENC_FLAG_40MHZ;
 	if (rate_n_flags & RATE_MCS_SGI_MSK)
-		rx_status.flag |= RX_FLAG_SHORT_GI;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (phy_res->phy_flags & RX_RES_PHY_FLAGS_AGG_MSK) {
 		/* We know which subframes of an A-MPDU belong
@@ -5799,6 +5799,8 @@ il4965_mac_setup_register(struct il_priv *il, u32 max_probe_length)
 
 	il_leds_init(il);
 
+	wiphy_ext_feature_set(il->hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = ieee80211_register_hw(il->hw);
 	if (ret) {
 		IL_ERR("Failed to register hw (error %d)\n", ret);
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index a867ae7f4095..c055f6da11c6 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -2211,7 +2211,7 @@ il4965_rs_get_rate(void *il_r, struct ieee80211_sta *sta, void *il_sta,
 
 	/* Get max rate if user set max rate */
 	if (lq_sta) {
-		lq_sta->max_rate_idx = txrc->max_rate_idx;
+		lq_sta->max_rate_idx = fls(txrc->rate_idx_mask) - 1;
 		if (sband->band == NL80211_BAND_5GHZ &&
 		    lq_sta->max_rate_idx != -1)
 			lq_sta->max_rate_idx += IL_FIRST_OFDM_RATE;
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 92e611841200..411cb91c102f 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -7,6 +7,7 @@ iwlwifi-objs		+= iwl-notif-wait.o
 iwlwifi-objs		+= iwl-eeprom-read.o iwl-eeprom-parse.o
 iwlwifi-objs		+= iwl-phy-db.o iwl-nvm-parse.o
 iwlwifi-objs		+= pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o
+iwlwifi-objs		+= pcie/ctxt-info.o pcie/trans-gen2.o pcie/tx-gen2.o
 iwlwifi-$(CONFIG_IWLDVM) += iwl-1000.o iwl-2000.o iwl-5000.o iwl-6000.o
 iwlwifi-$(CONFIG_IWLMVM) += iwl-7000.o iwl-8000.o iwl-9000.o iwl-a000.o
 iwlwifi-objs		+= iwl-trans.o
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/lib.c b/drivers/net/wireless/intel/iwlwifi/dvm/lib.c
index 6c2d6da7eec6..74e52f7c5aa1 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/lib.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/lib.c
@@ -180,7 +180,7 @@ void iwlagn_dev_txfifo_flush(struct iwl_priv *priv)
 		goto done;
 	}
 	IWL_DEBUG_INFO(priv, "wait transmit/flush all frames\n");
-	iwl_trans_wait_tx_queue_empty(priv->trans, 0xffffffff);
+	iwl_trans_wait_tx_queues_empty(priv->trans, 0xffffffff);
 done:
 	ieee80211_wake_queues(priv->hw);
 	mutex_unlock(&priv->mutex);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c
index 2a04d0cd71ae..444c74371929 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c
@@ -213,6 +213,8 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv,
 
 	iwl_leds_init(priv);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = ieee80211_register_hw(priv->hw);
 	if (ret) {
 		IWL_ERR(priv, "Failed to register hw (error %d)\n", ret);
@@ -1143,7 +1145,7 @@ static void iwlagn_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	}
 
 	IWL_DEBUG_TX_QUEUES(priv, "wait transmit/flush all frames\n");
-	iwl_trans_wait_tx_queue_empty(priv->trans, scd_queues);
+	iwl_trans_wait_tx_queues_empty(priv->trans, scd_queues);
 done:
 	mutex_unlock(&priv->mutex);
 	IWL_DEBUG_MAC80211(priv, "leave\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
index ff44ebc5829d..ddcd8c2d66cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
@@ -2720,7 +2720,7 @@ static void rs_get_rate(void *priv_r, struct ieee80211_sta *sta, void *priv_sta,
 
 	/* Get max rate if user set max rate */
 	if (lq_sta) {
-		lq_sta->max_rate_idx = txrc->max_rate_idx;
+		lq_sta->max_rate_idx = fls(txrc->rate_idx_mask) - 1;
 		if ((sband->band == NL80211_BAND_5GHZ) &&
 		    (lq_sta->max_rate_idx != -1))
 			lq_sta->max_rate_idx += IWL_FIRST_OFDM_RATE;
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
index dfa2041cfdac..1ee1ba9931a7 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
@@ -873,7 +873,7 @@ static void iwlagn_rx_reply_rx(struct iwl_priv *priv,
 
 	/* set the preamble flag if appropriate */
 	if (phy_res->phy_flags & RX_RES_PHY_FLAGS_SHORT_PREAMBLE_MSK)
-		rx_status.flag |= RX_FLAG_SHORTPRE;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if (phy_res->phy_flags & RX_RES_PHY_FLAGS_AGG_MSK) {
 		/*
@@ -887,13 +887,13 @@ static void iwlagn_rx_reply_rx(struct iwl_priv *priv,
 
 	/* Set up the HT phy flags */
 	if (rate_n_flags & RATE_MCS_HT_MSK)
-		rx_status.flag |= RX_FLAG_HT;
+		rx_status.encoding = RX_ENC_HT;
 	if (rate_n_flags & RATE_MCS_HT40_MSK)
-		rx_status.flag |= RX_FLAG_40MHZ;
+		rx_status.enc_flags |= RX_ENC_FLAG_40MHZ;
 	if (rate_n_flags & RATE_MCS_SGI_MSK)
-		rx_status.flag |= RX_FLAG_SHORT_GI;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	if (rate_n_flags & RATE_MCS_GF_MSK)
-		rx_status.flag |= RX_FLAG_HT_GF;
+		rx_status.enc_flags |= RX_ENC_FLAG_HT_GF;
 
 	iwlagn_pass_packet_to_mac80211(priv, header, len, ampdu_status,
 				    rxb, &rx_status);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c
index a72e58623d3a..3b3e076571d6 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c
@@ -73,8 +73,8 @@
 /* Highest firmware API version supported */
 #define IWL7260_UCODE_API_MAX	17
 #define IWL7265_UCODE_API_MAX	17
-#define IWL7265D_UCODE_API_MAX	28
-#define IWL3168_UCODE_API_MAX	28
+#define IWL7265D_UCODE_API_MAX	29
+#define IWL3168_UCODE_API_MAX	29
 
 /* Lowest firmware API version supported */
 #define IWL7260_UCODE_API_MIN	17
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
index b7953bf55f6f..b9718c0cf174 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
@@ -70,8 +70,8 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL8000_UCODE_API_MAX	28
-#define IWL8265_UCODE_API_MAX	28
+#define IWL8000_UCODE_API_MAX	30
+#define IWL8265_UCODE_API_MAX	30
 
 /* Lowest firmware API version supported */
 #define IWL8000_UCODE_API_MIN	17
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-9000.c b/drivers/net/wireless/intel/iwlwifi/iwl-9000.c
index a5f0c0bf85ec..110ceefccc15 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-9000.c
@@ -5,7 +5,7 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2015-2016 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -18,7 +18,7 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2015-2016 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -55,10 +55,10 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL9000_UCODE_API_MAX	28
+#define IWL9000_UCODE_API_MAX	30
 
 /* Lowest firmware API version supported */
-#define IWL9000_UCODE_API_MIN	17
+#define IWL9000_UCODE_API_MIN	30
 
 /* NVM versions */
 #define IWL9000_NVM_VERSION		0x0a1d
@@ -73,14 +73,14 @@
 #define IWL9000_SMEM_LEN		0x68000
 
 #define  IWL9000_FW_PRE "iwlwifi-9000-pu-a0-jf-a0-"
-#define  IWL9260_FW_PRE "iwlwifi-9260-th-a0-jf-a0-"
-#define  IWL9000LC_FW_PRE "iwlwifi-9000-pu-a0-lc-a0-"
+#define  IWL9260A_FW_PRE "iwlwifi-9260-th-a0-jf-a0-"
+#define  IWL9260B_FW_PRE "iwlwifi-9260-th-b0-jf-b0-"
 #define IWL9000_MODULE_FIRMWARE(api) \
 	IWL9000_FW_PRE "-" __stringify(api) ".ucode"
-#define IWL9260_MODULE_FIRMWARE(api) \
-	IWL9260_FW_PRE "-" __stringify(api) ".ucode"
-#define IWL9000LC_MODULE_FIRMWARE(api) \
-	IWL9000LC_FW_PRE "-" __stringify(api) ".ucode"
+#define IWL9260A_MODULE_FIRMWARE(api) \
+	IWL9260A_FW_PRE "-" __stringify(api) ".ucode"
+#define IWL9260B_MODULE_FIRMWARE(api) \
+	IWL9260B_FW_PRE "-" __stringify(api) ".ucode"
 
 #define NVM_HW_SECTION_NUM_FAMILY_9000		10
 
@@ -148,7 +148,8 @@ static const struct iwl_tt_params iwl9000_tt_params = {
 
 const struct iwl_cfg iwl9160_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 9160",
-	.fw_name_pre = IWL9260_FW_PRE,
+	.fw_name_pre = IWL9260A_FW_PRE,
+	.fw_name_pre_next_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
 	.ht_params = &iwl9000_ht_params,
 	.nvm_ver = IWL9000_NVM_VERSION,
@@ -158,7 +159,8 @@ const struct iwl_cfg iwl9160_2ac_cfg = {
 
 const struct iwl_cfg iwl9260_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 9260",
-	.fw_name_pre = IWL9260_FW_PRE,
+	.fw_name_pre = IWL9260A_FW_PRE,
+	.fw_name_pre_next_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
 	.ht_params = &iwl9000_ht_params,
 	.nvm_ver = IWL9000_NVM_VERSION,
@@ -168,7 +170,8 @@ const struct iwl_cfg iwl9260_2ac_cfg = {
 
 const struct iwl_cfg iwl9270_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 9270",
-	.fw_name_pre = IWL9260_FW_PRE,
+	.fw_name_pre = IWL9260A_FW_PRE,
+	.fw_name_pre_next_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
 	.ht_params = &iwl9000_ht_params,
 	.nvm_ver = IWL9000_NVM_VERSION,
@@ -198,21 +201,6 @@ const struct iwl_cfg iwl9560_2ac_cfg = {
 	.integrated = true,
 };
 
-/*
- * TODO the struct below is for internal testing only this should be
- * removed by EO 2016~
- */
-const struct iwl_cfg iwl9000lc_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 9000",
-	.fw_name_pre = IWL9000LC_FW_PRE,
-	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
-	.integrated = true,
-};
-
 MODULE_FIRMWARE(IWL9000_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL9260_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL9000LC_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL9260A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL9260B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-a000.c b/drivers/net/wireless/intel/iwlwifi/iwl-a000.c
index 15dd7f6137c8..c648cfb981a3 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-a000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-a000.c
@@ -5,7 +5,7 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2015-2016 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -18,7 +18,7 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2015-2016 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -55,7 +55,7 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL_A000_UCODE_API_MAX	28
+#define IWL_A000_UCODE_API_MAX	30
 
 /* Lowest firmware API version supported */
 #define IWL_A000_UCODE_API_MIN	24
@@ -65,15 +65,16 @@
 #define IWL_A000_TX_POWER_VERSION	0xffff /* meaningless */
 
 /* Memory offsets and lengths */
-#define IWL_A000_DCCM_OFFSET		0x800000
-#define IWL_A000_DCCM_LEN		0x18000
+#define IWL_A000_DCCM_OFFSET		0x800000 /* LMAC1 */
+#define IWL_A000_DCCM_LEN		0x10000 /* LMAC1 */
 #define IWL_A000_DCCM2_OFFSET		0x880000
 #define IWL_A000_DCCM2_LEN		0x8000
 #define IWL_A000_SMEM_OFFSET		0x400000
-#define IWL_A000_SMEM_LEN		0x68000
+#define IWL_A000_SMEM_LEN		0xD0000
 
-#define IWL_A000_JF_FW_PRE "iwlwifi-Qu-a0-jf-b0-"
-#define IWL_A000_HR_FW_PRE "iwlwifi-Qu-a0-hr-a0-"
+#define IWL_A000_JF_FW_PRE	"iwlwifi-Qu-a0-jf-b0-"
+#define IWL_A000_HR_FW_PRE	"iwlwifi-Qu-a0-hr-a0-"
+#define IWL_A000_HR_CDB_FW_PRE	"iwlwifi-QuIcp-a0-hrcdb-a0-"
 
 #define IWL_A000_HR_MODULE_FIRMWARE(api) \
 	IWL_A000_HR_FW_PRE "-" __stringify(api) ".ucode"
@@ -84,7 +85,7 @@
 
 static const struct iwl_base_params iwl_a000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_A000,
-	.num_of_queues = 31,
+	.num_of_queues = 512,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
@@ -121,7 +122,8 @@ static const struct iwl_ht_params iwl_a000_ht_params = {
 	.vht_mu_mimo_supported = true,					\
 	.mac_addr_from_csr = true,					\
 	.use_tfh = true,						\
-	.rf_id = true
+	.rf_id = true,							\
+	.gen2 = true
 
 const struct iwl_cfg iwla000_2ac_cfg_hr = {
 		.name = "Intel(R) Dual Band Wireless AC a000",
@@ -133,6 +135,17 @@ const struct iwl_cfg iwla000_2ac_cfg_hr = {
 		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
+const struct iwl_cfg iwla000_2ac_cfg_hr_cdb = {
+		.name = "Intel(R) Dual Band Wireless AC a000",
+		.fw_name_pre = IWL_A000_HR_CDB_FW_PRE,
+		IWL_DEVICE_A000,
+		.ht_params = &iwl_a000_ht_params,
+		.nvm_ver = IWL_A000_NVM_VERSION,
+		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+		.cdb = true,
+};
+
 const struct iwl_cfg iwla000_2ac_cfg_jf = {
 		.name = "Intel(R) Dual Band Wireless AC a000",
 		.fw_name_pre = IWL_A000_JF_FW_PRE,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 94f8a51b633e..a12197e3ce78 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -6,7 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2016 Intel Deutschland GmbH
+ * Copyright (C) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -32,7 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2016 Intel Deutschland GmbH
+ * Copyright (C) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -90,16 +90,6 @@ enum iwl_device_family {
 	IWL_DEVICE_FAMILY_8000,
 };
 
-static inline bool iwl_has_secure_boot(u32 hw_rev,
-				       enum iwl_device_family family)
-{
-	/* return 1 only for family 8000 B0 */
-	if ((family == IWL_DEVICE_FAMILY_8000) && (hw_rev & 0xC))
-		return true;
-
-	return false;
-}
-
 /*
  * LED mode
  *    IWL_LED_DEFAULT:  use device default
@@ -180,7 +170,7 @@ struct iwl_base_params {
 	   apmg_wake_up_wa:1,
 	   scd_chain_ext_wa:1;
 
-	u8 num_of_queues;	/* def: HW dependent */
+	u16 num_of_queues;	/* def: HW dependent */
 
 	u8 max_ll_items;
 	u8 led_compensation;
@@ -283,6 +273,8 @@ struct iwl_pwr_tx_backoff {
  * @fw_name_pre: Firmware filename prefix. The api version and extension
  *	(.ucode) will be added to filename before loading from disk. The
  *	filename is constructed as fw_name_pre<api>.ucode.
+ * @fw_name_pre_next_step: same as @fw_name_pre, only for next step
+ *	(if supported)
  * @ucode_api_max: Highest version of uCode API supported by driver.
  * @ucode_api_min: Lowest version of uCode API supported by driver.
  * @max_inst_size: The maximal length of the fw inst section
@@ -321,6 +313,8 @@ struct iwl_pwr_tx_backoff {
  * @vht_mu_mimo_supported: VHT MU-MIMO support
  * @rf_id: need to read rf_id to determine the firmware image
  * @integrated: discrete or integrated
+ * @gen2: a000 and on transport operation
+ * @cdb: CDB support
  *
  * We enable the driver to be backward compatible wrt. hardware features.
  * API differences in uCode shouldn't be handled here but through TLVs
@@ -330,6 +324,7 @@ struct iwl_cfg {
 	/* params specific to an individual device within a device family */
 	const char *name;
 	const char *fw_name_pre;
+	const char *fw_name_pre_next_step;
 	/* params not likely to change within a device family */
 	const struct iwl_base_params *base_params;
 	/* params likely to change within a device family */
@@ -365,7 +360,9 @@ struct iwl_cfg {
 	    vht_mu_mimo_supported:1,
 	    rf_id:1,
 	    integrated:1,
-	    use_tfh:1;
+	    use_tfh:1,
+	    gen2:1,
+	    cdb:1;
 	u8 valid_tx_ant;
 	u8 valid_rx_ant;
 	u8 non_shared_ant;
@@ -449,13 +446,13 @@ extern const struct iwl_cfg iwl4165_2ac_cfg;
 extern const struct iwl_cfg iwl8260_2ac_sdio_cfg;
 extern const struct iwl_cfg iwl8265_2ac_sdio_cfg;
 extern const struct iwl_cfg iwl4165_2ac_sdio_cfg;
-extern const struct iwl_cfg iwl9000lc_2ac_cfg;
 extern const struct iwl_cfg iwl9160_2ac_cfg;
 extern const struct iwl_cfg iwl9260_2ac_cfg;
 extern const struct iwl_cfg iwl9270_2ac_cfg;
 extern const struct iwl_cfg iwl9460_2ac_cfg;
 extern const struct iwl_cfg iwl9560_2ac_cfg;
 extern const struct iwl_cfg iwla000_2ac_cfg_hr;
+extern const struct iwl_cfg iwla000_2ac_cfg_hr_cdb;
 extern const struct iwl_cfg iwla000_2ac_cfg_jf;
 #endif /* CONFIG_IWLMVM */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
new file mode 100644
index 000000000000..b870c0986744
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
@@ -0,0 +1,203 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+
+#ifndef __iwl_context_info_file_h__
+#define __iwl_context_info_file_h__
+
+/* maximmum number of DRAM map entries supported by FW */
+#define IWL_MAX_DRAM_ENTRY	64
+#define CSR_CTXT_INFO_BA	0x40
+
+/**
+ * enum iwl_context_info_flags - Context information control flags
+ * @IWL_CTXT_INFO_AUTO_FUNC_INIT: If set, FW will not wait before interrupting
+ *	the init done for driver command that configures several system modes
+ * @IWL_CTXT_INFO_EARLY_DEBUG: enable early debug
+ * @IWL_CTXT_INFO_ENABLE_CDMP: enable core dump
+ * @IWL_CTXT_INFO_RB_SIZE_4K: Use 4K RB size (the default is 2K)
+ * @IWL_CTXT_INFO_RB_CB_SIZE_POS: position of the RBD Cyclic Buffer Size
+ *	exponent, the actual size is 2**value, valid sizes are 8-2048.
+ *	The value is four bits long. Maximum valid exponent is 12
+ * @IWL_CTXT_INFO_TFD_FORMAT_LONG: use long TFD Format (the
+ *	default is short format - not supported by the driver)
+ */
+enum iwl_context_info_flags {
+	IWL_CTXT_INFO_AUTO_FUNC_INIT	= BIT(0),
+	IWL_CTXT_INFO_EARLY_DEBUG	= BIT(1),
+	IWL_CTXT_INFO_ENABLE_CDMP	= BIT(2),
+	IWL_CTXT_INFO_RB_SIZE_4K	= BIT(3),
+	IWL_CTXT_INFO_RB_CB_SIZE_POS	= 4,
+	IWL_CTXT_INFO_TFD_FORMAT_LONG	= BIT(8),
+};
+
+/*
+ * struct iwl_context_info_version - version structure
+ * @mac_id: SKU and revision id
+ * @version: context information version id
+ * @size: the size of the context information in DWs
+ */
+struct iwl_context_info_version {
+	__le16 mac_id;
+	__le16 version;
+	__le16 size;
+	__le16 reserved;
+} __packed;
+
+/*
+ * struct iwl_context_info_control - version structure
+ * @control_flags: context information flags see &enum iwl_context_info_flags
+ */
+struct iwl_context_info_control {
+	__le32 control_flags;
+	__le32 reserved;
+} __packed;
+
+/*
+ * struct iwl_context_info_dram - images DRAM map
+ * each entry in the map represents a DRAM chunk of up to 32 KB
+ * @umac_img: UMAC image DRAM map
+ * @lmac_img: LMAC image DRAM map
+ * @virtual_img: paged image DRAM map
+ */
+struct iwl_context_info_dram {
+	__le64 umac_img[IWL_MAX_DRAM_ENTRY];
+	__le64 lmac_img[IWL_MAX_DRAM_ENTRY];
+	__le64 virtual_img[IWL_MAX_DRAM_ENTRY];
+} __packed;
+
+/*
+ * struct iwl_context_info_rbd_cfg - RBDs configuration
+ * @free_rbd_addr: default queue free RB CB base address
+ * @used_rbd_addr: default queue used RB CB base address
+ * @status_wr_ptr: default queue used RB status write pointer
+ */
+struct iwl_context_info_rbd_cfg {
+	__le64 free_rbd_addr;
+	__le64 used_rbd_addr;
+	__le64 status_wr_ptr;
+} __packed;
+
+/*
+ * struct iwl_context_info_hcmd_cfg  - command queue configuration
+ * @cmd_queue_addr: address of command queue
+ * @cmd_queue_size: number of entries
+ */
+struct iwl_context_info_hcmd_cfg {
+	__le64 cmd_queue_addr;
+	u8 cmd_queue_size;
+	u8 reserved[7];
+} __packed;
+
+/*
+ * struct iwl_context_info_dump_cfg - Core Dump configuration
+ * @core_dump_addr: core dump (debug DRAM address) start address
+ * @core_dump_size: size, in DWs
+ */
+struct iwl_context_info_dump_cfg {
+	__le64 core_dump_addr;
+	__le32 core_dump_size;
+	__le32 reserved;
+} __packed;
+
+/*
+ * struct iwl_context_info_pnvm_cfg - platform NVM data configuration
+ * @platform_nvm_addr: Platform NVM data start address
+ * @platform_nvm_size: size in DWs
+ */
+struct iwl_context_info_pnvm_cfg {
+	__le64 platform_nvm_addr;
+	__le32 platform_nvm_size;
+	__le32 reserved;
+} __packed;
+
+/*
+ * struct iwl_context_info_early_dbg_cfg - early debug configuration for
+ *	dumping DRAM addresses
+ * @early_debug_addr: early debug start address
+ * @early_debug_size: size in DWs
+ */
+struct iwl_context_info_early_dbg_cfg {
+	__le64 early_debug_addr;
+	__le32 early_debug_size;
+	__le32 reserved;
+} __packed;
+
+/*
+ * struct iwl_context_info - device INIT configuration
+ * @version: version information of context info and HW
+ * @control: control flags of FH configurations
+ * @rbd_cfg: default RX queue configuration
+ * @hcmd_cfg: command queue configuration
+ * @dump_cfg: core dump data
+ * @edbg_cfg: early debug configuration
+ * @pnvm_cfg: platform nvm configuration
+ * @dram: firmware image addresses in DRAM
+ */
+struct iwl_context_info {
+	struct iwl_context_info_version version;
+	struct iwl_context_info_control control;
+	__le64 reserved0;
+	struct iwl_context_info_rbd_cfg rbd_cfg;
+	struct iwl_context_info_hcmd_cfg hcmd_cfg;
+	__le32 reserved1[4];
+	struct iwl_context_info_dump_cfg dump_cfg;
+	struct iwl_context_info_early_dbg_cfg edbg_cfg;
+	struct iwl_context_info_pnvm_cfg pnvm_cfg;
+	__le32 reserved2[16];
+	struct iwl_context_info_dram dram;
+	__le32 reserved3[16];
+} __packed;
+
+int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, const struct fw_img *fw);
+void iwl_pcie_ctxt_info_free(struct iwl_trans *trans);
+void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans);
+
+#endif /* __iwl_context_info_file_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index 4ee3b621ec27..fa120fb55373 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -348,7 +348,6 @@ enum {
 
 /* RF_ID value */
 #define CSR_HW_RF_ID_TYPE_JF		(0x00105000)
-#define CSR_HW_RF_ID_TYPE_LC		(0x00101000)
 #define CSR_HW_RF_ID_TYPE_HR		(0x00109000)
 
 /* EEPROM REG */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index be466a074c1d..5cfacb0bca84 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -211,24 +211,46 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw,
 
 static int iwl_request_firmware(struct iwl_drv *drv, bool first)
 {
-	const char *name_pre = drv->trans->cfg->fw_name_pre;
+	const struct iwl_cfg *cfg = drv->trans->cfg;
 	char tag[8];
+	const char *fw_pre_name;
+
+	if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000 &&
+	    CSR_HW_REV_STEP(drv->trans->hw_rev) == SILICON_B_STEP)
+		fw_pre_name = cfg->fw_name_pre_next_step;
+	else
+		fw_pre_name = cfg->fw_name_pre;
 
 	if (first) {
-		drv->fw_index = drv->trans->cfg->ucode_api_max;
+		drv->fw_index = cfg->ucode_api_max;
 		sprintf(tag, "%d", drv->fw_index);
 	} else {
 		drv->fw_index--;
 		sprintf(tag, "%d", drv->fw_index);
 	}
 
-	if (drv->fw_index < drv->trans->cfg->ucode_api_min) {
+	if (drv->fw_index < cfg->ucode_api_min) {
 		IWL_ERR(drv, "no suitable firmware found!\n");
+
+		if (cfg->ucode_api_min == cfg->ucode_api_max) {
+			IWL_ERR(drv, "%s%d is required\n", fw_pre_name,
+				cfg->ucode_api_max);
+		} else {
+			IWL_ERR(drv, "minimum version required: %s%d\n",
+				fw_pre_name,
+				cfg->ucode_api_min);
+			IWL_ERR(drv, "maximum version supported: %s%d\n",
+				fw_pre_name,
+				cfg->ucode_api_max);
+		}
+
+		IWL_ERR(drv,
+			"check git://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git\n");
 		return -ENOENT;
 	}
 
 	snprintf(drv->firmware_name, sizeof(drv->firmware_name), "%s%s.ucode",
-		 name_pre, tag);
+		 fw_pre_name, tag);
 
 	IWL_DEBUG_INFO(drv, "attempting to load firmware '%s'\n",
 		       drv->firmware_name);
@@ -1260,7 +1282,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 
 	pieces = kzalloc(sizeof(*pieces), GFP_KERNEL);
 	if (!pieces)
-		return;
+		goto out_free_fw;
 
 	if (!ucode_raw)
 		goto try_again;
@@ -1472,7 +1494,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	 * or hangs loading.
 	 */
 	if (load_module) {
-		err = request_module("%s", op->name);
+		request_module("%s", op->name);
 #ifdef CONFIG_IWLWIFI_OPMODE_MODULAR
 		if (err)
 			IWL_ERR(drv,
@@ -1490,17 +1512,18 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	goto free;
 
  out_free_fw:
-	IWL_ERR(drv, "failed to allocate pci memory\n");
 	iwl_dealloc_ucode(drv);
 	release_firmware(ucode_raw);
  out_unbind:
 	complete(&drv->request_firmware_complete);
 	device_release_driver(drv->trans->dev);
  free:
-	for (i = 0; i < ARRAY_SIZE(pieces->img); i++)
-		kfree(pieces->img[i].sec);
-	kfree(pieces->dbg_mem_tlv);
-	kfree(pieces);
+	if (pieces) {
+		for (i = 0; i < ARRAY_SIZE(pieces->img); i++)
+			kfree(pieces->img[i].sec);
+		kfree(pieces->dbg_mem_tlv);
+		kfree(pieces);
+	}
 }
 
 struct iwl_drv *iwl_drv_start(struct iwl_trans *trans)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index 33ef5372d195..62f9fe926d78 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -614,6 +614,8 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
 #define RX_POOL_SIZE		(MQ_RX_NUM_RBDS +	\
 				 IWL_MAX_RX_HW_QUEUES *	\
 				 (RX_CLAIM_REQ_ALLOC - RX_POST_REQ_ALLOC))
+/* cb size is the exponent */
+#define RX_QUEUE_CB_SIZE(x)	ilog2(x)
 
 #define RX_QUEUE_SIZE                         256
 #define RX_QUEUE_MASK                         255
@@ -639,6 +641,8 @@ struct iwl_rb_status {
 
 
 #define TFD_QUEUE_SIZE_MAX      (256)
+/* cb size is the exponent - 3 */
+#define TFD_QUEUE_CB_SIZE(x)	(ilog2(x) - 3)
 #define TFD_QUEUE_SIZE_BC_DUP	(64)
 #define TFD_QUEUE_BC_SIZE	(TFD_QUEUE_SIZE_MAX + TFD_QUEUE_SIZE_BC_DUP)
 #define IWL_TX_DMA_MASK        DMA_BIT_MASK(36)
@@ -647,7 +651,7 @@ struct iwl_rb_status {
 
 static inline u8 iwl_get_dma_hi_addr(dma_addr_t addr)
 {
-	return (sizeof(addr) > sizeof(u32) ? (addr >> 16) >> 16 : 0) & 0xF;
+	return (sizeof(addr) > sizeof(u32) ? upper_32_bits(addr) : 0) & 0xF;
 }
 /**
  * struct iwl_tfd_tb transmit buffer descriptor within transmit frame descriptor
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h b/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h
index d01701ee4777..44419e82da1b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fw-file.h
@@ -241,6 +241,9 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t;
  *	iteration complete notification, and the timestamp reported for RX
  *	received during scan, are reported in TSF of the mac specified in the
  *	scan request.
+ * @IWL_UCODE_TLV_API_TKIP_MIC_KEYS: This ucode supports version 2 of
+ *	ADD_MODIFY_STA_KEY_API_S_VER_2.
+ * @IWL_UCODE_TLV_API_STA_TYPE: This ucode supports station type assignement.
  *
  * @NUM_IWL_UCODE_TLV_API: number of bits used
  */
@@ -250,6 +253,8 @@ enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_LQ_SS_PARAMS		= (__force iwl_ucode_tlv_api_t)18,
 	IWL_UCODE_TLV_API_NEW_VERSION		= (__force iwl_ucode_tlv_api_t)20,
 	IWL_UCODE_TLV_API_SCAN_TSF_REPORT	= (__force iwl_ucode_tlv_api_t)28,
+	IWL_UCODE_TLV_API_TKIP_MIC_KEYS		= (__force iwl_ucode_tlv_api_t)29,
+	IWL_UCODE_TLV_API_STA_TYPE		= (__force iwl_ucode_tlv_api_t)30,
 
 	NUM_IWL_UCODE_TLV_API
 #ifdef __CHECKER__
@@ -344,6 +349,8 @@ enum iwl_ucode_tlv_capa {
 	IWL_UCODE_TLV_CAPA_BT_COEX_RRC			= (__force iwl_ucode_tlv_capa_t)30,
 	IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT		= (__force iwl_ucode_tlv_capa_t)31,
 	IWL_UCODE_TLV_CAPA_STA_PM_NOTIF			= (__force iwl_ucode_tlv_capa_t)38,
+	IWL_UCODE_TLV_CAPA_BINDING_CDB_SUPPORT		= (__force iwl_ucode_tlv_capa_t)39,
+	IWL_UCODE_TLV_CAPA_CDB_SUPPORT			= (__force iwl_ucode_tlv_capa_t)40,
 	IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE		= (__force iwl_ucode_tlv_capa_t)64,
 	IWL_UCODE_TLV_CAPA_SHORT_PM_TIMEOUTS		= (__force iwl_ucode_tlv_capa_t)65,
 	IWL_UCODE_TLV_CAPA_BT_MPLUT_SUPPORT		= (__force iwl_ucode_tlv_capa_t)67,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.c b/drivers/net/wireless/intel/iwlwifi/iwl-io.c
index a9f69fdd170b..9c8b09cf1f7b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-io.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.c
@@ -54,8 +54,8 @@ IWL_EXPORT_SYMBOL(iwl_write32);
 void iwl_write64(struct iwl_trans *trans, u64 ofs, u64 val)
 {
 	trace_iwlwifi_dev_iowrite64(trans->dev, ofs, val);
-	iwl_trans_write32(trans, ofs, val & 0xffffffff);
-	iwl_trans_write32(trans, ofs + 4, val >> 32);
+	iwl_trans_write32(trans, ofs, lower_32_bits(val));
+	iwl_trans_write32(trans, ofs + 4, upper_32_bits(val));
 }
 IWL_EXPORT_SYMBOL(iwl_write64);
 
@@ -246,6 +246,9 @@ void iwl_force_nmi(struct iwl_trans *trans)
 			       DEVICE_SET_NMI_VAL_DRV);
 		iwl_write_prph(trans, DEVICE_SET_NMI_REG,
 			       DEVICE_SET_NMI_VAL_HW);
+	} else if (trans->cfg->gen2) {
+		iwl_write_prph(trans, UREG_NIC_SET_NMI_DRIVER,
+			       DEVICE_SET_NMI_8000_VAL);
 	} else {
 		iwl_write_prph(trans, DEVICE_SET_NMI_8000_REG,
 			       DEVICE_SET_NMI_8000_VAL);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.c b/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.c
index 88f260db3744..68412ff2112e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.c
@@ -76,8 +76,8 @@ void iwl_notification_wait_init(struct iwl_notif_wait_data *notif_wait)
 }
 IWL_EXPORT_SYMBOL(iwl_notification_wait_init);
 
-void iwl_notification_wait_notify(struct iwl_notif_wait_data *notif_wait,
-				  struct iwl_rx_packet *pkt)
+bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait,
+			   struct iwl_rx_packet *pkt)
 {
 	bool triggered = false;
 
@@ -118,13 +118,11 @@ void iwl_notification_wait_notify(struct iwl_notif_wait_data *notif_wait,
 			}
 		}
 		spin_unlock(&notif_wait->notif_wait_lock);
-
 	}
 
-	if (triggered)
-		wake_up_all(&notif_wait->notif_waitq);
+	return triggered;
 }
-IWL_EXPORT_SYMBOL(iwl_notification_wait_notify);
+IWL_EXPORT_SYMBOL(iwl_notification_wait);
 
 void iwl_abort_notification_waits(struct iwl_notif_wait_data *notif_wait)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.h b/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.h
index 0f9995ed71cd..368884be4e7c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-notif-wait.h
@@ -6,7 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -32,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -89,10 +90,10 @@ struct iwl_notif_wait_data {
  *
  * This structure is not used directly, to wait for a
  * notification declare it on the stack, and call
- * iwlagn_init_notification_wait() with appropriate
+ * iwl_init_notification_wait() with appropriate
  * parameters. Then do whatever will cause the ucode
  * to notify the driver, and to wait for that then
- * call iwlagn_wait_notification().
+ * call iwl_wait_notification().
  *
  * Each notification is one-shot. If at some point we
  * need to support multi-shot notifications (which
@@ -114,10 +115,24 @@ struct iwl_notification_wait {
 
 /* caller functions */
 void iwl_notification_wait_init(struct iwl_notif_wait_data *notif_data);
-void iwl_notification_wait_notify(struct iwl_notif_wait_data *notif_data,
-				  struct iwl_rx_packet *pkt);
+bool iwl_notification_wait(struct iwl_notif_wait_data *notif_data,
+			   struct iwl_rx_packet *pkt);
 void iwl_abort_notification_waits(struct iwl_notif_wait_data *notif_data);
 
+static inline void
+iwl_notification_notify(struct iwl_notif_wait_data *notif_data)
+{
+	wake_up_all(&notif_data->notif_waitq);
+}
+
+static inline void
+iwl_notification_wait_notify(struct iwl_notif_wait_data *notif_data,
+			     struct iwl_rx_packet *pkt)
+{
+	if (iwl_notification_wait(notif_data, pkt))
+		iwl_notification_notify(notif_data);
+}
+
 /* user functions */
 void __acquires(wait_entry)
 iwl_init_notification_wait(struct iwl_notif_wait_data *notif_data,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 3bd6fc1b76d4..721ae6bef5da 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,6 +34,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -438,25 +439,16 @@ static void iwl_init_vht_hw_capab(const struct iwl_cfg *cfg,
 	vht_cap->vht_mcs.tx_mcs_map = vht_cap->vht_mcs.rx_mcs_map;
 }
 
-static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
-			    struct iwl_nvm_data *data,
-			    const __le16 *ch_section,
-			    u8 tx_chains, u8 rx_chains, bool lar_supported)
+void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
+		     struct iwl_nvm_data *data, const __le16 *nvm_ch_flags,
+		     u8 tx_chains, u8 rx_chains, bool lar_supported)
 {
 	int n_channels;
 	int n_used = 0;
 	struct ieee80211_supported_band *sband;
 
-	if (cfg->device_family != IWL_DEVICE_FAMILY_8000)
-		n_channels = iwl_init_channel_map(
-				dev, cfg, data,
-				&ch_section[NVM_CHANNELS], lar_supported);
-	else
-		n_channels = iwl_init_channel_map(
-				dev, cfg, data,
-				&ch_section[NVM_CHANNELS_FAMILY_8000],
-				lar_supported);
-
+	n_channels = iwl_init_channel_map(dev, cfg, data, nvm_ch_flags,
+					  lar_supported);
 	sband = &data->bands[NL80211_BAND_2GHZ];
 	sband->band = NL80211_BAND_2GHZ;
 	sband->bitrates = &iwl_cfg80211_rates[RATES_24_OFFS];
@@ -482,6 +474,7 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 		IWL_ERR_DEV(dev, "NVM: used only %d of %d channels\n",
 			    n_used, n_channels);
 }
+IWL_EXPORT_SYMBOL(iwl_init_sbands);
 
 static int iwl_get_sku(const struct iwl_cfg *cfg, const __le16 *nvm_sw,
 		       const __le16 *phy_sku)
@@ -559,8 +552,8 @@ static void iwl_flip_hw_address(__le32 mac_addr0, __le32 mac_addr1, u8 *dest)
 	dest[5] = hw_addr[0];
 }
 
-static void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
-					struct iwl_nvm_data *data)
+void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
+				 struct iwl_nvm_data *data)
 {
 	__le32 mac_addr0 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR0_STRAP));
 	__le32 mac_addr1 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR1_STRAP));
@@ -578,6 +571,7 @@ static void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
 
 	iwl_flip_hw_address(mac_addr0, mac_addr1, data->hw_addr);
 }
+IWL_EXPORT_SYMBOL(iwl_set_hw_address_from_csr);
 
 static void iwl_set_hw_address_family_8000(struct iwl_trans *trans,
 					   const struct iwl_cfg *cfg,
@@ -718,7 +712,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		data->xtal_calib[0] = *(nvm_calib + XTAL_CALIB);
 		data->xtal_calib[1] = *(nvm_calib + XTAL_CALIB + 1);
 		lar_enabled = true;
-		ch_section = nvm_sw;
+		ch_section = &nvm_sw[NVM_CHANNELS];
 	} else {
 		u16 lar_offset = data->nvm_version < 0xE39 ?
 				 NVM_LAR_OFFSET_FAMILY_8000_OLD :
@@ -728,7 +722,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		data->lar_enabled = !!(lar_config &
 				       NVM_LAR_ENABLED_FAMILY_8000);
 		lar_enabled = data->lar_enabled;
-		ch_section = regulatory;
+		ch_section = &regulatory[NVM_CHANNELS_FAMILY_8000];
 	}
 
 	/* If no valid mac address was found - bail out */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index 7249e5b403f4..3fd6506a02ab 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -6,7 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2008 - 2015 Intel Corporation. All rights reserved.
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -32,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -82,6 +83,19 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		   u8 tx_chains, u8 rx_chains, bool lar_fw_supported);
 
 /**
+ * iwl_set_hw_address_from_csr - sets HW address for 9000 devices and on
+ */
+void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
+				 struct iwl_nvm_data *data);
+
+/**
+ * iwl_init_sbands - parse and set all channel profiles
+ */
+void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
+		     struct iwl_nvm_data *data, const __le16 *nvm_ch_flags,
+		     u8 tx_chains, u8 rx_chains, bool lar_supported);
+
+/**
  * iwl_parse_mcc_info - parse MCC (mobile country code) info coming from FW
  *
  * This function parses the regulatory channel data received as a
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
index 406ef301b8ab..306bc967742e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
@@ -114,6 +114,7 @@
 #define DEVICE_SET_NMI_VAL_DRV BIT(7)
 #define DEVICE_SET_NMI_8000_REG 0x00a01c24
 #define DEVICE_SET_NMI_8000_VAL 0x1000000
+#define UREG_NIC_SET_NMI_DRIVER 0x00a05c10
 
 /* Shared registers (0x0..0x3ff, via target indirect or periphery */
 #define SHR_BASE	0x00a10000
@@ -294,9 +295,6 @@
 
 /*********************** END TX SCHEDULER *************************************/
 
-/* tcp checksum offload */
-#define RX_EN_CSUM		(0x00a00d88)
-
 /* Oscillator clock */
 #define OSC_CLK				(0xa04068)
 #define OSC_CLK_FORCE_CONTROL		(0x8)
@@ -309,6 +307,7 @@
  * Note this address is cleared after MAC reset.
  */
 #define UREG_UCODE_LOAD_STATUS		(0xa05c40)
+#define UREG_CPU_INIT_RUN		(0xa05c44)
 
 #define LMPM_SECURE_UCODE_LOAD_CPU1_HDR_ADDR	(0x1E78)
 #define LMPM_SECURE_UCODE_LOAD_CPU2_HDR_ADDR	(0x1E7C)
@@ -316,6 +315,8 @@
 #define LMPM_SECURE_CPU1_HDR_MEM_SPACE		(0x420000)
 #define LMPM_SECURE_CPU2_HDR_MEM_SPACE		(0x420400)
 
+#define LMAC2_PRPH_OFFSET		(0x100000)
+
 /* Rx FIFO */
 #define RXF_SIZE_ADDR			(0xa00c88)
 #define RXF_RD_D_SPACE			(0xa00c40)
@@ -378,6 +379,7 @@
 #define RADIO_REG_SYS_MANUAL_DFT_0	0xAD4078
 #define RFIC_REG_RD			0xAD0470
 #define WFPM_CTRL_REG			0xA03030
+#define WFPM_GP2			0xA030B4
 enum {
 	ENABLE_WFPM = BIT(31),
 	WFPM_AUX_CTL_AUX_IF_MAC_OWNER_MSK	= 0x80000000,
@@ -398,6 +400,8 @@ enum aux_misc_master1_en {
 #define PREG_AUX_BUS_WPROT_0		0xA04CC0
 #define SB_CPU_1_STATUS			0xA01E30
 #define SB_CPU_2_STATUS			0xA01E34
+#define UMAG_SB_CPU_1_STATUS		0xA038C0
+#define UMAG_SB_CPU_2_STATUS		0xA038C4
 
 /* FW chicken bits */
 #define LMPM_CHICK			0xA01FF8
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index d42cab291025..0bde26bab15d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -70,8 +70,7 @@
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  struct device *dev,
 				  const struct iwl_cfg *cfg,
-				  const struct iwl_trans_ops *ops,
-				  size_t dev_cmd_headroom)
+				  const struct iwl_trans_ops *ops)
 {
 	struct iwl_trans *trans;
 #ifdef CONFIG_LOCKDEP
@@ -90,15 +89,13 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 	trans->dev = dev;
 	trans->cfg = cfg;
 	trans->ops = ops;
-	trans->dev_cmd_headroom = dev_cmd_headroom;
 	trans->num_rx_queues = 1;
 
 	snprintf(trans->dev_cmd_pool_name, sizeof(trans->dev_cmd_pool_name),
 		 "iwl_cmd_pool:%s", dev_name(trans->dev));
 	trans->dev_cmd_pool =
 		kmem_cache_create(trans->dev_cmd_pool_name,
-				  sizeof(struct iwl_device_cmd)
-				  + trans->dev_cmd_headroom,
+				  sizeof(struct iwl_device_cmd),
 				  sizeof(void *),
 				  SLAB_HWCACHE_ALIGN,
 				  NULL);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 0296124a7f9c..0ebfdbb22992 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -396,7 +396,10 @@ static inline void iwl_free_rxb(struct iwl_rx_cmd_buffer *r)
  * currently supports
  */
 #define IWL_MAX_HW_QUEUES		32
+#define IWL_MAX_TVQM_QUEUES		512
+
 #define IWL_MAX_TID_COUNT	8
+#define IWL_MGMT_TID		15
 #define IWL_FRAME_LIMIT	64
 #define IWL_MAX_RX_HW_QUEUES	16
 
@@ -530,6 +533,44 @@ struct iwl_trans_txq_scd_cfg {
 	int frame_limit;
 };
 
+/* Available options for &struct iwl_tx_queue_cfg_cmd */
+enum iwl_tx_queue_cfg_actions {
+	TX_QUEUE_CFG_ENABLE_QUEUE		= BIT(0),
+	TX_QUEUE_CFG_TFD_SHORT_FORMAT		= BIT(1),
+};
+
+/**
+ * struct iwl_tx_queue_cfg_cmd - txq hw scheduler config command
+ * @sta_id: station id
+ * @tid: tid of the queue
+ * @flags: Bit 0 - on enable, off - disable, Bit 1 - short TFD format
+ * @cb_size: size of TFD cyclic buffer. Value is exponent - 3.
+ *	Minimum value 0 (8 TFDs), maximum value 5 (256 TFDs)
+ * @byte_cnt_addr: address of byte count table
+ * @tfdq_addr: address of TFD circular buffer
+ */
+struct iwl_tx_queue_cfg_cmd {
+	u8 sta_id;
+	u8 tid;
+	__le16 flags;
+	__le32 cb_size;
+	__le64 byte_cnt_addr;
+	__le64 tfdq_addr;
+} __packed; /* TX_QUEUE_CFG_CMD_API_S_VER_2 */
+
+/**
+ * struct iwl_tx_queue_cfg_rsp - response to txq hw scheduler config
+ * @queue_number: queue number assigned to this RA -TID
+ * @flags: set on failure
+ * @write_pointer: initial value for write pointer
+ */
+struct iwl_tx_queue_cfg_rsp {
+	__le16 queue_number;
+	__le16 flags;
+	__le16 write_pointer;
+	__le16 reserved;
+} __packed; /* TX_QUEUE_CFG_RSP_API_S_VER_2 */
+
 /**
  * struct iwl_trans_ops - transport specific operations
  *
@@ -640,13 +681,17 @@ struct iwl_trans_ops {
 			   unsigned int queue_wdg_timeout);
 	void (*txq_disable)(struct iwl_trans *trans, int queue,
 			    bool configure_scd);
+	/* a000 functions */
+	int (*txq_alloc)(struct iwl_trans *trans,
+			 struct iwl_tx_queue_cfg_cmd *cmd,
+			 int cmd_id,
+			 unsigned int queue_wdg_timeout);
+	void (*txq_free)(struct iwl_trans *trans, int queue);
 
 	void (*txq_set_shared_mode)(struct iwl_trans *trans, u32 txq_id,
 				    bool shared);
 
-	dma_addr_t (*get_txq_byte_table)(struct iwl_trans *trans, int txq_id);
-
-	int (*wait_tx_queue_empty)(struct iwl_trans *trans, u32 txq_bm);
+	int (*wait_tx_queues_empty)(struct iwl_trans *trans, u32 txq_bm);
 	void (*freeze_txq_timer)(struct iwl_trans *trans, unsigned long txqs,
 				 bool freeze);
 	void (*block_txq_ptrs)(struct iwl_trans *trans, bool block);
@@ -774,9 +819,6 @@ enum iwl_plat_pm_mode {
  *	the transport must set this before calling iwl_drv_start()
  * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
  *	The user should use iwl_trans_{alloc,free}_tx_cmd.
- * @dev_cmd_headroom: room needed for the transport's private use before the
- *	device_cmd for Tx - for internal use only
- *	The user should use iwl_trans_{alloc,free}_tx_cmd.
  * @rx_mpdu_cmd: MPDU RX command ID, must be assigned by opmode before
  *	starting the firmware, used for tracing
  * @rx_mpdu_cmd_hdr_size: used for tracing, amount of data before the
@@ -827,7 +869,6 @@ struct iwl_trans {
 
 	/* The following fields are internal only */
 	struct kmem_cache *dev_cmd_pool;
-	size_t dev_cmd_headroom;
 	char dev_cmd_pool_name[50];
 
 	struct dentry *dbgfs_dir;
@@ -1000,13 +1041,13 @@ iwl_trans_dump_data(struct iwl_trans *trans,
 static inline struct iwl_device_cmd *
 iwl_trans_alloc_tx_cmd(struct iwl_trans *trans)
 {
-	u8 *dev_cmd_ptr = kmem_cache_alloc(trans->dev_cmd_pool, GFP_ATOMIC);
+	struct iwl_device_cmd *dev_cmd_ptr =
+		kmem_cache_alloc(trans->dev_cmd_pool, GFP_ATOMIC);
 
 	if (unlikely(dev_cmd_ptr == NULL))
 		return NULL;
 
-	return (struct iwl_device_cmd *)
-			(dev_cmd_ptr + trans->dev_cmd_headroom);
+	return dev_cmd_ptr;
 }
 
 int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
@@ -1014,9 +1055,7 @@ int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
 static inline void iwl_trans_free_tx_cmd(struct iwl_trans *trans,
 					 struct iwl_device_cmd *dev_cmd)
 {
-	u8 *dev_cmd_ptr = (u8 *)dev_cmd - trans->dev_cmd_headroom;
-
-	kmem_cache_free(trans->dev_cmd_pool, dev_cmd_ptr);
+	kmem_cache_free(trans->dev_cmd_pool, dev_cmd);
 }
 
 static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb,
@@ -1065,20 +1104,39 @@ iwl_trans_txq_enable_cfg(struct iwl_trans *trans, int queue, u16 ssn,
 	trans->ops->txq_enable(trans, queue, ssn, cfg, queue_wdg_timeout);
 }
 
-static inline void iwl_trans_txq_set_shared_mode(struct iwl_trans *trans,
-						 int queue, bool shared_mode)
+static inline void
+iwl_trans_txq_free(struct iwl_trans *trans, int queue)
 {
-	if (trans->ops->txq_set_shared_mode)
-		trans->ops->txq_set_shared_mode(trans, queue, shared_mode);
+	if (WARN_ON_ONCE(!trans->ops->txq_free))
+		return;
+
+	trans->ops->txq_free(trans, queue);
 }
 
-static inline dma_addr_t iwl_trans_get_txq_byte_table(struct iwl_trans *trans,
-						      int queue)
+static inline int
+iwl_trans_txq_alloc(struct iwl_trans *trans,
+		    struct iwl_tx_queue_cfg_cmd *cmd,
+		    int cmd_id,
+		    unsigned int queue_wdg_timeout)
 {
-	/* we should never be called if the trans doesn't support it */
-	BUG_ON(!trans->ops->get_txq_byte_table);
+	might_sleep();
+
+	if (WARN_ON_ONCE(!trans->ops->txq_alloc))
+		return -ENOTSUPP;
+
+	if (WARN_ON_ONCE(trans->state != IWL_TRANS_FW_ALIVE)) {
+		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
+		return -EIO;
+	}
 
-	return trans->ops->get_txq_byte_table(trans, queue);
+	return trans->ops->txq_alloc(trans, cmd, cmd_id, queue_wdg_timeout);
+}
+
+static inline void iwl_trans_txq_set_shared_mode(struct iwl_trans *trans,
+						 int queue, bool shared_mode)
+{
+	if (trans->ops->txq_set_shared_mode)
+		trans->ops->txq_set_shared_mode(trans, queue, shared_mode);
 }
 
 static inline void iwl_trans_txq_enable(struct iwl_trans *trans, int queue,
@@ -1137,15 +1195,15 @@ static inline void iwl_trans_block_txq_ptrs(struct iwl_trans *trans,
 		trans->ops->block_txq_ptrs(trans, block);
 }
 
-static inline int iwl_trans_wait_tx_queue_empty(struct iwl_trans *trans,
-						u32 txqs)
+static inline int iwl_trans_wait_tx_queues_empty(struct iwl_trans *trans,
+						 u32 txqs)
 {
 	if (WARN_ON_ONCE(trans->state != IWL_TRANS_FW_ALIVE)) {
 		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
 		return -EIO;
 	}
 
-	return trans->ops->wait_tx_queue_empty(trans, txqs);
+	return trans->ops->wait_tx_queues_empty(trans, txqs);
 }
 
 static inline void iwl_trans_write8(struct iwl_trans *trans, u32 ofs, u8 val)
@@ -1248,8 +1306,7 @@ static inline void iwl_trans_fw_error(struct iwl_trans *trans)
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  struct device *dev,
 				  const struct iwl_cfg *cfg,
-				  const struct iwl_trans_ops *ops,
-				  size_t dev_cmd_headroom);
+				  const struct iwl_trans_ops *ops);
 void iwl_trans_free(struct iwl_trans *trans);
 
 /*****************************************************
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/binding.c b/drivers/net/wireless/intel/iwlwifi/mvm/binding.c
index 7cb68f6ed1b0..75d35f6b041e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/binding.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/binding.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2016 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2016 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -82,9 +84,22 @@ static int iwl_mvm_binding_cmd(struct iwl_mvm *mvm, u32 action,
 	struct iwl_mvm_phy_ctxt *phyctxt = data->phyctxt;
 	int i, ret;
 	u32 status;
+	int size;
 
 	memset(&cmd, 0, sizeof(cmd));
 
+	if (fw_has_capa(&mvm->fw->ucode_capa,
+			IWL_UCODE_TLV_CAPA_BINDING_CDB_SUPPORT)) {
+		size = sizeof(cmd);
+		if (phyctxt->channel->band == NL80211_BAND_2GHZ ||
+		    !iwl_mvm_is_cdb_supported(mvm))
+			cmd.lmac_id = cpu_to_le32(IWL_LMAC_24G_INDEX);
+		else
+			cmd.lmac_id = cpu_to_le32(IWL_LMAC_5G_INDEX);
+	} else {
+		size = IWL_BINDING_CMD_SIZE_V1;
+	}
+
 	cmd.id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(phyctxt->id,
 							   phyctxt->color));
 	cmd.action = cpu_to_le32(action);
@@ -99,7 +114,7 @@ static int iwl_mvm_binding_cmd(struct iwl_mvm *mvm, u32 action,
 
 	status = 0;
 	ret = iwl_mvm_send_cmd_pdu_status(mvm, BINDING_CONTEXT_CMD,
-					  sizeof(cmd), &cmd, &status);
+					  size, &cmd, &status);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to send binding (action:%d): %d\n",
 			action, ret);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index 5bdb6c2c8390..49b4418e6c35 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -756,7 +756,7 @@ void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	 * Rssi update while not associated - can happen since the statistics
 	 * are handled asynchronously
 	 */
-	if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT)
+	if (mvmvif->ap_sta_id == IWL_MVM_INVALID_STA)
 		return;
 
 	/* No BT - reports should be disabled */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index c7eb1983c4f9..119a3bd92c50 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -665,6 +665,19 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	struct iwl_binding_cmd binding_cmd = {};
 	struct iwl_time_quota_cmd quota_cmd = {};
 	u32 status;
+	int size;
+
+	if (fw_has_capa(&mvm->fw->ucode_capa,
+			IWL_UCODE_TLV_CAPA_BINDING_CDB_SUPPORT)) {
+		size = sizeof(binding_cmd);
+		if (mvmvif->phy_ctxt->channel->band == NL80211_BAND_2GHZ ||
+		    !iwl_mvm_is_cdb_supported(mvm))
+			binding_cmd.lmac_id = cpu_to_le32(IWL_LMAC_24G_INDEX);
+		else
+			binding_cmd.lmac_id = cpu_to_le32(IWL_LMAC_5G_INDEX);
+	} else {
+		size = IWL_BINDING_CMD_SIZE_V1;
+	}
 
 	/* add back the PHY */
 	if (WARN_ON(!mvmvif->phy_ctxt))
@@ -711,8 +724,7 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	status = 0;
 	ret = iwl_mvm_send_cmd_pdu_status(mvm, BINDING_CONTEXT_CMD,
-					  sizeof(binding_cmd), &binding_cmd,
-					  &status);
+					  size, &binding_cmd, &status);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to add binding: %d\n", ret);
 		return ret;
@@ -986,7 +998,9 @@ int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 			goto out;
 	}
 
-	if (key_data.use_tkip) {
+	if (key_data.use_tkip &&
+	    !fw_has_api(&mvm->fw->ucode_capa,
+			IWL_UCODE_TLV_API_TKIP_MIC_KEYS)) {
 		ret = iwl_mvm_send_cmd_pdu(mvm,
 					   WOWLAN_TKIP_PARAM,
 					   cmd_flags, sizeof(tkip_cmd),
@@ -1194,7 +1208,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 
 	mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
-	if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT) {
+	if (mvmvif->ap_sta_id == IWL_MVM_INVALID_STA) {
 		/* if we're not associated, this must be netdetect */
 		if (!wowlan->nd_config) {
 			ret = 1;
@@ -2102,6 +2116,10 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 	 */
 	iwl_mvm_update_changed_regdom(mvm);
 
+	if (!unified_image)
+		/*  Re-configure default SAR profile */
+		iwl_mvm_sar_select_profile(mvm, 1, 1);
+
 	if (mvm->net_detect) {
 		/* If this is a non-unified image, we restart the FW,
 		 * so no need to stop the netdetect scan.  If that
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index f4d75ffe3d8a..5d475b4850ae 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -280,7 +280,7 @@ static ssize_t iwl_dbgfs_mac_params_read(struct file *file,
 				 mvmvif->queue_params[i].uapsd);
 
 	if (vif->type == NL80211_IFTYPE_STATION &&
-	    ap_sta_id != IWL_MVM_STATION_COUNT) {
+	    ap_sta_id != IWL_MVM_INVALID_STA) {
 		struct iwl_mvm_sta *mvm_sta;
 
 		mvm_sta = iwl_mvm_sta_from_staid_protected(mvm, ap_sta_id);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index a260cd503200..402846650cbe 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -330,7 +330,7 @@ static ssize_t iwl_dbgfs_stations_read(struct file *file, char __user *user_buf,
 
 	mutex_lock(&mvm->mutex);
 
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		pos += scnprintf(buf + pos, bufsz - pos, "%.2d: ", i);
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i],
 						lockdep_is_held(&mvm->mutex));
@@ -1056,6 +1056,8 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm,
 
 	if (ret)
 		return ret;
+	if (count == 0)
+		return 0;
 
 	iwl_mvm_fw_dbg_collect(mvm, FW_DBG_TRIGGER_USER, buf,
 			       (count - 1), NULL);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-mac.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-mac.h
index 480a54af4534..970b030ed28d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-mac.h
@@ -73,7 +73,9 @@
 #define NUM_MAC_INDEX		(NUM_MAC_INDEX_DRIVER + 1)
 #define NUM_MAC_INDEX_CDB	(NUM_MAC_INDEX_DRIVER + 2)
 
-#define IWL_MVM_STATION_COUNT	16
+#define IWL_MVM_STATION_COUNT		16
+#define IWL_MVM_INVALID_STA		0xFF
+
 #define IWL_MVM_TDLS_STA_COUNT	4
 
 enum iwl_ac {
@@ -155,7 +157,8 @@ enum iwl_tsf_id {
  * @bi_reciprocal: 2^32 / bi
  * @dtim_interval: dtim transmit time in TU
  * @dtim_reciprocal: 2^32 / dtim_interval
- * @mcast_qid: queue ID for multicast traffic
+ * @mcast_qid: queue ID for multicast traffic.
+ *	NOTE: obsolete from VER2 and on
  * @beacon_template: beacon template ID
  */
 struct iwl_mac_data_ap {
@@ -167,7 +170,7 @@ struct iwl_mac_data_ap {
 	__le32 dtim_reciprocal;
 	__le32 mcast_qid;
 	__le32 beacon_template;
-} __packed; /* AP_MAC_DATA_API_S_VER_1 */
+} __packed; /* AP_MAC_DATA_API_S_VER_2 */
 
 /**
  * struct iwl_mac_data_ibss - configuration data for IBSS MAC context
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-power.h
index 3fa43d1348a2..750510aff70b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-power.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-power.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -351,6 +351,45 @@ struct iwl_dev_tx_power_cmd {
 	u8 reserved[3];
 } __packed; /* TX_REDUCED_POWER_API_S_VER_4 */
 
+#define IWL_NUM_GEO_PROFILES	3
+
+/**
+ * enum iwl_geo_per_chain_offset_operation - type of operation
+ * @IWL_PER_CHAIN_OFFSET_SET_TABLES: send the tables from the host to the FW.
+ * @IWL_PER_CHAIN_OFFSET_GET_CURRENT_TABLE: retrieve the last configured table.
+ */
+enum iwl_geo_per_chain_offset_operation {
+	IWL_PER_CHAIN_OFFSET_SET_TABLES,
+	IWL_PER_CHAIN_OFFSET_GET_CURRENT_TABLE,
+};  /* GEO_TX_POWER_LIMIT FLAGS TYPE */
+
+/**
+ * struct iwl_per_chain_offset - embedded struct for GEO_TX_POWER_LIMIT.
+ * @max_tx_power: maximum allowed tx power.
+ * @chain_a: tx power offset for chain a.
+ * @chain_b: tx power offset for chain b.
+ */
+struct iwl_per_chain_offset {
+	__le16 max_tx_power;
+	u8 chain_a;
+	u8 chain_b;
+} __packed; /* PER_CHAIN_LIMIT_OFFSET_PER_CHAIN_S_VER_1 */
+
+struct iwl_per_chain_offset_group {
+	struct iwl_per_chain_offset lb;
+	struct iwl_per_chain_offset hb;
+} __packed; /* PER_CHAIN_LIMIT_OFFSET_GROUP_S_VER_1 */
+
+/**
+ * struct iwl_geo_tx_power_profile_cmd - struct for GEO_TX_POWER_LIMIT cmd.
+ * @ops: operations, value from &enum iwl_geo_per_chain_offset_operation
+ * @table: offset profile per band.
+ */
+struct iwl_geo_tx_power_profiles_cmd {
+	__le32 ops;
+	struct iwl_per_chain_offset_group table[IWL_NUM_GEO_PROFILES];
+} __packed; /* GEO_TX_POWER_LIMIT */
+
 /**
  * struct iwl_beacon_filter_cmd
  * REPLY_BEACON_FILTERING_CMD = 0xd2 (command)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-rs.h
index ad9cc03e16c4..1b7d265ffb0a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-rs.h
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -227,6 +229,9 @@ enum {
  */
 #define RATE_LEGACY_RATE_MSK 0xff
 
+/* Bit 10 - OFDM HE */
+#define RATE_MCS_OFDM_HE_POS		10
+#define RATE_MCS_OFDM_HE_MSK		BIT(RATE_MCS_OFDM_HE_POS)
 
 /*
  * Bit 11-12: (0) 20MHz, (1) 40MHz, (2) 80MHz, (3) 160MHz
@@ -255,18 +260,29 @@ enum {
 #define RATE_MCS_ANT_MSK		RATE_MCS_ANT_ABC_MSK
 #define RATE_MCS_ANT_NUM 3
 
-/* Bit 17-18: (0) SS, (1) SS*2 */
+/* Bit 17: (0) SS, (1) SS*2 */
 #define RATE_MCS_STBC_POS		17
-#define RATE_MCS_HT_STBC_MSK		(3 << RATE_MCS_STBC_POS)
-#define RATE_MCS_VHT_STBC_MSK		(1 << RATE_MCS_STBC_POS)
+#define RATE_MCS_STBC_MSK		BIT(RATE_MCS_STBC_POS)
+
+/* Bit 18: OFDM-HE dual carrier mode */
+#define RATE_HE_DUAL_CARRIER_MODE	18
+#define RATE_HE_DUAL_CARRIER_MODE_MSK	BIT(RATE_HE_DUAL_CARRIER_MODE)
 
 /* Bit 19: (0) Beamforming is off, (1) Beamforming is on */
 #define RATE_MCS_BF_POS			19
 #define RATE_MCS_BF_MSK			(1 << RATE_MCS_BF_POS)
 
-/* Bit 20: (0) ZLF is off, (1) ZLF is on */
-#define RATE_MCS_ZLF_POS		20
-#define RATE_MCS_ZLF_MSK		(1 << RATE_MCS_ZLF_POS)
+/*
+ * Bit 20-21: HE guard interval and LTF type.
+ * (0) 1xLTF+1.6us, (1) 2xLTF+0.8us,
+ * (2) 2xLTF+1.6us, (3) 4xLTF+3.2us
+ */
+#define RATE_MCS_HE_GI_LTF_POS		20
+#define RATE_MCS_HE_GI_LTF_MSK		(3 << RATE_MCS_HE_GI_LTF_POS)
+
+/* Bit 22-23: HE type. (0) SU, (1) SU_EXT, (2) MU, (3) trigger based */
+#define RATE_MCS_HE_TYPE_POS		22
+#define RATE_MCS_HE_TYPE_MSK		(3 << RATE_MCS_HE_TYPE_POS)
 
 /* Bit 24-25: (0) 20MHz (no dup), (1) 2x20MHz, (2) 4x20MHz, 3 8x20MHz */
 #define RATE_MCS_DUP_POS		24
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-scan.h
index c78a0c499459..3178eb96e395 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-scan.h
@@ -516,7 +516,7 @@ struct iwl_scan_dwell {
  *				scan_config_channel_flag
  * @channel_array:		default supported channels
  */
-struct iwl_scan_config {
+struct iwl_scan_config_v1 {
 	__le32 flags;
 	__le32 tx_chains;
 	__le32 rx_chains;
@@ -532,7 +532,7 @@ struct iwl_scan_config {
 
 #define SCAN_TWO_LMACS 2
 
-struct iwl_scan_config_cdb {
+struct iwl_scan_config {
 	__le32 flags;
 	__le32 tx_chains;
 	__le32 rx_chains;
@@ -669,7 +669,7 @@ struct iwl_scan_req_umac {
 			u8 n_channels;
 			__le16 reserved;
 			u8 data[];
-		} no_cdb; /* SCAN_REQUEST_CMD_UMAC_API_S_VER_1 */
+		} v1; /* SCAN_REQUEST_CMD_UMAC_API_S_VER_1 */
 		struct {
 			__le32 max_out_time[SCAN_TWO_LMACS];
 			__le32 suspend_time[SCAN_TWO_LMACS];
@@ -679,13 +679,13 @@ struct iwl_scan_req_umac {
 			u8 n_channels;
 			__le16 reserved;
 			u8 data[];
-		} cdb; /* SCAN_REQUEST_CMD_UMAC_API_S_VER_5 */
+		} v6; /* SCAN_REQUEST_CMD_UMAC_API_S_VER_6 */
 	};
 } __packed;
 
-#define IWL_SCAN_REQ_UMAC_SIZE_CDB sizeof(struct iwl_scan_req_umac)
-#define IWL_SCAN_REQ_UMAC_SIZE (sizeof(struct iwl_scan_req_umac) - \
-				2 * sizeof(__le32))
+#define IWL_SCAN_REQ_UMAC_SIZE sizeof(struct iwl_scan_req_umac)
+#define IWL_SCAN_REQ_UMAC_SIZE_V1 (sizeof(struct iwl_scan_req_umac) - \
+				   2 * sizeof(__le32))
 
 /**
  * struct iwl_umac_scan_abort
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-sta.h
index 3b5150e9975d..421b9dd1fb66 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-sta.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -179,7 +179,7 @@ enum iwl_sta_key_flag {
  * enum iwl_sta_modify_flag - indicate to the fw what flag are being changed
  * @STA_MODIFY_QUEUE_REMOVAL: this command removes a queue
  * @STA_MODIFY_TID_DISABLE_TX: this command modifies %tid_disable_tx
- * @STA_MODIFY_UAPSD_ACS: this command modifies %uapsd_trigger_acs
+ * @STA_MODIFY_UAPSD_ACS: this command modifies %uapsd_acs
  * @STA_MODIFY_ADD_BA_TID: this command modifies %add_immediate_ba_tid
  * @STA_MODIFY_REMOVE_BA_TID: this command modifies %remove_immediate_ba_tid
  * @STA_MODIFY_SLEEPING_STA_TX_COUNT: this command modifies %sleep_tx_count
@@ -214,20 +214,6 @@ enum iwl_sta_sleep_flag {
 	STA_SLEEP_STATE_MOREDATA	= BIT(2),
 };
 
-/* STA ID and color bits definitions */
-#define STA_ID_SEED		(0x0f)
-#define STA_ID_POS		(0)
-#define STA_ID_MSK		(STA_ID_SEED << STA_ID_POS)
-
-#define STA_COLOR_SEED		(0x7)
-#define STA_COLOR_POS		(4)
-#define STA_COLOR_MSK		(STA_COLOR_SEED << STA_COLOR_POS)
-
-#define STA_ID_N_COLOR_GET_COLOR(id_n_color) \
-	(((id_n_color) & STA_COLOR_MSK) >> STA_COLOR_POS)
-#define STA_ID_N_COLOR_GET_ID(id_n_color)    \
-	(((id_n_color) & STA_ID_MSK) >> STA_ID_POS)
-
 #define STA_KEY_MAX_NUM (16)
 #define STA_KEY_IDX_INVALID (0xff)
 #define STA_KEY_MAX_DATA_KEY_NUM (4)
@@ -324,6 +310,24 @@ struct iwl_mvm_add_sta_cmd_v7 {
 } __packed; /* ADD_STA_CMD_API_S_VER_7 */
 
 /**
+ * enum iwl_sta_type - FW station types
+ * ( REPLY_ADD_STA = 0x18 )
+ * @IWL_STA_LINK: Link station - normal RX and TX traffic.
+ * @IWL_STA_GENERAL_PURPOSE: General purpose. In AP mode used for beacons
+ *	and probe responses.
+ * @IWL_STA_MULTICAST: multicast traffic,
+ * @IWL_STA_TDLS_LINK: TDLS link station
+ * @IWL_STA_AUX_ACTIVITY: auxilary station (scan, ROC and so on).
+ */
+enum iwl_sta_type {
+	IWL_STA_LINK,
+	IWL_STA_GENERAL_PURPOSE,
+	IWL_STA_MULTICAST,
+	IWL_STA_TDLS_LINK,
+	IWL_STA_AUX_ACTIVITY,
+};
+
+/**
  * struct iwl_mvm_add_sta_cmd - Add/modify a station in the fw's sta table.
  * ( REPLY_ADD_STA = 0x18 )
  * @add_modify: 1: modify existing, 0: add new station
@@ -347,14 +351,17 @@ struct iwl_mvm_add_sta_cmd_v7 {
  * @sleep_tx_count: number of packets to transmit to station even though it is
  *	asleep. Used to synchronise PS-poll and u-APSD responses while ucode
  *	keeps track of STA sleep state.
+ * @station_type: type of this station. See &enum iwl_sta_type.
  * @sleep_state_flags: Look at %iwl_sta_sleep_flag.
  * @assoc_id: assoc_id to be sent in VHT PLCP (9-bit), for grp use 0, for AP
  *	mac-addr.
  * @beamform_flags: beam forming controls
- * @tfd_queue_msk: tfd queues used by this station
+ * @tfd_queue_msk: tfd queues used by this station.
+ *	Obselete for new TX API (9 and above).
  * @rx_ba_window: aggregation window size
- * @scd_queue_bank: queue bank in used. Each bank contains 32 queues. 0 means
- *	that the queues used by this station are in the first 32.
+ * @sp_length: the size of the SP as it appears in the WME IE
+ * @uapsd_acs:  4 LS bits are trigger enabled ACs, 4 MS bits are the deliver
+ *	enabled ACs.
  *
  * The device contains an internal table of per-station information, with info
  * on security keys, aggregation parameters, and Tx rates for initial Tx
@@ -379,38 +386,61 @@ struct iwl_mvm_add_sta_cmd {
 	u8 remove_immediate_ba_tid;
 	__le16 add_immediate_ba_ssn;
 	__le16 sleep_tx_count;
-	__le16 sleep_state_flags;
+	u8 sleep_state_flags;
+	u8 station_type;
 	__le16 assoc_id;
 	__le16 beamform_flags;
 	__le32 tfd_queue_msk;
 	__le16 rx_ba_window;
-	u8 scd_queue_bank;
-	u8 uapsd_trigger_acs;
-} __packed; /* ADD_STA_CMD_API_S_VER_8 */
+	u8 sp_length;
+	u8 uapsd_acs;
+} __packed; /* ADD_STA_CMD_API_S_VER_10 */
 
 /**
- * struct iwl_mvm_add_sta_key_cmd - add/modify sta key
+ * struct iwl_mvm_add_sta_key_common - add/modify sta key common part
  * ( REPLY_ADD_STA_KEY = 0x17 )
  * @sta_id: index of station in uCode's station table
  * @key_offset: key offset in key storage
  * @key_flags: type %iwl_sta_key_flag
  * @key: key material data
  * @rx_secur_seq_cnt: RX security sequence counter for the key
- * @tkip_rx_tsc_byte2: TSC[2] for key mix ph1 detection
- * @tkip_rx_ttak: 10-byte unicast TKIP TTAK for Rx
  */
-struct iwl_mvm_add_sta_key_cmd {
+struct iwl_mvm_add_sta_key_common {
 	u8 sta_id;
 	u8 key_offset;
 	__le16 key_flags;
 	u8 key[32];
 	u8 rx_secur_seq_cnt[16];
+} __packed;
+
+/**
+ * struct iwl_mvm_add_sta_key_cmd_v1 - add/modify sta key
+ * @common: see &struct iwl_mvm_add_sta_key_common
+ * @tkip_rx_tsc_byte2: TSC[2] for key mix ph1 detection
+ * @tkip_rx_ttak: 10-byte unicast TKIP TTAK for Rx
+ */
+struct iwl_mvm_add_sta_key_cmd_v1 {
+	struct iwl_mvm_add_sta_key_common common;
 	u8 tkip_rx_tsc_byte2;
 	u8 reserved;
 	__le16 tkip_rx_ttak[5];
 } __packed; /* ADD_MODIFY_STA_KEY_API_S_VER_1 */
 
 /**
+ * struct iwl_mvm_add_sta_key_cmd - add/modify sta key
+ * @common: see &struct iwl_mvm_add_sta_key_common
+ * @rx_mic_key: TKIP RX unicast or multicast key
+ * @tx_mic_key: TKIP TX key
+ * @transmit_seq_cnt: TSC, transmit packet number
+ */
+struct iwl_mvm_add_sta_key_cmd {
+	struct iwl_mvm_add_sta_key_common common;
+	__le64 rx_mic_key;
+	__le64 tx_mic_key;
+	__le64 transmit_seq_cnt;
+} __packed; /* ADD_MODIFY_STA_KEY_API_S_VER_2 */
+
+/**
  * enum iwl_mvm_add_sta_rsp_status - status in the response to ADD_STA command
  * @ADD_STA_SUCCESS: operation was executed successfully
  * @ADD_STA_STATIONS_OVERLOAD: no room left in the fw's station table
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h
index b38cc073adcc..81b98915b1a4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h
@@ -6,7 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -32,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -124,6 +125,20 @@ enum iwl_tx_flags {
 }; /* TX_FLAGS_BITS_API_S_VER_1 */
 
 /**
+ * enum iwl_tx_cmd_flags - bitmasks for tx_flags in TX command for a000
+ * @IWL_TX_FLAGS_CMD_RATE: use rate from the TX command
+ * @IWL_TX_FLAGS_ENCRYPT_DIS: frame should not be encrypted, even if it belongs
+ *	to a secured STA
+ * @IWL_TX_FLAGS_HIGH_PRI: high priority frame (like EAPOL) - can affect rate
+ *	selection, retry limits and BT kill
+ */
+enum iwl_tx_cmd_flags {
+	IWL_TX_FLAGS_CMD_RATE		= BIT(0),
+	IWL_TX_FLAGS_ENCRYPT_DIS	= BIT(1),
+	IWL_TX_FLAGS_HIGH_PRI		= BIT(2),
+}; /* TX_FLAGS_BITS_API_S_VER_3 */
+
+/**
  * enum iwl_tx_pm_timeouts - pm timeout values in TX command
  * @PM_FRAME_NONE: no need to suspend sleep mode
  * @PM_FRAME_MGMT: fw suspend sleep mode for 100TU
@@ -159,7 +174,7 @@ enum iwl_tx_cmd_sec_ctrl {
 	TX_CMD_SEC_EXT			= 0x04,
 	TX_CMD_SEC_GCMP			= 0x05,
 	TX_CMD_SEC_KEY128		= 0x08,
-	TX_CMD_SEC_KEY_FROM_TABLE	= 0x08,
+	TX_CMD_SEC_KEY_FROM_TABLE	= 0x10,
 };
 
 /* TODO: how does these values are OK with only 16 bit variable??? */
@@ -301,6 +316,31 @@ struct iwl_tx_cmd {
 	struct ieee80211_hdr hdr[0];
 } __packed; /* TX_CMD_API_S_VER_6 */
 
+struct iwl_dram_sec_info {
+	__le32 pn_low;
+	__le16 pn_high;
+	__le16 aux_info;
+} __packed; /* DRAM_SEC_INFO_API_S_VER_1 */
+
+/**
+ * struct iwl_tx_cmd_gen2 - TX command struct to FW for a000 devices
+ * ( TX_CMD = 0x1c )
+ * @len: in bytes of the payload, see below for details
+ * @offload_assist: TX offload configuration
+ * @tx_flags: combination of &iwl_tx_cmd_flags
+ * @dram_info: FW internal DRAM storage
+ * @rate_n_flags: rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is
+ *	cleared. Combination of RATE_MCS_*
+ */
+struct iwl_tx_cmd_gen2 {
+	__le16 len;
+	__le16 offload_assist;
+	__le32 flags;
+	struct iwl_dram_sec_info dram_info;
+	__le32 rate_n_flags;
+	struct ieee80211_hdr hdr[0];
+} __packed; /* TX_CMD_API_S_VER_7 */
+
 /*
  * TX response related data
  */
@@ -508,9 +548,11 @@ struct agg_tx_status {
  * @tlc_info: TLC rate info
  * @ra_tid: bits [3:0] = ra, bits [7:4] = tid
  * @frame_ctrl: frame control
+ * @tx_queue: TX queue for this response
  * @status: for non-agg:  frame status TX_STATUS_*
  *	for agg: status of 1st frame, AGG_TX_STATE_*; other frame status fields
  *	follow this one, up to frame_count.
+ *	For version 6 TX response isn't received for aggregation at all.
  *
  * After the array of statuses comes the SSN of the SCD. Look at
  * %iwl_mvm_get_scd_ssn for more details.
@@ -537,9 +579,17 @@ struct iwl_mvm_tx_resp {
 	u8 tlc_info;
 	u8 ra_tid;
 	__le16 frame_ctrl;
-
-	struct agg_tx_status status;
-} __packed; /* TX_RSP_API_S_VER_3 */
+	union {
+		struct {
+			struct agg_tx_status status;
+		} v3;/* TX_RSP_API_S_VER_3 */
+		struct {
+			__le16 tx_queue;
+			__le16 reserved2;
+			struct agg_tx_status status;
+		} v6;
+	};
+} __packed; /* TX_RSP_API_S_VER_6 */
 
 /**
  * struct iwl_mvm_ba_notif - notifies about reception of BA
@@ -579,11 +629,14 @@ struct iwl_mvm_ba_notif {
  * struct iwl_mvm_compressed_ba_tfd - progress of a TFD queue
  * @q_num: TFD queue number
  * @tfd_index: Index of first un-acked frame in the  TFD queue
+ * @scd_queue: For debug only - the physical queue the TFD queue is bound to
  */
 struct iwl_mvm_compressed_ba_tfd {
-	u8 q_num;
-	u8 reserved;
+	__le16 q_num;
 	__le16 tfd_index;
+	u8 scd_queue;
+	u8 reserved;
+	__le16 reserved2;
 } __packed; /* COMPRESSED_BA_TFD_API_S_VER_1 */
 
 /**
@@ -635,6 +688,10 @@ enum iwl_mvm_ba_resp_flags {
  * @tx_rate: the rate the aggregation was sent at
  * @tfd_cnt: number of TFD-Q elements
  * @ra_tid_cnt: number of RATID-Q elements
+ * @ba_tfd: array of TFD queue status updates. See &iwl_mvm_compressed_ba_tfd
+ *	for details.
+ * @ra_tid: array of RA-TID queue status updates. For debug purposes only. See
+ *	&iwl_mvm_compressed_ba_ratid for more details.
  */
 struct iwl_mvm_compressed_ba_notif {
 	__le32 flags;
@@ -646,6 +703,7 @@ struct iwl_mvm_compressed_ba_notif {
 	__le16 query_frame_cnt;
 	__le16 txed;
 	__le16 done;
+	__le16 reserved;
 	__le32 wireless_time;
 	__le32 tx_rate;
 	__le16 tfd_cnt;
@@ -754,25 +812,6 @@ struct iwl_tx_path_flush_cmd {
 	__le16 reserved;
 } __packed; /* TX_PATH_FLUSH_CMD_API_S_VER_1 */
 
-/**
- * iwl_mvm_get_scd_ssn - returns the SSN of the SCD
- * @tx_resp: the Tx response from the fw (agg or non-agg)
- *
- * When the fw sends an AMPDU, it fetches the MPDUs one after the other. Since
- * it can't know that everything will go well until the end of the AMPDU, it
- * can't know in advance the number of MPDUs that will be sent in the current
- * batch. This is why it writes the agg Tx response while it fetches the MPDUs.
- * Hence, it can't know in advance what the SSN of the SCD will be at the end
- * of the batch. This is why the SSN of the SCD is written at the end of the
- * whole struct at a variable offset. This function knows how to cope with the
- * variable offset and returns the SSN of the SCD.
- */
-static inline u32 iwl_mvm_get_scd_ssn(struct iwl_mvm_tx_resp *tx_resp)
-{
-	return le32_to_cpup((__le32 *)&tx_resp->status +
-			    tx_resp->frame_count) & 0xfff;
-}
-
 /* Available options for the SCD_QUEUE_CFG HCMD */
 enum iwl_scd_cfg_actions {
 	SCD_CFG_DISABLE_QUEUE		= 0x0,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h
index cf2b836f3888..f545c5f9e4e3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -320,12 +320,14 @@ enum iwl_phy_ops_subcmd_ids {
 	CMD_DTS_MEASUREMENT_TRIGGER_WIDE = 0x0,
 	CTDP_CONFIG_CMD = 0x03,
 	TEMP_REPORTING_THRESHOLDS_CMD = 0x04,
+	GEO_TX_POWER_LIMIT = 0x05,
 	CT_KILL_NOTIFICATION = 0xFE,
 	DTS_MEASUREMENT_NOTIF_WIDE = 0xFF,
 };
 
 enum iwl_system_subcmd_ids {
 	SHARED_MEM_CFG_CMD = 0x0,
+	INIT_EXTENDED_CFG_CMD = 0x03,
 };
 
 enum iwl_data_path_subcmd_ids {
@@ -345,9 +347,10 @@ enum iwl_regulatory_and_nvm_subcmd_ids {
 	NVM_ACCESS_COMPLETE = 0x0,
 };
 
-enum iwl_fmac_debug_cmds {
+enum iwl_debug_cmds {
 	LMAC_RD_WR = 0x0,
 	UMAC_RD_WR = 0x1,
+	MFU_ASSERT_DUMP_NTF = 0xFE,
 };
 
 /* command groups */
@@ -673,10 +676,8 @@ struct iwl_error_resp {
 
 
 /* Common PHY, MAC and Bindings definitions */
-
 #define MAX_MACS_IN_BINDING	(3)
 #define MAX_BINDINGS		(4)
-#define AUX_BINDING_INDEX	(3)
 
 /* Used to extract ID and color from the context dword */
 #define FW_CTXT_ID_POS	  (0)
@@ -689,7 +690,7 @@ struct iwl_error_resp {
 					  (_color << FW_CTXT_COLOR_POS))
 
 /* Possible actions on PHYs, MACs and Bindings */
-enum {
+enum iwl_phy_ctxt_action {
 	FW_CTXT_ACTION_STUB = 0,
 	FW_CTXT_ACTION_ADD,
 	FW_CTXT_ACTION_MODIFY,
@@ -960,6 +961,7 @@ struct iwl_time_event_notif {
  * @action: action to perform, one of FW_CTXT_ACTION_*
  * @macs: array of MAC id and colors which belong to the binding
  * @phy: PHY id and color which belongs to the binding
+ * @lmac_id: the lmac id the binding belongs to
  */
 struct iwl_binding_cmd {
 	/* COMMON_INDEX_HDR_API_S_VER_1 */
@@ -968,7 +970,13 @@ struct iwl_binding_cmd {
 	/* BINDING_DATA_API_S_VER_1 */
 	__le32 macs[MAX_MACS_IN_BINDING];
 	__le32 phy;
-} __packed; /* BINDING_CMD_API_S_VER_1 */
+	/* BINDING_CMD_API_S_VER_1 */
+	__le32 lmac_id;
+} __packed; /* BINDING_CMD_API_S_VER_2 */
+
+#define IWL_BINDING_CMD_SIZE_V1	offsetof(struct iwl_binding_cmd, lmac_id)
+#define IWL_LMAC_24G_INDEX		0
+#define IWL_LMAC_5G_INDEX		1
 
 /* The maximal number of fragments in the FW's schedule session */
 #define IWL_MVM_MAX_QUOTA 128
@@ -990,6 +998,9 @@ struct iwl_time_quota_data {
  * struct iwl_time_quota_cmd - configuration of time quota between bindings
  * ( TIME_QUOTA_CMD = 0x2c )
  * @quotas: allocations per binding
+ * Note: on non-CDB the fourth one is the auxilary mac and is
+ *	essentially zero.
+ *	On CDB the fourth one is a regular binding.
  */
 struct iwl_time_quota_cmd {
 	struct iwl_time_quota_data quotas[MAX_BINDINGS];
@@ -1231,6 +1242,25 @@ struct iwl_mfuart_load_notif {
 } __packed; /*MFU_LOADER_NTFY_API_S_VER_2*/
 
 /**
+ * struct iwl_mfu_assert_dump_notif - mfuart dump logs
+ * ( MFU_ASSERT_DUMP_NTF = 0xfe )
+ * @assert_id: mfuart assert id that cause the notif
+ * @curr_reset_num: number of asserts since uptime
+ * @index_num: current chunk id
+ * @parts_num: total number of chunks
+ * @data_size: number of data bytes sent
+ * @data: data buffer
+ */
+struct iwl_mfu_assert_dump_notif {
+	__le32   assert_id;
+	__le32   curr_reset_num;
+	__le16   index_num;
+	__le16   parts_num;
+	__le32   data_size;
+	__le32   data[0];
+} __packed; /*MFU_DUMP_ASSERT_API_S_VER_1*/
+
+/**
  * struct iwl_set_calib_default_cmd - set default value for calibration.
  * ( SET_CALIB_DEFAULT_CMD = 0x8e )
  * @calib_index: the calibration to set value for
@@ -1998,19 +2028,48 @@ struct iwl_shared_mem_cfg_v1 {
 	__le32 internal_txfifo_size[TX_FIFO_INTERNAL_MAX_NUM];
 } __packed; /* SHARED_MEM_ALLOC_API_S_VER_2 */
 
+/**
+ * struct iwl_shared_mem_lmac_cfg - LMAC shared memory configuration
+ *
+ * @txfifo_addr: start addr of TXF0 (excluding the context table 0.5KB)
+ * @txfifo_size: size of TX FIFOs
+ * @rxfifo1_addr: RXF1 addr
+ * @rxfifo1_size: RXF1 size
+ */
+struct iwl_shared_mem_lmac_cfg {
+	__le32 txfifo_addr;
+	__le32 txfifo_size[TX_FIFO_MAX_NUM];
+	__le32 rxfifo1_addr;
+	__le32 rxfifo1_size;
+
+} __packed; /* SHARED_MEM_ALLOC_LMAC_API_S_VER_1 */
+
+/**
+ * Shared memory configuration information from the FW
+ *
+ * @shared_mem_addr: shared memory address
+ * @shared_mem_size: shared memory size
+ * @sample_buff_addr: internal sample (mon/adc) buff addr
+ * @sample_buff_size: internal sample buff size
+ * @rxfifo2_addr: start addr of RXF2
+ * @rxfifo2_size: size of RXF2
+ * @page_buff_addr: used by UMAC and performance debug (page miss analysis),
+ *	when paging is not supported this should be 0
+ * @page_buff_size: size of %page_buff_addr
+ * @lmac_num: number of LMACs (1 or 2)
+ * @lmac_smem: per - LMAC smem data
+ */
 struct iwl_shared_mem_cfg {
 	__le32 shared_mem_addr;
 	__le32 shared_mem_size;
 	__le32 sample_buff_addr;
 	__le32 sample_buff_size;
-	__le32 txfifo_addr;
-	__le32 txfifo_size[TX_FIFO_MAX_NUM];
-	__le32 rxfifo_size[RX_FIFO_MAX_NUM];
+	__le32 rxfifo2_addr;
+	__le32 rxfifo2_size;
 	__le32 page_buff_addr;
 	__le32 page_buff_size;
-	__le32 rxfifo_addr;
-	__le32 internal_txfifo_addr;
-	__le32 internal_txfifo_size[TX_FIFO_INTERNAL_MAX_NUM];
+	__le32 lmac_num;
+	struct iwl_shared_mem_lmac_cfg lmac_smem[2];
 } __packed; /* SHARED_MEM_ALLOC_API_S_VER_3 */
 
 /**
@@ -2178,4 +2237,26 @@ struct iwl_nvm_access_complete_cmd {
 	__le32 reserved;
 } __packed; /* NVM_ACCESS_COMPLETE_CMD_API_S_VER_1 */
 
+/**
+ * enum iwl_extended_cfg_flag - commands driver may send before
+ *	finishing init flow
+ * @IWL_INIT_DEBUG_CFG: driver is going to send debug config command
+ * @IWL_INIT_NVM: driver is going to send NVM_ACCESS commands
+ * @IWL_INIT_PHY: driver is going to send PHY_DB commands
+ */
+enum iwl_extended_cfg_flags {
+	IWL_INIT_DEBUG_CFG,
+	IWL_INIT_NVM,
+	IWL_INIT_PHY,
+};
+
+/**
+ * struct iwl_extended_cfg_cmd - mark what commands ucode should wait for
+ * before finishing init flows
+ * @init_flags: values from iwl_extended_cfg_flags
+ */
+struct iwl_init_extended_cfg_cmd {
+	__le32 init_flags;
+} __packed; /* INIT_EXTENDED_CFG_CMD_API_S_VER_1 */
+
 #endif /* __fw_api_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c
index a027b11bbdb3..7b86a4f1b574 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -32,7 +32,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -99,10 +99,120 @@ static void iwl_mvm_read_radio_reg(struct iwl_mvm *mvm,
 	iwl_trans_release_nic_access(mvm->trans, &flags);
 }
 
+static void iwl_mvm_dump_rxf(struct iwl_mvm *mvm,
+			     struct iwl_fw_error_dump_data **dump_data,
+			     int size, u32 offset, int fifo_num)
+{
+	struct iwl_fw_error_dump_fifo *fifo_hdr;
+	u32 *fifo_data;
+	u32 fifo_len;
+	int i;
+
+	fifo_hdr = (void *)(*dump_data)->data;
+	fifo_data = (void *)fifo_hdr->data;
+	fifo_len = size;
+
+	/* No need to try to read the data if the length is 0 */
+	if (fifo_len == 0)
+		return;
+
+	/* Add a TLV for the RXF */
+	(*dump_data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_RXF);
+	(*dump_data)->len = cpu_to_le32(fifo_len + sizeof(*fifo_hdr));
+
+	fifo_hdr->fifo_num = cpu_to_le32(fifo_num);
+	fifo_hdr->available_bytes =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						RXF_RD_D_SPACE + offset));
+	fifo_hdr->wr_ptr =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						RXF_RD_WR_PTR + offset));
+	fifo_hdr->rd_ptr =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						RXF_RD_RD_PTR + offset));
+	fifo_hdr->fence_ptr =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						RXF_RD_FENCE_PTR + offset));
+	fifo_hdr->fence_mode =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						RXF_SET_FENCE_MODE + offset));
+
+	/* Lock fence */
+	iwl_trans_write_prph(mvm->trans, RXF_SET_FENCE_MODE + offset, 0x1);
+	/* Set fence pointer to the same place like WR pointer */
+	iwl_trans_write_prph(mvm->trans, RXF_LD_WR2FENCE + offset, 0x1);
+	/* Set fence offset */
+	iwl_trans_write_prph(mvm->trans,
+			     RXF_LD_FENCE_OFFSET_ADDR + offset, 0x0);
+
+	/* Read FIFO */
+	fifo_len /= sizeof(u32); /* Size in DWORDS */
+	for (i = 0; i < fifo_len; i++)
+		fifo_data[i] = iwl_trans_read_prph(mvm->trans,
+						 RXF_FIFO_RD_FENCE_INC +
+						 offset);
+	*dump_data = iwl_fw_error_next_data(*dump_data);
+}
+
+static void iwl_mvm_dump_txf(struct iwl_mvm *mvm,
+			     struct iwl_fw_error_dump_data **dump_data,
+			     int size, u32 offset, int fifo_num)
+{
+	struct iwl_fw_error_dump_fifo *fifo_hdr;
+	u32 *fifo_data;
+	u32 fifo_len;
+	int i;
+
+	fifo_hdr = (void *)(*dump_data)->data;
+	fifo_data = (void *)fifo_hdr->data;
+	fifo_len = size;
+
+	/* No need to try to read the data if the length is 0 */
+	if (fifo_len == 0)
+		return;
+
+	/* Add a TLV for the FIFO */
+	(*dump_data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXF);
+	(*dump_data)->len = cpu_to_le32(fifo_len + sizeof(*fifo_hdr));
+
+	fifo_hdr->fifo_num = cpu_to_le32(fifo_num);
+	fifo_hdr->available_bytes =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						TXF_FIFO_ITEM_CNT + offset));
+	fifo_hdr->wr_ptr =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						TXF_WR_PTR + offset));
+	fifo_hdr->rd_ptr =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						TXF_RD_PTR + offset));
+	fifo_hdr->fence_ptr =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						TXF_FENCE_PTR + offset));
+	fifo_hdr->fence_mode =
+		cpu_to_le32(iwl_trans_read_prph(mvm->trans,
+						TXF_LOCK_FENCE + offset));
+
+	/* Set the TXF_READ_MODIFY_ADDR to TXF_WR_PTR */
+	iwl_trans_write_prph(mvm->trans, TXF_READ_MODIFY_ADDR + offset,
+			     TXF_WR_PTR + offset);
+
+	/* Dummy-read to advance the read pointer to the head */
+	iwl_trans_read_prph(mvm->trans, TXF_READ_MODIFY_DATA + offset);
+
+	/* Read FIFO */
+	fifo_len /= sizeof(u32); /* Size in DWORDS */
+	for (i = 0; i < fifo_len; i++)
+		fifo_data[i] = iwl_trans_read_prph(mvm->trans,
+						  TXF_READ_MODIFY_DATA +
+						  offset);
+	*dump_data = iwl_fw_error_next_data(*dump_data);
+}
+
 static void iwl_mvm_dump_fifos(struct iwl_mvm *mvm,
 			       struct iwl_fw_error_dump_data **dump_data)
 {
 	struct iwl_fw_error_dump_fifo *fifo_hdr;
+	struct iwl_mvm_shared_mem_cfg *cfg = &mvm->smem_cfg;
 	u32 *fifo_data;
 	u32 fifo_len;
 	unsigned long flags;
@@ -111,126 +221,47 @@ static void iwl_mvm_dump_fifos(struct iwl_mvm *mvm,
 	if (!iwl_trans_grab_nic_access(mvm->trans, &flags))
 		return;
 
-	/* Pull RXF data from all RXFs */
-	for (i = 0; i < ARRAY_SIZE(mvm->shared_mem_cfg.rxfifo_size); i++) {
-		/*
-		 * Keep aside the additional offset that might be needed for
-		 * next RXF
-		 */
-		u32 offset_diff = RXF_DIFF_FROM_PREV * i;
-
-		fifo_hdr = (void *)(*dump_data)->data;
-		fifo_data = (void *)fifo_hdr->data;
-		fifo_len = mvm->shared_mem_cfg.rxfifo_size[i];
-
-		/* No need to try to read the data if the length is 0 */
-		if (fifo_len == 0)
-			continue;
-
-		/* Add a TLV for the RXF */
-		(*dump_data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_RXF);
-		(*dump_data)->len = cpu_to_le32(fifo_len + sizeof(*fifo_hdr));
-
-		fifo_hdr->fifo_num = cpu_to_le32(i);
-		fifo_hdr->available_bytes =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							RXF_RD_D_SPACE +
-							offset_diff));
-		fifo_hdr->wr_ptr =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							RXF_RD_WR_PTR +
-							offset_diff));
-		fifo_hdr->rd_ptr =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							RXF_RD_RD_PTR +
-							offset_diff));
-		fifo_hdr->fence_ptr =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							RXF_RD_FENCE_PTR +
-							offset_diff));
-		fifo_hdr->fence_mode =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							RXF_SET_FENCE_MODE +
-							offset_diff));
-
-		/* Lock fence */
-		iwl_trans_write_prph(mvm->trans,
-				     RXF_SET_FENCE_MODE + offset_diff, 0x1);
-		/* Set fence pointer to the same place like WR pointer */
-		iwl_trans_write_prph(mvm->trans,
-				     RXF_LD_WR2FENCE + offset_diff, 0x1);
-		/* Set fence offset */
-		iwl_trans_write_prph(mvm->trans,
-				     RXF_LD_FENCE_OFFSET_ADDR + offset_diff,
-				     0x0);
-
-		/* Read FIFO */
-		fifo_len /= sizeof(u32); /* Size in DWORDS */
-		for (j = 0; j < fifo_len; j++)
-			fifo_data[j] = iwl_trans_read_prph(mvm->trans,
-							 RXF_FIFO_RD_FENCE_INC +
-							 offset_diff);
-		*dump_data = iwl_fw_error_next_data(*dump_data);
-	}
-
-	/* Pull TXF data from all TXFs */
-	for (i = 0; i < ARRAY_SIZE(mvm->shared_mem_cfg.txfifo_size); i++) {
+	/* Pull RXF1 */
+	iwl_mvm_dump_rxf(mvm, dump_data, cfg->lmac[0].rxfifo1_size, 0, 0);
+	/* Pull RXF2 */
+	iwl_mvm_dump_rxf(mvm, dump_data, cfg->rxfifo2_size,
+			 RXF_DIFF_FROM_PREV, 1);
+	/* Pull LMAC2 RXF1 */
+	if (mvm->smem_cfg.num_lmacs > 1)
+		iwl_mvm_dump_rxf(mvm, dump_data, cfg->lmac[1].rxfifo1_size,
+				 LMAC2_PRPH_OFFSET, 2);
+
+	/* Pull TXF data from LMAC1 */
+	for (i = 0; i < mvm->smem_cfg.num_txfifo_entries; i++) {
 		/* Mark the number of TXF we're pulling now */
 		iwl_trans_write_prph(mvm->trans, TXF_LARC_NUM, i);
+		iwl_mvm_dump_txf(mvm, dump_data, cfg->lmac[0].txfifo_size[i],
+				 0, i);
+	}
 
-		fifo_hdr = (void *)(*dump_data)->data;
-		fifo_data = (void *)fifo_hdr->data;
-		fifo_len = mvm->shared_mem_cfg.txfifo_size[i];
-
-		/* No need to try to read the data if the length is 0 */
-		if (fifo_len == 0)
-			continue;
-
-		/* Add a TLV for the FIFO */
-		(*dump_data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXF);
-		(*dump_data)->len = cpu_to_le32(fifo_len + sizeof(*fifo_hdr));
-
-		fifo_hdr->fifo_num = cpu_to_le32(i);
-		fifo_hdr->available_bytes =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							TXF_FIFO_ITEM_CNT));
-		fifo_hdr->wr_ptr =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							TXF_WR_PTR));
-		fifo_hdr->rd_ptr =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							TXF_RD_PTR));
-		fifo_hdr->fence_ptr =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							TXF_FENCE_PTR));
-		fifo_hdr->fence_mode =
-			cpu_to_le32(iwl_trans_read_prph(mvm->trans,
-							TXF_LOCK_FENCE));
-
-		/* Set the TXF_READ_MODIFY_ADDR to TXF_WR_PTR */
-		iwl_trans_write_prph(mvm->trans, TXF_READ_MODIFY_ADDR,
-				     TXF_WR_PTR);
-
-		/* Dummy-read to advance the read pointer to the head */
-		iwl_trans_read_prph(mvm->trans, TXF_READ_MODIFY_DATA);
-
-		/* Read FIFO */
-		fifo_len /= sizeof(u32); /* Size in DWORDS */
-		for (j = 0; j < fifo_len; j++)
-			fifo_data[j] = iwl_trans_read_prph(mvm->trans,
-							  TXF_READ_MODIFY_DATA);
-		*dump_data = iwl_fw_error_next_data(*dump_data);
+	/* Pull TXF data from LMAC2 */
+	if (mvm->smem_cfg.num_lmacs > 1) {
+		for (i = 0; i < mvm->smem_cfg.num_txfifo_entries; i++) {
+			/* Mark the number of TXF we're pulling now */
+			iwl_trans_write_prph(mvm->trans,
+					     TXF_LARC_NUM + LMAC2_PRPH_OFFSET,
+					     i);
+			iwl_mvm_dump_txf(mvm, dump_data,
+					 cfg->lmac[1].txfifo_size[i],
+					 LMAC2_PRPH_OFFSET,
+					 i + cfg->num_txfifo_entries);
+		}
 	}
 
 	if (fw_has_capa(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 		/* Pull UMAC internal TXF data from all TXFs */
 		for (i = 0;
-		     i < ARRAY_SIZE(mvm->shared_mem_cfg.internal_txfifo_size);
+		     i < ARRAY_SIZE(mvm->smem_cfg.internal_txfifo_size);
 		     i++) {
 			fifo_hdr = (void *)(*dump_data)->data;
 			fifo_data = (void *)fifo_hdr->data;
-			fifo_len = mvm->shared_mem_cfg.internal_txfifo_size[i];
+			fifo_len = mvm->smem_cfg.internal_txfifo_size[i];
 
 			/* No need to try to read the data if the length is 0 */
 			if (fifo_len == 0)
@@ -246,7 +277,7 @@ static void iwl_mvm_dump_fifos(struct iwl_mvm *mvm,
 
 			/* Mark the number of TXF we're pulling now */
 			iwl_trans_write_prph(mvm->trans, TXF_CPU2_NUM, i +
-				ARRAY_SIZE(mvm->shared_mem_cfg.txfifo_size));
+				mvm->smem_cfg.num_txfifo_entries);
 
 			fifo_hdr->available_bytes =
 				cpu_to_le32(iwl_trans_read_prph(mvm->trans,
@@ -553,31 +584,45 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm)
 
 	/* reading RXF/TXF sizes */
 	if (test_bit(STATUS_FW_ERROR, &mvm->trans->status)) {
-		struct iwl_mvm_shared_mem_cfg *mem_cfg = &mvm->shared_mem_cfg;
+		struct iwl_mvm_shared_mem_cfg *mem_cfg = &mvm->smem_cfg;
 
 		fifo_data_len = 0;
 
-		/* Count RXF size */
-		for (i = 0; i < ARRAY_SIZE(mem_cfg->rxfifo_size); i++) {
-			if (!mem_cfg->rxfifo_size[i])
-				continue;
-
+		/* Count RXF2 size */
+		if (mem_cfg->rxfifo2_size) {
 			/* Add header info */
-			fifo_data_len += mem_cfg->rxfifo_size[i] +
+			fifo_data_len += mem_cfg->rxfifo2_size +
 					 sizeof(*dump_data) +
 					 sizeof(struct iwl_fw_error_dump_fifo);
 		}
 
-		for (i = 0; i < mem_cfg->num_txfifo_entries; i++) {
-			if (!mem_cfg->txfifo_size[i])
+		/* Count RXF1 sizes */
+		for (i = 0; i < mem_cfg->num_lmacs; i++) {
+			if (!mem_cfg->lmac[i].rxfifo1_size)
 				continue;
 
 			/* Add header info */
-			fifo_data_len += mem_cfg->txfifo_size[i] +
+			fifo_data_len += mem_cfg->lmac[i].rxfifo1_size +
 					 sizeof(*dump_data) +
 					 sizeof(struct iwl_fw_error_dump_fifo);
 		}
 
+		/* Count TXF sizes */
+		for (i = 0; i < mem_cfg->num_lmacs; i++) {
+			int j;
+
+			for (j = 0; j < mem_cfg->num_txfifo_entries; j++) {
+				if (!mem_cfg->lmac[i].txfifo_size[j])
+					continue;
+
+				/* Add header info */
+				fifo_data_len +=
+					mem_cfg->lmac[i].txfifo_size[j] +
+					sizeof(*dump_data) +
+					sizeof(struct iwl_fw_error_dump_fifo);
+			}
+		}
+
 		if (fw_has_capa(&mvm->fw->ucode_capa,
 				IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 			for (i = 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 45cb4f476e76..e6c9528eeeda 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,6 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -271,6 +272,27 @@ static int iwl_fill_paging_mem(struct iwl_mvm *mvm, const struct fw_img *image)
 	return 0;
 }
 
+void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm,
+				   struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_mfu_assert_dump_notif *mfu_dump_notif = (void *)pkt->data;
+	__le32 *dump_data = mfu_dump_notif->data;
+	int n_words = le32_to_cpu(mfu_dump_notif->data_size) / sizeof(__le32);
+	int i;
+
+	if (mfu_dump_notif->index_num == 0)
+		IWL_INFO(mvm, "MFUART assert id 0x%x occurred\n",
+			 le32_to_cpu(mfu_dump_notif->assert_id));
+
+	for (i = 0; i < n_words; i++)
+		IWL_DEBUG_INFO(mvm,
+			       "MFUART assert dump, dword %u: 0x%08x\n",
+			       le16_to_cpu(mfu_dump_notif->index_num) *
+			       n_words + i,
+			       le32_to_cpu(dump_data[i]));
+}
+
 static int iwl_alloc_fw_paging_mem(struct iwl_mvm *mvm,
 				   const struct fw_img *image)
 {
@@ -617,11 +639,18 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	ret = iwl_wait_notification(&mvm->notif_wait, &alive_wait,
 				    MVM_UCODE_ALIVE_TIMEOUT);
 	if (ret) {
-		if (mvm->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
+		struct iwl_trans *trans = mvm->trans;
+
+		if (trans->cfg->gen2)
+			IWL_ERR(mvm,
+				"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
+				iwl_read_prph(trans, UMAG_SB_CPU_1_STATUS),
+				iwl_read_prph(trans, UMAG_SB_CPU_2_STATUS));
+		else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
 			IWL_ERR(mvm,
 				"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
-				iwl_read_prph(mvm->trans, SB_CPU_1_STATUS),
-				iwl_read_prph(mvm->trans, SB_CPU_2_STATUS));
+				iwl_read_prph(trans, SB_CPU_1_STATUS),
+				iwl_read_prph(trans, SB_CPU_2_STATUS));
 		mvm->cur_ucode = old_type;
 		return ret;
 	}
@@ -669,6 +698,82 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	return 0;
 }
 
+static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
+{
+	struct iwl_notification_wait init_wait;
+	struct iwl_nvm_access_complete_cmd nvm_complete = {};
+	struct iwl_init_extended_cfg_cmd init_cfg = {
+		.init_flags = cpu_to_le32(BIT(IWL_INIT_NVM)),
+	};
+	static const u16 init_complete[] = {
+		INIT_COMPLETE_NOTIF,
+	};
+	int ret;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	iwl_init_notification_wait(&mvm->notif_wait,
+				   &init_wait,
+				   init_complete,
+				   ARRAY_SIZE(init_complete),
+				   iwl_wait_init_complete,
+				   NULL);
+
+	/* Will also start the device */
+	ret = iwl_mvm_load_ucode_wait_alive(mvm, IWL_UCODE_REGULAR);
+	if (ret) {
+		IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
+		goto error;
+	}
+
+	/* Send init config command to mark that we are sending NVM access
+	 * commands
+	 */
+	ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(SYSTEM_GROUP,
+						INIT_EXTENDED_CFG_CMD), 0,
+				   sizeof(init_cfg), &init_cfg);
+	if (ret) {
+		IWL_ERR(mvm, "Failed to run init config command: %d\n",
+			ret);
+		goto error;
+	}
+
+	/* Read the NVM only at driver load time, no need to do this twice */
+	if (read_nvm) {
+		/* Read nvm */
+		ret = iwl_nvm_init(mvm, true);
+		if (ret) {
+			IWL_ERR(mvm, "Failed to read NVM: %d\n", ret);
+			goto error;
+		}
+	}
+
+	/* In case we read the NVM from external file, load it to the NIC */
+	if (mvm->nvm_file_name)
+		iwl_mvm_load_nvm_to_nic(mvm);
+
+	ret = iwl_nvm_check_version(mvm->nvm_data, mvm->trans);
+	if (WARN_ON(ret))
+		goto error;
+
+	ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(REGULATORY_AND_NVM_GROUP,
+						NVM_ACCESS_COMPLETE), 0,
+				   sizeof(nvm_complete), &nvm_complete);
+	if (ret) {
+		IWL_ERR(mvm, "Failed to run complete NVM access: %d\n",
+			ret);
+		goto error;
+	}
+
+	/* We wait for the INIT complete notification */
+	return iwl_wait_notification(&mvm->notif_wait, &init_wait,
+				     MVM_UCODE_ALIVE_TIMEOUT);
+
+error:
+	iwl_remove_notification(&mvm->notif_wait, &init_wait);
+	return ret;
+}
+
 static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 {
 	struct iwl_phy_cfg_cmd phy_cfg_cmd;
@@ -697,6 +802,9 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	};
 	int ret;
 
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return iwl_run_unified_mvm_ucode(mvm, true);
+
 	lockdep_assert_held(&mvm->mutex);
 
 	if (WARN_ON_ONCE(mvm->calibrating))
@@ -803,97 +911,31 @@ out:
 	return ret;
 }
 
-int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
-{
-	struct iwl_notification_wait init_wait;
-	struct iwl_nvm_access_complete_cmd nvm_complete = {};
-	static const u16 init_complete[] = {
-		INIT_COMPLETE_NOTIF,
-	};
-	int ret;
-
-	lockdep_assert_held(&mvm->mutex);
-
-	iwl_init_notification_wait(&mvm->notif_wait,
-				   &init_wait,
-				   init_complete,
-				   ARRAY_SIZE(init_complete),
-				   iwl_wait_init_complete,
-				   NULL);
-
-	/* Will also start the device */
-	ret = iwl_mvm_load_ucode_wait_alive(mvm, IWL_UCODE_REGULAR);
-	if (ret) {
-		IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
-		goto error;
-	}
-
-	/* TODO: remove when integrating context info */
-	ret = iwl_mvm_init_paging(mvm);
-	if (ret) {
-		IWL_ERR(mvm, "Failed to init paging: %d\n",
-			ret);
-		goto error;
-	}
-
-	/* Read the NVM only at driver load time, no need to do this twice */
-	if (read_nvm) {
-		/* Read nvm */
-		ret = iwl_nvm_init(mvm, true);
-		if (ret) {
-			IWL_ERR(mvm, "Failed to read NVM: %d\n", ret);
-			goto error;
-		}
-	}
-
-	/* In case we read the NVM from external file, load it to the NIC */
-	if (mvm->nvm_file_name)
-		iwl_mvm_load_nvm_to_nic(mvm);
-
-	ret = iwl_nvm_check_version(mvm->nvm_data, mvm->trans);
-	if (WARN_ON(ret))
-		goto error;
-
-	ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(REGULATORY_AND_NVM_GROUP,
-						NVM_ACCESS_COMPLETE), 0,
-				   sizeof(nvm_complete), &nvm_complete);
-	if (ret) {
-		IWL_ERR(mvm, "Failed to run complete NVM access: %d\n",
-			ret);
-		goto error;
-	}
-
-	/* We wait for the INIT complete notification */
-	return iwl_wait_notification(&mvm->notif_wait, &init_wait,
-				     MVM_UCODE_ALIVE_TIMEOUT);
-
-error:
-	iwl_remove_notification(&mvm->notif_wait, &init_wait);
-	return ret;
-}
-
 static void iwl_mvm_parse_shared_mem_a000(struct iwl_mvm *mvm,
 					  struct iwl_rx_packet *pkt)
 {
 	struct iwl_shared_mem_cfg *mem_cfg = (void *)pkt->data;
-	int i;
+	int i, lmac;
+	int lmac_num = le32_to_cpu(mem_cfg->lmac_num);
 
-	mvm->shared_mem_cfg.num_txfifo_entries =
-		ARRAY_SIZE(mvm->shared_mem_cfg.txfifo_size);
-	for (i = 0; i < ARRAY_SIZE(mem_cfg->txfifo_size); i++)
-		mvm->shared_mem_cfg.txfifo_size[i] =
-			le32_to_cpu(mem_cfg->txfifo_size[i]);
-	for (i = 0; i < ARRAY_SIZE(mvm->shared_mem_cfg.rxfifo_size); i++)
-		mvm->shared_mem_cfg.rxfifo_size[i] =
-			le32_to_cpu(mem_cfg->rxfifo_size[i]);
+	if (WARN_ON(lmac_num > ARRAY_SIZE(mem_cfg->lmac_smem)))
+		return;
+
+	mvm->smem_cfg.num_lmacs = lmac_num;
+	mvm->smem_cfg.num_txfifo_entries =
+		ARRAY_SIZE(mem_cfg->lmac_smem[0].txfifo_size);
+	mvm->smem_cfg.rxfifo2_size = le32_to_cpu(mem_cfg->rxfifo2_size);
 
-	BUILD_BUG_ON(sizeof(mvm->shared_mem_cfg.internal_txfifo_size) !=
-		     sizeof(mem_cfg->internal_txfifo_size));
+	for (lmac = 0; lmac < lmac_num; lmac++) {
+		struct iwl_shared_mem_lmac_cfg *lmac_cfg =
+			&mem_cfg->lmac_smem[lmac];
 
-	for (i = 0; i < ARRAY_SIZE(mvm->shared_mem_cfg.internal_txfifo_size);
-	     i++)
-		mvm->shared_mem_cfg.internal_txfifo_size[i] =
-			le32_to_cpu(mem_cfg->internal_txfifo_size[i]);
+		for (i = 0; i < ARRAY_SIZE(lmac_cfg->txfifo_size); i++)
+			mvm->smem_cfg.lmac[lmac].txfifo_size[i] =
+				le32_to_cpu(lmac_cfg->txfifo_size[i]);
+		mvm->smem_cfg.lmac[lmac].rxfifo1_size =
+			le32_to_cpu(lmac_cfg->rxfifo1_size);
+	}
 }
 
 static void iwl_mvm_parse_shared_mem(struct iwl_mvm *mvm,
@@ -902,25 +944,27 @@ static void iwl_mvm_parse_shared_mem(struct iwl_mvm *mvm,
 	struct iwl_shared_mem_cfg_v1 *mem_cfg = (void *)pkt->data;
 	int i;
 
-	mvm->shared_mem_cfg.num_txfifo_entries =
-		ARRAY_SIZE(mvm->shared_mem_cfg.txfifo_size);
+	mvm->smem_cfg.num_lmacs = 1;
+
+	mvm->smem_cfg.num_txfifo_entries = ARRAY_SIZE(mem_cfg->txfifo_size);
 	for (i = 0; i < ARRAY_SIZE(mem_cfg->txfifo_size); i++)
-		mvm->shared_mem_cfg.txfifo_size[i] =
+		mvm->smem_cfg.lmac[0].txfifo_size[i] =
 			le32_to_cpu(mem_cfg->txfifo_size[i]);
-	for (i = 0; i < ARRAY_SIZE(mvm->shared_mem_cfg.rxfifo_size); i++)
-		mvm->shared_mem_cfg.rxfifo_size[i] =
-			le32_to_cpu(mem_cfg->rxfifo_size[i]);
+
+	mvm->smem_cfg.lmac[0].rxfifo1_size =
+		le32_to_cpu(mem_cfg->rxfifo_size[0]);
+	mvm->smem_cfg.rxfifo2_size = le32_to_cpu(mem_cfg->rxfifo_size[1]);
 
 	/* new API has more data, from rxfifo_addr field and on */
 	if (fw_has_capa(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
-		BUILD_BUG_ON(sizeof(mvm->shared_mem_cfg.internal_txfifo_size) !=
+		BUILD_BUG_ON(sizeof(mvm->smem_cfg.internal_txfifo_size) !=
 			     sizeof(mem_cfg->internal_txfifo_size));
 
 		for (i = 0;
-		     i < ARRAY_SIZE(mvm->shared_mem_cfg.internal_txfifo_size);
+		     i < ARRAY_SIZE(mvm->smem_cfg.internal_txfifo_size);
 		     i++)
-			mvm->shared_mem_cfg.internal_txfifo_size[i] =
+			mvm->smem_cfg.internal_txfifo_size[i] =
 				le32_to_cpu(mem_cfg->internal_txfifo_size[i]);
 	}
 }
@@ -969,85 +1013,94 @@ static int iwl_mvm_config_ltr(struct iwl_mvm *mvm)
 				    sizeof(cmd), &cmd);
 }
 
-#define ACPI_WRDS_METHOD	"WRDS"
-#define ACPI_WRDS_WIFI		(0x07)
-#define ACPI_WRDS_TABLE_SIZE	10
+#ifdef CONFIG_ACPI
+#define ACPI_WRDS_METHOD		"WRDS"
+#define ACPI_EWRD_METHOD		"EWRD"
+#define ACPI_WGDS_METHOD		"WGDS"
+#define ACPI_WIFI_DOMAIN		(0x07)
+#define ACPI_WRDS_WIFI_DATA_SIZE	(IWL_MVM_SAR_TABLE_SIZE + 2)
+#define ACPI_EWRD_WIFI_DATA_SIZE	((IWL_MVM_SAR_PROFILE_NUM - 1) * \
+					 IWL_MVM_SAR_TABLE_SIZE + 3)
+#define ACPI_WGDS_WIFI_DATA_SIZE	18
+#define ACPI_WGDS_NUM_BANDS		2
+#define ACPI_WGDS_TABLE_SIZE		3
+
+static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm,
+				   union acpi_object *table,
+				   struct iwl_mvm_sar_profile *profile,
+				   bool enabled)
+{
+	int i;
 
-struct iwl_mvm_sar_table {
-	bool enabled;
-	u8 values[ACPI_WRDS_TABLE_SIZE];
-};
+	profile->enabled = enabled;
 
-#ifdef CONFIG_ACPI
-static int iwl_mvm_sar_get_wrds(struct iwl_mvm *mvm, union acpi_object *wrds,
-				struct iwl_mvm_sar_table *sar_table)
+	for (i = 0; i < IWL_MVM_SAR_TABLE_SIZE; i++) {
+		if ((table[i].type != ACPI_TYPE_INTEGER) ||
+		    (table[i].integer.value > U8_MAX))
+			return -EINVAL;
+
+		profile->table[i] = table[i].integer.value;
+	}
+
+	return 0;
+}
+
+static union acpi_object *iwl_mvm_sar_find_wifi_pkg(struct iwl_mvm *mvm,
+						    union acpi_object *data,
+						    int data_size)
 {
-	union acpi_object *data_pkg;
-	u32 i;
+	int i;
+	union acpi_object *wifi_pkg;
 
-	/* We need at least two packages, one for the revision and one
+	/*
+	 * We need at least two packages, one for the revision and one
 	 * for the data itself.  Also check that the revision is valid
 	 * (i.e. it is an integer set to 0).
-	*/
-	if (wrds->type != ACPI_TYPE_PACKAGE ||
-	    wrds->package.count < 2 ||
-	    wrds->package.elements[0].type != ACPI_TYPE_INTEGER ||
-	    wrds->package.elements[0].integer.value != 0) {
-		IWL_DEBUG_RADIO(mvm, "Unsupported wrds structure\n");
-		return -EINVAL;
+	 */
+	if (data->type != ACPI_TYPE_PACKAGE ||
+	    data->package.count < 2 ||
+	    data->package.elements[0].type != ACPI_TYPE_INTEGER ||
+	    data->package.elements[0].integer.value != 0) {
+		IWL_DEBUG_RADIO(mvm, "Unsupported packages structure\n");
+		return ERR_PTR(-EINVAL);
 	}
 
 	/* loop through all the packages to find the one for WiFi */
-	for (i = 1; i < wrds->package.count; i++) {
+	for (i = 1; i < data->package.count; i++) {
 		union acpi_object *domain;
 
-		data_pkg = &wrds->package.elements[i];
+		wifi_pkg = &data->package.elements[i];
 
 		/* Skip anything that is not a package with the right
 		 * amount of elements (i.e. domain_type,
-		 * enabled/disabled plus the sar table size.
+		 * enabled/disabled plus the actual data size.
 		 */
-		if (data_pkg->type != ACPI_TYPE_PACKAGE ||
-		    data_pkg->package.count != ACPI_WRDS_TABLE_SIZE + 2)
+		if (wifi_pkg->type != ACPI_TYPE_PACKAGE ||
+		    wifi_pkg->package.count != data_size)
 			continue;
 
-		domain = &data_pkg->package.elements[0];
+		domain = &wifi_pkg->package.elements[0];
 		if (domain->type == ACPI_TYPE_INTEGER &&
-		    domain->integer.value == ACPI_WRDS_WIFI)
+		    domain->integer.value == ACPI_WIFI_DOMAIN)
 			break;
 
-		data_pkg = NULL;
+		wifi_pkg = NULL;
 	}
 
-	if (!data_pkg)
-		return -ENOENT;
-
-	if (data_pkg->package.elements[1].type != ACPI_TYPE_INTEGER)
-		return -EINVAL;
-
-	sar_table->enabled = !!(data_pkg->package.elements[1].integer.value);
-
-	for (i = 0; i < ACPI_WRDS_TABLE_SIZE; i++) {
-		union acpi_object *entry;
-
-		entry = &data_pkg->package.elements[i + 2];
-		if ((entry->type != ACPI_TYPE_INTEGER) ||
-		    (entry->integer.value > U8_MAX))
-			return -EINVAL;
-
-		sar_table->values[i] = entry->integer.value;
-	}
+	if (!wifi_pkg)
+		return ERR_PTR(-ENOENT);
 
-	return 0;
+	return wifi_pkg;
 }
 
-static int iwl_mvm_sar_get_table(struct iwl_mvm *mvm,
-				 struct iwl_mvm_sar_table *sar_table)
+static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm)
 {
+	union acpi_object *wifi_pkg, *table;
 	acpi_handle root_handle;
 	acpi_handle handle;
 	struct acpi_buffer wrds = {ACPI_ALLOCATE_BUFFER, NULL};
 	acpi_status status;
+	bool enabled;
 	int ret;
 
 	root_handle = ACPI_HANDLE(mvm->dev);
@@ -1072,62 +1125,307 @@ static int iwl_mvm_sar_get_table(struct iwl_mvm *mvm,
 		return -ENOENT;
 	}
 
-	ret = iwl_mvm_sar_get_wrds(mvm, wrds.pointer, sar_table);
+	wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, wrds.pointer,
+					     ACPI_WRDS_WIFI_DATA_SIZE);
+	if (IS_ERR(wifi_pkg)) {
+		ret = PTR_ERR(wifi_pkg);
+		goto out_free;
+	}
+
+	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	enabled = !!(wifi_pkg->package.elements[1].integer.value);
+
+	/* position of the actual table */
+	table = &wifi_pkg->package.elements[2];
+
+	/* The profile from WRDS is officially profile 1, but goes
+	 * into sar_profiles[0] (because we don't have a profile 0).
+	 */
+	ret = iwl_mvm_sar_set_profile(mvm, table, &mvm->sar_profiles[0],
+				      enabled);
+
+out_free:
 	kfree(wrds.pointer);
+	return ret;
+}
 
+static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm)
+{
+	union acpi_object *wifi_pkg;
+	acpi_handle root_handle;
+	acpi_handle handle;
+	struct acpi_buffer ewrd = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_status status;
+	bool enabled;
+	int i, n_profiles, ret;
+
+	root_handle = ACPI_HANDLE(mvm->dev);
+	if (!root_handle) {
+		IWL_DEBUG_RADIO(mvm,
+				"Could not retrieve root port ACPI handle\n");
+		return -ENOENT;
+	}
+
+	/* Get the method's handle */
+	status = acpi_get_handle(root_handle, (acpi_string)ACPI_EWRD_METHOD,
+				 &handle);
+	if (ACPI_FAILURE(status)) {
+		IWL_DEBUG_RADIO(mvm, "EWRD method not found\n");
+		return -ENOENT;
+	}
+
+	/* Call EWRD with no arguments */
+	status = acpi_evaluate_object(handle, NULL, NULL, &ewrd);
+	if (ACPI_FAILURE(status)) {
+		IWL_DEBUG_RADIO(mvm, "EWRD invocation failed (0x%x)\n", status);
+		return -ENOENT;
+	}
+
+	wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, ewrd.pointer,
+					     ACPI_EWRD_WIFI_DATA_SIZE);
+	if (IS_ERR(wifi_pkg)) {
+		ret = PTR_ERR(wifi_pkg);
+		goto out_free;
+	}
+
+	if ((wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) ||
+	    (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER)) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	enabled = !!(wifi_pkg->package.elements[1].integer.value);
+	n_profiles = wifi_pkg->package.elements[2].integer.value;
+
+	/* in case of BIOS bug */
+	if (n_profiles <= 0) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	for (i = 0; i < n_profiles; i++) {
+		/* the tables start at element 3 */
+		static int pos = 3;
+
+		/* The EWRD profiles officially go from 2 to 4, but we
+		 * save them in sar_profiles[1-3] (because we don't
+		 * have profile 0).  So in the array we start from 1.
+		 */
+		ret = iwl_mvm_sar_set_profile(mvm,
+					      &wifi_pkg->package.elements[pos],
+					      &mvm->sar_profiles[i + 1],
+					      enabled);
+		if (ret < 0)
+			break;
+
+		/* go to the next table */
+		pos += IWL_MVM_SAR_TABLE_SIZE;
+	}
+
+out_free:
+	kfree(ewrd.pointer);
 	return ret;
 }
-#else /* CONFIG_ACPI */
-static int iwl_mvm_sar_get_table(struct iwl_mvm *mvm,
-				 struct iwl_mvm_sar_table *sar_table)
+
+static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm,
+				      struct iwl_mvm_geo_table *geo_table)
 {
-	return -ENOENT;
+	union acpi_object *wifi_pkg;
+	acpi_handle root_handle;
+	acpi_handle handle;
+	struct acpi_buffer wgds = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_status status;
+	int i, ret;
+
+	root_handle = ACPI_HANDLE(mvm->dev);
+	if (!root_handle) {
+		IWL_DEBUG_RADIO(mvm,
+				"Could not retrieve root port ACPI handle\n");
+		return -ENOENT;
+	}
+
+	/* Get the method's handle */
+	status = acpi_get_handle(root_handle, (acpi_string)ACPI_WGDS_METHOD,
+				 &handle);
+	if (ACPI_FAILURE(status)) {
+		IWL_DEBUG_RADIO(mvm, "WGDS method not found\n");
+		return -ENOENT;
+	}
+
+	/* Call WGDS with no arguments */
+	status = acpi_evaluate_object(handle, NULL, NULL, &wgds);
+	if (ACPI_FAILURE(status)) {
+		IWL_DEBUG_RADIO(mvm, "WGDS invocation failed (0x%x)\n", status);
+		return -ENOENT;
+	}
+
+	wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, wgds.pointer,
+					     ACPI_WGDS_WIFI_DATA_SIZE);
+	if (IS_ERR(wifi_pkg)) {
+		ret = PTR_ERR(wifi_pkg);
+		goto out_free;
+	}
+
+	for (i = 0; i < ACPI_WGDS_WIFI_DATA_SIZE; i++) {
+		union acpi_object *entry;
+
+		entry = &wifi_pkg->package.elements[i + 1];
+		if ((entry->type != ACPI_TYPE_INTEGER) ||
+		    (entry->integer.value > U8_MAX))
+			return -EINVAL;
+
+		geo_table->values[i] = entry->integer.value;
+	}
+	ret = 0;
+out_free:
+	kfree(wgds.pointer);
+	return ret;
 }
-#endif /* CONFIG_ACPI */
 
-static int iwl_mvm_sar_init(struct iwl_mvm *mvm)
+int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 {
-	struct iwl_mvm_sar_table sar_table;
 	struct iwl_dev_tx_power_cmd cmd = {
 		.v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
 	};
-	int ret, i, j, idx;
+	int i, j, idx;
+	int profs[IWL_NUM_CHAIN_LIMITS] = { prof_a, prof_b };
 	int len = sizeof(cmd);
 
+	BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS < 2);
+	BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS * IWL_NUM_SUB_BANDS !=
+		     IWL_MVM_SAR_TABLE_SIZE);
+
 	if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TX_POWER_ACK))
 		len = sizeof(cmd.v3);
 
-	ret = iwl_mvm_sar_get_table(mvm, &sar_table);
+	for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) {
+		struct iwl_mvm_sar_profile *prof;
+
+		/* don't allow SAR to be disabled (profile 0 means disable) */
+		if (profs[i] == 0)
+			return -EPERM;
+
+		/* we are off by one, so allow up to IWL_MVM_SAR_PROFILE_NUM */
+		if (profs[i] > IWL_MVM_SAR_PROFILE_NUM)
+			return -EINVAL;
+
+		/* profiles go from 1 to 4, so decrement to access the array */
+		prof = &mvm->sar_profiles[profs[i] - 1];
+
+		/* if the profile is disabled, do nothing */
+		if (!prof->enabled) {
+			IWL_DEBUG_RADIO(mvm, "SAR profile %d is disabled.\n",
+					profs[i]);
+			/* if one of the profiles is disabled, we fail all */
+			return -ENOENT;
+		}
+
+		IWL_DEBUG_RADIO(mvm, "  Chain[%d]:\n", i);
+		for (j = 0; j < IWL_NUM_SUB_BANDS; j++) {
+			idx = (i * IWL_NUM_SUB_BANDS) + j;
+			cmd.v3.per_chain_restriction[i][j] =
+				cpu_to_le16(prof->table[idx]);
+			IWL_DEBUG_RADIO(mvm, "    Band[%d] = %d * .125dBm\n",
+					j, prof->table[idx]);
+		}
+	}
+
+	IWL_DEBUG_RADIO(mvm, "Sending REDUCE_TX_POWER_CMD per chain\n");
+
+	return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd);
+}
+
+static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
+{
+	struct iwl_mvm_geo_table geo_table;
+	struct iwl_geo_tx_power_profiles_cmd cmd = {
+		.ops = cpu_to_le32(IWL_PER_CHAIN_OFFSET_SET_TABLES),
+	};
+	int ret, i, j, idx;
+	u16 cmd_wide_id =  WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT);
+
+	ret = iwl_mvm_sar_get_wgds_table(mvm, &geo_table);
 	if (ret < 0) {
 		IWL_DEBUG_RADIO(mvm,
-				"SAR BIOS table invalid or unavailable. (%d)\n",
+				"Geo SAR BIOS table invalid or unavailable. (%d)\n",
 				ret);
 		/* we don't fail if the table is not available */
 		return 0;
 	}
 
-	if (!sar_table.enabled)
-		return 0;
+	IWL_DEBUG_RADIO(mvm, "Sending GEO_TX_POWER_LIMIT\n");
 
-	IWL_DEBUG_RADIO(mvm, "Sending REDUCE_TX_POWER_CMD per chain\n");
+	BUILD_BUG_ON(IWL_NUM_GEO_PROFILES * ACPI_WGDS_NUM_BANDS *
+		     ACPI_WGDS_TABLE_SIZE !=  ACPI_WGDS_WIFI_DATA_SIZE);
 
-	BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS * IWL_NUM_SUB_BANDS !=
-		     ACPI_WRDS_TABLE_SIZE);
+	for (i = 0; i < IWL_NUM_GEO_PROFILES; i++) {
+		struct iwl_per_chain_offset *chain =
+			(struct iwl_per_chain_offset *)&cmd.table[i];
 
-	for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) {
-		IWL_DEBUG_RADIO(mvm, "  Chain[%d]:\n", i);
-		for (j = 0; j < IWL_NUM_SUB_BANDS; j++) {
-			idx = (i * IWL_NUM_SUB_BANDS) + j;
-			cmd.v3.per_chain_restriction[i][j] =
-				cpu_to_le16(sar_table.values[idx]);
-			IWL_DEBUG_RADIO(mvm, "    Band[%d] = %d * .125dBm\n",
-					j, sar_table.values[idx]);
+		for (j = 0; j < ACPI_WGDS_NUM_BANDS; j++) {
+			u8 *value;
+
+			idx = i * ACPI_WGDS_NUM_BANDS * ACPI_WGDS_TABLE_SIZE +
+				j * ACPI_WGDS_TABLE_SIZE;
+			value = &geo_table.values[idx];
+			chain[j].max_tx_power = cpu_to_le16(value[0]);
+			chain[j].chain_a = value[1];
+			chain[j].chain_b = value[2];
+			IWL_DEBUG_RADIO(mvm,
+					"SAR geographic profile[%d] Band[%d]: chain A = %d chain B = %d max_tx_power = %d\n",
+					i, j, value[1], value[2], value[0]);
 		}
 	}
+	return iwl_mvm_send_cmd_pdu(mvm, cmd_wide_id, 0, sizeof(cmd), &cmd);
+}
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd);
-	if (ret)
-		IWL_ERR(mvm, "failed to set per-chain TX power: %d\n", ret);
+#else /* CONFIG_ACPI */
+static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm)
+{
+	return -ENOENT;
+}
+
+static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm)
+{
+	return -ENOENT;
+}
+
+static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
+{
+	return 0;
+}
+#endif /* CONFIG_ACPI */
+
+static int iwl_mvm_sar_init(struct iwl_mvm *mvm)
+{
+	int ret;
+
+	ret = iwl_mvm_sar_get_wrds_table(mvm);
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(mvm,
+				"WRDS SAR BIOS table invalid or unavailable. (%d)\n",
+				ret);
+		/* if not available, don't fail and don't bother with EWRD */
+		return 0;
+	}
+
+	ret = iwl_mvm_sar_get_ewrd_table(mvm);
+	/* if EWRD is not available, we can still use WRDS, so don't fail */
+	if (ret < 0)
+		IWL_DEBUG_RADIO(mvm,
+				"EWRD SAR BIOS table invalid or unavailable. (%d)\n",
+				ret);
+
+	/* choose profile 1 (WRDS) as default for both chains */
+	ret = iwl_mvm_sar_select_profile(mvm, 1, 1);
+
+	/* if we don't have profile 0 from BIOS, just skip it */
+	if (ret == -ENOENT)
+		return 0;
 
 	return ret;
 }
@@ -1219,7 +1517,8 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	}
 
 	/* Init RSS configuration */
-	if (iwl_mvm_has_new_rx_api(mvm)) {
+	/* TODO - remove a000 disablement when we have RXQ config API */
+	if (iwl_mvm_has_new_rx_api(mvm) && !iwl_mvm_has_new_tx_api(mvm)) {
 		ret = iwl_send_rss_cfg_cmd(mvm);
 		if (ret) {
 			IWL_ERR(mvm, "Failed to configure RSS queues: %d\n",
@@ -1229,10 +1528,10 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	}
 
 	/* init the fw <-> mac80211 STA mapping */
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++)
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++)
 		RCU_INIT_POINTER(mvm->fw_id_to_mac_id[i], NULL);
 
-	mvm->tdls_cs.peer.sta_id = IWL_MVM_STATION_COUNT;
+	mvm->tdls_cs.peer.sta_id = IWL_MVM_INVALID_STA;
 
 	/* reset quota debouncing buffer - 0xff will yield invalid data */
 	memset(&mvm->last_quota_cmd, 0xff, sizeof(mvm->last_quota_cmd));
@@ -1313,10 +1612,6 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 			goto error;
 	}
 
-	if (iwl_mvm_is_csum_supported(mvm) &&
-	    mvm->cfg->features & NETIF_F_RXCSUM)
-		iwl_trans_write_prph(mvm->trans, RX_EN_CSUM, 0x3);
-
 	/* allow FW/transport low power modes if not during restart */
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
 		iwl_mvm_unref(mvm, IWL_MVM_REF_UCODE_DOWN);
@@ -1325,6 +1620,10 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	if (ret)
 		goto error;
 
+	ret = iwl_mvm_sar_geo_init(mvm);
+	if (ret)
+		goto error;
+
 	IWL_DEBUG_INFO(mvm, "RT uCode started.\n");
 	return 0;
  error:
@@ -1362,7 +1661,7 @@ int iwl_mvm_load_d3_fw(struct iwl_mvm *mvm)
 		goto error;
 
 	/* init the fw <-> mac80211 STA mapping */
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++)
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++)
 		RCU_INIT_POINTER(mvm->fw_id_to_mac_id[i], NULL);
 
 	/* Add auxiliary station for scanning */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 99132ea16ede..0f1831b41915 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -216,7 +216,8 @@ u32 iwl_mvm_mac_get_queues_mask(struct ieee80211_vif *vif)
 			qmask |= BIT(vif->hw_queue[ac]);
 	}
 
-	if (vif->type == NL80211_IFTYPE_AP)
+	if (vif->type == NL80211_IFTYPE_AP ||
+	    vif->type == NL80211_IFTYPE_ADHOC)
 		qmask |= BIT(vif->cab_queue);
 
 	return qmask;
@@ -466,13 +467,19 @@ static int iwl_mvm_mac_ctxt_allocate_resources(struct iwl_mvm *mvm,
 			queue = IWL_MVM_DQA_GCAST_QUEUE;
 		}
 
+		/*
+		 * For TVQM this will be overwritten later with the FW assigned
+		 * queue value (when queue is enabled).
+		 */
+		mvmvif->cab_queue = queue;
 		vif->cab_queue = queue;
 	} else {
 		vif->cab_queue = IEEE80211_INVAL_HW_QUEUE;
 	}
 
-	mvmvif->bcast_sta.sta_id = IWL_MVM_STATION_COUNT;
-	mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT;
+	mvmvif->bcast_sta.sta_id = IWL_MVM_INVALID_STA;
+	mvmvif->mcast_sta.sta_id = IWL_MVM_INVALID_STA;
+	mvmvif->ap_sta_id = IWL_MVM_INVALID_STA;
 
 	for (i = 0; i < NUM_IWL_MVM_SMPS_REQ; i++)
 		mvmvif->smps_requests[i] = IEEE80211_SMPS_AUTOMATIC;
@@ -900,7 +907,7 @@ static int iwl_mvm_mac_ctxt_cmd_listener(struct iwl_mvm *mvm,
 
 	/* Allocate sniffer station */
 	ret = iwl_mvm_allocate_int_sta(mvm, &mvm->snif_sta, tfd_queue_msk,
-				       vif->type);
+				       vif->type, IWL_STA_GENERAL_PURPOSE);
 	if (ret)
 		return ret;
 
@@ -1221,7 +1228,9 @@ static void iwl_mvm_mac_ctxt_cmd_fill_ap(struct iwl_mvm *mvm,
 		cpu_to_le32(iwl_mvm_reciprocal(vif->bss_conf.beacon_int *
 					       vif->bss_conf.dtim_period));
 
-	ctxt_ap->mcast_qid = cpu_to_le32(vif->cab_queue);
+	if (!fw_has_api(&mvm->fw->ucode_capa,
+			IWL_UCODE_TLV_API_STA_TYPE))
+		ctxt_ap->mcast_qid = cpu_to_le32(vif->cab_queue);
 
 	/*
 	 * Only set the beacon time when the MAC is being added, when we
@@ -1441,6 +1450,7 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
 	struct iwl_mvm_tx_resp *beacon_notify_hdr;
 	struct ieee80211_vif *csa_vif;
 	struct ieee80211_vif *tx_blocked_vif;
+	struct agg_tx_status *agg_status;
 	u16 status;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -1448,7 +1458,8 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
 	beacon_notify_hdr = &beacon->beacon_notify_hdr;
 	mvm->ap_last_beacon_gp2 = le32_to_cpu(beacon->gp2);
 
-	status = le16_to_cpu(beacon_notify_hdr->status.status) & TX_STATUS_MSK;
+	agg_status = iwl_mvm_get_agg_status(mvm, beacon_notify_hdr);
+	status = le16_to_cpu(agg_status->status) & TX_STATUS_MSK;
 	IWL_DEBUG_RX(mvm,
 		     "beacon status %#x retries:%d tsf:0x%16llX gp2:0x%X rate:%d\n",
 		     status, beacon_notify_hdr->failure_frame,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index d37b1695c64e..a67aa1f5a51c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -6,8 +6,8 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -33,7 +33,8 @@
  * BSD LICENSE
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -619,7 +620,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	else
 		hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
-	hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
+	hw->wiphy->max_sched_scan_reqs = 1;
 	hw->wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX;
 	hw->wiphy->max_match_sets = IWL_SCAN_MAX_PROFILES;
 	/* we create the 802.11 header and zero length SSID IE. */
@@ -766,7 +767,7 @@ static bool iwl_mvm_defer_tx(struct iwl_mvm *mvm,
 		goto out;
 
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
-	if (mvmsta->sta_id == IWL_MVM_STATION_COUNT ||
+	if (mvmsta->sta_id == IWL_MVM_INVALID_STA ||
 	    mvmsta->sta_id != mvm->d0i3_ap_sta_id)
 		goto out;
 
@@ -1010,7 +1011,7 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
 	mvmvif->uploaded = false;
-	mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT;
+	mvmvif->ap_sta_id = IWL_MVM_INVALID_STA;
 
 	spin_lock_bh(&mvm->time_event_lock);
 	iwl_mvm_te_clear_data(mvm, &mvmvif->time_event_data);
@@ -1053,7 +1054,7 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm)
 	ieee80211_iterate_interfaces(mvm->hw, 0, iwl_mvm_cleanup_iterator, mvm);
 
 	mvm->p2p_device_vif = NULL;
-	mvm->d0i3_ap_sta_id = IWL_MVM_STATION_COUNT;
+	mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
 
 	iwl_mvm_reset_phy_ctxts(mvm);
 	memset(mvm->fw_key_table, 0, sizeof(mvm->fw_key_table));
@@ -1351,6 +1352,18 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 			goto out_release;
 		}
 
+		if (iwl_mvm_is_dqa_supported(mvm)) {
+			/*
+			 * Only queue for this station is the mcast queue,
+			 * which shouldn't be in TFD mask anyway
+			 */
+			ret = iwl_mvm_allocate_int_sta(mvm, &mvmvif->mcast_sta,
+						       0, vif->type,
+						       IWL_STA_MULTICAST);
+			if (ret)
+				goto out_release;
+		}
+
 		iwl_mvm_vif_dbgfs_register(mvm, vif);
 		goto out_unlock;
 	}
@@ -1465,7 +1478,7 @@ static void iwl_mvm_prepare_mac_removal(struct iwl_mvm *mvm,
 		 * already marked as draining, so to complete the draining, we
 		 * just need to wait until the transport is empty.
 		 */
-		iwl_trans_wait_tx_queue_empty(mvm->trans, tfd_msk);
+		iwl_trans_wait_tx_queues_empty(mvm->trans, tfd_msk);
 	}
 
 	if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
@@ -1516,6 +1529,7 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw,
 			mvm->noa_duration = 0;
 		}
 #endif
+		iwl_mvm_dealloc_int_sta(mvm, &mvmvif->mcast_sta);
 		iwl_mvm_dealloc_bcast_sta(mvm, vif);
 		goto out_release;
 	}
@@ -1952,7 +1966,7 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 						    IWL_MVM_SMPS_REQ_PROT,
 						    IEEE80211_SMPS_DYNAMIC);
 			}
-		} else if (mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
+		} else if (mvmvif->ap_sta_id != IWL_MVM_INVALID_STA) {
 			/*
 			 * If update fails - SF might be running in associated
 			 * mode while disassociated - which is forbidden.
@@ -1966,8 +1980,8 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 				IWL_ERR(mvm, "failed to remove AP station\n");
 
 			if (mvm->d0i3_ap_sta_id == mvmvif->ap_sta_id)
-				mvm->d0i3_ap_sta_id = IWL_MVM_STATION_COUNT;
-			mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT;
+				mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
+			mvmvif->ap_sta_id = IWL_MVM_INVALID_STA;
 			/* remove quota for this interface */
 			ret = iwl_mvm_update_quotas(mvm, false, NULL);
 			if (ret)
@@ -2098,11 +2112,15 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	if (ret)
 		goto out_remove;
 
+	ret = iwl_mvm_add_mcast_sta(mvm, vif);
+	if (ret)
+		goto out_unbind;
+
 	/* Send the bcast station. At this stage the TBTT and DTIM time events
 	 * are added and applied to the scheduler */
 	ret = iwl_mvm_send_add_bcast_sta(mvm, vif);
 	if (ret)
-		goto out_unbind;
+		goto out_rm_mcast;
 
 	/* must be set before quota calculations */
 	mvmvif->ap_ibss_active = true;
@@ -2132,6 +2150,8 @@ out_quota_failed:
 	iwl_mvm_power_update_mac(mvm);
 	mvmvif->ap_ibss_active = false;
 	iwl_mvm_send_rm_bcast_sta(mvm, vif);
+out_rm_mcast:
+	iwl_mvm_rm_mcast_sta(mvm, vif);
 out_unbind:
 	iwl_mvm_binding_remove_vif(mvm, vif);
 out_remove:
@@ -2177,7 +2197,20 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif, false, NULL);
 
 	iwl_mvm_update_quotas(mvm, false, NULL);
+
+	/*
+	 * This is not very nice, but the simplest:
+	 * For older FWs removing the mcast sta before the bcast station may
+	 * cause assert 0x2b00.
+	 * This is fixed in later FW (which will stop beaconing when removing
+	 * bcast station).
+	 * So make the order of removal depend on the TLV
+	 */
+	if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE))
+		iwl_mvm_rm_mcast_sta(mvm, vif);
 	iwl_mvm_send_rm_bcast_sta(mvm, vif);
+	if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE))
+		iwl_mvm_rm_mcast_sta(mvm, vif);
 	iwl_mvm_binding_remove_vif(mvm, vif);
 
 	iwl_mvm_power_update_mac(mvm);
@@ -2319,7 +2352,7 @@ iwl_mvm_mac_release_buffered_frames(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	/* Called when we need to transmit (a) frame(s) from agg queue */
+	/* Called when we need to transmit (a) frame(s) from agg or dqa queue */
 
 	iwl_mvm_sta_modify_sleep_tx_count(mvm, sta, reason, num_frames,
 					  tids, more_data, true);
@@ -2338,10 +2371,14 @@ static void __iwl_mvm_mac_sta_notify(struct ieee80211_hw *hw,
 	for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
 		struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid];
 
-		if (tid_data->state != IWL_AGG_ON &&
+		if (!iwl_mvm_is_dqa_supported(mvm) &&
+		    tid_data->state != IWL_AGG_ON &&
 		    tid_data->state != IWL_EMPTYING_HW_QUEUE_DELBA)
 			continue;
 
+		if (tid_data->txq_id == IWL_MVM_INVALID_QUEUE)
+			continue;
+
 		__set_bit(tid_data->txq_id, &txqs);
 
 		if (iwl_mvm_tid_queued(tid_data) == 0)
@@ -2367,7 +2404,7 @@ static void __iwl_mvm_mac_sta_notify(struct ieee80211_hw *hw,
 		 */
 		break;
 	case STA_NOTIFY_AWAKE:
-		if (WARN_ON(mvmsta->sta_id == IWL_MVM_STATION_COUNT))
+		if (WARN_ON(mvmsta->sta_id == IWL_MVM_INVALID_STA))
 			break;
 
 		if (txqs)
@@ -2400,7 +2437,7 @@ void iwl_mvm_sta_pm_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 		return;
 
 	rcu_read_lock();
-	sta = mvm->fw_id_to_mac_id[notif->sta_id];
+	sta = rcu_dereference(mvm->fw_id_to_mac_id[notif->sta_id]);
 	if (WARN_ON(IS_ERR_OR_NULL(sta))) {
 		rcu_read_unlock();
 		return;
@@ -3710,7 +3747,8 @@ static int __iwl_mvm_mac_testmode_cmd(struct iwl_mvm *mvm,
 	int err;
 	u32 noa_duration;
 
-	err = nla_parse(tb, IWL_MVM_TM_ATTR_MAX, data, len, iwl_mvm_tm_policy);
+	err = nla_parse(tb, IWL_MVM_TM_ATTR_MAX, data, len, iwl_mvm_tm_policy,
+			NULL);
 	if (err)
 		return err;
 
@@ -3937,7 +3975,7 @@ static void iwl_mvm_mac_flush(struct ieee80211_hw *hw,
 	mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
 	/* flush the AP-station and all TDLS peers */
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i],
 						lockdep_is_held(&mvm->mutex));
 		if (IS_ERR_OR_NULL(sta))
@@ -3963,7 +4001,7 @@ static void iwl_mvm_mac_flush(struct ieee80211_hw *hw,
 		/* this can take a while, and we may need/want other operations
 		 * to succeed while doing this, so do it without the mutex held
 		 */
-		iwl_trans_wait_tx_queue_empty(mvm->trans, msk);
+		iwl_trans_wait_tx_queues_empty(mvm->trans, msk);
 	}
 }
 
@@ -4194,7 +4232,8 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvm->mutex);
 
-	if (!iwl_mvm_has_new_rx_api(mvm))
+	/* TODO - remove a000 disablement when we have RXQ config API */
+	if (!iwl_mvm_has_new_rx_api(mvm) || iwl_mvm_has_new_tx_api(mvm))
 		return;
 
 	notif->cookie = mvm->queue_sync_cookie;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 73a216524af2..4e74a6b90e70 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -380,6 +380,8 @@ struct iwl_mvm_vif {
 	bool associated;
 	u8 ap_assoc_sta_count;
 
+	u16 cab_queue;
+
 	bool uploaded;
 	bool ap_ibss_active;
 	bool pm_enabled;
@@ -407,6 +409,7 @@ struct iwl_mvm_vif {
 	struct iwl_mvm_time_event_data hs_time_event_data;
 
 	struct iwl_mvm_int_sta bcast_sta;
+	struct iwl_mvm_int_sta mcast_sta;
 
 	/*
 	 * Assigned while mac80211 has the interface in a channel context,
@@ -603,10 +606,15 @@ enum iwl_mvm_tdls_cs_state {
 	IWL_MVM_TDLS_SW_ACTIVE,
 };
 
+#define MAX_NUM_LMAC 2
 struct iwl_mvm_shared_mem_cfg {
+	int num_lmacs;
 	int num_txfifo_entries;
-	u32 txfifo_size[TX_FIFO_MAX_NUM];
-	u32 rxfifo_size[RX_FIFO_MAX_NUM];
+	struct {
+		u32 txfifo_size[TX_FIFO_MAX_NUM];
+		u32 rxfifo1_size;
+	} lmac[MAX_NUM_LMAC];
+	u32 rxfifo2_size;
 	u32 internal_txfifo_addr;
 	u32 internal_txfifo_size[TX_FIFO_INTERNAL_MAX_NUM];
 };
@@ -625,6 +633,7 @@ struct iwl_mvm_shared_mem_cfg {
  * @reorder_timer: timer for frames are in the reorder buffer. For AMSDU
  *	it is the time of last received sub-frame
  * @removed: prevent timer re-arming
+ * @valid: reordering is valid for this queue
  * @lock: protect reorder buffer internal state
  * @mvm: mvm pointer, needed for frame timer context
  */
@@ -640,6 +649,7 @@ struct iwl_mvm_reorder_buffer {
 	unsigned long reorder_time[IEEE80211_MAX_AMPDU_BUF];
 	struct timer_list reorder_timer;
 	bool removed;
+	bool valid;
 	spinlock_t lock;
 	struct iwl_mvm *mvm;
 } ____cacheline_aligned_in_smp;
@@ -707,8 +717,25 @@ enum iwl_mvm_queue_status {
 };
 
 #define IWL_MVM_DQA_QUEUE_TIMEOUT	(5 * HZ)
+#define IWL_MVM_INVALID_QUEUE		0xFFFF
+
 #define IWL_MVM_NUM_CIPHERS             10
 
+#ifdef CONFIG_ACPI
+#define IWL_MVM_SAR_TABLE_SIZE		10
+#define IWL_MVM_SAR_PROFILE_NUM		4
+#define IWL_MVM_GEO_TABLE_SIZE		18
+
+struct iwl_mvm_sar_profile {
+	bool enabled;
+	u8 table[IWL_MVM_SAR_TABLE_SIZE];
+};
+
+struct iwl_mvm_geo_table {
+	u8 values[IWL_MVM_GEO_TABLE_SIZE];
+};
+#endif
+
 struct iwl_mvm {
 	/* for logger access */
 	struct device *dev;
@@ -761,9 +788,9 @@ struct iwl_mvm {
 		u64 on_time_scan;
 	} radio_stats, accu_radio_stats;
 
+	u8 hw_queue_to_mac80211[IWL_MAX_TVQM_QUEUES];
+
 	struct {
-		/* Map to HW queue */
-		u32 hw_queue_to_mac80211;
 		u8 hw_queue_refcount;
 		u8 ra_sta_id; /* The RA this queue is mapped to, if exists */
 		bool reserved; /* Is this the TXQ reserved for a STA */
@@ -975,7 +1002,10 @@ struct iwl_mvm {
 #endif
 
 	/* Tx queues */
-	u8 aux_queue;
+	u16 aux_queue;
+	u16 probe_queue;
+	u16 p2p_dev_queue;
+
 	u8 first_agg_queue;
 	u8 last_agg_queue;
 
@@ -1018,7 +1048,7 @@ struct iwl_mvm {
 		} peer;
 	} tdls_cs;
 
-	struct iwl_mvm_shared_mem_cfg shared_mem_cfg;
+	struct iwl_mvm_shared_mem_cfg smem_cfg;
 
 	u32 ciphers[IWL_MVM_NUM_CIPHERS];
 	struct ieee80211_cipher_scheme cs[IWL_UCODE_MAX_CS];
@@ -1035,6 +1065,9 @@ struct iwl_mvm {
 	bool drop_bcn_ap_mode;
 
 	struct delayed_work cs_tx_unblock_dwork;
+#ifdef CONFIG_ACPI
+	struct iwl_mvm_sar_profile sar_profiles[IWL_MVM_SAR_PROFILE_NUM];
+#endif
 };
 
 /* Extract MVM priv from op_mode and _hw */
@@ -1222,13 +1255,25 @@ static inline bool iwl_mvm_is_cdb_supported(struct iwl_mvm *mvm)
 {
 	/*
 	 * TODO:
-	 * The issue of how to determine CDB support is still not well defined.
-	 * It may be that it will be for all next HW devices and it may be per
-	 * FW compilation and it may also differ between different devices.
-	 * For now take a ride on the new TX API and get back to it when
-	 * it is well defined.
+	 * The issue of how to determine CDB APIs and usage is still not fully
+	 * defined.
+	 * There is a compilation for CDB and non-CDB FW, but there may
+	 * be also runtime check.
+	 * For now there is a TLV for checking compilation mode, but a
+	 * runtime check will also have to be here - once defined.
 	 */
-	return iwl_mvm_has_new_tx_api(mvm);
+	return fw_has_capa(&mvm->fw->ucode_capa,
+			   IWL_UCODE_TLV_CAPA_CDB_SUPPORT);
+}
+
+static inline struct agg_tx_status*
+iwl_mvm_get_agg_status(struct iwl_mvm *mvm,
+		       struct iwl_mvm_tx_resp *tx_resp)
+{
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return &tx_resp->v6.status;
+	else
+		return &tx_resp->v3.status;
 }
 
 static inline bool iwl_mvm_is_tt_in_fw(struct iwl_mvm *mvm)
@@ -1271,7 +1316,6 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm);
  ******************/
 /* uCode */
 int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm);
-int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm);
 
 /* Utils */
 int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags,
@@ -1389,6 +1433,8 @@ int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask,
 void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 			    int queue);
 void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb);
+void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm,
+				   struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_rx_ant_coupling_notif(struct iwl_mvm *mvm,
 				   struct iwl_rx_cmd_buffer *rxb);
@@ -1668,6 +1714,9 @@ static inline bool iwl_mvm_vif_low_latency(struct iwl_mvm_vif *mvmvif)
 void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 			u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg,
 			unsigned int wdg_timeout);
+int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, int mac80211_queue,
+			    u8 sta_id, u8 tid, unsigned int timeout);
+
 /*
  * Disable a TXQ.
  * Note that in non-DQA mode the %mac80211_queue and %tid params are ignored.
@@ -1701,7 +1750,8 @@ void iwl_mvm_enable_ac_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 
 static inline void iwl_mvm_stop_device(struct iwl_mvm *mvm)
 {
-	iwl_free_fw_paging(mvm);
+	if (!iwl_mvm_has_new_tx_api(mvm))
+		iwl_free_fw_paging(mvm);
 	mvm->ucode_loaded = false;
 	iwl_trans_stop_device(mvm->trans);
 }
@@ -1781,6 +1831,7 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 				     u32 size);
 void iwl_mvm_reorder_timer_expired(unsigned long data);
 struct ieee80211_vif *iwl_mvm_get_bss_vif(struct iwl_mvm *mvm);
+bool iwl_mvm_is_vif_assoc(struct iwl_mvm *mvm);
 
 void iwl_mvm_inactivity_check(struct iwl_mvm *mvm);
 
@@ -1797,4 +1848,14 @@ int iwl_mvm_send_lqm_cmd(struct ieee80211_vif *vif,
 			 u32 duration, u32 timeout);
 bool iwl_mvm_lqm_active(struct iwl_mvm *mvm);
 
+#ifdef CONFIG_ACPI
+int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b);
+#else
+static inline
+int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
+{
+	return -ENOENT;
+}
+#endif /* CONFIG_ACPI */
+
 #endif /* __IWL_MVM_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index eade099b6dbf..283c41df622c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -817,6 +817,11 @@ void iwl_mvm_rx_chub_update_mcc(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (iwl_mvm_is_vif_assoc(mvm) && notif->source_id == MCC_SOURCE_WIFI) {
+		IWL_DEBUG_LAR(mvm, "Ignore mcc update while associated\n");
+		return;
+	}
+
 	if (WARN_ON_ONCE(!iwl_mvm_is_lar_supported(mvm)))
 		return;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 4cd72d4cdc47..9ffff6ed8133 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -302,6 +302,8 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 		   RX_HANDLER_SYNC),
 	RX_HANDLER(TOF_NOTIFICATION, iwl_mvm_tof_resp_handler,
 		   RX_HANDLER_ASYNC_LOCKED),
+	RX_HANDLER_GRP(DEBUG_GROUP, MFU_ASSERT_DUMP_NTF,
+		       iwl_mvm_mfu_assert_dump_notif, RX_HANDLER_SYNC),
 	RX_HANDLER_GRP(PROT_OFFLOAD_GROUP, STORED_BEACON_NTF,
 		       iwl_mvm_rx_stored_beacon_notif, RX_HANDLER_SYNC),
 	RX_HANDLER_GRP(DATA_PATH_GROUP, MU_GROUP_MGMT_NOTIF,
@@ -426,6 +428,7 @@ static const struct iwl_hcmd_names iwl_mvm_legacy_names[] = {
  */
 static const struct iwl_hcmd_names iwl_mvm_system_names[] = {
 	HCMD_NAME(SHARED_MEM_CFG_CMD),
+	HCMD_NAME(INIT_EXTENDED_CFG_CMD),
 };
 
 /* Please keep this array *SORTED* by hex value.
@@ -444,6 +447,7 @@ static const struct iwl_hcmd_names iwl_mvm_phy_names[] = {
 	HCMD_NAME(CMD_DTS_MEASUREMENT_TRIGGER_WIDE),
 	HCMD_NAME(CTDP_CONFIG_CMD),
 	HCMD_NAME(TEMP_REPORTING_THRESHOLDS_CMD),
+	HCMD_NAME(GEO_TX_POWER_LIMIT),
 	HCMD_NAME(CT_KILL_NOTIFICATION),
 	HCMD_NAME(DTS_MEASUREMENT_NOTIF_WIDE),
 };
@@ -452,6 +456,7 @@ static const struct iwl_hcmd_names iwl_mvm_phy_names[] = {
  * Access is done through binary search
  */
 static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = {
+	HCMD_NAME(DQA_ENABLE_CMD),
 	HCMD_NAME(UPDATE_MU_GROUPS_CMD),
 	HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD),
 	HCMD_NAME(STA_PM_NOTIF),
@@ -462,6 +467,13 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = {
 /* Please keep this array *SORTED* by hex value.
  * Access is done through binary search
  */
+static const struct iwl_hcmd_names iwl_mvm_debug_names[] = {
+	HCMD_NAME(MFU_ASSERT_DUMP_NTF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
 static const struct iwl_hcmd_names iwl_mvm_prot_offload_names[] = {
 	HCMD_NAME(STORED_BEACON_NTF),
 };
@@ -602,6 +614,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		}
 	} else {
 		mvm->aux_queue = IWL_MVM_DQA_AUX_QUEUE;
+		mvm->probe_queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
+		mvm->p2p_dev_queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
 		mvm->first_agg_queue = IWL_MVM_DQA_MIN_DATA_QUEUE;
 		mvm->last_agg_queue = IWL_MVM_DQA_MAX_DATA_QUEUE;
 	}
@@ -732,10 +746,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	mutex_lock(&mvm->mutex);
 	iwl_mvm_ref(mvm, IWL_MVM_REF_INIT_UCODE);
-	if (iwl_mvm_has_new_tx_api(mvm))
-		err = iwl_run_unified_mvm_ucode(mvm, true);
-	else
-		err = iwl_run_init_mvm_ucode(mvm, true);
+	err = iwl_run_init_mvm_ucode(mvm, true);
 	if (!err || !iwlmvm_mod_params.init_dbg)
 		iwl_mvm_stop_device(mvm);
 	iwl_mvm_unref(mvm, IWL_MVM_REF_INIT_UCODE);
@@ -1033,7 +1044,7 @@ static void iwl_mvm_stop_sw_queue(struct iwl_op_mode *op_mode, int hw_queue)
 	unsigned long mq;
 
 	spin_lock_bh(&mvm->queue_info_lock);
-	mq = mvm->queue_info[hw_queue].hw_queue_to_mac80211;
+	mq = mvm->hw_queue_to_mac80211[hw_queue];
 	spin_unlock_bh(&mvm->queue_info_lock);
 
 	iwl_mvm_stop_mac_queues(mvm, mq);
@@ -1063,7 +1074,7 @@ static void iwl_mvm_wake_sw_queue(struct iwl_op_mode *op_mode, int hw_queue)
 	unsigned long mq;
 
 	spin_lock_bh(&mvm->queue_info_lock);
-	mq = mvm->queue_info[hw_queue].hw_queue_to_mac80211;
+	mq = mvm->hw_queue_to_mac80211[hw_queue];
 	spin_unlock_bh(&mvm->queue_info_lock);
 
 	iwl_mvm_start_mac_queues(mvm, mq);
@@ -1256,7 +1267,7 @@ static bool iwl_mvm_disallow_offloading(struct iwl_mvm *mvm,
 	u8 tid;
 
 	if (WARN_ON(vif->type != NL80211_IFTYPE_STATION ||
-		    mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT))
+		    mvmvif->ap_sta_id == IWL_MVM_INVALID_STA))
 		return false;
 
 	mvmsta = iwl_mvm_sta_from_staid_rcu(mvm, mvmvif->ap_sta_id);
@@ -1344,7 +1355,7 @@ static void iwl_mvm_set_wowlan_data(struct iwl_mvm *mvm,
 	struct ieee80211_sta *ap_sta;
 	struct iwl_mvm_sta *mvm_ap_sta;
 
-	if (iter_data->ap_sta_id == IWL_MVM_STATION_COUNT)
+	if (iter_data->ap_sta_id == IWL_MVM_INVALID_STA)
 		return;
 
 	rcu_read_lock();
@@ -1414,7 +1425,7 @@ int iwl_mvm_enter_d0i3(struct iwl_op_mode *op_mode)
 		mvm->d0i3_offloading = !d0i3_iter_data.disable_offloading;
 	} else {
 		WARN_ON_ONCE(d0i3_iter_data.vif_count > 1);
-		mvm->d0i3_ap_sta_id = IWL_MVM_STATION_COUNT;
+		mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
 		mvm->d0i3_offloading = false;
 	}
 
@@ -1427,7 +1438,7 @@ int iwl_mvm_enter_d0i3(struct iwl_op_mode *op_mode)
 		return ret;
 
 	/* configure wowlan configuration only if needed */
-	if (mvm->d0i3_ap_sta_id != IWL_MVM_STATION_COUNT) {
+	if (mvm->d0i3_ap_sta_id != IWL_MVM_INVALID_STA) {
 		/* wake on beacons only if beacon storing isn't supported */
 		if (!fw_has_capa(&mvm->fw->ucode_capa,
 				 IWL_UCODE_TLV_CAPA_BEACON_STORING))
@@ -1504,7 +1515,7 @@ void iwl_mvm_d0i3_enable_tx(struct iwl_mvm *mvm, __le16 *qos_seq)
 
 	spin_lock_bh(&mvm->d0i3_tx_lock);
 
-	if (mvm->d0i3_ap_sta_id == IWL_MVM_STATION_COUNT)
+	if (mvm->d0i3_ap_sta_id == IWL_MVM_INVALID_STA)
 		goto out;
 
 	IWL_DEBUG_RPM(mvm, "re-enqueue packets\n");
@@ -1542,7 +1553,7 @@ out:
 	}
 	clear_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status);
 	wake_up(&mvm->d0i3_exit_waitq);
-	mvm->d0i3_ap_sta_id = IWL_MVM_STATION_COUNT;
+	mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
 	if (wake_queues)
 		ieee80211_wake_queues(mvm->hw);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
index 95138830b9f8..d59efe804356 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2017           Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -250,12 +251,30 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 			     struct cfg80211_chan_def *chandef,
 			     u8 chains_static, u8 chains_dynamic)
 {
+	enum iwl_phy_ctxt_action action = FW_CTXT_ACTION_MODIFY;
+
 	lockdep_assert_held(&mvm->mutex);
 
+	/* In CDB mode we cannot modify PHY context between bands so... */
+	if (iwl_mvm_has_new_tx_api(mvm) &&
+	    ctxt->channel->band != chandef->chan->band) {
+		int ret;
+
+		/* ... remove it here ...*/
+		ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
+					     chains_static, chains_dynamic,
+					     FW_CTXT_ACTION_REMOVE, 0);
+		if (ret)
+			return ret;
+
+		/* ... and proceed to add it again */
+		action = FW_CTXT_ACTION_ADD;
+	}
+
 	ctxt->channel = chandef->chan;
 	return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
 				      chains_static, chains_dynamic,
-				      FW_CTXT_ACTION_MODIFY, 0);
+				      action, 0);
 }
 
 void iwl_mvm_phy_ctxt_unref(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index ce907c58ebf6..7788eefcd2bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -826,7 +826,7 @@ static u32 ucode_rate_from_rs_rate(struct iwl_mvm *mvm,
 	if (is_siso(rate) && rate->stbc) {
 		/* To enable STBC we need to set both a flag and ANT_AB */
 		ucode_rate |= RATE_MCS_ANT_AB_MSK;
-		ucode_rate |= RATE_MCS_VHT_STBC_MSK;
+		ucode_rate |= RATE_MCS_STBC_MSK;
 	}
 
 	ucode_rate |= rate->bw;
@@ -873,7 +873,7 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 		rate->sgi = true;
 	if (ucode_rate & RATE_MCS_LDPC_MSK)
 		rate->ldpc = true;
-	if (ucode_rate & RATE_MCS_VHT_STBC_MSK)
+	if (ucode_rate & RATE_MCS_STBC_MSK)
 		rate->stbc = true;
 	if (ucode_rate & RATE_MCS_BF_MSK)
 		rate->bfer = true;
@@ -3641,13 +3641,12 @@ int rs_pretty_print_rate(char *buf, const u32 rate)
 		bw = "BAD BW";
 	}
 
-	return sprintf(buf, "%s | ANT: %s BW: %s MCS: %d NSS: %d %s%s%s%s%s\n",
+	return sprintf(buf, "%s | ANT: %s BW: %s MCS: %d NSS: %d %s%s%s%s\n",
 		       type, rs_pretty_ant(ant), bw, mcs, nss,
 		       (rate & RATE_MCS_SGI_MSK) ? "SGI " : "NGI ",
-		       (rate & RATE_MCS_HT_STBC_MSK) ? "STBC " : "",
+		       (rate & RATE_MCS_STBC_MSK) ? "STBC " : "",
 		       (rate & RATE_MCS_LDPC_MSK) ? "LDPC " : "",
-		       (rate & RATE_MCS_BF_MSK) ? "BF " : "",
-		       (rate & RATE_MCS_ZLF_MSK) ? "ZLF " : "");
+		       (rate & RATE_MCS_BF_MSK) ? "BF " : "");
 }
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 20473df79c94..fd1dd06c4f18 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -104,7 +104,20 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 					    u8 crypt_len,
 					    struct iwl_rx_cmd_buffer *rxb)
 {
-	unsigned int hdrlen, fraglen;
+	unsigned int hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	unsigned int fraglen;
+
+	/*
+	 * The 'hdrlen' (plus the 8 bytes for the SNAP and the crypt_len,
+	 * but those are all multiples of 4 long) all goes away, but we
+	 * want the *end* of it, which is going to be the start of the IP
+	 * header, to be aligned when it gets pulled in.
+	 * The beginning of the skb->data is aligned on at least a 4-byte
+	 * boundary after allocation. Everything here is aligned at least
+	 * on a 2-byte boundary so we can just take hdrlen & 3 and pad by
+	 * the result.
+	 */
+	skb_reserve(skb, hdrlen & 3);
 
 	/* If frame is small enough to fit in skb->head, pull it completely.
 	 * If not, only pull ieee80211_hdr (including crypto if present, and
@@ -118,8 +131,7 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 	 * If the latter changes (there are efforts in the standards group
 	 * to do so) we should revisit this and ieee80211_data_to_8023().
 	 */
-	hdrlen = (len <= skb_tailroom(skb)) ? len :
-					      sizeof(*hdr) + crypt_len + 8;
+	hdrlen = (len <= skb_tailroom(skb)) ? len : hdrlen + crypt_len + 8;
 
 	memcpy(skb_put(skb, hdrlen), hdr, hdrlen);
 	fraglen = len - hdrlen;
@@ -339,7 +351,7 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 		id >>= RX_MDPU_RES_STATUS_STA_ID_SHIFT;
 
-		if (!WARN_ON_ONCE(id >= IWL_MVM_STATION_COUNT)) {
+		if (!WARN_ON_ONCE(id >= ARRAY_SIZE(mvm->fw_id_to_mac_id))) {
 			sta = rcu_dereference(mvm->fw_id_to_mac_id[id]);
 			if (IS_ERR(sta))
 				sta = NULL;
@@ -398,7 +410,7 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 	/* set the preamble flag if appropriate */
 	if (phy_info->phy_flags & cpu_to_le16(RX_RES_PHY_FLAGS_SHORT_PREAMBLE))
-		rx_status->flag |= RX_FLAG_SHORTPRE;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if (phy_info->phy_flags & cpu_to_le16(RX_RES_PHY_FLAGS_AGG)) {
 		/*
@@ -415,42 +427,49 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 	case RATE_MCS_CHAN_WIDTH_20:
 		break;
 	case RATE_MCS_CHAN_WIDTH_40:
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 		break;
 	case RATE_MCS_CHAN_WIDTH_80:
-		rx_status->vht_flag |= RX_VHT_FLAG_80MHZ;
+		rx_status->bw = RATE_INFO_BW_80;
 		break;
 	case RATE_MCS_CHAN_WIDTH_160:
-		rx_status->vht_flag |= RX_VHT_FLAG_160MHZ;
+		rx_status->bw = RATE_INFO_BW_160;
 		break;
 	}
 	if (rate_n_flags & RATE_MCS_SGI_MSK)
-		rx_status->flag |= RX_FLAG_SHORT_GI;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	if (rate_n_flags & RATE_HT_MCS_GF_MSK)
-		rx_status->flag |= RX_FLAG_HT_GF;
+		rx_status->enc_flags |= RX_ENC_FLAG_HT_GF;
 	if (rate_n_flags & RATE_MCS_LDPC_MSK)
-		rx_status->flag |= RX_FLAG_LDPC;
+		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
 	if (rate_n_flags & RATE_MCS_HT_MSK) {
-		u8 stbc = (rate_n_flags & RATE_MCS_HT_STBC_MSK) >>
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
 				RATE_MCS_STBC_POS;
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 		rx_status->rate_idx = rate_n_flags & RATE_HT_MCS_INDEX_MSK;
-		rx_status->flag |= stbc << RX_FLAG_STBC_SHIFT;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 	} else if (rate_n_flags & RATE_MCS_VHT_MSK) {
-		u8 stbc = (rate_n_flags & RATE_MCS_VHT_STBC_MSK) >>
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
 				RATE_MCS_STBC_POS;
-		rx_status->vht_nss =
+		rx_status->nss =
 			((rate_n_flags & RATE_VHT_MCS_NSS_MSK) >>
 						RATE_VHT_MCS_NSS_POS) + 1;
 		rx_status->rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
-		rx_status->flag |= RX_FLAG_VHT;
-		rx_status->flag |= stbc << RX_FLAG_STBC_SHIFT;
+		rx_status->encoding = RX_ENC_VHT;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		if (rate_n_flags & RATE_MCS_BF_MSK)
-			rx_status->vht_flag |= RX_VHT_FLAG_BF;
+			rx_status->enc_flags |= RX_ENC_FLAG_BF;
 	} else {
-		rx_status->rate_idx =
-			iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
-							    rx_status->band);
+		int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
+							       rx_status->band);
+
+		if (WARN(rate < 0 || rate > 0xFF,
+			 "Invalid rate flags 0x%x, band %d,\n",
+			 rate_n_flags, rx_status->band)) {
+			kfree_skb(skb);
+			return;
+		}
+		rx_status->rate_idx = rate;
 	}
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -637,6 +656,9 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 		.mvm = mvm,
 	};
 	int expected_size;
+	int i;
+	u8 *energy;
+	__le32 *bytes, *air_time;
 
 	if (iwl_mvm_is_cdb_supported(mvm))
 		expected_size = sizeof(*stats);
@@ -645,8 +667,11 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 	else
 		expected_size = sizeof(struct iwl_notif_statistics_v10);
 
-	if (iwl_rx_packet_payload_len(pkt) != expected_size)
-		goto invalid;
+	if (iwl_rx_packet_payload_len(pkt) != expected_size) {
+		IWL_ERR(mvm, "received invalid statistics size (%d)!\n",
+			iwl_rx_packet_payload_len(pkt));
+		return;
+	}
 
 	data.mac_id = stats->rx.general.mac_id;
 	data.beacon_filter_average_energy =
@@ -662,38 +687,6 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 		le64_to_cpu(stats->general.common.on_time_scan);
 
 	data.general = &stats->general;
-	if (iwl_mvm_has_new_rx_api(mvm)) {
-		int i;
-		u8 *energy;
-		__le32 *bytes, *air_time;
-
-		if (!iwl_mvm_is_cdb_supported(mvm)) {
-			struct iwl_notif_statistics_v11 *v11 =
-				(void *)&pkt->data;
-
-			energy = (void *)&v11->load_stats.avg_energy;
-			bytes = (void *)&v11->load_stats.byte_count;
-			air_time = (void *)&v11->load_stats.air_time;
-		} else {
-			energy = (void *)&stats->load_stats.avg_energy;
-			bytes = (void *)&stats->load_stats.byte_count;
-			air_time = (void *)&stats->load_stats.air_time;
-		}
-
-		rcu_read_lock();
-		for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
-			struct iwl_mvm_sta *sta;
-
-			if (!energy[i])
-				continue;
-
-			sta = iwl_mvm_sta_from_staid_rcu(mvm, i);
-			if (!sta)
-				continue;
-			sta->avg_energy = energy[i];
-		}
-		rcu_read_unlock();
-	}
 
 	iwl_mvm_rx_stats_check_trigger(mvm, pkt);
 
@@ -701,10 +694,36 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 					    IEEE80211_IFACE_ITER_NORMAL,
 					    iwl_mvm_stat_iterator,
 					    &data);
-	return;
- invalid:
-	IWL_ERR(mvm, "received invalid statistics size (%d)!\n",
-		iwl_rx_packet_payload_len(pkt));
+
+	if (!iwl_mvm_has_new_rx_api(mvm))
+		return;
+
+	if (!iwl_mvm_is_cdb_supported(mvm)) {
+		struct iwl_notif_statistics_v11 *v11 =
+			(void *)&pkt->data;
+
+		energy = (void *)&v11->load_stats.avg_energy;
+		bytes = (void *)&v11->load_stats.byte_count;
+		air_time = (void *)&v11->load_stats.air_time;
+	} else {
+		energy = (void *)&stats->load_stats.avg_energy;
+		bytes = (void *)&stats->load_stats.byte_count;
+		air_time = (void *)&stats->load_stats.air_time;
+	}
+
+	rcu_read_lock();
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
+		struct iwl_mvm_sta *sta;
+
+		if (!energy[i])
+			continue;
+
+		sta = iwl_mvm_sta_from_staid_rcu(mvm, i);
+		if (!sta)
+			continue;
+		sta->avg_energy = energy[i];
+	}
+	rcu_read_unlock();
 }
 
 void iwl_mvm_rx_statistics(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index d79e9c2a2654..966cd7543629 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -29,7 +29,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -462,6 +462,7 @@ void iwl_mvm_reorder_timer_expired(unsigned long data)
 	int i;
 	u16 sn = 0, index = 0;
 	bool expired = false;
+	bool cont = false;
 
 	spin_lock(&buf->lock);
 
@@ -473,12 +474,21 @@ void iwl_mvm_reorder_timer_expired(unsigned long data)
 	for (i = 0; i < buf->buf_size ; i++) {
 		index = (buf->head_sn + i) % buf->buf_size;
 
-		if (skb_queue_empty(&buf->entries[index]))
+		if (skb_queue_empty(&buf->entries[index])) {
+			/*
+			 * If there is a hole and the next frame didn't expire
+			 * we want to break and not advance SN
+			 */
+			cont = false;
 			continue;
-		if (!time_after(jiffies, buf->reorder_time[index] +
-				RX_REORDER_BUF_TIMEOUT_MQ))
+		}
+		if (!cont && !time_after(jiffies, buf->reorder_time[index] +
+					 RX_REORDER_BUF_TIMEOUT_MQ))
 			break;
+
 		expired = true;
+		/* continue until next hole after this expired frames */
+		cont = true;
 		sn = ieee80211_sn_add(buf->head_sn, i + 1);
 	}
 
@@ -626,9 +636,13 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 		return false;
 
 	baid_data = rcu_dereference(mvm->baid_map[baid]);
-	if (WARN(!baid_data,
-		 "Received baid %d, but no data exists for this BAID\n", baid))
+	if (!baid_data) {
+		WARN(!(reorder & IWL_RX_MPDU_REORDER_BA_OLD_SN),
+		     "Received baid %d, but no data exists for this BAID\n",
+		     baid);
 		return false;
+	}
+
 	if (WARN(tid != baid_data->tid || mvm_sta->sta_id != baid_data->sta_id,
 		 "baid 0x%x is mapped to sta:%d tid:%d, but was received for sta:%d tid:%d\n",
 		 baid, baid_data->sta_id, baid_data->tid, mvm_sta->sta_id,
@@ -643,6 +657,14 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 
 	spin_lock_bh(&buffer->lock);
 
+	if (!buffer->valid) {
+		if (reorder & IWL_RX_MPDU_REORDER_BA_OLD_SN) {
+			spin_unlock_bh(&buffer->lock);
+			return false;
+		}
+		buffer->valid = true;
+	}
+
 	if (ieee80211_is_back_req(hdr->frame_control)) {
 		iwl_mvm_release_frames(mvm, sta, napi, buffer, nssn);
 		goto drop;
@@ -727,7 +749,8 @@ drop:
 	return true;
 }
 
-static void iwl_mvm_agg_rx_received(struct iwl_mvm *mvm, u8 baid)
+static void iwl_mvm_agg_rx_received(struct iwl_mvm *mvm,
+				    u32 reorder_data, u8 baid)
 {
 	unsigned long now = jiffies;
 	unsigned long timeout;
@@ -736,8 +759,10 @@ static void iwl_mvm_agg_rx_received(struct iwl_mvm *mvm, u8 baid)
 	rcu_read_lock();
 
 	data = rcu_dereference(mvm->baid_map[baid]);
-	if (WARN_ON(!data))
+	if (!data) {
+		WARN_ON(!(reorder_data & IWL_RX_MPDU_REORDER_BA_OLD_SN));
 		goto out;
+	}
 
 	if (!data->timeout)
 		goto out;
@@ -799,7 +824,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	}
 	/* set the preamble flag if appropriate */
 	if (phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE)
-		rx_status->flag |= RX_FLAG_SHORTPRE;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if (likely(!(phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
 		rx_status->mactime = le64_to_cpu(desc->tsf_on_air_rise);
@@ -831,7 +856,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	if (le16_to_cpu(desc->status) & IWL_RX_MPDU_STATUS_SRC_STA_FOUND) {
 		u8 id = desc->sta_id_flags & IWL_RX_MPDU_SIF_STA_ID_MASK;
 
-		if (!WARN_ON_ONCE(id >= IWL_MVM_STATION_COUNT)) {
+		if (!WARN_ON_ONCE(id >= ARRAY_SIZE(mvm->fw_id_to_mac_id))) {
 			sta = rcu_dereference(mvm->fw_id_to_mac_id[id]);
 			if (IS_ERR(sta))
 				sta = NULL;
@@ -893,26 +918,39 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 		if (iwl_mvm_is_nonagg_dup(sta, queue, rx_status, hdr, desc)) {
 			kfree_skb(skb);
-			rcu_read_unlock();
-			return;
+			goto out;
 		}
 
 		/*
 		 * Our hardware de-aggregates AMSDUs but copies the mac header
 		 * as it to the de-aggregated MPDUs. We need to turn off the
 		 * AMSDU bit in the QoS control ourselves.
+		 * In addition, HW reverses addr3 and addr4 - reverse it back.
 		 */
 		if ((desc->mac_flags2 & IWL_RX_MPDU_MFLG2_AMSDU) &&
 		    !WARN_ON(!ieee80211_is_data_qos(hdr->frame_control))) {
+			int i;
 			u8 *qc = ieee80211_get_qos_ctl(hdr);
+			u8 mac_addr[ETH_ALEN];
 
 			*qc &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT;
-			if (!(desc->amsdu_info &
-			      IWL_RX_MPDU_AMSDU_LAST_SUBFRAME))
-				rx_status->flag |= RX_FLAG_AMSDU_MORE;
+
+			for (i = 0; i < ETH_ALEN; i++)
+				mac_addr[i] = hdr->addr3[ETH_ALEN - i - 1];
+			ether_addr_copy(hdr->addr3, mac_addr);
+
+			if (ieee80211_has_a4(hdr->frame_control)) {
+				for (i = 0; i < ETH_ALEN; i++)
+					mac_addr[i] =
+						hdr->addr4[ETH_ALEN - i - 1];
+				ether_addr_copy(hdr->addr4, mac_addr);
+			}
+		}
+		if (baid != IWL_RX_REORDER_DATA_INVALID_BAID) {
+			u32 reorder_data = le32_to_cpu(desc->reorder_data);
+
+			iwl_mvm_agg_rx_received(mvm, reorder_data, baid);
 		}
-		if (baid != IWL_RX_REORDER_DATA_INVALID_BAID)
-			iwl_mvm_agg_rx_received(mvm, baid);
 	}
 
 	/* Set up the HT phy flags */
@@ -920,42 +958,50 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	case RATE_MCS_CHAN_WIDTH_20:
 		break;
 	case RATE_MCS_CHAN_WIDTH_40:
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 		break;
 	case RATE_MCS_CHAN_WIDTH_80:
-		rx_status->vht_flag |= RX_VHT_FLAG_80MHZ;
+		rx_status->bw = RATE_INFO_BW_80;
 		break;
 	case RATE_MCS_CHAN_WIDTH_160:
-		rx_status->vht_flag |= RX_VHT_FLAG_160MHZ;
+		rx_status->bw = RATE_INFO_BW_160;
 		break;
 	}
 	if (rate_n_flags & RATE_MCS_SGI_MSK)
-		rx_status->flag |= RX_FLAG_SHORT_GI;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	if (rate_n_flags & RATE_HT_MCS_GF_MSK)
-		rx_status->flag |= RX_FLAG_HT_GF;
+		rx_status->enc_flags |= RX_ENC_FLAG_HT_GF;
 	if (rate_n_flags & RATE_MCS_LDPC_MSK)
-		rx_status->flag |= RX_FLAG_LDPC;
+		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
 	if (rate_n_flags & RATE_MCS_HT_MSK) {
-		u8 stbc = (rate_n_flags & RATE_MCS_HT_STBC_MSK) >>
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
 				RATE_MCS_STBC_POS;
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 		rx_status->rate_idx = rate_n_flags & RATE_HT_MCS_INDEX_MSK;
-		rx_status->flag |= stbc << RX_FLAG_STBC_SHIFT;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 	} else if (rate_n_flags & RATE_MCS_VHT_MSK) {
-		u8 stbc = (rate_n_flags & RATE_MCS_VHT_STBC_MSK) >>
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
 				RATE_MCS_STBC_POS;
-		rx_status->vht_nss =
+		rx_status->nss =
 			((rate_n_flags & RATE_VHT_MCS_NSS_MSK) >>
 						RATE_VHT_MCS_NSS_POS) + 1;
 		rx_status->rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
-		rx_status->flag |= RX_FLAG_VHT;
-		rx_status->flag |= stbc << RX_FLAG_STBC_SHIFT;
+		rx_status->encoding = RX_ENC_VHT;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		if (rate_n_flags & RATE_MCS_BF_MSK)
-			rx_status->vht_flag |= RX_VHT_FLAG_BF;
+			rx_status->enc_flags |= RX_ENC_FLAG_BF;
 	} else {
-		rx_status->rate_idx =
-			iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
-							    rx_status->band);
+		int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
+							       rx_status->band);
+
+		if (WARN(rate < 0 || rate > 0xFF,
+			 "Invalid rate flags 0x%x, band %d,\n",
+			 rate_n_flags, rx_status->band)) {
+			kfree_skb(skb);
+			goto out;
+		}
+		rx_status->rate_idx = rate;
+
 	}
 
 	/* management stuff on default queue */
@@ -974,6 +1020,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	iwl_mvm_create_skb(skb, hdr, len, crypt_len, rxb);
 	if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc))
 		iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta);
+out:
 	rcu_read_unlock();
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 0a64efa844b7..8d1b994ae79f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -81,44 +81,30 @@ enum iwl_mvm_traffic_load {
 	IWL_MVM_TRAFFIC_HIGH,
 };
 
+#define IWL_SCAN_DWELL_ACTIVE		10
+#define IWL_SCAN_DWELL_PASSIVE		110
+#define IWL_SCAN_DWELL_FRAGMENTED	44
+#define IWL_SCAN_DWELL_EXTENDED		90
+
 struct iwl_mvm_scan_timing_params {
-	u32 dwell_active;
-	u32 dwell_passive;
-	u32 dwell_fragmented;
-	u32 dwell_extended;
 	u32 suspend_time;
 	u32 max_out_time;
 };
 
 static struct iwl_mvm_scan_timing_params scan_timing[] = {
 	[IWL_SCAN_TYPE_UNASSOC] = {
-		.dwell_active = 10,
-		.dwell_passive = 110,
-		.dwell_fragmented = 44,
-		.dwell_extended = 90,
 		.suspend_time = 0,
 		.max_out_time = 0,
 	},
 	[IWL_SCAN_TYPE_WILD] = {
-		.dwell_active = 10,
-		.dwell_passive = 110,
-		.dwell_fragmented = 44,
-		.dwell_extended = 90,
 		.suspend_time = 30,
 		.max_out_time = 120,
 	},
 	[IWL_SCAN_TYPE_MILD] = {
-		.dwell_active = 10,
-		.dwell_passive = 110,
-		.dwell_fragmented = 44,
-		.dwell_extended = 90,
 		.suspend_time = 120,
 		.max_out_time = 120,
 	},
 	[IWL_SCAN_TYPE_FRAGMENTED] = {
-		.dwell_active = 10,
-		.dwell_passive = 110,
-		.dwell_fragmented = 44,
 		.suspend_time = 95,
 		.max_out_time = 44,
 	},
@@ -294,34 +280,15 @@ int iwl_mvm_max_scan_ie_len(struct iwl_mvm *mvm)
 	return max_ie_len;
 }
 
-static u8 *iwl_mvm_dump_channel_list(struct iwl_scan_results_notif *res,
-				     int num_res, u8 *buf, size_t buf_size)
-{
-	int i;
-	u8 *pos = buf, *end = buf + buf_size;
-
-	for (i = 0; pos < end && i < num_res; i++)
-		pos += snprintf(pos, end - pos, " %u", res[i].channel);
-
-	/* terminate the string in case the buffer was too short */
-	*(buf + buf_size - 1) = '\0';
-
-	return buf;
-}
-
 void iwl_mvm_rx_lmac_scan_iter_complete_notif(struct iwl_mvm *mvm,
 					      struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_lmac_scan_complete_notif *notif = (void *)pkt->data;
-	u8 buf[256];
 
 	IWL_DEBUG_SCAN(mvm,
-		       "Scan offload iteration complete: status=0x%x scanned channels=%d channels list: %s\n",
-		       notif->status, notif->scanned_channels,
-		       iwl_mvm_dump_channel_list(notif->results,
-						 notif->scanned_channels, buf,
-						 sizeof(buf)));
+		       "Scan offload iteration complete: status=0x%x scanned channels=%d\n",
+		       notif->status, notif->scanned_channels);
 
 	if (mvm->sched_scan_pass_all == SCHED_SCAN_PASS_ALL_FOUND) {
 		IWL_DEBUG_SCAN(mvm, "Pass all scheduled scan results found\n");
@@ -743,10 +710,10 @@ static void iwl_mvm_scan_lmac_dwell(struct iwl_mvm *mvm,
 				    struct iwl_scan_req_lmac *cmd,
 				    struct iwl_mvm_scan_params *params)
 {
-	cmd->active_dwell = scan_timing[params->type].dwell_active;
-	cmd->passive_dwell = scan_timing[params->type].dwell_passive;
-	cmd->fragmented_dwell = scan_timing[params->type].dwell_fragmented;
-	cmd->extended_dwell = scan_timing[params->type].dwell_extended;
+	cmd->active_dwell = IWL_SCAN_DWELL_ACTIVE;
+	cmd->passive_dwell = IWL_SCAN_DWELL_PASSIVE;
+	cmd->fragmented_dwell = IWL_SCAN_DWELL_FRAGMENTED;
+	cmd->extended_dwell = IWL_SCAN_DWELL_EXTENDED;
 	cmd->max_out_time = cpu_to_le32(scan_timing[params->type].max_out_time);
 	cmd->suspend_time = cpu_to_le32(scan_timing[params->type].suspend_time);
 	cmd->scan_prio = cpu_to_le32(IWL_SCAN_PRIORITY_EXT_6);
@@ -944,13 +911,12 @@ static __le32 iwl_mvm_scan_config_rates(struct iwl_mvm *mvm)
 }
 
 static void iwl_mvm_fill_scan_dwell(struct iwl_mvm *mvm,
-				    struct iwl_scan_dwell *dwell,
-				    struct iwl_mvm_scan_timing_params *timing)
+				    struct iwl_scan_dwell *dwell)
 {
-	dwell->active = timing->dwell_active;
-	dwell->passive = timing->dwell_passive;
-	dwell->fragmented = timing->dwell_fragmented;
-	dwell->extended = timing->dwell_extended;
+	dwell->active = IWL_SCAN_DWELL_ACTIVE;
+	dwell->passive = IWL_SCAN_DWELL_PASSIVE;
+	dwell->fragmented = IWL_SCAN_DWELL_FRAGMENTED;
+	dwell->extended = IWL_SCAN_DWELL_EXTENDED;
 }
 
 static void iwl_mvm_fill_channels(struct iwl_mvm *mvm, u8 *channels)
@@ -966,11 +932,11 @@ static void iwl_mvm_fill_channels(struct iwl_mvm *mvm, u8 *channels)
 		channels[j] = band->channels[i].hw_value;
 }
 
-static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config,
-				     u32 flags, u8 channel_flags)
+static void iwl_mvm_fill_scan_config_v1(struct iwl_mvm *mvm, void *config,
+					u32 flags, u8 channel_flags)
 {
 	enum iwl_mvm_scan_type type = iwl_mvm_get_scan_type(mvm, false);
-	struct iwl_scan_config *cfg = config;
+	struct iwl_scan_config_v1 *cfg = config;
 
 	cfg->flags = cpu_to_le32(flags);
 	cfg->tx_chains = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm));
@@ -979,7 +945,7 @@ static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config,
 	cfg->out_of_channel_time = cpu_to_le32(scan_timing[type].max_out_time);
 	cfg->suspend_time = cpu_to_le32(scan_timing[type].suspend_time);
 
-	iwl_mvm_fill_scan_dwell(mvm, &cfg->dwell, &scan_timing[type]);
+	iwl_mvm_fill_scan_dwell(mvm, &cfg->dwell);
 
 	memcpy(&cfg->mac_addr, &mvm->addresses[0].addr, ETH_ALEN);
 
@@ -989,11 +955,11 @@ static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config,
 	iwl_mvm_fill_channels(mvm, cfg->channel_array);
 }
 
-static void iwl_mvm_fill_scan_config_cdb(struct iwl_mvm *mvm, void *config,
-					 u32 flags, u8 channel_flags)
+static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config,
+				     u32 flags, u8 channel_flags)
 {
 	enum iwl_mvm_scan_type type = iwl_mvm_get_scan_type(mvm, false);
-	struct iwl_scan_config_cdb *cfg = config;
+	struct iwl_scan_config *cfg = config;
 
 	cfg->flags = cpu_to_le32(flags);
 	cfg->tx_chains = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm));
@@ -1001,12 +967,16 @@ static void iwl_mvm_fill_scan_config_cdb(struct iwl_mvm *mvm, void *config,
 	cfg->legacy_rates = iwl_mvm_scan_config_rates(mvm);
 	cfg->out_of_channel_time[0] =
 		cpu_to_le32(scan_timing[type].max_out_time);
-	cfg->out_of_channel_time[1] =
-		cpu_to_le32(scan_timing[type].max_out_time);
 	cfg->suspend_time[0] = cpu_to_le32(scan_timing[type].suspend_time);
-	cfg->suspend_time[1] = cpu_to_le32(scan_timing[type].suspend_time);
 
-	iwl_mvm_fill_scan_dwell(mvm, &cfg->dwell, &scan_timing[type]);
+	if (iwl_mvm_is_cdb_supported(mvm)) {
+		cfg->suspend_time[1] =
+			cpu_to_le32(scan_timing[type].suspend_time);
+		cfg->out_of_channel_time[1] =
+			cpu_to_le32(scan_timing[type].max_out_time);
+	}
+
+	iwl_mvm_fill_scan_dwell(mvm, &cfg->dwell);
 
 	memcpy(&cfg->mac_addr, &mvm->addresses[0].addr, ETH_ALEN);
 
@@ -1033,16 +1003,13 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm)
 	if (WARN_ON(num_channels > mvm->fw->ucode_capa.n_scan_channels))
 		return -ENOBUFS;
 
-	if (type == mvm->scan_type) {
-		IWL_DEBUG_SCAN(mvm,
-			       "Ignoring UMAC scan config of the same type\n");
+	if (type == mvm->scan_type)
 		return 0;
-	}
 
-	if (iwl_mvm_is_cdb_supported(mvm))
-		cmd_size = sizeof(struct iwl_scan_config_cdb);
-	else
+	if (iwl_mvm_has_new_tx_api(mvm))
 		cmd_size = sizeof(struct iwl_scan_config);
+	else
+		cmd_size = sizeof(struct iwl_scan_config_v1);
 	cmd_size += mvm->fw->ucode_capa.n_scan_channels;
 
 	cfg = kzalloc(cmd_size, GFP_KERNEL);
@@ -1068,13 +1035,13 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm)
 			IWL_CHANNEL_FLAG_EBS_ADD |
 			IWL_CHANNEL_FLAG_PRE_SCAN_PASSIVE2ACTIVE;
 
-	if (iwl_mvm_is_cdb_supported(mvm)) {
+	if (iwl_mvm_has_new_tx_api(mvm)) {
 		flags |= (type == IWL_SCAN_TYPE_FRAGMENTED) ?
 			 SCAN_CONFIG_FLAG_SET_LMAC2_FRAGMENTED :
 			 SCAN_CONFIG_FLAG_CLEAR_LMAC2_FRAGMENTED;
-		iwl_mvm_fill_scan_config_cdb(mvm, cfg, flags, channel_flags);
-	} else {
 		iwl_mvm_fill_scan_config(mvm, cfg, flags, channel_flags);
+	} else {
+		iwl_mvm_fill_scan_config_v1(mvm, cfg, flags, channel_flags);
 	}
 
 	cmd.data[0] = cfg;
@@ -1113,22 +1080,26 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm,
 		cmd->passive_dwell = params->measurement_dwell;
 		cmd->extended_dwell = params->measurement_dwell;
 	} else {
-		cmd->active_dwell = timing->dwell_active;
-		cmd->passive_dwell = timing->dwell_passive;
-		cmd->extended_dwell = timing->dwell_extended;
+		cmd->active_dwell = IWL_SCAN_DWELL_ACTIVE;
+		cmd->passive_dwell = IWL_SCAN_DWELL_PASSIVE;
+		cmd->extended_dwell = IWL_SCAN_DWELL_EXTENDED;
 	}
-	cmd->fragmented_dwell = timing->dwell_fragmented;
-
-	if (iwl_mvm_is_cdb_supported(mvm)) {
-		cmd->cdb.max_out_time[0] = cpu_to_le32(timing->max_out_time);
-		cmd->cdb.suspend_time[0] = cpu_to_le32(timing->suspend_time);
-		cmd->cdb.max_out_time[1] = cpu_to_le32(timing->max_out_time);
-		cmd->cdb.suspend_time[1] = cpu_to_le32(timing->suspend_time);
-		cmd->cdb.scan_priority = cpu_to_le32(IWL_SCAN_PRIORITY_EXT_6);
+	cmd->fragmented_dwell = IWL_SCAN_DWELL_FRAGMENTED;
+
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		cmd->v6.scan_priority = cpu_to_le32(IWL_SCAN_PRIORITY_EXT_6);
+		cmd->v6.max_out_time[0] = cpu_to_le32(timing->max_out_time);
+		cmd->v6.suspend_time[0] = cpu_to_le32(timing->suspend_time);
+		if (iwl_mvm_is_cdb_supported(mvm)) {
+			cmd->v6.max_out_time[1] =
+				cpu_to_le32(timing->max_out_time);
+			cmd->v6.suspend_time[1] =
+				cpu_to_le32(timing->suspend_time);
+		}
 	} else {
-		cmd->no_cdb.max_out_time = cpu_to_le32(timing->max_out_time);
-		cmd->no_cdb.suspend_time = cpu_to_le32(timing->suspend_time);
-		cmd->no_cdb.scan_priority =
+		cmd->v1.max_out_time = cpu_to_le32(timing->max_out_time);
+		cmd->v1.suspend_time = cpu_to_le32(timing->suspend_time);
+		cmd->v1.scan_priority =
 			cpu_to_le32(IWL_SCAN_PRIORITY_EXT_6);
 	}
 
@@ -1207,8 +1178,8 @@ static int iwl_mvm_scan_umac(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			     int type)
 {
 	struct iwl_scan_req_umac *cmd = mvm->scan_cmd;
-	void *cmd_data = iwl_mvm_is_cdb_supported(mvm) ?
-			 (void *)&cmd->cdb.data : (void *)&cmd->no_cdb.data;
+	void *cmd_data = iwl_mvm_has_new_tx_api(mvm) ?
+			 (void *)&cmd->v6.data : (void *)&cmd->v1.data;
 	struct iwl_scan_req_umac_tail *sec_part = cmd_data +
 		sizeof(struct iwl_scan_channel_cfg_umac) *
 			mvm->fw->ucode_capa.n_scan_channels;
@@ -1245,12 +1216,12 @@ static int iwl_mvm_scan_umac(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
 				IWL_SCAN_CHANNEL_FLAG_CACHE_ADD;
 
-	if (iwl_mvm_is_cdb_supported(mvm)) {
-		cmd->cdb.channel_flags = channel_flags;
-		cmd->cdb.n_channels = params->n_channels;
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		cmd->v6.channel_flags = channel_flags;
+		cmd->v6.n_channels = params->n_channels;
 	} else {
-		cmd->no_cdb.channel_flags = channel_flags;
-		cmd->no_cdb.n_channels = params->n_channels;
+		cmd->v1.channel_flags = channel_flags;
+		cmd->v1.n_channels = params->n_channels;
 	}
 
 	iwl_scan_build_ssids(params, sec_part->direct_scan, &ssid_bitmap);
@@ -1607,16 +1578,12 @@ void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm,
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_umac_scan_iter_complete_notif *notif = (void *)pkt->data;
-	u8 buf[256];
 
 	mvm->scan_start = le64_to_cpu(notif->start_tsf);
 
 	IWL_DEBUG_SCAN(mvm,
-		       "UMAC Scan iteration complete: status=0x%x scanned_channels=%d channels list: %s\n",
-		       notif->status, notif->scanned_channels,
-		       iwl_mvm_dump_channel_list(notif->results,
-						 notif->scanned_channels, buf,
-						 sizeof(buf)));
+		       "UMAC Scan iteration complete: status=0x%x scanned_channels=%d\n",
+		       notif->status, notif->scanned_channels);
 
 	if (mvm->sched_scan_pass_all == SCHED_SCAN_PASS_ALL_FOUND) {
 		IWL_DEBUG_SCAN(mvm, "Pass all scheduled scan results found\n");
@@ -1692,10 +1659,10 @@ static int iwl_mvm_scan_stop_wait(struct iwl_mvm *mvm, int type)
 
 int iwl_mvm_scan_size(struct iwl_mvm *mvm)
 {
-	int base_size = IWL_SCAN_REQ_UMAC_SIZE;
+	int base_size = IWL_SCAN_REQ_UMAC_SIZE_V1;
 
-	if (iwl_mvm_is_cdb_supported(mvm))
-		base_size = IWL_SCAN_REQ_UMAC_SIZE_CDB;
+	if (iwl_mvm_has_new_tx_api(mvm))
+		base_size = IWL_SCAN_REQ_UMAC_SIZE;
 
 	if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_UMAC_SCAN))
 		return base_size +
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sf.c b/drivers/net/wireless/intel/iwlwifi/mvm/sf.c
index 101fb04a8573..539b06bf0803 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sf.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sf.c
@@ -235,7 +235,7 @@ static int iwl_mvm_sf_config(struct iwl_mvm *mvm, u8 sta_id,
 		iwl_mvm_fill_sf_command(mvm, &sf_cmd, NULL);
 		break;
 	case SF_FULL_ON:
-		if (sta_id == IWL_MVM_STATION_COUNT) {
+		if (sta_id == IWL_MVM_INVALID_STA) {
 			IWL_ERR(mvm,
 				"No station: Cannot switch SF to FULL_ON\n");
 			return -EINVAL;
@@ -276,12 +276,12 @@ int iwl_mvm_sf_update(struct iwl_mvm *mvm, struct ieee80211_vif *changed_vif,
 		      bool remove_vif)
 {
 	enum iwl_sf_state new_state;
-	u8 sta_id = IWL_MVM_STATION_COUNT;
+	u8 sta_id = IWL_MVM_INVALID_STA;
 	struct iwl_mvm_vif *mvmvif = NULL;
 	struct iwl_mvm_active_iface_iterator_data data = {
 		.ignore_vif = changed_vif,
 		.sta_vif_state = SF_UNINIT,
-		.sta_vif_ap_sta_id = IWL_MVM_STATION_COUNT,
+		.sta_vif_ap_sta_id = IWL_MVM_INVALID_STA,
 	};
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index bd1dcc863d8f..f5c786ddc526 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -77,9 +77,11 @@
  */
 static inline int iwl_mvm_add_sta_cmd_size(struct iwl_mvm *mvm)
 {
-	return iwl_mvm_has_new_rx_api(mvm) ?
-		sizeof(struct iwl_mvm_add_sta_cmd) :
-		sizeof(struct iwl_mvm_add_sta_cmd_v7);
+	if (iwl_mvm_has_new_rx_api(mvm) ||
+	    fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE))
+		return sizeof(struct iwl_mvm_add_sta_cmd);
+	else
+		return sizeof(struct iwl_mvm_add_sta_cmd_v7);
 }
 
 static int iwl_mvm_find_free_sta_id(struct iwl_mvm *mvm,
@@ -98,7 +100,7 @@ static int iwl_mvm_find_free_sta_id(struct iwl_mvm *mvm,
 		reserved_ids = BIT(0);
 
 	/* Don't take rcu_read_lock() since we are protected by mvm->mutex */
-	for (sta_id = 0; sta_id < IWL_MVM_STATION_COUNT; sta_id++) {
+	for (sta_id = 0; sta_id < ARRAY_SIZE(mvm->fw_id_to_mac_id); sta_id++) {
 		if (BIT(sta_id) & reserved_ids)
 			continue;
 
@@ -106,7 +108,7 @@ static int iwl_mvm_find_free_sta_id(struct iwl_mvm *mvm,
 					       lockdep_is_held(&mvm->mutex)))
 			return sta_id;
 	}
-	return IWL_MVM_STATION_COUNT;
+	return IWL_MVM_INVALID_STA;
 }
 
 /* send station add/update command to firmware */
@@ -126,12 +128,21 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	u32 status;
 	u32 agg_size = 0, mpdu_dens = 0;
 
+	if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE))
+		add_sta_cmd.station_type = mvm_sta->sta_type;
+
 	if (!update || (flags & STA_MODIFY_QUEUES)) {
-		add_sta_cmd.tfd_queue_msk = cpu_to_le32(mvm_sta->tfd_queue_msk);
 		memcpy(&add_sta_cmd.addr, sta->addr, ETH_ALEN);
 
-		if (flags & STA_MODIFY_QUEUES)
-			add_sta_cmd.modify_mask |= STA_MODIFY_QUEUES;
+		if (!iwl_mvm_has_new_tx_api(mvm)) {
+			add_sta_cmd.tfd_queue_msk =
+				cpu_to_le32(mvm_sta->tfd_queue_msk);
+
+			if (flags & STA_MODIFY_QUEUES)
+				add_sta_cmd.modify_mask |= STA_MODIFY_QUEUES;
+		} else {
+			WARN_ON(flags & STA_MODIFY_QUEUES);
+		}
 	}
 
 	switch (sta->bandwidth) {
@@ -209,13 +220,15 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		add_sta_cmd.modify_mask |= STA_MODIFY_UAPSD_ACS;
 
 		if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK)
-			add_sta_cmd.uapsd_trigger_acs |= BIT(AC_BK);
+			add_sta_cmd.uapsd_acs |= BIT(AC_BK);
 		if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE)
-			add_sta_cmd.uapsd_trigger_acs |= BIT(AC_BE);
+			add_sta_cmd.uapsd_acs |= BIT(AC_BE);
 		if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI)
-			add_sta_cmd.uapsd_trigger_acs |= BIT(AC_VI);
+			add_sta_cmd.uapsd_acs |= BIT(AC_VI);
 		if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO)
-			add_sta_cmd.uapsd_trigger_acs |= BIT(AC_VO);
+			add_sta_cmd.uapsd_acs |= BIT(AC_VO);
+		add_sta_cmd.uapsd_acs |= add_sta_cmd.uapsd_acs << 4;
+		add_sta_cmd.sp_length = sta->max_sp ? sta->max_sp * 2 : 128;
 	}
 
 	status = ADD_STA_SUCCESS;
@@ -337,6 +350,9 @@ static int iwl_mvm_invalidate_sta_queue(struct iwl_mvm *mvm, int queue,
 	u8 sta_id;
 	int ret;
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	spin_unlock_bh(&mvm->queue_info_lock);
@@ -387,6 +403,9 @@ static int iwl_mvm_get_queue_agg_tids(struct iwl_mvm *mvm, int queue)
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
@@ -426,6 +445,9 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue)
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
@@ -447,7 +469,7 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue)
 	for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) {
 		if (mvmsta->tid_data[tid].state == IWL_AGG_ON)
 			disable_agg_tids |= BIT(tid);
-		mvmsta->tid_data[tid].txq_id = IEEE80211_INVAL_HW_QUEUE;
+		mvmsta->tid_data[tid].txq_id = IWL_MVM_INVALID_QUEUE;
 	}
 
 	mvmsta->tfd_queue_msk &= ~BIT(queue); /* Don't use this queue anymore */
@@ -468,6 +490,9 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	txq_curr_ac = mvm->queue_info[queue].mac80211_ac;
 	sta_id = mvm->queue_info[queue].ra_sta_id;
@@ -475,6 +500,8 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 	spin_unlock_bh(&mvm->queue_info_lock);
 
 	mvmsta = iwl_mvm_sta_from_staid_protected(mvm, sta_id);
+	if (WARN_ON(!mvmsta))
+		return -EINVAL;
 
 	disable_agg_tids = iwl_mvm_remove_sta_queue_marking(mvm, queue);
 	/* Disable the queue */
@@ -512,6 +539,8 @@ static int iwl_mvm_get_shared_queue(struct iwl_mvm *mvm,
 	int i;
 
 	lockdep_assert_held(&mvm->queue_info_lock);
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
 
 	memset(&ac_to_queue, IEEE80211_INVAL_HW_QUEUE, sizeof(ac_to_queue));
 
@@ -596,6 +625,9 @@ int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 	unsigned long mq;
 	int ret;
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
+
 	/*
 	 * If the AC is lower than current one - FIFO needs to be redirected to
 	 * the lowest one of the streams in the queue. Check if this is needed
@@ -617,7 +649,7 @@ int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 	cmd.sta_id = mvm->queue_info[queue].ra_sta_id;
 	cmd.tx_fifo = iwl_mvm_ac_to_tx_fifo[mvm->queue_info[queue].mac80211_ac];
 	cmd.tid = mvm->queue_info[queue].txq_tid;
-	mq = mvm->queue_info[queue].hw_queue_to_mac80211;
+	mq = mvm->hw_queue_to_mac80211[queue];
 	shared_queue = (mvm->queue_info[queue].hw_queue_refcount > 1);
 	spin_unlock_bh(&mvm->queue_info_lock);
 
@@ -626,7 +658,7 @@ int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 
 	/* Stop MAC queues and wait for this queue to empty */
 	iwl_mvm_stop_mac_queues(mvm, mq);
-	ret = iwl_trans_wait_tx_queue_empty(mvm->trans, BIT(queue));
+	ret = iwl_trans_wait_tx_queues_empty(mvm->trans, BIT(queue));
 	if (ret) {
 		IWL_ERR(mvm, "Error draining queue %d before reconfig\n",
 			queue);
@@ -677,6 +709,37 @@ out:
 	return ret;
 }
 
+static int iwl_mvm_sta_alloc_queue_tvqm(struct iwl_mvm *mvm,
+					struct ieee80211_sta *sta, u8 ac,
+					int tid)
+{
+	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+	unsigned int wdg_timeout =
+		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false);
+	u8 mac_queue = mvmsta->vif->hw_queue[ac];
+	int queue = -1;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	IWL_DEBUG_TX_QUEUES(mvm,
+			    "Allocating queue for sta %d on tid %d\n",
+			    mvmsta->sta_id, tid);
+	queue = iwl_mvm_tvqm_enable_txq(mvm, mac_queue, mvmsta->sta_id, tid,
+					wdg_timeout);
+	if (queue < 0)
+		return queue;
+
+	IWL_DEBUG_TX_QUEUES(mvm, "Allocated queue is %d\n", queue);
+
+	spin_lock_bh(&mvmsta->lock);
+	mvmsta->tid_data[tid].txq_id = queue;
+	mvmsta->tid_data[tid].is_tid_active = true;
+	mvmsta->tfd_queue_msk |= BIT(queue);
+	spin_unlock_bh(&mvmsta->lock);
+
+	return 0;
+}
+
 static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 				   struct ieee80211_sta *sta, u8 ac, int tid,
 				   struct ieee80211_hdr *hdr)
@@ -702,6 +765,9 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return iwl_mvm_sta_alloc_queue_tvqm(mvm, sta, ac, tid);
+
 	spin_lock_bh(&mvmsta->lock);
 	tfd_queue_mask = mvmsta->tfd_queue_msk;
 	spin_unlock_bh(&mvmsta->lock);
@@ -880,6 +946,9 @@ static void iwl_mvm_change_queue_owner(struct iwl_mvm *mvm, int queue)
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
 	spin_unlock_bh(&mvm->queue_info_lock);
@@ -917,6 +986,10 @@ static void iwl_mvm_unshare_queue(struct iwl_mvm *mvm, int queue)
 	int ssn;
 	int ret = true;
 
+	/* queue sharing is disabled on new TX path */
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return;
+
 	lockdep_assert_held(&mvm->mutex);
 
 	spin_lock_bh(&mvm->queue_info_lock);
@@ -1014,7 +1087,7 @@ static void iwl_mvm_tx_deferred_stream(struct iwl_mvm *mvm,
 	ac = iwl_mvm_tid_to_ac_queue(tid);
 	mac_queue = IEEE80211_SKB_CB(skb)->hw_queue;
 
-	if (tid_data->txq_id == IEEE80211_INVAL_HW_QUEUE &&
+	if (tid_data->txq_id == IWL_MVM_INVALID_QUEUE &&
 	    iwl_mvm_sta_alloc_queue(mvm, sta, ac, tid, hdr)) {
 		IWL_ERR(mvm,
 			"Can't alloc TXQ for sta %d tid %d - dropping frame\n",
@@ -1059,8 +1132,12 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk)
 
 	mutex_lock(&mvm->mutex);
 
+	/* No queue reconfiguration in TVQM mode */
+	if (iwl_mvm_has_new_tx_api(mvm))
+		goto alloc_queues;
+
 	/* Reconfigure queues requiring reconfiguation */
-	for (queue = 0; queue < IWL_MAX_HW_QUEUES; queue++) {
+	for (queue = 0; queue < ARRAY_SIZE(mvm->queue_info); queue++) {
 		bool reconfig;
 		bool change_owner;
 
@@ -1088,6 +1165,7 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk)
 			iwl_mvm_change_queue_owner(mvm, queue);
 	}
 
+alloc_queues:
 	/* Go over all stations with deferred traffic */
 	for_each_set_bit(sta_id, mvm->sta_deferred_frames,
 			 IWL_MVM_STATION_COUNT) {
@@ -1116,6 +1194,10 @@ static int iwl_mvm_reserve_sta_stream(struct iwl_mvm *mvm,
 	int queue;
 	bool using_inactive_queue = false, same_sta = false;
 
+	/* queue reserving is disabled on new TX path */
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return 0;
+
 	/*
 	 * Check for inactive queues, so we don't reach a situation where we
 	 * can't add a STA due to a shortage in queues that doesn't really exist
@@ -1191,7 +1273,7 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm,
 		int ac;
 		u8 mac_queue;
 
-		if (txq_id == IEEE80211_INVAL_HW_QUEUE)
+		if (txq_id == IWL_MVM_INVALID_QUEUE)
 			continue;
 
 		skb_queue_head_init(&tid_data->deferred_tx_frames);
@@ -1199,20 +1281,31 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm,
 		ac = tid_to_mac80211_ac[i];
 		mac_queue = mvm_sta->vif->hw_queue[ac];
 
-		cfg.tid = i;
-		cfg.fifo = iwl_mvm_ac_to_tx_fifo[ac];
-		cfg.aggregate = (txq_id >= IWL_MVM_DQA_MIN_DATA_QUEUE ||
-				 txq_id == IWL_MVM_DQA_BSS_CLIENT_QUEUE);
+		if (iwl_mvm_has_new_tx_api(mvm)) {
+			IWL_DEBUG_TX_QUEUES(mvm,
+					    "Re-mapping sta %d tid %d\n",
+					    mvm_sta->sta_id, i);
+			txq_id = iwl_mvm_tvqm_enable_txq(mvm, mac_queue,
+							 mvm_sta->sta_id,
+							 i, wdg_timeout);
+			tid_data->txq_id = txq_id;
+		} else {
+			u16 seq = IEEE80211_SEQ_TO_SN(tid_data->seq_number);
 
-		IWL_DEBUG_TX_QUEUES(mvm,
-				    "Re-mapping sta %d tid %d to queue %d\n",
-				    mvm_sta->sta_id, i, txq_id);
+			cfg.tid = i;
+			cfg.fifo = iwl_mvm_ac_to_tx_fifo[ac];
+			cfg.aggregate = (txq_id >= IWL_MVM_DQA_MIN_DATA_QUEUE ||
+					 txq_id ==
+					 IWL_MVM_DQA_BSS_CLIENT_QUEUE);
 
-		iwl_mvm_enable_txq(mvm, txq_id, mac_queue,
-				   IEEE80211_SEQ_TO_SN(tid_data->seq_number),
-				   &cfg, wdg_timeout);
+			IWL_DEBUG_TX_QUEUES(mvm,
+					    "Re-mapping sta %d tid %d to queue %d\n",
+					    mvm_sta->sta_id, i, txq_id);
 
-		mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_READY;
+			iwl_mvm_enable_txq(mvm, txq_id, mac_queue, seq, &cfg,
+					   wdg_timeout);
+			mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_READY;
+		}
 	}
 
 	atomic_set(&mvm->pending_frames[mvm_sta->sta_id], 0);
@@ -1235,7 +1328,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm,
 	else
 		sta_id = mvm_sta->sta_id;
 
-	if (sta_id == IWL_MVM_STATION_COUNT)
+	if (sta_id == IWL_MVM_INVALID_STA)
 		return -ENOSPC;
 
 	spin_lock_init(&mvm_sta->lock);
@@ -1254,6 +1347,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm,
 	mvm_sta->max_agg_bufsize = LINK_QUAL_AGG_FRAME_LIMIT_DEF;
 	mvm_sta->tx_protection = 0;
 	mvm_sta->tt_tx_protection = false;
+	mvm_sta->sta_type = sta->tdls ? IWL_STA_TDLS_LINK : IWL_STA_LINK;
 
 	/* HW restart, don't assume the memory has been zeroed */
 	atomic_set(&mvm->pending_frames[sta_id], 0);
@@ -1287,7 +1381,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm,
 		 * Mark all queues for this STA as unallocated and defer TX
 		 * frames until the queue is allocated
 		 */
-		mvm_sta->tid_data[i].txq_id = IEEE80211_INVAL_HW_QUEUE;
+		mvm_sta->tid_data[i].txq_id = IWL_MVM_INVALID_QUEUE;
 		skb_queue_head_init(&mvm_sta->tid_data[i].deferred_tx_frames);
 	}
 	mvm_sta->deferred_traffic_tid_map = 0;
@@ -1303,7 +1397,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm,
 		mvm_sta->dup_data = dup_data;
 	}
 
-	if (iwl_mvm_is_dqa_supported(mvm)) {
+	if (iwl_mvm_is_dqa_supported(mvm) && !iwl_mvm_has_new_tx_api(mvm)) {
 		ret = iwl_mvm_reserve_sta_stream(mvm, sta,
 						 ieee80211_vif_type_p2p(vif));
 		if (ret)
@@ -1317,10 +1411,10 @@ update_fw:
 
 	if (vif->type == NL80211_IFTYPE_STATION) {
 		if (!sta->tdls) {
-			WARN_ON(mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT);
+			WARN_ON(mvmvif->ap_sta_id != IWL_MVM_INVALID_STA);
 			mvmvif->ap_sta_id = sta_id;
 		} else {
-			WARN_ON(mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT);
+			WARN_ON(mvmvif->ap_sta_id == IWL_MVM_INVALID_STA);
 		}
 	}
 
@@ -1486,13 +1580,13 @@ static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm,
 	lockdep_assert_held(&mvm->mutex);
 
 	for (i = 0; i < ARRAY_SIZE(mvm_sta->tid_data); i++) {
-		if (mvm_sta->tid_data[i].txq_id == IEEE80211_INVAL_HW_QUEUE)
+		if (mvm_sta->tid_data[i].txq_id == IWL_MVM_INVALID_QUEUE)
 			continue;
 
 		ac = iwl_mvm_tid_to_ac_queue(i);
 		iwl_mvm_disable_txq(mvm, mvm_sta->tid_data[i].txq_id,
 				    vif->hw_queue[ac], i, 0);
-		mvm_sta->tid_data[i].txq_id = IEEE80211_INVAL_HW_QUEUE;
+		mvm_sta->tid_data[i].txq_id = IWL_MVM_INVALID_QUEUE;
 	}
 }
 
@@ -1520,8 +1614,8 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 		ret = iwl_mvm_flush_tx_path(mvm, mvm_sta->tfd_queue_msk, 0);
 		if (ret)
 			return ret;
-		ret = iwl_trans_wait_tx_queue_empty(mvm->trans,
-						    mvm_sta->tfd_queue_msk);
+		ret = iwl_trans_wait_tx_queues_empty(mvm->trans,
+						     mvm_sta->tfd_queue_msk);
 		if (ret)
 			return ret;
 		ret = iwl_mvm_drain_sta(mvm, mvm_sta, false);
@@ -1571,11 +1665,11 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 				return ret;
 
 			/* unassoc - go ahead - remove the AP STA now */
-			mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT;
+			mvmvif->ap_sta_id = IWL_MVM_INVALID_STA;
 
 			/* clear d0i3_ap_sta_id if no longer relevant */
 			if (mvm->d0i3_ap_sta_id == sta_id)
-				mvm->d0i3_ap_sta_id = IWL_MVM_STATION_COUNT;
+				mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
 		}
 	}
 
@@ -1584,7 +1678,7 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 	 * before the STA is removed.
 	 */
 	if (WARN_ON_ONCE(mvm->tdls_cs.peer.sta_id == sta_id)) {
-		mvm->tdls_cs.peer.sta_id = IWL_MVM_STATION_COUNT;
+		mvm->tdls_cs.peer.sta_id = IWL_MVM_INVALID_STA;
 		cancel_delayed_work(&mvm->tdls_cs.dwork);
 	}
 
@@ -1637,27 +1731,28 @@ int iwl_mvm_rm_sta_id(struct iwl_mvm *mvm,
 
 int iwl_mvm_allocate_int_sta(struct iwl_mvm *mvm,
 			     struct iwl_mvm_int_sta *sta,
-			     u32 qmask, enum nl80211_iftype iftype)
+			     u32 qmask, enum nl80211_iftype iftype,
+			     enum iwl_sta_type type)
 {
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		sta->sta_id = iwl_mvm_find_free_sta_id(mvm, iftype);
-		if (WARN_ON_ONCE(sta->sta_id == IWL_MVM_STATION_COUNT))
+		if (WARN_ON_ONCE(sta->sta_id == IWL_MVM_INVALID_STA))
 			return -ENOSPC;
 	}
 
 	sta->tfd_queue_msk = qmask;
+	sta->type = type;
 
 	/* put a non-NULL value so iterating over the stations won't stop */
 	rcu_assign_pointer(mvm->fw_id_to_mac_id[sta->sta_id], ERR_PTR(-EINVAL));
 	return 0;
 }
 
-static void iwl_mvm_dealloc_int_sta(struct iwl_mvm *mvm,
-				    struct iwl_mvm_int_sta *sta)
+void iwl_mvm_dealloc_int_sta(struct iwl_mvm *mvm, struct iwl_mvm_int_sta *sta)
 {
 	RCU_INIT_POINTER(mvm->fw_id_to_mac_id[sta->sta_id], NULL);
 	memset(sta, 0, sizeof(struct iwl_mvm_int_sta));
-	sta->sta_id = IWL_MVM_STATION_COUNT;
+	sta->sta_id = IWL_MVM_INVALID_STA;
 }
 
 static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm,
@@ -1675,8 +1770,11 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm,
 	cmd.sta_id = sta->sta_id;
 	cmd.mac_id_n_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(mac_id,
 							     color));
+	if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE))
+		cmd.station_type = sta->type;
 
-	cmd.tfd_queue_msk = cpu_to_le32(sta->tfd_queue_msk);
+	if (!iwl_mvm_has_new_tx_api(mvm))
+		cmd.tfd_queue_msk = cpu_to_le32(sta->tfd_queue_msk);
 	cmd.tid_disable_tx = cpu_to_le16(0xffff);
 
 	if (addr)
@@ -1701,27 +1799,19 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm,
 	return ret;
 }
 
-int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm)
+static void iwl_mvm_enable_aux_queue(struct iwl_mvm *mvm)
 {
 	unsigned int wdg_timeout = iwlmvm_mod_params.tfd_q_hang_detect ?
 					mvm->cfg->base_params->wd_timeout :
 					IWL_WATCHDOG_DISABLED;
-	int ret;
-
-	lockdep_assert_held(&mvm->mutex);
-
-	/* Map Aux queue to fifo - needs to happen before adding Aux station */
-	if (!iwl_mvm_is_dqa_supported(mvm))
-		iwl_mvm_enable_ac_txq(mvm, mvm->aux_queue, mvm->aux_queue,
-				      IWL_MVM_TX_FIFO_MCAST, 0, wdg_timeout);
 
-	/* Allocate aux station and assign to it the aux queue */
-	ret = iwl_mvm_allocate_int_sta(mvm, &mvm->aux_sta, BIT(mvm->aux_queue),
-				       NL80211_IFTYPE_UNSPECIFIED);
-	if (ret)
-		return ret;
-
-	if (iwl_mvm_is_dqa_supported(mvm)) {
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		int queue = iwl_mvm_tvqm_enable_txq(mvm, mvm->aux_queue,
+						    mvm->aux_sta.sta_id,
+						    IWL_MAX_TID_COUNT,
+						    wdg_timeout);
+		mvm->aux_queue = queue;
+	} else if (iwl_mvm_is_dqa_supported(mvm)) {
 		struct iwl_trans_txq_scd_cfg cfg = {
 			.fifo = IWL_MVM_TX_FIFO_MCAST,
 			.sta_id = mvm->aux_sta.sta_id,
@@ -1732,14 +1822,44 @@ int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm)
 
 		iwl_mvm_enable_txq(mvm, mvm->aux_queue, mvm->aux_queue, 0, &cfg,
 				   wdg_timeout);
+	} else {
+		iwl_mvm_enable_ac_txq(mvm, mvm->aux_queue, mvm->aux_queue,
+				      IWL_MVM_TX_FIFO_MCAST, 0, wdg_timeout);
 	}
+}
 
-	ret = iwl_mvm_add_int_sta_common(mvm, &mvm->aux_sta, NULL,
-					 MAC_INDEX_AUX, 0);
+int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm)
+{
+	int ret;
 
+	lockdep_assert_held(&mvm->mutex);
+
+	/* Allocate aux station and assign to it the aux queue */
+	ret = iwl_mvm_allocate_int_sta(mvm, &mvm->aux_sta, BIT(mvm->aux_queue),
+				       NL80211_IFTYPE_UNSPECIFIED,
+				       IWL_STA_AUX_ACTIVITY);
 	if (ret)
+		return ret;
+
+	/* Map Aux queue to fifo - needs to happen before adding Aux station */
+	if (!iwl_mvm_has_new_tx_api(mvm))
+		iwl_mvm_enable_aux_queue(mvm);
+
+	ret = iwl_mvm_add_int_sta_common(mvm, &mvm->aux_sta, NULL,
+					 MAC_INDEX_AUX, 0);
+	if (ret) {
 		iwl_mvm_dealloc_int_sta(mvm, &mvm->aux_sta);
-	return ret;
+		return ret;
+	}
+
+	/*
+	 * For a000 firmware and on we cannot add queue to a station unknown
+	 * to firmware so enable queue here - after the station was added
+	 */
+	if (iwl_mvm_has_new_tx_api(mvm))
+		iwl_mvm_enable_aux_queue(mvm);
+
+	return 0;
 }
 
 int iwl_mvm_add_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
@@ -1790,38 +1910,39 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	struct iwl_mvm_int_sta *bsta = &mvmvif->bcast_sta;
 	static const u8 _baddr[] = {0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
 	const u8 *baddr = _baddr;
+	int queue;
 	int ret;
+	unsigned int wdg_timeout =
+		iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+	struct iwl_trans_txq_scd_cfg cfg = {
+		.fifo = IWL_MVM_TX_FIFO_VO,
+		.sta_id = mvmvif->bcast_sta.sta_id,
+		.tid = IWL_MAX_TID_COUNT,
+		.aggregate = false,
+		.frame_limit = IWL_FRAME_LIMIT,
+	};
 
 	lockdep_assert_held(&mvm->mutex);
 
-	if (iwl_mvm_is_dqa_supported(mvm)) {
-		struct iwl_trans_txq_scd_cfg cfg = {
-			.fifo = IWL_MVM_TX_FIFO_VO,
-			.sta_id = mvmvif->bcast_sta.sta_id,
-			.tid = IWL_MAX_TID_COUNT,
-			.aggregate = false,
-			.frame_limit = IWL_FRAME_LIMIT,
-		};
-		unsigned int wdg_timeout =
-			iwl_mvm_get_wd_timeout(mvm, vif, false, false);
-		int queue;
-
-		if (vif->type == NL80211_IFTYPE_AP)
-			queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
+	if (iwl_mvm_is_dqa_supported(mvm) && !iwl_mvm_has_new_tx_api(mvm)) {
+		if (vif->type == NL80211_IFTYPE_AP ||
+		    vif->type == NL80211_IFTYPE_ADHOC)
+			queue = mvm->probe_queue;
 		else if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
-			queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+			queue = mvm->p2p_dev_queue;
 		else if (WARN(1, "Missing required TXQ for adding bcast STA\n"))
 			return -EINVAL;
 
-		iwl_mvm_enable_txq(mvm, queue, vif->hw_queue[0], 0, &cfg,
-				   wdg_timeout);
 		bsta->tfd_queue_msk |= BIT(queue);
+
+		iwl_mvm_enable_txq(mvm, queue, vif->hw_queue[0], 0,
+				   &cfg, wdg_timeout);
 	}
 
 	if (vif->type == NL80211_IFTYPE_ADHOC)
 		baddr = vif->bss_conf.bssid;
 
-	if (WARN_ON_ONCE(bsta->sta_id == IWL_MVM_STATION_COUNT))
+	if (WARN_ON_ONCE(bsta->sta_id == IWL_MVM_INVALID_STA))
 		return -ENOSPC;
 
 	ret = iwl_mvm_add_int_sta_common(mvm, bsta, baddr,
@@ -1830,26 +1951,21 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		return ret;
 
 	/*
-	 * In AP vif type, we also need to enable the cab_queue. However, we
-	 * have to enable it after the ADD_STA command is sent, otherwise the
-	 * FW will throw an assert once we send the ADD_STA command (it'll
-	 * detect a mismatch in the tfd_queue_msk, as we can't add the
-	 * enabled-cab_queue to the mask)
+	 * For a000 firmware and on we cannot add queue to a station unknown
+	 * to firmware so enable queue here - after the station was added
 	 */
-	if (iwl_mvm_is_dqa_supported(mvm) &&
-	    vif->type == NL80211_IFTYPE_AP) {
-		struct iwl_trans_txq_scd_cfg cfg = {
-			.fifo = IWL_MVM_TX_FIFO_MCAST,
-			.sta_id = mvmvif->bcast_sta.sta_id,
-			.tid = IWL_MAX_TID_COUNT,
-			.aggregate = false,
-			.frame_limit = IWL_FRAME_LIMIT,
-		};
-		unsigned int wdg_timeout =
-			iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		queue = iwl_mvm_tvqm_enable_txq(mvm, vif->hw_queue[0],
+						bsta->sta_id,
+						IWL_MAX_TID_COUNT,
+						wdg_timeout);
+
+		if (vif->type == NL80211_IFTYPE_AP)
+			mvm->probe_queue = queue;
+		else if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
+			mvm->p2p_dev_queue = queue;
 
-		iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue,
-				   0, &cfg, wdg_timeout);
+		bsta->tfd_queue_msk |= BIT(queue);
 	}
 
 	return 0;
@@ -1862,28 +1978,23 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvm->mutex);
 
-	if (vif->type == NL80211_IFTYPE_AP)
+	if (vif->type == NL80211_IFTYPE_AP ||
+	    vif->type == NL80211_IFTYPE_ADHOC)
 		iwl_mvm_disable_txq(mvm, vif->cab_queue, vif->cab_queue,
 				    IWL_MAX_TID_COUNT, 0);
 
-	if (mvmvif->bcast_sta.tfd_queue_msk &
-	    BIT(IWL_MVM_DQA_AP_PROBE_RESP_QUEUE)) {
-		iwl_mvm_disable_txq(mvm,
-				    IWL_MVM_DQA_AP_PROBE_RESP_QUEUE,
+	if (mvmvif->bcast_sta.tfd_queue_msk & BIT(mvm->probe_queue)) {
+		iwl_mvm_disable_txq(mvm, mvm->probe_queue,
 				    vif->hw_queue[0], IWL_MAX_TID_COUNT,
 				    0);
-		mvmvif->bcast_sta.tfd_queue_msk &=
-			~BIT(IWL_MVM_DQA_AP_PROBE_RESP_QUEUE);
+		mvmvif->bcast_sta.tfd_queue_msk &= ~BIT(mvm->probe_queue);
 	}
 
-	if (mvmvif->bcast_sta.tfd_queue_msk &
-	    BIT(IWL_MVM_DQA_P2P_DEVICE_QUEUE)) {
-		iwl_mvm_disable_txq(mvm,
-				    IWL_MVM_DQA_P2P_DEVICE_QUEUE,
+	if (mvmvif->bcast_sta.tfd_queue_msk & BIT(mvm->p2p_dev_queue)) {
+		iwl_mvm_disable_txq(mvm, mvm->p2p_dev_queue,
 				    vif->hw_queue[0], IWL_MAX_TID_COUNT,
 				    0);
-		mvmvif->bcast_sta.tfd_queue_msk &=
-			~BIT(IWL_MVM_DQA_P2P_DEVICE_QUEUE);
+		mvmvif->bcast_sta.tfd_queue_msk &= ~BIT(mvm->p2p_dev_queue);
 	}
 }
 
@@ -1925,7 +2036,8 @@ int iwl_mvm_alloc_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	}
 
 	return iwl_mvm_allocate_int_sta(mvm, &mvmvif->bcast_sta, qmask,
-					ieee80211_vif_type_p2p(vif));
+					ieee80211_vif_type_p2p(vif),
+					IWL_STA_GENERAL_PURPOSE);
 }
 
 /* Allocate a new station entry for the broadcast station to the given vif,
@@ -1979,6 +2091,101 @@ int iwl_mvm_rm_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	return ret;
 }
 
+/*
+ * Allocate a new station entry for the multicast station to the given vif,
+ * and send it to the FW.
+ * Note that each AP/GO mac should have its own multicast station.
+ *
+ * @mvm: the mvm component
+ * @vif: the interface to which the multicast station is added
+ */
+int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_mvm_int_sta *msta = &mvmvif->mcast_sta;
+	static const u8 _maddr[] = {0x03, 0x00, 0x00, 0x00, 0x00, 0x00};
+	const u8 *maddr = _maddr;
+	struct iwl_trans_txq_scd_cfg cfg = {
+		.fifo = IWL_MVM_TX_FIFO_MCAST,
+		.sta_id = msta->sta_id,
+		.tid = IWL_MAX_TID_COUNT,
+		.aggregate = false,
+		.frame_limit = IWL_FRAME_LIMIT,
+	};
+	unsigned int timeout = iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+	int ret;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (!iwl_mvm_is_dqa_supported(mvm))
+		return 0;
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_AP))
+		return -ENOTSUPP;
+
+	/*
+	 * While in previous FWs we had to exclude cab queue from TFD queue
+	 * mask, now it is needed as any other queue.
+	 */
+	if (!iwl_mvm_has_new_tx_api(mvm) &&
+	    fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE)) {
+		iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue, 0,
+				   &cfg, timeout);
+		msta->tfd_queue_msk |= BIT(vif->cab_queue);
+	}
+	ret = iwl_mvm_add_int_sta_common(mvm, msta, maddr,
+					 mvmvif->id, mvmvif->color);
+	if (ret) {
+		iwl_mvm_dealloc_int_sta(mvm, msta);
+		return ret;
+	}
+
+	/*
+	 * Enable cab queue after the ADD_STA command is sent.
+	 * This is needed for a000 firmware which won't accept SCD_QUEUE_CFG
+	 * command with unknown station id, and for FW that doesn't support
+	 * station API since the cab queue is not included in the
+	 * tfd_queue_mask.
+	 */
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		int queue = iwl_mvm_tvqm_enable_txq(mvm, vif->cab_queue,
+						    msta->sta_id,
+						    IWL_MAX_TID_COUNT,
+						    timeout);
+		mvmvif->cab_queue = queue;
+	} else if (!fw_has_api(&mvm->fw->ucode_capa,
+			       IWL_UCODE_TLV_API_STA_TYPE)) {
+		iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue, 0,
+				   &cfg, timeout);
+	}
+
+	return 0;
+}
+
+/*
+ * Send the FW a request to remove the station from it's internal data
+ * structures, and in addition remove it from the local data structure.
+ */
+int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	int ret;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (!iwl_mvm_is_dqa_supported(mvm))
+		return 0;
+
+	iwl_mvm_disable_txq(mvm, mvmvif->cab_queue, vif->cab_queue,
+			    IWL_MAX_TID_COUNT, 0);
+
+	ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id);
+	if (ret)
+		IWL_WARN(mvm, "Failed sending remove station\n");
+
+	return ret;
+}
+
 #define IWL_MAX_RX_BA_SESSIONS 16
 
 static void iwl_mvm_sync_rxq_del_ba(struct iwl_mvm *mvm, u8 baid)
@@ -2056,6 +2263,7 @@ static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 		reorder_buf->mvm = mvm;
 		reorder_buf->queue = i;
 		reorder_buf->sta_id = sta_id;
+		reorder_buf->valid = false;
 		for (j = 0; j < reorder_buf->buf_size; j++)
 			__skb_queue_head_init(&reorder_buf->entries[j]);
 	}
@@ -2223,7 +2431,9 @@ int iwl_mvm_sta_tx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	cmd.mac_id_n_color = cpu_to_le32(mvm_sta->mac_id_n_color);
 	cmd.sta_id = mvm_sta->sta_id;
 	cmd.add_modify = STA_MODE_MODIFY;
-	cmd.modify_mask = STA_MODIFY_QUEUES | STA_MODIFY_TID_DISABLE_TX;
+	if (!iwl_mvm_has_new_tx_api(mvm))
+		cmd.modify_mask = STA_MODIFY_QUEUES;
+	cmd.modify_mask |= STA_MODIFY_TID_DISABLE_TX;
 	cmd.tfd_queue_msk = cpu_to_le32(mvm_sta->tfd_queue_msk);
 	cmd.tid_disable_tx = cpu_to_le16(mvm_sta->tid_disable_agg);
 
@@ -2307,10 +2517,18 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	 *	one and mark it as reserved
 	 *  3. In DQA mode, but no traffic yet on this TID: same treatment as in
 	 *	non-DQA mode, since the TXQ hasn't yet been allocated
+	 * Don't support case 3 for new TX path as it is not expected to happen
+	 * and aggregation will be offloaded soon anyway
 	 */
 	txq_id = mvmsta->tid_data[tid].txq_id;
-	if (iwl_mvm_is_dqa_supported(mvm) &&
-	    unlikely(mvm->queue_info[txq_id].status == IWL_MVM_QUEUE_SHARED)) {
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		if (txq_id == IWL_MVM_INVALID_QUEUE) {
+			ret = -ENXIO;
+			goto release_locks;
+		}
+	} else if (iwl_mvm_is_dqa_supported(mvm) &&
+		   unlikely(mvm->queue_info[txq_id].status ==
+			    IWL_MVM_QUEUE_SHARED)) {
 		ret = -ENXIO;
 		IWL_DEBUG_TX_QUEUES(mvm,
 				    "Can't start tid %d agg on shared queue!\n",
@@ -2406,6 +2624,20 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	tid_data->amsdu_in_ampdu_allowed = amsdu;
 	spin_unlock_bh(&mvmsta->lock);
 
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		/*
+		 * If no queue iwl_mvm_sta_tx_agg_start() would have failed so
+		 * no need to check queue's status
+		 */
+		if (buf_size < mvmsta->max_agg_bufsize)
+			return -ENOTSUPP;
+
+		ret = iwl_mvm_sta_tx_agg(mvm, sta, tid, queue, true);
+		if (ret)
+			return -EIO;
+		goto out;
+	}
+
 	cfg.fifo = iwl_mvm_ac_to_tx_fifo[tid_to_mac80211_ac[tid]];
 
 	spin_lock_bh(&mvm->queue_info_lock);
@@ -2427,8 +2659,8 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			 * If reconfiguring an existing queue, it first must be
 			 * drained
 			 */
-			ret = iwl_trans_wait_tx_queue_empty(mvm->trans,
-							    BIT(queue));
+			ret = iwl_trans_wait_tx_queues_empty(mvm->trans,
+							     BIT(queue));
 			if (ret) {
 				IWL_ERR(mvm,
 					"Error draining queue before reconfig\n");
@@ -2463,6 +2695,7 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	mvm->queue_info[queue].status = IWL_MVM_QUEUE_READY;
 	spin_unlock_bh(&mvm->queue_info_lock);
 
+out:
 	/*
 	 * Even though in theory the peer could have different
 	 * aggregation reorder buffer sizes for different sessions,
@@ -2480,6 +2713,27 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.lq, false);
 }
 
+static void iwl_mvm_unreserve_agg_queue(struct iwl_mvm *mvm,
+					struct iwl_mvm_sta *mvmsta,
+					u16 txq_id)
+{
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return;
+
+	spin_lock_bh(&mvm->queue_info_lock);
+	/*
+	 * The TXQ is marked as reserved only if no traffic came through yet
+	 * This means no traffic has been sent on this TID (agg'd or not), so
+	 * we no longer have use for the queue. Since it hasn't even been
+	 * allocated through iwl_mvm_enable_txq, so we can just mark it back as
+	 * free.
+	 */
+	if (mvm->queue_info[txq_id].status == IWL_MVM_QUEUE_RESERVED)
+		mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_FREE;
+
+	spin_unlock_bh(&mvm->queue_info_lock);
+}
+
 int iwl_mvm_sta_tx_agg_stop(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			    struct ieee80211_sta *sta, u16 tid)
 {
@@ -2506,18 +2760,7 @@ int iwl_mvm_sta_tx_agg_stop(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	mvmsta->agg_tids &= ~BIT(tid);
 
-	spin_lock_bh(&mvm->queue_info_lock);
-	/*
-	 * The TXQ is marked as reserved only if no traffic came through yet
-	 * This means no traffic has been sent on this TID (agg'd or not), so
-	 * we no longer have use for the queue. Since it hasn't even been
-	 * allocated through iwl_mvm_enable_txq, so we can just mark it back as
-	 * free.
-	 */
-	if (mvm->queue_info[txq_id].status == IWL_MVM_QUEUE_RESERVED)
-		mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_FREE;
-
-	spin_unlock_bh(&mvm->queue_info_lock);
+	iwl_mvm_unreserve_agg_queue(mvm, mvmsta, txq_id);
 
 	switch (tid_data->state) {
 	case IWL_AGG_ON:
@@ -2597,24 +2840,14 @@ int iwl_mvm_sta_tx_agg_flush(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	mvmsta->agg_tids &= ~BIT(tid);
 	spin_unlock_bh(&mvmsta->lock);
 
-	spin_lock_bh(&mvm->queue_info_lock);
-	/*
-	 * The TXQ is marked as reserved only if no traffic came through yet
-	 * This means no traffic has been sent on this TID (agg'd or not), so
-	 * we no longer have use for the queue. Since it hasn't even been
-	 * allocated through iwl_mvm_enable_txq, so we can just mark it back as
-	 * free.
-	 */
-	if (mvm->queue_info[txq_id].status == IWL_MVM_QUEUE_RESERVED)
-		mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_FREE;
-	spin_unlock_bh(&mvm->queue_info_lock);
+	iwl_mvm_unreserve_agg_queue(mvm, mvmsta, txq_id);
 
 	if (old_state >= IWL_AGG_ON) {
 		iwl_mvm_drain_sta(mvm, mvmsta, true);
 		if (iwl_mvm_flush_tx_path(mvm, BIT(txq_id), 0))
 			IWL_ERR(mvm, "Couldn't flush the AGG queue\n");
-		iwl_trans_wait_tx_queue_empty(mvm->trans,
-					      mvmsta->tfd_queue_msk);
+		iwl_trans_wait_tx_queues_empty(mvm->trans,
+					       mvmsta->tfd_queue_msk);
 		iwl_mvm_drain_sta(mvm, mvmsta, false);
 
 		iwl_mvm_sta_tx_agg(mvm, sta, tid, txq_id, false);
@@ -2672,7 +2905,7 @@ static struct iwl_mvm_sta *iwl_mvm_get_key_sta(struct iwl_mvm *mvm,
 	 * station ID, then use AP's station ID.
 	 */
 	if (vif->type == NL80211_IFTYPE_STATION &&
-	    mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
+	    mvmvif->ap_sta_id != IWL_MVM_INVALID_STA) {
 		u8 sta_id = mvmvif->ap_sta_id;
 
 		sta = rcu_dereference_check(mvm->fw_id_to_mac_id[sta_id],
@@ -2694,68 +2927,97 @@ static struct iwl_mvm_sta *iwl_mvm_get_key_sta(struct iwl_mvm *mvm,
 
 static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 				struct iwl_mvm_sta *mvm_sta,
-				struct ieee80211_key_conf *keyconf, bool mcast,
+				struct ieee80211_key_conf *key, bool mcast,
 				u32 tkip_iv32, u16 *tkip_p1k, u32 cmd_flags,
 				u8 key_offset)
 {
-	struct iwl_mvm_add_sta_key_cmd cmd = {};
+	union {
+		struct iwl_mvm_add_sta_key_cmd_v1 cmd_v1;
+		struct iwl_mvm_add_sta_key_cmd cmd;
+	} u = {};
 	__le16 key_flags;
 	int ret;
 	u32 status;
 	u16 keyidx;
-	int i;
-	u8 sta_id = mvm_sta->sta_id;
+	u64 pn = 0;
+	int i, size;
+	bool new_api = fw_has_api(&mvm->fw->ucode_capa,
+				  IWL_UCODE_TLV_API_TKIP_MIC_KEYS);
 
-	keyidx = (keyconf->keyidx << STA_KEY_FLG_KEYID_POS) &
+	keyidx = (key->keyidx << STA_KEY_FLG_KEYID_POS) &
 		 STA_KEY_FLG_KEYID_MSK;
 	key_flags = cpu_to_le16(keyidx);
 	key_flags |= cpu_to_le16(STA_KEY_FLG_WEP_KEY_MAP);
 
-	switch (keyconf->cipher) {
+	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_TKIP:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_TKIP);
-		cmd.tkip_rx_tsc_byte2 = tkip_iv32;
-		for (i = 0; i < 5; i++)
-			cmd.tkip_rx_ttak[i] = cpu_to_le16(tkip_p1k[i]);
-		memcpy(cmd.key, keyconf->key, keyconf->keylen);
+		if (new_api) {
+			memcpy((void *)&u.cmd.tx_mic_key,
+			       &key->key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY],
+			       IWL_MIC_KEY_SIZE);
+
+			memcpy((void *)&u.cmd.rx_mic_key,
+			       &key->key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY],
+			       IWL_MIC_KEY_SIZE);
+			pn = atomic64_read(&key->tx_pn);
+
+		} else {
+			u.cmd_v1.tkip_rx_tsc_byte2 = tkip_iv32;
+			for (i = 0; i < 5; i++)
+				u.cmd_v1.tkip_rx_ttak[i] =
+					cpu_to_le16(tkip_p1k[i]);
+		}
+		memcpy(u.cmd.common.key, key->key, key->keylen);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_CCM);
-		memcpy(cmd.key, keyconf->key, keyconf->keylen);
+		memcpy(u.cmd.common.key, key->key, key->keylen);
+		if (new_api)
+			pn = atomic64_read(&key->tx_pn);
 		break;
 	case WLAN_CIPHER_SUITE_WEP104:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_WEP_13BYTES);
 		/* fall through */
 	case WLAN_CIPHER_SUITE_WEP40:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_WEP);
-		memcpy(cmd.key + 3, keyconf->key, keyconf->keylen);
+		memcpy(u.cmd.common.key + 3, key->key, key->keylen);
 		break;
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_KEY_32BYTES);
 		/* fall through */
 	case WLAN_CIPHER_SUITE_GCMP:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_GCMP);
-		memcpy(cmd.key, keyconf->key, keyconf->keylen);
+		memcpy(u.cmd.common.key, key->key, key->keylen);
+		if (new_api)
+			pn = atomic64_read(&key->tx_pn);
 		break;
 	default:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_EXT);
-		memcpy(cmd.key, keyconf->key, keyconf->keylen);
+		memcpy(u.cmd.common.key, key->key, key->keylen);
 	}
 
 	if (mcast)
 		key_flags |= cpu_to_le16(STA_KEY_MULTICAST);
 
-	cmd.key_offset = key_offset;
-	cmd.key_flags = key_flags;
-	cmd.sta_id = sta_id;
+	u.cmd.common.key_offset = key_offset;
+	u.cmd.common.key_flags = key_flags;
+	u.cmd.common.sta_id = mvm_sta->sta_id;
+
+	if (new_api) {
+		u.cmd.transmit_seq_cnt = cpu_to_le64(pn);
+		size = sizeof(u.cmd);
+	} else {
+		size = sizeof(u.cmd_v1);
+	}
 
 	status = ADD_STA_SUCCESS;
 	if (cmd_flags & CMD_ASYNC)
-		ret =  iwl_mvm_send_cmd_pdu(mvm, ADD_STA_KEY, CMD_ASYNC,
-					    sizeof(cmd), &cmd);
+		ret = iwl_mvm_send_cmd_pdu(mvm, ADD_STA_KEY, CMD_ASYNC, size,
+					   &u.cmd);
 	else
-		ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY, sizeof(cmd),
-						  &cmd, &status);
+		ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY, size,
+						  &u.cmd, &status);
 
 	switch (status) {
 	case ADD_STA_SUCCESS:
@@ -2855,7 +3117,7 @@ static inline u8 *iwl_mvm_get_mac_addr(struct iwl_mvm *mvm,
 		return sta->addr;
 
 	if (vif->type == NL80211_IFTYPE_STATION &&
-	    mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
+	    mvmvif->ap_sta_id != IWL_MVM_INVALID_STA) {
 		u8 sta_id = mvmvif->ap_sta_id;
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
 						lockdep_is_held(&mvm->mutex));
@@ -2908,9 +3170,14 @@ static int __iwl_mvm_remove_sta_key(struct iwl_mvm *mvm, u8 sta_id,
 				    struct ieee80211_key_conf *keyconf,
 				    bool mcast)
 {
-	struct iwl_mvm_add_sta_key_cmd cmd = {};
+	union {
+		struct iwl_mvm_add_sta_key_cmd_v1 cmd_v1;
+		struct iwl_mvm_add_sta_key_cmd cmd;
+	} u = {};
+	bool new_api = fw_has_api(&mvm->fw->ucode_capa,
+				  IWL_UCODE_TLV_API_TKIP_MIC_KEYS);
 	__le16 key_flags;
-	int ret;
+	int ret, size;
 	u32 status;
 
 	key_flags = cpu_to_le16((keyconf->keyidx << STA_KEY_FLG_KEYID_POS) &
@@ -2921,13 +3188,19 @@ static int __iwl_mvm_remove_sta_key(struct iwl_mvm *mvm, u8 sta_id,
 	if (mcast)
 		key_flags |= cpu_to_le16(STA_KEY_MULTICAST);
 
-	cmd.key_flags = key_flags;
-	cmd.key_offset = keyconf->hw_key_idx;
-	cmd.sta_id = sta_id;
+	/*
+	 * The fields assigned here are in the same location at the start
+	 * of the command, so we can do this union trick.
+	 */
+	u.cmd.common.key_flags = key_flags;
+	u.cmd.common.key_offset = keyconf->hw_key_idx;
+	u.cmd.common.sta_id = sta_id;
+
+	size = new_api ? sizeof(u.cmd) : sizeof(u.cmd_v1);
 
 	status = ADD_STA_SUCCESS;
-	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY, sizeof(cmd),
-					  &cmd, &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY, size, &u.cmd,
+					  &status);
 
 	switch (status) {
 	case ADD_STA_SUCCESS:
@@ -3041,7 +3314,7 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
 {
 	bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
 	struct iwl_mvm_sta *mvm_sta;
-	u8 sta_id = IWL_MVM_STATION_COUNT;
+	u8 sta_id = IWL_MVM_INVALID_STA;
 	int ret, i;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -3135,7 +3408,7 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 				       struct ieee80211_sta *sta,
 				       enum ieee80211_frame_release_type reason,
 				       u16 cnt, u16 tids, bool more_data,
-				       bool agg)
+				       bool single_sta_queue)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	struct iwl_mvm_add_sta_cmd cmd = {
@@ -3155,14 +3428,14 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 	for_each_set_bit(tid, &_tids, IWL_MAX_TID_COUNT)
 		cmd.awake_acs |= BIT(tid_to_ucode_ac[tid]);
 
-	/* If we're releasing frames from aggregation queues then check if the
-	 * all queues combined that we're releasing frames from have
+	/* If we're releasing frames from aggregation or dqa queues then check
+	 * if all the queues that we're releasing frames from, combined, have:
 	 *  - more frames than the service period, in which case more_data
 	 *    needs to be set
 	 *  - fewer than 'cnt' frames, in which case we need to adjust the
 	 *    firmware command (but do that unconditionally)
 	 */
-	if (agg) {
+	if (single_sta_queue) {
 		int remaining = cnt;
 		int sleep_tx_count;
 
@@ -3172,7 +3445,8 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 			u16 n_queued;
 
 			tid_data = &mvmsta->tid_data[tid];
-			if (WARN(tid_data->state != IWL_AGG_ON &&
+			if (WARN(!iwl_mvm_is_dqa_supported(mvm) &&
+				 tid_data->state != IWL_AGG_ON &&
 				 tid_data->state != IWL_EMPTYING_HW_QUEUE_DELBA,
 				 "TID %d state is %d\n",
 				 tid, tid_data->state)) {
@@ -3203,13 +3477,13 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 
 	/* Note: this is ignored by firmware not supporting GO uAPSD */
 	if (more_data)
-		cmd.sleep_state_flags |= cpu_to_le16(STA_SLEEP_STATE_MOREDATA);
+		cmd.sleep_state_flags |= STA_SLEEP_STATE_MOREDATA;
 
 	if (reason == IEEE80211_FRAME_RELEASE_PSPOLL) {
 		mvmsta->next_status_eosp = true;
-		cmd.sleep_state_flags |= cpu_to_le16(STA_SLEEP_STATE_PS_POLL);
+		cmd.sleep_state_flags |= STA_SLEEP_STATE_PS_POLL;
 	} else {
-		cmd.sleep_state_flags |= cpu_to_le16(STA_SLEEP_STATE_UAPSD);
+		cmd.sleep_state_flags |= STA_SLEEP_STATE_UAPSD;
 	}
 
 	/* block the Tx queues until the FW updated the sleep Tx count */
@@ -3286,6 +3560,27 @@ void iwl_mvm_sta_modify_disable_tx_ap(struct iwl_mvm *mvm,
 	spin_unlock_bh(&mvm_sta->lock);
 }
 
+static void iwl_mvm_int_sta_modify_disable_tx(struct iwl_mvm *mvm,
+					      struct iwl_mvm_vif *mvmvif,
+					      struct iwl_mvm_int_sta *sta,
+					      bool disable)
+{
+	u32 id = FW_CMD_ID_AND_COLOR(mvmvif->id, mvmvif->color);
+	struct iwl_mvm_add_sta_cmd cmd = {
+		.add_modify = STA_MODE_MODIFY,
+		.sta_id = sta->sta_id,
+		.station_flags = disable ? cpu_to_le32(STA_FLG_DISABLE_TX) : 0,
+		.station_flags_msk = cpu_to_le32(STA_FLG_DISABLE_TX),
+		.mac_id_n_color = cpu_to_le32(id),
+	};
+	int ret;
+
+	ret = iwl_mvm_send_cmd_pdu(mvm, ADD_STA, 0,
+				   iwl_mvm_add_sta_cmd_size(mvm), &cmd);
+	if (ret)
+		IWL_ERR(mvm, "Failed to send ADD_STA command (%d)\n", ret);
+}
+
 void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 				       struct iwl_mvm_vif *mvmvif,
 				       bool disable)
@@ -3297,7 +3592,7 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 	lockdep_assert_held(&mvm->mutex);
 
 	/* Block/unblock all the stations of the given mvmvif */
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i],
 						lockdep_is_held(&mvm->mutex));
 		if (IS_ERR_OR_NULL(sta))
@@ -3310,6 +3605,22 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 
 		iwl_mvm_sta_modify_disable_tx_ap(mvm, sta, disable);
 	}
+
+	if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE))
+		return;
+
+	/* Need to block/unblock also multicast station */
+	if (mvmvif->mcast_sta.sta_id != IWL_MVM_INVALID_STA)
+		iwl_mvm_int_sta_modify_disable_tx(mvm, mvmvif,
+						  &mvmvif->mcast_sta, disable);
+
+	/*
+	 * Only unblock the broadcast station (FW blocks it for immediate
+	 * quiet, not the driver)
+	 */
+	if (!disable && mvmvif->bcast_sta.sta_id != IWL_MVM_INVALID_STA)
+		iwl_mvm_int_sta_modify_disable_tx(mvm, mvmvif,
+						  &mvmvif->bcast_sta, disable);
 }
 
 void iwl_mvm_csa_client_absent(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 4be34f902278..2716cb5483bf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -380,6 +380,7 @@ struct iwl_mvm_rxq_dup_data {
  * @tid_disable_agg: bitmap: if bit(tid) is set, the fw won't send ampdus for
  *	tid.
  * @max_agg_bufsize: the maximal size of the AGG buffer for this station
+ * @sta_type: station type
  * @bt_reduced_txpower: is reduced tx power enabled for this station
  * @next_status_eosp: the next reclaimed packet is a PS-Poll response and
  *	we need to signal the EOSP
@@ -416,6 +417,7 @@ struct iwl_mvm_sta {
 	u32 mac_id_n_color;
 	u16 tid_disable_agg;
 	u8 max_agg_bufsize;
+	enum iwl_sta_type sta_type;
 	bool bt_reduced_txpower;
 	bool next_status_eosp;
 	spinlock_t lock;
@@ -453,10 +455,12 @@ iwl_mvm_sta_from_mac80211(struct ieee80211_sta *sta)
  * struct iwl_mvm_int_sta - representation of an internal station (auxiliary or
  * broadcast)
  * @sta_id: the index of the station in the fw (will be replaced by id_n_color)
+ * @type: station type
  * @tfd_queue_msk: the tfd queues used by the station
  */
 struct iwl_mvm_int_sta {
 	u32 sta_id;
+	enum iwl_sta_type type;
 	u32 tfd_queue_msk;
 };
 
@@ -532,10 +536,14 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_send_rm_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_rm_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_allocate_int_sta(struct iwl_mvm *mvm,
 			     struct iwl_mvm_int_sta *sta,
-				    u32 qmask, enum nl80211_iftype iftype);
+				    u32 qmask, enum nl80211_iftype iftype,
+				    enum iwl_sta_type type);
 void iwl_mvm_dealloc_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+void iwl_mvm_dealloc_int_sta(struct iwl_mvm *mvm, struct iwl_mvm_int_sta *sta);
 int iwl_mvm_add_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 void iwl_mvm_dealloc_snif_sta(struct iwl_mvm *mvm);
@@ -547,7 +555,7 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 				       struct ieee80211_sta *sta,
 				       enum ieee80211_frame_release_type reason,
 				       u16 cnt, u16 tids, bool more_data,
-				       bool agg);
+				       bool single_sta_queue);
 int iwl_mvm_drain_sta(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
 		      bool drain);
 void iwl_mvm_sta_modify_disable_tx(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
index 9f160fc58cd0..df7cd87199ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -78,7 +80,7 @@ void iwl_mvm_teardown_tdls_peers(struct iwl_mvm *mvm)
 
 	lockdep_assert_held(&mvm->mutex);
 
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i],
 						lockdep_is_held(&mvm->mutex));
 		if (!sta || IS_ERR(sta) || !sta->tdls)
@@ -101,7 +103,7 @@ int iwl_mvm_tdls_sta_count(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	lockdep_assert_held(&mvm->mutex);
 
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i],
 						lockdep_is_held(&mvm->mutex));
 		if (!sta || IS_ERR(sta) || !sta->tdls)
@@ -145,7 +147,7 @@ static void iwl_mvm_tdls_config(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	/* populate TDLS peer data */
 	cnt = 0;
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i],
 						lockdep_is_held(&mvm->mutex));
 		if (IS_ERR_OR_NULL(sta) || !sta->tdls)
@@ -251,7 +253,7 @@ static void iwl_mvm_tdls_update_cs_state(struct iwl_mvm *mvm,
 			iwl_read_prph(mvm->trans, DEVICE_SYSTEM_TIME_REG);
 
 	if (state == IWL_MVM_TDLS_SW_IDLE)
-		mvm->tdls_cs.cur_sta_id = IWL_MVM_STATION_COUNT;
+		mvm->tdls_cs.cur_sta_id = IWL_MVM_INVALID_STA;
 }
 
 void iwl_mvm_rx_tdls_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
@@ -305,7 +307,7 @@ iwl_mvm_tdls_check_action(struct iwl_mvm *mvm,
 
 	/* get the existing peer if it's there */
 	if (mvm->tdls_cs.state != IWL_MVM_TDLS_SW_IDLE &&
-	    mvm->tdls_cs.cur_sta_id != IWL_MVM_STATION_COUNT) {
+	    mvm->tdls_cs.cur_sta_id != IWL_MVM_INVALID_STA) {
 		struct ieee80211_sta *sta = rcu_dereference_protected(
 				mvm->fw_id_to_mac_id[mvm->tdls_cs.cur_sta_id],
 				lockdep_is_held(&mvm->mutex));
@@ -523,7 +525,7 @@ void iwl_mvm_tdls_ch_switch_work(struct work_struct *work)
 	iwl_mvm_tdls_update_cs_state(mvm, IWL_MVM_TDLS_SW_IDLE);
 
 	/* station might be gone, in that case do nothing */
-	if (mvm->tdls_cs.peer.sta_id == IWL_MVM_STATION_COUNT)
+	if (mvm->tdls_cs.peer.sta_id == IWL_MVM_INVALID_STA)
 		goto out;
 
 	sta = rcu_dereference_protected(
@@ -573,7 +575,7 @@ iwl_mvm_tdls_channel_switch(struct ieee80211_hw *hw,
 		       sta->addr, chandef->chan->center_freq, chandef->width);
 
 	/* we only support a single peer for channel switching */
-	if (mvm->tdls_cs.peer.sta_id != IWL_MVM_STATION_COUNT) {
+	if (mvm->tdls_cs.peer.sta_id != IWL_MVM_INVALID_STA) {
 		IWL_DEBUG_TDLS(mvm,
 			       "Existing peer. Can't start switch with %pM\n",
 			       sta->addr);
@@ -633,7 +635,7 @@ void iwl_mvm_tdls_cancel_channel_switch(struct ieee80211_hw *hw,
 	IWL_DEBUG_TDLS(mvm, "TDLS cancel channel switch with %pM\n", sta->addr);
 
 	/* we only support a single peer for channel switching */
-	if (mvm->tdls_cs.peer.sta_id == IWL_MVM_STATION_COUNT) {
+	if (mvm->tdls_cs.peer.sta_id == IWL_MVM_INVALID_STA) {
 		IWL_DEBUG_TDLS(mvm, "No ch switch peer - %pM\n", sta->addr);
 		goto out;
 	}
@@ -654,7 +656,7 @@ void iwl_mvm_tdls_cancel_channel_switch(struct ieee80211_hw *hw,
 	    mvm->tdls_cs.state != IWL_MVM_TDLS_SW_IDLE)
 		wait_for_phy = true;
 
-	mvm->tdls_cs.peer.sta_id = IWL_MVM_STATION_COUNT;
+	mvm->tdls_cs.peer.sta_id = IWL_MVM_INVALID_STA;
 	dev_kfree_skb(mvm->tdls_cs.peer.skb);
 	mvm->tdls_cs.peer.skb = NULL;
 
@@ -697,7 +699,7 @@ iwl_mvm_tdls_recv_channel_switch(struct ieee80211_hw *hw,
 	if (params->action_code == WLAN_TDLS_CHANNEL_SWITCH_RESPONSE &&
 	    params->status != 0 &&
 	    mvm->tdls_cs.state == IWL_MVM_TDLS_SW_REQ_SENT &&
-	    mvm->tdls_cs.cur_sta_id != IWL_MVM_STATION_COUNT) {
+	    mvm->tdls_cs.cur_sta_id != IWL_MVM_INVALID_STA) {
 		struct ieee80211_sta *cur_sta;
 
 		/* make sure it's the same peer */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tof.c b/drivers/net/wireless/intel/iwlwifi/mvm/tof.c
index a1947d6f3a2c..16ce8a56b5b9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tof.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tof.c
@@ -80,7 +80,7 @@ void iwl_mvm_tof_init(struct iwl_mvm *mvm)
 	if (IWL_MVM_TOF_IS_RESPONDER) {
 		tof_data->responder_cfg.sub_grp_cmd_id =
 			cpu_to_le32(TOF_RESPONDER_CONFIG_CMD);
-		tof_data->responder_cfg.sta_id = IWL_MVM_STATION_COUNT;
+		tof_data->responder_cfg.sta_id = IWL_MVM_INVALID_STA;
 	}
 #endif
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index bec7d9c46087..f9cbd197246f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -356,7 +356,7 @@ static void iwl_mvm_tt_tx_protection(struct iwl_mvm *mvm, bool enable)
 	struct iwl_mvm_sta *mvmsta;
 	int i, err;
 
-	for (i = 0; i < IWL_MVM_STATION_COUNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
 		mvmsta = iwl_mvm_sta_from_staid_protected(mvm, i);
 		if (!mvmsta)
 			continue;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index dd2b4a300819..bcaceb64a6e8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,6 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -474,6 +475,39 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 
 	memset(dev_cmd, 0, sizeof(*dev_cmd));
 	dev_cmd->hdr.cmd = TX_CMD;
+
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		struct iwl_tx_cmd_gen2 *cmd = (void *)dev_cmd->payload;
+		u16 offload_assist = iwl_mvm_tx_csum(mvm, skb, hdr, info);
+
+		/* padding is inserted later in transport */
+		/* FIXME - check for AMSDU may need to be removed */
+		if (ieee80211_hdrlen(hdr->frame_control) % 4 &&
+		    !(offload_assist & BIT(TX_CMD_OFFLD_AMSDU)))
+			offload_assist |= BIT(TX_CMD_OFFLD_PAD);
+
+		cmd->offload_assist |= cpu_to_le16(offload_assist);
+
+		/* Total # bytes to be transmitted */
+		cmd->len = cpu_to_le16((u16)skb->len);
+
+		/* Copy MAC header from skb into command buffer */
+		memcpy(cmd->hdr, hdr, hdrlen);
+
+		if (!info->control.hw_key)
+			cmd->flags |= cpu_to_le32(IWL_TX_FLAGS_ENCRYPT_DIS);
+
+		/* For data packets rate info comes from the fw */
+		if (ieee80211_is_data(hdr->frame_control) && sta)
+			goto out;
+
+		cmd->flags |= cpu_to_le32(IWL_TX_FLAGS_CMD_RATE);
+		cmd->rate_n_flags =
+			cpu_to_le32(iwl_mvm_get_tx_rate(mvm, info, sta));
+
+		goto out;
+	}
+
 	tx_cmd = (struct iwl_tx_cmd *)dev_cmd->payload;
 
 	if (info->control.hw_key)
@@ -483,6 +517,10 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 
 	iwl_mvm_set_tx_cmd_rate(mvm, tx_cmd, info, sta, hdr->frame_control);
 
+	/* Copy MAC header from skb into command buffer */
+	memcpy(tx_cmd->hdr, hdr, hdrlen);
+
+out:
 	return dev_cmd;
 }
 
@@ -505,6 +543,7 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm,
 
 	switch (info->control.vif->type) {
 	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_ADHOC:
 		/*
 		 * Handle legacy hostapd as well, where station may be added
 		 * only after assoc. Take care of the case where we send a
@@ -512,20 +551,21 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm,
 		 */
 		if (ieee80211_is_probe_resp(fc) || ieee80211_is_auth(fc) ||
 		    ieee80211_is_deauth(fc))
-			return IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
+			return mvm->probe_queue;
 		if (info->hw_queue == info->control.vif->cab_queue)
 			return info->hw_queue;
 
-		WARN_ONCE(1, "fc=0x%02x", le16_to_cpu(fc));
-		return IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
+		WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC,
+			  "fc=0x%02x", le16_to_cpu(fc));
+		return mvm->probe_queue;
 	case NL80211_IFTYPE_P2P_DEVICE:
 		if (ieee80211_is_mgmt(fc))
-			return IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+			return mvm->p2p_dev_queue;
 		if (info->hw_queue == info->control.vif->cab_queue)
 			return info->hw_queue;
 
 		WARN_ON_ONCE(1);
-		return IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+		return mvm->p2p_dev_queue;
 	default:
 		WARN_ONCE(1, "Not a ctrl vif, no available queue\n");
 		return -1;
@@ -538,7 +578,6 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 	struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_info info;
 	struct iwl_device_cmd *dev_cmd;
-	struct iwl_tx_cmd *tx_cmd;
 	u8 sta_id;
 	int hdrlen = ieee80211_hdrlen(hdr->frame_control);
 	int queue;
@@ -583,18 +622,21 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 			iwl_mvm_vif_from_mac80211(info.control.vif);
 
 		if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE ||
-		    info.control.vif->type == NL80211_IFTYPE_AP) {
+		    info.control.vif->type == NL80211_IFTYPE_AP ||
+		    info.control.vif->type == NL80211_IFTYPE_ADHOC) {
 			sta_id = mvmvif->bcast_sta.sta_id;
 			queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info,
 							   hdr->frame_control);
 			if (queue < 0)
 				return -1;
 
+			if (queue == info.control.vif->cab_queue)
+				queue = mvmvif->cab_queue;
 		} else if (info.control.vif->type == NL80211_IFTYPE_STATION &&
 			   is_multicast_ether_addr(hdr->addr1)) {
 			u8 ap_sta_id = ACCESS_ONCE(mvmvif->ap_sta_id);
 
-			if (ap_sta_id != IWL_MVM_STATION_COUNT)
+			if (ap_sta_id != IWL_MVM_INVALID_STA)
 				sta_id = ap_sta_id;
 		} else if (iwl_mvm_is_dqa_supported(mvm) &&
 			   info.control.vif->type == NL80211_IFTYPE_STATION &&
@@ -612,11 +654,6 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 	/* From now on, we cannot access info->control */
 	iwl_mvm_skb_prepare_status(skb, dev_cmd);
 
-	tx_cmd = (struct iwl_tx_cmd *)dev_cmd->payload;
-
-	/* Copy MAC header from skb into command buffer */
-	memcpy(tx_cmd->hdr, hdr, hdrlen);
-
 	if (iwl_trans_tx(mvm->trans, skb, dev_cmd, queue)) {
 		iwl_trans_free_tx_cmd(mvm->trans, dev_cmd);
 		return -1;
@@ -628,8 +665,10 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 	 * values.
 	 * Note that we don't need to make sure it isn't agg'd, since we're
 	 * TXing non-sta
+	 * For DQA mode - we shouldn't increase it though
 	 */
-	atomic_inc(&mvm->pending_frames[sta_id]);
+	if (!iwl_mvm_is_dqa_supported(mvm))
+		atomic_inc(&mvm->pending_frames[sta_id]);
 
 	return 0;
 }
@@ -707,7 +746,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb,
 	 * fifo to be able to send bursts.
 	 */
 	max_amsdu_len = min_t(unsigned int, max_amsdu_len,
-			      mvm->shared_mem_cfg.txfifo_size[txf] - 256);
+			      mvm->smem_cfg.lmac[0].txfifo_size[txf] - 256);
 
 	if (unlikely(dbg_max_amsdu_len))
 		max_amsdu_len = min_t(unsigned int, max_amsdu_len,
@@ -856,6 +895,9 @@ static bool iwl_mvm_txq_should_update(struct iwl_mvm *mvm, int txq_id)
 	unsigned long now = jiffies;
 	int tid;
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return false;
+
 	for_each_set_bit(tid, &queue_tid_bitmap, IWL_MAX_TID_COUNT + 1) {
 		if (time_before(mvm->queue_info[txq_id].last_frame_time[tid] +
 				IWL_MVM_DQA_QUEUE_TIMEOUT, now))
@@ -875,11 +917,10 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_mvm_sta *mvmsta;
 	struct iwl_device_cmd *dev_cmd;
-	struct iwl_tx_cmd *tx_cmd;
 	__le16 fc;
 	u16 seq_number = 0;
 	u8 tid = IWL_MAX_TID_COUNT;
-	u8 txq_id = info->hw_queue;
+	u16 txq_id = info->hw_queue;
 	bool is_ampdu = false;
 	int hdrlen;
 
@@ -890,7 +931,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (WARN_ON_ONCE(!mvmsta))
 		return -1;
 
-	if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_STATION_COUNT))
+	if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_INVALID_STA))
 		return -1;
 
 	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, info, hdrlen,
@@ -898,8 +939,6 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (!dev_cmd)
 		goto drop;
 
-	tx_cmd = (struct iwl_tx_cmd *)dev_cmd->payload;
-
 	/*
 	 * we handle that entirely ourselves -- for uAPSD the firmware
 	 * will always send a notification, and for PS-Poll responses
@@ -920,18 +959,27 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 		if (WARN_ON_ONCE(tid >= IWL_MAX_TID_COUNT))
 			goto drop_unlock_sta;
 
-		seq_number = mvmsta->tid_data[tid].seq_number;
-		seq_number &= IEEE80211_SCTL_SEQ;
-		hdr->seq_ctrl &= cpu_to_le16(IEEE80211_SCTL_FRAG);
-		hdr->seq_ctrl |= cpu_to_le16(seq_number);
 		is_ampdu = info->flags & IEEE80211_TX_CTL_AMPDU;
 		if (WARN_ON_ONCE(is_ampdu &&
 				 mvmsta->tid_data[tid].state != IWL_AGG_ON))
 			goto drop_unlock_sta;
+
+		seq_number = mvmsta->tid_data[tid].seq_number;
+		seq_number &= IEEE80211_SCTL_SEQ;
+
+		if (!iwl_mvm_has_new_tx_api(mvm)) {
+			struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+
+			hdr->seq_ctrl &= cpu_to_le16(IEEE80211_SCTL_FRAG);
+			hdr->seq_ctrl |= cpu_to_le16(seq_number);
+			/* update the tx_cmd hdr as it was already copied */
+			tx_cmd->hdr->seq_ctrl = hdr->seq_ctrl;
+		}
 	}
 
 	if (iwl_mvm_is_dqa_supported(mvm) || is_ampdu)
 		txq_id = mvmsta->tid_data[tid].txq_id;
+
 	if (sta->tdls && !iwl_mvm_is_dqa_supported(mvm)) {
 		/* default to TID 0 for non-QoS packets */
 		u8 tdls_tid = tid == IWL_MAX_TID_COUNT ? 0 : tid;
@@ -939,17 +987,14 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 		txq_id = mvmsta->hw_queue[tid_to_mac80211_ac[tdls_tid]];
 	}
 
-	/* Copy MAC header from skb into command buffer */
-	memcpy(tx_cmd->hdr, hdr, hdrlen);
-
 	WARN_ON_ONCE(info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM);
 
 	/* Check if TXQ needs to be allocated or re-activated */
-	if (unlikely(txq_id == IEEE80211_INVAL_HW_QUEUE ||
+	if (unlikely(txq_id == IWL_MVM_INVALID_QUEUE ||
 		     !mvmsta->tid_data[tid].is_tid_active) &&
 	    iwl_mvm_is_dqa_supported(mvm)) {
 		/* If TXQ needs to be allocated... */
-		if (txq_id == IEEE80211_INVAL_HW_QUEUE) {
+		if (txq_id == IWL_MVM_INVALID_QUEUE) {
 			iwl_mvm_tx_add_stream(mvm, mvmsta, tid, skb);
 
 			/*
@@ -961,6 +1006,9 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 			return 0;
 		}
 
+		/* queue should always be active in new TX path */
+		WARN_ON(iwl_mvm_has_new_tx_api(mvm));
+
 		/* If we are here - TXQ exists and needs to be re-activated */
 		spin_lock(&mvm->queue_info_lock);
 		mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_READY;
@@ -971,7 +1019,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 				    txq_id);
 	}
 
-	if (iwl_mvm_is_dqa_supported(mvm)) {
+	if (iwl_mvm_is_dqa_supported(mvm) && !iwl_mvm_has_new_tx_api(mvm)) {
 		/* Keep track of the time of the last frame for this RA/TID */
 		mvm->queue_info[txq_id].last_frame_time[tid] = jiffies;
 
@@ -1005,11 +1053,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 
 	spin_unlock(&mvmsta->lock);
 
-	/* Increase pending frames count if this isn't AMPDU */
-	if ((iwl_mvm_is_dqa_supported(mvm) &&
-	     mvmsta->tid_data[tx_cmd->tid_tspec].state != IWL_AGG_ON &&
-	     mvmsta->tid_data[tx_cmd->tid_tspec].state != IWL_AGG_STARTING) ||
-	    (!iwl_mvm_is_dqa_supported(mvm) && !is_ampdu))
+	/* Increase pending frames count if this isn't AMPDU or DQA queue */
+	if (!iwl_mvm_is_dqa_supported(mvm) && !is_ampdu)
 		atomic_inc(&mvm->pending_frames[mvmsta->sta_id]);
 
 	return 0;
@@ -1033,7 +1078,7 @@ int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (WARN_ON_ONCE(!mvmsta))
 		return -1;
 
-	if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_STATION_COUNT))
+	if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_INVALID_STA))
 		return -1;
 
 	memcpy(&info, skb->cb, sizeof(info));
@@ -1079,12 +1124,13 @@ static void iwl_mvm_check_ratid_empty(struct iwl_mvm *mvm,
 	lockdep_assert_held(&mvmsta->lock);
 
 	if ((tid_data->state == IWL_AGG_ON ||
-	     tid_data->state == IWL_EMPTYING_HW_QUEUE_DELBA) &&
+	     tid_data->state == IWL_EMPTYING_HW_QUEUE_DELBA ||
+	     iwl_mvm_is_dqa_supported(mvm)) &&
 	    iwl_mvm_tid_queued(tid_data) == 0) {
 		/*
-		 * Now that this aggregation queue is empty tell mac80211 so it
-		 * knows we no longer have frames buffered for the station on
-		 * this TID (for the TIM bitmap calculation.)
+		 * Now that this aggregation or DQA queue is empty tell
+		 * mac80211 so it knows we no longer have frames buffered for
+		 * the station on this TID (for the TIM bitmap calculation.)
 		 */
 		ieee80211_sta_set_buffered(sta, tid, false);
 	}
@@ -1241,6 +1287,26 @@ static void iwl_mvm_tx_status_check_trigger(struct iwl_mvm *mvm,
 	}
 }
 
+/**
+ * iwl_mvm_get_scd_ssn - returns the SSN of the SCD
+ * @tx_resp: the Tx response from the fw (agg or non-agg)
+ *
+ * When the fw sends an AMPDU, it fetches the MPDUs one after the other. Since
+ * it can't know that everything will go well until the end of the AMPDU, it
+ * can't know in advance the number of MPDUs that will be sent in the current
+ * batch. This is why it writes the agg Tx response while it fetches the MPDUs.
+ * Hence, it can't know in advance what the SSN of the SCD will be at the end
+ * of the batch. This is why the SSN of the SCD is written at the end of the
+ * whole struct at a variable offset. This function knows how to cope with the
+ * variable offset and returns the SSN of the SCD.
+ */
+static inline u32 iwl_mvm_get_scd_ssn(struct iwl_mvm *mvm,
+				      struct iwl_mvm_tx_resp *tx_resp)
+{
+	return le32_to_cpup((__le32 *)iwl_mvm_get_agg_status(mvm, tx_resp) +
+			    tx_resp->frame_count) & 0xfff;
+}
+
 static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 				     struct iwl_rx_packet *pkt)
 {
@@ -1250,17 +1316,21 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 	struct iwl_mvm_tx_resp *tx_resp = (void *)pkt->data;
 	int sta_id = IWL_MVM_TX_RES_GET_RA(tx_resp->ra_tid);
 	int tid = IWL_MVM_TX_RES_GET_TID(tx_resp->ra_tid);
-	u32 status = le16_to_cpu(tx_resp->status.status);
-	u16 ssn = iwl_mvm_get_scd_ssn(tx_resp);
+	struct agg_tx_status *agg_status =
+		iwl_mvm_get_agg_status(mvm, tx_resp);
+	u32 status = le16_to_cpu(agg_status->status);
+	u16 ssn = iwl_mvm_get_scd_ssn(mvm, tx_resp);
 	struct iwl_mvm_sta *mvmsta;
 	struct sk_buff_head skbs;
 	u8 skb_freed = 0;
 	u16 next_reclaimed, seq_ctl;
 	bool is_ndp = false;
-	bool txq_agg = false; /* Is this TXQ aggregated */
 
 	__skb_queue_head_init(&skbs);
 
+	if (iwl_mvm_has_new_tx_api(mvm))
+		txq_id = le16_to_cpu(tx_resp->v6.tx_queue);
+
 	seq_ctl = le16_to_cpu(tx_resp->seq_ctl);
 
 	/* we can free until ssn % q.n_bd not inclusive */
@@ -1283,6 +1353,10 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 			info->flags |= IEEE80211_TX_STAT_ACK;
 			break;
 		case TX_STATUS_FAIL_DEST_PS:
+			/* In DQA, the FW should have stopped the queue and not
+			 * return this status
+			 */
+			WARN_ON(iwl_mvm_is_dqa_supported(mvm));
 			info->flags |= IEEE80211_TX_STAT_TX_FILTERED;
 			break;
 		default:
@@ -1381,21 +1455,12 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 	if (!IS_ERR(sta)) {
 		mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
-		if (tid != IWL_TID_NON_QOS) {
+		if (tid != IWL_TID_NON_QOS && tid != IWL_MGMT_TID) {
 			struct iwl_mvm_tid_data *tid_data =
 				&mvmsta->tid_data[tid];
 			bool send_eosp_ndp = false;
 
 			spin_lock_bh(&mvmsta->lock);
-			if (iwl_mvm_is_dqa_supported(mvm)) {
-				enum iwl_mvm_agg_state state;
-
-				state = mvmsta->tid_data[tid].state;
-				txq_agg = (state == IWL_AGG_ON ||
-					state == IWL_EMPTYING_HW_QUEUE_DELBA);
-			} else {
-				txq_agg = txq_id >= mvm->first_agg_queue;
-			}
 
 			if (!is_ndp) {
 				tid_data->next_reclaimed = next_reclaimed;
@@ -1452,11 +1517,11 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 	 * If the txq is not an AMPDU queue, there is no chance we freed
 	 * several skbs. Check that out...
 	 */
-	if (txq_agg)
+	if (iwl_mvm_is_dqa_supported(mvm) || txq_id >= mvm->first_agg_queue)
 		goto out;
 
 	/* We can't free more than one frame at once on a shared queue */
-	WARN_ON(!iwl_mvm_is_dqa_supported(mvm) && (skb_freed > 1));
+	WARN_ON(skb_freed > 1);
 
 	/* If we have still frames for this STA nothing to do here */
 	if (!atomic_sub_and_test(skb_freed, &mvm->pending_frames[sta_id]))
@@ -1522,7 +1587,8 @@ static void iwl_mvm_rx_tx_cmd_agg_dbg(struct iwl_mvm *mvm,
 				      struct iwl_rx_packet *pkt)
 {
 	struct iwl_mvm_tx_resp *tx_resp = (void *)pkt->data;
-	struct agg_tx_status *frame_status = &tx_resp->status;
+	struct agg_tx_status *frame_status =
+		iwl_mvm_get_agg_status(mvm, tx_resp);
 	int i;
 
 	for (i = 0; i < tx_resp->frame_count; i++) {
@@ -1724,6 +1790,9 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 		ba_info.status.status_driver_data[0] =
 			(void *)(uintptr_t)ba_res->reduced_txp;
 
+		if (!le16_to_cpu(ba_res->tfd_cnt))
+			goto out;
+
 		/*
 		 * TODO:
 		 * When supporting multi TID aggregations - we need to move
@@ -1732,12 +1801,16 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 		 * This will go together with SN and AddBA offload and cannot
 		 * be handled properly for now.
 		 */
-		WARN_ON(le16_to_cpu(ba_res->tfd_cnt) != 1);
-		iwl_mvm_tx_reclaim(mvm, sta_id, ba_res->ra_tid[0].tid,
-				   (int)ba_res->tfd[0].q_num,
+		WARN_ON(le16_to_cpu(ba_res->ra_tid_cnt) != 1);
+		tid = ba_res->ra_tid[0].tid;
+		if (tid == IWL_MGMT_TID)
+			tid = IWL_MAX_TID_COUNT;
+		iwl_mvm_tx_reclaim(mvm, sta_id, tid,
+				   (int)(le16_to_cpu(ba_res->tfd[0].q_num)),
 				   le16_to_cpu(ba_res->tfd[0].tfd_index),
 				   &ba_info, le32_to_cpu(ba_res->tx_rate));
 
+out:
 		IWL_DEBUG_TX_REPLY(mvm,
 				   "BA_NOTIFICATION Received from sta_id = %d, flags %x, sent:%d, acked:%d\n",
 				   sta_id, le32_to_cpu(ba_res->flags),
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index dedea96a8e0f..8f4f176e204e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright (C) 2015 Intel Deutschland GmbH
+ * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,6 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -591,6 +592,10 @@ int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id, u8 minq, u8 maxq)
 
 	lockdep_assert_held(&mvm->queue_info_lock);
 
+	/* This should not be hit with new TX path */
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -ENOSPC;
+
 	/* Start by looking for a free queue */
 	for (i = minq; i <= maxq; i++)
 		if (mvm->queue_info[i].hw_queue_refcount == 0 &&
@@ -627,6 +632,9 @@ int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id,
 	};
 	int ret;
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return -EINVAL;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	if (WARN(mvm->queue_info[queue].hw_queue_refcount == 0,
 		 "Trying to reconfig unallocated queue %d\n", queue)) {
@@ -644,50 +652,94 @@ int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id,
 	return ret;
 }
 
-void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
-			u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg,
-			unsigned int wdg_timeout)
+static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, int queue,
+				       int mac80211_queue, u8 sta_id, u8 tid)
 {
 	bool enable_queue = true;
 
 	spin_lock_bh(&mvm->queue_info_lock);
 
 	/* Make sure this TID isn't already enabled */
-	if (mvm->queue_info[queue].tid_bitmap & BIT(cfg->tid)) {
+	if (mvm->queue_info[queue].tid_bitmap & BIT(tid)) {
 		spin_unlock_bh(&mvm->queue_info_lock);
 		IWL_ERR(mvm, "Trying to enable TXQ %d with existing TID %d\n",
-			queue, cfg->tid);
-		return;
+			queue, tid);
+		return false;
 	}
 
 	/* Update mappings and refcounts */
 	if (mvm->queue_info[queue].hw_queue_refcount > 0)
 		enable_queue = false;
 
-	mvm->queue_info[queue].hw_queue_to_mac80211 |= BIT(mac80211_queue);
+	mvm->hw_queue_to_mac80211[queue] |= BIT(mac80211_queue);
+
 	mvm->queue_info[queue].hw_queue_refcount++;
-	mvm->queue_info[queue].tid_bitmap |= BIT(cfg->tid);
-	mvm->queue_info[queue].ra_sta_id = cfg->sta_id;
+	mvm->queue_info[queue].tid_bitmap |= BIT(tid);
+	mvm->queue_info[queue].ra_sta_id = sta_id;
 
 	if (enable_queue) {
-		if (cfg->tid != IWL_MAX_TID_COUNT)
+		if (tid != IWL_MAX_TID_COUNT)
 			mvm->queue_info[queue].mac80211_ac =
-				tid_to_mac80211_ac[cfg->tid];
+				tid_to_mac80211_ac[tid];
 		else
 			mvm->queue_info[queue].mac80211_ac = IEEE80211_AC_VO;
 
-		mvm->queue_info[queue].txq_tid = cfg->tid;
+		mvm->queue_info[queue].txq_tid = tid;
 	}
 
 	IWL_DEBUG_TX_QUEUES(mvm,
 			    "Enabling TXQ #%d refcount=%d (mac80211 map:0x%x)\n",
 			    queue, mvm->queue_info[queue].hw_queue_refcount,
-			    mvm->queue_info[queue].hw_queue_to_mac80211);
+			    mvm->hw_queue_to_mac80211[queue]);
 
 	spin_unlock_bh(&mvm->queue_info_lock);
 
+	return enable_queue;
+}
+
+int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, int mac80211_queue,
+			    u8 sta_id, u8 tid, unsigned int timeout)
+{
+	struct iwl_tx_queue_cfg_cmd cmd = {
+		.flags = cpu_to_le16(TX_QUEUE_CFG_ENABLE_QUEUE),
+		.sta_id = sta_id,
+		.tid = tid,
+	};
+	int queue;
+
+	if (cmd.tid == IWL_MAX_TID_COUNT)
+		cmd.tid = IWL_MGMT_TID;
+	queue = iwl_trans_txq_alloc(mvm->trans, (void *)&cmd,
+				    SCD_QUEUE_CFG, timeout);
+
+	if (queue < 0) {
+		IWL_DEBUG_TX_QUEUES(mvm,
+				    "Failed allocating TXQ for sta %d tid %d, ret: %d\n",
+				    sta_id, tid, queue);
+		return queue;
+	}
+
+	IWL_DEBUG_TX_QUEUES(mvm, "Enabling TXQ #%d for sta %d tid %d\n",
+			    queue, sta_id, tid);
+
+	mvm->hw_queue_to_mac80211[queue] |= BIT(mac80211_queue);
+	IWL_DEBUG_TX_QUEUES(mvm,
+			    "Enabling TXQ #%d (mac80211 map:0x%x)\n",
+			    queue, mvm->hw_queue_to_mac80211[queue]);
+
+	return queue;
+}
+
+void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
+			u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg,
+			unsigned int wdg_timeout)
+{
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return;
+
 	/* Send the enabling command if we need to */
-	if (enable_queue) {
+	if (iwl_mvm_update_txq_mapping(mvm, queue, mac80211_queue,
+				       cfg->sta_id, cfg->tid)) {
 		struct iwl_scd_txq_cfg_cmd cmd = {
 			.scd_queue = queue,
 			.action = SCD_CFG_ENABLE_QUEUE,
@@ -701,7 +753,8 @@ void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 
 		iwl_trans_txq_enable_cfg(mvm->trans, queue, ssn, NULL,
 					 wdg_timeout);
-		WARN(iwl_mvm_send_cmd_pdu(mvm, SCD_QUEUE_CFG, 0, sizeof(cmd),
+		WARN(iwl_mvm_send_cmd_pdu(mvm, SCD_QUEUE_CFG, 0,
+					  sizeof(struct iwl_scd_txq_cfg_cmd),
 					  &cmd),
 		     "Failed to configure queue %d on FIFO %d\n", queue,
 		     cfg->fifo);
@@ -718,6 +771,16 @@ int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 	bool remove_mac_queue = true;
 	int ret;
 
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		spin_lock_bh(&mvm->queue_info_lock);
+		mvm->hw_queue_to_mac80211[queue] &= ~BIT(mac80211_queue);
+		spin_unlock_bh(&mvm->queue_info_lock);
+
+		iwl_trans_txq_free(mvm->trans, queue);
+
+		return 0;
+	}
+
 	spin_lock_bh(&mvm->queue_info_lock);
 
 	if (WARN_ON(mvm->queue_info[queue].hw_queue_refcount == 0)) {
@@ -744,7 +807,7 @@ int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 	}
 
 	if (remove_mac_queue)
-		mvm->queue_info[queue].hw_queue_to_mac80211 &=
+		mvm->hw_queue_to_mac80211[queue] &=
 			~BIT(mac80211_queue);
 	mvm->queue_info[queue].hw_queue_refcount--;
 
@@ -757,7 +820,7 @@ int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 			    "Disabling TXQ #%d refcount=%d (mac80211 map:0x%x)\n",
 			    queue,
 			    mvm->queue_info[queue].hw_queue_refcount,
-			    mvm->queue_info[queue].hw_queue_to_mac80211);
+			    mvm->hw_queue_to_mac80211[queue]);
 
 	/* If the queue is still enabled - nothing left to do in this func */
 	if (cmd.action == SCD_CFG_ENABLE_QUEUE) {
@@ -771,16 +834,16 @@ int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 	/* Make sure queue info is correct even though we overwrite it */
 	WARN(mvm->queue_info[queue].hw_queue_refcount ||
 	     mvm->queue_info[queue].tid_bitmap ||
-	     mvm->queue_info[queue].hw_queue_to_mac80211,
+	     mvm->hw_queue_to_mac80211[queue],
 	     "TXQ #%d info out-of-sync - refcount=%d, mac map=0x%x, tid=0x%x\n",
 	     queue, mvm->queue_info[queue].hw_queue_refcount,
-	     mvm->queue_info[queue].hw_queue_to_mac80211,
+	     mvm->hw_queue_to_mac80211[queue],
 	     mvm->queue_info[queue].tid_bitmap);
 
 	/* If we are here - the queue is freed and we can zero out these vals */
 	mvm->queue_info[queue].hw_queue_refcount = 0;
 	mvm->queue_info[queue].tid_bitmap = 0;
-	mvm->queue_info[queue].hw_queue_to_mac80211 = 0;
+	mvm->hw_queue_to_mac80211[queue] = 0;
 
 	/* Regardless if this is a reserved TXQ for a STA - mark it as false */
 	mvm->queue_info[queue].reserved = false;
@@ -789,11 +852,11 @@ int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 
 	iwl_trans_txq_disable(mvm->trans, queue, false);
 	ret = iwl_mvm_send_cmd_pdu(mvm, SCD_QUEUE_CFG, flags,
-				   sizeof(cmd), &cmd);
+				   sizeof(struct iwl_scd_txq_cfg_cmd), &cmd);
+
 	if (ret)
 		IWL_ERR(mvm, "Failed to disable queue %d (ret=%d)\n",
 			queue, ret);
-
 	return ret;
 }
 
@@ -816,7 +879,7 @@ int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool init)
 		.data = { lq, },
 	};
 
-	if (WARN_ON(lq->sta_id == IWL_MVM_STATION_COUNT))
+	if (WARN_ON(lq->sta_id == IWL_MVM_INVALID_STA))
 		return -EINVAL;
 
 	return iwl_mvm_send_cmd(mvm, &cmd);
@@ -1006,6 +1069,35 @@ struct ieee80211_vif *iwl_mvm_get_bss_vif(struct iwl_mvm *mvm)
 	return bss_iter_data.vif;
 }
 
+struct iwl_sta_iter_data {
+	bool assoc;
+};
+
+static void iwl_mvm_sta_iface_iterator(void *_data, u8 *mac,
+				       struct ieee80211_vif *vif)
+{
+	struct iwl_sta_iter_data *data = _data;
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	if (vif->bss_conf.assoc)
+		data->assoc = true;
+}
+
+bool iwl_mvm_is_vif_assoc(struct iwl_mvm *mvm)
+{
+	struct iwl_sta_iter_data data = {
+		.assoc = false,
+	};
+
+	ieee80211_iterate_active_interfaces_atomic(mvm->hw,
+						   IEEE80211_IFACE_ITER_NORMAL,
+						   iwl_mvm_sta_iface_iterator,
+						   &data);
+	return data.assoc;
+}
+
 unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm,
 				    struct ieee80211_vif *vif,
 				    bool tdls, bool cmd_q)
@@ -1088,6 +1180,9 @@ static void iwl_mvm_remove_inactive_tids(struct iwl_mvm *mvm,
 	lockdep_assert_held(&mvmsta->lock);
 	lockdep_assert_held(&mvm->queue_info_lock);
 
+	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
+		return;
+
 	/* Go over all non-active TIDs, incl. IWL_MAX_TID_COUNT (for mgmt) */
 	for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) {
 		/* If some TFDs are still queued - don't mark TID as inactive */
@@ -1114,8 +1209,8 @@ static void iwl_mvm_remove_inactive_tids(struct iwl_mvm *mvm,
 	for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) {
 		int mac_queue = mvmsta->vif->hw_queue[tid_to_mac80211_ac[tid]];
 
-		mvmsta->tid_data[tid].txq_id = IEEE80211_INVAL_HW_QUEUE;
-		mvm->queue_info[queue].hw_queue_to_mac80211 &= ~BIT(mac_queue);
+		mvmsta->tid_data[tid].txq_id = IWL_MVM_INVALID_QUEUE;
+		mvm->hw_queue_to_mac80211[queue] &= ~BIT(mac_queue);
 		mvm->queue_info[queue].hw_queue_refcount--;
 		mvm->queue_info[queue].tid_bitmap &= ~BIT(tid);
 		mvmsta->tid_data[tid].is_tid_active = false;
@@ -1135,7 +1230,7 @@ static void iwl_mvm_remove_inactive_tids(struct iwl_mvm *mvm,
 	 */
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
 	for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) {
-		mvm->queue_info[queue].hw_queue_to_mac80211 |=
+		mvm->hw_queue_to_mac80211[queue] |=
 			BIT(mvmsta->vif->hw_queue[tid_to_mac80211_ac[tid]]);
 	}
 
@@ -1154,6 +1249,9 @@ void iwl_mvm_inactivity_check(struct iwl_mvm *mvm)
 	unsigned long now = jiffies;
 	int i;
 
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return;
+
 	spin_lock_bh(&mvm->queue_info_lock);
 	for (i = 0; i < IWL_MAX_HW_QUEUES; i++)
 		if (mvm->queue_info[i].hw_queue_refcount > 0)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
new file mode 100644
index 000000000000..b1f43397bb59
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -0,0 +1,281 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+
+#include "iwl-trans.h"
+#include "iwl-fh.h"
+#include "iwl-context-info.h"
+#include "internal.h"
+#include "iwl-prph.h"
+
+static int iwl_pcie_get_num_sections(const struct fw_img *fw,
+				     int start)
+{
+	int i = 0;
+
+	while (start < fw->num_sec &&
+	       fw->sec[start].offset != CPU1_CPU2_SEPARATOR_SECTION &&
+	       fw->sec[start].offset != PAGING_SEPARATOR_SECTION) {
+		start++;
+		i++;
+	}
+
+	return i;
+}
+
+static int iwl_pcie_ctxt_info_alloc_dma(struct iwl_trans *trans,
+					const struct fw_desc *sec,
+					struct iwl_dram_data *dram)
+{
+	dram->block = dma_alloc_coherent(trans->dev, sec->len,
+					 &dram->physical,
+					 GFP_KERNEL);
+	if (!dram->block)
+		return -ENOMEM;
+
+	dram->size = sec->len;
+	memcpy(dram->block, sec->data, sec->len);
+
+	return 0;
+}
+
+static void iwl_pcie_ctxt_info_free_fw_img(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
+	int i;
+
+	if (!dram->fw) {
+		WARN_ON(dram->fw_cnt);
+		return;
+	}
+
+	for (i = 0; i < dram->fw_cnt; i++)
+		dma_free_coherent(trans->dev, dram->fw[i].size,
+				  dram->fw[i].block, dram->fw[i].physical);
+
+	kfree(dram->fw);
+	dram->fw_cnt = 0;
+}
+
+void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
+	int i;
+
+	if (!dram->paging) {
+		WARN_ON(dram->paging_cnt);
+		return;
+	}
+
+	/* free paging*/
+	for (i = 0; i < dram->paging_cnt; i++)
+		dma_free_coherent(trans->dev, dram->paging[i].size,
+				  dram->paging[i].block,
+				  dram->paging[i].physical);
+
+	kfree(dram->paging);
+	dram->paging_cnt = 0;
+}
+
+static int iwl_pcie_ctxt_info_init_fw_sec(struct iwl_trans *trans,
+					  const struct fw_img *fw,
+					  struct iwl_context_info *ctxt_info)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
+	struct iwl_context_info_dram *ctxt_dram = &ctxt_info->dram;
+	int i, ret, lmac_cnt, umac_cnt, paging_cnt;
+
+	lmac_cnt = iwl_pcie_get_num_sections(fw, 0);
+	/* add 1 due to separator */
+	umac_cnt = iwl_pcie_get_num_sections(fw, lmac_cnt + 1);
+	/* add 2 due to separators */
+	paging_cnt = iwl_pcie_get_num_sections(fw, lmac_cnt + umac_cnt + 2);
+
+	dram->fw = kcalloc(umac_cnt + lmac_cnt, sizeof(*dram->fw), GFP_KERNEL);
+	if (!dram->fw)
+		return -ENOMEM;
+	dram->paging = kcalloc(paging_cnt, sizeof(*dram->paging), GFP_KERNEL);
+	if (!dram->paging)
+		return -ENOMEM;
+
+	/* initialize lmac sections */
+	for (i = 0; i < lmac_cnt; i++) {
+		ret = iwl_pcie_ctxt_info_alloc_dma(trans, &fw->sec[i],
+						   &dram->fw[dram->fw_cnt]);
+		if (ret)
+			return ret;
+		ctxt_dram->lmac_img[i] =
+			cpu_to_le64(dram->fw[dram->fw_cnt].physical);
+		dram->fw_cnt++;
+	}
+
+	/* initialize umac sections */
+	for (i = 0; i < umac_cnt; i++) {
+		/* access FW with +1 to make up for lmac separator */
+		ret = iwl_pcie_ctxt_info_alloc_dma(trans,
+						   &fw->sec[dram->fw_cnt + 1],
+						   &dram->fw[dram->fw_cnt]);
+		if (ret)
+			return ret;
+		ctxt_dram->umac_img[i] =
+			cpu_to_le64(dram->fw[dram->fw_cnt].physical);
+		dram->fw_cnt++;
+	}
+
+	/*
+	 * Initialize paging.
+	 * Paging memory isn't stored in dram->fw as the umac and lmac - it is
+	 * stored separately.
+	 * This is since the timing of its release is different -
+	 * while fw memory can be released on alive, the paging memory can be
+	 * freed only when the device goes down.
+	 * Given that, the logic here in accessing the fw image is a bit
+	 * different - fw_cnt isn't changing so loop counter is added to it.
+	 */
+	for (i = 0; i < paging_cnt; i++) {
+		/* access FW with +2 to make up for lmac & umac separators */
+		int fw_idx = dram->fw_cnt + i + 2;
+
+		ret = iwl_pcie_ctxt_info_alloc_dma(trans, &fw->sec[fw_idx],
+						   &dram->paging[i]);
+		if (ret)
+			return ret;
+
+		ctxt_dram->virtual_img[i] =
+			cpu_to_le64(dram->paging[i].physical);
+		dram->paging_cnt++;
+	}
+
+	return 0;
+}
+
+int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
+			    const struct fw_img *fw)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_context_info *ctxt_info;
+	struct iwl_context_info_rbd_cfg *rx_cfg;
+	u32 control_flags = 0;
+	int ret;
+
+	ctxt_info = dma_alloc_coherent(trans->dev, sizeof(*ctxt_info),
+				       &trans_pcie->ctxt_info_dma_addr,
+				       GFP_KERNEL);
+	if (!ctxt_info)
+		return -ENOMEM;
+
+	ctxt_info->version.version = 0;
+	ctxt_info->version.mac_id =
+		cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV));
+	/* size is in DWs */
+	ctxt_info->version.size = cpu_to_le16(sizeof(*ctxt_info) / 4);
+
+	BUILD_BUG_ON(RX_QUEUE_CB_SIZE(MQ_RX_TABLE_SIZE) > 0xF);
+	control_flags = IWL_CTXT_INFO_RB_SIZE_4K |
+			IWL_CTXT_INFO_TFD_FORMAT_LONG |
+			RX_QUEUE_CB_SIZE(MQ_RX_TABLE_SIZE) <<
+			IWL_CTXT_INFO_RB_CB_SIZE_POS;
+	ctxt_info->control.control_flags = cpu_to_le32(control_flags);
+
+	/* initialize RX default queue */
+	rx_cfg = &ctxt_info->rbd_cfg;
+	rx_cfg->free_rbd_addr = cpu_to_le64(trans_pcie->rxq->bd_dma);
+	rx_cfg->used_rbd_addr = cpu_to_le64(trans_pcie->rxq->used_bd_dma);
+	rx_cfg->status_wr_ptr = cpu_to_le64(trans_pcie->rxq->rb_stts_dma);
+
+	/* initialize TX command queue */
+	ctxt_info->hcmd_cfg.cmd_queue_addr =
+		cpu_to_le64(trans_pcie->txq[trans_pcie->cmd_queue]->dma_addr);
+	ctxt_info->hcmd_cfg.cmd_queue_size =
+		TFD_QUEUE_CB_SIZE(TFD_QUEUE_SIZE_MAX);
+
+	/* allocate ucode sections in dram and set addresses */
+	ret = iwl_pcie_ctxt_info_init_fw_sec(trans, fw, ctxt_info);
+	if (ret) {
+		dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info),
+				  ctxt_info, trans_pcie->ctxt_info_dma_addr);
+		return ret;
+	}
+
+	trans_pcie->ctxt_info = ctxt_info;
+
+	iwl_enable_interrupts(trans);
+
+	/* Configure debug, if exists */
+	if (trans->dbg_dest_tlv)
+		iwl_pcie_apply_destination(trans);
+
+	/* kick FW self load */
+	iwl_write64(trans, CSR_CTXT_INFO_BA, trans_pcie->ctxt_info_dma_addr);
+	iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
+
+	/* Context info will be released upon alive or failure to get one */
+
+	return 0;
+}
+
+void iwl_pcie_ctxt_info_free(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	if (!trans_pcie->ctxt_info)
+		return;
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info),
+			  trans_pcie->ctxt_info,
+			  trans_pcie->ctxt_info_dma_addr);
+	trans_pcie->ctxt_info_dma_addr = 0;
+	trans_pcie->ctxt_info = NULL;
+
+	iwl_pcie_ctxt_info_free_fw_img(trans);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index ba8a81cb0e2b..e51760e752d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -501,6 +501,10 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x24FD, 0x0930, iwl8265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24FD, 0x0950, iwl8265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24FD, 0x0850, iwl8265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1014, iwl8265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x3E02, iwl8275_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x3E01, iwl8275_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1012, iwl8275_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24FD, 0x0012, iwl8275_2ac_cfg)},
 
 /* 9000 Series */
@@ -533,7 +537,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xA370, 0x1030, iwl9560_2ac_cfg)},
 
 /* a000 Series */
-	{IWL_PCI_DEVICE(0x2720, 0x0A10, iwla000_2ac_cfg_hr)},
+	{IWL_PCI_DEVICE(0x2720, 0x0A10, iwla000_2ac_cfg_hr_cdb)},
+	{IWL_PCI_DEVICE(0x2722, 0x0A10, iwla000_2ac_cfg_hr)},
 #endif /* CONFIG_IWLMVM */
 
 	{0}
@@ -667,18 +672,11 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		iwl_trans->cfg = cfg_7265d;
 	}
 
-	if (iwl_trans->cfg->rf_id) {
-		if (cfg == &iwl9460_2ac_cfg &&
-		    iwl_trans->hw_rf_id == CSR_HW_RF_ID_TYPE_LC) {
-			cfg = &iwl9000lc_2ac_cfg;
-			iwl_trans->cfg = cfg;
-		}
-
-		if (cfg == &iwla000_2ac_cfg_hr &&
-		    iwl_trans->hw_rf_id == CSR_HW_RF_ID_TYPE_JF) {
-			cfg = &iwla000_2ac_cfg_jf;
-			iwl_trans->cfg = cfg;
-		}
+	if (iwl_trans->cfg->rf_id &&
+	    (cfg == &iwla000_2ac_cfg_hr || cfg == &iwla000_2ac_cfg_hr_cdb) &&
+	     iwl_trans->hw_rf_id == CSR_HW_RF_ID_TYPE_JF) {
+		cfg = &iwla000_2ac_cfg_jf;
+		iwl_trans->cfg = cfg;
 	}
 #endif
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 10937309641a..fd4faaaa1484 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -2,7 +2,7 @@
  *
  * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -205,11 +205,11 @@ struct iwl_cmd_meta {
  * into the buffer regardless of whether it should be mapped or not.
  * This indicates how big the first TB must be to include the scratch buffer
  * and the assigned PN.
- * Since PN location is 16 bytes at offset 24, it's 40 now.
+ * Since PN location is 8 bytes at offset 12, it's 20 now.
  * If we make it bigger then allocations will be bigger and copy slower, so
  * that's probably not useful.
  */
-#define IWL_FIRST_TB_SIZE	40
+#define IWL_FIRST_TB_SIZE	20
 #define IWL_FIRST_TB_SIZE_ALIGN ALIGN(IWL_FIRST_TB_SIZE, 64)
 
 struct iwl_pcie_txq_entry {
@@ -237,11 +237,11 @@ struct iwl_pcie_first_tb_buf {
  * @stuck_timer: timer that fires if queue gets stuck
  * @trans_pcie: pointer back to transport (for timer)
  * @need_update: indicates need to update read/write index
- * @active: stores if queue is active
  * @ampdu: true if this queue is an ampdu queue for an specific RA/TID
  * @wd_timeout: queue watchdog timeout (jiffies) - per queue
  * @frozen: tx stuck queue timer is frozen
  * @frozen_expiry_remainder: remember how long until the timer fires
+ * @bc_tbl: byte count table of the queue (relevant only for gen2 transport)
  * @write_ptr: 1-st empty entry (index) host_w
  * @read_ptr: last used entry (index) host_r
  * @dma_addr:  physical addr for BD's
@@ -277,11 +277,11 @@ struct iwl_txq {
 	struct iwl_trans_pcie *trans_pcie;
 	bool need_update;
 	bool frozen;
-	u8 active;
 	bool ampdu;
 	int block;
 	unsigned long wd_timeout;
 	struct sk_buff_head overflow_q;
+	struct iwl_dma_ptr bc_tbl;
 
 	int write_ptr;
 	int read_ptr;
@@ -315,11 +315,43 @@ enum iwl_shared_irq_flags {
 };
 
 /**
+ * struct iwl_dram_data
+ * @physical: page phy pointer
+ * @block: pointer to the allocated block/page
+ * @size: size of the block/page
+ */
+struct iwl_dram_data {
+	dma_addr_t physical;
+	void *block;
+	int size;
+};
+
+/**
+ * struct iwl_self_init_dram - dram data used by self init process
+ * @fw: lmac and umac dram data
+ * @fw_cnt: total number of items in array
+ * @paging: paging dram data
+ * @paging_cnt: total number of items in array
+ */
+struct iwl_self_init_dram {
+	struct iwl_dram_data *fw;
+	int fw_cnt;
+	struct iwl_dram_data *paging;
+	int paging_cnt;
+};
+
+/**
  * struct iwl_trans_pcie - PCIe transport specific data
  * @rxq: all the RX queue data
  * @rx_pool: initial pool of iwl_rx_mem_buffer for all the queues
  * @global_table: table mapping received VID from hw to rxb
  * @rba: allocator for RX replenishing
+ * @ctxt_info: context information for FW self init
+ * @ctxt_info_dma_addr: dma addr of context information
+ * @init_dram: DRAM data of firmware image (including paging).
+ *	Context information addresses will be taken from here.
+ *	This is driver's local copy for keeping track of size and
+ *	count for allocating and freeing the memory.
  * @trans: pointer to the generic transport area
  * @scd_base_addr: scheduler sram base address in SRAM
  * @scd_bc_tbls: pointer to the byte count table of the scheduler
@@ -357,6 +389,9 @@ struct iwl_trans_pcie {
 	struct iwl_rx_mem_buffer rx_pool[RX_POOL_SIZE];
 	struct iwl_rx_mem_buffer *global_table[RX_POOL_SIZE];
 	struct iwl_rb_allocator rba;
+	struct iwl_context_info *ctxt_info;
+	dma_addr_t ctxt_info_dma_addr;
+	struct iwl_self_init_dram init_dram;
 	struct iwl_trans *trans;
 
 	struct net_device napi_dev;
@@ -378,9 +413,10 @@ struct iwl_trans_pcie {
 	struct iwl_dma_ptr scd_bc_tbls;
 	struct iwl_dma_ptr kw;
 
-	struct iwl_txq *txq;
-	unsigned long queue_used[BITS_TO_LONGS(IWL_MAX_HW_QUEUES)];
-	unsigned long queue_stopped[BITS_TO_LONGS(IWL_MAX_HW_QUEUES)];
+	struct iwl_txq *txq_memory;
+	struct iwl_txq *txq[IWL_MAX_TVQM_QUEUES];
+	unsigned long queue_used[BITS_TO_LONGS(IWL_MAX_TVQM_QUEUES)];
+	unsigned long queue_stopped[BITS_TO_LONGS(IWL_MAX_TVQM_QUEUES)];
 
 	/* PCI bus related data */
 	struct pci_dev *pci_dev;
@@ -454,6 +490,7 @@ void iwl_trans_pcie_free(struct iwl_trans *trans);
 * RX
 ******************************************************/
 int iwl_pcie_rx_init(struct iwl_trans *trans);
+int iwl_pcie_gen2_rx_init(struct iwl_trans *trans);
 irqreturn_t iwl_pcie_msix_isr(int irq, void *data);
 irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id);
 irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id);
@@ -474,6 +511,7 @@ void iwl_pcie_disable_ict(struct iwl_trans *trans);
 * TX / HCMD
 ******************************************************/
 int iwl_pcie_tx_init(struct iwl_trans *trans);
+int iwl_pcie_gen2_tx_init(struct iwl_trans *trans);
 void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr);
 int iwl_pcie_tx_stop(struct iwl_trans *trans);
 void iwl_pcie_tx_free(struct iwl_trans *trans);
@@ -484,7 +522,6 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int queue,
 				bool configure_scd);
 void iwl_trans_pcie_txq_set_shared_mode(struct iwl_trans *trans, u32 txq_id,
 					bool shared_mode);
-dma_addr_t iwl_trans_pcie_get_txq_byte_table(struct iwl_trans *trans, int txq);
 void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans,
 				  struct iwl_txq *txq);
 int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
@@ -616,6 +653,12 @@ static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
 	}
 }
 
+static inline void *iwl_pcie_get_tfd(struct iwl_trans_pcie *trans_pcie,
+				     struct iwl_txq *txq, int idx)
+{
+	return txq->tfds + trans_pcie->tfd_size * idx;
+}
+
 static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -719,4 +762,41 @@ int iwl_pci_fw_enter_d0i3(struct iwl_trans *trans);
 
 void iwl_pcie_enable_rx_wake(struct iwl_trans *trans, bool enable);
 
+/* common functions that are used by gen2 transport */
+void iwl_pcie_apm_config(struct iwl_trans *trans);
+int iwl_pcie_prepare_card_hw(struct iwl_trans *trans);
+void iwl_pcie_synchronize_irqs(struct iwl_trans *trans);
+bool iwl_trans_check_hw_rf_kill(struct iwl_trans *trans);
+void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq);
+int iwl_queue_space(const struct iwl_txq *q);
+int iwl_pcie_apm_stop_master(struct iwl_trans *trans);
+void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie);
+int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
+		      int slots_num, bool cmd_queue);
+int iwl_pcie_txq_alloc(struct iwl_trans *trans,
+		       struct iwl_txq *txq, int slots_num,  bool cmd_queue);
+int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
+			   struct iwl_dma_ptr *ptr, size_t size);
+void iwl_pcie_free_dma_ptr(struct iwl_trans *trans, struct iwl_dma_ptr *ptr);
+void iwl_pcie_apply_destination(struct iwl_trans *trans);
+
+/* transport gen 2 exported functions */
+int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
+				 const struct fw_img *fw, bool run_in_rfkill);
+void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr);
+int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
+				 struct iwl_tx_queue_cfg_cmd *cmd,
+				 int cmd_id,
+				 unsigned int timeout);
+void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue);
+int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
+			   struct iwl_device_cmd *dev_cmd, int txq_id);
+int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
+				  struct iwl_host_cmd *cmd);
+void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans,
+				     bool low_power);
+void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans, bool low_power);
+void iwl_pcie_gen2_txq_unmap(struct iwl_trans *trans, int txq_id);
+void iwl_pcie_gen2_tx_free(struct iwl_trans *trans);
+void iwl_pcie_gen2_tx_stop(struct iwl_trans *trans);
 #endif /* __iwl_trans_int_pcie_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index de94dfdf2ec9..1da2de205cdf 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -2,7 +2,7 @@
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -880,7 +880,7 @@ static int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget)
 	return 0;
 }
 
-int iwl_pcie_rx_init(struct iwl_trans *trans)
+static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rxq *def_rxq;
@@ -958,20 +958,40 @@ int iwl_pcie_rx_init(struct iwl_trans *trans)
 
 	iwl_pcie_rxq_alloc_rbs(trans, GFP_KERNEL, def_rxq);
 
+	return 0;
+}
+
+int iwl_pcie_rx_init(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int ret = _iwl_pcie_rx_init(trans);
+
+	if (ret)
+		return ret;
+
 	if (trans->cfg->mq_rx_supported)
 		iwl_pcie_rx_mq_hw_init(trans);
 	else
-		iwl_pcie_rx_hw_init(trans, def_rxq);
+		iwl_pcie_rx_hw_init(trans, trans_pcie->rxq);
 
-	iwl_pcie_rxq_restock(trans, def_rxq);
+	iwl_pcie_rxq_restock(trans, trans_pcie->rxq);
 
-	spin_lock(&def_rxq->lock);
-	iwl_pcie_rxq_inc_wr_ptr(trans, def_rxq);
-	spin_unlock(&def_rxq->lock);
+	spin_lock(&trans_pcie->rxq->lock);
+	iwl_pcie_rxq_inc_wr_ptr(trans, trans_pcie->rxq);
+	spin_unlock(&trans_pcie->rxq->lock);
 
 	return 0;
 }
 
+int iwl_pcie_gen2_rx_init(struct iwl_trans *trans)
+{
+	/*
+	 * We don't configure the RFH.
+	 * Restock will be done at alive, after firmware configured the RFH.
+	 */
+	return _iwl_pcie_rx_init(trans);
+}
+
 void iwl_pcie_rx_free(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -1074,7 +1094,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 				bool emergency)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[trans_pcie->cmd_queue];
+	struct iwl_txq *txq = trans_pcie->txq[trans_pcie->cmd_queue];
 	bool page_stolen = false;
 	int max_len = PAGE_SIZE << trans_pcie->rx_page_order;
 	u32 offset = 0;
@@ -1127,7 +1147,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		 * Ucode should set SEQ_RX_FRAME bit if ucode-originated,
 		 *   but apparently a few don't get set; catch them here. */
 		reclaim = !(pkt->hdr.sequence & SEQ_RX_FRAME);
-		if (reclaim) {
+		if (reclaim && !pkt->hdr.group_id) {
 			int i;
 
 			for (i = 0; i < trans_pcie->n_no_reclaim_cmds; i++) {
@@ -1393,17 +1413,17 @@ static void iwl_pcie_irq_handle_error(struct iwl_trans *trans)
 		return;
 	}
 
-	iwl_pcie_dump_csr(trans);
-	iwl_dump_fh(trans, NULL);
-
 	local_bh_disable();
 	/* The STATUS_FW_ERROR bit is set in this function. This must happen
 	 * before we wake up the command caller, to ensure a proper cleanup. */
 	iwl_trans_fw_error(trans);
 	local_bh_enable();
 
-	for (i = 0; i < trans->cfg->base_params->num_of_queues; i++)
-		del_timer(&trans_pcie->txq[i].stuck_timer);
+	for (i = 0; i < trans->cfg->base_params->num_of_queues; i++) {
+		if (!trans_pcie->txq[i])
+			continue;
+		del_timer(&trans_pcie->txq[i]->stuck_timer);
+	}
 
 	clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
 	wake_up(&trans_pcie->wait_command_queue);
@@ -1597,6 +1617,13 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 		if (inta & CSR_INT_BIT_ALIVE) {
 			IWL_DEBUG_ISR(trans, "Alive interrupt\n");
 			isr_stats->alive++;
+			if (trans->cfg->gen2) {
+				/*
+				 * We can restock, since firmware configured
+				 * the RFH
+				 */
+				iwl_pcie_rxmq_restock(trans, trans_pcie->rxq);
+			}
 		}
 	}
 
@@ -1933,6 +1960,10 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 	if (inta_hw & MSIX_HW_INT_CAUSES_REG_ALIVE) {
 		IWL_DEBUG_ISR(trans, "Alive interrupt\n");
 		isr_stats->alive++;
+		if (trans->cfg->gen2) {
+			/* We can restock, since firmware configured the RFH */
+			iwl_pcie_rxmq_restock(trans, trans_pcie->rxq);
+		}
 	}
 
 	/* uCode wakes up after power-down sleep */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
new file mode 100644
index 000000000000..ac60a282d6de
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -0,0 +1,374 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#include "iwl-trans.h"
+#include "iwl-context-info.h"
+#include "internal.h"
+
+/*
+ * Start up NIC's basic functionality after it has been reset
+ * (e.g. after platform boot, or shutdown via iwl_pcie_apm_stop())
+ * NOTE:  This does not load uCode nor start the embedded processor
+ */
+static int iwl_pcie_gen2_apm_init(struct iwl_trans *trans)
+{
+	int ret = 0;
+
+	IWL_DEBUG_INFO(trans, "Init card's basic functions\n");
+
+	/*
+	 * Use "set_bit" below rather than "write", to preserve any hardware
+	 * bits already set by default after reset.
+	 */
+
+	/*
+	 * Disable L0s without affecting L1;
+	 * don't wait for ICH L0s (ICH bug W/A)
+	 */
+	iwl_set_bit(trans, CSR_GIO_CHICKEN_BITS,
+		    CSR_GIO_CHICKEN_BITS_REG_BIT_L1A_NO_L0S_RX);
+
+	/* Set FH wait threshold to maximum (HW error during stress W/A) */
+	iwl_set_bit(trans, CSR_DBG_HPET_MEM_REG, CSR_DBG_HPET_MEM_REG_VAL);
+
+	/*
+	 * Enable HAP INTA (interrupt from management bus) to
+	 * wake device's PCI Express link L1a -> L0s
+	 */
+	iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+		    CSR_HW_IF_CONFIG_REG_BIT_HAP_WAKE_L1A);
+
+	iwl_pcie_apm_config(trans);
+
+	/*
+	 * Set "initialization complete" bit to move adapter from
+	 * D0U* --> D0A* (powered-up active) state.
+	 */
+	iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+
+	/*
+	 * Wait for clock stabilization; once stabilized, access to
+	 * device-internal resources is supported, e.g. iwl_write_prph()
+	 * and accesses to uCode SRAM.
+	 */
+	ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
+			   CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
+			   CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY, 25000);
+	if (ret < 0) {
+		IWL_DEBUG_INFO(trans, "Failed to init the card\n");
+		return ret;
+	}
+
+	set_bit(STATUS_DEVICE_ENABLED, &trans->status);
+
+	return 0;
+}
+
+static void iwl_pcie_gen2_apm_stop(struct iwl_trans *trans, bool op_mode_leave)
+{
+	IWL_DEBUG_INFO(trans, "Stop card, put in low power state\n");
+
+	if (op_mode_leave) {
+		if (!test_bit(STATUS_DEVICE_ENABLED, &trans->status))
+			iwl_pcie_gen2_apm_init(trans);
+
+		/* inform ME that we are leaving */
+		iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+			    CSR_RESET_LINK_PWR_MGMT_DISABLED);
+		iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+			    CSR_HW_IF_CONFIG_REG_PREPARE |
+			    CSR_HW_IF_CONFIG_REG_ENABLE_PME);
+		mdelay(1);
+		iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+			      CSR_RESET_LINK_PWR_MGMT_DISABLED);
+		mdelay(5);
+	}
+
+	clear_bit(STATUS_DEVICE_ENABLED, &trans->status);
+
+	/* Stop device's DMA activity */
+	iwl_pcie_apm_stop_master(trans);
+
+	/* Reset the entire device */
+	iwl_set_bit(trans, CSR_RESET, CSR_RESET_REG_FLAG_SW_RESET);
+	usleep_range(1000, 2000);
+
+	/*
+	 * Clear "initialization complete" bit to move adapter from
+	 * D0A* (powered-up Active) --> D0U* (Uninitialized) state.
+	 */
+	iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+}
+
+void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans, bool low_power)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	bool hw_rfkill, was_hw_rfkill;
+
+	lockdep_assert_held(&trans_pcie->mutex);
+
+	if (trans_pcie->is_down)
+		return;
+
+	trans_pcie->is_down = true;
+
+	was_hw_rfkill = iwl_is_rfkill_set(trans);
+
+	/* tell the device to stop sending interrupts */
+	iwl_disable_interrupts(trans);
+
+	/* device going down, Stop using ICT table */
+	iwl_pcie_disable_ict(trans);
+
+	/*
+	 * If a HW restart happens during firmware loading,
+	 * then the firmware loading might call this function
+	 * and later it might be called again due to the
+	 * restart. So don't process again if the device is
+	 * already dead.
+	 */
+	if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) {
+		IWL_DEBUG_INFO(trans,
+			       "DEVICE_ENABLED bit was set and is now cleared\n");
+		iwl_pcie_gen2_tx_stop(trans);
+		iwl_pcie_rx_stop(trans);
+	}
+
+	iwl_pcie_ctxt_info_free_paging(trans);
+	iwl_pcie_ctxt_info_free(trans);
+
+	/* Make sure (redundant) we've released our request to stay awake */
+	iwl_clear_bit(trans, CSR_GP_CNTRL,
+		      CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+
+	/* Stop the device, and put it in low power state */
+	iwl_pcie_gen2_apm_stop(trans, false);
+
+	/* stop and reset the on-board processor */
+	iwl_write32(trans, CSR_RESET, CSR_RESET_REG_FLAG_SW_RESET);
+	usleep_range(1000, 2000);
+
+	/*
+	 * Upon stop, the IVAR table gets erased, so msi-x won't
+	 * work. This causes a bug in RF-KILL flows, since the interrupt
+	 * that enables radio won't fire on the correct irq, and the
+	 * driver won't be able to handle the interrupt.
+	 * Configure the IVAR table again after reset.
+	 */
+	iwl_pcie_conf_msix_hw(trans_pcie);
+
+	/*
+	 * Upon stop, the APM issues an interrupt if HW RF kill is set.
+	 * This is a bug in certain verions of the hardware.
+	 * Certain devices also keep sending HW RF kill interrupt all
+	 * the time, unless the interrupt is ACKed even if the interrupt
+	 * should be masked. Re-ACK all the interrupts here.
+	 */
+	iwl_disable_interrupts(trans);
+
+	/* clear all status bits */
+	clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
+	clear_bit(STATUS_INT_ENABLED, &trans->status);
+	clear_bit(STATUS_TPOWER_PMI, &trans->status);
+	clear_bit(STATUS_RFKILL, &trans->status);
+
+	/*
+	 * Even if we stop the HW, we still want the RF kill
+	 * interrupt
+	 */
+	iwl_enable_rfkill_int(trans);
+
+	/*
+	 * Check again since the RF kill state may have changed while
+	 * all the interrupts were disabled, in this case we couldn't
+	 * receive the RF kill interrupt and update the state in the
+	 * op_mode.
+	 * Don't call the op_mode if the rkfill state hasn't changed.
+	 * This allows the op_mode to call stop_device from the rfkill
+	 * notification without endless recursion. Under very rare
+	 * circumstances, we might have a small recursion if the rfkill
+	 * state changed exactly now while we were called from stop_device.
+	 * This is very unlikely but can happen and is supported.
+	 */
+	hw_rfkill = iwl_is_rfkill_set(trans);
+	if (hw_rfkill)
+		set_bit(STATUS_RFKILL, &trans->status);
+	else
+		clear_bit(STATUS_RFKILL, &trans->status);
+	if (hw_rfkill != was_hw_rfkill)
+		iwl_trans_pcie_rf_kill(trans, hw_rfkill);
+
+	/* re-take ownership to prevent other users from stealing the device */
+	iwl_pcie_prepare_card_hw(trans);
+}
+
+void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans, bool low_power)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	mutex_lock(&trans_pcie->mutex);
+	_iwl_trans_pcie_gen2_stop_device(trans, low_power);
+	mutex_unlock(&trans_pcie->mutex);
+}
+
+static int iwl_pcie_gen2_nic_init(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	/* TODO: most of the logic can be removed in A0 - but not in Z0 */
+	spin_lock(&trans_pcie->irq_lock);
+	iwl_pcie_gen2_apm_init(trans);
+	spin_unlock(&trans_pcie->irq_lock);
+
+	iwl_op_mode_nic_config(trans->op_mode);
+
+	/* Allocate the RX queue, or reset if it is already allocated */
+	if (iwl_pcie_gen2_rx_init(trans))
+		return -ENOMEM;
+
+	/* Allocate or reset and init all Tx and Command queues */
+	if (iwl_pcie_gen2_tx_init(trans))
+		return -ENOMEM;
+
+	/* enable shadow regs in HW */
+	iwl_set_bit(trans, CSR_MAC_SHADOW_REG_CTRL, 0x800FFFFF);
+	IWL_DEBUG_INFO(trans, "Enabling shadow registers in device\n");
+
+	return 0;
+}
+
+void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	iwl_pcie_reset_ict(trans);
+
+	/* make sure all queue are not stopped/used */
+	memset(trans_pcie->queue_stopped, 0, sizeof(trans_pcie->queue_stopped));
+	memset(trans_pcie->queue_used, 0, sizeof(trans_pcie->queue_used));
+
+	/* now that we got alive we can free the fw image & the context info.
+	 * paging memory cannot be freed included since FW will still use it
+	 */
+	iwl_pcie_ctxt_info_free(trans);
+}
+
+int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
+				 const struct fw_img *fw, bool run_in_rfkill)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	bool hw_rfkill;
+	int ret;
+
+	/* This may fail if AMT took ownership of the device */
+	if (iwl_pcie_prepare_card_hw(trans)) {
+		IWL_WARN(trans, "Exit HW not ready\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	iwl_enable_rfkill_int(trans);
+
+	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
+
+	/*
+	 * We enabled the RF-Kill interrupt and the handler may very
+	 * well be running. Disable the interrupts to make sure no other
+	 * interrupt can be fired.
+	 */
+	iwl_disable_interrupts(trans);
+
+	/* Make sure it finished running */
+	iwl_pcie_synchronize_irqs(trans);
+
+	mutex_lock(&trans_pcie->mutex);
+
+	/* If platform's RF_KILL switch is NOT set to KILL */
+	hw_rfkill = iwl_trans_check_hw_rf_kill(trans);
+	if (hw_rfkill && !run_in_rfkill) {
+		ret = -ERFKILL;
+		goto out;
+	}
+
+	/* Someone called stop_device, don't try to start_fw */
+	if (trans_pcie->is_down) {
+		IWL_WARN(trans,
+			 "Can't start_fw since the HW hasn't been started\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	/* make sure rfkill handshake bits are cleared */
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR,
+		    CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED);
+
+	/* clear (again), then enable host interrupts */
+	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
+
+	ret = iwl_pcie_gen2_nic_init(trans);
+	if (ret) {
+		IWL_ERR(trans, "Unable to init nic\n");
+		goto out;
+	}
+
+	ret = iwl_pcie_ctxt_info_init(trans, fw);
+	if (ret)
+		goto out;
+
+	/* re-check RF-Kill state since we may have missed the interrupt */
+	hw_rfkill = iwl_trans_check_hw_rf_kill(trans);
+	if (hw_rfkill && !run_in_rfkill)
+		ret = -ERFKILL;
+
+out:
+	mutex_unlock(&trans_pcie->mutex);
+	return ret;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 7f05fc56587a..70acf850a9f1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2007 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2005 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -201,7 +201,7 @@ static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)
 /* PCI registers */
 #define PCI_CFG_RETRY_TIMEOUT	0x041
 
-static void iwl_pcie_apm_config(struct iwl_trans *trans)
+void iwl_pcie_apm_config(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u16 lctl;
@@ -448,7 +448,7 @@ static void iwl_pcie_apm_lp_xtal_enable(struct iwl_trans *trans)
 				 ~SHR_APMG_XTAL_CFG_XTAL_ON_REQ);
 }
 
-static int iwl_pcie_apm_stop_master(struct iwl_trans *trans)
+int iwl_pcie_apm_stop_master(struct iwl_trans *trans)
 {
 	int ret = 0;
 
@@ -567,7 +567,7 @@ static int iwl_pcie_set_hw_ready(struct iwl_trans *trans)
 }
 
 /* Note: returns standard 0/-ERROR code */
-static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
+int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 {
 	int ret;
 	int t = 0;
@@ -636,29 +636,6 @@ static void iwl_pcie_load_firmware_chunk_fh(struct iwl_trans *trans,
 		    FH_TCSR_TX_CONFIG_REG_VAL_CIRQ_HOST_ENDTFD);
 }
 
-static void iwl_pcie_load_firmware_chunk_tfh(struct iwl_trans *trans,
-					     u32 dst_addr, dma_addr_t phy_addr,
-					     u32 byte_cnt)
-{
-	/* Stop DMA channel */
-	iwl_write32(trans, TFH_SRV_DMA_CHNL0_CTRL, 0);
-
-	/* Configure SRAM address */
-	iwl_write32(trans, TFH_SRV_DMA_CHNL0_SRAM_ADDR,
-		    dst_addr);
-
-	/* Configure DRAM address - 64 bit */
-	iwl_write64(trans, TFH_SRV_DMA_CHNL0_DRAM_ADDR, phy_addr);
-
-	/* Configure byte count to transfer */
-	iwl_write32(trans, TFH_SRV_DMA_CHNL0_BC, byte_cnt);
-
-	/* Enable the DRAM2SRAM to start */
-	iwl_write32(trans, TFH_SRV_DMA_CHNL0_CTRL, TFH_SRV_DMA_SNOOP |
-						   TFH_SRV_DMA_TO_DRIVER |
-						   TFH_SRV_DMA_START);
-}
-
 static int iwl_pcie_load_firmware_chunk(struct iwl_trans *trans,
 					u32 dst_addr, dma_addr_t phy_addr,
 					u32 byte_cnt)
@@ -672,12 +649,8 @@ static int iwl_pcie_load_firmware_chunk(struct iwl_trans *trans,
 	if (!iwl_trans_grab_nic_access(trans, &flags))
 		return -EIO;
 
-	if (trans->cfg->use_tfh)
-		iwl_pcie_load_firmware_chunk_tfh(trans, dst_addr, phy_addr,
-						 byte_cnt);
-	else
-		iwl_pcie_load_firmware_chunk_fh(trans, dst_addr, phy_addr,
-						byte_cnt);
+	iwl_pcie_load_firmware_chunk_fh(trans, dst_addr, phy_addr,
+					byte_cnt);
 	iwl_trans_release_nic_access(trans, &flags);
 
 	ret = wait_event_timeout(trans_pcie->ucode_write_waitq,
@@ -747,47 +720,6 @@ static int iwl_pcie_load_section(struct iwl_trans *trans, u8 section_num,
 	return ret;
 }
 
-/*
- * Driver Takes the ownership on secure machine before FW load
- * and prevent race with the BT load.
- * W/A for ROM bug. (should be remove in the next Si step)
- */
-static int iwl_pcie_rsa_race_bug_wa(struct iwl_trans *trans)
-{
-	u32 val, loop = 1000;
-
-	/*
-	 * Check the RSA semaphore is accessible.
-	 * If the HW isn't locked and the rsa semaphore isn't accessible,
-	 * we are in trouble.
-	 */
-	val = iwl_read_prph(trans, PREG_AUX_BUS_WPROT_0);
-	if (val & (BIT(1) | BIT(17))) {
-		IWL_DEBUG_INFO(trans,
-			       "can't access the RSA semaphore it is write protected\n");
-		return 0;
-	}
-
-	/* take ownership on the AUX IF */
-	iwl_write_prph(trans, WFPM_CTRL_REG, WFPM_AUX_CTL_AUX_IF_MAC_OWNER_MSK);
-	iwl_write_prph(trans, AUX_MISC_MASTER1_EN, AUX_MISC_MASTER1_EN_SBE_MSK);
-
-	do {
-		iwl_write_prph(trans, AUX_MISC_MASTER1_SMPHR_STATUS, 0x1);
-		val = iwl_read_prph(trans, AUX_MISC_MASTER1_SMPHR_STATUS);
-		if (val == 0x1) {
-			iwl_write_prph(trans, RSA_ENABLE, 0);
-			return 0;
-		}
-
-		udelay(10);
-		loop--;
-	} while (loop > 0);
-
-	IWL_ERR(trans, "Failed to take ownership on secure machine\n");
-	return -EIO;
-}
-
 static int iwl_pcie_load_cpu_sections_8000(struct iwl_trans *trans,
 					   const struct fw_img *image,
 					   int cpu,
@@ -828,15 +760,10 @@ static int iwl_pcie_load_cpu_sections_8000(struct iwl_trans *trans,
 			return ret;
 
 		/* Notify ucode of loaded section number and status */
-		if (trans->cfg->use_tfh) {
-			val = iwl_read_prph(trans, UREG_UCODE_LOAD_STATUS);
-			val = val | (sec_num << shift_param);
-			iwl_write_prph(trans, UREG_UCODE_LOAD_STATUS, val);
-		} else {
-			val = iwl_read_direct32(trans, FH_UCODE_LOAD_STATUS);
-			val = val | (sec_num << shift_param);
-			iwl_write_direct32(trans, FH_UCODE_LOAD_STATUS, val);
-		}
+		val = iwl_read_direct32(trans, FH_UCODE_LOAD_STATUS);
+		val = val | (sec_num << shift_param);
+		iwl_write_direct32(trans, FH_UCODE_LOAD_STATUS, val);
+
 		sec_num = (sec_num << 1) | 0x1;
 	}
 
@@ -904,7 +831,7 @@ static int iwl_pcie_load_cpu_sections(struct iwl_trans *trans,
 	return 0;
 }
 
-static void iwl_pcie_apply_destination(struct iwl_trans *trans)
+void iwl_pcie_apply_destination(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	const struct iwl_fw_dbg_dest_tlv *dest = trans->dbg_dest_tlv;
@@ -1042,10 +969,15 @@ static int iwl_pcie_load_given_ucode_8000(struct iwl_trans *trans,
 	if (trans->dbg_dest_tlv)
 		iwl_pcie_apply_destination(trans);
 
-	/* TODO: remove in the next Si step */
-	ret = iwl_pcie_rsa_race_bug_wa(trans);
-	if (ret)
-		return ret;
+	IWL_DEBUG_POWER(trans, "Original WFPM value = 0x%08X\n",
+			iwl_read_prph(trans, WFPM_GP2));
+
+	/*
+	 * Set default value. On resume reading the values that were
+	 * zeored can provide debug data on the resume flow.
+	 * This is for debugging only and has no functional impact.
+	 */
+	iwl_write_prph(trans, WFPM_GP2, 0x01010101);
 
 	/* configure the ucode to be ready to get the secured image */
 	/* release CPU reset */
@@ -1062,7 +994,7 @@ static int iwl_pcie_load_given_ucode_8000(struct iwl_trans *trans,
 					       &first_ucode_section);
 }
 
-static bool iwl_trans_check_hw_rf_kill(struct iwl_trans *trans)
+bool iwl_trans_check_hw_rf_kill(struct iwl_trans *trans)
 {
 	bool hw_rfkill = iwl_is_rfkill_set(trans);
 
@@ -1147,7 +1079,7 @@ static void iwl_pcie_map_rx_causes(struct iwl_trans *trans)
 		iwl_write8(trans, CSR_MSIX_RX_IVAR(1), val);
 }
 
-static void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie)
+void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie)
 {
 	struct iwl_trans *trans = trans_pcie->trans;
 
@@ -1299,7 +1231,7 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	iwl_pcie_prepare_card_hw(trans);
 }
 
-static void iwl_pcie_synchronize_irqs(struct iwl_trans *trans)
+void iwl_pcie_synchronize_irqs(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
@@ -1423,8 +1355,12 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state)
 
 	lockdep_assert_held(&trans_pcie->mutex);
 
-	if (iwl_op_mode_hw_rf_kill(trans->op_mode, state))
-		_iwl_trans_pcie_stop_device(trans, true);
+	if (iwl_op_mode_hw_rf_kill(trans->op_mode, state)) {
+		if (trans->cfg->gen2)
+			_iwl_trans_pcie_gen2_stop_device(trans, true);
+		else
+			_iwl_trans_pcie_stop_device(trans, true);
+	}
 }
 
 static void iwl_trans_pcie_d3_suspend(struct iwl_trans *trans, bool test,
@@ -1527,6 +1463,9 @@ static int iwl_trans_pcie_d3_resume(struct iwl_trans *trans,
 		}
 	}
 
+	IWL_DEBUG_POWER(trans, "WFPM value upon resume = 0x%08X\n",
+			iwl_read_prph(trans, WFPM_GP2));
+
 	val = iwl_read32(trans, CSR_RESET);
 	if (val & CSR_RESET_REG_FLAG_NEVO_RESET)
 		*status = IWL_D3_STATUS_RESET;
@@ -1828,7 +1767,10 @@ void iwl_trans_pcie_free(struct iwl_trans *trans)
 
 	iwl_pcie_synchronize_irqs(trans);
 
-	iwl_pcie_tx_free(trans);
+	if (trans->cfg->gen2)
+		iwl_pcie_gen2_tx_free(trans);
+	else
+		iwl_pcie_tx_free(trans);
 	iwl_pcie_rx_free(trans);
 
 	if (trans_pcie->msix_enabled) {
@@ -1998,7 +1940,7 @@ static void iwl_trans_pcie_freeze_txq_timer(struct iwl_trans *trans,
 	int queue;
 
 	for_each_set_bit(queue, &txqs, BITS_PER_LONG) {
-		struct iwl_txq *txq = &trans_pcie->txq[queue];
+		struct iwl_txq *txq = trans_pcie->txq[queue];
 		unsigned long now;
 
 		spin_lock_bh(&txq->lock);
@@ -2050,7 +1992,7 @@ static void iwl_trans_pcie_block_txq_ptrs(struct iwl_trans *trans, bool block)
 	int i;
 
 	for (i = 0; i < trans->cfg->base_params->num_of_queues; i++) {
-		struct iwl_txq *txq = &trans_pcie->txq[i];
+		struct iwl_txq *txq = trans_pcie->txq[i];
 
 		if (i == trans_pcie->cmd_queue)
 			continue;
@@ -2075,48 +2017,32 @@ static void iwl_trans_pcie_block_txq_ptrs(struct iwl_trans *trans, bool block)
 
 void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	u32 scd_sram_addr;
-	u8 buf[16];
-	int cnt;
+	u32 txq_id = txq->id;
+	u32 status;
+	bool active;
+	u8 fifo;
 
-	IWL_ERR(trans, "Current SW read_ptr %d write_ptr %d\n",
-		txq->read_ptr, txq->write_ptr);
-
-	if (trans->cfg->use_tfh)
+	if (trans->cfg->use_tfh) {
+		IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id,
+			txq->read_ptr, txq->write_ptr);
 		/* TODO: access new SCD registers and dump them */
 		return;
+	}
 
-	scd_sram_addr = trans_pcie->scd_base_addr +
-			SCD_TX_STTS_QUEUE_OFFSET(txq->id);
-	iwl_trans_read_mem_bytes(trans, scd_sram_addr, buf, sizeof(buf));
-
-	iwl_print_hex_error(trans, buf, sizeof(buf));
-
-	for (cnt = 0; cnt < FH_TCSR_CHNL_NUM; cnt++)
-		IWL_ERR(trans, "FH TRBs(%d) = 0x%08x\n", cnt,
-			iwl_read_direct32(trans, FH_TX_TRB_REG(cnt)));
-
-	for (cnt = 0; cnt < trans->cfg->base_params->num_of_queues; cnt++) {
-		u32 status = iwl_read_prph(trans, SCD_QUEUE_STATUS_BITS(cnt));
-		u8 fifo = (status >> SCD_QUEUE_STTS_REG_POS_TXF) & 0x7;
-		bool active = !!(status & BIT(SCD_QUEUE_STTS_REG_POS_ACTIVE));
-		u32 tbl_dw =
-			iwl_trans_read_mem32(trans, trans_pcie->scd_base_addr +
-					     SCD_TRANS_TBL_OFFSET_QUEUE(cnt));
-
-		if (cnt & 0x1)
-			tbl_dw = (tbl_dw & 0xFFFF0000) >> 16;
-		else
-			tbl_dw = tbl_dw & 0x0000FFFF;
+	status = iwl_read_prph(trans, SCD_QUEUE_STATUS_BITS(txq_id));
+	fifo = (status >> SCD_QUEUE_STTS_REG_POS_TXF) & 0x7;
+	active = !!(status & BIT(SCD_QUEUE_STTS_REG_POS_ACTIVE));
 
-		IWL_ERR(trans,
-			"Q %d is %sactive and mapped to fifo %d ra_tid 0x%04x [%d,%d]\n",
-			cnt, active ? "" : "in", fifo, tbl_dw,
-			iwl_read_prph(trans, SCD_QUEUE_RDPTR(cnt)) &
-				(TFD_QUEUE_SIZE_MAX - 1),
-			iwl_read_prph(trans, SCD_QUEUE_WRPTR(cnt)));
-	}
+	IWL_ERR(trans,
+		"Queue %d is %sactive on fifo %d and stuck for %u ms. SW [%d, %d] HW [%d, %d] FH TRB=0x0%x\n",
+		txq_id, active ? "" : "in", fifo,
+		jiffies_to_msecs(txq->wd_timeout),
+		txq->read_ptr, txq->write_ptr,
+		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
+			(TFD_QUEUE_SIZE_MAX - 1),
+		iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
+			(TFD_QUEUE_SIZE_MAX - 1),
+		iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
 }
 
 static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, u32 txq_bm)
@@ -2139,7 +2065,7 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, u32 txq_bm)
 			continue;
 
 		IWL_DEBUG_TX_QUEUES(trans, "Emptying queue %d...\n", cnt);
-		txq = &trans_pcie->txq[cnt];
+		txq = trans_pcie->txq[cnt];
 		wr_ptr = ACCESS_ONCE(txq->write_ptr);
 
 		while (txq->read_ptr != ACCESS_ONCE(txq->write_ptr) &&
@@ -2330,7 +2256,7 @@ static ssize_t iwl_dbgfs_tx_queue_read(struct file *file,
 
 	bufsz = sizeof(char) * 75 * trans->cfg->base_params->num_of_queues;
 
-	if (!trans_pcie->txq)
+	if (!trans_pcie->txq_memory)
 		return -EAGAIN;
 
 	buf = kzalloc(bufsz, GFP_KERNEL);
@@ -2338,7 +2264,7 @@ static ssize_t iwl_dbgfs_tx_queue_read(struct file *file,
 		return -ENOMEM;
 
 	for (cnt = 0; cnt < trans->cfg->base_params->num_of_queues; cnt++) {
-		txq = &trans_pcie->txq[cnt];
+		txq = trans_pcie->txq[cnt];
 		pos += scnprintf(buf + pos, bufsz - pos,
 				"hwq %.2d: read=%u write=%u use=%d stop=%d need_update=%d frozen=%d%s\n",
 				cnt, txq->read_ptr, txq->write_ptr,
@@ -2755,7 +2681,7 @@ static struct iwl_trans_dump_data
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_fw_error_dump_data *data;
-	struct iwl_txq *cmdq = &trans_pcie->txq[trans_pcie->cmd_queue];
+	struct iwl_txq *cmdq = trans_pcie->txq[trans_pcie->cmd_queue];
 	struct iwl_fw_error_dump_txcmd *txcmd;
 	struct iwl_trans_dump_data *dump_data;
 	u32 len, num_rbs;
@@ -2890,21 +2816,43 @@ static void iwl_trans_pcie_resume(struct iwl_trans *trans)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+#define IWL_TRANS_COMMON_OPS						\
+	.op_mode_leave = iwl_trans_pcie_op_mode_leave,			\
+	.write8 = iwl_trans_pcie_write8,				\
+	.write32 = iwl_trans_pcie_write32,				\
+	.read32 = iwl_trans_pcie_read32,				\
+	.read_prph = iwl_trans_pcie_read_prph,				\
+	.write_prph = iwl_trans_pcie_write_prph,			\
+	.read_mem = iwl_trans_pcie_read_mem,				\
+	.write_mem = iwl_trans_pcie_write_mem,				\
+	.configure = iwl_trans_pcie_configure,				\
+	.set_pmi = iwl_trans_pcie_set_pmi,				\
+	.grab_nic_access = iwl_trans_pcie_grab_nic_access,		\
+	.release_nic_access = iwl_trans_pcie_release_nic_access,	\
+	.set_bits_mask = iwl_trans_pcie_set_bits_mask,			\
+	.ref = iwl_trans_pcie_ref,					\
+	.unref = iwl_trans_pcie_unref,					\
+	.dump_data = iwl_trans_pcie_dump_data,				\
+	.wait_tx_queues_empty = iwl_trans_pcie_wait_txq_empty,		\
+	.d3_suspend = iwl_trans_pcie_d3_suspend,			\
+	.d3_resume = iwl_trans_pcie_d3_resume
+
+#ifdef CONFIG_PM_SLEEP
+#define IWL_TRANS_PM_OPS						\
+	.suspend = iwl_trans_pcie_suspend,				\
+	.resume = iwl_trans_pcie_resume,
+#else
+#define IWL_TRANS_PM_OPS
+#endif /* CONFIG_PM_SLEEP */
+
 static const struct iwl_trans_ops trans_ops_pcie = {
+	IWL_TRANS_COMMON_OPS,
+	IWL_TRANS_PM_OPS
 	.start_hw = iwl_trans_pcie_start_hw,
-	.op_mode_leave = iwl_trans_pcie_op_mode_leave,
 	.fw_alive = iwl_trans_pcie_fw_alive,
 	.start_fw = iwl_trans_pcie_start_fw,
 	.stop_device = iwl_trans_pcie_stop_device,
 
-	.d3_suspend = iwl_trans_pcie_d3_suspend,
-	.d3_resume = iwl_trans_pcie_d3_resume,
-
-#ifdef CONFIG_PM_SLEEP
-	.suspend = iwl_trans_pcie_suspend,
-	.resume = iwl_trans_pcie_resume,
-#endif /* CONFIG_PM_SLEEP */
-
 	.send_cmd = iwl_trans_pcie_send_hcmd,
 
 	.tx = iwl_trans_pcie_tx,
@@ -2913,31 +2861,27 @@ static const struct iwl_trans_ops trans_ops_pcie = {
 	.txq_disable = iwl_trans_pcie_txq_disable,
 	.txq_enable = iwl_trans_pcie_txq_enable,
 
-	.get_txq_byte_table = iwl_trans_pcie_get_txq_byte_table,
-
 	.txq_set_shared_mode = iwl_trans_pcie_txq_set_shared_mode,
 
-	.wait_tx_queue_empty = iwl_trans_pcie_wait_txq_empty,
 	.freeze_txq_timer = iwl_trans_pcie_freeze_txq_timer,
 	.block_txq_ptrs = iwl_trans_pcie_block_txq_ptrs,
+};
+
+static const struct iwl_trans_ops trans_ops_pcie_gen2 = {
+	IWL_TRANS_COMMON_OPS,
+	IWL_TRANS_PM_OPS
+	.start_hw = iwl_trans_pcie_start_hw,
+	.fw_alive = iwl_trans_pcie_gen2_fw_alive,
+	.start_fw = iwl_trans_pcie_gen2_start_fw,
+	.stop_device = iwl_trans_pcie_gen2_stop_device,
 
-	.write8 = iwl_trans_pcie_write8,
-	.write32 = iwl_trans_pcie_write32,
-	.read32 = iwl_trans_pcie_read32,
-	.read_prph = iwl_trans_pcie_read_prph,
-	.write_prph = iwl_trans_pcie_write_prph,
-	.read_mem = iwl_trans_pcie_read_mem,
-	.write_mem = iwl_trans_pcie_write_mem,
-	.configure = iwl_trans_pcie_configure,
-	.set_pmi = iwl_trans_pcie_set_pmi,
-	.grab_nic_access = iwl_trans_pcie_grab_nic_access,
-	.release_nic_access = iwl_trans_pcie_release_nic_access,
-	.set_bits_mask = iwl_trans_pcie_set_bits_mask,
-
-	.ref = iwl_trans_pcie_ref,
-	.unref = iwl_trans_pcie_unref,
-
-	.dump_data = iwl_trans_pcie_dump_data,
+	.send_cmd = iwl_trans_pcie_gen2_send_hcmd,
+
+	.tx = iwl_trans_pcie_gen2_tx,
+	.reclaim = iwl_trans_pcie_reclaim,
+
+	.txq_alloc = iwl_trans_pcie_dyn_txq_alloc,
+	.txq_free = iwl_trans_pcie_dyn_txq_free,
 };
 
 struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
@@ -2952,8 +2896,12 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	if (ret)
 		return ERR_PTR(ret);
 
-	trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
-				&pdev->dev, cfg, &trans_ops_pcie, 0);
+	if (cfg->gen2)
+		trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
+					&pdev->dev, cfg, &trans_ops_pcie_gen2);
+	else
+		trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
+					&pdev->dev, cfg, &trans_ops_pcie);
 	if (!trans)
 		return ERR_PTR(-ENOMEM);
 
@@ -3028,7 +2976,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	 * PCI Tx retries from interfering with C3 CPU state */
 	pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00);
 
-	trans->dev = &pdev->dev;
 	trans_pcie->pci_dev = pdev;
 	iwl_disable_interrupts(trans);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
new file mode 100644
index 000000000000..9fb46a6f47cf
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -0,0 +1,1018 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#include <linux/pm_runtime.h>
+
+#include "iwl-debug.h"
+#include "iwl-csr.h"
+#include "iwl-io.h"
+#include "internal.h"
+#include "mvm/fw-api.h"
+
+ /*
+ * iwl_pcie_gen2_tx_stop - Stop all Tx DMA channels
+ */
+void iwl_pcie_gen2_tx_stop(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int txq_id;
+
+	/*
+	 * This function can be called before the op_mode disabled the
+	 * queues. This happens when we have an rfkill interrupt.
+	 * Since we stop Tx altogether - mark the queues as stopped.
+	 */
+	memset(trans_pcie->queue_stopped, 0, sizeof(trans_pcie->queue_stopped));
+	memset(trans_pcie->queue_used, 0, sizeof(trans_pcie->queue_used));
+
+	/* Unmap DMA from host system and free skb's */
+	for (txq_id = 0; txq_id < ARRAY_SIZE(trans_pcie->txq); txq_id++) {
+		if (!trans_pcie->txq[txq_id])
+			continue;
+		iwl_pcie_gen2_txq_unmap(trans, txq_id);
+	}
+}
+
+/*
+ * iwl_pcie_txq_update_byte_tbl - Set up entry in Tx byte-count array
+ */
+static void iwl_pcie_gen2_update_byte_tbl(struct iwl_txq *txq, u16 byte_cnt,
+					  int num_tbs)
+{
+	struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
+	int write_ptr = txq->write_ptr;
+	u8 filled_tfd_size, num_fetch_chunks;
+	u16 len = byte_cnt;
+	__le16 bc_ent;
+
+	len = DIV_ROUND_UP(len, 4);
+
+	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))
+		return;
+
+	filled_tfd_size = offsetof(struct iwl_tfh_tfd, tbs) +
+				   num_tbs * sizeof(struct iwl_tfh_tb);
+	/*
+	 * filled_tfd_size contains the number of filled bytes in the TFD.
+	 * Dividing it by 64 will give the number of chunks to fetch
+	 * to SRAM- 0 for one chunk, 1 for 2 and so on.
+	 * If, for example, TFD contains only 3 TBs then 32 bytes
+	 * of the TFD are used, and only one chunk of 64 bytes should
+	 * be fetched
+	 */
+	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
+
+	bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
+	scd_bc_tbl->tfd_offset[write_ptr] = bc_ent;
+}
+
+/*
+ * iwl_pcie_gen2_txq_inc_wr_ptr - Send new write index to hardware
+ */
+static void iwl_pcie_gen2_txq_inc_wr_ptr(struct iwl_trans *trans,
+					 struct iwl_txq *txq)
+{
+	lockdep_assert_held(&txq->lock);
+
+	IWL_DEBUG_TX(trans, "Q:%d WR: 0x%x\n", txq->id, txq->write_ptr);
+
+	/*
+	 * if not in power-save mode, uCode will never sleep when we're
+	 * trying to tx (during RFKILL, we're not trying to tx).
+	 */
+	iwl_write32(trans, HBUS_TARG_WRPTR, txq->write_ptr | (txq->id << 16));
+}
+
+static u8 iwl_pcie_gen2_get_num_tbs(struct iwl_trans *trans,
+				    struct iwl_tfh_tfd *tfd)
+{
+	return le16_to_cpu(tfd->num_tbs) & 0x1f;
+}
+
+static void iwl_pcie_gen2_tfd_unmap(struct iwl_trans *trans,
+				    struct iwl_cmd_meta *meta,
+				    struct iwl_tfh_tfd *tfd)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int i, num_tbs;
+
+	/* Sanity check on number of chunks */
+	num_tbs = iwl_pcie_gen2_get_num_tbs(trans, tfd);
+
+	if (num_tbs >= trans_pcie->max_tbs) {
+		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
+		return;
+	}
+
+	/* first TB is never freed - it's the bidirectional DMA data */
+	for (i = 1; i < num_tbs; i++) {
+		if (meta->tbs & BIT(i))
+			dma_unmap_page(trans->dev,
+				       le64_to_cpu(tfd->tbs[i].addr),
+				       le16_to_cpu(tfd->tbs[i].tb_len),
+				       DMA_TO_DEVICE);
+		else
+			dma_unmap_single(trans->dev,
+					 le64_to_cpu(tfd->tbs[i].addr),
+					 le16_to_cpu(tfd->tbs[i].tb_len),
+					 DMA_TO_DEVICE);
+	}
+
+	tfd->num_tbs = 0;
+}
+
+static void iwl_pcie_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	/* rd_ptr is bounded by TFD_QUEUE_SIZE_MAX and
+	 * idx is bounded by n_window
+	 */
+	int rd_ptr = txq->read_ptr;
+	int idx = get_cmd_index(txq, rd_ptr);
+
+	lockdep_assert_held(&txq->lock);
+
+	/* We have only q->n_window txq->entries, but we use
+	 * TFD_QUEUE_SIZE_MAX tfds
+	 */
+	iwl_pcie_gen2_tfd_unmap(trans, &txq->entries[idx].meta,
+				iwl_pcie_get_tfd(trans_pcie, txq, rd_ptr));
+
+	/* free SKB */
+	if (txq->entries) {
+		struct sk_buff *skb;
+
+		skb = txq->entries[idx].skb;
+
+		/* Can be called from irqs-disabled context
+		 * If skb is not NULL, it means that the whole queue is being
+		 * freed and that the queue is not empty - free the skb
+		 */
+		if (skb) {
+			iwl_op_mode_free_skb(trans->op_mode, skb);
+			txq->entries[idx].skb = NULL;
+		}
+	}
+}
+
+static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
+				struct iwl_tfh_tfd *tfd, dma_addr_t addr,
+				u16 len)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int idx = iwl_pcie_gen2_get_num_tbs(trans, tfd);
+	struct iwl_tfh_tb *tb = &tfd->tbs[idx];
+
+	/* Each TFD can point to a maximum max_tbs Tx buffers */
+	if (le16_to_cpu(tfd->num_tbs) >= trans_pcie->max_tbs) {
+		IWL_ERR(trans, "Error can not send more than %d chunks\n",
+			trans_pcie->max_tbs);
+		return -EINVAL;
+	}
+
+	put_unaligned_le64(addr, &tb->addr);
+	tb->tb_len = cpu_to_le16(len);
+
+	tfd->num_tbs = cpu_to_le16(idx + 1);
+
+	return idx;
+}
+
+static
+struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
+					    struct iwl_txq *txq,
+					    struct iwl_device_cmd *dev_cmd,
+					    struct sk_buff *skb,
+					    struct iwl_cmd_meta *out_meta)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct iwl_tfh_tfd *tfd =
+		iwl_pcie_get_tfd(trans_pcie, txq, txq->write_ptr);
+	dma_addr_t tb_phys;
+	int i, len, tb1_len, tb2_len, hdr_len;
+	void *tb1_addr;
+
+	memset(tfd, 0, sizeof(*tfd));
+
+	tb_phys = iwl_pcie_get_first_tb_dma(txq, txq->write_ptr);
+	/* The first TB points to bi-directional DMA data */
+	memcpy(&txq->first_tb_bufs[txq->write_ptr], &dev_cmd->hdr,
+	       IWL_FIRST_TB_SIZE);
+
+	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
+
+	/* there must be data left over for TB1 or this code must be changed */
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
+
+	/*
+	 * The second TB (tb1) points to the remainder of the TX command
+	 * and the 802.11 header - dword aligned size
+	 * (This calculation modifies the TX command, so do it before the
+	 * setup of the first TB)
+	 */
+	len = sizeof(struct iwl_tx_cmd_gen2) + sizeof(struct iwl_cmd_header) +
+	      ieee80211_hdrlen(hdr->frame_control) - IWL_FIRST_TB_SIZE;
+
+	tb1_len = ALIGN(len, 4);
+
+	/* map the data for TB1 */
+	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
+	tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		goto out_err;
+	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
+
+	/* set up TFD's third entry to point to remainder of skb's head */
+	hdr_len = ieee80211_hdrlen(hdr->frame_control);
+	tb2_len = skb_headlen(skb) - hdr_len;
+
+	if (tb2_len > 0) {
+		tb_phys = dma_map_single(trans->dev, skb->data + hdr_len,
+					 tb2_len, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+			goto out_err;
+		iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb2_len);
+	}
+
+	/* set up the remaining entries to point to the data */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		int tb_idx;
+
+		if (!skb_frag_size(frag))
+			continue;
+
+		tb_phys = skb_frag_dma_map(trans->dev, frag, 0,
+					   skb_frag_size(frag), DMA_TO_DEVICE);
+
+		if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+			goto out_err;
+		tb_idx = iwl_pcie_gen2_set_tb(trans, tfd, tb_phys,
+					      skb_frag_size(frag));
+
+		out_meta->tbs |= BIT(tb_idx);
+	}
+
+	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr,
+			     IWL_FIRST_TB_SIZE + tb1_len,
+			     skb->data + hdr_len, tb2_len);
+	trace_iwlwifi_dev_tx_data(trans->dev, skb, hdr_len,
+				  skb->len - hdr_len);
+
+	return tfd;
+
+out_err:
+	iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+	return NULL;
+}
+
+int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
+			   struct iwl_device_cmd *dev_cmd, int txq_id)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
+	struct iwl_cmd_meta *out_meta;
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
+	void *tfd;
+
+	if (WARN_ONCE(!test_bit(txq_id, trans_pcie->queue_used),
+		      "TX on unused queue %d\n", txq_id))
+		return -EINVAL;
+
+	if (skb_is_nonlinear(skb) &&
+	    skb_shinfo(skb)->nr_frags > IWL_PCIE_MAX_FRAGS(trans_pcie) &&
+	    __skb_linearize(skb))
+		return -ENOMEM;
+
+	spin_lock(&txq->lock);
+
+	/* Set up driver data for this TFD */
+	txq->entries[txq->write_ptr].skb = skb;
+	txq->entries[txq->write_ptr].cmd = dev_cmd;
+
+	dev_cmd->hdr.sequence =
+		cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
+			    INDEX_TO_SEQ(txq->write_ptr)));
+
+	/* Set up first empty entry in queue's array of Tx/cmd buffers */
+	out_meta = &txq->entries[txq->write_ptr].meta;
+	out_meta->flags = 0;
+
+	tfd = iwl_pcie_gen2_build_tfd(trans, txq, dev_cmd, skb, out_meta);
+	if (!tfd) {
+		spin_unlock(&txq->lock);
+		return -1;
+	}
+
+	/* Set up entry for this TFD in Tx byte-count array */
+	iwl_pcie_gen2_update_byte_tbl(txq, le16_to_cpu(tx_cmd->len),
+				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
+
+	/* start timer if queue currently empty */
+	if (txq->read_ptr == txq->write_ptr) {
+		if (txq->wd_timeout)
+			mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
+		IWL_DEBUG_RPM(trans, "Q: %d first tx - take ref\n", txq->id);
+		iwl_trans_ref(trans);
+	}
+
+	/* Tell device the write index *just past* this latest filled TFD */
+	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
+	if (iwl_queue_space(txq) < txq->high_mark)
+		iwl_stop_queue(trans, txq);
+
+	/*
+	 * At this point the frame is "transmitted" successfully
+	 * and we will get a TX status notification eventually.
+	 */
+	spin_unlock(&txq->lock);
+	return 0;
+}
+
+/*************** HOST COMMAND QUEUE FUNCTIONS   *****/
+
+/*
+ * iwl_pcie_gen2_enqueue_hcmd - enqueue a uCode command
+ * @priv: device private data point
+ * @cmd: a pointer to the ucode command structure
+ *
+ * The function returns < 0 values to indicate the operation
+ * failed. On success, it returns the index (>= 0) of command in the
+ * command queue.
+ */
+static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
+				      struct iwl_host_cmd *cmd)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_txq *txq = trans_pcie->txq[trans_pcie->cmd_queue];
+	struct iwl_device_cmd *out_cmd;
+	struct iwl_cmd_meta *out_meta;
+	unsigned long flags;
+	void *dup_buf = NULL;
+	dma_addr_t phys_addr;
+	int idx, i, cmd_pos;
+	u16 copy_size, cmd_size, tb0_size;
+	bool had_nocopy = false;
+	u8 group_id = iwl_cmd_groupid(cmd->id);
+	const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD];
+	u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
+	struct iwl_tfh_tfd *tfd =
+		iwl_pcie_get_tfd(trans_pcie, txq, txq->write_ptr);
+
+	memset(tfd, 0, sizeof(*tfd));
+
+	copy_size = sizeof(struct iwl_cmd_header_wide);
+	cmd_size = sizeof(struct iwl_cmd_header_wide);
+
+	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
+		cmddata[i] = cmd->data[i];
+		cmdlen[i] = cmd->len[i];
+
+		if (!cmd->len[i])
+			continue;
+
+		/* need at least IWL_FIRST_TB_SIZE copied */
+		if (copy_size < IWL_FIRST_TB_SIZE) {
+			int copy = IWL_FIRST_TB_SIZE - copy_size;
+
+			if (copy > cmdlen[i])
+				copy = cmdlen[i];
+			cmdlen[i] -= copy;
+			cmddata[i] += copy;
+			copy_size += copy;
+		}
+
+		if (cmd->dataflags[i] & IWL_HCMD_DFL_NOCOPY) {
+			had_nocopy = true;
+			if (WARN_ON(cmd->dataflags[i] & IWL_HCMD_DFL_DUP)) {
+				idx = -EINVAL;
+				goto free_dup_buf;
+			}
+		} else if (cmd->dataflags[i] & IWL_HCMD_DFL_DUP) {
+			/*
+			 * This is also a chunk that isn't copied
+			 * to the static buffer so set had_nocopy.
+			 */
+			had_nocopy = true;
+
+			/* only allowed once */
+			if (WARN_ON(dup_buf)) {
+				idx = -EINVAL;
+				goto free_dup_buf;
+			}
+
+			dup_buf = kmemdup(cmddata[i], cmdlen[i],
+					  GFP_ATOMIC);
+			if (!dup_buf)
+				return -ENOMEM;
+		} else {
+			/* NOCOPY must not be followed by normal! */
+			if (WARN_ON(had_nocopy)) {
+				idx = -EINVAL;
+				goto free_dup_buf;
+			}
+			copy_size += cmdlen[i];
+		}
+		cmd_size += cmd->len[i];
+	}
+
+	/*
+	 * If any of the command structures end up being larger than the
+	 * TFD_MAX_PAYLOAD_SIZE and they aren't dynamically allocated into
+	 * separate TFDs, then we will need to increase the size of the buffers
+	 */
+	if (WARN(copy_size > TFD_MAX_PAYLOAD_SIZE,
+		 "Command %s (%#x) is too large (%d bytes)\n",
+		 iwl_get_cmd_string(trans, cmd->id), cmd->id, copy_size)) {
+		idx = -EINVAL;
+		goto free_dup_buf;
+	}
+
+	spin_lock_bh(&txq->lock);
+
+	if (iwl_queue_space(txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+		spin_unlock_bh(&txq->lock);
+
+		IWL_ERR(trans, "No space in command queue\n");
+		iwl_op_mode_cmd_queue_full(trans->op_mode);
+		idx = -ENOSPC;
+		goto free_dup_buf;
+	}
+
+	idx = get_cmd_index(txq, txq->write_ptr);
+	out_cmd = txq->entries[idx].cmd;
+	out_meta = &txq->entries[idx].meta;
+
+	/* re-initialize to NULL */
+	memset(out_meta, 0, sizeof(*out_meta));
+	if (cmd->flags & CMD_WANT_SKB)
+		out_meta->source = cmd;
+
+	/* set up the header */
+	out_cmd->hdr_wide.cmd = iwl_cmd_opcode(cmd->id);
+	out_cmd->hdr_wide.group_id = group_id;
+	out_cmd->hdr_wide.version = iwl_cmd_version(cmd->id);
+	out_cmd->hdr_wide.length =
+		cpu_to_le16(cmd_size - sizeof(struct iwl_cmd_header_wide));
+	out_cmd->hdr_wide.reserved = 0;
+	out_cmd->hdr_wide.sequence =
+		cpu_to_le16(QUEUE_TO_SEQ(trans_pcie->cmd_queue) |
+					 INDEX_TO_SEQ(txq->write_ptr));
+
+	cmd_pos = sizeof(struct iwl_cmd_header_wide);
+	copy_size = sizeof(struct iwl_cmd_header_wide);
+
+	/* and copy the data that needs to be copied */
+	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
+		int copy;
+
+		if (!cmd->len[i])
+			continue;
+
+		/* copy everything if not nocopy/dup */
+		if (!(cmd->dataflags[i] & (IWL_HCMD_DFL_NOCOPY |
+					   IWL_HCMD_DFL_DUP))) {
+			copy = cmd->len[i];
+
+			memcpy((u8 *)out_cmd + cmd_pos, cmd->data[i], copy);
+			cmd_pos += copy;
+			copy_size += copy;
+			continue;
+		}
+
+		/*
+		 * Otherwise we need at least IWL_FIRST_TB_SIZE copied
+		 * in total (for bi-directional DMA), but copy up to what
+		 * we can fit into the payload for debug dump purposes.
+		 */
+		copy = min_t(int, TFD_MAX_PAYLOAD_SIZE - cmd_pos, cmd->len[i]);
+
+		memcpy((u8 *)out_cmd + cmd_pos, cmd->data[i], copy);
+		cmd_pos += copy;
+
+		/* However, treat copy_size the proper way, we need it below */
+		if (copy_size < IWL_FIRST_TB_SIZE) {
+			copy = IWL_FIRST_TB_SIZE - copy_size;
+
+			if (copy > cmd->len[i])
+				copy = cmd->len[i];
+			copy_size += copy;
+		}
+	}
+
+	IWL_DEBUG_HC(trans,
+		     "Sending command %s (%.2x.%.2x), seq: 0x%04X, %d bytes at %d[%d]:%d\n",
+		     iwl_get_cmd_string(trans, cmd->id), group_id,
+		     out_cmd->hdr.cmd, le16_to_cpu(out_cmd->hdr.sequence),
+		     cmd_size, txq->write_ptr, idx, trans_pcie->cmd_queue);
+
+	/* start the TFD with the minimum copy bytes */
+	tb0_size = min_t(int, copy_size, IWL_FIRST_TB_SIZE);
+	memcpy(&txq->first_tb_bufs[idx], &out_cmd->hdr, tb0_size);
+	iwl_pcie_gen2_set_tb(trans, tfd, iwl_pcie_get_first_tb_dma(txq, idx),
+			     tb0_size);
+
+	/* map first command fragment, if any remains */
+	if (copy_size > tb0_size) {
+		phys_addr = dma_map_single(trans->dev,
+					   ((u8 *)&out_cmd->hdr) + tb0_size,
+					   copy_size - tb0_size,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(trans->dev, phys_addr)) {
+			idx = -ENOMEM;
+			iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+			goto out;
+		}
+		iwl_pcie_gen2_set_tb(trans, tfd, phys_addr,
+				     copy_size - tb0_size);
+	}
+
+	/* map the remaining (adjusted) nocopy/dup fragments */
+	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
+		const void *data = cmddata[i];
+
+		if (!cmdlen[i])
+			continue;
+		if (!(cmd->dataflags[i] & (IWL_HCMD_DFL_NOCOPY |
+					   IWL_HCMD_DFL_DUP)))
+			continue;
+		if (cmd->dataflags[i] & IWL_HCMD_DFL_DUP)
+			data = dup_buf;
+		phys_addr = dma_map_single(trans->dev, (void *)data,
+					   cmdlen[i], DMA_TO_DEVICE);
+		if (dma_mapping_error(trans->dev, phys_addr)) {
+			idx = -ENOMEM;
+			iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+			goto out;
+		}
+		iwl_pcie_gen2_set_tb(trans, tfd, phys_addr, cmdlen[i]);
+	}
+
+	BUILD_BUG_ON(IWL_TFH_NUM_TBS > sizeof(out_meta->tbs) * BITS_PER_BYTE);
+	out_meta->flags = cmd->flags;
+	if (WARN_ON_ONCE(txq->entries[idx].free_buf))
+		kzfree(txq->entries[idx].free_buf);
+	txq->entries[idx].free_buf = dup_buf;
+
+	trace_iwlwifi_dev_hcmd(trans->dev, cmd, cmd_size, &out_cmd->hdr_wide);
+
+	/* start timer if queue currently empty */
+	if (txq->read_ptr == txq->write_ptr && txq->wd_timeout)
+		mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
+
+	spin_lock_irqsave(&trans_pcie->reg_lock, flags);
+	if (!(cmd->flags & CMD_SEND_IN_IDLE) &&
+	    !trans_pcie->ref_cmd_in_flight) {
+		trans_pcie->ref_cmd_in_flight = true;
+		IWL_DEBUG_RPM(trans, "set ref_cmd_in_flight - ref\n");
+		iwl_trans_ref(trans);
+	}
+	/* Increment and update queue's write index */
+	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
+	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
+
+out:
+	spin_unlock_bh(&txq->lock);
+free_dup_buf:
+	if (idx < 0)
+		kfree(dup_buf);
+	return idx;
+}
+
+#define HOST_COMPLETE_TIMEOUT	(2 * HZ)
+
+static int iwl_pcie_gen2_send_hcmd_sync(struct iwl_trans *trans,
+					struct iwl_host_cmd *cmd)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	const char *cmd_str = iwl_get_cmd_string(trans, cmd->id);
+	struct iwl_txq *txq = trans_pcie->txq[trans_pcie->cmd_queue];
+	int cmd_idx;
+	int ret;
+
+	IWL_DEBUG_INFO(trans, "Attempting to send sync command %s\n", cmd_str);
+
+	if (WARN(test_and_set_bit(STATUS_SYNC_HCMD_ACTIVE,
+				  &trans->status),
+		 "Command %s: a command is already active!\n", cmd_str))
+		return -EIO;
+
+	IWL_DEBUG_INFO(trans, "Setting HCMD_ACTIVE for command %s\n", cmd_str);
+
+	if (pm_runtime_suspended(&trans_pcie->pci_dev->dev)) {
+		ret = wait_event_timeout(trans_pcie->d0i3_waitq,
+				 pm_runtime_active(&trans_pcie->pci_dev->dev),
+				 msecs_to_jiffies(IWL_TRANS_IDLE_TIMEOUT));
+		if (!ret) {
+			IWL_ERR(trans, "Timeout exiting D0i3 before hcmd\n");
+			return -ETIMEDOUT;
+		}
+	}
+
+	cmd_idx = iwl_pcie_gen2_enqueue_hcmd(trans, cmd);
+	if (cmd_idx < 0) {
+		ret = cmd_idx;
+		clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
+		IWL_ERR(trans, "Error sending %s: enqueue_hcmd failed: %d\n",
+			cmd_str, ret);
+		return ret;
+	}
+
+	ret = wait_event_timeout(trans_pcie->wait_command_queue,
+				 !test_bit(STATUS_SYNC_HCMD_ACTIVE,
+					   &trans->status),
+				 HOST_COMPLETE_TIMEOUT);
+	if (!ret) {
+		IWL_ERR(trans, "Error sending %s: time out after %dms.\n",
+			cmd_str, jiffies_to_msecs(HOST_COMPLETE_TIMEOUT));
+
+		IWL_ERR(trans, "Current CMD queue read_ptr %d write_ptr %d\n",
+			txq->read_ptr, txq->write_ptr);
+
+		clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
+		IWL_DEBUG_INFO(trans, "Clearing HCMD_ACTIVE for command %s\n",
+			       cmd_str);
+		ret = -ETIMEDOUT;
+
+		iwl_force_nmi(trans);
+		iwl_trans_fw_error(trans);
+
+		goto cancel;
+	}
+
+	if (test_bit(STATUS_FW_ERROR, &trans->status)) {
+		IWL_ERR(trans, "FW error in SYNC CMD %s\n", cmd_str);
+		dump_stack();
+		ret = -EIO;
+		goto cancel;
+	}
+
+	if (!(cmd->flags & CMD_SEND_IN_RFKILL) &&
+	    test_bit(STATUS_RFKILL, &trans->status)) {
+		IWL_DEBUG_RF_KILL(trans, "RFKILL in SYNC CMD... no rsp\n");
+		ret = -ERFKILL;
+		goto cancel;
+	}
+
+	if ((cmd->flags & CMD_WANT_SKB) && !cmd->resp_pkt) {
+		IWL_ERR(trans, "Error: Response NULL in '%s'\n", cmd_str);
+		ret = -EIO;
+		goto cancel;
+	}
+
+	return 0;
+
+cancel:
+	if (cmd->flags & CMD_WANT_SKB) {
+		/*
+		 * Cancel the CMD_WANT_SKB flag for the cmd in the
+		 * TX cmd queue. Otherwise in case the cmd comes
+		 * in later, it will possibly set an invalid
+		 * address (cmd->meta.source).
+		 */
+		txq->entries[cmd_idx].meta.flags &= ~CMD_WANT_SKB;
+	}
+
+	if (cmd->resp_pkt) {
+		iwl_free_resp(cmd);
+		cmd->resp_pkt = NULL;
+	}
+
+	return ret;
+}
+
+int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
+				  struct iwl_host_cmd *cmd)
+{
+	if (!(cmd->flags & CMD_SEND_IN_RFKILL) &&
+	    test_bit(STATUS_RFKILL, &trans->status)) {
+		IWL_DEBUG_RF_KILL(trans, "Dropping CMD 0x%x: RF KILL\n",
+				  cmd->id);
+		return -ERFKILL;
+	}
+
+	if (cmd->flags & CMD_ASYNC) {
+		int ret;
+
+		/* An asynchronous command can not expect an SKB to be set. */
+		if (WARN_ON(cmd->flags & CMD_WANT_SKB))
+			return -EINVAL;
+
+		ret = iwl_pcie_gen2_enqueue_hcmd(trans, cmd);
+		if (ret < 0) {
+			IWL_ERR(trans,
+				"Error sending %s: enqueue_hcmd failed: %d\n",
+				iwl_get_cmd_string(trans, cmd->id), ret);
+			return ret;
+		}
+		return 0;
+	}
+
+	return iwl_pcie_gen2_send_hcmd_sync(trans, cmd);
+}
+
+/*
+ * iwl_pcie_gen2_txq_unmap -  Unmap any remaining DMA mappings and free skb's
+ */
+void iwl_pcie_gen2_txq_unmap(struct iwl_trans *trans, int txq_id)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
+
+	spin_lock_bh(&txq->lock);
+	while (txq->write_ptr != txq->read_ptr) {
+		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
+				   txq_id, txq->read_ptr);
+
+		iwl_pcie_gen2_free_tfd(trans, txq);
+		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
+
+		if (txq->read_ptr == txq->write_ptr) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&trans_pcie->reg_lock, flags);
+			if (txq_id != trans_pcie->cmd_queue) {
+				IWL_DEBUG_RPM(trans, "Q %d - last tx freed\n",
+					      txq->id);
+				iwl_trans_unref(trans);
+			} else if (trans_pcie->ref_cmd_in_flight) {
+				trans_pcie->ref_cmd_in_flight = false;
+				IWL_DEBUG_RPM(trans,
+					      "clear ref_cmd_in_flight\n");
+				iwl_trans_unref(trans);
+			}
+			spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
+		}
+	}
+	spin_unlock_bh(&txq->lock);
+
+	/* just in case - this queue may have been stopped */
+	iwl_wake_queue(trans, txq);
+}
+
+static void iwl_pcie_gen2_txq_free_memory(struct iwl_trans *trans,
+					  struct iwl_txq *txq)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct device *dev = trans->dev;
+
+	/* De-alloc circular buffer of TFDs */
+	if (txq->tfds) {
+		dma_free_coherent(dev,
+				  trans_pcie->tfd_size * TFD_QUEUE_SIZE_MAX,
+				  txq->tfds, txq->dma_addr);
+		dma_free_coherent(dev,
+				  sizeof(*txq->first_tb_bufs) * txq->n_window,
+				  txq->first_tb_bufs, txq->first_tb_dma);
+	}
+
+	kfree(txq->entries);
+	iwl_pcie_free_dma_ptr(trans, &txq->bc_tbl);
+	kfree(txq);
+}
+
+/*
+ * iwl_pcie_txq_free - Deallocate DMA queue.
+ * @txq: Transmit queue to deallocate.
+ *
+ * Empty queue by removing and destroying all BD's.
+ * Free all buffers.
+ * 0-fill, but do not free "txq" descriptor structure.
+ */
+static void iwl_pcie_gen2_txq_free(struct iwl_trans *trans, int txq_id)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
+	int i;
+
+	if (WARN_ON(!txq))
+		return;
+
+	iwl_pcie_gen2_txq_unmap(trans, txq_id);
+
+	/* De-alloc array of command/tx buffers */
+	if (txq_id == trans_pcie->cmd_queue)
+		for (i = 0; i < txq->n_window; i++) {
+			kzfree(txq->entries[i].cmd);
+			kzfree(txq->entries[i].free_buf);
+		}
+	del_timer_sync(&txq->stuck_timer);
+
+	iwl_pcie_gen2_txq_free_memory(trans, txq);
+
+	trans_pcie->txq[txq_id] = NULL;
+
+	clear_bit(txq_id, trans_pcie->queue_used);
+}
+
+int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
+				 struct iwl_tx_queue_cfg_cmd *cmd,
+				 int cmd_id,
+				 unsigned int timeout)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_tx_queue_cfg_rsp *rsp;
+	struct iwl_txq *txq;
+	struct iwl_host_cmd hcmd = {
+		.id = cmd_id,
+		.len = { sizeof(*cmd) },
+		.data = { cmd, },
+		.flags = CMD_WANT_SKB,
+	};
+	int ret, qid;
+
+	txq = kzalloc(sizeof(*txq), GFP_KERNEL);
+	if (!txq)
+		return -ENOMEM;
+	ret = iwl_pcie_alloc_dma_ptr(trans, &txq->bc_tbl,
+				     sizeof(struct iwlagn_scd_bc_tbl));
+	if (ret) {
+		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
+		kfree(txq);
+		return -ENOMEM;
+	}
+
+	ret = iwl_pcie_txq_alloc(trans, txq, TFD_TX_CMD_SLOTS, false);
+	if (ret) {
+		IWL_ERR(trans, "Tx queue alloc failed\n");
+		goto error;
+	}
+	ret = iwl_pcie_txq_init(trans, txq, TFD_TX_CMD_SLOTS, false);
+	if (ret) {
+		IWL_ERR(trans, "Tx queue init failed\n");
+		goto error;
+	}
+
+	txq->wd_timeout = msecs_to_jiffies(timeout);
+
+	cmd->tfdq_addr = cpu_to_le64(txq->dma_addr);
+	cmd->byte_cnt_addr = cpu_to_le64(txq->bc_tbl.dma);
+	cmd->cb_size = cpu_to_le32(TFD_QUEUE_CB_SIZE(TFD_QUEUE_SIZE_MAX));
+
+	ret = iwl_trans_send_cmd(trans, &hcmd);
+	if (ret)
+		goto error;
+
+	if (WARN_ON(iwl_rx_packet_payload_len(hcmd.resp_pkt) != sizeof(*rsp))) {
+		ret = -EINVAL;
+		goto error;
+	}
+
+	rsp = (void *)hcmd.resp_pkt->data;
+	qid = le16_to_cpu(rsp->queue_number);
+
+	if (qid > ARRAY_SIZE(trans_pcie->txq)) {
+		WARN_ONCE(1, "queue index %d unsupported", qid);
+		ret = -EIO;
+		goto error;
+	}
+
+	if (test_and_set_bit(qid, trans_pcie->queue_used)) {
+		WARN_ONCE(1, "queue %d already used", qid);
+		ret = -EIO;
+		goto error;
+	}
+
+	txq->id = qid;
+	trans_pcie->txq[qid] = txq;
+
+	/* Place first TFD at index corresponding to start sequence number */
+	txq->read_ptr = le16_to_cpu(rsp->write_pointer);
+	txq->write_ptr = le16_to_cpu(rsp->write_pointer);
+	iwl_write_direct32(trans, HBUS_TARG_WRPTR,
+			   (txq->write_ptr) | (qid << 16));
+	IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d\n", qid);
+
+	return qid;
+
+error:
+	iwl_pcie_gen2_txq_free_memory(trans, txq);
+	return ret;
+}
+
+void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	/*
+	 * Upon HW Rfkill - we stop the device, and then stop the queues
+	 * in the op_mode. Just for the sake of the simplicity of the op_mode,
+	 * allow the op_mode to call txq_disable after it already called
+	 * stop_device.
+	 */
+	if (!test_and_clear_bit(queue, trans_pcie->queue_used)) {
+		WARN_ONCE(test_bit(STATUS_DEVICE_ENABLED, &trans->status),
+			  "queue %d not used", queue);
+		return;
+	}
+
+	iwl_pcie_gen2_txq_unmap(trans, queue);
+
+	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue);
+}
+
+void iwl_pcie_gen2_tx_free(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int i;
+
+	memset(trans_pcie->queue_used, 0, sizeof(trans_pcie->queue_used));
+
+	/* Free all TX queues */
+	for (i = 0; i < ARRAY_SIZE(trans_pcie->txq); i++) {
+		if (!trans_pcie->txq[i])
+			continue;
+
+		iwl_pcie_gen2_txq_free(trans, i);
+	}
+}
+
+int iwl_pcie_gen2_tx_init(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_txq *cmd_queue;
+	int txq_id = trans_pcie->cmd_queue, ret;
+
+	/* alloc and init the command queue */
+	if (!trans_pcie->txq[txq_id]) {
+		cmd_queue = kzalloc(sizeof(*cmd_queue), GFP_KERNEL);
+		if (!cmd_queue) {
+			IWL_ERR(trans, "Not enough memory for command queue\n");
+			return -ENOMEM;
+		}
+		trans_pcie->txq[txq_id] = cmd_queue;
+		ret = iwl_pcie_txq_alloc(trans, cmd_queue, TFD_CMD_SLOTS, true);
+		if (ret) {
+			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
+			goto error;
+		}
+	} else {
+		cmd_queue = trans_pcie->txq[txq_id];
+	}
+
+	ret = iwl_pcie_txq_init(trans, cmd_queue, TFD_CMD_SLOTS, true);
+	if (ret) {
+		IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
+		goto error;
+	}
+	trans_pcie->txq[txq_id]->id = txq_id;
+	set_bit(txq_id, trans_pcie->queue_used);
+
+	return 0;
+
+error:
+	iwl_pcie_gen2_tx_free(trans);
+	return ret;
+}
+
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 911cf9868107..386950a2d616 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -2,7 +2,7 @@
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -71,7 +71,7 @@
  *
  ***************************************************/
 
-static int iwl_queue_space(const struct iwl_txq *q)
+int iwl_queue_space(const struct iwl_txq *q)
 {
 	unsigned int max;
 	unsigned int used;
@@ -102,10 +102,9 @@ static int iwl_queue_space(const struct iwl_txq *q)
 /*
  * iwl_queue_init - Initialize queue's high/low-water and read/write indexes
  */
-static int iwl_queue_init(struct iwl_txq *q, int slots_num, u32 id)
+static int iwl_queue_init(struct iwl_txq *q, int slots_num)
 {
 	q->n_window = slots_num;
-	q->id = id;
 
 	/* slots_num must be power-of-two size, otherwise
 	 * get_cmd_index is broken. */
@@ -126,8 +125,8 @@ static int iwl_queue_init(struct iwl_txq *q, int slots_num, u32 id)
 	return 0;
 }
 
-static int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
-				  struct iwl_dma_ptr *ptr, size_t size)
+int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
+			   struct iwl_dma_ptr *ptr, size_t size)
 {
 	if (WARN_ON(ptr->addr))
 		return -EINVAL;
@@ -140,8 +139,7 @@ static int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
 	return 0;
 }
 
-static void iwl_pcie_free_dma_ptr(struct iwl_trans *trans,
-				  struct iwl_dma_ptr *ptr)
+void iwl_pcie_free_dma_ptr(struct iwl_trans *trans, struct iwl_dma_ptr *ptr)
 {
 	if (unlikely(!ptr->addr))
 		return;
@@ -164,9 +162,6 @@ static void iwl_pcie_txq_stuck_timer(unsigned long data)
 	}
 	spin_unlock(&txq->lock);
 
-	IWL_ERR(trans, "Queue %d stuck for %u ms.\n", txq->id,
-		jiffies_to_msecs(txq->wd_timeout));
-
 	iwl_trans_pcie_log_scd_error(trans, txq);
 
 	iwl_force_nmi(trans);
@@ -188,6 +183,7 @@ static void iwl_pcie_txq_update_byte_cnt_tbl(struct iwl_trans *trans,
 	__le16 bc_ent;
 	struct iwl_tx_cmd *tx_cmd =
 		(void *)txq->entries[txq->write_ptr].cmd->payload;
+	u8 sta_id = tx_cmd->sta_id;
 
 	scd_bc_tbl = trans_pcie->scd_bc_tbls.addr;
 
@@ -210,26 +206,7 @@ static void iwl_pcie_txq_update_byte_cnt_tbl(struct iwl_trans *trans,
 	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))
 		return;
 
-	if (trans->cfg->use_tfh) {
-		u8 filled_tfd_size = offsetof(struct iwl_tfh_tfd, tbs) +
-				     num_tbs * sizeof(struct iwl_tfh_tb);
-		/*
-		 * filled_tfd_size contains the number of filled bytes in the
-		 * TFD.
-		 * Dividing it by 64 will give the number of chunks to fetch
-		 * to SRAM- 0 for one chunk, 1 for 2 and so on.
-		 * If, for example, TFD contains only 3 TBs then 32 bytes
-		 * of the TFD are used, and only one chunk of 64 bytes should
-		 * be fetched
-		 */
-		u8 num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
-
-		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
-	} else {
-		u8 sta_id = tx_cmd->sta_id;
-
-		bc_ent = cpu_to_le16(len | (sta_id << 12));
-	}
+	bc_ent = cpu_to_le16(len | (sta_id << 12));
 
 	scd_bc_tbl[txq_id].tfd_offset[write_ptr] = bc_ent;
 
@@ -319,23 +296,17 @@ void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans)
 	int i;
 
 	for (i = 0; i < trans->cfg->base_params->num_of_queues; i++) {
-		struct iwl_txq *txq = &trans_pcie->txq[i];
+		struct iwl_txq *txq = trans_pcie->txq[i];
 
 		spin_lock_bh(&txq->lock);
-		if (trans_pcie->txq[i].need_update) {
+		if (txq->need_update) {
 			iwl_pcie_txq_inc_wr_ptr(trans, txq);
-			trans_pcie->txq[i].need_update = false;
+			txq->need_update = false;
 		}
 		spin_unlock_bh(&txq->lock);
 	}
 }
 
-static inline void *iwl_pcie_get_tfd(struct iwl_trans_pcie *trans_pcie,
-				     struct iwl_txq *txq, int idx)
-{
-	return txq->tfds + trans_pcie->tfd_size * idx;
-}
-
 static inline dma_addr_t iwl_pcie_tfd_tb_get_addr(struct iwl_trans *trans,
 						  void *_tfd, u8 idx)
 {
@@ -368,28 +339,17 @@ static inline dma_addr_t iwl_pcie_tfd_tb_get_addr(struct iwl_trans *trans,
 static inline void iwl_pcie_tfd_set_tb(struct iwl_trans *trans, void *tfd,
 				       u8 idx, dma_addr_t addr, u16 len)
 {
-	if (trans->cfg->use_tfh) {
-		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
-		struct iwl_tfh_tb *tb = &tfd_fh->tbs[idx];
+	struct iwl_tfd *tfd_fh = (void *)tfd;
+	struct iwl_tfd_tb *tb = &tfd_fh->tbs[idx];
 
-		put_unaligned_le64(addr, &tb->addr);
-		tb->tb_len = cpu_to_le16(len);
+	u16 hi_n_len = len << 4;
 
-		tfd_fh->num_tbs = cpu_to_le16(idx + 1);
-	} else {
-		struct iwl_tfd *tfd_fh = (void *)tfd;
-		struct iwl_tfd_tb *tb = &tfd_fh->tbs[idx];
-
-		u16 hi_n_len = len << 4;
-
-		put_unaligned_le32(addr, &tb->lo);
-		if (sizeof(dma_addr_t) > sizeof(u32))
-			hi_n_len |= ((addr >> 16) >> 16) & 0xF;
+	put_unaligned_le32(addr, &tb->lo);
+	hi_n_len |= iwl_get_dma_hi_addr(addr);
 
-		tb->hi_n_len = cpu_to_le16(hi_n_len);
+	tb->hi_n_len = cpu_to_le16(hi_n_len);
 
-		tfd_fh->num_tbs = idx + 1;
-	}
+	tfd_fh->num_tbs = idx + 1;
 }
 
 static inline u8 iwl_pcie_tfd_get_num_tbs(struct iwl_trans *trans, void *_tfd)
@@ -460,7 +420,7 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
  * Does NOT advance any TFD circular buffer read/write indexes
  * Does NOT free the TFD itself (which is within circular buffer)
  */
-static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
+void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 {
 	/* rd_ptr is bounded by TFD_QUEUE_SIZE_MAX and
 	 * idx is bounded by n_window
@@ -522,9 +482,8 @@ static int iwl_pcie_txq_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 	return num_tbs;
 }
 
-static int iwl_pcie_txq_alloc(struct iwl_trans *trans,
-			       struct iwl_txq *txq, int slots_num,
-			       u32 txq_id)
+int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
+		       int slots_num, bool cmd_queue)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	size_t tfd_sz = trans_pcie->tfd_size * TFD_QUEUE_SIZE_MAX;
@@ -547,7 +506,7 @@ static int iwl_pcie_txq_alloc(struct iwl_trans *trans,
 	if (!txq->entries)
 		goto error;
 
-	if (txq_id == trans_pcie->cmd_queue)
+	if (cmd_queue)
 		for (i = 0; i < slots_num; i++) {
 			txq->entries[i].cmd =
 				kmalloc(sizeof(struct iwl_device_cmd),
@@ -573,13 +532,11 @@ static int iwl_pcie_txq_alloc(struct iwl_trans *trans,
 	if (!txq->first_tb_bufs)
 		goto err_free_tfds;
 
-	txq->id = txq_id;
-
 	return 0;
 err_free_tfds:
 	dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->dma_addr);
 error:
-	if (txq->entries && txq_id == trans_pcie->cmd_queue)
+	if (txq->entries && cmd_queue)
 		for (i = 0; i < slots_num; i++)
 			kfree(txq->entries[i].cmd);
 	kfree(txq->entries);
@@ -589,10 +546,9 @@ error:
 
 }
 
-static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
-			      int slots_num, u32 txq_id)
+int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
+		      int slots_num, bool cmd_queue)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int ret;
 
 	txq->need_update = false;
@@ -602,13 +558,13 @@ static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
 	BUILD_BUG_ON(TFD_QUEUE_SIZE_MAX & (TFD_QUEUE_SIZE_MAX - 1));
 
 	/* Initialize queue's high/low-water marks, and head/tail indexes */
-	ret = iwl_queue_init(txq, slots_num, txq_id);
+	ret = iwl_queue_init(txq, slots_num);
 	if (ret)
 		return ret;
 
 	spin_lock_init(&txq->lock);
 
-	if (txq_id == trans_pcie->cmd_queue) {
+	if (cmd_queue) {
 		static struct lock_class_key iwl_pcie_cmd_queue_lock_class;
 
 		lockdep_set_class(&txq->lock, &iwl_pcie_cmd_queue_lock_class);
@@ -616,18 +572,6 @@ static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
 
 	__skb_queue_head_init(&txq->overflow_q);
 
-	/*
-	 * Tell nic where to find circular buffer of Tx Frame Descriptors for
-	 * given Tx queue, and enable the DMA channel used for that queue.
-	 * Circular buffer (TFD queue in DRAM) physical base address */
-	if (trans->cfg->use_tfh)
-		iwl_write_direct64(trans,
-				   FH_MEM_CBBC_QUEUE(trans, txq_id),
-				   txq->dma_addr);
-	else
-		iwl_write_direct32(trans, FH_MEM_CBBC_QUEUE(trans, txq_id),
-				   txq->dma_addr >> 8);
-
 	return 0;
 }
 
@@ -672,7 +616,7 @@ static void iwl_pcie_clear_cmd_in_flight(struct iwl_trans *trans)
 static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 
 	spin_lock_bh(&txq->lock);
 	while (txq->write_ptr != txq->read_ptr) {
@@ -704,7 +648,6 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 			spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
 		}
 	}
-	txq->active = false;
 
 	while (!skb_queue_empty(&txq->overflow_q)) {
 		struct sk_buff *skb = __skb_dequeue(&txq->overflow_q);
@@ -729,7 +672,7 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 	struct device *dev = trans->dev;
 	int i;
 
@@ -780,9 +723,6 @@ void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
 	memset(trans_pcie->queue_stopped, 0, sizeof(trans_pcie->queue_stopped));
 	memset(trans_pcie->queue_used, 0, sizeof(trans_pcie->queue_used));
 
-	if (trans->cfg->use_tfh)
-		return;
-
 	trans_pcie->scd_base_addr =
 		iwl_read_prph(trans, SCD_SRAM_BASE_ADDR);
 
@@ -832,9 +772,16 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int txq_id;
 
+	/*
+	 * we should never get here in gen2 trans mode return early to avoid
+	 * having invalid accesses
+	 */
+	if (WARN_ON_ONCE(trans->cfg->gen2))
+		return;
+
 	for (txq_id = 0; txq_id < trans->cfg->base_params->num_of_queues;
 	     txq_id++) {
-		struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+		struct iwl_txq *txq = trans_pcie->txq[txq_id];
 		if (trans->cfg->use_tfh)
 			iwl_write_direct64(trans,
 					   FH_MEM_CBBC_QUEUE(trans, txq_id),
@@ -914,7 +861,7 @@ int iwl_pcie_tx_stop(struct iwl_trans *trans)
 	memset(trans_pcie->queue_used, 0, sizeof(trans_pcie->queue_used));
 
 	/* This can happen: start_hw, stop_device */
-	if (!trans_pcie->txq)
+	if (!trans_pcie->txq_memory)
 		return 0;
 
 	/* Unmap DMA from host system and free skb's */
@@ -935,15 +882,20 @@ void iwl_pcie_tx_free(struct iwl_trans *trans)
 	int txq_id;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
+	memset(trans_pcie->queue_used, 0, sizeof(trans_pcie->queue_used));
+
 	/* Tx queues */
-	if (trans_pcie->txq) {
+	if (trans_pcie->txq_memory) {
 		for (txq_id = 0;
-		     txq_id < trans->cfg->base_params->num_of_queues; txq_id++)
+		     txq_id < trans->cfg->base_params->num_of_queues;
+		     txq_id++) {
 			iwl_pcie_txq_free(trans, txq_id);
+			trans_pcie->txq[txq_id] = NULL;
+		}
 	}
 
-	kfree(trans_pcie->txq);
-	trans_pcie->txq = NULL;
+	kfree(trans_pcie->txq_memory);
+	trans_pcie->txq_memory = NULL;
 
 	iwl_pcie_free_dma_ptr(trans, &trans_pcie->kw);
 
@@ -965,7 +917,7 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 
 	/*It is not allowed to alloc twice, so warn when this happens.
 	 * We cannot rely on the previous allocation, so free and fail */
-	if (WARN_ON(trans_pcie->txq)) {
+	if (WARN_ON(trans_pcie->txq_memory)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -984,9 +936,9 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 		goto error;
 	}
 
-	trans_pcie->txq = kcalloc(trans->cfg->base_params->num_of_queues,
-				  sizeof(struct iwl_txq), GFP_KERNEL);
-	if (!trans_pcie->txq) {
+	trans_pcie->txq_memory = kcalloc(trans->cfg->base_params->num_of_queues,
+					 sizeof(struct iwl_txq), GFP_KERNEL);
+	if (!trans_pcie->txq_memory) {
 		IWL_ERR(trans, "Not enough memory for txq\n");
 		ret = -ENOMEM;
 		goto error;
@@ -995,14 +947,17 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	/* Alloc and init all Tx queues, including the command queue (#4/#9) */
 	for (txq_id = 0; txq_id < trans->cfg->base_params->num_of_queues;
 	     txq_id++) {
-		slots_num = (txq_id == trans_pcie->cmd_queue) ?
-					TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS;
-		ret = iwl_pcie_txq_alloc(trans, &trans_pcie->txq[txq_id],
-					  slots_num, txq_id);
+		bool cmd_queue = (txq_id == trans_pcie->cmd_queue);
+
+		slots_num = cmd_queue ? TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS;
+		trans_pcie->txq[txq_id] = &trans_pcie->txq_memory[txq_id];
+		ret = iwl_pcie_txq_alloc(trans, trans_pcie->txq[txq_id],
+					 slots_num, cmd_queue);
 		if (ret) {
 			IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
 			goto error;
 		}
+		trans_pcie->txq[txq_id]->id = txq_id;
 	}
 
 	return 0;
@@ -1012,6 +967,7 @@ error:
 
 	return ret;
 }
+
 int iwl_pcie_tx_init(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -1019,7 +975,7 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 	int txq_id, slots_num;
 	bool alloc = false;
 
-	if (!trans_pcie->txq) {
+	if (!trans_pcie->txq_memory) {
 		ret = iwl_pcie_tx_alloc(trans);
 		if (ret)
 			goto error;
@@ -1040,22 +996,24 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 	/* Alloc and init all Tx queues, including the command queue (#4/#9) */
 	for (txq_id = 0; txq_id < trans->cfg->base_params->num_of_queues;
 	     txq_id++) {
-		slots_num = (txq_id == trans_pcie->cmd_queue) ?
-					TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS;
-		ret = iwl_pcie_txq_init(trans, &trans_pcie->txq[txq_id],
-					 slots_num, txq_id);
+		bool cmd_queue = (txq_id == trans_pcie->cmd_queue);
+
+		slots_num = cmd_queue ? TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS;
+		ret = iwl_pcie_txq_init(trans, trans_pcie->txq[txq_id],
+					slots_num, cmd_queue);
 		if (ret) {
 			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
 			goto error;
 		}
-	}
 
-	if (trans->cfg->use_tfh) {
-		iwl_write_direct32(trans, TFH_TRANSFER_MODE,
-				   TFH_TRANSFER_MAX_PENDING_REQ |
-				   TFH_CHUNK_SIZE_128 |
-				   TFH_CHUNK_SPLIT_MODE);
-		return 0;
+		/*
+		 * Tell nic where to find circular buffer of TFDs for a
+		 * given Tx queue, and enable the DMA channel used for that
+		 * queue.
+		 * Circular buffer (TFD queue in DRAM) physical base address
+		 */
+		iwl_write_direct32(trans, FH_MEM_CBBC_QUEUE(trans, txq_id),
+				   trans_pcie->txq[txq_id]->dma_addr >> 8);
 	}
 
 	iwl_set_bits_prph(trans, SCD_GP_CTRL, SCD_GP_CTRL_AUTO_ACTIVE_MODE);
@@ -1100,7 +1058,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			    struct sk_buff_head *skbs)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 	int tfd_num = ssn & (TFD_QUEUE_SIZE_MAX - 1);
 	int last_to_free;
 
@@ -1110,7 +1068,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	spin_lock_bh(&txq->lock);
 
-	if (!txq->active) {
+	if (!test_bit(txq_id, trans_pcie->queue_used)) {
 		IWL_DEBUG_TX_QUEUES(trans, "Q %d inactive - ignoring idx %d\n",
 				    txq_id, ssn);
 		goto out;
@@ -1257,7 +1215,7 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans,
 static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 	unsigned long flags;
 	int nfreed = 0;
 
@@ -1324,15 +1282,12 @@ void iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, u16 ssn,
 			       unsigned int wdg_timeout)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 	int fifo = -1;
 
 	if (test_and_set_bit(txq_id, trans_pcie->queue_used))
 		WARN_ONCE(1, "queue %d already used - expect issues", txq_id);
 
-	if (cfg && trans->cfg->use_tfh)
-		WARN_ONCE(1, "Expected no calls to SCD configuration");
-
 	txq->wd_timeout = msecs_to_jiffies(wdg_timeout);
 
 	if (cfg) {
@@ -1414,27 +1369,17 @@ void iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, u16 ssn,
 				    "Activate queue %d WrPtr: %d\n",
 				    txq_id, ssn & 0xff);
 	}
-
-	txq->active = true;
 }
 
 void iwl_trans_pcie_txq_set_shared_mode(struct iwl_trans *trans, u32 txq_id,
 					bool shared_mode)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
+	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 
 	txq->ampdu = !shared_mode;
 }
 
-dma_addr_t iwl_trans_pcie_get_txq_byte_table(struct iwl_trans *trans, int txq)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-
-	return trans_pcie->scd_bc_tbls.dma +
-	       txq * sizeof(struct iwlagn_scd_bc_tbl);
-}
-
 void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int txq_id,
 				bool configure_scd)
 {
@@ -1443,8 +1388,8 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int txq_id,
 			SCD_TX_STTS_QUEUE_OFFSET(txq_id);
 	static const u32 zero_val[4] = {};
 
-	trans_pcie->txq[txq_id].frozen_expiry_remainder = 0;
-	trans_pcie->txq[txq_id].frozen = false;
+	trans_pcie->txq[txq_id]->frozen_expiry_remainder = 0;
+	trans_pcie->txq[txq_id]->frozen = false;
 
 	/*
 	 * Upon HW Rfkill - we stop the device, and then stop the queues
@@ -1458,9 +1403,6 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int txq_id,
 		return;
 	}
 
-	if (configure_scd && trans->cfg->use_tfh)
-		WARN_ONCE(1, "Expected no calls to SCD configuration");
-
 	if (configure_scd) {
 		iwl_scd_txq_set_inactive(trans, txq_id);
 
@@ -1469,7 +1411,7 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int txq_id,
 	}
 
 	iwl_pcie_txq_unmap(trans, txq_id);
-	trans_pcie->txq[txq_id].ampdu = false;
+	trans_pcie->txq[txq_id]->ampdu = false;
 
 	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", txq_id);
 }
@@ -1489,7 +1431,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 				 struct iwl_host_cmd *cmd)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[trans_pcie->cmd_queue];
+	struct iwl_txq *txq = trans_pcie->txq[trans_pcie->cmd_queue];
 	struct iwl_device_cmd *out_cmd;
 	struct iwl_cmd_meta *out_meta;
 	unsigned long flags;
@@ -1774,16 +1716,15 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 	struct iwl_device_cmd *cmd;
 	struct iwl_cmd_meta *meta;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = &trans_pcie->txq[trans_pcie->cmd_queue];
+	struct iwl_txq *txq = trans_pcie->txq[trans_pcie->cmd_queue];
 
 	/* If a Tx command is being handled and it isn't in the actual
 	 * command queue then there a command routing bug has been introduced
 	 * in the queue management code. */
 	if (WARN(txq_id != trans_pcie->cmd_queue,
 		 "wrong command queue %d (should be %d), sequence 0x%X readp=%d writep=%d\n",
-		 txq_id, trans_pcie->cmd_queue, sequence,
-		 trans_pcie->txq[trans_pcie->cmd_queue].read_ptr,
-		 trans_pcie->txq[trans_pcie->cmd_queue].write_ptr)) {
+		 txq_id, trans_pcie->cmd_queue, sequence, txq->read_ptr,
+		 txq->write_ptr)) {
 		iwl_print_hex_error(trans, pkt, 32);
 		return;
 	}
@@ -1867,6 +1808,7 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans,
 				   struct iwl_host_cmd *cmd)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_txq *txq = trans_pcie->txq[trans_pcie->cmd_queue];
 	int cmd_idx;
 	int ret;
 
@@ -1907,8 +1849,6 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans,
 					   &trans->status),
 				 HOST_COMPLETE_TIMEOUT);
 	if (!ret) {
-		struct iwl_txq *txq = &trans_pcie->txq[trans_pcie->cmd_queue];
-
 		IWL_ERR(trans, "Error sending %s: time out after %dms.\n",
 			iwl_get_cmd_string(trans, cmd->id),
 			jiffies_to_msecs(HOST_COMPLETE_TIMEOUT));
@@ -1959,8 +1899,7 @@ cancel:
 		 * in later, it will possibly set an invalid
 		 * address (cmd->meta.source).
 		 */
-		trans_pcie->txq[trans_pcie->cmd_queue].
-			entries[cmd_idx].meta.flags &= ~CMD_WANT_SKB;
+		txq->entries[cmd_idx].meta.flags &= ~CMD_WANT_SKB;
 	}
 
 	if (cmd->resp_pkt) {
@@ -2314,7 +2253,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	u16 wifi_seq;
 	bool amsdu;
 
-	txq = &trans_pcie->txq[txq_id];
+	txq = trans_pcie->txq[txq_id];
 
 	if (WARN_ONCE(!test_bit(txq_id, trans_pcie->queue_used),
 		      "TX on unused queue %d\n", txq_id))
diff --git a/drivers/net/wireless/intersil/orinoco/cfg.c b/drivers/net/wireless/intersil/orinoco/cfg.c
index 7aa47069af0a..b2d5ec8634b5 100644
--- a/drivers/net/wireless/intersil/orinoco/cfg.c
+++ b/drivers/net/wireless/intersil/orinoco/cfg.c
@@ -97,7 +97,7 @@ int orinoco_wiphy_register(struct wiphy *wiphy)
 }
 
 static int orinoco_change_vif(struct wiphy *wiphy, struct net_device *dev,
-			      enum nl80211_iftype type, u32 *flags,
+			      enum nl80211_iftype type,
 			      struct vif_params *params)
 {
 	struct orinoco_private *priv = wiphy_priv(wiphy);
diff --git a/drivers/net/wireless/intersil/orinoco/main.c b/drivers/net/wireless/intersil/orinoco/main.c
index 28cf97489001..d9128bb25e85 100644
--- a/drivers/net/wireless/intersil/orinoco/main.c
+++ b/drivers/net/wireless/intersil/orinoco/main.c
@@ -2283,7 +2283,7 @@ int orinoco_if_add(struct orinoco_private *priv,
 	priv->ndev = dev;
 
 	/* Report what we've done */
-	dev_dbg(priv->dev, "Registerred interface %s.\n", dev->name);
+	dev_dbg(priv->dev, "Registered interface %s.\n", dev->name);
 
 	return 0;
 
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index 98e1380b9917..132f5fbda58b 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -769,18 +769,31 @@ static int ezusb_submit_in_urb(struct ezusb_priv *upriv)
 
 static inline int ezusb_8051_cpucs(struct ezusb_priv *upriv, int reset)
 {
-	u8 res_val = reset;	/* avoid argument promotion */
+	int ret;
+	u8 *res_val = NULL;
 
 	if (!upriv->udev) {
 		err("%s: !upriv->udev", __func__);
 		return -EFAULT;
 	}
-	return usb_control_msg(upriv->udev,
+
+	res_val = kmalloc(sizeof(*res_val), GFP_KERNEL);
+
+	if (!res_val)
+		return -ENOMEM;
+
+	*res_val = reset;	/* avoid argument promotion */
+
+	ret =  usb_control_msg(upriv->udev,
 			       usb_sndctrlpipe(upriv->udev, 0),
 			       EZUSB_REQUEST_FW_TRANS,
 			       USB_TYPE_VENDOR | USB_RECIP_DEVICE |
-			       USB_DIR_OUT, EZUSB_CPUCS_REG, 0, &res_val,
-			       sizeof(res_val), DEF_TIMEOUT);
+			       USB_DIR_OUT, EZUSB_CPUCS_REG, 0, res_val,
+			       sizeof(*res_val), DEF_TIMEOUT);
+
+	kfree(res_val);
+
+	return ret;
 }
 
 static int ezusb_firmware_download(struct ezusb_priv *upriv,
diff --git a/drivers/net/wireless/intersil/p54/txrx.c b/drivers/net/wireless/intersil/p54/txrx.c
index 1af7da0b386e..5e1c91a80c58 100644
--- a/drivers/net/wireless/intersil/p54/txrx.c
+++ b/drivers/net/wireless/intersil/p54/txrx.c
@@ -352,7 +352,7 @@ static int p54_rx_data(struct p54_common *priv, struct sk_buff *skb)
 
 	rx_status->signal = p54_rssi_to_dbm(priv, hdr->rssi);
 	if (hdr->rate & 0x10)
-		rx_status->flag |= RX_FLAG_SHORTPRE;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 	if (priv->hw->conf.chandef.chan->band == NL80211_BAND_5GHZ)
 		rx_status->rate_idx = (rate < 4) ? 0 : rate - 4;
 	else
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 50c219fb1a52..87444af20fc5 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -350,6 +350,7 @@ static const struct ieee80211_channel hwsim_channels_5ghz[] = {
 	CHAN5G(5785), /* Channel 157 */
 	CHAN5G(5805), /* Channel 161 */
 	CHAN5G(5825), /* Channel 165 */
+	CHAN5G(5845), /* Channel 169 */
 };
 
 static const struct ieee80211_rate hwsim_rates[] = {
@@ -389,7 +390,7 @@ static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy,
 	u32 val;
 
 	err = nla_parse(tb, QCA_WLAN_VENDOR_ATTR_MAX, data, data_len,
-			hwsim_vendor_test_policy);
+			hwsim_vendor_test_policy, NULL);
 	if (err)
 		return err;
 	if (!tb[QCA_WLAN_VENDOR_ATTR_TEST])
@@ -525,6 +526,11 @@ struct mac80211_hwsim_data {
 	struct ieee80211_vif *hw_scan_vif;
 	int scan_chan_idx;
 	u8 scan_addr[ETH_ALEN];
+	struct {
+		struct ieee80211_channel *channel;
+		unsigned long next_start, start, end;
+	} survey_data[ARRAY_SIZE(hwsim_channels_2ghz) +
+		      ARRAY_SIZE(hwsim_channels_5ghz)];
 
 	struct ieee80211_channel *channel;
 	u64 beacon_int	/* beacon interval in us */;
@@ -552,8 +558,6 @@ struct mac80211_hwsim_data {
 	/* wmediumd portid responsible for netgroup of this radio */
 	u32 wmediumd;
 
-	int power_level;
-
 	/* difference between this hw's clock and the real clock, in usecs */
 	s64 tsf_offset;
 	s64 bcn_delta;
@@ -1188,20 +1192,22 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 	if (info->control.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) {
 		rx_status.rate_idx =
 			ieee80211_rate_get_vht_mcs(&info->control.rates[0]);
-		rx_status.vht_nss =
+		rx_status.nss =
 			ieee80211_rate_get_vht_nss(&info->control.rates[0]);
-		rx_status.flag |= RX_FLAG_VHT;
+		rx_status.encoding = RX_ENC_VHT;
 	} else {
 		rx_status.rate_idx = info->control.rates[0].idx;
 		if (info->control.rates[0].flags & IEEE80211_TX_RC_MCS)
-			rx_status.flag |= RX_FLAG_HT;
+			rx_status.encoding = RX_ENC_HT;
 	}
 	if (info->control.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-		rx_status.flag |= RX_FLAG_40MHZ;
+		rx_status.enc_flags |= RX_ENC_FLAG_40MHZ;
 	if (info->control.rates[0].flags & IEEE80211_TX_RC_SHORT_GI)
-		rx_status.flag |= RX_FLAG_SHORT_GI;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	/* TODO: simulate real signal strength (and optional packet loss) */
-	rx_status.signal = data->power_level - 50;
+	rx_status.signal = -50;
+	if (info->control.vif)
+		rx_status.signal += info->control.vif->bss_conf.txpower;
 
 	if (data->ps != PS_DISABLED)
 		hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PM);
@@ -1576,6 +1582,7 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
 		[IEEE80211_SMPS_STATIC] = "static",
 		[IEEE80211_SMPS_DYNAMIC] = "dynamic",
 	};
+	int idx;
 
 	if (conf->chandef.chan)
 		wiphy_debug(hw->wiphy,
@@ -1598,11 +1605,34 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
 
 	data->idle = !!(conf->flags & IEEE80211_CONF_IDLE);
 
-	data->channel = conf->chandef.chan;
+	WARN_ON(conf->chandef.chan && data->use_chanctx);
+
+	mutex_lock(&data->mutex);
+	if (data->scanning && conf->chandef.chan) {
+		for (idx = 0; idx < ARRAY_SIZE(data->survey_data); idx++) {
+			if (data->survey_data[idx].channel == data->channel) {
+				data->survey_data[idx].start =
+					data->survey_data[idx].next_start;
+				data->survey_data[idx].end = jiffies;
+				break;
+			}
+		}
 
-	WARN_ON(data->channel && data->use_chanctx);
+		data->channel = conf->chandef.chan;
+
+		for (idx = 0; idx < ARRAY_SIZE(data->survey_data); idx++) {
+			if (data->survey_data[idx].channel &&
+			    data->survey_data[idx].channel != data->channel)
+				continue;
+			data->survey_data[idx].channel = data->channel;
+			data->survey_data[idx].next_start = jiffies;
+			break;
+		}
+	} else {
+		data->channel = conf->chandef.chan;
+	}
+	mutex_unlock(&data->mutex);
 
-	data->power_level = conf->power_level;
 	if (!data->started || !data->beacon_int)
 		tasklet_hrtimer_cancel(&data->beacon_timer);
 	else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
@@ -1787,28 +1817,37 @@ static int mac80211_hwsim_conf_tx(
 	return 0;
 }
 
-static int mac80211_hwsim_get_survey(
-	struct ieee80211_hw *hw, int idx,
-	struct survey_info *survey)
+static int mac80211_hwsim_get_survey(struct ieee80211_hw *hw, int idx,
+				     struct survey_info *survey)
 {
-	struct ieee80211_conf *conf = &hw->conf;
-
-	wiphy_debug(hw->wiphy, "%s (idx=%d)\n", __func__, idx);
+	struct mac80211_hwsim_data *hwsim = hw->priv;
 
-	if (idx != 0)
+	if (idx < 0 || idx >= ARRAY_SIZE(hwsim->survey_data))
 		return -ENOENT;
 
-	/* Current channel */
-	survey->channel = conf->chandef.chan;
+	mutex_lock(&hwsim->mutex);
+	survey->channel = hwsim->survey_data[idx].channel;
+	if (!survey->channel) {
+		mutex_unlock(&hwsim->mutex);
+		return -ENOENT;
+	}
 
 	/*
-	 * Magically conjured noise level --- this is only ok for simulated hardware.
+	 * Magically conjured dummy values --- this is only ok for simulated hardware.
 	 *
-	 * A real driver which cannot determine the real channel noise MUST NOT
-	 * report any noise, especially not a magically conjured one :-)
+	 * A real driver which cannot determine real values noise MUST NOT
+	 * report any, especially not a magically conjured ones :-)
 	 */
-	survey->filled = SURVEY_INFO_NOISE_DBM;
+	survey->filled = SURVEY_INFO_NOISE_DBM |
+			 SURVEY_INFO_TIME |
+			 SURVEY_INFO_TIME_BUSY;
 	survey->noise = -92;
+	survey->time =
+		jiffies_to_msecs(hwsim->survey_data[idx].end -
+				 hwsim->survey_data[idx].start);
+	/* report 12.5% of channel time is used */
+	survey->time_busy = survey->time/8;
+	mutex_unlock(&hwsim->mutex);
 
 	return 0;
 }
@@ -1852,7 +1891,7 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw,
 	int err, ps;
 
 	err = nla_parse(tb, HWSIM_TM_ATTR_MAX, data, len,
-			hwsim_testmode_policy);
+			hwsim_testmode_policy, NULL);
 	if (err)
 		return err;
 
@@ -1986,6 +2025,10 @@ static void hw_scan_work(struct work_struct *work)
 	}
 	ieee80211_queue_delayed_work(hwsim->hw, &hwsim->hw_scan,
 				     msecs_to_jiffies(dwell));
+	hwsim->survey_data[hwsim->scan_chan_idx].channel = hwsim->tmp_chan;
+	hwsim->survey_data[hwsim->scan_chan_idx].start = jiffies;
+	hwsim->survey_data[hwsim->scan_chan_idx].end =
+		jiffies + msecs_to_jiffies(dwell);
 	hwsim->scan_chan_idx++;
 	mutex_unlock(&hwsim->mutex);
 }
@@ -2011,6 +2054,7 @@ static int mac80211_hwsim_hw_scan(struct ieee80211_hw *hw,
 				     hw_req->req.mac_addr_mask);
 	else
 		memcpy(hwsim->scan_addr, vif->addr, ETH_ALEN);
+	memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data));
 	mutex_unlock(&hwsim->mutex);
 
 	wiphy_debug(hw->wiphy, "hwsim hw_scan request\n");
@@ -2057,6 +2101,7 @@ static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw,
 
 	memcpy(hwsim->scan_addr, mac_addr, ETH_ALEN);
 	hwsim->scanning = true;
+	memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data));
 
 out:
 	mutex_unlock(&hwsim->mutex);
@@ -2207,7 +2252,6 @@ static const char mac80211_hwsim_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"d_tx_failed",
 	"d_ps_mode",
 	"d_group",
-	"d_tx_power",
 };
 
 #define MAC80211_HWSIM_SSTATS_LEN ARRAY_SIZE(mac80211_hwsim_gstrings_stats)
@@ -2244,7 +2288,6 @@ static void mac80211_hwsim_get_et_stats(struct ieee80211_hw *hw,
 	data[i++] = ar->tx_failed;
 	data[i++] = ar->ps;
 	data[i++] = ar->group;
-	data[i++] = ar->power_level;
 
 	WARN_ON(i != MAC80211_HWSIM_SSTATS_LEN);
 }
@@ -2438,6 +2481,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		goto failed;
 	}
 
+	/* ieee80211_alloc_hw_nm may have used a default name */
+	param->hwname = wiphy_name(hw->wiphy);
+
 	if (info)
 		net = genl_info_net(info);
 	else
@@ -2645,6 +2691,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	if (param->no_vif)
 		ieee80211_hw_set(hw, NO_AUTO_VIF);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	err = ieee80211_register_hw(hw);
 	if (err < 0) {
 		printk(KERN_DEBUG "mac80211_hwsim: ieee80211_register_hw failed (%d)\n",
diff --git a/drivers/net/wireless/mac80211_hwsim.h b/drivers/net/wireless/mac80211_hwsim.h
index 39f22467ca2a..3f5eda591dba 100644
--- a/drivers/net/wireless/mac80211_hwsim.h
+++ b/drivers/net/wireless/mac80211_hwsim.h
@@ -57,12 +57,12 @@ enum hwsim_tx_control_flags {
  * @HWSIM_CMD_REGISTER: request to register and received all broadcasted
  *	frames by any mac80211_hwsim radio device.
  * @HWSIM_CMD_FRAME: send/receive a broadcasted frame from/to kernel/user
- * space, uses:
+ *	space, uses:
  *	%HWSIM_ATTR_ADDR_TRANSMITTER, %HWSIM_ATTR_ADDR_RECEIVER,
  *	%HWSIM_ATTR_FRAME, %HWSIM_ATTR_FLAGS, %HWSIM_ATTR_RX_RATE,
  *	%HWSIM_ATTR_SIGNAL, %HWSIM_ATTR_COOKIE, %HWSIM_ATTR_FREQ (optional)
  * @HWSIM_CMD_TX_INFO_FRAME: Transmission info report from user space to
- * kernel, uses:
+ *	kernel, uses:
  *	%HWSIM_ATTR_ADDR_TRANSMITTER, %HWSIM_ATTR_FLAGS,
  *	%HWSIM_ATTR_TX_INFO, %HWSIM_ATTR_SIGNAL, %HWSIM_ATTR_COOKIE
  * @HWSIM_CMD_NEW_RADIO: create a new radio with the given parameters,
diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c
index 3f97acb57e66..a0463fef79b0 100644
--- a/drivers/net/wireless/marvell/libertas/cfg.c
+++ b/drivers/net/wireless/marvell/libertas/cfg.c
@@ -1657,7 +1657,7 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
  */
 
 static int lbs_change_intf(struct wiphy *wiphy, struct net_device *dev,
-	enum nl80211_iftype type, u32 *flags,
+	enum nl80211_iftype type,
 	       struct vif_params *params)
 {
 	struct lbs_private *priv = wiphy_priv(wiphy);
diff --git a/drivers/net/wireless/marvell/libertas/if_spi.c b/drivers/net/wireless/marvell/libertas/if_spi.c
index c3a53cd6988e..7b4955cc38db 100644
--- a/drivers/net/wireless/marvell/libertas/if_spi.c
+++ b/drivers/net/wireless/marvell/libertas/if_spi.c
@@ -1181,6 +1181,10 @@ static int if_spi_probe(struct spi_device *spi)
 
 	/* Initialize interrupt handling stuff. */
 	card->workqueue = alloc_workqueue("libertas_spi", WQ_MEM_RECLAIM, 0);
+	if (!card->workqueue) {
+		err = -ENOMEM;
+		goto remove_card;
+	}
 	INIT_WORK(&card->packet_work, if_spi_host_to_card_worker);
 	INIT_WORK(&card->resume_work, if_spi_resume_worker);
 
@@ -1209,6 +1213,7 @@ release_irq:
 	free_irq(spi->irq, card);
 terminate_workqueue:
 	destroy_workqueue(card->workqueue);
+remove_card:
 	lbs_remove_card(priv); /* will call free_netdev */
 free_card:
 	free_if_spi_card(card);
diff --git a/drivers/net/wireless/marvell/libertas_tf/main.c b/drivers/net/wireless/marvell/libertas_tf/main.c
index 54e426c1e405..d80333117989 100644
--- a/drivers/net/wireless/marvell/libertas_tf/main.c
+++ b/drivers/net/wireless/marvell/libertas_tf/main.c
@@ -641,6 +641,8 @@ struct lbtf_private *lbtf_add_card(void *card, struct device *dmdev)
 		BIT(NL80211_IFTYPE_ADHOC);
 	skb_queue_head_init(&priv->bc_ps_buf);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	SET_IEEE80211_DEV(hw, dmdev);
 
 	INIT_WORK(&priv->cmd_work, lbtf_cmd_work);
diff --git a/drivers/net/wireless/marvell/mwifiex/11h.c b/drivers/net/wireless/marvell/mwifiex/11h.c
index 43dccd5b0291..366eb4991a7d 100644
--- a/drivers/net/wireless/marvell/mwifiex/11h.c
+++ b/drivers/net/wireless/marvell/mwifiex/11h.c
@@ -153,7 +153,8 @@ int mwifiex_cmd_issue_chan_report_request(struct mwifiex_private *priv,
 
 	cmd->command = cpu_to_le16(HostCmd_CMD_CHAN_REPORT_REQUEST);
 	cmd->size = cpu_to_le16(S_DS_GEN);
-	le16_add_cpu(&cmd->size, sizeof(struct host_cmd_ds_chan_rpt_req));
+	le16_unaligned_add_cpu(&cmd->size,
+			       sizeof(struct host_cmd_ds_chan_rpt_req));
 
 	cr_req->chan_desc.start_freq = cpu_to_le16(MWIFIEX_A_BAND_START_FREQ);
 	cr_req->chan_desc.chan_num = radar_params->chandef->chan->hw_value;
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 1e3bd435a694..7ec06bf13413 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -594,6 +594,24 @@ int mwifiex_send_domain_info_cmd_fw(struct wiphy *wiphy)
 	return 0;
 }
 
+static void mwifiex_reg_apply_radar_flags(struct wiphy *wiphy)
+{
+	struct ieee80211_supported_band *sband;
+	struct ieee80211_channel *chan;
+	unsigned int i;
+
+	if (!wiphy->bands[NL80211_BAND_5GHZ])
+		return;
+	sband = wiphy->bands[NL80211_BAND_5GHZ];
+
+	for (i = 0; i < sband->n_channels; i++) {
+		chan = &sband->channels[i];
+		if ((!(chan->flags & IEEE80211_CHAN_DISABLED)) &&
+		    (chan->flags & IEEE80211_CHAN_RADAR))
+			chan->flags |= IEEE80211_CHAN_NO_IR;
+	}
+}
+
 /*
  * CFG802.11 regulatory domain callback function.
  *
@@ -613,6 +631,7 @@ static void mwifiex_reg_notifier(struct wiphy *wiphy,
 	mwifiex_dbg(adapter, INFO,
 		    "info: cfg80211 regulatory domain callback for %c%c\n",
 		    request->alpha2[0], request->alpha2[1]);
+	mwifiex_reg_apply_radar_flags(wiphy);
 
 	switch (request->initiator) {
 	case NL80211_REGDOM_SET_BY_DRIVER:
@@ -916,7 +935,7 @@ mwifiex_init_new_priv_params(struct mwifiex_private *priv,
 static int
 mwifiex_change_vif_to_p2p(struct net_device *dev,
 			  enum nl80211_iftype curr_iftype,
-			  enum nl80211_iftype type, u32 *flags,
+			  enum nl80211_iftype type,
 			  struct vif_params *params)
 {
 	struct mwifiex_private *priv;
@@ -988,7 +1007,7 @@ mwifiex_change_vif_to_p2p(struct net_device *dev,
 static int
 mwifiex_change_vif_to_sta_adhoc(struct net_device *dev,
 				enum nl80211_iftype curr_iftype,
-				enum nl80211_iftype type, u32 *flags,
+				enum nl80211_iftype type,
 				struct vif_params *params)
 {
 	struct mwifiex_private *priv;
@@ -1047,7 +1066,7 @@ mwifiex_change_vif_to_sta_adhoc(struct net_device *dev,
 static int
 mwifiex_change_vif_to_ap(struct net_device *dev,
 			 enum nl80211_iftype curr_iftype,
-			 enum nl80211_iftype type, u32 *flags,
+			 enum nl80211_iftype type,
 			 struct vif_params *params)
 {
 	struct mwifiex_private *priv;
@@ -1103,7 +1122,7 @@ mwifiex_change_vif_to_ap(struct net_device *dev,
 static int
 mwifiex_cfg80211_change_virtual_intf(struct wiphy *wiphy,
 				     struct net_device *dev,
-				     enum nl80211_iftype type, u32 *flags,
+				     enum nl80211_iftype type,
 				     struct vif_params *params)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
@@ -1124,10 +1143,10 @@ mwifiex_cfg80211_change_virtual_intf(struct wiphy *wiphy,
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_P2P_GO:
 			return mwifiex_change_vif_to_p2p(dev, curr_iftype,
-							 type, flags, params);
+							 type, params);
 		case NL80211_IFTYPE_AP:
 			return mwifiex_change_vif_to_ap(dev, curr_iftype, type,
-							flags, params);
+							params);
 		case NL80211_IFTYPE_UNSPECIFIED:
 			mwifiex_dbg(priv->adapter, INFO,
 				    "%s: kept type as IBSS\n", dev->name);
@@ -1154,10 +1173,10 @@ mwifiex_cfg80211_change_virtual_intf(struct wiphy *wiphy,
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_P2P_GO:
 			return mwifiex_change_vif_to_p2p(dev, curr_iftype,
-							 type, flags, params);
+							 type, params);
 		case NL80211_IFTYPE_AP:
 			return mwifiex_change_vif_to_ap(dev, curr_iftype, type,
-							flags, params);
+							params);
 		case NL80211_IFTYPE_UNSPECIFIED:
 			mwifiex_dbg(priv->adapter, INFO,
 				    "%s: kept type as STA\n", dev->name);
@@ -1175,13 +1194,12 @@ mwifiex_cfg80211_change_virtual_intf(struct wiphy *wiphy,
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_STATION:
 			return mwifiex_change_vif_to_sta_adhoc(dev, curr_iftype,
-							       type, flags,
-							       params);
+							       type, params);
 			break;
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_P2P_GO:
 			return mwifiex_change_vif_to_p2p(dev, curr_iftype,
-							 type, flags, params);
+							 type, params);
 		case NL80211_IFTYPE_UNSPECIFIED:
 			mwifiex_dbg(priv->adapter, INFO,
 				    "%s: kept type as AP\n", dev->name);
@@ -1214,14 +1232,13 @@ mwifiex_cfg80211_change_virtual_intf(struct wiphy *wiphy,
 			if (mwifiex_cfg80211_deinit_p2p(priv))
 				return -EFAULT;
 			return mwifiex_change_vif_to_sta_adhoc(dev, curr_iftype,
-							       type, flags,
-							       params);
+							       type, params);
 			break;
 		case NL80211_IFTYPE_AP:
 			if (mwifiex_cfg80211_deinit_p2p(priv))
 				return -EFAULT;
 			return mwifiex_change_vif_to_ap(dev, curr_iftype, type,
-							flags, params);
+							params);
 		case NL80211_IFTYPE_UNSPECIFIED:
 			mwifiex_dbg(priv->adapter, INFO,
 				    "%s: kept type as P2P\n", dev->name);
@@ -2036,7 +2053,7 @@ mwifiex_cfg80211_disconnect(struct wiphy *wiphy, struct net_device *dev,
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
 	if (!mwifiex_stop_bg_scan(priv))
-		cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy, 0);
 
 	if (mwifiex_deauthenticate(priv, NULL))
 		return -EFAULT;
@@ -2304,7 +2321,7 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev,
 		    (int)sme->ssid_len, (char *)sme->ssid, sme->bssid);
 
 	if (!mwifiex_stop_bg_scan(priv))
-		cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy, 0);
 
 	ret = mwifiex_cfg80211_assoc(priv, sme->ssid_len, sme->ssid, sme->bssid,
 				     priv->bss_mode, sme->channel, sme, 0);
@@ -2513,7 +2530,7 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy,
 		priv->scan_block = false;
 
 	if (!mwifiex_stop_bg_scan(priv))
-		cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy, 0);
 
 	user_scan_cfg = kzalloc(sizeof(*user_scan_cfg), GFP_KERNEL);
 	if (!user_scan_cfg)
@@ -2528,9 +2545,11 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy,
 			priv->random_mac[i] |= get_random_int() &
 					       ~(request->mac_addr_mask[i]);
 		}
+		ether_addr_copy(user_scan_cfg->random_mac, priv->random_mac);
+	} else {
+		eth_zero_addr(priv->random_mac);
 	}
 
-	ether_addr_copy(user_scan_cfg->random_mac, priv->random_mac);
 	user_scan_cfg->num_ssids = request->n_ssids;
 	user_scan_cfg->ssid_list = request->ssids;
 
@@ -2701,7 +2720,7 @@ mwifiex_cfg80211_sched_scan_start(struct wiphy *wiphy,
  * previous bgscan configuration in the firmware
  */
 static int mwifiex_cfg80211_sched_scan_stop(struct wiphy *wiphy,
-					    struct net_device *dev)
+					    struct net_device *dev, u64 reqid)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
@@ -2822,7 +2841,6 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 					      const char *name,
 					      unsigned char name_assign_type,
 					      enum nl80211_iftype type,
-					      u32 *flags,
 					      struct vif_params *params)
 {
 	struct mwifiex_adapter *adapter = mwifiex_cfg80211_get_adapter(wiphy);
@@ -3997,8 +4015,8 @@ static int mwifiex_tm_cmd(struct wiphy *wiphy, struct wireless_dev *wdev,
 	if (!priv)
 		return -EINVAL;
 
-	err = nla_parse(tb, MWIFIEX_TM_ATTR_MAX, data, len,
-			mwifiex_tm_policy);
+	err = nla_parse(tb, MWIFIEX_TM_ATTR_MAX, data, len, mwifiex_tm_policy,
+			NULL);
 	if (err)
 		return err;
 
@@ -4279,7 +4297,6 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 	wiphy->flags |= WIPHY_FLAG_HAVE_AP_SME |
 			WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD |
 			WIPHY_FLAG_AP_UAPSD |
-			WIPHY_FLAG_SUPPORTS_SCHED_SCAN |
 			WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL |
 			WIPHY_FLAG_HAS_CHANNEL_SWITCH |
 			WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -4298,6 +4315,7 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 				    NL80211_PROBE_RESP_OFFLOAD_SUPPORT_WPS2 |
 				    NL80211_PROBE_RESP_OFFLOAD_SUPPORT_P2P;
 
+	wiphy->max_sched_scan_reqs = 1;
 	wiphy->max_sched_scan_ssids = MWIFIEX_MAX_SSID_LIST_LENGTH;
 	wiphy->max_sched_scan_ie_len = MWIFIEX_MAX_VSIE_LEN;
 	wiphy->max_match_sets = MWIFIEX_MAX_SSID_LIST_LENGTH;
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 25a7475702f7..0c3b217247b1 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -242,7 +242,7 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv,
 	mwifiex_dbg(adapter, CMD,
 		    "cmd: DNLD_CMD: %#x, act %#x, len %d, seqno %#x\n",
 		    cmd_code,
-		    le16_to_cpu(*(__le16 *)((u8 *)host_cmd + S_DS_GEN)),
+		    get_unaligned_le16((u8 *)host_cmd + S_DS_GEN),
 		    cmd_size, le16_to_cpu(host_cmd->seq_num));
 	mwifiex_dbg_dump(adapter, CMD_D, "cmd buffer:", host_cmd, cmd_size);
 
@@ -286,7 +286,7 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv,
 			(adapter->dbg.last_cmd_index + 1) % DBG_CMD_NUM;
 	adapter->dbg.last_cmd_id[adapter->dbg.last_cmd_index] = cmd_code;
 	adapter->dbg.last_cmd_act[adapter->dbg.last_cmd_index] =
-			le16_to_cpu(*(__le16 *) ((u8 *) host_cmd + S_DS_GEN));
+			get_unaligned_le16((u8 *)host_cmd + S_DS_GEN);
 
 	/* Clear BSS_NO_BITS from HostCmd */
 	cmd_code &= HostCmd_CMD_ID_MASK;
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index cb6a1a81d44e..6cf9ab9133ea 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -31,17 +31,35 @@ struct rfc_1042_hdr {
 	u8 llc_ctrl;
 	u8 snap_oui[3];
 	__be16 snap_type;
-};
+} __packed;
 
 struct rx_packet_hdr {
 	struct ethhdr eth803_hdr;
 	struct rfc_1042_hdr rfc1042_hdr;
-};
+} __packed;
 
 struct tx_packet_hdr {
 	struct ethhdr eth803_hdr;
 	struct rfc_1042_hdr rfc1042_hdr;
-};
+} __packed;
+
+struct mwifiex_fw_header {
+	__le32 dnld_cmd;
+	__le32 base_addr;
+	__le32 data_length;
+	__le32 crc;
+} __packed;
+
+struct mwifiex_fw_data {
+	struct mwifiex_fw_header header;
+	__le32 seq_num;
+	u8 data[1];
+} __packed;
+
+#define MWIFIEX_FW_DNLD_CMD_1 0x1
+#define MWIFIEX_FW_DNLD_CMD_5 0x5
+#define MWIFIEX_FW_DNLD_CMD_6 0x6
+#define MWIFIEX_FW_DNLD_CMD_7 0x7
 
 #define B_SUPPORTED_RATES               5
 #define G_SUPPORTED_RATES               9
@@ -707,7 +725,7 @@ struct uap_txpd {
 	u8 reserved1[2];
 	u8 tx_token_id;
 	u8 reserved[2];
-};
+} __packed;
 
 struct uap_rxpd {
 	u8 bss_type;
@@ -723,7 +741,7 @@ struct uap_rxpd {
 	u8 ht_info;
 	u8 reserved[3];
 	u8 flags;
-};
+} __packed;
 
 struct mwifiex_fw_chan_stats {
 	u8 chan_num;
@@ -987,7 +1005,7 @@ struct mwifiex_ps_param {
 	__le16 adhoc_wake_period;
 	__le16 mode;
 	__le16 delay_to_ps;
-};
+} __packed;
 
 #define HS_DEF_WAKE_INTERVAL          100
 #define HS_DEF_INACTIVITY_TIMEOUT      50
@@ -996,7 +1014,7 @@ struct mwifiex_ps_param_in_hs {
 	struct mwifiex_ie_types_header header;
 	__le32 hs_wake_int;
 	__le32 hs_inact_timeout;
-};
+} __packed;
 
 #define BITMAP_AUTO_DS         0x01
 #define BITMAP_STA_PS          0x10
@@ -1062,7 +1080,7 @@ struct host_cmd_ds_802_11_rssi_info {
 	__le16 nbcn;
 	__le16 reserved[9];
 	long long reserved_1;
-};
+} __packed;
 
 struct host_cmd_ds_802_11_rssi_info_rsp {
 	__le16 action;
@@ -1077,12 +1095,12 @@ struct host_cmd_ds_802_11_rssi_info_rsp {
 	__le16 bcn_rssi_avg;
 	__le16 bcn_nf_avg;
 	long long tsf_bcn;
-};
+} __packed;
 
 struct host_cmd_ds_802_11_mac_address {
 	__le16 action;
 	u8 mac_addr[ETH_ALEN];
-};
+} __packed;
 
 struct host_cmd_ds_mac_control {
 	__le32 action;
@@ -1230,7 +1248,7 @@ struct host_cmd_ds_802_11_get_log {
 	__le32 wep_icv_err_cnt[4];
 	__le32 bcn_rcv_cnt;
 	__le32 bcn_miss_cnt;
-};
+} __packed;
 
 /* Enumeration for rate format */
 enum _mwifiex_rate_format {
@@ -1368,12 +1386,12 @@ struct host_cmd_ds_rf_ant_mimo {
 	__le16 tx_ant_mode;
 	__le16 action_rx;
 	__le16 rx_ant_mode;
-};
+} __packed;
 
 struct host_cmd_ds_rf_ant_siso {
 	__le16 action;
 	__le16 ant_mode;
-};
+} __packed;
 
 struct host_cmd_ds_tdls_oper {
 	__le16 tdls_action;
@@ -1383,13 +1401,13 @@ struct host_cmd_ds_tdls_oper {
 
 struct mwifiex_tdls_config {
 	__le16 enable;
-};
+} __packed;
 
 struct mwifiex_tdls_config_cs_params {
 	u8 unit_time;
 	u8 thr_otherlink;
 	u8 thr_directlink;
-};
+} __packed;
 
 struct mwifiex_tdls_init_cs_params {
 	u8 peer_mac[ETH_ALEN];
@@ -1404,7 +1422,7 @@ struct mwifiex_tdls_init_cs_params {
 
 struct mwifiex_tdls_stop_cs_params {
 	u8 peer_mac[ETH_ALEN];
-};
+} __packed;
 
 struct host_cmd_ds_tdls_config {
 	__le16 tdls_action;
@@ -1709,7 +1727,7 @@ struct mwifiex_ie_types_local_pwr_constraint {
 struct mwifiex_ie_types_wmm_param_set {
 	struct mwifiex_ie_types_header header;
 	u8 wmm_ie[1];
-};
+} __packed;
 
 struct mwifiex_ie_types_mgmt_frame {
 	struct mwifiex_ie_types_header header;
@@ -1834,7 +1852,7 @@ struct host_cmd_ds_mem_access {
 	__le16 reserved;
 	__le32 addr;
 	__le32 value;
-};
+} __packed;
 
 struct mwifiex_ie_types_qos_info {
 	struct mwifiex_ie_types_header header;
diff --git a/drivers/net/wireless/marvell/mwifiex/ie.c b/drivers/net/wireless/marvell/mwifiex/ie.c
index c488c3068abc..922e3d69fd84 100644
--- a/drivers/net/wireless/marvell/mwifiex/ie.c
+++ b/drivers/net/wireless/marvell/mwifiex/ie.c
@@ -131,9 +131,10 @@ mwifiex_update_autoindex_ies(struct mwifiex_private *priv,
 			       sizeof(struct mwifiex_ie));
 		}
 
-		le16_add_cpu(&ie_list->len,
-			     le16_to_cpu(priv->mgmt_ie[index].ie_length) +
-			     MWIFIEX_IE_HDR_SIZE);
+		le16_unaligned_add_cpu(&ie_list->len,
+				       le16_to_cpu(
+					    priv->mgmt_ie[index].ie_length) +
+				       MWIFIEX_IE_HDR_SIZE);
 		input_len -= tlv_len + MWIFIEX_IE_HDR_SIZE;
 	}
 
@@ -172,21 +173,21 @@ mwifiex_update_uap_custom_ie(struct mwifiex_private *priv,
 		      le16_to_cpu(beacon_ie->ie_length);
 		memcpy(pos, beacon_ie, len);
 		pos += len;
-		le16_add_cpu(&ap_custom_ie->len, len);
+		le16_unaligned_add_cpu(&ap_custom_ie->len, len);
 	}
 	if (pr_ie) {
 		len = sizeof(struct mwifiex_ie) - IEEE_MAX_IE_SIZE +
 		      le16_to_cpu(pr_ie->ie_length);
 		memcpy(pos, pr_ie, len);
 		pos += len;
-		le16_add_cpu(&ap_custom_ie->len, len);
+		le16_unaligned_add_cpu(&ap_custom_ie->len, len);
 	}
 	if (ar_ie) {
 		len = sizeof(struct mwifiex_ie) - IEEE_MAX_IE_SIZE +
 		      le16_to_cpu(ar_ie->ie_length);
 		memcpy(pos, ar_ie, len);
 		pos += len;
-		le16_add_cpu(&ap_custom_ie->len, len);
+		le16_unaligned_add_cpu(&ap_custom_ie->len, len);
 	}
 
 	ret = mwifiex_update_autoindex_ies(priv, ap_custom_ie);
@@ -242,7 +243,7 @@ static int mwifiex_update_vs_ie(const u8 *ies, int ies_len,
 		vs_ie = (struct ieee_types_header *)vendor_ie;
 		memcpy(ie->ie_buffer + le16_to_cpu(ie->ie_length),
 		       vs_ie, vs_ie->len + 2);
-		le16_add_cpu(&ie->ie_length, vs_ie->len + 2);
+		le16_unaligned_add_cpu(&ie->ie_length, vs_ie->len + 2);
 		ie->mgmt_subtype_mask = cpu_to_le16(mask);
 		ie->ie_index = cpu_to_le16(MWIFIEX_AUTO_IDX_MASK);
 	}
diff --git a/drivers/net/wireless/marvell/mwifiex/ioctl.h b/drivers/net/wireless/marvell/mwifiex/ioctl.h
index 536ab834b126..48e154e1865d 100644
--- a/drivers/net/wireless/marvell/mwifiex/ioctl.h
+++ b/drivers/net/wireless/marvell/mwifiex/ioctl.h
@@ -91,6 +91,8 @@ struct wep_key {
 #define MWIFIEX_TDLS_DEF_QOS_CAPAB		0xf
 #define MWIFIEX_PRIO_BK				2
 #define MWIFIEX_PRIO_VI				5
+#define MWIFIEX_SUPPORTED_CHANNELS		2
+#define MWIFIEX_OPERATING_CLASSES		16
 
 struct mwifiex_uap_bss_param {
 	u8 channel;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 5ebca1d0cfc7..dd87b9ff64c3 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -17,6 +17,8 @@
  * this warranty disclaimer.
  */
 
+#include <linux/suspend.h>
+
 #include "main.h"
 #include "wmm.h"
 #include "cfg80211.h"
@@ -57,8 +59,8 @@ MODULE_PARM_DESC(mfg_mode, "manufacturing mode enable:1, disable:0");
  * In case of any errors during inittialization, this function also ensures
  * proper cleanup before exiting.
  */
-static int mwifiex_register(void *card, struct mwifiex_if_ops *if_ops,
-			    void **padapter)
+static int mwifiex_register(void *card, struct device *dev,
+			    struct mwifiex_if_ops *if_ops, void **padapter)
 {
 	struct mwifiex_adapter *adapter;
 	int i;
@@ -68,6 +70,7 @@ static int mwifiex_register(void *card, struct mwifiex_if_ops *if_ops,
 		return -ENOMEM;
 
 	*padapter = adapter;
+	adapter->dev = dev;
 	adapter->card = card;
 
 	/* Save interface specific operations in adapter */
@@ -146,7 +149,6 @@ static int mwifiex_unregister(struct mwifiex_adapter *adapter)
 
 	kfree(adapter->regd);
 
-	vfree(adapter->chan_stats);
 	kfree(adapter);
 	return 0;
 }
@@ -510,7 +512,7 @@ static void mwifiex_terminate_workqueue(struct mwifiex_adapter *adapter)
  *      - Download the correct firmware to card
  *      - Issue the init commands to firmware
  */
-static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
+static int _mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 {
 	int ret;
 	char fmt[64];
@@ -593,7 +595,7 @@ static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 	rtnl_lock();
 	/* Create station interface by default */
 	wdev = mwifiex_add_virtual_intf(adapter->wiphy, "mlan%d", NET_NAME_ENUM,
-					NL80211_IFTYPE_STATION, NULL, NULL);
+					NL80211_IFTYPE_STATION, NULL);
 	if (IS_ERR(wdev)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cannot create default STA interface\n");
@@ -603,7 +605,7 @@ static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 
 	if (driver_mode & MWIFIEX_DRIVER_MODE_UAP) {
 		wdev = mwifiex_add_virtual_intf(adapter->wiphy, "uap%d", NET_NAME_ENUM,
-						NL80211_IFTYPE_AP, NULL, NULL);
+						NL80211_IFTYPE_AP, NULL);
 		if (IS_ERR(wdev)) {
 			mwifiex_dbg(adapter, ERROR,
 				    "cannot create AP interface\n");
@@ -614,8 +616,7 @@ static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 
 	if (driver_mode & MWIFIEX_DRIVER_MODE_P2P) {
 		wdev = mwifiex_add_virtual_intf(adapter->wiphy, "p2p%d", NET_NAME_ENUM,
-						NL80211_IFTYPE_P2P_CLIENT, NULL,
-						NULL);
+						NL80211_IFTYPE_P2P_CLIENT, NULL);
 		if (IS_ERR(wdev)) {
 			mwifiex_dbg(adapter, ERROR,
 				    "cannot create p2p client interface\n");
@@ -630,6 +631,7 @@ static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 	goto done;
 
 err_add_intf:
+	vfree(adapter->chan_stats);
 	wiphy_unregister(adapter->wiphy);
 	wiphy_free(adapter->wiphy);
 err_init_fw:
@@ -663,11 +665,18 @@ done:
 		mwifiex_free_adapter(adapter);
 	/* Tell all current and future waiters we're finished */
 	complete_all(fw_done);
-	return;
+
+	return init_failed ? -EIO : 0;
+}
+
+static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
+{
+	_mwifiex_fw_dpc(firmware, context);
 }
 
 /*
- * This function initializes the hardware and gets firmware.
+ * This function gets the firmware and (if called asynchronously) kicks off the
+ * HW init when done.
  */
 static int mwifiex_init_hw_fw(struct mwifiex_adapter *adapter,
 			      bool req_fw_nowait)
@@ -690,20 +699,15 @@ static int mwifiex_init_hw_fw(struct mwifiex_adapter *adapter,
 		ret = request_firmware_nowait(THIS_MODULE, 1, adapter->fw_name,
 					      adapter->dev, GFP_KERNEL, adapter,
 					      mwifiex_fw_dpc);
-		if (ret < 0)
-			mwifiex_dbg(adapter, ERROR,
-				    "request_firmware_nowait error %d\n", ret);
 	} else {
 		ret = request_firmware(&adapter->firmware,
 				       adapter->fw_name,
 				       adapter->dev);
-		if (ret < 0)
-			mwifiex_dbg(adapter, ERROR,
-				    "request_firmware error %d\n", ret);
-		else
-			mwifiex_fw_dpc(adapter->firmware, (void *)adapter);
 	}
 
+	if (ret < 0)
+		mwifiex_dbg(adapter, ERROR, "request_firmware%s error %d\n",
+			    req_fw_nowait ? "_nowait" : "", ret);
 	return ret;
 }
 
@@ -744,7 +748,7 @@ mwifiex_close(struct net_device *dev)
 		mwifiex_dbg(priv->adapter, INFO,
 			    "aborting bgscan on ndo_stop\n");
 		mwifiex_stop_bg_scan(priv);
-		cfg80211_sched_scan_stopped(priv->wdev.wiphy);
+		cfg80211_sched_scan_stopped(priv->wdev.wiphy, 0);
 	}
 
 	return 0;
@@ -1412,6 +1416,7 @@ mwifiex_shutdown_sw(struct mwifiex_adapter *adapter)
 			mwifiex_del_virtual_intf(adapter->wiphy, &priv->wdev);
 		rtnl_unlock();
 	}
+	vfree(adapter->chan_stats);
 
 	mwifiex_dbg(adapter, INFO, "%s, successful\n", __func__);
 exit_return:
@@ -1425,6 +1430,8 @@ EXPORT_SYMBOL_GPL(mwifiex_shutdown_sw);
 int
 mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 {
+	int ret;
+
 	mwifiex_init_lock_list(adapter);
 	if (adapter->if_ops.up_dev)
 		adapter->if_ops.up_dev(adapter);
@@ -1434,6 +1441,7 @@ mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 	init_waitqueue_head(&adapter->init_wait_q);
 	adapter->is_suspended = false;
 	adapter->hs_activated = false;
+	adapter->is_cmd_timedout = 0;
 	init_waitqueue_head(&adapter->hs_activate_wait_q);
 	init_waitqueue_head(&adapter->cmd_wait_q.wait);
 	adapter->cmd_wait_q.status = 0;
@@ -1471,9 +1479,15 @@ mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 			    "%s: firmware init failed\n", __func__);
 		goto err_init_fw;
 	}
+
+	/* _mwifiex_fw_dpc() does its own cleanup */
+	ret = _mwifiex_fw_dpc(adapter->firmware, adapter);
+	if (ret) {
+		pr_err("Failed to bring up adapter: %d\n", ret);
+		return ret;
+	}
 	mwifiex_dbg(adapter, INFO, "%s, successful\n", __func__);
 
-	complete_all(adapter->fw_done);
 	return 0;
 
 err_init_fw:
@@ -1501,14 +1515,13 @@ static irqreturn_t mwifiex_irq_wakeup_handler(int irq, void *priv)
 {
 	struct mwifiex_adapter *adapter = priv;
 
-	if (adapter->irq_wakeup >= 0) {
-		dev_dbg(adapter->dev, "%s: wake by wifi", __func__);
-		adapter->wake_by_wifi = true;
-		disable_irq_nosync(irq);
-	}
+	dev_dbg(adapter->dev, "%s: wake by wifi", __func__);
+	adapter->wake_by_wifi = true;
+	disable_irq_nosync(irq);
 
 	/* Notify PM core we are wakeup source */
 	pm_wakeup_event(adapter->dev, 0);
+	pm_system_wakeup();
 
 	return IRQ_HANDLED;
 }
@@ -1568,12 +1581,11 @@ mwifiex_add_card(void *card, struct completion *fw_done,
 {
 	struct mwifiex_adapter *adapter;
 
-	if (mwifiex_register(card, if_ops, (void **)&adapter)) {
+	if (mwifiex_register(card, dev, if_ops, (void **)&adapter)) {
 		pr_err("%s: software init failed\n", __func__);
 		goto err_init_sw;
 	}
 
-	adapter->dev = dev;
 	mwifiex_probe_of(adapter);
 
 	adapter->iface_type = iface_type;
@@ -1714,10 +1726,14 @@ int mwifiex_remove_card(struct mwifiex_adapter *adapter)
 			mwifiex_del_virtual_intf(adapter->wiphy, &priv->wdev);
 		rtnl_unlock();
 	}
+	vfree(adapter->chan_stats);
 
 	wiphy_unregister(adapter->wiphy);
 	wiphy_free(adapter->wiphy);
 
+	if (adapter->irq_wakeup >= 0)
+		device_init_wakeup(adapter->dev, false);
+
 	/* Unregister device */
 	mwifiex_dbg(adapter, INFO,
 		    "info: unregister device\n");
@@ -1739,7 +1755,7 @@ void _mwifiex_dbg(const struct mwifiex_adapter *adapter, int mask,
 	struct va_format vaf;
 	va_list args;
 
-	if (!adapter->dev || !(adapter->debug_mask & mask))
+	if (!(adapter->debug_mask & mask))
 		return;
 
 	va_start(args, fmt);
@@ -1747,7 +1763,10 @@ void _mwifiex_dbg(const struct mwifiex_adapter *adapter, int mask,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	dev_info(adapter->dev, "%pV", &vaf);
+	if (adapter->dev)
+		dev_info(adapter->dev, "%pV", &vaf);
+	else
+		pr_info("%pV", &vaf);
 
 	va_end(args);
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 5c8297207f33..bb2a467d8b13 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1359,7 +1359,7 @@ mwifiex_netdev_get_priv(struct net_device *dev)
  */
 static inline bool mwifiex_is_skb_mgmt_frame(struct sk_buff *skb)
 {
-	return (le32_to_cpu(*(__le32 *)skb->data) == PKT_TYPE_MGMT);
+	return (get_unaligned_le32(skb->data) == PKT_TYPE_MGMT);
 }
 
 /* This function retrieves channel closed for operation by Channel
@@ -1529,7 +1529,6 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 					      const char *name,
 					      unsigned char name_assign_type,
 					      enum nl80211_iftype type,
-					      u32 *flags,
 					      struct vif_params *params);
 int mwifiex_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev);
 
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index a0d918094889..ac62bce50e96 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -119,7 +119,7 @@ static int mwifiex_read_reg_byte(struct mwifiex_adapter *adapter,
  */
 static bool mwifiex_pcie_ok_to_access_hw(struct mwifiex_adapter *adapter)
 {
-	u32 *cookie_addr;
+	u32 cookie_value;
 	struct pcie_service_card *card = adapter->card;
 	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
 
@@ -127,11 +127,11 @@ static bool mwifiex_pcie_ok_to_access_hw(struct mwifiex_adapter *adapter)
 		return true;
 
 	if (card->sleep_cookie_vbase) {
-		cookie_addr = (u32 *)card->sleep_cookie_vbase;
+		cookie_value = get_unaligned_le32(card->sleep_cookie_vbase);
 		mwifiex_dbg(adapter, INFO,
 			    "info: ACCESS_HW: sleep cookie=0x%x\n",
-			    *cookie_addr);
-		if (*cookie_addr == FW_AWAKE_COOKIE)
+			    cookie_value);
+		if (cookie_value == FW_AWAKE_COOKIE)
 			return true;
 	}
 
@@ -294,8 +294,6 @@ static void mwifiex_pcie_remove(struct pci_dev *pdev)
 	if (!adapter || !adapter->priv_num)
 		return;
 
-	cancel_work_sync(&card->work);
-
 	reg = card->pcie.reg;
 	if (reg)
 		ret = mwifiex_read_reg(adapter, reg->fw_status, &fw_status);
@@ -350,22 +348,16 @@ MODULE_DEVICE_TABLE(pci, mwifiex_ids);
 
 static void mwifiex_pcie_reset_notify(struct pci_dev *pdev, bool prepare)
 {
-	struct mwifiex_adapter *adapter;
-	struct pcie_service_card *card;
-
-	if (!pdev) {
-		pr_err("%s: PCIe device is not specified\n", __func__);
-		return;
-	}
+	struct pcie_service_card *card = pci_get_drvdata(pdev);
+	struct mwifiex_adapter *adapter = card->adapter;
+	int ret;
 
-	card = (struct pcie_service_card *)pci_get_drvdata(pdev);
-	if (!card || !card->adapter) {
-		pr_err("%s: Card or adapter structure is not valid (%ld)\n",
-		       __func__, (long)card);
+	if (!adapter) {
+		dev_err(&pdev->dev, "%s: adapter structure is not valid\n",
+			__func__);
 		return;
 	}
 
-	adapter = card->adapter;
 	mwifiex_dbg(adapter, INFO,
 		    "%s: vendor=0x%4.04x device=0x%4.04x rev=%d %s\n",
 		    __func__, pdev->vendor, pdev->device,
@@ -379,13 +371,19 @@ static void mwifiex_pcie_reset_notify(struct pci_dev *pdev, bool prepare)
 		 */
 		mwifiex_shutdown_sw(adapter);
 		adapter->surprise_removed = true;
+		clear_bit(MWIFIEX_IFACE_WORK_DEVICE_DUMP, &card->work_flags);
+		clear_bit(MWIFIEX_IFACE_WORK_CARD_RESET, &card->work_flags);
 	} else {
 		/* Kernel stores and restores PCIe function context before and
 		 * after performing FLR respectively. Reconfigure the software
 		 * and firmware including firmware redownload
 		 */
 		adapter->surprise_removed = false;
-		mwifiex_reinit_sw(adapter);
+		ret = mwifiex_reinit_sw(adapter);
+		if (ret) {
+			dev_err(&pdev->dev, "reinit failed: %d\n", ret);
+			return;
+		}
 	}
 	mwifiex_dbg(adapter, INFO, "%s, successful\n", __func__);
 }
@@ -447,7 +445,7 @@ static void mwifiex_delay_for_sleep_cookie(struct mwifiex_adapter *adapter,
 					    sizeof(sleep_cookie),
 					    PCI_DMA_FROMDEVICE);
 		buffer = cmdrsp->data;
-		sleep_cookie = READ_ONCE(*(u32 *)buffer);
+		sleep_cookie = get_unaligned_le32(buffer);
 
 		if (sleep_cookie == MWIFIEX_DEF_SLEEP_COOKIE) {
 			mwifiex_dbg(adapter, INFO,
@@ -1039,6 +1037,7 @@ static int mwifiex_pcie_delete_cmdrsp_buf(struct mwifiex_adapter *adapter)
 	if (card && card->cmd_buf) {
 		mwifiex_unmap_pci_memory(adapter, card->cmd_buf,
 					 PCI_DMA_TODEVICE);
+		dev_kfree_skb_any(card->cmd_buf);
 	}
 	return 0;
 }
@@ -1049,6 +1048,7 @@ static int mwifiex_pcie_delete_cmdrsp_buf(struct mwifiex_adapter *adapter)
 static int mwifiex_pcie_alloc_sleep_cookie_buf(struct mwifiex_adapter *adapter)
 {
 	struct pcie_service_card *card = adapter->card;
+	u32 tmp;
 
 	card->sleep_cookie_vbase = pci_alloc_consistent(card->dev, sizeof(u32),
 						     &card->sleep_cookie_pbase);
@@ -1058,11 +1058,12 @@ static int mwifiex_pcie_alloc_sleep_cookie_buf(struct mwifiex_adapter *adapter)
 		return -ENOMEM;
 	}
 	/* Init val of Sleep Cookie */
-	*(u32 *)card->sleep_cookie_vbase = FW_AWAKE_COOKIE;
+	tmp = FW_AWAKE_COOKIE;
+	put_unaligned(tmp, card->sleep_cookie_vbase);
 
 	mwifiex_dbg(adapter, INFO,
 		    "alloc_scook: sleep cookie=0x%x\n",
-		    *((u32 *)card->sleep_cookie_vbase));
+		    get_unaligned(card->sleep_cookie_vbase));
 
 	return 0;
 }
@@ -1223,7 +1224,6 @@ mwifiex_pcie_send_data(struct mwifiex_adapter *adapter, struct sk_buff *skb,
 	dma_addr_t buf_pa;
 	struct mwifiex_pcie_buf_desc *desc = NULL;
 	struct mwifiex_pfu_buf_desc *desc2 = NULL;
-	__le16 *tmp;
 
 	if (!(skb->data && skb->len)) {
 		mwifiex_dbg(adapter, ERROR,
@@ -1244,10 +1244,8 @@ mwifiex_pcie_send_data(struct mwifiex_adapter *adapter, struct sk_buff *skb,
 
 		adapter->data_sent = true;
 		payload = skb->data;
-		tmp = (__le16 *)&payload[0];
-		*tmp = cpu_to_le16((u16)skb->len);
-		tmp = (__le16 *)&payload[2];
-		*tmp = cpu_to_le16(MWIFIEX_TYPE_DATA);
+		put_unaligned_le16((u16)skb->len, payload + 0);
+		put_unaligned_le16(MWIFIEX_TYPE_DATA, payload + 2);
 
 		if (mwifiex_map_pci_memory(adapter, skb, skb->len,
 					   PCI_DMA_TODEVICE))
@@ -1376,7 +1374,6 @@ static int mwifiex_pcie_process_recv_data(struct mwifiex_adapter *adapter)
 		(card->rxbd_rdptr & reg->rx_rollover_ind))) {
 		struct sk_buff *skb_data;
 		u16 rx_len;
-		__le16 pkt_len;
 
 		rd_index = card->rxbd_rdptr & reg->rx_mask;
 		skb_data = card->rx_buf_list[rd_index];
@@ -1393,8 +1390,7 @@ static int mwifiex_pcie_process_recv_data(struct mwifiex_adapter *adapter)
 		/* Get data length from interface header -
 		 * first 2 bytes for len, next 2 bytes is for type
 		 */
-		pkt_len = *((__le16 *)skb_data->data);
-		rx_len = le16_to_cpu(pkt_len);
+		rx_len = get_unaligned_le16(skb_data->data);
 		if (WARN_ON(rx_len <= INTF_HEADER_LEN ||
 			    rx_len > MWIFIEX_RX_DATA_BUF_SIZE)) {
 			mwifiex_dbg(adapter, ERROR,
@@ -1601,13 +1597,18 @@ mwifiex_pcie_send_cmd(struct mwifiex_adapter *adapter, struct sk_buff *skb)
 
 	adapter->cmd_sent = true;
 
-	*(__le16 *)&payload[0] = cpu_to_le16((u16)skb->len);
-	*(__le16 *)&payload[2] = cpu_to_le16(MWIFIEX_TYPE_CMD);
+	put_unaligned_le16((u16)skb->len, &payload[0]);
+	put_unaligned_le16(MWIFIEX_TYPE_CMD, &payload[2]);
 
 	if (mwifiex_map_pci_memory(adapter, skb, skb->len, PCI_DMA_TODEVICE))
 		return -1;
 
 	card->cmd_buf = skb;
+	/*
+	 * Need to keep a reference, since core driver might free up this
+	 * buffer before we've unmapped it.
+	 */
+	skb_get(skb);
 
 	/* To send a command, the driver will:
 		1. Write the 64bit physical address of the data buffer to
@@ -1694,7 +1695,6 @@ static int mwifiex_pcie_process_cmd_complete(struct mwifiex_adapter *adapter)
 	struct sk_buff *skb = card->cmdrsp_buf;
 	int count = 0;
 	u16 rx_len;
-	__le16 pkt_len;
 
 	mwifiex_dbg(adapter, CMD,
 		    "info: Rx CMD Response\n");
@@ -1711,11 +1711,11 @@ static int mwifiex_pcie_process_cmd_complete(struct mwifiex_adapter *adapter)
 	if (card->cmd_buf) {
 		mwifiex_unmap_pci_memory(adapter, card->cmd_buf,
 					 PCI_DMA_TODEVICE);
+		dev_kfree_skb_any(card->cmd_buf);
 		card->cmd_buf = NULL;
 	}
 
-	pkt_len = *((__le16 *)skb->data);
-	rx_len = le16_to_cpu(pkt_len);
+	rx_len = get_unaligned_le16(skb->data);
 	skb_put(skb, MWIFIEX_UPLD_SIZE - skb->len);
 	skb_trim(skb, rx_len);
 
@@ -1856,7 +1856,7 @@ static int mwifiex_pcie_process_event_ready(struct mwifiex_adapter *adapter)
 		desc = card->evtbd_ring[rdptr];
 		memset(desc, 0, sizeof(*desc));
 
-		event = *(u32 *) &skb_cmd->data[INTF_HEADER_LEN];
+		event = get_unaligned_le32(&skb_cmd->data[INTF_HEADER_LEN]);
 		adapter->event_cause = event;
 		/* The first 4bytes will be the event transfer header
 		   len is 2 bytes followed by type which is 2 bytes */
@@ -1965,6 +1965,94 @@ static int mwifiex_pcie_event_complete(struct mwifiex_adapter *adapter,
 	return ret;
 }
 
+/* Combo firmware image is a combination of
+ * (1) combo crc heaer, start with CMD5
+ * (2) bluetooth image, start with CMD7, end with CMD6, data wrapped in CMD1.
+ * (3) wifi image.
+ *
+ * This function bypass the header and bluetooth part, return
+ * the offset of tail wifi-only part.
+ */
+
+static int mwifiex_extract_wifi_fw(struct mwifiex_adapter *adapter,
+				   const void *firmware, u32 firmware_len) {
+	const struct mwifiex_fw_data *fwdata;
+	u32 offset = 0, data_len, dnld_cmd;
+	int ret = 0;
+	bool cmd7_before = false;
+
+	while (1) {
+		/* Check for integer and buffer overflow */
+		if (offset + sizeof(fwdata->header) < sizeof(fwdata->header) ||
+		    offset + sizeof(fwdata->header) >= firmware_len) {
+			mwifiex_dbg(adapter, ERROR,
+				    "extract wifi-only fw failure!\n");
+			ret = -1;
+			goto done;
+		}
+
+		fwdata = firmware + offset;
+		dnld_cmd = le32_to_cpu(fwdata->header.dnld_cmd);
+		data_len = le32_to_cpu(fwdata->header.data_length);
+
+		/* Skip past header */
+		offset += sizeof(fwdata->header);
+
+		switch (dnld_cmd) {
+		case MWIFIEX_FW_DNLD_CMD_1:
+			if (!cmd7_before) {
+				mwifiex_dbg(adapter, ERROR,
+					    "no cmd7 before cmd1!\n");
+				ret = -1;
+				goto done;
+			}
+			if (offset + data_len < data_len) {
+				mwifiex_dbg(adapter, ERROR, "bad FW parse\n");
+				ret = -1;
+				goto done;
+			}
+			offset += data_len;
+			break;
+		case MWIFIEX_FW_DNLD_CMD_5:
+			/* Check for integer overflow */
+			if (offset + data_len < data_len) {
+				mwifiex_dbg(adapter, ERROR, "bad FW parse\n");
+				ret = -1;
+				goto done;
+			}
+			offset += data_len;
+			break;
+		case MWIFIEX_FW_DNLD_CMD_6:
+			/* Check for integer overflow */
+			if (offset + data_len < data_len) {
+				mwifiex_dbg(adapter, ERROR, "bad FW parse\n");
+				ret = -1;
+				goto done;
+			}
+			offset += data_len;
+			if (offset >= firmware_len) {
+				mwifiex_dbg(adapter, ERROR,
+					    "extract wifi-only fw failure!\n");
+				ret = -1;
+			} else {
+				ret = offset;
+			}
+			goto done;
+		case MWIFIEX_FW_DNLD_CMD_7:
+			cmd7_before = true;
+			break;
+		default:
+			mwifiex_dbg(adapter, ERROR, "unknown dnld_cmd %d\n",
+				    dnld_cmd);
+			ret = -1;
+			goto done;
+		}
+	}
+
+done:
+	return ret;
+}
+
 /*
  * This function downloads the firmware to the card.
  *
@@ -1980,7 +2068,7 @@ static int mwifiex_prog_fw_w_helper(struct mwifiex_adapter *adapter,
 	u32 firmware_len = fw->fw_len;
 	u32 offset = 0;
 	struct sk_buff *skb;
-	u32 txlen, tx_blocks = 0, tries, len;
+	u32 txlen, tx_blocks = 0, tries, len, val;
 	u32 block_retry_cnt = 0;
 	struct pcie_service_card *card = adapter->card;
 	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
@@ -2007,6 +2095,24 @@ static int mwifiex_prog_fw_w_helper(struct mwifiex_adapter *adapter,
 		goto done;
 	}
 
+	ret = mwifiex_read_reg(adapter, PCIE_SCRATCH_13_REG, &val);
+	if (ret) {
+		mwifiex_dbg(adapter, FATAL, "Failed to read scratch register 13\n");
+		goto done;
+	}
+
+	/* PCIE FLR case: extract wifi part from combo firmware*/
+	if (val == MWIFIEX_PCIE_FLR_HAPPENS) {
+		ret = mwifiex_extract_wifi_fw(adapter, firmware, firmware_len);
+		if (ret < 0) {
+			mwifiex_dbg(adapter, ERROR, "Failed to extract wifi fw\n");
+			goto done;
+		}
+		offset = ret;
+		mwifiex_dbg(adapter, MSG,
+			    "info: dnld wifi firmware from %d bytes\n", offset);
+	}
+
 	/* Perform firmware data transfer */
 	do {
 		u32 ireg_intr = 0;
@@ -2503,8 +2609,8 @@ mwifiex_pcie_reg_dump(struct mwifiex_adapter *adapter, char *drv_buf)
 	struct pcie_service_card *card = adapter->card;
 	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
 	int pcie_scratch_reg[] = {PCIE_SCRATCH_12_REG,
-				  PCIE_SCRATCH_13_REG,
-				  PCIE_SCRATCH_14_REG};
+				  PCIE_SCRATCH_14_REG,
+				  PCIE_SCRATCH_15_REG};
 
 	if (!p)
 		return 0;
@@ -2739,6 +2845,21 @@ static void mwifiex_pcie_device_dump(struct mwifiex_adapter *adapter)
 	schedule_work(&card->work);
 }
 
+static void mwifiex_pcie_free_buffers(struct mwifiex_adapter *adapter)
+{
+	struct pcie_service_card *card = adapter->card;
+	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
+
+	if (reg->sleep_cookie)
+		mwifiex_pcie_delete_sleep_cookie_buf(adapter);
+
+	mwifiex_pcie_delete_cmdrsp_buf(adapter);
+	mwifiex_pcie_delete_evtbd_ring(adapter);
+	mwifiex_pcie_delete_rxbd_ring(adapter);
+	mwifiex_pcie_delete_txbd_ring(adapter);
+	card->cmdrsp_buf = NULL;
+}
+
 /*
  * This function initializes the PCI-E host memory space, WCB rings, etc.
  *
@@ -2850,13 +2971,6 @@ err_enable_dev:
 
 /*
  * This function cleans up the allocated card buffers.
- *
- * The following are freed by this function -
- *      - TXBD ring buffers
- *      - RXBD ring buffers
- *      - Event BD ring buffers
- *      - Command response ring buffer
- *      - Sleep cookie buffer
  */
 static void mwifiex_cleanup_pcie(struct mwifiex_adapter *adapter)
 {
@@ -2866,6 +2980,8 @@ static void mwifiex_cleanup_pcie(struct mwifiex_adapter *adapter)
 	int ret;
 	u32 fw_status;
 
+	cancel_work_sync(&card->work);
+
 	ret = mwifiex_read_reg(adapter, reg->fw_status, &fw_status);
 	if (fw_status == FIRMWARE_READY_PCIE) {
 		mwifiex_dbg(adapter, INFO,
@@ -2875,6 +2991,8 @@ static void mwifiex_cleanup_pcie(struct mwifiex_adapter *adapter)
 				    "Failed to write driver not-ready signature\n");
 	}
 
+	mwifiex_pcie_free_buffers(adapter);
+
 	if (pdev) {
 		pci_iounmap(pdev, card->pci_mmap);
 		pci_iounmap(pdev, card->pci_mmap1);
@@ -3067,12 +3185,6 @@ static void mwifiex_pcie_up_dev(struct mwifiex_adapter *adapter)
 	struct pci_dev *pdev = card->dev;
 	const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
 
-	/* Bluetooth is not on pcie interface. Download Wifi only firmware
-	 * during pcie FLR, so that bluetooth part of firmware which is
-	 * already running doesn't get affected.
-	 */
-	strcpy(adapter->fw_name, PCIE8997_DEFAULT_WIFIFW_NAME);
-
 	/* tx_buf_size might be changed to 3584 by firmware during
 	 * data transfer, we should reset it to default size.
 	 */
@@ -3126,10 +3238,7 @@ err_cre_txbd:
 	pci_iounmap(pdev, card->pci_mmap1);
 }
 
-/* This function cleans up the PCI-E host memory space.
- * Some code is extracted from mwifiex_unregister_dev()
- *
- */
+/* This function cleans up the PCI-E host memory space. */
 static void mwifiex_pcie_down_dev(struct mwifiex_adapter *adapter)
 {
 	struct pcie_service_card *card = adapter->card;
@@ -3140,14 +3249,7 @@ static void mwifiex_pcie_down_dev(struct mwifiex_adapter *adapter)
 
 	adapter->seq_num = 0;
 
-	if (reg->sleep_cookie)
-		mwifiex_pcie_delete_sleep_cookie_buf(adapter);
-
-	mwifiex_pcie_delete_cmdrsp_buf(adapter);
-	mwifiex_pcie_delete_evtbd_ring(adapter);
-	mwifiex_pcie_delete_rxbd_ring(adapter);
-	mwifiex_pcie_delete_txbd_ring(adapter);
-	card->cmdrsp_buf = NULL;
+	mwifiex_pcie_free_buffers(adapter);
 }
 
 static struct mwifiex_if_ops pcie_ops = {
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.h b/drivers/net/wireless/marvell/mwifiex/pcie.h
index 00e8ee5ad4a8..f7ce9b6db6b4 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.h
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.h
@@ -35,7 +35,6 @@
 #define PCIE8897_B0_FW_NAME "mrvl/pcie8897_uapsta.bin"
 #define PCIEUART8997_FW_NAME_V4 "mrvl/pcieuart8997_combo_v4.bin"
 #define PCIEUSB8997_FW_NAME_V4 "mrvl/pcieusb8997_combo_v4.bin"
-#define PCIE8997_DEFAULT_WIFIFW_NAME "mrvl/pcie8997_wlan_v4.bin"
 
 #define PCIE_VENDOR_ID_MARVELL              (0x11ab)
 #define PCIE_VENDOR_ID_V2_MARVELL           (0x1b4b)
@@ -77,8 +76,9 @@
 #define PCIE_SCRATCH_10_REG				0xCE8
 #define PCIE_SCRATCH_11_REG				0xCEC
 #define PCIE_SCRATCH_12_REG				0xCF0
-#define PCIE_SCRATCH_13_REG				0xCF8
-#define PCIE_SCRATCH_14_REG				0xCFC
+#define PCIE_SCRATCH_13_REG				0xCF4
+#define PCIE_SCRATCH_14_REG				0xCF8
+#define PCIE_SCRATCH_15_REG				0xCFC
 #define PCIE_RD_DATA_PTR_Q0_Q1                          0xC08C
 #define PCIE_WR_DATA_PTR_Q0_Q1                          0xC05C
 
@@ -119,6 +119,8 @@
 #define MWIFIEX_SLEEP_COOKIE_SIZE			4
 #define MWIFIEX_MAX_DELAY_COUNT				100
 
+#define MWIFIEX_PCIE_FLR_HAPPENS 0xFEDCBABA
+
 struct mwifiex_pcie_card_reg {
 	u16 cmd_addr_lo;
 	u16 cmd_addr_hi;
@@ -217,8 +219,8 @@ static const struct mwifiex_pcie_card_reg mwifiex_reg_8897 = {
 	.ring_tx_start_ptr = MWIFIEX_BD_FLAG_TX_START_PTR,
 	.pfu_enabled = 1,
 	.sleep_cookie = 0,
-	.fw_dump_ctrl = 0xcf4,
-	.fw_dump_start = 0xcf8,
+	.fw_dump_ctrl = PCIE_SCRATCH_13_REG,
+	.fw_dump_start = PCIE_SCRATCH_14_REG,
 	.fw_dump_end = 0xcff,
 	.fw_dump_host_ready = 0xee,
 	.fw_dump_read_done = 0xfe,
@@ -254,8 +256,8 @@ static const struct mwifiex_pcie_card_reg mwifiex_reg_8997 = {
 	.ring_tx_start_ptr = MWIFIEX_BD_FLAG_TX_START_PTR,
 	.pfu_enabled = 1,
 	.sleep_cookie = 0,
-	.fw_dump_ctrl = 0xcf4,
-	.fw_dump_start = 0xcf8,
+	.fw_dump_ctrl = PCIE_SCRATCH_13_REG,
+	.fw_dump_start = PCIE_SCRATCH_14_REG,
 	.fw_dump_end = 0xcff,
 	.fw_dump_host_ready = 0xcc,
 	.fw_dump_read_done = 0xdd,
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 181691684a08..ce6936d0c5c0 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -691,8 +691,9 @@ mwifiex_scan_channel_list(struct mwifiex_private *priv,
 
 			/* Increment the TLV header length by the size
 			   appended */
-			le16_add_cpu(&chan_tlv_out->header.len,
-				     sizeof(chan_tlv_out->chan_scan_param));
+			le16_unaligned_add_cpu(&chan_tlv_out->header.len,
+					       sizeof(
+						chan_tlv_out->chan_scan_param));
 
 			/*
 			 * The tlv buffer length is set to the number of bytes
@@ -859,6 +860,7 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 	*scan_current_only = false;
 
 	if (user_scan_in) {
+		u8 tmpaddr[ETH_ALEN];
 
 		/* Default the ssid_filter flag to TRUE, set false under
 		   certain wildcard conditions and qualified by the existence
@@ -883,8 +885,10 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 		       user_scan_in->specific_bssid,
 		       sizeof(scan_cfg_out->specific_bssid));
 
+		memcpy(tmpaddr, scan_cfg_out->specific_bssid, ETH_ALEN);
+
 		if (adapter->ext_scan &&
-		    !is_zero_ether_addr(scan_cfg_out->specific_bssid)) {
+		    !is_zero_ether_addr(tmpaddr)) {
 			bssid_tlv =
 				(struct mwifiex_ie_types_bssid_list *)tlv_pos;
 			bssid_tlv->header.type = cpu_to_le16(TLV_TYPE_BSSID);
@@ -947,8 +951,9 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 		 *  truncate scan results.  That is not an issue with an SSID
 		 *  or BSSID filter applied to the scan results in the firmware.
 		 */
+		memcpy(tmpaddr, scan_cfg_out->specific_bssid, ETH_ALEN);
 		if ((i && ssid_filter) ||
-		    !is_zero_ether_addr(scan_cfg_out->specific_bssid))
+		    !is_zero_ether_addr(tmpaddr))
 			*filtered_scan = true;
 
 		if (user_scan_in->scan_chan_gap) {
@@ -989,10 +994,15 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 	 *  If a specific BSSID or SSID is used, the number of channels in the
 	 *  scan command will be increased to the absolute maximum.
 	 */
-	if (*filtered_scan)
+	if (*filtered_scan) {
 		*max_chan_per_scan = MWIFIEX_MAX_CHANNELS_PER_SPECIFIC_SCAN;
-	else
-		*max_chan_per_scan = MWIFIEX_DEF_CHANNELS_PER_SCAN_CMD;
+	} else {
+		if (!priv->media_connected)
+			*max_chan_per_scan = MWIFIEX_DEF_CHANNELS_PER_SCAN_CMD;
+		else
+			*max_chan_per_scan =
+					MWIFIEX_DEF_CHANNELS_PER_SCAN_CMD / 2;
+	}
 
 	if (adapter->ext_scan) {
 		bss_mode = (struct mwifiex_ie_types_bss_mode *)tlv_pos;
@@ -1742,7 +1752,7 @@ mwifiex_parse_single_response_buf(struct mwifiex_private *priv, u8 **bss_info,
 
 	if (*bytes_left >= sizeof(beacon_size)) {
 		/* Extract & convert beacon size from command buffer */
-		beacon_size = le16_to_cpu(*(__le16 *)(*bss_info));
+		beacon_size = get_unaligned_le16((*bss_info));
 		*bytes_left -= sizeof(beacon_size);
 		*bss_info += sizeof(beacon_size);
 	}
@@ -2369,8 +2379,9 @@ int mwifiex_cmd_802_11_bg_scan_config(struct mwifiex_private *priv,
 			temp_chan = chan_list_tlv->chan_scan_param + chan_idx;
 
 			/* Increment the TLV header length by size appended */
-			le16_add_cpu(&chan_list_tlv->header.len,
-				     sizeof(chan_list_tlv->chan_scan_param));
+			le16_unaligned_add_cpu(&chan_list_tlv->header.len,
+					       sizeof(
+					       chan_list_tlv->chan_scan_param));
 
 			temp_chan->chan_number =
 				bgscan_cfg_in->chan_list[chan_idx].chan_number;
@@ -2407,8 +2418,8 @@ int mwifiex_cmd_802_11_bg_scan_config(struct mwifiex_private *priv,
 			mwifiex_bgscan_create_channel_list(priv, bgscan_cfg_in,
 							   chan_list_tlv->
 							   chan_scan_param);
-		le16_add_cpu(&chan_list_tlv->header.len,
-			     chan_num *
+		le16_unaligned_add_cpu(&chan_list_tlv->header.len,
+				       chan_num *
 			     sizeof(chan_list_tlv->chan_scan_param[0]));
 	}
 
@@ -2432,7 +2443,7 @@ int mwifiex_cmd_802_11_bg_scan_config(struct mwifiex_private *priv,
 	/* Append vendor specific IE TLV */
 	mwifiex_cmd_append_vsie_tlv(priv, MWIFIEX_VSIE_MASK_BGSCAN, &tlv_pos);
 
-	le16_add_cpu(&cmd->size, tlv_pos - bgscan_config->tlv);
+	le16_unaligned_add_cpu(&cmd->size, tlv_pos - bgscan_config->tlv);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index a4b356d267f9..0af1c6733c92 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -387,8 +387,6 @@ mwifiex_sdio_remove(struct sdio_func *func)
 	if (!adapter || !adapter->priv_num)
 		return;
 
-	cancel_work_sync(&card->work);
-
 	mwifiex_dbg(adapter, INFO, "info: SDIO func num=%d\n", func->num);
 
 	ret = mwifiex_sdio_read_fw_status(adapter, &firmware_stat);
@@ -943,7 +941,7 @@ static int mwifiex_sdio_card_to_host(struct mwifiex_adapter *adapter,
 		return -1;
 	}
 
-	nb = le16_to_cpu(*(__le16 *) (buffer));
+	nb = get_unaligned_le16((buffer));
 	if (nb > npayload) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: invalid packet, nb=%d npayload=%d\n",
@@ -951,7 +949,7 @@ static int mwifiex_sdio_card_to_host(struct mwifiex_adapter *adapter,
 		return -1;
 	}
 
-	*type = le16_to_cpu(*(__le16 *) (buffer + 2));
+	*type = get_unaligned_le16((buffer + 2));
 
 	return ret;
 }
@@ -1139,7 +1137,8 @@ static void mwifiex_deaggr_sdio_pkt(struct mwifiex_adapter *adapter,
 				    __func__, blk_num, blk_size, total_pkt_len);
 			break;
 		}
-		pkt_len = le16_to_cpu(*(__le16 *)(data + SDIO_HEADER_OFFSET));
+		pkt_len = get_unaligned_le16((data +
+					     SDIO_HEADER_OFFSET));
 		if ((pkt_len + SDIO_HEADER_OFFSET) > blk_size) {
 			mwifiex_dbg(adapter, ERROR,
 				    "%s: error in pkt_len,\t"
@@ -1172,10 +1171,11 @@ static int mwifiex_decode_rx_packet(struct mwifiex_adapter *adapter,
 				    struct sk_buff *skb, u32 upld_typ)
 {
 	u8 *cmd_buf;
-	__le16 *curr_ptr = (__le16 *)skb->data;
-	u16 pkt_len = le16_to_cpu(*curr_ptr);
+	u16 pkt_len;
 	struct mwifiex_rxinfo *rx_info;
 
+	pkt_len = get_unaligned_le16(skb->data);
+
 	if (upld_typ != MWIFIEX_TYPE_AGGR_DATA) {
 		skb_trim(skb, pkt_len);
 		skb_pull(skb, INTF_HEADER_LEN);
@@ -1235,7 +1235,7 @@ static int mwifiex_decode_rx_packet(struct mwifiex_adapter *adapter,
 	case MWIFIEX_TYPE_EVENT:
 		mwifiex_dbg(adapter, EVENT,
 			    "info: --- Rx: Event ---\n");
-		adapter->event_cause = le32_to_cpu(*(__le32 *) skb->data);
+		adapter->event_cause = get_unaligned_le32(skb->data);
 
 		if ((skb->len > 0) && (skb->len  < MAX_EVENT_SIZE))
 			memcpy(adapter->event_body,
@@ -1380,7 +1380,7 @@ static int mwifiex_sdio_card_to_host_mp_aggr(struct mwifiex_adapter *adapter,
 		}
 
 		if (card->mpa_rx.pkt_cnt == 1)
-			mport = adapter->ioport + port;
+			mport = adapter->ioport + card->mpa_rx.start_port;
 
 		if (mwifiex_read_data_sync(adapter, card->mpa_rx.buf,
 					   card->mpa_rx.buf_len, mport, 1))
@@ -1392,8 +1392,8 @@ static int mwifiex_sdio_card_to_host_mp_aggr(struct mwifiex_adapter *adapter,
 			u32 *len_arr = card->mpa_rx.len_arr;
 
 			/* get curr PKT len & type */
-			pkt_len = le16_to_cpu(*(__le16 *) &curr_ptr[0]);
-			pkt_type = le16_to_cpu(*(__le16 *) &curr_ptr[2]);
+			pkt_len = get_unaligned_le16(&curr_ptr[0]);
+			pkt_type = get_unaligned_le16(&curr_ptr[2]);
 
 			/* copy pkt to deaggr buf */
 			skb_deaggr = mwifiex_alloc_dma_align_buf(len_arr[pind],
@@ -1813,7 +1813,7 @@ static int mwifiex_host_to_card_mp_aggr(struct mwifiex_adapter *adapter,
 		}
 
 		if (card->mpa_tx.pkt_cnt == 1)
-			mport = adapter->ioport + port;
+			mport = adapter->ioport + card->mpa_tx.start_port;
 
 		ret = mwifiex_write_data_to_card(adapter, card->mpa_tx.buf,
 						 card->mpa_tx.buf_len, mport);
@@ -1874,8 +1874,9 @@ static int mwifiex_sdio_host_to_card(struct mwifiex_adapter *adapter,
 	/* Allocate buffer and copy payload */
 	blk_size = MWIFIEX_SDIO_BLOCK_SIZE;
 	buf_block_len = (pkt_len + blk_size - 1) / blk_size;
-	*(__le16 *)&payload[0] = cpu_to_le16((u16)pkt_len);
-	*(__le16 *)&payload[2] = cpu_to_le16(type);
+	put_unaligned_le16((u16)pkt_len, payload + 0);
+	put_unaligned_le16((u32)type, payload + 2);
+
 
 	/*
 	 * This is SDIO specific header
@@ -2155,6 +2156,8 @@ static void mwifiex_cleanup_sdio(struct mwifiex_adapter *adapter)
 {
 	struct sdio_mmc_card *card = adapter->card;
 
+	cancel_work_sync(&card->work);
+
 	kfree(card->mp_regs);
 	kfree(card->mpa_rx.skb_arr);
 	kfree(card->mpa_rx.len_arr);
@@ -2193,6 +2196,7 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter)
 {
 	struct sdio_mmc_card *card = adapter->card;
 	struct sdio_func *func = card->func;
+	int ret;
 
 	mwifiex_shutdown_sw(adapter);
 
@@ -2207,7 +2211,9 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter)
 	clear_bit(MWIFIEX_IFACE_WORK_DEVICE_DUMP, &card->work_flags);
 	clear_bit(MWIFIEX_IFACE_WORK_CARD_RESET, &card->work_flags);
 
-	mwifiex_reinit_sw(adapter);
+	ret = mwifiex_reinit_sw(adapter);
+	if (ret)
+		dev_err(&func->dev, "reinit failed: %d\n", ret);
 }
 
 /* This function read/write firmware */
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
index 2f1f4d190b28..83916c1439af 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
@@ -126,19 +126,19 @@ static int mwifiex_cmd_802_11_snmp_mib(struct mwifiex_private *priv,
 	if (cmd_action == HostCmd_ACT_GEN_GET) {
 		snmp_mib->query_type = cpu_to_le16(HostCmd_ACT_GEN_GET);
 		snmp_mib->buf_size = cpu_to_le16(MAX_SNMP_BUF_SIZE);
-		le16_add_cpu(&cmd->size, MAX_SNMP_BUF_SIZE);
+		le16_unaligned_add_cpu(&cmd->size, MAX_SNMP_BUF_SIZE);
 	} else if (cmd_action == HostCmd_ACT_GEN_SET) {
 		snmp_mib->query_type = cpu_to_le16(HostCmd_ACT_GEN_SET);
 		snmp_mib->buf_size = cpu_to_le16(sizeof(u16));
-		*((__le16 *) (snmp_mib->value)) = cpu_to_le16(*ul_temp);
-		le16_add_cpu(&cmd->size, sizeof(u16));
+		put_unaligned_le16(*ul_temp, snmp_mib->value);
+		le16_unaligned_add_cpu(&cmd->size, sizeof(u16));
 	}
 
 	mwifiex_dbg(priv->adapter, CMD,
 		    "cmd: SNMP_CMD: Action=0x%x, OID=0x%x,\t"
 		    "OIDSize=0x%x, Value=0x%x\n",
 		    cmd_action, cmd_oid, le16_to_cpu(snmp_mib->buf_size),
-		    le16_to_cpu(*(__le16 *)snmp_mib->value));
+		    get_unaligned_le16(snmp_mib->value));
 	return 0;
 }
 
@@ -1357,8 +1357,9 @@ mwifiex_cmd_802_11_subsc_evt(struct mwifiex_private *priv,
 			    subsc_evt_cfg->bcn_l_rssi_cfg.evt_freq);
 
 		pos += sizeof(struct mwifiex_ie_types_rssi_threshold);
-		le16_add_cpu(&cmd->size,
-			     sizeof(struct mwifiex_ie_types_rssi_threshold));
+		le16_unaligned_add_cpu(&cmd->size,
+				       sizeof(
+				       struct mwifiex_ie_types_rssi_threshold));
 	}
 
 	if (event_bitmap & BITMASK_BCN_RSSI_HIGH) {
@@ -1378,8 +1379,9 @@ mwifiex_cmd_802_11_subsc_evt(struct mwifiex_private *priv,
 			    subsc_evt_cfg->bcn_h_rssi_cfg.evt_freq);
 
 		pos += sizeof(struct mwifiex_ie_types_rssi_threshold);
-		le16_add_cpu(&cmd->size,
-			     sizeof(struct mwifiex_ie_types_rssi_threshold));
+		le16_unaligned_add_cpu(&cmd->size,
+				       sizeof(
+				       struct mwifiex_ie_types_rssi_threshold));
 	}
 
 	return 0;
@@ -1398,7 +1400,7 @@ mwifiex_cmd_append_rpn_expression(struct mwifiex_private *priv,
 		filter = &mef_entry->filter[i];
 		if (!filter->filt_type)
 			break;
-		*(__le32 *)stack_ptr = cpu_to_le32((u32)filter->repeat);
+		put_unaligned_le32((u32)filter->repeat, stack_ptr);
 		stack_ptr += 4;
 		*stack_ptr = TYPE_DNUM;
 		stack_ptr += 1;
@@ -1410,8 +1412,7 @@ mwifiex_cmd_append_rpn_expression(struct mwifiex_private *priv,
 		stack_ptr += 1;
 		*stack_ptr = TYPE_BYTESEQ;
 		stack_ptr += 1;
-
-		*(__le32 *)stack_ptr = cpu_to_le32((u32)filter->offset);
+		put_unaligned_le32((u32)filter->offset, stack_ptr);
 		stack_ptr += 4;
 		*stack_ptr = TYPE_DNUM;
 		stack_ptr += 1;
@@ -1683,14 +1684,15 @@ mwifiex_cmd_coalesce_cfg(struct mwifiex_private *priv,
 					       sizeof(u8) + sizeof(u8));
 
 		/* Add the rule length to the command size*/
-		le16_add_cpu(&cmd->size, le16_to_cpu(rule->header.len) +
-			     sizeof(struct mwifiex_ie_types_header));
+		le16_unaligned_add_cpu(&cmd->size,
+				       le16_to_cpu(rule->header.len) +
+				       sizeof(struct mwifiex_ie_types_header));
 
 		rule = (void *)((u8 *)rule->params + length);
 	}
 
 	/* Add sizeof action, num_of_rules to total command length */
-	le16_add_cpu(&cmd->size, sizeof(u16) + sizeof(u16));
+	le16_unaligned_add_cpu(&cmd->size, sizeof(u16) + sizeof(u16));
 
 	return 0;
 }
@@ -1708,7 +1710,7 @@ mwifiex_cmd_tdls_config(struct mwifiex_private *priv,
 	cmd->command = cpu_to_le16(HostCmd_CMD_TDLS_CONFIG);
 	cmd->size = cpu_to_le16(S_DS_GEN);
 	tdls_config->tdls_action = cpu_to_le16(cmd_action);
-	le16_add_cpu(&cmd->size, sizeof(tdls_config->tdls_action));
+	le16_unaligned_add_cpu(&cmd->size, sizeof(tdls_config->tdls_action));
 
 	switch (cmd_action) {
 	case ACT_TDLS_CS_ENABLE_CONFIG:
@@ -1735,7 +1737,7 @@ mwifiex_cmd_tdls_config(struct mwifiex_private *priv,
 		return -ENOTSUPP;
 	}
 
-	le16_add_cpu(&cmd->size, len);
+	le16_unaligned_add_cpu(&cmd->size, len);
 	return 0;
 }
 
@@ -1759,7 +1761,8 @@ mwifiex_cmd_tdls_oper(struct mwifiex_private *priv,
 
 	cmd->command = cpu_to_le16(HostCmd_CMD_TDLS_OPER);
 	cmd->size = cpu_to_le16(S_DS_GEN);
-	le16_add_cpu(&cmd->size, sizeof(struct host_cmd_ds_tdls_oper));
+	le16_unaligned_add_cpu(&cmd->size,
+			       sizeof(struct host_cmd_ds_tdls_oper));
 
 	tdls_oper->reason = 0;
 	memcpy(tdls_oper->peer_mac, oper->peer_mac, ETH_ALEN);
@@ -1783,7 +1786,7 @@ mwifiex_cmd_tdls_oper(struct mwifiex_private *priv,
 			return -ENODATA;
 		}
 
-		*(__le16 *)pos = cpu_to_le16(params->capability);
+		put_unaligned_le16(params->capability, pos);
 		config_len += sizeof(params->capability);
 
 		qos_info = params->uapsd_queues | (params->max_sp << 5);
@@ -1861,7 +1864,7 @@ mwifiex_cmd_tdls_oper(struct mwifiex_private *priv,
 		return -ENOTSUPP;
 	}
 
-	le16_add_cpu(&cmd->size, config_len);
+	le16_unaligned_add_cpu(&cmd->size, config_len);
 
 	return 0;
 }
@@ -2032,7 +2035,7 @@ int mwifiex_sta_prepare_cmd(struct mwifiex_private *priv, uint16_t cmd_no,
 	case HostCmd_CMD_VERSION_EXT:
 		cmd_ptr->command = cpu_to_le16(cmd_no);
 		cmd_ptr->params.verext.version_str_sel =
-			(u8) (*((u32 *) data_buf));
+			(u8)(get_unaligned((u32 *)data_buf));
 		memcpy(&cmd_ptr->params, data_buf,
 		       sizeof(struct host_cmd_ds_version_ext));
 		cmd_ptr->size =
@@ -2043,7 +2046,8 @@ int mwifiex_sta_prepare_cmd(struct mwifiex_private *priv, uint16_t cmd_no,
 	case HostCmd_CMD_MGMT_FRAME_REG:
 		cmd_ptr->command = cpu_to_le16(cmd_no);
 		cmd_ptr->params.reg_mask.action = cpu_to_le16(cmd_action);
-		cmd_ptr->params.reg_mask.mask = cpu_to_le32(*(u32 *)data_buf);
+		cmd_ptr->params.reg_mask.mask = cpu_to_le32(
+						get_unaligned((u32 *)data_buf));
 		cmd_ptr->size =
 			cpu_to_le16(sizeof(struct host_cmd_ds_mgmt_frame_reg) +
 				    S_DS_GEN);
@@ -2063,7 +2067,8 @@ int mwifiex_sta_prepare_cmd(struct mwifiex_private *priv, uint16_t cmd_no,
 	case HostCmd_CMD_P2P_MODE_CFG:
 		cmd_ptr->command = cpu_to_le16(cmd_no);
 		cmd_ptr->params.mode_cfg.action = cpu_to_le16(cmd_action);
-		cmd_ptr->params.mode_cfg.mode = cpu_to_le16(*(u16 *)data_buf);
+		cmd_ptr->params.mode_cfg.mode = cpu_to_le16(
+						get_unaligned((u16 *)data_buf));
 		cmd_ptr->size =
 			cpu_to_le16(sizeof(struct host_cmd_ds_p2p_mode_cfg) +
 				    S_DS_GEN);
@@ -2359,8 +2364,7 @@ int mwifiex_sta_init_cmd(struct mwifiex_private *priv, u8 first_sta, bool init)
 	if (ret)
 		return -1;
 
-	if (!disable_auto_ds &&
-	    first_sta && priv->adapter->iface_type != MWIFIEX_USB &&
+	if (!disable_auto_ds && first_sta &&
 	    priv->bss_type != MWIFIEX_BSS_TYPE_UAP) {
 		/* Enable auto deep sleep */
 		auto_ds.auto_ds = DEEP_SLEEP_ON;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index 8548027abf71..f1d1f56fc23f 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -183,7 +183,7 @@ static int mwifiex_ret_802_11_snmp_mib(struct mwifiex_private *priv,
 		    "query_type = %#x, buf size = %#x\n",
 		    oid, query_type, le16_to_cpu(smib->buf_size));
 	if (query_type == HostCmd_ACT_GEN_GET) {
-		ul_temp = le16_to_cpu(*((__le16 *) (smib->value)));
+		ul_temp = get_unaligned_le16(smib->value);
 		if (data_buf)
 			*data_buf = ul_temp;
 		switch (oid) {
@@ -741,7 +741,7 @@ mwifiex_ret_p2p_mode_cfg(struct mwifiex_private *priv,
 	struct host_cmd_ds_p2p_mode_cfg *mode_cfg = &resp->params.mode_cfg;
 
 	if (data_buf)
-		*((u16 *)data_buf) = le16_to_cpu(mode_cfg->mode);
+		put_unaligned_le16(le16_to_cpu(mode_cfg->mode), data_buf);
 
 	return 0;
 }
@@ -1201,7 +1201,7 @@ int mwifiex_process_sta_cmdresp(struct mwifiex_private *priv, u16 cmdresp_no,
 		break;
 	case HostCmd_CMD_802_11_BG_SCAN_QUERY:
 		ret = mwifiex_ret_802_11_scan(priv, resp);
-		cfg80211_sched_scan_results(priv->wdev.wiphy);
+		cfg80211_sched_scan_results(priv->wdev.wiphy, 0);
 		mwifiex_dbg(adapter, CMD,
 			    "info: CMD_RESP: BG_SCAN result is ready!\n");
 		break;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index d63d163eb1ec..839df8a9634e 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -670,7 +670,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		adapter->dbg.num_event_deauth++;
 		if (priv->media_connected) {
 			reason_code =
-				le16_to_cpu(*(__le16 *)adapter->event_body);
+				get_unaligned_le16(adapter->event_body);
 			mwifiex_reset_connect_state(priv, reason_code, true);
 		}
 		break;
@@ -685,7 +685,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		adapter->dbg.num_event_disassoc++;
 		if (priv->media_connected) {
 			reason_code =
-				le16_to_cpu(*(__le16 *)adapter->event_body);
+				get_unaligned_le16(adapter->event_body);
 			mwifiex_reset_connect_state(priv, reason_code, true);
 		}
 		break;
@@ -695,7 +695,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		adapter->dbg.num_event_link_lost++;
 		if (priv->media_connected) {
 			reason_code =
-				le16_to_cpu(*(__le16 *)adapter->event_body);
+				get_unaligned_le16(adapter->event_body);
 			mwifiex_reset_connect_state(priv, reason_code, true);
 		}
 		break;
@@ -793,7 +793,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 
 	case EVENT_BG_SCAN_STOPPED:
 		dev_dbg(adapter->dev, "event: BGS_STOPPED\n");
-		cfg80211_sched_scan_stopped(priv->wdev.wiphy);
+		cfg80211_sched_scan_stopped(priv->wdev.wiphy, 0);
 		if (priv->sched_scanning)
 			priv->sched_scanning = false;
 		break;
@@ -923,7 +923,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 					      adapter->event_body);
 		break;
 	case EVENT_AMSDU_AGGR_CTRL:
-		ctrl = le16_to_cpu(*(__le16 *)adapter->event_body);
+		ctrl = get_unaligned_le16(adapter->event_body);
 		mwifiex_dbg(adapter, EVENT,
 			    "event: AMSDU_AGGR_CTRL %d\n", ctrl);
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 1532ac9cee0b..42997e05d90f 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -560,7 +560,7 @@ int mwifiex_enable_hs(struct mwifiex_adapter *adapter)
 #endif
 			mwifiex_dbg(adapter, CMD, "aborting bgscan!\n");
 			mwifiex_stop_bg_scan(priv);
-			cfg80211_sched_scan_stopped(priv->wdev.wiphy);
+			cfg80211_sched_scan_stopped(priv->wdev.wiphy, 0);
 #ifdef CONFIG_PM
 		}
 #endif
diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c
index df9704de0715..7d0d3ff3dd4c 100644
--- a/drivers/net/wireless/marvell/mwifiex/tdls.c
+++ b/drivers/net/wireless/marvell/mwifiex/tdls.c
@@ -349,7 +349,7 @@ static int mwifiex_tdls_add_vht_oper(struct mwifiex_private *priv,
 		chan_bw = IEEE80211_VHT_CHANWIDTH_USE_HT;
 		break;
 	}
-	vht_oper->center_freq_seg1_idx =
+	vht_oper->center_freq_seg0_idx =
 			mwifiex_get_center_freq_index(priv, BAND_AAC,
 						      bss_desc->channel,
 						      chan_bw);
@@ -431,6 +431,41 @@ mwifiex_add_wmm_info_ie(struct mwifiex_private *priv, struct sk_buff *skb,
 	*buf++ = qosinfo; /* U-APSD no in use */
 }
 
+static void mwifiex_tdls_add_bss_co_2040(struct sk_buff *skb)
+{
+	struct ieee_types_bss_co_2040 *bssco;
+
+	bssco = (void *)skb_put(skb, sizeof(struct ieee_types_bss_co_2040));
+	bssco->ieee_hdr.element_id = WLAN_EID_BSS_COEX_2040;
+	bssco->ieee_hdr.len = sizeof(struct ieee_types_bss_co_2040) -
+			      sizeof(struct ieee_types_header);
+	bssco->bss_2040co = 0x01;
+}
+
+static void mwifiex_tdls_add_supported_chan(struct sk_buff *skb)
+{
+	struct ieee_types_generic *supp_chan;
+	u8 chan_supp[] = {1, 11};
+
+	supp_chan = (void *)skb_put(skb, (sizeof(struct ieee_types_header) +
+					  sizeof(chan_supp)));
+	supp_chan->ieee_hdr.element_id = WLAN_EID_SUPPORTED_CHANNELS;
+	supp_chan->ieee_hdr.len = sizeof(chan_supp);
+	memcpy(supp_chan->data, chan_supp, sizeof(chan_supp));
+}
+
+static void mwifiex_tdls_add_oper_class(struct sk_buff *skb)
+{
+	struct ieee_types_generic *reg_class;
+	u8 rc_list[] = {1,
+		1, 2, 3, 4, 12, 22, 23, 24, 25, 27, 28, 29, 30, 32, 33};
+	reg_class = (void *)skb_put(skb, (sizeof(struct ieee_types_header) +
+					  sizeof(rc_list)));
+	reg_class->ieee_hdr.element_id = WLAN_EID_SUPPORTED_REGULATORY_CLASSES;
+	reg_class->ieee_hdr.len = sizeof(rc_list);
+	memcpy(reg_class->data, rc_list, sizeof(rc_list));
+}
+
 static int mwifiex_prep_tdls_encap_data(struct mwifiex_private *priv,
 					const u8 *peer, u8 action_code,
 					u8 dialog_token,
@@ -484,7 +519,9 @@ static int mwifiex_prep_tdls_encap_data(struct mwifiex_private *priv,
 		}
 
 		mwifiex_tdls_add_ext_capab(priv, skb);
-		mwifiex_tdls_add_qos_capab(skb);
+		mwifiex_tdls_add_bss_co_2040(skb);
+		mwifiex_tdls_add_supported_chan(skb);
+		mwifiex_tdls_add_oper_class(skb);
 		mwifiex_add_wmm_info_ie(priv, skb, 0);
 		break;
 
@@ -522,7 +559,9 @@ static int mwifiex_prep_tdls_encap_data(struct mwifiex_private *priv,
 		}
 
 		mwifiex_tdls_add_ext_capab(priv, skb);
-		mwifiex_tdls_add_qos_capab(skb);
+		mwifiex_tdls_add_bss_co_2040(skb);
+		mwifiex_tdls_add_supported_chan(skb);
+		mwifiex_tdls_add_oper_class(skb);
 		mwifiex_add_wmm_info_ie(priv, skb, 0);
 		break;
 
@@ -612,6 +651,9 @@ int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv, const u8 *peer,
 		  sizeof(struct ieee_types_bss_co_2040) +
 		  sizeof(struct ieee80211_ht_operation) +
 		  sizeof(struct ieee80211_tdls_lnkie) +
+		  (2 * (sizeof(struct ieee_types_header))) +
+		   MWIFIEX_SUPPORTED_CHANNELS +
+		   MWIFIEX_OPERATING_CLASSES +
 		  sizeof(struct ieee80211_wmm_param_ie) +
 		  extra_ies_len;
 
@@ -760,7 +802,10 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv,
 		}
 
 		mwifiex_tdls_add_ext_capab(priv, skb);
+		mwifiex_tdls_add_bss_co_2040(skb);
+		mwifiex_tdls_add_supported_chan(skb);
 		mwifiex_tdls_add_qos_capab(skb);
+		mwifiex_tdls_add_oper_class(skb);
 		break;
 	default:
 		mwifiex_dbg(priv->adapter, ERROR, "Unknown TDLS action frame type\n");
@@ -857,7 +902,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 	struct mwifiex_sta_node *sta_ptr;
 	u8 *peer, *pos, *end;
 	u8 i, action, basic;
-	__le16 cap = 0;
+	u16 cap = 0;
 	int ie_len = 0;
 
 	if (len < (sizeof(struct ethhdr) + 3))
@@ -879,7 +924,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 
 		pos = buf + sizeof(struct ethhdr) + 4;
 		/* payload 1+ category 1 + action 1 + dialog 1 */
-		cap = cpu_to_le16(*(u16 *)pos);
+		cap = get_unaligned_le16(pos);
 		ie_len = len - sizeof(struct ethhdr) - TDLS_REQ_FIX_LEN;
 		pos += 2;
 		break;
@@ -889,7 +934,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 			return;
 		/* payload 1+ category 1 + action 1 + dialog 1 + status code 2*/
 		pos = buf + sizeof(struct ethhdr) + 6;
-		cap = cpu_to_le16(*(u16 *)pos);
+		cap = get_unaligned_le16(pos);
 		ie_len = len - sizeof(struct ethhdr) - TDLS_RESP_FIX_LEN;
 		pos += 2;
 		break;
@@ -909,7 +954,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 	if (!sta_ptr)
 		return;
 
-	sta_ptr->tdls_cap.capab = cap;
+	sta_ptr->tdls_cap.capab = cpu_to_le16(cap);
 
 	for (end = pos + ie_len; pos + 1 < end; pos += 2 + pos[1]) {
 		if (pos + 2 + pos[1] > end)
@@ -969,7 +1014,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 		case WLAN_EID_AID:
 			if (priv->adapter->is_hw_11ac_capable)
 				sta_ptr->tdls_cap.aid =
-					      le16_to_cpu(*(__le16 *)(pos + 2));
+					get_unaligned_le16((pos + 2));
 		default:
 			break;
 		}
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_event.c b/drivers/net/wireless/marvell/mwifiex/uap_event.c
index d24eca34ac11..e10b2a52e78f 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_event.c
@@ -202,7 +202,7 @@ int mwifiex_process_uap_event(struct mwifiex_private *priv)
 			    "AP EVENT: event id: %#x\n", eventcause);
 		break;
 	case EVENT_AMSDU_AGGR_CTRL:
-		ctrl = le16_to_cpu(*(__le16 *)adapter->event_body);
+		ctrl = get_unaligned_le16(adapter->event_body);
 		mwifiex_dbg(adapter, EVENT,
 			    "event: AMSDU_AGGR_CTRL %d\n", ctrl);
 
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 9cf3334adf4d..2f7705c50161 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -306,9 +306,17 @@ static int mwifiex_usb_submit_rx_urb(struct urb_context *ctx, int size)
 		}
 	}
 
-	usb_fill_bulk_urb(ctx->urb, card->udev,
-			  usb_rcvbulkpipe(card->udev, ctx->ep), ctx->skb->data,
-			  size, mwifiex_usb_rx_complete, (void *)ctx);
+	if (card->rx_cmd_ep == ctx->ep &&
+	    card->rx_cmd_ep_type == USB_ENDPOINT_XFER_INT)
+		usb_fill_int_urb(ctx->urb, card->udev,
+				 usb_rcvintpipe(card->udev, ctx->ep),
+				 ctx->skb->data, size, mwifiex_usb_rx_complete,
+				 (void *)ctx, card->rx_cmd_interval);
+	else
+		usb_fill_bulk_urb(ctx->urb, card->udev,
+				  usb_rcvbulkpipe(card->udev, ctx->ep),
+				  ctx->skb->data, size, mwifiex_usb_rx_complete,
+				  (void *)ctx);
 
 	if (card->rx_cmd_ep == ctx->ep)
 		atomic_inc(&card->rx_cmd_urb_pending);
@@ -424,10 +432,13 @@ static int mwifiex_usb_probe(struct usb_interface *intf,
 		epd = &iface_desc->endpoint[i].desc;
 		if (usb_endpoint_dir_in(epd) &&
 		    usb_endpoint_num(epd) == MWIFIEX_USB_EP_CMD_EVENT &&
-		    usb_endpoint_xfer_bulk(epd)) {
-			pr_debug("info: bulk IN: max pkt size: %d, addr: %d\n",
+		    (usb_endpoint_xfer_bulk(epd) ||
+		     usb_endpoint_xfer_int(epd))) {
+			card->rx_cmd_ep_type = usb_endpoint_type(epd);
+			card->rx_cmd_interval = epd->bInterval;
+			pr_debug("info: Rx CMD/EVT:: max pkt size: %d, addr: %d, ep_type: %d\n",
 				 le16_to_cpu(epd->wMaxPacketSize),
-				 epd->bEndpointAddress);
+				 epd->bEndpointAddress, card->rx_cmd_ep_type);
 			card->rx_cmd_ep = usb_endpoint_num(epd);
 			atomic_set(&card->rx_cmd_urb_pending, 0);
 		}
@@ -461,10 +472,16 @@ static int mwifiex_usb_probe(struct usb_interface *intf,
 		}
 		if (usb_endpoint_dir_out(epd) &&
 		    usb_endpoint_num(epd) == MWIFIEX_USB_EP_CMD_EVENT &&
-		    usb_endpoint_xfer_bulk(epd)) {
+		    (usb_endpoint_xfer_bulk(epd) ||
+		     usb_endpoint_xfer_int(epd))) {
+			card->tx_cmd_ep_type = usb_endpoint_type(epd);
+			card->tx_cmd_interval = epd->bInterval;
 			pr_debug("info: bulk OUT: max pkt size: %d, addr: %d\n",
 				 le16_to_cpu(epd->wMaxPacketSize),
 				 epd->bEndpointAddress);
+			pr_debug("info: Tx CMD:: max pkt size: %d, addr: %d, ep_type: %d\n",
+				 le16_to_cpu(epd->wMaxPacketSize),
+				 epd->bEndpointAddress, card->tx_cmd_ep_type);
 			card->tx_cmd_ep = usb_endpoint_num(epd);
 			atomic_set(&card->tx_cmd_urb_pending, 0);
 			card->bulk_out_maxpktsize =
@@ -884,9 +901,17 @@ static int mwifiex_usb_host_to_card(struct mwifiex_adapter *adapter, u8 ep,
 	context->skb = skb;
 	tx_urb = context->urb;
 
-	usb_fill_bulk_urb(tx_urb, card->udev, usb_sndbulkpipe(card->udev, ep),
-			  data, skb->len, mwifiex_usb_tx_complete,
-			  (void *)context);
+	if (ep == card->tx_cmd_ep &&
+	    card->tx_cmd_ep_type == USB_ENDPOINT_XFER_INT)
+		usb_fill_int_urb(tx_urb, card->udev,
+				 usb_sndintpipe(card->udev, ep), data,
+				 skb->len, mwifiex_usb_tx_complete,
+				 (void *)context, card->tx_cmd_interval);
+	else
+		usb_fill_bulk_urb(tx_urb, card->udev,
+				  usb_sndbulkpipe(card->udev, ep), data,
+				  skb->len, mwifiex_usb_tx_complete,
+				  (void *)context);
 
 	tx_urb->transfer_flags |= URB_ZERO_PACKET;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.h b/drivers/net/wireless/marvell/mwifiex/usb.h
index e5f204ea018b..e36bd63172ff 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.h
+++ b/drivers/net/wireless/marvell/mwifiex/usb.h
@@ -90,6 +90,10 @@ struct usb_card_rec {
 	struct urb_context tx_cmd;
 	u8 mc_resync_flag;
 	struct usb_tx_data_port port[MWIFIEX_TX_DATA_PORT];
+	int rx_cmd_ep_type;
+	u8 rx_cmd_interval;
+	int tx_cmd_ep_type;
+	u8 tx_cmd_interval;
 };
 
 struct fw_header {
@@ -102,12 +106,12 @@ struct fw_header {
 struct fw_sync_header {
 	__le32 cmd;
 	__le32 seq_num;
-};
+} __packed;
 
 struct fw_data {
 	struct fw_header fw_hdr;
 	__le32 seq_num;
 	u8 data[1];
-};
+} __packed;
 
 #endif /*_MWIFIEX_USB_H */
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index b1ab8da121dd..0cd68ffc2c74 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -274,13 +274,13 @@ int mwifiex_debug_info_to_buffer(struct mwifiex_private *priv, char *buf,
 				val = *((u8 *)addr);
 				break;
 			case 2:
-				val = *((u16 *)addr);
+				val = get_unaligned((u16 *)addr);
 				break;
 			case 4:
-				val = *((u32 *)addr);
+				val = get_unaligned((u32 *)addr);
 				break;
 			case 8:
-				val = *((long long *)addr);
+				val = get_unaligned((long long *)addr);
 				break;
 			default:
 				val = -1;
diff --git a/drivers/net/wireless/marvell/mwifiex/util.h b/drivers/net/wireless/marvell/mwifiex/util.h
index b541d66c01eb..c386992abcdb 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.h
+++ b/drivers/net/wireless/marvell/mwifiex/util.h
@@ -93,4 +93,9 @@ static inline dma_addr_t MWIFIEX_SKB_DMA_ADDR(struct sk_buff *skb)
 int mwifiex_debug_info_to_buffer(struct mwifiex_private *priv, char *buf,
 				 struct mwifiex_debug_info *info);
 
+static inline void le16_unaligned_add_cpu(__le16 *var, u16 val)
+{
+	put_unaligned_le16(get_unaligned_le16(var) + val, var);
+}
+
 #endif /* !_MWIFIEX_UTIL_H_ */
diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c
index b1b400b59d86..e813b2ca740c 100644
--- a/drivers/net/wireless/marvell/mwl8k.c
+++ b/drivers/net/wireless/marvell/mwl8k.c
@@ -994,9 +994,9 @@ mwl8k_rxd_ap_process(void *_rxd, struct ieee80211_rx_status *status,
 	*noise = -rxd->noise_floor;
 
 	if (rxd->rate & MWL8K_AP_RATE_INFO_MCS_FORMAT) {
-		status->flag |= RX_FLAG_HT;
+		status->encoding = RX_ENC_HT;
 		if (rxd->rate & MWL8K_AP_RATE_INFO_40MHZ)
-			status->flag |= RX_FLAG_40MHZ;
+			status->bw = RATE_INFO_BW_40;
 		status->rate_idx = MWL8K_AP_RATE_INFO_RATEID(rxd->rate);
 	} else {
 		int i;
@@ -1011,7 +1011,7 @@ mwl8k_rxd_ap_process(void *_rxd, struct ieee80211_rx_status *status,
 
 	if (rxd->channel > 14) {
 		status->band = NL80211_BAND_5GHZ;
-		if (!(status->flag & RX_FLAG_HT))
+		if (!(status->encoding == RX_ENC_HT))
 			status->rate_idx -= 5;
 	} else {
 		status->band = NL80211_BAND_2GHZ;
@@ -1109,17 +1109,17 @@ mwl8k_rxd_sta_process(void *_rxd, struct ieee80211_rx_status *status,
 	status->rate_idx = MWL8K_STA_RATE_INFO_RATEID(rate_info);
 
 	if (rate_info & MWL8K_STA_RATE_INFO_SHORTPRE)
-		status->flag |= RX_FLAG_SHORTPRE;
+		status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 	if (rate_info & MWL8K_STA_RATE_INFO_40MHZ)
-		status->flag |= RX_FLAG_40MHZ;
+		status->bw = RATE_INFO_BW_40;
 	if (rate_info & MWL8K_STA_RATE_INFO_SHORTGI)
-		status->flag |= RX_FLAG_SHORT_GI;
+		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 	if (rate_info & MWL8K_STA_RATE_INFO_MCS_FORMAT)
-		status->flag |= RX_FLAG_HT;
+		status->encoding = RX_ENC_HT;
 
 	if (rxd->channel > 14) {
 		status->band = NL80211_BAND_5GHZ;
-		if (!(status->flag & RX_FLAG_HT))
+		if (!(status->encoding == RX_ENC_HT))
 			status->rate_idx -= 5;
 	} else {
 		status->band = NL80211_BAND_2GHZ;
@@ -6144,6 +6144,8 @@ static int mwl8k_firmware_load_success(struct mwl8k_priv *priv)
 	if (priv->sta_macids_supported || priv->device_info->fw_image_sta)
 		hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_STATION);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	rc = ieee80211_register_hw(hw);
 	if (rc) {
 		wiphy_err(hw->wiphy, "Cannot register device\n");
diff --git a/drivers/net/wireless/mediatek/mt7601u/init.c b/drivers/net/wireless/mediatek/mt7601u/init.c
index a6e901766226..d3b611aaf061 100644
--- a/drivers/net/wireless/mediatek/mt7601u/init.c
+++ b/drivers/net/wireless/mediatek/mt7601u/init.c
@@ -615,6 +615,8 @@ int mt7601u_register_device(struct mt7601u_dev *dev)
 	wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
 	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
 
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = mt76_init_sband_2g(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/mediatek/mt7601u/mac.c b/drivers/net/wireless/mediatek/mt7601u/mac.c
index 3c576392ed89..d6dc59bb00df 100644
--- a/drivers/net/wireless/mediatek/mt7601u/mac.c
+++ b/drivers/net/wireless/mediatek/mt7601u/mac.c
@@ -401,7 +401,7 @@ mt76_mac_process_rate(struct ieee80211_rx_status *status, u16 rate)
 	case MT_PHY_TYPE_CCK:
 		if (idx >= 8) {
 			idx -= 8;
-			status->flag |= RX_FLAG_SHORTPRE;
+			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 		}
 
 		if (WARN_ON(idx >= 4))
@@ -410,10 +410,10 @@ mt76_mac_process_rate(struct ieee80211_rx_status *status, u16 rate)
 		status->rate_idx = idx;
 		return;
 	case MT_PHY_TYPE_HT_GF:
-		status->flag |= RX_FLAG_HT_GF;
+		status->enc_flags |= RX_ENC_FLAG_HT_GF;
 		/* fall through */
 	case MT_PHY_TYPE_HT:
-		status->flag |= RX_FLAG_HT;
+		status->encoding = RX_ENC_HT;
 		status->rate_idx = idx;
 		break;
 	default:
@@ -422,13 +422,13 @@ mt76_mac_process_rate(struct ieee80211_rx_status *status, u16 rate)
 	}
 
 	if (rate & MT_RXWI_RATE_SGI)
-		status->flag |= RX_FLAG_SHORT_GI;
+		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (rate & MT_RXWI_RATE_STBC)
-		status->flag |= 1 << RX_FLAG_STBC_SHIFT;
+		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
 
 	if (rate & MT_RXWI_RATE_BW)
-		status->flag |= RX_FLAG_40MHZ;
+		status->bw = RATE_INFO_BW_40;
 }
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt7601u/mcu.c b/drivers/net/wireless/mediatek/mt7601u/mcu.c
index dbdfb3f5c507..a9f5f398b2f8 100644
--- a/drivers/net/wireless/mediatek/mt7601u/mcu.c
+++ b/drivers/net/wireless/mediatek/mt7601u/mcu.c
@@ -66,8 +66,10 @@ mt7601u_mcu_msg_alloc(struct mt7601u_dev *dev, const void *data, int len)
 	WARN_ON(len % 4); /* if length is not divisible by 4 we need to pad */
 
 	skb = alloc_skb(len + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
-	skb_reserve(skb, MT_DMA_HDR_LEN);
-	memcpy(skb_put(skb, len), data, len);
+	if (skb) {
+		skb_reserve(skb, MT_DMA_HDR_LEN);
+		memcpy(skb_put(skb, len), data, len);
+	}
 
 	return skb;
 }
@@ -170,6 +172,8 @@ static int mt7601u_mcu_function_select(struct mt7601u_dev *dev,
 	};
 
 	skb = mt7601u_mcu_msg_alloc(dev, &msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
 	return mt7601u_mcu_msg_send(dev, skb, CMD_FUN_SET_OP, func == 5);
 }
 
@@ -205,6 +209,8 @@ mt7601u_mcu_calibrate(struct mt7601u_dev *dev, enum mcu_calibrate cal, u32 val)
 	};
 
 	skb = mt7601u_mcu_msg_alloc(dev, &msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
 	return mt7601u_mcu_msg_send(dev, skb, CMD_CALIBRATION_OP, true);
 }
 
diff --git a/drivers/net/wireless/ralink/rt2x00/Kconfig b/drivers/net/wireless/ralink/rt2x00/Kconfig
index de62f5dcb62f..a1d1cfe214d2 100644
--- a/drivers/net/wireless/ralink/rt2x00/Kconfig
+++ b/drivers/net/wireless/ralink/rt2x00/Kconfig
@@ -201,7 +201,7 @@ endif
 
 config RT2800SOC
 	tristate "Ralink WiSoC support"
-	depends on SOC_RT288X || SOC_RT305X
+	depends on SOC_RT288X || SOC_RT305X || SOC_MT7620
 	select RT2X00_LIB_SOC
 	select RT2X00_LIB_MMIO
 	select RT2X00_LIB_CRYPTO
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800.h b/drivers/net/wireless/ralink/rt2x00/rt2800.h
index 256496bfbafb..6a8c93fb6a43 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800.h
@@ -79,6 +79,7 @@
 #define RF5372				0x5372
 #define RF5390				0x5390
 #define RF5392				0x5392
+#define RF7620				0x7620
 
 /*
  * Chipset revisions.
@@ -639,6 +640,24 @@
 #define RF_CSR_CFG_BUSY			FIELD32(0x00020000)
 
 /*
+ * MT7620 RF registers (reversed order)
+ */
+#define RF_CSR_CFG_DATA_MT7620		FIELD32(0x0000ff00)
+#define RF_CSR_CFG_REGNUM_MT7620	FIELD32(0x03ff0000)
+#define RF_CSR_CFG_WRITE_MT7620		FIELD32(0x00000010)
+#define RF_CSR_CFG_BUSY_MT7620		FIELD32(0x00000001)
+
+/* undocumented registers for calibration of new MAC */
+#define RF_CONTROL0			0x0518
+#define RF_BYPASS0			0x051c
+#define RF_CONTROL1			0x0520
+#define RF_BYPASS1			0x0524
+#define RF_CONTROL2			0x0528
+#define RF_BYPASS2			0x052c
+#define RF_CONTROL3			0x0530
+#define RF_BYPASS3			0x0534
+
+/*
  * EFUSE_CSR: RT30x0 EEPROM
  */
 #define EFUSE_CTRL			0x0580
@@ -1022,6 +1041,16 @@
 #define AUTOWAKEUP_CFG_AUTOWAKE		FIELD32(0x00008000)
 
 /*
+ * MIMO_PS_CFG: MIMO Power-save Configuration
+ */
+#define MIMO_PS_CFG			0x1210
+#define MIMO_PS_CFG_MMPS_BB_EN		FIELD32(0x00000001)
+#define MIMO_PS_CFG_MMPS_RX_ANT_NUM	FIELD32(0x00000006)
+#define MIMO_PS_CFG_MMPS_RF_EN		FIELD32(0x00000008)
+#define MIMO_PS_CFG_RX_STBY_POL		FIELD32(0x00000010)
+#define MIMO_PS_CFG_RX_RX_STBY0		FIELD32(0x00000020)
+
+/*
  * EDCA_AC0_CFG:
  */
 #define EDCA_AC0_CFG			0x1300
@@ -1095,6 +1124,12 @@
 #define TX_PWR_CFG_0_OFDM6_CH1		FIELD32(0x00f00000)
 #define TX_PWR_CFG_0_OFDM12_CH0		FIELD32(0x0f000000)
 #define TX_PWR_CFG_0_OFDM12_CH1		FIELD32(0xf0000000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_0B_1MBS_2MBS		FIELD32(0x000000ff)
+#define TX_PWR_CFG_0B_5MBS_11MBS		FIELD32(0x0000ff00)
+#define TX_PWR_CFG_0B_6MBS_9MBS		FIELD32(0x00ff0000)
+#define TX_PWR_CFG_0B_12MBS_18MBS	FIELD32(0xff000000)
+
 
 /*
  * TX_PWR_CFG_1:
@@ -1117,6 +1152,11 @@
 #define TX_PWR_CFG_1_MCS0_CH1		FIELD32(0x00f00000)
 #define TX_PWR_CFG_1_MCS2_CH0		FIELD32(0x0f000000)
 #define TX_PWR_CFG_1_MCS2_CH1		FIELD32(0xf0000000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_1B_24MBS_36MBS	FIELD32(0x000000ff)
+#define TX_PWR_CFG_1B_48MBS		FIELD32(0x0000ff00)
+#define TX_PWR_CFG_1B_MCS0_MCS1		FIELD32(0x00ff0000)
+#define TX_PWR_CFG_1B_MCS2_MCS3		FIELD32(0xff000000)
 
 /*
  * TX_PWR_CFG_2:
@@ -1139,6 +1179,11 @@
 #define TX_PWR_CFG_2_MCS8_CH1		FIELD32(0x00f00000)
 #define TX_PWR_CFG_2_MCS10_CH0		FIELD32(0x0f000000)
 #define TX_PWR_CFG_2_MCS10_CH1		FIELD32(0xf0000000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_2B_MCS4_MCS5		FIELD32(0x000000ff)
+#define TX_PWR_CFG_2B_MCS6_MCS7		FIELD32(0x0000ff00)
+#define TX_PWR_CFG_2B_MCS8_MCS9		FIELD32(0x00ff0000)
+#define TX_PWR_CFG_2B_MCS10_MCS11	FIELD32(0xff000000)
 
 /*
  * TX_PWR_CFG_3:
@@ -1161,6 +1206,11 @@
 #define TX_PWR_CFG_3_STBC0_CH1		FIELD32(0x00f00000)
 #define TX_PWR_CFG_3_STBC2_CH0		FIELD32(0x0f000000)
 #define TX_PWR_CFG_3_STBC2_CH1		FIELD32(0xf0000000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_3B_MCS12_MCS13	FIELD32(0x000000ff)
+#define TX_PWR_CFG_3B_MCS14		FIELD32(0x0000ff00)
+#define TX_PWR_CFG_3B_STBC_MCS0_MCS1	FIELD32(0x00ff0000)
+#define TX_PWR_CFG_3B_STBC_MCS2_MSC3	FIELD32(0xff000000)
 
 /*
  * TX_PWR_CFG_4:
@@ -1171,10 +1221,13 @@
 #define TX_PWR_CFG_4_UKNOWN7		FIELD32(0x00000f00)
 #define TX_PWR_CFG_4_UKNOWN8		FIELD32(0x0000f000)
 /* bits for 3T devices */
-#define TX_PWR_CFG_3_STBC4_CH0		FIELD32(0x0000000f)
-#define TX_PWR_CFG_3_STBC4_CH1		FIELD32(0x000000f0)
-#define TX_PWR_CFG_3_STBC6_CH0		FIELD32(0x00000f00)
-#define TX_PWR_CFG_3_STBC6_CH1		FIELD32(0x0000f000)
+#define TX_PWR_CFG_4_STBC4_CH0		FIELD32(0x0000000f)
+#define TX_PWR_CFG_4_STBC4_CH1		FIELD32(0x000000f0)
+#define TX_PWR_CFG_4_STBC6_CH0		FIELD32(0x00000f00)
+#define TX_PWR_CFG_4_STBC6_CH1		FIELD32(0x0000f000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_4B_STBC_MCS4_MCS5	FIELD32(0x000000ff)
+#define TX_PWR_CFG_4B_STBC_MCS6		FIELD32(0x0000ff00)
 
 /*
  * TX_PIN_CFG:
@@ -1201,6 +1254,8 @@
 #define TX_PIN_CFG_RFTR_POL		FIELD32(0x00020000)
 #define TX_PIN_CFG_TRSW_EN		FIELD32(0x00040000)
 #define TX_PIN_CFG_TRSW_POL		FIELD32(0x00080000)
+#define TX_PIN_CFG_RFRX_EN		FIELD32(0x00100000)
+#define TX_PIN_CFG_RFRX_POL		FIELD32(0x00200000)
 #define TX_PIN_CFG_PA_PE_A2_EN		FIELD32(0x01000000)
 #define TX_PIN_CFG_PA_PE_G2_EN		FIELD32(0x02000000)
 #define TX_PIN_CFG_PA_PE_A2_POL		FIELD32(0x04000000)
@@ -1547,6 +1602,95 @@
 #define TX_PWR_CFG_4_EXT_STBC4_CH2	FIELD32(0x0000000f)
 #define TX_PWR_CFG_4_EXT_STBC6_CH2	FIELD32(0x00000f00)
 
+/* TXn_RF_GAIN_CORRECT: RF Gain Correction for each RF_ALC[3:2]
+ * Unit: 0.1 dB, Range: -3.2 dB to 3.1 dB
+ */
+#define TX0_RF_GAIN_CORRECT		0x13a0
+#define TX0_RF_GAIN_CORRECT_GAIN_CORR_0	FIELD32(0x0000003f)
+#define TX0_RF_GAIN_CORRECT_GAIN_CORR_1	FIELD32(0x00003f00)
+#define TX0_RF_GAIN_CORRECT_GAIN_CORR_2	FIELD32(0x003f0000)
+#define TX0_RF_GAIN_CORRECT_GAIN_CORR_3	FIELD32(0x3f000000)
+
+#define TX1_RF_GAIN_CORRECT		0x13a4
+#define TX1_RF_GAIN_CORRECT_GAIN_CORR_0	FIELD32(0x0000003f)
+#define TX1_RF_GAIN_CORRECT_GAIN_CORR_1	FIELD32(0x00003f00)
+#define TX1_RF_GAIN_CORRECT_GAIN_CORR_2	FIELD32(0x003f0000)
+#define TX1_RF_GAIN_CORRECT_GAIN_CORR_3	FIELD32(0x3f000000)
+
+/* TXn_RF_GAIN_ATTEN: TXn RF Gain Attenuation Level
+ * Format: 7-bit, signed value
+ * Unit: 0.5 dB, Range: -20 dB to -5 dB
+ */
+#define TX0_RF_GAIN_ATTEN		0x13a8
+#define TX0_RF_GAIN_ATTEN_LEVEL_0	FIELD32(0x0000007f)
+#define TX0_RF_GAIN_ATTEN_LEVEL_1	FIELD32(0x00007f00)
+#define TX0_RF_GAIN_ATTEN_LEVEL_2	FIELD32(0x007f0000)
+#define TX0_RF_GAIN_ATTEN_LEVEL_3	FIELD32(0x7f000000)
+#define TX1_RF_GAIN_ATTEN		0x13ac
+#define TX1_RF_GAIN_ATTEN_LEVEL_0	FIELD32(0x0000007f)
+#define TX1_RF_GAIN_ATTEN_LEVEL_1	FIELD32(0x00007f00)
+#define TX1_RF_GAIN_ATTEN_LEVEL_2	FIELD32(0x007f0000)
+#define TX1_RF_GAIN_ATTEN_LEVEL_3	FIELD32(0x7f000000)
+
+/* TX_ALC_CFG_0: TX Automatic Level Control Configuration 0
+ * TX_ALC_LIMIT_n: TXn upper limit
+ * TX_ALC_CH_INIT_n: TXn channel initial transmission gain
+ * Unit: 0.5 dB, Range: 0 to 23.5 dB
+ */
+#define TX_ALC_CFG_0			0x13b0
+#define TX_ALC_CFG_0_CH_INIT_0		FIELD32(0x0000003f)
+#define TX_ALC_CFG_0_CH_INIT_1		FIELD32(0x00003f00)
+#define TX_ALC_CFG_0_LIMIT_0		FIELD32(0x003f0000)
+#define TX_ALC_CFG_0_LIMIT_1		FIELD32(0x3f000000)
+
+/* TX_ALC_CFG_1: TX Automatic Level Control Configuration 1
+ * TX_TEMP_COMP:      TX Power Temperature Compensation
+ *                    Unit: 0.5 dB, Range: -10 dB to 10 dB
+ * TXn_GAIN_FINE:     TXn Gain Fine Adjustment
+ *                    Unit: 0.1 dB, Range: -0.8 dB to 0.7 dB
+ * RF_TOS_DLY:        Sets the RF_TOS_EN assertion delay after
+ *                    deassertion of PA_PE.
+ *                    Unit: 0.25 usec
+ * TXn_RF_GAIN_ATTEN: TXn RF gain attentuation selector
+ * RF_TOS_TIMEOUT:    time-out value for RF_TOS_ENABLE
+ *                    deassertion if RF_TOS_DONE is missing.
+ *                    Unit: 0.25 usec
+ * RF_TOS_ENABLE:     TX offset calibration enable
+ * ROS_BUSY_EN:       RX offset calibration busy enable
+ */
+#define TX_ALC_CFG_1			0x13b4
+#define TX_ALC_CFG_1_TX_TEMP_COMP	FIELD32(0x0000003f)
+#define TX_ALC_CFG_1_TX0_GAIN_FINE	FIELD32(0x00000f00)
+#define TX_ALC_CFG_1_TX1_GAIN_FINE	FIELD32(0x0000f000)
+#define TX_ALC_CFG_1_RF_TOS_DLY		FIELD32(0x00070000)
+#define TX_ALC_CFG_1_TX0_RF_GAIN_ATTEN	FIELD32(0x00300000)
+#define TX_ALC_CFG_1_TX1_RF_GAIN_ATTEN	FIELD32(0x00c00000)
+#define TX_ALC_CFG_1_RF_TOS_TIMEOUT	FIELD32(0x3f000000)
+#define TX_ALC_CFG_1_RF_TOS_ENABLE	FIELD32(0x40000000)
+#define TX_ALC_CFG_1_ROS_BUSY_EN	FIELD32(0x80000000)
+
+/* TXn_BB_GAIN_ATTEN: TXn RF Gain Attenuation Level
+ * Format: 5-bit signed values
+ * Unit: 0.5 dB, Range: -8 dB to 7 dB
+ */
+#define TX0_BB_GAIN_ATTEN		0x13c0
+#define TX0_BB_GAIN_ATTEN_LEVEL_0	FIELD32(0x0000001f)
+#define TX0_BB_GAIN_ATTEN_LEVEL_1	FIELD32(0x00001f00)
+#define TX0_BB_GAIN_ATTEN_LEVEL_2	FIELD32(0x001f0000)
+#define TX0_BB_GAIN_ATTEN_LEVEL_3	FIELD32(0x1f000000)
+#define TX1_BB_GAIN_ATTEN		0x13c4
+#define TX1_BB_GAIN_ATTEN_LEVEL_0	FIELD32(0x0000001f)
+#define TX1_BB_GAIN_ATTEN_LEVEL_1	FIELD32(0x00001f00)
+#define TX1_BB_GAIN_ATTEN_LEVEL_2	FIELD32(0x001f0000)
+#define TX1_BB_GAIN_ATTEN_LEVEL_3	FIELD32(0x1f000000)
+
+/* TX_ALC_VGA3: TX Automatic Level Correction Variable Gain Amplifier 3 */
+#define TX_ALC_VGA3			0x13c8
+#define TX_ALC_VGA3_TX0_ALC_VGA3	FIELD32(0x0000001f)
+#define TX_ALC_VGA3_TX1_ALC_VGA3	FIELD32(0x00001f00)
+#define TX_ALC_VGA3_TX0_ALC_VGA2	FIELD32(0x001f0000)
+#define TX_ALC_VGA3_TX1_ALC_VGA2	FIELD32(0x1f000000)
+
 /* TX_PWR_CFG_7 */
 #define TX_PWR_CFG_7			0x13d4
 #define TX_PWR_CFG_7_OFDM54_CH0		FIELD32(0x0000000f)
@@ -1555,6 +1699,10 @@
 #define TX_PWR_CFG_7_MCS7_CH0		FIELD32(0x000f0000)
 #define TX_PWR_CFG_7_MCS7_CH1		FIELD32(0x00f00000)
 #define TX_PWR_CFG_7_MCS7_CH2		FIELD32(0x0f000000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_7B_54MBS		FIELD32(0x000000ff)
+#define TX_PWR_CFG_7B_MCS7		FIELD32(0x00ff0000)
+
 
 /* TX_PWR_CFG_8 */
 #define TX_PWR_CFG_8			0x13d8
@@ -1564,12 +1712,17 @@
 #define TX_PWR_CFG_8_MCS23_CH0		FIELD32(0x000f0000)
 #define TX_PWR_CFG_8_MCS23_CH1		FIELD32(0x00f00000)
 #define TX_PWR_CFG_8_MCS23_CH2		FIELD32(0x0f000000)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_8B_MCS15		FIELD32(0x000000ff)
+
 
 /* TX_PWR_CFG_9 */
 #define TX_PWR_CFG_9			0x13dc
 #define TX_PWR_CFG_9_STBC7_CH0		FIELD32(0x0000000f)
 #define TX_PWR_CFG_9_STBC7_CH1		FIELD32(0x000000f0)
 #define TX_PWR_CFG_9_STBC7_CH2		FIELD32(0x00000f00)
+/* bits for new 2T devices */
+#define TX_PWR_CFG_9B_STBC_MCS7		FIELD32(0x000000ff)
 
 /*
  * RX_FILTER_CFG: RX configuration register.
@@ -1760,6 +1913,8 @@
 #define TX_STA_FIFO_WCID		FIELD32(0x0000ff00)
 #define TX_STA_FIFO_SUCCESS_RATE	FIELD32(0xffff0000)
 #define TX_STA_FIFO_MCS			FIELD32(0x007f0000)
+#define TX_STA_FIFO_BW			FIELD32(0x00800000)
+#define TX_STA_FIFO_SGI			FIELD32(0x01000000)
 #define TX_STA_FIFO_PHYMODE		FIELD32(0xc0000000)
 
 /*
@@ -2135,11 +2290,14 @@ struct mac_iveiv_entry {
 #define RFCSR1_TX1_PD			FIELD8(0x20)
 #define RFCSR1_RX2_PD			FIELD8(0x40)
 #define RFCSR1_TX2_PD			FIELD8(0x80)
+#define RFCSR1_TX2_EN_MT7620		FIELD8(0x02)
 
 /*
  * RFCSR 2:
  */
 #define RFCSR2_RESCAL_EN		FIELD8(0x80)
+#define RFCSR2_RX2_EN_MT7620		FIELD8(0x02)
+#define RFCSR2_TX2_EN_MT7620		FIELD8(0x20)
 
 /*
  * RFCSR 3:
@@ -2158,6 +2316,12 @@ struct mac_iveiv_entry {
 #define RFCSR3_BIT5			FIELD8(0x20)
 
 /*
+ * RFCSR 4:
+ * VCOCAL_EN used by MT7620
+ */
+#define RFCSR4_VCOCAL_EN		FIELD8(0x80)
+
+/*
  * FRCSR 5:
  */
 #define RFCSR5_R1			FIELD8(0x0c)
@@ -2212,6 +2376,7 @@ struct mac_iveiv_entry {
  */
 #define RFCSR13_TX_POWER		FIELD8(0x1f)
 #define RFCSR13_DR0			FIELD8(0xe0)
+#define RFCSR13_RDIV_MT7620		FIELD8(0x03)
 
 /*
  * RFCSR 15:
@@ -2222,6 +2387,8 @@ struct mac_iveiv_entry {
  * RFCSR 16:
  */
 #define RFCSR16_TXMIXER_GAIN		FIELD8(0x07)
+#define RFCSR16_RF_PLL_FREQ_SEL_MT7620	FIELD8(0x0F)
+#define RFCSR16_SDM_MODE_MT7620		FIELD8(0xE0)
 
 /*
  * RFCSR 17:
@@ -2234,6 +2401,8 @@ struct mac_iveiv_entry {
 /* RFCSR 18 */
 #define RFCSR18_XO_TUNE_BYPASS		FIELD8(0x40)
 
+/* RFCSR 19 */
+#define RFCSR19_K			FIELD8(0x03)
 
 /*
  * RFCSR 20:
@@ -2244,11 +2413,14 @@ struct mac_iveiv_entry {
  * RFCSR 21:
  */
 #define RFCSR21_RX_LO2_EN		FIELD8(0x08)
+#define RFCSR21_BIT1			FIELD8(0x01)
+#define RFCSR21_BIT8			FIELD8(0x80)
 
 /*
  * RFCSR 22:
  */
 #define RFCSR22_BASEBAND_LOOPBACK	FIELD8(0x01)
+#define RFCSR22_FREQPLAN_D_MT7620	FIELD8(0x07)
 
 /*
  * RFCSR 23:
@@ -2271,6 +2443,11 @@ struct mac_iveiv_entry {
 #define RFCSR27_R4			FIELD8(0x40)
 
 /*
+ * RFCSR 28:
+ */
+#define RFCSR28_CH11_HT40		FIELD8(0x04)
+
+/*
  * RFCSR 29:
  */
 #define RFCSR29_ADC6_TEST		FIELD8(0x01)
@@ -2331,6 +2508,7 @@ struct mac_iveiv_entry {
  */
 #define RFCSR42_BIT1			FIELD8(0x01)
 #define RFCSR42_BIT4			FIELD8(0x08)
+#define RFCSR42_TX2_EN_MT7620		FIELD8(0x40)
 
 /*
  * RFCSR 49:
@@ -2433,6 +2611,7 @@ enum rt2800_eeprom_word {
 	EEPROM_TSSI_BOUND_BG5,
 	EEPROM_TXPOWER_A1,
 	EEPROM_TXPOWER_A2,
+	EEPROM_TXPOWER_INIT,
 	EEPROM_TSSI_BOUND_A1,
 	EEPROM_TSSI_BOUND_A2,
 	EEPROM_TSSI_BOUND_A3,
@@ -2987,29 +3166,4 @@ enum rt2800_eeprom_word {
  */
 #define BCN_TBTT_OFFSET 64
 
-/*
- * Hardware has 255 WCID table entries. First 32 entries are reserved for
- * shared keys. Since parts of the pairwise key table might be shared with
- * the beacon frame buffers 6 & 7 we could only use the first 222 entries.
- */
-#define WCID_START	33
-#define WCID_END	222
-#define STA_IDS_SIZE	(WCID_END - WCID_START + 2)
-
-/*
- * RT2800 driver data structure
- */
-struct rt2800_drv_data {
-	u8 calibration_bw20;
-	u8 calibration_bw40;
-	u8 bbp25;
-	u8 bbp26;
-	u8 txmixer_gain_24g;
-	u8 txmixer_gain_5g;
-	u8 max_psdu;
-	unsigned int tbtt_tick;
-	unsigned int ampdu_factor_cnt[4];
-	DECLARE_BITMAP(sta_ids, STA_IDS_SIZE);
-};
-
 #endif /* RT2800_H */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index 8223a1520316..d11c7b210e81 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -59,6 +59,9 @@
 	rt2800_regbusy_read((__dev), BBP_CSR_CFG, BBP_CSR_CFG_BUSY, (__reg))
 #define WAIT_FOR_RFCSR(__dev, __reg) \
 	rt2800_regbusy_read((__dev), RF_CSR_CFG, RF_CSR_CFG_BUSY, (__reg))
+#define WAIT_FOR_RFCSR_MT7620(__dev, __reg) \
+	rt2800_regbusy_read((__dev), RF_CSR_CFG, RF_CSR_CFG_BUSY_MT7620, \
+			    (__reg))
 #define WAIT_FOR_RF(__dev, __reg) \
 	rt2800_regbusy_read((__dev), RF_CSR_CFG0, RF_CSR_CFG0_BUSY, (__reg))
 #define WAIT_FOR_MCU(__dev, __reg) \
@@ -150,19 +153,56 @@ static void rt2800_rfcsr_write(struct rt2x00_dev *rt2x00dev,
 	 * Wait until the RFCSR becomes available, afterwards we
 	 * can safely write the new data into the register.
 	 */
-	if (WAIT_FOR_RFCSR(rt2x00dev, &reg)) {
-		reg = 0;
-		rt2x00_set_field32(&reg, RF_CSR_CFG_DATA, value);
-		rt2x00_set_field32(&reg, RF_CSR_CFG_REGNUM, word);
-		rt2x00_set_field32(&reg, RF_CSR_CFG_WRITE, 1);
-		rt2x00_set_field32(&reg, RF_CSR_CFG_BUSY, 1);
+	switch (rt2x00dev->chip.rt) {
+	case RT6352:
+		if (WAIT_FOR_RFCSR_MT7620(rt2x00dev, &reg)) {
+			reg = 0;
+			rt2x00_set_field32(&reg, RF_CSR_CFG_DATA_MT7620, value);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_REGNUM_MT7620,
+					   word);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_WRITE_MT7620, 1);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_BUSY_MT7620, 1);
+
+			rt2800_register_write_lock(rt2x00dev, RF_CSR_CFG, reg);
+		}
+		break;
 
-		rt2800_register_write_lock(rt2x00dev, RF_CSR_CFG, reg);
+	default:
+		if (WAIT_FOR_RFCSR(rt2x00dev, &reg)) {
+			reg = 0;
+			rt2x00_set_field32(&reg, RF_CSR_CFG_DATA, value);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_REGNUM, word);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_WRITE, 1);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_BUSY, 1);
+
+			rt2800_register_write_lock(rt2x00dev, RF_CSR_CFG, reg);
+		}
+		break;
 	}
 
 	mutex_unlock(&rt2x00dev->csr_mutex);
 }
 
+static void rt2800_rfcsr_write_bank(struct rt2x00_dev *rt2x00dev, const u8 bank,
+				    const unsigned int reg, const u8 value)
+{
+	rt2800_rfcsr_write(rt2x00dev, (reg | (bank << 6)), value);
+}
+
+static void rt2800_rfcsr_write_chanreg(struct rt2x00_dev *rt2x00dev,
+				       const unsigned int reg, const u8 value)
+{
+	rt2800_rfcsr_write_bank(rt2x00dev, 4, reg, value);
+	rt2800_rfcsr_write_bank(rt2x00dev, 6, reg, value);
+}
+
+static void rt2800_rfcsr_write_dccal(struct rt2x00_dev *rt2x00dev,
+				     const unsigned int reg, const u8 value)
+{
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, reg, value);
+	rt2800_rfcsr_write_bank(rt2x00dev, 7, reg, value);
+}
+
 static void rt2800_rfcsr_read(struct rt2x00_dev *rt2x00dev,
 			      const unsigned int word, u8 *value)
 {
@@ -178,22 +218,48 @@ static void rt2800_rfcsr_read(struct rt2x00_dev *rt2x00dev,
 	 * doesn't become available in time, reg will be 0xffffffff
 	 * which means we return 0xff to the caller.
 	 */
-	if (WAIT_FOR_RFCSR(rt2x00dev, &reg)) {
-		reg = 0;
-		rt2x00_set_field32(&reg, RF_CSR_CFG_REGNUM, word);
-		rt2x00_set_field32(&reg, RF_CSR_CFG_WRITE, 0);
-		rt2x00_set_field32(&reg, RF_CSR_CFG_BUSY, 1);
+	switch (rt2x00dev->chip.rt) {
+	case RT6352:
+		if (WAIT_FOR_RFCSR_MT7620(rt2x00dev, &reg)) {
+			reg = 0;
+			rt2x00_set_field32(&reg, RF_CSR_CFG_REGNUM_MT7620,
+					   word);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_WRITE_MT7620, 0);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_BUSY_MT7620, 1);
 
-		rt2800_register_write_lock(rt2x00dev, RF_CSR_CFG, reg);
+			rt2800_register_write_lock(rt2x00dev, RF_CSR_CFG, reg);
 
-		WAIT_FOR_RFCSR(rt2x00dev, &reg);
-	}
+			WAIT_FOR_RFCSR_MT7620(rt2x00dev, &reg);
+		}
+
+		*value = rt2x00_get_field32(reg, RF_CSR_CFG_DATA_MT7620);
+		break;
+
+	default:
+		if (WAIT_FOR_RFCSR(rt2x00dev, &reg)) {
+			reg = 0;
+			rt2x00_set_field32(&reg, RF_CSR_CFG_REGNUM, word);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_WRITE, 0);
+			rt2x00_set_field32(&reg, RF_CSR_CFG_BUSY, 1);
 
-	*value = rt2x00_get_field32(reg, RF_CSR_CFG_DATA);
+			rt2800_register_write_lock(rt2x00dev, RF_CSR_CFG, reg);
+
+			WAIT_FOR_RFCSR(rt2x00dev, &reg);
+		}
+
+		*value = rt2x00_get_field32(reg, RF_CSR_CFG_DATA);
+		break;
+	}
 
 	mutex_unlock(&rt2x00dev->csr_mutex);
 }
 
+static void rt2800_rfcsr_read_bank(struct rt2x00_dev *rt2x00dev, const u8 bank,
+				   const unsigned int reg, u8 *value)
+{
+	rt2800_rfcsr_read(rt2x00dev, (reg | (bank << 6)), value);
+}
+
 static void rt2800_rf_write(struct rt2x00_dev *rt2x00dev,
 			    const unsigned int word, const u32 value)
 {
@@ -250,6 +316,7 @@ static const unsigned int rt2800_eeprom_map[EEPROM_WORD_COUNT] = {
 	[EEPROM_TSSI_BOUND_BG5]		= 0x003b,
 	[EEPROM_TXPOWER_A1]		= 0x003c,
 	[EEPROM_TXPOWER_A2]		= 0x0053,
+	[EEPROM_TXPOWER_INIT]		= 0x0068,
 	[EEPROM_TSSI_BOUND_A1]		= 0x006a,
 	[EEPROM_TSSI_BOUND_A2]		= 0x006b,
 	[EEPROM_TSSI_BOUND_A3]		= 0x006c,
@@ -524,6 +591,7 @@ void rt2800_get_txwi_rxwi_size(struct rt2x00_dev *rt2x00dev,
 		break;
 
 	case RT5592:
+	case RT6352:
 		*txwi_size = TXWI_DESC_SIZE_5WORDS;
 		*rxwi_size = RXWI_DESC_SIZE_6WORDS;
 		break;
@@ -821,10 +889,10 @@ void rt2800_process_rxwi(struct queue_entry *entry,
 	rt2x00_desc_read(rxwi, 1, &word);
 
 	if (rt2x00_get_field32(word, RXWI_W1_SHORT_GI))
-		rxdesc->flags |= RX_FLAG_SHORT_GI;
+		rxdesc->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (rt2x00_get_field32(word, RXWI_W1_BW))
-		rxdesc->flags |= RX_FLAG_40MHZ;
+		rxdesc->bw = RATE_INFO_BW_40;
 
 	/*
 	 * Detect RX rate, always use MCS as signal type.
@@ -852,14 +920,49 @@ void rt2800_process_rxwi(struct queue_entry *entry,
 }
 EXPORT_SYMBOL_GPL(rt2800_process_rxwi);
 
-void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi)
+static void rt2800_rate_from_status(struct skb_frame_desc *skbdesc,
+				    u32 status, enum nl80211_band band)
+{
+	u8 flags = 0;
+	u8 idx = rt2x00_get_field32(status, TX_STA_FIFO_MCS);
+
+	switch (rt2x00_get_field32(status, TX_STA_FIFO_PHYMODE)) {
+	case RATE_MODE_HT_GREENFIELD:
+		flags |= IEEE80211_TX_RC_GREEN_FIELD;
+		/* fall through */
+	case RATE_MODE_HT_MIX:
+		flags |= IEEE80211_TX_RC_MCS;
+		break;
+	case RATE_MODE_OFDM:
+		if (band == NL80211_BAND_2GHZ)
+			idx += 4;
+		break;
+	case RATE_MODE_CCK:
+		if (idx >= 8)
+			idx -= 8;
+		break;
+	}
+
+	if (rt2x00_get_field32(status, TX_STA_FIFO_BW))
+		flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
+
+	if (rt2x00_get_field32(status, TX_STA_FIFO_SGI))
+		flags |= IEEE80211_TX_RC_SHORT_GI;
+
+	skbdesc->tx_rate_idx = idx;
+	skbdesc->tx_rate_flags = flags;
+}
+
+void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi,
+			 bool match)
 {
 	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
+	struct rt2800_drv_data *drv_data = rt2x00dev->drv_data;
 	struct skb_frame_desc *skbdesc = get_skb_frame_desc(entry->skb);
 	struct txdone_entry_desc txdesc;
 	u32 word;
 	u16 mcs, real_mcs;
-	int aggr, ampdu;
+	int aggr, ampdu, wcid, ack_req;
 
 	/*
 	 * Obtain the status about this packet.
@@ -872,6 +975,8 @@ void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi)
 
 	real_mcs = rt2x00_get_field32(status, TX_STA_FIFO_MCS);
 	aggr = rt2x00_get_field32(status, TX_STA_FIFO_TX_AGGRE);
+	wcid = rt2x00_get_field32(status, TX_STA_FIFO_WCID);
+	ack_req	= rt2x00_get_field32(status, TX_STA_FIFO_TX_ACK_REQUIRED);
 
 	/*
 	 * If a frame was meant to be sent as a single non-aggregated MPDU
@@ -888,15 +993,22 @@ void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi)
 	 * Hence, replace the requested rate with the real tx rate to not
 	 * confuse the rate control algortihm by providing clearly wrong
 	 * data.
-	 */
-	if (unlikely(aggr == 1 && ampdu == 0 && real_mcs != mcs)) {
-		skbdesc->tx_rate_idx = real_mcs;
+	 *
+	 * FIXME: if we do not find matching entry, we tell that frame was
+	 * posted without any retries. We need to find a way to fix that
+	 * and provide retry count.
+ 	 */
+	if (unlikely((aggr == 1 && ampdu == 0 && real_mcs != mcs)) || !match) {
+		rt2800_rate_from_status(skbdesc, status, rt2x00dev->curr_band);
 		mcs = real_mcs;
 	}
 
 	if (aggr == 1 || ampdu == 1)
 		__set_bit(TXDONE_AMPDU, &txdesc.flags);
 
+	if (!ack_req)
+		__set_bit(TXDONE_NO_ACK_REQ, &txdesc.flags);
+
 	/*
 	 * Ralink has a retry mechanism using a global fallback
 	 * table. We setup this fallback table to try the immediate
@@ -928,7 +1040,18 @@ void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi)
 	if (txdesc.retry)
 		__set_bit(TXDONE_FALLBACK, &txdesc.flags);
 
-	rt2x00lib_txdone(entry, &txdesc);
+	if (!match) {
+		/* RCU assures non-null sta will not be freed by mac80211. */
+		rcu_read_lock();
+		if (likely(wcid >= WCID_START && wcid <= WCID_END))
+			skbdesc->sta = drv_data->wcid_to_sta[wcid - WCID_START];
+		else
+			skbdesc->sta = NULL;
+		rt2x00lib_txdone_nomatch(entry, &txdesc);
+		rcu_read_unlock();
+	} else {
+		rt2x00lib_txdone(entry, &txdesc);
+	}
 }
 EXPORT_SYMBOL_GPL(rt2800_txdone_entry);
 
@@ -1468,6 +1591,7 @@ int rt2800_sta_add(struct rt2x00_dev *rt2x00dev, struct ieee80211_vif *vif,
 		return 0;
 
 	__set_bit(wcid - WCID_START, drv_data->sta_ids);
+	drv_data->wcid_to_sta[wcid - WCID_START] = sta;
 
 	/*
 	 * Clean up WCID attributes and write STA address to the device.
@@ -1498,6 +1622,7 @@ int rt2800_sta_remove(struct rt2x00_dev *rt2x00dev, struct ieee80211_sta *sta)
 	 * get renewed when the WCID is reused.
 	 */
 	rt2800_config_wcid(rt2x00dev, NULL, wcid);
+	drv_data->wcid_to_sta[wcid - WCID_START] = NULL;
 	__clear_bit(wcid - WCID_START, drv_data->sta_ids);
 
 	return 0;
@@ -2753,7 +2878,8 @@ static void rt2800_config_channel_rf53xx(struct rt2x00_dev *rt2x00dev,
 				rt2800_rfcsr_write(rt2x00dev, 59,
 						   r59_nonbt_rev[idx]);
 			} else if (rt2x00_rt(rt2x00dev, RT5390) ||
-				   rt2x00_rt(rt2x00dev, RT5392)) {
+				   rt2x00_rt(rt2x00dev, RT5392) ||
+				   rt2x00_rt(rt2x00dev, RT6352)) {
 				static const char r59_non_bt[] = {0x8f, 0x8f,
 					0x8f, 0x8f, 0x8f, 0x8f, 0x8f, 0x8d,
 					0x8a, 0x88, 0x88, 0x87, 0x87, 0x86};
@@ -3047,6 +3173,244 @@ static void rt2800_config_channel_rf55xx(struct rt2x00_dev *rt2x00dev,
 	rt2800_bbp_write(rt2x00dev, 196, (rf->channel <= 14) ? 0x19 : 0x7F);
 }
 
+static void rt2800_config_channel_rf7620(struct rt2x00_dev *rt2x00dev,
+					 struct ieee80211_conf *conf,
+					 struct rf_channel *rf,
+					 struct channel_info *info)
+{
+	struct rt2800_drv_data *drv_data = rt2x00dev->drv_data;
+	u8 rx_agc_fc, tx_agc_fc;
+	u8 rfcsr;
+
+	/* Frequeny plan setting */
+	/* Rdiv setting (set 0x03 if Xtal==20)
+	 * R13[1:0]
+	 */
+	rt2800_rfcsr_read(rt2x00dev, 13, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR13_RDIV_MT7620,
+			  rt2800_clk_is_20mhz(rt2x00dev) ? 3 : 0);
+	rt2800_rfcsr_write(rt2x00dev, 13, rfcsr);
+
+	/* N setting
+	 * R20[7:0] in rf->rf1
+	 * R21[0] always 0
+	 */
+	rt2800_rfcsr_read(rt2x00dev, 20, &rfcsr);
+	rfcsr = (rf->rf1 & 0x00ff);
+	rt2800_rfcsr_write(rt2x00dev, 20, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 21, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR21_BIT1, 0);
+	rt2800_rfcsr_write(rt2x00dev, 21, rfcsr);
+
+	/* K setting (always 0)
+	 * R16[3:0] (RF PLL freq selection)
+	 */
+	rt2800_rfcsr_read(rt2x00dev, 16, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR16_RF_PLL_FREQ_SEL_MT7620, 0);
+	rt2800_rfcsr_write(rt2x00dev, 16, rfcsr);
+
+	/* D setting (always 0)
+	 * R22[2:0] (D=15, R22[2:0]=<111>)
+	 */
+	rt2800_rfcsr_read(rt2x00dev, 22, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR22_FREQPLAN_D_MT7620, 0);
+	rt2800_rfcsr_write(rt2x00dev, 22, rfcsr);
+
+	/* Ksd setting
+	 * Ksd: R17<7:0> in rf->rf2
+	 *      R18<7:0> in rf->rf3
+	 *      R19<1:0> in rf->rf4
+	 */
+	rt2800_rfcsr_read(rt2x00dev, 17, &rfcsr);
+	rfcsr = rf->rf2;
+	rt2800_rfcsr_write(rt2x00dev, 17, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 18, &rfcsr);
+	rfcsr = rf->rf3;
+	rt2800_rfcsr_write(rt2x00dev, 18, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 19, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR19_K, rf->rf4);
+	rt2800_rfcsr_write(rt2x00dev, 19, rfcsr);
+
+	/* Default: XO=20MHz , SDM mode */
+	rt2800_rfcsr_read(rt2x00dev, 16, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR16_SDM_MODE_MT7620, 0x80);
+	rt2800_rfcsr_write(rt2x00dev, 16, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 21, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR21_BIT8, 1);
+	rt2800_rfcsr_write(rt2x00dev, 21, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 1, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR1_TX2_EN_MT7620,
+			  rt2x00dev->default_ant.tx_chain_num != 1);
+	rt2800_rfcsr_write(rt2x00dev, 1, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 2, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR2_TX2_EN_MT7620,
+			  rt2x00dev->default_ant.tx_chain_num != 1);
+	rt2x00_set_field8(&rfcsr, RFCSR2_RX2_EN_MT7620,
+			  rt2x00dev->default_ant.rx_chain_num != 1);
+	rt2800_rfcsr_write(rt2x00dev, 2, rfcsr);
+
+	rt2800_rfcsr_read(rt2x00dev, 42, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR42_TX2_EN_MT7620,
+			  rt2x00dev->default_ant.tx_chain_num != 1);
+	rt2800_rfcsr_write(rt2x00dev, 42, rfcsr);
+
+	/* RF for DC Cal BW */
+	if (conf_is_ht40(conf)) {
+		rt2800_rfcsr_write_dccal(rt2x00dev, 6, 0x10);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 7, 0x10);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 8, 0x04);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 58, 0x10);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 59, 0x10);
+	} else {
+		rt2800_rfcsr_write_dccal(rt2x00dev, 6, 0x20);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 7, 0x20);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 8, 0x00);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 58, 0x20);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 59, 0x20);
+	}
+
+	if (conf_is_ht40(conf)) {
+		rt2800_rfcsr_write_dccal(rt2x00dev, 58, 0x08);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 59, 0x08);
+	} else {
+		rt2800_rfcsr_write_dccal(rt2x00dev, 58, 0x28);
+		rt2800_rfcsr_write_dccal(rt2x00dev, 59, 0x28);
+	}
+
+	rt2800_rfcsr_read(rt2x00dev, 28, &rfcsr);
+	rt2x00_set_field8(&rfcsr, RFCSR28_CH11_HT40,
+			  conf_is_ht40(conf) && (rf->channel == 11));
+	rt2800_rfcsr_write(rt2x00dev, 28, rfcsr);
+
+	if (!test_bit(DEVICE_STATE_SCANNING, &rt2x00dev->flags)) {
+		if (conf_is_ht40(conf)) {
+			rx_agc_fc = drv_data->rx_calibration_bw40;
+			tx_agc_fc = drv_data->tx_calibration_bw40;
+		} else {
+			rx_agc_fc = drv_data->rx_calibration_bw20;
+			tx_agc_fc = drv_data->tx_calibration_bw20;
+		}
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 6, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= rx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 6, rfcsr);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 7, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= rx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 7, rfcsr);
+		rt2800_rfcsr_read_bank(rt2x00dev, 7, 6, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= rx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 7, 6, rfcsr);
+		rt2800_rfcsr_read_bank(rt2x00dev, 7, 7, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= rx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 7, 7, rfcsr);
+
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 58, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= tx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 58, rfcsr);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 59, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= tx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 59, rfcsr);
+		rt2800_rfcsr_read_bank(rt2x00dev, 7, 58, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= tx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 7, 58, rfcsr);
+		rt2800_rfcsr_read_bank(rt2x00dev, 7, 59, &rfcsr);
+		rfcsr &= (~0x3F);
+		rfcsr |= tx_agc_fc;
+		rt2800_rfcsr_write_bank(rt2x00dev, 7, 59, rfcsr);
+	}
+}
+
+static void rt2800_config_alc(struct rt2x00_dev *rt2x00dev,
+			      struct ieee80211_channel *chan,
+			      int power_level) {
+	u16 eeprom, target_power, max_power;
+	u32 mac_sys_ctrl, mac_status;
+	u32 reg;
+	u8 bbp;
+	int i;
+
+	/* hardware unit is 0.5dBm, limited to 23.5dBm */
+	power_level *= 2;
+	if (power_level > 0x2f)
+		power_level = 0x2f;
+
+	max_power = chan->max_power * 2;
+	if (max_power > 0x2f)
+		max_power = 0x2f;
+
+	rt2800_register_read(rt2x00dev, TX_ALC_CFG_0, &reg);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_0, power_level);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_1, power_level);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_LIMIT_0, max_power);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_0_LIMIT_1, max_power);
+
+	rt2800_eeprom_read(rt2x00dev, EEPROM_NIC_CONF1, &eeprom);
+	if (rt2x00_get_field16(eeprom, EEPROM_NIC_CONF1_INTERNAL_TX_ALC)) {
+		/* init base power by eeprom target power */
+		rt2800_eeprom_read(rt2x00dev, EEPROM_TXPOWER_INIT,
+				   &target_power);
+		rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_0, target_power);
+		rt2x00_set_field32(&reg, TX_ALC_CFG_0_CH_INIT_1, target_power);
+	}
+	rt2800_register_write(rt2x00dev, TX_ALC_CFG_0, reg);
+
+	rt2800_register_read(rt2x00dev, TX_ALC_CFG_1, &reg);
+	rt2x00_set_field32(&reg, TX_ALC_CFG_1_TX_TEMP_COMP, 0);
+	rt2800_register_write(rt2x00dev, TX_ALC_CFG_1, reg);
+
+	/* Save MAC SYS CTRL registers */
+	rt2800_register_read(rt2x00dev, MAC_SYS_CTRL, &mac_sys_ctrl);
+	/* Disable Tx/Rx */
+	rt2800_register_write(rt2x00dev, MAC_SYS_CTRL, 0);
+	/* Check MAC Tx/Rx idle */
+	for (i = 0; i < 10000; i++) {
+		rt2800_register_read(rt2x00dev, MAC_STATUS_CFG,
+				     &mac_status);
+		if (mac_status & 0x3)
+			usleep_range(50, 200);
+		else
+			break;
+	}
+
+	if (i == 10000)
+		rt2x00_warn(rt2x00dev, "Wait MAC Status to MAX !!!\n");
+
+	if (chan->center_freq > 2457) {
+		rt2800_bbp_read(rt2x00dev, 30, &bbp);
+		bbp = 0x40;
+		rt2800_bbp_write(rt2x00dev, 30, bbp);
+		rt2800_rfcsr_write(rt2x00dev, 39, 0);
+		if (rt2x00_has_cap_external_lna_bg(rt2x00dev))
+			rt2800_rfcsr_write(rt2x00dev, 42, 0xfb);
+		else
+			rt2800_rfcsr_write(rt2x00dev, 42, 0x7b);
+	} else {
+		rt2800_bbp_read(rt2x00dev, 30, &bbp);
+		bbp = 0x1f;
+		rt2800_bbp_write(rt2x00dev, 30, bbp);
+		rt2800_rfcsr_write(rt2x00dev, 39, 0x80);
+		if (rt2x00_has_cap_external_lna_bg(rt2x00dev))
+			rt2800_rfcsr_write(rt2x00dev, 42, 0xdb);
+		else
+			rt2800_rfcsr_write(rt2x00dev, 42, 0x5b);
+	}
+	rt2800_register_write(rt2x00dev, MAC_SYS_CTRL, mac_sys_ctrl);
+
+	rt2800_vco_calibration(rt2x00dev);
+}
+
 static void rt2800_bbp_write_with_rx_chain(struct rt2x00_dev *rt2x00dev,
 					   const unsigned int word,
 					   const u8 value)
@@ -3171,7 +3535,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 				  struct channel_info *info)
 {
 	u32 reg;
-	unsigned int tx_pin;
+	u32 tx_pin;
 	u8 bbp, rfcsr;
 
 	info->default_power1 = rt2800_txpower_to_dev(rt2x00dev, rf->channel,
@@ -3216,6 +3580,9 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 	case RF5592:
 		rt2800_config_channel_rf55xx(rt2x00dev, conf, rf, info);
 		break;
+	case RF7620:
+		rt2800_config_channel_rf7620(rt2x00dev, conf, rf, info);
+		break;
 	default:
 		rt2800_config_channel_rf2xxx(rt2x00dev, conf, rf, info);
 	}
@@ -3290,7 +3657,8 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 
 	if (rf->channel <= 14) {
 		if (!rt2x00_rt(rt2x00dev, RT5390) &&
-		    !rt2x00_rt(rt2x00dev, RT5392)) {
+		    !rt2x00_rt(rt2x00dev, RT5392) &&
+		    !rt2x00_rt(rt2x00dev, RT6352)) {
 			if (rt2x00_has_cap_external_lna_bg(rt2x00dev)) {
 				rt2800_bbp_write(rt2x00dev, 82, 0x62);
 				rt2800_bbp_write(rt2x00dev, 75, 0x46);
@@ -3310,7 +3678,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 			rt2800_bbp_write(rt2x00dev, 82, 0x94);
 		else if (rt2x00_rt(rt2x00dev, RT3593))
 			rt2800_bbp_write(rt2x00dev, 82, 0x82);
-		else
+		else if (!rt2x00_rt(rt2x00dev, RT6352))
 			rt2800_bbp_write(rt2x00dev, 82, 0xf2);
 
 		if (rt2x00_rt(rt2x00dev, RT3593))
@@ -3331,7 +3699,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 	if (rt2x00_rt(rt2x00dev, RT3572))
 		rt2800_rfcsr_write(rt2x00dev, 8, 0);
 
-	tx_pin = 0;
+	rt2800_register_read(rt2x00dev, TX_PIN_CFG, &tx_pin);
 
 	switch (rt2x00dev->default_ant.tx_chain_num) {
 	case 3:
@@ -3380,6 +3748,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 
 	rt2x00_set_field32(&tx_pin, TX_PIN_CFG_RFTR_EN, 1);
 	rt2x00_set_field32(&tx_pin, TX_PIN_CFG_TRSW_EN, 1);
+	rt2x00_set_field32(&tx_pin, TX_PIN_CFG_RFRX_EN, 1); /* mt7620 */
 
 	rt2800_register_write(rt2x00dev, TX_PIN_CFG, tx_pin);
 
@@ -3438,12 +3807,26 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 		usleep_range(1000, 1500);
 	}
 
-	if (rt2x00_rt(rt2x00dev, RT5592)) {
+	if (rt2x00_rt(rt2x00dev, RT5592) || rt2x00_rt(rt2x00dev, RT6352)) {
+		reg = 0x10;
+		if (!conf_is_ht40(conf)) {
+			if (rt2x00_rt(rt2x00dev, RT6352) &&
+			    rt2x00_has_cap_external_lna_bg(rt2x00dev)) {
+				reg |= 0x5;
+			} else {
+				reg |= 0xa;
+			}
+		}
 		rt2800_bbp_write(rt2x00dev, 195, 141);
-		rt2800_bbp_write(rt2x00dev, 196, conf_is_ht40(conf) ? 0x10 : 0x1a);
+		rt2800_bbp_write(rt2x00dev, 196, reg);
 
 		/* AGC init */
-		reg = (rf->channel <= 14 ? 0x1c : 0x24) + 2 * rt2x00dev->lna_gain;
+		if (rt2x00_rt(rt2x00dev, RT6352))
+			reg = 0x04;
+		else
+			reg = rf->channel <= 14 ? 0x1c : 0x24;
+
+		reg += 2 * rt2x00dev->lna_gain;
 		rt2800_bbp_write_with_rx_chain(rt2x00dev, 66, reg);
 
 		rt2800_iq_calibrate(rt2x00dev, rf->channel);
@@ -4125,6 +4508,128 @@ static void rt2800_config_txpower_rt3593(struct rt2x00_dev *rt2x00dev,
 			   (unsigned long) regs[i]);
 }
 
+static void rt2800_config_txpower_rt6352(struct rt2x00_dev *rt2x00dev,
+					 struct ieee80211_channel *chan,
+					 int power_level)
+{
+	u32 reg, pwreg;
+	u16 eeprom;
+	u32 data, gdata;
+	u8 t, i;
+	enum nl80211_band band = chan->band;
+	int delta;
+
+	/* Warn user if bw_comp is set in EEPROM */
+	delta = rt2800_get_txpower_bw_comp(rt2x00dev, band);
+
+	if (delta)
+		rt2x00_warn(rt2x00dev, "ignoring EEPROM HT40 power delta: %d\n",
+			    delta);
+
+	/* populate TX_PWR_CFG_0 up to TX_PWR_CFG_4 from EEPROM for HT20, limit
+	 * value to 0x3f and replace 0x20 by 0x21 as this is what the vendor
+	 * driver does as well, though it looks kinda wrong.
+	 * Maybe some misunderstanding of what a signed 8-bit value is? Maybe
+	 * the hardware has a problem handling 0x20, and as the code initially
+	 * used a fixed offset between HT20 and HT40 rates they had to work-
+	 * around that issue and most likely just forgot about it later on.
+	 * Maybe we should use rt2800_get_txpower_bw_comp() here as well,
+	 * however, the corresponding EEPROM value is not respected by the
+	 * vendor driver, so maybe this is rather being taken care of the
+	 * TXALC and the driver doesn't need to handle it...?
+	 * Though this is all very awkward, just do as they did, as that's what
+	 * board vendors expected when they populated the EEPROM...
+	 */
+	for (i = 0; i < 5; i++) {
+		rt2800_eeprom_read_from_array(rt2x00dev, EEPROM_TXPOWER_BYRATE,
+					      i * 2, &eeprom);
+
+		data = eeprom;
+
+		t = eeprom & 0x3f;
+		if (t == 32)
+			t++;
+
+		gdata = t;
+
+		t = (eeprom & 0x3f00) >> 8;
+		if (t == 32)
+			t++;
+
+		gdata |= (t << 8);
+
+		rt2800_eeprom_read_from_array(rt2x00dev, EEPROM_TXPOWER_BYRATE,
+					      (i * 2) + 1, &eeprom);
+
+		t = eeprom & 0x3f;
+		if (t == 32)
+			t++;
+
+		gdata |= (t << 16);
+
+		t = (eeprom & 0x3f00) >> 8;
+		if (t == 32)
+			t++;
+
+		gdata |= (t << 24);
+		data |= (eeprom << 16);
+
+		if (!test_bit(CONFIG_CHANNEL_HT40, &rt2x00dev->flags)) {
+			/* HT20 */
+			if (data != 0xffffffff)
+				rt2800_register_write(rt2x00dev,
+						      TX_PWR_CFG_0 + (i * 4),
+						      data);
+		} else {
+			/* HT40 */
+			if (gdata != 0xffffffff)
+				rt2800_register_write(rt2x00dev,
+						      TX_PWR_CFG_0 + (i * 4),
+						      gdata);
+		}
+	}
+
+	/* Aparently Ralink ran out of space in the BYRATE calibration section
+	 * of the EERPOM which is copied to the corresponding TX_PWR_CFG_x
+	 * registers. As recent 2T chips use 8-bit instead of 4-bit values for
+	 * power-offsets more space would be needed. Ralink decided to keep the
+	 * EEPROM layout untouched and rather have some shared values covering
+	 * multiple bitrates.
+	 * Populate the registers not covered by the EEPROM in the same way the
+	 * vendor driver does.
+	 */
+
+	/* For OFDM 54MBS use value from OFDM 48MBS */
+	pwreg = 0;
+	rt2800_register_read(rt2x00dev, TX_PWR_CFG_1, &reg);
+	t = rt2x00_get_field32(reg, TX_PWR_CFG_1B_48MBS);
+	rt2x00_set_field32(&pwreg, TX_PWR_CFG_7B_54MBS, t);
+
+	/* For MCS 7 use value from MCS 6 */
+	rt2800_register_read(rt2x00dev, TX_PWR_CFG_2, &reg);
+	t = rt2x00_get_field32(reg, TX_PWR_CFG_2B_MCS6_MCS7);
+	rt2x00_set_field32(&pwreg, TX_PWR_CFG_7B_MCS7, t);
+	rt2800_register_write(rt2x00dev, TX_PWR_CFG_7, pwreg);
+
+	/* For MCS 15 use value from MCS 14 */
+	pwreg = 0;
+	rt2800_register_read(rt2x00dev, TX_PWR_CFG_3, &reg);
+	t = rt2x00_get_field32(reg, TX_PWR_CFG_3B_MCS14);
+	rt2x00_set_field32(&pwreg, TX_PWR_CFG_8B_MCS15, t);
+	rt2800_register_write(rt2x00dev, TX_PWR_CFG_8, pwreg);
+
+	/* For STBC MCS 7 use value from STBC MCS 6 */
+	pwreg = 0;
+	rt2800_register_read(rt2x00dev, TX_PWR_CFG_4, &reg);
+	t = rt2x00_get_field32(reg, TX_PWR_CFG_4B_STBC_MCS6);
+	rt2x00_set_field32(&pwreg, TX_PWR_CFG_9B_STBC_MCS7, t);
+	rt2800_register_write(rt2x00dev, TX_PWR_CFG_9, pwreg);
+
+	rt2800_config_alc(rt2x00dev, chan, power_level);
+
+	/* TODO: temperature compensation code! */
+}
+
 /*
  * We configure transmit power using MAC TX_PWR_CFG_{0,...,N} registers and
  * BBP R1 register. TX_PWR_CFG_X allow to configure per rate TX power values,
@@ -4321,6 +4826,8 @@ static void rt2800_config_txpower(struct rt2x00_dev *rt2x00dev,
 {
 	if (rt2x00_rt(rt2x00dev, RT3593))
 		rt2800_config_txpower_rt3593(rt2x00dev, chan, power_level);
+	else if (rt2x00_rt(rt2x00dev, RT6352))
+		rt2800_config_txpower_rt6352(rt2x00dev, chan, power_level);
 	else
 		rt2800_config_txpower_rt28xx(rt2x00dev, chan, power_level);
 }
@@ -4336,6 +4843,7 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev)
 {
 	u32	tx_pin;
 	u8	rfcsr;
+	unsigned long min_sleep = 0;
 
 	/*
 	 * A voltage-controlled oscillator(VCO) is an electronic oscillator
@@ -4374,6 +4882,15 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev)
 		rt2800_rfcsr_read(rt2x00dev, 3, &rfcsr);
 		rt2x00_set_field8(&rfcsr, RFCSR3_VCOCAL_EN, 1);
 		rt2800_rfcsr_write(rt2x00dev, 3, rfcsr);
+		min_sleep = 1000;
+		break;
+	case RF7620:
+		rt2800_rfcsr_write(rt2x00dev, 5, 0x40);
+		rt2800_rfcsr_write(rt2x00dev, 4, 0x0C);
+		rt2800_rfcsr_read(rt2x00dev, 4, &rfcsr);
+		rt2x00_set_field8(&rfcsr, RFCSR4_VCOCAL_EN, 1);
+		rt2800_rfcsr_write(rt2x00dev, 4, rfcsr);
+		min_sleep = 2000;
 		break;
 	default:
 		WARN_ONCE(1, "Not supported RF chipet %x for VCO recalibration",
@@ -4381,7 +4898,8 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev)
 		return;
 	}
 
-	usleep_range(1000, 1500);
+	if (min_sleep > 0)
+		usleep_range(min_sleep, min_sleep * 2);
 
 	rt2800_register_read(rt2x00dev, TX_PIN_CFG, &tx_pin);
 	if (rt2x00dev->rf_channel <= 14) {
@@ -4413,6 +4931,42 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev)
 	}
 	rt2800_register_write(rt2x00dev, TX_PIN_CFG, tx_pin);
 
+	if (rt2x00_rt(rt2x00dev, RT6352)) {
+		if (rt2x00dev->default_ant.rx_chain_num == 1) {
+			rt2800_bbp_write(rt2x00dev, 91, 0x07);
+			rt2800_bbp_write(rt2x00dev, 95, 0x1A);
+			rt2800_bbp_write(rt2x00dev, 195, 128);
+			rt2800_bbp_write(rt2x00dev, 196, 0xA0);
+			rt2800_bbp_write(rt2x00dev, 195, 170);
+			rt2800_bbp_write(rt2x00dev, 196, 0x12);
+			rt2800_bbp_write(rt2x00dev, 195, 171);
+			rt2800_bbp_write(rt2x00dev, 196, 0x10);
+		} else {
+			rt2800_bbp_write(rt2x00dev, 91, 0x06);
+			rt2800_bbp_write(rt2x00dev, 95, 0x9A);
+			rt2800_bbp_write(rt2x00dev, 195, 128);
+			rt2800_bbp_write(rt2x00dev, 196, 0xE0);
+			rt2800_bbp_write(rt2x00dev, 195, 170);
+			rt2800_bbp_write(rt2x00dev, 196, 0x30);
+			rt2800_bbp_write(rt2x00dev, 195, 171);
+			rt2800_bbp_write(rt2x00dev, 196, 0x30);
+		}
+
+		if (rt2x00_has_cap_external_lna_bg(rt2x00dev)) {
+			rt2800_bbp_write(rt2x00dev, 75, 0x68);
+			rt2800_bbp_write(rt2x00dev, 76, 0x4C);
+			rt2800_bbp_write(rt2x00dev, 79, 0x1C);
+			rt2800_bbp_write(rt2x00dev, 80, 0x0C);
+			rt2800_bbp_write(rt2x00dev, 82, 0xB6);
+		}
+
+		/* On 11A, We should delay and wait RF/BBP to be stable
+		 * and the appropriate time should be 1000 micro seconds
+		 * 2005/06/05 - On 11G, we also need this delay time.
+		 * Otherwise it's difficult to pass the WHQL.
+		 */
+		usleep_range(1000, 1500);
+	}
 }
 EXPORT_SYMBOL_GPL(rt2800_vco_calibration);
 
@@ -4511,7 +5065,8 @@ static u8 rt2800_get_default_vgc(struct rt2x00_dev *rt2x00dev)
 		    rt2x00_rt(rt2x00dev, RT3593) ||
 		    rt2x00_rt(rt2x00dev, RT5390) ||
 		    rt2x00_rt(rt2x00dev, RT5392) ||
-		    rt2x00_rt(rt2x00dev, RT5592))
+		    rt2x00_rt(rt2x00dev, RT5592) ||
+		    rt2x00_rt(rt2x00dev, RT6352))
 			vgc = 0x1c + (2 * rt2x00dev->lna_gain);
 		else
 			vgc = 0x2e + rt2x00dev->lna_gain;
@@ -4738,7 +5293,8 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev)
 					      0x00000000);
 		}
 	} else if (rt2x00_rt(rt2x00dev, RT5390) ||
-		   rt2x00_rt(rt2x00dev, RT5392)) {
+		   rt2x00_rt(rt2x00dev, RT5392) ||
+		   rt2x00_rt(rt2x00dev, RT6352)) {
 		rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000404);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x00080606);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000);
@@ -4748,6 +5304,24 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev)
 		rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000);
 	} else if (rt2x00_rt(rt2x00dev, RT5350)) {
 		rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000404);
+	} else if (rt2x00_rt(rt2x00dev, RT6352)) {
+		rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000401);
+		rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x000C0000);
+		rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000);
+		rt2800_register_write(rt2x00dev, MIMO_PS_CFG, 0x00000002);
+		rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0x00150F0F);
+		rt2800_register_write(rt2x00dev, TX_ALC_VGA3, 0x06060606);
+		rt2800_register_write(rt2x00dev, TX0_BB_GAIN_ATTEN, 0x0);
+		rt2800_register_write(rt2x00dev, TX1_BB_GAIN_ATTEN, 0x0);
+		rt2800_register_write(rt2x00dev, TX0_RF_GAIN_ATTEN, 0x6C6C666C);
+		rt2800_register_write(rt2x00dev, TX1_RF_GAIN_ATTEN, 0x6C6C666C);
+		rt2800_register_write(rt2x00dev, TX0_RF_GAIN_CORRECT,
+				      0x3630363A);
+		rt2800_register_write(rt2x00dev, TX1_RF_GAIN_CORRECT,
+				      0x3630363A);
+		rt2800_register_read(rt2x00dev, TX_ALC_CFG_1, &reg);
+		rt2x00_set_field32(&reg, TX_ALC_CFG_1_ROS_BUSY_EN, 0);
+		rt2800_register_write(rt2x00dev, TX_ALC_CFG_1, reg);
 	} else {
 		rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000000);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x00080606);
@@ -5729,6 +6303,231 @@ static void rt2800_init_bbp_5592(struct rt2x00_dev *rt2x00dev)
 		rt2800_bbp_write(rt2x00dev, 103, 0xc0);
 }
 
+static void rt2800_bbp_glrt_write(struct rt2x00_dev *rt2x00dev,
+				  const u8 reg, const u8 value)
+{
+	rt2800_bbp_write(rt2x00dev, 195, reg);
+	rt2800_bbp_write(rt2x00dev, 196, value);
+}
+
+static void rt2800_bbp_dcoc_write(struct rt2x00_dev *rt2x00dev,
+				  const u8 reg, const u8 value)
+{
+	rt2800_bbp_write(rt2x00dev, 158, reg);
+	rt2800_bbp_write(rt2x00dev, 159, value);
+}
+
+static void rt2800_bbp_dcoc_read(struct rt2x00_dev *rt2x00dev,
+				 const u8 reg, u8 *value)
+{
+	rt2800_bbp_write(rt2x00dev, 158, reg);
+	rt2800_bbp_read(rt2x00dev, 159, value);
+}
+
+static void rt2800_init_bbp_6352(struct rt2x00_dev *rt2x00dev)
+{
+	u8 bbp;
+
+	/* Apply Maximum Likelihood Detection (MLD) for 2 stream case */
+	rt2800_bbp_read(rt2x00dev, 105, &bbp);
+	rt2x00_set_field8(&bbp, BBP105_MLD,
+			  rt2x00dev->default_ant.rx_chain_num == 2);
+	rt2800_bbp_write(rt2x00dev, 105, bbp);
+
+	/* Avoid data loss and CRC errors */
+	rt2800_bbp4_mac_if_ctrl(rt2x00dev);
+
+	/* Fix I/Q swap issue */
+	rt2800_bbp_read(rt2x00dev, 1, &bbp);
+	bbp |= 0x04;
+	rt2800_bbp_write(rt2x00dev, 1, bbp);
+
+	/* BBP for G band */
+	rt2800_bbp_write(rt2x00dev, 3, 0x08);
+	rt2800_bbp_write(rt2x00dev, 4, 0x00); /* rt2800_bbp4_mac_if_ctrl? */
+	rt2800_bbp_write(rt2x00dev, 6, 0x08);
+	rt2800_bbp_write(rt2x00dev, 14, 0x09);
+	rt2800_bbp_write(rt2x00dev, 15, 0xFF);
+	rt2800_bbp_write(rt2x00dev, 16, 0x01);
+	rt2800_bbp_write(rt2x00dev, 20, 0x06);
+	rt2800_bbp_write(rt2x00dev, 21, 0x00);
+	rt2800_bbp_write(rt2x00dev, 22, 0x00);
+	rt2800_bbp_write(rt2x00dev, 27, 0x00);
+	rt2800_bbp_write(rt2x00dev, 28, 0x00);
+	rt2800_bbp_write(rt2x00dev, 30, 0x00);
+	rt2800_bbp_write(rt2x00dev, 31, 0x48);
+	rt2800_bbp_write(rt2x00dev, 47, 0x40);
+	rt2800_bbp_write(rt2x00dev, 62, 0x00);
+	rt2800_bbp_write(rt2x00dev, 63, 0x00);
+	rt2800_bbp_write(rt2x00dev, 64, 0x00);
+	rt2800_bbp_write(rt2x00dev, 65, 0x2C);
+	rt2800_bbp_write(rt2x00dev, 66, 0x1C);
+	rt2800_bbp_write(rt2x00dev, 67, 0x20);
+	rt2800_bbp_write(rt2x00dev, 68, 0xDD);
+	rt2800_bbp_write(rt2x00dev, 69, 0x10);
+	rt2800_bbp_write(rt2x00dev, 70, 0x05);
+	rt2800_bbp_write(rt2x00dev, 73, 0x18);
+	rt2800_bbp_write(rt2x00dev, 74, 0x0F);
+	rt2800_bbp_write(rt2x00dev, 75, 0x60);
+	rt2800_bbp_write(rt2x00dev, 76, 0x44);
+	rt2800_bbp_write(rt2x00dev, 77, 0x59);
+	rt2800_bbp_write(rt2x00dev, 78, 0x1E);
+	rt2800_bbp_write(rt2x00dev, 79, 0x1C);
+	rt2800_bbp_write(rt2x00dev, 80, 0x0C);
+	rt2800_bbp_write(rt2x00dev, 81, 0x3A);
+	rt2800_bbp_write(rt2x00dev, 82, 0xB6);
+	rt2800_bbp_write(rt2x00dev, 83, 0x9A);
+	rt2800_bbp_write(rt2x00dev, 84, 0x9A);
+	rt2800_bbp_write(rt2x00dev, 86, 0x38);
+	rt2800_bbp_write(rt2x00dev, 88, 0x90);
+	rt2800_bbp_write(rt2x00dev, 91, 0x04);
+	rt2800_bbp_write(rt2x00dev, 92, 0x02);
+	rt2800_bbp_write(rt2x00dev, 95, 0x9A);
+	rt2800_bbp_write(rt2x00dev, 96, 0x00);
+	rt2800_bbp_write(rt2x00dev, 103, 0xC0);
+	rt2800_bbp_write(rt2x00dev, 104, 0x92);
+	/* FIXME BBP105 owerwrite */
+	rt2800_bbp_write(rt2x00dev, 105, 0x3C);
+	rt2800_bbp_write(rt2x00dev, 106, 0x12);
+	rt2800_bbp_write(rt2x00dev, 109, 0x00);
+	rt2800_bbp_write(rt2x00dev, 134, 0x10);
+	rt2800_bbp_write(rt2x00dev, 135, 0xA6);
+	rt2800_bbp_write(rt2x00dev, 137, 0x04);
+	rt2800_bbp_write(rt2x00dev, 142, 0x30);
+	rt2800_bbp_write(rt2x00dev, 143, 0xF7);
+	rt2800_bbp_write(rt2x00dev, 160, 0xEC);
+	rt2800_bbp_write(rt2x00dev, 161, 0xC4);
+	rt2800_bbp_write(rt2x00dev, 162, 0x77);
+	rt2800_bbp_write(rt2x00dev, 163, 0xF9);
+	rt2800_bbp_write(rt2x00dev, 164, 0x00);
+	rt2800_bbp_write(rt2x00dev, 165, 0x00);
+	rt2800_bbp_write(rt2x00dev, 186, 0x00);
+	rt2800_bbp_write(rt2x00dev, 187, 0x00);
+	rt2800_bbp_write(rt2x00dev, 188, 0x00);
+	rt2800_bbp_write(rt2x00dev, 186, 0x00);
+	rt2800_bbp_write(rt2x00dev, 187, 0x01);
+	rt2800_bbp_write(rt2x00dev, 188, 0x00);
+	rt2800_bbp_write(rt2x00dev, 189, 0x00);
+
+	rt2800_bbp_write(rt2x00dev, 91, 0x06);
+	rt2800_bbp_write(rt2x00dev, 92, 0x04);
+	rt2800_bbp_write(rt2x00dev, 93, 0x54);
+	rt2800_bbp_write(rt2x00dev, 99, 0x50);
+	rt2800_bbp_write(rt2x00dev, 148, 0x84);
+	rt2800_bbp_write(rt2x00dev, 167, 0x80);
+	rt2800_bbp_write(rt2x00dev, 178, 0xFF);
+	rt2800_bbp_write(rt2x00dev, 106, 0x13);
+
+	/* BBP for G band GLRT function (BBP_128 ~ BBP_221) */
+	rt2800_bbp_glrt_write(rt2x00dev, 0, 0x00);
+	rt2800_bbp_glrt_write(rt2x00dev, 1, 0x14);
+	rt2800_bbp_glrt_write(rt2x00dev, 2, 0x20);
+	rt2800_bbp_glrt_write(rt2x00dev, 3, 0x0A);
+	rt2800_bbp_glrt_write(rt2x00dev, 10, 0x16);
+	rt2800_bbp_glrt_write(rt2x00dev, 11, 0x06);
+	rt2800_bbp_glrt_write(rt2x00dev, 12, 0x02);
+	rt2800_bbp_glrt_write(rt2x00dev, 13, 0x07);
+	rt2800_bbp_glrt_write(rt2x00dev, 14, 0x05);
+	rt2800_bbp_glrt_write(rt2x00dev, 15, 0x09);
+	rt2800_bbp_glrt_write(rt2x00dev, 16, 0x20);
+	rt2800_bbp_glrt_write(rt2x00dev, 17, 0x08);
+	rt2800_bbp_glrt_write(rt2x00dev, 18, 0x4A);
+	rt2800_bbp_glrt_write(rt2x00dev, 19, 0x00);
+	rt2800_bbp_glrt_write(rt2x00dev, 20, 0x00);
+	rt2800_bbp_glrt_write(rt2x00dev, 128, 0xE0);
+	rt2800_bbp_glrt_write(rt2x00dev, 129, 0x1F);
+	rt2800_bbp_glrt_write(rt2x00dev, 130, 0x4F);
+	rt2800_bbp_glrt_write(rt2x00dev, 131, 0x32);
+	rt2800_bbp_glrt_write(rt2x00dev, 132, 0x08);
+	rt2800_bbp_glrt_write(rt2x00dev, 133, 0x28);
+	rt2800_bbp_glrt_write(rt2x00dev, 134, 0x19);
+	rt2800_bbp_glrt_write(rt2x00dev, 135, 0x0A);
+	rt2800_bbp_glrt_write(rt2x00dev, 138, 0x16);
+	rt2800_bbp_glrt_write(rt2x00dev, 139, 0x10);
+	rt2800_bbp_glrt_write(rt2x00dev, 140, 0x10);
+	rt2800_bbp_glrt_write(rt2x00dev, 141, 0x1A);
+	rt2800_bbp_glrt_write(rt2x00dev, 142, 0x36);
+	rt2800_bbp_glrt_write(rt2x00dev, 143, 0x2C);
+	rt2800_bbp_glrt_write(rt2x00dev, 144, 0x26);
+	rt2800_bbp_glrt_write(rt2x00dev, 145, 0x24);
+	rt2800_bbp_glrt_write(rt2x00dev, 146, 0x42);
+	rt2800_bbp_glrt_write(rt2x00dev, 147, 0x40);
+	rt2800_bbp_glrt_write(rt2x00dev, 148, 0x30);
+	rt2800_bbp_glrt_write(rt2x00dev, 149, 0x29);
+	rt2800_bbp_glrt_write(rt2x00dev, 150, 0x4C);
+	rt2800_bbp_glrt_write(rt2x00dev, 151, 0x46);
+	rt2800_bbp_glrt_write(rt2x00dev, 152, 0x3D);
+	rt2800_bbp_glrt_write(rt2x00dev, 153, 0x40);
+	rt2800_bbp_glrt_write(rt2x00dev, 154, 0x3E);
+	rt2800_bbp_glrt_write(rt2x00dev, 155, 0x38);
+	rt2800_bbp_glrt_write(rt2x00dev, 156, 0x3D);
+	rt2800_bbp_glrt_write(rt2x00dev, 157, 0x2F);
+	rt2800_bbp_glrt_write(rt2x00dev, 158, 0x3C);
+	rt2800_bbp_glrt_write(rt2x00dev, 159, 0x34);
+	rt2800_bbp_glrt_write(rt2x00dev, 160, 0x2C);
+	rt2800_bbp_glrt_write(rt2x00dev, 161, 0x2F);
+	rt2800_bbp_glrt_write(rt2x00dev, 162, 0x3C);
+	rt2800_bbp_glrt_write(rt2x00dev, 163, 0x35);
+	rt2800_bbp_glrt_write(rt2x00dev, 164, 0x2E);
+	rt2800_bbp_glrt_write(rt2x00dev, 165, 0x2F);
+	rt2800_bbp_glrt_write(rt2x00dev, 166, 0x49);
+	rt2800_bbp_glrt_write(rt2x00dev, 167, 0x41);
+	rt2800_bbp_glrt_write(rt2x00dev, 168, 0x36);
+	rt2800_bbp_glrt_write(rt2x00dev, 169, 0x39);
+	rt2800_bbp_glrt_write(rt2x00dev, 170, 0x30);
+	rt2800_bbp_glrt_write(rt2x00dev, 171, 0x30);
+	rt2800_bbp_glrt_write(rt2x00dev, 172, 0x0E);
+	rt2800_bbp_glrt_write(rt2x00dev, 173, 0x0D);
+	rt2800_bbp_glrt_write(rt2x00dev, 174, 0x28);
+	rt2800_bbp_glrt_write(rt2x00dev, 175, 0x21);
+	rt2800_bbp_glrt_write(rt2x00dev, 176, 0x1C);
+	rt2800_bbp_glrt_write(rt2x00dev, 177, 0x16);
+	rt2800_bbp_glrt_write(rt2x00dev, 178, 0x50);
+	rt2800_bbp_glrt_write(rt2x00dev, 179, 0x4A);
+	rt2800_bbp_glrt_write(rt2x00dev, 180, 0x43);
+	rt2800_bbp_glrt_write(rt2x00dev, 181, 0x50);
+	rt2800_bbp_glrt_write(rt2x00dev, 182, 0x10);
+	rt2800_bbp_glrt_write(rt2x00dev, 183, 0x10);
+	rt2800_bbp_glrt_write(rt2x00dev, 184, 0x10);
+	rt2800_bbp_glrt_write(rt2x00dev, 185, 0x10);
+	rt2800_bbp_glrt_write(rt2x00dev, 200, 0x7D);
+	rt2800_bbp_glrt_write(rt2x00dev, 201, 0x14);
+	rt2800_bbp_glrt_write(rt2x00dev, 202, 0x32);
+	rt2800_bbp_glrt_write(rt2x00dev, 203, 0x2C);
+	rt2800_bbp_glrt_write(rt2x00dev, 204, 0x36);
+	rt2800_bbp_glrt_write(rt2x00dev, 205, 0x4C);
+	rt2800_bbp_glrt_write(rt2x00dev, 206, 0x43);
+	rt2800_bbp_glrt_write(rt2x00dev, 207, 0x2C);
+	rt2800_bbp_glrt_write(rt2x00dev, 208, 0x2E);
+	rt2800_bbp_glrt_write(rt2x00dev, 209, 0x36);
+	rt2800_bbp_glrt_write(rt2x00dev, 210, 0x30);
+	rt2800_bbp_glrt_write(rt2x00dev, 211, 0x6E);
+
+	/* BBP for G band DCOC function */
+	rt2800_bbp_dcoc_write(rt2x00dev, 140, 0x0C);
+	rt2800_bbp_dcoc_write(rt2x00dev, 141, 0x00);
+	rt2800_bbp_dcoc_write(rt2x00dev, 142, 0x10);
+	rt2800_bbp_dcoc_write(rt2x00dev, 143, 0x10);
+	rt2800_bbp_dcoc_write(rt2x00dev, 144, 0x10);
+	rt2800_bbp_dcoc_write(rt2x00dev, 145, 0x10);
+	rt2800_bbp_dcoc_write(rt2x00dev, 146, 0x08);
+	rt2800_bbp_dcoc_write(rt2x00dev, 147, 0x40);
+	rt2800_bbp_dcoc_write(rt2x00dev, 148, 0x04);
+	rt2800_bbp_dcoc_write(rt2x00dev, 149, 0x04);
+	rt2800_bbp_dcoc_write(rt2x00dev, 150, 0x08);
+	rt2800_bbp_dcoc_write(rt2x00dev, 151, 0x08);
+	rt2800_bbp_dcoc_write(rt2x00dev, 152, 0x03);
+	rt2800_bbp_dcoc_write(rt2x00dev, 153, 0x03);
+	rt2800_bbp_dcoc_write(rt2x00dev, 154, 0x03);
+	rt2800_bbp_dcoc_write(rt2x00dev, 155, 0x02);
+	rt2800_bbp_dcoc_write(rt2x00dev, 156, 0x40);
+	rt2800_bbp_dcoc_write(rt2x00dev, 157, 0x40);
+	rt2800_bbp_dcoc_write(rt2x00dev, 158, 0x64);
+	rt2800_bbp_dcoc_write(rt2x00dev, 159, 0x64);
+
+	rt2800_bbp4_mac_if_ctrl(rt2x00dev);
+}
+
 static void rt2800_init_bbp(struct rt2x00_dev *rt2x00dev)
 {
 	unsigned int i;
@@ -5773,6 +6572,9 @@ static void rt2800_init_bbp(struct rt2x00_dev *rt2x00dev)
 	case RT5592:
 		rt2800_init_bbp_5592(rt2x00dev);
 		return;
+	case RT6352:
+		rt2800_init_bbp_6352(rt2x00dev);
+		break;
 	}
 
 	for (i = 0; i < EEPROM_BBP_SIZE; i++) {
@@ -6228,9 +7030,9 @@ static void rt2800_init_rfcsr_3290(struct rt2x00_dev *rt2x00dev)
 
 static void rt2800_init_rfcsr_3352(struct rt2x00_dev *rt2x00dev)
 {
-	int tx0_int_pa = test_bit(CAPABILITY_INTERNAL_PA_TX0,
+	int tx0_ext_pa = test_bit(CAPABILITY_EXTERNAL_PA_TX0,
 				  &rt2x00dev->cap_flags);
-	int tx1_int_pa = test_bit(CAPABILITY_INTERNAL_PA_TX1,
+	int tx1_ext_pa = test_bit(CAPABILITY_EXTERNAL_PA_TX1,
 				  &rt2x00dev->cap_flags);
 	u8 rfcsr;
 
@@ -6270,9 +7072,9 @@ static void rt2800_init_rfcsr_3352(struct rt2x00_dev *rt2x00dev)
 	rt2800_rfcsr_write(rt2x00dev, 32, 0x80);
 	rt2800_rfcsr_write(rt2x00dev, 33, 0x00);
 	rfcsr = 0x01;
-	if (!tx0_int_pa)
+	if (tx0_ext_pa)
 		rt2x00_set_field8(&rfcsr, RFCSR34_TX0_EXT_PA, 1);
-	if (!tx1_int_pa)
+	if (tx1_ext_pa)
 		rt2x00_set_field8(&rfcsr, RFCSR34_TX1_EXT_PA, 1);
 	rt2800_rfcsr_write(rt2x00dev, 34, rfcsr);
 	rt2800_rfcsr_write(rt2x00dev, 35, 0x03);
@@ -6282,13 +7084,13 @@ static void rt2800_init_rfcsr_3352(struct rt2x00_dev *rt2x00dev)
 	rt2800_rfcsr_write(rt2x00dev, 39, 0xc5);
 	rt2800_rfcsr_write(rt2x00dev, 40, 0x33);
 	rfcsr = 0x52;
-	if (tx0_int_pa) {
+	if (!tx0_ext_pa) {
 		rt2x00_set_field8(&rfcsr, RFCSR41_BIT1, 1);
 		rt2x00_set_field8(&rfcsr, RFCSR41_BIT4, 1);
 	}
 	rt2800_rfcsr_write(rt2x00dev, 41, rfcsr);
 	rfcsr = 0x52;
-	if (tx1_int_pa) {
+	if (!tx1_ext_pa) {
 		rt2x00_set_field8(&rfcsr, RFCSR42_BIT1, 1);
 		rt2x00_set_field8(&rfcsr, RFCSR42_BIT4, 1);
 	}
@@ -6301,19 +7103,19 @@ static void rt2800_init_rfcsr_3352(struct rt2x00_dev *rt2x00dev)
 	rt2800_rfcsr_write(rt2x00dev, 48, 0x14);
 	rt2800_rfcsr_write(rt2x00dev, 49, 0x00);
 	rfcsr = 0x2d;
-	if (!tx0_int_pa)
+	if (tx0_ext_pa)
 		rt2x00_set_field8(&rfcsr, RFCSR50_TX0_EXT_PA, 1);
-	if (!tx1_int_pa)
+	if (tx1_ext_pa)
 		rt2x00_set_field8(&rfcsr, RFCSR50_TX1_EXT_PA, 1);
 	rt2800_rfcsr_write(rt2x00dev, 50, rfcsr);
-	rt2800_rfcsr_write(rt2x00dev, 51, (tx0_int_pa ? 0x7f : 0x52));
-	rt2800_rfcsr_write(rt2x00dev, 52, (tx0_int_pa ? 0x00 : 0xc0));
-	rt2800_rfcsr_write(rt2x00dev, 53, (tx0_int_pa ? 0x52 : 0xd2));
-	rt2800_rfcsr_write(rt2x00dev, 54, (tx0_int_pa ? 0x1b : 0xc0));
-	rt2800_rfcsr_write(rt2x00dev, 55, (tx1_int_pa ? 0x7f : 0x52));
-	rt2800_rfcsr_write(rt2x00dev, 56, (tx1_int_pa ? 0x00 : 0xc0));
-	rt2800_rfcsr_write(rt2x00dev, 57, (tx0_int_pa ? 0x52 : 0x49));
-	rt2800_rfcsr_write(rt2x00dev, 58, (tx1_int_pa ? 0x1b : 0xc0));
+	rt2800_rfcsr_write(rt2x00dev, 51, (tx0_ext_pa ? 0x52 : 0x7f));
+	rt2800_rfcsr_write(rt2x00dev, 52, (tx0_ext_pa ? 0xc0 : 0x00));
+	rt2800_rfcsr_write(rt2x00dev, 53, (tx0_ext_pa ? 0xd2 : 0x52));
+	rt2800_rfcsr_write(rt2x00dev, 54, (tx0_ext_pa ? 0xc0 : 0x1b));
+	rt2800_rfcsr_write(rt2x00dev, 55, (tx1_ext_pa ? 0x52 : 0x7f));
+	rt2800_rfcsr_write(rt2x00dev, 56, (tx1_ext_pa ? 0xc0 : 0x00));
+	rt2800_rfcsr_write(rt2x00dev, 57, (tx0_ext_pa ? 0x49 : 0x52));
+	rt2800_rfcsr_write(rt2x00dev, 58, (tx1_ext_pa ? 0xc0 : 0x1b));
 	rt2800_rfcsr_write(rt2x00dev, 59, 0x00);
 	rt2800_rfcsr_write(rt2x00dev, 60, 0x00);
 	rt2800_rfcsr_write(rt2x00dev, 61, 0x00);
@@ -6844,6 +7646,617 @@ static void rt2800_init_rfcsr_5592(struct rt2x00_dev *rt2x00dev)
 	rt2800_led_open_drain_enable(rt2x00dev);
 }
 
+static void rt2800_bbp_core_soft_reset(struct rt2x00_dev *rt2x00dev,
+				       bool set_bw, bool is_ht40)
+{
+	u8 bbp_val;
+
+	rt2800_bbp_read(rt2x00dev, 21, &bbp_val);
+	bbp_val |= 0x1;
+	rt2800_bbp_write(rt2x00dev, 21, bbp_val);
+	usleep_range(100, 200);
+
+	if (set_bw) {
+		rt2800_bbp_read(rt2x00dev, 4, &bbp_val);
+		rt2x00_set_field8(&bbp_val, BBP4_BANDWIDTH, 2 * is_ht40);
+		rt2800_bbp_write(rt2x00dev, 4, bbp_val);
+		usleep_range(100, 200);
+	}
+
+	rt2800_bbp_read(rt2x00dev, 21, &bbp_val);
+	bbp_val &= (~0x1);
+	rt2800_bbp_write(rt2x00dev, 21, bbp_val);
+	usleep_range(100, 200);
+}
+
+static int rt2800_rf_lp_config(struct rt2x00_dev *rt2x00dev, bool btxcal)
+{
+	u8 rf_val;
+
+	if (btxcal)
+		rt2800_register_write(rt2x00dev, RF_CONTROL0, 0x04);
+	else
+		rt2800_register_write(rt2x00dev, RF_CONTROL0, 0x02);
+
+	rt2800_register_write(rt2x00dev, RF_BYPASS0, 0x06);
+
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 17, &rf_val);
+	rf_val |= 0x80;
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 17, rf_val);
+
+	if (btxcal) {
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 18, 0xC1);
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 19, 0x20);
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 20, 0x02);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 3, &rf_val);
+		rf_val &= (~0x3F);
+		rf_val |= 0x3F;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 3, rf_val);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 4, &rf_val);
+		rf_val &= (~0x3F);
+		rf_val |= 0x3F;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 4, rf_val);
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 5, 0x31);
+	} else {
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 18, 0xF1);
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 19, 0x18);
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 20, 0x02);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 3, &rf_val);
+		rf_val &= (~0x3F);
+		rf_val |= 0x34;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 3, rf_val);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 4, &rf_val);
+		rf_val &= (~0x3F);
+		rf_val |= 0x34;
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 4, rf_val);
+	}
+
+	return 0;
+}
+
+static char rt2800_lp_tx_filter_bw_cal(struct rt2x00_dev *rt2x00dev)
+{
+	unsigned int cnt;
+	u8 bbp_val;
+	char cal_val;
+
+	rt2800_bbp_dcoc_write(rt2x00dev, 0, 0x82);
+
+	cnt = 0;
+	do {
+		usleep_range(500, 2000);
+		rt2800_bbp_read(rt2x00dev, 159, &bbp_val);
+		if (bbp_val == 0x02 || cnt == 20)
+			break;
+
+		cnt++;
+	} while (cnt < 20);
+
+	rt2800_bbp_dcoc_read(rt2x00dev, 0x39, &bbp_val);
+	cal_val = bbp_val & 0x7F;
+	if (cal_val >= 0x40)
+		cal_val -= 128;
+
+	return cal_val;
+}
+
+static void rt2800_bw_filter_calibration(struct rt2x00_dev *rt2x00dev,
+					 bool btxcal)
+{
+	struct rt2800_drv_data *drv_data = rt2x00dev->drv_data;
+	u8 tx_agc_fc = 0, rx_agc_fc = 0, cmm_agc_fc;
+	u8 filter_target;
+	u8 tx_filter_target_20m = 0x09, tx_filter_target_40m = 0x02;
+	u8 rx_filter_target_20m = 0x27, rx_filter_target_40m = 0x31;
+	int loop = 0, is_ht40, cnt;
+	u8 bbp_val, rf_val;
+	char cal_r32_init, cal_r32_val, cal_diff;
+	u8 saverfb5r00, saverfb5r01, saverfb5r03, saverfb5r04, saverfb5r05;
+	u8 saverfb5r06, saverfb5r07;
+	u8 saverfb5r08, saverfb5r17, saverfb5r18, saverfb5r19, saverfb5r20;
+	u8 saverfb5r37, saverfb5r38, saverfb5r39, saverfb5r40, saverfb5r41;
+	u8 saverfb5r42, saverfb5r43, saverfb5r44, saverfb5r45, saverfb5r46;
+	u8 saverfb5r58, saverfb5r59;
+	u8 savebbp159r0, savebbp159r2, savebbpr23;
+	u32 MAC_RF_CONTROL0, MAC_RF_BYPASS0;
+
+	/* Save MAC registers */
+	rt2800_register_read(rt2x00dev, RF_CONTROL0, &MAC_RF_CONTROL0);
+	rt2800_register_read(rt2x00dev, RF_BYPASS0, &MAC_RF_BYPASS0);
+
+	/* save BBP registers */
+	rt2800_bbp_read(rt2x00dev, 23, &savebbpr23);
+
+	rt2800_bbp_dcoc_read(rt2x00dev, 0, &savebbp159r0);
+	rt2800_bbp_dcoc_read(rt2x00dev, 2, &savebbp159r2);
+
+	/* Save RF registers */
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 0, &saverfb5r00);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 1, &saverfb5r01);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 3, &saverfb5r03);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 4, &saverfb5r04);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 5, &saverfb5r05);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 6, &saverfb5r06);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 7, &saverfb5r07);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 8, &saverfb5r08);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 17, &saverfb5r17);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 18, &saverfb5r18);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 19, &saverfb5r19);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 20, &saverfb5r20);
+
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 37, &saverfb5r37);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 38, &saverfb5r38);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 39, &saverfb5r39);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 40, &saverfb5r40);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 41, &saverfb5r41);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 42, &saverfb5r42);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 43, &saverfb5r43);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 44, &saverfb5r44);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 45, &saverfb5r45);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 46, &saverfb5r46);
+
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 58, &saverfb5r58);
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 59, &saverfb5r59);
+
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 0, &rf_val);
+	rf_val |= 0x3;
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 0, rf_val);
+
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 1, &rf_val);
+	rf_val |= 0x1;
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 1, rf_val);
+
+	cnt = 0;
+	do {
+		usleep_range(500, 2000);
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 1, &rf_val);
+		if (((rf_val & 0x1) == 0x00) || (cnt == 40))
+			break;
+		cnt++;
+	} while (cnt < 40);
+
+	rt2800_rfcsr_read_bank(rt2x00dev, 5, 0, &rf_val);
+	rf_val &= (~0x3);
+	rf_val |= 0x1;
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 0, rf_val);
+
+	/* I-3 */
+	rt2800_bbp_read(rt2x00dev, 23, &bbp_val);
+	bbp_val &= (~0x1F);
+	bbp_val |= 0x10;
+	rt2800_bbp_write(rt2x00dev, 23, bbp_val);
+
+	do {
+		/* I-4,5,6,7,8,9 */
+		if (loop == 0) {
+			is_ht40 = false;
+
+			if (btxcal)
+				filter_target = tx_filter_target_20m;
+			else
+				filter_target = rx_filter_target_20m;
+		} else {
+			is_ht40 = true;
+
+			if (btxcal)
+				filter_target = tx_filter_target_40m;
+			else
+				filter_target = rx_filter_target_40m;
+		}
+
+		rt2800_rfcsr_read_bank(rt2x00dev, 5, 8, &rf_val);
+		rf_val &= (~0x04);
+		if (loop == 1)
+			rf_val |= 0x4;
+
+		rt2800_rfcsr_write_bank(rt2x00dev, 5, 8, rf_val);
+
+		rt2800_bbp_core_soft_reset(rt2x00dev, true, is_ht40);
+
+		rt2800_rf_lp_config(rt2x00dev, btxcal);
+		if (btxcal) {
+			tx_agc_fc = 0;
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 58, &rf_val);
+			rf_val &= (~0x7F);
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 58, rf_val);
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 59, &rf_val);
+			rf_val &= (~0x7F);
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 59, rf_val);
+		} else {
+			rx_agc_fc = 0;
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 6, &rf_val);
+			rf_val &= (~0x7F);
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 6, rf_val);
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 7, &rf_val);
+			rf_val &= (~0x7F);
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 7, rf_val);
+		}
+
+		usleep_range(1000, 2000);
+
+		rt2800_bbp_dcoc_read(rt2x00dev, 2, &bbp_val);
+		bbp_val &= (~0x6);
+		rt2800_bbp_dcoc_write(rt2x00dev, 2, bbp_val);
+
+		rt2800_bbp_core_soft_reset(rt2x00dev, false, is_ht40);
+
+		cal_r32_init = rt2800_lp_tx_filter_bw_cal(rt2x00dev);
+
+		rt2800_bbp_dcoc_read(rt2x00dev, 2, &bbp_val);
+		bbp_val |= 0x6;
+		rt2800_bbp_dcoc_write(rt2x00dev, 2, bbp_val);
+do_cal:
+		if (btxcal) {
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 58, &rf_val);
+			rf_val &= (~0x7F);
+			rf_val |= tx_agc_fc;
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 58, rf_val);
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 59, &rf_val);
+			rf_val &= (~0x7F);
+			rf_val |= tx_agc_fc;
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 59, rf_val);
+		} else {
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 6, &rf_val);
+			rf_val &= (~0x7F);
+			rf_val |= rx_agc_fc;
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 6, rf_val);
+			rt2800_rfcsr_read_bank(rt2x00dev, 5, 7, &rf_val);
+			rf_val &= (~0x7F);
+			rf_val |= rx_agc_fc;
+			rt2800_rfcsr_write_bank(rt2x00dev, 5, 7, rf_val);
+		}
+
+		usleep_range(500, 1000);
+
+		rt2800_bbp_core_soft_reset(rt2x00dev, false, is_ht40);
+
+		cal_r32_val = rt2800_lp_tx_filter_bw_cal(rt2x00dev);
+
+		cal_diff = cal_r32_init - cal_r32_val;
+
+		if (btxcal)
+			cmm_agc_fc = tx_agc_fc;
+		else
+			cmm_agc_fc = rx_agc_fc;
+
+		if (((cal_diff > filter_target) && (cmm_agc_fc == 0)) ||
+		    ((cal_diff < filter_target) && (cmm_agc_fc == 0x3f))) {
+			if (btxcal)
+				tx_agc_fc = 0;
+			else
+				rx_agc_fc = 0;
+		} else if ((cal_diff <= filter_target) && (cmm_agc_fc < 0x3f)) {
+			if (btxcal)
+				tx_agc_fc++;
+			else
+				rx_agc_fc++;
+			goto do_cal;
+		}
+
+		if (btxcal) {
+			if (loop == 0)
+				drv_data->tx_calibration_bw20 = tx_agc_fc;
+			else
+				drv_data->tx_calibration_bw40 = tx_agc_fc;
+		} else {
+			if (loop == 0)
+				drv_data->rx_calibration_bw20 = rx_agc_fc;
+			else
+				drv_data->rx_calibration_bw40 = rx_agc_fc;
+		}
+
+		loop++;
+	} while (loop <= 1);
+
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 0, saverfb5r00);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 1, saverfb5r01);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 3, saverfb5r03);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 4, saverfb5r04);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 5, saverfb5r05);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 6, saverfb5r06);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 7, saverfb5r07);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 8, saverfb5r08);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 17, saverfb5r17);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 18, saverfb5r18);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 19, saverfb5r19);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 20, saverfb5r20);
+
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 37, saverfb5r37);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 38, saverfb5r38);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 39, saverfb5r39);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 40, saverfb5r40);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 41, saverfb5r41);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 42, saverfb5r42);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 43, saverfb5r43);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 44, saverfb5r44);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 45, saverfb5r45);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 46, saverfb5r46);
+
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 58, saverfb5r58);
+	rt2800_rfcsr_write_bank(rt2x00dev, 5, 59, saverfb5r59);
+
+	rt2800_bbp_write(rt2x00dev, 23, savebbpr23);
+
+	rt2800_bbp_dcoc_write(rt2x00dev, 0, savebbp159r0);
+	rt2800_bbp_dcoc_write(rt2x00dev, 2, savebbp159r2);
+
+	rt2800_bbp_read(rt2x00dev, 4, &bbp_val);
+	rt2x00_set_field8(&bbp_val, BBP4_BANDWIDTH,
+			  2 * test_bit(CONFIG_CHANNEL_HT40, &rt2x00dev->flags));
+	rt2800_bbp_write(rt2x00dev, 4, bbp_val);
+
+	rt2800_register_write(rt2x00dev, RF_CONTROL0, MAC_RF_CONTROL0);
+	rt2800_register_write(rt2x00dev, RF_BYPASS0, MAC_RF_BYPASS0);
+}
+
+static void rt2800_init_rfcsr_6352(struct rt2x00_dev *rt2x00dev)
+{
+	/* Initialize RF central register to default value */
+	rt2800_rfcsr_write(rt2x00dev, 0, 0x02);
+	rt2800_rfcsr_write(rt2x00dev, 1, 0x03);
+	rt2800_rfcsr_write(rt2x00dev, 2, 0x33);
+	rt2800_rfcsr_write(rt2x00dev, 3, 0xFF);
+	rt2800_rfcsr_write(rt2x00dev, 4, 0x0C);
+	rt2800_rfcsr_write(rt2x00dev, 5, 0x40);
+	rt2800_rfcsr_write(rt2x00dev, 6, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 7, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 8, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 9, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 10, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 11, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 12, rt2x00dev->freq_offset);
+	rt2800_rfcsr_write(rt2x00dev, 13, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 14, 0x40);
+	rt2800_rfcsr_write(rt2x00dev, 15, 0x22);
+	rt2800_rfcsr_write(rt2x00dev, 16, 0x4C);
+	rt2800_rfcsr_write(rt2x00dev, 17, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 18, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 19, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 20, 0xA0);
+	rt2800_rfcsr_write(rt2x00dev, 21, 0x12);
+	rt2800_rfcsr_write(rt2x00dev, 22, 0x07);
+	rt2800_rfcsr_write(rt2x00dev, 23, 0x13);
+	rt2800_rfcsr_write(rt2x00dev, 24, 0xFE);
+	rt2800_rfcsr_write(rt2x00dev, 25, 0x24);
+	rt2800_rfcsr_write(rt2x00dev, 26, 0x7A);
+	rt2800_rfcsr_write(rt2x00dev, 27, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 28, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 29, 0x05);
+	rt2800_rfcsr_write(rt2x00dev, 30, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 31, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 32, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 33, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 34, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 35, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 36, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 37, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 38, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 39, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 40, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 41, 0xD0);
+	rt2800_rfcsr_write(rt2x00dev, 42, 0x5B);
+	rt2800_rfcsr_write(rt2x00dev, 43, 0x00);
+
+	rt2800_rfcsr_write(rt2x00dev, 11, 0x21);
+	if (rt2800_clk_is_20mhz(rt2x00dev))
+		rt2800_rfcsr_write(rt2x00dev, 13, 0x03);
+	else
+		rt2800_rfcsr_write(rt2x00dev, 13, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 14, 0x7C);
+	rt2800_rfcsr_write(rt2x00dev, 16, 0x80);
+	rt2800_rfcsr_write(rt2x00dev, 17, 0x99);
+	rt2800_rfcsr_write(rt2x00dev, 18, 0x99);
+	rt2800_rfcsr_write(rt2x00dev, 19, 0x09);
+	rt2800_rfcsr_write(rt2x00dev, 20, 0x50);
+	rt2800_rfcsr_write(rt2x00dev, 21, 0xB0);
+	rt2800_rfcsr_write(rt2x00dev, 22, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 23, 0x06);
+	rt2800_rfcsr_write(rt2x00dev, 24, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 25, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 26, 0x5D);
+	rt2800_rfcsr_write(rt2x00dev, 27, 0x00);
+	rt2800_rfcsr_write(rt2x00dev, 28, 0x61);
+	rt2800_rfcsr_write(rt2x00dev, 29, 0xB5);
+	rt2800_rfcsr_write(rt2x00dev, 43, 0x02);
+
+	rt2800_rfcsr_write(rt2x00dev, 28, 0x62);
+	rt2800_rfcsr_write(rt2x00dev, 29, 0xAD);
+	rt2800_rfcsr_write(rt2x00dev, 39, 0x80);
+
+	/* Initialize RF channel register to default value */
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 0, 0x03);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 1, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 2, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 3, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 4, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 5, 0x08);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 6, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 7, 0x51);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 8, 0x53);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 9, 0x16);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 10, 0x61);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 11, 0x53);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 12, 0x22);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 13, 0x3D);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 14, 0x06);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 15, 0x13);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 16, 0x22);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 17, 0x27);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 18, 0x02);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 19, 0xA7);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 20, 0x01);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 21, 0x52);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 22, 0x80);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 23, 0xB3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 24, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 25, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 26, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 27, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 28, 0x5C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 29, 0x6B);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 30, 0x6B);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 31, 0x31);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 32, 0x5D);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 33, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 34, 0xE6);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 35, 0x55);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 36, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 37, 0xBB);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 38, 0xB3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 39, 0xB3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 40, 0x03);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 41, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 42, 0x00);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 43, 0xB3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 44, 0xD3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 45, 0xD5);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 46, 0x07);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 47, 0x68);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 48, 0xEF);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 49, 0x1C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 54, 0x07);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 55, 0xA8);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 56, 0x85);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 57, 0x10);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 58, 0x07);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 59, 0x6A);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 60, 0x85);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 61, 0x10);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 62, 0x1C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 63, 0x00);
+
+	rt2800_rfcsr_write_bank(rt2x00dev, 6, 45, 0xC5);
+
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 9, 0x47);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 10, 0x71);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 11, 0x33);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 14, 0x0E);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 17, 0x23);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 19, 0xA4);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 20, 0x02);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 21, 0x12);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 28, 0x1C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 29, 0xEB);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 32, 0x7D);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 34, 0xD6);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 36, 0x08);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 38, 0xB4);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 43, 0xD3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 44, 0xB3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 45, 0xD5);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 46, 0x27);
+	rt2800_rfcsr_write_bank(rt2x00dev, 4, 47, 0x67);
+	rt2800_rfcsr_write_bank(rt2x00dev, 6, 47, 0x69);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 48, 0xFF);
+	rt2800_rfcsr_write_bank(rt2x00dev, 4, 54, 0x27);
+	rt2800_rfcsr_write_bank(rt2x00dev, 6, 54, 0x20);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 55, 0x66);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 56, 0xFF);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 57, 0x1C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 58, 0x20);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 59, 0x6B);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 60, 0xF7);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 61, 0x09);
+
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 10, 0x51);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 14, 0x06);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 19, 0xA7);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 28, 0x2C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 55, 0x64);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 8, 0x51);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 9, 0x36);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 11, 0x53);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 14, 0x16);
+
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 47, 0x6C);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 48, 0xFC);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 49, 0x1F);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 54, 0x27);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 55, 0x66);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 59, 0x6B);
+
+	/* Initialize RF channel register for DRQFN */
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 43, 0xD3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 44, 0xE3);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 45, 0xE5);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 47, 0x28);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 55, 0x68);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 56, 0xF7);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 58, 0x02);
+	rt2800_rfcsr_write_chanreg(rt2x00dev, 60, 0xC7);
+
+	/* Initialize RF DC calibration register to default value */
+	rt2800_rfcsr_write_dccal(rt2x00dev, 0, 0x47);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 1, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 2, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 3, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 4, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 5, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 6, 0x10);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 7, 0x10);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 8, 0x04);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 9, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 10, 0x07);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 11, 0x01);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 12, 0x07);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 13, 0x07);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 14, 0x07);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 15, 0x20);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 16, 0x22);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 17, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 18, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 19, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 20, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 21, 0xF1);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 22, 0x11);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 23, 0x02);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 24, 0x41);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 25, 0x20);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 26, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 27, 0xD7);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 28, 0xA2);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 29, 0x20);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 30, 0x49);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 31, 0x20);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 32, 0x04);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 33, 0xF1);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 34, 0xA1);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 35, 0x01);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 41, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 42, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 43, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 44, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 45, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 46, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 47, 0x3E);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 48, 0x3D);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 49, 0x3E);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 50, 0x3D);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 51, 0x3E);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 52, 0x3D);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 53, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 54, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 55, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 56, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 57, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 58, 0x10);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 59, 0x10);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 60, 0x0A);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 61, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 62, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 63, 0x00);
+
+	rt2800_rfcsr_write_dccal(rt2x00dev, 3, 0x08);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 4, 0x04);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 5, 0x20);
+
+	rt2800_rfcsr_write_dccal(rt2x00dev, 5, 0x00);
+	rt2800_rfcsr_write_dccal(rt2x00dev, 17, 0x7C);
+
+	rt2800_bw_filter_calibration(rt2x00dev, true);
+	rt2800_bw_filter_calibration(rt2x00dev, false);
+}
+
 static void rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev)
 {
 	if (rt2800_is_305x_soc(rt2x00dev)) {
@@ -6884,6 +8297,9 @@ static void rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev)
 	case RT5592:
 		rt2800_init_rfcsr_5592(rt2x00dev);
 		break;
+	case RT6352:
+		rt2800_init_rfcsr_6352(rt2x00dev);
+		break;
 	}
 }
 
@@ -7250,7 +8666,8 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	 */
 	if (rt2x00_rt(rt2x00dev, RT3290) ||
 	    rt2x00_rt(rt2x00dev, RT5390) ||
-	    rt2x00_rt(rt2x00dev, RT5392))
+	    rt2x00_rt(rt2x00dev, RT5392) ||
+	    rt2x00_rt(rt2x00dev, RT6352))
 		rt2800_eeprom_read(rt2x00dev, EEPROM_CHIP_ID, &rf);
 	else if (rt2x00_rt(rt2x00dev, RT3352))
 		rf = RF3322;
@@ -7282,6 +8699,7 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	case RF5390:
 	case RF5392:
 	case RF5592:
+	case RF7620:
 		break;
 	default:
 		rt2x00_err(rt2x00dev, "Invalid RF chipset 0x%04x detected\n",
@@ -7382,13 +8800,13 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	rt2800_eeprom_read(rt2x00dev, EEPROM_NIC_CONF1, &eeprom);
 
 	if (rt2x00_rt(rt2x00dev, RT3352)) {
-		if (!rt2x00_get_field16(eeprom,
+		if (rt2x00_get_field16(eeprom,
 		    EEPROM_NIC_CONF1_EXTERNAL_TX0_PA_3352))
-		    __set_bit(CAPABILITY_INTERNAL_PA_TX0,
+		    __set_bit(CAPABILITY_EXTERNAL_PA_TX0,
 			      &rt2x00dev->cap_flags);
-		if (!rt2x00_get_field16(eeprom,
+		if (rt2x00_get_field16(eeprom,
 		    EEPROM_NIC_CONF1_EXTERNAL_TX1_PA_3352))
-		    __set_bit(CAPABILITY_INTERNAL_PA_TX1,
+		    __set_bit(CAPABILITY_EXTERNAL_PA_TX1,
 			      &rt2x00dev->cap_flags);
 	}
 
@@ -7689,6 +9107,23 @@ static const struct rf_channel rf_vals_5592_xtal40[] = {
 	{196, 83, 0, 12, 1},
 };
 
+static const struct rf_channel rf_vals_7620[] = {
+	{1, 0x50, 0x99, 0x99, 1},
+	{2, 0x50, 0x44, 0x44, 2},
+	{3, 0x50, 0xEE, 0xEE, 2},
+	{4, 0x50, 0x99, 0x99, 3},
+	{5, 0x51, 0x44, 0x44, 0},
+	{6, 0x51, 0xEE, 0xEE, 0},
+	{7, 0x51, 0x99, 0x99, 1},
+	{8, 0x51, 0x44, 0x44, 2},
+	{9, 0x51, 0xEE, 0xEE, 2},
+	{10, 0x51, 0x99, 0x99, 3},
+	{11, 0x52, 0x44, 0x44, 0},
+	{12, 0x52, 0xEE, 0xEE, 0},
+	{13, 0x52, 0x99, 0x99, 1},
+	{14, 0x52, 0x33, 0x33, 3},
+};
+
 static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev)
 {
 	struct hw_mode_spec *spec = &rt2x00dev->spec;
@@ -7792,6 +9227,11 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev)
 			spec->channels = rf_vals_3x;
 		break;
 
+	case RF7620:
+		spec->num_channels = ARRAY_SIZE(rf_vals_7620);
+		spec->channels = rf_vals_7620;
+		break;
+
 	case RF3052:
 	case RF3053:
 		spec->num_channels = ARRAY_SIZE(rf_vals_3x);
@@ -7923,6 +9363,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev)
 	case RF5390:
 	case RF5392:
 	case RF5592:
+	case RF7620:
 		__set_bit(CAPABILITY_VCO_RECALIBRATION, &rt2x00dev->cap_flags);
 		break;
 	}
@@ -7967,6 +9408,9 @@ static int rt2800_probe_rt(struct rt2x00_dev *rt2x00dev)
 		return -ENODEV;
 	}
 
+	if (rt == RT5390 && rt2x00_is_soc(rt2x00dev))
+		rt = RT6352;
+
 	rt2x00_set_rt(rt2x00dev, rt, rev);
 
 	return 0;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h
index 0a8b4df665fe..f357531d9488 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h
@@ -20,6 +20,34 @@
 #ifndef RT2800LIB_H
 #define RT2800LIB_H
 
+/*
+ * Hardware has 255 WCID table entries. First 32 entries are reserved for
+ * shared keys. Since parts of the pairwise key table might be shared with
+ * the beacon frame buffers 6 & 7 we could only use the first 222 entries.
+ */
+#define WCID_START	33
+#define WCID_END	222
+#define STA_IDS_SIZE	(WCID_END - WCID_START + 2)
+
+/* RT2800 driver data structure */
+struct rt2800_drv_data {
+	u8 calibration_bw20;
+	u8 calibration_bw40;
+	char rx_calibration_bw20;
+	char rx_calibration_bw40;
+	char tx_calibration_bw20;
+	char tx_calibration_bw40;
+	u8 bbp25;
+	u8 bbp26;
+	u8 txmixer_gain_24g;
+	u8 txmixer_gain_5g;
+	u8 max_psdu;
+	unsigned int tbtt_tick;
+	unsigned int ampdu_factor_cnt[4];
+	DECLARE_BITMAP(sta_ids, STA_IDS_SIZE);
+	struct ieee80211_sta *wcid_to_sta[STA_IDS_SIZE];
+};
+
 struct rt2800_ops {
 	void (*register_read)(struct rt2x00_dev *rt2x00dev,
 			      const unsigned int offset, u32 *value);
@@ -167,7 +195,8 @@ void rt2800_write_tx_data(struct queue_entry *entry,
 			  struct txentry_desc *txdesc);
 void rt2800_process_rxwi(struct queue_entry *entry, struct rxdone_entry_desc *txdesc);
 
-void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32* txwi);
+void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi,
+			 bool match);
 
 void rt2800_write_beacon(struct queue_entry *entry, struct txentry_desc *txdesc);
 void rt2800_clear_beacon(struct queue_entry *entry);
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c b/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c
index de4790b41be7..3ab3b5323897 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800mmio.c
@@ -239,7 +239,7 @@ static bool rt2800mmio_txdone_release_entries(struct queue_entry *entry,
 {
 	if (test_bit(ENTRY_DATA_STATUS_SET, &entry->flags)) {
 		rt2800_txdone_entry(entry, entry->status,
-				    rt2800mmio_get_txwi(entry));
+				    rt2800mmio_get_txwi(entry), true);
 		return false;
 	}
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
index 205a7b8ac8a7..f11e3f532a84 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
@@ -501,8 +501,7 @@ static int rt2800usb_get_tx_data_len(struct queue_entry *entry)
 /*
  * TX control handlers
  */
-static enum txdone_entry_desc_flags
-rt2800usb_txdone_entry_check(struct queue_entry *entry, u32 reg)
+static bool rt2800usb_txdone_entry_check(struct queue_entry *entry, u32 reg)
 {
 	__le32 *txwi;
 	u32 word;
@@ -515,7 +514,7 @@ rt2800usb_txdone_entry_check(struct queue_entry *entry, u32 reg)
 	 * frame.
 	 */
 	if (test_bit(ENTRY_DATA_IO_FAILED, &entry->flags))
-		return TXDONE_FAILURE;
+		return false;
 
 	wcid	= rt2x00_get_field32(reg, TX_STA_FIFO_WCID);
 	ack	= rt2x00_get_field32(reg, TX_STA_FIFO_TX_ACK_REQUIRED);
@@ -537,10 +536,10 @@ rt2800usb_txdone_entry_check(struct queue_entry *entry, u32 reg)
 		rt2x00_dbg(entry->queue->rt2x00dev,
 			   "TX status report missed for queue %d entry %d\n",
 			   entry->queue->qid, entry->entry_idx);
-		return TXDONE_UNKNOWN;
+		return false;
 	}
 
-	return TXDONE_SUCCESS;
+	return true;
 }
 
 static void rt2800usb_txdone(struct rt2x00_dev *rt2x00dev)
@@ -549,7 +548,7 @@ static void rt2800usb_txdone(struct rt2x00_dev *rt2x00dev)
 	struct queue_entry *entry;
 	u32 reg;
 	u8 qid;
-	enum txdone_entry_desc_flags done_status;
+	bool match;
 
 	while (kfifo_get(&rt2x00dev->txstatus_fifo, &reg)) {
 		/*
@@ -574,11 +573,8 @@ static void rt2800usb_txdone(struct rt2x00_dev *rt2x00dev)
 			break;
 		}
 
-		done_status = rt2800usb_txdone_entry_check(entry, reg);
-		if (likely(done_status == TXDONE_SUCCESS))
-			rt2800_txdone_entry(entry, reg, rt2800usb_get_txwi(entry));
-		else
-			rt2x00lib_txdone_noinfo(entry, done_status);
+		match = rt2800usb_txdone_entry_check(entry, reg);
+		rt2800_txdone_entry(entry, reg, rt2800usb_get_txwi(entry), match);
 	}
 }
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 340787894c69..1bc353eafe37 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -174,6 +174,7 @@ struct rt2x00_chip {
 #define RT5390		0x5390  /* 2.4GHz */
 #define RT5392		0x5392  /* 2.4GHz */
 #define RT5592		0x5592
+#define RT6352		0x6352  /* WSOC 2.4GHz */
 
 	u16 rf;
 	u16 rev;
@@ -718,8 +719,8 @@ enum rt2x00_capability_flags {
 	CAPABILITY_DOUBLE_ANTENNA,
 	CAPABILITY_BT_COEXIST,
 	CAPABILITY_VCO_RECALIBRATION,
-	CAPABILITY_INTERNAL_PA_TX0,
-	CAPABILITY_INTERNAL_PA_TX1,
+	CAPABILITY_EXTERNAL_PA_TX0,
+	CAPABILITY_EXTERNAL_PA_TX1,
 };
 
 /*
@@ -1396,7 +1397,7 @@ void rt2x00queue_flush_queues(struct rt2x00_dev *rt2x00dev, bool drop);
  * rt2x00debug_dump_frame - Dump a frame to userspace through debugfs.
  * @rt2x00dev: Pointer to &struct rt2x00_dev.
  * @type: The type of frame that is being dumped.
- * @skb: The skb containing the frame to be dumped.
+ * @entry: The queue entry containing the frame to be dumped.
  */
 #ifdef CONFIG_RT2X00_LIB_DEBUGFS
 void rt2x00debug_dump_frame(struct rt2x00_dev *rt2x00dev,
@@ -1425,6 +1426,8 @@ void rt2x00lib_dmastart(struct queue_entry *entry);
 void rt2x00lib_dmadone(struct queue_entry *entry);
 void rt2x00lib_txdone(struct queue_entry *entry,
 		      struct txdone_entry_desc *txdesc);
+void rt2x00lib_txdone_nomatch(struct queue_entry *entry,
+			      struct txdone_entry_desc *txdesc);
 void rt2x00lib_txdone_noinfo(struct queue_entry *entry, u32 status);
 void rt2x00lib_rxdone(struct queue_entry *entry, gfp_t gfp);
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
index dd6678109b7e..357c0941aaad 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
@@ -313,73 +313,14 @@ static inline int rt2x00lib_txdone_bar_status(struct queue_entry *entry)
 	return ret;
 }
 
-void rt2x00lib_txdone(struct queue_entry *entry,
-		      struct txdone_entry_desc *txdesc)
+static void rt2x00lib_fill_tx_status(struct rt2x00_dev *rt2x00dev,
+				     struct ieee80211_tx_info *tx_info,
+				     struct skb_frame_desc *skbdesc,
+				     struct txdone_entry_desc *txdesc,
+				     bool success)
 {
-	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
-	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(entry->skb);
-	struct skb_frame_desc *skbdesc = get_skb_frame_desc(entry->skb);
-	unsigned int header_length, i;
 	u8 rate_idx, rate_flags, retry_rates;
-	u8 skbdesc_flags = skbdesc->flags;
-	bool success;
-
-	/*
-	 * Unmap the skb.
-	 */
-	rt2x00queue_unmap_skb(entry);
-
-	/*
-	 * Remove the extra tx headroom from the skb.
-	 */
-	skb_pull(entry->skb, rt2x00dev->extra_tx_headroom);
-
-	/*
-	 * Signal that the TX descriptor is no longer in the skb.
-	 */
-	skbdesc->flags &= ~SKBDESC_DESC_IN_SKB;
-
-	/*
-	 * Determine the length of 802.11 header.
-	 */
-	header_length = ieee80211_get_hdrlen_from_skb(entry->skb);
-
-	/*
-	 * Remove L2 padding which was added during
-	 */
-	if (rt2x00_has_cap_flag(rt2x00dev, REQUIRE_L2PAD))
-		rt2x00queue_remove_l2pad(entry->skb, header_length);
-
-	/*
-	 * If the IV/EIV data was stripped from the frame before it was
-	 * passed to the hardware, we should now reinsert it again because
-	 * mac80211 will expect the same data to be present it the
-	 * frame as it was passed to us.
-	 */
-	if (rt2x00_has_cap_hw_crypto(rt2x00dev))
-		rt2x00crypto_tx_insert_iv(entry->skb, header_length);
-
-	/*
-	 * Send frame to debugfs immediately, after this call is completed
-	 * we are going to overwrite the skb->cb array.
-	 */
-	rt2x00debug_dump_frame(rt2x00dev, DUMP_FRAME_TXDONE, entry);
-
-	/*
-	 * Determine if the frame has been successfully transmitted and
-	 * remove BARs from our check list while checking for their
-	 * TX status.
-	 */
-	success =
-	    rt2x00lib_txdone_bar_status(entry) ||
-	    test_bit(TXDONE_SUCCESS, &txdesc->flags) ||
-	    test_bit(TXDONE_UNKNOWN, &txdesc->flags);
-
-	/*
-	 * Update TX statistics.
-	 */
-	rt2x00dev->link.qual.tx_success += success;
-	rt2x00dev->link.qual.tx_failed += !success;
+	int i;
 
 	rate_idx = skbdesc->tx_rate_idx;
 	rate_flags = skbdesc->tx_rate_flags;
@@ -416,6 +357,9 @@ void rt2x00lib_txdone(struct queue_entry *entry,
 	if (i < (IEEE80211_TX_MAX_RATES - 1))
 		tx_info->status.rates[i].idx = -1; /* terminate */
 
+	if (test_bit(TXDONE_NO_ACK_REQ, &txdesc->flags))
+		tx_info->flags |= IEEE80211_TX_CTL_NO_ACK;
+
 	if (!(tx_info->flags & IEEE80211_TX_CTL_NO_ACK)) {
 		if (success)
 			tx_info->flags |= IEEE80211_TX_STAT_ACK;
@@ -434,7 +378,8 @@ void rt2x00lib_txdone(struct queue_entry *entry,
 	 */
 	if (test_bit(TXDONE_AMPDU, &txdesc->flags) ||
 	    tx_info->flags & IEEE80211_TX_CTL_AMPDU) {
-		tx_info->flags |= IEEE80211_TX_STAT_AMPDU;
+		tx_info->flags |= IEEE80211_TX_STAT_AMPDU |
+				  IEEE80211_TX_CTL_AMPDU;
 		tx_info->status.ampdu_len = 1;
 		tx_info->status.ampdu_ack_len = success ? 1 : 0;
 
@@ -448,21 +393,11 @@ void rt2x00lib_txdone(struct queue_entry *entry,
 		else
 			rt2x00dev->low_level_stats.dot11RTSFailureCount++;
 	}
+}
 
-	/*
-	 * Only send the status report to mac80211 when it's a frame
-	 * that originated in mac80211. If this was a extra frame coming
-	 * through a mac80211 library call (RTS/CTS) then we should not
-	 * send the status report back.
-	 */
-	if (!(skbdesc_flags & SKBDESC_NOT_MAC80211)) {
-		if (rt2x00_has_cap_flag(rt2x00dev, REQUIRE_TASKLET_CONTEXT))
-			ieee80211_tx_status(rt2x00dev->hw, entry->skb);
-		else
-			ieee80211_tx_status_ni(rt2x00dev->hw, entry->skb);
-	} else
-		dev_kfree_skb_any(entry->skb);
-
+static void rt2x00lib_clear_entry(struct rt2x00_dev *rt2x00dev,
+				  struct queue_entry *entry)
+{
 	/*
 	 * Make this entry available for reuse.
 	 */
@@ -485,6 +420,143 @@ void rt2x00lib_txdone(struct queue_entry *entry,
 		rt2x00queue_unpause_queue(entry->queue);
 	spin_unlock_bh(&entry->queue->tx_lock);
 }
+
+void rt2x00lib_txdone_nomatch(struct queue_entry *entry,
+			      struct txdone_entry_desc *txdesc)
+{
+	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
+	struct skb_frame_desc *skbdesc = get_skb_frame_desc(entry->skb);
+	struct ieee80211_tx_info txinfo = {};
+	bool success;
+
+	/*
+	 * Unmap the skb.
+	 */
+	rt2x00queue_unmap_skb(entry);
+
+	/*
+	 * Signal that the TX descriptor is no longer in the skb.
+	 */
+	skbdesc->flags &= ~SKBDESC_DESC_IN_SKB;
+
+	/*
+	 * Send frame to debugfs immediately, after this call is completed
+	 * we are going to overwrite the skb->cb array.
+	 */
+	rt2x00debug_dump_frame(rt2x00dev, DUMP_FRAME_TXDONE, entry);
+
+	/*
+	 * Determine if the frame has been successfully transmitted and
+	 * remove BARs from our check list while checking for their
+	 * TX status.
+	 */
+	success =
+	    rt2x00lib_txdone_bar_status(entry) ||
+	    test_bit(TXDONE_SUCCESS, &txdesc->flags);
+
+	if (!test_bit(TXDONE_UNKNOWN, &txdesc->flags)) {
+		/*
+		 * Update TX statistics.
+		 */
+		rt2x00dev->link.qual.tx_success += success;
+		rt2x00dev->link.qual.tx_failed += !success;
+
+		rt2x00lib_fill_tx_status(rt2x00dev, &txinfo, skbdesc, txdesc,
+					 success);
+		ieee80211_tx_status_noskb(rt2x00dev->hw, skbdesc->sta, &txinfo);
+	}
+
+	dev_kfree_skb_any(entry->skb);
+	rt2x00lib_clear_entry(rt2x00dev, entry);
+}
+EXPORT_SYMBOL_GPL(rt2x00lib_txdone_nomatch);
+
+void rt2x00lib_txdone(struct queue_entry *entry,
+		      struct txdone_entry_desc *txdesc)
+{
+	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
+	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(entry->skb);
+	struct skb_frame_desc *skbdesc = get_skb_frame_desc(entry->skb);
+	u8 skbdesc_flags = skbdesc->flags;
+	unsigned int header_length;
+	bool success;
+
+	/*
+	 * Unmap the skb.
+	 */
+	rt2x00queue_unmap_skb(entry);
+
+	/*
+	 * Remove the extra tx headroom from the skb.
+	 */
+	skb_pull(entry->skb, rt2x00dev->extra_tx_headroom);
+
+	/*
+	 * Signal that the TX descriptor is no longer in the skb.
+	 */
+	skbdesc->flags &= ~SKBDESC_DESC_IN_SKB;
+
+	/*
+	 * Determine the length of 802.11 header.
+	 */
+	header_length = ieee80211_get_hdrlen_from_skb(entry->skb);
+
+	/*
+	 * Remove L2 padding which was added during
+	 */
+	if (rt2x00_has_cap_flag(rt2x00dev, REQUIRE_L2PAD))
+		rt2x00queue_remove_l2pad(entry->skb, header_length);
+
+	/*
+	 * If the IV/EIV data was stripped from the frame before it was
+	 * passed to the hardware, we should now reinsert it again because
+	 * mac80211 will expect the same data to be present it the
+	 * frame as it was passed to us.
+	 */
+	if (rt2x00_has_cap_hw_crypto(rt2x00dev))
+		rt2x00crypto_tx_insert_iv(entry->skb, header_length);
+
+	/*
+	 * Send frame to debugfs immediately, after this call is completed
+	 * we are going to overwrite the skb->cb array.
+	 */
+	rt2x00debug_dump_frame(rt2x00dev, DUMP_FRAME_TXDONE, entry);
+
+	/*
+	 * Determine if the frame has been successfully transmitted and
+	 * remove BARs from our check list while checking for their
+	 * TX status.
+	 */
+	success =
+	    rt2x00lib_txdone_bar_status(entry) ||
+	    test_bit(TXDONE_SUCCESS, &txdesc->flags) ||
+	    test_bit(TXDONE_UNKNOWN, &txdesc->flags);
+
+	/*
+	 * Update TX statistics.
+	 */
+	rt2x00dev->link.qual.tx_success += success;
+	rt2x00dev->link.qual.tx_failed += !success;
+
+	rt2x00lib_fill_tx_status(rt2x00dev, tx_info, skbdesc, txdesc, success);
+
+	/*
+	 * Only send the status report to mac80211 when it's a frame
+	 * that originated in mac80211. If this was a extra frame coming
+	 * through a mac80211 library call (RTS/CTS) then we should not
+	 * send the status report back.
+	 */
+	if (!(skbdesc_flags & SKBDESC_NOT_MAC80211)) {
+		if (rt2x00_has_cap_flag(rt2x00dev, REQUIRE_TASKLET_CONTEXT))
+			ieee80211_tx_status(rt2x00dev->hw, entry->skb);
+		else
+			ieee80211_tx_status_ni(rt2x00dev->hw, entry->skb);
+	} else {
+		dev_kfree_skb_any(entry->skb);
+	}
+
+	rt2x00lib_clear_entry(rt2x00dev, entry);
+}
 EXPORT_SYMBOL_GPL(rt2x00lib_txdone);
 
 void rt2x00lib_txdone_noinfo(struct queue_entry *entry, u32 status)
@@ -753,7 +825,7 @@ void rt2x00lib_rxdone(struct queue_entry *entry, gfp_t gfp)
 	rate_idx = rt2x00lib_rxdone_read_signal(rt2x00dev, &rxdesc);
 	if (rxdesc.rate_mode == RATE_MODE_HT_MIX ||
 	    rxdesc.rate_mode == RATE_MODE_HT_GREENFIELD)
-		rxdesc.flags |= RX_FLAG_HT;
+		rxdesc.encoding = RX_ENC_HT;
 
 	/*
 	 * Check if this is a beacon, and more frames have been
@@ -793,6 +865,9 @@ void rt2x00lib_rxdone(struct queue_entry *entry, gfp_t gfp)
 	rx_status->rate_idx = rate_idx;
 	rx_status->signal = rxdesc.rssi;
 	rx_status->flag = rxdesc.flags;
+	rx_status->enc_flags = rxdesc.enc_flags;
+	rx_status->encoding = rxdesc.encoding;
+	rx_status->bw = rxdesc.bw;
 	rx_status->antenna = rt2x00dev->link.ant.active.rx;
 
 	ieee80211_rx_ni(rt2x00dev->hw, entry->skb);
@@ -1384,6 +1459,9 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 
 	rt2x00dev->hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
 
+	wiphy_ext_feature_set(rt2x00dev->hw->wiphy,
+			      NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	/*
 	 * Initialize ieee80211 structure.
 	 */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index e1660b92b20c..a2c1ca5c76d1 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -372,15 +372,16 @@ static void rt2x00queue_create_tx_descriptor_ht(struct rt2x00_dev *rt2x00dev,
 
 	/*
 	 * Determine IFS values
-	 * - Use TXOP_BACKOFF for management frames except beacons
+	 * - Use TXOP_BACKOFF for probe and management frames except beacons
 	 * - Use TXOP_SIFS for fragment bursts
 	 * - Use TXOP_HTTXOP for everything else
 	 *
 	 * Note: rt2800 devices won't use CTS protection (if used)
 	 * for frames not transmitted with TXOP_HTTXOP
 	 */
-	if (ieee80211_is_mgmt(hdr->frame_control) &&
-	    !ieee80211_is_beacon(hdr->frame_control))
+	if ((ieee80211_is_mgmt(hdr->frame_control) &&
+	     !ieee80211_is_beacon(hdr->frame_control)) ||
+	    (tx_info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE))
 		txdesc->u.ht.txop = TXOP_BACKOFF;
 	else if (!(tx_info->flags & IEEE80211_TX_CTL_FIRST_FRAGMENT))
 		txdesc->u.ht.txop = TXOP_SIFS;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.h b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.h
index 22d18818e850..6055f36211b9 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.h
@@ -102,7 +102,7 @@ enum skb_frame_desc_flags {
  *	of the scope of the skb->data pointer.
  * @iv: IV/EIV data used during encryption/decryption.
  * @skb_dma: (PCI-only) the DMA address associated with the sk buffer.
- * @entry: The entry to which this sk buffer belongs.
+ * @sta: The station where sk buffer was sent.
  */
 struct skb_frame_desc {
 	u8 flags;
@@ -116,6 +116,7 @@ struct skb_frame_desc {
 	__le32 iv[2];
 
 	dma_addr_t skb_dma;
+	struct ieee80211_sta *sta;
 };
 
 /**
@@ -183,6 +184,9 @@ struct rxdone_entry_desc {
 	int flags;
 	int dev_flags;
 	u16 rate_mode;
+	u16 enc_flags;
+	enum mac80211_rx_encoding encoding;
+	enum rate_info_bw bw;
 	u8 cipher;
 	u8 cipher_status;
 
@@ -214,6 +218,7 @@ enum txdone_entry_desc_flags {
 	TXDONE_FAILURE,
 	TXDONE_EXCESSIVE_RETRY,
 	TXDONE_AMPDU,
+	TXDONE_NO_ACK_REQ,
 };
 
 /**
diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c
index e895a84481da..225c1c8851cc 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c
@@ -315,7 +315,7 @@ static void rtl8180_handle_rx(struct ieee80211_hw *dev)
 			rx_status.mactime = tsft;
 			rx_status.flag |= RX_FLAG_MACTIME_START;
 			if (flags & RTL818X_RX_DESC_FLAG_SPLCP)
-				rx_status.flag |= RX_FLAG_SHORTPRE;
+				rx_status.enc_flags |= RX_ENC_FLAG_SHORTPRE;
 			if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 				rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 
@@ -1877,6 +1877,8 @@ static int rtl8180_probe(struct pci_dev *pdev,
 	else
 		ieee80211_hw_set(dev, SIGNAL_UNSPEC);
 
+	wiphy_ext_feature_set(dev->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	rtl8180_eeprom_read(priv);
 
 	switch (priv->rf_type) {
diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
index 231f84db9ab0..35fe991dcc56 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
@@ -389,7 +389,7 @@ static void rtl8187_rx_cb(struct urb *urb)
 	rx_status.band = dev->conf.chandef.chan->band;
 	rx_status.flag |= RX_FLAG_MACTIME_START;
 	if (flags & RTL818X_RX_DESC_FLAG_SPLCP)
-		rx_status.flag |= RX_FLAG_SHORTPRE;
+		rx_status.enc_flags |= RX_ENC_FLAG_SHORTPRE;
 	if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 		rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
@@ -946,8 +946,7 @@ static int rtl8187_start(struct ieee80211_hw *dev)
 		      (7 << 13 /* RX FIFO threshold NONE */) |
 		      (7 << 10 /* MAX RX DMA */) |
 		      RTL818X_RX_CONF_RX_AUTORESETPHY |
-		      RTL818X_RX_CONF_ONLYERLPKT |
-		      RTL818X_RX_CONF_MULTICAST;
+		      RTL818X_RX_CONF_ONLYERLPKT;
 		priv->rx_conf = reg;
 		rtl818x_iowrite32(priv, &priv->map->RX_CONF, reg);
 
@@ -1319,12 +1318,11 @@ static void rtl8187_configure_filter(struct ieee80211_hw *dev,
 		priv->rx_conf ^= RTL818X_RX_CONF_FCS;
 	if (changed_flags & FIF_CONTROL)
 		priv->rx_conf ^= RTL818X_RX_CONF_CTRL;
-	if (changed_flags & FIF_OTHER_BSS)
-		priv->rx_conf ^= RTL818X_RX_CONF_MONITOR;
-	if (*total_flags & FIF_ALLMULTI || multicast > 0)
-		priv->rx_conf |= RTL818X_RX_CONF_MULTICAST;
+	if (*total_flags & FIF_OTHER_BSS ||
+	    *total_flags & FIF_ALLMULTI || multicast > 0)
+		priv->rx_conf |= RTL818X_RX_CONF_MONITOR;
 	else
-		priv->rx_conf &= ~RTL818X_RX_CONF_MULTICAST;
+		priv->rx_conf &= ~RTL818X_RX_CONF_MONITOR;
 
 	*total_flags = 0;
 
@@ -1332,10 +1330,10 @@ static void rtl8187_configure_filter(struct ieee80211_hw *dev,
 		*total_flags |= FIF_FCSFAIL;
 	if (priv->rx_conf & RTL818X_RX_CONF_CTRL)
 		*total_flags |= FIF_CONTROL;
-	if (priv->rx_conf & RTL818X_RX_CONF_MONITOR)
+	if (priv->rx_conf & RTL818X_RX_CONF_MONITOR) {
 		*total_flags |= FIF_OTHER_BSS;
-	if (priv->rx_conf & RTL818X_RX_CONF_MULTICAST)
 		*total_flags |= FIF_ALLMULTI;
+	}
 
 	rtl818x_iowrite32_async(priv, &priv->map->RX_CONF, priv->rx_conf);
 }
@@ -1609,6 +1607,8 @@ static int rtl8187_probe(struct usb_interface *intf,
 	dev->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
 				      BIT(NL80211_IFTYPE_ADHOC) ;
 
+	wiphy_ext_feature_set(dev->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	if ((id->driver_info == DEVICE_RTL8187) && priv->is_rtl8187b)
 		printk(KERN_INFO "rtl8187: inconsistency between id with OEM"
 		       " info!\n");
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index e544dd1d618c..39d56313bc94 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -5041,7 +5041,7 @@ static void rtl8xxxu_rx_parse_phystats(struct rtl8xxxu_priv *priv,
 				       u32 rxmcs)
 {
 	if (phy_stats->sgi_en)
-		rx_status->flag |= RX_FLAG_SHORT_GI;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (rxmcs < DESC_RATE_6M) {
 		/*
@@ -5267,10 +5267,10 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
 		if (rx_desc->crc32)
 			rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 		if (rx_desc->bw)
-			rx_status->flag |= RX_FLAG_40MHZ;
+			rx_status->bw = RATE_INFO_BW_40;
 
 		if (rx_desc->rxht) {
-			rx_status->flag |= RX_FLAG_HT;
+			rx_status->encoding = RX_ENC_HT;
 			rx_status->rate_idx = rx_desc->rxmcs - DESC_RATE_MCS0;
 		} else {
 			rx_status->rate_idx = rx_desc->rxmcs;
@@ -5337,10 +5337,10 @@ int rtl8xxxu_parse_rxdesc24(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
 	if (rx_desc->crc32)
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 	if (rx_desc->bw)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (rx_desc->rxmcs >= DESC_RATE_MCS0) {
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 		rx_status->rate_idx = rx_desc->rxmcs - DESC_RATE_MCS0;
 	} else {
 		rx_status->rate_idx = rx_desc->rxmcs;
@@ -6135,6 +6135,8 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
 	ieee80211_hw_set(hw, AMPDU_AGGREGATION);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	ret = ieee80211_register_hw(priv->hw);
 	if (ret) {
 		dev_err(&udev->dev, "%s: Failed to register: %i\n",
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index caea350f05aa..bdc379178e87 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -1742,12 +1742,14 @@ void rtl_c2hcmd_enqueue(struct ieee80211_hw *hw, u8 tag, u8 len, u8 *val)
 	unsigned long flags;
 	struct rtl_c2hcmd *c2hcmd;
 
-	c2hcmd = kmalloc(sizeof(*c2hcmd), GFP_KERNEL);
+	c2hcmd = kmalloc(sizeof(*c2hcmd),
+			 in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
 
 	if (!c2hcmd)
 		goto label_err;
 
-	c2hcmd->val = kmalloc(len, GFP_KERNEL);
+	c2hcmd->val = kmalloc(len,
+			      in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
 
 	if (!c2hcmd->val)
 		goto label_err2;
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.c
index ffa1f438424d..57e633dbf9a9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.c
@@ -44,7 +44,7 @@ static struct coex_dm_8192e_2ant *coex_dm = &glcoex_dm_8192e_2ant;
 static struct coex_sta_8192e_2ant glcoex_sta_8192e_2ant;
 static struct coex_sta_8192e_2ant *coex_sta = &glcoex_sta_8192e_2ant;
 
-static const char *const GLBtInfoSrc8192e2Ant[] = {
+static const char *const glbt_info_src_8192e_2ant[] = {
 	"BT Info[wifi fw]",
 	"BT Info[bt rsp]",
 	"BT Info[bt auto report]",
@@ -57,31 +57,31 @@ static u32 glcoex_ver_8192e_2ant = 0x34;
  *   local function proto type if needed
  **************************************************************/
 /**************************************************************
- *   local function start with halbtc8192e2ant_
+ *   local function start with btc8192e2ant_
  **************************************************************/
-static u8 halbtc8192e2ant_btrssi_state(struct btc_coexist *btcoexist,
-					u8 level_num, u8 rssi_thresh,
-				       u8 rssi_thresh1)
+static u8 btc8192e2ant_bt_rssi_state(struct btc_coexist *btcoexist,
+				     u8 level_num, u8 rssi_thresh,
+				     u8 rssi_thresh1)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	int btrssi = 0;
-	u8 btrssi_state = coex_sta->pre_bt_rssi_state;
+	int bt_rssi = 0;
+	u8 bt_rssi_state = coex_sta->pre_bt_rssi_state;
 
-	btrssi = coex_sta->bt_rssi;
+	bt_rssi = coex_sta->bt_rssi;
 
 	if (level_num == 2) {
 		if ((coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-			if (btrssi >=
+			if (bt_rssi >=
 			    (rssi_thresh + BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
-				btrssi_state = BTC_RSSI_STATE_HIGH;
+				bt_rssi_state = BTC_RSSI_STATE_HIGH;
 			else
-				btrssi_state = BTC_RSSI_STATE_STAY_LOW;
+				bt_rssi_state = BTC_RSSI_STATE_STAY_LOW;
 		} else {
-			if (btrssi < rssi_thresh)
-				btrssi_state = BTC_RSSI_STATE_LOW;
+			if (bt_rssi < rssi_thresh)
+				bt_rssi_state = BTC_RSSI_STATE_LOW;
 			else
-				btrssi_state = BTC_RSSI_STATE_STAY_HIGH;
+				bt_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
 		}
 	} else if (level_num == 3) {
 		if (rssi_thresh > rssi_thresh1) {
@@ -89,62 +89,63 @@ static u8 halbtc8192e2ant_btrssi_state(struct btc_coexist *btcoexist,
 				 "[BTCoex], BT Rssi thresh error!!\n");
 			return coex_sta->pre_bt_rssi_state;
 		}
+
 		if ((coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-			if (btrssi >=
+			if (bt_rssi >=
 			    (rssi_thresh + BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
-				btrssi_state = BTC_RSSI_STATE_MEDIUM;
+				bt_rssi_state = BTC_RSSI_STATE_MEDIUM;
 			else
-				btrssi_state = BTC_RSSI_STATE_STAY_LOW;
+				bt_rssi_state = BTC_RSSI_STATE_STAY_LOW;
 		} else if ((coex_sta->pre_bt_rssi_state ==
 			    BTC_RSSI_STATE_MEDIUM) ||
 			   (coex_sta->pre_bt_rssi_state ==
 			    BTC_RSSI_STATE_STAY_MEDIUM)) {
-			if (btrssi >= (rssi_thresh1 +
+			if (bt_rssi >= (rssi_thresh1 +
 					BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
-				btrssi_state = BTC_RSSI_STATE_HIGH;
-			else if (btrssi < rssi_thresh)
-				btrssi_state = BTC_RSSI_STATE_LOW;
+				bt_rssi_state = BTC_RSSI_STATE_HIGH;
+			else if (bt_rssi < rssi_thresh)
+				bt_rssi_state = BTC_RSSI_STATE_LOW;
 			else
-				btrssi_state = BTC_RSSI_STATE_STAY_MEDIUM;
+				bt_rssi_state = BTC_RSSI_STATE_STAY_MEDIUM;
 		} else {
-			if (btrssi < rssi_thresh1)
-				btrssi_state = BTC_RSSI_STATE_MEDIUM;
+			if (bt_rssi < rssi_thresh1)
+				bt_rssi_state = BTC_RSSI_STATE_MEDIUM;
 			else
-				btrssi_state = BTC_RSSI_STATE_STAY_HIGH;
+				bt_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
 		}
 	}
 
-	coex_sta->pre_bt_rssi_state = btrssi_state;
+	coex_sta->pre_bt_rssi_state = bt_rssi_state;
 
-	return btrssi_state;
+	return bt_rssi_state;
 }
 
-static u8 halbtc8192e2ant_wifirssi_state(struct btc_coexist *btcoexist,
-					 u8 index, u8 level_num, u8 rssi_thresh,
-					 u8 rssi_thresh1)
+static u8 btc8192e2ant_wifi_rssi_state(struct btc_coexist *btcoexist,
+				       u8 index, u8 level_num, u8 rssi_thresh,
+				       u8 rssi_thresh1)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	int wifirssi = 0;
-	u8 wifirssi_state = coex_sta->pre_wifi_rssi_state[index];
+	int wifi_rssi = 0;
+	u8 wifi_rssi_state = coex_sta->pre_wifi_rssi_state[index];
 
-	btcoexist->btc_get(btcoexist, BTC_GET_S4_WIFI_RSSI, &wifirssi);
+	btcoexist->btc_get(btcoexist, BTC_GET_S4_WIFI_RSSI, &wifi_rssi);
 
 	if (level_num == 2) {
 		if ((coex_sta->pre_wifi_rssi_state[index] ==
 		     BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_wifi_rssi_state[index] ==
 		     BTC_RSSI_STATE_STAY_LOW)) {
-			if (wifirssi >= (rssi_thresh +
-					 BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
-				wifirssi_state = BTC_RSSI_STATE_HIGH;
+			if (wifi_rssi >=
+			    (rssi_thresh + BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
+				wifi_rssi_state = BTC_RSSI_STATE_HIGH;
 			else
-				wifirssi_state = BTC_RSSI_STATE_STAY_LOW;
+				wifi_rssi_state = BTC_RSSI_STATE_STAY_LOW;
 		} else {
-			if (wifirssi < rssi_thresh)
-				wifirssi_state = BTC_RSSI_STATE_LOW;
+			if (wifi_rssi < rssi_thresh)
+				wifi_rssi_state = BTC_RSSI_STATE_LOW;
 			else
-				wifirssi_state = BTC_RSSI_STATE_STAY_HIGH;
+				wifi_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
 		}
 	} else if (level_num == 3) {
 		if (rssi_thresh > rssi_thresh1) {
@@ -157,36 +158,37 @@ static u8 halbtc8192e2ant_wifirssi_state(struct btc_coexist *btcoexist,
 		     BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_wifi_rssi_state[index] ==
 		     BTC_RSSI_STATE_STAY_LOW)) {
-			if (wifirssi >= (rssi_thresh +
-					 BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
-				wifirssi_state = BTC_RSSI_STATE_MEDIUM;
+			if (wifi_rssi >=
+			    (rssi_thresh + BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
+				wifi_rssi_state = BTC_RSSI_STATE_MEDIUM;
 			else
-				wifirssi_state = BTC_RSSI_STATE_STAY_LOW;
+				wifi_rssi_state = BTC_RSSI_STATE_STAY_LOW;
 		} else if ((coex_sta->pre_wifi_rssi_state[index] ==
 			    BTC_RSSI_STATE_MEDIUM) ||
 			   (coex_sta->pre_wifi_rssi_state[index] ==
 			    BTC_RSSI_STATE_STAY_MEDIUM)) {
-			if (wifirssi >= (rssi_thresh1 +
+			if (wifi_rssi >= (rssi_thresh1 +
 					 BTC_RSSI_COEX_THRESH_TOL_8192E_2ANT))
-				wifirssi_state = BTC_RSSI_STATE_HIGH;
-			else if (wifirssi < rssi_thresh)
-				wifirssi_state = BTC_RSSI_STATE_LOW;
+				wifi_rssi_state = BTC_RSSI_STATE_HIGH;
+			else if (wifi_rssi < rssi_thresh)
+				wifi_rssi_state = BTC_RSSI_STATE_LOW;
 			else
-				wifirssi_state = BTC_RSSI_STATE_STAY_MEDIUM;
+				wifi_rssi_state = BTC_RSSI_STATE_STAY_MEDIUM;
 		} else {
-			if (wifirssi < rssi_thresh1)
-				wifirssi_state = BTC_RSSI_STATE_MEDIUM;
+			if (wifi_rssi < rssi_thresh1)
+				wifi_rssi_state = BTC_RSSI_STATE_MEDIUM;
 			else
-				wifirssi_state = BTC_RSSI_STATE_STAY_HIGH;
+				wifi_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
 		}
 	}
 
-	coex_sta->pre_wifi_rssi_state[index] = wifirssi_state;
+	coex_sta->pre_wifi_rssi_state[index] = wifi_rssi_state;
 
-	return wifirssi_state;
+	return wifi_rssi_state;
 }
 
-static void btc8192e2ant_monitor_bt_enable_dis(struct btc_coexist *btcoexist)
+static void btc8192e2ant_monitor_bt_enable_disable(struct btc_coexist
+						   *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	static bool pre_bt_disabled;
@@ -236,57 +238,57 @@ static void btc8192e2ant_monitor_bt_enable_dis(struct btc_coexist *btcoexist)
 	}
 }
 
-static u32 halbtc8192e2ant_decidera_mask(struct btc_coexist *btcoexist,
-					 u8 sstype, u32 ra_masktype)
+static u32 btc8192e2ant_decide_ra_mask(struct btc_coexist *btcoexist,
+				       u8 ss_type, u32 ra_mask_type)
 {
-	u32 disra_mask = 0x0;
+	u32 dis_ra_mask = 0x0;
 
-	switch (ra_masktype) {
+	switch (ra_mask_type) {
 	case 0: /* normal mode */
-		if (sstype == 2)
-			disra_mask = 0x0;	/* enable 2ss */
+		if (ss_type == 2)
+			dis_ra_mask = 0x0; /* enable 2ss */
 		else
-			disra_mask = 0xfff00000;/* disable 2ss */
+			dis_ra_mask = 0xfff00000; /* disable 2ss */
 		break;
 	case 1: /* disable cck 1/2 */
-		if (sstype == 2)
-			disra_mask = 0x00000003;/* enable 2ss */
+		if (ss_type == 2)
+			dis_ra_mask = 0x00000003; /* enable 2ss */
 		else
-			disra_mask = 0xfff00003;/* disable 2ss */
+			dis_ra_mask = 0xfff00003; /* disable 2ss */
 		break;
 	case 2: /* disable cck 1/2/5.5, ofdm 6/9/12/18/24, mcs 0/1/2/3/4 */
-		if (sstype == 2)
-			disra_mask = 0x0001f1f7;/* enable 2ss */
+		if (ss_type == 2)
+			dis_ra_mask = 0x0001f1f7; /* enable 2ss */
 		else
-			disra_mask = 0xfff1f1f7;/* disable 2ss */
+			dis_ra_mask = 0xfff1f1f7; /* disable 2ss */
 		break;
 	default:
 		break;
 	}
 
-	return disra_mask;
+	return dis_ra_mask;
 }
 
-static void halbtc8192e2ant_Updatera_mask(struct btc_coexist *btcoexist,
-					  bool force_exec, u32 dis_ratemask)
+static void btc8192e2ant_update_ra_mask(struct btc_coexist *btcoexist,
+					bool force_exec, u32 dis_rate_mask)
 {
-	coex_dm->curra_mask = dis_ratemask;
+	coex_dm->cur_ra_mask = dis_rate_mask;
 
-	if (force_exec || (coex_dm->prera_mask != coex_dm->curra_mask))
-		btcoexist->btc_set(btcoexist, BTC_SET_ACT_UPDATE_ra_mask,
-				   &coex_dm->curra_mask);
-	coex_dm->prera_mask = coex_dm->curra_mask;
+	if (force_exec || (coex_dm->pre_ra_mask != coex_dm->cur_ra_mask))
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_UPDATE_RAMASK,
+				   &coex_dm->cur_ra_mask);
+	coex_dm->pre_ra_mask = coex_dm->cur_ra_mask;
 }
 
-static void btc8192e2ant_autorate_fallback_retry(struct btc_coexist *btcoexist,
-						 bool force_exec, u8 type)
+static void btc8192e2ant_auto_rate_fallback_retry(struct btc_coexist *btcoexist,
+						  bool force_exec, u8 type)
 {
-	bool wifi_under_bmode = false;
+	bool wifi_under_b_mode = false;
 
-	coex_dm->cur_arfrtype = type;
+	coex_dm->cur_arfr_type = type;
 
-	if (force_exec || (coex_dm->pre_arfrtype != coex_dm->cur_arfrtype)) {
-		switch (coex_dm->cur_arfrtype) {
+	if (force_exec || (coex_dm->pre_arfr_type != coex_dm->cur_arfr_type)) {
+		switch (coex_dm->cur_arfr_type) {
 		case 0:	/* normal mode */
 			btcoexist->btc_write_4byte(btcoexist, 0x430,
 						   coex_dm->backup_arfr_cnt1);
@@ -296,8 +298,8 @@ static void btc8192e2ant_autorate_fallback_retry(struct btc_coexist *btcoexist,
 		case 1:
 			btcoexist->btc_get(btcoexist,
 					   BTC_GET_BL_WIFI_UNDER_B_MODE,
-					   &wifi_under_bmode);
-			if (wifi_under_bmode) {
+					   &wifi_under_b_mode);
+			if (wifi_under_b_mode) {
 				btcoexist->btc_write_4byte(btcoexist, 0x430,
 							   0x0);
 				btcoexist->btc_write_4byte(btcoexist, 0x434,
@@ -314,46 +316,45 @@ static void btc8192e2ant_autorate_fallback_retry(struct btc_coexist *btcoexist,
 		}
 	}
 
-	coex_dm->pre_arfrtype = coex_dm->cur_arfrtype;
+	coex_dm->pre_arfr_type = coex_dm->cur_arfr_type;
 }
 
-static void halbtc8192e2ant_retrylimit(struct btc_coexist *btcoexist,
-				       bool force_exec, u8 type)
+static void btc8192e2ant_retry_limit(struct btc_coexist *btcoexist,
+				     bool force_exec, u8 type)
 {
-	coex_dm->cur_retrylimit_type = type;
+	coex_dm->cur_retry_limit_type = type;
 
-	if (force_exec || (coex_dm->pre_retrylimit_type !=
-			   coex_dm->cur_retrylimit_type)) {
-		switch (coex_dm->cur_retrylimit_type) {
+	if (force_exec || (coex_dm->pre_retry_limit_type !=
+			   coex_dm->cur_retry_limit_type)) {
+		switch (coex_dm->cur_retry_limit_type) {
 		case 0:	/* normal mode */
-				btcoexist->btc_write_2byte(btcoexist, 0x42a,
-						    coex_dm->backup_retrylimit);
-				break;
+			btcoexist->btc_write_2byte(btcoexist, 0x42a,
+						   coex_dm->backup_retry_limit);
+			break;
 		case 1:	/* retry limit = 8 */
-				btcoexist->btc_write_2byte(btcoexist, 0x42a,
-							   0x0808);
-				break;
+			btcoexist->btc_write_2byte(btcoexist, 0x42a, 0x0808);
+			break;
 		default:
-				break;
+			break;
 		}
 	}
 
-	coex_dm->pre_retrylimit_type = coex_dm->cur_retrylimit_type;
+	coex_dm->pre_retry_limit_type = coex_dm->cur_retry_limit_type;
 }
 
-static void halbtc8192e2ant_ampdu_maxtime(struct btc_coexist *btcoexist,
-					  bool force_exec, u8 type)
+static void btc8192e2ant_ampdu_maxtime(struct btc_coexist *btcoexist,
+				       bool force_exec, u8 type)
 {
-	coex_dm->cur_ampdutime_type = type;
+	coex_dm->cur_ampdu_time_type = type;
 
-	if (force_exec || (coex_dm->pre_ampdutime_type !=
-			   coex_dm->cur_ampdutime_type)) {
-		switch (coex_dm->cur_ampdutime_type) {
+	if (force_exec || (coex_dm->pre_ampdu_time_type !=
+			   coex_dm->cur_ampdu_time_type)) {
+		switch (coex_dm->cur_ampdu_time_type) {
 		case 0:	/* normal mode */
 			btcoexist->btc_write_1byte(btcoexist, 0x456,
 						coex_dm->backup_ampdu_maxtime);
 			break;
-		case 1:	/* AMPDU timw = 0x38 * 32us */
+		case 1:	/* AMPDU time = 0x38 * 32us */
 			btcoexist->btc_write_1byte(btcoexist, 0x456, 0x38);
 			break;
 		default:
@@ -361,30 +362,30 @@ static void halbtc8192e2ant_ampdu_maxtime(struct btc_coexist *btcoexist,
 		}
 	}
 
-	coex_dm->pre_ampdutime_type = coex_dm->cur_ampdutime_type;
+	coex_dm->pre_ampdu_time_type = coex_dm->cur_ampdu_time_type;
 }
 
-static void halbtc8192e2ant_limited_tx(struct btc_coexist *btcoexist,
-				       bool force_exec, u8 ra_masktype,
-				       u8 arfr_type, u8 retrylimit_type,
-				       u8 ampdutime_type)
+static void btc8192e2ant_limited_tx(struct btc_coexist *btcoexist,
+				    bool force_exec, u8 ra_mask_type,
+				    u8 arfr_type, u8 retry_limit_type,
+				    u8 ampdu_time_type)
 {
-	u32 disra_mask = 0x0;
+	u32 dis_ra_mask = 0x0;
 
-	coex_dm->curra_masktype = ra_masktype;
-	disra_mask = halbtc8192e2ant_decidera_mask(btcoexist,
-						   coex_dm->cur_sstype,
-						   ra_masktype);
-	halbtc8192e2ant_Updatera_mask(btcoexist, force_exec, disra_mask);
-btc8192e2ant_autorate_fallback_retry(btcoexist, force_exec, arfr_type);
-	halbtc8192e2ant_retrylimit(btcoexist, force_exec, retrylimit_type);
-	halbtc8192e2ant_ampdu_maxtime(btcoexist, force_exec, ampdutime_type);
+	coex_dm->cur_ra_mask_type = ra_mask_type;
+	dis_ra_mask =
+		 btc8192e2ant_decide_ra_mask(btcoexist, coex_dm->cur_ss_type,
+					     ra_mask_type);
+	btc8192e2ant_update_ra_mask(btcoexist, force_exec, dis_ra_mask);
+	btc8192e2ant_auto_rate_fallback_retry(btcoexist, force_exec, arfr_type);
+	btc8192e2ant_retry_limit(btcoexist, force_exec, retry_limit_type);
+	btc8192e2ant_ampdu_maxtime(btcoexist, force_exec, ampdu_time_type);
 }
 
-static void halbtc8192e2ant_limited_rx(struct btc_coexist *btcoexist,
-				       bool force_exec, bool rej_ap_agg_pkt,
-				       bool bt_ctrl_agg_buf_size,
-				       u8 agg_buf_size)
+static void btc8192e2ant_limited_rx(struct btc_coexist *btcoexist,
+				    bool force_exec, bool rej_ap_agg_pkt,
+				    bool bt_ctrl_agg_buf_size,
+				    u8 agg_buf_size)
 {
 	bool reject_rx_agg = rej_ap_agg_pkt;
 	bool bt_ctrl_rx_agg_size = bt_ctrl_agg_buf_size;
@@ -406,7 +407,7 @@ static void halbtc8192e2ant_limited_rx(struct btc_coexist *btcoexist,
 	btcoexist->btc_set(btcoexist, BTC_SET_ACT_AGGREGATE_CTRL, NULL);
 }
 
-static void halbtc8192e2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
+static void btc8192e2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u32 reg_hp_txrx, reg_lp_txrx, u32tmp;
@@ -417,11 +418,11 @@ static void halbtc8192e2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 
 	u32tmp = btcoexist->btc_read_4byte(btcoexist, reg_hp_txrx);
 	reg_hp_tx = u32tmp & MASKLWORD;
-	reg_hp_rx = (u32tmp & MASKHWORD)>>16;
+	reg_hp_rx = (u32tmp & MASKHWORD) >> 16;
 
 	u32tmp = btcoexist->btc_read_4byte(btcoexist, reg_lp_txrx);
 	reg_lp_tx = u32tmp & MASKLWORD;
-	reg_lp_rx = (u32tmp & MASKHWORD)>>16;
+	reg_lp_rx = (u32tmp & MASKHWORD) >> 16;
 
 	coex_sta->high_priority_tx = reg_hp_tx;
 	coex_sta->high_priority_rx = reg_hp_rx;
@@ -439,14 +440,14 @@ static void halbtc8192e2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
 }
 
-static void halbtc8192e2ant_querybt_info(struct btc_coexist *btcoexist)
+static void btc8192e2ant_query_bt_info(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
 	coex_sta->c2h_bt_info_req_sent = true;
 
-	h2c_parameter[0] |= BIT0;	/* trigger */
+	h2c_parameter[0] |= BIT0; /* trigger */
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Query Bt Info, FW write 0x61 = 0x%x\n",
@@ -455,12 +456,12 @@ static void halbtc8192e2ant_querybt_info(struct btc_coexist *btcoexist)
 	btcoexist->btc_fill_h2c(btcoexist, 0x61, 1, h2c_parameter);
 }
 
-static void halbtc8192e2ant_update_btlink_info(struct btc_coexist *btcoexist)
+static void btc8192e2ant_update_bt_link_info(struct btc_coexist *btcoexist)
 {
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
-	bool bt_hson = false;
+	bool bt_hs_on = false;
 
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hson);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
 	bt_link_info->bt_link_exist = coex_sta->bt_link_exist;
 	bt_link_info->sco_exist = coex_sta->sco_exist;
@@ -469,7 +470,7 @@ static void halbtc8192e2ant_update_btlink_info(struct btc_coexist *btcoexist)
 	bt_link_info->hid_exist = coex_sta->hid_exist;
 
 	/* work around for HS mode. */
-	if (bt_hson) {
+	if (bt_hs_on) {
 		bt_link_info->pan_exist = true;
 		bt_link_info->bt_link_exist = true;
 	}
@@ -511,16 +512,16 @@ static void halbtc8192e2ant_update_btlink_info(struct btc_coexist *btcoexist)
 		bt_link_info->hid_only = false;
 }
 
-static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
+static u8 btc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 	struct btc_stack_info *stack_info = &btcoexist->stack_info;
-	bool bt_hson = false;
+	bool bt_hs_on = false;
 	u8 algorithm = BT_8192E_2ANT_COEX_ALGO_UNDEFINED;
-	u8 numdiffprofile = 0;
+	u8 num_of_diff_profile = 0;
 
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hson);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
 	if (!bt_link_info->bt_link_exist) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -529,15 +530,15 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 	}
 
 	if (bt_link_info->sco_exist)
-		numdiffprofile++;
+		num_of_diff_profile++;
 	if (bt_link_info->hid_exist)
-		numdiffprofile++;
+		num_of_diff_profile++;
 	if (bt_link_info->pan_exist)
-		numdiffprofile++;
+		num_of_diff_profile++;
 	if (bt_link_info->a2dp_exist)
-		numdiffprofile++;
+		num_of_diff_profile++;
 
-	if (numdiffprofile == 1) {
+	if (num_of_diff_profile == 1) {
 		if (bt_link_info->sco_exist) {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "SCO only\n");
@@ -552,7 +553,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 					 "A2DP only\n");
 				algorithm = BT_8192E_2ANT_COEX_ALGO_A2DP;
 			} else if (bt_link_info->pan_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "PAN(HS) only\n");
@@ -567,7 +568,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				}
 			}
 		}
-	} else if (numdiffprofile == 2) {
+	} else if (num_of_diff_profile == 2) {
 		if (bt_link_info->sco_exist) {
 			if (bt_link_info->hid_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -578,7 +579,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 					 "SCO + A2DP ==> SCO\n");
 				algorithm = BT_8192E_2ANT_COEX_ALGO_PANEDR_HID;
 			} else if (bt_link_info->pan_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "SCO + PAN(HS)\n");
@@ -609,7 +610,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				}
 			} else if (bt_link_info->hid_exist &&
 				   bt_link_info->pan_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "HID + PAN(HS)\n");
@@ -623,7 +624,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				}
 			} else if (bt_link_info->pan_exist &&
 				   bt_link_info->a2dp_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "A2DP + PAN(HS)\n");
@@ -638,7 +639,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				}
 			}
 		}
-	} else if (numdiffprofile == 3) {
+	} else if (num_of_diff_profile == 3) {
 		if (bt_link_info->sco_exist) {
 			if (bt_link_info->hid_exist &&
 			    bt_link_info->a2dp_exist) {
@@ -647,7 +648,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				algorithm = BT_8192E_2ANT_COEX_ALGO_PANEDR_HID;
 			} else if (bt_link_info->hid_exist &&
 				   bt_link_info->pan_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "SCO + HID + PAN(HS)\n");
@@ -661,7 +662,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				}
 			} else if (bt_link_info->pan_exist &&
 				   bt_link_info->a2dp_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "SCO + A2DP + PAN(HS)\n");
@@ -678,7 +679,7 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 			if (bt_link_info->hid_exist &&
 			    bt_link_info->pan_exist &&
 			    bt_link_info->a2dp_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "HID + A2DP + PAN(HS)\n");
@@ -693,12 +694,12 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 				}
 			}
 		}
-	} else if (numdiffprofile >= 3) {
+	} else if (num_of_diff_profile >= 3) {
 		if (bt_link_info->sco_exist) {
 			if (bt_link_info->hid_exist &&
 			    bt_link_info->pan_exist &&
 			    bt_link_info->a2dp_exist) {
-				if (bt_hson) {
+				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "ErrorSCO+HID+A2DP+PAN(HS)\n");
@@ -717,8 +718,8 @@ static u8 halbtc8192e2ant_action_algorithm(struct btc_coexist *btcoexist)
 	return algorithm;
 }
 
-static void halbtc8192e2ant_setfw_dac_swinglevel(struct btc_coexist *btcoexist,
-						 u8 dac_swinglvl)
+static void btc8192e2ant_set_fw_dac_swing_level(struct btc_coexist *btcoexist,
+						u8 dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
@@ -726,81 +727,81 @@ static void halbtc8192e2ant_setfw_dac_swinglevel(struct btc_coexist *btcoexist,
 	/* There are several type of dacswing
 	 * 0x18/ 0x10/ 0xc/ 0x8/ 0x4/ 0x6
 	 */
-	h2c_parameter[0] = dac_swinglvl;
+	h2c_parameter[0] = dac_swing_lvl;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], Set Dac Swing Level = 0x%x\n", dac_swinglvl);
+		 "[BTCoex], Set Dac Swing Level = 0x%x\n", dac_swing_lvl);
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], FW write 0x64 = 0x%x\n", h2c_parameter[0]);
 
 	btcoexist->btc_fill_h2c(btcoexist, 0x64, 1, h2c_parameter);
 }
 
-static void halbtc8192e2ant_set_fwdec_btpwr(struct btc_coexist *btcoexist,
-					    u8 dec_btpwr_lvl)
+static void btc8192e2ant_set_fw_dec_bt_pwr(struct btc_coexist *btcoexist,
+					   u8 dec_bt_pwr_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
-	h2c_parameter[0] = dec_btpwr_lvl;
+	h2c_parameter[0] = dec_bt_pwr_lvl;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex] decrease Bt Power level = %d, FW write 0x62 = 0x%x\n",
-		 dec_btpwr_lvl, h2c_parameter[0]);
+		 dec_bt_pwr_lvl, h2c_parameter[0]);
 
 	btcoexist->btc_fill_h2c(btcoexist, 0x62, 1, h2c_parameter);
 }
 
-static void halbtc8192e2ant_dec_btpwr(struct btc_coexist *btcoexist,
-				      bool force_exec, u8 dec_btpwr_lvl)
+static void btc8192e2ant_dec_bt_pwr(struct btc_coexist *btcoexist,
+				    bool force_exec, u8 dec_bt_pwr_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s Dec BT power level = %d\n",
-		 force_exec ? "force to" : "", dec_btpwr_lvl);
-	coex_dm->cur_dec_bt_pwr = dec_btpwr_lvl;
+		 force_exec ? "force to" : "", dec_bt_pwr_lvl);
+	coex_dm->cur_dec_bt_pwr = dec_bt_pwr_lvl;
 
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], preBtDecPwrLvl=%d, curBtDecPwrLvl=%d\n",
 			 coex_dm->pre_dec_bt_pwr, coex_dm->cur_dec_bt_pwr);
 	}
-	halbtc8192e2ant_set_fwdec_btpwr(btcoexist, coex_dm->cur_dec_bt_pwr);
+	btc8192e2ant_set_fw_dec_bt_pwr(btcoexist, coex_dm->cur_dec_bt_pwr);
 
 	coex_dm->pre_dec_bt_pwr = coex_dm->cur_dec_bt_pwr;
 }
 
-static void halbtc8192e2ant_set_bt_autoreport(struct btc_coexist *btcoexist,
-					      bool enable_autoreport)
+static void btc8192e2ant_set_bt_auto_report(struct btc_coexist *btcoexist,
+					    bool enable_auto_report)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
 	h2c_parameter[0] = 0;
 
-	if (enable_autoreport)
+	if (enable_auto_report)
 		h2c_parameter[0] |= BIT0;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], BT FW auto report : %s, FW write 0x68 = 0x%x\n",
-		 (enable_autoreport ? "Enabled!!" : "Disabled!!"),
+		 (enable_auto_report ? "Enabled!!" : "Disabled!!"),
 		 h2c_parameter[0]);
 
 	btcoexist->btc_fill_h2c(btcoexist, 0x68, 1, h2c_parameter);
 }
 
-static void halbtc8192e2ant_bt_autoreport(struct btc_coexist *btcoexist,
-					  bool force_exec,
-					  bool enable_autoreport)
+static void btc8192e2ant_bt_auto_report(struct btc_coexist *btcoexist,
+					bool force_exec,
+					bool enable_auto_report)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s BT Auto report = %s\n",
 		 (force_exec ? "force to" : ""),
-		 ((enable_autoreport) ? "Enabled" : "Disabled"));
-	coex_dm->cur_bt_auto_report = enable_autoreport;
+		 ((enable_auto_report) ? "Enabled" : "Disabled"));
+	coex_dm->cur_bt_auto_report = enable_auto_report;
 
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -811,21 +812,21 @@ static void halbtc8192e2ant_bt_autoreport(struct btc_coexist *btcoexist,
 		if (coex_dm->pre_bt_auto_report == coex_dm->cur_bt_auto_report)
 			return;
 	}
-	halbtc8192e2ant_set_bt_autoreport(btcoexist,
-					  coex_dm->cur_bt_auto_report);
+	btc8192e2ant_set_bt_auto_report(btcoexist,
+					coex_dm->cur_bt_auto_report);
 
 	coex_dm->pre_bt_auto_report = coex_dm->cur_bt_auto_report;
 }
 
-static void halbtc8192e2ant_fw_dac_swinglvl(struct btc_coexist *btcoexist,
-					    bool force_exec, u8 fw_dac_swinglvl)
+static void btc8192e2ant_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
+					  bool force_exec, u8 fw_dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s set FW Dac Swing level = %d\n",
-		 (force_exec ? "force to" : ""), fw_dac_swinglvl);
-	coex_dm->cur_fw_dac_swing_lvl = fw_dac_swinglvl;
+		 (force_exec ? "force to" : ""), fw_dac_swing_lvl);
+	coex_dm->cur_fw_dac_swing_lvl = fw_dac_swing_lvl;
 
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -838,8 +839,8 @@ static void halbtc8192e2ant_fw_dac_swinglvl(struct btc_coexist *btcoexist,
 			return;
 	}
 
-	halbtc8192e2ant_setfw_dac_swinglevel(btcoexist,
-					     coex_dm->cur_fw_dac_swing_lvl);
+	btc8192e2ant_set_fw_dac_swing_level(btcoexist,
+					    coex_dm->cur_fw_dac_swing_lvl);
 
 	coex_dm->pre_fw_dac_swing_lvl = coex_dm->cur_fw_dac_swing_lvl;
 }
@@ -869,8 +870,8 @@ static void btc8192e2ant_set_sw_rf_rx_lpf_corner(struct btc_coexist *btcoexist,
 	}
 }
 
-static void halbtc8192e2ant_rf_shrink(struct btc_coexist *btcoexist,
-				      bool force_exec, bool rx_rf_shrink_on)
+static void btc8192e2ant_rf_shrink(struct btc_coexist *btcoexist,
+				   bool force_exec, bool rx_rf_shrink_on)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -896,8 +897,8 @@ static void halbtc8192e2ant_rf_shrink(struct btc_coexist *btcoexist,
 	coex_dm->pre_rf_rx_lpf_shrink = coex_dm->cur_rf_rx_lpf_shrink;
 }
 
-static void halbtc8192e2ant_set_dac_swingreg(struct btc_coexist *btcoexist,
-					     u32 level)
+static void btc8192e2ant_set_dac_swing_reg(struct btc_coexist *btcoexist,
+					   u32 level)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 val = (u8)level;
@@ -907,28 +908,28 @@ static void halbtc8192e2ant_set_dac_swingreg(struct btc_coexist *btcoexist,
 	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x883, 0x3e, val);
 }
 
-static void btc8192e2ant_setsw_full_swing(struct btc_coexist *btcoexist,
-					  bool sw_dac_swingon,
-					  u32 sw_dac_swinglvl)
+static void btc8192e2ant_set_sw_full_swing(struct btc_coexist *btcoexist,
+					   bool sw_dac_swing_on,
+					   u32 sw_dac_swing_lvl)
 {
-	if (sw_dac_swingon)
-		halbtc8192e2ant_set_dac_swingreg(btcoexist, sw_dac_swinglvl);
+	if (sw_dac_swing_on)
+		btc8192e2ant_set_dac_swing_reg(btcoexist, sw_dac_swing_lvl);
 	else
-		halbtc8192e2ant_set_dac_swingreg(btcoexist, 0x18);
+		btc8192e2ant_set_dac_swing_reg(btcoexist, 0x18);
 }
 
-static void halbtc8192e2ant_DacSwing(struct btc_coexist *btcoexist,
-				     bool force_exec, bool dac_swingon,
-				     u32 dac_swinglvl)
+static void btc8192e2ant_dac_swing(struct btc_coexist *btcoexist,
+				   bool force_exec, bool dac_swing_on,
+				   u32 dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s turn DacSwing=%s, dac_swinglvl = 0x%x\n",
+		 "[BTCoex], %s turn DacSwing=%s, dac_swing_lvl = 0x%x\n",
 		 (force_exec ? "force to" : ""),
-		 ((dac_swingon) ? "ON" : "OFF"), dac_swinglvl);
-	coex_dm->cur_dac_swing_on = dac_swingon;
-	coex_dm->cur_dac_swing_lvl = dac_swinglvl;
+		 ((dac_swing_on) ? "ON" : "OFF"), dac_swing_lvl);
+	coex_dm->cur_dac_swing_on = dac_swing_on;
+	coex_dm->cur_dac_swing_lvl = dac_swing_lvl;
 
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -945,14 +946,14 @@ static void halbtc8192e2ant_DacSwing(struct btc_coexist *btcoexist,
 			return;
 	}
 	mdelay(30);
-	btc8192e2ant_setsw_full_swing(btcoexist, dac_swingon, dac_swinglvl);
+	btc8192e2ant_set_sw_full_swing(btcoexist, dac_swing_on, dac_swing_lvl);
 
 	coex_dm->pre_dac_swing_on = coex_dm->cur_dac_swing_on;
 	coex_dm->pre_dac_swing_lvl = coex_dm->cur_dac_swing_lvl;
 }
 
-static void halbtc8192e2ant_set_agc_table(struct btc_coexist *btcoexist,
-					  bool agc_table_en)
+static void btc8192e2ant_set_agc_table(struct btc_coexist *btcoexist,
+				       bool agc_table_en)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -978,8 +979,8 @@ static void halbtc8192e2ant_set_agc_table(struct btc_coexist *btcoexist,
 	}
 }
 
-static void halbtc8192e2ant_AgcTable(struct btc_coexist *btcoexist,
-				     bool force_exec, bool agc_table_en)
+static void btc8192e2ant_agc_table(struct btc_coexist *btcoexist,
+				   bool force_exec, bool agc_table_en)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -998,14 +999,14 @@ static void halbtc8192e2ant_AgcTable(struct btc_coexist *btcoexist,
 		if (coex_dm->pre_agc_table_en == coex_dm->cur_agc_table_en)
 			return;
 	}
-	halbtc8192e2ant_set_agc_table(btcoexist, agc_table_en);
+	btc8192e2ant_set_agc_table(btcoexist, agc_table_en);
 
 	coex_dm->pre_agc_table_en = coex_dm->cur_agc_table_en;
 }
 
-static void halbtc8192e2ant_set_coex_table(struct btc_coexist *btcoexist,
-					   u32 val0x6c0, u32 val0x6c4,
-					   u32 val0x6c8, u8 val0x6cc)
+static void btc8192e2ant_set_coex_table(struct btc_coexist *btcoexist,
+					u32 val0x6c0, u32 val0x6c4,
+					u32 val0x6c8, u8 val0x6cc)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1026,10 +1027,9 @@ static void halbtc8192e2ant_set_coex_table(struct btc_coexist *btcoexist,
 	btcoexist->btc_write_1byte(btcoexist, 0x6cc, val0x6cc);
 }
 
-static void halbtc8192e2ant_coex_table(struct btc_coexist *btcoexist,
-				       bool force_exec,
-				       u32 val0x6c0, u32 val0x6c4,
-				       u32 val0x6c8, u8 val0x6cc)
+static void btc8192e2ant_coex_table(struct btc_coexist *btcoexist,
+				    bool force_exec, u32 val0x6c0, u32 val0x6c4,
+				    u32 val0x6c8, u8 val0x6cc)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1064,8 +1064,8 @@ static void halbtc8192e2ant_coex_table(struct btc_coexist *btcoexist,
 		    (coex_dm->pre_val0x6cc == coex_dm->cur_val0x6cc))
 			return;
 	}
-	halbtc8192e2ant_set_coex_table(btcoexist, val0x6c0, val0x6c4,
-				       val0x6c8, val0x6cc);
+	btc8192e2ant_set_coex_table(btcoexist, val0x6c0, val0x6c4, val0x6c8,
+				    val0x6cc);
 
 	coex_dm->pre_val0x6c0 = coex_dm->cur_val0x6c0;
 	coex_dm->pre_val0x6c4 = coex_dm->cur_val0x6c4;
@@ -1073,37 +1073,37 @@ static void halbtc8192e2ant_coex_table(struct btc_coexist *btcoexist,
 	coex_dm->pre_val0x6cc = coex_dm->cur_val0x6cc;
 }
 
-static void btc8192e2ant_coex_tbl_w_type(struct btc_coexist *btcoexist,
-					 bool force_exec, u8 type)
+static void btc8192e2ant_coex_table_with_type(struct btc_coexist *btcoexist,
+					      bool force_exec, u8 type)
 {
 	switch (type) {
 	case 0:
-		halbtc8192e2ant_coex_table(btcoexist, force_exec, 0x55555555,
-					   0x5a5a5a5a, 0xffffff, 0x3);
+		btc8192e2ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x5a5a5a5a, 0xffffff, 0x3);
 		break;
 	case 1:
-		halbtc8192e2ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
-					   0x5a5a5a5a, 0xffffff, 0x3);
+		btc8192e2ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
+					0x5a5a5a5a, 0xffffff, 0x3);
 		break;
 	case 2:
-		halbtc8192e2ant_coex_table(btcoexist, force_exec, 0x55555555,
-					   0x5ffb5ffb, 0xffffff, 0x3);
+		btc8192e2ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x5ffb5ffb, 0xffffff, 0x3);
 		break;
 	case 3:
-		halbtc8192e2ant_coex_table(btcoexist, force_exec, 0xdfffdfff,
-					   0x5fdb5fdb, 0xffffff, 0x3);
+		btc8192e2ant_coex_table(btcoexist, force_exec, 0xdfffdfff,
+					0x5fdb5fdb, 0xffffff, 0x3);
 		break;
 	case 4:
-		halbtc8192e2ant_coex_table(btcoexist, force_exec, 0xdfffdfff,
-					   0x5ffb5ffb, 0xffffff, 0x3);
+		btc8192e2ant_coex_table(btcoexist, force_exec, 0xdfffdfff,
+					0x5ffb5ffb, 0xffffff, 0x3);
 		break;
 	default:
 		break;
 	}
 }
 
-static void halbtc8192e2ant_set_fw_ignore_wlanact(struct btc_coexist *btcoexist,
-						  bool enable)
+static void btc8192e2ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoexist,
+						bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
@@ -1118,8 +1118,8 @@ static void halbtc8192e2ant_set_fw_ignore_wlanact(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x63, 1, h2c_parameter);
 }
 
-static void halbtc8192e2ant_IgnoreWlanAct(struct btc_coexist *btcoexist,
-					  bool force_exec, bool enable)
+static void btc8192e2ant_ignore_wlan_act(struct btc_coexist *btcoexist,
+					 bool force_exec, bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1140,12 +1140,12 @@ static void halbtc8192e2ant_IgnoreWlanAct(struct btc_coexist *btcoexist,
 		    coex_dm->cur_ignore_wlan_act)
 			return;
 	}
-	halbtc8192e2ant_set_fw_ignore_wlanact(btcoexist, enable);
+	btc8192e2ant_set_fw_ignore_wlan_act(btcoexist, enable);
 
 	coex_dm->pre_ignore_wlan_act = coex_dm->cur_ignore_wlan_act;
 }
 
-static void halbtc8192e2ant_SetFwPstdma(struct btc_coexist *btcoexist, u8 byte1,
+static void btc8192e2ant_set_fw_ps_tdma(struct btc_coexist *btcoexist, u8 byte1,
 					u8 byte2, u8 byte3, u8 byte4, u8 byte5)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
@@ -1173,24 +1173,24 @@ static void halbtc8192e2ant_SetFwPstdma(struct btc_coexist *btcoexist, u8 byte1,
 	btcoexist->btc_fill_h2c(btcoexist, 0x60, 5, h2c_parameter);
 }
 
-static void btc8192e2ant_sw_mec1(struct btc_coexist *btcoexist,
-				 bool shrink_rx_lpf, bool low_penalty_ra,
-				 bool limited_dig, bool btlan_constrain)
+static void btc8192e2ant_sw_mechanism1(struct btc_coexist *btcoexist,
+				       bool shrink_rx_lpf, bool low_penalty_ra,
+				       bool limited_dig, bool btlan_constrain)
 {
-	halbtc8192e2ant_rf_shrink(btcoexist, NORMAL_EXEC, shrink_rx_lpf);
+	btc8192e2ant_rf_shrink(btcoexist, NORMAL_EXEC, shrink_rx_lpf);
 }
 
-static void btc8192e2ant_sw_mec2(struct btc_coexist *btcoexist,
-				 bool agc_table_shift, bool adc_backoff,
-				 bool sw_dac_swing, u32 dac_swinglvl)
+static void btc8192e2ant_sw_mechanism2(struct btc_coexist *btcoexist,
+				       bool agc_table_shift, bool adc_backoff,
+				       bool sw_dac_swing, u32 dac_swing_lvl)
 {
-	halbtc8192e2ant_AgcTable(btcoexist, NORMAL_EXEC, agc_table_shift);
-	halbtc8192e2ant_DacSwing(btcoexist, NORMAL_EXEC, sw_dac_swing,
-				 dac_swinglvl);
+	btc8192e2ant_agc_table(btcoexist, NORMAL_EXEC, agc_table_shift);
+	btc8192e2ant_dac_swing(btcoexist, NORMAL_EXEC, sw_dac_swing,
+			       dac_swing_lvl);
 }
 
-static void halbtc8192e2ant_ps_tdma(struct btc_coexist *btcoexist,
-				    bool force_exec, bool turn_on, u8 type)
+static void btc8192e2ant_ps_tdma(struct btc_coexist *btcoexist,
+				 bool force_exec, bool turn_on, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1217,91 +1217,91 @@ static void halbtc8192e2ant_ps_tdma(struct btc_coexist *btcoexist,
 		switch (type) {
 		case 1:
 		default:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1a,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
 						    0x1a, 0xe1, 0x90);
 			break;
 		case 2:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x12,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
 						    0x12, 0xe1, 0x90);
 			break;
 		case 3:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1c,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
 						    0x3, 0xf1, 0x90);
 			break;
 		case 4:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x10,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
 						    0x3, 0xf1, 0x90);
 			break;
 		case 5:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1a,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
 						    0x1a, 0x60, 0x90);
 			break;
 		case 6:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x12,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
 						    0x12, 0x60, 0x90);
 			break;
 		case 7:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1c,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
 						    0x3, 0x70, 0x90);
 			break;
 		case 8:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xa3, 0x10,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xa3, 0x10,
 						    0x3, 0x70, 0x90);
 			break;
 		case 9:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1a,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
 						    0x1a, 0xe1, 0x10);
 			break;
 		case 10:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x12,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
 						    0x12, 0xe1, 0x10);
 			break;
 		case 11:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1c,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
 						    0x3, 0xf1, 0x10);
 			break;
 		case 12:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x10,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
 						    0x3, 0xf1, 0x10);
 			break;
 		case 13:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1a,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
 						    0x1a, 0xe0, 0x10);
 			break;
 		case 14:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x12,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
 						    0x12, 0xe0, 0x10);
 			break;
 		case 15:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1c,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
 						    0x3, 0xf0, 0x10);
 			break;
 		case 16:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x12,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
 						    0x3, 0xf0, 0x10);
 			break;
 		case 17:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0x61, 0x20,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0x61, 0x20,
 						    0x03, 0x10, 0x10);
 			break;
 		case 18:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x5,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x5,
 						    0x5, 0xe1, 0x90);
 			break;
 		case 19:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x25,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
 						    0x25, 0xe1, 0x90);
 			break;
 		case 20:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x25,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
 						    0x25, 0x60, 0x90);
 			break;
 		case 21:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x15,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x15,
 						    0x03, 0x70, 0x90);
 			break;
 		case 71:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0xe3, 0x1a,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
 						    0x1a, 0xe1, 0x90);
 			break;
 		}
@@ -1310,12 +1310,12 @@ static void halbtc8192e2ant_ps_tdma(struct btc_coexist *btcoexist,
 		switch (type) {
 		default:
 		case 0:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0x8, 0x0, 0x0,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0x8, 0x0, 0x0,
 						    0x0, 0x0);
 			btcoexist->btc_write_1byte(btcoexist, 0x92c, 0x4);
 			break;
 		case 1:
-			halbtc8192e2ant_SetFwPstdma(btcoexist, 0x0, 0x0, 0x0,
+			btc8192e2ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
 						    0x8, 0x0);
 			mdelay(5);
 			btcoexist->btc_write_1byte(btcoexist, 0x92c, 0x20);
@@ -1328,22 +1328,22 @@ static void halbtc8192e2ant_ps_tdma(struct btc_coexist *btcoexist,
 	coex_dm->pre_ps_tdma = coex_dm->cur_ps_tdma;
 }
 
-static void halbtc8192e2ant_set_switch_sstype(struct btc_coexist *btcoexist,
-					      u8 sstype)
+static void btc8192e2ant_set_switch_ss_type(struct btc_coexist *btcoexist,
+					    u8 ss_type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 mimops = BTC_MIMO_PS_DYNAMIC;
-	u32 disra_mask = 0x0;
+	u32 dis_ra_mask = 0x0;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], REAL set SS Type = %d\n", sstype);
+		 "[BTCoex], REAL set SS Type = %d\n", ss_type);
 
-	disra_mask = halbtc8192e2ant_decidera_mask(btcoexist, sstype,
-						   coex_dm->curra_masktype);
-	halbtc8192e2ant_Updatera_mask(btcoexist, FORCE_EXEC, disra_mask);
+	dis_ra_mask = btc8192e2ant_decide_ra_mask(btcoexist, ss_type,
+						  coex_dm->cur_ra_mask_type);
+	btc8192e2ant_update_ra_mask(btcoexist, FORCE_EXEC, dis_ra_mask);
 
-	if (sstype == 1) {
-		halbtc8192e2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
+	if (ss_type == 1) {
+		btc8192e2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
 		/* switch ofdm path */
 		btcoexist->btc_write_1byte(btcoexist, 0xc04, 0x11);
 		btcoexist->btc_write_1byte(btcoexist, 0xd04, 0x1);
@@ -1352,8 +1352,8 @@ static void halbtc8192e2ant_set_switch_sstype(struct btc_coexist *btcoexist,
 		btcoexist->btc_write_1byte_bitmask(btcoexist, 0xe77, 0x4, 0x1);
 		btcoexist->btc_write_1byte(btcoexist, 0xa07, 0x81);
 		mimops = BTC_MIMO_PS_STATIC;
-	} else if (sstype == 2) {
-		halbtc8192e2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 0);
+	} else if (ss_type == 2) {
+		btc8192e2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 0);
 		btcoexist->btc_write_1byte(btcoexist, 0xc04, 0x33);
 		btcoexist->btc_write_1byte(btcoexist, 0xd04, 0x3);
 		btcoexist->btc_write_4byte(btcoexist, 0x90c, 0x81121313);
@@ -1365,89 +1365,89 @@ static void halbtc8192e2ant_set_switch_sstype(struct btc_coexist *btcoexist,
 	btcoexist->btc_set(btcoexist, BTC_SET_ACT_SEND_MIMO_PS, &mimops);
 }
 
-static void halbtc8192e2ant_switch_sstype(struct btc_coexist *btcoexist,
-					  bool force_exec, u8 new_sstype)
+static void btc8192e2ant_switch_ss_type(struct btc_coexist *btcoexist,
+					bool force_exec, u8 new_ss_type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s Switch SS Type = %d\n",
-		 (force_exec ? "force to" : ""), new_sstype);
-	coex_dm->cur_sstype = new_sstype;
+		 (force_exec ? "force to" : ""), new_ss_type);
+	coex_dm->cur_ss_type = new_ss_type;
 
 	if (!force_exec) {
-		if (coex_dm->pre_sstype == coex_dm->cur_sstype)
+		if (coex_dm->pre_ss_type == coex_dm->cur_ss_type)
 			return;
 	}
-	halbtc8192e2ant_set_switch_sstype(btcoexist, coex_dm->cur_sstype);
+	btc8192e2ant_set_switch_ss_type(btcoexist, coex_dm->cur_ss_type);
 
-	coex_dm->pre_sstype = coex_dm->cur_sstype;
+	coex_dm->pre_ss_type = coex_dm->cur_ss_type;
 }
 
-static void halbtc8192e2ant_coex_alloff(struct btc_coexist *btcoexist)
+static void btc8192e2ant_coex_all_off(struct btc_coexist *btcoexist)
 {
 	/* fw all off */
-	halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
-	halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
+	btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
 	/* sw all off */
-	btc8192e2ant_sw_mec1(btcoexist, false, false, false, false);
-	btc8192e2ant_sw_mec2(btcoexist, false, false, false, 0x18);
+	btc8192e2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8192e2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
 
 	/* hw all off */
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 0);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 }
 
-static void halbtc8192e2ant_init_coex_dm(struct btc_coexist *btcoexist)
+static void btc8192e2ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	/* force to reset coex mechanism */
 
-	halbtc8192e2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, FORCE_EXEC, 6);
-	halbtc8192e2ant_dec_btpwr(btcoexist, FORCE_EXEC, 0);
+	btc8192e2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, FORCE_EXEC, 6);
+	btc8192e2ant_dec_bt_pwr(btcoexist, FORCE_EXEC, 0);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, FORCE_EXEC, 0);
-	halbtc8192e2ant_switch_sstype(btcoexist, FORCE_EXEC, 2);
+	btc8192e2ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
+	btc8192e2ant_switch_ss_type(btcoexist, FORCE_EXEC, 2);
 
-	btc8192e2ant_sw_mec1(btcoexist, false, false, false, false);
-	btc8192e2ant_sw_mec2(btcoexist, false, false, false, 0x18);
+	btc8192e2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8192e2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
 }
 
-static void halbtc8192e2ant_action_bt_inquiry(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_bt_inquiry(struct btc_coexist *btcoexist)
 {
 	bool low_pwr_disable = true;
 
 	btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 			   &low_pwr_disable);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 2);
-	halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
-	halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
+	btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-	btc8192e2ant_sw_mec1(btcoexist, false, false, false, false);
-	btc8192e2ant_sw_mec2(btcoexist, false, false, false, 0x18);
+	btc8192e2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8192e2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
 }
 
-static bool halbtc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
+static bool btc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 	bool common = false, wifi_connected = false, wifi_busy = false;
-	bool bt_hson = false, low_pwr_disable = false;
+	bool bt_hs_on = false, low_pwr_disable = false;
 
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hson);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 			   &wifi_connected);
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
 
 	if (bt_link_info->sco_exist || bt_link_info->hid_exist)
-		halbtc8192e2ant_limited_tx(btcoexist, NORMAL_EXEC, 1, 0, 0, 0);
+		btc8192e2ant_limited_tx(btcoexist, NORMAL_EXEC, 1, 0, 0, 0);
 	else
-		halbtc8192e2ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+		btc8192e2ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
 
 	if (!wifi_connected) {
 		low_pwr_disable = false;
@@ -1461,26 +1461,24 @@ static bool halbtc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
 		     coex_dm->bt_status) ||
 		    (BT_8192E_2ANT_BT_STATUS_CONNECTED_IDLE ==
 		     coex_dm->bt_status)) {
-			halbtc8192e2ant_switch_sstype(btcoexist,
-						      NORMAL_EXEC, 2);
-			btc8192e2ant_coex_tbl_w_type(btcoexist,
-						     NORMAL_EXEC, 1);
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 0);
+			btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 2);
+			btc8192e2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
+			btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
 		} else {
-			halbtc8192e2ant_switch_sstype(btcoexist,
-						      NORMAL_EXEC, 1);
-			btc8192e2ant_coex_tbl_w_type(btcoexist,
-						     NORMAL_EXEC, 0);
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 1);
+			btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+			btc8192e2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 0);
+			btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 		}
 
-		halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-		btc8192e2ant_sw_mec1(btcoexist, false, false, false, false);
-		btc8192e2ant_sw_mec2(btcoexist, false, false, false, 0x18);
+		btc8192e2ant_sw_mechanism1(btcoexist, false, false, false,
+					   false);
+		btc8192e2ant_sw_mechanism2(btcoexist, false, false, false,
+					   0x18);
 
 		common = true;
 	} else {
@@ -1494,20 +1492,18 @@ static bool halbtc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Wifi connected + BT non connected-idle!!\n");
 
-			halbtc8192e2ant_switch_sstype(btcoexist,
-						      NORMAL_EXEC, 2);
-			btc8192e2ant_coex_tbl_w_type(btcoexist,
-						     NORMAL_EXEC, 1);
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 0);
-			halbtc8192e2ant_fw_dac_swinglvl(btcoexist,
-							NORMAL_EXEC, 6);
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 2);
+			btc8192e2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
+			btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
+			btc8192e2ant_fw_dac_swing_lvl(btcoexist,
+						      NORMAL_EXEC, 6);
+			btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 
 			common = true;
 		} else if (BT_8192E_2ANT_BT_STATUS_CONNECTED_IDLE ==
@@ -1517,25 +1513,25 @@ static bool halbtc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
 					   BTC_SET_ACT_DISABLE_LOW_POWER,
 					   &low_pwr_disable);
 
-			if (bt_hson)
+			if (bt_hs_on)
 				return false;
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Wifi connected + BT connected-idle!!\n");
 
-			halbtc8192e2ant_switch_sstype(btcoexist,
-						      NORMAL_EXEC, 2);
-			btc8192e2ant_coex_tbl_w_type(btcoexist,
-						     NORMAL_EXEC, 1);
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 0);
-			halbtc8192e2ant_fw_dac_swinglvl(btcoexist,
-							NORMAL_EXEC, 6);
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_switch_ss_type(btcoexist,
+						    NORMAL_EXEC, 2);
+			btc8192e2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
+			btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     false, 0);
+			btc8192e2ant_fw_dac_swing_lvl(btcoexist,
+						      NORMAL_EXEC, 6);
+			btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 
 			common = true;
 		} else {
@@ -1552,20 +1548,21 @@ static bool halbtc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "Wifi Connected-Idle + BT Busy!!\n");
 
-				halbtc8192e2ant_switch_sstype(btcoexist,
-							      NORMAL_EXEC, 1);
-				btc8192e2ant_coex_tbl_w_type(btcoexist,
-							     NORMAL_EXEC, 2);
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 21);
-				halbtc8192e2ant_fw_dac_swinglvl(btcoexist,
-								NORMAL_EXEC, 6);
-				halbtc8192e2ant_dec_btpwr(btcoexist,
-							  NORMAL_EXEC, 0);
-				btc8192e2ant_sw_mec1(btcoexist, false,
-						     false, false, false);
-				btc8192e2ant_sw_mec2(btcoexist, false,
-						     false, false, 0x18);
+				btc8192e2ant_switch_ss_type(btcoexist,
+							    NORMAL_EXEC, 1);
+				btc8192e2ant_coex_table_with_type(btcoexist,
+								  NORMAL_EXEC,
+								  2);
+				btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
+						     true, 21);
+				btc8192e2ant_fw_dac_swing_lvl(btcoexist,
+							      NORMAL_EXEC, 6);
+				btc8192e2ant_dec_bt_pwr(btcoexist,
+							NORMAL_EXEC, 0);
+				btc8192e2ant_sw_mechanism1(btcoexist, false,
+							   false, false, false);
+				btc8192e2ant_sw_mechanism2(btcoexist, false,
+							   false, false, 0x18);
 				common = true;
 			}
 		}
@@ -1573,588 +1570,9 @@ static bool halbtc8192e2ant_is_common_action(struct btc_coexist *btcoexist)
 	return common;
 }
 
-static void btc8192e_int1(struct btc_coexist *btcoexist, bool tx_pause,
-			  int result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-
-		if (coex_dm->cur_ps_tdma == 71) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-			coex_dm->tdma_adj_type = 5;
-		} else if (coex_dm->cur_ps_tdma == 1) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-			coex_dm->tdma_adj_type = 5;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 13);
-			coex_dm->tdma_adj_type = 13;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 5);
-				coex_dm->tdma_adj_type = 5;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 13);
-				coex_dm->tdma_adj_type = 13;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 71);
-			coex_dm->tdma_adj_type = 71;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 9);
-			coex_dm->tdma_adj_type = 9;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 71) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 1);
-				coex_dm->tdma_adj_type = 1;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 1);
-				coex_dm->tdma_adj_type = 1;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 71);
-				coex_dm->tdma_adj_type = 71;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			}
-		}
-	}
-}
-
-static void btc8192e_int2(struct btc_coexist *btcoexist, bool tx_pause,
-			  int result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-		if (coex_dm->cur_ps_tdma == 1) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			}
-		}
-	}
-}
-
-static void btc8192e_int3(struct btc_coexist *btcoexist, bool tx_pause,
-			  int result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-		if (coex_dm->cur_ps_tdma == 1) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			}
-		}
-	}
-}
-
-static void halbtc8192e2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
-						 bool sco_hid, bool tx_pause,
-						 u8 max_interval)
+static void btc8192e2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
+					      bool sco_hid, bool tx_pause,
+					      u8 max_interval)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	static int up, dn, m, n, wait_cnt;
@@ -2174,72 +1592,72 @@ static void halbtc8192e2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 		if (sco_hid) {
 			if (tx_pause) {
 				if (max_interval == 1) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 13);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 13);
 					coex_dm->tdma_adj_type = 13;
 				} else if (max_interval == 2) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 14);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 14);
 					coex_dm->tdma_adj_type = 14;
 				} else {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 15);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
 					coex_dm->tdma_adj_type = 15;
 				}
 			} else {
 				if (max_interval == 1) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 9);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 9);
 					coex_dm->tdma_adj_type = 9;
 				} else if (max_interval == 2) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 10);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 10);
 					coex_dm->tdma_adj_type = 10;
 				} else {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 11);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 11);
 					coex_dm->tdma_adj_type = 11;
 				}
 			}
 		} else {
 			if (tx_pause) {
 				if (max_interval == 1) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 5);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 5);
 					coex_dm->tdma_adj_type = 5;
 				} else if (max_interval == 2) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 6);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 6);
 					coex_dm->tdma_adj_type = 6;
 				} else {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 7);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
 					coex_dm->tdma_adj_type = 7;
 				}
 			} else {
 				if (max_interval == 1) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 1);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 1);
 					coex_dm->tdma_adj_type = 1;
 				} else if (max_interval == 2) {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 2);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 2);
 					coex_dm->tdma_adj_type = 2;
 				} else {
-					halbtc8192e2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 3);
+					btc8192e2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
 					coex_dm->tdma_adj_type = 3;
 				}
 			}
@@ -2322,12 +1740,6 @@ static void halbtc8192e2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], max Interval = %d\n", max_interval);
-		if (max_interval == 1)
-			btc8192e_int1(btcoexist, tx_pause, result);
-		else if (max_interval == 2)
-			btc8192e_int2(btcoexist, tx_pause, result);
-		else if (max_interval == 3)
-			btc8192e_int3(btcoexist, tx_pause, result);
 	}
 
 	/* if current PsTdma not match with
@@ -2348,9 +1760,8 @@ static void halbtc8192e2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
 
 		if (!scan && !link && !roam)
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true,
-						coex_dm->tdma_adj_type);
+			btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, coex_dm->tdma_adj_type);
 		else
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], roaming/link/scan is under progress, will adjust next time!!!\n");
@@ -2358,583 +1769,578 @@ static void halbtc8192e2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 }
 
 /* SCO only or SCO+PAN(HS) */
-static void halbtc8192e2ant_action_sco(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_sco(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_STAY_LOW;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_STAY_LOW;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 4);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 4);
 
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 13);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 13);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
 	}
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x6);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x6);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x6);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x6);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x6);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x6);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x6);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x6);
 		}
 	}
 }
 
-static void halbtc8192e2ant_action_sco_pan(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_sco_pan(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_STAY_LOW;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_STAY_LOW;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 4);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 4);
 
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
 	}
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x6);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x6);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x6);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x6);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x6);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x6);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x6);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x6);
 		}
 	}
 }
 
-static void halbtc8192e2ant_action_hid(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_hid(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 3);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 3);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 13);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 13);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
 	}
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
 /* A2DP only / PAN(EDR) only/ A2DP+PAN(HS) */
-static void halbtc8192e2ant_action_a2dp(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_a2dp(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 	bool long_dist = false;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW ||
-	     btrssi_state == BTC_RSSI_STATE_STAY_LOW) &&
-	    (wifirssi_state == BTC_RSSI_STATE_LOW ||
-	     wifirssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW ||
+	     bt_rssi_state == BTC_RSSI_STATE_STAY_LOW) &&
+	    (wifi_rssi_state == BTC_RSSI_STATE_LOW ||
+	     wifi_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], A2dp, wifi/bt rssi both LOW!!\n");
 		long_dist = true;
 	}
 	if (long_dist) {
-		halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, true,
-					   0x4);
+		btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, true,
+					0x4);
 	} else {
-		halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-		halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false,
-					   0x8);
+		btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+		btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false,
+					0x8);
 	}
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
 	if (long_dist)
-		btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 	else
-		btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 
 	if (long_dist) {
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 17);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 17);
 		coex_dm->auto_tdma_adjust = false;
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 	} else {
-		if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-		    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-			halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-							     true, 1);
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-			   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-			halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-							     false, 1);
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-			   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-							     false, 1);
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
+		if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+		    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+			btc8192e2ant_tdma_duration_adjust(btcoexist, false,
+							  true, 1);
+			btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+			   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+			btc8192e2ant_tdma_duration_adjust(btcoexist, false,
+							  false, 1);
+			btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+			   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_tdma_duration_adjust(btcoexist, false,
+							  false, 1);
+			btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
 		}
 	}
 
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8192e2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 2);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, false, true, 2);
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-						     false, 2);
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-						     false, 2);
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_tdma_duration_adjust(btcoexist, false, true, 2);
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_tdma_duration_adjust(btcoexist, false, false, 2);
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_tdma_duration_adjust(btcoexist, false, false, 2);
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
 	}
 
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     true, 0x6);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   true, 0x6);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     true, 0x6);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   true, 0x6);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     true, 0x6);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   true, 0x6);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     true, 0x6);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   true, 0x6);
 		}
 	}
 }
 
-static void halbtc8192e2ant_action_pan_edr(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_pan_edr(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 2);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 1);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 1);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 1);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 1);
 	}
 
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
 /* PAN(HS) only */
-static void halbtc8192e2ant_action_pan_hs(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_pan_hs(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 2);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
 	}
-	halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+	btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
 /* PAN(EDR)+A2DP */
-static void halbtc8192e2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 2);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, false, true, 3);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-						     false, 3);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, false,
-						     false, 3);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, false, true, 3);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, false, false, 3);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, false, false, 3);
 	}
 
 	/* sw mechanism	*/
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, false,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8192e2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 3);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 3);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-			halbtc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_ps_tdma(btcoexist, NORMAL_EXEC,
+				     true, 10);
 	}
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
@@ -2942,125 +2348,125 @@ static void halbtc8192e2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 /* HID+A2DP+PAN(EDR) */
 static void btc8192e2ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	halbtc8192e2ant_fw_dac_swinglvl(btcoexist, NORMAL_EXEC, 6);
+	btc8192e2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 3);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 3);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, true, true, 3);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 3);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 3);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, true, true, 3);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 3);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 3);
 	}
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8192e2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
+static void btc8192e2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 {
-	u8 wifirssi_state, btrssi_state = BTC_RSSI_STATE_HIGH;
+	u8 wifi_rssi_state, bt_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_bw;
 
-	wifirssi_state = halbtc8192e2ant_wifirssi_state(btcoexist, 0, 2, 15, 0);
-	btrssi_state = halbtc8192e2ant_btrssi_state(btcoexist, 3, 34, 42);
+	wifi_rssi_state = btc8192e2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8192e2ant_bt_rssi_state(btcoexist, 3, 34, 42);
 
-	halbtc8192e2ant_switch_sstype(btcoexist, NORMAL_EXEC, 1);
-	halbtc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8192e2ant_switch_ss_type(btcoexist, NORMAL_EXEC, 1);
+	btc8192e2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, NORMAL_EXEC, 3);
+	btc8192e2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 3);
 
-	if ((btrssi_state == BTC_RSSI_STATE_LOW) ||
-	    (btrssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 0);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, true, true, 2);
-	} else if ((btrssi_state == BTC_RSSI_STATE_MEDIUM) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_MEDIUM))	{
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 2);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 2);
-	} else if ((btrssi_state == BTC_RSSI_STATE_HIGH) ||
-		   (btrssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		halbtc8192e2ant_dec_btpwr(btcoexist, NORMAL_EXEC, 4);
-		halbtc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 2);
+	if ((bt_rssi_state == BTC_RSSI_STATE_LOW) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, true, true, 2);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_MEDIUM) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_MEDIUM))	{
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 2);
+	} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8192e2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 4);
+		btc8192e2ant_tdma_duration_adjust(btcoexist, true, false, 2);
 	}
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, true, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		if ((wifirssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifirssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, true, false,
-					     false, 0x18);
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8192e2ant_sw_mec1(btcoexist, false, true,
-					     false, false);
-			btc8192e2ant_sw_mec2(btcoexist, false, false,
-					     false, 0x18);
+			btc8192e2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8192e2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8192e2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
+static void btc8192e2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 algorithm = 0;
@@ -3080,12 +2486,12 @@ static void halbtc8192e2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		return;
 	}
 
-	algorithm = halbtc8192e2ant_action_algorithm(btcoexist);
+	algorithm = btc8192e2ant_action_algorithm(btcoexist);
 	if (coex_sta->c2h_bt_inquiry_page &&
 	    (BT_8192E_2ANT_COEX_ALGO_PANHS != algorithm)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], BT is under inquiry/page scan !!\n");
-		halbtc8192e2ant_action_bt_inquiry(btcoexist);
+		btc8192e2ant_action_bt_inquiry(btcoexist);
 		return;
 	}
 
@@ -3093,7 +2499,7 @@ static void halbtc8192e2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Algorithm = %d\n", coex_dm->cur_algorithm);
 
-	if (halbtc8192e2ant_is_common_action(btcoexist)) {
+	if (btc8192e2ant_is_common_action(btcoexist)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Action 2-Ant common\n");
 		coex_dm->auto_tdma_adjust = false;
@@ -3109,47 +2515,47 @@ static void halbtc8192e2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		case BT_8192E_2ANT_COEX_ALGO_SCO:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = SCO\n");
-			halbtc8192e2ant_action_sco(btcoexist);
+			btc8192e2ant_action_sco(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_SCO_PAN:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = SCO+PAN(EDR)\n");
-			halbtc8192e2ant_action_sco_pan(btcoexist);
+			btc8192e2ant_action_sco_pan(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_HID:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = HID\n");
-			halbtc8192e2ant_action_hid(btcoexist);
+			btc8192e2ant_action_hid(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = A2DP\n");
-			halbtc8192e2ant_action_a2dp(btcoexist);
+			btc8192e2ant_action_a2dp(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_A2DP_PANHS:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = A2DP+PAN(HS)\n");
-			halbtc8192e2ant_action_a2dp_pan_hs(btcoexist);
+			btc8192e2ant_action_a2dp_pan_hs(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_PANEDR:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = PAN(EDR)\n");
-			halbtc8192e2ant_action_pan_edr(btcoexist);
+			btc8192e2ant_action_pan_edr(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_PANHS:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = HS mode\n");
-			halbtc8192e2ant_action_pan_hs(btcoexist);
+			btc8192e2ant_action_pan_hs(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_PANEDR_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = PAN+A2DP\n");
-			halbtc8192e2ant_action_pan_edr_a2dp(btcoexist);
+			btc8192e2ant_action_pan_edr_a2dp(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_PANEDR_HID:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = PAN(EDR)+HID\n");
-			halbtc8192e2ant_action_pan_edr_hid(btcoexist);
+			btc8192e2ant_action_pan_edr_hid(btcoexist);
 			break;
 		case BT_8192E_2ANT_COEX_ALGO_HID_A2DP_PANEDR:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3159,20 +2565,20 @@ static void halbtc8192e2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		case BT_8192E_2ANT_COEX_ALGO_HID_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = HID+A2DP\n");
-			halbtc8192e2ant_action_hid_a2dp(btcoexist);
+			btc8192e2ant_action_hid_a2dp(btcoexist);
 			break;
 		default:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "Action 2-Ant, algorithm = unknown!!\n");
-			/* halbtc8192e2ant_coex_alloff(btcoexist); */
+			/* btc8192e2ant_coex_all_off(btcoexist); */
 			break;
 		}
 		coex_dm->pre_algorithm = coex_dm->cur_algorithm;
 	}
 }
 
-static void halbtc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist,
-					  bool backup)
+static void btc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist,
+				       bool backup)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u16 u16tmp = 0;
@@ -3191,7 +2597,7 @@ static void halbtc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist,
 								      0x430);
 		coex_dm->backup_arfr_cnt2 = btcoexist->btc_read_4byte(btcoexist,
 								     0x434);
-		coex_dm->backup_retrylimit = btcoexist->btc_read_2byte(
+		coex_dm->backup_retry_limit = btcoexist->btc_read_2byte(
 								    btcoexist,
 								    0x42a);
 		coex_dm->backup_ampdu_maxtime = btcoexist->btc_read_1byte(
@@ -3209,7 +2615,7 @@ static void halbtc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist,
 	else
 		btcoexist->btc_write_4byte(btcoexist, 0x64, 0x30030004);
 
-	btc8192e2ant_coex_tbl_w_type(btcoexist, FORCE_EXEC, 0);
+	btc8192e2ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
 
 	/* antenna switch control parameter */
 	btcoexist->btc_write_4byte(btcoexist, 0x858, 0x55555555);
@@ -3232,7 +2638,7 @@ static void halbtc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist,
 	u16tmp |= BIT9;
 	btcoexist->btc_write_2byte(btcoexist, 0x40, u16tmp);
 
-	/* enable PTA I2C mailbox  */
+	/* enable PTA I2C mailbox */
 	u8tmp = btcoexist->btc_read_1byte(btcoexist, 0x101);
 	u8tmp |= BIT4;
 	btcoexist->btc_write_1byte(btcoexist, 0x101, u8tmp);
@@ -3247,29 +2653,25 @@ static void halbtc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist,
 	btcoexist->btc_write_1byte(btcoexist, 0x7, u8tmp);
 }
 
-/*************************************************************
- *   work around function start with wa_halbtc8192e2ant_
- *************************************************************/
-
 /************************************************************
- *   extern function start with EXhalbtc8192e2ant_
+ *   extern function start with ex_btc8192e2ant_
  ************************************************************/
 
-void ex_halbtc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist)
+void ex_btc8192e2ant_init_hwconfig(struct btc_coexist *btcoexist)
 {
-	halbtc8192e2ant_init_hwconfig(btcoexist, true);
+	btc8192e2ant_init_hwconfig(btcoexist, true);
 }
 
-void ex_halbtc8192e2ant_init_coex_dm(struct btc_coexist *btcoexist)
+void ex_btc8192e2ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Coex Mechanism Init!!\n");
-	halbtc8192e2ant_init_coex_dm(btcoexist);
+	btc8192e2ant_init_coex_dm(btcoexist);
 }
 
-void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
+void ex_btc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 {
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	struct btc_stack_info *stack_info = &btcoexist->stack_info;
@@ -3278,8 +2680,8 @@ void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 	u16 u16tmp[4];
 	u32 u32tmp[4];
 	bool roam = false, scan = false, link = false, wifi_under_5g = false;
-	bool bt_hson = false, wifi_busy = false;
-	int wifirssi = 0, bt_hs_rssi = 0;
+	bool bt_hs_on = false, wifi_busy = false;
+	int wifi_rssi = 0, bt_hs_rssi = 0;
 	u32 wifi_bw, wifi_traffic_dir;
 	u8 wifi_dot11_chnl, wifi_hs_chnl;
 	u32 fw_ver = 0, bt_patch_ver = 0;
@@ -3316,21 +2718,21 @@ void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 		 glcoex_ver_date_8192e_2ant, glcoex_ver_8192e_2ant,
 		 fw_ver, bt_patch_ver, bt_patch_ver);
 
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hson);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 	btcoexist->btc_get(btcoexist, BTC_GET_U1_WIFI_DOT11_CHNL,
 			   &wifi_dot11_chnl);
 	btcoexist->btc_get(btcoexist, BTC_GET_U1_WIFI_HS_CHNL, &wifi_hs_chnl);
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = %d / %d(%d)",
 		 "Dot11 channel / HsMode(HsChnl)",
-		 wifi_dot11_chnl, bt_hson, wifi_hs_chnl);
+		 wifi_dot11_chnl, bt_hs_on, wifi_hs_chnl);
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = %3ph ",
 		 "H2C Wifi inform bt chnl Info", coex_dm->wifi_chnl_info);
 
-	btcoexist->btc_get(btcoexist, BTC_GET_S4_WIFI_RSSI, &wifirssi);
+	btcoexist->btc_get(btcoexist, BTC_GET_S4_WIFI_RSSI, &wifi_rssi);
 	btcoexist->btc_get(btcoexist, BTC_GET_S4_HS_RSSI, &bt_hs_rssi);
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = %d/ %d",
-		 "Wifi rssi/ HS rssi", wifirssi, bt_hs_rssi);
+		 "Wifi rssi/ HS rssi", wifi_rssi, bt_hs_rssi);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
@@ -3377,7 +2779,7 @@ void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 		if (coex_sta->bt_info_c2h_cnt[i]) {
 			RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG,
 				 "\r\n %-35s = %7ph(%d)",
-				 GLBtInfoSrc8192e2Ant[i],
+				 glbt_info_src_8192e_2ant[i],
 				 coex_sta->bt_info_c2h[i],
 				 coex_sta->bt_info_c2h_cnt[i]);
 		}
@@ -3390,7 +2792,7 @@ void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 	btcoexist->btc_disp_dbg_msg(btcoexist, BTC_DBG_DISP_FW_PWR_MODE_CMD);
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = 0x%x ", "SS Type",
-		 coex_dm->cur_sstype);
+		 coex_dm->cur_ss_type);
 
 	/* Sw mechanism	*/
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s",
@@ -3429,7 +2831,7 @@ void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = 0x%x/0x%x/0x%x/0x%x",
 		 "backup ARFR1/ARFR2/RL/AMaxTime", coex_dm->backup_arfr_cnt1,
-		 coex_dm->backup_arfr_cnt2, coex_dm->backup_retrylimit,
+		 coex_dm->backup_arfr_cnt2, coex_dm->backup_retry_limit,
 		 coex_dm->backup_ampdu_maxtime);
 
 	u32tmp[0] = btcoexist->btc_read_4byte(btcoexist, 0x430);
@@ -3485,12 +2887,12 @@ void ex_halbtc8192e2ant_display_coex_info(struct btc_coexist *btcoexist)
 		 "0x774(lp rx[31:16]/tx[15:0])",
 		 coex_sta->low_priority_rx, coex_sta->low_priority_tx);
 #if (BT_AUTO_REPORT_ONLY_8192E_2ANT == 1)
-	halbtc8192e2ant_monitor_bt_ctr(btcoexist);
+	btc8192e2ant_monitor_bt_ctr(btcoexist);
 #endif
 	btcoexist->btc_disp_dbg_msg(btcoexist, BTC_DBG_DISP_COEX_STATISTICS);
 }
 
-void ex_halbtc8192e2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8192e2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3498,7 +2900,7 @@ void ex_halbtc8192e2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS ENTER notify\n");
 		coex_sta->under_ips = true;
-		halbtc8192e2ant_coex_alloff(btcoexist);
+		btc8192e2ant_coex_all_off(btcoexist);
 	} else if (BTC_IPS_LEAVE == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS LEAVE notify\n");
@@ -3506,7 +2908,7 @@ void ex_halbtc8192e2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 	}
 }
 
-void ex_halbtc8192e2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8192e2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3521,7 +2923,7 @@ void ex_halbtc8192e2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 	}
 }
 
-void ex_halbtc8192e2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8192e2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3533,7 +2935,7 @@ void ex_halbtc8192e2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 			 "[BTCoex], SCAN FINISH notify\n");
 }
 
-void ex_halbtc8192e2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8192e2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3545,8 +2947,8 @@ void ex_halbtc8192e2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 			 "[BTCoex], CONNECT FINISH notify\n");
 }
 
-void ex_halbtc8192e2ant_media_status_notify(struct btc_coexist *btcoexist,
-					    u8 type)
+void ex_btc8192e2ant_media_status_notify(struct btc_coexist *btcoexist,
+					 u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[3] = {0};
@@ -3591,8 +2993,8 @@ void ex_halbtc8192e2ant_media_status_notify(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x66, 3, h2c_parameter);
 }
 
-void ex_halbtc8192e2ant_special_packet_notify(struct btc_coexist *btcoexist,
-					      u8 type)
+void ex_btc8192e2ant_special_packet_notify(struct btc_coexist *btcoexist,
+					   u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3601,8 +3003,8 @@ void ex_halbtc8192e2ant_special_packet_notify(struct btc_coexist *btcoexist,
 			 "[BTCoex], DHCP Packet notify\n");
 }
 
-void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
-				       u8 *tmp_buf, u8 length)
+void ex_btc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
+				    u8 *tmp_buf, u8 length)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 bt_info = 0;
@@ -3633,7 +3035,8 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 	}
 
 	if (BT_INFO_SRC_8192E_2ANT_WIFI_FW != rsp_source) {
-		coex_sta->bt_retry_cnt =	/* [3:0] */
+		/* [3:0] */
+		coex_sta->bt_retry_cnt =
 			coex_sta->bt_info_c2h[rsp_source][2] & 0xf;
 
 		coex_sta->bt_rssi =
@@ -3651,11 +3054,11 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 			btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 					   &wifi_connected);
 			if (wifi_connected)
-				ex_halbtc8192e2ant_media_status_notify(
+				ex_btc8192e2ant_media_status_notify(
 							btcoexist,
 							BTC_MEDIA_CONNECT);
 			else
-				ex_halbtc8192e2ant_media_status_notify(
+				ex_btc8192e2ant_media_status_notify(
 							btcoexist,
 							BTC_MEDIA_DISCONNECT);
 		}
@@ -3665,9 +3068,9 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 			    !btcoexist->stop_coex_dm) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "bit3, BT NOT ignore Wlan active!\n");
-				halbtc8192e2ant_IgnoreWlanAct(btcoexist,
-							      FORCE_EXEC,
-							      false);
+				btc8192e2ant_ignore_wlan_act(btcoexist,
+							     FORCE_EXEC,
+							     false);
 			}
 		} else {
 			/* BT already NOT ignore Wlan active,
@@ -3679,8 +3082,8 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 		if ((coex_sta->bt_info_ext & BIT4)) {
 			/* BT auto report already enabled, do nothing */
 		} else {
-			halbtc8192e2ant_bt_autoreport(btcoexist, FORCE_EXEC,
-						      true);
+			btc8192e2ant_bt_auto_report(btcoexist, FORCE_EXEC,
+						    true);
 		}
 #endif
 	}
@@ -3718,9 +3121,9 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 			coex_sta->sco_exist = false;
 	}
 
-	halbtc8192e2ant_update_btlink_info(btcoexist);
+	btc8192e2ant_update_bt_link_info(btcoexist);
 
-	if (!(bt_info&BT_INFO_8192E_2ANT_B_CONNECTION)) {
+	if (!(bt_info & BT_INFO_8192E_2ANT_B_CONNECTION)) {
 		coex_dm->bt_status = BT_8192E_2ANT_BT_STATUS_NON_CONNECTED_IDLE;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], BT Non-Connected idle!!!\n");
@@ -3728,12 +3131,12 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_dm->bt_status = BT_8192E_2ANT_BT_STATUS_CONNECTED_IDLE;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], bt_infoNotify(), BT Connected-idle!!!\n");
-	} else if ((bt_info&BT_INFO_8192E_2ANT_B_SCO_ESCO) ||
-		   (bt_info&BT_INFO_8192E_2ANT_B_SCO_BUSY)) {
+	} else if ((bt_info & BT_INFO_8192E_2ANT_B_SCO_ESCO) ||
+		   (bt_info & BT_INFO_8192E_2ANT_B_SCO_BUSY)) {
 		coex_dm->bt_status = BT_8192E_2ANT_BT_STATUS_SCO_BUSY;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], bt_infoNotify(), BT SCO busy!!!\n");
-	} else if (bt_info&BT_INFO_8192E_2ANT_B_ACL_BUSY) {
+	} else if (bt_info & BT_INFO_8192E_2ANT_B_ACL_BUSY) {
 		coex_dm->bt_status = BT_8192E_2ANT_BT_STATUS_ACL_BUSY;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], bt_infoNotify(), BT ACL busy!!!\n");
@@ -3758,12 +3161,7 @@ void ex_halbtc8192e2ant_bt_info_notify(struct btc_coexist *btcoexist,
 	coex_dm->limited_dig = limited_dig;
 	btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_LIMITED_DIG, &limited_dig);
 
-	halbtc8192e2ant_run_coexist_mechanism(btcoexist);
-}
-
-void ex_halbtc8192e2ant_stack_operation_notify(struct btc_coexist *btcoexist,
-					       u8 type)
-{
+	btc8192e2ant_run_coexist_mechanism(btcoexist);
 }
 
 void ex_halbtc8192e2ant_halt_notify(struct btc_coexist *btcoexist)
@@ -3772,11 +3170,11 @@ void ex_halbtc8192e2ant_halt_notify(struct btc_coexist *btcoexist)
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD, "[BTCoex], Halt notify\n");
 
-	halbtc8192e2ant_IgnoreWlanAct(btcoexist, FORCE_EXEC, true);
-	ex_halbtc8192e2ant_media_status_notify(btcoexist, BTC_MEDIA_DISCONNECT);
+	btc8192e2ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
+	ex_btc8192e2ant_media_status_notify(btcoexist, BTC_MEDIA_DISCONNECT);
 }
 
-void ex_halbtc8192e2ant_periodical(struct btc_coexist *btcoexist)
+void ex_btc8192e2ant_periodical(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	static u8 dis_ver_info_cnt;
@@ -3810,12 +3208,12 @@ void ex_halbtc8192e2ant_periodical(struct btc_coexist *btcoexist)
 	}
 
 #if (BT_AUTO_REPORT_ONLY_8192E_2ANT == 0)
-	halbtc8192e2ant_querybt_info(btcoexist);
-	halbtc8192e2ant_monitor_bt_ctr(btcoexist);
-	btc8192e2ant_monitor_bt_enable_dis(btcoexist);
+	btc8192e2ant_query_bt_info(btcoexist);
+	btc8192e2ant_monitor_bt_ctr(btcoexist);
+	btc8192e2ant_monitor_bt_enable_disable(btcoexist);
 #else
-	if (halbtc8192e2ant_iswifi_status_changed(btcoexist) ||
+	if (btc8192e2ant_is_wifi_status_changed(btcoexist) ||
 	    coex_dm->auto_tdma_adjust)
-		halbtc8192e2ant_run_coexist_mechanism(btcoexist);
+		btc8192e2ant_run_coexist_mechanism(btcoexist);
 #endif
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.h b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.h
index 75e1f7d0db06..fc0fa87ec404 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.h
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8192e2ant.h
@@ -116,7 +116,7 @@ struct coex_dm_8192e_2ant {
 
 	u32 backup_arfr_cnt1;	/* Auto Rate Fallback Retry cnt */
 	u32 backup_arfr_cnt2;	/* Auto Rate Fallback Retry cnt */
-	u16 backup_retrylimit;
+	u16 backup_retry_limit;
 	u8 backup_ampdu_maxtime;
 
 	/* algorithm related */
@@ -125,18 +125,18 @@ struct coex_dm_8192e_2ant {
 	u8 bt_status;
 	u8 wifi_chnl_info[3];
 
-	u8 pre_sstype;
-	u8 cur_sstype;
+	u8 pre_ss_type;
+	u8 cur_ss_type;
 
-	u32 prera_mask;
-	u32 curra_mask;
-	u8 curra_masktype;
-	u8 pre_arfrtype;
-	u8 cur_arfrtype;
-	u8 pre_retrylimit_type;
-	u8 cur_retrylimit_type;
-	u8 pre_ampdutime_type;
-	u8 cur_ampdutime_type;
+	u32 pre_ra_mask;
+	u32 cur_ra_mask;
+	u8 cur_ra_mask_type;
+	u8 pre_arfr_type;
+	u8 cur_arfr_type;
+	u8 pre_retry_limit_type;
+	u8 cur_retry_limit_type;
+	u8 pre_ampdu_time_type;
+	u8 cur_ampdu_time_type;
 };
 
 struct coex_sta_8192e_2ant {
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c
index d67bbfb6ad8e..2003c8c51dcc 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c
@@ -45,7 +45,7 @@ static struct coex_dm_8723b_1ant *coex_dm = &glcoex_dm_8723b_1ant;
 static struct coex_sta_8723b_1ant glcoex_sta_8723b_1ant;
 static struct coex_sta_8723b_1ant *coex_sta = &glcoex_sta_8723b_1ant;
 
-static const char *const GLBtInfoSrc8723b1Ant[] = {
+static const char *const glbt_info_src_8723b_1ant[] = {
 	"BT Info[wifi fw]",
 	"BT Info[bt rsp]",
 	"BT Info[bt auto report]",
@@ -60,188 +60,6 @@ static u32 glcoex_ver_8723b_1ant = 0x47;
 /***************************************************************
  * local function start with halbtc8723b1ant_
  ***************************************************************/
-static u8 halbtc8723b1ant_bt_rssi_state(struct btc_coexist *btcoexist,
-					u8 level_num, u8 rssi_thresh,
-					u8 rssi_thresh1)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	s32 bt_rssi = 0;
-	u8 bt_rssi_state = coex_sta->pre_bt_rssi_state;
-
-	bt_rssi = coex_sta->bt_rssi;
-
-	if (level_num == 2) {
-		if ((coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_LOW) ||
-		    (coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-			if (bt_rssi >= rssi_thresh +
-					BTC_RSSI_COEX_THRESH_TOL_8723B_1ANT) {
-				bt_rssi_state = BTC_RSSI_STATE_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state switch to High\n");
-			} else {
-				bt_rssi_state = BTC_RSSI_STATE_STAY_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state stay at Low\n");
-			}
-		} else {
-			if (bt_rssi < rssi_thresh) {
-				bt_rssi_state = BTC_RSSI_STATE_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state switch to Low\n");
-			} else {
-				bt_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state stay at High\n");
-			}
-		}
-	} else if (level_num == 3) {
-		if (rssi_thresh > rssi_thresh1) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], BT Rssi thresh error!!\n");
-			return coex_sta->pre_bt_rssi_state;
-		}
-
-		if ((coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_LOW) ||
-		    (coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-			if (bt_rssi >= rssi_thresh +
-					BTC_RSSI_COEX_THRESH_TOL_8723B_1ANT) {
-				bt_rssi_state = BTC_RSSI_STATE_MEDIUM;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state switch to Medium\n");
-			} else {
-				bt_rssi_state = BTC_RSSI_STATE_STAY_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state stay at Low\n");
-			}
-		} else if ((coex_sta->pre_bt_rssi_state ==
-					BTC_RSSI_STATE_MEDIUM) ||
-			  (coex_sta->pre_bt_rssi_state ==
-					BTC_RSSI_STATE_STAY_MEDIUM)) {
-			if (bt_rssi >= rssi_thresh1 +
-					BTC_RSSI_COEX_THRESH_TOL_8723B_1ANT) {
-				bt_rssi_state = BTC_RSSI_STATE_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state switch to High\n");
-			} else if (bt_rssi < rssi_thresh) {
-				bt_rssi_state = BTC_RSSI_STATE_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state switch to Low\n");
-			} else {
-				bt_rssi_state = BTC_RSSI_STATE_STAY_MEDIUM;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state stay at Medium\n");
-			}
-		} else {
-			if (bt_rssi < rssi_thresh1) {
-				bt_rssi_state = BTC_RSSI_STATE_MEDIUM;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state switch to Medium\n");
-			} else {
-				bt_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Rssi state stay at High\n");
-			}
-		}
-	}
-
-	coex_sta->pre_bt_rssi_state = bt_rssi_state;
-
-	return bt_rssi_state;
-}
-
-static u8 halbtc8723b1ant_wifi_rssi_state(struct btc_coexist *btcoexist,
-					  u8 index, u8 level_num,
-					  u8 rssi_thresh, u8 rssi_thresh1)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	s32 wifi_rssi = 0;
-	u8 wifi_rssi_state = coex_sta->pre_wifi_rssi_state[index];
-
-	btcoexist->btc_get(btcoexist,
-		BTC_GET_S4_WIFI_RSSI, &wifi_rssi);
-
-	if (level_num == 2) {
-		if ((coex_sta->pre_wifi_rssi_state[index] ==
-					BTC_RSSI_STATE_LOW) ||
-		    (coex_sta->pre_wifi_rssi_state[index] ==
-					BTC_RSSI_STATE_STAY_LOW)) {
-			if (wifi_rssi >= rssi_thresh +
-					BTC_RSSI_COEX_THRESH_TOL_8723B_1ANT) {
-				wifi_rssi_state = BTC_RSSI_STATE_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state switch to High\n");
-			} else {
-				wifi_rssi_state = BTC_RSSI_STATE_STAY_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state stay at Low\n");
-			}
-		} else {
-			if (wifi_rssi < rssi_thresh) {
-				wifi_rssi_state = BTC_RSSI_STATE_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state switch to Low\n");
-			} else {
-				wifi_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state stay at High\n");
-			}
-		}
-	} else if (level_num == 3) {
-		if (rssi_thresh > rssi_thresh1) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], wifi RSSI thresh error!!\n");
-			return coex_sta->pre_wifi_rssi_state[index];
-		}
-
-		if ((coex_sta->pre_wifi_rssi_state[index] ==
-						BTC_RSSI_STATE_LOW) ||
-		    (coex_sta->pre_wifi_rssi_state[index] ==
-						BTC_RSSI_STATE_STAY_LOW)) {
-			if (wifi_rssi >= rssi_thresh +
-					 BTC_RSSI_COEX_THRESH_TOL_8723B_1ANT) {
-				wifi_rssi_state = BTC_RSSI_STATE_MEDIUM;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state switch to Medium\n");
-			} else {
-				wifi_rssi_state = BTC_RSSI_STATE_STAY_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state stay at Low\n");
-			}
-		} else if ((coex_sta->pre_wifi_rssi_state[index] ==
-						BTC_RSSI_STATE_MEDIUM) ||
-			   (coex_sta->pre_wifi_rssi_state[index] ==
-						BTC_RSSI_STATE_STAY_MEDIUM)) {
-			if (wifi_rssi >= rssi_thresh1 +
-					 BTC_RSSI_COEX_THRESH_TOL_8723B_1ANT) {
-				wifi_rssi_state = BTC_RSSI_STATE_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state switch to High\n");
-			} else if (wifi_rssi < rssi_thresh) {
-				wifi_rssi_state = BTC_RSSI_STATE_LOW;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state switch to Low\n");
-			} else {
-				wifi_rssi_state = BTC_RSSI_STATE_STAY_MEDIUM;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state stay at Medium\n");
-			}
-		} else {
-			if (wifi_rssi < rssi_thresh1) {
-				wifi_rssi_state = BTC_RSSI_STATE_MEDIUM;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state switch to Medium\n");
-			} else {
-				wifi_rssi_state = BTC_RSSI_STATE_STAY_HIGH;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], wifi RSSI state stay at High\n");
-			}
-		}
-	}
-
-	coex_sta->pre_wifi_rssi_state[index] = wifi_rssi_state;
-
-	return wifi_rssi_state;
-}
 
 static void halbtc8723b1ant_updatera_mask(struct btc_coexist *btcoexist,
 					  bool force_exec, u32 dis_rate_mask)
@@ -249,7 +67,7 @@ static void halbtc8723b1ant_updatera_mask(struct btc_coexist *btcoexist,
 	coex_dm->curra_mask = dis_rate_mask;
 
 	if (force_exec || (coex_dm->prera_mask != coex_dm->curra_mask))
-		btcoexist->btc_set(btcoexist, BTC_SET_ACT_UPDATE_ra_mask,
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_UPDATE_RAMASK,
 				   &coex_dm->curra_mask);
 
 	coex_dm->prera_mask = coex_dm->curra_mask;
@@ -326,15 +144,14 @@ static void halbtc8723b1ant_ampdu_maxtime(struct btc_coexist *btcoexist,
 		coex_dm->cur_ampdu_time_type)) {
 		switch (coex_dm->cur_ampdu_time_type) {
 		case 0:	/* normal mode */
-				btcoexist->btc_write_1byte(btcoexist, 0x456,
-						coex_dm->backup_ampdu_max_time);
-				break;
+			btcoexist->btc_write_1byte(btcoexist, 0x456,
+					coex_dm->backup_ampdu_max_time);
+			break;
 		case 1:	/* AMPDU timw = 0x38 * 32us */
-				btcoexist->btc_write_1byte(btcoexist,
-							   0x456, 0x38);
-				break;
+			btcoexist->btc_write_1byte(btcoexist, 0x456, 0x38);
+			break;
 		default:
-				break;
+			break;
 		}
 	}
 
@@ -354,7 +171,7 @@ static void halbtc8723b1ant_limited_tx(struct btc_coexist *btcoexist,
 		halbtc8723b1ant_updatera_mask(btcoexist, force_exec,
 					      0x00000003);
 		break;
-	/* disable cck 1/2/5.5, ofdm 6/9/12/18/24, mcs 0/1/2/3/4*/
+	/* disable cck 1/2/5.5, ofdm 6/9/12/18/24, mcs 0/1/2/3/4 */
 	case 2:
 		halbtc8723b1ant_updatera_mask(btcoexist, force_exec,
 					      0x0001f1f7);
@@ -426,7 +243,8 @@ static void halbtc8723b1ant_query_bt_info(struct btc_coexist *btcoexist)
 
 	coex_sta->c2h_bt_info_req_sent = true;
 
-	h2c_parameter[0] |= BIT0;	/* trigger*/
+	/* trigger */
+	h2c_parameter[0] |= BIT0;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Query Bt Info, FW write 0x61 = 0x%x\n",
@@ -515,202 +333,6 @@ static void halbtc8723b1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 		bt_link_info->hid_only = false;
 }
 
-static u8 halbtc8723b1ant_action_algorithm(struct btc_coexist *btcoexist)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
-	bool bt_hs_on = false;
-	u8 algorithm = BT_8723B_1ANT_COEX_ALGO_UNDEFINED;
-	u8 numdiffprofile = 0;
-
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
-
-	if (!bt_link_info->bt_link_exist) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], No BT link exists!!!\n");
-		return algorithm;
-	}
-
-	if (bt_link_info->sco_exist)
-		numdiffprofile++;
-	if (bt_link_info->hid_exist)
-		numdiffprofile++;
-	if (bt_link_info->pan_exist)
-		numdiffprofile++;
-	if (bt_link_info->a2dp_exist)
-		numdiffprofile++;
-
-	if (numdiffprofile == 1) {
-		if (bt_link_info->sco_exist) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], BT Profile = SCO only\n");
-			algorithm = BT_8723B_1ANT_COEX_ALGO_SCO;
-		} else {
-			if (bt_link_info->hid_exist) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Profile = HID only\n");
-				algorithm = BT_8723B_1ANT_COEX_ALGO_HID;
-			} else if (bt_link_info->a2dp_exist) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Profile = A2DP only\n");
-				algorithm = BT_8723B_1ANT_COEX_ALGO_A2DP;
-			} else if (bt_link_info->pan_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = PAN(HS) only\n");
-					algorithm =
-						BT_8723B_1ANT_COEX_ALGO_PANHS;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = PAN(EDR) only\n");
-					algorithm =
-						BT_8723B_1ANT_COEX_ALGO_PANEDR;
-				}
-			}
-		}
-	} else if (numdiffprofile == 2) {
-		if (bt_link_info->sco_exist) {
-			if (bt_link_info->hid_exist) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Profile = SCO + HID\n");
-				algorithm = BT_8723B_1ANT_COEX_ALGO_HID;
-			} else if (bt_link_info->a2dp_exist) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Profile = SCO + A2DP ==> SCO\n");
-				algorithm = BT_8723B_1ANT_COEX_ALGO_SCO;
-			} else if (bt_link_info->pan_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + PAN(HS)\n");
-					algorithm = BT_8723B_1ANT_COEX_ALGO_SCO;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + PAN(EDR)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_PANEDR_HID;
-				}
-			}
-		} else {
-			if (bt_link_info->hid_exist &&
-			    bt_link_info->a2dp_exist) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Profile = HID + A2DP\n");
-				algorithm = BT_8723B_1ANT_COEX_ALGO_HID_A2DP;
-			} else if (bt_link_info->hid_exist &&
-				   bt_link_info->pan_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = HID + PAN(HS)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_HID_A2DP;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = HID + PAN(EDR)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_PANEDR_HID;
-				}
-			} else if (bt_link_info->pan_exist &&
-				   bt_link_info->a2dp_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = A2DP + PAN(HS)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_A2DP_PANHS;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = A2DP + PAN(EDR)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_PANEDR_A2DP;
-				}
-			}
-		}
-	} else if (numdiffprofile == 3) {
-		if (bt_link_info->sco_exist) {
-			if (bt_link_info->hid_exist &&
-			    bt_link_info->a2dp_exist) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], BT Profile = SCO + HID + A2DP ==> HID\n");
-				algorithm = BT_8723B_1ANT_COEX_ALGO_HID;
-			} else if (bt_link_info->hid_exist &&
-				   bt_link_info->pan_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + HID + PAN(HS)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_HID_A2DP;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + HID + PAN(EDR)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_PANEDR_HID;
-				}
-			} else if (bt_link_info->pan_exist &&
-				   bt_link_info->a2dp_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + A2DP + PAN(HS)\n");
-					algorithm = BT_8723B_1ANT_COEX_ALGO_SCO;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + A2DP + PAN(EDR) ==> HID\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_PANEDR_HID;
-				}
-			}
-		} else {
-			if (bt_link_info->hid_exist &&
-			    bt_link_info->pan_exist &&
-			    bt_link_info->a2dp_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = HID + A2DP + PAN(HS)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_HID_A2DP;
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = HID + A2DP + PAN(EDR)\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_HID_A2DP_PANEDR;
-				}
-			}
-		}
-	} else if (numdiffprofile >= 3) {
-		if (bt_link_info->sco_exist) {
-			if (bt_link_info->hid_exist &&
-			    bt_link_info->pan_exist &&
-			    bt_link_info->a2dp_exist) {
-				if (bt_hs_on) {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], Error!!! BT Profile = SCO + HID + A2DP + PAN(HS)\n");
-				} else {
-					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
-						 DBG_LOUD,
-						 "[BTCoex], BT Profile = SCO + HID + A2DP + PAN(EDR)==>PAN(EDR)+HID\n");
-					algorithm =
-					    BT_8723B_1ANT_COEX_ALGO_PANEDR_HID;
-				}
-			}
-		}
-	}
-
-	return algorithm;
-}
-
 static void btc8723b1ant_set_sw_pen_tx_rate_adapt(struct btc_coexist *btcoexist,
 						  bool low_penalty_ra)
 {
@@ -721,11 +343,11 @@ static void btc8723b1ant_set_sw_pen_tx_rate_adapt(struct btc_coexist *btcoexist,
 
 	if (low_penalty_ra) {
 		h2c_parameter[1] |= BIT0;
-		/*normal rate except MCS7/6/5, OFDM54/48/36 */
+		/* normal rate except MCS7/6/5, OFDM54/48/36 */
 		h2c_parameter[2] = 0x00;
-		h2c_parameter[3] = 0xf7;  /*MCS7 or OFDM54 */
-		h2c_parameter[4] = 0xf8;  /*MCS6 or OFDM48 */
-		h2c_parameter[5] = 0xf9;  /*MCS5 or OFDM36 */
+		h2c_parameter[3] = 0xf7;  /* MCS7 or OFDM54 */
+		h2c_parameter[4] = 0xf8;  /* MCS6 or OFDM48 */
+		h2c_parameter[5] = 0xf9;  /* MCS5 or OFDM36 */
 	}
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -846,8 +468,9 @@ static void halbtc8723b1ant_coex_table_with_type(struct btc_coexist *btcoexist,
 	}
 }
 
-static void halbtc8723b1ant_SetFwIgnoreWlanAct(struct btc_coexist *btcoexist,
-					       bool enable)
+static void
+halbtc8723b1ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoexist,
+				       bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
@@ -882,7 +505,7 @@ static void halbtc8723b1ant_ignore_wlan_act(struct btc_coexist *btcoexist,
 		    coex_dm->cur_ignore_wlan_act)
 			return;
 	}
-	halbtc8723b1ant_SetFwIgnoreWlanAct(btcoexist, enable);
+	halbtc8723b1ant_set_fw_ignore_wlan_act(btcoexist, enable);
 
 	coex_dm->pre_ignore_wlan_act = coex_dm->cur_ignore_wlan_act;
 }
@@ -944,9 +567,9 @@ static void halbtc8723b1ant_set_lps_rpwm(struct btc_coexist *btcoexist,
 	btcoexist->btc_set(btcoexist, BTC_SET_U1_RPWM_VAL, &rpwm);
 }
 
-static void halbtc8723b1ant_LpsRpwm(struct btc_coexist *btcoexist,
-				    bool force_exec,
-				    u8 lps_val, u8 rpwm_val)
+static void halbtc8723b1ant_lps_rpwm(struct btc_coexist *btcoexist,
+				     bool force_exec,
+				     u8 lps_val, u8 rpwm_val)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -987,9 +610,9 @@ static void halbtc8723b1ant_sw_mechanism(struct btc_coexist *btcoexist,
 	halbtc8723b1ant_low_penalty_ra(btcoexist, NORMAL_EXEC, low_penalty_ra);
 }
 
-static void halbtc8723b1ant_SetAntPath(struct btc_coexist *btcoexist,
-				       u8 ant_pos_type, bool init_hw_cfg,
-				bool wifi_off)
+static void halbtc8723b1ant_set_ant_path(struct btc_coexist *btcoexist,
+					 u8 ant_pos_type, bool init_hw_cfg,
+					 bool wifi_off)
 {
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	u32 fw_ver = 0, u32tmp = 0;
@@ -1028,7 +651,7 @@ static void halbtc8723b1ant_SetAntPath(struct btc_coexist *btcoexist,
 	if (use_ext_switch) {
 		if (init_hw_cfg) {
 			/* 0x4c[23] = 0, 0x4c[24] = 1
-			 *	Antenna control by WL/BT
+			 * Antenna control by WL/BT
 			 */
 			u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
 			u32tmp &= ~BIT23;
@@ -1037,35 +660,36 @@ static void halbtc8723b1ant_SetAntPath(struct btc_coexist *btcoexist,
 
 			if (board_info->btdm_ant_pos ==
 			    BTC_ANTENNA_AT_MAIN_PORT) {
-				/* Main Ant to  BT for IPS case 0x4c[23] = 1 */
+				/* Main Ant to BT for IPS case 0x4c[23] = 1 */
 				btcoexist->btc_write_1byte_bitmask(btcoexist,
 								   0x64, 0x1,
 								   0x1);
 
-				/*tell firmware "no antenna inverse"*/
+				/* tell firmware "no antenna inverse" */
 				h2c_parameter[0] = 0;
 				h2c_parameter[1] = 1;  /*ext switch type*/
 				btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 							h2c_parameter);
 			} else {
-				/*Aux Ant to  BT for IPS case 0x4c[23] = 1 */
+				/* Aux Ant to  BT for IPS case 0x4c[23] = 1 */
 				btcoexist->btc_write_1byte_bitmask(btcoexist,
 								   0x64, 0x1,
 								   0x0);
 
-				/*tell firmware "antenna inverse"*/
+				/* tell firmware "antenna inverse" */
 				h2c_parameter[0] = 1;
-				h2c_parameter[1] = 1;  /*ext switch type*/
+				h2c_parameter[1] = 1; /* ext switch type */
 				btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 							h2c_parameter);
 			}
 		}
 
-		/* fixed internal switch first*/
-		/* fixed internal switch S1->WiFi, S0->BT*/
+		/* fixed internal switch first
+		 * fixed internal switch S1->WiFi, S0->BT
+		 */
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT)
 			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
-		else/* fixed internal switch S0->WiFi, S1->BT*/
+		else	/* fixed internal switch S0->WiFi, S1->BT */
 			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x280);
 
 		/* ext switch setting */
@@ -1108,7 +732,7 @@ static void halbtc8723b1ant_SetAntPath(struct btc_coexist *btcoexist,
 
 	} else {
 		if (init_hw_cfg) {
-			/* 0x4c[23] = 1, 0x4c[24] = 0  Antenna control by 0x64*/
+			/* 0x4c[23] = 1, 0x4c[24] = 0 Antenna control by 0x64 */
 			u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
 			u32tmp |= BIT23;
 			u32tmp &= ~BIT24;
@@ -1116,41 +740,42 @@ static void halbtc8723b1ant_SetAntPath(struct btc_coexist *btcoexist,
 
 			if (board_info->btdm_ant_pos ==
 			    BTC_ANTENNA_AT_MAIN_PORT) {
-				/*Main Ant to  WiFi for IPS case 0x4c[23] = 1*/
+				/* Main Ant to WiFi for IPS case 0x4c[23] = 1 */
 				btcoexist->btc_write_1byte_bitmask(btcoexist,
 								   0x64, 0x1,
 								   0x0);
 
-				/*tell firmware "no antenna inverse"*/
+				/* tell firmware "no antenna inverse" */
 				h2c_parameter[0] = 0;
-				h2c_parameter[1] = 0;  /*internal switch type*/
+				h2c_parameter[1] = 0; /* internal switch type */
 				btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 							h2c_parameter);
 			} else {
-				/*Aux Ant to  BT for IPS case 0x4c[23] = 1*/
+				/* Aux Ant to BT for IPS case 0x4c[23] = 1 */
 				btcoexist->btc_write_1byte_bitmask(btcoexist,
 								   0x64, 0x1,
 								   0x1);
 
-				/*tell firmware "antenna inverse"*/
+				/* tell firmware "antenna inverse" */
 				h2c_parameter[0] = 1;
-				h2c_parameter[1] = 0;  /*internal switch type*/
+				h2c_parameter[1] = 0; /* internal switch type */
 				btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 							h2c_parameter);
 			}
 		}
 
-		/* fixed external switch first*/
-		/*Main->WiFi, Aux->BT*/
+		/* fixed external switch first
+		 * Main->WiFi, Aux->BT
+		 */
 		if (board_info->btdm_ant_pos ==
 			BTC_ANTENNA_AT_MAIN_PORT)
 			btcoexist->btc_write_1byte_bitmask(btcoexist, 0x92c,
 							   0x3, 0x1);
-		else/*Main->BT, Aux->WiFi */
+		else	/* Main->BT, Aux->WiFi */
 			btcoexist->btc_write_1byte_bitmask(btcoexist, 0x92c,
 							   0x3, 0x2);
 
-		/* internal switch setting*/
+		/* internal switch setting */
 		switch (ant_pos_type) {
 		case BTC_ANT_PATH_WIFI:
 			if (board_info->btdm_ant_pos ==
@@ -1365,7 +990,7 @@ static void halbtc8723b1ant_ps_tdma(struct btc_coexist *btcoexist,
 			halbtc8723b1ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x12,
 						       0x3, 0x14, 0x50);
 			break;
-		/* SoftAP only with no sta associated,BT disable ,
+		/* SoftAP only with no sta associated, BT disable,
 		 * TDMA mode for power saving
 		 * here softap mode screen off will cost 70-80mA for phone
 		 */
@@ -1376,24 +1001,29 @@ static void halbtc8723b1ant_ps_tdma(struct btc_coexist *btcoexist,
 		}
 	} else {
 		switch (type) {
-		case 8: /*PTA Control */
+		case 8: /* PTA Control */
 			halbtc8723b1ant_set_fw_ps_tdma(btcoexist, 0x8, 0x0,
 						       0x0, 0x0, 0x0);
-			halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_PTA,
-						   false, false);
+			halbtc8723b1ant_set_ant_path(btcoexist,
+						     BTC_ANT_PATH_PTA,
+						     false, false);
 			break;
 		case 0:
-		default:  /*Software control, Antenna at BT side */
+		default:
+			/* Software control, Antenna at BT side */
 			halbtc8723b1ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0,
 						       0x0, 0x0, 0x0);
-			halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_BT,
-						   false, false);
+			halbtc8723b1ant_set_ant_path(btcoexist,
+						     BTC_ANT_PATH_BT,
+						     false, false);
 			break;
-		case 9:   /*Software control, Antenna at WiFi side */
+		case 9:
+			/* Software control, Antenna at WiFi side */
 			halbtc8723b1ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0,
 						       0x0, 0x0, 0x0);
-			halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_WIFI,
-						   false, false);
+			halbtc8723b1ant_set_ant_path(btcoexist,
+						     BTC_ANT_PATH_WIFI,
+						     false, false);
 			break;
 		}
 	}
@@ -1407,247 +1037,15 @@ static void halbtc8723b1ant_ps_tdma(struct btc_coexist *btcoexist,
 	coex_dm->pre_ps_tdma = coex_dm->cur_ps_tdma;
 }
 
-static bool halbtc8723b1ant_is_common_action(struct btc_coexist *btcoexist)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool commom = false, wifi_connected = false;
-	bool wifi_busy = false;
-
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
-			   &wifi_connected);
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
-
-	if (!wifi_connected &&
-	    BT_8723B_1ANT_BT_STATUS_NON_CONNECTED_IDLE == coex_dm->bt_status) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi non connected-idle + BT non connected-idle!!\n");
-		halbtc8723b1ant_sw_mechanism(btcoexist, false);
-		commom = true;
-	} else if (wifi_connected &&
-		   (BT_8723B_1ANT_BT_STATUS_NON_CONNECTED_IDLE ==
-		    coex_dm->bt_status)) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi connected + BT non connected-idle!!\n");
-		halbtc8723b1ant_sw_mechanism(btcoexist, false);
-		commom = true;
-	} else if (!wifi_connected &&
-		   (BT_8723B_1ANT_BT_STATUS_CONNECTED_IDLE ==
-		    coex_dm->bt_status)) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi non connected-idle + BT connected-idle!!\n");
-		halbtc8723b1ant_sw_mechanism(btcoexist, false);
-		commom = true;
-	} else if (wifi_connected &&
-		   (BT_8723B_1ANT_BT_STATUS_CONNECTED_IDLE ==
-		    coex_dm->bt_status)) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi connected + BT connected-idle!!\n");
-		halbtc8723b1ant_sw_mechanism(btcoexist, false);
-		commom = true;
-	} else if (!wifi_connected &&
-		   (BT_8723B_1ANT_BT_STATUS_CONNECTED_IDLE !=
-		    coex_dm->bt_status)) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi non connected-idle + BT Busy!!\n");
-		halbtc8723b1ant_sw_mechanism(btcoexist, false);
-		commom = true;
-	} else {
-		if (wifi_busy)
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi Connected-Busy + BT Busy!!\n");
-		else
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi Connected-Idle + BT Busy!!\n");
-
-		commom = false;
-	}
-
-	return commom;
-}
-
-static void btc8723b1ant_tdma_dur_adj_for_acl(struct btc_coexist *btcoexist,
-					      u8 wifi_status)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static s32 up, dn, m, n, wait_count;
-	/* 0: no change, +1: increase WiFi duration,
-	 * -1: decrease WiFi duration
-	 */
-	s32 result;
-	u8 retry_count = 0, bt_info_ext;
-	bool wifi_busy = false;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], TdmaDurationAdjustForAcl()\n");
-
-	if (BT_8723B_1ANT_WIFI_STATUS_CONNECTED_BUSY == wifi_status)
-		wifi_busy = true;
-	else
-		wifi_busy = false;
-
-	if ((BT_8723B_1ANT_WIFI_STATUS_NON_CONNECTED_ASSO_AUTH_SCAN ==
-							 wifi_status) ||
-	    (BT_8723B_1ANT_WIFI_STATUS_CONNECTED_SCAN == wifi_status) ||
-	    (BT_8723B_1ANT_WIFI_STATUS_CONNECTED_SPECIAL_PKT == wifi_status)) {
-		if (coex_dm->cur_ps_tdma != 1 && coex_dm->cur_ps_tdma != 2 &&
-		    coex_dm->cur_ps_tdma != 3 && coex_dm->cur_ps_tdma != 9) {
-			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 9);
-			coex_dm->tdma_adj_type = 9;
-
-			up = 0;
-			dn = 0;
-			m = 1;
-			n = 3;
-			result = 0;
-			wait_count = 0;
-		}
-		return;
-	}
-
-	if (!coex_dm->auto_tdma_adjust) {
-		coex_dm->auto_tdma_adjust = true;
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], first run TdmaDurationAdjust()!!\n");
-
-		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 2);
-		coex_dm->tdma_adj_type = 2;
-
-		up = 0;
-		dn = 0;
-		m = 1;
-		n = 3;
-		result = 0;
-		wait_count = 0;
-	} else {
-		/*accquire the BT TRx retry count from BT_Info byte2 */
-		retry_count = coex_sta->bt_retry_cnt;
-		bt_info_ext = coex_sta->bt_info_ext;
-		result = 0;
-		wait_count++;
-		/* no retry in the last 2-second duration */
-		if (retry_count == 0) {
-			up++;
-			dn--;
-
-			if (dn <= 0)
-				dn = 0;
-
-			if (up >= n) {
-				wait_count = 0;
-				n = 3;
-				up = 0;
-				dn = 0;
-				result = 1;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Increase wifi duration!!\n");
-			}
-		} else if (retry_count <= 3) {
-			up--;
-			dn++;
-
-			if (up <= 0)
-				up = 0;
-
-			if (dn == 2) {
-				if (wait_count <= 2)
-					m++;
-				else
-					m = 1;
-
-				if (m >= 20)
-					m = 20;
-
-				n = 3 * m;
-				up = 0;
-				dn = 0;
-				wait_count = 0;
-				result = -1;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Decrease wifi duration for retryCounter<3!!\n");
-			}
-		} else {
-			if (wait_count == 1)
-				m++;
-			else
-				m = 1;
-
-			if (m >= 20)
-				m = 20;
-
-			n = 3 * m;
-			up = 0;
-			dn = 0;
-			wait_count = 0;
-			result = -1;
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Decrease wifi duration for retryCounter>3!!\n");
-		}
-
-		if (result == -1) {
-			if ((BT_INFO_8723B_1ANT_A2DP_BASIC_RATE(bt_info_ext)) &&
-			    ((coex_dm->cur_ps_tdma == 1) ||
-			     (coex_dm->cur_ps_tdma == 2))) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			}
-		} else if (result == 1) {
-			if ((BT_INFO_8723B_1ANT_A2DP_BASIC_RATE(bt_info_ext)) &&
-			    ((coex_dm->cur_ps_tdma == 1) ||
-			     (coex_dm->cur_ps_tdma == 2))) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 1);
-				coex_dm->tdma_adj_type = 1;
-			}
-		} else {	  /*no change */
-			/*if busy / idle change */
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex],********* TDMA(on, %d) ********\n",
-				 coex_dm->cur_ps_tdma);
-		}
-
-		if (coex_dm->cur_ps_tdma != 1 && coex_dm->cur_ps_tdma != 2 &&
-		    coex_dm->cur_ps_tdma != 9 && coex_dm->cur_ps_tdma != 11) {
-			/* recover to previous adjust type */
-			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true,
-						coex_dm->tdma_adj_type);
-		}
-	}
-}
-
-static void btc8723b1ant_pstdmachkpwrsave(struct btc_coexist *btcoexist,
-					  bool new_ps_state)
+static void halbtc8723b1ant_ps_tdma_chk_pwr_save(struct btc_coexist *btcoexist,
+						 bool new_ps_state)
 {
 	u8 lps_mode = 0x0;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U1_LPS_MODE, &lps_mode);
 
-	if (lps_mode) {	/* already under LPS state */
+	if (lps_mode) {
+		/* already under LPS state */
 		if (new_ps_state) {
 			/* keep state under LPS, do nothing. */
 		} else {
@@ -1655,7 +1053,8 @@ static void btc8723b1ant_pstdmachkpwrsave(struct btc_coexist *btcoexist,
 			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
 						false, 0);
 		}
-	} else {	/* NO PS state */
+	} else {
+		/* NO PS state */
 		if (new_ps_state) {
 			/* will enter LPS state, turn off psTdma first */
 			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
@@ -1681,18 +1080,18 @@ static void halbtc8723b1ant_power_save_state(struct btc_coexist *btcoexist,
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_NORMAL_LPS, NULL);
 		break;
 	case BTC_PS_LPS_ON:
-		btc8723b1ant_pstdmachkpwrsave(btcoexist, true);
-		halbtc8723b1ant_LpsRpwm(btcoexist, NORMAL_EXEC, lps_val,
-					rpwm_val);
-		/* when coex force to enter LPS, do not enter 32k low power. */
+		halbtc8723b1ant_ps_tdma_chk_pwr_save(btcoexist, true);
+		halbtc8723b1ant_lps_rpwm(btcoexist, NORMAL_EXEC, lps_val,
+					 rpwm_val);
+		/* when coex force to enter LPS, do not enter 32k low power */
 		low_pwr_disable = true;
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 				   &low_pwr_disable);
-		/* power save must executed before psTdma.	 */
+		/* power save must executed before psTdma */
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_ENTER_LPS, NULL);
 		break;
 	case BTC_PS_LPS_OFF:
-		btc8723b1ant_pstdmachkpwrsave(btcoexist, false);
+		halbtc8723b1ant_ps_tdma_chk_pwr_save(btcoexist, false);
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_LEAVE_LPS, NULL);
 		break;
 	default:
@@ -1700,66 +1099,6 @@ static void halbtc8723b1ant_power_save_state(struct btc_coexist *btcoexist,
 	}
 }
 
-/***************************************************
- *
- *	Software Coex Mechanism start
- *
- ***************************************************/
-/* SCO only or SCO+PAN(HS) */
-static void halbtc8723b1ant_action_sco(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, true);
-}
-
-static void halbtc8723b1ant_action_hid(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, true);
-}
-
-/*A2DP only / PAN(EDR) only/ A2DP+PAN(HS) */
-static void halbtc8723b1ant_action_a2dp(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, false);
-}
-
-static void halbtc8723b1ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, false);
-}
-
-static void halbtc8723b1ant_action_pan_edr(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, false);
-}
-
-/* PAN(HS) only */
-static void halbtc8723b1ant_action_pan_hs(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, false);
-}
-
-/*PAN(EDR)+A2DP */
-static void halbtc8723b1ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, false);
-}
-
-static void halbtc8723b1ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, true);
-}
-
-/* HID+A2DP+PAN(EDR) */
-static void btc8723b1ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, true);
-}
-
-static void halbtc8723b1ant_action_hid_a2dp(struct btc_coexist *btcoexist)
-{
-	halbtc8723b1ant_sw_mechanism(btcoexist, true);
-}
-
 /*****************************************************
  *
  *	Non-Software Coex Mechanism start
@@ -1826,11 +1165,11 @@ static void btc8723b1ant_act_bt_sco_hid_only_busy(struct btc_coexist *btcoexist,
 			   &wifi_connected);
 
 	/* tdma and coex table */
-
 	if (bt_link_info->sco_exist) {
 		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
 		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
-	} else { /* HID */
+	} else {
+		/* HID */
 		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 6);
 		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 5);
 	}
@@ -1840,30 +1179,21 @@ static void halbtc8723b1ant_action_wifi_connected_bt_acl_busy(
 					struct btc_coexist *btcoexist,
 					u8 wifi_status)
 {
-	u8 bt_rssi_state;
-
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
-	bt_rssi_state = halbtc8723b1ant_bt_rssi_state(btcoexist, 2, 28, 0);
 
-	if (bt_link_info->hid_only) {  /*HID */
+	if (bt_link_info->hid_only) { /* HID */
 		btc8723b1ant_act_bt_sco_hid_only_busy(btcoexist, wifi_status);
 		coex_dm->auto_tdma_adjust = false;
 		return;
-	} else if (bt_link_info->a2dp_only) { /*A2DP */
-		if (BT_8723B_1ANT_WIFI_STATUS_CONNECTED_IDLE == wifi_status) {
+	} else if (bt_link_info->a2dp_only) { /* A2DP */
+		if (wifi_status == BT_8723B_1ANT_WIFI_STATUS_CONNECTED_IDLE) {
 			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
 						false, 8);
 			halbtc8723b1ant_coex_table_with_type(btcoexist,
 							     NORMAL_EXEC, 2);
 			coex_dm->auto_tdma_adjust = false;
-		} else if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-			   (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b1ant_tdma_dur_adj_for_acl(btcoexist,
-							  wifi_status);
-			halbtc8723b1ant_coex_table_with_type(btcoexist,
-							     NORMAL_EXEC, 1);
-		} else { /*for low BT RSSI */
+		} else { /* for low BT RSSI */
 			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
 						true, 11);
 			halbtc8723b1ant_coex_table_with_type(btcoexist,
@@ -1871,18 +1201,18 @@ static void halbtc8723b1ant_action_wifi_connected_bt_acl_busy(
 			coex_dm->auto_tdma_adjust = false;
 		}
 	} else if (bt_link_info->hid_exist &&
-			bt_link_info->a2dp_exist) { /*HID+A2DP */
-		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+		bt_link_info->a2dp_exist) { /* HID + A2DP */
+		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,	true, 14);
 		coex_dm->auto_tdma_adjust = false;
 
 		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 6);
-	 /*PAN(OPP,FTP), HID+PAN(OPP,FTP) */
+	 /* PAN(OPP,FTP), HID + PAN(OPP,FTP) */
 	} else if (bt_link_info->pan_only ||
 		   (bt_link_info->hid_exist && bt_link_info->pan_exist)) {
 		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
 		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 6);
 		coex_dm->auto_tdma_adjust = false;
-	 /*A2DP+PAN(OPP,FTP), HID+A2DP+PAN(OPP,FTP)*/
+	 /* A2DP + PAN(OPP,FTP), HID + A2DP + PAN(OPP,FTP) */
 	} else if ((bt_link_info->a2dp_exist && bt_link_info->pan_exist) ||
 		   (bt_link_info->hid_exist && bt_link_info->a2dp_exist &&
 		    bt_link_info->pan_exist)) {
@@ -1907,57 +1237,59 @@ static void btc8723b1ant_action_wifi_not_conn(struct btc_coexist *btcoexist)
 	halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 }
 
-static void btc8723b1ant_action_wifi_not_conn_scan(struct btc_coexist *btcoex)
+static void
+btc8723b1ant_action_wifi_not_conn_scan(struct btc_coexist *btcoexist)
 {
-	struct btc_bt_link_info *bt_link_info = &btcoex->bt_link_info;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
-	halbtc8723b1ant_power_save_state(btcoex, BTC_PS_WIFI_NATIVE,
+	halbtc8723b1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
 					 0x0, 0x0);
 
 	/* tdma and coex table */
 	if (BT_8723B_1ANT_BT_STATUS_ACL_BUSY == coex_dm->bt_status) {
 		if (bt_link_info->a2dp_exist && bt_link_info->pan_exist) {
-			halbtc8723b1ant_ps_tdma(btcoex, NORMAL_EXEC,
+			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
 						true, 22);
-			halbtc8723b1ant_coex_table_with_type(btcoex,
+			halbtc8723b1ant_coex_table_with_type(btcoexist,
 							     NORMAL_EXEC, 1);
 		} else if (bt_link_info->pan_only) {
-			halbtc8723b1ant_ps_tdma(btcoex, NORMAL_EXEC,
+			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
 						true, 20);
-			halbtc8723b1ant_coex_table_with_type(btcoex,
+			halbtc8723b1ant_coex_table_with_type(btcoexist,
 							     NORMAL_EXEC, 2);
 		} else {
-			halbtc8723b1ant_ps_tdma(btcoex, NORMAL_EXEC,
+			halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC,
 						true, 20);
-			halbtc8723b1ant_coex_table_with_type(btcoex,
+			halbtc8723b1ant_coex_table_with_type(btcoexist,
 							     NORMAL_EXEC, 1);
 		}
 	} else if ((BT_8723B_1ANT_BT_STATUS_SCO_BUSY == coex_dm->bt_status) ||
 		   (BT_8723B_1ANT_BT_STATUS_ACL_SCO_BUSY ==
 		    coex_dm->bt_status)){
-		btc8723b1ant_act_bt_sco_hid_only_busy(btcoex,
+		btc8723b1ant_act_bt_sco_hid_only_busy(btcoexist,
 				BT_8723B_1ANT_WIFI_STATUS_CONNECTED_SCAN);
 	} else {
-		halbtc8723b1ant_ps_tdma(btcoex, NORMAL_EXEC, false, 8);
-		halbtc8723b1ant_coex_table_with_type(btcoex, NORMAL_EXEC, 2);
+		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 	}
 }
 
-static void btc8723b1ant_act_wifi_not_conn_asso_auth(struct btc_coexist *btcoex)
+static void
+btc8723b1ant_act_wifi_not_conn_asso_auth(struct btc_coexist *btcoexist)
 {
-	struct btc_bt_link_info *bt_link_info = &btcoex->bt_link_info;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
-	halbtc8723b1ant_power_save_state(btcoex, BTC_PS_WIFI_NATIVE,
+	halbtc8723b1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
 					 0x0, 0x0);
 
 	if ((BT_8723B_1ANT_BT_STATUS_CONNECTED_IDLE == coex_dm->bt_status) ||
 	    (bt_link_info->sco_exist) || (bt_link_info->hid_only) ||
 	    (bt_link_info->a2dp_only) || (bt_link_info->pan_only)) {
-		halbtc8723b1ant_ps_tdma(btcoex, NORMAL_EXEC, false, 8);
-		halbtc8723b1ant_coex_table_with_type(btcoex, NORMAL_EXEC, 7);
+		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
 	} else {
-		halbtc8723b1ant_ps_tdma(btcoex, NORMAL_EXEC, true, 20);
-		halbtc8723b1ant_coex_table_with_type(btcoex, NORMAL_EXEC, 1);
+		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 	}
 }
 
@@ -2109,75 +1441,6 @@ static void halbtc8723b1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 	}
 }
 
-static void btc8723b1ant_run_sw_coex_mech(struct btc_coexist *btcoexist)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 algorithm = 0;
-
-	algorithm = halbtc8723b1ant_action_algorithm(btcoexist);
-	coex_dm->cur_algorithm = algorithm;
-
-	if (!halbtc8723b1ant_is_common_action(btcoexist)) {
-		switch (coex_dm->cur_algorithm) {
-		case BT_8723B_1ANT_COEX_ALGO_SCO:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = SCO\n");
-			halbtc8723b1ant_action_sco(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_HID:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = HID\n");
-			halbtc8723b1ant_action_hid(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_A2DP:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = A2DP\n");
-			halbtc8723b1ant_action_a2dp(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_A2DP_PANHS:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = A2DP+PAN(HS)\n");
-			halbtc8723b1ant_action_a2dp_pan_hs(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_PANEDR:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = PAN(EDR)\n");
-			halbtc8723b1ant_action_pan_edr(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_PANHS:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = HS mode\n");
-			halbtc8723b1ant_action_pan_hs(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_PANEDR_A2DP:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = PAN+A2DP\n");
-			halbtc8723b1ant_action_pan_edr_a2dp(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_PANEDR_HID:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = PAN(EDR)+HID\n");
-			halbtc8723b1ant_action_pan_edr_hid(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_HID_A2DP_PANEDR:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = HID+A2DP+PAN\n");
-			btc8723b1ant_action_hid_a2dp_pan_edr(btcoexist);
-			break;
-		case BT_8723B_1ANT_COEX_ALGO_HID_A2DP:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = HID+A2DP\n");
-			halbtc8723b1ant_action_hid_a2dp(btcoexist);
-			break;
-		default:
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Action algorithm = coexist All Off!!\n");
-			break;
-		}
-		coex_dm->pre_algorithm = coex_dm->cur_algorithm;
-	}
-}
-
 static void halbtc8723b1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
@@ -2186,7 +1449,6 @@ static void halbtc8723b1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 	bool increase_scan_dev_num = false;
 	bool bt_ctrl_agg_buf_size = false;
 	u8 agg_buf_size = 5;
-	u8 wifi_rssi_state = BTC_RSSI_STATE_HIGH;
 	u32 wifi_link_status = 0;
 	u32 num_of_wifi_link = 0;
 
@@ -2238,16 +1500,12 @@ static void halbtc8723b1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 	if (!bt_link_info->sco_exist && !bt_link_info->hid_exist) {
 		halbtc8723b1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
 	} else {
-		if (wifi_connected) {
-			wifi_rssi_state =
-				halbtc8723b1ant_wifi_rssi_state(btcoexist,
-								1, 2, 30, 0);
+		if (wifi_connected)
 			halbtc8723b1ant_limited_tx(btcoexist,
 						   NORMAL_EXEC, 1, 1, 1, 1);
-		} else {
+		else
 			halbtc8723b1ant_limited_tx(btcoexist, NORMAL_EXEC,
 						   0, 0, 0, 0);
-		}
 	}
 
 	if (bt_link_info->sco_exist) {
@@ -2263,8 +1521,6 @@ static void halbtc8723b1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 	halbtc8723b1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
 				   bt_ctrl_agg_buf_size, agg_buf_size);
 
-	btc8723b1ant_run_sw_coex_mech(btcoexist);
-
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
 	if (coex_sta->c2h_bt_inquiry_page) {
@@ -2364,28 +1620,19 @@ static void halbtc8723b1ant_init_hw_config(struct btc_coexist *btcoexist,
 	btcoexist->btc_write_1byte(btcoexist, 0x790, u8tmp);
 
 	/* Enable counter statistics */
-	/*0x76e[3] =1, WLAN_Act control by PTA */
+	/*0x76e[3] = 1, WLAN_Act control by PTA */
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
 	btcoexist->btc_write_1byte(btcoexist, 0x778, 0x1);
 	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x40, 0x20, 0x1);
 
-	/*Antenna config */
-	halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_PTA, true, false);
+	/* Antenna config */
+	halbtc8723b1ant_set_ant_path(btcoexist, BTC_ANT_PATH_PTA, true, false);
 	/* PTA parameter */
 	halbtc8723b1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
 }
 
-static void halbtc8723b1ant_wifi_off_hw_cfg(struct btc_coexist *btcoexist)
-{
-	/* set wlan_act to low */
-	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0x4);
-}
-
 /**************************************************************
- * work around function start with wa_halbtc8723b1ant_
- **************************************************************/
-/**************************************************************
- * extern function start with EXhalbtc8723b1ant_
+ * extern function start with ex_halbtc8723b1ant_
  **************************************************************/
 
 void ex_halbtc8723b1ant_init_hwconfig(struct btc_coexist *btcoexist)
@@ -2539,7 +1786,7 @@ void ex_halbtc8723b1ant_display_coex_info(struct btc_coexist *btcoexist)
 		if (coex_sta->bt_info_c2h_cnt[i]) {
 			RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG,
 				 "\r\n %-35s = %7ph(%d)",
-				 GLBtInfoSrc8723b1Ant[i],
+				 glbt_info_src_8723b_1ant[i],
 				 coex_sta->bt_info_c2h[i],
 				 coex_sta->bt_info_c2h_cnt[i]);
 		}
@@ -2697,13 +1944,12 @@ void ex_halbtc8723b1ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 			 "[BTCoex], IPS ENTER notify\n");
 		coex_sta->under_ips = true;
 
-		halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_BT,
-					   false, true);
+		halbtc8723b1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
+					     false, true);
 		/* set PTA control */
 		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
 		halbtc8723b1ant_coex_table_with_type(btcoexist,
 						     NORMAL_EXEC, 0);
-		halbtc8723b1ant_wifi_off_hw_cfg(btcoexist);
 	} else if (BTC_IPS_LEAVE == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS LEAVE notify\n");
@@ -2774,14 +2020,17 @@ void ex_halbtc8723b1ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 	if (BTC_SCAN_START == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], SCAN START notify\n");
-		if (!wifi_connected)	/* non-connected scan */
+		if (!wifi_connected)
+			/* non-connected scan */
 			btc8723b1ant_action_wifi_not_conn_scan(btcoexist);
-		else	/* wifi is connected */
+		else
+			/* wifi is connected */
 			btc8723b1ant_action_wifi_conn_scan(btcoexist);
 	} else if (BTC_SCAN_FINISH == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], SCAN FINISH notify\n");
-		if (!wifi_connected)	/* non-connected scan */
+		if (!wifi_connected)
+			/* non-connected scan */
 			btc8723b1ant_action_wifi_not_conn(btcoexist);
 		else
 			halbtc8723b1ant_action_wifi_connected(btcoexist);
@@ -2831,7 +2080,8 @@ void ex_halbtc8723b1ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 				   &wifi_connected);
-		if (!wifi_connected) /* non-connected scan */
+		if (!wifi_connected)
+			/* non-connected scan */
 			btc8723b1ant_action_wifi_not_conn(btcoexist);
 		else
 			halbtc8723b1ant_action_wifi_connected(btcoexist);
@@ -3020,7 +2270,8 @@ void ex_halbtc8723b1ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_sta->a2dp_exist = false;
 		coex_sta->hid_exist = false;
 		coex_sta->sco_exist = false;
-	} else { /* connection exists */
+	} else {
+		/* connection exists */
 		coex_sta->bt_link_exist = true;
 		if (bt_info & BT_INFO_8723B_1ANT_B_FTP)
 			coex_sta->pan_exist = true;
@@ -3089,9 +2340,8 @@ void ex_halbtc8723b1ant_halt_notify(struct btc_coexist *btcoexist)
 
 	btcoexist->stop_coex_dm = true;
 
-	halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_BT, false, true);
+	halbtc8723b1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT, false, true);
 
-	halbtc8723b1ant_wifi_off_hw_cfg(btcoexist);
 	halbtc8723b1ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
 
 	halbtc8723b1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
@@ -3111,13 +2361,12 @@ void ex_halbtc8723b1ant_pnp_notify(struct btc_coexist *btcoexist, u8 pnp_state)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Pnp notify to SLEEP\n");
 		btcoexist->stop_coex_dm = true;
-		halbtc8723b1ant_SetAntPath(btcoexist, BTC_ANT_PATH_BT, false,
-					   true);
+		halbtc8723b1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT, false,
+					     true);
 		halbtc8723b1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
 						 0x0, 0x0);
 		halbtc8723b1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
 		halbtc8723b1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
-		halbtc8723b1ant_wifi_off_hw_cfg(btcoexist);
 	} else if (BTC_WIFI_PNP_WAKE_UP == pnp_state) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Pnp notify to WAKE UP\n");
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
index 12125966a911..2f3946be4ce2 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
@@ -240,9 +240,33 @@ static u8 btc8723b2ant_wifi_rssi_state(struct btc_coexist *btcoexist,
 	return wifi_rssi_state;
 }
 
+static
+void btc8723b2ant_limited_rx(struct btc_coexist *btcoexist, bool force_exec,
+			     bool rej_ap_agg_pkt, bool bt_ctrl_agg_buf_size,
+			     u8 agg_buf_size)
+{
+	bool reject_rx_agg = rej_ap_agg_pkt;
+	bool bt_ctrl_rx_agg_size = bt_ctrl_agg_buf_size;
+	u8 rx_agg_size = agg_buf_size;
+
+	/* ============================================ */
+	/*	Rx Aggregation related setting		*/
+	/* ============================================ */
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_TO_REJ_AP_AGG_PKT,
+			   &reject_rx_agg);
+	/* decide BT control aggregation buf size or not */
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_CTRL_AGG_SIZE,
+			   &bt_ctrl_rx_agg_size);
+	/* aggregate buf size, only work when BT control Rx aggregate size */
+	btcoexist->btc_set(btcoexist, BTC_SET_U1_AGG_BUF_SIZE, &rx_agg_size);
+	/* real update aggregation setting */
+	btcoexist->btc_set(btcoexist, BTC_SET_ACT_AGGREGATE_CTRL, NULL);
+}
+
 static void btc8723b2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 	u32 reg_hp_txrx, reg_lp_txrx, u32tmp;
 	u32 reg_hp_tx = 0, reg_hp_rx = 0;
 	u32 reg_lp_tx = 0, reg_lp_rx = 0;
@@ -263,6 +287,17 @@ static void btc8723b2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 	coex_sta->low_priority_tx = reg_lp_tx;
 	coex_sta->low_priority_rx = reg_lp_rx;
 
+	if ((coex_sta->low_priority_tx > 1050) &&
+	    (!coex_sta->c2h_bt_inquiry_page))
+		coex_sta->pop_event_cnt++;
+
+	if ((coex_sta->low_priority_rx >= 950) &&
+	    (coex_sta->low_priority_rx >= coex_sta->low_priority_tx) &&
+	    (!coex_sta->under_ips))
+		bt_link_info->slave_role = true;
+	else
+		bt_link_info->slave_role = false;
+
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], High Priority Tx/Rx(reg 0x%x)=0x%x(%d)/0x%x(%d)\n",
 		 reg_hp_txrx, reg_hp_tx, reg_hp_tx, reg_hp_rx, reg_hp_rx);
@@ -274,6 +309,43 @@ static void btc8723b2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
 }
 
+static void btc8723b2ant_monitor_wifi_ctr(struct btc_coexist *btcoexist)
+{
+	if (coex_sta->under_ips) {
+		coex_sta->crc_ok_cck = 0;
+		coex_sta->crc_ok_11g = 0;
+		coex_sta->crc_ok_11n = 0;
+		coex_sta->crc_ok_11n_agg = 0;
+
+		coex_sta->crc_err_cck = 0;
+		coex_sta->crc_err_11g = 0;
+		coex_sta->crc_err_11n = 0;
+		coex_sta->crc_err_11n_agg = 0;
+	} else {
+		coex_sta->crc_ok_cck =
+			btcoexist->btc_read_4byte(btcoexist, 0xf88);
+		coex_sta->crc_ok_11g =
+			btcoexist->btc_read_2byte(btcoexist, 0xf94);
+		coex_sta->crc_ok_11n =
+			btcoexist->btc_read_2byte(btcoexist, 0xf90);
+		coex_sta->crc_ok_11n_agg =
+			btcoexist->btc_read_2byte(btcoexist, 0xfb8);
+
+		coex_sta->crc_err_cck =
+			btcoexist->btc_read_4byte(btcoexist, 0xf84);
+		coex_sta->crc_err_11g =
+			btcoexist->btc_read_2byte(btcoexist, 0xf96);
+		coex_sta->crc_err_11n =
+			btcoexist->btc_read_2byte(btcoexist, 0xf92);
+		coex_sta->crc_err_11n_agg =
+			btcoexist->btc_read_2byte(btcoexist, 0xfba);
+	}
+
+	/* reset counter */
+	btcoexist->btc_write_1byte_bitmask(btcoexist, 0xf16, 0x1, 0x1);
+	btcoexist->btc_write_1byte_bitmask(btcoexist, 0xf16, 0x1, 0x0);
+}
+
 static void btc8723b2ant_query_bt_info(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
@@ -297,6 +369,8 @@ static bool btc8723b2ant_is_wifi_status_changed(struct btc_coexist *btcoexist)
 	static bool pre_bt_hs_on;
 	bool wifi_busy = false, under_4way = false, bt_hs_on = false;
 	bool wifi_connected = false;
+	u8 wifi_rssi_state = BTC_RSSI_STATE_HIGH;
+	u8 tmp;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 			   &wifi_connected);
@@ -320,6 +394,15 @@ static bool btc8723b2ant_is_wifi_status_changed(struct btc_coexist *btcoexist)
 			pre_bt_hs_on = bt_hs_on;
 			return true;
 		}
+
+		tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+				 coex_dm->switch_thres_offset;
+		wifi_rssi_state =
+		     btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, tmp, 0);
+
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_LOW))
+			return true;
 	}
 
 	return false;
@@ -327,11 +410,9 @@ static bool btc8723b2ant_is_wifi_status_changed(struct btc_coexist *btcoexist)
 
 static void btc8723b2ant_update_bt_link_info(struct btc_coexist *btcoexist)
 {
-	/*struct btc_stack_info *stack_info = &btcoexist->stack_info;*/
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 	bool bt_hs_on = false;
 
-#if (BT_AUTO_REPORT_ONLY_8723B_2ANT == 1) /* profile from bt patch */
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
 	bt_link_info->bt_link_exist = coex_sta->bt_link_exist;
@@ -345,21 +426,7 @@ static void btc8723b2ant_update_bt_link_info(struct btc_coexist *btcoexist)
 		bt_link_info->pan_exist = true;
 		bt_link_info->bt_link_exist = true;
 	}
-#else	/* profile from bt stack */
-	bt_link_info->bt_link_exist = stack_info->bt_link_exist;
-	bt_link_info->sco_exist = stack_info->sco_exist;
-	bt_link_info->a2dp_exist = stack_info->a2dp_exist;
-	bt_link_info->pan_exist = stack_info->pan_exist;
-	bt_link_info->hid_exist = stack_info->hid_exist;
-
-	/*for win-8 stack HID report error*/
-	if (!stack_info->hid_exist)
-		stack_info->hid_exist = coex_sta->hid_exist;
-	/*sync  BTInfo with BT firmware and stack*/
-	/* when stack HID report error, here we use the info from bt fw.*/
-	if (!stack_info->bt_link_exist)
-		stack_info->bt_link_exist = coex_sta->bt_link_exist;
-#endif
+
 	/* check if Sco only */
 	if (bt_link_info->sco_exist && !bt_link_info->a2dp_exist &&
 	    !bt_link_info->pan_exist && !bt_link_info->hid_exist)
@@ -584,44 +651,6 @@ static u8 btc8723b2ant_action_algorithm(struct btc_coexist *btcoexist)
 	return algorithm;
 }
 
-static bool btc8723b_need_dec_pwr(struct btc_coexist *btcoexist)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool ret = false;
-	bool bt_hs_on = false, wifi_connected = false;
-	s32 bt_hs_rssi = 0;
-	u8 bt_rssi_state;
-
-	if (!btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on))
-		return false;
-	if (!btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
-				&wifi_connected))
-		return false;
-	if (!btcoexist->btc_get(btcoexist, BTC_GET_S4_HS_RSSI, &bt_hs_rssi))
-		return false;
-
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
-
-	if (wifi_connected) {
-		if (bt_hs_on) {
-			if (bt_hs_rssi > 37) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Need to decrease bt power for HS mode!!\n");
-				ret = true;
-			}
-		} else {
-			if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-			    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Need to decrease bt power for Wifi is connected!!\n");
-				ret = true;
-			}
-		}
-	}
-
-	return ret;
-}
-
 static void btc8723b2ant_set_fw_dac_swing_level(struct btc_coexist *btcoexist,
 						u8 dac_swing_lvl)
 {
@@ -642,44 +671,40 @@ static void btc8723b2ant_set_fw_dac_swing_level(struct btc_coexist *btcoexist,
 }
 
 static void btc8723b2ant_set_fw_dec_bt_pwr(struct btc_coexist *btcoexist,
-					   bool dec_bt_pwr)
+					   u8 dec_bt_pwr_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
-	h2c_parameter[0] = 0;
-
-	if (dec_bt_pwr)
-		h2c_parameter[0] |= BIT1;
+	h2c_parameter[0] = dec_bt_pwr_lvl;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], decrease Bt Power : %s, FW write 0x62=0x%x\n",
-		    (dec_bt_pwr ? "Yes!!" : "No!!"), h2c_parameter[0]);
+		 "[BTCoex], decrease Bt Power Level : %u\n", dec_bt_pwr_lvl);
 
 	btcoexist->btc_fill_h2c(btcoexist, 0x62, 1, h2c_parameter);
 }
 
 static void btc8723b2ant_dec_bt_pwr(struct btc_coexist *btcoexist,
-				    bool force_exec, bool dec_bt_pwr)
+				    bool force_exec, u8 dec_bt_pwr_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s Dec BT power = %s\n",
-		    force_exec ? "force to" : "", dec_bt_pwr ? "ON" : "OFF");
-	coex_dm->cur_dec_bt_pwr = dec_bt_pwr;
+		 "[BTCoex], Dec BT power level = %u\n", dec_bt_pwr_lvl);
+	coex_dm->cur_dec_bt_pwr_lvl = dec_bt_pwr_lvl;
 
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], bPreDecBtPwr=%d, bCurDecBtPwr=%d\n",
-			    coex_dm->pre_dec_bt_pwr, coex_dm->cur_dec_bt_pwr);
+			 "[BTCoex], PreDecBtPwrLvl=%d, CurDecBtPwrLvl=%d\n",
+			    coex_dm->pre_dec_bt_pwr_lvl,
+			    coex_dm->cur_dec_bt_pwr_lvl);
 
-		if (coex_dm->pre_dec_bt_pwr == coex_dm->cur_dec_bt_pwr)
+		if (coex_dm->pre_dec_bt_pwr_lvl == coex_dm->cur_dec_bt_pwr_lvl)
 			return;
 	}
-	btc8723b2ant_set_fw_dec_bt_pwr(btcoexist, coex_dm->cur_dec_bt_pwr);
+	btc8723b2ant_set_fw_dec_bt_pwr(btcoexist, coex_dm->cur_dec_bt_pwr_lvl);
 
-	coex_dm->pre_dec_bt_pwr = coex_dm->cur_dec_bt_pwr;
+	coex_dm->pre_dec_bt_pwr_lvl = coex_dm->cur_dec_bt_pwr_lvl;
 }
 
 static void btc8723b2ant_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
@@ -708,72 +733,21 @@ static void btc8723b2ant_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
 	coex_dm->pre_fw_dac_swing_lvl = coex_dm->cur_fw_dac_swing_lvl;
 }
 
-static void btc8723b2ant_set_sw_rf_rx_lpf_corner(struct btc_coexist *btcoexist,
-						 bool rx_rf_shrink_on)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	if (rx_rf_shrink_on) {
-		/* Shrink RF Rx LPF corner */
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Shrink RF Rx LPF corner!!\n");
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1e,
-					  0xfffff, 0xffffc);
-	} else {
-		/* Resume RF Rx LPF corner */
-		/* After initialized, we can use coex_dm->btRf0x1eBackup */
-		if (btcoexist->initilized) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Resume RF Rx LPF corner!!\n");
-			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1e,
-						  0xfffff,
-						  coex_dm->bt_rf0x1e_backup);
-		}
-	}
-}
-
-static void btc8723b2ant_rf_shrink(struct btc_coexist *btcoexist,
-				   bool force_exec, bool rx_rf_shrink_on)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s turn Rx RF Shrink = %s\n",
-		    (force_exec ? "force to" : ""), (rx_rf_shrink_on ?
-						     "ON" : "OFF"));
-	coex_dm->cur_rf_rx_lpf_shrink = rx_rf_shrink_on;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], bPreRfRxLpfShrink=%d, bCurRfRxLpfShrink=%d\n",
-			    coex_dm->pre_rf_rx_lpf_shrink,
-			    coex_dm->cur_rf_rx_lpf_shrink);
-
-		if (coex_dm->pre_rf_rx_lpf_shrink ==
-		    coex_dm->cur_rf_rx_lpf_shrink)
-			return;
-	}
-	btc8723b2ant_set_sw_rf_rx_lpf_corner(btcoexist,
-					     coex_dm->cur_rf_rx_lpf_shrink);
-
-	coex_dm->pre_rf_rx_lpf_shrink = coex_dm->cur_rf_rx_lpf_shrink;
-}
-
 static void btc8723b_set_penalty_txrate(struct btc_coexist *btcoexist,
 					bool low_penalty_ra)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[6] = {0};
 
-	h2c_parameter[0] = 0x6;	/* opCode, 0x6= Retry_Penalty*/
+	h2c_parameter[0] = 0x6;	/* op_code, 0x6 = Retry_Penalty */
 
 	if (low_penalty_ra) {
 		h2c_parameter[1] |= BIT0;
-		/*normal rate except MCS7/6/5, OFDM54/48/36*/
+		/* normal rate except MCS7/6/5, OFDM54/48/36 */
 		h2c_parameter[2] = 0x00;
-		h2c_parameter[3] = 0xf7;  /*MCS7 or OFDM54*/
-		h2c_parameter[4] = 0xf8;  /*MCS6 or OFDM48*/
-		h2c_parameter[5] = 0xf9;  /*MCS5 or OFDM36*/
+		h2c_parameter[3] = 0xf4; /* MCS7 or OFDM54 */
+		h2c_parameter[4] = 0xf5; /* MCS6 or OFDM48 */
+		h2c_parameter[5] = 0xf6; /* MCS5 or OFDM36 */
 	}
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -788,7 +762,6 @@ static void btc8723b2ant_low_penalty_ra(struct btc_coexist *btcoexist,
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
-	/*return; */
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s turn LowPenaltyRA = %s\n",
 		 (force_exec ? "force to" : ""), (low_penalty_ra ?
@@ -830,9 +803,9 @@ static void btc8723b2ant_set_sw_fulltime_dac_swing(struct btc_coexist *btcoex,
 		btc8723b2ant_set_dac_swing_reg(btcoex, 0x18);
 }
 
-static void btc8723b2ant_dac_swing(struct btc_coexist *btcoexist,
-				   bool force_exec, bool dac_swing_on,
-				   u32 dac_swing_lvl)
+void btc8723b2ant_dac_swing(struct btc_coexist *btcoexist,
+			    bool force_exec, bool dac_swing_on,
+			    u32 dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -863,105 +836,6 @@ static void btc8723b2ant_dac_swing(struct btc_coexist *btcoexist,
 	coex_dm->pre_dac_swing_lvl = coex_dm->cur_dac_swing_lvl;
 }
 
-static void btc8723b2ant_set_agc_table(struct btc_coexist *btcoexist,
-				       bool agc_table_en)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 rssi_adjust_val = 0;
-
-	/*  BB AGC Gain Table */
-	if (agc_table_en) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BB Agc Table On!\n");
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x6e1A0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x6d1B0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x6c1C0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x6b1D0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x6a1E0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x691F0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0x68200001);
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BB Agc Table Off!\n");
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xaa1A0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xa91B0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xa81C0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xa71D0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xa61E0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xa51F0001);
-		btcoexist->btc_write_4byte(btcoexist, 0xc78, 0xa4200001);
-	}
-
-	/* RF Gain */
-	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0xef, 0xfffff, 0x02000);
-	if (agc_table_en) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Agc Table On!\n");
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x3b,
-					  0xfffff, 0x38fff);
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x3b,
-					  0xfffff, 0x38ffe);
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Agc Table Off!\n");
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x3b,
-					  0xfffff, 0x380c3);
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x3b,
-					  0xfffff, 0x28ce6);
-	}
-	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0xef, 0xfffff, 0x0);
-
-	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0xed, 0xfffff, 0x1);
-
-	if (agc_table_en) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Agc Table On!\n");
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x40,
-					  0xfffff, 0x38fff);
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x40,
-					  0xfffff, 0x38ffe);
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Agc Table Off!\n");
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x40,
-					  0xfffff, 0x380c3);
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x40,
-					  0xfffff, 0x28ce6);
-	}
-	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0xed, 0xfffff, 0x0);
-
-	/* set rssiAdjustVal for wifi module. */
-	if (agc_table_en)
-		rssi_adjust_val = 8;
-	btcoexist->btc_set(btcoexist, BTC_SET_U1_RSSI_ADJ_VAL_FOR_AGC_TABLE_ON,
-			   &rssi_adjust_val);
-}
-
-static void btc8723b2ant_agc_table(struct btc_coexist *btcoexist,
-				   bool force_exec, bool agc_table_en)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s %s Agc Table\n",
-		 (force_exec ? "force to" : ""),
-		 (agc_table_en ? "Enable" : "Disable"));
-	coex_dm->cur_agc_table_en = agc_table_en;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], bPreAgcTableEn=%d, bCurAgcTableEn=%d\n",
-			 coex_dm->pre_agc_table_en,
-			 coex_dm->cur_agc_table_en);
-
-		if (coex_dm->pre_agc_table_en == coex_dm->cur_agc_table_en)
-			return;
-	}
-	btc8723b2ant_set_agc_table(btcoexist, agc_table_en);
-
-	coex_dm->pre_agc_table_en = coex_dm->cur_agc_table_en;
-}
-
 static void btc8723b2ant_set_coex_table(struct btc_coexist *btcoexist,
 					u32 val0x6c0, u32 val0x6c4,
 					u32 val0x6c8, u8 val0x6cc)
@@ -1026,61 +900,73 @@ static void btc8723b2ant_coex_table(struct btc_coexist *btcoexist,
 	coex_dm->pre_val0x6cc = coex_dm->cur_val0x6cc;
 }
 
-static void btc8723b_coex_tbl_type(struct btc_coexist *btcoexist,
-				   bool force_exec, u8 type)
+static void btc8723b2ant_coex_table_with_type(struct btc_coexist *btcoexist,
+					      bool force_exec, u8 type)
 {
 	switch (type) {
 	case 0:
 		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55555555,
-					0x55555555, 0xffff, 0x3);
+					0x55555555, 0xffffff, 0x3);
 		break;
 	case 1:
 		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55555555,
-					0x5afa5afa, 0xffff, 0x3);
+					0x5afa5afa, 0xffffff, 0x3);
 		break;
 	case 2:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
-					0x5a5a5a5a, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x5ada5ada,
+					0x5ada5ada, 0xffffff, 0x3);
 		break;
 	case 3:
 		btc8723b2ant_coex_table(btcoexist, force_exec, 0xaaaaaaaa,
-					0xaaaaaaaa, 0xffff, 0x3);
+					0xaaaaaaaa, 0xffffff, 0x3);
 		break;
 	case 4:
 		btc8723b2ant_coex_table(btcoexist, force_exec, 0xffffffff,
-					0xffffffff, 0xffff, 0x3);
+					0xffffffff, 0xffffff, 0x3);
 		break;
 	case 5:
 		btc8723b2ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
-					0x5fff5fff, 0xffff, 0x3);
+					0x5fff5fff, 0xffffff, 0x3);
 		break;
 	case 6:
 		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					0x5a5a5a5a, 0xffff, 0x3);
+					0x5a5a5a5a, 0xffffff, 0x3);
 		break;
 	case 7:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					0x5afa5afa, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
 		break;
 	case 8:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x5aea5aea,
-					0x5aea5aea, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
 		break;
 	case 9:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					0x5aea5aea, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
 		break;
 	case 10:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					0x5aff5aff, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
 		break;
 	case 11:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					0x5a5f5a5f, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
 		break;
 	case 12:
-		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					0x5f5f5f5f, 0xffff, 0x3);
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 13:
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
+					0xaaaaaaaa, 0xffffff, 0x3);
+		break;
+	case 14:
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 15:
+		btc8723b2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0xaaaaaaaa, 0xffffff, 0x3);
 		break;
 	default:
 		break;
@@ -1094,7 +980,7 @@ static void btc8723b2ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoexist,
 	u8 h2c_parameter[1] = {0};
 
 	if (enable)
-		h2c_parameter[0] |= BIT0;/* function enable*/
+		h2c_parameter[0] |= BIT0; /* function enable */
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], set FW for BT Ignore Wlan_Act, FW write 0x63=0x%x\n",
@@ -1103,6 +989,33 @@ static void btc8723b2ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x63, 1, h2c_parameter);
 }
 
+static void btc8723b2ant_set_lps_rpwm(struct btc_coexist *btcoexist,
+				      u8 lps_val, u8 rpwm_val)
+{
+	u8 lps = lps_val;
+	u8 rpwm = rpwm_val;
+
+	btcoexist->btc_set(btcoexist, BTC_SET_U1_LPS_VAL, &lps);
+	btcoexist->btc_set(btcoexist, BTC_SET_U1_RPWM_VAL, &rpwm);
+}
+
+static void btc8723b2ant_lps_rpwm(struct btc_coexist *btcoexist,
+				  bool force_exec, u8 lps_val, u8 rpwm_val)
+{
+	coex_dm->cur_lps = lps_val;
+	coex_dm->cur_rpwm = rpwm_val;
+
+	if (!force_exec) {
+		if ((coex_dm->pre_lps == coex_dm->cur_lps) &&
+		    (coex_dm->pre_rpwm == coex_dm->cur_rpwm))
+			return;
+	}
+	btc8723b2ant_set_lps_rpwm(btcoexist, lps_val, rpwm_val);
+
+	coex_dm->pre_lps = coex_dm->cur_lps;
+	coex_dm->pre_rpwm = coex_dm->cur_rpwm;
+}
+
 static void btc8723b2ant_ignore_wlan_act(struct btc_coexist *btcoexist,
 					 bool force_exec, bool enable)
 {
@@ -1133,6 +1046,8 @@ static void btc8723b2ant_set_fw_ps_tdma(struct btc_coexist *btcoexist, u8 byte1,
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[5];
+	if ((coex_sta->a2dp_exist) && (coex_sta->hid_exist))
+		byte5 = byte5 | 0x1;
 
 	h2c_parameter[0] = byte1;
 	h2c_parameter[1] = byte2;
@@ -1155,23 +1070,13 @@ static void btc8723b2ant_set_fw_ps_tdma(struct btc_coexist *btcoexist, u8 byte1,
 	btcoexist->btc_fill_h2c(btcoexist, 0x60, 5, h2c_parameter);
 }
 
-static void btc8723b2ant_sw_mechanism1(struct btc_coexist *btcoexist,
-				       bool shrink_rx_lpf, bool low_penalty_ra,
-				       bool limited_dig, bool bt_lna_constrain)
+static void btc8723b2ant_sw_mechanism(struct btc_coexist *btcoexist,
+				      bool shrink_rx_lpf, bool low_penalty_ra,
+				      bool limited_dig, bool bt_lna_constrain)
 {
-	btc8723b2ant_rf_shrink(btcoexist, NORMAL_EXEC, shrink_rx_lpf);
 	btc8723b2ant_low_penalty_ra(btcoexist, NORMAL_EXEC, low_penalty_ra);
 }
 
-static void btc8723b2ant_sw_mechanism2(struct btc_coexist *btcoexist,
-				       bool agc_table_shift, bool adc_backoff,
-				       bool sw_dac_swing, u32 dac_swing_lvl)
-{
-	btc8723b2ant_agc_table(btcoexist, NORMAL_EXEC, agc_table_shift);
-	btc8723b2ant_dac_swing(btcoexist, NORMAL_EXEC, sw_dac_swing,
-			       dac_swing_lvl);
-}
-
 static void btc8723b2ant_set_ant_path(struct btc_coexist *btcoexist,
 				      u8 antpos_type, bool init_hwcfg,
 				      bool wifi_off)
@@ -1189,44 +1094,66 @@ static void btc8723b2ant_set_ant_path(struct btc_coexist *btcoexist,
 		use_ext_switch = true;
 
 	if (init_hwcfg) {
-		/* 0x4c[23] = 0, 0x4c[24] = 1  Antenna control by WL/BT */
-		u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
-		u32tmp &= ~BIT23;
-		u32tmp |= BIT24;
-		btcoexist->btc_write_4byte(btcoexist, 0x4c, u32tmp);
-
+		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x39, 0x8, 0x1);
 		btcoexist->btc_write_1byte(btcoexist, 0x974, 0xff);
 		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x944, 0x3, 0x3);
 		btcoexist->btc_write_1byte(btcoexist, 0x930, 0x77);
 		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x67, 0x20, 0x1);
 
-		/* Force GNT_BT to low */
-		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x765, 0x18, 0x0);
+		if (fw_ver >= 0x180000) {
+			/* Use H2C to set GNT_BT to High to avoid A2DP click */
+			h2c_parameter[0] = 1;
+			btcoexist->btc_fill_h2c(btcoexist, 0x6E, 1,
+						h2c_parameter);
+		} else {
+			btcoexist->btc_write_1byte(btcoexist, 0x765, 0x18);
+		}
+
+		btcoexist->btc_write_4byte(btcoexist, 0x948, 0x0);
+
+		/* WiFi TRx Mask off */
+		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A,
+					  0x1, 0xfffff, 0x0);
 
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT) {
 			/* tell firmware "no antenna inverse" */
 			h2c_parameter[0] = 0;
-			h2c_parameter[1] = 1;  /* ext switch type */
-			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
-						h2c_parameter);
-			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
 		} else {
 			/* tell firmware "antenna inverse" */
 			h2c_parameter[0] = 1;
-			h2c_parameter[1] = 1;  /* ext switch type */
-			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
+		}
+
+		if (use_ext_switch) {
+			/* ext switch type */
+			h2c_parameter[1] = 1;
+		} else {
+			/* int switch type */
+			h2c_parameter[1] = 0;
+		}
+		btcoexist->btc_fill_h2c(btcoexist, 0x65, 2, h2c_parameter);
+	} else {
+		if (fw_ver >= 0x180000) {
+			/* Use H2C to set GNT_BT to "Control by PTA"*/
+			h2c_parameter[0] = 0;
+			btcoexist->btc_fill_h2c(btcoexist, 0x6E, 1,
 						h2c_parameter);
-			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x280);
+		} else {
+			btcoexist->btc_write_1byte(btcoexist, 0x765, 0x0);
 		}
 	}
 
 	/* ext switch setting */
 	if (use_ext_switch) {
+		if (init_hwcfg) {
+			/* 0x4c[23] = 0, 0x4c[24] = 1 Ant controlled by WL/BT */
+			u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
+			u32tmp &= ~BIT23;
+			u32tmp |= BIT24;
+			btcoexist->btc_write_4byte(btcoexist, 0x4c, u32tmp);
+		}
+
 		/* fixed internal switch S1->WiFi, S0->BT */
-		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT)
-			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
-		else
-			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x280);
+		btcoexist->btc_write_4byte(btcoexist, 0x948, 0x0);
 
 		switch (antpos_type) {
 		case BTC_ANT_WIFI_AT_MAIN:
@@ -1240,9 +1167,18 @@ static void btc8723b2ant_set_ant_path(struct btc_coexist *btcoexist,
 							   0x92c, 0x3, 0x2);
 			break;
 		}
-	} else {	/* internal switch */
-		/* fixed ext switch */
-		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x92c, 0x3, 0x1);
+	} else {
+		/* internal switch */
+		if (init_hwcfg) {
+			/* 0x4c[23] = 0, 0x4c[24] = 1 Ant controlled by WL/BT */
+			u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
+			u32tmp |= BIT23;
+			u32tmp &= ~BIT24;
+			btcoexist->btc_write_4byte(btcoexist, 0x4c, u32tmp);
+		}
+
+		/* fixed ext switch, S1->Main, S0->Aux */
+		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x64, 0x1, 0x0);
 		switch (antpos_type) {
 		case BTC_ANT_WIFI_AT_MAIN:
 			/* fixed internal switch S1->WiFi, S0->BT */
@@ -1260,6 +1196,17 @@ static void btc8723b2ant_ps_tdma(struct btc_coexist *btcoexist, bool force_exec,
 				 bool turn_on, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+	u8 wifi_rssi_state, bt_rssi_state;
+	s8 wifi_duration_adjust = 0x0;
+	u8 tdma_byte4_modify = 0x0;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s turn %s PS TDMA, type=%d\n",
@@ -1268,6 +1215,15 @@ static void btc8723b2ant_ps_tdma(struct btc_coexist *btcoexist, bool force_exec,
 	coex_dm->cur_ps_tdma_on = turn_on;
 	coex_dm->cur_ps_tdma = type;
 
+	if (!(BTC_RSSI_HIGH(wifi_rssi_state) &&
+	      BTC_RSSI_HIGH(bt_rssi_state)) && turn_on) {
+		 /* for WiFi RSSI low or BT RSSI low */
+		type = type + 100;
+		coex_dm->is_switch_to_1dot5_ant = true;
+	} else {
+		coex_dm->is_switch_to_1dot5_ant = false;
+	}
+
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], bPrePsTdmaOn = %d, bCurPsTdmaOn = %d!!\n",
@@ -1280,83 +1236,131 @@ static void btc8723b2ant_ps_tdma(struct btc_coexist *btcoexist, bool force_exec,
 		    (coex_dm->pre_ps_tdma == coex_dm->cur_ps_tdma))
 			return;
 	}
+
+	if (coex_sta->scan_ap_num <= 5) {
+		if (coex_sta->a2dp_bit_pool >= 45)
+			wifi_duration_adjust = -15;
+		else if (coex_sta->a2dp_bit_pool >= 35)
+			wifi_duration_adjust = -10;
+		else
+			wifi_duration_adjust = 5;
+	} else if (coex_sta->scan_ap_num <= 20) {
+		if (coex_sta->a2dp_bit_pool >= 45)
+			wifi_duration_adjust = -15;
+		else if (coex_sta->a2dp_bit_pool >= 35)
+			wifi_duration_adjust = -10;
+		else
+			wifi_duration_adjust = 0;
+	} else if (coex_sta->scan_ap_num <= 40) {
+		if (coex_sta->a2dp_bit_pool >= 45)
+			wifi_duration_adjust = -15;
+		else if (coex_sta->a2dp_bit_pool >= 35)
+			wifi_duration_adjust = -10;
+		else
+			wifi_duration_adjust = -5;
+	} else {
+		if (coex_sta->a2dp_bit_pool >= 45)
+			wifi_duration_adjust = -15;
+		else if (coex_sta->a2dp_bit_pool >= 35)
+			wifi_duration_adjust = -10;
+		else
+			wifi_duration_adjust = -10;
+	}
+
+	if ((bt_link_info->slave_role) && (bt_link_info->a2dp_exist))
+		/* 0x778 = 0x1 at wifi slot (no blocking BT Low-Pri pkts) */
+		tdma_byte4_modify = 0x1;
+
 	if (turn_on) {
 		switch (type) {
 		case 1:
 		default:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
-						    0x1a, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x3c,
+				0x03, 0xf1, 0x90 | tdma_byte4_modify);
 			break;
 		case 2:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
-						    0x12, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x2d,
+				0x03, 0xf1, 0x90 | tdma_byte4_modify);
 			break;
 		case 3:
-			/* This call breaks BT when wireless is active -
-			 * comment it out for now until a better fix is found:
-			 * btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
-			 *			    0x3, 0xf1, 0x90);
-			 */
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0xf1,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 4:
 			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
-						    0x03, 0xf1, 0x90);
+						    0x03, 0xf1,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 5:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
-						    0x1a, 0x60, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x3c,
+				0x3, 0x70, 0x90 | tdma_byte4_modify);
 			break;
 		case 6:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
-						    0x12, 0x60, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x2d,
+				0x3, 0x70, 0x90 | tdma_byte4_modify);
 			break;
 		case 7:
 			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
-						    0x3, 0x70, 0x90);
+						    0x3, 0x70,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 8:
 			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xa3, 0x10,
-						    0x3, 0x70, 0x90);
+						    0x3, 0x70,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 9:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
-						    0x1a, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x3c + wifi_duration_adjust,
+				0x03, 0xf1, 0x90 | tdma_byte4_modify);
 			break;
 		case 10:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
-						    0x12, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x2d,
+				0x03, 0xf1, 0x90 | tdma_byte4_modify);
 			break;
 		case 11:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0xa,
-						    0xa, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0xf1,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 12:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x5,
-						    0x5, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
+						    0x3, 0xf1,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 13:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
-						    0x1a, 0x60, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x3c,
+				0x3, 0x70, 0x90 | tdma_byte4_modify);
 			break;
 		case 14:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x12,
-						    0x12, 0x60, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x2d,
+				0x3, 0x70, 0x90 | tdma_byte4_modify);
 			break;
 		case 15:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0xa,
-						    0xa, 0x60, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0x70,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 16:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x5,
-						    0x5, 0x60, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
+						    0x3, 0x70,
+						    0x90 | tdma_byte4_modify);
 			break;
 		case 17:
 			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xa3, 0x2f,
 						    0x2f, 0x60, 0x90);
 			break;
 		case 18:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x5,
-						    0x5, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x5, 0x5,
+						    0xe1, 0x90);
 			break;
 		case 19:
 			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
@@ -1370,9 +1374,63 @@ static void btc8723b2ant_ps_tdma(struct btc_coexist *btcoexist, bool force_exec,
 			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x15,
 						    0x03, 0x70, 0x90);
 			break;
+
+		case 23:
+		case 123:
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x35,
+						    0x03, 0x71, 0x10);
+			break;
 		case 71:
-			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1a,
-						    0x1a, 0xe1, 0x90);
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xe3, 0x3c + wifi_duration_adjust,
+				0x03, 0xf1, 0x90);
+			break;
+		case 101:
+		case 105:
+		case 113:
+		case 171:
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xd3, 0x3a + wifi_duration_adjust,
+				0x03, 0x70, 0x50 | tdma_byte4_modify);
+			break;
+		case 102:
+		case 106:
+		case 110:
+		case 114:
+			btc8723b2ant_set_fw_ps_tdma(
+				btcoexist, 0xd3, 0x2d + wifi_duration_adjust,
+				0x03, 0x70, 0x50 | tdma_byte4_modify);
+			break;
+		case 103:
+		case 107:
+		case 111:
+		case 115:
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x1c,
+						    0x03, 0x70,
+						    0x50 | tdma_byte4_modify);
+			break;
+		case 104:
+		case 108:
+		case 112:
+		case 116:
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x10,
+						    0x03, 0x70,
+						    0x50 | tdma_byte4_modify);
+			break;
+		case 109:
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x03, 0xf1,
+						    0x90 | tdma_byte4_modify);
+			break;
+		case 121:
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x15,
+						    0x03, 0x70,
+						    0x90 | tdma_byte4_modify);
+			break;
+		case 22:
+		case 122:
+			btc8723b2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x35,
+						    0x03, 0x71, 0x11);
 			break;
 		}
 	} else {
@@ -1398,62 +1456,202 @@ static void btc8723b2ant_ps_tdma(struct btc_coexist *btcoexist, bool force_exec,
 	coex_dm->pre_ps_tdma = coex_dm->cur_ps_tdma;
 }
 
+static void btc8723b2ant_ps_tdma_check_for_power_save_state(
+		struct btc_coexist *btcoexist, bool new_ps_state)
+{
+	u8 lps_mode = 0x0;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U1_LPS_MODE, &lps_mode);
+
+	if (lps_mode) {
+		/* already under LPS state */
+		if (new_ps_state) {
+			/* keep state under LPS, do nothing. */
+		} else {
+			/* will leave LPS state, turn off psTdma first */
+			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+		}
+	} else {
+		/* NO PS state */
+		if (new_ps_state) {
+			/* will enter LPS state, turn off psTdma first */
+			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+		} else {
+			/* keep state under NO PS state, do nothing. */
+		}
+	}
+}
+
+static void btc8723b2ant_power_save_state(struct btc_coexist *btcoexist,
+					  u8 ps_type, u8 lps_val, u8 rpwm_val)
+{
+	bool low_pwr_disable = false;
+
+	switch (ps_type) {
+	case BTC_PS_WIFI_NATIVE:
+		/* recover to original 32k low power setting */
+		low_pwr_disable = false;
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
+				   &low_pwr_disable);
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_NORMAL_LPS, NULL);
+		coex_sta->force_lps_on = false;
+		break;
+	case BTC_PS_LPS_ON:
+		btc8723b2ant_ps_tdma_check_for_power_save_state(btcoexist,
+								true);
+		btc8723b2ant_lps_rpwm(btcoexist, NORMAL_EXEC, lps_val,
+				      rpwm_val);
+		/* when coex force to enter LPS, do not enter 32k low power */
+		low_pwr_disable = true;
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
+				   &low_pwr_disable);
+		/* power save must executed before psTdma */
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_ENTER_LPS, NULL);
+		coex_sta->force_lps_on = true;
+		break;
+	case BTC_PS_LPS_OFF:
+		btc8723b2ant_ps_tdma_check_for_power_save_state(btcoexist,
+								false);
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_LEAVE_LPS, NULL);
+		coex_sta->force_lps_on = false;
+		break;
+	default:
+		break;
+	}
+}
+
 static void btc8723b2ant_coex_alloff(struct btc_coexist *btcoexist)
 {
 	/* fw all off */
+	btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
 	btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-	btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
 	/* sw all off */
-	btc8723b2ant_sw_mechanism1(btcoexist, false, false, false, false);
-	btc8723b2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
+	btc8723b2ant_sw_mechanism(btcoexist, false, false, false, false);
 
 	/* hw all off */
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 0);
+	btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 }
 
 static void btc8723b2ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	/* force to reset coex mechanism*/
+	btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+	btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
 
 	btc8723b2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, FORCE_EXEC, 6);
-	btc8723b2ant_dec_bt_pwr(btcoexist, FORCE_EXEC, false);
+	btc8723b2ant_dec_bt_pwr(btcoexist, FORCE_EXEC, 0);
 
-	btc8723b2ant_sw_mechanism1(btcoexist, false, false, false, false);
-	btc8723b2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
+	btc8723b2ant_sw_mechanism(btcoexist, false, false, false, false);
+
+	coex_sta->pop_event_cnt = 0;
 }
 
 static void btc8723b2ant_action_bt_inquiry(struct btc_coexist *btcoexist)
 {
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	bool wifi_connected = false;
 	bool low_pwr_disable = true;
+	bool scan = false, link = false, roam = false;
 
 	btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 			   &low_pwr_disable);
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 			   &wifi_connected);
 
-	if (wifi_connected) {
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
-		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
+
+	btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+
+	if (coex_sta->bt_abnormal_scan) {
+		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 3);
+	} else if (scan || link || roam) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Wifi link process + BT Inq/Page!!\n");
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 15);
+		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
+	} else if (wifi_connected) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Wifi connected + BT Inq/Page!!\n");
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 15);
+		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
 	} else {
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 0);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 	}
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, FORCE_EXEC, 6);
-	btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+	btc8723b2ant_sw_mechanism(btcoexist, false, false, false, false);
+}
+
+static void btc8723b2ant_action_wifi_link_process(struct btc_coexist
+						     *btcoexist)
+{
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u32 u32tmp;
+	u8 u8tmpa, u8tmpb;
 
-	btc8723b2ant_sw_mechanism1(btcoexist, false, false, false, false);
-	btc8723b2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
+	btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 15);
+	btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
 
-	coex_dm->need_recover_0x948 = true;
-	coex_dm->backup_0x948 = btcoexist->btc_read_2byte(btcoexist, 0x948);
+	btc8723b2ant_sw_mechanism(btcoexist, false, false, false, false);
 
-	btc8723b2ant_set_ant_path(btcoexist, BTC_ANT_WIFI_AT_AUX,
-				  false, false);
+	u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x948);
+	u8tmpa = btcoexist->btc_read_1byte(btcoexist, 0x765);
+	u8tmpb = btcoexist->btc_read_1byte(btcoexist, 0x76e);
+
+	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+		 "[BTCoex], 0x948 = 0x%x, 0x765 = 0x%x, 0x76e = 0x%x\n",
+		 u32tmp, u8tmpa, u8tmpb);
+}
+
+static bool btc8723b2ant_action_wifi_idle_process(struct btc_coexist *btcoexist)
+{
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u8 ap_num = 0;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+		 coex_dm->switch_thres_offset - coex_dm->switch_thres_offset;
+
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+	      coex_dm->switch_thres_offset - coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U1_AP_NUM, &ap_num);
+
+	/* office environment */
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && (coex_sta->hid_exist) &&
+	    (coex_sta->a2dp_exist)) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Wifi  idle process for BT HID+A2DP exist!!\n");
+
+		btc8723b2ant_dac_swing(btcoexist, NORMAL_EXEC, true, 0x6);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+		/* sw all off */
+		btc8723b2ant_sw_mechanism(btcoexist, false, false, false,
+					  false);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+
+		return true;
+	}
+
+	btc8723b2ant_dac_swing(btcoexist, NORMAL_EXEC, true, 0x18);
+	return false;
 }
 
 static bool btc8723b2ant_is_common_action(struct btc_coexist *btcoexist)
@@ -1472,21 +1670,21 @@ static bool btc8723b2ant_is_common_action(struct btc_coexist *btcoexist)
 		low_pwr_disable = false;
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 				   &low_pwr_disable);
+		btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC,
+					false, false, 0x8);
 
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Wifi non-connected idle!!\n");
 
 		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff,
 					  0x0);
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 0);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 		btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-		btc8723b2ant_sw_mechanism1(btcoexist, false, false, false,
-					   false);
-		btc8723b2ant_sw_mechanism2(btcoexist, false, false, false,
-					   0x18);
+		btc8723b2ant_sw_mechanism(btcoexist, false, false, false,
+					  false);
 
 		common = true;
 	} else {
@@ -1496,23 +1694,23 @@ static bool btc8723b2ant_is_common_action(struct btc_coexist *btcoexist)
 			btcoexist->btc_set(btcoexist,
 					   BTC_SET_ACT_DISABLE_LOW_POWER,
 					   &low_pwr_disable);
+			btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC,
+						false, false, 0x8);
 
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Wifi connected + BT non connected-idle!!\n");
 
 			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1,
 						  0xfffff, 0x0);
-			btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 0);
+			btc8723b2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 0);
 			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 			btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC,
 						      0xb);
-			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC,
-						false);
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 
 			common = true;
 		} else if (BT_8723B_2ANT_BT_STATUS_CONNECTED_IDLE ==
@@ -1526,20 +1724,20 @@ static bool btc8723b2ant_is_common_action(struct btc_coexist *btcoexist)
 				return false;
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Wifi connected + BT connected-idle!!\n");
+			btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC,
+						false, false, 0x8);
 
 			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1,
 						  0xfffff, 0x0);
-			btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 0);
+			btc8723b2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 0);
 			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 			btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC,
 						      0xb);
-			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC,
-						false);
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 
 			common = true;
 		} else {
@@ -1553,36 +1751,12 @@ static bool btc8723b2ant_is_common_action(struct btc_coexist *btcoexist)
 					 "[BTCoex], Wifi Connected-Busy + BT Busy!!\n");
 				common = false;
 			} else {
-				if (bt_hs_on)
-					return false;
-
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], Wifi Connected-Idle + BT Busy!!\n");
 
-				btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A,
-							  0x1, 0xfffff, 0x0);
-				btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC,
-						       7);
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 21);
-				btc8723b2ant_fw_dac_swing_lvl(btcoexist,
-							      NORMAL_EXEC,
-							      0xb);
-				if (btc8723b_need_dec_pwr(btcoexist))
-					btc8723b2ant_dec_bt_pwr(btcoexist,
-								NORMAL_EXEC,
-								true);
-				else
-					btc8723b2ant_dec_bt_pwr(btcoexist,
-								NORMAL_EXEC,
-								false);
-				btc8723b2ant_sw_mechanism1(btcoexist, false,
-							   false, false,
-							   false);
-				btc8723b2ant_sw_mechanism2(btcoexist, false,
-							   false, false,
-							   0x18);
-				common = true;
+				common =
+				    btc8723b2ant_action_wifi_idle_process(
+						btcoexist);
 			}
 		}
 	}
@@ -1590,550 +1764,6 @@ static bool btc8723b2ant_is_common_action(struct btc_coexist *btcoexist)
 	return common;
 }
 
-static void set_tdma_int1(struct btc_coexist *btcoexist, bool tx_pause,
-			  s32 result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	/* Set PS TDMA for max interval == 1 */
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-
-		if (coex_dm->cur_ps_tdma == 71) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 5);
-			coex_dm->tdma_adj_type = 5;
-		} else if (coex_dm->cur_ps_tdma == 1) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 5);
-			coex_dm->tdma_adj_type = 5;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-
-		if (coex_dm->cur_ps_tdma == 9) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 13);
-			coex_dm->tdma_adj_type = 13;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					     true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		}  else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 5);
-				coex_dm->tdma_adj_type = 5;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 13);
-				coex_dm->tdma_adj_type = 13;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 71);
-			coex_dm->tdma_adj_type = 71;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-
-		if (coex_dm->cur_ps_tdma == 13) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 9);
-			coex_dm->tdma_adj_type = 9;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 71) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 1);
-				coex_dm->tdma_adj_type = 1;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		}  else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 1);
-				coex_dm->tdma_adj_type = 1;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 71);
-				coex_dm->tdma_adj_type = 71;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 9);
-				coex_dm->tdma_adj_type = 9;
-			}
-		}
-	}
-}
-
-static void set_tdma_int2(struct btc_coexist *btcoexist, bool tx_pause,
-			  s32 result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	/* Set PS TDMA for max interval == 2 */
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-		if (coex_dm->cur_ps_tdma == 1) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		}  else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 14);
-				coex_dm->tdma_adj_type = 14;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 1) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 10);
-				coex_dm->tdma_adj_type = 10;
-			}
-		}
-	}
-}
-
-static void set_tdma_int3(struct btc_coexist *btcoexist, bool tx_pause,
-			  s32 result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	/* Set PS TDMA for max interval == 3 */
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-		if (coex_dm->cur_ps_tdma == 1) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		}  else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 15);
-				coex_dm->tdma_adj_type = 15;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 1) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						     true, 11);
-				coex_dm->tdma_adj_type = 11;
-			}
-		}
-	}
-}
-
 static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					  bool sco_hid, bool tx_pause,
 					  u8 max_interval)
@@ -2157,34 +1787,44 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 13);
-					coex_dm->tdma_adj_type = 13;
+					coex_dm->ps_tdma_du_adj_type = 13;
 				} else if (max_interval == 2) {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 14);
-					coex_dm->tdma_adj_type = 14;
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (max_interval == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
 				} else {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 15);
-					coex_dm->tdma_adj_type = 15;
+					coex_dm->ps_tdma_du_adj_type = 15;
 				}
 			} else {
 				if (max_interval == 1) {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 9);
-					coex_dm->tdma_adj_type = 9;
+					coex_dm->ps_tdma_du_adj_type = 9;
 				} else if (max_interval == 2) {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 10);
-					coex_dm->tdma_adj_type = 10;
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (max_interval == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+						     true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
 				} else {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 11);
-					coex_dm->tdma_adj_type = 11;
+					coex_dm->ps_tdma_du_adj_type = 11;
 				}
 			}
 		} else {
@@ -2193,34 +1833,44 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 5);
-					coex_dm->tdma_adj_type = 5;
+					coex_dm->ps_tdma_du_adj_type = 5;
 				} else if (max_interval == 2) {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 6);
-					coex_dm->tdma_adj_type = 6;
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (max_interval == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
 				} else {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 7);
-					coex_dm->tdma_adj_type = 7;
+					coex_dm->ps_tdma_du_adj_type = 7;
 				}
 			} else {
 				if (max_interval == 1) {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 1);
-					coex_dm->tdma_adj_type = 1;
+					coex_dm->ps_tdma_du_adj_type = 1;
 				} else if (max_interval == 2) {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 2);
-					coex_dm->tdma_adj_type = 2;
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (max_interval == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
 				} else {
 					btc8723b2ant_ps_tdma(btcoexist,
 							     NORMAL_EXEC,
 							     true, 3);
-					coex_dm->tdma_adj_type = 3;
+					coex_dm->ps_tdma_du_adj_type = 3;
 				}
 			}
 		}
@@ -2234,6 +1884,11 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 	} else {
 		/*accquire the BT TRx retry count from BT_Info byte2*/
 		retry_count = coex_sta->bt_retry_cnt;
+
+		if ((coex_sta->low_priority_tx) > 1050 ||
+		    (coex_sta->low_priority_rx) > 1250)
+			retry_count++;
+
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], retry_count = %d\n", retry_count);
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -2250,6 +1905,9 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 				dn = 0;
 
 			if (up >= n) {
+				/* if retry count during continuous n*2
+				 * seconds is 0, enlarge WiFi duration
+				 */
 				wait_count = 0;
 				n = 3;
 				up = 0;
@@ -2266,12 +1924,20 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 				up = 0;
 
 			if (dn == 2) {
+				/* if continuous 2 retry count(every 2
+				 * seconds) >0 and < 3, reduce WiFi duration
+				 */
 				if (wait_count <= 2)
+					/* avoid loop between the two levels */
 					m++;
 				else
 					m = 1;
 
 				if (m >= 20)
+					/* maximum of m = 20 ' will recheck if
+					 * need to adjust wifi duration in
+					 * maximum time interval 120 seconds
+					 */
 					m = 20;
 
 				n = 3 * m;
@@ -2283,12 +1949,20 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					 "[BTCoex], Decrease wifi duration for retry_counter<3!!\n");
 			}
 		} else {
+			/* retry count > 3, once retry count > 3, to reduce
+			 *  WiFi duration
+			 */
 			if (wait_count == 1)
+				/* to avoid loop between the two levels */
 				m++;
 			else
 				m = 1;
 
 			if (m >= 20)
+				/* maximum of m = 20 ' will recheck if need to
+				 * adjust wifi duration in maximum time interval
+				 * 120 seconds
+				 */
 				m = 20;
 
 			n = 3 * m;
@@ -2302,22 +1976,765 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], max Interval = %d\n", max_interval);
-		if (max_interval == 1)
-			set_tdma_int1(btcoexist, tx_pause, result);
-		else if (max_interval == 2)
-			set_tdma_int2(btcoexist, tx_pause, result);
-		else if (max_interval == 3)
-			set_tdma_int3(btcoexist, tx_pause, result);
+		if (max_interval == 1) {
+			if (tx_pause) {
+				if (coex_dm->cur_ps_tdma == 71) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 5);
+					coex_dm->ps_tdma_du_adj_type = 5;
+				} else if (coex_dm->cur_ps_tdma == 1) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 5);
+					coex_dm->ps_tdma_du_adj_type = 5;
+				} else if (coex_dm->cur_ps_tdma == 2) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (coex_dm->cur_ps_tdma == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 4) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 8);
+					coex_dm->ps_tdma_du_adj_type = 8;
+				}
+				if (coex_dm->cur_ps_tdma == 9) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 13);
+					coex_dm->ps_tdma_du_adj_type = 13;
+				} else if (coex_dm->cur_ps_tdma == 10) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (coex_dm->cur_ps_tdma == 11) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 12) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 16);
+					coex_dm->ps_tdma_du_adj_type = 16;
+				}
+
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 5) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 8);
+						coex_dm->ps_tdma_du_adj_type =
+							8;
+					} else if (coex_dm->cur_ps_tdma == 13) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 16);
+						coex_dm->ps_tdma_du_adj_type =
+							16;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 8) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 5);
+						coex_dm->ps_tdma_du_adj_type =
+							5;
+					} else if (coex_dm->cur_ps_tdma == 16) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 13);
+						coex_dm->ps_tdma_du_adj_type =
+							13;
+					}
+				}
+			} else {
+				if (coex_dm->cur_ps_tdma == 5) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 71);
+					coex_dm->ps_tdma_du_adj_type = 71;
+				} else if (coex_dm->cur_ps_tdma == 6) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (coex_dm->cur_ps_tdma == 7) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 8) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 4);
+					coex_dm->ps_tdma_du_adj_type = 4;
+				}
+				if (coex_dm->cur_ps_tdma == 13) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 9);
+					coex_dm->ps_tdma_du_adj_type = 9;
+				} else if (coex_dm->cur_ps_tdma == 14) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (coex_dm->cur_ps_tdma == 15) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 16) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 12);
+					coex_dm->ps_tdma_du_adj_type = 12;
+				}
+
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 71) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 1);
+						coex_dm->ps_tdma_du_adj_type =
+							1;
+					} else if (coex_dm->cur_ps_tdma == 1) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 4);
+						coex_dm->ps_tdma_du_adj_type =
+							4;
+					} else if (coex_dm->cur_ps_tdma == 9) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 12);
+						coex_dm->ps_tdma_du_adj_type =
+							12;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 4) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 1);
+						coex_dm->ps_tdma_du_adj_type =
+							1;
+					} else if (coex_dm->cur_ps_tdma == 1) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 71);
+						coex_dm->ps_tdma_du_adj_type =
+							71;
+					} else if (coex_dm->cur_ps_tdma == 12) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 9);
+						coex_dm->ps_tdma_du_adj_type =
+							9;
+					}
+				}
+			}
+		} else if (max_interval == 2) {
+			if (tx_pause) {
+				if (coex_dm->cur_ps_tdma == 1) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (coex_dm->cur_ps_tdma == 2) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (coex_dm->cur_ps_tdma == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 4) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 8);
+					coex_dm->ps_tdma_du_adj_type = 8;
+				}
+				if (coex_dm->cur_ps_tdma == 9) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (coex_dm->cur_ps_tdma == 10) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (coex_dm->cur_ps_tdma == 11) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 12) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 16);
+					coex_dm->ps_tdma_du_adj_type = 16;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 5) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 8);
+						coex_dm->ps_tdma_du_adj_type =
+							8;
+					} else if (coex_dm->cur_ps_tdma == 13) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 16);
+						coex_dm->ps_tdma_du_adj_type =
+							16;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 8) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 16) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					}
+				}
+			} else {
+				if (coex_dm->cur_ps_tdma == 5) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (coex_dm->cur_ps_tdma == 6) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (coex_dm->cur_ps_tdma == 7) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 8) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 4);
+					coex_dm->ps_tdma_du_adj_type = 4;
+				}
+				if (coex_dm->cur_ps_tdma == 13) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (coex_dm->cur_ps_tdma == 14) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (coex_dm->cur_ps_tdma == 15) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 16) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 12);
+					coex_dm->ps_tdma_du_adj_type = 12;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 1) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 4);
+						coex_dm->ps_tdma_du_adj_type =
+							4;
+					} else if (coex_dm->cur_ps_tdma == 9) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 12);
+						coex_dm->ps_tdma_du_adj_type =
+							12;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 4) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 12) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					}
+				}
+			}
+		} else if (max_interval == 3) {
+			if (tx_pause) {
+				if (coex_dm->cur_ps_tdma == 1) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 2) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 3) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 4) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 8);
+					coex_dm->ps_tdma_du_adj_type = 8;
+				}
+				if (coex_dm->cur_ps_tdma == 9) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 10) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 11) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 12) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 16);
+					coex_dm->ps_tdma_du_adj_type = 16;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 5) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 8);
+						coex_dm->ps_tdma_du_adj_type =
+							8;
+					} else if (coex_dm->cur_ps_tdma == 13) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 16);
+						coex_dm->ps_tdma_du_adj_type =
+							16;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 8) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 16) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					}
+				}
+			} else {
+				if (coex_dm->cur_ps_tdma == 5) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 6) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 7) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 8) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 4);
+					coex_dm->ps_tdma_du_adj_type = 4;
+				}
+				if (coex_dm->cur_ps_tdma == 13) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 14) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 15) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 16) {
+					btc8723b2ant_ps_tdma(btcoexist,
+							     NORMAL_EXEC,
+							     true, 12);
+					coex_dm->ps_tdma_du_adj_type = 12;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 1) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 4);
+						coex_dm->ps_tdma_du_adj_type =
+							4;
+					} else if (coex_dm->cur_ps_tdma == 9) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 12);
+						coex_dm->ps_tdma_du_adj_type =
+							12;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 4) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 12) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8723b2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					}
+				}
+			}
+		}
 	}
 
-	/*if current PsTdma not match with the recorded one (when scan, dhcp..),
-	 *then we have to adjust it back to the previous recorded one.
+	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+		 "[BTCoex], max Interval = %d\n", max_interval);
+
+	/* if current PsTdma not match with the recorded one (scan, dhcp, ...),
+	 * then we have to adjust it back to the previous recorded one.
 	 */
-	if (coex_dm->cur_ps_tdma != coex_dm->tdma_adj_type) {
+	if (coex_dm->cur_ps_tdma != coex_dm->ps_tdma_du_adj_type) {
 		bool scan = false, link = false, roam = false;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], PsTdma type dismatch!!!, curPsTdma=%d, recordPsTdma=%d\n",
-			 coex_dm->cur_ps_tdma, coex_dm->tdma_adj_type);
+			 coex_dm->cur_ps_tdma, coex_dm->ps_tdma_du_adj_type);
 
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
@@ -2325,7 +2742,7 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 
 		if (!scan && !link && !roam)
 			btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true,
-					     coex_dm->tdma_adj_type);
+					     coex_dm->ps_tdma_du_adj_type);
 		else
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], roaming/link/scan is under progress, will adjust next time!!!\n");
@@ -2335,58 +2752,55 @@ static void btc8723b2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 /* SCO only or SCO+PAN(HS) */
 static void btc8723b2ant_action_sco(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state;
+	u8 wifi_rssi_state, bt_rssi_state;
 	u32 wifi_bw;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(
+		btcoexist, 2, BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+					       coex_dm->switch_thres_offset,
+		0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 4);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	/*for SCO quality at 11b/g mode*/
 	if (BTC_WIFI_BW_LEGACY == wifi_bw)
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 2);
-	else  /*for SCO quality & wifi performance balance at 11n mode*/
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 8);
+		/* for SCO quality at 11b/g mode */
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
+	else
+		/* for SCO quality & wifi performance balance at 11n mode */
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 8);
 
-	/*for voice quality */
+	/* for voice quality */
 	btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   true, 0x4);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   true, 0x4);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   true, 0x4);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   true, 0x4);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		}
 	}
 }
@@ -2395,26 +2809,32 @@ static void btc8723b2ant_action_hid(struct btc_coexist *btcoexist)
 {
 	u8 wifi_rssi_state, bt_rssi_state;
 	u32 wifi_bw;
+	u8 tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	if (BTC_WIFI_BW_LEGACY == wifi_bw) /*/for HID at 11b/g mode*/
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
-	else  /*for HID quality & wifi performance balance at 11n mode*/
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 9);
+	if (wifi_bw == BTC_WIFI_BW_LEGACY)
+		/* for HID at 11b/g mode */
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+	else
+		/* for HID quality & wifi performance balance at 11n mode */
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 9);
+
+	btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
 
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
@@ -2426,44 +2846,36 @@ static void btc8723b2ant_action_hid(struct btc_coexist *btcoexist)
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		}
 	}
 }
 
-/*A2DP only / PAN(EDR) only/ A2DP+PAN(HS)*/
+/* A2DP only / PAN(EDR) only/ A2DP+PAN(HS) */
 static void btc8723b2ant_action_a2dp(struct btc_coexist *btcoexist)
 {
 	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
 	u8 ap_num = 0;
+	u8 tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist,
-							1, 2, 40, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2, 40, 0);
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U1_AP_NUM, &ap_num);
 
@@ -2474,35 +2886,40 @@ static void btc8723b2ant_action_a2dp(struct btc_coexist *btcoexist)
 					  0x0);
 		btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 0);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 
 		/* sw mechanism */
 		btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 		if (BTC_WIFI_BW_HT40 == wifi_bw) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   true, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   true, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		}
 		return;
 	}
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
@@ -2516,104 +2933,116 @@ static void btc8723b2ant_action_a2dp(struct btc_coexist *btcoexist)
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		}
 	}
 }
 
 static void btc8723b2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
 	btc8723b2ant_tdma_duration_adjust(btcoexist, false, true, 2);
 
 	/* sw mechanism */
-	btcoexist->btc_get(btcoexist,
-		BTC_GET_U4_WIFI_BW, &wifi_bw);
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		}
 	}
 }
 
 static void btc8723b2ant_action_pan_edr(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state, bt_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 10);
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 10);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
@@ -2626,109 +3055,109 @@ static void btc8723b2ant_action_pan_edr(struct btc_coexist *btcoexist)
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		}
 	}
 }
 
-/*PAN(HS) only*/
+/* PAN(HS) only */
 static void btc8723b2ant_action_pan_hs(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-	    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
-
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
+	btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
 	btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		}
 	}
 }
 
-/*PAN(EDR)+A2DP*/
+/* PAN(EDR) + A2DP */
 static void btc8723b2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state, bt_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	else
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 12);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 12);
 		if (BTC_WIFI_BW_HT40 == wifi_bw)
 			btc8723b2ant_tdma_duration_adjust(btcoexist, false,
 							  true, 3);
@@ -2736,74 +3165,80 @@ static void btc8723b2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 			btc8723b2ant_tdma_duration_adjust(btcoexist, false,
 							  false, 3);
 	} else {
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
-		btc8723b2ant_tdma_duration_adjust(btcoexist, false, true, 3);
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
 	}
 
 	/* sw mechanism	*/
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, false,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, false,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, false,
+						  false, false);
 		}
 	}
 }
 
 static void btc8723b2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state, bt_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
-
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 14);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
 		if (BTC_WIFI_BW_HT40 == wifi_bw) {
 			btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC,
 						      3);
-			btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 11);
 			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1,
 						  0xfffff, 0x780);
 		} else {
 			btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC,
 						      6);
-			btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
 			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1,
 						  0xfffff, 0x0);
 		}
 		btc8723b2ant_tdma_duration_adjust(btcoexist, true, false, 2);
 	} else {
 		btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 11);
 		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff,
 					  0x0);
 		btc8723b2ant_tdma_duration_adjust(btcoexist, true, true, 2);
@@ -2813,54 +3248,61 @@ static void btc8723b2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		}
 	}
 }
 
-/* HID+A2DP+PAN(EDR) */
+/* HID + A2DP + PAN(EDR) */
 static void btc8723b2ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state, bt_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, tmp, 0);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 14);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
 
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
@@ -2878,94 +3320,148 @@ static void btc8723b2ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		}
 	}
 }
 
 static void btc8723b2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 {
-	u8 wifi_rssi_state, bt_rssi_state;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
 	u32 wifi_bw;
+	u8 ap_num = 0;
+	u8 tmp = BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES -
+			coex_dm->switch_thres_offset;
 
-	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist,
-						       0, 2, 15, 0);
-	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 2, 29, 0);
+	wifi_rssi_state = btc8723b2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8723b2ant_wifi_rssi_state(btcoexist, 1, 2,
+							tmp, 0);
+	tmp = BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES -
+			 coex_dm->switch_thres_offset;
+	bt_rssi_state = btc8723b2ant_bt_rssi_state(btcoexist, 3, tmp, 37);
 
 	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
+	btc8723b2ant_limited_rx(btcoexist, NORMAL_EXEC, false, true, 0x5);
 	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (btc8723b_need_dec_pwr(btcoexist))
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
-	else
-		btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
-
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	btc8723b_coex_tbl_type(btcoexist, NORMAL_EXEC, 7);
+	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
+		if (BTC_RSSI_HIGH(bt_rssi_state))
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		else if (BTC_RSSI_MEDIUM(bt_rssi_state))
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		else
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+	} else {
+		/* only 802.11N mode we have to dec bt power to 4 degree */
+		if (BTC_RSSI_HIGH(bt_rssi_state)) {
+			/* need to check ap Number of Not */
+			if (ap_num < 10)
+				btc8723b2ant_dec_bt_pwr(btcoexist,
+							NORMAL_EXEC, 4);
+			else
+				btc8723b2ant_dec_bt_pwr(btcoexist,
+							NORMAL_EXEC, 2);
+		} else if (BTC_RSSI_MEDIUM(bt_rssi_state)) {
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+		} else {
+			btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+		}
+	}
 
-	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
-		btc8723b2ant_tdma_duration_adjust(btcoexist, true, false, 2);
-	else
-		btc8723b2ant_tdma_duration_adjust(btcoexist, true, true, 2);
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 14);
+		btc8723b2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
+
+	if (BTC_RSSI_HIGH(bt_rssi_state)) {
+		if (ap_num < 10)
+			btc8723b2ant_tdma_duration_adjust(btcoexist, true,
+							  false, 1);
+		else
+			btc8723b2ant_tdma_duration_adjust(btcoexist, true,
+							  false, 3);
+	} else {
+		btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 18);
+		btcoexist->btc_write_1byte(btcoexist, 0x456, 0x38);
+		btcoexist->btc_write_2byte(btcoexist, 0x42a, 0x0808);
+		btcoexist->btc_write_4byte(btcoexist, 0x430, 0x0);
+		btcoexist->btc_write_4byte(btcoexist, 0x434, 0x01010000);
+
+		if (ap_num < 10)
+			btc8723b2ant_tdma_duration_adjust(btcoexist, true,
+							  true, 1);
+		else
+			btc8723b2ant_tdma_duration_adjust(btcoexist, true,
+							  true, 3);
+	}
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, true, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, true, true,
+						  false, false);
 		}
 	} else {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, true, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		} else {
-			btc8723b2ant_sw_mechanism1(btcoexist, false, true,
-						   false, false);
-			btc8723b2ant_sw_mechanism2(btcoexist, false, false,
-						   false, 0x18);
+			btc8723b2ant_sw_mechanism(btcoexist, false, true,
+						  false, false);
 		}
 	}
 }
 
+static void btc8723b2ant_action_wifi_multi_port(struct btc_coexist *btcoexist)
+{
+	btc8723b2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8723b2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+	/* sw all off */
+	btc8723b2ant_sw_mechanism(btcoexist, false, false, false, false);
+
+	/* hw all off */
+	btc8723b2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+
+	btc8723b2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8723b2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+}
+
 static void btc8723b2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 algorithm = 0;
+	u32 num_of_wifi_link = 0;
+	u32 wifi_link_status = 0;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+	bool miracast_plus_bt = false;
+	bool scan = false, link = false, roam = false;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], RunCoexistMechanism()===>\n");
@@ -2989,14 +3485,46 @@ static void btc8723b2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 			 "[BTCoex], BT is under inquiry/page scan !!\n");
 		btc8723b2ant_action_bt_inquiry(btcoexist);
 		return;
-	} else {
-		if (coex_dm->need_recover_0x948) {
-			coex_dm->need_recover_0x948 = false;
-			btcoexist->btc_write_2byte(btcoexist, 0x948,
-						   coex_dm->backup_0x948);
-		}
 	}
 
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
+
+	if (scan || link || roam) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], WiFi is under Link Process !!\n");
+		btc8723b2ant_action_wifi_link_process(btcoexist);
+		return;
+	}
+
+	/* for P2P */
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_LINK_STATUS,
+			   &wifi_link_status);
+	num_of_wifi_link = wifi_link_status >> 16;
+
+	if ((num_of_wifi_link >= 2) ||
+	    (wifi_link_status & WIFI_P2P_GO_CONNECTED)) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "############# [BTCoex],  Multi-Port num_of_wifi_link = %d, wifi_link_status = 0x%x\n",
+			 num_of_wifi_link, wifi_link_status);
+
+		if (bt_link_info->bt_link_exist)
+			miracast_plus_bt = true;
+		else
+			miracast_plus_bt = false;
+
+		btcoexist->btc_set(btcoexist, BTC_SET_BL_MIRACAST_PLUS_BT,
+				   &miracast_plus_bt);
+		btc8723b2ant_action_wifi_multi_port(btcoexist);
+
+		return;
+	}
+
+	miracast_plus_bt = false;
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_MIRACAST_PLUS_BT,
+			   &miracast_plus_bt);
+
 	coex_dm->cur_algorithm = algorithm;
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Algorithm = %d\n",
@@ -3077,19 +3605,37 @@ static void btc8723b2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 
 static void btc8723b2ant_wifioff_hwcfg(struct btc_coexist *btcoexist)
 {
+	bool is_in_mp_mode = false;
+	u8 h2c_parameter[2] = {0};
+	u32 fw_ver = 0;
+
 	/* set wlan_act to low */
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0x4);
-	/* Force GNT_BT to High */
-	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x765, 0x18, 0x3);
-	/* BT select s0/s1 is controlled by BT */
-	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x67, 0x20, 0x0);
+
+	/* WiFi standby while GNT_BT 0 -> 1 */
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x780);
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_FW_VER, &fw_ver);
+	if (fw_ver >= 0x180000) {
+		/* Use H2C to set GNT_BT to HIGH */
+		h2c_parameter[0] = 1;
+		btcoexist->btc_fill_h2c(btcoexist, 0x6E, 1, h2c_parameter);
+	} else {
+		btcoexist->btc_write_1byte(btcoexist, 0x765, 0x18);
+	}
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_IS_IN_MP_MODE,
+			   &is_in_mp_mode);
+	if (!is_in_mp_mode)
+		/* BT select s0/s1 is controlled by BT */
+		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x67, 0x20, 0x0);
+	else
+		/* BT select s0/s1 is controlled by WiFi */
+		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x67, 0x20, 0x1);
 }
 
 /*********************************************************************
- *  work around function start with wa_btc8723b2ant_
- *********************************************************************/
-/*********************************************************************
- *  extern function start with EXbtc8723b2ant_
+ *  extern function start with ex_btc8723b2ant_
  *********************************************************************/
 void ex_btc8723b2ant_init_hwconfig(struct btc_coexist *btcoexist)
 {
@@ -3107,19 +3653,90 @@ void ex_btc8723b2ant_init_hwconfig(struct btc_coexist *btcoexist)
 	u8tmp |= 0x5;
 	btcoexist->btc_write_1byte(btcoexist, 0x790, u8tmp);
 
-	/*Antenna config */
+	/* Antenna config */
 	btc8723b2ant_set_ant_path(btcoexist, BTC_ANT_WIFI_AT_MAIN,
 				  true, false);
+	coex_sta->dis_ver_info_cnt = 0;
+
 	/* PTA parameter */
-	btc8723b_coex_tbl_type(btcoexist, FORCE_EXEC, 0);
+	btc8723b2ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
 
 	/* Enable counter statistics */
-	/*0x76e[3] =1, WLAN_Act control by PTA*/
-	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
+	/* 0x76e[3] = 1, WLAN_ACT controlled by PTA */
+	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0x4);
 	btcoexist->btc_write_1byte(btcoexist, 0x778, 0x3);
 	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x40, 0x20, 0x1);
 }
 
+void ex_btc8723b2ant_power_on_setting(struct btc_coexist *btcoexist)
+{
+	struct btc_board_info *board_info = &btcoexist->board_info;
+	u16 u16tmp = 0x0;
+	u32 value = 0;
+
+	btcoexist->btc_write_1byte(btcoexist, 0x67, 0x20);
+
+	/* enable BB, REG_SYS_FUNC_EN such that we can write 0x948 correctly */
+	u16tmp = btcoexist->btc_read_2byte(btcoexist, 0x2);
+	btcoexist->btc_write_2byte(btcoexist, 0x2, u16tmp | BIT0 | BIT1);
+
+	btcoexist->btc_write_4byte(btcoexist, 0x948, 0x0);
+
+	if (btcoexist->chip_interface == BTC_INTF_USB) {
+		/* fixed at S0 for USB interface */
+		board_info->btdm_ant_pos = BTC_ANTENNA_AT_AUX_PORT;
+	} else {
+		/* for PCIE and SDIO interface, we check efuse 0xc3[6] */
+		if (board_info->single_ant_path == 0) {
+			/* set to S1 */
+			board_info->btdm_ant_pos = BTC_ANTENNA_AT_MAIN_PORT;
+		} else if (board_info->single_ant_path == 1) {
+			/* set to S0 */
+			board_info->btdm_ant_pos = BTC_ANTENNA_AT_AUX_PORT;
+		}
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_ANTPOSREGRISTRY_CTRL,
+				   &value);
+	}
+}
+
+void ex_btc8723b2ant_pre_load_firmware(struct btc_coexist *btcoexist)
+{
+	struct btc_board_info *board_info = &btcoexist->board_info;
+	u8 u8tmp = 0x4; /* Set BIT2 by default since it's 2ant case */
+
+	/**
+	 * S0 or S1 setting and Local register setting(By this fw can get
+	 * ant number, S0/S1, ... info)
+	 *
+	 * Local setting bit define
+	 *	BIT0: "0" : no antenna inverse; "1" : antenna inverse
+	 *	BIT1: "0" : internal switch; "1" : external switch
+	 *	BIT2: "0" : one antenna; "1" : two antennas
+	 *
+	 * NOTE: here default all internal switch and 1-antenna ==> BIT1=0 and
+	 * BIT2 = 0
+	 */
+	if (btcoexist->chip_interface == BTC_INTF_USB) {
+		/* fixed at S0 for USB interface */
+		u8tmp |= 0x1; /* antenna inverse */
+		btcoexist->btc_write_local_reg_1byte(btcoexist, 0xfe08, u8tmp);
+	} else {
+		/* for PCIE and SDIO interface, we check efuse 0xc3[6] */
+		if (board_info->single_ant_path == 0) {
+		} else if (board_info->single_ant_path == 1) {
+			/* set to S0 */
+			u8tmp |= 0x1; /* antenna inverse */
+		}
+
+		if (btcoexist->chip_interface == BTC_INTF_PCI)
+			btcoexist->btc_write_local_reg_1byte(btcoexist, 0x384,
+							     u8tmp);
+		else if (btcoexist->chip_interface == BTC_INTF_SDIO)
+			btcoexist->btc_write_local_reg_1byte(btcoexist, 0x60,
+							     u8tmp);
+	}
+}
+
 void ex_btc8723b2ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
@@ -3215,7 +3832,6 @@ void ex_btc8723b2ant_display_coex_info(struct btc_coexist *btcoexist)
 		 ((wifi_traffic_dir == BTC_WIFI_TRAFFIC_TX) ?
 		  "uplink" : "downlink")));
 
-
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = %d / %d / %d / %d",
 		 "SCO/HID/PAN/A2DP",
 		 bt_link_info->sco_exist, bt_link_info->hid_exist,
@@ -3265,7 +3881,7 @@ void ex_btc8723b2ant_display_coex_info(struct btc_coexist *btcoexist)
 		 ps_tdma_case, coex_dm->auto_tdma_adjust);
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s = %d/ %d ",
-		 "DecBtPwr/ IgnWlanAct", coex_dm->cur_dec_bt_pwr,
+		 "DecBtPwr/ IgnWlanAct", coex_dm->cur_dec_bt_pwr_lvl,
 		 coex_dm->cur_ignore_wlan_act);
 
 	/* Hw setting */
@@ -3396,6 +4012,12 @@ void ex_btc8723b2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 void ex_btc8723b2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u32 u32tmp;
+	u8 u8tmpa, u8tmpb;
+
+	u32tmp = btcoexist->btc_read_4byte(btcoexist, 0x948);
+	u8tmpa = btcoexist->btc_read_1byte(btcoexist, 0x765);
+	u8tmpb = btcoexist->btc_read_1byte(btcoexist, 0x76e);
 
 	if (BTC_SCAN_START == type)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3403,6 +4025,12 @@ void ex_btc8723b2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 	else if (BTC_SCAN_FINISH == type)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], SCAN FINISH notify\n");
+	btcoexist->btc_get(btcoexist, BTC_GET_U1_AP_NUM,
+			   &coex_sta->scan_ap_num);
+
+	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+		 "############# [BTCoex], 0x948=0x%x, 0x765=0x%x, 0x76e=0x%x\n",
+		u32tmp, u8tmpa, u8tmpb);
 }
 
 void ex_btc8723b2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
@@ -3424,6 +4052,7 @@ void ex_btc8723b2ant_media_status_notify(struct btc_coexist *btcoexist,
 	u8 h2c_parameter[3] = {0};
 	u32 wifi_bw;
 	u8 wifi_central_chnl;
+	u8 ap_num = 0;
 
 	if (BTC_MEDIA_CONNECT == type)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3441,10 +4070,16 @@ void ex_btc8723b2ant_media_status_notify(struct btc_coexist *btcoexist,
 		h2c_parameter[1] = wifi_central_chnl;
 		btcoexist->btc_get(btcoexist,
 			BTC_GET_U4_WIFI_BW, &wifi_bw);
-		if (BTC_WIFI_BW_HT40 == wifi_bw)
+		if (wifi_bw == BTC_WIFI_BW_HT40) {
 			h2c_parameter[2] = 0x30;
-		else
-			h2c_parameter[2] = 0x20;
+		} else {
+			btcoexist->btc_get(btcoexist, BTC_GET_U1_AP_NUM,
+					   &ap_num);
+			if (ap_num < 10)
+				h2c_parameter[2] = 0x30;
+			else
+				h2c_parameter[2] = 0x20;
+		}
 	}
 
 	coex_dm->wifi_chnl_info[0] = h2c_parameter[0];
@@ -3492,7 +4127,7 @@ void ex_btc8723b2ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_sta->bt_info_c2h[rsp_source][i] = tmpbuf[i];
 		if (i == 1)
 			bt_info = tmpbuf[i];
-		if (i == length-1)
+		if (i == length - 1)
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "0x%02x]\n", tmpbuf[i]);
 		else
@@ -3507,17 +4142,30 @@ void ex_btc8723b2ant_bt_info_notify(struct btc_coexist *btcoexist,
 	}
 
 	if (BT_INFO_SRC_8723B_2ANT_WIFI_FW != rsp_source) {
-		coex_sta->bt_retry_cnt =	/* [3:0]*/
+		coex_sta->bt_retry_cnt =
 			coex_sta->bt_info_c2h[rsp_source][2] & 0xf;
 
+		if (coex_sta->bt_retry_cnt >= 1)
+			coex_sta->pop_event_cnt++;
+
 		coex_sta->bt_rssi =
 			coex_sta->bt_info_c2h[rsp_source][3] * 2 + 10;
 
-		coex_sta->bt_info_ext =
-			coex_sta->bt_info_c2h[rsp_source][4];
+		coex_sta->bt_info_ext = coex_sta->bt_info_c2h[rsp_source][4];
+
+		if (coex_sta->bt_info_c2h[rsp_source][2] & 0x20)
+			coex_sta->c2h_bt_remote_name_req = true;
+		else
+			coex_sta->c2h_bt_remote_name_req = false;
+
+		if (coex_sta->bt_info_c2h[rsp_source][1] == 0x49)
+			coex_sta->a2dp_bit_pool =
+				coex_sta->bt_info_c2h[rsp_source][6];
+		else
+			coex_sta->a2dp_bit_pool = 0;
 
 		/* Here we need to resend some wifi info to BT
-		     because bt is reset and loss of the info.
+		 * because BT is reset and loss of the info.
 		 */
 		if ((coex_sta->bt_info_ext & BIT1)) {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3552,20 +4200,21 @@ void ex_btc8723b2ant_bt_info_notify(struct btc_coexist *btcoexist,
 #endif
 	}
 
-	/* check BIT2 first ==> check if bt is under inquiry or page scan*/
+	/* check BIT2 first ==> check if bt is under inquiry or page scan */
 	if (bt_info & BT_INFO_8723B_2ANT_B_INQ_PAGE)
 		coex_sta->c2h_bt_inquiry_page = true;
 	else
 		coex_sta->c2h_bt_inquiry_page = false;
 
-	/* set link exist status*/
 	if (!(bt_info & BT_INFO_8723B_2ANT_B_CONNECTION)) {
+		/* set link exist status */
 		coex_sta->bt_link_exist = false;
 		coex_sta->pan_exist = false;
 		coex_sta->a2dp_exist = false;
 		coex_sta->hid_exist = false;
 		coex_sta->sco_exist = false;
-	} else { /* connection exists */
+	} else {
+		/* connection exists */
 		coex_sta->bt_link_exist = true;
 		if (bt_info & BT_INFO_8723B_2ANT_B_FTP)
 			coex_sta->pan_exist = true;
@@ -3583,6 +4232,16 @@ void ex_btc8723b2ant_bt_info_notify(struct btc_coexist *btcoexist,
 			coex_sta->sco_exist = true;
 		else
 			coex_sta->sco_exist = false;
+
+		if ((!coex_sta->hid_exist) &&
+		    (!coex_sta->c2h_bt_inquiry_page) &&
+		    (!coex_sta->sco_exist)) {
+			if (coex_sta->high_priority_tx +
+				    coex_sta->high_priority_rx >= 160) {
+				coex_sta->hid_exist = true;
+				bt_info = bt_info | 0x28;
+			}
+		}
 	}
 
 	btc8723b2ant_update_bt_link_info(btcoexist);
@@ -3640,46 +4299,67 @@ void ex_btc8723b2ant_halt_notify(struct btc_coexist *btcoexist)
 	ex_btc8723b2ant_media_status_notify(btcoexist, BTC_MEDIA_DISCONNECT);
 }
 
+void ex_btc8723b2ant_pnp_notify(struct btc_coexist *btcoexist, u8 pnp_state)
+{
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
+
+	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD, "[BTCoex], Pnp notify\n");
+
+	if (pnp_state == BTC_WIFI_PNP_SLEEP) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Pnp notify to SLEEP\n");
+
+		/* Driver do not leave IPS/LPS when driver is going to sleep, so
+		 * BTCoexistence think wifi is still under IPS/LPS
+		 *
+		 * BT should clear UnderIPS/UnderLPS state to avoid mismatch
+		 * state after wakeup.
+		 */
+		coex_sta->under_ips = false;
+		coex_sta->under_lps = false;
+	} else if (pnp_state == BTC_WIFI_PNP_WAKE_UP) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Pnp notify to WAKE UP\n");
+		ex_btc8723b2ant_init_hwconfig(btcoexist);
+		btc8723b2ant_init_coex_dm(btcoexist);
+		btc8723b2ant_query_bt_info(btcoexist);
+	}
+}
+
 void ex_btc8723b2ant_periodical(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	struct btc_board_info *board_info = &btcoexist->board_info;
-	struct btc_stack_info *stack_info = &btcoexist->stack_info;
-	static u8 dis_ver_info_cnt;
-	u32 fw_ver = 0, bt_patch_ver = 0;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], ==========================Periodical===========================\n");
 
-	if (dis_ver_info_cnt <= 5) {
-		dis_ver_info_cnt += 1;
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], ****************************************************************\n");
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Ant PG Num/ Ant Mech/ Ant Pos = %d/ %d/ %d\n",
-			      board_info->pg_ant_num,
-			      board_info->btdm_ant_num,
-			      board_info->btdm_ant_pos);
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BT stack/ hci ext ver = %s / %d\n",
-			      stack_info->profile_notified ? "Yes" : "No",
-			      stack_info->hci_version);
-		btcoexist->btc_get(btcoexist, BTC_GET_U4_BT_PATCH_VER,
-				   &bt_patch_ver);
-		btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_FW_VER, &fw_ver);
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], CoexVer/ fw_ver/ PatchVer = %d_%x/ 0x%x/ 0x%x(%d)\n",
-			      glcoex_ver_date_8723b_2ant, glcoex_ver_8723b_2ant,
-			      fw_ver, bt_patch_ver, bt_patch_ver);
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], ****************************************************************\n");
+	if (coex_sta->dis_ver_info_cnt <= 5) {
+		coex_sta->dis_ver_info_cnt += 1;
+		if (coex_sta->dis_ver_info_cnt == 3) {
+			/* Antenna config to set 0x765 = 0x0 (GNT_BT control by
+			 * PTA) after initial
+			 */
+			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+				 "[BTCoex], Set GNT_BT control by PTA\n");
+			btc8723b2ant_set_ant_path(
+				btcoexist, BTC_ANT_WIFI_AT_MAIN, false, false);
+		}
 	}
 
 #if (BT_AUTO_REPORT_ONLY_8723B_2ANT == 0)
 	btc8723b2ant_query_bt_info(btcoexist);
-	btc8723b2ant_monitor_bt_ctr(btcoexist);
-	btc8723b2ant_monitor_bt_enable_disable(btcoexist);
 #else
+	btc8723b2ant_monitor_bt_ctr(btcoexist);
+	btc8723b2ant_monitor_wifi_ctr(btcoexist);
+
+	/* for some BT speakers that High-Priority pkts appear before
+	 * playing, this will cause HID exist
+	 */
+	if ((coex_sta->high_priority_tx + coex_sta->high_priority_rx < 50) &&
+	    (bt_link_info->hid_exist))
+		bt_link_info->hid_exist = false;
+
 	if (btc8723b2ant_is_wifi_status_changed(btcoexist) ||
 	    coex_dm->auto_tdma_adjust)
 		btc8723b2ant_run_coexist_mechanism(btcoexist);
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.h b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.h
index 567f354caf95..18a35c7faba9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.h
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.h
@@ -41,6 +41,11 @@
 
 #define BTC_RSSI_COEX_THRESH_TOL_8723B_2ANT		2
 
+/* WiFi RSSI Threshold for 2-Ant TDMA/1-Ant PS-TDMA translation */
+#define BT_8723B_2ANT_WIFI_RSSI_COEXSWITCH_THRES	42
+/* BT RSSI Threshold for 2-Ant TDMA/1-Ant PS-TDMA translation */
+#define BT_8723B_2ANT_BT_RSSI_COEXSWITCH_THRES		46
+
 enum BT_INFO_SRC_8723B_2ANT {
 	BT_INFO_SRC_8723B_2ANT_WIFI_FW			= 0x0,
 	BT_INFO_SRC_8723B_2ANT_BT_RSP			= 0x1,
@@ -75,8 +80,8 @@ enum BT_8723B_2ANT_COEX_ALGO {
 
 struct coex_dm_8723b_2ant {
 	/* fw mechanism */
-	bool pre_dec_bt_pwr;
-	bool cur_dec_bt_pwr;
+	bool pre_dec_bt_pwr_lvl;
+	bool cur_dec_bt_pwr_lvl;
 	u8 pre_fw_dac_swing_lvl;
 	u8 cur_fw_dac_swing_lvl;
 	bool cur_ignore_wlan_act;
@@ -84,7 +89,7 @@ struct coex_dm_8723b_2ant {
 	u8 pre_ps_tdma;
 	u8 cur_ps_tdma;
 	u8 ps_tdma_para[5];
-	u8 tdma_adj_type;
+	u8 ps_tdma_du_adj_type;
 	bool reset_tdma_adjust;
 	bool auto_tdma_adjust;
 	bool pre_ps_tdma_on;
@@ -122,8 +127,13 @@ struct coex_dm_8723b_2ant {
 	u8 bt_status;
 	u8 wifi_chnl_info[3];
 
-	bool need_recover_0x948;
-	u16 backup_0x948;
+	u8 pre_lps;
+	u8 cur_lps;
+	u8 pre_rpwm;
+	u8 cur_rpwm;
+
+	bool is_switch_to_1dot5_ant;
+	u8 switch_thres_offset;
 };
 
 struct coex_sta_8723b_2ant {
@@ -132,6 +142,7 @@ struct coex_sta_8723b_2ant {
 	bool a2dp_exist;
 	bool hid_exist;
 	bool pan_exist;
+	bool bt_abnormal_scan;
 
 	bool under_lps;
 	bool under_ips;
@@ -140,14 +151,33 @@ struct coex_sta_8723b_2ant {
 	u32 low_priority_tx;
 	u32 low_priority_rx;
 	u8 bt_rssi;
+	bool bt_tx_rx_mask;
 	u8 pre_bt_rssi_state;
 	u8 pre_wifi_rssi_state[4];
 	bool c2h_bt_info_req_sent;
 	u8 bt_info_c2h[BT_INFO_SRC_8723B_2ANT_MAX][10];
 	u32 bt_info_c2h_cnt[BT_INFO_SRC_8723B_2ANT_MAX];
 	bool c2h_bt_inquiry_page;
+	bool c2h_bt_remote_name_req;
 	u8 bt_retry_cnt;
 	u8 bt_info_ext;
+	u32 pop_event_cnt;
+	u8 scan_ap_num;
+
+	u32 crc_ok_cck;
+	u32 crc_ok_11g;
+	u32 crc_ok_11n;
+	u32 crc_ok_11n_agg;
+
+	u32 crc_err_cck;
+	u32 crc_err_11g;
+	u32 crc_err_11n;
+	u32 crc_err_11n_agg;
+	bool force_lps_on;
+
+	u8 dis_ver_info_cnt;
+
+	u8 a2dp_bit_pool;
 };
 
 /*********************************************************************
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.c
index 8b689ed9a629..5e9f3b0f7a25 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.c
@@ -23,7 +23,7 @@
  *
  *****************************************************************************/
 
-/*============================================================
+/**************************************************************
  * Description:
  *
  * This file is for RTL8821A Co-exist mechanism
@@ -31,21 +31,21 @@
  * History
  * 2012/11/15 Cosa first check in.
  *
- *============================================================
-*/
-/*============================================================
+ **************************************************************/
+
+/**************************************************************
  * include files
- *============================================================
- */
+ **************************************************************/
 #include "halbt_precomp.h"
-/*============================================================
+/**************************************************************
  * Global variables, these are static variables
- *============================================================
- */
+ **************************************************************/
 static struct coex_dm_8821a_1ant glcoex_dm_8821a_1ant;
 static struct coex_dm_8821a_1ant *coex_dm = &glcoex_dm_8821a_1ant;
 static struct coex_sta_8821a_1ant glcoex_sta_8821a_1ant;
 static struct coex_sta_8821a_1ant *coex_sta = &glcoex_sta_8821a_1ant;
+static void btc8821a1ant_act_bt_sco_hid_only_busy(struct btc_coexist *btcoexist,
+						  u8 wifi_status);
 
 static const char *const glbt_info_src_8821a_1ant[] = {
 	  "BT Info[wifi fw]",
@@ -53,22 +53,21 @@ static const char *const glbt_info_src_8821a_1ant[] = {
 	  "BT Info[bt auto report]",
 };
 
-static u32	glcoex_ver_date_8821a_1ant = 20130816;
-static u32	glcoex_ver_8821a_1ant = 0x41;
+static u32 glcoex_ver_date_8821a_1ant = 20130816;
+static u32 glcoex_ver_8821a_1ant = 0x41;
 
-/*============================================================
+/**************************************************************
  * local function proto type if needed
  *
- * local function start with halbtc8821a1ant_
- *============================================================
- */
-static u8 halbtc8821a1ant_bt_rssi_state(struct btc_coexist *btcoexist,
-					u8 level_num, u8 rssi_thresh,
-					u8 rssi_thresh1)
+ * local function start with btc8821a1ant_
+ **************************************************************/
+static u8 btc8821a1ant_bt_rssi_state(struct btc_coexist *btcoexist,
+				     u8 level_num, u8 rssi_thresh,
+				     u8 rssi_thresh1)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	long	bt_rssi = 0;
-	u8	bt_rssi_state = coex_sta->pre_bt_rssi_state;
+	long bt_rssi = 0;
+	u8 bt_rssi_state = coex_sta->pre_bt_rssi_state;
 
 	bt_rssi = coex_sta->bt_rssi;
 
@@ -150,9 +149,9 @@ static u8 halbtc8821a1ant_bt_rssi_state(struct btc_coexist *btcoexist,
 	return bt_rssi_state;
 }
 
-static u8 halbtc8821a1ant_WifiRssiState(struct btc_coexist *btcoexist,
-					u8 index, u8 level_num, u8 rssi_thresh,
-					u8 rssi_thresh1)
+static u8 btc8821a1ant_wifi_rssi_state(struct btc_coexist *btcoexist,
+				       u8 index, u8 level_num, u8 rssi_thresh,
+				       u8 rssi_thresh1)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	long	wifi_rssi = 0;
@@ -165,8 +164,8 @@ static u8 halbtc8821a1ant_WifiRssiState(struct btc_coexist *btcoexist,
 		     BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_wifi_rssi_state[index] ==
 		     BTC_RSSI_STATE_STAY_LOW)) {
-			if (wifi_rssi >=
-			    (rssi_thresh+BTC_RSSI_COEX_THRESH_TOL_8821A_1ANT)) {
+			if (wifi_rssi >= (rssi_thresh +
+					BTC_RSSI_COEX_THRESH_TOL_8821A_1ANT)) {
 				wifi_rssi_state = BTC_RSSI_STATE_HIGH;
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], wifi RSSI state switch to High\n");
@@ -197,8 +196,8 @@ static u8 halbtc8821a1ant_WifiRssiState(struct btc_coexist *btcoexist,
 		     BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_wifi_rssi_state[index] ==
 		     BTC_RSSI_STATE_STAY_LOW)) {
-			if (wifi_rssi >=
-			    (rssi_thresh+BTC_RSSI_COEX_THRESH_TOL_8821A_1ANT)) {
+			if (wifi_rssi >= (rssi_thresh +
+					BTC_RSSI_COEX_THRESH_TOL_8821A_1ANT)) {
 				wifi_rssi_state = BTC_RSSI_STATE_MEDIUM;
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], wifi RSSI state switch to Medium\n");
@@ -211,9 +210,8 @@ static u8 halbtc8821a1ant_WifiRssiState(struct btc_coexist *btcoexist,
 			BTC_RSSI_STATE_MEDIUM) ||
 			(coex_sta->pre_wifi_rssi_state[index] ==
 			BTC_RSSI_STATE_STAY_MEDIUM)) {
-			if (wifi_rssi >=
-			    (rssi_thresh1 +
-			     BTC_RSSI_COEX_THRESH_TOL_8821A_1ANT)) {
+			if (wifi_rssi >= (rssi_thresh1 +
+					BTC_RSSI_COEX_THRESH_TOL_8821A_1ANT)) {
 				wifi_rssi_state = BTC_RSSI_STATE_HIGH;
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], wifi RSSI state switch to High\n");
@@ -243,14 +241,14 @@ static u8 halbtc8821a1ant_WifiRssiState(struct btc_coexist *btcoexist,
 	return wifi_rssi_state;
 }
 
-static void halbtc8821a1ant_update_ra_mask(struct btc_coexist *btcoexist,
-					   bool force_exec, u32 dis_rate_mask)
+static void btc8821a1ant_update_ra_mask(struct btc_coexist *btcoexist,
+					bool force_exec, u32 dis_rate_mask)
 {
 	coex_dm->cur_ra_mask = dis_rate_mask;
 
 	if (force_exec ||
 	    (coex_dm->pre_ra_mask != coex_dm->cur_ra_mask)) {
-		btcoexist->btc_set(btcoexist, BTC_SET_ACT_UPDATE_ra_mask,
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_UPDATE_RAMASK,
 				   &coex_dm->cur_ra_mask);
 	}
 	coex_dm->pre_ra_mask = coex_dm->cur_ra_mask;
@@ -259,14 +257,14 @@ static void halbtc8821a1ant_update_ra_mask(struct btc_coexist *btcoexist,
 static void btc8821a1ant_auto_rate_fb_retry(struct btc_coexist *btcoexist,
 					    bool force_exec, u8 type)
 {
-	bool	wifi_under_b_mode = false;
+	bool wifi_under_b_mode = false;
 
 	coex_dm->cur_arfr_type = type;
 
 	if (force_exec ||
 	    (coex_dm->pre_arfr_type != coex_dm->cur_arfr_type)) {
 		switch (coex_dm->cur_arfr_type) {
-		case 0:	/* normal mode*/
+		case 0:	/* normal mode */
 			btcoexist->btc_write_4byte(btcoexist, 0x430,
 						   coex_dm->backup_arfr_cnt1);
 			btcoexist->btc_write_4byte(btcoexist, 0x434,
@@ -296,19 +294,19 @@ static void btc8821a1ant_auto_rate_fb_retry(struct btc_coexist *btcoexist,
 	coex_dm->pre_arfr_type = coex_dm->cur_arfr_type;
 }
 
-static void halbtc8821a1ant_retry_limit(struct btc_coexist *btcoexist,
-					bool force_exec, u8 type)
+static void btc8821a1ant_retry_limit(struct btc_coexist *btcoexist,
+				     bool force_exec, u8 type)
 {
 	coex_dm->cur_retry_limit_type = type;
 
 	if (force_exec ||
 	    (coex_dm->pre_retry_limit_type != coex_dm->cur_retry_limit_type)) {
 		switch (coex_dm->cur_retry_limit_type) {
-		case 0:	/* normal mode*/
+		case 0:	/* normal mode */
 			btcoexist->btc_write_2byte(btcoexist, 0x42a,
 						   coex_dm->backup_retry_limit);
 			break;
-		case 1:	/* retry limit = 8*/
+		case 1:	/* retry limit = 8 */
 			btcoexist->btc_write_2byte(btcoexist, 0x42a, 0x0808);
 			break;
 		default:
@@ -318,19 +316,19 @@ static void halbtc8821a1ant_retry_limit(struct btc_coexist *btcoexist,
 	coex_dm->pre_retry_limit_type = coex_dm->cur_retry_limit_type;
 }
 
-static void halbtc8821a1ant_ampdu_max_time(struct btc_coexist *btcoexist,
-					   bool force_exec, u8 type)
+static void btc8821a1ant_ampdu_max_time(struct btc_coexist *btcoexist,
+					bool force_exec, u8 type)
 {
 	coex_dm->cur_ampdu_time_type = type;
 
 	if (force_exec ||
 	    (coex_dm->pre_ampdu_time_type != coex_dm->cur_ampdu_time_type)) {
 		switch (coex_dm->cur_ampdu_time_type) {
-		case 0:	/* normal mode*/
+		case 0:	/* normal mode */
 			btcoexist->btc_write_1byte(btcoexist, 0x456,
 						   coex_dm->backup_ampdu_max_time);
 			break;
-		case 1:	/* AMPDU timw = 0x38 * 32us*/
+		case 1:	/* AMPDU time = 0x38 * 32us */
 			btcoexist->btc_write_1byte(btcoexist, 0x456, 0x38);
 			break;
 		default:
@@ -341,88 +339,85 @@ static void halbtc8821a1ant_ampdu_max_time(struct btc_coexist *btcoexist,
 	coex_dm->pre_ampdu_time_type = coex_dm->cur_ampdu_time_type;
 }
 
-static void halbtc8821a1ant_limited_tx(struct btc_coexist *btcoexist,
-				       bool force_exec, u8 ra_mask_type,
-				       u8 arfr_type, u8 retry_limit_type,
-				       u8 ampdu_time_type)
+static void btc8821a1ant_limited_tx(struct btc_coexist *btcoexist,
+				    bool force_exec, u8 ra_mask_type,
+				    u8 arfr_type, u8 retry_limit_type,
+				    u8 ampdu_time_type)
 {
 	switch (ra_mask_type) {
-	case 0:	/* normal mode*/
-		halbtc8821a1ant_update_ra_mask(btcoexist, force_exec, 0x0);
+	case 0:	/* normal mode */
+		btc8821a1ant_update_ra_mask(btcoexist, force_exec, 0x0);
 		break;
-	case 1:	/* disable cck 1/2*/
-		halbtc8821a1ant_update_ra_mask(btcoexist, force_exec,
-					       0x00000003);
+	case 1:	/* disable cck 1/2 */
+		btc8821a1ant_update_ra_mask(btcoexist, force_exec,
+					    0x00000003);
 		break;
-	case 2:	/* disable cck 1/2/5.5, ofdm 6/9/12/18/24, mcs 0/1/2/3/4*/
-		halbtc8821a1ant_update_ra_mask(btcoexist, force_exec,
-					       0x0001f1f7);
+	case 2:	/* disable cck 1/2/5.5, ofdm 6/9/12/18/24, mcs 0/1/2/3/4 */
+		btc8821a1ant_update_ra_mask(btcoexist, force_exec,
+					    0x0001f1f7);
 		break;
 	default:
 		break;
 	}
 
 	btc8821a1ant_auto_rate_fb_retry(btcoexist, force_exec, arfr_type);
-	halbtc8821a1ant_retry_limit(btcoexist, force_exec, retry_limit_type);
-	halbtc8821a1ant_ampdu_max_time(btcoexist, force_exec, ampdu_time_type);
+	btc8821a1ant_retry_limit(btcoexist, force_exec, retry_limit_type);
+	btc8821a1ant_ampdu_max_time(btcoexist, force_exec, ampdu_time_type);
 }
 
-static void halbtc8821a1ant_limited_rx(struct btc_coexist *btcoexist,
-				       bool force_exec, bool rej_ap_agg_pkt,
-				       bool bt_ctrl_agg_buf_size,
-				       u8 agg_buf_size)
+static void btc8821a1ant_limited_rx(struct btc_coexist *btcoexist,
+				    bool force_exec, bool rej_ap_agg_pkt,
+				    bool bt_ctrl_agg_buf_size, u8 agg_buf_size)
 {
 	bool reject_rx_agg = rej_ap_agg_pkt;
 	bool bt_ctrl_rx_agg_size = bt_ctrl_agg_buf_size;
 	u8 rx_agg_size = agg_buf_size;
 
-	/*============================================*/
-	/*	Rx Aggregation related setting*/
-	/*============================================*/
+	/* Rx Aggregation related setting */
 	btcoexist->btc_set(btcoexist,
 		 BTC_SET_BL_TO_REJ_AP_AGG_PKT, &reject_rx_agg);
-	/* decide BT control aggregation buf size or not*/
+	/* decide BT control aggregation buf size or not */
 	btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_CTRL_AGG_SIZE,
 			   &bt_ctrl_rx_agg_size);
-	/* aggregation buf size, only work when BT control Rx agg size.*/
+	/* aggregation buf size, only work when BT control Rx agg size */
 	btcoexist->btc_set(btcoexist, BTC_SET_U1_AGG_BUF_SIZE, &rx_agg_size);
-	/* real update aggregation setting*/
+	/* real update aggregation setting */
 	btcoexist->btc_set(btcoexist, BTC_SET_ACT_AGGREGATE_CTRL, NULL);
 }
 
-static void halbtc8821a1ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
+static void btc8821a1ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 {
-	u32	reg_hp_tx_rx, reg_lp_tx_rx, u4_tmp;
-	u32	reg_hp_tx = 0, reg_hp_rx = 0, reg_lp_tx = 0, reg_lp_rx = 0;
+	u32 reg_hp_tx_rx, reg_lp_tx_rx, u4_tmp;
+	u32 reg_hp_tx = 0, reg_hp_rx = 0, reg_lp_tx = 0, reg_lp_rx = 0;
 
 	reg_hp_tx_rx = 0x770;
 	reg_lp_tx_rx = 0x774;
 
 	u4_tmp = btcoexist->btc_read_4byte(btcoexist, reg_hp_tx_rx);
 	reg_hp_tx = u4_tmp & MASKLWORD;
-	reg_hp_rx = (u4_tmp & MASKHWORD)>>16;
+	reg_hp_rx = (u4_tmp & MASKHWORD) >> 16;
 
 	u4_tmp = btcoexist->btc_read_4byte(btcoexist, reg_lp_tx_rx);
 	reg_lp_tx = u4_tmp & MASKLWORD;
-	reg_lp_rx = (u4_tmp & MASKHWORD)>>16;
+	reg_lp_rx = (u4_tmp & MASKHWORD) >> 16;
 
 	coex_sta->high_priority_tx = reg_hp_tx;
 	coex_sta->high_priority_rx = reg_hp_rx;
 	coex_sta->low_priority_tx = reg_lp_tx;
 	coex_sta->low_priority_rx = reg_lp_rx;
 
-	/* reset counter*/
+	/* reset counter */
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
 }
 
-static void halbtc8821a1ant_query_bt_info(struct btc_coexist *btcoexist)
+static void btc8821a1ant_query_bt_info(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
 	coex_sta->c2h_bt_info_req_sent = true;
 
-	h2c_parameter[0] |= BIT0;	/* trigger*/
+	h2c_parameter[0] |= BIT0; /* trigger */
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Query Bt Info, FW write 0x61 = 0x%x\n",
@@ -431,10 +426,43 @@ static void halbtc8821a1ant_query_bt_info(struct btc_coexist *btcoexist)
 	btcoexist->btc_fill_h2c(btcoexist, 0x61, 1, h2c_parameter);
 }
 
-static void halbtc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
+bool btc8821a1ant_is_wifi_status_changed(struct btc_coexist *btcoexist)
+{
+	static bool pre_wifi_busy = true;
+	static bool pre_under_4way = true;
+	static bool pre_bt_hs_on = true;
+	bool wifi_busy = false, under_4way = false, bt_hs_on = false;
+	bool wifi_connected = false;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
+			   &wifi_connected);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_4_WAY_PROGRESS,
+			   &under_4way);
+
+	if (wifi_connected) {
+		if (wifi_busy != pre_wifi_busy) {
+			pre_wifi_busy = wifi_busy;
+			return true;
+		}
+		if (under_4way != pre_under_4way) {
+			pre_under_4way = under_4way;
+			return true;
+		}
+		if (bt_hs_on != pre_bt_hs_on) {
+			pre_bt_hs_on = bt_hs_on;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static void btc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 {
 	struct btc_bt_link_info	*bt_link_info = &btcoexist->bt_link_info;
-	bool	bt_hs_on = false;
+	bool bt_hs_on = false;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
@@ -444,13 +472,13 @@ static void halbtc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 	bt_link_info->pan_exist = coex_sta->pan_exist;
 	bt_link_info->hid_exist = coex_sta->hid_exist;
 
-	/* work around for HS mode.*/
+	/* work around for HS mode */
 	if (bt_hs_on) {
 		bt_link_info->pan_exist = true;
 		bt_link_info->bt_link_exist = true;
 	}
 
-	/* check if Sco only*/
+	/* check if Sco only */
 	if (bt_link_info->sco_exist &&
 	    !bt_link_info->a2dp_exist &&
 	    !bt_link_info->pan_exist &&
@@ -459,7 +487,7 @@ static void halbtc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 	else
 		bt_link_info->sco_only = false;
 
-	/* check if A2dp only*/
+	/* check if A2dp only */
 	if (!bt_link_info->sco_exist &&
 	    bt_link_info->a2dp_exist &&
 	    !bt_link_info->pan_exist &&
@@ -468,7 +496,7 @@ static void halbtc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 	else
 		bt_link_info->a2dp_only = false;
 
-	/* check if Pan only*/
+	/* check if Pan only */
 	if (!bt_link_info->sco_exist &&
 	    !bt_link_info->a2dp_exist &&
 	    bt_link_info->pan_exist &&
@@ -477,7 +505,7 @@ static void halbtc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 	else
 		bt_link_info->pan_only = false;
 
-	/* check if Hid only*/
+	/* check if Hid only */
 	if (!bt_link_info->sco_exist &&
 	    !bt_link_info->a2dp_exist &&
 	    !bt_link_info->pan_exist &&
@@ -487,13 +515,13 @@ static void halbtc8821a1ant_update_bt_link_info(struct btc_coexist *btcoexist)
 		bt_link_info->hid_only = false;
 }
 
-static u8 halbtc8821a1ant_action_algorithm(struct btc_coexist *btcoexist)
+static u8 btc8821a1ant_action_algorithm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
-	bool	bt_hs_on = false;
-	u8	algorithm = BT_8821A_1ANT_COEX_ALGO_UNDEFINED;
-	u8	num_of_diff_profile = 0;
+	bool bt_hs_on = false;
+	u8 algorithm = BT_8821A_1ANT_COEX_ALGO_UNDEFINED;
+	u8 num_of_diff_profile = 0;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
@@ -605,7 +633,7 @@ static u8 halbtc8821a1ant_action_algorithm(struct btc_coexist *btcoexist)
 					 "[BTCoex], BT Profile = SCO + HID + A2DP ==> HID\n");
 				algorithm = BT_8821A_1ANT_COEX_ALGO_HID;
 			} else if (bt_link_info->hid_exist &&
-				bt_link_info->pan_exist) {
+				   bt_link_info->pan_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
@@ -618,7 +646,7 @@ static u8 halbtc8821a1ant_action_algorithm(struct btc_coexist *btcoexist)
 					algorithm = BT_8821A_1ANT_COEX_ALGO_PANEDR_HID;
 				}
 			} else if (bt_link_info->pan_exist &&
-				bt_link_info->a2dp_exist) {
+				   bt_link_info->a2dp_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
@@ -670,53 +698,8 @@ static u8 halbtc8821a1ant_action_algorithm(struct btc_coexist *btcoexist)
 	return algorithm;
 }
 
-static void halbtc8821a1ant_set_bt_auto_report(struct btc_coexist *btcoexist,
-					       bool enable_auto_report)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 h2c_parameter[1] = {0};
-
-	h2c_parameter[0] = 0;
-
-	if (enable_auto_report)
-		h2c_parameter[0] |= BIT0;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], BT FW auto report : %s, FW write 0x68 = 0x%x\n",
-		 (enable_auto_report ? "Enabled!!" : "Disabled!!"),
-		 h2c_parameter[0]);
-
-	btcoexist->btc_fill_h2c(btcoexist, 0x68, 1, h2c_parameter);
-}
-
-static void halbtc8821a1ant_bt_auto_report(struct btc_coexist *btcoexist,
-					   bool force_exec,
-					   bool enable_auto_report)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s BT Auto report = %s\n",
-		 (force_exec ? "force to" : ""), ((enable_auto_report) ?
-						     "Enabled" : "Disabled"));
-	coex_dm->cur_bt_auto_report = enable_auto_report;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_bt_auto_report = %d, cur_bt_auto_report = %d\n",
-			    coex_dm->pre_bt_auto_report,
-			    coex_dm->cur_bt_auto_report);
-
-		if (coex_dm->pre_bt_auto_report == coex_dm->cur_bt_auto_report)
-			return;
-	}
-	halbtc8821a1ant_set_bt_auto_report(btcoexist, coex_dm->cur_bt_auto_report);
-
-	coex_dm->pre_bt_auto_report = coex_dm->cur_bt_auto_report;
-}
-
-static void btc8821a1ant_set_sw_pen_tx_rate(struct btc_coexist *btcoexist,
-					    bool low_penalty_ra)
+static void btc8821a1ant_set_sw_penalty_tx_rate(struct btc_coexist *btcoexist,
+						bool low_penalty_ra)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[6] = {0};
@@ -725,11 +708,11 @@ static void btc8821a1ant_set_sw_pen_tx_rate(struct btc_coexist *btcoexist,
 
 	if (low_penalty_ra) {
 		h2c_parameter[1] |= BIT0;
-		/*normal rate except MCS7/6/5, OFDM54/48/36*/
+		/* normal rate except MCS7/6/5, OFDM54/48/36 */
 		h2c_parameter[2] = 0x00;
-		h2c_parameter[3] = 0xf7;  /*MCS7 or OFDM54*/
-		h2c_parameter[4] = 0xf8;  /*MCS6 or OFDM48*/
-		h2c_parameter[5] = 0xf9;	/*MCS5 or OFDM36*/
+		h2c_parameter[3] = 0xf7; /* MCS7 or OFDM54 */
+		h2c_parameter[4] = 0xf8; /* MCS6 or OFDM48 */
+		h2c_parameter[5] = 0xf9; /* MCS5 or OFDM36 */
 	}
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -739,8 +722,8 @@ static void btc8821a1ant_set_sw_pen_tx_rate(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x69, 6, h2c_parameter);
 }
 
-static void halbtc8821a1ant_low_penalty_ra(struct btc_coexist *btcoexist,
-					   bool force_exec, bool low_penalty_ra)
+static void btc8821a1ant_low_penalty_ra(struct btc_coexist *btcoexist,
+					bool force_exec, bool low_penalty_ra)
 {
 	coex_dm->cur_low_penalty_ra = low_penalty_ra;
 
@@ -748,14 +731,15 @@ static void halbtc8821a1ant_low_penalty_ra(struct btc_coexist *btcoexist,
 		if (coex_dm->pre_low_penalty_ra == coex_dm->cur_low_penalty_ra)
 			return;
 	}
-	btc8821a1ant_set_sw_pen_tx_rate(btcoexist, coex_dm->cur_low_penalty_ra);
+	btc8821a1ant_set_sw_penalty_tx_rate(btcoexist,
+					    coex_dm->cur_low_penalty_ra);
 
 	coex_dm->pre_low_penalty_ra = coex_dm->cur_low_penalty_ra;
 }
 
-static void halbtc8821a1ant_set_coex_table(struct btc_coexist *btcoexist,
-					   u32 val0x6c0, u32 val0x6c4,
-					   u32 val0x6c8, u8 val0x6cc)
+static void btc8821a1ant_set_coex_table(struct btc_coexist *btcoexist,
+					u32 val0x6c0, u32 val0x6c4,
+					u32 val0x6c8, u8 val0x6cc)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -776,9 +760,9 @@ static void halbtc8821a1ant_set_coex_table(struct btc_coexist *btcoexist,
 	btcoexist->btc_write_1byte(btcoexist, 0x6cc, val0x6cc);
 }
 
-static void halbtc8821a1ant_coex_table(struct btc_coexist *btcoexist,
-				       bool force_exec, u32 val0x6c0,
-				       u32 val0x6c4, u32 val0x6c8, u8 val0x6cc)
+static void btc8821a1ant_coex_table(struct btc_coexist *btcoexist,
+				    bool force_exec, u32 val0x6c0, u32 val0x6c4,
+				    u32 val0x6c8, u8 val0x6cc)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -798,8 +782,8 @@ static void halbtc8821a1ant_coex_table(struct btc_coexist *btcoexist,
 		    (coex_dm->pre_val_0x6cc == coex_dm->cur_val_0x6cc))
 			return;
 	}
-	halbtc8821a1ant_set_coex_table(btcoexist, val0x6c0, val0x6c4,
-				       val0x6c8, val0x6cc);
+	btc8821a1ant_set_coex_table(btcoexist, val0x6c0, val0x6c4,
+				    val0x6c8, val0x6cc);
 
 	coex_dm->pre_val_0x6c0 = coex_dm->cur_val_0x6c0;
 	coex_dm->pre_val_0x6c4 = coex_dm->cur_val_0x6c4;
@@ -807,42 +791,41 @@ static void halbtc8821a1ant_coex_table(struct btc_coexist *btcoexist,
 	coex_dm->pre_val_0x6cc = coex_dm->cur_val_0x6cc;
 }
 
-static void halbtc8821a1ant_coex_table_with_type(struct btc_coexist *btcoexist,
-						 bool force_exec, u8 type)
+static void btc8821a1ant_coex_table_with_type(struct btc_coexist *btcoexist,
+					      bool force_exec, u8 type)
 {
 	switch (type) {
 	case 0:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0x55555555,
-					   0x55555555, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x55555555, 0xffffff, 0x3);
 		break;
 	case 1:
-			halbtc8821a1ant_coex_table(btcoexist, force_exec,
-						   0x55555555, 0x5a5a5a5a,
-						   0xffffff, 0x3);
-			break;
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x5a5a5a5a, 0xffffff, 0x3);
+		break;
 	case 2:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
-					   0x5a5a5a5a, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
+					0x5a5a5a5a, 0xffffff, 0x3);
 		break;
 	case 3:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0x55555555,
-					   0xaaaaaaaa, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
+					0xaaaaaaaa, 0xffffff, 0x3);
 		break;
 	case 4:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0xffffffff,
-					   0xffffffff, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x5a5a5a5a, 0xffffff, 0x3);
 		break;
 	case 5:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
-					   0x5fff5fff, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x5a5a5a5a,
+					0xaaaa5a5a, 0xffffff, 0x3);
 		break;
 	case 6:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
-					   0x5a5a5a5a, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0xaaaa5a5a, 0xffffff, 0x3);
 		break;
 	case 7:
-		halbtc8821a1ant_coex_table(btcoexist, force_exec, 0x5afa5afa,
-					   0x5afa5afa, 0xffffff, 0x3);
+		btc8821a1ant_coex_table(btcoexist, force_exec, 0xaaaaaaaa,
+					0xaaaaaaaa, 0xffffff, 0x3);
 		break;
 	default:
 		break;
@@ -853,10 +836,10 @@ static void btc8821a1ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoexist,
 						bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8	h2c_parameter[1] = {0};
+	u8 h2c_parameter[1] = {0};
 
 	if (enable)
-		h2c_parameter[0] |= BIT0;	/* function enable*/
+		h2c_parameter[0] |= BIT0; /* function enable */
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], set FW for BT Ignore Wlan_Act, FW write 0x63 = 0x%x\n",
@@ -865,8 +848,8 @@ static void btc8821a1ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x63, 1, h2c_parameter);
 }
 
-static void halbtc8821a1ant_ignore_wlan_act(struct btc_coexist *btcoexist,
-					    bool force_exec, bool enable)
+static void btc8821a1ant_ignore_wlan_act(struct btc_coexist *btcoexist,
+					 bool force_exec, bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -890,24 +873,40 @@ static void halbtc8821a1ant_ignore_wlan_act(struct btc_coexist *btcoexist,
 	coex_dm->pre_ignore_wlan_act = coex_dm->cur_ignore_wlan_act;
 }
 
-static void halbtc8821a1ant_set_fw_pstdma(struct btc_coexist *btcoexist,
-					  u8 byte1, u8 byte2, u8 byte3,
-					  u8 byte4, u8 byte5)
+static void btc8821a1ant_set_fw_ps_tdma(struct btc_coexist *btcoexist, u8 byte1,
+					u8 byte2, u8 byte3, u8 byte4, u8 byte5)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[5] = {0};
+	u8 real_byte1 = byte1, real_byte5 = byte5;
+	bool ap_enable = false;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_AP_MODE_ENABLE,
+			   &ap_enable);
+
+	if (ap_enable) {
+		if (byte1 & BIT4 && !(byte1 & BIT5)) {
+			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+				 "[BTCoex], FW for 1Ant AP mode\n");
+			real_byte1 &= ~BIT4;
+			real_byte1 |= BIT5;
+
+			real_byte5 |= BIT5;
+			real_byte5 &= ~BIT6;
+		}
+	}
 
-	h2c_parameter[0] = byte1;
+	h2c_parameter[0] = real_byte1;
 	h2c_parameter[1] = byte2;
 	h2c_parameter[2] = byte3;
 	h2c_parameter[3] = byte4;
-	h2c_parameter[4] = byte5;
+	h2c_parameter[4] = real_byte5;
 
-	coex_dm->ps_tdma_para[0] = byte1;
+	coex_dm->ps_tdma_para[0] = real_byte1;
 	coex_dm->ps_tdma_para[1] = byte2;
 	coex_dm->ps_tdma_para[2] = byte3;
 	coex_dm->ps_tdma_para[3] = byte4;
-	coex_dm->ps_tdma_para[4] = byte5;
+	coex_dm->ps_tdma_para[4] = real_byte5;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], PS-TDMA H2C cmd =0x%x%08x\n",
@@ -919,18 +918,18 @@ static void halbtc8821a1ant_set_fw_pstdma(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x60, 5, h2c_parameter);
 }
 
-static void halbtc8821a1ant_set_lps_rpwm(struct btc_coexist *btcoexist,
-					 u8 lps_val, u8 rpwm_val)
+static void btc8821a1ant_set_lps_rpwm(struct btc_coexist *btcoexist,
+				      u8 lps_val, u8 rpwm_val)
 {
-	u8	lps = lps_val;
-	u8	rpwm = rpwm_val;
+	u8 lps = lps_val;
+	u8 rpwm = rpwm_val;
 
 	btcoexist->btc_set(btcoexist, BTC_SET_U1_LPS_VAL, &lps);
 	btcoexist->btc_set(btcoexist, BTC_SET_U1_RPWM_VAL, &rpwm);
 }
 
-static void halbtc8821a1ant_lps_rpwm(struct btc_coexist *btcoexist,
-				     bool force_exec, u8 lps_val, u8 rpwm_val)
+static void btc8821a1ant_lps_rpwm(struct btc_coexist *btcoexist,
+				  bool force_exec, u8 lps_val, u8 rpwm_val)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -954,33 +953,33 @@ static void halbtc8821a1ant_lps_rpwm(struct btc_coexist *btcoexist,
 			return;
 		}
 	}
-	halbtc8821a1ant_set_lps_rpwm(btcoexist, lps_val, rpwm_val);
+	btc8821a1ant_set_lps_rpwm(btcoexist, lps_val, rpwm_val);
 
 	coex_dm->pre_lps = coex_dm->cur_lps;
 	coex_dm->pre_rpwm = coex_dm->cur_rpwm;
 }
 
-static void halbtc8821a1ant_sw_mechanism(struct btc_coexist *btcoexist,
-					 bool low_penalty_ra)
+static void btc8821a1ant_sw_mechanism(struct btc_coexist *btcoexist,
+				      bool low_penalty_ra)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], SM[LpRA] = %d\n", low_penalty_ra);
 
-	halbtc8821a1ant_low_penalty_ra(btcoexist, NORMAL_EXEC, low_penalty_ra);
+	btc8821a1ant_low_penalty_ra(btcoexist, NORMAL_EXEC, low_penalty_ra);
 }
 
-static void halbtc8821a1ant_set_ant_path(struct btc_coexist *btcoexist,
-					 u8 ant_pos_type, bool init_hw_cfg,
-					 bool wifi_off)
+static void btc8821a1ant_set_ant_path(struct btc_coexist *btcoexist,
+				      u8 ant_pos_type, bool init_hw_cfg,
+				      bool wifi_off)
 {
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	u32 u4_tmp = 0;
 	u8 h2c_parameter[2] = {0};
 
 	if (init_hw_cfg) {
-		/* 0x4c[23] = 0, 0x4c[24] = 1  Antenna control by WL/BT*/
+		/* 0x4c[23] = 0, 0x4c[24] = 1  Antenna control by WL/BT */
 		u4_tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
 		u4_tmp &= ~BIT23;
 		u4_tmp |= BIT24;
@@ -990,41 +989,42 @@ static void halbtc8821a1ant_set_ant_path(struct btc_coexist *btcoexist,
 		btcoexist->btc_write_1byte(btcoexist, 0xcb4, 0x77);
 
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT) {
-			/*tell firmware "antenna inverse"  ==>
-			 * WRONG firmware antenna control code.==>need fw to fix
+			/* tell firmware "antenna inverse"
+			 * WRONG firmware antenna control code, need fw to fix
 			 */
 			h2c_parameter[0] = 1;
 			h2c_parameter[1] = 1;
 			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 						h2c_parameter);
-			/*Main Ant to  BT for IPS case 0x4c[23] = 1*/
-			btcoexist->btc_write_1byte_bitmask(btcoexist, 0x64,
-							   0x1, 0x1);
 		} else {
-			/*tell firmware "no antenna inverse" ==>
-			 * WRONG firmware antenna control code.==>need fw to fix
+			/* tell firmware "no antenna inverse"
+			 * WRONG firmware antenna control code, need fw to fix
 			 */
 			h2c_parameter[0] = 0;
 			h2c_parameter[1] = 1;
 			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 						h2c_parameter);
-			/*Aux Ant to  BT for IPS case 0x4c[23] = 1*/
-			btcoexist->btc_write_1byte_bitmask(btcoexist, 0x64,
-							   0x1, 0x0);
 		}
 	} else if (wifi_off) {
 		/* 0x4c[24:23] = 00, Set Antenna control
-		 *	by BT_RFE_CTRL	BT Vendor 0xac = 0xf002
+		 * by BT_RFE_CTRL BT Vendor 0xac = 0xf002
 		 */
 		u4_tmp = btcoexist->btc_read_4byte(btcoexist, 0x4c);
 		u4_tmp &= ~BIT23;
 		u4_tmp &= ~BIT24;
 		btcoexist->btc_write_4byte(btcoexist, 0x4c, u4_tmp);
+
+		/* 0x765 = 0x18 */
+		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x765, 0x18, 0x3);
+	} else {
+		/* 0x765 = 0x0 */
+		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x765, 0x18, 0x0);
 	}
 
-	/* ext switch setting*/
+	/* ext switch setting */
 	switch (ant_pos_type) {
 	case BTC_ANT_PATH_WIFI:
+		btcoexist->btc_write_1byte(btcoexist, 0xcb4, 0x77);
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT)
 			btcoexist->btc_write_1byte_bitmask(btcoexist, 0xcb7,
 							   0x30, 0x1);
@@ -1033,6 +1033,7 @@ static void halbtc8821a1ant_set_ant_path(struct btc_coexist *btcoexist,
 							   0x30, 0x2);
 		break;
 	case BTC_ANT_PATH_BT:
+		btcoexist->btc_write_1byte(btcoexist, 0xcb4, 0x77);
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT)
 			btcoexist->btc_write_1byte_bitmask(btcoexist, 0xcb7,
 							   0x30, 0x2);
@@ -1042,6 +1043,7 @@ static void halbtc8821a1ant_set_ant_path(struct btc_coexist *btcoexist,
 		break;
 	default:
 	case BTC_ANT_PATH_PTA:
+		btcoexist->btc_write_1byte(btcoexist, 0xcb4, 0x66);
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT)
 			btcoexist->btc_write_1byte_bitmask(btcoexist, 0xcb7,
 							   0x30, 0x1);
@@ -1052,8 +1054,8 @@ static void halbtc8821a1ant_set_ant_path(struct btc_coexist *btcoexist,
 	}
 }
 
-static void halbtc8821a1ant_ps_tdma(struct btc_coexist *btcoexist,
-				    bool force_exec, bool turn_on, u8 type)
+static void btc8821a1ant_ps_tdma(struct btc_coexist *btcoexist,
+				 bool force_exec, bool turn_on, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 rssi_adjust_val = 0;
@@ -1078,185 +1080,189 @@ static void halbtc8821a1ant_ps_tdma(struct btc_coexist *btcoexist,
 	if (turn_on) {
 		switch (type) {
 		default:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x1a,
-						      0x1a, 0x0, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x1a,
+						    0x1a, 0x0, 0x50);
 			break;
 		case 1:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x3a,
-						      0x03, 0x10, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x3a,
+						    0x03, 0x10, 0x50);
 			rssi_adjust_val = 11;
 			break;
 		case 2:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x2b,
-						      0x03, 0x10, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x2b,
+						    0x03, 0x10, 0x50);
 			rssi_adjust_val = 14;
 			break;
 		case 3:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x1d,
-						      0x1d, 0x0, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x1d,
+						    0x1d, 0x0, 0x10);
 			break;
 		case 4:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x93, 0x15,
-						      0x3, 0x14, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x93, 0x15,
+						    0x3, 0x14, 0x0);
 			rssi_adjust_val = 17;
 			break;
 		case 5:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x61, 0x15,
-						      0x3, 0x11, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x61, 0x15,
+						    0x3, 0x11, 0x10);
 			break;
 		case 6:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x13, 0xa,
-						      0x3, 0x0, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x13, 0xa,
+						    0x3, 0x0, 0x0);
 			break;
 		case 7:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x13, 0xc,
-						      0x5, 0x0, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x13, 0xc,
+						    0x5, 0x0, 0x0);
 			break;
 		case 8:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x93, 0x25,
-						      0x3, 0x10, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x93, 0x25,
+						    0x3, 0x10, 0x0);
 			break;
 		case 9:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x21,
-						      0x3, 0x10, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x21,
+						    0x3, 0x10, 0x50);
 			rssi_adjust_val = 18;
 			break;
 		case 10:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x13, 0xa,
-						      0xa, 0x0, 0x40);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x13, 0xa,
+						    0xa, 0x0, 0x40);
 			break;
 		case 11:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x14,
-						      0x03, 0x10, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x14,
+						    0x03, 0x10, 0x10);
 			rssi_adjust_val = 20;
 			break;
 		case 12:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x0a,
-						      0x0a, 0x0, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x0a,
+						    0x0a, 0x0, 0x50);
 			break;
 		case 13:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x18,
-						      0x18, 0x0, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x18,
+						    0x18, 0x0, 0x10);
 			break;
 		case 14:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x21,
-						      0x3, 0x10, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x1e,
+						    0x3, 0x10, 0x14);
 			break;
 		case 15:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x13, 0xa,
-						      0x3, 0x8, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x13, 0xa,
+						    0x3, 0x8, 0x0);
 			break;
 		case 16:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x93, 0x15,
-						      0x3, 0x10, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x93, 0x15,
+						    0x3, 0x10, 0x0);
 			rssi_adjust_val = 18;
 			break;
 		case 18:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x93, 0x25,
-						      0x3, 0x10, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x93, 0x25,
+						    0x3, 0x10, 0x0);
 			rssi_adjust_val = 14;
 			break;
 		case 20:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x61, 0x35,
-						      0x03, 0x11, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x61, 0x35,
+						    0x03, 0x11, 0x10);
 			break;
 		case 21:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x61, 0x15,
-						      0x03, 0x11, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x61, 0x15,
+						    0x03, 0x11, 0x10);
 			break;
 		case 22:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x61, 0x25,
-						      0x03, 0x11, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x61, 0x25,
+						    0x03, 0x11, 0x10);
 			break;
 		case 23:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xe3, 0x25,
-						      0x3, 0x31, 0x18);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
+						    0x3, 0x31, 0x18);
 			rssi_adjust_val = 22;
 			break;
 		case 24:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xe3, 0x15,
-						      0x3, 0x31, 0x18);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x15,
+						    0x3, 0x31, 0x18);
 			rssi_adjust_val = 22;
 			break;
 		case 25:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xe3, 0xa,
-						      0x3, 0x31, 0x18);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xe3, 0xa,
+						    0x3, 0x31, 0x18);
 			rssi_adjust_val = 22;
 			break;
 		case 26:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xe3, 0xa,
-						      0x3, 0x31, 0x18);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xe3, 0xa,
+						    0x3, 0x31, 0x18);
 			rssi_adjust_val = 22;
 			break;
 		case 27:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xe3, 0x25,
-						      0x3, 0x31, 0x98);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
+						    0x3, 0x31, 0x98);
 			rssi_adjust_val = 22;
 			break;
 		case 28:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x69, 0x25,
-						      0x3, 0x31, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x69, 0x25,
+						    0x3, 0x31, 0x0);
 			break;
 		case 29:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xab, 0x1a,
-						      0x1a, 0x1, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xab, 0x1a,
+						    0x1a, 0x1, 0x10);
 			break;
 		case 30:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x51, 0x14,
-						      0x3, 0x10, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x51, 0x14,
+						    0x3, 0x10, 0x50);
 			break;
 		case 31:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xd3, 0x1a,
-						      0x1a, 0, 0x58);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x1a,
+						    0x1a, 0, 0x58);
 			break;
 		case 32:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x61, 0xa,
-						      0x3, 0x10, 0x0);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x61, 0xa,
+						    0x3, 0x10, 0x0);
 			break;
 		case 33:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xa3, 0x25,
-						      0x3, 0x30, 0x90);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xa3, 0x25,
+						    0x3, 0x30, 0x90);
 			break;
 		case 34:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x53, 0x1a,
-						      0x1a, 0x0, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x53, 0x1a,
+						    0x1a, 0x0, 0x10);
 			break;
 		case 35:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x63, 0x1a,
-						      0x1a, 0x0, 0x10);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x63, 0x1a,
+						    0x1a, 0x0, 0x10);
 			break;
 		case 36:
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0xd3, 0x12,
-						      0x3, 0x14, 0x50);
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x12,
+						    0x3, 0x14, 0x50);
 			break;
 		}
 	} else {
-		/* disable PS tdma*/
+		/* disable PS tdma */
 		switch (type) {
-		case 8: /*PTA Control*/
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x8, 0x0, 0x0,
-						      0x0, 0x0);
-			halbtc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_PTA,
-						     false, false);
+		case 8:
+			/* PTA Control */
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x8, 0x0, 0x0,
+						    0x0, 0x0);
+			btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_PTA,
+						  false, false);
 			break;
 		case 0:
-		default:  /*Software control, Antenna at BT side*/
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x0, 0x0, 0x0,
-						      0x0, 0x0);
-			halbtc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
-						     false, false);
+		default:
+			/* Software control, Antenna at BT side */
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
+						    0x0, 0x0);
+			btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
+						  false, false);
 			break;
-		case 9:   /*Software control, Antenna at WiFi side*/
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x0, 0x0, 0x0,
-						      0x0, 0x0);
-			halbtc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_WIFI,
-						     false, false);
+		case 9:
+			/* Software control, Antenna at WiFi side */
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
+						    0x0, 0x0);
+			btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_WIFI,
+						  false, false);
 			break;
-		case 10:	/* under 5G*/
-			halbtc8821a1ant_set_fw_pstdma(btcoexist, 0x0, 0x0, 0x0,
-						      0x8, 0x0);
-			halbtc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
-						     false, false);
+		case 10:
+			/* under 5G */
+			btc8821a1ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
+						    0x8, 0x0);
+			btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
+						  false, false);
 			break;
 		}
 	}
@@ -1264,15 +1270,15 @@ static void halbtc8821a1ant_ps_tdma(struct btc_coexist *btcoexist,
 	btcoexist->btc_set(btcoexist,
 		 BTC_SET_U1_RSSI_ADJ_VAL_FOR_1ANT_COEX_TYPE, &rssi_adjust_val);
 
-	/* update pre state*/
+	/* update pre state */
 	coex_dm->pre_ps_tdma_on = coex_dm->cur_ps_tdma_on;
 	coex_dm->pre_ps_tdma = coex_dm->cur_ps_tdma;
 }
 
-static bool halbtc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
+static bool btc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool	common = false, wifi_connected = false, wifi_busy = false;
+	bool common = false, wifi_connected = false, wifi_busy = false;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 			   &wifi_connected);
@@ -1283,7 +1289,7 @@ static bool halbtc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
 	    coex_dm->bt_status) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Wifi non connected-idle + BT non connected-idle!!\n");
-		halbtc8821a1ant_sw_mechanism(btcoexist, false);
+		btc8821a1ant_sw_mechanism(btcoexist, false);
 
 		common = true;
 	} else if (wifi_connected &&
@@ -1291,7 +1297,7 @@ static bool halbtc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
 		    coex_dm->bt_status)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Wifi connected + BT non connected-idle!!\n");
-		halbtc8821a1ant_sw_mechanism(btcoexist, false);
+		btc8821a1ant_sw_mechanism(btcoexist, false);
 
 		common = true;
 	} else if (!wifi_connected &&
@@ -1299,15 +1305,15 @@ static bool halbtc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
 		    coex_dm->bt_status)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Wifi non connected-idle + BT connected-idle!!\n");
-		halbtc8821a1ant_sw_mechanism(btcoexist, false);
+		btc8821a1ant_sw_mechanism(btcoexist, false);
 
 		common = true;
 	} else if (wifi_connected &&
 		   (BT_8821A_1ANT_BT_STATUS_CONNECTED_IDLE ==
-		   coex_dm->bt_status)) {
+		    coex_dm->bt_status)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Wifi connected + BT connected-idle!!\n");
-		halbtc8821a1ant_sw_mechanism(btcoexist, false);
+		btc8821a1ant_sw_mechanism(btcoexist, false);
 
 		common = true;
 	} else if (!wifi_connected &&
@@ -1315,7 +1321,7 @@ static bool halbtc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
 		    coex_dm->bt_status)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Wifi non connected-idle + BT Busy!!\n");
-		halbtc8821a1ant_sw_mechanism(btcoexist, false);
+		btc8821a1ant_sw_mechanism(btcoexist, false);
 
 		common = true;
 	} else {
@@ -1333,231 +1339,40 @@ static bool halbtc8821a1ant_is_common_action(struct btc_coexist *btcoexist)
 	return common;
 }
 
-static void btc8821a1ant_tdma_dur_adj(struct btc_coexist *btcoexist,
-				      u8 wifi_status)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static long		up, dn, m, n, wait_count;
-	/*0: no change, +1: increase WiFi duration, -1: decrease WiFi duration*/
-	long			result;
-	u8			retry_count = 0, bt_info_ext;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], TdmaDurationAdjustForAcl()\n");
-
-	if ((BT_8821A_1ANT_WIFI_STATUS_NON_CONNECTED_ASSO_AUTH_SCAN ==
-	     wifi_status) ||
-	    (BT_8821A_1ANT_WIFI_STATUS_CONNECTED_SCAN ==
-	     wifi_status) ||
-	    (BT_8821A_1ANT_WIFI_STATUS_CONNECTED_SPECIAL_PKT ==
-	     wifi_status)) {
-		if (coex_dm->cur_ps_tdma != 1 &&
-		    coex_dm->cur_ps_tdma != 2 &&
-		    coex_dm->cur_ps_tdma != 3 &&
-		    coex_dm->cur_ps_tdma != 9) {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 9);
-			coex_dm->tdma_adj_type = 9;
-
-			up = 0;
-			dn = 0;
-			m = 1;
-			n = 3;
-			result = 0;
-			wait_count = 0;
-		}
-		return;
-	}
-
-	if (!coex_dm->auto_tdma_adjust) {
-		coex_dm->auto_tdma_adjust = true;
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], first run TdmaDurationAdjust()!!\n");
-
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 2);
-		coex_dm->tdma_adj_type = 2;
-		/*============*/
-		up = 0;
-		dn = 0;
-		m = 1;
-		n = 3;
-		result = 0;
-		wait_count = 0;
-	} else {
-		/*accquire the BT TRx retry count from BT_Info byte2*/
-		retry_count = coex_sta->bt_retry_cnt;
-		bt_info_ext = coex_sta->bt_info_ext;
-		result = 0;
-		wait_count++;
-
-		if (retry_count == 0) {
-			/* no retry in the last 2-second duration*/
-			up++;
-			dn--;
-
-			if (dn <= 0)
-				dn = 0;
-
-			if (up >= n) {
-				/* if (retry count == 0) for 2*n seconds ,
-				 * make WiFi duration wider
-				 */
-				wait_count = 0;
-				n = 3;
-				up = 0;
-				dn = 0;
-				result = 1;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Increase wifi duration!!\n");
-			}
-		} else if (retry_count <= 3) {
-			/* <=3 retry in the last 2-second duration*/
-			up--;
-			dn++;
-
-			if (up <= 0)
-				up = 0;
-
-			if (dn == 2) {
-				/* if retry count< 3 for 2*2 seconds,
-				 * shrink wifi duration
-				 */
-				if (wait_count <= 2)
-					m++; /* avoid bounce in two levels */
-				else
-					m = 1;
-
-				if (m >= 20) {
-					/* m max value is 20, max time is 120 s,
-					 *	recheck if adjust WiFi duration.
-					 */
-					m = 20;
-				}
-				n = 3*m;
-				up = 0;
-				dn = 0;
-				wait_count = 0;
-				result = -1;
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Decrease wifi duration for retryCounter<3!!\n");
-			}
-		} else {
-			/* retry count > 3, if retry count > 3 happens once,
-			 *	shrink WiFi duration
-			 */
-			if (wait_count == 1)
-				m++; /* avoid bounce in two levels */
-			else
-				m = 1;
-		/* m max value is 20, max time is 120 second,
-		 *	recheck if adjust WiFi duration.
-		*/
-			if (m >= 20)
-				m = 20;
-
-			n = 3*m;
-			up = 0;
-			dn = 0;
-			wait_count = 0;
-			result = -1;
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Decrease wifi duration for retryCounter>3!!\n");
-		}
-
-		if (result == -1) {
-			if ((BT_INFO_8821A_1ANT_A2DP_BASIC_RATE(bt_info_ext)) &&
-			    ((coex_dm->cur_ps_tdma == 1) ||
-			     (coex_dm->cur_ps_tdma == 2))) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			}
-		} else if (result == 1) {
-			if ((BT_INFO_8821A_1ANT_A2DP_BASIC_RATE(bt_info_ext)) &&
-			    ((coex_dm->cur_ps_tdma == 1) ||
-			     (coex_dm->cur_ps_tdma == 2))) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 1);
-				coex_dm->tdma_adj_type = 1;
-			}
-		} else {
-			/*no change*/
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], ********** TDMA(on, %d) **********\n",
-				 coex_dm->cur_ps_tdma);
-		}
-
-		if (coex_dm->cur_ps_tdma != 1 &&
-		    coex_dm->cur_ps_tdma != 2 &&
-		    coex_dm->cur_ps_tdma != 9 &&
-		    coex_dm->cur_ps_tdma != 11) {
-			/* recover to previous adjust type*/
-			halbtc8821a1ant_ps_tdma(btcoexist,
-						NORMAL_EXEC, true,
-						coex_dm->tdma_adj_type);
-		}
-	}
-}
-
 static void btc8821a1ant_ps_tdma_check_for_pwr_save(struct btc_coexist *btcoex,
 						    bool new_ps_state)
 {
-	u8	lps_mode = 0x0;
+	u8 lps_mode = 0x0;
 
 	btcoex->btc_get(btcoex, BTC_GET_U1_LPS_MODE, &lps_mode);
 
 	if (lps_mode) {
-		/* already under LPS state*/
+		/* already under LPS state */
 		if (new_ps_state) {
-			/* keep state under LPS, do nothing.*/
+			/* keep state under LPS, do nothing */
 		} else {
-			/* will leave LPS state, turn off psTdma first*/
-			halbtc8821a1ant_ps_tdma(btcoex, NORMAL_EXEC, false, 0);
+			/* will leave LPS state, turn off psTdma first */
+			btc8821a1ant_ps_tdma(btcoex, NORMAL_EXEC, false, 0);
 		}
 	} else {
 		/* NO PS state*/
 		if (new_ps_state) {
-			/* will enter LPS state, turn off psTdma first*/
-			halbtc8821a1ant_ps_tdma(btcoex, NORMAL_EXEC, false, 0);
+			/* will enter LPS state, turn off psTdma first */
+			btc8821a1ant_ps_tdma(btcoex, NORMAL_EXEC, false, 0);
 		} else {
-			/* keep state under NO PS state, do nothing.*/
+			/* keep state under NO PS state, do nothing */
 		}
 	}
 }
 
-static void halbtc8821a1ant_power_save_state(struct btc_coexist *btcoexist,
-					     u8 ps_type, u8 lps_val,
-					     u8 rpwm_val)
+static void btc8821a1ant_power_save_state(struct btc_coexist *btcoexist,
+					  u8 ps_type, u8 lps_val, u8 rpwm_val)
 {
 	bool low_pwr_disable = false;
 
 	switch (ps_type) {
 	case BTC_PS_WIFI_NATIVE:
-		/* recover to original 32k low power setting*/
+		/* recover to original 32k low power setting */
 		low_pwr_disable = false;
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 				   &low_pwr_disable);
@@ -1566,13 +1381,13 @@ static void halbtc8821a1ant_power_save_state(struct btc_coexist *btcoexist,
 	case BTC_PS_LPS_ON:
 		btc8821a1ant_ps_tdma_check_for_pwr_save(btcoexist,
 							true);
-		halbtc8821a1ant_lps_rpwm(btcoexist,
-					 NORMAL_EXEC, lps_val, rpwm_val);
-		/* when coex force to enter LPS, do not enter 32k low power.*/
+		btc8821a1ant_lps_rpwm(btcoexist, NORMAL_EXEC, lps_val,
+				      rpwm_val);
+		/* when coex force to enter LPS, do not enter 32k low power */
 		low_pwr_disable = true;
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 				   &low_pwr_disable);
-		/* power save must executed before psTdma.*/
+		/* power save must executed before psTdma */
 		btcoexist->btc_set(btcoexist, BTC_SET_ACT_ENTER_LPS, NULL);
 		break;
 	case BTC_PS_LPS_OFF:
@@ -1584,295 +1399,332 @@ static void halbtc8821a1ant_power_save_state(struct btc_coexist *btcoexist,
 	}
 }
 
-static void halbtc8821a1ant_coex_under_5g(struct btc_coexist *btcoexist)
+static void btc8821a1ant_coex_under_5g(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
-					 0x0, 0x0);
-	halbtc8821a1ant_ignore_wlan_act(btcoexist, NORMAL_EXEC, true);
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+				      0x0, 0x0);
+	btc8821a1ant_ignore_wlan_act(btcoexist, NORMAL_EXEC, true);
 
-	halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 10);
+	btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 10);
 
-	halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+	btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 
-	halbtc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+	btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
 
-	halbtc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 5);
+	btc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 5);
 }
 
-static void halbtc8821a1ant_action_wifi_only(struct btc_coexist *btcoexist)
+/***********************************************
+ *
+ *	Software Coex Mechanism start
+ *
+ ***********************************************/
+
+/* SCO only or SCO+PAN(HS) */
+static void btc8821a1ant_action_sco(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
-	halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 9);
+	btc8821a1ant_sw_mechanism(btcoexist, true);
 }
 
-static void btc8821a1ant_mon_bt_en_dis(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_hid(struct btc_coexist *btcoexist)
 {
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static bool	pre_bt_disabled;
-	static u32	bt_disable_cnt;
-	bool		bt_active = true, bt_disabled = false;
-
-	/* This function check if bt is disabled*/
-
-	if (coex_sta->high_priority_tx == 0 &&
-	    coex_sta->high_priority_rx == 0 &&
-	    coex_sta->low_priority_tx == 0 &&
-	    coex_sta->low_priority_rx == 0) {
-		bt_active = false;
-	}
-	if (coex_sta->high_priority_tx == 0xffff &&
-	    coex_sta->high_priority_rx == 0xffff &&
-	    coex_sta->low_priority_tx == 0xffff &&
-	    coex_sta->low_priority_rx == 0xffff) {
-		bt_active = false;
-	}
-	if (bt_active) {
-		bt_disable_cnt = 0;
-		bt_disabled = false;
-		btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_DISABLE,
-				   &bt_disabled);
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BT is enabled !!\n");
-	} else {
-		bt_disable_cnt++;
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], bt all counters = 0, %d times!!\n",
-			 bt_disable_cnt);
-		if (bt_disable_cnt >= 2) {
-			bt_disabled = true;
-			btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_DISABLE,
-					   &bt_disabled);
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], BT is disabled !!\n");
-			halbtc8821a1ant_action_wifi_only(btcoexist);
-		}
-	}
-	if (pre_bt_disabled != bt_disabled) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BT is from %s to %s!!\n",
-			    (pre_bt_disabled ? "disabled" : "enabled"),
-			    (bt_disabled ? "disabled" : "enabled"));
-		pre_bt_disabled = bt_disabled;
-		if (bt_disabled) {
-			btcoexist->btc_set(btcoexist, BTC_SET_ACT_LEAVE_LPS,
-					   NULL);
-			btcoexist->btc_set(btcoexist, BTC_SET_ACT_NORMAL_LPS,
-					   NULL);
-		}
-	}
+	btc8821a1ant_sw_mechanism(btcoexist, true);
 }
 
-/*=============================================*/
-/**/
-/*	Software Coex Mechanism start*/
-/**/
-/*=============================================*/
-
-/* SCO only or SCO+PAN(HS)*/
-static void halbtc8821a1ant_action_sco(struct btc_coexist *btcoexist)
+/* A2DP only / PAN(EDR) only/ A2DP+PAN(HS) */
+static void btc8821a1ant_action_a2dp(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, true);
+	btc8821a1ant_sw_mechanism(btcoexist, false);
 }
 
-static void halbtc8821a1ant_action_hid(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, true);
+	btc8821a1ant_sw_mechanism(btcoexist, false);
 }
 
-/*A2DP only / PAN(EDR) only/ A2DP+PAN(HS)*/
-static void halbtc8821a1ant_action_a2dp(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_pan_edr(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, false);
+	btc8821a1ant_sw_mechanism(btcoexist, false);
 }
 
-static void halbtc8821a1ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
+/* PAN(HS) only */
+static void btc8821a1ant_action_pan_hs(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, false);
+	btc8821a1ant_sw_mechanism(btcoexist, false);
 }
 
-static void halbtc8821a1ant_action_pan_edr(struct btc_coexist *btcoexist)
+/* PAN(EDR)+A2DP */
+static void btc8821a1ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, false);
+	btc8821a1ant_sw_mechanism(btcoexist, false);
 }
 
-/*PAN(HS) only*/
-static void halbtc8821a1ant_action_pan_hs(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, false);
+	btc8821a1ant_sw_mechanism(btcoexist, true);
 }
 
-/*PAN(EDR)+A2DP*/
-static void halbtc8821a1ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
+/* HID+A2DP+PAN(EDR) */
+static void btc8821a1ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, false);
+	btc8821a1ant_sw_mechanism(btcoexist, true);
 }
 
-static void halbtc8821a1ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, true);
+	btc8821a1ant_sw_mechanism(btcoexist, true);
 }
 
-/* HID+A2DP+PAN(EDR)*/
-static void btc8821a1ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
+/***********************************************
+ *
+ *	Non-Software Coex Mechanism start
+ *
+ ***********************************************/
+static
+void btc8821a1ant_action_wifi_multi_port(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, true);
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	/* tdma and coex table */
+	if (coex_dm->bt_status == BT_8821A_1ANT_BT_STATUS_ACL_BUSY) {
+		if (bt_link_info->a2dp_exist) {
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
+		} else if (bt_link_info->a2dp_exist &&
+			   bt_link_info->pan_exist) {
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 4);
+		} else {
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 4);
+		}
+	} else if ((coex_dm->bt_status == BT_8821A_1ANT_BT_STATUS_SCO_BUSY) ||
+		   (BT_8821A_1ANT_BT_STATUS_ACL_SCO_BUSY ==
+		    coex_dm->bt_status)) {
+		btc8821a1ant_act_bt_sco_hid_only_busy(btcoexist,
+				BT_8821A_1ANT_WIFI_STATUS_CONNECTED_SCAN);
+	} else {
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
+	}
 }
 
-static void halbtc8821a1ant_action_hid_a2dp(struct btc_coexist *btcoexist)
+static
+void btc8821a1ant_action_wifi_not_connected_asso_auth(
+					struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_sw_mechanism(btcoexist, true);
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0,
+				      0x0);
+
+	/* tdma and coex table */
+	if ((bt_link_info->sco_exist) || (bt_link_info->hid_exist)) {
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+	} else if ((bt_link_info->a2dp_exist) || (bt_link_info->pan_exist)) {
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 4);
+	} else {
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
+	}
 }
 
-/*=============================================*/
-/**/
-/*	Non-Software Coex Mechanism start*/
-/**/
-/*=============================================*/
 
-static void halbtc8821a1ant_action_hs(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_hs(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
-	halbtc8821a1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 2);
+	btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
+	btc8821a1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 2);
 }
 
-static void halbtc8821a1ant_action_bt_inquiry(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_bt_inquiry(struct btc_coexist *btcoexist)
 {
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 	bool wifi_connected = false;
+	bool ap_enable = false;
+	bool wifi_busy = false, bt_busy = false;
 
-	btcoexist->btc_get(btcoexist,
-		 BTC_GET_BL_WIFI_CONNECTED, &wifi_connected);
-
-	if (!wifi_connected) {
-		halbtc8821a1ant_power_save_state(btcoexist,
-						 BTC_PS_WIFI_NATIVE, 0x0, 0x0);
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
-	} else if ((bt_link_info->sco_exist) ||
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
+			   &wifi_connected);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_AP_MODE_ENABLE,
+			   &ap_enable);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_TRAFFIC_BUSY, &bt_busy);
+
+	if (!wifi_connected && !coex_sta->wifi_is_high_pri_task) {
+		btc8821a1ant_power_save_state(btcoexist,
+					      BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+	} else if ((bt_link_info->sco_exist) || (bt_link_info->a2dp_exist) ||
 		   (bt_link_info->hid_only)) {
-		/* SCO/HID-only busy*/
-		halbtc8821a1ant_power_save_state(btcoexist,
-						 BTC_PS_WIFI_NATIVE, 0x0, 0x0);
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 32);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		/* SCO/HID-only busy */
+		btc8821a1ant_power_save_state(btcoexist,
+					      BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 32);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 4);
+	} else if ((bt_link_info->a2dp_exist) && (bt_link_info->hid_exist)) {
+		/* A2DP+HID busy */
+		btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+	} else if ((bt_link_info->pan_exist) || (wifi_busy)) {
+		btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 4);
 	} else {
-		halbtc8821a1ant_power_save_state(btcoexist, BTC_PS_LPS_ON,
-						 0x50, 0x4);
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 30);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
 	}
 }
 
 static void btc8821a1ant_act_bt_sco_hid_only_busy(struct btc_coexist *btcoexist,
-						  u8 wifi_status) {
-	/* tdma and coex table*/
-	halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
+						  u8 wifi_status)
+{
+	/* tdma and coex table */
+	btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
 
-	halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+	if (BT_8821A_1ANT_WIFI_STATUS_NON_CONNECTED_ASSO_AUTH_SCAN ==
+	    wifi_status)
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+	else
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 }
 
 static void btc8821a1ant_act_wifi_con_bt_acl_busy(struct btc_coexist *btcoexist,
 						  u8 wifi_status)
 {
-	u8		bt_rssi_state;
+	u8 bt_rssi_state;
 
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
-	bt_rssi_state = halbtc8821a1ant_bt_rssi_state(btcoexist, 2, 28, 0);
+	bt_rssi_state = btc8821a1ant_bt_rssi_state(btcoexist, 2, 28, 0);
 
 	if (bt_link_info->hid_only) {
-		/*HID*/
+		/* HID */
 		btc8821a1ant_act_bt_sco_hid_only_busy(btcoexist,
 						      wifi_status);
 		coex_dm->auto_tdma_adjust = false;
 		return;
 	} else if (bt_link_info->a2dp_only) {
-		/*A2DP*/
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a1ant_tdma_dur_adj(btcoexist, wifi_status);
-		} else {
-			/*for low BT RSSI*/
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
+		/* A2DP */
+		if ((bt_rssi_state != BTC_RSSI_STATE_HIGH) &&
+		    (bt_rssi_state != BTC_RSSI_STATE_STAY_HIGH)) {
+			/* for low BT RSSI */
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 11);
 			coex_dm->auto_tdma_adjust = false;
 		}
 
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 	} else if (bt_link_info->hid_exist && bt_link_info->a2dp_exist) {
-		/*HID+A2DP*/
+		/* HID+A2DP */
 		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 14);
 			coex_dm->auto_tdma_adjust = false;
 		} else {
 			/*for low BT RSSI*/
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 11);
 			coex_dm->auto_tdma_adjust = false;
 		}
 
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 	} else if ((bt_link_info->pan_only) ||
 		(bt_link_info->hid_exist && bt_link_info->pan_exist)) {
-		/*PAN(OPP, FTP), HID+PAN(OPP, FTP)*/
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		/* PAN(OPP, FTP), HID+PAN(OPP, FTP) */
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 		coex_dm->auto_tdma_adjust = false;
 	} else if (((bt_link_info->a2dp_exist) && (bt_link_info->pan_exist)) ||
 		   (bt_link_info->hid_exist && bt_link_info->a2dp_exist &&
 		    bt_link_info->pan_exist)) {
-		/*A2DP+PAN(OPP, FTP), HID+A2DP+PAN(OPP, FTP)*/
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 13);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		/* A2DP+PAN(OPP, FTP), HID+A2DP+PAN(OPP, FTP) */
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 13);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 		coex_dm->auto_tdma_adjust = false;
 	} else {
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 		coex_dm->auto_tdma_adjust = false;
 	}
 }
 
-static void halbtc8821a1ant_action_wifi_not_connected(
-	struct btc_coexist *btcoexist)
+static
+void btc8821a1ant_action_wifi_not_connected(struct btc_coexist *btcoexist)
 {
-	/* power save state*/
-	halbtc8821a1ant_power_save_state(btcoexist,
-					 BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	/* power save state */
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
 
-	/* tdma and coex table*/
-	halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
-	halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+	/* tdma and coex table */
+	btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+	btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 }
 
 static void btc8821a1ant_act_wifi_not_conn_scan(struct btc_coexist *btcoexist)
 {
-	halbtc8821a1ant_power_save_state(btcoexist,
-					 BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
-	halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
-	halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+
+	/* tdma and coex table */
+	if (coex_dm->bt_status == BT_8821A_1ANT_BT_STATUS_ACL_BUSY) {
+		if (bt_link_info->a2dp_exist) {
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
+		} else if (bt_link_info->a2dp_exist &&
+			   bt_link_info->pan_exist) {
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 4);
+		} else {
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 4);
+		}
+	} else if ((coex_dm->bt_status == BT_8821A_1ANT_BT_STATUS_SCO_BUSY) ||
+		   (BT_8821A_1ANT_BT_STATUS_ACL_SCO_BUSY ==
+		    coex_dm->bt_status)) {
+		btc8821a1ant_act_bt_sco_hid_only_busy(btcoexist,
+				BT_8821A_1ANT_WIFI_STATUS_CONNECTED_SCAN);
+	} else {
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
+	}
 }
 
-static void halbtc8821a1ant_action_wifi_connected_scan(
-	struct btc_coexist *btcoexist) {
+static
+void btc8821a1ant_action_wifi_connected_scan(struct btc_coexist *btcoexist)
+{
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 
-	/* power save state*/
-	halbtc8821a1ant_power_save_state(btcoexist,
-					 BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	/* power save state */
+	btc8821a1ant_power_save_state(btcoexist,
+				      BTC_PS_WIFI_NATIVE, 0x0, 0x0);
 
-	/* tdma and coex table*/
+	/* tdma and coex table */
 	if (BT_8821A_1ANT_BT_STATUS_ACL_BUSY == coex_dm->bt_status) {
 		if (bt_link_info->a2dp_exist && bt_link_info->pan_exist) {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 22);
-			halbtc8821a1ant_coex_table_with_type(btcoexist,
-							     NORMAL_EXEC, 1);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
 		} else {
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 	}
 	} else if ((BT_8821A_1ANT_BT_STATUS_SCO_BUSY ==
 		    coex_dm->bt_status) ||
@@ -1881,52 +1733,52 @@ static void halbtc8821a1ant_action_wifi_connected_scan(
 		btc8821a1ant_act_bt_sco_hid_only_busy(btcoexist,
 			BT_8821A_1ANT_WIFI_STATUS_CONNECTED_SCAN);
 	} else {
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 	}
 }
 
 static void btc8821a1ant_act_wifi_conn_sp_pkt(struct btc_coexist *btcoexist)
 {
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
-	bool	hs_connecting = false;
+	bool hs_connecting = false;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_CONNECTING, &hs_connecting);
 
-	halbtc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
-					 0x0, 0x0);
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+				      0x0, 0x0);
 
-	/* tdma and coex table*/
-	if (BT_8821A_1ANT_BT_STATUS_ACL_BUSY == coex_dm->bt_status) {
+	/* tdma and coex table */
+	if (coex_dm->bt_status == BT_8821A_1ANT_BT_STATUS_ACL_BUSY) {
 		if (bt_link_info->a2dp_exist && bt_link_info->pan_exist) {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 22);
-			halbtc8821a1ant_coex_table_with_type(btcoexist,
-							     NORMAL_EXEC, 1);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 22);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
 		} else {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 20);
-			halbtc8821a1ant_coex_table_with_type(btcoexist,
-							     NORMAL_EXEC, 1);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 20);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 1);
 		}
 	} else {
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
-		halbtc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 20);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 1);
 	}
 }
 
-static void halbtc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
+static void btc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool	wifi_busy = false;
-	bool	scan = false, link = false, roam = false;
-	bool	under_4way = false;
+	bool wifi_busy = false;
+	bool scan = false, link = false, roam = false;
+	bool under_4way = false;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], CoexForWifiConnect()===>\n");
 
-	btcoexist->btc_get(btcoexist,
-		 BTC_GET_BL_WIFI_4_WAY_PROGRESS, &under_4way);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_4_WAY_PROGRESS,
+			   &under_4way);
 	if (under_4way) {
 		btc8821a1ant_act_wifi_conn_sp_pkt(btcoexist);
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -1938,7 +1790,7 @@ static void halbtc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
 	if (scan || link || roam) {
-		halbtc8821a1ant_action_wifi_connected_scan(btcoexist);
+		btc8821a1ant_action_wifi_connected_scan(btcoexist);
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], CoexForWifiConnect(), return for wifi is under scan<===\n");
 		return;
@@ -1947,14 +1799,14 @@ static void halbtc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 	/* power save state*/
 	if (BT_8821A_1ANT_BT_STATUS_ACL_BUSY ==
 			coex_dm->bt_status && !btcoexist->bt_link_info.hid_only)
-		halbtc8821a1ant_power_save_state(btcoexist,
-						 BTC_PS_LPS_ON, 0x50, 0x4);
+		btc8821a1ant_power_save_state(btcoexist,
+					      BTC_PS_LPS_ON, 0x50, 0x4);
 	else
-		halbtc8821a1ant_power_save_state(btcoexist,
-						 BTC_PS_WIFI_NATIVE,
-						 0x0, 0x0);
+		btc8821a1ant_power_save_state(btcoexist,
+					      BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
 
-	/* tdma and coex table*/
+	/* tdma and coex table */
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
 	if (!wifi_busy) {
 		if (BT_8821A_1ANT_BT_STATUS_ACL_BUSY == coex_dm->bt_status) {
@@ -1967,10 +1819,10 @@ static void halbtc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 			btc8821a1ant_act_bt_sco_hid_only_busy(btcoexist,
 				BT_8821A_1ANT_WIFI_STATUS_CONNECTED_IDLE);
 		} else {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-			halbtc8821a1ant_coex_table_with_type(btcoexist,
-							     NORMAL_EXEC, 2);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 5);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 2);
 		}
 	} else {
 		if (BT_8821A_1ANT_BT_STATUS_ACL_BUSY == coex_dm->bt_status) {
@@ -1983,10 +1835,9 @@ static void halbtc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 			btc8821a1ant_act_bt_sco_hid_only_busy(btcoexist,
 				BT_8821A_1ANT_WIFI_STATUS_CONNECTED_BUSY);
 		} else {
-			halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-			halbtc8821a1ant_coex_table_with_type(btcoexist,
-							     NORMAL_EXEC, 2);
+			btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
+			btc8821a1ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 2);
 		}
 	}
 }
@@ -1994,52 +1845,52 @@ static void halbtc8821a1ant_action_wifi_connected(struct btc_coexist *btcoexist)
 static void btc8821a1ant_run_sw_coex_mech(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8	algorithm = 0;
+	u8 algorithm = 0;
 
-	algorithm = halbtc8821a1ant_action_algorithm(btcoexist);
+	algorithm = btc8821a1ant_action_algorithm(btcoexist);
 	coex_dm->cur_algorithm = algorithm;
 
-	if (!halbtc8821a1ant_is_common_action(btcoexist)) {
+	if (!btc8821a1ant_is_common_action(btcoexist)) {
 		switch (coex_dm->cur_algorithm) {
 		case BT_8821A_1ANT_COEX_ALGO_SCO:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = SCO\n");
-			halbtc8821a1ant_action_sco(btcoexist);
+			btc8821a1ant_action_sco(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_HID:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = HID\n");
-			halbtc8821a1ant_action_hid(btcoexist);
+			btc8821a1ant_action_hid(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = A2DP\n");
-			halbtc8821a1ant_action_a2dp(btcoexist);
+			btc8821a1ant_action_a2dp(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_A2DP_PANHS:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = A2DP+PAN(HS)\n");
-			halbtc8821a1ant_action_a2dp_pan_hs(btcoexist);
+			btc8821a1ant_action_a2dp_pan_hs(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_PANEDR:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = PAN(EDR)\n");
-			halbtc8821a1ant_action_pan_edr(btcoexist);
+			btc8821a1ant_action_pan_edr(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_PANHS:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = HS mode\n");
-			halbtc8821a1ant_action_pan_hs(btcoexist);
+			btc8821a1ant_action_pan_hs(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_PANEDR_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = PAN+A2DP\n");
-			halbtc8821a1ant_action_pan_edr_a2dp(btcoexist);
+			btc8821a1ant_action_pan_edr_a2dp(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_PANEDR_HID:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = PAN(EDR)+HID\n");
-			halbtc8821a1ant_action_pan_edr_hid(btcoexist);
+			btc8821a1ant_action_pan_edr_hid(btcoexist);
 			break;
 		case BT_8821A_1ANT_COEX_ALGO_HID_A2DP_PANEDR:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -2049,28 +1900,30 @@ static void btc8821a1ant_run_sw_coex_mech(struct btc_coexist *btcoexist)
 		case BT_8821A_1ANT_COEX_ALGO_HID_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = HID+A2DP\n");
-			halbtc8821a1ant_action_hid_a2dp(btcoexist);
+			btc8821a1ant_action_hid_a2dp(btcoexist);
 			break;
 		default:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action algorithm = coexist All Off!!\n");
-			/*halbtc8821a1ant_coex_all_off(btcoexist);*/
+			/*btc8821a1ant_coex_all_off(btcoexist);*/
 			break;
 		}
 		coex_dm->pre_algorithm = coex_dm->cur_algorithm;
 	}
 }
 
-static void halbtc8821a1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
+static void btc8821a1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
-	bool	wifi_connected = false, bt_hs_on = false;
-	bool	increase_scan_dev_num = false;
-	bool	bt_ctrl_agg_buf_size = false;
-	u8	agg_buf_size = 5;
-	u8	wifi_rssi_state = BTC_RSSI_STATE_HIGH;
-	bool	wifi_under_5g = false;
+	bool wifi_connected = false, bt_hs_on = false;
+	bool increase_scan_dev_num = false;
+	bool bt_ctrl_agg_buf_size = false;
+	u8 agg_buf_size = 5;
+	u8 wifi_rssi_state = BTC_RSSI_STATE_HIGH;
+	u32 wifi_link_status = 0;
+	u32 num_of_wifi_link = 0;
+	bool wifi_under_5g = false;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], RunCoexistMechanism()===>\n");
@@ -2097,7 +1950,7 @@ static void halbtc8821a1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 	if (wifi_under_5g) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
-		halbtc8821a1ant_coex_under_5g(btcoexist);
+		btc8821a1ant_coex_under_5g(btcoexist);
 		return;
 	}
 
@@ -2109,21 +1962,41 @@ static void halbtc8821a1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 	btcoexist->btc_set(btcoexist, BTC_SET_BL_INC_SCAN_DEV_NUM,
 			   &increase_scan_dev_num);
 
-	btcoexist->btc_get(btcoexist,
-		 BTC_GET_BL_WIFI_CONNECTED, &wifi_connected);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
+			   &wifi_connected);
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_LINK_STATUS,
+			   &wifi_link_status);
+	num_of_wifi_link = wifi_link_status >> 16;
+	if ((num_of_wifi_link >= 2) ||
+	    (wifi_link_status & WIFI_P2P_GO_CONNECTED)) {
+		btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+		btc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
+					bt_ctrl_agg_buf_size, agg_buf_size);
+		btc8821a1ant_action_wifi_multi_port(btcoexist);
+		return;
+	}
 
 	if (!bt_link_info->sco_exist && !bt_link_info->hid_exist) {
-		halbtc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+		btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
 	} else {
 		if (wifi_connected) {
 			wifi_rssi_state =
-				 halbtc8821a1ant_WifiRssiState(btcoexist, 1, 2,
-							       30, 0);
-			halbtc8821a1ant_limited_tx(btcoexist,
-						   NORMAL_EXEC, 1, 1, 1, 1);
+				btc8821a1ant_wifi_rssi_state(btcoexist, 1, 2,
+							     30, 0);
+			if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+			    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+				btc8821a1ant_limited_tx(btcoexist,
+							NORMAL_EXEC, 1, 1,
+							1, 1);
+			} else {
+				btc8821a1ant_limited_tx(btcoexist,
+							NORMAL_EXEC, 1, 1,
+							1, 1);
+			}
 		} else {
-			halbtc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC,
-						   0, 0, 0, 0);
+			btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC,
+						0, 0, 0, 0);
 		}
 	}
 
@@ -2137,22 +2010,22 @@ static void halbtc8821a1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		bt_ctrl_agg_buf_size = true;
 		agg_buf_size = 0x8;
 	}
-	halbtc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
-				   bt_ctrl_agg_buf_size, agg_buf_size);
+	btc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
+				bt_ctrl_agg_buf_size, agg_buf_size);
 
 	btc8821a1ant_run_sw_coex_mech(btcoexist);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 	if (coex_sta->c2h_bt_inquiry_page) {
-		halbtc8821a1ant_action_bt_inquiry(btcoexist);
+		btc8821a1ant_action_bt_inquiry(btcoexist);
 		return;
 	} else if (bt_hs_on) {
-		halbtc8821a1ant_action_hs(btcoexist);
+		btc8821a1ant_action_hs(btcoexist);
 		return;
 	}
 
 	if (!wifi_connected) {
-		bool	scan = false, link = false, roam = false;
+		bool scan = false, link = false, roam = false;
 
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], wifi is non connected-idle !!!\n");
@@ -2161,48 +2034,57 @@ static void halbtc8821a1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
 
-		if (scan || link || roam)
-			btc8821a1ant_act_wifi_not_conn_scan(btcoexist);
-		else
-			halbtc8821a1ant_action_wifi_not_connected(btcoexist);
+		if (scan || link || roam) {
+			if (scan)
+				btc8821a1ant_act_wifi_not_conn_scan(btcoexist);
+			else
+				btc8821a1ant_action_wifi_not_connected_asso_auth(
+					btcoexist);
+		} else {
+			btc8821a1ant_action_wifi_not_connected(btcoexist);
+		}
 	} else {
-		/* wifi LPS/Busy*/
-		halbtc8821a1ant_action_wifi_connected(btcoexist);
+		/* wifi LPS/Busy */
+		btc8821a1ant_action_wifi_connected(btcoexist);
 	}
 }
 
-static void halbtc8821a1ant_init_coex_dm(struct btc_coexist *btcoexist)
+static void btc8821a1ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
-	/* force to reset coex mechanism*/
-	/* sw all off*/
-	halbtc8821a1ant_sw_mechanism(btcoexist, false);
+	/* force to reset coex mechanism
+	 * sw all off
+	 */
+	btc8821a1ant_sw_mechanism(btcoexist, false);
 
-	halbtc8821a1ant_ps_tdma(btcoexist, FORCE_EXEC, false, 8);
-	halbtc8821a1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
+	btc8821a1ant_ps_tdma(btcoexist, FORCE_EXEC, false, 8);
+	btc8821a1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
 }
 
-static void halbtc8821a1ant_init_hw_config(struct btc_coexist *btcoexist,
-					   bool back_up)
+static void btc8821a1ant_init_hw_config(struct btc_coexist *btcoexist,
+					bool back_up, bool wifi_only)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8	u1_tmp = 0;
-	bool	wifi_under_5g = false;
+	u8 u1_tmp = 0;
+	bool wifi_under_5g = false;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], 1Ant Init HW Config!!\n");
 
+	if (wifi_only)
+		return;
+
 	if (back_up) {
 		coex_dm->backup_arfr_cnt1 = btcoexist->btc_read_4byte(btcoexist,
 								      0x430);
 		coex_dm->backup_arfr_cnt2 = btcoexist->btc_read_4byte(btcoexist,
 								      0x434);
 		coex_dm->backup_retry_limit =
-			 btcoexist->btc_read_2byte(btcoexist, 0x42a);
+			btcoexist->btc_read_2byte(btcoexist, 0x42a);
 		coex_dm->backup_ampdu_max_time =
-			 btcoexist->btc_read_1byte(btcoexist, 0x456);
+			btcoexist->btc_read_1byte(btcoexist, 0x456);
 	}
 
-	/* 0x790[5:0] = 0x5*/
+	/* 0x790[5:0] = 0x5 */
 	u1_tmp = btcoexist->btc_read_1byte(btcoexist, 0x790);
 	u1_tmp &= 0xc0;
 	u1_tmp |= 0x5;
@@ -2210,35 +2092,33 @@ static void halbtc8821a1ant_init_hw_config(struct btc_coexist *btcoexist,
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
 
-	/*Antenna config*/
+	/* Antenna config */
 	if (wifi_under_5g)
-		halbtc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
-					     true, false);
+		btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT,
+					  true, false);
 	else
-		halbtc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_PTA,
-					     true, false);
-	/* PTA parameter*/
-	halbtc8821a1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
-
-	/* Enable counter statistics*/
-	/*0x76e[3] =1, WLAN_Act control by PTA*/
+		btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_PTA,
+					  true, false);
+	/* PTA parameter */
+	btc8821a1ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
+
+	/* Enable counter statistics
+	 * 0x76e[3] =1, WLAN_Act control by PTA
+	 */
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
 	btcoexist->btc_write_1byte(btcoexist, 0x778, 0x3);
 	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x40, 0x20, 0x1);
 }
 
-/*============================================================*/
-/* work around function start with wa_halbtc8821a1ant_*/
-/*============================================================*/
-/*============================================================*/
-/* extern function start with EXhalbtc8821a1ant_*/
-/*============================================================*/
-void ex_halbtc8821a1ant_init_hwconfig(struct btc_coexist *btcoexist)
+/**************************************************************
+ * extern function start with ex_btc8821a1ant_
+ **************************************************************/
+void ex_btc8821a1ant_init_hwconfig(struct btc_coexist *btcoexist, bool wifionly)
 {
-	halbtc8821a1ant_init_hw_config(btcoexist, true);
+	btc8821a1ant_init_hw_config(btcoexist, true, wifionly);
 }
 
-void ex_halbtc8821a1ant_init_coex_dm(struct btc_coexist *btcoexist)
+void ex_btc8821a1ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -2247,12 +2127,12 @@ void ex_halbtc8821a1ant_init_coex_dm(struct btc_coexist *btcoexist)
 
 	btcoexist->stop_coex_dm = false;
 
-	halbtc8821a1ant_init_coex_dm(btcoexist);
+	btc8821a1ant_init_coex_dm(btcoexist);
 
-	halbtc8821a1ant_query_bt_info(btcoexist);
+	btc8821a1ant_query_bt_info(btcoexist);
 }
 
-void ex_halbtc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
+void ex_btc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
 {
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	struct btc_stack_info *stack_info = &btcoexist->stack_info;
@@ -2359,7 +2239,7 @@ void ex_halbtc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
 		 "uplink" : "downlink")));
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG,
 		   "\r\n %-35s = [%s/ %d/ %d] ", "BT [status/ rssi/ retryCnt]",
-		   ((btcoexist->bt_info.bt_disabled) ? ("disabled") :
+		   ((coex_sta->bt_disabled) ? ("disabled") :
 		   ((coex_sta->c2h_bt_inquiry_page) ? ("inquiry/page scan") :
 		   ((BT_8821A_1ANT_BT_STATUS_NON_CONNECTED_IDLE ==
 		     coex_dm->bt_status) ?
@@ -2397,7 +2277,7 @@ void ex_halbtc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
 		 "\r\n %-35s = %s/%s, (0x%x/0x%x)",
 		 "PS state, IPS/LPS, (lps/rpwm)",
 		 ((coex_sta->under_ips ? "IPS ON" : "IPS OFF")),
-		 ((coex_sta->under_Lps ? "LPS ON" : "LPS OFF")),
+		 ((coex_sta->under_lps ? "LPS ON" : "LPS OFF")),
 		 btcoexist->bt_info.lps_val,
 		 btcoexist->bt_info.rpwm_val);
 	btcoexist->btc_disp_dbg_msg(btcoexist, BTC_DBG_DISP_FW_PWR_MODE_CMD);
@@ -2422,7 +2302,7 @@ void ex_halbtc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
 			 "\r\n %-35s = 0x%x ", "Rate Mask",
 			 btcoexist->bt_info.ra_mask);
 
-		/* Fw mechanism*/
+		/* Fw mechanism */
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "\r\n %-35s",
 			 "============[Fw mechanism]============");
 
@@ -2444,7 +2324,7 @@ void ex_halbtc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
 			 coex_dm->cur_ignore_wlan_act);
 	}
 
-	/* Hw setting*/
+	/* Hw setting */
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG,
 		 "\r\n %-35s", "============[Hw setting]============");
 
@@ -2527,38 +2407,46 @@ void ex_halbtc8821a1ant_display_coex_info(struct btc_coexist *btcoexist)
 		 "\r\n %-35s = %d/ %d", "0x774(low-pri rx/tx)",
 		 coex_sta->low_priority_rx, coex_sta->low_priority_tx);
 #if (BT_AUTO_REPORT_ONLY_8821A_1ANT == 1)
-	halbtc8821a1ant_monitor_bt_ctr(btcoexist);
+	btc8821a1ant_monitor_bt_ctr(btcoexist);
 #endif
 	btcoexist->btc_disp_dbg_msg(btcoexist, BTC_DBG_DISP_COEX_STATISTICS);
 }
 
-void ex_halbtc8821a1ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a1ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	bool wifi_under_5g = false;
 
 	if (btcoexist->manual_control || btcoexist->stop_coex_dm)
 		return;
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
+		return;
+	}
 
 	if (BTC_IPS_ENTER == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS ENTER notify\n");
 		coex_sta->under_ips = true;
-		halbtc8821a1ant_set_ant_path(btcoexist,
-					     BTC_ANT_PATH_BT, false, true);
-		/*set PTA control*/
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
-		halbtc8821a1ant_coex_table_with_type(btcoexist,
-						     NORMAL_EXEC, 0);
+		btc8821a1ant_set_ant_path(btcoexist,
+					  BTC_ANT_PATH_BT, false, true);
+		/* set PTA control */
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 8);
+		btc8821a1ant_coex_table_with_type(btcoexist,
+						  NORMAL_EXEC, 0);
 	} else if (BTC_IPS_LEAVE == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS LEAVE notify\n");
 		coex_sta->under_ips = false;
 
-		halbtc8821a1ant_run_coexist_mechanism(btcoexist);
+		btc8821a1ant_run_coexist_mechanism(btcoexist);
 	}
 }
 
-void ex_halbtc8821a1ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a1ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -2568,22 +2456,35 @@ void ex_halbtc8821a1ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 	if (BTC_LPS_ENABLE == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], LPS ENABLE notify\n");
-		coex_sta->under_Lps = true;
+		coex_sta->under_lps = true;
 	} else if (BTC_LPS_DISABLE == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], LPS DISABLE notify\n");
-		coex_sta->under_Lps = false;
+		coex_sta->under_lps = false;
 	}
 }
 
-void ex_halbtc8821a1ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a1ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	bool wifi_connected = false, bt_hs_on = false;
+	bool bt_ctrl_agg_buf_size = false;
+	bool wifi_under_5g = false;
+	u32 wifi_link_status = 0;
+	u32 num_of_wifi_link = 0;
+	u8 agg_buf_size = 5;
+
+	if (btcoexist->manual_control || btcoexist->stop_coex_dm)
+		return;
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
+		return;
+	}
 
-	if (btcoexist->manual_control ||
-	    btcoexist->stop_coex_dm ||
-	    btcoexist->bt_info.bt_disabled)
+	if (coex_sta->bt_disabled)
 		return;
 
 	btcoexist->btc_get(btcoexist,
@@ -2591,13 +2492,24 @@ void ex_halbtc8821a1ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 	btcoexist->btc_get(btcoexist,
 		 BTC_GET_BL_WIFI_CONNECTED, &wifi_connected);
 
-	halbtc8821a1ant_query_bt_info(btcoexist);
+	btc8821a1ant_query_bt_info(btcoexist);
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_LINK_STATUS,
+			   &wifi_link_status);
+	num_of_wifi_link = wifi_link_status >> 16;
+	if (num_of_wifi_link >= 2) {
+		btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+		btc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
+					bt_ctrl_agg_buf_size, agg_buf_size);
+		btc8821a1ant_action_wifi_multi_port(btcoexist);
+		return;
+	}
 
 	if (coex_sta->c2h_bt_inquiry_page) {
-		halbtc8821a1ant_action_bt_inquiry(btcoexist);
+		btc8821a1ant_action_bt_inquiry(btcoexist);
 		return;
 	} else if (bt_hs_on) {
-		halbtc8821a1ant_action_hs(btcoexist);
+		btc8821a1ant_action_hs(btcoexist);
 		return;
 	}
 
@@ -2605,40 +2517,62 @@ void ex_halbtc8821a1ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], SCAN START notify\n");
 		if (!wifi_connected) {
-			/* non-connected scan*/
+			/* non-connected scan */
 			btc8821a1ant_act_wifi_not_conn_scan(btcoexist);
 		} else {
-			/* wifi is connected*/
-			halbtc8821a1ant_action_wifi_connected_scan(btcoexist);
+			/* wifi is connected */
+			btc8821a1ant_action_wifi_connected_scan(btcoexist);
 		}
 	} else if (BTC_SCAN_FINISH == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], SCAN FINISH notify\n");
 		if (!wifi_connected) {
-			/* non-connected scan*/
-			halbtc8821a1ant_action_wifi_not_connected(btcoexist);
+			/* non-connected scan */
+			btc8821a1ant_action_wifi_not_connected(btcoexist);
 		} else {
-			halbtc8821a1ant_action_wifi_connected(btcoexist);
+			btc8821a1ant_action_wifi_connected(btcoexist);
 		}
 	}
 }
 
-void ex_halbtc8821a1ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a1ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	bool	wifi_connected = false, bt_hs_on = false;
+	u32 wifi_link_status = 0;
+	u32 num_of_wifi_link = 0;
+	bool bt_ctrl_agg_buf_size = false;
+	bool wifi_under_5g = false;
+	u8 agg_buf_size = 5;
+
+	if (btcoexist->manual_control || btcoexist->stop_coex_dm ||
+	    coex_sta->bt_disabled)
+		return;
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
+		return;
+	}
 
-	if (btcoexist->manual_control ||
-	    btcoexist->stop_coex_dm ||
-	    btcoexist->bt_info.bt_disabled)
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_LINK_STATUS,
+			   &wifi_link_status);
+	num_of_wifi_link = wifi_link_status >> 16;
+	if (num_of_wifi_link >= 2) {
+		btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+		btc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
+					bt_ctrl_agg_buf_size, agg_buf_size);
+		btc8821a1ant_action_wifi_multi_port(btcoexist);
 		return;
+	}
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 	if (coex_sta->c2h_bt_inquiry_page) {
-		halbtc8821a1ant_action_bt_inquiry(btcoexist);
+		btc8821a1ant_action_bt_inquiry(btcoexist);
 		return;
 	} else if (bt_hs_on) {
-		halbtc8821a1ant_action_hs(btcoexist);
+		btc8821a1ant_action_hs(btcoexist);
 		return;
 	}
 
@@ -2653,26 +2587,33 @@ void ex_halbtc8821a1ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 		btcoexist->btc_get(btcoexist,
 			 BTC_GET_BL_WIFI_CONNECTED, &wifi_connected);
 		if (!wifi_connected) {
-			/* non-connected scan*/
-			halbtc8821a1ant_action_wifi_not_connected(btcoexist);
+			/* non-connected scan */
+			btc8821a1ant_action_wifi_not_connected(btcoexist);
 		} else {
-			halbtc8821a1ant_action_wifi_connected(btcoexist);
+			btc8821a1ant_action_wifi_connected(btcoexist);
 		}
 	}
 }
 
-void ex_halbtc8821a1ant_media_status_notify(struct btc_coexist *btcoexist,
-					    u8 type)
+void ex_btc8821a1ant_media_status_notify(struct btc_coexist *btcoexist,
+					 u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[3] = {0};
 	u32 wifi_bw;
 	u8 wifi_central_chnl;
+	bool wifi_under_5g = false;
 
-	if (btcoexist->manual_control ||
-	    btcoexist->stop_coex_dm ||
-	    btcoexist->bt_info.bt_disabled)
+	if (btcoexist->manual_control || btcoexist->stop_coex_dm ||
+	    coex_sta->bt_disabled)
+		return;
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
 		return;
+	}
 
 	if (BTC_MEDIA_CONNECT == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -2682,17 +2623,16 @@ void ex_halbtc8821a1ant_media_status_notify(struct btc_coexist *btcoexist,
 			 "[BTCoex], MEDIA disconnect notify\n");
 	}
 
-	/* only 2.4G we need to inform bt the chnl mask*/
+	/* only 2.4G we need to inform bt the chnl mask */
 	btcoexist->btc_get(btcoexist,
 			   BTC_GET_U1_WIFI_CENTRAL_CHNL,
 			   &wifi_central_chnl);
-	if ((BTC_MEDIA_CONNECT == type) &&
+	if ((type == BTC_MEDIA_CONNECT) &&
 	    (wifi_central_chnl <= 14)) {
-		/*h2c_parameter[0] = 0x1;*/
 		h2c_parameter[0] = 0x0;
 		h2c_parameter[1] = wifi_central_chnl;
 		btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
-		if (BTC_WIFI_BW_HT40 == wifi_bw)
+		if (wifi_bw == BTC_WIFI_BW_HT40)
 			h2c_parameter[2] = 0x30;
 		else
 			h2c_parameter[2] = 0x20;
@@ -2711,25 +2651,48 @@ void ex_halbtc8821a1ant_media_status_notify(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x66, 3, h2c_parameter);
 }
 
-void ex_halbtc8821a1ant_special_packet_notify(struct btc_coexist *btcoexist,
-					      u8 type)
+void ex_btc8821a1ant_special_packet_notify(struct btc_coexist *btcoexist,
+					   u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	bool bt_hs_on = false;
+	bool bt_ctrl_agg_buf_size = false;
+	bool wifi_under_5g = false;
+	u32 wifi_link_status = 0;
+	u32 num_of_wifi_link = 0;
+	u8 agg_buf_size = 5;
+
+	if (btcoexist->manual_control || btcoexist->stop_coex_dm ||
+	    coex_sta->bt_disabled)
+		return;
 
-	if (btcoexist->manual_control ||
-	    btcoexist->stop_coex_dm ||
-	    btcoexist->bt_info.bt_disabled)
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
 		return;
+	}
 
 	coex_sta->special_pkt_period_cnt = 0;
 
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_LINK_STATUS,
+			   &wifi_link_status);
+	num_of_wifi_link = wifi_link_status >> 16;
+	if (num_of_wifi_link >= 2) {
+		btc8821a1ant_limited_tx(btcoexist, NORMAL_EXEC, 0, 0, 0, 0);
+		btc8821a1ant_limited_rx(btcoexist, NORMAL_EXEC, false,
+					bt_ctrl_agg_buf_size, agg_buf_size);
+		btc8821a1ant_action_wifi_multi_port(btcoexist);
+		return;
+	}
+
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 	if (coex_sta->c2h_bt_inquiry_page) {
-		halbtc8821a1ant_action_bt_inquiry(btcoexist);
+		btc8821a1ant_action_bt_inquiry(btcoexist);
 		return;
 	} else if (bt_hs_on) {
-		halbtc8821a1ant_action_hs(btcoexist);
+		btc8821a1ant_action_hs(btcoexist);
 		return;
 	}
 
@@ -2741,12 +2704,13 @@ void ex_halbtc8821a1ant_special_packet_notify(struct btc_coexist *btcoexist,
 	}
 }
 
-void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
-				       u8 *tmp_buf, u8 length)
+void ex_btc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
+				    u8 *tmp_buf, u8 length)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u8 i;
 	u8 bt_info = 0;
-	u8 i, rsp_source = 0;
+	u8 rsp_source = 0;
 	bool wifi_connected = false;
 	bool bt_busy = false;
 	bool wifi_under_5g = false;
@@ -2756,7 +2720,7 @@ void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
 	btcoexist->btc_get(btcoexist,
 		 BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
 
-	rsp_source = tmp_buf[0]&0xf;
+	rsp_source = tmp_buf[0] & 0xf;
 	if (rsp_source >= BT_INFO_SRC_8821A_1ANT_MAX)
 		rsp_source = BT_INFO_SRC_8821A_1ANT_WIFI_FW;
 	coex_sta->bt_info_c2h_cnt[rsp_source]++;
@@ -2768,7 +2732,7 @@ void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_sta->bt_info_c2h[rsp_source][i] = tmp_buf[i];
 		if (i == 1)
 			bt_info = tmp_buf[i];
-		if (i == length-1) {
+		if (i == length - 1) {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "0x%02x]\n", tmp_buf[i]);
 		} else {
@@ -2787,19 +2751,19 @@ void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_sta->bt_info_ext =
 			coex_sta->bt_info_c2h[rsp_source][4];
 
-		/* Here we need to resend some wifi info to BT*/
-		/* because bt is reset and loss of the info.*/
+		/* Here we need to resend some wifi info to BT
+		 * because bt is reset and lost the info
+		 */
 		if (coex_sta->bt_info_ext & BIT1) {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], BT ext info bit1 check, send wifi BW&Chnl to BT!!\n");
-			btcoexist->btc_get(btcoexist,
-					   BTC_GET_BL_WIFI_CONNECTED,
+			btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 					   &wifi_connected);
 			if (wifi_connected) {
-				ex_halbtc8821a1ant_media_status_notify(btcoexist,
+				ex_btc8821a1ant_media_status_notify(btcoexist,
 							       BTC_MEDIA_CONNECT);
 			} else {
-				ex_halbtc8821a1ant_media_status_notify(btcoexist,
+				ex_btc8821a1ant_media_status_notify(btcoexist,
 							       BTC_MEDIA_DISCONNECT);
 			}
 		}
@@ -2809,36 +2773,28 @@ void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
 			    !btcoexist->stop_coex_dm) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], BT ext info bit3 check, set BT NOT to ignore Wlan active!!\n");
-				halbtc8821a1ant_ignore_wlan_act(btcoexist,
-								FORCE_EXEC,
-								false);
+				btc8821a1ant_ignore_wlan_act(btcoexist,
+							     FORCE_EXEC,
+							     false);
 			}
 		}
-#if (BT_AUTO_REPORT_ONLY_8821A_1ANT == 0)
-		if (!(coex_sta->bt_info_ext & BIT4)) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], BT ext info bit4 check, set BT to enable Auto Report!!\n");
-			halbtc8821a1ant_bt_auto_report(btcoexist,
-						       FORCE_EXEC, true);
-		}
-#endif
 	}
 
-	/* check BIT2 first ==> check if bt is under inquiry or page scan*/
+	/* check BIT2 first ==> check if bt is under inquiry or page scan */
 	if (bt_info & BT_INFO_8821A_1ANT_B_INQ_PAGE)
 		coex_sta->c2h_bt_inquiry_page = true;
 	else
 		coex_sta->c2h_bt_inquiry_page = false;
 
-	/* set link exist status*/
-	if (!(bt_info&BT_INFO_8821A_1ANT_B_CONNECTION)) {
+	/* set link exist status */
+	if (!(bt_info & BT_INFO_8821A_1ANT_B_CONNECTION)) {
 		coex_sta->bt_link_exist = false;
 		coex_sta->pan_exist = false;
 		coex_sta->a2dp_exist = false;
 		coex_sta->hid_exist = false;
 		coex_sta->sco_exist = false;
 	} else {
-		/* connection exists*/
+		/* connection exists */
 		coex_sta->bt_link_exist = true;
 		if (bt_info & BT_INFO_8821A_1ANT_B_FTP)
 			coex_sta->pan_exist = true;
@@ -2858,14 +2814,19 @@ void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
 			coex_sta->sco_exist = false;
 	}
 
-	halbtc8821a1ant_update_bt_link_info(btcoexist);
+	btc8821a1ant_update_bt_link_info(btcoexist);
 
-	if (!(bt_info&BT_INFO_8821A_1ANT_B_CONNECTION)) {
+	/* mask profile bit for connect-ilde identification
+	 * (for CSR case: A2DP idle --> 0x41)
+	 */
+	bt_info = bt_info & 0x1f;
+
+	if (!(bt_info & BT_INFO_8821A_1ANT_B_CONNECTION)) {
 		coex_dm->bt_status = BT_8821A_1ANT_BT_STATUS_NON_CONNECTED_IDLE;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], BtInfoNotify(), BT Non-Connected idle!!!\n");
 	} else if (bt_info == BT_INFO_8821A_1ANT_B_CONNECTION) {
-		/* connection exists but no busy*/
+		/* connection exists but no busy */
 		coex_dm->bt_status = BT_8821A_1ANT_BT_STATUS_CONNECTED_IDLE;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], BtInfoNotify(), BT Connected-idle!!!\n");
@@ -2895,33 +2856,48 @@ void ex_halbtc8821a1ant_bt_info_notify(struct btc_coexist *btcoexist,
 	btcoexist->btc_set(btcoexist,
 			   BTC_SET_BL_BT_TRAFFIC_BUSY, &bt_busy);
 
-	halbtc8821a1ant_run_coexist_mechanism(btcoexist);
+	btc8821a1ant_run_coexist_mechanism(btcoexist);
 }
 
-void ex_halbtc8821a1ant_halt_notify(struct btc_coexist *btcoexist)
+void ex_btc8821a1ant_halt_notify(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	bool wifi_under_5g = false;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Halt notify\n");
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
+		return;
+	}
+
 
 	btcoexist->stop_coex_dm = true;
 
-	halbtc8821a1ant_set_ant_path(btcoexist,
-				     BTC_ANT_PATH_BT, false, true);
-	halbtc8821a1ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
+	btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT, false, true);
+	btc8821a1ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
 
-	halbtc8821a1ant_power_save_state(btcoexist,
-					 BTC_PS_WIFI_NATIVE, 0x0, 0x0);
-	halbtc8821a1ant_ps_tdma(btcoexist, FORCE_EXEC, false, 0);
+	btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8821a1ant_ps_tdma(btcoexist, FORCE_EXEC, false, 0);
 
-	ex_halbtc8821a1ant_media_status_notify(btcoexist,
-					       BTC_MEDIA_DISCONNECT);
+	ex_btc8821a1ant_media_status_notify(btcoexist, BTC_MEDIA_DISCONNECT);
 }
 
-void ex_halbtc8821a1ant_pnp_notify(struct btc_coexist *btcoexist, u8 pnp_state)
+void ex_btc8821a1ant_pnp_notify(struct btc_coexist *btcoexist, u8 pnp_state)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	bool wifi_under_5g = false;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	if (wifi_under_5g) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], RunCoexistMechanism(), return for 5G <===\n");
+		btc8821a1ant_coex_under_5g(btcoexist);
+		return;
+	}
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Pnp notify\n");
@@ -2929,26 +2905,33 @@ void ex_halbtc8821a1ant_pnp_notify(struct btc_coexist *btcoexist, u8 pnp_state)
 	if (BTC_WIFI_PNP_SLEEP == pnp_state) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Pnp notify to SLEEP\n");
+		/* BT should clear UnderIPS/UnderLPS state to avoid mismatch
+		 * state after wakeup.
+		 */
+		coex_sta->under_ips = false;
+		coex_sta->under_lps = false;
 		btcoexist->stop_coex_dm = true;
-		halbtc8821a1ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
-		halbtc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
-						 0x0, 0x0);
-		halbtc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 9);
+		btc8821a1ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a1ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
+		btc8821a1ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
+		btc8821a1ant_set_ant_path(btcoexist, BTC_ANT_PATH_BT, false,
+					  true);
 	} else if (BTC_WIFI_PNP_WAKE_UP == pnp_state) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Pnp notify to WAKE UP\n");
 		btcoexist->stop_coex_dm = false;
-		halbtc8821a1ant_init_hw_config(btcoexist, false);
-		halbtc8821a1ant_init_coex_dm(btcoexist);
-		halbtc8821a1ant_query_bt_info(btcoexist);
+		btc8821a1ant_init_hw_config(btcoexist, false, false);
+		btc8821a1ant_init_coex_dm(btcoexist);
+		btc8821a1ant_query_bt_info(btcoexist);
 	}
 }
 
-void ex_halbtc8821a1ant_periodical(struct btc_coexist *btcoexist)
+void ex_btc8821a1ant_periodical(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static u8	dis_ver_info_cnt;
-	u32		fw_ver = 0, bt_patch_ver = 0;
+	static u8 dis_ver_info_cnt;
+	u32 fw_ver = 0, bt_patch_ver = 0;
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	struct btc_stack_info *stack_info = &btcoexist->stack_info;
 
@@ -2982,16 +2965,9 @@ void ex_halbtc8821a1ant_periodical(struct btc_coexist *btcoexist)
 	}
 
 #if (BT_AUTO_REPORT_ONLY_8821A_1ANT == 0)
-	halbtc8821a1ant_query_bt_info(btcoexist);
-	halbtc8821a1ant_monitor_bt_ctr(btcoexist);
-	btc8821a1ant_mon_bt_en_dis(btcoexist);
+	btc8821a1ant_query_bt_info(btcoexist);
+	btc8821a1ant_monitor_bt_ctr(btcoexist);
 #else
-	if (halbtc8821a1ant_Is_wifi_status_changed(btcoexist) ||
-	    coex_dm->auto_tdma_adjust) {
-		if (coex_sta->special_pkt_period_cnt > 2)
-			halbtc8821a1ant_run_coexist_mechanism(btcoexist);
-	}
-
 	coex_sta->special_pkt_period_cnt++;
 #endif
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.h b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.h
index 20e904890fc2..1bd1ebe3364e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.h
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a1ant.h
@@ -140,13 +140,14 @@ struct coex_dm_8821a_1ant {
 };
 
 struct coex_sta_8821a_1ant {
+	bool	bt_disabled;
 	bool	bt_link_exist;
 	bool	sco_exist;
 	bool	a2dp_exist;
 	bool	hid_exist;
 	bool	pan_exist;
 
-	bool	under_Lps;
+	bool	under_lps;
 	bool	under_ips;
 	u32	special_pkt_period_cnt;
 	u32	high_priority_tx;
@@ -160,6 +161,7 @@ struct coex_sta_8821a_1ant {
 	u8	bt_info_c2h[BT_INFO_SRC_8821A_1ANT_MAX][10];
 	u32	bt_info_c2h_cnt[BT_INFO_SRC_8821A_1ANT_MAX];
 	bool	c2h_bt_inquiry_page;
+	bool	wifi_is_high_pri_task;
 	u8	bt_retry_cnt;
 	u8	bt_info_ext;
 };
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c
index 1717e9ce96ca..841b4a83ab70 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c
@@ -23,7 +23,7 @@
  *
  *****************************************************************************/
 
-/*============================================================
+/************************************************************
  * Description:
  *
  * This file is for RTL8821A Co-exist mechanism
@@ -32,22 +32,19 @@
  * 2012/08/22 Cosa first check in.
  * 2012/11/14 Cosa Revise for 8821A 2Ant out sourcing.
  *
- *============================================================
- */
+ ************************************************************/
 
-/*============================================================
+/************************************************************
  * include files
- *============================================================
-*/
+ ************************************************************/
 #include "halbt_precomp.h"
-/*============================================================
+/************************************************************
  * Global variables, these are static variables
- *============================================================
- */
-static struct coex_dm_8821a_2ant	glcoex_dm_8821a_2ant;
-static struct coex_dm_8821a_2ant	*coex_dm = &glcoex_dm_8821a_2ant;
-static struct coex_sta_8821a_2ant	glcoex_sta_8821a_2ant;
-static struct coex_sta_8821a_2ant	*coex_sta = &glcoex_sta_8821a_2ant;
+ ************************************************************/
+static struct coex_dm_8821a_2ant glcoex_dm_8821a_2ant;
+static struct coex_dm_8821a_2ant *coex_dm = &glcoex_dm_8821a_2ant;
+static struct coex_sta_8821a_2ant glcoex_sta_8821a_2ant;
+static struct coex_sta_8821a_2ant *coex_sta = &glcoex_sta_8821a_2ant;
 
 static const char *const glbt_info_src_8821a_2ant[] = {
 	"BT Info[wifi fw]",
@@ -55,32 +52,29 @@ static const char *const glbt_info_src_8821a_2ant[] = {
 	"BT Info[bt auto report]",
 };
 
-static u32	glcoex_ver_date_8821a_2ant = 20130618;
-static u32	glcoex_ver_8821a_2ant = 0x5050;
+static u32 glcoex_ver_date_8821a_2ant = 20130618;
+static u32 glcoex_ver_8821a_2ant = 0x5050;
 
-/*============================================================
+/************************************************************
  * local function proto type if needed
- *============================================================
- *============================================================
- * local function start with halbtc8821a2ant_
- *============================================================
- */
-static u8 halbtc8821a2ant_bt_rssi_state(struct btc_coexist *btcoexist,
-					u8 level_num, u8 rssi_thresh,
-					u8 rssi_thresh1)
+ *
+ * local function start with btc8821a2ant_
+ ************************************************************/
+static u8 btc8821a2ant_bt_rssi_state(struct btc_coexist *btcoexist,
+				     u8 level_num, u8 rssi_thresh,
+				     u8 rssi_thresh1)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	long	bt_rssi = 0;
-	u8	bt_rssi_state = coex_sta->pre_bt_rssi_state;
+	long bt_rssi = 0;
+	u8 bt_rssi_state = coex_sta->pre_bt_rssi_state;
 
 	bt_rssi = coex_sta->bt_rssi;
 
 	if (level_num == 2) {
 		if ((coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
-			long tmp = rssi_thresh +
-				   BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT;
-			if (bt_rssi >= tmp) {
+			if (bt_rssi >=
+			    rssi_thresh + BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT) {
 				bt_rssi_state = BTC_RSSI_STATE_HIGH;
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], BT Rssi state switch to High\n");
@@ -110,7 +104,8 @@ static u8 halbtc8821a2ant_bt_rssi_state(struct btc_coexist *btcoexist,
 		if ((coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_LOW) ||
 		    (coex_sta->pre_bt_rssi_state == BTC_RSSI_STATE_STAY_LOW)) {
 			if (bt_rssi >=
-			    (rssi_thresh+BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT)) {
+			    (rssi_thresh +
+			     BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT)) {
 				bt_rssi_state = BTC_RSSI_STATE_MEDIUM;
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], BT Rssi state switch to Medium\n");
@@ -156,13 +151,13 @@ static u8 halbtc8821a2ant_bt_rssi_state(struct btc_coexist *btcoexist,
 	return bt_rssi_state;
 }
 
-static u8 halbtc8821a2ant_wifi_rssi_state(struct btc_coexist *btcoexist,
-					  u8 index, u8 level_num,
-					  u8 rssi_thresh, u8 rssi_thresh1)
+static u8 btc8821a2ant_wifi_rssi_state(struct btc_coexist *btcoexist,
+				       u8 index, u8 level_num,
+				       u8 rssi_thresh, u8 rssi_thresh1)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	long	wifi_rssi = 0;
-	u8	wifi_rssi_state = coex_sta->pre_wifi_rssi_state[index];
+	long wifi_rssi = 0;
+	u8 wifi_rssi_state = coex_sta->pre_wifi_rssi_state[index];
 
 	btcoexist->btc_get(btcoexist, BTC_GET_S4_WIFI_RSSI, &wifi_rssi);
 
@@ -204,7 +199,8 @@ static u8 halbtc8821a2ant_wifi_rssi_state(struct btc_coexist *btcoexist,
 		    (coex_sta->pre_wifi_rssi_state[index] ==
 		     BTC_RSSI_STATE_STAY_LOW)) {
 			if (wifi_rssi >=
-			    (rssi_thresh+BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT)) {
+			    (rssi_thresh +
+			     BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT)) {
 				wifi_rssi_state = BTC_RSSI_STATE_MEDIUM;
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], wifi RSSI state switch to Medium\n");
@@ -248,76 +244,57 @@ static u8 halbtc8821a2ant_wifi_rssi_state(struct btc_coexist *btcoexist,
 	return wifi_rssi_state;
 }
 
-static void btc8821a2ant_mon_bt_en_dis(struct btc_coexist *btcoexist)
+static
+void btc8821a2ant_limited_rx(struct btc_coexist *btcoexist, bool force_exec,
+			     bool rej_ap_agg_pkt, bool bt_ctrl_agg_buf_size,
+			     u8 agg_buf_size)
 {
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static bool	pre_bt_disabled;
-	static u32	bt_disable_cnt;
-	bool		bt_active = true, bt_disabled = false;
-
-	/* This function check if bt is disabled*/
-
-	if (coex_sta->high_priority_tx == 0 &&
-	    coex_sta->high_priority_rx == 0 &&
-	    coex_sta->low_priority_tx == 0 &&
-	    coex_sta->low_priority_rx == 0)
-		bt_active = false;
-	if (coex_sta->high_priority_tx == 0xffff &&
-	    coex_sta->high_priority_rx == 0xffff &&
-	    coex_sta->low_priority_tx == 0xffff &&
-	    coex_sta->low_priority_rx == 0xffff)
-		bt_active = false;
-	if (bt_active) {
-		bt_disable_cnt = 0;
-		bt_disabled = false;
-		btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_DISABLE,
-				   &bt_disabled);
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BT is enabled !!\n");
-	} else {
-		bt_disable_cnt++;
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], bt all counters = 0, %d times!!\n",
-			 bt_disable_cnt);
-		if (bt_disable_cnt >= 2) {
-			bt_disabled = true;
-			btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_DISABLE,
-					   &bt_disabled);
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], BT is disabled !!\n");
-		}
-	}
-	if (pre_bt_disabled != bt_disabled) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BT is from %s to %s!!\n",
-			 (pre_bt_disabled ? "disabled" : "enabled"),
-			 (bt_disabled ? "disabled" : "enabled"));
-		pre_bt_disabled = bt_disabled;
-	}
+	bool reject_rx_agg = rej_ap_agg_pkt;
+	bool bt_ctrl_rx_agg_size = bt_ctrl_agg_buf_size;
+	u8 rx_agg_size = agg_buf_size;
+
+	/* Rx Aggregation related setting */
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_TO_REJ_AP_AGG_PKT,
+			   &reject_rx_agg);
+	/* decide BT control aggregation buf size or not */
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_BT_CTRL_AGG_SIZE,
+			   &bt_ctrl_rx_agg_size);
+	/* aggregation buf size, works when BT control Rx aggregation size */
+	btcoexist->btc_set(btcoexist, BTC_SET_U1_AGG_BUF_SIZE, &rx_agg_size);
+	/* real update aggregation setting */
+	btcoexist->btc_set(btcoexist, BTC_SET_ACT_AGGREGATE_CTRL, NULL);
 }
 
-static void halbtc8821a2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
+static void btc8821a2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u32	reg_hp_txrx, reg_lp_txrx, u4tmp;
-	u32	reg_hp_tx = 0, reg_hp_rx = 0, reg_lp_tx = 0, reg_lp_rx = 0;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+	u32 reg_hp_txrx, reg_lp_txrx, u4tmp;
+	u32 reg_hp_tx = 0, reg_hp_rx = 0, reg_lp_tx = 0, reg_lp_rx = 0;
 
 	reg_hp_txrx = 0x770;
 	reg_lp_txrx = 0x774;
 
 	u4tmp = btcoexist->btc_read_4byte(btcoexist, reg_hp_txrx);
 	reg_hp_tx = u4tmp & MASKLWORD;
-	reg_hp_rx = (u4tmp & MASKHWORD)>>16;
+	reg_hp_rx = (u4tmp & MASKHWORD) >> 16;
 
 	u4tmp = btcoexist->btc_read_4byte(btcoexist, reg_lp_txrx);
 	reg_lp_tx = u4tmp & MASKLWORD;
-	reg_lp_rx = (u4tmp & MASKHWORD)>>16;
+	reg_lp_rx = (u4tmp & MASKHWORD) >> 16;
 
 	coex_sta->high_priority_tx = reg_hp_tx;
 	coex_sta->high_priority_rx = reg_hp_rx;
 	coex_sta->low_priority_tx = reg_lp_tx;
 	coex_sta->low_priority_rx = reg_lp_rx;
 
+	if ((coex_sta->low_priority_rx >= 950) &&
+	    (coex_sta->low_priority_rx >= coex_sta->low_priority_tx) &&
+	    (!coex_sta->under_ips))
+		bt_link_info->slave_role = true;
+	else
+		bt_link_info->slave_role = false;
+
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], High Priority Tx/Rx (reg 0x%x) = 0x%x(%d)/0x%x(%d)\n",
 		    reg_hp_txrx, reg_hp_tx, reg_hp_tx, reg_hp_rx, reg_hp_rx);
@@ -329,14 +306,51 @@ static void halbtc8821a2ant_monitor_bt_ctr(struct btc_coexist *btcoexist)
 	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
 }
 
-static void halbtc8821a2ant_query_bt_info(struct btc_coexist *btcoexist)
+static void btc8821a2ant_monitor_wifi_ctr(struct btc_coexist *btcoexist)
+{
+	if (coex_sta->under_ips) {
+		coex_sta->crc_ok_cck = 0;
+		coex_sta->crc_ok_11g = 0;
+		coex_sta->crc_ok_11n = 0;
+		coex_sta->crc_ok_11n_agg = 0;
+
+		coex_sta->crc_err_cck = 0;
+		coex_sta->crc_err_11g = 0;
+		coex_sta->crc_err_11n = 0;
+		coex_sta->crc_err_11n_agg = 0;
+	} else {
+		coex_sta->crc_ok_cck =
+			btcoexist->btc_read_4byte(btcoexist, 0xf88);
+		coex_sta->crc_ok_11g =
+			btcoexist->btc_read_2byte(btcoexist, 0xf94);
+		coex_sta->crc_ok_11n =
+			btcoexist->btc_read_2byte(btcoexist, 0xf90);
+		coex_sta->crc_ok_11n_agg =
+			btcoexist->btc_read_2byte(btcoexist, 0xfb8);
+
+		coex_sta->crc_err_cck =
+			btcoexist->btc_read_4byte(btcoexist, 0xf84);
+		coex_sta->crc_err_11g =
+			btcoexist->btc_read_2byte(btcoexist, 0xf96);
+		coex_sta->crc_err_11n =
+			btcoexist->btc_read_2byte(btcoexist, 0xf92);
+		coex_sta->crc_err_11n_agg =
+			btcoexist->btc_read_2byte(btcoexist, 0xfba);
+	}
+
+	/* reset counter */
+	btcoexist->btc_write_1byte_bitmask(btcoexist, 0xf16, 0x1, 0x1);
+	btcoexist->btc_write_1byte_bitmask(btcoexist, 0xf16, 0x1, 0x0);
+}
+
+static void btc8821a2ant_query_bt_info(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
 	coex_sta->c2h_bt_info_req_sent = true;
 
-	h2c_parameter[0] |= BIT0;	/* trigger */
+	h2c_parameter[0] |= BIT0; /* trigger */
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Query Bt Info, FW write 0x61 = 0x%x\n",
@@ -345,54 +359,135 @@ static void halbtc8821a2ant_query_bt_info(struct btc_coexist *btcoexist)
 	btcoexist->btc_fill_h2c(btcoexist, 0x61, 1, h2c_parameter);
 }
 
-static u8 halbtc8821a2ant_action_algorithm(struct btc_coexist *btcoexist)
+bool btc8821a2ant_is_wifi_status_changed(struct btc_coexist *btcoexist)
+{
+	static bool pre_wifi_busy = true;
+	static bool pre_under_4way = true;
+	static bool pre_bt_hs_on = true;
+	bool wifi_busy = false, under_4way = false, bt_hs_on = false;
+	bool wifi_connected = false;
+	u8 wifi_rssi_state = BTC_RSSI_STATE_HIGH;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
+			   &wifi_connected);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_4_WAY_PROGRESS,
+			   &under_4way);
+
+	if (wifi_connected) {
+		if (wifi_busy != pre_wifi_busy) {
+			pre_wifi_busy = wifi_busy;
+			return true;
+		}
+		if (under_4way != pre_under_4way) {
+			pre_under_4way = under_4way;
+			return true;
+		}
+		if (bt_hs_on != pre_bt_hs_on) {
+			pre_bt_hs_on = bt_hs_on;
+			return true;
+		}
+
+		wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 3, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+
+		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (wifi_rssi_state == BTC_RSSI_STATE_LOW))
+			return true;
+	}
+
+	return false;
+}
+
+static void btc8821a2ant_update_bt_link_info(struct btc_coexist *btcoexist)
+{
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+	bool bt_hs_on = false;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
+
+	bt_link_info->bt_link_exist = coex_sta->bt_link_exist;
+	bt_link_info->sco_exist = coex_sta->sco_exist;
+	bt_link_info->a2dp_exist = coex_sta->a2dp_exist;
+	bt_link_info->pan_exist = coex_sta->pan_exist;
+	bt_link_info->hid_exist = coex_sta->hid_exist;
+
+	/* work around for HS mode. */
+	if (bt_hs_on) {
+		bt_link_info->pan_exist = true;
+		bt_link_info->bt_link_exist = true;
+	}
+
+	/* check if Sco only */
+	if (bt_link_info->sco_exist && !bt_link_info->a2dp_exist &&
+	    !bt_link_info->pan_exist && !bt_link_info->hid_exist)
+		bt_link_info->sco_only = true;
+	else
+		bt_link_info->sco_only = false;
+
+	/* check if A2dp only */
+	if (!bt_link_info->sco_exist && bt_link_info->a2dp_exist &&
+	    !bt_link_info->pan_exist && !bt_link_info->hid_exist)
+		bt_link_info->a2dp_only = true;
+	else
+		bt_link_info->a2dp_only = false;
+
+	/* check if Pan only */
+	if (!bt_link_info->sco_exist && !bt_link_info->a2dp_exist &&
+	    bt_link_info->pan_exist && !bt_link_info->hid_exist)
+		bt_link_info->pan_only = true;
+	else
+		bt_link_info->pan_only = false;
+
+	/* check if Hid only */
+	if (!bt_link_info->sco_exist && !bt_link_info->a2dp_exist &&
+	    !bt_link_info->pan_exist && bt_link_info->hid_exist)
+		bt_link_info->hid_only = true;
+	else
+		bt_link_info->hid_only = false;
+}
+
+static u8 btc8821a2ant_action_algorithm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	struct btc_stack_info *stack_info = &btcoexist->stack_info;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
 	bool bt_hs_on = false;
 	u8 algorithm = BT_8821A_2ANT_COEX_ALGO_UNDEFINED;
 	u8 num_of_diff_profile = 0;
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
 
-	/*for win-8 stack HID report error*/
-	/* sync  BTInfo with BT firmware and stack */
-	if (!stack_info->hid_exist)
-		stack_info->hid_exist = coex_sta->hid_exist;
-	/* when stack HID report error, here we use the info from bt fw. */
-	if (!stack_info->bt_link_exist)
-		stack_info->bt_link_exist = coex_sta->bt_link_exist;
-
-	if (!coex_sta->bt_link_exist) {
+	if (!bt_link_info->bt_link_exist) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], No profile exists!!!\n");
+			"[BTCoex], No BT link exists!!!\n");
 		return algorithm;
 	}
 
-	if (coex_sta->sco_exist)
+	if (bt_link_info->sco_exist)
 		num_of_diff_profile++;
-	if (coex_sta->hid_exist)
+	if (bt_link_info->hid_exist)
 		num_of_diff_profile++;
-	if (coex_sta->pan_exist)
+	if (bt_link_info->pan_exist)
 		num_of_diff_profile++;
-	if (coex_sta->a2dp_exist)
+	if (bt_link_info->a2dp_exist)
 		num_of_diff_profile++;
 
 	if (num_of_diff_profile == 1) {
-		if (coex_sta->sco_exist) {
+		if (bt_link_info->sco_exist) {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], SCO only\n");
 			algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 		} else {
-			if (coex_sta->hid_exist) {
+			if (bt_link_info->hid_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], HID only\n");
 				algorithm = BT_8821A_2ANT_COEX_ALGO_HID;
-			} else if (coex_sta->a2dp_exist) {
+			} else if (bt_link_info->a2dp_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], A2DP only\n");
 				algorithm = BT_8821A_2ANT_COEX_ALGO_A2DP;
-			} else if (coex_sta->pan_exist) {
+			} else if (bt_link_info->pan_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
@@ -407,16 +502,16 @@ static u8 halbtc8821a2ant_action_algorithm(struct btc_coexist *btcoexist)
 			}
 		}
 	} else if (num_of_diff_profile == 2) {
-		if (coex_sta->sco_exist) {
-			if (coex_sta->hid_exist) {
+		if (bt_link_info->sco_exist) {
+			if (bt_link_info->hid_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], SCO + HID\n");
-				algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
-			} else if (coex_sta->a2dp_exist) {
+				algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
+			} else if (bt_link_info->a2dp_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], SCO + A2DP ==> SCO\n");
-				algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
-			} else if (coex_sta->pan_exist) {
+				algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
+			} else if (bt_link_info->pan_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
@@ -426,99 +521,104 @@ static u8 halbtc8821a2ant_action_algorithm(struct btc_coexist *btcoexist)
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], SCO + PAN(EDR)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 				}
 			}
 		} else {
-			if (coex_sta->hid_exist &&
-			    coex_sta->a2dp_exist) {
+			if (bt_link_info->hid_exist &&
+			    bt_link_info->a2dp_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], HID + A2DP\n");
 				algorithm = BT_8821A_2ANT_COEX_ALGO_HID_A2DP;
-			} else if (coex_sta->hid_exist &&
-				coex_sta->pan_exist) {
+			} else if (bt_link_info->hid_exist &&
+				bt_link_info->pan_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], HID + PAN(HS)\n");
-					algorithm =  BT_8821A_2ANT_COEX_ALGO_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_HID;
 				} else {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], HID + PAN(EDR)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm =
+					    BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
 				}
-			} else if (coex_sta->pan_exist &&
-				coex_sta->a2dp_exist) {
+			} else if (bt_link_info->pan_exist &&
+				bt_link_info->a2dp_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], A2DP + PAN(HS)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_A2DP_PANHS;
+					algorithm =
+					    BT_8821A_2ANT_COEX_ALGO_A2DP_PANHS;
 				} else {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], A2DP + PAN(EDR)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_A2DP;
+					algorithm =
+					    BT_8821A_2ANT_COEX_ALGO_PANEDR_A2DP;
 				}
 			}
 		}
 	} else if (num_of_diff_profile == 3) {
-		if (coex_sta->sco_exist) {
-			if (coex_sta->hid_exist &&
-			    coex_sta->a2dp_exist) {
+		if (bt_link_info->sco_exist) {
+			if (bt_link_info->hid_exist &&
+			    bt_link_info->a2dp_exist) {
 				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 					 "[BTCoex], SCO + HID + A2DP ==> HID\n");
-				algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
-			} else if (coex_sta->hid_exist &&
-				coex_sta->pan_exist) {
+				algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
+			} else if (bt_link_info->hid_exist &&
+				bt_link_info->pan_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], SCO + HID + PAN(HS)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 				} else {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], SCO + HID + PAN(EDR)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 				}
-			} else if (coex_sta->pan_exist &&
-				   coex_sta->a2dp_exist) {
+			} else if (bt_link_info->pan_exist &&
+				   bt_link_info->a2dp_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], SCO + A2DP + PAN(HS)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 				} else {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], SCO + A2DP + PAN(EDR) ==> HID\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 				}
 			}
 		} else {
-			if (coex_sta->hid_exist &&
-			    coex_sta->pan_exist &&
-			    coex_sta->a2dp_exist) {
+			if (bt_link_info->hid_exist &&
+			    bt_link_info->pan_exist &&
+			    bt_link_info->a2dp_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], HID + A2DP + PAN(HS)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_HID_A2DP;
+					algorithm =
+					    BT_8821A_2ANT_COEX_ALGO_HID_A2DP;
 				} else {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], HID + A2DP + PAN(EDR)\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_HID_A2DP_PANEDR;
+					algorithm =
+					BT_8821A_2ANT_COEX_ALGO_HID_A2DP_PANEDR;
 				}
 			}
 		}
 	} else if (num_of_diff_profile >= 3) {
-		if (coex_sta->sco_exist) {
-			if (coex_sta->hid_exist &&
-			    coex_sta->pan_exist &&
-			    coex_sta->a2dp_exist) {
+		if (bt_link_info->sco_exist) {
+			if (bt_link_info->hid_exist &&
+			    bt_link_info->pan_exist &&
+			    bt_link_info->a2dp_exist) {
 				if (bt_hs_on) {
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
@@ -528,7 +628,7 @@ static u8 halbtc8821a2ant_action_algorithm(struct btc_coexist *btcoexist)
 					RT_TRACE(rtlpriv, COMP_BT_COEXIST,
 						 DBG_LOUD,
 						 "[BTCoex], SCO + HID + A2DP + PAN(EDR)==>PAN(EDR)+HID\n");
-					algorithm = BT_8821A_2ANT_COEX_ALGO_PANEDR_HID;
+					algorithm = BT_8821A_2ANT_COEX_ALGO_SCO;
 				}
 			}
 		}
@@ -536,44 +636,7 @@ static u8 halbtc8821a2ant_action_algorithm(struct btc_coexist *btcoexist)
 	return algorithm;
 }
 
-static bool halbtc8821a2ant_need_to_dec_bt_pwr(struct btc_coexist *btcoexist)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool ret = false;
-	bool bt_hs_on = false, wifi_connected = false;
-	long bt_hs_rssi = 0;
-	u8 bt_rssi_state;
-
-	if (!btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on))
-		return false;
-	if (!btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
-				&wifi_connected))
-		return false;
-	if (!btcoexist->btc_get(btcoexist, BTC_GET_S4_HS_RSSI, &bt_hs_rssi))
-		return false;
-
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
-
-	if (wifi_connected) {
-		if (bt_hs_on) {
-			if (bt_hs_rssi > 37) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Need to decrease bt power for HS mode!!\n");
-				ret = true;
-			}
-		} else {
-			if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-			    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-					 "[BTCoex], Need to decrease bt power for Wifi is connected!!\n");
-				ret = true;
-			}
-		}
-	}
-	return ret;
-}
-
-static void btc8821a2ant_set_fw_dac_swing_lev(struct btc_coexist *btcoexist,
+static void btc8821a2ant_set_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
 					      u8 dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
@@ -592,185 +655,47 @@ static void btc8821a2ant_set_fw_dac_swing_lev(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x64, 1, h2c_parameter);
 }
 
-static void halbtc8821a2ant_set_fw_dec_bt_pwr(struct btc_coexist *btcoexist,
-					      bool dec_bt_pwr)
+static void btc8821a2ant_set_fw_dec_bt_pwr(struct btc_coexist *btcoexist,
+					   u8 dec_bt_pwr_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[1] = {0};
 
-	h2c_parameter[0] = 0;
-
-	if (dec_bt_pwr)
-		h2c_parameter[0] |= BIT1;
+	h2c_parameter[0] = dec_bt_pwr_lvl;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], decrease Bt Power : %s, FW write 0x62 = 0x%x\n",
-		 (dec_bt_pwr ? "Yes!!" : "No!!"), h2c_parameter[0]);
+		 "[BTCoex], decrease Bt Power Level : %u, FW write 0x62 = 0x%x\n",
+		 dec_bt_pwr_lvl, h2c_parameter[0]);
 
 	btcoexist->btc_fill_h2c(btcoexist, 0x62, 1, h2c_parameter);
 }
 
-static void halbtc8821a2ant_dec_bt_pwr(struct btc_coexist *btcoexist,
-				       bool force_exec, bool dec_bt_pwr)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s Dec BT power = %s\n",
-		    (force_exec ? "force to" : ""),
-		    ((dec_bt_pwr) ? "ON" : "OFF"));
-	coex_dm->cur_dec_bt_pwr = dec_bt_pwr;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_dec_bt_pwr = %d, cur_dec_bt_pwr = %d\n",
-			    coex_dm->pre_dec_bt_pwr, coex_dm->cur_dec_bt_pwr);
-
-		if (coex_dm->pre_dec_bt_pwr == coex_dm->cur_dec_bt_pwr)
-			return;
-	}
-	halbtc8821a2ant_set_fw_dec_bt_pwr(btcoexist, coex_dm->cur_dec_bt_pwr);
-
-	coex_dm->pre_dec_bt_pwr = coex_dm->cur_dec_bt_pwr;
-}
-
-static void btc8821a2ant_set_fw_bt_lna_constr(struct btc_coexist *btcoexist,
-					      bool bt_lna_cons_on)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 h2c_parameter[2] = {0};
-
-	h2c_parameter[0] = 0x3;	/* opCode, 0x3 = BT_SET_LNA_CONSTRAIN */
-
-	if (bt_lna_cons_on)
-		h2c_parameter[1] |= BIT0;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], set BT LNA Constrain: %s, FW write 0x69 = 0x%x\n",
-		 bt_lna_cons_on ? "ON!!" : "OFF!!",
-		 h2c_parameter[0] << 8 | h2c_parameter[1]);
-
-	btcoexist->btc_fill_h2c(btcoexist, 0x69, 2, h2c_parameter);
-}
-
-static void btc8821a2_set_bt_lna_const(struct btc_coexist *btcoexist,
-				       bool force_exec, bool bt_lna_cons_on)
+static void btc8821a2ant_dec_bt_pwr(struct btc_coexist *btcoexist,
+				    bool force_exec, u8 dec_bt_pwr_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s BT Constrain = %s\n",
-		 (force_exec ? "force" : ""),
-		 ((bt_lna_cons_on) ? "ON" : "OFF"));
-	coex_dm->cur_bt_lna_constrain = bt_lna_cons_on;
+		 "[BTCoex], %s Dec BT power level = %u\n",
+		    (force_exec ? "force to" : ""), dec_bt_pwr_lvl);
+	coex_dm->cur_dec_bt_pwr_lvl = dec_bt_pwr_lvl;
 
 	if (!force_exec) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_bt_lna_constrain = %d,cur_bt_lna_constrain = %d\n",
-			    coex_dm->pre_bt_lna_constrain,
-			    coex_dm->cur_bt_lna_constrain);
+			 "[BTCoex], pre_dec_bt_pwr_lvl = %d, cur_dec_bt_pwr_lvl = %d\n",
+			    coex_dm->pre_dec_bt_pwr_lvl,
+			    coex_dm->cur_dec_bt_pwr_lvl);
 
-		if (coex_dm->pre_bt_lna_constrain ==
-		    coex_dm->cur_bt_lna_constrain)
+		if (coex_dm->pre_dec_bt_pwr_lvl == coex_dm->cur_dec_bt_pwr_lvl)
 			return;
 	}
-	btc8821a2ant_set_fw_bt_lna_constr(btcoexist,
-					  coex_dm->cur_bt_lna_constrain);
-
-	coex_dm->pre_bt_lna_constrain = coex_dm->cur_bt_lna_constrain;
-}
-
-static void halbtc8821a2ant_set_fw_bt_psd_mode(struct btc_coexist *btcoexist,
-					       u8 bt_psd_mode)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 h2c_parameter[2] = {0};
+	btc8821a2ant_set_fw_dec_bt_pwr(btcoexist, coex_dm->cur_dec_bt_pwr_lvl);
 
-	h2c_parameter[0] = 0x2;	/* opCode, 0x2 = BT_SET_PSD_MODE */
-
-	h2c_parameter[1] = bt_psd_mode;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], set BT PSD mode = 0x%x, FW write 0x69 = 0x%x\n",
-		 h2c_parameter[1],
-		 h2c_parameter[0] << 8 | h2c_parameter[1]);
-
-	btcoexist->btc_fill_h2c(btcoexist, 0x69, 2, h2c_parameter);
+	coex_dm->pre_dec_bt_pwr_lvl = coex_dm->cur_dec_bt_pwr_lvl;
 }
 
-static void halbtc8821a2ant_set_bt_psd_mode(struct btc_coexist *btcoexist,
-					    bool force_exec, u8 bt_psd_mode)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s BT PSD mode = 0x%x\n",
-		 (force_exec ? "force" : ""), bt_psd_mode);
-	coex_dm->cur_bt_psd_mode = bt_psd_mode;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_bt_psd_mode = 0x%x, cur_bt_psd_mode = 0x%x\n",
-			 coex_dm->pre_bt_psd_mode, coex_dm->cur_bt_psd_mode);
-
-		if (coex_dm->pre_bt_psd_mode == coex_dm->cur_bt_psd_mode)
-			return;
-	}
-	halbtc8821a2ant_set_fw_bt_psd_mode(btcoexist,
-					   coex_dm->cur_bt_psd_mode);
-
-	coex_dm->pre_bt_psd_mode = coex_dm->cur_bt_psd_mode;
-}
-
-static void halbtc8821a2ant_set_bt_auto_report(struct btc_coexist *btcoexist,
-					       bool enable_auto_report)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8 h2c_parameter[1] = {0};
-
-	h2c_parameter[0] = 0;
-
-	if (enable_auto_report)
-		h2c_parameter[0] |= BIT0;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], BT FW auto report : %s, FW write 0x68 = 0x%x\n",
-		 (enable_auto_report ? "Enabled!!" : "Disabled!!"),
-		 h2c_parameter[0]);
-
-	btcoexist->btc_fill_h2c(btcoexist, 0x68, 1, h2c_parameter);
-}
-
-static void halbtc8821a2ant_bt_auto_report(struct btc_coexist *btcoexist,
-					   bool force_exec,
-					   bool enable_auto_report)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s BT Auto report = %s\n",
-		 (force_exec ? "force to" : ""),
-		 ((enable_auto_report) ? "Enabled" : "Disabled"));
-	coex_dm->cur_bt_auto_report = enable_auto_report;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_bt_auto_report = %d, cur_bt_auto_report = %d\n",
-			    coex_dm->pre_bt_auto_report,
-			    coex_dm->cur_bt_auto_report);
-
-		if (coex_dm->pre_bt_auto_report == coex_dm->cur_bt_auto_report)
-			return;
-	}
-	halbtc8821a2ant_set_bt_auto_report(btcoexist,
-					   coex_dm->cur_bt_auto_report);
-
-	coex_dm->pre_bt_auto_report = coex_dm->cur_bt_auto_report;
-}
-
-static void halbtc8821a2ant_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
-					     bool force_exec,
-					     u8 fw_dac_swing_lvl)
+static void btc8821a2ant_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
+					  bool force_exec, u8 fw_dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -790,66 +715,14 @@ static void halbtc8821a2ant_fw_dac_swing_lvl(struct btc_coexist *btcoexist,
 			return;
 	}
 
-	btc8821a2ant_set_fw_dac_swing_lev(btcoexist,
+	btc8821a2ant_set_fw_dac_swing_lvl(btcoexist,
 					  coex_dm->cur_fw_dac_swing_lvl);
 
 	coex_dm->pre_fw_dac_swing_lvl = coex_dm->cur_fw_dac_swing_lvl;
 }
 
-static void btc8821a2ant_set_sw_rf_rx_lpf_corner(struct btc_coexist *btcoexist,
-						 bool rx_rf_shrink_on)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	if (rx_rf_shrink_on) {
-		/* Shrink RF Rx LPF corner */
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Shrink RF Rx LPF corner!!\n");
-		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1e,
-					  0xfffff, 0xffffc);
-	} else {
-		/* Resume RF Rx LPF corner
-		 * After initialized, we can use coex_dm->bt_rf0x1e_backup
-		 */
-		if (btcoexist->initilized) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Resume RF Rx LPF corner!!\n");
-			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A,
-						  0x1e, 0xfffff,
-						   coex_dm->bt_rf0x1e_backup);
-		}
-	}
-}
-
-static void halbtc8821a2ant_RfShrink(struct btc_coexist *btcoexist,
-				     bool force_exec, bool rx_rf_shrink_on)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s turn Rx RF Shrink = %s\n",
-		    (force_exec ? "force to" : ""),
-		    ((rx_rf_shrink_on) ? "ON" : "OFF"));
-	coex_dm->cur_rf_rx_lpf_shrink = rx_rf_shrink_on;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_rf_rx_lpf_shrink = %d, cur_rf_rx_lpf_shrink = %d\n",
-			 coex_dm->pre_rf_rx_lpf_shrink,
-			 coex_dm->cur_rf_rx_lpf_shrink);
-
-		if (coex_dm->pre_rf_rx_lpf_shrink ==
-		    coex_dm->cur_rf_rx_lpf_shrink)
-			return;
-	}
-	btc8821a2ant_set_sw_rf_rx_lpf_corner(btcoexist,
-					     coex_dm->cur_rf_rx_lpf_shrink);
-
-	coex_dm->pre_rf_rx_lpf_shrink = coex_dm->cur_rf_rx_lpf_shrink;
-}
-
-static void btc8821a2ant_SetSwPenTxRateAdapt(struct btc_coexist *btcoexist,
-					     bool low_penalty_ra)
+static void btc8821a2ant_set_sw_penalty_tx_rate_adaptive(
+		struct btc_coexist *btcoexist, bool low_penalty_ra)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[6] = {0};
@@ -858,14 +731,14 @@ static void btc8821a2ant_SetSwPenTxRateAdapt(struct btc_coexist *btcoexist,
 
 	if (low_penalty_ra) {
 		h2c_parameter[1] |= BIT0;
-		/*normal rate except MCS7/6/5, OFDM54/48/36 */
+		/* normal rate except MCS7/6/5, OFDM54/48/36 */
 		h2c_parameter[2] = 0x00;
-		/*MCS7 or OFDM54 */
-		h2c_parameter[3] = 0xf7;
-		/*MCS6 or OFDM48 */
-		h2c_parameter[4] = 0xf8;
-		/*MCS5 or OFDM36 */
-		h2c_parameter[5] = 0xf9;
+		/* MCS7 or OFDM54 */
+		h2c_parameter[3] = 0xf5;
+		/* MCS6 or OFDM48 */
+		h2c_parameter[4] = 0xa0;
+		/* MCS5 or OFDM36 */
+		h2c_parameter[5] = 0xa0;
 	}
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -875,12 +748,11 @@ static void btc8821a2ant_SetSwPenTxRateAdapt(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x69, 6, h2c_parameter);
 }
 
-static void halbtc8821a2ant_low_penalty_ra(struct btc_coexist *btcoexist,
-					   bool force_exec, bool low_penalty_ra)
+static void btc8821a2ant_low_penalty_ra(struct btc_coexist *btcoexist,
+					bool force_exec, bool low_penalty_ra)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
-	/*return;*/
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s turn LowPenaltyRA = %s\n",
 		 (force_exec ? "force to" : ""),
@@ -891,19 +763,19 @@ static void halbtc8821a2ant_low_penalty_ra(struct btc_coexist *btcoexist,
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], pre_low_penalty_ra = %d, cur_low_penalty_ra = %d\n",
 			 coex_dm->pre_low_penalty_ra,
-			    coex_dm->cur_low_penalty_ra);
+			 coex_dm->cur_low_penalty_ra);
 
 		if (coex_dm->pre_low_penalty_ra == coex_dm->cur_low_penalty_ra)
 			return;
 	}
-	btc8821a2ant_SetSwPenTxRateAdapt(btcoexist,
+	btc8821a2ant_set_sw_penalty_tx_rate_adaptive(btcoexist,
 					 coex_dm->cur_low_penalty_ra);
 
 	coex_dm->pre_low_penalty_ra = coex_dm->cur_low_penalty_ra;
 }
 
-static void halbtc8821a2ant_set_dac_swing_reg(struct btc_coexist *btcoexist,
-					      u32 level)
+static void btc8821a2ant_set_dac_swing_reg(struct btc_coexist *btcoexist,
+					   u32 level)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 val = (u8)level;
@@ -918,14 +790,14 @@ static void btc8821a2ant_set_sw_full_dac_swing(struct btc_coexist *btcoexist,
 					       u32 sw_dac_swing_lvl)
 {
 	if (sw_dac_swing_on)
-		halbtc8821a2ant_set_dac_swing_reg(btcoexist, sw_dac_swing_lvl);
+		btc8821a2ant_set_dac_swing_reg(btcoexist, sw_dac_swing_lvl);
 	else
-		halbtc8821a2ant_set_dac_swing_reg(btcoexist, 0x18);
+		btc8821a2ant_set_dac_swing_reg(btcoexist, 0x18);
 }
 
-static void halbtc8821a2ant_dac_swing(struct btc_coexist *btcoexist,
-				      bool force_exec, bool dac_swing_on,
-				      u32 dac_swing_lvl)
+static void btc8821a2ant_dac_swing(struct btc_coexist *btcoexist,
+				   bool force_exec, bool dac_swing_on,
+				   u32 dac_swing_lvl)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -958,50 +830,9 @@ static void halbtc8821a2ant_dac_swing(struct btc_coexist *btcoexist,
 	coex_dm->pre_dac_swing_lvl = coex_dm->cur_dac_swing_lvl;
 }
 
-static void halbtc8821a2ant_set_adc_back_off(struct btc_coexist *btcoexist,
-					     bool adc_back_off)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	if (adc_back_off) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BB BackOff Level On!\n");
-		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x8db, 0x60, 0x3);
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], BB BackOff Level Off!\n");
-		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x8db, 0x60, 0x1);
-	}
-}
-
-static void halbtc8821a2ant_adc_back_off(struct btc_coexist *btcoexist,
-					 bool force_exec, bool adc_back_off)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-
-	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-		 "[BTCoex], %s turn AdcBackOff = %s\n",
-		 (force_exec ? "force to" : ""),
-		 ((adc_back_off) ? "ON" : "OFF"));
-	coex_dm->cur_adc_back_off = adc_back_off;
-
-	if (!force_exec) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], pre_adc_back_off = %d, cur_adc_back_off = %d\n",
-			 coex_dm->pre_adc_back_off,
-			 coex_dm->cur_adc_back_off);
-
-		if (coex_dm->pre_adc_back_off == coex_dm->cur_adc_back_off)
-			return;
-	}
-	halbtc8821a2ant_set_adc_back_off(btcoexist, coex_dm->cur_adc_back_off);
-
-	coex_dm->pre_adc_back_off = coex_dm->cur_adc_back_off;
-}
-
-static void halbtc8821a2ant_set_coex_table(struct btc_coexist *btcoexist,
-					   u32 val0x6c0, u32 val0x6c4,
-					   u32 val0x6c8, u8 val0x6cc)
+static void btc8821a2ant_set_coex_table(struct btc_coexist *btcoexist,
+					u32 val0x6c0, u32 val0x6c4,
+					u32 val0x6c8, u8 val0x6cc)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1022,9 +853,9 @@ static void halbtc8821a2ant_set_coex_table(struct btc_coexist *btcoexist,
 	btcoexist->btc_write_1byte(btcoexist, 0x6cc, val0x6cc);
 }
 
-static void halbtc8821a2ant_coex_table(struct btc_coexist *btcoexist,
-				       bool force_exec, u32 val0x6c0,
-				       u32 val0x6c4, u32 val0x6c8, u8 val0x6cc)
+static void btc8821a2ant_coex_table(struct btc_coexist *btcoexist,
+				    bool force_exec, u32 val0x6c0,
+				    u32 val0x6c4, u32 val0x6c8, u8 val0x6cc)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1057,8 +888,8 @@ static void halbtc8821a2ant_coex_table(struct btc_coexist *btcoexist,
 		    (coex_dm->pre_val0x6cc == coex_dm->cur_val0x6cc))
 			return;
 	}
-	halbtc8821a2ant_set_coex_table(btcoexist, val0x6c0, val0x6c4, val0x6c8,
-				       val0x6cc);
+	btc8821a2ant_set_coex_table(btcoexist, val0x6c0, val0x6c4, val0x6c8,
+				    val0x6cc);
 
 	coex_dm->pre_val0x6c0 = coex_dm->cur_val0x6c0;
 	coex_dm->pre_val0x6c4 = coex_dm->cur_val0x6c4;
@@ -1066,14 +897,97 @@ static void halbtc8821a2ant_coex_table(struct btc_coexist *btcoexist,
 	coex_dm->pre_val0x6cc = coex_dm->cur_val0x6cc;
 }
 
-static void halbtc8821a2ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoex,
-						   bool enable)
+static void btc8821a2ant_coex_table_with_type(struct btc_coexist *btcoexist,
+					      bool force_exec, u8 type)
+{
+	coex_sta->coex_table_type = type;
+
+	switch (type) {
+	case 0:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x55555555, 0xffffff, 0x3);
+		break;
+	case 1:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55555555,
+					0x5afa5afa, 0xffffff, 0x3);
+		break;
+	case 2:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x5ada5ada,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 3:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0xaaaaaaaa,
+					0xaaaaaaaa, 0xffffff, 0x3);
+		break;
+	case 4:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0xffffffff,
+					0xffffffff, 0xffffff, 0x3);
+		break;
+	case 5:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
+					0x5fff5fff, 0xffffff, 0x3);
+		break;
+	case 6:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55ff55ff,
+					0x5a5a5a5a, 0xffffff, 0x3);
+		break;
+	case 7:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 8:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 9:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 10:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 11:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 12:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 13:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
+					0xaaaaaaaa, 0xffffff, 0x3);
+		break;
+	case 14:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x5fff5fff,
+					0x5ada5ada, 0xffffff, 0x3);
+		break;
+	case 15:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x55dd55dd,
+					0xaaaaaaaa, 0xffffff, 0x3);
+		break;
+	case 16:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0x5fdf5fdf,
+					0x5fdb5fdb, 0xffffff, 0x3);
+		break;
+	case 17:
+		btc8821a2ant_coex_table(btcoexist, force_exec, 0xfafafafa,
+					0xfafafafa, 0xffffff, 0x3);
+		break;
+	default:
+		break;
+	}
+}
+
+static void btc8821a2ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoex,
+						bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoex->adapter;
 	u8 h2c_parameter[1] = {0};
 
 	if (enable)
-		h2c_parameter[0] |= BIT0;/* function enable */
+		h2c_parameter[0] |= BIT0; /* function enable */
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], set FW for BT Ignore Wlan_Act, FW write 0x63 = 0x%x\n",
@@ -1082,8 +996,35 @@ static void halbtc8821a2ant_set_fw_ignore_wlan_act(struct btc_coexist *btcoex,
 	btcoex->btc_fill_h2c(btcoex, 0x63, 1, h2c_parameter);
 }
 
-static void halbtc8821a2ant_ignore_wlan_act(struct btc_coexist *btcoexist,
-					    bool force_exec, bool enable)
+static void btc8821a2ant_set_lps_rpwm(struct btc_coexist *btcoexist, u8 lps_val,
+				      u8 rpwm_val)
+{
+	u8 lps = lps_val;
+	u8 rpwm = rpwm_val;
+
+	btcoexist->btc_set(btcoexist, BTC_SET_U1_LPS_VAL, &lps);
+	btcoexist->btc_set(btcoexist, BTC_SET_U1_RPWM_VAL, &rpwm);
+}
+
+static void btc8821a2ant_lps_rpwm(struct btc_coexist *btcoexist,
+				  bool force_exec, u8 lps_val, u8 rpwm_val)
+{
+	coex_dm->cur_lps = lps_val;
+	coex_dm->cur_rpwm = rpwm_val;
+
+	if (!force_exec) {
+		if ((coex_dm->pre_lps == coex_dm->cur_lps) &&
+		    (coex_dm->pre_rpwm == coex_dm->cur_rpwm))
+			return;
+	}
+	btc8821a2ant_set_lps_rpwm(btcoexist, lps_val, rpwm_val);
+
+	coex_dm->pre_lps = coex_dm->cur_lps;
+	coex_dm->pre_rpwm = coex_dm->cur_rpwm;
+}
+
+static void btc8821a2ant_ignore_wlan_act(struct btc_coexist *btcoexist,
+					 bool force_exec, bool enable)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -1102,14 +1043,14 @@ static void halbtc8821a2ant_ignore_wlan_act(struct btc_coexist *btcoexist,
 		    coex_dm->cur_ignore_wlan_act)
 			return;
 	}
-	halbtc8821a2ant_set_fw_ignore_wlan_act(btcoexist, enable);
+	btc8821a2ant_set_fw_ignore_wlan_act(btcoexist, enable);
 
 	coex_dm->pre_ignore_wlan_act = coex_dm->cur_ignore_wlan_act;
 }
 
-static void halbtc8821a2ant_set_fw_pstdma(struct btc_coexist *btcoexist,
-					  u8 byte1, u8 byte2, u8 byte3,
-					  u8 byte4, u8 byte5)
+static void btc8821a2ant_set_fw_ps_tdma(struct btc_coexist *btcoexist,
+					u8 byte1, u8 byte2, u8 byte3,
+					u8 byte4, u8 byte5)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 h2c_parameter[5];
@@ -1137,45 +1078,24 @@ static void halbtc8821a2ant_set_fw_pstdma(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x60, 5, h2c_parameter);
 }
 
-static void btc8821a2ant_sw_mech1(struct btc_coexist *btcoexist,
-				  bool shrink_rx_lpf,
-				  bool low_penalty_ra, bool limited_dig,
-				  bool bt_lna_constrain)
+static void btc8821a2ant_sw_mechanism1(struct btc_coexist *btcoexist,
+				       bool shrink_rx_lpf, bool low_penalty_ra,
+				       bool limited_dig, bool bt_lna_constrain)
 {
-	u32 wifi_bw;
-
-	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
-
-	if (BTC_WIFI_BW_HT40 != wifi_bw) {
-		/*only shrink RF Rx LPF for HT40*/
-		if (shrink_rx_lpf)
-			shrink_rx_lpf = false;
-	}
-
-	halbtc8821a2ant_RfShrink(btcoexist, NORMAL_EXEC, shrink_rx_lpf);
-	halbtc8821a2ant_low_penalty_ra(btcoexist,
-				       NORMAL_EXEC, low_penalty_ra);
-
-	/* no limited DIG
-	 * btc8821a2_set_bt_lna_const(btcoexist,
-		NORMAL_EXEC, bBTLNAConstrain);
-	 */
+	btc8821a2ant_low_penalty_ra(btcoexist, NORMAL_EXEC, low_penalty_ra);
 }
 
-static void btc8821a2ant_sw_mech2(struct btc_coexist *btcoexist,
-				  bool agc_table_shift,
-				  bool adc_back_off, bool sw_dac_swing,
-				  u32 dac_swing_lvl)
+static void btc8821a2ant_sw_mechanism2(struct btc_coexist *btcoexist,
+				       bool agc_table_shift, bool adc_back_off,
+				       bool sw_dac_swing, u32 dac_swing_lvl)
 {
-	/* halbtc8821a2ant_AgcTable(btcoexist, NORMAL_EXEC, bAGCTableShift); */
-	halbtc8821a2ant_adc_back_off(btcoexist, NORMAL_EXEC, adc_back_off);
-	halbtc8821a2ant_dac_swing(btcoexist, NORMAL_EXEC, sw_dac_swing,
-				  sw_dac_swing);
+	btc8821a2ant_dac_swing(btcoexist, NORMAL_EXEC, sw_dac_swing,
+			       dac_swing_lvl);
 }
 
-static void halbtc8821a2ant_set_ant_path(struct btc_coexist *btcoexist,
-					 u8 ant_pos_type, bool init_hw_cfg,
-					 bool wifi_off)
+static void btc8821a2ant_set_ant_path(struct btc_coexist *btcoexist,
+				      u8 ant_pos_type, bool init_hw_cfg,
+				      bool wifi_off)
 {
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	u32 u4tmp = 0;
@@ -1189,21 +1109,18 @@ static void halbtc8821a2ant_set_ant_path(struct btc_coexist *btcoexist,
 		btcoexist->btc_write_4byte(btcoexist, 0x4c, u4tmp);
 
 		btcoexist->btc_write_4byte(btcoexist, 0x974, 0x3ff);
-		btcoexist->btc_write_1byte(btcoexist, 0xcb4, 0x77);
 
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT) {
-			/* tell firmware "antenna inverse"  ==>
-			 *	WRONG firmware antenna control code.
-			 *	==>need fw to fix
+			/* tell firmware "antenna inverse"  ==> WRONG firmware
+			 * antenna control code ==>need fw to fix
 			 */
 			h2c_parameter[0] = 1;
 			h2c_parameter[1] = 1;
 			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 						h2c_parameter);
 		} else {
-			/* tell firmware "no antenna inverse"
-			 *	==> WRONG firmware antenna control code.
-			 *	==>need fw to fix
+			/* tell firmware "no antenna inverse" ==> WRONG firmware
+			 * antenna control code ==>need fw to fix
 			 */
 			h2c_parameter[0] = 0;
 			h2c_parameter[1] = 1;
@@ -1223,11 +1140,25 @@ static void halbtc8821a2ant_set_ant_path(struct btc_coexist *btcoexist,
 	}
 }
 
-static void halbtc8821a2ant_ps_tdma(struct btc_coexist *btcoexist,
-				    bool force_exec, bool turn_on, u8 type)
+static void btc8821a2ant_ps_tdma(struct btc_coexist *btcoexist,
+				 bool force_exec, bool turn_on, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
+	u8 wifi_rssi_state, bt_rssi_state;
+
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist, 2,
+				BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
+
+	if (!(BTC_RSSI_HIGH(wifi_rssi_state) &&
+	      BTC_RSSI_HIGH(bt_rssi_state)) &&
+	    turn_on) {
+		/* for WiFi RSSI low or BT RSSI low */
+		type = type + 100;
+	}
+
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], %s turn %s PS TDMA, type = %d\n",
 		 (force_exec ? "force to" : ""), (turn_on ? "ON" : "OFF"),
@@ -1251,108 +1182,181 @@ static void halbtc8821a2ant_ps_tdma(struct btc_coexist *btcoexist,
 		switch (type) {
 		case 1:
 		default:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1a,
-						      0x1a, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x03, 0xf1, 0x90);
 			break;
 		case 2:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x12,
-						      0x12, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x2d,
+						    0x03, 0xf1, 0x90);
 			break;
 		case 3:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1c,
-						      0x3, 0xf1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0xf1, 0x90);
 			break;
 		case 4:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x10,
-						      0x03, 0xf1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
+						    0x03, 0xf1, 0x90);
 			break;
 		case 5:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1a,
-						      0x1a, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x3, 0x70, 0x90);
 			break;
 		case 6:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x12,
-						      0x12, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x2d,
+						    0x3, 0x70, 0x90);
 			break;
 		case 7:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1c,
-						      0x3, 0x70, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0x70, 0x90);
 			break;
 		case 8:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xa3, 0x10,
-						      0x3, 0x70, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xa3, 0x10,
+						    0x3, 0x70, 0x90);
 			break;
 		case 9:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1a,
-						      0x1a, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x03, 0xf1, 0x90);
 			break;
 		case 10:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x12,
-						      0x12, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x2d,
+						    0x03, 0xf1, 0x90);
 			break;
 		case 11:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0xa,
-						      0xa, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0xf1, 0x90);
 			break;
 		case 12:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x5,
-						      0x5, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
+						    0x3, 0xf1, 0x90);
 			break;
 		case 13:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1a,
-						      0x1a, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x3, 0x70, 0x90);
 			break;
 		case 14:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3,
-						      0x12, 0x12, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x2d,
+						    0x3, 0x70, 0x90);
 			break;
 		case 15:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0xa,
-						      0xa, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1c,
+						    0x3, 0x70, 0x90);
 			break;
 		case 16:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x5,
-						      0x5, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x10,
+						    0x3, 0x70, 0x90);
 			break;
 		case 17:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xa3, 0x2f,
-						      0x2f, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xa3, 0x2f,
+						    0x2f, 0x60, 0x90);
 			break;
 		case 18:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x5,
-						      0x5, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x5, 0x5,
+						    0xe1, 0x90);
 			break;
 		case 19:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x25,
-						      0x25, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
+						    0x25, 0xe1, 0x90);
 			break;
 		case 20:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x25,
-						      0x25, 0x60, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x25,
+						    0x25, 0x60, 0x90);
 			break;
 		case 21:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x15,
-						      0x03, 0x70, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x15,
+						    0x03, 0x70, 0x90);
+			break;
+		case 23:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x1e,
+						    0x03, 0xf0, 0x14);
+			break;
+		case 24:
+		case 124:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x3c,
+						    0x03, 0x70, 0x50);
+			break;
+		case 25:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x14,
+						    0x03, 0xf1, 0x90);
+			break;
+		case 26:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x30,
+						    0x03, 0xf1, 0x90);
 			break;
 		case 71:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0xe3, 0x1a,
-						      0x1a, 0xe1, 0x90);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x03, 0xf1, 0x90);
+			break;
+		case 101:
+		case 105:
+		case 171:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x3a,
+						    0x03, 0x70, 0x50);
+			break;
+		case 102:
+		case 106:
+		case 110:
+		case 114:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x2d,
+						    0x03, 0x70, 0x50);
+			break;
+		case 103:
+		case 107:
+		case 111:
+		case 115:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x1c,
+						    0x03, 0x70, 0x50);
+			break;
+		case 104:
+		case 108:
+		case 112:
+		case 116:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x10,
+						    0x03, 0x70, 0x50);
+			break;
+		case 109:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x03, 0xf1, 0x90);
+			break;
+		case 113:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x3c,
+						    0x03, 0x70, 0x90);
+			break;
+		case 121:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x15,
+						    0x03, 0x70, 0x90);
+			break;
+		case 22:
+		case 122:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xe3, 0x35,
+						    0x03, 0x71, 0x11);
+			break;
+		case 123:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x1c,
+						    0x03, 0x70, 0x54);
+			break;
+		case 125:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x14,
+						    0x03, 0x70, 0x50);
+			break;
+		case 126:
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0xd3, 0x30,
+						    0x03, 0x70, 0x50);
 			break;
 		}
 	} else {
 		/* disable PS tdma */
 		switch (type) {
 		case 0:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0x0, 0x0, 0x0,
-						      0x40, 0x0);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
+						    0x40, 0x0);
 			break;
 		case 1:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0x0, 0x0, 0x0,
-						      0x48, 0x0);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
+						    0x48, 0x0);
 			break;
 		default:
-			halbtc8821a2ant_set_fw_pstdma(btcoexist, 0x0, 0x0, 0x0,
-						      0x40, 0x0);
+			btc8821a2ant_set_fw_ps_tdma(btcoexist, 0x0, 0x0, 0x0,
+						    0x40, 0x0);
 			break;
 		}
 	}
@@ -1362,867 +1366,450 @@ static void halbtc8821a2ant_ps_tdma(struct btc_coexist *btcoexist,
 	coex_dm->pre_ps_tdma = coex_dm->cur_ps_tdma;
 }
 
-static void halbtc8821a2ant_coex_all_off(struct btc_coexist *btcoexist)
+static void
+btc8821a2ant_ps_tdma_check_for_power_save_state(struct btc_coexist *btcoexist,
+						bool new_ps_state)
+{
+	u8 lps_mode = 0x0;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U1_LPS_MODE, &lps_mode);
+
+	if (lps_mode) {
+		/* already under LPS state */
+		if (new_ps_state) {
+			/* keep state under LPS, do nothing */
+		} else {
+			/* will leave LPS state, turn off psTdma first */
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+		}
+	} else {
+		/* NO PS state */
+		if (new_ps_state) {
+			/* will enter LPS state, turn off psTdma first */
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+		} else {
+			/* keep state under NO PS state, do nothing */
+		}
+	}
+}
+
+static void btc8821a2ant_power_save_state(struct btc_coexist *btcoexist,
+					  u8 ps_type, u8 lps_val, u8 rpwm_val)
+{
+	bool low_pwr_disable = false;
+
+	switch (ps_type) {
+	case BTC_PS_WIFI_NATIVE:
+		/* recover to original 32k low power setting */
+		low_pwr_disable = false;
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
+				   &low_pwr_disable);
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_NORMAL_LPS, NULL);
+		coex_sta->force_lps_on = false;
+		break;
+	case BTC_PS_LPS_ON:
+		btc8821a2ant_ps_tdma_check_for_power_save_state(btcoexist,
+								true);
+		btc8821a2ant_lps_rpwm(btcoexist, NORMAL_EXEC, lps_val,
+				      rpwm_val);
+		/* when coex force to enter LPS, do not enter 32k low power */
+		low_pwr_disable = true;
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
+				   &low_pwr_disable);
+		/* power save must executed before psTdma */
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_ENTER_LPS, NULL);
+		coex_sta->force_lps_on = true;
+		break;
+	case BTC_PS_LPS_OFF:
+		btc8821a2ant_ps_tdma_check_for_power_save_state(btcoexist,
+								false);
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_LEAVE_LPS, NULL);
+		coex_sta->force_lps_on = false;
+		break;
+	default:
+		break;
+	}
+}
+
+static void btc8821a2ant_coex_all_off(struct btc_coexist *btcoexist)
 {
 	/* fw all off */
-	halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-	halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
 	/* sw all off */
-	btc8821a2ant_sw_mech1(btcoexist, false, false, false, false);
-	btc8821a2ant_sw_mech2(btcoexist, false, false, false, 0x18);
+	btc8821a2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8821a2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
 
 	/* hw all off */
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC,
-				   0x55555555, 0x55555555, 0xffff, 0x3);
+	btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 }
 
-static void halbtc8821a2ant_coex_under_5g(struct btc_coexist *btcoexist)
+static void btc8821a2ant_coex_under_5g(struct btc_coexist *btcoexist)
 {
-	halbtc8821a2ant_coex_all_off(btcoexist);
+	btc8821a2ant_coex_all_off(btcoexist);
+	btc8821a2ant_ignore_wlan_act(btcoexist, NORMAL_EXEC, true);
 }
 
-static void halbtc8821a2ant_init_coex_dm(struct btc_coexist *btcoexist)
+static void btc8821a2ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	/* force to reset coex mechanism */
-	halbtc8821a2ant_coex_table(btcoexist, FORCE_EXEC, 0x55555555,
-				   0x55555555, 0xffff, 0x3);
+	btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 
-	halbtc8821a2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, FORCE_EXEC, 6);
-	halbtc8821a2ant_dec_bt_pwr(btcoexist, FORCE_EXEC, false);
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8821a2ant_ps_tdma(btcoexist, FORCE_EXEC, false, 1);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, FORCE_EXEC, 6);
+	btc8821a2ant_dec_bt_pwr(btcoexist, FORCE_EXEC, 0);
 
-	btc8821a2ant_sw_mech1(btcoexist, false, false, false, false);
-	btc8821a2ant_sw_mech2(btcoexist, false, false, false, 0x18);
+	btc8821a2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8821a2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
 }
 
-static void halbtc8821a2ant_bt_inquiry_page(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_bt_inquiry(struct btc_coexist *btcoexist)
 {
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	bool wifi_connected = false;
 	bool low_pwr_disable = true;
+	bool scan = false, link = false, roam = false;
+
+	wifi_rssi_state =
+		btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+		2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
 	btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
 			   &low_pwr_disable);
-
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-				   0x5afa5afa, 0xffff, 0x3);
-	halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3);
-}
-
-static bool halbtc8821a2ant_is_common_action(struct btc_coexist *btcoexist)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool common = false, wifi_connected = false, wifi_busy = false;
-	bool low_pwr_disable = false;
-
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
 			   &wifi_connected);
-	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
 
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-				   0x5afa5afa, 0xffff, 0x3);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
 
-	if (!wifi_connected &&
-	    BT_8821A_2ANT_BT_STATUS_IDLE == coex_dm->bt_status) {
-		low_pwr_disable = false;
-		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
-				   &low_pwr_disable);
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
 
+	if (scan || link || roam) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Wifi link process + BT Inq/Page!!\n");
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 15);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
+	} else if (wifi_connected) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Wifi connected + BT Inq/Page!!\n");
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 15);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
+	} else {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi IPS + BT IPS!!\n");
+			 "[BTCoex], Wifi no-link + BT Inq/Page!!\n");
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+	}
 
-		halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, FORCE_EXEC, 6);
+	btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-		btc8821a2ant_sw_mech1(btcoexist, false, false, false, false);
-		btc8821a2ant_sw_mech2(btcoexist, false, false, false, 0x18);
+	btc8821a2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8821a2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
+}
 
-		common = true;
-	} else if (wifi_connected &&
-		   (BT_8821A_2ANT_BT_STATUS_IDLE == coex_dm->bt_status)) {
-		low_pwr_disable = false;
-		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
-				   &low_pwr_disable);
+void btc8821a2ant_action_wifi_link_process(struct btc_coexist *btcoexist)
+{
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u8 u8tmpa, u8tmpb;
 
-		if (wifi_busy) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi Busy + BT IPS!!\n");
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 1);
-		} else {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi LPS + BT IPS!!\n");
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 1);
-		}
+	btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 15);
+	btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 22);
 
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	btc8821a2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8821a2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
 
-		btc8821a2ant_sw_mech1(btcoexist, false, false, false, false);
-		btc8821a2ant_sw_mech2(btcoexist, false, false, false, 0x18);
+	u8tmpa = btcoexist->btc_read_1byte(btcoexist, 0x765);
+	u8tmpb = btcoexist->btc_read_1byte(btcoexist, 0x76e);
 
-		common = true;
-	} else if (!wifi_connected &&
-		   (BT_8821A_2ANT_BT_STATUS_CON_IDLE == coex_dm->bt_status)) {
-		low_pwr_disable = true;
-		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
-				   &low_pwr_disable);
+	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+		 "[BTCoex], 0x765=0x%x, 0x76e=0x%x\n", u8tmpa, u8tmpb);
+}
 
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi IPS + BT LPS!!\n");
+static bool btc8821a2ant_action_wifi_idle_process(struct btc_coexist *btcoexist)
+{
+	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u8 ap_num = 0;
 
-		halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	wifi_rssi_state =
+		btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+			BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES - 20, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+			2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-		btc8821a2ant_sw_mech1(btcoexist, false, false, false, false);
-		btc8821a2ant_sw_mech2(btcoexist, false, false, false, 0x18);
-		common = true;
-	} else if (wifi_connected &&
-		   (BT_8821A_2ANT_BT_STATUS_CON_IDLE == coex_dm->bt_status)) {
-		low_pwr_disable = true;
-		btcoexist->btc_set(btcoexist,
-			BTC_SET_ACT_DISABLE_LOW_POWER, &low_pwr_disable);
+	btcoexist->btc_get(btcoexist, BTC_GET_U1_AP_NUM, &ap_num);
 
-		if (wifi_busy) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi Busy + BT LPS!!\n");
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 1);
-		} else {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi LPS + BT LPS!!\n");
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 1);
-		}
+	/* define the office environment */
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && (coex_sta->hid_exist) &&
+	    (coex_sta->a2dp_exist)) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], Wifi  idle process for BT HID+A2DP exist!!\n");
 
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dac_swing(btcoexist, NORMAL_EXEC, true, 0x6);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-		btc8821a2ant_sw_mech1(btcoexist, true, true, true, true);
-		btc8821a2ant_sw_mech2(btcoexist, false, false, false, 0x18);
+		/* sw all off */
+		btc8821a2ant_sw_mechanism1(btcoexist, false, false, false,
+					   false);
+		btc8821a2ant_sw_mechanism2(btcoexist, false, false, false,
+					   0x18);
 
-		common = true;
-	} else if (!wifi_connected &&
-		   (BT_8821A_2ANT_BT_STATUS_NON_IDLE ==
-		    coex_dm->bt_status)) {
-		low_pwr_disable = false;
-		btcoexist->btc_set(btcoexist,
-			BTC_SET_ACT_DISABLE_LOW_POWER, &low_pwr_disable);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 
+		return true;
+	} else if (coex_sta->pan_exist) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], Wifi IPS + BT Busy!!\n");
+			 "[BTCoex], Wifi  idle process for BT PAN exist!!\n");
 
-		halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dac_swing(btcoexist, NORMAL_EXEC, true, 0x6);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-		btc8821a2ant_sw_mech1(btcoexist, false, false,
-				      false, false);
-		btc8821a2ant_sw_mech2(btcoexist, false, false,
-				      false, 0x18);
+		/* sw all off */
+		btc8821a2ant_sw_mechanism1(btcoexist, false, false, false,
+					   false);
+		btc8821a2ant_sw_mechanism2(btcoexist, false, false, false,
+					   0x18);
 
-		common = true;
-	} else {
-		low_pwr_disable = true;
-		btcoexist->btc_set(btcoexist,
-				   BTC_SET_ACT_DISABLE_LOW_POWER,
-				   &low_pwr_disable);
-
-		if (wifi_busy) {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi Busy + BT Busy!!\n");
-			common = false;
-		} else {
-			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-				 "[BTCoex], Wifi LPS + BT Busy!!\n");
-			halbtc8821a2ant_ps_tdma(btcoexist,
-						NORMAL_EXEC, true, 21);
-
-			if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-				halbtc8821a2ant_dec_bt_pwr(btcoexist,
-							   NORMAL_EXEC, true);
-			else
-				halbtc8821a2ant_dec_bt_pwr(btcoexist,
-							   NORMAL_EXEC, false);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
 
-			common = true;
-		}
-		btc8821a2ant_sw_mech1(btcoexist, true, true, true, true);
+		return true;
 	}
-	return common;
+	btc8821a2ant_dac_swing(btcoexist, NORMAL_EXEC, true, 0x18);
+	return false;
 }
 
-static void btc8821a2_int1(struct btc_coexist *btcoexist, bool tx_pause,
-			   int result)
+static bool btc8821a2ant_is_common_action(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
+	bool common = false, wifi_connected = false, wifi_busy = false;
+	bool low_pwr_disable = false;
+	bool bt_hs_on = false;
+
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_CONNECTED,
+			   &wifi_connected);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_BUSY, &wifi_busy);
+
+	if (!wifi_connected) {
+		low_pwr_disable = false;
+		btcoexist->btc_set(btcoexist, BTC_SET_ACT_DISABLE_LOW_POWER,
+				   &low_pwr_disable);
+		btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false,
+					0x8);
 
-	if (tx_pause) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-
-		if (coex_dm->cur_ps_tdma == 71) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-			coex_dm->tdma_adj_type = 5;
-		} else if (coex_dm->cur_ps_tdma == 1) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-			coex_dm->tdma_adj_type = 5;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 13);
-			coex_dm->tdma_adj_type = 13;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
+			    "[BTCoex], Wifi non-connected idle!!\n");
+
+		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff,
+					  0x0);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+		btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+		btc8821a2ant_sw_mechanism1(btcoexist, false, false, false,
+					   false);
+		btc8821a2ant_sw_mechanism2(btcoexist, false, false, false,
+					   0x18);
 
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 5);
-				coex_dm->tdma_adj_type = 5;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 13);
-				coex_dm->tdma_adj_type = 13;
-			}
-		}
+		common = true;
 	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 71);
-			coex_dm->tdma_adj_type = 71;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 9);
-			coex_dm->tdma_adj_type = 9;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
+		if (BT_8821A_2ANT_BT_STATUS_IDLE ==
+		    coex_dm->bt_status) {
+			low_pwr_disable = false;
+			btcoexist->btc_set(btcoexist,
+					   BTC_SET_ACT_DISABLE_LOW_POWER,
+					   &low_pwr_disable);
+			btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC,
+						false, false, 0x8);
 
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 71) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 1);
-				coex_dm->tdma_adj_type = 1;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 1);
-				coex_dm->tdma_adj_type = 1;
-			} else if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 71);
-				coex_dm->tdma_adj_type = 71;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 9);
-				coex_dm->tdma_adj_type = 9;
-			}
-		}
-	}
-}
+			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+				 "[BTCoex], Wifi connected + BT non connected-idle!!\n");
 
-static void btc8821a2_int2(struct btc_coexist *btcoexist, bool tx_pause,
-			   int result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
+			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1,
+						  0xfffff, 0x0);
+			btc8821a2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 0);
 
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-		if (coex_dm->cur_ps_tdma == 1) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 6);
-			coex_dm->tdma_adj_type = 6;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
-			coex_dm->tdma_adj_type = 14;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 6);
-				coex_dm->tdma_adj_type = 6;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 14);
-				coex_dm->tdma_adj_type = 14;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 2);
-			coex_dm->tdma_adj_type = 2;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
-			coex_dm->tdma_adj_type = 10;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 2);
-				coex_dm->tdma_adj_type = 2;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 10);
-				coex_dm->tdma_adj_type = 10;
-			}
-		}
-	}
-}
+			btc8821a2ant_power_save_state(
+				btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+			btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC,
+						      0xb);
+			btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-static void btc8821a2_int3(struct btc_coexist *btcoexist, bool tx_pause,
-			   int result)
-{
-	struct rtl_priv *rtlpriv = btcoexist->adapter;
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 
-	if (tx_pause) {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 1\n");
-		if (coex_dm->cur_ps_tdma == 1) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 2) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 3) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 7);
-			coex_dm->tdma_adj_type = 7;
-		} else if (coex_dm->cur_ps_tdma == 4) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 8);
-			coex_dm->tdma_adj_type = 8;
-		}
-		if (coex_dm->cur_ps_tdma == 9) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 10) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 11) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 15);
-			coex_dm->tdma_adj_type = 15;
-		} else if (coex_dm->cur_ps_tdma == 12) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 16);
-			coex_dm->tdma_adj_type = 16;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 5) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 8);
-				coex_dm->tdma_adj_type = 8;
-			} else if (coex_dm->cur_ps_tdma == 13) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 16);
-				coex_dm->tdma_adj_type = 16;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 8) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 7) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 6) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 7);
-				coex_dm->tdma_adj_type = 7;
-			} else if (coex_dm->cur_ps_tdma == 16) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 15) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			} else if (coex_dm->cur_ps_tdma == 14) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 15);
-				coex_dm->tdma_adj_type = 15;
-			}
-		}
-	} else {
-		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
-			 "[BTCoex], TxPause = 0\n");
-		if (coex_dm->cur_ps_tdma == 5) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 6) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 7) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 3);
-			coex_dm->tdma_adj_type = 3;
-		} else if (coex_dm->cur_ps_tdma == 8) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 4);
-			coex_dm->tdma_adj_type = 4;
-		}
-		if (coex_dm->cur_ps_tdma == 13) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 14) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 15) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 11);
-			coex_dm->tdma_adj_type = 11;
-		} else if (coex_dm->cur_ps_tdma == 16) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 12);
-			coex_dm->tdma_adj_type = 12;
-		}
-		if (result == -1) {
-			if (coex_dm->cur_ps_tdma == 1) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 4);
-				coex_dm->tdma_adj_type = 4;
-			} else if (coex_dm->cur_ps_tdma == 9) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 12);
-				coex_dm->tdma_adj_type = 12;
-			}
-		} else if (result == 1) {
-			if (coex_dm->cur_ps_tdma == 4) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 3) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 2) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 3);
-				coex_dm->tdma_adj_type = 3;
-			} else if (coex_dm->cur_ps_tdma == 12) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 11) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
-			} else if (coex_dm->cur_ps_tdma == 10) {
-				halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-							true, 11);
-				coex_dm->tdma_adj_type = 11;
+			common = true;
+		} else if (BT_8821A_2ANT_BT_STATUS_CON_IDLE ==
+			   coex_dm->bt_status) {
+			low_pwr_disable = true;
+			btcoexist->btc_set(btcoexist,
+					   BTC_SET_ACT_DISABLE_LOW_POWER,
+					   &low_pwr_disable);
+
+			if (bt_hs_on)
+				return false;
+			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+				 "[BTCoex], Wifi connected + BT connected-idle!!\n");
+			btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC,
+						false, false, 0x8);
+
+			btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1,
+						  0xfffff, 0x0);
+			btc8821a2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 0);
+
+			btc8821a2ant_power_save_state(
+				btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+			btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC,
+						      0xb);
+			btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
+			common = true;
+		} else {
+			low_pwr_disable = true;
+			btcoexist->btc_set(btcoexist,
+					   BTC_SET_ACT_DISABLE_LOW_POWER,
+					   &low_pwr_disable);
+
+			if (wifi_busy) {
+				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+					 "[BTCoex], Wifi Connected-Busy + BT Busy!!\n");
+				common = false;
+			} else {
+				RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+					 "[BTCoex], Wifi Connected-Idle + BT Busy!!\n");
+				common =
+				    btc8821a2ant_action_wifi_idle_process(
+					     btcoexist);
 			}
 		}
 	}
+	return common;
 }
 
-static void btc8821a2ant_tdma_dur_adj(struct btc_coexist *btcoexist,
-				      bool sco_hid, bool tx_pause,
-				      u8 max_interval)
+static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
+					      bool sco_hid, bool tx_pause,
+					      u8 max_interval)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static long	up, dn, m, n, wait_count;
-	 /* 0: no change, +1: increase WiFi duration,
+	static long up, dn, m, n, wait_count;
+	 /* 0 : no change
+	  * +1: increase WiFi duration
 	  * -1: decrease WiFi duration
 	  */
-	int		result;
-	u8		retry_count = 0;
+	int result;
+	u8 retry_count = 0;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], TdmaDurationAdjust()\n");
 
-	if (coex_dm->reset_tdma_adjust) {
-		coex_dm->reset_tdma_adjust = false;
+	if (coex_dm->auto_tdma_adjust) {
+		coex_dm->auto_tdma_adjust = false;
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], first run TdmaDurationAdjust()!!\n");
 		if (sco_hid) {
 			if (tx_pause) {
 				if (max_interval == 1) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 13);
-					coex_dm->tdma_adj_type = 13;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 13);
+					coex_dm->ps_tdma_du_adj_type = 13;
 				} else if (max_interval == 2) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 14);
-					coex_dm->tdma_adj_type = 14;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (max_interval == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
 				} else {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 15);
-					coex_dm->tdma_adj_type = 15;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
 				}
 			} else {
 				if (max_interval == 1) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 9);
-					coex_dm->tdma_adj_type = 9;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 9);
+					coex_dm->ps_tdma_du_adj_type = 9;
 				} else if (max_interval == 2) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 10);
-					coex_dm->tdma_adj_type = 10;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (max_interval == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
 				} else {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 11);
-					coex_dm->tdma_adj_type = 11;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
 				}
 			}
 		} else {
 			if (tx_pause) {
 				if (max_interval == 1) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 5);
-					coex_dm->tdma_adj_type = 5;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 5);
+					coex_dm->ps_tdma_du_adj_type = 5;
 				} else if (max_interval == 2) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 6);
-					coex_dm->tdma_adj_type = 6;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (max_interval == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
 				} else {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 7);
-					coex_dm->tdma_adj_type = 7;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
 				}
 			} else {
 				if (max_interval == 1) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 1);
-					coex_dm->tdma_adj_type = 1;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 1);
+					coex_dm->ps_tdma_du_adj_type = 1;
 				} else if (max_interval == 2) {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 2);
-					coex_dm->tdma_adj_type = 2;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (max_interval == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
 				} else {
-					halbtc8821a2ant_ps_tdma(btcoexist,
-								NORMAL_EXEC,
-								true, 3);
-					coex_dm->tdma_adj_type = 3;
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
 				}
 			}
 		}
@@ -2273,7 +1860,7 @@ static void btc8821a2ant_tdma_dur_adj(struct btc_coexist *btcoexist,
 				up = 0;
 
 			if (dn == 2) {
-				/* if retry count< 3 for 2*2 seconds,
+				/* if retry count < 3 for 2*2 seconds,
 				 * shrink wifi duration
 				 */
 				if (wait_count <= 2)
@@ -2286,7 +1873,7 @@ static void btc8821a2ant_tdma_dur_adj(struct btc_coexist *btcoexist,
 				if (m >= 20)
 					m = 20;
 
-				n = 3*m;
+				n = 3 * m;
 				up = 0;
 				dn = 0;
 				wait_count = 0;
@@ -2308,7 +1895,7 @@ static void btc8821a2ant_tdma_dur_adj(struct btc_coexist *btcoexist,
 			if (m >= 20)
 				m = 20;
 
-			n = 3*m;
+			n = 3 * m;
 			up = 0;
 			dn = 0;
 			wait_count = 0;
@@ -2319,624 +1906,1313 @@ static void btc8821a2ant_tdma_dur_adj(struct btc_coexist *btcoexist,
 
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], max Interval = %d\n", max_interval);
-		if (max_interval == 1)
-			btc8821a2_int1(btcoexist, tx_pause, result);
-		else if (max_interval == 2)
-			btc8821a2_int2(btcoexist, tx_pause, result);
-		else if (max_interval == 3)
-			btc8821a2_int3(btcoexist, tx_pause, result);
+
+		if (max_interval == 1) {
+			if (tx_pause) {
+				if (coex_dm->cur_ps_tdma == 71) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 5);
+					coex_dm->ps_tdma_du_adj_type = 5;
+				} else if (coex_dm->cur_ps_tdma == 1) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 5);
+					coex_dm->ps_tdma_du_adj_type = 5;
+				} else if (coex_dm->cur_ps_tdma == 2) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (coex_dm->cur_ps_tdma == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 4) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 8);
+					coex_dm->ps_tdma_du_adj_type = 8;
+				}
+				if (coex_dm->cur_ps_tdma == 9) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 13);
+					coex_dm->ps_tdma_du_adj_type = 13;
+				} else if (coex_dm->cur_ps_tdma == 10) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (coex_dm->cur_ps_tdma == 11) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 12) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 16);
+					coex_dm->ps_tdma_du_adj_type = 16;
+				}
+
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 5) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 8);
+						coex_dm->ps_tdma_du_adj_type =
+							8;
+					} else if (coex_dm->cur_ps_tdma == 13) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 16);
+						coex_dm->ps_tdma_du_adj_type =
+							16;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 8) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 5);
+						coex_dm->ps_tdma_du_adj_type =
+							5;
+					} else if (coex_dm->cur_ps_tdma == 16) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 13);
+						coex_dm->ps_tdma_du_adj_type =
+							13;
+					}
+				}
+			} else {
+				if (coex_dm->cur_ps_tdma == 5) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 71);
+					coex_dm->ps_tdma_du_adj_type = 71;
+				} else if (coex_dm->cur_ps_tdma == 6) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (coex_dm->cur_ps_tdma == 7) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 8) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 4);
+					coex_dm->ps_tdma_du_adj_type = 4;
+				}
+				if (coex_dm->cur_ps_tdma == 13) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 9);
+					coex_dm->ps_tdma_du_adj_type = 9;
+				} else if (coex_dm->cur_ps_tdma == 14) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (coex_dm->cur_ps_tdma == 15) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 16) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 12);
+					coex_dm->ps_tdma_du_adj_type = 12;
+				}
+
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 71) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 1);
+						coex_dm->ps_tdma_du_adj_type =
+							1;
+					} else if (coex_dm->cur_ps_tdma == 1) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 4);
+						coex_dm->ps_tdma_du_adj_type =
+							4;
+					} else if (coex_dm->cur_ps_tdma == 9) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 12);
+						coex_dm->ps_tdma_du_adj_type =
+							12;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 4) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 1);
+						coex_dm->ps_tdma_du_adj_type =
+							1;
+					} else if (coex_dm->cur_ps_tdma == 1) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 71);
+						coex_dm->ps_tdma_du_adj_type =
+							71;
+					} else if (coex_dm->cur_ps_tdma == 12) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 9);
+						coex_dm->ps_tdma_du_adj_type =
+							9;
+					}
+				}
+			}
+		} else if (max_interval == 2) {
+			if (tx_pause) {
+				if (coex_dm->cur_ps_tdma == 1) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (coex_dm->cur_ps_tdma == 2) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 6);
+					coex_dm->ps_tdma_du_adj_type = 6;
+				} else if (coex_dm->cur_ps_tdma == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 4) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 8);
+					coex_dm->ps_tdma_du_adj_type = 8;
+				}
+				if (coex_dm->cur_ps_tdma == 9) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (coex_dm->cur_ps_tdma == 10) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 14);
+					coex_dm->ps_tdma_du_adj_type = 14;
+				} else if (coex_dm->cur_ps_tdma == 11) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 12) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 16);
+					coex_dm->ps_tdma_du_adj_type = 16;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 5) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 8);
+						coex_dm->ps_tdma_du_adj_type =
+							8;
+					} else if (coex_dm->cur_ps_tdma == 13) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 16);
+						coex_dm->ps_tdma_du_adj_type =
+							16;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 8) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 6);
+						coex_dm->ps_tdma_du_adj_type =
+							6;
+					} else if (coex_dm->cur_ps_tdma == 16) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 14);
+						coex_dm->ps_tdma_du_adj_type =
+							14;
+					}
+				}
+			} else {
+				if (coex_dm->cur_ps_tdma == 5) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (coex_dm->cur_ps_tdma == 6) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 2);
+					coex_dm->ps_tdma_du_adj_type = 2;
+				} else if (coex_dm->cur_ps_tdma == 7) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 8) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 4);
+					coex_dm->ps_tdma_du_adj_type = 4;
+				}
+				if (coex_dm->cur_ps_tdma == 13) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (coex_dm->cur_ps_tdma == 14) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 10);
+					coex_dm->ps_tdma_du_adj_type = 10;
+				} else if (coex_dm->cur_ps_tdma == 15) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 16) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 12);
+					coex_dm->ps_tdma_du_adj_type = 12;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 1) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 4);
+						coex_dm->ps_tdma_du_adj_type =
+							4;
+					} else if (coex_dm->cur_ps_tdma == 9) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 12);
+						coex_dm->ps_tdma_du_adj_type =
+							12;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 4) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 2);
+						coex_dm->ps_tdma_du_adj_type =
+							2;
+					} else if (coex_dm->cur_ps_tdma == 12) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 10);
+						coex_dm->ps_tdma_du_adj_type =
+							10;
+					}
+				}
+			}
+		} else if (max_interval == 3) {
+			if (tx_pause) {
+				if (coex_dm->cur_ps_tdma == 1) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 2) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 3) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 7);
+					coex_dm->ps_tdma_du_adj_type = 7;
+				} else if (coex_dm->cur_ps_tdma == 4) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 8);
+					coex_dm->ps_tdma_du_adj_type = 8;
+				}
+				if (coex_dm->cur_ps_tdma == 9) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 10) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 11) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 15);
+					coex_dm->ps_tdma_du_adj_type = 15;
+				} else if (coex_dm->cur_ps_tdma == 12) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 16);
+					coex_dm->ps_tdma_du_adj_type = 16;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 5) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 8);
+						coex_dm->ps_tdma_du_adj_type =
+							8;
+					} else if (coex_dm->cur_ps_tdma == 13) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 16);
+						coex_dm->ps_tdma_du_adj_type =
+							16;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 8) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 7) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 6) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 7);
+						coex_dm->ps_tdma_du_adj_type =
+							7;
+					} else if (coex_dm->cur_ps_tdma == 16) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 15) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					} else if (coex_dm->cur_ps_tdma == 14) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 15);
+						coex_dm->ps_tdma_du_adj_type =
+							15;
+					}
+				}
+			} else {
+				if (coex_dm->cur_ps_tdma == 5) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 6) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 7) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 3);
+					coex_dm->ps_tdma_du_adj_type = 3;
+				} else if (coex_dm->cur_ps_tdma == 8) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 4);
+					coex_dm->ps_tdma_du_adj_type = 4;
+				}
+				if (coex_dm->cur_ps_tdma == 13) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 14) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 15) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 11);
+					coex_dm->ps_tdma_du_adj_type = 11;
+				} else if (coex_dm->cur_ps_tdma == 16) {
+					btc8821a2ant_ps_tdma(btcoexist,
+							NORMAL_EXEC, true, 12);
+					coex_dm->ps_tdma_du_adj_type = 12;
+				}
+				if (result == -1) {
+					if (coex_dm->cur_ps_tdma == 1) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 4);
+						coex_dm->ps_tdma_du_adj_type =
+							4;
+					} else if (coex_dm->cur_ps_tdma == 9) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 12);
+						coex_dm->ps_tdma_du_adj_type =
+							12;
+					}
+				} else if (result == 1) {
+					if (coex_dm->cur_ps_tdma == 4) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 3) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 2) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 3);
+						coex_dm->ps_tdma_du_adj_type =
+							3;
+					} else if (coex_dm->cur_ps_tdma == 12) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 11) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					} else if (coex_dm->cur_ps_tdma == 10) {
+						btc8821a2ant_ps_tdma(
+							btcoexist, NORMAL_EXEC,
+							true, 11);
+						coex_dm->ps_tdma_du_adj_type =
+							11;
+					}
+				}
+			}
+		}
 	}
 
 	/* if current PsTdma not match with the recorded one
 	 * (when scan, dhcp...), then we have to adjust it back to
 	 * the previous recorded one.
 	 */
-	if (coex_dm->cur_ps_tdma != coex_dm->tdma_adj_type) {
-		bool	scan = false, link = false, roam = false;
+	if (coex_dm->cur_ps_tdma != coex_dm->ps_tdma_du_adj_type) {
+		bool scan = false, link = false, roam = false;
 
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], PsTdma type dismatch!!!, cur_ps_tdma = %d, recordPsTdma = %d\n",
-			    coex_dm->cur_ps_tdma, coex_dm->tdma_adj_type);
+			 coex_dm->cur_ps_tdma, coex_dm->ps_tdma_du_adj_type);
 
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
 		btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
 
 		if (!scan && !link && !roam) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true,
-						coex_dm->tdma_adj_type);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true,
+					     coex_dm->ps_tdma_du_adj_type);
 		} else {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], roaming/link/scan is under progress, will adjust next time!!!\n");
 		}
 	}
-
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 0x6);
 }
 
 /* SCO only or SCO+PAN(HS)*/
-static void halbtc8821a2ant_action_sco(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_sco(struct btc_coexist *btcoexist)
 {
-	u8	wifi_rssi_state, bt_rssi_state;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+	u8 wifi_rssi_state, bt_rssi_state;
 	u32 wifi_bw;
 
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 4);
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 4);
+
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	if (BTC_WIFI_BW_LEGACY == wifi_bw) {
+	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
 		/* for SCO quality at 11b/g mode */
-		halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC,
-					   0x5a5a5a5a, 0x5a5a5a5a, 0xffff, 0x3);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 	} else {
 		/* for SCO quality & wifi performance balance at 11n mode */
-		halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC,
-					   0x5aea5aea, 0x5aea5aea, 0xffff, 0x3);
+		if (wifi_bw == BTC_WIFI_BW_HT40) {
+			btc8821a2ant_coex_table_with_type(btcoexist,
+							  NORMAL_EXEC, 8);
+		} else {
+			if (bt_link_info->sco_only)
+				btc8821a2ant_coex_table_with_type(
+					btcoexist, NORMAL_EXEC, 17);
+			else
+				btc8821a2ant_coex_table_with_type(
+					btcoexist, NORMAL_EXEC, 12);
+		}
 	}
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism
-		 * halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
-		 */
-
-		halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-					false, 0); /*for voice quality*/
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	/* for voice quality */
+	btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 0);
 
-		/* sw mechanism */
+	/* sw mechanism */
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   true, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   true, 0x18);
 		}
 	} else {
-		/* fw mechanism
-		 * halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 5);
-		 */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 0); /*for voice quality*/
-		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						false, 0); /*for voice quality*/
-		}
-
-		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   true, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   true, 0x18);
 		}
 	}
 }
 
-static void halbtc8821a2ant_action_hid(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_hid(struct btc_coexist *btcoexist)
 {
-	u8	wifi_rssi_state, bt_rssi_state;
-	u32	wifi_bw;
+	u8 wifi_rssi_state, bt_rssi_state;
+	u32 wifi_bw;
 
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist,
-							  0, 2, 15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+		2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	if (BTC_WIFI_BW_LEGACY == wifi_bw) {
+	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
 		/* for HID at 11b/g mode */
-		halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-					   0x5a5a5a5a, 0xffff, 0x3);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
 	} else {
 		/* for HID quality & wifi performance balance at 11n mode */
-		halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-					   0x5aea5aea, 0xffff, 0x3);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 2);
 	}
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 9);
-		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 13);
-		}
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 24);
 
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 9);
-		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 13);
-		}
-
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
 /* A2DP only / PAN(EDR) only/ A2DP+PAN(HS) */
-static void halbtc8821a2ant_action_a2dp(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_a2dp(struct btc_coexist *btcoexist)
 {
-	u8		wifi_rssi_state, bt_rssi_state;
-	u32		wifi_bw;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u8 ap_num = 0;
+	u32 wifi_bw;
 
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+		2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-	/* fw dac swing is called in btc8821a2ant_tdma_dur_adj()
-	 * halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-	 */
+	if ((ap_num >= 10) && BTC_RSSI_HIGH(wifi_rssi_state1) &&
+	    BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
-	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff,
+					  0x0);
+		btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false,
+					0x8);
+		btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 
-	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, false, 1);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23);
+
+		/* sw mechanism */
+		btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+		if (wifi_bw == BTC_WIFI_BW_HT40) {
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   true, 0x6);
 		} else {
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 1);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   true, 0x6);
 		}
+		return;
+	}
 
-		/* sw mechanism */
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+	else
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
+
+	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23);
+	} else {
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23);
+	}
+
+	/* sw mechanism */
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, false, 1);
-		} else {
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 1);
-		}
-
-		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8821a2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
 {
-	u8		wifi_rssi_state, bt_rssi_state, bt_info_ext;
-	u32		wifi_bw;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u32 wifi_bw;
 
-	bt_info_ext = coex_sta->bt_info_ext;
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+		2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-	/*fw dac swing is called in btc8821a2ant_tdma_dur_adj()
-	 *halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
-	 */
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism */
-		if (bt_info_ext&BIT0) {
-			/*a2dp basic rate*/
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 2);
-		} else {
-			/*a2dp edr rate*/
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 1);
-		}
+	btc8821a2ant_tdma_duration_adjust(btcoexist, false, true, 2);
 
-		/* sw mechanism */
+	/* sw mechanism */
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		/* fw mechanism */
-		if (bt_info_ext&BIT0) {
-			/* a2dp basic rate */
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 2);
-		} else {
-			/* a2dp edr rate */
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 1);
-		}
-
-		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8821a2ant_action_pan_edr(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_pan_edr(struct btc_coexist *btcoexist)
 {
-	u8		wifi_rssi_state, bt_rssi_state;
-	u32		wifi_bw;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u32 wifi_bw;
 
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+				2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
-	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
 
-	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (BTC_WIFI_BW_LEGACY == wifi_bw) {
-		/* for HID at 11b/g mode */
-		halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-					   0x5aff5aff, 0xffff, 0x3);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	else
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state)) {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 10);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
 	} else {
-		/* for HID quality & wifi performance balance at 11n mode */
-		halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-					   0x5aff5aff, 0xffff, 0x3);
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
 	}
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 1);
-		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-		}
+	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 26);
+	else
+		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 26);
 
-		/* sw mechanism */
+	/* sw mechanism */
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 1);
-		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 5);
-		}
-
-		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
 /* PAN(HS) only */
-static void halbtc8821a2ant_action_pan_hs(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_pan_hs(struct btc_coexist *btcoexist)
 {
-	u8		wifi_rssi_state, bt_rssi_state;
-	u32		wifi_bw;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u32 wifi_bw;
 
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist,
-							  0, 2, 15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+				2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
-	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism */
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC,
-						   true);
-		} else {
-			halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC,
-						   false);
-		}
-		halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+	else
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-		/* sw mechanism */
+	btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		/* fw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_dec_bt_pwr(btcoexist,
-						   NORMAL_EXEC, true);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			halbtc8821a2ant_dec_bt_pwr(btcoexist,
-						   NORMAL_EXEC, false);
-		}
-
-		halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
-
-		/* sw mechanism */
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
-		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
 /* PAN(EDR)+A2DP */
-static void halbtc8821a2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 {
-	u8	wifi_rssi_state, bt_rssi_state, bt_info_ext;
-	u32	wifi_bw;
+	u8 wifi_rssi_state, wifi_rssi_state1, bt_rssi_state;
+	u32 wifi_bw;
 
-	bt_info_ext = coex_sta->bt_info_ext;
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	wifi_rssi_state1 = btc8821a2ant_wifi_rssi_state(btcoexist, 1, 2,
+				BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+				2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
+
+	btcoexist->btc_set_rf_reg(btcoexist, BTC_RF_A, 0x1, 0xfffff, 0x0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
+	else
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(wifi_rssi_state1) && BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-				   0x5afa5afa, 0xffff, 0x3);
+	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 12);
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
-			btc8821a2ant_tdma_dur_adj(btcoexist, false,
-						  false, 3);
+		if (wifi_bw == BTC_WIFI_BW_HT40)
+			btc8821a2ant_tdma_duration_adjust(btcoexist, false,
+							  true, 3);
 		else
-			btc8821a2ant_tdma_dur_adj(btcoexist, false,
-						  true, 3);
+			btc8821a2ant_tdma_duration_adjust(btcoexist, false,
+							  false, 3);
+	} else {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 13);
+		btc8821a2ant_tdma_duration_adjust(btcoexist, false, true, 3);
+	}
 
-		/* sw mechanism */
+	/* sw mechanism	 */
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		/* fw mechanism */
-		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, false, 3);
-		else
-			btc8821a2ant_tdma_dur_adj(btcoexist, false, true, 3);
-
-		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, false,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, false,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8821a2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 {
-	u8	wifi_rssi_state, bt_rssi_state;
-	u32	wifi_bw;
+	u8 wifi_rssi_state, bt_rssi_state;
+	u32 wifi_bw;
 
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist,
+				2, BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES, 0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-				   0x5a5f5a5f, 0xffff, 0x3);
+	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
+		/* for HID at 11b/g mode */
+		btc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
+					0x5a5f5a5f, 0xffff, 0x3);
+	} else {
+		/* for HID quality & wifi performance balance at 11n mode */
+		btc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
+					0x5a5f5a5f, 0xffff, 0x3);
+	}
 
-	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 3);
+	if (wifi_bw == BTC_WIFI_BW_HT40) {
+		btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 3);
 		/* fw mechanism */
 		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
+					     true, 10);
 		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
 		}
 
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
-		halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+		btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 		/* fw mechanism */
 		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 10);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10);
 		} else {
-			halbtc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC,
-						true, 14);
+			btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14);
 		}
 
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
@@ -2944,42 +3220,70 @@ static void halbtc8821a2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 /* HID+A2DP+PAN(EDR) */
 static void btc8821a2ant_act_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 {
-	u8	wifi_rssi_state, bt_rssi_state, bt_info_ext;
-	u32	wifi_bw;
+	u8 wifi_rssi_state, bt_rssi_state, bt_info_ext;
+	u32 wifi_bw;
 
 	bt_info_ext = coex_sta->bt_info_ext;
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist,
-							  0, 2, 15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
 
-	halbtc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8821a2ant_limited_rx(btcoexist, NORMAL_EXEC, false, false, 0x8);
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 2);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-				   0x5a5a5a5a, 0xffff, 0x3);
+	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
+		/* for HID at 11b/g mode */
+		btc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
+					0x5a5a5a5a, 0xffff, 0x3);
+	} else {
+		/* for HID quality & wifi performance balance at 11n mode */
+		btc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
+					0x5a5a5a5a, 0xffff, 0x3);
+	}
 
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		/* fw mechanism */
-		btc8821a2ant_tdma_dur_adj(btcoexist, true, true, 3);
+		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			if (bt_info_ext&BIT0) {
+				/* a2dp basic rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+							true, true, 3);
+			} else {
+				/* a2dp edr rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+							true, true, 3);
+			}
+		} else {
+			if (bt_info_ext&BIT0) {
+				/* a2dp basic rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+							true, true, 3);
+			} else {
+				/* a2dp edr rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+							true, true, 3);
+			}
+		}
 
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
 		/* fw mechanism */
@@ -2987,103 +3291,183 @@ static void btc8821a2ant_act_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
 			if (bt_info_ext&BIT0) {
 				/* a2dp basic rate */
-				btc8821a2ant_tdma_dur_adj(btcoexist, true,
-							  false, 3);
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+							true, false, 3);
 			} else {
 				/* a2dp edr rate */
-				btc8821a2ant_tdma_dur_adj(btcoexist, true,
-							  false, 3);
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+							true, false, 3);
 			}
 		} else {
 			if (bt_info_ext&BIT0) {
 				/* a2dp basic rate */
-				btc8821a2ant_tdma_dur_adj(btcoexist, true,
-							  true, 3);
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  3);
 			} else {
 				/* a2dp edr rate */
-				btc8821a2ant_tdma_dur_adj(btcoexist, true,
-							  true, 3);
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  3);
 			}
 		}
 
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8821a2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 {
-	u8	wifi_rssi_state, bt_rssi_state, bt_info_ext;
-	u32	wifi_bw;
+	u8 wifi_rssi_state, bt_rssi_state, bt_info_ext;
+	u32 wifi_bw;
 
 	bt_info_ext = coex_sta->bt_info_ext;
-	wifi_rssi_state = halbtc8821a2ant_wifi_rssi_state(btcoexist, 0, 2,
-							  15, 0);
-	bt_rssi_state = halbtc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
+	wifi_rssi_state = btc8821a2ant_wifi_rssi_state(btcoexist, 0, 2, 15, 0);
+	bt_rssi_state = btc8821a2ant_bt_rssi_state(btcoexist, 2, 35, 0);
 
-	if (halbtc8821a2ant_need_to_dec_bt_pwr(btcoexist))
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
+	if (BTC_RSSI_HIGH(bt_rssi_state))
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, true);
 	else
-		halbtc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
+		btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, false);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
-	halbtc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
-				   0x5f5b5f5b, 0xffffff, 0x3);
+	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 7);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE,
+					      0x0, 0x0);
+	} else {
+		btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 14);
+		btc8821a2ant_power_save_state(btcoexist, BTC_PS_LPS_ON, 0x50,
+					      0x4);
+	}
 
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
 		/* fw mechanism */
-		btc8821a2ant_tdma_dur_adj(btcoexist, true, true, 2);
+		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			if (bt_info_ext & BIT0) {
+				/* a2dp basic rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			} else {
+				/* a2dp edr rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			}
+		} else {
+			if (bt_info_ext & BIT0) {
+				/* a2dp basic rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			} else {
+				/* a2dp edr rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			}
+		}
 
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, true, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, true, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	} else {
 		/* fw mechanism */
-		btc8821a2ant_tdma_dur_adj(btcoexist, true, true, 2);
+		if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
+		    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
+			if (bt_info_ext & BIT0) {
+				/* a2dp basic rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+
+			} else {
+				/* a2dp edr rate */
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			}
+		} else {
+			if (bt_info_ext & BIT0) {
+				/*a2dp basic rate*/
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			} else {
+				/*a2dp edr rate*/
+				btc8821a2ant_tdma_duration_adjust(btcoexist,
+								  true, true,
+								  2);
+			}
+		}
 
 		/* sw mechanism */
 		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
 		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, true, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, true, false,
+						   false, 0x18);
 		} else {
-			btc8821a2ant_sw_mech1(btcoexist, false, true,
-					      false, false);
-			btc8821a2ant_sw_mech2(btcoexist, false, false,
-					      false, 0x18);
+			btc8821a2ant_sw_mechanism1(btcoexist, false, true,
+						   false, false);
+			btc8821a2ant_sw_mechanism2(btcoexist, false, false,
+						   false, 0x18);
 		}
 	}
 }
 
-static void halbtc8821a2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
+static void btc8821a2ant_action_wifi_multi_port(struct btc_coexist *btcoexist)
+{
+	btc8821a2ant_fw_dac_swing_lvl(btcoexist, NORMAL_EXEC, 6);
+	btc8821a2ant_dec_bt_pwr(btcoexist, NORMAL_EXEC, 0);
+
+	/* sw all off */
+	btc8821a2ant_sw_mechanism1(btcoexist, false, false, false, false);
+	btc8821a2ant_sw_mechanism2(btcoexist, false, false, false, 0x18);
+
+	/* hw all off */
+	btc8821a2ant_coex_table_with_type(btcoexist, NORMAL_EXEC, 0);
+
+	btc8821a2ant_power_save_state(btcoexist, BTC_PS_WIFI_NATIVE, 0x0, 0x0);
+	btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, false, 1);
+}
+
+static void btc8821a2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	bool	wifi_under_5g = false;
-	u8	algorithm = 0;
+	struct btc_bt_link_info *bt_link_info = &btcoexist->bt_link_info;
+	bool wifi_under_5g = false;
+	u8 algorithm = 0;
+	u32 num_of_wifi_link = 0;
+	u32 wifi_link_status = 0;
+	bool miracast_plus_bt = false;
+	bool scan = false, link = false, roam = false;
 
 	if (btcoexist->manual_control) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3091,30 +3475,73 @@ static void halbtc8821a2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		return;
 	}
 
-	btcoexist->btc_get(btcoexist,
-		BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_UNDER_5G, &wifi_under_5g);
 
 	if (wifi_under_5g) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], RunCoexistMechanism(), run 5G coex setting!!<===\n");
-		halbtc8821a2ant_coex_under_5g(btcoexist);
+		btc8821a2ant_coex_under_5g(btcoexist);
 		return;
 	}
 
-	algorithm = halbtc8821a2ant_action_algorithm(btcoexist);
+	if (coex_sta->under_ips) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], wifi is under IPS !!!\n");
+		return;
+	}
+
+	algorithm = btc8821a2ant_action_algorithm(btcoexist);
 	if (coex_sta->c2h_bt_inquiry_page &&
 	    (BT_8821A_2ANT_COEX_ALGO_PANHS != algorithm)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], BT is under inquiry/page scan !!\n");
-		halbtc8821a2ant_bt_inquiry_page(btcoexist);
+		btc8821a2ant_action_bt_inquiry(btcoexist);
 		return;
 	}
 
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_LINK, &link);
+	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_ROAM, &roam);
+
+	if (scan || link || roam) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "[BTCoex], WiFi is under Link Process !!\n");
+		btc8821a2ant_action_wifi_link_process(btcoexist);
+		return;
+	}
+
+	/* for P2P */
+	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_LINK_STATUS,
+			   &wifi_link_status);
+	num_of_wifi_link = wifi_link_status >> 16;
+
+	if ((num_of_wifi_link >= 2) ||
+	    (wifi_link_status & WIFI_P2P_GO_CONNECTED)) {
+		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
+			 "############# [BTCoex],  Multi-Port num_of_wifi_link = %d, wifi_link_status = 0x%x\n",
+			 num_of_wifi_link, wifi_link_status);
+
+		if (bt_link_info->bt_link_exist)
+			miracast_plus_bt = true;
+		else
+			miracast_plus_bt = false;
+
+		btcoexist->btc_set(btcoexist, BTC_SET_BL_MIRACAST_PLUS_BT,
+				   &miracast_plus_bt);
+		btc8821a2ant_action_wifi_multi_port(btcoexist);
+
+		return;
+	}
+
+	miracast_plus_bt = false;
+	btcoexist->btc_set(btcoexist, BTC_SET_BL_MIRACAST_PLUS_BT,
+			   &miracast_plus_bt);
+
 	coex_dm->cur_algorithm = algorithm;
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Algorithm = %d\n", coex_dm->cur_algorithm);
 
-	if (halbtc8821a2ant_is_common_action(btcoexist)) {
+	if (btc8821a2ant_is_common_action(btcoexist)) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], Action 2-Ant common\n");
 		coex_dm->reset_tdma_adjust = true;
@@ -3130,42 +3557,42 @@ static void halbtc8821a2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		case BT_8821A_2ANT_COEX_ALGO_SCO:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = SCO\n");
-			halbtc8821a2ant_action_sco(btcoexist);
+			btc8821a2ant_action_sco(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_HID:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = HID\n");
-			halbtc8821a2ant_action_hid(btcoexist);
+			btc8821a2ant_action_hid(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = A2DP\n");
-			halbtc8821a2ant_action_a2dp(btcoexist);
+			btc8821a2ant_action_a2dp(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_A2DP_PANHS:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = A2DP+PAN(HS)\n");
-			halbtc8821a2ant_action_a2dp_pan_hs(btcoexist);
+			btc8821a2ant_action_a2dp_pan_hs(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_PANEDR:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = PAN(EDR)\n");
-			halbtc8821a2ant_action_pan_edr(btcoexist);
+			btc8821a2ant_action_pan_edr(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_PANHS:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = HS mode\n");
-			halbtc8821a2ant_action_pan_hs(btcoexist);
+			btc8821a2ant_action_pan_hs(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_PANEDR_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = PAN+A2DP\n");
-			halbtc8821a2ant_action_pan_edr_a2dp(btcoexist);
+			btc8821a2ant_action_pan_edr_a2dp(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_PANEDR_HID:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = PAN(EDR)+HID\n");
-			halbtc8821a2ant_action_pan_edr_hid(btcoexist);
+			btc8821a2ant_action_pan_edr_hid(btcoexist);
 			break;
 		case BT_8821A_2ANT_COEX_ALGO_HID_A2DP_PANEDR:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3175,26 +3602,22 @@ static void halbtc8821a2ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 		case BT_8821A_2ANT_COEX_ALGO_HID_A2DP:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = HID+A2DP\n");
-			halbtc8821a2ant_action_hid_a2dp(btcoexist);
+			btc8821a2ant_action_hid_a2dp(btcoexist);
 			break;
 		default:
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "[BTCoex], Action 2-Ant, algorithm = coexist All Off!!\n");
-			halbtc8821a2ant_coex_all_off(btcoexist);
+			btc8821a2ant_coex_all_off(btcoexist);
 			break;
 		}
 		coex_dm->pre_algorithm = coex_dm->cur_algorithm;
 	}
 }
 
-/*============================================================
- *work around function start with wa_halbtc8821a2ant_
- *============================================================
- *============================================================
- * extern function start with EXhalbtc8821a2ant_
- *============================================================
- */
-void ex_halbtc8821a2ant_init_hwconfig(struct btc_coexist *btcoexist)
+/**************************************************************
+ * extern function start with ex_btc8821a2ant_
+ **************************************************************/
+void ex_btc8821a2ant_init_hwconfig(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 	u8 u1tmp = 0;
@@ -3212,36 +3635,30 @@ void ex_halbtc8821a2ant_init_hwconfig(struct btc_coexist *btcoexist)
 	u1tmp |= 0x5;
 	btcoexist->btc_write_1byte(btcoexist, 0x790, u1tmp);
 
-	/*Antenna config */
-	halbtc8821a2ant_set_ant_path(btcoexist,
-				     BTC_ANT_WIFI_AT_MAIN, true, false);
+	/* Antenna config */
+	btc8821a2ant_set_ant_path(btcoexist, BTC_ANT_WIFI_AT_MAIN, true, false);
 
 	/* PTA parameter */
-	halbtc8821a2ant_coex_table(btcoexist,
-				   FORCE_EXEC, 0x55555555, 0x55555555,
-				   0xffff, 0x3);
+	btc8821a2ant_coex_table_with_type(btcoexist, FORCE_EXEC, 0);
 
 	/* Enable counter statistics */
-	/*0x76e[3] = 1, WLAN_Act control by PTA*/
-	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0xc);
+	/* 0x76e[3] = 1, WLAN_Act control by PTA */
+	btcoexist->btc_write_1byte(btcoexist, 0x76e, 0x4);
 	btcoexist->btc_write_1byte(btcoexist, 0x778, 0x3);
 	btcoexist->btc_write_1byte_bitmask(btcoexist, 0x40, 0x20, 0x1);
 }
 
-void ex_halbtc8821a2ant_init_coex_dm(struct btc_coexist *btcoexist)
+void ex_btc8821a2ant_init_coex_dm(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Coex Mechanism Init!!\n");
 
-	halbtc8821a2ant_init_coex_dm(btcoexist);
+	btc8821a2ant_init_coex_dm(btcoexist);
 }
 
-void
-ex_halbtc8821a2ant_display_coex_info(
-	struct btc_coexist *btcoexist
-	)
+void ex_btc8821a2ant_display_coex_info(struct btc_coexist *btcoexist)
 {
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	struct btc_stack_info *stack_info = &btcoexist->stack_info;
@@ -3397,7 +3814,7 @@ ex_halbtc8821a2ant_display_coex_info(
 
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG,
 			 "\r\n %-35s = %d/ %d ", "DecBtPwr/ IgnWlanAct",
-			 coex_dm->cur_dec_bt_pwr,
+			 coex_dm->cur_dec_bt_pwr_lvl,
 			 coex_dm->cur_ignore_wlan_act);
 	}
 
@@ -3475,7 +3892,7 @@ ex_halbtc8821a2ant_display_coex_info(
 	btcoexist->btc_disp_dbg_msg(btcoexist, BTC_DBG_DISP_COEX_STATISTICS);
 }
 
-void ex_halbtc8821a2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3483,16 +3900,15 @@ void ex_halbtc8821a2ant_ips_notify(struct btc_coexist *btcoexist, u8 type)
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS ENTER notify\n");
 		coex_sta->under_ips = true;
-		halbtc8821a2ant_coex_all_off(btcoexist);
+		btc8821a2ant_coex_all_off(btcoexist);
 	} else if (BTC_IPS_LEAVE == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 			 "[BTCoex], IPS LEAVE notify\n");
 		coex_sta->under_ips = false;
-		/*halbtc8821a2ant_init_coex_dm(btcoexist);*/
 	}
 }
 
-void ex_halbtc8821a2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3507,7 +3923,7 @@ void ex_halbtc8821a2ant_lps_notify(struct btc_coexist *btcoexist, u8 type)
 	}
 }
 
-void ex_halbtc8821a2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3520,7 +3936,7 @@ void ex_halbtc8821a2ant_scan_notify(struct btc_coexist *btcoexist, u8 type)
 	}
 }
 
-void ex_halbtc8821a2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
+void ex_btc8821a2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
@@ -3533,13 +3949,14 @@ void ex_halbtc8821a2ant_connect_notify(struct btc_coexist *btcoexist, u8 type)
 	}
 }
 
-void ex_halbtc8821a2ant_media_status_notify(struct btc_coexist *btcoexist,
-					    u8 type)
+void ex_btc8821a2ant_media_status_notify(struct btc_coexist *btcoexist,
+					 u8 type)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8	h2c_parameter[3] = {0};
-	u32	wifi_bw;
-	u8	wifi_central_chnl;
+	u8 h2c_parameter[3] = {0};
+	u32 wifi_bw;
+	u8 wifi_central_chnl;
+	u8 ap_num = 0;
 
 	if (BTC_MEDIA_CONNECT == type) {
 		RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
@@ -3549,7 +3966,7 @@ void ex_halbtc8821a2ant_media_status_notify(struct btc_coexist *btcoexist,
 			 "[BTCoex], MEDIA disconnect notify\n");
 	}
 
-	/* only 2.4G we need to inform bt the chnl mask*/
+	/* only 2.4G we need to inform bt the chnl mask */
 	btcoexist->btc_get(btcoexist, BTC_GET_U1_WIFI_CENTRAL_CHNL,
 			   &wifi_central_chnl);
 	if ((BTC_MEDIA_CONNECT == type) &&
@@ -3557,10 +3974,15 @@ void ex_halbtc8821a2ant_media_status_notify(struct btc_coexist *btcoexist,
 		h2c_parameter[0] = 0x1;
 		h2c_parameter[1] = wifi_central_chnl;
 		btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
-		if (BTC_WIFI_BW_HT40 == wifi_bw)
+		if (wifi_bw == BTC_WIFI_BW_HT40) {
 			h2c_parameter[2] = 0x30;
-		else
+		} else {
 			h2c_parameter[2] = 0x20;
+			if (ap_num < 10)
+				h2c_parameter[2] = 0x30;
+			else
+				h2c_parameter[2] = 0x20;
+		}
 	}
 
 	coex_dm->wifi_chnl_info[0] = h2c_parameter[0];
@@ -3576,8 +3998,9 @@ void ex_halbtc8821a2ant_media_status_notify(struct btc_coexist *btcoexist,
 	btcoexist->btc_fill_h2c(btcoexist, 0x66, 3, h2c_parameter);
 }
 
-void ex_halbtc8821a2ant_special_packet_notify(struct btc_coexist *btcoexist,
-					      u8 type) {
+void ex_btc8821a2ant_special_packet_notify(struct btc_coexist *btcoexist,
+					   u8 type)
+{
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	if (type == BTC_PACKET_DHCP) {
@@ -3586,19 +4009,18 @@ void ex_halbtc8821a2ant_special_packet_notify(struct btc_coexist *btcoexist,
 	}
 }
 
-void ex_halbtc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
-				       u8 *tmp_buf, u8 length)
+void ex_btc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
+				    u8 *tmp_buf, u8 length)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	u8		bt_info = 0;
-	u8		i, rsp_source = 0;
-	static u32	set_bt_lna_cnt, set_bt_psd_mode;
-	bool		bt_busy = false, limited_dig = false;
-	bool		wifi_connected = false, bt_hs_on = false;
+	u8 bt_info = 0;
+	u8 i, rsp_source = 0;
+	bool bt_busy = false, limited_dig = false;
+	bool wifi_connected = false, bt_hs_on = false;
 
 	coex_sta->c2h_bt_info_req_sent = false;
 
-	rsp_source = tmp_buf[0]&0xf;
+	rsp_source = tmp_buf[0] & 0xf;
 	if (rsp_source >= BT_INFO_SRC_8821A_2ANT_MAX)
 		rsp_source = BT_INFO_SRC_8821A_2ANT_WIFI_FW;
 	coex_sta->bt_info_c2h_cnt[rsp_source]++;
@@ -3610,7 +4032,7 @@ void ex_halbtc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_sta->bt_info_c2h[rsp_source][i] = tmp_buf[i];
 		if (i == 1)
 			bt_info = tmp_buf[i];
-		if (i == length-1) {
+		if (i == length - 1) {
 			RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 				 "0x%02x]\n", tmp_buf[i]);
 		} else {
@@ -3620,7 +4042,8 @@ void ex_halbtc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
 	}
 
 	if (BT_INFO_SRC_8821A_2ANT_WIFI_FW != rsp_source) {
-		coex_sta->bt_retry_cnt =	/* [3:0]*/
+		/* [3:0] */
+		coex_sta->bt_retry_cnt =
 			coex_sta->bt_info_c2h[rsp_source][2]&0xf;
 
 		coex_sta->bt_rssi =
@@ -3629,53 +4052,28 @@ void ex_halbtc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
 		coex_sta->bt_info_ext =
 			coex_sta->bt_info_c2h[rsp_source][4];
 
-		/* Here we need to resend some wifi info to BT*/
-		/* because bt is reset and loss of the info.*/
+		/* Here we need to resend some wifi info to BT
+		 * because bt is reset and loss of the info
+		 */
 		if ((coex_sta->bt_info_ext & BIT1)) {
 			btcoexist->btc_get(btcoexist,
 				BTC_GET_BL_WIFI_CONNECTED, &wifi_connected);
 			if (wifi_connected) {
-				ex_halbtc8821a2ant_media_status_notify(btcoexist,
+				ex_btc8821a2ant_media_status_notify(btcoexist,
 					BTC_MEDIA_CONNECT);
 			} else {
-				ex_halbtc8821a2ant_media_status_notify(btcoexist,
+				ex_btc8821a2ant_media_status_notify(btcoexist,
 					BTC_MEDIA_DISCONNECT);
 			}
 
-			set_bt_psd_mode = 0;
-		}
-		if (set_bt_psd_mode <= 3) {
-			halbtc8821a2ant_set_bt_psd_mode(btcoexist, FORCE_EXEC,
-							0x0); /*fix CH-BW mode*/
-			set_bt_psd_mode++;
-		}
-
-		if (coex_dm->cur_bt_lna_constrain) {
-			if (!(coex_sta->bt_info_ext & BIT2)) {
-				if (set_bt_lna_cnt <= 3) {
-					btc8821a2_set_bt_lna_const(btcoexist,
-								   FORCE_EXEC,
-								   true);
-					set_bt_lna_cnt++;
-				}
-			}
-		} else {
-			set_bt_lna_cnt = 0;
 		}
 
 		if ((coex_sta->bt_info_ext & BIT3)) {
-			halbtc8821a2ant_ignore_wlan_act(btcoexist,
-							FORCE_EXEC, false);
+			btc8821a2ant_ignore_wlan_act(btcoexist,
+						     FORCE_EXEC, false);
 		} else {
 			/* BT already NOT ignore Wlan active, do nothing here.*/
 		}
-
-		if ((coex_sta->bt_info_ext & BIT4)) {
-			/* BT auto report already enabled, do nothing*/
-		} else {
-			halbtc8821a2ant_bt_auto_report(btcoexist,
-						       FORCE_EXEC, true);
-		}
 	}
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_HS_OPERATION, &bt_hs_on);
@@ -3718,8 +4116,7 @@ void ex_halbtc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
 			coex_dm->bt_status = BT_8821A_2ANT_BT_STATUS_IDLE;
 		}
 
-		if (bt_hs_on)
-			coex_dm->bt_status = BT_8821A_2ANT_BT_STATUS_NON_IDLE;
+		btc8821a2ant_update_bt_link_info(btcoexist);
 	}
 
 	if (BT_8821A_2ANT_BT_STATUS_NON_IDLE == coex_dm->bt_status)
@@ -3736,27 +4133,27 @@ void ex_halbtc8821a2ant_bt_info_notify(struct btc_coexist *btcoexist,
 	btcoexist->btc_set(btcoexist,
 		BTC_SET_BL_BT_LIMITED_DIG, &limited_dig);
 
-	halbtc8821a2ant_run_coexist_mechanism(btcoexist);
+	btc8821a2ant_run_coexist_mechanism(btcoexist);
 }
 
-void ex_halbtc8821a2ant_halt_notify(struct btc_coexist *btcoexist)
+void ex_btc8821a2ant_halt_notify(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], Halt notify\n");
 
-	halbtc8821a2ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
-	ex_halbtc8821a2ant_media_status_notify(btcoexist, BTC_MEDIA_DISCONNECT);
+	btc8821a2ant_ignore_wlan_act(btcoexist, FORCE_EXEC, true);
+	ex_btc8821a2ant_media_status_notify(btcoexist, BTC_MEDIA_DISCONNECT);
 }
 
-void ex_halbtc8821a2ant_periodical(struct btc_coexist *btcoexist)
+void ex_btc8821a2ant_periodical(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv = btcoexist->adapter;
-	static u8	dis_ver_info_cnt;
-	u32		fw_ver = 0, bt_patch_ver = 0;
+	static u8 dis_ver_info_cnt;
 	struct btc_board_info *board_info = &btcoexist->board_info;
 	struct btc_stack_info *stack_info = &btcoexist->stack_info;
+	u32 fw_ver = 0, bt_patch_ver = 0;
 
 	RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
 		 "[BTCoex], ==========================Periodical===========================\n");
@@ -3785,7 +4182,7 @@ void ex_halbtc8821a2ant_periodical(struct btc_coexist *btcoexist)
 			 "[BTCoex], ****************************************************************\n");
 	}
 
-	halbtc8821a2ant_query_bt_info(btcoexist);
-	halbtc8821a2ant_monitor_bt_ctr(btcoexist);
-	btc8821a2ant_mon_bt_en_dis(btcoexist);
+	btc8821a2ant_query_bt_info(btcoexist);
+	btc8821a2ant_monitor_bt_ctr(btcoexist);
+	btc8821a2ant_monitor_wifi_ctr(btcoexist);
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.h b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.h
index b4cf1f53d510..535ca10e910b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.h
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.h
@@ -38,6 +38,11 @@
 
 #define	BTC_RSSI_COEX_THRESH_TOL_8821A_2ANT	2
 
+/* WiFi RSSI Threshold for 2-Ant TDMA/1-Ant PS-TDMA translation */
+#define BT_8821A_2ANT_WIFI_RSSI_COEXSWITCH_THRES 42
+/* BT RSSI Threshold for 2-Ant TDMA/1-Ant PS-TDMA translation */
+#define BT_8821A_2ANT_BT_RSSI_COEXSWITCH_THRES	46
+
 enum _BT_INFO_SRC_8821A_2ANT {
 	BT_INFO_SRC_8821A_2ANT_WIFI_FW		= 0x0,
 	BT_INFO_SRC_8821A_2ANT_BT_RSP		= 0x1,
@@ -69,8 +74,8 @@ enum _BT_8821A_2ANT_COEX_ALGO {
 
 struct coex_dm_8821a_2ant {
 	/* fw mechanism */
-	bool		pre_dec_bt_pwr;
-	bool		cur_dec_bt_pwr;
+	bool		pre_dec_bt_pwr_lvl;
+	bool		cur_dec_bt_pwr_lvl;
 	bool		pre_bt_lna_constrain;
 	bool		cur_bt_lna_constrain;
 	u8		pre_bt_psd_mode;
@@ -82,8 +87,9 @@ struct coex_dm_8821a_2ant {
 	u8		pre_ps_tdma;
 	u8		cur_ps_tdma;
 	u8		ps_tdma_para[5];
-	u8		tdma_adj_type;
+	u8		ps_tdma_du_adj_type;
 	bool		reset_tdma_adjust;
+	bool		auto_tdma_adjust;
 	bool		pre_ps_tdma_on;
 	bool		cur_ps_tdma_on;
 	bool		pre_bt_auto_report;
@@ -118,6 +124,10 @@ struct coex_dm_8821a_2ant {
 	u8		cur_algorithm;
 	u8		bt_status;
 	u8		wifi_chnl_info[3];
+	u8		pre_lps;
+	u8		cur_lps;
+	u8		pre_rpwm;
+	u8		cur_rpwm;
 };
 
 struct coex_sta_8821a_2ant {
@@ -141,6 +151,19 @@ struct coex_sta_8821a_2ant {
 	bool	c2h_bt_inquiry_page;
 	u8	bt_retry_cnt;
 	u8	bt_info_ext;
+
+	u32	crc_ok_cck;
+	u32	crc_ok_11g;
+	u32	crc_ok_11n;
+	u32	crc_ok_11n_agg;
+
+	u32	crc_err_cck;
+	u32	crc_err_11g;
+	u32	crc_err_11n;
+	u32	crc_err_11n_agg;
+
+	u8	coex_table_type;
+	bool	force_lps_on;
 };
 
 /*===========================================
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
index 150aeb8e79d1..f13000612913 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
@@ -466,7 +466,7 @@ static bool halbtc_set(void *void_btcoexist, u8 set_type, void *in_buf)
 	case BTC_SET_ACT_DISABLE_LOW_POWER:
 		halbtc_disable_low_power();
 		break;
-	case BTC_SET_ACT_UPDATE_ra_mask:
+	case BTC_SET_ACT_UPDATE_RAMASK:
 		btcoexist->bt_info.ra_mask = *u32_tmp;
 		break;
 	case BTC_SET_ACT_SEND_MIMO_PS:
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h
index 601bbe1d22b3..c8271135aaaa 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h
@@ -66,6 +66,15 @@
 #define		BTC_ANT_WIFI_AT_CPL_MAIN		0
 #define		BTC_ANT_WIFI_AT_CPL_AUX			1
 
+enum btc_bt_reg_type {
+	BTC_BT_REG_RF		= 0,
+	BTC_BT_REG_MODEM	= 1,
+	BTC_BT_REG_BLUEWIZE	= 2,
+	BTC_BT_REG_VENDOR	= 3,
+	BTC_BT_REG_LE		= 4,
+	BTC_BT_REG_MAX
+};
+
 enum btc_chip_interface {
 	BTC_INTF_UNKNOWN	= 0,
 	BTC_INTF_PCI		= 1,
@@ -139,6 +148,7 @@ struct btc_board_info {
 	u8 pg_ant_num;	/* pg ant number */
 	u8 btdm_ant_num;	/* ant number for btdm */
 	u8 btdm_ant_pos;
+	u8 single_ant_path; /* current used for 8723b only, 1=>s0,  0=>s1 */
 	bool bt_exist;
 };
 
@@ -205,6 +215,7 @@ enum btc_get_type {
 	BTC_GET_BL_WIFI_ENABLE_ENCRYPTION,
 	BTC_GET_BL_WIFI_UNDER_B_MODE,
 	BTC_GET_BL_EXT_SWITCH,
+	BTC_GET_BL_WIFI_IS_IN_MP_MODE,
 
 	/* type s4Byte */
 	BTC_GET_S4_WIFI_RSSI,
@@ -249,6 +260,8 @@ enum btc_set_type {
 	BTC_SET_BL_TO_REJ_AP_AGG_PKT,
 	BTC_SET_BL_BT_CTRL_AGG_SIZE,
 	BTC_SET_BL_INC_SCAN_DEV_NUM,
+	BTC_SET_BL_BT_TX_RX_MASK,
+	BTC_SET_BL_MIRACAST_PLUS_BT,
 
 	/* type u1Byte */
 	BTC_SET_U1_RSSI_ADJ_VAL_FOR_AGC_TABLE_ON,
@@ -275,7 +288,7 @@ enum btc_set_type {
 	BTC_SET_ACT_NORMAL_LPS,
 	BTC_SET_ACT_INC_FORCE_EXEC_PWR_CMD_CNT,
 	BTC_SET_ACT_DISABLE_LOW_POWER,
-	BTC_SET_ACT_UPDATE_ra_mask,
+	BTC_SET_ACT_UPDATE_RAMASK,
 	BTC_SET_ACT_SEND_MIMO_PS,
 	/* BT Coex related */
 	BTC_SET_ACT_CTRL_BT_INFO,
@@ -366,6 +379,7 @@ typedef void (*bfp_btc_w2)(void *btc_context, u32 reg_addr, u16 data);
 
 typedef void (*bfp_btc_w4)(void *btc_context, u32 reg_addr, u32 data);
 
+typedef void (*bfp_btc_local_reg_w1)(void *btc_context, u32 reg_addr, u8 data);
 typedef void (*bfp_btc_wr_1byte_bit_mask)(void *btc_context, u32 reg_addr,
 					  u8 bit_mask, u8 data);
 
@@ -388,6 +402,9 @@ typedef	bool (*bfp_btc_get)(void *btcoexist, u8 get_type, void *out_buf);
 
 typedef	bool (*bfp_btc_set)(void *btcoexist, u8 set_type, void *in_buf);
 
+typedef void (*bfp_btc_set_bt_reg)(void *btc_context, u8 reg_type, u32 offset,
+				   u32 value);
+
 typedef void (*bfp_btc_disp_dbg_msg)(void *btcoexist, u8 disp_type);
 
 struct btc_bt_info {
@@ -459,6 +476,7 @@ struct btc_bt_link_info {
 	bool hid_only;
 	bool pan_exist;
 	bool pan_only;
+	bool slave_role;
 };
 
 enum btc_antenna_pos {
@@ -492,6 +510,7 @@ struct btc_coexist {
 	bfp_btc_w2 btc_write_2byte;
 	bfp_btc_r4 btc_read_4byte;
 	bfp_btc_w4 btc_write_4byte;
+	bfp_btc_local_reg_w1 btc_write_local_reg_1byte;
 
 	bfp_btc_set_bb_reg btc_set_bb_reg;
 	bfp_btc_get_bb_reg btc_get_bb_reg;
@@ -505,6 +524,8 @@ struct btc_coexist {
 
 	bfp_btc_get btc_get;
 	bfp_btc_set btc_set;
+
+	bfp_btc_set_bt_reg btc_set_bt_reg;
 };
 
 bool halbtc_is_wifi_uplink(struct rtl_priv *adapter);
diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c
index 558c31bf5c80..1bf3eb25c1da 100644
--- a/drivers/net/wireless/realtek/rtlwifi/regd.c
+++ b/drivers/net/wireless/realtek/rtlwifi/regd.c
@@ -435,7 +435,7 @@ int rtl_regd_init(struct ieee80211_hw *hw,
 		channel_plan_to_country_code(rtlpriv->efuse.channel_plan);
 
 	RT_TRACE(rtlpriv, COMP_REGD, DBG_DMESG,
-		 "rtl: EEPROM regdomain: 0x%0x conuntry code: %d\n",
+		 "rtl: EEPROM regdomain: 0x%0x country code: %d\n",
 		 rtlpriv->efuse.channel_plan, rtlpriv->regd.country_code);
 
 	if (rtlpriv->regd.country_code >= COUNTRY_CODE_MAX) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
index 09c908d4cf91..dd3e12b74447 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
@@ -444,10 +444,10 @@ bool rtl88ee_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (status->rx_is40Mhzpacket)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (status->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c
index 3616ba21959d..94a4b39437cd 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c
@@ -369,10 +369,10 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (stats->rx_is40Mhzpacket)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (stats->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c
index 1611e42479d9..41422e4da8b7 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c
@@ -329,9 +329,9 @@ bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
 	if (!GET_RX_DESC_SWDEC(pdesc))
 		rx_status->flag |= RX_FLAG_DECRYPTED;
 	if (GET_RX_DESC_BW(pdesc))
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 	if (GET_RX_DESC_RX_HT(pdesc))
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
@@ -398,9 +398,9 @@ static void _rtl_rx_process(struct ieee80211_hw *hw, struct sk_buff *skb)
 	if (!GET_RX_DESC_SWDEC(rxdesc))
 		rx_status->flag |= RX_FLAG_DECRYPTED;
 	if (GET_RX_DESC_BW(rxdesc))
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 	if (GET_RX_DESC_RX_HT(rxdesc))
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 	/* Data rate */
 	rx_status->rate_idx = rtlwifi_rate_mapping(hw, stats.is_ht,
 						   false, stats.rate);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
index 5c9c8741134f..86019f654428 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
@@ -503,9 +503,9 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw,	struct rtl_stats *stats,
 	if (!GET_RX_DESC_SWDEC(pdesc))
 		rx_status->flag |= RX_FLAG_DECRYPTED;
 	if (GET_RX_DESC_BW(pdesc))
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 	if (GET_RX_DESC_RXHT(pdesc))
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c
index 9fec345a42a0..1f42ce5f8f27 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c
@@ -468,8 +468,10 @@ void rtl92ee_set_fw_media_status_rpt_cmd(struct ieee80211_hw *hw, u8 mstatus)
 #define PSPOLL_PG		2
 #define NULL_PG			3
 #define PROBERSP_PG		4 /* ->5 */
+#define QOS_NULL_PG		6
+#define BT_QOS_NULL_PG	7
 
-#define TOTAL_RESERVED_PKT_LEN	768
+#define TOTAL_RESERVED_PKT_LEN	1024
 
 static u8 reserved_page_packet[TOTAL_RESERVED_PKT_LEN] = {
 	/* page 0 beacon */
@@ -570,6 +572,42 @@ static u8 reserved_page_packet[TOTAL_RESERVED_PKT_LEN] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x1A, 0x00, 0x28, 0x8C, 0x00, 0x12, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* page 6 qos null data */
+	0xC8, 0x01, 0x00, 0x00, 0x84, 0xC9, 0xB2, 0xA7,
+	0xB3, 0x6E, 0x00, 0xE0, 0x4C, 0x02, 0x51, 0x02,
+	0x84, 0xC9, 0xB2, 0xA7, 0xB3, 0x6E, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x1A, 0x00, 0x28, 0x8C, 0x00, 0x12, 0x00, 0x00,
+	0x00, 0x00, 0x80, 0x00, 0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* page 7 BT-qos null data */
+	0xC8, 0x01, 0x00, 0x00, 0x84, 0xC9, 0xB2, 0xA7,
+	0xB3, 0x6E, 0x00, 0xE0, 0x4C, 0x02, 0x51, 0x02,
+	0x84, 0xC9, 0xB2, 0xA7, 0xB3, 0x6E, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -595,6 +633,8 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 	u8 *p_pspoll;
 	u8 *nullfunc;
 	u8 *p_probersp;
+	u8 *qosnull;
+	u8 *btqosnull;
 	/*---------------------------------------------------------
 	 *			(1) beacon
 	 *---------------------------------------------------------
@@ -636,6 +676,28 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 
 	SET_H2CCMD_RSVDPAGE_LOC_PROBE_RSP(u1rsvdpageloc, PROBERSP_PG);
 
+	/*---------------------------------------------------------
+	 *			(5) QoS null data
+	 *----------------------------------------------------------
+	 */
+	qosnull = &reserved_page_packet[QOS_NULL_PG * 128];
+	SET_80211_HDR_ADDRESS1(qosnull, mac->bssid);
+	SET_80211_HDR_ADDRESS2(qosnull, mac->mac_addr);
+	SET_80211_HDR_ADDRESS3(qosnull, mac->bssid);
+
+	SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(u1rsvdpageloc, QOS_NULL_PG);
+
+	/*---------------------------------------------------------
+	 *			(6) BT QoS null data
+	 *----------------------------------------------------------
+	 */
+	btqosnull = &reserved_page_packet[BT_QOS_NULL_PG * 128];
+	SET_80211_HDR_ADDRESS1(btqosnull, mac->bssid);
+	SET_80211_HDR_ADDRESS2(btqosnull, mac->mac_addr);
+	SET_80211_HDR_ADDRESS3(btqosnull, mac->bssid);
+
+	SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(u1rsvdpageloc, BT_QOS_NULL_PG);
+
 	totalpacketlen = TOTAL_RESERVED_PKT_LEN;
 
 	RT_PRINT_DATA(rtlpriv, COMP_CMD, DBG_LOUD ,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.h
index 72da3f92f02c..af8271967a88 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.h
@@ -165,6 +165,10 @@ enum rtl8192e_c2h_evt {
 	SET_BITS_TO_LE_1BYTE((__ph2ccmd)+1, 0, 8, __val)
 #define SET_H2CCMD_RSVDPAGE_LOC_NULL_DATA(__ph2ccmd, __val)		\
 	SET_BITS_TO_LE_1BYTE((__ph2ccmd)+2, 0, 8, __val)
+#define SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(__ph2ccmd, __val)		\
+	SET_BITS_TO_LE_1BYTE((__ph2ccmd) + 3, 0, 8, __val)
+#define SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(__ph2ccmd, __val)	\
+	SET_BITS_TO_LE_1BYTE((__ph2ccmd) + 4, 0, 8, __val)
 
 /* _MEDIA_STATUS_RPT_PARM_CMD1 */
 #define SET_H2CCMD_MSRRPT_PARM_OPMODE(__cmd, __val)		\
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
index 56ca7f5351ea..6f5098a18655 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
@@ -699,9 +699,9 @@ static bool _rtl92ee_llt_table_init(struct ieee80211_hw *hw)
 	u8 txpktbuf_bndy;
 	u8 u8tmp, testcnt = 0;
 
-	txpktbuf_bndy = 0xFA;
+	txpktbuf_bndy = 0xF7;
 
-	rtl_write_dword(rtlpriv, REG_RQPN, 0x80E90808);
+	rtl_write_dword(rtlpriv, REG_RQPN, 0x80E60808);
 
 	rtl_write_byte(rtlpriv, REG_TRXFF_BNDY, txpktbuf_bndy);
 	rtl_write_word(rtlpriv, REG_TRXFF_BNDY + 2, 0x3d00 - 1);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c
index 07440e9a8ca2..b1864bb07c2c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c
@@ -394,10 +394,10 @@ bool rtl92ee_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (status->rx_is40Mhzpacket)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (status->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
index 12cef01e593b..a01dbd31d1b4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
@@ -289,10 +289,10 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (stats->rx_is40Mhzpacket)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (stats->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
index c9838f52a7ea..f713c7249fed 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
@@ -317,10 +317,10 @@ bool rtl8723e_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (status->rx_is40Mhzpacket)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (status->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.c
index c7ee9ba5e26e..4fc839b1d601 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.c
@@ -284,8 +284,10 @@ void rtl8723be_set_fw_media_status_rpt_cmd(struct ieee80211_hw *hw, u8 mstatus)
 #define PSPOLL_PG		2
 #define NULL_PG			3
 #define PROBERSP_PG		4 /* ->5 */
+#define QOS_NULL_PG		6
+#define BT_QOS_NULL_PG	7
 
-#define TOTAL_RESERVED_PKT_LEN	768
+#define TOTAL_RESERVED_PKT_LEN	1024	/* can be up to 1280 (tx_bndy=245) */
 
 static u8 reserved_page_packet[TOTAL_RESERVED_PKT_LEN] = {
 	/* page 0 beacon */
@@ -390,11 +392,48 @@ static u8 reserved_page_packet[TOTAL_RESERVED_PKT_LEN] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x1A, 0x00, 0x28, 0x8C, 0x00, 0x12, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* page 6 qos null data */
+	0xC8, 0x01, 0x00, 0x00, 0x84, 0xC9, 0xB2, 0xA7,
+	0xB3, 0x6E, 0x00, 0xE0, 0x4C, 0x02, 0x51, 0x02,
+	0x84, 0xC9, 0xB2, 0xA7, 0xB3, 0x6E, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x1A, 0x00, 0x28, 0x8C, 0x00, 0x12, 0x00, 0x00,
+	0x00, 0x00, 0x80, 0x00, 0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
+	/* page 7 BT-qos null data */
+	0xC8, 0x01, 0x00, 0x00, 0x84, 0xC9, 0xB2, 0xA7,
+	0xB3, 0x6E, 0x00, 0xE0, 0x4C, 0x02, 0x51, 0x02,
+	0x84, 0xC9, 0xB2, 0xA7, 0xB3, 0x6E, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+
 };
 
 void rtl8723be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
@@ -413,6 +452,8 @@ void rtl8723be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 	u8 *p_pspoll;
 	u8 *nullfunc;
 	u8 *p_probersp;
+	u8 *qosnull;
+	u8 *btqosnull;
 	/*---------------------------------------------------------
 	 *			(1) beacon
 	 *---------------------------------------------------------
@@ -454,6 +495,28 @@ void rtl8723be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 
 	SET_H2CCMD_RSVDPAGE_LOC_PROBE_RSP(u1rsvdpageloc, PROBERSP_PG);
 
+	/*---------------------------------------------------------
+	 *			(5) QoS Null
+	 *---------------------------------------------------------
+	 */
+	qosnull = &reserved_page_packet[QOS_NULL_PG * 128];
+	SET_80211_HDR_ADDRESS1(qosnull, mac->bssid);
+	SET_80211_HDR_ADDRESS2(qosnull, mac->mac_addr);
+	SET_80211_HDR_ADDRESS3(qosnull, mac->bssid);
+
+	SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(u1rsvdpageloc, QOS_NULL_PG);
+
+	/*---------------------------------------------------------
+	 *			(5) QoS Null
+	 *---------------------------------------------------------
+	 */
+	btqosnull = &reserved_page_packet[BT_QOS_NULL_PG * 128];
+	SET_80211_HDR_ADDRESS1(btqosnull, mac->bssid);
+	SET_80211_HDR_ADDRESS2(btqosnull, mac->mac_addr);
+	SET_80211_HDR_ADDRESS3(btqosnull, mac->bssid);
+
+	SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(u1rsvdpageloc, BT_QOS_NULL_PG);
+
 	totalpacketlen = TOTAL_RESERVED_PKT_LEN;
 
 	RT_PRINT_DATA(rtlpriv, COMP_CMD, DBG_LOUD,
@@ -461,7 +524,7 @@ void rtl8723be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 		      &reserved_page_packet[0], totalpacketlen);
 	RT_PRINT_DATA(rtlpriv, COMP_CMD, DBG_DMESG,
 		      "rtl8723be_set_fw_rsvdpagepkt(): HW_VAR_SET_TX_CMD: ALL\n",
-		      u1rsvdpageloc, 3);
+		      u1rsvdpageloc, sizeof(u1rsvdpageloc));
 
 	skb = dev_alloc_skb(totalpacketlen);
 	memcpy((u8 *)skb_put(skb, totalpacketlen),
@@ -476,7 +539,7 @@ void rtl8723be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 		RT_TRACE(rtlpriv, COMP_POWER, DBG_LOUD,
 			 "Set RSVD page location to Fw.\n");
 		RT_PRINT_DATA(rtlpriv, COMP_CMD, DBG_DMESG, "H2C_RSVDPAGE:\n",
-			      u1rsvdpageloc, 3);
+			      u1rsvdpageloc, sizeof(u1rsvdpageloc));
 		rtl8723be_fill_h2c_cmd(hw, H2C_8723B_RSVDPAGE,
 				       sizeof(u1rsvdpageloc), u1rsvdpageloc);
 	} else
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.h
index c652fa1339a7..2482b3bc2bfa 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/fw.h
@@ -139,6 +139,10 @@ enum rtl8723b_c2h_evt {
 	SET_BITS_TO_LE_1BYTE((__ph2ccmd)+1, 0, 8, __val)
 #define SET_H2CCMD_RSVDPAGE_LOC_NULL_DATA(__ph2ccmd, __val)		\
 	SET_BITS_TO_LE_1BYTE((__ph2ccmd)+2, 0, 8, __val)
+#define SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(__ph2ccmd, __val)	\
+	SET_BITS_TO_LE_1BYTE((__ph2ccmd) + 3, 0, 8, __val)
+#define SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(__ph2ccmd, __val)	\
+	SET_BITS_TO_LE_1BYTE((__ph2ccmd) + 4, 0, 8, __val)
 
 
 void rtl8723be_fill_h2c_cmd(struct ieee80211_hw *hw, u8 element_id,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
index 92dbfa8f297f..8c0ac96b5430 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
@@ -91,7 +91,7 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
-	char *fw_name = "rtlwifi/rtl8723befw.bin";
+	char *fw_name = "rtlwifi/rtl8723befw_36.bin";
 
 	rtl8723be_bt_reg_init(hw);
 	rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer();
@@ -187,8 +187,16 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
-		pr_err("Failed to request firmware!\n");
-		return 1;
+		/* Failed to get firmware. Check if old version available */
+		fw_name = "rtlwifi/rtl8723befw.bin";
+		pr_info("Using firmware %s\n", fw_name);
+		err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
+					      rtlpriv->io.dev, GFP_KERNEL, hw,
+					      rtl_fw_cb);
+		if (err) {
+			pr_err("Failed to request firmware!\n");
+			return 1;
+		}
 	}
 	return 0;
 }
@@ -384,6 +392,7 @@ MODULE_AUTHOR("Realtek WlanFAE	<wlanfae@realtek.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Realtek 8723BE 802.11n PCI wireless");
 MODULE_FIRMWARE("rtlwifi/rtl8723befw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723befw_36.bin");
 
 module_param_named(swenc, rtl8723be_mod_params.sw_crypto, bool, 0444);
 module_param_named(debug_level, rtl8723be_mod_params.debug_level, int, 0644);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c
index 6f65003a895a..3c6ce994c6aa 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c
@@ -373,10 +373,10 @@ bool rtl8723be_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (status->rx_is40Mhzpacket)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 
 	if (status->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.c
index a504dfae4ed3..73350103b736 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.c
@@ -678,12 +678,13 @@ void rtl8821ae_set_fw_global_info_cmd(struct ieee80211_hw *hw)
 #define PSPOLL_PG		1
 #define NULL_PG			2
 #define QOSNULL_PG		3
-#define ARPRESP_PG		4
-#define REMOTE_PG		5
-#define GTKEXT_PG		6
+#define BT_QOSNULL_PG	4
+#define ARPRESP_PG		5
+#define REMOTE_PG		6
+#define GTKEXT_PG		7
 
-#define TOTAL_RESERVED_PKT_LEN_8812	3584
-#define TOTAL_RESERVED_PKT_LEN_8821	1792
+#define TOTAL_RESERVED_PKT_LEN_8812	4096
+#define TOTAL_RESERVED_PKT_LEN_8821	2048
 
 static u8 reserved_page_packet_8821[TOTAL_RESERVED_PKT_LEN_8821] = {
 	/* page 0: beacon */
@@ -813,13 +814,46 @@ static u8 reserved_page_packet_8821[TOTAL_RESERVED_PKT_LEN_8821] = {
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x1A, 0x00, 0x28, 0x8C,  0x00, 0x12, 0x00, 0x00,
+	0x00, 0x00, 0x80, 0x00,  0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x80, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	/* page 4: BT qos null data */
+	0xC8, 0x01, 0x00, 0x00,  0x84, 0xC9, 0xB2, 0xA7,
+	0xB3, 0x6E, 0x00, 0xE0,  0x4C, 0x02, 0x51, 0x02,
+	0x84, 0xC9, 0xB2, 0xA7,  0xB3, 0x6E, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x3C, 0x00, 0x28, 0x8C,  0x00, 0x12, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x01, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x80, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
-	/* page 4~6 is for wowlan */
-	/* page 4: ARP resp */
+	/* page 5~7 is for wowlan */
+	/* page 5: ARP resp */
 	0x08, 0x01, 0x00, 0x00,  0x84, 0xC9, 0xB2, 0xA7,
 	0xB3, 0x6E, 0x00, 0xE0,  0x4C, 0x02, 0x51, 0x02,
 	0x84, 0xC9, 0xB2, 0xA7,  0xB3, 0x6E, 0x00, 0x00,
@@ -852,7 +886,7 @@ static u8 reserved_page_packet_8821[TOTAL_RESERVED_PKT_LEN_8821] = {
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
-	/* page 5: H2C_REMOTE_WAKE_CTRL_INFO */
+	/* page 6: H2C_REMOTE_WAKE_CTRL_INFO */
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
@@ -885,7 +919,7 @@ static u8 reserved_page_packet_8821[TOTAL_RESERVED_PKT_LEN_8821] = {
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
-	/* page 6: Rsvd GTK extend memory (zero memory) */
+	/* page 7: Rsvd GTK extend memory (zero memory) */
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
@@ -1176,13 +1210,78 @@ static u8 reserved_page_packet_8812[TOTAL_RESERVED_PKT_LEN_8812] = {
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x1A, 0x00, 0x28, 0x8C,  0x00, 0x12, 0x00, 0x00,
+	0x00, 0x00, 0x80, 0x00,  0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x80, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	/* page 4: BT Qos null data */
+	0xC8, 0x01, 0x00, 0x00,  0x84, 0xC9, 0xB2, 0xA7,
+	0xB3, 0x6E, 0x00, 0xE0,  0x4C, 0x02, 0x51, 0x02,
+	0x84, 0xC9, 0xB2, 0xA7,  0xB3, 0x6E, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x3C, 0x00, 0x28, 0x8C,  0x00, 0x12, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x01, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x80, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
-	/* page 4~6 is for wowlan */
-	/* page 4: ARP resp */
+	/* page 5~7 is for wowlan */
+	/* page 5: ARP resp */
 	0x08, 0x01, 0x00, 0x00,  0x84, 0xC9, 0xB2, 0xA7,
 	0xB3, 0x6E, 0x00, 0xE0,  0x4C, 0x02, 0x51, 0x02,
 	0x84, 0xC9, 0xB2, 0xA7,  0xB3, 0x6E, 0x00, 0x00,
@@ -1247,7 +1346,7 @@ static u8 reserved_page_packet_8812[TOTAL_RESERVED_PKT_LEN_8812] = {
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
-	/* page 5: H2C_REMOTE_WAKE_CTRL_INFO */
+	/* page 6: H2C_REMOTE_WAKE_CTRL_INFO */
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
@@ -1312,7 +1411,7 @@ static u8 reserved_page_packet_8812[TOTAL_RESERVED_PKT_LEN_8812] = {
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
-	/* page 6: Rsvd GTK extend memory (zero memory) */
+	/* page 7: Rsvd GTK extend memory (zero memory) */
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00,  0x00, 0x00, 0x00, 0x00,
@@ -1394,6 +1493,7 @@ void rtl8812ae_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 	u8 *p_pspoll;
 	u8 *nullfunc;
 	u8 *qosnull;
+	u8 *btqosnull;
 	u8 *arpresp;
 
 	/*---------------------------------------------------------
@@ -1441,12 +1541,23 @@ void rtl8812ae_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 
 	SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(u1RsvdPageLoc, QOSNULL_PG);
 
+	/*---------------------------------------------------------
+	 *			(5) BT Qos null data
+	 *----------------------------------------------------------
+	 */
+	btqosnull = &reserved_page_packet_8812[BT_QOSNULL_PG * 512];
+	SET_80211_HDR_ADDRESS1(btqosnull, mac->bssid);
+	SET_80211_HDR_ADDRESS2(btqosnull, mac->mac_addr);
+	SET_80211_HDR_ADDRESS3(btqosnull, mac->bssid);
+
+	SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(u1RsvdPageLoc, BT_QOSNULL_PG);
+
 	if (!dl_whole_packets) {
-		totalpacketlen = 512 * (QOSNULL_PG + 1) - 40;
+		totalpacketlen = 512 * (BT_QOSNULL_PG + 1) - 40;
 		goto out;
 	}
 	/*---------------------------------------------------------
-	 *			(5) ARP Resp
+	 *			(6) ARP Resp
 	 *----------------------------------------------------------
 	 */
 	arpresp = &reserved_page_packet_8812[ARPRESP_PG * 512];
@@ -1457,14 +1568,14 @@ void rtl8812ae_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 	SET_8821AE_H2CCMD_AOAC_RSVDPAGE_LOC_ARP_RSP(u1RsvdPageLoc2, ARPRESP_PG);
 
 	/*---------------------------------------------------------
-	 *			(6) Remote Wake Ctrl
+	 *			(7) Remote Wake Ctrl
 	 *----------------------------------------------------------
 	 */
 	SET_8821AE_H2CCMD_AOAC_RSVDPAGE_LOC_REMOTE_WAKE_CTRL_INFO(u1RsvdPageLoc2,
 								REMOTE_PG);
 
 	/*---------------------------------------------------------
-	 *			(7) GTK Ext Memory
+	 *			(8) GTK Ext Memory
 	 *----------------------------------------------------------
 	 */
 	SET_8821AE_H2CCMD_AOAC_RSVDPAGE_LOC_GTK_EXT_MEM(u1RsvdPageLoc2, GTKEXT_PG);
@@ -1518,6 +1629,7 @@ void rtl8821ae_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 	u8 *p_pspoll;
 	u8 *nullfunc;
 	u8 *qosnull;
+	u8 *btqosnull;
 	u8 *arpresp;
 
 	/*---------------------------------------------------------
@@ -1565,12 +1677,23 @@ void rtl8821ae_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 
 	SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(u1RsvdPageLoc, QOSNULL_PG);
 
+	/*---------------------------------------------------------
+	 *			(5) Qos null data
+	 *----------------------------------------------------------
+	 */
+	btqosnull = &reserved_page_packet_8821[BT_QOSNULL_PG * 256];
+	SET_80211_HDR_ADDRESS1(btqosnull, mac->bssid);
+	SET_80211_HDR_ADDRESS2(btqosnull, mac->mac_addr);
+	SET_80211_HDR_ADDRESS3(btqosnull, mac->bssid);
+
+	SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(u1RsvdPageLoc, BT_QOSNULL_PG);
+
 	if (!dl_whole_packets) {
-		totalpacketlen = 256 * (QOSNULL_PG + 1) - 40;
+		totalpacketlen = 256 * (BT_QOSNULL_PG + 1) - 40;
 		goto out;
 	}
 	/*---------------------------------------------------------
-	 *			(5) ARP Resp
+	 *			(6) ARP Resp
 	 *----------------------------------------------------------
 	 */
 	arpresp = &reserved_page_packet_8821[ARPRESP_PG * 256];
@@ -1581,14 +1704,14 @@ void rtl8821ae_set_fw_rsvdpagepkt(struct ieee80211_hw *hw,
 	SET_8821AE_H2CCMD_AOAC_RSVDPAGE_LOC_ARP_RSP(u1RsvdPageLoc2, ARPRESP_PG);
 
 	/*---------------------------------------------------------
-	 *			(6) Remote Wake Ctrl
+	 *			(7) Remote Wake Ctrl
 	 *----------------------------------------------------------
 	 */
 	SET_8821AE_H2CCMD_AOAC_RSVDPAGE_LOC_REMOTE_WAKE_CTRL_INFO(u1RsvdPageLoc2,
 									REMOTE_PG);
 
 	/*---------------------------------------------------------
-	 *			(7) GTK Ext Memory
+	 *			(8) GTK Ext Memory
 	 *----------------------------------------------------------
 	 */
 	SET_8821AE_H2CCMD_AOAC_RSVDPAGE_LOC_GTK_EXT_MEM(u1RsvdPageLoc2, GTKEXT_PG);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h
index 90a98ed879f7..98d871afd92a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h
@@ -229,6 +229,8 @@ enum rtl8821a_h2c_cmd {
 	SET_BITS_TO_LE_1BYTE((__ph2ccmd)+2, 0, 8, __val)
 #define SET_H2CCMD_RSVDPAGE_LOC_QOS_NULL_DATA(__ph2ccmd, __val)		\
 	SET_BITS_TO_LE_1BYTE((__ph2ccmd)+3, 0, 8, __val)
+#define SET_H2CCMD_RSVDPAGE_LOC_BT_QOS_NULL_DATA(__ph2ccmd, __val)	\
+	SET_BITS_TO_LE_1BYTE((__ph2ccmd) + 4, 0, 8, __val)
 
 /* _MEDIA_STATUS_RPT_PARM_CMD1 */
 #define SET_H2CCMD_MSRRPT_PARM_OPMODE(__cmd, __value)	\
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index 363d2f28da1f..3571ce4bd276 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -842,12 +842,8 @@ static bool _rtl8821ae_llt_table_init(struct ieee80211_hw *hw)
 	bool status;
 
 	maxpage = 255;
-	txpktbuf_bndy = 0xF8;
-	rqpn = 0x80e70808;
-	if (rtlpriv->rtlhal.hw_type == HARDWARE_TYPE_RTL8812AE) {
-		txpktbuf_bndy = 0xFA;
-		rqpn = 0x80e90808;
-	}
+	txpktbuf_bndy = 0xF7;
+	rqpn = 0x80e60808;
 
 	rtl_write_byte(rtlpriv, REG_TRXFF_BNDY, txpktbuf_bndy);
 	rtl_write_word(rtlpriv, REG_TRXFF_BNDY + 2, MAX_RX_DMA_BUFFER_SIZE - 1);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 8da874cbec1a..aa3ccc740521 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -358,6 +358,107 @@ bool rtl8821ae_phy_rf_config(struct ieee80211_hw *hw)
 	return rtl8821ae_phy_rf6052_config(hw);
 }
 
+static void _rtl8812ae_phy_set_rfe_reg_24g(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u8 tmp;
+
+	switch (rtlhal->rfe_type) {
+	case 3:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x54337770);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x54337770);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, 0x900, 0x00000303, 0x1);
+		break;
+	case 4:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x001);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x001);
+		break;
+	case 5:
+		rtl_write_byte(rtlpriv, RA_RFE_PINMUX + 2, 0x77);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		tmp = rtl_read_byte(rtlpriv, RA_RFE_INV + 3);
+		rtl_write_byte(rtlpriv, RA_RFE_INV + 3, tmp & ~0x1);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		break;
+	case 1:
+		if (rtlpriv->btcoexist.bt_coexistence) {
+			rtl_set_bbreg(hw, RA_RFE_PINMUX, 0xffffff, 0x777777);
+			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
+				      0x77777777);
+			rtl_set_bbreg(hw, RA_RFE_INV, 0x33f00000, 0x000);
+			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+			break;
+		}
+	case 0:
+	case 2:
+	default:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x000);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		break;
+	}
+}
+
+static void _rtl8812ae_phy_set_rfe_reg_5g(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u8 tmp;
+
+	switch (rtlhal->rfe_type) {
+	case 0:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77337717);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337717);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		break;
+	case 1:
+		if (rtlpriv->btcoexist.bt_coexistence) {
+			rtl_set_bbreg(hw, RA_RFE_PINMUX, 0xffffff, 0x337717);
+			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
+				      0x77337717);
+			rtl_set_bbreg(hw, RA_RFE_INV, 0x33f00000, 0x000);
+			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		} else {
+			rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD,
+				      0x77337717);
+			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
+				      0x77337717);
+			rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x000);
+			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		}
+		break;
+	case 3:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x54337717);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x54337717);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, 0x900, 0x00000303, 0x1);
+		break;
+	case 5:
+		rtl_write_byte(rtlpriv, RA_RFE_PINMUX + 2, 0x33);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337777);
+		tmp = rtl_read_byte(rtlpriv, RA_RFE_INV + 3);
+		rtl_write_byte(rtlpriv, RA_RFE_INV + 3, tmp | 0x1);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		break;
+	case 2:
+	case 4:
+	default:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77337777);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337777);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		break;
+	}
+}
+
 u32 phy_get_tx_swing_8812A(struct ieee80211_hw *hw, u8	band,
 			   u8 rf_path)
 {
@@ -552,14 +653,9 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band)
 			/* 0x82C[1:0] = 2b'00 */
 			rtl_set_bbreg(hw, 0x82c, 0x3, 0);
 		}
-		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-			rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD,
-				      0x77777777);
-			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
-				      0x77777777);
-			rtl_set_bbreg(hw, RA_RFE_INV, 0x3ff00000, 0x000);
-			rtl_set_bbreg(hw, RB_RFE_INV, 0x3ff00000, 0x000);
-		}
+
+		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE)
+			_rtl8812ae_phy_set_rfe_reg_24g(hw);
 
 		rtl_set_bbreg(hw, RTXPATH, 0xf0, 0x1);
 		rtl_set_bbreg(hw, RCCK_RX, 0x0f000000, 0x1);
@@ -614,14 +710,8 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band)
 			/* 0x82C[1:0] = 2'b00 */
 			rtl_set_bbreg(hw, 0x82c, 0x3, 1);
 
-		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-			rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD,
-				      0x77337777);
-			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
-				      0x77337777);
-			rtl_set_bbreg(hw, RA_RFE_INV, 0x3ff00000, 0x010);
-			rtl_set_bbreg(hw, RB_RFE_INV, 0x3ff00000, 0x010);
-		}
+		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE)
+			_rtl8812ae_phy_set_rfe_reg_5g(hw);
 
 		rtl_set_bbreg(hw, RTXPATH, 0xf0, 0);
 		rtl_set_bbreg(hw, RCCK_RX, 0x0f000000, 0xf);
@@ -660,6 +750,88 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band)
 	return;
 }
 
+static bool _rtl8821ae_check_positive(struct ieee80211_hw *hw,
+				      const u32 condition1,
+				      const u32 condition2)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
+	u32 cut_ver = ((rtlhal->version & CHIP_VER_RTL_MASK)
+					>> CHIP_VER_RTL_SHIFT);
+	u32 intf = (rtlhal->interface == INTF_USB ? BIT(1) : BIT(0));
+
+	u8  board_type = ((rtlhal->board_type & BIT(4)) >> 4) << 0 | /* _GLNA */
+			 ((rtlhal->board_type & BIT(3)) >> 3) << 1 | /* _GPA  */
+			 ((rtlhal->board_type & BIT(7)) >> 7) << 2 | /* _ALNA */
+			 ((rtlhal->board_type & BIT(6)) >> 6) << 3 | /* _APA  */
+			 ((rtlhal->board_type & BIT(2)) >> 2) << 4;  /* _BT   */
+
+	u32 cond1 = condition1, cond2 = condition2;
+	u32 driver1 = cut_ver << 24 |	/* CUT ver */
+		      0 << 20 |			/* interface 2/2 */
+		      0x04 << 16 |		/* platform */
+		      rtlhal->package_type << 12 |
+		      intf << 8 |			/* interface 1/2 */
+		      board_type;
+
+	u32 driver2 = rtlhal->type_glna <<  0 |
+		      rtlhal->type_gpa  <<  8 |
+		      rtlhal->type_alna << 16 |
+		      rtlhal->type_apa  << 24;
+
+	RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE,
+		 "===> [8812A] CheckPositive (cond1, cond2) = (0x%X 0x%X)\n",
+		 cond1, cond2);
+	RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE,
+		 "===> [8812A] CheckPositive (driver1, driver2) = (0x%X 0x%X)\n",
+		 driver1, driver2);
+
+	RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE,
+		 "	(Platform, Interface) = (0x%X, 0x%X)\n", 0x04, intf);
+	RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE,
+		 "	(Board, Package) = (0x%X, 0x%X)\n",
+		 rtlhal->board_type, rtlhal->package_type);
+
+	/*============== Value Defined Check ===============*/
+	/*QFN Type [15:12] and Cut Version [27:24] need to do value check*/
+
+	if (((cond1 & 0x0000F000) != 0) && ((cond1 & 0x0000F000) !=
+		(driver1 & 0x0000F000)))
+		return false;
+	if (((cond1 & 0x0F000000) != 0) && ((cond1 & 0x0F000000) !=
+		(driver1 & 0x0F000000)))
+		return false;
+
+	/*=============== Bit Defined Check ================*/
+	/* We don't care [31:28] */
+
+	cond1   &= 0x00FF0FFF;
+	driver1 &= 0x00FF0FFF;
+
+	if ((cond1 & driver1) == cond1) {
+		u32 mask = 0;
+
+		if ((cond1 & 0x0F) == 0) /* BoardType is DONTCARE*/
+			return true;
+
+		if ((cond1 & BIT(0)) != 0) /*GLNA*/
+			mask |= 0x000000FF;
+		if ((cond1 & BIT(1)) != 0) /*GPA*/
+			mask |= 0x0000FF00;
+		if ((cond1 & BIT(2)) != 0) /*ALNA*/
+			mask |= 0x00FF0000;
+		if ((cond1 & BIT(3)) != 0) /*APA*/
+			mask |= 0xFF000000;
+
+		/* BoardType of each RF path is matched*/
+		if ((cond2 & mask) == (driver2 & mask))
+			return true;
+		else
+			return false;
+	} else
+		return false;
+}
+
 static bool _rtl8821ae_check_condition(struct ieee80211_hw *hw,
 				       const u32 condition)
 {
@@ -1695,55 +1867,78 @@ static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw)
 	return true;
 }
 
+static bool
+__rtl8821ae_phy_config_with_headerfile(struct ieee80211_hw *hw,
+				       u32 *array_table, u16 arraylen,
+				       void (*set_reg)(struct ieee80211_hw *hw,
+						       u32 regaddr, u32 data))
+{
+	#define COND_ELSE  2
+	#define COND_ENDIF 3
+
+	int i = 0;
+	u8 cond;
+	bool matched = true, skipped = false;
+
+	while ((i + 1) < arraylen) {
+		u32 v1 = array_table[i];
+		u32 v2 = array_table[i + 1];
+
+		if (v1 & (BIT(31) | BIT(30))) {/*positive & negative condition*/
+			if (v1 & BIT(31)) {/* positive condition*/
+				cond  = (u8)((v1 & (BIT(29) | BIT(28))) >> 28);
+				if (cond == COND_ENDIF) {/*end*/
+					matched = true;
+					skipped = false;
+				} else if (cond == COND_ELSE) /*else*/
+					matched = skipped ? false : true;
+				else {/*if , else if*/
+					if (skipped) {
+						matched = false;
+					} else {
+						if (_rtl8821ae_check_positive(
+								hw, v1, v2)) {
+							matched = true;
+							skipped = true;
+						} else {
+							matched = false;
+							skipped = false;
+						}
+					}
+				}
+			} else if (v1 & BIT(30)) { /*negative condition*/
+			/*do nothing*/
+			}
+		} else {
+			if (matched)
+				set_reg(hw, v1, v2);
+		}
+		i = i + 2;
+	}
+
+	return true;
+}
+
 static bool _rtl8821ae_phy_config_mac_with_headerfile(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
-	u32 i, v1, v2;
 	u32 arraylength;
 	u32 *ptrarray;
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "Read MAC_REG_Array\n");
 	if (rtlhal->hw_type == HARDWARE_TYPE_RTL8821AE) {
-		arraylength = RTL8821AEMAC_1T_ARRAYLEN;
+		arraylength = RTL8821AE_MAC_1T_ARRAYLEN;
 		ptrarray = RTL8821AE_MAC_REG_ARRAY;
 	} else {
-		arraylength = RTL8812AEMAC_1T_ARRAYLEN;
+		arraylength = RTL8812AE_MAC_1T_ARRAYLEN;
 		ptrarray = RTL8812AE_MAC_REG_ARRAY;
 	}
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD,
 		 "Img: MAC_REG_ARRAY LEN %d\n", arraylength);
-	for (i = 0; i < arraylength; i += 2) {
-		v1 = ptrarray[i];
-		v2 = (u8)ptrarray[i + 1];
-		if (v1 < 0xCDCDCDCD) {
-			rtl_write_byte(rtlpriv, v1, (u8)v2);
-			continue;
-		} else {
-			if (!_rtl8821ae_check_condition(hw, v1)) {
-				/*Discard the following (offset, data) pairs*/
-				READ_NEXT_PAIR(ptrarray, v1, v2, i);
-				while (v2 != 0xDEAD &&
-				       v2 != 0xCDEF &&
-				       v2 != 0xCDCD && i < arraylength - 2) {
-					READ_NEXT_PAIR(ptrarray, v1, v2, i);
-				}
-				i -= 2; /* prevent from for-loop += 2*/
-			} else {/*Configure matched pairs and skip to end of if-else.*/
-				READ_NEXT_PAIR(ptrarray, v1, v2, i);
-				while (v2 != 0xDEAD &&
-				       v2 != 0xCDEF &&
-				       v2 != 0xCDCD && i < arraylength - 2) {
-					rtl_write_byte(rtlpriv, v1, v2);
-					READ_NEXT_PAIR(ptrarray, v1, v2, i);
-				}
 
-				while (v2 != 0xDEAD && i < arraylength - 2)
-					READ_NEXT_PAIR(ptrarray, v1, v2, i);
-			}
-		}
-	}
-	return true;
+	return __rtl8821ae_phy_config_with_headerfile(hw,
+			ptrarray, arraylength, rtl_write_byte_with_val32);
 }
 
 static bool _rtl8821ae_phy_config_bb_with_headerfile(struct ieee80211_hw *hw,
@@ -1751,111 +1946,33 @@ static bool _rtl8821ae_phy_config_bb_with_headerfile(struct ieee80211_hw *hw,
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
-	int i;
 	u32 *array_table;
 	u16 arraylen;
-	u32 v1 = 0, v2 = 0;
 
 	if (configtype == BASEBAND_CONFIG_PHY_REG) {
 		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-			arraylen = RTL8812AEPHY_REG_1TARRAYLEN;
+			arraylen = RTL8812AE_PHY_REG_1TARRAYLEN;
 			array_table = RTL8812AE_PHY_REG_ARRAY;
 		} else {
-			arraylen = RTL8821AEPHY_REG_1TARRAYLEN;
+			arraylen = RTL8821AE_PHY_REG_1TARRAYLEN;
 			array_table = RTL8821AE_PHY_REG_ARRAY;
 		}
 
-		for (i = 0; i < arraylen; i += 2) {
-			v1 = array_table[i];
-			v2 = array_table[i + 1];
-			if (v1 < 0xCDCDCDCD) {
-				_rtl8821ae_config_bb_reg(hw, v1, v2);
-				continue;
-			} else {/*This line is the start line of branch.*/
-				if (!_rtl8821ae_check_condition(hw, v1)) {
-					/*Discard the following (offset, data) pairs*/
-					READ_NEXT_PAIR(array_table, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD &&
-					       i < arraylen - 2) {
-						READ_NEXT_PAIR(array_table, v1,
-								v2, i);
-					}
-
-					i -= 2; /* prevent from for-loop += 2*/
-				} else {/*Configure matched pairs and skip to end of if-else.*/
-					READ_NEXT_PAIR(array_table, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD &&
-					       i < arraylen - 2) {
-						_rtl8821ae_config_bb_reg(hw, v1,
-									 v2);
-						READ_NEXT_PAIR(array_table, v1,
-							       v2, i);
-					}
-
-					while (v2 != 0xDEAD &&
-					       i < arraylen - 2) {
-						READ_NEXT_PAIR(array_table, v1,
-							       v2, i);
-					}
-				}
-			}
-		}
+		return __rtl8821ae_phy_config_with_headerfile(hw,
+				array_table, arraylen,
+				_rtl8821ae_config_bb_reg);
 	} else if (configtype == BASEBAND_CONFIG_AGC_TAB) {
 		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-			arraylen = RTL8812AEAGCTAB_1TARRAYLEN;
+			arraylen = RTL8812AE_AGC_TAB_1TARRAYLEN;
 			array_table = RTL8812AE_AGC_TAB_ARRAY;
 		} else {
-			arraylen = RTL8821AEAGCTAB_1TARRAYLEN;
+			arraylen = RTL8821AE_AGC_TAB_1TARRAYLEN;
 			array_table = RTL8821AE_AGC_TAB_ARRAY;
 		}
 
-		for (i = 0; i < arraylen; i = i + 2) {
-			v1 = array_table[i];
-			v2 = array_table[i+1];
-			if (v1 < 0xCDCDCDCD) {
-				rtl_set_bbreg(hw, v1, MASKDWORD, v2);
-				udelay(1);
-				continue;
-			} else {/*This line is the start line of branch.*/
-				if (!_rtl8821ae_check_condition(hw, v1)) {
-					/*Discard the following (offset, data) pairs*/
-					READ_NEXT_PAIR(array_table, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD &&
-					       i < arraylen - 2) {
-						READ_NEXT_PAIR(array_table, v1,
-								v2, i);
-					}
-					i -= 2; /* prevent from for-loop += 2*/
-				} else {/*Configure matched pairs and skip to end of if-else.*/
-					READ_NEXT_PAIR(array_table, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD &&
-					       i < arraylen - 2) {
-						rtl_set_bbreg(hw, v1, MASKDWORD,
-							      v2);
-						udelay(1);
-						READ_NEXT_PAIR(array_table, v1,
-							       v2, i);
-					}
-
-					while (v2 != 0xDEAD &&
-						i < arraylen - 2) {
-						READ_NEXT_PAIR(array_table, v1,
-								v2, i);
-					}
-				}
-				RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE,
-					 "The agctab_array_table[0] is %x Rtl818EEPHY_REGArray[1] is %x\n",
-					  array_table[i],  array_table[i + 1]);
-			}
-		}
+		return __rtl8821ae_phy_config_with_headerfile(hw,
+				array_table, arraylen,
+				rtl_set_bbreg_with_dwmask);
 	}
 	return true;
 }
@@ -1913,10 +2030,10 @@ static bool _rtl8821ae_phy_config_bb_with_pgheaderfile(struct ieee80211_hw *hw,
 	u32 v1, v2, v3, v4, v5, v6;
 
 	if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-		arraylen = RTL8812AEPHY_REG_ARRAY_PGLEN;
+		arraylen = RTL8812AE_PHY_REG_ARRAY_PGLEN;
 		array = RTL8812AE_PHY_REG_ARRAY_PG;
 	} else {
-		arraylen = RTL8821AEPHY_REG_ARRAY_PGLEN;
+		arraylen = RTL8821AE_PHY_REG_ARRAY_PGLEN;
 		array = RTL8821AE_PHY_REG_ARRAY_PG;
 	}
 
@@ -1980,12 +2097,10 @@ static bool _rtl8821ae_phy_config_bb_with_pgheaderfile(struct ieee80211_hw *hw,
 bool rtl8812ae_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 					     enum radio_path rfpath)
 {
-	int i;
 	bool rtstatus = true;
 	u32 *radioa_array_table_a, *radioa_array_table_b;
 	u16 radioa_arraylen_a, radioa_arraylen_b;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	u32 v1 = 0, v2 = 0;
 
 	radioa_arraylen_a = RTL8812AE_RADIOA_1TARRAYLEN;
 	radioa_array_table_a = RTL8812AE_RADIOA_ARRAY;
@@ -1997,69 +2112,14 @@ bool rtl8812ae_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 	rtstatus = true;
 	switch (rfpath) {
 	case RF90_PATH_A:
-		for (i = 0; i < radioa_arraylen_a; i = i + 2) {
-			v1 = radioa_array_table_a[i];
-			v2 = radioa_array_table_a[i+1];
-			if (v1 < 0xcdcdcdcd) {
-				_rtl8821ae_config_rf_radio_a(hw, v1, v2);
-				continue;
-			} else{/*This line is the start line of branch.*/
-				if (!_rtl8821ae_check_condition(hw, v1)) {
-					/*Discard the following (offset, data) pairs*/
-					READ_NEXT_PAIR(radioa_array_table_a, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD && i < radioa_arraylen_a-2)
-						READ_NEXT_PAIR(radioa_array_table_a, v1, v2, i);
-
-					i -= 2; /* prevent from for-loop += 2*/
-				} else {/*Configure matched pairs and skip to end of if-else.*/
-					READ_NEXT_PAIR(radioa_array_table_a, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD && i < radioa_arraylen_a - 2) {
-						_rtl8821ae_config_rf_radio_a(hw, v1, v2);
-						READ_NEXT_PAIR(radioa_array_table_a, v1, v2, i);
-					}
-
-					while (v2 != 0xDEAD && i < radioa_arraylen_a-2)
-						READ_NEXT_PAIR(radioa_array_table_a, v1, v2, i);
-
-				}
-			}
-		}
+		return __rtl8821ae_phy_config_with_headerfile(hw,
+				radioa_array_table_a, radioa_arraylen_a,
+				_rtl8821ae_config_rf_radio_a);
 		break;
 	case RF90_PATH_B:
-		for (i = 0; i < radioa_arraylen_b; i = i + 2) {
-			v1 = radioa_array_table_b[i];
-			v2 = radioa_array_table_b[i+1];
-			if (v1 < 0xcdcdcdcd) {
-				_rtl8821ae_config_rf_radio_b(hw, v1, v2);
-				continue;
-			} else{/*This line is the start line of branch.*/
-				if (!_rtl8821ae_check_condition(hw, v1)) {
-					/*Discard the following (offset, data) pairs*/
-					READ_NEXT_PAIR(radioa_array_table_b, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD && i < radioa_arraylen_b-2)
-						READ_NEXT_PAIR(radioa_array_table_b, v1, v2, i);
-
-					i -= 2; /* prevent from for-loop += 2*/
-				} else {/*Configure matched pairs and skip to end of if-else.*/
-					READ_NEXT_PAIR(radioa_array_table_b, v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD && i < radioa_arraylen_b-2) {
-						_rtl8821ae_config_rf_radio_b(hw, v1, v2);
-						READ_NEXT_PAIR(radioa_array_table_b, v1, v2, i);
-					}
-
-					while (v2 != 0xDEAD && i < radioa_arraylen_b-2)
-						READ_NEXT_PAIR(radioa_array_table_b, v1, v2, i);
-				}
-			}
-		}
+		return __rtl8821ae_phy_config_with_headerfile(hw,
+				radioa_array_table_b, radioa_arraylen_b,
+				_rtl8821ae_config_rf_radio_b);
 		break;
 	case RF90_PATH_C:
 	case RF90_PATH_D:
@@ -2072,21 +2132,10 @@ bool rtl8812ae_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 bool rtl8821ae_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 						enum radio_path rfpath)
 {
-	#define READ_NEXT_RF_PAIR(v1, v2, i) \
-	do { \
-		i += 2; \
-		v1 = radioa_array_table[i]; \
-		v2 = radioa_array_table[i+1]; \
-	} \
-	while (0)
-
-	int i;
 	bool rtstatus = true;
 	u32 *radioa_array_table;
 	u16 radioa_arraylen;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	/* struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); */
-	u32 v1 = 0, v2 = 0;
 
 	radioa_arraylen = RTL8821AE_RADIOA_1TARRAYLEN;
 	radioa_array_table = RTL8821AE_RADIOA_ARRAY;
@@ -2096,35 +2145,9 @@ bool rtl8821ae_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 	rtstatus = true;
 	switch (rfpath) {
 	case RF90_PATH_A:
-		for (i = 0; i < radioa_arraylen; i = i + 2) {
-			v1 = radioa_array_table[i];
-			v2 = radioa_array_table[i+1];
-			if (v1 < 0xcdcdcdcd)
-				_rtl8821ae_config_rf_radio_a(hw, v1, v2);
-			else{/*This line is the start line of branch.*/
-				if (!_rtl8821ae_check_condition(hw, v1)) {
-					/*Discard the following (offset, data) pairs*/
-					READ_NEXT_RF_PAIR(v1, v2, i);
-					while (v2 != 0xDEAD &&
-						v2 != 0xCDEF &&
-						v2 != 0xCDCD && i < radioa_arraylen - 2)
-						READ_NEXT_RF_PAIR(v1, v2, i);
-
-					i -= 2; /* prevent from for-loop += 2*/
-				} else {/*Configure matched pairs and skip to end of if-else.*/
-					READ_NEXT_RF_PAIR(v1, v2, i);
-					while (v2 != 0xDEAD &&
-					       v2 != 0xCDEF &&
-					       v2 != 0xCDCD && i < radioa_arraylen - 2) {
-						_rtl8821ae_config_rf_radio_a(hw, v1, v2);
-						READ_NEXT_RF_PAIR(v1, v2, i);
-					}
-
-					while (v2 != 0xDEAD && i < radioa_arraylen - 2)
-						READ_NEXT_RF_PAIR(v1, v2, i);
-				}
-			}
-		}
+		return __rtl8821ae_phy_config_with_headerfile(hw,
+			radioa_array_table, radioa_arraylen,
+			_rtl8821ae_config_rf_radio_a);
 		break;
 
 	case RF90_PATH_B:
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h
index 1d6110f9c1fb..ed69dbe178ff 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h
@@ -2424,6 +2424,7 @@
 #define	BMASKH4BITS			0xf0000000
 #define BMASKOFDM_D			0xffc00000
 #define	BMASKCCK			0x3f3f3f3f
+#define BMASKRFEINV			0x3ff00000
 
 #define BRFREGOFFSETMASK		0xfffff
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 77cf3b2cd3f1..abaf34cb1433 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -203,7 +203,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
 		fw_name = "rtlwifi/rtl8812aefw.bin";
 		wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin";
 	} else {
-		fw_name = "rtlwifi/rtl8821aefw.bin";
+		fw_name = "rtlwifi/rtl8821aefw_29.bin";
 		wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin";
 	}
 
@@ -214,8 +214,16 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
-		pr_err("Failed to request normal firmware!\n");
-		return 1;
+		/* Failed to get firmware. Check if old version available */
+		fw_name = "rtlwifi/rtl8821aefw.bin";
+		pr_info("Using firmware %s\n", fw_name);
+		err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
+					      rtlpriv->io.dev, GFP_KERNEL, hw,
+					      rtl_fw_cb);
+		if (err) {
+			pr_err("Failed to request normal firmware!\n");
+			return 1;
+		}
 	}
 	/*load wowlan firmware*/
 	pr_info("Using firmware %s\n", wowlan_fw_name);
@@ -428,6 +436,7 @@ MODULE_AUTHOR("Realtek WlanFAE	<wlanfae@realtek.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Realtek 8821ae 802.11ac PCI wireless");
 MODULE_FIRMWARE("rtlwifi/rtl8821aefw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8821aefw_29.bin");
 
 module_param_named(swenc, rtl8821ae_mod_params.sw_crypto, bool, 0444);
 module_param_named(debug_level, rtl8821ae_mod_params.debug_level, int, 0644);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c
index 62a0fb76f080..408c4611e5de 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c
@@ -38,7 +38,7 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0x824, 0x00030FE0,
 		0x828, 0x00000000,
 		0x82C, 0x002083DD,
-		0x830, 0x2AAA6C86,
+		0x830, 0x2EAAEEB8,
 		0x834, 0x0037A706,
 		0x838, 0x06C89B44,
 		0x83C, 0x0000095B,
@@ -68,7 +68,7 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0x8BC, 0x4CA520A3,
 		0x8C0, 0x27F00020,
 		0x8C4, 0x00000000,
-		0x8C8, 0x00013169,
+		0x8C8, 0x00012D69,
 		0x8CC, 0x08248492,
 		0x8D0, 0x0000B800,
 		0x8DC, 0x00000000,
@@ -76,13 +76,7 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0x8D8, 0x290B5612,
 		0x8F8, 0x400002C0,
 		0x8FC, 0x00000000,
-	0xFF0F07D8, 0xABCD,
 		0x900, 0x00000701,
-	0xFF0F07D0, 0xCDEF,
-		0x900, 0x00000701,
-	0xCDCDCDCD, 0xCDCD,
-		0x900, 0x00000700,
-	0xFF0F07D8, 0xDEAD,
 		0x90C, 0x00000000,
 		0x910, 0x0000FC00,
 		0x914, 0x00000404,
@@ -120,7 +114,7 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0x9D4, 0x00000000,
 		0x9D8, 0x00000000,
 		0x9DC, 0x00000000,
-		0x9E4, 0x00000002,
+		0x9E4, 0x00000003,
 		0x9E8, 0x000002D5,
 		0xA00, 0x00D047C8,
 		0xA04, 0x01FF000C,
@@ -189,7 +183,21 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0xC5C, 0x00000058,
 		0xC60, 0x34344443,
 		0xC64, 0x07003333,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
+		0xC68, 0x59791979,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
+		0xC68, 0x59791979,
+	0x90000002, 0x00000000, 0x40000000, 0x00000000,
+		0xC68, 0x59791979,
+	0x90000004, 0x00000000, 0x40000000, 0x00000000,
+		0xC68, 0x59791979,
+	0x90000001, 0x00000000, 0x40000000, 0x00000000,
+		0xC68, 0x59791979,
+	0x90000001, 0x00000005, 0x40000000, 0x00000000,
 		0xC68, 0x59791979,
+	0xA0000000, 0x00000000,
+		0xC68, 0x59799979,
+	0xB0000000, 0x00000000,
 		0xC6C, 0x59795979,
 		0xC70, 0x19795979,
 		0xC74, 0x19795979,
@@ -203,19 +211,7 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0xCA0, 0x00000029,
 		0xCA4, 0x08040201,
 		0xCA8, 0x80402010,
-	0xFF0F0740, 0xABCD,
-		0xCB0, 0x77547717,
-	0xFF0F01C0, 0xCDEF,
-		0xCB0, 0x77547717,
-	0xFF0F02C0, 0xCDEF,
-		0xCB0, 0x77547717,
-	0xFF0F07D8, 0xCDEF,
-		0xCB0, 0x54547710,
-	0xFF0F07D0, 0xCDEF,
-		0xCB0, 0x54547710,
-	0xCDCDCDCD, 0xCDCD,
 		0xCB0, 0x77547777,
-	0xFF0F0740, 0xDEAD,
 		0xCB4, 0x00000077,
 		0xCB8, 0x00508242,
 		0xE00, 0x00000007,
@@ -257,23 +253,14 @@ u32 RTL8812AE_PHY_REG_ARRAY[] = {
 		0xEA0, 0x00000029,
 		0xEA4, 0x08040201,
 		0xEA8, 0x80402010,
-	0xFF0F0740, 0xABCD,
-		0xEB0, 0x77547717,
-	0xFF0F01C0, 0xCDEF,
-		0xEB0, 0x77547717,
-	0xFF0F02C0, 0xCDEF,
-		0xEB0, 0x77547717,
-	0xFF0F07D8, 0xCDEF,
-		0xEB0, 0x54547710,
-	0xFF0F07D0, 0xCDEF,
-		0xEB0, 0x54547710,
-	0xCDCDCDCD, 0xCDCD,
 		0xEB0, 0x77547777,
-	0xFF0F0740, 0xDEAD,
 		0xEB4, 0x00000077,
 		0xEB8, 0x00508242,
 };
 
+u32 RTL8812AE_PHY_REG_1TARRAYLEN =
+	sizeof(RTL8812AE_PHY_REG_ARRAY) / sizeof(u32);
+
 u32 RTL8821AE_PHY_REG_ARRAY[] = {
 	0x800, 0x0020D090,
 	0x804, 0x080112E0,
@@ -449,6 +436,9 @@ u32 RTL8821AE_PHY_REG_ARRAY[] = {
 	0xCB8, 0x00508240,
 };
 
+u32 RTL8821AE_PHY_REG_1TARRAYLEN =
+	sizeof(RTL8821AE_PHY_REG_ARRAY) / sizeof(u32);
+
 u32 RTL8812AE_PHY_REG_ARRAY_PG[] = {
 	0, 0, 0, 0x00000c20, 0xffffffff, 0x34363840,
 	0, 0, 0, 0x00000c24, 0xffffffff, 0x42424444,
@@ -498,6 +488,9 @@ u32 RTL8812AE_PHY_REG_ARRAY_PG[] = {
 	1, 1, 1, 0x00000e4c, 0xffffffff, 0x22242628
 };
 
+u32 RTL8812AE_PHY_REG_ARRAY_PGLEN =
+		sizeof(RTL8812AE_PHY_REG_ARRAY_PG) / sizeof(u32);
+
 u32 RTL8821AE_PHY_REG_ARRAY_PG[] = {
 	0, 0, 0, 0x00000c20, 0xffffffff, 0x32343638,
 	0, 0, 0, 0x00000c24, 0xffffffff, 0x36363838,
@@ -516,6 +509,9 @@ u32 RTL8821AE_PHY_REG_ARRAY_PG[] = {
 	1, 0, 0, 0x00000c44, 0x0000ffff, 0x00002022
 };
 
+u32 RTL8821AE_PHY_REG_ARRAY_PGLEN =
+		sizeof(RTL8821AE_PHY_REG_ARRAY_PG) / sizeof(u32);
+
 u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x000, 0x00010000,
 		0x018, 0x0001712A,
@@ -523,26 +519,25 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x066, 0x00040000,
 		0x01E, 0x00080000,
 		0x089, 0x00000080,
-	0xFF0F0740, 0xABCD,
-		0x086, 0x00014B38,
-	0xFF0F02C0, 0xCDEF,
-		0x086, 0x00014B38,
-	0xFF0F01C0, 0xCDEF,
-		0x086, 0x00014B38,
-	0xFF0F07D8, 0xCDEF,
+	0x80000001, 0x00000000, 0x40000000, 0x00000000,
 		0x086, 0x00014B3A,
-	0xFF0F07D0, 0xCDEF,
+	0x90000001, 0x00000005, 0x40000000, 0x00000000,
 		0x086, 0x00014B3A,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x086, 0x00014B38,
-	0xFF0F0740, 0xDEAD,
+	0xB0000000, 0x00000000,
+	0x80000004, 0x00000000, 0x40000000, 0x00000000,
+		0x08B, 0x00080180,
+	0xA0000000, 0x00000000,
+		0x08B, 0x00087180,
+	0xB0000000, 0x00000000,
 		0x0B1, 0x0001FC1A,
 		0x0B3, 0x000F0810,
 		0x0B4, 0x0001A78D,
 		0x0BA, 0x00086180,
 		0x018, 0x00000006,
 		0x0EF, 0x00002000,
-	0xFF0F07D8, 0xABCD,
+	0x80000001, 0x00000000, 0x40000000, 0x00000000,
 		0x03B, 0x0003F218,
 		0x03B, 0x00030A58,
 		0x03B, 0x0002FA58,
@@ -550,7 +545,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x03B, 0x0001FA50,
 		0x03B, 0x00010248,
 		0x03B, 0x00008240,
-	0xFF0F07D0, 0xCDEF,
+	0x90000001, 0x00000005, 0x40000000, 0x00000000,
 		0x03B, 0x0003F218,
 		0x03B, 0x00030A58,
 		0x03B, 0x0002FA58,
@@ -558,7 +553,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x03B, 0x0001FA50,
 		0x03B, 0x00010248,
 		0x03B, 0x00008240,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x03B, 0x00038A58,
 		0x03B, 0x00037A58,
 		0x03B, 0x0002A590,
@@ -566,9 +561,9 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x03B, 0x00018248,
 		0x03B, 0x00010240,
 		0x03B, 0x00008240,
-	0xFF0F07D8, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000100,
-	0xFF0F07D8, 0xABCD,
+	0x80000002, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0000A4EE,
 		0x034, 0x00009076,
 		0x034, 0x00008073,
@@ -580,7 +575,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x034, 0x00002028,
 		0x034, 0x00001025,
 		0x034, 0x00000022,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x034, 0x0000ADF4,
 		0x034, 0x00009DF1,
 		0x034, 0x00008DEE,
@@ -592,7 +587,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x034, 0x000024E7,
 		0x034, 0x0000146B,
 		0x034, 0x0000006D,
-	0xFF0F07D8, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
 		0x0EF, 0x000020A2,
 		0x0DF, 0x00000080,
@@ -646,7 +641,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x03B, 0x0006B064,
 		0x03C, 0x00004000,
 		0x03A, 0x000000D8,
-		0x03B, 0x00023070,
+		0x03B, 0x00063070,
 		0x03C, 0x00004000,
 		0x03A, 0x00000468,
 		0x03B, 0x0005B870,
@@ -685,43 +680,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x03B, 0x00082080,
 		0x03C, 0x00010000,
 		0x0EF, 0x00001100,
-	0xFF0F0740, 0xABCD,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xFF0F02C0, 0xCDEF,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xFF0F01C0, 0xCDEF,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xFF0F07D8, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0004A0B2,
 		0x034, 0x000490AF,
 		0x034, 0x00048070,
@@ -733,80 +692,32 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x034, 0x0004200A,
 		0x034, 0x00041007,
 		0x034, 0x00040004,
-	0xFF0F07D0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x034, 0x0004A0B2,
 		0x034, 0x000490AF,
 		0x034, 0x00048070,
 		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xCDCDCDCD, 0xCDCD,
+		0x034, 0x0004604D,
+		0x034, 0x0004504A,
+		0x034, 0x00044047,
+		0x034, 0x00043044,
+		0x034, 0x00042007,
+		0x034, 0x00041004,
+		0x034, 0x00040001,
+	0xA0000000, 0x00000000,
 		0x034, 0x0004ADF5,
 		0x034, 0x00049DF2,
 		0x034, 0x00048DEF,
 		0x034, 0x00047DEC,
 		0x034, 0x00046DE9,
-		0x034, 0x00045DC9,
-		0x034, 0x00044CE8,
-		0x034, 0x000438CA,
-		0x034, 0x00042889,
-		0x034, 0x0004184A,
-		0x034, 0x0004044A,
-	0xFF0F0740, 0xDEAD,
-	0xFF0F0740, 0xABCD,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F02C0, 0xCDEF,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F01C0, 0xCDEF,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F07D8, 0xCDEF,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F07D0, 0xCDEF,
+		0x034, 0x00045DE6,
+		0x034, 0x00044DE3,
+		0x034, 0x000438C8,
+		0x034, 0x000428C5,
+		0x034, 0x000418C2,
+		0x034, 0x000408C0,
+	0xB0000000, 0x00000000,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0002A0B2,
 		0x034, 0x000290AF,
 		0x034, 0x00028070,
@@ -818,32 +729,32 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x034, 0x0002200A,
 		0x034, 0x00021007,
 		0x034, 0x00020004,
-	0xCDCDCDCD, 0xCDCD,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
+		0x034, 0x0002A0B4,
+		0x034, 0x000290B1,
+		0x034, 0x00028072,
+		0x034, 0x0002706F,
+		0x034, 0x0002604F,
+		0x034, 0x0002504C,
+		0x034, 0x00024049,
+		0x034, 0x00023046,
+		0x034, 0x00022009,
+		0x034, 0x00021006,
+		0x034, 0x00020003,
+	0xA0000000, 0x00000000,
 		0x034, 0x0002ADF5,
 		0x034, 0x00029DF2,
 		0x034, 0x00028DEF,
 		0x034, 0x00027DEC,
 		0x034, 0x00026DE9,
-		0x034, 0x00025DC9,
-		0x034, 0x00024CE8,
-		0x034, 0x000238CA,
-		0x034, 0x00022889,
-		0x034, 0x0002184A,
-		0x034, 0x0002044A,
-	0xFF0F0740, 0xDEAD,
-	0xFF0F0740, 0xABCD,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
-		0x034, 0x00008070,
-		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xFF0F02C0, 0xCDEF,
+		0x034, 0x00025DE6,
+		0x034, 0x00024DE3,
+		0x034, 0x000238C8,
+		0x034, 0x000228C5,
+		0x034, 0x000218C2,
+		0x034, 0x000208C0,
+	0xB0000000, 0x00000000,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0000A0B2,
 		0x034, 0x000090AF,
 		0x034, 0x00008070,
@@ -855,93 +766,33 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x034, 0x0000200A,
 		0x034, 0x00001007,
 		0x034, 0x00000004,
-	0xFF0F01C0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x034, 0x0000A0B2,
 		0x034, 0x000090AF,
 		0x034, 0x00008070,
 		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xFF0F07D8, 0xCDEF,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
-		0x034, 0x00008070,
-		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xFF0F07D0, 0xCDEF,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
-		0x034, 0x00008070,
-		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xCDCDCDCD, 0xCDCD,
+		0x034, 0x0000604D,
+		0x034, 0x0000504A,
+		0x034, 0x00004047,
+		0x034, 0x00003044,
+		0x034, 0x00002007,
+		0x034, 0x00001004,
+		0x034, 0x00000001,
+	0xA0000000, 0x00000000,
 		0x034, 0x0000AFF7,
 		0x034, 0x00009DF7,
 		0x034, 0x00008DF4,
 		0x034, 0x00007DF1,
 		0x034, 0x00006DEE,
-		0x034, 0x00005DCD,
-		0x034, 0x00004CEB,
+		0x034, 0x00005DEB,
+		0x034, 0x00004DE8,
 		0x034, 0x000038CC,
-		0x034, 0x0000288B,
-		0x034, 0x0000184C,
-		0x034, 0x0000044C,
-	0xFF0F0740, 0xDEAD,
+		0x034, 0x000028C9,
+		0x034, 0x000018C6,
+		0x034, 0x000008C3,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
-	0xFF0F0740, 0xABCD,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000040,
-		0x035, 0x000001D4,
-		0x035, 0x000081D4,
-		0x035, 0x000101D4,
-		0x035, 0x000201B4,
-		0x035, 0x000281B4,
-		0x035, 0x000301B4,
-		0x035, 0x000401B4,
-		0x035, 0x000481B4,
-		0x035, 0x000501B4,
-	0xFF0F02C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000040,
-		0x035, 0x000001D4,
-		0x035, 0x000081D4,
-		0x035, 0x000101D4,
-		0x035, 0x000201B4,
-		0x035, 0x000281B4,
-		0x035, 0x000301B4,
-		0x035, 0x000401B4,
-		0x035, 0x000481B4,
-		0x035, 0x000501B4,
-	0xFF0F01C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000040,
-		0x035, 0x000001D4,
-		0x035, 0x000081D4,
-		0x035, 0x000101D4,
-		0x035, 0x000201B4,
-		0x035, 0x000281B4,
-		0x035, 0x000301B4,
-		0x035, 0x000401B4,
-		0x035, 0x000481B4,
-		0x035, 0x000501B4,
-	0xFF0F07D8, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000040,
 		0x035, 0x000001D4,
@@ -953,7 +804,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x035, 0x000401B4,
 		0x035, 0x000481B4,
 		0x035, 0x000501B4,
-	0xFF0F07D0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000040,
 		0x035, 0x000001D4,
@@ -965,7 +816,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x035, 0x000401B4,
 		0x035, 0x000481B4,
 		0x035, 0x000501B4,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000040,
 		0x035, 0x00000188,
@@ -977,54 +828,9 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x035, 0x000401D8,
 		0x035, 0x000481D8,
 		0x035, 0x000501D8,
-	0xFF0F0740, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
-	0xFF0F0740, 0xABCD,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000010,
-		0x036, 0x00004BFB,
-		0x036, 0x0000CBFB,
-		0x036, 0x00014BFB,
-		0x036, 0x0001CBFB,
-		0x036, 0x00024F4B,
-		0x036, 0x0002CF4B,
-		0x036, 0x00034F4B,
-		0x036, 0x0003CF4B,
-		0x036, 0x00044F4B,
-		0x036, 0x0004CF4B,
-		0x036, 0x00054F4B,
-		0x036, 0x0005CF4B,
-	0xFF0F02C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000010,
-		0x036, 0x00004BFB,
-		0x036, 0x0000CBFB,
-		0x036, 0x00014BFB,
-		0x036, 0x0001CBFB,
-		0x036, 0x00024F4B,
-		0x036, 0x0002CF4B,
-		0x036, 0x00034F4B,
-		0x036, 0x0003CF4B,
-		0x036, 0x00044F4B,
-		0x036, 0x0004CF4B,
-		0x036, 0x00054F4B,
-		0x036, 0x0005CF4B,
-	0xFF0F01C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000010,
-		0x036, 0x00004BFB,
-		0x036, 0x0000CBFB,
-		0x036, 0x00014BFB,
-		0x036, 0x0001CBFB,
-		0x036, 0x00024F4B,
-		0x036, 0x0002CF4B,
-		0x036, 0x00034F4B,
-		0x036, 0x0003CF4B,
-		0x036, 0x00044F4B,
-		0x036, 0x0004CF4B,
-		0x036, 0x00054F4B,
-		0x036, 0x0005CF4B,
-	0xFF0F07D8, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000010,
 		0x036, 0x00004BFB,
@@ -1039,7 +845,7 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x036, 0x0004CF4B,
 		0x036, 0x00054F4B,
 		0x036, 0x0005CF4B,
-	0xFF0F07D0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000010,
 		0x036, 0x00004BFB,
@@ -1054,91 +860,61 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x036, 0x0004CF4B,
 		0x036, 0x00054F4B,
 		0x036, 0x0005CF4B,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000010,
 		0x036, 0x00084EB4,
 		0x036, 0x0008CC35,
 		0x036, 0x00094C35,
 		0x036, 0x0009CC35,
-		0x036, 0x000A4935,
+		0x036, 0x000A4C35,
 		0x036, 0x000ACC35,
 		0x036, 0x000B4C35,
 		0x036, 0x000BCC35,
-		0x036, 0x000C4EB4,
-		0x036, 0x000CCEB5,
-		0x036, 0x000D4EB5,
-		0x036, 0x000DCEB5,
-	0xFF0F0740, 0xDEAD,
+		0x036, 0x000C4C34,
+		0x036, 0x000CCC35,
+		0x036, 0x000D4C35,
+		0x036, 0x000DCC35,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
 		0x0EF, 0x00000008,
-	0xFF0F0740, 0xABCD,
-		0x03C, 0x000002CC,
-		0x03C, 0x00000522,
-		0x03C, 0x00000902,
-	0xFF0F02C0, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x03C, 0x000002CC,
 		0x03C, 0x00000522,
 		0x03C, 0x00000902,
-	0xFF0F01C0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x03C, 0x000002CC,
 		0x03C, 0x00000522,
 		0x03C, 0x00000902,
-	0xFF0F07D8, 0xCDEF,
-		0x03C, 0x000002CC,
-		0x03C, 0x00000522,
-		0x03C, 0x00000902,
-	0xFF0F07D0, 0xCDEF,
-		0x03C, 0x000002CC,
-		0x03C, 0x00000522,
-		0x03C, 0x00000902,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x03C, 0x000002A8,
 		0x03C, 0x000005A2,
 		0x03C, 0x00000880,
-	0xFF0F0740, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000002,
 		0x0DF, 0x00000080,
-		0x01F, 0x00040064,
-	0xFF0F0740, 0xABCD,
-		0x061, 0x000FDD43,
-		0x062, 0x00038F4B,
-		0x063, 0x00032117,
-		0x064, 0x000194AC,
-		0x065, 0x000931D1,
-	0xFF0F02C0, 0xCDEF,
+		0x01F, 0x00000064,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x061, 0x000FDD43,
 		0x062, 0x00038F4B,
 		0x063, 0x00032117,
 		0x064, 0x000194AC,
 		0x065, 0x000931D1,
-	0xFF0F01C0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x061, 0x000FDD43,
 		0x062, 0x00038F4B,
 		0x063, 0x00032117,
 		0x064, 0x000194AC,
-		0x065, 0x000931D1,
-	0xFF0F07D8, 0xCDEF,
-		0x061, 0x000FDD43,
-		0x062, 0x00038F4B,
-		0x063, 0x00032117,
-		0x064, 0x000194AC,
-		0x065, 0x000931D1,
-	0xFF0F07D0, 0xCDEF,
-		0x061, 0x000FDD43,
-		0x062, 0x00038F4B,
-		0x063, 0x00032117,
-		0x064, 0x000194AC,
-		0x065, 0x000931D1,
-	0xCDCDCDCD, 0xCDCD,
+		0x065, 0x000931D2,
+	0xA0000000, 0x00000000,
 		0x061, 0x000E5D53,
 		0x062, 0x00038FCD,
-		0x063, 0x000314EB,
+		0x063, 0x000114EB,
 		0x064, 0x000196AC,
 		0x065, 0x000911D7,
-	0xFF0F0740, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x008, 0x00008400,
 		0x01C, 0x000739D2,
 		0x0B4, 0x0001E78D,
@@ -1149,29 +925,29 @@ u32 RTL8812AE_RADIOA_ARRAY[] = {
 		0x0FE, 0x00000000,
 		0x0B4, 0x0001A78D,
 		0x018, 0x0001712A,
-
 };
 
+u32 RTL8812AE_RADIOA_1TARRAYLEN = sizeof(RTL8812AE_RADIOA_ARRAY) / sizeof(u32);
+
 u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x056, 0x00051CF2,
 		0x066, 0x00040000,
 		0x089, 0x00000080,
-	0xFF0F0740, 0xABCD,
-		0x086, 0x00014B38,
-	0xFF0F01C0, 0xCDEF,
-		0x086, 0x00014B38,
-	0xFF0F02C0, 0xCDEF,
-		0x086, 0x00014B38,
-	0xFF0F07D8, 0xCDEF,
+	0x80000001, 0x00000000, 0x40000000, 0x00000000,
 		0x086, 0x00014B3A,
-	0xFF0F07D0, 0xCDEF,
+	0x90000001, 0x00000005, 0x40000000, 0x00000000,
 		0x086, 0x00014B3A,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x086, 0x00014B38,
-	0xFF0F0740, 0xDEAD,
+	0xB0000000, 0x00000000,
+	0x80000004, 0x00000000, 0x40000000, 0x00000000,
+		0x08B, 0x00080180,
+	0xA0000000, 0x00000000,
+		0x08B, 0x00087180,
+	0xB0000000, 0x00000000,
 		0x018, 0x00000006,
 		0x0EF, 0x00002000,
-	0xFF0F07D8, 0xABCD,
+	0x80000001, 0x00000000, 0x40000000, 0x00000000,
 		0x03B, 0x0003F218,
 		0x03B, 0x00030A58,
 		0x03B, 0x0002FA58,
@@ -1179,7 +955,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x03B, 0x0001FA50,
 		0x03B, 0x00010248,
 		0x03B, 0x00008240,
-	0xFF0F07D0, 0xCDEF,
+	0x90000001, 0x00000005, 0x40000000, 0x00000000,
 		0x03B, 0x0003F218,
 		0x03B, 0x00030A58,
 		0x03B, 0x0002FA58,
@@ -1187,7 +963,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x03B, 0x0001FA50,
 		0x03B, 0x00010248,
 		0x03B, 0x00008240,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x03B, 0x00038A58,
 		0x03B, 0x00037A58,
 		0x03B, 0x0002A590,
@@ -1195,9 +971,9 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x03B, 0x00018248,
 		0x03B, 0x00010240,
 		0x03B, 0x00008240,
-	0xFF0F07D8, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000100,
-	0xFF0F07D8, 0xABCD,
+	0x80000002, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0000A4EE,
 		0x034, 0x00009076,
 		0x034, 0x00008073,
@@ -1209,7 +985,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x034, 0x00002028,
 		0x034, 0x00001025,
 		0x034, 0x00000022,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x034, 0x0000ADF4,
 		0x034, 0x00009DF1,
 		0x034, 0x00008DEE,
@@ -1221,7 +997,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x034, 0x000024E7,
 		0x034, 0x0000146B,
 		0x034, 0x0000006D,
-	0xFF0F07D8, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
 		0x0EF, 0x000020A2,
 		0x0DF, 0x00000080,
@@ -1314,31 +1090,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x03B, 0x00082080,
 		0x03C, 0x00010000,
 		0x0EF, 0x00001100,
-	0xFF0F0740, 0xABCD,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xFF0F01C0, 0xCDEF,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xFF0F02C0, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0004A0B2,
 		0x034, 0x000490AF,
 		0x034, 0x00048070,
@@ -1350,80 +1102,32 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x034, 0x0004200A,
 		0x034, 0x00041007,
 		0x034, 0x00040004,
-	0xFF0F07D8, 0xCDEF,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xFF0F07D0, 0xCDEF,
-		0x034, 0x0004A0B2,
-		0x034, 0x000490AF,
-		0x034, 0x00048070,
-		0x034, 0x0004706D,
-		0x034, 0x00046050,
-		0x034, 0x0004504D,
-		0x034, 0x0004404A,
-		0x034, 0x00043047,
-		0x034, 0x0004200A,
-		0x034, 0x00041007,
-		0x034, 0x00040004,
-	0xCDCDCDCD, 0xCDCD,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
+		0x034, 0x0004A0B1,
+		0x034, 0x000490AE,
+		0x034, 0x0004806F,
+		0x034, 0x0004706C,
+		0x034, 0x0004604C,
+		0x034, 0x00045049,
+		0x034, 0x00044046,
+		0x034, 0x00043043,
+		0x034, 0x00042006,
+		0x034, 0x00041003,
+		0x034, 0x00040000,
+	0xA0000000, 0x00000000,
 		0x034, 0x0004ADF5,
 		0x034, 0x00049DF2,
 		0x034, 0x00048DEF,
 		0x034, 0x00047DEC,
 		0x034, 0x00046DE9,
-		0x034, 0x00045DC9,
-		0x034, 0x00044CE8,
-		0x034, 0x000438CA,
-		0x034, 0x00042889,
-		0x034, 0x0004184A,
-		0x034, 0x0004044A,
-	0xFF0F0740, 0xDEAD,
-	0xFF0F0740, 0xABCD,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F01C0, 0xCDEF,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F02C0, 0xCDEF,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xFF0F07D8, 0xCDEF,
+		0x034, 0x00045DE6,
+		0x034, 0x00044DE3,
+		0x034, 0x000438C8,
+		0x034, 0x000428C5,
+		0x034, 0x000418C2,
+		0x034, 0x000408C0,
+	0xB0000000, 0x00000000,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0002A0B2,
 		0x034, 0x000290AF,
 		0x034, 0x00028070,
@@ -1435,68 +1139,32 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x034, 0x0002200A,
 		0x034, 0x00021007,
 		0x034, 0x00020004,
-	0xFF0F07D0, 0xCDEF,
-		0x034, 0x0002A0B2,
-		0x034, 0x000290AF,
-		0x034, 0x00028070,
-		0x034, 0x0002706D,
-		0x034, 0x00026050,
-		0x034, 0x0002504D,
-		0x034, 0x0002404A,
-		0x034, 0x00023047,
-		0x034, 0x0002200A,
-		0x034, 0x00021007,
-		0x034, 0x00020004,
-	0xCDCDCDCD, 0xCDCD,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
+		0x034, 0x0002A0B3,
+		0x034, 0x000290B0,
+		0x034, 0x00028071,
+		0x034, 0x0002706E,
+		0x034, 0x0002604E,
+		0x034, 0x0002504B,
+		0x034, 0x00024048,
+		0x034, 0x00023045,
+		0x034, 0x00022008,
+		0x034, 0x00021005,
+		0x034, 0x00020002,
+	0xA0000000, 0x00000000,
 		0x034, 0x0002ADF5,
 		0x034, 0x00029DF2,
 		0x034, 0x00028DEF,
 		0x034, 0x00027DEC,
 		0x034, 0x00026DE9,
-		0x034, 0x00025DC9,
-		0x034, 0x00024CE8,
-		0x034, 0x000238CA,
-		0x034, 0x00022889,
-		0x034, 0x0002184A,
-		0x034, 0x0002044A,
-	0xFF0F0740, 0xDEAD,
-	0xFF0F0740, 0xABCD,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
-		0x034, 0x00008070,
-		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xFF0F01C0, 0xCDEF,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
-		0x034, 0x00008070,
-		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xFF0F02C0, 0xCDEF,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
-		0x034, 0x00008070,
-		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xFF0F07D8, 0xCDEF,
+		0x034, 0x00025DE6,
+		0x034, 0x00024DE3,
+		0x034, 0x000238C8,
+		0x034, 0x000228C5,
+		0x034, 0x000218C2,
+		0x034, 0x000208C0,
+	0xB0000000, 0x00000000,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x034, 0x0000A0B2,
 		0x034, 0x000090AF,
 		0x034, 0x00008070,
@@ -1508,72 +1176,33 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x034, 0x0000200A,
 		0x034, 0x00001007,
 		0x034, 0x00000004,
-	0xFF0F07D0, 0xCDEF,
-		0x034, 0x0000A0B2,
-		0x034, 0x000090AF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
+		0x034, 0x0000A0B3,
+		0x034, 0x000090B0,
 		0x034, 0x00008070,
 		0x034, 0x0000706D,
-		0x034, 0x00006050,
-		0x034, 0x0000504D,
-		0x034, 0x0000404A,
-		0x034, 0x00003047,
-		0x034, 0x0000200A,
-		0x034, 0x00001007,
-		0x034, 0x00000004,
-	0xCDCDCDCD, 0xCDCD,
+		0x034, 0x0000604D,
+		0x034, 0x0000504A,
+		0x034, 0x00004047,
+		0x034, 0x00003044,
+		0x034, 0x00002007,
+		0x034, 0x00001004,
+		0x034, 0x00000001,
+	0xA0000000, 0x00000000,
 		0x034, 0x0000AFF7,
 		0x034, 0x00009DF7,
 		0x034, 0x00008DF4,
 		0x034, 0x00007DF1,
 		0x034, 0x00006DEE,
-		0x034, 0x00005DCD,
-		0x034, 0x00004CEB,
+		0x034, 0x00005DEB,
+		0x034, 0x00004DE8,
 		0x034, 0x000038CC,
-		0x034, 0x0000288B,
-		0x034, 0x0000184C,
-		0x034, 0x0000044C,
-	0xFF0F0740, 0xDEAD,
-		0x0EF, 0x00000000,
-	0xFF0F0740, 0xABCD,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000040,
-		0x035, 0x000001C5,
-		0x035, 0x000081C5,
-		0x035, 0x000101C5,
-		0x035, 0x00020174,
-		0x035, 0x00028174,
-		0x035, 0x00030174,
-		0x035, 0x00040185,
-		0x035, 0x00048185,
-		0x035, 0x00050185,
-		0x0EF, 0x00000000,
-	0xFF0F01C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000040,
-		0x035, 0x000001C5,
-		0x035, 0x000081C5,
-		0x035, 0x000101C5,
-		0x035, 0x00020174,
-		0x035, 0x00028174,
-		0x035, 0x00030174,
-		0x035, 0x00040185,
-		0x035, 0x00048185,
-		0x035, 0x00050185,
-		0x0EF, 0x00000000,
-	0xFF0F02C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000040,
-		0x035, 0x000001C5,
-		0x035, 0x000081C5,
-		0x035, 0x000101C5,
-		0x035, 0x00020174,
-		0x035, 0x00028174,
-		0x035, 0x00030174,
-		0x035, 0x00040185,
-		0x035, 0x00048185,
-		0x035, 0x00050185,
+		0x034, 0x000028C9,
+		0x034, 0x000018C6,
+		0x034, 0x000008C3,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
-	0xFF0F07D8, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000040,
 		0x035, 0x000001C5,
@@ -1586,7 +1215,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x035, 0x00048185,
 		0x035, 0x00050185,
 		0x0EF, 0x00000000,
-	0xFF0F07D0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000040,
 		0x035, 0x000001C5,
@@ -1599,51 +1228,21 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x035, 0x00048185,
 		0x035, 0x00050185,
 		0x0EF, 0x00000000,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000040,
-		0x035, 0x00000186,
-		0x035, 0x00008186,
-		0x035, 0x00010185,
-		0x035, 0x000201D5,
-		0x035, 0x000281D5,
-		0x035, 0x000301D5,
-		0x035, 0x000401D5,
-		0x035, 0x000481D5,
-		0x035, 0x000501D5,
+		0x035, 0x00000188,
+		0x035, 0x00008147,
+		0x035, 0x00010147,
+		0x035, 0x000201D7,
+		0x035, 0x000281D7,
+		0x035, 0x000301D7,
+		0x035, 0x000401D8,
+		0x035, 0x000481D8,
+		0x035, 0x000501D8,
 		0x0EF, 0x00000000,
-	0xFF0F0740, 0xDEAD,
-	0xFF0F0740, 0xABCD,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000010,
-		0x036, 0x00005B8B,
-		0x036, 0x0000DB8B,
-		0x036, 0x00015B8B,
-		0x036, 0x0001DB8B,
-		0x036, 0x000262DB,
-		0x036, 0x0002E2DB,
-		0x036, 0x000362DB,
-		0x036, 0x0003E2DB,
-		0x036, 0x0004553B,
-		0x036, 0x0004D53B,
-		0x036, 0x0005553B,
-		0x036, 0x0005D53B,
-	0xFF0F01C0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000010,
-		0x036, 0x00005B8B,
-		0x036, 0x0000DB8B,
-		0x036, 0x00015B8B,
-		0x036, 0x0001DB8B,
-		0x036, 0x000262DB,
-		0x036, 0x0002E2DB,
-		0x036, 0x000362DB,
-		0x036, 0x0003E2DB,
-		0x036, 0x0004553B,
-		0x036, 0x0004D53B,
-		0x036, 0x0005553B,
-		0x036, 0x0005D53B,
-	0xFF0F02C0, 0xCDEF,
+	0xB0000000, 0x00000000,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000010,
 		0x036, 0x00005B8B,
@@ -1658,7 +1257,7 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x036, 0x0004D53B,
 		0x036, 0x0005553B,
 		0x036, 0x0005D53B,
-	0xFF0F07D8, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000010,
 		0x036, 0x00005B8B,
@@ -1673,109 +1272,71 @@ u32 RTL8812AE_RADIOB_ARRAY[] = {
 		0x036, 0x0004D53B,
 		0x036, 0x0005553B,
 		0x036, 0x0005D53B,
-	0xFF0F07D0, 0xCDEF,
-		0x018, 0x0001712A,
-		0x0EF, 0x00000010,
-		0x036, 0x00005B8B,
-		0x036, 0x0000DB8B,
-		0x036, 0x00015B8B,
-		0x036, 0x0001DB8B,
-		0x036, 0x000262DB,
-		0x036, 0x0002E2DB,
-		0x036, 0x000362DB,
-		0x036, 0x0003E2DB,
-		0x036, 0x0004553B,
-		0x036, 0x0004D53B,
-		0x036, 0x0005553B,
-		0x036, 0x0005D53B,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000010,
 		0x036, 0x00084EB4,
-		0x036, 0x0008C9B4,
-		0x036, 0x000949B4,
-		0x036, 0x0009C9B4,
-		0x036, 0x000A4935,
-		0x036, 0x000AC935,
-		0x036, 0x000B4935,
-		0x036, 0x000BC935,
-		0x036, 0x000C4EB4,
-		0x036, 0x000CCEB4,
-		0x036, 0x000D4EB4,
-		0x036, 0x000DCEB4,
-	0xFF0F0740, 0xDEAD,
+		0x036, 0x0008CC35,
+		0x036, 0x00094C35,
+		0x036, 0x0009CC35,
+		0x036, 0x000A4C35,
+		0x036, 0x000ACC35,
+		0x036, 0x000B4C35,
+		0x036, 0x000BCC35,
+		0x036, 0x000C4C34,
+		0x036, 0x000CCC35,
+		0x036, 0x000D4C35,
+		0x036, 0x000DCC35,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
 		0x0EF, 0x00000008,
-	0xFF0F0740, 0xABCD,
-		0x03C, 0x000002DC,
-		0x03C, 0x00000524,
-		0x03C, 0x00000902,
-	0xFF0F01C0, 0xCDEF,
-		0x03C, 0x000002DC,
-		0x03C, 0x00000524,
-		0x03C, 0x00000902,
-	0xFF0F02C0, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x03C, 0x000002DC,
 		0x03C, 0x00000524,
 		0x03C, 0x00000902,
-	0xFF0F07D8, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x03C, 0x000002DC,
 		0x03C, 0x00000524,
 		0x03C, 0x00000902,
-	0xFF0F07D0, 0xCDEF,
-		0x03C, 0x000002DC,
-		0x03C, 0x00000524,
-		0x03C, 0x00000902,
-	0xCDCDCDCD, 0xCDCD,
-		0x03C, 0x000002AA,
+	0xA0000000, 0x00000000,
+		0x03C, 0x000002A8,
 		0x03C, 0x000005A2,
 		0x03C, 0x00000880,
-	0xFF0F0740, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0x0EF, 0x00000000,
 		0x018, 0x0001712A,
 		0x0EF, 0x00000002,
 		0x0DF, 0x00000080,
-	0xFF0F0740, 0xABCD,
-		0x061, 0x000EAC43,
-		0x062, 0x00038F47,
-		0x063, 0x00031157,
-		0x064, 0x0001C4AC,
-		0x065, 0x000931D1,
-	0xFF0F01C0, 0xCDEF,
+	0x80000008, 0x00000000, 0x40000000, 0x00000000,
 		0x061, 0x000EAC43,
 		0x062, 0x00038F47,
 		0x063, 0x00031157,
 		0x064, 0x0001C4AC,
 		0x065, 0x000931D1,
-	0xFF0F02C0, 0xCDEF,
+	0x90000008, 0x05000000, 0x40000000, 0x00000000,
 		0x061, 0x000EAC43,
 		0x062, 0x00038F47,
 		0x063, 0x00031157,
 		0x064, 0x0001C4AC,
-		0x065, 0x000931D1,
-	0xFF0F07D8, 0xCDEF,
+		0x065, 0x000931D2,
+	0x90000002, 0x00000000, 0x40000000, 0x00000000,
 		0x061, 0x000EAC43,
 		0x062, 0x00038F47,
 		0x063, 0x00031157,
 		0x064, 0x0001C4AC,
 		0x065, 0x000931D1,
-	0xFF0F07D0, 0xCDEF,
-		0x061, 0x000EAC43,
-		0x062, 0x00038F47,
-		0x063, 0x00031157,
-		0x064, 0x0001C4AC,
-		0x065, 0x000931D1,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x061, 0x000E5D53,
 		0x062, 0x00038FCD,
-		0x063, 0x000314EB,
+		0x063, 0x000114EB,
 		0x064, 0x000196AC,
-		0x065, 0x000931D7,
-	0xFF0F0740, 0xDEAD,
+		0x065, 0x000911D7,
+	0xB0000000, 0x00000000,
 		0x008, 0x00008400,
-
 };
 
+u32 RTL8812AE_RADIOB_1TARRAYLEN = sizeof(RTL8812AE_RADIOB_ARRAY) / sizeof(u32);
+
 u32 RTL8821AE_RADIOA_ARRAY[] = {
 		0x018, 0x0001712A,
 		0x056, 0x00051CF2,
@@ -2285,16 +1846,16 @@ u32 RTL8821AE_RADIOA_ARRAY[] = {
 		0x0EF, 0x00000000,
 		0x0EF, 0x00000100,
 		0x034, 0x0000ADF3,
-		0x034, 0x00009DEF,
-		0x034, 0x00008DEC,
-		0x034, 0x00007DE9,
-		0x034, 0x00006CED,
-		0x034, 0x00005CE9,
-		0x034, 0x000044E9,
-		0x034, 0x000034E6,
-		0x034, 0x0000246A,
-		0x034, 0x00001467,
-		0x034, 0x00000068,
+		0x034, 0x00009DF0,
+		0x034, 0x00008D70,
+		0x034, 0x00007D6D,
+		0x034, 0x00006CEE,
+		0x034, 0x00005CCC,
+		0x034, 0x000044EC,
+		0x034, 0x000034AC,
+		0x034, 0x0000246D,
+		0x034, 0x0000106F,
+		0x034, 0x0000006C,
 		0x0EF, 0x00000000,
 		0x0ED, 0x00000010,
 		0x044, 0x0000ADF2,
@@ -2365,18 +1926,21 @@ u32 RTL8821AE_RADIOA_ARRAY[] = {
 		0x0FE, 0x00000000,
 		0x0FE, 0x00000000,
 		0x018, 0x0001712A,
+
 };
 
+u32 RTL8821AE_RADIOA_1TARRAYLEN = sizeof(RTL8821AE_RADIOA_ARRAY) / sizeof(u32);
+
 u32 RTL8812AE_MAC_REG_ARRAY[] = {
 		0x010, 0x0000000C,
-	0xFF0F0180, 0xABCD,
-		0x025, 0x0000000F,
-	0xFF0F01C0, 0xCDEF,
+	0x80000200, 0x00000000, 0x40000000, 0x00000000,
+		0x011, 0x00000066,
+	0xA0000000, 0x00000000,
+		0x011, 0x0000005A,
+	0xB0000000, 0x00000000,
 		0x025, 0x0000000F,
-	0xCDCDCDCD, 0xCDCD,
-		0x025, 0x0000006F,
-	0xFF0F0180, 0xDEAD,
 		0x072, 0x00000000,
+		0x420, 0x00000080,
 		0x428, 0x0000000A,
 		0x429, 0x00000010,
 		0x430, 0x00000000,
@@ -2443,7 +2007,7 @@ u32 RTL8812AE_MAC_REG_ARRAY[] = {
 		0x559, 0x00000002,
 		0x55C, 0x00000050,
 		0x55D, 0x000000FF,
-		0x604, 0x00000001,
+		0x604, 0x00000009,
 		0x605, 0x00000030,
 		0x607, 0x00000003,
 		0x608, 0x0000000E,
@@ -2475,9 +2039,10 @@ u32 RTL8812AE_MAC_REG_ARRAY[] = {
 		0x70A, 0x00000065,
 		0x70B, 0x00000087,
 		0x718, 0x00000040,
-
 };
 
+u32 RTL8812AE_MAC_1T_ARRAYLEN = sizeof(RTL8812AE_MAC_REG_ARRAY) / sizeof(u32);
+
 u32 RTL8821AE_MAC_REG_ARRAY[] = {
 		0x428, 0x0000000A,
 		0x429, 0x00000010,
@@ -2578,8 +2143,10 @@ u32 RTL8821AE_MAC_REG_ARRAY[] = {
 		0x718, 0x00000040,
 };
 
+u32 RTL8821AE_MAC_1T_ARRAYLEN = sizeof(RTL8821AE_MAC_REG_ARRAY) / sizeof(u32);
+
 u32 RTL8812AE_AGC_TAB_ARRAY[] = {
-	0xFF0F07D8, 0xABCD,
+	0x80000001, 0x00000000, 0x40000000, 0x00000000,
 		0x81C, 0xFC000001,
 		0x81C, 0xFB020001,
 		0x81C, 0xFA040001,
@@ -2644,7 +2211,7 @@ u32 RTL8812AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0x217A0001,
 		0x81C, 0x217C0001,
 		0x81C, 0x217E0001,
-	0xFF0F07D0, 0xCDEF,
+	0x90000001, 0x00000005, 0x40000000, 0x00000000,
 		0x81C, 0xF9000001,
 		0x81C, 0xF8020001,
 		0x81C, 0xF7040001,
@@ -2709,7 +2276,7 @@ u32 RTL8812AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0x217A0001,
 		0x81C, 0x217C0001,
 		0x81C, 0x217E0001,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x81C, 0xFF000001,
 		0x81C, 0xFF020001,
 		0x81C, 0xFF040001,
@@ -2774,333 +2341,8 @@ u32 RTL8812AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0x417A0001,
 		0x81C, 0x417C0001,
 		0x81C, 0x417E0001,
-	0xFF0F07D8, 0xDEAD,
-	0xFF0F0180, 0xABCD,
-		0x81C, 0xFC800001,
-		0x81C, 0xFB820001,
-		0x81C, 0xFA840001,
-		0x81C, 0xF9860001,
-		0x81C, 0xF8880001,
-		0x81C, 0xF78A0001,
-		0x81C, 0xF68C0001,
-		0x81C, 0xF58E0001,
-		0x81C, 0xF4900001,
-		0x81C, 0xF3920001,
-		0x81C, 0xF2940001,
-		0x81C, 0xF1960001,
-		0x81C, 0xF0980001,
-		0x81C, 0xEF9A0001,
-		0x81C, 0xEE9C0001,
-		0x81C, 0xED9E0001,
-		0x81C, 0xECA00001,
-		0x81C, 0xEBA20001,
-		0x81C, 0xEAA40001,
-		0x81C, 0xE9A60001,
-		0x81C, 0xE8A80001,
-		0x81C, 0xE7AA0001,
-		0x81C, 0xE6AC0001,
-		0x81C, 0xE5AE0001,
-		0x81C, 0xE4B00001,
-		0x81C, 0xE3B20001,
-		0x81C, 0xA8B40001,
-		0x81C, 0xA7B60001,
-		0x81C, 0xA6B80001,
-		0x81C, 0xA5BA0001,
-		0x81C, 0xA4BC0001,
-		0x81C, 0xA3BE0001,
-		0x81C, 0xA2C00001,
-		0x81C, 0xA1C20001,
-		0x81C, 0x68C40001,
-		0x81C, 0x67C60001,
-		0x81C, 0x66C80001,
-		0x81C, 0x65CA0001,
-		0x81C, 0x64CC0001,
-		0x81C, 0x47CE0001,
-		0x81C, 0x46D00001,
-		0x81C, 0x45D20001,
-		0x81C, 0x44D40001,
-		0x81C, 0x43D60001,
-		0x81C, 0x42D80001,
-		0x81C, 0x08DA0001,
-		0x81C, 0x07DC0001,
-		0x81C, 0x06DE0001,
-		0x81C, 0x05E00001,
-		0x81C, 0x04E20001,
-		0x81C, 0x03E40001,
-		0x81C, 0x02E60001,
-		0x81C, 0x01E80001,
-		0x81C, 0x01EA0001,
-		0x81C, 0x01EC0001,
-		0x81C, 0x01EE0001,
-		0x81C, 0x01F00001,
-		0x81C, 0x01F20001,
-		0x81C, 0x01F40001,
-		0x81C, 0x01F60001,
-		0x81C, 0x01F80001,
-		0x81C, 0x01FA0001,
-		0x81C, 0x01FC0001,
-		0x81C, 0x01FE0001,
-	0xFF0F0280, 0xCDEF,
-		0x81C, 0xFC800001,
-		0x81C, 0xFB820001,
-		0x81C, 0xFA840001,
-		0x81C, 0xF9860001,
-		0x81C, 0xF8880001,
-		0x81C, 0xF78A0001,
-		0x81C, 0xF68C0001,
-		0x81C, 0xF58E0001,
-		0x81C, 0xF4900001,
-		0x81C, 0xF3920001,
-		0x81C, 0xF2940001,
-		0x81C, 0xF1960001,
-		0x81C, 0xF0980001,
-		0x81C, 0xEF9A0001,
-		0x81C, 0xEE9C0001,
-		0x81C, 0xED9E0001,
-		0x81C, 0xECA00001,
-		0x81C, 0xEBA20001,
-		0x81C, 0xEAA40001,
-		0x81C, 0xE9A60001,
-		0x81C, 0xE8A80001,
-		0x81C, 0xE7AA0001,
-		0x81C, 0xE6AC0001,
-		0x81C, 0xE5AE0001,
-		0x81C, 0xE4B00001,
-		0x81C, 0xE3B20001,
-		0x81C, 0xA8B40001,
-		0x81C, 0xA7B60001,
-		0x81C, 0xA6B80001,
-		0x81C, 0xA5BA0001,
-		0x81C, 0xA4BC0001,
-		0x81C, 0xA3BE0001,
-		0x81C, 0xA2C00001,
-		0x81C, 0xA1C20001,
-		0x81C, 0x68C40001,
-		0x81C, 0x67C60001,
-		0x81C, 0x66C80001,
-		0x81C, 0x65CA0001,
-		0x81C, 0x64CC0001,
-		0x81C, 0x47CE0001,
-		0x81C, 0x46D00001,
-		0x81C, 0x45D20001,
-		0x81C, 0x44D40001,
-		0x81C, 0x43D60001,
-		0x81C, 0x42D80001,
-		0x81C, 0x08DA0001,
-		0x81C, 0x07DC0001,
-		0x81C, 0x06DE0001,
-		0x81C, 0x05E00001,
-		0x81C, 0x04E20001,
-		0x81C, 0x03E40001,
-		0x81C, 0x02E60001,
-		0x81C, 0x01E80001,
-		0x81C, 0x01EA0001,
-		0x81C, 0x01EC0001,
-		0x81C, 0x01EE0001,
-		0x81C, 0x01F00001,
-		0x81C, 0x01F20001,
-		0x81C, 0x01F40001,
-		0x81C, 0x01F60001,
-		0x81C, 0x01F80001,
-		0x81C, 0x01FA0001,
-		0x81C, 0x01FC0001,
-		0x81C, 0x01FE0001,
-	0xFF0F01C0, 0xCDEF,
-		0x81C, 0xFC800001,
-		0x81C, 0xFB820001,
-		0x81C, 0xFA840001,
-		0x81C, 0xF9860001,
-		0x81C, 0xF8880001,
-		0x81C, 0xF78A0001,
-		0x81C, 0xF68C0001,
-		0x81C, 0xF58E0001,
-		0x81C, 0xF4900001,
-		0x81C, 0xF3920001,
-		0x81C, 0xF2940001,
-		0x81C, 0xF1960001,
-		0x81C, 0xF0980001,
-		0x81C, 0xEF9A0001,
-		0x81C, 0xEE9C0001,
-		0x81C, 0xED9E0001,
-		0x81C, 0xECA00001,
-		0x81C, 0xEBA20001,
-		0x81C, 0xEAA40001,
-		0x81C, 0xE9A60001,
-		0x81C, 0xE8A80001,
-		0x81C, 0xE7AA0001,
-		0x81C, 0xE6AC0001,
-		0x81C, 0xE5AE0001,
-		0x81C, 0xE4B00001,
-		0x81C, 0xE3B20001,
-		0x81C, 0xA8B40001,
-		0x81C, 0xA7B60001,
-		0x81C, 0xA6B80001,
-		0x81C, 0xA5BA0001,
-		0x81C, 0xA4BC0001,
-		0x81C, 0xA3BE0001,
-		0x81C, 0xA2C00001,
-		0x81C, 0xA1C20001,
-		0x81C, 0x68C40001,
-		0x81C, 0x67C60001,
-		0x81C, 0x66C80001,
-		0x81C, 0x65CA0001,
-		0x81C, 0x64CC0001,
-		0x81C, 0x47CE0001,
-		0x81C, 0x46D00001,
-		0x81C, 0x45D20001,
-		0x81C, 0x44D40001,
-		0x81C, 0x43D60001,
-		0x81C, 0x42D80001,
-		0x81C, 0x08DA0001,
-		0x81C, 0x07DC0001,
-		0x81C, 0x06DE0001,
-		0x81C, 0x05E00001,
-		0x81C, 0x04E20001,
-		0x81C, 0x03E40001,
-		0x81C, 0x02E60001,
-		0x81C, 0x01E80001,
-		0x81C, 0x01EA0001,
-		0x81C, 0x01EC0001,
-		0x81C, 0x01EE0001,
-		0x81C, 0x01F00001,
-		0x81C, 0x01F20001,
-		0x81C, 0x01F40001,
-		0x81C, 0x01F60001,
-		0x81C, 0x01F80001,
-		0x81C, 0x01FA0001,
-		0x81C, 0x01FC0001,
-		0x81C, 0x01FE0001,
-	0xFF0F02C0, 0xCDEF,
-		0x81C, 0xFC800001,
-		0x81C, 0xFB820001,
-		0x81C, 0xFA840001,
-		0x81C, 0xF9860001,
-		0x81C, 0xF8880001,
-		0x81C, 0xF78A0001,
-		0x81C, 0xF68C0001,
-		0x81C, 0xF58E0001,
-		0x81C, 0xF4900001,
-		0x81C, 0xF3920001,
-		0x81C, 0xF2940001,
-		0x81C, 0xF1960001,
-		0x81C, 0xF0980001,
-		0x81C, 0xEF9A0001,
-		0x81C, 0xEE9C0001,
-		0x81C, 0xED9E0001,
-		0x81C, 0xECA00001,
-		0x81C, 0xEBA20001,
-		0x81C, 0xEAA40001,
-		0x81C, 0xE9A60001,
-		0x81C, 0xE8A80001,
-		0x81C, 0xE7AA0001,
-		0x81C, 0xE6AC0001,
-		0x81C, 0xE5AE0001,
-		0x81C, 0xE4B00001,
-		0x81C, 0xE3B20001,
-		0x81C, 0xA8B40001,
-		0x81C, 0xA7B60001,
-		0x81C, 0xA6B80001,
-		0x81C, 0xA5BA0001,
-		0x81C, 0xA4BC0001,
-		0x81C, 0xA3BE0001,
-		0x81C, 0xA2C00001,
-		0x81C, 0xA1C20001,
-		0x81C, 0x68C40001,
-		0x81C, 0x67C60001,
-		0x81C, 0x66C80001,
-		0x81C, 0x65CA0001,
-		0x81C, 0x64CC0001,
-		0x81C, 0x47CE0001,
-		0x81C, 0x46D00001,
-		0x81C, 0x45D20001,
-		0x81C, 0x44D40001,
-		0x81C, 0x43D60001,
-		0x81C, 0x42D80001,
-		0x81C, 0x08DA0001,
-		0x81C, 0x07DC0001,
-		0x81C, 0x06DE0001,
-		0x81C, 0x05E00001,
-		0x81C, 0x04E20001,
-		0x81C, 0x03E40001,
-		0x81C, 0x02E60001,
-		0x81C, 0x01E80001,
-		0x81C, 0x01EA0001,
-		0x81C, 0x01EC0001,
-		0x81C, 0x01EE0001,
-		0x81C, 0x01F00001,
-		0x81C, 0x01F20001,
-		0x81C, 0x01F40001,
-		0x81C, 0x01F60001,
-		0x81C, 0x01F80001,
-		0x81C, 0x01FA0001,
-		0x81C, 0x01FC0001,
-		0x81C, 0x01FE0001,
-	0xFF0F07D8, 0xCDEF,
-		0x81C, 0xFC800001,
-		0x81C, 0xFB820001,
-		0x81C, 0xFA840001,
-		0x81C, 0xF9860001,
-		0x81C, 0xF8880001,
-		0x81C, 0xF78A0001,
-		0x81C, 0xF68C0001,
-		0x81C, 0xF58E0001,
-		0x81C, 0xF4900001,
-		0x81C, 0xF3920001,
-		0x81C, 0xF2940001,
-		0x81C, 0xF1960001,
-		0x81C, 0xF0980001,
-		0x81C, 0xEF9A0001,
-		0x81C, 0xEE9C0001,
-		0x81C, 0xED9E0001,
-		0x81C, 0xECA00001,
-		0x81C, 0xEBA20001,
-		0x81C, 0xEAA40001,
-		0x81C, 0xE9A60001,
-		0x81C, 0xE8A80001,
-		0x81C, 0xE7AA0001,
-		0x81C, 0xE6AC0001,
-		0x81C, 0xE5AE0001,
-		0x81C, 0xE4B00001,
-		0x81C, 0xE3B20001,
-		0x81C, 0xA8B40001,
-		0x81C, 0xA7B60001,
-		0x81C, 0xA6B80001,
-		0x81C, 0xA5BA0001,
-		0x81C, 0xA4BC0001,
-		0x81C, 0xA3BE0001,
-		0x81C, 0xA2C00001,
-		0x81C, 0xA1C20001,
-		0x81C, 0x68C40001,
-		0x81C, 0x67C60001,
-		0x81C, 0x66C80001,
-		0x81C, 0x65CA0001,
-		0x81C, 0x64CC0001,
-		0x81C, 0x47CE0001,
-		0x81C, 0x46D00001,
-		0x81C, 0x45D20001,
-		0x81C, 0x44D40001,
-		0x81C, 0x43D60001,
-		0x81C, 0x42D80001,
-		0x81C, 0x08DA0001,
-		0x81C, 0x07DC0001,
-		0x81C, 0x06DE0001,
-		0x81C, 0x05E00001,
-		0x81C, 0x04E20001,
-		0x81C, 0x03E40001,
-		0x81C, 0x02E60001,
-		0x81C, 0x01E80001,
-		0x81C, 0x01EA0001,
-		0x81C, 0x01EC0001,
-		0x81C, 0x01EE0001,
-		0x81C, 0x01F00001,
-		0x81C, 0x01F20001,
-		0x81C, 0x01F40001,
-		0x81C, 0x01F60001,
-		0x81C, 0x01F80001,
-		0x81C, 0x01FA0001,
-		0x81C, 0x01FC0001,
-		0x81C, 0x01FE0001,
-	0xFF0F07D0, 0xCDEF,
+	0xB0000000, 0x00000000,
+	0x80000004, 0x00000000, 0x40000000, 0x00000000,
 		0x81C, 0xFC800001,
 		0x81C, 0xFB820001,
 		0x81C, 0xFA840001,
@@ -3165,7 +2407,7 @@ u32 RTL8812AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0x01FA0001,
 		0x81C, 0x01FC0001,
 		0x81C, 0x01FE0001,
-	0xCDCDCDCD, 0xCDCD,
+	0xA0000000, 0x00000000,
 		0x81C, 0xFF800001,
 		0x81C, 0xFF820001,
 		0x81C, 0xFF840001,
@@ -3230,14 +2472,16 @@ u32 RTL8812AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0x01FA0001,
 		0x81C, 0x01FC0001,
 		0x81C, 0x01FE0001,
-	0xFF0F0180, 0xDEAD,
+	0xB0000000, 0x00000000,
 		0xC50, 0x00000022,
 		0xC50, 0x00000020,
 		0xE50, 0x00000022,
 		0xE50, 0x00000020,
-
 };
 
+u32 RTL8812AE_AGC_TAB_1TARRAYLEN =
+	sizeof(RTL8812AE_AGC_TAB_ARRAY) / sizeof(u32);
+
 u32 RTL8821AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0xBF000001,
 		0x81C, 0xBF020001,
@@ -3430,9 +2674,11 @@ u32 RTL8821AE_AGC_TAB_ARRAY[] = {
 		0x81C, 0x017E0101,
 		0xC50, 0x00000022,
 		0xC50, 0x00000020,
-
 };
 
+u32 RTL8821AE_AGC_TAB_1TARRAYLEN =
+	sizeof(RTL8821AE_AGC_TAB_ARRAY) / sizeof(u32);
+
 /******************************************************************************
 *                           TXPWR_LMT.TXT
 ******************************************************************************/
@@ -3717,9 +2963,9 @@ u8 *RTL8812AE_TXPWR_LMT[] = {
 	"FCC", "5G", "20M", "OFDM", "1T", "100", "30",
 	"ETSI", "5G", "20M", "OFDM", "1T", "100", "32",
 	"MKK", "5G", "20M", "OFDM", "1T", "100", "32",
-	"FCC", "5G", "20M", "OFDM", "1T", "114", "30",
-	"ETSI", "5G", "20M", "OFDM", "1T", "114", "32",
-	"MKK", "5G", "20M", "OFDM", "1T", "114", "32",
+	"FCC", "5G", "20M", "OFDM", "1T", "104", "30",
+	"ETSI", "5G", "20M", "OFDM", "1T", "104", "32",
+	"MKK", "5G", "20M", "OFDM", "1T", "104", "32",
 	"FCC", "5G", "20M", "OFDM", "1T", "108", "32",
 	"ETSI", "5G", "20M", "OFDM", "1T", "108", "32",
 	"MKK", "5G", "20M", "OFDM", "1T", "108", "32",
@@ -3789,9 +3035,9 @@ u8 *RTL8812AE_TXPWR_LMT[] = {
 	"FCC", "5G", "20M", "HT", "1T", "100", "30",
 	"ETSI", "5G", "20M", "HT", "1T", "100", "32",
 	"MKK", "5G", "20M", "HT", "1T", "100", "32",
-	"FCC", "5G", "20M", "HT", "1T", "114", "30",
-	"ETSI", "5G", "20M", "HT", "1T", "114", "32",
-	"MKK", "5G", "20M", "HT", "1T", "114", "32",
+	"FCC", "5G", "20M", "HT", "1T", "104", "30",
+	"ETSI", "5G", "20M", "HT", "1T", "104", "32",
+	"MKK", "5G", "20M", "HT", "1T", "104", "32",
 	"FCC", "5G", "20M", "HT", "1T", "108", "32",
 	"ETSI", "5G", "20M", "HT", "1T", "108", "32",
 	"MKK", "5G", "20M", "HT", "1T", "108", "32",
@@ -3861,9 +3107,9 @@ u8 *RTL8812AE_TXPWR_LMT[] = {
 	"FCC", "5G", "20M", "HT", "2T", "100", "28",
 	"ETSI", "5G", "20M", "HT", "2T", "100", "30",
 	"MKK", "5G", "20M", "HT", "2T", "100", "30",
-	"FCC", "5G", "20M", "HT", "2T", "114", "28",
-	"ETSI", "5G", "20M", "HT", "2T", "114", "30",
-	"MKK", "5G", "20M", "HT", "2T", "114", "30",
+	"FCC", "5G", "20M", "HT", "2T", "104", "28",
+	"ETSI", "5G", "20M", "HT", "2T", "104", "30",
+	"MKK", "5G", "20M", "HT", "2T", "104", "30",
 	"FCC", "5G", "20M", "HT", "2T", "108", "30",
 	"ETSI", "5G", "20M", "HT", "2T", "108", "30",
 	"MKK", "5G", "20M", "HT", "2T", "108", "30",
@@ -4004,6 +3250,8 @@ u8 *RTL8812AE_TXPWR_LMT[] = {
 	"MKK", "5G", "80M", "VHT", "2T", "155", "63"
 };
 
+u32 RTL8812AE_TXPWR_LMT_ARRAY_LEN = sizeof(RTL8812AE_TXPWR_LMT) / sizeof(u8 *);
+
 u8 *RTL8821AE_TXPWR_LMT[] = {
 	"FCC", "2.4G", "20M", "CCK", "1T", "01", "32",
 	"ETSI", "2.4G", "20M", "CCK", "1T", "01", "32",
@@ -4284,9 +3532,9 @@ u8 *RTL8821AE_TXPWR_LMT[] = {
 	"FCC", "5G", "20M", "OFDM", "1T", "100", "32",
 	"ETSI", "5G", "20M", "OFDM", "1T", "100", "30",
 	"MKK", "5G", "20M", "OFDM", "1T", "100", "30",
-	"FCC", "5G", "20M", "OFDM", "1T", "114", "32",
-	"ETSI", "5G", "20M", "OFDM", "1T", "114", "30",
-	"MKK", "5G", "20M", "OFDM", "1T", "114", "30",
+	"FCC", "5G", "20M", "OFDM", "1T", "104", "32",
+	"ETSI", "5G", "20M", "OFDM", "1T", "104", "30",
+	"MKK", "5G", "20M", "OFDM", "1T", "104", "30",
 	"FCC", "5G", "20M", "OFDM", "1T", "108", "32",
 	"ETSI", "5G", "20M", "OFDM", "1T", "108", "30",
 	"MKK", "5G", "20M", "OFDM", "1T", "108", "30",
@@ -4356,9 +3604,9 @@ u8 *RTL8821AE_TXPWR_LMT[] = {
 	"FCC", "5G", "20M", "HT", "1T", "100", "32",
 	"ETSI", "5G", "20M", "HT", "1T", "100", "30",
 	"MKK", "5G", "20M", "HT", "1T", "100", "30",
-	"FCC", "5G", "20M", "HT", "1T", "114", "32",
-	"ETSI", "5G", "20M", "HT", "1T", "114", "30",
-	"MKK", "5G", "20M", "HT", "1T", "114", "30",
+	"FCC", "5G", "20M", "HT", "1T", "104", "32",
+	"ETSI", "5G", "20M", "HT", "1T", "104", "30",
+	"MKK", "5G", "20M", "HT", "1T", "104", "30",
 	"FCC", "5G", "20M", "HT", "1T", "108", "32",
 	"ETSI", "5G", "20M", "HT", "1T", "108", "30",
 	"MKK", "5G", "20M", "HT", "1T", "108", "30",
@@ -4428,9 +3676,9 @@ u8 *RTL8821AE_TXPWR_LMT[] = {
 	"FCC", "5G", "20M", "HT", "2T", "100", "28",
 	"ETSI", "5G", "20M", "HT", "2T", "100", "30",
 	"MKK", "5G", "20M", "HT", "2T", "100", "30",
-	"FCC", "5G", "20M", "HT", "2T", "114", "28",
-	"ETSI", "5G", "20M", "HT", "2T", "114", "30",
-	"MKK", "5G", "20M", "HT", "2T", "114", "30",
+	"FCC", "5G", "20M", "HT", "2T", "104", "28",
+	"ETSI", "5G", "20M", "HT", "2T", "104", "30",
+	"MKK", "5G", "20M", "HT", "2T", "104", "30",
 	"FCC", "5G", "20M", "HT", "2T", "108", "30",
 	"ETSI", "5G", "20M", "HT", "2T", "108", "30",
 	"MKK", "5G", "20M", "HT", "2T", "108", "30",
@@ -4570,3 +3818,5 @@ u8 *RTL8821AE_TXPWR_LMT[] = {
 	"ETSI", "5G", "80M", "VHT", "2T", "155", "30",
 	"MKK", "5G", "80M", "VHT", "2T", "155", "63"
 };
+
+u32 RTL8821AE_TXPWR_LMT_ARRAY_LEN = sizeof(RTL8821AE_TXPWR_LMT) / sizeof(u8 *);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h
index 24bcff6bc507..36c2388b60bc 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h
@@ -29,32 +29,30 @@
 #define __RTL8821AE_TABLE__H_
 
 #include <linux/types.h>
-#define  RTL8821AEPHY_REG_1TARRAYLEN	344
+extern u32 RTL8821AE_PHY_REG_1TARRAYLEN;
 extern u32 RTL8821AE_PHY_REG_ARRAY[];
-#define  RTL8812AEPHY_REG_1TARRAYLEN	490
+extern u32 RTL8812AE_PHY_REG_1TARRAYLEN;
 extern u32 RTL8812AE_PHY_REG_ARRAY[];
-#define RTL8821AEPHY_REG_ARRAY_PGLEN	90
+extern u32 RTL8821AE_PHY_REG_ARRAY_PGLEN;
 extern u32 RTL8821AE_PHY_REG_ARRAY_PG[];
-#define RTL8812AEPHY_REG_ARRAY_PGLEN	276
+extern u32 RTL8812AE_PHY_REG_ARRAY_PGLEN;
 extern u32 RTL8812AE_PHY_REG_ARRAY_PG[];
-/* #define	RTL8723BE_RADIOA_1TARRAYLEN	206 */
-/* extern u8 *RTL8821AE_TXPWR_LMT_ARRAY[]; */
-#define	RTL8812AE_RADIOA_1TARRAYLEN	1264
+extern u32 RTL8812AE_RADIOA_1TARRAYLEN;
 extern u32 RTL8812AE_RADIOA_ARRAY[];
-#define	RTL8812AE_RADIOB_1TARRAYLEN	1240
+extern u32 RTL8812AE_RADIOB_1TARRAYLEN;
 extern u32 RTL8812AE_RADIOB_ARRAY[];
-#define	RTL8821AE_RADIOA_1TARRAYLEN	1176
+extern u32 RTL8821AE_RADIOA_1TARRAYLEN;
 extern u32 RTL8821AE_RADIOA_ARRAY[];
-#define RTL8821AEMAC_1T_ARRAYLEN		194
+extern u32 RTL8821AE_MAC_1T_ARRAYLEN;
 extern u32 RTL8821AE_MAC_REG_ARRAY[];
-#define RTL8812AEMAC_1T_ARRAYLEN		214
+extern u32 RTL8812AE_MAC_1T_ARRAYLEN;
 extern u32 RTL8812AE_MAC_REG_ARRAY[];
-#define RTL8821AEAGCTAB_1TARRAYLEN		382
+extern u32 RTL8821AE_AGC_TAB_1TARRAYLEN;
 extern u32 RTL8821AE_AGC_TAB_ARRAY[];
-#define RTL8812AEAGCTAB_1TARRAYLEN		1312
+extern u32 RTL8812AE_AGC_TAB_1TARRAYLEN;
 extern u32 RTL8812AE_AGC_TAB_ARRAY[];
-#define RTL8812AE_TXPWR_LMT_ARRAY_LEN		3948
+extern u32 RTL8812AE_TXPWR_LMT_ARRAY_LEN;
 extern u8 *RTL8812AE_TXPWR_LMT[];
-#define RTL8821AE_TXPWR_LMT_ARRAY_LEN		3948
+extern u32 RTL8821AE_TXPWR_LMT_ARRAY_LEN;
 extern u8 *RTL8821AE_TXPWR_LMT[];
 #endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
index 108098152cf3..03665e82065f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
@@ -520,18 +520,18 @@ bool rtl8821ae_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 
 	if (status->rx_packet_bw == HT_CHANNEL_WIDTH_20_40)
-		rx_status->flag |= RX_FLAG_40MHZ;
+		rx_status->bw = RATE_INFO_BW_40;
 	else if (status->rx_packet_bw == HT_CHANNEL_WIDTH_80)
-		rx_status->vht_flag |= RX_VHT_FLAG_80MHZ;
+		rx_status->bw = RATE_INFO_BW_80;
 	if (status->is_ht)
-		rx_status->flag |= RX_FLAG_HT;
+		rx_status->encoding = RX_ENC_HT;
 	if (status->is_vht)
-		rx_status->flag |= RX_FLAG_VHT;
+		rx_status->encoding = RX_ENC_VHT;
 
 	if (status->is_short_gi)
-		rx_status->flag |= RX_FLAG_SHORT_GI;
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
-	rx_status->vht_nss = status->vht_nss;
+	rx_status->nss = status->vht_nss;
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	/* hw will set status->decrypted true, if it finds the
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 65ef42b37651..c0d2601bc55f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -1529,6 +1529,10 @@ struct rtl_hal {
 	u8 external_lna_2g;
 	u8 external_pa_5g;
 	u8 external_lna_5g;
+	u8 type_glna;
+	u8 type_gpa;
+	u8 type_alna;
+	u8 type_apa;
 	u8 rfe_type;
 
 	/*firmware */
@@ -2933,6 +2937,14 @@ static inline void rtl_write_byte(struct rtl_priv *rtlpriv, u32 addr, u8 val8)
 		rtlpriv->io.read8_sync(rtlpriv, addr);
 }
 
+static inline void rtl_write_byte_with_val32(struct ieee80211_hw *hw,
+					     u32 addr, u32 val8)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	rtl_write_byte(rtlpriv, addr, (u8)val8);
+}
+
 static inline void rtl_write_word(struct rtl_priv *rtlpriv, u32 addr, u16 val16)
 {
 	rtlpriv->io.write16_async(rtlpriv, addr, val16);
@@ -2966,6 +2978,12 @@ static inline void rtl_set_bbreg(struct ieee80211_hw *hw, u32 regaddr,
 	rtlpriv->cfg->ops->set_bbreg(hw, regaddr, bitmask, data);
 }
 
+static inline void rtl_set_bbreg_with_dwmask(struct ieee80211_hw *hw,
+				 u32 regaddr, u32 data)
+{
+	rtl_set_bbreg(hw, regaddr, 0xffffffff, data);
+}
+
 static inline u32 rtl_get_rfreg(struct ieee80211_hw *hw,
 				enum radio_path rfpath, u32 regaddr,
 				u32 bitmask)
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 785334f7a538..9935bd09db1f 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -479,7 +479,7 @@ struct rndis_wlan_private {
  */
 static int rndis_change_virtual_intf(struct wiphy *wiphy,
 					struct net_device *dev,
-					enum nl80211_iftype type, u32 *flags,
+					enum nl80211_iftype type,
 					struct vif_params *params);
 
 static int rndis_scan(struct wiphy *wiphy,
@@ -1857,7 +1857,7 @@ error:
  */
 static int rndis_change_virtual_intf(struct wiphy *wiphy,
 					struct net_device *dev,
-					enum nl80211_iftype type, u32 *flags,
+					enum nl80211_iftype type,
 					struct vif_params *params)
 {
 	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
@@ -2830,15 +2830,22 @@ static void rndis_wlan_do_link_up_work(struct usbnet *usbdev)
 	}
 
 	if (priv->infra_mode == NDIS_80211_INFRA_INFRA) {
-		if (!roamed)
+		if (!roamed) {
 			cfg80211_connect_result(usbdev->net, bssid, req_ie,
 						req_ie_len, resp_ie,
 						resp_ie_len, 0, GFP_KERNEL);
-		else
-			cfg80211_roamed(usbdev->net,
-					get_current_channel(usbdev, NULL),
-					bssid, req_ie, req_ie_len,
-					resp_ie, resp_ie_len, GFP_KERNEL);
+		} else {
+			struct cfg80211_roam_info roam_info = {
+				.channel = get_current_channel(usbdev, NULL),
+				.bssid = bssid,
+				.req_ie = req_ie,
+				.req_ie_len = req_ie_len,
+				.resp_ie = resp_ie,
+				.resp_ie_len = resp_ie_len,
+			};
+
+			cfg80211_roamed(usbdev->net, &roam_info, GFP_KERNEL);
+		}
 	} else if (priv->infra_mode == NDIS_80211_INFRA_ADHOC)
 		cfg80211_ibss_joined(usbdev->net, bssid,
 				     get_current_channel(usbdev, NULL),
@@ -3392,6 +3399,7 @@ static const struct net_device_ops rndis_wlan_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= rndis_wlan_set_multicast_list,
@@ -3427,6 +3435,10 @@ static int rndis_wlan_bind(struct usbnet *usbdev, struct usb_interface *intf)
 
 	/* because rndis_command() sleeps we need to use workqueue */
 	priv->workqueue = create_singlethread_workqueue("rndis_wlan");
+	if (!priv->workqueue) {
+		wiphy_free(wiphy);
+		return -ENOMEM;
+	}
 	INIT_WORK(&priv->work, rndis_wlan_worker);
 	INIT_DELAYED_WORK(&priv->dev_poller_work, rndis_device_poller);
 	INIT_DELAYED_WORK(&priv->scan_work, rndis_get_scan_results);
diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index e3216473aecb..021e5ac5f107 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -1261,6 +1261,8 @@ int rsi_mac80211_attach(struct rsi_common *common)
 
 	wiphy->reg_notifier = rsi_reg_notify;
 
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	status = ieee80211_register_hw(hw);
 	if (status)
 		return status;
diff --git a/drivers/net/wireless/st/cw1200/cw1200_sdio.c b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
index d3acc85932a5..709f56e5ad87 100644
--- a/drivers/net/wireless/st/cw1200/cw1200_sdio.c
+++ b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
 #include <linux/mmc/host.h>
diff --git a/drivers/net/wireless/st/cw1200/txrx.c b/drivers/net/wireless/st/cw1200/txrx.c
index 3d170287cd0b..cd63ffef025a 100644
--- a/drivers/net/wireless/st/cw1200/txrx.c
+++ b/drivers/net/wireless/st/cw1200/txrx.c
@@ -1085,7 +1085,7 @@ void cw1200_rx_cb(struct cw1200_common *priv,
 			hdr->band);
 
 	if (arg->rx_rate >= 14) {
-		hdr->flag |= RX_FLAG_HT;
+		hdr->encoding = RX_ENC_HT;
 		hdr->rate_idx = arg->rx_rate - 14;
 	} else if (arg->rx_rate >= 4) {
 		hdr->rate_idx = arg->rx_rate - 2;
diff --git a/drivers/net/wireless/ti/wl1251/rx.c b/drivers/net/wireless/ti/wl1251/rx.c
index a27d4c22b6e8..50fb2a4a5259 100644
--- a/drivers/net/wireless/ti/wl1251/rx.c
+++ b/drivers/net/wireless/ti/wl1251/rx.c
@@ -141,7 +141,7 @@ static void wl1251_rx_status(struct wl1251 *wl,
 	}
 
 	if (desc->mod_pre & SHORT_PREAMBLE_BIT)
-		status->flag |= RX_FLAG_SHORTPRE;
+		status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 }
 
 static void wl1251_rx_body(struct wl1251 *wl,
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c
index 58e148d7bc7b..de7e2a5fdffa 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.c
+++ b/drivers/net/wireless/ti/wlcore/debugfs.c
@@ -1249,7 +1249,7 @@ static ssize_t fw_logger_write(struct file *file,
 	}
 
 	if (wl->conf.fwlog.output == 0) {
-		wl1271_warning("iligal opperation - fw logger disabled by default, please change mode via wlconf");
+		wl1271_warning("invalid operation - fw logger disabled by default, please change mode via wlconf");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index a21fda910529..382ec15ec1af 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6128,6 +6128,7 @@ static int wl1271_init_ieee80211(struct wl1271 *wl)
 	wl->hw->wiphy->max_scan_ie_len = WL1271_CMD_TEMPL_MAX_SIZE -
 			sizeof(struct ieee80211_header);
 
+	wl->hw->wiphy->max_sched_scan_reqs = 1;
 	wl->hw->wiphy->max_sched_scan_ie_len = WL1271_CMD_TEMPL_MAX_SIZE -
 		sizeof(struct ieee80211_header);
 
@@ -6135,7 +6136,6 @@ static int wl1271_init_ieee80211(struct wl1271 *wl)
 
 	wl->hw->wiphy->flags |= WIPHY_FLAG_AP_UAPSD |
 				WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL |
-				WIPHY_FLAG_SUPPORTS_SCHED_SCAN |
 				WIPHY_FLAG_HAS_CHANNEL_SWITCH;
 
 	wl->hw->wiphy->features |= NL80211_FEATURE_AP_SCAN;
diff --git a/drivers/net/wireless/ti/wlcore/rx.c b/drivers/net/wireless/ti/wlcore/rx.c
index b9e14045195f..52a55f9acd80 100644
--- a/drivers/net/wireless/ti/wlcore/rx.c
+++ b/drivers/net/wireless/ti/wlcore/rx.c
@@ -72,7 +72,7 @@ static void wl1271_rx_status(struct wl1271 *wl,
 
 	/* 11n support */
 	if (desc->rate <= wl->hw_min_ht_rate)
-		status->flag |= RX_FLAG_HT;
+		status->encoding = RX_ENC_HT;
 
 	/*
 	* Read the signal level and antenna diversity indication.
diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c
index ddad58f614da..009ec07c4cec 100644
--- a/drivers/net/wireless/ti/wlcore/testmode.c
+++ b/drivers/net/wireless/ti/wlcore/testmode.c
@@ -366,7 +366,8 @@ int wl1271_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	u32 nla_cmd;
 	int err;
 
-	err = nla_parse(tb, WL1271_TM_ATTR_MAX, data, len, wl1271_tm_policy);
+	err = nla_parse(tb, WL1271_TM_ATTR_MAX, data, len, wl1271_tm_policy,
+			NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
index fd4e9ba176c9..5c0bcb1fe1a1 100644
--- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c
+++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
@@ -41,7 +41,7 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy,
 		return -EINVAL;
 
 	ret = nla_parse(tb, MAX_WLCORE_VENDOR_ATTR, data, data_len,
-			wlcore_vendor_attr_policy);
+			wlcore_vendor_attr_policy, NULL);
 	if (ret)
 		return ret;
 
@@ -116,7 +116,7 @@ wlcore_vendor_cmd_smart_config_set_group_key(struct wiphy *wiphy,
 		return -EINVAL;
 
 	ret = nla_parse(tb, MAX_WLCORE_VENDOR_ATTR, data, data_len,
-			wlcore_vendor_attr_policy);
+			wlcore_vendor_attr_policy, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
index 3e37a045f702..fe6517a621b0 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
@@ -1408,6 +1408,8 @@ struct ieee80211_hw *zd_mac_alloc_hw(struct usb_interface *intf)
 		BIT(NL80211_IFTYPE_ADHOC) |
 		BIT(NL80211_IFTYPE_AP);
 
+	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+
 	hw->max_signal = 100;
 	hw->queues = 1;
 	hw->extra_tx_headroom = sizeof(struct zd_ctrlset);
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index c5effd6c6be9..01ca1d57b3d9 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -1278,6 +1278,9 @@ static int eject_installer(struct usb_interface *intf)
 	u8 bulk_out_ep;
 	int r;
 
+	if (iface_desc->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
 	/* Find bulk out endpoint */
 	for (r = 1; r >= 0; r--) {
 		endpoint = &iface_desc->endpoint[r].desc;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 829b26cd4549..8397f6c92451 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -165,13 +165,17 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
-	unsigned int num_queues = vif->num_queues;
+	unsigned int num_queues;
 	u16 index;
 	struct xenvif_rx_cb *cb;
 
 	BUG_ON(skb->dev != dev);
 
-	/* Drop the packet if queues are not set up */
+	/* Drop the packet if queues are not set up.
+	 * This handler should be called inside an RCU read section
+	 * so we don't need to enter it here explicitly.
+	 */
+	num_queues = READ_ONCE(vif->num_queues);
 	if (num_queues < 1)
 		goto drop;
 
@@ -222,18 +226,18 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues;
 	u64 rx_bytes = 0;
 	u64 rx_packets = 0;
 	u64 tx_bytes = 0;
 	u64 tx_packets = 0;
 	unsigned int index;
 
-	spin_lock(&vif->lock);
-	if (vif->queues == NULL)
-		goto out;
+	rcu_read_lock();
+	num_queues = READ_ONCE(vif->num_queues);
 
 	/* Aggregate tx and rx stats from each queue */
-	for (index = 0; index < vif->num_queues; ++index) {
+	for (index = 0; index < num_queues; ++index) {
 		queue = &vif->queues[index];
 		rx_bytes += queue->stats.rx_bytes;
 		rx_packets += queue->stats.rx_packets;
@@ -241,8 +245,7 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 		tx_packets += queue->stats.tx_packets;
 	}
 
-out:
-	spin_unlock(&vif->lock);
+	rcu_read_unlock();
 
 	vif->dev->stats.rx_bytes = rx_bytes;
 	vif->dev->stats.rx_packets = rx_packets;
@@ -378,10 +381,13 @@ static void xenvif_get_ethtool_stats(struct net_device *dev,
 				     struct ethtool_stats *stats, u64 * data)
 {
 	struct xenvif *vif = netdev_priv(dev);
-	unsigned int num_queues = vif->num_queues;
+	unsigned int num_queues;
 	int i;
 	unsigned int queue_index;
 
+	rcu_read_lock();
+	num_queues = READ_ONCE(vif->num_queues);
+
 	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
 		unsigned long accum = 0;
 		for (queue_index = 0; queue_index < num_queues; ++queue_index) {
@@ -390,6 +396,8 @@ static void xenvif_get_ethtool_stats(struct net_device *dev,
 		}
 		data[i] = accum;
 	}
+
+	rcu_read_unlock();
 }
 
 static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index f9bcf4a665bc..602d408fa25e 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -214,7 +214,7 @@ static void xenvif_fatal_tx_err(struct xenvif *vif)
 	netdev_err(vif->dev, "fatal error; disabling device\n");
 	vif->disabled = true;
 	/* Disable the vif from queue 0's kthread */
-	if (vif->queues)
+	if (vif->num_queues)
 		xenvif_kick_thread(&vif->queues[0]);
 }
 
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index d2d7cd9145b1..a56d3eab35dd 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -495,26 +495,26 @@ static void backend_disconnect(struct backend_info *be)
 	struct xenvif *vif = be->vif;
 
 	if (vif) {
+		unsigned int num_queues = vif->num_queues;
 		unsigned int queue_index;
-		struct xenvif_queue *queues;
 
 		xen_unregister_watchers(vif);
 #ifdef CONFIG_DEBUG_FS
 		xenvif_debugfs_delif(vif);
 #endif /* CONFIG_DEBUG_FS */
 		xenvif_disconnect_data(vif);
-		for (queue_index = 0;
-		     queue_index < vif->num_queues;
-		     ++queue_index)
-			xenvif_deinit_queue(&vif->queues[queue_index]);
 
-		spin_lock(&vif->lock);
-		queues = vif->queues;
+		/* At this point some of the handlers may still be active
+		 * so we need to have additional synchronization here.
+		 */
 		vif->num_queues = 0;
-		vif->queues = NULL;
-		spin_unlock(&vif->lock);
+		synchronize_net();
 
-		vfree(queues);
+		for (queue_index = 0; queue_index < num_queues; ++queue_index)
+			xenvif_deinit_queue(&vif->queues[queue_index]);
+
+		vfree(vif->queues);
+		vif->queues = NULL;
 
 		xenvif_disconnect_ctrl(vif);
 	}
diff --git a/drivers/nfc/Kconfig b/drivers/nfc/Kconfig
index 9d2369269abf..c4208487fadc 100644
--- a/drivers/nfc/Kconfig
+++ b/drivers/nfc/Kconfig
@@ -5,17 +5,6 @@
 menu "Near Field Communication (NFC) devices"
 	depends on NFC
 
-config NFC_WILINK
-	tristate "Texas Instruments NFC WiLink driver"
-	depends on TI_ST && NFC_NCI
-	help
-	  This enables the NFC driver for Texas Instrument's BT/FM/GPS/NFC
-	  combo devices. This makes use of shared transport line discipline
-	  core driver to communicate with the NFC core of the combo chip.
-
-	  Say Y here to compile support for Texas Instrument's NFC WiLink driver
-	  into the kernel or say M to compile it as module.
-
 config NFC_TRF7970A
 	tristate "Texas Instruments TRF7970a NFC driver"
 	depends on SPI && NFC_DIGITAL
diff --git a/drivers/nfc/Makefile b/drivers/nfc/Makefile
index bab8ef06ae35..640b7274371c 100644
--- a/drivers/nfc/Makefile
+++ b/drivers/nfc/Makefile
@@ -6,7 +6,6 @@ obj-$(CONFIG_NFC_FDP)		+= fdp/
 obj-$(CONFIG_NFC_PN544)		+= pn544/
 obj-$(CONFIG_NFC_MICROREAD)	+= microread/
 obj-$(CONFIG_NFC_PN533)		+= pn533/
-obj-$(CONFIG_NFC_WILINK)	+= nfcwilink.o
 obj-$(CONFIG_NFC_MEI_PHY)	+= mei_phy.o
 obj-$(CONFIG_NFC_SIM)		+= nfcsim.o
 obj-$(CONFIG_NFC_PORT100)	+= port100.o
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 5e797d5c38ed..712936f5d2d6 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -210,14 +210,14 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id)
 	struct sk_buff *skb;
 	int r;
 
-	client = phy->i2c_dev;
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	if (!phy || irq != phy->i2c_dev->irq) {
 		WARN_ON_ONCE(1);
 		return IRQ_NONE;
 	}
 
+	client = phy->i2c_dev;
+	dev_dbg(&client->dev, "%s\n", __func__);
+
 	r = fdp_nci_i2c_read(phy, &skb);
 
 	if (r == -EREMOTEIO)
diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c
index f8dcdf4b24f6..c38bdd6a5a82 100644
--- a/drivers/nfc/nfcmrvl/fw_dnld.c
+++ b/drivers/nfc/nfcmrvl/fw_dnld.c
@@ -17,7 +17,7 @@
  */
 
 #include <linux/module.h>
-#include <linux/unaligned/access_ok.h>
+#include <asm/unaligned.h>
 #include <linux/firmware.h>
 #include <linux/nfc.h>
 #include <net/nfc/nci.h>
@@ -281,12 +281,11 @@ static int process_state_fw_dnld(struct nfcmrvl_private *priv,
 			return -EINVAL;
 		}
 		skb_pull(skb, 1);
-		memcpy(&len, skb->data, 2);
+		len = get_unaligned_le16(skb->data);
 		skb_pull(skb, 2);
+		comp_len = get_unaligned_le16(skb->data);
 		memcpy(&comp_len, skb->data, 2);
 		skb_pull(skb, 2);
-		len = get_unaligned_le16(&len);
-		comp_len = get_unaligned_le16(&comp_len);
 		if (((~len) & 0xFFFF) != comp_len) {
 			nfc_err(priv->dev, "bad len complement: %x %x %x",
 				len, comp_len, (~len & 0xFFFF));
diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c
index a7faa0bcc01e..8e0ddb434770 100644
--- a/drivers/nfc/nfcmrvl/spi.c
+++ b/drivers/nfc/nfcmrvl/spi.c
@@ -26,7 +26,6 @@
 #include <net/nfc/nci.h>
 #include <net/nfc/nci_core.h>
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
 #include "nfcmrvl.h"
 
 #define SPI_WAIT_HANDSHAKE	1
@@ -96,10 +95,9 @@ static int nfcmrvl_spi_nci_send(struct nfcmrvl_private *priv,
 	/* Send the SPI packet */
 	err = nci_spi_send(drv_data->nci_spi, &drv_data->handshake_completion,
 			   skb);
-	if (err != 0) {
+	if (err)
 		nfc_err(priv->dev, "spi_send failed %d", err);
-		kfree_skb(skb);
-	}
+
 	return err;
 }
 
diff --git a/drivers/nfc/nfcwilink.c b/drivers/nfc/nfcwilink.c
deleted file mode 100644
index 3fbd18b8e473..000000000000
--- a/drivers/nfc/nfcwilink.c
+++ /dev/null
@@ -1,578 +0,0 @@
-/*
- *  Texas Instrument's NFC Driver For Shared Transport.
- *
- *  NFC Driver acts as interface between NCI core and
- *  TI Shared Transport Layer.
- *
- *  Copyright (C) 2011 Texas Instruments, Inc.
- *
- *  Written by Ilan Elias <ilane@ti.com>
- *
- *  Acknowledgements:
- *  This file is based on btwilink.c, which was written
- *  by Raja Mani and Pavan Savoy.
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- */
-#include <linux/platform_device.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/firmware.h>
-#include <linux/nfc.h>
-#include <net/nfc/nci.h>
-#include <net/nfc/nci_core.h>
-#include <linux/ti_wilink_st.h>
-
-#define NFCWILINK_CHNL			12
-#define NFCWILINK_OPCODE		7
-#define NFCWILINK_MAX_FRAME_SIZE	300
-#define NFCWILINK_HDR_LEN		4
-#define NFCWILINK_OFFSET_LEN_IN_HDR	1
-#define NFCWILINK_LEN_SIZE		2
-#define NFCWILINK_REGISTER_TIMEOUT	8000	/* 8 sec */
-#define NFCWILINK_CMD_TIMEOUT		5000	/* 5 sec */
-
-#define BTS_FILE_NAME_MAX_SIZE		40
-#define BTS_FILE_HDR_MAGIC		0x42535442
-#define BTS_FILE_CMD_MAX_LEN		0xff
-#define BTS_FILE_ACTION_TYPE_SEND_CMD	1
-
-#define NCI_VS_NFCC_INFO_CMD_GID	0x2f
-#define NCI_VS_NFCC_INFO_CMD_OID	0x12
-#define NCI_VS_NFCC_INFO_RSP_GID	0x4f
-#define NCI_VS_NFCC_INFO_RSP_OID	0x12
-
-struct nfcwilink_hdr {
-	__u8 chnl;
-	__u8 opcode;
-	__le16 len;
-} __packed;
-
-struct nci_vs_nfcc_info_cmd {
-	__u8 gid;
-	__u8 oid;
-	__u8 plen;
-} __packed;
-
-struct nci_vs_nfcc_info_rsp {
-	__u8 gid;
-	__u8 oid;
-	__u8 plen;
-	__u8 status;
-	__u8 hw_id;
-	__u8 sw_ver_x;
-	__u8 sw_ver_z;
-	__u8 patch_id;
-} __packed;
-
-struct bts_file_hdr {
-	__le32 magic;
-	__le32 ver;
-	__u8 rfu[24];
-	__u8 actions[0];
-} __packed;
-
-struct bts_file_action {
-	__le16 type;
-	__le16 len;
-	__u8 data[0];
-} __packed;
-
-struct nfcwilink {
-	struct platform_device		*pdev;
-	struct nci_dev			*ndev;
-	unsigned long			flags;
-
-	int				st_register_cb_status;
-	long				(*st_write) (struct sk_buff *);
-
-	struct completion		completed;
-
-	struct nci_vs_nfcc_info_rsp	nfcc_info;
-};
-
-/* NFCWILINK driver flags */
-enum {
-	NFCWILINK_RUNNING,
-	NFCWILINK_FW_DOWNLOAD,
-};
-
-static int nfcwilink_send(struct nci_dev *ndev, struct sk_buff *skb);
-
-static inline struct sk_buff *nfcwilink_skb_alloc(unsigned int len, gfp_t how)
-{
-	struct sk_buff *skb;
-
-	skb = alloc_skb(len + NFCWILINK_HDR_LEN, how);
-	if (skb)
-		skb_reserve(skb, NFCWILINK_HDR_LEN);
-
-	return skb;
-}
-
-static void nfcwilink_fw_download_receive(struct nfcwilink *drv,
-						struct sk_buff *skb)
-{
-	struct nci_vs_nfcc_info_rsp *rsp = (void *)skb->data;
-
-	/* Detect NCI_VS_NFCC_INFO_RSP and store the result */
-	if ((skb->len > 3) && (rsp->gid == NCI_VS_NFCC_INFO_RSP_GID) &&
-		(rsp->oid == NCI_VS_NFCC_INFO_RSP_OID)) {
-		memcpy(&drv->nfcc_info, rsp,
-			sizeof(struct nci_vs_nfcc_info_rsp));
-	}
-
-	kfree_skb(skb);
-
-	complete(&drv->completed);
-}
-
-static int nfcwilink_get_bts_file_name(struct nfcwilink *drv, char *file_name)
-{
-	struct nci_vs_nfcc_info_cmd *cmd;
-	struct sk_buff *skb;
-	unsigned long comp_ret;
-	int rc;
-
-	skb = nfcwilink_skb_alloc(sizeof(struct nci_vs_nfcc_info_cmd),
-					GFP_KERNEL);
-	if (!skb) {
-		nfc_err(&drv->pdev->dev,
-			"no memory for nci_vs_nfcc_info_cmd\n");
-		return -ENOMEM;
-	}
-
-	cmd = (struct nci_vs_nfcc_info_cmd *)
-			skb_put(skb, sizeof(struct nci_vs_nfcc_info_cmd));
-	cmd->gid = NCI_VS_NFCC_INFO_CMD_GID;
-	cmd->oid = NCI_VS_NFCC_INFO_CMD_OID;
-	cmd->plen = 0;
-
-	drv->nfcc_info.plen = 0;
-
-	rc = nfcwilink_send(drv->ndev, skb);
-	if (rc)
-		return rc;
-
-	comp_ret = wait_for_completion_timeout(&drv->completed,
-				msecs_to_jiffies(NFCWILINK_CMD_TIMEOUT));
-	dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld\n",
-		comp_ret);
-	if (comp_ret == 0) {
-		nfc_err(&drv->pdev->dev,
-			"timeout on wait_for_completion_timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	dev_dbg(&drv->pdev->dev, "nci_vs_nfcc_info_rsp: plen %d, status %d\n",
-		drv->nfcc_info.plen, drv->nfcc_info.status);
-
-	if ((drv->nfcc_info.plen != 5) || (drv->nfcc_info.status != 0)) {
-		nfc_err(&drv->pdev->dev, "invalid nci_vs_nfcc_info_rsp\n");
-		return -EINVAL;
-	}
-
-	snprintf(file_name, BTS_FILE_NAME_MAX_SIZE,
-			"TINfcInit_%d.%d.%d.%d.bts",
-			drv->nfcc_info.hw_id,
-			drv->nfcc_info.sw_ver_x,
-			drv->nfcc_info.sw_ver_z,
-			drv->nfcc_info.patch_id);
-
-	nfc_info(&drv->pdev->dev, "nfcwilink FW file name: %s\n", file_name);
-
-	return 0;
-}
-
-static int nfcwilink_send_bts_cmd(struct nfcwilink *drv, __u8 *data, int len)
-{
-	struct nfcwilink_hdr *hdr = (struct nfcwilink_hdr *)data;
-	struct sk_buff *skb;
-	unsigned long comp_ret;
-	int rc;
-
-	/* verify valid cmd for the NFC channel */
-	if ((len <= sizeof(struct nfcwilink_hdr)) ||
-		(len > BTS_FILE_CMD_MAX_LEN) ||
-		(hdr->chnl != NFCWILINK_CHNL) ||
-		(hdr->opcode != NFCWILINK_OPCODE)) {
-		nfc_err(&drv->pdev->dev,
-			"ignoring invalid bts cmd, len %d, chnl %d, opcode %d\n",
-			len, hdr->chnl, hdr->opcode);
-		return 0;
-	}
-
-	/* remove the ST header */
-	len -= sizeof(struct nfcwilink_hdr);
-	data += sizeof(struct nfcwilink_hdr);
-
-	skb = nfcwilink_skb_alloc(len, GFP_KERNEL);
-	if (!skb) {
-		nfc_err(&drv->pdev->dev, "no memory for bts cmd\n");
-		return -ENOMEM;
-	}
-
-	memcpy(skb_put(skb, len), data, len);
-
-	rc = nfcwilink_send(drv->ndev, skb);
-	if (rc)
-		return rc;
-
-	comp_ret = wait_for_completion_timeout(&drv->completed,
-				msecs_to_jiffies(NFCWILINK_CMD_TIMEOUT));
-	dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld\n",
-		comp_ret);
-	if (comp_ret == 0) {
-		nfc_err(&drv->pdev->dev,
-			"timeout on wait_for_completion_timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int nfcwilink_download_fw(struct nfcwilink *drv)
-{
-	unsigned char file_name[BTS_FILE_NAME_MAX_SIZE];
-	const struct firmware *fw;
-	__u16 action_type, action_len;
-	__u8 *ptr;
-	int len, rc;
-
-	set_bit(NFCWILINK_FW_DOWNLOAD, &drv->flags);
-
-	rc = nfcwilink_get_bts_file_name(drv, file_name);
-	if (rc)
-		goto exit;
-
-	rc = request_firmware(&fw, file_name, &drv->pdev->dev);
-	if (rc) {
-		nfc_err(&drv->pdev->dev, "request_firmware failed %d\n", rc);
-
-		/* if the file is not found, don't exit with failure */
-		if (rc == -ENOENT)
-			rc = 0;
-
-		goto exit;
-	}
-
-	len = fw->size;
-	ptr = (__u8 *)fw->data;
-
-	if ((len == 0) || (ptr == NULL)) {
-		dev_dbg(&drv->pdev->dev,
-			"request_firmware returned size %d\n", len);
-		goto release_fw;
-	}
-
-	if (__le32_to_cpu(((struct bts_file_hdr *)ptr)->magic) !=
-			BTS_FILE_HDR_MAGIC) {
-		nfc_err(&drv->pdev->dev, "wrong bts magic number\n");
-		rc = -EINVAL;
-		goto release_fw;
-	}
-
-	/* remove the BTS header */
-	len -= sizeof(struct bts_file_hdr);
-	ptr += sizeof(struct bts_file_hdr);
-
-	while (len > 0) {
-		action_type =
-			__le16_to_cpu(((struct bts_file_action *)ptr)->type);
-		action_len =
-			__le16_to_cpu(((struct bts_file_action *)ptr)->len);
-
-		dev_dbg(&drv->pdev->dev, "bts_file_action type %d, len %d\n",
-			action_type, action_len);
-
-		switch (action_type) {
-		case BTS_FILE_ACTION_TYPE_SEND_CMD:
-			rc = nfcwilink_send_bts_cmd(drv,
-					((struct bts_file_action *)ptr)->data,
-					action_len);
-			if (rc)
-				goto release_fw;
-			break;
-		}
-
-		/* advance to the next action */
-		len -= (sizeof(struct bts_file_action) + action_len);
-		ptr += (sizeof(struct bts_file_action) + action_len);
-	}
-
-release_fw:
-	release_firmware(fw);
-
-exit:
-	clear_bit(NFCWILINK_FW_DOWNLOAD, &drv->flags);
-	return rc;
-}
-
-/* Called by ST when registration is complete */
-static void nfcwilink_register_complete(void *priv_data, int data)
-{
-	struct nfcwilink *drv = priv_data;
-
-	/* store ST registration status */
-	drv->st_register_cb_status = data;
-
-	/* complete the wait in nfc_st_open() */
-	complete(&drv->completed);
-}
-
-/* Called by ST when receive data is available */
-static long nfcwilink_receive(void *priv_data, struct sk_buff *skb)
-{
-	struct nfcwilink *drv = priv_data;
-	int rc;
-
-	if (!skb)
-		return -EFAULT;
-
-	if (!drv) {
-		kfree_skb(skb);
-		return -EFAULT;
-	}
-
-	dev_dbg(&drv->pdev->dev, "receive entry, len %d\n", skb->len);
-
-	/* strip the ST header
-	(apart for the chnl byte, which is not received in the hdr) */
-	skb_pull(skb, (NFCWILINK_HDR_LEN-1));
-
-	if (test_bit(NFCWILINK_FW_DOWNLOAD, &drv->flags)) {
-		nfcwilink_fw_download_receive(drv, skb);
-		return 0;
-	}
-
-	/* Forward skb to NCI core layer */
-	rc = nci_recv_frame(drv->ndev, skb);
-	if (rc < 0) {
-		nfc_err(&drv->pdev->dev, "nci_recv_frame failed %d\n", rc);
-		return rc;
-	}
-
-	return 0;
-}
-
-/* protocol structure registered with ST */
-static struct st_proto_s nfcwilink_proto = {
-	.chnl_id = NFCWILINK_CHNL,
-	.max_frame_size = NFCWILINK_MAX_FRAME_SIZE,
-	.hdr_len = (NFCWILINK_HDR_LEN-1),	/* not including chnl byte */
-	.offset_len_in_hdr = NFCWILINK_OFFSET_LEN_IN_HDR,
-	.len_size = NFCWILINK_LEN_SIZE,
-	.reserve = 0,
-	.recv = nfcwilink_receive,
-	.reg_complete_cb = nfcwilink_register_complete,
-	.write = NULL,
-};
-
-static int nfcwilink_open(struct nci_dev *ndev)
-{
-	struct nfcwilink *drv = nci_get_drvdata(ndev);
-	unsigned long comp_ret;
-	int rc;
-
-	if (test_and_set_bit(NFCWILINK_RUNNING, &drv->flags)) {
-		rc = -EBUSY;
-		goto exit;
-	}
-
-	nfcwilink_proto.priv_data = drv;
-
-	init_completion(&drv->completed);
-	drv->st_register_cb_status = -EINPROGRESS;
-
-	rc = st_register(&nfcwilink_proto);
-	if (rc < 0) {
-		if (rc == -EINPROGRESS) {
-			comp_ret = wait_for_completion_timeout(
-			&drv->completed,
-			msecs_to_jiffies(NFCWILINK_REGISTER_TIMEOUT));
-
-			dev_dbg(&drv->pdev->dev,
-				"wait_for_completion_timeout returned %ld\n",
-				comp_ret);
-
-			if (comp_ret == 0) {
-				/* timeout */
-				rc = -ETIMEDOUT;
-				goto clear_exit;
-			} else if (drv->st_register_cb_status != 0) {
-				rc = drv->st_register_cb_status;
-				nfc_err(&drv->pdev->dev,
-					"st_register_cb failed %d\n", rc);
-				goto clear_exit;
-			}
-		} else {
-			nfc_err(&drv->pdev->dev, "st_register failed %d\n", rc);
-			goto clear_exit;
-		}
-	}
-
-	/* st_register MUST fill the write callback */
-	BUG_ON(nfcwilink_proto.write == NULL);
-	drv->st_write = nfcwilink_proto.write;
-
-	if (nfcwilink_download_fw(drv)) {
-		nfc_err(&drv->pdev->dev, "nfcwilink_download_fw failed %d\n",
-			rc);
-		/* open should succeed, even if the FW download failed */
-	}
-
-	goto exit;
-
-clear_exit:
-	clear_bit(NFCWILINK_RUNNING, &drv->flags);
-
-exit:
-	return rc;
-}
-
-static int nfcwilink_close(struct nci_dev *ndev)
-{
-	struct nfcwilink *drv = nci_get_drvdata(ndev);
-	int rc;
-
-	if (!test_and_clear_bit(NFCWILINK_RUNNING, &drv->flags))
-		return 0;
-
-	rc = st_unregister(&nfcwilink_proto);
-	if (rc)
-		nfc_err(&drv->pdev->dev, "st_unregister failed %d\n", rc);
-
-	drv->st_write = NULL;
-
-	return rc;
-}
-
-static int nfcwilink_send(struct nci_dev *ndev, struct sk_buff *skb)
-{
-	struct nfcwilink *drv = nci_get_drvdata(ndev);
-	struct nfcwilink_hdr hdr = {NFCWILINK_CHNL, NFCWILINK_OPCODE, 0x0000};
-	long len;
-
-	dev_dbg(&drv->pdev->dev, "send entry, len %d\n", skb->len);
-
-	if (!test_bit(NFCWILINK_RUNNING, &drv->flags)) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
-	/* add the ST hdr to the start of the buffer */
-	hdr.len = cpu_to_le16(skb->len);
-	memcpy(skb_push(skb, NFCWILINK_HDR_LEN), &hdr, NFCWILINK_HDR_LEN);
-
-	/* Insert skb to shared transport layer's transmit queue.
-	 * Freeing skb memory is taken care in shared transport layer,
-	 * so don't free skb memory here.
-	 */
-	len = drv->st_write(skb);
-	if (len < 0) {
-		kfree_skb(skb);
-		nfc_err(&drv->pdev->dev, "st_write failed %ld\n", len);
-		return -EFAULT;
-	}
-
-	return 0;
-}
-
-static struct nci_ops nfcwilink_ops = {
-	.open = nfcwilink_open,
-	.close = nfcwilink_close,
-	.send = nfcwilink_send,
-};
-
-static int nfcwilink_probe(struct platform_device *pdev)
-{
-	struct nfcwilink *drv;
-	int rc;
-	__u32 protocols;
-
-	drv = devm_kzalloc(&pdev->dev, sizeof(struct nfcwilink), GFP_KERNEL);
-	if (!drv) {
-		rc = -ENOMEM;
-		goto exit;
-	}
-
-	drv->pdev = pdev;
-
-	protocols = NFC_PROTO_JEWEL_MASK
-		| NFC_PROTO_MIFARE_MASK | NFC_PROTO_FELICA_MASK
-		| NFC_PROTO_ISO14443_MASK
-		| NFC_PROTO_ISO14443_B_MASK
-		| NFC_PROTO_NFC_DEP_MASK;
-
-	drv->ndev = nci_allocate_device(&nfcwilink_ops,
-					protocols,
-					NFCWILINK_HDR_LEN,
-					0);
-	if (!drv->ndev) {
-		nfc_err(&pdev->dev, "nci_allocate_device failed\n");
-		rc = -ENOMEM;
-		goto exit;
-	}
-
-	nci_set_parent_dev(drv->ndev, &pdev->dev);
-	nci_set_drvdata(drv->ndev, drv);
-
-	rc = nci_register_device(drv->ndev);
-	if (rc < 0) {
-		nfc_err(&pdev->dev, "nci_register_device failed %d\n", rc);
-		goto free_dev_exit;
-	}
-
-	dev_set_drvdata(&pdev->dev, drv);
-
-	goto exit;
-
-free_dev_exit:
-	nci_free_device(drv->ndev);
-
-exit:
-	return rc;
-}
-
-static int nfcwilink_remove(struct platform_device *pdev)
-{
-	struct nfcwilink *drv = dev_get_drvdata(&pdev->dev);
-	struct nci_dev *ndev;
-
-	if (!drv)
-		return -EFAULT;
-
-	ndev = drv->ndev;
-
-	nci_unregister_device(ndev);
-	nci_free_device(ndev);
-
-	return 0;
-}
-
-static struct platform_driver nfcwilink_driver = {
-	.probe = nfcwilink_probe,
-	.remove = nfcwilink_remove,
-	.driver = {
-		.name = "nfcwilink",
-	},
-};
-
-module_platform_driver(nfcwilink_driver);
-
-/* ------ Module Info ------ */
-
-MODULE_AUTHOR("Ilan Elias <ilane@ti.com>");
-MODULE_DESCRIPTION("NFC Driver for TI Shared Transport");
-MODULE_LICENSE("GPL");
diff --git a/drivers/nfc/nxp-nci/firmware.c b/drivers/nfc/nxp-nci/firmware.c
index 5291797324ba..553011f58339 100644
--- a/drivers/nfc/nxp-nci/firmware.c
+++ b/drivers/nfc/nxp-nci/firmware.c
@@ -24,7 +24,7 @@
 #include <linux/completion.h>
 #include <linux/firmware.h>
 #include <linux/nfc.h>
-#include <linux/unaligned/access_ok.h>
+#include <asm/unaligned.h>
 
 #include "nxp-nci.h"
 
diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c
index 36099e557730..ff22d761183c 100644
--- a/drivers/nfc/nxp-nci/i2c.c
+++ b/drivers/nfc/nxp-nci/i2c.c
@@ -29,14 +29,13 @@
 #include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
-#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/nfc.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of_gpio.h>
 #include <linux/of_irq.h>
 #include <linux/platform_data/nxp-nci.h>
-#include <linux/unaligned/access_ok.h>
+#include <asm/unaligned.h>
 
 #include <net/nfc/nfc.h>
 
@@ -86,7 +85,7 @@ static int nxp_nci_i2c_write(void *phy_id, struct sk_buff *skb)
 	r = i2c_master_send(client, skb->data, skb->len);
 	if (r < 0) {
 		/* Retry, chip was in standby */
-		usleep_range(110000, 120000);
+		msleep(110);
 		r = i2c_master_send(client, skb->data, skb->len);
 	}
 
@@ -127,7 +126,7 @@ static int nxp_nci_i2c_fw_read(struct nxp_nci_i2c_phy *phy,
 		goto fw_read_exit;
 	}
 
-	frame_len = (get_unaligned_be16(&header) & NXP_NCI_FW_FRAME_LEN_MASK) +
+	frame_len = (be16_to_cpu(header) & NXP_NCI_FW_FRAME_LEN_MASK) +
 		    NXP_NCI_FW_CRC_LEN;
 
 	*skb = alloc_skb(NXP_NCI_FW_HDR_LEN + frame_len, GFP_KERNEL);
diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c
index 1dc89248e58e..8f60ce039b0d 100644
--- a/drivers/nfc/pn533/i2c.c
+++ b/drivers/nfc/pn533/i2c.c
@@ -51,7 +51,7 @@ static int pn533_i2c_send_ack(struct pn533 *dev, gfp_t flags)
 {
 	struct pn533_i2c_phy *phy = dev->phy;
 	struct i2c_client *client = phy->i2c_dev;
-	u8 ack[6] = {0x00, 0x00, 0xff, 0x00, 0xff, 0x00};
+	static const u8 ack[6] = {0x00, 0x00, 0xff, 0x00, 0xff, 0x00};
 	/* spec 6.2.1.3:  Preamble, SoPC (2), ACK Code (2), Postamble */
 	int rc;
 
@@ -206,14 +206,6 @@ static int pn533_i2c_probe(struct i2c_client *client,
 	phy->i2c_dev = client;
 	i2c_set_clientdata(client, phy);
 
-	r = request_threaded_irq(client->irq, NULL, pn533_i2c_irq_thread_fn,
-				 IRQF_TRIGGER_FALLING |
-				 IRQF_SHARED | IRQF_ONESHOT,
-				 PN533_I2C_DRIVER_NAME, phy);
-
-	if (r < 0)
-		nfc_err(&client->dev, "Unable to register IRQ handler\n");
-
 	priv = pn533_register_device(PN533_DEVICE_PN532,
 				     PN533_NO_TYPE_B_PROTOCOLS,
 				     PN533_PROTO_REQ_ACK_RESP,
@@ -223,16 +215,32 @@ static int pn533_i2c_probe(struct i2c_client *client,
 
 	if (IS_ERR(priv)) {
 		r = PTR_ERR(priv);
-		goto err_register;
+		return r;
 	}
 
 	phy->priv = priv;
 
+	r = request_threaded_irq(client->irq, NULL, pn533_i2c_irq_thread_fn,
+				IRQF_TRIGGER_FALLING |
+				IRQF_SHARED | IRQF_ONESHOT,
+				PN533_I2C_DRIVER_NAME, phy);
+	if (r < 0) {
+		nfc_err(&client->dev, "Unable to register IRQ handler\n");
+		goto irq_rqst_err;
+	}
+
+	r = pn533_finalize_setup(priv);
+	if (r)
+		goto fn_setup_err;
+
 	return 0;
 
-err_register:
+fn_setup_err:
 	free_irq(client->irq, phy);
 
+irq_rqst_err:
+	pn533_unregister_device(phy->priv);
+
 	return r;
 }
 
@@ -242,10 +250,10 @@ static int pn533_i2c_remove(struct i2c_client *client)
 
 	dev_dbg(&client->dev, "%s\n", __func__);
 
-	pn533_unregister_device(phy->priv);
-
 	free_irq(client->irq, phy);
 
+	pn533_unregister_device(phy->priv);
+
 	return 0;
 }
 
diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c
index a966c6a85ea8..65bbaa5fcdda 100644
--- a/drivers/nfc/pn533/pn533.c
+++ b/drivers/nfc/pn533/pn533.c
@@ -383,14 +383,18 @@ static void pn533_build_cmd_frame(struct pn533 *dev, u8 cmd_code,
 static int pn533_send_async_complete(struct pn533 *dev)
 {
 	struct pn533_cmd *cmd = dev->cmd;
-	int status = cmd->status;
+	struct sk_buff *resp;
+	int status, rc = 0;
 
-	struct sk_buff *req = cmd->req;
-	struct sk_buff *resp = cmd->resp;
+	if (!cmd) {
+		dev_dbg(dev->dev, "%s: cmd not set\n", __func__);
+		goto done;
+	}
 
-	int rc;
+	dev_kfree_skb(cmd->req);
 
-	dev_kfree_skb(req);
+	status = cmd->status;
+	resp = cmd->resp;
 
 	if (status < 0) {
 		rc = cmd->complete_cb(dev, cmd->complete_cb_context,
@@ -399,8 +403,14 @@ static int pn533_send_async_complete(struct pn533 *dev)
 		goto done;
 	}
 
-	skb_pull(resp, dev->ops->rx_header_len);
-	skb_trim(resp, resp->len - dev->ops->rx_tail_len);
+	/* when no response is set we got interrupted */
+	if (!resp)
+		resp = ERR_PTR(-EINTR);
+
+	if (!IS_ERR(resp)) {
+		skb_pull(resp, dev->ops->rx_header_len);
+		skb_trim(resp, resp->len - dev->ops->rx_tail_len);
+	}
 
 	rc = cmd->complete_cb(dev, cmd->complete_cb_context, resp);
 
@@ -434,12 +444,14 @@ static int __pn533_send_async(struct pn533 *dev, u8 cmd_code,
 	mutex_lock(&dev->cmd_lock);
 
 	if (!dev->cmd_pending) {
+		dev->cmd = cmd;
 		rc = dev->phy_ops->send_frame(dev, req);
-		if (rc)
+		if (rc) {
+			dev->cmd = NULL;
 			goto error;
+		}
 
 		dev->cmd_pending = 1;
-		dev->cmd = cmd;
 		goto unlock;
 	}
 
@@ -511,11 +523,12 @@ static int pn533_send_cmd_direct_async(struct pn533 *dev, u8 cmd_code,
 
 	pn533_build_cmd_frame(dev, cmd_code, req);
 
+	dev->cmd = cmd;
 	rc = dev->phy_ops->send_frame(dev, req);
-	if (rc < 0)
+	if (rc < 0) {
+		dev->cmd = NULL;
 		kfree(cmd);
-	else
-		dev->cmd = cmd;
+	}
 
 	return rc;
 }
@@ -550,14 +563,15 @@ static void pn533_wq_cmd(struct work_struct *work)
 
 	mutex_unlock(&dev->cmd_lock);
 
+	dev->cmd = cmd;
 	rc = dev->phy_ops->send_frame(dev, cmd->req);
 	if (rc < 0) {
+		dev->cmd = NULL;
 		dev_kfree_skb(cmd->req);
 		kfree(cmd);
 		return;
 	}
 
-	dev->cmd = cmd;
 }
 
 struct pn533_sync_cmd_response {
@@ -2556,6 +2570,31 @@ static int pn533_setup(struct pn533 *dev)
 	return 0;
 }
 
+int pn533_finalize_setup(struct pn533 *dev)
+{
+
+	struct pn533_fw_version fw_ver;
+	int rc;
+
+	memset(&fw_ver, 0, sizeof(fw_ver));
+
+	rc = pn533_get_firmware_version(dev, &fw_ver);
+	if (rc) {
+		nfc_err(dev->dev, "Unable to get FW version\n");
+		return rc;
+	}
+
+	nfc_info(dev->dev, "NXP PN5%02X firmware ver %d.%d now attached\n",
+		fw_ver.ic, fw_ver.ver, fw_ver.rev);
+
+	rc = pn533_setup(dev);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pn533_finalize_setup);
+
 struct pn533 *pn533_register_device(u32 device_type,
 				u32 protocols,
 				enum pn533_protocol_type protocol_type,
@@ -2565,7 +2604,6 @@ struct pn533 *pn533_register_device(u32 device_type,
 				struct device *dev,
 				struct device *parent)
 {
-	struct pn533_fw_version fw_ver;
 	struct pn533 *priv;
 	int rc = -ENOMEM;
 
@@ -2608,15 +2646,6 @@ struct pn533 *pn533_register_device(u32 device_type,
 
 	INIT_LIST_HEAD(&priv->cmd_queue);
 
-	memset(&fw_ver, 0, sizeof(fw_ver));
-	rc = pn533_get_firmware_version(priv, &fw_ver);
-	if (rc < 0)
-		goto destroy_wq;
-
-	nfc_info(dev, "NXP PN5%02X firmware ver %d.%d now attached\n",
-		 fw_ver.ic, fw_ver.ver, fw_ver.rev);
-
-
 	priv->nfc_dev = nfc_allocate_device(&pn533_nfc_ops, protocols,
 					   priv->ops->tx_header_len +
 					   PN533_CMD_DATAEXCH_HEAD_LEN,
@@ -2633,15 +2662,8 @@ struct pn533 *pn533_register_device(u32 device_type,
 	if (rc)
 		goto free_nfc_dev;
 
-	rc = pn533_setup(priv);
-	if (rc)
-		goto unregister_nfc_dev;
-
 	return priv;
 
-unregister_nfc_dev:
-	nfc_unregister_device(priv->nfc_dev);
-
 free_nfc_dev:
 	nfc_free_device(priv->nfc_dev);
 
diff --git a/drivers/nfc/pn533/pn533.h b/drivers/nfc/pn533/pn533.h
index 553c7d171fd1..88d569666c51 100644
--- a/drivers/nfc/pn533/pn533.h
+++ b/drivers/nfc/pn533/pn533.h
@@ -231,6 +231,7 @@ struct pn533 *pn533_register_device(u32 device_type,
 				struct device *dev,
 				struct device *parent);
 
+int pn533_finalize_setup(struct pn533 *dev);
 void pn533_unregister_device(struct pn533 *priv);
 void pn533_recv_frame(struct pn533 *dev, struct sk_buff *skb, int status);
 
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index 33ed78be2750..8ed203ea21ea 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -148,11 +148,11 @@ static int pn533_submit_urb_for_ack(struct pn533_usb_phy *phy, gfp_t flags)
 static int pn533_usb_send_ack(struct pn533 *dev, gfp_t flags)
 {
 	struct pn533_usb_phy *phy = dev->phy;
-	u8 ack[6] = {0x00, 0x00, 0xff, 0x00, 0xff, 0x00};
+	static const u8 ack[6] = {0x00, 0x00, 0xff, 0x00, 0xff, 0x00};
 	/* spec 7.1.1.3:  Preamble, SoPC (2), ACK Code (2), Postamble */
 	int rc;
 
-	phy->out_urb->transfer_buffer = ack;
+	phy->out_urb->transfer_buffer = (u8 *)ack;
 	phy->out_urb->transfer_buffer_length = sizeof(ack);
 	rc = usb_submit_urb(phy->out_urb, flags);
 
@@ -543,6 +543,10 @@ static int pn533_usb_probe(struct usb_interface *interface,
 
 	phy->priv = priv;
 
+	rc = pn533_finalize_setup(priv);
+	if (rc)
+		goto error;
+
 	usb_set_intfdata(interface, phy);
 
 	return 0;
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index f837c39a8017..71ac0836c9f4 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -21,17 +21,13 @@
 #include <linux/crc-ccitt.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
-#include <linux/of_irq.h>
 #include <linux/acpi.h>
-#include <linux/miscdevice.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/nfc.h>
 #include <linux/firmware.h>
 #include <linux/gpio/consumer.h>
-#include <linux/platform_data/pn544.h>
+
 #include <asm/unaligned.h>
 
 #include <net/nfc/hci.h>
@@ -165,8 +161,9 @@ struct pn544_i2c_phy {
 	struct i2c_client *i2c_dev;
 	struct nfc_hci_dev *hdev;
 
-	unsigned int gpio_en;
-	unsigned int gpio_fw;
+	struct gpio_desc *gpiod_en;
+	struct gpio_desc *gpiod_fw;
+
 	unsigned int en_polarity;
 
 	u8 hw_variant;
@@ -208,19 +205,18 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
 	nfc_info(&phy->i2c_dev->dev, "Detecting nfc_en polarity\n");
 
 	/* Disable fw download */
-	gpio_set_value_cansleep(phy->gpio_fw, 0);
+	gpiod_set_value_cansleep(phy->gpiod_fw, 0);
 
 	for (polarity = 0; polarity < 2; polarity++) {
 		phy->en_polarity = polarity;
 		retry = 3;
 		while (retry--) {
 			/* power off */
-			gpio_set_value_cansleep(phy->gpio_en,
-						!phy->en_polarity);
+			gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
 			usleep_range(10000, 15000);
 
 			/* power on */
-			gpio_set_value_cansleep(phy->gpio_en, phy->en_polarity);
+			gpiod_set_value_cansleep(phy->gpiod_en, phy->en_polarity);
 			usleep_range(10000, 15000);
 
 			/* send reset */
@@ -239,14 +235,13 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
 		"Could not detect nfc_en polarity, fallback to active high\n");
 
 out:
-	gpio_set_value_cansleep(phy->gpio_en, !phy->en_polarity);
+	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
 }
 
 static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)
 {
-	gpio_set_value_cansleep(phy->gpio_fw,
-				run_mode == PN544_FW_MODE ? 1 : 0);
-	gpio_set_value_cansleep(phy->gpio_en, phy->en_polarity);
+	gpiod_set_value_cansleep(phy->gpiod_fw, run_mode == PN544_FW_MODE ? 1 : 0);
+	gpiod_set_value_cansleep(phy->gpiod_en, phy->en_polarity);
 	usleep_range(10000, 15000);
 
 	phy->run_mode = run_mode;
@@ -269,14 +264,14 @@ static void pn544_hci_i2c_disable(void *phy_id)
 {
 	struct pn544_i2c_phy *phy = phy_id;
 
-	gpio_set_value_cansleep(phy->gpio_fw, 0);
-	gpio_set_value_cansleep(phy->gpio_en, !phy->en_polarity);
+	gpiod_set_value_cansleep(phy->gpiod_fw, 0);
+	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
 	usleep_range(10000, 15000);
 
-	gpio_set_value_cansleep(phy->gpio_en, phy->en_polarity);
+	gpiod_set_value_cansleep(phy->gpiod_en, phy->en_polarity);
 	usleep_range(10000, 15000);
 
-	gpio_set_value_cansleep(phy->gpio_en, !phy->en_polarity);
+	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
 	usleep_range(10000, 15000);
 
 	phy->powered = 0;
@@ -874,106 +869,20 @@ exit_state_wait_secure_write_answer:
 	}
 }
 
-static int pn544_hci_i2c_acpi_request_resources(struct i2c_client *client)
-{
-	struct pn544_i2c_phy *phy = i2c_get_clientdata(client);
-	struct gpio_desc *gpiod_en, *gpiod_fw;
-	struct device *dev = &client->dev;
-
-	/* Get EN GPIO from ACPI */
-	gpiod_en = devm_gpiod_get_index(dev, PN544_GPIO_NAME_EN, 1,
-					GPIOD_OUT_LOW);
-	if (IS_ERR(gpiod_en)) {
-		nfc_err(dev, "Unable to get EN GPIO\n");
-		return -ENODEV;
-	}
-
-	phy->gpio_en = desc_to_gpio(gpiod_en);
-
-	/* Get FW GPIO from ACPI */
-	gpiod_fw = devm_gpiod_get_index(dev, PN544_GPIO_NAME_FW, 2,
-					GPIOD_OUT_LOW);
-	if (IS_ERR(gpiod_fw)) {
-		nfc_err(dev, "Unable to get FW GPIO\n");
-		return -ENODEV;
-	}
-
-	phy->gpio_fw = desc_to_gpio(gpiod_fw);
-
-	return 0;
-}
-
-static int pn544_hci_i2c_of_request_resources(struct i2c_client *client)
-{
-	struct pn544_i2c_phy *phy = i2c_get_clientdata(client);
-	struct device_node *pp;
-	int ret;
-
-	pp = client->dev.of_node;
-	if (!pp) {
-		ret = -ENODEV;
-		goto err_dt;
-	}
-
-	/* Obtention of EN GPIO from device tree */
-	ret = of_get_named_gpio(pp, "enable-gpios", 0);
-	if (ret < 0) {
-		if (ret != -EPROBE_DEFER)
-			nfc_err(&client->dev,
-				"Failed to get EN gpio, error: %d\n", ret);
-		goto err_dt;
-	}
-	phy->gpio_en = ret;
-
-	/* Configuration of EN GPIO */
-	ret = gpio_request(phy->gpio_en, PN544_GPIO_NAME_EN);
-	if (ret) {
-		nfc_err(&client->dev, "Fail EN pin\n");
-		goto err_dt;
-	}
-	ret = gpio_direction_output(phy->gpio_en, 0);
-	if (ret) {
-		nfc_err(&client->dev, "Fail EN pin direction\n");
-		goto err_gpio_en;
-	}
-
-	/* Obtention of FW GPIO from device tree */
-	ret = of_get_named_gpio(pp, "firmware-gpios", 0);
-	if (ret < 0) {
-		if (ret != -EPROBE_DEFER)
-			nfc_err(&client->dev,
-				"Failed to get FW gpio, error: %d\n", ret);
-		goto err_gpio_en;
-	}
-	phy->gpio_fw = ret;
-
-	/* Configuration of FW GPIO */
-	ret = gpio_request(phy->gpio_fw, PN544_GPIO_NAME_FW);
-	if (ret) {
-		nfc_err(&client->dev, "Fail FW pin\n");
-		goto err_gpio_en;
-	}
-	ret = gpio_direction_output(phy->gpio_fw, 0);
-	if (ret) {
-		nfc_err(&client->dev, "Fail FW pin direction\n");
-		goto err_gpio_fw;
-	}
-
-	return 0;
+static const struct acpi_gpio_params enable_gpios = { 1, 0, false };
+static const struct acpi_gpio_params firmware_gpios = { 2, 0, false };
 
-err_gpio_fw:
-	gpio_free(phy->gpio_fw);
-err_gpio_en:
-	gpio_free(phy->gpio_en);
-err_dt:
-	return ret;
-}
+static const struct acpi_gpio_mapping acpi_pn544_gpios[] = {
+	{ "enable-gpios", &enable_gpios, 1 },
+	{ "firmware-gpios", &firmware_gpios, 1 },
+	{ },
+};
 
 static int pn544_hci_i2c_probe(struct i2c_client *client,
 			       const struct i2c_device_id *id)
 {
+	struct device *dev = &client->dev;
 	struct pn544_i2c_phy *phy;
-	struct pn544_nfc_platform_data *pdata;
 	int r = 0;
 
 	dev_dbg(&client->dev, "%s\n", __func__);
@@ -995,53 +904,33 @@ static int pn544_hci_i2c_probe(struct i2c_client *client,
 	phy->i2c_dev = client;
 	i2c_set_clientdata(client, phy);
 
-	pdata = client->dev.platform_data;
-
-	/* No platform data, using device tree. */
-	if (!pdata && client->dev.of_node) {
-		r = pn544_hci_i2c_of_request_resources(client);
-		if (r) {
-			nfc_err(&client->dev, "No DT data\n");
-			return r;
-		}
-	/* Using platform data. */
-	} else if (pdata) {
-
-		if (pdata->request_resources == NULL) {
-			nfc_err(&client->dev, "request_resources() missing\n");
-			return -EINVAL;
-		}
+	r = acpi_dev_add_driver_gpios(ACPI_COMPANION(dev), acpi_pn544_gpios);
+	if (r)
+		dev_dbg(dev, "Unable to add GPIO mapping table\n");
 
-		r = pdata->request_resources(client);
-		if (r) {
-			nfc_err(&client->dev,
-				"Cannot get platform resources\n");
-			return r;
-		}
+	/* Get EN GPIO */
+	phy->gpiod_en = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(phy->gpiod_en)) {
+		nfc_err(dev, "Unable to get EN GPIO\n");
+		return PTR_ERR(phy->gpiod_en);
+	}
 
-		phy->gpio_en = pdata->get_gpio(NFC_GPIO_ENABLE);
-		phy->gpio_fw = pdata->get_gpio(NFC_GPIO_FW_RESET);
-	/* Using ACPI */
-	} else if (ACPI_HANDLE(&client->dev)) {
-		r = pn544_hci_i2c_acpi_request_resources(client);
-		if (r) {
-			nfc_err(&client->dev,
-				"Cannot get ACPI data\n");
-			return r;
-		}
-	} else {
-		nfc_err(&client->dev, "No platform data\n");
-		return -EINVAL;
+	/* Get FW GPIO */
+	phy->gpiod_fw = devm_gpiod_get(dev, "firmware", GPIOD_OUT_LOW);
+	if (IS_ERR(phy->gpiod_fw)) {
+		nfc_err(dev, "Unable to get FW GPIO\n");
+		return PTR_ERR(phy->gpiod_fw);
 	}
 
 	pn544_hci_i2c_platform_init(phy);
 
-	r = request_threaded_irq(client->irq, NULL, pn544_hci_i2c_irq_thread_fn,
-				 IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-				 PN544_HCI_I2C_DRIVER_NAME, phy);
+	r = devm_request_threaded_irq(&client->dev, client->irq, NULL,
+				      pn544_hci_i2c_irq_thread_fn,
+				      IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				      PN544_HCI_I2C_DRIVER_NAME, phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to register IRQ handler\n");
-		goto err_rti;
+		return r;
 	}
 
 	r = pn544_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
@@ -1049,28 +938,14 @@ static int pn544_hci_i2c_probe(struct i2c_client *client,
 			    PN544_HCI_I2C_LLC_MAX_PAYLOAD,
 			    pn544_hci_i2c_fw_download, &phy->hdev);
 	if (r < 0)
-		goto err_hci;
+		return r;
 
 	return 0;
-
-err_hci:
-	free_irq(client->irq, phy);
-
-err_rti:
-	if (!pdata) {
-		gpio_free(phy->gpio_en);
-		gpio_free(phy->gpio_fw);
-	} else if (pdata->free_resources) {
-		pdata->free_resources();
-	}
-
-	return r;
 }
 
 static int pn544_hci_i2c_remove(struct i2c_client *client)
 {
 	struct pn544_i2c_phy *phy = i2c_get_clientdata(client);
-	struct pn544_nfc_platform_data *pdata = client->dev.platform_data;
 
 	dev_dbg(&client->dev, "%s\n", __func__);
 
@@ -1083,17 +958,7 @@ static int pn544_hci_i2c_remove(struct i2c_client *client)
 	if (phy->powered)
 		pn544_hci_i2c_disable(phy);
 
-	free_irq(client->irq, phy);
-
-	/* No platform data, GPIOs have been requested by this driver */
-	if (!pdata) {
-		gpio_free(phy->gpio_en);
-		gpio_free(phy->gpio_fw);
-	/* Using platform data */
-	} else if (pdata->free_resources) {
-		pdata->free_resources();
-	}
-
+	acpi_dev_remove_driver_gpios(ACPI_COMPANION(&client->dev));
 	return 0;
 }
 
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index 2b2330b235e6..19be93e177fe 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -21,8 +21,9 @@
 
 #define VERSION "0.1"
 
-#define SONY_VENDOR_ID    0x054c
-#define RCS380_PRODUCT_ID 0x06c1
+#define SONY_VENDOR_ID		0x054c
+#define RCS380S_PRODUCT_ID	0x06c1
+#define RCS380P_PRODUCT_ID	0x06c3
 
 #define PORT100_PROTOCOLS (NFC_PROTO_JEWEL_MASK    | \
 			   NFC_PROTO_MIFARE_MASK   | \
@@ -725,23 +726,33 @@ static int port100_submit_urb_for_ack(struct port100 *dev, gfp_t flags)
 
 static int port100_send_ack(struct port100 *dev)
 {
-	int rc;
+	int rc = 0;
 
 	mutex_lock(&dev->out_urb_lock);
 
-	init_completion(&dev->cmd_cancel_done);
+	/*
+	 * If prior cancel is in-flight (dev->cmd_cancel == true), we
+	 * can skip to send cancel. Then this will wait the prior
+	 * cancel, or merged into the next cancel rarely if next
+	 * cancel was started before waiting done. In any case, this
+	 * will be waked up soon or later.
+	 */
+	if (!dev->cmd_cancel) {
+		reinit_completion(&dev->cmd_cancel_done);
 
-	usb_kill_urb(dev->out_urb);
+		usb_kill_urb(dev->out_urb);
 
-	dev->out_urb->transfer_buffer = ack_frame;
-	dev->out_urb->transfer_buffer_length = sizeof(ack_frame);
-	rc = usb_submit_urb(dev->out_urb, GFP_KERNEL);
+		dev->out_urb->transfer_buffer = ack_frame;
+		dev->out_urb->transfer_buffer_length = sizeof(ack_frame);
+		rc = usb_submit_urb(dev->out_urb, GFP_KERNEL);
 
-	/* Set the cmd_cancel flag only if the URB has been successfully
-	 * submitted. It will be reset by the out URB completion callback
-	 * port100_send_complete().
-	 */
-	dev->cmd_cancel = !rc;
+		/*
+		 * Set the cmd_cancel flag only if the URB has been
+		 * successfully submitted. It will be reset by the out
+		 * URB completion callback port100_send_complete().
+		 */
+		dev->cmd_cancel = !rc;
+	}
 
 	mutex_unlock(&dev->out_urb_lock);
 
@@ -928,8 +939,8 @@ static void port100_send_complete(struct urb *urb)
 	struct port100 *dev = urb->context;
 
 	if (dev->cmd_cancel) {
+		complete_all(&dev->cmd_cancel_done);
 		dev->cmd_cancel = false;
-		complete(&dev->cmd_cancel_done);
 	}
 
 	switch (urb->status) {
@@ -1477,7 +1488,8 @@ static struct nfc_digital_ops port100_digital_ops = {
 };
 
 static const struct usb_device_id port100_table[] = {
-	{ USB_DEVICE(SONY_VENDOR_ID, RCS380_PRODUCT_ID), },
+	{ USB_DEVICE(SONY_VENDOR_ID, RCS380S_PRODUCT_ID), },
+	{ USB_DEVICE(SONY_VENDOR_ID, RCS380P_PRODUCT_ID), },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, port100_table);
@@ -1538,11 +1550,13 @@ static int port100_probe(struct usb_interface *interface,
 	usb_fill_bulk_urb(dev->out_urb, dev->udev,
 			  usb_sndbulkpipe(dev->udev, out_endpoint),
 			  NULL, 0, port100_send_complete, dev);
+	dev->out_urb->transfer_flags = URB_ZERO_PACKET;
 
 	dev->skb_headroom = PORT100_FRAME_HEADER_LEN +
 			    PORT100_COMM_RF_HEAD_MAX_LEN;
 	dev->skb_tailroom = PORT100_FRAME_TAIL_LEN;
 
+	init_completion(&dev->cmd_cancel_done);
 	INIT_WORK(&dev->cmd_complete_work, port100_wq_cmd_complete);
 
 	/* The first thing to do with the Port-100 is to set the command type
diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c
index dacb9166081b..50be3b788f1c 100644
--- a/drivers/nfc/st21nfca/core.c
+++ b/drivers/nfc/st21nfca/core.c
@@ -959,10 +959,8 @@ int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
 	unsigned long quirks = 0;
 
 	info = kzalloc(sizeof(struct st21nfca_hci_info), GFP_KERNEL);
-	if (!info) {
-		r = -ENOMEM;
-		goto err_alloc_hdev;
-	}
+	if (!info)
+		return -ENOMEM;
 
 	info->phy_ops = phy_ops;
 	info->phy_id = phy_id;
@@ -978,8 +976,10 @@ int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
 	 * persistent info to discriminate 2 identical chips
 	 */
 	dev_num = find_first_zero_bit(dev_mask, ST21NFCA_NUM_DEVICES);
-	if (dev_num >= ST21NFCA_NUM_DEVICES)
-		return -ENODEV;
+	if (dev_num >= ST21NFCA_NUM_DEVICES) {
+		r = -ENODEV;
+		goto err_alloc_hdev;
+	}
 
 	set_bit(dev_num, dev_mask);
 
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index 5a82f553906c..02a920ca07c8 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -20,17 +20,15 @@
 #include <linux/crc-ccitt.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of_irq.h>
 #include <linux/of_gpio.h>
 #include <linux/acpi.h>
-#include <linux/miscdevice.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/nfc.h>
 #include <linux/firmware.h>
-#include <linux/platform_data/st21nfca.h>
+
 #include <asm/unaligned.h>
 
 #include <net/nfc/hci.h>
@@ -60,6 +58,7 @@
 #define IS_START_OF_FRAME(buf) (buf[0] == ST21NFCA_SOF_EOF && \
 				buf[1] == 0)
 
+#define ST21NFCA_HCI_DRIVER_NAME "st21nfca_hci"
 #define ST21NFCA_HCI_I2C_DRIVER_NAME "st21nfca_hci_i2c"
 
 #define ST21NFCA_GPIO_NAME_EN "enable"
@@ -68,9 +67,7 @@ struct st21nfca_i2c_phy {
 	struct i2c_client *i2c_dev;
 	struct nfc_hci_dev *hdev;
 
-	unsigned int gpio_ena;
-	unsigned int irq_polarity;
-
+	struct gpio_desc *gpiod_ena;
 	struct st21nfca_se_status se_status;
 
 	struct sk_buff *pending_skb;
@@ -151,7 +148,7 @@ static int st21nfca_hci_i2c_enable(void *phy_id)
 {
 	struct st21nfca_i2c_phy *phy = phy_id;
 
-	gpio_set_value(phy->gpio_ena, 1);
+	gpiod_set_value(phy->gpiod_ena, 1);
 	phy->powered = 1;
 	phy->run_mode = ST21NFCA_HCI_MODE;
 
@@ -164,7 +161,7 @@ static void st21nfca_hci_i2c_disable(void *phy_id)
 {
 	struct st21nfca_i2c_phy *phy = phy_id;
 
-	gpio_set_value(phy->gpio_ena, 0);
+	gpiod_set_value(phy->gpiod_ena, 0);
 
 	phy->powered = 0;
 }
@@ -507,33 +504,14 @@ static struct nfc_phy_ops i2c_phy_ops = {
 static int st21nfca_hci_i2c_acpi_request_resources(struct i2c_client *client)
 {
 	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
-	struct gpio_desc *gpiod_ena;
 	struct device *dev = &client->dev;
-	u8 tmp;
 
 	/* Get EN GPIO from ACPI */
-	gpiod_ena = devm_gpiod_get_index(dev, ST21NFCA_GPIO_NAME_EN, 1,
-					 GPIOD_OUT_LOW);
-	if (!IS_ERR(gpiod_ena)) {
+	phy->gpiod_ena = devm_gpiod_get_index(dev, ST21NFCA_GPIO_NAME_EN, 1,
+					      GPIOD_OUT_LOW);
+	if (IS_ERR(phy->gpiod_ena)) {
 		nfc_err(dev, "Unable to get ENABLE GPIO\n");
-		return -ENODEV;
-	}
-
-	phy->gpio_ena = desc_to_gpio(gpiod_ena);
-
-	phy->irq_polarity = irq_get_trigger_type(client->irq);
-
-	phy->se_status.is_ese_present = false;
-	phy->se_status.is_uicc_present = false;
-
-	if (device_property_present(dev, "ese-present")) {
-		device_property_read_u8(dev, "ese-present", &tmp);
-		phy->se_status.is_ese_present = tmp;
-	}
-
-	if (device_property_present(dev, "uicc-present")) {
-		device_property_read_u8(dev, "uicc-present", &tmp);
-		phy->se_status.is_uicc_present = tmp;
+		return PTR_ERR(phy->gpiod_ena);
 	}
 
 	return 0;
@@ -542,70 +520,16 @@ static int st21nfca_hci_i2c_acpi_request_resources(struct i2c_client *client)
 static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client)
 {
 	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
-	struct device_node *pp;
-	int gpio;
-	int r;
-
-	pp = client->dev.of_node;
-	if (!pp)
-		return -ENODEV;
+	struct device *dev = &client->dev;
 
 	/* Get GPIO from device tree */
-	gpio = of_get_named_gpio(pp, "enable-gpios", 0);
-	if (gpio < 0) {
-		nfc_err(&client->dev, "Failed to retrieve enable-gpios from device tree\n");
-		return gpio;
-	}
-
-	/* GPIO request and configuration */
-	r = devm_gpio_request_one(&client->dev, gpio, GPIOF_OUT_INIT_HIGH,
-				  ST21NFCA_GPIO_NAME_EN);
-	if (r) {
-		nfc_err(&client->dev, "Failed to request enable pin\n");
-		return r;
+	phy->gpiod_ena = devm_gpiod_get_index(dev, ST21NFCA_GPIO_NAME_EN, 0,
+					      GPIOD_OUT_HIGH);
+	if (IS_ERR(phy->gpiod_ena)) {
+		nfc_err(dev, "Failed to request enable pin\n");
+		return PTR_ERR(phy->gpiod_ena);
 	}
 
-	phy->gpio_ena = gpio;
-
-	phy->irq_polarity = irq_get_trigger_type(client->irq);
-
-	phy->se_status.is_ese_present =
-				of_property_read_bool(pp, "ese-present");
-	phy->se_status.is_uicc_present =
-				of_property_read_bool(pp, "uicc-present");
-
-	return 0;
-}
-
-static int st21nfca_hci_i2c_request_resources(struct i2c_client *client)
-{
-	struct st21nfca_nfc_platform_data *pdata;
-	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
-	int r;
-
-	pdata = client->dev.platform_data;
-	if (pdata == NULL) {
-		nfc_err(&client->dev, "No platform data\n");
-		return -EINVAL;
-	}
-
-	/* store for later use */
-	phy->gpio_ena = pdata->gpio_ena;
-	phy->irq_polarity = pdata->irq_polarity;
-
-	if (phy->gpio_ena > 0) {
-		r = devm_gpio_request_one(&client->dev, phy->gpio_ena,
-					  GPIOF_OUT_INIT_HIGH,
-					  ST21NFCA_GPIO_NAME_EN);
-		if (r) {
-			pr_err("%s : ena gpio_request failed\n", __FILE__);
-			return r;
-		}
-	}
-
-	phy->se_status.is_ese_present = pdata->is_ese_present;
-	phy->se_status.is_uicc_present = pdata->is_uicc_present;
-
 	return 0;
 }
 
@@ -613,7 +537,6 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
 	struct st21nfca_i2c_phy *phy;
-	struct st21nfca_nfc_platform_data *pdata;
 	int r;
 
 	dev_dbg(&client->dev, "%s\n", __func__);
@@ -639,19 +562,12 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	mutex_init(&phy->phy_lock);
 	i2c_set_clientdata(client, phy);
 
-	pdata = client->dev.platform_data;
-	if (!pdata && client->dev.of_node) {
+	if (client->dev.of_node) {
 		r = st21nfca_hci_i2c_of_request_resources(client);
 		if (r) {
 			nfc_err(&client->dev, "No platform data\n");
 			return r;
 		}
-	} else if (pdata) {
-		r = st21nfca_hci_i2c_request_resources(client);
-		if (r) {
-			nfc_err(&client->dev, "Cannot get platform resources\n");
-			return r;
-		}
 	} else if (ACPI_HANDLE(&client->dev)) {
 		r = st21nfca_hci_i2c_acpi_request_resources(client);
 		if (r) {
@@ -663,6 +579,11 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
+	phy->se_status.is_ese_present =
+			device_property_read_bool(&client->dev, "ese-present");
+	phy->se_status.is_uicc_present =
+			device_property_read_bool(&client->dev, "uicc-present");
+
 	r = st21nfca_hci_platform_init(phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to reboot st21nfca\n");
@@ -671,7 +592,7 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 
 	r = devm_request_threaded_irq(&client->dev, client->irq, NULL,
 				st21nfca_hci_irq_thread_fn,
-				phy->irq_polarity | IRQF_ONESHOT,
+				IRQF_ONESHOT,
 				ST21NFCA_HCI_DRIVER_NAME, phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to register IRQ handler\n");
diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c
index 26c9dbbccb0c..2d1c8ca6e679 100644
--- a/drivers/nfc/trf7970a.c
+++ b/drivers/nfc/trf7970a.c
@@ -124,6 +124,9 @@
 		 NFC_PROTO_ISO15693_MASK | NFC_PROTO_NFC_DEP_MASK)
 
 #define TRF7970A_AUTOSUSPEND_DELAY		30000 /* 30 seconds */
+#define TRF7970A_13MHZ_CLOCK_FREQUENCY		13560000
+#define TRF7970A_27MHZ_CLOCK_FREQUENCY		27120000
+
 
 #define TRF7970A_RX_SKB_ALLOC_SIZE		256
 
@@ -441,6 +444,7 @@ struct trf7970a {
 	u8				iso_ctrl_tech;
 	u8				modulator_sys_clk_ctrl;
 	u8				special_fcn_reg1;
+	u8				io_ctrl;
 	unsigned int			guard_time;
 	int				technology;
 	int				framing;
@@ -1048,6 +1052,11 @@ static int trf7970a_init(struct trf7970a *trf)
 	if (ret)
 		goto err_out;
 
+	ret = trf7970a_write(trf, TRF7970A_REG_IO_CTRL,
+			trf->io_ctrl | TRF7970A_REG_IO_CTRL_VRS(0x1));
+	if (ret)
+		goto err_out;
+
 	ret = trf7970a_write(trf, TRF7970A_NFC_TARGET_LEVEL, 0);
 	if (ret)
 		goto err_out;
@@ -1056,12 +1065,11 @@ static int trf7970a_init(struct trf7970a *trf)
 
 	trf->chip_status_ctrl &= ~TRF7970A_CHIP_STATUS_RF_ON;
 
-	ret = trf7970a_write(trf, TRF7970A_MODULATOR_SYS_CLK_CTRL, 0);
+	ret = trf7970a_write(trf, TRF7970A_MODULATOR_SYS_CLK_CTRL,
+			trf->modulator_sys_clk_ctrl);
 	if (ret)
 		goto err_out;
 
-	trf->modulator_sys_clk_ctrl = 0;
-
 	ret = trf7970a_write(trf, TRF7970A_ADJUTABLE_FIFO_IRQ_LEVELS,
 			TRF7970A_ADJUTABLE_FIFO_IRQ_LEVELS_WLH_96 |
 			TRF7970A_ADJUTABLE_FIFO_IRQ_LEVELS_WLL_32);
@@ -1181,27 +1189,37 @@ static int trf7970a_in_config_rf_tech(struct trf7970a *trf, int tech)
 	switch (tech) {
 	case NFC_DIGITAL_RF_TECH_106A:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_14443A_106;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_OOK;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_OOK;
 		trf->guard_time = TRF7970A_GUARD_TIME_NFCA;
 		break;
 	case NFC_DIGITAL_RF_TECH_106B:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_14443B_106;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_ASK10;
 		trf->guard_time = TRF7970A_GUARD_TIME_NFCB;
 		break;
 	case NFC_DIGITAL_RF_TECH_212F:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_FELICA_212;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_ASK10;
 		trf->guard_time = TRF7970A_GUARD_TIME_NFCF;
 		break;
 	case NFC_DIGITAL_RF_TECH_424F:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_FELICA_424;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_ASK10;
 		trf->guard_time = TRF7970A_GUARD_TIME_NFCF;
 		break;
 	case NFC_DIGITAL_RF_TECH_ISO15693:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_15693_SGL_1OF4_2648;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_OOK;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_OOK;
 		trf->guard_time = TRF7970A_GUARD_TIME_15693;
 		break;
 	default:
@@ -1571,17 +1589,23 @@ static int trf7970a_tg_config_rf_tech(struct trf7970a *trf, int tech)
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_NFC_NFC_CE_MODE |
 			TRF7970A_ISO_CTRL_NFC_CE |
 			TRF7970A_ISO_CTRL_NFC_CE_14443A;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_OOK;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_OOK;
 		break;
 	case NFC_DIGITAL_RF_TECH_212F:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_NFC_NFC_CE_MODE |
 			TRF7970A_ISO_CTRL_NFC_NFCF_212;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_ASK10;
 		break;
 	case NFC_DIGITAL_RF_TECH_424F:
 		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_NFC_NFC_CE_MODE |
 			TRF7970A_ISO_CTRL_NFC_NFCF_424;
-		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		trf->modulator_sys_clk_ctrl =
+			(trf->modulator_sys_clk_ctrl & 0xf8) |
+			TRF7970A_MODULATOR_DEPTH_ASK10;
 		break;
 	default:
 		dev_dbg(trf->dev, "Unsupported rf technology: %d\n", tech);
@@ -1749,7 +1773,7 @@ static int _trf7970a_tg_listen(struct nfc_digital_dev *ddev, u16 timeout,
 		goto out_err;
 
 	ret = trf7970a_write(trf, TRF7970A_REG_IO_CTRL,
-			TRF7970A_REG_IO_CTRL_VRS(0x1));
+			trf->io_ctrl | TRF7970A_REG_IO_CTRL_VRS(0x1));
 	if (ret)
 		goto out_err;
 
@@ -1885,8 +1909,10 @@ static int trf7970a_power_up(struct trf7970a *trf)
 	usleep_range(5000, 6000);
 
 	if (!(trf->quirks & TRF7970A_QUIRK_EN2_MUST_STAY_LOW)) {
-		gpio_set_value(trf->en2_gpio, 1);
-		usleep_range(1000, 2000);
+		if (gpio_is_valid(trf->en2_gpio)) {
+			gpio_set_value(trf->en2_gpio, 1);
+			usleep_range(1000, 2000);
+		}
 	}
 
 	gpio_set_value(trf->en_gpio, 1);
@@ -1914,7 +1940,8 @@ static int trf7970a_power_down(struct trf7970a *trf)
 	}
 
 	gpio_set_value(trf->en_gpio, 0);
-	gpio_set_value(trf->en2_gpio, 0);
+	if (gpio_is_valid(trf->en2_gpio))
+		gpio_set_value(trf->en2_gpio, 0);
 
 	ret = regulator_disable(trf->regulator);
 	if (ret)
@@ -1987,6 +2014,7 @@ static int trf7970a_probe(struct spi_device *spi)
 	struct device_node *np = spi->dev.of_node;
 	struct trf7970a *trf;
 	int uvolts, autosuspend_delay, ret;
+	u32 clk_freq = TRF7970A_13MHZ_CLOCK_FREQUENCY;
 
 	if (!np) {
 		dev_err(&spi->dev, "No Device Tree entry\n");
@@ -2032,15 +2060,23 @@ static int trf7970a_probe(struct spi_device *spi)
 
 	trf->en2_gpio = of_get_named_gpio(np, "ti,enable-gpios", 1);
 	if (!gpio_is_valid(trf->en2_gpio)) {
-		dev_err(trf->dev, "No EN2 GPIO property\n");
-		return trf->en2_gpio;
+		dev_info(trf->dev, "No EN2 GPIO property\n");
+	} else {
+		ret = devm_gpio_request_one(trf->dev, trf->en2_gpio,
+				GPIOF_DIR_OUT | GPIOF_INIT_LOW, "trf7970a EN2");
+		if (ret) {
+			dev_err(trf->dev, "Can't request EN2 GPIO: %d\n", ret);
+			return ret;
+		}
 	}
 
-	ret = devm_gpio_request_one(trf->dev, trf->en2_gpio,
-			GPIOF_DIR_OUT | GPIOF_INIT_LOW, "trf7970a EN2");
-	if (ret) {
-		dev_err(trf->dev, "Can't request EN2 GPIO: %d\n", ret);
-		return ret;
+	of_property_read_u32(np, "clock-frequency", &clk_freq);
+	if ((clk_freq != TRF7970A_27MHZ_CLOCK_FREQUENCY) ||
+		(clk_freq != TRF7970A_13MHZ_CLOCK_FREQUENCY)) {
+		dev_err(trf->dev,
+			"clock-frequency (%u Hz) unsupported\n",
+			clk_freq);
+		return -EINVAL;
 	}
 
 	if (of_property_read_bool(np, "en2-rf-quirk"))
@@ -2077,6 +2113,24 @@ static int trf7970a_probe(struct spi_device *spi)
 	if (uvolts > 4000000)
 		trf->chip_status_ctrl = TRF7970A_CHIP_STATUS_VRS5_3;
 
+	trf->regulator = devm_regulator_get(&spi->dev, "vdd-io");
+	if (IS_ERR(trf->regulator)) {
+		ret = PTR_ERR(trf->regulator);
+		dev_err(trf->dev, "Can't get VDD_IO regulator: %d\n", ret);
+		goto err_destroy_lock;
+	}
+
+	ret = regulator_enable(trf->regulator);
+	if (ret) {
+		dev_err(trf->dev, "Can't enable VDD_IO: %d\n", ret);
+		goto err_destroy_lock;
+	}
+
+	if (regulator_get_voltage(trf->regulator) == 1800000) {
+		trf->io_ctrl = TRF7970A_REG_IO_CTRL_IO_LOW;
+		dev_dbg(trf->dev, "trf7970a config vdd_io to 1.8V\n");
+	}
+
 	trf->ddev = nfc_digital_allocate_device(&trf7970a_nfc_ops,
 			TRF7970A_SUPPORTED_PROTOCOLS,
 			NFC_DIGITAL_DRV_CAPS_IN_CRC |
diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c
index 3319cf19deeb..77a48a5164ff 100644
--- a/drivers/nubus/nubus.c
+++ b/drivers/nubus/nubus.c
@@ -44,8 +44,8 @@ extern void oss_nubus_init(void);
 
 /* Globals */
 
-struct nubus_dev*   nubus_devices;
-struct nubus_board* nubus_boards;
+struct nubus_dev *nubus_devices;
+struct nubus_board *nubus_boards;
 
 /* Meaning of "bytelanes":
 
@@ -69,26 +69,26 @@ struct nubus_board* nubus_boards;
 
    Etcetera, etcetera.  Hopefully this clears up some confusion over
    what the following code actually does.  */
- 
+
 static inline int not_useful(void *p, int map)
 {
-	unsigned long pv=(unsigned long)p;
+	unsigned long pv = (unsigned long)p;
+
 	pv &= 3;
-	if(map & (1<<pv))
+	if (map & (1 << pv))
 		return 0;
 	return 1;
 }
- 
+
 static unsigned long nubus_get_rom(unsigned char **ptr, int len, int map)
 {
 	/* This will hold the result */
 	unsigned long v = 0;
 	unsigned char *p = *ptr;
 
-	while(len)
-	{
+	while (len) {
 		v <<= 8;
-		while(not_useful(p,map))
+		while (not_useful(p, map))
 			p++;
 		v |= *p++;
 		len--;
@@ -99,31 +99,28 @@ static unsigned long nubus_get_rom(unsigned char **ptr, int len, int map)
 
 static void nubus_rewind(unsigned char **ptr, int len, int map)
 {
-	unsigned char *p=*ptr;
+	unsigned char *p = *ptr;
 
 	/* Sanity check */
-	if(len > 65536)
-		printk(KERN_ERR "rewind of 0x%08x!\n", len);
-	while(len)
-	{
-		do
-		{
+	if (len > 65536)
+		pr_err("rewind of 0x%08x!\n", len);
+	while (len) {
+		do {
 			p--;
-		}
-		while(not_useful(p, map));
+		} while (not_useful(p, map));
 		len--;
 	}
-	*ptr=p;
+	*ptr = p;
 }
 
 static void nubus_advance(unsigned char **ptr, int len, int map)
 {
 	unsigned char *p = *ptr;
-	if(len>65536)
-		printk(KERN_ERR "advance of 0x%08x!\n", len);
-	while(len)
-	{
-		while(not_useful(p,map))
+
+	if (len > 65536)
+		pr_err("advance of 0x%08x!\n", len);
+	while (len) {
+		while (not_useful(p, map))
 			p++;
 		p++;
 		len--;
@@ -133,9 +130,9 @@ static void nubus_advance(unsigned char **ptr, int len, int map)
 
 static void nubus_move(unsigned char **ptr, int len, int map)
 {
-	if(len > 0)
+	if (len > 0)
 		nubus_advance(ptr, len, map);
-	else if(len < 0)
+	else if (len < 0)
 		nubus_rewind(ptr, -len, map);
 }
 
@@ -148,23 +145,24 @@ static void nubus_move(unsigned char **ptr, int len, int map)
 
 static inline long nubus_expand32(long foo)
 {
-	if(foo & 0x00800000)	/* 24bit negative */
+	if (foo & 0x00800000)	/* 24bit negative */
 		foo |= 0xFF000000;
 	return foo;
 }
 
 static inline void *nubus_rom_addr(int slot)
-{	
+{
 	/*
 	 *	Returns the first byte after the card. We then walk
 	 *	backwards to get the lane register and the config
 	 */
-	return (void *)(0xF1000000+(slot<<24));
+	return (void *)(0xF1000000 + (slot << 24));
 }
 
 static unsigned char *nubus_dirptr(const struct nubus_dirent *nd)
 {
 	unsigned char *p = nd->base;
+
 	/* Essentially, just step over the bytelanes using whatever
 	   offset we might have found */
 	nubus_move(&p, nubus_expand32(nd->data), nd->mask);
@@ -175,36 +173,36 @@ static unsigned char *nubus_dirptr(const struct nubus_dirent *nd)
 /* These two are for pulling resource data blocks (i.e. stuff that's
    pointed to with offsets) out of the card ROM. */
 
-void nubus_get_rsrc_mem(void *dest, const struct nubus_dirent* dirent,
+void nubus_get_rsrc_mem(void *dest, const struct nubus_dirent *dirent,
 			int len)
 {
 	unsigned char *t = (unsigned char *)dest;
 	unsigned char *p = nubus_dirptr(dirent);
-	while(len)
-	{
+
+	while (len) {
 		*t++ = nubus_get_rom(&p, 1, dirent->mask);
 		len--;
 	}
 }
 EXPORT_SYMBOL(nubus_get_rsrc_mem);
 
-void nubus_get_rsrc_str(void *dest, const struct nubus_dirent* dirent,
+void nubus_get_rsrc_str(void *dest, const struct nubus_dirent *dirent,
 			int len)
 {
-	unsigned char *t=(unsigned char *)dest;
+	unsigned char *t = (unsigned char *)dest;
 	unsigned char *p = nubus_dirptr(dirent);
-	while(len)
-	{
+
+	while (len) {
 		*t = nubus_get_rom(&p, 1, dirent->mask);
-		if(!*t++)
+		if (!*t++)
 			break;
 		len--;
 	}
 }
 EXPORT_SYMBOL(nubus_get_rsrc_str);
 
-int nubus_get_root_dir(const struct nubus_board* board,
-		       struct nubus_dir* dir)
+int nubus_get_root_dir(const struct nubus_board *board,
+		       struct nubus_dir *dir)
 {
 	dir->ptr = dir->base = board->directory;
 	dir->done = 0;
@@ -214,8 +212,8 @@ int nubus_get_root_dir(const struct nubus_board* board,
 EXPORT_SYMBOL(nubus_get_root_dir);
 
 /* This is a slyly renamed version of the above */
-int nubus_get_func_dir(const struct nubus_dev* dev,
-		       struct nubus_dir* dir)
+int nubus_get_func_dir(const struct nubus_dev *dev,
+		       struct nubus_dir *dir)
 {
 	dir->ptr = dir->base = dev->directory;
 	dir->done = 0;
@@ -224,11 +222,11 @@ int nubus_get_func_dir(const struct nubus_dev* dev,
 }
 EXPORT_SYMBOL(nubus_get_func_dir);
 
-int nubus_get_board_dir(const struct nubus_board* board,
-			struct nubus_dir* dir)
+int nubus_get_board_dir(const struct nubus_board *board,
+			struct nubus_dir *dir)
 {
 	struct nubus_dirent ent;
-	
+
 	dir->ptr = dir->base = board->directory;
 	dir->done = 0;
 	dir->mask = board->lanes;
@@ -256,6 +254,7 @@ EXPORT_SYMBOL(nubus_get_subdir);
 int nubus_readdir(struct nubus_dir *nd, struct nubus_dirent *ent)
 {
 	u32 resid;
+
 	if (nd->done)
 		return -1;
 
@@ -266,25 +265,25 @@ int nubus_readdir(struct nubus_dir *nd, struct nubus_dirent *ent)
 	resid = nubus_get_rom(&nd->ptr, 4, nd->mask);
 
 	/* EOL marker, as per the Apple docs */
-	if((resid&0xff000000) == 0xff000000)
-	{
+	if ((resid & 0xff000000) == 0xff000000) {
 		/* Mark it as done */
 		nd->done = 1;
 		return -1;
 	}
 
 	/* First byte is the resource ID */
-	ent->type  = resid >> 24;
+	ent->type = resid >> 24;
 	/* Low 3 bytes might contain data (or might not) */
 	ent->data = resid & 0xffffff;
-	ent->mask  = nd->mask;
+	ent->mask = nd->mask;
 	return 0;
 }
 EXPORT_SYMBOL(nubus_readdir);
 
-int nubus_rewinddir(struct nubus_dir* dir)
+int nubus_rewinddir(struct nubus_dir *dir)
 {
 	dir->ptr = dir->base;
+	dir->done = 0;
 	return 0;
 }
 EXPORT_SYMBOL(nubus_rewinddir);
@@ -292,20 +291,15 @@ EXPORT_SYMBOL(nubus_rewinddir);
 /* Driver interface functions, more or less like in pci.c */
 
 struct nubus_dev*
-nubus_find_device(unsigned short category,
-		  unsigned short type,
-		  unsigned short dr_hw,
-		  unsigned short dr_sw,
-		  const struct nubus_dev* from)
+nubus_find_device(unsigned short category, unsigned short type,
+		  unsigned short dr_hw, unsigned short dr_sw,
+		  const struct nubus_dev *from)
 {
-	struct nubus_dev* itor =
-		from ? from->next : nubus_devices;
+	struct nubus_dev *itor = from ? from->next : nubus_devices;
 
 	while (itor) {
-		if (itor->category == category
-		    && itor->type == type
-		    && itor->dr_hw == dr_hw
-		    && itor->dr_sw == dr_sw)
+		if (itor->category == category && itor->type == type &&
+		    itor->dr_hw == dr_hw && itor->dr_sw == dr_sw)
 			return itor;
 		itor = itor->next;
 	}
@@ -314,16 +308,13 @@ nubus_find_device(unsigned short category,
 EXPORT_SYMBOL(nubus_find_device);
 
 struct nubus_dev*
-nubus_find_type(unsigned short category,
-		unsigned short type,
-		const struct nubus_dev* from)
+nubus_find_type(unsigned short category, unsigned short type,
+		const struct nubus_dev *from)
 {
-	struct nubus_dev* itor =
-		from ? from->next : nubus_devices;
+	struct nubus_dev *itor = from ? from->next : nubus_devices;
 
 	while (itor) {
-		if (itor->category == category
-		    && itor->type == type)
+		if (itor->category == category && itor->type == type)
 			return itor;
 		itor = itor->next;
 	}
@@ -332,12 +323,10 @@ nubus_find_type(unsigned short category,
 EXPORT_SYMBOL(nubus_find_type);
 
 struct nubus_dev*
-nubus_find_slot(unsigned int slot,
-		const struct nubus_dev* from)
+nubus_find_slot(unsigned int slot, const struct nubus_dev *from)
 {
-	struct nubus_dev* itor =
-		from ? from->next : nubus_devices;
-	
+	struct nubus_dev *itor = from ? from->next : nubus_devices;
+
 	while (itor) {
 		if (itor->board->slot == slot)
 			return itor;
@@ -348,13 +337,13 @@ nubus_find_slot(unsigned int slot,
 EXPORT_SYMBOL(nubus_find_slot);
 
 int
-nubus_find_rsrc(struct nubus_dir* dir, unsigned char rsrc_type,
-		struct nubus_dirent* ent)
+nubus_find_rsrc(struct nubus_dir *dir, unsigned char rsrc_type,
+		struct nubus_dirent *ent)
 {
 	while (nubus_readdir(dir, ent) != -1) {
 		if (ent->type == rsrc_type)
 			return 0;
-	}	
+	}
 	return -1;
 }
 EXPORT_SYMBOL(nubus_find_rsrc);
@@ -368,77 +357,74 @@ EXPORT_SYMBOL(nubus_find_rsrc);
    among other things.  The rest of it should go in the /proc code.
    For now, we just use it to give verbose boot logs. */
 
-static int __init nubus_show_display_resource(struct nubus_dev* dev,
-					      const struct nubus_dirent* ent)
+static int __init nubus_show_display_resource(struct nubus_dev *dev,
+					      const struct nubus_dirent *ent)
 {
 	switch (ent->type) {
 	case NUBUS_RESID_GAMMADIR:
-		printk(KERN_INFO "    gamma directory offset: 0x%06x\n", ent->data);
+		pr_info("    gamma directory offset: 0x%06x\n", ent->data);
 		break;
 	case 0x0080 ... 0x0085:
-		printk(KERN_INFO "    mode %02X info offset: 0x%06x\n",
+		pr_info("    mode %02X info offset: 0x%06x\n",
 		       ent->type, ent->data);
 		break;
 	default:
-		printk(KERN_INFO "    unknown resource %02X, data 0x%06x\n",
+		pr_info("    unknown resource %02X, data 0x%06x\n",
 		       ent->type, ent->data);
 	}
 	return 0;
 }
 
-static int __init nubus_show_network_resource(struct nubus_dev* dev,
-					      const struct nubus_dirent* ent)
+static int __init nubus_show_network_resource(struct nubus_dev *dev,
+					      const struct nubus_dirent *ent)
 {
 	switch (ent->type) {
 	case NUBUS_RESID_MAC_ADDRESS:
 	{
 		char addr[6];
-		int i;
-		
+
 		nubus_get_rsrc_mem(addr, ent, 6);
-		printk(KERN_INFO "    MAC address: ");
-		for (i = 0; i < 6; i++)
-			printk("%02x%s", addr[i] & 0xff,
-			       i == 5 ? "" : ":");
-		printk("\n");
+		pr_info("    MAC address: %pM\n", addr);
 		break;
 	}
 	default:
-		printk(KERN_INFO "    unknown resource %02X, data 0x%06x\n",
+		pr_info("    unknown resource %02X, data 0x%06x\n",
 		       ent->type, ent->data);
 	}
 	return 0;
 }
 
-static int __init nubus_show_cpu_resource(struct nubus_dev* dev,
-					  const struct nubus_dirent* ent)
+static int __init nubus_show_cpu_resource(struct nubus_dev *dev,
+					  const struct nubus_dirent *ent)
 {
 	switch (ent->type) {
 	case NUBUS_RESID_MEMINFO:
 	{
 		unsigned long meminfo[2];
+
 		nubus_get_rsrc_mem(&meminfo, ent, 8);
-		printk(KERN_INFO "    memory: [ 0x%08lx 0x%08lx ]\n",
+		pr_info("    memory: [ 0x%08lx 0x%08lx ]\n",
 		       meminfo[0], meminfo[1]);
 		break;
 	}
 	case NUBUS_RESID_ROMINFO:
 	{
 		unsigned long rominfo[2];
+
 		nubus_get_rsrc_mem(&rominfo, ent, 8);
-		printk(KERN_INFO "    ROM:    [ 0x%08lx 0x%08lx ]\n",
+		pr_info("    ROM:    [ 0x%08lx 0x%08lx ]\n",
 		       rominfo[0], rominfo[1]);
 		break;
 	}
 	default:
-		printk(KERN_INFO "    unknown resource %02X, data 0x%06x\n",
+		pr_info("    unknown resource %02X, data 0x%06x\n",
 		       ent->type, ent->data);
 	}
 	return 0;
 }
 
-static int __init nubus_show_private_resource(struct nubus_dev* dev,
-					      const struct nubus_dirent* ent)
+static int __init nubus_show_private_resource(struct nubus_dev *dev,
+					      const struct nubus_dirent *ent)
 {
 	switch (dev->category) {
 	case NUBUS_CAT_DISPLAY:
@@ -451,59 +437,56 @@ static int __init nubus_show_private_resource(struct nubus_dev* dev,
 		nubus_show_cpu_resource(dev, ent);
 		break;
 	default:
-		printk(KERN_INFO "    unknown resource %02X, data 0x%06x\n",
+		pr_info("    unknown resource %02X, data 0x%06x\n",
 		       ent->type, ent->data);
 	}
 	return 0;
 }
 
-static struct nubus_dev* __init
-	   nubus_get_functional_resource(struct nubus_board* board,
-					 int slot,
-					 const struct nubus_dirent* parent)
+static struct nubus_dev * __init
+nubus_get_functional_resource(struct nubus_board *board, int slot,
+			      const struct nubus_dirent *parent)
 {
-	struct nubus_dir    dir;
+	struct nubus_dir dir;
 	struct nubus_dirent ent;
-	struct nubus_dev*   dev;
-	
-	printk(KERN_INFO "  Function 0x%02x:\n", parent->type);
+	struct nubus_dev *dev;
+
+	pr_info("  Function 0x%02x:\n", parent->type);
 	nubus_get_subdir(parent, &dir);
 
 	/* Apple seems to have botched the ROM on the IIx */
 	if (slot == 0 && (unsigned long)dir.base % 2)
 		dir.base += 1;
-	
-	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
-		printk(KERN_DEBUG "nubus_get_functional_resource: parent is 0x%p, dir is 0x%p\n",
-		       parent->base, dir.base);
+
+	pr_debug("%s: parent is 0x%p, dir is 0x%p\n",
+	         __func__, parent->base, dir.base);
 
 	/* Actually we should probably panic if this fails */
 	if ((dev = kzalloc(sizeof(*dev), GFP_ATOMIC)) == NULL)
-		return NULL;	
+		return NULL;
 	dev->resid = parent->type;
 	dev->directory = dir.base;
 	dev->board = board;
-	
-	while (nubus_readdir(&dir, &ent) != -1)
-	{
-		switch(ent.type)
-		{
+
+	while (nubus_readdir(&dir, &ent) != -1) {
+		switch (ent.type) {
 		case NUBUS_RESID_TYPE:
 		{
 			unsigned short nbtdata[4];
+
 			nubus_get_rsrc_mem(nbtdata, &ent, 8);
 			dev->category = nbtdata[0];
 			dev->type     = nbtdata[1];
 			dev->dr_sw    = nbtdata[2];
 			dev->dr_hw    = nbtdata[3];
-			printk(KERN_INFO "    type: [cat 0x%x type 0x%x hw 0x%x sw 0x%x]\n",
-			       nbtdata[0], nbtdata[1], nbtdata[2], nbtdata[3]);
+			pr_info("    type: [cat 0x%x type 0x%x sw 0x%x hw 0x%x]\n",
+			        nbtdata[0], nbtdata[1], nbtdata[2], nbtdata[3]);
 			break;
 		}
 		case NUBUS_RESID_NAME:
 		{
 			nubus_get_rsrc_str(dev->name, &ent, 64);
-			printk(KERN_INFO "    name: %s\n", dev->name);
+			pr_info("    name: %s\n", dev->name);
 			break;
 		}
 		case NUBUS_RESID_DRVRDIR:
@@ -512,11 +495,11 @@ static struct nubus_dev* __init
 			   use this :-) */
 			struct nubus_dir drvr_dir;
 			struct nubus_dirent drvr_ent;
+
 			nubus_get_subdir(&ent, &drvr_dir);
 			nubus_readdir(&drvr_dir, &drvr_ent);
 			dev->driver = nubus_dirptr(&drvr_ent);
-			printk(KERN_INFO "    driver at: 0x%p\n",
-			       dev->driver);
+			pr_info("    driver at: 0x%p\n", dev->driver);
 			break;
 		}
 		case NUBUS_RESID_MINOR_BASEOS:
@@ -524,22 +507,20 @@ static struct nubus_dev* __init
 			   multiple framebuffers.  It might be handy
 			   for Ethernet as well */
 			nubus_get_rsrc_mem(&dev->iobase, &ent, 4);
-			printk(KERN_INFO "    memory offset: 0x%08lx\n",
-			       dev->iobase);
+			pr_info("    memory offset: 0x%08lx\n", dev->iobase);
 			break;
 		case NUBUS_RESID_MINOR_LENGTH:
 			/* Ditto */
 			nubus_get_rsrc_mem(&dev->iosize, &ent, 4);
-			printk(KERN_INFO "    memory length: 0x%08lx\n",
-			       dev->iosize);
-			break;			
+			pr_info("    memory length: 0x%08lx\n", dev->iosize);
+			break;
 		case NUBUS_RESID_FLAGS:
 			dev->flags = ent.data;
-			printk(KERN_INFO "    flags: 0x%06x\n", dev->flags);
+			pr_info("    flags: 0x%06x\n", dev->flags);
 			break;
 		case NUBUS_RESID_HWDEVID:
 			dev->hwdevid = ent.data;
-			printk(KERN_INFO "    hwdevid: 0x%06x\n", dev->hwdevid);
+			pr_info("    hwdevid: 0x%06x\n", dev->hwdevid);
 			break;
 		default:
 			/* Local/Private resources have their own
@@ -547,16 +528,17 @@ static struct nubus_dev* __init
 			nubus_show_private_resource(dev, &ent);
 		}
 	}
-		
+
 	return dev;
 }
 
 /* This is cool. */
-static int __init nubus_get_vidnames(struct nubus_board* board,
-				     const struct nubus_dirent* parent)
+static int __init nubus_get_vidnames(struct nubus_board *board,
+				     const struct nubus_dirent *parent)
 {
-	struct nubus_dir    dir;
+	struct nubus_dir dir;
 	struct nubus_dirent ent;
+
 	/* FIXME: obviously we want to put this in a header file soon */
 	struct vidmode {
 		u32 size;
@@ -566,100 +548,92 @@ static int __init nubus_get_vidnames(struct nubus_board* board,
 		char name[32];
 	};
 
-	printk(KERN_INFO "    video modes supported:\n");
+	pr_info("    video modes supported:\n");
 	nubus_get_subdir(parent, &dir);
-	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
-		printk(KERN_DEBUG "nubus_get_vidnames: parent is 0x%p, dir is 0x%p\n",
-		       parent->base, dir.base);
+	pr_debug("%s: parent is 0x%p, dir is 0x%p\n",
+	         __func__, parent->base, dir.base);
 
-	while(nubus_readdir(&dir, &ent) != -1)
-	{
+	while (nubus_readdir(&dir, &ent) != -1) {
 		struct vidmode mode;
 		u32 size;
 
 		/* First get the length */
 		nubus_get_rsrc_mem(&size, &ent, 4);
-		
+
 		/* Now clobber the whole thing */
 		if (size > sizeof(mode) - 1)
 			size = sizeof(mode) - 1;
 		memset(&mode, 0, sizeof(mode));
 		nubus_get_rsrc_mem(&mode, &ent, size);
-		printk (KERN_INFO "      %02X: (%02X) %s\n", ent.type,
+		pr_info("      %02X: (%02X) %s\n", ent.type,
 			mode.id, mode.name);
 	}
 	return 0;
 }
 
 /* This is *really* cool. */
-static int __init nubus_get_icon(struct nubus_board* board,
-				 const struct nubus_dirent* ent)
+static int __init nubus_get_icon(struct nubus_board *board,
+				 const struct nubus_dirent *ent)
 {
 	/* Should be 32x32 if my memory serves me correctly */
 	unsigned char icon[128];
 	int x, y;
-	
+
 	nubus_get_rsrc_mem(&icon, ent, 128);
-	printk(KERN_INFO "    icon:\n");
+	pr_info("    icon:\n");
 
 	/* We should actually plot these somewhere in the framebuffer
 	   init.  This is just to demonstrate that they do, in fact,
 	   exist */
 	for (y = 0; y < 32; y++) {
-		printk(KERN_INFO "      ");
+		pr_info("      ");
 		for (x = 0; x < 32; x++) {
-			if (icon[y*4 + x/8]
-			    & (0x80 >> (x%8)))
-				printk("*");
+			if (icon[y * 4 + x / 8] & (0x80 >> (x % 8)))
+				pr_cont("*");
 			else
-				printk(" ");
+				pr_cont(" ");
 		}
-		printk("\n");
+		pr_cont("\n");
 	}
 	return 0;
 }
 
-static int __init nubus_get_vendorinfo(struct nubus_board* board,
-				       const struct nubus_dirent* parent)
+static int __init nubus_get_vendorinfo(struct nubus_board *board,
+				       const struct nubus_dirent *parent)
 {
-	struct nubus_dir    dir;
+	struct nubus_dir dir;
 	struct nubus_dirent ent;
-	static char* vendor_fields[6] = {"ID", "serial", "revision",
-					 "part", "date", "unknown field"};
+	static char *vendor_fields[6] = { "ID", "serial", "revision",
+	                                  "part", "date", "unknown field" };
 
-	printk(KERN_INFO "    vendor info:\n");
+	pr_info("    vendor info:\n");
 	nubus_get_subdir(parent, &dir);
-	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
-		printk(KERN_DEBUG "nubus_get_vendorinfo: parent is 0x%p, dir is 0x%p\n",
-		       parent->base, dir.base);
+	pr_debug("%s: parent is 0x%p, dir is 0x%p\n",
+	         __func__, parent->base, dir.base);
 
-	while(nubus_readdir(&dir, &ent) != -1)
-	{
+	while (nubus_readdir(&dir, &ent) != -1) {
 		char name[64];
-		
+
 		/* These are all strings, we think */
 		nubus_get_rsrc_str(name, &ent, 64);
 		if (ent.type > 5)
 			ent.type = 5;
-		printk(KERN_INFO "    %s: %s\n",
-		       vendor_fields[ent.type-1], name);
+		pr_info("    %s: %s\n", vendor_fields[ent.type - 1], name);
 	}
 	return 0;
 }
 
-static int __init nubus_get_board_resource(struct nubus_board* board, int slot,
-					   const struct nubus_dirent* parent)
+static int __init nubus_get_board_resource(struct nubus_board *board, int slot,
+					   const struct nubus_dirent *parent)
 {
-	struct nubus_dir    dir;
+	struct nubus_dir dir;
 	struct nubus_dirent ent;
-	
+
 	nubus_get_subdir(parent, &dir);
-	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
-		printk(KERN_DEBUG "nubus_get_board_resource: parent is 0x%p, dir is 0x%p\n",
-		       parent->base, dir.base);
+	pr_debug("%s: parent is 0x%p, dir is 0x%p\n",
+	         __func__, parent->base, dir.base);
 
-	while(nubus_readdir(&dir, &ent) != -1)
-	{
+	while (nubus_readdir(&dir, &ent) != -1) {
 		switch (ent.type) {
 		case NUBUS_RESID_TYPE:
 		{
@@ -668,50 +642,49 @@ static int __init nubus_get_board_resource(struct nubus_board* board, int slot,
 			   useful except insofar as it tells us that
 			   we really are looking at a board resource. */
 			nubus_get_rsrc_mem(nbtdata, &ent, 8);
-			printk(KERN_INFO "    type: [cat 0x%x type 0x%x hw 0x%x sw 0x%x]\n",
-			       nbtdata[0], nbtdata[1], nbtdata[2],
-			       nbtdata[3]);
+			pr_info("    type: [cat 0x%x type 0x%x sw 0x%x hw 0x%x]\n",
+			        nbtdata[0], nbtdata[1], nbtdata[2], nbtdata[3]);
 			if (nbtdata[0] != 1 || nbtdata[1] != 0 ||
 			    nbtdata[2] != 0 || nbtdata[3] != 0)
-				printk(KERN_ERR "this sResource is not a board resource!\n");
+				pr_err("this sResource is not a board resource!\n");
 			break;
 		}
 		case NUBUS_RESID_NAME:
 			nubus_get_rsrc_str(board->name, &ent, 64);
-			printk(KERN_INFO "    name: %s\n", board->name);
+			pr_info("    name: %s\n", board->name);
 			break;
 		case NUBUS_RESID_ICON:
 			nubus_get_icon(board, &ent);
 			break;
 		case NUBUS_RESID_BOARDID:
-			printk(KERN_INFO "    board id: 0x%x\n", ent.data);
+			pr_info("    board id: 0x%x\n", ent.data);
 			break;
 		case NUBUS_RESID_PRIMARYINIT:
-			printk(KERN_INFO "    primary init offset: 0x%06x\n", ent.data);
+			pr_info("    primary init offset: 0x%06x\n", ent.data);
 			break;
 		case NUBUS_RESID_VENDORINFO:
 			nubus_get_vendorinfo(board, &ent);
 			break;
 		case NUBUS_RESID_FLAGS:
-			printk(KERN_INFO "    flags: 0x%06x\n", ent.data);
+			pr_info("    flags: 0x%06x\n", ent.data);
 			break;
 		case NUBUS_RESID_HWDEVID:
-			printk(KERN_INFO "    hwdevid: 0x%06x\n", ent.data);
+			pr_info("    hwdevid: 0x%06x\n", ent.data);
 			break;
 		case NUBUS_RESID_SECONDINIT:
-			printk(KERN_INFO "    secondary init offset: 0x%06x\n", ent.data);
+			pr_info("    secondary init offset: 0x%06x\n", ent.data);
 			break;
-			/* WTF isn't this in the functional resources? */ 
+			/* WTF isn't this in the functional resources? */
 		case NUBUS_RESID_VIDNAMES:
 			nubus_get_vidnames(board, &ent);
 			break;
 			/* Same goes for this */
 		case NUBUS_RESID_VIDMODES:
-			printk(KERN_INFO "    video mode parameter directory offset: 0x%06x\n",
+			pr_info("    video mode parameter directory offset: 0x%06x\n",
 			       ent.data);
-			break;			
+			break;
 		default:
-			printk(KERN_INFO "    unknown resource %02X, data 0x%06x\n",
+			pr_info("    unknown resource %02X, data 0x%06x\n",
 			       ent.type, ent.data);
 		}
 	}
@@ -722,8 +695,8 @@ static int __init nubus_get_board_resource(struct nubus_board* board, int slot,
    sResources in the motherboard ROM */
 static void __init nubus_find_rom_dir(struct nubus_board* board)
 {
-	unsigned char* rp;
-	unsigned char* romdir;
+	unsigned char *rp;
+	unsigned char *romdir;
 	struct nubus_dir dir;
 	struct nubus_dirent ent;
 
@@ -756,14 +729,14 @@ static void __init nubus_find_rom_dir(struct nubus_board* board)
 	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
 		printk(KERN_INFO "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data);
 	/* This one takes us to where we want to go. */
-	if (nubus_readdir(&dir, &ent) == -1) 
+	if (nubus_readdir(&dir, &ent) == -1)
 		goto badrom;
 	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
 		printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data);
 	nubus_get_subdir(&ent, &dir);
 
 	/* Resource ID 01, also an "Unknown Macintosh" */
-	if (nubus_readdir(&dir, &ent) == -1) 
+	if (nubus_readdir(&dir, &ent) == -1)
 		goto badrom;
 	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
 		printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data);
@@ -782,12 +755,12 @@ static void __init nubus_find_rom_dir(struct nubus_board* board)
 		goto badrom;
 	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
 		printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data);
-	
+
 	/* Bwahahahaha... */
 	nubus_get_subdir(&ent, &dir);
 	board->directory = dir.base;
 	return;
-	
+
 	/* Even more evil laughter... */
  badrom:
 	board->directory = board->fblock;
@@ -796,43 +769,38 @@ static void __init nubus_find_rom_dir(struct nubus_board* board)
 }
 
 /* Add a board (might be many devices) to the list */
-static struct nubus_board* __init nubus_add_board(int slot, int bytelanes)
+static struct nubus_board * __init nubus_add_board(int slot, int bytelanes)
 {
-	struct nubus_board* board;
-	struct nubus_board** boardp;
-
+	struct nubus_board *board;
+	struct nubus_board **boardp;
 	unsigned char *rp;
 	unsigned long dpat;
 	struct nubus_dir dir;
 	struct nubus_dirent ent;
 
 	/* Move to the start of the format block */
-	rp = nubus_rom_addr(slot);		
+	rp = nubus_rom_addr(slot);
 	nubus_rewind(&rp, FORMAT_BLOCK_SIZE, bytelanes);
 
 	/* Actually we should probably panic if this fails */
 	if ((board = kzalloc(sizeof(*board), GFP_ATOMIC)) == NULL)
-		return NULL;	
+		return NULL;
 	board->fblock = rp;
 
 	/* Dump the format block for debugging purposes */
-	if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) {
-		int i;
-		printk(KERN_DEBUG "Slot %X, format block at 0x%p\n",
-		       slot, rp);
-		printk(KERN_DEBUG "Format block: ");
-		for (i = 0; i < FORMAT_BLOCK_SIZE; i += 4) {
-			unsigned short foo, bar;
-			foo = nubus_get_rom(&rp, 2, bytelanes);
-			bar = nubus_get_rom(&rp, 2, bytelanes);
-			printk("%04x %04x  ", foo, bar);
-		}
-		printk("\n");
-		rp = board->fblock;
-	}
-	
+	pr_debug("Slot %X, format block at 0x%p:\n", slot, rp);
+	pr_debug("%02lx\n", nubus_get_rom(&rp, 1, bytelanes));
+	pr_debug("%02lx\n", nubus_get_rom(&rp, 1, bytelanes));
+	pr_debug("%08lx\n", nubus_get_rom(&rp, 4, bytelanes));
+	pr_debug("%02lx\n", nubus_get_rom(&rp, 1, bytelanes));
+	pr_debug("%02lx\n", nubus_get_rom(&rp, 1, bytelanes));
+	pr_debug("%08lx\n", nubus_get_rom(&rp, 4, bytelanes));
+	pr_debug("%08lx\n", nubus_get_rom(&rp, 4, bytelanes));
+	pr_debug("%08lx\n", nubus_get_rom(&rp, 4, bytelanes));
+	rp = board->fblock;
+
 	board->slot = slot;
-	board->slot_addr = (unsigned long) nubus_slot_addr(slot);
+	board->slot_addr = (unsigned long)nubus_slot_addr(slot);
 	board->doffset = nubus_get_rom(&rp, 4, bytelanes);
 	/* rom_length is *supposed* to be the total length of the
 	 * ROM.  In practice it is the "amount of ROM used to compute
@@ -843,16 +811,16 @@ static struct nubus_board* __init nubus_add_board(int slot, int bytelanes)
 	board->rom_length = nubus_get_rom(&rp, 4, bytelanes);
 	board->crc = nubus_get_rom(&rp, 4, bytelanes);
 	board->rev = nubus_get_rom(&rp, 1, bytelanes);
-	board->format = nubus_get_rom(&rp,1, bytelanes);
+	board->format = nubus_get_rom(&rp, 1, bytelanes);
 	board->lanes = bytelanes;
 
 	/* Directory offset should be small and negative... */
-	if(!(board->doffset & 0x00FF0000))
-		printk(KERN_WARNING "Dodgy doffset!\n");
+	if (!(board->doffset & 0x00FF0000))
+		pr_warn("Dodgy doffset!\n");
 	dpat = nubus_get_rom(&rp, 4, bytelanes);
-	if(dpat != NUBUS_TEST_PATTERN)
-		printk(KERN_WARNING "Wrong test pattern %08lx!\n", dpat);
-		
+	if (dpat != NUBUS_TEST_PATTERN)
+		pr_warn("Wrong test pattern %08lx!\n", dpat);
+
 	/*
 	 *	I wonder how the CRC is meant to work -
 	 *		any takers ?
@@ -862,10 +830,10 @@ static struct nubus_board* __init nubus_add_board(int slot, int bytelanes)
 
 	/* Attempt to work around slot zero weirdness */
 	nubus_find_rom_dir(board);
-	nubus_get_root_dir(board, &dir);	
+	nubus_get_root_dir(board, &dir);
 
 	/* We're ready to rock */
-	printk(KERN_INFO "Slot %X:\n", slot);
+	pr_info("Slot %X:\n", slot);
 
 	/* Each slot should have one board resource and any number of
 	   functional resources.  So we'll fill in some fields in the
@@ -874,10 +842,10 @@ static struct nubus_board* __init nubus_add_board(int slot, int bytelanes)
 	   for each of them. */
 	if (nubus_readdir(&dir, &ent) == -1) {
 		/* We can't have this! */
-		printk(KERN_ERR "Board resource not found!\n");
+		pr_err("Board resource not found!\n");
 		return NULL;
 	} else {
-		printk(KERN_INFO "  Board resource:\n");
+		pr_info("  Board resource:\n");
 		nubus_get_board_resource(board, slot, &ent);
 	}
 
@@ -885,8 +853,9 @@ static struct nubus_board* __init nubus_add_board(int slot, int bytelanes)
 	   resources.  I have no idea WTF to do about this. */
 
 	while (nubus_readdir(&dir, &ent) != -1) {
-		struct nubus_dev*  dev;
-		struct nubus_dev** devp;
+		struct nubus_dev *dev;
+		struct nubus_dev **devp;
+
 		dev = nubus_get_functional_resource(board, slot, &ent);
 		if (dev == NULL)
 			continue;
@@ -894,32 +863,33 @@ static struct nubus_board* __init nubus_add_board(int slot, int bytelanes)
 		/* We zeroed this out above */
 		if (board->first_dev == NULL)
 			board->first_dev = dev;
-		
+
 		/* Put it on the global NuBus device chain. Keep entries in order. */
-		for (devp=&nubus_devices; *devp!=NULL; devp=&((*devp)->next))
+		for (devp = &nubus_devices; *devp != NULL;
+		     devp = &((*devp)->next))
 			/* spin */;
 		*devp = dev;
-		dev->next = NULL;		
+		dev->next = NULL;
 	}
 
 	/* Put it on the global NuBus board chain. Keep entries in order. */
-	for (boardp=&nubus_boards; *boardp!=NULL; boardp=&((*boardp)->next))
+	for (boardp = &nubus_boards; *boardp != NULL;
+	     boardp = &((*boardp)->next))
 		/* spin */;
 	*boardp = board;
 	board->next = NULL;
-	
+
 	return board;
 }
 
 void __init nubus_probe_slot(int slot)
 {
 	unsigned char dp;
-	unsigned char* rp;
+	unsigned char *rp;
 	int i;
 
-	rp = nubus_rom_addr(slot);	
-	for(i = 4; i; i--)
-	{
+	rp = nubus_rom_addr(slot);
+	for (i = 4; i; i--) {
 		int card_present;
 
 		rp--;
@@ -927,7 +897,6 @@ void __init nubus_probe_slot(int slot)
 		if (!card_present)
 			continue;
 
-		printk(KERN_DEBUG "Now probing slot %X at %p\n", slot, rp);
 		dp = *rp;
 		if(dp == 0)
 			continue;
@@ -935,11 +904,11 @@ void __init nubus_probe_slot(int slot)
 		/* The last byte of the format block consists of two
 		   nybbles which are "mirror images" of each other.
 		   These show us the valid bytelanes */
-		if ((((dp>>4) ^ dp) & 0x0F) != 0x0F)
+		if ((((dp >> 4) ^ dp) & 0x0F) != 0x0F)
 			continue;
 		/* Check that this value is actually *on* one of the
 		   bytelanes it claims are valid! */
-		if ((dp & 0x0F) >= (1<<i))
+		if ((dp & 0x0F) >= (1 << i))
 			continue;
 
 		/* Looks promising.  Let's put it on the list. */
@@ -952,19 +921,19 @@ void __init nubus_probe_slot(int slot)
 void __init nubus_scan_bus(void)
 {
 	int slot;
+
 	/* This might not work on your machine */
 #ifdef I_WANT_TO_PROBE_SLOT_ZERO
 	nubus_probe_slot(0);
 #endif
-	for(slot = 9; slot < 15; slot++)
-	{
+	for (slot = 9; slot < 15; slot++) {
 		nubus_probe_slot(slot);
 	}
 }
 
 static int __init nubus_init(void)
 {
-	if (!MACH_IS_MAC) 
+	if (!MACH_IS_MAC)
 		return 0;
 
 	/* Initialize the NuBus interrupts */
@@ -980,11 +949,11 @@ static int __init nubus_init(void)
 	   gurus can fix the real cause of the problem. */
 	mdelay(1000);
 #endif
-	
+
 	/* And probe */
-	printk("NuBus: Scanning NuBus slots.\n");
+	pr_info("NuBus: Scanning NuBus slots.\n");
 	nubus_devices = NULL;
-	nubus_boards  = NULL;
+	nubus_boards = NULL;
 	nubus_scan_bus();
 	nubus_proc_init();
 	return 0;
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 23d4a1728cdf..351bac8f6503 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -934,8 +934,14 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, NULL);
 	if (rc < 0)
 		goto out_unlock;
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+
 	if (copy_to_user(p, buf, buf_len))
 		rc = -EFAULT;
+
+	vfree(buf);
+	return rc;
+
  out_unlock:
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
  out:
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index b3323c0697f6..ca6d572c48fc 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -243,7 +243,15 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
-		if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)) {
+		/*
+		 * FIXME: nsio_rw_bytes() may be called from atomic
+		 * context in the btt case and nvdimm_clear_poison()
+		 * takes a sleeping lock. Until the locking can be
+		 * reworked this capability requires that the namespace
+		 * is not claimed by btt.
+		 */
+		if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)
+				&& (!ndns->claim || !is_nd_btt(ndns->claim))) {
 			long cleared;
 
 			cleared = nvdimm_clear_poison(&ndns->dev, offset, size);
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 0eedc49e0d47..8b721321be5b 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -395,7 +395,7 @@ EXPORT_SYMBOL_GPL(nvdimm_create);
 
 int alias_dpa_busy(struct device *dev, void *data)
 {
-	resource_size_t map_end, blk_start, new, busy;
+	resource_size_t map_end, blk_start, new;
 	struct blk_alloc_info *info = data;
 	struct nd_mapping *nd_mapping;
 	struct nd_region *nd_region;
@@ -436,29 +436,19 @@ int alias_dpa_busy(struct device *dev, void *data)
  retry:
 	/*
 	 * Find the free dpa from the end of the last pmem allocation to
-	 * the end of the interleave-set mapping that is not already
-	 * covered by a blk allocation.
+	 * the end of the interleave-set mapping.
 	 */
-	busy = 0;
 	for_each_dpa_resource(ndd, res) {
+		if (strncmp(res->name, "pmem", 4) != 0)
+			continue;
 		if ((res->start >= blk_start && res->start < map_end)
 				|| (res->end >= blk_start
 					&& res->end <= map_end)) {
-			if (strncmp(res->name, "pmem", 4) == 0) {
-				new = max(blk_start, min(map_end + 1,
-							res->end + 1));
-				if (new != blk_start) {
-					blk_start = new;
-					goto retry;
-				}
-			} else
-				busy += min(map_end, res->end)
-					- max(nd_mapping->start, res->start) + 1;
-		} else if (nd_mapping->start > res->start
-				&& map_end < res->end) {
-			/* total eclipse of the PMEM region mapping */
-			busy += nd_mapping->size;
-			break;
+			new = max(blk_start, min(map_end + 1, res->end + 1));
+			if (new != blk_start) {
+				blk_start = new;
+				goto retry;
+			}
 		}
 	}
 
@@ -470,52 +460,11 @@ int alias_dpa_busy(struct device *dev, void *data)
 		return 1;
 	}
 
-	info->available -= blk_start - nd_mapping->start + busy;
+	info->available -= blk_start - nd_mapping->start;
 
 	return 0;
 }
 
-static int blk_dpa_busy(struct device *dev, void *data)
-{
-	struct blk_alloc_info *info = data;
-	struct nd_mapping *nd_mapping;
-	struct nd_region *nd_region;
-	resource_size_t map_end;
-	int i;
-
-	if (!is_nd_pmem(dev))
-		return 0;
-
-	nd_region = to_nd_region(dev);
-	for (i = 0; i < nd_region->ndr_mappings; i++) {
-		nd_mapping  = &nd_region->mapping[i];
-		if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
-			break;
-	}
-
-	if (i >= nd_region->ndr_mappings)
-		return 0;
-
-	map_end = nd_mapping->start + nd_mapping->size - 1;
-	if (info->res->start >= nd_mapping->start
-			&& info->res->start < map_end) {
-		if (info->res->end <= map_end) {
-			info->busy = 0;
-			return 1;
-		} else {
-			info->busy -= info->res->end - map_end;
-			return 0;
-		}
-	} else if (info->res->end >= nd_mapping->start
-			&& info->res->end <= map_end) {
-		info->busy -= nd_mapping->start - info->res->start;
-		return 0;
-	} else {
-		info->busy -= nd_mapping->size;
-		return 0;
-	}
-}
-
 /**
  * nd_blk_available_dpa - account the unused dpa of BLK region
  * @nd_mapping: container of dpa-resource-root + labels
@@ -545,11 +494,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 	for_each_dpa_resource(ndd, res) {
 		if (strncmp(res->name, "blk", 3) != 0)
 			continue;
-
-		info.res = res;
-		info.busy = resource_size(res);
-		device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy);
-		info.available -= info.busy;
+		info.available -= resource_size(res);
 	}
 
 	return info.available;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 5b536be5a12e..fbc640bf06b0 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -25,6 +25,7 @@
 #include <linux/badblocks.h>
 #include <linux/memremap.h>
 #include <linux/vmalloc.h>
+#include <linux/blk-mq.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/pmem.h>
@@ -231,6 +232,11 @@ static void pmem_release_queue(void *q)
 	blk_cleanup_queue(q);
 }
 
+static void pmem_freeze_queue(void *q)
+{
+	blk_freeze_queue_start(q);
+}
+
 static void pmem_release_disk(void *disk)
 {
 	del_gendisk(disk);
@@ -284,6 +290,9 @@ static int pmem_attach_disk(struct device *dev,
 	if (!q)
 		return -ENOMEM;
 
+	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
+		return -ENOMEM;
+
 	pmem->pfn_flags = PFN_DEV;
 	if (is_nd_pfn(dev)) {
 		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
@@ -303,10 +312,10 @@ static int pmem_attach_disk(struct device *dev,
 				pmem->size, ARCH_MEMREMAP_PMEM);
 
 	/*
-	 * At release time the queue must be dead before
+	 * At release time the queue must be frozen before
 	 * devm_memremap_pages is unwound
 	 */
-	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
+	if (devm_add_action_or_reset(dev, pmem_freeze_queue, q))
 		return -ENOMEM;
 
 	if (IS_ERR(addr))
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9b3b57fef446..d5e0906262ea 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -49,10 +49,9 @@ unsigned char shutdown_timeout = 5;
 module_param(shutdown_timeout, byte, 0644);
 MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
 
-unsigned int nvme_max_retries = 5;
-module_param_named(max_retries, nvme_max_retries, uint, 0644);
+static u8 nvme_max_retries = 5;
+module_param_named(max_retries, nvme_max_retries, byte, 0644);
 MODULE_PARM_DESC(max_retries, "max number of retries a command may have");
-EXPORT_SYMBOL_GPL(nvme_max_retries);
 
 static int nvme_char_major;
 module_param(nvme_char_major, int, 0);
@@ -62,11 +61,66 @@ module_param(default_ps_max_latency_us, ulong, 0644);
 MODULE_PARM_DESC(default_ps_max_latency_us,
 		 "max power saving latency for new devices; use PM QOS to change per device");
 
+static bool force_apst;
+module_param(force_apst, bool, 0644);
+MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
+
 static LIST_HEAD(nvme_ctrl_list);
 static DEFINE_SPINLOCK(dev_list_lock);
 
 static struct class *nvme_class;
 
+static int nvme_error_status(struct request *req)
+{
+	switch (nvme_req(req)->status & 0x7ff) {
+	case NVME_SC_SUCCESS:
+		return 0;
+	case NVME_SC_CAP_EXCEEDED:
+		return -ENOSPC;
+	default:
+		return -EIO;
+
+	/*
+	 * XXX: these errors are a nasty side-band protocol to
+	 * drivers/md/dm-mpath.c:noretry_error() that aren't documented
+	 * anywhere..
+	 */
+	case NVME_SC_CMD_SEQ_ERROR:
+		return -EILSEQ;
+	case NVME_SC_ONCS_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case NVME_SC_WRITE_FAULT:
+	case NVME_SC_READ_ERROR:
+	case NVME_SC_UNWRITTEN_BLOCK:
+		return -ENODATA;
+	}
+}
+
+static inline bool nvme_req_needs_retry(struct request *req)
+{
+	if (blk_noretry_request(req))
+		return false;
+	if (nvme_req(req)->status & NVME_SC_DNR)
+		return false;
+	if (jiffies - req->start_time >= req->timeout)
+		return false;
+	if (nvme_req(req)->retries >= nvme_max_retries)
+		return false;
+	return true;
+}
+
+void nvme_complete_rq(struct request *req)
+{
+	if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) {
+		nvme_req(req)->retries++;
+		blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q));
+		return;
+	}
+
+	blk_mq_end_request(req, nvme_error_status(req));
+}
+EXPORT_SYMBOL_GPL(nvme_complete_rq);
+
 void nvme_cancel_request(struct request *req, void *data, bool reserved)
 {
 	int status;
@@ -80,7 +134,9 @@ void nvme_cancel_request(struct request *req, void *data, bool reserved)
 	status = NVME_SC_ABORT_REQ;
 	if (blk_queue_dying(req->q))
 		status |= NVME_SC_DNR;
-	blk_mq_complete_request(req, status);
+	nvme_req(req)->status = status;
+	blk_mq_complete_request(req);
+
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
 
@@ -205,12 +261,6 @@ fail:
 	return NULL;
 }
 
-void nvme_requeue_req(struct request *req)
-{
-	blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q));
-}
-EXPORT_SYMBOL_GPL(nvme_requeue_req);
-
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags, int qid)
 {
@@ -270,7 +320,7 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
 	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->dsm.nr = segments - 1;
+	cmnd->dsm.nr = cpu_to_le32(segments - 1);
 	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
 	req->special_vec.bv_page = virt_to_page(range);
@@ -327,6 +377,12 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 {
 	int ret = BLK_MQ_RQ_QUEUE_OK;
 
+	if (!(req->rq_flags & RQF_DONTPREP)) {
+		nvme_req(req)->retries = 0;
+		nvme_req(req)->flags = 0;
+		req->rq_flags |= RQF_DONTPREP;
+	}
+
 	switch (req_op(req)) {
 	case REQ_OP_DRV_IN:
 	case REQ_OP_DRV_OUT:
@@ -335,6 +391,8 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		/* currently only aliased to deallocate for a few ctrls: */
 	case REQ_OP_DISCARD:
 		ret = nvme_setup_discard(ns, req, cmd);
 		break;
@@ -378,7 +436,10 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	blk_execute_rq(req->q, NULL, req, at_head);
 	if (result)
 		*result = nvme_req(req)->result;
-	ret = req->errors;
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+		ret = -EINTR;
+	else
+		ret = nvme_req(req)->status;
  out:
 	blk_mq_free_request(req);
 	return ret;
@@ -463,7 +524,10 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 	}
  submit:
 	blk_execute_rq(req->q, disk, req, 0);
-	ret = req->errors;
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+		ret = -EINTR;
+	else
+		ret = nvme_req(req)->status;
 	if (result)
 		*result = le32_to_cpu(nvme_req(req)->result.u32);
 	if (meta && !ret && !write) {
@@ -900,16 +964,14 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	if (ctrl->quirks & NVME_QUIRK_DISCARD_ZEROES)
-		ns->queue->limits.discard_zeroes_data = 1;
-	else
-		ns->queue->limits.discard_zeroes_data = 0;
-
 	ns->queue->limits.discard_alignment = logical_block_size;
 	ns->queue->limits.discard_granularity = logical_block_size;
 	blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
 	blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
+
+	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+		blk_queue_max_write_zeroes_sectors(ns->queue, UINT_MAX);
 }
 
 static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
@@ -1267,7 +1329,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 	 * heuristic: we are willing to spend at most 2% of the time
 	 * transitioning between power states.  Therefore, when running
 	 * in any given state, we will enter the next lower-power
-	 * non-operational state after waiting 100 * (enlat + exlat)
+	 * non-operational state after waiting 50 * (enlat + exlat)
 	 * microseconds, as long as that state's total latency is under
 	 * the requested maximum latency.
 	 *
@@ -1278,6 +1340,8 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 
 	unsigned apste;
 	struct nvme_feat_auto_pst *table;
+	u64 max_lat_us = 0;
+	int max_ps = -1;
 	int ret;
 
 	/*
@@ -1299,6 +1363,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 	if (ctrl->ps_max_latency_us == 0) {
 		/* Turn off APST. */
 		apste = 0;
+		dev_dbg(ctrl->device, "APST disabled\n");
 	} else {
 		__le64 target = cpu_to_le64(0);
 		int state;
@@ -1316,6 +1381,14 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 				table->entries[state] = target;
 
 			/*
+			 * Don't allow transitions to the deepest state
+			 * if it's quirked off.
+			 */
+			if (state == ctrl->npss &&
+			    (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS))
+				continue;
+
+			/*
 			 * Is this state a useful non-operational state for
 			 * higher-power states to autonomously transition to?
 			 */
@@ -1340,9 +1413,22 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 
 			target = cpu_to_le64((state << 3) |
 					     (transition_ms << 8));
+
+			if (max_ps == -1)
+				max_ps = state;
+
+			if (total_latency_us > max_lat_us)
+				max_lat_us = total_latency_us;
 		}
 
 		apste = 1;
+
+		if (max_ps == -1) {
+			dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n");
+		} else {
+			dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n",
+				max_ps, max_lat_us, (int)sizeof(*table), table);
+		}
 	}
 
 	ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste,
@@ -1387,16 +1473,15 @@ struct nvme_core_quirk_entry {
 };
 
 static const struct nvme_core_quirk_entry core_quirks[] = {
-	/*
-	 * Seen on a Samsung "SM951 NVMe SAMSUNG 256GB": using APST causes
-	 * the controller to go out to lunch.  It dies when the watchdog
-	 * timer reads CSTS and gets 0xffffffff.
-	 */
 	{
-		.vid = 0x144d,
-		.fr = "BXW75D0Q",
+		/*
+		 * This Toshiba device seems to die using any APST states.  See:
+		 * https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1678184/comments/11
+		 */
+		.vid = 0x1179,
+		.mn = "THNSF5256GPUK TOSHIBA",
 		.quirks = NVME_QUIRK_NO_APST,
-	},
+	}
 };
 
 /* match is null-terminated but idstr is space-padded. */
@@ -1481,6 +1566,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		}
 	}
 
+	if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
+		dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
+		ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
+	}
+
 	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->vid = le16_to_cpu(id->vid);
 	ctrl->oncs = le16_to_cpup(&id->oncs);
@@ -1503,7 +1593,16 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	ctrl->npss = id->npss;
 	prev_apsta = ctrl->apsta;
-	ctrl->apsta = (ctrl->quirks & NVME_QUIRK_NO_APST) ? 0 : id->apsta;
+	if (ctrl->quirks & NVME_QUIRK_NO_APST) {
+		if (force_apst && id->apsta) {
+			dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
+			ctrl->apsta = 1;
+		} else {
+			ctrl->apsta = 0;
+		}
+	} else {
+		ctrl->apsta = id->apsta;
+	}
 	memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
 
 	if (ctrl->ops->is_fabrics) {
@@ -2386,7 +2485,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 
 	mutex_lock(&ctrl->namespaces_mutex);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
-		blk_mq_freeze_queue_start(ns->queue);
+		blk_freeze_queue_start(ns->queue);
 	mutex_unlock(&ctrl->namespaces_mutex);
 }
 EXPORT_SYMBOL_GPL(nvme_start_freeze);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 5b7386f69f4d..990e6fb32a63 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -471,6 +471,16 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 }
 EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
 
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->opts->max_reconnects != -1 &&
+	    ctrl->opts->nr_reconnects < ctrl->opts->max_reconnects)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(nvmf_should_reconnect);
+
 /**
  * nvmf_register_transport() - NVMe Fabrics Library registration function.
  * @ops:	Transport ops instance to be registered to the
@@ -533,6 +543,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_QUEUE_SIZE,		"queue_size=%d"		},
 	{ NVMF_OPT_NR_IO_QUEUES,	"nr_io_queues=%d"	},
 	{ NVMF_OPT_RECONNECT_DELAY,	"reconnect_delay=%d"	},
+	{ NVMF_OPT_CTRL_LOSS_TMO,	"ctrl_loss_tmo=%d"	},
 	{ NVMF_OPT_KATO,		"keep_alive_tmo=%d"	},
 	{ NVMF_OPT_HOSTNQN,		"hostnqn=%s"		},
 	{ NVMF_OPT_HOST_TRADDR,		"host_traddr=%s"	},
@@ -546,6 +557,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	char *options, *o, *p;
 	int token, ret = 0;
 	size_t nqnlen  = 0;
+	int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
 
 	/* Set defaults */
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
@@ -655,6 +667,16 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			}
 			opts->kato = token;
 			break;
+		case NVMF_OPT_CTRL_LOSS_TMO:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (token < 0)
+				pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n");
+			ctrl_loss_tmo = token;
+			break;
 		case NVMF_OPT_HOSTNQN:
 			if (opts->host) {
 				pr_err("hostnqn already user-assigned: %s\n",
@@ -710,6 +732,12 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 		}
 	}
 
+	if (ctrl_loss_tmo < 0)
+		opts->max_reconnects = -1;
+	else
+		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+						opts->reconnect_delay);
+
 	if (!opts->host) {
 		kref_get(&nvmf_default_host->ref);
 		opts->host = nvmf_default_host;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 156018182ce4..f5a9c1fb186f 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -21,6 +21,8 @@
 #define NVMF_MAX_QUEUE_SIZE	1024
 #define NVMF_DEF_QUEUE_SIZE	128
 #define NVMF_DEF_RECONNECT_DELAY	10
+/* default to 600 seconds of reconnect attempts before giving up */
+#define NVMF_DEF_CTRL_LOSS_TMO		600
 
 /*
  * Define a host as seen by the target.  We allocate one at boot, but also
@@ -53,6 +55,7 @@ enum {
 	NVMF_OPT_HOSTNQN	= 1 << 8,
 	NVMF_OPT_RECONNECT_DELAY = 1 << 9,
 	NVMF_OPT_HOST_TRADDR	= 1 << 10,
+	NVMF_OPT_CTRL_LOSS_TMO	= 1 << 11,
 };
 
 /**
@@ -77,6 +80,10 @@ enum {
  * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN.
  * @kato:	Keep-alive timeout.
  * @host:	Virtual NVMe host, contains the NQN and Host ID.
+ * @nr_reconnects: number of reconnect attempted since the last ctrl failure
+ * @max_reconnects: maximum number of allowed reconnect attempts before removing
+ *              the controller, (-1) means reconnect forever, zero means remove
+ *              immediately;
  */
 struct nvmf_ctrl_options {
 	unsigned		mask;
@@ -91,6 +98,8 @@ struct nvmf_ctrl_options {
 	bool			discovery_nqn;
 	unsigned int		kato;
 	struct nvmf_host	*host;
+	int			nr_reconnects;
+	int			max_reconnects;
 };
 
 /*
@@ -133,5 +142,6 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
 
 #endif /* _NVME_FABRICS_H */
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 9690beb15e69..4976db56e351 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -19,6 +19,7 @@
 #include <linux/parser.h>
 #include <uapi/scsi/fc/fc_fs.h>
 #include <uapi/scsi/fc/fc_els.h>
+#include <linux/delay.h>
 
 #include "nvme.h"
 #include "fabrics.h"
@@ -44,6 +45,8 @@ enum nvme_fc_queue_flags {
 
 #define NVMEFC_QUEUE_DELAY	3		/* ms units */
 
+#define NVME_FC_MAX_CONNECT_ATTEMPTS	1
+
 struct nvme_fc_queue {
 	struct nvme_fc_ctrl	*ctrl;
 	struct device		*dev;
@@ -61,16 +64,24 @@ struct nvme_fc_queue {
 	unsigned long		flags;
 } __aligned(sizeof(u64));	/* alignment for other things alloc'd with */
 
+enum nvme_fcop_flags {
+	FCOP_FLAGS_TERMIO	= (1 << 0),
+	FCOP_FLAGS_RELEASED	= (1 << 1),
+	FCOP_FLAGS_COMPLETE	= (1 << 2),
+	FCOP_FLAGS_AEN		= (1 << 3),
+};
+
 struct nvmefc_ls_req_op {
 	struct nvmefc_ls_req	ls_req;
 
-	struct nvme_fc_ctrl	*ctrl;
+	struct nvme_fc_rport	*rport;
 	struct nvme_fc_queue	*queue;
 	struct request		*rq;
+	u32			flags;
 
 	int			ls_error;
 	struct completion	ls_done;
-	struct list_head	lsreq_list;	/* ctrl->ls_req_list */
+	struct list_head	lsreq_list;	/* rport->ls_req_list */
 	bool			req_queued;
 };
 
@@ -79,6 +90,7 @@ enum nvme_fcpop_state {
 	FCPOP_STATE_IDLE	= 1,
 	FCPOP_STATE_ACTIVE	= 2,
 	FCPOP_STATE_ABORTED	= 3,
+	FCPOP_STATE_COMPLETE	= 4,
 };
 
 struct nvme_fc_fcp_op {
@@ -97,6 +109,7 @@ struct nvme_fc_fcp_op {
 	struct request		*rq;
 
 	atomic_t		state;
+	u32			flags;
 	u32			rqno;
 	u32			nents;
 
@@ -120,23 +133,24 @@ struct nvme_fc_rport {
 
 	struct list_head		endp_list; /* for lport->endp_list */
 	struct list_head		ctrl_list;
+	struct list_head		ls_req_list;
+	struct device			*dev;	/* physical device for dma */
+	struct nvme_fc_lport		*lport;
 	spinlock_t			lock;
 	struct kref			ref;
 } __aligned(sizeof(u64));	/* alignment for other things alloc'd with */
 
-enum nvme_fcctrl_state {
-	FCCTRL_INIT		= 0,
-	FCCTRL_ACTIVE		= 1,
+enum nvme_fcctrl_flags {
+	FCCTRL_TERMIO		= (1 << 0),
 };
 
 struct nvme_fc_ctrl {
 	spinlock_t		lock;
 	struct nvme_fc_queue	*queues;
-	u32			queue_count;
-
 	struct device		*dev;
 	struct nvme_fc_lport	*lport;
 	struct nvme_fc_rport	*rport;
+	u32			queue_count;
 	u32			cnum;
 
 	u64			association_id;
@@ -144,14 +158,19 @@ struct nvme_fc_ctrl {
 	u64			cap;
 
 	struct list_head	ctrl_list;	/* rport->ctrl_list */
-	struct list_head	ls_req_list;
 
 	struct blk_mq_tag_set	admin_tag_set;
 	struct blk_mq_tag_set	tag_set;
 
 	struct work_struct	delete_work;
+	struct work_struct	reset_work;
+	struct delayed_work	connect_work;
+	int			reconnect_delay;
+	int			connect_attempts;
+
 	struct kref		ref;
-	int			state;
+	u32			flags;
+	u32			iocnt;
 
 	struct nvme_fc_fcp_op	aen_ops[NVME_FC_NR_AEN_COMMANDS];
 
@@ -419,9 +438,12 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport,
 
 	INIT_LIST_HEAD(&newrec->endp_list);
 	INIT_LIST_HEAD(&newrec->ctrl_list);
+	INIT_LIST_HEAD(&newrec->ls_req_list);
 	kref_init(&newrec->ref);
 	spin_lock_init(&newrec->lock);
 	newrec->remoteport.localport = &lport->localport;
+	newrec->dev = lport->dev;
+	newrec->lport = lport;
 	newrec->remoteport.private = &newrec[1];
 	newrec->remoteport.port_role = pinfo->port_role;
 	newrec->remoteport.node_name = pinfo->node_name;
@@ -444,7 +466,6 @@ out_kfree_rport:
 out_reghost_failed:
 	*portptr = NULL;
 	return ret;
-
 }
 EXPORT_SYMBOL_GPL(nvme_fc_register_remoteport);
 
@@ -487,6 +508,30 @@ nvme_fc_rport_get(struct nvme_fc_rport *rport)
 	return kref_get_unless_zero(&rport->ref);
 }
 
+static int
+nvme_fc_abort_lsops(struct nvme_fc_rport *rport)
+{
+	struct nvmefc_ls_req_op *lsop;
+	unsigned long flags;
+
+restart:
+	spin_lock_irqsave(&rport->lock, flags);
+
+	list_for_each_entry(lsop, &rport->ls_req_list, lsreq_list) {
+		if (!(lsop->flags & FCOP_FLAGS_TERMIO)) {
+			lsop->flags |= FCOP_FLAGS_TERMIO;
+			spin_unlock_irqrestore(&rport->lock, flags);
+			rport->lport->ops->ls_abort(&rport->lport->localport,
+						&rport->remoteport,
+						&lsop->ls_req);
+			goto restart;
+		}
+	}
+	spin_unlock_irqrestore(&rport->lock, flags);
+
+	return 0;
+}
+
 /**
  * nvme_fc_unregister_remoteport - transport entry point called by an
  *                              LLDD to deregister/remove a previously
@@ -522,6 +567,8 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr)
 
 	spin_unlock_irqrestore(&rport->lock, flags);
 
+	nvme_fc_abort_lsops(rport);
+
 	nvme_fc_rport_put(rport);
 	return 0;
 }
@@ -624,16 +671,16 @@ static int nvme_fc_ctrl_get(struct nvme_fc_ctrl *);
 
 
 static void
-__nvme_fc_finish_ls_req(struct nvme_fc_ctrl *ctrl,
-		struct nvmefc_ls_req_op *lsop)
+__nvme_fc_finish_ls_req(struct nvmefc_ls_req_op *lsop)
 {
+	struct nvme_fc_rport *rport = lsop->rport;
 	struct nvmefc_ls_req *lsreq = &lsop->ls_req;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
+	spin_lock_irqsave(&rport->lock, flags);
 
 	if (!lsop->req_queued) {
-		spin_unlock_irqrestore(&ctrl->lock, flags);
+		spin_unlock_irqrestore(&rport->lock, flags);
 		return;
 	}
 
@@ -641,56 +688,71 @@ __nvme_fc_finish_ls_req(struct nvme_fc_ctrl *ctrl,
 
 	lsop->req_queued = false;
 
-	spin_unlock_irqrestore(&ctrl->lock, flags);
+	spin_unlock_irqrestore(&rport->lock, flags);
 
-	fc_dma_unmap_single(ctrl->dev, lsreq->rqstdma,
+	fc_dma_unmap_single(rport->dev, lsreq->rqstdma,
 				  (lsreq->rqstlen + lsreq->rsplen),
 				  DMA_BIDIRECTIONAL);
 
-	nvme_fc_ctrl_put(ctrl);
+	nvme_fc_rport_put(rport);
 }
 
 static int
-__nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl,
+__nvme_fc_send_ls_req(struct nvme_fc_rport *rport,
 		struct nvmefc_ls_req_op *lsop,
 		void (*done)(struct nvmefc_ls_req *req, int status))
 {
 	struct nvmefc_ls_req *lsreq = &lsop->ls_req;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
-	if (!nvme_fc_ctrl_get(ctrl))
+	if (rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
+		return -ECONNREFUSED;
+
+	if (!nvme_fc_rport_get(rport))
 		return -ESHUTDOWN;
 
 	lsreq->done = done;
-	lsop->ctrl = ctrl;
+	lsop->rport = rport;
 	lsop->req_queued = false;
 	INIT_LIST_HEAD(&lsop->lsreq_list);
 	init_completion(&lsop->ls_done);
 
-	lsreq->rqstdma = fc_dma_map_single(ctrl->dev, lsreq->rqstaddr,
+	lsreq->rqstdma = fc_dma_map_single(rport->dev, lsreq->rqstaddr,
 				  lsreq->rqstlen + lsreq->rsplen,
 				  DMA_BIDIRECTIONAL);
-	if (fc_dma_mapping_error(ctrl->dev, lsreq->rqstdma)) {
-		nvme_fc_ctrl_put(ctrl);
-		dev_err(ctrl->dev,
-			"els request command failed EFAULT.\n");
-		return -EFAULT;
+	if (fc_dma_mapping_error(rport->dev, lsreq->rqstdma)) {
+		ret = -EFAULT;
+		goto out_putrport;
 	}
 	lsreq->rspdma = lsreq->rqstdma + lsreq->rqstlen;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
+	spin_lock_irqsave(&rport->lock, flags);
 
-	list_add_tail(&lsop->lsreq_list, &ctrl->ls_req_list);
+	list_add_tail(&lsop->lsreq_list, &rport->ls_req_list);
 
 	lsop->req_queued = true;
 
-	spin_unlock_irqrestore(&ctrl->lock, flags);
+	spin_unlock_irqrestore(&rport->lock, flags);
 
-	ret = ctrl->lport->ops->ls_req(&ctrl->lport->localport,
-					&ctrl->rport->remoteport, lsreq);
+	ret = rport->lport->ops->ls_req(&rport->lport->localport,
+					&rport->remoteport, lsreq);
 	if (ret)
-		lsop->ls_error = ret;
+		goto out_unlink;
+
+	return 0;
+
+out_unlink:
+	lsop->ls_error = ret;
+	spin_lock_irqsave(&rport->lock, flags);
+	lsop->req_queued = false;
+	list_del(&lsop->lsreq_list);
+	spin_unlock_irqrestore(&rport->lock, flags);
+	fc_dma_unmap_single(rport->dev, lsreq->rqstdma,
+				  (lsreq->rqstlen + lsreq->rsplen),
+				  DMA_BIDIRECTIONAL);
+out_putrport:
+	nvme_fc_rport_put(rport);
 
 	return ret;
 }
@@ -705,15 +767,15 @@ nvme_fc_send_ls_req_done(struct nvmefc_ls_req *lsreq, int status)
 }
 
 static int
-nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
+nvme_fc_send_ls_req(struct nvme_fc_rport *rport, struct nvmefc_ls_req_op *lsop)
 {
 	struct nvmefc_ls_req *lsreq = &lsop->ls_req;
 	struct fcnvme_ls_rjt *rjt = lsreq->rspaddr;
 	int ret;
 
-	ret = __nvme_fc_send_ls_req(ctrl, lsop, nvme_fc_send_ls_req_done);
+	ret = __nvme_fc_send_ls_req(rport, lsop, nvme_fc_send_ls_req_done);
 
-	if (!ret)
+	if (!ret) {
 		/*
 		 * No timeout/not interruptible as we need the struct
 		 * to exist until the lldd calls us back. Thus mandate
@@ -722,14 +784,14 @@ nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
 		 */
 		wait_for_completion(&lsop->ls_done);
 
-	__nvme_fc_finish_ls_req(ctrl, lsop);
+		__nvme_fc_finish_ls_req(lsop);
 
-	if (ret) {
-		dev_err(ctrl->dev,
-			"ls request command failed (%d).\n", ret);
-		return ret;
+		ret = lsop->ls_error;
 	}
 
+	if (ret)
+		return ret;
+
 	/* ACC or RJT payload ? */
 	if (rjt->w0.ls_cmd == FCNVME_LS_RJT)
 		return -ENXIO;
@@ -737,19 +799,14 @@ nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
 	return 0;
 }
 
-static void
-nvme_fc_send_ls_req_async(struct nvme_fc_ctrl *ctrl,
+static int
+nvme_fc_send_ls_req_async(struct nvme_fc_rport *rport,
 		struct nvmefc_ls_req_op *lsop,
 		void (*done)(struct nvmefc_ls_req *req, int status))
 {
-	int ret;
-
-	ret = __nvme_fc_send_ls_req(ctrl, lsop, done);
-
 	/* don't wait for completion */
 
-	if (ret)
-		done(&lsop->ls_req, ret);
+	return __nvme_fc_send_ls_req(rport, lsop, done);
 }
 
 /* Validation Error indexes into the string table below */
@@ -839,7 +896,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 	lsreq->rsplen = sizeof(*assoc_acc);
 	lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
 
-	ret = nvme_fc_send_ls_req(ctrl, lsop);
+	ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
 	if (ret)
 		goto out_free_buffer;
 
@@ -848,11 +905,12 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 	/* validate the ACC response */
 	if (assoc_acc->hdr.w0.ls_cmd != FCNVME_LS_ACC)
 		fcret = VERR_LSACC;
-	if (assoc_acc->hdr.desc_list_len !=
+	else if (assoc_acc->hdr.desc_list_len !=
 			fcnvme_lsdesc_len(
 				sizeof(struct fcnvme_ls_cr_assoc_acc)))
 		fcret = VERR_CR_ASSOC_ACC_LEN;
-	if (assoc_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
+	else if (assoc_acc->hdr.rqst.desc_tag !=
+			cpu_to_be32(FCNVME_LSDESC_RQST))
 		fcret = VERR_LSDESC_RQST;
 	else if (assoc_acc->hdr.rqst.desc_len !=
 			fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst)))
@@ -946,7 +1004,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	lsreq->rsplen = sizeof(*conn_acc);
 	lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
 
-	ret = nvme_fc_send_ls_req(ctrl, lsop);
+	ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
 	if (ret)
 		goto out_free_buffer;
 
@@ -955,10 +1013,10 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	/* validate the ACC response */
 	if (conn_acc->hdr.w0.ls_cmd != FCNVME_LS_ACC)
 		fcret = VERR_LSACC;
-	if (conn_acc->hdr.desc_list_len !=
+	else if (conn_acc->hdr.desc_list_len !=
 			fcnvme_lsdesc_len(sizeof(struct fcnvme_ls_cr_conn_acc)))
 		fcret = VERR_CR_CONN_ACC_LEN;
-	if (conn_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
+	else if (conn_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
 		fcret = VERR_LSDESC_RQST;
 	else if (conn_acc->hdr.rqst.desc_len !=
 			fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst)))
@@ -997,14 +1055,8 @@ static void
 nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status)
 {
 	struct nvmefc_ls_req_op *lsop = ls_req_to_lsop(lsreq);
-	struct nvme_fc_ctrl *ctrl = lsop->ctrl;
 
-	__nvme_fc_finish_ls_req(ctrl, lsop);
-
-	if (status)
-		dev_err(ctrl->dev,
-			"disconnect assoc ls request command failed (%d).\n",
-			status);
+	__nvme_fc_finish_ls_req(lsop);
 
 	/* fc-nvme iniator doesn't care about success or failure of cmd */
 
@@ -1035,6 +1087,7 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 	struct fcnvme_ls_disconnect_acc *discon_acc;
 	struct nvmefc_ls_req_op *lsop;
 	struct nvmefc_ls_req *lsreq;
+	int ret;
 
 	lsop = kzalloc((sizeof(*lsop) +
 			 ctrl->lport->ops->lsrqst_priv_sz +
@@ -1077,7 +1130,10 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 	lsreq->rsplen = sizeof(*discon_acc);
 	lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
 
-	nvme_fc_send_ls_req_async(ctrl, lsop, nvme_fc_disconnect_assoc_done);
+	ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop,
+				nvme_fc_disconnect_assoc_done);
+	if (ret)
+		kfree(lsop);
 
 	/* only meaningful part to terminating the association */
 	ctrl->association_id = 0;
@@ -1086,6 +1142,7 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 
 /* *********************** NVME Ctrl Routines **************************** */
 
+static void __nvme_fc_final_op_cleanup(struct request *rq);
 
 static int
 nvme_fc_reinit_request(void *data, struct request *rq)
@@ -1123,21 +1180,84 @@ nvme_fc_exit_request(void *data, struct request *rq,
 	return __nvme_fc_exit_request(data, op);
 }
 
+static int
+__nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
+{
+	int state;
+
+	state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
+	if (state != FCPOP_STATE_ACTIVE) {
+		atomic_set(&op->state, state);
+		return -ECANCELED;
+	}
+
+	ctrl->lport->ops->fcp_abort(&ctrl->lport->localport,
+					&ctrl->rport->remoteport,
+					op->queue->lldd_handle,
+					&op->fcp_req);
+
+	return 0;
+}
+
 static void
-nvme_fc_exit_aen_ops(struct nvme_fc_ctrl *ctrl)
+nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl)
 {
 	struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops;
-	int i;
+	unsigned long flags;
+	int i, ret;
 
 	for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
-		if (atomic_read(&aen_op->state) == FCPOP_STATE_UNINIT)
+		if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE)
 			continue;
-		__nvme_fc_exit_request(ctrl, aen_op);
-		nvme_fc_ctrl_put(ctrl);
+
+		spin_lock_irqsave(&ctrl->lock, flags);
+		if (ctrl->flags & FCCTRL_TERMIO) {
+			ctrl->iocnt++;
+			aen_op->flags |= FCOP_FLAGS_TERMIO;
+		}
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+
+		ret = __nvme_fc_abort_op(ctrl, aen_op);
+		if (ret) {
+			/*
+			 * if __nvme_fc_abort_op failed the io wasn't
+			 * active. Thus this call path is running in
+			 * parallel to the io complete. Treat as non-error.
+			 */
+
+			/* back out the flags/counters */
+			spin_lock_irqsave(&ctrl->lock, flags);
+			if (ctrl->flags & FCCTRL_TERMIO)
+				ctrl->iocnt--;
+			aen_op->flags &= ~FCOP_FLAGS_TERMIO;
+			spin_unlock_irqrestore(&ctrl->lock, flags);
+			return;
+		}
 	}
 }
 
-void
+static inline int
+__nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
+		struct nvme_fc_fcp_op *op)
+{
+	unsigned long flags;
+	bool complete_rq = false;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
+		if (ctrl->flags & FCCTRL_TERMIO)
+			ctrl->iocnt--;
+	}
+	if (op->flags & FCOP_FLAGS_RELEASED)
+		complete_rq = true;
+	else
+		op->flags |= FCOP_FLAGS_COMPLETE;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	return complete_rq;
+}
+
+static void
 nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 {
 	struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req);
@@ -1146,7 +1266,10 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
 	struct nvme_fc_queue *queue = op->queue;
 	struct nvme_completion *cqe = &op->rsp_iu.cqe;
-	u16 status;
+	struct nvme_command *sqe = &op->cmd_iu.sqe;
+	__le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
+	union nvme_result result;
+	bool complete_rq;
 
 	/*
 	 * WARNING:
@@ -1181,9 +1304,9 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 				sizeof(op->rsp_iu), DMA_FROM_DEVICE);
 
 	if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
-		status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
-	else
-		status = freq->status;
+		status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
+	else if (freq->status)
+		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
 
 	/*
 	 * For the linux implementation, if we have an unsuccesful
@@ -1211,10 +1334,10 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 		 */
 		if (freq->transferred_length !=
 			be32_to_cpu(op->cmd_iu.data_len)) {
-			status = -EIO;
+			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
 			goto done;
 		}
-		op->nreq.result.u64 = 0;
+		result.u64 = 0;
 		break;
 
 	case sizeof(struct nvme_fc_ersp_iu):
@@ -1226,28 +1349,40 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 					(freq->rcv_rsplen / 4) ||
 			     be32_to_cpu(op->rsp_iu.xfrd_len) !=
 					freq->transferred_length ||
-			     op->rqno != le16_to_cpu(cqe->command_id))) {
-			status = -EIO;
+			     op->rsp_iu.status_code ||
+			     sqe->common.command_id != cqe->command_id)) {
+			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
 			goto done;
 		}
-		op->nreq.result = cqe->result;
-		status = le16_to_cpu(cqe->status) >> 1;
+		result = cqe->result;
+		status = cqe->status;
 		break;
 
 	default:
-		status = -EIO;
+		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
 		goto done;
 	}
 
 done:
-	if (!queue->qnum && op->rqno >= AEN_CMDID_BASE) {
-		nvme_complete_async_event(&queue->ctrl->ctrl, status,
-					&op->nreq.result);
+	if (op->flags & FCOP_FLAGS_AEN) {
+		nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
+		complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
+		atomic_set(&op->state, FCPOP_STATE_IDLE);
+		op->flags = FCOP_FLAGS_AEN;	/* clear other flags */
 		nvme_fc_ctrl_put(ctrl);
 		return;
 	}
 
-	blk_mq_complete_request(rq, status);
+	complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
+	if (!complete_rq) {
+		if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
+			status = cpu_to_le16(NVME_SC_ABORT_REQ);
+			if (blk_queue_dying(rq->q))
+				status |= cpu_to_le16(NVME_SC_DNR);
+		}
+		nvme_end_request(rq, status, result);
+	} else
+		__nvme_fc_final_op_cleanup(rq);
 }
 
 static int
@@ -1328,25 +1463,55 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl)
 	struct nvme_fc_fcp_op *aen_op;
 	struct nvme_fc_cmd_iu *cmdiu;
 	struct nvme_command *sqe;
+	void *private;
 	int i, ret;
 
 	aen_op = ctrl->aen_ops;
 	for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
+		private = kzalloc(ctrl->lport->ops->fcprqst_priv_sz,
+						GFP_KERNEL);
+		if (!private)
+			return -ENOMEM;
+
 		cmdiu = &aen_op->cmd_iu;
 		sqe = &cmdiu->sqe;
 		ret = __nvme_fc_init_request(ctrl, &ctrl->queues[0],
 				aen_op, (struct request *)NULL,
 				(AEN_CMDID_BASE + i));
-		if (ret)
+		if (ret) {
+			kfree(private);
 			return ret;
+		}
+
+		aen_op->flags = FCOP_FLAGS_AEN;
+		aen_op->fcp_req.first_sgl = NULL; /* no sg list */
+		aen_op->fcp_req.private = private;
 
 		memset(sqe, 0, sizeof(*sqe));
 		sqe->common.opcode = nvme_admin_async_event;
+		/* Note: core layer may overwrite the sqe.command_id value */
 		sqe->common.command_id = AEN_CMDID_BASE + i;
 	}
 	return 0;
 }
 
+static void
+nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl)
+{
+	struct nvme_fc_fcp_op *aen_op;
+	int i;
+
+	aen_op = ctrl->aen_ops;
+	for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
+		if (!aen_op->fcp_req.private)
+			continue;
+
+		__nvme_fc_exit_request(ctrl, aen_op);
+
+		kfree(aen_op->fcp_req.private);
+		aen_op->fcp_req.private = NULL;
+	}
+}
 
 static inline void
 __nvme_fc_init_hctx(struct blk_mq_hw_ctx *hctx, struct nvme_fc_ctrl *ctrl,
@@ -1446,15 +1611,6 @@ __nvme_fc_delete_hw_queue(struct nvme_fc_ctrl *ctrl,
 }
 
 static void
-nvme_fc_destroy_admin_queue(struct nvme_fc_ctrl *ctrl)
-{
-	__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
-	blk_mq_free_tag_set(&ctrl->admin_tag_set);
-	nvme_fc_free_queue(&ctrl->queues[0]);
-}
-
-static void
 nvme_fc_free_io_queues(struct nvme_fc_ctrl *ctrl)
 {
 	int i;
@@ -1541,19 +1697,27 @@ nvme_fc_ctrl_free(struct kref *ref)
 		container_of(ref, struct nvme_fc_ctrl, ref);
 	unsigned long flags;
 
-	if (ctrl->state != FCCTRL_INIT) {
-		/* remove from rport list */
-		spin_lock_irqsave(&ctrl->rport->lock, flags);
-		list_del(&ctrl->ctrl_list);
-		spin_unlock_irqrestore(&ctrl->rport->lock, flags);
+	if (ctrl->ctrl.tagset) {
+		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_free_tag_set(&ctrl->tag_set);
 	}
 
+	/* remove from rport list */
+	spin_lock_irqsave(&ctrl->rport->lock, flags);
+	list_del(&ctrl->ctrl_list);
+	spin_unlock_irqrestore(&ctrl->rport->lock, flags);
+
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+
+	kfree(ctrl->queues);
+
 	put_device(ctrl->dev);
 	nvme_fc_rport_put(ctrl->rport);
 
-	kfree(ctrl->queues);
 	ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
-	nvmf_free_options(ctrl->ctrl.opts);
+	if (ctrl->ctrl.opts)
+		nvmf_free_options(ctrl->ctrl.opts);
 	kfree(ctrl);
 }
 
@@ -1574,57 +1738,38 @@ nvme_fc_ctrl_get(struct nvme_fc_ctrl *ctrl)
  * controller. Called after last nvme_put_ctrl() call
  */
 static void
-nvme_fc_free_nvme_ctrl(struct nvme_ctrl *nctrl)
+nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
 	WARN_ON(nctrl != &ctrl->ctrl);
 
-	/*
-	 * Tear down the association, which will generate link
-	 * traffic to terminate connections
-	 */
-
-	if (ctrl->state != FCCTRL_INIT) {
-		/* send a Disconnect(association) LS to fc-nvme target */
-		nvme_fc_xmt_disconnect_assoc(ctrl);
-
-		if (ctrl->ctrl.tagset) {
-			blk_cleanup_queue(ctrl->ctrl.connect_q);
-			blk_mq_free_tag_set(&ctrl->tag_set);
-			nvme_fc_delete_hw_io_queues(ctrl);
-			nvme_fc_free_io_queues(ctrl);
-		}
-
-		nvme_fc_exit_aen_ops(ctrl);
-
-		nvme_fc_destroy_admin_queue(ctrl);
-	}
-
 	nvme_fc_ctrl_put(ctrl);
 }
 
-
-static int
-__nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
+static void
+nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 {
-	int state;
+	dev_warn(ctrl->ctrl.device,
+		"NVME-FC{%d}: transport association error detected: %s\n",
+		ctrl->cnum, errmsg);
+	dev_info(ctrl->ctrl.device,
+		"NVME-FC{%d}: resetting controller\n", ctrl->cnum);
 
-	state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
-	if (state != FCPOP_STATE_ACTIVE) {
-		atomic_set(&op->state, state);
-		return -ECANCELED; /* fail */
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+		dev_err(ctrl->ctrl.device,
+			"NVME-FC{%d}: error_recovery: Couldn't change state "
+			"to RECONNECTING\n", ctrl->cnum);
+		return;
 	}
 
-	ctrl->lport->ops->fcp_abort(&ctrl->lport->localport,
-					&ctrl->rport->remoteport,
-					op->queue->lldd_handle,
-					&op->fcp_req);
-
-	return 0;
+	if (!queue_work(nvme_fc_wq, &ctrl->reset_work))
+		dev_err(ctrl->ctrl.device,
+			"NVME-FC{%d}: error_recovery: Failed to schedule "
+			"reset work\n", ctrl->cnum);
 }
 
-enum blk_eh_timer_return
+static enum blk_eh_timer_return
 nvme_fc_timeout(struct request *rq, bool reserved)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
@@ -1640,11 +1785,13 @@ nvme_fc_timeout(struct request *rq, bool reserved)
 		return BLK_EH_HANDLED;
 
 	/*
-	 * TODO: force a controller reset
-	 *   when that happens, queues will be torn down and outstanding
-	 *   ios will be terminated, and the above abort, on a single io
-	 *   will no longer be needed.
+	 * we can't individually ABTS an io without affecting the queue,
+	 * thus killing the queue, adn thus the association.
+	 * So resolve by performing a controller reset, which will stop
+	 * the host/io stack, terminate the association on the link,
+	 * and recreate an association on the link.
 	 */
+	nvme_fc_error_recovery(ctrl, "io timeout error");
 
 	return BLK_EH_HANDLED;
 }
@@ -1738,6 +1885,13 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	u32 csn;
 	int ret;
 
+	/*
+	 * before attempting to send the io, check to see if we believe
+	 * the target device is present
+	 */
+	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
+		return BLK_MQ_RQ_QUEUE_ERROR;
+
 	if (!nvme_fc_ctrl_get(ctrl))
 		return BLK_MQ_RQ_QUEUE_ERROR;
 
@@ -1761,7 +1915,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	op->fcp_req.io_dir = io_dir;
 	op->fcp_req.transferred_length = 0;
 	op->fcp_req.rcv_rsplen = 0;
-	op->fcp_req.status = 0;
+	op->fcp_req.status = NVME_SC_SUCCESS;
 	op->fcp_req.sqid = cpu_to_le16(queue->qnum);
 
 	/*
@@ -1782,14 +1936,9 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
 	sqe->rw.dptr.sgl.addr = 0;
 
-	/* odd that we set the command_id - should come from nvme-fabrics */
-	WARN_ON_ONCE(sqe->common.command_id != cpu_to_le16(op->rqno));
-
-	if (op->rq) {				/* skipped on aens */
+	if (!(op->flags & FCOP_FLAGS_AEN)) {
 		ret = nvme_fc_map_data(ctrl, op->rq, op);
 		if (ret < 0) {
-			dev_err(queue->ctrl->ctrl.device,
-			     "Failed to map data (%d)\n", ret);
 			nvme_cleanup_cmd(op->rq);
 			nvme_fc_ctrl_put(ctrl);
 			return (ret == -ENOMEM || ret == -EAGAIN) ?
@@ -1802,7 +1951,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 
 	atomic_set(&op->state, FCPOP_STATE_ACTIVE);
 
-	if (op->rq)
+	if (!(op->flags & FCOP_FLAGS_AEN))
 		blk_mq_start_request(op->rq);
 
 	ret = ctrl->lport->ops->fcp_io(&ctrl->lport->localport,
@@ -1810,9 +1959,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 					queue->lldd_handle, &op->fcp_req);
 
 	if (ret) {
-		dev_err(ctrl->dev,
-			"Send nvme command failed - lldd returned %d.\n", ret);
-
 		if (op->rq) {			/* normal request */
 			nvme_fc_unmap_data(ctrl, op->rq, op);
 			nvme_cleanup_cmd(op->rq);
@@ -1882,12 +2028,8 @@ nvme_fc_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
 	struct nvme_fc_fcp_op *op;
 
 	req = blk_mq_tag_to_rq(nvme_fc_tagset(queue), tag);
-	if (!req) {
-		dev_err(queue->ctrl->ctrl.device,
-			 "tag 0x%x on QNum %#x not found\n",
-			tag, queue->qnum);
+	if (!req)
 		return 0;
-	}
 
 	op = blk_mq_rq_to_pdu(req);
 
@@ -1904,11 +2046,21 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(arg);
 	struct nvme_fc_fcp_op *aen_op;
+	unsigned long flags;
+	bool terminating = false;
 	int ret;
 
 	if (aer_idx > NVME_FC_NR_AEN_COMMANDS)
 		return;
 
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (ctrl->flags & FCCTRL_TERMIO)
+		terminating = true;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	if (terminating)
+		return;
+
 	aen_op = &ctrl->aen_ops[aer_idx];
 
 	ret = nvme_fc_start_fcp_op(ctrl, aen_op->queue, aen_op, 0,
@@ -1919,36 +2071,101 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
 }
 
 static void
-nvme_fc_complete_rq(struct request *rq)
+__nvme_fc_final_op_cleanup(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
-	int error = 0, state;
 
-	state = atomic_xchg(&op->state, FCPOP_STATE_IDLE);
+	atomic_set(&op->state, FCPOP_STATE_IDLE);
+	op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED |
+			FCOP_FLAGS_COMPLETE);
 
 	nvme_cleanup_cmd(rq);
-
 	nvme_fc_unmap_data(ctrl, rq, op);
+	nvme_complete_rq(rq);
+	nvme_fc_ctrl_put(ctrl);
 
-	if (unlikely(rq->errors)) {
-		if (nvme_req_needs_retry(rq, rq->errors)) {
-			nvme_requeue_req(rq);
-			return;
-		}
+}
 
-		if (blk_rq_is_passthrough(rq))
-			error = rq->errors;
-		else
-			error = nvme_error_status(rq->errors);
+static void
+nvme_fc_complete_rq(struct request *rq)
+{
+	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
+	struct nvme_fc_ctrl *ctrl = op->ctrl;
+	unsigned long flags;
+	bool completed = false;
+
+	/*
+	 * the core layer, on controller resets after calling
+	 * nvme_shutdown_ctrl(), calls complete_rq without our
+	 * calling blk_mq_complete_request(), thus there may still
+	 * be live i/o outstanding with the LLDD. Means transport has
+	 * to track complete calls vs fcpio_done calls to know what
+	 * path to take on completes and dones.
+	 */
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (op->flags & FCOP_FLAGS_COMPLETE)
+		completed = true;
+	else
+		op->flags |= FCOP_FLAGS_RELEASED;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	if (completed)
+		__nvme_fc_final_op_cleanup(rq);
+}
+
+/*
+ * This routine is used by the transport when it needs to find active
+ * io on a queue that is to be terminated. The transport uses
+ * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
+ * this routine to kill them on a 1 by 1 basis.
+ *
+ * As FC allocates FC exchange for each io, the transport must contact
+ * the LLDD to terminate the exchange, thus releasing the FC exchange.
+ * After terminating the exchange the LLDD will call the transport's
+ * normal io done path for the request, but it will have an aborted
+ * status. The done path will return the io request back to the block
+ * layer with an error status.
+ */
+static void
+nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+{
+	struct nvme_ctrl *nctrl = data;
+	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
+	unsigned long flags;
+	int status;
+
+	if (!blk_mq_request_started(req))
+		return;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (ctrl->flags & FCCTRL_TERMIO) {
+		ctrl->iocnt++;
+		op->flags |= FCOP_FLAGS_TERMIO;
 	}
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
-	nvme_fc_ctrl_put(ctrl);
+	status = __nvme_fc_abort_op(ctrl, op);
+	if (status) {
+		/*
+		 * if __nvme_fc_abort_op failed the io wasn't
+		 * active. Thus this call path is running in
+		 * parallel to the io complete. Treat as non-error.
+		 */
 
-	blk_mq_end_request(rq, error);
+		/* back out the flags/counters */
+		spin_lock_irqsave(&ctrl->lock, flags);
+		if (ctrl->flags & FCCTRL_TERMIO)
+			ctrl->iocnt--;
+		op->flags &= ~FCOP_FLAGS_TERMIO;
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+		return;
+	}
 }
 
-static struct blk_mq_ops nvme_fc_mq_ops = {
+
+static const struct blk_mq_ops nvme_fc_mq_ops = {
 	.queue_rq	= nvme_fc_queue_rq,
 	.complete	= nvme_fc_complete_rq,
 	.init_request	= nvme_fc_init_request,
@@ -1959,145 +2176,275 @@ static struct blk_mq_ops nvme_fc_mq_ops = {
 	.timeout	= nvme_fc_timeout,
 };
 
-static struct blk_mq_ops nvme_fc_admin_mq_ops = {
-	.queue_rq	= nvme_fc_queue_rq,
-	.complete	= nvme_fc_complete_rq,
-	.init_request	= nvme_fc_init_admin_request,
-	.exit_request	= nvme_fc_exit_request,
-	.reinit_request	= nvme_fc_reinit_request,
-	.init_hctx	= nvme_fc_init_admin_hctx,
-	.timeout	= nvme_fc_timeout,
-};
-
 static int
-nvme_fc_configure_admin_queue(struct nvme_fc_ctrl *ctrl)
+nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 {
-	u32 segs;
-	int error;
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	int ret;
 
-	nvme_fc_init_queue(ctrl, 0, NVME_FC_AQ_BLKMQ_DEPTH);
+	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+	if (ret) {
+		dev_info(ctrl->ctrl.device,
+			"set_queue_count failed: %d\n", ret);
+		return ret;
+	}
 
-	error = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0],
-				NVME_FC_AQ_BLKMQ_DEPTH,
-				(NVME_FC_AQ_BLKMQ_DEPTH / 4));
-	if (error)
-		return error;
+	ctrl->queue_count = opts->nr_io_queues + 1;
+	if (!opts->nr_io_queues)
+		return 0;
 
-	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
-	ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
-	ctrl->admin_tag_set.queue_depth = NVME_FC_AQ_BLKMQ_DEPTH;
-	ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */
-	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
-	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
+	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
+			opts->nr_io_queues);
+
+	nvme_fc_init_io_queues(ctrl);
+
+	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
+	ctrl->tag_set.ops = &nvme_fc_mq_ops;
+	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
+	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+	ctrl->tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	ctrl->tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
 					(SG_CHUNK_SIZE *
 						sizeof(struct scatterlist)) +
 					ctrl->lport->ops->fcprqst_priv_sz;
-	ctrl->admin_tag_set.driver_data = ctrl;
-	ctrl->admin_tag_set.nr_hw_queues = 1;
-	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
+	ctrl->tag_set.driver_data = ctrl;
+	ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
+	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
 
-	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
-	if (error)
-		goto out_free_queue;
+	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
+	if (ret)
+		return ret;
 
-	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
-	if (IS_ERR(ctrl->ctrl.admin_q)) {
-		error = PTR_ERR(ctrl->ctrl.admin_q);
-		goto out_free_tagset;
+	ctrl->ctrl.tagset = &ctrl->tag_set;
+
+	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
+	if (IS_ERR(ctrl->ctrl.connect_q)) {
+		ret = PTR_ERR(ctrl->ctrl.connect_q);
+		goto out_free_tag_set;
+	}
+
+	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	if (ret)
+		goto out_cleanup_blk_queue;
+
+	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	if (ret)
+		goto out_delete_hw_queues;
+
+	return 0;
+
+out_delete_hw_queues:
+	nvme_fc_delete_hw_io_queues(ctrl);
+out_cleanup_blk_queue:
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	blk_cleanup_queue(ctrl->ctrl.connect_q);
+out_free_tag_set:
+	blk_mq_free_tag_set(&ctrl->tag_set);
+	nvme_fc_free_io_queues(ctrl);
+
+	/* force put free routine to ignore io queues */
+	ctrl->ctrl.tagset = NULL;
+
+	return ret;
+}
+
+static int
+nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
+{
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	int ret;
+
+	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+	if (ret) {
+		dev_info(ctrl->ctrl.device,
+			"set_queue_count failed: %d\n", ret);
+		return ret;
 	}
 
-	error = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
+	/* check for io queues existing */
+	if (ctrl->queue_count == 1)
+		return 0;
+
+	dev_info(ctrl->ctrl.device, "Recreating %d I/O queues.\n",
+			opts->nr_io_queues);
+
+	nvme_fc_init_io_queues(ctrl);
+
+	ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+	if (ret)
+		goto out_free_io_queues;
+
+	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	if (ret)
+		goto out_free_io_queues;
+
+	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	if (ret)
+		goto out_delete_hw_queues;
+
+	return 0;
+
+out_delete_hw_queues:
+	nvme_fc_delete_hw_io_queues(ctrl);
+out_free_io_queues:
+	nvme_fc_free_io_queues(ctrl);
+	return ret;
+}
+
+/*
+ * This routine restarts the controller on the host side, and
+ * on the link side, recreates the controller association.
+ */
+static int
+nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
+{
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	u32 segs;
+	int ret;
+	bool changed;
+
+	ctrl->connect_attempts++;
+
+	/*
+	 * Create the admin queue
+	 */
+
+	nvme_fc_init_queue(ctrl, 0, NVME_FC_AQ_BLKMQ_DEPTH);
+
+	ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
 				NVME_FC_AQ_BLKMQ_DEPTH);
-	if (error)
-		goto out_cleanup_queue;
+	if (ret)
+		goto out_free_queue;
 
-	error = nvmf_connect_admin_queue(&ctrl->ctrl);
-	if (error)
+	ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0],
+				NVME_FC_AQ_BLKMQ_DEPTH,
+				(NVME_FC_AQ_BLKMQ_DEPTH / 4));
+	if (ret)
 		goto out_delete_hw_queue;
 
-	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
-	if (error) {
+	if (ctrl->ctrl.state != NVME_CTRL_NEW)
+		blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
+
+	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
+	if (ret)
+		goto out_disconnect_admin_queue;
+
+	/*
+	 * Check controller capabilities
+	 *
+	 * todo:- add code to check if ctrl attributes changed from
+	 * prior connection values
+	 */
+
+	ret = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (ret) {
 		dev_err(ctrl->ctrl.device,
 			"prop_get NVME_REG_CAP failed\n");
-		goto out_delete_hw_queue;
+		goto out_disconnect_admin_queue;
 	}
 
 	ctrl->ctrl.sqsize =
 		min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
 
-	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
-	if (error)
-		goto out_delete_hw_queue;
+	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+	if (ret)
+		goto out_disconnect_admin_queue;
 
 	segs = min_t(u32, NVME_FC_MAX_SEGMENTS,
 			ctrl->lport->ops->max_sgl_segments);
 	ctrl->ctrl.max_hw_sectors = (segs - 1) << (PAGE_SHIFT - 9);
 
-	error = nvme_init_identify(&ctrl->ctrl);
-	if (error)
-		goto out_delete_hw_queue;
+	ret = nvme_init_identify(&ctrl->ctrl);
+	if (ret)
+		goto out_disconnect_admin_queue;
+
+	/* sanity checks */
+
+	/* FC-NVME does not have other data in the capsule */
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
+				ctrl->ctrl.icdoff);
+		goto out_disconnect_admin_queue;
+	}
 
 	nvme_start_keep_alive(&ctrl->ctrl);
 
-	return 0;
+	/* FC-NVME supports normal SGL Data Block Descriptors */
 
+	if (opts->queue_size > ctrl->ctrl.maxcmd) {
+		/* warn if maxcmd is lower than queue_size */
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl maxcmd %u, reducing "
+			"to queue_size\n",
+			opts->queue_size, ctrl->ctrl.maxcmd);
+		opts->queue_size = ctrl->ctrl.maxcmd;
+	}
+
+	ret = nvme_fc_init_aen_ops(ctrl);
+	if (ret)
+		goto out_term_aen_ops;
+
+	/*
+	 * Create the io queues
+	 */
+
+	if (ctrl->queue_count > 1) {
+		if (ctrl->ctrl.state == NVME_CTRL_NEW)
+			ret = nvme_fc_create_io_queues(ctrl);
+		else
+			ret = nvme_fc_reinit_io_queues(ctrl);
+		if (ret)
+			goto out_term_aen_ops;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	ctrl->connect_attempts = 0;
+
+	kref_get(&ctrl->ctrl.kref);
+
+	if (ctrl->queue_count > 1) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_queue_scan(&ctrl->ctrl);
+		nvme_queue_async_events(&ctrl->ctrl);
+	}
+
+	return 0;	/* Success */
+
+out_term_aen_ops:
+	nvme_fc_term_aen_ops(ctrl);
+	nvme_stop_keep_alive(&ctrl->ctrl);
+out_disconnect_admin_queue:
+	/* send a Disconnect(association) LS to fc-nvme target */
+	nvme_fc_xmt_disconnect_assoc(ctrl);
 out_delete_hw_queue:
 	__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
-out_cleanup_queue:
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
-out_free_tagset:
-	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 out_free_queue:
 	nvme_fc_free_queue(&ctrl->queues[0]);
-	return error;
+
+	return ret;
 }
 
 /*
- * This routine is used by the transport when it needs to find active
- * io on a queue that is to be terminated. The transport uses
- * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
- * this routine to kill them on a 1 by 1 basis.
- *
- * As FC allocates FC exchange for each io, the transport must contact
- * the LLDD to terminate the exchange, thus releasing the FC exchange.
- * After terminating the exchange the LLDD will call the transport's
- * normal io done path for the request, but it will have an aborted
- * status. The done path will return the io request back to the block
- * layer with an error status.
+ * This routine stops operation of the controller on the host side.
+ * On the host os stack side: Admin and IO queues are stopped,
+ *   outstanding ios on them terminated via FC ABTS.
+ * On the link side: the association is terminated.
  */
 static void
-nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
 {
-	struct nvme_ctrl *nctrl = data;
-	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
-	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
-int status;
-
-	if (!blk_mq_request_started(req))
-		return;
+	unsigned long flags;
 
-	/* this performs an ABTS-LS on the FC exchange for the io */
-	status = __nvme_fc_abort_op(ctrl, op);
-	/*
-	 * if __nvme_fc_abort_op failed: io wasn't active to abort
-	 * consider it done. Assume completion path already completing
-	 * in parallel
-	 */
-	if (status)
-		/* io wasn't active to abort consider it done */
-		/* assume completion path already completing in parallel */
-		return;
-}
+	nvme_stop_keep_alive(&ctrl->ctrl);
 
+	spin_lock_irqsave(&ctrl->lock, flags);
+	ctrl->flags |= FCCTRL_TERMIO;
+	ctrl->iocnt = 0;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
-/*
- * This routine stops operation of the controller. Admin and IO queues
- * are stopped, outstanding ios on them terminated, and the nvme ctrl
- * is shutdown.
- */
-static void
-nvme_fc_shutdown_ctrl(struct nvme_fc_ctrl *ctrl)
-{
 	/*
 	 * If io queues are present, stop them and terminate all outstanding
 	 * ios on them. As FC allocates FC exchange for each io, the
@@ -2116,35 +2463,79 @@ nvme_fc_shutdown_ctrl(struct nvme_fc_ctrl *ctrl)
 				nvme_fc_terminate_exchange, &ctrl->ctrl);
 	}
 
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
-		nvme_shutdown_ctrl(&ctrl->ctrl);
+	/*
+	 * Other transports, which don't have link-level contexts bound
+	 * to sqe's, would try to gracefully shutdown the controller by
+	 * writing the registers for shutdown and polling (call
+	 * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
+	 * just aborted and we will wait on those contexts, and given
+	 * there was no indication of how live the controlelr is on the
+	 * link, don't send more io to create more contexts for the
+	 * shutdown. Let the controller fail via keepalive failure if
+	 * its still present.
+	 */
 
 	/*
-	 * now clean up the admin queue. Same thing as above.
+	 * clean up the admin queue. Same thing as above.
 	 * use blk_mq_tagset_busy_itr() and the transport routine to
 	 * terminate the exchanges.
 	 */
 	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_fc_terminate_exchange, &ctrl->ctrl);
+
+	/* kill the aens as they are a separate path */
+	nvme_fc_abort_aen_ops(ctrl);
+
+	/* wait for all io that had to be aborted */
+	spin_lock_irqsave(&ctrl->lock, flags);
+	while (ctrl->iocnt) {
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+		msleep(1000);
+		spin_lock_irqsave(&ctrl->lock, flags);
+	}
+	ctrl->flags &= ~FCCTRL_TERMIO;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	nvme_fc_term_aen_ops(ctrl);
+
+	/*
+	 * send a Disconnect(association) LS to fc-nvme target
+	 * Note: could have been sent at top of process, but
+	 * cleaner on link traffic if after the aborts complete.
+	 * Note: if association doesn't exist, association_id will be 0
+	 */
+	if (ctrl->association_id)
+		nvme_fc_xmt_disconnect_assoc(ctrl);
+
+	if (ctrl->ctrl.tagset) {
+		nvme_fc_delete_hw_io_queues(ctrl);
+		nvme_fc_free_io_queues(ctrl);
+	}
+
+	__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
+	nvme_fc_free_queue(&ctrl->queues[0]);
 }
 
-/*
- * Called to teardown an association.
- * May be called with association fully in place or partially in place.
- */
 static void
-__nvme_fc_remove_ctrl(struct nvme_fc_ctrl *ctrl)
+nvme_fc_delete_ctrl_work(struct work_struct *work)
 {
-	nvme_stop_keep_alive(&ctrl->ctrl);
+	struct nvme_fc_ctrl *ctrl =
+		container_of(work, struct nvme_fc_ctrl, delete_work);
 
-	/* stop and terminate ios on admin and io queues */
-	nvme_fc_shutdown_ctrl(ctrl);
+	cancel_work_sync(&ctrl->reset_work);
+	cancel_delayed_work_sync(&ctrl->connect_work);
+
+	/*
+	 * kill the association on the link side.  this will block
+	 * waiting for io to terminate
+	 */
+	nvme_fc_delete_association(ctrl);
 
 	/*
 	 * tear down the controller
 	 * This will result in the last reference on the nvme ctrl to
-	 * expire, calling the transport nvme_fc_free_nvme_ctrl() callback.
+	 * expire, calling the transport nvme_fc_nvme_ctrl_freed() callback.
 	 * From there, the transport will tear down it's logical queues and
 	 * association.
 	 */
@@ -2153,15 +2544,6 @@ __nvme_fc_remove_ctrl(struct nvme_fc_ctrl *ctrl)
 	nvme_put_ctrl(&ctrl->ctrl);
 }
 
-static void
-nvme_fc_del_ctrl_work(struct work_struct *work)
-{
-	struct nvme_fc_ctrl *ctrl =
-			container_of(work, struct nvme_fc_ctrl, delete_work);
-
-	__nvme_fc_remove_ctrl(ctrl);
-}
-
 static int
 __nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
 {
@@ -2181,25 +2563,85 @@ static int
 nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
-	struct nvme_fc_rport *rport = ctrl->rport;
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&rport->lock, flags);
+	if (!kref_get_unless_zero(&ctrl->ctrl.kref))
+		return -EBUSY;
+
 	ret = __nvme_fc_del_ctrl(ctrl);
-	spin_unlock_irqrestore(&rport->lock, flags);
-	if (ret)
-		return ret;
 
-	flush_work(&ctrl->delete_work);
+	if (!ret)
+		flush_workqueue(nvme_fc_wq);
 
-	return 0;
+	nvme_put_ctrl(&ctrl->ctrl);
+
+	return ret;
+}
+
+static void
+nvme_fc_reset_ctrl_work(struct work_struct *work)
+{
+	struct nvme_fc_ctrl *ctrl =
+			container_of(work, struct nvme_fc_ctrl, reset_work);
+	int ret;
+
+	/* will block will waiting for io to terminate */
+	nvme_fc_delete_association(ctrl);
+
+	ret = nvme_fc_create_association(ctrl);
+	if (ret) {
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
+			ctrl->cnum, ret);
+		if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
+			dev_warn(ctrl->ctrl.device,
+				"NVME-FC{%d}: Max reconnect attempts (%d) "
+				"reached. Removing controller\n",
+				ctrl->cnum, ctrl->connect_attempts);
+
+			if (!nvme_change_ctrl_state(&ctrl->ctrl,
+				NVME_CTRL_DELETING)) {
+				dev_err(ctrl->ctrl.device,
+					"NVME-FC{%d}: failed to change state "
+					"to DELETING\n", ctrl->cnum);
+				return;
+			}
+
+			WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
+			return;
+		}
+
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+			ctrl->cnum, ctrl->reconnect_delay);
+		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+				ctrl->reconnect_delay * HZ);
+	} else
+		dev_info(ctrl->ctrl.device,
+			"NVME-FC{%d}: controller reset complete\n", ctrl->cnum);
 }
 
+/*
+ * called by the nvme core layer, for sysfs interface that requests
+ * a reset of the nvme controller
+ */
 static int
 nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl)
 {
-	return -EIO;
+	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+
+	dev_warn(ctrl->ctrl.device,
+		"NVME-FC{%d}: admin requested controller reset\n", ctrl->cnum);
+
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
+
+	if (!queue_work(nvme_fc_wq, &ctrl->reset_work))
+		return -EBUSY;
+
+	flush_work(&ctrl->reset_work);
+
+	return 0;
 }
 
 static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
@@ -2210,95 +2652,75 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
 	.reset_ctrl		= nvme_fc_reset_nvme_ctrl,
-	.free_ctrl		= nvme_fc_free_nvme_ctrl,
+	.free_ctrl		= nvme_fc_nvme_ctrl_freed,
 	.submit_async_event	= nvme_fc_submit_async_event,
 	.delete_ctrl		= nvme_fc_del_nvme_ctrl,
 	.get_subsysnqn		= nvmf_get_subsysnqn,
 	.get_address		= nvmf_get_address,
 };
 
-static int
-nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
+static void
+nvme_fc_connect_ctrl_work(struct work_struct *work)
 {
-	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 	int ret;
 
-	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
-	if (ret) {
-		dev_info(ctrl->ctrl.device,
-			"set_queue_count failed: %d\n", ret);
-		return ret;
-	}
-
-	ctrl->queue_count = opts->nr_io_queues + 1;
-	if (!opts->nr_io_queues)
-		return 0;
-
-	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
-			opts->nr_io_queues);
-
-	nvme_fc_init_io_queues(ctrl);
-
-	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
-	ctrl->tag_set.ops = &nvme_fc_mq_ops;
-	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
-	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
-	ctrl->tag_set.numa_node = NUMA_NO_NODE;
-	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
-	ctrl->tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
-					(SG_CHUNK_SIZE *
-						sizeof(struct scatterlist)) +
-					ctrl->lport->ops->fcprqst_priv_sz;
-	ctrl->tag_set.driver_data = ctrl;
-	ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
-	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
-
-	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
-	if (ret)
-		return ret;
-
-	ctrl->ctrl.tagset = &ctrl->tag_set;
-
-	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
-	if (IS_ERR(ctrl->ctrl.connect_q)) {
-		ret = PTR_ERR(ctrl->ctrl.connect_q);
-		goto out_free_tag_set;
-	}
-
-	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
-	if (ret)
-		goto out_cleanup_blk_queue;
+	struct nvme_fc_ctrl *ctrl =
+			container_of(to_delayed_work(work),
+				struct nvme_fc_ctrl, connect_work);
 
-	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
-	if (ret)
-		goto out_delete_hw_queues;
+	ret = nvme_fc_create_association(ctrl);
+	if (ret) {
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: Reconnect attempt failed (%d)\n",
+			ctrl->cnum, ret);
+		if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
+			dev_warn(ctrl->ctrl.device,
+				"NVME-FC{%d}: Max reconnect attempts (%d) "
+				"reached. Removing controller\n",
+				ctrl->cnum, ctrl->connect_attempts);
+
+			if (!nvme_change_ctrl_state(&ctrl->ctrl,
+				NVME_CTRL_DELETING)) {
+				dev_err(ctrl->ctrl.device,
+					"NVME-FC{%d}: failed to change state "
+					"to DELETING\n", ctrl->cnum);
+				return;
+			}
 
-	return 0;
+			WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
+			return;
+		}
 
-out_delete_hw_queues:
-	nvme_fc_delete_hw_io_queues(ctrl);
-out_cleanup_blk_queue:
-	nvme_stop_keep_alive(&ctrl->ctrl);
-	blk_cleanup_queue(ctrl->ctrl.connect_q);
-out_free_tag_set:
-	blk_mq_free_tag_set(&ctrl->tag_set);
-	nvme_fc_free_io_queues(ctrl);
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+			ctrl->cnum, ctrl->reconnect_delay);
+		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+				ctrl->reconnect_delay * HZ);
+	} else
+		dev_info(ctrl->ctrl.device,
+			"NVME-FC{%d}: controller reconnect complete\n",
+			ctrl->cnum);
+}
 
-	/* force put free routine to ignore io queues */
-	ctrl->ctrl.tagset = NULL;
 
-	return ret;
-}
+static const struct blk_mq_ops nvme_fc_admin_mq_ops = {
+	.queue_rq	= nvme_fc_queue_rq,
+	.complete	= nvme_fc_complete_rq,
+	.init_request	= nvme_fc_init_admin_request,
+	.exit_request	= nvme_fc_exit_request,
+	.reinit_request	= nvme_fc_reinit_request,
+	.init_hctx	= nvme_fc_init_admin_hctx,
+	.timeout	= nvme_fc_timeout,
+};
 
 
 static struct nvme_ctrl *
-__nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
+nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	struct nvme_fc_lport *lport, struct nvme_fc_rport *rport)
 {
 	struct nvme_fc_ctrl *ctrl;
 	unsigned long flags;
 	int ret, idx;
-	bool changed;
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
 	if (!ctrl) {
@@ -2314,21 +2736,18 @@ __nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->ctrl_list);
-	INIT_LIST_HEAD(&ctrl->ls_req_list);
 	ctrl->lport = lport;
 	ctrl->rport = rport;
 	ctrl->dev = lport->dev;
-	ctrl->state = FCCTRL_INIT;
 	ctrl->cnum = idx;
 
-	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
-	if (ret)
-		goto out_free_ida;
-
 	get_device(ctrl->dev);
 	kref_init(&ctrl->ref);
 
-	INIT_WORK(&ctrl->delete_work, nvme_fc_del_ctrl_work);
+	INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work);
+	INIT_WORK(&ctrl->reset_work, nvme_fc_reset_ctrl_work);
+	INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
+	ctrl->reconnect_delay = opts->reconnect_delay;
 	spin_lock_init(&ctrl->lock);
 
 	/* io queue count */
@@ -2345,87 +2764,87 @@ __nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	ctrl->queues = kcalloc(ctrl->queue_count, sizeof(struct nvme_fc_queue),
 				GFP_KERNEL);
 	if (!ctrl->queues)
-		goto out_uninit_ctrl;
-
-	ret = nvme_fc_configure_admin_queue(ctrl);
-	if (ret)
-		goto out_uninit_ctrl;
-
-	/* sanity checks */
-
-	/* FC-NVME does not have other data in the capsule */
-	if (ctrl->ctrl.icdoff) {
-		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
-				ctrl->ctrl.icdoff);
-		goto out_remove_admin_queue;
-	}
-
-	/* FC-NVME supports normal SGL Data Block Descriptors */
+		goto out_free_ida;
 
-	if (opts->queue_size > ctrl->ctrl.maxcmd) {
-		/* warn if maxcmd is lower than queue_size */
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl maxcmd %u, reducing "
-			"to queue_size\n",
-			opts->queue_size, ctrl->ctrl.maxcmd);
-		opts->queue_size = ctrl->ctrl.maxcmd;
-	}
+	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
+	ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
+	ctrl->admin_tag_set.queue_depth = NVME_FC_AQ_BLKMQ_DEPTH;
+	ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */
+	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
+					(SG_CHUNK_SIZE *
+						sizeof(struct scatterlist)) +
+					ctrl->lport->ops->fcprqst_priv_sz;
+	ctrl->admin_tag_set.driver_data = ctrl;
+	ctrl->admin_tag_set.nr_hw_queues = 1;
+	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
 
-	ret = nvme_fc_init_aen_ops(ctrl);
+	ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
 	if (ret)
-		goto out_exit_aen_ops;
+		goto out_free_queues;
 
-	if (ctrl->queue_count > 1) {
-		ret = nvme_fc_create_io_queues(ctrl);
-		if (ret)
-			goto out_exit_aen_ops;
+	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.admin_q)) {
+		ret = PTR_ERR(ctrl->ctrl.admin_q);
+		goto out_free_admin_tag_set;
 	}
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	ctrl->state = FCCTRL_ACTIVE;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
+	/*
+	 * Would have been nice to init io queues tag set as well.
+	 * However, we require interaction from the controller
+	 * for max io queue count before we can do so.
+	 * Defer this to the connect path.
+	 */
 
-	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
-		ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
+	if (ret)
+		goto out_cleanup_admin_q;
 
-	kref_get(&ctrl->ctrl.kref);
+	/* at this point, teardown path changes to ref counting on nvme ctrl */
 
 	spin_lock_irqsave(&rport->lock, flags);
 	list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
 	spin_unlock_irqrestore(&rport->lock, flags);
 
-	if (opts->nr_io_queues) {
-		nvme_queue_scan(&ctrl->ctrl);
-		nvme_queue_async_events(&ctrl->ctrl);
+	ret = nvme_fc_create_association(ctrl);
+	if (ret) {
+		ctrl->ctrl.opts = NULL;
+		/* initiate nvme ctrl ref counting teardown */
+		nvme_uninit_ctrl(&ctrl->ctrl);
+		nvme_put_ctrl(&ctrl->ctrl);
+
+		/* as we're past the point where we transition to the ref
+		 * counting teardown path, if we return a bad pointer here,
+		 * the calling routine, thinking it's prior to the
+		 * transition, will do an rport put. Since the teardown
+		 * path also does a rport put, we do an extra get here to
+		 * so proper order/teardown happens.
+		 */
+		nvme_fc_rport_get(rport);
+
+		if (ret > 0)
+			ret = -EIO;
+		return ERR_PTR(ret);
 	}
 
-	return &ctrl->ctrl;
+	dev_info(ctrl->ctrl.device,
+		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
+		ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
 
-out_exit_aen_ops:
-	nvme_fc_exit_aen_ops(ctrl);
-out_remove_admin_queue:
-	/* send a Disconnect(association) LS to fc-nvme target */
-	nvme_fc_xmt_disconnect_assoc(ctrl);
-	nvme_stop_keep_alive(&ctrl->ctrl);
-	nvme_fc_destroy_admin_queue(ctrl);
-out_uninit_ctrl:
-	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
-	if (ret > 0)
-		ret = -EIO;
-	/* exit via here will follow ctlr ref point callbacks to free */
-	return ERR_PTR(ret);
+	return &ctrl->ctrl;
 
+out_cleanup_admin_q:
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_free_admin_tag_set:
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+out_free_queues:
+	kfree(ctrl->queues);
 out_free_ida:
+	put_device(ctrl->dev);
 	ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
 out_free_ctrl:
 	kfree(ctrl);
 out_fail:
-	nvme_fc_rport_put(rport);
 	/* exit via here doesn't follow ctlr ref points */
 	return ERR_PTR(ret);
 }
@@ -2497,6 +2916,7 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 {
 	struct nvme_fc_lport *lport;
 	struct nvme_fc_rport *rport;
+	struct nvme_ctrl *ctrl;
 	struct nvmet_fc_traddr laddr = { 0L, 0L };
 	struct nvmet_fc_traddr raddr = { 0L, 0L };
 	unsigned long flags;
@@ -2528,7 +2948,10 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 
 			spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
-			return __nvme_fc_create_ctrl(dev, opts, lport, rport);
+			ctrl = nvme_fc_init_ctrl(dev, opts, lport, rport);
+			if (IS_ERR(ctrl))
+				nvme_fc_rport_put(rport);
+			return ctrl;
 		}
 	}
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
@@ -2546,11 +2969,20 @@ static struct nvmf_transport_ops nvme_fc_transport = {
 
 static int __init nvme_fc_init_module(void)
 {
+	int ret;
+
 	nvme_fc_wq = create_workqueue("nvme_fc_wq");
 	if (!nvme_fc_wq)
 		return -ENOMEM;
 
-	return nvmf_register_transport(&nvme_fc_transport);
+	ret = nvmf_register_transport(&nvme_fc_transport);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	destroy_workqueue(nvme_fc_wq);
+	return ret;
 }
 
 static void __exit nvme_fc_exit_module(void)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 21cac8523bd8..e4e4e60b1224 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -241,9 +241,9 @@ static inline void _nvme_nvm_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 16);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64);
 }
 
 static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
@@ -324,7 +324,7 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 	nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
 	nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
 	memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
-					sizeof(struct nvme_nvm_addr_format));
+					sizeof(struct nvm_addr_format));
 
 	ret = init_grps(nvm_id, nvme_nvm_id);
 out:
@@ -483,8 +483,8 @@ static void nvme_nvm_end_io(struct request *rq, int error)
 {
 	struct nvm_rq *rqd = rq->end_io_data;
 
-	rqd->ppa_status = nvme_req(rq)->result.u64;
-	rqd->error = error;
+	rqd->ppa_status = le64_to_cpu(nvme_req(rq)->result.u64);
+	rqd->error = nvme_req(rq)->status;
 	nvm_end_io(rqd);
 
 	kfree(nvme_req(rq)->cmd);
@@ -510,12 +510,12 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	}
 	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
-	rq->ioprio = bio_prio(bio);
-	if (bio_has_data(bio))
-		rq->nr_phys_segments = bio_phys_segments(q, bio);
-
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
+	if (bio) {
+		blk_init_request_from_bio(rq, bio);
+	} else {
+		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+		rq->__data_len = 0;
+	}
 
 	nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
 
@@ -526,21 +526,6 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	return 0;
 }
 
-static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
-{
-	struct request_queue *q = dev->q;
-	struct nvme_ns *ns = q->queuedata;
-	struct nvme_nvm_command c = {};
-
-	c.erase.opcode = NVM_OP_ERASE;
-	c.erase.nsid = cpu_to_le32(ns->ns_id);
-	c.erase.spba = cpu_to_le64(rqd->ppa_addr.ppa);
-	c.erase.length = cpu_to_le16(rqd->nr_ppas - 1);
-	c.erase.control = cpu_to_le16(rqd->flags);
-
-	return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
-}
-
 static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
@@ -576,7 +561,6 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
 	.set_bb_tbl		= nvme_nvm_set_bb_tbl,
 
 	.submit_io		= nvme_nvm_submit_io,
-	.erase_block		= nvme_nvm_erase_block,
 
 	.create_dma_pool	= nvme_nvm_create_dma_pool,
 	.destroy_dma_pool	= nvme_nvm_destroy_dma_pool,
@@ -611,7 +595,7 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q,
 	__le64 *metadata = NULL;
 	dma_addr_t metadata_dma;
 	DECLARE_COMPLETION_ONSTACK(wait);
-	int ret;
+	int ret = 0;
 
 	rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
 			NVME_QID_ANY);
@@ -681,9 +665,12 @@ submit:
 
 	wait_for_completion_io(&wait);
 
-	ret = nvme_error_status(rq->errors);
+	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
+		ret = -EINTR;
+	else if (nvme_req(rq)->status & 0x7ff)
+		ret = -EIO;
 	if (result)
-		*result = rq->errors & 0x7ff;
+		*result = nvme_req(rq)->status & 0x7ff;
 	if (status)
 		*status = le64_to_cpu(nvme_req(rq)->result.u64);
 
@@ -766,7 +753,7 @@ static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
 	c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
 	/* cdw11-12 */
 	c.ph_rw.length = cpu_to_le16(vcmd.nppas);
-	c.ph_rw.control  = cpu_to_le32(vcmd.control);
+	c.ph_rw.control  = cpu_to_le16(vcmd.control);
 	c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
 	c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
 	c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
@@ -809,6 +796,8 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
 	struct request_queue *q = ns->queue;
 	struct nvm_dev *dev;
 
+	_nvme_nvm_check_size();
+
 	dev = nvm_alloc_dev(node);
 	if (!dev)
 		return -ENOMEM;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2aa20e3e5675..29c708ca9621 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -21,16 +21,6 @@
 #include <linux/lightnvm.h>
 #include <linux/sed-opal.h>
 
-enum {
-	/*
-	 * Driver internal status code for commands that were cancelled due
-	 * to timeouts or controller shutdown.  The value is negative so
-	 * that it a) doesn't overlap with the unsigned hardware error codes,
-	 * and b) can easily be tested for.
-	 */
-	NVME_SC_CANCELLED		= -EINTR,
-};
-
 extern unsigned char nvme_io_timeout;
 #define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
 
@@ -43,8 +33,6 @@ extern unsigned char shutdown_timeout;
 #define NVME_DEFAULT_KATO	5
 #define NVME_KATO_GRACE		10
 
-extern unsigned int nvme_max_retries;
-
 enum {
 	NVME_NS_LBA		= 0,
 	NVME_NS_LIGHTNVM	= 1,
@@ -68,10 +56,10 @@ enum nvme_quirks {
 	NVME_QUIRK_IDENTIFY_CNS			= (1 << 1),
 
 	/*
-	 * The controller deterministically returns O's on reads to discarded
-	 * logical blocks.
+	 * The controller deterministically returns O's on reads to
+	 * logical blocks that deallocate was called on.
 	 */
-	NVME_QUIRK_DISCARD_ZEROES		= (1 << 2),
+	NVME_QUIRK_DEALLOCATE_ZEROES		= (1 << 2),
 
 	/*
 	 * The controller needs a delay before starts checking the device
@@ -83,6 +71,11 @@ enum nvme_quirks {
 	 * APST should not be used.
 	 */
 	NVME_QUIRK_NO_APST			= (1 << 4),
+
+	/*
+	 * The deepest sleep state should not be used.
+	 */
+	NVME_QUIRK_NO_DEEPEST_PS		= (1 << 5),
 };
 
 /*
@@ -92,6 +85,13 @@ enum nvme_quirks {
 struct nvme_request {
 	struct nvme_command	*cmd;
 	union nvme_result	result;
+	u8			retries;
+	u8			flags;
+	u16			status;
+};
+
+enum {
+	NVME_REQ_CANCELLED		= (1 << 0),
 };
 
 static inline struct nvme_request *nvme_req(struct request *req)
@@ -249,25 +249,17 @@ static inline void nvme_cleanup_cmd(struct request *req)
 	}
 }
 
-static inline int nvme_error_status(u16 status)
+static inline void nvme_end_request(struct request *req, __le16 status,
+		union nvme_result result)
 {
-	switch (status & 0x7ff) {
-	case NVME_SC_SUCCESS:
-		return 0;
-	case NVME_SC_CAP_EXCEEDED:
-		return -ENOSPC;
-	default:
-		return -EIO;
-	}
-}
+	struct nvme_request *rq = nvme_req(req);
 
-static inline bool nvme_req_needs_retry(struct request *req, u16 status)
-{
-	return !(status & NVME_SC_DNR || blk_noretry_request(req)) &&
-		(jiffies - req->start_time) < req->timeout &&
-		req->retries < nvme_max_retries;
+	rq->status = le16_to_cpu(status) >> 1;
+	rq->result = result;
+	blk_mq_complete_request(req);
 }
 
+void nvme_complete_rq(struct request *req);
 void nvme_cancel_request(struct request *req, void *data, bool reserved);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state);
@@ -302,7 +294,6 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags, int qid);
-void nvme_requeue_req(struct request *req);
 int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 26a5fd05fe88..c8541c3dcd19 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -19,6 +19,7 @@
 #include <linux/blk-mq-pci.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/genhd.h>
@@ -103,8 +104,22 @@ struct nvme_dev {
 	u32 cmbloc;
 	struct nvme_ctrl ctrl;
 	struct completion ioq_wait;
+	u32 *dbbuf_dbs;
+	dma_addr_t dbbuf_dbs_dma_addr;
+	u32 *dbbuf_eis;
+	dma_addr_t dbbuf_eis_dma_addr;
 };
 
+static inline unsigned int sq_idx(unsigned int qid, u32 stride)
+{
+	return qid * 2 * stride;
+}
+
+static inline unsigned int cq_idx(unsigned int qid, u32 stride)
+{
+	return (qid * 2 + 1) * stride;
+}
+
 static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
 {
 	return container_of(ctrl, struct nvme_dev, ctrl);
@@ -133,6 +148,10 @@ struct nvme_queue {
 	u16 qid;
 	u8 cq_phase;
 	u8 cqe_seen;
+	u32 *dbbuf_sq_db;
+	u32 *dbbuf_cq_db;
+	u32 *dbbuf_sq_ei;
+	u32 *dbbuf_cq_ei;
 };
 
 /*
@@ -171,6 +190,112 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
+	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
+}
+
+static inline unsigned int nvme_dbbuf_size(u32 stride)
+{
+	return ((num_possible_cpus() + 1) * 8 * stride);
+}
+
+static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
+{
+	unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+
+	if (dev->dbbuf_dbs)
+		return 0;
+
+	dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
+					    &dev->dbbuf_dbs_dma_addr,
+					    GFP_KERNEL);
+	if (!dev->dbbuf_dbs)
+		return -ENOMEM;
+	dev->dbbuf_eis = dma_alloc_coherent(dev->dev, mem_size,
+					    &dev->dbbuf_eis_dma_addr,
+					    GFP_KERNEL);
+	if (!dev->dbbuf_eis) {
+		dma_free_coherent(dev->dev, mem_size,
+				  dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
+		dev->dbbuf_dbs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nvme_dbbuf_dma_free(struct nvme_dev *dev)
+{
+	unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+
+	if (dev->dbbuf_dbs) {
+		dma_free_coherent(dev->dev, mem_size,
+				  dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
+		dev->dbbuf_dbs = NULL;
+	}
+	if (dev->dbbuf_eis) {
+		dma_free_coherent(dev->dev, mem_size,
+				  dev->dbbuf_eis, dev->dbbuf_eis_dma_addr);
+		dev->dbbuf_eis = NULL;
+	}
+}
+
+static void nvme_dbbuf_init(struct nvme_dev *dev,
+			    struct nvme_queue *nvmeq, int qid)
+{
+	if (!dev->dbbuf_dbs || !qid)
+		return;
+
+	nvmeq->dbbuf_sq_db = &dev->dbbuf_dbs[sq_idx(qid, dev->db_stride)];
+	nvmeq->dbbuf_cq_db = &dev->dbbuf_dbs[cq_idx(qid, dev->db_stride)];
+	nvmeq->dbbuf_sq_ei = &dev->dbbuf_eis[sq_idx(qid, dev->db_stride)];
+	nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)];
+}
+
+static void nvme_dbbuf_set(struct nvme_dev *dev)
+{
+	struct nvme_command c;
+
+	if (!dev->dbbuf_dbs)
+		return;
+
+	memset(&c, 0, sizeof(c));
+	c.dbbuf.opcode = nvme_admin_dbbuf;
+	c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
+	c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
+
+	if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
+		dev_warn(dev->dev, "unable to set dbbuf\n");
+		/* Free memory and continue on */
+		nvme_dbbuf_dma_free(dev);
+	}
+}
+
+static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old)
+{
+	return (u16)(new_idx - event_idx - 1) < (u16)(new_idx - old);
+}
+
+/* Update dbbuf and return true if an MMIO is required */
+static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
+					      volatile u32 *dbbuf_ei)
+{
+	if (dbbuf_db) {
+		u16 old_value;
+
+		/*
+		 * Ensure that the queue is written before updating
+		 * the doorbell in memory
+		 */
+		wmb();
+
+		old_value = *dbbuf_db;
+		*dbbuf_db = value;
+
+		if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+			return false;
+	}
+
+	return true;
 }
 
 /*
@@ -297,7 +422,9 @@ static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
 
 	if (++tail == nvmeq->q_depth)
 		tail = 0;
-	writel(tail, nvmeq->q_db);
+	if (nvme_dbbuf_update_and_check_event(tail, nvmeq->dbbuf_sq_db,
+					      nvmeq->dbbuf_sq_ei))
+		writel(tail, nvmeq->q_db);
 	nvmeq->sq_tail = tail;
 }
 
@@ -326,10 +453,6 @@ static int nvme_init_iod(struct request *rq, struct nvme_dev *dev)
 	iod->nents = 0;
 	iod->length = size;
 
-	if (!(rq->rq_flags & RQF_DONTPREP)) {
-		rq->retries = 0;
-		rq->rq_flags |= RQF_DONTPREP;
-	}
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
@@ -628,34 +751,12 @@ out_free_cmd:
 	return ret;
 }
 
-static void nvme_complete_rq(struct request *req)
+static void nvme_pci_complete_rq(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	struct nvme_dev *dev = iod->nvmeq->dev;
-	int error = 0;
-
-	nvme_unmap_data(dev, req);
 
-	if (unlikely(req->errors)) {
-		if (nvme_req_needs_retry(req, req->errors)) {
-			req->retries++;
-			nvme_requeue_req(req);
-			return;
-		}
-
-		if (blk_rq_is_passthrough(req))
-			error = req->errors;
-		else
-			error = nvme_error_status(req->errors);
-	}
-
-	if (unlikely(iod->aborted)) {
-		dev_warn(dev->ctrl.device,
-			"completing aborted command with status: %04x\n",
-			req->errors);
-	}
-
-	blk_mq_end_request(req, error);
+	nvme_unmap_data(iod->nvmeq->dev, req);
+	nvme_complete_rq(req);
 }
 
 /* We read the CQE phase first to check if the rest of the entry is valid */
@@ -705,15 +806,16 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag)
 		}
 
 		req = blk_mq_tag_to_rq(*nvmeq->tags, cqe.command_id);
-		nvme_req(req)->result = cqe.result;
-		blk_mq_complete_request(req, le16_to_cpu(cqe.status) >> 1);
+		nvme_end_request(req, cqe.status, cqe.result);
 	}
 
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
 		return;
 
 	if (likely(nvmeq->cq_vector >= 0))
-		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
+		if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
+						      nvmeq->dbbuf_cq_ei))
+			writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
 	nvmeq->cq_head = head;
 	nvmeq->cq_phase = phase;
 
@@ -745,10 +847,8 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 	return IRQ_NONE;
 }
 
-static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
 {
-	struct nvme_queue *nvmeq = hctx->driver_data;
-
 	if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) {
 		spin_lock_irq(&nvmeq->q_lock);
 		__nvme_process_cq(nvmeq, &tag);
@@ -761,6 +861,13 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
 	return 0;
 }
 
+static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+{
+	struct nvme_queue *nvmeq = hctx->driver_data;
+
+	return __nvme_poll(nvmeq, tag);
+}
+
 static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx)
 {
 	struct nvme_dev *dev = to_nvme_dev(ctrl);
@@ -812,7 +919,7 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 						struct nvme_queue *nvmeq)
 {
 	struct nvme_command c;
-	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
+	int flags = NVME_QUEUE_PHYS_CONTIG;
 
 	/*
 	 * Note: we (ab)use the fact the the prp fields survive if no data
@@ -843,9 +950,9 @@ static void abort_endio(struct request *req, int error)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = iod->nvmeq;
-	u16 status = req->errors;
 
-	dev_warn(nvmeq->dev->ctrl.device, "Abort status: 0x%x", status);
+	dev_warn(nvmeq->dev->ctrl.device,
+		 "Abort status: 0x%x", nvme_req(req)->status);
 	atomic_inc(&nvmeq->dev->ctrl.abort_limit);
 	blk_mq_free_request(req);
 }
@@ -859,6 +966,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_command cmd;
 
 	/*
+	 * Did we miss an interrupt?
+	 */
+	if (__nvme_poll(nvmeq, req->tag)) {
+		dev_warn(dev->ctrl.device,
+			 "I/O %d QID %d timeout, completion polled\n",
+			 req->tag, nvmeq->qid);
+		return BLK_EH_HANDLED;
+	}
+
+	/*
 	 * Shutdown immediately if controller times out while starting. The
 	 * reset work will see the pci device disabled when it gets the forced
 	 * cancellation error. All outstanding requests are completed on
@@ -869,7 +986,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_dev_disable(dev, false);
-		req->errors = NVME_SC_CANCELLED;
+		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_HANDLED;
 	}
 
@@ -889,7 +1006,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		 * Mark the request as handled, since the inline shutdown
 		 * forces all outstanding requests to complete.
 		 */
-		req->errors = NVME_SC_CANCELLED;
+		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_HANDLED;
 	}
 
@@ -1097,6 +1214,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+	nvme_dbbuf_init(dev, nvmeq, qid);
 	dev->online_queues++;
 	spin_unlock_irq(&nvmeq->q_lock);
 }
@@ -1129,18 +1247,18 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	return result;
 }
 
-static struct blk_mq_ops nvme_mq_admin_ops = {
+static const struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
-	.complete	= nvme_complete_rq,
+	.complete	= nvme_pci_complete_rq,
 	.init_hctx	= nvme_admin_init_hctx,
 	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_admin_init_request,
 	.timeout	= nvme_timeout,
 };
 
-static struct blk_mq_ops nvme_mq_ops = {
+static const struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
-	.complete	= nvme_complete_rq,
+	.complete	= nvme_pci_complete_rq,
 	.init_hctx	= nvme_init_hctx,
 	.init_request	= nvme_init_request,
 	.map_queues	= nvme_pci_map_queues,
@@ -1569,6 +1687,8 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		if (blk_mq_alloc_tag_set(&dev->tagset))
 			return 0;
 		dev->ctrl.tagset = &dev->tagset;
+
+		nvme_dbbuf_set(dev);
 	} else {
 		blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
 
@@ -1755,6 +1875,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 {
 	struct nvme_dev *dev = to_nvme_dev(ctrl);
 
+	nvme_dbbuf_dma_free(dev);
 	put_device(dev->dev);
 	if (dev->tagset.tags)
 		blk_mq_free_tag_set(&dev->tagset);
@@ -1822,6 +1943,13 @@ static void nvme_reset_work(struct work_struct *work)
 		dev->ctrl.opal_dev = NULL;
 	}
 
+	if (dev->ctrl.oacs & NVME_CTRL_OACS_DBBUF_SUPP) {
+		result = nvme_dbbuf_dma_alloc(dev);
+		if (result)
+			dev_warn(dev->dev,
+				 "unable to allocate dma for dbbuf\n");
+	}
+
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out;
@@ -1943,10 +2071,31 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	return -ENODEV;
 }
 
+static unsigned long check_dell_samsung_bug(struct pci_dev *pdev)
+{
+	if (pdev->vendor == 0x144d && pdev->device == 0xa802) {
+		/*
+		 * Several Samsung devices seem to drop off the PCIe bus
+		 * randomly when APST is on and uses the deepest sleep state.
+		 * This has been observed on a Samsung "SM951 NVMe SAMSUNG
+		 * 256GB", a "PM951 NVMe SAMSUNG 512GB", and a "Samsung SSD
+		 * 950 PRO 256GB", but it seems to be restricted to two Dell
+		 * laptops.
+		 */
+		if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.") &&
+		    (dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") ||
+		     dmi_match(DMI_PRODUCT_NAME, "Precision 5510")))
+			return NVME_QUIRK_NO_DEEPEST_PS;
+	}
+
+	return 0;
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
 	struct nvme_dev *dev;
+	unsigned long quirks = id->driver_data;
 
 	node = dev_to_node(&pdev->dev);
 	if (node == NUMA_NO_NODE)
@@ -1978,8 +2127,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto put_pci;
 
+	quirks |= check_dell_samsung_bug(pdev);
+
 	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
-			id->driver_data);
+			quirks);
 	if (result)
 		goto release_pools;
 
@@ -2135,13 +2286,13 @@ static const struct pci_error_handlers nvme_err_handler = {
 static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x0953),
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DISCARD_ZEROES, },
+				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x0a53),
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DISCARD_ZEROES, },
+				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x0a54),
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DISCARD_ZEROES, },
+				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 779f516e7a4e..29cf88ac3f61 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -34,7 +34,7 @@
 #include "fabrics.h"
 
 
-#define NVME_RDMA_CONNECT_TIMEOUT_MS	1000		/* 1 second */
+#define NVME_RDMA_CONNECT_TIMEOUT_MS	3000		/* 3 second */
 
 #define NVME_RDMA_MAX_SEGMENT_SIZE	0xffffff	/* 24-bit SGL field */
 
@@ -118,7 +118,6 @@ struct nvme_rdma_ctrl {
 
 	struct nvme_rdma_qe	async_event_sqe;
 
-	int			reconnect_delay;
 	struct delayed_work	reconnect_work;
 
 	struct list_head	list;
@@ -129,14 +128,8 @@ struct nvme_rdma_ctrl {
 	u64			cap;
 	u32			max_fr_pages;
 
-	union {
-		struct sockaddr addr;
-		struct sockaddr_in addr_in;
-	};
-	union {
-		struct sockaddr src_addr;
-		struct sockaddr_in src_addr_in;
-	};
+	struct sockaddr_storage addr;
+	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
 };
@@ -343,8 +336,6 @@ static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl,
 	struct ib_device *ibdev = dev->dev;
 	int ret;
 
-	BUG_ON(queue_idx >= ctrl->queue_count);
-
 	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
 			DMA_TO_DEVICE);
 	if (ret)
@@ -571,11 +562,12 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
 		return PTR_ERR(queue->cm_id);
 	}
 
-	queue->cm_error = -ETIMEDOUT;
 	if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
-		src_addr = &ctrl->src_addr;
+		src_addr = (struct sockaddr *)&ctrl->src_addr;
 
-	ret = rdma_resolve_addr(queue->cm_id, src_addr, &ctrl->addr,
+	queue->cm_error = -ETIMEDOUT;
+	ret = rdma_resolve_addr(queue->cm_id, src_addr,
+			(struct sockaddr *)&ctrl->addr,
 			NVME_RDMA_CONNECT_TIMEOUT_MS);
 	if (ret) {
 		dev_info(ctrl->ctrl.device,
@@ -652,8 +644,22 @@ out_free_queues:
 
 static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
 {
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	unsigned int nr_io_queues;
 	int i, ret;
 
+	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+	if (ret)
+		return ret;
+
+	ctrl->queue_count = nr_io_queues + 1;
+	if (ctrl->queue_count < 2)
+		return 0;
+
+	dev_info(ctrl->ctrl.device,
+		"creating %d I/O queues.\n", nr_io_queues);
+
 	for (i = 1; i < ctrl->queue_count; i++) {
 		ret = nvme_rdma_init_queue(ctrl, i,
 					   ctrl->ctrl.opts->queue_size);
@@ -700,6 +706,26 @@ free_ctrl:
 	kfree(ctrl);
 }
 
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+{
+	/* If we are resetting/deleting then do nothing */
+	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+			ctrl->ctrl.state == NVME_CTRL_LIVE);
+		return;
+	}
+
+	if (nvmf_should_reconnect(&ctrl->ctrl)) {
+		dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
+			ctrl->ctrl.opts->reconnect_delay);
+		queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+				ctrl->ctrl.opts->reconnect_delay * HZ);
+	} else {
+		dev_info(ctrl->ctrl.device, "Removing controller...\n");
+		queue_work(nvme_rdma_wq, &ctrl->delete_work);
+	}
+}
+
 static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
@@ -707,6 +733,8 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	bool changed;
 	int ret;
 
+	++ctrl->ctrl.opts->nr_reconnects;
+
 	if (ctrl->queue_count > 1) {
 		nvme_rdma_free_io_queues(ctrl);
 
@@ -751,6 +779,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
+	ctrl->ctrl.opts->nr_reconnects = 0;
 
 	if (ctrl->queue_count > 1) {
 		nvme_start_queues(&ctrl->ctrl);
@@ -765,13 +794,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 stop_admin_q:
 	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
 requeue:
-	/* Make sure we are not resetting/deleting */
-	if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) {
-		dev_info(ctrl->ctrl.device,
-			"Failed reconnect attempt, requeueing...\n");
-		queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
-					ctrl->reconnect_delay * HZ);
-	}
+	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
+			ctrl->ctrl.opts->nr_reconnects);
+	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
 static void nvme_rdma_error_recovery_work(struct work_struct *work)
@@ -798,11 +823,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 
-	dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n",
-		ctrl->reconnect_delay);
-
-	queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
-				ctrl->reconnect_delay * HZ);
+	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
 static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
@@ -1157,8 +1178,7 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
 	    wc->ex.invalidate_rkey == req->mr->rkey)
 		req->mr->need_inval = false;
 
-	req->req.result = cqe->result;
-	blk_mq_complete_request(rq, le16_to_cpu(cqe->status) >> 1);
+	nvme_end_request(rq, cqe->status, cqe->result);
 	return ret;
 }
 
@@ -1395,7 +1415,7 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	nvme_rdma_error_recovery(req->queue->ctrl);
 
 	/* fail with DNR on cmd timeout */
-	rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
 
 	return BLK_EH_HANDLED;
 }
@@ -1497,27 +1517,12 @@ static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
 static void nvme_rdma_complete_rq(struct request *rq)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
-	struct nvme_rdma_queue *queue = req->queue;
-	int error = 0;
-
-	nvme_rdma_unmap_data(queue, rq);
-
-	if (unlikely(rq->errors)) {
-		if (nvme_req_needs_retry(rq, rq->errors)) {
-			nvme_requeue_req(rq);
-			return;
-		}
 
-		if (blk_rq_is_passthrough(rq))
-			error = rq->errors;
-		else
-			error = nvme_error_status(rq->errors);
-	}
-
-	blk_mq_end_request(rq, error);
+	nvme_rdma_unmap_data(req->queue, rq);
+	nvme_complete_rq(rq);
 }
 
-static struct blk_mq_ops nvme_rdma_mq_ops = {
+static const struct blk_mq_ops nvme_rdma_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
 	.init_request	= nvme_rdma_init_request,
@@ -1528,7 +1533,7 @@ static struct blk_mq_ops nvme_rdma_mq_ops = {
 	.timeout	= nvme_rdma_timeout,
 };
 
-static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
+static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
 	.init_request	= nvme_rdma_init_admin_request,
@@ -1594,7 +1599,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl)
 	}
 
 	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+		min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize);
 
 	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
 	if (error)
@@ -1791,20 +1796,8 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
 
 static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
 {
-	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 	int ret;
 
-	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
-	if (ret)
-		return ret;
-
-	ctrl->queue_count = opts->nr_io_queues + 1;
-	if (ctrl->queue_count < 2)
-		return 0;
-
-	dev_info(ctrl->ctrl.device,
-		"creating %d I/O queues.\n", opts->nr_io_queues);
-
 	ret = nvme_rdma_init_io_queues(ctrl);
 	if (ret)
 		return ret;
@@ -1857,27 +1850,13 @@ out_free_io_queues:
 	return ret;
 }
 
-static int nvme_rdma_parse_ipaddr(struct sockaddr_in *in_addr, char *p)
-{
-	u8 *addr = (u8 *)&in_addr->sin_addr.s_addr;
-	size_t buflen = strlen(p);
-
-	/* XXX: handle IPv6 addresses */
-
-	if (buflen > INET_ADDRSTRLEN)
-		return -EINVAL;
-	if (in4_pton(p, buflen, addr, '\0', NULL) == 0)
-		return -EINVAL;
-	in_addr->sin_family = AF_INET;
-	return 0;
-}
-
 static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
 	struct nvme_rdma_ctrl *ctrl;
 	int ret;
 	bool changed;
+	char *port;
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
 	if (!ctrl)
@@ -1885,40 +1864,33 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
 
-	ret = nvme_rdma_parse_ipaddr(&ctrl->addr_in, opts->traddr);
+	if (opts->mask & NVMF_OPT_TRSVCID)
+		port = opts->trsvcid;
+	else
+		port = __stringify(NVME_RDMA_IP_PORT);
+
+	ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
+			opts->traddr, port, &ctrl->addr);
 	if (ret) {
-		pr_err("malformed IP address passed: %s\n", opts->traddr);
+		pr_err("malformed address passed: %s:%s\n", opts->traddr, port);
 		goto out_free_ctrl;
 	}
 
 	if (opts->mask & NVMF_OPT_HOST_TRADDR) {
-		ret = nvme_rdma_parse_ipaddr(&ctrl->src_addr_in,
-				opts->host_traddr);
+		ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
+			opts->host_traddr, NULL, &ctrl->src_addr);
 		if (ret) {
-			pr_err("malformed src IP address passed: %s\n",
+			pr_err("malformed src address passed: %s\n",
 			       opts->host_traddr);
 			goto out_free_ctrl;
 		}
 	}
 
-	if (opts->mask & NVMF_OPT_TRSVCID) {
-		u16 port;
-
-		ret = kstrtou16(opts->trsvcid, 0, &port);
-		if (ret)
-			goto out_free_ctrl;
-
-		ctrl->addr_in.sin_port = cpu_to_be16(port);
-	} else {
-		ctrl->addr_in.sin_port = cpu_to_be16(NVME_RDMA_IP_PORT);
-	}
-
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
 				0 /* no quirks, we're perfect! */);
 	if (ret)
 		goto out_free_ctrl;
 
-	ctrl->reconnect_delay = opts->reconnect_delay;
 	INIT_DELAYED_WORK(&ctrl->reconnect_work,
 			nvme_rdma_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
@@ -1977,7 +1949,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
 	kref_get(&ctrl->ctrl.kref);
@@ -2013,7 +1985,7 @@ static struct nvmf_transport_ops nvme_rdma_transport = {
 	.name		= "rdma",
 	.required_opts	= NVMF_OPT_TRADDR,
 	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
-			  NVMF_OPT_HOST_TRADDR,
+			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO,
 	.create_ctrl	= nvme_rdma_create_ctrl,
 };
 
@@ -2055,12 +2027,20 @@ static int __init nvme_rdma_init_module(void)
 		return -ENOMEM;
 
 	ret = ib_register_client(&nvme_rdma_ib_client);
-	if (ret) {
-		destroy_workqueue(nvme_rdma_wq);
-		return ret;
-	}
+	if (ret)
+		goto err_destroy_wq;
+
+	ret = nvmf_register_transport(&nvme_rdma_transport);
+	if (ret)
+		goto err_unreg_client;
+
+	return 0;
 
-	return nvmf_register_transport(&nvme_rdma_transport);
+err_unreg_client:
+	ib_unregister_client(&nvme_rdma_ib_client);
+err_destroy_wq:
+	destroy_workqueue(nvme_rdma_wq);
+	return ret;
 }
 
 static void __exit nvme_rdma_cleanup_module(void)
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index f49ae2758bb7..1f7671e631dd 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -1609,7 +1609,7 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	struct nvme_command c;
 	u8 opcode = (is_write ? nvme_cmd_write : nvme_cmd_read);
 	u16 control;
-	u32 max_blocks = queue_max_hw_sectors(ns->queue);
+	u32 max_blocks = queue_max_hw_sectors(ns->queue) >> (ns->lba_shift - 9);
 
 	num_cmds = nvme_trans_io_get_num_cmds(hdr, cdb_info, max_blocks);
 
@@ -2138,15 +2138,6 @@ static int nvme_trans_request_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	return res;
 }
 
-static int nvme_trans_security_protocol(struct nvme_ns *ns,
-					struct sg_io_hdr *hdr,
-					u8 *cmd)
-{
-	return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
-				ILLEGAL_REQUEST, SCSI_ASC_ILLEGAL_COMMAND,
-				SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-}
-
 static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr)
 {
@@ -2414,10 +2405,6 @@ static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
 	case REQUEST_SENSE:
 		retcode = nvme_trans_request_sense(ns, hdr, cmd);
 		break;
-	case SECURITY_PROTOCOL_IN:
-	case SECURITY_PROTOCOL_OUT:
-		retcode = nvme_trans_security_protocol(ns, hdr, cmd);
-		break;
 	case SYNCHRONIZE_CACHE:
 		retcode = nvme_trans_synchronize_cache(ns, hdr);
 		break;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index a7bcff45f437..ff1f97006322 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -100,7 +100,7 @@ static u16 nvmet_get_smart_log(struct nvmet_req *req,
 	u16 status;
 
 	WARN_ON(req == NULL || slog == NULL);
-	if (req->cmd->get_log_page.nsid == 0xFFFFFFFF)
+	if (req->cmd->get_log_page.nsid == cpu_to_le32(0xFFFFFFFF))
 		status = nvmet_get_smart_log_all(req, slog);
 	else
 		status = nvmet_get_smart_log_nsid(req, slog);
@@ -121,7 +121,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
 	}
 
 	switch (req->cmd->get_log_page.lid) {
-	case 0x01:
+	case NVME_LOG_ERROR:
 		/*
 		 * We currently never set the More bit in the status field,
 		 * so all error log entries are invalid and can be zeroed out.
@@ -129,7 +129,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
 		 * mandatory log page.
 		 */
 		break;
-	case 0x02:
+	case NVME_LOG_SMART:
 		/*
 		 * XXX: fill out actual smart log
 		 *
@@ -149,7 +149,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
 			goto err;
 		}
 		break;
-	case 0x03:
+	case NVME_LOG_FW_SLOT:
 		/*
 		 * We only support a single firmware slot which always is
 		 * active, so we can zero out the whole firmware slot log and
@@ -480,31 +480,25 @@ static void nvmet_execute_keep_alive(struct nvmet_req *req)
 	nvmet_req_complete(req, 0);
 }
 
-int nvmet_parse_admin_cmd(struct nvmet_req *req)
+u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
+	u16 ret;
 
 	req->ns = NULL;
 
-	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
-		pr_err("nvmet: got admin cmd %d while CC.EN == 0\n",
-				cmd->common.opcode);
-		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
-	}
-	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
-		pr_err("nvmet: got admin cmd %d while CSTS.RDY == 0\n",
-				cmd->common.opcode);
-		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
-	}
+	ret = nvmet_check_ctrl_status(req, cmd);
+	if (unlikely(ret))
+		return ret;
 
 	switch (cmd->common.opcode) {
 	case nvme_admin_get_log_page:
 		req->data_len = nvmet_get_log_page_len(cmd);
 
 		switch (cmd->get_log_page.lid) {
-		case 0x01:
-		case 0x02:
-		case 0x03:
+		case NVME_LOG_ERROR:
+		case NVME_LOG_SMART:
+		case NVME_LOG_FW_SLOT:
 			req->execute = nvmet_execute_get_log_page;
 			return 0;
 		}
@@ -545,6 +539,7 @@ int nvmet_parse_admin_cmd(struct nvmet_req *req)
 		return 0;
 	}
 
-	pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+	pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+	       req->sq->qid);
 	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 }
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 11b0a0a5f661..cf90713043da 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -273,8 +273,8 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 	ns->bdev = blkdev_get_by_path(ns->device_path, FMODE_READ | FMODE_WRITE,
 			NULL);
 	if (IS_ERR(ns->bdev)) {
-		pr_err("nvmet: failed to open block device %s: (%ld)\n",
-			ns->device_path, PTR_ERR(ns->bdev));
+		pr_err("failed to open block device %s: (%ld)\n",
+		       ns->device_path, PTR_ERR(ns->bdev));
 		ret = PTR_ERR(ns->bdev);
 		ns->bdev = NULL;
 		goto out_unlock;
@@ -425,6 +425,13 @@ void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
 	ctrl->sqs[qid] = sq;
 }
 
+static void nvmet_confirm_sq(struct percpu_ref *ref)
+{
+	struct nvmet_sq *sq = container_of(ref, struct nvmet_sq, ref);
+
+	complete(&sq->confirm_done);
+}
+
 void nvmet_sq_destroy(struct nvmet_sq *sq)
 {
 	/*
@@ -433,7 +440,8 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
 	 */
 	if (sq->ctrl && sq->ctrl->sqs && sq->ctrl->sqs[0] == sq)
 		nvmet_async_events_free(sq->ctrl);
-	percpu_ref_kill(&sq->ref);
+	percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq);
+	wait_for_completion(&sq->confirm_done);
 	wait_for_completion(&sq->free_done);
 	percpu_ref_exit(&sq->ref);
 
@@ -461,6 +469,7 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 		return ret;
 	}
 	init_completion(&sq->free_done);
+	init_completion(&sq->confirm_done);
 
 	return 0;
 }
@@ -652,6 +661,23 @@ out:
 	return status;
 }
 
+u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
+{
+	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
+		pr_err("got io cmd %d while CC.EN == 0 on qid = %d\n",
+		       cmd->common.opcode, req->sq->qid);
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+
+	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+		pr_err("got io cmd %d while CSTS.RDY == 0 on qid = %d\n",
+		       cmd->common.opcode, req->sq->qid);
+		req->ns = NULL;
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+	return 0;
+}
+
 static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
 		const char *hostnqn)
 {
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index af8aabf05335..1aaf597e81fc 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -159,15 +159,15 @@ out:
 	nvmet_req_complete(req, status);
 }
 
-int nvmet_parse_discovery_cmd(struct nvmet_req *req)
+u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
 
 	req->ns = NULL;
 
 	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
-		pr_err("nvmet: got cmd %d while not ready\n",
-				cmd->common.opcode);
+		pr_err("got cmd %d while not ready\n",
+		       cmd->common.opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
@@ -180,8 +180,8 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
 			req->execute = nvmet_execute_get_disc_log_page;
 			return 0;
 		default:
-			pr_err("nvmet: unsupported get_log_page lid %d\n",
-				cmd->get_log_page.lid);
+			pr_err("unsupported get_log_page lid %d\n",
+			       cmd->get_log_page.lid);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	case nvme_admin_identify:
@@ -192,17 +192,16 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
 				nvmet_execute_identify_disc_ctrl;
 			return 0;
 		default:
-			pr_err("nvmet: unsupported identify cns %d\n",
-				cmd->identify.cns);
+			pr_err("unsupported identify cns %d\n",
+			       cmd->identify.cns);
 			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	default:
-		pr_err("nvmet: unsupported cmd %d\n",
-				cmd->common.opcode);
+		pr_err("unsupported cmd %d\n", cmd->common.opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
-	pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+	pr_err("unhandled cmd %d\n", cmd->common.opcode);
 	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 }
 
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 8bd022af3df6..3cc17269504b 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -73,7 +73,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
-int nvmet_parse_fabrics_cmd(struct nvmet_req *req)
+u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
 
@@ -122,7 +122,15 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	struct nvmet_ctrl *ctrl = NULL;
 	u16 status = 0;
 
-	d = kmap(sg_page(req->sg)) + req->sg->offset;
+	d = kmalloc(sizeof(*d), GFP_KERNEL);
+	if (!d) {
+		status = NVME_SC_INTERNAL;
+		goto complete;
+	}
+
+	status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+	if (status)
+		goto out;
 
 	/* zero out initial completion result, assign values as needed */
 	req->rsp->result.u32 = 0;
@@ -143,7 +151,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	}
 
 	status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
-			le32_to_cpu(c->kato), &ctrl);
+				  le32_to_cpu(c->kato), &ctrl);
 	if (status)
 		goto out;
 
@@ -158,7 +166,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	req->rsp->result.u16 = cpu_to_le16(ctrl->cntlid);
 
 out:
-	kunmap(sg_page(req->sg));
+	kfree(d);
+complete:
 	nvmet_req_complete(req, status);
 }
 
@@ -170,7 +179,15 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	u16 qid = le16_to_cpu(c->qid);
 	u16 status = 0;
 
-	d = kmap(sg_page(req->sg)) + req->sg->offset;
+	d = kmalloc(sizeof(*d), GFP_KERNEL);
+	if (!d) {
+		status = NVME_SC_INTERNAL;
+		goto complete;
+	}
+
+	status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+	if (status)
+		goto out;
 
 	/* zero out initial completion result, assign values as needed */
 	req->rsp->result.u32 = 0;
@@ -183,8 +200,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	}
 
 	status = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
-			le16_to_cpu(d->cntlid),
-			req, &ctrl);
+				     le16_to_cpu(d->cntlid),
+				     req, &ctrl);
 	if (status)
 		goto out;
 
@@ -205,7 +222,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	pr_info("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid);
 
 out:
-	kunmap(sg_page(req->sg));
+	kfree(d);
+complete:
 	nvmet_req_complete(req, status);
 	return;
 
@@ -214,7 +232,7 @@ out_ctrl_put:
 	goto out;
 }
 
-int nvmet_parse_connect_cmd(struct nvmet_req *req)
+u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
 
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 8f483ee7868c..62eba29c85fb 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -82,10 +82,13 @@ struct nvmet_fc_fcp_iod {
 	enum nvmet_fcp_datadir		io_dir;
 	bool				active;
 	bool				abort;
+	bool				aborted;
+	bool				writedataactive;
 	spinlock_t			flock;
 
 	struct nvmet_req		req;
 	struct work_struct		work;
+	struct work_struct		done_work;
 
 	struct nvmet_fc_tgtport		*tgtport;
 	struct nvmet_fc_tgt_queue	*queue;
@@ -116,7 +119,7 @@ struct nvmet_fc_tgt_queue {
 	u16				qid;
 	u16				sqsize;
 	u16				ersp_ratio;
-	u16				sqhd;
+	__le16				sqhd;
 	int				cpu;
 	atomic_t			connected;
 	atomic_t			sqtail;
@@ -213,6 +216,7 @@ static DEFINE_IDA(nvmet_fc_tgtport_cnt);
 
 static void nvmet_fc_handle_ls_rqst_work(struct work_struct *work);
 static void nvmet_fc_handle_fcp_rqst_work(struct work_struct *work);
+static void nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work);
 static void nvmet_fc_tgt_a_put(struct nvmet_fc_tgt_assoc *assoc);
 static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
 static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
@@ -414,9 +418,13 @@ nvmet_fc_prep_fcp_iodlist(struct nvmet_fc_tgtport *tgtport,
 
 	for (i = 0; i < queue->sqsize; fod++, i++) {
 		INIT_WORK(&fod->work, nvmet_fc_handle_fcp_rqst_work);
+		INIT_WORK(&fod->done_work, nvmet_fc_fcp_rqst_op_done_work);
 		fod->tgtport = tgtport;
 		fod->queue = queue;
 		fod->active = false;
+		fod->abort = false;
+		fod->aborted = false;
+		fod->fcpreq = NULL;
 		list_add_tail(&fod->fcp_list, &queue->fod_list);
 		spin_lock_init(&fod->flock);
 
@@ -463,7 +471,6 @@ nvmet_fc_alloc_fcp_iod(struct nvmet_fc_tgt_queue *queue)
 	if (fod) {
 		list_del(&fod->fcp_list);
 		fod->active = true;
-		fod->abort = false;
 		/*
 		 * no queue reference is taken, as it was taken by the
 		 * queue lookup just prior to the allocation. The iod
@@ -479,17 +486,30 @@ static void
 nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue,
 			struct nvmet_fc_fcp_iod *fod)
 {
+	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+	struct nvmet_fc_tgtport *tgtport = fod->tgtport;
 	unsigned long flags;
 
+	fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
+				sizeof(fod->rspiubuf), DMA_TO_DEVICE);
+
+	fcpreq->nvmet_fc_private = NULL;
+
 	spin_lock_irqsave(&queue->qlock, flags);
 	list_add_tail(&fod->fcp_list, &fod->queue->fod_list);
 	fod->active = false;
+	fod->abort = false;
+	fod->aborted = false;
+	fod->writedataactive = false;
+	fod->fcpreq = NULL;
 	spin_unlock_irqrestore(&queue->qlock, flags);
 
 	/*
 	 * release the reference taken at queue lookup and fod allocation
 	 */
 	nvmet_fc_tgt_q_put(queue);
+
+	tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq);
 }
 
 static int
@@ -616,32 +636,12 @@ nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue)
 
 
 static void
-nvmet_fc_abort_op(struct nvmet_fc_tgtport *tgtport,
-				struct nvmefc_tgt_fcp_req *fcpreq)
-{
-	int ret;
-
-	fcpreq->op = NVMET_FCOP_ABORT;
-	fcpreq->offset = 0;
-	fcpreq->timeout = 0;
-	fcpreq->transfer_length = 0;
-	fcpreq->transferred_length = 0;
-	fcpreq->fcp_error = 0;
-	fcpreq->sg_cnt = 0;
-
-	ret = tgtport->ops->fcp_op(&tgtport->fc_target_port, fcpreq);
-	if (ret)
-		/* should never reach here !! */
-		WARN_ON(1);
-}
-
-
-static void
 nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue)
 {
+	struct nvmet_fc_tgtport *tgtport = queue->assoc->tgtport;
 	struct nvmet_fc_fcp_iod *fod = queue->fod;
 	unsigned long flags;
-	int i;
+	int i, writedataactive;
 	bool disconnect;
 
 	disconnect = atomic_xchg(&queue->connected, 0);
@@ -652,7 +652,20 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue)
 		if (fod->active) {
 			spin_lock(&fod->flock);
 			fod->abort = true;
+			writedataactive = fod->writedataactive;
 			spin_unlock(&fod->flock);
+			/*
+			 * only call lldd abort routine if waiting for
+			 * writedata. other outstanding ops should finish
+			 * on their own.
+			 */
+			if (writedataactive) {
+				spin_lock(&fod->flock);
+				fod->aborted = true;
+				spin_unlock(&fod->flock);
+				tgtport->ops->fcp_abort(
+					&tgtport->fc_target_port, fod->fcpreq);
+			}
 		}
 	}
 	spin_unlock_irqrestore(&queue->qlock, flags);
@@ -846,7 +859,8 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	int ret, idx;
 
 	if (!template->xmt_ls_rsp || !template->fcp_op ||
-	    !template->targetport_delete ||
+	    !template->fcp_abort ||
+	    !template->fcp_req_release || !template->targetport_delete ||
 	    !template->max_hw_queues || !template->max_sgl_segments ||
 	    !template->max_dif_sgl_segments || !template->dma_boundary) {
 		ret = -EINVAL;
@@ -1044,7 +1058,7 @@ EXPORT_SYMBOL_GPL(nvmet_fc_unregister_targetport);
 
 
 static void
-nvmet_fc_format_rsp_hdr(void *buf, u8 ls_cmd, u32 desc_len, u8 rqst_ls_cmd)
+nvmet_fc_format_rsp_hdr(void *buf, u8 ls_cmd, __be32 desc_len, u8 rqst_ls_cmd)
 {
 	struct fcnvme_ls_acc_hdr *acc = buf;
 
@@ -1189,8 +1203,8 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport,
 			validation_errors[ret]);
 		iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
 				NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
-				ELS_RJT_LOGIC,
-				ELS_EXPL_NONE, 0);
+				FCNVME_RJT_RC_LOGIC,
+				FCNVME_RJT_EXP_NONE, 0);
 		return;
 	}
 
@@ -1281,8 +1295,9 @@ nvmet_fc_ls_create_connection(struct nvmet_fc_tgtport *tgtport,
 		iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
 				NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
 				(ret == VERR_NO_ASSOC) ?
-						ELS_RJT_PROT : ELS_RJT_LOGIC,
-				ELS_EXPL_NONE, 0);
+					FCNVME_RJT_RC_INV_ASSOC :
+					FCNVME_RJT_RC_LOGIC,
+				FCNVME_RJT_EXP_NONE, 0);
 		return;
 	}
 
@@ -1369,8 +1384,12 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			validation_errors[ret]);
 		iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
 				NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
-				(ret == 8) ? ELS_RJT_PROT : ELS_RJT_LOGIC,
-				ELS_EXPL_NONE, 0);
+				(ret == VERR_NO_ASSOC) ?
+					FCNVME_RJT_RC_INV_ASSOC :
+					(ret == VERR_NO_CONN) ?
+						FCNVME_RJT_RC_INV_CONN :
+						FCNVME_RJT_RC_LOGIC,
+				FCNVME_RJT_EXP_NONE, 0);
 		return;
 	}
 
@@ -1479,7 +1498,7 @@ nvmet_fc_handle_ls_rqst(struct nvmet_fc_tgtport *tgtport,
 	default:
 		iod->lsreq->rsplen = nvmet_fc_format_rjt(iod->rspbuf,
 				NVME_FC_MAX_LS_BUFFER_SIZE, w0->ls_cmd,
-				ELS_RJT_INVAL, ELS_EXPL_NONE, 0);
+				FCNVME_RJT_RC_INVAL, FCNVME_RJT_EXP_NONE, 0);
 	}
 
 	nvmet_fc_xmt_ls_rsp(tgtport, iod);
@@ -1619,6 +1638,8 @@ nvmet_fc_free_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
 	for_each_sg(fod->data_sg, sg, fod->data_sg_cnt, count)
 		__free_page(sg_page(sg));
 	kfree(fod->data_sg);
+	fod->data_sg = NULL;
+	fod->data_sg_cnt = 0;
 }
 
 
@@ -1679,7 +1700,7 @@ nvmet_fc_prep_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
 	    xfr_length != fod->total_length ||
 	    (le16_to_cpu(cqe->status) & 0xFFFE) || cqewd[0] || cqewd[1] ||
 	    (sqe->flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND)) ||
-	    queue_90percent_full(fod->queue, cqe->sq_head))
+	    queue_90percent_full(fod->queue, le16_to_cpu(cqe->sq_head)))
 		send_ersp = true;
 
 	/* re-set the fields */
@@ -1704,6 +1725,26 @@ nvmet_fc_prep_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
 static void nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq);
 
 static void
+nvmet_fc_abort_op(struct nvmet_fc_tgtport *tgtport,
+				struct nvmet_fc_fcp_iod *fod)
+{
+	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+
+	/* data no longer needed */
+	nvmet_fc_free_tgt_pgs(fod);
+
+	/*
+	 * if an ABTS was received or we issued the fcp_abort early
+	 * don't call abort routine again.
+	 */
+	/* no need to take lock - lock was taken earlier to get here */
+	if (!fod->aborted)
+		tgtport->ops->fcp_abort(&tgtport->fc_target_port, fcpreq);
+
+	nvmet_fc_free_fcp_iod(fod->queue, fod);
+}
+
+static void
 nvmet_fc_xmt_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
 				struct nvmet_fc_fcp_iod *fod)
 {
@@ -1716,7 +1757,7 @@ nvmet_fc_xmt_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
 
 	ret = tgtport->ops->fcp_op(&tgtport->fc_target_port, fod->fcpreq);
 	if (ret)
-		nvmet_fc_abort_op(tgtport, fod->fcpreq);
+		nvmet_fc_abort_op(tgtport, fod);
 }
 
 static void
@@ -1725,6 +1766,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 {
 	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
 	struct scatterlist *sg, *datasg;
+	unsigned long flags;
 	u32 tlen, sg_off;
 	int ret;
 
@@ -1789,10 +1831,13 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 		 */
 		fod->abort = true;
 
-		if (op == NVMET_FCOP_WRITEDATA)
+		if (op == NVMET_FCOP_WRITEDATA) {
+			spin_lock_irqsave(&fod->flock, flags);
+			fod->writedataactive = false;
+			spin_unlock_irqrestore(&fod->flock, flags);
 			nvmet_req_complete(&fod->req,
 					NVME_SC_FC_TRANSPORT_ERROR);
-		else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
+		} else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
 			fcpreq->fcp_error = ret;
 			fcpreq->transferred_length = 0;
 			nvmet_fc_xmt_fcp_op_done(fod->fcpreq);
@@ -1800,32 +1845,54 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 	}
 }
 
+static inline bool
+__nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort)
+{
+	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+	struct nvmet_fc_tgtport *tgtport = fod->tgtport;
+
+	/* if in the middle of an io and we need to tear down */
+	if (abort) {
+		if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
+			nvmet_req_complete(&fod->req,
+					NVME_SC_FC_TRANSPORT_ERROR);
+			return true;
+		}
+
+		nvmet_fc_abort_op(tgtport, fod);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * actual done handler for FCP operations when completed by the lldd
+ */
 static void
-nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
+nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 {
-	struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
 	struct nvmet_fc_tgtport *tgtport = fod->tgtport;
 	unsigned long flags;
 	bool abort;
 
 	spin_lock_irqsave(&fod->flock, flags);
 	abort = fod->abort;
+	fod->writedataactive = false;
 	spin_unlock_irqrestore(&fod->flock, flags);
 
-	/* if in the middle of an io and we need to tear down */
-	if (abort && fcpreq->op != NVMET_FCOP_ABORT) {
-		/* data no longer needed */
-		nvmet_fc_free_tgt_pgs(fod);
-
-		nvmet_req_complete(&fod->req, fcpreq->fcp_error);
-		return;
-	}
-
 	switch (fcpreq->op) {
 
 	case NVMET_FCOP_WRITEDATA:
+		if (__nvmet_fc_fod_op_abort(fod, abort))
+			return;
 		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
+			spin_lock(&fod->flock);
+			fod->abort = true;
+			spin_unlock(&fod->flock);
+
 			nvmet_req_complete(&fod->req,
 					NVME_SC_FC_TRANSPORT_ERROR);
 			return;
@@ -1833,6 +1900,10 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 
 		fod->offset += fcpreq->transferred_length;
 		if (fod->offset != fod->total_length) {
+			spin_lock_irqsave(&fod->flock, flags);
+			fod->writedataactive = true;
+			spin_unlock_irqrestore(&fod->flock, flags);
+
 			/* transfer the next chunk */
 			nvmet_fc_transfer_fcp_data(tgtport, fod,
 						NVMET_FCOP_WRITEDATA);
@@ -1847,12 +1918,11 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 
 	case NVMET_FCOP_READDATA:
 	case NVMET_FCOP_READDATA_RSP:
+		if (__nvmet_fc_fod_op_abort(fod, abort))
+			return;
 		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
-			/* data no longer needed */
-			nvmet_fc_free_tgt_pgs(fod);
-
-			nvmet_fc_abort_op(tgtport, fod->fcpreq);
+			nvmet_fc_abort_op(tgtport, fod);
 			return;
 		}
 
@@ -1861,8 +1931,6 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 		if (fcpreq->op == NVMET_FCOP_READDATA_RSP) {
 			/* data no longer needed */
 			nvmet_fc_free_tgt_pgs(fod);
-			fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
-					sizeof(fod->rspiubuf), DMA_TO_DEVICE);
 			nvmet_fc_free_fcp_iod(fod->queue, fod);
 			return;
 		}
@@ -1885,19 +1953,38 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
 		break;
 
 	case NVMET_FCOP_RSP:
-	case NVMET_FCOP_ABORT:
-		fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
-				sizeof(fod->rspiubuf), DMA_TO_DEVICE);
+		if (__nvmet_fc_fod_op_abort(fod, abort))
+			return;
 		nvmet_fc_free_fcp_iod(fod->queue, fod);
 		break;
 
 	default:
-		nvmet_fc_free_tgt_pgs(fod);
-		nvmet_fc_abort_op(tgtport, fod->fcpreq);
 		break;
 	}
 }
 
+static void
+nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work)
+{
+	struct nvmet_fc_fcp_iod *fod =
+		container_of(work, struct nvmet_fc_fcp_iod, done_work);
+
+	nvmet_fc_fod_op_done(fod);
+}
+
+static void
+nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
+{
+	struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+	struct nvmet_fc_tgt_queue *queue = fod->queue;
+
+	if (fod->tgtport->ops->target_features & NVMET_FCTGTFEAT_OPDONE_IN_ISR)
+		/* context switch so completion is not in ISR context */
+		queue_work_on(queue->cpu, queue->work_q, &fod->done_work);
+	else
+		nvmet_fc_fod_op_done(fod);
+}
+
 /*
  * actual completion handler after execution by the nvmet layer
  */
@@ -1919,10 +2006,7 @@ __nvmet_fc_fcp_nvme_cmd_done(struct nvmet_fc_tgtport *tgtport,
 		fod->queue->sqhd = cqe->sq_head;
 
 	if (abort) {
-		/* data no longer needed */
-		nvmet_fc_free_tgt_pgs(fod);
-
-		nvmet_fc_abort_op(tgtport, fod->fcpreq);
+		nvmet_fc_abort_op(tgtport, fod);
 		return;
 	}
 
@@ -1971,7 +2055,7 @@ nvmet_fc_fcp_nvme_cmd_done(struct nvmet_req *nvme_req)
 /*
  * Actual processing routine for received FC-NVME LS Requests from the LLD
  */
-void
+static void
 nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 			struct nvmet_fc_fcp_iod *fod)
 {
@@ -2018,8 +2102,8 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 				&fod->queue->nvme_cq,
 				&fod->queue->nvme_sq,
 				&nvmet_fc_tgt_fcp_ops);
-	if (!ret) {	/* bad SQE content */
-		nvmet_fc_abort_op(tgtport, fod->fcpreq);
+	if (!ret) {	/* bad SQE content or invalid ctrl state */
+		nvmet_fc_abort_op(tgtport, fod);
 		return;
 	}
 
@@ -2059,7 +2143,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 	return;
 
 transport_error:
-	nvmet_fc_abort_op(tgtport, fod->fcpreq);
+	nvmet_fc_abort_op(tgtport, fod);
 }
 
 /*
@@ -2089,7 +2173,7 @@ nvmet_fc_handle_fcp_rqst_work(struct work_struct *work)
  * If this routine returns error, the lldd should abort the exchange.
  *
  * @target_port: pointer to the (registered) target port the FCP CMD IU
- *              was receive on.
+ *              was received on.
  * @fcpreq:     pointer to a fcpreq request structure to be used to reference
  *              the exchange corresponding to the FCP Exchange.
  * @cmdiubuf:   pointer to the buffer containing the FCP CMD IU
@@ -2112,7 +2196,6 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port,
 			(be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4)))
 		return -EIO;
 
-
 	queue = nvmet_fc_find_target_queue(tgtport,
 				be64_to_cpu(cmdiu->connection_id));
 	if (!queue)
@@ -2142,12 +2225,68 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port,
 			((queue->qid - 1) % tgtport->ops->max_hw_queues) : 0;
 	memcpy(&fod->cmdiubuf, cmdiubuf, cmdiubuf_len);
 
-	queue_work_on(queue->cpu, queue->work_q, &fod->work);
+	if (tgtport->ops->target_features & NVMET_FCTGTFEAT_CMD_IN_ISR)
+		queue_work_on(queue->cpu, queue->work_q, &fod->work);
+	else
+		nvmet_fc_handle_fcp_rqst(tgtport, fod);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_req);
 
+/**
+ * nvmet_fc_rcv_fcp_abort - transport entry point called by an LLDD
+ *                       upon the reception of an ABTS for a FCP command
+ *
+ * Notify the transport that an ABTS has been received for a FCP command
+ * that had been given to the transport via nvmet_fc_rcv_fcp_req(). The
+ * LLDD believes the command is still being worked on
+ * (template_ops->fcp_req_release() has not been called).
+ *
+ * The transport will wait for any outstanding work (an op to the LLDD,
+ * which the lldd should complete with error due to the ABTS; or the
+ * completion from the nvmet layer of the nvme command), then will
+ * stop processing and call the nvmet_fc_rcv_fcp_req() callback to
+ * return the i/o context to the LLDD.  The LLDD may send the BA_ACC
+ * to the ABTS either after return from this function (assuming any
+ * outstanding op work has been terminated) or upon the callback being
+ * called.
+ *
+ * @target_port: pointer to the (registered) target port the FCP CMD IU
+ *              was received on.
+ * @fcpreq:     pointer to the fcpreq request structure that corresponds
+ *              to the exchange that received the ABTS.
+ */
+void
+nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *target_port,
+			struct nvmefc_tgt_fcp_req *fcpreq)
+{
+	struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+	struct nvmet_fc_tgt_queue *queue;
+	unsigned long flags;
+
+	if (!fod || fod->fcpreq != fcpreq)
+		/* job appears to have already completed, ignore abort */
+		return;
+
+	queue = fod->queue;
+
+	spin_lock_irqsave(&queue->qlock, flags);
+	if (fod->active) {
+		/*
+		 * mark as abort. The abort handler, invoked upon completion
+		 * of any work, will detect the aborted status and do the
+		 * callback.
+		 */
+		spin_lock(&fod->flock);
+		fod->abort = true;
+		fod->aborted = true;
+		spin_unlock(&fod->flock);
+	}
+	spin_unlock_irqrestore(&queue->qlock, flags);
+}
+EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_abort);
+
 enum {
 	FCT_TRADDR_ERR		= 0,
 	FCT_TRADDR_WWNN		= 1 << 0,
@@ -2177,7 +2316,7 @@ nvmet_fc_parse_traddr(struct nvmet_fc_traddr *traddr, char *buf)
 	if (!options)
 		return -ENOMEM;
 
-	while ((p = strsep(&o, ",\n")) != NULL) {
+	while ((p = strsep(&o, ":\n")) != NULL) {
 		if (!*p)
 			continue;
 
@@ -2238,6 +2377,7 @@ nvmet_fc_add_port(struct nvmet_port *port)
 			if (!tgtport->port) {
 				tgtport->port = port;
 				port->priv = tgtport;
+				nvmet_fc_tgtport_get(tgtport);
 				ret = 0;
 			} else
 				ret = -EALREADY;
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 4e8e6a22bce1..15551ef79c8c 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -246,11 +246,19 @@ struct fcloop_lsreq {
 struct fcloop_fcpreq {
 	struct fcloop_tport		*tport;
 	struct nvmefc_fcp_req		*fcpreq;
+	spinlock_t			reqlock;
 	u16				status;
+	bool				active;
+	bool				aborted;
 	struct work_struct		work;
 	struct nvmefc_tgt_fcp_req	tgt_fcp_req;
 };
 
+struct fcloop_ini_fcpreq {
+	struct nvmefc_fcp_req		*fcpreq;
+	struct fcloop_fcpreq		*tfcp_req;
+	struct work_struct		iniwork;
+};
 
 static inline struct fcloop_lsreq *
 tgt_ls_req_to_lsreq(struct nvmefc_tgt_ls_req *tgt_lsreq)
@@ -341,7 +349,21 @@ fcloop_xmt_ls_rsp(struct nvmet_fc_target_port *tport,
 }
 
 /*
- * FCP IO operation done. call back up initiator "done" flows.
+ * FCP IO operation done by initiator abort.
+ * call back up initiator "done" flows.
+ */
+static void
+fcloop_tgt_fcprqst_ini_done_work(struct work_struct *work)
+{
+	struct fcloop_ini_fcpreq *inireq =
+		container_of(work, struct fcloop_ini_fcpreq, iniwork);
+
+	inireq->fcpreq->done(inireq->fcpreq);
+}
+
+/*
+ * FCP IO operation done by target completion.
+ * call back up initiator "done" flows.
  */
 static void
 fcloop_tgt_fcprqst_done_work(struct work_struct *work)
@@ -349,12 +371,18 @@ fcloop_tgt_fcprqst_done_work(struct work_struct *work)
 	struct fcloop_fcpreq *tfcp_req =
 		container_of(work, struct fcloop_fcpreq, work);
 	struct fcloop_tport *tport = tfcp_req->tport;
-	struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+	struct nvmefc_fcp_req *fcpreq;
 
-	if (tport->remoteport) {
+	spin_lock(&tfcp_req->reqlock);
+	fcpreq = tfcp_req->fcpreq;
+	spin_unlock(&tfcp_req->reqlock);
+
+	if (tport->remoteport && fcpreq) {
 		fcpreq->status = tfcp_req->status;
 		fcpreq->done(fcpreq);
 	}
+
+	kfree(tfcp_req);
 }
 
 
@@ -364,20 +392,25 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport,
 			void *hw_queue_handle,
 			struct nvmefc_fcp_req *fcpreq)
 {
-	struct fcloop_fcpreq *tfcp_req = fcpreq->private;
 	struct fcloop_rport *rport = remoteport->private;
+	struct fcloop_ini_fcpreq *inireq = fcpreq->private;
+	struct fcloop_fcpreq *tfcp_req;
 	int ret = 0;
 
-	INIT_WORK(&tfcp_req->work, fcloop_tgt_fcprqst_done_work);
+	if (!rport->targetport)
+		return -ECONNREFUSED;
 
-	if (!rport->targetport) {
-		tfcp_req->status = NVME_SC_FC_TRANSPORT_ERROR;
-		schedule_work(&tfcp_req->work);
-		return ret;
-	}
+	tfcp_req = kzalloc(sizeof(*tfcp_req), GFP_KERNEL);
+	if (!tfcp_req)
+		return -ENOMEM;
 
+	inireq->fcpreq = fcpreq;
+	inireq->tfcp_req = tfcp_req;
+	INIT_WORK(&inireq->iniwork, fcloop_tgt_fcprqst_ini_done_work);
 	tfcp_req->fcpreq = fcpreq;
 	tfcp_req->tport = rport->targetport->private;
+	spin_lock_init(&tfcp_req->reqlock);
+	INIT_WORK(&tfcp_req->work, fcloop_tgt_fcprqst_done_work);
 
 	ret = nvmet_fc_rcv_fcp_req(rport->targetport, &tfcp_req->tgt_fcp_req,
 				 fcpreq->cmdaddr, fcpreq->cmdlen);
@@ -444,63 +477,129 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 			struct nvmefc_tgt_fcp_req *tgt_fcpreq)
 {
 	struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
-	struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+	struct nvmefc_fcp_req *fcpreq;
 	u32 rsplen = 0, xfrlen = 0;
-	int fcp_err = 0;
+	int fcp_err = 0, active, aborted;
 	u8 op = tgt_fcpreq->op;
 
+	spin_lock(&tfcp_req->reqlock);
+	fcpreq = tfcp_req->fcpreq;
+	active = tfcp_req->active;
+	aborted = tfcp_req->aborted;
+	tfcp_req->active = true;
+	spin_unlock(&tfcp_req->reqlock);
+
+	if (unlikely(active))
+		/* illegal - call while i/o active */
+		return -EALREADY;
+
+	if (unlikely(aborted)) {
+		/* target transport has aborted i/o prior */
+		spin_lock(&tfcp_req->reqlock);
+		tfcp_req->active = false;
+		spin_unlock(&tfcp_req->reqlock);
+		tgt_fcpreq->transferred_length = 0;
+		tgt_fcpreq->fcp_error = -ECANCELED;
+		tgt_fcpreq->done(tgt_fcpreq);
+		return 0;
+	}
+
+	/*
+	 * if fcpreq is NULL, the I/O has been aborted (from
+	 * initiator side). For the target side, act as if all is well
+	 * but don't actually move data.
+	 */
+
 	switch (op) {
 	case NVMET_FCOP_WRITEDATA:
 		xfrlen = tgt_fcpreq->transfer_length;
-		fcloop_fcp_copy_data(op, tgt_fcpreq->sg, fcpreq->first_sgl,
-					tgt_fcpreq->offset, xfrlen);
-		fcpreq->transferred_length += xfrlen;
+		if (fcpreq) {
+			fcloop_fcp_copy_data(op, tgt_fcpreq->sg,
+					fcpreq->first_sgl, tgt_fcpreq->offset,
+					xfrlen);
+			fcpreq->transferred_length += xfrlen;
+		}
 		break;
 
 	case NVMET_FCOP_READDATA:
 	case NVMET_FCOP_READDATA_RSP:
 		xfrlen = tgt_fcpreq->transfer_length;
-		fcloop_fcp_copy_data(op, tgt_fcpreq->sg, fcpreq->first_sgl,
-					tgt_fcpreq->offset, xfrlen);
-		fcpreq->transferred_length += xfrlen;
+		if (fcpreq) {
+			fcloop_fcp_copy_data(op, tgt_fcpreq->sg,
+					fcpreq->first_sgl, tgt_fcpreq->offset,
+					xfrlen);
+			fcpreq->transferred_length += xfrlen;
+		}
 		if (op == NVMET_FCOP_READDATA)
 			break;
 
 		/* Fall-Thru to RSP handling */
 
 	case NVMET_FCOP_RSP:
-		rsplen = ((fcpreq->rsplen < tgt_fcpreq->rsplen) ?
-				fcpreq->rsplen : tgt_fcpreq->rsplen);
-		memcpy(fcpreq->rspaddr, tgt_fcpreq->rspaddr, rsplen);
-		if (rsplen < tgt_fcpreq->rsplen)
-			fcp_err = -E2BIG;
-		fcpreq->rcv_rsplen = rsplen;
-		fcpreq->status = 0;
+		if (fcpreq) {
+			rsplen = ((fcpreq->rsplen < tgt_fcpreq->rsplen) ?
+					fcpreq->rsplen : tgt_fcpreq->rsplen);
+			memcpy(fcpreq->rspaddr, tgt_fcpreq->rspaddr, rsplen);
+			if (rsplen < tgt_fcpreq->rsplen)
+				fcp_err = -E2BIG;
+			fcpreq->rcv_rsplen = rsplen;
+			fcpreq->status = 0;
+		}
 		tfcp_req->status = 0;
 		break;
 
-	case NVMET_FCOP_ABORT:
-		tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
-		break;
-
 	default:
 		fcp_err = -EINVAL;
 		break;
 	}
 
+	spin_lock(&tfcp_req->reqlock);
+	tfcp_req->active = false;
+	spin_unlock(&tfcp_req->reqlock);
+
 	tgt_fcpreq->transferred_length = xfrlen;
 	tgt_fcpreq->fcp_error = fcp_err;
 	tgt_fcpreq->done(tgt_fcpreq);
 
-	if ((!fcp_err) && (op == NVMET_FCOP_RSP ||
-			op == NVMET_FCOP_READDATA_RSP ||
-			op == NVMET_FCOP_ABORT))
-		schedule_work(&tfcp_req->work);
-
 	return 0;
 }
 
 static void
+fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
+			struct nvmefc_tgt_fcp_req *tgt_fcpreq)
+{
+	struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+	int active;
+
+	/*
+	 * mark aborted only in case there were 2 threads in transport
+	 * (one doing io, other doing abort) and only kills ops posted
+	 * after the abort request
+	 */
+	spin_lock(&tfcp_req->reqlock);
+	active = tfcp_req->active;
+	tfcp_req->aborted = true;
+	spin_unlock(&tfcp_req->reqlock);
+
+	tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+
+	/*
+	 * nothing more to do. If io wasn't active, the transport should
+	 * immediately call the req_release. If it was active, the op
+	 * will complete, and the lldd should call req_release.
+	 */
+}
+
+static void
+fcloop_fcp_req_release(struct nvmet_fc_target_port *tgtport,
+			struct nvmefc_tgt_fcp_req *tgt_fcpreq)
+{
+	struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+
+	schedule_work(&tfcp_req->work);
+}
+
+static void
 fcloop_ls_abort(struct nvme_fc_local_port *localport,
 			struct nvme_fc_remote_port *remoteport,
 				struct nvmefc_ls_req *lsreq)
@@ -513,6 +612,27 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 			void *hw_queue_handle,
 			struct nvmefc_fcp_req *fcpreq)
 {
+	struct fcloop_rport *rport = remoteport->private;
+	struct fcloop_ini_fcpreq *inireq = fcpreq->private;
+	struct fcloop_fcpreq *tfcp_req = inireq->tfcp_req;
+
+	if (!tfcp_req)
+		/* abort has already been called */
+		return;
+
+	if (rport->targetport)
+		nvmet_fc_rcv_fcp_abort(rport->targetport,
+					&tfcp_req->tgt_fcp_req);
+
+	/* break initiator/target relationship for io */
+	spin_lock(&tfcp_req->reqlock);
+	inireq->tfcp_req = NULL;
+	tfcp_req->fcpreq = NULL;
+	spin_unlock(&tfcp_req->reqlock);
+
+	/* post the aborted io completion */
+	fcpreq->status = -ECANCELED;
+	schedule_work(&inireq->iniwork);
 }
 
 static void
@@ -546,7 +666,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport)
 #define	FCLOOP_SGL_SEGS			256
 #define FCLOOP_DMABOUND_4G		0xFFFFFFFF
 
-struct nvme_fc_port_template fctemplate = {
+static struct nvme_fc_port_template fctemplate = {
 	.localport_delete	= fcloop_localport_delete,
 	.remoteport_delete	= fcloop_remoteport_delete,
 	.create_queue		= fcloop_create_queue,
@@ -563,20 +683,23 @@ struct nvme_fc_port_template fctemplate = {
 	.local_priv_sz		= sizeof(struct fcloop_lport),
 	.remote_priv_sz		= sizeof(struct fcloop_rport),
 	.lsrqst_priv_sz		= sizeof(struct fcloop_lsreq),
-	.fcprqst_priv_sz	= sizeof(struct fcloop_fcpreq),
+	.fcprqst_priv_sz	= sizeof(struct fcloop_ini_fcpreq),
 };
 
-struct nvmet_fc_target_template tgttemplate = {
+static struct nvmet_fc_target_template tgttemplate = {
 	.targetport_delete	= fcloop_targetport_delete,
 	.xmt_ls_rsp		= fcloop_xmt_ls_rsp,
 	.fcp_op			= fcloop_fcp_op,
+	.fcp_abort		= fcloop_tgt_fcp_abort,
+	.fcp_req_release	= fcloop_fcp_req_release,
 	.max_hw_queues		= FCLOOP_HW_QUEUES,
 	.max_sgl_segments	= FCLOOP_SGL_SEGS,
 	.max_dif_sgl_segments	= FCLOOP_SGL_SEGS,
 	.dma_boundary		= FCLOOP_DMABOUND_4G,
 	/* optional features */
-	.target_features	= NVMET_FCTGTFEAT_READDATA_RSP |
-				  NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED,
+	.target_features	= NVMET_FCTGTFEAT_CMD_IN_ISR |
+				  NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
+				  NVMET_FCTGTFEAT_OPDONE_IN_ISR,
 	/* sizes of additional private data for data structures */
 	.target_priv_sz		= sizeof(struct fcloop_tport),
 };
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index 4195115c7e54..c77940d80fc8 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -180,11 +180,11 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
 
 	sector = le64_to_cpu(write_zeroes->slba) <<
 		(req->ns->blksize_shift - 9);
-	nr_sector = (((sector_t)le32_to_cpu(write_zeroes->length)) <<
+	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length)) <<
 		(req->ns->blksize_shift - 9)) + 1;
 
 	if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
-				GFP_KERNEL, &bio, true))
+				GFP_KERNEL, &bio, 0))
 		status = NVME_SC_INTERNAL | NVME_SC_DNR;
 
 	if (bio) {
@@ -196,26 +196,19 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
 	}
 }
 
-int nvmet_parse_io_cmd(struct nvmet_req *req)
+u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
+	u16 ret;
 
-	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
-		pr_err("nvmet: got io cmd %d while CC.EN == 0\n",
-				cmd->common.opcode);
+	ret = nvmet_check_ctrl_status(req, cmd);
+	if (unlikely(ret)) {
 		req->ns = NULL;
-		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
-	}
-
-	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
-		pr_err("nvmet: got io cmd %d while CSTS.RDY == 0\n",
-				cmd->common.opcode);
-		req->ns = NULL;
-		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+		return ret;
 	}
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
-	if (!req->ns)
+	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
 
 	switch (cmd->common.opcode) {
@@ -230,14 +223,15 @@ int nvmet_parse_io_cmd(struct nvmet_req *req)
 		return 0;
 	case nvme_cmd_dsm:
 		req->execute = nvmet_execute_dsm;
-		req->data_len = le32_to_cpu(cmd->dsm.nr + 1) *
+		req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
 			sizeof(struct nvme_dsm_range);
 		return 0;
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_execute_write_zeroes;
 		return 0;
 	default:
-		pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+		       req->sq->qid);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d1f06e7768ff..304f1c87c160 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -13,12 +13,10 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/scatterlist.h>
-#include <linux/delay.h>
 #include <linux/blk-mq.h>
 #include <linux/nvme.h>
 #include <linux/module.h>
 #include <linux/parser.h>
-#include <linux/t10-pi.h>
 #include "nvmet.h"
 #include "../host/nvme.h"
 #include "../host/fabrics.h"
@@ -93,31 +91,26 @@ static inline int nvme_loop_queue_idx(struct nvme_loop_queue *queue)
 static void nvme_loop_complete_rq(struct request *req)
 {
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
-	int error = 0;
 
 	nvme_cleanup_cmd(req);
 	sg_free_table_chained(&iod->sg_table, true);
+	nvme_complete_rq(req);
+}
 
-	if (unlikely(req->errors)) {
-		if (nvme_req_needs_retry(req, req->errors)) {
-			nvme_requeue_req(req);
-			return;
-		}
-
-		if (blk_rq_is_passthrough(req))
-			error = req->errors;
-		else
-			error = nvme_error_status(req->errors);
-	}
+static struct blk_mq_tags *nvme_loop_tagset(struct nvme_loop_queue *queue)
+{
+	u32 queue_idx = nvme_loop_queue_idx(queue);
 
-	blk_mq_end_request(req, error);
+	if (queue_idx == 0)
+		return queue->ctrl->admin_tag_set.tags[queue_idx];
+	return queue->ctrl->tag_set.tags[queue_idx - 1];
 }
 
 static void nvme_loop_queue_response(struct nvmet_req *req)
 {
-	struct nvme_loop_iod *iod =
-		container_of(req, struct nvme_loop_iod, req);
-	struct nvme_completion *cqe = &iod->rsp;
+	struct nvme_loop_queue *queue =
+		container_of(req->sq, struct nvme_loop_queue, nvme_sq);
+	struct nvme_completion *cqe = req->rsp;
 
 	/*
 	 * AEN requests are special as they don't time out and can
@@ -125,15 +118,22 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvme_loop_queue_idx(iod->queue) == 0 &&
+	if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
 			cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
-		nvme_complete_async_event(&iod->queue->ctrl->ctrl, cqe->status,
+		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
 				&cqe->result);
 	} else {
-		struct request *rq = blk_mq_rq_from_pdu(iod);
+		struct request *rq;
+
+		rq = blk_mq_tag_to_rq(nvme_loop_tagset(queue), cqe->command_id);
+		if (!rq) {
+			dev_err(queue->ctrl->ctrl.device,
+				"tag 0x%x on queue %d not found\n",
+				cqe->command_id, nvme_loop_queue_idx(queue));
+			return;
+		}
 
-		iod->nvme_req.result = cqe->result;
-		blk_mq_complete_request(rq, le16_to_cpu(cqe->status) >> 1);
+		nvme_end_request(rq, cqe->status, cqe->result);
 	}
 }
 
@@ -154,7 +154,7 @@ nvme_loop_timeout(struct request *rq, bool reserved)
 	schedule_work(&iod->queue->ctrl->reset_work);
 
 	/* fail with DNR on admin cmd timeout */
-	rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
 
 	return BLK_EH_HANDLED;
 }
@@ -223,8 +223,6 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
 static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl,
 		struct nvme_loop_iod *iod, unsigned int queue_idx)
 {
-	BUG_ON(queue_idx >= ctrl->queue_count);
-
 	iod->req.cmd = &iod->cmd;
 	iod->req.rsp = &iod->rsp;
 	iod->queue = &ctrl->queues[queue_idx];
@@ -270,7 +268,7 @@ static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 	return 0;
 }
 
-static struct blk_mq_ops nvme_loop_mq_ops = {
+static const struct blk_mq_ops nvme_loop_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
 	.init_request	= nvme_loop_init_request,
@@ -278,7 +276,7 @@ static struct blk_mq_ops nvme_loop_mq_ops = {
 	.timeout	= nvme_loop_timeout,
 };
 
-static struct blk_mq_ops nvme_loop_admin_mq_ops = {
+static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
 	.init_request	= nvme_loop_init_admin_request,
@@ -288,9 +286,9 @@ static struct blk_mq_ops nvme_loop_admin_mq_ops = {
 
 static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
+	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
-	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
 }
 
 static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
@@ -314,6 +312,56 @@ free_ctrl:
 	kfree(ctrl);
 }
 
+static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+	int i;
+
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+}
+
+static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	unsigned int nr_io_queues;
+	int ret, i;
+
+	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+	if (ret || !nr_io_queues)
+		return ret;
+
+	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues);
+
+	for (i = 1; i <= nr_io_queues; i++) {
+		ctrl->queues[i].ctrl = ctrl;
+		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
+		if (ret)
+			goto out_destroy_queues;
+
+		ctrl->queue_count++;
+	}
+
+	return 0;
+
+out_destroy_queues:
+	nvme_loop_destroy_io_queues(ctrl);
+	return ret;
+}
+
+static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+	int i, ret;
+
+	for (i = 1; i < ctrl->queue_count; i++) {
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
 	int error;
@@ -357,7 +405,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 	}
 
 	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+		min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize);
 
 	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
 	if (error)
@@ -385,17 +433,13 @@ out_free_sq:
 
 static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 {
-	int i;
-
 	nvme_stop_keep_alive(&ctrl->ctrl);
 
 	if (ctrl->queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
-
-		for (i = 1; i < ctrl->queue_count; i++)
-			nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+		nvme_loop_destroy_io_queues(ctrl);
 	}
 
 	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
@@ -459,7 +503,7 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	struct nvme_loop_ctrl *ctrl = container_of(work,
 					struct nvme_loop_ctrl, reset_work);
 	bool changed;
-	int i, ret;
+	int ret;
 
 	nvme_loop_shutdown_ctrl(ctrl);
 
@@ -467,20 +511,13 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	if (ret)
 		goto out_disable;
 
-	for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
-		ctrl->queues[i].ctrl = ctrl;
-		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
-		if (ret)
-			goto out_free_queues;
-
-		ctrl->queue_count++;
-	}
+	ret = nvme_loop_init_io_queues(ctrl);
+	if (ret)
+		goto out_destroy_admin;
 
-	for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
-		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
-		if (ret)
-			goto out_free_queues;
-	}
+	ret = nvme_loop_connect_io_queues(ctrl);
+	if (ret)
+		goto out_destroy_io;
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
@@ -492,9 +529,9 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 
 	return;
 
-out_free_queues:
-	for (i = 1; i < ctrl->queue_count; i++)
-		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+out_destroy_io:
+	nvme_loop_destroy_io_queues(ctrl);
+out_destroy_admin:
 	nvme_loop_destroy_admin_queue(ctrl);
 out_disable:
 	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
@@ -533,25 +570,12 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 {
-	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
-	int ret, i;
+	int ret;
 
-	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
-	if (ret || !opts->nr_io_queues)
+	ret = nvme_loop_init_io_queues(ctrl);
+	if (ret)
 		return ret;
 
-	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
-		opts->nr_io_queues);
-
-	for (i = 1; i <= opts->nr_io_queues; i++) {
-		ctrl->queues[i].ctrl = ctrl;
-		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
-		if (ret)
-			goto out_destroy_queues;
-
-		ctrl->queue_count++;
-	}
-
 	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
 	ctrl->tag_set.ops = &nvme_loop_mq_ops;
 	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
@@ -575,11 +599,9 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 		goto out_free_tagset;
 	}
 
-	for (i = 1; i <= opts->nr_io_queues; i++) {
-		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
-		if (ret)
-			goto out_cleanup_connect_q;
-	}
+	ret = nvme_loop_connect_io_queues(ctrl);
+	if (ret)
+		goto out_cleanup_connect_q;
 
 	return 0;
 
@@ -588,8 +610,7 @@ out_cleanup_connect_q:
 out_free_tagset:
 	blk_mq_free_tag_set(&ctrl->tag_set);
 out_destroy_queues:
-	for (i = 1; i < ctrl->queue_count; i++)
-		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+	nvme_loop_destroy_io_queues(ctrl);
 	return ret;
 }
 
@@ -724,7 +745,12 @@ static int __init nvme_loop_init_module(void)
 	ret = nvmet_register_transport(&nvme_loop_ops);
 	if (ret)
 		return ret;
-	return nvmf_register_transport(&nvme_loop_transport);
+
+	ret = nvmf_register_transport(&nvme_loop_transport);
+	if (ret)
+		nvmet_unregister_transport(&nvme_loop_ops);
+
+	return ret;
 }
 
 static void __exit nvme_loop_cleanup_module(void)
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 1370eee0a3c0..7cb77ba5993b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -73,6 +73,7 @@ struct nvmet_sq {
 	u16			qid;
 	u16			size;
 	struct completion	free_done;
+	struct completion	confirm_done;
 };
 
 /**
@@ -252,11 +253,11 @@ struct nvmet_async_event {
 	u8			log_page;
 };
 
-int nvmet_parse_connect_cmd(struct nvmet_req *req);
-int nvmet_parse_io_cmd(struct nvmet_req *req);
-int nvmet_parse_admin_cmd(struct nvmet_req *req);
-int nvmet_parse_discovery_cmd(struct nvmet_req *req);
-int nvmet_parse_fabrics_cmd(struct nvmet_req *req);
+u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
+u16 nvmet_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
+u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
+u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
 
 bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops);
@@ -277,6 +278,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
 		struct nvmet_req *req, struct nvmet_ctrl **ret);
 void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
+u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd);
 
 struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 		enum nvme_subsys_type type);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 9aa1da3778b3..99c69018a35f 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -703,11 +703,6 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 {
 	u16 status;
 
-	cmd->queue = queue;
-	cmd->n_rdma = 0;
-	cmd->req.port = queue->port;
-
-
 	ib_dma_sync_single_for_cpu(queue->dev->device,
 		cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
 		DMA_FROM_DEVICE);
@@ -760,9 +755,12 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	cmd->queue = queue;
 	rsp = nvmet_rdma_get_rsp(queue);
+	rsp->queue = queue;
 	rsp->cmd = cmd;
 	rsp->flags = 0;
 	rsp->req.cmd = cmd->nvme_cmd;
+	rsp->req.port = queue->port;
+	rsp->n_rdma = 0;
 
 	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
 		unsigned long flags;
@@ -1201,6 +1199,11 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 	}
 	queue->port = cm_id->context;
 
+	if (queue->host_qid == 0) {
+		/* Let inflight controller teardown complete */
+		flush_scheduled_work();
+	}
+
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
 	if (ret)
 		goto release_queue;
@@ -1429,12 +1432,16 @@ restart:
 static int nvmet_rdma_add_port(struct nvmet_port *port)
 {
 	struct rdma_cm_id *cm_id;
-	struct sockaddr_in addr_in;
-	u16 port_in;
+	struct sockaddr_storage addr = { };
+	__kernel_sa_family_t af;
 	int ret;
 
 	switch (port->disc_addr.adrfam) {
 	case NVMF_ADDR_FAMILY_IP4:
+		af = AF_INET;
+		break;
+	case NVMF_ADDR_FAMILY_IP6:
+		af = AF_INET6;
 		break;
 	default:
 		pr_err("address family %d not supported\n",
@@ -1442,13 +1449,13 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
 		return -EINVAL;
 	}
 
-	ret = kstrtou16(port->disc_addr.trsvcid, 0, &port_in);
-	if (ret)
+	ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
+			port->disc_addr.trsvcid, &addr);
+	if (ret) {
+		pr_err("malformed ip/port passed: %s:%s\n",
+			port->disc_addr.traddr, port->disc_addr.trsvcid);
 		return ret;
-
-	addr_in.sin_family = AF_INET;
-	addr_in.sin_addr.s_addr = in_aton(port->disc_addr.traddr);
-	addr_in.sin_port = htons(port_in);
+	}
 
 	cm_id = rdma_create_id(&init_net, nvmet_rdma_cm_handler, port,
 			RDMA_PS_TCP, IB_QPT_RC);
@@ -1457,20 +1464,32 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
 		return PTR_ERR(cm_id);
 	}
 
-	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr_in);
+	/*
+	 * Allow both IPv4 and IPv6 sockets to bind a single port
+	 * at the same time.
+	 */
+	ret = rdma_set_afonly(cm_id, 1);
+	if (ret) {
+		pr_err("rdma_set_afonly failed (%d)\n", ret);
+		goto out_destroy_id;
+	}
+
+	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr);
 	if (ret) {
-		pr_err("binding CM ID to %pISpc failed (%d)\n", &addr_in, ret);
+		pr_err("binding CM ID to %pISpcs failed (%d)\n",
+			(struct sockaddr *)&addr, ret);
 		goto out_destroy_id;
 	}
 
 	ret = rdma_listen(cm_id, 128);
 	if (ret) {
-		pr_err("listening to %pISpc failed (%d)\n", &addr_in, ret);
+		pr_err("listening to %pISpcs failed (%d)\n",
+			(struct sockaddr *)&addr, ret);
 		goto out_destroy_id;
 	}
 
-	pr_info("enabling port %d (%pISpc)\n",
-		le16_to_cpu(port->disc_addr.portid), &addr_in);
+	pr_info("enabling port %d (%pISpcs)\n",
+		le16_to_cpu(port->disc_addr.portid), (struct sockaddr *)&addr);
 	port->priv = cm_id;
 	return 0;
 
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 0b2979816dbf..7e4c80f9b6cd 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -22,6 +22,8 @@
 #include <linux/of_net.h>
 #include <linux/module.h>
 
+#define DEFAULT_GPIO_RESET_DELAY	10	/* in microseconds */
+
 MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
 MODULE_LICENSE("GPL");
 
@@ -221,6 +223,11 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 
 	mdio->dev.of_node = np;
 
+	/* Get bus level PHY reset GPIO details */
+	mdio->reset_delay_us = DEFAULT_GPIO_RESET_DELAY;
+	of_property_read_u32(np, "reset-delay-us", &mdio->reset_delay_us);
+	mdio->num_reset_gpios = of_gpio_named_count(np, "reset-gpios");
+
 	/* Register the MDIO bus */
 	rc = mdiobus_register(mdio);
 	if (rc)
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index bc090daa850a..5dc53d420ca8 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -939,8 +939,10 @@ parport_register_dev_model(struct parport *port, const char *name,
 	 * pardevice fields. -arca
 	 */
 	port->ops->init_state(par_dev, par_dev->state);
-	port->proc_device = par_dev;
-	parport_device_proc_register(par_dev);
+	if (!test_and_set_bit(PARPORT_DEVPROC_REGISTERED, &port->devflags)) {
+		port->proc_device = par_dev;
+		parport_device_proc_register(par_dev);
+	}
 
 	return par_dev;
 
diff --git a/drivers/pci/dwc/Kconfig b/drivers/pci/dwc/Kconfig
index dfb8a69afc28..d2d2ba5b8a68 100644
--- a/drivers/pci/dwc/Kconfig
+++ b/drivers/pci/dwc/Kconfig
@@ -89,6 +89,7 @@ config PCI_HISI
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIEPORTBUS
 	select PCIE_DW_HOST
+	select PCI_HOST_COMMON
 	help
 	  Say Y here if you want PCIe controller support on HiSilicon
 	  Hip05 and Hip06 SoCs
diff --git a/drivers/pci/dwc/pci-exynos.c b/drivers/pci/dwc/pci-exynos.c
index 993b650ef275..44f774c12fb2 100644
--- a/drivers/pci/dwc/pci-exynos.c
+++ b/drivers/pci/dwc/pci-exynos.c
@@ -132,10 +132,6 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev,
 	struct device *dev = pci->dev;
 	struct resource *res;
 
-	/* If using the PHY framework, doesn't need to get other resource */
-	if (ep->using_phy)
-		return 0;
-
 	ep->mem_res = devm_kzalloc(dev, sizeof(*ep->mem_res), GFP_KERNEL);
 	if (!ep->mem_res)
 		return -ENOMEM;
@@ -145,6 +141,10 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev,
 	if (IS_ERR(ep->mem_res->elbi_base))
 		return PTR_ERR(ep->mem_res->elbi_base);
 
+	/* If using the PHY framework, doesn't need to get other resource */
+	if (ep->using_phy)
+		return 0;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	ep->mem_res->phy_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(ep->mem_res->phy_base))
diff --git a/drivers/pci/dwc/pcie-artpec6.c b/drivers/pci/dwc/pcie-artpec6.c
index fcd3ef845883..6d23683c0892 100644
--- a/drivers/pci/dwc/pcie-artpec6.c
+++ b/drivers/pci/dwc/pcie-artpec6.c
@@ -234,6 +234,9 @@ static int artpec6_add_pcie_port(struct artpec6_pcie *artpec6_pcie,
 	return 0;
 }
 
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
 static int artpec6_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -252,6 +255,7 @@ static int artpec6_pcie_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pci->dev = dev;
+	pci->ops = &dw_pcie_ops;
 
 	artpec6_pcie->pci = pci;
 
diff --git a/drivers/pci/dwc/pcie-designware-plat.c b/drivers/pci/dwc/pcie-designware-plat.c
index b6c832ba39dd..f20d494922ab 100644
--- a/drivers/pci/dwc/pcie-designware-plat.c
+++ b/drivers/pci/dwc/pcie-designware-plat.c
@@ -86,6 +86,9 @@ static int dw_plat_add_pcie_port(struct pcie_port *pp,
 	return 0;
 }
 
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
 static int dw_plat_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -103,6 +106,7 @@ static int dw_plat_pcie_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pci->dev = dev;
+	pci->ops = &dw_pcie_ops;
 
 	dw_plat_pcie->pci = pci;
 
diff --git a/drivers/pci/dwc/pcie-hisi.c b/drivers/pci/dwc/pcie-hisi.c
index fd66a3199db7..cf9d6a9d9fd4 100644
--- a/drivers/pci/dwc/pcie-hisi.c
+++ b/drivers/pci/dwc/pcie-hisi.c
@@ -380,9 +380,13 @@ struct pci_ecam_ops hisi_pcie_platform_ops = {
 
 static const struct of_device_id hisi_pcie_almost_ecam_of_match[] = {
 	{
-		.compatible = "hisilicon,pcie-almost-ecam",
+		.compatible =  "hisilicon,hip06-pcie-ecam",
 		.data	    = (void *) &hisi_pcie_platform_ops,
 	},
+	{
+		.compatible =  "hisilicon,hip07-pcie-ecam",
+		.data       = (void *) &hisi_pcie_platform_ops,
+	},
 	{},
 };
 
diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c
index 52b5bdccf5f0..6e031b522529 100644
--- a/drivers/pci/host/pci-thunder-pem.c
+++ b/drivers/pci/host/pci-thunder-pem.c
@@ -14,6 +14,7 @@
  * Copyright (C) 2015 - 2016 Cavium, Inc.
  */
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/of_address.h>
@@ -334,6 +335,49 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 
+#define PEM_RES_BASE		0x87e0c0000000UL
+#define PEM_NODE_MASK		GENMASK(45, 44)
+#define PEM_INDX_MASK		GENMASK(26, 24)
+#define PEM_MIN_DOM_IN_NODE	4
+#define PEM_MAX_DOM_IN_NODE	10
+
+static void thunder_pem_reserve_range(struct device *dev, int seg,
+				      struct resource *r)
+{
+	resource_size_t start = r->start, end = r->end;
+	struct resource *res;
+	const char *regionid;
+
+	regionid = kasprintf(GFP_KERNEL, "PEM RC:%d", seg);
+	if (!regionid)
+		return;
+
+	res = request_mem_region(start, end - start + 1, regionid);
+	if (res)
+		res->flags &= ~IORESOURCE_BUSY;
+	else
+		kfree(regionid);
+
+	dev_info(dev, "%pR %s reserved\n", r,
+		 res ? "has been" : "could not be");
+}
+
+static void thunder_pem_legacy_fw(struct acpi_pci_root *root,
+				 struct resource *res_pem)
+{
+	int node = acpi_get_node(root->device->handle);
+	int index;
+
+	if (node == NUMA_NO_NODE)
+		node = 0;
+
+	index = root->segment - PEM_MIN_DOM_IN_NODE;
+	index -= node * PEM_MAX_DOM_IN_NODE;
+	res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) |
+					FIELD_PREP(PEM_INDX_MASK, index);
+	res_pem->flags = IORESOURCE_MEM;
+}
+
 static int thunder_pem_acpi_init(struct pci_config_window *cfg)
 {
 	struct device *dev = cfg->parent;
@@ -346,10 +390,24 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg)
 	if (!res_pem)
 		return -ENOMEM;
 
-	ret = acpi_get_rc_resources(dev, "THRX0002", root->segment, res_pem);
+	ret = acpi_get_rc_resources(dev, "CAVA02B", root->segment, res_pem);
+
+	/*
+	 * If we fail to gather resources it means that we run with old
+	 * FW where we need to calculate PEM-specific resources manually.
+	 */
 	if (ret) {
-		dev_err(dev, "can't get rc base address\n");
-		return ret;
+		thunder_pem_legacy_fw(root, res_pem);
+		/*
+		 * Reserve 64K size PEM specific resources. The full 16M range
+		 * size is required for thunder_pem_init() call.
+		 */
+		res_pem->end = res_pem->start + SZ_64K - 1;
+		thunder_pem_reserve_range(dev, root->segment, res_pem);
+		res_pem->end = res_pem->start + SZ_16M - 1;
+
+		/* Reserve PCI configuration space as well. */
+		thunder_pem_reserve_range(dev, root->segment, &cfg->res);
 	}
 
 	return thunder_pem_init(dev, cfg, res_pem);
diff --git a/drivers/pci/host/pcie-iproc-bcma.c b/drivers/pci/host/pcie-iproc-bcma.c
index bd4c9ec25edc..384c27e664fe 100644
--- a/drivers/pci/host/pcie-iproc-bcma.c
+++ b/drivers/pci/host/pcie-iproc-bcma.c
@@ -44,8 +44,7 @@ static int iproc_pcie_bcma_probe(struct bcma_device *bdev)
 {
 	struct device *dev = &bdev->dev;
 	struct iproc_pcie *pcie;
-	LIST_HEAD(res);
-	struct resource res_mem;
+	LIST_HEAD(resources);
 	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
@@ -63,22 +62,23 @@ static int iproc_pcie_bcma_probe(struct bcma_device *bdev)
 
 	pcie->base_addr = bdev->addr;
 
-	res_mem.start = bdev->addr_s[0];
-	res_mem.end = bdev->addr_s[0] + SZ_128M - 1;
-	res_mem.name = "PCIe MEM space";
-	res_mem.flags = IORESOURCE_MEM;
-	pci_add_resource(&res, &res_mem);
+	pcie->mem.start = bdev->addr_s[0];
+	pcie->mem.end = bdev->addr_s[0] + SZ_128M - 1;
+	pcie->mem.name = "PCIe MEM space";
+	pcie->mem.flags = IORESOURCE_MEM;
+	pci_add_resource(&resources, &pcie->mem);
 
 	pcie->map_irq = iproc_pcie_bcma_map_irq;
 
-	ret = iproc_pcie_setup(pcie, &res);
-	if (ret)
+	ret = iproc_pcie_setup(pcie, &resources);
+	if (ret) {
 		dev_err(dev, "PCIe controller setup failed\n");
-
-	pci_free_resource_list(&res);
+		pci_free_resource_list(&resources);
+		return ret;
+	}
 
 	bcma_set_drvdata(bdev, pcie);
-	return ret;
+	return 0;
 }
 
 static void iproc_pcie_bcma_remove(struct bcma_device *bdev)
diff --git a/drivers/pci/host/pcie-iproc-platform.c b/drivers/pci/host/pcie-iproc-platform.c
index f4909bb0b2ad..8c6a327ca6cd 100644
--- a/drivers/pci/host/pcie-iproc-platform.c
+++ b/drivers/pci/host/pcie-iproc-platform.c
@@ -51,7 +51,7 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	struct resource reg;
 	resource_size_t iobase = 0;
-	LIST_HEAD(res);
+	LIST_HEAD(resources);
 	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
@@ -96,10 +96,10 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 		pcie->phy = NULL;
 	}
 
-	ret = of_pci_get_host_bridge_resources(np, 0, 0xff, &res, &iobase);
+	ret = of_pci_get_host_bridge_resources(np, 0, 0xff, &resources,
+					       &iobase);
 	if (ret) {
-		dev_err(dev,
-			"unable to get PCI host bridge resources\n");
+		dev_err(dev, "unable to get PCI host bridge resources\n");
 		return ret;
 	}
 
@@ -112,14 +112,15 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 		pcie->map_irq = of_irq_parse_and_map_pci;
 	}
 
-	ret = iproc_pcie_setup(pcie, &res);
-	if (ret)
+	ret = iproc_pcie_setup(pcie, &resources);
+	if (ret) {
 		dev_err(dev, "PCIe controller setup failed\n");
-
-	pci_free_resource_list(&res);
+		pci_free_resource_list(&resources);
+		return ret;
+	}
 
 	platform_set_drvdata(pdev, pcie);
-	return ret;
+	return 0;
 }
 
 static int iproc_pcie_pltfm_remove(struct platform_device *pdev)
diff --git a/drivers/pci/host/pcie-iproc.h b/drivers/pci/host/pcie-iproc.h
index 04fed8e907f1..0bbe2ea44f3e 100644
--- a/drivers/pci/host/pcie-iproc.h
+++ b/drivers/pci/host/pcie-iproc.h
@@ -90,6 +90,7 @@ struct iproc_pcie {
 #ifdef CONFIG_ARM
 	struct pci_sys_data sysdata;
 #endif
+	struct resource mem;
 	struct pci_bus *root_bus;
 	struct phy *phy;
 	int (*map_irq)(const struct pci_dev *, u8, u8);
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index 6684f153ab57..f9f2a0324ecc 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -31,7 +31,7 @@ static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
  * driver).
  *
  * Returns:
- *  a suggestion for fixing it (although the driver is not required to
+ * a suggestion for fixing it (although the driver is not required to
  * act on this).
  */
 enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *pdev)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index d571bc330686..0042c365b29b 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -973,27 +973,6 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
 	return msix_capability_init(dev, entries, nvec, affd);
 }
 
-/**
- * pci_enable_msix - configure device's MSI-X capability structure
- * @dev: pointer to the pci_dev data structure of MSI-X device function
- * @entries: pointer to an array of MSI-X entries (optional)
- * @nvec: number of MSI-X irqs requested for allocation by device driver
- *
- * Setup the MSI-X capability structure of device function with the number
- * of requested irqs upon its software driver call to request for
- * MSI-X mode enabled on its hardware device function. A return of zero
- * indicates the successful configuration of MSI-X capability structure
- * with new allocated MSI-X irqs. A return of < 0 indicates a failure.
- * Or a return of > 0 indicates that driver request is exceeding the number
- * of irqs or MSI-X vectors available. Driver should use the returned value to
- * re-send its request.
- **/
-int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
-{
-	return __pci_enable_msix(dev, entries, nvec, NULL);
-}
-EXPORT_SYMBOL(pci_enable_msix);
-
 void pci_msix_shutdown(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 973472c23d89..1dfa10cc566b 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -478,7 +478,7 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 
 static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 {
-	struct pci_dev *child, *parent = link->pdev;
+	struct pci_dev *child = link->downstream, *parent = link->pdev;
 	struct pci_bus *linkbus = parent->subordinate;
 	struct aspm_register_info upreg, dwreg;
 
@@ -491,9 +491,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	/* Get upstream/downstream components' register state */
 	pcie_get_aspm_reg(parent, &upreg);
-	child = pci_function_0(linkbus);
 	pcie_get_aspm_reg(child, &dwreg);
-	link->downstream = child;
 
 	/*
 	 * If ASPM not supported, don't mess with the clocks and link,
@@ -800,6 +798,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
 	INIT_LIST_HEAD(&link->children);
 	INIT_LIST_HEAD(&link->link);
 	link->pdev = pdev;
+	link->downstream = pci_function_0(pdev->subordinate);
 
 	/*
 	 * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f754453fe754..673683660b5c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2174,6 +2174,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005d, quirk_blacklist_vpd);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005f, quirk_blacklist_vpd);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID,
 		quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_QLOGIC, 0x2261, quirk_blacklist_vpd);
 
 /*
  * For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index dc5277ad1b5a..005cadb7a3f8 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -449,6 +449,7 @@ config PHY_QCOM_UFS
 config PHY_QCOM_USB_HS
 	tristate "Qualcomm USB HS PHY module"
 	depends on USB_ULPI_BUS
+	depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in
 	select GENERIC_PHY
 	help
 	  Support for the USB high-speed ULPI compliant phy on Qualcomm
@@ -510,12 +511,4 @@ config PHY_MESON8B_USB2
 	  and GXBB SoCs.
 	  If unsure, say N.
 
-config PHY_NSP_USB3
-	tristate "Broadcom NorthStar plus USB3 PHY driver"
-	depends on OF && (ARCH_BCM_NSP || COMPILE_TEST)
-	select GENERIC_PHY
-	default ARCH_BCM_NSP
-	help
-	  Enable this to support the Broadcom Northstar plus USB3 PHY.
-	  If unsure, say N.
 endmenu
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index e7b0feb1e125..dd8f3b5d2918 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -62,4 +62,3 @@ obj-$(CONFIG_PHY_CYGNUS_PCIE)		+= phy-bcm-cygnus-pcie.o
 obj-$(CONFIG_ARCH_TEGRA) += tegra/
 obj-$(CONFIG_PHY_NS2_PCIE)		+= phy-bcm-ns2-pcie.o
 obj-$(CONFIG_PHY_MESON8B_USB2)		+= phy-meson8b-usb2.o
-obj-$(CONFIG_PHY_NSP_USB3)		+= phy-bcm-nsp-usb3.o
diff --git a/drivers/phy/phy-bcm-nsp-usb3.c b/drivers/phy/phy-bcm-nsp-usb3.c
deleted file mode 100644
index 49024eaa5545..000000000000
--- a/drivers/phy/phy-bcm-nsp-usb3.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * Copyright (C) 2016 Broadcom
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <linux/mfd/syscon.h>
-#include <linux/mdio.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/phy/phy.h>
-#include <linux/regmap.h>
-
-#define NSP_USB3_RST_CTRL_OFFSET	0x3f8
-
-/* mdio reg access */
-#define NSP_USB3_PHY_BASE_ADDR_REG	0x1f
-
-#define NSP_USB3_PHY_PLL30_BLOCK	0x8000
-#define NSP_USB3_PLL_CONTROL		0x01
-#define NSP_USB3_PLLA_CONTROL0		0x0a
-#define NSP_USB3_PLLA_CONTROL1		0x0b
-
-#define NSP_USB3_PHY_TX_PMD_BLOCK	0x8040
-#define NSP_USB3_TX_PMD_CONTROL1	0x01
-
-#define NSP_USB3_PHY_PIPE_BLOCK		0x8060
-#define NSP_USB3_LFPS_CMP		0x02
-#define NSP_USB3_LFPS_DEGLITCH		0x03
-
-struct nsp_usb3_phy {
-	struct regmap *usb3_ctrl;
-	struct phy *phy;
-	struct mdio_device *mdiodev;
-};
-
-static int nsp_usb3_phy_init(struct phy *phy)
-{
-	struct nsp_usb3_phy *iphy = phy_get_drvdata(phy);
-	struct mii_bus *bus = iphy->mdiodev->bus;
-	int addr = iphy->mdiodev->addr;
-	u32 data;
-	int rc;
-
-	rc = regmap_read(iphy->usb3_ctrl, 0, &data);
-	if (rc)
-		return rc;
-	data |= 1;
-	rc = regmap_write(iphy->usb3_ctrl, 0, data);
-	if (rc)
-		return rc;
-
-	rc = regmap_write(iphy->usb3_ctrl, NSP_USB3_RST_CTRL_OFFSET, 1);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PHY_BASE_ADDR_REG,
-			   NSP_USB3_PHY_PLL30_BLOCK);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PLL_CONTROL, 0x1000);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PLLA_CONTROL0, 0x6400);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PLLA_CONTROL1, 0xc000);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PLLA_CONTROL1, 0x8000);
-	if (rc)
-		return rc;
-
-	rc = regmap_write(iphy->usb3_ctrl, NSP_USB3_RST_CTRL_OFFSET, 0);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PLL_CONTROL, 0x9000);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PHY_BASE_ADDR_REG,
-			   NSP_USB3_PHY_PIPE_BLOCK);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_LFPS_CMP, 0xf30d);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_LFPS_DEGLITCH, 0x6302);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_PHY_BASE_ADDR_REG,
-			   NSP_USB3_PHY_TX_PMD_BLOCK);
-	if (rc)
-		return rc;
-
-	rc = mdiobus_write(bus, addr, NSP_USB3_TX_PMD_CONTROL1, 0x1003);
-
-	return rc;
-}
-
-static struct phy_ops nsp_usb3_phy_ops = {
-	.init	= nsp_usb3_phy_init,
-	.owner	= THIS_MODULE,
-};
-
-static int nsp_usb3_phy_probe(struct mdio_device *mdiodev)
-{
-	struct device *dev = &mdiodev->dev;
-	struct phy_provider *provider;
-	struct nsp_usb3_phy *iphy;
-
-	iphy = devm_kzalloc(dev, sizeof(*iphy), GFP_KERNEL);
-	if (!iphy)
-		return -ENOMEM;
-	iphy->mdiodev = mdiodev;
-
-	iphy->usb3_ctrl = syscon_regmap_lookup_by_phandle(dev->of_node,
-						 "usb3-ctrl-syscon");
-	if (IS_ERR(iphy->usb3_ctrl))
-		return PTR_ERR(iphy->usb3_ctrl);
-
-	iphy->phy = devm_phy_create(dev, dev->of_node, &nsp_usb3_phy_ops);
-	if (IS_ERR(iphy->phy)) {
-		dev_err(dev, "failed to create PHY\n");
-		return PTR_ERR(iphy->phy);
-	}
-
-	phy_set_drvdata(iphy->phy, iphy);
-
-	provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
-	if (IS_ERR(provider)) {
-		dev_err(dev, "could not register PHY provider\n");
-		return PTR_ERR(provider);
-	}
-
-	return 0;
-}
-
-static const struct of_device_id nsp_usb3_phy_of_match[] = {
-	{.compatible = "brcm,nsp-usb3-phy",},
-	{ /* sentinel */ }
-};
-
-static struct mdio_driver nsp_usb3_phy_driver = {
-	.mdiodrv = {
-		.driver = {
-			.name = "nsp-usb3-phy",
-			.of_match_table = nsp_usb3_phy_of_match,
-		},
-	},
-	.probe = nsp_usb3_phy_probe,
-};
-
-mdio_module_driver(nsp_usb3_phy_driver);
-
-MODULE_DESCRIPTION("Broadcom NSP USB3 PHY driver");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Yendapally Reddy Dhananjaya Reddy <yendapally.reddy@broadcom.com");
diff --git a/drivers/phy/phy-exynos-pcie.c b/drivers/phy/phy-exynos-pcie.c
index 4f60b83641d5..60baf25d98e2 100644
--- a/drivers/phy/phy-exynos-pcie.c
+++ b/drivers/phy/phy-exynos-pcie.c
@@ -254,8 +254,8 @@ static int exynos_pcie_phy_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	exynos_phy->blk_base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(exynos_phy->phy_base))
-		return PTR_ERR(exynos_phy->phy_base);
+	if (IS_ERR(exynos_phy->blk_base))
+		return PTR_ERR(exynos_phy->blk_base);
 
 	exynos_phy->drv_data = drv_data;
 
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 8f8c2af45781..37af5e3029d5 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -41,6 +41,17 @@ config PINCTRL_ADI2
 	  future processors. This option is selected automatically when specific
 	  machine and arch are selected to build.
 
+config PINCTRL_ARTPEC6
+        bool "Axis ARTPEC-6 pin controller driver"
+        depends on MACH_ARTPEC6
+        select PINMUX
+        select GENERIC_PINCONF
+        help
+          This is the driver for the Axis ARTPEC-6 pin controller. This driver
+          supports pin function multiplexing as well as pin bias and drive
+          strength configuration. Device tree integration instructions can be
+          found in Documentation/devicetree/bindings/pinctrl/axis,artpec6-pinctrl.txt
+
 config PINCTRL_AS3722
 	tristate "Pinctrl and GPIO driver for ams AS3722 PMIC"
 	depends on MFD_AS3722 && GPIOLIB
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index a251f439626f..0e9b2226a7c2 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_PINCONF)		+= pinconf.o
 obj-$(CONFIG_OF)		+= devicetree.o
 obj-$(CONFIG_GENERIC_PINCONF)	+= pinconf-generic.o
 obj-$(CONFIG_PINCTRL_ADI2)	+= pinctrl-adi2.o
+obj-$(CONFIG_PINCTRL_ARTPEC6)	+= pinctrl-artpec6.o
 obj-$(CONFIG_PINCTRL_AS3722)	+= pinctrl-as3722.o
 obj-$(CONFIG_PINCTRL_BF54x)	+= pinctrl-adi2-bf54x.o
 obj-$(CONFIG_PINCTRL_BF60x)	+= pinctrl-adi2-bf60x.o
@@ -44,7 +45,7 @@ obj-y				+= bcm/
 obj-$(CONFIG_PINCTRL_BERLIN)	+= berlin/
 obj-y				+= freescale/
 obj-$(CONFIG_X86)		+= intel/
-obj-$(CONFIG_PINCTRL_MVEBU)	+= mvebu/
+obj-y				+= mvebu/
 obj-y				+= nomadik/
 obj-$(CONFIG_PINCTRL_PXA)	+= pxa/
 obj-$(CONFIG_ARCH_QCOM)		+= qcom/
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g4.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g4.c
index 7de596e2b9d4..cf3106cec048 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g4.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g4.c
@@ -856,8 +856,8 @@ SIG_EXPR_DECL(VPIG3, VPI18, VPI18_DESC, AB1_DESC);
 SIG_EXPR_DECL(VPIG3, VPI24, VPI24_DESC, AB1_DESC);
 SIG_EXPR_DECL(VPIG3, VPI30, VPI30_DESC, AB1_DESC);
 SIG_EXPR_LIST_DECL(VPIG3, SIG_EXPR_PTR(VPIG3, VPI18),
-		SIG_EXPR_PTR(VPIG2, VPI24),
-		SIG_EXPR_PTR(VPIG2, VPI30));
+		SIG_EXPR_PTR(VPIG3, VPI24),
+		SIG_EXPR_PTR(VPIG3, VPI30));
 SIG_EXPR_LIST_DECL_SINGLE(PWM3, PWM3, AB1_DESC);
 MS_PIN_DECL(AB1, GPION3, VPIG3, PWM3);
 FUNC_GROUP_DECL(PWM3, AB1);
@@ -868,8 +868,8 @@ SIG_EXPR_DECL(VPIG4, VPI18, VPI18_DESC, W5_DESC);
 SIG_EXPR_DECL(VPIG4, VPI24, VPI24_DESC, W5_DESC);
 SIG_EXPR_DECL(VPIG4, VPI30, VPI30_DESC, W5_DESC);
 SIG_EXPR_LIST_DECL(VPIG4, SIG_EXPR_PTR(VPIG4, VPI18),
-		SIG_EXPR_PTR(VPIG2, VPI24),
-		SIG_EXPR_PTR(VPIG2, VPI30));
+		SIG_EXPR_PTR(VPIG4, VPI24),
+		SIG_EXPR_PTR(VPIG4, VPI30));
 SIG_EXPR_LIST_DECL_SINGLE(PWM4, PWM4, W5_DESC);
 MS_PIN_DECL(W5, GPION4, VPIG4, PWM4);
 FUNC_GROUP_DECL(PWM4, W5);
@@ -880,8 +880,8 @@ SIG_EXPR_DECL(VPIG5, VPI18, VPI18_DESC, Y4_DESC);
 SIG_EXPR_DECL(VPIG5, VPI24, VPI24_DESC, Y4_DESC);
 SIG_EXPR_DECL(VPIG5, VPI30, VPI30_DESC, Y4_DESC);
 SIG_EXPR_LIST_DECL(VPIG5, SIG_EXPR_PTR(VPIG5, VPI18),
-		SIG_EXPR_PTR(VPIG2, VPI24),
-		SIG_EXPR_PTR(VPIG2, VPI30));
+		SIG_EXPR_PTR(VPIG5, VPI24),
+		SIG_EXPR_PTR(VPIG5, VPI30));
 SIG_EXPR_LIST_DECL_SINGLE(PWM5, PWM5, Y4_DESC);
 MS_PIN_DECL(Y4, GPION5, VPIG5, PWM5);
 FUNC_GROUP_DECL(PWM5, Y4);
@@ -2234,6 +2234,110 @@ static const struct aspeed_pin_function aspeed_g4_functions[] = {
 	ASPEED_PINCTRL_FUNC(WDTRST2),
 };
 
+static const struct aspeed_pin_config aspeed_g4_configs[] = {
+	/* GPIO banks ranges [A, B], [D, J], [M, R] */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { D6,  D5  }, SCU8C, 16 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { D6,  D5  }, SCU8C, 16 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { J21, E18 }, SCU8C, 17 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { J21, E18 }, SCU8C, 17 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A18, E15 }, SCU8C, 19 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A18, E15 }, SCU8C, 19 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { D15, B14 }, SCU8C, 20 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { D15, B14 }, SCU8C, 20 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { D18, C17 }, SCU8C, 21 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { D18, C17 }, SCU8C, 21 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A14, U18 }, SCU8C, 22 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A14, U18 }, SCU8C, 22 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A8,  E7  }, SCU8C, 23 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A8,  E7  }, SCU8C, 23 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { C22, E20 }, SCU8C, 24 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { C22, E20 }, SCU8C, 24 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { J5,  T1  }, SCU8C, 25 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { J5,  T1  }, SCU8C, 25 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { U1,  U5  }, SCU8C, 26 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { U1,  U5  }, SCU8C, 26 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { V3,  V5  }, SCU8C, 27 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { V3,  V5  }, SCU8C, 27 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { W4,  AB2 }, SCU8C, 28 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { W4,  AB2 }, SCU8C, 28 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { V6,  V7  }, SCU8C, 29 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { V6,  V7  }, SCU8C, 29 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { Y6,  AB7 }, SCU8C, 30 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { Y6,  AB7 }, SCU8C, 30 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { V20, A5  }, SCU8C, 31 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { V20, A5  }, SCU8C, 31 },
+
+	/* GPIOs T[0-5] (RGMII1 Tx pins) */
+	{ PIN_CONFIG_DRIVE_STRENGTH, { A12, A13 }, SCU90, 9  },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A12, A13 }, SCU90, 12 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A12, A13 }, SCU90, 12 },
+
+	/* GPIOs T[6-7], U[0-3] (RGMII2 TX pins) */
+	{ PIN_CONFIG_DRIVE_STRENGTH, { D9,  D10 }, SCU90, 11 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { D9,  D10 }, SCU90, 14 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { D9,  D10 }, SCU90, 14 },
+
+	/* GPIOs U[4-7], V[0-1] (RGMII1 Rx pins) */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { E11, E10 }, SCU90, 13 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { E11, E10 }, SCU90, 13 },
+
+	/* GPIOs V[2-7] (RGMII2 Rx pins) */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { C9,  C8  }, SCU90, 15 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { C9,  C8  }, SCU90, 15 },
+
+	/* ADC pull-downs (SCUA8[19:4]) */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { L5,  L5  }, SCUA8, 4 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { L5,  L5  }, SCUA8, 4 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { L4,  L4  }, SCUA8, 5 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { L4,  L4  }, SCUA8, 5 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { L3,  L3  }, SCUA8, 6 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { L3,  L3  }, SCUA8, 6 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { L2,  L2  }, SCUA8, 7 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { L2,  L2  }, SCUA8, 7 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { L1,  L1  }, SCUA8, 8 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { L1,  L1  }, SCUA8, 8 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { M5,  M5  }, SCUA8, 9 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { M5,  M5  }, SCUA8, 9 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { M4,  M4  }, SCUA8, 10 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { M4,  M4  }, SCUA8, 10 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { M3,  M3  }, SCUA8, 11 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { M3,  M3  }, SCUA8, 11 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { M2,  M2  }, SCUA8, 12 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { M2,  M2  }, SCUA8, 12 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { M1,  M1  }, SCUA8, 13 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { M1,  M1  }, SCUA8, 13 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { N5,  N5  }, SCUA8, 14 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { N5,  N5  }, SCUA8, 14 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { N4,  N4  }, SCUA8, 15 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { N4,  N4  }, SCUA8, 15 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { N3,  N3  }, SCUA8, 16 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { N3,  N3  }, SCUA8, 16 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { N2,  N2  }, SCUA8, 17 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { N2,  N2  }, SCUA8, 17 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { N1,  N1  }, SCUA8, 18 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { N1,  N1  }, SCUA8, 18 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { P5,  P5  }, SCUA8, 19 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { P5,  P5  }, SCUA8, 19 },
+
+	/*
+	 * Debounce settings for GPIOs D and E passthrough mode are in
+	 * SCUA8[27:20] and so are managed by pinctrl. Normal GPIO debounce for
+	 * banks D and E is handled by the GPIO driver - GPIO passthrough is
+	 * treated like any other non-GPIO mux function. There is a catch
+	 * however, in that the debounce period is configured in the GPIO
+	 * controller. Due to this tangle between GPIO and pinctrl we don't yet
+	 * fully support pass-through debounce.
+	 */
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { A18, D16 }, SCUA8, 20 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { B17, A17 }, SCUA8, 21 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { C16, B16 }, SCUA8, 22 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { A16, E15 }, SCUA8, 23 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { D15, C15 }, SCUA8, 24 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { B15, A15 }, SCUA8, 25 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { E14, D14 }, SCUA8, 26 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { C14, B14 }, SCUA8, 27 },
+};
+
 static struct aspeed_pinctrl_data aspeed_g4_pinctrl_data = {
 	.pins = aspeed_g4_pins,
 	.npins = ARRAY_SIZE(aspeed_g4_pins),
@@ -2241,6 +2345,8 @@ static struct aspeed_pinctrl_data aspeed_g4_pinctrl_data = {
 	.ngroups = ARRAY_SIZE(aspeed_g4_groups),
 	.functions = aspeed_g4_functions,
 	.nfunctions = ARRAY_SIZE(aspeed_g4_functions),
+	.configs = aspeed_g4_configs,
+	.nconfigs = ARRAY_SIZE(aspeed_g4_configs),
 };
 
 static struct pinmux_ops aspeed_g4_pinmux_ops = {
@@ -2257,16 +2363,25 @@ static struct pinctrl_ops aspeed_g4_pinctrl_ops = {
 	.get_group_name = aspeed_pinctrl_get_group_name,
 	.get_group_pins = aspeed_pinctrl_get_group_pins,
 	.pin_dbg_show = aspeed_pinctrl_pin_dbg_show,
-	.dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_all,
 	.dt_free_map = pinctrl_utils_free_map,
 };
 
+static const struct pinconf_ops aspeed_g4_conf_ops = {
+	.is_generic = true,
+	.pin_config_get = aspeed_pin_config_get,
+	.pin_config_set = aspeed_pin_config_set,
+	.pin_config_group_get = aspeed_pin_config_group_get,
+	.pin_config_group_set = aspeed_pin_config_group_set,
+};
+
 static struct pinctrl_desc aspeed_g4_pinctrl_desc = {
 	.name = "aspeed-g4-pinctrl",
 	.pins = aspeed_g4_pins,
 	.npins = ARRAY_SIZE(aspeed_g4_pins),
 	.pctlops = &aspeed_g4_pinctrl_ops,
 	.pmxops = &aspeed_g4_pinmux_ops,
+	.confops = &aspeed_g4_conf_ops,
 };
 
 static int aspeed_g4_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c
index 43221a3c7e23..68aa04664a62 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c
@@ -2285,6 +2285,146 @@ static const struct aspeed_pin_function aspeed_g5_functions[] = {
 	ASPEED_PINCTRL_FUNC(WDTRST2),
 };
 
+static struct aspeed_pin_config aspeed_g5_configs[] = {
+	/* GPIOA, GPIOQ */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { B14, B13 }, SCU8C, 16 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { B14, B13 }, SCU8C, 16 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A11, N20 }, SCU8C, 16 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A11, N20 }, SCU8C, 16 },
+
+	/* GPIOB, GPIOR */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { K19, H20 }, SCU8C, 17 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { K19, H20 }, SCU8C, 17 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { AA19, E10 }, SCU8C, 17 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { AA19, E10 }, SCU8C, 17 },
+
+	/* GPIOC, GPIOS*/
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { C12, B11 }, SCU8C, 18 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { C12, B11 }, SCU8C, 18 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { V20, AA20 }, SCU8C, 18 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { V20, AA20 }, SCU8C, 18 },
+
+	/* GPIOD, GPIOY */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { F19, C21 }, SCU8C, 19 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { F19, C21 }, SCU8C, 19 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { R22, P20 }, SCU8C, 19 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { R22, P20 }, SCU8C, 19 },
+
+	/* GPIOE, GPIOZ */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { B20, B19 }, SCU8C, 20 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { B20, B19 }, SCU8C, 20 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { Y20, W21 }, SCU8C, 20 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { Y20, W21 }, SCU8C, 20 },
+
+	/* GPIOF, GPIOAA */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { J19, H18 }, SCU8C, 21 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { J19, H18 }, SCU8C, 21 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { Y21, P19 }, SCU8C, 21 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { Y21, P19 }, SCU8C, 21 },
+
+	/* GPIOG, GPIOAB */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A19, E14 }, SCU8C, 22 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A19, E14 }, SCU8C, 22 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { N19, R20 }, SCU8C, 22 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { N19, R20 }, SCU8C, 22 },
+
+	/* GPIOH, GPIOAC */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { A18,  D18  }, SCU8C, 23 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { A18,  D18  }, SCU8C, 23 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { G21,  G22  }, SCU8C, 23 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { G21,  G22  }, SCU8C, 23 },
+
+	/* GPIOs [I, P] */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { C18, A15 }, SCU8C, 24 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { C18, A15 }, SCU8C, 24 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { R2,  T3  }, SCU8C, 25 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { R2,  T3  }, SCU8C, 25 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { L3,  R1  }, SCU8C, 26 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { L3,  R1  }, SCU8C, 26 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { T2,  W1  }, SCU8C, 27 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { T2,  W1  }, SCU8C, 27 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { Y1,  T5  }, SCU8C, 28 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { Y1,  T5  }, SCU8C, 28 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { V2,  T4  }, SCU8C, 29 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { V2,  T4  }, SCU8C, 29 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { U5,  W4  }, SCU8C, 30 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { U5,  W4  }, SCU8C, 30 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { V4,  V6  }, SCU8C, 31 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { V4,  V6  }, SCU8C, 31 },
+
+	/* GPIOs T[0-5] (RGMII1 Tx pins) */
+	{ PIN_CONFIG_DRIVE_STRENGTH, { B5, B5 }, SCU90, 8 },
+	{ PIN_CONFIG_DRIVE_STRENGTH, { E9, A5 }, SCU90, 9 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { B5, D7 }, SCU90, 12 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { B5, D7 }, SCU90, 12 },
+
+	/* GPIOs T[6-7], U[0-3] (RGMII2 TX pins) */
+	{ PIN_CONFIG_DRIVE_STRENGTH, { B2, B2 }, SCU90, 10 },
+	{ PIN_CONFIG_DRIVE_STRENGTH, { B1, B3 }, SCU90, 11 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { B2, D4 }, SCU90, 14 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { B2, D4 }, SCU90, 14 },
+
+	/* GPIOs U[4-7], V[0-1] (RGMII1 Rx pins) */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { B4, C4 }, SCU90, 13 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { B4, C4 }, SCU90, 13 },
+
+	/* GPIOs V[2-7] (RGMII2 Rx pins) */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { C2, E6 }, SCU90, 15 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { C2, E6 }, SCU90, 15 },
+
+	/* ADC pull-downs (SCUA8[19:4]) */
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { F4, F4 }, SCUA8, 4 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { F4, F4 }, SCUA8, 4 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { F5, F5 }, SCUA8, 5 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { F5, F5 }, SCUA8, 5 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { E2, E2 }, SCUA8, 6 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { E2, E2 }, SCUA8, 6 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { E1, E1 }, SCUA8, 7 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { E1, E1 }, SCUA8, 7 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { F3, F3 }, SCUA8, 8 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { F3, F3 }, SCUA8, 8 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { E3, E3 }, SCUA8, 9 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { E3, E3 }, SCUA8, 9 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { G5, G5 }, SCUA8, 10 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { G5, G5 }, SCUA8, 10 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { G4, G4 }, SCUA8, 11 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { G4, G4 }, SCUA8, 11 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { F2, F2 }, SCUA8, 12 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { F2, F2 }, SCUA8, 12 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { G3, G3 }, SCUA8, 13 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { G3, G3 }, SCUA8, 13 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { G2, G2 }, SCUA8, 14 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { G2, G2 }, SCUA8, 14 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { F1, F1 }, SCUA8, 15 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { F1, F1 }, SCUA8, 15 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { H5, H5 }, SCUA8, 16 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { H5, H5 }, SCUA8, 16 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { G1, G1 }, SCUA8, 17 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { G1, G1 }, SCUA8, 17 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { H3, H3 }, SCUA8, 18 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { H3, H3 }, SCUA8, 18 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, { H4, H4 }, SCUA8, 19 },
+	{ PIN_CONFIG_BIAS_DISABLE,   { H4, H4 }, SCUA8, 19 },
+
+	/*
+	 * Debounce settings for GPIOs D and E passthrough mode are in
+	 * SCUA8[27:20] and so are managed by pinctrl. Normal GPIO debounce for
+	 * banks D and E is handled by the GPIO driver - GPIO passthrough is
+	 * treated like any other non-GPIO mux function. There is a catch
+	 * however, in that the debounce period is configured in the GPIO
+	 * controller. Due to this tangle between GPIO and pinctrl we don't yet
+	 * fully support pass-through debounce.
+	 */
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { F19, E21 }, SCUA8, 20 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { F20, D20 }, SCUA8, 21 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { D21, E20 }, SCUA8, 22 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { G18, C21 }, SCUA8, 23 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { B20, C20 }, SCUA8, 24 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { F18, F17 }, SCUA8, 25 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { E18, D19 }, SCUA8, 26 },
+	{ PIN_CONFIG_INPUT_DEBOUNCE, { A20, B19 }, SCUA8, 27 },
+};
+
 static struct aspeed_pinctrl_data aspeed_g5_pinctrl_data = {
 	.pins = aspeed_g5_pins,
 	.npins = ARRAY_SIZE(aspeed_g5_pins),
@@ -2292,6 +2432,8 @@ static struct aspeed_pinctrl_data aspeed_g5_pinctrl_data = {
 	.ngroups = ARRAY_SIZE(aspeed_g5_groups),
 	.functions = aspeed_g5_functions,
 	.nfunctions = ARRAY_SIZE(aspeed_g5_functions),
+	.configs = aspeed_g5_configs,
+	.nconfigs = ARRAY_SIZE(aspeed_g5_configs),
 };
 
 static struct pinmux_ops aspeed_g5_pinmux_ops = {
@@ -2308,16 +2450,25 @@ static struct pinctrl_ops aspeed_g5_pinctrl_ops = {
 	.get_group_name = aspeed_pinctrl_get_group_name,
 	.get_group_pins = aspeed_pinctrl_get_group_pins,
 	.pin_dbg_show = aspeed_pinctrl_pin_dbg_show,
-	.dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_all,
 	.dt_free_map = pinctrl_utils_free_map,
 };
 
+static struct pinconf_ops aspeed_g5_conf_ops = {
+	.is_generic = true,
+	.pin_config_get = aspeed_pin_config_get,
+	.pin_config_set = aspeed_pin_config_set,
+	.pin_config_group_get = aspeed_pin_config_group_get,
+	.pin_config_group_set = aspeed_pin_config_group_set,
+};
+
 static struct pinctrl_desc aspeed_g5_pinctrl_desc = {
 	.name = "aspeed-g5-pinctrl",
 	.pins = aspeed_g5_pins,
 	.npins = ARRAY_SIZE(aspeed_g5_pins),
 	.pctlops = &aspeed_g5_pinctrl_ops,
 	.pmxops = &aspeed_g5_pinmux_ops,
+	.confops = &aspeed_g5_conf_ops,
 };
 
 static int aspeed_g5_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 76f62bd45f02..a86a4d66099c 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -198,9 +198,19 @@ static int aspeed_sig_expr_set(const struct aspeed_sig_expr *expr,
 		 * them. This may mean that certain functions cannot be
 		 * deconfigured and is the reason we re-evaluate after writing
 		 * all descriptor bits.
+		 *
+		 * Port D and port E GPIO loopback modes are the only exception
+		 * as those are commonly used with front-panel buttons to allow
+		 * normal operation of the host when the BMC is powered off or
+		 * fails to boot. Once the BMC has booted, the loopback mode
+		 * must be disabled for the BMC to control host power-on and
+		 * reset.
 		 */
-		if ((desc->reg == HW_STRAP1 || desc->reg == HW_STRAP2) &&
-				desc->ip == ASPEED_IP_SCU)
+		if (desc->ip == ASPEED_IP_SCU && desc->reg == HW_STRAP1 &&
+		    !(desc->mask & (BIT(21) | BIT(22))))
+			continue;
+
+		if (desc->ip == ASPEED_IP_SCU && desc->reg == HW_STRAP2)
 			continue;
 
 		ret = regmap_update_bits(maps[desc->ip], desc->reg,
@@ -537,3 +547,214 @@ int aspeed_pinctrl_probe(struct platform_device *pdev,
 
 	return 0;
 }
+
+static inline bool pin_in_config_range(unsigned int offset,
+		const struct aspeed_pin_config *config)
+{
+	return offset >= config->pins[0] && offset <= config->pins[1];
+}
+
+static inline const struct aspeed_pin_config *find_pinconf_config(
+		const struct aspeed_pinctrl_data *pdata,
+		unsigned int offset,
+		enum pin_config_param param)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->nconfigs; i++) {
+		if (param == pdata->configs[i].param &&
+				pin_in_config_range(offset, &pdata->configs[i]))
+			return &pdata->configs[i];
+	}
+
+	return NULL;
+}
+
+/**
+ * @param: pinconf configuration parameter
+ * @arg: The supported argument for @param, or -1 if any value is supported
+ * @value: The register value to write to configure @arg for @param
+ *
+ * The map is to be used in conjunction with the configuration array supplied
+ * by the driver implementation.
+ */
+struct aspeed_pin_config_map {
+	enum pin_config_param param;
+	s32 arg;
+	u32 val;
+};
+
+enum aspeed_pin_config_map_type { MAP_TYPE_ARG, MAP_TYPE_VAL };
+
+/* Aspeed consistently both:
+ *
+ * 1. Defines "disable bits" for internal pull-downs
+ * 2. Uses 8mA or 16mA drive strengths
+ */
+static const struct aspeed_pin_config_map pin_config_map[] = {
+	{ PIN_CONFIG_BIAS_PULL_DOWN,  0, 1 },
+	{ PIN_CONFIG_BIAS_PULL_DOWN, -1, 0 },
+	{ PIN_CONFIG_BIAS_DISABLE,   -1, 1 },
+	{ PIN_CONFIG_DRIVE_STRENGTH,  8, 0 },
+	{ PIN_CONFIG_DRIVE_STRENGTH, 16, 1 },
+};
+
+static const struct aspeed_pin_config_map *find_pinconf_map(
+		enum pin_config_param param,
+		enum aspeed_pin_config_map_type type,
+		s64 value)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pin_config_map); i++) {
+		const struct aspeed_pin_config_map *elem;
+		bool match;
+
+		elem = &pin_config_map[i];
+
+		switch (type) {
+		case MAP_TYPE_ARG:
+			match = (elem->arg == -1 || elem->arg == value);
+			break;
+		case MAP_TYPE_VAL:
+			match = (elem->val == value);
+			break;
+		}
+
+		if (param == elem->param && match)
+			return elem;
+	}
+
+	return NULL;
+}
+
+int aspeed_pin_config_get(struct pinctrl_dev *pctldev, unsigned int offset,
+		unsigned long *config)
+{
+	const enum pin_config_param param = pinconf_to_config_param(*config);
+	const struct aspeed_pin_config_map *pmap;
+	const struct aspeed_pinctrl_data *pdata;
+	const struct aspeed_pin_config *pconf;
+	unsigned int val;
+	int rc = 0;
+	u32 arg;
+
+	pdata = pinctrl_dev_get_drvdata(pctldev);
+	pconf = find_pinconf_config(pdata, offset, param);
+	if (!pconf)
+		return -ENOTSUPP;
+
+	rc = regmap_read(pdata->maps[ASPEED_IP_SCU], pconf->reg, &val);
+	if (rc < 0)
+		return rc;
+
+	pmap = find_pinconf_map(param, MAP_TYPE_VAL,
+			(val & BIT(pconf->bit)) >> pconf->bit);
+
+	if (!pmap)
+		return -EINVAL;
+
+	if (param == PIN_CONFIG_DRIVE_STRENGTH)
+		arg = (u32) pmap->arg;
+	else if (param == PIN_CONFIG_BIAS_PULL_DOWN)
+		arg = !!pmap->arg;
+	else
+		arg = 1;
+
+	if (!arg)
+		return -EINVAL;
+
+	*config = pinconf_to_config_packed(param, arg);
+
+	return 0;
+}
+
+int aspeed_pin_config_set(struct pinctrl_dev *pctldev, unsigned int offset,
+		unsigned long *configs, unsigned int num_configs)
+{
+	const struct aspeed_pinctrl_data *pdata;
+	unsigned int i;
+	int rc = 0;
+
+	pdata = pinctrl_dev_get_drvdata(pctldev);
+
+	for (i = 0; i < num_configs; i++) {
+		const struct aspeed_pin_config_map *pmap;
+		const struct aspeed_pin_config *pconf;
+		enum pin_config_param param;
+		unsigned int val;
+		u32 arg;
+
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		pconf = find_pinconf_config(pdata, offset, param);
+		if (!pconf)
+			return -ENOTSUPP;
+
+		pmap = find_pinconf_map(param, MAP_TYPE_ARG, arg);
+
+		if (unlikely(WARN_ON(!pmap)))
+			return -EINVAL;
+
+		val = pmap->val << pconf->bit;
+
+		rc = regmap_update_bits(pdata->maps[ASPEED_IP_SCU], pconf->reg,
+				BIT(pconf->bit), val);
+
+		if (rc < 0)
+			return rc;
+
+		pr_debug("%s: Set SCU%02X[%d]=%d for param %d(=%d) on pin %d\n",
+				__func__, pconf->reg, pconf->bit, pmap->val,
+				param, arg, offset);
+	}
+
+	return 0;
+}
+
+int aspeed_pin_config_group_get(struct pinctrl_dev *pctldev,
+		unsigned int selector,
+		unsigned long *config)
+{
+	const unsigned int *pins;
+	unsigned int npins;
+	int rc;
+
+	rc = aspeed_pinctrl_get_group_pins(pctldev, selector, &pins, &npins);
+	if (rc < 0)
+		return rc;
+
+	if (!npins)
+		return -ENODEV;
+
+	rc = aspeed_pin_config_get(pctldev, pins[0], config);
+
+	return rc;
+}
+
+int aspeed_pin_config_group_set(struct pinctrl_dev *pctldev,
+		unsigned int selector,
+		unsigned long *configs,
+		unsigned int num_configs)
+{
+	const unsigned int *pins;
+	unsigned int npins;
+	int rc;
+	int i;
+
+	pr_debug("%s: Fetching pins for group selector %d\n",
+			__func__, selector);
+	rc = aspeed_pinctrl_get_group_pins(pctldev, selector, &pins, &npins);
+	if (rc < 0)
+		return rc;
+
+	for (i = 0; i < npins; i++) {
+		rc = aspeed_pin_config_set(pctldev, pins[i], configs,
+				num_configs);
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.h b/drivers/pinctrl/aspeed/pinctrl-aspeed.h
index 08a10d4db229..fa125db828f5 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.h
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.h
@@ -514,6 +514,20 @@ struct aspeed_pin_desc {
 	SIG_EXPR_LIST_DECL_SINGLE(gpio, gpio); \
 	MS_PIN_DECL_(pin, SIG_EXPR_LIST_PTR(gpio))
 
+/**
+ * @param The pinconf parameter type
+ * @pins The pin range this config struct covers, [low, high]
+ * @reg The register housing the configuration bits
+ * @mask The mask to select the bits of interest in @reg
+ */
+struct aspeed_pin_config {
+	enum pin_config_param param;
+	unsigned int pins[2];
+	unsigned int reg;
+	u8 bit;
+	u8 value;
+};
+
 struct aspeed_pinctrl_data {
 	struct regmap *maps[ASPEED_NR_PINMUX_IPS];
 
@@ -525,6 +539,9 @@ struct aspeed_pinctrl_data {
 
 	const struct aspeed_pin_function *functions;
 	const unsigned int nfunctions;
+
+	const struct aspeed_pin_config *configs;
+	const unsigned int nconfigs;
 };
 
 #define ASPEED_PINCTRL_PIN(name_) \
@@ -580,5 +597,16 @@ int aspeed_gpio_request_enable(struct pinctrl_dev *pctldev,
 int aspeed_pinctrl_probe(struct platform_device *pdev,
 		struct pinctrl_desc *pdesc,
 		struct aspeed_pinctrl_data *pdata);
+int aspeed_pin_config_get(struct pinctrl_dev *pctldev, unsigned int offset,
+		unsigned long *config);
+int aspeed_pin_config_set(struct pinctrl_dev *pctldev, unsigned int offset,
+		unsigned long *configs, unsigned int num_configs);
+int aspeed_pin_config_group_get(struct pinctrl_dev *pctldev,
+		unsigned int selector,
+		unsigned long *config);
+int aspeed_pin_config_group_set(struct pinctrl_dev *pctldev,
+		unsigned int selector,
+		unsigned long *configs,
+		unsigned int num_configs);
 
 #endif /* PINCTRL_ASPEED */
diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
index 3ca925dfefd1..af5e904d4a1e 100644
--- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
@@ -99,7 +99,7 @@ struct iproc_gpio {
 	void __iomem *base;
 	void __iomem *io_ctrl;
 
-	spinlock_t lock;
+	raw_spinlock_t lock;
 
 	struct gpio_chip gc;
 	unsigned num_banks;
@@ -221,9 +221,9 @@ static void iproc_gpio_irq_mask(struct irq_data *d)
 	struct iproc_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	iproc_gpio_irq_set_mask(d, false);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static void iproc_gpio_irq_unmask(struct irq_data *d)
@@ -232,9 +232,9 @@ static void iproc_gpio_irq_unmask(struct irq_data *d)
 	struct iproc_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	iproc_gpio_irq_set_mask(d, true);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static int iproc_gpio_irq_set_type(struct irq_data *d, unsigned int type)
@@ -274,13 +274,13 @@ static int iproc_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	iproc_set_bit(chip, IPROC_GPIO_INT_TYPE_OFFSET, gpio,
 		       level_triggered);
 	iproc_set_bit(chip, IPROC_GPIO_INT_DE_OFFSET, gpio, dual_edge);
 	iproc_set_bit(chip, IPROC_GPIO_INT_EDGE_OFFSET, gpio,
 		       rising_or_high);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev,
 		"gpio:%u level_triggered:%d dual_edge:%d rising_or_high:%d\n",
@@ -328,9 +328,9 @@ static int iproc_gpio_direction_input(struct gpio_chip *gc, unsigned gpio)
 	struct iproc_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	iproc_set_bit(chip, IPROC_GPIO_OUT_EN_OFFSET, gpio, false);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set input\n", gpio);
 
@@ -343,10 +343,10 @@ static int iproc_gpio_direction_output(struct gpio_chip *gc, unsigned gpio,
 	struct iproc_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	iproc_set_bit(chip, IPROC_GPIO_OUT_EN_OFFSET, gpio, true);
 	iproc_set_bit(chip, IPROC_GPIO_DATA_OUT_OFFSET, gpio, !!(val));
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set output, value:%d\n", gpio, val);
 
@@ -358,9 +358,9 @@ static void iproc_gpio_set(struct gpio_chip *gc, unsigned gpio, int val)
 	struct iproc_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	iproc_set_bit(chip, IPROC_GPIO_DATA_OUT_OFFSET, gpio, !!(val));
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set, value:%d\n", gpio, val);
 }
@@ -461,7 +461,7 @@ static int iproc_gpio_set_pull(struct iproc_gpio *chip, unsigned gpio,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 
 	if (disable) {
 		iproc_set_bit(chip, IPROC_GPIO_RES_EN_OFFSET, gpio, false);
@@ -471,7 +471,7 @@ static int iproc_gpio_set_pull(struct iproc_gpio *chip, unsigned gpio,
 		iproc_set_bit(chip, IPROC_GPIO_RES_EN_OFFSET, gpio, true);
 	}
 
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set pullup:%d\n", gpio, pull_up);
 
@@ -483,10 +483,10 @@ static void iproc_gpio_get_pull(struct iproc_gpio *chip, unsigned gpio,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	*disable = !iproc_get_bit(chip, IPROC_GPIO_RES_EN_OFFSET, gpio);
 	*pull_up = iproc_get_bit(chip, IPROC_GPIO_PAD_RES_OFFSET, gpio);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static int iproc_gpio_set_strength(struct iproc_gpio *chip, unsigned gpio,
@@ -515,7 +515,7 @@ static int iproc_gpio_set_strength(struct iproc_gpio *chip, unsigned gpio,
 	dev_dbg(chip->dev, "gpio:%u set drive strength:%d mA\n", gpio,
 		strength);
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	strength = (strength / 2) - 1;
 	for (i = 0; i < GPIO_DRV_STRENGTH_BITS; i++) {
 		val = readl(base + offset);
@@ -524,7 +524,7 @@ static int iproc_gpio_set_strength(struct iproc_gpio *chip, unsigned gpio,
 		writel(val, base + offset);
 		offset += 4;
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	return 0;
 }
@@ -548,7 +548,7 @@ static int iproc_gpio_get_strength(struct iproc_gpio *chip, unsigned gpio,
 
 	shift = IPROC_GPIO_SHIFT(gpio);
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	*strength = 0;
 	for (i = 0; i < GPIO_DRV_STRENGTH_BITS; i++) {
 		val = readl(base + offset) & BIT(shift);
@@ -559,7 +559,7 @@ static int iproc_gpio_get_strength(struct iproc_gpio *chip, unsigned gpio,
 
 	/* convert to mA */
 	*strength = (*strength + 1) * 2;
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	return 0;
 }
@@ -769,7 +769,7 @@ static int iproc_gpio_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	spin_lock_init(&chip->lock);
+	raw_spin_lock_init(&chip->lock);
 
 	gc = &chip->gc;
 	gc->base = -1;
diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
index 91ea32dc1e7f..22442438275a 100644
--- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
@@ -73,7 +73,7 @@ struct nsp_gpio {
 	struct pinctrl_dev *pctl;
 	struct pinctrl_desc pctldesc;
 	struct irq_domain *irq_domain;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 };
 
 enum base_type {
@@ -203,9 +203,9 @@ static void nsp_gpio_irq_mask(struct irq_data *d)
 	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	nsp_gpio_irq_set_mask(d, false);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static void nsp_gpio_irq_unmask(struct irq_data *d)
@@ -213,9 +213,9 @@ static void nsp_gpio_irq_unmask(struct irq_data *d)
 	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	nsp_gpio_irq_set_mask(d, true);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static int nsp_gpio_irq_set_type(struct irq_data *d, unsigned int type)
@@ -226,7 +226,7 @@ static int nsp_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	bool falling;
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	falling = nsp_get_bit(chip, REG, NSP_GPIO_EVENT_INT_POLARITY, gpio);
 	level_low = nsp_get_bit(chip, REG, NSP_GPIO_INT_POLARITY, gpio);
 
@@ -250,13 +250,13 @@ static int nsp_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	default:
 		dev_err(chip->dev, "invalid GPIO IRQ type 0x%x\n",
 			type);
-		spin_unlock_irqrestore(&chip->lock, flags);
+		raw_spin_unlock_irqrestore(&chip->lock, flags);
 		return -EINVAL;
 	}
 
 	nsp_set_bit(chip, REG, NSP_GPIO_EVENT_INT_POLARITY, gpio, falling);
 	nsp_set_bit(chip, REG, NSP_GPIO_INT_POLARITY, gpio, level_low);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u level_low:%s falling:%s\n", gpio,
 		level_low ? "true" : "false", falling ? "true" : "false");
@@ -295,9 +295,9 @@ static int nsp_gpio_direction_input(struct gpio_chip *gc, unsigned gpio)
 	struct nsp_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	nsp_set_bit(chip, REG, NSP_GPIO_OUT_EN, gpio, false);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set input\n", gpio);
 	return 0;
@@ -309,10 +309,10 @@ static int nsp_gpio_direction_output(struct gpio_chip *gc, unsigned gpio,
 	struct nsp_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	nsp_set_bit(chip, REG, NSP_GPIO_OUT_EN, gpio, true);
 	nsp_set_bit(chip, REG, NSP_GPIO_DATA_OUT, gpio, !!(val));
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set output, value:%d\n", gpio, val);
 	return 0;
@@ -323,9 +323,9 @@ static void nsp_gpio_set(struct gpio_chip *gc, unsigned gpio, int val)
 	struct nsp_gpio *chip = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	nsp_set_bit(chip, REG, NSP_GPIO_DATA_OUT, gpio, !!(val));
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set, value:%d\n", gpio, val);
 }
@@ -381,10 +381,10 @@ static int nsp_gpio_set_pull(struct nsp_gpio *chip, unsigned gpio,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	nsp_set_bit(chip, IO_CTRL, NSP_PULL_DOWN_EN, gpio, pull_down);
 	nsp_set_bit(chip, IO_CTRL, NSP_PULL_UP_EN, gpio, pull_up);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	dev_dbg(chip->dev, "gpio:%u set pullup:%d pulldown: %d\n",
 		gpio, pull_up, pull_down);
@@ -396,10 +396,10 @@ static void nsp_gpio_get_pull(struct nsp_gpio *chip, unsigned gpio,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	*pull_up = nsp_get_bit(chip, IO_CTRL, NSP_PULL_UP_EN, gpio);
 	*pull_down = nsp_get_bit(chip, IO_CTRL, NSP_PULL_DOWN_EN, gpio);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static int nsp_gpio_set_strength(struct nsp_gpio *chip, unsigned gpio,
@@ -417,7 +417,7 @@ static int nsp_gpio_set_strength(struct nsp_gpio *chip, unsigned gpio,
 	offset = NSP_GPIO_DRV_CTRL;
 	dev_dbg(chip->dev, "gpio:%u set drive strength:%d mA\n", gpio,
 		strength);
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	strength = (strength / 2) - 1;
 	for (i = GPIO_DRV_STRENGTH_BITS; i > 0; i--) {
 		val = readl(chip->io_ctrl + offset);
@@ -426,7 +426,7 @@ static int nsp_gpio_set_strength(struct nsp_gpio *chip, unsigned gpio,
 		writel(val, chip->io_ctrl + offset);
 		offset += 4;
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	return 0;
 }
@@ -442,7 +442,7 @@ static int nsp_gpio_get_strength(struct nsp_gpio *chip, unsigned gpio,
 	offset = NSP_GPIO_DRV_CTRL;
 	shift = gpio;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	raw_spin_lock_irqsave(&chip->lock, flags);
 	*strength = 0;
 	for (i = (GPIO_DRV_STRENGTH_BITS - 1); i >= 0; i--) {
 		val = readl(chip->io_ctrl + offset) & BIT(shift);
@@ -453,7 +453,7 @@ static int nsp_gpio_get_strength(struct nsp_gpio *chip, unsigned gpio,
 
 	/* convert to mA */
 	*strength = (*strength + 1) * 2;
-	spin_unlock_irqrestore(&chip->lock, flags);
+	raw_spin_unlock_irqrestore(&chip->lock, flags);
 
 	return 0;
 }
@@ -660,7 +660,7 @@ static int nsp_gpio_probe(struct platform_device *pdev)
 		return PTR_ERR(chip->io_ctrl);
 	}
 
-	spin_lock_init(&chip->lock);
+	raw_spin_lock_init(&chip->lock);
 	gc = &chip->gc;
 	gc->base = -1;
 	gc->can_sleep = false;
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index d69046537b75..1653cbda6a82 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -525,7 +525,7 @@ pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_find_gpio_range_from_pin);
 
 /**
- * pinctrl_remove_gpio_range() - remove a range of GPIOs fro a pin controller
+ * pinctrl_remove_gpio_range() - remove a range of GPIOs from a pin controller
  * @pctldev: pin controller device to remove the range from
  * @range: the GPIO range to remove
  */
@@ -1062,7 +1062,7 @@ static struct pinctrl *create_pinctrl(struct device *dev,
 	mutex_unlock(&pinctrl_maps_mutex);
 
 	if (ret < 0) {
-		/* If some other error than deferral occured, return here */
+		/* If some other error than deferral occurred, return here */
 		pinctrl_free(p, false);
 		return ERR_PTR(ret);
 	}
@@ -1939,9 +1939,9 @@ static int pinctrl_check_ops(struct pinctrl_dev *pctldev)
  * @dev: parent device for this pin controller
  * @driver_data: private pin controller data for this pin controller
  */
-struct pinctrl_dev *pinctrl_init_controller(struct pinctrl_desc *pctldesc,
-					    struct device *dev,
-					    void *driver_data)
+static struct pinctrl_dev *
+pinctrl_init_controller(struct pinctrl_desc *pctldesc, struct device *dev,
+			void *driver_data)
 {
 	struct pinctrl_dev *pctldev;
 	int ret;
@@ -2010,29 +2010,57 @@ out_err:
 	return ERR_PTR(ret);
 }
 
-static int pinctrl_create_and_start(struct pinctrl_dev *pctldev)
+static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
 {
 	pctldev->p = create_pinctrl(pctldev->dev, pctldev);
-	if (!IS_ERR(pctldev->p)) {
-		kref_get(&pctldev->p->users);
-		pctldev->hog_default =
-			pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
-		if (IS_ERR(pctldev->hog_default)) {
-			dev_dbg(pctldev->dev,
-				"failed to lookup the default state\n");
-		} else {
-			if (pinctrl_select_state(pctldev->p,
-						pctldev->hog_default))
-				dev_err(pctldev->dev,
-					"failed to select default state\n");
-		}
+	if (PTR_ERR(pctldev->p) == -ENODEV) {
+		dev_dbg(pctldev->dev, "no hogs found\n");
 
-		pctldev->hog_sleep =
-			pinctrl_lookup_state(pctldev->p,
-						    PINCTRL_STATE_SLEEP);
-		if (IS_ERR(pctldev->hog_sleep))
-			dev_dbg(pctldev->dev,
-				"failed to lookup the sleep state\n");
+		return 0;
+	}
+
+	if (IS_ERR(pctldev->p)) {
+		dev_err(pctldev->dev, "error claiming hogs: %li\n",
+			PTR_ERR(pctldev->p));
+
+		return PTR_ERR(pctldev->p);
+	}
+
+	kref_get(&pctldev->p->users);
+	pctldev->hog_default =
+		pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
+	if (IS_ERR(pctldev->hog_default)) {
+		dev_dbg(pctldev->dev,
+			"failed to lookup the default state\n");
+	} else {
+		if (pinctrl_select_state(pctldev->p,
+					 pctldev->hog_default))
+			dev_err(pctldev->dev,
+				"failed to select default state\n");
+	}
+
+	pctldev->hog_sleep =
+		pinctrl_lookup_state(pctldev->p,
+				     PINCTRL_STATE_SLEEP);
+	if (IS_ERR(pctldev->hog_sleep))
+		dev_dbg(pctldev->dev,
+			"failed to lookup the sleep state\n");
+
+	return 0;
+}
+
+int pinctrl_enable(struct pinctrl_dev *pctldev)
+{
+	int error;
+
+	error = pinctrl_claim_hogs(pctldev);
+	if (error) {
+		dev_err(pctldev->dev, "could not claim hogs: %i\n",
+			error);
+		mutex_destroy(&pctldev->mutex);
+		kfree(pctldev);
+
+		return error;
 	}
 
 	mutex_lock(&pinctrldev_list_mutex);
@@ -2043,6 +2071,7 @@ static int pinctrl_create_and_start(struct pinctrl_dev *pctldev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pinctrl_enable);
 
 /**
  * pinctrl_register() - register a pin controller device
@@ -2065,25 +2094,30 @@ struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
 	if (IS_ERR(pctldev))
 		return pctldev;
 
-	error = pinctrl_create_and_start(pctldev);
-	if (error) {
-		mutex_destroy(&pctldev->mutex);
-		kfree(pctldev);
-
+	error = pinctrl_enable(pctldev);
+	if (error)
 		return ERR_PTR(error);
-	}
 
 	return pctldev;
 
 }
 EXPORT_SYMBOL_GPL(pinctrl_register);
 
+/**
+ * pinctrl_register_and_init() - register and init pin controller device
+ * @pctldesc: descriptor for this pin controller
+ * @dev: parent device for this pin controller
+ * @driver_data: private pin controller data for this pin controller
+ * @pctldev: pin controller device
+ *
+ * Note that pinctrl_enable() still needs to be manually called after
+ * this once the driver is ready.
+ */
 int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
 			      struct device *dev, void *driver_data,
 			      struct pinctrl_dev **pctldev)
 {
 	struct pinctrl_dev *p;
-	int error;
 
 	p = pinctrl_init_controller(pctldesc, dev, driver_data);
 	if (IS_ERR(p))
@@ -2097,15 +2131,6 @@ int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
 	 */
 	*pctldev = p;
 
-	error = pinctrl_create_and_start(p);
-	if (error) {
-		mutex_destroy(&p->mutex);
-		kfree(p);
-		*pctldev = NULL;
-
-		return error;
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pinctrl_register_and_init);
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index a7ace9e1ad81..74bd90dfd7b1 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -790,7 +790,7 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 
 	dev_info(&pdev->dev, "initialized IMX pinctrl driver\n");
 
-	return 0;
+	return pinctrl_enable(ipctl->pctl);
 
 free:
 	imx_free_resources(ipctl);
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index f80134e3e0b6..2debba62fac9 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -13,6 +13,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/dmi.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -148,6 +149,7 @@ struct chv_community {
 	size_t ngpio_ranges;
 	size_t ngpios;
 	size_t nirqs;
+	acpi_adr_space_type acpi_space_id;
 };
 
 struct chv_pin_context {
@@ -404,6 +406,7 @@ static const struct chv_community southwest_community = {
 	 * trigger GPEs.
 	 */
 	.nirqs = 8,
+	.acpi_space_id = 0x91,
 };
 
 static const struct pinctrl_pin_desc north_pins[] = {
@@ -493,6 +496,7 @@ static const struct chv_community north_community = {
 	 * GPEs.
 	 */
 	.nirqs = 8,
+	.acpi_space_id = 0x92,
 };
 
 static const struct pinctrl_pin_desc east_pins[] = {
@@ -536,6 +540,7 @@ static const struct chv_community east_community = {
 	.ngpio_ranges = ARRAY_SIZE(east_gpio_ranges),
 	.ngpios = ARRAY_SIZE(east_pins),
 	.nirqs = 16,
+	.acpi_space_id = 0x93,
 };
 
 static const struct pinctrl_pin_desc southeast_pins[] = {
@@ -662,6 +667,7 @@ static const struct chv_community southeast_community = {
 	.ngpio_ranges = ARRAY_SIZE(southeast_gpio_ranges),
 	.ngpios = ARRAY_SIZE(southeast_pins),
 	.nirqs = 16,
+	.acpi_space_id = 0x94,
 };
 
 static const struct chv_community *chv_communities[] = {
@@ -1524,10 +1530,31 @@ static void chv_gpio_irq_handler(struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
+/*
+ * Certain machines seem to hardcode Linux IRQ numbers in their ACPI
+ * tables. Since we leave GPIOs that are not capable of generating
+ * interrupts out of the irqdomain the numbering will be different and
+ * cause devices using the hardcoded IRQ numbers fail. In order not to
+ * break such machines we will only mask pins from irqdomain if the machine
+ * is not listed below.
+ */
+static const struct dmi_system_id chv_no_valid_mask[] = {
+	{
+		/* See https://bugzilla.kernel.org/show_bug.cgi?id=194945 */
+		.ident = "Acer Chromebook (CYAN)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"),
+			DMI_MATCH(DMI_BIOS_DATE, "05/21/2016"),
+		},
+	}
+};
+
 static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 {
 	const struct chv_gpio_pinrange *range;
 	struct gpio_chip *chip = &pctrl->chip;
+	bool need_valid_mask = !dmi_check_system(chv_no_valid_mask);
 	int ret, i, offset;
 
 	*chip = chv_gpio_chip;
@@ -1536,7 +1563,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 	chip->label = dev_name(pctrl->dev);
 	chip->parent = pctrl->dev;
 	chip->base = -1;
-	chip->irq_need_valid_mask = true;
+	chip->irq_need_valid_mask = need_valid_mask;
 
 	ret = devm_gpiochip_add_data(pctrl->dev, chip, pctrl);
 	if (ret) {
@@ -1567,7 +1594,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 		intsel &= CHV_PADCTRL0_INTSEL_MASK;
 		intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
 
-		if (intsel >= pctrl->community->nirqs)
+		if (need_valid_mask && intsel >= pctrl->community->nirqs)
 			clear_bit(i, chip->irq_valid_mask);
 	}
 
@@ -1586,11 +1613,34 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 	return 0;
 }
 
+static acpi_status chv_pinctrl_mmio_access_handler(u32 function,
+	acpi_physical_address address, u32 bits, u64 *value,
+	void *handler_context, void *region_context)
+{
+	struct chv_pinctrl *pctrl = region_context;
+	unsigned long flags;
+	acpi_status ret = AE_OK;
+
+	raw_spin_lock_irqsave(&chv_lock, flags);
+
+	if (function == ACPI_WRITE)
+		chv_writel((u32)(*value), pctrl->regs + (u32)address);
+	else if (function == ACPI_READ)
+		*value = readl(pctrl->regs + (u32)address);
+	else
+		ret = AE_BAD_PARAMETER;
+
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
+
+	return ret;
+}
+
 static int chv_pinctrl_probe(struct platform_device *pdev)
 {
 	struct chv_pinctrl *pctrl;
 	struct acpi_device *adev;
 	struct resource *res;
+	acpi_status status;
 	int ret, irq, i;
 
 	adev = ACPI_COMPANION(&pdev->dev);
@@ -1646,11 +1696,29 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	status = acpi_install_address_space_handler(adev->handle,
+					pctrl->community->acpi_space_id,
+					chv_pinctrl_mmio_access_handler,
+					NULL, pctrl);
+	if (ACPI_FAILURE(status))
+		dev_err(&pdev->dev, "failed to install ACPI addr space handler\n");
+
 	platform_set_drvdata(pdev, pctrl);
 
 	return 0;
 }
 
+static int chv_pinctrl_remove(struct platform_device *pdev)
+{
+	struct chv_pinctrl *pctrl = platform_get_drvdata(pdev);
+
+	acpi_remove_address_space_handler(ACPI_COMPANION(&pdev->dev),
+					  pctrl->community->acpi_space_id,
+					  chv_pinctrl_mmio_access_handler);
+
+	return 0;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int chv_pinctrl_suspend_noirq(struct device *dev)
 {
@@ -1758,6 +1826,7 @@ MODULE_DEVICE_TABLE(acpi, chv_pinctrl_acpi_match);
 
 static struct platform_driver chv_pinctrl_driver = {
 	.probe = chv_pinctrl_probe,
+	.remove = chv_pinctrl_remove,
 	.driver = {
 		.name = "cherryview-pinctrl",
 		.pm = &chv_pinctrl_pm_ops,
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index 7671424d46cb..9b00be15d258 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -236,6 +236,12 @@ static const unsigned int hdmi_hpd_pins[]	= { PIN(GPIOH_0, EE_OFF) };
 static const unsigned int hdmi_sda_pins[]	= { PIN(GPIOH_1, EE_OFF) };
 static const unsigned int hdmi_scl_pins[]	= { PIN(GPIOH_2, EE_OFF) };
 
+static const unsigned int i2s_out_ch23_y_pins[]	= { PIN(GPIOY_8, EE_OFF) };
+static const unsigned int i2s_out_ch45_y_pins[]	= { PIN(GPIOY_9, EE_OFF) };
+static const unsigned int i2s_out_ch67_y_pins[]	= { PIN(GPIOY_10, EE_OFF) };
+
+static const unsigned int spdif_out_y_pins[]	= { PIN(GPIOY_12, EE_OFF) };
+
 static const struct pinctrl_pin_desc meson_gxbb_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0, 0),
 	MESON_PIN(GPIOAO_1, 0),
@@ -274,6 +280,16 @@ static const unsigned int pwm_ao_a_6_pins[]	= { PIN(GPIOAO_6, 0) };
 static const unsigned int pwm_ao_a_12_pins[]	= { PIN(GPIOAO_12, 0) };
 static const unsigned int pwm_ao_b_pins[]	= { PIN(GPIOAO_13, 0) };
 
+static const unsigned int i2s_am_clk_pins[]	 = { PIN(GPIOAO_8, 0) };
+static const unsigned int i2s_out_ao_clk_pins[]	 = { PIN(GPIOAO_9, 0) };
+static const unsigned int i2s_out_lr_clk_pins[]	 = { PIN(GPIOAO_10, 0) };
+static const unsigned int i2s_out_ch01_ao_pins[] = { PIN(GPIOAO_11, 0) };
+static const unsigned int i2s_out_ch23_ao_pins[] = { PIN(GPIOAO_12, 0) };
+static const unsigned int i2s_out_ch45_ao_pins[] = { PIN(GPIOAO_13, 0) };
+
+static const unsigned int spdif_out_ao_6_pins[]	= { PIN(GPIOAO_6, 0) };
+static const unsigned int spdif_out_ao_13_pins[] = { PIN(GPIOAO_13, 0) };
+
 static struct meson_pmx_group meson_gxbb_periphs_groups[] = {
 	GPIO_GROUP(GPIOZ_0, EE_OFF),
 	GPIO_GROUP(GPIOZ_1, EE_OFF),
@@ -426,6 +442,10 @@ static struct meson_pmx_group meson_gxbb_periphs_groups[] = {
 	GROUP(uart_rx_c,	1,	16),
 	GROUP(pwm_a_y,		1,	21),
 	GROUP(pwm_f_y,		1,	20),
+	GROUP(i2s_out_ch23_y,	1,	5),
+	GROUP(i2s_out_ch45_y,	1,	6),
+	GROUP(i2s_out_ch67_y,	1,	7),
+	GROUP(spdif_out_y,	1,	9),
 
 	/* Bank Z */
 	GROUP(eth_mdio,		6,	1),
@@ -523,6 +543,14 @@ static struct meson_pmx_group meson_gxbb_aobus_groups[] = {
 	GROUP(pwm_ao_a_6,	0,	18),
 	GROUP(pwm_ao_a_12,	0,	17),
 	GROUP(pwm_ao_b,		0,	3),
+	GROUP(i2s_am_clk,	0,	30),
+	GROUP(i2s_out_ao_clk,	0,	29),
+	GROUP(i2s_out_lr_clk,	0,	28),
+	GROUP(i2s_out_ch01_ao,	0,	27),
+	GROUP(i2s_out_ch23_ao,	1,	0),
+	GROUP(i2s_out_ch45_ao,	1,	1),
+	GROUP(spdif_out_ao_6,	0,	16),
+	GROUP(spdif_out_ao_13,	0,	4),
 };
 
 static const char * const gpio_periphs_groups[] = {
@@ -652,6 +680,14 @@ static const char * const hdmi_i2c_groups[] = {
 	"hdmi_sda", "hdmi_scl",
 };
 
+static const char * const i2s_out_groups[] = {
+	"i2s_out_ch23_y", "i2s_out_ch45_y", "i2s_out_ch67_y",
+};
+
+static const char * const spdif_out_groups[] = {
+	"spdif_out_y",
+};
+
 static const char * const gpio_aobus_groups[] = {
 	"GPIOAO_0", "GPIOAO_1", "GPIOAO_2", "GPIOAO_3", "GPIOAO_4",
 	"GPIOAO_5", "GPIOAO_6", "GPIOAO_7", "GPIOAO_8", "GPIOAO_9",
@@ -667,11 +703,11 @@ static const char * const uart_ao_b_groups[] = {
 };
 
 static const char * const i2c_ao_groups[] = {
-	"i2c_sdk_ao", "i2c_sda_ao",
+	"i2c_sck_ao", "i2c_sda_ao",
 };
 
 static const char * const i2c_slave_ao_groups[] = {
-	"i2c_slave_sdk_ao", "i2c_slave_sda_ao",
+	"i2c_slave_sck_ao", "i2c_slave_sda_ao",
 };
 
 static const char * const remote_input_ao_groups[] = {
@@ -694,6 +730,15 @@ static const char * const pwm_ao_b_groups[] = {
 	"pwm_ao_b",
 };
 
+static const char * const i2s_out_ao_groups[] = {
+	"i2s_am_clk", "i2s_out_ao_clk", "i2s_out_lr_clk",
+	"i2s_out_ch01_ao", "i2s_out_ch23_ao", "i2s_out_ch45_ao",
+};
+
+static const char * const spdif_out_ao_groups[] = {
+	"spdif_out_ao_6", "spdif_out_ao_13",
+};
+
 static struct meson_pmx_func meson_gxbb_periphs_functions[] = {
 	FUNCTION(gpio_periphs),
 	FUNCTION(emmc),
@@ -717,6 +762,8 @@ static struct meson_pmx_func meson_gxbb_periphs_functions[] = {
 	FUNCTION(pwm_f_y),
 	FUNCTION(hdmi_hpd),
 	FUNCTION(hdmi_i2c),
+	FUNCTION(i2s_out),
+	FUNCTION(spdif_out),
 };
 
 static struct meson_pmx_func meson_gxbb_aobus_functions[] = {
@@ -730,6 +777,8 @@ static struct meson_pmx_func meson_gxbb_aobus_functions[] = {
 	FUNCTION(pwm_ao_a_6),
 	FUNCTION(pwm_ao_a_12),
 	FUNCTION(pwm_ao_b),
+	FUNCTION(i2s_out_ao),
+	FUNCTION(spdif_out_ao),
 };
 
 static struct meson_bank meson_gxbb_periphs_banks[] = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
index 4ab94a85e306..998210eacf37 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
@@ -136,6 +136,11 @@ static const unsigned int emmc_clk_pins[] = { PIN(BOOT_8, EE_OFF) };
 static const unsigned int emmc_cmd_pins[] = { PIN(BOOT_10, EE_OFF) };
 static const unsigned int emmc_ds_pins[] = { PIN(BOOT_15, EE_OFF) };
 
+static const unsigned int nor_d_pins[]		= { PIN(BOOT_11, EE_OFF) };
+static const unsigned int nor_q_pins[]		= { PIN(BOOT_12, EE_OFF) };
+static const unsigned int nor_c_pins[]		= { PIN(BOOT_13, EE_OFF) };
+static const unsigned int nor_cs_pins[]		= { PIN(BOOT_15, EE_OFF) };
+
 static const unsigned int sdcard_d0_pins[] = { PIN(CARD_1, EE_OFF) };
 static const unsigned int sdcard_d1_pins[] = { PIN(CARD_0, EE_OFF) };
 static const unsigned int sdcard_d2_pins[] = { PIN(CARD_5, EE_OFF) };
@@ -167,9 +172,13 @@ static const unsigned int uart_rts_a_pins[]	= { PIN(GPIOX_15, EE_OFF) };
 
 static const unsigned int uart_tx_b_pins[]	= { PIN(GPIODV_24, EE_OFF) };
 static const unsigned int uart_rx_b_pins[]	= { PIN(GPIODV_25, EE_OFF) };
+static const unsigned int uart_cts_b_pins[]	= { PIN(GPIODV_26, EE_OFF) };
+static const unsigned int uart_rts_b_pins[]	= { PIN(GPIODV_27, EE_OFF) };
 
 static const unsigned int uart_tx_c_pins[]	= { PIN(GPIOX_8, EE_OFF) };
 static const unsigned int uart_rx_c_pins[]	= { PIN(GPIOX_9, EE_OFF) };
+static const unsigned int uart_cts_c_pins[]	= { PIN(GPIOX_10, EE_OFF) };
+static const unsigned int uart_rts_c_pins[]	= { PIN(GPIOX_11, EE_OFF) };
 
 static const unsigned int i2c_sck_a_pins[]	= { PIN(GPIODV_25, EE_OFF) };
 static const unsigned int i2c_sda_a_pins[]	= { PIN(GPIODV_24, EE_OFF) };
@@ -180,6 +189,9 @@ static const unsigned int i2c_sda_b_pins[]	= { PIN(GPIODV_26, EE_OFF) };
 static const unsigned int i2c_sck_c_pins[]	= { PIN(GPIODV_29, EE_OFF) };
 static const unsigned int i2c_sda_c_pins[]	= { PIN(GPIODV_28, EE_OFF) };
 
+static const unsigned int i2c_sck_c_dv19_pins[]	= { PIN(GPIODV_19, EE_OFF) };
+static const unsigned int i2c_sda_c_dv18_pins[]	= { PIN(GPIODV_18, EE_OFF) };
+
 static const unsigned int eth_mdio_pins[]	= { PIN(GPIOZ_0, EE_OFF) };
 static const unsigned int eth_mdc_pins[]	= { PIN(GPIOZ_1, EE_OFF) };
 static const unsigned int eth_clk_rx_clk_pins[]	= { PIN(GPIOZ_2, EE_OFF) };
@@ -195,12 +207,33 @@ static const unsigned int eth_txd1_pins[]	= { PIN(GPIOZ_11, EE_OFF) };
 static const unsigned int eth_txd2_pins[]	= { PIN(GPIOZ_12, EE_OFF) };
 static const unsigned int eth_txd3_pins[]	= { PIN(GPIOZ_13, EE_OFF) };
 
+static const unsigned int pwm_a_pins[]		= { PIN(GPIOX_6, EE_OFF) };
+
+static const unsigned int pwm_b_pins[]		= { PIN(GPIODV_29, EE_OFF) };
+
+static const unsigned int pwm_c_pins[]		= { PIN(GPIOZ_15, EE_OFF) };
+
+static const unsigned int pwm_d_pins[]		= { PIN(GPIODV_28, EE_OFF) };
+
 static const unsigned int pwm_e_pins[]		= { PIN(GPIOX_16, EE_OFF) };
 
+static const unsigned int pwm_f_clk_pins[]	= { PIN(GPIOCLK_1, EE_OFF) };
+static const unsigned int pwm_f_x_pins[]	= { PIN(GPIOX_7, EE_OFF) };
+
 static const unsigned int hdmi_hpd_pins[]	= { PIN(GPIOH_0, EE_OFF) };
 static const unsigned int hdmi_sda_pins[]	= { PIN(GPIOH_1, EE_OFF) };
 static const unsigned int hdmi_scl_pins[]	= { PIN(GPIOH_2, EE_OFF) };
 
+static const unsigned int i2s_am_clk_pins[]	= { PIN(GPIOH_6, EE_OFF) };
+static const unsigned int i2s_out_ao_clk_pins[]	= { PIN(GPIOH_7, EE_OFF) };
+static const unsigned int i2s_out_lr_clk_pins[]	= { PIN(GPIOH_8, EE_OFF) };
+static const unsigned int i2s_out_ch01_pins[]	= { PIN(GPIOH_9, EE_OFF) };
+static const unsigned int i2s_out_ch23_z_pins[]	= { PIN(GPIOZ_5, EE_OFF) };
+static const unsigned int i2s_out_ch45_z_pins[]	= { PIN(GPIOZ_6, EE_OFF) };
+static const unsigned int i2s_out_ch67_z_pins[]	= { PIN(GPIOZ_7, EE_OFF) };
+
+static const unsigned int spdif_out_h_pins[]	= { PIN(GPIOH_4, EE_OFF) };
+
 static const struct pinctrl_pin_desc meson_gxl_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0, 0),
 	MESON_PIN(GPIOAO_1, 0),
@@ -216,6 +249,8 @@ static const struct pinctrl_pin_desc meson_gxl_aobus_pins[] = {
 
 static const unsigned int uart_tx_ao_a_pins[]	= { PIN(GPIOAO_0, 0) };
 static const unsigned int uart_rx_ao_a_pins[]	= { PIN(GPIOAO_1, 0) };
+static const unsigned int uart_tx_ao_b_0_pins[]	= { PIN(GPIOAO_0, 0) };
+static const unsigned int uart_rx_ao_b_1_pins[]	= { PIN(GPIOAO_1, 0) };
 static const unsigned int uart_cts_ao_a_pins[]	= { PIN(GPIOAO_2, 0) };
 static const unsigned int uart_rts_ao_a_pins[]	= { PIN(GPIOAO_3, 0) };
 static const unsigned int uart_tx_ao_b_pins[]	= { PIN(GPIOAO_4, 0) };
@@ -223,9 +258,24 @@ static const unsigned int uart_rx_ao_b_pins[]	= { PIN(GPIOAO_5, 0) };
 static const unsigned int uart_cts_ao_b_pins[]	= { PIN(GPIOAO_2, 0) };
 static const unsigned int uart_rts_ao_b_pins[]	= { PIN(GPIOAO_3, 0) };
 
+static const unsigned int i2c_sck_ao_pins[] = {PIN(GPIOAO_4, 0) };
+static const unsigned int i2c_sda_ao_pins[] = {PIN(GPIOAO_5, 0) };
+static const unsigned int i2c_slave_sck_ao_pins[] = {PIN(GPIOAO_4, 0) };
+static const unsigned int i2c_slave_sda_ao_pins[] = {PIN(GPIOAO_5, 0) };
+
 static const unsigned int remote_input_ao_pins[] = {PIN(GPIOAO_7, 0) };
 
+static const unsigned int pwm_ao_a_3_pins[]	= { PIN(GPIOAO_3, 0) };
+static const unsigned int pwm_ao_a_8_pins[]	= { PIN(GPIOAO_8, 0) };
+
 static const unsigned int pwm_ao_b_pins[]	= { PIN(GPIOAO_9, 0) };
+static const unsigned int pwm_ao_b_6_pins[]	= { PIN(GPIOAO_6, 0) };
+
+static const unsigned int i2s_out_ch23_ao_pins[] = { PIN(GPIOAO_8, EE_OFF) };
+static const unsigned int i2s_out_ch45_ao_pins[] = { PIN(GPIOAO_9, EE_OFF) };
+
+static const unsigned int spdif_out_ao_6_pins[]	= { PIN(GPIOAO_6, EE_OFF) };
+static const unsigned int spdif_out_ao_9_pins[]	= { PIN(GPIOAO_9, EE_OFF) };
 
 static struct meson_pmx_group meson_gxl_periphs_groups[] = {
 	GPIO_GROUP(GPIOZ_0, EE_OFF),
@@ -341,8 +391,8 @@ static struct meson_pmx_group meson_gxl_periphs_groups[] = {
 	GROUP(sdio_d1,		5,	30),
 	GROUP(sdio_d2,		5,	29),
 	GROUP(sdio_d3,		5,	28),
-	GROUP(sdio_cmd,		5,	27),
-	GROUP(sdio_clk,		5,	26),
+	GROUP(sdio_clk,		5,	27),
+	GROUP(sdio_cmd,		5,	26),
 	GROUP(sdio_irq,		5,	24),
 	GROUP(uart_tx_a,	5,	19),
 	GROUP(uart_rx_a,	5,	18),
@@ -350,11 +400,15 @@ static struct meson_pmx_group meson_gxl_periphs_groups[] = {
 	GROUP(uart_rts_a,	5,	16),
 	GROUP(uart_tx_c,	5,	13),
 	GROUP(uart_rx_c,	5,	12),
+	GROUP(uart_cts_c,	5,	11),
+	GROUP(uart_rts_c,	5,	10),
+	GROUP(pwm_a,		5,	25),
 	GROUP(pwm_e,		5,	15),
+	GROUP(pwm_f_x,		5,	14),
 
 	/* Bank Z */
-	GROUP(eth_mdio,		4,	22),
-	GROUP(eth_mdc,		4,	23),
+	GROUP(eth_mdio,		4,	23),
+	GROUP(eth_mdc,		4,	22),
 	GROUP(eth_clk_rx_clk,	4,	21),
 	GROUP(eth_rx_dv,	4,	20),
 	GROUP(eth_rxd0,		4,	19),
@@ -367,27 +421,46 @@ static struct meson_pmx_group meson_gxl_periphs_groups[] = {
 	GROUP(eth_txd1,		4,	12),
 	GROUP(eth_txd2,		4,	11),
 	GROUP(eth_txd3,		4,	10),
+	GROUP(pwm_c,		3,	20),
+	GROUP(i2s_out_ch23_z,	3,	26),
+	GROUP(i2s_out_ch45_z,	3,	25),
+	GROUP(i2s_out_ch67_z,	3,	24),
 
 	/* Bank H */
 	GROUP(hdmi_hpd,		6,	31),
 	GROUP(hdmi_sda,		6,	30),
 	GROUP(hdmi_scl,		6,	29),
+	GROUP(i2s_am_clk,	6,	26),
+	GROUP(i2s_out_ao_clk,	6,	25),
+	GROUP(i2s_out_lr_clk,	6,	24),
+	GROUP(i2s_out_ch01,	6,	23),
+	GROUP(spdif_out_h,	6,	28),
 
 	/* Bank DV */
 	GROUP(uart_tx_b,	2,	16),
 	GROUP(uart_rx_b,	2,	15),
-	GROUP(i2c_sck_a,	1,	15),
-	GROUP(i2c_sda_a,	1,	14),
-	GROUP(i2c_sck_b,	1,	13),
-	GROUP(i2c_sda_b,	1,	12),
-	GROUP(i2c_sck_c,	1,	11),
-	GROUP(i2c_sda_c,	1,	10),
+	GROUP(uart_cts_b,	2,	14),
+	GROUP(uart_rts_b,	2,	13),
+	GROUP(i2c_sda_c_dv18,	1,	17),
+	GROUP(i2c_sck_c_dv19,	1,	16),
+	GROUP(i2c_sda_a,	1,	15),
+	GROUP(i2c_sck_a,	1,	14),
+	GROUP(i2c_sda_b,	1,	13),
+	GROUP(i2c_sck_b,	1,	12),
+	GROUP(i2c_sda_c,	1,	11),
+	GROUP(i2c_sck_c,	1,	10),
+	GROUP(pwm_b,		2,	11),
+	GROUP(pwm_d,		2,	12),
 
 	/* Bank BOOT */
 	GROUP(emmc_nand_d07,	7,	31),
 	GROUP(emmc_clk,		7,	30),
 	GROUP(emmc_cmd,		7,	29),
 	GROUP(emmc_ds,		7,	28),
+	GROUP(nor_d,		7,	13),
+	GROUP(nor_q,		7,	12),
+	GROUP(nor_c,		7,	11),
+	GROUP(nor_cs,		7,	10),
 	GROUP(nand_ce0,		7,	7),
 	GROUP(nand_ce1,		7,	6),
 	GROUP(nand_rb0,		7,	5),
@@ -404,6 +477,9 @@ static struct meson_pmx_group meson_gxl_periphs_groups[] = {
 	GROUP(sdcard_d2,	6,	0),
 	GROUP(sdcard_cmd,	6,	2),
 	GROUP(sdcard_clk,	6,	3),
+
+	/* Bank CLK */
+	GROUP(pwm_f_clk,	8,	30),
 };
 
 static struct meson_pmx_group meson_gxl_aobus_groups[] = {
@@ -419,16 +495,29 @@ static struct meson_pmx_group meson_gxl_aobus_groups[] = {
 	GPIO_GROUP(GPIOAO_9, 0),
 
 	/* bank AO */
+	GROUP(uart_tx_ao_b_0,	0,	26),
+	GROUP(uart_rx_ao_b_1,	0,	25),
 	GROUP(uart_tx_ao_b,	0,	24),
-	GROUP(uart_rx_ao_b,	0,	25),
+	GROUP(uart_rx_ao_b,	0,	23),
 	GROUP(uart_tx_ao_a,	0,	12),
 	GROUP(uart_rx_ao_a,	0,	11),
 	GROUP(uart_cts_ao_a,	0,	10),
 	GROUP(uart_rts_ao_a,	0,	9),
 	GROUP(uart_cts_ao_b,	0,	8),
 	GROUP(uart_rts_ao_b,	0,	7),
+	GROUP(i2c_sck_ao,	0,	6),
+	GROUP(i2c_sda_ao,	0,	5),
+	GROUP(i2c_slave_sck_ao, 0,	2),
+	GROUP(i2c_slave_sda_ao, 0,	1),
 	GROUP(remote_input_ao,	0,	0),
+	GROUP(pwm_ao_a_3,	0,	22),
+	GROUP(pwm_ao_b_6,	0,	18),
+	GROUP(pwm_ao_a_8,	0,	17),
 	GROUP(pwm_ao_b,		0,	3),
+	GROUP(i2s_out_ch23_ao,	1,	0),
+	GROUP(i2s_out_ch45_ao,	1,	1),
+	GROUP(spdif_out_ao_6,	0,	16),
+	GROUP(spdif_out_ao_9,	0,	4),
 };
 
 static const char * const gpio_periphs_groups[] = {
@@ -467,6 +556,10 @@ static const char * const emmc_groups[] = {
 	"emmc_nand_d07", "emmc_clk", "emmc_cmd", "emmc_ds",
 };
 
+static const char * const nor_groups[] = {
+	"nor_d", "nor_q", "nor_c", "nor_cs",
+};
+
 static const char * const sdcard_groups[] = {
 	"sdcard_d0", "sdcard_d1", "sdcard_d2", "sdcard_d3",
 	"sdcard_cmd", "sdcard_clk",
@@ -487,11 +580,11 @@ static const char * const uart_a_groups[] = {
 };
 
 static const char * const uart_b_groups[] = {
-	"uart_tx_b", "uart_rx_b",
+	"uart_tx_b", "uart_rx_b", "uart_cts_b", "uart_rts_b",
 };
 
 static const char * const uart_c_groups[] = {
-	"uart_tx_c", "uart_rx_c",
+	"uart_tx_c", "uart_rx_c", "uart_cts_c", "uart_rts_c",
 };
 
 static const char * const i2c_a_groups[] = {
@@ -503,7 +596,7 @@ static const char * const i2c_b_groups[] = {
 };
 
 static const char * const i2c_c_groups[] = {
-	"i2c_sck_c", "i2c_sda_c",
+	"i2c_sck_c", "i2c_sda_c", "i2c_sda_c_dv18", "i2c_sck_c_dv19",
 };
 
 static const char * const eth_groups[] = {
@@ -513,10 +606,30 @@ static const char * const eth_groups[] = {
 	"eth_txd0", "eth_txd1", "eth_txd2", "eth_txd3",
 };
 
+static const char * const pwm_a_groups[] = {
+	"pwm_a",
+};
+
+static const char * const pwm_b_groups[] = {
+	"pwm_b",
+};
+
+static const char * const pwm_c_groups[] = {
+	"pwm_c",
+};
+
+static const char * const pwm_d_groups[] = {
+	"pwm_d",
+};
+
 static const char * const pwm_e_groups[] = {
 	"pwm_e",
 };
 
+static const char * const pwm_f_groups[] = {
+	"pwm_f_clk", "pwm_f_x",
+};
+
 static const char * const hdmi_hpd_groups[] = {
 	"hdmi_hpd",
 };
@@ -525,6 +638,15 @@ static const char * const hdmi_i2c_groups[] = {
 	"hdmi_sda", "hdmi_scl",
 };
 
+static const char * const i2s_out_groups[] = {
+	"i2s_am_clk", "i2s_out_ao_clk", "i2s_out_lr_clk",
+	"i2s_out_ch01", "i2s_out_ch23_z", "i2s_out_ch45_z", "i2s_out_ch67_z",
+};
+
+static const char * const spdif_out_groups[] = {
+	"spdif_out_h",
+};
+
 static const char * const gpio_aobus_groups[] = {
 	"GPIOAO_0", "GPIOAO_1", "GPIOAO_2", "GPIOAO_3", "GPIOAO_4",
 	"GPIOAO_5", "GPIOAO_6", "GPIOAO_7", "GPIOAO_8", "GPIOAO_9",
@@ -536,19 +658,41 @@ static const char * const uart_ao_groups[] = {
 
 static const char * const uart_ao_b_groups[] = {
 	"uart_tx_ao_b", "uart_rx_ao_b", "uart_cts_ao_b", "uart_rts_ao_b",
+	"uart_tx_ao_b_0", "uart_rx_ao_b_1",
+};
+
+static const char * const i2c_ao_groups[] = {
+	"i2c_sck_ao", "i2c_sda_ao",
+};
+
+static const char * const i2c_slave_ao_groups[] = {
+	"i2c_slave_sck_ao", "i2c_slave_sda_ao",
 };
 
 static const char * const remote_input_ao_groups[] = {
 	"remote_input_ao",
 };
 
+static const char * const pwm_ao_a_groups[] = {
+	"pwm_ao_a_3", "pwm_ao_a_8",
+};
+
 static const char * const pwm_ao_b_groups[] = {
-	"pwm_ao_b",
+	"pwm_ao_b", "pwm_ao_b_6",
+};
+
+static const char * const i2s_out_ao_groups[] = {
+	"i2s_out_ch23_ao", "i2s_out_ch45_ao",
+};
+
+static const char * const spdif_out_ao_groups[] = {
+	"spdif_out_ao_6", "spdif_out_ao_9",
 };
 
 static struct meson_pmx_func meson_gxl_periphs_functions[] = {
 	FUNCTION(gpio_periphs),
 	FUNCTION(emmc),
+	FUNCTION(nor),
 	FUNCTION(sdcard),
 	FUNCTION(sdio),
 	FUNCTION(nand),
@@ -559,17 +703,29 @@ static struct meson_pmx_func meson_gxl_periphs_functions[] = {
 	FUNCTION(i2c_b),
 	FUNCTION(i2c_c),
 	FUNCTION(eth),
+	FUNCTION(pwm_a),
+	FUNCTION(pwm_b),
+	FUNCTION(pwm_c),
+	FUNCTION(pwm_d),
 	FUNCTION(pwm_e),
+	FUNCTION(pwm_f),
 	FUNCTION(hdmi_hpd),
 	FUNCTION(hdmi_i2c),
+	FUNCTION(i2s_out),
+	FUNCTION(spdif_out),
 };
 
 static struct meson_pmx_func meson_gxl_aobus_functions[] = {
 	FUNCTION(gpio_aobus),
 	FUNCTION(uart_ao),
 	FUNCTION(uart_ao_b),
+	FUNCTION(i2c_ao),
+	FUNCTION(i2c_slave_ao),
 	FUNCTION(remote_input_ao),
+	FUNCTION(pwm_ao_a),
 	FUNCTION(pwm_ao_b),
+	FUNCTION(i2s_out_ao),
+	FUNCTION(spdif_out_ao),
 };
 
 static struct meson_bank meson_gxl_periphs_banks[] = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index cf1686e04378..66ed70c12733 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -555,22 +555,10 @@ static int meson_gpiolib_register(struct meson_pinctrl *pc)
 	if (ret) {
 		dev_err(pc->dev, "can't add gpio chip %s\n",
 			pc->data->name);
-		goto fail;
-	}
-
-	ret = gpiochip_add_pin_range(&pc->chip, dev_name(pc->dev),
-				     0, pc->data->pin_base,
-				     pc->chip.ngpio);
-	if (ret) {
-		dev_err(pc->dev, "can't add pin range\n");
-		goto fail;
+		return ret;
 	}
 
 	return 0;
-fail:
-	gpiochip_remove(&pc->chip);
-
-	return ret;
 }
 
 static struct regmap_config meson_regmap_config = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c
index 76f077f18193..bf747eb1f3f4 100644
--- a/drivers/pinctrl/meson/pinctrl-meson8b.c
+++ b/drivers/pinctrl/meson/pinctrl-meson8b.c
@@ -267,8 +267,8 @@ static const unsigned int nand_ale_pins[]	= { PIN(BOOT_11, 0) };
 static const unsigned int nand_cle_pins[]	= { PIN(BOOT_12, 0) };
 static const unsigned int nand_wen_clk_pins[]	= { PIN(BOOT_13, 0) };
 static const unsigned int nand_ren_clk_pins[]	= { PIN(BOOT_14, 0) };
-static const unsigned int nand_dqs_0_pins[]	= { PIN(BOOT_15, 0) };
-static const unsigned int nand_dqs_1_pins[]	= { PIN(BOOT_18, 0) };
+static const unsigned int nand_dqs_15_pins[]	= { PIN(BOOT_15, 0) };
+static const unsigned int nand_dqs_18_pins[]	= { PIN(BOOT_18, 0) };
 
 static const unsigned int sdxc_d0_c_pins[]	= { PIN(BOOT_0, 0)};
 static const unsigned int sdxc_d13_c_pins[]	= { PIN(BOOT_1, 0), PIN(BOOT_2, 0),
@@ -527,8 +527,8 @@ static struct meson_pmx_group meson8b_cbus_groups[] = {
 	GROUP(nand_cle,		2,	20),
 	GROUP(nand_wen_clk,	2,	19),
 	GROUP(nand_ren_clk,	2,	18),
-	GROUP(nand_dqs_0,	2,	27),
-	GROUP(nand_dqs_1,	2,	28),
+	GROUP(nand_dqs_15,	2,	27),
+	GROUP(nand_dqs_18,	2,	28),
 	GROUP(sdxc_d0_c,	4,	30),
 	GROUP(sdxc_d13_c,	4,	29),
 	GROUP(sdxc_d47_c,	4,	28),
@@ -739,8 +739,8 @@ static const char * const sdxc_c_groups[] = {
 static const char * const nand_groups[] = {
 	"nand_io", "nand_io_ce0", "nand_io_ce1",
 	"nand_io_rb0", "nand_ale", "nand_cle",
-	"nand_wen_clk", "nand_ren_clk", "nand_dqs0",
-	"nand_dqs1"
+	"nand_wen_clk", "nand_ren_clk", "nand_dqs_15",
+	"nand_dqs_18"
 };
 
 static const char * const nor_groups[] = {
diff --git a/drivers/pinctrl/mvebu/Kconfig b/drivers/pinctrl/mvebu/Kconfig
index 170602407c0d..5bade32d3089 100644
--- a/drivers/pinctrl/mvebu/Kconfig
+++ b/drivers/pinctrl/mvebu/Kconfig
@@ -39,3 +39,10 @@ config PINCTRL_ORION
 	select PINCTRL_MVEBU
 
 endif
+
+config PINCTRL_ARMADA_37XX
+       bool
+       select GENERIC_PINCONF
+       select MFD_SYSCON
+       select PINCONF
+       select PINMUX
diff --git a/drivers/pinctrl/mvebu/Makefile b/drivers/pinctrl/mvebu/Makefile
index 18270cd5ea43..60c245a60f39 100644
--- a/drivers/pinctrl/mvebu/Makefile
+++ b/drivers/pinctrl/mvebu/Makefile
@@ -1,4 +1,4 @@
-obj-y				+= pinctrl-mvebu.o
+obj-$(CONFIG_PINCTRL_MVEBU)	+= pinctrl-mvebu.o
 obj-$(CONFIG_PINCTRL_DOVE)	+= pinctrl-dove.o
 obj-$(CONFIG_PINCTRL_KIRKWOOD)	+= pinctrl-kirkwood.o
 obj-$(CONFIG_PINCTRL_ARMADA_370) += pinctrl-armada-370.o
@@ -6,4 +6,5 @@ obj-$(CONFIG_PINCTRL_ARMADA_375) += pinctrl-armada-375.o
 obj-$(CONFIG_PINCTRL_ARMADA_38X) += pinctrl-armada-38x.o
 obj-$(CONFIG_PINCTRL_ARMADA_39X) += pinctrl-armada-39x.o
 obj-$(CONFIG_PINCTRL_ARMADA_XP)  += pinctrl-armada-xp.o
+obj-$(CONFIG_PINCTRL_ARMADA_37XX)  += pinctrl-armada-37xx.o
 obj-$(CONFIG_PINCTRL_ORION)  += pinctrl-orion.o
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
new file mode 100644
index 000000000000..5c96f5558310
--- /dev/null
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -0,0 +1,748 @@
+/*
+ * Marvell 37xx SoC pinctrl driver
+ *
+ * Copyright (C) 2017 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2 or later. This program is licensed "as is"
+ * without any warranty of any kind, whether express or implied.
+ */
+
+#include <linux/gpio/driver.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include "../pinctrl-utils.h"
+
+#define OUTPUT_EN	0x0
+#define INPUT_VAL	0x10
+#define OUTPUT_VAL	0x18
+#define OUTPUT_CTL	0x20
+#define SELECTION	0x30
+
+#define NB_FUNCS 2
+#define GPIO_PER_REG	32
+
+/**
+ * struct armada_37xx_pin_group: represents group of pins of a pinmux function.
+ * The pins of a pinmux groups are composed of one or two groups of contiguous
+ * pins.
+ * @name:	Name of the pin group, used to lookup the group.
+ * @start_pins:	Index of the first pin of the main range of pins belonging to
+ *		the group
+ * @npins:	Number of pins included in the first range
+ * @reg_mask:	Bit mask matching the group in the selection register
+ * @extra_pins:	Index of the first pin of the optional second range of pins
+ *		belonging to the group
+ * @npins:	Number of pins included in the second optional range
+ * @funcs:	A list of pinmux functions that can be selected for this group.
+ * @pins:	List of the pins included in the group
+ */
+struct armada_37xx_pin_group {
+	const char	*name;
+	unsigned int	start_pin;
+	unsigned int	npins;
+	u32		reg_mask;
+	u32		val[NB_FUNCS];
+	unsigned int	extra_pin;
+	unsigned int	extra_npins;
+	const char	*funcs[NB_FUNCS];
+	unsigned int	*pins;
+};
+
+struct armada_37xx_pin_data {
+	u8				nr_pins;
+	char				*name;
+	struct armada_37xx_pin_group	*groups;
+	int				ngroups;
+};
+
+struct armada_37xx_pmx_func {
+	const char		*name;
+	const char		**groups;
+	unsigned int		ngroups;
+};
+
+struct armada_37xx_pinctrl {
+	struct regmap			*regmap;
+	const struct armada_37xx_pin_data	*data;
+	struct device			*dev;
+	struct gpio_chip		gpio_chip;
+	struct pinctrl_desc		pctl;
+	struct pinctrl_dev		*pctl_dev;
+	struct armada_37xx_pin_group	*groups;
+	unsigned int			ngroups;
+	struct armada_37xx_pmx_func	*funcs;
+	unsigned int			nfuncs;
+};
+
+#define PIN_GRP(_name, _start, _nr, _mask, _func1, _func2)	\
+	{					\
+		.name = _name,			\
+		.start_pin = _start,		\
+		.npins = _nr,			\
+		.reg_mask = _mask,		\
+		.val = {0, _mask},		\
+		.funcs = {_func1, _func2}	\
+	}
+
+#define PIN_GRP_GPIO(_name, _start, _nr, _mask, _func1)	\
+	{					\
+		.name = _name,			\
+		.start_pin = _start,		\
+		.npins = _nr,			\
+		.reg_mask = _mask,		\
+		.val = {0, _mask},		\
+		.funcs = {_func1, "gpio"}	\
+	}
+
+#define PIN_GRP_GPIO_2(_name, _start, _nr, _mask, _val1, _val2, _func1)   \
+	{					\
+		.name = _name,			\
+		.start_pin = _start,		\
+		.npins = _nr,			\
+		.reg_mask = _mask,		\
+		.val = {_val1, _val2},		\
+		.funcs = {_func1, "gpio"}	\
+	}
+
+#define PIN_GRP_EXTRA(_name, _start, _nr, _mask, _v1, _v2, _start2, _nr2, \
+		      _f1, _f2)				\
+	{						\
+		.name = _name,				\
+		.start_pin = _start,			\
+		.npins = _nr,				\
+		.reg_mask = _mask,			\
+		.val = {_v1, _v2},			\
+		.extra_pin = _start2,			\
+		.extra_npins = _nr2,			\
+		.funcs = {_f1, _f2}			\
+	}
+
+static struct armada_37xx_pin_group armada_37xx_nb_groups[] = {
+	PIN_GRP_GPIO("jtag", 20, 5, BIT(0), "jtag"),
+	PIN_GRP_GPIO("sdio0", 8, 3, BIT(1), "sdio"),
+	PIN_GRP_GPIO("emmc_nb", 27, 9, BIT(2), "emmc"),
+	PIN_GRP_GPIO("pwm0", 11, 1, BIT(3), "pwm"),
+	PIN_GRP_GPIO("pwm1", 12, 1, BIT(4), "pwm"),
+	PIN_GRP_GPIO("pwm2", 13, 1, BIT(5), "pwm"),
+	PIN_GRP_GPIO("pwm3", 14, 1, BIT(6), "pwm"),
+	PIN_GRP_GPIO("pmic1", 17, 1, BIT(7), "pmic"),
+	PIN_GRP_GPIO("pmic0", 16, 1, BIT(8), "pmic"),
+	PIN_GRP_GPIO("i2c2", 2, 2, BIT(9), "i2c"),
+	PIN_GRP_GPIO("i2c1", 0, 2, BIT(10), "i2c"),
+	PIN_GRP_GPIO("spi_cs1", 17, 1, BIT(12), "spi"),
+	PIN_GRP_GPIO_2("spi_cs2", 18, 1, BIT(13) | BIT(19), 0, BIT(13), "spi"),
+	PIN_GRP_GPIO_2("spi_cs3", 19, 1, BIT(14) | BIT(19), 0, BIT(14), "spi"),
+	PIN_GRP_GPIO("onewire", 4, 1, BIT(16), "onewire"),
+	PIN_GRP_GPIO("uart1", 25, 2, BIT(17), "uart"),
+	PIN_GRP_GPIO("spi_quad", 15, 2, BIT(18), "spi"),
+	PIN_GRP_EXTRA("uart2", 9, 2, BIT(13) | BIT(14) | BIT(19),
+		      BIT(13) | BIT(14), BIT(19), 18, 2, "gpio", "uart"),
+	PIN_GRP_GPIO("led0_od", 11, 1, BIT(20), "led"),
+	PIN_GRP_GPIO("led1_od", 12, 1, BIT(21), "led"),
+	PIN_GRP_GPIO("led2_od", 13, 1, BIT(22), "led"),
+	PIN_GRP_GPIO("led3_od", 14, 1, BIT(23), "led"),
+
+};
+
+static struct armada_37xx_pin_group armada_37xx_sb_groups[] = {
+	PIN_GRP_GPIO("usb32_drvvbus0", 0, 1, BIT(0), "drvbus"),
+	PIN_GRP_GPIO("usb2_drvvbus1", 1, 1, BIT(1), "drvbus"),
+	PIN_GRP_GPIO("sdio_sb", 24, 5, BIT(2), "sdio"),
+	PIN_GRP_EXTRA("rgmii", 6, 14, BIT(3), 0, BIT(3), 23, 1, "mii", "gpio"),
+	PIN_GRP_GPIO("pcie1", 3, 2, BIT(4), "pcie"),
+	PIN_GRP_GPIO("ptp", 20, 3, BIT(5), "ptp"),
+	PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"),
+	PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"),
+	PIN_GRP("mii_col", 23, 1, BIT(8), "mii", "mii_err"),
+};
+
+const struct armada_37xx_pin_data armada_37xx_pin_nb = {
+	.nr_pins = 36,
+	.name = "GPIO1",
+	.groups = armada_37xx_nb_groups,
+	.ngroups = ARRAY_SIZE(armada_37xx_nb_groups),
+};
+
+const struct armada_37xx_pin_data armada_37xx_pin_sb = {
+	.nr_pins = 29,
+	.name = "GPIO2",
+	.groups = armada_37xx_sb_groups,
+	.ngroups = ARRAY_SIZE(armada_37xx_sb_groups),
+};
+
+static inline void armada_37xx_update_reg(unsigned int *reg,
+					  unsigned int offset)
+{
+	/* We never have more than 2 registers */
+	if (offset >= GPIO_PER_REG) {
+		offset -= GPIO_PER_REG;
+		*reg += sizeof(u32);
+	}
+}
+
+static int armada_37xx_get_func_reg(struct armada_37xx_pin_group *grp,
+				    const char *func)
+{
+	int f;
+
+	for (f = 0; f < NB_FUNCS; f++)
+		if (!strcmp(grp->funcs[f], func))
+			return f;
+
+	return -ENOTSUPP;
+}
+
+static struct armada_37xx_pin_group *armada_37xx_find_next_grp_by_pin(
+	struct armada_37xx_pinctrl *info, int pin, int *grp)
+{
+	while (*grp < info->ngroups) {
+		struct armada_37xx_pin_group *group = &info->groups[*grp];
+		int j;
+
+		*grp = *grp + 1;
+		for (j = 0; j < (group->npins + group->extra_npins); j++)
+			if (group->pins[j] == pin)
+				return group;
+	}
+	return NULL;
+}
+
+static int armada_37xx_pin_config_group_get(struct pinctrl_dev *pctldev,
+			    unsigned int selector, unsigned long *config)
+{
+	return -ENOTSUPP;
+}
+
+static int armada_37xx_pin_config_group_set(struct pinctrl_dev *pctldev,
+			    unsigned int selector, unsigned long *configs,
+			    unsigned int num_configs)
+{
+	return -ENOTSUPP;
+}
+
+static struct pinconf_ops armada_37xx_pinconf_ops = {
+	.is_generic = true,
+	.pin_config_group_get = armada_37xx_pin_config_group_get,
+	.pin_config_group_set = armada_37xx_pin_config_group_set,
+};
+
+static int armada_37xx_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->ngroups;
+}
+
+static const char *armada_37xx_get_group_name(struct pinctrl_dev *pctldev,
+					      unsigned int group)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->groups[group].name;
+}
+
+static int armada_37xx_get_group_pins(struct pinctrl_dev *pctldev,
+				      unsigned int selector,
+				      const unsigned int **pins,
+				      unsigned int *npins)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	if (selector >= info->ngroups)
+		return -EINVAL;
+
+	*pins = info->groups[selector].pins;
+	*npins = info->groups[selector].npins +
+		info->groups[selector].extra_npins;
+
+	return 0;
+}
+
+static const struct pinctrl_ops armada_37xx_pctrl_ops = {
+	.get_groups_count	= armada_37xx_get_groups_count,
+	.get_group_name		= armada_37xx_get_group_name,
+	.get_group_pins		= armada_37xx_get_group_pins,
+	.dt_node_to_map		= pinconf_generic_dt_node_to_map_group,
+	.dt_free_map		= pinctrl_utils_free_map,
+};
+
+/*
+ * Pinmux_ops handling
+ */
+
+static int armada_37xx_pmx_get_funcs_count(struct pinctrl_dev *pctldev)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->nfuncs;
+}
+
+static const char *armada_37xx_pmx_get_func_name(struct pinctrl_dev *pctldev,
+						 unsigned int selector)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	return info->funcs[selector].name;
+}
+
+static int armada_37xx_pmx_get_groups(struct pinctrl_dev *pctldev,
+				      unsigned int selector,
+				      const char * const **groups,
+				      unsigned int * const num_groups)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = info->funcs[selector].groups;
+	*num_groups = info->funcs[selector].ngroups;
+
+	return 0;
+}
+
+static int armada_37xx_pmx_set_by_name(struct pinctrl_dev *pctldev,
+				       const char *name,
+				       struct armada_37xx_pin_group *grp)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	unsigned int reg = SELECTION;
+	unsigned int mask = grp->reg_mask;
+	int func, val;
+
+	dev_dbg(info->dev, "enable function %s group %s\n",
+		name, grp->name);
+
+	func = armada_37xx_get_func_reg(grp, name);
+
+	if (func < 0)
+		return func;
+
+	val = grp->val[func];
+
+	regmap_update_bits(info->regmap, reg, mask, val);
+
+	return 0;
+}
+
+static int armada_37xx_pmx_set(struct pinctrl_dev *pctldev,
+			       unsigned int selector,
+			       unsigned int group)
+{
+
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	struct armada_37xx_pin_group *grp = &info->groups[group];
+	const char *name = info->funcs[selector].name;
+
+	return armada_37xx_pmx_set_by_name(pctldev, name, grp);
+}
+
+static int armada_37xx_gpio_direction_input(struct gpio_chip *chip,
+					    unsigned int offset)
+{
+	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = OUTPUT_EN;
+	unsigned int mask;
+
+	armada_37xx_update_reg(&reg, offset);
+	mask = BIT(offset);
+
+	return regmap_update_bits(info->regmap, reg, mask, 0);
+}
+
+static int armada_37xx_gpio_get_direction(struct gpio_chip *chip,
+					  unsigned int offset)
+{
+	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = OUTPUT_EN;
+	unsigned int val, mask;
+
+	armada_37xx_update_reg(&reg, offset);
+	mask = BIT(offset);
+	regmap_read(info->regmap, reg, &val);
+
+	return !(val & mask);
+}
+
+static int armada_37xx_gpio_direction_output(struct gpio_chip *chip,
+					     unsigned int offset, int value)
+{
+	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = OUTPUT_EN;
+	unsigned int mask;
+
+	armada_37xx_update_reg(&reg, offset);
+	mask = BIT(offset);
+
+	return regmap_update_bits(info->regmap, reg, mask, mask);
+}
+
+static int armada_37xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = INPUT_VAL;
+	unsigned int val, mask;
+
+	armada_37xx_update_reg(&reg, offset);
+	mask = BIT(offset);
+
+	regmap_read(info->regmap, reg, &val);
+
+	return (val & mask) != 0;
+}
+
+static void armada_37xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
+				 int value)
+{
+	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = OUTPUT_VAL;
+	unsigned int mask, val;
+
+	armada_37xx_update_reg(&reg, offset);
+	mask = BIT(offset);
+	val = value ? mask : 0;
+
+	regmap_update_bits(info->regmap, reg, mask, val);
+}
+
+static int armada_37xx_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
+					      struct pinctrl_gpio_range *range,
+					      unsigned int offset, bool input)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	struct gpio_chip *chip = range->gc;
+
+	dev_dbg(info->dev, "gpio_direction for pin %u as %s-%d to %s\n",
+		offset, range->name, offset, input ? "input" : "output");
+
+	if (input)
+		armada_37xx_gpio_direction_input(chip, offset);
+	else
+		armada_37xx_gpio_direction_output(chip, offset, 0);
+
+	return 0;
+}
+
+static int armada_37xx_gpio_request_enable(struct pinctrl_dev *pctldev,
+					   struct pinctrl_gpio_range *range,
+					   unsigned int offset)
+{
+	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	struct armada_37xx_pin_group *group;
+	int grp = 0;
+
+	dev_dbg(info->dev, "requesting gpio %d\n", offset);
+
+	while ((group = armada_37xx_find_next_grp_by_pin(info, offset, &grp)))
+		armada_37xx_pmx_set_by_name(pctldev, "gpio", group);
+
+	return 0;
+}
+
+static const struct pinmux_ops armada_37xx_pmx_ops = {
+	.get_functions_count	= armada_37xx_pmx_get_funcs_count,
+	.get_function_name	= armada_37xx_pmx_get_func_name,
+	.get_function_groups	= armada_37xx_pmx_get_groups,
+	.set_mux		= armada_37xx_pmx_set,
+	.gpio_request_enable	= armada_37xx_gpio_request_enable,
+	.gpio_set_direction	= armada_37xx_pmx_gpio_set_direction,
+};
+
+static const struct gpio_chip armada_37xx_gpiolib_chip = {
+	.request = gpiochip_generic_request,
+	.free = gpiochip_generic_free,
+	.set = armada_37xx_gpio_set,
+	.get = armada_37xx_gpio_get,
+	.get_direction	= armada_37xx_gpio_get_direction,
+	.direction_input = armada_37xx_gpio_direction_input,
+	.direction_output = armada_37xx_gpio_direction_output,
+	.owner = THIS_MODULE,
+};
+
+static int armada_37xx_gpiochip_register(struct platform_device *pdev,
+					struct armada_37xx_pinctrl *info)
+{
+	struct device_node *np;
+	struct gpio_chip *gc;
+	int ret = -ENODEV;
+
+	for_each_child_of_node(info->dev->of_node, np) {
+		if (of_find_property(np, "gpio-controller", NULL)) {
+			ret = 0;
+			break;
+		}
+	};
+	if (ret)
+		return ret;
+
+	info->gpio_chip = armada_37xx_gpiolib_chip;
+
+	gc = &info->gpio_chip;
+	gc->ngpio = info->data->nr_pins;
+	gc->parent = &pdev->dev;
+	gc->base = -1;
+	gc->of_node = np;
+	gc->label = info->data->name;
+
+	ret = devm_gpiochip_add_data(&pdev->dev, gc, info);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * armada_37xx_add_function() - Add a new function to the list
+ * @funcs: array of function to add the new one
+ * @funcsize: size of the remaining space for the function
+ * @name: name of the function to add
+ *
+ * If it is a new function then create it by adding its name else
+ * increment the number of group associated to this function.
+ */
+static int armada_37xx_add_function(struct armada_37xx_pmx_func *funcs,
+				    int *funcsize, const char *name)
+{
+	int i = 0;
+
+	if (*funcsize <= 0)
+		return -EOVERFLOW;
+
+	while (funcs->ngroups) {
+		/* function already there */
+		if (strcmp(funcs->name, name) == 0) {
+			funcs->ngroups++;
+
+			return -EEXIST;
+		}
+		funcs++;
+		i++;
+	}
+
+	/* append new unique function */
+	funcs->name = name;
+	funcs->ngroups = 1;
+	(*funcsize)--;
+
+	return 0;
+}
+
+/**
+ * armada_37xx_fill_group() - complete the group array
+ * @info: info driver instance
+ *
+ * Based on the data available from the armada_37xx_pin_group array
+ * completes the last member of the struct for each function: the list
+ * of the groups associated to this function.
+ *
+ */
+static int armada_37xx_fill_group(struct armada_37xx_pinctrl *info)
+{
+	int n, num = 0, funcsize = info->data->nr_pins;
+
+	for (n = 0; n < info->ngroups; n++) {
+		struct armada_37xx_pin_group *grp = &info->groups[n];
+		int i, j, f;
+
+		grp->pins = devm_kzalloc(info->dev,
+					 (grp->npins + grp->extra_npins) *
+					 sizeof(*grp->pins), GFP_KERNEL);
+		if (!grp->pins)
+			return -ENOMEM;
+
+		for (i = 0; i < grp->npins; i++)
+			grp->pins[i] = grp->start_pin + i;
+
+		for (j = 0; j < grp->extra_npins; j++)
+			grp->pins[i+j] = grp->extra_pin + j;
+
+		for (f = 0; f < NB_FUNCS; f++) {
+			int ret;
+			/* check for unique functions and count groups */
+			ret = armada_37xx_add_function(info->funcs, &funcsize,
+					    grp->funcs[f]);
+			if (ret == -EOVERFLOW)
+				dev_err(info->dev,
+					"More functions than pins(%d)\n",
+					info->data->nr_pins);
+			if (ret < 0)
+				continue;
+			num++;
+		}
+	}
+
+	info->nfuncs = num;
+
+	return 0;
+}
+
+/**
+ * armada_37xx_fill_funcs() - complete the funcs array
+ * @info: info driver instance
+ *
+ * Based on the data available from the armada_37xx_pin_group array
+ * completes the last two member of the struct for each group:
+ * - the list of the pins included in the group
+ * - the list of pinmux functions that can be selected for this group
+ *
+ */
+static int armada_37xx_fill_func(struct armada_37xx_pinctrl *info)
+{
+	struct armada_37xx_pmx_func *funcs = info->funcs;
+	int n;
+
+	for (n = 0; n < info->nfuncs; n++) {
+		const char *name = funcs[n].name;
+		const char **groups;
+		int g;
+
+		funcs[n].groups = devm_kzalloc(info->dev, funcs[n].ngroups *
+					       sizeof(*(funcs[n].groups)),
+					       GFP_KERNEL);
+		if (!funcs[n].groups)
+			return -ENOMEM;
+
+		groups = funcs[n].groups;
+
+		for (g = 0; g < info->ngroups; g++) {
+			struct armada_37xx_pin_group *gp = &info->groups[g];
+			int f;
+
+			for (f = 0; f < NB_FUNCS; f++) {
+				if (strcmp(gp->funcs[f], name) == 0) {
+					*groups = gp->name;
+					groups++;
+				}
+			}
+		}
+	}
+	return 0;
+}
+
+static int armada_37xx_pinctrl_register(struct platform_device *pdev,
+					struct armada_37xx_pinctrl *info)
+{
+	const struct armada_37xx_pin_data *pin_data = info->data;
+	struct pinctrl_desc *ctrldesc = &info->pctl;
+	struct pinctrl_pin_desc *pindesc, *pdesc;
+	int pin, ret;
+
+	info->groups = pin_data->groups;
+	info->ngroups = pin_data->ngroups;
+
+	ctrldesc->name = "armada_37xx-pinctrl";
+	ctrldesc->owner = THIS_MODULE;
+	ctrldesc->pctlops = &armada_37xx_pctrl_ops;
+	ctrldesc->pmxops = &armada_37xx_pmx_ops;
+	ctrldesc->confops = &armada_37xx_pinconf_ops;
+
+	pindesc = devm_kzalloc(&pdev->dev, sizeof(*pindesc) *
+			       pin_data->nr_pins, GFP_KERNEL);
+	if (!pindesc)
+		return -ENOMEM;
+
+	ctrldesc->pins = pindesc;
+	ctrldesc->npins = pin_data->nr_pins;
+
+	pdesc = pindesc;
+	for (pin = 0; pin < pin_data->nr_pins; pin++) {
+		pdesc->number = pin;
+		pdesc->name = kasprintf(GFP_KERNEL, "%s-%d",
+					pin_data->name, pin);
+		pdesc++;
+	}
+
+	/*
+	 * we allocate functions for number of pins and hope there are
+	 * fewer unique functions than pins available
+	 */
+	info->funcs = devm_kzalloc(&pdev->dev, pin_data->nr_pins *
+			   sizeof(struct armada_37xx_pmx_func), GFP_KERNEL);
+	if (!info->funcs)
+		return -ENOMEM;
+
+
+	ret = armada_37xx_fill_group(info);
+	if (ret)
+		return ret;
+
+	ret = armada_37xx_fill_func(info);
+	if (ret)
+		return ret;
+
+	info->pctl_dev = devm_pinctrl_register(&pdev->dev, ctrldesc, info);
+	if (IS_ERR(info->pctl_dev)) {
+		dev_err(&pdev->dev, "could not register pinctrl driver\n");
+		return PTR_ERR(info->pctl_dev);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id armada_37xx_pinctrl_of_match[] = {
+	{
+		.compatible = "marvell,armada3710-sb-pinctrl",
+		.data = (void *)&armada_37xx_pin_sb,
+	},
+	{
+		.compatible = "marvell,armada3710-nb-pinctrl",
+		.data = (void *)&armada_37xx_pin_nb,
+	},
+	{ },
+};
+
+static int __init armada_37xx_pinctrl_probe(struct platform_device *pdev)
+{
+	struct armada_37xx_pinctrl *info;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct regmap *regmap;
+	int ret;
+
+	info = devm_kzalloc(dev, sizeof(struct armada_37xx_pinctrl),
+			    GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->dev = dev;
+
+	regmap = syscon_node_to_regmap(np);
+	if (IS_ERR(regmap)) {
+		dev_err(&pdev->dev, "cannot get regmap\n");
+		return PTR_ERR(regmap);
+	}
+	info->regmap = regmap;
+
+	info->data = of_device_get_match_data(dev);
+
+	ret = armada_37xx_pinctrl_register(pdev, info);
+	if (ret)
+		return ret;
+
+	ret = armada_37xx_gpiochip_register(pdev, info);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, info);
+
+	return 0;
+}
+
+static struct platform_driver armada_37xx_pinctrl_driver = {
+	.driver = {
+		.name = "armada-37xx-pinctrl",
+		.of_match_table = armada_37xx_pinctrl_of_match,
+	},
+};
+
+builtin_platform_driver_probe(armada_37xx_pinctrl_driver,
+			      armada_37xx_pinctrl_probe);
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index ce3335accb5b..0d6b7f4b82af 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -35,6 +35,7 @@ static const struct pin_config_item conf_items[] = {
 	PCONFDUMP(PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
 				"input bias pull to pin specific state", NULL, false),
 	PCONFDUMP(PIN_CONFIG_BIAS_PULL_UP, "input bias pull up", NULL, false),
+	PCONFDUMP(PIN_CONFIG_BIDIRECTIONAL, "bi-directional pin operations", NULL, false),
 	PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_DRAIN, "output drive open drain", NULL, false),
 	PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_SOURCE, "output drive open source", NULL, false),
 	PCONFDUMP(PIN_CONFIG_DRIVE_PUSH_PULL, "output drive push pull", NULL, false),
@@ -160,6 +161,7 @@ static const struct pinconf_generic_params dt_params[] = {
 	{ "bias-pull-up", PIN_CONFIG_BIAS_PULL_UP, 1 },
 	{ "bias-pull-pin-default", PIN_CONFIG_BIAS_PULL_PIN_DEFAULT, 1 },
 	{ "bias-pull-down", PIN_CONFIG_BIAS_PULL_DOWN, 1 },
+	{ "bi-directional", PIN_CONFIG_BIDIRECTIONAL, 1 },
 	{ "drive-open-drain", PIN_CONFIG_DRIVE_OPEN_DRAIN, 0 },
 	{ "drive-open-source", PIN_CONFIG_DRIVE_OPEN_SOURCE, 0 },
 	{ "drive-push-pull", PIN_CONFIG_DRIVE_PUSH_PULL, 0 },
@@ -172,6 +174,7 @@ static const struct pinconf_generic_params dt_params[] = {
 	{ "input-schmitt-enable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 1 },
 	{ "low-power-disable", PIN_CONFIG_LOW_POWER_MODE, 0 },
 	{ "low-power-enable", PIN_CONFIG_LOW_POWER_MODE, 1 },
+	{ "output-enable", PIN_CONFIG_OUTPUT, 1, },
 	{ "output-high", PIN_CONFIG_OUTPUT, 1, },
 	{ "output-low", PIN_CONFIG_OUTPUT, 0, },
 	{ "power-source", PIN_CONFIG_POWER_SOURCE, 0 },
@@ -187,7 +190,7 @@ static const struct pinconf_generic_params dt_params[] = {
  * @ncfg:	Number of entries in @cfg
  *
  * Parse the config options described in @params from @np and puts the result
- * in @cfg. @cfg does not need to be empty, entries are added beggining at
+ * in @cfg. @cfg does not need to be empty, entries are added beginning at
  * @ncfg. @ncfg is updated to reflect the number of entries after parsing. @cfg
  * needs to have enough memory allocated to hold all possible entries.
  */
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index c1c1ccc58267..a02dba35fcf3 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -284,7 +284,7 @@ void pinconf_show_setting(struct seq_file *s,
 	}
 
 	/*
-	 * FIXME: We should really get the pin controler to dump the config
+	 * FIXME: We should really get the pin controller to dump the config
 	 * values, so they can be decoded to something meaningful.
 	 */
 	pinconf_show_config(s, pctldev, setting->data.configs.configs,
@@ -473,7 +473,7 @@ exit:
  *     "config_pin" or "config_group", alternatives like config_mux are not
  *     supported yet.
  * <devicename> <state> <name> are values that should match the pinctrl-maps
- * <newvalue> reflects the new config and is driver dependant
+ * <newvalue> reflects the new config and is driver dependent
  */
 static ssize_t pinconf_dbg_config_write(struct file *file,
 	const char __user *user_buf, size_t count, loff_t *ppos)
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index d69e357a7a98..043ac9bcbccb 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -41,11 +41,11 @@ static int amd_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
 	u32 pin_reg;
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + offset * 4);
 	pin_reg &= ~BIT(OUTPUT_ENABLE_OFF);
 	writel(pin_reg, gpio_dev->base + offset * 4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	return 0;
 }
@@ -57,7 +57,7 @@ static int amd_gpio_direction_output(struct gpio_chip *gc, unsigned offset,
 	unsigned long flags;
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + offset * 4);
 	pin_reg |= BIT(OUTPUT_ENABLE_OFF);
 	if (value)
@@ -65,7 +65,7 @@ static int amd_gpio_direction_output(struct gpio_chip *gc, unsigned offset,
 	else
 		pin_reg &= ~BIT(OUTPUT_VALUE_OFF);
 	writel(pin_reg, gpio_dev->base + offset * 4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	return 0;
 }
@@ -76,9 +76,9 @@ static int amd_gpio_get_value(struct gpio_chip *gc, unsigned offset)
 	unsigned long flags;
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + offset * 4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	return !!(pin_reg & BIT(PIN_STS_OFF));
 }
@@ -89,14 +89,14 @@ static void amd_gpio_set_value(struct gpio_chip *gc, unsigned offset, int value)
 	unsigned long flags;
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + offset * 4);
 	if (value)
 		pin_reg |= BIT(OUTPUT_VALUE_OFF);
 	else
 		pin_reg &= ~BIT(OUTPUT_VALUE_OFF);
 	writel(pin_reg, gpio_dev->base + offset * 4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 }
 
 static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset,
@@ -108,7 +108,7 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset,
 	unsigned long flags;
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + offset * 4);
 
 	if (debounce) {
@@ -159,7 +159,7 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset,
 		pin_reg &= ~DB_CNTRl_MASK;
 	}
 	writel(pin_reg, gpio_dev->base + offset * 4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	return ret;
 }
@@ -224,9 +224,9 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc)
 		}
 		for (; i < pin_num; i++) {
 			seq_printf(s, "pin%d\t", i);
-			spin_lock_irqsave(&gpio_dev->lock, flags);
+			raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 			pin_reg = readl(gpio_dev->base + i * 4);
-			spin_unlock_irqrestore(&gpio_dev->lock, flags);
+			raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 			if (pin_reg & BIT(INTERRUPT_ENABLE_OFF)) {
 				interrupt_enable = "interrupt is enabled|";
@@ -331,12 +331,12 @@ static void amd_gpio_irq_enable(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
 	pin_reg |= BIT(INTERRUPT_ENABLE_OFF);
 	pin_reg |= BIT(INTERRUPT_MASK_OFF);
 	writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 }
 
 static void amd_gpio_irq_disable(struct irq_data *d)
@@ -346,12 +346,12 @@ static void amd_gpio_irq_disable(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
 	pin_reg &= ~BIT(INTERRUPT_ENABLE_OFF);
 	pin_reg &= ~BIT(INTERRUPT_MASK_OFF);
 	writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 }
 
 static void amd_gpio_irq_mask(struct irq_data *d)
@@ -361,11 +361,11 @@ static void amd_gpio_irq_mask(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
 	pin_reg &= ~BIT(INTERRUPT_MASK_OFF);
 	writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 }
 
 static void amd_gpio_irq_unmask(struct irq_data *d)
@@ -375,11 +375,11 @@ static void amd_gpio_irq_unmask(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
 	pin_reg |= BIT(INTERRUPT_MASK_OFF);
 	writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 }
 
 static void amd_gpio_irq_eoi(struct irq_data *d)
@@ -389,11 +389,11 @@ static void amd_gpio_irq_eoi(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG);
 	reg |= EOI_MASK;
 	writel(reg, gpio_dev->base + WAKE_INT_MASTER_REG);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 }
 
 static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type)
@@ -404,7 +404,7 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct amd_gpio *gpio_dev = gpiochip_get_data(gc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
 
 	/* Ignore the settings coming from the client and
@@ -469,7 +469,7 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 
 	pin_reg |= CLR_INTR_STAT << INTERRUPT_STS_OFF;
 	writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	return ret;
 }
@@ -511,14 +511,14 @@ static void amd_gpio_irq_handler(struct irq_desc *desc)
 
 	chained_irq_enter(chip, desc);
 	/*enable GPIO interrupt again*/
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	reg = readl(gpio_dev->base + WAKE_INT_STATUS_REG1);
 	reg64 = reg;
 	reg64 = reg64 << 32;
 
 	reg = readl(gpio_dev->base + WAKE_INT_STATUS_REG0);
 	reg64 |= reg;
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	/*
 	 * first 46 bits indicates interrupt status.
@@ -546,11 +546,11 @@ static void amd_gpio_irq_handler(struct irq_desc *desc)
 	if (handled == 0)
 		handle_bad_irq(desc);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG);
 	reg |= EOI_MASK;
 	writel(reg, gpio_dev->base + WAKE_INT_MASTER_REG);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	chained_irq_exit(chip, desc);
 }
@@ -602,9 +602,9 @@ static int amd_pinconf_get(struct pinctrl_dev *pctldev,
 	struct amd_gpio *gpio_dev = pinctrl_dev_get_drvdata(pctldev);
 	enum pin_config_param param = pinconf_to_config_param(*config);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + pin*4);
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	switch (param) {
 	case PIN_CONFIG_INPUT_DEBOUNCE:
 		arg = pin_reg & DB_TMR_OUT_MASK;
@@ -644,7 +644,7 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	enum pin_config_param param;
 	struct amd_gpio *gpio_dev = pinctrl_dev_get_drvdata(pctldev);
 
-	spin_lock_irqsave(&gpio_dev->lock, flags);
+	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 	for (i = 0; i < num_configs; i++) {
 		param = pinconf_to_config_param(configs[i]);
 		arg = pinconf_to_config_argument(configs[i]);
@@ -683,7 +683,7 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 
 		writel(pin_reg, gpio_dev->base + pin*4);
 	}
-	spin_unlock_irqrestore(&gpio_dev->lock, flags);
+	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 	return ret;
 }
@@ -751,7 +751,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
 	if (!gpio_dev)
 		return -ENOMEM;
 
-	spin_lock_init(&gpio_dev->lock);
+	raw_spin_lock_init(&gpio_dev->lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index c03f77822069..5b1cb965c767 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -87,7 +87,7 @@ struct amd_function {
 };
 
 struct amd_gpio {
-	spinlock_t              lock;
+	raw_spinlock_t          lock;
 	void __iomem            *base;
 
 	const struct amd_pingroup *groups;
diff --git a/drivers/pinctrl/pinctrl-artpec6.c b/drivers/pinctrl/pinctrl-artpec6.c
new file mode 100644
index 000000000000..357516d524bd
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-artpec6.c
@@ -0,0 +1,979 @@
+/*
+ * Driver for the Axis ARTPEC-6 pin controller
+ *
+ * Author: Chris Paterson <chris.paterson@linux.pieboy.co.uk>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/slab.h>
+#include "core.h"
+#include "pinconf.h"
+#include "pinctrl-utils.h"
+
+#define ARTPEC6_LAST_PIN	97	/* 97 pins in pinmux */
+#define ARTPEC6_MAX_MUXABLE	35	/* Last pin with muxable function */
+
+/* Pinmux control register bit definitions */
+#define ARTPEC6_PINMUX_UDC0_MASK	0x00000001
+#define ARTPEC6_PINMUX_UDC0_SHIFT	0
+#define ARTPEC6_PINMUX_UDC1_MASK	0x00000002
+#define ARTPEC6_PINMUX_UDC1_SHIFT	1
+#define ARTPEC6_PINMUX_DRV_MASK		0x00000060
+#define ARTPEC6_PINMUX_DRV_SHIFT	5
+#define ARTPEC6_PINMUX_SEL_MASK		0x00003000
+#define ARTPEC6_PINMUX_SEL_SHIFT	12
+
+/* Pinmux configurations */
+#define ARTPEC6_CONFIG_0		0
+#define ARTPEC6_CONFIG_1		1
+#define ARTPEC6_CONFIG_2		2
+#define ARTPEC6_CONFIG_3		3
+
+/* Pin drive strength options */
+#define ARTPEC6_DRIVE_4mA		4
+#define ARTPEC6_DRIVE_4mA_SET		0
+#define ARTPEC6_DRIVE_6mA		6
+#define ARTPEC6_DRIVE_6mA_SET		1
+#define ARTPEC6_DRIVE_8mA		8
+#define ARTPEC6_DRIVE_8mA_SET		2
+#define ARTPEC6_DRIVE_9mA		9
+#define ARTPEC6_DRIVE_9mA_SET		3
+
+struct artpec6_pmx {
+	struct device			*dev;
+	struct pinctrl_dev		*pctl;
+	void __iomem			*base;
+	struct pinctrl_pin_desc		*pins;
+	unsigned int			num_pins;
+	const struct artpec6_pin_group	*pin_groups;
+	unsigned int			num_pin_groups;
+	const struct artpec6_pmx_func	*functions;
+	unsigned int			num_functions;
+};
+
+struct artpec6_pin_group {
+	const char	   *name;
+	const unsigned int *pins;
+	const unsigned int num_pins;
+	unsigned char	   config;
+};
+
+struct artpec6_pmx_func {
+	const char	   *name;
+	const char * const *groups;
+	const unsigned int num_groups;
+};
+
+/* pins */
+static struct pinctrl_pin_desc artpec6_pins[] = {
+	PINCTRL_PIN(0, "GPIO0"),
+	PINCTRL_PIN(1, "GPIO1"),
+	PINCTRL_PIN(2, "GPIO2"),
+	PINCTRL_PIN(3, "GPIO3"),
+	PINCTRL_PIN(4, "GPIO4"),
+	PINCTRL_PIN(5, "GPIO5"),
+	PINCTRL_PIN(6, "GPIO6"),
+	PINCTRL_PIN(7, "GPIO7"),
+	PINCTRL_PIN(8, "GPIO8"),
+	PINCTRL_PIN(9, "GPIO9"),
+	PINCTRL_PIN(10, "GPIO10"),
+	PINCTRL_PIN(11, "GPIO11"),
+	PINCTRL_PIN(12, "GPIO12"),
+	PINCTRL_PIN(13, "GPIO13"),
+	PINCTRL_PIN(14, "GPIO14"),
+	PINCTRL_PIN(15, "GPIO15"),
+	PINCTRL_PIN(16, "GPIO16"),
+	PINCTRL_PIN(17, "GPIO17"),
+	PINCTRL_PIN(18, "GPIO18"),
+	PINCTRL_PIN(19, "GPIO19"),
+	PINCTRL_PIN(20, "GPIO20"),
+	PINCTRL_PIN(21, "GPIO21"),
+	PINCTRL_PIN(22, "GPIO22"),
+	PINCTRL_PIN(23, "GPIO23"),
+	PINCTRL_PIN(24, "GPIO24"),
+	PINCTRL_PIN(25, "GPIO25"),
+	PINCTRL_PIN(26, "GPIO26"),
+	PINCTRL_PIN(27, "GPIO27"),
+	PINCTRL_PIN(28, "GPIO28"),
+	PINCTRL_PIN(29, "GPIO29"),
+	PINCTRL_PIN(30, "GPIO30"),
+	PINCTRL_PIN(31, "GPIO31"),
+	PINCTRL_PIN(32, "UART3_TXD"),
+	PINCTRL_PIN(33, "UART3_RXD"),
+	PINCTRL_PIN(34, "UART3_RTS"),
+	PINCTRL_PIN(35, "UART3_CTS"),
+	PINCTRL_PIN(36, "NF_ALE"),
+	PINCTRL_PIN(37, "NF_CE0_N"),
+	PINCTRL_PIN(38, "NF_CE1_N"),
+	PINCTRL_PIN(39, "NF_CLE"),
+	PINCTRL_PIN(40, "NF_RE_N"),
+	PINCTRL_PIN(41, "NF_WE_N"),
+	PINCTRL_PIN(42, "NF_WP0_N"),
+	PINCTRL_PIN(43, "NF_WP1_N"),
+	PINCTRL_PIN(44, "NF_IO0"),
+	PINCTRL_PIN(45, "NF_IO1"),
+	PINCTRL_PIN(46, "NF_IO2"),
+	PINCTRL_PIN(47, "NF_IO3"),
+	PINCTRL_PIN(48, "NF_IO4"),
+	PINCTRL_PIN(49, "NF_IO5"),
+	PINCTRL_PIN(50, "NF_IO6"),
+	PINCTRL_PIN(51, "NF_IO7"),
+	PINCTRL_PIN(52, "NF_RB0_N"),
+	PINCTRL_PIN(53, "SDIO0_CLK"),
+	PINCTRL_PIN(54, "SDIO0_CMD"),
+	PINCTRL_PIN(55, "SDIO0_DAT0"),
+	PINCTRL_PIN(56, "SDIO0_DAT1"),
+	PINCTRL_PIN(57, "SDIO0_DAT2"),
+	PINCTRL_PIN(58, "SDIO0_DAT3"),
+	PINCTRL_PIN(59, "SDI0_CD"),
+	PINCTRL_PIN(60, "SDI0_WP"),
+	PINCTRL_PIN(61, "SDIO1_CLK"),
+	PINCTRL_PIN(62, "SDIO1_CMD"),
+	PINCTRL_PIN(63, "SDIO1_DAT0"),
+	PINCTRL_PIN(64, "SDIO1_DAT1"),
+	PINCTRL_PIN(65, "SDIO1_DAT2"),
+	PINCTRL_PIN(66, "SDIO1_DAT3"),
+	PINCTRL_PIN(67, "SDIO1_CD"),
+	PINCTRL_PIN(68, "SDIO1_WP"),
+	PINCTRL_PIN(69, "GBE_REFCLk"),
+	PINCTRL_PIN(70, "GBE_GTX_CLK"),
+	PINCTRL_PIN(71, "GBE_TX_CLK"),
+	PINCTRL_PIN(72, "GBE_TX_EN"),
+	PINCTRL_PIN(73, "GBE_TX_ER"),
+	PINCTRL_PIN(74, "GBE_TXD0"),
+	PINCTRL_PIN(75, "GBE_TXD1"),
+	PINCTRL_PIN(76, "GBE_TXD2"),
+	PINCTRL_PIN(77, "GBE_TXD3"),
+	PINCTRL_PIN(78, "GBE_TXD4"),
+	PINCTRL_PIN(79, "GBE_TXD5"),
+	PINCTRL_PIN(80, "GBE_TXD6"),
+	PINCTRL_PIN(81, "GBE_TXD7"),
+	PINCTRL_PIN(82, "GBE_RX_CLK"),
+	PINCTRL_PIN(83, "GBE_RX_DV"),
+	PINCTRL_PIN(84, "GBE_RX_ER"),
+	PINCTRL_PIN(85, "GBE_RXD0"),
+	PINCTRL_PIN(86, "GBE_RXD1"),
+	PINCTRL_PIN(87, "GBE_RXD2"),
+	PINCTRL_PIN(88, "GBE_RXD3"),
+	PINCTRL_PIN(89, "GBE_RXD4"),
+	PINCTRL_PIN(90, "GBE_RXD5"),
+	PINCTRL_PIN(91, "GBE_RXD6"),
+	PINCTRL_PIN(92, "GBE_RXD7"),
+	PINCTRL_PIN(93, "GBE_CRS"),
+	PINCTRL_PIN(94, "GBE_COL"),
+	PINCTRL_PIN(95, "GBE_MDC"),
+	PINCTRL_PIN(96, "GBE_MDIO"),
+};
+
+static const unsigned int cpuclkout_pins0[] = { 0 };
+static const unsigned int udlclkout_pins0[] = { 1 };
+static const unsigned int i2c1_pins0[] = { 2, 3 };
+static const unsigned int i2c2_pins0[] = { 4, 5 };
+static const unsigned int i2c3_pins0[] = { 6, 7 };
+static const unsigned int i2s0_pins0[] = { 8, 9, 10, 11 };
+static const unsigned int i2s1_pins0[] = { 12, 13, 14, 15 };
+static const unsigned int i2srefclk_pins0[] = { 19 };
+static const unsigned int spi0_pins0[] = { 12, 13, 14, 15 };
+static const unsigned int spi1_pins0[] = { 16, 17, 18, 19 };
+static const unsigned int pciedebug_pins0[] = { 12, 13, 14, 15 };
+static const unsigned int uart0_pins0[] = { 16, 17, 18, 19, 20,
+					    21, 22, 23, 24, 25 };
+static const unsigned int uart0_pins1[] = { 20, 21, 22, 23 };
+static const unsigned int uart1_pins0[] = { 24, 25, 26, 27 };
+static const unsigned int uart2_pins0[] = { 26, 27, 28, 29, 30,
+					    31, 32, 33, 34, 35 };
+static const unsigned int uart2_pins1[] = { 28, 29, 30, 31 };
+static const unsigned int uart3_pins0[] = { 32, 33, 34, 35 };
+static const unsigned int uart4_pins0[] = { 20, 21, 22, 23 };
+static const unsigned int uart5_pins0[] = { 28, 29, 30, 31 };
+static const unsigned int nand_pins0[]  = { 36, 37, 38, 39, 40, 41,
+					    42, 43, 44, 45, 46, 47,
+					    48, 49, 50, 51, 52 };
+static const unsigned int sdio0_pins0[] = { 53, 54, 55, 56, 57, 58, 59, 60 };
+static const unsigned int sdio1_pins0[] = { 61, 62, 63, 64, 65, 66, 67, 68 };
+static const unsigned int ethernet_pins0[]  = { 69, 70, 71, 72, 73, 74, 75,
+						76, 77, 78, 79, 80, 81, 82,
+						83, 84,	85, 86, 87, 88, 89,
+						90, 91, 92, 93, 94, 95, 96 };
+
+static const struct artpec6_pin_group artpec6_pin_groups[] = {
+	{
+		.name = "cpuclkoutgrp0",
+		.pins = cpuclkout_pins0,
+		.num_pins = ARRAY_SIZE(cpuclkout_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "udlclkoutgrp0",
+		.pins = udlclkout_pins0,
+		.num_pins = ARRAY_SIZE(udlclkout_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "i2c1grp0",
+		.pins = i2c1_pins0,
+		.num_pins = ARRAY_SIZE(i2c1_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "i2c2grp0",
+		.pins = i2c2_pins0,
+		.num_pins = ARRAY_SIZE(i2c2_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "i2c3grp0",
+		.pins = i2c3_pins0,
+		.num_pins = ARRAY_SIZE(i2c3_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "i2s0grp0",
+		.pins = i2s0_pins0,
+		.num_pins = ARRAY_SIZE(i2s0_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "i2s1grp0",
+		.pins = i2s1_pins0,
+		.num_pins = ARRAY_SIZE(i2s1_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "i2srefclkgrp0",
+		.pins = i2srefclk_pins0,
+		.num_pins = ARRAY_SIZE(i2srefclk_pins0),
+		.config = ARTPEC6_CONFIG_3,
+	},
+	{
+		.name = "spi0grp0",
+		.pins = spi0_pins0,
+		.num_pins = ARRAY_SIZE(spi0_pins0),
+		.config = ARTPEC6_CONFIG_2,
+	},
+	{
+		.name = "spi1grp0",
+		.pins = spi1_pins0,
+		.num_pins = ARRAY_SIZE(spi1_pins0),
+		.config = ARTPEC6_CONFIG_2,
+	},
+	{
+		.name = "pciedebuggrp0",
+		.pins = pciedebug_pins0,
+		.num_pins = ARRAY_SIZE(pciedebug_pins0),
+		.config = ARTPEC6_CONFIG_3,
+	},
+	{
+		.name = "uart0grp0",
+		.pins = uart0_pins0,
+		.num_pins = ARRAY_SIZE(uart0_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "uart0grp1",
+		.pins = uart0_pins1,
+		.num_pins = ARRAY_SIZE(uart0_pins1),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "uart1grp0",
+		.pins = uart1_pins0,
+		.num_pins = ARRAY_SIZE(uart1_pins0),
+		.config = ARTPEC6_CONFIG_2,
+	},
+	{
+		.name = "uart2grp0",
+		.pins = uart2_pins0,
+		.num_pins = ARRAY_SIZE(uart2_pins0),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "uart2grp1",
+		.pins = uart2_pins1,
+		.num_pins = ARRAY_SIZE(uart2_pins1),
+		.config = ARTPEC6_CONFIG_1,
+	},
+	{
+		.name = "uart3grp0",
+		.pins = uart3_pins0,
+		.num_pins = ARRAY_SIZE(uart3_pins0),
+		.config = ARTPEC6_CONFIG_0,
+	},
+	{
+		.name = "uart4grp0",
+		.pins = uart4_pins0,
+		.num_pins = ARRAY_SIZE(uart4_pins0),
+		.config = ARTPEC6_CONFIG_2,
+	},
+	{
+		.name = "uart5grp0",
+		.pins = uart5_pins0,
+		.num_pins = ARRAY_SIZE(uart5_pins0),
+		.config = ARTPEC6_CONFIG_2,
+	},
+	{
+		.name = "uart5nocts",
+		.pins = uart5_pins0,
+		.num_pins = ARRAY_SIZE(uart5_pins0) - 1,
+		.config = ARTPEC6_CONFIG_2,
+	},
+	{
+		.name = "nandgrp0",
+		.pins = nand_pins0,
+		.num_pins = ARRAY_SIZE(nand_pins0),
+		.config = ARTPEC6_CONFIG_0,
+	},
+	{
+		.name = "sdio0grp0",
+		.pins = sdio0_pins0,
+		.num_pins = ARRAY_SIZE(sdio0_pins0),
+		.config = ARTPEC6_CONFIG_0,
+	},
+	{
+		.name = "sdio1grp0",
+		.pins = sdio1_pins0,
+		.num_pins = ARRAY_SIZE(sdio1_pins0),
+		.config = ARTPEC6_CONFIG_0,
+	},
+	{
+		.name = "ethernetgrp0",
+		.pins = ethernet_pins0,
+		.num_pins = ARRAY_SIZE(ethernet_pins0),
+		.config = ARTPEC6_CONFIG_0,
+	},
+};
+
+struct pin_register {
+	unsigned int start;
+	unsigned int end;
+	unsigned int reg_base;
+};
+
+/*
+ * The register map has two holes where the pin number
+ * no longer fits directly with the register offset.
+ * This table allows us to map this easily.
+ */
+static const struct pin_register pin_register[] = {
+	{ 0, 35, 0x0 },		/* 0x0 - 0x8c */
+	{ 36, 52, 0x100 },	/* 0x100 - 0x140 */
+	{ 53, 96, 0x180 },	/* 0x180 - 0x22c */
+};
+
+static unsigned int artpec6_pmx_reg_offset(unsigned int pin)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pin_register); i++) {
+		if (pin <= pin_register[i].end) {
+			return (pin - pin_register[i].start) * 4 +
+				pin_register[i].reg_base;
+		}
+	}
+	/*
+	 * Anything we return here is wrong, but we can only
+	 * get here if pin is outside registered range.
+	 */
+	pr_err("%s: Impossible pin %d\n", __func__, pin);
+	return 0;
+}
+
+static int artpec6_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(artpec6_pin_groups);
+}
+
+static const char *artpec6_get_group_name(struct pinctrl_dev *pctldev,
+					  unsigned int group)
+{
+	return artpec6_pin_groups[group].name;
+}
+
+static int artpec6_get_group_pins(struct pinctrl_dev *pctldev,
+				  unsigned int group,
+				  const unsigned int **pins,
+				  unsigned int *num_pins)
+{
+	*pins = (unsigned int *)artpec6_pin_groups[group].pins;
+	*num_pins = artpec6_pin_groups[group].num_pins;
+	return 0;
+}
+
+static int artpec6_pconf_drive_mA_to_field(unsigned int mA)
+{
+	switch (mA) {
+	case ARTPEC6_DRIVE_4mA:
+		return ARTPEC6_DRIVE_4mA_SET;
+	case ARTPEC6_DRIVE_6mA:
+		return ARTPEC6_DRIVE_6mA_SET;
+	case ARTPEC6_DRIVE_8mA:
+		return ARTPEC6_DRIVE_8mA_SET;
+	case ARTPEC6_DRIVE_9mA:
+		return ARTPEC6_DRIVE_9mA_SET;
+	default:
+		return -EINVAL;
+	}
+}
+
+static unsigned int artpec6_pconf_drive_field_to_mA(int field)
+{
+	switch (field) {
+	case ARTPEC6_DRIVE_4mA_SET:
+		return ARTPEC6_DRIVE_4mA;
+	case ARTPEC6_DRIVE_6mA_SET:
+		return ARTPEC6_DRIVE_6mA;
+	case ARTPEC6_DRIVE_8mA_SET:
+		return ARTPEC6_DRIVE_8mA;
+	case ARTPEC6_DRIVE_9mA_SET:
+		return ARTPEC6_DRIVE_9mA;
+	default:
+		/* Shouldn't happen */
+		return 0;
+	}
+}
+
+static struct pinctrl_ops artpec6_pctrl_ops = {
+	.get_group_pins		= artpec6_get_group_pins,
+	.get_groups_count	= artpec6_get_groups_count,
+	.get_group_name		= artpec6_get_group_name,
+	.dt_node_to_map		= pinconf_generic_dt_node_to_map_all,
+	.dt_free_map		= pinctrl_utils_free_map,
+};
+
+static const char * const gpiogrps[] = {
+	"cpuclkoutgrp0", "udlclkoutgrp0", "i2c1grp0", "i2c2grp0",
+	"i2c3grp0", "i2s0grp0", "i2s1grp0", "i2srefclkgrp0",
+	"spi0grp0", "spi1grp0", "pciedebuggrp0", "uart0grp0",
+	"uart0grp1", "uart1grp0", "uart2grp0", "uart2grp1",
+	"uart4grp0", "uart5grp0",
+};
+static const char * const cpuclkoutgrps[] = { "cpuclkoutgrp0" };
+static const char * const udlclkoutgrps[] = { "udlclkoutgrp0" };
+static const char * const i2c1grps[]	  = { "i2c1grp0" };
+static const char * const i2c2grps[]	  = { "i2c2grp0" };
+static const char * const i2c3grps[]	  = { "i2c3grp0" };
+static const char * const i2s0grps[]	  = { "i2s0grp0" };
+static const char * const i2s1grps[]	  = { "i2s1grp0" };
+static const char * const i2srefclkgrps[] = { "i2srefclkgrp0" };
+static const char * const spi0grps[]	  = { "spi0grp0" };
+static const char * const spi1grps[]	  = { "spi1grp0" };
+static const char * const pciedebuggrps[] = { "pciedebuggrp0" };
+static const char * const uart0grps[]	  = { "uart0grp0", "uart0grp1" };
+static const char * const uart1grps[]	  = { "uart1grp0" };
+static const char * const uart2grps[]	  = { "uart2grp0", "uart2grp1" };
+static const char * const uart3grps[]	  = { "uart3grp0" };
+static const char * const uart4grps[]	  = { "uart4grp0" };
+static const char * const uart5grps[]	  = { "uart5grp0", "uart5nocts" };
+static const char * const nandgrps[]	  = { "nandgrp0" };
+static const char * const sdio0grps[]	  = { "sdio0grp0" };
+static const char * const sdio1grps[]	  = { "sdio1grp0" };
+static const char * const ethernetgrps[]  = { "ethernetgrp0" };
+
+static const struct artpec6_pmx_func artpec6_pmx_functions[] = {
+	{
+		.name = "gpio",
+		.groups = gpiogrps,
+		.num_groups = ARRAY_SIZE(gpiogrps),
+	},
+	{
+		.name = "cpuclkout",
+		.groups = cpuclkoutgrps,
+		.num_groups = ARRAY_SIZE(cpuclkoutgrps),
+	},
+	{
+		.name = "udlclkout",
+		.groups = udlclkoutgrps,
+		.num_groups = ARRAY_SIZE(udlclkoutgrps),
+	},
+	{
+		.name = "i2c1",
+		.groups = i2c1grps,
+		.num_groups = ARRAY_SIZE(i2c1grps),
+	},
+	{
+		.name = "i2c2",
+		.groups = i2c2grps,
+		.num_groups = ARRAY_SIZE(i2c2grps),
+	},
+	{
+		.name = "i2c3",
+		.groups = i2c3grps,
+		.num_groups = ARRAY_SIZE(i2c3grps),
+	},
+	{
+		.name = "i2s0",
+		.groups = i2s0grps,
+		.num_groups = ARRAY_SIZE(i2s0grps),
+	},
+	{
+		.name = "i2s1",
+		.groups = i2s1grps,
+		.num_groups = ARRAY_SIZE(i2s1grps),
+	},
+	{
+		.name = "i2srefclk",
+		.groups = i2srefclkgrps,
+		.num_groups = ARRAY_SIZE(i2srefclkgrps),
+	},
+	{
+		.name = "spi0",
+		.groups = spi0grps,
+		.num_groups = ARRAY_SIZE(spi0grps),
+	},
+	{
+		.name = "spi1",
+		.groups = spi1grps,
+		.num_groups = ARRAY_SIZE(spi1grps),
+	},
+	{
+		.name = "pciedebug",
+		.groups = pciedebuggrps,
+		.num_groups = ARRAY_SIZE(pciedebuggrps),
+	},
+	{
+		.name = "uart0",
+		.groups = uart0grps,
+		.num_groups = ARRAY_SIZE(uart0grps),
+	},
+	{
+		.name = "uart1",
+		.groups = uart1grps,
+		.num_groups = ARRAY_SIZE(uart1grps),
+	},
+	{
+		.name = "uart2",
+		.groups = uart2grps,
+		.num_groups = ARRAY_SIZE(uart2grps),
+	},
+	{
+		.name = "uart3",
+		.groups = uart3grps,
+		.num_groups = ARRAY_SIZE(uart3grps),
+	},
+	{
+		.name = "uart4",
+		.groups = uart4grps,
+		.num_groups = ARRAY_SIZE(uart4grps),
+	},
+	{
+		.name = "uart5",
+		.groups = uart5grps,
+		.num_groups = ARRAY_SIZE(uart5grps),
+	},
+	{
+		.name = "nand",
+		.groups = nandgrps,
+		.num_groups = ARRAY_SIZE(nandgrps),
+	},
+	{
+		.name = "sdio0",
+		.groups = sdio0grps,
+		.num_groups = ARRAY_SIZE(sdio0grps),
+	},
+	{
+		.name = "sdio1",
+		.groups = sdio1grps,
+		.num_groups = ARRAY_SIZE(sdio1grps),
+	},
+	{
+		.name = "ethernet",
+		.groups = ethernetgrps,
+		.num_groups = ARRAY_SIZE(ethernetgrps),
+	},
+};
+
+static int artpec6_pmx_get_functions_count(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(artpec6_pmx_functions);
+}
+
+static const char *artpec6_pmx_get_fname(struct pinctrl_dev *pctldev,
+				  unsigned int function)
+{
+	return artpec6_pmx_functions[function].name;
+}
+
+static int artpec6_pmx_get_fgroups(struct pinctrl_dev *pctldev,
+				   unsigned int function,
+				   const char * const **groups,
+				   unsigned int * const num_groups)
+{
+	*groups = artpec6_pmx_functions[function].groups;
+	*num_groups = artpec6_pmx_functions[function].num_groups;
+	return 0;
+}
+
+static void artpec6_pmx_select_func(struct pinctrl_dev *pctldev,
+				    unsigned int function, unsigned int group,
+				    bool enable)
+{
+	unsigned int regval, val;
+	unsigned int reg;
+	int i;
+	struct artpec6_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+
+	for (i = 0; i < artpec6_pin_groups[group].num_pins; i++) {
+		/*
+		 * Registers for pins above a ARTPEC6_MAX_MUXABLE
+		 * do not have a SEL field and are always selected.
+		 */
+		if (artpec6_pin_groups[group].pins[i] > ARTPEC6_MAX_MUXABLE)
+			continue;
+
+		if (!strcmp(artpec6_pmx_get_fname(pctldev, function), "gpio")) {
+			/* GPIO is always config 0 */
+			val = ARTPEC6_CONFIG_0 << ARTPEC6_PINMUX_SEL_SHIFT;
+		} else {
+			if (enable)
+				val = artpec6_pin_groups[group].config
+					<< ARTPEC6_PINMUX_SEL_SHIFT;
+			else
+				val = ARTPEC6_CONFIG_0
+					<< ARTPEC6_PINMUX_SEL_SHIFT;
+		}
+
+		reg = artpec6_pmx_reg_offset(artpec6_pin_groups[group].pins[i]);
+
+		regval = readl(pmx->base + reg);
+		regval &= ~ARTPEC6_PINMUX_SEL_MASK;
+		regval |= val;
+		writel(regval, pmx->base + reg);
+	}
+}
+
+int artpec6_pmx_enable(struct pinctrl_dev *pctldev, unsigned int function,
+		       unsigned int group)
+{
+	struct artpec6_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+
+	dev_dbg(pmx->dev, "enabling %s function for pin group %s\n",
+		artpec6_pmx_get_fname(pctldev, function),
+		artpec6_get_group_name(pctldev, group));
+
+	artpec6_pmx_select_func(pctldev, function, group, true);
+
+	return 0;
+}
+
+void artpec6_pmx_disable(struct pinctrl_dev *pctldev, unsigned int function,
+			 unsigned int group)
+{
+	struct artpec6_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+
+	dev_dbg(pmx->dev, "disabling %s function for pin group %s\n",
+		artpec6_pmx_get_fname(pctldev, function),
+		artpec6_get_group_name(pctldev, group));
+
+	artpec6_pmx_select_func(pctldev, function, group, false);
+}
+
+static int artpec6_pmx_request_gpio(struct pinctrl_dev *pctldev,
+				    struct pinctrl_gpio_range *range,
+				    unsigned int pin)
+{
+	struct artpec6_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+	unsigned int reg = artpec6_pmx_reg_offset(pin);
+	u32 val;
+
+	if (pin >= 32)
+		return -EINVAL;
+
+	val = readl_relaxed(pmx->base + reg);
+	val &= ~ARTPEC6_PINMUX_SEL_MASK;
+	val |= ARTPEC6_CONFIG_0 << ARTPEC6_PINMUX_SEL_SHIFT;
+	writel_relaxed(val, pmx->base + reg);
+
+	return 0;
+}
+
+static const struct pinmux_ops artpec6_pmx_ops = {
+	.get_functions_count	= artpec6_pmx_get_functions_count,
+	.get_function_name	= artpec6_pmx_get_fname,
+	.get_function_groups	= artpec6_pmx_get_fgroups,
+	.set_mux		= artpec6_pmx_enable,
+	.gpio_request_enable = artpec6_pmx_request_gpio,
+};
+
+static int artpec6_pconf_get(struct pinctrl_dev *pctldev, unsigned int pin,
+			     unsigned long *config)
+{
+	struct artpec6_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param = pinconf_to_config_param(*config);
+	unsigned int regval;
+
+	/* Check for valid pin */
+	if (pin >= pmx->num_pins) {
+		dev_dbg(pmx->dev, "pinconf is not supported for pin %s\n",
+			pmx->pins[pin].name);
+		return -ENOTSUPP;
+	}
+
+	dev_dbg(pmx->dev, "getting configuration for pin %s\n",
+		pmx->pins[pin].name);
+
+	/* Read pin register values */
+	regval = readl(pmx->base + artpec6_pmx_reg_offset(pin));
+
+	/* If valid, get configuration for parameter */
+	switch (param) {
+	case PIN_CONFIG_BIAS_DISABLE:
+		if (!(regval & ARTPEC6_PINMUX_UDC1_MASK))
+			return -EINVAL;
+		break;
+
+	case PIN_CONFIG_BIAS_PULL_UP:
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		if (regval & ARTPEC6_PINMUX_UDC1_MASK)
+			return -EINVAL;
+
+		regval = regval & ARTPEC6_PINMUX_UDC0_MASK;
+		if ((param == PIN_CONFIG_BIAS_PULL_UP && !regval) ||
+		    (param == PIN_CONFIG_BIAS_PULL_DOWN && regval))
+			return -EINVAL;
+		break;
+	case PIN_CONFIG_DRIVE_STRENGTH:
+		regval = (regval & ARTPEC6_PINMUX_DRV_MASK)
+			>> ARTPEC6_PINMUX_DRV_SHIFT;
+		regval = artpec6_pconf_drive_field_to_mA(regval);
+		*config = pinconf_to_config_packed(param, regval);
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+/*
+ * Valid combinations of param and arg:
+ *
+ * param		     arg
+ * PIN_CONFIG_BIAS_DISABLE:   x (disable bias)
+ * PIN_CONFIG_BIAS_PULL_UP:   1 (pull up bias + enable)
+ * PIN_CONFIG_BIAS_PULL_DOWN: 1 (pull down bias + enable)
+ * PIN_CONFIG_DRIVE_STRENGTH: x (4mA, 6mA, 8mA, 9mA)
+ *
+ * All other args are invalid. All other params are not supported.
+ */
+static int artpec6_pconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
+			     unsigned long *configs, unsigned int num_configs)
+{
+	struct artpec6_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param;
+	unsigned int arg;
+	unsigned int regval;
+	unsigned int *reg;
+	int i;
+
+	/* Check for valid pin */
+	if (pin >= pmx->num_pins) {
+		dev_dbg(pmx->dev, "pinconf is not supported for pin %s\n",
+			pmx->pins[pin].name);
+		return -ENOTSUPP;
+	}
+
+	dev_dbg(pmx->dev, "setting configuration for pin %s\n",
+		pmx->pins[pin].name);
+
+	reg = pmx->base + artpec6_pmx_reg_offset(pin);
+
+	/* For each config */
+	for (i = 0; i < num_configs; i++) {
+		int drive;
+
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			regval = readl(reg);
+			regval |= (1 << ARTPEC6_PINMUX_UDC1_SHIFT);
+			writel(regval, reg);
+			break;
+
+		case PIN_CONFIG_BIAS_PULL_UP:
+			if (arg != 1) {
+				dev_dbg(pctldev->dev, "%s: arg %u out of range\n",
+					__func__, arg);
+				return -EINVAL;
+			}
+
+			regval = readl(reg);
+			regval |= (arg << ARTPEC6_PINMUX_UDC0_SHIFT);
+			regval &= ~ARTPEC6_PINMUX_UDC1_MASK; /* Enable */
+			writel(regval, reg);
+			break;
+
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			if (arg != 1) {
+				dev_dbg(pctldev->dev, "%s: arg %u out of range\n",
+					__func__, arg);
+				return -EINVAL;
+			}
+
+			regval = readl(reg);
+			regval &= ~(arg << ARTPEC6_PINMUX_UDC0_SHIFT);
+			regval &= ~ARTPEC6_PINMUX_UDC1_MASK; /* Enable */
+			writel(regval, reg);
+			break;
+
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			drive = artpec6_pconf_drive_mA_to_field(arg);
+			if (drive < 0) {
+				dev_dbg(pctldev->dev, "%s: arg %u out of range\n",
+					__func__, arg);
+				return -EINVAL;
+			}
+
+			regval = readl(reg);
+			regval &= ~ARTPEC6_PINMUX_DRV_MASK;
+			regval |= (drive << ARTPEC6_PINMUX_DRV_SHIFT);
+			writel(regval, reg);
+			break;
+
+		default:
+			dev_dbg(pmx->dev, "parameter not supported\n");
+			return -ENOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int artpec6_pconf_group_set(struct pinctrl_dev *pctldev,
+				   unsigned int group, unsigned long *configs,
+				   unsigned int num_configs)
+{
+	unsigned int num_pins, current_pin;
+	int ret;
+
+	dev_dbg(pctldev->dev, "setting group %s configuration\n",
+		artpec6_get_group_name(pctldev, group));
+
+	num_pins = artpec6_pin_groups[group].num_pins;
+
+	for (current_pin = 0; current_pin < num_pins; current_pin++) {
+		ret = artpec6_pconf_set(pctldev,
+				artpec6_pin_groups[group].pins[current_pin],
+				configs, num_configs);
+
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct pinconf_ops artpec6_pconf_ops = {
+	.is_generic		= true,
+	.pin_config_get		= artpec6_pconf_get,
+	.pin_config_set		= artpec6_pconf_set,
+	.pin_config_group_set	= artpec6_pconf_group_set,
+};
+
+static struct pinctrl_desc artpec6_desc = {
+	.name	 = "artpec6-pinctrl",
+	.owner	 = THIS_MODULE,
+	.pins	 = artpec6_pins,
+	.npins	 = ARRAY_SIZE(artpec6_pins),
+	.pctlops = &artpec6_pctrl_ops,
+	.pmxops	 = &artpec6_pmx_ops,
+	.confops = &artpec6_pconf_ops,
+};
+
+/* The reset values say 4mA, but we want 8mA as default. */
+static void artpec6_pmx_reset(struct artpec6_pmx *pmx)
+{
+	void __iomem *base = pmx->base;
+	int i;
+
+	for (i = 0; i < ARTPEC6_LAST_PIN; i++) {
+		u32 val;
+
+		val = readl_relaxed(base + artpec6_pmx_reg_offset(i));
+		val &= ~ARTPEC6_PINMUX_DRV_MASK;
+		val |= ARTPEC6_DRIVE_8mA_SET << ARTPEC6_PINMUX_DRV_SHIFT;
+		writel_relaxed(val, base + artpec6_pmx_reg_offset(i));
+	}
+}
+
+static int artpec6_pmx_probe(struct platform_device *pdev)
+{
+	struct artpec6_pmx *pmx;
+	struct resource *res;
+
+	pmx = devm_kzalloc(&pdev->dev, sizeof(*pmx), GFP_KERNEL);
+	if (!pmx)
+		return -ENOMEM;
+
+	pmx->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pmx->base = devm_ioremap_resource(&pdev->dev, res);
+
+	if (IS_ERR(pmx->base))
+		return PTR_ERR(pmx->base);
+
+	artpec6_pmx_reset(pmx);
+
+	pmx->pins	    = artpec6_pins;
+	pmx->num_pins	    = ARRAY_SIZE(artpec6_pins);
+	pmx->functions	    = artpec6_pmx_functions;
+	pmx->num_functions  = ARRAY_SIZE(artpec6_pmx_functions);
+	pmx->pin_groups	    = artpec6_pin_groups;
+	pmx->num_pin_groups = ARRAY_SIZE(artpec6_pin_groups);
+	pmx->pctl	    = pinctrl_register(&artpec6_desc, &pdev->dev, pmx);
+
+	if (IS_ERR(pmx->pctl)) {
+		dev_err(&pdev->dev, "could not register pinctrl driver\n");
+		return PTR_ERR(pmx->pctl);
+	}
+
+	platform_set_drvdata(pdev, pmx);
+
+	dev_info(&pdev->dev, "initialised Axis ARTPEC-6 pinctrl driver\n");
+
+	return 0;
+}
+
+static int artpec6_pmx_remove(struct platform_device *pdev)
+{
+	struct artpec6_pmx *pmx = platform_get_drvdata(pdev);
+
+	pinctrl_unregister(pmx->pctl);
+
+	return 0;
+}
+
+static const struct of_device_id artpec6_pinctrl_match[] = {
+	{ .compatible = "axis,artpec6-pinctrl" },
+	{},
+};
+
+static struct platform_driver artpec6_pmx_driver = {
+	.driver = {
+		.name = "artpec6-pinctrl",
+		.of_match_table = artpec6_pinctrl_match,
+	},
+	.probe = artpec6_pmx_probe,
+	.remove = artpec6_pmx_remove,
+};
+
+static int __init artpec6_pmx_init(void)
+{
+	return platform_driver_register(&artpec6_pmx_driver);
+}
+arch_initcall(artpec6_pmx_init);
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 28bbc1bb9e6c..dc8591543dee 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -126,7 +126,11 @@ struct atmel_pioctrl {
 	struct irq_domain	*irq_domain;
 	int			*irqs;
 	unsigned		*pm_wakeup_sources;
-	unsigned		*pm_suspend_backup;
+	struct {
+		u32		imr;
+		u32		odsr;
+		u32		cfgr[ATMEL_PIO_NPINS_PER_BANK];
+	} *pm_suspend_backup;
 	struct device		*dev;
 	struct device_node	*node;
 };
@@ -830,17 +834,26 @@ static int __maybe_unused atmel_pctrl_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct atmel_pioctrl *atmel_pioctrl = platform_get_drvdata(pdev);
-	int i;
+	int i, j;
 
 	/*
 	 * For each bank, save IMR to restore it later and disable all GPIO
 	 * interrupts excepting the ones marked as wakeup sources.
 	 */
 	for (i = 0; i < atmel_pioctrl->nbanks; i++) {
-		atmel_pioctrl->pm_suspend_backup[i] =
+		atmel_pioctrl->pm_suspend_backup[i].imr =
 			atmel_gpio_read(atmel_pioctrl, i, ATMEL_PIO_IMR);
 		atmel_gpio_write(atmel_pioctrl, i, ATMEL_PIO_IDR,
 				 ~atmel_pioctrl->pm_wakeup_sources[i]);
+		atmel_pioctrl->pm_suspend_backup[i].odsr =
+			atmel_gpio_read(atmel_pioctrl, i, ATMEL_PIO_ODSR);
+		for (j = 0; j < ATMEL_PIO_NPINS_PER_BANK; j++) {
+			atmel_gpio_write(atmel_pioctrl, i,
+					 ATMEL_PIO_MSKR, BIT(j));
+			atmel_pioctrl->pm_suspend_backup[i].cfgr[j] =
+				atmel_gpio_read(atmel_pioctrl, i,
+						ATMEL_PIO_CFGR);
+		}
 	}
 
 	return 0;
@@ -850,11 +863,20 @@ static int __maybe_unused atmel_pctrl_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct atmel_pioctrl *atmel_pioctrl = platform_get_drvdata(pdev);
-	int i;
+	int i, j;
 
-	for (i = 0; i < atmel_pioctrl->nbanks; i++)
+	for (i = 0; i < atmel_pioctrl->nbanks; i++) {
 		atmel_gpio_write(atmel_pioctrl, i, ATMEL_PIO_IER,
-				 atmel_pioctrl->pm_suspend_backup[i]);
+				 atmel_pioctrl->pm_suspend_backup[i].imr);
+		atmel_gpio_write(atmel_pioctrl, i, ATMEL_PIO_SODR,
+				 atmel_pioctrl->pm_suspend_backup[i].odsr);
+		for (j = 0; j < ATMEL_PIO_NPINS_PER_BANK; j++) {
+			atmel_gpio_write(atmel_pioctrl, i,
+					 ATMEL_PIO_MSKR, BIT(j));
+			atmel_gpio_write(atmel_pioctrl, i, ATMEL_PIO_CFGR,
+					 atmel_pioctrl->pm_suspend_backup[i].cfgr[j]);
+		}
+	}
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 7813599e43fa..f141aa0430b1 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -59,7 +59,7 @@
 #define GPIO_LS_SYNC		0x60
 
 enum rockchip_pinctrl_type {
-	RK1108,
+	RV1108,
 	RK2928,
 	RK3066B,
 	RK3188,
@@ -75,6 +75,8 @@ enum rockchip_pinctrl_type {
 #define IOMUX_WIDTH_4BIT	BIT(1)
 #define IOMUX_SOURCE_PMU	BIT(2)
 #define IOMUX_UNROUTED		BIT(3)
+#define IOMUX_WIDTH_3BIT	BIT(4)
+#define IOMUX_RECALCED		BIT(5)
 
 /**
  * @type: iomux variant using IOMUX_* constants
@@ -141,6 +143,9 @@ struct rockchip_drv {
  * @gpio_chip: gpiolib chip
  * @grange: gpio range
  * @slock: spinlock for the gpio bank
+ * @irq_lock: bus lock for irq chip
+ * @new_irqs: newly configured irqs which must be muxed as GPIOs in
+ *	irq_bus_sync_unlock()
  */
 struct rockchip_pin_bank {
 	void __iomem			*reg_base;
@@ -161,8 +166,10 @@ struct rockchip_pin_bank {
 	struct irq_domain		*domain;
 	struct gpio_chip		gpio_chip;
 	struct pinctrl_gpio_range	grange;
-	spinlock_t			slock;
+	raw_spinlock_t			slock;
 	u32				toggle_edge_mode;
+	struct mutex			irq_lock;
+	u32				new_irqs;
 };
 
 #define PIN_BANK(id, pins, label)			\
@@ -304,6 +311,11 @@ struct rockchip_pin_ctrl {
 	void	(*drv_calc_reg)(struct rockchip_pin_bank *bank,
 				    int pin_num, struct regmap **regmap,
 				    int *reg, u8 *bit);
+	void	(*iomux_recalc)(u8 bank_num, int pin, int *reg,
+				u8 *bit, int *mask);
+	int	(*schmitt_calc_reg)(struct rockchip_pin_bank *bank,
+				    int pin_num, struct regmap **regmap,
+				    int *reg, u8 *bit);
 };
 
 struct rockchip_pin_config {
@@ -355,6 +367,22 @@ struct rockchip_pinctrl {
 	unsigned int			nfunctions;
 };
 
+/**
+ * struct rockchip_mux_recalced_data: represent a pin iomux data.
+ * @num: bank number.
+ * @pin: pin number.
+ * @bit: index at register.
+ * @reg: register offset.
+ * @mask: mask bit
+ */
+struct rockchip_mux_recalced_data {
+	u8 num;
+	u8 pin;
+	u8 reg;
+	u8 bit;
+	u8 mask;
+};
+
 static struct regmap_config rockchip_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
@@ -514,13 +542,57 @@ static const struct pinctrl_ops rockchip_pctrl_ops = {
  * Hardware access
  */
 
+static const struct rockchip_mux_recalced_data rk3328_mux_recalced_data[] = {
+	{
+		.num = 2,
+		.pin = 12,
+		.reg = 0x24,
+		.bit = 8,
+		.mask = 0x3
+	}, {
+		.num = 2,
+		.pin = 15,
+		.reg = 0x28,
+		.bit = 0,
+		.mask = 0x7
+	}, {
+		.num = 2,
+		.pin = 23,
+		.reg = 0x30,
+		.bit = 14,
+		.mask = 0x3
+	},
+};
+
+static void rk3328_recalc_mux(u8 bank_num, int pin, int *reg,
+			      u8 *bit, int *mask)
+{
+	const struct rockchip_mux_recalced_data *data = NULL;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rk3328_mux_recalced_data); i++)
+		if (rk3328_mux_recalced_data[i].num == bank_num &&
+		    rk3328_mux_recalced_data[i].pin == pin) {
+			data = &rk3328_mux_recalced_data[i];
+			break;
+		}
+
+	if (!data)
+		return;
+
+	*reg = data->reg;
+	*mask = data->mask;
+	*bit = data->bit;
+}
+
 static int rockchip_get_mux(struct rockchip_pin_bank *bank, int pin)
 {
 	struct rockchip_pinctrl *info = bank->drvdata;
+	struct rockchip_pin_ctrl *ctrl = info->ctrl;
 	int iomux_num = (pin / 8);
 	struct regmap *regmap;
 	unsigned int val;
-	int reg, ret, mask;
+	int reg, ret, mask, mux_type;
 	u8 bit;
 
 	if (iomux_num > 3)
@@ -538,16 +610,26 @@ static int rockchip_get_mux(struct rockchip_pin_bank *bank, int pin)
 				? info->regmap_pmu : info->regmap_base;
 
 	/* get basic quadrupel of mux registers and the correct reg inside */
-	mask = (bank->iomux[iomux_num].type & IOMUX_WIDTH_4BIT) ? 0xf : 0x3;
+	mux_type = bank->iomux[iomux_num].type;
 	reg = bank->iomux[iomux_num].offset;
-	if (bank->iomux[iomux_num].type & IOMUX_WIDTH_4BIT) {
+	if (mux_type & IOMUX_WIDTH_4BIT) {
 		if ((pin % 8) >= 4)
 			reg += 0x4;
 		bit = (pin % 4) * 4;
+		mask = 0xf;
+	} else if (mux_type & IOMUX_WIDTH_3BIT) {
+		if ((pin % 8) >= 5)
+			reg += 0x4;
+		bit = (pin % 8 % 5) * 3;
+		mask = 0x7;
 	} else {
 		bit = (pin % 8) * 2;
+		mask = 0x3;
 	}
 
+	if (ctrl->iomux_recalc && (mux_type & IOMUX_RECALCED))
+		ctrl->iomux_recalc(bank->bank_num, pin, &reg, &bit, &mask);
+
 	ret = regmap_read(regmap, reg, &val);
 	if (ret)
 		return ret;
@@ -555,6 +637,31 @@ static int rockchip_get_mux(struct rockchip_pin_bank *bank, int pin)
 	return ((val >> bit) & mask);
 }
 
+static int rockchip_verify_mux(struct rockchip_pin_bank *bank,
+			       int pin, int mux)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+	int iomux_num = (pin / 8);
+
+	if (iomux_num > 3)
+		return -EINVAL;
+
+	if (bank->iomux[iomux_num].type & IOMUX_UNROUTED) {
+		dev_err(info->dev, "pin %d is unrouted\n", pin);
+		return -EINVAL;
+	}
+
+	if (bank->iomux[iomux_num].type & IOMUX_GPIO_ONLY) {
+		if (mux != RK_FUNC_GPIO) {
+			dev_err(info->dev,
+				"pin %d only supports a gpio mux\n", pin);
+			return -ENOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Set a new mux function for a pin.
  *
@@ -571,30 +678,19 @@ static int rockchip_get_mux(struct rockchip_pin_bank *bank, int pin)
 static int rockchip_set_mux(struct rockchip_pin_bank *bank, int pin, int mux)
 {
 	struct rockchip_pinctrl *info = bank->drvdata;
+	struct rockchip_pin_ctrl *ctrl = info->ctrl;
 	int iomux_num = (pin / 8);
 	struct regmap *regmap;
-	int reg, ret, mask;
-	unsigned long flags;
+	int reg, ret, mask, mux_type;
 	u8 bit;
 	u32 data, rmask;
 
-	if (iomux_num > 3)
-		return -EINVAL;
-
-	if (bank->iomux[iomux_num].type & IOMUX_UNROUTED) {
-		dev_err(info->dev, "pin %d is unrouted\n", pin);
-		return -EINVAL;
-	}
+	ret = rockchip_verify_mux(bank, pin, mux);
+	if (ret < 0)
+		return ret;
 
-	if (bank->iomux[iomux_num].type & IOMUX_GPIO_ONLY) {
-		if (mux != RK_FUNC_GPIO) {
-			dev_err(info->dev,
-				"pin %d only supports a gpio mux\n", pin);
-			return -ENOTSUPP;
-		} else {
-			return 0;
-		}
-	}
+	if (bank->iomux[iomux_num].type & IOMUX_GPIO_ONLY)
+		return 0;
 
 	dev_dbg(info->dev, "setting mux of GPIO%d-%d to %d\n",
 						bank->bank_num, pin, mux);
@@ -603,35 +699,41 @@ static int rockchip_set_mux(struct rockchip_pin_bank *bank, int pin, int mux)
 				? info->regmap_pmu : info->regmap_base;
 
 	/* get basic quadrupel of mux registers and the correct reg inside */
-	mask = (bank->iomux[iomux_num].type & IOMUX_WIDTH_4BIT) ? 0xf : 0x3;
+	mux_type = bank->iomux[iomux_num].type;
 	reg = bank->iomux[iomux_num].offset;
-	if (bank->iomux[iomux_num].type & IOMUX_WIDTH_4BIT) {
+	if (mux_type & IOMUX_WIDTH_4BIT) {
 		if ((pin % 8) >= 4)
 			reg += 0x4;
 		bit = (pin % 4) * 4;
+		mask = 0xf;
+	} else if (mux_type & IOMUX_WIDTH_3BIT) {
+		if ((pin % 8) >= 5)
+			reg += 0x4;
+		bit = (pin % 8 % 5) * 3;
+		mask = 0x7;
 	} else {
 		bit = (pin % 8) * 2;
+		mask = 0x3;
 	}
 
-	spin_lock_irqsave(&bank->slock, flags);
+	if (ctrl->iomux_recalc && (mux_type & IOMUX_RECALCED))
+		ctrl->iomux_recalc(bank->bank_num, pin, &reg, &bit, &mask);
 
 	data = (mask << (bit + 16));
 	rmask = data | (data >> 16);
 	data |= (mux & mask) << bit;
 	ret = regmap_update_bits(regmap, reg, rmask, data);
 
-	spin_unlock_irqrestore(&bank->slock, flags);
-
 	return ret;
 }
 
-#define RK1108_PULL_PMU_OFFSET		0x10
-#define RK1108_PULL_OFFSET		0x110
-#define RK1108_PULL_PINS_PER_REG	8
-#define RK1108_PULL_BITS_PER_PIN	2
-#define RK1108_PULL_BANK_STRIDE		16
+#define RV1108_PULL_PMU_OFFSET		0x10
+#define RV1108_PULL_OFFSET		0x110
+#define RV1108_PULL_PINS_PER_REG	8
+#define RV1108_PULL_BITS_PER_PIN	2
+#define RV1108_PULL_BANK_STRIDE		16
 
-static void rk1108_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank,
+static void rv1108_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank,
 					 int pin_num, struct regmap **regmap,
 					 int *reg, u8 *bit)
 {
@@ -640,27 +742,27 @@ static void rk1108_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank,
 	/* The first 24 pins of the first bank are located in PMU */
 	if (bank->bank_num == 0) {
 		*regmap = info->regmap_pmu;
-		*reg = RK1108_PULL_PMU_OFFSET;
+		*reg = RV1108_PULL_PMU_OFFSET;
 	} else {
-		*reg = RK1108_PULL_OFFSET;
+		*reg = RV1108_PULL_OFFSET;
 		*regmap = info->regmap_base;
 		/* correct the offset, as we're starting with the 2nd bank */
 		*reg -= 0x10;
-		*reg += bank->bank_num * RK1108_PULL_BANK_STRIDE;
+		*reg += bank->bank_num * RV1108_PULL_BANK_STRIDE;
 	}
 
-	*reg += ((pin_num / RK1108_PULL_PINS_PER_REG) * 4);
-	*bit = (pin_num % RK1108_PULL_PINS_PER_REG);
-	*bit *= RK1108_PULL_BITS_PER_PIN;
+	*reg += ((pin_num / RV1108_PULL_PINS_PER_REG) * 4);
+	*bit = (pin_num % RV1108_PULL_PINS_PER_REG);
+	*bit *= RV1108_PULL_BITS_PER_PIN;
 }
 
-#define RK1108_DRV_PMU_OFFSET		0x20
-#define RK1108_DRV_GRF_OFFSET		0x210
-#define RK1108_DRV_BITS_PER_PIN		2
-#define RK1108_DRV_PINS_PER_REG		8
-#define RK1108_DRV_BANK_STRIDE		16
+#define RV1108_DRV_PMU_OFFSET		0x20
+#define RV1108_DRV_GRF_OFFSET		0x210
+#define RV1108_DRV_BITS_PER_PIN		2
+#define RV1108_DRV_PINS_PER_REG		8
+#define RV1108_DRV_BANK_STRIDE		16
 
-static void rk1108_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank,
+static void rv1108_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank,
 					int pin_num, struct regmap **regmap,
 					int *reg, u8 *bit)
 {
@@ -669,19 +771,19 @@ static void rk1108_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank,
 	/* The first 24 pins of the first bank are located in PMU */
 	if (bank->bank_num == 0) {
 		*regmap = info->regmap_pmu;
-		*reg = RK1108_DRV_PMU_OFFSET;
+		*reg = RV1108_DRV_PMU_OFFSET;
 	} else {
 		*regmap = info->regmap_base;
-		*reg = RK1108_DRV_GRF_OFFSET;
+		*reg = RV1108_DRV_GRF_OFFSET;
 
 		/* correct the offset, as we're starting with the 2nd bank */
 		*reg -= 0x10;
-		*reg += bank->bank_num * RK1108_DRV_BANK_STRIDE;
+		*reg += bank->bank_num * RV1108_DRV_BANK_STRIDE;
 	}
 
-	*reg += ((pin_num / RK1108_DRV_PINS_PER_REG) * 4);
-	*bit = pin_num % RK1108_DRV_PINS_PER_REG;
-	*bit *= RK1108_DRV_BITS_PER_PIN;
+	*reg += ((pin_num / RV1108_DRV_PINS_PER_REG) * 4);
+	*bit = pin_num % RV1108_DRV_PINS_PER_REG;
+	*bit *= RV1108_DRV_BITS_PER_PIN;
 }
 
 #define RK2928_PULL_OFFSET		0x118
@@ -1047,7 +1149,6 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 	struct rockchip_pinctrl *info = bank->drvdata;
 	struct rockchip_pin_ctrl *ctrl = info->ctrl;
 	struct regmap *regmap;
-	unsigned long flags;
 	int reg, ret, i;
 	u32 data, rmask, rmask_bits, temp;
 	u8 bit;
@@ -1075,8 +1176,6 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 		return ret;
 	}
 
-	spin_lock_irqsave(&bank->slock, flags);
-
 	switch (drv_type) {
 	case DRV_TYPE_IO_1V8_3V0_AUTO:
 	case DRV_TYPE_IO_3V3_ONLY:
@@ -1097,17 +1196,14 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 			rmask = BIT(15) | BIT(31);
 			data |= BIT(31);
 			ret = regmap_update_bits(regmap, reg, rmask, data);
-			if (ret) {
-				spin_unlock_irqrestore(&bank->slock, flags);
+			if (ret)
 				return ret;
-			}
 
 			rmask = 0x3 | (0x3 << 16);
 			temp |= (0x3 << 16);
 			reg += 0x4;
 			ret = regmap_update_bits(regmap, reg, rmask, temp);
 
-			spin_unlock_irqrestore(&bank->slock, flags);
 			return ret;
 		case 18 ... 21:
 			/* setting fully enclosed in the second register */
@@ -1115,7 +1211,6 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 			bit -= 16;
 			break;
 		default:
-			spin_unlock_irqrestore(&bank->slock, flags);
 			dev_err(info->dev, "unsupported bit: %d for pinctrl drive type: %d\n",
 				bit, drv_type);
 			return -EINVAL;
@@ -1127,7 +1222,6 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 		rmask_bits = RK3288_DRV_BITS_PER_PIN;
 		break;
 	default:
-		spin_unlock_irqrestore(&bank->slock, flags);
 		dev_err(info->dev, "unsupported pinctrl drive type: %d\n",
 			drv_type);
 		return -EINVAL;
@@ -1139,7 +1233,6 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 	data |= (ret << bit);
 
 	ret = regmap_update_bits(regmap, reg, rmask, data);
-	spin_unlock_irqrestore(&bank->slock, flags);
 
 	return ret;
 }
@@ -1183,7 +1276,7 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num)
 		return !(data & BIT(bit))
 				? PIN_CONFIG_BIAS_PULL_PIN_DEFAULT
 				: PIN_CONFIG_BIAS_DISABLE;
-	case RK1108:
+	case RV1108:
 	case RK3188:
 	case RK3288:
 	case RK3368:
@@ -1206,7 +1299,6 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank,
 	struct rockchip_pin_ctrl *ctrl = info->ctrl;
 	struct regmap *regmap;
 	int reg, ret, i, pull_type;
-	unsigned long flags;
 	u8 bit;
 	u32 data, rmask;
 
@@ -1221,16 +1313,12 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank,
 
 	switch (ctrl->type) {
 	case RK2928:
-		spin_lock_irqsave(&bank->slock, flags);
-
 		data = BIT(bit + 16);
 		if (pull == PIN_CONFIG_BIAS_DISABLE)
 			data |= BIT(bit);
 		ret = regmap_write(regmap, reg, data);
-
-		spin_unlock_irqrestore(&bank->slock, flags);
 		break;
-	case RK1108:
+	case RV1108:
 	case RK3188:
 	case RK3288:
 	case RK3368:
@@ -1251,16 +1339,12 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank,
 			return ret;
 		}
 
-		spin_lock_irqsave(&bank->slock, flags);
-
 		/* enable the write to the equivalent lower bits */
 		data = ((1 << RK3188_PULL_BITS_PER_PIN) - 1) << (bit + 16);
 		rmask = data | (data >> 16);
 		data |= (ret << bit);
 
 		ret = regmap_update_bits(regmap, reg, rmask, data);
-
-		spin_unlock_irqrestore(&bank->slock, flags);
 		break;
 	default:
 		dev_err(info->dev, "unsupported pinctrl type\n");
@@ -1270,6 +1354,73 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank,
 	return ret;
 }
 
+#define RK3328_SCHMITT_BITS_PER_PIN		1
+#define RK3328_SCHMITT_PINS_PER_REG		16
+#define RK3328_SCHMITT_BANK_STRIDE		8
+#define RK3328_SCHMITT_GRF_OFFSET		0x380
+
+static int rk3328_calc_schmitt_reg_and_bit(struct rockchip_pin_bank *bank,
+					   int pin_num,
+					   struct regmap **regmap,
+					   int *reg, u8 *bit)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+
+	*regmap = info->regmap_base;
+	*reg = RK3328_SCHMITT_GRF_OFFSET;
+
+	*reg += bank->bank_num * RK3328_SCHMITT_BANK_STRIDE;
+	*reg += ((pin_num / RK3328_SCHMITT_PINS_PER_REG) * 4);
+	*bit = pin_num % RK3328_SCHMITT_PINS_PER_REG;
+
+	return 0;
+}
+
+static int rockchip_get_schmitt(struct rockchip_pin_bank *bank, int pin_num)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+	struct rockchip_pin_ctrl *ctrl = info->ctrl;
+	struct regmap *regmap;
+	int reg, ret;
+	u8 bit;
+	u32 data;
+
+	ret = ctrl->schmitt_calc_reg(bank, pin_num, &regmap, &reg, &bit);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(regmap, reg, &data);
+	if (ret)
+		return ret;
+
+	data >>= bit;
+	return data & 0x1;
+}
+
+static int rockchip_set_schmitt(struct rockchip_pin_bank *bank,
+				int pin_num, int enable)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+	struct rockchip_pin_ctrl *ctrl = info->ctrl;
+	struct regmap *regmap;
+	int reg, ret;
+	u8 bit;
+	u32 data, rmask;
+
+	dev_dbg(info->dev, "setting input schmitt of GPIO%d-%d to %d\n",
+		bank->bank_num, pin_num, enable);
+
+	ret = ctrl->schmitt_calc_reg(bank, pin_num, &regmap, &reg, &bit);
+	if (ret)
+		return ret;
+
+	/* enable the write to the equivalent lower bits */
+	data = BIT(bit + 16) | (enable << bit);
+	rmask = BIT(bit + 16) | BIT(bit);
+
+	return regmap_update_bits(regmap, reg, rmask, data);
+}
+
 /*
  * Pinmux_ops handling
  */
@@ -1366,7 +1517,7 @@ static int _rockchip_pmx_gpio_set_direction(struct gpio_chip *chip,
 		return ret;
 
 	clk_enable(bank->clk);
-	spin_lock_irqsave(&bank->slock, flags);
+	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	data = readl_relaxed(bank->reg_base + GPIO_SWPORT_DDR);
 	/* set bit to 1 for output, 0 for input */
@@ -1376,7 +1527,7 @@ static int _rockchip_pmx_gpio_set_direction(struct gpio_chip *chip,
 		data &= ~BIT(pin);
 	writel_relaxed(data, bank->reg_base + GPIO_SWPORT_DDR);
 
-	spin_unlock_irqrestore(&bank->slock, flags);
+	raw_spin_unlock_irqrestore(&bank->slock, flags);
 	clk_disable(bank->clk);
 
 	return 0;
@@ -1420,7 +1571,7 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl,
 					pull == PIN_CONFIG_BIAS_DISABLE);
 	case RK3066B:
 		return pull ? false : true;
-	case RK1108:
+	case RV1108:
 	case RK3188:
 	case RK3288:
 	case RK3368:
@@ -1489,6 +1640,15 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			if (rc < 0)
 				return rc;
 			break;
+		case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+			if (!info->ctrl->schmitt_calc_reg)
+				return -ENOTSUPP;
+
+			rc = rockchip_set_schmitt(bank,
+						  pin - bank->pin_base, arg);
+			if (rc < 0)
+				return rc;
+			break;
 		default:
 			return -ENOTSUPP;
 			break;
@@ -1549,6 +1709,16 @@ static int rockchip_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin,
 
 		arg = rc;
 		break;
+	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		if (!info->ctrl->schmitt_calc_reg)
+			return -ENOTSUPP;
+
+		rc = rockchip_get_schmitt(bank, pin - bank->pin_base);
+		if (rc < 0)
+			return rc;
+
+		arg = rc;
+		break;
 	default:
 		return -ENOTSUPP;
 		break;
@@ -1807,7 +1977,7 @@ static void rockchip_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
 	u32 data;
 
 	clk_enable(bank->clk);
-	spin_lock_irqsave(&bank->slock, flags);
+	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	data = readl(reg);
 	data &= ~BIT(offset);
@@ -1815,7 +1985,7 @@ static void rockchip_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
 		data |= BIT(offset);
 	writel(data, reg);
 
-	spin_unlock_irqrestore(&bank->slock, flags);
+	raw_spin_unlock_irqrestore(&bank->slock, flags);
 	clk_disable(bank->clk);
 }
 
@@ -1927,7 +2097,7 @@ static void rockchip_irq_demux(struct irq_desc *desc)
 
 			data = readl_relaxed(bank->reg_base + GPIO_EXT_PORT);
 			do {
-				spin_lock_irqsave(&bank->slock, flags);
+				raw_spin_lock_irqsave(&bank->slock, flags);
 
 				polarity = readl_relaxed(bank->reg_base +
 							 GPIO_INT_POLARITY);
@@ -1938,7 +2108,7 @@ static void rockchip_irq_demux(struct irq_desc *desc)
 				writel(polarity,
 				       bank->reg_base + GPIO_INT_POLARITY);
 
-				spin_unlock_irqrestore(&bank->slock, flags);
+				raw_spin_unlock_irqrestore(&bank->slock, flags);
 
 				data_old = data;
 				data = readl_relaxed(bank->reg_base +
@@ -1964,25 +2134,26 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type)
 	int ret;
 
 	/* make sure the pin is configured as gpio input */
-	ret = rockchip_set_mux(bank, d->hwirq, RK_FUNC_GPIO);
+	ret = rockchip_verify_mux(bank, d->hwirq, RK_FUNC_GPIO);
 	if (ret < 0)
 		return ret;
 
-	clk_enable(bank->clk);
-	spin_lock_irqsave(&bank->slock, flags);
+	bank->new_irqs |= mask;
+
+	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	data = readl_relaxed(bank->reg_base + GPIO_SWPORT_DDR);
 	data &= ~mask;
 	writel_relaxed(data, bank->reg_base + GPIO_SWPORT_DDR);
 
-	spin_unlock_irqrestore(&bank->slock, flags);
+	raw_spin_unlock_irqrestore(&bank->slock, flags);
 
 	if (type & IRQ_TYPE_EDGE_BOTH)
 		irq_set_handler_locked(d, handle_edge_irq);
 	else
 		irq_set_handler_locked(d, handle_level_irq);
 
-	spin_lock_irqsave(&bank->slock, flags);
+	raw_spin_lock_irqsave(&bank->slock, flags);
 	irq_gc_lock(gc);
 
 	level = readl_relaxed(gc->reg_base + GPIO_INTTYPE_LEVEL);
@@ -2025,8 +2196,7 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type)
 		break;
 	default:
 		irq_gc_unlock(gc);
-		spin_unlock_irqrestore(&bank->slock, flags);
-		clk_disable(bank->clk);
+		raw_spin_unlock_irqrestore(&bank->slock, flags);
 		return -EINVAL;
 	}
 
@@ -2034,8 +2204,7 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type)
 	writel_relaxed(polarity, gc->reg_base + GPIO_INT_POLARITY);
 
 	irq_gc_unlock(gc);
-	spin_unlock_irqrestore(&bank->slock, flags);
-	clk_disable(bank->clk);
+	raw_spin_unlock_irqrestore(&bank->slock, flags);
 
 	return 0;
 }
@@ -2061,7 +2230,7 @@ static void rockchip_irq_resume(struct irq_data *d)
 	clk_disable(bank->clk);
 }
 
-static void rockchip_irq_gc_mask_clr_bit(struct irq_data *d)
+static void rockchip_irq_enable(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct rockchip_pin_bank *bank = gc->private;
@@ -2070,7 +2239,7 @@ static void rockchip_irq_gc_mask_clr_bit(struct irq_data *d)
 	irq_gc_mask_clr_bit(d);
 }
 
-static void rockchip_irq_gc_mask_set_bit(struct irq_data *d)
+static void rockchip_irq_disable(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct rockchip_pin_bank *bank = gc->private;
@@ -2079,6 +2248,34 @@ static void rockchip_irq_gc_mask_set_bit(struct irq_data *d)
 	clk_disable(bank->clk);
 }
 
+static void rockchip_irq_bus_lock(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct rockchip_pin_bank *bank = gc->private;
+
+	clk_enable(bank->clk);
+	mutex_lock(&bank->irq_lock);
+}
+
+static void rockchip_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct rockchip_pin_bank *bank = gc->private;
+
+	while (bank->new_irqs) {
+		unsigned int irq = __ffs(bank->new_irqs);
+		int ret;
+
+		ret = rockchip_set_mux(bank, irq, RK_FUNC_GPIO);
+		WARN_ON(ret < 0);
+
+		bank->new_irqs &= ~BIT(irq);
+	}
+
+	mutex_unlock(&bank->irq_lock);
+	clk_disable(bank->clk);
+}
+
 static int rockchip_interrupts_register(struct platform_device *pdev,
 						struct rockchip_pinctrl *info)
 {
@@ -2137,13 +2334,17 @@ static int rockchip_interrupts_register(struct platform_device *pdev,
 		gc->chip_types[0].regs.mask = GPIO_INTMASK;
 		gc->chip_types[0].regs.ack = GPIO_PORTS_EOI;
 		gc->chip_types[0].chip.irq_ack = irq_gc_ack_set_bit;
-		gc->chip_types[0].chip.irq_mask = rockchip_irq_gc_mask_set_bit;
-		gc->chip_types[0].chip.irq_unmask =
-						  rockchip_irq_gc_mask_clr_bit;
+		gc->chip_types[0].chip.irq_mask = irq_gc_mask_set_bit;
+		gc->chip_types[0].chip.irq_unmask = irq_gc_mask_clr_bit;
+		gc->chip_types[0].chip.irq_enable = rockchip_irq_enable;
+		gc->chip_types[0].chip.irq_disable = rockchip_irq_disable;
 		gc->chip_types[0].chip.irq_set_wake = irq_gc_set_wake;
 		gc->chip_types[0].chip.irq_suspend = rockchip_irq_suspend;
 		gc->chip_types[0].chip.irq_resume = rockchip_irq_resume;
 		gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type;
+		gc->chip_types[0].chip.irq_bus_lock = rockchip_irq_bus_lock;
+		gc->chip_types[0].chip.irq_bus_sync_unlock =
+						rockchip_irq_bus_sync_unlock;
 		gc->wake_enabled = IRQ_MSK(bank->nr_pins);
 
 		irq_set_chained_handler_and_data(bank->irq,
@@ -2316,7 +2517,8 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data(
 	for (i = 0; i < ctrl->nr_banks; ++i, ++bank) {
 		int bank_pins = 0;
 
-		spin_lock_init(&bank->slock);
+		raw_spin_lock_init(&bank->slock);
+		mutex_init(&bank->irq_lock);
 		bank->drvdata = d;
 		bank->pin_base = ctrl->nr_pins;
 		ctrl->nr_pins += bank->nr_pins;
@@ -2359,7 +2561,8 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data(
 			 * Increase offset according to iomux width.
 			 * 4bit iomux'es are spread over two registers.
 			 */
-			inc = (iom->type & IOMUX_WIDTH_4BIT) ? 8 : 4;
+			inc = (iom->type & (IOMUX_WIDTH_4BIT |
+					    IOMUX_WIDTH_3BIT)) ? 8 : 4;
 			if (iom->type & IOMUX_SOURCE_PMU)
 				pmu_offs += inc;
 			else
@@ -2518,7 +2721,7 @@ static int rockchip_pinctrl_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static struct rockchip_pin_bank rk1108_pin_banks[] = {
+static struct rockchip_pin_bank rv1108_pin_banks[] = {
 	PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU,
 					     IOMUX_SOURCE_PMU,
 					     IOMUX_SOURCE_PMU,
@@ -2528,15 +2731,15 @@ static struct rockchip_pin_bank rk1108_pin_banks[] = {
 	PIN_BANK_IOMUX_FLAGS(3, 32, "gpio3", 0, 0, 0, 0),
 };
 
-static struct rockchip_pin_ctrl rk1108_pin_ctrl = {
-	.pin_banks		= rk1108_pin_banks,
-	.nr_banks		= ARRAY_SIZE(rk1108_pin_banks),
-	.label			= "RK1108-GPIO",
-	.type			= RK1108,
+static struct rockchip_pin_ctrl rv1108_pin_ctrl = {
+	.pin_banks		= rv1108_pin_banks,
+	.nr_banks		= ARRAY_SIZE(rv1108_pin_banks),
+	.label			= "RV1108-GPIO",
+	.type			= RV1108,
 	.grf_mux_offset		= 0x10,
 	.pmu_mux_offset		= 0x0,
-	.pull_calc_reg		= rk1108_calc_pull_reg_and_bit,
-	.drv_calc_reg		= rk1108_calc_drv_reg_and_bit,
+	.pull_calc_reg		= rv1108_calc_pull_reg_and_bit,
+	.drv_calc_reg		= rv1108_calc_drv_reg_and_bit,
 };
 
 static struct rockchip_pin_bank rk2928_pin_banks[] = {
@@ -2679,6 +2882,32 @@ static struct rockchip_pin_ctrl rk3288_pin_ctrl = {
 		.drv_calc_reg		= rk3288_calc_drv_reg_and_bit,
 };
 
+static struct rockchip_pin_bank rk3328_pin_banks[] = {
+	PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", 0, 0, 0, 0),
+	PIN_BANK_IOMUX_FLAGS(1, 32, "gpio1", 0, 0, 0, 0),
+	PIN_BANK_IOMUX_FLAGS(2, 32, "gpio2", 0,
+			     IOMUX_WIDTH_3BIT | IOMUX_RECALCED,
+			     IOMUX_WIDTH_3BIT | IOMUX_RECALCED,
+			     0),
+	PIN_BANK_IOMUX_FLAGS(3, 32, "gpio3",
+			     IOMUX_WIDTH_3BIT,
+			     IOMUX_WIDTH_3BIT | IOMUX_RECALCED,
+			     0,
+			     0),
+};
+
+static struct rockchip_pin_ctrl rk3328_pin_ctrl = {
+		.pin_banks		= rk3328_pin_banks,
+		.nr_banks		= ARRAY_SIZE(rk3328_pin_banks),
+		.label			= "RK3328-GPIO",
+		.type			= RK3288,
+		.grf_mux_offset		= 0x0,
+		.pull_calc_reg		= rk3228_calc_pull_reg_and_bit,
+		.drv_calc_reg		= rk3228_calc_drv_reg_and_bit,
+		.iomux_recalc		= rk3328_recalc_mux,
+		.schmitt_calc_reg	= rk3328_calc_schmitt_reg_and_bit,
+};
+
 static struct rockchip_pin_bank rk3368_pin_banks[] = {
 	PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU,
 					     IOMUX_SOURCE_PMU,
@@ -2768,8 +2997,8 @@ static struct rockchip_pin_ctrl rk3399_pin_ctrl = {
 };
 
 static const struct of_device_id rockchip_pinctrl_dt_match[] = {
-	{ .compatible = "rockchip,rk1108-pinctrl",
-		.data = (void *)&rk1108_pin_ctrl },
+	{ .compatible = "rockchip,rv1108-pinctrl",
+		.data = (void *)&rv1108_pin_ctrl },
 	{ .compatible = "rockchip,rk2928-pinctrl",
 		.data = (void *)&rk2928_pin_ctrl },
 	{ .compatible = "rockchip,rk3036-pinctrl",
@@ -2784,6 +3013,8 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = {
 		.data = (void *)&rk3228_pin_ctrl },
 	{ .compatible = "rockchip,rk3288-pinctrl",
 		.data = (void *)&rk3288_pin_ctrl },
+	{ .compatible = "rockchip,rk3328-pinctrl",
+		.data = (void *)&rk3328_pin_ctrl },
 	{ .compatible = "rockchip,rk3368-pinctrl",
 		.data = (void *)&rk3368_pin_ctrl },
 	{ .compatible = "rockchip,rk3399-pinctrl",
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 8b2d45e85bae..9c267dcda094 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1781,7 +1781,7 @@ static int pcs_probe(struct platform_device *pdev)
 	dev_info(pcs->dev, "%i pins at pa %p size %u\n",
 		 pcs->desc.npins, pcs->base, pcs->size);
 
-	return 0;
+	return pinctrl_enable(pcs->pctl);
 
 free:
 	pcs_free_resources(pcs);
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 676efcc032d2..3ae8066bc127 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1285,6 +1285,22 @@ static void st_gpio_irq_unmask(struct irq_data *d)
 	writel(BIT(d->hwirq), bank->base + REG_PIO_SET_PMASK);
 }
 
+static int st_gpio_irq_request_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+
+	st_gpio_direction_input(gc, d->hwirq);
+
+	return gpiochip_lock_as_irq(gc, d->hwirq);
+}
+
+static void st_gpio_irq_release_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+
+	gpiochip_unlock_as_irq(gc, d->hwirq);
+}
+
 static int st_gpio_irq_set_type(struct irq_data *d, unsigned type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1438,12 +1454,14 @@ static struct gpio_chip st_gpio_template = {
 };
 
 static struct irq_chip st_gpio_irqchip = {
-	.name		= "GPIO",
-	.irq_disable	= st_gpio_irq_mask,
-	.irq_mask	= st_gpio_irq_mask,
-	.irq_unmask	= st_gpio_irq_unmask,
-	.irq_set_type	= st_gpio_irq_set_type,
-	.flags		= IRQCHIP_SKIP_SET_WAKE,
+	.name			= "GPIO",
+	.irq_request_resources	= st_gpio_irq_request_resources,
+	.irq_release_resources	= st_gpio_irq_release_resources,
+	.irq_disable		= st_gpio_irq_mask,
+	.irq_mask		= st_gpio_irq_mask,
+	.irq_unmask		= st_gpio_irq_unmask,
+	.irq_set_type		= st_gpio_irq_set_type,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static int st_gpiolib_register_bank(struct st_pinctrl *info,
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 29ad3151abec..9fd6d9087dc5 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -763,7 +763,7 @@ struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinmux_generic_get_function);
 
 /**
- * pinmux_generic_get_function_groups() - gets the function groups
+ * pinmux_generic_add_function() - adds a function group
  * @pctldev: pin controller device
  * @name: name of the function
  * @groups: array of pin groups
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
index b68ae424cee2..743d1f458205 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq4019.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
@@ -405,6 +405,36 @@ static const struct msm_pingroup ipq4019_groups[] = {
 	PINGROUP(67, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
 	PINGROUP(68, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
 	PINGROUP(69, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(70, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(71, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(72, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(73, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(74, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(75, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(76, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(77, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(78, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(79, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(80, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(81, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(82, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(83, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(84, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(85, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(86, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(87, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(88, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(89, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(90, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(91, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(92, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(93, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(94, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(95, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(96, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(97, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(98, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(99, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
 };
 
 static const struct msm_pinctrl_soc_data ipq4019_pinctrl = {
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index f8e9e1c2b2f6..273badd92561 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -422,6 +422,20 @@ static int msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, in
 	return 0;
 }
 
+static int msm_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+	struct msm_pinctrl *pctrl = gpiochip_get_data(chip);
+	const struct msm_pingroup *g;
+	u32 val;
+
+	g = &pctrl->soc->groups[offset];
+
+	val = readl(pctrl->regs + g->ctl_reg);
+
+	/* 0 = output, 1 = input */
+	return val & BIT(g->oe_bit) ? 0 : 1;
+}
+
 static int msm_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	const struct msm_pingroup *g;
@@ -510,6 +524,7 @@ static void msm_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 static struct gpio_chip msm_gpio_template = {
 	.direction_input  = msm_gpio_direction_input,
 	.direction_output = msm_gpio_direction_output,
+	.get_direction    = msm_gpio_get_direction,
 	.get              = msm_gpio_get,
 	.set              = msm_gpio_set,
 	.request          = gpiochip_generic_request,
@@ -594,10 +609,6 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
 
 	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
-	val = readl(pctrl->regs + g->intr_status_reg);
-	val &= ~BIT(g->intr_status_bit);
-	writel(val, pctrl->regs + g->intr_status_reg);
-
 	val = readl(pctrl->regs + g->intr_cfg_reg);
 	val |= BIT(g->intr_enable_bit);
 	writel(val, pctrl->regs + g->intr_cfg_reg);
diff --git a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
index f448534edf46..bb3ce5c3e18b 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
@@ -35,10 +35,14 @@ static struct msm_pinctrl_soc_data qdf2xxx_pinctrl;
 /* A reasonable limit to the number of GPIOS */
 #define MAX_GPIOS	256
 
+/* maximum size of each gpio name (enough room for "gpioXXX" + null) */
+#define NAME_SIZE	8
+
 static int qdf2xxx_pinctrl_probe(struct platform_device *pdev)
 {
 	struct pinctrl_pin_desc *pins;
 	struct msm_pingroup *groups;
+	char (*names)[NAME_SIZE];
 	unsigned int i;
 	u32 num_gpios;
 	int ret;
@@ -59,15 +63,21 @@ static int qdf2xxx_pinctrl_probe(struct platform_device *pdev)
 		sizeof(struct pinctrl_pin_desc), GFP_KERNEL);
 	groups = devm_kcalloc(&pdev->dev, num_gpios,
 		sizeof(struct msm_pingroup), GFP_KERNEL);
+	names = devm_kcalloc(&pdev->dev, num_gpios, NAME_SIZE, GFP_KERNEL);
 
-	if (!pins || !groups)
+	if (!pins || !groups || !names)
 		return -ENOMEM;
 
 	for (i = 0; i < num_gpios; i++) {
+		snprintf(names[i], NAME_SIZE, "gpio%u", i);
+
 		pins[i].number = i;
+		pins[i].name = names[i];
 
-		groups[i].npins = 1,
+		groups[i].npins = 1;
+		groups[i].name = names[i];
 		groups[i].pins = &pins[i].number;
+
 		groups[i].ctl_reg = 0x10000 * i;
 		groups[i].io_reg = 0x04 + 0x10000 * i;
 		groups[i].intr_cfg_reg = 0x08 + 0x10000 * i;
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index f9b49967f512..7b0e6cc35e04 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -777,6 +777,7 @@ exynos_retention_init(struct samsung_pinctrl_drv_data *drvdata,
 {
 	struct samsung_retention_ctrl *ctrl;
 	struct regmap *pmu_regs;
+	int i;
 
 	ctrl = devm_kzalloc(drvdata->dev, sizeof(*ctrl), GFP_KERNEL);
 	if (!ctrl)
@@ -794,6 +795,10 @@ exynos_retention_init(struct samsung_pinctrl_drv_data *drvdata,
 	ctrl->enable = exynos_retention_enable;
 	ctrl->disable = exynos_retention_disable;
 
+	/* Ensure that retention is disabled on driver init */
+	for (i = 0; i < ctrl->nr_regs; i++)
+		regmap_write(pmu_regs, ctrl->regs[i], ctrl->value);
+
 	return ctrl;
 }
 
@@ -1468,82 +1473,130 @@ const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = {
 
 /* pin banks of exynos5433 pin-controller - ALIVE */
 static const struct samsung_pin_bank_data exynos5433_pin_banks0[] __initconst = {
-	EXYNOS_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
-	EXYNOS_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
-	EXYNOS_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
-	EXYNOS_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
-	EXYNOS_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
-	EXYNOS_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
+	EXYNOS5433_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
+	EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
 };
 
 /* pin banks of exynos5433 pin-controller - AUD */
 static const struct samsung_pin_bank_data exynos5433_pin_banks1[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
-	EXYNOS_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
+	EXYNOS5433_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
 };
 
 /* pin banks of exynos5433 pin-controller - CPIF */
 static const struct samsung_pin_bank_data exynos5433_pin_banks2[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - eSE */
 static const struct samsung_pin_bank_data exynos5433_pin_banks3[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - FINGER */
 static const struct samsung_pin_bank_data exynos5433_pin_banks4[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - FSYS */
 static const struct samsung_pin_bank_data exynos5433_pin_banks5[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
-	EXYNOS_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
-	EXYNOS_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
-	EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
-	EXYNOS_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
-	EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
 };
 
 /* pin banks of exynos5433 pin-controller - IMEM */
 static const struct samsung_pin_bank_data exynos5433_pin_banks6[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - NFC */
 static const struct samsung_pin_bank_data exynos5433_pin_banks7[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
 };
 
 /* pin banks of exynos5433 pin-controller - PERIC */
 static const struct samsung_pin_bank_data exynos5433_pin_banks8[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
-	EXYNOS_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
-	EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
-	EXYNOS_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
-	EXYNOS_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
-	EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
-	EXYNOS_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
-	EXYNOS_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
-	EXYNOS_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
-	EXYNOS_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
-	EXYNOS_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
-	EXYNOS_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
-	EXYNOS_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
-	EXYNOS_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
-	EXYNOS_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
-	EXYNOS_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
-	EXYNOS_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
+	EXYNOS5433_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
+	EXYNOS5433_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
+	EXYNOS5433_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
+	EXYNOS5433_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
+	EXYNOS5433_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
+	EXYNOS5433_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
 };
 
 /* pin banks of exynos5433 pin-controller - TOUCH */
 static const struct samsung_pin_bank_data exynos5433_pin_banks9[] __initconst = {
-	EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
+	EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
+};
+
+/* PMU pin retention groups registers for Exynos5433 (without audio & fsys) */
+static const u32 exynos5433_retention_regs[] = {
+	EXYNOS5433_PAD_RETENTION_TOP_OPTION,
+	EXYNOS5433_PAD_RETENTION_UART_OPTION,
+	EXYNOS5433_PAD_RETENTION_EBIA_OPTION,
+	EXYNOS5433_PAD_RETENTION_EBIB_OPTION,
+	EXYNOS5433_PAD_RETENTION_SPI_OPTION,
+	EXYNOS5433_PAD_RETENTION_MIF_OPTION,
+	EXYNOS5433_PAD_RETENTION_USBXTI_OPTION,
+	EXYNOS5433_PAD_RETENTION_BOOTLDO_OPTION,
+	EXYNOS5433_PAD_RETENTION_UFS_OPTION,
+	EXYNOS5433_PAD_RETENTION_FSYSGENIO_OPTION,
+};
+
+static const struct samsung_retention_data exynos5433_retention_data __initconst = {
+	.regs	 = exynos5433_retention_regs,
+	.nr_regs = ARRAY_SIZE(exynos5433_retention_regs),
+	.value	 = EXYNOS_WAKEUP_FROM_LOWPWR,
+	.refcnt	 = &exynos_shared_retention_refcnt,
+	.init	 = exynos_retention_init,
+};
+
+/* PMU retention control for audio pins can be tied to audio pin bank */
+static const u32 exynos5433_audio_retention_regs[] = {
+	EXYNOS5433_PAD_RETENTION_AUD_OPTION,
+};
+
+static const struct samsung_retention_data exynos5433_audio_retention_data __initconst = {
+	.regs	 = exynos5433_audio_retention_regs,
+	.nr_regs = ARRAY_SIZE(exynos5433_audio_retention_regs),
+	.value	 = EXYNOS_WAKEUP_FROM_LOWPWR,
+	.init	 = exynos_retention_init,
+};
+
+/* PMU retention control for mmc pins can be tied to fsys pin bank */
+static const u32 exynos5433_fsys_retention_regs[] = {
+	EXYNOS5433_PAD_RETENTION_MMC0_OPTION,
+	EXYNOS5433_PAD_RETENTION_MMC1_OPTION,
+	EXYNOS5433_PAD_RETENTION_MMC2_OPTION,
+};
+
+static const struct samsung_retention_data exynos5433_fsys_retention_data __initconst = {
+	.regs	 = exynos5433_fsys_retention_regs,
+	.nr_regs = ARRAY_SIZE(exynos5433_fsys_retention_regs),
+	.value	 = EXYNOS_WAKEUP_FROM_LOWPWR,
+	.init	 = exynos_retention_init,
 };
 
 /*
@@ -1559,6 +1612,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
 		.nr_ext_resources = 1,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5433_pin_banks1,
@@ -1566,6 +1620,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_audio_retention_data,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5433_pin_banks2,
@@ -1573,6 +1628,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 3 data */
 		.pin_banks	= exynos5433_pin_banks3,
@@ -1580,6 +1636,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 4 data */
 		.pin_banks	= exynos5433_pin_banks4,
@@ -1587,6 +1644,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 5 data */
 		.pin_banks	= exynos5433_pin_banks5,
@@ -1594,6 +1652,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_fsys_retention_data,
 	}, {
 		/* pin-controller instance 6 data */
 		.pin_banks	= exynos5433_pin_banks6,
@@ -1601,6 +1660,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 7 data */
 		.pin_banks	= exynos5433_pin_banks7,
@@ -1608,6 +1668,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 8 data */
 		.pin_banks	= exynos5433_pin_banks8,
@@ -1615,6 +1676,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	}, {
 		/* pin-controller instance 9 data */
 		.pin_banks	= exynos5433_pin_banks9,
@@ -1622,6 +1684,7 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = {
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.suspend	= exynos_pinctrl_suspend,
 		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynos5433_retention_data,
 	},
 };
 
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h
index a473092fb8d2..cd046eb7d705 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.h
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.h
@@ -79,17 +79,6 @@
 		.name		= id			\
 	}
 
-#define EXYNOS_PIN_BANK_EINTW_EXT(pins, reg, id, offs, pctl_idx) \
-	{						\
-		.type           = &bank_type_alive,	\
-		.pctl_offset    = reg,                  \
-		.nr_pins        = pins,                 \
-		.eint_type      = EINT_TYPE_WKUP,       \
-		.eint_offset    = offs,                 \
-		.name           = id,                   \
-		.pctl_res_idx   = pctl_idx,             \
-	}						\
-
 #define EXYNOS5433_PIN_BANK_EINTG(pins, reg, id, offs)		\
 	{							\
 		.type		= &exynos5433_bank_type_off,	\
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index f9ddba7decc1..a4a0da5d2a32 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -566,13 +566,11 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc,
 {
 	const struct samsung_pin_bank_type *type;
 	struct samsung_pin_bank *bank;
-	struct samsung_pinctrl_drv_data *drvdata;
 	void __iomem *reg;
 	u32 data, mask, shift;
 
 	bank = gpiochip_get_data(gc);
 	type = bank->type;
-	drvdata = bank->drvdata;
 
 	reg = bank->pctl_base + bank->pctl_offset
 			+ type->reg_offset[PINCFG_TYPE_FUNC];
@@ -884,7 +882,7 @@ static int samsung_pinctrl_register(struct platform_device *pdev,
 		pin_bank->grange.id = bank;
 		pin_bank->grange.pin_base = drvdata->pin_base
 						+ pin_bank->pin_base;
-		pin_bank->grange.base = pin_bank->gpio_chip.base;
+		pin_bank->grange.base = pin_bank->grange.pin_base;
 		pin_bank->grange.npins = pin_bank->gpio_chip.ngpio;
 		pin_bank->grange.gc = &pin_bank->gpio_chip;
 		pinctrl_add_gpio_range(drvdata->pctl_dev, &pin_bank->grange);
@@ -893,6 +891,19 @@ static int samsung_pinctrl_register(struct platform_device *pdev,
 	return 0;
 }
 
+/* unregister the pinctrl interface with the pinctrl subsystem */
+static int samsung_pinctrl_unregister(struct platform_device *pdev,
+				      struct samsung_pinctrl_drv_data *drvdata)
+{
+	struct samsung_pin_bank *bank = drvdata->pin_banks;
+	int i;
+
+	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
+		pinctrl_remove_gpio_range(drvdata->pctl_dev, &bank->grange);
+
+	return 0;
+}
+
 static const struct gpio_chip samsung_gpiolib_chip = {
 	.request = gpiochip_generic_request,
 	.free = gpiochip_generic_free,
@@ -917,39 +928,21 @@ static int samsung_gpiolib_register(struct platform_device *pdev,
 		bank->gpio_chip = samsung_gpiolib_chip;
 
 		gc = &bank->gpio_chip;
-		gc->base = drvdata->pin_base + bank->pin_base;
+		gc->base = bank->grange.base;
 		gc->ngpio = bank->nr_pins;
 		gc->parent = &pdev->dev;
 		gc->of_node = bank->of_node;
 		gc->label = bank->name;
 
-		ret = gpiochip_add_data(gc, bank);
+		ret = devm_gpiochip_add_data(&pdev->dev, gc, bank);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to register gpio_chip %s, error code: %d\n",
 							gc->label, ret);
-			goto fail;
+			return ret;
 		}
 	}
 
 	return 0;
-
-fail:
-	for (--i, --bank; i >= 0; --i, --bank)
-		gpiochip_remove(&bank->gpio_chip);
-	return ret;
-}
-
-/* unregister the gpiolib interface with the gpiolib subsystem */
-static int samsung_gpiolib_unregister(struct platform_device *pdev,
-				      struct samsung_pinctrl_drv_data *drvdata)
-{
-	struct samsung_pin_bank *bank = drvdata->pin_banks;
-	int i;
-
-	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
-		gpiochip_remove(&bank->gpio_chip);
-
-	return 0;
 }
 
 /* retrieve the soc specific data */
@@ -988,9 +981,16 @@ samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d,
 
 	for (i = 0; i < ctrl->nr_ext_resources + 1; i++) {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
-		virt_base[i] = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(virt_base[i]))
-			return ERR_CAST(virt_base[i]);
+		if (!res) {
+			dev_err(&pdev->dev, "failed to get mem%d resource\n", i);
+			return ERR_PTR(-EINVAL);
+		}
+		virt_base[i] = devm_ioremap(&pdev->dev, res->start,
+						resource_size(res));
+		if (!virt_base[i]) {
+			dev_err(&pdev->dev, "failed to ioremap %pR\n", res);
+			return ERR_PTR(-EIO);
+		}
 	}
 
 	bank = d->pin_banks;
@@ -1062,13 +1062,13 @@ static int samsung_pinctrl_probe(struct platform_device *pdev)
 			return PTR_ERR(drvdata->retention_ctrl);
 	}
 
-	ret = samsung_gpiolib_register(pdev, drvdata);
+	ret = samsung_pinctrl_register(pdev, drvdata);
 	if (ret)
 		return ret;
 
-	ret = samsung_pinctrl_register(pdev, drvdata);
+	ret = samsung_gpiolib_register(pdev, drvdata);
 	if (ret) {
-		samsung_gpiolib_unregister(pdev, drvdata);
+		samsung_pinctrl_unregister(pdev, drvdata);
 		return ret;
 	}
 
diff --git a/drivers/pinctrl/sh-pfc/Makefile b/drivers/pinctrl/sh-pfc/Makefile
index 2dda8c63f3cf..8e08684774af 100644
--- a/drivers/pinctrl/sh-pfc/Makefile
+++ b/drivers/pinctrl/sh-pfc/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_PINCTRL_PFC_R8A7792)	+= pfc-r8a7792.o
 obj-$(CONFIG_PINCTRL_PFC_R8A7793)	+= pfc-r8a7791.o
 obj-$(CONFIG_PINCTRL_PFC_R8A7794)	+= pfc-r8a7794.o
 obj-$(CONFIG_PINCTRL_PFC_R8A7795)	+= pfc-r8a7795.o
+obj-$(CONFIG_PINCTRL_PFC_R8A7795)	+= pfc-r8a7795-es1.o
 obj-$(CONFIG_PINCTRL_PFC_R8A7796)	+= pfc-r8a7796.o
 obj-$(CONFIG_PINCTRL_PFC_SH7203)	+= pfc-sh7203.o
 obj-$(CONFIG_PINCTRL_PFC_SH7264)	+= pfc-sh7264.o
diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c
index cf80ce1dd7ce..4a5a0feb931b 100644
--- a/drivers/pinctrl/sh-pfc/core.c
+++ b/drivers/pinctrl/sh-pfc/core.c
@@ -586,6 +586,9 @@ static int sh_pfc_probe(struct platform_device *pdev)
 		ret = info->ops->init(pfc);
 		if (ret < 0)
 			return ret;
+
+		/* .init() may have overridden pfc->info */
+		info = pfc->info;
 	}
 
 	/* Enable dummy states for those platforms without pinctrl support */
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 841cecdca7ea..2ed7eeb50aac 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -203,7 +203,7 @@ enum {
 
 	/* IPSR6 */
 	FN_AUDIO_CLKB, FN_STP_OPWM_0_B, FN_MSIOF1_SCK_B,
-	FN_SCIF_CLK, FN_BPFCLK_E,
+	FN_SCIF_CLK, FN_DVC_MUTE, FN_BPFCLK_E,
 	FN_AUDIO_CLKC, FN_SCIFB0_SCK_C, FN_MSIOF1_SYNC_B, FN_RX2,
 	FN_SCIFA2_RXD, FN_FMIN_E,
 	FN_AUDIO_CLKOUT, FN_MSIOF1_SS1_B, FN_TX2, FN_SCIFA2_TXD,
@@ -573,7 +573,7 @@ enum {
 
 	/* IPSR6 */
 	AUDIO_CLKB_MARK, STP_OPWM_0_B_MARK, MSIOF1_SCK_B_MARK,
-	SCIF_CLK_MARK, BPFCLK_E_MARK,
+	SCIF_CLK_MARK, DVC_MUTE_MARK, BPFCLK_E_MARK,
 	AUDIO_CLKC_MARK, SCIFB0_SCK_C_MARK, MSIOF1_SYNC_B_MARK, RX2_MARK,
 	SCIFA2_RXD_MARK, FMIN_E_MARK,
 	AUDIO_CLKOUT_MARK, MSIOF1_SS1_B_MARK, TX2_MARK, SCIFA2_TXD_MARK,
@@ -1010,14 +1010,17 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP4_12_10, SCL2, SEL_IIC2_0),
 	PINMUX_IPSR_MSEL(IP4_12_10, GPS_CLK_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP4_12_10, GLO_Q0_D, SEL_GPS_3),
+	PINMUX_IPSR_MSEL(IP4_12_10, HSCK1_E, SEL_HSCIF1_4),
 	PINMUX_IPSR_GPSR(IP4_15_13, SSI_WS2),
 	PINMUX_IPSR_MSEL(IP4_15_13, SDA2, SEL_IIC2_0),
 	PINMUX_IPSR_MSEL(IP4_15_13, GPS_SIGN_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP4_15_13, RX2_E, SEL_SCIF2_4),
 	PINMUX_IPSR_MSEL(IP4_15_13, GLO_Q1_D, SEL_GPS_3),
+	PINMUX_IPSR_MSEL(IP4_15_13, HCTS1_N_E, SEL_HSCIF1_4),
 	PINMUX_IPSR_GPSR(IP4_18_16, SSI_SDATA2),
 	PINMUX_IPSR_MSEL(IP4_18_16, GPS_MAG_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP4_18_16, TX2_E, SEL_SCIF2_4),
+	PINMUX_IPSR_MSEL(IP4_18_16, HRTS1_N_E, SEL_HSCIF1_4),
 	PINMUX_IPSR_GPSR(IP4_19, SSI_SCK34),
 	PINMUX_IPSR_GPSR(IP4_20, SSI_WS34),
 	PINMUX_IPSR_GPSR(IP4_21, SSI_SDATA3),
@@ -1090,6 +1093,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP6_2_0, STP_OPWM_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_2_0, MSIOF1_SCK_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_2_0, SCIF_CLK, SEL_SCIF_0),
+	PINMUX_IPSR_GPSR(IP6_2_0, DVC_MUTE),
 	PINMUX_IPSR_MSEL(IP6_2_0, BPFCLK_E, SEL_FM_4),
 	PINMUX_IPSR_GPSR(IP6_5_3, AUDIO_CLKC),
 	PINMUX_IPSR_MSEL(IP6_5_3, SCIFB0_SCK_C, SEL_SCIFB_2),
@@ -1099,7 +1103,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP6_5_3, FMIN_E, SEL_FM_4),
 	PINMUX_IPSR_GPSR(IP6_7_6, AUDIO_CLKOUT),
 	PINMUX_IPSR_MSEL(IP6_7_6, MSIOF1_SS1_B, SEL_SOF1_1),
-	PINMUX_IPSR_MSEL(IP6_5_3, TX2, SEL_SCIF2_0),
+	PINMUX_IPSR_MSEL(IP6_7_6, TX2, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP6_7_6, SCIFA2_TXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_GPSR(IP6_9_8, IRQ0),
 	PINMUX_IPSR_MSEL(IP6_9_8, SCIFB1_RXD_D, SEL_SCIFB1_3),
@@ -5707,7 +5711,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 	},
 	{ PINMUX_CFG_REG_VAR("IPSR2", 0xE6060028, 32,
 			     2, 3, 2, 2, 2, 2, 3, 3, 3, 3, 2, 2, 3) {
-		/* IP2_31_20 [2] */
+		/* IP2_31_30 [2] */
 		0, 0, 0, 0,
 		/* IP2_29_27 [3] */
 		FN_EX_CS3_N, FN_ATADIR0_N, FN_MSIOF2_TXD,
@@ -5727,7 +5731,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		/* IP2_15_13 [3] */
 		FN_A24, FN_DREQ2, FN_IO3, FN_TX1, FN_SCIFA1_TXD,
 		0, 0, 0,
-		/* IP2_12_0 [3] */
+		/* IP2_12_10 [3] */
 		FN_A23, FN_IO2, FN_BPFCLK_B, FN_RX0, FN_SCIFA0_RXD,
 		0, 0, 0,
 		/* IP2_9_7 [3] */
@@ -5896,7 +5900,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		0, 0,
 		/* IP6_2_0 [3] */
 		FN_AUDIO_CLKB, FN_STP_OPWM_0_B, FN_MSIOF1_SCK_B,
-		FN_SCIF_CLK, 0, FN_BPFCLK_E,
+		FN_SCIF_CLK, FN_DVC_MUTE, FN_BPFCLK_E,
 		0, 0, }
 	},
 	{ PINMUX_CFG_REG_VAR("IPSR7", 0xE606003C, 32,
@@ -6038,7 +6042,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		/* IP10_24_22 [3] */
 		FN_VI0_R1, FN_VI2_DATA2, FN_GLO_I1_B, FN_TS_SCK0_C, FN_ATAG1_N,
 		0, 0, 0,
-		/* IP10_21_29 [3] */
+		/* IP10_21_19 [3] */
 		FN_VI0_R0, FN_VI2_DATA1, FN_GLO_I0_B,
 		FN_TS_SDATA0_C, FN_ATACS11_N,
 		0, 0, 0,
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7794.c b/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
index ed734f560c84..ef093ac0cf2f 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
@@ -281,8 +281,8 @@ enum {
 	FN_AVB_AVTP_CAPTURE, FN_ETH_CRS_DV_B, FN_SSI_WS1, FN_SCIF1_TXD_B,
 	FN_IIC1_SDA_C, FN_VI1_DATA0, FN_CAN0_TX_D, FN_AVB_AVTP_MATCH,
 	FN_ETH_RX_ER_B, FN_SSI_SDATA1, FN_HSCIF1_HRX_B, FN_SDATA, FN_VI1_DATA1,
-	FN_ATAG0_N, FN_ETH_RXD0_B, FN_SSI_SCK2, FN_HSCIF1_HTX_B, FN_VI1_DATA2,
-	FN_MDATA, FN_ATAWR0_N, FN_ETH_RXD1_B,
+	FN_ATAWR0_N, FN_ETH_RXD0_B, FN_SSI_SCK2, FN_HSCIF1_HTX_B, FN_VI1_DATA2,
+	FN_MDATA, FN_ATAG0_N, FN_ETH_RXD1_B,
 
 	/* IPSR13 */
 	FN_SSI_WS2, FN_HSCIF1_HCTS_N_B, FN_SCIFA0_RXD_D, FN_VI1_DATA3, FN_SCKZ,
@@ -575,8 +575,8 @@ enum {
 	ETH_CRS_DV_B_MARK, SSI_WS1_MARK, SCIF1_TXD_B_MARK, IIC1_SDA_C_MARK,
 	VI1_DATA0_MARK, CAN0_TX_D_MARK, AVB_AVTP_MATCH_MARK, ETH_RX_ER_B_MARK,
 	SSI_SDATA1_MARK, HSCIF1_HRX_B_MARK, VI1_DATA1_MARK, SDATA_MARK,
-	ATAG0_N_MARK, ETH_RXD0_B_MARK, SSI_SCK2_MARK, HSCIF1_HTX_B_MARK,
-	VI1_DATA2_MARK, MDATA_MARK, ATAWR0_N_MARK, ETH_RXD1_B_MARK,
+	ATAWR0_N_MARK, ETH_RXD0_B_MARK, SSI_SCK2_MARK, HSCIF1_HTX_B_MARK,
+	VI1_DATA2_MARK, MDATA_MARK, ATAG0_N_MARK, ETH_RXD1_B_MARK,
 
 	/* IPSR13 */
 	SSI_WS2_MARK, HSCIF1_HCTS_N_B_MARK, SCIFA0_RXD_D_MARK, VI1_DATA3_MARK,
@@ -1413,13 +1413,13 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP12_26_24, HSCIF1_HRX_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_GPSR(IP12_26_24, VI1_DATA1),
 	PINMUX_IPSR_MSEL(IP12_26_24, SDATA, SEL_FSN_0),
-	PINMUX_IPSR_GPSR(IP12_26_24, ATAG0_N),
+	PINMUX_IPSR_GPSR(IP12_26_24, ATAWR0_N),
 	PINMUX_IPSR_MSEL(IP12_26_24, ETH_RXD0_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP12_29_27, SSI_SCK2, SEL_SSI2_0),
 	PINMUX_IPSR_MSEL(IP12_29_27, HSCIF1_HTX_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_GPSR(IP12_29_27, VI1_DATA2),
 	PINMUX_IPSR_MSEL(IP12_29_27, MDATA, SEL_FSN_0),
-	PINMUX_IPSR_GPSR(IP12_29_27, ATAWR0_N),
+	PINMUX_IPSR_GPSR(IP12_29_27, ATAG0_N),
 	PINMUX_IPSR_MSEL(IP12_29_27, ETH_RXD1_B, SEL_ETH_1),
 
 	/* IPSR13 */
@@ -4938,10 +4938,10 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		0, 0, 0, 0,
 		/* IP12_29_27 [3] */
 		FN_SSI_SCK2, FN_HSCIF1_HTX_B, FN_VI1_DATA2, FN_MDATA,
-		FN_ATAWR0_N, FN_ETH_RXD1_B, 0, 0,
+		FN_ATAG0_N, FN_ETH_RXD1_B, 0, 0,
 		/* IP12_26_24 [3] */
 		FN_SSI_SDATA1, FN_HSCIF1_HRX_B, FN_VI1_DATA1, FN_SDATA,
-		FN_ATAG0_N, FN_ETH_RXD0_B, 0, 0,
+		FN_ATAWR0_N, FN_ETH_RXD0_B, 0, 0,
 		/* IP12_23_21 [3] */
 		FN_SSI_WS1, FN_SCIF1_TXD_B, FN_IIC1_SDA_C, FN_VI1_DATA0,
 		FN_CAN0_TX_D, FN_AVB_AVTP_MATCH, FN_ETH_RX_ER_B, 0,
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7795-es1.c b/drivers/pinctrl/sh-pfc/pfc-r8a7795-es1.c
new file mode 100644
index 000000000000..081efda9a280
--- /dev/null
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7795-es1.c
@@ -0,0 +1,5705 @@
+/*
+ * R8A7795 ES1.x processor support - PFC hardware block.
+ *
+ * Copyright (C) 2015  Renesas Electronics Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/kernel.h>
+
+#include "core.h"
+#include "sh_pfc.h"
+
+#define CFG_FLAGS (SH_PFC_PIN_CFG_DRIVE_STRENGTH | \
+		   SH_PFC_PIN_CFG_PULL_UP | \
+		   SH_PFC_PIN_CFG_PULL_DOWN)
+
+#define CPU_ALL_PORT(fn, sfx)						\
+	PORT_GP_CFG_16(0, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_15(2, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE),	\
+	PORT_GP_CFG_1(3, 12, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_1(3, 13, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_1(3, 14, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_1(3, 15, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE),	\
+	PORT_GP_CFG_26(5, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_32(6, fn, sfx, CFG_FLAGS),	\
+	PORT_GP_CFG_4(7, fn, sfx, CFG_FLAGS)
+/*
+ * F_() : just information
+ * FM() : macro for FN_xxx / xxx_MARK
+ */
+
+/* GPSR0 */
+#define GPSR0_15	F_(D15,			IP7_11_8)
+#define GPSR0_14	F_(D14,			IP7_7_4)
+#define GPSR0_13	F_(D13,			IP7_3_0)
+#define GPSR0_12	F_(D12,			IP6_31_28)
+#define GPSR0_11	F_(D11,			IP6_27_24)
+#define GPSR0_10	F_(D10,			IP6_23_20)
+#define GPSR0_9		F_(D9,			IP6_19_16)
+#define GPSR0_8		F_(D8,			IP6_15_12)
+#define GPSR0_7		F_(D7,			IP6_11_8)
+#define GPSR0_6		F_(D6,			IP6_7_4)
+#define GPSR0_5		F_(D5,			IP6_3_0)
+#define GPSR0_4		F_(D4,			IP5_31_28)
+#define GPSR0_3		F_(D3,			IP5_27_24)
+#define GPSR0_2		F_(D2,			IP5_23_20)
+#define GPSR0_1		F_(D1,			IP5_19_16)
+#define GPSR0_0		F_(D0,			IP5_15_12)
+
+/* GPSR1 */
+#define GPSR1_27	F_(EX_WAIT0_A,		IP5_11_8)
+#define GPSR1_26	F_(WE1_N,		IP5_7_4)
+#define GPSR1_25	F_(WE0_N,		IP5_3_0)
+#define GPSR1_24	F_(RD_WR_N,		IP4_31_28)
+#define GPSR1_23	F_(RD_N,		IP4_27_24)
+#define GPSR1_22	F_(BS_N,		IP4_23_20)
+#define GPSR1_21	F_(CS1_N_A26,		IP4_19_16)
+#define GPSR1_20	F_(CS0_N,		IP4_15_12)
+#define GPSR1_19	F_(A19,			IP4_11_8)
+#define GPSR1_18	F_(A18,			IP4_7_4)
+#define GPSR1_17	F_(A17,			IP4_3_0)
+#define GPSR1_16	F_(A16,			IP3_31_28)
+#define GPSR1_15	F_(A15,			IP3_27_24)
+#define GPSR1_14	F_(A14,			IP3_23_20)
+#define GPSR1_13	F_(A13,			IP3_19_16)
+#define GPSR1_12	F_(A12,			IP3_15_12)
+#define GPSR1_11	F_(A11,			IP3_11_8)
+#define GPSR1_10	F_(A10,			IP3_7_4)
+#define GPSR1_9		F_(A9,			IP3_3_0)
+#define GPSR1_8		F_(A8,			IP2_31_28)
+#define GPSR1_7		F_(A7,			IP2_27_24)
+#define GPSR1_6		F_(A6,			IP2_23_20)
+#define GPSR1_5		F_(A5,			IP2_19_16)
+#define GPSR1_4		F_(A4,			IP2_15_12)
+#define GPSR1_3		F_(A3,			IP2_11_8)
+#define GPSR1_2		F_(A2,			IP2_7_4)
+#define GPSR1_1		F_(A1,			IP2_3_0)
+#define GPSR1_0		F_(A0,			IP1_31_28)
+
+/* GPSR2 */
+#define GPSR2_14	F_(AVB_AVTP_CAPTURE_A,	IP0_23_20)
+#define GPSR2_13	F_(AVB_AVTP_MATCH_A,	IP0_19_16)
+#define GPSR2_12	F_(AVB_LINK,		IP0_15_12)
+#define GPSR2_11	F_(AVB_PHY_INT,		IP0_11_8)
+#define GPSR2_10	F_(AVB_MAGIC,		IP0_7_4)
+#define GPSR2_9		F_(AVB_MDC,		IP0_3_0)
+#define GPSR2_8		F_(PWM2_A,		IP1_27_24)
+#define GPSR2_7		F_(PWM1_A,		IP1_23_20)
+#define GPSR2_6		F_(PWM0,		IP1_19_16)
+#define GPSR2_5		F_(IRQ5,		IP1_15_12)
+#define GPSR2_4		F_(IRQ4,		IP1_11_8)
+#define GPSR2_3		F_(IRQ3,		IP1_7_4)
+#define GPSR2_2		F_(IRQ2,		IP1_3_0)
+#define GPSR2_1		F_(IRQ1,		IP0_31_28)
+#define GPSR2_0		F_(IRQ0,		IP0_27_24)
+
+/* GPSR3 */
+#define GPSR3_15	F_(SD1_WP,		IP10_23_20)
+#define GPSR3_14	F_(SD1_CD,		IP10_19_16)
+#define GPSR3_13	F_(SD0_WP,		IP10_15_12)
+#define GPSR3_12	F_(SD0_CD,		IP10_11_8)
+#define GPSR3_11	F_(SD1_DAT3,		IP8_31_28)
+#define GPSR3_10	F_(SD1_DAT2,		IP8_27_24)
+#define GPSR3_9		F_(SD1_DAT1,		IP8_23_20)
+#define GPSR3_8		F_(SD1_DAT0,		IP8_19_16)
+#define GPSR3_7		F_(SD1_CMD,		IP8_15_12)
+#define GPSR3_6		F_(SD1_CLK,		IP8_11_8)
+#define GPSR3_5		F_(SD0_DAT3,		IP8_7_4)
+#define GPSR3_4		F_(SD0_DAT2,		IP8_3_0)
+#define GPSR3_3		F_(SD0_DAT1,		IP7_31_28)
+#define GPSR3_2		F_(SD0_DAT0,		IP7_27_24)
+#define GPSR3_1		F_(SD0_CMD,		IP7_23_20)
+#define GPSR3_0		F_(SD0_CLK,		IP7_19_16)
+
+/* GPSR4 */
+#define GPSR4_17	FM(SD3_DS)
+#define GPSR4_16	F_(SD3_DAT7,		IP10_7_4)
+#define GPSR4_15	F_(SD3_DAT6,		IP10_3_0)
+#define GPSR4_14	F_(SD3_DAT5,		IP9_31_28)
+#define GPSR4_13	F_(SD3_DAT4,		IP9_27_24)
+#define GPSR4_12	FM(SD3_DAT3)
+#define GPSR4_11	FM(SD3_DAT2)
+#define GPSR4_10	FM(SD3_DAT1)
+#define GPSR4_9		FM(SD3_DAT0)
+#define GPSR4_8		FM(SD3_CMD)
+#define GPSR4_7		FM(SD3_CLK)
+#define GPSR4_6		F_(SD2_DS,		IP9_23_20)
+#define GPSR4_5		F_(SD2_DAT3,		IP9_19_16)
+#define GPSR4_4		F_(SD2_DAT2,		IP9_15_12)
+#define GPSR4_3		F_(SD2_DAT1,		IP9_11_8)
+#define GPSR4_2		F_(SD2_DAT0,		IP9_7_4)
+#define GPSR4_1		FM(SD2_CMD)
+#define GPSR4_0		F_(SD2_CLK,		IP9_3_0)
+
+/* GPSR5 */
+#define GPSR5_25	F_(MLB_DAT,		IP13_19_16)
+#define GPSR5_24	F_(MLB_SIG,		IP13_15_12)
+#define GPSR5_23	F_(MLB_CLK,		IP13_11_8)
+#define GPSR5_22	FM(MSIOF0_RXD)
+#define GPSR5_21	F_(MSIOF0_SS2,		IP13_7_4)
+#define GPSR5_20	FM(MSIOF0_TXD)
+#define GPSR5_19	F_(MSIOF0_SS1,		IP13_3_0)
+#define GPSR5_18	F_(MSIOF0_SYNC,		IP12_31_28)
+#define GPSR5_17	FM(MSIOF0_SCK)
+#define GPSR5_16	F_(HRTS0_N,		IP12_27_24)
+#define GPSR5_15	F_(HCTS0_N,		IP12_23_20)
+#define GPSR5_14	F_(HTX0,		IP12_19_16)
+#define GPSR5_13	F_(HRX0,		IP12_15_12)
+#define GPSR5_12	F_(HSCK0,		IP12_11_8)
+#define GPSR5_11	F_(RX2_A,		IP12_7_4)
+#define GPSR5_10	F_(TX2_A,		IP12_3_0)
+#define GPSR5_9		F_(SCK2,		IP11_31_28)
+#define GPSR5_8		F_(RTS1_N_TANS,		IP11_27_24)
+#define GPSR5_7		F_(CTS1_N,		IP11_23_20)
+#define GPSR5_6		F_(TX1_A,		IP11_19_16)
+#define GPSR5_5		F_(RX1_A,		IP11_15_12)
+#define GPSR5_4		F_(RTS0_N_TANS,		IP11_11_8)
+#define GPSR5_3		F_(CTS0_N,		IP11_7_4)
+#define GPSR5_2		F_(TX0,			IP11_3_0)
+#define GPSR5_1		F_(RX0,			IP10_31_28)
+#define GPSR5_0		F_(SCK0,		IP10_27_24)
+
+/* GPSR6 */
+#define GPSR6_31	F_(USB31_OVC,		IP17_7_4)
+#define GPSR6_30	F_(USB31_PWEN,		IP17_3_0)
+#define GPSR6_29	F_(USB30_OVC,		IP16_31_28)
+#define GPSR6_28	F_(USB30_PWEN,		IP16_27_24)
+#define GPSR6_27	F_(USB1_OVC,		IP16_23_20)
+#define GPSR6_26	F_(USB1_PWEN,		IP16_19_16)
+#define GPSR6_25	F_(USB0_OVC,		IP16_15_12)
+#define GPSR6_24	F_(USB0_PWEN,		IP16_11_8)
+#define GPSR6_23	F_(AUDIO_CLKB_B,	IP16_7_4)
+#define GPSR6_22	F_(AUDIO_CLKA_A,	IP16_3_0)
+#define GPSR6_21	F_(SSI_SDATA9_A,	IP15_31_28)
+#define GPSR6_20	F_(SSI_SDATA8,		IP15_27_24)
+#define GPSR6_19	F_(SSI_SDATA7,		IP15_23_20)
+#define GPSR6_18	F_(SSI_WS78,		IP15_19_16)
+#define GPSR6_17	F_(SSI_SCK78,		IP15_15_12)
+#define GPSR6_16	F_(SSI_SDATA6,		IP15_11_8)
+#define GPSR6_15	F_(SSI_WS6,		IP15_7_4)
+#define GPSR6_14	F_(SSI_SCK6,		IP15_3_0)
+#define GPSR6_13	FM(SSI_SDATA5)
+#define GPSR6_12	FM(SSI_WS5)
+#define GPSR6_11	FM(SSI_SCK5)
+#define GPSR6_10	F_(SSI_SDATA4,		IP14_31_28)
+#define GPSR6_9		F_(SSI_WS4,		IP14_27_24)
+#define GPSR6_8		F_(SSI_SCK4,		IP14_23_20)
+#define GPSR6_7		F_(SSI_SDATA3,		IP14_19_16)
+#define GPSR6_6		F_(SSI_WS34,		IP14_15_12)
+#define GPSR6_5		F_(SSI_SCK34,		IP14_11_8)
+#define GPSR6_4		F_(SSI_SDATA2_A,	IP14_7_4)
+#define GPSR6_3		F_(SSI_SDATA1_A,	IP14_3_0)
+#define GPSR6_2		F_(SSI_SDATA0,		IP13_31_28)
+#define GPSR6_1		F_(SSI_WS01239,		IP13_27_24)
+#define GPSR6_0		F_(SSI_SCK01239,	IP13_23_20)
+
+/* GPSR7 */
+#define GPSR7_3		FM(HDMI1_CEC)
+#define GPSR7_2		FM(HDMI0_CEC)
+#define GPSR7_1		FM(AVS2)
+#define GPSR7_0		FM(AVS1)
+
+
+/* IPSRx */		/* 0 */			/* 1 */		/* 2 */			/* 3 */				/* 4 */		/* 5 */		/* 6 */			/* 7 */		/* 8 */			/* 9 */		/* A */		/* B */		/* C - F */
+#define IP0_3_0		FM(AVB_MDC)		F_(0, 0)	FM(MSIOF2_SS2_C)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_7_4		FM(AVB_MAGIC)		F_(0, 0)	FM(MSIOF2_SS1_C)	FM(SCK4_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_11_8	FM(AVB_PHY_INT)		F_(0, 0)	FM(MSIOF2_SYNC_C)	FM(RX4_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_15_12	FM(AVB_LINK)		F_(0, 0)	FM(MSIOF2_SCK_C)	FM(TX4_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_19_16	FM(AVB_AVTP_MATCH_A)	F_(0, 0)	FM(MSIOF2_RXD_C)	FM(CTS4_N_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_23_20	FM(AVB_AVTP_CAPTURE_A)	F_(0, 0)	FM(MSIOF2_TXD_C)	FM(RTS4_N_TANS_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_27_24	FM(IRQ0)		FM(QPOLB)	F_(0, 0)		FM(DU_CDE)			FM(VI4_DATA0_B)	FM(CAN0_TX_B)	FM(CANFD0_TX_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_31_28	FM(IRQ1)		FM(QPOLA)	F_(0, 0)		FM(DU_DISP)			FM(VI4_DATA1_B)	FM(CAN0_RX_B)	FM(CANFD0_RX_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_3_0		FM(IRQ2)		FM(QCPV_QDE)	F_(0, 0)		FM(DU_EXODDF_DU_ODDF_DISP_CDE)	FM(VI4_DATA2_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM3_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_7_4		FM(IRQ3)		FM(QSTVB_QVE)	FM(A25)			FM(DU_DOTCLKOUT1)		FM(VI4_DATA3_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM4_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_11_8	FM(IRQ4)		FM(QSTH_QHS)	FM(A24)			FM(DU_EXHSYNC_DU_HSYNC)		FM(VI4_DATA4_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM5_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_15_12	FM(IRQ5)		FM(QSTB_QHE)	FM(A23)			FM(DU_EXVSYNC_DU_VSYNC)		FM(VI4_DATA5_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM6_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_19_16	FM(PWM0)		FM(AVB_AVTP_PPS)FM(A22)			F_(0, 0)			FM(VI4_DATA6_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(IECLK_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_23_20	FM(PWM1_A)		F_(0, 0)	FM(A21)			FM(HRX3_D)			FM(VI4_DATA7_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(IERX_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_27_24	FM(PWM2_A)		F_(0, 0)	FM(A20)			FM(HTX3_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(IETX_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_31_28	FM(A0)			FM(LCDOUT16)	FM(MSIOF3_SYNC_B)	F_(0, 0)			FM(VI4_DATA8)	F_(0, 0)	FM(DU_DB0)		F_(0, 0)	F_(0, 0)		FM(PWM3_A)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_3_0		FM(A1)			FM(LCDOUT17)	FM(MSIOF3_TXD_B)	F_(0, 0)			FM(VI4_DATA9)	F_(0, 0)	FM(DU_DB1)		F_(0, 0)	F_(0, 0)		FM(PWM4_A)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_7_4		FM(A2)			FM(LCDOUT18)	FM(MSIOF3_SCK_B)	F_(0, 0)			FM(VI4_DATA10)	F_(0, 0)	FM(DU_DB2)		F_(0, 0)	F_(0, 0)		FM(PWM5_A)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_11_8	FM(A3)			FM(LCDOUT19)	FM(MSIOF3_RXD_B)	F_(0, 0)			FM(VI4_DATA11)	F_(0, 0)	FM(DU_DB3)		F_(0, 0)	F_(0, 0)		FM(PWM6_A)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+/* IPSRx */		/* 0 */			/* 1 */		/* 2 */			/* 3 */				/* 4 */		/* 5 */		/* 6 */			/* 7 */		/* 8 */			/* 9 */		/* A */		/* B */		/* C - F */
+#define IP2_15_12	FM(A4)			FM(LCDOUT20)	FM(MSIOF3_SS1_B)	F_(0, 0)			FM(VI4_DATA12)	FM(VI5_DATA12)	FM(DU_DB4)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_19_16	FM(A5)			FM(LCDOUT21)	FM(MSIOF3_SS2_B)	FM(SCK4_B)			FM(VI4_DATA13)	FM(VI5_DATA13)	FM(DU_DB5)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_23_20	FM(A6)			FM(LCDOUT22)	FM(MSIOF2_SS1_A)	FM(RX4_B)			FM(VI4_DATA14)	FM(VI5_DATA14)	FM(DU_DB6)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_27_24	FM(A7)			FM(LCDOUT23)	FM(MSIOF2_SS2_A)	FM(TX4_B)			FM(VI4_DATA15)	FM(VI5_DATA15)	FM(DU_DB7)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP2_31_28	FM(A8)			FM(RX3_B)	FM(MSIOF2_SYNC_A)	FM(HRX4_B)			F_(0, 0)	F_(0, 0)	F_(0, 0)		FM(SDA6_A)	FM(AVB_AVTP_MATCH_B)	FM(PWM1_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_3_0		FM(A9)			F_(0, 0)	FM(MSIOF2_SCK_A)	FM(CTS4_N_B)			F_(0, 0)	FM(VI5_VSYNC_N)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_7_4		FM(A10)			F_(0, 0)	FM(MSIOF2_RXD_A)	FM(RTS4_N_TANS_B)		F_(0, 0)	FM(VI5_HSYNC_N)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_11_8	FM(A11)			FM(TX3_B)	FM(MSIOF2_TXD_A)	FM(HTX4_B)			FM(HSCK4)	FM(VI5_FIELD)	F_(0, 0)		FM(SCL6_A)	FM(AVB_AVTP_CAPTURE_B)	FM(PWM2_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_15_12	FM(A12)			FM(LCDOUT12)	FM(MSIOF3_SCK_C)	F_(0, 0)			FM(HRX4_A)	FM(VI5_DATA8)	FM(DU_DG4)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_19_16	FM(A13)			FM(LCDOUT13)	FM(MSIOF3_SYNC_C)	F_(0, 0)			FM(HTX4_A)	FM(VI5_DATA9)	FM(DU_DG5)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_23_20	FM(A14)			FM(LCDOUT14)	FM(MSIOF3_RXD_C)	F_(0, 0)			FM(HCTS4_N)	FM(VI5_DATA10)	FM(DU_DG6)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_27_24	FM(A15)			FM(LCDOUT15)	FM(MSIOF3_TXD_C)	F_(0, 0)			FM(HRTS4_N)	FM(VI5_DATA11)	FM(DU_DG7)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP3_31_28	FM(A16)			FM(LCDOUT8)	F_(0, 0)		F_(0, 0)			FM(VI4_FIELD)	F_(0, 0)	FM(DU_DG0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_3_0		FM(A17)			FM(LCDOUT9)	F_(0, 0)		F_(0, 0)			FM(VI4_VSYNC_N)	F_(0, 0)	FM(DU_DG1)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_7_4		FM(A18)			FM(LCDOUT10)	F_(0, 0)		F_(0, 0)			FM(VI4_HSYNC_N)	F_(0, 0)	FM(DU_DG2)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_11_8	FM(A19)			FM(LCDOUT11)	F_(0, 0)		F_(0, 0)			FM(VI4_CLKENB)	F_(0, 0)	FM(DU_DG3)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_15_12	FM(CS0_N)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(VI5_CLKENB)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_19_16	FM(CS1_N_A26)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(VI5_CLK)	F_(0, 0)		FM(EX_WAIT0_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_23_20	FM(BS_N)		FM(QSTVA_QVS)	FM(MSIOF3_SCK_D)	FM(SCK3)			FM(HSCK3)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(CAN1_TX)		FM(CANFD1_TX)	FM(IETX_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_27_24	FM(RD_N)		F_(0, 0)	FM(MSIOF3_SYNC_D)	FM(RX3_A)			FM(HRX3_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(CAN0_TX_A)		FM(CANFD0_TX_A)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP4_31_28	FM(RD_WR_N)		F_(0, 0)	FM(MSIOF3_RXD_D)	FM(TX3_A)			FM(HTX3_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(CAN0_RX_A)		FM(CANFD0_RX_A)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_3_0		FM(WE0_N)		F_(0, 0)	FM(MSIOF3_TXD_D)	FM(CTS3_N)			FM(HCTS3_N)	F_(0, 0)	F_(0, 0)		FM(SCL6_B)	FM(CAN_CLK)		F_(0, 0)	FM(IECLK_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_7_4		FM(WE1_N)		F_(0, 0)	FM(MSIOF3_SS1_D)	FM(RTS3_N_TANS)			FM(HRTS3_N)	F_(0, 0)	F_(0, 0)		FM(SDA6_B)	FM(CAN1_RX)		FM(CANFD1_RX)	FM(IERX_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_11_8	FM(EX_WAIT0_A)		FM(QCLK)	F_(0, 0)		F_(0, 0)			FM(VI4_CLK)	F_(0, 0)	FM(DU_DOTCLKOUT0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_15_12	FM(D0)			FM(MSIOF2_SS1_B)FM(MSIOF3_SCK_A)	F_(0, 0)			FM(VI4_DATA16)	FM(VI5_DATA0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_19_16	FM(D1)			FM(MSIOF2_SS2_B)FM(MSIOF3_SYNC_A)	F_(0, 0)			FM(VI4_DATA17)	FM(VI5_DATA1)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_23_20	FM(D2)			F_(0, 0)	FM(MSIOF3_RXD_A)	F_(0, 0)			FM(VI4_DATA18)	FM(VI5_DATA2)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_27_24	FM(D3)			F_(0, 0)	FM(MSIOF3_TXD_A)	F_(0, 0)			FM(VI4_DATA19)	FM(VI5_DATA3)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP5_31_28	FM(D4)			FM(MSIOF2_SCK_B)F_(0, 0)		F_(0, 0)			FM(VI4_DATA20)	FM(VI5_DATA4)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_3_0		FM(D5)			FM(MSIOF2_SYNC_B)F_(0, 0)		F_(0, 0)			FM(VI4_DATA21)	FM(VI5_DATA5)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_7_4		FM(D6)			FM(MSIOF2_RXD_B)F_(0, 0)		F_(0, 0)			FM(VI4_DATA22)	FM(VI5_DATA6)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_11_8	FM(D7)			FM(MSIOF2_TXD_B)F_(0, 0)		F_(0, 0)			FM(VI4_DATA23)	FM(VI5_DATA7)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_15_12	FM(D8)			FM(LCDOUT0)	FM(MSIOF2_SCK_D)	FM(SCK4_C)			FM(VI4_DATA0_A)	F_(0, 0)	FM(DU_DR0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_19_16	FM(D9)			FM(LCDOUT1)	FM(MSIOF2_SYNC_D)	F_(0, 0)			FM(VI4_DATA1_A)	F_(0, 0)	FM(DU_DR1)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_23_20	FM(D10)			FM(LCDOUT2)	FM(MSIOF2_RXD_D)	FM(HRX3_B)			FM(VI4_DATA2_A)	FM(CTS4_N_C)	FM(DU_DR2)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_27_24	FM(D11)			FM(LCDOUT3)	FM(MSIOF2_TXD_D)	FM(HTX3_B)			FM(VI4_DATA3_A)	FM(RTS4_N_TANS_C)FM(DU_DR3)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP6_31_28	FM(D12)			FM(LCDOUT4)	FM(MSIOF2_SS1_D)	FM(RX4_C)			FM(VI4_DATA4_A)	F_(0, 0)	FM(DU_DR4)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_3_0		FM(D13)			FM(LCDOUT5)	FM(MSIOF2_SS2_D)	FM(TX4_C)			FM(VI4_DATA5_A)	F_(0, 0)	FM(DU_DR5)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_7_4		FM(D14)			FM(LCDOUT6)	FM(MSIOF3_SS1_A)	FM(HRX3_C)			FM(VI4_DATA6_A)	F_(0, 0)	FM(DU_DR6)		FM(SCL6_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_11_8	FM(D15)			FM(LCDOUT7)	FM(MSIOF3_SS2_A)	FM(HTX3_C)			FM(VI4_DATA7_A)	F_(0, 0)	FM(DU_DR7)		FM(SDA6_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_15_12	FM(FSCLKST)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_19_16	FM(SD0_CLK)		F_(0, 0)	FM(MSIOF1_SCK_E)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_OPWM_0_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+/* IPSRx */		/* 0 */			/* 1 */		/* 2 */			/* 3 */				/* 4 */		/* 5 */		/* 6 */			/* 7 */		/* 8 */			/* 9 */		/* A */		/* B */		/* C - F */
+#define IP7_23_20	FM(SD0_CMD)		F_(0, 0)	FM(MSIOF1_SYNC_E)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_0_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_27_24	FM(SD0_DAT0)		F_(0, 0)	FM(MSIOF1_RXD_E)	F_(0, 0)			F_(0, 0)	FM(TS_SCK0_B)	FM(STP_ISCLK_0_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP7_31_28	FM(SD0_DAT1)		F_(0, 0)	FM(MSIOF1_TXD_E)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_B)FM(STP_ISSYNC_0_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_3_0		FM(SD0_DAT2)		F_(0, 0)	FM(MSIOF1_SS1_E)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_B)	FM(STP_ISD_0_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_7_4		FM(SD0_DAT3)		F_(0, 0)	FM(MSIOF1_SS2_E)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_B)	FM(STP_ISEN_0_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_11_8	FM(SD1_CLK)		F_(0, 0)	FM(MSIOF1_SCK_G)	F_(0, 0)			F_(0, 0)	FM(SIM0_CLK_A)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_15_12	FM(SD1_CMD)		F_(0, 0)	FM(MSIOF1_SYNC_G)	F_(0, 0)			F_(0, 0)	FM(SIM0_D_A)	FM(STP_IVCXO27_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_19_16	FM(SD1_DAT0)		FM(SD2_DAT4)	FM(MSIOF1_RXD_G)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_B)	FM(STP_ISCLK_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_23_20	FM(SD1_DAT1)		FM(SD2_DAT5)	FM(MSIOF1_TXD_G)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_B)FM(STP_ISSYNC_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_27_24	FM(SD1_DAT2)		FM(SD2_DAT6)	FM(MSIOF1_SS1_G)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_B)	FM(STP_ISD_1_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_31_28	FM(SD1_DAT3)		FM(SD2_DAT7)	FM(MSIOF1_SS2_G)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_B)	FM(STP_ISEN_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_3_0		FM(SD2_CLK)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_7_4		FM(SD2_DAT0)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_11_8	FM(SD2_DAT1)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_15_12	FM(SD2_DAT2)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_19_16	FM(SD2_DAT3)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_23_20	FM(SD2_DS)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(SATA_DEVSLP_B)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_27_24	FM(SD3_DAT4)		FM(SD2_CD_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_31_28	FM(SD3_DAT5)		FM(SD2_WP_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_3_0	FM(SD3_DAT6)		FM(SD3_CD)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_7_4	FM(SD3_DAT7)		FM(SD3_WP)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_11_8	FM(SD0_CD)		F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SCL2_B)	FM(SIM0_RST_A)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_15_12	FM(SD0_WP)		F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SDA2_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_19_16	FM(SD1_CD)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(SIM0_CLK_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_23_20	FM(SD1_WP)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(SIM0_D_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_27_24	FM(SCK0)		FM(HSCK1_B)	FM(MSIOF1_SS2_B)	FM(AUDIO_CLKC_B)		FM(SDA2_A)	FM(SIM0_RST_B)	FM(STP_OPWM_0_C)	FM(RIF0_CLK_B)	F_(0, 0)		FM(ADICHS2)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_31_28	FM(RX0)			FM(HRX1_B)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SCK0_C)	FM(STP_ISCLK_0_C)	FM(RIF0_D0_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_3_0	FM(TX0)			FM(HTX1_B)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_C)FM(STP_ISSYNC_0_C)	FM(RIF0_D1_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_7_4	FM(CTS0_N)		FM(HCTS1_N_B)	FM(MSIOF1_SYNC_B)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_C)FM(STP_ISSYNC_1_C)	FM(RIF1_SYNC_B)	FM(AUDIO_CLKOUT_C)	FM(ADICS_SAMP)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_11_8	FM(RTS0_N_TANS)		FM(HRTS1_N_B)	FM(MSIOF1_SS1_B)	FM(AUDIO_CLKA_B)		FM(SCL2_A)	F_(0, 0)	FM(STP_IVCXO27_1_C)	FM(RIF0_SYNC_B)	F_(0, 0)		FM(ADICHS1)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_15_12	FM(RX1_A)		FM(HRX1_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_C)	FM(STP_ISD_0_C)		FM(RIF1_CLK_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_19_16	FM(TX1_A)		FM(HTX1_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_C)	FM(STP_ISEN_0_C)	FM(RIF1_D0_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_23_20	FM(CTS1_N)		FM(HCTS1_N_A)	FM(MSIOF1_RXD_B)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_C)	FM(STP_ISEN_1_C)	FM(RIF1_D0_B)	F_(0, 0)		FM(ADIDATA)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_27_24	FM(RTS1_N_TANS)		FM(HRTS1_N_A)	FM(MSIOF1_TXD_B)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_C)	FM(STP_ISD_1_C)		FM(RIF1_D1_B)	F_(0, 0)		FM(ADICHS0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_31_28	FM(SCK2)		FM(SCIF_CLK_B)	FM(MSIOF1_SCK_B)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_C)	FM(STP_ISCLK_1_C)	FM(RIF1_CLK_B)	F_(0, 0)		FM(ADICLK)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_3_0	FM(TX2_A)		F_(0, 0)	F_(0, 0)		FM(SD2_CD_B)			FM(SCL1_A)	F_(0, 0)	FM(FMCLK_A)		FM(RIF1_D1_C)	F_(0, 0)		FM(FSO_CFE_0_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_7_4	FM(RX2_A)		F_(0, 0)	F_(0, 0)		FM(SD2_WP_B)			FM(SDA1_A)	F_(0, 0)	FM(FMIN_A)		FM(RIF1_SYNC_C)	F_(0, 0)		FM(FSO_CFE_1_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_11_8	FM(HSCK0)		F_(0, 0)	FM(MSIOF1_SCK_D)	FM(AUDIO_CLKB_A)		FM(SSI_SDATA1_B)FM(TS_SCK0_D)	FM(STP_ISCLK_0_D)	FM(RIF0_CLK_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_15_12	FM(HRX0)		F_(0, 0)	FM(MSIOF1_RXD_D)	F_(0, 0)			FM(SSI_SDATA2_B)FM(TS_SDEN0_D)	FM(STP_ISEN_0_D)	FM(RIF0_D0_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_19_16	FM(HTX0)		F_(0, 0)	FM(MSIOF1_TXD_D)	F_(0, 0)			FM(SSI_SDATA9_B)FM(TS_SDAT0_D)	FM(STP_ISD_0_D)		FM(RIF0_D1_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_23_20	FM(HCTS0_N)		FM(RX2_B)	FM(MSIOF1_SYNC_D)	F_(0, 0)			FM(SSI_SCK9_A)	FM(TS_SPSYNC0_D)FM(STP_ISSYNC_0_D)	FM(RIF0_SYNC_C)	FM(AUDIO_CLKOUT1_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_27_24	FM(HRTS0_N)		FM(TX2_B)	FM(MSIOF1_SS1_D)	F_(0, 0)			FM(SSI_WS9_A)	F_(0, 0)	FM(STP_IVCXO27_0_D)	FM(BPFCLK_A)	FM(AUDIO_CLKOUT2_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+/* IPSRx */		/* 0 */			/* 1 */		/* 2 */			/* 3 */				/* 4 */		/* 5 */		/* 6 */			/* 7 */		/* 8 */			/* 9 */		/* A */		/* B */		/* C - F */
+#define IP12_31_28	FM(MSIOF0_SYNC)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(AUDIO_CLKOUT_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_3_0	FM(MSIOF0_SS1)		FM(RX5)		F_(0, 0)		FM(AUDIO_CLKA_C)		FM(SSI_SCK2_A)	F_(0, 0)	FM(STP_IVCXO27_0_C)	F_(0, 0)	FM(AUDIO_CLKOUT3_A)	F_(0, 0)	FM(TCLK1_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_7_4	FM(MSIOF0_SS2)		FM(TX5)		FM(MSIOF1_SS2_D)	FM(AUDIO_CLKC_A)		FM(SSI_WS2_A)	F_(0, 0)	FM(STP_OPWM_0_D)	F_(0, 0)	FM(AUDIO_CLKOUT_D)	F_(0, 0)	FM(SPEEDIN_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_11_8	FM(MLB_CLK)		F_(0, 0)	FM(MSIOF1_SCK_F)	F_(0, 0)			FM(SCL1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_15_12	FM(MLB_SIG)		FM(RX1_B)	FM(MSIOF1_SYNC_F)	F_(0, 0)			FM(SDA1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_19_16	FM(MLB_DAT)		FM(TX1_B)	FM(MSIOF1_RXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_23_20	FM(SSI_SCK01239)	F_(0, 0)	FM(MSIOF1_TXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_27_24	FM(SSI_WS01239)		F_(0, 0)	FM(MSIOF1_SS1_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_31_28	FM(SSI_SDATA0)		F_(0, 0)	FM(MSIOF1_SS2_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_3_0	FM(SSI_SDATA1_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_7_4	FM(SSI_SDATA2_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SSI_SCK1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_11_8	FM(SSI_SCK34)		F_(0, 0)	FM(MSIOF1_SS1_A)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_OPWM_0_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_15_12	FM(SSI_WS34)		FM(HCTS2_N_A)	FM(MSIOF1_SS2_A)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_0_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_19_16	FM(SSI_SDATA3)		FM(HRTS2_N_A)	FM(MSIOF1_TXD_A)	F_(0, 0)			F_(0, 0)	FM(TS_SCK0_A)	FM(STP_ISCLK_0_A)	FM(RIF0_D1_A)	FM(RIF2_D0_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_23_20	FM(SSI_SCK4)		FM(HRX2_A)	FM(MSIOF1_SCK_A)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_A)	FM(STP_ISD_0_A)		FM(RIF0_CLK_A)	FM(RIF2_CLK_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_27_24	FM(SSI_WS4)		FM(HTX2_A)	FM(MSIOF1_SYNC_A)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_A)	FM(STP_ISEN_0_A)	FM(RIF0_SYNC_A)	FM(RIF2_SYNC_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_31_28	FM(SSI_SDATA4)		FM(HSCK2_A)	FM(MSIOF1_RXD_A)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_A)FM(STP_ISSYNC_0_A)	FM(RIF0_D0_A)	FM(RIF2_D1_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_3_0	FM(SSI_SCK6)		FM(USB2_PWEN)	F_(0, 0)		FM(SIM0_RST_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_7_4	FM(SSI_WS6)		FM(USB2_OVC)	F_(0, 0)		FM(SIM0_D_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_11_8	FM(SSI_SDATA6)		F_(0, 0)	F_(0, 0)		FM(SIM0_CLK_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(SATA_DEVSLP_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_15_12	FM(SSI_SCK78)		FM(HRX2_B)	FM(MSIOF1_SCK_C)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_A)	FM(STP_ISCLK_1_A)	FM(RIF1_CLK_A)	FM(RIF3_CLK_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_19_16	FM(SSI_WS78)		FM(HTX2_B)	FM(MSIOF1_SYNC_C)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_A)	FM(STP_ISD_1_A)		FM(RIF1_SYNC_A)	FM(RIF3_SYNC_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_23_20	FM(SSI_SDATA7)		FM(HCTS2_N_B)	FM(MSIOF1_RXD_C)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_A)	FM(STP_ISEN_1_A)	FM(RIF1_D0_A)	FM(RIF3_D0_A)		F_(0, 0)	FM(TCLK2_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_27_24	FM(SSI_SDATA8)		FM(HRTS2_N_B)	FM(MSIOF1_TXD_C)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_A)FM(STP_ISSYNC_1_A)	FM(RIF1_D1_A)	FM(RIF3_D1_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_31_28	FM(SSI_SDATA9_A)	FM(HSCK2_B)	FM(MSIOF1_SS1_C)	FM(HSCK1_A)			FM(SSI_WS1_B)	FM(SCK1)	FM(STP_IVCXO27_1_A)	FM(SCK5)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_3_0	FM(AUDIO_CLKA_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	FM(CC5_OSCOUT)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_7_4	FM(AUDIO_CLKB_B)	FM(SCIF_CLK_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_1_D)	FM(REMOCON_A)	F_(0, 0)		F_(0, 0)	FM(TCLK1_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_11_8	FM(USB0_PWEN)		F_(0, 0)	F_(0, 0)		FM(SIM0_RST_C)			F_(0, 0)	FM(TS_SCK1_D)	FM(STP_ISCLK_1_D)	FM(BPFCLK_B)	FM(RIF3_CLK_B)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_15_12	FM(USB0_OVC)		F_(0, 0)	F_(0, 0)		FM(SIM0_D_C)			F_(0, 0)	FM(TS_SDAT1_D)	FM(STP_ISD_1_D)		F_(0, 0)	FM(RIF3_SYNC_B)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_19_16	FM(USB1_PWEN)		F_(0, 0)	F_(0, 0)		FM(SIM0_CLK_C)			FM(SSI_SCK1_A)	FM(TS_SCK0_E)	FM(STP_ISCLK_0_E)	FM(FMCLK_B)	FM(RIF2_CLK_B)		F_(0, 0)	FM(SPEEDIN_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_23_20	FM(USB1_OVC)		F_(0, 0)	FM(MSIOF1_SS2_C)	F_(0, 0)			FM(SSI_WS1_A)	FM(TS_SDAT0_E)	FM(STP_ISD_0_E)		FM(FMIN_B)	FM(RIF2_SYNC_B)		F_(0, 0)	FM(REMOCON_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_27_24	FM(USB30_PWEN)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT_B)		FM(SSI_SCK2_B)	FM(TS_SDEN1_D)	FM(STP_ISEN_1_D)	FM(STP_OPWM_0_E)FM(RIF3_D0_B)		F_(0, 0)	FM(TCLK2_B)	FM(TPU0TO0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_31_28	FM(USB30_OVC)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT1_B)		FM(SSI_WS2_B)	FM(TS_SPSYNC1_D)FM(STP_ISSYNC_1_D)	FM(STP_IVCXO27_0_E)FM(RIF3_D1_B)	F_(0, 0)	FM(FSO_TOE_B)	FM(TPU0TO1)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP17_3_0	FM(USB31_PWEN)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT2_B)		FM(SSI_SCK9_B)	FM(TS_SDEN0_E)	FM(STP_ISEN_0_E)	F_(0, 0)	FM(RIF2_D0_B)		F_(0, 0)	F_(0, 0)	FM(TPU0TO2)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP17_7_4	FM(USB31_OVC)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT3_B)		FM(SSI_WS9_B)	FM(TS_SPSYNC0_E)FM(STP_ISSYNC_0_E)	F_(0, 0)	FM(RIF2_D1_B)		F_(0, 0)	F_(0, 0)	FM(TPU0TO3)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+#define PINMUX_GPSR	\
+\
+												GPSR6_31 \
+												GPSR6_30 \
+												GPSR6_29 \
+												GPSR6_28 \
+		GPSR1_27									GPSR6_27 \
+		GPSR1_26									GPSR6_26 \
+		GPSR1_25							GPSR5_25	GPSR6_25 \
+		GPSR1_24							GPSR5_24	GPSR6_24 \
+		GPSR1_23							GPSR5_23	GPSR6_23 \
+		GPSR1_22							GPSR5_22	GPSR6_22 \
+		GPSR1_21							GPSR5_21	GPSR6_21 \
+		GPSR1_20							GPSR5_20	GPSR6_20 \
+		GPSR1_19							GPSR5_19	GPSR6_19 \
+		GPSR1_18							GPSR5_18	GPSR6_18 \
+		GPSR1_17					GPSR4_17	GPSR5_17	GPSR6_17 \
+		GPSR1_16					GPSR4_16	GPSR5_16	GPSR6_16 \
+GPSR0_15	GPSR1_15			GPSR3_15	GPSR4_15	GPSR5_15	GPSR6_15 \
+GPSR0_14	GPSR1_14	GPSR2_14	GPSR3_14	GPSR4_14	GPSR5_14	GPSR6_14 \
+GPSR0_13	GPSR1_13	GPSR2_13	GPSR3_13	GPSR4_13	GPSR5_13	GPSR6_13 \
+GPSR0_12	GPSR1_12	GPSR2_12	GPSR3_12	GPSR4_12	GPSR5_12	GPSR6_12 \
+GPSR0_11	GPSR1_11	GPSR2_11	GPSR3_11	GPSR4_11	GPSR5_11	GPSR6_11 \
+GPSR0_10	GPSR1_10	GPSR2_10	GPSR3_10	GPSR4_10	GPSR5_10	GPSR6_10 \
+GPSR0_9		GPSR1_9		GPSR2_9		GPSR3_9		GPSR4_9		GPSR5_9		GPSR6_9 \
+GPSR0_8		GPSR1_8		GPSR2_8		GPSR3_8		GPSR4_8		GPSR5_8		GPSR6_8 \
+GPSR0_7		GPSR1_7		GPSR2_7		GPSR3_7		GPSR4_7		GPSR5_7		GPSR6_7 \
+GPSR0_6		GPSR1_6		GPSR2_6		GPSR3_6		GPSR4_6		GPSR5_6		GPSR6_6 \
+GPSR0_5		GPSR1_5		GPSR2_5		GPSR3_5		GPSR4_5		GPSR5_5		GPSR6_5 \
+GPSR0_4		GPSR1_4		GPSR2_4		GPSR3_4		GPSR4_4		GPSR5_4		GPSR6_4 \
+GPSR0_3		GPSR1_3		GPSR2_3		GPSR3_3		GPSR4_3		GPSR5_3		GPSR6_3		GPSR7_3 \
+GPSR0_2		GPSR1_2		GPSR2_2		GPSR3_2		GPSR4_2		GPSR5_2		GPSR6_2		GPSR7_2 \
+GPSR0_1		GPSR1_1		GPSR2_1		GPSR3_1		GPSR4_1		GPSR5_1		GPSR6_1		GPSR7_1 \
+GPSR0_0		GPSR1_0		GPSR2_0		GPSR3_0		GPSR4_0		GPSR5_0		GPSR6_0		GPSR7_0
+
+#define PINMUX_IPSR				\
+\
+FM(IP0_3_0)	IP0_3_0		FM(IP1_3_0)	IP1_3_0		FM(IP2_3_0)	IP2_3_0		FM(IP3_3_0)	IP3_3_0 \
+FM(IP0_7_4)	IP0_7_4		FM(IP1_7_4)	IP1_7_4		FM(IP2_7_4)	IP2_7_4		FM(IP3_7_4)	IP3_7_4 \
+FM(IP0_11_8)	IP0_11_8	FM(IP1_11_8)	IP1_11_8	FM(IP2_11_8)	IP2_11_8	FM(IP3_11_8)	IP3_11_8 \
+FM(IP0_15_12)	IP0_15_12	FM(IP1_15_12)	IP1_15_12	FM(IP2_15_12)	IP2_15_12	FM(IP3_15_12)	IP3_15_12 \
+FM(IP0_19_16)	IP0_19_16	FM(IP1_19_16)	IP1_19_16	FM(IP2_19_16)	IP2_19_16	FM(IP3_19_16)	IP3_19_16 \
+FM(IP0_23_20)	IP0_23_20	FM(IP1_23_20)	IP1_23_20	FM(IP2_23_20)	IP2_23_20	FM(IP3_23_20)	IP3_23_20 \
+FM(IP0_27_24)	IP0_27_24	FM(IP1_27_24)	IP1_27_24	FM(IP2_27_24)	IP2_27_24	FM(IP3_27_24)	IP3_27_24 \
+FM(IP0_31_28)	IP0_31_28	FM(IP1_31_28)	IP1_31_28	FM(IP2_31_28)	IP2_31_28	FM(IP3_31_28)	IP3_31_28 \
+\
+FM(IP4_3_0)	IP4_3_0		FM(IP5_3_0)	IP5_3_0		FM(IP6_3_0)	IP6_3_0		FM(IP7_3_0)	IP7_3_0 \
+FM(IP4_7_4)	IP4_7_4		FM(IP5_7_4)	IP5_7_4		FM(IP6_7_4)	IP6_7_4		FM(IP7_7_4)	IP7_7_4 \
+FM(IP4_11_8)	IP4_11_8	FM(IP5_11_8)	IP5_11_8	FM(IP6_11_8)	IP6_11_8	FM(IP7_11_8)	IP7_11_8 \
+FM(IP4_15_12)	IP4_15_12	FM(IP5_15_12)	IP5_15_12	FM(IP6_15_12)	IP6_15_12	FM(IP7_15_12)	IP7_15_12 \
+FM(IP4_19_16)	IP4_19_16	FM(IP5_19_16)	IP5_19_16	FM(IP6_19_16)	IP6_19_16	FM(IP7_19_16)	IP7_19_16 \
+FM(IP4_23_20)	IP4_23_20	FM(IP5_23_20)	IP5_23_20	FM(IP6_23_20)	IP6_23_20	FM(IP7_23_20)	IP7_23_20 \
+FM(IP4_27_24)	IP4_27_24	FM(IP5_27_24)	IP5_27_24	FM(IP6_27_24)	IP6_27_24	FM(IP7_27_24)	IP7_27_24 \
+FM(IP4_31_28)	IP4_31_28	FM(IP5_31_28)	IP5_31_28	FM(IP6_31_28)	IP6_31_28	FM(IP7_31_28)	IP7_31_28 \
+\
+FM(IP8_3_0)	IP8_3_0		FM(IP9_3_0)	IP9_3_0		FM(IP10_3_0)	IP10_3_0	FM(IP11_3_0)	IP11_3_0 \
+FM(IP8_7_4)	IP8_7_4		FM(IP9_7_4)	IP9_7_4		FM(IP10_7_4)	IP10_7_4	FM(IP11_7_4)	IP11_7_4 \
+FM(IP8_11_8)	IP8_11_8	FM(IP9_11_8)	IP9_11_8	FM(IP10_11_8)	IP10_11_8	FM(IP11_11_8)	IP11_11_8 \
+FM(IP8_15_12)	IP8_15_12	FM(IP9_15_12)	IP9_15_12	FM(IP10_15_12)	IP10_15_12	FM(IP11_15_12)	IP11_15_12 \
+FM(IP8_19_16)	IP8_19_16	FM(IP9_19_16)	IP9_19_16	FM(IP10_19_16)	IP10_19_16	FM(IP11_19_16)	IP11_19_16 \
+FM(IP8_23_20)	IP8_23_20	FM(IP9_23_20)	IP9_23_20	FM(IP10_23_20)	IP10_23_20	FM(IP11_23_20)	IP11_23_20 \
+FM(IP8_27_24)	IP8_27_24	FM(IP9_27_24)	IP9_27_24	FM(IP10_27_24)	IP10_27_24	FM(IP11_27_24)	IP11_27_24 \
+FM(IP8_31_28)	IP8_31_28	FM(IP9_31_28)	IP9_31_28	FM(IP10_31_28)	IP10_31_28	FM(IP11_31_28)	IP11_31_28 \
+\
+FM(IP12_3_0)	IP12_3_0	FM(IP13_3_0)	IP13_3_0	FM(IP14_3_0)	IP14_3_0	FM(IP15_3_0)	IP15_3_0 \
+FM(IP12_7_4)	IP12_7_4	FM(IP13_7_4)	IP13_7_4	FM(IP14_7_4)	IP14_7_4	FM(IP15_7_4)	IP15_7_4 \
+FM(IP12_11_8)	IP12_11_8	FM(IP13_11_8)	IP13_11_8	FM(IP14_11_8)	IP14_11_8	FM(IP15_11_8)	IP15_11_8 \
+FM(IP12_15_12)	IP12_15_12	FM(IP13_15_12)	IP13_15_12	FM(IP14_15_12)	IP14_15_12	FM(IP15_15_12)	IP15_15_12 \
+FM(IP12_19_16)	IP12_19_16	FM(IP13_19_16)	IP13_19_16	FM(IP14_19_16)	IP14_19_16	FM(IP15_19_16)	IP15_19_16 \
+FM(IP12_23_20)	IP12_23_20	FM(IP13_23_20)	IP13_23_20	FM(IP14_23_20)	IP14_23_20	FM(IP15_23_20)	IP15_23_20 \
+FM(IP12_27_24)	IP12_27_24	FM(IP13_27_24)	IP13_27_24	FM(IP14_27_24)	IP14_27_24	FM(IP15_27_24)	IP15_27_24 \
+FM(IP12_31_28)	IP12_31_28	FM(IP13_31_28)	IP13_31_28	FM(IP14_31_28)	IP14_31_28	FM(IP15_31_28)	IP15_31_28 \
+\
+FM(IP16_3_0)	IP16_3_0	FM(IP17_3_0)	IP17_3_0 \
+FM(IP16_7_4)	IP16_7_4	FM(IP17_7_4)	IP17_7_4 \
+FM(IP16_11_8)	IP16_11_8 \
+FM(IP16_15_12)	IP16_15_12 \
+FM(IP16_19_16)	IP16_19_16 \
+FM(IP16_23_20)	IP16_23_20 \
+FM(IP16_27_24)	IP16_27_24 \
+FM(IP16_31_28)	IP16_31_28
+
+/* MOD_SEL0 */			/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */			/* 6 */			/* 7 */
+#define MOD_SEL0_30_29		FM(SEL_MSIOF3_0)	FM(SEL_MSIOF3_1)	FM(SEL_MSIOF3_2)	FM(SEL_MSIOF3_3)
+#define MOD_SEL0_28_27		FM(SEL_MSIOF2_0)	FM(SEL_MSIOF2_1)	FM(SEL_MSIOF2_2)	FM(SEL_MSIOF2_3)
+#define MOD_SEL0_26_25_24	FM(SEL_MSIOF1_0)	FM(SEL_MSIOF1_1)	FM(SEL_MSIOF1_2)	FM(SEL_MSIOF1_3)	FM(SEL_MSIOF1_4)	FM(SEL_MSIOF1_5)	FM(SEL_MSIOF1_6)	F_(0, 0)
+#define MOD_SEL0_23		FM(SEL_LBSC_0)		FM(SEL_LBSC_1)
+#define MOD_SEL0_22		FM(SEL_IEBUS_0)		FM(SEL_IEBUS_1)
+#define MOD_SEL0_21_20		FM(SEL_I2C6_0)		FM(SEL_I2C6_1)		FM(SEL_I2C6_2)		F_(0, 0)
+#define MOD_SEL0_19		FM(SEL_I2C2_0)		FM(SEL_I2C2_1)
+#define MOD_SEL0_18		FM(SEL_I2C1_0)		FM(SEL_I2C1_1)
+#define MOD_SEL0_17		FM(SEL_HSCIF4_0)	FM(SEL_HSCIF4_1)
+#define MOD_SEL0_16_15		FM(SEL_HSCIF3_0)	FM(SEL_HSCIF3_1)	FM(SEL_HSCIF3_2)	FM(SEL_HSCIF3_3)
+#define MOD_SEL0_14		FM(SEL_HSCIF2_0)	FM(SEL_HSCIF2_1)
+#define MOD_SEL0_13		FM(SEL_HSCIF1_0)	FM(SEL_HSCIF1_1)
+#define MOD_SEL0_12		FM(SEL_FSO_0)		FM(SEL_FSO_1)
+#define MOD_SEL0_11		FM(SEL_FM_0)		FM(SEL_FM_1)
+#define MOD_SEL0_10		FM(SEL_ETHERAVB_0)	FM(SEL_ETHERAVB_1)
+#define MOD_SEL0_9		FM(SEL_DRIF3_0)		FM(SEL_DRIF3_1)
+#define MOD_SEL0_8		FM(SEL_DRIF2_0)		FM(SEL_DRIF2_1)
+#define MOD_SEL0_7_6		FM(SEL_DRIF1_0)		FM(SEL_DRIF1_1)		FM(SEL_DRIF1_2)		F_(0, 0)
+#define MOD_SEL0_5_4		FM(SEL_DRIF0_0)		FM(SEL_DRIF0_1)		FM(SEL_DRIF0_2)		F_(0, 0)
+#define MOD_SEL0_3		FM(SEL_CANFD0_0)	FM(SEL_CANFD0_1)
+#define MOD_SEL0_2_1		FM(SEL_ADG_0)		FM(SEL_ADG_1)		FM(SEL_ADG_2)		FM(SEL_ADG_3)
+
+/* MOD_SEL1 */			/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */			/* 6 */			/* 7 */
+#define MOD_SEL1_31_30		FM(SEL_TSIF1_0)		FM(SEL_TSIF1_1)		FM(SEL_TSIF1_2)		FM(SEL_TSIF1_3)
+#define MOD_SEL1_29_28_27	FM(SEL_TSIF0_0)		FM(SEL_TSIF0_1)		FM(SEL_TSIF0_2)		FM(SEL_TSIF0_3)		FM(SEL_TSIF0_4)		F_(0, 0)		F_(0, 0)		F_(0, 0)
+#define MOD_SEL1_26		FM(SEL_TIMER_TMU_0)	FM(SEL_TIMER_TMU_1)
+#define MOD_SEL1_25_24		FM(SEL_SSP1_1_0)	FM(SEL_SSP1_1_1)	FM(SEL_SSP1_1_2)	FM(SEL_SSP1_1_3)
+#define MOD_SEL1_23_22_21	FM(SEL_SSP1_0_0)	FM(SEL_SSP1_0_1)	FM(SEL_SSP1_0_2)	FM(SEL_SSP1_0_3)	FM(SEL_SSP1_0_4)	F_(0, 0)		F_(0, 0)		F_(0, 0)
+#define MOD_SEL1_20		FM(SEL_SSI_0)		FM(SEL_SSI_1)
+#define MOD_SEL1_19		FM(SEL_SPEED_PULSE_0)	FM(SEL_SPEED_PULSE_1)
+#define MOD_SEL1_18_17		FM(SEL_SIMCARD_0)	FM(SEL_SIMCARD_1)	FM(SEL_SIMCARD_2)	FM(SEL_SIMCARD_3)
+#define MOD_SEL1_16		FM(SEL_SDHI2_0)		FM(SEL_SDHI2_1)
+#define MOD_SEL1_15_14		FM(SEL_SCIF4_0)		FM(SEL_SCIF4_1)		FM(SEL_SCIF4_2)		F_(0, 0)
+#define MOD_SEL1_13		FM(SEL_SCIF3_0)		FM(SEL_SCIF3_1)
+#define MOD_SEL1_12		FM(SEL_SCIF2_0)		FM(SEL_SCIF2_1)
+#define MOD_SEL1_11		FM(SEL_SCIF1_0)		FM(SEL_SCIF1_1)
+#define MOD_SEL1_10		FM(SEL_SATA_0)		FM(SEL_SATA_1)
+#define MOD_SEL1_9		FM(SEL_REMOCON_0)	FM(SEL_REMOCON_1)
+#define MOD_SEL1_6		FM(SEL_RCAN0_0)		FM(SEL_RCAN0_1)
+#define MOD_SEL1_5		FM(SEL_PWM6_0)		FM(SEL_PWM6_1)
+#define MOD_SEL1_4		FM(SEL_PWM5_0)		FM(SEL_PWM5_1)
+#define MOD_SEL1_3		FM(SEL_PWM4_0)		FM(SEL_PWM4_1)
+#define MOD_SEL1_2		FM(SEL_PWM3_0)		FM(SEL_PWM3_1)
+#define MOD_SEL1_1		FM(SEL_PWM2_0)		FM(SEL_PWM2_1)
+#define MOD_SEL1_0		FM(SEL_PWM1_0)		FM(SEL_PWM1_1)
+
+/* MOD_SEL2 */			/* 0 */			/* 1 */			/* 2 */			/* 3 */
+#define MOD_SEL2_31		FM(I2C_SEL_5_0)		FM(I2C_SEL_5_1)
+#define MOD_SEL2_30		FM(I2C_SEL_3_0)		FM(I2C_SEL_3_1)
+#define MOD_SEL2_29		FM(I2C_SEL_0_0)		FM(I2C_SEL_0_1)
+#define MOD_SEL2_0		FM(SEL_VIN4_0)		FM(SEL_VIN4_1)
+
+#define PINMUX_MOD_SELS\
+\
+			MOD_SEL1_31_30		MOD_SEL2_31 \
+MOD_SEL0_30_29					MOD_SEL2_30 \
+			MOD_SEL1_29_28_27	MOD_SEL2_29 \
+MOD_SEL0_28_27 \
+\
+MOD_SEL0_26_25_24	MOD_SEL1_26 \
+			MOD_SEL1_25_24 \
+\
+MOD_SEL0_23		MOD_SEL1_23_22_21 \
+MOD_SEL0_22 \
+MOD_SEL0_21_20 \
+			MOD_SEL1_20 \
+MOD_SEL0_19		MOD_SEL1_19 \
+MOD_SEL0_18		MOD_SEL1_18_17 \
+MOD_SEL0_17 \
+MOD_SEL0_16_15		MOD_SEL1_16 \
+			MOD_SEL1_15_14 \
+MOD_SEL0_14 \
+MOD_SEL0_13		MOD_SEL1_13 \
+MOD_SEL0_12		MOD_SEL1_12 \
+MOD_SEL0_11		MOD_SEL1_11 \
+MOD_SEL0_10		MOD_SEL1_10 \
+MOD_SEL0_9		MOD_SEL1_9 \
+MOD_SEL0_8 \
+MOD_SEL0_7_6 \
+			MOD_SEL1_6 \
+MOD_SEL0_5_4		MOD_SEL1_5 \
+			MOD_SEL1_4 \
+MOD_SEL0_3		MOD_SEL1_3 \
+MOD_SEL0_2_1		MOD_SEL1_2 \
+			MOD_SEL1_1 \
+			MOD_SEL1_0		MOD_SEL2_0
+
+/*
+ * These pins are not able to be muxed but have other properties
+ * that can be set, such as drive-strength or pull-up/pull-down enable.
+ */
+#define PINMUX_STATIC \
+	FM(QSPI0_SPCLK) FM(QSPI0_SSL) FM(QSPI0_MOSI_IO0) FM(QSPI0_MISO_IO1) \
+	FM(QSPI0_IO2) FM(QSPI0_IO3) \
+	FM(QSPI1_SPCLK) FM(QSPI1_SSL) FM(QSPI1_MOSI_IO0) FM(QSPI1_MISO_IO1) \
+	FM(QSPI1_IO2) FM(QSPI1_IO3) \
+	FM(RPC_INT) FM(RPC_WP) FM(RPC_RESET) \
+	FM(AVB_TX_CTL) FM(AVB_TXC) FM(AVB_TD0) FM(AVB_TD1) FM(AVB_TD2) FM(AVB_TD3) \
+	FM(AVB_RX_CTL) FM(AVB_RXC) FM(AVB_RD0) FM(AVB_RD1) FM(AVB_RD2) FM(AVB_RD3) \
+	FM(AVB_TXCREFCLK) FM(AVB_MDIO) \
+	FM(CLKOUT) FM(PRESETOUT) \
+	FM(DU_DOTCLKIN0) FM(DU_DOTCLKIN1) FM(DU_DOTCLKIN2) FM(DU_DOTCLKIN3) \
+	FM(TMS) FM(TDO) FM(ASEBRK) FM(MLB_REF) FM(TDI) FM(TCK) FM(TRST) FM(EXTALR)
+
+enum {
+	PINMUX_RESERVED = 0,
+
+	PINMUX_DATA_BEGIN,
+	GP_ALL(DATA),
+	PINMUX_DATA_END,
+
+#define F_(x, y)
+#define FM(x)	FN_##x,
+	PINMUX_FUNCTION_BEGIN,
+	GP_ALL(FN),
+	PINMUX_GPSR
+	PINMUX_IPSR
+	PINMUX_MOD_SELS
+	PINMUX_FUNCTION_END,
+#undef F_
+#undef FM
+
+#define F_(x, y)
+#define FM(x)	x##_MARK,
+	PINMUX_MARK_BEGIN,
+	PINMUX_GPSR
+	PINMUX_IPSR
+	PINMUX_MOD_SELS
+	PINMUX_STATIC
+	PINMUX_MARK_END,
+#undef F_
+#undef FM
+};
+
+static const u16 pinmux_data[] = {
+	PINMUX_DATA_GP_ALL(),
+
+	PINMUX_SINGLE(AVS1),
+	PINMUX_SINGLE(AVS2),
+	PINMUX_SINGLE(HDMI0_CEC),
+	PINMUX_SINGLE(HDMI1_CEC),
+	PINMUX_SINGLE(I2C_SEL_0_1),
+	PINMUX_SINGLE(I2C_SEL_3_1),
+	PINMUX_SINGLE(I2C_SEL_5_1),
+	PINMUX_SINGLE(MSIOF0_RXD),
+	PINMUX_SINGLE(MSIOF0_SCK),
+	PINMUX_SINGLE(MSIOF0_TXD),
+	PINMUX_SINGLE(SD2_CMD),
+	PINMUX_SINGLE(SD3_CLK),
+	PINMUX_SINGLE(SD3_CMD),
+	PINMUX_SINGLE(SD3_DAT0),
+	PINMUX_SINGLE(SD3_DAT1),
+	PINMUX_SINGLE(SD3_DAT2),
+	PINMUX_SINGLE(SD3_DAT3),
+	PINMUX_SINGLE(SD3_DS),
+	PINMUX_SINGLE(SSI_SCK5),
+	PINMUX_SINGLE(SSI_SDATA5),
+	PINMUX_SINGLE(SSI_WS5),
+
+	/* IPSR0 */
+	PINMUX_IPSR_GPSR(IP0_3_0,	AVB_MDC),
+	PINMUX_IPSR_MSEL(IP0_3_0,	MSIOF2_SS2_C,		SEL_MSIOF2_2),
+
+	PINMUX_IPSR_GPSR(IP0_7_4,	AVB_MAGIC),
+	PINMUX_IPSR_MSEL(IP0_7_4,	MSIOF2_SS1_C,		SEL_MSIOF2_2),
+	PINMUX_IPSR_MSEL(IP0_7_4,	SCK4_A,			SEL_SCIF4_0),
+
+	PINMUX_IPSR_GPSR(IP0_11_8,	AVB_PHY_INT),
+	PINMUX_IPSR_MSEL(IP0_11_8,	MSIOF2_SYNC_C,		SEL_MSIOF2_2),
+	PINMUX_IPSR_MSEL(IP0_11_8,	RX4_A,			SEL_SCIF4_0),
+
+	PINMUX_IPSR_GPSR(IP0_15_12,	AVB_LINK),
+	PINMUX_IPSR_MSEL(IP0_15_12,	MSIOF2_SCK_C,		SEL_MSIOF2_2),
+	PINMUX_IPSR_MSEL(IP0_15_12,	TX4_A,			SEL_SCIF4_0),
+
+	PINMUX_IPSR_MSEL(IP0_19_16,	AVB_AVTP_MATCH_A,	SEL_ETHERAVB_0),
+	PINMUX_IPSR_MSEL(IP0_19_16,	MSIOF2_RXD_C,		SEL_MSIOF2_2),
+	PINMUX_IPSR_MSEL(IP0_19_16,	CTS4_N_A,		SEL_SCIF4_0),
+
+	PINMUX_IPSR_MSEL(IP0_23_20,	AVB_AVTP_CAPTURE_A,	SEL_ETHERAVB_0),
+	PINMUX_IPSR_MSEL(IP0_23_20,	MSIOF2_TXD_C,		SEL_MSIOF2_2),
+	PINMUX_IPSR_MSEL(IP0_23_20,	RTS4_N_TANS_A,		SEL_SCIF4_0),
+
+	PINMUX_IPSR_GPSR(IP0_27_24,	IRQ0),
+	PINMUX_IPSR_GPSR(IP0_27_24,	QPOLB),
+	PINMUX_IPSR_GPSR(IP0_27_24,	DU_CDE),
+	PINMUX_IPSR_MSEL(IP0_27_24,	VI4_DATA0_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP0_27_24,	CAN0_TX_B,		SEL_RCAN0_1),
+	PINMUX_IPSR_MSEL(IP0_27_24,	CANFD0_TX_B,		SEL_CANFD0_1),
+
+	PINMUX_IPSR_GPSR(IP0_31_28,	IRQ1),
+	PINMUX_IPSR_GPSR(IP0_31_28,	QPOLA),
+	PINMUX_IPSR_GPSR(IP0_31_28,	DU_DISP),
+	PINMUX_IPSR_MSEL(IP0_31_28,	VI4_DATA1_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP0_31_28,	CAN0_RX_B,		SEL_RCAN0_1),
+	PINMUX_IPSR_MSEL(IP0_31_28,	CANFD0_RX_B,		SEL_CANFD0_1),
+
+	/* IPSR1 */
+	PINMUX_IPSR_GPSR(IP1_3_0,	IRQ2),
+	PINMUX_IPSR_GPSR(IP1_3_0,	QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP1_3_0,	DU_EXODDF_DU_ODDF_DISP_CDE),
+	PINMUX_IPSR_MSEL(IP1_3_0,	VI4_DATA2_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP1_3_0,	PWM3_B,			SEL_PWM3_1),
+
+	PINMUX_IPSR_GPSR(IP1_7_4,	IRQ3),
+	PINMUX_IPSR_GPSR(IP1_7_4,	QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP1_7_4,	A25),
+	PINMUX_IPSR_GPSR(IP1_7_4,	DU_DOTCLKOUT1),
+	PINMUX_IPSR_MSEL(IP1_7_4,	VI4_DATA3_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP1_7_4,	PWM4_B,			SEL_PWM4_1),
+
+	PINMUX_IPSR_GPSR(IP1_11_8,	IRQ4),
+	PINMUX_IPSR_GPSR(IP1_11_8,	QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP1_11_8,	A24),
+	PINMUX_IPSR_GPSR(IP1_11_8,	DU_EXHSYNC_DU_HSYNC),
+	PINMUX_IPSR_MSEL(IP1_11_8,	VI4_DATA4_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP1_11_8,	PWM5_B,			SEL_PWM5_1),
+
+	PINMUX_IPSR_GPSR(IP1_15_12,	IRQ5),
+	PINMUX_IPSR_GPSR(IP1_15_12,	QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP1_15_12,	A23),
+	PINMUX_IPSR_GPSR(IP1_15_12,	DU_EXVSYNC_DU_VSYNC),
+	PINMUX_IPSR_MSEL(IP1_15_12,	VI4_DATA5_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP1_15_12,	PWM6_B,			SEL_PWM6_1),
+
+	PINMUX_IPSR_GPSR(IP1_19_16,	PWM0),
+	PINMUX_IPSR_GPSR(IP1_19_16,	AVB_AVTP_PPS),
+	PINMUX_IPSR_GPSR(IP1_19_16,	A22),
+	PINMUX_IPSR_MSEL(IP1_19_16,	VI4_DATA6_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP1_19_16,	IECLK_B,		SEL_IEBUS_1),
+
+	PINMUX_IPSR_MSEL(IP1_23_20,	PWM1_A,			SEL_PWM1_0),
+	PINMUX_IPSR_GPSR(IP1_23_20,	A21),
+	PINMUX_IPSR_MSEL(IP1_23_20,	HRX3_D,			SEL_HSCIF3_3),
+	PINMUX_IPSR_MSEL(IP1_23_20,	VI4_DATA7_B,		SEL_VIN4_1),
+	PINMUX_IPSR_MSEL(IP1_23_20,	IERX_B,			SEL_IEBUS_1),
+
+	PINMUX_IPSR_MSEL(IP1_27_24,	PWM2_A,			SEL_PWM2_0),
+	PINMUX_IPSR_GPSR(IP1_27_24,	A20),
+	PINMUX_IPSR_MSEL(IP1_27_24,	HTX3_D,			SEL_HSCIF3_3),
+	PINMUX_IPSR_MSEL(IP1_27_24,	IETX_B,			SEL_IEBUS_1),
+
+	PINMUX_IPSR_GPSR(IP1_31_28,	A0),
+	PINMUX_IPSR_GPSR(IP1_31_28,	LCDOUT16),
+	PINMUX_IPSR_MSEL(IP1_31_28,	MSIOF3_SYNC_B,		SEL_MSIOF3_1),
+	PINMUX_IPSR_GPSR(IP1_31_28,	VI4_DATA8),
+	PINMUX_IPSR_GPSR(IP1_31_28,	DU_DB0),
+	PINMUX_IPSR_MSEL(IP1_31_28,	PWM3_A,			SEL_PWM3_0),
+
+	/* IPSR2 */
+	PINMUX_IPSR_GPSR(IP2_3_0,	A1),
+	PINMUX_IPSR_GPSR(IP2_3_0,	LCDOUT17),
+	PINMUX_IPSR_MSEL(IP2_3_0,	MSIOF3_TXD_B,		SEL_MSIOF3_1),
+	PINMUX_IPSR_GPSR(IP2_3_0,	VI4_DATA9),
+	PINMUX_IPSR_GPSR(IP2_3_0,	DU_DB1),
+	PINMUX_IPSR_MSEL(IP2_3_0,	PWM4_A,			SEL_PWM4_0),
+
+	PINMUX_IPSR_GPSR(IP2_7_4,	A2),
+	PINMUX_IPSR_GPSR(IP2_7_4,	LCDOUT18),
+	PINMUX_IPSR_MSEL(IP2_7_4,	MSIOF3_SCK_B,		SEL_MSIOF3_1),
+	PINMUX_IPSR_GPSR(IP2_7_4,	VI4_DATA10),
+	PINMUX_IPSR_GPSR(IP2_7_4,	DU_DB2),
+	PINMUX_IPSR_MSEL(IP2_7_4,	PWM5_A,			SEL_PWM5_0),
+
+	PINMUX_IPSR_GPSR(IP2_11_8,	A3),
+	PINMUX_IPSR_GPSR(IP2_11_8,	LCDOUT19),
+	PINMUX_IPSR_MSEL(IP2_11_8,	MSIOF3_RXD_B,		SEL_MSIOF3_1),
+	PINMUX_IPSR_GPSR(IP2_11_8,	VI4_DATA11),
+	PINMUX_IPSR_GPSR(IP2_11_8,	DU_DB3),
+	PINMUX_IPSR_MSEL(IP2_11_8,	PWM6_A,			SEL_PWM6_0),
+
+	PINMUX_IPSR_GPSR(IP2_15_12,	A4),
+	PINMUX_IPSR_GPSR(IP2_15_12,	LCDOUT20),
+	PINMUX_IPSR_MSEL(IP2_15_12,	MSIOF3_SS1_B,		SEL_MSIOF3_1),
+	PINMUX_IPSR_GPSR(IP2_15_12,	VI4_DATA12),
+	PINMUX_IPSR_GPSR(IP2_15_12,	VI5_DATA12),
+	PINMUX_IPSR_GPSR(IP2_15_12,	DU_DB4),
+
+	PINMUX_IPSR_GPSR(IP2_19_16,	A5),
+	PINMUX_IPSR_GPSR(IP2_19_16,	LCDOUT21),
+	PINMUX_IPSR_MSEL(IP2_19_16,	MSIOF3_SS2_B,		SEL_MSIOF3_1),
+	PINMUX_IPSR_MSEL(IP2_19_16,	SCK4_B,			SEL_SCIF4_1),
+	PINMUX_IPSR_GPSR(IP2_19_16,	VI4_DATA13),
+	PINMUX_IPSR_GPSR(IP2_19_16,	VI5_DATA13),
+	PINMUX_IPSR_GPSR(IP2_19_16,	DU_DB5),
+
+	PINMUX_IPSR_GPSR(IP2_23_20,	A6),
+	PINMUX_IPSR_GPSR(IP2_23_20,	LCDOUT22),
+	PINMUX_IPSR_MSEL(IP2_23_20,	MSIOF2_SS1_A,		SEL_MSIOF2_0),
+	PINMUX_IPSR_MSEL(IP2_23_20,	RX4_B,			SEL_SCIF4_1),
+	PINMUX_IPSR_GPSR(IP2_23_20,	VI4_DATA14),
+	PINMUX_IPSR_GPSR(IP2_23_20,	VI5_DATA14),
+	PINMUX_IPSR_GPSR(IP2_23_20,	DU_DB6),
+
+	PINMUX_IPSR_GPSR(IP2_27_24,	A7),
+	PINMUX_IPSR_GPSR(IP2_27_24,	LCDOUT23),
+	PINMUX_IPSR_MSEL(IP2_27_24,	MSIOF2_SS2_A,		SEL_MSIOF2_0),
+	PINMUX_IPSR_MSEL(IP2_27_24,	TX4_B,			SEL_SCIF4_1),
+	PINMUX_IPSR_GPSR(IP2_27_24,	VI4_DATA15),
+	PINMUX_IPSR_GPSR(IP2_27_24,	VI5_DATA15),
+	PINMUX_IPSR_GPSR(IP2_27_24,	DU_DB7),
+
+	PINMUX_IPSR_GPSR(IP2_31_28,	A8),
+	PINMUX_IPSR_MSEL(IP2_31_28,	RX3_B,			SEL_SCIF3_1),
+	PINMUX_IPSR_MSEL(IP2_31_28,	MSIOF2_SYNC_A,		SEL_MSIOF2_0),
+	PINMUX_IPSR_MSEL(IP2_31_28,	HRX4_B,			SEL_HSCIF4_1),
+	PINMUX_IPSR_MSEL(IP2_31_28,	SDA6_A,			SEL_I2C6_0),
+	PINMUX_IPSR_MSEL(IP2_31_28,	AVB_AVTP_MATCH_B,	SEL_ETHERAVB_1),
+	PINMUX_IPSR_MSEL(IP2_31_28,	PWM1_B,			SEL_PWM1_1),
+
+	/* IPSR3 */
+	PINMUX_IPSR_GPSR(IP3_3_0,	A9),
+	PINMUX_IPSR_MSEL(IP3_3_0,	MSIOF2_SCK_A,		SEL_MSIOF2_0),
+	PINMUX_IPSR_MSEL(IP3_3_0,	CTS4_N_B,		SEL_SCIF4_1),
+	PINMUX_IPSR_GPSR(IP3_3_0,	VI5_VSYNC_N),
+
+	PINMUX_IPSR_GPSR(IP3_7_4,	A10),
+	PINMUX_IPSR_MSEL(IP3_7_4,	MSIOF2_RXD_A,		SEL_MSIOF2_0),
+	PINMUX_IPSR_MSEL(IP3_7_4,	RTS4_N_TANS_B,		SEL_SCIF4_1),
+	PINMUX_IPSR_GPSR(IP3_7_4,	VI5_HSYNC_N),
+
+	PINMUX_IPSR_GPSR(IP3_11_8,	A11),
+	PINMUX_IPSR_MSEL(IP3_11_8,	TX3_B,			SEL_SCIF3_1),
+	PINMUX_IPSR_MSEL(IP3_11_8,	MSIOF2_TXD_A,		SEL_MSIOF2_0),
+	PINMUX_IPSR_MSEL(IP3_11_8,	HTX4_B,			SEL_HSCIF4_1),
+	PINMUX_IPSR_GPSR(IP3_11_8,	HSCK4),
+	PINMUX_IPSR_GPSR(IP3_11_8,	VI5_FIELD),
+	PINMUX_IPSR_MSEL(IP3_11_8,	SCL6_A,			SEL_I2C6_0),
+	PINMUX_IPSR_MSEL(IP3_11_8,	AVB_AVTP_CAPTURE_B,	SEL_ETHERAVB_1),
+	PINMUX_IPSR_MSEL(IP3_11_8,	PWM2_B,			SEL_PWM2_1),
+
+	PINMUX_IPSR_GPSR(IP3_15_12,	A12),
+	PINMUX_IPSR_GPSR(IP3_15_12,	LCDOUT12),
+	PINMUX_IPSR_MSEL(IP3_15_12,	MSIOF3_SCK_C,		SEL_MSIOF3_2),
+	PINMUX_IPSR_MSEL(IP3_15_12,	HRX4_A,			SEL_HSCIF4_0),
+	PINMUX_IPSR_GPSR(IP3_15_12,	VI5_DATA8),
+	PINMUX_IPSR_GPSR(IP3_15_12,	DU_DG4),
+
+	PINMUX_IPSR_GPSR(IP3_19_16,	A13),
+	PINMUX_IPSR_GPSR(IP3_19_16,	LCDOUT13),
+	PINMUX_IPSR_MSEL(IP3_19_16,	MSIOF3_SYNC_C,		SEL_MSIOF3_2),
+	PINMUX_IPSR_MSEL(IP3_19_16,	HTX4_A,			SEL_HSCIF4_0),
+	PINMUX_IPSR_GPSR(IP3_19_16,	VI5_DATA9),
+	PINMUX_IPSR_GPSR(IP3_19_16,	DU_DG5),
+
+	PINMUX_IPSR_GPSR(IP3_23_20,	A14),
+	PINMUX_IPSR_GPSR(IP3_23_20,	LCDOUT14),
+	PINMUX_IPSR_MSEL(IP3_23_20,	MSIOF3_RXD_C,		SEL_MSIOF3_2),
+	PINMUX_IPSR_GPSR(IP3_23_20,	HCTS4_N),
+	PINMUX_IPSR_GPSR(IP3_23_20,	VI5_DATA10),
+	PINMUX_IPSR_GPSR(IP3_23_20,	DU_DG6),
+
+	PINMUX_IPSR_GPSR(IP3_27_24,	A15),
+	PINMUX_IPSR_GPSR(IP3_27_24,	LCDOUT15),
+	PINMUX_IPSR_MSEL(IP3_27_24,	MSIOF3_TXD_C,		SEL_MSIOF3_2),
+	PINMUX_IPSR_GPSR(IP3_27_24,	HRTS4_N),
+	PINMUX_IPSR_GPSR(IP3_27_24,	VI5_DATA11),
+	PINMUX_IPSR_GPSR(IP3_27_24,	DU_DG7),
+
+	PINMUX_IPSR_GPSR(IP3_31_28,	A16),
+	PINMUX_IPSR_GPSR(IP3_31_28,	LCDOUT8),
+	PINMUX_IPSR_GPSR(IP3_31_28,	VI4_FIELD),
+	PINMUX_IPSR_GPSR(IP3_31_28,	DU_DG0),
+
+	/* IPSR4 */
+	PINMUX_IPSR_GPSR(IP4_3_0,	A17),
+	PINMUX_IPSR_GPSR(IP4_3_0,	LCDOUT9),
+	PINMUX_IPSR_GPSR(IP4_3_0,	VI4_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP4_3_0,	DU_DG1),
+
+	PINMUX_IPSR_GPSR(IP4_7_4,	A18),
+	PINMUX_IPSR_GPSR(IP4_7_4,	LCDOUT10),
+	PINMUX_IPSR_GPSR(IP4_7_4,	VI4_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP4_7_4,	DU_DG2),
+
+	PINMUX_IPSR_GPSR(IP4_11_8,	A19),
+	PINMUX_IPSR_GPSR(IP4_11_8,	LCDOUT11),
+	PINMUX_IPSR_GPSR(IP4_11_8,	VI4_CLKENB),
+	PINMUX_IPSR_GPSR(IP4_11_8,	DU_DG3),
+
+	PINMUX_IPSR_GPSR(IP4_15_12,	CS0_N),
+	PINMUX_IPSR_GPSR(IP4_15_12,	VI5_CLKENB),
+
+	PINMUX_IPSR_GPSR(IP4_19_16,	CS1_N_A26),
+	PINMUX_IPSR_GPSR(IP4_19_16,	VI5_CLK),
+	PINMUX_IPSR_MSEL(IP4_19_16,	EX_WAIT0_B,		SEL_LBSC_1),
+
+	PINMUX_IPSR_GPSR(IP4_23_20,	BS_N),
+	PINMUX_IPSR_GPSR(IP4_23_20,	QSTVA_QVS),
+	PINMUX_IPSR_MSEL(IP4_23_20,	MSIOF3_SCK_D,		SEL_MSIOF3_3),
+	PINMUX_IPSR_GPSR(IP4_23_20,	SCK3),
+	PINMUX_IPSR_GPSR(IP4_23_20,	HSCK3),
+	PINMUX_IPSR_GPSR(IP4_23_20,	CAN1_TX),
+	PINMUX_IPSR_GPSR(IP4_23_20,	CANFD1_TX),
+	PINMUX_IPSR_MSEL(IP4_23_20,	IETX_A,			SEL_IEBUS_0),
+
+	PINMUX_IPSR_GPSR(IP4_27_24,	RD_N),
+	PINMUX_IPSR_MSEL(IP4_27_24,	MSIOF3_SYNC_D,		SEL_MSIOF3_3),
+	PINMUX_IPSR_MSEL(IP4_27_24,	RX3_A,			SEL_SCIF3_0),
+	PINMUX_IPSR_MSEL(IP4_27_24,	HRX3_A,			SEL_HSCIF3_0),
+	PINMUX_IPSR_MSEL(IP4_27_24,	CAN0_TX_A,		SEL_RCAN0_0),
+	PINMUX_IPSR_MSEL(IP4_27_24,	CANFD0_TX_A,		SEL_CANFD0_0),
+
+	PINMUX_IPSR_GPSR(IP4_31_28,	RD_WR_N),
+	PINMUX_IPSR_MSEL(IP4_31_28,	MSIOF3_RXD_D,		SEL_MSIOF3_3),
+	PINMUX_IPSR_MSEL(IP4_31_28,	TX3_A,			SEL_SCIF3_0),
+	PINMUX_IPSR_MSEL(IP4_31_28,	HTX3_A,			SEL_HSCIF3_0),
+	PINMUX_IPSR_MSEL(IP4_31_28,	CAN0_RX_A,		SEL_RCAN0_0),
+	PINMUX_IPSR_MSEL(IP4_31_28,	CANFD0_RX_A,		SEL_CANFD0_0),
+
+	/* IPSR5 */
+	PINMUX_IPSR_GPSR(IP5_3_0,	WE0_N),
+	PINMUX_IPSR_MSEL(IP5_3_0,	MSIOF3_TXD_D,		SEL_MSIOF3_3),
+	PINMUX_IPSR_GPSR(IP5_3_0,	CTS3_N),
+	PINMUX_IPSR_GPSR(IP5_3_0,	HCTS3_N),
+	PINMUX_IPSR_MSEL(IP5_3_0,	SCL6_B,			SEL_I2C6_1),
+	PINMUX_IPSR_GPSR(IP5_3_0,	CAN_CLK),
+	PINMUX_IPSR_MSEL(IP5_3_0,	IECLK_A,		SEL_IEBUS_0),
+
+	PINMUX_IPSR_GPSR(IP5_7_4,	WE1_N),
+	PINMUX_IPSR_MSEL(IP5_7_4,	MSIOF3_SS1_D,		SEL_MSIOF3_3),
+	PINMUX_IPSR_GPSR(IP5_7_4,	RTS3_N_TANS),
+	PINMUX_IPSR_GPSR(IP5_7_4,	HRTS3_N),
+	PINMUX_IPSR_MSEL(IP5_7_4,	SDA6_B,			SEL_I2C6_1),
+	PINMUX_IPSR_GPSR(IP5_7_4,	CAN1_RX),
+	PINMUX_IPSR_GPSR(IP5_7_4,	CANFD1_RX),
+	PINMUX_IPSR_MSEL(IP5_7_4,	IERX_A,			SEL_IEBUS_0),
+
+	PINMUX_IPSR_MSEL(IP5_11_8,	EX_WAIT0_A,		SEL_LBSC_0),
+	PINMUX_IPSR_GPSR(IP5_11_8,	QCLK),
+	PINMUX_IPSR_GPSR(IP5_11_8,	VI4_CLK),
+	PINMUX_IPSR_GPSR(IP5_11_8,	DU_DOTCLKOUT0),
+
+	PINMUX_IPSR_GPSR(IP5_15_12,	D0),
+	PINMUX_IPSR_MSEL(IP5_15_12,	MSIOF2_SS1_B,		SEL_MSIOF2_1),
+	PINMUX_IPSR_MSEL(IP5_15_12,	MSIOF3_SCK_A,		SEL_MSIOF3_0),
+	PINMUX_IPSR_GPSR(IP5_15_12,	VI4_DATA16),
+	PINMUX_IPSR_GPSR(IP5_15_12,	VI5_DATA0),
+
+	PINMUX_IPSR_GPSR(IP5_19_16,	D1),
+	PINMUX_IPSR_MSEL(IP5_19_16,	MSIOF2_SS2_B,		SEL_MSIOF2_1),
+	PINMUX_IPSR_MSEL(IP5_19_16,	MSIOF3_SYNC_A,		SEL_MSIOF3_0),
+	PINMUX_IPSR_GPSR(IP5_19_16,	VI4_DATA17),
+	PINMUX_IPSR_GPSR(IP5_19_16,	VI5_DATA1),
+
+	PINMUX_IPSR_GPSR(IP5_23_20,	D2),
+	PINMUX_IPSR_MSEL(IP5_23_20,	MSIOF3_RXD_A,		SEL_MSIOF3_0),
+	PINMUX_IPSR_GPSR(IP5_23_20,	VI4_DATA18),
+	PINMUX_IPSR_GPSR(IP5_23_20,	VI5_DATA2),
+
+	PINMUX_IPSR_GPSR(IP5_27_24,	D3),
+	PINMUX_IPSR_MSEL(IP5_27_24,	MSIOF3_TXD_A,		SEL_MSIOF3_0),
+	PINMUX_IPSR_GPSR(IP5_27_24,	VI4_DATA19),
+	PINMUX_IPSR_GPSR(IP5_27_24,	VI5_DATA3),
+
+	PINMUX_IPSR_GPSR(IP5_31_28,	D4),
+	PINMUX_IPSR_MSEL(IP5_31_28,	MSIOF2_SCK_B,		SEL_MSIOF2_1),
+	PINMUX_IPSR_GPSR(IP5_31_28,	VI4_DATA20),
+	PINMUX_IPSR_GPSR(IP5_31_28,	VI5_DATA4),
+
+	/* IPSR6 */
+	PINMUX_IPSR_GPSR(IP6_3_0,	D5),
+	PINMUX_IPSR_MSEL(IP6_3_0,	MSIOF2_SYNC_B,		SEL_MSIOF2_1),
+	PINMUX_IPSR_GPSR(IP6_3_0,	VI4_DATA21),
+	PINMUX_IPSR_GPSR(IP6_3_0,	VI5_DATA5),
+
+	PINMUX_IPSR_GPSR(IP6_7_4,	D6),
+	PINMUX_IPSR_MSEL(IP6_7_4,	MSIOF2_RXD_B,		SEL_MSIOF2_1),
+	PINMUX_IPSR_GPSR(IP6_7_4,	VI4_DATA22),
+	PINMUX_IPSR_GPSR(IP6_7_4,	VI5_DATA6),
+
+	PINMUX_IPSR_GPSR(IP6_11_8,	D7),
+	PINMUX_IPSR_MSEL(IP6_11_8,	MSIOF2_TXD_B,		SEL_MSIOF2_1),
+	PINMUX_IPSR_GPSR(IP6_11_8,	VI4_DATA23),
+	PINMUX_IPSR_GPSR(IP6_11_8,	VI5_DATA7),
+
+	PINMUX_IPSR_GPSR(IP6_15_12,	D8),
+	PINMUX_IPSR_GPSR(IP6_15_12,	LCDOUT0),
+	PINMUX_IPSR_MSEL(IP6_15_12,	MSIOF2_SCK_D,		SEL_MSIOF2_3),
+	PINMUX_IPSR_MSEL(IP6_15_12,	SCK4_C,			SEL_SCIF4_2),
+	PINMUX_IPSR_MSEL(IP6_15_12,	VI4_DATA0_A,		SEL_VIN4_0),
+	PINMUX_IPSR_GPSR(IP6_15_12,	DU_DR0),
+
+	PINMUX_IPSR_GPSR(IP6_19_16,	D9),
+	PINMUX_IPSR_GPSR(IP6_19_16,	LCDOUT1),
+	PINMUX_IPSR_MSEL(IP6_19_16,	MSIOF2_SYNC_D,		SEL_MSIOF2_3),
+	PINMUX_IPSR_MSEL(IP6_19_16,	VI4_DATA1_A,		SEL_VIN4_0),
+	PINMUX_IPSR_GPSR(IP6_19_16,	DU_DR1),
+
+	PINMUX_IPSR_GPSR(IP6_23_20,	D10),
+	PINMUX_IPSR_GPSR(IP6_23_20,	LCDOUT2),
+	PINMUX_IPSR_MSEL(IP6_23_20,	MSIOF2_RXD_D,		SEL_MSIOF2_3),
+	PINMUX_IPSR_MSEL(IP6_23_20,	HRX3_B,			SEL_HSCIF3_1),
+	PINMUX_IPSR_MSEL(IP6_23_20,	VI4_DATA2_A,		SEL_VIN4_0),
+	PINMUX_IPSR_MSEL(IP6_23_20,	CTS4_N_C,		SEL_SCIF4_2),
+	PINMUX_IPSR_GPSR(IP6_23_20,	DU_DR2),
+
+	PINMUX_IPSR_GPSR(IP6_27_24,	D11),
+	PINMUX_IPSR_GPSR(IP6_27_24,	LCDOUT3),
+	PINMUX_IPSR_MSEL(IP6_27_24,	MSIOF2_TXD_D,		SEL_MSIOF2_3),
+	PINMUX_IPSR_MSEL(IP6_27_24,	HTX3_B,			SEL_HSCIF3_1),
+	PINMUX_IPSR_MSEL(IP6_27_24,	VI4_DATA3_A,		SEL_VIN4_0),
+	PINMUX_IPSR_MSEL(IP6_27_24,	RTS4_N_TANS_C,		SEL_SCIF4_2),
+	PINMUX_IPSR_GPSR(IP6_27_24,	DU_DR3),
+
+	PINMUX_IPSR_GPSR(IP6_31_28,	D12),
+	PINMUX_IPSR_GPSR(IP6_31_28,	LCDOUT4),
+	PINMUX_IPSR_MSEL(IP6_31_28,	MSIOF2_SS1_D,		SEL_MSIOF2_3),
+	PINMUX_IPSR_MSEL(IP6_31_28,	RX4_C,			SEL_SCIF4_2),
+	PINMUX_IPSR_MSEL(IP6_31_28,	VI4_DATA4_A,		SEL_VIN4_0),
+	PINMUX_IPSR_GPSR(IP6_31_28,	DU_DR4),
+
+	/* IPSR7 */
+	PINMUX_IPSR_GPSR(IP7_3_0,	D13),
+	PINMUX_IPSR_GPSR(IP7_3_0,	LCDOUT5),
+	PINMUX_IPSR_MSEL(IP7_3_0,	MSIOF2_SS2_D,		SEL_MSIOF2_3),
+	PINMUX_IPSR_MSEL(IP7_3_0,	TX4_C,			SEL_SCIF4_2),
+	PINMUX_IPSR_MSEL(IP7_3_0,	VI4_DATA5_A,		SEL_VIN4_0),
+	PINMUX_IPSR_GPSR(IP7_3_0,	DU_DR5),
+
+	PINMUX_IPSR_GPSR(IP7_7_4,	D14),
+	PINMUX_IPSR_GPSR(IP7_7_4,	LCDOUT6),
+	PINMUX_IPSR_MSEL(IP7_7_4,	MSIOF3_SS1_A,		SEL_MSIOF3_0),
+	PINMUX_IPSR_MSEL(IP7_7_4,	HRX3_C,			SEL_HSCIF3_2),
+	PINMUX_IPSR_MSEL(IP7_7_4,	VI4_DATA6_A,		SEL_VIN4_0),
+	PINMUX_IPSR_GPSR(IP7_7_4,	DU_DR6),
+	PINMUX_IPSR_MSEL(IP7_7_4,	SCL6_C,			SEL_I2C6_2),
+
+	PINMUX_IPSR_GPSR(IP7_11_8,	D15),
+	PINMUX_IPSR_GPSR(IP7_11_8,	LCDOUT7),
+	PINMUX_IPSR_MSEL(IP7_11_8,	MSIOF3_SS2_A,		SEL_MSIOF3_0),
+	PINMUX_IPSR_MSEL(IP7_11_8,	HTX3_C,			SEL_HSCIF3_2),
+	PINMUX_IPSR_MSEL(IP7_11_8,	VI4_DATA7_A,		SEL_VIN4_0),
+	PINMUX_IPSR_GPSR(IP7_11_8,	DU_DR7),
+	PINMUX_IPSR_MSEL(IP7_11_8,	SDA6_C,			SEL_I2C6_2),
+
+	PINMUX_IPSR_GPSR(IP7_15_12,	FSCLKST),
+
+	PINMUX_IPSR_GPSR(IP7_19_16,	SD0_CLK),
+	PINMUX_IPSR_MSEL(IP7_19_16,	MSIOF1_SCK_E,		SEL_MSIOF1_4),
+	PINMUX_IPSR_MSEL(IP7_19_16,	STP_OPWM_0_B,		SEL_SSP1_0_1),
+
+	PINMUX_IPSR_GPSR(IP7_23_20,	SD0_CMD),
+	PINMUX_IPSR_MSEL(IP7_23_20,	MSIOF1_SYNC_E,		SEL_MSIOF1_4),
+	PINMUX_IPSR_MSEL(IP7_23_20,	STP_IVCXO27_0_B,	SEL_SSP1_0_1),
+
+	PINMUX_IPSR_GPSR(IP7_27_24,	SD0_DAT0),
+	PINMUX_IPSR_MSEL(IP7_27_24,	MSIOF1_RXD_E,		SEL_MSIOF1_4),
+	PINMUX_IPSR_MSEL(IP7_27_24,	TS_SCK0_B,		SEL_TSIF0_1),
+	PINMUX_IPSR_MSEL(IP7_27_24,	STP_ISCLK_0_B,		SEL_SSP1_0_1),
+
+	PINMUX_IPSR_GPSR(IP7_31_28,	SD0_DAT1),
+	PINMUX_IPSR_MSEL(IP7_31_28,	MSIOF1_TXD_E,		SEL_MSIOF1_4),
+	PINMUX_IPSR_MSEL(IP7_31_28,	TS_SPSYNC0_B,		SEL_TSIF0_1),
+	PINMUX_IPSR_MSEL(IP7_31_28,	STP_ISSYNC_0_B,		SEL_SSP1_0_1),
+
+	/* IPSR8 */
+	PINMUX_IPSR_GPSR(IP8_3_0,	SD0_DAT2),
+	PINMUX_IPSR_MSEL(IP8_3_0,	MSIOF1_SS1_E,		SEL_MSIOF1_4),
+	PINMUX_IPSR_MSEL(IP8_3_0,	TS_SDAT0_B,		SEL_TSIF0_1),
+	PINMUX_IPSR_MSEL(IP8_3_0,	STP_ISD_0_B,		SEL_SSP1_0_1),
+
+	PINMUX_IPSR_GPSR(IP8_7_4,	SD0_DAT3),
+	PINMUX_IPSR_MSEL(IP8_7_4,	MSIOF1_SS2_E,		SEL_MSIOF1_4),
+	PINMUX_IPSR_MSEL(IP8_7_4,	TS_SDEN0_B,		SEL_TSIF0_1),
+	PINMUX_IPSR_MSEL(IP8_7_4,	STP_ISEN_0_B,		SEL_SSP1_0_1),
+
+	PINMUX_IPSR_GPSR(IP8_11_8,	SD1_CLK),
+	PINMUX_IPSR_MSEL(IP8_11_8,	MSIOF1_SCK_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_11_8,	SIM0_CLK_A,		SEL_SIMCARD_0),
+
+	PINMUX_IPSR_GPSR(IP8_15_12,	SD1_CMD),
+	PINMUX_IPSR_MSEL(IP8_15_12,	MSIOF1_SYNC_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_15_12,	SIM0_D_A,		SEL_SIMCARD_0),
+	PINMUX_IPSR_MSEL(IP8_15_12,	STP_IVCXO27_1_B,	SEL_SSP1_1_1),
+
+	PINMUX_IPSR_GPSR(IP8_19_16,	SD1_DAT0),
+	PINMUX_IPSR_GPSR(IP8_19_16,	SD2_DAT4),
+	PINMUX_IPSR_MSEL(IP8_19_16,	MSIOF1_RXD_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_19_16,	TS_SCK1_B,		SEL_TSIF1_1),
+	PINMUX_IPSR_MSEL(IP8_19_16,	STP_ISCLK_1_B,		SEL_SSP1_1_1),
+
+	PINMUX_IPSR_GPSR(IP8_23_20,	SD1_DAT1),
+	PINMUX_IPSR_GPSR(IP8_23_20,	SD2_DAT5),
+	PINMUX_IPSR_MSEL(IP8_23_20,	MSIOF1_TXD_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_23_20,	TS_SPSYNC1_B,		SEL_TSIF1_1),
+	PINMUX_IPSR_MSEL(IP8_23_20,	STP_ISSYNC_1_B,		SEL_SSP1_1_1),
+
+	PINMUX_IPSR_GPSR(IP8_27_24,	SD1_DAT2),
+	PINMUX_IPSR_GPSR(IP8_27_24,	SD2_DAT6),
+	PINMUX_IPSR_MSEL(IP8_27_24,	MSIOF1_SS1_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_27_24,	TS_SDAT1_B,		SEL_TSIF1_1),
+	PINMUX_IPSR_MSEL(IP8_27_24,	STP_ISD_1_B,		SEL_SSP1_1_1),
+
+	PINMUX_IPSR_GPSR(IP8_31_28,	SD1_DAT3),
+	PINMUX_IPSR_GPSR(IP8_31_28,	SD2_DAT7),
+	PINMUX_IPSR_MSEL(IP8_31_28,	MSIOF1_SS2_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_31_28,	TS_SDEN1_B,		SEL_TSIF1_1),
+	PINMUX_IPSR_MSEL(IP8_31_28,	STP_ISEN_1_B,		SEL_SSP1_1_1),
+
+	/* IPSR9 */
+	PINMUX_IPSR_GPSR(IP9_3_0,	SD2_CLK),
+
+	PINMUX_IPSR_GPSR(IP9_7_4,	SD2_DAT0),
+
+	PINMUX_IPSR_GPSR(IP9_11_8,	SD2_DAT1),
+
+	PINMUX_IPSR_GPSR(IP9_15_12,	SD2_DAT2),
+
+	PINMUX_IPSR_GPSR(IP9_19_16,	SD2_DAT3),
+
+	PINMUX_IPSR_GPSR(IP9_23_20,	SD2_DS),
+	PINMUX_IPSR_MSEL(IP9_23_20,	SATA_DEVSLP_B,		SEL_SATA_1),
+
+	PINMUX_IPSR_GPSR(IP9_27_24,	SD3_DAT4),
+	PINMUX_IPSR_MSEL(IP9_27_24,	SD2_CD_A,		SEL_SDHI2_0),
+
+	PINMUX_IPSR_GPSR(IP9_31_28,	SD3_DAT5),
+	PINMUX_IPSR_MSEL(IP9_31_28,	SD2_WP_A,		SEL_SDHI2_0),
+
+	/* IPSR10 */
+	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_DAT6),
+	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_CD),
+
+	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_DAT7),
+	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_WP),
+
+	PINMUX_IPSR_GPSR(IP10_11_8,	SD0_CD),
+	PINMUX_IPSR_MSEL(IP10_11_8,	SCL2_B,			SEL_I2C2_1),
+	PINMUX_IPSR_MSEL(IP10_11_8,	SIM0_RST_A,		SEL_SIMCARD_0),
+
+	PINMUX_IPSR_GPSR(IP10_15_12,	SD0_WP),
+	PINMUX_IPSR_MSEL(IP10_15_12,	SDA2_B,			SEL_I2C2_1),
+
+	PINMUX_IPSR_GPSR(IP10_19_16,	SD1_CD),
+	PINMUX_IPSR_MSEL(IP10_19_16,	SIM0_CLK_B,		SEL_SIMCARD_1),
+
+	PINMUX_IPSR_GPSR(IP10_23_20,	SD1_WP),
+	PINMUX_IPSR_MSEL(IP10_23_20,	SIM0_D_B,		SEL_SIMCARD_1),
+
+	PINMUX_IPSR_GPSR(IP10_27_24,	SCK0),
+	PINMUX_IPSR_MSEL(IP10_27_24,	HSCK1_B,		SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP10_27_24,	MSIOF1_SS2_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP10_27_24,	AUDIO_CLKC_B,		SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP10_27_24,	SDA2_A,			SEL_I2C2_0),
+	PINMUX_IPSR_MSEL(IP10_27_24,	SIM0_RST_B,		SEL_SIMCARD_1),
+	PINMUX_IPSR_MSEL(IP10_27_24,	STP_OPWM_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP10_27_24,	RIF0_CLK_B,		SEL_DRIF0_1),
+	PINMUX_IPSR_GPSR(IP10_27_24,	ADICHS2),
+
+	PINMUX_IPSR_GPSR(IP10_31_28,	RX0),
+	PINMUX_IPSR_MSEL(IP10_31_28,	HRX1_B,			SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP10_31_28,	TS_SCK0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP10_31_28,	STP_ISCLK_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP10_31_28,	RIF0_D0_B,		SEL_DRIF0_1),
+
+	/* IPSR11 */
+	PINMUX_IPSR_GPSR(IP11_3_0,	TX0),
+	PINMUX_IPSR_MSEL(IP11_3_0,	HTX1_B,			SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP11_3_0,	TS_SPSYNC0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP11_3_0,	STP_ISSYNC_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP11_3_0,	RIF0_D1_B,		SEL_DRIF0_1),
+
+	PINMUX_IPSR_GPSR(IP11_7_4,	CTS0_N),
+	PINMUX_IPSR_MSEL(IP11_7_4,	HCTS1_N_B,		SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP11_7_4,	MSIOF1_SYNC_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP11_7_4,	TS_SPSYNC1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP11_7_4,	STP_ISSYNC_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP11_7_4,	RIF1_SYNC_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_MSEL(IP11_7_4,	AUDIO_CLKOUT_C,		SEL_ADG_2),
+	PINMUX_IPSR_GPSR(IP11_7_4,	ADICS_SAMP),
+
+	PINMUX_IPSR_GPSR(IP11_11_8,	RTS0_N_TANS),
+	PINMUX_IPSR_MSEL(IP11_11_8,	HRTS1_N_B,		SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP11_11_8,	MSIOF1_SS1_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP11_11_8,	AUDIO_CLKA_B,		SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP11_11_8,	SCL2_A,			SEL_I2C2_0),
+	PINMUX_IPSR_MSEL(IP11_11_8,	STP_IVCXO27_1_C,	SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP11_11_8,	RIF0_SYNC_B,		SEL_DRIF0_1),
+	PINMUX_IPSR_GPSR(IP11_11_8,	ADICHS1),
+
+	PINMUX_IPSR_MSEL(IP11_15_12,	RX1_A,			SEL_SCIF1_0),
+	PINMUX_IPSR_MSEL(IP11_15_12,	HRX1_A,			SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP11_15_12,	TS_SDAT0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP11_15_12,	STP_ISD_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP11_15_12,	RIF1_CLK_C,		SEL_DRIF1_2),
+
+	PINMUX_IPSR_MSEL(IP11_19_16,	TX1_A,			SEL_SCIF1_0),
+	PINMUX_IPSR_MSEL(IP11_19_16,	HTX1_A,			SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP11_19_16,	TS_SDEN0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP11_19_16,	STP_ISEN_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP11_19_16,	RIF1_D0_C,		SEL_DRIF1_2),
+
+	PINMUX_IPSR_GPSR(IP11_23_20,	CTS1_N),
+	PINMUX_IPSR_MSEL(IP11_23_20,	HCTS1_N_A,		SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP11_23_20,	MSIOF1_RXD_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP11_23_20,	TS_SDEN1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP11_23_20,	STP_ISEN_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP11_23_20,	RIF1_D0_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP11_23_20,	ADIDATA),
+
+	PINMUX_IPSR_GPSR(IP11_27_24,	RTS1_N_TANS),
+	PINMUX_IPSR_MSEL(IP11_27_24,	HRTS1_N_A,		SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP11_27_24,	MSIOF1_TXD_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP11_27_24,	TS_SDAT1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP11_27_24,	STP_ISD_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP11_27_24,	RIF1_D1_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP11_27_24,	ADICHS0),
+
+	PINMUX_IPSR_GPSR(IP11_31_28,	SCK2),
+	PINMUX_IPSR_MSEL(IP11_31_28,	SCIF_CLK_B,		SEL_SCIF1_1),
+	PINMUX_IPSR_MSEL(IP11_31_28,	MSIOF1_SCK_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP11_31_28,	TS_SCK1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP11_31_28,	STP_ISCLK_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP11_31_28,	RIF1_CLK_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP11_31_28,	ADICLK),
+
+	/* IPSR12 */
+	PINMUX_IPSR_MSEL(IP12_3_0,	TX2_A,			SEL_SCIF2_0),
+	PINMUX_IPSR_MSEL(IP12_3_0,	SD2_CD_B,		SEL_SDHI2_1),
+	PINMUX_IPSR_MSEL(IP12_3_0,	SCL1_A,			SEL_I2C1_0),
+	PINMUX_IPSR_MSEL(IP12_3_0,	FMCLK_A,		SEL_FM_0),
+	PINMUX_IPSR_MSEL(IP12_3_0,	RIF1_D1_C,		SEL_DRIF1_2),
+	PINMUX_IPSR_MSEL(IP12_3_0,	FSO_CFE_0_B,		SEL_FSO_1),
+
+	PINMUX_IPSR_MSEL(IP12_7_4,	RX2_A,			SEL_SCIF2_0),
+	PINMUX_IPSR_MSEL(IP12_7_4,	SD2_WP_B,		SEL_SDHI2_1),
+	PINMUX_IPSR_MSEL(IP12_7_4,	SDA1_A,			SEL_I2C1_0),
+	PINMUX_IPSR_MSEL(IP12_7_4,	FMIN_A,			SEL_FM_0),
+	PINMUX_IPSR_MSEL(IP12_7_4,	RIF1_SYNC_C,		SEL_DRIF1_2),
+	PINMUX_IPSR_MSEL(IP12_7_4,	FSO_CFE_1_B,		SEL_FSO_1),
+
+	PINMUX_IPSR_GPSR(IP12_11_8,	HSCK0),
+	PINMUX_IPSR_MSEL(IP12_11_8,	MSIOF1_SCK_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP12_11_8,	AUDIO_CLKB_A,		SEL_ADG_0),
+	PINMUX_IPSR_MSEL(IP12_11_8,	SSI_SDATA1_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP12_11_8,	TS_SCK0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP12_11_8,	STP_ISCLK_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP12_11_8,	RIF0_CLK_C,		SEL_DRIF0_2),
+
+	PINMUX_IPSR_GPSR(IP12_15_12,	HRX0),
+	PINMUX_IPSR_MSEL(IP12_15_12,	MSIOF1_RXD_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP12_15_12,	SSI_SDATA2_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP12_15_12,	TS_SDEN0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP12_15_12,	STP_ISEN_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP12_15_12,	RIF0_D0_C,		SEL_DRIF0_2),
+
+	PINMUX_IPSR_GPSR(IP12_19_16,	HTX0),
+	PINMUX_IPSR_MSEL(IP12_19_16,	MSIOF1_TXD_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP12_19_16,	SSI_SDATA9_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP12_19_16,	TS_SDAT0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP12_19_16,	STP_ISD_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP12_19_16,	RIF0_D1_C,		SEL_DRIF0_2),
+
+	PINMUX_IPSR_GPSR(IP12_23_20,	HCTS0_N),
+	PINMUX_IPSR_MSEL(IP12_23_20,	RX2_B,			SEL_SCIF2_1),
+	PINMUX_IPSR_MSEL(IP12_23_20,	MSIOF1_SYNC_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP12_23_20,	SSI_SCK9_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP12_23_20,	TS_SPSYNC0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP12_23_20,	STP_ISSYNC_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP12_23_20,	RIF0_SYNC_C,		SEL_DRIF0_2),
+	PINMUX_IPSR_MSEL(IP12_23_20,	AUDIO_CLKOUT1_A,	SEL_ADG_0),
+
+	PINMUX_IPSR_GPSR(IP12_27_24,	HRTS0_N),
+	PINMUX_IPSR_MSEL(IP12_27_24,	TX2_B,			SEL_SCIF2_1),
+	PINMUX_IPSR_MSEL(IP12_27_24,	MSIOF1_SS1_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP12_27_24,	SSI_WS9_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP12_27_24,	STP_IVCXO27_0_D,	SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP12_27_24,	BPFCLK_A,		SEL_FM_0),
+	PINMUX_IPSR_MSEL(IP12_27_24,	AUDIO_CLKOUT2_A,	SEL_ADG_0),
+
+	PINMUX_IPSR_GPSR(IP12_31_28,	MSIOF0_SYNC),
+	PINMUX_IPSR_MSEL(IP12_31_28,	AUDIO_CLKOUT_A,		SEL_ADG_0),
+
+	/* IPSR13 */
+	PINMUX_IPSR_GPSR(IP13_3_0,	MSIOF0_SS1),
+	PINMUX_IPSR_GPSR(IP13_3_0,	RX5),
+	PINMUX_IPSR_MSEL(IP13_3_0,	AUDIO_CLKA_C,		SEL_ADG_2),
+	PINMUX_IPSR_MSEL(IP13_3_0,	SSI_SCK2_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP13_3_0,	STP_IVCXO27_0_C,	SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP13_3_0,	AUDIO_CLKOUT3_A,	SEL_ADG_0),
+	PINMUX_IPSR_MSEL(IP13_3_0,	TCLK1_B,		SEL_TIMER_TMU_1),
+
+	PINMUX_IPSR_GPSR(IP13_7_4,	MSIOF0_SS2),
+	PINMUX_IPSR_GPSR(IP13_7_4,	TX5),
+	PINMUX_IPSR_MSEL(IP13_7_4,	MSIOF1_SS2_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP13_7_4,	AUDIO_CLKC_A,		SEL_ADG_0),
+	PINMUX_IPSR_MSEL(IP13_7_4,	SSI_WS2_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP13_7_4,	STP_OPWM_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP13_7_4,	AUDIO_CLKOUT_D,		SEL_ADG_3),
+	PINMUX_IPSR_MSEL(IP13_7_4,	SPEEDIN_B,		SEL_SPEED_PULSE_1),
+
+	PINMUX_IPSR_GPSR(IP13_11_8,	MLB_CLK),
+	PINMUX_IPSR_MSEL(IP13_11_8,	MSIOF1_SCK_F,		SEL_MSIOF1_5),
+	PINMUX_IPSR_MSEL(IP13_11_8,	SCL1_B,			SEL_I2C1_1),
+
+	PINMUX_IPSR_GPSR(IP13_15_12,	MLB_SIG),
+	PINMUX_IPSR_MSEL(IP13_15_12,	RX1_B,			SEL_SCIF1_1),
+	PINMUX_IPSR_MSEL(IP13_15_12,	MSIOF1_SYNC_F,		SEL_MSIOF1_5),
+	PINMUX_IPSR_MSEL(IP13_15_12,	SDA1_B,			SEL_I2C1_1),
+
+	PINMUX_IPSR_GPSR(IP13_19_16,	MLB_DAT),
+	PINMUX_IPSR_MSEL(IP13_19_16,	TX1_B,			SEL_SCIF1_1),
+	PINMUX_IPSR_MSEL(IP13_19_16,	MSIOF1_RXD_F,		SEL_MSIOF1_5),
+
+	PINMUX_IPSR_GPSR(IP13_23_20,	SSI_SCK01239),
+	PINMUX_IPSR_MSEL(IP13_23_20,	MSIOF1_TXD_F,		SEL_MSIOF1_5),
+
+	PINMUX_IPSR_GPSR(IP13_27_24,	SSI_WS01239),
+	PINMUX_IPSR_MSEL(IP13_27_24,	MSIOF1_SS1_F,		SEL_MSIOF1_5),
+
+	PINMUX_IPSR_GPSR(IP13_31_28,	SSI_SDATA0),
+	PINMUX_IPSR_MSEL(IP13_31_28,	MSIOF1_SS2_F,		SEL_MSIOF1_5),
+
+	/* IPSR14 */
+	PINMUX_IPSR_MSEL(IP14_3_0,	SSI_SDATA1_A,		SEL_SSI_0),
+
+	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_SDATA2_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_SCK1_B,		SEL_SSI_1),
+
+	PINMUX_IPSR_GPSR(IP14_11_8,	SSI_SCK34),
+	PINMUX_IPSR_MSEL(IP14_11_8,	MSIOF1_SS1_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP14_11_8,	STP_OPWM_0_A,		SEL_SSP1_0_0),
+
+	PINMUX_IPSR_GPSR(IP14_15_12,	SSI_WS34),
+	PINMUX_IPSR_MSEL(IP14_15_12,	HCTS2_N_A,		SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP14_15_12,	MSIOF1_SS2_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP14_15_12,	STP_IVCXO27_0_A,	SEL_SSP1_0_0),
+
+	PINMUX_IPSR_GPSR(IP14_19_16,	SSI_SDATA3),
+	PINMUX_IPSR_MSEL(IP14_19_16,	HRTS2_N_A,		SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP14_19_16,	MSIOF1_TXD_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP14_19_16,	TS_SCK0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP14_19_16,	STP_ISCLK_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP14_19_16,	RIF0_D1_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP14_19_16,	RIF2_D0_A,		SEL_DRIF2_0),
+
+	PINMUX_IPSR_GPSR(IP14_23_20,	SSI_SCK4),
+	PINMUX_IPSR_MSEL(IP14_23_20,	HRX2_A,			SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP14_23_20,	MSIOF1_SCK_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP14_23_20,	TS_SDAT0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP14_23_20,	STP_ISD_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP14_23_20,	RIF0_CLK_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP14_23_20,	RIF2_CLK_A,		SEL_DRIF2_0),
+
+	PINMUX_IPSR_GPSR(IP14_27_24,	SSI_WS4),
+	PINMUX_IPSR_MSEL(IP14_27_24,	HTX2_A,			SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP14_27_24,	MSIOF1_SYNC_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP14_27_24,	TS_SDEN0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP14_27_24,	STP_ISEN_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP14_27_24,	RIF0_SYNC_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP14_27_24,	RIF2_SYNC_A,		SEL_DRIF2_0),
+
+	PINMUX_IPSR_GPSR(IP14_31_28,	SSI_SDATA4),
+	PINMUX_IPSR_MSEL(IP14_31_28,	HSCK2_A,		SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP14_31_28,	MSIOF1_RXD_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP14_31_28,	TS_SPSYNC0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP14_31_28,	STP_ISSYNC_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP14_31_28,	RIF0_D0_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP14_31_28,	RIF2_D1_A,		SEL_DRIF2_0),
+
+	/* IPSR15 */
+	PINMUX_IPSR_GPSR(IP15_3_0,	SSI_SCK6),
+	PINMUX_IPSR_GPSR(IP15_3_0,	USB2_PWEN),
+	PINMUX_IPSR_MSEL(IP15_3_0,	SIM0_RST_D,		SEL_SIMCARD_3),
+
+	PINMUX_IPSR_GPSR(IP15_7_4,	SSI_WS6),
+	PINMUX_IPSR_GPSR(IP15_7_4,	USB2_OVC),
+	PINMUX_IPSR_MSEL(IP15_7_4,	SIM0_D_D,		SEL_SIMCARD_3),
+
+	PINMUX_IPSR_GPSR(IP15_11_8,	SSI_SDATA6),
+	PINMUX_IPSR_MSEL(IP15_11_8,	SIM0_CLK_D,		SEL_SIMCARD_3),
+	PINMUX_IPSR_MSEL(IP15_11_8,	SATA_DEVSLP_A,		SEL_SATA_0),
+
+	PINMUX_IPSR_GPSR(IP15_15_12,	SSI_SCK78),
+	PINMUX_IPSR_MSEL(IP15_15_12,	HRX2_B,			SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP15_15_12,	MSIOF1_SCK_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP15_15_12,	TS_SCK1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP15_15_12,	STP_ISCLK_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP15_15_12,	RIF1_CLK_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP15_15_12,	RIF3_CLK_A,		SEL_DRIF3_0),
+
+	PINMUX_IPSR_GPSR(IP15_19_16,	SSI_WS78),
+	PINMUX_IPSR_MSEL(IP15_19_16,	HTX2_B,			SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP15_19_16,	MSIOF1_SYNC_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP15_19_16,	TS_SDAT1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	STP_ISD_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	RIF1_SYNC_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	RIF3_SYNC_A,		SEL_DRIF3_0),
+
+	PINMUX_IPSR_GPSR(IP15_23_20,	SSI_SDATA7),
+	PINMUX_IPSR_MSEL(IP15_23_20,	HCTS2_N_B,		SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP15_23_20,	MSIOF1_RXD_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP15_23_20,	TS_SDEN1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	STP_ISEN_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	RIF1_D0_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	RIF3_D0_A,		SEL_DRIF3_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	TCLK2_A,		SEL_TIMER_TMU_0),
+
+	PINMUX_IPSR_GPSR(IP15_27_24,	SSI_SDATA8),
+	PINMUX_IPSR_MSEL(IP15_27_24,	HRTS2_N_B,		SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP15_27_24,	MSIOF1_TXD_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP15_27_24,	TS_SPSYNC1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	STP_ISSYNC_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	RIF1_D1_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	RIF3_D1_A,		SEL_DRIF3_0),
+
+	PINMUX_IPSR_MSEL(IP15_31_28,	SSI_SDATA9_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	HSCK2_B,		SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP15_31_28,	MSIOF1_SS1_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP15_31_28,	HSCK1_A,		SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	SSI_WS1_B,		SEL_SSI_1),
+	PINMUX_IPSR_GPSR(IP15_31_28,	SCK1),
+	PINMUX_IPSR_MSEL(IP15_31_28,	STP_IVCXO27_1_A,	SEL_SSP1_1_0),
+	PINMUX_IPSR_GPSR(IP15_31_28,	SCK5),
+
+	/* IPSR16 */
+	PINMUX_IPSR_MSEL(IP16_3_0,	AUDIO_CLKA_A,		SEL_ADG_0),
+	PINMUX_IPSR_GPSR(IP16_3_0,	CC5_OSCOUT),
+
+	PINMUX_IPSR_MSEL(IP16_7_4,	AUDIO_CLKB_B,		SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP16_7_4,	SCIF_CLK_A,		SEL_SCIF1_0),
+	PINMUX_IPSR_MSEL(IP16_7_4,	STP_IVCXO27_1_D,	SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP16_7_4,	REMOCON_A,		SEL_REMOCON_0),
+	PINMUX_IPSR_MSEL(IP16_7_4,	TCLK1_A,		SEL_TIMER_TMU_0),
+
+	PINMUX_IPSR_GPSR(IP16_11_8,	USB0_PWEN),
+	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_RST_C,		SEL_SIMCARD_2),
+	PINMUX_IPSR_MSEL(IP16_11_8,	TS_SCK1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP16_11_8,	STP_ISCLK_1_D,		SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP16_11_8,	BPFCLK_B,		SEL_FM_1),
+	PINMUX_IPSR_MSEL(IP16_11_8,	RIF3_CLK_B,		SEL_DRIF3_1),
+
+	PINMUX_IPSR_GPSR(IP16_15_12,	USB0_OVC),
+	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_D_C,		SEL_SIMCARD_2),
+	PINMUX_IPSR_MSEL(IP16_11_8,	TS_SDAT1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP16_11_8,	STP_ISD_1_D,		SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP16_11_8,	RIF3_SYNC_B,		SEL_DRIF3_1),
+
+	PINMUX_IPSR_GPSR(IP16_19_16,	USB1_PWEN),
+	PINMUX_IPSR_MSEL(IP16_19_16,	SIM0_CLK_C,		SEL_SIMCARD_2),
+	PINMUX_IPSR_MSEL(IP16_19_16,	SSI_SCK1_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP16_19_16,	TS_SCK0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP16_19_16,	STP_ISCLK_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP16_19_16,	FMCLK_B,		SEL_FM_1),
+	PINMUX_IPSR_MSEL(IP16_19_16,	RIF2_CLK_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_MSEL(IP16_19_16,	SPEEDIN_A,		SEL_SPEED_PULSE_0),
+
+	PINMUX_IPSR_GPSR(IP16_23_20,	USB1_OVC),
+	PINMUX_IPSR_MSEL(IP16_23_20,	MSIOF1_SS2_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP16_23_20,	SSI_WS1_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP16_23_20,	TS_SDAT0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP16_23_20,	STP_ISD_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP16_23_20,	FMIN_B,			SEL_FM_1),
+	PINMUX_IPSR_MSEL(IP16_23_20,	RIF2_SYNC_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_MSEL(IP16_23_20,	REMOCON_B,		SEL_REMOCON_1),
+
+	PINMUX_IPSR_GPSR(IP16_27_24,	USB30_PWEN),
+	PINMUX_IPSR_MSEL(IP16_27_24,	AUDIO_CLKOUT_B,		SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP16_27_24,	SSI_SCK2_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP16_27_24,	TS_SDEN1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP16_27_24,	STP_ISEN_1_D,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP16_27_24,	STP_OPWM_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP16_27_24,	RIF3_D0_B,		SEL_DRIF3_1),
+	PINMUX_IPSR_MSEL(IP16_27_24,	TCLK2_B,		SEL_TIMER_TMU_1),
+	PINMUX_IPSR_GPSR(IP16_27_24,	TPU0TO0),
+
+	PINMUX_IPSR_GPSR(IP16_31_28,	USB30_OVC),
+	PINMUX_IPSR_MSEL(IP16_31_28,	AUDIO_CLKOUT1_B,	SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP16_31_28,	SSI_WS2_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP16_31_28,	TS_SPSYNC1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP16_31_28,	STP_ISSYNC_1_D,		SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP16_31_28,	STP_IVCXO27_0_E,	SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP16_31_28,	RIF3_D1_B,		SEL_DRIF3_1),
+	PINMUX_IPSR_MSEL(IP16_31_28,	FSO_TOE_B,		SEL_FSO_1),
+	PINMUX_IPSR_GPSR(IP16_31_28,	TPU0TO1),
+
+	/* IPSR17 */
+	PINMUX_IPSR_GPSR(IP17_3_0,	USB31_PWEN),
+	PINMUX_IPSR_MSEL(IP17_3_0,	AUDIO_CLKOUT2_B,	SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP17_3_0,	SSI_SCK9_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP17_3_0,	TS_SDEN0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP17_3_0,	STP_ISEN_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP17_3_0,	RIF2_D0_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_GPSR(IP17_3_0,	TPU0TO2),
+
+	PINMUX_IPSR_GPSR(IP17_7_4,	USB31_OVC),
+	PINMUX_IPSR_MSEL(IP17_7_4,	AUDIO_CLKOUT3_B,	SEL_ADG_1),
+	PINMUX_IPSR_MSEL(IP17_7_4,	SSI_WS9_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP17_7_4,	TS_SPSYNC0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP17_7_4,	STP_ISSYNC_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP17_7_4,	RIF2_D1_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_GPSR(IP17_7_4,	TPU0TO3),
+
+/*
+ * Static pins can not be muxed between different functions but
+ * still needs a mark entry in the pinmux list. Add each static
+ * pin to the list without an associated function. The sh-pfc
+ * core will do the right thing and skip trying to mux then pin
+ * while still applying configuration to it
+ */
+#define FM(x)	PINMUX_DATA(x##_MARK, 0),
+	PINMUX_STATIC
+#undef FM
+};
+
+/*
+ * R8A7795 has 8 banks with 32 PGIOS in each => 256 GPIOs.
+ * Physical layout rows: A - AW, cols: 1 - 39.
+ */
+#define ROW_GROUP_A(r) ('Z' - 'A' + 1 + (r))
+#define PIN_NUMBER(r, c) (((r) - 'A') * 39 + (c) + 300)
+#define PIN_A_NUMBER(r, c) PIN_NUMBER(ROW_GROUP_A(r), c)
+
+static const struct sh_pfc_pin pinmux_pins[] = {
+	PINMUX_GPIO_GP_ALL(),
+
+	/*
+	 * Pins not associated with a GPIO port.
+	 *
+	 * The pin positions are different between different r8a7795
+	 * packages, all that is needed for the pfc driver is a unique
+	 * number for each pin. To this end use the pin layout from
+	 * R-Car H3SiP to calculate a unique number for each pin.
+	 */
+	SH_PFC_PIN_NAMED_CFG('A',  8, AVB_TX_CTL, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A',  9, AVB_MDIO, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 12, AVB_TXCREFCLK, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 13, AVB_RD0, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 14, AVB_RD2, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 16, AVB_RX_CTL, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 17, AVB_TD2, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 18, AVB_TD0, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('A', 19, AVB_TXC, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('B', 13, AVB_RD1, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('B', 14, AVB_RD3, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('B', 17, AVB_TD3, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('B', 18, AVB_TD1, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('B', 19, AVB_RXC, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('C',  1, PRESETOUT#, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('F',  1, CLKOUT, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('H', 37, MLB_REF, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('V',  3, QSPI1_SPCLK, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('V',  5, QSPI1_SSL, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('V',  6, RPC_WP#, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('V',  7, RPC_RESET#, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('W',  3, QSPI0_SPCLK, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('Y',  3, QSPI0_SSL, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('Y',  6, QSPI0_IO2, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG('Y',  7, RPC_INT#, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('B'),  4, QSPI0_MISO_IO1, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('B'),  6, QSPI0_IO3, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('C'),  3, QSPI1_IO3, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('C'),  5, QSPI0_MOSI_IO0, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('C'),  7, QSPI1_MOSI_IO0, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('D'), 38, FSCLKST#, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('D'), 39, EXTALR, SH_PFC_PIN_CFG_PULL_UP | SH_PFC_PIN_CFG_PULL_DOWN),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('E'),  4, QSPI1_IO2, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('E'),  5, QSPI1_MISO_IO1, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('P'),  7, DU_DOTCLKIN0, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('P'),  8, DU_DOTCLKIN1, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('R'),  7, DU_DOTCLKIN2, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('R'),  8, DU_DOTCLKIN3, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('R'), 26, TRST#, SH_PFC_PIN_CFG_PULL_UP | SH_PFC_PIN_CFG_PULL_DOWN),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('R'), 29, TDI, SH_PFC_PIN_CFG_PULL_UP | SH_PFC_PIN_CFG_PULL_DOWN),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('R'), 30, TMS, CFG_FLAGS),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('T'), 27, TCK, SH_PFC_PIN_CFG_PULL_UP | SH_PFC_PIN_CFG_PULL_DOWN),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('T'), 28, TDO, SH_PFC_PIN_CFG_DRIVE_STRENGTH),
+	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('T'), 30, ASEBRK, CFG_FLAGS),
+};
+
+/* - AUDIO CLOCK ------------------------------------------------------------ */
+static const unsigned int audio_clk_a_a_pins[] = {
+	/* CLK A */
+	RCAR_GP_PIN(6, 22),
+};
+static const unsigned int audio_clk_a_a_mux[] = {
+	AUDIO_CLKA_A_MARK,
+};
+static const unsigned int audio_clk_a_b_pins[] = {
+	/* CLK A */
+	RCAR_GP_PIN(5, 4),
+};
+static const unsigned int audio_clk_a_b_mux[] = {
+	AUDIO_CLKA_B_MARK,
+};
+static const unsigned int audio_clk_a_c_pins[] = {
+	/* CLK A */
+	RCAR_GP_PIN(5, 19),
+};
+static const unsigned int audio_clk_a_c_mux[] = {
+	AUDIO_CLKA_C_MARK,
+};
+static const unsigned int audio_clk_b_a_pins[] = {
+	/* CLK B */
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int audio_clk_b_a_mux[] = {
+	AUDIO_CLKB_A_MARK,
+};
+static const unsigned int audio_clk_b_b_pins[] = {
+	/* CLK B */
+	RCAR_GP_PIN(6, 23),
+};
+static const unsigned int audio_clk_b_b_mux[] = {
+	AUDIO_CLKB_B_MARK,
+};
+static const unsigned int audio_clk_c_a_pins[] = {
+	/* CLK C */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int audio_clk_c_a_mux[] = {
+	AUDIO_CLKC_A_MARK,
+};
+static const unsigned int audio_clk_c_b_pins[] = {
+	/* CLK C */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int audio_clk_c_b_mux[] = {
+	AUDIO_CLKC_B_MARK,
+};
+static const unsigned int audio_clkout_a_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(5, 18),
+};
+static const unsigned int audio_clkout_a_mux[] = {
+	AUDIO_CLKOUT_A_MARK,
+};
+static const unsigned int audio_clkout_b_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(6, 28),
+};
+static const unsigned int audio_clkout_b_mux[] = {
+	AUDIO_CLKOUT_B_MARK,
+};
+static const unsigned int audio_clkout_c_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(5, 3),
+};
+static const unsigned int audio_clkout_c_mux[] = {
+	AUDIO_CLKOUT_C_MARK,
+};
+static const unsigned int audio_clkout_d_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int audio_clkout_d_mux[] = {
+	AUDIO_CLKOUT_D_MARK,
+};
+static const unsigned int audio_clkout1_a_pins[] = {
+	/* CLKOUT1 */
+	RCAR_GP_PIN(5, 15),
+};
+static const unsigned int audio_clkout1_a_mux[] = {
+	AUDIO_CLKOUT1_A_MARK,
+};
+static const unsigned int audio_clkout1_b_pins[] = {
+	/* CLKOUT1 */
+	RCAR_GP_PIN(6, 29),
+};
+static const unsigned int audio_clkout1_b_mux[] = {
+	AUDIO_CLKOUT1_B_MARK,
+};
+static const unsigned int audio_clkout2_a_pins[] = {
+	/* CLKOUT2 */
+	RCAR_GP_PIN(5, 16),
+};
+static const unsigned int audio_clkout2_a_mux[] = {
+	AUDIO_CLKOUT2_A_MARK,
+};
+static const unsigned int audio_clkout2_b_pins[] = {
+	/* CLKOUT2 */
+	RCAR_GP_PIN(6, 30),
+};
+static const unsigned int audio_clkout2_b_mux[] = {
+	AUDIO_CLKOUT2_B_MARK,
+};
+
+static const unsigned int audio_clkout3_a_pins[] = {
+	/* CLKOUT3 */
+	RCAR_GP_PIN(5, 19),
+};
+static const unsigned int audio_clkout3_a_mux[] = {
+	AUDIO_CLKOUT3_A_MARK,
+};
+static const unsigned int audio_clkout3_b_pins[] = {
+	/* CLKOUT3 */
+	RCAR_GP_PIN(6, 31),
+};
+static const unsigned int audio_clkout3_b_mux[] = {
+	AUDIO_CLKOUT3_B_MARK,
+};
+
+/* - EtherAVB --------------------------------------------------------------- */
+static const unsigned int avb_link_pins[] = {
+	/* AVB_LINK */
+	RCAR_GP_PIN(2, 12),
+};
+static const unsigned int avb_link_mux[] = {
+	AVB_LINK_MARK,
+};
+static const unsigned int avb_magic_pins[] = {
+	/* AVB_MAGIC_ */
+	RCAR_GP_PIN(2, 10),
+};
+static const unsigned int avb_magic_mux[] = {
+	AVB_MAGIC_MARK,
+};
+static const unsigned int avb_phy_int_pins[] = {
+	/* AVB_PHY_INT */
+	RCAR_GP_PIN(2, 11),
+};
+static const unsigned int avb_phy_int_mux[] = {
+	AVB_PHY_INT_MARK,
+};
+static const unsigned int avb_mdc_pins[] = {
+	/* AVB_MDC, AVB_MDIO */
+	RCAR_GP_PIN(2, 9), PIN_NUMBER('A', 9),
+};
+static const unsigned int avb_mdc_mux[] = {
+	AVB_MDC_MARK, AVB_MDIO_MARK,
+};
+static const unsigned int avb_mii_pins[] = {
+	/*
+	 * AVB_TX_CTL, AVB_TXC, AVB_TD0,
+	 * AVB_TD1, AVB_TD2, AVB_TD3,
+	 * AVB_RX_CTL, AVB_RXC, AVB_RD0,
+	 * AVB_RD1, AVB_RD2, AVB_RD3,
+	 * AVB_TXCREFCLK
+	 */
+	PIN_NUMBER('A', 8), PIN_NUMBER('A', 19), PIN_NUMBER('A', 18),
+	PIN_NUMBER('B', 18), PIN_NUMBER('A', 17), PIN_NUMBER('B', 17),
+	PIN_NUMBER('A', 16), PIN_NUMBER('B', 19), PIN_NUMBER('A', 13),
+	PIN_NUMBER('B', 13), PIN_NUMBER('A', 14), PIN_NUMBER('B', 14),
+	PIN_NUMBER('A', 12),
+
+};
+static const unsigned int avb_mii_mux[] = {
+	AVB_TX_CTL_MARK, AVB_TXC_MARK, AVB_TD0_MARK,
+	AVB_TD1_MARK, AVB_TD2_MARK, AVB_TD3_MARK,
+	AVB_RX_CTL_MARK, AVB_RXC_MARK, AVB_RD0_MARK,
+	AVB_RD1_MARK, AVB_RD2_MARK, AVB_RD3_MARK,
+	AVB_TXCREFCLK_MARK,
+};
+static const unsigned int avb_avtp_pps_pins[] = {
+	/* AVB_AVTP_PPS */
+	RCAR_GP_PIN(2, 6),
+};
+static const unsigned int avb_avtp_pps_mux[] = {
+	AVB_AVTP_PPS_MARK,
+};
+static const unsigned int avb_avtp_match_a_pins[] = {
+	/* AVB_AVTP_MATCH_A */
+	RCAR_GP_PIN(2, 13),
+};
+static const unsigned int avb_avtp_match_a_mux[] = {
+	AVB_AVTP_MATCH_A_MARK,
+};
+static const unsigned int avb_avtp_capture_a_pins[] = {
+	/* AVB_AVTP_CAPTURE_A */
+	RCAR_GP_PIN(2, 14),
+};
+static const unsigned int avb_avtp_capture_a_mux[] = {
+	AVB_AVTP_CAPTURE_A_MARK,
+};
+static const unsigned int avb_avtp_match_b_pins[] = {
+	/*  AVB_AVTP_MATCH_B */
+	RCAR_GP_PIN(1, 8),
+};
+static const unsigned int avb_avtp_match_b_mux[] = {
+	AVB_AVTP_MATCH_B_MARK,
+};
+static const unsigned int avb_avtp_capture_b_pins[] = {
+	/* AVB_AVTP_CAPTURE_B */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int avb_avtp_capture_b_mux[] = {
+	AVB_AVTP_CAPTURE_B_MARK,
+};
+
+/* - CAN ------------------------------------------------------------------ */
+static const unsigned int can0_data_a_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 23),	RCAR_GP_PIN(1, 24),
+};
+static const unsigned int can0_data_a_mux[] = {
+	CAN0_TX_A_MARK,		CAN0_RX_A_MARK,
+};
+static const unsigned int can0_data_b_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(2, 0),	RCAR_GP_PIN(2, 1),
+};
+static const unsigned int can0_data_b_mux[] = {
+	CAN0_TX_B_MARK,		CAN0_RX_B_MARK,
+};
+static const unsigned int can1_data_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 22),	RCAR_GP_PIN(1, 26),
+};
+static const unsigned int can1_data_mux[] = {
+	CAN1_TX_MARK,		CAN1_RX_MARK,
+};
+
+/* - CAN Clock -------------------------------------------------------------- */
+static const unsigned int can_clk_pins[] = {
+	/* CLK */
+	RCAR_GP_PIN(1, 25),
+};
+static const unsigned int can_clk_mux[] = {
+	CAN_CLK_MARK,
+};
+
+/* - CAN FD --------------------------------------------------------------- */
+static const unsigned int canfd0_data_a_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 23),     RCAR_GP_PIN(1, 24),
+};
+static const unsigned int canfd0_data_a_mux[] = {
+	CANFD0_TX_A_MARK,       CANFD0_RX_A_MARK,
+};
+static const unsigned int canfd0_data_b_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(2, 0),      RCAR_GP_PIN(2, 1),
+};
+static const unsigned int canfd0_data_b_mux[] = {
+	CANFD0_TX_B_MARK,       CANFD0_RX_B_MARK,
+};
+static const unsigned int canfd1_data_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 22),     RCAR_GP_PIN(1, 26),
+};
+static const unsigned int canfd1_data_mux[] = {
+	CANFD1_TX_MARK,         CANFD1_RX_MARK,
+};
+
+/* - DRIF0 --------------------------------------------------------------- */
+static const unsigned int drif0_ctrl_a_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+static const unsigned int drif0_ctrl_a_mux[] = {
+	RIF0_CLK_A_MARK, RIF0_SYNC_A_MARK,
+};
+static const unsigned int drif0_data0_a_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int drif0_data0_a_mux[] = {
+	RIF0_D0_A_MARK,
+};
+static const unsigned int drif0_data1_a_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(6, 7),
+};
+static const unsigned int drif0_data1_a_mux[] = {
+	RIF0_D1_A_MARK,
+};
+static const unsigned int drif0_ctrl_b_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 4),
+};
+static const unsigned int drif0_ctrl_b_mux[] = {
+	RIF0_CLK_B_MARK, RIF0_SYNC_B_MARK,
+};
+static const unsigned int drif0_data0_b_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(5, 1),
+};
+static const unsigned int drif0_data0_b_mux[] = {
+	RIF0_D0_B_MARK,
+};
+static const unsigned int drif0_data1_b_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(5, 2),
+};
+static const unsigned int drif0_data1_b_mux[] = {
+	RIF0_D1_B_MARK,
+};
+static const unsigned int drif0_ctrl_c_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(5, 12), RCAR_GP_PIN(5, 15),
+};
+static const unsigned int drif0_ctrl_c_mux[] = {
+	RIF0_CLK_C_MARK, RIF0_SYNC_C_MARK,
+};
+static const unsigned int drif0_data0_c_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(5, 13),
+};
+static const unsigned int drif0_data0_c_mux[] = {
+	RIF0_D0_C_MARK,
+};
+static const unsigned int drif0_data1_c_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(5, 14),
+};
+static const unsigned int drif0_data1_c_mux[] = {
+	RIF0_D1_C_MARK,
+};
+/* - DRIF1 --------------------------------------------------------------- */
+static const unsigned int drif1_ctrl_a_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+static const unsigned int drif1_ctrl_a_mux[] = {
+	RIF1_CLK_A_MARK, RIF1_SYNC_A_MARK,
+};
+static const unsigned int drif1_data0_a_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(6, 19),
+};
+static const unsigned int drif1_data0_a_mux[] = {
+	RIF1_D0_A_MARK,
+};
+static const unsigned int drif1_data1_a_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(6, 20),
+};
+static const unsigned int drif1_data1_a_mux[] = {
+	RIF1_D1_A_MARK,
+};
+static const unsigned int drif1_ctrl_b_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(5, 9), RCAR_GP_PIN(5, 3),
+};
+static const unsigned int drif1_ctrl_b_mux[] = {
+	RIF1_CLK_B_MARK, RIF1_SYNC_B_MARK,
+};
+static const unsigned int drif1_data0_b_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(5, 7),
+};
+static const unsigned int drif1_data0_b_mux[] = {
+	RIF1_D0_B_MARK,
+};
+static const unsigned int drif1_data1_b_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(5, 8),
+};
+static const unsigned int drif1_data1_b_mux[] = {
+	RIF1_D1_B_MARK,
+};
+static const unsigned int drif1_ctrl_c_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 11),
+};
+static const unsigned int drif1_ctrl_c_mux[] = {
+	RIF1_CLK_C_MARK, RIF1_SYNC_C_MARK,
+};
+static const unsigned int drif1_data0_c_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(5, 6),
+};
+static const unsigned int drif1_data0_c_mux[] = {
+	RIF1_D0_C_MARK,
+};
+static const unsigned int drif1_data1_c_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(5, 10),
+};
+static const unsigned int drif1_data1_c_mux[] = {
+	RIF1_D1_C_MARK,
+};
+/* - DRIF2 --------------------------------------------------------------- */
+static const unsigned int drif2_ctrl_a_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+static const unsigned int drif2_ctrl_a_mux[] = {
+	RIF2_CLK_A_MARK, RIF2_SYNC_A_MARK,
+};
+static const unsigned int drif2_data0_a_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(6, 7),
+};
+static const unsigned int drif2_data0_a_mux[] = {
+	RIF2_D0_A_MARK,
+};
+static const unsigned int drif2_data1_a_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int drif2_data1_a_mux[] = {
+	RIF2_D1_A_MARK,
+};
+static const unsigned int drif2_ctrl_b_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
+};
+static const unsigned int drif2_ctrl_b_mux[] = {
+	RIF2_CLK_B_MARK, RIF2_SYNC_B_MARK,
+};
+static const unsigned int drif2_data0_b_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(6, 30),
+};
+static const unsigned int drif2_data0_b_mux[] = {
+	RIF2_D0_B_MARK,
+};
+static const unsigned int drif2_data1_b_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(6, 31),
+};
+static const unsigned int drif2_data1_b_mux[] = {
+	RIF2_D1_B_MARK,
+};
+/* - DRIF3 --------------------------------------------------------------- */
+static const unsigned int drif3_ctrl_a_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+static const unsigned int drif3_ctrl_a_mux[] = {
+	RIF3_CLK_A_MARK, RIF3_SYNC_A_MARK,
+};
+static const unsigned int drif3_data0_a_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(6, 19),
+};
+static const unsigned int drif3_data0_a_mux[] = {
+	RIF3_D0_A_MARK,
+};
+static const unsigned int drif3_data1_a_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(6, 20),
+};
+static const unsigned int drif3_data1_a_mux[] = {
+	RIF3_D1_A_MARK,
+};
+static const unsigned int drif3_ctrl_b_pins[] = {
+	/* CLK, SYNC */
+	RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25),
+};
+static const unsigned int drif3_ctrl_b_mux[] = {
+	RIF3_CLK_B_MARK, RIF3_SYNC_B_MARK,
+};
+static const unsigned int drif3_data0_b_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(6, 28),
+};
+static const unsigned int drif3_data0_b_mux[] = {
+	RIF3_D0_B_MARK,
+};
+static const unsigned int drif3_data1_b_pins[] = {
+	/* D1 */
+	RCAR_GP_PIN(6, 29),
+};
+static const unsigned int drif3_data1_b_mux[] = {
+	RIF3_D1_B_MARK,
+};
+
+/* - DU --------------------------------------------------------------------- */
+static const unsigned int du_rgb666_pins[] = {
+	/* R[7:2], G[7:2], B[7:2] */
+	RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 13),
+	RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10),
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 13),
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 19), RCAR_GP_PIN(1, 18),
+	RCAR_GP_PIN(1, 7),  RCAR_GP_PIN(1, 6),  RCAR_GP_PIN(1, 5),
+	RCAR_GP_PIN(1, 4),  RCAR_GP_PIN(1, 3),  RCAR_GP_PIN(1, 2),
+};
+static const unsigned int du_rgb666_mux[] = {
+	DU_DR7_MARK, DU_DR6_MARK, DU_DR5_MARK, DU_DR4_MARK,
+	DU_DR3_MARK, DU_DR2_MARK,
+	DU_DG7_MARK, DU_DG6_MARK, DU_DG5_MARK, DU_DG4_MARK,
+	DU_DG3_MARK, DU_DG2_MARK,
+	DU_DB7_MARK, DU_DB6_MARK, DU_DB5_MARK, DU_DB4_MARK,
+	DU_DB3_MARK, DU_DB2_MARK,
+};
+static const unsigned int du_rgb888_pins[] = {
+	/* R[7:0], G[7:0], B[7:0] */
+	RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 13),
+	RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10),
+	RCAR_GP_PIN(0, 9),  RCAR_GP_PIN(0, 8),
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 13),
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 19), RCAR_GP_PIN(1, 18),
+	RCAR_GP_PIN(1, 17), RCAR_GP_PIN(1, 16),
+	RCAR_GP_PIN(1, 7),  RCAR_GP_PIN(1, 6),  RCAR_GP_PIN(1, 5),
+	RCAR_GP_PIN(1, 4),  RCAR_GP_PIN(1, 3),  RCAR_GP_PIN(1, 2),
+	RCAR_GP_PIN(1, 1),  RCAR_GP_PIN(1, 0),
+};
+static const unsigned int du_rgb888_mux[] = {
+	DU_DR7_MARK, DU_DR6_MARK, DU_DR5_MARK, DU_DR4_MARK,
+	DU_DR3_MARK, DU_DR2_MARK, DU_DR1_MARK, DU_DR0_MARK,
+	DU_DG7_MARK, DU_DG6_MARK, DU_DG5_MARK, DU_DG4_MARK,
+	DU_DG3_MARK, DU_DG2_MARK, DU_DG1_MARK, DU_DG0_MARK,
+	DU_DB7_MARK, DU_DB6_MARK, DU_DB5_MARK, DU_DB4_MARK,
+	DU_DB3_MARK, DU_DB2_MARK, DU_DB1_MARK, DU_DB0_MARK,
+};
+static const unsigned int du_clk_out_0_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(1, 27),
+};
+static const unsigned int du_clk_out_0_mux[] = {
+	DU_DOTCLKOUT0_MARK
+};
+static const unsigned int du_clk_out_1_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(2, 3),
+};
+static const unsigned int du_clk_out_1_mux[] = {
+	DU_DOTCLKOUT1_MARK
+};
+static const unsigned int du_sync_pins[] = {
+	/* EXVSYNC/VSYNC, EXHSYNC/HSYNC */
+	RCAR_GP_PIN(2, 5), RCAR_GP_PIN(2, 4),
+};
+static const unsigned int du_sync_mux[] = {
+	DU_EXVSYNC_DU_VSYNC_MARK, DU_EXHSYNC_DU_HSYNC_MARK
+};
+static const unsigned int du_oddf_pins[] = {
+	/* EXDISP/EXODDF/EXCDE */
+	RCAR_GP_PIN(2, 2),
+};
+static const unsigned int du_oddf_mux[] = {
+	DU_EXODDF_DU_ODDF_DISP_CDE_MARK,
+};
+static const unsigned int du_cde_pins[] = {
+	/* CDE */
+	RCAR_GP_PIN(2, 0),
+};
+static const unsigned int du_cde_mux[] = {
+	DU_CDE_MARK,
+};
+static const unsigned int du_disp_pins[] = {
+	/* DISP */
+	RCAR_GP_PIN(2, 1),
+};
+static const unsigned int du_disp_mux[] = {
+	DU_DISP_MARK,
+};
+/* - HSCIF0 ----------------------------------------------------------------- */
+static const unsigned int hscif0_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14),
+};
+static const unsigned int hscif0_data_mux[] = {
+	HRX0_MARK, HTX0_MARK,
+};
+static const unsigned int hscif0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int hscif0_clk_mux[] = {
+	HSCK0_MARK,
+};
+static const unsigned int hscif0_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15),
+};
+static const unsigned int hscif0_ctrl_mux[] = {
+	HRTS0_N_MARK, HCTS0_N_MARK,
+};
+/* - HSCIF1 ----------------------------------------------------------------- */
+static const unsigned int hscif1_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
+};
+static const unsigned int hscif1_data_a_mux[] = {
+	HRX1_A_MARK, HTX1_A_MARK,
+};
+static const unsigned int hscif1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int hscif1_clk_a_mux[] = {
+	HSCK1_A_MARK,
+};
+static const unsigned int hscif1_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
+};
+static const unsigned int hscif1_ctrl_a_mux[] = {
+	HRTS1_N_A_MARK, HCTS1_N_A_MARK,
+};
+
+static const unsigned int hscif1_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+static const unsigned int hscif1_data_b_mux[] = {
+	HRX1_B_MARK, HTX1_B_MARK,
+};
+static const unsigned int hscif1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int hscif1_clk_b_mux[] = {
+	HSCK1_B_MARK,
+};
+static const unsigned int hscif1_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
+};
+static const unsigned int hscif1_ctrl_b_mux[] = {
+	HRTS1_N_B_MARK, HCTS1_N_B_MARK,
+};
+/* - HSCIF2 ----------------------------------------------------------------- */
+static const unsigned int hscif2_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+static const unsigned int hscif2_data_a_mux[] = {
+	HRX2_A_MARK, HTX2_A_MARK,
+};
+static const unsigned int hscif2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int hscif2_clk_a_mux[] = {
+	HSCK2_A_MARK,
+};
+static const unsigned int hscif2_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6),
+};
+static const unsigned int hscif2_ctrl_a_mux[] = {
+	HRTS2_N_A_MARK, HCTS2_N_A_MARK,
+};
+
+static const unsigned int hscif2_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+static const unsigned int hscif2_data_b_mux[] = {
+	HRX2_B_MARK, HTX2_B_MARK,
+};
+static const unsigned int hscif2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int hscif2_clk_b_mux[] = {
+	HSCK2_B_MARK,
+};
+static const unsigned int hscif2_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19),
+};
+static const unsigned int hscif2_ctrl_b_mux[] = {
+	HRTS2_N_B_MARK, HCTS2_N_B_MARK,
+};
+/* - HSCIF3 ----------------------------------------------------------------- */
+static const unsigned int hscif3_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
+};
+static const unsigned int hscif3_data_a_mux[] = {
+	HRX3_A_MARK, HTX3_A_MARK,
+};
+static const unsigned int hscif3_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+static const unsigned int hscif3_clk_mux[] = {
+	HSCK3_MARK,
+};
+static const unsigned int hscif3_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+static const unsigned int hscif3_ctrl_mux[] = {
+	HRTS3_N_MARK, HCTS3_N_MARK,
+};
+
+static const unsigned int hscif3_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11),
+};
+static const unsigned int hscif3_data_b_mux[] = {
+	HRX3_B_MARK, HTX3_B_MARK,
+};
+static const unsigned int hscif3_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15),
+};
+static const unsigned int hscif3_data_c_mux[] = {
+	HRX3_C_MARK, HTX3_C_MARK,
+};
+static const unsigned int hscif3_data_d_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8),
+};
+static const unsigned int hscif3_data_d_mux[] = {
+	HRX3_D_MARK, HTX3_D_MARK,
+};
+/* - HSCIF4 ----------------------------------------------------------------- */
+static const unsigned int hscif4_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13),
+};
+static const unsigned int hscif4_data_a_mux[] = {
+	HRX4_A_MARK, HTX4_A_MARK,
+};
+static const unsigned int hscif4_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int hscif4_clk_mux[] = {
+	HSCK4_MARK,
+};
+static const unsigned int hscif4_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14),
+};
+static const unsigned int hscif4_ctrl_mux[] = {
+	HRTS4_N_MARK, HCTS4_N_MARK,
+};
+
+static const unsigned int hscif4_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+static const unsigned int hscif4_data_b_mux[] = {
+	HRX4_B_MARK, HTX4_B_MARK,
+};
+
+/* - I2C -------------------------------------------------------------------- */
+static const unsigned int i2c1_a_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(5, 11), RCAR_GP_PIN(5, 10),
+};
+static const unsigned int i2c1_a_mux[] = {
+	SDA1_A_MARK, SCL1_A_MARK,
+};
+static const unsigned int i2c1_b_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 23),
+};
+static const unsigned int i2c1_b_mux[] = {
+	SDA1_B_MARK, SCL1_B_MARK,
+};
+static const unsigned int i2c2_a_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 4),
+};
+static const unsigned int i2c2_a_mux[] = {
+	SDA2_A_MARK, SCL2_A_MARK,
+};
+static const unsigned int i2c2_b_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(3, 13), RCAR_GP_PIN(3, 12),
+};
+static const unsigned int i2c2_b_mux[] = {
+	SDA2_B_MARK, SCL2_B_MARK,
+};
+static const unsigned int i2c6_a_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+static const unsigned int i2c6_a_mux[] = {
+	SDA6_A_MARK, SCL6_A_MARK,
+};
+static const unsigned int i2c6_b_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+static const unsigned int i2c6_b_mux[] = {
+	SDA6_B_MARK, SCL6_B_MARK,
+};
+static const unsigned int i2c6_c_pins[] = {
+	/* SDA, SCL */
+	RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14),
+};
+static const unsigned int i2c6_c_mux[] = {
+	SDA6_C_MARK, SCL6_C_MARK,
+};
+
+/* - INTC-EX ---------------------------------------------------------------- */
+static const unsigned int intc_ex_irq0_pins[] = {
+	/* IRQ0 */
+	RCAR_GP_PIN(2, 0),
+};
+static const unsigned int intc_ex_irq0_mux[] = {
+	IRQ0_MARK,
+};
+static const unsigned int intc_ex_irq1_pins[] = {
+	/* IRQ1 */
+	RCAR_GP_PIN(2, 1),
+};
+static const unsigned int intc_ex_irq1_mux[] = {
+	IRQ1_MARK,
+};
+static const unsigned int intc_ex_irq2_pins[] = {
+	/* IRQ2 */
+	RCAR_GP_PIN(2, 2),
+};
+static const unsigned int intc_ex_irq2_mux[] = {
+	IRQ2_MARK,
+};
+static const unsigned int intc_ex_irq3_pins[] = {
+	/* IRQ3 */
+	RCAR_GP_PIN(2, 3),
+};
+static const unsigned int intc_ex_irq3_mux[] = {
+	IRQ3_MARK,
+};
+static const unsigned int intc_ex_irq4_pins[] = {
+	/* IRQ4 */
+	RCAR_GP_PIN(2, 4),
+};
+static const unsigned int intc_ex_irq4_mux[] = {
+	IRQ4_MARK,
+};
+static const unsigned int intc_ex_irq5_pins[] = {
+	/* IRQ5 */
+	RCAR_GP_PIN(2, 5),
+};
+static const unsigned int intc_ex_irq5_mux[] = {
+	IRQ5_MARK,
+};
+
+/* - MSIOF0 ----------------------------------------------------------------- */
+static const unsigned int msiof0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 17),
+};
+static const unsigned int msiof0_clk_mux[] = {
+	MSIOF0_SCK_MARK,
+};
+static const unsigned int msiof0_sync_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 18),
+};
+static const unsigned int msiof0_sync_mux[] = {
+	MSIOF0_SYNC_MARK,
+};
+static const unsigned int msiof0_ss1_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(5, 19),
+};
+static const unsigned int msiof0_ss1_mux[] = {
+	MSIOF0_SS1_MARK,
+};
+static const unsigned int msiof0_ss2_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int msiof0_ss2_mux[] = {
+	MSIOF0_SS2_MARK,
+};
+static const unsigned int msiof0_txd_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(5, 20),
+};
+static const unsigned int msiof0_txd_mux[] = {
+	MSIOF0_TXD_MARK,
+};
+static const unsigned int msiof0_rxd_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 22),
+};
+static const unsigned int msiof0_rxd_mux[] = {
+	MSIOF0_RXD_MARK,
+};
+/* - MSIOF1 ----------------------------------------------------------------- */
+static const unsigned int msiof1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 8),
+};
+static const unsigned int msiof1_clk_a_mux[] = {
+	MSIOF1_SCK_A_MARK,
+};
+static const unsigned int msiof1_sync_a_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(6, 9),
+};
+static const unsigned int msiof1_sync_a_mux[] = {
+	MSIOF1_SYNC_A_MARK,
+};
+static const unsigned int msiof1_ss1_a_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(6, 5),
+};
+static const unsigned int msiof1_ss1_a_mux[] = {
+	MSIOF1_SS1_A_MARK,
+};
+static const unsigned int msiof1_ss2_a_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(6, 6),
+};
+static const unsigned int msiof1_ss2_a_mux[] = {
+	MSIOF1_SS2_A_MARK,
+};
+static const unsigned int msiof1_txd_a_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(6, 7),
+};
+static const unsigned int msiof1_txd_a_mux[] = {
+	MSIOF1_TXD_A_MARK,
+};
+static const unsigned int msiof1_rxd_a_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int msiof1_rxd_a_mux[] = {
+	MSIOF1_RXD_A_MARK,
+};
+static const unsigned int msiof1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 9),
+};
+static const unsigned int msiof1_clk_b_mux[] = {
+	MSIOF1_SCK_B_MARK,
+};
+static const unsigned int msiof1_sync_b_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 3),
+};
+static const unsigned int msiof1_sync_b_mux[] = {
+	MSIOF1_SYNC_B_MARK,
+};
+static const unsigned int msiof1_ss1_b_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(5, 4),
+};
+static const unsigned int msiof1_ss1_b_mux[] = {
+	MSIOF1_SS1_B_MARK,
+};
+static const unsigned int msiof1_ss2_b_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int msiof1_ss2_b_mux[] = {
+	MSIOF1_SS2_B_MARK,
+};
+static const unsigned int msiof1_txd_b_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(5, 8),
+};
+static const unsigned int msiof1_txd_b_mux[] = {
+	MSIOF1_TXD_B_MARK,
+};
+static const unsigned int msiof1_rxd_b_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 7),
+};
+static const unsigned int msiof1_rxd_b_mux[] = {
+	MSIOF1_RXD_B_MARK,
+};
+static const unsigned int msiof1_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 17),
+};
+static const unsigned int msiof1_clk_c_mux[] = {
+	MSIOF1_SCK_C_MARK,
+};
+static const unsigned int msiof1_sync_c_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(6, 18),
+};
+static const unsigned int msiof1_sync_c_mux[] = {
+	MSIOF1_SYNC_C_MARK,
+};
+static const unsigned int msiof1_ss1_c_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int msiof1_ss1_c_mux[] = {
+	MSIOF1_SS1_C_MARK,
+};
+static const unsigned int msiof1_ss2_c_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(6, 27),
+};
+static const unsigned int msiof1_ss2_c_mux[] = {
+	MSIOF1_SS2_C_MARK,
+};
+static const unsigned int msiof1_txd_c_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(6, 20),
+};
+static const unsigned int msiof1_txd_c_mux[] = {
+	MSIOF1_TXD_C_MARK,
+};
+static const unsigned int msiof1_rxd_c_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(6, 19),
+};
+static const unsigned int msiof1_rxd_c_mux[] = {
+	MSIOF1_RXD_C_MARK,
+};
+static const unsigned int msiof1_clk_d_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int msiof1_clk_d_mux[] = {
+	MSIOF1_SCK_D_MARK,
+};
+static const unsigned int msiof1_sync_d_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 15),
+};
+static const unsigned int msiof1_sync_d_mux[] = {
+	MSIOF1_SYNC_D_MARK,
+};
+static const unsigned int msiof1_ss1_d_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(5, 16),
+};
+static const unsigned int msiof1_ss1_d_mux[] = {
+	MSIOF1_SS1_D_MARK,
+};
+static const unsigned int msiof1_ss2_d_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int msiof1_ss2_d_mux[] = {
+	MSIOF1_SS2_D_MARK,
+};
+static const unsigned int msiof1_txd_d_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(5, 14),
+};
+static const unsigned int msiof1_txd_d_mux[] = {
+	MSIOF1_TXD_D_MARK,
+};
+static const unsigned int msiof1_rxd_d_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 13),
+};
+static const unsigned int msiof1_rxd_d_mux[] = {
+	MSIOF1_RXD_D_MARK,
+};
+static const unsigned int msiof1_clk_e_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(3, 0),
+};
+static const unsigned int msiof1_clk_e_mux[] = {
+	MSIOF1_SCK_E_MARK,
+};
+static const unsigned int msiof1_sync_e_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(3, 1),
+};
+static const unsigned int msiof1_sync_e_mux[] = {
+	MSIOF1_SYNC_E_MARK,
+};
+static const unsigned int msiof1_ss1_e_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(3, 4),
+};
+static const unsigned int msiof1_ss1_e_mux[] = {
+	MSIOF1_SS1_E_MARK,
+};
+static const unsigned int msiof1_ss2_e_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(3, 5),
+};
+static const unsigned int msiof1_ss2_e_mux[] = {
+	MSIOF1_SS2_E_MARK,
+};
+static const unsigned int msiof1_txd_e_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(3, 3),
+};
+static const unsigned int msiof1_txd_e_mux[] = {
+	MSIOF1_TXD_E_MARK,
+};
+static const unsigned int msiof1_rxd_e_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(3, 2),
+};
+static const unsigned int msiof1_rxd_e_mux[] = {
+	MSIOF1_RXD_E_MARK,
+};
+static const unsigned int msiof1_clk_f_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 23),
+};
+static const unsigned int msiof1_clk_f_mux[] = {
+	MSIOF1_SCK_F_MARK,
+};
+static const unsigned int msiof1_sync_f_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 24),
+};
+static const unsigned int msiof1_sync_f_mux[] = {
+	MSIOF1_SYNC_F_MARK,
+};
+static const unsigned int msiof1_ss1_f_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(6, 1),
+};
+static const unsigned int msiof1_ss1_f_mux[] = {
+	MSIOF1_SS1_F_MARK,
+};
+static const unsigned int msiof1_ss2_f_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(6, 2),
+};
+static const unsigned int msiof1_ss2_f_mux[] = {
+	MSIOF1_SS2_F_MARK,
+};
+static const unsigned int msiof1_txd_f_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(6, 0),
+};
+static const unsigned int msiof1_txd_f_mux[] = {
+	MSIOF1_TXD_F_MARK,
+};
+static const unsigned int msiof1_rxd_f_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 25),
+};
+static const unsigned int msiof1_rxd_f_mux[] = {
+	MSIOF1_RXD_F_MARK,
+};
+static const unsigned int msiof1_clk_g_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(3, 6),
+};
+static const unsigned int msiof1_clk_g_mux[] = {
+	MSIOF1_SCK_G_MARK,
+};
+static const unsigned int msiof1_sync_g_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(3, 7),
+};
+static const unsigned int msiof1_sync_g_mux[] = {
+	MSIOF1_SYNC_G_MARK,
+};
+static const unsigned int msiof1_ss1_g_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(3, 10),
+};
+static const unsigned int msiof1_ss1_g_mux[] = {
+	MSIOF1_SS1_G_MARK,
+};
+static const unsigned int msiof1_ss2_g_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(3, 11),
+};
+static const unsigned int msiof1_ss2_g_mux[] = {
+	MSIOF1_SS2_G_MARK,
+};
+static const unsigned int msiof1_txd_g_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(3, 9),
+};
+static const unsigned int msiof1_txd_g_mux[] = {
+	MSIOF1_TXD_G_MARK,
+};
+static const unsigned int msiof1_rxd_g_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(3, 8),
+};
+static const unsigned int msiof1_rxd_g_mux[] = {
+	MSIOF1_RXD_G_MARK,
+};
+/* - MSIOF2 ----------------------------------------------------------------- */
+static const unsigned int msiof2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 9),
+};
+static const unsigned int msiof2_clk_a_mux[] = {
+	MSIOF2_SCK_A_MARK,
+};
+static const unsigned int msiof2_sync_a_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 8),
+};
+static const unsigned int msiof2_sync_a_mux[] = {
+	MSIOF2_SYNC_A_MARK,
+};
+static const unsigned int msiof2_ss1_a_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(1, 6),
+};
+static const unsigned int msiof2_ss1_a_mux[] = {
+	MSIOF2_SS1_A_MARK,
+};
+static const unsigned int msiof2_ss2_a_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(1, 7),
+};
+static const unsigned int msiof2_ss2_a_mux[] = {
+	MSIOF2_SS2_A_MARK,
+};
+static const unsigned int msiof2_txd_a_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int msiof2_txd_a_mux[] = {
+	MSIOF2_TXD_A_MARK,
+};
+static const unsigned int msiof2_rxd_a_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 10),
+};
+static const unsigned int msiof2_rxd_a_mux[] = {
+	MSIOF2_RXD_A_MARK,
+};
+static const unsigned int msiof2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 4),
+};
+static const unsigned int msiof2_clk_b_mux[] = {
+	MSIOF2_SCK_B_MARK,
+};
+static const unsigned int msiof2_sync_b_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(0, 5),
+};
+static const unsigned int msiof2_sync_b_mux[] = {
+	MSIOF2_SYNC_B_MARK,
+};
+static const unsigned int msiof2_ss1_b_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(0, 0),
+};
+static const unsigned int msiof2_ss1_b_mux[] = {
+	MSIOF2_SS1_B_MARK,
+};
+static const unsigned int msiof2_ss2_b_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(0, 1),
+};
+static const unsigned int msiof2_ss2_b_mux[] = {
+	MSIOF2_SS2_B_MARK,
+};
+static const unsigned int msiof2_txd_b_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(0, 7),
+};
+static const unsigned int msiof2_txd_b_mux[] = {
+	MSIOF2_TXD_B_MARK,
+};
+static const unsigned int msiof2_rxd_b_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(0, 6),
+};
+static const unsigned int msiof2_rxd_b_mux[] = {
+	MSIOF2_RXD_B_MARK,
+};
+static const unsigned int msiof2_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(2, 12),
+};
+static const unsigned int msiof2_clk_c_mux[] = {
+	MSIOF2_SCK_C_MARK,
+};
+static const unsigned int msiof2_sync_c_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(2, 11),
+};
+static const unsigned int msiof2_sync_c_mux[] = {
+	MSIOF2_SYNC_C_MARK,
+};
+static const unsigned int msiof2_ss1_c_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(2, 10),
+};
+static const unsigned int msiof2_ss1_c_mux[] = {
+	MSIOF2_SS1_C_MARK,
+};
+static const unsigned int msiof2_ss2_c_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(2, 9),
+};
+static const unsigned int msiof2_ss2_c_mux[] = {
+	MSIOF2_SS2_C_MARK,
+};
+static const unsigned int msiof2_txd_c_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(2, 14),
+};
+static const unsigned int msiof2_txd_c_mux[] = {
+	MSIOF2_TXD_C_MARK,
+};
+static const unsigned int msiof2_rxd_c_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(2, 13),
+};
+static const unsigned int msiof2_rxd_c_mux[] = {
+	MSIOF2_RXD_C_MARK,
+};
+static const unsigned int msiof2_clk_d_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 8),
+};
+static const unsigned int msiof2_clk_d_mux[] = {
+	MSIOF2_SCK_D_MARK,
+};
+static const unsigned int msiof2_sync_d_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(0, 9),
+};
+static const unsigned int msiof2_sync_d_mux[] = {
+	MSIOF2_SYNC_D_MARK,
+};
+static const unsigned int msiof2_ss1_d_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(0, 12),
+};
+static const unsigned int msiof2_ss1_d_mux[] = {
+	MSIOF2_SS1_D_MARK,
+};
+static const unsigned int msiof2_ss2_d_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(0, 13),
+};
+static const unsigned int msiof2_ss2_d_mux[] = {
+	MSIOF2_SS2_D_MARK,
+};
+static const unsigned int msiof2_txd_d_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(0, 11),
+};
+static const unsigned int msiof2_txd_d_mux[] = {
+	MSIOF2_TXD_D_MARK,
+};
+static const unsigned int msiof2_rxd_d_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(0, 10),
+};
+static const unsigned int msiof2_rxd_d_mux[] = {
+	MSIOF2_RXD_D_MARK,
+};
+/* - MSIOF3 ----------------------------------------------------------------- */
+static const unsigned int msiof3_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 0),
+};
+static const unsigned int msiof3_clk_a_mux[] = {
+	MSIOF3_SCK_A_MARK,
+};
+static const unsigned int msiof3_sync_a_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(0, 1),
+};
+static const unsigned int msiof3_sync_a_mux[] = {
+	MSIOF3_SYNC_A_MARK,
+};
+static const unsigned int msiof3_ss1_a_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(0, 14),
+};
+static const unsigned int msiof3_ss1_a_mux[] = {
+	MSIOF3_SS1_A_MARK,
+};
+static const unsigned int msiof3_ss2_a_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(0, 15),
+};
+static const unsigned int msiof3_ss2_a_mux[] = {
+	MSIOF3_SS2_A_MARK,
+};
+static const unsigned int msiof3_txd_a_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(0, 3),
+};
+static const unsigned int msiof3_txd_a_mux[] = {
+	MSIOF3_TXD_A_MARK,
+};
+static const unsigned int msiof3_rxd_a_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(0, 2),
+};
+static const unsigned int msiof3_rxd_a_mux[] = {
+	MSIOF3_RXD_A_MARK,
+};
+static const unsigned int msiof3_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 2),
+};
+static const unsigned int msiof3_clk_b_mux[] = {
+	MSIOF3_SCK_B_MARK,
+};
+static const unsigned int msiof3_sync_b_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 0),
+};
+static const unsigned int msiof3_sync_b_mux[] = {
+	MSIOF3_SYNC_B_MARK,
+};
+static const unsigned int msiof3_ss1_b_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(1, 4),
+};
+static const unsigned int msiof3_ss1_b_mux[] = {
+	MSIOF3_SS1_B_MARK,
+};
+static const unsigned int msiof3_ss2_b_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(1, 5),
+};
+static const unsigned int msiof3_ss2_b_mux[] = {
+	MSIOF3_SS2_B_MARK,
+};
+static const unsigned int msiof3_txd_b_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 1),
+};
+static const unsigned int msiof3_txd_b_mux[] = {
+	MSIOF3_TXD_B_MARK,
+};
+static const unsigned int msiof3_rxd_b_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 3),
+};
+static const unsigned int msiof3_rxd_b_mux[] = {
+	MSIOF3_RXD_B_MARK,
+};
+static const unsigned int msiof3_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 12),
+};
+static const unsigned int msiof3_clk_c_mux[] = {
+	MSIOF3_SCK_C_MARK,
+};
+static const unsigned int msiof3_sync_c_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 13),
+};
+static const unsigned int msiof3_sync_c_mux[] = {
+	MSIOF3_SYNC_C_MARK,
+};
+static const unsigned int msiof3_txd_c_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 15),
+};
+static const unsigned int msiof3_txd_c_mux[] = {
+	MSIOF3_TXD_C_MARK,
+};
+static const unsigned int msiof3_rxd_c_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 14),
+};
+static const unsigned int msiof3_rxd_c_mux[] = {
+	MSIOF3_RXD_C_MARK,
+};
+static const unsigned int msiof3_clk_d_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+static const unsigned int msiof3_clk_d_mux[] = {
+	MSIOF3_SCK_D_MARK,
+};
+static const unsigned int msiof3_sync_d_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 23),
+};
+static const unsigned int msiof3_sync_d_mux[] = {
+	MSIOF3_SYNC_D_MARK,
+};
+static const unsigned int msiof3_ss1_d_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(1, 26),
+};
+static const unsigned int msiof3_ss1_d_mux[] = {
+	MSIOF3_SS1_D_MARK,
+};
+static const unsigned int msiof3_txd_d_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 25),
+};
+static const unsigned int msiof3_txd_d_mux[] = {
+	MSIOF3_TXD_D_MARK,
+};
+static const unsigned int msiof3_rxd_d_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 24),
+};
+static const unsigned int msiof3_rxd_d_mux[] = {
+	MSIOF3_RXD_D_MARK,
+};
+
+/* - PWM0 --------------------------------------------------------------------*/
+static const unsigned int pwm0_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 6),
+};
+static const unsigned int pwm0_mux[] = {
+	PWM0_MARK,
+};
+/* - PWM1 --------------------------------------------------------------------*/
+static const unsigned int pwm1_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 7),
+};
+static const unsigned int pwm1_a_mux[] = {
+	PWM1_A_MARK,
+};
+static const unsigned int pwm1_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 8),
+};
+static const unsigned int pwm1_b_mux[] = {
+	PWM1_B_MARK,
+};
+/* - PWM2 --------------------------------------------------------------------*/
+static const unsigned int pwm2_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 8),
+};
+static const unsigned int pwm2_a_mux[] = {
+	PWM2_A_MARK,
+};
+static const unsigned int pwm2_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int pwm2_b_mux[] = {
+	PWM2_B_MARK,
+};
+/* - PWM3 --------------------------------------------------------------------*/
+static const unsigned int pwm3_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 0),
+};
+static const unsigned int pwm3_a_mux[] = {
+	PWM3_A_MARK,
+};
+static const unsigned int pwm3_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 2),
+};
+static const unsigned int pwm3_b_mux[] = {
+	PWM3_B_MARK,
+};
+/* - PWM4 --------------------------------------------------------------------*/
+static const unsigned int pwm4_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 1),
+};
+static const unsigned int pwm4_a_mux[] = {
+	PWM4_A_MARK,
+};
+static const unsigned int pwm4_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 3),
+};
+static const unsigned int pwm4_b_mux[] = {
+	PWM4_B_MARK,
+};
+/* - PWM5 --------------------------------------------------------------------*/
+static const unsigned int pwm5_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 2),
+};
+static const unsigned int pwm5_a_mux[] = {
+	PWM5_A_MARK,
+};
+static const unsigned int pwm5_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 4),
+};
+static const unsigned int pwm5_b_mux[] = {
+	PWM5_B_MARK,
+};
+/* - PWM6 --------------------------------------------------------------------*/
+static const unsigned int pwm6_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 3),
+};
+static const unsigned int pwm6_a_mux[] = {
+	PWM6_A_MARK,
+};
+static const unsigned int pwm6_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 5),
+};
+static const unsigned int pwm6_b_mux[] = {
+	PWM6_B_MARK,
+};
+
+/* - QSPI0 ------------------------------------------------------------------ */
+static const unsigned int qspi0_ctrl_pins[] = {
+	/* QSPI0_SPCLK, QSPI0_SSL */
+	PIN_NUMBER('W', 3), PIN_NUMBER('Y', 3),
+};
+static const unsigned int qspi0_ctrl_mux[] = {
+	QSPI0_SPCLK_MARK, QSPI0_SSL_MARK,
+};
+static const unsigned int qspi0_data2_pins[] = {
+	/* QSPI0_MOSI_IO0, QSPI0_MISO_IO1 */
+	PIN_A_NUMBER('C', 5), PIN_A_NUMBER('B', 4),
+};
+static const unsigned int qspi0_data2_mux[] = {
+	QSPI0_MOSI_IO0_MARK, QSPI0_MISO_IO1_MARK,
+};
+static const unsigned int qspi0_data4_pins[] = {
+	/* QSPI0_MOSI_IO0, QSPI0_MISO_IO1, QSPI0_IO2, QSPI0_IO3 */
+	PIN_A_NUMBER('C', 5), PIN_A_NUMBER('B', 4),
+	PIN_NUMBER('Y', 6), PIN_A_NUMBER('B', 6),
+};
+static const unsigned int qspi0_data4_mux[] = {
+	QSPI0_MOSI_IO0_MARK, QSPI0_MISO_IO1_MARK,
+	QSPI0_IO2_MARK, QSPI0_IO3_MARK,
+};
+/* - QSPI1 ------------------------------------------------------------------ */
+static const unsigned int qspi1_ctrl_pins[] = {
+	/* QSPI1_SPCLK, QSPI1_SSL */
+	PIN_NUMBER('V', 3), PIN_NUMBER('V', 5),
+};
+static const unsigned int qspi1_ctrl_mux[] = {
+	QSPI1_SPCLK_MARK, QSPI1_SSL_MARK,
+};
+static const unsigned int qspi1_data2_pins[] = {
+	/* QSPI1_MOSI_IO0, QSPI1_MISO_IO1 */
+	PIN_A_NUMBER('C', 7), PIN_A_NUMBER('E', 5),
+};
+static const unsigned int qspi1_data2_mux[] = {
+	QSPI1_MOSI_IO0_MARK, QSPI1_MISO_IO1_MARK,
+};
+static const unsigned int qspi1_data4_pins[] = {
+	/* QSPI1_MOSI_IO0, QSPI1_MISO_IO1, QSPI1_IO2, QSPI1_IO3 */
+	PIN_A_NUMBER('C', 7), PIN_A_NUMBER('E', 5),
+	PIN_A_NUMBER('E', 4), PIN_A_NUMBER('C', 3),
+};
+static const unsigned int qspi1_data4_mux[] = {
+	QSPI1_MOSI_IO0_MARK, QSPI1_MISO_IO1_MARK,
+	QSPI1_IO2_MARK, QSPI1_IO3_MARK,
+};
+
+/* - SATA --------------------------------------------------------------------*/
+static const unsigned int sata0_devslp_a_pins[] = {
+	/* DEVSLP */
+	RCAR_GP_PIN(6, 16),
+};
+static const unsigned int sata0_devslp_a_mux[] = {
+	SATA_DEVSLP_A_MARK,
+};
+static const unsigned int sata0_devslp_b_pins[] = {
+	/* DEVSLP */
+	RCAR_GP_PIN(4, 6),
+};
+static const unsigned int sata0_devslp_b_mux[] = {
+	SATA_DEVSLP_B_MARK,
+};
+
+/* - SCIF0 ------------------------------------------------------------------ */
+static const unsigned int scif0_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+static const unsigned int scif0_data_mux[] = {
+	RX0_MARK, TX0_MARK,
+};
+static const unsigned int scif0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int scif0_clk_mux[] = {
+	SCK0_MARK,
+};
+static const unsigned int scif0_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
+};
+static const unsigned int scif0_ctrl_mux[] = {
+	RTS0_N_TANS_MARK, CTS0_N_MARK,
+};
+/* - SCIF1 ------------------------------------------------------------------ */
+static const unsigned int scif1_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
+};
+static const unsigned int scif1_data_a_mux[] = {
+	RX1_A_MARK, TX1_A_MARK,
+};
+static const unsigned int scif1_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int scif1_clk_mux[] = {
+	SCK1_MARK,
+};
+static const unsigned int scif1_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
+};
+static const unsigned int scif1_ctrl_mux[] = {
+	RTS1_N_TANS_MARK, CTS1_N_MARK,
+};
+
+static const unsigned int scif1_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 25),
+};
+static const unsigned int scif1_data_b_mux[] = {
+	RX1_B_MARK, TX1_B_MARK,
+};
+/* - SCIF2 ------------------------------------------------------------------ */
+static const unsigned int scif2_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 11), RCAR_GP_PIN(5, 10),
+};
+static const unsigned int scif2_data_a_mux[] = {
+	RX2_A_MARK, TX2_A_MARK,
+};
+static const unsigned int scif2_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 9),
+};
+static const unsigned int scif2_clk_mux[] = {
+	SCK2_MARK,
+};
+static const unsigned int scif2_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 16),
+};
+static const unsigned int scif2_data_b_mux[] = {
+	RX2_B_MARK, TX2_B_MARK,
+};
+/* - SCIF3 ------------------------------------------------------------------ */
+static const unsigned int scif3_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
+};
+static const unsigned int scif3_data_a_mux[] = {
+	RX3_A_MARK, TX3_A_MARK,
+};
+static const unsigned int scif3_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+static const unsigned int scif3_clk_mux[] = {
+	SCK3_MARK,
+};
+static const unsigned int scif3_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+static const unsigned int scif3_ctrl_mux[] = {
+	RTS3_N_TANS_MARK, CTS3_N_MARK,
+};
+static const unsigned int scif3_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+static const unsigned int scif3_data_b_mux[] = {
+	RX3_B_MARK, TX3_B_MARK,
+};
+/* - SCIF4 ------------------------------------------------------------------ */
+static const unsigned int scif4_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(2, 11), RCAR_GP_PIN(2, 12),
+};
+static const unsigned int scif4_data_a_mux[] = {
+	RX4_A_MARK, TX4_A_MARK,
+};
+static const unsigned int scif4_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(2, 10),
+};
+static const unsigned int scif4_clk_a_mux[] = {
+	SCK4_A_MARK,
+};
+static const unsigned int scif4_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(2, 14), RCAR_GP_PIN(2, 13),
+};
+static const unsigned int scif4_ctrl_a_mux[] = {
+	RTS4_N_TANS_A_MARK, CTS4_N_A_MARK,
+};
+static const unsigned int scif4_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7),
+};
+static const unsigned int scif4_data_b_mux[] = {
+	RX4_B_MARK, TX4_B_MARK,
+};
+static const unsigned int scif4_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 5),
+};
+static const unsigned int scif4_clk_b_mux[] = {
+	SCK4_B_MARK,
+};
+static const unsigned int scif4_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 10), RCAR_GP_PIN(1, 9),
+};
+static const unsigned int scif4_ctrl_b_mux[] = {
+	RTS4_N_TANS_B_MARK, CTS4_N_B_MARK,
+};
+static const unsigned int scif4_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 13),
+};
+static const unsigned int scif4_data_c_mux[] = {
+	RX4_C_MARK, TX4_C_MARK,
+};
+static const unsigned int scif4_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 8),
+};
+static const unsigned int scif4_clk_c_mux[] = {
+	SCK4_C_MARK,
+};
+static const unsigned int scif4_ctrl_c_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10),
+};
+static const unsigned int scif4_ctrl_c_mux[] = {
+	RTS4_N_TANS_C_MARK, CTS4_N_C_MARK,
+};
+/* - SCIF5 ------------------------------------------------------------------ */
+static const unsigned int scif5_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 21),
+};
+static const unsigned int scif5_data_mux[] = {
+	RX5_MARK, TX5_MARK,
+};
+static const unsigned int scif5_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int scif5_clk_mux[] = {
+	SCK5_MARK,
+};
+
+/* - SCIF Clock ------------------------------------------------------------- */
+static const unsigned int scif_clk_a_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(6, 23),
+};
+static const unsigned int scif_clk_a_mux[] = {
+	SCIF_CLK_A_MARK,
+};
+static const unsigned int scif_clk_b_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(5, 9),
+};
+static const unsigned int scif_clk_b_mux[] = {
+	SCIF_CLK_B_MARK,
+};
+
+/* - SDHI0 ------------------------------------------------------------------ */
+static const unsigned int sdhi0_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(3, 2),
+};
+static const unsigned int sdhi0_data1_mux[] = {
+	SD0_DAT0_MARK,
+};
+static const unsigned int sdhi0_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(3, 2), RCAR_GP_PIN(3, 3),
+	RCAR_GP_PIN(3, 4), RCAR_GP_PIN(3, 5),
+};
+static const unsigned int sdhi0_data4_mux[] = {
+	SD0_DAT0_MARK, SD0_DAT1_MARK,
+	SD0_DAT2_MARK, SD0_DAT3_MARK,
+};
+static const unsigned int sdhi0_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(3, 0), RCAR_GP_PIN(3, 1),
+};
+static const unsigned int sdhi0_ctrl_mux[] = {
+	SD0_CLK_MARK, SD0_CMD_MARK,
+};
+static const unsigned int sdhi0_cd_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(3, 12),
+};
+static const unsigned int sdhi0_cd_mux[] = {
+	SD0_CD_MARK,
+};
+static const unsigned int sdhi0_wp_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(3, 13),
+};
+static const unsigned int sdhi0_wp_mux[] = {
+	SD0_WP_MARK,
+};
+/* - SDHI1 ------------------------------------------------------------------ */
+static const unsigned int sdhi1_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(3, 8),
+};
+static const unsigned int sdhi1_data1_mux[] = {
+	SD1_DAT0_MARK,
+};
+static const unsigned int sdhi1_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(3, 8),  RCAR_GP_PIN(3, 9),
+	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11),
+};
+static const unsigned int sdhi1_data4_mux[] = {
+	SD1_DAT0_MARK, SD1_DAT1_MARK,
+	SD1_DAT2_MARK, SD1_DAT3_MARK,
+};
+static const unsigned int sdhi1_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(3, 6), RCAR_GP_PIN(3, 7),
+};
+static const unsigned int sdhi1_ctrl_mux[] = {
+	SD1_CLK_MARK, SD1_CMD_MARK,
+};
+static const unsigned int sdhi1_cd_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(3, 14),
+};
+static const unsigned int sdhi1_cd_mux[] = {
+	SD1_CD_MARK,
+};
+static const unsigned int sdhi1_wp_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(3, 15),
+};
+static const unsigned int sdhi1_wp_mux[] = {
+	SD1_WP_MARK,
+};
+/* - SDHI2 ------------------------------------------------------------------ */
+static const unsigned int sdhi2_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(4, 2),
+};
+static const unsigned int sdhi2_data1_mux[] = {
+	SD2_DAT0_MARK,
+};
+static const unsigned int sdhi2_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(4, 2), RCAR_GP_PIN(4, 3),
+	RCAR_GP_PIN(4, 4), RCAR_GP_PIN(4, 5),
+};
+static const unsigned int sdhi2_data4_mux[] = {
+	SD2_DAT0_MARK, SD2_DAT1_MARK,
+	SD2_DAT2_MARK, SD2_DAT3_MARK,
+};
+static const unsigned int sdhi2_data8_pins[] = {
+	/* D[0:7] */
+	RCAR_GP_PIN(4, 2),  RCAR_GP_PIN(4, 3),
+	RCAR_GP_PIN(4, 4),  RCAR_GP_PIN(4, 5),
+	RCAR_GP_PIN(3, 8),  RCAR_GP_PIN(3, 9),
+	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11),
+};
+static const unsigned int sdhi2_data8_mux[] = {
+	SD2_DAT0_MARK, SD2_DAT1_MARK,
+	SD2_DAT2_MARK, SD2_DAT3_MARK,
+	SD2_DAT4_MARK, SD2_DAT5_MARK,
+	SD2_DAT6_MARK, SD2_DAT7_MARK,
+};
+static const unsigned int sdhi2_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(4, 0), RCAR_GP_PIN(4, 1),
+};
+static const unsigned int sdhi2_ctrl_mux[] = {
+	SD2_CLK_MARK, SD2_CMD_MARK,
+};
+static const unsigned int sdhi2_cd_a_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(4, 13),
+};
+static const unsigned int sdhi2_cd_a_mux[] = {
+	SD2_CD_A_MARK,
+};
+static const unsigned int sdhi2_cd_b_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(5, 10),
+};
+static const unsigned int sdhi2_cd_b_mux[] = {
+	SD2_CD_B_MARK,
+};
+static const unsigned int sdhi2_wp_a_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(4, 14),
+};
+static const unsigned int sdhi2_wp_a_mux[] = {
+	SD2_WP_A_MARK,
+};
+static const unsigned int sdhi2_wp_b_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(5, 11),
+};
+static const unsigned int sdhi2_wp_b_mux[] = {
+	SD2_WP_B_MARK,
+};
+static const unsigned int sdhi2_ds_pins[] = {
+	/* DS */
+	RCAR_GP_PIN(4, 6),
+};
+static const unsigned int sdhi2_ds_mux[] = {
+	SD2_DS_MARK,
+};
+/* - SDHI3 ------------------------------------------------------------------ */
+static const unsigned int sdhi3_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(4, 9),
+};
+static const unsigned int sdhi3_data1_mux[] = {
+	SD3_DAT0_MARK,
+};
+static const unsigned int sdhi3_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(4, 9),  RCAR_GP_PIN(4, 10),
+	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
+};
+static const unsigned int sdhi3_data4_mux[] = {
+	SD3_DAT0_MARK, SD3_DAT1_MARK,
+	SD3_DAT2_MARK, SD3_DAT3_MARK,
+};
+static const unsigned int sdhi3_data8_pins[] = {
+	/* D[0:7] */
+	RCAR_GP_PIN(4, 9),  RCAR_GP_PIN(4, 10),
+	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
+	RCAR_GP_PIN(4, 13), RCAR_GP_PIN(4, 14),
+	RCAR_GP_PIN(4, 15), RCAR_GP_PIN(4, 16),
+};
+static const unsigned int sdhi3_data8_mux[] = {
+	SD3_DAT0_MARK, SD3_DAT1_MARK,
+	SD3_DAT2_MARK, SD3_DAT3_MARK,
+	SD3_DAT4_MARK, SD3_DAT5_MARK,
+	SD3_DAT6_MARK, SD3_DAT7_MARK,
+};
+static const unsigned int sdhi3_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(4, 7), RCAR_GP_PIN(4, 8),
+};
+static const unsigned int sdhi3_ctrl_mux[] = {
+	SD3_CLK_MARK, SD3_CMD_MARK,
+};
+static const unsigned int sdhi3_cd_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(4, 15),
+};
+static const unsigned int sdhi3_cd_mux[] = {
+	SD3_CD_MARK,
+};
+static const unsigned int sdhi3_wp_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(4, 16),
+};
+static const unsigned int sdhi3_wp_mux[] = {
+	SD3_WP_MARK,
+};
+static const unsigned int sdhi3_ds_pins[] = {
+	/* DS */
+	RCAR_GP_PIN(4, 17),
+};
+static const unsigned int sdhi3_ds_mux[] = {
+	SD3_DS_MARK,
+};
+
+/* - SSI -------------------------------------------------------------------- */
+static const unsigned int ssi0_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 2),
+};
+static const unsigned int ssi0_data_mux[] = {
+	SSI_SDATA0_MARK,
+};
+static const unsigned int ssi01239_ctrl_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 0), RCAR_GP_PIN(6, 1),
+};
+static const unsigned int ssi01239_ctrl_mux[] = {
+	SSI_SCK01239_MARK, SSI_WS01239_MARK,
+};
+static const unsigned int ssi1_data_a_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 3),
+};
+static const unsigned int ssi1_data_a_mux[] = {
+	SSI_SDATA1_A_MARK,
+};
+static const unsigned int ssi1_data_b_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int ssi1_data_b_mux[] = {
+	SSI_SDATA1_B_MARK,
+};
+static const unsigned int ssi1_ctrl_a_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
+};
+static const unsigned int ssi1_ctrl_a_mux[] = {
+	SSI_SCK1_A_MARK, SSI_WS1_A_MARK,
+};
+static const unsigned int ssi1_ctrl_b_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 4), RCAR_GP_PIN(6, 21),
+};
+static const unsigned int ssi1_ctrl_b_mux[] = {
+	SSI_SCK1_B_MARK, SSI_WS1_B_MARK,
+};
+static const unsigned int ssi2_data_a_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 4),
+};
+static const unsigned int ssi2_data_a_mux[] = {
+	SSI_SDATA2_A_MARK,
+};
+static const unsigned int ssi2_data_b_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(5, 13),
+};
+static const unsigned int ssi2_data_b_mux[] = {
+	SSI_SDATA2_B_MARK,
+};
+static const unsigned int ssi2_ctrl_a_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 21),
+};
+static const unsigned int ssi2_ctrl_a_mux[] = {
+	SSI_SCK2_A_MARK, SSI_WS2_A_MARK,
+};
+static const unsigned int ssi2_ctrl_b_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 29),
+};
+static const unsigned int ssi2_ctrl_b_mux[] = {
+	SSI_SCK2_B_MARK, SSI_WS2_B_MARK,
+};
+static const unsigned int ssi3_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 7),
+};
+static const unsigned int ssi3_data_mux[] = {
+	SSI_SDATA3_MARK,
+};
+static const unsigned int ssi34_ctrl_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 5), RCAR_GP_PIN(6, 6),
+};
+static const unsigned int ssi34_ctrl_mux[] = {
+	SSI_SCK34_MARK, SSI_WS34_MARK,
+};
+static const unsigned int ssi4_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int ssi4_data_mux[] = {
+	SSI_SDATA4_MARK,
+};
+static const unsigned int ssi4_ctrl_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+static const unsigned int ssi4_ctrl_mux[] = {
+	SSI_SCK4_MARK, SSI_WS4_MARK,
+};
+static const unsigned int ssi5_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 13),
+};
+static const unsigned int ssi5_data_mux[] = {
+	SSI_SDATA5_MARK,
+};
+static const unsigned int ssi5_ctrl_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 11), RCAR_GP_PIN(6, 12),
+};
+static const unsigned int ssi5_ctrl_mux[] = {
+	SSI_SCK5_MARK, SSI_WS5_MARK,
+};
+static const unsigned int ssi6_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 16),
+};
+static const unsigned int ssi6_data_mux[] = {
+	SSI_SDATA6_MARK,
+};
+static const unsigned int ssi6_ctrl_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15),
+};
+static const unsigned int ssi6_ctrl_mux[] = {
+	SSI_SCK6_MARK, SSI_WS6_MARK,
+};
+static const unsigned int ssi7_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 19),
+};
+static const unsigned int ssi7_data_mux[] = {
+	SSI_SDATA7_MARK,
+};
+static const unsigned int ssi78_ctrl_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+static const unsigned int ssi78_ctrl_mux[] = {
+	SSI_SCK78_MARK, SSI_WS78_MARK,
+};
+static const unsigned int ssi8_data_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 20),
+};
+static const unsigned int ssi8_data_mux[] = {
+	SSI_SDATA8_MARK,
+};
+static const unsigned int ssi9_data_a_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int ssi9_data_a_mux[] = {
+	SSI_SDATA9_A_MARK,
+};
+static const unsigned int ssi9_data_b_pins[] = {
+	/* SDATA */
+	RCAR_GP_PIN(5, 14),
+};
+static const unsigned int ssi9_data_b_mux[] = {
+	SSI_SDATA9_B_MARK,
+};
+static const unsigned int ssi9_ctrl_a_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 16),
+};
+static const unsigned int ssi9_ctrl_a_mux[] = {
+	SSI_SCK9_A_MARK, SSI_WS9_A_MARK,
+};
+static const unsigned int ssi9_ctrl_b_pins[] = {
+	/* SCK, WS */
+	RCAR_GP_PIN(6, 30), RCAR_GP_PIN(6, 31),
+};
+static const unsigned int ssi9_ctrl_b_mux[] = {
+	SSI_SCK9_B_MARK, SSI_WS9_B_MARK,
+};
+
+/* - USB0 ------------------------------------------------------------------- */
+static const unsigned int usb0_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25),
+};
+static const unsigned int usb0_mux[] = {
+	USB0_PWEN_MARK, USB0_OVC_MARK,
+};
+/* - USB1 ------------------------------------------------------------------- */
+static const unsigned int usb1_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
+};
+static const unsigned int usb1_mux[] = {
+	USB1_PWEN_MARK, USB1_OVC_MARK,
+};
+/* - USB2 ------------------------------------------------------------------- */
+static const unsigned int usb2_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15),
+};
+static const unsigned int usb2_mux[] = {
+	USB2_PWEN_MARK, USB2_OVC_MARK,
+};
+
+static const struct sh_pfc_pin_group pinmux_groups[] = {
+	SH_PFC_PIN_GROUP(audio_clk_a_a),
+	SH_PFC_PIN_GROUP(audio_clk_a_b),
+	SH_PFC_PIN_GROUP(audio_clk_a_c),
+	SH_PFC_PIN_GROUP(audio_clk_b_a),
+	SH_PFC_PIN_GROUP(audio_clk_b_b),
+	SH_PFC_PIN_GROUP(audio_clk_c_a),
+	SH_PFC_PIN_GROUP(audio_clk_c_b),
+	SH_PFC_PIN_GROUP(audio_clkout_a),
+	SH_PFC_PIN_GROUP(audio_clkout_b),
+	SH_PFC_PIN_GROUP(audio_clkout_c),
+	SH_PFC_PIN_GROUP(audio_clkout_d),
+	SH_PFC_PIN_GROUP(audio_clkout1_a),
+	SH_PFC_PIN_GROUP(audio_clkout1_b),
+	SH_PFC_PIN_GROUP(audio_clkout2_a),
+	SH_PFC_PIN_GROUP(audio_clkout2_b),
+	SH_PFC_PIN_GROUP(audio_clkout3_a),
+	SH_PFC_PIN_GROUP(audio_clkout3_b),
+	SH_PFC_PIN_GROUP(avb_link),
+	SH_PFC_PIN_GROUP(avb_magic),
+	SH_PFC_PIN_GROUP(avb_phy_int),
+	SH_PFC_PIN_GROUP(avb_mdc),
+	SH_PFC_PIN_GROUP(avb_mii),
+	SH_PFC_PIN_GROUP(avb_avtp_pps),
+	SH_PFC_PIN_GROUP(avb_avtp_match_a),
+	SH_PFC_PIN_GROUP(avb_avtp_capture_a),
+	SH_PFC_PIN_GROUP(avb_avtp_match_b),
+	SH_PFC_PIN_GROUP(avb_avtp_capture_b),
+	SH_PFC_PIN_GROUP(can0_data_a),
+	SH_PFC_PIN_GROUP(can0_data_b),
+	SH_PFC_PIN_GROUP(can1_data),
+	SH_PFC_PIN_GROUP(can_clk),
+	SH_PFC_PIN_GROUP(canfd0_data_a),
+	SH_PFC_PIN_GROUP(canfd0_data_b),
+	SH_PFC_PIN_GROUP(canfd1_data),
+	SH_PFC_PIN_GROUP(drif0_ctrl_a),
+	SH_PFC_PIN_GROUP(drif0_data0_a),
+	SH_PFC_PIN_GROUP(drif0_data1_a),
+	SH_PFC_PIN_GROUP(drif0_ctrl_b),
+	SH_PFC_PIN_GROUP(drif0_data0_b),
+	SH_PFC_PIN_GROUP(drif0_data1_b),
+	SH_PFC_PIN_GROUP(drif0_ctrl_c),
+	SH_PFC_PIN_GROUP(drif0_data0_c),
+	SH_PFC_PIN_GROUP(drif0_data1_c),
+	SH_PFC_PIN_GROUP(drif1_ctrl_a),
+	SH_PFC_PIN_GROUP(drif1_data0_a),
+	SH_PFC_PIN_GROUP(drif1_data1_a),
+	SH_PFC_PIN_GROUP(drif1_ctrl_b),
+	SH_PFC_PIN_GROUP(drif1_data0_b),
+	SH_PFC_PIN_GROUP(drif1_data1_b),
+	SH_PFC_PIN_GROUP(drif1_ctrl_c),
+	SH_PFC_PIN_GROUP(drif1_data0_c),
+	SH_PFC_PIN_GROUP(drif1_data1_c),
+	SH_PFC_PIN_GROUP(drif2_ctrl_a),
+	SH_PFC_PIN_GROUP(drif2_data0_a),
+	SH_PFC_PIN_GROUP(drif2_data1_a),
+	SH_PFC_PIN_GROUP(drif2_ctrl_b),
+	SH_PFC_PIN_GROUP(drif2_data0_b),
+	SH_PFC_PIN_GROUP(drif2_data1_b),
+	SH_PFC_PIN_GROUP(drif3_ctrl_a),
+	SH_PFC_PIN_GROUP(drif3_data0_a),
+	SH_PFC_PIN_GROUP(drif3_data1_a),
+	SH_PFC_PIN_GROUP(drif3_ctrl_b),
+	SH_PFC_PIN_GROUP(drif3_data0_b),
+	SH_PFC_PIN_GROUP(drif3_data1_b),
+	SH_PFC_PIN_GROUP(du_rgb666),
+	SH_PFC_PIN_GROUP(du_rgb888),
+	SH_PFC_PIN_GROUP(du_clk_out_0),
+	SH_PFC_PIN_GROUP(du_clk_out_1),
+	SH_PFC_PIN_GROUP(du_sync),
+	SH_PFC_PIN_GROUP(du_oddf),
+	SH_PFC_PIN_GROUP(du_cde),
+	SH_PFC_PIN_GROUP(du_disp),
+	SH_PFC_PIN_GROUP(hscif0_data),
+	SH_PFC_PIN_GROUP(hscif0_clk),
+	SH_PFC_PIN_GROUP(hscif0_ctrl),
+	SH_PFC_PIN_GROUP(hscif1_data_a),
+	SH_PFC_PIN_GROUP(hscif1_clk_a),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif1_data_b),
+	SH_PFC_PIN_GROUP(hscif1_clk_b),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_a),
+	SH_PFC_PIN_GROUP(hscif2_clk_a),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif2_data_b),
+	SH_PFC_PIN_GROUP(hscif2_clk_b),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif3_data_a),
+	SH_PFC_PIN_GROUP(hscif3_clk),
+	SH_PFC_PIN_GROUP(hscif3_ctrl),
+	SH_PFC_PIN_GROUP(hscif3_data_b),
+	SH_PFC_PIN_GROUP(hscif3_data_c),
+	SH_PFC_PIN_GROUP(hscif3_data_d),
+	SH_PFC_PIN_GROUP(hscif4_data_a),
+	SH_PFC_PIN_GROUP(hscif4_clk),
+	SH_PFC_PIN_GROUP(hscif4_ctrl),
+	SH_PFC_PIN_GROUP(hscif4_data_b),
+	SH_PFC_PIN_GROUP(i2c1_a),
+	SH_PFC_PIN_GROUP(i2c1_b),
+	SH_PFC_PIN_GROUP(i2c2_a),
+	SH_PFC_PIN_GROUP(i2c2_b),
+	SH_PFC_PIN_GROUP(i2c6_a),
+	SH_PFC_PIN_GROUP(i2c6_b),
+	SH_PFC_PIN_GROUP(i2c6_c),
+	SH_PFC_PIN_GROUP(intc_ex_irq0),
+	SH_PFC_PIN_GROUP(intc_ex_irq1),
+	SH_PFC_PIN_GROUP(intc_ex_irq2),
+	SH_PFC_PIN_GROUP(intc_ex_irq3),
+	SH_PFC_PIN_GROUP(intc_ex_irq4),
+	SH_PFC_PIN_GROUP(intc_ex_irq5),
+	SH_PFC_PIN_GROUP(msiof0_clk),
+	SH_PFC_PIN_GROUP(msiof0_sync),
+	SH_PFC_PIN_GROUP(msiof0_ss1),
+	SH_PFC_PIN_GROUP(msiof0_ss2),
+	SH_PFC_PIN_GROUP(msiof0_txd),
+	SH_PFC_PIN_GROUP(msiof0_rxd),
+	SH_PFC_PIN_GROUP(msiof1_clk_a),
+	SH_PFC_PIN_GROUP(msiof1_sync_a),
+	SH_PFC_PIN_GROUP(msiof1_ss1_a),
+	SH_PFC_PIN_GROUP(msiof1_ss2_a),
+	SH_PFC_PIN_GROUP(msiof1_txd_a),
+	SH_PFC_PIN_GROUP(msiof1_rxd_a),
+	SH_PFC_PIN_GROUP(msiof1_clk_b),
+	SH_PFC_PIN_GROUP(msiof1_sync_b),
+	SH_PFC_PIN_GROUP(msiof1_ss1_b),
+	SH_PFC_PIN_GROUP(msiof1_ss2_b),
+	SH_PFC_PIN_GROUP(msiof1_txd_b),
+	SH_PFC_PIN_GROUP(msiof1_rxd_b),
+	SH_PFC_PIN_GROUP(msiof1_clk_c),
+	SH_PFC_PIN_GROUP(msiof1_sync_c),
+	SH_PFC_PIN_GROUP(msiof1_ss1_c),
+	SH_PFC_PIN_GROUP(msiof1_ss2_c),
+	SH_PFC_PIN_GROUP(msiof1_txd_c),
+	SH_PFC_PIN_GROUP(msiof1_rxd_c),
+	SH_PFC_PIN_GROUP(msiof1_clk_d),
+	SH_PFC_PIN_GROUP(msiof1_sync_d),
+	SH_PFC_PIN_GROUP(msiof1_ss1_d),
+	SH_PFC_PIN_GROUP(msiof1_ss2_d),
+	SH_PFC_PIN_GROUP(msiof1_txd_d),
+	SH_PFC_PIN_GROUP(msiof1_rxd_d),
+	SH_PFC_PIN_GROUP(msiof1_clk_e),
+	SH_PFC_PIN_GROUP(msiof1_sync_e),
+	SH_PFC_PIN_GROUP(msiof1_ss1_e),
+	SH_PFC_PIN_GROUP(msiof1_ss2_e),
+	SH_PFC_PIN_GROUP(msiof1_txd_e),
+	SH_PFC_PIN_GROUP(msiof1_rxd_e),
+	SH_PFC_PIN_GROUP(msiof1_clk_f),
+	SH_PFC_PIN_GROUP(msiof1_sync_f),
+	SH_PFC_PIN_GROUP(msiof1_ss1_f),
+	SH_PFC_PIN_GROUP(msiof1_ss2_f),
+	SH_PFC_PIN_GROUP(msiof1_txd_f),
+	SH_PFC_PIN_GROUP(msiof1_rxd_f),
+	SH_PFC_PIN_GROUP(msiof1_clk_g),
+	SH_PFC_PIN_GROUP(msiof1_sync_g),
+	SH_PFC_PIN_GROUP(msiof1_ss1_g),
+	SH_PFC_PIN_GROUP(msiof1_ss2_g),
+	SH_PFC_PIN_GROUP(msiof1_txd_g),
+	SH_PFC_PIN_GROUP(msiof1_rxd_g),
+	SH_PFC_PIN_GROUP(msiof2_clk_a),
+	SH_PFC_PIN_GROUP(msiof2_sync_a),
+	SH_PFC_PIN_GROUP(msiof2_ss1_a),
+	SH_PFC_PIN_GROUP(msiof2_ss2_a),
+	SH_PFC_PIN_GROUP(msiof2_txd_a),
+	SH_PFC_PIN_GROUP(msiof2_rxd_a),
+	SH_PFC_PIN_GROUP(msiof2_clk_b),
+	SH_PFC_PIN_GROUP(msiof2_sync_b),
+	SH_PFC_PIN_GROUP(msiof2_ss1_b),
+	SH_PFC_PIN_GROUP(msiof2_ss2_b),
+	SH_PFC_PIN_GROUP(msiof2_txd_b),
+	SH_PFC_PIN_GROUP(msiof2_rxd_b),
+	SH_PFC_PIN_GROUP(msiof2_clk_c),
+	SH_PFC_PIN_GROUP(msiof2_sync_c),
+	SH_PFC_PIN_GROUP(msiof2_ss1_c),
+	SH_PFC_PIN_GROUP(msiof2_ss2_c),
+	SH_PFC_PIN_GROUP(msiof2_txd_c),
+	SH_PFC_PIN_GROUP(msiof2_rxd_c),
+	SH_PFC_PIN_GROUP(msiof2_clk_d),
+	SH_PFC_PIN_GROUP(msiof2_sync_d),
+	SH_PFC_PIN_GROUP(msiof2_ss1_d),
+	SH_PFC_PIN_GROUP(msiof2_ss2_d),
+	SH_PFC_PIN_GROUP(msiof2_txd_d),
+	SH_PFC_PIN_GROUP(msiof2_rxd_d),
+	SH_PFC_PIN_GROUP(msiof3_clk_a),
+	SH_PFC_PIN_GROUP(msiof3_sync_a),
+	SH_PFC_PIN_GROUP(msiof3_ss1_a),
+	SH_PFC_PIN_GROUP(msiof3_ss2_a),
+	SH_PFC_PIN_GROUP(msiof3_txd_a),
+	SH_PFC_PIN_GROUP(msiof3_rxd_a),
+	SH_PFC_PIN_GROUP(msiof3_clk_b),
+	SH_PFC_PIN_GROUP(msiof3_sync_b),
+	SH_PFC_PIN_GROUP(msiof3_ss1_b),
+	SH_PFC_PIN_GROUP(msiof3_ss2_b),
+	SH_PFC_PIN_GROUP(msiof3_txd_b),
+	SH_PFC_PIN_GROUP(msiof3_rxd_b),
+	SH_PFC_PIN_GROUP(msiof3_clk_c),
+	SH_PFC_PIN_GROUP(msiof3_sync_c),
+	SH_PFC_PIN_GROUP(msiof3_txd_c),
+	SH_PFC_PIN_GROUP(msiof3_rxd_c),
+	SH_PFC_PIN_GROUP(msiof3_clk_d),
+	SH_PFC_PIN_GROUP(msiof3_sync_d),
+	SH_PFC_PIN_GROUP(msiof3_ss1_d),
+	SH_PFC_PIN_GROUP(msiof3_txd_d),
+	SH_PFC_PIN_GROUP(msiof3_rxd_d),
+	SH_PFC_PIN_GROUP(pwm0),
+	SH_PFC_PIN_GROUP(pwm1_a),
+	SH_PFC_PIN_GROUP(pwm1_b),
+	SH_PFC_PIN_GROUP(pwm2_a),
+	SH_PFC_PIN_GROUP(pwm2_b),
+	SH_PFC_PIN_GROUP(pwm3_a),
+	SH_PFC_PIN_GROUP(pwm3_b),
+	SH_PFC_PIN_GROUP(pwm4_a),
+	SH_PFC_PIN_GROUP(pwm4_b),
+	SH_PFC_PIN_GROUP(pwm5_a),
+	SH_PFC_PIN_GROUP(pwm5_b),
+	SH_PFC_PIN_GROUP(pwm6_a),
+	SH_PFC_PIN_GROUP(pwm6_b),
+	SH_PFC_PIN_GROUP(qspi0_ctrl),
+	SH_PFC_PIN_GROUP(qspi0_data2),
+	SH_PFC_PIN_GROUP(qspi0_data4),
+	SH_PFC_PIN_GROUP(qspi1_ctrl),
+	SH_PFC_PIN_GROUP(qspi1_data2),
+	SH_PFC_PIN_GROUP(qspi1_data4),
+	SH_PFC_PIN_GROUP(sata0_devslp_a),
+	SH_PFC_PIN_GROUP(sata0_devslp_b),
+	SH_PFC_PIN_GROUP(scif0_data),
+	SH_PFC_PIN_GROUP(scif0_clk),
+	SH_PFC_PIN_GROUP(scif0_ctrl),
+	SH_PFC_PIN_GROUP(scif1_data_a),
+	SH_PFC_PIN_GROUP(scif1_clk),
+	SH_PFC_PIN_GROUP(scif1_ctrl),
+	SH_PFC_PIN_GROUP(scif1_data_b),
+	SH_PFC_PIN_GROUP(scif2_data_a),
+	SH_PFC_PIN_GROUP(scif2_clk),
+	SH_PFC_PIN_GROUP(scif2_data_b),
+	SH_PFC_PIN_GROUP(scif3_data_a),
+	SH_PFC_PIN_GROUP(scif3_clk),
+	SH_PFC_PIN_GROUP(scif3_ctrl),
+	SH_PFC_PIN_GROUP(scif3_data_b),
+	SH_PFC_PIN_GROUP(scif4_data_a),
+	SH_PFC_PIN_GROUP(scif4_clk_a),
+	SH_PFC_PIN_GROUP(scif4_ctrl_a),
+	SH_PFC_PIN_GROUP(scif4_data_b),
+	SH_PFC_PIN_GROUP(scif4_clk_b),
+	SH_PFC_PIN_GROUP(scif4_ctrl_b),
+	SH_PFC_PIN_GROUP(scif4_data_c),
+	SH_PFC_PIN_GROUP(scif4_clk_c),
+	SH_PFC_PIN_GROUP(scif4_ctrl_c),
+	SH_PFC_PIN_GROUP(scif5_data),
+	SH_PFC_PIN_GROUP(scif5_clk),
+	SH_PFC_PIN_GROUP(scif_clk_a),
+	SH_PFC_PIN_GROUP(scif_clk_b),
+	SH_PFC_PIN_GROUP(sdhi0_data1),
+	SH_PFC_PIN_GROUP(sdhi0_data4),
+	SH_PFC_PIN_GROUP(sdhi0_ctrl),
+	SH_PFC_PIN_GROUP(sdhi0_cd),
+	SH_PFC_PIN_GROUP(sdhi0_wp),
+	SH_PFC_PIN_GROUP(sdhi1_data1),
+	SH_PFC_PIN_GROUP(sdhi1_data4),
+	SH_PFC_PIN_GROUP(sdhi1_ctrl),
+	SH_PFC_PIN_GROUP(sdhi1_cd),
+	SH_PFC_PIN_GROUP(sdhi1_wp),
+	SH_PFC_PIN_GROUP(sdhi2_data1),
+	SH_PFC_PIN_GROUP(sdhi2_data4),
+	SH_PFC_PIN_GROUP(sdhi2_data8),
+	SH_PFC_PIN_GROUP(sdhi2_ctrl),
+	SH_PFC_PIN_GROUP(sdhi2_cd_a),
+	SH_PFC_PIN_GROUP(sdhi2_wp_a),
+	SH_PFC_PIN_GROUP(sdhi2_cd_b),
+	SH_PFC_PIN_GROUP(sdhi2_wp_b),
+	SH_PFC_PIN_GROUP(sdhi2_ds),
+	SH_PFC_PIN_GROUP(sdhi3_data1),
+	SH_PFC_PIN_GROUP(sdhi3_data4),
+	SH_PFC_PIN_GROUP(sdhi3_data8),
+	SH_PFC_PIN_GROUP(sdhi3_ctrl),
+	SH_PFC_PIN_GROUP(sdhi3_cd),
+	SH_PFC_PIN_GROUP(sdhi3_wp),
+	SH_PFC_PIN_GROUP(sdhi3_ds),
+	SH_PFC_PIN_GROUP(ssi0_data),
+	SH_PFC_PIN_GROUP(ssi01239_ctrl),
+	SH_PFC_PIN_GROUP(ssi1_data_a),
+	SH_PFC_PIN_GROUP(ssi1_data_b),
+	SH_PFC_PIN_GROUP(ssi1_ctrl_a),
+	SH_PFC_PIN_GROUP(ssi1_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi2_data_a),
+	SH_PFC_PIN_GROUP(ssi2_data_b),
+	SH_PFC_PIN_GROUP(ssi2_ctrl_a),
+	SH_PFC_PIN_GROUP(ssi2_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi3_data),
+	SH_PFC_PIN_GROUP(ssi34_ctrl),
+	SH_PFC_PIN_GROUP(ssi4_data),
+	SH_PFC_PIN_GROUP(ssi4_ctrl),
+	SH_PFC_PIN_GROUP(ssi5_data),
+	SH_PFC_PIN_GROUP(ssi5_ctrl),
+	SH_PFC_PIN_GROUP(ssi6_data),
+	SH_PFC_PIN_GROUP(ssi6_ctrl),
+	SH_PFC_PIN_GROUP(ssi7_data),
+	SH_PFC_PIN_GROUP(ssi78_ctrl),
+	SH_PFC_PIN_GROUP(ssi8_data),
+	SH_PFC_PIN_GROUP(ssi9_data_a),
+	SH_PFC_PIN_GROUP(ssi9_data_b),
+	SH_PFC_PIN_GROUP(ssi9_ctrl_a),
+	SH_PFC_PIN_GROUP(ssi9_ctrl_b),
+	SH_PFC_PIN_GROUP(usb0),
+	SH_PFC_PIN_GROUP(usb1),
+	SH_PFC_PIN_GROUP(usb2),
+};
+
+static const char * const audio_clk_groups[] = {
+	"audio_clk_a_a",
+	"audio_clk_a_b",
+	"audio_clk_a_c",
+	"audio_clk_b_a",
+	"audio_clk_b_b",
+	"audio_clk_c_a",
+	"audio_clk_c_b",
+	"audio_clkout_a",
+	"audio_clkout_b",
+	"audio_clkout_c",
+	"audio_clkout_d",
+	"audio_clkout1_a",
+	"audio_clkout1_b",
+	"audio_clkout2_a",
+	"audio_clkout2_b",
+	"audio_clkout3_a",
+	"audio_clkout3_b",
+};
+
+static const char * const avb_groups[] = {
+	"avb_link",
+	"avb_magic",
+	"avb_phy_int",
+	"avb_mdc",
+	"avb_mii",
+	"avb_avtp_pps",
+	"avb_avtp_match_a",
+	"avb_avtp_capture_a",
+	"avb_avtp_match_b",
+	"avb_avtp_capture_b",
+};
+
+static const char * const can0_groups[] = {
+	"can0_data_a",
+	"can0_data_b",
+};
+
+static const char * const can1_groups[] = {
+	"can1_data",
+};
+
+static const char * const can_clk_groups[] = {
+	"can_clk",
+};
+
+static const char * const canfd0_groups[] = {
+	"canfd0_data_a",
+	"canfd0_data_b",
+};
+
+static const char * const canfd1_groups[] = {
+	"canfd1_data",
+};
+
+static const char * const drif0_groups[] = {
+	"drif0_ctrl_a",
+	"drif0_data0_a",
+	"drif0_data1_a",
+	"drif0_ctrl_b",
+	"drif0_data0_b",
+	"drif0_data1_b",
+	"drif0_ctrl_c",
+	"drif0_data0_c",
+	"drif0_data1_c",
+};
+
+static const char * const drif1_groups[] = {
+	"drif1_ctrl_a",
+	"drif1_data0_a",
+	"drif1_data1_a",
+	"drif1_ctrl_b",
+	"drif1_data0_b",
+	"drif1_data1_b",
+	"drif1_ctrl_c",
+	"drif1_data0_c",
+	"drif1_data1_c",
+};
+
+static const char * const drif2_groups[] = {
+	"drif2_ctrl_a",
+	"drif2_data0_a",
+	"drif2_data1_a",
+	"drif2_ctrl_b",
+	"drif2_data0_b",
+	"drif2_data1_b",
+};
+
+static const char * const drif3_groups[] = {
+	"drif3_ctrl_a",
+	"drif3_data0_a",
+	"drif3_data1_a",
+	"drif3_ctrl_b",
+	"drif3_data0_b",
+	"drif3_data1_b",
+};
+
+static const char * const du_groups[] = {
+	"du_rgb666",
+	"du_rgb888",
+	"du_clk_out_0",
+	"du_clk_out_1",
+	"du_sync",
+	"du_oddf",
+	"du_cde",
+	"du_disp",
+};
+
+static const char * const hscif0_groups[] = {
+	"hscif0_data",
+	"hscif0_clk",
+	"hscif0_ctrl",
+};
+
+static const char * const hscif1_groups[] = {
+	"hscif1_data_a",
+	"hscif1_clk_a",
+	"hscif1_ctrl_a",
+	"hscif1_data_b",
+	"hscif1_clk_b",
+	"hscif1_ctrl_b",
+};
+
+static const char * const hscif2_groups[] = {
+	"hscif2_data_a",
+	"hscif2_clk_a",
+	"hscif2_ctrl_a",
+	"hscif2_data_b",
+	"hscif2_clk_b",
+	"hscif2_ctrl_b",
+};
+
+static const char * const hscif3_groups[] = {
+	"hscif3_data_a",
+	"hscif3_clk",
+	"hscif3_ctrl",
+	"hscif3_data_b",
+	"hscif3_data_c",
+	"hscif3_data_d",
+};
+
+static const char * const hscif4_groups[] = {
+	"hscif4_data_a",
+	"hscif4_clk",
+	"hscif4_ctrl",
+	"hscif4_data_b",
+};
+
+static const char * const i2c1_groups[] = {
+	"i2c1_a",
+	"i2c1_b",
+};
+
+static const char * const i2c2_groups[] = {
+	"i2c2_a",
+	"i2c2_b",
+};
+
+static const char * const i2c6_groups[] = {
+	"i2c6_a",
+	"i2c6_b",
+	"i2c6_c",
+};
+
+static const char * const intc_ex_groups[] = {
+	"intc_ex_irq0",
+	"intc_ex_irq1",
+	"intc_ex_irq2",
+	"intc_ex_irq3",
+	"intc_ex_irq4",
+	"intc_ex_irq5",
+};
+
+static const char * const msiof0_groups[] = {
+	"msiof0_clk",
+	"msiof0_sync",
+	"msiof0_ss1",
+	"msiof0_ss2",
+	"msiof0_txd",
+	"msiof0_rxd",
+};
+
+static const char * const msiof1_groups[] = {
+	"msiof1_clk_a",
+	"msiof1_sync_a",
+	"msiof1_ss1_a",
+	"msiof1_ss2_a",
+	"msiof1_txd_a",
+	"msiof1_rxd_a",
+	"msiof1_clk_b",
+	"msiof1_sync_b",
+	"msiof1_ss1_b",
+	"msiof1_ss2_b",
+	"msiof1_txd_b",
+	"msiof1_rxd_b",
+	"msiof1_clk_c",
+	"msiof1_sync_c",
+	"msiof1_ss1_c",
+	"msiof1_ss2_c",
+	"msiof1_txd_c",
+	"msiof1_rxd_c",
+	"msiof1_clk_d",
+	"msiof1_sync_d",
+	"msiof1_ss1_d",
+	"msiof1_ss2_d",
+	"msiof1_txd_d",
+	"msiof1_rxd_d",
+	"msiof1_clk_e",
+	"msiof1_sync_e",
+	"msiof1_ss1_e",
+	"msiof1_ss2_e",
+	"msiof1_txd_e",
+	"msiof1_rxd_e",
+	"msiof1_clk_f",
+	"msiof1_sync_f",
+	"msiof1_ss1_f",
+	"msiof1_ss2_f",
+	"msiof1_txd_f",
+	"msiof1_rxd_f",
+	"msiof1_clk_g",
+	"msiof1_sync_g",
+	"msiof1_ss1_g",
+	"msiof1_ss2_g",
+	"msiof1_txd_g",
+	"msiof1_rxd_g",
+};
+
+static const char * const msiof2_groups[] = {
+	"msiof2_clk_a",
+	"msiof2_sync_a",
+	"msiof2_ss1_a",
+	"msiof2_ss2_a",
+	"msiof2_txd_a",
+	"msiof2_rxd_a",
+	"msiof2_clk_b",
+	"msiof2_sync_b",
+	"msiof2_ss1_b",
+	"msiof2_ss2_b",
+	"msiof2_txd_b",
+	"msiof2_rxd_b",
+	"msiof2_clk_c",
+	"msiof2_sync_c",
+	"msiof2_ss1_c",
+	"msiof2_ss2_c",
+	"msiof2_txd_c",
+	"msiof2_rxd_c",
+	"msiof2_clk_d",
+	"msiof2_sync_d",
+	"msiof2_ss1_d",
+	"msiof2_ss2_d",
+	"msiof2_txd_d",
+	"msiof2_rxd_d",
+};
+
+static const char * const msiof3_groups[] = {
+	"msiof3_clk_a",
+	"msiof3_sync_a",
+	"msiof3_ss1_a",
+	"msiof3_ss2_a",
+	"msiof3_txd_a",
+	"msiof3_rxd_a",
+	"msiof3_clk_b",
+	"msiof3_sync_b",
+	"msiof3_ss1_b",
+	"msiof3_ss2_b",
+	"msiof3_txd_b",
+	"msiof3_rxd_b",
+	"msiof3_clk_c",
+	"msiof3_sync_c",
+	"msiof3_txd_c",
+	"msiof3_rxd_c",
+	"msiof3_clk_d",
+	"msiof3_sync_d",
+	"msiof3_ss1_d",
+	"msiof3_txd_d",
+	"msiof3_rxd_d",
+};
+
+static const char * const pwm0_groups[] = {
+	"pwm0",
+};
+
+static const char * const pwm1_groups[] = {
+	"pwm1_a",
+	"pwm1_b",
+};
+
+static const char * const pwm2_groups[] = {
+	"pwm2_a",
+	"pwm2_b",
+};
+
+static const char * const pwm3_groups[] = {
+	"pwm3_a",
+	"pwm3_b",
+};
+
+static const char * const pwm4_groups[] = {
+	"pwm4_a",
+	"pwm4_b",
+};
+
+static const char * const pwm5_groups[] = {
+	"pwm5_a",
+	"pwm5_b",
+};
+
+static const char * const pwm6_groups[] = {
+	"pwm6_a",
+	"pwm6_b",
+};
+
+static const char * const qspi0_groups[] = {
+	"qspi0_ctrl",
+	"qspi0_data2",
+	"qspi0_data4",
+};
+
+static const char * const qspi1_groups[] = {
+	"qspi1_ctrl",
+	"qspi1_data2",
+	"qspi1_data4",
+};
+
+static const char * const sata0_groups[] = {
+	"sata0_devslp_a",
+	"sata0_devslp_b",
+};
+
+static const char * const scif0_groups[] = {
+	"scif0_data",
+	"scif0_clk",
+	"scif0_ctrl",
+};
+
+static const char * const scif1_groups[] = {
+	"scif1_data_a",
+	"scif1_clk",
+	"scif1_ctrl",
+	"scif1_data_b",
+};
+
+static const char * const scif2_groups[] = {
+	"scif2_data_a",
+	"scif2_clk",
+	"scif2_data_b",
+};
+
+static const char * const scif3_groups[] = {
+	"scif3_data_a",
+	"scif3_clk",
+	"scif3_ctrl",
+	"scif3_data_b",
+};
+
+static const char * const scif4_groups[] = {
+	"scif4_data_a",
+	"scif4_clk_a",
+	"scif4_ctrl_a",
+	"scif4_data_b",
+	"scif4_clk_b",
+	"scif4_ctrl_b",
+	"scif4_data_c",
+	"scif4_clk_c",
+	"scif4_ctrl_c",
+};
+
+static const char * const scif5_groups[] = {
+	"scif5_data",
+	"scif5_clk",
+};
+
+static const char * const scif_clk_groups[] = {
+	"scif_clk_a",
+	"scif_clk_b",
+};
+
+static const char * const sdhi0_groups[] = {
+	"sdhi0_data1",
+	"sdhi0_data4",
+	"sdhi0_ctrl",
+	"sdhi0_cd",
+	"sdhi0_wp",
+};
+
+static const char * const sdhi1_groups[] = {
+	"sdhi1_data1",
+	"sdhi1_data4",
+	"sdhi1_ctrl",
+	"sdhi1_cd",
+	"sdhi1_wp",
+};
+
+static const char * const sdhi2_groups[] = {
+	"sdhi2_data1",
+	"sdhi2_data4",
+	"sdhi2_data8",
+	"sdhi2_ctrl",
+	"sdhi2_cd_a",
+	"sdhi2_wp_a",
+	"sdhi2_cd_b",
+	"sdhi2_wp_b",
+	"sdhi2_ds",
+};
+
+static const char * const sdhi3_groups[] = {
+	"sdhi3_data1",
+	"sdhi3_data4",
+	"sdhi3_data8",
+	"sdhi3_ctrl",
+	"sdhi3_cd",
+	"sdhi3_wp",
+	"sdhi3_ds",
+};
+
+static const char * const ssi_groups[] = {
+	"ssi0_data",
+	"ssi01239_ctrl",
+	"ssi1_data_a",
+	"ssi1_data_b",
+	"ssi1_ctrl_a",
+	"ssi1_ctrl_b",
+	"ssi2_data_a",
+	"ssi2_data_b",
+	"ssi2_ctrl_a",
+	"ssi2_ctrl_b",
+	"ssi3_data",
+	"ssi34_ctrl",
+	"ssi4_data",
+	"ssi4_ctrl",
+	"ssi5_data",
+	"ssi5_ctrl",
+	"ssi6_data",
+	"ssi6_ctrl",
+	"ssi7_data",
+	"ssi78_ctrl",
+	"ssi8_data",
+	"ssi9_data_a",
+	"ssi9_data_b",
+	"ssi9_ctrl_a",
+	"ssi9_ctrl_b",
+};
+
+static const char * const usb0_groups[] = {
+	"usb0",
+};
+
+static const char * const usb1_groups[] = {
+	"usb1",
+};
+
+static const char * const usb2_groups[] = {
+	"usb2",
+};
+
+static const struct sh_pfc_function pinmux_functions[] = {
+	SH_PFC_FUNCTION(audio_clk),
+	SH_PFC_FUNCTION(avb),
+	SH_PFC_FUNCTION(can0),
+	SH_PFC_FUNCTION(can1),
+	SH_PFC_FUNCTION(can_clk),
+	SH_PFC_FUNCTION(canfd0),
+	SH_PFC_FUNCTION(canfd1),
+	SH_PFC_FUNCTION(drif0),
+	SH_PFC_FUNCTION(drif1),
+	SH_PFC_FUNCTION(drif2),
+	SH_PFC_FUNCTION(drif3),
+	SH_PFC_FUNCTION(du),
+	SH_PFC_FUNCTION(hscif0),
+	SH_PFC_FUNCTION(hscif1),
+	SH_PFC_FUNCTION(hscif2),
+	SH_PFC_FUNCTION(hscif3),
+	SH_PFC_FUNCTION(hscif4),
+	SH_PFC_FUNCTION(i2c1),
+	SH_PFC_FUNCTION(i2c2),
+	SH_PFC_FUNCTION(i2c6),
+	SH_PFC_FUNCTION(intc_ex),
+	SH_PFC_FUNCTION(msiof0),
+	SH_PFC_FUNCTION(msiof1),
+	SH_PFC_FUNCTION(msiof2),
+	SH_PFC_FUNCTION(msiof3),
+	SH_PFC_FUNCTION(pwm0),
+	SH_PFC_FUNCTION(pwm1),
+	SH_PFC_FUNCTION(pwm2),
+	SH_PFC_FUNCTION(pwm3),
+	SH_PFC_FUNCTION(pwm4),
+	SH_PFC_FUNCTION(pwm5),
+	SH_PFC_FUNCTION(pwm6),
+	SH_PFC_FUNCTION(qspi0),
+	SH_PFC_FUNCTION(qspi1),
+	SH_PFC_FUNCTION(sata0),
+	SH_PFC_FUNCTION(scif0),
+	SH_PFC_FUNCTION(scif1),
+	SH_PFC_FUNCTION(scif2),
+	SH_PFC_FUNCTION(scif3),
+	SH_PFC_FUNCTION(scif4),
+	SH_PFC_FUNCTION(scif5),
+	SH_PFC_FUNCTION(scif_clk),
+	SH_PFC_FUNCTION(sdhi0),
+	SH_PFC_FUNCTION(sdhi1),
+	SH_PFC_FUNCTION(sdhi2),
+	SH_PFC_FUNCTION(sdhi3),
+	SH_PFC_FUNCTION(ssi),
+	SH_PFC_FUNCTION(usb0),
+	SH_PFC_FUNCTION(usb1),
+	SH_PFC_FUNCTION(usb2),
+};
+
+static const struct pinmux_cfg_reg pinmux_config_regs[] = {
+#define F_(x, y)	FN_##y
+#define FM(x)		FN_##x
+	{ PINMUX_CFG_REG("GPSR0", 0xe6060100, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_0_15_FN,	GPSR0_15,
+		GP_0_14_FN,	GPSR0_14,
+		GP_0_13_FN,	GPSR0_13,
+		GP_0_12_FN,	GPSR0_12,
+		GP_0_11_FN,	GPSR0_11,
+		GP_0_10_FN,	GPSR0_10,
+		GP_0_9_FN,	GPSR0_9,
+		GP_0_8_FN,	GPSR0_8,
+		GP_0_7_FN,	GPSR0_7,
+		GP_0_6_FN,	GPSR0_6,
+		GP_0_5_FN,	GPSR0_5,
+		GP_0_4_FN,	GPSR0_4,
+		GP_0_3_FN,	GPSR0_3,
+		GP_0_2_FN,	GPSR0_2,
+		GP_0_1_FN,	GPSR0_1,
+		GP_0_0_FN,	GPSR0_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR1", 0xe6060104, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_1_27_FN,	GPSR1_27,
+		GP_1_26_FN,	GPSR1_26,
+		GP_1_25_FN,	GPSR1_25,
+		GP_1_24_FN,	GPSR1_24,
+		GP_1_23_FN,	GPSR1_23,
+		GP_1_22_FN,	GPSR1_22,
+		GP_1_21_FN,	GPSR1_21,
+		GP_1_20_FN,	GPSR1_20,
+		GP_1_19_FN,	GPSR1_19,
+		GP_1_18_FN,	GPSR1_18,
+		GP_1_17_FN,	GPSR1_17,
+		GP_1_16_FN,	GPSR1_16,
+		GP_1_15_FN,	GPSR1_15,
+		GP_1_14_FN,	GPSR1_14,
+		GP_1_13_FN,	GPSR1_13,
+		GP_1_12_FN,	GPSR1_12,
+		GP_1_11_FN,	GPSR1_11,
+		GP_1_10_FN,	GPSR1_10,
+		GP_1_9_FN,	GPSR1_9,
+		GP_1_8_FN,	GPSR1_8,
+		GP_1_7_FN,	GPSR1_7,
+		GP_1_6_FN,	GPSR1_6,
+		GP_1_5_FN,	GPSR1_5,
+		GP_1_4_FN,	GPSR1_4,
+		GP_1_3_FN,	GPSR1_3,
+		GP_1_2_FN,	GPSR1_2,
+		GP_1_1_FN,	GPSR1_1,
+		GP_1_0_FN,	GPSR1_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR2", 0xe6060108, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_2_14_FN,	GPSR2_14,
+		GP_2_13_FN,	GPSR2_13,
+		GP_2_12_FN,	GPSR2_12,
+		GP_2_11_FN,	GPSR2_11,
+		GP_2_10_FN,	GPSR2_10,
+		GP_2_9_FN,	GPSR2_9,
+		GP_2_8_FN,	GPSR2_8,
+		GP_2_7_FN,	GPSR2_7,
+		GP_2_6_FN,	GPSR2_6,
+		GP_2_5_FN,	GPSR2_5,
+		GP_2_4_FN,	GPSR2_4,
+		GP_2_3_FN,	GPSR2_3,
+		GP_2_2_FN,	GPSR2_2,
+		GP_2_1_FN,	GPSR2_1,
+		GP_2_0_FN,	GPSR2_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR3", 0xe606010c, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_3_15_FN,	GPSR3_15,
+		GP_3_14_FN,	GPSR3_14,
+		GP_3_13_FN,	GPSR3_13,
+		GP_3_12_FN,	GPSR3_12,
+		GP_3_11_FN,	GPSR3_11,
+		GP_3_10_FN,	GPSR3_10,
+		GP_3_9_FN,	GPSR3_9,
+		GP_3_8_FN,	GPSR3_8,
+		GP_3_7_FN,	GPSR3_7,
+		GP_3_6_FN,	GPSR3_6,
+		GP_3_5_FN,	GPSR3_5,
+		GP_3_4_FN,	GPSR3_4,
+		GP_3_3_FN,	GPSR3_3,
+		GP_3_2_FN,	GPSR3_2,
+		GP_3_1_FN,	GPSR3_1,
+		GP_3_0_FN,	GPSR3_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR4", 0xe6060110, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_4_17_FN,	GPSR4_17,
+		GP_4_16_FN,	GPSR4_16,
+		GP_4_15_FN,	GPSR4_15,
+		GP_4_14_FN,	GPSR4_14,
+		GP_4_13_FN,	GPSR4_13,
+		GP_4_12_FN,	GPSR4_12,
+		GP_4_11_FN,	GPSR4_11,
+		GP_4_10_FN,	GPSR4_10,
+		GP_4_9_FN,	GPSR4_9,
+		GP_4_8_FN,	GPSR4_8,
+		GP_4_7_FN,	GPSR4_7,
+		GP_4_6_FN,	GPSR4_6,
+		GP_4_5_FN,	GPSR4_5,
+		GP_4_4_FN,	GPSR4_4,
+		GP_4_3_FN,	GPSR4_3,
+		GP_4_2_FN,	GPSR4_2,
+		GP_4_1_FN,	GPSR4_1,
+		GP_4_0_FN,	GPSR4_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR5", 0xe6060114, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_5_25_FN,	GPSR5_25,
+		GP_5_24_FN,	GPSR5_24,
+		GP_5_23_FN,	GPSR5_23,
+		GP_5_22_FN,	GPSR5_22,
+		GP_5_21_FN,	GPSR5_21,
+		GP_5_20_FN,	GPSR5_20,
+		GP_5_19_FN,	GPSR5_19,
+		GP_5_18_FN,	GPSR5_18,
+		GP_5_17_FN,	GPSR5_17,
+		GP_5_16_FN,	GPSR5_16,
+		GP_5_15_FN,	GPSR5_15,
+		GP_5_14_FN,	GPSR5_14,
+		GP_5_13_FN,	GPSR5_13,
+		GP_5_12_FN,	GPSR5_12,
+		GP_5_11_FN,	GPSR5_11,
+		GP_5_10_FN,	GPSR5_10,
+		GP_5_9_FN,	GPSR5_9,
+		GP_5_8_FN,	GPSR5_8,
+		GP_5_7_FN,	GPSR5_7,
+		GP_5_6_FN,	GPSR5_6,
+		GP_5_5_FN,	GPSR5_5,
+		GP_5_4_FN,	GPSR5_4,
+		GP_5_3_FN,	GPSR5_3,
+		GP_5_2_FN,	GPSR5_2,
+		GP_5_1_FN,	GPSR5_1,
+		GP_5_0_FN,	GPSR5_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR6", 0xe6060118, 32, 1) {
+		GP_6_31_FN,	GPSR6_31,
+		GP_6_30_FN,	GPSR6_30,
+		GP_6_29_FN,	GPSR6_29,
+		GP_6_28_FN,	GPSR6_28,
+		GP_6_27_FN,	GPSR6_27,
+		GP_6_26_FN,	GPSR6_26,
+		GP_6_25_FN,	GPSR6_25,
+		GP_6_24_FN,	GPSR6_24,
+		GP_6_23_FN,	GPSR6_23,
+		GP_6_22_FN,	GPSR6_22,
+		GP_6_21_FN,	GPSR6_21,
+		GP_6_20_FN,	GPSR6_20,
+		GP_6_19_FN,	GPSR6_19,
+		GP_6_18_FN,	GPSR6_18,
+		GP_6_17_FN,	GPSR6_17,
+		GP_6_16_FN,	GPSR6_16,
+		GP_6_15_FN,	GPSR6_15,
+		GP_6_14_FN,	GPSR6_14,
+		GP_6_13_FN,	GPSR6_13,
+		GP_6_12_FN,	GPSR6_12,
+		GP_6_11_FN,	GPSR6_11,
+		GP_6_10_FN,	GPSR6_10,
+		GP_6_9_FN,	GPSR6_9,
+		GP_6_8_FN,	GPSR6_8,
+		GP_6_7_FN,	GPSR6_7,
+		GP_6_6_FN,	GPSR6_6,
+		GP_6_5_FN,	GPSR6_5,
+		GP_6_4_FN,	GPSR6_4,
+		GP_6_3_FN,	GPSR6_3,
+		GP_6_2_FN,	GPSR6_2,
+		GP_6_1_FN,	GPSR6_1,
+		GP_6_0_FN,	GPSR6_0, }
+	},
+	{ PINMUX_CFG_REG("GPSR7", 0xe606011c, 32, 1) {
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		0, 0,
+		GP_7_3_FN, GPSR7_3,
+		GP_7_2_FN, GPSR7_2,
+		GP_7_1_FN, GPSR7_1,
+		GP_7_0_FN, GPSR7_0, }
+	},
+#undef F_
+#undef FM
+
+#define F_(x, y)	x,
+#define FM(x)		FN_##x,
+	{ PINMUX_CFG_REG("IPSR0", 0xe6060200, 32, 4) {
+		IP0_31_28
+		IP0_27_24
+		IP0_23_20
+		IP0_19_16
+		IP0_15_12
+		IP0_11_8
+		IP0_7_4
+		IP0_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR1", 0xe6060204, 32, 4) {
+		IP1_31_28
+		IP1_27_24
+		IP1_23_20
+		IP1_19_16
+		IP1_15_12
+		IP1_11_8
+		IP1_7_4
+		IP1_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR2", 0xe6060208, 32, 4) {
+		IP2_31_28
+		IP2_27_24
+		IP2_23_20
+		IP2_19_16
+		IP2_15_12
+		IP2_11_8
+		IP2_7_4
+		IP2_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR3", 0xe606020c, 32, 4) {
+		IP3_31_28
+		IP3_27_24
+		IP3_23_20
+		IP3_19_16
+		IP3_15_12
+		IP3_11_8
+		IP3_7_4
+		IP3_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR4", 0xe6060210, 32, 4) {
+		IP4_31_28
+		IP4_27_24
+		IP4_23_20
+		IP4_19_16
+		IP4_15_12
+		IP4_11_8
+		IP4_7_4
+		IP4_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR5", 0xe6060214, 32, 4) {
+		IP5_31_28
+		IP5_27_24
+		IP5_23_20
+		IP5_19_16
+		IP5_15_12
+		IP5_11_8
+		IP5_7_4
+		IP5_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR6", 0xe6060218, 32, 4) {
+		IP6_31_28
+		IP6_27_24
+		IP6_23_20
+		IP6_19_16
+		IP6_15_12
+		IP6_11_8
+		IP6_7_4
+		IP6_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR7", 0xe606021c, 32, 4) {
+		IP7_31_28
+		IP7_27_24
+		IP7_23_20
+		IP7_19_16
+		IP7_15_12
+		IP7_11_8
+		IP7_7_4
+		IP7_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR8", 0xe6060220, 32, 4) {
+		IP8_31_28
+		IP8_27_24
+		IP8_23_20
+		IP8_19_16
+		IP8_15_12
+		IP8_11_8
+		IP8_7_4
+		IP8_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR9", 0xe6060224, 32, 4) {
+		IP9_31_28
+		IP9_27_24
+		IP9_23_20
+		IP9_19_16
+		IP9_15_12
+		IP9_11_8
+		IP9_7_4
+		IP9_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR10", 0xe6060228, 32, 4) {
+		IP10_31_28
+		IP10_27_24
+		IP10_23_20
+		IP10_19_16
+		IP10_15_12
+		IP10_11_8
+		IP10_7_4
+		IP10_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR11", 0xe606022c, 32, 4) {
+		IP11_31_28
+		IP11_27_24
+		IP11_23_20
+		IP11_19_16
+		IP11_15_12
+		IP11_11_8
+		IP11_7_4
+		IP11_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR12", 0xe6060230, 32, 4) {
+		IP12_31_28
+		IP12_27_24
+		IP12_23_20
+		IP12_19_16
+		IP12_15_12
+		IP12_11_8
+		IP12_7_4
+		IP12_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR13", 0xe6060234, 32, 4) {
+		IP13_31_28
+		IP13_27_24
+		IP13_23_20
+		IP13_19_16
+		IP13_15_12
+		IP13_11_8
+		IP13_7_4
+		IP13_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR14", 0xe6060238, 32, 4) {
+		IP14_31_28
+		IP14_27_24
+		IP14_23_20
+		IP14_19_16
+		IP14_15_12
+		IP14_11_8
+		IP14_7_4
+		IP14_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR15", 0xe606023c, 32, 4) {
+		IP15_31_28
+		IP15_27_24
+		IP15_23_20
+		IP15_19_16
+		IP15_15_12
+		IP15_11_8
+		IP15_7_4
+		IP15_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR16", 0xe6060240, 32, 4) {
+		IP16_31_28
+		IP16_27_24
+		IP16_23_20
+		IP16_19_16
+		IP16_15_12
+		IP16_11_8
+		IP16_7_4
+		IP16_3_0 }
+	},
+	{ PINMUX_CFG_REG("IPSR17", 0xe6060244, 32, 4) {
+		/* IP17_31_28 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP17_27_24 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP17_23_20 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP17_19_16 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP17_15_12 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP17_11_8  */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		IP17_7_4
+		IP17_3_0 }
+	},
+#undef F_
+#undef FM
+
+#define F_(x, y)	x,
+#define FM(x)		FN_##x,
+	{ PINMUX_CFG_REG_VAR("MOD_SEL0", 0xe6060500, 32,
+			     1, 2, 2, 3, 1, 1, 2, 1, 1, 1,
+			     2, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 2, 1) {
+		0, 0, /* RESERVED 31 */
+		MOD_SEL0_30_29
+		MOD_SEL0_28_27
+		MOD_SEL0_26_25_24
+		MOD_SEL0_23
+		MOD_SEL0_22
+		MOD_SEL0_21_20
+		MOD_SEL0_19
+		MOD_SEL0_18
+		MOD_SEL0_17
+		MOD_SEL0_16_15
+		MOD_SEL0_14
+		MOD_SEL0_13
+		MOD_SEL0_12
+		MOD_SEL0_11
+		MOD_SEL0_10
+		MOD_SEL0_9
+		MOD_SEL0_8
+		MOD_SEL0_7_6
+		MOD_SEL0_5_4
+		MOD_SEL0_3
+		MOD_SEL0_2_1
+		0, 0, /* RESERVED 0 */ }
+	},
+	{ PINMUX_CFG_REG_VAR("MOD_SEL1", 0xe6060504, 32,
+			     2, 3, 1, 2, 3, 1, 1, 2, 1,
+			     2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1) {
+		MOD_SEL1_31_30
+		MOD_SEL1_29_28_27
+		MOD_SEL1_26
+		MOD_SEL1_25_24
+		MOD_SEL1_23_22_21
+		MOD_SEL1_20
+		MOD_SEL1_19
+		MOD_SEL1_18_17
+		MOD_SEL1_16
+		MOD_SEL1_15_14
+		MOD_SEL1_13
+		MOD_SEL1_12
+		MOD_SEL1_11
+		MOD_SEL1_10
+		MOD_SEL1_9
+		0, 0, 0, 0, /* RESERVED 8, 7 */
+		MOD_SEL1_6
+		MOD_SEL1_5
+		MOD_SEL1_4
+		MOD_SEL1_3
+		MOD_SEL1_2
+		MOD_SEL1_1
+		MOD_SEL1_0 }
+	},
+	{ PINMUX_CFG_REG_VAR("MOD_SEL2", 0xe6060508, 32,
+			     1, 1, 1, 1, 4, 4, 4,
+			     4, 4, 4, 1, 2, 1) {
+		MOD_SEL2_31
+		MOD_SEL2_30
+		MOD_SEL2_29
+		/* RESERVED 28 */
+		0, 0,
+		/* RESERVED 27, 26, 25, 24 */
+		0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0,
+		/* RESERVED 23, 22, 21, 20 */
+		0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0,
+		/* RESERVED 19, 18, 17, 16 */
+		0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0,
+		/* RESERVED 15, 14, 13, 12 */
+		0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0,
+		/* RESERVED 11, 10, 9, 8 */
+		0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0,
+		/* RESERVED 7, 6, 5, 4 */
+		0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0,
+		/* RESERVED 3 */
+		0, 0,
+		/* RESERVED 2, 1 */
+		0, 0, 0, 0,
+		MOD_SEL2_0 }
+	},
+	{ },
+};
+
+static const struct pinmux_drive_reg pinmux_drive_regs[] = {
+	{ PINMUX_DRIVE_REG("DRVCTRL0", 0xe6060300) {
+		{ PIN_NUMBER('W', 3),   28, 2 },	/* QSPI0_SPCLK */
+		{ PIN_A_NUMBER('C', 5), 24, 2 },	/* QSPI0_MOSI_IO0 */
+		{ PIN_A_NUMBER('B', 4), 20, 2 },	/* QSPI0_MISO_IO1 */
+		{ PIN_NUMBER('Y', 6),   16, 2 },	/* QSPI0_IO2 */
+		{ PIN_A_NUMBER('B', 6), 12, 2 },	/* QSPI0_IO3 */
+		{ PIN_NUMBER('Y', 3),    8, 2 },	/* QSPI0_SSL */
+		{ PIN_NUMBER('V', 3),    4, 2 },	/* QSPI1_SPCLK */
+		{ PIN_A_NUMBER('C', 7),  0, 2 },	/* QSPI1_MOSI_IO0 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL1", 0xe6060304) {
+		{ PIN_A_NUMBER('E', 5), 28, 2 },	/* QSPI1_MISO_IO1 */
+		{ PIN_A_NUMBER('E', 4), 24, 2 },	/* QSPI1_IO2 */
+		{ PIN_A_NUMBER('C', 3), 20, 2 },	/* QSPI1_IO3 */
+		{ PIN_NUMBER('V', 5),   16, 2 },	/* QSPI1_SSL */
+		{ PIN_NUMBER('Y', 7),   12, 2 },	/* RPC_INT# */
+		{ PIN_NUMBER('V', 6),    8, 2 },	/* RPC_WP# */
+		{ PIN_NUMBER('V', 7),    4, 2 },	/* RPC_RESET# */
+		{ PIN_NUMBER('A', 16),   0, 3 },	/* AVB_RX_CTL */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL2", 0xe6060308) {
+		{ PIN_NUMBER('B', 19),  28, 3 },	/* AVB_RXC */
+		{ PIN_NUMBER('A', 13),  24, 3 },	/* AVB_RD0 */
+		{ PIN_NUMBER('B', 13),  20, 3 },	/* AVB_RD1 */
+		{ PIN_NUMBER('A', 14),  16, 3 },	/* AVB_RD2 */
+		{ PIN_NUMBER('B', 14),  12, 3 },	/* AVB_RD3 */
+		{ PIN_NUMBER('A', 8),    8, 3 },	/* AVB_TX_CTL */
+		{ PIN_NUMBER('A', 19),   4, 3 },	/* AVB_TXC */
+		{ PIN_NUMBER('A', 18),   0, 3 },	/* AVB_TD0 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL3", 0xe606030c) {
+		{ PIN_NUMBER('B', 18),  28, 3 },	/* AVB_TD1 */
+		{ PIN_NUMBER('A', 17),  24, 3 },	/* AVB_TD2 */
+		{ PIN_NUMBER('B', 17),  20, 3 },	/* AVB_TD3 */
+		{ PIN_NUMBER('A', 12),  16, 3 },	/* AVB_TXCREFCLK */
+		{ PIN_NUMBER('A', 9),   12, 3 },	/* AVB_MDIO */
+		{ RCAR_GP_PIN(2,  9),    8, 3 },	/* AVB_MDC */
+		{ RCAR_GP_PIN(2, 10),    4, 3 },	/* AVB_MAGIC */
+		{ RCAR_GP_PIN(2, 11),    0, 3 },	/* AVB_PHY_INT */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL4", 0xe6060310) {
+		{ RCAR_GP_PIN(2, 12), 28, 3 },	/* AVB_LINK */
+		{ RCAR_GP_PIN(2, 13), 24, 3 },	/* AVB_AVTP_MATCH */
+		{ RCAR_GP_PIN(2, 14), 20, 3 },	/* AVB_AVTP_CAPTURE */
+		{ RCAR_GP_PIN(2,  0), 16, 3 },	/* IRQ0 */
+		{ RCAR_GP_PIN(2,  1), 12, 3 },	/* IRQ1 */
+		{ RCAR_GP_PIN(2,  2),  8, 3 },	/* IRQ2 */
+		{ RCAR_GP_PIN(2,  3),  4, 3 },	/* IRQ3 */
+		{ RCAR_GP_PIN(2,  4),  0, 3 },	/* IRQ4 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL5", 0xe6060314) {
+		{ RCAR_GP_PIN(2,  5), 28, 3 },	/* IRQ5 */
+		{ RCAR_GP_PIN(2,  6), 24, 3 },	/* PWM0 */
+		{ RCAR_GP_PIN(2,  7), 20, 3 },	/* PWM1 */
+		{ RCAR_GP_PIN(2,  8), 16, 3 },	/* PWM2 */
+		{ RCAR_GP_PIN(1,  0), 12, 3 },	/* A0 */
+		{ RCAR_GP_PIN(1,  1),  8, 3 },	/* A1 */
+		{ RCAR_GP_PIN(1,  2),  4, 3 },	/* A2 */
+		{ RCAR_GP_PIN(1,  3),  0, 3 },	/* A3 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL6", 0xe6060318) {
+		{ RCAR_GP_PIN(1,  4), 28, 3 },	/* A4 */
+		{ RCAR_GP_PIN(1,  5), 24, 3 },	/* A5 */
+		{ RCAR_GP_PIN(1,  6), 20, 3 },	/* A6 */
+		{ RCAR_GP_PIN(1,  7), 16, 3 },	/* A7 */
+		{ RCAR_GP_PIN(1,  8), 12, 3 },	/* A8 */
+		{ RCAR_GP_PIN(1,  9),  8, 3 },	/* A9 */
+		{ RCAR_GP_PIN(1, 10),  4, 3 },	/* A10 */
+		{ RCAR_GP_PIN(1, 11),  0, 3 },	/* A11 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL7", 0xe606031c) {
+		{ RCAR_GP_PIN(1, 12), 28, 3 },	/* A12 */
+		{ RCAR_GP_PIN(1, 13), 24, 3 },	/* A13 */
+		{ RCAR_GP_PIN(1, 14), 20, 3 },	/* A14 */
+		{ RCAR_GP_PIN(1, 15), 16, 3 },	/* A15 */
+		{ RCAR_GP_PIN(1, 16), 12, 3 },	/* A16 */
+		{ RCAR_GP_PIN(1, 17),  8, 3 },	/* A17 */
+		{ RCAR_GP_PIN(1, 18),  4, 3 },	/* A18 */
+		{ RCAR_GP_PIN(1, 19),  0, 3 },	/* A19 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL8", 0xe6060320) {
+		{ PIN_NUMBER('F', 1), 28, 3 },	/* CLKOUT */
+		{ RCAR_GP_PIN(1, 20), 24, 3 },	/* CS0 */
+		{ RCAR_GP_PIN(1, 21), 20, 3 },	/* CS1_A26 */
+		{ RCAR_GP_PIN(1, 22), 16, 3 },	/* BS */
+		{ RCAR_GP_PIN(1, 23), 12, 3 },	/* RD */
+		{ RCAR_GP_PIN(1, 24),  8, 3 },	/* RD_WR */
+		{ RCAR_GP_PIN(1, 25),  4, 3 },	/* WE0 */
+		{ RCAR_GP_PIN(1, 26),  0, 3 },	/* WE1 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL9", 0xe6060324) {
+		{ RCAR_GP_PIN(1, 27), 28, 3 },	/* EX_WAIT0 */
+		{ PIN_NUMBER('C', 1), 24, 3 },	/* PRESETOUT# */
+		{ RCAR_GP_PIN(0,  0), 20, 3 },	/* D0 */
+		{ RCAR_GP_PIN(0,  1), 16, 3 },	/* D1 */
+		{ RCAR_GP_PIN(0,  2), 12, 3 },	/* D2 */
+		{ RCAR_GP_PIN(0,  3),  8, 3 },	/* D3 */
+		{ RCAR_GP_PIN(0,  4),  4, 3 },	/* D4 */
+		{ RCAR_GP_PIN(0,  5),  0, 3 },	/* D5 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL10", 0xe6060328) {
+		{ RCAR_GP_PIN(0,  6), 28, 3 },	/* D6 */
+		{ RCAR_GP_PIN(0,  7), 24, 3 },	/* D7 */
+		{ RCAR_GP_PIN(0,  8), 20, 3 },	/* D8 */
+		{ RCAR_GP_PIN(0,  9), 16, 3 },	/* D9 */
+		{ RCAR_GP_PIN(0, 10), 12, 3 },	/* D10 */
+		{ RCAR_GP_PIN(0, 11),  8, 3 },	/* D11 */
+		{ RCAR_GP_PIN(0, 12),  4, 3 },	/* D12 */
+		{ RCAR_GP_PIN(0, 13),  0, 3 },	/* D13 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL11", 0xe606032c) {
+		{ RCAR_GP_PIN(0, 14),   28, 3 },	/* D14 */
+		{ RCAR_GP_PIN(0, 15),   24, 3 },	/* D15 */
+		{ RCAR_GP_PIN(7,  0),   20, 3 },	/* AVS1 */
+		{ RCAR_GP_PIN(7,  1),   16, 3 },	/* AVS2 */
+		{ RCAR_GP_PIN(7,  2),   12, 3 },	/* HDMI0_CEC */
+		{ RCAR_GP_PIN(7,  3),    8, 3 },	/* HDMI1_CEC */
+		{ PIN_A_NUMBER('P', 7),  4, 2 },	/* DU_DOTCLKIN0 */
+		{ PIN_A_NUMBER('P', 8),  0, 2 },	/* DU_DOTCLKIN1 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL12", 0xe6060330) {
+		{ PIN_A_NUMBER('R', 7),  28, 2 },	/* DU_DOTCLKIN2 */
+		{ PIN_A_NUMBER('R', 8),  24, 2 },	/* DU_DOTCLKIN3 */
+		{ PIN_A_NUMBER('D', 38), 20, 2 },	/* FSCLKST# */
+		{ PIN_A_NUMBER('R', 30),  4, 2 },	/* TMS */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL13", 0xe6060334) {
+		{ PIN_A_NUMBER('T', 28), 28, 2 },	/* TDO */
+		{ PIN_A_NUMBER('T', 30), 24, 2 },	/* ASEBRK */
+		{ RCAR_GP_PIN(3,  0),    20, 3 },	/* SD0_CLK */
+		{ RCAR_GP_PIN(3,  1),    16, 3 },	/* SD0_CMD */
+		{ RCAR_GP_PIN(3,  2),    12, 3 },	/* SD0_DAT0 */
+		{ RCAR_GP_PIN(3,  3),     8, 3 },	/* SD0_DAT1 */
+		{ RCAR_GP_PIN(3,  4),     4, 3 },	/* SD0_DAT2 */
+		{ RCAR_GP_PIN(3,  5),     0, 3 },	/* SD0_DAT3 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL14", 0xe6060338) {
+		{ RCAR_GP_PIN(3,  6), 28, 3 },	/* SD1_CLK */
+		{ RCAR_GP_PIN(3,  7), 24, 3 },	/* SD1_CMD */
+		{ RCAR_GP_PIN(3,  8), 20, 3 },	/* SD1_DAT0 */
+		{ RCAR_GP_PIN(3,  9), 16, 3 },	/* SD1_DAT1 */
+		{ RCAR_GP_PIN(3, 10), 12, 3 },	/* SD1_DAT2 */
+		{ RCAR_GP_PIN(3, 11),  8, 3 },	/* SD1_DAT3 */
+		{ RCAR_GP_PIN(4,  0),  4, 3 },	/* SD2_CLK */
+		{ RCAR_GP_PIN(4,  1),  0, 3 },	/* SD2_CMD */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL15", 0xe606033c) {
+		{ RCAR_GP_PIN(4,  2), 28, 3 },	/* SD2_DAT0 */
+		{ RCAR_GP_PIN(4,  3), 24, 3 },	/* SD2_DAT1 */
+		{ RCAR_GP_PIN(4,  4), 20, 3 },	/* SD2_DAT2 */
+		{ RCAR_GP_PIN(4,  5), 16, 3 },	/* SD2_DAT3 */
+		{ RCAR_GP_PIN(4,  6), 12, 3 },	/* SD2_DS */
+		{ RCAR_GP_PIN(4,  7),  8, 3 },	/* SD3_CLK */
+		{ RCAR_GP_PIN(4,  8),  4, 3 },	/* SD3_CMD */
+		{ RCAR_GP_PIN(4,  9),  0, 3 },	/* SD3_DAT0 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL16", 0xe6060340) {
+		{ RCAR_GP_PIN(4, 10), 28, 3 },	/* SD3_DAT1 */
+		{ RCAR_GP_PIN(4, 11), 24, 3 },	/* SD3_DAT2 */
+		{ RCAR_GP_PIN(4, 12), 20, 3 },	/* SD3_DAT3 */
+		{ RCAR_GP_PIN(4, 13), 16, 3 },	/* SD3_DAT4 */
+		{ RCAR_GP_PIN(4, 14), 12, 3 },	/* SD3_DAT5 */
+		{ RCAR_GP_PIN(4, 15),  8, 3 },	/* SD3_DAT6 */
+		{ RCAR_GP_PIN(4, 16),  4, 3 },	/* SD3_DAT7 */
+		{ RCAR_GP_PIN(4, 17),  0, 3 },	/* SD3_DS */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL17", 0xe6060344) {
+		{ RCAR_GP_PIN(3, 12), 28, 3 },	/* SD0_CD */
+		{ RCAR_GP_PIN(3, 13), 24, 3 },	/* SD0_WP */
+		{ RCAR_GP_PIN(3, 14), 20, 3 },	/* SD1_CD */
+		{ RCAR_GP_PIN(3, 15), 16, 3 },	/* SD1_WP */
+		{ RCAR_GP_PIN(5,  0), 12, 3 },	/* SCK0 */
+		{ RCAR_GP_PIN(5,  1),  8, 3 },	/* RX0 */
+		{ RCAR_GP_PIN(5,  2),  4, 3 },	/* TX0 */
+		{ RCAR_GP_PIN(5,  3),  0, 3 },	/* CTS0 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL18", 0xe6060348) {
+		{ RCAR_GP_PIN(5,  4), 28, 3 },	/* RTS0_TANS */
+		{ RCAR_GP_PIN(5,  5), 24, 3 },	/* RX1 */
+		{ RCAR_GP_PIN(5,  6), 20, 3 },	/* TX1 */
+		{ RCAR_GP_PIN(5,  7), 16, 3 },	/* CTS1 */
+		{ RCAR_GP_PIN(5,  8), 12, 3 },	/* RTS1_TANS */
+		{ RCAR_GP_PIN(5,  9),  8, 3 },	/* SCK2 */
+		{ RCAR_GP_PIN(5, 10),  4, 3 },	/* TX2 */
+		{ RCAR_GP_PIN(5, 11),  0, 3 },	/* RX2 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL19", 0xe606034c) {
+		{ RCAR_GP_PIN(5, 12), 28, 3 },	/* HSCK0 */
+		{ RCAR_GP_PIN(5, 13), 24, 3 },	/* HRX0 */
+		{ RCAR_GP_PIN(5, 14), 20, 3 },	/* HTX0 */
+		{ RCAR_GP_PIN(5, 15), 16, 3 },	/* HCTS0 */
+		{ RCAR_GP_PIN(5, 16), 12, 3 },	/* HRTS0 */
+		{ RCAR_GP_PIN(5, 17),  8, 3 },	/* MSIOF0_SCK */
+		{ RCAR_GP_PIN(5, 18),  4, 3 },	/* MSIOF0_SYNC */
+		{ RCAR_GP_PIN(5, 19),  0, 3 },	/* MSIOF0_SS1 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL20", 0xe6060350) {
+		{ RCAR_GP_PIN(5, 20), 28, 3 },	/* MSIOF0_TXD */
+		{ RCAR_GP_PIN(5, 21), 24, 3 },	/* MSIOF0_SS2 */
+		{ RCAR_GP_PIN(5, 22), 20, 3 },	/* MSIOF0_RXD */
+		{ RCAR_GP_PIN(5, 23), 16, 3 },	/* MLB_CLK */
+		{ RCAR_GP_PIN(5, 24), 12, 3 },	/* MLB_SIG */
+		{ RCAR_GP_PIN(5, 25),  8, 3 },	/* MLB_DAT */
+		{ PIN_NUMBER('H', 37),  4, 3 },	/* MLB_REF */
+		{ RCAR_GP_PIN(6,  0),  0, 3 },	/* SSI_SCK01239 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL21", 0xe6060354) {
+		{ RCAR_GP_PIN(6,  1), 28, 3 },	/* SSI_WS01239 */
+		{ RCAR_GP_PIN(6,  2), 24, 3 },	/* SSI_SDATA0 */
+		{ RCAR_GP_PIN(6,  3), 20, 3 },	/* SSI_SDATA1 */
+		{ RCAR_GP_PIN(6,  4), 16, 3 },	/* SSI_SDATA2 */
+		{ RCAR_GP_PIN(6,  5), 12, 3 },	/* SSI_SCK34 */
+		{ RCAR_GP_PIN(6,  6),  8, 3 },	/* SSI_WS34 */
+		{ RCAR_GP_PIN(6,  7),  4, 3 },	/* SSI_SDATA3 */
+		{ RCAR_GP_PIN(6,  8),  0, 3 },	/* SSI_SCK4 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL22", 0xe6060358) {
+		{ RCAR_GP_PIN(6,  9), 28, 3 },	/* SSI_WS4 */
+		{ RCAR_GP_PIN(6, 10), 24, 3 },	/* SSI_SDATA4 */
+		{ RCAR_GP_PIN(6, 11), 20, 3 },	/* SSI_SCK5 */
+		{ RCAR_GP_PIN(6, 12), 16, 3 },	/* SSI_WS5 */
+		{ RCAR_GP_PIN(6, 13), 12, 3 },	/* SSI_SDATA5 */
+		{ RCAR_GP_PIN(6, 14),  8, 3 },	/* SSI_SCK6 */
+		{ RCAR_GP_PIN(6, 15),  4, 3 },	/* SSI_WS6 */
+		{ RCAR_GP_PIN(6, 16),  0, 3 },	/* SSI_SDATA6 */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL23", 0xe606035c) {
+		{ RCAR_GP_PIN(6, 17), 28, 3 },	/* SSI_SCK78 */
+		{ RCAR_GP_PIN(6, 18), 24, 3 },	/* SSI_WS78 */
+		{ RCAR_GP_PIN(6, 19), 20, 3 },	/* SSI_SDATA7 */
+		{ RCAR_GP_PIN(6, 20), 16, 3 },	/* SSI_SDATA8 */
+		{ RCAR_GP_PIN(6, 21), 12, 3 },	/* SSI_SDATA9 */
+		{ RCAR_GP_PIN(6, 22),  8, 3 },	/* AUDIO_CLKA */
+		{ RCAR_GP_PIN(6, 23),  4, 3 },	/* AUDIO_CLKB */
+		{ RCAR_GP_PIN(6, 24),  0, 3 },	/* USB0_PWEN */
+	} },
+	{ PINMUX_DRIVE_REG("DRVCTRL24", 0xe6060360) {
+		{ RCAR_GP_PIN(6, 25), 28, 3 },	/* USB0_OVC */
+		{ RCAR_GP_PIN(6, 26), 24, 3 },	/* USB1_PWEN */
+		{ RCAR_GP_PIN(6, 27), 20, 3 },	/* USB1_OVC */
+		{ RCAR_GP_PIN(6, 28), 16, 3 },	/* USB30_PWEN */
+		{ RCAR_GP_PIN(6, 29), 12, 3 },	/* USB30_OVC */
+		{ RCAR_GP_PIN(6, 30),  8, 3 },	/* USB31_PWEN */
+		{ RCAR_GP_PIN(6, 31),  4, 3 },	/* USB31_OVC */
+	} },
+	{ },
+};
+
+static int r8a7795es1_pin_to_pocctrl(struct sh_pfc *pfc, unsigned int pin,
+				     u32 *pocctrl)
+{
+	int bit = -EINVAL;
+
+	*pocctrl = 0xe6060380;
+
+	if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 11))
+		bit = pin & 0x1f;
+
+	if (pin >= RCAR_GP_PIN(4, 0) && pin <= RCAR_GP_PIN(4, 17))
+		bit = (pin & 0x1f) + 12;
+
+	return bit;
+}
+
+#define PUEN	0xe6060400
+#define PUD	0xe6060440
+
+#define PU0	0x00
+#define PU1	0x04
+#define PU2	0x08
+#define PU3	0x0c
+#define PU4	0x10
+#define PU5	0x14
+#define PU6	0x18
+
+static const struct sh_pfc_bias_info bias_info[] = {
+	{ RCAR_GP_PIN(2, 11),    PU0, 31 },	/* AVB_PHY_INT */
+	{ RCAR_GP_PIN(2, 10),    PU0, 30 },	/* AVB_MAGIC */
+	{ RCAR_GP_PIN(2,  9),    PU0, 29 },	/* AVB_MDC */
+	{ PIN_NUMBER('A', 9),    PU0, 28 },	/* AVB_MDIO */
+	{ PIN_NUMBER('A', 12),   PU0, 27 },	/* AVB_TXCREFCLK */
+	{ PIN_NUMBER('B', 17),   PU0, 26 },	/* AVB_TD3 */
+	{ PIN_NUMBER('A', 17),   PU0, 25 },	/* AVB_TD2 */
+	{ PIN_NUMBER('B', 18),   PU0, 24 },	/* AVB_TD1 */
+	{ PIN_NUMBER('A', 18),   PU0, 23 },	/* AVB_TD0 */
+	{ PIN_NUMBER('A', 19),   PU0, 22 },	/* AVB_TXC */
+	{ PIN_NUMBER('A', 8),    PU0, 21 },	/* AVB_TX_CTL */
+	{ PIN_NUMBER('B', 14),   PU0, 20 },	/* AVB_RD3 */
+	{ PIN_NUMBER('A', 14),   PU0, 19 },	/* AVB_RD2 */
+	{ PIN_NUMBER('B', 13),   PU0, 18 },	/* AVB_RD1 */
+	{ PIN_NUMBER('A', 13),   PU0, 17 },	/* AVB_RD0 */
+	{ PIN_NUMBER('B', 19),   PU0, 16 },	/* AVB_RXC */
+	{ PIN_NUMBER('A', 16),   PU0, 15 },	/* AVB_RX_CTL */
+	{ PIN_NUMBER('V', 7),    PU0, 14 },	/* RPC_RESET# */
+	{ PIN_NUMBER('V', 6),    PU0, 13 },	/* RPC_WP# */
+	{ PIN_NUMBER('Y', 7),    PU0, 12 },	/* RPC_INT# */
+	{ PIN_NUMBER('V', 5),    PU0, 11 },	/* QSPI1_SSL */
+	{ PIN_A_NUMBER('C', 3),  PU0, 10 },	/* QSPI1_IO3 */
+	{ PIN_A_NUMBER('E', 4),  PU0,  9 },	/* QSPI1_IO2 */
+	{ PIN_A_NUMBER('E', 5),  PU0,  8 },	/* QSPI1_MISO_IO1 */
+	{ PIN_A_NUMBER('C', 7),  PU0,  7 },	/* QSPI1_MOSI_IO0 */
+	{ PIN_NUMBER('V', 3),    PU0,  6 },	/* QSPI1_SPCLK */
+	{ PIN_NUMBER('Y', 3),    PU0,  5 },	/* QSPI0_SSL */
+	{ PIN_A_NUMBER('B', 6),  PU0,  4 },	/* QSPI0_IO3 */
+	{ PIN_NUMBER('Y', 6),    PU0,  3 },	/* QSPI0_IO2 */
+	{ PIN_A_NUMBER('B', 4),  PU0,  2 },	/* QSPI0_MISO_IO1 */
+	{ PIN_A_NUMBER('C', 5),  PU0,  1 },	/* QSPI0_MOSI_IO0 */
+	{ PIN_NUMBER('W', 3),    PU0,  0 },	/* QSPI0_SPCLK */
+
+	{ RCAR_GP_PIN(1, 19),    PU1, 31 },	/* A19 */
+	{ RCAR_GP_PIN(1, 18),    PU1, 30 },	/* A18 */
+	{ RCAR_GP_PIN(1, 17),    PU1, 29 },	/* A17 */
+	{ RCAR_GP_PIN(1, 16),    PU1, 28 },	/* A16 */
+	{ RCAR_GP_PIN(1, 15),    PU1, 27 },	/* A15 */
+	{ RCAR_GP_PIN(1, 14),    PU1, 26 },	/* A14 */
+	{ RCAR_GP_PIN(1, 13),    PU1, 25 },	/* A13 */
+	{ RCAR_GP_PIN(1, 12),    PU1, 24 },	/* A12 */
+	{ RCAR_GP_PIN(1, 11),    PU1, 23 },	/* A11 */
+	{ RCAR_GP_PIN(1, 10),    PU1, 22 },	/* A10 */
+	{ RCAR_GP_PIN(1,  9),    PU1, 21 },	/* A9 */
+	{ RCAR_GP_PIN(1,  8),    PU1, 20 },	/* A8 */
+	{ RCAR_GP_PIN(1,  7),    PU1, 19 },	/* A7 */
+	{ RCAR_GP_PIN(1,  6),    PU1, 18 },	/* A6 */
+	{ RCAR_GP_PIN(1,  5),    PU1, 17 },	/* A5 */
+	{ RCAR_GP_PIN(1,  4),    PU1, 16 },	/* A4 */
+	{ RCAR_GP_PIN(1,  3),    PU1, 15 },	/* A3 */
+	{ RCAR_GP_PIN(1,  2),    PU1, 14 },	/* A2 */
+	{ RCAR_GP_PIN(1,  1),    PU1, 13 },	/* A1 */
+	{ RCAR_GP_PIN(1,  0),    PU1, 12 },	/* A0 */
+	{ RCAR_GP_PIN(2,  8),    PU1, 11 },	/* PWM2_A */
+	{ RCAR_GP_PIN(2,  7),    PU1, 10 },	/* PWM1_A */
+	{ RCAR_GP_PIN(2,  6),    PU1,  9 },	/* PWM0 */
+	{ RCAR_GP_PIN(2,  5),    PU1,  8 },	/* IRQ5 */
+	{ RCAR_GP_PIN(2,  4),    PU1,  7 },	/* IRQ4 */
+	{ RCAR_GP_PIN(2,  3),    PU1,  6 },	/* IRQ3 */
+	{ RCAR_GP_PIN(2,  2),    PU1,  5 },	/* IRQ2 */
+	{ RCAR_GP_PIN(2,  1),    PU1,  4 },	/* IRQ1 */
+	{ RCAR_GP_PIN(2,  0),    PU1,  3 },	/* IRQ0 */
+	{ RCAR_GP_PIN(2, 14),    PU1,  2 },	/* AVB_AVTP_CAPTURE_A */
+	{ RCAR_GP_PIN(2, 13),    PU1,  1 },	/* AVB_AVTP_MATCH_A */
+	{ RCAR_GP_PIN(2, 12),    PU1,  0 },	/* AVB_LINK */
+
+	{ PIN_A_NUMBER('P', 8),  PU2, 31 },	/* DU_DOTCLKIN1 */
+	{ PIN_A_NUMBER('P', 7),  PU2, 30 },	/* DU_DOTCLKIN0 */
+	{ RCAR_GP_PIN(7,  3),    PU2, 29 },	/* HDMI1_CEC */
+	{ RCAR_GP_PIN(7,  2),    PU2, 28 },	/* HDMI0_CEC */
+	{ RCAR_GP_PIN(7,  1),    PU2, 27 },	/* AVS2 */
+	{ RCAR_GP_PIN(7,  0),    PU2, 26 },	/* AVS1 */
+	{ RCAR_GP_PIN(0, 15),    PU2, 25 },	/* D15 */
+	{ RCAR_GP_PIN(0, 14),    PU2, 24 },	/* D14 */
+	{ RCAR_GP_PIN(0, 13),    PU2, 23 },	/* D13 */
+	{ RCAR_GP_PIN(0, 12),    PU2, 22 },	/* D12 */
+	{ RCAR_GP_PIN(0, 11),    PU2, 21 },	/* D11 */
+	{ RCAR_GP_PIN(0, 10),    PU2, 20 },	/* D10 */
+	{ RCAR_GP_PIN(0,  9),    PU2, 19 },	/* D9 */
+	{ RCAR_GP_PIN(0,  8),    PU2, 18 },	/* D8 */
+	{ RCAR_GP_PIN(0,  7),    PU2, 17 },	/* D7 */
+	{ RCAR_GP_PIN(0,  6),    PU2, 16 },	/* D6 */
+	{ RCAR_GP_PIN(0,  5),    PU2, 15 },	/* D5 */
+	{ RCAR_GP_PIN(0,  4),    PU2, 14 },	/* D4 */
+	{ RCAR_GP_PIN(0,  3),    PU2, 13 },	/* D3 */
+	{ RCAR_GP_PIN(0,  2),    PU2, 12 },	/* D2 */
+	{ RCAR_GP_PIN(0,  1),    PU2, 11 },	/* D1 */
+	{ RCAR_GP_PIN(0,  0),    PU2, 10 },	/* D0 */
+	{ PIN_NUMBER('C', 1),    PU2,  9 },	/* PRESETOUT# */
+	{ RCAR_GP_PIN(1, 27),    PU2,  8 },	/* EX_WAIT0_A */
+	{ RCAR_GP_PIN(1, 26),    PU2,  7 },	/* WE1_N */
+	{ RCAR_GP_PIN(1, 25),    PU2,  6 },	/* WE0_N */
+	{ RCAR_GP_PIN(1, 24),    PU2,  5 },	/* RD_WR_N */
+	{ RCAR_GP_PIN(1, 23),    PU2,  4 },	/* RD_N */
+	{ RCAR_GP_PIN(1, 22),    PU2,  3 },	/* BS_N */
+	{ RCAR_GP_PIN(1, 21),    PU2,  2 },	/* CS1_N_A26 */
+	{ RCAR_GP_PIN(1, 20),    PU2,  1 },	/* CS0_N */
+	{ PIN_NUMBER('F', 1),    PU2,  0 },	/* CLKOUT */
+
+	{ RCAR_GP_PIN(4,  9),    PU3, 31 },	/* SD3_DAT0 */
+	{ RCAR_GP_PIN(4,  8),    PU3, 30 },	/* SD3_CMD */
+	{ RCAR_GP_PIN(4,  7),    PU3, 29 },	/* SD3_CLK */
+	{ RCAR_GP_PIN(4,  6),    PU3, 28 },	/* SD2_DS */
+	{ RCAR_GP_PIN(4,  5),    PU3, 27 },	/* SD2_DAT3 */
+	{ RCAR_GP_PIN(4,  4),    PU3, 26 },	/* SD2_DAT2 */
+	{ RCAR_GP_PIN(4,  3),    PU3, 25 },	/* SD2_DAT1 */
+	{ RCAR_GP_PIN(4,  2),    PU3, 24 },	/* SD2_DAT0 */
+	{ RCAR_GP_PIN(4,  1),    PU3, 23 },	/* SD2_CMD */
+	{ RCAR_GP_PIN(4,  0),    PU3, 22 },	/* SD2_CLK */
+	{ RCAR_GP_PIN(3, 11),    PU3, 21 },	/* SD1_DAT3 */
+	{ RCAR_GP_PIN(3, 10),    PU3, 20 },	/* SD1_DAT2 */
+	{ RCAR_GP_PIN(3,  9),    PU3, 19 },	/* SD1_DAT1 */
+	{ RCAR_GP_PIN(3,  8),    PU3, 18 },	/* SD1_DAT0 */
+	{ RCAR_GP_PIN(3,  7),    PU3, 17 },	/* SD1_CMD */
+	{ RCAR_GP_PIN(3,  6),    PU3, 16 },	/* SD1_CLK */
+	{ RCAR_GP_PIN(3,  5),    PU3, 15 },	/* SD0_DAT3 */
+	{ RCAR_GP_PIN(3,  4),    PU3, 14 },	/* SD0_DAT2 */
+	{ RCAR_GP_PIN(3,  3),    PU3, 13 },	/* SD0_DAT1 */
+	{ RCAR_GP_PIN(3,  2),    PU3, 12 },	/* SD0_DAT0 */
+	{ RCAR_GP_PIN(3,  1),    PU3, 11 },	/* SD0_CMD */
+	{ RCAR_GP_PIN(3,  0),    PU3, 10 },	/* SD0_CLK */
+	{ PIN_A_NUMBER('T', 30), PU3,  9 },	/* ASEBRK */
+	/* bit 8 n/a */
+	{ PIN_A_NUMBER('R', 29), PU3,  7 },	/* TDI */
+	{ PIN_A_NUMBER('R', 30), PU3,  6 },	/* TMS */
+	{ PIN_A_NUMBER('T', 27), PU3,  5 },	/* TCK */
+	{ PIN_A_NUMBER('R', 26), PU3,  4 },	/* TRST# */
+	{ PIN_A_NUMBER('D', 39), PU3,  3 },	/* EXTALR*/
+	{ PIN_A_NUMBER('D', 38), PU3,  2 },	/* FSCLKST# */
+	{ PIN_A_NUMBER('R', 8),  PU3,  1 },	/* DU_DOTCLKIN3 */
+	{ PIN_A_NUMBER('R', 7),  PU3,  0 },	/* DU_DOTCLKIN2 */
+
+	{ RCAR_GP_PIN(5, 19),    PU4, 31 },	/* MSIOF0_SS1 */
+	{ RCAR_GP_PIN(5, 18),    PU4, 30 },	/* MSIOF0_SYNC */
+	{ RCAR_GP_PIN(5, 17),    PU4, 29 },	/* MSIOF0_SCK */
+	{ RCAR_GP_PIN(5, 16),    PU4, 28 },	/* HRTS0_N */
+	{ RCAR_GP_PIN(5, 15),    PU4, 27 },	/* HCTS0_N */
+	{ RCAR_GP_PIN(5, 14),    PU4, 26 },	/* HTX0 */
+	{ RCAR_GP_PIN(5, 13),    PU4, 25 },	/* HRX0 */
+	{ RCAR_GP_PIN(5, 12),    PU4, 24 },	/* HSCK0 */
+	{ RCAR_GP_PIN(5, 11),    PU4, 23 },	/* RX2_A */
+	{ RCAR_GP_PIN(5, 10),    PU4, 22 },	/* TX2_A */
+	{ RCAR_GP_PIN(5,  9),    PU4, 21 },	/* SCK2 */
+	{ RCAR_GP_PIN(5,  8),    PU4, 20 },	/* RTS1_N_TANS */
+	{ RCAR_GP_PIN(5,  7),    PU4, 19 },	/* CTS1_N */
+	{ RCAR_GP_PIN(5,  6),    PU4, 18 },	/* TX1_A */
+	{ RCAR_GP_PIN(5,  5),    PU4, 17 },	/* RX1_A */
+	{ RCAR_GP_PIN(5,  4),    PU4, 16 },	/* RTS0_N_TANS */
+	{ RCAR_GP_PIN(5,  3),    PU4, 15 },	/* CTS0_N */
+	{ RCAR_GP_PIN(5,  2),    PU4, 14 },	/* TX0 */
+	{ RCAR_GP_PIN(5,  1),    PU4, 13 },	/* RX0 */
+	{ RCAR_GP_PIN(5,  0),    PU4, 12 },	/* SCK0 */
+	{ RCAR_GP_PIN(3, 15),    PU4, 11 },	/* SD1_WP */
+	{ RCAR_GP_PIN(3, 14),    PU4, 10 },	/* SD1_CD */
+	{ RCAR_GP_PIN(3, 13),    PU4,  9 },	/* SD0_WP */
+	{ RCAR_GP_PIN(3, 12),    PU4,  8 },	/* SD0_CD */
+	{ RCAR_GP_PIN(4, 17),    PU4,  7 },	/* SD3_DS */
+	{ RCAR_GP_PIN(4, 16),    PU4,  6 },	/* SD3_DAT7 */
+	{ RCAR_GP_PIN(4, 15),    PU4,  5 },	/* SD3_DAT6 */
+	{ RCAR_GP_PIN(4, 14),    PU4,  4 },	/* SD3_DAT5 */
+	{ RCAR_GP_PIN(4, 13),    PU4,  3 },	/* SD3_DAT4 */
+	{ RCAR_GP_PIN(4, 12),    PU4,  2 },	/* SD3_DAT3 */
+	{ RCAR_GP_PIN(4, 11),    PU4,  1 },	/* SD3_DAT2 */
+	{ RCAR_GP_PIN(4, 10),    PU4,  0 },	/* SD3_DAT1 */
+
+	{ RCAR_GP_PIN(6, 24),    PU5, 31 },	/* USB0_PWEN */
+	{ RCAR_GP_PIN(6, 23),    PU5, 30 },	/* AUDIO_CLKB_B */
+	{ RCAR_GP_PIN(6, 22),    PU5, 29 },	/* AUDIO_CLKA_A */
+	{ RCAR_GP_PIN(6, 21),    PU5, 28 },	/* SSI_SDATA9_A */
+	{ RCAR_GP_PIN(6, 20),    PU5, 27 },	/* SSI_SDATA8 */
+	{ RCAR_GP_PIN(6, 19),    PU5, 26 },	/* SSI_SDATA7 */
+	{ RCAR_GP_PIN(6, 18),    PU5, 25 },	/* SSI_WS78 */
+	{ RCAR_GP_PIN(6, 17),    PU5, 24 },	/* SSI_SCK78 */
+	{ RCAR_GP_PIN(6, 16),    PU5, 23 },	/* SSI_SDATA6 */
+	{ RCAR_GP_PIN(6, 15),    PU5, 22 },	/* SSI_WS6 */
+	{ RCAR_GP_PIN(6, 14),    PU5, 21 },	/* SSI_SCK6 */
+	{ RCAR_GP_PIN(6, 13),    PU5, 20 },	/* SSI_SDATA5 */
+	{ RCAR_GP_PIN(6, 12),    PU5, 19 },	/* SSI_WS5 */
+	{ RCAR_GP_PIN(6, 11),    PU5, 18 },	/* SSI_SCK5 */
+	{ RCAR_GP_PIN(6, 10),    PU5, 17 },	/* SSI_SDATA4 */
+	{ RCAR_GP_PIN(6,  9),    PU5, 16 },	/* SSI_WS4 */
+	{ RCAR_GP_PIN(6,  8),    PU5, 15 },	/* SSI_SCK4 */
+	{ RCAR_GP_PIN(6,  7),    PU5, 14 },	/* SSI_SDATA3 */
+	{ RCAR_GP_PIN(6,  6),    PU5, 13 },	/* SSI_WS34 */
+	{ RCAR_GP_PIN(6,  5),    PU5, 12 },	/* SSI_SCK34 */
+	{ RCAR_GP_PIN(6,  4),    PU5, 11 },	/* SSI_SDATA2_A */
+	{ RCAR_GP_PIN(6,  3),    PU5, 10 },	/* SSI_SDATA1_A */
+	{ RCAR_GP_PIN(6,  2),    PU5,  9 },	/* SSI_SDATA0 */
+	{ RCAR_GP_PIN(6,  1),    PU5,  8 },	/* SSI_WS01239 */
+	{ RCAR_GP_PIN(6,  0),    PU5,  7 },	/* SSI_SCK01239 */
+	{ PIN_NUMBER('H', 37),   PU5,  6 },	/* MLB_REF */
+	{ RCAR_GP_PIN(5, 25),    PU5,  5 },	/* MLB_DAT */
+	{ RCAR_GP_PIN(5, 24),    PU5,  4 },	/* MLB_SIG */
+	{ RCAR_GP_PIN(5, 23),    PU5,  3 },	/* MLB_CLK */
+	{ RCAR_GP_PIN(5, 22),    PU5,  2 },	/* MSIOF0_RXD */
+	{ RCAR_GP_PIN(5, 21),    PU5,  1 },	/* MSIOF0_SS2 */
+	{ RCAR_GP_PIN(5, 20),    PU5,  0 },	/* MSIOF0_TXD */
+
+	{ RCAR_GP_PIN(6, 31),    PU6,  6 },	/* USB31_OVC */
+	{ RCAR_GP_PIN(6, 30),    PU6,  5 },	/* USB31_PWEN */
+	{ RCAR_GP_PIN(6, 29),    PU6,  4 },	/* USB30_OVC */
+	{ RCAR_GP_PIN(6, 28),    PU6,  3 },	/* USB30_PWEN */
+	{ RCAR_GP_PIN(6, 27),    PU6,  2 },	/* USB1_OVC */
+	{ RCAR_GP_PIN(6, 26),    PU6,  1 },	/* USB1_PWEN */
+	{ RCAR_GP_PIN(6, 25),    PU6,  0 },	/* USB0_OVC */
+};
+
+static unsigned int r8a7795es1_pinmux_get_bias(struct sh_pfc *pfc,
+					       unsigned int pin)
+{
+	const struct sh_pfc_bias_info *info;
+	u32 reg;
+	u32 bit;
+
+	info = sh_pfc_pin_to_bias_info(bias_info, ARRAY_SIZE(bias_info), pin);
+	if (!info)
+		return PIN_CONFIG_BIAS_DISABLE;
+
+	reg = info->reg;
+	bit = BIT(info->bit);
+
+	if (!(sh_pfc_read_reg(pfc, PUEN + reg, 32) & bit))
+		return PIN_CONFIG_BIAS_DISABLE;
+	else if (sh_pfc_read_reg(pfc, PUD + reg, 32) & bit)
+		return PIN_CONFIG_BIAS_PULL_UP;
+	else
+		return PIN_CONFIG_BIAS_PULL_DOWN;
+}
+
+static void r8a7795es1_pinmux_set_bias(struct sh_pfc *pfc, unsigned int pin,
+				       unsigned int bias)
+{
+	const struct sh_pfc_bias_info *info;
+	u32 enable, updown;
+	u32 reg;
+	u32 bit;
+
+	info = sh_pfc_pin_to_bias_info(bias_info, ARRAY_SIZE(bias_info), pin);
+	if (!info)
+		return;
+
+	reg = info->reg;
+	bit = BIT(info->bit);
+
+	enable = sh_pfc_read_reg(pfc, PUEN + reg, 32) & ~bit;
+	if (bias != PIN_CONFIG_BIAS_DISABLE)
+		enable |= bit;
+
+	updown = sh_pfc_read_reg(pfc, PUD + reg, 32) & ~bit;
+	if (bias == PIN_CONFIG_BIAS_PULL_UP)
+		updown |= bit;
+
+	sh_pfc_write_reg(pfc, PUD + reg, 32, updown);
+	sh_pfc_write_reg(pfc, PUEN + reg, 32, enable);
+}
+
+static const struct sh_pfc_soc_operations r8a7795es1_pinmux_ops = {
+	.pin_to_pocctrl = r8a7795es1_pin_to_pocctrl,
+	.get_bias = r8a7795es1_pinmux_get_bias,
+	.set_bias = r8a7795es1_pinmux_set_bias,
+};
+
+const struct sh_pfc_soc_info r8a7795es1_pinmux_info = {
+	.name = "r8a77950_pfc",
+	.ops = &r8a7795es1_pinmux_ops,
+	.unlock_reg = 0xe6060000, /* PMMR */
+
+	.function = { PINMUX_FUNCTION_BEGIN, PINMUX_FUNCTION_END },
+
+	.pins = pinmux_pins,
+	.nr_pins = ARRAY_SIZE(pinmux_pins),
+	.groups = pinmux_groups,
+	.nr_groups = ARRAY_SIZE(pinmux_groups),
+	.functions = pinmux_functions,
+	.nr_functions = ARRAY_SIZE(pinmux_functions),
+
+	.cfg_regs = pinmux_config_regs,
+	.drive_regs = pinmux_drive_regs,
+
+	.pinmux_data = pinmux_data,
+	.pinmux_data_size = ARRAY_SIZE(pinmux_data),
+};
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
index 504d0c3d7f74..0454f31c0831 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
@@ -1,7 +1,7 @@
 /*
- * R8A7795 processor support - PFC hardware block.
+ * R8A7795 ES2.0+ processor support - PFC hardware block.
  *
- * Copyright (C) 2015  Renesas Electronics Corporation
+ * Copyright (C) 2015-2016 Renesas Electronics Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -9,6 +9,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sys_soc.h>
 
 #include "core.h"
 #include "sh_pfc.h"
@@ -101,10 +102,10 @@
 #define GPSR2_0		F_(IRQ0,		IP0_27_24)
 
 /* GPSR3 */
-#define GPSR3_15	F_(SD1_WP,		IP10_23_20)
-#define GPSR3_14	F_(SD1_CD,		IP10_19_16)
-#define GPSR3_13	F_(SD0_WP,		IP10_15_12)
-#define GPSR3_12	F_(SD0_CD,		IP10_11_8)
+#define GPSR3_15	F_(SD1_WP,		IP11_23_20)
+#define GPSR3_14	F_(SD1_CD,		IP11_19_16)
+#define GPSR3_13	F_(SD0_WP,		IP11_15_12)
+#define GPSR3_12	F_(SD0_CD,		IP11_11_8)
 #define GPSR3_11	F_(SD1_DAT3,		IP8_31_28)
 #define GPSR3_10	F_(SD1_DAT2,		IP8_27_24)
 #define GPSR3_9		F_(SD1_DAT1,		IP8_23_20)
@@ -119,86 +120,86 @@
 #define GPSR3_0		F_(SD0_CLK,		IP7_19_16)
 
 /* GPSR4 */
-#define GPSR4_17	FM(SD3_DS)
-#define GPSR4_16	F_(SD3_DAT7,		IP10_7_4)
-#define GPSR4_15	F_(SD3_DAT6,		IP10_3_0)
-#define GPSR4_14	F_(SD3_DAT5,		IP9_31_28)
-#define GPSR4_13	F_(SD3_DAT4,		IP9_27_24)
-#define GPSR4_12	FM(SD3_DAT3)
-#define GPSR4_11	FM(SD3_DAT2)
-#define GPSR4_10	FM(SD3_DAT1)
-#define GPSR4_9		FM(SD3_DAT0)
-#define GPSR4_8		FM(SD3_CMD)
-#define GPSR4_7		FM(SD3_CLK)
-#define GPSR4_6		F_(SD2_DS,		IP9_23_20)
-#define GPSR4_5		F_(SD2_DAT3,		IP9_19_16)
-#define GPSR4_4		F_(SD2_DAT2,		IP9_15_12)
-#define GPSR4_3		F_(SD2_DAT1,		IP9_11_8)
-#define GPSR4_2		F_(SD2_DAT0,		IP9_7_4)
-#define GPSR4_1		FM(SD2_CMD)
+#define GPSR4_17	F_(SD3_DS,		IP11_7_4)
+#define GPSR4_16	F_(SD3_DAT7,		IP11_3_0)
+#define GPSR4_15	F_(SD3_DAT6,		IP10_31_28)
+#define GPSR4_14	F_(SD3_DAT5,		IP10_27_24)
+#define GPSR4_13	F_(SD3_DAT4,		IP10_23_20)
+#define GPSR4_12	F_(SD3_DAT3,		IP10_19_16)
+#define GPSR4_11	F_(SD3_DAT2,		IP10_15_12)
+#define GPSR4_10	F_(SD3_DAT1,		IP10_11_8)
+#define GPSR4_9		F_(SD3_DAT0,		IP10_7_4)
+#define GPSR4_8		F_(SD3_CMD,		IP10_3_0)
+#define GPSR4_7		F_(SD3_CLK,		IP9_31_28)
+#define GPSR4_6		F_(SD2_DS,		IP9_27_24)
+#define GPSR4_5		F_(SD2_DAT3,		IP9_23_20)
+#define GPSR4_4		F_(SD2_DAT2,		IP9_19_16)
+#define GPSR4_3		F_(SD2_DAT1,		IP9_15_12)
+#define GPSR4_2		F_(SD2_DAT0,		IP9_11_8)
+#define GPSR4_1		F_(SD2_CMD,		IP9_7_4)
 #define GPSR4_0		F_(SD2_CLK,		IP9_3_0)
 
 /* GPSR5 */
-#define GPSR5_25	F_(MLB_DAT,		IP13_19_16)
-#define GPSR5_24	F_(MLB_SIG,		IP13_15_12)
-#define GPSR5_23	F_(MLB_CLK,		IP13_11_8)
+#define GPSR5_25	F_(MLB_DAT,		IP14_19_16)
+#define GPSR5_24	F_(MLB_SIG,		IP14_15_12)
+#define GPSR5_23	F_(MLB_CLK,		IP14_11_8)
 #define GPSR5_22	FM(MSIOF0_RXD)
-#define GPSR5_21	F_(MSIOF0_SS2,		IP13_7_4)
+#define GPSR5_21	F_(MSIOF0_SS2,		IP14_7_4)
 #define GPSR5_20	FM(MSIOF0_TXD)
-#define GPSR5_19	F_(MSIOF0_SS1,		IP13_3_0)
-#define GPSR5_18	F_(MSIOF0_SYNC,		IP12_31_28)
+#define GPSR5_19	F_(MSIOF0_SS1,		IP14_3_0)
+#define GPSR5_18	F_(MSIOF0_SYNC,		IP13_31_28)
 #define GPSR5_17	FM(MSIOF0_SCK)
-#define GPSR5_16	F_(HRTS0_N,		IP12_27_24)
-#define GPSR5_15	F_(HCTS0_N,		IP12_23_20)
-#define GPSR5_14	F_(HTX0,		IP12_19_16)
-#define GPSR5_13	F_(HRX0,		IP12_15_12)
-#define GPSR5_12	F_(HSCK0,		IP12_11_8)
-#define GPSR5_11	F_(RX2_A,		IP12_7_4)
-#define GPSR5_10	F_(TX2_A,		IP12_3_0)
-#define GPSR5_9		F_(SCK2,		IP11_31_28)
-#define GPSR5_8		F_(RTS1_N_TANS,		IP11_27_24)
-#define GPSR5_7		F_(CTS1_N,		IP11_23_20)
-#define GPSR5_6		F_(TX1_A,		IP11_19_16)
-#define GPSR5_5		F_(RX1_A,		IP11_15_12)
-#define GPSR5_4		F_(RTS0_N_TANS,		IP11_11_8)
-#define GPSR5_3		F_(CTS0_N,		IP11_7_4)
-#define GPSR5_2		F_(TX0,			IP11_3_0)
-#define GPSR5_1		F_(RX0,			IP10_31_28)
-#define GPSR5_0		F_(SCK0,		IP10_27_24)
+#define GPSR5_16	F_(HRTS0_N,		IP13_27_24)
+#define GPSR5_15	F_(HCTS0_N,		IP13_23_20)
+#define GPSR5_14	F_(HTX0,		IP13_19_16)
+#define GPSR5_13	F_(HRX0,		IP13_15_12)
+#define GPSR5_12	F_(HSCK0,		IP13_11_8)
+#define GPSR5_11	F_(RX2_A,		IP13_7_4)
+#define GPSR5_10	F_(TX2_A,		IP13_3_0)
+#define GPSR5_9		F_(SCK2,		IP12_31_28)
+#define GPSR5_8		F_(RTS1_N_TANS,		IP12_27_24)
+#define GPSR5_7		F_(CTS1_N,		IP12_23_20)
+#define GPSR5_6		F_(TX1_A,		IP12_19_16)
+#define GPSR5_5		F_(RX1_A,		IP12_15_12)
+#define GPSR5_4		F_(RTS0_N_TANS,		IP12_11_8)
+#define GPSR5_3		F_(CTS0_N,		IP12_7_4)
+#define GPSR5_2		F_(TX0,			IP12_3_0)
+#define GPSR5_1		F_(RX0,			IP11_31_28)
+#define GPSR5_0		F_(SCK0,		IP11_27_24)
 
 /* GPSR6 */
-#define GPSR6_31	F_(USB31_OVC,		IP17_7_4)
-#define GPSR6_30	F_(USB31_PWEN,		IP17_3_0)
-#define GPSR6_29	F_(USB30_OVC,		IP16_31_28)
-#define GPSR6_28	F_(USB30_PWEN,		IP16_27_24)
-#define GPSR6_27	F_(USB1_OVC,		IP16_23_20)
-#define GPSR6_26	F_(USB1_PWEN,		IP16_19_16)
-#define GPSR6_25	F_(USB0_OVC,		IP16_15_12)
-#define GPSR6_24	F_(USB0_PWEN,		IP16_11_8)
-#define GPSR6_23	F_(AUDIO_CLKB_B,	IP16_7_4)
-#define GPSR6_22	F_(AUDIO_CLKA_A,	IP16_3_0)
-#define GPSR6_21	F_(SSI_SDATA9_A,	IP15_31_28)
-#define GPSR6_20	F_(SSI_SDATA8,		IP15_27_24)
-#define GPSR6_19	F_(SSI_SDATA7,		IP15_23_20)
-#define GPSR6_18	F_(SSI_WS78,		IP15_19_16)
-#define GPSR6_17	F_(SSI_SCK78,		IP15_15_12)
-#define GPSR6_16	F_(SSI_SDATA6,		IP15_11_8)
-#define GPSR6_15	F_(SSI_WS6,		IP15_7_4)
-#define GPSR6_14	F_(SSI_SCK6,		IP15_3_0)
+#define GPSR6_31	F_(USB3_OVC,		IP18_7_4)
+#define GPSR6_30	F_(USB3_PWEN,		IP18_3_0)
+#define GPSR6_29	F_(USB30_OVC,		IP17_31_28)
+#define GPSR6_28	F_(USB30_PWEN,		IP17_27_24)
+#define GPSR6_27	F_(USB1_OVC,		IP17_23_20)
+#define GPSR6_26	F_(USB1_PWEN,		IP17_19_16)
+#define GPSR6_25	F_(USB0_OVC,		IP17_15_12)
+#define GPSR6_24	F_(USB0_PWEN,		IP17_11_8)
+#define GPSR6_23	F_(AUDIO_CLKB_B,	IP17_7_4)
+#define GPSR6_22	F_(AUDIO_CLKA_A,	IP17_3_0)
+#define GPSR6_21	F_(SSI_SDATA9_A,	IP16_31_28)
+#define GPSR6_20	F_(SSI_SDATA8,		IP16_27_24)
+#define GPSR6_19	F_(SSI_SDATA7,		IP16_23_20)
+#define GPSR6_18	F_(SSI_WS78,		IP16_19_16)
+#define GPSR6_17	F_(SSI_SCK78,		IP16_15_12)
+#define GPSR6_16	F_(SSI_SDATA6,		IP16_11_8)
+#define GPSR6_15	F_(SSI_WS6,		IP16_7_4)
+#define GPSR6_14	F_(SSI_SCK6,		IP16_3_0)
 #define GPSR6_13	FM(SSI_SDATA5)
 #define GPSR6_12	FM(SSI_WS5)
 #define GPSR6_11	FM(SSI_SCK5)
-#define GPSR6_10	F_(SSI_SDATA4,		IP14_31_28)
-#define GPSR6_9		F_(SSI_WS4,		IP14_27_24)
-#define GPSR6_8		F_(SSI_SCK4,		IP14_23_20)
-#define GPSR6_7		F_(SSI_SDATA3,		IP14_19_16)
-#define GPSR6_6		F_(SSI_WS34,		IP14_15_12)
-#define GPSR6_5		F_(SSI_SCK34,		IP14_11_8)
-#define GPSR6_4		F_(SSI_SDATA2_A,	IP14_7_4)
-#define GPSR6_3		F_(SSI_SDATA1_A,	IP14_3_0)
-#define GPSR6_2		F_(SSI_SDATA0,		IP13_31_28)
-#define GPSR6_1		F_(SSI_WS01239,		IP13_27_24)
-#define GPSR6_0		F_(SSI_SCK01239,	IP13_23_20)
+#define GPSR6_10	F_(SSI_SDATA4,		IP15_31_28)
+#define GPSR6_9		F_(SSI_WS4,		IP15_27_24)
+#define GPSR6_8		F_(SSI_SCK4,		IP15_23_20)
+#define GPSR6_7		F_(SSI_SDATA3,		IP15_19_16)
+#define GPSR6_6		F_(SSI_WS34,		IP15_15_12)
+#define GPSR6_5		F_(SSI_SCK34,		IP15_11_8)
+#define GPSR6_4		F_(SSI_SDATA2_A,	IP15_7_4)
+#define GPSR6_3		F_(SSI_SDATA1_A,	IP15_3_0)
+#define GPSR6_2		F_(SSI_SDATA0,		IP14_31_28)
+#define GPSR6_1		F_(SSI_WS01239,		IP14_27_24)
+#define GPSR6_0		F_(SSI_SCK01239,		IP14_23_20)
 
 /* GPSR7 */
 #define GPSR7_3		FM(HDMI1_CEC)
@@ -212,14 +213,14 @@
 #define IP0_7_4		FM(AVB_MAGIC)		F_(0, 0)	FM(MSIOF2_SS1_C)	FM(SCK4_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP0_11_8	FM(AVB_PHY_INT)		F_(0, 0)	FM(MSIOF2_SYNC_C)	FM(RX4_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP0_15_12	FM(AVB_LINK)		F_(0, 0)	FM(MSIOF2_SCK_C)	FM(TX4_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP0_19_16	FM(AVB_AVTP_MATCH_A)	F_(0, 0)	FM(MSIOF2_RXD_C)	FM(CTS4_N_A)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_19_16	FM(AVB_AVTP_MATCH_A)	F_(0, 0)	FM(MSIOF2_RXD_C)	FM(CTS4_N_A)			F_(0, 0)	FM(FSCLKST2_N_A) F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP0_23_20	FM(AVB_AVTP_CAPTURE_A)	F_(0, 0)	FM(MSIOF2_TXD_C)	FM(RTS4_N_TANS_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP0_27_24	FM(IRQ0)		FM(QPOLB)	F_(0, 0)		FM(DU_CDE)			FM(VI4_DATA0_B)	FM(CAN0_TX_B)	FM(CANFD0_TX_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP0_31_28	FM(IRQ1)		FM(QPOLA)	F_(0, 0)		FM(DU_DISP)			FM(VI4_DATA1_B)	FM(CAN0_RX_B)	FM(CANFD0_RX_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP1_3_0		FM(IRQ2)		FM(QCPV_QDE)	F_(0, 0)		FM(DU_EXODDF_DU_ODDF_DISP_CDE)	FM(VI4_DATA2_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM3_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP1_7_4		FM(IRQ3)		FM(QSTVB_QVE)	FM(A25)			FM(DU_DOTCLKOUT1)		FM(VI4_DATA3_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM4_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP1_11_8	FM(IRQ4)		FM(QSTH_QHS)	FM(A24)			FM(DU_EXHSYNC_DU_HSYNC)		FM(VI4_DATA4_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM5_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP1_15_12	FM(IRQ5)		FM(QSTB_QHE)	FM(A23)			FM(DU_EXVSYNC_DU_VSYNC)		FM(VI4_DATA5_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(PWM6_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_27_24	FM(IRQ0)		FM(QPOLB)	F_(0, 0)		FM(DU_CDE)			FM(VI4_DATA0_B) FM(CAN0_TX_B)	FM(CANFD0_TX_B)		FM(MSIOF3_SS1_E) F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP0_31_28	FM(IRQ1)		FM(QPOLA)	F_(0, 0)		FM(DU_DISP)			FM(VI4_DATA1_B) FM(CAN0_RX_B)	FM(CANFD0_RX_B)		FM(MSIOF3_SS2_E) F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_3_0		FM(IRQ2)		FM(QCPV_QDE)	F_(0, 0)		FM(DU_EXODDF_DU_ODDF_DISP_CDE)	FM(VI4_DATA2_B) F_(0, 0)	F_(0, 0)		FM(MSIOF3_SYNC_E) F_(0, 0)		FM(PWM3_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_7_4		FM(IRQ3)		FM(QSTVB_QVE)	FM(A25)			FM(DU_DOTCLKOUT1)		FM(VI4_DATA3_B) F_(0, 0)	F_(0, 0)		FM(MSIOF3_SCK_E) F_(0, 0)		FM(PWM4_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_11_8	FM(IRQ4)		FM(QSTH_QHS)	FM(A24)			FM(DU_EXHSYNC_DU_HSYNC)		FM(VI4_DATA4_B) F_(0, 0)	F_(0, 0)		FM(MSIOF3_RXD_E) F_(0, 0)		FM(PWM5_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP1_15_12	FM(IRQ5)		FM(QSTB_QHE)	FM(A23)			FM(DU_EXVSYNC_DU_VSYNC)		FM(VI4_DATA5_B) FM(FSCLKST2_N_B) F_(0, 0)		FM(MSIOF3_TXD_E) F_(0, 0)		FM(PWM6_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP1_19_16	FM(PWM0)		FM(AVB_AVTP_PPS)FM(A22)			F_(0, 0)			FM(VI4_DATA6_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(IECLK_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP1_23_20	FM(PWM1_A)		F_(0, 0)	FM(A21)			FM(HRX3_D)			FM(VI4_DATA7_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(IERX_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP1_27_24	FM(PWM2_A)		F_(0, 0)	FM(A20)			FM(HTX3_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		FM(IETX_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
@@ -279,79 +280,89 @@
 #define IP8_3_0		FM(SD0_DAT2)		F_(0, 0)	FM(MSIOF1_SS1_E)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_B)	FM(STP_ISD_0_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP8_7_4		FM(SD0_DAT3)		F_(0, 0)	FM(MSIOF1_SS2_E)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_B)	FM(STP_ISEN_0_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP8_11_8	FM(SD1_CLK)		F_(0, 0)	FM(MSIOF1_SCK_G)	F_(0, 0)			F_(0, 0)	FM(SIM0_CLK_A)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP8_15_12	FM(SD1_CMD)		F_(0, 0)	FM(MSIOF1_SYNC_G)	F_(0, 0)			F_(0, 0)	FM(SIM0_D_A)	FM(STP_IVCXO27_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP8_19_16	FM(SD1_DAT0)		FM(SD2_DAT4)	FM(MSIOF1_RXD_G)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_B)	FM(STP_ISCLK_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP8_23_20	FM(SD1_DAT1)		FM(SD2_DAT5)	FM(MSIOF1_TXD_G)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_B)FM(STP_ISSYNC_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP8_27_24	FM(SD1_DAT2)		FM(SD2_DAT6)	FM(MSIOF1_SS1_G)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_B)	FM(STP_ISD_1_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP8_31_28	FM(SD1_DAT3)		FM(SD2_DAT7)	FM(MSIOF1_SS2_G)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_B)	FM(STP_ISEN_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_3_0		FM(SD2_CLK)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_7_4		FM(SD2_DAT0)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_11_8	FM(SD2_DAT1)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_15_12	FM(SD2_DAT2)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_19_16	FM(SD2_DAT3)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_23_20	FM(SD2_DS)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(SATA_DEVSLP_B)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_27_24	FM(SD3_DAT4)		FM(SD2_CD_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP9_31_28	FM(SD3_DAT5)		FM(SD2_WP_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_3_0	FM(SD3_DAT6)		FM(SD3_CD)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_7_4	FM(SD3_DAT7)		FM(SD3_WP)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_11_8	FM(SD0_CD)		F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SCL2_B)	FM(SIM0_RST_A)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_15_12	FM(SD0_WP)		F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SDA2_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_19_16	FM(SD1_CD)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(SIM0_CLK_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_23_20	FM(SD1_WP)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(SIM0_D_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_27_24	FM(SCK0)		FM(HSCK1_B)	FM(MSIOF1_SS2_B)	FM(AUDIO_CLKC_B)		FM(SDA2_A)	FM(SIM0_RST_B)	FM(STP_OPWM_0_C)	FM(RIF0_CLK_B)	F_(0, 0)		FM(ADICHS2)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP10_31_28	FM(RX0)			FM(HRX1_B)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SCK0_C)	FM(STP_ISCLK_0_C)	FM(RIF0_D0_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_3_0	FM(TX0)			FM(HTX1_B)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_C)FM(STP_ISSYNC_0_C)	FM(RIF0_D1_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_7_4	FM(CTS0_N)		FM(HCTS1_N_B)	FM(MSIOF1_SYNC_B)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_C)FM(STP_ISSYNC_1_C)	FM(RIF1_SYNC_B)	FM(AUDIO_CLKOUT_C)	FM(ADICS_SAMP)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_11_8	FM(RTS0_N_TANS)		FM(HRTS1_N_B)	FM(MSIOF1_SS1_B)	FM(AUDIO_CLKA_B)		FM(SCL2_A)	F_(0, 0)	FM(STP_IVCXO27_1_C)	FM(RIF0_SYNC_B)	F_(0, 0)		FM(ADICHS1)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_15_12	FM(RX1_A)		FM(HRX1_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_C)	FM(STP_ISD_0_C)		FM(RIF1_CLK_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_19_16	FM(TX1_A)		FM(HTX1_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_C)	FM(STP_ISEN_0_C)	FM(RIF1_D0_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_23_20	FM(CTS1_N)		FM(HCTS1_N_A)	FM(MSIOF1_RXD_B)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_C)	FM(STP_ISEN_1_C)	FM(RIF1_D0_B)	F_(0, 0)		FM(ADIDATA)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_27_24	FM(RTS1_N_TANS)		FM(HRTS1_N_A)	FM(MSIOF1_TXD_B)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_C)	FM(STP_ISD_1_C)		FM(RIF1_D1_B)	F_(0, 0)		FM(ADICHS0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_31_28	FM(SCK2)		FM(SCIF_CLK_B)	FM(MSIOF1_SCK_B)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_C)	FM(STP_ISCLK_1_C)	FM(RIF1_CLK_B)	F_(0, 0)		FM(ADICLK)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_3_0	FM(TX2_A)		F_(0, 0)	F_(0, 0)		FM(SD2_CD_B)			FM(SCL1_A)	F_(0, 0)	FM(FMCLK_A)		FM(RIF1_D1_C)	F_(0, 0)		FM(FSO_CFE_0_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_7_4	FM(RX2_A)		F_(0, 0)	F_(0, 0)		FM(SD2_WP_B)			FM(SDA1_A)	F_(0, 0)	FM(FMIN_A)		FM(RIF1_SYNC_C)	F_(0, 0)		FM(FSO_CFE_1_B)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_11_8	FM(HSCK0)		F_(0, 0)	FM(MSIOF1_SCK_D)	FM(AUDIO_CLKB_A)		FM(SSI_SDATA1_B)FM(TS_SCK0_D)	FM(STP_ISCLK_0_D)	FM(RIF0_CLK_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_15_12	FM(HRX0)		F_(0, 0)	FM(MSIOF1_RXD_D)	F_(0, 0)			FM(SSI_SDATA2_B)FM(TS_SDEN0_D)	FM(STP_ISEN_0_D)	FM(RIF0_D0_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_19_16	FM(HTX0)		F_(0, 0)	FM(MSIOF1_TXD_D)	F_(0, 0)			FM(SSI_SDATA9_B)FM(TS_SDAT0_D)	FM(STP_ISD_0_D)		FM(RIF0_D1_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_23_20	FM(HCTS0_N)		FM(RX2_B)	FM(MSIOF1_SYNC_D)	F_(0, 0)			FM(SSI_SCK9_A)	FM(TS_SPSYNC0_D)FM(STP_ISSYNC_0_D)	FM(RIF0_SYNC_C)	FM(AUDIO_CLKOUT1_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP12_27_24	FM(HRTS0_N)		FM(TX2_B)	FM(MSIOF1_SS1_D)	F_(0, 0)			FM(SSI_WS9_A)	F_(0, 0)	FM(STP_IVCXO27_0_D)	FM(BPFCLK_A)	FM(AUDIO_CLKOUT2_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_15_12	FM(SD1_CMD)		F_(0, 0)	FM(MSIOF1_SYNC_G)	FM(NFCE_N_B)			F_(0, 0)	FM(SIM0_D_A)	FM(STP_IVCXO27_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_19_16	FM(SD1_DAT0)		FM(SD2_DAT4)	FM(MSIOF1_RXD_G)	FM(NFWP_N_B)			F_(0, 0)	FM(TS_SCK1_B)	FM(STP_ISCLK_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_23_20	FM(SD1_DAT1)		FM(SD2_DAT5)	FM(MSIOF1_TXD_G)	FM(NFDATA14_B)			F_(0, 0)	FM(TS_SPSYNC1_B)FM(STP_ISSYNC_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_27_24	FM(SD1_DAT2)		FM(SD2_DAT6)	FM(MSIOF1_SS1_G)	FM(NFDATA15_B)			F_(0, 0)	FM(TS_SDAT1_B)	FM(STP_ISD_1_B)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP8_31_28	FM(SD1_DAT3)		FM(SD2_DAT7)	FM(MSIOF1_SS2_G)	FM(NFRB_N_B)			F_(0, 0)	FM(TS_SDEN1_B)	FM(STP_ISEN_1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_3_0		FM(SD2_CLK)		F_(0, 0)	F_(0, 0)		FM(NFDATA8)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_7_4		FM(SD2_CMD)		F_(0, 0)	F_(0, 0)		FM(NFDATA9)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_11_8	FM(SD2_DAT0)		F_(0, 0)	F_(0, 0)		FM(NFDATA10)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_15_12	FM(SD2_DAT1)		F_(0, 0)	F_(0, 0)		FM(NFDATA11)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_19_16	FM(SD2_DAT2)		F_(0, 0)	F_(0, 0)		FM(NFDATA12)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_23_20	FM(SD2_DAT3)		F_(0, 0)	F_(0, 0)		FM(NFDATA13)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_27_24	FM(SD2_DS)		F_(0, 0)	F_(0, 0)		FM(NFALE)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(SATA_DEVSLP_B)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP9_31_28	FM(SD3_CLK)		F_(0, 0)	F_(0, 0)		FM(NFWE_N)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_3_0	FM(SD3_CMD)		F_(0, 0)	F_(0, 0)		FM(NFRE_N)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_7_4	FM(SD3_DAT0)		F_(0, 0)	F_(0, 0)		FM(NFDATA0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_11_8	FM(SD3_DAT1)		F_(0, 0)	F_(0, 0)		FM(NFDATA1)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_15_12	FM(SD3_DAT2)		F_(0, 0)	F_(0, 0)		FM(NFDATA2)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_19_16	FM(SD3_DAT3)		F_(0, 0)	F_(0, 0)		FM(NFDATA3)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_23_20	FM(SD3_DAT4)		FM(SD2_CD_A)	F_(0, 0)		FM(NFDATA4)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_27_24	FM(SD3_DAT5)		FM(SD2_WP_A)	F_(0, 0)		FM(NFDATA5)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP10_31_28	FM(SD3_DAT6)		FM(SD3_CD)	F_(0, 0)		FM(NFDATA6)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_3_0	FM(SD3_DAT7)		FM(SD3_WP)	F_(0, 0)		FM(NFDATA7)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_7_4	FM(SD3_DS)		F_(0, 0)	F_(0, 0)		FM(NFCLE)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_11_8	FM(SD0_CD)		F_(0, 0)	FM(NFDATA14_A)		F_(0, 0)			FM(SCL2_B)	FM(SIM0_RST_A)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 
 /* IPSRx */		/* 0 */			/* 1 */		/* 2 */			/* 3 */				/* 4 */		/* 5 */		/* 6 */			/* 7 */		/* 8 */			/* 9 */		/* A */		/* B */		/* C - F */
-#define IP12_31_28	FM(MSIOF0_SYNC)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(AUDIO_CLKOUT_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_3_0	FM(MSIOF0_SS1)		FM(RX5)		F_(0, 0)		FM(AUDIO_CLKA_C)		FM(SSI_SCK2_A)	F_(0, 0)	FM(STP_IVCXO27_0_C)	F_(0, 0)	FM(AUDIO_CLKOUT3_A)	F_(0, 0)	FM(TCLK1_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_7_4	FM(MSIOF0_SS2)		FM(TX5)		FM(MSIOF1_SS2_D)	FM(AUDIO_CLKC_A)		FM(SSI_WS2_A)	F_(0, 0)	FM(STP_OPWM_0_D)	F_(0, 0)	FM(AUDIO_CLKOUT_D)	F_(0, 0)	FM(SPEEDIN_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_11_8	FM(MLB_CLK)		F_(0, 0)	FM(MSIOF1_SCK_F)	F_(0, 0)			FM(SCL1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_15_12	FM(MLB_SIG)		FM(RX1_B)	FM(MSIOF1_SYNC_F)	F_(0, 0)			FM(SDA1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_19_16	FM(MLB_DAT)		FM(TX1_B)	FM(MSIOF1_RXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_23_20	FM(SSI_SCK01239)	F_(0, 0)	FM(MSIOF1_TXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_27_24	FM(SSI_WS01239)		F_(0, 0)	FM(MSIOF1_SS1_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_31_28	FM(SSI_SDATA0)		F_(0, 0)	FM(MSIOF1_SS2_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_3_0	FM(SSI_SDATA1_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_7_4	FM(SSI_SDATA2_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SSI_SCK1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_11_8	FM(SSI_SCK34)		F_(0, 0)	FM(MSIOF1_SS1_A)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_OPWM_0_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_15_12	FM(SSI_WS34)		FM(HCTS2_N_A)	FM(MSIOF1_SS2_A)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_0_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_19_16	FM(SSI_SDATA3)		FM(HRTS2_N_A)	FM(MSIOF1_TXD_A)	F_(0, 0)			F_(0, 0)	FM(TS_SCK0_A)	FM(STP_ISCLK_0_A)	FM(RIF0_D1_A)	FM(RIF2_D0_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_23_20	FM(SSI_SCK4)		FM(HRX2_A)	FM(MSIOF1_SCK_A)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_A)	FM(STP_ISD_0_A)		FM(RIF0_CLK_A)	FM(RIF2_CLK_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_27_24	FM(SSI_WS4)		FM(HTX2_A)	FM(MSIOF1_SYNC_A)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_A)	FM(STP_ISEN_0_A)	FM(RIF0_SYNC_A)	FM(RIF2_SYNC_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP14_31_28	FM(SSI_SDATA4)		FM(HSCK2_A)	FM(MSIOF1_RXD_A)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_A)FM(STP_ISSYNC_0_A)	FM(RIF0_D0_A)	FM(RIF2_D1_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_3_0	FM(SSI_SCK6)		FM(USB2_PWEN)	F_(0, 0)		FM(SIM0_RST_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_7_4	FM(SSI_WS6)		FM(USB2_OVC)	F_(0, 0)		FM(SIM0_D_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_11_8	FM(SSI_SDATA6)		F_(0, 0)	F_(0, 0)		FM(SIM0_CLK_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(SATA_DEVSLP_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_15_12	FM(SSI_SCK78)		FM(HRX2_B)	FM(MSIOF1_SCK_C)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_A)	FM(STP_ISCLK_1_A)	FM(RIF1_CLK_A)	FM(RIF3_CLK_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_19_16	FM(SSI_WS78)		FM(HTX2_B)	FM(MSIOF1_SYNC_C)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_A)	FM(STP_ISD_1_A)		FM(RIF1_SYNC_A)	FM(RIF3_SYNC_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_23_20	FM(SSI_SDATA7)		FM(HCTS2_N_B)	FM(MSIOF1_RXD_C)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_A)	FM(STP_ISEN_1_A)	FM(RIF1_D0_A)	FM(RIF3_D0_A)		F_(0, 0)	FM(TCLK2_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_27_24	FM(SSI_SDATA8)		FM(HRTS2_N_B)	FM(MSIOF1_TXD_C)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_A)FM(STP_ISSYNC_1_A)	FM(RIF1_D1_A)	FM(RIF3_D1_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP15_31_28	FM(SSI_SDATA9_A)	FM(HSCK2_B)	FM(MSIOF1_SS1_C)	FM(HSCK1_A)			FM(SSI_WS1_B)	FM(SCK1)	FM(STP_IVCXO27_1_A)	FM(SCK5)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_3_0	FM(AUDIO_CLKA_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	FM(CC5_OSCOUT)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_7_4	FM(AUDIO_CLKB_B)	FM(SCIF_CLK_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_1_D)	FM(REMOCON_A)	F_(0, 0)		F_(0, 0)	FM(TCLK1_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_11_8	FM(USB0_PWEN)		F_(0, 0)	F_(0, 0)		FM(SIM0_RST_C)			F_(0, 0)	FM(TS_SCK1_D)	FM(STP_ISCLK_1_D)	FM(BPFCLK_B)	FM(RIF3_CLK_B)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_15_12	FM(USB0_OVC)		F_(0, 0)	F_(0, 0)		FM(SIM0_D_C)			F_(0, 0)	FM(TS_SDAT1_D)	FM(STP_ISD_1_D)		F_(0, 0)	FM(RIF3_SYNC_B)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_19_16	FM(USB1_PWEN)		F_(0, 0)	F_(0, 0)		FM(SIM0_CLK_C)			FM(SSI_SCK1_A)	FM(TS_SCK0_E)	FM(STP_ISCLK_0_E)	FM(FMCLK_B)	FM(RIF2_CLK_B)		F_(0, 0)	FM(SPEEDIN_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_23_20	FM(USB1_OVC)		F_(0, 0)	FM(MSIOF1_SS2_C)	F_(0, 0)			FM(SSI_WS1_A)	FM(TS_SDAT0_E)	FM(STP_ISD_0_E)		FM(FMIN_B)	FM(RIF2_SYNC_B)		F_(0, 0)	FM(REMOCON_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_27_24	FM(USB30_PWEN)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT_B)		FM(SSI_SCK2_B)	FM(TS_SDEN1_D)	FM(STP_ISEN_1_D)	FM(STP_OPWM_0_E)FM(RIF3_D0_B)		F_(0, 0)	FM(TCLK2_B)	FM(TPU0TO0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP16_31_28	FM(USB30_OVC)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT1_B)		FM(SSI_WS2_B)	FM(TS_SPSYNC1_D)FM(STP_ISSYNC_1_D)	FM(STP_IVCXO27_0_E)FM(RIF3_D1_B)	F_(0, 0)	FM(FSO_TOE_B)	FM(TPU0TO1)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP17_3_0	FM(USB31_PWEN)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT2_B)		FM(SSI_SCK9_B)	FM(TS_SDEN0_E)	FM(STP_ISEN_0_E)	F_(0, 0)	FM(RIF2_D0_B)		F_(0, 0)	F_(0, 0)	FM(TPU0TO2)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP17_7_4	FM(USB31_OVC)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT3_B)		FM(SSI_WS9_B)	FM(TS_SPSYNC0_E)FM(STP_ISSYNC_0_E)	F_(0, 0)	FM(RIF2_D1_B)		F_(0, 0)	F_(0, 0)	FM(TPU0TO3)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_15_12	FM(SD0_WP)		F_(0, 0)	FM(NFDATA15_A)		F_(0, 0)			FM(SDA2_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_19_16	FM(SD1_CD)		F_(0, 0)	FM(NFRB_N_A)		F_(0, 0)			F_(0, 0)	FM(SIM0_CLK_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_23_20	FM(SD1_WP)		F_(0, 0)	FM(NFCE_N_A)		F_(0, 0)			F_(0, 0)	FM(SIM0_D_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_27_24	FM(SCK0)		FM(HSCK1_B)	FM(MSIOF1_SS2_B)	FM(AUDIO_CLKC_B)		FM(SDA2_A)	FM(SIM0_RST_B)	FM(STP_OPWM_0_C)	FM(RIF0_CLK_B)	F_(0, 0)		FM(ADICHS2)	FM(SCK5_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_31_28	FM(RX0)			FM(HRX1_B)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SCK0_C)	FM(STP_ISCLK_0_C)	FM(RIF0_D0_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_3_0	FM(TX0)			FM(HTX1_B)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_C)FM(STP_ISSYNC_0_C)	FM(RIF0_D1_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_7_4	FM(CTS0_N)		FM(HCTS1_N_B)	FM(MSIOF1_SYNC_B)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_C)FM(STP_ISSYNC_1_C)	FM(RIF1_SYNC_B)	FM(AUDIO_CLKOUT_C)	FM(ADICS_SAMP)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_11_8	FM(RTS0_N_TANS)		FM(HRTS1_N_B)	FM(MSIOF1_SS1_B)	FM(AUDIO_CLKA_B)		FM(SCL2_A)	F_(0, 0)	FM(STP_IVCXO27_1_C)	FM(RIF0_SYNC_B)	F_(0, 0)		FM(ADICHS1)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_15_12	FM(RX1_A)		FM(HRX1_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_C)	FM(STP_ISD_0_C)		FM(RIF1_CLK_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_19_16	FM(TX1_A)		FM(HTX1_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_C)	FM(STP_ISEN_0_C)	FM(RIF1_D0_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_23_20	FM(CTS1_N)		FM(HCTS1_N_A)	FM(MSIOF1_RXD_B)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_C)	FM(STP_ISEN_1_C)	FM(RIF1_D0_B)	F_(0, 0)		FM(ADIDATA)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_27_24	FM(RTS1_N_TANS)		FM(HRTS1_N_A)	FM(MSIOF1_TXD_B)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_C)	FM(STP_ISD_1_C)		FM(RIF1_D1_B)	F_(0, 0)		FM(ADICHS0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP12_31_28	FM(SCK2)		FM(SCIF_CLK_B)	FM(MSIOF1_SCK_B)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_C)	FM(STP_ISCLK_1_C)	FM(RIF1_CLK_B)	F_(0, 0)		FM(ADICLK)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_3_0	FM(TX2_A)		F_(0, 0)	F_(0, 0)		FM(SD2_CD_B)			FM(SCL1_A)	F_(0, 0)	FM(FMCLK_A)		FM(RIF1_D1_C)	F_(0, 0)		FM(FSO_CFE_0_N)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_7_4	FM(RX2_A)		F_(0, 0)	F_(0, 0)		FM(SD2_WP_B)			FM(SDA1_A)	F_(0, 0)	FM(FMIN_A)		FM(RIF1_SYNC_C)	F_(0, 0)		FM(FSO_CFE_1_N)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_11_8	FM(HSCK0)		F_(0, 0)	FM(MSIOF1_SCK_D)	FM(AUDIO_CLKB_A)		FM(SSI_SDATA1_B)FM(TS_SCK0_D)	FM(STP_ISCLK_0_D)	FM(RIF0_CLK_C)	F_(0, 0)		F_(0, 0)	FM(RX5_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_15_12	FM(HRX0)		F_(0, 0)	FM(MSIOF1_RXD_D)	F_(0, 0)			FM(SSI_SDATA2_B)FM(TS_SDEN0_D)	FM(STP_ISEN_0_D)	FM(RIF0_D0_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_19_16	FM(HTX0)		F_(0, 0)	FM(MSIOF1_TXD_D)	F_(0, 0)			FM(SSI_SDATA9_B)FM(TS_SDAT0_D)	FM(STP_ISD_0_D)		FM(RIF0_D1_C)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_23_20	FM(HCTS0_N)		FM(RX2_B)	FM(MSIOF1_SYNC_D)	F_(0, 0)			FM(SSI_SCK9_A)	FM(TS_SPSYNC0_D)FM(STP_ISSYNC_0_D)	FM(RIF0_SYNC_C)	FM(AUDIO_CLKOUT1_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_27_24	FM(HRTS0_N)		FM(TX2_B)	FM(MSIOF1_SS1_D)	F_(0, 0)			FM(SSI_WS9_A)	F_(0, 0)	FM(STP_IVCXO27_0_D)	FM(BPFCLK_A)	FM(AUDIO_CLKOUT2_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_31_28	FM(MSIOF0_SYNC)		F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(AUDIO_CLKOUT_A)	F_(0, 0)	FM(TX5_B)	F_(0, 0)	F_(0, 0) FM(BPFCLK_D) F_(0, 0) F_(0, 0)
+#define IP14_3_0	FM(MSIOF0_SS1)		FM(RX5_A)	FM(NFWP_N_A)		FM(AUDIO_CLKA_C)		FM(SSI_SCK2_A)	F_(0, 0)	FM(STP_IVCXO27_0_C)	F_(0, 0)	FM(AUDIO_CLKOUT3_A)	F_(0, 0)	FM(TCLK1_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_7_4	FM(MSIOF0_SS2)		FM(TX5_A)	FM(MSIOF1_SS2_D)	FM(AUDIO_CLKC_A)		FM(SSI_WS2_A)	F_(0, 0)	FM(STP_OPWM_0_D)	F_(0, 0)	FM(AUDIO_CLKOUT_D)	F_(0, 0)	FM(SPEEDIN_B)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_11_8	FM(MLB_CLK)		F_(0, 0)	FM(MSIOF1_SCK_F)	F_(0, 0)			FM(SCL1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_15_12	FM(MLB_SIG)		FM(RX1_B)	FM(MSIOF1_SYNC_F)	F_(0, 0)			FM(SDA1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_19_16	FM(MLB_DAT)		FM(TX1_B)	FM(MSIOF1_RXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_23_20	FM(SSI_SCK01239)	F_(0, 0)	FM(MSIOF1_TXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP14_27_24	FM(SSI_WS01239)		F_(0, 0)	FM(MSIOF1_SS1_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+/* IPSRx */		/* 0 */			/* 1 */		/* 2 */			/* 3 */				/* 4 */		/* 5 */		/* 6 */			/* 7 */		/* 8 */			/* 9 */		/* A */		/* B */		/* C - F */
+#define IP14_31_28	FM(SSI_SDATA0)		F_(0, 0)	FM(MSIOF1_SS2_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_3_0	FM(SSI_SDATA1_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_7_4	FM(SSI_SDATA2_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SSI_SCK1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_11_8	FM(SSI_SCK34)		F_(0, 0)	FM(MSIOF1_SS1_A)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_OPWM_0_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_15_12	FM(SSI_WS34)		FM(HCTS2_N_A)	FM(MSIOF1_SS2_A)	F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_0_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_19_16	FM(SSI_SDATA3)		FM(HRTS2_N_A)	FM(MSIOF1_TXD_A)	F_(0, 0)			F_(0, 0)	FM(TS_SCK0_A)	FM(STP_ISCLK_0_A)	FM(RIF0_D1_A)	FM(RIF2_D0_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_23_20	FM(SSI_SCK4)		FM(HRX2_A)	FM(MSIOF1_SCK_A)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT0_A)	FM(STP_ISD_0_A)		FM(RIF0_CLK_A)	FM(RIF2_CLK_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_27_24	FM(SSI_WS4)		FM(HTX2_A)	FM(MSIOF1_SYNC_A)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN0_A)	FM(STP_ISEN_0_A)	FM(RIF0_SYNC_A)	FM(RIF2_SYNC_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP15_31_28	FM(SSI_SDATA4)		FM(HSCK2_A)	FM(MSIOF1_RXD_A)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC0_A)FM(STP_ISSYNC_0_A)	FM(RIF0_D0_A)	FM(RIF2_D1_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_3_0	FM(SSI_SCK6)		FM(USB2_PWEN)	F_(0, 0)		FM(SIM0_RST_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_7_4	FM(SSI_WS6)		FM(USB2_OVC)	F_(0, 0)		FM(SIM0_D_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_11_8	FM(SSI_SDATA6)		F_(0, 0)	F_(0, 0)		FM(SIM0_CLK_D)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	FM(SATA_DEVSLP_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_15_12	FM(SSI_SCK78)		FM(HRX2_B)	FM(MSIOF1_SCK_C)	F_(0, 0)			F_(0, 0)	FM(TS_SCK1_A)	FM(STP_ISCLK_1_A)	FM(RIF1_CLK_A)	FM(RIF3_CLK_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_19_16	FM(SSI_WS78)		FM(HTX2_B)	FM(MSIOF1_SYNC_C)	F_(0, 0)			F_(0, 0)	FM(TS_SDAT1_A)	FM(STP_ISD_1_A)		FM(RIF1_SYNC_A)	FM(RIF3_SYNC_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_23_20	FM(SSI_SDATA7)		FM(HCTS2_N_B)	FM(MSIOF1_RXD_C)	F_(0, 0)			F_(0, 0)	FM(TS_SDEN1_A)	FM(STP_ISEN_1_A)	FM(RIF1_D0_A)	FM(RIF3_D0_A)		F_(0, 0)	FM(TCLK2_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_27_24	FM(SSI_SDATA8)		FM(HRTS2_N_B)	FM(MSIOF1_TXD_C)	F_(0, 0)			F_(0, 0)	FM(TS_SPSYNC1_A)FM(STP_ISSYNC_1_A)	FM(RIF1_D1_A)	FM(RIF3_D1_A)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP16_31_28	FM(SSI_SDATA9_A)	FM(HSCK2_B)	FM(MSIOF1_SS1_C)	FM(HSCK1_A)			FM(SSI_WS1_B)	FM(SCK1)	FM(STP_IVCXO27_1_A)	FM(SCK5_A)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP17_3_0	FM(AUDIO_CLKA_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	FM(CC5_OSCOUT)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP17_7_4	FM(AUDIO_CLKB_B)	FM(SCIF_CLK_A)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	FM(STP_IVCXO27_1_D)	FM(REMOCON_A)	F_(0, 0)		F_(0, 0)	FM(TCLK1_A)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP17_11_8	FM(USB0_PWEN)		F_(0, 0)	F_(0, 0)		FM(SIM0_RST_C)			F_(0, 0)	FM(TS_SCK1_D)	FM(STP_ISCLK_1_D)	FM(BPFCLK_B)	FM(RIF3_CLK_B)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) FM(HSCK2_C) F_(0, 0) F_(0, 0)
+#define IP17_15_12	FM(USB0_OVC)		F_(0, 0)	F_(0, 0)		FM(SIM0_D_C)			F_(0, 0)	FM(TS_SDAT1_D)	FM(STP_ISD_1_D)		F_(0, 0)	FM(RIF3_SYNC_B)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) FM(HRX2_C) F_(0, 0) F_(0, 0)
+#define IP17_19_16	FM(USB1_PWEN)		F_(0, 0)	F_(0, 0)		FM(SIM0_CLK_C)			FM(SSI_SCK1_A)	FM(TS_SCK0_E)	FM(STP_ISCLK_0_E)	FM(FMCLK_B)	FM(RIF2_CLK_B)		F_(0, 0)	FM(SPEEDIN_A)	F_(0, 0)	F_(0, 0) FM(HTX2_C) F_(0, 0) F_(0, 0)
+#define IP17_23_20	FM(USB1_OVC)		F_(0, 0)	FM(MSIOF1_SS2_C)	F_(0, 0)			FM(SSI_WS1_A)	FM(TS_SDAT0_E)	FM(STP_ISD_0_E)		FM(FMIN_B)	FM(RIF2_SYNC_B)		F_(0, 0)	FM(REMOCON_B)	F_(0, 0)	F_(0, 0) FM(HCTS2_N_C) F_(0, 0) F_(0, 0)
+#define IP17_27_24	FM(USB30_PWEN)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT_B)		FM(SSI_SCK2_B)	FM(TS_SDEN1_D)	FM(STP_ISEN_1_D)	FM(STP_OPWM_0_E)FM(RIF3_D0_B)		F_(0, 0)	FM(TCLK2_B)	FM(TPU0TO0)	FM(BPFCLK_C) FM(HRTS2_N_C) F_(0, 0) F_(0, 0)
+#define IP17_31_28	FM(USB30_OVC)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT1_B)		FM(SSI_WS2_B)	FM(TS_SPSYNC1_D)FM(STP_ISSYNC_1_D)	FM(STP_IVCXO27_0_E)FM(RIF3_D1_B)	F_(0, 0)	FM(FSO_TOE_N)	FM(TPU0TO1)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP18_3_0	FM(USB3_PWEN)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT2_B)		FM(SSI_SCK9_B)	FM(TS_SDEN0_E)	FM(STP_ISEN_0_E)	F_(0, 0)	FM(RIF2_D0_B)		F_(0, 0)	F_(0, 0)	FM(TPU0TO2)	F_(0, 0) FM(FMCLK_C) FM(FMCLK_D) F_(0, 0)
+#define IP18_7_4	FM(USB3_OVC)		F_(0, 0)	F_(0, 0)		FM(AUDIO_CLKOUT3_B)		FM(SSI_WS9_B)	FM(TS_SPSYNC0_E)FM(STP_ISSYNC_0_E)	F_(0, 0)	FM(RIF2_D1_B)		F_(0, 0)	F_(0, 0)	FM(TPU0TO3)	F_(0, 0) FM(FMIN_C) FM(FMIN_D) F_(0, 0)
 
 #define PINMUX_GPSR	\
 \
@@ -426,37 +437,34 @@ FM(IP12_23_20)	IP12_23_20	FM(IP13_23_20)	IP13_23_20	FM(IP14_23_20)	IP14_23_20	FM
 FM(IP12_27_24)	IP12_27_24	FM(IP13_27_24)	IP13_27_24	FM(IP14_27_24)	IP14_27_24	FM(IP15_27_24)	IP15_27_24 \
 FM(IP12_31_28)	IP12_31_28	FM(IP13_31_28)	IP13_31_28	FM(IP14_31_28)	IP14_31_28	FM(IP15_31_28)	IP15_31_28 \
 \
-FM(IP16_3_0)	IP16_3_0	FM(IP17_3_0)	IP17_3_0 \
-FM(IP16_7_4)	IP16_7_4	FM(IP17_7_4)	IP17_7_4 \
-FM(IP16_11_8)	IP16_11_8 \
-FM(IP16_15_12)	IP16_15_12 \
-FM(IP16_19_16)	IP16_19_16 \
-FM(IP16_23_20)	IP16_23_20 \
-FM(IP16_27_24)	IP16_27_24 \
-FM(IP16_31_28)	IP16_31_28
+FM(IP16_3_0)	IP16_3_0	FM(IP17_3_0)	IP17_3_0	FM(IP18_3_0)	IP18_3_0 \
+FM(IP16_7_4)	IP16_7_4	FM(IP17_7_4)	IP17_7_4	FM(IP18_7_4)	IP18_7_4 \
+FM(IP16_11_8)	IP16_11_8	FM(IP17_11_8)	IP17_11_8 \
+FM(IP16_15_12)	IP16_15_12	FM(IP17_15_12)	IP17_15_12 \
+FM(IP16_19_16)	IP16_19_16	FM(IP17_19_16)	IP17_19_16 \
+FM(IP16_23_20)	IP16_23_20	FM(IP17_23_20)	IP17_23_20 \
+FM(IP16_27_24)	IP16_27_24	FM(IP17_27_24)	IP17_27_24 \
+FM(IP16_31_28)	IP16_31_28	FM(IP17_31_28)	IP17_31_28
 
 /* MOD_SEL0 */			/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */			/* 6 */			/* 7 */
-#define MOD_SEL0_30_29		FM(SEL_MSIOF3_0)	FM(SEL_MSIOF3_1)	FM(SEL_MSIOF3_2)	FM(SEL_MSIOF3_3)
+#define MOD_SEL0_31_30_29	FM(SEL_MSIOF3_0)	FM(SEL_MSIOF3_1)	FM(SEL_MSIOF3_2)	FM(SEL_MSIOF3_3)	FM(SEL_MSIOF3_4)	F_(0, 0)		F_(0, 0)		F_(0, 0)
 #define MOD_SEL0_28_27		FM(SEL_MSIOF2_0)	FM(SEL_MSIOF2_1)	FM(SEL_MSIOF2_2)	FM(SEL_MSIOF2_3)
 #define MOD_SEL0_26_25_24	FM(SEL_MSIOF1_0)	FM(SEL_MSIOF1_1)	FM(SEL_MSIOF1_2)	FM(SEL_MSIOF1_3)	FM(SEL_MSIOF1_4)	FM(SEL_MSIOF1_5)	FM(SEL_MSIOF1_6)	F_(0, 0)
 #define MOD_SEL0_23		FM(SEL_LBSC_0)		FM(SEL_LBSC_1)
 #define MOD_SEL0_22		FM(SEL_IEBUS_0)		FM(SEL_IEBUS_1)
-#define MOD_SEL0_21_20		FM(SEL_I2C6_0)		FM(SEL_I2C6_1)		FM(SEL_I2C6_2)		F_(0, 0)
-#define MOD_SEL0_19		FM(SEL_I2C2_0)		FM(SEL_I2C2_1)
-#define MOD_SEL0_18		FM(SEL_I2C1_0)		FM(SEL_I2C1_1)
-#define MOD_SEL0_17		FM(SEL_HSCIF4_0)	FM(SEL_HSCIF4_1)
-#define MOD_SEL0_16_15		FM(SEL_HSCIF3_0)	FM(SEL_HSCIF3_1)	FM(SEL_HSCIF3_2)	FM(SEL_HSCIF3_3)
-#define MOD_SEL0_14		FM(SEL_HSCIF2_0)	FM(SEL_HSCIF2_1)
-#define MOD_SEL0_13		FM(SEL_HSCIF1_0)	FM(SEL_HSCIF1_1)
-#define MOD_SEL0_12		FM(SEL_FSO_0)		FM(SEL_FSO_1)
-#define MOD_SEL0_11		FM(SEL_FM_0)		FM(SEL_FM_1)
-#define MOD_SEL0_10		FM(SEL_ETHERAVB_0)	FM(SEL_ETHERAVB_1)
-#define MOD_SEL0_9		FM(SEL_DRIF3_0)		FM(SEL_DRIF3_1)
-#define MOD_SEL0_8		FM(SEL_DRIF2_0)		FM(SEL_DRIF2_1)
-#define MOD_SEL0_7_6		FM(SEL_DRIF1_0)		FM(SEL_DRIF1_1)		FM(SEL_DRIF1_2)		F_(0, 0)
-#define MOD_SEL0_5_4		FM(SEL_DRIF0_0)		FM(SEL_DRIF0_1)		FM(SEL_DRIF0_2)		F_(0, 0)
-#define MOD_SEL0_3		FM(SEL_CANFD0_0)	FM(SEL_CANFD0_1)
-#define MOD_SEL0_2_1		FM(SEL_ADG_0)		FM(SEL_ADG_1)		FM(SEL_ADG_2)		FM(SEL_ADG_3)
+#define MOD_SEL0_21		FM(SEL_I2C2_0)		FM(SEL_I2C2_1)
+#define MOD_SEL0_20		FM(SEL_I2C1_0)		FM(SEL_I2C1_1)
+#define MOD_SEL0_19		FM(SEL_HSCIF4_0)	FM(SEL_HSCIF4_1)
+#define MOD_SEL0_18_17		FM(SEL_HSCIF3_0)	FM(SEL_HSCIF3_1)	FM(SEL_HSCIF3_2)	FM(SEL_HSCIF3_3)
+#define MOD_SEL0_16		FM(SEL_HSCIF1_0)	FM(SEL_HSCIF1_1)
+#define MOD_SEL0_14_13		FM(SEL_HSCIF2_0)	FM(SEL_HSCIF2_1)	FM(SEL_HSCIF2_2)	F_(0, 0)
+#define MOD_SEL0_12		FM(SEL_ETHERAVB_0)	FM(SEL_ETHERAVB_1)
+#define MOD_SEL0_11		FM(SEL_DRIF3_0)		FM(SEL_DRIF3_1)
+#define MOD_SEL0_10		FM(SEL_DRIF2_0)		FM(SEL_DRIF2_1)
+#define MOD_SEL0_9_8		FM(SEL_DRIF1_0)		FM(SEL_DRIF1_1)		FM(SEL_DRIF1_2)		F_(0, 0)
+#define MOD_SEL0_7_6		FM(SEL_DRIF0_0)		FM(SEL_DRIF0_1)		FM(SEL_DRIF0_2)		F_(0, 0)
+#define MOD_SEL0_5		FM(SEL_CANFD0_0)	FM(SEL_CANFD0_1)
+#define MOD_SEL0_4_3		FM(SEL_ADG_A_0)		FM(SEL_ADG_A_1)		FM(SEL_ADG_A_2)		FM(SEL_ADG_A_3)
 
 /* MOD_SEL1 */			/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */			/* 6 */			/* 7 */
 #define MOD_SEL1_31_30		FM(SEL_TSIF1_0)		FM(SEL_TSIF1_1)		FM(SEL_TSIF1_2)		FM(SEL_TSIF1_3)
@@ -486,40 +494,46 @@ FM(IP16_31_28)	IP16_31_28
 #define MOD_SEL2_31		FM(I2C_SEL_5_0)		FM(I2C_SEL_5_1)
 #define MOD_SEL2_30		FM(I2C_SEL_3_0)		FM(I2C_SEL_3_1)
 #define MOD_SEL2_29		FM(I2C_SEL_0_0)		FM(I2C_SEL_0_1)
+#define MOD_SEL2_28_27		FM(SEL_FM_0)		FM(SEL_FM_1)		FM(SEL_FM_2)		FM(SEL_FM_3)
+#define MOD_SEL2_26		FM(SEL_SCIF5_0)		FM(SEL_SCIF5_1)
+#define MOD_SEL2_25_24_23	FM(SEL_I2C6_0)		FM(SEL_I2C6_1)		FM(SEL_I2C6_2)		F_(0, 0)		F_(0, 0)		F_(0, 0)		F_(0, 0)		F_(0, 0)
+#define MOD_SEL2_22		FM(SEL_NDF_0)		FM(SEL_NDF_1)
+#define MOD_SEL2_21		FM(SEL_SSI2_0)		FM(SEL_SSI2_1)
+#define MOD_SEL2_20		FM(SEL_SSI9_0)		FM(SEL_SSI9_1)
+#define MOD_SEL2_19		FM(SEL_TIMER_TMU2_0)	FM(SEL_TIMER_TMU2_1)
+#define MOD_SEL2_18		FM(SEL_ADG_B_0)		FM(SEL_ADG_B_1)
+#define MOD_SEL2_17		FM(SEL_ADG_C_0)		FM(SEL_ADG_C_1)
 #define MOD_SEL2_0		FM(SEL_VIN4_0)		FM(SEL_VIN4_1)
 
-#define PINMUX_MOD_SELS\
+#define PINMUX_MOD_SELS	\
 \
-			MOD_SEL1_31_30		MOD_SEL2_31 \
-MOD_SEL0_30_29					MOD_SEL2_30 \
+MOD_SEL0_31_30_29	MOD_SEL1_31_30		MOD_SEL2_31 \
+						MOD_SEL2_30 \
 			MOD_SEL1_29_28_27	MOD_SEL2_29 \
-MOD_SEL0_28_27 \
-\
-MOD_SEL0_26_25_24	MOD_SEL1_26 \
-			MOD_SEL1_25_24 \
-\
+MOD_SEL0_28_27					MOD_SEL2_28_27 \
+MOD_SEL0_26_25_24	MOD_SEL1_26		MOD_SEL2_26 \
+			MOD_SEL1_25_24		MOD_SEL2_25_24_23 \
 MOD_SEL0_23		MOD_SEL1_23_22_21 \
-MOD_SEL0_22 \
-MOD_SEL0_21_20 \
-			MOD_SEL1_20 \
-MOD_SEL0_19		MOD_SEL1_19 \
-MOD_SEL0_18		MOD_SEL1_18_17 \
-MOD_SEL0_17 \
-MOD_SEL0_16_15		MOD_SEL1_16 \
+MOD_SEL0_22					MOD_SEL2_22 \
+MOD_SEL0_21					MOD_SEL2_21 \
+MOD_SEL0_20		MOD_SEL1_20		MOD_SEL2_20 \
+MOD_SEL0_19		MOD_SEL1_19		MOD_SEL2_19 \
+MOD_SEL0_18_17		MOD_SEL1_18_17		MOD_SEL2_18 \
+						MOD_SEL2_17 \
+MOD_SEL0_16		MOD_SEL1_16 \
 			MOD_SEL1_15_14 \
-MOD_SEL0_14 \
-MOD_SEL0_13		MOD_SEL1_13 \
+MOD_SEL0_14_13 \
+			MOD_SEL1_13 \
 MOD_SEL0_12		MOD_SEL1_12 \
 MOD_SEL0_11		MOD_SEL1_11 \
 MOD_SEL0_10		MOD_SEL1_10 \
-MOD_SEL0_9		MOD_SEL1_9 \
-MOD_SEL0_8 \
+MOD_SEL0_9_8		MOD_SEL1_9 \
 MOD_SEL0_7_6 \
 			MOD_SEL1_6 \
-MOD_SEL0_5_4		MOD_SEL1_5 \
-			MOD_SEL1_4 \
-MOD_SEL0_3		MOD_SEL1_3 \
-MOD_SEL0_2_1		MOD_SEL1_2 \
+MOD_SEL0_5		MOD_SEL1_5 \
+MOD_SEL0_4_3		MOD_SEL1_4 \
+			MOD_SEL1_3 \
+			MOD_SEL1_2 \
 			MOD_SEL1_1 \
 			MOD_SEL1_0		MOD_SEL2_0
 
@@ -583,14 +597,6 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(MSIOF0_RXD),
 	PINMUX_SINGLE(MSIOF0_SCK),
 	PINMUX_SINGLE(MSIOF0_TXD),
-	PINMUX_SINGLE(SD2_CMD),
-	PINMUX_SINGLE(SD3_CLK),
-	PINMUX_SINGLE(SD3_CMD),
-	PINMUX_SINGLE(SD3_DAT0),
-	PINMUX_SINGLE(SD3_DAT1),
-	PINMUX_SINGLE(SD3_DAT2),
-	PINMUX_SINGLE(SD3_DAT3),
-	PINMUX_SINGLE(SD3_DS),
 	PINMUX_SINGLE(SSI_SCK5),
 	PINMUX_SINGLE(SSI_SDATA5),
 	PINMUX_SINGLE(SSI_WS5),
@@ -614,6 +620,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP0_19_16,	AVB_AVTP_MATCH_A,	SEL_ETHERAVB_0),
 	PINMUX_IPSR_MSEL(IP0_19_16,	MSIOF2_RXD_C,		SEL_MSIOF2_2),
 	PINMUX_IPSR_MSEL(IP0_19_16,	CTS4_N_A,		SEL_SCIF4_0),
+	PINMUX_IPSR_GPSR(IP0_19_16,	FSCLKST2_N_A),
 
 	PINMUX_IPSR_MSEL(IP0_23_20,	AVB_AVTP_CAPTURE_A,	SEL_ETHERAVB_0),
 	PINMUX_IPSR_MSEL(IP0_23_20,	MSIOF2_TXD_C,		SEL_MSIOF2_2),
@@ -625,6 +632,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP0_27_24,	VI4_DATA0_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP0_27_24,	CAN0_TX_B,		SEL_RCAN0_1),
 	PINMUX_IPSR_MSEL(IP0_27_24,	CANFD0_TX_B,		SEL_CANFD0_1),
+	PINMUX_IPSR_MSEL(IP0_27_24,	MSIOF3_SS2_E,		SEL_MSIOF3_4),
 
 	PINMUX_IPSR_GPSR(IP0_31_28,	IRQ1),
 	PINMUX_IPSR_GPSR(IP0_31_28,	QPOLA),
@@ -632,6 +640,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP0_31_28,	VI4_DATA1_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP0_31_28,	CAN0_RX_B,		SEL_RCAN0_1),
 	PINMUX_IPSR_MSEL(IP0_31_28,	CANFD0_RX_B,		SEL_CANFD0_1),
+	PINMUX_IPSR_MSEL(IP0_31_28,	MSIOF3_SS1_E,		SEL_MSIOF3_4),
 
 	/* IPSR1 */
 	PINMUX_IPSR_GPSR(IP1_3_0,	IRQ2),
@@ -639,6 +648,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP1_3_0,	DU_EXODDF_DU_ODDF_DISP_CDE),
 	PINMUX_IPSR_MSEL(IP1_3_0,	VI4_DATA2_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_3_0,	PWM3_B,			SEL_PWM3_1),
+	PINMUX_IPSR_MSEL(IP1_3_0,	MSIOF3_SYNC_E,		SEL_MSIOF3_4),
 
 	PINMUX_IPSR_GPSR(IP1_7_4,	IRQ3),
 	PINMUX_IPSR_GPSR(IP1_7_4,	QSTVB_QVE),
@@ -646,6 +656,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP1_7_4,	DU_DOTCLKOUT1),
 	PINMUX_IPSR_MSEL(IP1_7_4,	VI4_DATA3_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_7_4,	PWM4_B,			SEL_PWM4_1),
+	PINMUX_IPSR_MSEL(IP1_7_4,	MSIOF3_SCK_E,		SEL_MSIOF3_4),
 
 	PINMUX_IPSR_GPSR(IP1_11_8,	IRQ4),
 	PINMUX_IPSR_GPSR(IP1_11_8,	QSTH_QHS),
@@ -653,6 +664,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP1_11_8,	DU_EXHSYNC_DU_HSYNC),
 	PINMUX_IPSR_MSEL(IP1_11_8,	VI4_DATA4_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_11_8,	PWM5_B,			SEL_PWM5_1),
+	PINMUX_IPSR_MSEL(IP1_11_8,	MSIOF3_RXD_E,		SEL_MSIOF3_4),
 
 	PINMUX_IPSR_GPSR(IP1_15_12,	IRQ5),
 	PINMUX_IPSR_GPSR(IP1_15_12,	QSTB_QHE),
@@ -660,6 +672,8 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP1_15_12,	DU_EXVSYNC_DU_VSYNC),
 	PINMUX_IPSR_MSEL(IP1_15_12,	VI4_DATA5_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_15_12,	PWM6_B,			SEL_PWM6_1),
+	PINMUX_IPSR_GPSR(IP1_15_12,	FSCLKST2_N_B),
+	PINMUX_IPSR_MSEL(IP1_15_12,	MSIOF3_TXD_E,		SEL_MSIOF3_4),
 
 	PINMUX_IPSR_GPSR(IP1_19_16,	PWM0),
 	PINMUX_IPSR_GPSR(IP1_19_16,	AVB_AVTP_PPS),
@@ -1009,426 +1023,481 @@ static const u16 pinmux_data[] = {
 
 	PINMUX_IPSR_GPSR(IP8_15_12,	SD1_CMD),
 	PINMUX_IPSR_MSEL(IP8_15_12,	MSIOF1_SYNC_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_15_12,	NFCE_N_B,		SEL_NDF_1),
 	PINMUX_IPSR_MSEL(IP8_15_12,	SIM0_D_A,		SEL_SIMCARD_0),
 	PINMUX_IPSR_MSEL(IP8_15_12,	STP_IVCXO27_1_B,	SEL_SSP1_1_1),
 
 	PINMUX_IPSR_GPSR(IP8_19_16,	SD1_DAT0),
 	PINMUX_IPSR_GPSR(IP8_19_16,	SD2_DAT4),
 	PINMUX_IPSR_MSEL(IP8_19_16,	MSIOF1_RXD_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_19_16,	NFWP_N_B,		SEL_NDF_1),
 	PINMUX_IPSR_MSEL(IP8_19_16,	TS_SCK1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_19_16,	STP_ISCLK_1_B,		SEL_SSP1_1_1),
 
 	PINMUX_IPSR_GPSR(IP8_23_20,	SD1_DAT1),
 	PINMUX_IPSR_GPSR(IP8_23_20,	SD2_DAT5),
 	PINMUX_IPSR_MSEL(IP8_23_20,	MSIOF1_TXD_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_23_20,	NFDATA14_B,		SEL_NDF_1),
 	PINMUX_IPSR_MSEL(IP8_23_20,	TS_SPSYNC1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_23_20,	STP_ISSYNC_1_B,		SEL_SSP1_1_1),
 
 	PINMUX_IPSR_GPSR(IP8_27_24,	SD1_DAT2),
 	PINMUX_IPSR_GPSR(IP8_27_24,	SD2_DAT6),
 	PINMUX_IPSR_MSEL(IP8_27_24,	MSIOF1_SS1_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_27_24,	NFDATA15_B,		SEL_NDF_1),
 	PINMUX_IPSR_MSEL(IP8_27_24,	TS_SDAT1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_27_24,	STP_ISD_1_B,		SEL_SSP1_1_1),
 
 	PINMUX_IPSR_GPSR(IP8_31_28,	SD1_DAT3),
 	PINMUX_IPSR_GPSR(IP8_31_28,	SD2_DAT7),
 	PINMUX_IPSR_MSEL(IP8_31_28,	MSIOF1_SS2_G,		SEL_MSIOF1_6),
+	PINMUX_IPSR_MSEL(IP8_31_28,	NFRB_N_B,		SEL_NDF_1),
 	PINMUX_IPSR_MSEL(IP8_31_28,	TS_SDEN1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_31_28,	STP_ISEN_1_B,		SEL_SSP1_1_1),
 
 	/* IPSR9 */
 	PINMUX_IPSR_GPSR(IP9_3_0,	SD2_CLK),
+	PINMUX_IPSR_GPSR(IP9_3_0,	NFDATA8),
 
-	PINMUX_IPSR_GPSR(IP9_7_4,	SD2_DAT0),
+	PINMUX_IPSR_GPSR(IP9_7_4,	SD2_CMD),
+	PINMUX_IPSR_GPSR(IP9_7_4,	NFDATA9),
 
-	PINMUX_IPSR_GPSR(IP9_11_8,	SD2_DAT1),
+	PINMUX_IPSR_GPSR(IP9_11_8,	SD2_DAT0),
+	PINMUX_IPSR_GPSR(IP9_11_8,	NFDATA10),
 
-	PINMUX_IPSR_GPSR(IP9_15_12,	SD2_DAT2),
+	PINMUX_IPSR_GPSR(IP9_15_12,	SD2_DAT1),
+	PINMUX_IPSR_GPSR(IP9_15_12,	NFDATA11),
 
-	PINMUX_IPSR_GPSR(IP9_19_16,	SD2_DAT3),
+	PINMUX_IPSR_GPSR(IP9_19_16,	SD2_DAT2),
+	PINMUX_IPSR_GPSR(IP9_19_16,	NFDATA12),
 
-	PINMUX_IPSR_GPSR(IP9_23_20,	SD2_DS),
-	PINMUX_IPSR_MSEL(IP9_23_20,	SATA_DEVSLP_B,		SEL_SATA_1),
+	PINMUX_IPSR_GPSR(IP9_23_20,	SD2_DAT3),
+	PINMUX_IPSR_GPSR(IP9_23_20,	NFDATA13),
 
-	PINMUX_IPSR_GPSR(IP9_27_24,	SD3_DAT4),
-	PINMUX_IPSR_MSEL(IP9_27_24,	SD2_CD_A,		SEL_SDHI2_0),
+	PINMUX_IPSR_GPSR(IP9_27_24,	SD2_DS),
+	PINMUX_IPSR_GPSR(IP9_27_24,	NFALE),
+	PINMUX_IPSR_GPSR(IP9_27_24,	SATA_DEVSLP_B),
 
-	PINMUX_IPSR_GPSR(IP9_31_28,	SD3_DAT5),
-	PINMUX_IPSR_MSEL(IP9_31_28,	SD2_WP_A,		SEL_SDHI2_0),
+	PINMUX_IPSR_GPSR(IP9_31_28,	SD3_CLK),
+	PINMUX_IPSR_GPSR(IP9_31_28,	NFWE_N),
 
 	/* IPSR10 */
-	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_DAT6),
-	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_CD),
+	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_CMD),
+	PINMUX_IPSR_GPSR(IP10_3_0,	NFRE_N),
 
-	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_DAT7),
-	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_WP),
+	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_DAT0),
+	PINMUX_IPSR_GPSR(IP10_7_4,	NFDATA0),
 
-	PINMUX_IPSR_GPSR(IP10_11_8,	SD0_CD),
-	PINMUX_IPSR_MSEL(IP10_11_8,	SCL2_B,			SEL_I2C2_1),
-	PINMUX_IPSR_MSEL(IP10_11_8,	SIM0_RST_A,		SEL_SIMCARD_0),
+	PINMUX_IPSR_GPSR(IP10_11_8,	SD3_DAT1),
+	PINMUX_IPSR_GPSR(IP10_11_8,	NFDATA1),
 
-	PINMUX_IPSR_GPSR(IP10_15_12,	SD0_WP),
-	PINMUX_IPSR_MSEL(IP10_15_12,	SDA2_B,			SEL_I2C2_1),
+	PINMUX_IPSR_GPSR(IP10_15_12,	SD3_DAT2),
+	PINMUX_IPSR_GPSR(IP10_15_12,	NFDATA2),
 
-	PINMUX_IPSR_GPSR(IP10_19_16,	SD1_CD),
-	PINMUX_IPSR_MSEL(IP10_19_16,	SIM0_CLK_B,		SEL_SIMCARD_1),
+	PINMUX_IPSR_GPSR(IP10_19_16,	SD3_DAT3),
+	PINMUX_IPSR_GPSR(IP10_19_16,	NFDATA3),
 
-	PINMUX_IPSR_GPSR(IP10_23_20,	SD1_WP),
-	PINMUX_IPSR_MSEL(IP10_23_20,	SIM0_D_B,		SEL_SIMCARD_1),
+	PINMUX_IPSR_GPSR(IP10_23_20,	SD3_DAT4),
+	PINMUX_IPSR_MSEL(IP10_23_20,	SD2_CD_A,		SEL_SDHI2_0),
+	PINMUX_IPSR_GPSR(IP10_23_20,	NFDATA4),
 
-	PINMUX_IPSR_GPSR(IP10_27_24,	SCK0),
-	PINMUX_IPSR_MSEL(IP10_27_24,	HSCK1_B,		SEL_HSCIF1_1),
-	PINMUX_IPSR_MSEL(IP10_27_24,	MSIOF1_SS2_B,		SEL_MSIOF1_1),
-	PINMUX_IPSR_MSEL(IP10_27_24,	AUDIO_CLKC_B,		SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP10_27_24,	SDA2_A,			SEL_I2C2_0),
-	PINMUX_IPSR_MSEL(IP10_27_24,	SIM0_RST_B,		SEL_SIMCARD_1),
-	PINMUX_IPSR_MSEL(IP10_27_24,	STP_OPWM_0_C,		SEL_SSP1_0_2),
-	PINMUX_IPSR_MSEL(IP10_27_24,	RIF0_CLK_B,		SEL_DRIF0_1),
-	PINMUX_IPSR_GPSR(IP10_27_24,	ADICHS2),
+	PINMUX_IPSR_GPSR(IP10_27_24,	SD3_DAT5),
+	PINMUX_IPSR_MSEL(IP10_27_24,	SD2_WP_A,		SEL_SDHI2_0),
+	PINMUX_IPSR_GPSR(IP10_27_24,	NFDATA5),
 
-	PINMUX_IPSR_GPSR(IP10_31_28,	RX0),
-	PINMUX_IPSR_MSEL(IP10_31_28,	HRX1_B,			SEL_HSCIF1_1),
-	PINMUX_IPSR_MSEL(IP10_31_28,	TS_SCK0_C,		SEL_TSIF0_2),
-	PINMUX_IPSR_MSEL(IP10_31_28,	STP_ISCLK_0_C,		SEL_SSP1_0_2),
-	PINMUX_IPSR_MSEL(IP10_31_28,	RIF0_D0_B,		SEL_DRIF0_1),
+	PINMUX_IPSR_GPSR(IP10_31_28,	SD3_DAT6),
+	PINMUX_IPSR_GPSR(IP10_31_28,	SD3_CD),
+	PINMUX_IPSR_GPSR(IP10_31_28,	NFDATA6),
 
 	/* IPSR11 */
-	PINMUX_IPSR_GPSR(IP11_3_0,	TX0),
-	PINMUX_IPSR_MSEL(IP11_3_0,	HTX1_B,			SEL_HSCIF1_1),
-	PINMUX_IPSR_MSEL(IP11_3_0,	TS_SPSYNC0_C,		SEL_TSIF0_2),
-	PINMUX_IPSR_MSEL(IP11_3_0,	STP_ISSYNC_0_C,		SEL_SSP1_0_2),
-	PINMUX_IPSR_MSEL(IP11_3_0,	RIF0_D1_B,		SEL_DRIF0_1),
-
-	PINMUX_IPSR_GPSR(IP11_7_4,	CTS0_N),
-	PINMUX_IPSR_MSEL(IP11_7_4,	HCTS1_N_B,		SEL_HSCIF1_1),
-	PINMUX_IPSR_MSEL(IP11_7_4,	MSIOF1_SYNC_B,		SEL_MSIOF1_1),
-	PINMUX_IPSR_MSEL(IP11_7_4,	TS_SPSYNC1_C,		SEL_TSIF1_2),
-	PINMUX_IPSR_MSEL(IP11_7_4,	STP_ISSYNC_1_C,		SEL_SSP1_1_2),
-	PINMUX_IPSR_MSEL(IP11_7_4,	RIF1_SYNC_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_MSEL(IP11_7_4,	AUDIO_CLKOUT_C,		SEL_ADG_2),
-	PINMUX_IPSR_GPSR(IP11_7_4,	ADICS_SAMP),
-
-	PINMUX_IPSR_GPSR(IP11_11_8,	RTS0_N_TANS),
-	PINMUX_IPSR_MSEL(IP11_11_8,	HRTS1_N_B,		SEL_HSCIF1_1),
-	PINMUX_IPSR_MSEL(IP11_11_8,	MSIOF1_SS1_B,		SEL_MSIOF1_1),
-	PINMUX_IPSR_MSEL(IP11_11_8,	AUDIO_CLKA_B,		SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP11_11_8,	SCL2_A,			SEL_I2C2_0),
-	PINMUX_IPSR_MSEL(IP11_11_8,	STP_IVCXO27_1_C,	SEL_SSP1_1_2),
-	PINMUX_IPSR_MSEL(IP11_11_8,	RIF0_SYNC_B,		SEL_DRIF0_1),
-	PINMUX_IPSR_GPSR(IP11_11_8,	ADICHS1),
-
-	PINMUX_IPSR_MSEL(IP11_15_12,	RX1_A,			SEL_SCIF1_0),
-	PINMUX_IPSR_MSEL(IP11_15_12,	HRX1_A,			SEL_HSCIF1_0),
-	PINMUX_IPSR_MSEL(IP11_15_12,	TS_SDAT0_C,		SEL_TSIF0_2),
-	PINMUX_IPSR_MSEL(IP11_15_12,	STP_ISD_0_C,		SEL_SSP1_0_2),
-	PINMUX_IPSR_MSEL(IP11_15_12,	RIF1_CLK_C,		SEL_DRIF1_2),
-
-	PINMUX_IPSR_MSEL(IP11_19_16,	TX1_A,			SEL_SCIF1_0),
-	PINMUX_IPSR_MSEL(IP11_19_16,	HTX1_A,			SEL_HSCIF1_0),
-	PINMUX_IPSR_MSEL(IP11_19_16,	TS_SDEN0_C,		SEL_TSIF0_2),
-	PINMUX_IPSR_MSEL(IP11_19_16,	STP_ISEN_0_C,		SEL_SSP1_0_2),
-	PINMUX_IPSR_MSEL(IP11_19_16,	RIF1_D0_C,		SEL_DRIF1_2),
-
-	PINMUX_IPSR_GPSR(IP11_23_20,	CTS1_N),
-	PINMUX_IPSR_MSEL(IP11_23_20,	HCTS1_N_A,		SEL_HSCIF1_0),
-	PINMUX_IPSR_MSEL(IP11_23_20,	MSIOF1_RXD_B,		SEL_MSIOF1_1),
-	PINMUX_IPSR_MSEL(IP11_23_20,	TS_SDEN1_C,		SEL_TSIF1_2),
-	PINMUX_IPSR_MSEL(IP11_23_20,	STP_ISEN_1_C,		SEL_SSP1_1_2),
-	PINMUX_IPSR_MSEL(IP11_23_20,	RIF1_D0_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_GPSR(IP11_23_20,	ADIDATA),
-
-	PINMUX_IPSR_GPSR(IP11_27_24,	RTS1_N_TANS),
-	PINMUX_IPSR_MSEL(IP11_27_24,	HRTS1_N_A,		SEL_HSCIF1_0),
-	PINMUX_IPSR_MSEL(IP11_27_24,	MSIOF1_TXD_B,		SEL_MSIOF1_1),
-	PINMUX_IPSR_MSEL(IP11_27_24,	TS_SDAT1_C,		SEL_TSIF1_2),
-	PINMUX_IPSR_MSEL(IP11_27_24,	STP_ISD_1_C,		SEL_SSP1_1_2),
-	PINMUX_IPSR_MSEL(IP11_27_24,	RIF1_D1_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_GPSR(IP11_27_24,	ADICHS0),
-
-	PINMUX_IPSR_GPSR(IP11_31_28,	SCK2),
-	PINMUX_IPSR_MSEL(IP11_31_28,	SCIF_CLK_B,		SEL_SCIF1_1),
-	PINMUX_IPSR_MSEL(IP11_31_28,	MSIOF1_SCK_B,		SEL_MSIOF1_1),
-	PINMUX_IPSR_MSEL(IP11_31_28,	TS_SCK1_C,		SEL_TSIF1_2),
-	PINMUX_IPSR_MSEL(IP11_31_28,	STP_ISCLK_1_C,		SEL_SSP1_1_2),
-	PINMUX_IPSR_MSEL(IP11_31_28,	RIF1_CLK_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_GPSR(IP11_31_28,	ADICLK),
+	PINMUX_IPSR_GPSR(IP11_3_0,	SD3_DAT7),
+	PINMUX_IPSR_GPSR(IP11_3_0,	SD3_WP),
+	PINMUX_IPSR_GPSR(IP11_3_0,	NFDATA7),
+
+	PINMUX_IPSR_GPSR(IP11_7_4,	SD3_DS),
+	PINMUX_IPSR_GPSR(IP11_7_4,	NFCLE),
+
+	PINMUX_IPSR_GPSR(IP11_11_8,	SD0_CD),
+	PINMUX_IPSR_MSEL(IP11_11_8,	SCL2_B,			SEL_I2C2_1),
+	PINMUX_IPSR_MSEL(IP11_11_8,	SIM0_RST_A,		SEL_SIMCARD_0),
+
+	PINMUX_IPSR_GPSR(IP11_15_12,	SD0_WP),
+	PINMUX_IPSR_MSEL(IP11_15_12,	SDA2_B,			SEL_I2C2_1),
+
+	PINMUX_IPSR_GPSR(IP11_19_16,	SD1_CD),
+	PINMUX_IPSR_MSEL(IP11_19_16,	SIM0_CLK_B,		SEL_SIMCARD_1),
+
+	PINMUX_IPSR_GPSR(IP11_23_20,	SD1_WP),
+	PINMUX_IPSR_MSEL(IP11_23_20,	SIM0_D_B,		SEL_SIMCARD_1),
+
+	PINMUX_IPSR_GPSR(IP11_27_24,	SCK0),
+	PINMUX_IPSR_MSEL(IP11_27_24,	HSCK1_B,		SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP11_27_24,	MSIOF1_SS2_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP11_27_24,	AUDIO_CLKC_B,		SEL_ADG_C_1),
+	PINMUX_IPSR_MSEL(IP11_27_24,	SDA2_A,			SEL_I2C2_0),
+	PINMUX_IPSR_MSEL(IP11_27_24,	SIM0_RST_B,		SEL_SIMCARD_1),
+	PINMUX_IPSR_MSEL(IP11_27_24,	STP_OPWM_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP11_27_24,	RIF0_CLK_B,		SEL_DRIF0_1),
+	PINMUX_IPSR_GPSR(IP11_27_24,	ADICHS2),
+	PINMUX_IPSR_MSEL(IP11_27_24,	SCK5_B,			SEL_SCIF5_1),
+
+	PINMUX_IPSR_GPSR(IP11_31_28,	RX0),
+	PINMUX_IPSR_MSEL(IP11_31_28,	HRX1_B,			SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP11_31_28,	TS_SCK0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP11_31_28,	STP_ISCLK_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP11_31_28,	RIF0_D0_B,		SEL_DRIF0_1),
 
 	/* IPSR12 */
-	PINMUX_IPSR_MSEL(IP12_3_0,	TX2_A,			SEL_SCIF2_0),
-	PINMUX_IPSR_MSEL(IP12_3_0,	SD2_CD_B,		SEL_SDHI2_1),
-	PINMUX_IPSR_MSEL(IP12_3_0,	SCL1_A,			SEL_I2C1_0),
-	PINMUX_IPSR_MSEL(IP12_3_0,	FMCLK_A,		SEL_FM_0),
-	PINMUX_IPSR_MSEL(IP12_3_0,	RIF1_D1_C,		SEL_DRIF1_2),
-	PINMUX_IPSR_MSEL(IP12_3_0,	FSO_CFE_0_B,		SEL_FSO_1),
-
-	PINMUX_IPSR_MSEL(IP12_7_4,	RX2_A,			SEL_SCIF2_0),
-	PINMUX_IPSR_MSEL(IP12_7_4,	SD2_WP_B,		SEL_SDHI2_1),
-	PINMUX_IPSR_MSEL(IP12_7_4,	SDA1_A,			SEL_I2C1_0),
-	PINMUX_IPSR_MSEL(IP12_7_4,	FMIN_A,			SEL_FM_0),
-	PINMUX_IPSR_MSEL(IP12_7_4,	RIF1_SYNC_C,		SEL_DRIF1_2),
-	PINMUX_IPSR_MSEL(IP12_7_4,	FSO_CFE_1_B,		SEL_FSO_1),
-
-	PINMUX_IPSR_GPSR(IP12_11_8,	HSCK0),
-	PINMUX_IPSR_MSEL(IP12_11_8,	MSIOF1_SCK_D,		SEL_MSIOF1_3),
-	PINMUX_IPSR_MSEL(IP12_11_8,	AUDIO_CLKB_A,		SEL_ADG_0),
-	PINMUX_IPSR_MSEL(IP12_11_8,	SSI_SDATA1_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP12_11_8,	TS_SCK0_D,		SEL_TSIF0_3),
-	PINMUX_IPSR_MSEL(IP12_11_8,	STP_ISCLK_0_D,		SEL_SSP1_0_3),
-	PINMUX_IPSR_MSEL(IP12_11_8,	RIF0_CLK_C,		SEL_DRIF0_2),
-
-	PINMUX_IPSR_GPSR(IP12_15_12,	HRX0),
-	PINMUX_IPSR_MSEL(IP12_15_12,	MSIOF1_RXD_D,		SEL_MSIOF1_3),
-	PINMUX_IPSR_MSEL(IP12_15_12,	SSI_SDATA2_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP12_15_12,	TS_SDEN0_D,		SEL_TSIF0_3),
-	PINMUX_IPSR_MSEL(IP12_15_12,	STP_ISEN_0_D,		SEL_SSP1_0_3),
-	PINMUX_IPSR_MSEL(IP12_15_12,	RIF0_D0_C,		SEL_DRIF0_2),
-
-	PINMUX_IPSR_GPSR(IP12_19_16,	HTX0),
-	PINMUX_IPSR_MSEL(IP12_19_16,	MSIOF1_TXD_D,		SEL_MSIOF1_3),
-	PINMUX_IPSR_MSEL(IP12_19_16,	SSI_SDATA9_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP12_19_16,	TS_SDAT0_D,		SEL_TSIF0_3),
-	PINMUX_IPSR_MSEL(IP12_19_16,	STP_ISD_0_D,		SEL_SSP1_0_3),
-	PINMUX_IPSR_MSEL(IP12_19_16,	RIF0_D1_C,		SEL_DRIF0_2),
-
-	PINMUX_IPSR_GPSR(IP12_23_20,	HCTS0_N),
-	PINMUX_IPSR_MSEL(IP12_23_20,	RX2_B,			SEL_SCIF2_1),
-	PINMUX_IPSR_MSEL(IP12_23_20,	MSIOF1_SYNC_D,		SEL_MSIOF1_3),
-	PINMUX_IPSR_MSEL(IP12_23_20,	SSI_SCK9_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP12_23_20,	TS_SPSYNC0_D,		SEL_TSIF0_3),
-	PINMUX_IPSR_MSEL(IP12_23_20,	STP_ISSYNC_0_D,		SEL_SSP1_0_3),
-	PINMUX_IPSR_MSEL(IP12_23_20,	RIF0_SYNC_C,		SEL_DRIF0_2),
-	PINMUX_IPSR_MSEL(IP12_23_20,	AUDIO_CLKOUT1_A,	SEL_ADG_0),
-
-	PINMUX_IPSR_GPSR(IP12_27_24,	HRTS0_N),
-	PINMUX_IPSR_MSEL(IP12_27_24,	TX2_B,			SEL_SCIF2_1),
-	PINMUX_IPSR_MSEL(IP12_27_24,	MSIOF1_SS1_D,		SEL_MSIOF1_3),
-	PINMUX_IPSR_MSEL(IP12_27_24,	SSI_WS9_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP12_27_24,	STP_IVCXO27_0_D,	SEL_SSP1_0_3),
-	PINMUX_IPSR_MSEL(IP12_27_24,	BPFCLK_A,		SEL_FM_0),
-	PINMUX_IPSR_MSEL(IP12_27_24,	AUDIO_CLKOUT2_A,	SEL_ADG_0),
-
-	PINMUX_IPSR_GPSR(IP12_31_28,	MSIOF0_SYNC),
-	PINMUX_IPSR_MSEL(IP12_31_28,	AUDIO_CLKOUT_A,		SEL_ADG_0),
+	PINMUX_IPSR_GPSR(IP12_3_0,	TX0),
+	PINMUX_IPSR_MSEL(IP12_3_0,	HTX1_B,			SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP12_3_0,	TS_SPSYNC0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP12_3_0,	STP_ISSYNC_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP12_3_0,	RIF0_D1_B,		SEL_DRIF0_1),
+
+	PINMUX_IPSR_GPSR(IP12_7_4,	CTS0_N),
+	PINMUX_IPSR_MSEL(IP12_7_4,	HCTS1_N_B,		SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP12_7_4,	MSIOF1_SYNC_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP12_7_4,	TS_SPSYNC1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP12_7_4,	STP_ISSYNC_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP12_7_4,	RIF1_SYNC_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP12_7_4,	AUDIO_CLKOUT_C),
+	PINMUX_IPSR_GPSR(IP12_7_4,	ADICS_SAMP),
+
+	PINMUX_IPSR_GPSR(IP12_11_8,	RTS0_N_TANS),
+	PINMUX_IPSR_MSEL(IP12_11_8,	HRTS1_N_B,		SEL_HSCIF1_1),
+	PINMUX_IPSR_MSEL(IP12_11_8,	MSIOF1_SS1_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP12_11_8,	AUDIO_CLKA_B,		SEL_ADG_A_1),
+	PINMUX_IPSR_MSEL(IP12_11_8,	SCL2_A,			SEL_I2C2_0),
+	PINMUX_IPSR_MSEL(IP12_11_8,	STP_IVCXO27_1_C,	SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP12_11_8,	RIF0_SYNC_B,		SEL_DRIF0_1),
+	PINMUX_IPSR_GPSR(IP12_11_8,	ADICHS1),
+
+	PINMUX_IPSR_MSEL(IP12_15_12,	RX1_A,			SEL_SCIF1_0),
+	PINMUX_IPSR_MSEL(IP12_15_12,	HRX1_A,			SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP12_15_12,	TS_SDAT0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP12_15_12,	STP_ISD_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP12_15_12,	RIF1_CLK_C,		SEL_DRIF1_2),
+
+	PINMUX_IPSR_MSEL(IP12_19_16,	TX1_A,			SEL_SCIF1_0),
+	PINMUX_IPSR_MSEL(IP12_19_16,	HTX1_A,			SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP12_19_16,	TS_SDEN0_C,		SEL_TSIF0_2),
+	PINMUX_IPSR_MSEL(IP12_19_16,	STP_ISEN_0_C,		SEL_SSP1_0_2),
+	PINMUX_IPSR_MSEL(IP12_19_16,	RIF1_D0_C,		SEL_DRIF1_2),
+
+	PINMUX_IPSR_GPSR(IP12_23_20,	CTS1_N),
+	PINMUX_IPSR_MSEL(IP12_23_20,	HCTS1_N_A,		SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP12_23_20,	MSIOF1_RXD_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP12_23_20,	TS_SDEN1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP12_23_20,	STP_ISEN_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP12_23_20,	RIF1_D0_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP12_23_20,	ADIDATA),
+
+	PINMUX_IPSR_GPSR(IP12_27_24,	RTS1_N_TANS),
+	PINMUX_IPSR_MSEL(IP12_27_24,	HRTS1_N_A,		SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP12_27_24,	MSIOF1_TXD_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP12_27_24,	TS_SDAT1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP12_27_24,	STP_ISD_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP12_27_24,	RIF1_D1_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP12_27_24,	ADICHS0),
+
+	PINMUX_IPSR_GPSR(IP12_31_28,	SCK2),
+	PINMUX_IPSR_MSEL(IP12_31_28,	SCIF_CLK_B,		SEL_SCIF1_1),
+	PINMUX_IPSR_MSEL(IP12_31_28,	MSIOF1_SCK_B,		SEL_MSIOF1_1),
+	PINMUX_IPSR_MSEL(IP12_31_28,	TS_SCK1_C,		SEL_TSIF1_2),
+	PINMUX_IPSR_MSEL(IP12_31_28,	STP_ISCLK_1_C,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP12_31_28,	RIF1_CLK_B,		SEL_DRIF1_1),
+	PINMUX_IPSR_GPSR(IP12_31_28,	ADICLK),
 
 	/* IPSR13 */
-	PINMUX_IPSR_GPSR(IP13_3_0,	MSIOF0_SS1),
-	PINMUX_IPSR_GPSR(IP13_3_0,	RX5),
-	PINMUX_IPSR_MSEL(IP13_3_0,	AUDIO_CLKA_C,		SEL_ADG_2),
-	PINMUX_IPSR_MSEL(IP13_3_0,	SSI_SCK2_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP13_3_0,	STP_IVCXO27_0_C,	SEL_SSP1_0_2),
-	PINMUX_IPSR_MSEL(IP13_3_0,	AUDIO_CLKOUT3_A,	SEL_ADG_0),
-	PINMUX_IPSR_MSEL(IP13_3_0,	TCLK1_B,		SEL_TIMER_TMU_1),
-
-	PINMUX_IPSR_GPSR(IP13_7_4,	MSIOF0_SS2),
-	PINMUX_IPSR_GPSR(IP13_7_4,	TX5),
-	PINMUX_IPSR_MSEL(IP13_7_4,	MSIOF1_SS2_D,		SEL_MSIOF1_3),
-	PINMUX_IPSR_MSEL(IP13_7_4,	AUDIO_CLKC_A,		SEL_ADG_0),
-	PINMUX_IPSR_MSEL(IP13_7_4,	SSI_WS2_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP13_7_4,	STP_OPWM_0_D,		SEL_SSP1_0_3),
-	PINMUX_IPSR_MSEL(IP13_7_4,	AUDIO_CLKOUT_D,		SEL_ADG_3),
-	PINMUX_IPSR_MSEL(IP13_7_4,	SPEEDIN_B,		SEL_SPEED_PULSE_1),
-
-	PINMUX_IPSR_GPSR(IP13_11_8,	MLB_CLK),
-	PINMUX_IPSR_MSEL(IP13_11_8,	MSIOF1_SCK_F,		SEL_MSIOF1_5),
-	PINMUX_IPSR_MSEL(IP13_11_8,	SCL1_B,			SEL_I2C1_1),
-
-	PINMUX_IPSR_GPSR(IP13_15_12,	MLB_SIG),
-	PINMUX_IPSR_MSEL(IP13_15_12,	RX1_B,			SEL_SCIF1_1),
-	PINMUX_IPSR_MSEL(IP13_15_12,	MSIOF1_SYNC_F,		SEL_MSIOF1_5),
-	PINMUX_IPSR_MSEL(IP13_15_12,	SDA1_B,			SEL_I2C1_1),
-
-	PINMUX_IPSR_GPSR(IP13_19_16,	MLB_DAT),
-	PINMUX_IPSR_MSEL(IP13_19_16,	TX1_B,			SEL_SCIF1_1),
-	PINMUX_IPSR_MSEL(IP13_19_16,	MSIOF1_RXD_F,		SEL_MSIOF1_5),
-
-	PINMUX_IPSR_GPSR(IP13_23_20,	SSI_SCK01239),
-	PINMUX_IPSR_MSEL(IP13_23_20,	MSIOF1_TXD_F,		SEL_MSIOF1_5),
-
-	PINMUX_IPSR_GPSR(IP13_27_24,	SSI_WS01239),
-	PINMUX_IPSR_MSEL(IP13_27_24,	MSIOF1_SS1_F,		SEL_MSIOF1_5),
-
-	PINMUX_IPSR_GPSR(IP13_31_28,	SSI_SDATA0),
-	PINMUX_IPSR_MSEL(IP13_31_28,	MSIOF1_SS2_F,		SEL_MSIOF1_5),
+	PINMUX_IPSR_MSEL(IP13_3_0,	TX2_A,			SEL_SCIF2_0),
+	PINMUX_IPSR_MSEL(IP13_3_0,	SD2_CD_B,		SEL_SDHI2_1),
+	PINMUX_IPSR_MSEL(IP13_3_0,	SCL1_A,			SEL_I2C1_0),
+	PINMUX_IPSR_MSEL(IP13_3_0,	FMCLK_A,		SEL_FM_0),
+	PINMUX_IPSR_MSEL(IP13_3_0,	RIF1_D1_C,		SEL_DRIF1_2),
+	PINMUX_IPSR_GPSR(IP13_3_0,	FSO_CFE_0_N),
+
+	PINMUX_IPSR_MSEL(IP13_7_4,	RX2_A,			SEL_SCIF2_0),
+	PINMUX_IPSR_MSEL(IP13_7_4,	SD2_WP_B,		SEL_SDHI2_1),
+	PINMUX_IPSR_MSEL(IP13_7_4,	SDA1_A,			SEL_I2C1_0),
+	PINMUX_IPSR_MSEL(IP13_7_4,	FMIN_A,			SEL_FM_0),
+	PINMUX_IPSR_MSEL(IP13_7_4,	RIF1_SYNC_C,		SEL_DRIF1_2),
+	PINMUX_IPSR_GPSR(IP13_7_4,	FSO_CFE_1_N),
+
+	PINMUX_IPSR_GPSR(IP13_11_8,	HSCK0),
+	PINMUX_IPSR_MSEL(IP13_11_8,	MSIOF1_SCK_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP13_11_8,	AUDIO_CLKB_A,		SEL_ADG_B_0),
+	PINMUX_IPSR_MSEL(IP13_11_8,	SSI_SDATA1_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP13_11_8,	TS_SCK0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP13_11_8,	STP_ISCLK_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP13_11_8,	RIF0_CLK_C,		SEL_DRIF0_2),
+	PINMUX_IPSR_MSEL(IP13_11_8,	RX5_B,			SEL_SCIF5_1),
+
+	PINMUX_IPSR_GPSR(IP13_15_12,	HRX0),
+	PINMUX_IPSR_MSEL(IP13_15_12,	MSIOF1_RXD_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP13_15_12,	SSI_SDATA2_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP13_15_12,	TS_SDEN0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP13_15_12,	STP_ISEN_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP13_15_12,	RIF0_D0_C,		SEL_DRIF0_2),
+
+	PINMUX_IPSR_GPSR(IP13_19_16,	HTX0),
+	PINMUX_IPSR_MSEL(IP13_19_16,	MSIOF1_TXD_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP13_19_16,	SSI_SDATA9_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP13_19_16,	TS_SDAT0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP13_19_16,	STP_ISD_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP13_19_16,	RIF0_D1_C,		SEL_DRIF0_2),
+
+	PINMUX_IPSR_GPSR(IP13_23_20,	HCTS0_N),
+	PINMUX_IPSR_MSEL(IP13_23_20,	RX2_B,			SEL_SCIF2_1),
+	PINMUX_IPSR_MSEL(IP13_23_20,	MSIOF1_SYNC_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP13_23_20,	SSI_SCK9_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP13_23_20,	TS_SPSYNC0_D,		SEL_TSIF0_3),
+	PINMUX_IPSR_MSEL(IP13_23_20,	STP_ISSYNC_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP13_23_20,	RIF0_SYNC_C,		SEL_DRIF0_2),
+	PINMUX_IPSR_GPSR(IP13_23_20,	AUDIO_CLKOUT1_A),
+
+	PINMUX_IPSR_GPSR(IP13_27_24,	HRTS0_N),
+	PINMUX_IPSR_MSEL(IP13_27_24,	TX2_B,			SEL_SCIF2_1),
+	PINMUX_IPSR_MSEL(IP13_27_24,	MSIOF1_SS1_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP13_27_24,	SSI_WS9_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP13_27_24,	STP_IVCXO27_0_D,	SEL_SSP1_0_3),
+	PINMUX_IPSR_MSEL(IP13_27_24,	BPFCLK_A,		SEL_FM_0),
+	PINMUX_IPSR_GPSR(IP13_27_24,	AUDIO_CLKOUT2_A),
+
+	PINMUX_IPSR_GPSR(IP13_31_28,	MSIOF0_SYNC),
+	PINMUX_IPSR_GPSR(IP13_31_28,	AUDIO_CLKOUT_A),
+	PINMUX_IPSR_MSEL(IP13_31_28,	TX5_B,			SEL_SCIF5_1),
+	PINMUX_IPSR_MSEL(IP13_31_28,	BPFCLK_D,		SEL_FM_3),
 
 	/* IPSR14 */
-	PINMUX_IPSR_MSEL(IP14_3_0,	SSI_SDATA1_A,		SEL_SSI_0),
-
-	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_SDATA2_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_SCK1_B,		SEL_SSI_1),
-
-	PINMUX_IPSR_GPSR(IP14_11_8,	SSI_SCK34),
-	PINMUX_IPSR_MSEL(IP14_11_8,	MSIOF1_SS1_A,		SEL_MSIOF1_0),
-	PINMUX_IPSR_MSEL(IP14_11_8,	STP_OPWM_0_A,		SEL_SSP1_0_0),
-
-	PINMUX_IPSR_GPSR(IP14_15_12,	SSI_WS34),
-	PINMUX_IPSR_MSEL(IP14_15_12,	HCTS2_N_A,		SEL_HSCIF2_0),
-	PINMUX_IPSR_MSEL(IP14_15_12,	MSIOF1_SS2_A,		SEL_MSIOF1_0),
-	PINMUX_IPSR_MSEL(IP14_15_12,	STP_IVCXO27_0_A,	SEL_SSP1_0_0),
-
-	PINMUX_IPSR_GPSR(IP14_19_16,	SSI_SDATA3),
-	PINMUX_IPSR_MSEL(IP14_19_16,	HRTS2_N_A,		SEL_HSCIF2_0),
-	PINMUX_IPSR_MSEL(IP14_19_16,	MSIOF1_TXD_A,		SEL_MSIOF1_0),
-	PINMUX_IPSR_MSEL(IP14_19_16,	TS_SCK0_A,		SEL_TSIF0_0),
-	PINMUX_IPSR_MSEL(IP14_19_16,	STP_ISCLK_0_A,		SEL_SSP1_0_0),
-	PINMUX_IPSR_MSEL(IP14_19_16,	RIF0_D1_A,		SEL_DRIF0_0),
-	PINMUX_IPSR_MSEL(IP14_19_16,	RIF2_D0_A,		SEL_DRIF2_0),
-
-	PINMUX_IPSR_GPSR(IP14_23_20,	SSI_SCK4),
-	PINMUX_IPSR_MSEL(IP14_23_20,	HRX2_A,			SEL_HSCIF2_0),
-	PINMUX_IPSR_MSEL(IP14_23_20,	MSIOF1_SCK_A,		SEL_MSIOF1_0),
-	PINMUX_IPSR_MSEL(IP14_23_20,	TS_SDAT0_A,		SEL_TSIF0_0),
-	PINMUX_IPSR_MSEL(IP14_23_20,	STP_ISD_0_A,		SEL_SSP1_0_0),
-	PINMUX_IPSR_MSEL(IP14_23_20,	RIF0_CLK_A,		SEL_DRIF0_0),
-	PINMUX_IPSR_MSEL(IP14_23_20,	RIF2_CLK_A,		SEL_DRIF2_0),
-
-	PINMUX_IPSR_GPSR(IP14_27_24,	SSI_WS4),
-	PINMUX_IPSR_MSEL(IP14_27_24,	HTX2_A,			SEL_HSCIF2_0),
-	PINMUX_IPSR_MSEL(IP14_27_24,	MSIOF1_SYNC_A,		SEL_MSIOF1_0),
-	PINMUX_IPSR_MSEL(IP14_27_24,	TS_SDEN0_A,		SEL_TSIF0_0),
-	PINMUX_IPSR_MSEL(IP14_27_24,	STP_ISEN_0_A,		SEL_SSP1_0_0),
-	PINMUX_IPSR_MSEL(IP14_27_24,	RIF0_SYNC_A,		SEL_DRIF0_0),
-	PINMUX_IPSR_MSEL(IP14_27_24,	RIF2_SYNC_A,		SEL_DRIF2_0),
-
-	PINMUX_IPSR_GPSR(IP14_31_28,	SSI_SDATA4),
-	PINMUX_IPSR_MSEL(IP14_31_28,	HSCK2_A,		SEL_HSCIF2_0),
-	PINMUX_IPSR_MSEL(IP14_31_28,	MSIOF1_RXD_A,		SEL_MSIOF1_0),
-	PINMUX_IPSR_MSEL(IP14_31_28,	TS_SPSYNC0_A,		SEL_TSIF0_0),
-	PINMUX_IPSR_MSEL(IP14_31_28,	STP_ISSYNC_0_A,		SEL_SSP1_0_0),
-	PINMUX_IPSR_MSEL(IP14_31_28,	RIF0_D0_A,		SEL_DRIF0_0),
-	PINMUX_IPSR_MSEL(IP14_31_28,	RIF2_D1_A,		SEL_DRIF2_0),
+	PINMUX_IPSR_GPSR(IP14_3_0,	MSIOF0_SS1),
+	PINMUX_IPSR_MSEL(IP14_3_0,	RX5_A,			SEL_SCIF5_0),
+	PINMUX_IPSR_MSEL(IP14_3_0,	NFWP_N_A,		SEL_NDF_0),
+	PINMUX_IPSR_MSEL(IP14_3_0,	AUDIO_CLKA_C,		SEL_ADG_A_2),
+	PINMUX_IPSR_MSEL(IP14_3_0,	SSI_SCK2_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP14_3_0,	STP_IVCXO27_0_C,	SEL_SSP1_0_2),
+	PINMUX_IPSR_GPSR(IP14_3_0,	AUDIO_CLKOUT3_A),
+	PINMUX_IPSR_MSEL(IP14_3_0,	TCLK1_B,		SEL_TIMER_TMU_1),
+
+	PINMUX_IPSR_GPSR(IP14_7_4,	MSIOF0_SS2),
+	PINMUX_IPSR_MSEL(IP14_7_4,	TX5_A,			SEL_SCIF5_0),
+	PINMUX_IPSR_MSEL(IP14_7_4,	MSIOF1_SS2_D,		SEL_MSIOF1_3),
+	PINMUX_IPSR_MSEL(IP14_7_4,	AUDIO_CLKC_A,		SEL_ADG_C_0),
+	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_WS2_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP14_7_4,	STP_OPWM_0_D,		SEL_SSP1_0_3),
+	PINMUX_IPSR_GPSR(IP14_7_4,	AUDIO_CLKOUT_D),
+	PINMUX_IPSR_MSEL(IP14_7_4,	SPEEDIN_B,		SEL_SPEED_PULSE_1),
+
+	PINMUX_IPSR_GPSR(IP14_11_8,	MLB_CLK),
+	PINMUX_IPSR_MSEL(IP14_11_8,	MSIOF1_SCK_F,		SEL_MSIOF1_5),
+	PINMUX_IPSR_MSEL(IP14_11_8,	SCL1_B,			SEL_I2C1_1),
+
+	PINMUX_IPSR_GPSR(IP14_15_12,	MLB_SIG),
+	PINMUX_IPSR_MSEL(IP14_15_12,	RX1_B,			SEL_SCIF1_1),
+	PINMUX_IPSR_MSEL(IP14_15_12,	MSIOF1_SYNC_F,		SEL_MSIOF1_5),
+	PINMUX_IPSR_MSEL(IP14_15_12,	SDA1_B,			SEL_I2C1_1),
+
+	PINMUX_IPSR_GPSR(IP14_19_16,	MLB_DAT),
+	PINMUX_IPSR_MSEL(IP14_19_16,	TX1_B,			SEL_SCIF1_1),
+	PINMUX_IPSR_MSEL(IP14_19_16,	MSIOF1_RXD_F,		SEL_MSIOF1_5),
+
+	PINMUX_IPSR_GPSR(IP14_23_20,	SSI_SCK01239),
+	PINMUX_IPSR_MSEL(IP14_23_20,	MSIOF1_TXD_F,		SEL_MSIOF1_5),
+
+	PINMUX_IPSR_GPSR(IP14_27_24,	SSI_WS01239),
+	PINMUX_IPSR_MSEL(IP14_27_24,	MSIOF1_SS1_F,		SEL_MSIOF1_5),
+
+	PINMUX_IPSR_GPSR(IP14_31_28,	SSI_SDATA0),
+	PINMUX_IPSR_MSEL(IP14_31_28,	MSIOF1_SS2_F,		SEL_MSIOF1_5),
 
 	/* IPSR15 */
-	PINMUX_IPSR_GPSR(IP15_3_0,	SSI_SCK6),
-	PINMUX_IPSR_GPSR(IP15_3_0,	USB2_PWEN),
-	PINMUX_IPSR_MSEL(IP15_3_0,	SIM0_RST_D,		SEL_SIMCARD_3),
-
-	PINMUX_IPSR_GPSR(IP15_7_4,	SSI_WS6),
-	PINMUX_IPSR_GPSR(IP15_7_4,	USB2_OVC),
-	PINMUX_IPSR_MSEL(IP15_7_4,	SIM0_D_D,		SEL_SIMCARD_3),
-
-	PINMUX_IPSR_GPSR(IP15_11_8,	SSI_SDATA6),
-	PINMUX_IPSR_MSEL(IP15_11_8,	SIM0_CLK_D,		SEL_SIMCARD_3),
-	PINMUX_IPSR_MSEL(IP15_11_8,	SATA_DEVSLP_A,		SEL_SATA_0),
-
-	PINMUX_IPSR_GPSR(IP15_15_12,	SSI_SCK78),
-	PINMUX_IPSR_MSEL(IP15_15_12,	HRX2_B,			SEL_HSCIF2_1),
-	PINMUX_IPSR_MSEL(IP15_15_12,	MSIOF1_SCK_C,		SEL_MSIOF1_2),
-	PINMUX_IPSR_MSEL(IP15_15_12,	TS_SCK1_A,		SEL_TSIF1_0),
-	PINMUX_IPSR_MSEL(IP15_15_12,	STP_ISCLK_1_A,		SEL_SSP1_1_0),
-	PINMUX_IPSR_MSEL(IP15_15_12,	RIF1_CLK_A,		SEL_DRIF1_0),
-	PINMUX_IPSR_MSEL(IP15_15_12,	RIF3_CLK_A,		SEL_DRIF3_0),
-
-	PINMUX_IPSR_GPSR(IP15_19_16,	SSI_WS78),
-	PINMUX_IPSR_MSEL(IP15_19_16,	HTX2_B,			SEL_HSCIF2_1),
-	PINMUX_IPSR_MSEL(IP15_19_16,	MSIOF1_SYNC_C,		SEL_MSIOF1_2),
-	PINMUX_IPSR_MSEL(IP15_19_16,	TS_SDAT1_A,		SEL_TSIF1_0),
-	PINMUX_IPSR_MSEL(IP15_19_16,	STP_ISD_1_A,		SEL_SSP1_1_0),
-	PINMUX_IPSR_MSEL(IP15_19_16,	RIF1_SYNC_A,		SEL_DRIF1_0),
-	PINMUX_IPSR_MSEL(IP15_19_16,	RIF3_SYNC_A,		SEL_DRIF3_0),
-
-	PINMUX_IPSR_GPSR(IP15_23_20,	SSI_SDATA7),
-	PINMUX_IPSR_MSEL(IP15_23_20,	HCTS2_N_B,		SEL_HSCIF2_1),
-	PINMUX_IPSR_MSEL(IP15_23_20,	MSIOF1_RXD_C,		SEL_MSIOF1_2),
-	PINMUX_IPSR_MSEL(IP15_23_20,	TS_SDEN1_A,		SEL_TSIF1_0),
-	PINMUX_IPSR_MSEL(IP15_23_20,	STP_ISEN_1_A,		SEL_SSP1_1_0),
-	PINMUX_IPSR_MSEL(IP15_23_20,	RIF1_D0_A,		SEL_DRIF1_0),
-	PINMUX_IPSR_MSEL(IP15_23_20,	RIF3_D0_A,		SEL_DRIF3_0),
-	PINMUX_IPSR_MSEL(IP15_23_20,	TCLK2_A,		SEL_TIMER_TMU_0),
-
-	PINMUX_IPSR_GPSR(IP15_27_24,	SSI_SDATA8),
-	PINMUX_IPSR_MSEL(IP15_27_24,	HRTS2_N_B,		SEL_HSCIF2_1),
-	PINMUX_IPSR_MSEL(IP15_27_24,	MSIOF1_TXD_C,		SEL_MSIOF1_2),
-	PINMUX_IPSR_MSEL(IP15_27_24,	TS_SPSYNC1_A,		SEL_TSIF1_0),
-	PINMUX_IPSR_MSEL(IP15_27_24,	STP_ISSYNC_1_A,		SEL_SSP1_1_0),
-	PINMUX_IPSR_MSEL(IP15_27_24,	RIF1_D1_A,		SEL_DRIF1_0),
-	PINMUX_IPSR_MSEL(IP15_27_24,	RIF3_D1_A,		SEL_DRIF3_0),
-
-	PINMUX_IPSR_MSEL(IP15_31_28,	SSI_SDATA9_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP15_31_28,	HSCK2_B,		SEL_HSCIF2_1),
-	PINMUX_IPSR_MSEL(IP15_31_28,	MSIOF1_SS1_C,		SEL_MSIOF1_2),
-	PINMUX_IPSR_MSEL(IP15_31_28,	HSCK1_A,		SEL_HSCIF1_0),
-	PINMUX_IPSR_MSEL(IP15_31_28,	SSI_WS1_B,		SEL_SSI_1),
-	PINMUX_IPSR_GPSR(IP15_31_28,	SCK1),
-	PINMUX_IPSR_MSEL(IP15_31_28,	STP_IVCXO27_1_A,	SEL_SSP1_1_0),
-	PINMUX_IPSR_GPSR(IP15_31_28,	SCK5),
+	PINMUX_IPSR_MSEL(IP15_3_0,	SSI_SDATA1_A,		SEL_SSI_0),
+
+	PINMUX_IPSR_MSEL(IP15_7_4,	SSI_SDATA2_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP15_7_4,	SSI_SCK1_B,		SEL_SSI_1),
+
+	PINMUX_IPSR_GPSR(IP15_11_8,	SSI_SCK34),
+	PINMUX_IPSR_MSEL(IP15_11_8,	MSIOF1_SS1_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP15_11_8,	STP_OPWM_0_A,		SEL_SSP1_0_0),
+
+	PINMUX_IPSR_GPSR(IP15_15_12,	SSI_WS34),
+	PINMUX_IPSR_MSEL(IP15_15_12,	HCTS2_N_A,		SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP15_15_12,	MSIOF1_SS2_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP15_15_12,	STP_IVCXO27_0_A,	SEL_SSP1_0_0),
+
+	PINMUX_IPSR_GPSR(IP15_19_16,	SSI_SDATA3),
+	PINMUX_IPSR_MSEL(IP15_19_16,	HRTS2_N_A,		SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	MSIOF1_TXD_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	TS_SCK0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	STP_ISCLK_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	RIF0_D1_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP15_19_16,	RIF2_D0_A,		SEL_DRIF2_0),
+
+	PINMUX_IPSR_GPSR(IP15_23_20,	SSI_SCK4),
+	PINMUX_IPSR_MSEL(IP15_23_20,	HRX2_A,			SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	MSIOF1_SCK_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	TS_SDAT0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	STP_ISD_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	RIF0_CLK_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP15_23_20,	RIF2_CLK_A,		SEL_DRIF2_0),
+
+	PINMUX_IPSR_GPSR(IP15_27_24,	SSI_WS4),
+	PINMUX_IPSR_MSEL(IP15_27_24,	HTX2_A,			SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	MSIOF1_SYNC_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	TS_SDEN0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	STP_ISEN_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	RIF0_SYNC_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP15_27_24,	RIF2_SYNC_A,		SEL_DRIF2_0),
+
+	PINMUX_IPSR_GPSR(IP15_31_28,	SSI_SDATA4),
+	PINMUX_IPSR_MSEL(IP15_31_28,	HSCK2_A,		SEL_HSCIF2_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	MSIOF1_RXD_A,		SEL_MSIOF1_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	TS_SPSYNC0_A,		SEL_TSIF0_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	STP_ISSYNC_0_A,		SEL_SSP1_0_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	RIF0_D0_A,		SEL_DRIF0_0),
+	PINMUX_IPSR_MSEL(IP15_31_28,	RIF2_D1_A,		SEL_DRIF2_0),
 
 	/* IPSR16 */
-	PINMUX_IPSR_MSEL(IP16_3_0,	AUDIO_CLKA_A,		SEL_ADG_0),
-	PINMUX_IPSR_GPSR(IP16_3_0,	CC5_OSCOUT),
-
-	PINMUX_IPSR_MSEL(IP16_7_4,	AUDIO_CLKB_B,		SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP16_7_4,	SCIF_CLK_A,		SEL_SCIF1_0),
-	PINMUX_IPSR_MSEL(IP16_7_4,	STP_IVCXO27_1_D,	SEL_SSP1_1_3),
-	PINMUX_IPSR_MSEL(IP16_7_4,	REMOCON_A,		SEL_REMOCON_0),
-	PINMUX_IPSR_MSEL(IP16_7_4,	TCLK1_A,		SEL_TIMER_TMU_0),
-
-	PINMUX_IPSR_GPSR(IP16_11_8,	USB0_PWEN),
-	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_RST_C,		SEL_SIMCARD_2),
-	PINMUX_IPSR_MSEL(IP16_11_8,	TS_SCK1_D,		SEL_TSIF1_3),
-	PINMUX_IPSR_MSEL(IP16_11_8,	STP_ISCLK_1_D,		SEL_SSP1_1_3),
-	PINMUX_IPSR_MSEL(IP16_11_8,	BPFCLK_B,		SEL_FM_1),
-	PINMUX_IPSR_MSEL(IP16_11_8,	RIF3_CLK_B,		SEL_DRIF3_1),
-
-	PINMUX_IPSR_GPSR(IP16_15_12,	USB0_OVC),
-	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_D_C,		SEL_SIMCARD_2),
-	PINMUX_IPSR_MSEL(IP16_11_8,	TS_SDAT1_D,		SEL_TSIF1_3),
-	PINMUX_IPSR_MSEL(IP16_11_8,	STP_ISD_1_D,		SEL_SSP1_1_3),
-	PINMUX_IPSR_MSEL(IP16_11_8,	RIF3_SYNC_B,		SEL_DRIF3_1),
-
-	PINMUX_IPSR_GPSR(IP16_19_16,	USB1_PWEN),
-	PINMUX_IPSR_MSEL(IP16_19_16,	SIM0_CLK_C,		SEL_SIMCARD_2),
-	PINMUX_IPSR_MSEL(IP16_19_16,	SSI_SCK1_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP16_19_16,	TS_SCK0_E,		SEL_TSIF0_4),
-	PINMUX_IPSR_MSEL(IP16_19_16,	STP_ISCLK_0_E,		SEL_SSP1_0_4),
-	PINMUX_IPSR_MSEL(IP16_19_16,	FMCLK_B,		SEL_FM_1),
-	PINMUX_IPSR_MSEL(IP16_19_16,	RIF2_CLK_B,		SEL_DRIF2_1),
-	PINMUX_IPSR_MSEL(IP16_19_16,	SPEEDIN_A,		SEL_SPEED_PULSE_0),
-
-	PINMUX_IPSR_GPSR(IP16_23_20,	USB1_OVC),
-	PINMUX_IPSR_MSEL(IP16_23_20,	MSIOF1_SS2_C,		SEL_MSIOF1_2),
-	PINMUX_IPSR_MSEL(IP16_23_20,	SSI_WS1_A,		SEL_SSI_0),
-	PINMUX_IPSR_MSEL(IP16_23_20,	TS_SDAT0_E,		SEL_TSIF0_4),
-	PINMUX_IPSR_MSEL(IP16_23_20,	STP_ISD_0_E,		SEL_SSP1_0_4),
-	PINMUX_IPSR_MSEL(IP16_23_20,	FMIN_B,			SEL_FM_1),
-	PINMUX_IPSR_MSEL(IP16_23_20,	RIF2_SYNC_B,		SEL_DRIF2_1),
-	PINMUX_IPSR_MSEL(IP16_23_20,	REMOCON_B,		SEL_REMOCON_1),
-
-	PINMUX_IPSR_GPSR(IP16_27_24,	USB30_PWEN),
-	PINMUX_IPSR_MSEL(IP16_27_24,	AUDIO_CLKOUT_B,		SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP16_27_24,	SSI_SCK2_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP16_27_24,	TS_SDEN1_D,		SEL_TSIF1_3),
-	PINMUX_IPSR_MSEL(IP16_27_24,	STP_ISEN_1_D,		SEL_SSP1_1_2),
-	PINMUX_IPSR_MSEL(IP16_27_24,	STP_OPWM_0_E,		SEL_SSP1_0_4),
-	PINMUX_IPSR_MSEL(IP16_27_24,	RIF3_D0_B,		SEL_DRIF3_1),
-	PINMUX_IPSR_MSEL(IP16_27_24,	TCLK2_B,		SEL_TIMER_TMU_1),
-	PINMUX_IPSR_GPSR(IP16_27_24,	TPU0TO0),
-
-	PINMUX_IPSR_GPSR(IP16_31_28,	USB30_OVC),
-	PINMUX_IPSR_MSEL(IP16_31_28,	AUDIO_CLKOUT1_B,	SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP16_31_28,	SSI_WS2_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP16_31_28,	TS_SPSYNC1_D,		SEL_TSIF1_3),
-	PINMUX_IPSR_MSEL(IP16_31_28,	STP_ISSYNC_1_D,		SEL_SSP1_1_3),
-	PINMUX_IPSR_MSEL(IP16_31_28,	STP_IVCXO27_0_E,	SEL_SSP1_0_4),
-	PINMUX_IPSR_MSEL(IP16_31_28,	RIF3_D1_B,		SEL_DRIF3_1),
-	PINMUX_IPSR_MSEL(IP16_31_28,	FSO_TOE_B,		SEL_FSO_1),
-	PINMUX_IPSR_GPSR(IP16_31_28,	TPU0TO1),
+	PINMUX_IPSR_GPSR(IP16_3_0,	SSI_SCK6),
+	PINMUX_IPSR_GPSR(IP16_3_0,	USB2_PWEN),
+	PINMUX_IPSR_MSEL(IP16_3_0,	SIM0_RST_D,		SEL_SIMCARD_3),
+
+	PINMUX_IPSR_GPSR(IP16_7_4,	SSI_WS6),
+	PINMUX_IPSR_GPSR(IP16_7_4,	USB2_OVC),
+	PINMUX_IPSR_MSEL(IP16_7_4,	SIM0_D_D,		SEL_SIMCARD_3),
+
+	PINMUX_IPSR_GPSR(IP16_11_8,	SSI_SDATA6),
+	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_CLK_D,		SEL_SIMCARD_3),
+	PINMUX_IPSR_GPSR(IP16_11_8,	SATA_DEVSLP_A),
+
+	PINMUX_IPSR_GPSR(IP16_15_12,	SSI_SCK78),
+	PINMUX_IPSR_MSEL(IP16_15_12,	HRX2_B,			SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP16_15_12,	MSIOF1_SCK_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP16_15_12,	TS_SCK1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP16_15_12,	STP_ISCLK_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP16_15_12,	RIF1_CLK_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP16_15_12,	RIF3_CLK_A,		SEL_DRIF3_0),
+
+	PINMUX_IPSR_GPSR(IP16_19_16,	SSI_WS78),
+	PINMUX_IPSR_MSEL(IP16_19_16,	HTX2_B,			SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP16_19_16,	MSIOF1_SYNC_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP16_19_16,	TS_SDAT1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP16_19_16,	STP_ISD_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP16_19_16,	RIF1_SYNC_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP16_19_16,	RIF3_SYNC_A,		SEL_DRIF3_0),
+
+	PINMUX_IPSR_GPSR(IP16_23_20,	SSI_SDATA7),
+	PINMUX_IPSR_MSEL(IP16_23_20,	HCTS2_N_B,		SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP16_23_20,	MSIOF1_RXD_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP16_23_20,	TS_SDEN1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP16_23_20,	STP_ISEN_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP16_23_20,	RIF1_D0_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP16_23_20,	RIF3_D0_A,		SEL_DRIF3_0),
+	PINMUX_IPSR_MSEL(IP16_23_20,	TCLK2_A,		SEL_TIMER_TMU_0),
+
+	PINMUX_IPSR_GPSR(IP16_27_24,	SSI_SDATA8),
+	PINMUX_IPSR_MSEL(IP16_27_24,	HRTS2_N_B,		SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP16_27_24,	MSIOF1_TXD_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP16_27_24,	TS_SPSYNC1_A,		SEL_TSIF1_0),
+	PINMUX_IPSR_MSEL(IP16_27_24,	STP_ISSYNC_1_A,		SEL_SSP1_1_0),
+	PINMUX_IPSR_MSEL(IP16_27_24,	RIF1_D1_A,		SEL_DRIF1_0),
+	PINMUX_IPSR_MSEL(IP16_27_24,	RIF3_D1_A,		SEL_DRIF3_0),
+
+	PINMUX_IPSR_MSEL(IP16_31_28,	SSI_SDATA9_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP16_31_28,	HSCK2_B,		SEL_HSCIF2_1),
+	PINMUX_IPSR_MSEL(IP16_31_28,	MSIOF1_SS1_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP16_31_28,	HSCK1_A,		SEL_HSCIF1_0),
+	PINMUX_IPSR_MSEL(IP16_31_28,	SSI_WS1_B,		SEL_SSI_1),
+	PINMUX_IPSR_GPSR(IP16_31_28,	SCK1),
+	PINMUX_IPSR_MSEL(IP16_31_28,	STP_IVCXO27_1_A,	SEL_SSP1_1_0),
+	PINMUX_IPSR_GPSR(IP16_31_28,	SCK5_A),
 
 	/* IPSR17 */
-	PINMUX_IPSR_GPSR(IP17_3_0,	USB31_PWEN),
-	PINMUX_IPSR_MSEL(IP17_3_0,	AUDIO_CLKOUT2_B,	SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP17_3_0,	SSI_SCK9_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP17_3_0,	TS_SDEN0_E,		SEL_TSIF0_4),
-	PINMUX_IPSR_MSEL(IP17_3_0,	STP_ISEN_0_E,		SEL_SSP1_0_4),
-	PINMUX_IPSR_MSEL(IP17_3_0,	RIF2_D0_B,		SEL_DRIF2_1),
-	PINMUX_IPSR_GPSR(IP17_3_0,	TPU0TO2),
-
-	PINMUX_IPSR_GPSR(IP17_7_4,	USB31_OVC),
-	PINMUX_IPSR_MSEL(IP17_7_4,	AUDIO_CLKOUT3_B,	SEL_ADG_1),
-	PINMUX_IPSR_MSEL(IP17_7_4,	SSI_WS9_B,		SEL_SSI_1),
-	PINMUX_IPSR_MSEL(IP17_7_4,	TS_SPSYNC0_E,		SEL_TSIF0_4),
-	PINMUX_IPSR_MSEL(IP17_7_4,	STP_ISSYNC_0_E,		SEL_SSP1_0_4),
-	PINMUX_IPSR_MSEL(IP17_7_4,	RIF2_D1_B,		SEL_DRIF2_1),
-	PINMUX_IPSR_GPSR(IP17_7_4,	TPU0TO3),
+	PINMUX_IPSR_MSEL(IP17_3_0,	AUDIO_CLKA_A,		SEL_ADG_A_0),
+	PINMUX_IPSR_GPSR(IP17_3_0,	CC5_OSCOUT),
+
+	PINMUX_IPSR_MSEL(IP17_7_4,	AUDIO_CLKB_B,		SEL_ADG_B_1),
+	PINMUX_IPSR_MSEL(IP17_7_4,	SCIF_CLK_A,		SEL_SCIF1_0),
+	PINMUX_IPSR_MSEL(IP17_7_4,	STP_IVCXO27_1_D,	SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP17_7_4,	REMOCON_A,		SEL_REMOCON_0),
+	PINMUX_IPSR_MSEL(IP17_7_4,	TCLK1_A,		SEL_TIMER_TMU_0),
+
+	PINMUX_IPSR_GPSR(IP17_11_8,	USB0_PWEN),
+	PINMUX_IPSR_MSEL(IP17_11_8,	SIM0_RST_C,		SEL_SIMCARD_2),
+	PINMUX_IPSR_MSEL(IP17_11_8,	TS_SCK1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP17_11_8,	STP_ISCLK_1_D,		SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP17_11_8,	BPFCLK_B,		SEL_FM_1),
+	PINMUX_IPSR_MSEL(IP17_11_8,	RIF3_CLK_B,		SEL_DRIF3_1),
+	PINMUX_IPSR_MSEL(IP17_11_8,	HSCK2_C,		SEL_HSCIF2_2),
+
+	PINMUX_IPSR_GPSR(IP17_15_12,	USB0_OVC),
+	PINMUX_IPSR_MSEL(IP17_15_12,	SIM0_D_C,		SEL_SIMCARD_2),
+	PINMUX_IPSR_MSEL(IP17_15_12,	TS_SDAT1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP17_15_12,	STP_ISD_1_D,		SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP17_15_12,	RIF3_SYNC_B,		SEL_DRIF3_1),
+	PINMUX_IPSR_MSEL(IP17_15_12,	HRX2_C,			SEL_HSCIF2_2),
+
+	PINMUX_IPSR_GPSR(IP17_19_16,	USB1_PWEN),
+	PINMUX_IPSR_MSEL(IP17_19_16,	SIM0_CLK_C,		SEL_SIMCARD_2),
+	PINMUX_IPSR_MSEL(IP17_19_16,	SSI_SCK1_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP17_19_16,	TS_SCK0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP17_19_16,	STP_ISCLK_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP17_19_16,	FMCLK_B,		SEL_FM_1),
+	PINMUX_IPSR_MSEL(IP17_19_16,	RIF2_CLK_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_MSEL(IP17_19_16,	SPEEDIN_A,		SEL_SPEED_PULSE_0),
+	PINMUX_IPSR_MSEL(IP17_19_16,	HTX2_C,			SEL_HSCIF2_2),
+
+	PINMUX_IPSR_GPSR(IP17_23_20,	USB1_OVC),
+	PINMUX_IPSR_MSEL(IP17_23_20,	MSIOF1_SS2_C,		SEL_MSIOF1_2),
+	PINMUX_IPSR_MSEL(IP17_23_20,	SSI_WS1_A,		SEL_SSI_0),
+	PINMUX_IPSR_MSEL(IP17_23_20,	TS_SDAT0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP17_23_20,	STP_ISD_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP17_23_20,	FMIN_B,			SEL_FM_1),
+	PINMUX_IPSR_MSEL(IP17_23_20,	RIF2_SYNC_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_MSEL(IP17_23_20,	REMOCON_B,		SEL_REMOCON_1),
+	PINMUX_IPSR_MSEL(IP17_23_20,	HCTS2_N_C,		SEL_HSCIF2_2),
+
+	PINMUX_IPSR_GPSR(IP17_27_24,	USB30_PWEN),
+	PINMUX_IPSR_GPSR(IP17_27_24,	AUDIO_CLKOUT_B),
+	PINMUX_IPSR_MSEL(IP17_27_24,	SSI_SCK2_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP17_27_24,	TS_SDEN1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP17_27_24,	STP_ISEN_1_D,		SEL_SSP1_1_2),
+	PINMUX_IPSR_MSEL(IP17_27_24,	STP_OPWM_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP17_27_24,	RIF3_D0_B,		SEL_DRIF3_1),
+	PINMUX_IPSR_MSEL(IP17_27_24,	TCLK2_B,		SEL_TIMER_TMU_1),
+	PINMUX_IPSR_GPSR(IP17_27_24,	TPU0TO0),
+	PINMUX_IPSR_MSEL(IP17_27_24,	BPFCLK_C,		SEL_FM_2),
+	PINMUX_IPSR_MSEL(IP17_27_24,	HRTS2_N_C,		SEL_HSCIF2_2),
+
+	PINMUX_IPSR_GPSR(IP17_31_28,	USB30_OVC),
+	PINMUX_IPSR_GPSR(IP17_31_28,	AUDIO_CLKOUT1_B),
+	PINMUX_IPSR_MSEL(IP17_31_28,	SSI_WS2_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP17_31_28,	TS_SPSYNC1_D,		SEL_TSIF1_3),
+	PINMUX_IPSR_MSEL(IP17_31_28,	STP_ISSYNC_1_D,		SEL_SSP1_1_3),
+	PINMUX_IPSR_MSEL(IP17_31_28,	STP_IVCXO27_0_E,	SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP17_31_28,	RIF3_D1_B,		SEL_DRIF3_1),
+	PINMUX_IPSR_GPSR(IP17_31_28,	FSO_TOE_N),
+	PINMUX_IPSR_GPSR(IP17_31_28,	TPU0TO1),
+
+	/* IPSR18 */
+	PINMUX_IPSR_GPSR(IP18_3_0,	USB3_PWEN),
+	PINMUX_IPSR_GPSR(IP18_3_0,	AUDIO_CLKOUT2_B),
+	PINMUX_IPSR_MSEL(IP18_3_0,	SSI_SCK9_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP18_3_0,	TS_SDEN0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP18_3_0,	STP_ISEN_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP18_3_0,	RIF2_D0_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_GPSR(IP18_3_0,	TPU0TO2),
+	PINMUX_IPSR_MSEL(IP18_3_0,	FMCLK_C,		SEL_FM_2),
+	PINMUX_IPSR_MSEL(IP18_3_0,	FMCLK_D,		SEL_FM_3),
+
+	PINMUX_IPSR_GPSR(IP18_7_4,	USB3_OVC),
+	PINMUX_IPSR_GPSR(IP18_7_4,	AUDIO_CLKOUT3_B),
+	PINMUX_IPSR_MSEL(IP18_7_4,	SSI_WS9_B,		SEL_SSI_1),
+	PINMUX_IPSR_MSEL(IP18_7_4,	TS_SPSYNC0_E,		SEL_TSIF0_4),
+	PINMUX_IPSR_MSEL(IP18_7_4,	STP_ISSYNC_0_E,		SEL_SSP1_0_4),
+	PINMUX_IPSR_MSEL(IP18_7_4,	RIF2_D1_B,		SEL_DRIF2_1),
+	PINMUX_IPSR_GPSR(IP18_7_4,	TPU0TO3),
+	PINMUX_IPSR_MSEL(IP18_7_4,	FMIN_C,			SEL_FM_2),
+	PINMUX_IPSR_MSEL(IP18_7_4,	FMIN_D,			SEL_FM_3),
 
 /*
  * Static pins can not be muxed between different functions but
@@ -1507,1616 +1576,6 @@ static const struct sh_pfc_pin pinmux_pins[] = {
 	SH_PFC_PIN_NAMED_CFG(ROW_GROUP_A('T'), 30, ASEBRK, CFG_FLAGS),
 };
 
-/* - AUDIO CLOCK ------------------------------------------------------------ */
-static const unsigned int audio_clk_a_a_pins[] = {
-	/* CLK A */
-	RCAR_GP_PIN(6, 22),
-};
-static const unsigned int audio_clk_a_a_mux[] = {
-	AUDIO_CLKA_A_MARK,
-};
-static const unsigned int audio_clk_a_b_pins[] = {
-	/* CLK A */
-	RCAR_GP_PIN(5, 4),
-};
-static const unsigned int audio_clk_a_b_mux[] = {
-	AUDIO_CLKA_B_MARK,
-};
-static const unsigned int audio_clk_a_c_pins[] = {
-	/* CLK A */
-	RCAR_GP_PIN(5, 19),
-};
-static const unsigned int audio_clk_a_c_mux[] = {
-	AUDIO_CLKA_C_MARK,
-};
-static const unsigned int audio_clk_b_a_pins[] = {
-	/* CLK B */
-	RCAR_GP_PIN(5, 12),
-};
-static const unsigned int audio_clk_b_a_mux[] = {
-	AUDIO_CLKB_A_MARK,
-};
-static const unsigned int audio_clk_b_b_pins[] = {
-	/* CLK B */
-	RCAR_GP_PIN(6, 23),
-};
-static const unsigned int audio_clk_b_b_mux[] = {
-	AUDIO_CLKB_B_MARK,
-};
-static const unsigned int audio_clk_c_a_pins[] = {
-	/* CLK C */
-	RCAR_GP_PIN(5, 21),
-};
-static const unsigned int audio_clk_c_a_mux[] = {
-	AUDIO_CLKC_A_MARK,
-};
-static const unsigned int audio_clk_c_b_pins[] = {
-	/* CLK C */
-	RCAR_GP_PIN(5, 0),
-};
-static const unsigned int audio_clk_c_b_mux[] = {
-	AUDIO_CLKC_B_MARK,
-};
-static const unsigned int audio_clkout_a_pins[] = {
-	/* CLKOUT */
-	RCAR_GP_PIN(5, 18),
-};
-static const unsigned int audio_clkout_a_mux[] = {
-	AUDIO_CLKOUT_A_MARK,
-};
-static const unsigned int audio_clkout_b_pins[] = {
-	/* CLKOUT */
-	RCAR_GP_PIN(6, 28),
-};
-static const unsigned int audio_clkout_b_mux[] = {
-	AUDIO_CLKOUT_B_MARK,
-};
-static const unsigned int audio_clkout_c_pins[] = {
-	/* CLKOUT */
-	RCAR_GP_PIN(5, 3),
-};
-static const unsigned int audio_clkout_c_mux[] = {
-	AUDIO_CLKOUT_C_MARK,
-};
-static const unsigned int audio_clkout_d_pins[] = {
-	/* CLKOUT */
-	RCAR_GP_PIN(5, 21),
-};
-static const unsigned int audio_clkout_d_mux[] = {
-	AUDIO_CLKOUT_D_MARK,
-};
-static const unsigned int audio_clkout1_a_pins[] = {
-	/* CLKOUT1 */
-	RCAR_GP_PIN(5, 15),
-};
-static const unsigned int audio_clkout1_a_mux[] = {
-	AUDIO_CLKOUT1_A_MARK,
-};
-static const unsigned int audio_clkout1_b_pins[] = {
-	/* CLKOUT1 */
-	RCAR_GP_PIN(6, 29),
-};
-static const unsigned int audio_clkout1_b_mux[] = {
-	AUDIO_CLKOUT1_B_MARK,
-};
-static const unsigned int audio_clkout2_a_pins[] = {
-	/* CLKOUT2 */
-	RCAR_GP_PIN(5, 16),
-};
-static const unsigned int audio_clkout2_a_mux[] = {
-	AUDIO_CLKOUT2_A_MARK,
-};
-static const unsigned int audio_clkout2_b_pins[] = {
-	/* CLKOUT2 */
-	RCAR_GP_PIN(6, 30),
-};
-static const unsigned int audio_clkout2_b_mux[] = {
-	AUDIO_CLKOUT2_B_MARK,
-};
-
-static const unsigned int audio_clkout3_a_pins[] = {
-	/* CLKOUT3 */
-	RCAR_GP_PIN(5, 19),
-};
-static const unsigned int audio_clkout3_a_mux[] = {
-	AUDIO_CLKOUT3_A_MARK,
-};
-static const unsigned int audio_clkout3_b_pins[] = {
-	/* CLKOUT3 */
-	RCAR_GP_PIN(6, 31),
-};
-static const unsigned int audio_clkout3_b_mux[] = {
-	AUDIO_CLKOUT3_B_MARK,
-};
-
-/* - EtherAVB --------------------------------------------------------------- */
-static const unsigned int avb_link_pins[] = {
-	/* AVB_LINK */
-	RCAR_GP_PIN(2, 12),
-};
-static const unsigned int avb_link_mux[] = {
-	AVB_LINK_MARK,
-};
-static const unsigned int avb_magic_pins[] = {
-	/* AVB_MAGIC_ */
-	RCAR_GP_PIN(2, 10),
-};
-static const unsigned int avb_magic_mux[] = {
-	AVB_MAGIC_MARK,
-};
-static const unsigned int avb_phy_int_pins[] = {
-	/* AVB_PHY_INT */
-	RCAR_GP_PIN(2, 11),
-};
-static const unsigned int avb_phy_int_mux[] = {
-	AVB_PHY_INT_MARK,
-};
-static const unsigned int avb_mdc_pins[] = {
-	/* AVB_MDC, AVB_MDIO */
-	RCAR_GP_PIN(2, 9), PIN_NUMBER('A', 9),
-};
-static const unsigned int avb_mdc_mux[] = {
-	AVB_MDC_MARK, AVB_MDIO_MARK,
-};
-static const unsigned int avb_mii_pins[] = {
-	/*
-	 * AVB_TX_CTL, AVB_TXC, AVB_TD0,
-	 * AVB_TD1, AVB_TD2, AVB_TD3,
-	 * AVB_RX_CTL, AVB_RXC, AVB_RD0,
-	 * AVB_RD1, AVB_RD2, AVB_RD3,
-	 * AVB_TXCREFCLK
-	 */
-	PIN_NUMBER('A', 8), PIN_NUMBER('A', 19), PIN_NUMBER('A', 18),
-	PIN_NUMBER('B', 18), PIN_NUMBER('A', 17), PIN_NUMBER('B', 17),
-	PIN_NUMBER('A', 16), PIN_NUMBER('B', 19), PIN_NUMBER('A', 13),
-	PIN_NUMBER('B', 13), PIN_NUMBER('A', 14), PIN_NUMBER('B', 14),
-	PIN_NUMBER('A', 12),
-
-};
-static const unsigned int avb_mii_mux[] = {
-	AVB_TX_CTL_MARK, AVB_TXC_MARK, AVB_TD0_MARK,
-	AVB_TD1_MARK, AVB_TD2_MARK, AVB_TD3_MARK,
-	AVB_RX_CTL_MARK, AVB_RXC_MARK, AVB_RD0_MARK,
-	AVB_RD1_MARK, AVB_RD2_MARK, AVB_RD3_MARK,
-	AVB_TXCREFCLK_MARK,
-};
-static const unsigned int avb_avtp_pps_pins[] = {
-	/* AVB_AVTP_PPS */
-	RCAR_GP_PIN(2, 6),
-};
-static const unsigned int avb_avtp_pps_mux[] = {
-	AVB_AVTP_PPS_MARK,
-};
-static const unsigned int avb_avtp_match_a_pins[] = {
-	/* AVB_AVTP_MATCH_A */
-	RCAR_GP_PIN(2, 13),
-};
-static const unsigned int avb_avtp_match_a_mux[] = {
-	AVB_AVTP_MATCH_A_MARK,
-};
-static const unsigned int avb_avtp_capture_a_pins[] = {
-	/* AVB_AVTP_CAPTURE_A */
-	RCAR_GP_PIN(2, 14),
-};
-static const unsigned int avb_avtp_capture_a_mux[] = {
-	AVB_AVTP_CAPTURE_A_MARK,
-};
-static const unsigned int avb_avtp_match_b_pins[] = {
-	/*  AVB_AVTP_MATCH_B */
-	RCAR_GP_PIN(1, 8),
-};
-static const unsigned int avb_avtp_match_b_mux[] = {
-	AVB_AVTP_MATCH_B_MARK,
-};
-static const unsigned int avb_avtp_capture_b_pins[] = {
-	/* AVB_AVTP_CAPTURE_B */
-	RCAR_GP_PIN(1, 11),
-};
-static const unsigned int avb_avtp_capture_b_mux[] = {
-	AVB_AVTP_CAPTURE_B_MARK,
-};
-
-/* - CAN ------------------------------------------------------------------ */
-static const unsigned int can0_data_a_pins[] = {
-	/* TX, RX */
-	RCAR_GP_PIN(1, 23),	RCAR_GP_PIN(1, 24),
-};
-static const unsigned int can0_data_a_mux[] = {
-	CAN0_TX_A_MARK,		CAN0_RX_A_MARK,
-};
-static const unsigned int can0_data_b_pins[] = {
-	/* TX, RX */
-	RCAR_GP_PIN(2, 0),	RCAR_GP_PIN(2, 1),
-};
-static const unsigned int can0_data_b_mux[] = {
-	CAN0_TX_B_MARK,		CAN0_RX_B_MARK,
-};
-static const unsigned int can1_data_pins[] = {
-	/* TX, RX */
-	RCAR_GP_PIN(1, 22),	RCAR_GP_PIN(1, 26),
-};
-static const unsigned int can1_data_mux[] = {
-	CAN1_TX_MARK,		CAN1_RX_MARK,
-};
-
-/* - CAN Clock -------------------------------------------------------------- */
-static const unsigned int can_clk_pins[] = {
-	/* CLK */
-	RCAR_GP_PIN(1, 25),
-};
-static const unsigned int can_clk_mux[] = {
-	CAN_CLK_MARK,
-};
-
-/* - CAN FD --------------------------------------------------------------- */
-static const unsigned int canfd0_data_a_pins[] = {
-	/* TX, RX */
-	RCAR_GP_PIN(1, 23),     RCAR_GP_PIN(1, 24),
-};
-static const unsigned int canfd0_data_a_mux[] = {
-	CANFD0_TX_A_MARK,       CANFD0_RX_A_MARK,
-};
-static const unsigned int canfd0_data_b_pins[] = {
-	/* TX, RX */
-	RCAR_GP_PIN(2, 0),      RCAR_GP_PIN(2, 1),
-};
-static const unsigned int canfd0_data_b_mux[] = {
-	CANFD0_TX_B_MARK,       CANFD0_RX_B_MARK,
-};
-static const unsigned int canfd1_data_pins[] = {
-	/* TX, RX */
-	RCAR_GP_PIN(1, 22),     RCAR_GP_PIN(1, 26),
-};
-static const unsigned int canfd1_data_mux[] = {
-	CANFD1_TX_MARK,         CANFD1_RX_MARK,
-};
-
-/* - DRIF0 --------------------------------------------------------------- */
-static const unsigned int drif0_ctrl_a_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
-};
-static const unsigned int drif0_ctrl_a_mux[] = {
-	RIF0_CLK_A_MARK, RIF0_SYNC_A_MARK,
-};
-static const unsigned int drif0_data0_a_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(6, 10),
-};
-static const unsigned int drif0_data0_a_mux[] = {
-	RIF0_D0_A_MARK,
-};
-static const unsigned int drif0_data1_a_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(6, 7),
-};
-static const unsigned int drif0_data1_a_mux[] = {
-	RIF0_D1_A_MARK,
-};
-static const unsigned int drif0_ctrl_b_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 4),
-};
-static const unsigned int drif0_ctrl_b_mux[] = {
-	RIF0_CLK_B_MARK, RIF0_SYNC_B_MARK,
-};
-static const unsigned int drif0_data0_b_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(5, 1),
-};
-static const unsigned int drif0_data0_b_mux[] = {
-	RIF0_D0_B_MARK,
-};
-static const unsigned int drif0_data1_b_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(5, 2),
-};
-static const unsigned int drif0_data1_b_mux[] = {
-	RIF0_D1_B_MARK,
-};
-static const unsigned int drif0_ctrl_c_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(5, 12), RCAR_GP_PIN(5, 15),
-};
-static const unsigned int drif0_ctrl_c_mux[] = {
-	RIF0_CLK_C_MARK, RIF0_SYNC_C_MARK,
-};
-static const unsigned int drif0_data0_c_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(5, 13),
-};
-static const unsigned int drif0_data0_c_mux[] = {
-	RIF0_D0_C_MARK,
-};
-static const unsigned int drif0_data1_c_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(5, 14),
-};
-static const unsigned int drif0_data1_c_mux[] = {
-	RIF0_D1_C_MARK,
-};
-/* - DRIF1 --------------------------------------------------------------- */
-static const unsigned int drif1_ctrl_a_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
-};
-static const unsigned int drif1_ctrl_a_mux[] = {
-	RIF1_CLK_A_MARK, RIF1_SYNC_A_MARK,
-};
-static const unsigned int drif1_data0_a_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(6, 19),
-};
-static const unsigned int drif1_data0_a_mux[] = {
-	RIF1_D0_A_MARK,
-};
-static const unsigned int drif1_data1_a_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(6, 20),
-};
-static const unsigned int drif1_data1_a_mux[] = {
-	RIF1_D1_A_MARK,
-};
-static const unsigned int drif1_ctrl_b_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(5, 9), RCAR_GP_PIN(5, 3),
-};
-static const unsigned int drif1_ctrl_b_mux[] = {
-	RIF1_CLK_B_MARK, RIF1_SYNC_B_MARK,
-};
-static const unsigned int drif1_data0_b_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(5, 7),
-};
-static const unsigned int drif1_data0_b_mux[] = {
-	RIF1_D0_B_MARK,
-};
-static const unsigned int drif1_data1_b_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(5, 8),
-};
-static const unsigned int drif1_data1_b_mux[] = {
-	RIF1_D1_B_MARK,
-};
-static const unsigned int drif1_ctrl_c_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 11),
-};
-static const unsigned int drif1_ctrl_c_mux[] = {
-	RIF1_CLK_C_MARK, RIF1_SYNC_C_MARK,
-};
-static const unsigned int drif1_data0_c_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(5, 6),
-};
-static const unsigned int drif1_data0_c_mux[] = {
-	RIF1_D0_C_MARK,
-};
-static const unsigned int drif1_data1_c_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(5, 10),
-};
-static const unsigned int drif1_data1_c_mux[] = {
-	RIF1_D1_C_MARK,
-};
-/* - DRIF2 --------------------------------------------------------------- */
-static const unsigned int drif2_ctrl_a_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
-};
-static const unsigned int drif2_ctrl_a_mux[] = {
-	RIF2_CLK_A_MARK, RIF2_SYNC_A_MARK,
-};
-static const unsigned int drif2_data0_a_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(6, 7),
-};
-static const unsigned int drif2_data0_a_mux[] = {
-	RIF2_D0_A_MARK,
-};
-static const unsigned int drif2_data1_a_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(6, 10),
-};
-static const unsigned int drif2_data1_a_mux[] = {
-	RIF2_D1_A_MARK,
-};
-static const unsigned int drif2_ctrl_b_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
-};
-static const unsigned int drif2_ctrl_b_mux[] = {
-	RIF2_CLK_B_MARK, RIF2_SYNC_B_MARK,
-};
-static const unsigned int drif2_data0_b_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(6, 30),
-};
-static const unsigned int drif2_data0_b_mux[] = {
-	RIF2_D0_B_MARK,
-};
-static const unsigned int drif2_data1_b_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(6, 31),
-};
-static const unsigned int drif2_data1_b_mux[] = {
-	RIF2_D1_B_MARK,
-};
-/* - DRIF3 --------------------------------------------------------------- */
-static const unsigned int drif3_ctrl_a_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
-};
-static const unsigned int drif3_ctrl_a_mux[] = {
-	RIF3_CLK_A_MARK, RIF3_SYNC_A_MARK,
-};
-static const unsigned int drif3_data0_a_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(6, 19),
-};
-static const unsigned int drif3_data0_a_mux[] = {
-	RIF3_D0_A_MARK,
-};
-static const unsigned int drif3_data1_a_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(6, 20),
-};
-static const unsigned int drif3_data1_a_mux[] = {
-	RIF3_D1_A_MARK,
-};
-static const unsigned int drif3_ctrl_b_pins[] = {
-	/* CLK, SYNC */
-	RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25),
-};
-static const unsigned int drif3_ctrl_b_mux[] = {
-	RIF3_CLK_B_MARK, RIF3_SYNC_B_MARK,
-};
-static const unsigned int drif3_data0_b_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(6, 28),
-};
-static const unsigned int drif3_data0_b_mux[] = {
-	RIF3_D0_B_MARK,
-};
-static const unsigned int drif3_data1_b_pins[] = {
-	/* D1 */
-	RCAR_GP_PIN(6, 29),
-};
-static const unsigned int drif3_data1_b_mux[] = {
-	RIF3_D1_B_MARK,
-};
-
-/* - DU --------------------------------------------------------------------- */
-static const unsigned int du_rgb666_pins[] = {
-	/* R[7:2], G[7:2], B[7:2] */
-	RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 13),
-	RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10),
-	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 13),
-	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 19), RCAR_GP_PIN(1, 18),
-	RCAR_GP_PIN(1, 7),  RCAR_GP_PIN(1, 6),  RCAR_GP_PIN(1, 5),
-	RCAR_GP_PIN(1, 4),  RCAR_GP_PIN(1, 3),  RCAR_GP_PIN(1, 2),
-};
-static const unsigned int du_rgb666_mux[] = {
-	DU_DR7_MARK, DU_DR6_MARK, DU_DR5_MARK, DU_DR4_MARK,
-	DU_DR3_MARK, DU_DR2_MARK,
-	DU_DG7_MARK, DU_DG6_MARK, DU_DG5_MARK, DU_DG4_MARK,
-	DU_DG3_MARK, DU_DG2_MARK,
-	DU_DB7_MARK, DU_DB6_MARK, DU_DB5_MARK, DU_DB4_MARK,
-	DU_DB3_MARK, DU_DB2_MARK,
-};
-static const unsigned int du_rgb888_pins[] = {
-	/* R[7:0], G[7:0], B[7:0] */
-	RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 13),
-	RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10),
-	RCAR_GP_PIN(0, 9),  RCAR_GP_PIN(0, 8),
-	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 13),
-	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 19), RCAR_GP_PIN(1, 18),
-	RCAR_GP_PIN(1, 17), RCAR_GP_PIN(1, 16),
-	RCAR_GP_PIN(1, 7),  RCAR_GP_PIN(1, 6),  RCAR_GP_PIN(1, 5),
-	RCAR_GP_PIN(1, 4),  RCAR_GP_PIN(1, 3),  RCAR_GP_PIN(1, 2),
-	RCAR_GP_PIN(1, 1),  RCAR_GP_PIN(1, 0),
-};
-static const unsigned int du_rgb888_mux[] = {
-	DU_DR7_MARK, DU_DR6_MARK, DU_DR5_MARK, DU_DR4_MARK,
-	DU_DR3_MARK, DU_DR2_MARK, DU_DR1_MARK, DU_DR0_MARK,
-	DU_DG7_MARK, DU_DG6_MARK, DU_DG5_MARK, DU_DG4_MARK,
-	DU_DG3_MARK, DU_DG2_MARK, DU_DG1_MARK, DU_DG0_MARK,
-	DU_DB7_MARK, DU_DB6_MARK, DU_DB5_MARK, DU_DB4_MARK,
-	DU_DB3_MARK, DU_DB2_MARK, DU_DB1_MARK, DU_DB0_MARK,
-};
-static const unsigned int du_clk_out_0_pins[] = {
-	/* CLKOUT */
-	RCAR_GP_PIN(1, 27),
-};
-static const unsigned int du_clk_out_0_mux[] = {
-	DU_DOTCLKOUT0_MARK
-};
-static const unsigned int du_clk_out_1_pins[] = {
-	/* CLKOUT */
-	RCAR_GP_PIN(2, 3),
-};
-static const unsigned int du_clk_out_1_mux[] = {
-	DU_DOTCLKOUT1_MARK
-};
-static const unsigned int du_sync_pins[] = {
-	/* EXVSYNC/VSYNC, EXHSYNC/HSYNC */
-	RCAR_GP_PIN(2, 5), RCAR_GP_PIN(2, 4),
-};
-static const unsigned int du_sync_mux[] = {
-	DU_EXVSYNC_DU_VSYNC_MARK, DU_EXHSYNC_DU_HSYNC_MARK
-};
-static const unsigned int du_oddf_pins[] = {
-	/* EXDISP/EXODDF/EXCDE */
-	RCAR_GP_PIN(2, 2),
-};
-static const unsigned int du_oddf_mux[] = {
-	DU_EXODDF_DU_ODDF_DISP_CDE_MARK,
-};
-static const unsigned int du_cde_pins[] = {
-	/* CDE */
-	RCAR_GP_PIN(2, 0),
-};
-static const unsigned int du_cde_mux[] = {
-	DU_CDE_MARK,
-};
-static const unsigned int du_disp_pins[] = {
-	/* DISP */
-	RCAR_GP_PIN(2, 1),
-};
-static const unsigned int du_disp_mux[] = {
-	DU_DISP_MARK,
-};
-/* - HSCIF0 ----------------------------------------------------------------- */
-static const unsigned int hscif0_data_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14),
-};
-static const unsigned int hscif0_data_mux[] = {
-	HRX0_MARK, HTX0_MARK,
-};
-static const unsigned int hscif0_clk_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(5, 12),
-};
-static const unsigned int hscif0_clk_mux[] = {
-	HSCK0_MARK,
-};
-static const unsigned int hscif0_ctrl_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15),
-};
-static const unsigned int hscif0_ctrl_mux[] = {
-	HRTS0_N_MARK, HCTS0_N_MARK,
-};
-/* - HSCIF1 ----------------------------------------------------------------- */
-static const unsigned int hscif1_data_a_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
-};
-static const unsigned int hscif1_data_a_mux[] = {
-	HRX1_A_MARK, HTX1_A_MARK,
-};
-static const unsigned int hscif1_clk_a_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(6, 21),
-};
-static const unsigned int hscif1_clk_a_mux[] = {
-	HSCK1_A_MARK,
-};
-static const unsigned int hscif1_ctrl_a_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
-};
-static const unsigned int hscif1_ctrl_a_mux[] = {
-	HRTS1_N_A_MARK, HCTS1_N_A_MARK,
-};
-
-static const unsigned int hscif1_data_b_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
-};
-static const unsigned int hscif1_data_b_mux[] = {
-	HRX1_B_MARK, HTX1_B_MARK,
-};
-static const unsigned int hscif1_clk_b_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(5, 0),
-};
-static const unsigned int hscif1_clk_b_mux[] = {
-	HSCK1_B_MARK,
-};
-static const unsigned int hscif1_ctrl_b_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
-};
-static const unsigned int hscif1_ctrl_b_mux[] = {
-	HRTS1_N_B_MARK, HCTS1_N_B_MARK,
-};
-/* - HSCIF2 ----------------------------------------------------------------- */
-static const unsigned int hscif2_data_a_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
-};
-static const unsigned int hscif2_data_a_mux[] = {
-	HRX2_A_MARK, HTX2_A_MARK,
-};
-static const unsigned int hscif2_clk_a_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(6, 10),
-};
-static const unsigned int hscif2_clk_a_mux[] = {
-	HSCK2_A_MARK,
-};
-static const unsigned int hscif2_ctrl_a_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6),
-};
-static const unsigned int hscif2_ctrl_a_mux[] = {
-	HRTS2_N_A_MARK, HCTS2_N_A_MARK,
-};
-
-static const unsigned int hscif2_data_b_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
-};
-static const unsigned int hscif2_data_b_mux[] = {
-	HRX2_B_MARK, HTX2_B_MARK,
-};
-static const unsigned int hscif2_clk_b_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(6, 21),
-};
-static const unsigned int hscif2_clk_b_mux[] = {
-	HSCK1_B_MARK,
-};
-static const unsigned int hscif2_ctrl_b_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19),
-};
-static const unsigned int hscif2_ctrl_b_mux[] = {
-	HRTS2_N_B_MARK, HCTS2_N_B_MARK,
-};
-/* - HSCIF3 ----------------------------------------------------------------- */
-static const unsigned int hscif3_data_a_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
-};
-static const unsigned int hscif3_data_a_mux[] = {
-	HRX3_A_MARK, HTX3_A_MARK,
-};
-static const unsigned int hscif3_clk_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(1, 22),
-};
-static const unsigned int hscif3_clk_mux[] = {
-	HSCK3_MARK,
-};
-static const unsigned int hscif3_ctrl_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
-};
-static const unsigned int hscif3_ctrl_mux[] = {
-	HRTS3_N_MARK, HCTS3_N_MARK,
-};
-
-static const unsigned int hscif3_data_b_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11),
-};
-static const unsigned int hscif3_data_b_mux[] = {
-	HRX3_B_MARK, HTX3_B_MARK,
-};
-static const unsigned int hscif3_data_c_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15),
-};
-static const unsigned int hscif3_data_c_mux[] = {
-	HRX3_C_MARK, HTX3_C_MARK,
-};
-static const unsigned int hscif3_data_d_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8),
-};
-static const unsigned int hscif3_data_d_mux[] = {
-	HRX3_D_MARK, HTX3_D_MARK,
-};
-/* - HSCIF4 ----------------------------------------------------------------- */
-static const unsigned int hscif4_data_a_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13),
-};
-static const unsigned int hscif4_data_a_mux[] = {
-	HRX4_A_MARK, HTX4_A_MARK,
-};
-static const unsigned int hscif4_clk_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(1, 11),
-};
-static const unsigned int hscif4_clk_mux[] = {
-	HSCK4_MARK,
-};
-static const unsigned int hscif4_ctrl_pins[] = {
-	/* RTS, CTS */
-	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14),
-};
-static const unsigned int hscif4_ctrl_mux[] = {
-	HRTS4_N_MARK, HCTS3_N_MARK,
-};
-
-static const unsigned int hscif4_data_b_pins[] = {
-	/* RX, TX */
-	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
-};
-static const unsigned int hscif4_data_b_mux[] = {
-	HRX4_B_MARK, HTX4_B_MARK,
-};
-
-/* - I2C -------------------------------------------------------------------- */
-static const unsigned int i2c1_a_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(5, 11), RCAR_GP_PIN(5, 10),
-};
-static const unsigned int i2c1_a_mux[] = {
-	SDA1_A_MARK, SCL1_A_MARK,
-};
-static const unsigned int i2c1_b_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 23),
-};
-static const unsigned int i2c1_b_mux[] = {
-	SDA1_B_MARK, SCL1_B_MARK,
-};
-static const unsigned int i2c2_a_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 4),
-};
-static const unsigned int i2c2_a_mux[] = {
-	SDA2_A_MARK, SCL2_A_MARK,
-};
-static const unsigned int i2c2_b_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(3, 13), RCAR_GP_PIN(3, 12),
-};
-static const unsigned int i2c2_b_mux[] = {
-	SDA2_B_MARK, SCL2_B_MARK,
-};
-static const unsigned int i2c6_a_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
-};
-static const unsigned int i2c6_a_mux[] = {
-	SDA6_A_MARK, SCL6_A_MARK,
-};
-static const unsigned int i2c6_b_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
-};
-static const unsigned int i2c6_b_mux[] = {
-	SDA6_B_MARK, SCL6_B_MARK,
-};
-static const unsigned int i2c6_c_pins[] = {
-	/* SDA, SCL */
-	RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14),
-};
-static const unsigned int i2c6_c_mux[] = {
-	SDA6_C_MARK, SCL6_C_MARK,
-};
-
-/* - INTC-EX ---------------------------------------------------------------- */
-static const unsigned int intc_ex_irq0_pins[] = {
-	/* IRQ0 */
-	RCAR_GP_PIN(2, 0),
-};
-static const unsigned int intc_ex_irq0_mux[] = {
-	IRQ0_MARK,
-};
-static const unsigned int intc_ex_irq1_pins[] = {
-	/* IRQ1 */
-	RCAR_GP_PIN(2, 1),
-};
-static const unsigned int intc_ex_irq1_mux[] = {
-	IRQ1_MARK,
-};
-static const unsigned int intc_ex_irq2_pins[] = {
-	/* IRQ2 */
-	RCAR_GP_PIN(2, 2),
-};
-static const unsigned int intc_ex_irq2_mux[] = {
-	IRQ2_MARK,
-};
-static const unsigned int intc_ex_irq3_pins[] = {
-	/* IRQ3 */
-	RCAR_GP_PIN(2, 3),
-};
-static const unsigned int intc_ex_irq3_mux[] = {
-	IRQ3_MARK,
-};
-static const unsigned int intc_ex_irq4_pins[] = {
-	/* IRQ4 */
-	RCAR_GP_PIN(2, 4),
-};
-static const unsigned int intc_ex_irq4_mux[] = {
-	IRQ4_MARK,
-};
-static const unsigned int intc_ex_irq5_pins[] = {
-	/* IRQ5 */
-	RCAR_GP_PIN(2, 5),
-};
-static const unsigned int intc_ex_irq5_mux[] = {
-	IRQ5_MARK,
-};
-
-/* - MSIOF0 ----------------------------------------------------------------- */
-static const unsigned int msiof0_clk_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(5, 17),
-};
-static const unsigned int msiof0_clk_mux[] = {
-	MSIOF0_SCK_MARK,
-};
-static const unsigned int msiof0_sync_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(5, 18),
-};
-static const unsigned int msiof0_sync_mux[] = {
-	MSIOF0_SYNC_MARK,
-};
-static const unsigned int msiof0_ss1_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(5, 19),
-};
-static const unsigned int msiof0_ss1_mux[] = {
-	MSIOF0_SS1_MARK,
-};
-static const unsigned int msiof0_ss2_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(5, 21),
-};
-static const unsigned int msiof0_ss2_mux[] = {
-	MSIOF0_SS2_MARK,
-};
-static const unsigned int msiof0_txd_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(5, 20),
-};
-static const unsigned int msiof0_txd_mux[] = {
-	MSIOF0_TXD_MARK,
-};
-static const unsigned int msiof0_rxd_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(5, 22),
-};
-static const unsigned int msiof0_rxd_mux[] = {
-	MSIOF0_RXD_MARK,
-};
-/* - MSIOF1 ----------------------------------------------------------------- */
-static const unsigned int msiof1_clk_a_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(6, 8),
-};
-static const unsigned int msiof1_clk_a_mux[] = {
-	MSIOF1_SCK_A_MARK,
-};
-static const unsigned int msiof1_sync_a_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(6, 9),
-};
-static const unsigned int msiof1_sync_a_mux[] = {
-	MSIOF1_SYNC_A_MARK,
-};
-static const unsigned int msiof1_ss1_a_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(6, 5),
-};
-static const unsigned int msiof1_ss1_a_mux[] = {
-	MSIOF1_SS1_A_MARK,
-};
-static const unsigned int msiof1_ss2_a_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(6, 6),
-};
-static const unsigned int msiof1_ss2_a_mux[] = {
-	MSIOF1_SS2_A_MARK,
-};
-static const unsigned int msiof1_txd_a_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(6, 7),
-};
-static const unsigned int msiof1_txd_a_mux[] = {
-	MSIOF1_TXD_A_MARK,
-};
-static const unsigned int msiof1_rxd_a_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(6, 10),
-};
-static const unsigned int msiof1_rxd_a_mux[] = {
-	MSIOF1_RXD_A_MARK,
-};
-static const unsigned int msiof1_clk_b_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(5, 9),
-};
-static const unsigned int msiof1_clk_b_mux[] = {
-	MSIOF1_SCK_B_MARK,
-};
-static const unsigned int msiof1_sync_b_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(5, 3),
-};
-static const unsigned int msiof1_sync_b_mux[] = {
-	MSIOF1_SYNC_B_MARK,
-};
-static const unsigned int msiof1_ss1_b_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(5, 4),
-};
-static const unsigned int msiof1_ss1_b_mux[] = {
-	MSIOF1_SS1_B_MARK,
-};
-static const unsigned int msiof1_ss2_b_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(5, 0),
-};
-static const unsigned int msiof1_ss2_b_mux[] = {
-	MSIOF1_SS2_B_MARK,
-};
-static const unsigned int msiof1_txd_b_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(5, 8),
-};
-static const unsigned int msiof1_txd_b_mux[] = {
-	MSIOF1_TXD_B_MARK,
-};
-static const unsigned int msiof1_rxd_b_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(5, 7),
-};
-static const unsigned int msiof1_rxd_b_mux[] = {
-	MSIOF1_RXD_B_MARK,
-};
-static const unsigned int msiof1_clk_c_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(6, 17),
-};
-static const unsigned int msiof1_clk_c_mux[] = {
-	MSIOF1_SCK_C_MARK,
-};
-static const unsigned int msiof1_sync_c_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(6, 18),
-};
-static const unsigned int msiof1_sync_c_mux[] = {
-	MSIOF1_SYNC_C_MARK,
-};
-static const unsigned int msiof1_ss1_c_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(6, 21),
-};
-static const unsigned int msiof1_ss1_c_mux[] = {
-	MSIOF1_SS1_C_MARK,
-};
-static const unsigned int msiof1_ss2_c_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(6, 27),
-};
-static const unsigned int msiof1_ss2_c_mux[] = {
-	MSIOF1_SS2_C_MARK,
-};
-static const unsigned int msiof1_txd_c_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(6, 20),
-};
-static const unsigned int msiof1_txd_c_mux[] = {
-	MSIOF1_TXD_C_MARK,
-};
-static const unsigned int msiof1_rxd_c_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(6, 19),
-};
-static const unsigned int msiof1_rxd_c_mux[] = {
-	MSIOF1_RXD_C_MARK,
-};
-static const unsigned int msiof1_clk_d_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(5, 12),
-};
-static const unsigned int msiof1_clk_d_mux[] = {
-	MSIOF1_SCK_D_MARK,
-};
-static const unsigned int msiof1_sync_d_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(5, 15),
-};
-static const unsigned int msiof1_sync_d_mux[] = {
-	MSIOF1_SYNC_D_MARK,
-};
-static const unsigned int msiof1_ss1_d_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(5, 16),
-};
-static const unsigned int msiof1_ss1_d_mux[] = {
-	MSIOF1_SS1_D_MARK,
-};
-static const unsigned int msiof1_ss2_d_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(5, 21),
-};
-static const unsigned int msiof1_ss2_d_mux[] = {
-	MSIOF1_SS2_D_MARK,
-};
-static const unsigned int msiof1_txd_d_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(5, 14),
-};
-static const unsigned int msiof1_txd_d_mux[] = {
-	MSIOF1_TXD_D_MARK,
-};
-static const unsigned int msiof1_rxd_d_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(5, 13),
-};
-static const unsigned int msiof1_rxd_d_mux[] = {
-	MSIOF1_RXD_D_MARK,
-};
-static const unsigned int msiof1_clk_e_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(3, 0),
-};
-static const unsigned int msiof1_clk_e_mux[] = {
-	MSIOF1_SCK_E_MARK,
-};
-static const unsigned int msiof1_sync_e_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(3, 1),
-};
-static const unsigned int msiof1_sync_e_mux[] = {
-	MSIOF1_SYNC_E_MARK,
-};
-static const unsigned int msiof1_ss1_e_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(3, 4),
-};
-static const unsigned int msiof1_ss1_e_mux[] = {
-	MSIOF1_SS1_E_MARK,
-};
-static const unsigned int msiof1_ss2_e_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(3, 5),
-};
-static const unsigned int msiof1_ss2_e_mux[] = {
-	MSIOF1_SS2_E_MARK,
-};
-static const unsigned int msiof1_txd_e_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(3, 3),
-};
-static const unsigned int msiof1_txd_e_mux[] = {
-	MSIOF1_TXD_E_MARK,
-};
-static const unsigned int msiof1_rxd_e_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(3, 2),
-};
-static const unsigned int msiof1_rxd_e_mux[] = {
-	MSIOF1_RXD_E_MARK,
-};
-static const unsigned int msiof1_clk_f_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(5, 23),
-};
-static const unsigned int msiof1_clk_f_mux[] = {
-	MSIOF1_SCK_F_MARK,
-};
-static const unsigned int msiof1_sync_f_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(5, 24),
-};
-static const unsigned int msiof1_sync_f_mux[] = {
-	MSIOF1_SYNC_F_MARK,
-};
-static const unsigned int msiof1_ss1_f_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(6, 1),
-};
-static const unsigned int msiof1_ss1_f_mux[] = {
-	MSIOF1_SS1_F_MARK,
-};
-static const unsigned int msiof1_ss2_f_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(6, 2),
-};
-static const unsigned int msiof1_ss2_f_mux[] = {
-	MSIOF1_SS2_F_MARK,
-};
-static const unsigned int msiof1_txd_f_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(6, 0),
-};
-static const unsigned int msiof1_txd_f_mux[] = {
-	MSIOF1_TXD_F_MARK,
-};
-static const unsigned int msiof1_rxd_f_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(5, 25),
-};
-static const unsigned int msiof1_rxd_f_mux[] = {
-	MSIOF1_RXD_F_MARK,
-};
-static const unsigned int msiof1_clk_g_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(3, 6),
-};
-static const unsigned int msiof1_clk_g_mux[] = {
-	MSIOF1_SCK_G_MARK,
-};
-static const unsigned int msiof1_sync_g_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(3, 7),
-};
-static const unsigned int msiof1_sync_g_mux[] = {
-	MSIOF1_SYNC_G_MARK,
-};
-static const unsigned int msiof1_ss1_g_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(3, 10),
-};
-static const unsigned int msiof1_ss1_g_mux[] = {
-	MSIOF1_SS1_G_MARK,
-};
-static const unsigned int msiof1_ss2_g_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(3, 11),
-};
-static const unsigned int msiof1_ss2_g_mux[] = {
-	MSIOF1_SS2_G_MARK,
-};
-static const unsigned int msiof1_txd_g_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(3, 9),
-};
-static const unsigned int msiof1_txd_g_mux[] = {
-	MSIOF1_TXD_G_MARK,
-};
-static const unsigned int msiof1_rxd_g_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(3, 8),
-};
-static const unsigned int msiof1_rxd_g_mux[] = {
-	MSIOF1_RXD_G_MARK,
-};
-/* - MSIOF2 ----------------------------------------------------------------- */
-static const unsigned int msiof2_clk_a_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(1, 9),
-};
-static const unsigned int msiof2_clk_a_mux[] = {
-	MSIOF2_SCK_A_MARK,
-};
-static const unsigned int msiof2_sync_a_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(1, 8),
-};
-static const unsigned int msiof2_sync_a_mux[] = {
-	MSIOF2_SYNC_A_MARK,
-};
-static const unsigned int msiof2_ss1_a_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(1, 6),
-};
-static const unsigned int msiof2_ss1_a_mux[] = {
-	MSIOF2_SS1_A_MARK,
-};
-static const unsigned int msiof2_ss2_a_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(1, 7),
-};
-static const unsigned int msiof2_ss2_a_mux[] = {
-	MSIOF2_SS2_A_MARK,
-};
-static const unsigned int msiof2_txd_a_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(1, 11),
-};
-static const unsigned int msiof2_txd_a_mux[] = {
-	MSIOF2_TXD_A_MARK,
-};
-static const unsigned int msiof2_rxd_a_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(1, 10),
-};
-static const unsigned int msiof2_rxd_a_mux[] = {
-	MSIOF2_RXD_A_MARK,
-};
-static const unsigned int msiof2_clk_b_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(0, 4),
-};
-static const unsigned int msiof2_clk_b_mux[] = {
-	MSIOF2_SCK_B_MARK,
-};
-static const unsigned int msiof2_sync_b_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(0, 5),
-};
-static const unsigned int msiof2_sync_b_mux[] = {
-	MSIOF2_SYNC_B_MARK,
-};
-static const unsigned int msiof2_ss1_b_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(0, 0),
-};
-static const unsigned int msiof2_ss1_b_mux[] = {
-	MSIOF2_SS1_B_MARK,
-};
-static const unsigned int msiof2_ss2_b_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(0, 1),
-};
-static const unsigned int msiof2_ss2_b_mux[] = {
-	MSIOF2_SS2_B_MARK,
-};
-static const unsigned int msiof2_txd_b_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(0, 7),
-};
-static const unsigned int msiof2_txd_b_mux[] = {
-	MSIOF2_TXD_B_MARK,
-};
-static const unsigned int msiof2_rxd_b_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(0, 6),
-};
-static const unsigned int msiof2_rxd_b_mux[] = {
-	MSIOF2_RXD_B_MARK,
-};
-static const unsigned int msiof2_clk_c_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(2, 12),
-};
-static const unsigned int msiof2_clk_c_mux[] = {
-	MSIOF2_SCK_C_MARK,
-};
-static const unsigned int msiof2_sync_c_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(2, 11),
-};
-static const unsigned int msiof2_sync_c_mux[] = {
-	MSIOF2_SYNC_C_MARK,
-};
-static const unsigned int msiof2_ss1_c_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(2, 10),
-};
-static const unsigned int msiof2_ss1_c_mux[] = {
-	MSIOF2_SS1_C_MARK,
-};
-static const unsigned int msiof2_ss2_c_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(2, 9),
-};
-static const unsigned int msiof2_ss2_c_mux[] = {
-	MSIOF2_SS2_C_MARK,
-};
-static const unsigned int msiof2_txd_c_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(2, 14),
-};
-static const unsigned int msiof2_txd_c_mux[] = {
-	MSIOF2_TXD_C_MARK,
-};
-static const unsigned int msiof2_rxd_c_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(2, 13),
-};
-static const unsigned int msiof2_rxd_c_mux[] = {
-	MSIOF2_RXD_C_MARK,
-};
-static const unsigned int msiof2_clk_d_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(0, 8),
-};
-static const unsigned int msiof2_clk_d_mux[] = {
-	MSIOF2_SCK_D_MARK,
-};
-static const unsigned int msiof2_sync_d_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(0, 9),
-};
-static const unsigned int msiof2_sync_d_mux[] = {
-	MSIOF2_SYNC_D_MARK,
-};
-static const unsigned int msiof2_ss1_d_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(0, 12),
-};
-static const unsigned int msiof2_ss1_d_mux[] = {
-	MSIOF2_SS1_D_MARK,
-};
-static const unsigned int msiof2_ss2_d_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(0, 13),
-};
-static const unsigned int msiof2_ss2_d_mux[] = {
-	MSIOF2_SS2_D_MARK,
-};
-static const unsigned int msiof2_txd_d_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(0, 11),
-};
-static const unsigned int msiof2_txd_d_mux[] = {
-	MSIOF2_TXD_D_MARK,
-};
-static const unsigned int msiof2_rxd_d_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(0, 10),
-};
-static const unsigned int msiof2_rxd_d_mux[] = {
-	MSIOF2_RXD_D_MARK,
-};
-/* - MSIOF3 ----------------------------------------------------------------- */
-static const unsigned int msiof3_clk_a_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(0, 0),
-};
-static const unsigned int msiof3_clk_a_mux[] = {
-	MSIOF3_SCK_A_MARK,
-};
-static const unsigned int msiof3_sync_a_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(0, 1),
-};
-static const unsigned int msiof3_sync_a_mux[] = {
-	MSIOF3_SYNC_A_MARK,
-};
-static const unsigned int msiof3_ss1_a_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(0, 14),
-};
-static const unsigned int msiof3_ss1_a_mux[] = {
-	MSIOF3_SS1_A_MARK,
-};
-static const unsigned int msiof3_ss2_a_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(0, 15),
-};
-static const unsigned int msiof3_ss2_a_mux[] = {
-	MSIOF3_SS2_A_MARK,
-};
-static const unsigned int msiof3_txd_a_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(0, 3),
-};
-static const unsigned int msiof3_txd_a_mux[] = {
-	MSIOF3_TXD_A_MARK,
-};
-static const unsigned int msiof3_rxd_a_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(0, 2),
-};
-static const unsigned int msiof3_rxd_a_mux[] = {
-	MSIOF3_RXD_A_MARK,
-};
-static const unsigned int msiof3_clk_b_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(1, 2),
-};
-static const unsigned int msiof3_clk_b_mux[] = {
-	MSIOF3_SCK_B_MARK,
-};
-static const unsigned int msiof3_sync_b_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(1, 0),
-};
-static const unsigned int msiof3_sync_b_mux[] = {
-	MSIOF3_SYNC_B_MARK,
-};
-static const unsigned int msiof3_ss1_b_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(1, 4),
-};
-static const unsigned int msiof3_ss1_b_mux[] = {
-	MSIOF3_SS1_B_MARK,
-};
-static const unsigned int msiof3_ss2_b_pins[] = {
-	/* SS2 */
-	RCAR_GP_PIN(1, 5),
-};
-static const unsigned int msiof3_ss2_b_mux[] = {
-	MSIOF3_SS2_B_MARK,
-};
-static const unsigned int msiof3_txd_b_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(1, 1),
-};
-static const unsigned int msiof3_txd_b_mux[] = {
-	MSIOF3_TXD_B_MARK,
-};
-static const unsigned int msiof3_rxd_b_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(1, 3),
-};
-static const unsigned int msiof3_rxd_b_mux[] = {
-	MSIOF3_RXD_B_MARK,
-};
-static const unsigned int msiof3_clk_c_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(1, 12),
-};
-static const unsigned int msiof3_clk_c_mux[] = {
-	MSIOF3_SCK_C_MARK,
-};
-static const unsigned int msiof3_sync_c_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(1, 13),
-};
-static const unsigned int msiof3_sync_c_mux[] = {
-	MSIOF3_SYNC_C_MARK,
-};
-static const unsigned int msiof3_txd_c_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(1, 15),
-};
-static const unsigned int msiof3_txd_c_mux[] = {
-	MSIOF3_TXD_C_MARK,
-};
-static const unsigned int msiof3_rxd_c_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(1, 14),
-};
-static const unsigned int msiof3_rxd_c_mux[] = {
-	MSIOF3_RXD_C_MARK,
-};
-static const unsigned int msiof3_clk_d_pins[] = {
-	/* SCK */
-	RCAR_GP_PIN(1, 22),
-};
-static const unsigned int msiof3_clk_d_mux[] = {
-	MSIOF3_SCK_D_MARK,
-};
-static const unsigned int msiof3_sync_d_pins[] = {
-	/* SYNC */
-	RCAR_GP_PIN(1, 23),
-};
-static const unsigned int msiof3_sync_d_mux[] = {
-	MSIOF3_SYNC_D_MARK,
-};
-static const unsigned int msiof3_ss1_d_pins[] = {
-	/* SS1 */
-	RCAR_GP_PIN(1, 26),
-};
-static const unsigned int msiof3_ss1_d_mux[] = {
-	MSIOF3_SS1_D_MARK,
-};
-static const unsigned int msiof3_txd_d_pins[] = {
-	/* TXD */
-	RCAR_GP_PIN(1, 25),
-};
-static const unsigned int msiof3_txd_d_mux[] = {
-	MSIOF3_TXD_D_MARK,
-};
-static const unsigned int msiof3_rxd_d_pins[] = {
-	/* RXD */
-	RCAR_GP_PIN(1, 24),
-};
-static const unsigned int msiof3_rxd_d_mux[] = {
-	MSIOF3_RXD_D_MARK,
-};
-
-/* - PWM0 --------------------------------------------------------------------*/
-static const unsigned int pwm0_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 6),
-};
-static const unsigned int pwm0_mux[] = {
-	PWM0_MARK,
-};
-/* - PWM1 --------------------------------------------------------------------*/
-static const unsigned int pwm1_a_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 7),
-};
-static const unsigned int pwm1_a_mux[] = {
-	PWM1_A_MARK,
-};
-static const unsigned int pwm1_b_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(1, 8),
-};
-static const unsigned int pwm1_b_mux[] = {
-	PWM1_B_MARK,
-};
-/* - PWM2 --------------------------------------------------------------------*/
-static const unsigned int pwm2_a_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 8),
-};
-static const unsigned int pwm2_a_mux[] = {
-	PWM2_A_MARK,
-};
-static const unsigned int pwm2_b_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(1, 11),
-};
-static const unsigned int pwm2_b_mux[] = {
-	PWM2_B_MARK,
-};
-/* - PWM3 --------------------------------------------------------------------*/
-static const unsigned int pwm3_a_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(1, 0),
-};
-static const unsigned int pwm3_a_mux[] = {
-	PWM3_A_MARK,
-};
-static const unsigned int pwm3_b_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 2),
-};
-static const unsigned int pwm3_b_mux[] = {
-	PWM3_B_MARK,
-};
-/* - PWM4 --------------------------------------------------------------------*/
-static const unsigned int pwm4_a_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(1, 1),
-};
-static const unsigned int pwm4_a_mux[] = {
-	PWM4_A_MARK,
-};
-static const unsigned int pwm4_b_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 3),
-};
-static const unsigned int pwm4_b_mux[] = {
-	PWM4_B_MARK,
-};
-/* - PWM5 --------------------------------------------------------------------*/
-static const unsigned int pwm5_a_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(1, 2),
-};
-static const unsigned int pwm5_a_mux[] = {
-	PWM5_A_MARK,
-};
-static const unsigned int pwm5_b_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 4),
-};
-static const unsigned int pwm5_b_mux[] = {
-	PWM5_B_MARK,
-};
-/* - PWM6 --------------------------------------------------------------------*/
-static const unsigned int pwm6_a_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(1, 3),
-};
-static const unsigned int pwm6_a_mux[] = {
-	PWM6_A_MARK,
-};
-static const unsigned int pwm6_b_pins[] = {
-	/* PWM */
-	RCAR_GP_PIN(2, 5),
-};
-static const unsigned int pwm6_b_mux[] = {
-	PWM6_B_MARK,
-};
-
-/* - SATA --------------------------------------------------------------------*/
-static const unsigned int sata0_devslp_a_pins[] = {
-	/* DEVSLP */
-	RCAR_GP_PIN(6, 16),
-};
-static const unsigned int sata0_devslp_a_mux[] = {
-	SATA_DEVSLP_A_MARK,
-};
-static const unsigned int sata0_devslp_b_pins[] = {
-	/* DEVSLP */
-	RCAR_GP_PIN(4, 6),
-};
-static const unsigned int sata0_devslp_b_mux[] = {
-	SATA_DEVSLP_B_MARK,
-};
-
 /* - SCIF0 ------------------------------------------------------------------ */
 static const unsigned int scif0_data_pins[] = {
 	/* RX, TX */
@@ -3285,225 +1744,33 @@ static const unsigned int scif4_ctrl_c_mux[] = {
 	RTS4_N_TANS_C_MARK, CTS4_N_C_MARK,
 };
 /* - SCIF5 ------------------------------------------------------------------ */
-static const unsigned int scif5_data_pins[] = {
+static const unsigned int scif5_data_a_pins[] = {
 	/* RX, TX */
 	RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 21),
 };
-static const unsigned int scif5_data_mux[] = {
-	RX5_MARK, TX5_MARK,
+static const unsigned int scif5_data_a_mux[] = {
+	RX5_A_MARK, TX5_A_MARK,
 };
-static const unsigned int scif5_clk_pins[] = {
+static const unsigned int scif5_clk_a_pins[] = {
 	/* SCK */
 	RCAR_GP_PIN(6, 21),
 };
-static const unsigned int scif5_clk_mux[] = {
-	SCK5_MARK,
-};
-/* - SDHI0 ------------------------------------------------------------------ */
-static const unsigned int sdhi0_data1_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(3, 2),
-};
-static const unsigned int sdhi0_data1_mux[] = {
-	SD0_DAT0_MARK,
-};
-static const unsigned int sdhi0_data4_pins[] = {
-	/* D[0:3] */
-	RCAR_GP_PIN(3, 2), RCAR_GP_PIN(3, 3),
-	RCAR_GP_PIN(3, 4), RCAR_GP_PIN(3, 5),
-};
-static const unsigned int sdhi0_data4_mux[] = {
-	SD0_DAT0_MARK, SD0_DAT1_MARK,
-	SD0_DAT2_MARK, SD0_DAT3_MARK,
-};
-static const unsigned int sdhi0_ctrl_pins[] = {
-	/* CLK, CMD */
-	RCAR_GP_PIN(3, 0), RCAR_GP_PIN(3, 1),
-};
-static const unsigned int sdhi0_ctrl_mux[] = {
-	SD0_CLK_MARK, SD0_CMD_MARK,
-};
-static const unsigned int sdhi0_cd_pins[] = {
-	/* CD */
-	RCAR_GP_PIN(3, 12),
-};
-static const unsigned int sdhi0_cd_mux[] = {
-	SD0_CD_MARK,
-};
-static const unsigned int sdhi0_wp_pins[] = {
-	/* WP */
-	RCAR_GP_PIN(3, 13),
-};
-static const unsigned int sdhi0_wp_mux[] = {
-	SD0_WP_MARK,
-};
-/* - SDHI1 ------------------------------------------------------------------ */
-static const unsigned int sdhi1_data1_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(3, 8),
-};
-static const unsigned int sdhi1_data1_mux[] = {
-	SD1_DAT0_MARK,
-};
-static const unsigned int sdhi1_data4_pins[] = {
-	/* D[0:3] */
-	RCAR_GP_PIN(3, 8),  RCAR_GP_PIN(3, 9),
-	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11),
-};
-static const unsigned int sdhi1_data4_mux[] = {
-	SD1_DAT0_MARK, SD1_DAT1_MARK,
-	SD1_DAT2_MARK, SD1_DAT3_MARK,
-};
-static const unsigned int sdhi1_ctrl_pins[] = {
-	/* CLK, CMD */
-	RCAR_GP_PIN(3, 6), RCAR_GP_PIN(3, 7),
-};
-static const unsigned int sdhi1_ctrl_mux[] = {
-	SD1_CLK_MARK, SD1_CMD_MARK,
-};
-static const unsigned int sdhi1_cd_pins[] = {
-	/* CD */
-	RCAR_GP_PIN(3, 14),
-};
-static const unsigned int sdhi1_cd_mux[] = {
-	SD1_CD_MARK,
-};
-static const unsigned int sdhi1_wp_pins[] = {
-	/* WP */
-	RCAR_GP_PIN(3, 15),
-};
-static const unsigned int sdhi1_wp_mux[] = {
-	SD1_WP_MARK,
-};
-/* - SDHI2 ------------------------------------------------------------------ */
-static const unsigned int sdhi2_data1_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(4, 2),
-};
-static const unsigned int sdhi2_data1_mux[] = {
-	SD2_DAT0_MARK,
-};
-static const unsigned int sdhi2_data4_pins[] = {
-	/* D[0:3] */
-	RCAR_GP_PIN(4, 2), RCAR_GP_PIN(4, 3),
-	RCAR_GP_PIN(4, 4), RCAR_GP_PIN(4, 5),
-};
-static const unsigned int sdhi2_data4_mux[] = {
-	SD2_DAT0_MARK, SD2_DAT1_MARK,
-	SD2_DAT2_MARK, SD2_DAT3_MARK,
-};
-static const unsigned int sdhi2_data8_pins[] = {
-	/* D[0:7] */
-	RCAR_GP_PIN(4, 2),  RCAR_GP_PIN(4, 3),
-	RCAR_GP_PIN(4, 4),  RCAR_GP_PIN(4, 5),
-	RCAR_GP_PIN(3, 8),  RCAR_GP_PIN(3, 9),
-	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11),
-};
-static const unsigned int sdhi2_data8_mux[] = {
-	SD2_DAT0_MARK, SD2_DAT1_MARK,
-	SD2_DAT2_MARK, SD2_DAT3_MARK,
-	SD2_DAT4_MARK, SD2_DAT5_MARK,
-	SD2_DAT6_MARK, SD2_DAT7_MARK,
-};
-static const unsigned int sdhi2_ctrl_pins[] = {
-	/* CLK, CMD */
-	RCAR_GP_PIN(4, 0), RCAR_GP_PIN(4, 1),
-};
-static const unsigned int sdhi2_ctrl_mux[] = {
-	SD2_CLK_MARK, SD2_CMD_MARK,
-};
-static const unsigned int sdhi2_cd_a_pins[] = {
-	/* CD */
-	RCAR_GP_PIN(4, 13),
-};
-static const unsigned int sdhi2_cd_a_mux[] = {
-	SD2_CD_A_MARK,
-};
-static const unsigned int sdhi2_cd_b_pins[] = {
-	/* CD */
-	RCAR_GP_PIN(5, 10),
-};
-static const unsigned int sdhi2_cd_b_mux[] = {
-	SD2_CD_B_MARK,
-};
-static const unsigned int sdhi2_wp_a_pins[] = {
-	/* WP */
-	RCAR_GP_PIN(4, 14),
-};
-static const unsigned int sdhi2_wp_a_mux[] = {
-	SD2_WP_A_MARK,
-};
-static const unsigned int sdhi2_wp_b_pins[] = {
-	/* WP */
-	RCAR_GP_PIN(5, 11),
-};
-static const unsigned int sdhi2_wp_b_mux[] = {
-	SD2_WP_B_MARK,
-};
-static const unsigned int sdhi2_ds_pins[] = {
-	/* DS */
-	RCAR_GP_PIN(4, 6),
-};
-static const unsigned int sdhi2_ds_mux[] = {
-	SD2_DS_MARK,
-};
-/* - SDHI3 ------------------------------------------------------------------ */
-static const unsigned int sdhi3_data1_pins[] = {
-	/* D0 */
-	RCAR_GP_PIN(4, 9),
+static const unsigned int scif5_clk_a_mux[] = {
+	SCK5_A_MARK,
 };
-static const unsigned int sdhi3_data1_mux[] = {
-	SD3_DAT0_MARK,
-};
-static const unsigned int sdhi3_data4_pins[] = {
-	/* D[0:3] */
-	RCAR_GP_PIN(4, 9),  RCAR_GP_PIN(4, 10),
-	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
-};
-static const unsigned int sdhi3_data4_mux[] = {
-	SD3_DAT0_MARK, SD3_DAT1_MARK,
-	SD3_DAT2_MARK, SD3_DAT3_MARK,
-};
-static const unsigned int sdhi3_data8_pins[] = {
-	/* D[0:7] */
-	RCAR_GP_PIN(4, 9),  RCAR_GP_PIN(4, 10),
-	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
-	RCAR_GP_PIN(4, 13), RCAR_GP_PIN(4, 14),
-	RCAR_GP_PIN(4, 15), RCAR_GP_PIN(4, 16),
-};
-static const unsigned int sdhi3_data8_mux[] = {
-	SD3_DAT0_MARK, SD3_DAT1_MARK,
-	SD3_DAT2_MARK, SD3_DAT3_MARK,
-	SD3_DAT4_MARK, SD3_DAT5_MARK,
-	SD3_DAT6_MARK, SD3_DAT7_MARK,
-};
-static const unsigned int sdhi3_ctrl_pins[] = {
-	/* CLK, CMD */
-	RCAR_GP_PIN(4, 7), RCAR_GP_PIN(4, 8),
-};
-static const unsigned int sdhi3_ctrl_mux[] = {
-	SD3_CLK_MARK, SD3_CMD_MARK,
-};
-static const unsigned int sdhi3_cd_pins[] = {
-	/* CD */
-	RCAR_GP_PIN(4, 15),
-};
-static const unsigned int sdhi3_cd_mux[] = {
-	SD3_CD_MARK,
-};
-static const unsigned int sdhi3_wp_pins[] = {
-	/* WP */
-	RCAR_GP_PIN(4, 16),
+static const unsigned int scif5_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 12), RCAR_GP_PIN(5, 18),
 };
-static const unsigned int sdhi3_wp_mux[] = {
-	SD3_WP_MARK,
+static const unsigned int scif5_data_b_mux[] = {
+	RX5_B_MARK, TX5_B_MARK,
 };
-static const unsigned int sdhi3_ds_pins[] = {
-	/* DS */
-	RCAR_GP_PIN(4, 17),
+static const unsigned int scif5_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
 };
-static const unsigned int sdhi3_ds_mux[] = {
-	SD3_DS_MARK,
+static const unsigned int scif5_clk_b_mux[] = {
+	SCK5_B_MARK,
 };
 
 /* - SCIF Clock ------------------------------------------------------------- */
@@ -3522,476 +1789,7 @@ static const unsigned int scif_clk_b_mux[] = {
 	SCIF_CLK_B_MARK,
 };
 
-/* - SSI -------------------------------------------------------------------- */
-static const unsigned int ssi0_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 2),
-};
-static const unsigned int ssi0_data_mux[] = {
-	SSI_SDATA0_MARK,
-};
-static const unsigned int ssi01239_ctrl_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 0), RCAR_GP_PIN(6, 1),
-};
-static const unsigned int ssi01239_ctrl_mux[] = {
-	SSI_SCK01239_MARK, SSI_WS01239_MARK,
-};
-static const unsigned int ssi1_data_a_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 3),
-};
-static const unsigned int ssi1_data_a_mux[] = {
-	SSI_SDATA1_A_MARK,
-};
-static const unsigned int ssi1_data_b_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(5, 12),
-};
-static const unsigned int ssi1_data_b_mux[] = {
-	SSI_SDATA1_B_MARK,
-};
-static const unsigned int ssi1_ctrl_a_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
-};
-static const unsigned int ssi1_ctrl_a_mux[] = {
-	SSI_SCK1_A_MARK, SSI_WS1_A_MARK,
-};
-static const unsigned int ssi1_ctrl_b_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 4), RCAR_GP_PIN(6, 21),
-};
-static const unsigned int ssi1_ctrl_b_mux[] = {
-	SSI_SCK1_B_MARK, SSI_WS1_B_MARK,
-};
-static const unsigned int ssi2_data_a_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 4),
-};
-static const unsigned int ssi2_data_a_mux[] = {
-	SSI_SDATA2_A_MARK,
-};
-static const unsigned int ssi2_data_b_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(5, 13),
-};
-static const unsigned int ssi2_data_b_mux[] = {
-	SSI_SDATA2_B_MARK,
-};
-static const unsigned int ssi2_ctrl_a_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 21),
-};
-static const unsigned int ssi2_ctrl_a_mux[] = {
-	SSI_SCK2_A_MARK, SSI_WS2_A_MARK,
-};
-static const unsigned int ssi2_ctrl_b_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 29),
-};
-static const unsigned int ssi2_ctrl_b_mux[] = {
-	SSI_SCK2_B_MARK, SSI_WS2_B_MARK,
-};
-static const unsigned int ssi3_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 7),
-};
-static const unsigned int ssi3_data_mux[] = {
-	SSI_SDATA3_MARK,
-};
-static const unsigned int ssi34_ctrl_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 5), RCAR_GP_PIN(6, 6),
-};
-static const unsigned int ssi34_ctrl_mux[] = {
-	SSI_SCK34_MARK, SSI_WS34_MARK,
-};
-static const unsigned int ssi4_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 10),
-};
-static const unsigned int ssi4_data_mux[] = {
-	SSI_SDATA4_MARK,
-};
-static const unsigned int ssi4_ctrl_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
-};
-static const unsigned int ssi4_ctrl_mux[] = {
-	SSI_SCK4_MARK, SSI_WS4_MARK,
-};
-static const unsigned int ssi5_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 13),
-};
-static const unsigned int ssi5_data_mux[] = {
-	SSI_SDATA5_MARK,
-};
-static const unsigned int ssi5_ctrl_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 11), RCAR_GP_PIN(6, 12),
-};
-static const unsigned int ssi5_ctrl_mux[] = {
-	SSI_SCK5_MARK, SSI_WS5_MARK,
-};
-static const unsigned int ssi6_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 16),
-};
-static const unsigned int ssi6_data_mux[] = {
-	SSI_SDATA6_MARK,
-};
-static const unsigned int ssi6_ctrl_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15),
-};
-static const unsigned int ssi6_ctrl_mux[] = {
-	SSI_SCK6_MARK, SSI_WS6_MARK,
-};
-static const unsigned int ssi7_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 19),
-};
-static const unsigned int ssi7_data_mux[] = {
-	SSI_SDATA7_MARK,
-};
-static const unsigned int ssi78_ctrl_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
-};
-static const unsigned int ssi78_ctrl_mux[] = {
-	SSI_SCK78_MARK, SSI_WS78_MARK,
-};
-static const unsigned int ssi8_data_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 20),
-};
-static const unsigned int ssi8_data_mux[] = {
-	SSI_SDATA8_MARK,
-};
-static const unsigned int ssi9_data_a_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(6, 21),
-};
-static const unsigned int ssi9_data_a_mux[] = {
-	SSI_SDATA9_A_MARK,
-};
-static const unsigned int ssi9_data_b_pins[] = {
-	/* SDATA */
-	RCAR_GP_PIN(5, 14),
-};
-static const unsigned int ssi9_data_b_mux[] = {
-	SSI_SDATA9_B_MARK,
-};
-static const unsigned int ssi9_ctrl_a_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 16),
-};
-static const unsigned int ssi9_ctrl_a_mux[] = {
-	SSI_SCK9_A_MARK, SSI_WS9_A_MARK,
-};
-static const unsigned int ssi9_ctrl_b_pins[] = {
-	/* SCK, WS */
-	RCAR_GP_PIN(6, 30), RCAR_GP_PIN(6, 31),
-};
-static const unsigned int ssi9_ctrl_b_mux[] = {
-	SSI_SCK9_B_MARK, SSI_WS9_B_MARK,
-};
-
-/* - USB0 ------------------------------------------------------------------- */
-static const unsigned int usb0_pins[] = {
-	/* PWEN, OVC */
-	RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25),
-};
-static const unsigned int usb0_mux[] = {
-	USB0_PWEN_MARK, USB0_OVC_MARK,
-};
-/* - USB1 ------------------------------------------------------------------- */
-static const unsigned int usb1_pins[] = {
-	/* PWEN, OVC */
-	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
-};
-static const unsigned int usb1_mux[] = {
-	USB1_PWEN_MARK, USB1_OVC_MARK,
-};
-/* - USB2 ------------------------------------------------------------------- */
-static const unsigned int usb2_pins[] = {
-	/* PWEN, OVC */
-	RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15),
-};
-static const unsigned int usb2_mux[] = {
-	USB2_PWEN_MARK, USB2_OVC_MARK,
-};
-
-/* - QSPI0 ------------------------------------------------------------------ */
-static const unsigned int qspi0_ctrl_pins[] = {
-	/* QSPI0_SPCLK, QSPI0_SSL */
-	PIN_NUMBER('W', 3), PIN_NUMBER('Y', 3),
-};
-static const unsigned int qspi0_ctrl_mux[] = {
-	QSPI0_SPCLK_MARK, QSPI0_SSL_MARK,
-};
-static const unsigned int qspi0_data2_pins[] = {
-	/* QSPI0_MOSI_IO0, QSPI0_MISO_IO1 */
-	PIN_A_NUMBER('C', 5), PIN_A_NUMBER('B', 4),
-};
-static const unsigned int qspi0_data2_mux[] = {
-	QSPI0_MOSI_IO0_MARK, QSPI0_MISO_IO1_MARK,
-};
-static const unsigned int qspi0_data4_pins[] = {
-	/* QSPI0_MOSI_IO0, QSPI0_MISO_IO1, QSPI0_IO2, QSPI0_IO3 */
-	PIN_A_NUMBER('C', 5), PIN_A_NUMBER('B', 4),
-	PIN_NUMBER('Y', 6), PIN_A_NUMBER('B', 6),
-};
-static const unsigned int qspi0_data4_mux[] = {
-	QSPI0_MOSI_IO0_MARK, QSPI0_MISO_IO1_MARK,
-	QSPI0_IO2_MARK, QSPI0_IO3_MARK,
-};
-/* - QSPI1 ------------------------------------------------------------------ */
-static const unsigned int qspi1_ctrl_pins[] = {
-	/* QSPI1_SPCLK, QSPI1_SSL */
-	PIN_NUMBER('V', 3), PIN_NUMBER('V', 5),
-};
-static const unsigned int qspi1_ctrl_mux[] = {
-	QSPI1_SPCLK_MARK, QSPI1_SSL_MARK,
-};
-static const unsigned int qspi1_data2_pins[] = {
-	/* QSPI1_MOSI_IO0, QSPI1_MISO_IO1 */
-	PIN_A_NUMBER('C', 7), PIN_A_NUMBER('E', 5),
-};
-static const unsigned int qspi1_data2_mux[] = {
-	QSPI1_MOSI_IO0_MARK, QSPI1_MISO_IO1_MARK,
-};
-static const unsigned int qspi1_data4_pins[] = {
-	/* QSPI1_MOSI_IO0, QSPI1_MISO_IO1, QSPI1_IO2, QSPI1_IO3 */
-	PIN_A_NUMBER('C', 7), PIN_A_NUMBER('E', 5),
-	PIN_A_NUMBER('E', 4), PIN_A_NUMBER('C', 3),
-};
-static const unsigned int qspi1_data4_mux[] = {
-	QSPI1_MOSI_IO0_MARK, QSPI1_MISO_IO1_MARK,
-	QSPI1_IO2_MARK, QSPI1_IO3_MARK,
-};
-
 static const struct sh_pfc_pin_group pinmux_groups[] = {
-	SH_PFC_PIN_GROUP(audio_clk_a_a),
-	SH_PFC_PIN_GROUP(audio_clk_a_b),
-	SH_PFC_PIN_GROUP(audio_clk_a_c),
-	SH_PFC_PIN_GROUP(audio_clk_b_a),
-	SH_PFC_PIN_GROUP(audio_clk_b_b),
-	SH_PFC_PIN_GROUP(audio_clk_c_a),
-	SH_PFC_PIN_GROUP(audio_clk_c_b),
-	SH_PFC_PIN_GROUP(audio_clkout_a),
-	SH_PFC_PIN_GROUP(audio_clkout_b),
-	SH_PFC_PIN_GROUP(audio_clkout_c),
-	SH_PFC_PIN_GROUP(audio_clkout_d),
-	SH_PFC_PIN_GROUP(audio_clkout1_a),
-	SH_PFC_PIN_GROUP(audio_clkout1_b),
-	SH_PFC_PIN_GROUP(audio_clkout2_a),
-	SH_PFC_PIN_GROUP(audio_clkout2_b),
-	SH_PFC_PIN_GROUP(audio_clkout3_a),
-	SH_PFC_PIN_GROUP(audio_clkout3_b),
-	SH_PFC_PIN_GROUP(avb_link),
-	SH_PFC_PIN_GROUP(avb_magic),
-	SH_PFC_PIN_GROUP(avb_phy_int),
-	SH_PFC_PIN_GROUP(avb_mdc),
-	SH_PFC_PIN_GROUP(avb_mii),
-	SH_PFC_PIN_GROUP(avb_avtp_pps),
-	SH_PFC_PIN_GROUP(avb_avtp_match_a),
-	SH_PFC_PIN_GROUP(avb_avtp_capture_a),
-	SH_PFC_PIN_GROUP(avb_avtp_match_b),
-	SH_PFC_PIN_GROUP(avb_avtp_capture_b),
-	SH_PFC_PIN_GROUP(can0_data_a),
-	SH_PFC_PIN_GROUP(can0_data_b),
-	SH_PFC_PIN_GROUP(can1_data),
-	SH_PFC_PIN_GROUP(can_clk),
-	SH_PFC_PIN_GROUP(canfd0_data_a),
-	SH_PFC_PIN_GROUP(canfd0_data_b),
-	SH_PFC_PIN_GROUP(canfd1_data),
-	SH_PFC_PIN_GROUP(drif0_ctrl_a),
-	SH_PFC_PIN_GROUP(drif0_data0_a),
-	SH_PFC_PIN_GROUP(drif0_data1_a),
-	SH_PFC_PIN_GROUP(drif0_ctrl_b),
-	SH_PFC_PIN_GROUP(drif0_data0_b),
-	SH_PFC_PIN_GROUP(drif0_data1_b),
-	SH_PFC_PIN_GROUP(drif0_ctrl_c),
-	SH_PFC_PIN_GROUP(drif0_data0_c),
-	SH_PFC_PIN_GROUP(drif0_data1_c),
-	SH_PFC_PIN_GROUP(drif1_ctrl_a),
-	SH_PFC_PIN_GROUP(drif1_data0_a),
-	SH_PFC_PIN_GROUP(drif1_data1_a),
-	SH_PFC_PIN_GROUP(drif1_ctrl_b),
-	SH_PFC_PIN_GROUP(drif1_data0_b),
-	SH_PFC_PIN_GROUP(drif1_data1_b),
-	SH_PFC_PIN_GROUP(drif1_ctrl_c),
-	SH_PFC_PIN_GROUP(drif1_data0_c),
-	SH_PFC_PIN_GROUP(drif1_data1_c),
-	SH_PFC_PIN_GROUP(drif2_ctrl_a),
-	SH_PFC_PIN_GROUP(drif2_data0_a),
-	SH_PFC_PIN_GROUP(drif2_data1_a),
-	SH_PFC_PIN_GROUP(drif2_ctrl_b),
-	SH_PFC_PIN_GROUP(drif2_data0_b),
-	SH_PFC_PIN_GROUP(drif2_data1_b),
-	SH_PFC_PIN_GROUP(drif3_ctrl_a),
-	SH_PFC_PIN_GROUP(drif3_data0_a),
-	SH_PFC_PIN_GROUP(drif3_data1_a),
-	SH_PFC_PIN_GROUP(drif3_ctrl_b),
-	SH_PFC_PIN_GROUP(drif3_data0_b),
-	SH_PFC_PIN_GROUP(drif3_data1_b),
-	SH_PFC_PIN_GROUP(du_rgb666),
-	SH_PFC_PIN_GROUP(du_rgb888),
-	SH_PFC_PIN_GROUP(du_clk_out_0),
-	SH_PFC_PIN_GROUP(du_clk_out_1),
-	SH_PFC_PIN_GROUP(du_sync),
-	SH_PFC_PIN_GROUP(du_oddf),
-	SH_PFC_PIN_GROUP(du_cde),
-	SH_PFC_PIN_GROUP(du_disp),
-	SH_PFC_PIN_GROUP(hscif0_data),
-	SH_PFC_PIN_GROUP(hscif0_clk),
-	SH_PFC_PIN_GROUP(hscif0_ctrl),
-	SH_PFC_PIN_GROUP(hscif1_data_a),
-	SH_PFC_PIN_GROUP(hscif1_clk_a),
-	SH_PFC_PIN_GROUP(hscif1_ctrl_a),
-	SH_PFC_PIN_GROUP(hscif1_data_b),
-	SH_PFC_PIN_GROUP(hscif1_clk_b),
-	SH_PFC_PIN_GROUP(hscif1_ctrl_b),
-	SH_PFC_PIN_GROUP(hscif2_data_a),
-	SH_PFC_PIN_GROUP(hscif2_clk_a),
-	SH_PFC_PIN_GROUP(hscif2_ctrl_a),
-	SH_PFC_PIN_GROUP(hscif2_data_b),
-	SH_PFC_PIN_GROUP(hscif2_clk_b),
-	SH_PFC_PIN_GROUP(hscif2_ctrl_b),
-	SH_PFC_PIN_GROUP(hscif3_data_a),
-	SH_PFC_PIN_GROUP(hscif3_clk),
-	SH_PFC_PIN_GROUP(hscif3_ctrl),
-	SH_PFC_PIN_GROUP(hscif3_data_b),
-	SH_PFC_PIN_GROUP(hscif3_data_c),
-	SH_PFC_PIN_GROUP(hscif3_data_d),
-	SH_PFC_PIN_GROUP(hscif4_data_a),
-	SH_PFC_PIN_GROUP(hscif4_clk),
-	SH_PFC_PIN_GROUP(hscif4_ctrl),
-	SH_PFC_PIN_GROUP(hscif4_data_b),
-	SH_PFC_PIN_GROUP(i2c1_a),
-	SH_PFC_PIN_GROUP(i2c1_b),
-	SH_PFC_PIN_GROUP(i2c2_a),
-	SH_PFC_PIN_GROUP(i2c2_b),
-	SH_PFC_PIN_GROUP(i2c6_a),
-	SH_PFC_PIN_GROUP(i2c6_b),
-	SH_PFC_PIN_GROUP(i2c6_c),
-	SH_PFC_PIN_GROUP(intc_ex_irq0),
-	SH_PFC_PIN_GROUP(intc_ex_irq1),
-	SH_PFC_PIN_GROUP(intc_ex_irq2),
-	SH_PFC_PIN_GROUP(intc_ex_irq3),
-	SH_PFC_PIN_GROUP(intc_ex_irq4),
-	SH_PFC_PIN_GROUP(intc_ex_irq5),
-	SH_PFC_PIN_GROUP(msiof0_clk),
-	SH_PFC_PIN_GROUP(msiof0_sync),
-	SH_PFC_PIN_GROUP(msiof0_ss1),
-	SH_PFC_PIN_GROUP(msiof0_ss2),
-	SH_PFC_PIN_GROUP(msiof0_txd),
-	SH_PFC_PIN_GROUP(msiof0_rxd),
-	SH_PFC_PIN_GROUP(msiof1_clk_a),
-	SH_PFC_PIN_GROUP(msiof1_sync_a),
-	SH_PFC_PIN_GROUP(msiof1_ss1_a),
-	SH_PFC_PIN_GROUP(msiof1_ss2_a),
-	SH_PFC_PIN_GROUP(msiof1_txd_a),
-	SH_PFC_PIN_GROUP(msiof1_rxd_a),
-	SH_PFC_PIN_GROUP(msiof1_clk_b),
-	SH_PFC_PIN_GROUP(msiof1_sync_b),
-	SH_PFC_PIN_GROUP(msiof1_ss1_b),
-	SH_PFC_PIN_GROUP(msiof1_ss2_b),
-	SH_PFC_PIN_GROUP(msiof1_txd_b),
-	SH_PFC_PIN_GROUP(msiof1_rxd_b),
-	SH_PFC_PIN_GROUP(msiof1_clk_c),
-	SH_PFC_PIN_GROUP(msiof1_sync_c),
-	SH_PFC_PIN_GROUP(msiof1_ss1_c),
-	SH_PFC_PIN_GROUP(msiof1_ss2_c),
-	SH_PFC_PIN_GROUP(msiof1_txd_c),
-	SH_PFC_PIN_GROUP(msiof1_rxd_c),
-	SH_PFC_PIN_GROUP(msiof1_clk_d),
-	SH_PFC_PIN_GROUP(msiof1_sync_d),
-	SH_PFC_PIN_GROUP(msiof1_ss1_d),
-	SH_PFC_PIN_GROUP(msiof1_ss2_d),
-	SH_PFC_PIN_GROUP(msiof1_txd_d),
-	SH_PFC_PIN_GROUP(msiof1_rxd_d),
-	SH_PFC_PIN_GROUP(msiof1_clk_e),
-	SH_PFC_PIN_GROUP(msiof1_sync_e),
-	SH_PFC_PIN_GROUP(msiof1_ss1_e),
-	SH_PFC_PIN_GROUP(msiof1_ss2_e),
-	SH_PFC_PIN_GROUP(msiof1_txd_e),
-	SH_PFC_PIN_GROUP(msiof1_rxd_e),
-	SH_PFC_PIN_GROUP(msiof1_clk_f),
-	SH_PFC_PIN_GROUP(msiof1_sync_f),
-	SH_PFC_PIN_GROUP(msiof1_ss1_f),
-	SH_PFC_PIN_GROUP(msiof1_ss2_f),
-	SH_PFC_PIN_GROUP(msiof1_txd_f),
-	SH_PFC_PIN_GROUP(msiof1_rxd_f),
-	SH_PFC_PIN_GROUP(msiof1_clk_g),
-	SH_PFC_PIN_GROUP(msiof1_sync_g),
-	SH_PFC_PIN_GROUP(msiof1_ss1_g),
-	SH_PFC_PIN_GROUP(msiof1_ss2_g),
-	SH_PFC_PIN_GROUP(msiof1_txd_g),
-	SH_PFC_PIN_GROUP(msiof1_rxd_g),
-	SH_PFC_PIN_GROUP(msiof2_clk_a),
-	SH_PFC_PIN_GROUP(msiof2_sync_a),
-	SH_PFC_PIN_GROUP(msiof2_ss1_a),
-	SH_PFC_PIN_GROUP(msiof2_ss2_a),
-	SH_PFC_PIN_GROUP(msiof2_txd_a),
-	SH_PFC_PIN_GROUP(msiof2_rxd_a),
-	SH_PFC_PIN_GROUP(msiof2_clk_b),
-	SH_PFC_PIN_GROUP(msiof2_sync_b),
-	SH_PFC_PIN_GROUP(msiof2_ss1_b),
-	SH_PFC_PIN_GROUP(msiof2_ss2_b),
-	SH_PFC_PIN_GROUP(msiof2_txd_b),
-	SH_PFC_PIN_GROUP(msiof2_rxd_b),
-	SH_PFC_PIN_GROUP(msiof2_clk_c),
-	SH_PFC_PIN_GROUP(msiof2_sync_c),
-	SH_PFC_PIN_GROUP(msiof2_ss1_c),
-	SH_PFC_PIN_GROUP(msiof2_ss2_c),
-	SH_PFC_PIN_GROUP(msiof2_txd_c),
-	SH_PFC_PIN_GROUP(msiof2_rxd_c),
-	SH_PFC_PIN_GROUP(msiof2_clk_d),
-	SH_PFC_PIN_GROUP(msiof2_sync_d),
-	SH_PFC_PIN_GROUP(msiof2_ss1_d),
-	SH_PFC_PIN_GROUP(msiof2_ss2_d),
-	SH_PFC_PIN_GROUP(msiof2_txd_d),
-	SH_PFC_PIN_GROUP(msiof2_rxd_d),
-	SH_PFC_PIN_GROUP(msiof3_clk_a),
-	SH_PFC_PIN_GROUP(msiof3_sync_a),
-	SH_PFC_PIN_GROUP(msiof3_ss1_a),
-	SH_PFC_PIN_GROUP(msiof3_ss2_a),
-	SH_PFC_PIN_GROUP(msiof3_txd_a),
-	SH_PFC_PIN_GROUP(msiof3_rxd_a),
-	SH_PFC_PIN_GROUP(msiof3_clk_b),
-	SH_PFC_PIN_GROUP(msiof3_sync_b),
-	SH_PFC_PIN_GROUP(msiof3_ss1_b),
-	SH_PFC_PIN_GROUP(msiof3_ss2_b),
-	SH_PFC_PIN_GROUP(msiof3_txd_b),
-	SH_PFC_PIN_GROUP(msiof3_rxd_b),
-	SH_PFC_PIN_GROUP(msiof3_clk_c),
-	SH_PFC_PIN_GROUP(msiof3_sync_c),
-	SH_PFC_PIN_GROUP(msiof3_txd_c),
-	SH_PFC_PIN_GROUP(msiof3_rxd_c),
-	SH_PFC_PIN_GROUP(msiof3_clk_d),
-	SH_PFC_PIN_GROUP(msiof3_sync_d),
-	SH_PFC_PIN_GROUP(msiof3_ss1_d),
-	SH_PFC_PIN_GROUP(msiof3_txd_d),
-	SH_PFC_PIN_GROUP(msiof3_rxd_d),
-	SH_PFC_PIN_GROUP(pwm0),
-	SH_PFC_PIN_GROUP(pwm1_a),
-	SH_PFC_PIN_GROUP(pwm1_b),
-	SH_PFC_PIN_GROUP(pwm2_a),
-	SH_PFC_PIN_GROUP(pwm2_b),
-	SH_PFC_PIN_GROUP(pwm3_a),
-	SH_PFC_PIN_GROUP(pwm3_b),
-	SH_PFC_PIN_GROUP(pwm4_a),
-	SH_PFC_PIN_GROUP(pwm4_b),
-	SH_PFC_PIN_GROUP(pwm5_a),
-	SH_PFC_PIN_GROUP(pwm5_b),
-	SH_PFC_PIN_GROUP(pwm6_a),
-	SH_PFC_PIN_GROUP(pwm6_b),
-	SH_PFC_PIN_GROUP(sata0_devslp_a),
-	SH_PFC_PIN_GROUP(sata0_devslp_b),
 	SH_PFC_PIN_GROUP(scif0_data),
 	SH_PFC_PIN_GROUP(scif0_clk),
 	SH_PFC_PIN_GROUP(scif0_ctrl),
@@ -4015,387 +1813,12 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(scif4_data_c),
 	SH_PFC_PIN_GROUP(scif4_clk_c),
 	SH_PFC_PIN_GROUP(scif4_ctrl_c),
-	SH_PFC_PIN_GROUP(scif5_data),
-	SH_PFC_PIN_GROUP(scif5_clk),
+	SH_PFC_PIN_GROUP(scif5_data_a),
+	SH_PFC_PIN_GROUP(scif5_clk_a),
+	SH_PFC_PIN_GROUP(scif5_data_b),
+	SH_PFC_PIN_GROUP(scif5_clk_b),
 	SH_PFC_PIN_GROUP(scif_clk_a),
 	SH_PFC_PIN_GROUP(scif_clk_b),
-	SH_PFC_PIN_GROUP(sdhi0_data1),
-	SH_PFC_PIN_GROUP(sdhi0_data4),
-	SH_PFC_PIN_GROUP(sdhi0_ctrl),
-	SH_PFC_PIN_GROUP(sdhi0_cd),
-	SH_PFC_PIN_GROUP(sdhi0_wp),
-	SH_PFC_PIN_GROUP(sdhi1_data1),
-	SH_PFC_PIN_GROUP(sdhi1_data4),
-	SH_PFC_PIN_GROUP(sdhi1_ctrl),
-	SH_PFC_PIN_GROUP(sdhi1_cd),
-	SH_PFC_PIN_GROUP(sdhi1_wp),
-	SH_PFC_PIN_GROUP(sdhi2_data1),
-	SH_PFC_PIN_GROUP(sdhi2_data4),
-	SH_PFC_PIN_GROUP(sdhi2_data8),
-	SH_PFC_PIN_GROUP(sdhi2_ctrl),
-	SH_PFC_PIN_GROUP(sdhi2_cd_a),
-	SH_PFC_PIN_GROUP(sdhi2_wp_a),
-	SH_PFC_PIN_GROUP(sdhi2_cd_b),
-	SH_PFC_PIN_GROUP(sdhi2_wp_b),
-	SH_PFC_PIN_GROUP(sdhi2_ds),
-	SH_PFC_PIN_GROUP(sdhi3_data1),
-	SH_PFC_PIN_GROUP(sdhi3_data4),
-	SH_PFC_PIN_GROUP(sdhi3_data8),
-	SH_PFC_PIN_GROUP(sdhi3_ctrl),
-	SH_PFC_PIN_GROUP(sdhi3_cd),
-	SH_PFC_PIN_GROUP(sdhi3_wp),
-	SH_PFC_PIN_GROUP(sdhi3_ds),
-	SH_PFC_PIN_GROUP(ssi0_data),
-	SH_PFC_PIN_GROUP(ssi01239_ctrl),
-	SH_PFC_PIN_GROUP(ssi1_data_a),
-	SH_PFC_PIN_GROUP(ssi1_data_b),
-	SH_PFC_PIN_GROUP(ssi1_ctrl_a),
-	SH_PFC_PIN_GROUP(ssi1_ctrl_b),
-	SH_PFC_PIN_GROUP(ssi2_data_a),
-	SH_PFC_PIN_GROUP(ssi2_data_b),
-	SH_PFC_PIN_GROUP(ssi2_ctrl_a),
-	SH_PFC_PIN_GROUP(ssi2_ctrl_b),
-	SH_PFC_PIN_GROUP(ssi3_data),
-	SH_PFC_PIN_GROUP(ssi34_ctrl),
-	SH_PFC_PIN_GROUP(ssi4_data),
-	SH_PFC_PIN_GROUP(ssi4_ctrl),
-	SH_PFC_PIN_GROUP(ssi5_data),
-	SH_PFC_PIN_GROUP(ssi5_ctrl),
-	SH_PFC_PIN_GROUP(ssi6_data),
-	SH_PFC_PIN_GROUP(ssi6_ctrl),
-	SH_PFC_PIN_GROUP(ssi7_data),
-	SH_PFC_PIN_GROUP(ssi78_ctrl),
-	SH_PFC_PIN_GROUP(ssi8_data),
-	SH_PFC_PIN_GROUP(ssi9_data_a),
-	SH_PFC_PIN_GROUP(ssi9_data_b),
-	SH_PFC_PIN_GROUP(ssi9_ctrl_a),
-	SH_PFC_PIN_GROUP(ssi9_ctrl_b),
-	SH_PFC_PIN_GROUP(usb0),
-	SH_PFC_PIN_GROUP(usb1),
-	SH_PFC_PIN_GROUP(usb2),
-	SH_PFC_PIN_GROUP(qspi0_ctrl),
-	SH_PFC_PIN_GROUP(qspi0_data2),
-	SH_PFC_PIN_GROUP(qspi0_data4),
-	SH_PFC_PIN_GROUP(qspi1_ctrl),
-	SH_PFC_PIN_GROUP(qspi1_data2),
-	SH_PFC_PIN_GROUP(qspi1_data4),
-};
-
-static const char * const audio_clk_groups[] = {
-	"audio_clk_a_a",
-	"audio_clk_a_b",
-	"audio_clk_a_c",
-	"audio_clk_b_a",
-	"audio_clk_b_b",
-	"audio_clk_c_a",
-	"audio_clk_c_b",
-	"audio_clkout_a",
-	"audio_clkout_b",
-	"audio_clkout_c",
-	"audio_clkout_d",
-	"audio_clkout1_a",
-	"audio_clkout1_b",
-	"audio_clkout2_a",
-	"audio_clkout2_b",
-	"audio_clkout3_a",
-	"audio_clkout3_b",
-};
-
-static const char * const avb_groups[] = {
-	"avb_link",
-	"avb_magic",
-	"avb_phy_int",
-	"avb_mdc",
-	"avb_mii",
-	"avb_avtp_pps",
-	"avb_avtp_match_a",
-	"avb_avtp_capture_a",
-	"avb_avtp_match_b",
-	"avb_avtp_capture_b",
-};
-
-static const char * const can0_groups[] = {
-	"can0_data_a",
-	"can0_data_b",
-};
-
-static const char * const can1_groups[] = {
-	"can1_data",
-};
-
-static const char * const can_clk_groups[] = {
-	"can_clk",
-};
-
-static const char * const canfd0_groups[] = {
-	"canfd0_data_a",
-	"canfd0_data_b",
-};
-
-static const char * const canfd1_groups[] = {
-	"canfd1_data",
-};
-
-static const char * const drif0_groups[] = {
-	"drif0_ctrl_a",
-	"drif0_data0_a",
-	"drif0_data1_a",
-	"drif0_ctrl_b",
-	"drif0_data0_b",
-	"drif0_data1_b",
-	"drif0_ctrl_c",
-	"drif0_data0_c",
-	"drif0_data1_c",
-};
-
-static const char * const drif1_groups[] = {
-	"drif1_ctrl_a",
-	"drif1_data0_a",
-	"drif1_data1_a",
-	"drif1_ctrl_b",
-	"drif1_data0_b",
-	"drif1_data1_b",
-	"drif1_ctrl_c",
-	"drif1_data0_c",
-	"drif1_data1_c",
-};
-
-static const char * const drif2_groups[] = {
-	"drif2_ctrl_a",
-	"drif2_data0_a",
-	"drif2_data1_a",
-	"drif2_ctrl_b",
-	"drif2_data0_b",
-	"drif2_data1_b",
-};
-
-static const char * const drif3_groups[] = {
-	"drif3_ctrl_a",
-	"drif3_data0_a",
-	"drif3_data1_a",
-	"drif3_ctrl_b",
-	"drif3_data0_b",
-	"drif3_data1_b",
-};
-
-static const char * const du_groups[] = {
-	"du_rgb666",
-	"du_rgb888",
-	"du_clk_out_0",
-	"du_clk_out_1",
-	"du_sync",
-	"du_oddf",
-	"du_cde",
-	"du_disp",
-};
-
-static const char * const hscif0_groups[] = {
-	"hscif0_data",
-	"hscif0_clk",
-	"hscif0_ctrl",
-};
-
-static const char * const hscif1_groups[] = {
-	"hscif1_data_a",
-	"hscif1_clk_a",
-	"hscif1_ctrl_a",
-	"hscif1_data_b",
-	"hscif1_clk_b",
-	"hscif1_ctrl_b",
-};
-
-static const char * const hscif2_groups[] = {
-	"hscif2_data_a",
-	"hscif2_clk_a",
-	"hscif2_ctrl_a",
-	"hscif2_data_b",
-	"hscif2_clk_b",
-	"hscif2_ctrl_b",
-};
-
-static const char * const hscif3_groups[] = {
-	"hscif3_data_a",
-	"hscif3_clk",
-	"hscif3_ctrl",
-	"hscif3_data_b",
-	"hscif3_data_c",
-	"hscif3_data_d",
-};
-
-static const char * const hscif4_groups[] = {
-	"hscif4_data_a",
-	"hscif4_clk",
-	"hscif4_ctrl",
-	"hscif4_data_b",
-};
-
-static const char * const i2c1_groups[] = {
-	"i2c1_a",
-	"i2c1_b",
-};
-
-static const char * const i2c2_groups[] = {
-	"i2c2_a",
-	"i2c2_b",
-};
-
-static const char * const i2c6_groups[] = {
-	"i2c6_a",
-	"i2c6_b",
-	"i2c6_c",
-};
-
-static const char * const intc_ex_groups[] = {
-	"intc_ex_irq0",
-	"intc_ex_irq1",
-	"intc_ex_irq2",
-	"intc_ex_irq3",
-	"intc_ex_irq4",
-	"intc_ex_irq5",
-};
-
-static const char * const msiof0_groups[] = {
-	"msiof0_clk",
-	"msiof0_sync",
-	"msiof0_ss1",
-	"msiof0_ss2",
-	"msiof0_txd",
-	"msiof0_rxd",
-};
-
-static const char * const msiof1_groups[] = {
-	"msiof1_clk_a",
-	"msiof1_sync_a",
-	"msiof1_ss1_a",
-	"msiof1_ss2_a",
-	"msiof1_txd_a",
-	"msiof1_rxd_a",
-	"msiof1_clk_b",
-	"msiof1_sync_b",
-	"msiof1_ss1_b",
-	"msiof1_ss2_b",
-	"msiof1_txd_b",
-	"msiof1_rxd_b",
-	"msiof1_clk_c",
-	"msiof1_sync_c",
-	"msiof1_ss1_c",
-	"msiof1_ss2_c",
-	"msiof1_txd_c",
-	"msiof1_rxd_c",
-	"msiof1_clk_d",
-	"msiof1_sync_d",
-	"msiof1_ss1_d",
-	"msiof1_ss2_d",
-	"msiof1_txd_d",
-	"msiof1_rxd_d",
-	"msiof1_clk_e",
-	"msiof1_sync_e",
-	"msiof1_ss1_e",
-	"msiof1_ss2_e",
-	"msiof1_txd_e",
-	"msiof1_rxd_e",
-	"msiof1_clk_f",
-	"msiof1_sync_f",
-	"msiof1_ss1_f",
-	"msiof1_ss2_f",
-	"msiof1_txd_f",
-	"msiof1_rxd_f",
-	"msiof1_clk_g",
-	"msiof1_sync_g",
-	"msiof1_ss1_g",
-	"msiof1_ss2_g",
-	"msiof1_txd_g",
-	"msiof1_rxd_g",
-};
-
-static const char * const msiof2_groups[] = {
-	"msiof2_clk_a",
-	"msiof2_sync_a",
-	"msiof2_ss1_a",
-	"msiof2_ss2_a",
-	"msiof2_txd_a",
-	"msiof2_rxd_a",
-	"msiof2_clk_b",
-	"msiof2_sync_b",
-	"msiof2_ss1_b",
-	"msiof2_ss2_b",
-	"msiof2_txd_b",
-	"msiof2_rxd_b",
-	"msiof2_clk_c",
-	"msiof2_sync_c",
-	"msiof2_ss1_c",
-	"msiof2_ss2_c",
-	"msiof2_txd_c",
-	"msiof2_rxd_c",
-	"msiof2_clk_d",
-	"msiof2_sync_d",
-	"msiof2_ss1_d",
-	"msiof2_ss2_d",
-	"msiof2_txd_d",
-	"msiof2_rxd_d",
-};
-
-static const char * const msiof3_groups[] = {
-	"msiof3_clk_a",
-	"msiof3_sync_a",
-	"msiof3_ss1_a",
-	"msiof3_ss2_a",
-	"msiof3_txd_a",
-	"msiof3_rxd_a",
-	"msiof3_clk_b",
-	"msiof3_sync_b",
-	"msiof3_ss1_b",
-	"msiof3_ss2_b",
-	"msiof3_txd_b",
-	"msiof3_rxd_b",
-	"msiof3_clk_c",
-	"msiof3_sync_c",
-	"msiof3_txd_c",
-	"msiof3_rxd_c",
-	"msiof3_clk_d",
-	"msiof3_sync_d",
-	"msiof3_ss1_d",
-	"msiof3_txd_d",
-	"msiof3_rxd_d",
-};
-
-static const char * const pwm0_groups[] = {
-	"pwm0",
-};
-
-static const char * const pwm1_groups[] = {
-	"pwm1_a",
-	"pwm1_b",
-};
-
-static const char * const pwm2_groups[] = {
-	"pwm2_a",
-	"pwm2_b",
-};
-
-static const char * const pwm3_groups[] = {
-	"pwm3_a",
-	"pwm3_b",
-};
-
-static const char * const pwm4_groups[] = {
-	"pwm4_a",
-	"pwm4_b",
-};
-
-static const char * const pwm5_groups[] = {
-	"pwm5_a",
-	"pwm5_b",
-};
-
-static const char * const pwm6_groups[] = {
-	"pwm6_a",
-	"pwm6_b",
-};
-
-static const char * const sata0_groups[] = {
-	"sata0_devslp_a",
-	"sata0_devslp_b",
 };
 
 static const char * const scif0_groups[] = {
@@ -4437,8 +1860,10 @@ static const char * const scif4_groups[] = {
 };
 
 static const char * const scif5_groups[] = {
-	"scif5_data",
-	"scif5_clk",
+	"scif5_data_a",
+	"scif5_clk_a",
+	"scif5_data_b",
+	"scif5_clk_b",
 };
 
 static const char * const scif_clk_groups[] = {
@@ -4446,130 +1871,7 @@ static const char * const scif_clk_groups[] = {
 	"scif_clk_b",
 };
 
-static const char * const sdhi0_groups[] = {
-	"sdhi0_data1",
-	"sdhi0_data4",
-	"sdhi0_ctrl",
-	"sdhi0_cd",
-	"sdhi0_wp",
-};
-
-static const char * const sdhi1_groups[] = {
-	"sdhi1_data1",
-	"sdhi1_data4",
-	"sdhi1_ctrl",
-	"sdhi1_cd",
-	"sdhi1_wp",
-};
-
-static const char * const sdhi2_groups[] = {
-	"sdhi2_data1",
-	"sdhi2_data4",
-	"sdhi2_data8",
-	"sdhi2_ctrl",
-	"sdhi2_cd_a",
-	"sdhi2_wp_a",
-	"sdhi2_cd_b",
-	"sdhi2_wp_b",
-	"sdhi2_ds",
-};
-
-static const char * const sdhi3_groups[] = {
-	"sdhi3_data1",
-	"sdhi3_data4",
-	"sdhi3_data8",
-	"sdhi3_ctrl",
-	"sdhi3_cd",
-	"sdhi3_wp",
-	"sdhi3_ds",
-};
-
-static const char * const ssi_groups[] = {
-	"ssi0_data",
-	"ssi01239_ctrl",
-	"ssi1_data_a",
-	"ssi1_data_b",
-	"ssi1_ctrl_a",
-	"ssi1_ctrl_b",
-	"ssi2_data_a",
-	"ssi2_data_b",
-	"ssi2_ctrl_a",
-	"ssi2_ctrl_b",
-	"ssi3_data",
-	"ssi34_ctrl",
-	"ssi4_data",
-	"ssi4_ctrl",
-	"ssi5_data",
-	"ssi5_ctrl",
-	"ssi6_data",
-	"ssi6_ctrl",
-	"ssi7_data",
-	"ssi78_ctrl",
-	"ssi8_data",
-	"ssi9_data_a",
-	"ssi9_data_b",
-	"ssi9_ctrl_a",
-	"ssi9_ctrl_b",
-};
-
-static const char * const usb0_groups[] = {
-	"usb0",
-};
-
-static const char * const usb1_groups[] = {
-	"usb1",
-};
-
-static const char * const usb2_groups[] = {
-	"usb2",
-};
-
-static const char * const qspi0_groups[] = {
-	"qspi0_ctrl",
-	"qspi0_data2",
-	"qspi0_data4",
-};
-
-static const char * const qspi1_groups[] = {
-	"qspi1_ctrl",
-	"qspi1_data2",
-	"qspi1_data4",
-};
-
 static const struct sh_pfc_function pinmux_functions[] = {
-	SH_PFC_FUNCTION(audio_clk),
-	SH_PFC_FUNCTION(avb),
-	SH_PFC_FUNCTION(can0),
-	SH_PFC_FUNCTION(can1),
-	SH_PFC_FUNCTION(can_clk),
-	SH_PFC_FUNCTION(canfd0),
-	SH_PFC_FUNCTION(canfd1),
-	SH_PFC_FUNCTION(drif0),
-	SH_PFC_FUNCTION(drif1),
-	SH_PFC_FUNCTION(drif2),
-	SH_PFC_FUNCTION(drif3),
-	SH_PFC_FUNCTION(du),
-	SH_PFC_FUNCTION(hscif0),
-	SH_PFC_FUNCTION(hscif1),
-	SH_PFC_FUNCTION(hscif2),
-	SH_PFC_FUNCTION(hscif3),
-	SH_PFC_FUNCTION(hscif4),
-	SH_PFC_FUNCTION(i2c1),
-	SH_PFC_FUNCTION(i2c2),
-	SH_PFC_FUNCTION(i2c6),
-	SH_PFC_FUNCTION(intc_ex),
-	SH_PFC_FUNCTION(msiof0),
-	SH_PFC_FUNCTION(msiof1),
-	SH_PFC_FUNCTION(msiof2),
-	SH_PFC_FUNCTION(msiof3),
-	SH_PFC_FUNCTION(pwm0),
-	SH_PFC_FUNCTION(pwm1),
-	SH_PFC_FUNCTION(pwm2),
-	SH_PFC_FUNCTION(pwm3),
-	SH_PFC_FUNCTION(pwm4),
-	SH_PFC_FUNCTION(pwm5),
-	SH_PFC_FUNCTION(pwm6),
-	SH_PFC_FUNCTION(sata0),
 	SH_PFC_FUNCTION(scif0),
 	SH_PFC_FUNCTION(scif1),
 	SH_PFC_FUNCTION(scif2),
@@ -4577,16 +1879,6 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(scif4),
 	SH_PFC_FUNCTION(scif5),
 	SH_PFC_FUNCTION(scif_clk),
-	SH_PFC_FUNCTION(sdhi0),
-	SH_PFC_FUNCTION(sdhi1),
-	SH_PFC_FUNCTION(sdhi2),
-	SH_PFC_FUNCTION(sdhi3),
-	SH_PFC_FUNCTION(ssi),
-	SH_PFC_FUNCTION(usb0),
-	SH_PFC_FUNCTION(usb1),
-	SH_PFC_FUNCTION(usb2),
-	SH_PFC_FUNCTION(qspi0),
-	SH_PFC_FUNCTION(qspi1),
 };
 
 static const struct pinmux_cfg_reg pinmux_config_regs[] = {
@@ -5040,46 +2332,54 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		IP16_3_0 }
 	},
 	{ PINMUX_CFG_REG("IPSR17", 0xe6060244, 32, 4) {
-		/* IP17_31_28 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		/* IP17_27_24 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		/* IP17_23_20 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		/* IP17_19_16 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		/* IP17_15_12 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		/* IP17_11_8  */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		IP17_31_28
+		IP17_27_24
+		IP17_23_20
+		IP17_19_16
+		IP17_15_12
+		IP17_11_8
 		IP17_7_4
 		IP17_3_0 }
 	},
+	{ PINMUX_CFG_REG("IPSR18", 0xe6060248, 32, 4) {
+		/* IP18_31_28 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP18_27_24 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP18_23_20 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP18_19_16 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP18_15_12 */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		/* IP18_11_8  */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		IP18_7_4
+		IP18_3_0 }
+	},
 #undef F_
 #undef FM
 
 #define F_(x, y)	x,
 #define FM(x)		FN_##x,
 	{ PINMUX_CFG_REG_VAR("MOD_SEL0", 0xe6060500, 32,
-			     1, 2, 2, 3, 1, 1, 2, 1, 1, 1,
-			     2, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 2, 1) {
-		0, 0, /* RESERVED 31 */
-		MOD_SEL0_30_29
+			     3, 2, 3, 1, 1, 1, 1, 1, 2, 1,
+			     1, 2, 1, 1, 1, 2, 2, 1, 2, 3) {
+		MOD_SEL0_31_30_29
 		MOD_SEL0_28_27
 		MOD_SEL0_26_25_24
 		MOD_SEL0_23
 		MOD_SEL0_22
-		MOD_SEL0_21_20
+		MOD_SEL0_21
+		MOD_SEL0_20
 		MOD_SEL0_19
-		MOD_SEL0_18
-		MOD_SEL0_17
-		MOD_SEL0_16_15
-		MOD_SEL0_14
-		MOD_SEL0_13
+		MOD_SEL0_18_17
+		MOD_SEL0_16
+		0, 0, /* RESERVED 15 */
+		MOD_SEL0_14_13
 		MOD_SEL0_12
 		MOD_SEL0_11
 		MOD_SEL0_10
-		MOD_SEL0_9
-		MOD_SEL0_8
+		MOD_SEL0_9_8
 		MOD_SEL0_7_6
-		MOD_SEL0_5_4
-		MOD_SEL0_3
-		MOD_SEL0_2_1
-		0, 0, /* RESERVED 0 */ }
+		MOD_SEL0_5
+		MOD_SEL0_4_3
+		/* RESERVED 2, 1, 0 */
+		0, 0, 0, 0, 0, 0, 0, 0 }
 	},
 	{ PINMUX_CFG_REG_VAR("MOD_SEL1", 0xe6060504, 32,
 			     2, 3, 1, 2, 3, 1, 1, 2, 1,
@@ -5109,22 +2409,22 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		MOD_SEL1_0 }
 	},
 	{ PINMUX_CFG_REG_VAR("MOD_SEL2", 0xe6060508, 32,
-			     1, 1, 1, 1, 4, 4, 4,
-			     4, 4, 4, 1, 2, 1) {
+			     1, 1, 1, 2, 1, 3, 1, 1, 1, 1, 1, 1, 1,
+			     4, 4, 4, 3, 1) {
 		MOD_SEL2_31
 		MOD_SEL2_30
 		MOD_SEL2_29
-		/* RESERVED 28 */
+		MOD_SEL2_28_27
+		MOD_SEL2_26
+		MOD_SEL2_25_24_23
+		MOD_SEL2_22
+		MOD_SEL2_21
+		MOD_SEL2_20
+		MOD_SEL2_19
+		MOD_SEL2_18
+		MOD_SEL2_17
+		/* RESERVED 16 */
 		0, 0,
-		/* RESERVED 27, 26, 25, 24 */
-		0, 0, 0, 0, 0, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
-		/* RESERVED 23, 22, 21, 20 */
-		0, 0, 0, 0, 0, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
-		/* RESERVED 19, 18, 17, 16 */
-		0, 0, 0, 0, 0, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
 		/* RESERVED 15, 14, 13, 12 */
 		0, 0, 0, 0, 0, 0, 0, 0,
 		0, 0, 0, 0, 0, 0, 0, 0,
@@ -5134,10 +2434,8 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		/* RESERVED 7, 6, 5, 4 */
 		0, 0, 0, 0, 0, 0, 0, 0,
 		0, 0, 0, 0, 0, 0, 0, 0,
-		/* RESERVED 3 */
-		0, 0,
-		/* RESERVED 2, 1 */
-		0, 0, 0, 0,
+		/* RESERVED 3, 2, 1 */
+		0, 0, 0, 0, 0, 0, 0, 0,
 		MOD_SEL2_0 }
 	},
 	{ },
@@ -5386,8 +2684,8 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = {
 		{ RCAR_GP_PIN(6, 27), 20, 3 },	/* USB1_OVC */
 		{ RCAR_GP_PIN(6, 28), 16, 3 },	/* USB30_PWEN */
 		{ RCAR_GP_PIN(6, 29), 12, 3 },	/* USB30_OVC */
-		{ RCAR_GP_PIN(6, 30),  8, 3 },	/* USB31_PWEN */
-		{ RCAR_GP_PIN(6, 31),  4, 3 },	/* USB31_OVC */
+		{ RCAR_GP_PIN(6, 30),  8, 3 },	/* USB3_PWEN */
+		{ RCAR_GP_PIN(6, 31),  4, 3 },	/* USB3_OVC */
 	} },
 	{ },
 };
@@ -5617,8 +2915,8 @@ static const struct sh_pfc_bias_info bias_info[] = {
 	{ RCAR_GP_PIN(5, 21),    PU5,  1 },	/* MSIOF0_SS2 */
 	{ RCAR_GP_PIN(5, 20),    PU5,  0 },	/* MSIOF0_TXD */
 
-	{ RCAR_GP_PIN(6, 31),    PU6,  6 },	/* USB31_OVC */
-	{ RCAR_GP_PIN(6, 30),    PU6,  5 },	/* USB31_PWEN */
+	{ RCAR_GP_PIN(6, 31),    PU6,  6 },	/* USB3_OVC */
+	{ RCAR_GP_PIN(6, 30),    PU6,  5 },	/* USB3_PWEN */
 	{ RCAR_GP_PIN(6, 29),    PU6,  4 },	/* USB30_OVC */
 	{ RCAR_GP_PIN(6, 28),    PU6,  3 },	/* USB30_PWEN */
 	{ RCAR_GP_PIN(6, 27),    PU6,  2 },	/* USB1_OVC */
@@ -5675,14 +2973,28 @@ static void r8a7795_pinmux_set_bias(struct sh_pfc *pfc, unsigned int pin,
 	sh_pfc_write_reg(pfc, PUEN + reg, 32, enable);
 }
 
+static const struct soc_device_attribute r8a7795es1[] = {
+	{ .soc_id = "r8a7795", .revision = "ES1.*" },
+	{ /* sentinel */ }
+};
+
+static int r8a7795_pinmux_init(struct sh_pfc *pfc)
+{
+	if (soc_device_match(r8a7795es1))
+		pfc->info = &r8a7795es1_pinmux_info;
+
+	return 0;
+}
+
 static const struct sh_pfc_soc_operations r8a7795_pinmux_ops = {
+	.init = r8a7795_pinmux_init,
 	.pin_to_pocctrl = r8a7795_pin_to_pocctrl,
 	.get_bias = r8a7795_pinmux_get_bias,
 	.set_bias = r8a7795_pinmux_set_bias,
 };
 
 const struct sh_pfc_soc_info r8a7795_pinmux_info = {
-	.name = "r8a77950_pfc",
+	.name = "r8a77951_pfc",
 	.ops = &r8a7795_pinmux_ops,
 	.unlock_reg = 0xe6060000, /* PMMR */
 
diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c
index 08150a321be6..a70157f0acf4 100644
--- a/drivers/pinctrl/sh-pfc/pinctrl.c
+++ b/drivers/pinctrl/sh-pfc/pinctrl.c
@@ -816,6 +816,13 @@ int sh_pfc_register_pinctrl(struct sh_pfc *pfc)
 	pmx->pctl_desc.pins = pmx->pins;
 	pmx->pctl_desc.npins = pfc->info->nr_pins;
 
-	return devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
-					      &pmx->pctl);
+	ret = devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
+					     &pmx->pctl);
+	if (ret) {
+		dev_err(pfc->dev, "could not register: %i\n", ret);
+
+		return ret;
+	}
+
+	return pinctrl_enable(pmx->pctl);
 }
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index e42cc7a8d10e..f31eb6c1e87d 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -267,6 +267,7 @@ extern const struct sh_pfc_soc_info r8a7792_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7793_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7794_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7795_pinmux_info;
+extern const struct sh_pfc_soc_info r8a7795es1_pinmux_info;
 extern const struct sh_pfc_soc_info r8a7796_pinmux_info;
 extern const struct sh_pfc_soc_info sh7203_pinmux_info;
 extern const struct sh_pfc_soc_info sh7264_pinmux_info;
diff --git a/drivers/pinctrl/sirf/pinctrl-atlas7.c b/drivers/pinctrl/sirf/pinctrl-atlas7.c
index 600d6427a978..1efa315a7dbe 100644
--- a/drivers/pinctrl/sirf/pinctrl-atlas7.c
+++ b/drivers/pinctrl/sirf/pinctrl-atlas7.c
@@ -352,7 +352,7 @@ struct atlas7_gpio_chip {
 	void __iomem *reg;
 	struct clk *clk;
 	int nbank;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct gpio_chip chip;
 	struct atlas7_gpio_bank banks[0];
 };
@@ -5650,13 +5650,13 @@ static void atlas7_gpio_irq_ack(struct irq_data *d)
 	pin_in_bank = d->hwirq - bank->gpio_offset;
 	ctrl_reg = ATLAS7_GPIO_CTRL(bank, pin_in_bank);
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	val = readl(ctrl_reg);
 	/* clear interrupt status */
 	writel(val, ctrl_reg);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 }
 
 static void __atlas7_gpio_irq_mask(struct atlas7_gpio_chip *a7gc, int idx)
@@ -5681,11 +5681,11 @@ static void atlas7_gpio_irq_mask(struct irq_data *d)
 	struct atlas7_gpio_chip *a7gc = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	__atlas7_gpio_irq_mask(a7gc, d->hwirq);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 }
 
 static void atlas7_gpio_irq_unmask(struct irq_data *d)
@@ -5701,14 +5701,14 @@ static void atlas7_gpio_irq_unmask(struct irq_data *d)
 	pin_in_bank = d->hwirq - bank->gpio_offset;
 	ctrl_reg = ATLAS7_GPIO_CTRL(bank, pin_in_bank);
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	val = readl(ctrl_reg);
 	val &= ~ATLAS7_GPIO_CTL_INTR_STATUS_MASK;
 	val |= ATLAS7_GPIO_CTL_INTR_EN_MASK;
 	writel(val, ctrl_reg);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 }
 
 static int atlas7_gpio_irq_type(struct irq_data *d,
@@ -5725,7 +5725,7 @@ static int atlas7_gpio_irq_type(struct irq_data *d,
 	pin_in_bank = d->hwirq - bank->gpio_offset;
 	ctrl_reg = ATLAS7_GPIO_CTRL(bank, pin_in_bank);
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	val = readl(ctrl_reg);
 	val &= ~(ATLAS7_GPIO_CTL_INTR_STATUS_MASK |
@@ -5768,7 +5768,7 @@ static int atlas7_gpio_irq_type(struct irq_data *d,
 
 	writel(val, ctrl_reg);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 
 	return 0;
 }
@@ -5863,7 +5863,7 @@ static int atlas7_gpio_request(struct gpio_chip *chip,
 	if (pinctrl_request_gpio(chip->base + gpio))
 		return -ENODEV;
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	/*
 	 * default status:
@@ -5872,7 +5872,7 @@ static int atlas7_gpio_request(struct gpio_chip *chip,
 	__atlas7_gpio_set_input(a7gc, gpio);
 	__atlas7_gpio_irq_mask(a7gc, gpio);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 
 	return 0;
 }
@@ -5883,12 +5883,12 @@ static void atlas7_gpio_free(struct gpio_chip *chip,
 	struct atlas7_gpio_chip *a7gc = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	__atlas7_gpio_irq_mask(a7gc, gpio);
 	__atlas7_gpio_set_input(a7gc, gpio);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 
 	pinctrl_free_gpio(chip->base + gpio);
 }
@@ -5899,11 +5899,11 @@ static int atlas7_gpio_direction_input(struct gpio_chip *chip,
 	struct atlas7_gpio_chip *a7gc = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	__atlas7_gpio_set_input(a7gc, gpio);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 
 	return 0;
 }
@@ -5936,11 +5936,11 @@ static int atlas7_gpio_direction_output(struct gpio_chip *chip,
 	struct atlas7_gpio_chip *a7gc = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	__atlas7_gpio_set_output(a7gc, gpio, value);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 
 	return 0;
 }
@@ -5956,11 +5956,11 @@ static int atlas7_gpio_get_value(struct gpio_chip *chip,
 	bank = atlas7_gpio_to_bank(a7gc, gpio);
 	pin_in_bank = gpio - bank->gpio_offset;
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	val = readl(ATLAS7_GPIO_CTRL(bank, pin_in_bank));
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 
 	return !!(val & ATLAS7_GPIO_CTL_DATAIN_MASK);
 }
@@ -5978,7 +5978,7 @@ static void atlas7_gpio_set_value(struct gpio_chip *chip,
 	pin_in_bank = gpio - bank->gpio_offset;
 	ctrl_reg = ATLAS7_GPIO_CTRL(bank, pin_in_bank);
 
-	spin_lock_irqsave(&a7gc->lock, flags);
+	raw_spin_lock_irqsave(&a7gc->lock, flags);
 
 	ctrl = readl(ctrl_reg);
 	if (value)
@@ -5987,7 +5987,7 @@ static void atlas7_gpio_set_value(struct gpio_chip *chip,
 		ctrl &= ~ATLAS7_GPIO_CTL_DATAOUT_MASK;
 	writel(ctrl, ctrl_reg);
 
-	spin_unlock_irqrestore(&a7gc->lock, flags);
+	raw_spin_unlock_irqrestore(&a7gc->lock, flags);
 }
 
 static const struct of_device_id atlas7_gpio_ids[] = {
@@ -6036,7 +6036,7 @@ static int atlas7_gpio_probe(struct platform_device *pdev)
 	}
 
 	a7gc->nbank = nbank;
-	spin_lock_init(&a7gc->lock);
+	raw_spin_lock_init(&a7gc->lock);
 
 	/* Setup GPIO Chip */
 	chip = &a7gc->chip;
diff --git a/drivers/pinctrl/stm32/Kconfig b/drivers/pinctrl/stm32/Kconfig
index f5ccabd8535e..3b8026fca057 100644
--- a/drivers/pinctrl/stm32/Kconfig
+++ b/drivers/pinctrl/stm32/Kconfig
@@ -14,6 +14,12 @@ config PINCTRL_STM32F429
 	default MACH_STM32F429
 	select PINCTRL_STM32
 
+config PINCTRL_STM32F469
+	bool "STMicroelectronics STM32F469 pin control" if COMPILE_TEST && !MACH_STM32F469
+	depends on OF && IRQ_DOMAIN_HIERARCHY
+	default MACH_STM32F469
+	select PINCTRL_STM32
+
 config PINCTRL_STM32F746
 	bool "STMicroelectronics STM32F746 pin control" if COMPILE_TEST && !MACH_STM32F746
 	depends on OF && IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/pinctrl/stm32/Makefile b/drivers/pinctrl/stm32/Makefile
index cb31b4d24c44..5f379f5153f1 100644
--- a/drivers/pinctrl/stm32/Makefile
+++ b/drivers/pinctrl/stm32/Makefile
@@ -3,5 +3,6 @@ obj-$(CONFIG_PINCTRL_STM32) += pinctrl-stm32.o
 
 # SoC Drivers
 obj-$(CONFIG_PINCTRL_STM32F429)	+= pinctrl-stm32f429.o
+obj-$(CONFIG_PINCTRL_STM32F469)	+= pinctrl-stm32f469.o
 obj-$(CONFIG_PINCTRL_STM32F746)	+= pinctrl-stm32f746.o
 obj-$(CONFIG_PINCTRL_STM32H743)	+= pinctrl-stm32h743.o
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index abc405be0212..d3c5f5dfbbd7 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -71,6 +71,7 @@ struct stm32_gpio_bank {
 	struct pinctrl_gpio_range range;
 	struct fwnode_handle *fwnode;
 	struct irq_domain *domain;
+	u32 bank_nr;
 };
 
 struct stm32_pinctrl {
@@ -138,6 +139,17 @@ static inline void __stm32_gpio_set(struct stm32_gpio_bank *bank,
 
 static int stm32_gpio_request(struct gpio_chip *chip, unsigned offset)
 {
+	struct stm32_gpio_bank *bank = gpiochip_get_data(chip);
+	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
+	struct pinctrl_gpio_range *range;
+	int pin = offset + (bank->bank_nr * STM32_GPIO_PINS_PER_BANK);
+
+	range = pinctrl_find_gpio_range_from_pin_nolock(pctl->pctl_dev, pin);
+	if (!range) {
+		dev_err(pctl->dev, "pin %d not in range.\n", pin);
+		return -EINVAL;
+	}
+
 	return pinctrl_request_gpio(chip->base + offset);
 }
 
@@ -235,7 +247,7 @@ static void stm32_gpio_domain_activate(struct irq_domain *d,
 	struct stm32_gpio_bank *bank = d->host_data;
 	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
 
-	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->range.id);
+	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr);
 	gpiochip_lock_as_irq(&bank->gpio_chip, irq_data->hwirq);
 }
 
@@ -589,7 +601,7 @@ static int stm32_pmx_set_mux(struct pinctrl_dev *pctldev,
 	}
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, g->pin);
-	bank = gpio_range_to_bank(range);
+	bank = gpiochip_get_data(range->gc);
 	pin = stm32_gpio_pin(g->pin);
 
 	mode = stm32_gpio_get_mode(function);
@@ -604,7 +616,7 @@ static int stm32_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range, unsigned gpio,
 			bool input)
 {
-	struct stm32_gpio_bank *bank = gpio_range_to_bank(range);
+	struct stm32_gpio_bank *bank = gpiochip_get_data(range->gc);
 	int pin = stm32_gpio_pin(gpio);
 
 	stm32_pmx_set_mode(bank, pin, !input, 0);
@@ -762,7 +774,7 @@ static int stm32_pconf_parse_conf(struct pinctrl_dev *pctldev,
 	int offset, ret = 0;
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
-	bank = gpio_range_to_bank(range);
+	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
 	switch (param) {
@@ -843,7 +855,7 @@ static void stm32_pconf_dbg_show(struct pinctrl_dev *pctldev,
 	bool val;
 
 	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
-	bank = gpio_range_to_bank(range);
+	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
 	stm32_pmx_get_mode(bank, offset, &mode, &alt);
@@ -898,13 +910,14 @@ static const struct pinconf_ops stm32_pconf_ops = {
 static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 	struct device_node *np)
 {
-	int bank_nr = pctl->nbanks;
-	struct stm32_gpio_bank *bank = &pctl->banks[bank_nr];
+	struct stm32_gpio_bank *bank = &pctl->banks[pctl->nbanks];
 	struct pinctrl_gpio_range *range = &bank->range;
+	struct of_phandle_args args;
 	struct device *dev = pctl->dev;
 	struct resource res;
 	struct reset_control *rstc;
-	int err, npins;
+	int npins = STM32_GPIO_PINS_PER_BANK;
+	int bank_nr, err;
 
 	rstc = of_reset_control_get(np, NULL);
 	if (!IS_ERR(rstc))
@@ -929,28 +942,33 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 		return err;
 	}
 
-	npins = pctl->match_data->npins;
-	npins -= bank_nr * STM32_GPIO_PINS_PER_BANK;
-	if (npins < 0)
-		return -EINVAL;
-	else if (npins > STM32_GPIO_PINS_PER_BANK)
-		npins = STM32_GPIO_PINS_PER_BANK;
-
 	bank->gpio_chip = stm32_gpio_template;
+
+	of_property_read_string(np, "st,bank-name", &bank->gpio_chip.label);
+
+	if (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args)) {
+		bank_nr = args.args[1] / STM32_GPIO_PINS_PER_BANK;
+		bank->gpio_chip.base = args.args[1];
+	} else {
+		bank_nr = pctl->nbanks;
+		bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
+		range->name = bank->gpio_chip.label;
+		range->id = bank_nr;
+		range->pin_base = range->id * STM32_GPIO_PINS_PER_BANK;
+		range->base = range->id * STM32_GPIO_PINS_PER_BANK;
+		range->npins = npins;
+		range->gc = &bank->gpio_chip;
+		pinctrl_add_gpio_range(pctl->pctl_dev,
+				       &pctl->banks[bank_nr].range);
+	}
 	bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
+
 	bank->gpio_chip.ngpio = npins;
 	bank->gpio_chip.of_node = np;
 	bank->gpio_chip.parent = dev;
+	bank->bank_nr = bank_nr;
 	spin_lock_init(&bank->lock);
 
-	of_property_read_string(np, "st,bank-name", &range->name);
-	bank->gpio_chip.label = range->name;
-
-	range->id = bank_nr;
-	range->pin_base = range->base = range->id * STM32_GPIO_PINS_PER_BANK;
-	range->npins = bank->gpio_chip.ngpio;
-	range->gc = &bank->gpio_chip;
-
 	/* create irq hierarchical domain */
 	bank->fwnode = of_node_to_fwnode(np);
 
@@ -967,7 +985,7 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 		return err;
 	}
 
-	dev_info(dev, "%s bank added\n", range->name);
+	dev_info(dev, "%s bank added\n", bank->gpio_chip.label);
 	return 0;
 }
 
@@ -1086,30 +1104,6 @@ int stm32_pctl_probe(struct platform_device *pdev)
 			return ret;
 	}
 
-	for_each_child_of_node(np, child)
-		if (of_property_read_bool(child, "gpio-controller"))
-			banks++;
-
-	if (!banks) {
-		dev_err(dev, "at least one GPIO bank is required\n");
-		return -EINVAL;
-	}
-
-	pctl->banks = devm_kcalloc(dev, banks, sizeof(*pctl->banks),
-			GFP_KERNEL);
-	if (!pctl->banks)
-		return -ENOMEM;
-
-	for_each_child_of_node(np, child) {
-		if (of_property_read_bool(child, "gpio-controller")) {
-			ret = stm32_gpiolib_register_bank(pctl, child);
-			if (ret)
-				return ret;
-
-			pctl->nbanks++;
-		}
-	}
-
 	pins = devm_kcalloc(&pdev->dev, pctl->match_data->npins, sizeof(*pins),
 			    GFP_KERNEL);
 	if (!pins)
@@ -1129,13 +1123,34 @@ int stm32_pctl_probe(struct platform_device *pdev)
 
 	pctl->pctl_dev = devm_pinctrl_register(&pdev->dev, &pctl->pctl_desc,
 					       pctl);
+
 	if (IS_ERR(pctl->pctl_dev)) {
 		dev_err(&pdev->dev, "Failed pinctrl registration\n");
 		return PTR_ERR(pctl->pctl_dev);
 	}
 
-	for (i = 0; i < pctl->nbanks; i++)
-		pinctrl_add_gpio_range(pctl->pctl_dev, &pctl->banks[i].range);
+	for_each_child_of_node(np, child)
+		if (of_property_read_bool(child, "gpio-controller"))
+			banks++;
+
+	if (!banks) {
+		dev_err(dev, "at least one GPIO bank is required\n");
+		return -EINVAL;
+	}
+	pctl->banks = devm_kcalloc(dev, banks, sizeof(*pctl->banks),
+			GFP_KERNEL);
+	if (!pctl->banks)
+		return -ENOMEM;
+
+	for_each_child_of_node(np, child) {
+		if (of_property_read_bool(child, "gpio-controller")) {
+			ret = stm32_gpiolib_register_bank(pctl, child);
+			if (ret)
+				return ret;
+
+			pctl->nbanks++;
+		}
+	}
 
 	dev_info(dev, "Pinctrl STM32 initialized\n");
 
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32f429.c b/drivers/pinctrl/stm32/pinctrl-stm32f429.c
index 990b867b9625..4bbade25acc6 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32f429.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32f429.c
@@ -1584,4 +1584,8 @@ static struct platform_driver stm32f429_pinctrl_driver = {
 	},
 };
 
-builtin_platform_driver(stm32f429_pinctrl_driver);
+static int __init stm32f429_pinctrl_init(void)
+{
+	return platform_driver_register(&stm32f429_pinctrl_driver);
+}
+arch_initcall(stm32f429_pinctrl_init);
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32f469.c b/drivers/pinctrl/stm32/pinctrl-stm32f469.c
new file mode 100644
index 000000000000..86c8cebfa9b9
--- /dev/null
+++ b/drivers/pinctrl/stm32/pinctrl-stm32f469.c
@@ -0,0 +1,1578 @@
+/*
+ * Copyright (C) Alexandre Torgue 2016
+ * Author:  Alexandre Torgue <alexandre.torgue@st.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-stm32.h"
+
+static const struct stm32_desc_pin stm32f469_pins[] = {
+	STM32_PIN(
+		PINCTRL_PIN(0, "PA0"),
+		STM32_FUNCTION(0, "GPIOA0"),
+		STM32_FUNCTION(2, "TIM2_CH1 TIM2_ETR"),
+		STM32_FUNCTION(3, "TIM5_CH1"),
+		STM32_FUNCTION(4, "TIM8_ETR"),
+		STM32_FUNCTION(8, "USART2_CTS"),
+		STM32_FUNCTION(9, "UART4_TX"),
+		STM32_FUNCTION(12, "ETH_MII_CRS"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(1, "PA1"),
+		STM32_FUNCTION(0, "GPIOA1"),
+		STM32_FUNCTION(2, "TIM2_CH2"),
+		STM32_FUNCTION(3, "TIM5_CH2"),
+		STM32_FUNCTION(8, "USART2_RTS"),
+		STM32_FUNCTION(9, "UART4_RX"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO3"),
+		STM32_FUNCTION(12, "ETH_MII_RX_CLK ETH_RMII_REF_CLK"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(2, "PA2"),
+		STM32_FUNCTION(0, "GPIOA2"),
+		STM32_FUNCTION(2, "TIM2_CH3"),
+		STM32_FUNCTION(3, "TIM5_CH3"),
+		STM32_FUNCTION(4, "TIM9_CH1"),
+		STM32_FUNCTION(8, "USART2_TX"),
+		STM32_FUNCTION(12, "ETH_MDIO"),
+		STM32_FUNCTION(15, "LCD_R1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(3, "PA3"),
+		STM32_FUNCTION(0, "GPIOA3"),
+		STM32_FUNCTION(2, "TIM2_CH4"),
+		STM32_FUNCTION(3, "TIM5_CH4"),
+		STM32_FUNCTION(4, "TIM9_CH2"),
+		STM32_FUNCTION(8, "USART2_RX"),
+		STM32_FUNCTION(10, "LCD_B2"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D0"),
+		STM32_FUNCTION(12, "ETH_MII_COL"),
+		STM32_FUNCTION(15, "LCD_B5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(4, "PA4"),
+		STM32_FUNCTION(0, "GPIOA4"),
+		STM32_FUNCTION(6, "SPI1_NSS"),
+		STM32_FUNCTION(7, "SPI3_NSS I2S3_WS"),
+		STM32_FUNCTION(8, "USART2_CK"),
+		STM32_FUNCTION(13, "OTG_HS_SOF"),
+		STM32_FUNCTION(14, "DCMI_HSYNC"),
+		STM32_FUNCTION(15, "LCD_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(5, "PA5"),
+		STM32_FUNCTION(0, "GPIOA5"),
+		STM32_FUNCTION(2, "TIM2_CH1 TIM2_ETR"),
+		STM32_FUNCTION(4, "TIM8_CH1N"),
+		STM32_FUNCTION(6, "SPI1_SCK"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_CK"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(6, "PA6"),
+		STM32_FUNCTION(0, "GPIOA6"),
+		STM32_FUNCTION(2, "TIM1_BKIN"),
+		STM32_FUNCTION(3, "TIM3_CH1"),
+		STM32_FUNCTION(4, "TIM8_BKIN"),
+		STM32_FUNCTION(6, "SPI1_MISO"),
+		STM32_FUNCTION(10, "TIM13_CH1"),
+		STM32_FUNCTION(14, "DCMI_PIXCLK"),
+		STM32_FUNCTION(15, "LCD_G2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(7, "PA7"),
+		STM32_FUNCTION(0, "GPIOA7"),
+		STM32_FUNCTION(2, "TIM1_CH1N"),
+		STM32_FUNCTION(3, "TIM3_CH2"),
+		STM32_FUNCTION(4, "TIM8_CH1N"),
+		STM32_FUNCTION(6, "SPI1_MOSI"),
+		STM32_FUNCTION(10, "TIM14_CH1"),
+		STM32_FUNCTION(11, "QUADSPI_CLK"),
+		STM32_FUNCTION(12, "ETH_MII_RX_DV ETH_RMII_CRS_DV"),
+		STM32_FUNCTION(13, "FMC_SDNWE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(8, "PA8"),
+		STM32_FUNCTION(0, "GPIOA8"),
+		STM32_FUNCTION(1, "MCO1"),
+		STM32_FUNCTION(2, "TIM1_CH1"),
+		STM32_FUNCTION(5, "I2C3_SCL"),
+		STM32_FUNCTION(8, "USART1_CK"),
+		STM32_FUNCTION(11, "OTG_FS_SOF"),
+		STM32_FUNCTION(15, "LCD_R6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(9, "PA9"),
+		STM32_FUNCTION(0, "GPIOA9"),
+		STM32_FUNCTION(2, "TIM1_CH2"),
+		STM32_FUNCTION(5, "I2C3_SMBA"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART1_TX"),
+		STM32_FUNCTION(14, "DCMI_D0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(10, "PA10"),
+		STM32_FUNCTION(0, "GPIOA10"),
+		STM32_FUNCTION(2, "TIM1_CH3"),
+		STM32_FUNCTION(8, "USART1_RX"),
+		STM32_FUNCTION(11, "OTG_FS_ID"),
+		STM32_FUNCTION(14, "DCMI_D1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(11, "PA11"),
+		STM32_FUNCTION(0, "GPIOA11"),
+		STM32_FUNCTION(2, "TIM1_CH4"),
+		STM32_FUNCTION(8, "USART1_CTS"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(11, "OTG_FS_DM"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(12, "PA12"),
+		STM32_FUNCTION(0, "GPIOA12"),
+		STM32_FUNCTION(2, "TIM1_ETR"),
+		STM32_FUNCTION(8, "USART1_RTS"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(11, "OTG_FS_DP"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(13, "PA13"),
+		STM32_FUNCTION(0, "GPIOA13"),
+		STM32_FUNCTION(1, "JTMS SWDIO"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(14, "PA14"),
+		STM32_FUNCTION(0, "GPIOA14"),
+		STM32_FUNCTION(1, "JTCK SWCLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(15, "PA15"),
+		STM32_FUNCTION(0, "GPIOA15"),
+		STM32_FUNCTION(1, "JTDI"),
+		STM32_FUNCTION(2, "TIM2_CH1 TIM2_ETR"),
+		STM32_FUNCTION(6, "SPI1_NSS"),
+		STM32_FUNCTION(7, "SPI3_NSS I2S3_WS"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(16, "PB0"),
+		STM32_FUNCTION(0, "GPIOB0"),
+		STM32_FUNCTION(2, "TIM1_CH2N"),
+		STM32_FUNCTION(3, "TIM3_CH3"),
+		STM32_FUNCTION(4, "TIM8_CH2N"),
+		STM32_FUNCTION(10, "LCD_R3"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D1"),
+		STM32_FUNCTION(12, "ETH_MII_RXD2"),
+		STM32_FUNCTION(15, "LCD_G1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(17, "PB1"),
+		STM32_FUNCTION(0, "GPIOB1"),
+		STM32_FUNCTION(2, "TIM1_CH3N"),
+		STM32_FUNCTION(3, "TIM3_CH4"),
+		STM32_FUNCTION(4, "TIM8_CH3N"),
+		STM32_FUNCTION(10, "LCD_R6"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D2"),
+		STM32_FUNCTION(12, "ETH_MII_RXD3"),
+		STM32_FUNCTION(15, "LCD_G0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(18, "PB2"),
+		STM32_FUNCTION(0, "GPIOB2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(19, "PB3"),
+		STM32_FUNCTION(0, "GPIOB3"),
+		STM32_FUNCTION(1, "JTDO TRACESWO"),
+		STM32_FUNCTION(2, "TIM2_CH2"),
+		STM32_FUNCTION(6, "SPI1_SCK"),
+		STM32_FUNCTION(7, "SPI3_SCK I2S3_CK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(20, "PB4"),
+		STM32_FUNCTION(0, "GPIOB4"),
+		STM32_FUNCTION(1, "NJTRST"),
+		STM32_FUNCTION(3, "TIM3_CH1"),
+		STM32_FUNCTION(6, "SPI1_MISO"),
+		STM32_FUNCTION(7, "SPI3_MISO"),
+		STM32_FUNCTION(8, "I2S3EXT_SD"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(21, "PB5"),
+		STM32_FUNCTION(0, "GPIOB5"),
+		STM32_FUNCTION(3, "TIM3_CH2"),
+		STM32_FUNCTION(5, "I2C1_SMBA"),
+		STM32_FUNCTION(6, "SPI1_MOSI"),
+		STM32_FUNCTION(7, "SPI3_MOSI I2S3_SD"),
+		STM32_FUNCTION(10, "CAN2_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D7"),
+		STM32_FUNCTION(12, "ETH_PPS_OUT"),
+		STM32_FUNCTION(13, "FMC_SDCKE1"),
+		STM32_FUNCTION(14, "DCMI_D10"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(22, "PB6"),
+		STM32_FUNCTION(0, "GPIOB6"),
+		STM32_FUNCTION(3, "TIM4_CH1"),
+		STM32_FUNCTION(5, "I2C1_SCL"),
+		STM32_FUNCTION(8, "USART1_TX"),
+		STM32_FUNCTION(10, "CAN2_TX"),
+		STM32_FUNCTION(11, "QUADSPI_BK1_NCS"),
+		STM32_FUNCTION(13, "FMC_SDNE1"),
+		STM32_FUNCTION(14, "DCMI_D5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(23, "PB7"),
+		STM32_FUNCTION(0, "GPIOB7"),
+		STM32_FUNCTION(3, "TIM4_CH2"),
+		STM32_FUNCTION(5, "I2C1_SDA"),
+		STM32_FUNCTION(8, "USART1_RX"),
+		STM32_FUNCTION(13, "FMC_NL"),
+		STM32_FUNCTION(14, "DCMI_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(24, "PB8"),
+		STM32_FUNCTION(0, "GPIOB8"),
+		STM32_FUNCTION(3, "TIM4_CH3"),
+		STM32_FUNCTION(4, "TIM10_CH1"),
+		STM32_FUNCTION(5, "I2C1_SCL"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(12, "ETH_MII_TXD3"),
+		STM32_FUNCTION(13, "SDIO_D4"),
+		STM32_FUNCTION(14, "DCMI_D6"),
+		STM32_FUNCTION(15, "LCD_B6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(25, "PB9"),
+		STM32_FUNCTION(0, "GPIOB9"),
+		STM32_FUNCTION(3, "TIM4_CH4"),
+		STM32_FUNCTION(4, "TIM11_CH1"),
+		STM32_FUNCTION(5, "I2C1_SDA"),
+		STM32_FUNCTION(6, "SPI2_NSS I2S2_WS"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(13, "SDIO_D5"),
+		STM32_FUNCTION(14, "DCMI_D7"),
+		STM32_FUNCTION(15, "LCD_B7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(26, "PB10"),
+		STM32_FUNCTION(0, "GPIOB10"),
+		STM32_FUNCTION(2, "TIM2_CH3"),
+		STM32_FUNCTION(5, "I2C2_SCL"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART3_TX"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_NCS"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D3"),
+		STM32_FUNCTION(12, "ETH_MII_RX_ER"),
+		STM32_FUNCTION(15, "LCD_G4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(27, "PB11"),
+		STM32_FUNCTION(0, "GPIOB11"),
+		STM32_FUNCTION(2, "TIM2_CH4"),
+		STM32_FUNCTION(5, "I2C2_SDA"),
+		STM32_FUNCTION(8, "USART3_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D4"),
+		STM32_FUNCTION(12, "ETH_MII_TX_EN ETH_RMII_TX_EN"),
+		STM32_FUNCTION(14, "DSIHOST_TE"),
+		STM32_FUNCTION(15, "LCD_G5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(28, "PB12"),
+		STM32_FUNCTION(0, "GPIOB12"),
+		STM32_FUNCTION(2, "TIM1_BKIN"),
+		STM32_FUNCTION(5, "I2C2_SMBA"),
+		STM32_FUNCTION(6, "SPI2_NSS I2S2_WS"),
+		STM32_FUNCTION(8, "USART3_CK"),
+		STM32_FUNCTION(10, "CAN2_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D5"),
+		STM32_FUNCTION(12, "ETH_MII_TXD0 ETH_RMII_TXD0"),
+		STM32_FUNCTION(13, "OTG_HS_ID"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(29, "PB13"),
+		STM32_FUNCTION(0, "GPIOB13"),
+		STM32_FUNCTION(2, "TIM1_CH1N"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART3_CTS"),
+		STM32_FUNCTION(10, "CAN2_TX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D6"),
+		STM32_FUNCTION(12, "ETH_MII_TXD1 ETH_RMII_TXD1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(30, "PB14"),
+		STM32_FUNCTION(0, "GPIOB14"),
+		STM32_FUNCTION(2, "TIM1_CH2N"),
+		STM32_FUNCTION(4, "TIM8_CH2N"),
+		STM32_FUNCTION(6, "SPI2_MISO"),
+		STM32_FUNCTION(7, "I2S2EXT_SD"),
+		STM32_FUNCTION(8, "USART3_RTS"),
+		STM32_FUNCTION(10, "TIM12_CH1"),
+		STM32_FUNCTION(13, "OTG_HS_DM"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(31, "PB15"),
+		STM32_FUNCTION(0, "GPIOB15"),
+		STM32_FUNCTION(1, "RTC_REFIN"),
+		STM32_FUNCTION(2, "TIM1_CH3N"),
+		STM32_FUNCTION(4, "TIM8_CH3N"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(10, "TIM12_CH2"),
+		STM32_FUNCTION(13, "OTG_HS_DP"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(32, "PC0"),
+		STM32_FUNCTION(0, "GPIOC0"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_STP"),
+		STM32_FUNCTION(13, "FMC_SDNWE"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(33, "PC1"),
+		STM32_FUNCTION(0, "GPIOC1"),
+		STM32_FUNCTION(1, "TRACED0"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(7, "SAI1_SD_A"),
+		STM32_FUNCTION(12, "ETH_MDC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(34, "PC2"),
+		STM32_FUNCTION(0, "GPIOC2"),
+		STM32_FUNCTION(6, "SPI2_MISO"),
+		STM32_FUNCTION(7, "I2S2EXT_SD"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_DIR"),
+		STM32_FUNCTION(12, "ETH_MII_TXD2"),
+		STM32_FUNCTION(13, "FMC_SDNE0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(35, "PC3"),
+		STM32_FUNCTION(0, "GPIOC3"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_NXT"),
+		STM32_FUNCTION(12, "ETH_MII_TX_CLK"),
+		STM32_FUNCTION(13, "FMC_SDCKE0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(36, "PC4"),
+		STM32_FUNCTION(0, "GPIOC4"),
+		STM32_FUNCTION(12, "ETH_MII_RXD0 ETH_RMII_RXD0"),
+		STM32_FUNCTION(13, "FMC_SDNE0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(37, "PC5"),
+		STM32_FUNCTION(0, "GPIOC5"),
+		STM32_FUNCTION(12, "ETH_MII_RXD1 ETH_RMII_RXD1"),
+		STM32_FUNCTION(13, "FMC_SDCKE0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(38, "PC6"),
+		STM32_FUNCTION(0, "GPIOC6"),
+		STM32_FUNCTION(3, "TIM3_CH1"),
+		STM32_FUNCTION(4, "TIM8_CH1"),
+		STM32_FUNCTION(6, "I2S2_MCK"),
+		STM32_FUNCTION(9, "USART6_TX"),
+		STM32_FUNCTION(13, "SDIO_D6"),
+		STM32_FUNCTION(14, "DCMI_D0"),
+		STM32_FUNCTION(15, "LCD_HSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(39, "PC7"),
+		STM32_FUNCTION(0, "GPIOC7"),
+		STM32_FUNCTION(3, "TIM3_CH2"),
+		STM32_FUNCTION(4, "TIM8_CH2"),
+		STM32_FUNCTION(7, "I2S3_MCK"),
+		STM32_FUNCTION(9, "USART6_RX"),
+		STM32_FUNCTION(13, "SDIO_D7"),
+		STM32_FUNCTION(14, "DCMI_D1"),
+		STM32_FUNCTION(15, "LCD_G6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(40, "PC8"),
+		STM32_FUNCTION(0, "GPIOC8"),
+		STM32_FUNCTION(1, "TRACED1"),
+		STM32_FUNCTION(3, "TIM3_CH3"),
+		STM32_FUNCTION(4, "TIM8_CH3"),
+		STM32_FUNCTION(9, "USART6_CK"),
+		STM32_FUNCTION(13, "SDIO_D0"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(41, "PC9"),
+		STM32_FUNCTION(0, "GPIOC9"),
+		STM32_FUNCTION(1, "MCO2"),
+		STM32_FUNCTION(3, "TIM3_CH4"),
+		STM32_FUNCTION(4, "TIM8_CH4"),
+		STM32_FUNCTION(5, "I2C3_SDA"),
+		STM32_FUNCTION(6, "I2S_CKIN"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO0"),
+		STM32_FUNCTION(13, "SDIO_D1"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(42, "PC10"),
+		STM32_FUNCTION(0, "GPIOC10"),
+		STM32_FUNCTION(7, "SPI3_SCK I2S3_CK"),
+		STM32_FUNCTION(8, "USART3_TX"),
+		STM32_FUNCTION(9, "UART4_TX"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO1"),
+		STM32_FUNCTION(13, "SDIO_D2"),
+		STM32_FUNCTION(14, "DCMI_D8"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(43, "PC11"),
+		STM32_FUNCTION(0, "GPIOC11"),
+		STM32_FUNCTION(6, "I2S3EXT_SD"),
+		STM32_FUNCTION(7, "SPI3_MISO"),
+		STM32_FUNCTION(8, "USART3_RX"),
+		STM32_FUNCTION(9, "UART4_RX"),
+		STM32_FUNCTION(10, "QUADSPI_BK2_NCS"),
+		STM32_FUNCTION(13, "SDIO_D3"),
+		STM32_FUNCTION(14, "DCMI_D4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(44, "PC12"),
+		STM32_FUNCTION(0, "GPIOC12"),
+		STM32_FUNCTION(1, "TRACED3"),
+		STM32_FUNCTION(7, "SPI3_MOSI I2S3_SD"),
+		STM32_FUNCTION(8, "USART3_CK"),
+		STM32_FUNCTION(9, "UART5_TX"),
+		STM32_FUNCTION(13, "SDIO_CK"),
+		STM32_FUNCTION(14, "DCMI_D9"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(45, "PC13"),
+		STM32_FUNCTION(0, "GPIOC13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(46, "PC14"),
+		STM32_FUNCTION(0, "GPIOC14"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(47, "PC15"),
+		STM32_FUNCTION(0, "GPIOC15"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(48, "PD0"),
+		STM32_FUNCTION(0, "GPIOD0"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(13, "FMC_D2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(49, "PD1"),
+		STM32_FUNCTION(0, "GPIOD1"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(13, "FMC_D3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(50, "PD2"),
+		STM32_FUNCTION(0, "GPIOD2"),
+		STM32_FUNCTION(1, "TRACED2"),
+		STM32_FUNCTION(3, "TIM3_ETR"),
+		STM32_FUNCTION(9, "UART5_RX"),
+		STM32_FUNCTION(13, "SDIO_CMD"),
+		STM32_FUNCTION(14, "DCMI_D11"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(51, "PD3"),
+		STM32_FUNCTION(0, "GPIOD3"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART2_CTS"),
+		STM32_FUNCTION(13, "FMC_CLK"),
+		STM32_FUNCTION(14, "DCMI_D5"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(52, "PD4"),
+		STM32_FUNCTION(0, "GPIOD4"),
+		STM32_FUNCTION(8, "USART2_RTS"),
+		STM32_FUNCTION(13, "FMC_NOE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(53, "PD5"),
+		STM32_FUNCTION(0, "GPIOD5"),
+		STM32_FUNCTION(8, "USART2_TX"),
+		STM32_FUNCTION(13, "FMC_NWE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(54, "PD6"),
+		STM32_FUNCTION(0, "GPIOD6"),
+		STM32_FUNCTION(6, "SPI3_MOSI I2S3_SD"),
+		STM32_FUNCTION(7, "SAI1_SD_A"),
+		STM32_FUNCTION(8, "USART2_RX"),
+		STM32_FUNCTION(13, "FMC_NWAIT"),
+		STM32_FUNCTION(14, "DCMI_D10"),
+		STM32_FUNCTION(15, "LCD_B2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(55, "PD7"),
+		STM32_FUNCTION(0, "GPIOD7"),
+		STM32_FUNCTION(8, "USART2_CK"),
+		STM32_FUNCTION(13, "FMC_NE1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(56, "PD8"),
+		STM32_FUNCTION(0, "GPIOD8"),
+		STM32_FUNCTION(8, "USART3_TX"),
+		STM32_FUNCTION(13, "FMC_D13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(57, "PD9"),
+		STM32_FUNCTION(0, "GPIOD9"),
+		STM32_FUNCTION(8, "USART3_RX"),
+		STM32_FUNCTION(13, "FMC_D14"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(58, "PD10"),
+		STM32_FUNCTION(0, "GPIOD10"),
+		STM32_FUNCTION(8, "USART3_CK"),
+		STM32_FUNCTION(13, "FMC_D15"),
+		STM32_FUNCTION(15, "LCD_B3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(59, "PD11"),
+		STM32_FUNCTION(0, "GPIOD11"),
+		STM32_FUNCTION(8, "USART3_CTS"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO0"),
+		STM32_FUNCTION(13, "FMC_A16 FMC_CLE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(60, "PD12"),
+		STM32_FUNCTION(0, "GPIOD12"),
+		STM32_FUNCTION(3, "TIM4_CH1"),
+		STM32_FUNCTION(8, "USART3_RTS"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO1"),
+		STM32_FUNCTION(13, "FMC_A17 FMC_ALE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(61, "PD13"),
+		STM32_FUNCTION(0, "GPIOD13"),
+		STM32_FUNCTION(3, "TIM4_CH2"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO3"),
+		STM32_FUNCTION(13, "FMC_A18"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(62, "PD14"),
+		STM32_FUNCTION(0, "GPIOD14"),
+		STM32_FUNCTION(3, "TIM4_CH3"),
+		STM32_FUNCTION(13, "FMC_D0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(63, "PD15"),
+		STM32_FUNCTION(0, "GPIOD15"),
+		STM32_FUNCTION(3, "TIM4_CH4"),
+		STM32_FUNCTION(13, "FMC_D1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(64, "PE0"),
+		STM32_FUNCTION(0, "GPIOE0"),
+		STM32_FUNCTION(3, "TIM4_ETR"),
+		STM32_FUNCTION(9, "UART8_RX"),
+		STM32_FUNCTION(13, "FMC_NBL0"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(65, "PE1"),
+		STM32_FUNCTION(0, "GPIOE1"),
+		STM32_FUNCTION(9, "UART8_TX"),
+		STM32_FUNCTION(13, "FMC_NBL1"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(66, "PE2"),
+		STM32_FUNCTION(0, "GPIOE2"),
+		STM32_FUNCTION(1, "TRACECLK"),
+		STM32_FUNCTION(6, "SPI4_SCK"),
+		STM32_FUNCTION(7, "SAI1_MCLK_A"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO2"),
+		STM32_FUNCTION(12, "ETH_MII_TXD3"),
+		STM32_FUNCTION(13, "FMC_A23"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(67, "PE3"),
+		STM32_FUNCTION(0, "GPIOE3"),
+		STM32_FUNCTION(1, "TRACED0"),
+		STM32_FUNCTION(7, "SAI1_SD_B"),
+		STM32_FUNCTION(13, "FMC_A19"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(68, "PE4"),
+		STM32_FUNCTION(0, "GPIOE4"),
+		STM32_FUNCTION(1, "TRACED1"),
+		STM32_FUNCTION(6, "SPI4_NSS"),
+		STM32_FUNCTION(7, "SAI1_FS_A"),
+		STM32_FUNCTION(13, "FMC_A20"),
+		STM32_FUNCTION(14, "DCMI_D4"),
+		STM32_FUNCTION(15, "LCD_B0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(69, "PE5"),
+		STM32_FUNCTION(0, "GPIOE5"),
+		STM32_FUNCTION(1, "TRACED2"),
+		STM32_FUNCTION(4, "TIM9_CH1"),
+		STM32_FUNCTION(6, "SPI4_MISO"),
+		STM32_FUNCTION(7, "SAI1_SCK_A"),
+		STM32_FUNCTION(13, "FMC_A21"),
+		STM32_FUNCTION(14, "DCMI_D6"),
+		STM32_FUNCTION(15, "LCD_G0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(70, "PE6"),
+		STM32_FUNCTION(0, "GPIOE6"),
+		STM32_FUNCTION(1, "TRACED3"),
+		STM32_FUNCTION(4, "TIM9_CH2"),
+		STM32_FUNCTION(6, "SPI4_MOSI"),
+		STM32_FUNCTION(7, "SAI1_SD_A"),
+		STM32_FUNCTION(13, "FMC_A22"),
+		STM32_FUNCTION(14, "DCMI_D7"),
+		STM32_FUNCTION(15, "LCD_G1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(71, "PE7"),
+		STM32_FUNCTION(0, "GPIOE7"),
+		STM32_FUNCTION(2, "TIM1_ETR"),
+		STM32_FUNCTION(9, "UART7_RX"),
+		STM32_FUNCTION(11, "QUADSPI_BK2_IO0"),
+		STM32_FUNCTION(13, "FMC_D4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(72, "PE8"),
+		STM32_FUNCTION(0, "GPIOE8"),
+		STM32_FUNCTION(2, "TIM1_CH1N"),
+		STM32_FUNCTION(9, "UART7_TX"),
+		STM32_FUNCTION(11, "QUADSPI_BK2_IO1"),
+		STM32_FUNCTION(13, "FMC_D5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(73, "PE9"),
+		STM32_FUNCTION(0, "GPIOE9"),
+		STM32_FUNCTION(2, "TIM1_CH1"),
+		STM32_FUNCTION(11, "QUADSPI_BK2_IO2"),
+		STM32_FUNCTION(13, "FMC_D6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(74, "PE10"),
+		STM32_FUNCTION(0, "GPIOE10"),
+		STM32_FUNCTION(2, "TIM1_CH2N"),
+		STM32_FUNCTION(11, "QUADSPI_BK2_IO3"),
+		STM32_FUNCTION(13, "FMC_D7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(75, "PE11"),
+		STM32_FUNCTION(0, "GPIOE11"),
+		STM32_FUNCTION(2, "TIM1_CH2"),
+		STM32_FUNCTION(6, "SPI4_NSS"),
+		STM32_FUNCTION(13, "FMC_D8"),
+		STM32_FUNCTION(15, "LCD_G3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(76, "PE12"),
+		STM32_FUNCTION(0, "GPIOE12"),
+		STM32_FUNCTION(2, "TIM1_CH3N"),
+		STM32_FUNCTION(6, "SPI4_SCK"),
+		STM32_FUNCTION(13, "FMC_D9"),
+		STM32_FUNCTION(15, "LCD_B4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(77, "PE13"),
+		STM32_FUNCTION(0, "GPIOE13"),
+		STM32_FUNCTION(2, "TIM1_CH3"),
+		STM32_FUNCTION(6, "SPI4_MISO"),
+		STM32_FUNCTION(13, "FMC_D10"),
+		STM32_FUNCTION(15, "LCD_DE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(78, "PE14"),
+		STM32_FUNCTION(0, "GPIOE14"),
+		STM32_FUNCTION(2, "TIM1_CH4"),
+		STM32_FUNCTION(6, "SPI4_MOSI"),
+		STM32_FUNCTION(13, "FMC_D11"),
+		STM32_FUNCTION(15, "LCD_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(79, "PE15"),
+		STM32_FUNCTION(0, "GPIOE15"),
+		STM32_FUNCTION(2, "TIM1_BKIN"),
+		STM32_FUNCTION(13, "FMC_D12"),
+		STM32_FUNCTION(15, "LCD_R7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(80, "PF0"),
+		STM32_FUNCTION(0, "GPIOF0"),
+		STM32_FUNCTION(5, "I2C2_SDA"),
+		STM32_FUNCTION(13, "FMC_A0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(81, "PF1"),
+		STM32_FUNCTION(0, "GPIOF1"),
+		STM32_FUNCTION(5, "I2C2_SCL"),
+		STM32_FUNCTION(13, "FMC_A1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(82, "PF2"),
+		STM32_FUNCTION(0, "GPIOF2"),
+		STM32_FUNCTION(5, "I2C2_SMBA"),
+		STM32_FUNCTION(13, "FMC_A2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(83, "PF3"),
+		STM32_FUNCTION(0, "GPIOF3"),
+		STM32_FUNCTION(13, "FMC_A3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(84, "PF4"),
+		STM32_FUNCTION(0, "GPIOF4"),
+		STM32_FUNCTION(13, "FMC_A4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(85, "PF5"),
+		STM32_FUNCTION(0, "GPIOF5"),
+		STM32_FUNCTION(13, "FMC_A5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(86, "PF6"),
+		STM32_FUNCTION(0, "GPIOF6"),
+		STM32_FUNCTION(4, "TIM10_CH1"),
+		STM32_FUNCTION(6, "SPI5_NSS"),
+		STM32_FUNCTION(7, "SAI1_SD_B"),
+		STM32_FUNCTION(9, "UART7_RX"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(87, "PF7"),
+		STM32_FUNCTION(0, "GPIOF7"),
+		STM32_FUNCTION(4, "TIM11_CH1"),
+		STM32_FUNCTION(6, "SPI5_SCK"),
+		STM32_FUNCTION(7, "SAI1_MCLK_B"),
+		STM32_FUNCTION(9, "UART7_TX"),
+		STM32_FUNCTION(10, "QUADSPI_BK1_IO2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(88, "PF8"),
+		STM32_FUNCTION(0, "GPIOF8"),
+		STM32_FUNCTION(6, "SPI5_MISO"),
+		STM32_FUNCTION(7, "SAI1_SCK_B"),
+		STM32_FUNCTION(10, "TIM13_CH1"),
+		STM32_FUNCTION(11, "QUADSPI_BK1_IO0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(89, "PF9"),
+		STM32_FUNCTION(0, "GPIOF9"),
+		STM32_FUNCTION(6, "SPI5_MOSI"),
+		STM32_FUNCTION(7, "SAI1_FS_B"),
+		STM32_FUNCTION(10, "TIM14_CH1"),
+		STM32_FUNCTION(11, "QUADSPI_BK1_IO1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(90, "PF10"),
+		STM32_FUNCTION(0, "GPIOF10"),
+		STM32_FUNCTION(10, "QUADSPI_CLK"),
+		STM32_FUNCTION(14, "DCMI_D11"),
+		STM32_FUNCTION(15, "LCD_DE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(91, "PF11"),
+		STM32_FUNCTION(0, "GPIOF11"),
+		STM32_FUNCTION(6, "SPI5_MOSI"),
+		STM32_FUNCTION(13, "FMC_SDNRAS"),
+		STM32_FUNCTION(14, "DCMI_D12"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(92, "PF12"),
+		STM32_FUNCTION(0, "GPIOF12"),
+		STM32_FUNCTION(13, "FMC_A6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(93, "PF13"),
+		STM32_FUNCTION(0, "GPIOF13"),
+		STM32_FUNCTION(13, "FMC_A7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(94, "PF14"),
+		STM32_FUNCTION(0, "GPIOF14"),
+		STM32_FUNCTION(13, "FMC_A8"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(95, "PF15"),
+		STM32_FUNCTION(0, "GPIOF15"),
+		STM32_FUNCTION(13, "FMC_A9"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(96, "PG0"),
+		STM32_FUNCTION(0, "GPIOG0"),
+		STM32_FUNCTION(13, "FMC_A10"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(97, "PG1"),
+		STM32_FUNCTION(0, "GPIOG1"),
+		STM32_FUNCTION(13, "FMC_A11"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(98, "PG2"),
+		STM32_FUNCTION(0, "GPIOG2"),
+		STM32_FUNCTION(13, "FMC_A12"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(99, "PG3"),
+		STM32_FUNCTION(0, "GPIOG3"),
+		STM32_FUNCTION(13, "FMC_A13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(100, "PG4"),
+		STM32_FUNCTION(0, "GPIOG4"),
+		STM32_FUNCTION(13, "FMC_A14 FMC_BA0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(101, "PG5"),
+		STM32_FUNCTION(0, "GPIOG5"),
+		STM32_FUNCTION(13, "FMC_A15 FMC_BA1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(102, "PG6"),
+		STM32_FUNCTION(0, "GPIOG6"),
+		STM32_FUNCTION(14, "DCMI_D12"),
+		STM32_FUNCTION(15, "LCD_R7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(103, "PG7"),
+		STM32_FUNCTION(0, "GPIOG7"),
+		STM32_FUNCTION(7, "SAI1_MCLK_A"),
+		STM32_FUNCTION(9, "USART6_CK"),
+		STM32_FUNCTION(13, "FMC_INT"),
+		STM32_FUNCTION(14, "DCMI_D13"),
+		STM32_FUNCTION(15, "LCD_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(104, "PG8"),
+		STM32_FUNCTION(0, "GPIOG8"),
+		STM32_FUNCTION(6, "SPI6_NSS"),
+		STM32_FUNCTION(9, "USART6_RTS"),
+		STM32_FUNCTION(12, "ETH_PPS_OUT"),
+		STM32_FUNCTION(13, "FMC_SDCLK"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(105, "PG9"),
+		STM32_FUNCTION(0, "GPIOG9"),
+		STM32_FUNCTION(9, "USART6_RX"),
+		STM32_FUNCTION(10, "QUADSPI_BK2_IO2"),
+		STM32_FUNCTION(13, "FMC_NE2 FMC_NCE"),
+		STM32_FUNCTION(14, "DCMI_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(106, "PG10"),
+		STM32_FUNCTION(0, "GPIOG10"),
+		STM32_FUNCTION(10, "LCD_G3"),
+		STM32_FUNCTION(13, "FMC_NE3"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(15, "LCD_B2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(107, "PG11"),
+		STM32_FUNCTION(0, "GPIOG11"),
+		STM32_FUNCTION(12, "ETH_MII_TX_EN ETH_RMII_TX_EN"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(15, "LCD_B3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(108, "PG12"),
+		STM32_FUNCTION(0, "GPIOG12"),
+		STM32_FUNCTION(6, "SPI6_MISO"),
+		STM32_FUNCTION(9, "USART6_RTS"),
+		STM32_FUNCTION(10, "LCD_B4"),
+		STM32_FUNCTION(13, "FMC_NE4"),
+		STM32_FUNCTION(15, "LCD_B1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(109, "PG13"),
+		STM32_FUNCTION(0, "GPIOG13"),
+		STM32_FUNCTION(1, "TRACED0"),
+		STM32_FUNCTION(6, "SPI6_SCK"),
+		STM32_FUNCTION(9, "USART6_CTS"),
+		STM32_FUNCTION(12, "ETH_MII_TXD0 ETH_RMII_TXD0"),
+		STM32_FUNCTION(13, "FMC_A24"),
+		STM32_FUNCTION(15, "LCD_R0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(110, "PG14"),
+		STM32_FUNCTION(0, "GPIOG14"),
+		STM32_FUNCTION(1, "TRACED1"),
+		STM32_FUNCTION(6, "SPI6_MOSI"),
+		STM32_FUNCTION(9, "USART6_TX"),
+		STM32_FUNCTION(10, "QUADSPI_BK2_IO3"),
+		STM32_FUNCTION(12, "ETH_MII_TXD1 ETH_RMII_TXD1"),
+		STM32_FUNCTION(13, "FMC_A25"),
+		STM32_FUNCTION(15, "LCD_B0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(111, "PG15"),
+		STM32_FUNCTION(0, "GPIOG15"),
+		STM32_FUNCTION(9, "USART6_CTS"),
+		STM32_FUNCTION(13, "FMC_SDNCAS"),
+		STM32_FUNCTION(14, "DCMI_D13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(112, "PH0"),
+		STM32_FUNCTION(0, "GPIOH0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(113, "PH1"),
+		STM32_FUNCTION(0, "GPIOH1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(114, "PH2"),
+		STM32_FUNCTION(0, "GPIOH2"),
+		STM32_FUNCTION(10, "QUADSPI_BK2_IO0"),
+		STM32_FUNCTION(12, "ETH_MII_CRS"),
+		STM32_FUNCTION(13, "FMC_SDCKE0"),
+		STM32_FUNCTION(15, "LCD_R0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(115, "PH3"),
+		STM32_FUNCTION(0, "GPIOH3"),
+		STM32_FUNCTION(10, "QUADSPI_BK2_IO1"),
+		STM32_FUNCTION(12, "ETH_MII_COL"),
+		STM32_FUNCTION(13, "FMC_SDNE0"),
+		STM32_FUNCTION(15, "LCD_R1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(116, "PH4"),
+		STM32_FUNCTION(0, "GPIOH4"),
+		STM32_FUNCTION(5, "I2C2_SCL"),
+		STM32_FUNCTION(10, "LCD_G5"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_NXT"),
+		STM32_FUNCTION(15, "LCD_G4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(117, "PH5"),
+		STM32_FUNCTION(0, "GPIOH5"),
+		STM32_FUNCTION(5, "I2C2_SDA"),
+		STM32_FUNCTION(6, "SPI5_NSS"),
+		STM32_FUNCTION(13, "FMC_SDNWE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(118, "PH6"),
+		STM32_FUNCTION(0, "GPIOH6"),
+		STM32_FUNCTION(5, "I2C2_SMBA"),
+		STM32_FUNCTION(6, "SPI5_SCK"),
+		STM32_FUNCTION(10, "TIM12_CH1"),
+		STM32_FUNCTION(12, "ETH_MII_RXD2"),
+		STM32_FUNCTION(13, "FMC_SDNE1"),
+		STM32_FUNCTION(14, "DCMI_D8"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(119, "PH7"),
+		STM32_FUNCTION(0, "GPIOH7"),
+		STM32_FUNCTION(5, "I2C3_SCL"),
+		STM32_FUNCTION(6, "SPI5_MISO"),
+		STM32_FUNCTION(12, "ETH_MII_RXD3"),
+		STM32_FUNCTION(13, "FMC_SDCKE1"),
+		STM32_FUNCTION(14, "DCMI_D9"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(120, "PH8"),
+		STM32_FUNCTION(0, "GPIOH8"),
+		STM32_FUNCTION(5, "I2C3_SDA"),
+		STM32_FUNCTION(13, "FMC_D16"),
+		STM32_FUNCTION(14, "DCMI_HSYNC"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(121, "PH9"),
+		STM32_FUNCTION(0, "GPIOH9"),
+		STM32_FUNCTION(5, "I2C3_SMBA"),
+		STM32_FUNCTION(10, "TIM12_CH2"),
+		STM32_FUNCTION(13, "FMC_D17"),
+		STM32_FUNCTION(14, "DCMI_D0"),
+		STM32_FUNCTION(15, "LCD_R3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(122, "PH10"),
+		STM32_FUNCTION(0, "GPIOH10"),
+		STM32_FUNCTION(3, "TIM5_CH1"),
+		STM32_FUNCTION(13, "FMC_D18"),
+		STM32_FUNCTION(14, "DCMI_D1"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(123, "PH11"),
+		STM32_FUNCTION(0, "GPIOH11"),
+		STM32_FUNCTION(3, "TIM5_CH2"),
+		STM32_FUNCTION(13, "FMC_D19"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(124, "PH12"),
+		STM32_FUNCTION(0, "GPIOH12"),
+		STM32_FUNCTION(3, "TIM5_CH3"),
+		STM32_FUNCTION(13, "FMC_D20"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(15, "LCD_R6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(125, "PH13"),
+		STM32_FUNCTION(0, "GPIOH13"),
+		STM32_FUNCTION(4, "TIM8_CH1N"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(13, "FMC_D21"),
+		STM32_FUNCTION(15, "LCD_G2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(126, "PH14"),
+		STM32_FUNCTION(0, "GPIOH14"),
+		STM32_FUNCTION(4, "TIM8_CH2N"),
+		STM32_FUNCTION(13, "FMC_D22"),
+		STM32_FUNCTION(14, "DCMI_D4"),
+		STM32_FUNCTION(15, "LCD_G3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(127, "PH15"),
+		STM32_FUNCTION(0, "GPIOH15"),
+		STM32_FUNCTION(4, "TIM8_CH3N"),
+		STM32_FUNCTION(13, "FMC_D23"),
+		STM32_FUNCTION(14, "DCMI_D11"),
+		STM32_FUNCTION(15, "LCD_G4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(128, "PI0"),
+		STM32_FUNCTION(0, "GPIOI0"),
+		STM32_FUNCTION(3, "TIM5_CH4"),
+		STM32_FUNCTION(6, "SPI2_NSS I2S2_WS"),
+		STM32_FUNCTION(13, "FMC_D24"),
+		STM32_FUNCTION(14, "DCMI_D13"),
+		STM32_FUNCTION(15, "LCD_G5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(129, "PI1"),
+		STM32_FUNCTION(0, "GPIOI1"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(13, "FMC_D25"),
+		STM32_FUNCTION(14, "DCMI_D8"),
+		STM32_FUNCTION(15, "LCD_G6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(130, "PI2"),
+		STM32_FUNCTION(0, "GPIOI2"),
+		STM32_FUNCTION(4, "TIM8_CH4"),
+		STM32_FUNCTION(6, "SPI2_MISO"),
+		STM32_FUNCTION(7, "I2S2EXT_SD"),
+		STM32_FUNCTION(13, "FMC_D26"),
+		STM32_FUNCTION(14, "DCMI_D9"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(131, "PI3"),
+		STM32_FUNCTION(0, "GPIOI3"),
+		STM32_FUNCTION(4, "TIM8_ETR"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(13, "FMC_D27"),
+		STM32_FUNCTION(14, "DCMI_D10"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(132, "PI4"),
+		STM32_FUNCTION(0, "GPIOI4"),
+		STM32_FUNCTION(4, "TIM8_BKIN"),
+		STM32_FUNCTION(13, "FMC_NBL2"),
+		STM32_FUNCTION(14, "DCMI_D5"),
+		STM32_FUNCTION(15, "LCD_B4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(133, "PI5"),
+		STM32_FUNCTION(0, "GPIOI5"),
+		STM32_FUNCTION(4, "TIM8_CH1"),
+		STM32_FUNCTION(13, "FMC_NBL3"),
+		STM32_FUNCTION(14, "DCMI_VSYNC"),
+		STM32_FUNCTION(15, "LCD_B5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(134, "PI6"),
+		STM32_FUNCTION(0, "GPIOI6"),
+		STM32_FUNCTION(4, "TIM8_CH2"),
+		STM32_FUNCTION(13, "FMC_D28"),
+		STM32_FUNCTION(14, "DCMI_D6"),
+		STM32_FUNCTION(15, "LCD_B6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(135, "PI7"),
+		STM32_FUNCTION(0, "GPIOI7"),
+		STM32_FUNCTION(4, "TIM8_CH3"),
+		STM32_FUNCTION(13, "FMC_D29"),
+		STM32_FUNCTION(14, "DCMI_D7"),
+		STM32_FUNCTION(15, "LCD_B7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(136, "PI8"),
+		STM32_FUNCTION(0, "GPIOI8"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(137, "PI9"),
+		STM32_FUNCTION(0, "GPIOI9"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(13, "FMC_D30"),
+		STM32_FUNCTION(15, "LCD_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(138, "PI10"),
+		STM32_FUNCTION(0, "GPIOI10"),
+		STM32_FUNCTION(12, "ETH_MII_RX_ER"),
+		STM32_FUNCTION(13, "FMC_D31"),
+		STM32_FUNCTION(15, "LCD_HSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(139, "PI11"),
+		STM32_FUNCTION(0, "GPIOI11"),
+		STM32_FUNCTION(10, "LCD_G6"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_DIR"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(140, "PI12"),
+		STM32_FUNCTION(0, "GPIOI12"),
+		STM32_FUNCTION(15, "LCD_HSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(141, "PI13"),
+		STM32_FUNCTION(0, "GPIOI13"),
+		STM32_FUNCTION(15, "LCD_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(142, "PI14"),
+		STM32_FUNCTION(0, "GPIOI14"),
+		STM32_FUNCTION(15, "LCD_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(143, "PI15"),
+		STM32_FUNCTION(0, "GPIOI15"),
+		STM32_FUNCTION(10, "LCD_G2"),
+		STM32_FUNCTION(15, "LCD_R0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(144, "PJ0"),
+		STM32_FUNCTION(0, "GPIOJ0"),
+		STM32_FUNCTION(10, "LCD_R7"),
+		STM32_FUNCTION(15, "LCD_R1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(145, "PJ1"),
+		STM32_FUNCTION(0, "GPIOJ1"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(146, "PJ2"),
+		STM32_FUNCTION(0, "GPIOJ2"),
+		STM32_FUNCTION(14, "DSIHOST_TE"),
+		STM32_FUNCTION(15, "LCD_R3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(147, "PJ3"),
+		STM32_FUNCTION(0, "GPIOJ3"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(148, "PJ4"),
+		STM32_FUNCTION(0, "GPIOJ4"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(149, "PJ5"),
+		STM32_FUNCTION(0, "GPIOJ5"),
+		STM32_FUNCTION(15, "LCD_R6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(156, "PJ12"),
+		STM32_FUNCTION(0, "GPIOJ12"),
+		STM32_FUNCTION(10, "LCD_G3"),
+		STM32_FUNCTION(15, "LCD_B0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(157, "PJ13"),
+		STM32_FUNCTION(0, "GPIOJ13"),
+		STM32_FUNCTION(10, "LCD_G4"),
+		STM32_FUNCTION(15, "LCD_B1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(158, "PJ14"),
+		STM32_FUNCTION(0, "GPIOJ14"),
+		STM32_FUNCTION(15, "LCD_B2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(159, "PJ15"),
+		STM32_FUNCTION(0, "GPIOJ15"),
+		STM32_FUNCTION(15, "LCD_B3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(163, "PK3"),
+		STM32_FUNCTION(0, "GPIOK3"),
+		STM32_FUNCTION(15, "LCD_B4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(164, "PK4"),
+		STM32_FUNCTION(0, "GPIOK4"),
+		STM32_FUNCTION(15, "LCD_B5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(165, "PK5"),
+		STM32_FUNCTION(0, "GPIOK5"),
+		STM32_FUNCTION(15, "LCD_B6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(166, "PK6"),
+		STM32_FUNCTION(0, "GPIOK6"),
+		STM32_FUNCTION(15, "LCD_B7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(167, "PK7"),
+		STM32_FUNCTION(0, "GPIOK7"),
+		STM32_FUNCTION(15, "LCD_DE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+};
+
+static struct stm32_pinctrl_match_data stm32f469_match_data = {
+	.pins = stm32f469_pins,
+	.npins = ARRAY_SIZE(stm32f469_pins),
+};
+
+static const struct of_device_id stm32f469_pctrl_match[] = {
+	{
+		.compatible = "st,stm32f469-pinctrl",
+		.data = &stm32f469_match_data,
+	},
+	{ }
+};
+
+static struct platform_driver stm32f469_pinctrl_driver = {
+	.probe = stm32_pctl_probe,
+	.driver = {
+		.name = "stm32f469-pinctrl",
+		.of_match_table = stm32f469_pctrl_match,
+	},
+};
+
+static int __init stm32f469_pinctrl_init(void)
+{
+	return platform_driver_register(&stm32f469_pinctrl_driver);
+}
+arch_initcall(stm32f469_pinctrl_init);
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32f746.c b/drivers/pinctrl/stm32/pinctrl-stm32f746.c
index c0b4462ce97e..a2fae7357c36 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32f746.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32f746.c
@@ -1678,4 +1678,9 @@ static struct platform_driver stm32f746_pinctrl_driver = {
 		.of_match_table = stm32f746_pctrl_match,
 	},
 };
-builtin_platform_driver(stm32f746_pinctrl_driver);
+
+static int __init stm32f746_pinctrl_init(void)
+{
+	return platform_driver_register(&stm32f746_pinctrl_driver);
+}
+arch_initcall(stm32f746_pinctrl_init);
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32h743.c b/drivers/pinctrl/stm32/pinctrl-stm32h743.c
index f7f9eacd3768..e34b2b9217ce 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32h743.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32h743.c
@@ -1977,4 +1977,8 @@ static struct platform_driver stm32h743_pinctrl_driver = {
 	},
 };
 
-builtin_platform_driver(stm32h743_pinctrl_driver);
+static int __init stm32h743_pinctrl_init(void)
+{
+	return platform_driver_register(&stm32h743_pinctrl_driver);
+}
+arch_initcall(stm32h743_pinctrl_init);
diff --git a/drivers/pinctrl/sunxi/Kconfig b/drivers/pinctrl/sunxi/Kconfig
index 816015cf7053..793e6f94fa0b 100644
--- a/drivers/pinctrl/sunxi/Kconfig
+++ b/drivers/pinctrl/sunxi/Kconfig
@@ -4,6 +4,7 @@ config PINCTRL_SUNXI
 	bool
 	select PINMUX
 	select GENERIC_PINCONF
+	select GPIOLIB
 
 config PINCTRL_SUN4I_A10
 	def_bool MACH_SUN4I
@@ -48,8 +49,8 @@ config PINCTRL_SUN8I_H3
 	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_H3_R
-	def_bool MACH_SUN8I
-	select PINCTRL_SUNXI_COMMON
+	def_bool MACH_SUN8I || (ARM64 && ARCH_SUNXI)
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_V3S
 	def_bool MACH_SUN8I
@@ -65,11 +66,15 @@ config PINCTRL_SUN9I_A80_R
 	select PINCTRL_SUNXI
 
 config PINCTRL_SUN50I_A64
-	bool
+	def_bool ARM64 && ARCH_SUNXI
+	select PINCTRL_SUNXI
+
+config PINCTRL_SUN50I_A64_R
+	def_bool ARM64 && ARCH_SUNXI
 	select PINCTRL_SUNXI
 
 config PINCTRL_SUN50I_H5
-	bool
+	def_bool ARM64 && ARCH_SUNXI
 	select PINCTRL_SUNXI
 
 endif
diff --git a/drivers/pinctrl/sunxi/Makefile b/drivers/pinctrl/sunxi/Makefile
index 04ccb88ebd5f..df4ccd6cd44c 100644
--- a/drivers/pinctrl/sunxi/Makefile
+++ b/drivers/pinctrl/sunxi/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_PINCTRL_SUN8I_A23)		+= pinctrl-sun8i-a23.o
 obj-$(CONFIG_PINCTRL_SUN8I_A23_R)	+= pinctrl-sun8i-a23-r.o
 obj-$(CONFIG_PINCTRL_SUN8I_A33)		+= pinctrl-sun8i-a33.o
 obj-$(CONFIG_PINCTRL_SUN50I_A64)	+= pinctrl-sun50i-a64.o
+obj-$(CONFIG_PINCTRL_SUN50I_A64_R)	+= pinctrl-sun50i-a64-r.o
 obj-$(CONFIG_PINCTRL_SUN8I_A83T)	+= pinctrl-sun8i-a83t.o
 obj-$(CONFIG_PINCTRL_SUN8I_H3)		+= pinctrl-sun8i-h3.o
 obj-$(CONFIG_PINCTRL_SUN8I_H3_R)	+= pinctrl-sun8i-h3-r.o
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-a64-r.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-a64-r.c
new file mode 100644
index 000000000000..e69c8dae121a
--- /dev/null
+++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-a64-r.c
@@ -0,0 +1,125 @@
+/*
+ * Allwinner A64 SoCs special pins pinctrl driver.
+ *
+ * Based on pinctrl-sun8i-a23-r.c
+ *
+ * Copyright (C) 2016 Icenowy Zheng
+ * Icenowy Zheng <icenowy@aosc.xyz>
+ *
+ * Copyright (C) 2014 Chen-Yu Tsai
+ * Chen-Yu Tsai <wens@csie.org>
+ *
+ * Copyright (C) 2014 Boris Brezillon
+ * Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * Copyright (C) 2014 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "pinctrl-sunxi.h"
+
+static const struct sunxi_desc_pin sun50i_a64_r_pins[] = {
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_rsb"),		/* SCK */
+		  SUNXI_FUNCTION(0x3, "s_i2c"),		/* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 0)),	/* PL_EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_rsb"),		/* SDA */
+		  SUNXI_FUNCTION(0x3, "s_i2c"),		/* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 1)),	/* PL_EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_uart"),	/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 2)),	/* PL_EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_uart"),	/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 3)),	/* PL_EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),	/* MS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 4)),	/* PL_EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),	/* CK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 5)),	/* PL_EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),	/* DO */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 6)),	/* PL_EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),	/* DI */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 7)),	/* PL_EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2c"),		/* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 8)),	/* PL_EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2c"),		/* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 9)),	/* PL_EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_pwm"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 10)),	/* PL_EINT10 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_cir_rx"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 11)),	/* PL_EINT11 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 12)),	/* PL_EINT12 */
+};
+
+static const struct sunxi_pinctrl_desc sun50i_a64_r_pinctrl_data = {
+	.pins = sun50i_a64_r_pins,
+	.npins = ARRAY_SIZE(sun50i_a64_r_pins),
+	.pin_base = PL_BASE,
+	.irq_banks = 1,
+};
+
+static int sun50i_a64_r_pinctrl_probe(struct platform_device *pdev)
+{
+	return sunxi_pinctrl_init(pdev,
+				  &sun50i_a64_r_pinctrl_data);
+}
+
+static const struct of_device_id sun50i_a64_r_pinctrl_match[] = {
+	{ .compatible = "allwinner,sun50i-a64-r-pinctrl", },
+	{}
+};
+
+static struct platform_driver sun50i_a64_r_pinctrl_driver = {
+	.probe	= sun50i_a64_r_pinctrl_probe,
+	.driver	= {
+		.name		= "sun50i-a64-r-pinctrl",
+		.of_match_table	= sun50i_a64_r_pinctrl_match,
+	},
+};
+builtin_platform_driver(sun50i_a64_r_pinctrl_driver);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 60e6e36c4a7e..58774acfc814 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -581,11 +581,11 @@ static int sunxi_pconf_group_set(struct pinctrl_dev *pctldev,
 			return -ENOTSUPP;
 		}
 
-		spin_lock_irqsave(&pctl->lock, flags);
+		raw_spin_lock_irqsave(&pctl->lock, flags);
 		reg = readl(pctl->membase + offset);
 		reg &= ~(mask << shift);
 		writel(reg | val << shift, pctl->membase + offset);
-		spin_unlock_irqrestore(&pctl->lock, flags);
+		raw_spin_unlock_irqrestore(&pctl->lock, flags);
 	} /* for each config */
 
 	return 0;
@@ -634,7 +634,7 @@ static void sunxi_pmx_set(struct pinctrl_dev *pctldev,
 	unsigned long flags;
 	u32 val, mask;
 
-	spin_lock_irqsave(&pctl->lock, flags);
+	raw_spin_lock_irqsave(&pctl->lock, flags);
 
 	pin -= pctl->desc->pin_base;
 	val = readl(pctl->membase + sunxi_mux_reg(pin));
@@ -642,7 +642,7 @@ static void sunxi_pmx_set(struct pinctrl_dev *pctldev,
 	writel((val & ~mask) | config << sunxi_mux_offset(pin),
 		pctl->membase + sunxi_mux_reg(pin));
 
-	spin_unlock_irqrestore(&pctl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 }
 
 static int sunxi_pmx_set_mux(struct pinctrl_dev *pctldev,
@@ -733,7 +733,7 @@ static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip,
 	unsigned long flags;
 	u32 regval;
 
-	spin_lock_irqsave(&pctl->lock, flags);
+	raw_spin_lock_irqsave(&pctl->lock, flags);
 
 	regval = readl(pctl->membase + reg);
 
@@ -744,7 +744,7 @@ static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip,
 
 	writel(regval, pctl->membase + reg);
 
-	spin_unlock_irqrestore(&pctl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 }
 
 static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip,
@@ -856,7 +856,7 @@ static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&pctl->lock, flags);
+	raw_spin_lock_irqsave(&pctl->lock, flags);
 
 	if (type & IRQ_TYPE_LEVEL_MASK)
 		irq_set_chip_handler_name_locked(d, &sunxi_pinctrl_level_irq_chip,
@@ -869,7 +869,7 @@ static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type)
 	regval &= ~(IRQ_CFG_IRQ_MASK << index);
 	writel(regval | (mode << index), pctl->membase + reg);
 
-	spin_unlock_irqrestore(&pctl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 
 	return 0;
 }
@@ -893,13 +893,13 @@ static void sunxi_pinctrl_irq_mask(struct irq_data *d)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&pctl->lock, flags);
+	raw_spin_lock_irqsave(&pctl->lock, flags);
 
 	/* Mask the IRQ */
 	val = readl(pctl->membase + reg);
 	writel(val & ~(1 << idx), pctl->membase + reg);
 
-	spin_unlock_irqrestore(&pctl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 }
 
 static void sunxi_pinctrl_irq_unmask(struct irq_data *d)
@@ -910,13 +910,13 @@ static void sunxi_pinctrl_irq_unmask(struct irq_data *d)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&pctl->lock, flags);
+	raw_spin_lock_irqsave(&pctl->lock, flags);
 
 	/* Unmask the IRQ */
 	val = readl(pctl->membase + reg);
 	writel(val | (1 << idx), pctl->membase + reg);
 
-	spin_unlock_irqrestore(&pctl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 }
 
 static void sunxi_pinctrl_irq_ack_unmask(struct irq_data *d)
@@ -1253,7 +1253,7 @@ int sunxi_pinctrl_init_with_variant(struct platform_device *pdev,
 		return -ENOMEM;
 	platform_set_drvdata(pdev, pctl);
 
-	spin_lock_init(&pctl->lock);
+	raw_spin_lock_init(&pctl->lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pctl->membase = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
index e1aedd260b2e..a9d315a1256c 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
@@ -134,7 +134,7 @@ struct sunxi_pinctrl {
 	unsigned			ngroups;
 	int				*irq;
 	unsigned			*irq_array;
-	spinlock_t			lock;
+	raw_spinlock_t			lock;
 	struct pinctrl_dev		*pctl_dev;
 	unsigned long			variant;
 };
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra-xusb.c b/drivers/pinctrl/tegra/pinctrl-tegra-xusb.c
index 6f68a9eebc58..ebedc2d32411 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra-xusb.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra-xusb.c
@@ -873,6 +873,10 @@ static const struct of_device_id tegra_xusb_padctl_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, tegra_xusb_padctl_of_match);
 
+/* predeclare these in order to silence sparse */
+int tegra_xusb_padctl_legacy_probe(struct platform_device *pdev);
+int tegra_xusb_padctl_legacy_remove(struct platform_device *pdev);
+
 int tegra_xusb_padctl_legacy_probe(struct platform_device *pdev)
 {
 	struct tegra_xusb_padctl *padctl;
diff --git a/drivers/pinctrl/ti/Kconfig b/drivers/pinctrl/ti/Kconfig
index 815a88673d38..542077069391 100644
--- a/drivers/pinctrl/ti/Kconfig
+++ b/drivers/pinctrl/ti/Kconfig
@@ -1,6 +1,6 @@
 config PINCTRL_TI_IODELAY
 	tristate "TI IODelay Module pinconf driver"
-	depends on OF
+	depends on OF && (SOC_DRA7XX || COMPILE_TEST)
 	select GENERIC_PINCTRL_GROUPS
 	select GENERIC_PINMUX_FUNCTIONS
 	select GENERIC_PINCONF
diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
index 717e3404900c..362c50918c13 100644
--- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
+++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
@@ -893,6 +893,8 @@ static int ti_iodelay_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, iod);
 
+	return pinctrl_enable(iod->pctl);
+
 exit_out:
 	of_node_put(np);
 	return ret;
diff --git a/drivers/pinctrl/uniphier/Kconfig b/drivers/pinctrl/uniphier/Kconfig
index e077a9ec23d9..e5826eaa7170 100644
--- a/drivers/pinctrl/uniphier/Kconfig
+++ b/drivers/pinctrl/uniphier/Kconfig
@@ -9,35 +9,35 @@ menuconfig PINCTRL_UNIPHIER
 if PINCTRL_UNIPHIER
 
 config PINCTRL_UNIPHIER_LD4
-	tristate "UniPhier PH1-LD4 SoC pinctrl driver"
+	bool "UniPhier LD4 SoC pinctrl driver"
 	default ARM
 
 config PINCTRL_UNIPHIER_PRO4
-	tristate "UniPhier PH1-Pro4 SoC pinctrl driver"
+	bool "UniPhier Pro4 SoC pinctrl driver"
 	default ARM
 
 config PINCTRL_UNIPHIER_SLD8
-	tristate "UniPhier PH1-sLD8 SoC pinctrl driver"
+	bool "UniPhier sLD8 SoC pinctrl driver"
 	default ARM
 
 config PINCTRL_UNIPHIER_PRO5
-	tristate "UniPhier PH1-Pro5 SoC pinctrl driver"
+	bool "UniPhier Pro5 SoC pinctrl driver"
 	default ARM
 
 config PINCTRL_UNIPHIER_PXS2
-	tristate "UniPhier ProXstream2 SoC pinctrl driver"
+	bool "UniPhier PXs2 SoC pinctrl driver"
 	default ARM
 
 config PINCTRL_UNIPHIER_LD6B
-	tristate "UniPhier PH1-LD6b SoC pinctrl driver"
+	bool "UniPhier LD6b SoC pinctrl driver"
 	default ARM
 
 config PINCTRL_UNIPHIER_LD11
-	tristate "UniPhier PH1-LD11 SoC pinctrl driver"
+	bool "UniPhier LD11 SoC pinctrl driver"
 	default ARM64
 
 config PINCTRL_UNIPHIER_LD20
-	tristate "UniPhier PH1-LD20 SoC pinctrl driver"
+	bool "UniPhier LD20 SoC pinctrl driver"
 	default ARM64
 
 endif
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c
index 546f23c9040c..30dec0ee7f35 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -26,11 +27,18 @@
 #include "../pinctrl-utils.h"
 #include "pinctrl-uniphier.h"
 
+#define UNIPHIER_PINCTRL_PINMUX_BASE	0x1000
+#define UNIPHIER_PINCTRL_LOAD_PINMUX	0x1700
+#define UNIPHIER_PINCTRL_DRVCTRL_BASE	0x1800
+#define UNIPHIER_PINCTRL_DRV2CTRL_BASE	0x1900
+#define UNIPHIER_PINCTRL_DRV3CTRL_BASE	0x1980
+#define UNIPHIER_PINCTRL_PUPDCTRL_BASE	0x1a00
+#define UNIPHIER_PINCTRL_IECTRL		0x1d00
+
 struct uniphier_pinctrl_priv {
 	struct pinctrl_desc pctldesc;
 	struct pinctrl_dev *pctldev;
 	struct regmap *regmap;
-	unsigned int regbase;
 	struct uniphier_pinctrl_socdata *socdata;
 };
 
@@ -171,7 +179,7 @@ static int uniphier_conf_pin_bias_get(struct pinctrl_dev *pctldev,
 	reg = UNIPHIER_PINCTRL_PUPDCTRL_BASE + pupdctrl / 32 * 4;
 	shift = pupdctrl % 32;
 
-	ret = regmap_read(priv->regmap, priv->regbase + reg, &val);
+	ret = regmap_read(priv->regmap, reg, &val);
 	if (ret)
 		return ret;
 
@@ -231,7 +239,7 @@ static int uniphier_conf_pin_drive_get(struct pinctrl_dev *pctldev,
 	shift = drvctrl % 32;
 	mask = (1U << width) - 1;
 
-	ret = regmap_read(priv->regmap, priv->regbase + reg, &val);
+	ret = regmap_read(priv->regmap, reg, &val);
 	if (ret)
 		return ret;
 
@@ -252,8 +260,7 @@ static int uniphier_conf_pin_input_enable_get(struct pinctrl_dev *pctldev,
 		/* This pin is always input-enabled. */
 		return 0;
 
-	ret = regmap_read(priv->regmap,
-			  priv->regbase + UNIPHIER_PINCTRL_IECTRL, &val);
+	ret = regmap_read(priv->regmap, UNIPHIER_PINCTRL_IECTRL, &val);
 	if (ret)
 		return ret;
 
@@ -366,8 +373,7 @@ static int uniphier_conf_pin_bias_set(struct pinctrl_dev *pctldev,
 	reg = UNIPHIER_PINCTRL_PUPDCTRL_BASE + pupdctrl / 32 * 4;
 	shift = pupdctrl % 32;
 
-	return regmap_update_bits(priv->regmap, priv->regbase + reg,
-				  1 << shift, val << shift);
+	return regmap_update_bits(priv->regmap, reg, 1 << shift, val << shift);
 }
 
 static int uniphier_conf_pin_drive_set(struct pinctrl_dev *pctldev,
@@ -427,7 +433,7 @@ static int uniphier_conf_pin_drive_set(struct pinctrl_dev *pctldev,
 	shift = drvctrl % 32;
 	mask = (1U << width) - 1;
 
-	return regmap_update_bits(priv->regmap, priv->regbase + reg,
+	return regmap_update_bits(priv->regmap, reg,
 				  mask << shift, val << shift);
 }
 
@@ -451,7 +457,7 @@ static int uniphier_conf_pin_input_enable(struct pinctrl_dev *pctldev,
 	if (iectrl == UNIPHIER_PIN_IECTRL_NONE)
 		return enable ? 0 : -EINVAL;
 
-	reg = priv->regbase + UNIPHIER_PINCTRL_IECTRL + iectrl / 32 * 4;
+	reg = UNIPHIER_PINCTRL_IECTRL + iectrl / 32 * 4;
 	mask = BIT(iectrl % 32);
 
 	return regmap_update_bits(priv->regmap, reg, mask, enable ? mask : 0);
@@ -601,7 +607,7 @@ static int uniphier_pmx_set_one_mux(struct pinctrl_dev *pctldev, unsigned pin,
 	 * stored in the offset+4.
 	 */
 	for (; reg < reg_end; reg += 4) {
-		ret = regmap_update_bits(priv->regmap, priv->regbase + reg,
+		ret = regmap_update_bits(priv->regmap, reg,
 					 mask << shift, muxval << shift);
 		if (ret)
 			return ret;
@@ -610,8 +616,7 @@ static int uniphier_pmx_set_one_mux(struct pinctrl_dev *pctldev, unsigned pin,
 
 	if (load_pinctrl) {
 		ret = regmap_write(priv->regmap,
-				   priv->regbase + UNIPHIER_PINCTRL_LOAD_PINMUX,
-				   1);
+				   UNIPHIER_PINCTRL_LOAD_PINMUX, 1);
 		if (ret)
 			return ret;
 	}
@@ -698,20 +703,9 @@ int uniphier_pinctrl_probe(struct platform_device *pdev,
 	if (!priv)
 		return -ENOMEM;
 
-	if (of_device_is_compatible(dev->of_node, "socionext,ph1-ld4-pinctrl") ||
-	    of_device_is_compatible(dev->of_node, "socionext,ph1-pro4-pinctrl") ||
-	    of_device_is_compatible(dev->of_node, "socionext,ph1-sld8-pinctrl") ||
-	    of_device_is_compatible(dev->of_node, "socionext,ph1-pro5-pinctrl") ||
-	    of_device_is_compatible(dev->of_node, "socionext,proxstream2-pinctrl") ||
-	    of_device_is_compatible(dev->of_node, "socionext,ph1-ld6b-pinctrl")) {
-		/* old binding */
-		priv->regmap = syscon_node_to_regmap(dev->of_node);
-	} else {
-		priv->regbase = 0x1000;
-		parent = of_get_parent(dev->of_node);
-		priv->regmap = syscon_node_to_regmap(parent);
-		of_node_put(parent);
-	}
+	parent = of_get_parent(dev->of_node);
+	priv->regmap = syscon_node_to_regmap(parent);
+	of_node_put(parent);
 
 	if (IS_ERR(priv->regmap)) {
 		dev_err(dev, "failed to get regmap\n");
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
index 77a0236ee781..706effe0a492 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2016 Socionext Inc.
+ * Copyright (C) 2016-2017 Socionext Inc.
  *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -14,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -390,22 +390,22 @@ static const struct pinctrl_pin_desc uniphier_ld11_pins[] = {
 	UNIPHIER_PINCTRL_PIN(140, "AO1D0", 140,
 			     140, UNIPHIER_PIN_DRV_1BIT,
 			     140, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(141, "TCON0", 141,
+	UNIPHIER_PINCTRL_PIN(141, "AO1D1", 141,
 			     141, UNIPHIER_PIN_DRV_1BIT,
 			     141, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(142, "TCON1", 142,
+	UNIPHIER_PINCTRL_PIN(142, "AO1D2", 142,
 			     142, UNIPHIER_PIN_DRV_1BIT,
 			     142, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(143, "TCON2", 143,
+	UNIPHIER_PINCTRL_PIN(143, "XIRQ9", 143,
 			     143, UNIPHIER_PIN_DRV_1BIT,
 			     143, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(144, "TCON3", 144,
+	UNIPHIER_PINCTRL_PIN(144, "XIRQ10", 144,
 			     144, UNIPHIER_PIN_DRV_1BIT,
 			     144, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(145, "TCON4", 145,
+	UNIPHIER_PINCTRL_PIN(145, "XIRQ11", 145,
 			     145, UNIPHIER_PIN_DRV_1BIT,
 			     145, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(146, "TCON5", 146,
+	UNIPHIER_PINCTRL_PIN(146, "XIRQ13", 146,
 			     146, UNIPHIER_PIN_DRV_1BIT,
 			     146, UNIPHIER_PIN_PULL_DOWN),
 	UNIPHIER_PINCTRL_PIN(147, "PWMA", 147,
@@ -936,7 +936,6 @@ static const struct of_device_id uniphier_ld11_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-ld11-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_ld11_pinctrl_match);
 
 static struct platform_driver uniphier_ld11_pinctrl_driver = {
 	.probe = uniphier_ld11_pinctrl_probe,
@@ -945,8 +944,4 @@ static struct platform_driver uniphier_ld11_pinctrl_driver = {
 		.of_match_table = uniphier_ld11_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_ld11_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-LD11 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_ld11_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
index 96686336e3a3..c8d18a2d3a88 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2016 Socionext Inc.
+ * Copyright (C) 2016-2017 Socionext Inc.
  *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -14,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -1034,7 +1034,6 @@ static const struct of_device_id uniphier_ld20_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-ld20-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_ld20_pinctrl_match);
 
 static struct platform_driver uniphier_ld20_pinctrl_driver = {
 	.probe = uniphier_ld20_pinctrl_probe,
@@ -1043,8 +1042,4 @@ static struct platform_driver uniphier_ld20_pinctrl_driver = {
 		.of_match_table = uniphier_ld20_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_ld20_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-LD20 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_ld20_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
index 3edfb6f9d6df..8f2ad1c4c6f4 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -13,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -929,10 +930,8 @@ static int uniphier_ld4_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id uniphier_ld4_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-ld4-pinctrl" },
-	{ .compatible = "socionext,ph1-ld4-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_ld4_pinctrl_match);
 
 static struct platform_driver uniphier_ld4_pinctrl_driver = {
 	.probe = uniphier_ld4_pinctrl_probe,
@@ -941,8 +940,4 @@ static struct platform_driver uniphier_ld4_pinctrl_driver = {
 		.of_match_table = uniphier_ld4_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_ld4_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-LD4 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_ld4_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
index 708e5100cf34..8a0da937b670 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -13,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -1290,10 +1291,8 @@ static int uniphier_ld6b_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id uniphier_ld6b_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-ld6b-pinctrl" },
-	{ .compatible = "socionext,ph1-ld6b-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_ld6b_pinctrl_match);
 
 static struct platform_driver uniphier_ld6b_pinctrl_driver = {
 	.probe = uniphier_ld6b_pinctrl_probe,
@@ -1302,8 +1301,4 @@ static struct platform_driver uniphier_ld6b_pinctrl_driver = {
 		.of_match_table = uniphier_ld6b_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_ld6b_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-LD6b pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_ld6b_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
index c306e844f584..a433a306a2d0 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -13,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -1600,10 +1601,8 @@ static int uniphier_pro4_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id uniphier_pro4_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-pro4-pinctrl" },
-	{ .compatible = "socionext,ph1-pro4-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_pro4_pinctrl_match);
 
 static struct platform_driver uniphier_pro4_pinctrl_driver = {
 	.probe = uniphier_pro4_pinctrl_probe,
@@ -1612,8 +1611,4 @@ static struct platform_driver uniphier_pro4_pinctrl_driver = {
 		.of_match_table = uniphier_pro4_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_pro4_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-Pro4 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_pro4_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
index 55d4a12282a0..04d00c398eaf 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -13,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -1365,10 +1366,8 @@ static int uniphier_pro5_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id uniphier_pro5_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-pro5-pinctrl" },
-	{ .compatible = "socionext,ph1-pro5-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_pro5_pinctrl_match);
 
 static struct platform_driver uniphier_pro5_pinctrl_driver = {
 	.probe = uniphier_pro5_pinctrl_probe,
@@ -1377,8 +1376,4 @@ static struct platform_driver uniphier_pro5_pinctrl_driver = {
 		.of_match_table = uniphier_pro5_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_pro5_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-Pro5 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_pro5_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
index 85ca5e2d8a9c..53b6b774654e 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -13,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -1277,10 +1278,8 @@ static int uniphier_pxs2_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id uniphier_pxs2_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-pxs2-pinctrl" },
-	{ .compatible = "socionext,proxstream2-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_pxs2_pinctrl_match);
 
 static struct platform_driver uniphier_pxs2_pinctrl_driver = {
 	.probe = uniphier_pxs2_pinctrl_probe,
@@ -1289,8 +1288,4 @@ static struct platform_driver uniphier_pxs2_pinctrl_driver = {
 		.of_match_table = uniphier_pxs2_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_pxs2_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier ProXstream2 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_pxs2_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
index da689d880f46..37deaf615dcf 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -13,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/platform_device.h>
 
@@ -856,10 +857,8 @@ static int uniphier_sld8_pinctrl_probe(struct platform_device *pdev)
 
 static const struct of_device_id uniphier_sld8_pinctrl_match[] = {
 	{ .compatible = "socionext,uniphier-sld8-pinctrl" },
-	{ .compatible = "socionext,ph1-sld8-pinctrl" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, uniphier_sld8_pinctrl_match);
 
 static struct platform_driver uniphier_sld8_pinctrl_driver = {
 	.probe = uniphier_sld8_pinctrl_probe,
@@ -868,8 +867,4 @@ static struct platform_driver uniphier_sld8_pinctrl_driver = {
 		.of_match_table = uniphier_sld8_pinctrl_match,
 	},
 };
-module_platform_driver(uniphier_sld8_pinctrl_driver);
-
-MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PH1-sLD8 pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(uniphier_sld8_pinctrl_driver);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier.h b/drivers/pinctrl/uniphier/pinctrl-uniphier.h
index 923f36cb245d..6f2f33bf788f 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier.h
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier.h
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ * Copyright (C) 2015-2017 Socionext Inc.
+ *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -22,14 +23,6 @@
 
 struct platform_device;
 
-#define UNIPHIER_PINCTRL_PINMUX_BASE	0x0
-#define UNIPHIER_PINCTRL_LOAD_PINMUX	0x700
-#define UNIPHIER_PINCTRL_DRVCTRL_BASE	0x800
-#define UNIPHIER_PINCTRL_DRV2CTRL_BASE	0x900
-#define UNIPHIER_PINCTRL_DRV3CTRL_BASE	0x980
-#define UNIPHIER_PINCTRL_PUPDCTRL_BASE	0xa00
-#define UNIPHIER_PINCTRL_IECTRL		0xd00
-
 /* input enable control register bit */
 #define UNIPHIER_PIN_IECTRL_SHIFT	0
 #define UNIPHIER_PIN_IECTRL_BITS	8
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 4bc88eb52712..e1bffc9bb194 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -141,6 +141,14 @@ config DELL_WMI_AIO
 	  To compile this driver as a module, choose M here: the module will
 	  be called dell-wmi-aio.
 
+config DELL_WMI_LED
+	tristate "External LED on Dell Business Netbooks"
+	depends on LEDS_CLASS
+	depends on ACPI_WMI
+	help
+	  This adds support for the Latitude 2100 and similar
+	  notebooks that have an external LED.
+
 config DELL_SMO8800
 	tristate "Dell Latitude freefall driver (ACPI SMO88XX)"
 	depends on ACPI
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 299d0f9e40f7..776b3a7a4984 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_DELL_SMBIOS)	+= dell-smbios.o
 obj-$(CONFIG_DELL_LAPTOP)	+= dell-laptop.o
 obj-$(CONFIG_DELL_WMI)		+= dell-wmi.o
 obj-$(CONFIG_DELL_WMI_AIO)	+= dell-wmi-aio.o
+obj-$(CONFIG_DELL_WMI_LED)	+= dell-wmi-led.o
 obj-$(CONFIG_DELL_SMO8800)	+= dell-smo8800.o
 obj-$(CONFIG_DELL_RBTN)		+= dell-rbtn.o
 obj-$(CONFIG_ACER_WMI)		+= acer-wmi.o
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 5be4783e40d4..dea98ffb6f60 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -103,15 +103,6 @@ static struct quirk_entry quirk_asus_x200ca = {
 	.wapf = 2,
 };
 
-static struct quirk_entry quirk_no_rfkill = {
-	.no_rfkill = true,
-};
-
-static struct quirk_entry quirk_no_rfkill_wapf4 = {
-	.wapf = 4,
-	.no_rfkill = true,
-};
-
 static struct quirk_entry quirk_asus_ux303ub = {
 	.wmi_backlight_native = true,
 };
@@ -194,7 +185,7 @@ static const struct dmi_system_id asus_quirks[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "X456UA"),
 		},
-		.driver_data = &quirk_no_rfkill_wapf4,
+		.driver_data = &quirk_asus_wapf4,
 	},
 	{
 		.callback = dmi_matched,
@@ -203,7 +194,7 @@ static const struct dmi_system_id asus_quirks[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "X456UF"),
 		},
-		.driver_data = &quirk_no_rfkill_wapf4,
+		.driver_data = &quirk_asus_wapf4,
 	},
 	{
 		.callback = dmi_matched,
@@ -369,42 +360,6 @@ static const struct dmi_system_id asus_quirks[] = {
 	},
 	{
 		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. X555UB",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X555UB"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. N552VW",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N552VW"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. U303LB",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "U303LB"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. Z550MA",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Z550MA"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
 		.ident = "ASUSTeK COMPUTER INC. UX303UB",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 43cb680adbb4..8fe5890bf539 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -159,6 +159,8 @@ MODULE_LICENSE("GPL");
 #define USB_INTEL_XUSB2PR		0xD0
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI	0x9c31
 
+static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
+
 struct bios_args {
 	u32 arg0;
 	u32 arg1;
@@ -2051,6 +2053,16 @@ static int asus_wmi_fan_init(struct asus_wmi *asus)
 	return 0;
 }
 
+static bool ashs_present(void)
+{
+	int i = 0;
+	while (ashs_ids[i]) {
+		if (acpi_dev_found(ashs_ids[i++]))
+			return true;
+	}
+	return false;
+}
+
 /*
  * WMI Driver
  */
@@ -2095,7 +2107,11 @@ static int asus_wmi_add(struct platform_device *pdev)
 	if (err)
 		goto fail_leds;
 
-	if (!asus->driver->quirks->no_rfkill) {
+	asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
+	if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
+		asus->driver->wlan_ctrl_by_user = 1;
+
+	if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) {
 		err = asus_wmi_rfkill_init(asus);
 		if (err)
 			goto fail_rfkill;
@@ -2134,10 +2150,6 @@ static int asus_wmi_add(struct platform_device *pdev)
 	if (err)
 		goto fail_debugfs;
 
-	asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
-	if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
-		asus->driver->wlan_ctrl_by_user = 1;
-
 	return 0;
 
 fail_debugfs:
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index fdff626c3b51..c9589d9342bb 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -39,7 +39,6 @@ struct key_entry;
 struct asus_wmi;
 
 struct quirk_entry {
-	bool no_rfkill;
 	bool hotplug_wireless;
 	bool scalar_panel_brightness;
 	bool store_backlight_power;
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index f57dd282a002..2e237bad4995 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/i8042.h>
 #include <linux/debugfs.h>
+#include <linux/dell-led.h>
 #include <linux/seq_file.h>
 #include <acpi/video.h>
 #include "dell-rbtn.h"
@@ -42,6 +43,8 @@
 #define KBD_LED_AUTO_50_TOKEN 0x02EB
 #define KBD_LED_AUTO_75_TOKEN 0x02EC
 #define KBD_LED_AUTO_100_TOKEN 0x02F6
+#define GLOBAL_MIC_MUTE_ENABLE 0x0364
+#define GLOBAL_MIC_MUTE_DISABLE 0x0365
 
 struct quirk_entry {
 	u8 touchpad_led;
@@ -1978,6 +1981,31 @@ static void kbd_led_exit(void)
 	led_classdev_unregister(&kbd_led);
 }
 
+int dell_micmute_led_set(int state)
+{
+	struct calling_interface_buffer *buffer;
+	struct calling_interface_token *token;
+
+	if (state == 0)
+		token = dell_smbios_find_token(GLOBAL_MIC_MUTE_DISABLE);
+	else if (state == 1)
+		token = dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE);
+	else
+		return -EINVAL;
+
+	if (!token)
+		return -ENODEV;
+
+	buffer = dell_smbios_get_buffer();
+	buffer->input[0] = token->location;
+	buffer->input[1] = token->value;
+	dell_smbios_send_request(1, 0);
+	dell_smbios_release_buffer();
+
+	return state;
+}
+EXPORT_SYMBOL_GPL(dell_micmute_led_set);
+
 static int __init dell_init(void)
 {
 	struct calling_interface_buffer *buffer;
diff --git a/drivers/leds/dell-led.c b/drivers/platform/x86/dell-wmi-led.c
index b3d6e9c15cf9..a0c7e99530ef 100644
--- a/drivers/leds/dell-led.c
+++ b/drivers/platform/x86/dell-wmi-led.c
@@ -1,6 +1,4 @@
 /*
- * dell_led.c - Dell LED Driver
- *
  * Copyright (C) 2010 Dell Inc.
  * Louis Davis <louis_davis@dell.com>
  * Jim Dailey <jim_dailey@dell.com>
@@ -15,16 +13,12 @@
 #include <linux/leds.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/dmi.h>
-#include <linux/dell-led.h>
-#include "../platform/x86/dell-smbios.h"
 
 MODULE_AUTHOR("Louis Davis/Jim Dailey");
 MODULE_DESCRIPTION("Dell LED Control Driver");
 MODULE_LICENSE("GPL");
 
 #define DELL_LED_BIOS_GUID "F6E4FE6E-909D-47cb-8BAB-C9F6F2F8D396"
-#define DELL_APP_GUID "A80593CE-A997-11DA-B012-B622A1EF5492"
 MODULE_ALIAS("wmi:" DELL_LED_BIOS_GUID);
 
 /* Error Result Codes: */
@@ -43,53 +37,6 @@ MODULE_ALIAS("wmi:" DELL_LED_BIOS_GUID);
 #define CMD_LED_OFF	17
 #define CMD_LED_BLINK	18
 
-#define GLOBAL_MIC_MUTE_ENABLE	0x364
-#define GLOBAL_MIC_MUTE_DISABLE	0x365
-
-static int dell_micmute_led_set(int state)
-{
-	struct calling_interface_buffer *buffer;
-	struct calling_interface_token *token;
-
-	if (!wmi_has_guid(DELL_APP_GUID))
-		return -ENODEV;
-
-	if (state == 0)
-		token = dell_smbios_find_token(GLOBAL_MIC_MUTE_DISABLE);
-	else if (state == 1)
-		token = dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE);
-	else
-		return -EINVAL;
-
-	if (!token)
-		return -ENODEV;
-
-	buffer = dell_smbios_get_buffer();
-	buffer->input[0] = token->location;
-	buffer->input[1] = token->value;
-	dell_smbios_send_request(1, 0);
-	dell_smbios_release_buffer();
-
-	return state;
-}
-
-int dell_app_wmi_led_set(int whichled, int on)
-{
-	int state = 0;
-
-	switch (whichled) {
-	case DELL_LED_MICMUTE:
-		state = dell_micmute_led_set(on);
-		break;
-	default:
-		pr_warn("led type %x is not supported\n", whichled);
-		break;
-	}
-
-	return state;
-}
-EXPORT_SYMBOL_GPL(dell_app_wmi_led_set);
-
 struct bios_args {
 	unsigned char length;
 	unsigned char result_code;
@@ -99,37 +46,29 @@ struct bios_args {
 	unsigned char off_time;
 };
 
-static int dell_led_perform_fn(u8 length,
-		u8 result_code,
-		u8 device_id,
-		u8 command,
-		u8 on_time,
-		u8 off_time)
+static int dell_led_perform_fn(u8 length, u8 result_code, u8 device_id,
+			       u8 command, u8 on_time, u8 off_time)
 {
-	struct bios_args *bios_return;
-	u8 return_code;
-	union acpi_object *obj;
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct bios_args *bios_return;
 	struct acpi_buffer input;
+	union acpi_object *obj;
 	acpi_status status;
+	u8 return_code;
 
-	struct bios_args args;
-	args.length = length;
-	args.result_code = result_code;
-	args.device_id = device_id;
-	args.command = command;
-	args.on_time = on_time;
-	args.off_time = off_time;
+	struct bios_args args = {
+		.length = length,
+		.result_code = result_code,
+		.device_id = device_id,
+		.command = command,
+		.on_time = on_time,
+		.off_time = off_time
+	};
 
 	input.length = sizeof(struct bios_args);
 	input.pointer = &args;
 
-	status = wmi_evaluate_method(DELL_LED_BIOS_GUID,
-		1,
-		1,
-		&input,
-		&output);
-
+	status = wmi_evaluate_method(DELL_LED_BIOS_GUID, 1, 1, &input, &output);
 	if (ACPI_FAILURE(status))
 		return status;
 
@@ -137,7 +76,7 @@ static int dell_led_perform_fn(u8 length,
 
 	if (!obj)
 		return -EINVAL;
-	else if (obj->type != ACPI_TYPE_BUFFER) {
+	if (obj->type != ACPI_TYPE_BUFFER) {
 		kfree(obj);
 		return -EINVAL;
 	}
@@ -170,8 +109,7 @@ static int led_off(void)
 		0);			/* not used */
 }
 
-static int led_blink(unsigned char on_eighths,
-		unsigned char off_eighths)
+static int led_blink(unsigned char on_eighths, unsigned char off_eighths)
 {
 	return dell_led_perform_fn(5,	/* Length of command */
 		INTERFACE_ERROR,	/* Init to  INTERFACE_ERROR */
@@ -182,7 +120,7 @@ static int led_blink(unsigned char on_eighths,
 }
 
 static void dell_led_set(struct led_classdev *led_cdev,
-		enum led_brightness value)
+			 enum led_brightness value)
 {
 	if (value == LED_OFF)
 		led_off();
@@ -191,27 +129,22 @@ static void dell_led_set(struct led_classdev *led_cdev,
 }
 
 static int dell_led_blink(struct led_classdev *led_cdev,
-		unsigned long *delay_on,
-		unsigned long *delay_off)
+			  unsigned long *delay_on, unsigned long *delay_off)
 {
 	unsigned long on_eighths;
 	unsigned long off_eighths;
 
-	/* The Dell LED delay is based on 125ms intervals.
-	   Need to round up to next interval. */
+	/*
+	 * The Dell LED delay is based on 125ms intervals.
+	 * Need to round up to next interval.
+	 */
 
-	on_eighths = (*delay_on + 124) / 125;
-	if (0 == on_eighths)
-		on_eighths = 1;
-	if (on_eighths > 255)
-		on_eighths = 255;
+	on_eighths = DIV_ROUND_UP(*delay_on, 125);
+	on_eighths = clamp_t(unsigned long, on_eighths, 1, 255);
 	*delay_on = on_eighths * 125;
 
-	off_eighths = (*delay_off + 124) / 125;
-	if (0 == off_eighths)
-		off_eighths = 1;
-	if (off_eighths > 255)
-		off_eighths = 255;
+	off_eighths = DIV_ROUND_UP(*delay_off, 125);
+	off_eighths = clamp_t(unsigned long, off_eighths, 1, 255);
 	*delay_off = off_eighths * 125;
 
 	led_blink(on_eighths, off_eighths);
@@ -232,29 +165,21 @@ static int __init dell_led_init(void)
 {
 	int error = 0;
 
-	if (!wmi_has_guid(DELL_LED_BIOS_GUID) && !wmi_has_guid(DELL_APP_GUID))
+	if (!wmi_has_guid(DELL_LED_BIOS_GUID))
 		return -ENODEV;
 
-	if (wmi_has_guid(DELL_LED_BIOS_GUID)) {
-		error = led_off();
-		if (error != 0)
-			return -ENODEV;
-
-		error = led_classdev_register(NULL, &dell_led);
-	}
+	error = led_off();
+	if (error != 0)
+		return -ENODEV;
 
-	return error;
+	return led_classdev_register(NULL, &dell_led);
 }
 
 static void __exit dell_led_exit(void)
 {
-	int error = 0;
+	led_classdev_unregister(&dell_led);
 
-	if (wmi_has_guid(DELL_LED_BIOS_GUID)) {
-		error = led_off();
-		if (error == 0)
-			led_classdev_unregister(&dell_led);
-	}
+	led_off();
 }
 
 module_init(dell_led_init);
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 2b218b1d13e5..e12cc3504d48 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -78,18 +78,18 @@
 
 #define FUJITSU_LCD_N_LEVELS 8
 
-#define ACPI_FUJITSU_CLASS              "fujitsu"
-#define ACPI_FUJITSU_HID                "FUJ02B1"
-#define ACPI_FUJITSU_DRIVER_NAME	"Fujitsu laptop FUJ02B1 ACPI brightness driver"
-#define ACPI_FUJITSU_DEVICE_NAME        "Fujitsu FUJ02B1"
-#define ACPI_FUJITSU_HOTKEY_HID 	"FUJ02E3"
-#define ACPI_FUJITSU_HOTKEY_DRIVER_NAME "Fujitsu laptop FUJ02E3 ACPI hotkeys driver"
-#define ACPI_FUJITSU_HOTKEY_DEVICE_NAME "Fujitsu FUJ02E3"
+#define ACPI_FUJITSU_CLASS		"fujitsu"
+#define ACPI_FUJITSU_BL_HID		"FUJ02B1"
+#define ACPI_FUJITSU_BL_DRIVER_NAME	"Fujitsu laptop FUJ02B1 ACPI brightness driver"
+#define ACPI_FUJITSU_BL_DEVICE_NAME	"Fujitsu FUJ02B1"
+#define ACPI_FUJITSU_LAPTOP_HID		"FUJ02E3"
+#define ACPI_FUJITSU_LAPTOP_DRIVER_NAME	"Fujitsu laptop FUJ02E3 ACPI hotkeys driver"
+#define ACPI_FUJITSU_LAPTOP_DEVICE_NAME	"Fujitsu FUJ02E3"
 
 #define ACPI_FUJITSU_NOTIFY_CODE1     0x80
 
 /* FUNC interface - command values */
-#define FUNC_RFKILL	0x1000
+#define FUNC_FLAGS	0x1000
 #define FUNC_LEDS	0x1001
 #define FUNC_BUTTONS	0x1002
 #define FUNC_BACKLIGHT  0x1004
@@ -97,6 +97,11 @@
 /* FUNC interface - responses */
 #define UNSUPPORTED_CMD 0x80000000
 
+/* FUNC interface - status flags */
+#define FLAG_RFKILL	0x020
+#define FLAG_LID	0x100
+#define FLAG_DOCK	0x200
+
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 /* FUNC interface - LED control */
 #define FUNC_LED_OFF	0x1
@@ -136,7 +141,7 @@
 #endif
 
 /* Device controlling the backlight and associated keys */
-struct fujitsu_t {
+struct fujitsu_bl {
 	acpi_handle acpi_handle;
 	struct acpi_device *dev;
 	struct input_dev *input;
@@ -150,12 +155,12 @@ struct fujitsu_t {
 	unsigned int brightness_level;
 };
 
-static struct fujitsu_t *fujitsu;
+static struct fujitsu_bl *fujitsu_bl;
 static int use_alt_lcd_levels = -1;
 static int disable_brightness_adjust = -1;
 
-/* Device used to access other hotkeys on the laptop */
-struct fujitsu_hotkey_t {
+/* Device used to access hotkeys and other features on the laptop */
+struct fujitsu_laptop {
 	acpi_handle acpi_handle;
 	struct acpi_device *dev;
 	struct input_dev *input;
@@ -163,17 +168,15 @@ struct fujitsu_hotkey_t {
 	struct platform_device *pf_device;
 	struct kfifo fifo;
 	spinlock_t fifo_lock;
-	int rfkill_supported;
-	int rfkill_state;
+	int flags_supported;
+	int flags_state;
 	int logolamp_registered;
 	int kblamps_registered;
 	int radio_led_registered;
 	int eco_led_registered;
 };
 
-static struct fujitsu_hotkey_t *fujitsu_hotkey;
-
-static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event);
+static struct fujitsu_laptop *fujitsu_laptop;
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 static enum led_brightness logolamp_get(struct led_classdev *cdev);
@@ -222,8 +225,6 @@ static struct led_classdev eco_led = {
 static u32 dbg_level = 0x03;
 #endif
 
-static void acpi_fujitsu_notify(struct acpi_device *device, u32 event);
-
 /* Fujitsu ACPI interface function */
 
 static int call_fext_func(int cmd, int arg0, int arg1, int arg2)
@@ -239,7 +240,7 @@ static int call_fext_func(int cmd, int arg0, int arg1, int arg2)
 	unsigned long long value;
 	acpi_handle handle = NULL;
 
-	status = acpi_get_handle(fujitsu_hotkey->acpi_handle, "FUNC", &handle);
+	status = acpi_get_handle(fujitsu_laptop->acpi_handle, "FUNC", &handle);
 	if (ACPI_FAILURE(status)) {
 		vdbg_printk(FUJLAPTOP_DBG_ERROR,
 				"FUNC interface is not present\n");
@@ -300,9 +301,9 @@ static int radio_led_set(struct led_classdev *cdev,
 				enum led_brightness brightness)
 {
 	if (brightness >= LED_FULL)
-		return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON);
+		return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, RADIO_LED_ON);
 	else
-		return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
+		return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, 0x0);
 }
 
 static int eco_led_set(struct led_classdev *cdev,
@@ -346,7 +347,7 @@ static enum led_brightness radio_led_get(struct led_classdev *cdev)
 {
 	enum led_brightness brightness = LED_OFF;
 
-	if (call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0) & RADIO_LED_ON)
+	if (call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0) & RADIO_LED_ON)
 		brightness = LED_FULL;
 
 	return brightness;
@@ -373,10 +374,10 @@ static int set_lcd_level(int level)
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBLL [%d]\n",
 		    level);
 
-	if (level < 0 || level >= fujitsu->max_brightness)
+	if (level < 0 || level >= fujitsu_bl->max_brightness)
 		return -EINVAL;
 
-	status = acpi_get_handle(fujitsu->acpi_handle, "SBLL", &handle);
+	status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBLL", &handle);
 	if (ACPI_FAILURE(status)) {
 		vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBLL not present\n");
 		return -ENODEV;
@@ -398,10 +399,10 @@ static int set_lcd_level_alt(int level)
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBL2 [%d]\n",
 		    level);
 
-	if (level < 0 || level >= fujitsu->max_brightness)
+	if (level < 0 || level >= fujitsu_bl->max_brightness)
 		return -EINVAL;
 
-	status = acpi_get_handle(fujitsu->acpi_handle, "SBL2", &handle);
+	status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBL2", &handle);
 	if (ACPI_FAILURE(status)) {
 		vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBL2 not present\n");
 		return -ENODEV;
@@ -421,19 +422,19 @@ static int get_lcd_level(void)
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get lcd level via GBLL\n");
 
-	status =
-	    acpi_evaluate_integer(fujitsu->acpi_handle, "GBLL", NULL, &state);
+	status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "GBLL", NULL,
+				       &state);
 	if (ACPI_FAILURE(status))
 		return 0;
 
-	fujitsu->brightness_level = state & 0x0fffffff;
+	fujitsu_bl->brightness_level = state & 0x0fffffff;
 
 	if (state & 0x80000000)
-		fujitsu->brightness_changed = 1;
+		fujitsu_bl->brightness_changed = 1;
 	else
-		fujitsu->brightness_changed = 0;
+		fujitsu_bl->brightness_changed = 0;
 
-	return fujitsu->brightness_level;
+	return fujitsu_bl->brightness_level;
 }
 
 static int get_max_brightness(void)
@@ -443,14 +444,14 @@ static int get_max_brightness(void)
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get max lcd level via RBLL\n");
 
-	status =
-	    acpi_evaluate_integer(fujitsu->acpi_handle, "RBLL", NULL, &state);
+	status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "RBLL", NULL,
+				       &state);
 	if (ACPI_FAILURE(status))
 		return -1;
 
-	fujitsu->max_brightness = state;
+	fujitsu_bl->max_brightness = state;
 
-	return fujitsu->max_brightness;
+	return fujitsu_bl->max_brightness;
 }
 
 /* Backlight device stuff */
@@ -483,7 +484,7 @@ static int bl_update_status(struct backlight_device *b)
 	return ret;
 }
 
-static const struct backlight_ops fujitsubl_ops = {
+static const struct backlight_ops fujitsu_bl_ops = {
 	.get_brightness = bl_get_brightness,
 	.update_status = bl_update_status,
 };
@@ -511,7 +512,7 @@ show_brightness_changed(struct device *dev,
 
 	int ret;
 
-	ret = fujitsu->brightness_changed;
+	ret = fujitsu_bl->brightness_changed;
 	if (ret < 0)
 		return ret;
 
@@ -539,7 +540,7 @@ static ssize_t store_lcd_level(struct device *dev,
 	int level, ret;
 
 	if (sscanf(buf, "%i", &level) != 1
-	    || (level < 0 || level >= fujitsu->max_brightness))
+	    || (level < 0 || level >= fujitsu_bl->max_brightness))
 		return -EINVAL;
 
 	if (use_alt_lcd_levels)
@@ -567,9 +568,9 @@ static ssize_t
 show_lid_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	if (!(fujitsu_hotkey->rfkill_supported & 0x100))
+	if (!(fujitsu_laptop->flags_supported & FLAG_LID))
 		return sprintf(buf, "unknown\n");
-	if (fujitsu_hotkey->rfkill_state & 0x100)
+	if (fujitsu_laptop->flags_state & FLAG_LID)
 		return sprintf(buf, "open\n");
 	else
 		return sprintf(buf, "closed\n");
@@ -579,9 +580,9 @@ static ssize_t
 show_dock_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	if (!(fujitsu_hotkey->rfkill_supported & 0x200))
+	if (!(fujitsu_laptop->flags_supported & FLAG_DOCK))
 		return sprintf(buf, "unknown\n");
-	if (fujitsu_hotkey->rfkill_state & 0x200)
+	if (fujitsu_laptop->flags_state & FLAG_DOCK)
 		return sprintf(buf, "docked\n");
 	else
 		return sprintf(buf, "undocked\n");
@@ -591,9 +592,9 @@ static ssize_t
 show_radios_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	if (!(fujitsu_hotkey->rfkill_supported & 0x20))
+	if (!(fujitsu_laptop->flags_supported & FLAG_RFKILL))
 		return sprintf(buf, "unknown\n");
-	if (fujitsu_hotkey->rfkill_state & 0x20)
+	if (fujitsu_laptop->flags_state & FLAG_RFKILL)
 		return sprintf(buf, "on\n");
 	else
 		return sprintf(buf, "killed\n");
@@ -607,7 +608,7 @@ static DEVICE_ATTR(lid, 0444, show_lid_state, ignore_store);
 static DEVICE_ATTR(dock, 0444, show_dock_state, ignore_store);
 static DEVICE_ATTR(radios, 0444, show_radios_state, ignore_store);
 
-static struct attribute *fujitsupf_attributes[] = {
+static struct attribute *fujitsu_pf_attributes[] = {
 	&dev_attr_brightness_changed.attr,
 	&dev_attr_max_brightness.attr,
 	&dev_attr_lcd_level.attr,
@@ -617,11 +618,11 @@ static struct attribute *fujitsupf_attributes[] = {
 	NULL
 };
 
-static struct attribute_group fujitsupf_attribute_group = {
-	.attrs = fujitsupf_attributes
+static struct attribute_group fujitsu_pf_attribute_group = {
+	.attrs = fujitsu_pf_attributes
 };
 
-static struct platform_driver fujitsupf_driver = {
+static struct platform_driver fujitsu_pf_driver = {
 	.driver = {
 		   .name = "fujitsu-laptop",
 		   }
@@ -630,39 +631,30 @@ static struct platform_driver fujitsupf_driver = {
 static void __init dmi_check_cb_common(const struct dmi_system_id *id)
 {
 	pr_info("Identified laptop model '%s'\n", id->ident);
-	if (use_alt_lcd_levels == -1) {
-		if (acpi_has_method(NULL,
-				"\\_SB.PCI0.LPCB.FJEX.SBL2"))
-			use_alt_lcd_levels = 1;
-		else
-			use_alt_lcd_levels = 0;
-		vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as "
-			"%i\n", use_alt_lcd_levels);
-	}
 }
 
 static int __init dmi_check_cb_s6410(const struct dmi_system_id *id)
 {
 	dmi_check_cb_common(id);
-	fujitsu->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
-	fujitsu->keycode2 = KEY_HELP;	/* "Mobility Center" */
+	fujitsu_bl->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
+	fujitsu_bl->keycode2 = KEY_HELP;	/* "Mobility Center" */
 	return 1;
 }
 
 static int __init dmi_check_cb_s6420(const struct dmi_system_id *id)
 {
 	dmi_check_cb_common(id);
-	fujitsu->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
-	fujitsu->keycode2 = KEY_HELP;	/* "Mobility Center" */
+	fujitsu_bl->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
+	fujitsu_bl->keycode2 = KEY_HELP;	/* "Mobility Center" */
 	return 1;
 }
 
 static int __init dmi_check_cb_p8010(const struct dmi_system_id *id)
 {
 	dmi_check_cb_common(id);
-	fujitsu->keycode1 = KEY_HELP;	/* "Support" */
-	fujitsu->keycode3 = KEY_SWITCHVIDEOMODE;	/* "Presentation" */
-	fujitsu->keycode4 = KEY_WWW;	/* "Internet" */
+	fujitsu_bl->keycode1 = KEY_HELP;		/* "Support" */
+	fujitsu_bl->keycode3 = KEY_SWITCHVIDEOMODE;	/* "Presentation" */
+	fujitsu_bl->keycode4 = KEY_WWW;			/* "Internet" */
 	return 1;
 }
 
@@ -693,7 +685,7 @@ static const struct dmi_system_id fujitsu_dmi_table[] __initconst = {
 
 /* ACPI device for LCD brightness control */
 
-static int acpi_fujitsu_add(struct acpi_device *device)
+static int acpi_fujitsu_bl_add(struct acpi_device *device)
 {
 	int state = 0;
 	struct input_dev *input;
@@ -702,22 +694,22 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 	if (!device)
 		return -EINVAL;
 
-	fujitsu->acpi_handle = device->handle;
-	sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_DEVICE_NAME);
+	fujitsu_bl->acpi_handle = device->handle;
+	sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_BL_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
-	device->driver_data = fujitsu;
+	device->driver_data = fujitsu_bl;
 
-	fujitsu->input = input = input_allocate_device();
+	fujitsu_bl->input = input = input_allocate_device();
 	if (!input) {
 		error = -ENOMEM;
 		goto err_stop;
 	}
 
-	snprintf(fujitsu->phys, sizeof(fujitsu->phys),
+	snprintf(fujitsu_bl->phys, sizeof(fujitsu_bl->phys),
 		 "%s/video/input0", acpi_device_hid(device));
 
 	input->name = acpi_device_name(device);
-	input->phys = fujitsu->phys;
+	input->phys = fujitsu_bl->phys;
 	input->id.bustype = BUS_HOST;
 	input->id.product = 0x06;
 	input->dev.parent = &device->dev;
@@ -730,7 +722,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 	if (error)
 		goto err_free_input_dev;
 
-	error = acpi_bus_update_power(fujitsu->acpi_handle, &state);
+	error = acpi_bus_update_power(fujitsu_bl->acpi_handle, &state);
 	if (error) {
 		pr_err("Error reading power state\n");
 		goto err_unregister_input_dev;
@@ -740,7 +732,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 	       acpi_device_name(device), acpi_device_bid(device),
 	       !device->power.state ? "on" : "off");
 
-	fujitsu->dev = device;
+	fujitsu_bl->dev = device;
 
 	if (acpi_has_method(device->handle, METHOD_NAME__INI)) {
 		vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n");
@@ -750,6 +742,15 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 			pr_err("_INI Method failed\n");
 	}
 
+	if (use_alt_lcd_levels == -1) {
+		if (acpi_has_method(NULL, "\\_SB.PCI0.LPCB.FJEX.SBL2"))
+			use_alt_lcd_levels = 1;
+		else
+			use_alt_lcd_levels = 0;
+		vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as %i\n",
+			    use_alt_lcd_levels);
+	}
+
 	/* do config (detect defaults) */
 	use_alt_lcd_levels = use_alt_lcd_levels == 1 ? 1 : 0;
 	disable_brightness_adjust = disable_brightness_adjust == 1 ? 1 : 0;
@@ -758,7 +759,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 		    use_alt_lcd_levels, disable_brightness_adjust);
 
 	if (get_max_brightness() <= 0)
-		fujitsu->max_brightness = FUJITSU_LCD_N_LEVELS;
+		fujitsu_bl->max_brightness = FUJITSU_LCD_N_LEVELS;
 	get_lcd_level();
 
 	return 0;
@@ -772,38 +773,38 @@ err_stop:
 	return error;
 }
 
-static int acpi_fujitsu_remove(struct acpi_device *device)
+static int acpi_fujitsu_bl_remove(struct acpi_device *device)
 {
-	struct fujitsu_t *fujitsu = acpi_driver_data(device);
-	struct input_dev *input = fujitsu->input;
+	struct fujitsu_bl *fujitsu_bl = acpi_driver_data(device);
+	struct input_dev *input = fujitsu_bl->input;
 
 	input_unregister_device(input);
 
-	fujitsu->acpi_handle = NULL;
+	fujitsu_bl->acpi_handle = NULL;
 
 	return 0;
 }
 
 /* Brightness notify */
 
-static void acpi_fujitsu_notify(struct acpi_device *device, u32 event)
+static void acpi_fujitsu_bl_notify(struct acpi_device *device, u32 event)
 {
 	struct input_dev *input;
 	int keycode;
 	int oldb, newb;
 
-	input = fujitsu->input;
+	input = fujitsu_bl->input;
 
 	switch (event) {
 	case ACPI_FUJITSU_NOTIFY_CODE1:
 		keycode = 0;
-		oldb = fujitsu->brightness_level;
+		oldb = fujitsu_bl->brightness_level;
 		get_lcd_level();
-		newb = fujitsu->brightness_level;
+		newb = fujitsu_bl->brightness_level;
 
 		vdbg_printk(FUJLAPTOP_DBG_TRACE,
 			    "brightness button event [%i -> %i (%i)]\n",
-			    oldb, newb, fujitsu->brightness_changed);
+			    oldb, newb, fujitsu_bl->brightness_changed);
 
 		if (oldb < newb) {
 			if (disable_brightness_adjust != 1) {
@@ -840,7 +841,7 @@ static void acpi_fujitsu_notify(struct acpi_device *device, u32 event)
 
 /* ACPI device for hotkey handling */
 
-static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
+static int acpi_fujitsu_laptop_add(struct acpi_device *device)
 {
 	int result = 0;
 	int state = 0;
@@ -851,42 +852,42 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	if (!device)
 		return -EINVAL;
 
-	fujitsu_hotkey->acpi_handle = device->handle;
+	fujitsu_laptop->acpi_handle = device->handle;
 	sprintf(acpi_device_name(device), "%s",
-		ACPI_FUJITSU_HOTKEY_DEVICE_NAME);
+		ACPI_FUJITSU_LAPTOP_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
-	device->driver_data = fujitsu_hotkey;
+	device->driver_data = fujitsu_laptop;
 
 	/* kfifo */
-	spin_lock_init(&fujitsu_hotkey->fifo_lock);
-	error = kfifo_alloc(&fujitsu_hotkey->fifo, RINGBUFFERSIZE * sizeof(int),
+	spin_lock_init(&fujitsu_laptop->fifo_lock);
+	error = kfifo_alloc(&fujitsu_laptop->fifo, RINGBUFFERSIZE * sizeof(int),
 			GFP_KERNEL);
 	if (error) {
 		pr_err("kfifo_alloc failed\n");
 		goto err_stop;
 	}
 
-	fujitsu_hotkey->input = input = input_allocate_device();
+	fujitsu_laptop->input = input = input_allocate_device();
 	if (!input) {
 		error = -ENOMEM;
 		goto err_free_fifo;
 	}
 
-	snprintf(fujitsu_hotkey->phys, sizeof(fujitsu_hotkey->phys),
+	snprintf(fujitsu_laptop->phys, sizeof(fujitsu_laptop->phys),
 		 "%s/video/input0", acpi_device_hid(device));
 
 	input->name = acpi_device_name(device);
-	input->phys = fujitsu_hotkey->phys;
+	input->phys = fujitsu_laptop->phys;
 	input->id.bustype = BUS_HOST;
 	input->id.product = 0x06;
 	input->dev.parent = &device->dev;
 
 	set_bit(EV_KEY, input->evbit);
-	set_bit(fujitsu->keycode1, input->keybit);
-	set_bit(fujitsu->keycode2, input->keybit);
-	set_bit(fujitsu->keycode3, input->keybit);
-	set_bit(fujitsu->keycode4, input->keybit);
-	set_bit(fujitsu->keycode5, input->keybit);
+	set_bit(fujitsu_bl->keycode1, input->keybit);
+	set_bit(fujitsu_bl->keycode2, input->keybit);
+	set_bit(fujitsu_bl->keycode3, input->keybit);
+	set_bit(fujitsu_bl->keycode4, input->keybit);
+	set_bit(fujitsu_bl->keycode5, input->keybit);
 	set_bit(KEY_TOUCHPAD_TOGGLE, input->keybit);
 	set_bit(KEY_UNKNOWN, input->keybit);
 
@@ -894,7 +895,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	if (error)
 		goto err_free_input_dev;
 
-	error = acpi_bus_update_power(fujitsu_hotkey->acpi_handle, &state);
+	error = acpi_bus_update_power(fujitsu_laptop->acpi_handle, &state);
 	if (error) {
 		pr_err("Error reading power state\n");
 		goto err_unregister_input_dev;
@@ -904,7 +905,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 		acpi_device_name(device), acpi_device_bid(device),
 		!device->power.state ? "on" : "off");
 
-	fujitsu_hotkey->dev = device;
+	fujitsu_laptop->dev = device;
 
 	if (acpi_has_method(device->handle, METHOD_NAME__INI)) {
 		vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n");
@@ -920,27 +921,27 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 		; /* No action, result is discarded */
 	vdbg_printk(FUJLAPTOP_DBG_INFO, "Discarded %i ringbuffer entries\n", i);
 
-	fujitsu_hotkey->rfkill_supported =
-		call_fext_func(FUNC_RFKILL, 0x0, 0x0, 0x0);
+	fujitsu_laptop->flags_supported =
+		call_fext_func(FUNC_FLAGS, 0x0, 0x0, 0x0);
 
 	/* Make sure our bitmask of supported functions is cleared if the
 	   RFKILL function block is not implemented, like on the S7020. */
-	if (fujitsu_hotkey->rfkill_supported == UNSUPPORTED_CMD)
-		fujitsu_hotkey->rfkill_supported = 0;
+	if (fujitsu_laptop->flags_supported == UNSUPPORTED_CMD)
+		fujitsu_laptop->flags_supported = 0;
 
-	if (fujitsu_hotkey->rfkill_supported)
-		fujitsu_hotkey->rfkill_state =
-			call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
+	if (fujitsu_laptop->flags_supported)
+		fujitsu_laptop->flags_state =
+			call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0);
 
 	/* Suspect this is a keymap of the application panel, print it */
 	pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 	if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&logolamp_led);
 		if (result == 0) {
-			fujitsu_hotkey->logolamp_registered = 1;
+			fujitsu_laptop->logolamp_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for logo lamp, error %i\n",
 			       result);
@@ -949,10 +950,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 
 	if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & KEYBOARD_LAMPS) &&
 	   (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) == 0x0)) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&kblamps_led);
 		if (result == 0) {
-			fujitsu_hotkey->kblamps_registered = 1;
+			fujitsu_laptop->kblamps_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for keyboard lamps, error %i\n",
 			       result);
@@ -966,10 +967,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	 * that an RF LED is present.
 	 */
 	if (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) & BIT(24)) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&radio_led);
 		if (result == 0) {
-			fujitsu_hotkey->radio_led_registered = 1;
+			fujitsu_laptop->radio_led_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for radio LED, error %i\n",
 			       result);
@@ -983,10 +984,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	*/
 	if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & BIT(14)) &&
 	   (call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0) != UNSUPPORTED_CMD)) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&eco_led);
 		if (result == 0) {
-			fujitsu_hotkey->eco_led_registered = 1;
+			fujitsu_laptop->eco_led_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for eco LED, error %i\n",
 			       result);
@@ -1002,47 +1003,47 @@ err_unregister_input_dev:
 err_free_input_dev:
 	input_free_device(input);
 err_free_fifo:
-	kfifo_free(&fujitsu_hotkey->fifo);
+	kfifo_free(&fujitsu_laptop->fifo);
 err_stop:
 	return error;
 }
 
-static int acpi_fujitsu_hotkey_remove(struct acpi_device *device)
+static int acpi_fujitsu_laptop_remove(struct acpi_device *device)
 {
-	struct fujitsu_hotkey_t *fujitsu_hotkey = acpi_driver_data(device);
-	struct input_dev *input = fujitsu_hotkey->input;
+	struct fujitsu_laptop *fujitsu_laptop = acpi_driver_data(device);
+	struct input_dev *input = fujitsu_laptop->input;
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
-	if (fujitsu_hotkey->logolamp_registered)
+	if (fujitsu_laptop->logolamp_registered)
 		led_classdev_unregister(&logolamp_led);
 
-	if (fujitsu_hotkey->kblamps_registered)
+	if (fujitsu_laptop->kblamps_registered)
 		led_classdev_unregister(&kblamps_led);
 
-	if (fujitsu_hotkey->radio_led_registered)
+	if (fujitsu_laptop->radio_led_registered)
 		led_classdev_unregister(&radio_led);
 
-	if (fujitsu_hotkey->eco_led_registered)
+	if (fujitsu_laptop->eco_led_registered)
 		led_classdev_unregister(&eco_led);
 #endif
 
 	input_unregister_device(input);
 
-	kfifo_free(&fujitsu_hotkey->fifo);
+	kfifo_free(&fujitsu_laptop->fifo);
 
-	fujitsu_hotkey->acpi_handle = NULL;
+	fujitsu_laptop->acpi_handle = NULL;
 
 	return 0;
 }
 
-static void acpi_fujitsu_hotkey_press(int keycode)
+static void acpi_fujitsu_laptop_press(int keycode)
 {
-	struct input_dev *input = fujitsu_hotkey->input;
+	struct input_dev *input = fujitsu_laptop->input;
 	int status;
 
-	status = kfifo_in_locked(&fujitsu_hotkey->fifo,
+	status = kfifo_in_locked(&fujitsu_laptop->fifo,
 				 (unsigned char *)&keycode, sizeof(keycode),
-				 &fujitsu_hotkey->fifo_lock);
+				 &fujitsu_laptop->fifo_lock);
 	if (status != sizeof(keycode)) {
 		vdbg_printk(FUJLAPTOP_DBG_WARN,
 			    "Could not push keycode [0x%x]\n", keycode);
@@ -1054,16 +1055,16 @@ static void acpi_fujitsu_hotkey_press(int keycode)
 		    "Push keycode into ringbuffer [%d]\n", keycode);
 }
 
-static void acpi_fujitsu_hotkey_release(void)
+static void acpi_fujitsu_laptop_release(void)
 {
-	struct input_dev *input = fujitsu_hotkey->input;
+	struct input_dev *input = fujitsu_laptop->input;
 	int keycode, status;
 
 	while (true) {
-		status = kfifo_out_locked(&fujitsu_hotkey->fifo,
+		status = kfifo_out_locked(&fujitsu_laptop->fifo,
 					  (unsigned char *)&keycode,
 					  sizeof(keycode),
-					  &fujitsu_hotkey->fifo_lock);
+					  &fujitsu_laptop->fifo_lock);
 		if (status != sizeof(keycode))
 			return;
 		input_report_key(input, keycode, 0);
@@ -1073,14 +1074,14 @@ static void acpi_fujitsu_hotkey_release(void)
 	}
 }
 
-static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
+static void acpi_fujitsu_laptop_notify(struct acpi_device *device, u32 event)
 {
 	struct input_dev *input;
 	int keycode;
 	unsigned int irb = 1;
 	int i;
 
-	input = fujitsu_hotkey->input;
+	input = fujitsu_laptop->input;
 
 	if (event != ACPI_FUJITSU_NOTIFY_CODE1) {
 		keycode = KEY_UNKNOWN;
@@ -1093,9 +1094,9 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
 		return;
 	}
 
-	if (fujitsu_hotkey->rfkill_supported)
-		fujitsu_hotkey->rfkill_state =
-			call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
+	if (fujitsu_laptop->flags_supported)
+		fujitsu_laptop->flags_state =
+			call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0);
 
 	i = 0;
 	while ((irb =
@@ -1103,19 +1104,19 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
 			&& (i++) < MAX_HOTKEY_RINGBUFFER_SIZE) {
 		switch (irb & 0x4ff) {
 		case KEY1_CODE:
-			keycode = fujitsu->keycode1;
+			keycode = fujitsu_bl->keycode1;
 			break;
 		case KEY2_CODE:
-			keycode = fujitsu->keycode2;
+			keycode = fujitsu_bl->keycode2;
 			break;
 		case KEY3_CODE:
-			keycode = fujitsu->keycode3;
+			keycode = fujitsu_bl->keycode3;
 			break;
 		case KEY4_CODE:
-			keycode = fujitsu->keycode4;
+			keycode = fujitsu_bl->keycode4;
 			break;
 		case KEY5_CODE:
-			keycode = fujitsu->keycode5;
+			keycode = fujitsu_bl->keycode5;
 			break;
 		case 0:
 			keycode = 0;
@@ -1128,17 +1129,17 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
 		}
 
 		if (keycode > 0)
-			acpi_fujitsu_hotkey_press(keycode);
+			acpi_fujitsu_laptop_press(keycode);
 		else if (keycode == 0)
-			acpi_fujitsu_hotkey_release();
+			acpi_fujitsu_laptop_release();
 	}
 
 	/* On some models (first seen on the Skylake-based Lifebook
 	 * E736/E746/E756), the touchpad toggle hotkey (Fn+F4) is
-	 * handled in software; its state is queried using FUNC_RFKILL
+	 * handled in software; its state is queried using FUNC_FLAGS
 	 */
-	if ((fujitsu_hotkey->rfkill_supported & BIT(26)) &&
-	    (call_fext_func(FUNC_RFKILL, 0x1, 0x0, 0x0) & BIT(26))) {
+	if ((fujitsu_laptop->flags_supported & BIT(26)) &&
+	    (call_fext_func(FUNC_FLAGS, 0x1, 0x0, 0x0) & BIT(26))) {
 		keycode = KEY_TOUCHPAD_TOGGLE;
 		input_report_key(input, keycode, 1);
 		input_sync(input);
@@ -1150,83 +1151,81 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
 
 /* Initialization */
 
-static const struct acpi_device_id fujitsu_device_ids[] = {
-	{ACPI_FUJITSU_HID, 0},
+static const struct acpi_device_id fujitsu_bl_device_ids[] = {
+	{ACPI_FUJITSU_BL_HID, 0},
 	{"", 0},
 };
 
-static struct acpi_driver acpi_fujitsu_driver = {
-	.name = ACPI_FUJITSU_DRIVER_NAME,
+static struct acpi_driver acpi_fujitsu_bl_driver = {
+	.name = ACPI_FUJITSU_BL_DRIVER_NAME,
 	.class = ACPI_FUJITSU_CLASS,
-	.ids = fujitsu_device_ids,
+	.ids = fujitsu_bl_device_ids,
 	.ops = {
-		.add = acpi_fujitsu_add,
-		.remove = acpi_fujitsu_remove,
-		.notify = acpi_fujitsu_notify,
+		.add = acpi_fujitsu_bl_add,
+		.remove = acpi_fujitsu_bl_remove,
+		.notify = acpi_fujitsu_bl_notify,
 		},
 };
 
-static const struct acpi_device_id fujitsu_hotkey_device_ids[] = {
-	{ACPI_FUJITSU_HOTKEY_HID, 0},
+static const struct acpi_device_id fujitsu_laptop_device_ids[] = {
+	{ACPI_FUJITSU_LAPTOP_HID, 0},
 	{"", 0},
 };
 
-static struct acpi_driver acpi_fujitsu_hotkey_driver = {
-	.name = ACPI_FUJITSU_HOTKEY_DRIVER_NAME,
+static struct acpi_driver acpi_fujitsu_laptop_driver = {
+	.name = ACPI_FUJITSU_LAPTOP_DRIVER_NAME,
 	.class = ACPI_FUJITSU_CLASS,
-	.ids = fujitsu_hotkey_device_ids,
+	.ids = fujitsu_laptop_device_ids,
 	.ops = {
-		.add = acpi_fujitsu_hotkey_add,
-		.remove = acpi_fujitsu_hotkey_remove,
-		.notify = acpi_fujitsu_hotkey_notify,
+		.add = acpi_fujitsu_laptop_add,
+		.remove = acpi_fujitsu_laptop_remove,
+		.notify = acpi_fujitsu_laptop_notify,
 		},
 };
 
 static const struct acpi_device_id fujitsu_ids[] __used = {
-	{ACPI_FUJITSU_HID, 0},
-	{ACPI_FUJITSU_HOTKEY_HID, 0},
+	{ACPI_FUJITSU_BL_HID, 0},
+	{ACPI_FUJITSU_LAPTOP_HID, 0},
 	{"", 0}
 };
 MODULE_DEVICE_TABLE(acpi, fujitsu_ids);
 
 static int __init fujitsu_init(void)
 {
-	int ret, result, max_brightness;
+	int ret, max_brightness;
 
 	if (acpi_disabled)
 		return -ENODEV;
 
-	fujitsu = kzalloc(sizeof(struct fujitsu_t), GFP_KERNEL);
-	if (!fujitsu)
+	fujitsu_bl = kzalloc(sizeof(struct fujitsu_bl), GFP_KERNEL);
+	if (!fujitsu_bl)
 		return -ENOMEM;
-	fujitsu->keycode1 = KEY_PROG1;
-	fujitsu->keycode2 = KEY_PROG2;
-	fujitsu->keycode3 = KEY_PROG3;
-	fujitsu->keycode4 = KEY_PROG4;
-	fujitsu->keycode5 = KEY_RFKILL;
+	fujitsu_bl->keycode1 = KEY_PROG1;
+	fujitsu_bl->keycode2 = KEY_PROG2;
+	fujitsu_bl->keycode3 = KEY_PROG3;
+	fujitsu_bl->keycode4 = KEY_PROG4;
+	fujitsu_bl->keycode5 = KEY_RFKILL;
 	dmi_check_system(fujitsu_dmi_table);
 
-	result = acpi_bus_register_driver(&acpi_fujitsu_driver);
-	if (result < 0) {
-		ret = -ENODEV;
+	ret = acpi_bus_register_driver(&acpi_fujitsu_bl_driver);
+	if (ret)
 		goto fail_acpi;
-	}
 
 	/* Register platform stuff */
 
-	fujitsu->pf_device = platform_device_alloc("fujitsu-laptop", -1);
-	if (!fujitsu->pf_device) {
+	fujitsu_bl->pf_device = platform_device_alloc("fujitsu-laptop", -1);
+	if (!fujitsu_bl->pf_device) {
 		ret = -ENOMEM;
 		goto fail_platform_driver;
 	}
 
-	ret = platform_device_add(fujitsu->pf_device);
+	ret = platform_device_add(fujitsu_bl->pf_device);
 	if (ret)
 		goto fail_platform_device1;
 
 	ret =
-	    sysfs_create_group(&fujitsu->pf_device->dev.kobj,
-			       &fujitsupf_attribute_group);
+	    sysfs_create_group(&fujitsu_bl->pf_device->dev.kobj,
+			       &fujitsu_pf_attribute_group);
 	if (ret)
 		goto fail_platform_device2;
 
@@ -1236,90 +1235,88 @@ static int __init fujitsu_init(void)
 		struct backlight_properties props;
 
 		memset(&props, 0, sizeof(struct backlight_properties));
-		max_brightness = fujitsu->max_brightness;
+		max_brightness = fujitsu_bl->max_brightness;
 		props.type = BACKLIGHT_PLATFORM;
 		props.max_brightness = max_brightness - 1;
-		fujitsu->bl_device = backlight_device_register("fujitsu-laptop",
-							       NULL, NULL,
-							       &fujitsubl_ops,
-							       &props);
-		if (IS_ERR(fujitsu->bl_device)) {
-			ret = PTR_ERR(fujitsu->bl_device);
-			fujitsu->bl_device = NULL;
+		fujitsu_bl->bl_device = backlight_device_register("fujitsu-laptop",
+								  NULL, NULL,
+								  &fujitsu_bl_ops,
+								  &props);
+		if (IS_ERR(fujitsu_bl->bl_device)) {
+			ret = PTR_ERR(fujitsu_bl->bl_device);
+			fujitsu_bl->bl_device = NULL;
 			goto fail_sysfs_group;
 		}
-		fujitsu->bl_device->props.brightness = fujitsu->brightness_level;
+		fujitsu_bl->bl_device->props.brightness = fujitsu_bl->brightness_level;
 	}
 
-	ret = platform_driver_register(&fujitsupf_driver);
+	ret = platform_driver_register(&fujitsu_pf_driver);
 	if (ret)
 		goto fail_backlight;
 
-	/* Register hotkey driver */
+	/* Register laptop driver */
 
-	fujitsu_hotkey = kzalloc(sizeof(struct fujitsu_hotkey_t), GFP_KERNEL);
-	if (!fujitsu_hotkey) {
+	fujitsu_laptop = kzalloc(sizeof(struct fujitsu_laptop), GFP_KERNEL);
+	if (!fujitsu_laptop) {
 		ret = -ENOMEM;
-		goto fail_hotkey;
+		goto fail_laptop;
 	}
 
-	result = acpi_bus_register_driver(&acpi_fujitsu_hotkey_driver);
-	if (result < 0) {
-		ret = -ENODEV;
-		goto fail_hotkey1;
-	}
+	ret = acpi_bus_register_driver(&acpi_fujitsu_laptop_driver);
+	if (ret)
+		goto fail_laptop1;
 
 	/* Sync backlight power status (needs FUJ02E3 device, hence deferred) */
 	if (acpi_video_get_backlight_type() == acpi_backlight_vendor) {
 		if (call_fext_func(FUNC_BACKLIGHT, 0x2, 0x4, 0x0) == 3)
-			fujitsu->bl_device->props.power = FB_BLANK_POWERDOWN;
+			fujitsu_bl->bl_device->props.power = FB_BLANK_POWERDOWN;
 		else
-			fujitsu->bl_device->props.power = FB_BLANK_UNBLANK;
+			fujitsu_bl->bl_device->props.power = FB_BLANK_UNBLANK;
 	}
 
 	pr_info("driver " FUJITSU_DRIVER_VERSION " successfully loaded\n");
 
 	return 0;
 
-fail_hotkey1:
-	kfree(fujitsu_hotkey);
-fail_hotkey:
-	platform_driver_unregister(&fujitsupf_driver);
+fail_laptop1:
+	kfree(fujitsu_laptop);
+fail_laptop:
+	platform_driver_unregister(&fujitsu_pf_driver);
 fail_backlight:
-	backlight_device_unregister(fujitsu->bl_device);
+	backlight_device_unregister(fujitsu_bl->bl_device);
 fail_sysfs_group:
-	sysfs_remove_group(&fujitsu->pf_device->dev.kobj,
-			   &fujitsupf_attribute_group);
+	sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj,
+			   &fujitsu_pf_attribute_group);
 fail_platform_device2:
-	platform_device_del(fujitsu->pf_device);
+	platform_device_del(fujitsu_bl->pf_device);
 fail_platform_device1:
-	platform_device_put(fujitsu->pf_device);
+	platform_device_put(fujitsu_bl->pf_device);
 fail_platform_driver:
-	acpi_bus_unregister_driver(&acpi_fujitsu_driver);
+	acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver);
 fail_acpi:
-	kfree(fujitsu);
+	kfree(fujitsu_bl);
 
 	return ret;
 }
 
 static void __exit fujitsu_cleanup(void)
 {
-	acpi_bus_unregister_driver(&acpi_fujitsu_hotkey_driver);
+	acpi_bus_unregister_driver(&acpi_fujitsu_laptop_driver);
 
-	kfree(fujitsu_hotkey);
+	kfree(fujitsu_laptop);
 
-	platform_driver_unregister(&fujitsupf_driver);
+	platform_driver_unregister(&fujitsu_pf_driver);
 
-	backlight_device_unregister(fujitsu->bl_device);
+	backlight_device_unregister(fujitsu_bl->bl_device);
 
-	sysfs_remove_group(&fujitsu->pf_device->dev.kobj,
-			   &fujitsupf_attribute_group);
+	sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj,
+			   &fujitsu_pf_attribute_group);
 
-	platform_device_unregister(fujitsu->pf_device);
+	platform_device_unregister(fujitsu_bl->pf_device);
 
-	acpi_bus_unregister_driver(&acpi_fujitsu_driver);
+	acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver);
 
-	kfree(fujitsu);
+	kfree(fujitsu_bl);
 
 	pr_info("driver unloaded\n");
 }
@@ -1341,7 +1338,3 @@ MODULE_AUTHOR("Jonathan Woithe, Peter Gruber, Tony Vroon");
 MODULE_DESCRIPTION("Fujitsu laptop extras support");
 MODULE_VERSION(FUJITSU_DRIVER_VERSION);
 MODULE_LICENSE("GPL");
-
-MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1D3:*:cvrS6410:*");
-MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1E6:*:cvrS6420:*");
-MODULE_ALIAS("dmi:*:svnFUJITSU:*:pvr:rvnFUJITSU:rnFJNB19C:*:cvrS7020:*");
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index 438d4c72c7b3..ff563db025b3 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -54,7 +54,7 @@ __asm__(".text			\n"
 
 #define Q2_SET_SEL(cpu, selname, address, size) \
 do { \
-	struct desc_struct *gdt = get_cpu_gdt_table((cpu)); \
+	struct desc_struct *gdt = get_cpu_gdt_rw((cpu)); \
 	set_desc_base(&gdt[(selname) >> 3], (u32)(address)); \
 	set_desc_limit(&gdt[(selname) >> 3], (size) - 1); \
 } while(0)
@@ -95,8 +95,8 @@ static inline u16 call_pnp_bios(u16 func, u16 arg1, u16 arg2, u16 arg3,
 		return PNP_FUNCTION_NOT_SUPPORTED;
 
 	cpu = get_cpu();
-	save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8];
-	get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc;
+	save_desc_40 = get_cpu_gdt_rw(cpu)[0x40 / 8];
+	get_cpu_gdt_rw(cpu)[0x40 / 8] = bad_bios_desc;
 
 	/* On some boxes IRQ's during PnP BIOS calls are deadly.  */
 	spin_lock_irqsave(&pnp_bios_lock, flags);
@@ -134,7 +134,7 @@ static inline u16 call_pnp_bios(u16 func, u16 arg1, u16 arg2, u16 arg3,
 			     :"memory");
 	spin_unlock_irqrestore(&pnp_bios_lock, flags);
 
-	get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40;
+	get_cpu_gdt_rw(cpu)[0x40 / 8] = save_desc_40;
 	put_cpu();
 
 	/* If we get here and this is set then the PnP BIOS faulted on us. */
@@ -477,7 +477,7 @@ void pnpbios_calls_init(union pnp_bios_install_struct *header)
 	pnp_bios_callpoint.segment = PNP_CS16;
 
 	for_each_possible_cpu(i) {
-		struct desc_struct *gdt = get_cpu_gdt_table(i);
+		struct desc_struct *gdt = get_cpu_gdt_rw(i);
 		if (!gdt)
 			continue;
 		set_desc_base(&gdt[GDT_ENTRY_PNPBIOS_CS32],
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c
index 56bce1908be2..85812521b6ba 100644
--- a/drivers/power/avs/rockchip-io-domain.c
+++ b/drivers/power/avs/rockchip-io-domain.c
@@ -43,6 +43,10 @@
 #define RK3288_SOC_CON2_FLASH0		BIT(7)
 #define RK3288_SOC_FLASH_SUPPLY_NUM	2
 
+#define RK3328_SOC_CON4			0x410
+#define RK3328_SOC_CON4_VCCIO2		BIT(7)
+#define RK3328_SOC_VCCIO2_SUPPLY_NUM	1
+
 #define RK3368_SOC_CON15		0x43c
 #define RK3368_SOC_CON15_FLASH0		BIT(14)
 #define RK3368_SOC_FLASH_SUPPLY_NUM	2
@@ -166,6 +170,25 @@ static void rk3288_iodomain_init(struct rockchip_iodomain *iod)
 		dev_warn(iod->dev, "couldn't update flash0 ctrl\n");
 }
 
+static void rk3328_iodomain_init(struct rockchip_iodomain *iod)
+{
+	int ret;
+	u32 val;
+
+	/* if no vccio2 supply we should leave things alone */
+	if (!iod->supplies[RK3328_SOC_VCCIO2_SUPPLY_NUM].reg)
+		return;
+
+	/*
+	 * set vccio2 iodomain to also use this framework
+	 * instead of a special gpio.
+	 */
+	val = RK3328_SOC_CON4_VCCIO2 | (RK3328_SOC_CON4_VCCIO2 << 16);
+	ret = regmap_write(iod->grf, RK3328_SOC_CON4, val);
+	if (ret < 0)
+		dev_warn(iod->dev, "couldn't update vccio2 vsel ctrl\n");
+}
+
 static void rk3368_iodomain_init(struct rockchip_iodomain *iod)
 {
 	int ret;
@@ -247,6 +270,20 @@ static const struct rockchip_iodomain_soc_data soc_data_rk3288 = {
 	.init = rk3288_iodomain_init,
 };
 
+static const struct rockchip_iodomain_soc_data soc_data_rk3328 = {
+	.grf_offset = 0x410,
+	.supply_names = {
+		"vccio1",
+		"vccio2",
+		"vccio3",
+		"vccio4",
+		"vccio5",
+		"vccio6",
+		"pmuio",
+	},
+	.init = rk3328_iodomain_init,
+};
+
 static const struct rockchip_iodomain_soc_data soc_data_rk3368 = {
 	.grf_offset = 0x900,
 	.supply_names = {
@@ -312,6 +349,10 @@ static const struct of_device_id rockchip_iodomain_match[] = {
 		.data = (void *)&soc_data_rk3288
 	},
 	{
+		.compatible = "rockchip,rk3328-io-voltage-domain",
+		.data = (void *)&soc_data_rk3328
+	},
+	{
 		.compatible = "rockchip,rk3368-io-voltage-domain",
 		.data = (void *)&soc_data_rk3368
 	},
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index b8cacccf18c8..13f1714cf6f7 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -67,6 +67,15 @@ config POWER_RESET_BRCMSTB
 	  Say Y here if you have a Broadcom STB board and you wish
 	  to have restart support.
 
+config POWER_RESET_GEMINI_POWEROFF
+	bool "Cortina Gemini power-off driver"
+	depends on ARCH_GEMINI || COMPILE_TEST
+	depends on OF && HAS_IOMEM
+	default ARCH_GEMINI
+	help
+	  This driver supports turning off the Cortina Gemini SoC.
+	  Select this if you're building a kernel with Gemini SoC support.
+
 config POWER_RESET_GPIO
 	bool "GPIO power-off driver"
 	depends on OF_GPIO
diff --git a/drivers/power/reset/Makefile b/drivers/power/reset/Makefile
index 11dae3b56ff9..58cf5b30559f 100644
--- a/drivers/power/reset/Makefile
+++ b/drivers/power/reset/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_POWER_RESET_AT91_SAMA5D2_SHDWC) += at91-sama5d2_shdwc.o
 obj-$(CONFIG_POWER_RESET_AXXIA) += axxia-reset.o
 obj-$(CONFIG_POWER_RESET_BRCMKONA) += brcm-kona-reset.o
 obj-$(CONFIG_POWER_RESET_BRCMSTB) += brcmstb-reboot.o
+obj-$(CONFIG_POWER_RESET_GEMINI_POWEROFF) += gemini-poweroff.o
 obj-$(CONFIG_POWER_RESET_GPIO) += gpio-poweroff.o
 obj-$(CONFIG_POWER_RESET_GPIO_RESTART) += gpio-restart.o
 obj-$(CONFIG_POWER_RESET_HISI) += hisi-reboot.o
diff --git a/drivers/power/reset/gemini-poweroff.c b/drivers/power/reset/gemini-poweroff.c
new file mode 100644
index 000000000000..de878fd26f27
--- /dev/null
+++ b/drivers/power/reset/gemini-poweroff.c
@@ -0,0 +1,160 @@
+/*
+ * Gemini power management controller
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Inspired by code from the SL3516 board support by Jason Lee
+ * Inspired by code from Janos Laube <janos.dev@gmail.com>
+ */
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+
+#define GEMINI_PWC_ID		0x00010500
+#define	GEMINI_PWC_IDREG	0x00
+#define	GEMINI_PWC_CTRLREG	0x04
+#define	GEMINI_PWC_STATREG	0x08
+
+#define GEMINI_CTRL_SHUTDOWN	BIT(0)
+#define GEMINI_CTRL_ENABLE	BIT(1)
+#define GEMINI_CTRL_IRQ_CLR	BIT(2)
+
+#define GEMINI_STAT_CIR		BIT(4)
+#define	GEMINI_STAT_RTC		BIT(5)
+#define	GEMINI_STAT_POWERBUTTON	BIT(6)
+
+struct gemini_powercon {
+        struct device           *dev;
+        void __iomem            *base;
+};
+
+static irqreturn_t gemini_powerbutton_interrupt(int irq, void *data)
+{
+	struct gemini_powercon *gpw = data;
+	u32 val;
+
+	/* ACK the IRQ */
+	val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+	val |= GEMINI_CTRL_IRQ_CLR;
+	writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+	val = readl(gpw->base + GEMINI_PWC_STATREG);
+	val &= 0x70U;
+	switch (val) {
+	case GEMINI_STAT_CIR:
+		dev_info(gpw->dev, "infrared poweroff\n");
+		orderly_poweroff(true);
+		break;
+	case GEMINI_STAT_RTC:
+		dev_info(gpw->dev, "RTC poweroff\n");
+		orderly_poweroff(true);
+		break;
+	case GEMINI_STAT_POWERBUTTON:
+		dev_info(gpw->dev, "poweroff button pressed\n");
+		orderly_poweroff(true);
+		break;
+	default:
+		dev_info(gpw->dev, "other power management IRQ\n");
+		break;
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* This callback needs this static local as it has void as argument */
+static struct gemini_powercon *gpw_poweroff;
+
+static void gemini_poweroff(void)
+{
+	struct gemini_powercon *gpw = gpw_poweroff;
+	u32 val;
+
+	dev_crit(gpw->dev, "Gemini power off\n");
+	val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+	val |= GEMINI_CTRL_ENABLE | GEMINI_CTRL_IRQ_CLR;
+	writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+	val &= ~GEMINI_CTRL_ENABLE;
+	val |= GEMINI_CTRL_SHUTDOWN;
+	writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+}
+
+static int gemini_poweroff_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct gemini_powercon *gpw;
+	u32 val;
+	int irq;
+	int ret;
+
+	gpw = devm_kzalloc(dev, sizeof(*gpw), GFP_KERNEL);
+	if (!gpw)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gpw->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(gpw->base))
+		return PTR_ERR(gpw->base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (!irq)
+		return -EINVAL;
+
+	gpw->dev = dev;
+
+	val = readl(gpw->base + GEMINI_PWC_IDREG);
+	val &= 0xFFFFFF00U;
+	if (val != GEMINI_PWC_ID) {
+		dev_err(dev, "wrong power controller ID: %08x\n",
+			val);
+		return -ENODEV;
+	}
+
+	/* Clear the power management IRQ */
+	val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+	val |= GEMINI_CTRL_IRQ_CLR;
+	writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+	ret = devm_request_irq(dev, irq, gemini_powerbutton_interrupt, 0,
+			       "poweroff", gpw);
+	if (ret)
+		return ret;
+
+	pm_power_off = gemini_poweroff;
+	gpw_poweroff = gpw;
+
+	/*
+	 * Enable the power controller. This is crucial on Gemini
+	 * systems: if this is not done, pressing the power button
+	 * will result in unconditional poweroff without any warning.
+	 * This makes the kernel handle the poweroff.
+	 */
+	val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+	val |= GEMINI_CTRL_ENABLE;
+	writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+	dev_info(dev, "Gemini poweroff driver registered\n");
+
+	return 0;
+}
+
+static const struct of_device_id gemini_poweroff_of_match[] = {
+	{
+		.compatible = "cortina,gemini-power-controller",
+	},
+	{}
+};
+
+static struct platform_driver gemini_poweroff_driver = {
+	.probe = gemini_poweroff_probe,
+	.driver = {
+		.name = "gemini-poweroff",
+		.of_match_table = gemini_poweroff_of_match,
+	},
+};
+builtin_platform_driver(gemini_poweroff_driver);
diff --git a/drivers/power/reset/syscon-poweroff.c b/drivers/power/reset/syscon-poweroff.c
index b68338399e5e..f9f1cb54fbf9 100644
--- a/drivers/power/reset/syscon-poweroff.c
+++ b/drivers/power/reset/syscon-poweroff.c
@@ -28,12 +28,13 @@
 
 static struct regmap *map;
 static u32 offset;
+static u32 value;
 static u32 mask;
 
 static void syscon_poweroff(void)
 {
 	/* Issue the poweroff */
-	regmap_write(map, offset, mask);
+	regmap_update_bits(map, offset, mask, value);
 
 	mdelay(1000);
 
@@ -43,6 +44,7 @@ static void syscon_poweroff(void)
 static int syscon_poweroff_probe(struct platform_device *pdev)
 {
 	char symname[KSYM_NAME_LEN];
+	int mask_err, value_err;
 
 	map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "regmap");
 	if (IS_ERR(map)) {
@@ -55,11 +57,22 @@ static int syscon_poweroff_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (of_property_read_u32(pdev->dev.of_node, "mask", &mask)) {
-		dev_err(&pdev->dev, "unable to read 'mask'");
+	value_err = of_property_read_u32(pdev->dev.of_node, "value", &value);
+	mask_err = of_property_read_u32(pdev->dev.of_node, "mask", &mask);
+	if (value_err && mask_err) {
+		dev_err(&pdev->dev, "unable to read 'value' and 'mask'");
 		return -EINVAL;
 	}
 
+	if (value_err) {
+		/* support old binding */
+		value = mask;
+		mask = 0xFFFFFFFF;
+	} else if (mask_err) {
+		/* support value without mask*/
+		mask = 0xFFFFFFFF;
+	}
+
 	if (pm_power_off) {
 		lookup_symbol_name((ulong)pm_power_off, symname);
 		dev_err(&pdev->dev,
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index da54ac88f068..da922756149f 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -117,6 +117,12 @@ config BATTERY_DS2782
 	  Say Y here to enable support for the DS2782/DS2786 standalone battery
 	  gas-gauge.
 
+config BATTERY_LEGO_EV3
+	tristate "LEGO MINDSTORMS EV3 battery"
+	depends on OF && IIO && GPIOLIB
+	help
+	  Say Y here to enable support for the LEGO MINDSTORMS EV3 battery.
+
 config BATTERY_PMU
 	tristate "Apple PMU battery"
 	depends on PPC32 && ADB_PMU
@@ -317,6 +323,14 @@ config BATTERY_RX51
 	  Say Y here to enable support for battery information on Nokia
 	  RX-51, also known as N900 tablet.
 
+config CHARGER_CPCAP
+	tristate "CPCAP PMIC Charger Driver"
+	depends on MFD_CPCAP && IIO
+	default MFD_CPCAP
+	help
+	  Say Y to enable support for CPCAP PMIC charger driver for Motorola
+	  mobile devices such as Droid 4.
+
 config CHARGER_ISP1704
 	tristate "ISP1704 USB Charger Detection"
 	depends on USB_PHY
@@ -438,6 +452,7 @@ config CHARGER_BQ2415X
 config CHARGER_BQ24190
 	tristate "TI BQ24190 battery charger driver"
 	depends on I2C
+	depends on EXTCON
 	depends on GPIOLIB || COMPILE_TEST
 	help
 	  Say Y to enable support for the TI BQ24190 battery charger.
diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile
index 3789a2c06fdf..39fc733e6cc4 100644
--- a/drivers/power/supply/Makefile
+++ b/drivers/power/supply/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_BATTERY_DS2781)	+= ds2781_battery.o
 obj-$(CONFIG_BATTERY_DS2782)	+= ds2782_battery.o
 obj-$(CONFIG_BATTERY_GAUGE_LTC2941)	+= ltc2941-battery-gauge.o
 obj-$(CONFIG_BATTERY_GOLDFISH)	+= goldfish_battery.o
+obj-$(CONFIG_BATTERY_LEGO_EV3)	+= lego_ev3_battery.o
 obj-$(CONFIG_BATTERY_PMU)	+= pmu_battery.o
 obj-$(CONFIG_BATTERY_OLPC)	+= olpc_battery.o
 obj-$(CONFIG_BATTERY_TOSA)	+= tosa_battery.o
@@ -51,6 +52,7 @@ obj-$(CONFIG_CHARGER_PCF50633)	+= pcf50633-charger.o
 obj-$(CONFIG_BATTERY_JZ4740)	+= jz4740-battery.o
 obj-$(CONFIG_BATTERY_RX51)	+= rx51_battery.o
 obj-$(CONFIG_AB8500_BM)		+= ab8500_bmdata.o ab8500_charger.o ab8500_fg.o ab8500_btemp.o abx500_chargalg.o pm2301_charger.o
+obj-$(CONFIG_CHARGER_CPCAP)	+= cpcap-charger.o
 obj-$(CONFIG_CHARGER_ISP1704)	+= isp1704_charger.o
 obj-$(CONFIG_CHARGER_MAX8903)	+= max8903_charger.o
 obj-$(CONFIG_CHARGER_TWL4030)	+= twl4030_charger.o
diff --git a/drivers/power/supply/ab8500_bmdata.c b/drivers/power/supply/ab8500_bmdata.c
index d29864533093..8c49586015d0 100644
--- a/drivers/power/supply/ab8500_bmdata.c
+++ b/drivers/power/supply/ab8500_bmdata.c
@@ -430,10 +430,10 @@ static const struct abx500_maxim_parameters ab8500_maxi_params = {
 };
 
 static const struct abx500_maxim_parameters abx540_maxi_params = {
-        .ena_maxi = true,
-        .chg_curr = 3000,
-        .wait_cycles = 10,
-        .charger_curr_step = 200,
+	.ena_maxi = true,
+	.chg_curr = 3000,
+	.wait_cycles = 10,
+	.charger_curr_step = 200,
 };
 
 static const struct abx500_bm_charger_parameters chg = {
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index 6be2fe27bb07..d51ebd1da65e 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/regmap.h>
@@ -113,7 +114,8 @@
 #define ILIM_3000MA			3000	/* 3000mA */
 
 #define AXP288_EXTCON_DEV_NAME		"axp288_extcon"
-#define USB_HOST_EXTCON_DEV_NAME	"INT3496:00"
+#define USB_HOST_EXTCON_HID		"INT3496"
+#define USB_HOST_EXTCON_NAME		"INT3496:00"
 
 static const unsigned int cable_ids[] =
 	{ EXTCON_CHG_USB_SDP, EXTCON_CHG_USB_CDP, EXTCON_CHG_USB_DCP };
@@ -807,10 +809,14 @@ static int axp288_charger_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_DEV_NAME);
-	if (info->otg.cable == NULL) {
-		dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
-		return -EPROBE_DEFER;
+	if (acpi_dev_present(USB_HOST_EXTCON_HID, NULL, -1)) {
+		info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_NAME);
+		if (info->otg.cable == NULL) {
+			dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
+			return -EPROBE_DEFER;
+		}
+		dev_info(&pdev->dev,
+			 "Using " USB_HOST_EXTCON_HID " extcon for usb-id\n");
 	}
 
 	platform_set_drvdata(pdev, info);
@@ -849,13 +855,15 @@ static int axp288_charger_probe(struct platform_device *pdev)
 	/* Register for OTG notification */
 	INIT_WORK(&info->otg.work, axp288_charger_otg_evt_worker);
 	info->otg.id_nb.notifier_call = axp288_charger_handle_otg_evt;
-	ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable,
+	if (info->otg.cable) {
+		ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable,
 					EXTCON_USB_HOST, &info->otg.id_nb);
-	if (ret) {
-		dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n");
-		return ret;
+		if (ret) {
+			dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n");
+			return ret;
+		}
+		schedule_work(&info->otg.work);
 	}
-	schedule_work(&info->otg.work);
 
 	/* Register charger interrupts */
 	for (i = 0; i < CHRG_INTR_END; i++) {
diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index a4f08492abeb..bd9e5c3d8cc2 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -11,16 +11,15 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/extcon.h>
 #include <linux/of_irq.h>
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/power_supply.h>
+#include <linux/workqueue.h>
 #include <linux/gpio.h>
 #include <linux/i2c.h>
 
-#include <linux/power/bq24190_charger.h>
-
-
 #define	BQ24190_MANUFACTURER	"Texas Instruments"
 
 #define BQ24190_REG_ISC		0x00 /* Input Source Control */
@@ -39,6 +38,9 @@
 #define BQ24190_REG_POC_WDT_RESET_SHIFT		6
 #define BQ24190_REG_POC_CHG_CONFIG_MASK		(BIT(5) | BIT(4))
 #define BQ24190_REG_POC_CHG_CONFIG_SHIFT	4
+#define BQ24190_REG_POC_CHG_CONFIG_DISABLE		0x0
+#define BQ24190_REG_POC_CHG_CONFIG_CHARGE		0x1
+#define BQ24190_REG_POC_CHG_CONFIG_OTG			0x2
 #define BQ24190_REG_POC_SYS_MIN_MASK		(BIT(3) | BIT(2) | BIT(1))
 #define BQ24190_REG_POC_SYS_MIN_SHIFT		1
 #define BQ24190_REG_POC_BOOST_LIM_MASK		BIT(0)
@@ -151,10 +153,12 @@ struct bq24190_dev_info {
 	struct device			*dev;
 	struct power_supply		*charger;
 	struct power_supply		*battery;
+	struct extcon_dev		*extcon;
+	struct notifier_block		extcon_nb;
+	struct delayed_work		extcon_work;
 	char				model_name[I2C_NAME_SIZE];
-	kernel_ulong_t			model;
-	unsigned int			gpio_int;
-	unsigned int			irq;
+	bool				initialized;
+	bool				irq_event;
 	struct mutex			f_reg_lock;
 	u8				f_reg;
 	u8				ss_reg;
@@ -168,6 +172,12 @@ struct bq24190_dev_info {
  * number at that index in the array is the real-world value that it
  * represents.
  */
+
+/* REG00[2:0] (IINLIM) in uAh */
+static const int bq24190_isc_iinlim_values[] = {
+	 100000,  150000,  500000,  900000, 1200000, 1500000, 2000000, 3000000
+};
+
 /* REG02[7:2] (ICHG) in uAh */
 static const int bq24190_ccc_ichg_values[] = {
 	 512000,  576000,  640000,  704000,  768000,  832000,  896000,  960000,
@@ -418,6 +428,7 @@ static ssize_t bq24190_sysfs_show(struct device *dev,
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq24190_dev_info *bdi = power_supply_get_drvdata(psy);
 	struct bq24190_sysfs_field_info *info;
+	ssize_t count;
 	int ret;
 	u8 v;
 
@@ -425,11 +436,20 @@ static ssize_t bq24190_sysfs_show(struct device *dev,
 	if (!info)
 		return -EINVAL;
 
+	ret = pm_runtime_get_sync(bdi->dev);
+	if (ret < 0)
+		return ret;
+
 	ret = bq24190_read_mask(bdi, info->reg, info->mask, info->shift, &v);
 	if (ret)
-		return ret;
+		count = ret;
+	else
+		count = scnprintf(buf, PAGE_SIZE, "%hhx\n", v);
+
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%hhx\n", v);
+	return count;
 }
 
 static ssize_t bq24190_sysfs_store(struct device *dev,
@@ -449,9 +469,16 @@ static ssize_t bq24190_sysfs_store(struct device *dev,
 	if (ret < 0)
 		return ret;
 
+	ret = pm_runtime_get_sync(bdi->dev);
+	if (ret < 0)
+		return ret;
+
 	ret = bq24190_write_mask(bdi, info->reg, info->mask, info->shift, v);
 	if (ret)
-		return ret;
+		count = ret;
+
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
 
 	return count;
 }
@@ -523,16 +550,13 @@ static int bq24190_register_reset(struct bq24190_dev_info *bdi)
 		if (ret < 0)
 			return ret;
 
-		if (!v)
-			break;
+		if (v == 0)
+			return 0;
 
-		udelay(10);
+		usleep_range(100, 200);
 	} while (--limit);
 
-	if (!limit)
-		return -EIO;
-
-	return 0;
+	return -EIO;
 }
 
 /* Charger power supply property routines */
@@ -793,7 +817,9 @@ static int bq24190_charger_get_property(struct power_supply *psy,
 
 	dev_dbg(bdi->dev, "prop: %d\n", psp);
 
-	pm_runtime_get_sync(bdi->dev);
+	ret = pm_runtime_get_sync(bdi->dev);
+	if (ret < 0)
+		return ret;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
@@ -833,7 +859,9 @@ static int bq24190_charger_get_property(struct power_supply *psy,
 		ret = -ENODATA;
 	}
 
-	pm_runtime_put_sync(bdi->dev);
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
 	return ret;
 }
 
@@ -846,7 +874,9 @@ static int bq24190_charger_set_property(struct power_supply *psy,
 
 	dev_dbg(bdi->dev, "prop: %d\n", psp);
 
-	pm_runtime_get_sync(bdi->dev);
+	ret = pm_runtime_get_sync(bdi->dev);
+	if (ret < 0)
+		return ret;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
@@ -862,7 +892,9 @@ static int bq24190_charger_set_property(struct power_supply *psy,
 		ret = -EINVAL;
 	}
 
-	pm_runtime_put_sync(bdi->dev);
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
 	return ret;
 }
 
@@ -1063,7 +1095,9 @@ static int bq24190_battery_get_property(struct power_supply *psy,
 
 	dev_dbg(bdi->dev, "prop: %d\n", psp);
 
-	pm_runtime_get_sync(bdi->dev);
+	ret = pm_runtime_get_sync(bdi->dev);
+	if (ret < 0)
+		return ret;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
@@ -1091,7 +1125,9 @@ static int bq24190_battery_get_property(struct power_supply *psy,
 		ret = -ENODATA;
 	}
 
-	pm_runtime_put_sync(bdi->dev);
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
 	return ret;
 }
 
@@ -1104,7 +1140,9 @@ static int bq24190_battery_set_property(struct power_supply *psy,
 
 	dev_dbg(bdi->dev, "prop: %d\n", psp);
 
-	pm_runtime_get_sync(bdi->dev);
+	ret = pm_runtime_get_sync(bdi->dev);
+	if (ret < 0)
+		return ret;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
@@ -1117,7 +1155,9 @@ static int bq24190_battery_set_property(struct power_supply *psy,
 		ret = -EINVAL;
 	}
 
-	pm_runtime_put_sync(bdi->dev);
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
 	return ret;
 }
 
@@ -1157,9 +1197,8 @@ static const struct power_supply_desc bq24190_battery_desc = {
 	.property_is_writeable	= bq24190_battery_property_is_writeable,
 };
 
-static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
+static void bq24190_check_status(struct bq24190_dev_info *bdi)
 {
-	struct bq24190_dev_info *bdi = data;
 	const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
 	const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
 				| BQ24190_REG_F_NTC_FAULT_MASK;
@@ -1167,12 +1206,10 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 	u8 ss_reg = 0, f_reg = 0;
 	int i, ret;
 
-	pm_runtime_get_sync(bdi->dev);
-
 	ret = bq24190_read(bdi, BQ24190_REG_SS, &ss_reg);
 	if (ret < 0) {
 		dev_err(bdi->dev, "Can't read SS reg: %d\n", ret);
-		goto out;
+		return;
 	}
 
 	i = 0;
@@ -1180,12 +1217,17 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 		ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
 		if (ret < 0) {
 			dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
-			goto out;
+			return;
 		}
 	} while (f_reg && ++i < 2);
 
+	/* ignore over/under voltage fault after disconnect */
+	if (f_reg == (1 << BQ24190_REG_F_CHRG_FAULT_SHIFT) &&
+	    !(ss_reg & BQ24190_REG_SS_PG_STAT_MASK))
+		f_reg = 0;
+
 	if (f_reg != bdi->f_reg) {
-		dev_info(bdi->dev,
+		dev_warn(bdi->dev,
 			"Fault: boost %d, charge %d, battery %d, ntc %d\n",
 			!!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
 			!!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
@@ -1229,90 +1271,126 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 	if (alert_battery)
 		power_supply_changed(bdi->battery);
 
-out:
-	pm_runtime_put_sync(bdi->dev);
-
 	dev_dbg(bdi->dev, "ss_reg: 0x%02x, f_reg: 0x%02x\n", ss_reg, f_reg);
+}
+
+static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
+{
+	struct bq24190_dev_info *bdi = data;
+	int error;
+
+	bdi->irq_event = true;
+	error = pm_runtime_get_sync(bdi->dev);
+	if (error < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+		pm_runtime_put_noidle(bdi->dev);
+		return IRQ_NONE;
+	}
+	bq24190_check_status(bdi);
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+	bdi->irq_event = false;
 
 	return IRQ_HANDLED;
 }
 
-static int bq24190_hw_init(struct bq24190_dev_info *bdi)
+static void bq24190_extcon_work(struct work_struct *work)
 {
+	struct bq24190_dev_info *bdi =
+		container_of(work, struct bq24190_dev_info, extcon_work.work);
+	int error, iinlim = 0;
 	u8 v;
-	int ret;
-
-	pm_runtime_get_sync(bdi->dev);
 
-	/* First check that the device really is what its supposed to be */
-	ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
-			BQ24190_REG_VPRS_PN_MASK,
-			BQ24190_REG_VPRS_PN_SHIFT,
-			&v);
-	if (ret < 0)
-		goto out;
+	error = pm_runtime_get_sync(bdi->dev);
+	if (error < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+		pm_runtime_put_noidle(bdi->dev);
+		return;
+	}
 
-	if (v != bdi->model) {
-		ret = -ENODEV;
-		goto out;
+	if      (extcon_get_state(bdi->extcon, EXTCON_CHG_USB_SDP) == 1)
+		iinlim =  500000;
+	else if (extcon_get_state(bdi->extcon, EXTCON_CHG_USB_CDP) == 1 ||
+		 extcon_get_state(bdi->extcon, EXTCON_CHG_USB_ACA) == 1)
+		iinlim = 1500000;
+	else if (extcon_get_state(bdi->extcon, EXTCON_CHG_USB_DCP) == 1)
+		iinlim = 2000000;
+
+	if (iinlim) {
+		error = bq24190_set_field_val(bdi, BQ24190_REG_ISC,
+					      BQ24190_REG_ISC_IINLIM_MASK,
+					      BQ24190_REG_ISC_IINLIM_SHIFT,
+					      bq24190_isc_iinlim_values,
+					      ARRAY_SIZE(bq24190_isc_iinlim_values),
+					      iinlim);
+		if (error < 0)
+			dev_err(bdi->dev, "Can't set IINLIM: %d\n", error);
 	}
 
-	ret = bq24190_register_reset(bdi);
-	if (ret < 0)
-		goto out;
+	/* if no charger found and in USB host mode, set OTG 5V boost, else normal */
+	if (!iinlim && extcon_get_state(bdi->extcon, EXTCON_USB_HOST) == 1)
+		v = BQ24190_REG_POC_CHG_CONFIG_OTG;
+	else
+		v = BQ24190_REG_POC_CHG_CONFIG_CHARGE;
 
-	ret = bq24190_set_mode_host(bdi);
-	if (ret < 0)
-		goto out;
+	error = bq24190_write_mask(bdi, BQ24190_REG_POC,
+				   BQ24190_REG_POC_CHG_CONFIG_MASK,
+				   BQ24190_REG_POC_CHG_CONFIG_SHIFT,
+				   v);
+	if (error < 0)
+		dev_err(bdi->dev, "Can't set CHG_CONFIG: %d\n", error);
 
-	ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
-out:
-	pm_runtime_put_sync(bdi->dev);
-	return ret;
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
 }
 
-#ifdef CONFIG_OF
-static int bq24190_setup_dt(struct bq24190_dev_info *bdi)
+static int bq24190_extcon_event(struct notifier_block *nb, unsigned long event,
+				void *param)
 {
-	bdi->irq = irq_of_parse_and_map(bdi->dev->of_node, 0);
-	if (bdi->irq <= 0)
-		return -1;
+	struct bq24190_dev_info *bdi =
+		container_of(nb, struct bq24190_dev_info, extcon_nb);
 
-	return 0;
-}
-#else
-static int bq24190_setup_dt(struct bq24190_dev_info *bdi)
-{
-	return -1;
+	/*
+	 * The Power-Good detection may take up to 220ms, sometimes
+	 * the external charger detection is quicker, and the bq24190 will
+	 * reset to iinlim based on its own charger detection (which is not
+	 * hooked up when using external charger detection) resulting in
+	 * a too low default 500mA iinlim. Delay applying the extcon value
+	 * for 300ms to avoid this.
+	 */
+	queue_delayed_work(system_wq, &bdi->extcon_work, msecs_to_jiffies(300));
+
+	return NOTIFY_OK;
 }
-#endif
 
-static int bq24190_setup_pdata(struct bq24190_dev_info *bdi,
-		struct bq24190_platform_data *pdata)
+static int bq24190_hw_init(struct bq24190_dev_info *bdi)
 {
+	u8 v;
 	int ret;
 
-	if (!gpio_is_valid(pdata->gpio_int))
-		return -1;
-
-	ret = gpio_request(pdata->gpio_int, dev_name(bdi->dev));
+	/* First check that the device really is what its supposed to be */
+	ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
+			BQ24190_REG_VPRS_PN_MASK,
+			BQ24190_REG_VPRS_PN_SHIFT,
+			&v);
 	if (ret < 0)
-		return -1;
+		return ret;
 
-	ret = gpio_direction_input(pdata->gpio_int);
-	if (ret < 0)
-		goto out;
+	if (v != BQ24190_REG_VPRS_PN_24190 &&
+	    v != BQ24190_REG_VPRS_PN_24192I) {
+		dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v);
+		return -ENODEV;
+	}
 
-	bdi->irq = gpio_to_irq(pdata->gpio_int);
-	if (!bdi->irq)
-		goto out;
+	ret = bq24190_register_reset(bdi);
+	if (ret < 0)
+		return ret;
 
-	bdi->gpio_int = pdata->gpio_int;
-	return 0;
+	ret = bq24190_set_mode_host(bdi);
+	if (ret < 0)
+		return ret;
 
-out:
-	gpio_free(pdata->gpio_int);
-	return -1;
+	return bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
 }
 
 static int bq24190_probe(struct i2c_client *client,
@@ -1320,9 +1398,9 @@ static int bq24190_probe(struct i2c_client *client,
 {
 	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
 	struct device *dev = &client->dev;
-	struct bq24190_platform_data *pdata = client->dev.platform_data;
 	struct power_supply_config charger_cfg = {}, battery_cfg = {};
 	struct bq24190_dev_info *bdi;
+	const char *name;
 	int ret;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
@@ -1338,7 +1416,6 @@ static int bq24190_probe(struct i2c_client *client,
 
 	bdi->client = client;
 	bdi->dev = dev;
-	bdi->model = id->driver_data;
 	strncpy(bdi->model_name, id->name, I2C_NAME_SIZE);
 	mutex_init(&bdi->f_reg_lock);
 	bdi->f_reg = 0;
@@ -1346,23 +1423,43 @@ static int bq24190_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, bdi);
 
-	if (dev->of_node)
-		ret = bq24190_setup_dt(bdi);
-	else
-		ret = bq24190_setup_pdata(bdi, pdata);
-
-	if (ret) {
+	if (!client->irq) {
 		dev_err(dev, "Can't get irq info\n");
 		return -EINVAL;
 	}
 
+	/*
+	 * Devicetree platforms should get extcon via phandle (not yet supported).
+	 * On ACPI platforms, extcon clients may invoke us with:
+	 * struct property_entry pe[] =
+	 *   { PROPERTY_ENTRY_STRING("extcon-name", client_name), ... };
+	 * struct i2c_board_info bi =
+	 *   { .type = "bq24190", .addr = 0x6b, .properties = pe, .irq = irq };
+	 * struct i2c_adapter ad = { ... };
+	 * i2c_add_adapter(&ad);
+	 * i2c_new_device(&ad, &bi);
+	 */
+	if (device_property_read_string(dev, "extcon-name", &name) == 0) {
+		bdi->extcon = extcon_get_extcon_dev(name);
+		if (!bdi->extcon)
+			return -EPROBE_DEFER;
+
+		dev_info(bdi->dev, "using extcon device %s\n", name);
+	}
+
 	pm_runtime_enable(dev);
-	pm_runtime_resume(dev);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, 600);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm_runtime_get failed: %i\n", ret);
+		goto out_pmrt;
+	}
 
 	ret = bq24190_hw_init(bdi);
 	if (ret < 0) {
 		dev_err(dev, "Hardware init failed\n");
-		goto out1;
+		goto out_pmrt;
 	}
 
 	charger_cfg.drv_data = bdi;
@@ -1373,7 +1470,7 @@ static int bq24190_probe(struct i2c_client *client,
 	if (IS_ERR(bdi->charger)) {
 		dev_err(dev, "Can't register charger\n");
 		ret = PTR_ERR(bdi->charger);
-		goto out1;
+		goto out_pmrt;
 	}
 
 	battery_cfg.drv_data = bdi;
@@ -1382,87 +1479,160 @@ static int bq24190_probe(struct i2c_client *client,
 	if (IS_ERR(bdi->battery)) {
 		dev_err(dev, "Can't register battery\n");
 		ret = PTR_ERR(bdi->battery);
-		goto out2;
+		goto out_charger;
 	}
 
 	ret = bq24190_sysfs_create_group(bdi);
 	if (ret) {
 		dev_err(dev, "Can't create sysfs entries\n");
-		goto out3;
+		goto out_battery;
 	}
 
-	ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
+	bdi->initialized = true;
+
+	ret = devm_request_threaded_irq(dev, client->irq, NULL,
 			bq24190_irq_handler_thread,
 			IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 			"bq24190-charger", bdi);
 	if (ret < 0) {
 		dev_err(dev, "Can't set up irq handler\n");
-		goto out4;
+		goto out_sysfs;
+	}
+
+	if (bdi->extcon) {
+		INIT_DELAYED_WORK(&bdi->extcon_work, bq24190_extcon_work);
+		bdi->extcon_nb.notifier_call = bq24190_extcon_event;
+		ret = devm_extcon_register_notifier_all(dev, bdi->extcon,
+							&bdi->extcon_nb);
+		if (ret) {
+			dev_err(dev, "Can't register extcon\n");
+			goto out_sysfs;
+		}
+
+		/* Sync initial cable state */
+		queue_delayed_work(system_wq, &bdi->extcon_work, 0);
 	}
 
+	enable_irq_wake(client->irq);
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
 	return 0;
 
-out4:
+out_sysfs:
 	bq24190_sysfs_remove_group(bdi);
 
-out3:
+out_battery:
 	power_supply_unregister(bdi->battery);
 
-out2:
+out_charger:
 	power_supply_unregister(bdi->charger);
 
-out1:
+out_pmrt:
+	pm_runtime_put_sync(dev);
+	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
-	if (bdi->gpio_int)
-		gpio_free(bdi->gpio_int);
 	return ret;
 }
 
 static int bq24190_remove(struct i2c_client *client)
 {
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+	int error;
 
-	pm_runtime_get_sync(bdi->dev);
-	bq24190_register_reset(bdi);
-	pm_runtime_put_sync(bdi->dev);
+	error = pm_runtime_get_sync(bdi->dev);
+	if (error < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+		pm_runtime_put_noidle(bdi->dev);
+	}
 
+	bq24190_register_reset(bdi);
 	bq24190_sysfs_remove_group(bdi);
 	power_supply_unregister(bdi->battery);
 	power_supply_unregister(bdi->charger);
+	if (error >= 0)
+		pm_runtime_put_sync(bdi->dev);
+	pm_runtime_dont_use_autosuspend(bdi->dev);
 	pm_runtime_disable(bdi->dev);
 
-	if (bdi->gpio_int)
-		gpio_free(bdi->gpio_int);
+	return 0;
+}
+
+static __maybe_unused int bq24190_runtime_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+
+	if (!bdi->initialized)
+		return 0;
+
+	dev_dbg(bdi->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static __maybe_unused int bq24190_runtime_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+
+	if (!bdi->initialized)
+		return 0;
+
+	if (!bdi->irq_event) {
+		dev_dbg(bdi->dev, "checking events on possible wakeirq\n");
+		bq24190_check_status(bdi);
+	}
 
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int bq24190_pm_suspend(struct device *dev)
+static __maybe_unused int bq24190_pm_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+	int error;
+
+	error = pm_runtime_get_sync(bdi->dev);
+	if (error < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+		pm_runtime_put_noidle(bdi->dev);
+	}
 
-	pm_runtime_get_sync(bdi->dev);
 	bq24190_register_reset(bdi);
-	pm_runtime_put_sync(bdi->dev);
+
+	if (error >= 0) {
+		pm_runtime_mark_last_busy(bdi->dev);
+		pm_runtime_put_autosuspend(bdi->dev);
+	}
 
 	return 0;
 }
 
-static int bq24190_pm_resume(struct device *dev)
+static __maybe_unused int bq24190_pm_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+	int error;
 
 	bdi->f_reg = 0;
 	bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
 
-	pm_runtime_get_sync(bdi->dev);
+	error = pm_runtime_get_sync(bdi->dev);
+	if (error < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+		pm_runtime_put_noidle(bdi->dev);
+	}
+
 	bq24190_register_reset(bdi);
 	bq24190_set_mode_host(bdi);
 	bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
-	pm_runtime_put_sync(bdi->dev);
+
+	if (error >= 0) {
+		pm_runtime_mark_last_busy(bdi->dev);
+		pm_runtime_put_autosuspend(bdi->dev);
+	}
 
 	/* Things may have changed while suspended so alert upper layer */
 	power_supply_changed(bdi->charger);
@@ -1470,17 +1640,16 @@ static int bq24190_pm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(bq24190_pm_ops, bq24190_pm_suspend, bq24190_pm_resume);
+static const struct dev_pm_ops bq24190_pm_ops = {
+	SET_RUNTIME_PM_OPS(bq24190_runtime_suspend, bq24190_runtime_resume,
+			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(bq24190_pm_suspend, bq24190_pm_resume)
+};
 
-/*
- * Only support the bq24190 right now.  The bq24192, bq24192i, and bq24193
- * are similar but not identical so the driver needs to be extended to
- * support them.
- */
 static const struct i2c_device_id bq24190_i2c_ids[] = {
-	{ "bq24190", BQ24190_REG_VPRS_PN_24190 },
+	{ "bq24190" },
+	{ "bq24192i" },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids);
diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c
index f993a55cde20..8e2c41ded171 100644
--- a/drivers/power/supply/bq25890_charger.c
+++ b/drivers/power/supply/bq25890_charger.c
@@ -723,7 +723,7 @@ static int bq25890_irq_probe(struct bq25890_device *bq)
 {
 	struct gpio_desc *irq;
 
-	irq = devm_gpiod_get_index(bq->dev, BQ25890_IRQ_PIN, 0, GPIOD_IN);
+	irq = devm_gpiod_get(bq->dev, BQ25890_IRQ_PIN, GPIOD_IN);
 	if (IS_ERR(irq)) {
 		dev_err(bq->dev, "Could not probe irq pin.\n");
 		return PTR_ERR(irq);
diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index e664ca7c0afd..adc3761831e1 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -1198,7 +1198,7 @@ static int charger_extcon_notifier(struct notifier_block *self,
 static int charger_extcon_init(struct charger_manager *cm,
 		struct charger_cable *cable)
 {
-	int ret = 0;
+	int ret;
 
 	/*
 	 * Charger manager use Extcon framework to identify
@@ -1232,7 +1232,7 @@ static int charger_manager_register_extcon(struct charger_manager *cm)
 {
 	struct charger_desc *desc = cm->desc;
 	struct charger_regulator *charger;
-	int ret = 0;
+	int ret;
 	int i;
 	int j;
 
@@ -1255,15 +1255,14 @@ static int charger_manager_register_extcon(struct charger_manager *cm)
 			if (ret < 0) {
 				dev_err(cm->dev, "Cannot initialize charger(%s)\n",
 					charger->regulator_name);
-				goto err;
+				return ret;
 			}
 			cable->charger = charger;
 			cable->cm = cm;
 		}
 	}
 
-err:
-	return ret;
+	return 0;
 }
 
 /* help function of sysfs node to control charger(regulator) */
@@ -1372,7 +1371,7 @@ static int charger_manager_register_sysfs(struct charger_manager *cm)
 	int chargers_externally_control = 1;
 	char buf[11];
 	char *str;
-	int ret = 0;
+	int ret;
 	int i;
 
 	/* Create sysfs entry to control charger(regulator) */
@@ -1382,10 +1381,9 @@ static int charger_manager_register_sysfs(struct charger_manager *cm)
 		snprintf(buf, 10, "charger.%d", i);
 		str = devm_kzalloc(cm->dev,
 				sizeof(char) * (strlen(buf) + 1), GFP_KERNEL);
-		if (!str) {
-			ret = -ENOMEM;
-			goto err;
-		}
+		if (!str)
+			return -ENOMEM;
+
 		strcpy(str, buf);
 
 		charger->attrs[0] = &charger->attr_name.attr;
@@ -1426,19 +1424,16 @@ static int charger_manager_register_sysfs(struct charger_manager *cm)
 		if (ret < 0) {
 			dev_err(cm->dev, "Cannot create sysfs entry of %s regulator\n",
 				charger->regulator_name);
-			ret = -EINVAL;
-			goto err;
+			return ret;
 		}
 	}
 
 	if (chargers_externally_control) {
 		dev_err(cm->dev, "Cannot register regulator because charger-manager must need at least one charger for charging battery\n");
-		ret = -EINVAL;
-		goto err;
+		return -EINVAL;
 	}
 
-err:
-	return ret;
+	return 0;
 }
 
 static int cm_init_thermal_data(struct charger_manager *cm,
@@ -1626,7 +1621,7 @@ static int charger_manager_probe(struct platform_device *pdev)
 {
 	struct charger_desc *desc = cm_get_drv_data(pdev);
 	struct charger_manager *cm;
-	int ret = 0, i = 0;
+	int ret, i = 0;
 	int j = 0;
 	union power_supply_propval val;
 	struct power_supply *fuel_gauge;
@@ -1887,14 +1882,12 @@ MODULE_DEVICE_TABLE(platform, charger_manager_id);
 
 static int cm_suspend_noirq(struct device *dev)
 {
-	int ret = 0;
-
 	if (device_may_wakeup(dev)) {
 		device_set_wakeup_capable(dev, false);
-		ret = -EAGAIN;
+		return -EAGAIN;
 	}
 
-	return ret;
+	return 0;
 }
 
 static bool cm_need_to_awake(void)
diff --git a/drivers/power/supply/cpcap-charger.c b/drivers/power/supply/cpcap-charger.c
new file mode 100644
index 000000000000..543a1bd21ab9
--- /dev/null
+++ b/drivers/power/supply/cpcap-charger.c
@@ -0,0 +1,681 @@
+/*
+ * Motorola CPCAP PMIC battery charger driver
+ *
+ * Copyright (C) 2017 Tony Lindgren <tony@atomide.com>
+ *
+ * Rewritten for Linux power framework with some parts based on
+ * on earlier driver found in the Motorola Linux kernel:
+ *
+ * Copyright (C) 2009-2010 Motorola, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/atomic.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/regmap.h>
+
+#include <linux/gpio/consumer.h>
+#include <linux/usb/phy_companion.h>
+#include <linux/phy/omap_usb.h>
+#include <linux/usb/otg.h>
+#include <linux/iio/consumer.h>
+#include <linux/mfd/motorola-cpcap.h>
+
+/* CPCAP_REG_CRM register bits */
+#define CPCAP_REG_CRM_UNUSED_641_15	BIT(15)	/* 641 = register number */
+#define CPCAP_REG_CRM_UNUSED_641_14	BIT(14)	/* 641 = register number */
+#define CPCAP_REG_CRM_CHRG_LED_EN	BIT(13)
+#define CPCAP_REG_CRM_RVRSMODE		BIT(12)
+#define CPCAP_REG_CRM_ICHRG_TR1		BIT(11)
+#define CPCAP_REG_CRM_ICHRG_TR0		BIT(10)
+#define CPCAP_REG_CRM_FET_OVRD		BIT(9)
+#define CPCAP_REG_CRM_FET_CTRL		BIT(8)
+#define CPCAP_REG_CRM_VCHRG3		BIT(7)
+#define CPCAP_REG_CRM_VCHRG2		BIT(6)
+#define CPCAP_REG_CRM_VCHRG1		BIT(5)
+#define CPCAP_REG_CRM_VCHRG0		BIT(4)
+#define CPCAP_REG_CRM_ICHRG3		BIT(3)
+#define CPCAP_REG_CRM_ICHRG2		BIT(2)
+#define CPCAP_REG_CRM_ICHRG1		BIT(1)
+#define CPCAP_REG_CRM_ICHRG0		BIT(0)
+
+/* CPCAP_REG_CRM trickle charge voltages */
+#define CPCAP_REG_CRM_TR(val)		(((val) & 0x3) << 10)
+#define CPCAP_REG_CRM_TR_0A00		CPCAP_REG_CRM_TR(0x0)
+#define CPCAP_REG_CRM_TR_0A24		CPCAP_REG_CRM_TR(0x1)
+#define CPCAP_REG_CRM_TR_0A48		CPCAP_REG_CRM_TR(0x2)
+#define CPCAP_REG_CRM_TR_0A72		CPCAP_REG_CRM_TR(0x4)
+
+/* CPCAP_REG_CRM charge voltages */
+#define CPCAP_REG_CRM_VCHRG(val)	(((val) & 0xf) << 4)
+#define CPCAP_REG_CRM_VCHRG_3V80	CPCAP_REG_CRM_VCHRG(0x0)
+#define CPCAP_REG_CRM_VCHRG_4V10	CPCAP_REG_CRM_VCHRG(0x1)
+#define CPCAP_REG_CRM_VCHRG_4V15	CPCAP_REG_CRM_VCHRG(0x2)
+#define CPCAP_REG_CRM_VCHRG_4V20	CPCAP_REG_CRM_VCHRG(0x3)
+#define CPCAP_REG_CRM_VCHRG_4V22	CPCAP_REG_CRM_VCHRG(0x4)
+#define CPCAP_REG_CRM_VCHRG_4V24	CPCAP_REG_CRM_VCHRG(0x5)
+#define CPCAP_REG_CRM_VCHRG_4V26	CPCAP_REG_CRM_VCHRG(0x6)
+#define CPCAP_REG_CRM_VCHRG_4V28	CPCAP_REG_CRM_VCHRG(0x7)
+#define CPCAP_REG_CRM_VCHRG_4V30	CPCAP_REG_CRM_VCHRG(0x8)
+#define CPCAP_REG_CRM_VCHRG_4V32	CPCAP_REG_CRM_VCHRG(0x9)
+#define CPCAP_REG_CRM_VCHRG_4V34	CPCAP_REG_CRM_VCHRG(0xa)
+#define CPCAP_REG_CRM_VCHRG_4V36	CPCAP_REG_CRM_VCHRG(0xb)
+#define CPCAP_REG_CRM_VCHRG_4V38	CPCAP_REG_CRM_VCHRG(0xc)
+#define CPCAP_REG_CRM_VCHRG_4V40	CPCAP_REG_CRM_VCHRG(0xd)
+#define CPCAP_REG_CRM_VCHRG_4V42	CPCAP_REG_CRM_VCHRG(0xe)
+#define CPCAP_REG_CRM_VCHRG_4V44	CPCAP_REG_CRM_VCHRG(0xf)
+
+/* CPCAP_REG_CRM charge currents */
+#define CPCAP_REG_CRM_ICHRG(val)	(((val) & 0xf) << 0)
+#define CPCAP_REG_CRM_ICHRG_0A000	CPCAP_REG_CRM_ICHRG(0x0)
+#define CPCAP_REG_CRM_ICHRG_0A070	CPCAP_REG_CRM_ICHRG(0x1)
+#define CPCAP_REG_CRM_ICHRG_0A176	CPCAP_REG_CRM_ICHRG(0x2)
+#define CPCAP_REG_CRM_ICHRG_0A264	CPCAP_REG_CRM_ICHRG(0x3)
+#define CPCAP_REG_CRM_ICHRG_0A352	CPCAP_REG_CRM_ICHRG(0x4)
+#define CPCAP_REG_CRM_ICHRG_0A440	CPCAP_REG_CRM_ICHRG(0x5)
+#define CPCAP_REG_CRM_ICHRG_0A528	CPCAP_REG_CRM_ICHRG(0x6)
+#define CPCAP_REG_CRM_ICHRG_0A616	CPCAP_REG_CRM_ICHRG(0x7)
+#define CPCAP_REG_CRM_ICHRG_0A704	CPCAP_REG_CRM_ICHRG(0x8)
+#define CPCAP_REG_CRM_ICHRG_0A792	CPCAP_REG_CRM_ICHRG(0x9)
+#define CPCAP_REG_CRM_ICHRG_0A880	CPCAP_REG_CRM_ICHRG(0xa)
+#define CPCAP_REG_CRM_ICHRG_0A968	CPCAP_REG_CRM_ICHRG(0xb)
+#define CPCAP_REG_CRM_ICHRG_1A056	CPCAP_REG_CRM_ICHRG(0xc)
+#define CPCAP_REG_CRM_ICHRG_1A144	CPCAP_REG_CRM_ICHRG(0xd)
+#define CPCAP_REG_CRM_ICHRG_1A584	CPCAP_REG_CRM_ICHRG(0xe)
+#define CPCAP_REG_CRM_ICHRG_NO_LIMIT	CPCAP_REG_CRM_ICHRG(0xf)
+
+enum {
+	CPCAP_CHARGER_IIO_BATTDET,
+	CPCAP_CHARGER_IIO_VOLTAGE,
+	CPCAP_CHARGER_IIO_VBUS,
+	CPCAP_CHARGER_IIO_CHRG_CURRENT,
+	CPCAP_CHARGER_IIO_BATT_CURRENT,
+	CPCAP_CHARGER_IIO_NR,
+};
+
+struct cpcap_charger_ddata {
+	struct device *dev;
+	struct regmap *reg;
+	struct list_head irq_list;
+	struct delayed_work detect_work;
+	struct delayed_work vbus_work;
+	struct gpio_desc *gpio[2];		/* gpio_reven0 & 1 */
+
+	struct iio_channel *channels[CPCAP_CHARGER_IIO_NR];
+
+	struct power_supply *usb;
+
+	struct phy_companion comparator;	/* For USB VBUS */
+	bool vbus_enabled;
+	atomic_t active;
+
+	int status;
+};
+
+struct cpcap_interrupt_desc {
+	int irq;
+	struct list_head node;
+	const char *name;
+};
+
+struct cpcap_charger_ints_state {
+	bool chrg_det;
+	bool rvrs_chrg;
+	bool vbusov;
+
+	bool chrg_se1b;
+	bool rvrs_mode;
+	bool chrgcurr1;
+	bool vbusvld;
+
+	bool battdetb;
+};
+
+static enum power_supply_property cpcap_charger_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+static bool cpcap_charger_battery_found(struct cpcap_charger_ddata *ddata)
+{
+	struct iio_channel *channel;
+	int error, value;
+
+	channel = ddata->channels[CPCAP_CHARGER_IIO_BATTDET];
+	error = iio_read_channel_raw(channel, &value);
+	if (error < 0) {
+		dev_warn(ddata->dev, "%s failed: %i\n", __func__, error);
+
+		return false;
+	}
+
+	return value == 1;
+}
+
+static int cpcap_charger_get_charge_voltage(struct cpcap_charger_ddata *ddata)
+{
+	struct iio_channel *channel;
+	int error, value = 0;
+
+	channel = ddata->channels[CPCAP_CHARGER_IIO_VOLTAGE];
+	error = iio_read_channel_processed(channel, &value);
+	if (error < 0) {
+		dev_warn(ddata->dev, "%s failed: %i\n", __func__, error);
+
+		return 0;
+	}
+
+	return value;
+}
+
+static int cpcap_charger_get_charge_current(struct cpcap_charger_ddata *ddata)
+{
+	struct iio_channel *channel;
+	int error, value = 0;
+
+	channel = ddata->channels[CPCAP_CHARGER_IIO_CHRG_CURRENT];
+	error = iio_read_channel_processed(channel, &value);
+	if (error < 0) {
+		dev_warn(ddata->dev, "%s failed: %i\n", __func__, error);
+
+		return 0;
+	}
+
+	return value;
+}
+
+static int cpcap_charger_get_property(struct power_supply *psy,
+				      enum power_supply_property psp,
+				      union power_supply_propval *val)
+{
+	struct cpcap_charger_ddata *ddata = dev_get_drvdata(psy->dev.parent);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		val->intval = ddata->status;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		if (ddata->status == POWER_SUPPLY_STATUS_CHARGING)
+			val->intval = cpcap_charger_get_charge_voltage(ddata) *
+				1000;
+		else
+			val->intval = 0;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		if (ddata->status == POWER_SUPPLY_STATUS_CHARGING)
+			val->intval = cpcap_charger_get_charge_current(ddata) *
+				1000;
+		else
+			val->intval = 0;
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = ddata->status == POWER_SUPPLY_STATUS_CHARGING;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void cpcap_charger_set_cable_path(struct cpcap_charger_ddata *ddata,
+					 bool enabled)
+{
+	if (!ddata->gpio[0])
+		return;
+
+	gpiod_set_value(ddata->gpio[0], enabled);
+}
+
+static void cpcap_charger_set_inductive_path(struct cpcap_charger_ddata *ddata,
+					     bool enabled)
+{
+	if (!ddata->gpio[1])
+		return;
+
+	gpiod_set_value(ddata->gpio[1], enabled);
+}
+
+static int cpcap_charger_set_state(struct cpcap_charger_ddata *ddata,
+				   int max_voltage, int charge_current,
+				   int trickle_current)
+{
+	bool enable;
+	int error;
+
+	enable = max_voltage && (charge_current || trickle_current);
+	dev_dbg(ddata->dev, "%s enable: %i\n", __func__, enable);
+
+	if (!enable) {
+		error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM,
+					   0x3fff,
+					   CPCAP_REG_CRM_FET_OVRD |
+					   CPCAP_REG_CRM_FET_CTRL);
+		if (error) {
+			ddata->status = POWER_SUPPLY_STATUS_UNKNOWN;
+			goto out_err;
+		}
+
+		ddata->status = POWER_SUPPLY_STATUS_DISCHARGING;
+
+		return 0;
+	}
+
+	error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM, 0x3fff,
+				   CPCAP_REG_CRM_CHRG_LED_EN |
+				   trickle_current |
+				   CPCAP_REG_CRM_FET_OVRD |
+				   CPCAP_REG_CRM_FET_CTRL |
+				   max_voltage |
+				   charge_current);
+	if (error) {
+		ddata->status = POWER_SUPPLY_STATUS_UNKNOWN;
+		goto out_err;
+	}
+
+	ddata->status = POWER_SUPPLY_STATUS_CHARGING;
+
+	return 0;
+
+out_err:
+	dev_err(ddata->dev, "%s failed with %i\n", __func__, error);
+
+	return error;
+}
+
+static bool cpcap_charger_vbus_valid(struct cpcap_charger_ddata *ddata)
+{
+	int error, value = 0;
+	struct iio_channel *channel =
+		ddata->channels[CPCAP_CHARGER_IIO_VBUS];
+
+	error = iio_read_channel_processed(channel, &value);
+	if (error >= 0)
+		return value > 3900 ? true : false;
+
+	dev_err(ddata->dev, "error reading VBUS: %i\n", error);
+
+	return false;
+}
+
+/* VBUS control functions for the USB PHY companion */
+
+static void cpcap_charger_vbus_work(struct work_struct *work)
+{
+	struct cpcap_charger_ddata *ddata;
+	bool vbus = false;
+	int error;
+
+	ddata = container_of(work, struct cpcap_charger_ddata,
+			     vbus_work.work);
+
+	if (ddata->vbus_enabled) {
+		vbus = cpcap_charger_vbus_valid(ddata);
+		if (vbus) {
+			dev_info(ddata->dev, "VBUS already provided\n");
+
+			return;
+		}
+
+		cpcap_charger_set_cable_path(ddata, false);
+		cpcap_charger_set_inductive_path(ddata, false);
+
+		error = cpcap_charger_set_state(ddata, 0, 0, 0);
+		if (error)
+			goto out_err;
+
+		error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM,
+					   CPCAP_REG_CRM_RVRSMODE,
+					   CPCAP_REG_CRM_RVRSMODE);
+		if (error)
+			goto out_err;
+	} else {
+		error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM,
+					   CPCAP_REG_CRM_RVRSMODE, 0);
+		if (error)
+			goto out_err;
+
+		cpcap_charger_set_cable_path(ddata, true);
+		cpcap_charger_set_inductive_path(ddata, true);
+	}
+
+	return;
+
+out_err:
+	dev_err(ddata->dev, "%s could not %s vbus: %i\n", __func__,
+		ddata->vbus_enabled ? "enable" : "disable", error);
+}
+
+static int cpcap_charger_set_vbus(struct phy_companion *comparator,
+				  bool enabled)
+{
+	struct cpcap_charger_ddata *ddata =
+		container_of(comparator, struct cpcap_charger_ddata,
+			     comparator);
+
+	ddata->vbus_enabled = enabled;
+	schedule_delayed_work(&ddata->vbus_work, 0);
+
+	return 0;
+}
+
+/* Charger interrupt handling functions */
+
+static int cpcap_charger_get_ints_state(struct cpcap_charger_ddata *ddata,
+					struct cpcap_charger_ints_state *s)
+{
+	int val, error;
+
+	error = regmap_read(ddata->reg, CPCAP_REG_INTS1, &val);
+	if (error)
+		return error;
+
+	s->chrg_det = val & BIT(13);
+	s->rvrs_chrg = val & BIT(12);
+	s->vbusov = val & BIT(11);
+
+	error = regmap_read(ddata->reg, CPCAP_REG_INTS2, &val);
+	if (error)
+		return error;
+
+	s->chrg_se1b = val & BIT(13);
+	s->rvrs_mode = val & BIT(6);
+	s->chrgcurr1 = val & BIT(4);
+	s->vbusvld = val & BIT(3);
+
+	error = regmap_read(ddata->reg, CPCAP_REG_INTS4, &val);
+	if (error)
+		return error;
+
+	s->battdetb = val & BIT(6);
+
+	return 0;
+}
+
+static void cpcap_usb_detect(struct work_struct *work)
+{
+	struct cpcap_charger_ddata *ddata;
+	struct cpcap_charger_ints_state s;
+	int error;
+
+	ddata = container_of(work, struct cpcap_charger_ddata,
+			     detect_work.work);
+
+	error = cpcap_charger_get_ints_state(ddata, &s);
+	if (error)
+		return;
+
+	if (cpcap_charger_vbus_valid(ddata) && s.chrgcurr1) {
+		int max_current;
+
+		if (cpcap_charger_battery_found(ddata))
+			max_current = CPCAP_REG_CRM_ICHRG_1A584;
+		else
+			max_current = CPCAP_REG_CRM_ICHRG_0A528;
+
+		error = cpcap_charger_set_state(ddata,
+						CPCAP_REG_CRM_VCHRG_4V20,
+						max_current,
+						CPCAP_REG_CRM_TR_0A72);
+		if (error)
+			goto out_err;
+	} else {
+		error = cpcap_charger_set_state(ddata, 0, 0, 0);
+		if (error)
+			goto out_err;
+	}
+
+	return;
+
+out_err:
+	dev_err(ddata->dev, "%s failed with %i\n", __func__, error);
+}
+
+static irqreturn_t cpcap_charger_irq_thread(int irq, void *data)
+{
+	struct cpcap_charger_ddata *ddata = data;
+
+	if (!atomic_read(&ddata->active))
+		return IRQ_NONE;
+
+	schedule_delayed_work(&ddata->detect_work, 0);
+
+	return IRQ_HANDLED;
+}
+
+static int cpcap_usb_init_irq(struct platform_device *pdev,
+			      struct cpcap_charger_ddata *ddata,
+			      const char *name)
+{
+	struct cpcap_interrupt_desc *d;
+	int irq, error;
+
+	irq = platform_get_irq_byname(pdev, name);
+	if (!irq)
+		return -ENODEV;
+
+	error = devm_request_threaded_irq(ddata->dev, irq, NULL,
+					  cpcap_charger_irq_thread,
+					  IRQF_SHARED,
+					  name, ddata);
+	if (error) {
+		dev_err(ddata->dev, "could not get irq %s: %i\n",
+			name, error);
+
+		return error;
+	}
+
+	d = devm_kzalloc(ddata->dev, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	d->name = name;
+	d->irq = irq;
+	list_add(&d->node, &ddata->irq_list);
+
+	return 0;
+}
+
+static const char * const cpcap_charger_irqs[] = {
+	/* REG_INT_0 */
+	"chrg_det", "rvrs_chrg",
+
+	/* REG_INT1 */
+	"chrg_se1b", "se0conn", "rvrs_mode", "chrgcurr1", "vbusvld",
+
+	/* REG_INT_3 */
+	"battdetb",
+};
+
+static int cpcap_usb_init_interrupts(struct platform_device *pdev,
+				     struct cpcap_charger_ddata *ddata)
+{
+	int i, error;
+
+	for (i = 0; i < ARRAY_SIZE(cpcap_charger_irqs); i++) {
+		error = cpcap_usb_init_irq(pdev, ddata, cpcap_charger_irqs[i]);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static void cpcap_charger_init_optional_gpios(struct cpcap_charger_ddata *ddata)
+{
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		ddata->gpio[i] = devm_gpiod_get_index(ddata->dev, "mode",
+						      i, GPIOD_OUT_HIGH);
+		if (IS_ERR(ddata->gpio[i])) {
+			dev_info(ddata->dev, "no mode change GPIO%i: %li\n",
+				 i, PTR_ERR(ddata->gpio[i]));
+				 ddata->gpio[i] = NULL;
+		}
+	}
+}
+
+static int cpcap_charger_init_iio(struct cpcap_charger_ddata *ddata)
+{
+	const char * const names[CPCAP_CHARGER_IIO_NR] = {
+		"battdetb", "battp", "vbus", "chg_isense", "batti",
+	};
+	int error, i;
+
+	for (i = 0; i < CPCAP_CHARGER_IIO_NR; i++) {
+		ddata->channels[i] = devm_iio_channel_get(ddata->dev,
+							  names[i]);
+		if (IS_ERR(ddata->channels[i])) {
+			error = PTR_ERR(ddata->channels[i]);
+			goto out_err;
+		}
+
+		if (!ddata->channels[i]->indio_dev) {
+			error = -ENXIO;
+			goto out_err;
+		}
+	}
+
+	return 0;
+
+out_err:
+	dev_err(ddata->dev, "could not initialize VBUS or ID IIO: %i\n",
+		error);
+
+	return error;
+}
+
+static const struct power_supply_desc cpcap_charger_usb_desc = {
+	.name		= "cpcap_usb",
+	.type		= POWER_SUPPLY_TYPE_USB,
+	.properties	= cpcap_charger_props,
+	.num_properties	= ARRAY_SIZE(cpcap_charger_props),
+	.get_property	= cpcap_charger_get_property,
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id cpcap_charger_id_table[] = {
+	{
+		.compatible = "motorola,mapphone-cpcap-charger",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, cpcap_charger_id_table);
+#endif
+
+static int cpcap_charger_probe(struct platform_device *pdev)
+{
+	struct cpcap_charger_ddata *ddata;
+	const struct of_device_id *of_id;
+	int error;
+
+	of_id = of_match_device(of_match_ptr(cpcap_charger_id_table),
+				&pdev->dev);
+	if (!of_id)
+		return -EINVAL;
+
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	ddata->dev = &pdev->dev;
+
+	ddata->reg = dev_get_regmap(ddata->dev->parent, NULL);
+	if (!ddata->reg)
+		return -ENODEV;
+
+	INIT_LIST_HEAD(&ddata->irq_list);
+	INIT_DELAYED_WORK(&ddata->detect_work, cpcap_usb_detect);
+	INIT_DELAYED_WORK(&ddata->vbus_work, cpcap_charger_vbus_work);
+	platform_set_drvdata(pdev, ddata);
+
+	error = cpcap_charger_init_iio(ddata);
+	if (error)
+		return error;
+
+	atomic_set(&ddata->active, 1);
+
+	ddata->usb = devm_power_supply_register(ddata->dev,
+						&cpcap_charger_usb_desc,
+						NULL);
+	if (IS_ERR(ddata->usb)) {
+		error = PTR_ERR(ddata->usb);
+		dev_err(ddata->dev, "failed to register USB charger: %i\n",
+			error);
+
+		return error;
+	}
+
+	error = cpcap_usb_init_interrupts(pdev, ddata);
+	if (error)
+		return error;
+
+	ddata->comparator.set_vbus = cpcap_charger_set_vbus;
+	error = omap_usb2_set_comparator(&ddata->comparator);
+	if (error == -ENODEV) {
+		dev_info(ddata->dev, "charger needs phy, deferring probe\n");
+		return -EPROBE_DEFER;
+	}
+
+	cpcap_charger_init_optional_gpios(ddata);
+
+	schedule_delayed_work(&ddata->detect_work, 0);
+
+	return 0;
+}
+
+static int cpcap_charger_remove(struct platform_device *pdev)
+{
+	struct cpcap_charger_ddata *ddata = platform_get_drvdata(pdev);
+	int error;
+
+	atomic_set(&ddata->active, 0);
+	error = omap_usb2_set_comparator(NULL);
+	if (error)
+		dev_warn(ddata->dev, "could not clear USB comparator: %i\n",
+			 error);
+
+	error = cpcap_charger_set_state(ddata, 0, 0, 0);
+	if (error)
+		dev_warn(ddata->dev, "could not clear charger: %i\n",
+			 error);
+	cancel_delayed_work_sync(&ddata->vbus_work);
+	cancel_delayed_work_sync(&ddata->detect_work);
+
+	return 0;
+}
+
+static struct platform_driver cpcap_charger_driver = {
+	.probe = cpcap_charger_probe,
+	.driver	= {
+		.name	= "cpcap-charger",
+		.of_match_table = of_match_ptr(cpcap_charger_id_table),
+	},
+	.remove	= cpcap_charger_remove,
+};
+module_platform_driver(cpcap_charger_driver);
+
+MODULE_AUTHOR("Tony Lindgren <tony@atomide.com>");
+MODULE_DESCRIPTION("CPCAP Battery Charger Interface driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:cpcap-charger");
diff --git a/drivers/power/supply/lego_ev3_battery.c b/drivers/power/supply/lego_ev3_battery.c
new file mode 100644
index 000000000000..7b993d669f7f
--- /dev/null
+++ b/drivers/power/supply/lego_ev3_battery.c
@@ -0,0 +1,228 @@
+/*
+ * Battery driver for LEGO MINDSTORMS EV3
+ *
+ * Copyright (C) 2017 David Lechner <david@lechnology.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/iio/consumer.h>
+#include <linux/iio/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+
+struct lego_ev3_battery {
+	struct iio_channel *iio_v;
+	struct iio_channel *iio_i;
+	struct gpio_desc *rechargeable_gpio;
+	struct power_supply *psy;
+	int technology;
+	int v_max;
+	int v_min;
+};
+
+static int lego_ev3_battery_get_property(struct power_supply *psy,
+					 enum power_supply_property psp,
+					 union power_supply_propval *val)
+{
+	struct lego_ev3_battery *batt = power_supply_get_drvdata(psy);
+	int val2;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		val->intval = batt->technology;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		/* battery voltage is iio channel * 2 + Vce of transistor */
+		iio_read_channel_processed(batt->iio_v, &val->intval);
+		val->intval *= 2000;
+		val->intval += 200000;
+		/* plus adjust for shunt resistor drop */
+		iio_read_channel_processed(batt->iio_i, &val2);
+		val2 *= 1000;
+		val2 /= 15;
+		val->intval += val2;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+		val->intval = batt->v_max;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		val->intval = batt->v_min;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		/* battery current is iio channel / 15 / 0.05 ohms */
+		iio_read_channel_processed(batt->iio_i, &val->intval);
+		val->intval *= 20000;
+		val->intval /= 15;
+		break;
+	case POWER_SUPPLY_PROP_SCOPE:
+		val->intval = POWER_SUPPLY_SCOPE_SYSTEM;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int lego_ev3_battery_set_property(struct power_supply *psy,
+					 enum power_supply_property psp,
+					 const union power_supply_propval *val)
+{
+	struct lego_ev3_battery *batt = power_supply_get_drvdata(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		/*
+		 * Only allow changing technology from Unknown to NiMH. Li-ion
+		 * batteries are automatically detected and should not be
+		 * overridden. Rechargeable AA batteries, on the other hand,
+		 * cannot be automatically detected, and so must be manually
+		 * specified. This should only be set once during system init,
+		 * so there is no mechanism to go back to Unknown.
+		 */
+		if (batt->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN)
+			return -EINVAL;
+		switch (val->intval) {
+		case POWER_SUPPLY_TECHNOLOGY_NiMH:
+			batt->technology = POWER_SUPPLY_TECHNOLOGY_NiMH;
+			batt->v_max = 7800000;
+			batt->v_min = 5400000;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int lego_ev3_battery_property_is_writeable(struct power_supply *psy,
+						  enum power_supply_property psp)
+{
+	struct lego_ev3_battery *batt = power_supply_get_drvdata(psy);
+
+	return psp == POWER_SUPPLY_PROP_TECHNOLOGY &&
+		batt->technology == POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+}
+
+static enum power_supply_property lego_ev3_battery_props[] = {
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_SCOPE,
+};
+
+static const struct power_supply_desc lego_ev3_battery_desc = {
+	.name			= "lego-ev3-battery",
+	.type			= POWER_SUPPLY_TYPE_BATTERY,
+	.properties		= lego_ev3_battery_props,
+	.num_properties		= ARRAY_SIZE(lego_ev3_battery_props),
+	.get_property		= lego_ev3_battery_get_property,
+	.set_property		= lego_ev3_battery_set_property,
+	.property_is_writeable	= lego_ev3_battery_property_is_writeable,
+};
+
+static int lego_ev3_battery_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct lego_ev3_battery *batt;
+	struct power_supply_config psy_cfg = {};
+	int err;
+
+	batt = devm_kzalloc(dev, sizeof(*batt), GFP_KERNEL);
+	if (!batt)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, batt);
+
+	batt->iio_v = devm_iio_channel_get(dev, "voltage");
+	err = PTR_ERR_OR_ZERO(batt->iio_v);
+	if (err) {
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get voltage iio channel\n");
+		return err;
+	}
+
+	batt->iio_i = devm_iio_channel_get(dev, "current");
+	err = PTR_ERR_OR_ZERO(batt->iio_i);
+	if (err) {
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get current iio channel\n");
+		return err;
+	}
+
+	batt->rechargeable_gpio = devm_gpiod_get(dev, "rechargeable", GPIOD_IN);
+	err = PTR_ERR_OR_ZERO(batt->rechargeable_gpio);
+	if (err) {
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get rechargeable gpio\n");
+		return err;
+	}
+
+	/*
+	 * The rechargeable battery indication switch cannot be changed without
+	 * removing the battery, so we only need to read it once.
+	 */
+	if (gpiod_get_value(batt->rechargeable_gpio)) {
+		/* 2-cell Li-ion, 7.4V nominal */
+		batt->technology = POWER_SUPPLY_TECHNOLOGY_LION;
+		batt->v_max = 84000000;
+		batt->v_min = 60000000;
+	} else {
+		/* 6x AA Alkaline, 9V nominal */
+		batt->technology = POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+		batt->v_max = 90000000;
+		batt->v_min = 48000000;
+	}
+
+	psy_cfg.of_node = pdev->dev.of_node;
+	psy_cfg.drv_data = batt;
+
+	batt->psy = devm_power_supply_register(dev, &lego_ev3_battery_desc,
+					       &psy_cfg);
+	err = PTR_ERR_OR_ZERO(batt->psy);
+	if (err) {
+		dev_err(dev, "failed to register power supply\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_lego_ev3_battery_match[] = {
+	{ .compatible = "lego,ev3-battery", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, of_lego_ev3_battery_match);
+
+static struct platform_driver lego_ev3_battery_driver = {
+	.driver	= {
+		.name		= "lego-ev3-battery",
+		.of_match_table = of_lego_ev3_battery_match,
+	},
+	.probe	= lego_ev3_battery_probe,
+};
+module_platform_driver(lego_ev3_battery_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("David Lechner <david@lechnology.com>");
+MODULE_DESCRIPTION("LEGO MINDSTORMS EV3 Battery Driver");
diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c
index 509e2b341bd6..677f7c40b25a 100644
--- a/drivers/power/supply/lp8788-charger.c
+++ b/drivers/power/supply/lp8788-charger.c
@@ -651,7 +651,7 @@ static ssize_t lp8788_show_eoc_time(struct device *dev,
 {
 	struct lp8788_charger *pchg = dev_get_drvdata(dev);
 	char *stime[] = { "400ms", "5min", "10min", "15min",
-			"20min", "25min", "30min" "No timeout" };
+			"20min", "25min", "30min", "No timeout" };
 	u8 val;
 
 	lp8788_read_byte(pchg->lp, LP8788_CHG_EOC, &val);
diff --git a/drivers/power/supply/ltc2941-battery-gauge.c b/drivers/power/supply/ltc2941-battery-gauge.c
index 4adf2ba021ce..7efb908f4451 100644
--- a/drivers/power/supply/ltc2941-battery-gauge.c
+++ b/drivers/power/supply/ltc2941-battery-gauge.c
@@ -9,6 +9,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/swab.h>
@@ -61,7 +62,7 @@ struct ltc294x_info {
 	struct power_supply *supply;	/* Supply pointer */
 	struct power_supply_desc supply_desc;	/* Supply description */
 	struct delayed_work work;	/* Work scheduler */
-	int num_regs;	/* Number of registers (chip type) */
+	unsigned long num_regs;	/* Number of registers (chip type) */
 	int charge;	/* Last charge register content */
 	int r_sense;	/* mOhm */
 	int Qlsb;	/* nAh */
@@ -387,7 +388,7 @@ static int ltc294x_i2c_probe(struct i2c_client *client,
 
 	np = of_node_get(client->dev.of_node);
 
-	info->num_regs = id->driver_data;
+	info->num_regs = (unsigned long)of_device_get_match_data(&client->dev);
 	info->supply_desc.name = np->name;
 
 	/* r_sense can be negative, when sense+ is connected to the battery
@@ -497,9 +498,23 @@ static const struct i2c_device_id ltc294x_i2c_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ltc294x_i2c_id);
 
+static const struct of_device_id ltc294x_i2c_of_match[] = {
+	{
+		.compatible = "lltc,ltc2941",
+		.data = (void *)LTC2941_NUM_REGS
+	},
+	{
+		.compatible = "lltc,ltc2943",
+		.data = (void *)LTC2943_NUM_REGS
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ltc294x_i2c_of_match);
+
 static struct i2c_driver ltc294x_driver = {
 	.driver = {
 		.name	= "LTC2941",
+		.of_match_table = ltc294x_i2c_of_match,
 		.pm	= LTC294X_PM_OPS,
 	},
 	.probe		= ltc294x_i2c_probe,
diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c
index e7c3649b31a0..33c40f79d23d 100644
--- a/drivers/power/supply/max17040_battery.c
+++ b/drivers/power/supply/max17040_battery.c
@@ -277,9 +277,17 @@ static const struct i2c_device_id max17040_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, max17040_id);
 
+static const struct of_device_id max17040_of_match[] = {
+	{ .compatible = "maxim,max17040" },
+	{ .compatible = "maxim,max77836-battery" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, max17040_of_match);
+
 static struct i2c_driver max17040_i2c_driver = {
 	.driver	= {
 		.name	= "max17040",
+		.of_match_table = max17040_of_match,
 		.pm	= MAX17040_PM_OPS,
 	},
 	.probe		= max17040_probe,
diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c
index 353765a5f44c..15947dbb511e 100644
--- a/drivers/power/supply/sbs-charger.c
+++ b/drivers/power/supply/sbs-charger.c
@@ -137,10 +137,7 @@ static enum power_supply_property sbs_properties[] = {
 
 static bool sbs_readable_reg(struct device *dev, unsigned int reg)
 {
-	if (reg < SBS_CHARGER_REG_SPEC_INFO)
-		return false;
-	else
-		return true;
+	return reg >= SBS_CHARGER_REG_SPEC_INFO;
 }
 
 static bool sbs_volatile_reg(struct device *dev, unsigned int reg)
diff --git a/drivers/power/supply/tps65217_charger.c b/drivers/power/supply/tps65217_charger.c
index 29b61e81b385..1f5234098aaf 100644
--- a/drivers/power/supply/tps65217_charger.c
+++ b/drivers/power/supply/tps65217_charger.c
@@ -58,8 +58,6 @@ static int tps65217_config_charger(struct tps65217_charger *charger)
 {
 	int ret;
 
-	dev_dbg(charger->dev, "%s\n", __func__);
-
 	/*
 	 * tps65217 rev. G, p. 31 (see p. 32 for NTC schematic)
 	 *
@@ -205,8 +203,6 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 	int ret;
 	int i;
 
-	dev_dbg(&pdev->dev, "%s\n", __func__);
-
 	charger = devm_kzalloc(&pdev->dev, sizeof(*charger), GFP_KERNEL);
 	if (!charger)
 		return -ENOMEM;
diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c
index bcd4dc304f27..990ff3d218bc 100644
--- a/drivers/power/supply/twl4030_charger.c
+++ b/drivers/power/supply/twl4030_charger.c
@@ -1117,7 +1117,7 @@ fail:
 	return ret;
 }
 
-static int __exit twl4030_bci_remove(struct platform_device *pdev)
+static int twl4030_bci_remove(struct platform_device *pdev)
 {
 	struct twl4030_bci *bci = platform_get_drvdata(pdev);
 
@@ -1148,11 +1148,11 @@ MODULE_DEVICE_TABLE(of, twl_bci_of_match);
 
 static struct platform_driver twl4030_bci_driver = {
 	.probe = twl4030_bci_probe,
+	.remove	= twl4030_bci_remove,
 	.driver	= {
 		.name	= "twl4030_bci",
 		.of_match_table = of_match_ptr(twl_bci_of_match),
 	},
-	.remove	= __exit_p(twl4030_bci_remove),
 };
 module_platform_driver(twl4030_bci_driver);
 
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index e8142803a1a7..b77435783ef3 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -97,30 +97,26 @@ static s32 scaled_ppm_to_ppb(long ppm)
 
 /* posix clock implementation */
 
-static int ptp_clock_getres(struct posix_clock *pc, struct timespec *tp)
+static int ptp_clock_getres(struct posix_clock *pc, struct timespec64 *tp)
 {
 	tp->tv_sec = 0;
 	tp->tv_nsec = 1;
 	return 0;
 }
 
-static int ptp_clock_settime(struct posix_clock *pc, const struct timespec *tp)
+static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp)
 {
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
-	struct timespec64 ts = timespec_to_timespec64(*tp);
 
-	return  ptp->info->settime64(ptp->info, &ts);
+	return  ptp->info->settime64(ptp->info, tp);
 }
 
-static int ptp_clock_gettime(struct posix_clock *pc, struct timespec *tp)
+static int ptp_clock_gettime(struct posix_clock *pc, struct timespec64 *tp)
 {
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
-	struct timespec64 ts;
 	int err;
 
-	err = ptp->info->gettime64(ptp->info, &ts);
-	if (!err)
-		*tp = timespec64_to_timespec(ts);
+	err = ptp->info->gettime64(ptp->info, tp);
 	return err;
 }
 
@@ -133,7 +129,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx)
 	ops = ptp->info;
 
 	if (tx->modes & ADJ_SETOFFSET) {
-		struct timespec ts;
+		struct timespec64 ts;
 		ktime_t kt;
 		s64 delta;
 
@@ -146,7 +142,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx)
 		if ((unsigned long) ts.tv_nsec >= NSEC_PER_SEC)
 			return -EINVAL;
 
-		kt = timespec_to_ktime(ts);
+		kt = timespec64_to_ktime(ts);
 		delta = ktime_to_ns(kt);
 		err = ops->adjtime(ops, delta);
 	} else if (tx->modes & ADJ_FREQUENCY) {
diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c
index 09b4df74291e..bb865695d7a6 100644
--- a/drivers/ptp/ptp_kvm.c
+++ b/drivers/ptp/ptp_kvm.c
@@ -193,10 +193,7 @@ static int __init ptp_kvm_init(void)
 
 	kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL);
 
-	if (IS_ERR(kvm_ptp_clock.ptp_clock))
-		return PTR_ERR(kvm_ptp_clock.ptp_clock);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(kvm_ptp_clock.ptp_clock);
 }
 
 module_init(ptp_kvm_init);
diff --git a/drivers/pwm/pwm-lpss-pci.c b/drivers/pwm/pwm-lpss-pci.c
index 053088b9b66e..c1527cb645be 100644
--- a/drivers/pwm/pwm-lpss-pci.c
+++ b/drivers/pwm/pwm-lpss-pci.c
@@ -36,6 +36,14 @@ static const struct pwm_lpss_boardinfo pwm_lpss_bxt_info = {
 	.clk_rate = 19200000,
 	.npwm = 4,
 	.base_unit_bits = 22,
+	.bypass = true,
+};
+
+/* Tangier */
+static const struct pwm_lpss_boardinfo pwm_lpss_tng_info = {
+	.clk_rate = 19200000,
+	.npwm = 4,
+	.base_unit_bits = 22,
 };
 
 static int pwm_lpss_probe_pci(struct pci_dev *pdev,
@@ -97,7 +105,7 @@ static const struct pci_device_id pwm_lpss_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x0ac8), (unsigned long)&pwm_lpss_bxt_info},
 	{ PCI_VDEVICE(INTEL, 0x0f08), (unsigned long)&pwm_lpss_byt_info},
 	{ PCI_VDEVICE(INTEL, 0x0f09), (unsigned long)&pwm_lpss_byt_info},
-	{ PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_bxt_info},
+	{ PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_tng_info},
 	{ PCI_VDEVICE(INTEL, 0x1ac8), (unsigned long)&pwm_lpss_bxt_info},
 	{ PCI_VDEVICE(INTEL, 0x2288), (unsigned long)&pwm_lpss_bsw_info},
 	{ PCI_VDEVICE(INTEL, 0x2289), (unsigned long)&pwm_lpss_bsw_info},
diff --git a/drivers/pwm/pwm-lpss-platform.c b/drivers/pwm/pwm-lpss-platform.c
index b22b6fdadb9a..5d6ed1507d29 100644
--- a/drivers/pwm/pwm-lpss-platform.c
+++ b/drivers/pwm/pwm-lpss-platform.c
@@ -37,6 +37,7 @@ static const struct pwm_lpss_boardinfo pwm_lpss_bxt_info = {
 	.clk_rate = 19200000,
 	.npwm = 4,
 	.base_unit_bits = 22,
+	.bypass = true,
 };
 
 static int pwm_lpss_probe_platform(struct platform_device *pdev)
diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c
index 689d2c1cbead..8db0d40ccacd 100644
--- a/drivers/pwm/pwm-lpss.c
+++ b/drivers/pwm/pwm-lpss.c
@@ -57,7 +57,7 @@ static inline void pwm_lpss_write(const struct pwm_device *pwm, u32 value)
 	writel(value, lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM);
 }
 
-static int pwm_lpss_update(struct pwm_device *pwm)
+static int pwm_lpss_wait_for_update(struct pwm_device *pwm)
 {
 	struct pwm_lpss_chip *lpwm = to_lpwm(pwm->chip);
 	const void __iomem *addr = lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM;
@@ -65,8 +65,6 @@ static int pwm_lpss_update(struct pwm_device *pwm)
 	u32 val;
 	int err;
 
-	pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
-
 	/*
 	 * PWM Configuration register has SW_UPDATE bit that is set when a new
 	 * configuration is written to the register. The bit is automatically
@@ -122,6 +120,12 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm,
 	pwm_lpss_write(pwm, ctrl);
 }
 
+static inline void pwm_lpss_cond_enable(struct pwm_device *pwm, bool cond)
+{
+	if (cond)
+		pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE);
+}
+
 static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			  struct pwm_state *state)
 {
@@ -137,18 +141,21 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 				return ret;
 			}
 			pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period);
-			ret = pwm_lpss_update(pwm);
+			pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
+			pwm_lpss_cond_enable(pwm, lpwm->info->bypass == false);
+			ret = pwm_lpss_wait_for_update(pwm);
 			if (ret) {
 				pm_runtime_put(chip->dev);
 				return ret;
 			}
-			pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE);
+			pwm_lpss_cond_enable(pwm, lpwm->info->bypass == true);
 		} else {
 			ret = pwm_lpss_is_updating(pwm);
 			if (ret)
 				return ret;
 			pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period);
-			return pwm_lpss_update(pwm);
+			pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
+			return pwm_lpss_wait_for_update(pwm);
 		}
 	} else if (pwm_is_enabled(pwm)) {
 		pwm_lpss_write(pwm, pwm_lpss_read(pwm) & ~PWM_ENABLE);
diff --git a/drivers/pwm/pwm-lpss.h b/drivers/pwm/pwm-lpss.h
index c94cd7c2695d..98306bb02cfe 100644
--- a/drivers/pwm/pwm-lpss.h
+++ b/drivers/pwm/pwm-lpss.h
@@ -22,6 +22,7 @@ struct pwm_lpss_boardinfo {
 	unsigned long clk_rate;
 	unsigned int npwm;
 	unsigned long base_unit_bits;
+	bool bypass;
 };
 
 struct pwm_lpss_chip *pwm_lpss_probe(struct device *dev, struct resource *r,
diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c
index ef89df1f7336..744d56197286 100644
--- a/drivers/pwm/pwm-rockchip.c
+++ b/drivers/pwm/pwm-rockchip.c
@@ -191,6 +191,28 @@ static int rockchip_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	return 0;
 }
 
+static int rockchip_pwm_enable(struct pwm_chip *chip,
+			 struct pwm_device *pwm,
+			 bool enable,
+			 enum pwm_polarity polarity)
+{
+	struct rockchip_pwm_chip *pc = to_rockchip_pwm_chip(chip);
+	int ret;
+
+	if (enable) {
+		ret = clk_enable(pc->clk);
+		if (ret)
+			return ret;
+	}
+
+	pc->data->set_enable(chip, pwm, enable, polarity);
+
+	if (!enable)
+		clk_disable(pc->clk);
+
+	return 0;
+}
+
 static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			      struct pwm_state *state)
 {
@@ -207,22 +229,26 @@ static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return ret;
 
 	if (state->polarity != curstate.polarity && enabled) {
-		pc->data->set_enable(chip, pwm, false, state->polarity);
+		ret = rockchip_pwm_enable(chip, pwm, false, state->polarity);
+		if (ret)
+			goto out;
 		enabled = false;
 	}
 
 	ret = rockchip_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (ret) {
 		if (enabled != curstate.enabled)
-			pc->data->set_enable(chip, pwm, !enabled,
-					     state->polarity);
-
+			rockchip_pwm_enable(chip, pwm, !enabled,
+				      state->polarity);
 		goto out;
 	}
 
-	if (state->enabled != enabled)
-		pc->data->set_enable(chip, pwm, state->enabled,
-				     state->polarity);
+	if (state->enabled != enabled) {
+		ret = rockchip_pwm_enable(chip, pwm, state->enabled,
+				    state->polarity);
+		if (ret)
+			goto out;
+	}
 
 	/*
 	 * Update the state with the real hardware, which can differ a bit
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index 9d19b9a62011..315a4be8dc1e 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -37,8 +37,8 @@
 #include "tsi721.h"
 
 #ifdef DEBUG
-u32 dbg_level;
-module_param(dbg_level, uint, S_IWUSR | S_IRUGO);
+u32 tsi_dbg_level;
+module_param_named(dbg_level, tsi_dbg_level, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(dbg_level, "Debugging output level (default 0 = none)");
 #endif
 
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index 5941437cbdd1..957eadc58150 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -40,11 +40,11 @@ enum {
 };
 
 #ifdef DEBUG
-extern u32 dbg_level;
+extern u32 tsi_dbg_level;
 
 #define tsi_debug(level, dev, fmt, arg...)				\
 	do {								\
-		if (DBG_##level & dbg_level)				\
+		if (DBG_##level & tsi_dbg_level)				\
 			dev_dbg(dev, "%s: " fmt "\n", __func__, ##arg);	\
 	} while (0)
 #else
diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile
index d7f73341ced3..7b26dd3aa5d0 100644
--- a/drivers/ras/Makefile
+++ b/drivers/ras/Makefile
@@ -1 +1,2 @@
-obj-$(CONFIG_RAS) += ras.o debugfs.o
+obj-$(CONFIG_RAS)	+= ras.o debugfs.o
+obj-$(CONFIG_RAS_CEC)	+= cec.o
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
new file mode 100644
index 000000000000..6aab46d91d33
--- /dev/null
+++ b/drivers/ras/cec.c
@@ -0,0 +1,532 @@
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+
+#include <asm/mce.h>
+
+#include "debugfs.h"
+
+/*
+ * RAS Correctable Errors Collector
+ *
+ * This is a simple gadget which collects correctable errors and counts their
+ * occurrence per physical page address.
+ *
+ * We've opted for possibly the simplest data structure to collect those - an
+ * array of the size of a memory page. It stores 512 u64's with the following
+ * structure:
+ *
+ * [63 ... PFN ... 12 | 11 ... generation ... 10 | 9 ... count ... 0]
+ *
+ * The generation in the two highest order bits is two bits which are set to 11b
+ * on every insertion. During the course of each entry's existence, the
+ * generation field gets decremented during spring cleaning to 10b, then 01b and
+ * then 00b.
+ *
+ * This way we're employing the natural numeric ordering to make sure that newly
+ * inserted/touched elements have higher 12-bit counts (which we've manufactured)
+ * and thus iterating over the array initially won't kick out those elements
+ * which were inserted last.
+ *
+ * Spring cleaning is what we do when we reach a certain number CLEAN_ELEMS of
+ * elements entered into the array, during which, we're decaying all elements.
+ * If, after decay, an element gets inserted again, its generation is set to 11b
+ * to make sure it has higher numerical count than other, older elements and
+ * thus emulate an an LRU-like behavior when deleting elements to free up space
+ * in the page.
+ *
+ * When an element reaches it's max count of count_threshold, we try to poison
+ * it by assuming that errors triggered count_threshold times in a single page
+ * are excessive and that page shouldn't be used anymore. count_threshold is
+ * initialized to COUNT_MASK which is the maximum.
+ *
+ * That error event entry causes cec_add_elem() to return !0 value and thus
+ * signal to its callers to log the error.
+ *
+ * To the question why we've chosen a page and moving elements around with
+ * memmove(), it is because it is a very simple structure to handle and max data
+ * movement is 4K which on highly optimized modern CPUs is almost unnoticeable.
+ * We wanted to avoid the pointer traversal of more complex structures like a
+ * linked list or some sort of a balancing search tree.
+ *
+ * Deleting an element takes O(n) but since it is only a single page, it should
+ * be fast enough and it shouldn't happen all too often depending on error
+ * patterns.
+ */
+
+#undef pr_fmt
+#define pr_fmt(fmt) "RAS: " fmt
+
+/*
+ * We use DECAY_BITS bits of PAGE_SHIFT bits for counting decay, i.e., how long
+ * elements have stayed in the array without having been accessed again.
+ */
+#define DECAY_BITS		2
+#define DECAY_MASK		((1ULL << DECAY_BITS) - 1)
+#define MAX_ELEMS		(PAGE_SIZE / sizeof(u64))
+
+/*
+ * Threshold amount of inserted elements after which we start spring
+ * cleaning.
+ */
+#define CLEAN_ELEMS		(MAX_ELEMS >> DECAY_BITS)
+
+/* Bits which count the number of errors happened in this 4K page. */
+#define COUNT_BITS		(PAGE_SHIFT - DECAY_BITS)
+#define COUNT_MASK		((1ULL << COUNT_BITS) - 1)
+#define FULL_COUNT_MASK		(PAGE_SIZE - 1)
+
+/*
+ * u64: [ 63 ... 12 | DECAY_BITS | COUNT_BITS ]
+ */
+
+#define PFN(e)			((e) >> PAGE_SHIFT)
+#define DECAY(e)		(((e) >> COUNT_BITS) & DECAY_MASK)
+#define COUNT(e)		((unsigned int)(e) & COUNT_MASK)
+#define FULL_COUNT(e)		((e) & (PAGE_SIZE - 1))
+
+static struct ce_array {
+	u64 *array;			/* container page */
+	unsigned int n;			/* number of elements in the array */
+
+	unsigned int decay_count;	/*
+					 * number of element insertions/increments
+					 * since the last spring cleaning.
+					 */
+
+	u64 pfns_poisoned;		/*
+					 * number of PFNs which got poisoned.
+					 */
+
+	u64 ces_entered;		/*
+					 * The number of correctable errors
+					 * entered into the collector.
+					 */
+
+	u64 decays_done;		/*
+					 * Times we did spring cleaning.
+					 */
+
+	union {
+		struct {
+			__u32	disabled : 1,	/* cmdline disabled */
+			__resv   : 31;
+		};
+		__u32 flags;
+	};
+} ce_arr;
+
+static DEFINE_MUTEX(ce_mutex);
+static u64 dfs_pfn;
+
+/* Amount of errors after which we offline */
+static unsigned int count_threshold = COUNT_MASK;
+
+/*
+ * The timer "decays" element count each timer_interval which is 24hrs by
+ * default.
+ */
+
+#define CEC_TIMER_DEFAULT_INTERVAL	24 * 60 * 60	/* 24 hrs */
+#define CEC_TIMER_MIN_INTERVAL		 1 * 60 * 60	/* 1h */
+#define CEC_TIMER_MAX_INTERVAL	   30 *	24 * 60 * 60	/* one month */
+static struct timer_list cec_timer;
+static u64 timer_interval = CEC_TIMER_DEFAULT_INTERVAL;
+
+/*
+ * Decrement decay value. We're using DECAY_BITS bits to denote decay of an
+ * element in the array. On insertion and any access, it gets reset to max.
+ */
+static void do_spring_cleaning(struct ce_array *ca)
+{
+	int i;
+
+	for (i = 0; i < ca->n; i++) {
+		u8 decay = DECAY(ca->array[i]);
+
+		if (!decay)
+			continue;
+
+		decay--;
+
+		ca->array[i] &= ~(DECAY_MASK << COUNT_BITS);
+		ca->array[i] |= (decay << COUNT_BITS);
+	}
+	ca->decay_count = 0;
+	ca->decays_done++;
+}
+
+/*
+ * @interval in seconds
+ */
+static void cec_mod_timer(struct timer_list *t, unsigned long interval)
+{
+	unsigned long iv;
+
+	iv = interval * HZ + jiffies;
+
+	mod_timer(t, round_jiffies(iv));
+}
+
+static void cec_timer_fn(unsigned long data)
+{
+	struct ce_array *ca = (struct ce_array *)data;
+
+	do_spring_cleaning(ca);
+
+	cec_mod_timer(&cec_timer, timer_interval);
+}
+
+/*
+ * @to: index of the smallest element which is >= then @pfn.
+ *
+ * Return the index of the pfn if found, otherwise negative value.
+ */
+static int __find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+	u64 this_pfn;
+	int min = 0, max = ca->n;
+
+	while (min < max) {
+		int tmp = (max + min) >> 1;
+
+		this_pfn = PFN(ca->array[tmp]);
+
+		if (this_pfn < pfn)
+			min = tmp + 1;
+		else if (this_pfn > pfn)
+			max = tmp;
+		else {
+			min = tmp;
+			break;
+		}
+	}
+
+	if (to)
+		*to = min;
+
+	this_pfn = PFN(ca->array[min]);
+
+	if (this_pfn == pfn)
+		return min;
+
+	return -ENOKEY;
+}
+
+static int find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+	WARN_ON(!to);
+
+	if (!ca->n) {
+		*to = 0;
+		return -ENOKEY;
+	}
+	return __find_elem(ca, pfn, to);
+}
+
+static void del_elem(struct ce_array *ca, int idx)
+{
+	/* Save us a function call when deleting the last element. */
+	if (ca->n - (idx + 1))
+		memmove((void *)&ca->array[idx],
+			(void *)&ca->array[idx + 1],
+			(ca->n - (idx + 1)) * sizeof(u64));
+
+	ca->n--;
+}
+
+static u64 del_lru_elem_unlocked(struct ce_array *ca)
+{
+	unsigned int min = FULL_COUNT_MASK;
+	int i, min_idx = 0;
+
+	for (i = 0; i < ca->n; i++) {
+		unsigned int this = FULL_COUNT(ca->array[i]);
+
+		if (min > this) {
+			min = this;
+			min_idx = i;
+		}
+	}
+
+	del_elem(ca, min_idx);
+
+	return PFN(ca->array[min_idx]);
+}
+
+/*
+ * We return the 0th pfn in the error case under the assumption that it cannot
+ * be poisoned and excessive CEs in there are a serious deal anyway.
+ */
+static u64 __maybe_unused del_lru_elem(void)
+{
+	struct ce_array *ca = &ce_arr;
+	u64 pfn;
+
+	if (!ca->n)
+		return 0;
+
+	mutex_lock(&ce_mutex);
+	pfn = del_lru_elem_unlocked(ca);
+	mutex_unlock(&ce_mutex);
+
+	return pfn;
+}
+
+
+int cec_add_elem(u64 pfn)
+{
+	struct ce_array *ca = &ce_arr;
+	unsigned int to;
+	int count, ret = 0;
+
+	/*
+	 * We can be called very early on the identify_cpu() path where we are
+	 * not initialized yet. We ignore the error for simplicity.
+	 */
+	if (!ce_arr.array || ce_arr.disabled)
+		return -ENODEV;
+
+	ca->ces_entered++;
+
+	mutex_lock(&ce_mutex);
+
+	if (ca->n == MAX_ELEMS)
+		WARN_ON(!del_lru_elem_unlocked(ca));
+
+	ret = find_elem(ca, pfn, &to);
+	if (ret < 0) {
+		/*
+		 * Shift range [to-end] to make room for one more element.
+		 */
+		memmove((void *)&ca->array[to + 1],
+			(void *)&ca->array[to],
+			(ca->n - to) * sizeof(u64));
+
+		ca->array[to] = (pfn << PAGE_SHIFT) |
+				(DECAY_MASK << COUNT_BITS) | 1;
+
+		ca->n++;
+
+		ret = 0;
+
+		goto decay;
+	}
+
+	count = COUNT(ca->array[to]);
+
+	if (count < count_threshold) {
+		ca->array[to] |= (DECAY_MASK << COUNT_BITS);
+		ca->array[to]++;
+
+		ret = 0;
+	} else {
+		u64 pfn = ca->array[to] >> PAGE_SHIFT;
+
+		if (!pfn_valid(pfn)) {
+			pr_warn("CEC: Invalid pfn: 0x%llx\n", pfn);
+		} else {
+			/* We have reached max count for this page, soft-offline it. */
+			pr_err("Soft-offlining pfn: 0x%llx\n", pfn);
+			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
+			ca->pfns_poisoned++;
+		}
+
+		del_elem(ca, to);
+
+		/*
+		 * Return a >0 value to denote that we've reached the offlining
+		 * threshold.
+		 */
+		ret = 1;
+
+		goto unlock;
+	}
+
+decay:
+	ca->decay_count++;
+
+	if (ca->decay_count >= CLEAN_ELEMS)
+		do_spring_cleaning(ca);
+
+unlock:
+	mutex_unlock(&ce_mutex);
+
+	return ret;
+}
+
+static int u64_get(void *data, u64 *val)
+{
+	*val = *(u64 *)data;
+
+	return 0;
+}
+
+static int pfn_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	return cec_add_elem(val);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
+
+static int decay_interval_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	if (val < CEC_TIMER_MIN_INTERVAL)
+		return -EINVAL;
+
+	if (val > CEC_TIMER_MAX_INTERVAL)
+		return -EINVAL;
+
+	timer_interval = val;
+
+	cec_mod_timer(&cec_timer, timer_interval);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
+
+static int count_threshold_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	if (val > COUNT_MASK)
+		val = COUNT_MASK;
+
+	count_threshold = val;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(count_threshold_ops, u64_get, count_threshold_set, "%lld\n");
+
+static int array_dump(struct seq_file *m, void *v)
+{
+	struct ce_array *ca = &ce_arr;
+	u64 prev = 0;
+	int i;
+
+	mutex_lock(&ce_mutex);
+
+	seq_printf(m, "{ n: %d\n", ca->n);
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		seq_printf(m, " %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
+
+		WARN_ON(prev > this);
+
+		prev = this;
+	}
+
+	seq_printf(m, "}\n");
+
+	seq_printf(m, "Stats:\nCEs: %llu\nofflined pages: %llu\n",
+		   ca->ces_entered, ca->pfns_poisoned);
+
+	seq_printf(m, "Flags: 0x%x\n", ca->flags);
+
+	seq_printf(m, "Timer interval: %lld seconds\n", timer_interval);
+	seq_printf(m, "Decays: %lld\n", ca->decays_done);
+
+	seq_printf(m, "Action threshold: %d\n", count_threshold);
+
+	mutex_unlock(&ce_mutex);
+
+	return 0;
+}
+
+static int array_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, array_dump, NULL);
+}
+
+static const struct file_operations array_ops = {
+	.owner	 = THIS_MODULE,
+	.open	 = array_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+static int __init create_debugfs_nodes(void)
+{
+	struct dentry *d, *pfn, *decay, *count, *array;
+
+	d = debugfs_create_dir("cec", ras_debugfs_dir);
+	if (!d) {
+		pr_warn("Error creating cec debugfs node!\n");
+		return -1;
+	}
+
+	pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
+	if (!pfn) {
+		pr_warn("Error creating pfn debugfs node!\n");
+		goto err;
+	}
+
+	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_ops);
+	if (!array) {
+		pr_warn("Error creating array debugfs node!\n");
+		goto err;
+	}
+
+	decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
+				    &timer_interval, &decay_interval_ops);
+	if (!decay) {
+		pr_warn("Error creating decay_interval debugfs node!\n");
+		goto err;
+	}
+
+	count = debugfs_create_file("count_threshold", S_IRUSR | S_IWUSR, d,
+				    &count_threshold, &count_threshold_ops);
+	if (!decay) {
+		pr_warn("Error creating count_threshold debugfs node!\n");
+		goto err;
+	}
+
+
+	return 0;
+
+err:
+	debugfs_remove_recursive(d);
+
+	return 1;
+}
+
+void __init cec_init(void)
+{
+	if (ce_arr.disabled)
+		return;
+
+	ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!ce_arr.array) {
+		pr_err("Error allocating CE array page!\n");
+		return;
+	}
+
+	if (create_debugfs_nodes())
+		return;
+
+	setup_timer(&cec_timer, cec_timer_fn, (unsigned long)&ce_arr);
+	cec_mod_timer(&cec_timer, CEC_TIMER_DEFAULT_INTERVAL);
+
+	pr_info("Correctable Errors collector initialized.\n");
+}
+
+int __init parse_cec_param(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (*str == '=')
+		str++;
+
+	if (!strncmp(str, "cec_disable", 7))
+		ce_arr.disabled = 1;
+	else
+		return 0;
+
+	return 1;
+}
diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c
index 0322acf67ea5..501603057dff 100644
--- a/drivers/ras/debugfs.c
+++ b/drivers/ras/debugfs.c
@@ -1,6 +1,6 @@
 #include <linux/debugfs.h>
 
-static struct dentry *ras_debugfs_dir;
+struct dentry *ras_debugfs_dir;
 
 static atomic_t trace_count = ATOMIC_INIT(0);
 
diff --git a/drivers/ras/debugfs.h b/drivers/ras/debugfs.h
new file mode 100644
index 000000000000..db72e4513191
--- /dev/null
+++ b/drivers/ras/debugfs.h
@@ -0,0 +1,8 @@
+#ifndef __RAS_DEBUGFS_H__
+#define __RAS_DEBUGFS_H__
+
+#include <linux/debugfs.h>
+
+extern struct dentry *ras_debugfs_dir;
+
+#endif /* __RAS_DEBUGFS_H__ */
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index b67dd362b7b6..94f8038864b4 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -27,3 +27,14 @@ subsys_initcall(ras_init);
 EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
 #endif
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
+
+
+int __init parse_ras_param(char *str)
+{
+#ifdef CONFIG_RAS_CEC
+	parse_cec_param(str);
+#endif
+
+	return 1;
+}
+__setup("ras", parse_ras_param);
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 65f86bc24c07..faad69a1a597 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -76,7 +76,7 @@ config QCOM_ADSP_PIL
 	depends on OF && ARCH_QCOM
 	depends on REMOTEPROC
 	depends on QCOM_SMEM
-	depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
 	select MFD_SYSCON
 	select QCOM_MDT_LOADER
 	select QCOM_RPROC_COMMON
@@ -93,7 +93,7 @@ config QCOM_Q6V5_PIL
 	depends on OF && ARCH_QCOM
 	depends on QCOM_SMEM
 	depends on REMOTEPROC
-	depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
 	select MFD_SYSCON
 	select QCOM_RPROC_COMMON
 	select QCOM_SCM
@@ -104,7 +104,7 @@ config QCOM_Q6V5_PIL
 config QCOM_WCNSS_PIL
 	tristate "Qualcomm WCNSS Peripheral Image Loader"
 	depends on OF && ARCH_QCOM
-	depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
 	depends on QCOM_SMEM
 	depends on REMOTEPROC
 	select QCOM_MDT_LOADER
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index f1e5e65388bb..cd739d2fa160 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -275,7 +275,7 @@ int reset_control_status(struct reset_control *rstc)
 }
 EXPORT_SYMBOL_GPL(reset_control_status);
 
-static struct reset_control *__reset_control_get(
+static struct reset_control *__reset_control_get_internal(
 				struct reset_controller_dev *rcdev,
 				unsigned int index, bool shared)
 {
@@ -308,7 +308,7 @@ static struct reset_control *__reset_control_get(
 	return rstc;
 }
 
-static void __reset_control_put(struct reset_control *rstc)
+static void __reset_control_put_internal(struct reset_control *rstc)
 {
 	lockdep_assert_held(&reset_list_mutex);
 
@@ -377,7 +377,7 @@ struct reset_control *__of_reset_control_get(struct device_node *node,
 	}
 
 	/* reset_list_mutex also protects the rcdev's reset_control list */
-	rstc = __reset_control_get(rcdev, rstc_id, shared);
+	rstc = __reset_control_get_internal(rcdev, rstc_id, shared);
 
 	mutex_unlock(&reset_list_mutex);
 
@@ -385,6 +385,17 @@ struct reset_control *__of_reset_control_get(struct device_node *node,
 }
 EXPORT_SYMBOL_GPL(__of_reset_control_get);
 
+struct reset_control *__reset_control_get(struct device *dev, const char *id,
+					  int index, bool shared, bool optional)
+{
+	if (dev->of_node)
+		return __of_reset_control_get(dev->of_node, id, index, shared,
+					      optional);
+
+	return optional ? NULL : ERR_PTR(-EINVAL);
+}
+EXPORT_SYMBOL_GPL(__reset_control_get);
+
 /**
  * reset_control_put - free the reset controller
  * @rstc: reset controller
@@ -396,7 +407,7 @@ void reset_control_put(struct reset_control *rstc)
 		return;
 
 	mutex_lock(&reset_list_mutex);
-	__reset_control_put(rstc);
+	__reset_control_put_internal(rstc);
 	mutex_unlock(&reset_list_mutex);
 }
 EXPORT_SYMBOL_GPL(reset_control_put);
@@ -417,8 +428,7 @@ struct reset_control *__devm_reset_control_get(struct device *dev,
 	if (!ptr)
 		return ERR_PTR(-ENOMEM);
 
-	rstc = __of_reset_control_get(dev ? dev->of_node : NULL,
-				      id, index, shared, optional);
+	rstc = __reset_control_get(dev, id, index, shared, optional);
 	if (!IS_ERR(rstc)) {
 		*ptr = rstc;
 		devres_add(dev, ptr);
diff --git a/drivers/rpmsg/Kconfig b/drivers/rpmsg/Kconfig
index f12ac0b28263..edc008f55663 100644
--- a/drivers/rpmsg/Kconfig
+++ b/drivers/rpmsg/Kconfig
@@ -16,7 +16,6 @@ config RPMSG_CHAR
 config RPMSG_QCOM_SMD
 	tristate "Qualcomm Shared Memory Driver (SMD)"
 	depends on QCOM_SMEM
-	depends on QCOM_SMD=n
 	select RPMSG
 	help
 	  Say y here to enable support for the Qualcomm Shared Memory Driver
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index 774da20ceb58..107cd3361e29 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -1052,8 +1052,9 @@ dasd_3990_erp_com_rej(struct dasd_ccw_req * erp, char *sense)
 	} else {
 		/* fatal error -  set status to FAILED
 		   internal error 09 - Command Reject */
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "09");
+		if (!test_bit(DASD_CQR_SUPPRESS_CR, &erp->flags))
+			dev_err(&device->cdev->dev,
+				"An error occurred in the DASD device driver, reason=09\n");
 
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	}
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 0b38217f8147..122456e4db89 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -4927,10 +4927,14 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
 		dasd_eckd_dump_sense_tcw(device, req, irb);
 	} else {
 		/*
-		 * In some cases the 'No Record Found' error might be expected
-		 * and log messages shouldn't be written then. Check if the
-		 * according suppress bit is set.
+		 * In some cases the 'Command Reject' or 'No Record Found'
+		 * error might be expected and log messages shouldn't be
+		 * written then. Check if the according suppress bit is set.
 		 */
+		if (sense && sense[0] & SNS0_CMD_REJECT &&
+		    test_bit(DASD_CQR_SUPPRESS_CR, &req->flags))
+			return;
+
 		if (sense && sense[1] & SNS1_NO_REC_FOUND &&
 		    test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags))
 			return;
@@ -5172,6 +5176,10 @@ static int dasd_eckd_query_host_access(struct dasd_device *device,
 	if (!device->block && private->lcu->pav == HYPER_PAV)
 		return -EOPNOTSUPP;
 
+	/* may not be supported by the storage server */
+	if (!(private->features.feature[14] & 0x80))
+		return -EOPNOTSUPP;
+
 	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */	+ 1 /* RSSD */,
 				   sizeof(struct dasd_psf_prssd_data) + 1,
 				   device);
@@ -5219,6 +5227,8 @@ static int dasd_eckd_query_host_access(struct dasd_device *device,
 
 	cqr->buildclk = get_tod_clock();
 	cqr->status = DASD_CQR_FILLED;
+	/* the command might not be supported, suppress error message */
+	__set_bit(DASD_CQR_SUPPRESS_CR, &cqr->flags);
 	rc = dasd_sleep_on_interruptible(cqr);
 	if (rc == 0) {
 		*data = *host_access;
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 518dba2732d5..dca7cb1e6f65 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -239,11 +239,11 @@ struct dasd_ccw_req {
 					 */
 /*
  * The following flags are used to suppress output of certain errors.
- * These flags should only be used for format checks!
  */
 #define DASD_CQR_SUPPRESS_NRF	4	/* Suppress 'No Record Found' error */
 #define DASD_CQR_SUPPRESS_FP	5	/* Suppress 'File Protected' error*/
 #define DASD_CQR_SUPPRESS_IL	6	/* Suppress 'Incorrect Length' error */
+#define DASD_CQR_SUPPRESS_CR	7	/* Suppress 'Command Reject' error */
 
 /* Signature for error recovery functions. */
 typedef struct dasd_ccw_req *(*dasd_erp_fn_t) (struct dasd_ccw_req *);
diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile
index 3ab9aedeb84a..bdf47526038a 100644
--- a/drivers/s390/cio/Makefile
+++ b/drivers/s390/cio/Makefile
@@ -17,3 +17,6 @@ obj-$(CONFIG_CCWGROUP) += ccwgroup.o
 
 qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o
 obj-$(CONFIG_QDIO) += qdio.o
+
+vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o
+obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 1b350665c823..89216174fcbb 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -170,12 +170,14 @@ cio_start_key (struct subchannel *sch,	/* subchannel structure */
 		return ccode;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_start_key);
 
 int
 cio_start (struct subchannel *sch, struct ccw1 *cpa, __u8 lpm)
 {
 	return cio_start_key(sch, cpa, lpm, PAGE_DEFAULT_KEY);
 }
+EXPORT_SYMBOL_GPL(cio_start);
 
 /*
  * resume suspended I/O operation
@@ -208,6 +210,7 @@ cio_resume (struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_resume);
 
 /*
  * halt I/O operation
@@ -241,6 +244,7 @@ cio_halt(struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_halt);
 
 /*
  * Clear I/O operation
@@ -271,6 +275,7 @@ cio_clear(struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_clear);
 
 /*
  * Function: cio_cancel
@@ -308,7 +313,68 @@ cio_cancel (struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_cancel);
 
+/**
+ * cio_cancel_halt_clear - Cancel running I/O by performing cancel, halt
+ * and clear ordinally if subchannel is valid.
+ * @sch: subchannel on which to perform the cancel_halt_clear operation
+ * @iretry: the number of the times remained to retry the next operation
+ *
+ * This should be called repeatedly since halt/clear are asynchronous
+ * operations. We do one try with cio_cancel, three tries with cio_halt,
+ * 255 tries with cio_clear. The caller should initialize @iretry with
+ * the value 255 for its first call to this, and keep using the same
+ * @iretry in the subsequent calls until it gets a non -EBUSY return.
+ *
+ * Returns 0 if device now idle, -ENODEV for device not operational,
+ * -EBUSY if an interrupt is expected (either from halt/clear or from a
+ * status pending), and -EIO if out of retries.
+ */
+int cio_cancel_halt_clear(struct subchannel *sch, int *iretry)
+{
+	int ret;
+
+	if (cio_update_schib(sch))
+		return -ENODEV;
+	if (!sch->schib.pmcw.ena)
+		/* Not operational -> done. */
+		return 0;
+	/* Stage 1: cancel io. */
+	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_HALT_PEND) &&
+	    !(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
+		if (!scsw_is_tm(&sch->schib.scsw)) {
+			ret = cio_cancel(sch);
+			if (ret != -EINVAL)
+				return ret;
+		}
+		/*
+		 * Cancel io unsuccessful or not applicable (transport mode).
+		 * Continue with asynchronous instructions.
+		 */
+		*iretry = 3;	/* 3 halt retries. */
+	}
+	/* Stage 2: halt io. */
+	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
+		if (*iretry) {
+			*iretry -= 1;
+			ret = cio_halt(sch);
+			if (ret != -EBUSY)
+				return (ret == 0) ? -EBUSY : ret;
+		}
+		/* Halt io unsuccessful. */
+		*iretry = 255;	/* 255 clear retries. */
+	}
+	/* Stage 3: clear io. */
+	if (*iretry) {
+		*iretry -= 1;
+		ret = cio_clear(sch);
+		return (ret == 0) ? -EBUSY : ret;
+	}
+	/* Function was unsuccessful */
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(cio_cancel_halt_clear);
 
 static void cio_apply_config(struct subchannel *sch, struct schib *schib)
 {
@@ -382,6 +448,7 @@ int cio_commit_config(struct subchannel *sch)
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cio_commit_config);
 
 /**
  * cio_update_schib - Perform stsch and update schib if subchannel is valid.
@@ -987,6 +1054,7 @@ int cio_tm_start_key(struct subchannel *sch, struct tcw *tcw, u8 lpm, u8 key)
 		return cio_start_handle_notoper(sch, lpm);
 	}
 }
+EXPORT_SYMBOL_GPL(cio_tm_start_key);
 
 /**
  * cio_tm_intrg - perform interrogate function
@@ -1012,3 +1080,4 @@ int cio_tm_intrg(struct subchannel *sch)
 		return -ENODEV;
 	}
 }
+EXPORT_SYMBOL_GPL(cio_tm_intrg);
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index f0e57aefb5f2..939596d81b73 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -123,6 +123,7 @@ extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
 extern int cio_clear (struct subchannel *);
+extern int cio_cancel_halt_clear(struct subchannel *, int *);
 extern int cio_resume (struct subchannel *);
 extern int cio_halt (struct subchannel *);
 extern int cio_start (struct subchannel *, struct ccw1 *, __u8);
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 9afb5ce13007..12016e32e519 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -124,14 +124,6 @@ ccw_device_set_timeout(struct ccw_device *cdev, int expires)
 	add_timer(&cdev->private->timer);
 }
 
-/*
- * Cancel running i/o. This is called repeatedly since halt/clear are
- * asynchronous operations. We do one try with cio_cancel, two tries
- * with cio_halt, 255 tries with cio_clear. If everythings fails panic.
- * Returns 0 if device now idle, -ENODEV for device not operational and
- * -EBUSY if an interrupt is expected (either from halt/clear or from a
- * status pending).
- */
 int
 ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 {
@@ -139,44 +131,14 @@ ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 	int ret;
 
 	sch = to_subchannel(cdev->dev.parent);
-	if (cio_update_schib(sch))
-		return -ENODEV; 
-	if (!sch->schib.pmcw.ena)
-		/* Not operational -> done. */
-		return 0;
-	/* Stage 1: cancel io. */
-	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_HALT_PEND) &&
-	    !(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
-		if (!scsw_is_tm(&sch->schib.scsw)) {
-			ret = cio_cancel(sch);
-			if (ret != -EINVAL)
-				return ret;
-		}
-		/* cancel io unsuccessful or not applicable (transport mode).
-		 * Continue with asynchronous instructions. */
-		cdev->private->iretry = 3;	/* 3 halt retries. */
-	}
-	if (!(scsw_actl(&sch->schib.scsw) & SCSW_ACTL_CLEAR_PEND)) {
-		/* Stage 2: halt io. */
-		if (cdev->private->iretry) {
-			cdev->private->iretry--;
-			ret = cio_halt(sch);
-			if (ret != -EBUSY)
-				return (ret == 0) ? -EBUSY : ret;
-		}
-		/* halt io unsuccessful. */
-		cdev->private->iretry = 255;	/* 255 clear retries. */
-	}
-	/* Stage 3: clear io. */
-	if (cdev->private->iretry) {
-		cdev->private->iretry--;
-		ret = cio_clear (sch);
-		return (ret == 0) ? -EBUSY : ret;
-	}
-	/* Function was unsuccessful */
-	CIO_MSG_EVENT(0, "0.%x.%04x: could not stop I/O\n",
-		      cdev->private->dev_id.ssid, cdev->private->dev_id.devno);
-	return -EIO;
+	ret = cio_cancel_halt_clear(sch, &cdev->private->iretry);
+
+	if (ret == -EIO)
+		CIO_MSG_EVENT(0, "0.%x.%04x: could not stop I/O\n",
+			      cdev->private->dev_id.ssid,
+			      cdev->private->dev_id.devno);
+
+	return ret;
 }
 
 void ccw_device_update_sense_data(struct ccw_device *cdev)
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
new file mode 100644
index 000000000000..ba6ac83a6c25
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -0,0 +1,842 @@
+/*
+ * channel program interfaces
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/iommu.h>
+#include <linux/vfio.h>
+#include <asm/idals.h>
+
+#include "vfio_ccw_cp.h"
+
+/*
+ * Max length for ccw chain.
+ * XXX: Limit to 256, need to check more?
+ */
+#define CCWCHAIN_LEN_MAX	256
+
+struct pfn_array {
+	unsigned long		pa_iova;
+	unsigned long		*pa_iova_pfn;
+	unsigned long		*pa_pfn;
+	int			pa_nr;
+};
+
+struct pfn_array_table {
+	struct pfn_array	*pat_pa;
+	int			pat_nr;
+};
+
+struct ccwchain {
+	struct list_head	next;
+	struct ccw1		*ch_ccw;
+	/* Guest physical address of the current chain. */
+	u64			ch_iova;
+	/* Count of the valid ccws in chain. */
+	int			ch_len;
+	/* Pinned PAGEs for the original data. */
+	struct pfn_array_table	*ch_pat;
+};
+
+/*
+ * pfn_array_pin() - pin user pages in memory
+ * @pa: pfn_array on which to perform the operation
+ * @mdev: the mediated device to perform pin/unpin operations
+ *
+ * Attempt to pin user pages in memory.
+ *
+ * Usage of pfn_array:
+ * @pa->pa_iova     starting guest physical I/O address. Assigned by caller.
+ * @pa->pa_iova_pfn array that stores PFNs of the pages need to pin. Allocated
+ *                  by caller.
+ * @pa->pa_pfn      array that receives PFNs of the pages pinned. Allocated by
+ *                  caller.
+ * @pa->pa_nr       number of pages from @pa->pa_iova to pin. Assigned by
+ *                  caller.
+ *                  number of pages pinned. Assigned by callee.
+ *
+ * Returns:
+ *   Number of pages pinned on success.
+ *   If @pa->pa_nr is 0 or negative, returns 0.
+ *   If no pages were pinned, returns -errno.
+ */
+static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
+{
+	int i, ret;
+
+	if (pa->pa_nr <= 0) {
+		pa->pa_nr = 0;
+		return 0;
+	}
+
+	pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
+	for (i = 1; i < pa->pa_nr; i++)
+		pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
+
+	ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
+			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
+
+	if (ret > 0 && ret != pa->pa_nr) {
+		vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
+		pa->pa_nr = 0;
+		return 0;
+	}
+
+	return ret;
+}
+
+/* Unpin the pages before releasing the memory. */
+static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
+{
+	vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+	pa->pa_nr = 0;
+	kfree(pa->pa_iova_pfn);
+}
+
+/* Alloc memory for PFNs, then pin pages with them. */
+static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
+			       u64 iova, unsigned int len)
+{
+	int ret = 0;
+
+	if (!len || pa->pa_nr)
+		return -EINVAL;
+
+	pa->pa_iova = iova;
+
+	pa->pa_nr = ((iova & ~PAGE_MASK) + len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+	if (!pa->pa_nr)
+		return -EINVAL;
+
+	pa->pa_iova_pfn = kcalloc(pa->pa_nr,
+				  sizeof(*pa->pa_iova_pfn) +
+				  sizeof(*pa->pa_pfn),
+				  GFP_KERNEL);
+	if (unlikely(!pa->pa_iova_pfn))
+		return -ENOMEM;
+	pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
+
+	ret = pfn_array_pin(pa, mdev);
+
+	if (ret > 0)
+		return ret;
+	else if (!ret)
+		ret = -EINVAL;
+
+	kfree(pa->pa_iova_pfn);
+
+	return ret;
+}
+
+static int pfn_array_table_init(struct pfn_array_table *pat, int nr)
+{
+	pat->pat_pa = kcalloc(nr, sizeof(*pat->pat_pa), GFP_KERNEL);
+	if (unlikely(ZERO_OR_NULL_PTR(pat->pat_pa))) {
+		pat->pat_nr = 0;
+		return -ENOMEM;
+	}
+
+	pat->pat_nr = nr;
+
+	return 0;
+}
+
+static void pfn_array_table_unpin_free(struct pfn_array_table *pat,
+				       struct device *mdev)
+{
+	int i;
+
+	for (i = 0; i < pat->pat_nr; i++)
+		pfn_array_unpin_free(pat->pat_pa + i, mdev);
+
+	if (pat->pat_nr) {
+		kfree(pat->pat_pa);
+		pat->pat_pa = NULL;
+		pat->pat_nr = 0;
+	}
+}
+
+static bool pfn_array_table_iova_pinned(struct pfn_array_table *pat,
+					unsigned long iova)
+{
+	struct pfn_array *pa = pat->pat_pa;
+	unsigned long iova_pfn = iova >> PAGE_SHIFT;
+	int i, j;
+
+	for (i = 0; i < pat->pat_nr; i++, pa++)
+		for (j = 0; j < pa->pa_nr; j++)
+			if (pa->pa_iova_pfn[i] == iova_pfn)
+				return true;
+
+	return false;
+}
+/* Create the list idal words for a pfn_array_table. */
+static inline void pfn_array_table_idal_create_words(
+	struct pfn_array_table *pat,
+	unsigned long *idaws)
+{
+	struct pfn_array *pa;
+	int i, j, k;
+
+	/*
+	 * Idal words (execept the first one) rely on the memory being 4k
+	 * aligned. If a user virtual address is 4K aligned, then it's
+	 * corresponding kernel physical address will also be 4K aligned. Thus
+	 * there will be no problem here to simply use the phys to create an
+	 * idaw.
+	 */
+	k = 0;
+	for (i = 0; i < pat->pat_nr; i++) {
+		pa = pat->pat_pa + i;
+		for (j = 0; j < pa->pa_nr; j++) {
+			idaws[k] = pa->pa_pfn[j] << PAGE_SHIFT;
+			if (k == 0)
+				idaws[k] += pa->pa_iova & (PAGE_SIZE - 1);
+			k++;
+		}
+	}
+}
+
+
+/*
+ * Within the domain (@mdev), copy @n bytes from a guest physical
+ * address (@iova) to a host physical address (@to).
+ */
+static long copy_from_iova(struct device *mdev,
+			   void *to, u64 iova,
+			   unsigned long n)
+{
+	struct pfn_array pa = {0};
+	u64 from;
+	int i, ret;
+	unsigned long l, m;
+
+	ret = pfn_array_alloc_pin(&pa, mdev, iova, n);
+	if (ret <= 0)
+		return ret;
+
+	l = n;
+	for (i = 0; i < pa.pa_nr; i++) {
+		from = pa.pa_pfn[i] << PAGE_SHIFT;
+		m = PAGE_SIZE;
+		if (i == 0) {
+			from += iova & (PAGE_SIZE - 1);
+			m -= iova & (PAGE_SIZE - 1);
+		}
+
+		m = min(l, m);
+		memcpy(to + (n - l), (void *)from, m);
+
+		l -= m;
+		if (l == 0)
+			break;
+	}
+
+	pfn_array_unpin_free(&pa, mdev);
+
+	return l;
+}
+
+static long copy_ccw_from_iova(struct channel_program *cp,
+			       struct ccw1 *to, u64 iova,
+			       unsigned long len)
+{
+	struct ccw0 ccw0;
+	struct ccw1 *pccw1;
+	int ret;
+	int i;
+
+	ret = copy_from_iova(cp->mdev, to, iova, len * sizeof(struct ccw1));
+	if (ret)
+		return ret;
+
+	if (!cp->orb.cmd.fmt) {
+		pccw1 = to;
+		for (i = 0; i < len; i++) {
+			ccw0 = *(struct ccw0 *)pccw1;
+			if ((pccw1->cmd_code & 0x0f) == CCW_CMD_TIC) {
+				pccw1->cmd_code = CCW_CMD_TIC;
+				pccw1->flags = 0;
+				pccw1->count = 0;
+			} else {
+				pccw1->cmd_code = ccw0.cmd_code;
+				pccw1->flags = ccw0.flags;
+				pccw1->count = ccw0.count;
+			}
+			pccw1->cda = ccw0.cda;
+			pccw1++;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Helpers to operate ccwchain.
+ */
+#define ccw_is_test(_ccw) (((_ccw)->cmd_code & 0x0F) == 0)
+
+#define ccw_is_noop(_ccw) ((_ccw)->cmd_code == CCW_CMD_NOOP)
+
+#define ccw_is_tic(_ccw) ((_ccw)->cmd_code == CCW_CMD_TIC)
+
+#define ccw_is_idal(_ccw) ((_ccw)->flags & CCW_FLAG_IDA)
+
+
+#define ccw_is_chain(_ccw) ((_ccw)->flags & (CCW_FLAG_CC | CCW_FLAG_DC))
+
+static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
+{
+	struct ccwchain *chain;
+	void *data;
+	size_t size;
+
+	/* Make ccw address aligned to 8. */
+	size = ((sizeof(*chain) + 7L) & -8L) +
+		sizeof(*chain->ch_ccw) * len +
+		sizeof(*chain->ch_pat) * len;
+	chain = kzalloc(size, GFP_DMA | GFP_KERNEL);
+	if (!chain)
+		return NULL;
+
+	data = (u8 *)chain + ((sizeof(*chain) + 7L) & -8L);
+	chain->ch_ccw = (struct ccw1 *)data;
+
+	data = (u8 *)(chain->ch_ccw) + sizeof(*chain->ch_ccw) * len;
+	chain->ch_pat = (struct pfn_array_table *)data;
+
+	chain->ch_len = len;
+
+	list_add_tail(&chain->next, &cp->ccwchain_list);
+
+	return chain;
+}
+
+static void ccwchain_free(struct ccwchain *chain)
+{
+	list_del(&chain->next);
+	kfree(chain);
+}
+
+/* Free resource for a ccw that allocated memory for its cda. */
+static void ccwchain_cda_free(struct ccwchain *chain, int idx)
+{
+	struct ccw1 *ccw = chain->ch_ccw + idx;
+
+	if (!ccw->count)
+		return;
+
+	kfree((void *)(u64)ccw->cda);
+}
+
+/* Unpin the pages then free the memory resources. */
+static void cp_unpin_free(struct channel_program *cp)
+{
+	struct ccwchain *chain, *temp;
+	int i;
+
+	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
+		for (i = 0; i < chain->ch_len; i++) {
+			pfn_array_table_unpin_free(chain->ch_pat + i,
+						   cp->mdev);
+			ccwchain_cda_free(chain, i);
+		}
+		ccwchain_free(chain);
+	}
+}
+
+/**
+ * ccwchain_calc_length - calculate the length of the ccw chain.
+ * @iova: guest physical address of the target ccw chain
+ * @cp: channel_program on which to perform the operation
+ *
+ * This is the chain length not considering any TICs.
+ * You need to do a new round for each TIC target.
+ *
+ * Returns: the length of the ccw chain or -errno.
+ */
+static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
+{
+	struct ccw1 *ccw, *p;
+	int cnt;
+
+	/*
+	 * Copy current chain from guest to host kernel.
+	 * Currently the chain length is limited to CCWCHAIN_LEN_MAX (256).
+	 * So copying 2K is enough (safe).
+	 */
+	p = ccw = kcalloc(CCWCHAIN_LEN_MAX, sizeof(*ccw), GFP_KERNEL);
+	if (!ccw)
+		return -ENOMEM;
+
+	cnt = copy_ccw_from_iova(cp, ccw, iova, CCWCHAIN_LEN_MAX);
+	if (cnt) {
+		kfree(ccw);
+		return cnt;
+	}
+
+	cnt = 0;
+	do {
+		cnt++;
+
+		if ((!ccw_is_chain(ccw)) && (!ccw_is_tic(ccw)))
+			break;
+
+		ccw++;
+	} while (cnt < CCWCHAIN_LEN_MAX + 1);
+
+	if (cnt == CCWCHAIN_LEN_MAX + 1)
+		cnt = -EINVAL;
+
+	kfree(p);
+	return cnt;
+}
+
+static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
+{
+	struct ccwchain *chain;
+	u32 ccw_head, ccw_tail;
+
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		ccw_head = chain->ch_iova;
+		ccw_tail = ccw_head + (chain->ch_len - 1) * sizeof(struct ccw1);
+
+		if ((ccw_head <= tic->cda) && (tic->cda <= ccw_tail))
+			return 1;
+	}
+
+	return 0;
+}
+
+static int ccwchain_loop_tic(struct ccwchain *chain,
+			     struct channel_program *cp);
+
+static int ccwchain_handle_tic(struct ccw1 *tic, struct channel_program *cp)
+{
+	struct ccwchain *chain;
+	int len, ret;
+
+	/* May transfer to an existing chain. */
+	if (tic_target_chain_exists(tic, cp))
+		return 0;
+
+	/* Get chain length. */
+	len = ccwchain_calc_length(tic->cda, cp);
+	if (len < 0)
+		return len;
+
+	/* Need alloc a new chain for this one. */
+	chain = ccwchain_alloc(cp, len);
+	if (!chain)
+		return -ENOMEM;
+	chain->ch_iova = tic->cda;
+
+	/* Copy the new chain from user. */
+	ret = copy_ccw_from_iova(cp, chain->ch_ccw, tic->cda, len);
+	if (ret) {
+		ccwchain_free(chain);
+		return ret;
+	}
+
+	/* Loop for tics on this new chain. */
+	return ccwchain_loop_tic(chain, cp);
+}
+
+/* Loop for TICs. */
+static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
+{
+	struct ccw1 *tic;
+	int i, ret;
+
+	for (i = 0; i < chain->ch_len; i++) {
+		tic = chain->ch_ccw + i;
+
+		if (!ccw_is_tic(tic))
+			continue;
+
+		ret = ccwchain_handle_tic(tic, cp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int ccwchain_fetch_tic(struct ccwchain *chain,
+			      int idx,
+			      struct channel_program *cp)
+{
+	struct ccw1 *ccw = chain->ch_ccw + idx;
+	struct ccwchain *iter;
+	u32 ccw_head, ccw_tail;
+
+	list_for_each_entry(iter, &cp->ccwchain_list, next) {
+		ccw_head = iter->ch_iova;
+		ccw_tail = ccw_head + (iter->ch_len - 1) * sizeof(struct ccw1);
+
+		if ((ccw_head <= ccw->cda) && (ccw->cda <= ccw_tail)) {
+			ccw->cda = (__u32) (addr_t) (iter->ch_ccw +
+						     (ccw->cda - ccw_head));
+			return 0;
+		}
+	}
+
+	return -EFAULT;
+}
+
+static int ccwchain_fetch_direct(struct ccwchain *chain,
+				 int idx,
+				 struct channel_program *cp)
+{
+	struct ccw1 *ccw;
+	struct pfn_array_table *pat;
+	unsigned long *idaws;
+	int idaw_nr;
+
+	ccw = chain->ch_ccw + idx;
+
+	/*
+	 * Pin data page(s) in memory.
+	 * The number of pages actually is the count of the idaws which will be
+	 * needed when translating a direct ccw to a idal ccw.
+	 */
+	pat = chain->ch_pat + idx;
+	if (pfn_array_table_init(pat, 1))
+		return -ENOMEM;
+	idaw_nr = pfn_array_alloc_pin(pat->pat_pa, cp->mdev,
+				      ccw->cda, ccw->count);
+	if (idaw_nr < 0)
+		return idaw_nr;
+
+	/* Translate this direct ccw to a idal ccw. */
+	idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
+	if (!idaws) {
+		pfn_array_table_unpin_free(pat, cp->mdev);
+		return -ENOMEM;
+	}
+	ccw->cda = (__u32) virt_to_phys(idaws);
+	ccw->flags |= CCW_FLAG_IDA;
+
+	pfn_array_table_idal_create_words(pat, idaws);
+
+	return 0;
+}
+
+static int ccwchain_fetch_idal(struct ccwchain *chain,
+			       int idx,
+			       struct channel_program *cp)
+{
+	struct ccw1 *ccw;
+	struct pfn_array_table *pat;
+	unsigned long *idaws;
+	u64 idaw_iova;
+	unsigned int idaw_nr, idaw_len;
+	int i, ret;
+
+	ccw = chain->ch_ccw + idx;
+
+	/* Calculate size of idaws. */
+	ret = copy_from_iova(cp->mdev, &idaw_iova, ccw->cda, sizeof(idaw_iova));
+	if (ret)
+		return ret;
+	idaw_nr = idal_nr_words((void *)(idaw_iova), ccw->count);
+	idaw_len = idaw_nr * sizeof(*idaws);
+
+	/* Pin data page(s) in memory. */
+	pat = chain->ch_pat + idx;
+	ret = pfn_array_table_init(pat, idaw_nr);
+	if (ret)
+		return ret;
+
+	/* Translate idal ccw to use new allocated idaws. */
+	idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL);
+	if (!idaws) {
+		ret = -ENOMEM;
+		goto out_unpin;
+	}
+
+	ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idaw_len);
+	if (ret)
+		goto out_free_idaws;
+
+	ccw->cda = virt_to_phys(idaws);
+
+	for (i = 0; i < idaw_nr; i++) {
+		idaw_iova = *(idaws + i);
+		if (IS_ERR_VALUE(idaw_iova)) {
+			ret = -EFAULT;
+			goto out_free_idaws;
+		}
+
+		ret = pfn_array_alloc_pin(pat->pat_pa + i, cp->mdev,
+					  idaw_iova, 1);
+		if (ret < 0)
+			goto out_free_idaws;
+	}
+
+	pfn_array_table_idal_create_words(pat, idaws);
+
+	return 0;
+
+out_free_idaws:
+	kfree(idaws);
+out_unpin:
+	pfn_array_table_unpin_free(pat, cp->mdev);
+	return ret;
+}
+
+/*
+ * Fetch one ccw.
+ * To reduce memory copy, we'll pin the cda page in memory,
+ * and to get rid of the cda 2G limitiaion of ccw1, we'll translate
+ * direct ccws to idal ccws.
+ */
+static int ccwchain_fetch_one(struct ccwchain *chain,
+			      int idx,
+			      struct channel_program *cp)
+{
+	struct ccw1 *ccw = chain->ch_ccw + idx;
+
+	if (ccw_is_test(ccw) || ccw_is_noop(ccw))
+		return 0;
+
+	if (ccw_is_tic(ccw))
+		return ccwchain_fetch_tic(chain, idx, cp);
+
+	if (ccw_is_idal(ccw))
+		return ccwchain_fetch_idal(chain, idx, cp);
+
+	return ccwchain_fetch_direct(chain, idx, cp);
+}
+
+/**
+ * cp_init() - allocate ccwchains for a channel program.
+ * @cp: channel_program on which to perform the operation
+ * @mdev: the mediated device to perform pin/unpin operations
+ * @orb: control block for the channel program from the guest
+ *
+ * This creates one or more ccwchain(s), and copies the raw data of
+ * the target channel program from @orb->cmd.iova to the new ccwchain(s).
+ *
+ * Limitations:
+ * 1. Supports only prefetch enabled mode.
+ * 2. Supports idal(c64) ccw chaining.
+ * 3. Supports 4k idaw.
+ *
+ * Returns:
+ *   %0 on success and a negative error value on failure.
+ */
+int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
+{
+	u64 iova = orb->cmd.cpa;
+	struct ccwchain *chain;
+	int len, ret;
+
+	/*
+	 * XXX:
+	 * Only support prefetch enable mode now.
+	 * Only support 64bit addressing idal.
+	 * Only support 4k IDAW.
+	 */
+	if (!orb->cmd.pfch || !orb->cmd.c64 || orb->cmd.i2k)
+		return -EOPNOTSUPP;
+
+	INIT_LIST_HEAD(&cp->ccwchain_list);
+	memcpy(&cp->orb, orb, sizeof(*orb));
+	cp->mdev = mdev;
+
+	/* Get chain length. */
+	len = ccwchain_calc_length(iova, cp);
+	if (len < 0)
+		return len;
+
+	/* Alloc mem for the head chain. */
+	chain = ccwchain_alloc(cp, len);
+	if (!chain)
+		return -ENOMEM;
+	chain->ch_iova = iova;
+
+	/* Copy the head chain from guest. */
+	ret = copy_ccw_from_iova(cp, chain->ch_ccw, iova, len);
+	if (ret) {
+		ccwchain_free(chain);
+		return ret;
+	}
+
+	/* Now loop for its TICs. */
+	ret = ccwchain_loop_tic(chain, cp);
+	if (ret)
+		cp_unpin_free(cp);
+
+	return ret;
+}
+
+
+/**
+ * cp_free() - free resources for channel program.
+ * @cp: channel_program on which to perform the operation
+ *
+ * This unpins the memory pages and frees the memory space occupied by
+ * @cp, which must have been returned by a previous call to cp_init().
+ * Otherwise, undefined behavior occurs.
+ */
+void cp_free(struct channel_program *cp)
+{
+	cp_unpin_free(cp);
+}
+
+/**
+ * cp_prefetch() - translate a guest physical address channel program to
+ *                 a real-device runnable channel program.
+ * @cp: channel_program on which to perform the operation
+ *
+ * This function translates the guest-physical-address channel program
+ * and stores the result to ccwchain list. @cp must have been
+ * initialized by a previous call with cp_init(). Otherwise, undefined
+ * behavior occurs.
+ *
+ * The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced
+ * as helpers to do ccw chain translation inside the kernel. Basically
+ * they accept a channel program issued by a virtual machine, and
+ * translate the channel program to a real-device runnable channel
+ * program.
+ *
+ * These APIs will copy the ccws into kernel-space buffers, and update
+ * the guest phsical addresses with their corresponding host physical
+ * addresses.  Then channel I/O device drivers could issue the
+ * translated channel program to real devices to perform an I/O
+ * operation.
+ *
+ * These interfaces are designed to support translation only for
+ * channel programs, which are generated and formatted by a
+ * guest. Thus this will make it possible for things like VFIO to
+ * leverage the interfaces to passthrough a channel I/O mediated
+ * device in QEMU.
+ *
+ * We support direct ccw chaining by translating them to idal ccws.
+ *
+ * Returns:
+ *   %0 on success and a negative error value on failure.
+ */
+int cp_prefetch(struct channel_program *cp)
+{
+	struct ccwchain *chain;
+	int len, idx, ret;
+
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		len = chain->ch_len;
+		for (idx = 0; idx < len; idx++) {
+			ret = ccwchain_fetch_one(chain, idx, cp);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * cp_get_orb() - get the orb of the channel program
+ * @cp: channel_program on which to perform the operation
+ * @intparm: new intparm for the returned orb
+ * @lpm: candidate value of the logical-path mask for the returned orb
+ *
+ * This function returns the address of the updated orb of the channel
+ * program. Channel I/O device drivers could use this orb to issue a
+ * ssch.
+ */
+union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm)
+{
+	union orb *orb;
+	struct ccwchain *chain;
+	struct ccw1 *cpa;
+
+	orb = &cp->orb;
+
+	orb->cmd.intparm = intparm;
+	orb->cmd.fmt = 1;
+	orb->cmd.key = PAGE_DEFAULT_KEY >> 4;
+
+	if (orb->cmd.lpm == 0)
+		orb->cmd.lpm = lpm;
+
+	chain = list_first_entry(&cp->ccwchain_list, struct ccwchain, next);
+	cpa = chain->ch_ccw;
+	orb->cmd.cpa = (__u32) __pa(cpa);
+
+	return orb;
+}
+
+/**
+ * cp_update_scsw() - update scsw for a channel program.
+ * @cp: channel_program on which to perform the operation
+ * @scsw: I/O results of the channel program and also the target to be
+ *        updated
+ *
+ * @scsw contains the I/O results of the channel program that pointed
+ * to by @cp. However what @scsw->cpa stores is a host physical
+ * address, which is meaningless for the guest, which is waiting for
+ * the I/O results.
+ *
+ * This function updates @scsw->cpa to its coressponding guest physical
+ * address.
+ */
+void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
+{
+	struct ccwchain *chain;
+	u32 cpa = scsw->cmd.cpa;
+	u32 ccw_head, ccw_tail;
+
+	/*
+	 * LATER:
+	 * For now, only update the cmd.cpa part. We may need to deal with
+	 * other portions of the schib as well, even if we don't return them
+	 * in the ioctl directly. Path status changes etc.
+	 */
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		ccw_head = (u32)(u64)chain->ch_ccw;
+		ccw_tail = (u32)(u64)(chain->ch_ccw + chain->ch_len - 1);
+
+		if ((ccw_head <= cpa) && (cpa <= ccw_tail)) {
+			/*
+			 * (cpa - ccw_head) is the offset value of the host
+			 * physical ccw to its chain head.
+			 * Adding this value to the guest physical ccw chain
+			 * head gets us the guest cpa.
+			 */
+			cpa = chain->ch_iova + (cpa - ccw_head);
+			break;
+		}
+	}
+
+	scsw->cmd.cpa = cpa;
+}
+
+/**
+ * cp_iova_pinned() - check if an iova is pinned for a ccw chain.
+ * @cmd: ccwchain command on which to perform the operation
+ * @iova: the iova to check
+ *
+ * If the @iova is currently pinned for the ccw chain, return true;
+ * else return false.
+ */
+bool cp_iova_pinned(struct channel_program *cp, u64 iova)
+{
+	struct ccwchain *chain;
+	int i;
+
+	list_for_each_entry(chain, &cp->ccwchain_list, next) {
+		for (i = 0; i < chain->ch_len; i++)
+			if (pfn_array_table_iova_pinned(chain->ch_pat + i,
+							iova))
+				return true;
+	}
+
+	return false;
+}
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
new file mode 100644
index 000000000000..7a1996b3b36d
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -0,0 +1,42 @@
+/*
+ * channel program interfaces
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#ifndef _VFIO_CCW_CP_H_
+#define _VFIO_CCW_CP_H_
+
+#include <asm/cio.h>
+#include <asm/scsw.h>
+
+#include "orb.h"
+
+/**
+ * struct channel_program - manage information for channel program
+ * @ccwchain_list: list head of ccwchains
+ * @orb: orb for the currently processed ssch request
+ * @mdev: the mediated device to perform page pinning/unpinning
+ *
+ * @ccwchain_list is the head of a ccwchain list, that contents the
+ * translated result of the guest channel program that pointed out by
+ * the iova parameter when calling cp_init.
+ */
+struct channel_program {
+	struct list_head ccwchain_list;
+	union orb orb;
+	struct device *mdev;
+};
+
+extern int cp_init(struct channel_program *cp, struct device *mdev,
+		   union orb *orb);
+extern void cp_free(struct channel_program *cp);
+extern int cp_prefetch(struct channel_program *cp);
+extern union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm);
+extern void cp_update_scsw(struct channel_program *cp, union scsw *scsw);
+extern bool cp_iova_pinned(struct channel_program *cp, u64 iova);
+
+#endif
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
new file mode 100644
index 000000000000..e90dd43d2a55
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -0,0 +1,308 @@
+/*
+ * VFIO based Physical Subchannel device driver
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include <linux/mdev.h>
+
+#include <asm/isc.h>
+
+#include "ioasm.h"
+#include "css.h"
+#include "vfio_ccw_private.h"
+
+struct workqueue_struct *vfio_ccw_work_q;
+
+/*
+ * Helpers
+ */
+int vfio_ccw_sch_quiesce(struct subchannel *sch)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	DECLARE_COMPLETION_ONSTACK(completion);
+	int iretry, ret = 0;
+
+	spin_lock_irq(sch->lock);
+	if (!sch->schib.pmcw.ena)
+		goto out_unlock;
+	ret = cio_disable_subchannel(sch);
+	if (ret != -EBUSY)
+		goto out_unlock;
+
+	do {
+		iretry = 255;
+
+		ret = cio_cancel_halt_clear(sch, &iretry);
+		while (ret == -EBUSY) {
+			/*
+			 * Flush all I/O and wait for
+			 * cancel/halt/clear completion.
+			 */
+			private->completion = &completion;
+			spin_unlock_irq(sch->lock);
+
+			wait_for_completion_timeout(&completion, 3*HZ);
+
+			spin_lock_irq(sch->lock);
+			private->completion = NULL;
+			flush_workqueue(vfio_ccw_work_q);
+			ret = cio_cancel_halt_clear(sch, &iretry);
+		};
+
+		ret = cio_disable_subchannel(sch);
+	} while (ret == -EBUSY);
+out_unlock:
+	private->state = VFIO_CCW_STATE_NOT_OPER;
+	spin_unlock_irq(sch->lock);
+	return ret;
+}
+
+static void vfio_ccw_sch_io_todo(struct work_struct *work)
+{
+	struct vfio_ccw_private *private;
+	struct subchannel *sch;
+	struct irb *irb;
+
+	private = container_of(work, struct vfio_ccw_private, io_work);
+	irb = &private->irb;
+	sch = private->sch;
+
+	if (scsw_is_solicited(&irb->scsw)) {
+		cp_update_scsw(&private->cp, &irb->scsw);
+		cp_free(&private->cp);
+	}
+	memcpy(private->io_region.irb_area, irb, sizeof(*irb));
+
+	if (private->io_trigger)
+		eventfd_signal(private->io_trigger, 1);
+
+	if (private->mdev)
+		private->state = VFIO_CCW_STATE_IDLE;
+}
+
+/*
+ * Sysfs interfaces
+ */
+static ssize_t chpids_show(struct device *dev,
+			   struct device_attribute *attr,
+			   char *buf)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	struct chsc_ssd_info *ssd = &sch->ssd_info;
+	ssize_t ret = 0;
+	int chp;
+	int mask;
+
+	for (chp = 0; chp < 8; chp++) {
+		mask = 0x80 >> chp;
+		if (ssd->path_mask & mask)
+			ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id);
+		else
+			ret += sprintf(buf + ret, "00 ");
+	}
+	ret += sprintf(buf+ret, "\n");
+	return ret;
+}
+
+static ssize_t pimpampom_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct subchannel *sch = to_subchannel(dev);
+	struct pmcw *pmcw = &sch->schib.pmcw;
+
+	return sprintf(buf, "%02x %02x %02x\n",
+		       pmcw->pim, pmcw->pam, pmcw->pom);
+}
+
+static DEVICE_ATTR(chpids, 0444, chpids_show, NULL);
+static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL);
+
+static struct attribute *vfio_subchannel_attrs[] = {
+	&dev_attr_chpids.attr,
+	&dev_attr_pimpampom.attr,
+	NULL,
+};
+
+static struct attribute_group vfio_subchannel_attr_group = {
+	.attrs = vfio_subchannel_attrs,
+};
+
+/*
+ * Css driver callbacks
+ */
+static void vfio_ccw_sch_irq(struct subchannel *sch)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+
+	inc_irq_stat(IRQIO_CIO);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_INTERRUPT);
+}
+
+static int vfio_ccw_sch_probe(struct subchannel *sch)
+{
+	struct pmcw *pmcw = &sch->schib.pmcw;
+	struct vfio_ccw_private *private;
+	int ret;
+
+	if (pmcw->qf) {
+		dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n",
+			 dev_name(&sch->dev));
+		return -ENODEV;
+	}
+
+	private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA);
+	if (!private)
+		return -ENOMEM;
+	private->sch = sch;
+	dev_set_drvdata(&sch->dev, private);
+
+	spin_lock_irq(sch->lock);
+	private->state = VFIO_CCW_STATE_NOT_OPER;
+	sch->isc = VFIO_CCW_ISC;
+	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
+	spin_unlock_irq(sch->lock);
+	if (ret)
+		goto out_free;
+
+	ret = sysfs_create_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
+	if (ret)
+		goto out_disable;
+
+	ret = vfio_ccw_mdev_reg(sch);
+	if (ret)
+		goto out_rm_group;
+
+	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
+	atomic_set(&private->avail, 1);
+	private->state = VFIO_CCW_STATE_STANDBY;
+
+	return 0;
+
+out_rm_group:
+	sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
+out_disable:
+	cio_disable_subchannel(sch);
+out_free:
+	dev_set_drvdata(&sch->dev, NULL);
+	kfree(private);
+	return ret;
+}
+
+static int vfio_ccw_sch_remove(struct subchannel *sch)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+
+	vfio_ccw_sch_quiesce(sch);
+
+	vfio_ccw_mdev_unreg(sch);
+
+	sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group);
+
+	dev_set_drvdata(&sch->dev, NULL);
+
+	kfree(private);
+
+	return 0;
+}
+
+static void vfio_ccw_sch_shutdown(struct subchannel *sch)
+{
+	vfio_ccw_sch_quiesce(sch);
+}
+
+/**
+ * vfio_ccw_sch_event - process subchannel event
+ * @sch: subchannel
+ * @process: non-zero if function is called in process context
+ *
+ * An unspecified event occurred for this subchannel. Adjust data according
+ * to the current operational state of the subchannel. Return zero when the
+ * event has been handled sufficiently or -EAGAIN when this function should
+ * be called again in process context.
+ */
+static int vfio_ccw_sch_event(struct subchannel *sch, int process)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(sch->lock, flags);
+	if (!device_is_registered(&sch->dev))
+		goto out_unlock;
+
+	if (work_pending(&sch->todo_work))
+		goto out_unlock;
+
+	if (cio_update_schib(sch)) {
+		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+		goto out_unlock;
+	}
+
+	private = dev_get_drvdata(&sch->dev);
+	if (private->state == VFIO_CCW_STATE_NOT_OPER) {
+		private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
+				 VFIO_CCW_STATE_STANDBY;
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(sch->lock, flags);
+
+	return 0;
+}
+
+static struct css_device_id vfio_ccw_sch_ids[] = {
+	{ .match_flags = 0x1, .type = SUBCHANNEL_TYPE_IO, },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(css, vfio_ccw_sch_ids);
+
+static struct css_driver vfio_ccw_sch_driver = {
+	.drv = {
+		.name = "vfio_ccw",
+		.owner = THIS_MODULE,
+	},
+	.subchannel_type = vfio_ccw_sch_ids,
+	.irq = vfio_ccw_sch_irq,
+	.probe = vfio_ccw_sch_probe,
+	.remove = vfio_ccw_sch_remove,
+	.shutdown = vfio_ccw_sch_shutdown,
+	.sch_event = vfio_ccw_sch_event,
+};
+
+static int __init vfio_ccw_sch_init(void)
+{
+	int ret;
+
+	vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
+	if (!vfio_ccw_work_q)
+		return -ENOMEM;
+
+	isc_register(VFIO_CCW_ISC);
+	ret = css_driver_register(&vfio_ccw_sch_driver);
+	if (ret) {
+		isc_unregister(VFIO_CCW_ISC);
+		destroy_workqueue(vfio_ccw_work_q);
+	}
+
+	return ret;
+}
+
+static void __exit vfio_ccw_sch_exit(void)
+{
+	css_driver_unregister(&vfio_ccw_sch_driver);
+	isc_unregister(VFIO_CCW_ISC);
+	destroy_workqueue(vfio_ccw_work_q);
+}
+module_init(vfio_ccw_sch_init);
+module_exit(vfio_ccw_sch_exit);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
new file mode 100644
index 000000000000..80a0559cd7ce
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -0,0 +1,203 @@
+/*
+ * Finite state machine for vfio-ccw device handling
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "ioasm.h"
+#include "vfio_ccw_private.h"
+
+static int fsm_io_helper(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	union orb *orb;
+	int ccode;
+	__u8 lpm;
+	unsigned long flags;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+	private->state = VFIO_CCW_STATE_BUSY;
+	spin_unlock_irqrestore(sch->lock, flags);
+
+	orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
+
+	/* Issue "Start Subchannel" */
+	ccode = ssch(sch->schid, orb);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
+		return 0;
+	case 1:		/* Status pending */
+	case 2:		/* Busy */
+		return -EBUSY;
+	case 3:		/* Device/path not operational */
+	{
+		lpm = orb->cmd.lpm;
+		if (lpm != 0)
+			sch->lpm &= ~lpm;
+		else
+			sch->lpm = 0;
+
+		if (cio_update_schib(sch))
+			return -ENODEV;
+
+		return sch->lpm ? -EACCES : -ENODEV;
+	}
+	default:
+		return ccode;
+	}
+}
+
+static void fsm_notoper(struct vfio_ccw_private *private,
+			enum vfio_ccw_event event)
+{
+	struct subchannel *sch = private->sch;
+
+	/*
+	 * TODO:
+	 * Probably we should send the machine check to the guest.
+	 */
+	css_sched_sch_todo(sch, SCH_TODO_UNREG);
+	private->state = VFIO_CCW_STATE_NOT_OPER;
+}
+
+/*
+ * No operation action.
+ */
+static void fsm_nop(struct vfio_ccw_private *private,
+		    enum vfio_ccw_event event)
+{
+}
+
+static void fsm_io_error(struct vfio_ccw_private *private,
+			 enum vfio_ccw_event event)
+{
+	pr_err("vfio-ccw: FSM: I/O request from state:%d\n", private->state);
+	private->io_region.ret_code = -EIO;
+}
+
+static void fsm_io_busy(struct vfio_ccw_private *private,
+			enum vfio_ccw_event event)
+{
+	private->io_region.ret_code = -EBUSY;
+}
+
+static void fsm_disabled_irq(struct vfio_ccw_private *private,
+			     enum vfio_ccw_event event)
+{
+	struct subchannel *sch = private->sch;
+
+	/*
+	 * An interrupt in a disabled state means a previous disable was not
+	 * successful - should not happen, but we try to disable again.
+	 */
+	cio_disable_subchannel(sch);
+}
+
+/*
+ * Deal with the ccw command request from the userspace.
+ */
+static void fsm_io_request(struct vfio_ccw_private *private,
+			   enum vfio_ccw_event event)
+{
+	union orb *orb;
+	union scsw *scsw = &private->scsw;
+	struct ccw_io_region *io_region = &private->io_region;
+	struct mdev_device *mdev = private->mdev;
+
+	private->state = VFIO_CCW_STATE_BOXED;
+
+	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
+
+	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
+		orb = (union orb *)io_region->orb_area;
+
+		io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev),
+					      orb);
+		if (io_region->ret_code)
+			goto err_out;
+
+		io_region->ret_code = cp_prefetch(&private->cp);
+		if (io_region->ret_code) {
+			cp_free(&private->cp);
+			goto err_out;
+		}
+
+		/* Start channel program and wait for I/O interrupt. */
+		io_region->ret_code = fsm_io_helper(private);
+		if (io_region->ret_code) {
+			cp_free(&private->cp);
+			goto err_out;
+		}
+		return;
+	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
+		/* XXX: Handle halt. */
+		io_region->ret_code = -EOPNOTSUPP;
+		goto err_out;
+	} else if (scsw->cmd.fctl & SCSW_FCTL_CLEAR_FUNC) {
+		/* XXX: Handle clear. */
+		io_region->ret_code = -EOPNOTSUPP;
+		goto err_out;
+	}
+
+err_out:
+	private->state = VFIO_CCW_STATE_IDLE;
+}
+
+/*
+ * Got an interrupt for a normal io (state busy).
+ */
+static void fsm_irq(struct vfio_ccw_private *private,
+		    enum vfio_ccw_event event)
+{
+	struct irb *irb = this_cpu_ptr(&cio_irb);
+
+	memcpy(&private->irb, irb, sizeof(*irb));
+
+	queue_work(vfio_ccw_work_q, &private->io_work);
+
+	if (private->completion)
+		complete(private->completion);
+}
+
+/*
+ * Device statemachine
+ */
+fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = {
+	[VFIO_CCW_STATE_NOT_OPER] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_nop,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_disabled_irq,
+	},
+	[VFIO_CCW_STATE_STANDBY] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_IDLE] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_request,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_BOXED] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_BUSY] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+};
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
new file mode 100644
index 000000000000..e72abbc18ee3
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -0,0 +1,425 @@
+/*
+ * Physical device callbacks for vfio_ccw
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "vfio_ccw_private.h"
+
+static int vfio_ccw_mdev_reset(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private;
+	struct subchannel *sch;
+	int ret;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	sch = private->sch;
+	/*
+	 * TODO:
+	 * In the cureent stage, some things like "no I/O running" and "no
+	 * interrupt pending" are clear, but we are not sure what other state
+	 * we need to care about.
+	 * There are still a lot more instructions need to be handled. We
+	 * should come back here later.
+	 */
+	ret = vfio_ccw_sch_quiesce(sch);
+	if (ret)
+		return ret;
+
+	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
+	if (!ret)
+		private->state = VFIO_CCW_STATE_IDLE;
+
+	return ret;
+}
+
+static int vfio_ccw_mdev_notifier(struct notifier_block *nb,
+				  unsigned long action,
+				  void *data)
+{
+	struct vfio_ccw_private *private =
+		container_of(nb, struct vfio_ccw_private, nb);
+
+	/*
+	 * Vendor drivers MUST unpin pages in response to an
+	 * invalidation.
+	 */
+	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
+		struct vfio_iommu_type1_dma_unmap *unmap = data;
+
+		if (!cp_iova_pinned(&private->cp, unmap->iova))
+			return NOTIFY_OK;
+
+		if (vfio_ccw_mdev_reset(private->mdev))
+			return NOTIFY_BAD;
+
+		cp_free(&private->cp);
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static ssize_t name_show(struct kobject *kobj, struct device *dev, char *buf)
+{
+	return sprintf(buf, "I/O subchannel (Non-QDIO)\n");
+}
+MDEV_TYPE_ATTR_RO(name);
+
+static ssize_t device_api_show(struct kobject *kobj, struct device *dev,
+			       char *buf)
+{
+	return sprintf(buf, "%s\n", VFIO_DEVICE_API_CCW_STRING);
+}
+MDEV_TYPE_ATTR_RO(device_api);
+
+static ssize_t available_instances_show(struct kobject *kobj,
+					struct device *dev, char *buf)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", atomic_read(&private->avail));
+}
+MDEV_TYPE_ATTR_RO(available_instances);
+
+static struct attribute *mdev_types_attrs[] = {
+	&mdev_type_attr_name.attr,
+	&mdev_type_attr_device_api.attr,
+	&mdev_type_attr_available_instances.attr,
+	NULL,
+};
+
+static struct attribute_group mdev_type_group = {
+	.name  = "io",
+	.attrs = mdev_types_attrs,
+};
+
+struct attribute_group *mdev_type_groups[] = {
+	&mdev_type_group,
+	NULL,
+};
+
+static int vfio_ccw_mdev_create(struct kobject *kobj, struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if (private->state == VFIO_CCW_STATE_NOT_OPER)
+		return -ENODEV;
+
+	if (atomic_dec_if_positive(&private->avail) < 0)
+		return -EPERM;
+
+	private->mdev = mdev;
+	private->state = VFIO_CCW_STATE_IDLE;
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
+	    (private->state != VFIO_CCW_STATE_STANDBY)) {
+		if (!vfio_ccw_mdev_reset(mdev))
+			private->state = VFIO_CCW_STATE_STANDBY;
+		/* The state will be NOT_OPER on error. */
+	}
+
+	private->mdev = NULL;
+	atomic_inc(&private->avail);
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_open(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
+
+	private->nb.notifier_call = vfio_ccw_mdev_notifier;
+
+	return vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+				      &events, &private->nb);
+}
+
+void vfio_ccw_mdev_release(struct mdev_device *mdev)
+{
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
+
+	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+				 &private->nb);
+}
+
+static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
+				  char __user *buf,
+				  size_t count,
+				  loff_t *ppos)
+{
+	struct vfio_ccw_private *private;
+	struct ccw_io_region *region;
+
+	if (*ppos + count > sizeof(*region))
+		return -EINVAL;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	region = &private->io_region;
+	if (copy_to_user(buf, (void *)region + *ppos, count))
+		return -EFAULT;
+
+	return count;
+}
+
+static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
+				   const char __user *buf,
+				   size_t count,
+				   loff_t *ppos)
+{
+	struct vfio_ccw_private *private;
+	struct ccw_io_region *region;
+
+	if (*ppos + count > sizeof(*region))
+		return -EINVAL;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (private->state != VFIO_CCW_STATE_IDLE)
+		return -EACCES;
+
+	region = &private->io_region;
+	if (copy_from_user((void *)region + *ppos, buf, count))
+		return -EFAULT;
+
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
+	if (region->ret_code != 0) {
+		private->state = VFIO_CCW_STATE_IDLE;
+		return region->ret_code;
+	}
+
+	return count;
+}
+
+static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info)
+{
+	info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET;
+	info->num_regions = VFIO_CCW_NUM_REGIONS;
+	info->num_irqs = VFIO_CCW_NUM_IRQS;
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
+					 u16 *cap_type_id,
+					 void **cap_type)
+{
+	switch (info->index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		info->offset = 0;
+		info->size = sizeof(struct ccw_io_region);
+		info->flags = VFIO_REGION_INFO_FLAG_READ
+			      | VFIO_REGION_INFO_FLAG_WRITE;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
+{
+	if (info->index != VFIO_CCW_IO_IRQ_INDEX)
+		return -EINVAL;
+
+	info->count = 1;
+	info->flags = VFIO_IRQ_INFO_EVENTFD;
+
+	return 0;
+}
+
+static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
+				  uint32_t flags,
+				  void __user *data)
+{
+	struct vfio_ccw_private *private;
+	struct eventfd_ctx **ctx;
+
+	if (!(flags & VFIO_IRQ_SET_ACTION_TRIGGER))
+		return -EINVAL;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	ctx = &private->io_trigger;
+
+	switch (flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
+	case VFIO_IRQ_SET_DATA_NONE:
+	{
+		if (*ctx)
+			eventfd_signal(*ctx, 1);
+		return 0;
+	}
+	case VFIO_IRQ_SET_DATA_BOOL:
+	{
+		uint8_t trigger;
+
+		if (get_user(trigger, (uint8_t __user *)data))
+			return -EFAULT;
+
+		if (trigger && *ctx)
+			eventfd_signal(*ctx, 1);
+		return 0;
+	}
+	case VFIO_IRQ_SET_DATA_EVENTFD:
+	{
+		int32_t fd;
+
+		if (get_user(fd, (int32_t __user *)data))
+			return -EFAULT;
+
+		if (fd == -1) {
+			if (*ctx)
+				eventfd_ctx_put(*ctx);
+			*ctx = NULL;
+		} else if (fd >= 0) {
+			struct eventfd_ctx *efdctx;
+
+			efdctx = eventfd_ctx_fdget(fd);
+			if (IS_ERR(efdctx))
+				return PTR_ERR(efdctx);
+
+			if (*ctx)
+				eventfd_ctx_put(*ctx);
+
+			*ctx = efdctx;
+		} else
+			return -EINVAL;
+
+		return 0;
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
+				   unsigned int cmd,
+				   unsigned long arg)
+{
+	int ret = 0;
+	unsigned long minsz;
+
+	switch (cmd) {
+	case VFIO_DEVICE_GET_INFO:
+	{
+		struct vfio_device_info info;
+
+		minsz = offsetofend(struct vfio_device_info, num_irqs);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		ret = vfio_ccw_mdev_get_device_info(&info);
+		if (ret)
+			return ret;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+	}
+	case VFIO_DEVICE_GET_REGION_INFO:
+	{
+		struct vfio_region_info info;
+		u16 cap_type_id = 0;
+		void *cap_type = NULL;
+
+		minsz = offsetofend(struct vfio_region_info, offset);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		ret = vfio_ccw_mdev_get_region_info(&info, &cap_type_id,
+						    &cap_type);
+		if (ret)
+			return ret;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+	}
+	case VFIO_DEVICE_GET_IRQ_INFO:
+	{
+		struct vfio_irq_info info;
+
+		minsz = offsetofend(struct vfio_irq_info, count);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz || info.index >= VFIO_CCW_NUM_IRQS)
+			return -EINVAL;
+
+		ret = vfio_ccw_mdev_get_irq_info(&info);
+		if (ret)
+			return ret;
+
+		if (info.count == -1)
+			return -EINVAL;
+
+		return copy_to_user((void __user *)arg, &info, minsz);
+	}
+	case VFIO_DEVICE_SET_IRQS:
+	{
+		struct vfio_irq_set hdr;
+		size_t data_size;
+		void __user *data;
+
+		minsz = offsetofend(struct vfio_irq_set, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		ret = vfio_set_irqs_validate_and_prepare(&hdr, 1,
+							 VFIO_CCW_NUM_IRQS,
+							 &data_size);
+		if (ret)
+			return ret;
+
+		data = (void __user *)(arg + minsz);
+		return vfio_ccw_mdev_set_irqs(mdev, hdr.flags, data);
+	}
+	case VFIO_DEVICE_RESET:
+		return vfio_ccw_mdev_reset(mdev);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct mdev_parent_ops vfio_ccw_mdev_ops = {
+	.owner			= THIS_MODULE,
+	.supported_type_groups  = mdev_type_groups,
+	.create			= vfio_ccw_mdev_create,
+	.remove			= vfio_ccw_mdev_remove,
+	.open			= vfio_ccw_mdev_open,
+	.release		= vfio_ccw_mdev_release,
+	.read			= vfio_ccw_mdev_read,
+	.write			= vfio_ccw_mdev_write,
+	.ioctl			= vfio_ccw_mdev_ioctl,
+};
+
+int vfio_ccw_mdev_reg(struct subchannel *sch)
+{
+	return mdev_register_device(&sch->dev, &vfio_ccw_mdev_ops);
+}
+
+void vfio_ccw_mdev_unreg(struct subchannel *sch)
+{
+	mdev_unregister_device(&sch->dev);
+}
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
new file mode 100644
index 000000000000..fc0f01c16ef9
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -0,0 +1,96 @@
+/*
+ * Private stuff for vfio_ccw driver
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ */
+
+#ifndef _VFIO_CCW_PRIVATE_H_
+#define _VFIO_CCW_PRIVATE_H_
+
+#include <linux/completion.h>
+#include <linux/eventfd.h>
+#include <linux/workqueue.h>
+#include <linux/vfio_ccw.h>
+
+#include "css.h"
+#include "vfio_ccw_cp.h"
+
+/**
+ * struct vfio_ccw_private
+ * @sch: pointer to the subchannel
+ * @state: internal state of the device
+ * @completion: synchronization helper of the I/O completion
+ * @avail: available for creating a mediated device
+ * @mdev: pointer to the mediated device
+ * @nb: notifier for vfio events
+ * @io_region: MMIO region to input/output I/O arguments/results
+ * @cp: channel program for the current I/O operation
+ * @irb: irb info received from interrupt
+ * @scsw: scsw info
+ * @io_trigger: eventfd ctx for signaling userspace I/O results
+ * @io_work: work for deferral process of I/O handling
+ */
+struct vfio_ccw_private {
+	struct subchannel	*sch;
+	int			state;
+	struct completion	*completion;
+	atomic_t		avail;
+	struct mdev_device	*mdev;
+	struct notifier_block	nb;
+	struct ccw_io_region	io_region;
+
+	struct channel_program	cp;
+	struct irb		irb;
+	union scsw		scsw;
+
+	struct eventfd_ctx	*io_trigger;
+	struct work_struct	io_work;
+} __aligned(8);
+
+extern int vfio_ccw_mdev_reg(struct subchannel *sch);
+extern void vfio_ccw_mdev_unreg(struct subchannel *sch);
+
+extern int vfio_ccw_sch_quiesce(struct subchannel *sch);
+
+/*
+ * States of the device statemachine.
+ */
+enum vfio_ccw_state {
+	VFIO_CCW_STATE_NOT_OPER,
+	VFIO_CCW_STATE_STANDBY,
+	VFIO_CCW_STATE_IDLE,
+	VFIO_CCW_STATE_BOXED,
+	VFIO_CCW_STATE_BUSY,
+	/* last element! */
+	NR_VFIO_CCW_STATES
+};
+
+/*
+ * Asynchronous events of the device statemachine.
+ */
+enum vfio_ccw_event {
+	VFIO_CCW_EVENT_NOT_OPER,
+	VFIO_CCW_EVENT_IO_REQ,
+	VFIO_CCW_EVENT_INTERRUPT,
+	/* last element! */
+	NR_VFIO_CCW_EVENTS
+};
+
+/*
+ * Action called through jumptable.
+ */
+typedef void (fsm_func_t)(struct vfio_ccw_private *, enum vfio_ccw_event);
+extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS];
+
+static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private,
+				     int event)
+{
+	vfio_ccw_jumptable[private->state][event](private, event);
+}
+
+extern struct workqueue_struct *vfio_ccw_work_q;
+
+#endif
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 40f1136f5568..ea86da8c75f9 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -80,7 +80,7 @@ struct secaeskeytoken {
  * token. If keybitsize is given, the bitsize of the key is
  * also checked. Returns 0 on success or errno value on failure.
  */
-static int check_secaeskeytoken(u8 *token, int keybitsize)
+static int check_secaeskeytoken(const u8 *token, int keybitsize)
 {
 	struct secaeskeytoken *t = (struct secaeskeytoken *) token;
 
@@ -572,6 +572,12 @@ int pkey_sec2protkey(u16 cardnr, u16 domain,
 		rc = -EIO;
 		goto out;
 	}
+	if (prepcblk->ccp_rscode != 0) {
+		DEBUG_WARN(
+			"pkey_sec2protkey unwrap secure key warning, card response %d/%d\n",
+			(int) prepcblk->ccp_rtcode,
+			(int) prepcblk->ccp_rscode);
+	}
 
 	/* process response cprb param block */
 	prepcblk->rpl_parmb = ((u8 *) prepcblk) + sizeof(struct CPRBX);
@@ -761,9 +767,10 @@ out:
 }
 
 /*
- * Fetch just the mkvp value via query_crypto_facility from adapter.
+ * Fetch the current and old mkvp values via
+ * query_crypto_facility from adapter.
  */
-static int fetch_mkvp(u16 cardnr, u16 domain, u64 *mkvp)
+static int fetch_mkvp(u16 cardnr, u16 domain, u64 mkvp[2])
 {
 	int rc, found = 0;
 	size_t rlen, vlen;
@@ -779,9 +786,10 @@ static int fetch_mkvp(u16 cardnr, u16 domain, u64 *mkvp)
 	rc = query_crypto_facility(cardnr, domain, "STATICSA",
 				   rarray, &rlen, varray, &vlen);
 	if (rc == 0 && rlen > 8*8 && vlen > 184+8) {
-		if (rarray[64] == '2') {
+		if (rarray[8*8] == '2') {
 			/* current master key state is valid */
-			*mkvp = *((u64 *)(varray + 184));
+			mkvp[0] = *((u64 *)(varray + 184));
+			mkvp[1] = *((u64 *)(varray + 172));
 			found = 1;
 		}
 	}
@@ -796,14 +804,14 @@ struct mkvp_info {
 	struct list_head list;
 	u16 cardnr;
 	u16 domain;
-	u64 mkvp;
+	u64 mkvp[2];
 };
 
 /* a list with mkvp_info entries */
 static LIST_HEAD(mkvp_list);
 static DEFINE_SPINLOCK(mkvp_list_lock);
 
-static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
+static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 mkvp[2])
 {
 	int rc = -ENOENT;
 	struct mkvp_info *ptr;
@@ -812,7 +820,7 @@ static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
 	list_for_each_entry(ptr, &mkvp_list, list) {
 		if (ptr->cardnr == cardnr &&
 		    ptr->domain == domain) {
-			*mkvp = ptr->mkvp;
+			memcpy(mkvp, ptr->mkvp, 2 * sizeof(u64));
 			rc = 0;
 			break;
 		}
@@ -822,7 +830,7 @@ static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
 	return rc;
 }
 
-static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
+static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp[2])
 {
 	int found = 0;
 	struct mkvp_info *ptr;
@@ -831,7 +839,7 @@ static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
 	list_for_each_entry(ptr, &mkvp_list, list) {
 		if (ptr->cardnr == cardnr &&
 		    ptr->domain == domain) {
-			ptr->mkvp = mkvp;
+			memcpy(ptr->mkvp, mkvp, 2 * sizeof(u64));
 			found = 1;
 			break;
 		}
@@ -844,7 +852,7 @@ static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
 		}
 		ptr->cardnr = cardnr;
 		ptr->domain = domain;
-		ptr->mkvp = mkvp;
+		memcpy(ptr->mkvp, mkvp, 2 * sizeof(u64));
 		list_add(&ptr->list, &mkvp_list);
 	}
 	spin_unlock_bh(&mkvp_list_lock);
@@ -888,8 +896,8 @@ int pkey_findcard(const struct pkey_seckey *seckey,
 	struct secaeskeytoken *t = (struct secaeskeytoken *) seckey;
 	struct zcrypt_device_matrix *device_matrix;
 	u16 card, dom;
-	u64 mkvp;
-	int i, rc;
+	u64 mkvp[2];
+	int i, rc, oi = -1;
 
 	/* mkvp must not be zero */
 	if (t->mkvp == 0)
@@ -910,14 +918,14 @@ int pkey_findcard(const struct pkey_seckey *seckey,
 		    device_matrix->device[i].functions & 0x04) {
 			/* an enabled CCA Coprocessor card */
 			/* try cached mkvp */
-			if (mkvp_cache_fetch(card, dom, &mkvp) == 0 &&
-			    t->mkvp == mkvp) {
+			if (mkvp_cache_fetch(card, dom, mkvp) == 0 &&
+			    t->mkvp == mkvp[0]) {
 				if (!verify)
 					break;
 				/* verify: fetch mkvp from adapter */
-				if (fetch_mkvp(card, dom, &mkvp) == 0) {
+				if (fetch_mkvp(card, dom, mkvp) == 0) {
 					mkvp_cache_update(card, dom, mkvp);
-					if (t->mkvp == mkvp)
+					if (t->mkvp == mkvp[0])
 						break;
 				}
 			}
@@ -936,14 +944,21 @@ int pkey_findcard(const struct pkey_seckey *seckey,
 			card = AP_QID_CARD(device_matrix->device[i].qid);
 			dom = AP_QID_QUEUE(device_matrix->device[i].qid);
 			/* fresh fetch mkvp from adapter */
-			if (fetch_mkvp(card, dom, &mkvp) == 0) {
+			if (fetch_mkvp(card, dom, mkvp) == 0) {
 				mkvp_cache_update(card, dom, mkvp);
-				if (t->mkvp == mkvp)
+				if (t->mkvp == mkvp[0])
 					break;
+				if (t->mkvp == mkvp[1] && oi < 0)
+					oi = i;
 			}
 		}
+		if (i >= MAX_ZDEV_ENTRIES && oi >= 0) {
+			/* old mkvp matched, use this card then */
+			card = AP_QID_CARD(device_matrix->device[oi].qid);
+			dom = AP_QID_QUEUE(device_matrix->device[oi].qid);
+		}
 	}
-	if (i < MAX_ZDEV_ENTRIES) {
+	if (i < MAX_ZDEV_ENTRIES || oi >= 0) {
 		if (pcardnr)
 			*pcardnr = card;
 		if (pdomain)
@@ -989,6 +1004,53 @@ int pkey_skey2pkey(const struct pkey_seckey *seckey,
 EXPORT_SYMBOL(pkey_skey2pkey);
 
 /*
+ * Verify key and give back some info about the key.
+ */
+int pkey_verifykey(const struct pkey_seckey *seckey,
+		   u16 *pcardnr, u16 *pdomain,
+		   u16 *pkeysize, u32 *pattributes)
+{
+	struct secaeskeytoken *t = (struct secaeskeytoken *) seckey;
+	u16 cardnr, domain;
+	u64 mkvp[2];
+	int rc;
+
+	/* check the secure key for valid AES secure key */
+	rc = check_secaeskeytoken((u8 *) seckey, 0);
+	if (rc)
+		goto out;
+	if (pattributes)
+		*pattributes = PKEY_VERIFY_ATTR_AES;
+	if (pkeysize)
+		*pkeysize = t->bitsize;
+
+	/* try to find a card which can handle this key */
+	rc = pkey_findcard(seckey, &cardnr, &domain, 1);
+	if (rc)
+		goto out;
+
+	/* check mkvp for old mkvp match */
+	rc = mkvp_cache_fetch(cardnr, domain, mkvp);
+	if (rc)
+		goto out;
+	if (t->mkvp == mkvp[1]) {
+		DEBUG_DBG("pkey_verifykey secure key has old mkvp\n");
+		if (pattributes)
+			*pattributes |= PKEY_VERIFY_ATTR_OLD_MKVP;
+	}
+
+	if (pcardnr)
+		*pcardnr = cardnr;
+	if (pdomain)
+		*pdomain = domain;
+
+out:
+	DEBUG_DBG("pkey_verifykey rc=%d\n", rc);
+	return rc;
+}
+EXPORT_SYMBOL(pkey_verifykey);
+
+/*
  * File io functions
  */
 
@@ -1089,6 +1151,21 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		break;
 	}
+	case PKEY_VERIFYKEY: {
+		struct pkey_verifykey __user *uvk = (void __user *) arg;
+		struct pkey_verifykey kvk;
+
+		if (copy_from_user(&kvk, uvk, sizeof(kvk)))
+			return -EFAULT;
+		rc = pkey_verifykey(&kvk.seckey, &kvk.cardnr, &kvk.domain,
+				    &kvk.keysize, &kvk.attributes);
+		DEBUG_DBG("pkey_ioctl pkey_verifykey()=%d\n", rc);
+		if (rc)
+			break;
+		if (copy_to_user(uvk, &kvk, sizeof(kvk)))
+			return -EFAULT;
+		break;
+	}
 	default:
 		/* unknown/unsupported ioctl cmd */
 		return -ENOTTY;
diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c
index fd5944bbe224..730d9619400e 100644
--- a/drivers/s390/net/ctcm_fsms.c
+++ b/drivers/s390/net/ctcm_fsms.c
@@ -1283,7 +1283,7 @@ static void ctcmpc_chx_txdone(fsm_instance *fi, int event, void *arg)
 		p_header = (struct pdu *)
 			(skb_tail_pointer(ch->trans_skb) - skb->len);
 		p_header->pdu_flag = 0x00;
-		if (skb->protocol == ntohs(ETH_P_SNAP))
+		if (be16_to_cpu(skb->protocol) == ETH_P_SNAP)
 			p_header->pdu_flag |= 0x60;
 		else
 			p_header->pdu_flag |= 0x20;
diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c
index ac65f12bcd43..198842ce6876 100644
--- a/drivers/s390/net/ctcm_main.c
+++ b/drivers/s390/net/ctcm_main.c
@@ -106,7 +106,7 @@ void ctcm_unpack_skb(struct channel *ch, struct sk_buff *pskb)
 			priv->stats.rx_frame_errors++;
 			return;
 		}
-		pskb->protocol = ntohs(header->type);
+		pskb->protocol = cpu_to_be16(header->type);
 		if ((header->length <= LL_HEADER_LENGTH) ||
 		    (len <= LL_HEADER_LENGTH)) {
 			if (!(ch->logflags & LOG_FLAG_ILLEGALSIZE)) {
@@ -125,7 +125,7 @@ void ctcm_unpack_skb(struct channel *ch, struct sk_buff *pskb)
 		header->length -= LL_HEADER_LENGTH;
 		len -= LL_HEADER_LENGTH;
 		if ((header->length > skb_tailroom(pskb)) ||
-			(header->length > len)) {
+		    (header->length > len)) {
 			if (!(ch->logflags & LOG_FLAG_OVERRUN)) {
 				CTCM_DBF_TEXT_(ERROR, CTC_DBF_ERROR,
 					"%s(%s): Packet size %d (overrun)"
@@ -485,7 +485,7 @@ static int ctcm_transmit_skb(struct channel *ch, struct sk_buff *skb)
 		} else {
 			atomic_inc(&skb->users);
 			header.length = l;
-			header.type = skb->protocol;
+			header.type = be16_to_cpu(skb->protocol);
 			header.unused = 0;
 			memcpy(skb_push(skb, LL_HEADER_LENGTH), &header,
 			       LL_HEADER_LENGTH);
@@ -503,7 +503,7 @@ static int ctcm_transmit_skb(struct channel *ch, struct sk_buff *skb)
 	atomic_inc(&skb->users);
 	ch->prof.txlen += skb->len;
 	header.length = skb->len + LL_HEADER_LENGTH;
-	header.type = skb->protocol;
+	header.type = be16_to_cpu(skb->protocol);
 	header.unused = 0;
 	memcpy(skb_push(skb, LL_HEADER_LENGTH), &header, LL_HEADER_LENGTH);
 	block_len = skb->len + 2;
@@ -690,7 +690,7 @@ static int ctcmpc_transmit_skb(struct channel *ch, struct sk_buff *skb)
 		p_header->pdu_offset = skb->len;
 		p_header->pdu_proto = 0x01;
 		p_header->pdu_flag = 0x00;
-		if (skb->protocol == ntohs(ETH_P_SNAP)) {
+		if (be16_to_cpu(skb->protocol) == ETH_P_SNAP) {
 			p_header->pdu_flag |= PDU_FIRST | PDU_CNTL;
 		} else {
 			p_header->pdu_flag |= PDU_FIRST;
@@ -745,7 +745,7 @@ static int ctcmpc_transmit_skb(struct channel *ch, struct sk_buff *skb)
 	p_header->pdu_proto = 0x01;
 	p_header->pdu_flag = 0x00;
 	p_header->pdu_seq = 0;
-	if (skb->protocol == ntohs(ETH_P_SNAP)) {
+	if (be16_to_cpu(skb->protocol) == ETH_P_SNAP) {
 		p_header->pdu_flag |= PDU_FIRST | PDU_CNTL;
 	} else {
 		p_header->pdu_flag |= PDU_FIRST;
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 3f85b97ab8d2..dba94b486f05 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -635,7 +635,7 @@ static void netiucv_unpack_skb(struct iucv_connection *conn,
 	skb_put(pskb, NETIUCV_HDRLEN);
 	pskb->dev = dev;
 	pskb->ip_summed = CHECKSUM_NONE;
-	pskb->protocol = ntohs(ETH_P_IP);
+	pskb->protocol = cpu_to_be16(ETH_P_IP);
 
 	while (1) {
 		struct sk_buff *skb;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index e7addea8741b..f6aa21176d89 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -240,7 +240,6 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa,
 #define QETH_TX_TIMEOUT		100 * HZ
 #define QETH_RCD_TIMEOUT	60 * HZ
 #define QETH_RECLAIM_WORK_TIME	HZ
-#define QETH_HEADER_SIZE	32
 #define QETH_MAX_PORTNO		15
 
 /*IPv6 address autoconfiguration stuff*/
@@ -447,7 +446,7 @@ struct qeth_qdio_out_buffer {
 	atomic_t state;
 	int next_element_to_fill;
 	struct sk_buff_head skb_list;
-	int is_header[16];
+	int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
 
 	struct qaob *aob;
 	struct qeth_qdio_out_q *q;
@@ -503,22 +502,12 @@ struct qeth_qdio_info {
 	int default_out_queue;
 };
 
-enum qeth_send_errors {
-	QETH_SEND_ERROR_NONE,
-	QETH_SEND_ERROR_LINK_FAILURE,
-	QETH_SEND_ERROR_RETRY,
-	QETH_SEND_ERROR_KICK_IT,
-};
-
 #define QETH_ETH_MAC_V4      0x0100 /* like v4 */
 #define QETH_ETH_MAC_V6      0x3333 /* like v6 */
 /* tr mc mac is longer, but that will be enough to detect mc frames */
 #define QETH_TR_MAC_NC       0xc000 /* non-canonical */
 #define QETH_TR_MAC_C        0x0300 /* canonical */
 
-#define DEFAULT_ADD_HHLEN 0
-#define MAX_ADD_HHLEN 1024
-
 /**
  * buffer stuff for read channel
  */
@@ -644,7 +633,6 @@ struct qeth_reply {
 	atomic_t refcnt;
 };
 
-
 struct qeth_card_blkt {
 	int time_total;
 	int inter_packet;
@@ -685,7 +673,6 @@ struct qeth_card_options {
 	struct qeth_ipa_info ipa6;
 	struct qeth_sbp_info sbp; /* SETBRIDGEPORT options */
 	int fake_broadcast;
-	int add_hhlen;
 	int layer2;
 	int performance_stats;
 	int rx_sg_cb;
@@ -717,17 +704,16 @@ struct qeth_discipline {
 	void (*start_poll)(struct ccw_device *, int, unsigned long);
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
+	int (*process_rx_buffer)(struct qeth_card *card, int budget, int *done);
 	int (*recover)(void *ptr);
 	int (*setup) (struct ccwgroup_device *);
 	void (*remove) (struct ccwgroup_device *);
 	int (*set_online) (struct ccwgroup_device *);
 	int (*set_offline) (struct ccwgroup_device *);
-	void (*shutdown)(struct ccwgroup_device *);
-	int (*prepare) (struct ccwgroup_device *);
-	void (*complete) (struct ccwgroup_device *);
 	int (*freeze)(struct ccwgroup_device *);
 	int (*thaw) (struct ccwgroup_device *);
 	int (*restore)(struct ccwgroup_device *);
+	int (*do_ioctl)(struct net_device *dev, struct ifreq *rq, int cmd);
 	int (*control_event_handler)(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
 };
@@ -856,9 +842,9 @@ static inline int qeth_get_ip_version(struct sk_buff *skb)
 {
 	__be16 *p = &((struct ethhdr *)skb->data)->h_proto;
 
-	if (*p == ETH_P_8021Q)
+	if (be16_to_cpu(*p) == ETH_P_8021Q)
 		p += 2;
-	switch (*p) {
+	switch (be16_to_cpu(*p)) {
 	case ETH_P_IPV6:
 		return 6;
 	case ETH_P_IP:
@@ -920,14 +906,12 @@ int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *,
 			enum qeth_ipa_cmds, enum qeth_prot_versions);
 int qeth_query_setadapterparms(struct qeth_card *);
-int qeth_check_qdio_errors(struct qeth_card *, struct qdio_buffer *,
-		unsigned int, const char *);
-void qeth_queue_input_buffer(struct qeth_card *, int);
 struct sk_buff *qeth_core_get_next_skb(struct qeth_card *,
 		struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *,
 		struct qeth_hdr **);
 void qeth_schedule_recovery(struct qeth_card *);
 void qeth_qdio_start_poll(struct ccw_device *, int, unsigned long);
+int qeth_poll(struct napi_struct *napi, int budget);
 void qeth_qdio_input_handler(struct ccw_device *,
 		unsigned int, unsigned int, int,
 		int, unsigned long);
@@ -948,9 +932,6 @@ void qeth_prepare_control_data(struct qeth_card *, int,
 void qeth_release_buffer(struct qeth_channel *, struct qeth_cmd_buffer *);
 void qeth_prepare_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, char);
 struct qeth_cmd_buffer *qeth_wait_for_buffer(struct qeth_channel *);
-int qeth_mdio_read(struct net_device *, int, int);
-int qeth_snmp_command(struct qeth_card *, char __user *);
-int qeth_query_oat_command(struct qeth_card *, char __user *);
 int qeth_query_switch_attributes(struct qeth_card *card,
 				  struct qeth_switch_info *sw_info);
 int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *,
@@ -961,19 +942,22 @@ int qeth_bridgeport_query_ports(struct qeth_card *card,
 int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
 int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
 int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
-int qeth_get_elements_no(struct qeth_card *, struct sk_buff *, int);
+int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
+			 int extra_elems, int data_offset);
 int qeth_get_elements_for_frags(struct sk_buff *);
 int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *,
-			struct sk_buff *, struct qeth_hdr *, int, int, int);
+			struct sk_buff *, struct qeth_hdr *, int, int);
 int qeth_do_send_packet(struct qeth_card *, struct qeth_qdio_out_q *,
 		    struct sk_buff *, struct qeth_hdr *, int);
+int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 int qeth_core_get_sset_count(struct net_device *, int);
 void qeth_core_get_ethtool_stats(struct net_device *,
 				struct ethtool_stats *, u64 *);
 void qeth_core_get_strings(struct net_device *, u32, u8 *);
 void qeth_core_get_drvinfo(struct net_device *, struct ethtool_drvinfo *);
 void qeth_dbf_longtext(debug_info_t *id, int level, char *text, ...);
-int qeth_core_ethtool_get_settings(struct net_device *, struct ethtool_cmd *);
+int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev,
+					 struct ethtool_link_ksettings *cmd);
 int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback);
 int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int);
 int qeth_configure_cq(struct qeth_card *, enum qeth_cq);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 315d8a2db7c0..38114a8d56e0 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -55,7 +55,6 @@ static struct mutex qeth_mod_mutex;
 
 static void qeth_send_control_data_cb(struct qeth_channel *,
 			struct qeth_cmd_buffer *);
-static int qeth_issue_next_read(struct qeth_card *);
 static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *);
 static void qeth_setup_ccw(struct qeth_channel *, unsigned char *, __u32);
 static void qeth_free_buffer_pool(struct qeth_card *);
@@ -1202,7 +1201,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q,
 	while (skb) {
 		QETH_CARD_TEXT_(q->card, 5, "skbn%d", notification);
 		QETH_CARD_TEXT_(q->card, 5, "%lx", (long) skb);
-		if (skb->protocol == ETH_P_AF_IUCV) {
+		if (be16_to_cpu(skb->protocol) == ETH_P_AF_IUCV) {
 			if (skb->sk) {
 				struct iucv_sock *iucv = iucv_sk(skb->sk);
 				iucv->sk_txnotify(skb, notification);
@@ -1233,7 +1232,8 @@ static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf)
 	while (skb) {
 		QETH_CARD_TEXT(buf->q->card, 5, "skbr");
 		QETH_CARD_TEXT_(buf->q->card, 5, "%lx", (long) skb);
-		if (notify_general_error && skb->protocol == ETH_P_AF_IUCV) {
+		if (notify_general_error &&
+		    be16_to_cpu(skb->protocol) == ETH_P_AF_IUCV) {
 			if (skb->sk) {
 				iucv = iucv_sk(skb->sk);
 				iucv->sk_txnotify(skb, TX_NOTIFY_GENERALERROR);
@@ -1396,7 +1396,6 @@ static void qeth_set_intial_options(struct qeth_card *card)
 	card->options.route4.type = NO_ROUTER;
 	card->options.route6.type = NO_ROUTER;
 	card->options.fake_broadcast = 0;
-	card->options.add_hhlen = DEFAULT_ADD_HHLEN;
 	card->options.performance_stats = 0;
 	card->options.rx_sg_cb = QETH_RX_SG_CB;
 	card->options.isolation = ISOLATION_MODE_NONE;
@@ -3217,8 +3216,10 @@ int qeth_hw_trap(struct qeth_card *card, enum qeth_diags_trap_action action)
 }
 EXPORT_SYMBOL_GPL(qeth_hw_trap);
 
-int qeth_check_qdio_errors(struct qeth_card *card, struct qdio_buffer *buf,
-		unsigned int qdio_error, const char *dbftext)
+static int qeth_check_qdio_errors(struct qeth_card *card,
+				  struct qdio_buffer *buf,
+				  unsigned int qdio_error,
+				  const char *dbftext)
 {
 	if (qdio_error) {
 		QETH_CARD_TEXT(card, 2, dbftext);
@@ -3235,18 +3236,8 @@ int qeth_check_qdio_errors(struct qeth_card *card, struct qdio_buffer *buf,
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_check_qdio_errors);
 
-static void qeth_buffer_reclaim_work(struct work_struct *work)
-{
-	struct qeth_card *card = container_of(work, struct qeth_card,
-		buffer_reclaim_work.work);
-
-	QETH_CARD_TEXT_(card, 2, "brw:%x", card->reclaim_index);
-	qeth_queue_input_buffer(card, card->reclaim_index);
-}
-
-void qeth_queue_input_buffer(struct qeth_card *card, int index)
+static void qeth_queue_input_buffer(struct qeth_card *card, int index)
 {
 	struct qeth_qdio_q *queue = card->qdio.in_q;
 	struct list_head *lh;
@@ -3320,9 +3311,17 @@ void qeth_queue_input_buffer(struct qeth_card *card, int index)
 					  QDIO_MAX_BUFFERS_PER_Q;
 	}
 }
-EXPORT_SYMBOL_GPL(qeth_queue_input_buffer);
 
-static int qeth_handle_send_error(struct qeth_card *card,
+static void qeth_buffer_reclaim_work(struct work_struct *work)
+{
+	struct qeth_card *card = container_of(work, struct qeth_card,
+		buffer_reclaim_work.work);
+
+	QETH_CARD_TEXT_(card, 2, "brw:%x", card->reclaim_index);
+	qeth_queue_input_buffer(card, card->reclaim_index);
+}
+
+static void qeth_handle_send_error(struct qeth_card *card,
 		struct qeth_qdio_out_buffer *buffer, unsigned int qdio_err)
 {
 	int sbalf15 = buffer->buffer->element[15].sflags;
@@ -3338,15 +3337,14 @@ static int qeth_handle_send_error(struct qeth_card *card,
 	qeth_check_qdio_errors(card, buffer->buffer, qdio_err, "qouterr");
 
 	if (!qdio_err)
-		return QETH_SEND_ERROR_NONE;
+		return;
 
 	if ((sbalf15 >= 15) && (sbalf15 <= 31))
-		return QETH_SEND_ERROR_RETRY;
+		return;
 
 	QETH_CARD_TEXT(card, 1, "lnkfail");
 	QETH_CARD_TEXT_(card, 1, "%04x %02x",
 		       (u16)qdio_err, (u8)sbalf15);
-	return QETH_SEND_ERROR_LINK_FAILURE;
 }
 
 /*
@@ -3799,9 +3797,9 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
 		return qeth_cut_iqd_prio(card, ~skb->priority >> 1 & 3);
 	case QETH_PRIO_Q_ING_VLAN:
 		tci = &((struct ethhdr *)skb->data)->h_proto;
-		if (*tci == ETH_P_8021Q)
-			return qeth_cut_iqd_prio(card, ~*(tci + 1) >>
-			(VLAN_PRIO_SHIFT + 1) & 3);
+		if (be16_to_cpu(*tci) == ETH_P_8021Q)
+			return qeth_cut_iqd_prio(card,
+			~be16_to_cpu(*(tci + 1)) >> (VLAN_PRIO_SHIFT + 1) & 3);
 		break;
 	default:
 		break;
@@ -3837,6 +3835,7 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
  * @card:			qeth card structure, to check max. elems.
  * @skb:			SKB address
  * @extra_elems:		extra elems needed, to check against max.
+ * @data_offset:		range starts at skb->data + data_offset
  *
  * Returns the number of pages, and thus QDIO buffer elements, needed to cover
  * skb data, including linear part and fragments. Checks if the result plus
@@ -3844,10 +3843,10 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
  * Note: extra_elems is not included in the returned result.
  */
 int qeth_get_elements_no(struct qeth_card *card,
-		     struct sk_buff *skb, int extra_elems)
+		     struct sk_buff *skb, int extra_elems, int data_offset)
 {
 	int elements = qeth_get_elements_for_range(
-				(addr_t)skb->data,
+				(addr_t)skb->data + data_offset,
 				(addr_t)skb->data + skb_headlen(skb)) +
 			qeth_get_elements_for_frags(skb);
 
@@ -4025,8 +4024,7 @@ static inline int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 
 int qeth_do_send_packet_fast(struct qeth_card *card,
 		struct qeth_qdio_out_q *queue, struct sk_buff *skb,
-		struct qeth_hdr *hdr, int elements_needed,
-		int offset, int hd_len)
+		struct qeth_hdr *hdr, int offset, int hd_len)
 {
 	struct qeth_qdio_out_buffer *buffer;
 	int index;
@@ -4418,7 +4416,7 @@ void qeth_tx_timeout(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(qeth_tx_timeout);
 
-int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum)
+static int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum)
 {
 	struct qeth_card *card = dev->ml_priv;
 	int rc = 0;
@@ -4481,7 +4479,6 @@ int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum)
 	}
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_mdio_read);
 
 static int qeth_send_ipa_snmp_cmd(struct qeth_card *card,
 		struct qeth_cmd_buffer *iob, int len,
@@ -4571,7 +4568,7 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	return 0;
 }
 
-int qeth_snmp_command(struct qeth_card *card, char __user *udata)
+static int qeth_snmp_command(struct qeth_card *card, char __user *udata)
 {
 	struct qeth_cmd_buffer *iob;
 	struct qeth_ipa_cmd *cmd;
@@ -4631,7 +4628,6 @@ out:
 	kfree(qinfo.udata);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_snmp_command);
 
 static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
@@ -4663,7 +4659,7 @@ static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
 	return 0;
 }
 
-int qeth_query_oat_command(struct qeth_card *card, char __user *udata)
+static int qeth_query_oat_command(struct qeth_card *card, char __user *udata)
 {
 	int rc = 0;
 	struct qeth_cmd_buffer *iob;
@@ -4733,7 +4729,6 @@ out_free:
 out:
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_query_oat_command);
 
 static int qeth_query_card_info_cb(struct qeth_card *card,
 				   struct qeth_reply *reply, unsigned long data)
@@ -4774,12 +4769,10 @@ static int qeth_query_card_info(struct qeth_card *card,
 
 static inline int qeth_get_qdio_q_format(struct qeth_card *card)
 {
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_IQD:
-		return 2;
-	default:
-		return 0;
-	}
+	if (card->info.type == QETH_CARD_TYPE_IQD)
+		return QDIO_IQDIO_QFMT;
+	else
+		return QDIO_QETH_QFMT;
 }
 
 static void qeth_determine_capabilities(struct qeth_card *card)
@@ -4818,8 +4811,9 @@ static void qeth_determine_capabilities(struct qeth_card *card)
 		QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc);
 
 	QETH_DBF_TEXT_(SETUP, 2, "qfmt%d", card->ssqd.qfmt);
-	QETH_DBF_TEXT_(SETUP, 2, "%d", card->ssqd.qdioac1);
-	QETH_DBF_TEXT_(SETUP, 2, "%d", card->ssqd.qdioac3);
+	QETH_DBF_TEXT_(SETUP, 2, "ac1:%02x", card->ssqd.qdioac1);
+	QETH_DBF_TEXT_(SETUP, 2, "ac2:%04x", card->ssqd.qdioac2);
+	QETH_DBF_TEXT_(SETUP, 2, "ac3:%04x", card->ssqd.qdioac3);
 	QETH_DBF_TEXT_(SETUP, 2, "icnt%d", card->ssqd.icnt);
 	if (!((card->ssqd.qfmt != QDIO_IQDIO_QFMT) ||
 	    ((card->ssqd.qdioac1 & CHSC_AC1_INITIATE_INPUTQ) == 0) ||
@@ -5287,6 +5281,83 @@ no_mem:
 }
 EXPORT_SYMBOL_GPL(qeth_core_get_next_skb);
 
+int qeth_poll(struct napi_struct *napi, int budget)
+{
+	struct qeth_card *card = container_of(napi, struct qeth_card, napi);
+	int work_done = 0;
+	struct qeth_qdio_buffer *buffer;
+	int done;
+	int new_budget = budget;
+
+	if (card->options.performance_stats) {
+		card->perf_stats.inbound_cnt++;
+		card->perf_stats.inbound_start_time = qeth_get_micros();
+	}
+
+	while (1) {
+		if (!card->rx.b_count) {
+			card->rx.qdio_err = 0;
+			card->rx.b_count = qdio_get_next_buffers(
+				card->data.ccwdev, 0, &card->rx.b_index,
+				&card->rx.qdio_err);
+			if (card->rx.b_count <= 0) {
+				card->rx.b_count = 0;
+				break;
+			}
+			card->rx.b_element =
+				&card->qdio.in_q->bufs[card->rx.b_index]
+				.buffer->element[0];
+			card->rx.e_offset = 0;
+		}
+
+		while (card->rx.b_count) {
+			buffer = &card->qdio.in_q->bufs[card->rx.b_index];
+			if (!(card->rx.qdio_err &&
+			    qeth_check_qdio_errors(card, buffer->buffer,
+			    card->rx.qdio_err, "qinerr")))
+				work_done +=
+					card->discipline->process_rx_buffer(
+						card, new_budget, &done);
+			else
+				done = 1;
+
+			if (done) {
+				if (card->options.performance_stats)
+					card->perf_stats.bufs_rec++;
+				qeth_put_buffer_pool_entry(card,
+					buffer->pool_entry);
+				qeth_queue_input_buffer(card, card->rx.b_index);
+				card->rx.b_count--;
+				if (card->rx.b_count) {
+					card->rx.b_index =
+						(card->rx.b_index + 1) %
+						QDIO_MAX_BUFFERS_PER_Q;
+					card->rx.b_element =
+						&card->qdio.in_q
+						->bufs[card->rx.b_index]
+						.buffer->element[0];
+					card->rx.e_offset = 0;
+				}
+			}
+
+			if (work_done >= budget)
+				goto out;
+			else
+				new_budget = budget - work_done;
+		}
+	}
+
+	napi_complete(napi);
+	if (qdio_start_irq(card->data.ccwdev, 0))
+		napi_schedule(&card->napi);
+out:
+	if (card->options.performance_stats)
+		card->perf_stats.inbound_time += qeth_get_micros() -
+			card->perf_stats.inbound_start_time;
+	return work_done;
+}
+EXPORT_SYMBOL_GPL(qeth_poll);
+
 int qeth_setassparms_cb(struct qeth_card *card,
 			struct qeth_reply *reply, unsigned long data)
 {
@@ -5677,23 +5748,12 @@ static int qeth_core_set_offline(struct ccwgroup_device *gdev)
 static void qeth_core_shutdown(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
-	if (card->discipline && card->discipline->shutdown)
-		card->discipline->shutdown(gdev);
-}
-
-static int qeth_core_prepare(struct ccwgroup_device *gdev)
-{
-	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
-	if (card->discipline && card->discipline->prepare)
-		return card->discipline->prepare(gdev);
-	return 0;
-}
-
-static void qeth_core_complete(struct ccwgroup_device *gdev)
-{
-	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
-	if (card->discipline && card->discipline->complete)
-		card->discipline->complete(gdev);
+	qeth_set_allowed_threads(card, 0, 1);
+	if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
+		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
+	qeth_qdio_clear_card(card, 0);
+	qeth_clear_qdio_buffers(card);
+	qdio_free(CARD_DDEV(card));
 }
 
 static int qeth_core_freeze(struct ccwgroup_device *gdev)
@@ -5730,8 +5790,8 @@ static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
 	.set_online = qeth_core_set_online,
 	.set_offline = qeth_core_set_offline,
 	.shutdown = qeth_core_shutdown,
-	.prepare = qeth_core_prepare,
-	.complete = qeth_core_complete,
+	.prepare = NULL,
+	.complete = NULL,
 	.freeze = qeth_core_freeze,
 	.thaw = qeth_core_thaw,
 	.restore = qeth_core_restore,
@@ -5761,6 +5821,60 @@ static const struct attribute_group *qeth_drv_attr_groups[] = {
 	NULL,
 };
 
+int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct qeth_card *card = dev->ml_priv;
+	struct mii_ioctl_data *mii_data;
+	int rc = 0;
+
+	if (!card)
+		return -ENODEV;
+
+	if (!qeth_card_hw_is_reachable(card))
+		return -ENODEV;
+
+	if (card->info.type == QETH_CARD_TYPE_OSN)
+		return -EPERM;
+
+	switch (cmd) {
+	case SIOC_QETH_ADP_SET_SNMP_CONTROL:
+		rc = qeth_snmp_command(card, rq->ifr_ifru.ifru_data);
+		break;
+	case SIOC_QETH_GET_CARD_TYPE:
+		if ((card->info.type == QETH_CARD_TYPE_OSD ||
+		     card->info.type == QETH_CARD_TYPE_OSM ||
+		     card->info.type == QETH_CARD_TYPE_OSX) &&
+		    !card->info.guestlan)
+			return 1;
+		else
+			return 0;
+	case SIOCGMIIPHY:
+		mii_data = if_mii(rq);
+		mii_data->phy_id = 0;
+		break;
+	case SIOCGMIIREG:
+		mii_data = if_mii(rq);
+		if (mii_data->phy_id != 0)
+			rc = -EINVAL;
+		else
+			mii_data->val_out = qeth_mdio_read(dev,
+				mii_data->phy_id, mii_data->reg_num);
+		break;
+	case SIOC_QETH_QUERY_OAT:
+		rc = qeth_query_oat_command(card, rq->ifr_ifru.ifru_data);
+		break;
+	default:
+		if (card->discipline->do_ioctl)
+			rc = card->discipline->do_ioctl(dev, rq, cmd);
+		else
+			rc = -EOPNOTSUPP;
+	}
+	if (rc)
+		QETH_CARD_TEXT_(card, 2, "ioce%x", rc);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(qeth_do_ioctl);
+
 static struct {
 	const char str[ETH_GSTRING_LEN];
 } qeth_ethtool_stats_keys[] = {
@@ -5895,104 +6009,124 @@ void qeth_core_get_drvinfo(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(qeth_core_get_drvinfo);
 
-/* Helper function to fill 'advertizing' and 'supported' which are the same. */
-/* Autoneg and full-duplex are supported and advertized uncondionally.	     */
-/* Always advertize and support all speeds up to specified, and only one     */
+/* Helper function to fill 'advertising' and 'supported' which are the same. */
+/* Autoneg and full-duplex are supported and advertised unconditionally.     */
+/* Always advertise and support all speeds up to specified, and only one     */
 /* specified port type.							     */
-static void qeth_set_ecmd_adv_sup(struct ethtool_cmd *ecmd,
+static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd,
 				int maxspeed, int porttype)
 {
-	int port_sup, port_adv, spd_sup, spd_adv;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_zero_link_mode(cmd, lp_advertising);
+
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
 
 	switch (porttype) {
 	case PORT_TP:
-		port_sup = SUPPORTED_TP;
-		port_adv = ADVERTISED_TP;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
 		break;
 	case PORT_FIBRE:
-		port_sup = SUPPORTED_FIBRE;
-		port_adv = ADVERTISED_FIBRE;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
 		break;
 	default:
-		port_sup = SUPPORTED_TP;
-		port_adv = ADVERTISED_TP;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
 		WARN_ON_ONCE(1);
 	}
 
-	/* "Fallthrough" case'es ordered from high to low result in setting  */
-	/* flags cumulatively, starting from the specified speed and down to */
-	/* the lowest possible.						     */
-	spd_sup = 0;
-	spd_adv = 0;
+	/* fallthrough from high to low, to select all legal speeds: */
 	switch (maxspeed) {
 	case SPEED_10000:
-		spd_sup |= SUPPORTED_10000baseT_Full;
-		spd_adv |= ADVERTISED_10000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     10000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     10000baseT_Full);
 	case SPEED_1000:
-		spd_sup |= SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full;
-		spd_adv |= ADVERTISED_1000baseT_Half |
-						ADVERTISED_1000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     1000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     1000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     1000baseT_Half);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     1000baseT_Half);
 	case SPEED_100:
-		spd_sup |= SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full;
-		spd_adv |= ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     100baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     100baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     100baseT_Half);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     100baseT_Half);
 	case SPEED_10:
-		spd_sup |= SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full;
-		spd_adv |= ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full;
-	break;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     10baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     10baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     10baseT_Half);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     10baseT_Half);
+		/* end fallthrough */
+		break;
 	default:
-		spd_sup = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full;
-		spd_adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     10baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     10baseT_Full);
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     10baseT_Half);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     10baseT_Half);
 		WARN_ON_ONCE(1);
 	}
-	ecmd->advertising = ADVERTISED_Autoneg | port_adv | spd_adv;
-	ecmd->supported = SUPPORTED_Autoneg | port_sup | spd_sup;
 }
 
-int qeth_core_ethtool_get_settings(struct net_device *netdev,
-					struct ethtool_cmd *ecmd)
+int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev,
+		struct ethtool_link_ksettings *cmd)
 {
 	struct qeth_card *card = netdev->ml_priv;
 	enum qeth_link_types link_type;
 	struct carrier_info carrier_info;
 	int rc;
-	u32 speed;
 
 	if ((card->info.type == QETH_CARD_TYPE_IQD) || (card->info.guestlan))
 		link_type = QETH_LINK_TYPE_10GBIT_ETH;
 	else
 		link_type = card->info.link_type;
 
-	ecmd->transceiver = XCVR_INTERNAL;
-	ecmd->duplex = DUPLEX_FULL;
-	ecmd->autoneg = AUTONEG_ENABLE;
+	cmd->base.duplex = DUPLEX_FULL;
+	cmd->base.autoneg = AUTONEG_ENABLE;
+	cmd->base.phy_address = 0;
+	cmd->base.mdio_support = 0;
+	cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
+	cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
 
 	switch (link_type) {
 	case QETH_LINK_TYPE_FAST_ETH:
 	case QETH_LINK_TYPE_LANE_ETH100:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_100, PORT_TP);
-		speed = SPEED_100;
-		ecmd->port = PORT_TP;
+		cmd->base.speed = SPEED_100;
+		cmd->base.port = PORT_TP;
 		break;
-
 	case QETH_LINK_TYPE_GBIT_ETH:
 	case QETH_LINK_TYPE_LANE_ETH1000:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_1000, PORT_FIBRE);
-		speed = SPEED_1000;
-		ecmd->port = PORT_FIBRE;
+		cmd->base.speed = SPEED_1000;
+		cmd->base.port = PORT_FIBRE;
 		break;
-
 	case QETH_LINK_TYPE_10GBIT_ETH:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_10000, PORT_FIBRE);
-		speed = SPEED_10000;
-		ecmd->port = PORT_FIBRE;
+		cmd->base.speed = SPEED_10000;
+		cmd->base.port = PORT_FIBRE;
 		break;
-
 	default:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_10, PORT_TP);
-		speed = SPEED_10;
-		ecmd->port = PORT_TP;
+		cmd->base.speed = SPEED_10;
+		cmd->base.port = PORT_TP;
 	}
-	ethtool_cmd_speed_set(ecmd, speed);
+	qeth_set_cmd_adv_sup(cmd, cmd->base.speed, cmd->base.port);
 
 	/* Check if we can obtain more accurate information.	 */
 	/* If QUERY_CARD_INFO command is not supported or fails, */
@@ -6017,49 +6151,48 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev,
 	switch (carrier_info.card_type) {
 	case CARD_INFO_TYPE_1G_COPPER_A:
 	case CARD_INFO_TYPE_1G_COPPER_B:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_1000, PORT_TP);
-		ecmd->port = PORT_TP;
+		cmd->base.port = PORT_TP;
+		qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port);
 		break;
 	case CARD_INFO_TYPE_1G_FIBRE_A:
 	case CARD_INFO_TYPE_1G_FIBRE_B:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_1000, PORT_FIBRE);
-		ecmd->port = PORT_FIBRE;
+		cmd->base.port = PORT_FIBRE;
+		qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port);
 		break;
 	case CARD_INFO_TYPE_10G_FIBRE_A:
 	case CARD_INFO_TYPE_10G_FIBRE_B:
-		qeth_set_ecmd_adv_sup(ecmd, SPEED_10000, PORT_FIBRE);
-		ecmd->port = PORT_FIBRE;
+		cmd->base.port = PORT_FIBRE;
+		qeth_set_cmd_adv_sup(cmd, SPEED_10000, cmd->base.port);
 		break;
 	}
 
 	switch (carrier_info.port_mode) {
 	case CARD_INFO_PORTM_FULLDUPLEX:
-		ecmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 		break;
 	case CARD_INFO_PORTM_HALFDUPLEX:
-		ecmd->duplex = DUPLEX_HALF;
+		cmd->base.duplex = DUPLEX_HALF;
 		break;
 	}
 
 	switch (carrier_info.port_speed) {
 	case CARD_INFO_PORTS_10M:
-		speed = SPEED_10;
+		cmd->base.speed = SPEED_10;
 		break;
 	case CARD_INFO_PORTS_100M:
-		speed = SPEED_100;
+		cmd->base.speed = SPEED_100;
 		break;
 	case CARD_INFO_PORTS_1G:
-		speed = SPEED_1000;
+		cmd->base.speed = SPEED_1000;
 		break;
 	case CARD_INFO_PORTS_10G:
-		speed = SPEED_10000;
+		cmd->base.speed = SPEED_10000;
 		break;
 	}
-	ethtool_cmd_speed_set(ecmd, speed);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_core_ethtool_get_settings);
+EXPORT_SYMBOL_GPL(qeth_core_ethtool_get_link_ksettings);
 
 /* Callback to handle checksum offload command reply from OSA card.
  * Verify that required features have been enabled on the card.
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index bc69d0a338ad..4accb0a61ce0 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -29,7 +29,6 @@ extern unsigned char IPA_PDU_HEADER[];
 #define QETH_TIMEOUT		(10 * HZ)
 #define QETH_IPA_TIMEOUT	(45 * HZ)
 #define QETH_IDX_COMMAND_SEQNO	0xffff0000
-#define SR_INFO_LEN		16
 
 #define QETH_CLEAR_CHANNEL_PARM	-10
 #define QETH_HALT_CHANNEL_PARM	-11
@@ -65,7 +64,6 @@ enum qeth_link_types {
 	QETH_LINK_TYPE_LANE_TR      = 0x82,
 	QETH_LINK_TYPE_LANE_ETH1000 = 0x83,
 	QETH_LINK_TYPE_LANE         = 0x88,
-	QETH_LINK_TYPE_ATM_NATIVE   = 0x90,
 };
 
 /*
@@ -185,8 +183,6 @@ enum qeth_ipa_return_codes {
 	IPA_RC_ENOMEM			= 0xfffe,
 	IPA_RC_FFFF			= 0xffff
 };
-/* for DELIP */
-#define IPA_RC_IP_ADDRESS_NOT_DEFINED	IPA_RC_PRIMARY_ALREADY_DEFINED
 /* for SET_DIAGNOSTIC_ASSIST */
 #define IPA_RC_INVALID_SUBCMD		IPA_RC_IP_TABLE_FULL
 #define IPA_RC_HARDWARE_AUTH_ERROR	IPA_RC_UNKNOWN_ERROR
@@ -631,14 +627,6 @@ enum qeth_ipa_addr_change_code {
 	IPA_ADDR_CHANGE_CODE_MACADDR		= 0x02,
 	IPA_ADDR_CHANGE_CODE_REMOVAL		= 0x80,	/* else addition */
 };
-enum qeth_ipa_addr_change_retcode {
-	IPA_ADDR_CHANGE_RETCODE_OK		= 0x0000,
-	IPA_ADDR_CHANGE_RETCODE_LOSTEVENTS	= 0x0010,
-};
-enum qeth_ipa_addr_change_lostmask {
-	IPA_ADDR_CHANGE_MASK_OVERFLOW		= 0x01,
-	IPA_ADDR_CHANGE_MASK_STATECHANGE	= 0x02,
-};
 
 struct qeth_ipacmd_addr_change_entry {
 	struct net_if_token token;
@@ -817,9 +805,4 @@ extern unsigned char IDX_ACTIVATE_WRITE[];
 	((buffer) && \
 	 (*(buffer + ((*(buffer + 0x0b)) + 4)) == 0xc1))
 
-#define ADDR_FRAME_TYPE_DIX 1
-#define ADDR_FRAME_TYPE_802_3 2
-#define ADDR_FRAME_TYPE_TR_WITHOUT_SR 0x10
-#define ADDR_FRAME_TYPE_TR_WITH_SR 0x20
-
 #endif
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index bea483307618..1b07f382d74c 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/etherdevice.h>
-#include <linux/mii.h>
 #include <linux/ip.h>
 #include <linux/list.h>
 #include <linux/hash.h>
@@ -28,63 +27,12 @@
 static int qeth_l2_set_offline(struct ccwgroup_device *);
 static int qeth_l2_stop(struct net_device *);
 static void qeth_l2_set_rx_mode(struct net_device *);
-static int qeth_l2_recover(void *);
 static void qeth_bridgeport_query_support(struct qeth_card *card);
 static void qeth_bridge_state_change(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
 static void qeth_bridge_host_event(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
 
-static int qeth_l2_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
-	struct qeth_card *card = dev->ml_priv;
-	struct mii_ioctl_data *mii_data;
-	int rc = 0;
-
-	if (!card)
-		return -ENODEV;
-
-	if (!qeth_card_hw_is_reachable(card))
-		return -ENODEV;
-
-	if (card->info.type == QETH_CARD_TYPE_OSN)
-		return -EPERM;
-
-	switch (cmd) {
-	case SIOC_QETH_ADP_SET_SNMP_CONTROL:
-		rc = qeth_snmp_command(card, rq->ifr_ifru.ifru_data);
-		break;
-	case SIOC_QETH_GET_CARD_TYPE:
-		if ((card->info.type == QETH_CARD_TYPE_OSD ||
-		     card->info.type == QETH_CARD_TYPE_OSM ||
-		     card->info.type == QETH_CARD_TYPE_OSX) &&
-		    !card->info.guestlan)
-			return 1;
-		return 0;
-		break;
-	case SIOCGMIIPHY:
-		mii_data = if_mii(rq);
-		mii_data->phy_id = 0;
-		break;
-	case SIOCGMIIREG:
-		mii_data = if_mii(rq);
-		if (mii_data->phy_id != 0)
-			rc = -EINVAL;
-		else
-			mii_data->val_out = qeth_mdio_read(dev,
-				mii_data->phy_id, mii_data->reg_num);
-		break;
-	case SIOC_QETH_QUERY_OAT:
-		rc = qeth_query_oat_command(card, rq->ifr_ifru.ifru_data);
-		break;
-	default:
-		rc = -EOPNOTSUPP;
-	}
-	if (rc)
-		QETH_CARD_TEXT_(card, 2, "ioce%d", rc);
-	return rc;
-}
-
 static int qeth_l2_verify_dev(struct net_device *dev)
 {
 	struct qeth_card *card;
@@ -332,7 +280,7 @@ static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 	else
 		hdr->hdr.l2.flags[2] |= QETH_LAYER2_FLAG_UNICAST;
 
-	hdr->hdr.l2.pkt_length = skb->len-QETH_HEADER_SIZE;
+	hdr->hdr.l2.pkt_length = skb->len - sizeof(struct qeth_hdr);
 	/* VSWITCH relies on the VLAN
 	 * information to be present in
 	 * the QDIO header */
@@ -552,81 +500,6 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card,
 	return work_done;
 }
 
-static int qeth_l2_poll(struct napi_struct *napi, int budget)
-{
-	struct qeth_card *card = container_of(napi, struct qeth_card, napi);
-	int work_done = 0;
-	struct qeth_qdio_buffer *buffer;
-	int done;
-	int new_budget = budget;
-
-	if (card->options.performance_stats) {
-		card->perf_stats.inbound_cnt++;
-		card->perf_stats.inbound_start_time = qeth_get_micros();
-	}
-
-	while (1) {
-		if (!card->rx.b_count) {
-			card->rx.qdio_err = 0;
-			card->rx.b_count = qdio_get_next_buffers(
-				card->data.ccwdev, 0, &card->rx.b_index,
-				&card->rx.qdio_err);
-			if (card->rx.b_count <= 0) {
-				card->rx.b_count = 0;
-				break;
-			}
-			card->rx.b_element =
-				&card->qdio.in_q->bufs[card->rx.b_index]
-				.buffer->element[0];
-			card->rx.e_offset = 0;
-		}
-
-		while (card->rx.b_count) {
-			buffer = &card->qdio.in_q->bufs[card->rx.b_index];
-			if (!(card->rx.qdio_err &&
-			    qeth_check_qdio_errors(card, buffer->buffer,
-			    card->rx.qdio_err, "qinerr")))
-				work_done += qeth_l2_process_inbound_buffer(
-					card, new_budget, &done);
-			else
-				done = 1;
-
-			if (done) {
-				if (card->options.performance_stats)
-					card->perf_stats.bufs_rec++;
-				qeth_put_buffer_pool_entry(card,
-					buffer->pool_entry);
-				qeth_queue_input_buffer(card, card->rx.b_index);
-				card->rx.b_count--;
-				if (card->rx.b_count) {
-					card->rx.b_index =
-						(card->rx.b_index + 1) %
-						QDIO_MAX_BUFFERS_PER_Q;
-					card->rx.b_element =
-						&card->qdio.in_q
-						->bufs[card->rx.b_index]
-						.buffer->element[0];
-					card->rx.e_offset = 0;
-				}
-			}
-
-			if (work_done >= budget)
-				goto out;
-			else
-				new_budget = budget - work_done;
-		}
-	}
-
-	napi_complete(napi);
-	if (qdio_start_irq(card->data.ccwdev, 0))
-		napi_schedule(&card->napi);
-out:
-	if (card->options.performance_stats)
-		card->perf_stats.inbound_time += qeth_get_micros() -
-			card->perf_stats.inbound_start_time;
-	return work_done;
-}
-
 static int qeth_l2_request_initial_mac(struct qeth_card *card)
 {
 	int rc = 0;
@@ -808,7 +681,8 @@ static void qeth_l2_set_rx_mode(struct net_device *dev)
 		qeth_promisc_to_bridge(card);
 }
 
-static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb,
+					   struct net_device *dev)
 {
 	int rc;
 	struct qeth_hdr *hdr = NULL;
@@ -849,7 +723,7 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * chaining we can not send long frag lists
 	 */
 	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
-	    !qeth_get_elements_no(card, new_skb, 0)) {
+	    !qeth_get_elements_no(card, new_skb, 0, 0)) {
 		int lin_rc = skb_linearize(new_skb);
 
 		if (card->options.performance_stats) {
@@ -894,7 +768,8 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	elements = qeth_get_elements_no(card, new_skb, elements_needed);
+	elements = qeth_get_elements_no(card, new_skb, elements_needed,
+					(data_offset > 0) ? data_offset : 0);
 	if (!elements) {
 		if (data_offset >= 0)
 			kmem_cache_free(qeth_core_header_cache, hdr);
@@ -909,7 +784,7 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					 elements);
 	} else
 		rc = qeth_do_send_packet_fast(card, queue, new_skb, hdr,
-					elements, data_offset, hd_len);
+					      data_offset, hd_len);
 	if (!rc) {
 		card->stats.tx_packets++;
 		card->stats.tx_bytes += tx_bytes;
@@ -1042,7 +917,7 @@ static const struct ethtool_ops qeth_l2_ethtool_ops = {
 	.get_ethtool_stats = qeth_core_get_ethtool_stats,
 	.get_sset_count = qeth_core_get_sset_count,
 	.get_drvinfo = qeth_core_get_drvinfo,
-	.get_settings = qeth_core_ethtool_get_settings,
+	.get_link_ksettings = qeth_core_ethtool_get_link_ksettings,
 };
 
 static const struct ethtool_ops qeth_l2_osn_ops = {
@@ -1059,7 +934,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_start_xmit		= qeth_l2_hard_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
-	.ndo_do_ioctl	   	= qeth_l2_do_ioctl,
+	.ndo_do_ioctl		= qeth_do_ioctl,
 	.ndo_set_mac_address    = qeth_l2_set_mac_address,
 	.ndo_change_mtu	   	= qeth_change_mtu,
 	.ndo_vlan_rx_add_vid	= qeth_l2_vlan_rx_add_vid,
@@ -1116,7 +991,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
 				  PAGE_SIZE;
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
-	netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
+	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
 	return register_netdev(card->dev);
 }
@@ -1326,17 +1201,6 @@ static void __exit qeth_l2_exit(void)
 	pr_info("unregister layer 2 discipline\n");
 }
 
-static void qeth_l2_shutdown(struct ccwgroup_device *gdev)
-{
-	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
-	qeth_set_allowed_threads(card, 0, 1);
-	if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
-		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
-	qeth_qdio_clear_card(card, 0);
-	qeth_clear_qdio_buffers(card);
-	qdio_free(CARD_DDEV(card));
-}
-
 static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
@@ -1408,15 +1272,16 @@ struct qeth_discipline qeth_l2_discipline = {
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
+	.process_rx_buffer = qeth_l2_process_inbound_buffer,
 	.recover = qeth_l2_recover,
 	.setup = qeth_l2_probe_device,
 	.remove = qeth_l2_remove_device,
 	.set_online = qeth_l2_set_online,
 	.set_offline = qeth_l2_set_offline,
-	.shutdown = qeth_l2_shutdown,
 	.freeze = qeth_l2_pm_suspend,
 	.thaw = qeth_l2_pm_resume,
 	.restore = qeth_l2_pm_resume,
+	.do_ioctl = NULL,
 	.control_event_handler = qeth_l2_control_event,
 };
 EXPORT_SYMBOL_GPL(qeth_l2_discipline);
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 692db49e3d2a..687972356d6b 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -8,9 +8,6 @@
 #include "qeth_core.h"
 #include "qeth_l2.h"
 
-#define QETH_DEVICE_ATTR(_id, _name, _mode, _show, _store) \
-struct device_attribute dev_attr_##_id = __ATTR(_name, _mode, _show, _store)
-
 static ssize_t qeth_bridge_port_role_state_show(struct device *dev,
 				struct device_attribute *attr, char *buf,
 				int show_state)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 06d0addcc058..6e0354ef4b86 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -16,7 +16,6 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/etherdevice.h>
-#include <linux/mii.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/inetdevice.h>
@@ -36,16 +35,12 @@
 
 
 static int qeth_l3_set_offline(struct ccwgroup_device *);
-static int qeth_l3_recover(void *);
 static int qeth_l3_stop(struct net_device *);
 static void qeth_l3_set_multicast_list(struct net_device *);
-static int qeth_l3_neigh_setup(struct net_device *, struct neigh_parms *);
 static int qeth_l3_register_addr_entry(struct qeth_card *,
 		struct qeth_ipaddr *);
 static int qeth_l3_deregister_addr_entry(struct qeth_card *,
 		struct qeth_ipaddr *);
-static int __qeth_l3_set_online(struct ccwgroup_device *, int);
-static int __qeth_l3_set_offline(struct ccwgroup_device *, int);
 
 static int qeth_l3_isxdigit(char *buf)
 {
@@ -1341,7 +1336,7 @@ qeth_diags_trace(struct qeth_card *card, enum qeth_diags_trace_cmds diags_cmd)
 	return qeth_send_ipa_cmd(card, iob, qeth_diags_trace_cb, NULL);
 }
 
-static void qeth_l3_get_mac_for_ipm(__u32 ipm, char *mac)
+static void qeth_l3_get_mac_for_ipm(__be32 ipm, char *mac)
 {
 	ip_eth_mc_map(ipm, mac);
 }
@@ -1414,7 +1409,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 	     im4 = rcu_dereference(im4->next_rcu)) {
 		qeth_l3_get_mac_for_ipm(im4->multiaddr, buf);
 
-		tmp->u.a4.addr = im4->multiaddr;
+		tmp->u.a4.addr = be32_to_cpu(im4->multiaddr);
 		memcpy(tmp->mac, buf, sizeof(tmp->mac));
 
 		ipm = qeth_l3_ip_from_hash(card, tmp);
@@ -1425,7 +1420,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 			if (!ipm)
 				continue;
 			memcpy(ipm->mac, buf, sizeof(tmp->mac));
-			ipm->u.a4.addr = im4->multiaddr;
+			ipm->u.a4.addr = be32_to_cpu(im4->multiaddr);
 			ipm->is_multicast = 1;
 			ipm->disp_flag = QETH_DISP_ADDR_ADD;
 			hash_add(card->ip_mc_htable,
@@ -1598,8 +1593,8 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 	spin_lock_bh(&card->ip_lock);
 
 	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
-		addr->u.a4.addr = ifa->ifa_address;
-		addr->u.a4.mask = ifa->ifa_mask;
+		addr->u.a4.addr = be32_to_cpu(ifa->ifa_address);
+		addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask);
 		addr->type = QETH_IP_TYPE_NORMAL;
 		qeth_l3_delete_ip(card, addr);
 	}
@@ -1690,25 +1685,25 @@ static inline int qeth_l3_rebuild_skb(struct qeth_card *card,
 			struct sk_buff *skb, struct qeth_hdr *hdr,
 			unsigned short *vlan_id)
 {
-	__be16 prot;
+	__u16 prot;
 	struct iphdr *ip_hdr;
 	unsigned char tg_addr[MAX_ADDR_LEN];
 	int is_vlan = 0;
 
 	if (!(hdr->hdr.l3.flags & QETH_HDR_PASSTHRU)) {
-		prot = htons((hdr->hdr.l3.flags & QETH_HDR_IPV6)? ETH_P_IPV6 :
-			      ETH_P_IP);
+		prot = (hdr->hdr.l3.flags & QETH_HDR_IPV6) ? ETH_P_IPV6 :
+			      ETH_P_IP;
 		switch (hdr->hdr.l3.flags & QETH_HDR_CAST_MASK) {
 		case QETH_CAST_MULTICAST:
 			switch (prot) {
 #ifdef CONFIG_QETH_IPV6
-			case __constant_htons(ETH_P_IPV6):
+			case ETH_P_IPV6:
 				ndisc_mc_map((struct in6_addr *)
 				     skb->data + 24,
 				     tg_addr, card->dev, 0);
 				break;
 #endif
-			case __constant_htons(ETH_P_IP):
+			case ETH_P_IP:
 				ip_hdr = (struct iphdr *)skb->data;
 				ip_eth_mc_map(ip_hdr->daddr, tg_addr);
 				break;
@@ -1795,7 +1790,7 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
 			magic = *(__u16 *)skb->data;
 			if ((card->info.type == QETH_CARD_TYPE_IQD) &&
 			    (magic == ETH_P_AF_IUCV)) {
-				skb->protocol = ETH_P_AF_IUCV;
+				skb->protocol = cpu_to_be16(ETH_P_AF_IUCV);
 				skb->pkt_type = PACKET_HOST;
 				skb->mac_header = NET_SKB_PAD;
 				skb->dev = card->dev;
@@ -1834,81 +1829,6 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
 	return work_done;
 }
 
-static int qeth_l3_poll(struct napi_struct *napi, int budget)
-{
-	struct qeth_card *card = container_of(napi, struct qeth_card, napi);
-	int work_done = 0;
-	struct qeth_qdio_buffer *buffer;
-	int done;
-	int new_budget = budget;
-
-	if (card->options.performance_stats) {
-		card->perf_stats.inbound_cnt++;
-		card->perf_stats.inbound_start_time = qeth_get_micros();
-	}
-
-	while (1) {
-		if (!card->rx.b_count) {
-			card->rx.qdio_err = 0;
-			card->rx.b_count = qdio_get_next_buffers(
-				card->data.ccwdev, 0, &card->rx.b_index,
-				&card->rx.qdio_err);
-			if (card->rx.b_count <= 0) {
-				card->rx.b_count = 0;
-				break;
-			}
-			card->rx.b_element =
-				&card->qdio.in_q->bufs[card->rx.b_index]
-				.buffer->element[0];
-			card->rx.e_offset = 0;
-		}
-
-		while (card->rx.b_count) {
-			buffer = &card->qdio.in_q->bufs[card->rx.b_index];
-			if (!(card->rx.qdio_err &&
-			    qeth_check_qdio_errors(card, buffer->buffer,
-			    card->rx.qdio_err, "qinerr")))
-				work_done += qeth_l3_process_inbound_buffer(
-					card, new_budget, &done);
-			else
-				done = 1;
-
-			if (done) {
-				if (card->options.performance_stats)
-					card->perf_stats.bufs_rec++;
-				qeth_put_buffer_pool_entry(card,
-					buffer->pool_entry);
-				qeth_queue_input_buffer(card, card->rx.b_index);
-				card->rx.b_count--;
-				if (card->rx.b_count) {
-					card->rx.b_index =
-						(card->rx.b_index + 1) %
-						QDIO_MAX_BUFFERS_PER_Q;
-					card->rx.b_element =
-						&card->qdio.in_q
-						->bufs[card->rx.b_index]
-						.buffer->element[0];
-					card->rx.e_offset = 0;
-				}
-			}
-
-			if (work_done >= budget)
-				goto out;
-			else
-				new_budget = budget - work_done;
-		}
-	}
-
-	napi_complete(napi);
-	if (qdio_start_irq(card->data.ccwdev, 0))
-		napi_schedule(&card->napi);
-out:
-	if (card->options.performance_stats)
-		card->perf_stats.inbound_time += qeth_get_micros() -
-			card->perf_stats.inbound_start_time;
-	return work_done;
-}
-
 static int qeth_l3_verify_vlan_dev(struct net_device *dev,
 			struct qeth_card *card)
 {
@@ -2461,15 +2381,8 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct qeth_card *card = dev->ml_priv;
 	struct qeth_arp_cache_entry arp_entry;
-	struct mii_ioctl_data *mii_data;
 	int rc = 0;
 
-	if (!card)
-		return -ENODEV;
-
-	if (!qeth_card_hw_is_reachable(card))
-		return -ENODEV;
-
 	switch (cmd) {
 	case SIOC_QETH_ARP_SET_NO_ENTRIES:
 		if (!capable(CAP_NET_ADMIN)) {
@@ -2514,37 +2427,9 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		}
 		rc = qeth_l3_arp_flush_cache(card);
 		break;
-	case SIOC_QETH_ADP_SET_SNMP_CONTROL:
-		rc = qeth_snmp_command(card, rq->ifr_ifru.ifru_data);
-		break;
-	case SIOC_QETH_GET_CARD_TYPE:
-		if ((card->info.type == QETH_CARD_TYPE_OSD ||
-		     card->info.type == QETH_CARD_TYPE_OSX) &&
-		    !card->info.guestlan)
-			return 1;
-		return 0;
-		break;
-	case SIOCGMIIPHY:
-		mii_data = if_mii(rq);
-		mii_data->phy_id = 0;
-		break;
-	case SIOCGMIIREG:
-		mii_data = if_mii(rq);
-		if (mii_data->phy_id != 0)
-			rc = -EINVAL;
-		else
-			mii_data->val_out = qeth_mdio_read(dev,
-							mii_data->phy_id,
-							mii_data->reg_num);
-		break;
-	case SIOC_QETH_QUERY_OAT:
-		rc = qeth_query_oat_command(card, rq->ifr_ifru.ifru_data);
-		break;
 	default:
 		rc = -EOPNOTSUPP;
 	}
-	if (rc)
-		QETH_CARD_TEXT_(card, 2, "ioce%d", rc);
 	return rc;
 }
 
@@ -2572,10 +2457,10 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 	rcu_read_unlock();
 
 	/* try something else */
-	if (skb->protocol == ETH_P_IPV6)
+	if (be16_to_cpu(skb->protocol) == ETH_P_IPV6)
 		return (skb_network_header(skb)[24] == 0xff) ?
 				RTN_MULTICAST : 0;
-	else if (skb->protocol == ETH_P_IP)
+	else if (be16_to_cpu(skb->protocol) == ETH_P_IP)
 		return ((skb_network_header(skb)[16] & 0xf0) == 0xe0) ?
 				RTN_MULTICAST : 0;
 	/* ... */
@@ -2609,17 +2494,13 @@ static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card,
 	char daddr[16];
 	struct af_iucv_trans_hdr *iucv_hdr;
 
-	skb_pull(skb, 14);
-	card->dev->header_ops->create(skb, card->dev, 0,
-				      card->dev->dev_addr, card->dev->dev_addr,
-				      card->dev->addr_len);
-	skb_pull(skb, 14);
-	iucv_hdr = (struct af_iucv_trans_hdr *)skb->data;
 	memset(hdr, 0, sizeof(struct qeth_hdr));
 	hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
 	hdr->hdr.l3.ext_flags = 0;
-	hdr->hdr.l3.length = skb->len;
+	hdr->hdr.l3.length = skb->len - ETH_HLEN;
 	hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
+
+	iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
 	memset(daddr, 0, sizeof(daddr));
 	daddr[0] = 0xfe;
 	daddr[1] = 0x80;
@@ -2730,7 +2611,7 @@ static void qeth_tso_fill_header(struct qeth_card *card,
 	hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len -
 				       sizeof(struct qeth_hdr_tso));
 	tcph->check = 0;
-	if (skb->protocol == ETH_P_IPV6) {
+	if (be16_to_cpu(skb->protocol) == ETH_P_IPV6) {
 		ip6h->payload_len = 0;
 		tcph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
 					       0, IPPROTO_TCP, 0);
@@ -2774,10 +2655,11 @@ static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
 	return elements;
 }
 
-static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
+					   struct net_device *dev)
 {
 	int rc;
-	u16 *tag;
+	__be16 *tag;
 	struct qeth_hdr *hdr = NULL;
 	int hdr_elements = 0;
 	int elements;
@@ -2798,7 +2680,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (((card->info.type == QETH_CARD_TYPE_IQD) &&
 	     (((card->options.cq != QETH_CQ_ENABLED) && !ipv) ||
 	      ((card->options.cq == QETH_CQ_ENABLED) &&
-	       (skb->protocol != ETH_P_AF_IUCV)))) ||
+	       (be16_to_cpu(skb->protocol) != ETH_P_AF_IUCV)))) ||
 	    card->options.sniffer)
 			goto tx_drop;
 
@@ -2823,10 +2705,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if ((card->info.type == QETH_CARD_TYPE_IQD) &&
 	    !skb_is_nonlinear(skb)) {
 		new_skb = skb;
-		if (new_skb->protocol == ETH_P_AF_IUCV)
-			data_offset = 0;
-		else
-			data_offset = ETH_HLEN;
+		data_offset = ETH_HLEN;
 		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 		if (!hdr)
 			goto tx_drop;
@@ -2854,9 +2733,9 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				new_skb->data + 8, 4);
 			skb_copy_to_linear_data_offset(new_skb, 8,
 				new_skb->data + 12, 4);
-			tag = (u16 *)(new_skb->data + 12);
-			*tag = __constant_htons(ETH_P_8021Q);
-			*(tag + 1) = htons(skb_vlan_tag_get(new_skb));
+			tag = (__be16 *)(new_skb->data + 12);
+			*tag = cpu_to_be16(ETH_P_8021Q);
+			*(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
 		}
 	}
 
@@ -2867,7 +2746,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
 	    ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
-	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) {
+	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
 		int lin_rc = skb_linearize(new_skb);
 
 		if (card->options.performance_stats) {
@@ -2894,7 +2773,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			qeth_l3_fill_header(card, hdr, new_skb, ipv,
 						cast_type);
 		} else {
-			if (new_skb->protocol == ETH_P_AF_IUCV)
+			if (be16_to_cpu(new_skb->protocol) == ETH_P_AF_IUCV)
 				qeth_l3_fill_af_iucv_hdr(card, hdr, new_skb);
 			else {
 				qeth_l3_fill_header(card, hdr, new_skb, ipv,
@@ -2909,7 +2788,8 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	elements = use_tso ?
 		   qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
-		   qeth_get_elements_no(card, new_skb, hdr_elements);
+		   qeth_get_elements_no(card, new_skb, hdr_elements,
+					(data_offset > 0) ? data_offset : 0);
 	if (!elements) {
 		if (data_offset >= 0)
 			kmem_cache_free(qeth_core_header_cache, hdr);
@@ -2931,7 +2811,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		rc = qeth_do_send_packet(card, queue, new_skb, hdr, elements);
 	} else
 		rc = qeth_do_send_packet_fast(card, queue, new_skb, hdr,
-					elements, data_offset, 0);
+					      data_offset, 0);
 
 	if (!rc) {
 		card->stats.tx_packets++;
@@ -3032,7 +2912,7 @@ static const struct ethtool_ops qeth_l3_ethtool_ops = {
 	.get_ethtool_stats = qeth_core_get_ethtool_stats,
 	.get_sset_count = qeth_core_get_sset_count,
 	.get_drvinfo = qeth_core_get_drvinfo,
-	.get_settings = qeth_core_ethtool_get_settings,
+	.get_link_ksettings = qeth_core_ethtool_get_link_ksettings,
 };
 
 /*
@@ -3066,7 +2946,7 @@ static const struct net_device_ops qeth_l3_netdev_ops = {
 	.ndo_start_xmit		= qeth_l3_hard_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
-	.ndo_do_ioctl		= qeth_l3_do_ioctl,
+	.ndo_do_ioctl		= qeth_do_ioctl,
 	.ndo_change_mtu		= qeth_change_mtu,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
@@ -3082,7 +2962,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
 	.ndo_start_xmit		= qeth_l3_hard_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
-	.ndo_do_ioctl		= qeth_l3_do_ioctl,
+	.ndo_do_ioctl		= qeth_do_ioctl,
 	.ndo_change_mtu		= qeth_change_mtu,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
@@ -3151,7 +3031,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				  PAGE_SIZE;
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
-	netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
+	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
 	return register_netdev(card->dev);
 }
@@ -3372,17 +3252,6 @@ static int qeth_l3_recover(void *ptr)
 	return 0;
 }
 
-static void qeth_l3_shutdown(struct ccwgroup_device *gdev)
-{
-	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
-	qeth_set_allowed_threads(card, 0, 1);
-	if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
-		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
-	qeth_qdio_clear_card(card, 0);
-	qeth_clear_qdio_buffers(card);
-	qdio_free(CARD_DDEV(card));
-}
-
 static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
@@ -3440,15 +3309,16 @@ struct qeth_discipline qeth_l3_discipline = {
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
+	.process_rx_buffer = qeth_l3_process_inbound_buffer,
 	.recover = qeth_l3_recover,
 	.setup = qeth_l3_probe_device,
 	.remove = qeth_l3_remove_device,
 	.set_online = qeth_l3_set_online,
 	.set_offline = qeth_l3_set_offline,
-	.shutdown = qeth_l3_shutdown,
 	.freeze = qeth_l3_pm_suspend,
 	.thaw = qeth_l3_pm_resume,
 	.restore = qeth_l3_pm_resume,
+	.do_ioctl = qeth_l3_do_ioctl,
 	.control_event_handler = qeth_l3_control_event,
 };
 EXPORT_SYMBOL_GPL(qeth_l3_discipline);
@@ -3472,8 +3342,8 @@ static int qeth_l3_ip_event(struct notifier_block *this,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
 	if (addr) {
-		addr->u.a4.addr = ifa->ifa_address;
-		addr->u.a4.mask = ifa->ifa_mask;
+		addr->u.a4.addr = be32_to_cpu(ifa->ifa_address);
+		addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask);
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
 		return NOTIFY_DONE;
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 05e9471e3d3f..ff29a4b416b4 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -286,7 +286,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 		if (!addr)
 			return -ENOMEM;
 
-		addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
+		addr->u.a6.addr.s6_addr32[0] = cpu_to_be32(0xfe800000);
 		addr->u.a6.addr.s6_addr32[1] = 0x00000000;
 		for (i = 8; i < 16; i++)
 			addr->u.a6.addr.s6_addr[i] =
@@ -320,7 +320,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
 	if (addr != NULL) {
-		addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
+		addr->u.a6.addr.s6_addr32[0] = cpu_to_be32(0xfe800000);
 		addr->u.a6.addr.s6_addr32[1] = 0x00000000;
 		for (i = 8; i < 16; i++)
 			addr->u.a6.addr.s6_addr[i] = card->options.hsuid[i - 8];
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index 6ff61dad5e21..62fed9dc893e 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -183,11 +183,33 @@ static void jsfd_read(char *buf, unsigned long p, size_t togo) {
 	}
 }
 
-static void jsfd_do_request(struct request_queue *q)
+static int jsfd_queue;
+
+static struct request *jsfd_next_request(void)
+{
+	struct request_queue *q;
+	struct request *rq;
+	int old_pos = jsfd_queue;
+
+	do {
+		q = jsfd_disk[jsfd_queue]->queue;
+		if (++jsfd_queue == JSF_MAX)
+			jsfd_queue = 0;
+		if (q) {
+			rq = blk_fetch_request(q);
+			if (rq)
+				return rq;
+		}
+	} while (jsfd_queue != old_pos);
+
+	return NULL;
+}
+
+static void jsfd_request(void)
 {
 	struct request *req;
 
-	req = blk_fetch_request(q);
+	req = jsfd_next_request();
 	while (req) {
 		struct jsfd_part *jdp = req->rq_disk->private_data;
 		unsigned long offset = blk_rq_pos(req) << 9;
@@ -211,10 +233,15 @@ static void jsfd_do_request(struct request_queue *q)
 		err = 0;
 	end:
 		if (!__blk_end_request_cur(req, err))
-			req = blk_fetch_request(q);
+			req = jsfd_next_request();
 	}
 }
 
+static void jsfd_do_request(struct request_queue *q)
+{
+	jsfd_request();
+}
+
 /*
  * The memory devices use the full 32/64 bits of the offset, and so we cannot
  * check against negative addresses: they are ok. The return value is weird,
@@ -544,8 +571,6 @@ static int jsflash_init(void)
 	return 0;
 }
 
-static struct request_queue *jsf_queue;
-
 static int jsfd_init(void)
 {
 	static DEFINE_SPINLOCK(lock);
@@ -562,6 +587,11 @@ static int jsfd_init(void)
 		struct gendisk *disk = alloc_disk(1);
 		if (!disk)
 			goto out;
+		disk->queue = blk_init_queue(jsfd_do_request, &lock);
+		if (!disk->queue) {
+			put_disk(disk);
+			goto out;
+		}
 		jsfd_disk[i] = disk;
 	}
 
@@ -570,13 +600,6 @@ static int jsfd_init(void)
 		goto out;
 	}
 
-	jsf_queue = blk_init_queue(jsfd_do_request, &lock);
-	if (!jsf_queue) {
-		err = -ENOMEM;
-		unregister_blkdev(JSFD_MAJOR, "jsfd");
-		goto out;
-	}
-
 	for (i = 0; i < JSF_MAX; i++) {
 		struct gendisk *disk = jsfd_disk[i];
 		if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
@@ -589,7 +612,6 @@ static int jsfd_init(void)
 		disk->fops = &jsfd_fops;
 		set_capacity(disk, jdp->dsize >> 9);
 		disk->private_data = jdp;
-		disk->queue = jsf_queue;
 		add_disk(disk);
 		set_disk_ro(disk, 1);
 	}
@@ -619,6 +641,7 @@ static void __exit jsflash_cleanup_module(void)
 	for (i = 0; i < JSF_MAX; i++) {
 		if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
 		del_gendisk(jsfd_disk[i]);
+		blk_cleanup_queue(jsfd_disk[i]->queue);
 		put_disk(jsfd_disk[i]);
 	}
 	if (jsf0.busy)
@@ -628,7 +651,6 @@ static void __exit jsflash_cleanup_module(void)
 
 	misc_deregister(&jsf_dev);
 	unregister_blkdev(JSFD_MAJOR, "jsfd");
-	blk_cleanup_queue(jsf_queue);
 }
 
 module_init(jsflash_init_module);
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 230043c1c90f..3c52867dfe28 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1241,16 +1241,15 @@ config SCSI_LPFC
 	tristate "Emulex LightPulse Fibre Channel Support"
 	depends on PCI && SCSI
 	depends on SCSI_FC_ATTRS
-	depends on NVME_FC && NVME_TARGET_FC
 	select CRC_T10DIF
-	help
+	---help---
           This lpfc driver supports the Emulex LightPulse
           Family of Fibre Channel PCI host adapters.
 
 config SCSI_LPFC_DEBUG_FS
 	bool "Emulex LightPulse Fibre Channel debugfs Support"
 	depends on SCSI_LPFC && DEBUG_FS
-	help
+	---help---
 	  This makes debugging information from the lpfc driver
 	  available via the debugfs filesystem.
 
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index fc2855565a51..93dbe58c47c8 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -166,6 +166,7 @@ scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
 scsi_mod-$(CONFIG_SCSI_NETLINK)	+= scsi_netlink.o
 scsi_mod-$(CONFIG_SYSCTL)	+= scsi_sysctl.o
 scsi_mod-$(CONFIG_SCSI_PROC_FS)	+= scsi_proc.o
+scsi_mod-$(CONFIG_BLK_DEBUG_FS)	+= scsi_debugfs.o
 scsi_mod-y			+= scsi_trace.o scsi_logging.o
 scsi_mod-$(CONFIG_PM)		+= scsi_pm.o
 scsi_mod-$(CONFIG_SCSI_DH)	+= scsi_dh.o
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index d036a806f31c..d281492009fb 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1690,9 +1690,6 @@ struct aac_dev
 #define aac_adapter_sync_cmd(dev, command, p1, p2, p3, p4, p5, p6, status, r1, r2, r3, r4) \
 	(dev)->a_ops.adapter_sync_cmd(dev, command, p1, p2, p3, p4, p5, p6, status, r1, r2, r3, r4)
 
-#define aac_adapter_check_health(dev) \
-	(dev)->a_ops.adapter_check_health(dev)
-
 #define aac_adapter_restart(dev, bled, reset_type) \
 	((dev)->a_ops.adapter_restart(dev, bled, reset_type))
 
@@ -2615,6 +2612,14 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor)
 	return capacity;
 }
 
+static inline int aac_adapter_check_health(struct aac_dev *dev)
+{
+	if (unlikely(pci_channel_offline(dev->pdev)))
+		return -1;
+
+	return (dev)->a_ops.adapter_check_health(dev);
+}
+
 /* SCp.phase values */
 #define AAC_OWNER_MIDLEVEL	0x101
 #define AAC_OWNER_LOWLEVEL	0x102
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a3ad04293487..1f4918355fdb 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1873,7 +1873,8 @@ int aac_check_health(struct aac_dev * aac)
 	spin_unlock_irqrestore(&aac->fib_lock, flagv);
 
 	if (BlinkLED < 0) {
-		printk(KERN_ERR "%s: Host adapter dead %d\n", aac->name, BlinkLED);
+		printk(KERN_ERR "%s: Host adapter is dead (or got a PCI error) %d\n",
+				aac->name, BlinkLED);
 		goto out;
 	}
 
@@ -2056,7 +2057,6 @@ static int fillup_pools(struct aac_dev *dev, struct hw_fib **hw_fib_pool,
 {
 	struct hw_fib **hw_fib_p;
 	struct fib **fib_p;
-	int rcode = 1;
 
 	hw_fib_p = hw_fib_pool;
 	fib_p = fib_pool;
@@ -2074,11 +2074,11 @@ static int fillup_pools(struct aac_dev *dev, struct hw_fib **hw_fib_pool,
 		}
 	}
 
+	/*
+	 * Get the actual number of allocated fibs
+	 */
 	num = hw_fib_p - hw_fib_pool;
-	if (!num)
-		rcode = 0;
-
-	return rcode;
+	return num;
 }
 
 static void wakeup_fibctx_threads(struct aac_dev *dev,
@@ -2186,7 +2186,6 @@ static void aac_process_events(struct aac_dev *dev)
 	struct fib *fib;
 	unsigned long flags;
 	spinlock_t *t_lock;
-	unsigned int rcode;
 
 	t_lock = dev->queues->queue[HostNormCmdQueue].lock;
 	spin_lock_irqsave(t_lock, flags);
@@ -2269,8 +2268,8 @@ static void aac_process_events(struct aac_dev *dev)
 		 * Fill up fib pointer pools with actual fibs
 		 * and hw_fibs
 		 */
-		rcode = fillup_pools(dev, hw_fib_pool, fib_pool, num);
-		if (!rcode)
+		num = fillup_pools(dev, hw_fib_pool, fib_pool, num);
+		if (!num)
 			goto free_mem;
 
 		/*
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 2e5338dec621..7b0410e0f569 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -468,7 +468,7 @@ err_out:
 	return -1;
 
 err_blink:
-	return (status > 16) & 0xFF;
+	return (status >> 16) & 0xFF;
 }
 
 static inline u32 aac_get_vector(struct aac_dev *dev)
diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c
index 109e2c99e6c1..95d8f25cbcca 100644
--- a/drivers/scsi/aic7xxx/aic79xx_core.c
+++ b/drivers/scsi/aic7xxx/aic79xx_core.c
@@ -6278,7 +6278,7 @@ ahd_reset(struct ahd_softc *ahd, int reinit)
 		 * does not disable its parity logic prior to
 		 * the start of the reset.  This may cause a
 		 * parity error to be detected and thus a
-		 * spurious SERR or PERR assertion.  Disble
+		 * spurious SERR or PERR assertion.  Disable
 		 * PERR and SERR responses during the CHIPRST.
 		 */
 		mod_cmd = cmd & ~(PCIM_CMD_PERRESPEN|PCIM_CMD_SERRESPEN);
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 48e200102221..c01b47e5b55a 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -113,7 +113,7 @@ struct alua_queue_data {
 #define ALUA_POLICY_SWITCH_ALL		1
 
 static void alua_rtpg_work(struct work_struct *work);
-static void alua_rtpg_queue(struct alua_port_group *pg,
+static bool alua_rtpg_queue(struct alua_port_group *pg,
 			    struct scsi_device *sdev,
 			    struct alua_queue_data *qdata, bool force);
 static void alua_check(struct scsi_device *sdev, bool force);
@@ -862,7 +862,13 @@ static void alua_rtpg_work(struct work_struct *work)
 	kref_put(&pg->kref, release_port_group);
 }
 
-static void alua_rtpg_queue(struct alua_port_group *pg,
+/**
+ * alua_rtpg_queue() - cause RTPG to be submitted asynchronously
+ *
+ * Returns true if and only if alua_rtpg_work() will be called asynchronously.
+ * That function is responsible for calling @qdata->fn().
+ */
+static bool alua_rtpg_queue(struct alua_port_group *pg,
 			    struct scsi_device *sdev,
 			    struct alua_queue_data *qdata, bool force)
 {
@@ -870,8 +876,8 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
 	unsigned long flags;
 	struct workqueue_struct *alua_wq = kaluad_wq;
 
-	if (!pg)
-		return;
+	if (WARN_ON_ONCE(!pg) || scsi_device_get(sdev))
+		return false;
 
 	spin_lock_irqsave(&pg->lock, flags);
 	if (qdata) {
@@ -884,14 +890,12 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
 		pg->flags |= ALUA_PG_RUN_RTPG;
 		kref_get(&pg->kref);
 		pg->rtpg_sdev = sdev;
-		scsi_device_get(sdev);
 		start_queue = 1;
 	} else if (!(pg->flags & ALUA_PG_RUN_RTPG) && force) {
 		pg->flags |= ALUA_PG_RUN_RTPG;
 		/* Do not queue if the worker is already running */
 		if (!(pg->flags & ALUA_PG_RUNNING)) {
 			kref_get(&pg->kref);
-			sdev = NULL;
 			start_queue = 1;
 		}
 	}
@@ -900,13 +904,17 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
 		alua_wq = kaluad_sync_wq;
 	spin_unlock_irqrestore(&pg->lock, flags);
 
-	if (start_queue &&
-	    !queue_delayed_work(alua_wq, &pg->rtpg_work,
-				msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) {
-		if (sdev)
-			scsi_device_put(sdev);
-		kref_put(&pg->kref, release_port_group);
+	if (start_queue) {
+		if (queue_delayed_work(alua_wq, &pg->rtpg_work,
+				msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS)))
+			sdev = NULL;
+		else
+			kref_put(&pg->kref, release_port_group);
 	}
+	if (sdev)
+		scsi_device_put(sdev);
+
+	return true;
 }
 
 /*
@@ -1007,11 +1015,13 @@ static int alua_activate(struct scsi_device *sdev,
 		mutex_unlock(&h->init_mutex);
 		goto out;
 	}
-	fn = NULL;
 	rcu_read_unlock();
 	mutex_unlock(&h->init_mutex);
 
-	alua_rtpg_queue(pg, sdev, qdata, true);
+	if (alua_rtpg_queue(pg, sdev, qdata, true))
+		fn = NULL;
+	else
+		err = SCSI_DH_DEV_OFFLINED;
 	kref_put(&pg->kref, release_port_group);
 out:
 	if (fn)
diff --git a/drivers/scsi/esas2r/esas2r_ioctl.c b/drivers/scsi/esas2r/esas2r_ioctl.c
index b35ed3829421..2d4b7f049a68 100644
--- a/drivers/scsi/esas2r/esas2r_ioctl.c
+++ b/drivers/scsi/esas2r/esas2r_ioctl.c
@@ -1289,32 +1289,13 @@ int esas2r_ioctl_handler(void *hostdata, int cmd, void __user *arg)
 	    || (cmd > EXPRESS_IOCTL_MAX))
 		return -ENOTSUPP;
 
-	if (!access_ok(VERIFY_WRITE, arg, sizeof(struct atto_express_ioctl))) {
+	ioctl = memdup_user(arg, sizeof(struct atto_express_ioctl));
+	if (IS_ERR(ioctl)) {
 		esas2r_log(ESAS2R_LOG_WARN,
 			   "ioctl_handler access_ok failed for cmd %d, "
 			   "address %p", cmd,
 			   arg);
-		return -EFAULT;
-	}
-
-	/* allocate a kernel memory buffer for the IOCTL data */
-	ioctl = kzalloc(sizeof(struct atto_express_ioctl), GFP_KERNEL);
-	if (ioctl == NULL) {
-		esas2r_log(ESAS2R_LOG_WARN,
-			   "ioctl_handler kzalloc failed for %zu bytes",
-			   sizeof(struct atto_express_ioctl));
-		return -ENOMEM;
-	}
-
-	err = __copy_from_user(ioctl, arg, sizeof(struct atto_express_ioctl));
-	if (err != 0) {
-		esas2r_log(ESAS2R_LOG_WARN,
-			   "copy_from_user didn't copy everything (err %d, cmd %d)",
-			   err,
-			   cmd);
-		kfree(ioctl);
-
-		return -EFAULT;
+		return PTR_ERR(ioctl);
 	}
 
 	/* verify the signature */
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 524a0c755ed7..9d659aaace15 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -2956,7 +2956,7 @@ static int hpsa_send_reset(struct ctlr_info *h, unsigned char *scsi3addr,
 	/* fill_cmd can't fail here, no data buffer to map. */
 	(void) fill_cmd(c, reset_type, h, NULL, 0, 0,
 			scsi3addr, TYPE_MSG);
-	rc = hpsa_scsi_do_simple_cmd(h, c, reply_queue, DEFAULT_TIMEOUT);
+	rc = hpsa_scsi_do_simple_cmd(h, c, reply_queue, NO_TIMEOUT);
 	if (rc) {
 		dev_warn(&h->pdev->dev, "Failed to send reset command\n");
 		goto out;
@@ -3714,7 +3714,7 @@ exit_failed:
  *  # (integer code indicating one of several NOT READY states
  *     describing why a volume is to be kept offline)
  */
-static int hpsa_volume_offline(struct ctlr_info *h,
+static unsigned char hpsa_volume_offline(struct ctlr_info *h,
 					unsigned char scsi3addr[])
 {
 	struct CommandList *c;
@@ -3735,7 +3735,7 @@ static int hpsa_volume_offline(struct ctlr_info *h,
 					DEFAULT_TIMEOUT);
 	if (rc) {
 		cmd_free(h, c);
-		return 0;
+		return HPSA_VPD_LV_STATUS_UNSUPPORTED;
 	}
 	sense = c->err_info->SenseInfo;
 	if (c->err_info->SenseLen > sizeof(c->err_info->SenseInfo))
@@ -3746,19 +3746,13 @@ static int hpsa_volume_offline(struct ctlr_info *h,
 	cmd_status = c->err_info->CommandStatus;
 	scsi_status = c->err_info->ScsiStatus;
 	cmd_free(h, c);
-	/* Is the volume 'not ready'? */
-	if (cmd_status != CMD_TARGET_STATUS ||
-		scsi_status != SAM_STAT_CHECK_CONDITION ||
-		sense_key != NOT_READY ||
-		asc != ASC_LUN_NOT_READY)  {
-		return 0;
-	}
 
 	/* Determine the reason for not ready state */
 	ldstat = hpsa_get_volume_status(h, scsi3addr);
 
 	/* Keep volume offline in certain cases: */
 	switch (ldstat) {
+	case HPSA_LV_FAILED:
 	case HPSA_LV_UNDERGOING_ERASE:
 	case HPSA_LV_NOT_AVAILABLE:
 	case HPSA_LV_UNDERGOING_RPI:
@@ -3780,7 +3774,7 @@ static int hpsa_volume_offline(struct ctlr_info *h,
 	default:
 		break;
 	}
-	return 0;
+	return HPSA_LV_OK;
 }
 
 /*
@@ -3853,10 +3847,10 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 	/* Do an inquiry to the device to see what it is. */
 	if (hpsa_scsi_do_inquiry(h, scsi3addr, 0, inq_buff,
 		(unsigned char) OBDR_TAPE_INQ_SIZE) != 0) {
-		/* Inquiry failed (msg printed already) */
 		dev_err(&h->pdev->dev,
-			"hpsa_update_device_info: inquiry failed\n");
-		rc = -EIO;
+			"%s: inquiry failed, device will be skipped.\n",
+			__func__);
+		rc = HPSA_INQUIRY_FAILED;
 		goto bail_out;
 	}
 
@@ -3885,15 +3879,20 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 	if ((this_device->devtype == TYPE_DISK ||
 		this_device->devtype == TYPE_ZBC) &&
 		is_logical_dev_addr_mode(scsi3addr)) {
-		int volume_offline;
+		unsigned char volume_offline;
 
 		hpsa_get_raid_level(h, scsi3addr, &this_device->raid_level);
 		if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC)
 			hpsa_get_ioaccel_status(h, scsi3addr, this_device);
 		volume_offline = hpsa_volume_offline(h, scsi3addr);
-		if (volume_offline < 0 || volume_offline > 0xff)
-			volume_offline = HPSA_VPD_LV_STATUS_UNSUPPORTED;
-		this_device->volume_offline = volume_offline & 0xff;
+		this_device->volume_offline = volume_offline;
+		if (volume_offline == HPSA_LV_FAILED) {
+			rc = HPSA_LV_FAILED;
+			dev_err(&h->pdev->dev,
+				"%s: LV failed, device will be skipped.\n",
+				__func__);
+			goto bail_out;
+		}
 	} else {
 		this_device->raid_level = RAID_UNKNOWN;
 		this_device->offload_config = 0;
@@ -4379,8 +4378,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 			goto out;
 		}
 		if (rc) {
-			dev_warn(&h->pdev->dev,
-				"Inquiry failed, skipping device.\n");
+			h->drv_req_rescan = 1;
 			continue;
 		}
 
@@ -5558,7 +5556,7 @@ static void hpsa_scan_complete(struct ctlr_info *h)
 
 	spin_lock_irqsave(&h->scan_lock, flags);
 	h->scan_finished = 1;
-	wake_up_all(&h->scan_wait_queue);
+	wake_up(&h->scan_wait_queue);
 	spin_unlock_irqrestore(&h->scan_lock, flags);
 }
 
@@ -5576,11 +5574,23 @@ static void hpsa_scan_start(struct Scsi_Host *sh)
 	if (unlikely(lockup_detected(h)))
 		return hpsa_scan_complete(h);
 
+	/*
+	 * If a scan is already waiting to run, no need to add another
+	 */
+	spin_lock_irqsave(&h->scan_lock, flags);
+	if (h->scan_waiting) {
+		spin_unlock_irqrestore(&h->scan_lock, flags);
+		return;
+	}
+
+	spin_unlock_irqrestore(&h->scan_lock, flags);
+
 	/* wait until any scan already in progress is finished. */
 	while (1) {
 		spin_lock_irqsave(&h->scan_lock, flags);
 		if (h->scan_finished)
 			break;
+		h->scan_waiting = 1;
 		spin_unlock_irqrestore(&h->scan_lock, flags);
 		wait_event(h->scan_wait_queue, h->scan_finished);
 		/* Note: We don't need to worry about a race between this
@@ -5590,6 +5600,7 @@ static void hpsa_scan_start(struct Scsi_Host *sh)
 		 */
 	}
 	h->scan_finished = 0; /* mark scan as in progress */
+	h->scan_waiting = 0;
 	spin_unlock_irqrestore(&h->scan_lock, flags);
 
 	if (unlikely(lockup_detected(h)))
@@ -8792,6 +8803,7 @@ reinit_after_soft_reset:
 	init_waitqueue_head(&h->event_sync_wait_queue);
 	mutex_init(&h->reset_mutex);
 	h->scan_finished = 1; /* no scan currently in progress */
+	h->scan_waiting = 0;
 
 	pci_set_drvdata(pdev, h);
 	h->ndevices = 0;
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index bf6cdc106654..6f04f2ad4125 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -201,6 +201,7 @@ struct ctlr_info {
 	dma_addr_t		errinfo_pool_dhandle;
 	unsigned long  		*cmd_pool_bits;
 	int			scan_finished;
+	u8			scan_waiting : 1;
 	spinlock_t		scan_lock;
 	wait_queue_head_t	scan_wait_queue;
 
diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index a584cdf07058..5961705eef76 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -156,6 +156,7 @@
 #define CFGTBL_BusType_Fibre2G  0x00000200l
 
 /* VPD Inquiry types */
+#define HPSA_INQUIRY_FAILED		0x02
 #define HPSA_VPD_SUPPORTED_PAGES        0x00
 #define HPSA_VPD_LV_DEVICE_ID           0x83
 #define HPSA_VPD_LV_DEVICE_GEOMETRY     0xC1
@@ -166,6 +167,7 @@
 /* Logical volume states */
 #define HPSA_VPD_LV_STATUS_UNSUPPORTED			0xff
 #define HPSA_LV_OK                                      0x0
+#define HPSA_LV_FAILED					0x01
 #define HPSA_LV_NOT_AVAILABLE				0x0b
 #define HPSA_LV_UNDERGOING_ERASE			0x0F
 #define HPSA_LV_UNDERGOING_RPI				0x12
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index b29afafc2885..5d5e272fd815 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6293,7 +6293,12 @@ static void ipr_erp_start(struct ipr_ioa_cfg *ioa_cfg,
 		break;
 	case IPR_IOASC_MED_DO_NOT_REALLOC: /* prevent retries */
 	case IPR_IOASA_IR_DUAL_IOA_DISABLED:
-		scsi_cmd->result |= (DID_PASSTHROUGH << 16);
+		/*
+		 * exception: do not set DID_PASSTHROUGH on CHECK CONDITION
+		 * so SCSI mid-layer and upper layers handle it accordingly.
+		 */
+		if (scsi_cmd->result != SAM_STAT_CHECK_CONDITION)
+			scsi_cmd->result |= (DID_PASSTHROUGH << 16);
 		break;
 	case IPR_IOASC_BUS_WAS_RESET:
 	case IPR_IOASC_BUS_WAS_RESET_BY_OTHER:
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 4228aba1f654..bbea8eac9abb 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -387,7 +387,7 @@ static int iscsi_sw_tcp_pdu_xmit(struct iscsi_task *task)
 		rc = 0;
 	}
 
-	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+	current_restore_flags(pflags, PF_MEMALLOC);
 	return rc;
 }
 
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 07c08ce68d70..894b1e3ebd56 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -561,8 +561,12 @@ static void iscsi_complete_task(struct iscsi_task *task, int state)
 	WARN_ON_ONCE(task->state == ISCSI_TASK_FREE);
 	task->state = state;
 
-	if (!list_empty(&task->running))
+	spin_lock_bh(&conn->taskqueuelock);
+	if (!list_empty(&task->running)) {
+		pr_debug_once("%s while task on list", __func__);
 		list_del_init(&task->running);
+	}
+	spin_unlock_bh(&conn->taskqueuelock);
 
 	if (conn->task == task)
 		conn->task = NULL;
@@ -784,7 +788,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 		if (session->tt->xmit_task(task))
 			goto free_task;
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->mgmtqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
@@ -1475,8 +1481,10 @@ void iscsi_requeue_task(struct iscsi_task *task)
 	 * this may be on the requeue list already if the xmit_task callout
 	 * is handling the r2ts while we are adding new ones
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 	if (list_empty(&task->running))
 		list_add_tail(&task->running, &conn->requeue);
+	spin_unlock_bh(&conn->taskqueuelock);
 	iscsi_conn_queue_work(conn);
 }
 EXPORT_SYMBOL_GPL(iscsi_requeue_task);
@@ -1513,22 +1521,26 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
 	 * only have one nop-out as a ping from us and targets should not
 	 * overflow us with nop-ins
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 check_mgmt:
 	while (!list_empty(&conn->mgmtqueue)) {
 		conn->task = list_entry(conn->mgmtqueue.next,
 					 struct iscsi_task, running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (iscsi_prep_mgmt_task(conn, conn->task)) {
 			/* regular RX path uses back_lock */
 			spin_lock_bh(&conn->session->back_lock);
 			__iscsi_put_task(conn->task);
 			spin_unlock_bh(&conn->session->back_lock);
 			conn->task = NULL;
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 	}
 
 	/* process pending command queue */
@@ -1536,19 +1548,24 @@ check_mgmt:
 		conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task,
 					running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (conn->session->state == ISCSI_STATE_LOGGING_OUT) {
 			fail_scsi_task(conn->task, DID_IMM_RETRY);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_prep_scsi_cmd_pdu(conn->task);
 		if (rc) {
 			if (rc == -ENOMEM || rc == -EACCES) {
+				spin_lock_bh(&conn->taskqueuelock);
 				list_add_tail(&conn->task->running,
 					      &conn->cmdqueue);
 				conn->task = NULL;
+				spin_unlock_bh(&conn->taskqueuelock);
 				goto done;
 			} else
 				fail_scsi_task(conn->task, DID_ABORT);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
@@ -1559,6 +1576,7 @@ check_mgmt:
 		 * we need to check the mgmt queue for nops that need to
 		 * be sent to aviod starvation
 		 */
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
@@ -1578,12 +1596,15 @@ check_mgmt:
 		conn->task = task;
 		list_del_init(&conn->task->running);
 		conn->task->state = ISCSI_TASK_RUNNING;
+		spin_unlock_bh(&conn->taskqueuelock);
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
+	spin_unlock_bh(&conn->taskqueuelock);
 	spin_unlock_bh(&conn->session->frwd_lock);
 	return -ENODATA;
 
@@ -1739,7 +1760,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 			goto prepd_reject;
 		}
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->cmdqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
@@ -2897,6 +2920,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 	INIT_LIST_HEAD(&conn->mgmtqueue);
 	INIT_LIST_HEAD(&conn->cmdqueue);
 	INIT_LIST_HEAD(&conn->requeue);
+	spin_lock_init(&conn->taskqueuelock);
 	INIT_WORK(&conn->xmitwork, iscsi_xmitworker);
 
 	/* allocate login_task used for the login/text sequences */
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 763f012fdeca..87f5e694dbed 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -221,7 +221,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		task->num_scatter = qc->n_elem;
 	} else {
 		for_each_sg(qc->sg, sg, qc->n_elem, si)
-			xfer += sg->length;
+			xfer += sg_dma_len(sg);
 
 		task->total_xfer_len = xfer;
 		task->num_scatter = si;
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 0bba2e30b4f0..6d7840b096e6 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -56,7 +56,7 @@ struct lpfc_sli2_slim;
 #define LPFC_MAX_SG_SEG_CNT	4096	/* sg element count per scsi cmnd */
 #define LPFC_MAX_SGL_SEG_CNT	512	/* SGL element count per scsi cmnd */
 #define LPFC_MAX_BPL_SEG_CNT	4096	/* BPL element count per scsi cmnd */
-#define LPFC_MIN_NVME_SEG_CNT	254
+#define LPFC_MAX_NVME_SEG_CNT	128	/* max SGL element cnt per NVME cmnd */
 
 #define LPFC_MAX_SGE_SIZE       0x80000000 /* Maximum data allowed in a SGE */
 #define LPFC_IOCB_LIST_CNT	2250	/* list of IOCBs for fast-path usage. */
@@ -99,12 +99,13 @@ struct lpfc_sli2_slim;
 #define FC_MAX_ADPTMSG		64
 
 #define MAX_HBAEVT	32
+#define MAX_HBAS_NO_RESET 16
 
 /* Number of MSI-X vectors the driver uses */
 #define LPFC_MSIX_VECTORS	2
 
 /* lpfc wait event data ready flag */
-#define LPFC_DATA_READY		(1<<0)
+#define LPFC_DATA_READY		0	/* bit 0 */
 
 /* queue dump line buffer size */
 #define LPFC_LBUF_SZ		128
@@ -473,6 +474,8 @@ struct lpfc_vport {
 	unsigned long rcv_buffer_time_stamp;
 	uint32_t vport_flag;
 #define STATIC_VPORT	1
+#define FAWWPN_SET	2
+#define FAWWPN_PARAM_CHG	4
 
 	uint16_t fdmi_num_disc;
 	uint32_t fdmi_hba_mask;
@@ -692,6 +695,7 @@ struct lpfc_hba {
 					 * capability
 					 */
 #define HBA_NVME_IOQ_FLUSH      0x80000 /* NVME IO queues flushed. */
+#define NVME_XRI_ABORT_EVENT	0x100000
 
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
@@ -779,6 +783,7 @@ struct lpfc_hba {
 	uint32_t cfg_nvmet_fb_size;
 	uint32_t cfg_total_seg_cnt;
 	uint32_t cfg_sg_seg_cnt;
+	uint32_t cfg_nvme_seg_cnt;
 	uint32_t cfg_sg_dma_buf_size;
 	uint64_t cfg_soft_wwnn;
 	uint64_t cfg_soft_wwpn;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 5c783ef7f260..513fd07715cd 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -2292,6 +2292,8 @@ lpfc_soft_wwn_enable_store(struct device *dev, struct device_attribute *attr,
 	struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
 	unsigned int cnt = count;
+	uint8_t vvvl = vport->fc_sparam.cmn.valid_vendor_ver_level;
+	u32 *fawwpn_key = (uint32_t *)&vport->fc_sparam.un.vendorVersion[0];
 
 	/*
 	 * We're doing a simple sanity check for soft_wwpn setting.
@@ -2305,6 +2307,12 @@ lpfc_soft_wwn_enable_store(struct device *dev, struct device_attribute *attr,
 	 * here. The intent is to protect against the random user or
 	 * application that is just writing attributes.
 	 */
+	if (vvvl == 1 && cpu_to_be32(*fawwpn_key) == FAPWWN_KEY_VENDOR) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				 "0051 "LPFC_DRIVER_NAME" soft wwpn can not"
+				 " be enabled: fawwpn is enabled\n");
+		return -EINVAL;
+	}
 
 	/* count may include a LF at end of string */
 	if (buf[cnt-1] == '\n')
@@ -3010,6 +3018,12 @@ MODULE_PARM_DESC(lpfc_poll, "FCP ring polling mode control:"
 static DEVICE_ATTR(lpfc_poll, S_IRUGO | S_IWUSR,
 		   lpfc_poll_show, lpfc_poll_store);
 
+int lpfc_no_hba_reset_cnt;
+unsigned long lpfc_no_hba_reset[MAX_HBAS_NO_RESET] = {
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+module_param_array(lpfc_no_hba_reset, ulong, &lpfc_no_hba_reset_cnt, 0444);
+MODULE_PARM_DESC(lpfc_no_hba_reset, "WWPN of HBAs that should not be reset");
+
 LPFC_ATTR(sli_mode, 0, 0, 3,
 	"SLI mode selector:"
 	" 0 - auto (SLI-3 if supported),"
@@ -3309,9 +3323,9 @@ LPFC_ATTR_R(nvmet_mrq_post, LPFC_DEF_MRQ_POST,
  * lpfc_enable_fc4_type: Defines what FC4 types are supported.
  * Supported Values:  1 - register just FCP
  *                    3 - register both FCP and NVME
- * Supported values are [1,3]. Default value is 3
+ * Supported values are [1,3]. Default value is 1
  */
-LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_BOTH,
+LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_FCP,
 	    LPFC_ENABLE_FCP, LPFC_ENABLE_BOTH,
 	    "Define fc4 type to register with fabric.");
 
@@ -3329,7 +3343,7 @@ LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_BOTH,
  * percentage will go to NVME.
  */
 LPFC_ATTR_R(xri_split, 50, 10, 90,
-	     "Division of XRI resources between SCSI and NVME");
+	    "Division of XRI resources between SCSI and NVME");
 
 /*
 # lpfc_log_verbose: Only turn this flag on if you are willing to risk being
@@ -4451,7 +4465,8 @@ lpfc_fcp_imax_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	phba->cfg_fcp_imax = (uint32_t)val;
-	for (i = 0; i < phba->io_channel_irqs; i++)
+
+	for (i = 0; i < phba->io_channel_irqs; i += LPFC_MAX_EQ_DELAY_EQID_CNT)
 		lpfc_modify_hba_eq_delay(phba, i);
 
 	return strlen(buf);
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 18157d2840a3..a1686c2d863c 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2486,6 +2486,10 @@ static int lpfcdiag_loop_self_reg(struct lpfc_hba *phba, uint16_t *rpi)
 				mbox, *rpi);
 	else {
 		*rpi = lpfc_sli4_alloc_rpi(phba);
+		if (*rpi == LPFC_RPI_ALLOC_ERROR) {
+			mempool_free(mbox, phba->mbox_mem_pool);
+			return -EBUSY;
+		}
 		status = lpfc_reg_rpi(phba, phba->pport->vpi,
 				phba->pport->fc_myDID,
 				(uint8_t *)&phba->pport->fc_sparam,
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 843dd73004da..944b32ca4931 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -24,6 +24,7 @@ typedef int (*node_filter)(struct lpfc_nodelist *, void *);
 
 struct fc_rport;
 struct fc_frame_header;
+struct lpfc_nvmet_rcv_ctx;
 void lpfc_down_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_sli_read_link_ste(struct lpfc_hba *);
 void lpfc_dump_mem(struct lpfc_hba *, LPFC_MBOXQ_t *, uint16_t, uint16_t);
@@ -99,7 +100,7 @@ void lpfc_issue_reg_vpi(struct lpfc_hba *, struct lpfc_vport *);
 
 int lpfc_check_sli_ndlp(struct lpfc_hba *, struct lpfc_sli_ring *,
 			struct lpfc_iocbq *, struct lpfc_nodelist *);
-void lpfc_nlp_init(struct lpfc_vport *, struct lpfc_nodelist *, uint32_t);
+struct lpfc_nodelist *lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did);
 struct lpfc_nodelist *lpfc_nlp_get(struct lpfc_nodelist *);
 int  lpfc_nlp_put(struct lpfc_nodelist *);
 int  lpfc_nlp_not_used(struct lpfc_nodelist *ndlp);
@@ -245,6 +246,10 @@ struct hbq_dmabuf *lpfc_sli4_rb_alloc(struct lpfc_hba *);
 void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
 struct rqb_dmabuf *lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba);
 void lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab);
+void lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
+			struct lpfc_dmabuf *mp);
+int lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
+			       struct fc_frame_header *fc_hdr);
 void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
 			uint16_t);
 int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
@@ -302,6 +307,8 @@ int lpfc_sli_check_eratt(struct lpfc_hba *);
 void lpfc_sli_handle_slow_ring_event(struct lpfc_hba *,
 				    struct lpfc_sli_ring *, uint32_t);
 void lpfc_sli4_handle_received_buffer(struct lpfc_hba *, struct hbq_dmabuf *);
+void lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
+			     struct fc_frame_header *fc_hdr, bool aborted);
 void lpfc_sli_def_mbox_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *, LPFC_MBOXQ_t *);
 int lpfc_sli_issue_iocb(struct lpfc_hba *, uint32_t,
@@ -384,7 +391,7 @@ void lpfc_free_sysfs_attr(struct lpfc_vport *);
 extern struct device_attribute *lpfc_hba_attrs[];
 extern struct device_attribute *lpfc_vport_attrs[];
 extern struct scsi_host_template lpfc_template;
-extern struct scsi_host_template lpfc_template_s3;
+extern struct scsi_host_template lpfc_template_no_hr;
 extern struct scsi_host_template lpfc_template_nvme;
 extern struct scsi_host_template lpfc_vport_template;
 extern struct fc_function_template lpfc_transport_functions;
@@ -554,3 +561,5 @@ void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba,
 				struct lpfc_wcqe_complete *abts_cmpl);
 extern int lpfc_enable_nvmet_cnt;
 extern unsigned long long lpfc_enable_nvmet[];
+extern int lpfc_no_hba_reset_cnt;
+extern unsigned long lpfc_no_hba_reset[];
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index c22bb3f887e1..1487406aea77 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -537,19 +537,53 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 	}
 }
 
+static void
+lpfc_ns_rsp_audit_did(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
+{
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_nodelist *ndlp = NULL;
+	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+
+	/*
+	 * To conserve rpi's, filter out addresses for other
+	 * vports on the same physical HBAs.
+	 */
+	if (Did != vport->fc_myDID &&
+	    (!lpfc_find_vport_by_did(phba, Did) ||
+	     vport->cfg_peer_port_login)) {
+		if (!phba->nvmet_support) {
+			/* FCPI/NVMEI path. Process Did */
+			lpfc_prep_node_fc4type(vport, Did, fc4_type);
+			return;
+		}
+		/* NVMET path.  NVMET only cares about NVMEI nodes. */
+		list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
+			if (ndlp->nlp_type != NLP_NVME_INITIATOR ||
+			    ndlp->nlp_state != NLP_STE_UNMAPPED_NODE)
+				continue;
+			spin_lock_irq(shost->host_lock);
+			if (ndlp->nlp_DID == Did)
+				ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
+			else
+				ndlp->nlp_flag |= NLP_NVMET_RECOV;
+			spin_unlock_irq(shost->host_lock);
+		}
+	}
+}
+
 static int
 lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
 	    uint32_t Size)
 {
-	struct lpfc_hba  *phba = vport->phba;
 	struct lpfc_sli_ct_request *Response =
 		(struct lpfc_sli_ct_request *) mp->virt;
-	struct lpfc_nodelist *ndlp = NULL;
 	struct lpfc_dmabuf *mlast, *next_mp;
 	uint32_t *ctptr = (uint32_t *) & Response->un.gid.PortType;
 	uint32_t Did, CTentry;
 	int Cnt;
 	struct list_head head;
+	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+	struct lpfc_nodelist *ndlp = NULL;
 
 	lpfc_set_disctmo(vport);
 	vport->num_disc_nodes = 0;
@@ -574,19 +608,7 @@ lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
 			/* Get next DID from NameServer List */
 			CTentry = *ctptr++;
 			Did = ((be32_to_cpu(CTentry)) & Mask_DID);
-
-			ndlp = NULL;
-
-			/*
-			 * Check for rscn processing or not
-			 * To conserve rpi's, filter out addresses for other
-			 * vports on the same physical HBAs.
-			 */
-			if ((Did != vport->fc_myDID) &&
-			    ((lpfc_find_vport_by_did(phba, Did) == NULL) ||
-			     vport->cfg_peer_port_login))
-				lpfc_prep_node_fc4type(vport, Did, fc4_type);
-
+			lpfc_ns_rsp_audit_did(vport, Did, fc4_type);
 			if (CTentry & (cpu_to_be32(SLI_CT_LAST_ENTRY)))
 				goto nsout1;
 
@@ -596,6 +618,22 @@ lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
 
 	}
 
+	/* All GID_FT entries processed.  If the driver is running in
+	 * in target mode, put impacted nodes into recovery and drop
+	 * the RPI to flush outstanding IO.
+	 */
+	if (vport->phba->nvmet_support) {
+		list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
+			if (!(ndlp->nlp_flag & NLP_NVMET_RECOV))
+				continue;
+			lpfc_disc_state_machine(vport, ndlp, NULL,
+						NLP_EVT_DEVICE_RECOVERY);
+			spin_lock_irq(shost->host_lock);
+			ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
+			spin_lock_irq(shost->host_lock);
+		}
+	}
+
 nsout1:
 	list_del(&head);
 	return 0;
@@ -939,8 +977,8 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 					 "FC4 x%08x, Data: x%08x x%08x\n",
 					 ndlp, did, ndlp->nlp_fc4_type,
 					 FC_TYPE_FCP, FC_TYPE_NVME);
+			ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 		}
-		ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
 		lpfc_issue_els_prli(vport, ndlp, 0);
 	} else
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 9f4798e9d938..fce549a91911 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -745,73 +745,102 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 {
 	struct lpfc_hba   *phba = vport->phba;
 	struct lpfc_nvmet_tgtport *tgtp;
+	struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
 	int len = 0;
+	int cnt;
 
 	if (phba->nvmet_support) {
 		if (!phba->targetport)
 			return len;
 		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"\nNVME Targetport Statistics\n");
 
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"LS: Rcv %08x Drop %08x Abort %08x\n",
 				atomic_read(&tgtp->rcv_ls_req_in),
 				atomic_read(&tgtp->rcv_ls_req_drop),
 				atomic_read(&tgtp->xmt_ls_abort));
 		if (atomic_read(&tgtp->rcv_ls_req_in) !=
 		    atomic_read(&tgtp->rcv_ls_req_out)) {
-			len += snprintf(buf+len, size-len,
+			len += snprintf(buf + len, size - len,
 					"Rcv LS: in %08x != out %08x\n",
 					atomic_read(&tgtp->rcv_ls_req_in),
 					atomic_read(&tgtp->rcv_ls_req_out));
 		}
 
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"LS: Xmt %08x Drop %08x Cmpl %08x Err %08x\n",
 				atomic_read(&tgtp->xmt_ls_rsp),
 				atomic_read(&tgtp->xmt_ls_drop),
 				atomic_read(&tgtp->xmt_ls_rsp_cmpl),
 				atomic_read(&tgtp->xmt_ls_rsp_error));
 
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"FCP: Rcv %08x Drop %08x\n",
 				atomic_read(&tgtp->rcv_fcp_cmd_in),
 				atomic_read(&tgtp->rcv_fcp_cmd_drop));
 
 		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
 		    atomic_read(&tgtp->rcv_fcp_cmd_out)) {
-			len += snprintf(buf+len, size-len,
+			len += snprintf(buf + len, size - len,
 					"Rcv FCP: in %08x != out %08x\n",
 					atomic_read(&tgtp->rcv_fcp_cmd_in),
 					atomic_read(&tgtp->rcv_fcp_cmd_out));
 		}
 
-		len += snprintf(buf+len, size-len,
-				"FCP Rsp: read %08x readrsp %08x write %08x rsp %08x\n",
+		len += snprintf(buf + len, size - len,
+				"FCP Rsp: read %08x readrsp %08x "
+				"write %08x rsp %08x\n",
 				atomic_read(&tgtp->xmt_fcp_read),
 				atomic_read(&tgtp->xmt_fcp_read_rsp),
 				atomic_read(&tgtp->xmt_fcp_write),
 				atomic_read(&tgtp->xmt_fcp_rsp));
 
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"FCP Rsp: abort %08x drop %08x\n",
 				atomic_read(&tgtp->xmt_fcp_abort),
 				atomic_read(&tgtp->xmt_fcp_drop));
 
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
 				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
 				atomic_read(&tgtp->xmt_fcp_rsp_error),
 				atomic_read(&tgtp->xmt_fcp_rsp_drop));
 
-		len += snprintf(buf+len, size-len,
+		len += snprintf(buf + len, size - len,
 				"ABORT: Xmt %08x Err %08x Cmpl %08x",
 				atomic_read(&tgtp->xmt_abort_rsp),
 				atomic_read(&tgtp->xmt_abort_rsp_error),
 				atomic_read(&tgtp->xmt_abort_cmpl));
 
-		len +=  snprintf(buf+len, size-len, "\n");
+		len +=  snprintf(buf + len, size - len, "\n");
+
+		cnt = 0;
+		spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		list_for_each_entry_safe(ctxp, next_ctxp,
+				&phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+				list) {
+			cnt++;
+		}
+		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		if (cnt) {
+			len += snprintf(buf + len, size - len,
+					"ABORT: %d ctx entries\n", cnt);
+			spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+			list_for_each_entry_safe(ctxp, next_ctxp,
+				    &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+				    list) {
+				if (len >= (size - LPFC_DEBUG_OUT_LINE_SZ))
+					break;
+				len += snprintf(buf + len, size - len,
+						"Entry: oxid %x state %x "
+						"flag %x\n",
+						ctxp->oxid, ctxp->state,
+						ctxp->flag);
+			}
+			spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		}
 	} else {
 		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
 			return len;
@@ -3128,8 +3157,6 @@ __lpfc_idiag_print_rqpair(struct lpfc_queue *qp, struct lpfc_queue *datqp,
 			datqp->queue_id, datqp->entry_count,
 			datqp->entry_size, datqp->host_index,
 			datqp->hba_index);
-	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
-
 	return len;
 }
 
@@ -3653,17 +3680,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
 			goto pass_check;
 		}
-		/* NVME LS complete queue */
-		if (phba->sli4_hba.nvmels_cq &&
-		    phba->sli4_hba.nvmels_cq->queue_id == queid) {
-			/* Sanity check */
-			rc = lpfc_idiag_que_param_check(
-					phba->sli4_hba.nvmels_cq, index, count);
-			if (rc)
-				goto error_out;
-			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
-			goto pass_check;
-		}
 		/* FCP complete queue */
 		if (phba->sli4_hba.fcp_cq) {
 			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
@@ -3738,17 +3754,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			idiag.ptr_private = phba->sli4_hba.nvmels_wq;
 			goto pass_check;
 		}
-		/* NVME LS work queue */
-		if (phba->sli4_hba.nvmels_wq &&
-		    phba->sli4_hba.nvmels_wq->queue_id == queid) {
-			/* Sanity check */
-			rc = lpfc_idiag_que_param_check(
-					phba->sli4_hba.nvmels_wq, index, count);
-			if (rc)
-				goto error_out;
-			idiag.ptr_private = phba->sli4_hba.nvmels_wq;
-			goto pass_check;
-		}
 		/* FCP work queue */
 		if (phba->sli4_hba.fcp_wq) {
 			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
@@ -5722,10 +5727,8 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	struct lpfc_hba   *phba = vport->phba;
 
-	if (vport->disc_trc) {
-		kfree(vport->disc_trc);
-		vport->disc_trc = NULL;
-	}
+	kfree(vport->disc_trc);
+	vport->disc_trc = NULL;
 
 	debugfs_remove(vport->debug_disc_trc); /* discovery_trace */
 	vport->debug_disc_trc = NULL;
@@ -5792,10 +5795,8 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 		debugfs_remove(phba->debug_readRef); /* readRef */
 		phba->debug_readRef = NULL;
 
-		if (phba->slow_ring_trc) {
-			kfree(phba->slow_ring_trc);
-			phba->slow_ring_trc = NULL;
-		}
+		kfree(phba->slow_ring_trc);
+		phba->slow_ring_trc = NULL;
 
 		/* slow_ring_trace */
 		debugfs_remove(phba->debug_slow_ring_trc);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index c05f56c3023f..7b7d314af0e0 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -44,14 +44,6 @@
 /* hbqinfo output buffer size */
 #define LPFC_HBQINFO_SIZE 8192
 
-enum {
-	DUMP_FCP,
-	DUMP_NVME,
-	DUMP_MBX,
-	DUMP_ELS,
-	DUMP_NVMELS,
-};
-
 /* nvmestat output buffer size */
 #define LPFC_NVMESTAT_SIZE 8192
 #define LPFC_NVMEKTIME_SIZE 8192
@@ -283,8 +275,22 @@ struct lpfc_idiag {
 	struct lpfc_idiag_offset offset;
 	void *ptr_private;
 };
+
+#else
+
+#define lpfc_nvmeio_data(phba, fmt, arg...) \
+	no_printk(fmt, ##arg)
+
 #endif
 
+enum {
+	DUMP_FCP,
+	DUMP_NVME,
+	DUMP_MBX,
+	DUMP_ELS,
+	DUMP_NVMELS,
+};
+
 /* Mask for discovery_trace */
 #define LPFC_DISC_TRC_ELS_CMD		0x1	/* Trace ELS commands */
 #define LPFC_DISC_TRC_ELS_RSP		0x2	/* Trace ELS response */
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index f4ff99d95db3..9d5a379f4b15 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -157,6 +157,7 @@ struct lpfc_node_rrq {
 #define NLP_LOGO_SND       0x00000100	/* sent LOGO request for this entry */
 #define NLP_RNID_SND       0x00000400	/* sent RNID request for this entry */
 #define NLP_ELS_SND_MASK   0x000007e0	/* sent ELS request for this entry */
+#define NLP_NVMET_RECOV    0x00001000   /* NVMET auditing node for recovery. */
 #define NLP_DEFER_RM       0x00010000	/* Remove this ndlp if no longer used */
 #define NLP_DELAY_TMO      0x00020000	/* delay timeout is running for node */
 #define NLP_NPR_2B_DISC    0x00040000	/* node is included in num_disc_nodes */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 2d26440e6f2f..67827e397431 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -603,9 +603,11 @@ lpfc_check_clean_addr_bit(struct lpfc_vport *vport,
 		memcmp(&vport->fabric_portname, &sp->portName,
 			sizeof(struct lpfc_name)) ||
 		memcmp(&vport->fabric_nodename, &sp->nodeName,
-			sizeof(struct lpfc_name)))
+			sizeof(struct lpfc_name)) ||
+		(vport->vport_flag & FAWWPN_PARAM_CHG)) {
 		fabric_param_changed = 1;
-
+		vport->vport_flag &= ~FAWWPN_PARAM_CHG;
+	}
 	/*
 	 * Word 1 Bit 31 in common service parameter is overloaded.
 	 * Word 1 Bit 31 in FLOGI request is multiple NPort request
@@ -895,10 +897,9 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			 * Cannot find existing Fabric ndlp, so allocate a
 			 * new one
 			 */
-			ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+			ndlp = lpfc_nlp_init(vport, PT2PT_RemoteID);
 			if (!ndlp)
 				goto fail;
-			lpfc_nlp_init(vport, ndlp, PT2PT_RemoteID);
 		} else if (!NLP_CHK_NODE_ACT(ndlp)) {
 			ndlp = lpfc_enable_node(vport, ndlp,
 						NLP_STE_UNUSED_NODE);
@@ -1364,7 +1365,6 @@ lpfc_els_abort_flogi(struct lpfc_hba *phba)
 int
 lpfc_initial_flogi(struct lpfc_vport *vport)
 {
-	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ndlp;
 
 	vport->port_state = LPFC_FLOGI;
@@ -1374,10 +1374,9 @@ lpfc_initial_flogi(struct lpfc_vport *vport)
 	ndlp = lpfc_findnode_did(vport, Fabric_DID);
 	if (!ndlp) {
 		/* Cannot find existing Fabric ndlp, so allocate a new one */
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, Fabric_DID);
 		if (!ndlp)
 			return 0;
-		lpfc_nlp_init(vport, ndlp, Fabric_DID);
 		/* Set the node type */
 		ndlp->nlp_type |= NLP_FABRIC;
 		/* Put ndlp onto node list */
@@ -1418,17 +1417,15 @@ lpfc_initial_flogi(struct lpfc_vport *vport)
 int
 lpfc_initial_fdisc(struct lpfc_vport *vport)
 {
-	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ndlp;
 
 	/* First look for the Fabric ndlp */
 	ndlp = lpfc_findnode_did(vport, Fabric_DID);
 	if (!ndlp) {
 		/* Cannot find existing Fabric ndlp, so allocate a new one */
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, Fabric_DID);
 		if (!ndlp)
 			return 0;
-		lpfc_nlp_init(vport, ndlp, Fabric_DID);
 		/* Put ndlp onto node list */
 		lpfc_enqueue_node(vport, ndlp);
 	} else if (!NLP_CHK_NODE_ACT(ndlp)) {
@@ -1564,14 +1561,13 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 					     phba->active_rrq_pool);
 			return ndlp;
 		}
-		new_ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_ATOMIC);
+		new_ndlp = lpfc_nlp_init(vport, ndlp->nlp_DID);
 		if (!new_ndlp) {
 			if (active_rrqs_xri_bitmap)
 				mempool_free(active_rrqs_xri_bitmap,
 					     phba->active_rrq_pool);
 			return ndlp;
 		}
-		lpfc_nlp_init(vport, new_ndlp, ndlp->nlp_DID);
 	} else if (!NLP_CHK_NODE_ACT(new_ndlp)) {
 		rc = memcmp(&ndlp->nlp_portname, name,
 			    sizeof(struct lpfc_name));
@@ -2845,10 +2841,9 @@ lpfc_issue_els_scr(struct lpfc_vport *vport, uint32_t nportid, uint8_t retry)
 
 	ndlp = lpfc_findnode_did(vport, nportid);
 	if (!ndlp) {
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, nportid);
 		if (!ndlp)
 			return 1;
-		lpfc_nlp_init(vport, ndlp, nportid);
 		lpfc_enqueue_node(vport, ndlp);
 	} else if (!NLP_CHK_NODE_ACT(ndlp)) {
 		ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
@@ -2938,10 +2933,9 @@ lpfc_issue_els_farpr(struct lpfc_vport *vport, uint32_t nportid, uint8_t retry)
 
 	ndlp = lpfc_findnode_did(vport, nportid);
 	if (!ndlp) {
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, nportid);
 		if (!ndlp)
 			return 1;
-		lpfc_nlp_init(vport, ndlp, nportid);
 		lpfc_enqueue_node(vport, ndlp);
 	} else if (!NLP_CHK_NODE_ACT(ndlp)) {
 		ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
@@ -4403,7 +4397,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	pcmd = (uint8_t *) (((struct lpfc_dmabuf *) elsiocb->context2)->virt);
 	memset(pcmd, 0, cmdsize);
 
-	*((uint32_t *) (pcmd)) = (ELS_CMD_ACC | (ELS_CMD_PRLI & ~ELS_RSP_MASK));
+	*((uint32_t *)(pcmd)) = elsrspcmd;
 	pcmd += sizeof(uint32_t);
 
 	/* For PRLI, remainder of payload is PRLI parameter page */
@@ -5177,15 +5171,15 @@ lpfc_rdp_res_speed(struct fc_rdp_port_speed_desc *desc, struct lpfc_hba *phba)
 
 static uint32_t
 lpfc_rdp_res_diag_port_names(struct fc_rdp_port_name_desc *desc,
-		struct lpfc_hba *phba)
+		struct lpfc_vport *vport)
 {
 
 	desc->tag = cpu_to_be32(RDP_PORT_NAMES_DESC_TAG);
 
-	memcpy(desc->port_names.wwnn, phba->wwnn,
+	memcpy(desc->port_names.wwnn, &vport->fc_nodename,
 			sizeof(desc->port_names.wwnn));
 
-	memcpy(desc->port_names.wwpn, phba->wwpn,
+	memcpy(desc->port_names.wwpn, &vport->fc_portname,
 			sizeof(desc->port_names.wwpn));
 
 	desc->length = cpu_to_be32(sizeof(desc->port_names));
@@ -5279,7 +5273,7 @@ lpfc_els_rdp_cmpl(struct lpfc_hba *phba, struct lpfc_rdp_context *rdp_context,
 	len += lpfc_rdp_res_link_error((struct fc_rdp_link_error_status_desc *)
 				       (len + pcmd), &rdp_context->link_stat);
 	len += lpfc_rdp_res_diag_port_names((struct fc_rdp_port_name_desc *)
-					     (len + pcmd), phba);
+					     (len + pcmd), vport);
 	len += lpfc_rdp_res_attach_port_names((struct fc_rdp_port_name_desc *)
 					(len + pcmd), vport, ndlp);
 	len += lpfc_rdp_res_fec_desc((struct fc_fec_rdp_desc *)(len + pcmd),
@@ -5867,8 +5861,11 @@ lpfc_rscn_recovery_check(struct lpfc_vport *vport)
 		    (ndlp->nlp_state == NLP_STE_UNUSED_NODE) ||
 		    !lpfc_rscn_payload_check(vport, ndlp->nlp_DID))
 			continue;
+
+		/* NVME Target mode does not do RSCN Recovery. */
 		if (vport->phba->nvmet_support)
 			continue;
+
 		lpfc_disc_state_machine(vport, ndlp, NULL,
 					NLP_EVT_DEVICE_RECOVERY);
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
@@ -6133,7 +6130,6 @@ int
 lpfc_els_handle_rscn(struct lpfc_vport *vport)
 {
 	struct lpfc_nodelist *ndlp;
-	struct lpfc_hba *phba = vport->phba;
 
 	/* Ignore RSCN if the port is being torn down. */
 	if (vport->load_flag & FC_UNLOADING) {
@@ -6157,22 +6153,16 @@ lpfc_els_handle_rscn(struct lpfc_vport *vport)
 	ndlp = lpfc_findnode_did(vport, NameServer_DID);
 	if (ndlp && NLP_CHK_NODE_ACT(ndlp)
 	    && ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) {
-		/* Good ndlp, issue CT Request to NameServer */
+		/* Good ndlp, issue CT Request to NameServer.  Need to
+		 * know how many gidfts were issued.  If none, then just
+		 * flush the RSCN.  Otherwise, the outstanding requests
+		 * need to complete.
+		 */
 		vport->gidft_inp = 0;
-		if (lpfc_issue_gidft(vport) == 0)
-			/* Wait for NameServer query cmpl before we can
-			 * continue
-			 */
+		if (lpfc_issue_gidft(vport) > 0)
 			return 1;
 	} else {
-		/* If login to NameServer does not exist, issue one */
-		/* Good status, issue PLOGI to NameServer */
-		ndlp = lpfc_findnode_did(vport, NameServer_DID);
-		if (ndlp && NLP_CHK_NODE_ACT(ndlp))
-			/* Wait for NameServer login cmpl before we can
-			   continue */
-			return 1;
-
+		/* Nameserver login in question.  Revalidate. */
 		if (ndlp) {
 			ndlp = lpfc_enable_node(vport, ndlp,
 						NLP_STE_PLOGI_ISSUE);
@@ -6182,12 +6172,11 @@ lpfc_els_handle_rscn(struct lpfc_vport *vport)
 			}
 			ndlp->nlp_prev_state = NLP_STE_UNUSED_NODE;
 		} else {
-			ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+			ndlp = lpfc_nlp_init(vport, NameServer_DID);
 			if (!ndlp) {
 				lpfc_els_flush_rscn(vport);
 				return 0;
 			}
-			lpfc_nlp_init(vport, ndlp, NameServer_DID);
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 		}
@@ -7746,11 +7735,9 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	ndlp = lpfc_findnode_did(vport, did);
 	if (!ndlp) {
 		/* Cannot find existing Fabric ndlp, so allocate a new one */
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, did);
 		if (!ndlp)
 			goto dropit;
-
-		lpfc_nlp_init(vport, ndlp, did);
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 		newnode = 1;
 		if ((did & Fabric_DID_MASK) == Fabric_DID_MASK)
@@ -7968,7 +7955,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPRLI++;
-		if (vport->port_state < LPFC_DISC_AUTH) {
+		if ((vport->port_state < LPFC_DISC_AUTH) &&
+		    (vport->fc_flag & FC_FABRIC)) {
 			rjt_err = LSRJT_UNABLE_TPC;
 			rjt_exp = LSEXP_NOTHING_MORE;
 			break;
@@ -8192,7 +8180,6 @@ lpfc_els_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 static void
 lpfc_start_fdmi(struct lpfc_vport *vport)
 {
-	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ndlp;
 
 	/* If this is the first time, allocate an ndlp and initialize
@@ -8201,9 +8188,8 @@ lpfc_start_fdmi(struct lpfc_vport *vport)
 	 */
 	ndlp = lpfc_findnode_did(vport, FDMI_DID);
 	if (!ndlp) {
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, FDMI_DID);
 		if (ndlp) {
-			lpfc_nlp_init(vport, ndlp, FDMI_DID);
 			ndlp->nlp_type |= NLP_FABRIC;
 		} else {
 			return;
@@ -8256,7 +8242,7 @@ lpfc_do_scr_ns_plogi(struct lpfc_hba *phba, struct lpfc_vport *vport)
 
 	ndlp = lpfc_findnode_did(vport, NameServer_DID);
 	if (!ndlp) {
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, NameServer_DID);
 		if (!ndlp) {
 			if (phba->fc_topology == LPFC_TOPOLOGY_LOOP) {
 				lpfc_disc_start(vport);
@@ -8267,7 +8253,6 @@ lpfc_do_scr_ns_plogi(struct lpfc_hba *phba, struct lpfc_vport *vport)
 					 "0251 NameServer login: no memory\n");
 			return;
 		}
-		lpfc_nlp_init(vport, ndlp, NameServer_DID);
 	} else if (!NLP_CHK_NODE_ACT(ndlp)) {
 		ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
 		if (!ndlp) {
@@ -8371,11 +8356,17 @@ lpfc_cmpl_reg_new_vport(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 			spin_lock_irq(shost->host_lock);
 			vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
 			spin_unlock_irq(shost->host_lock);
-			if (vport->port_type == LPFC_PHYSICAL_PORT
-				&& !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG))
-				lpfc_issue_init_vfi(vport);
-			else
+			if (mb->mbxStatus == MBX_NOT_FINISHED)
+				break;
+			if ((vport->port_type == LPFC_PHYSICAL_PORT) &&
+			    !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG)) {
+				if (phba->sli_rev == LPFC_SLI_REV4)
+					lpfc_issue_init_vfi(vport);
+				else
+					lpfc_initial_flogi(vport);
+			} else {
 				lpfc_initial_fdisc(vport);
+			}
 			break;
 		}
 	} else {
@@ -8764,7 +8755,7 @@ lpfc_issue_els_fdisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	pcmd += sizeof(uint32_t); /* Node Name */
 	pcmd += sizeof(uint32_t); /* Node Name */
 	memcpy(pcmd, &vport->fc_nodename, 8);
-
+	memset(sp->un.vendorVersion, 0, sizeof(sp->un.vendorVersion));
 	lpfc_set_disctmo(vport);
 
 	phba->fc_stat.elsXmitFDISC++;
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 194a14d5f8a9..0482c5580331 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -313,8 +313,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 				 ndlp->nlp_state, ndlp->nlp_rpi);
 	}
 
-	if (!(vport->load_flag & FC_UNLOADING) &&
-	    !(ndlp->nlp_flag & NLP_DELAY_TMO) &&
+	if (!(ndlp->nlp_flag & NLP_DELAY_TMO) &&
 	    !(ndlp->nlp_flag & NLP_NPR_2B_DISC) &&
 	    (ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
 	    (ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) &&
@@ -641,6 +640,8 @@ lpfc_work_done(struct lpfc_hba *phba)
 			lpfc_handle_rrq_active(phba);
 		if (phba->hba_flag & FCP_XRI_ABORT_EVENT)
 			lpfc_sli4_fcp_xri_abort_event_proc(phba);
+		if (phba->hba_flag & NVME_XRI_ABORT_EVENT)
+			lpfc_sli4_nvme_xri_abort_event_proc(phba);
 		if (phba->hba_flag & ELS_XRI_ABORT_EVENT)
 			lpfc_sli4_els_xri_abort_event_proc(phba);
 		if (phba->hba_flag & ASYNC_EVENT)
@@ -2173,7 +2174,7 @@ lpfc_mbx_cmpl_fcf_scan_read_fcf_rec(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	uint32_t boot_flag, addr_mode;
 	uint16_t fcf_index, next_fcf_index;
 	struct lpfc_fcf_rec *fcf_rec = NULL;
-	uint16_t vlan_id;
+	uint16_t vlan_id = LPFC_FCOE_NULL_VID;
 	bool select_new_fcf;
 	int rc;
 
@@ -3001,6 +3002,7 @@ lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	MAILBOX_t *mb = &pmb->u.mb;
 	struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *) pmb->context1;
 	struct lpfc_vport  *vport = pmb->vport;
+	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	struct serv_parm *sp = &vport->fc_sparam;
 	uint32_t ed_tov;
 
@@ -3030,6 +3032,7 @@ lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	}
 
 	lpfc_update_vport_wwn(vport);
+	fc_host_port_name(shost) = wwn_to_u64(vport->fc_portname.u.wwn);
 	if (vport->port_type == LPFC_PHYSICAL_PORT) {
 		memcpy(&phba->wwnn, &vport->fc_nodename, sizeof(phba->wwnn));
 		memcpy(&phba->wwpn, &vport->fc_portname, sizeof(phba->wwnn));
@@ -3308,6 +3311,7 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	struct lpfc_sli_ring *pring;
 	MAILBOX_t *mb = &pmb->u.mb;
 	struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *) (pmb->context1);
+	uint8_t attn_type;
 
 	/* Unblock ELS traffic */
 	pring = lpfc_phba_elsring(phba);
@@ -3324,6 +3328,7 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	}
 
 	la = (struct lpfc_mbx_read_top *) &pmb->u.mb.un.varReadTop;
+	attn_type = bf_get(lpfc_mbx_read_top_att_type, la);
 
 	memcpy(&phba->alpa_map[0], mp->virt, 128);
 
@@ -3336,7 +3341,7 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (phba->fc_eventTag <= la->eventTag) {
 		phba->fc_stat.LinkMultiEvent++;
-		if (bf_get(lpfc_mbx_read_top_att_type, la) == LPFC_ATT_LINK_UP)
+		if (attn_type == LPFC_ATT_LINK_UP)
 			if (phba->fc_eventTag != 0)
 				lpfc_linkdown(phba);
 	}
@@ -3352,7 +3357,7 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	}
 
 	phba->link_events++;
-	if ((bf_get(lpfc_mbx_read_top_att_type, la) == LPFC_ATT_LINK_UP) &&
+	if ((attn_type == LPFC_ATT_LINK_UP) &&
 	    !(phba->sli.sli_flag & LPFC_MENLO_MAINT)) {
 		phba->fc_stat.LinkUp++;
 		if (phba->link_flag & LS_LOOPBACK_MODE) {
@@ -3378,8 +3383,8 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 					phba->wait_4_mlo_maint_flg);
 		}
 		lpfc_mbx_process_link_up(phba, la);
-	} else if (bf_get(lpfc_mbx_read_top_att_type, la) ==
-		   LPFC_ATT_LINK_DOWN) {
+	} else if (attn_type == LPFC_ATT_LINK_DOWN ||
+		   attn_type == LPFC_ATT_UNEXP_WWPN) {
 		phba->fc_stat.LinkDown++;
 		if (phba->link_flag & LS_LOOPBACK_MODE)
 			lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
@@ -3388,6 +3393,14 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				"Data: x%x x%x x%x\n",
 				la->eventTag, phba->fc_eventTag,
 				phba->pport->port_state, vport->fc_flag);
+		else if (attn_type == LPFC_ATT_UNEXP_WWPN)
+			lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
+				"1313 Link Down UNEXP WWPN Event x%x received "
+				"Data: x%x x%x x%x x%x x%x\n",
+				la->eventTag, phba->fc_eventTag,
+				phba->pport->port_state, vport->fc_flag,
+				bf_get(lpfc_mbx_read_top_mm, la),
+				bf_get(lpfc_mbx_read_top_fa, la));
 		else
 			lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
 				"1305 Link Down Event x%x received "
@@ -3398,8 +3411,8 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				bf_get(lpfc_mbx_read_top_fa, la));
 		lpfc_mbx_issue_link_down(phba);
 	}
-	if ((phba->sli.sli_flag & LPFC_MENLO_MAINT) &&
-	    ((bf_get(lpfc_mbx_read_top_att_type, la) == LPFC_ATT_LINK_UP))) {
+	if (phba->sli.sli_flag & LPFC_MENLO_MAINT &&
+	    attn_type == LPFC_ATT_LINK_UP) {
 		if (phba->link_state != LPFC_LINK_DOWN) {
 			phba->fc_stat.LinkDown++;
 			lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
@@ -4020,9 +4033,11 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		rdata = rport->dd_data;
 		/* break the link before dropping the ref */
 		ndlp->rport = NULL;
-		if (rdata && rdata->pnode == ndlp)
-			lpfc_nlp_put(ndlp);
-		rdata->pnode = NULL;
+		if (rdata) {
+			if (rdata->pnode == ndlp)
+				lpfc_nlp_put(ndlp);
+			rdata->pnode = NULL;
+		}
 		/* drop reference for earlier registeration */
 		put_device(&rport->dev);
 	}
@@ -4133,7 +4148,6 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		       int old_state, int new_state)
 {
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
-	struct lpfc_hba *phba = vport->phba;
 
 	if (new_state == NLP_STE_UNMAPPED_NODE) {
 		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
@@ -4152,14 +4166,14 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			lpfc_unregister_remote_port(ndlp);
 		}
 
-		/* Notify the NVME transport of this rport's loss */
-		if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
-		     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) &&
-		    (vport->phba->nvmet_support == 0) &&
-		    ((ndlp->nlp_fc4_type & NLP_FC4_NVME) ||
-		    (ndlp->nlp_DID == Fabric_DID))) {
+		/* Notify the NVME transport of this rport's loss on the
+		 * Initiator.  For NVME Target, should upcall transport
+		 * in the else clause when API available.
+		 */
+		if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
 			vport->phba->nport_event_cnt++;
-			lpfc_nvme_unregister_port(vport, ndlp);
+			if (vport->phba->nvmet_support == 0)
+				lpfc_nvme_unregister_port(vport, ndlp);
 		}
 	}
 
@@ -4344,9 +4358,8 @@ lpfc_initialize_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	INIT_LIST_HEAD(&ndlp->els_retry_evt.evt_listp);
 	INIT_LIST_HEAD(&ndlp->dev_loss_evt.evt_listp);
-	init_timer(&ndlp->nlp_delayfunc);
-	ndlp->nlp_delayfunc.function = lpfc_els_retry_delay;
-	ndlp->nlp_delayfunc.data = (unsigned long)ndlp;
+	setup_timer(&ndlp->nlp_delayfunc, lpfc_els_retry_delay,
+			(unsigned long)ndlp);
 	ndlp->nlp_DID = did;
 	ndlp->vport = vport;
 	ndlp->phba = vport->phba;
@@ -4366,10 +4379,17 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	uint32_t did;
 	unsigned long flags;
 	unsigned long *active_rrqs_xri_bitmap = NULL;
+	int rpi = LPFC_RPI_ALLOC_ERROR;
 
 	if (!ndlp)
 		return NULL;
 
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		rpi = lpfc_sli4_alloc_rpi(vport->phba);
+		if (rpi == LPFC_RPI_ALLOC_ERROR)
+			return NULL;
+	}
+
 	spin_lock_irqsave(&phba->ndlp_lock, flags);
 	/* The ndlp should not be in memory free mode */
 	if (NLP_CHK_FREE_REQ(ndlp)) {
@@ -4379,7 +4399,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
 				kref_read(&ndlp->kref));
-		return NULL;
+		goto free_rpi;
 	}
 	/* The ndlp should not already be in active mode */
 	if (NLP_CHK_NODE_ACT(ndlp)) {
@@ -4389,7 +4409,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
 				kref_read(&ndlp->kref));
-		return NULL;
+		goto free_rpi;
 	}
 
 	/* Keep the original DID */
@@ -4407,7 +4427,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	spin_unlock_irqrestore(&phba->ndlp_lock, flags);
 	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
-		ndlp->nlp_rpi = lpfc_sli4_alloc_rpi(vport->phba);
+		ndlp->nlp_rpi = rpi;
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
 				 "0008 rpi:%x DID:%x flg:%x refcnt:%d "
 				 "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
@@ -4424,6 +4444,11 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		"node enable:       did:x%x",
 		ndlp->nlp_DID, 0, 0);
 	return ndlp;
+
+free_rpi:
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		lpfc_sli4_free_rpi(vport->phba, rpi);
+	return NULL;
 }
 
 void
@@ -4606,9 +4631,9 @@ lpfc_sli4_dequeue_nport_iocbs(struct lpfc_hba *phba,
 		pring = qp->pring;
 		if (!pring)
 			continue;
-		spin_lock_irq(&pring->ring_lock);
+		spin_lock(&pring->ring_lock);
 		__lpfc_dequeue_nport_iocbs(phba, ndlp, pring, dequeue_list);
-		spin_unlock_irq(&pring->ring_lock);
+		spin_unlock(&pring->ring_lock);
 	}
 	spin_unlock_irq(&phba->hbalock);
 }
@@ -5102,65 +5127,82 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 
 	ndlp = lpfc_findnode_did(vport, did);
 	if (!ndlp) {
+		if (vport->phba->nvmet_support)
+			return NULL;
 		if ((vport->fc_flag & FC_RSCN_MODE) != 0 &&
 		    lpfc_rscn_payload_check(vport, did) == 0)
 			return NULL;
-		ndlp = (struct lpfc_nodelist *)
-		     mempool_alloc(vport->phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, did);
 		if (!ndlp)
 			return NULL;
-		lpfc_nlp_init(vport, ndlp, did);
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-		if (vport->phba->nvmet_support)
-			return ndlp;
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
 		return ndlp;
 	} else if (!NLP_CHK_NODE_ACT(ndlp)) {
+		if (vport->phba->nvmet_support)
+			return NULL;
 		ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_NPR_NODE);
 		if (!ndlp)
 			return NULL;
-		if (vport->phba->nvmet_support)
-			return ndlp;
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
 		return ndlp;
 	}
 
+	/* The NVME Target does not want to actively manage an rport.
+	 * The goal is to allow the target to reset its state and clear
+	 * pending IO in preparation for the initiator to recover.
+	 */
 	if ((vport->fc_flag & FC_RSCN_MODE) &&
 	    !(vport->fc_flag & FC_NDISC_ACTIVE)) {
 		if (lpfc_rscn_payload_check(vport, did)) {
-			/* If we've already received a PLOGI from this NPort
-			 * we don't need to try to discover it again.
-			 */
-			if (ndlp->nlp_flag & NLP_RCV_PLOGI)
-				return NULL;
 
 			/* Since this node is marked for discovery,
 			 * delay timeout is not needed.
 			 */
 			lpfc_cancel_retry_delay_tmo(vport, ndlp);
+
+			/* NVME Target mode waits until rport is known to be
+			 * impacted by the RSCN before it transitions.  No
+			 * active management - just go to NPR provided the
+			 * node had a valid login.
+			 */
 			if (vport->phba->nvmet_support)
 				return ndlp;
+
+			/* If we've already received a PLOGI from this NPort
+			 * we don't need to try to discover it again.
+			 */
+			if (ndlp->nlp_flag & NLP_RCV_PLOGI)
+				return NULL;
+
 			spin_lock_irq(shost->host_lock);
 			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 			spin_unlock_irq(shost->host_lock);
 		} else
 			ndlp = NULL;
 	} else {
-		/* If we've already received a PLOGI from this NPort,
-		 * or we are already in the process of discovery on it,
-		 * we don't need to try to discover it again.
+		/* If the initiator received a PLOGI from this NPort or if the
+		 * initiator is already in the process of discovery on it,
+		 * there's no need to try to discover it again.
 		 */
 		if (ndlp->nlp_state == NLP_STE_ADISC_ISSUE ||
 		    ndlp->nlp_state == NLP_STE_PLOGI_ISSUE ||
-		    ndlp->nlp_flag & NLP_RCV_PLOGI)
+		    (!vport->phba->nvmet_support &&
+		     ndlp->nlp_flag & NLP_RCV_PLOGI))
 			return NULL;
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+
 		if (vport->phba->nvmet_support)
 			return ndlp;
+
+		/* Moving to NPR state clears unsolicited flags and
+		 * allows for rediscovery
+		 */
+		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
@@ -5885,16 +5927,31 @@ lpfc_find_vport_by_vpid(struct lpfc_hba *phba, uint16_t vpi)
 	return NULL;
 }
 
-void
-lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
-	      uint32_t did)
+struct lpfc_nodelist *
+lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did)
 {
+	struct lpfc_nodelist *ndlp;
+	int rpi = LPFC_RPI_ALLOC_ERROR;
+
+	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
+		rpi = lpfc_sli4_alloc_rpi(vport->phba);
+		if (rpi == LPFC_RPI_ALLOC_ERROR)
+			return NULL;
+	}
+
+	ndlp = mempool_alloc(vport->phba->nlp_mem_pool, GFP_KERNEL);
+	if (!ndlp) {
+		if (vport->phba->sli_rev == LPFC_SLI_REV4)
+			lpfc_sli4_free_rpi(vport->phba, rpi);
+		return NULL;
+	}
+
 	memset(ndlp, 0, sizeof (struct lpfc_nodelist));
 
 	lpfc_initialize_node(vport, ndlp, did);
 	INIT_LIST_HEAD(&ndlp->nlp_listp);
 	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
-		ndlp->nlp_rpi = lpfc_sli4_alloc_rpi(vport->phba);
+		ndlp->nlp_rpi = rpi;
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
 				 "0007 rpi:%x DID:%x flg:%x refcnt:%d "
 				 "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
@@ -5916,7 +5973,7 @@ lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		"node init:       did:x%x",
 		ndlp->nlp_DID, 0, 0);
 
-	return;
+	return ndlp;
 }
 
 /* This routine releases all resources associated with a specifc NPort's ndlp
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 15ca21484150..26a5647e057e 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -509,6 +509,8 @@ struct class_parms {
 	uint8_t word3Reserved2;	/* Fc Word 3, bit  0: 7 */
 };
 
+#define FAPWWN_KEY_VENDOR	0x42524344 /*valid vendor version fawwpn key*/
+
 struct serv_parm {	/* Structure is in Big Endian format */
 	struct csp cmn;
 	struct lpfc_name portName;
@@ -2885,6 +2887,7 @@ struct lpfc_mbx_read_top {
 #define LPFC_ATT_RESERVED    0x00	/* Reserved - attType */
 #define LPFC_ATT_LINK_UP     0x01	/* Link is up */
 #define LPFC_ATT_LINK_DOWN   0x02	/* Link is down */
+#define LPFC_ATT_UNEXP_WWPN  0x06	/* Link is down Unexpected WWWPN */
 	uint32_t word3;
 #define lpfc_mbx_read_top_alpa_granted_SHIFT	24
 #define lpfc_mbx_read_top_alpa_granted_MASK	0x000000FF
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index cfdb068a3bfc..1d12f2be36bc 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1001,7 +1001,7 @@ struct eq_delay_info {
 	uint32_t phase;
 	uint32_t delay_multi;
 };
-#define	LPFC_MAX_EQ_DELAY	8
+#define	LPFC_MAX_EQ_DELAY_EQID_CNT	8
 
 struct sgl_page_pairs {
 	uint32_t sgl_pg0_addr_lo;
@@ -1070,7 +1070,7 @@ struct lpfc_mbx_modify_eq_delay {
 	union {
 		struct {
 			uint32_t num_eq;
-			struct eq_delay_info eq[LPFC_MAX_EQ_DELAY];
+			struct eq_delay_info eq[LPFC_MAX_EQ_DELAY_EQID_CNT];
 		} request;
 		struct {
 			uint32_t word0;
@@ -2720,6 +2720,9 @@ struct lpfc_mbx_request_features {
 #define lpfc_mbx_rq_ftr_rq_ifip_SHIFT		7
 #define lpfc_mbx_rq_ftr_rq_ifip_MASK		0x00000001
 #define lpfc_mbx_rq_ftr_rq_ifip_WORD		word2
+#define lpfc_mbx_rq_ftr_rq_iaar_SHIFT		9
+#define lpfc_mbx_rq_ftr_rq_iaar_MASK		0x00000001
+#define lpfc_mbx_rq_ftr_rq_iaar_WORD		word2
 #define lpfc_mbx_rq_ftr_rq_perfh_SHIFT		11
 #define lpfc_mbx_rq_ftr_rq_perfh_MASK		0x00000001
 #define lpfc_mbx_rq_ftr_rq_perfh_WORD		word2
@@ -3853,6 +3856,7 @@ struct lpfc_acqe_fc_la {
 #define LPFC_FC_LA_TYPE_NO_HARD_ALPA	0x3
 #define LPFC_FC_LA_TYPE_MDS_LINK_DOWN	0x4
 #define LPFC_FC_LA_TYPE_MDS_LOOPBACK	0x5
+#define LPFC_FC_LA_TYPE_UNEXP_WWPN	0x6
 #define lpfc_acqe_fc_la_port_type_SHIFT		6
 #define lpfc_acqe_fc_la_port_type_MASK		0x00000003
 #define lpfc_acqe_fc_la_port_type_WORD		word0
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 0ee429d773f3..90ae354a9c45 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -42,6 +42,10 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/scsi_tcq.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <linux/nvme-fc-driver.h>
 
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
@@ -52,6 +56,7 @@
 #include "lpfc.h"
 #include "lpfc_scsi.h"
 #include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -335,6 +340,9 @@ lpfc_dump_wakeup_param_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 void
 lpfc_update_vport_wwn(struct lpfc_vport *vport)
 {
+	uint8_t vvvl = vport->fc_sparam.cmn.valid_vendor_ver_level;
+	u32 *fawwpn_key = (u32 *)&vport->fc_sparam.un.vendorVersion[0];
+
 	/* If the soft name exists then update it using the service params */
 	if (vport->phba->cfg_soft_wwnn)
 		u64_to_wwn(vport->phba->cfg_soft_wwnn,
@@ -354,9 +362,25 @@ lpfc_update_vport_wwn(struct lpfc_vport *vport)
 		memcpy(&vport->fc_sparam.nodeName, &vport->fc_nodename,
 			sizeof(struct lpfc_name));
 
-	if (vport->fc_portname.u.wwn[0] == 0 || vport->phba->cfg_soft_wwpn)
+	/*
+	 * If the port name has changed, then set the Param changes flag
+	 * to unreg the login
+	 */
+	if (vport->fc_portname.u.wwn[0] != 0 &&
+		memcmp(&vport->fc_portname, &vport->fc_sparam.portName,
+			sizeof(struct lpfc_name)))
+		vport->vport_flag |= FAWWPN_PARAM_CHG;
+
+	if (vport->fc_portname.u.wwn[0] == 0 ||
+	    vport->phba->cfg_soft_wwpn ||
+	    (vvvl == 1 && cpu_to_be32(*fawwpn_key) == FAPWWN_KEY_VENDOR) ||
+	    vport->vport_flag & FAWWPN_SET) {
 		memcpy(&vport->fc_portname, &vport->fc_sparam.portName,
 			sizeof(struct lpfc_name));
+		vport->vport_flag &= ~FAWWPN_SET;
+		if (vvvl == 1 && cpu_to_be32(*fawwpn_key) == FAPWWN_KEY_VENDOR)
+			vport->vport_flag |= FAWWPN_SET;
+	}
 	else
 		memcpy(&vport->fc_sparam.portName, &vport->fc_portname,
 			sizeof(struct lpfc_name));
@@ -1003,8 +1027,10 @@ static int
 lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 {
 	struct lpfc_scsi_buf *psb, *psb_next;
+	struct lpfc_nvmet_rcv_ctx *ctxp, *ctxp_next;
 	LIST_HEAD(aborts);
 	LIST_HEAD(nvme_aborts);
+	LIST_HEAD(nvmet_aborts);
 	unsigned long iflag = 0;
 	struct lpfc_sglq *sglq_entry = NULL;
 
@@ -1027,16 +1053,10 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 	list_for_each_entry(sglq_entry,
 		&phba->sli4_hba.lpfc_abts_els_sgl_list, list)
 		sglq_entry->state = SGL_FREED;
-	list_for_each_entry(sglq_entry,
-		&phba->sli4_hba.lpfc_abts_nvmet_sgl_list, list)
-		sglq_entry->state = SGL_FREED;
 
 	list_splice_init(&phba->sli4_hba.lpfc_abts_els_sgl_list,
 			&phba->sli4_hba.lpfc_els_sgl_list);
 
-	if (phba->sli4_hba.nvme_wq)
-		list_splice_init(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list,
-				 &phba->sli4_hba.lpfc_nvmet_sgl_list);
 
 	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	/* abts_scsi_buf_list_lock required because worker thread uses this
@@ -1053,6 +1073,8 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 		spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		list_splice_init(&phba->sli4_hba.lpfc_abts_nvme_buf_list,
 				 &nvme_aborts);
+		list_splice_init(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+				 &nvmet_aborts);
 		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 	}
 
@@ -1066,13 +1088,20 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 	list_splice(&aborts, &phba->lpfc_scsi_buf_list_put);
 	spin_unlock_irqrestore(&phba->scsi_buf_list_put_lock, iflag);
 
-	list_for_each_entry_safe(psb, psb_next, &nvme_aborts, list) {
-		psb->pCmd = NULL;
-		psb->status = IOSTAT_SUCCESS;
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		list_for_each_entry_safe(psb, psb_next, &nvme_aborts, list) {
+			psb->pCmd = NULL;
+			psb->status = IOSTAT_SUCCESS;
+		}
+		spin_lock_irqsave(&phba->nvme_buf_list_put_lock, iflag);
+		list_splice(&nvme_aborts, &phba->lpfc_nvme_buf_list_put);
+		spin_unlock_irqrestore(&phba->nvme_buf_list_put_lock, iflag);
+
+		list_for_each_entry_safe(ctxp, ctxp_next, &nvmet_aborts, list) {
+			ctxp->flag &= ~(LPFC_NVMET_XBUSY | LPFC_NVMET_ABORT_OP);
+			lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+		}
 	}
-	spin_lock_irqsave(&phba->nvme_buf_list_put_lock, iflag);
-	list_splice(&nvme_aborts, &phba->lpfc_nvme_buf_list_put);
-	spin_unlock_irqrestore(&phba->nvme_buf_list_put_lock, iflag);
 
 	lpfc_sli4_free_sp_events(phba);
 	return 0;
@@ -2874,34 +2903,38 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba)
 {
 	struct lpfc_nodelist  *ndlp, *next_ndlp;
 	struct lpfc_vport **vports;
-	int i;
+	int i, rpi;
+	unsigned long flags;
 
 	if (phba->sli_rev != LPFC_SLI_REV4)
 		return;
 
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports != NULL) {
-		for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
-			if (vports[i]->load_flag & FC_UNLOADING)
-				continue;
+	if (vports == NULL)
+		return;
 
-			list_for_each_entry_safe(ndlp, next_ndlp,
-						 &vports[i]->fc_nodes,
-						 nlp_listp) {
-				if (NLP_CHK_NODE_ACT(ndlp)) {
-					ndlp->nlp_rpi =
-						lpfc_sli4_alloc_rpi(phba);
-					lpfc_printf_vlog(ndlp->vport, KERN_INFO,
-							 LOG_NODE,
-							 "0009 rpi:%x DID:%x "
-							 "flg:%x map:%x %p\n",
-							 ndlp->nlp_rpi,
-							 ndlp->nlp_DID,
-							 ndlp->nlp_flag,
-							 ndlp->nlp_usg_map,
-							 ndlp);
-				}
+	for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
+		if (vports[i]->load_flag & FC_UNLOADING)
+			continue;
+
+		list_for_each_entry_safe(ndlp, next_ndlp,
+					 &vports[i]->fc_nodes,
+					 nlp_listp) {
+			if (!NLP_CHK_NODE_ACT(ndlp))
+				continue;
+			rpi = lpfc_sli4_alloc_rpi(phba);
+			if (rpi == LPFC_RPI_ALLOC_ERROR) {
+				spin_lock_irqsave(&phba->ndlp_lock, flags);
+				NLP_CLR_NODE_ACT(ndlp);
+				spin_unlock_irqrestore(&phba->ndlp_lock, flags);
+				continue;
 			}
+			ndlp->nlp_rpi = rpi;
+			lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
+					 "0009 rpi:%x DID:%x "
+					 "flg:%x map:%x %p\n", ndlp->nlp_rpi,
+					 ndlp->nlp_DID, ndlp->nlp_flag,
+					 ndlp->nlp_usg_map, ndlp);
 		}
 	}
 	lpfc_destroy_vport_work_array(phba, vports);
@@ -3508,6 +3541,12 @@ lpfc_sli4_scsi_sgl_update(struct lpfc_hba *phba)
 	spin_unlock(&phba->scsi_buf_list_put_lock);
 	spin_unlock_irq(&phba->scsi_buf_list_get_lock);
 
+	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+			"6060 Current allocated SCSI xri-sgl count:%d, "
+			"maximum  SCSI xri count:%d (split:%d)\n",
+			phba->sli4_hba.scsi_xri_cnt,
+			phba->sli4_hba.scsi_xri_max, phba->cfg_xri_split);
+
 	if (phba->sli4_hba.scsi_xri_cnt > phba->sli4_hba.scsi_xri_max) {
 		/* max scsi xri shrinked below the allocated scsi buffers */
 		scsi_xri_cnt = phba->sli4_hba.scsi_xri_cnt -
@@ -3555,6 +3594,44 @@ out_free_mem:
 	return rc;
 }
 
+static uint64_t
+lpfc_get_wwpn(struct lpfc_hba *phba)
+{
+	uint64_t wwn;
+	int rc;
+	LPFC_MBOXQ_t *mboxq;
+	MAILBOX_t *mb;
+
+
+	mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool,
+						GFP_KERNEL);
+	if (!mboxq)
+		return (uint64_t)-1;
+
+	/* First get WWN of HBA instance */
+	lpfc_read_nv(phba, mboxq);
+	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+	if (rc != MBX_SUCCESS) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"6019 Mailbox failed , mbxCmd x%x "
+				"READ_NV, mbxStatus x%x\n",
+				bf_get(lpfc_mqe_command, &mboxq->u.mqe),
+				bf_get(lpfc_mqe_status, &mboxq->u.mqe));
+		mempool_free(mboxq, phba->mbox_mem_pool);
+		return (uint64_t) -1;
+	}
+	mb = &mboxq->u.mb;
+	memcpy(&wwn, (char *)mb->un.varRDnvp.portname, sizeof(uint64_t));
+	/* wwn is WWPN of HBA instance */
+	mempool_free(mboxq, phba->mbox_mem_pool);
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return be64_to_cpu(wwn);
+	else
+		return (((wwn & 0xffffffff00000000) >> 32) |
+			((wwn & 0x00000000ffffffff) << 32));
+
+}
+
 /**
  * lpfc_sli4_nvme_sgl_update - update xri-sgl sizing and mapping
  * @phba: pointer to lpfc hba data structure.
@@ -3676,17 +3753,32 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
 	struct lpfc_vport *vport;
 	struct Scsi_Host  *shost = NULL;
 	int error = 0;
+	int i;
+	uint64_t wwn;
+	bool use_no_reset_hba = false;
+
+	wwn = lpfc_get_wwpn(phba);
+
+	for (i = 0; i < lpfc_no_hba_reset_cnt; i++) {
+		if (wwn == lpfc_no_hba_reset[i]) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"6020 Setting use_no_reset port=%llx\n",
+					wwn);
+			use_no_reset_hba = true;
+			break;
+		}
+	}
 
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
 		if (dev != &phba->pcidev->dev) {
 			shost = scsi_host_alloc(&lpfc_vport_template,
 						sizeof(struct lpfc_vport));
 		} else {
-			if (phba->sli_rev == LPFC_SLI_REV4)
+			if (!use_no_reset_hba)
 				shost = scsi_host_alloc(&lpfc_template,
 						sizeof(struct lpfc_vport));
 			else
-				shost = scsi_host_alloc(&lpfc_template_s3,
+				shost = scsi_host_alloc(&lpfc_template_no_hr,
 						sizeof(struct lpfc_vport));
 		}
 	} else if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
@@ -3734,17 +3826,14 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
 	INIT_LIST_HEAD(&vport->rcv_buffer_list);
 	spin_lock_init(&vport->work_port_lock);
 
-	init_timer(&vport->fc_disctmo);
-	vport->fc_disctmo.function = lpfc_disc_timeout;
-	vport->fc_disctmo.data = (unsigned long)vport;
+	setup_timer(&vport->fc_disctmo, lpfc_disc_timeout,
+			(unsigned long)vport);
 
-	init_timer(&vport->els_tmofunc);
-	vport->els_tmofunc.function = lpfc_els_timeout;
-	vport->els_tmofunc.data = (unsigned long)vport;
+	setup_timer(&vport->els_tmofunc, lpfc_els_timeout,
+			(unsigned long)vport);
 
-	init_timer(&vport->delayed_disc_tmo);
-	vport->delayed_disc_tmo.function = lpfc_delayed_disc_tmo;
-	vport->delayed_disc_tmo.data = (unsigned long)vport;
+	setup_timer(&vport->delayed_disc_tmo, lpfc_delayed_disc_tmo,
+			(unsigned long)vport);
 
 	error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev);
 	if (error)
@@ -4458,9 +4547,15 @@ lpfc_sli4_async_fc_evt(struct lpfc_hba *phba, struct lpfc_acqe_fc_la *acqe_fc)
 		/* Parse and translate link attention fields */
 		la = (struct lpfc_mbx_read_top *)&pmb->u.mb.un.varReadTop;
 		la->eventTag = acqe_fc->event_tag;
-		bf_set(lpfc_mbx_read_top_att_type, la,
-		       LPFC_FC_LA_TYPE_LINK_DOWN);
 
+		if (phba->sli4_hba.link_state.status ==
+		    LPFC_FC_LA_TYPE_UNEXP_WWPN) {
+			bf_set(lpfc_mbx_read_top_att_type, la,
+			       LPFC_FC_LA_TYPE_UNEXP_WWPN);
+		} else {
+			bf_set(lpfc_mbx_read_top_att_type, la,
+			       LPFC_FC_LA_TYPE_LINK_DOWN);
+		}
 		/* Invoke the mailbox command callback function */
 		lpfc_mbx_cmpl_read_topology(phba, pmb);
 
@@ -4666,10 +4761,9 @@ lpfc_sli4_perform_vport_cvl(struct lpfc_vport *vport)
 	ndlp = lpfc_findnode_did(vport, Fabric_DID);
 	if (!ndlp) {
 		/* Cannot find existing Fabric ndlp, so allocate a new one */
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, Fabric_DID);
 		if (!ndlp)
 			return 0;
-		lpfc_nlp_init(vport, ndlp, Fabric_DID);
 		/* Set the node type */
 		ndlp->nlp_type |= NLP_FABRIC;
 		/* Put ndlp onto node list */
@@ -5406,21 +5500,15 @@ lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba)
 	INIT_LIST_HEAD(&phba->luns);
 
 	/* MBOX heartbeat timer */
-	init_timer(&psli->mbox_tmo);
-	psli->mbox_tmo.function = lpfc_mbox_timeout;
-	psli->mbox_tmo.data = (unsigned long) phba;
+	setup_timer(&psli->mbox_tmo, lpfc_mbox_timeout, (unsigned long)phba);
 	/* Fabric block timer */
-	init_timer(&phba->fabric_block_timer);
-	phba->fabric_block_timer.function = lpfc_fabric_block_timeout;
-	phba->fabric_block_timer.data = (unsigned long) phba;
+	setup_timer(&phba->fabric_block_timer, lpfc_fabric_block_timeout,
+			(unsigned long)phba);
 	/* EA polling mode timer */
-	init_timer(&phba->eratt_poll);
-	phba->eratt_poll.function = lpfc_poll_eratt;
-	phba->eratt_poll.data = (unsigned long) phba;
+	setup_timer(&phba->eratt_poll, lpfc_poll_eratt,
+			(unsigned long)phba);
 	/* Heartbeat timer */
-	init_timer(&phba->hb_tmofunc);
-	phba->hb_tmofunc.function = lpfc_hb_timeout;
-	phba->hb_tmofunc.data = (unsigned long)phba;
+	setup_timer(&phba->hb_tmofunc, lpfc_hb_timeout, (unsigned long)phba);
 
 	return 0;
 }
@@ -5446,9 +5534,8 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 	 */
 
 	/* FCP polling mode timer */
-	init_timer(&phba->fcp_poll_timer);
-	phba->fcp_poll_timer.function = lpfc_poll_timeout;
-	phba->fcp_poll_timer.data = (unsigned long) phba;
+	setup_timer(&phba->fcp_poll_timer, lpfc_poll_timeout,
+			(unsigned long)phba);
 
 	/* Host attention work mask setup */
 	phba->work_ha_mask = (HA_ERATT | HA_MBATT | HA_LATT);
@@ -5482,7 +5569,8 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 
 	/* Initialize the host templates the configured values. */
 	lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt;
-	lpfc_template_s3.sg_tablesize = phba->cfg_sg_seg_cnt;
+	lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt;
+	lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt;
 
 	/* There are going to be 2 reserved BDEs: 1 FCP cmnd + 1 FCP rsp */
 	if (phba->cfg_enable_bg) {
@@ -5617,14 +5705,11 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	 * Initialize timers used by driver
 	 */
 
-	init_timer(&phba->rrq_tmr);
-	phba->rrq_tmr.function = lpfc_rrq_timeout;
-	phba->rrq_tmr.data = (unsigned long)phba;
+	setup_timer(&phba->rrq_tmr, lpfc_rrq_timeout, (unsigned long)phba);
 
 	/* FCF rediscover timer */
-	init_timer(&phba->fcf.redisc_wait);
-	phba->fcf.redisc_wait.function = lpfc_sli4_fcf_redisc_wait_tmo;
-	phba->fcf.redisc_wait.data = (unsigned long)phba;
+	setup_timer(&phba->fcf.redisc_wait, lpfc_sli4_fcf_redisc_wait_tmo,
+			(unsigned long)phba);
 
 	/*
 	 * Control structure for handling external multi-buffer mailbox
@@ -5706,6 +5791,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* Initialize the host templates with the updated values. */
 	lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt;
 	lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt;
+	lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt;
 
 	if (phba->cfg_sg_dma_buf_size  <= LPFC_MIN_SG_SLI4_BUF_SZ)
 		phba->cfg_sg_dma_buf_size = LPFC_MIN_SG_SLI4_BUF_SZ;
@@ -5736,6 +5822,9 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		/* Initialize the Abort nvme buffer list used by driver */
 		spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+		/* Fast-path XRI aborted CQ Event work queue list */
+		INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
 	}
 
 	/* This abort list used by worker thread */
@@ -5765,6 +5854,12 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_vfi_blk_list);
 	INIT_LIST_HEAD(&phba->lpfc_vpi_blk_list);
 
+	/* Initialize mboxq lists. If the early init routines fail
+	 * these lists need to be correctly initialized.
+	 */
+	INIT_LIST_HEAD(&phba->sli.mboxq);
+	INIT_LIST_HEAD(&phba->sli.mboxq_cmpl);
+
 	/* initialize optic_state to 0xFF */
 	phba->sli4_hba.lnk_info.optic_state = 0xff;
 
@@ -5830,6 +5925,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 					"READ_NV, mbxStatus x%x\n",
 					bf_get(lpfc_mqe_command, &mboxq->u.mqe),
 					bf_get(lpfc_mqe_status, &mboxq->u.mqe));
+			mempool_free(mboxq, phba->mbox_mem_pool);
 			rc = -EIO;
 			goto out_free_bsmbx;
 		}
@@ -5847,10 +5943,17 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		/* Check to see if it matches any module parameter */
 		for (i = 0; i < lpfc_enable_nvmet_cnt; i++) {
 			if (wwn == lpfc_enable_nvmet[i]) {
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6017 NVME Target %016llx\n",
 						wwn);
 				phba->nvmet_support = 1; /* a match */
+#else
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6021 Can't enable NVME Target."
+						" NVME_TARGET_FC infrastructure"
+						" is not in kernel\n");
+#endif
 			}
 		}
 	}
@@ -6347,7 +6450,7 @@ lpfc_init_sgl_list(struct lpfc_hba *phba)
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_els_sgl_list);
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_els_sgl_list);
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_sgl_list);
-	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
 
 	/* els xri-sgl book keeping */
 	phba->sli4_hba.els_xri_cnt = 0;
@@ -7748,7 +7851,7 @@ lpfc_alloc_fcp_wq_cq(struct lpfc_hba *phba, int wqidx)
 
 	/* Create Fast Path FCP WQs */
 	wqesize = (phba->fcp_embed_io) ?
-				LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
+		LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
 	qdesc = lpfc_sli4_queue_alloc(phba, wqesize, phba->sli4_hba.wq_ecount);
 	if (!qdesc) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -7779,7 +7882,7 @@ int
 lpfc_sli4_queue_create(struct lpfc_hba *phba)
 {
 	struct lpfc_queue *qdesc;
-	int idx, io_channel, max;
+	int idx, io_channel;
 
 	/*
 	 * Create HBA Record arrays.
@@ -7940,15 +8043,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 		if (lpfc_alloc_nvme_wq_cq(phba, idx))
 			goto out_error;
 
-	/* allocate MRQ CQs */
-	max = phba->cfg_nvme_io_channel;
-	if (max < phba->cfg_nvmet_mrq)
-		max = phba->cfg_nvmet_mrq;
-
-	for (idx = 0; idx < max; idx++)
-		if (lpfc_alloc_nvme_wq_cq(phba, idx))
-			goto out_error;
-
 	if (phba->nvmet_support) {
 		for (idx = 0; idx < phba->cfg_nvmet_mrq; idx++) {
 			qdesc = lpfc_sli4_queue_alloc(phba,
@@ -8170,11 +8264,11 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 
 	/* Release FCP cqs */
 	lpfc_sli4_release_queues(&phba->sli4_hba.fcp_cq,
-					phba->cfg_fcp_io_channel);
+				 phba->cfg_fcp_io_channel);
 
 	/* Release FCP wqs */
 	lpfc_sli4_release_queues(&phba->sli4_hba.fcp_wq,
-					phba->cfg_fcp_io_channel);
+				 phba->cfg_fcp_io_channel);
 
 	/* Release FCP CQ mapping array */
 	lpfc_sli4_release_queue_map(&phba->sli4_hba.fcp_cq_map);
@@ -8520,15 +8614,15 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"0528 %s not allocated\n",
 				phba->sli4_hba.mbx_cq ?
-						"Mailbox WQ" : "Mailbox CQ");
+				"Mailbox WQ" : "Mailbox CQ");
 		rc = -ENOMEM;
 		goto out_destroy;
 	}
 
 	rc = lpfc_create_wq_cq(phba, phba->sli4_hba.hba_eq[0],
-					phba->sli4_hba.mbx_cq,
-					phba->sli4_hba.mbx_wq,
-					NULL, 0, LPFC_MBOX);
+			       phba->sli4_hba.mbx_cq,
+			       phba->sli4_hba.mbx_wq,
+			       NULL, 0, LPFC_MBOX);
 	if (rc) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			"0529 Failed setup of mailbox WQ/CQ: rc = 0x%x\n",
@@ -8712,12 +8806,9 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 		}
 	}
 
-	/*
-	 * Configure EQ delay multipier for interrupt coalescing using
-	 * MODIFY_EQ_DELAY for all EQs created, LPFC_MAX_EQ_DELAY at a time.
-	 */
-	for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY)
+	for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY_EQID_CNT)
 		lpfc_modify_hba_eq_delay(phba, qidx);
+
 	return 0;
 
 out_destroy:
@@ -8973,6 +9064,11 @@ lpfc_sli4_cq_event_release_all(struct lpfc_hba *phba)
 	/* Pending ELS XRI abort events */
 	list_splice_init(&phba->sli4_hba.sp_els_xri_aborted_work_queue,
 			 &cqelist);
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		/* Pending NVME XRI abort events */
+		list_splice_init(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue,
+				 &cqelist);
+	}
 	/* Pending asynnc events */
 	list_splice_init(&phba->sli4_hba.sp_asynce_work_queue,
 			 &cqelist);
@@ -9881,17 +9977,19 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 {
 	int wait_time = 0;
 	int nvme_xri_cmpl = 1;
+	int nvmet_xri_cmpl = 1;
 	int fcp_xri_cmpl = 1;
 	int els_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
-	int nvmet_xri_cmpl =
-			list_empty(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
 
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
 		fcp_xri_cmpl =
 			list_empty(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
-	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
 		nvme_xri_cmpl =
 			list_empty(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+		nvmet_xri_cmpl =
+			list_empty(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+	}
 
 	while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl ||
 	       !nvmet_xri_cmpl) {
@@ -9917,9 +10015,12 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 			msleep(LPFC_XRI_EXCH_BUSY_WAIT_T1);
 			wait_time += LPFC_XRI_EXCH_BUSY_WAIT_T1;
 		}
-		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
 			nvme_xri_cmpl = list_empty(
 				&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+			nvmet_xri_cmpl = list_empty(
+				&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+		}
 
 		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
 			fcp_xri_cmpl = list_empty(
@@ -9928,8 +10029,6 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 		els_xri_cmpl =
 			list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
 
-		nvmet_xri_cmpl =
-			list_empty(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
 	}
 }
 
@@ -9995,9 +10094,14 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)
 	/* Stop kthread signal shall trigger work_done one more time */
 	kthread_stop(phba->worker_thread);
 
+	/* Unset the queues shared with the hardware then release all
+	 * allocated resources.
+	 */
+	lpfc_sli4_queue_unset(phba);
+	lpfc_sli4_queue_destroy(phba);
+
 	/* Reset SLI4 HBA FCoE function */
 	lpfc_pci_function_reset(phba);
-	lpfc_sli4_queue_destroy(phba);
 
 	/* Stop the SLI4 device port */
 	phba->pport->work_port_events = 0;
@@ -10253,6 +10357,7 @@ lpfc_pci_probe_one_s3(struct pci_dev *pdev, const struct pci_device_id *pid)
 	}
 
 	/* Initialize and populate the iocb list per host */
+
 	error = lpfc_init_iocb_list(phba, LPFC_IOCB_LIST_CNT);
 	if (error) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -10400,12 +10505,7 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev)
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
 
-	/* Perform ndlp cleanup on the physical port.  The nvme and nvmet
-	 * localports are destroyed after to cleanup all transport memory.
-	 */
 	lpfc_cleanup(vport);
-	lpfc_nvmet_destroy_targetport(phba);
-	lpfc_nvme_destroy_localport(vport);
 
 	/*
 	 * Bring down the SLI Layer. This step disable all interrupts,
@@ -11003,7 +11103,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	struct lpfc_hba   *phba;
 	struct lpfc_vport *vport = NULL;
 	struct Scsi_Host  *shost = NULL;
-	int error;
+	int error, cnt;
 	uint32_t cfg_mode, intr_mode;
 
 	/* Allocate memory for HBA structure */
@@ -11037,12 +11137,15 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 		goto out_unset_pci_mem_s4;
 	}
 
-	/* Initialize and populate the iocb list per host */
+	cnt = phba->cfg_iocb_cnt * 1024;
+	if (phba->nvmet_support)
+		cnt += phba->cfg_nvmet_mrq_post * phba->cfg_nvmet_mrq;
 
+	/* Initialize and populate the iocb list per host */
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"2821 initialize iocb list %d.\n",
-			phba->cfg_iocb_cnt*1024);
-	error = lpfc_init_iocb_list(phba, phba->cfg_iocb_cnt*1024);
+			"2821 initialize iocb list %d total %d\n",
+			phba->cfg_iocb_cnt, cnt);
+	error = lpfc_init_iocb_list(phba, cnt);
 
 	if (error) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -11129,7 +11232,9 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	if ((phba->nvmet_support == 0) &&
 	    (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
 		/* Create NVME binding with nvme_fc_transport. This
-		 * ensures the vport is initialized.
+		 * ensures the vport is initialized.  If the localport
+		 * create fails, it should not unload the driver to
+		 * support field issues.
 		 */
 		error = lpfc_nvme_create_localport(vport);
 		if (error) {
@@ -11137,7 +11242,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 					"6004 NVME registration failed, "
 					"error x%x\n",
 					error);
-			goto out_disable_intr;
 		}
 	}
 
@@ -11936,6 +12040,7 @@ int
 lpfc_fof_queue_create(struct lpfc_hba *phba)
 {
 	struct lpfc_queue *qdesc;
+	uint32_t wqesize;
 
 	/* Create FOF EQ */
 	qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.eq_esize,
@@ -11956,8 +12061,11 @@ lpfc_fof_queue_create(struct lpfc_hba *phba)
 		phba->sli4_hba.oas_cq = qdesc;
 
 		/* Create OAS WQ */
-		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.wq_esize,
+		wqesize = (phba->fcp_embed_io) ?
+				LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
+		qdesc = lpfc_sli4_queue_alloc(phba, wqesize,
 					      phba->sli4_hba.wq_ecount);
+
 		if (!qdesc)
 			goto out_error;
 
@@ -12018,6 +12126,7 @@ static struct pci_driver lpfc_driver = {
 	.id_table	= lpfc_id_table,
 	.probe		= lpfc_pci_probe_one,
 	.remove		= lpfc_pci_remove_one,
+	.shutdown	= lpfc_pci_remove_one,
 	.suspend        = lpfc_pci_suspend_one,
 	.resume		= lpfc_pci_resume_one,
 	.err_handler    = &lpfc_err_handler,
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index a928f5187fa4..ce25a18367b5 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2083,9 +2083,12 @@ lpfc_request_features(struct lpfc_hba *phba, struct lpfcMboxq *mboxq)
 	if (phba->max_vpi && phba->cfg_enable_npiv)
 		bf_set(lpfc_mbx_rq_ftr_rq_npiv, &mboxq->u.mqe.un.req_ftrs, 1);
 
-	if (phba->nvmet_support)
+	if (phba->nvmet_support) {
 		bf_set(lpfc_mbx_rq_ftr_rq_mrqp, &mboxq->u.mqe.un.req_ftrs, 1);
-
+		/* iaab/iaar NOT set for now */
+		 bf_set(lpfc_mbx_rq_ftr_rq_iaab, &mboxq->u.mqe.un.req_ftrs, 0);
+		 bf_set(lpfc_mbx_rq_ftr_rq_iaar, &mboxq->u.mqe.un.req_ftrs, 0);
+	}
 	return;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index c61d8d692ede..5986c7957199 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -646,7 +646,6 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
 	}
 
 	dma_buf->iocbq = lpfc_sli_get_iocbq(phba);
-	dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
 	if (!dma_buf->iocbq) {
 		kfree(dma_buf->context);
 		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
@@ -658,6 +657,7 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
 				"2621 Ran out of nvmet iocb/WQEs\n");
 		return NULL;
 	}
+	dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
 	nvmewqe = dma_buf->iocbq;
 	wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
 	/* Initialize WQE */
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 061626bdf701..8777c2d5f50d 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -361,8 +361,12 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	case  NLP_STE_PRLI_ISSUE:
 	case  NLP_STE_UNMAPPED_NODE:
 	case  NLP_STE_MAPPED_NODE:
-		/* lpfc_plogi_confirm_nport skips fabric did, handle it here */
-		if (!(ndlp->nlp_type & NLP_FABRIC)) {
+		/* For initiators, lpfc_plogi_confirm_nport skips fabric did.
+		 * For target mode, execute implicit logo.
+		 * Fabric nodes go into NPR.
+		 */
+		if (!(ndlp->nlp_type & NLP_FABRIC) &&
+		    !(phba->nvmet_support)) {
 			lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb,
 					 ndlp, NULL);
 			return 1;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 609a908ea9db..8008c8205fb6 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -316,7 +316,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 	bf_set(wqe_dfctl, &wqe->gen_req.wge_ctl, 0);
 	bf_set(wqe_si, &wqe->gen_req.wge_ctl, 1);
 	bf_set(wqe_la, &wqe->gen_req.wge_ctl, 1);
-	bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_DD_UNSOL_CTL);
+	bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_ELS4_REQ);
 	bf_set(wqe_type, &wqe->gen_req.wge_ctl, FC_TYPE_NVME);
 
 	/* Word 6 */
@@ -401,6 +401,7 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 	struct lpfc_nodelist *ndlp;
 	struct ulp_bde64 *bpl;
 	struct lpfc_dmabuf *bmp;
+	uint16_t ntype, nstate;
 
 	/* there are two dma buf in the request, actually there is one and
 	 * the second one is just the start address + cmd size.
@@ -417,11 +418,26 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 	vport = lport->vport;
 
 	ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
-	if (!ndlp) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
-				 "6043 Could not find node for DID %x\n",
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+				 "6051 DID x%06x not an active rport.\n",
 				 pnvme_rport->port_id);
-		return 1;
+		return -ENODEV;
+	}
+
+	/* The remote node has to be a mapped nvme target or an
+	 * unmapped nvme initiator or it's an error.
+	 */
+	ntype = ndlp->nlp_type;
+	nstate = ndlp->nlp_state;
+	if ((ntype & NLP_NVME_TARGET && nstate != NLP_STE_MAPPED_NODE) ||
+	    (ntype & NLP_NVME_INITIATOR && nstate != NLP_STE_UNMAPPED_NODE)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+				 "6088 DID x%06x not ready for "
+				 "IO. State x%x, Type x%x\n",
+				 pnvme_rport->port_id,
+				 ndlp->nlp_state, ndlp->nlp_type);
+		return -ENODEV;
 	}
 	bmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
 	if (!bmp) {
@@ -456,7 +472,7 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 
 	/* Expand print to include key fields. */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
-			 "6051 ENTER.  lport %p, rport %p lsreq%p rqstlen:%d "
+			 "6149 ENTER.  lport %p, rport %p lsreq%p rqstlen:%d "
 			 "rsplen:%d %pad %pad\n",
 			 pnvme_lport, pnvme_rport,
 			 pnvme_lsreq, pnvme_lsreq->rqstlen,
@@ -620,15 +636,15 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport,
 	 * Embed the payload in the last half of the WQE
 	 * WQE words 16-30 get the NVME CMD IU payload
 	 *
-	 * WQE Word 16 is already setup with flags
-	 * WQE words 17-19 get payload Words 2-4
+	 * WQE words 16-19 get payload Words 1-4
 	 * WQE words 20-21 get payload Words 6-7
 	 * WQE words 22-29 get payload Words 16-23
 	 */
-	wptr = &wqe->words[17];  /* WQE ptr */
+	wptr = &wqe->words[16];  /* WQE ptr */
 	dptr = (uint32_t *)nCmd->cmdaddr;  /* payload ptr */
-	dptr += 2;		/* Skip Words 0-1 in payload */
+	dptr++;			/* Skip Word 0 in payload */
 
+	*wptr++ = *dptr++;	/* Word 1 */
 	*wptr++ = *dptr++;	/* Word 2 */
 	*wptr++ = *dptr++;	/* Word 3 */
 	*wptr++ = *dptr++;	/* Word 4 */
@@ -745,6 +761,7 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	struct nvme_fc_cmd_iu *cp;
 	struct lpfc_nvme_rport *rport;
 	struct lpfc_nodelist *ndlp;
+	struct lpfc_nvme_fcpreq_priv *freqpriv;
 	unsigned long flags;
 	uint32_t code;
 	uint16_t cid, sqhd, data;
@@ -772,9 +789,8 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	ndlp = rport->ndlp;
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
-				 "6061 rport %p, ndlp %p, DID x%06x ndlp "
-				 "not ready.\n",
-				 rport, ndlp, rport->remoteport->port_id);
+				 "6061 rport %p,  DID x%06x node not ready.\n",
+				 rport, rport->remoteport->port_id);
 
 		ndlp = lpfc_findnode_did(vport, rport->remoteport->port_id);
 		if (!ndlp) {
@@ -853,15 +869,18 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 				break;
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
 					 "6081 NVME Completion Protocol Error: "
-					 "status x%x result x%x placed x%x\n",
+					 "xri %x status x%x result x%x "
+					 "placed x%x\n",
+					 lpfc_ncmd->cur_iocbq.sli4_xritag,
 					 lpfc_ncmd->status, lpfc_ncmd->result,
 					 wcqe->total_data_placed);
 			break;
 		default:
 out_err:
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
-					 "6072 NVME Completion Error: "
+					 "6072 NVME Completion Error: xri %x "
 					 "status x%x result x%x placed x%x\n",
+					 lpfc_ncmd->cur_iocbq.sli4_xritag,
 					 lpfc_ncmd->status, lpfc_ncmd->result,
 					 wcqe->total_data_placed);
 			nCmd->transferred_length = 0;
@@ -900,6 +919,8 @@ out_err:
 			phba->cpucheck_cmpl_io[lpfc_ncmd->cpu]++;
 	}
 #endif
+	freqpriv = nCmd->private;
+	freqpriv->nvme_buf = NULL;
 	nCmd->done(nCmd);
 
 	spin_lock_irqsave(&phba->hbalock, flags);
@@ -978,9 +999,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
 			       NVME_WRITE_CMD);
 
-			/* Word 16 */
-			wqe->words[16] = LPFC_NVME_EMBED_WRITE;
-
 			phba->fc4NvmeOutputRequests++;
 		} else {
 			/* Word 7 */
@@ -1002,9 +1020,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
 			       NVME_READ_CMD);
 
-			/* Word 16 */
-			wqe->words[16] = LPFC_NVME_EMBED_READ;
-
 			phba->fc4NvmeInputRequests++;
 		}
 	} else {
@@ -1026,9 +1041,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 		/* Word 11 */
 		bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD);
 
-		/* Word 16 */
-		wqe->words[16] = LPFC_NVME_EMBED_CMD;
-
 		phba->fc4NvmeControlRequests++;
 	}
 	/*
@@ -1108,12 +1120,12 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 
 		first_data_sgl = sgl;
 		lpfc_ncmd->seg_cnt = nCmd->sg_cnt;
-		if (lpfc_ncmd->seg_cnt > phba->cfg_sg_seg_cnt) {
+		if (lpfc_ncmd->seg_cnt > phba->cfg_nvme_seg_cnt) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 					"6058 Too many sg segments from "
 					"NVME Transport.  Max %d, "
 					"nvmeIO sg_cnt %d\n",
-					phba->cfg_sg_seg_cnt,
+					phba->cfg_nvme_seg_cnt,
 					lpfc_ncmd->seg_cnt);
 			lpfc_ncmd->seg_cnt = 0;
 			return 1;
@@ -1205,6 +1217,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	struct lpfc_nvme_buf *lpfc_ncmd;
 	struct lpfc_nvme_rport *rport;
 	struct lpfc_nvme_qhandle *lpfc_queue_info;
+	struct lpfc_nvme_fcpreq_priv *freqpriv = pnvme_fcreq->private;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	uint64_t start = 0;
 #endif
@@ -1283,9 +1296,10 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	 * Do not let the IO hang out forever.  There is no midlayer issuing
 	 * an abort so inform the FW of the maximum IO pending time.
 	 */
-	pnvme_fcreq->private = (void *)lpfc_ncmd;
+	freqpriv->nvme_buf = lpfc_ncmd;
 	lpfc_ncmd->nvmeCmd = pnvme_fcreq;
 	lpfc_ncmd->nrport = rport;
+	lpfc_ncmd->ndlp = ndlp;
 	lpfc_ncmd->start_time = jiffies;
 
 	lpfc_nvme_prep_io_cmd(vport, lpfc_ncmd, ndlp);
@@ -1319,7 +1333,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 				 "sid: x%x did: x%x oxid: x%x\n",
 				 ret, vport->fc_myDID, ndlp->nlp_DID,
 				 lpfc_ncmd->cur_iocbq.sli4_xritag);
-		ret = -EINVAL;
+		ret = -EBUSY;
 		goto out_free_nvme_buf;
 	}
 
@@ -1412,6 +1426,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	struct lpfc_nvme_buf *lpfc_nbuf;
 	struct lpfc_iocbq *abts_buf;
 	struct lpfc_iocbq *nvmereq_wqe;
+	struct lpfc_nvme_fcpreq_priv *freqpriv = pnvme_fcreq->private;
 	union lpfc_wqe *abts_wqe;
 	unsigned long flags;
 	int ret_val;
@@ -1422,7 +1437,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	phba = vport->phba;
 
 	/* Announce entry to new IO submit field. */
-	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS,
 			 "6002 Abort Request to rport DID x%06x "
 			 "for nvme_fc_req %p\n",
 			 pnvme_rport->port_id,
@@ -1452,7 +1467,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	/* The remote node has to be ready to send an abort. */
 	if ((ndlp->nlp_state != NLP_STE_MAPPED_NODE) &&
 	    !(ndlp->nlp_type & NLP_NVME_TARGET)) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_ABTS,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6048 rport %p, DID x%06x not ready for "
 				 "IO. State x%x, Type x%x\n",
 				 rport, pnvme_rport->port_id,
@@ -1467,27 +1482,28 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	/* driver queued commands are in process of being flushed */
 	if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6139 Driver in reset cleanup - flushing "
 				 "NVME Req now.  hba_flag x%x\n",
 				 phba->hba_flag);
 		return;
 	}
 
-	lpfc_nbuf = (struct lpfc_nvme_buf *)pnvme_fcreq->private;
+	lpfc_nbuf = freqpriv->nvme_buf;
 	if (!lpfc_nbuf) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6140 NVME IO req has no matching lpfc nvme "
 				 "io buffer.  Skipping abort req.\n");
 		return;
 	} else if (!lpfc_nbuf->nvmeCmd) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6141 lpfc NVME IO req has no nvme_fcreq "
 				 "io buffer.  Skipping abort req.\n");
 		return;
 	}
+	nvmereq_wqe = &lpfc_nbuf->cur_iocbq;
 
 	/*
 	 * The lpfc_nbuf and the mapped nvme_fcreq in the driver's
@@ -1498,23 +1514,22 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	 */
 	if (lpfc_nbuf->nvmeCmd != pnvme_fcreq) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6143 NVME req mismatch: "
 				 "lpfc_nbuf %p nvmeCmd %p, "
-				 "pnvme_fcreq %p.  Skipping Abort\n",
+				 "pnvme_fcreq %p.  Skipping Abort xri x%x\n",
 				 lpfc_nbuf, lpfc_nbuf->nvmeCmd,
-				 pnvme_fcreq);
+				 pnvme_fcreq, nvmereq_wqe->sli4_xritag);
 		return;
 	}
 
 	/* Don't abort IOs no longer on the pending queue. */
-	nvmereq_wqe = &lpfc_nbuf->cur_iocbq;
 	if (!(nvmereq_wqe->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6142 NVME IO req %p not queued - skipping "
-				 "abort req\n",
-				 pnvme_fcreq);
+				 "abort req xri x%x\n",
+				 pnvme_fcreq, nvmereq_wqe->sli4_xritag);
 		return;
 	}
 
@@ -1525,21 +1540,22 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	/* Outstanding abort is in progress */
 	if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6144 Outstanding NVME I/O Abort Request "
 				 "still pending on nvme_fcreq %p, "
-				 "lpfc_ncmd %p\n",
-				 pnvme_fcreq, lpfc_nbuf);
+				 "lpfc_ncmd %p xri x%x\n",
+				 pnvme_fcreq, lpfc_nbuf,
+				 nvmereq_wqe->sli4_xritag);
 		return;
 	}
 
 	abts_buf = __lpfc_sli_get_iocbq(phba);
 	if (!abts_buf) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6136 No available abort wqes. Skipping "
-				 "Abts req for nvme_fcreq %p.\n",
-				 pnvme_fcreq);
+				 "Abts req for nvme_fcreq %p xri x%x\n",
+				 pnvme_fcreq, nvmereq_wqe->sli4_xritag);
 		return;
 	}
 
@@ -1588,7 +1604,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	ret_val = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_buf);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 	if (ret_val == IOCB_ERROR) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
 				 "6137 Failed abts issue_wqe with status x%x "
 				 "for nvme_fcreq %p.\n",
 				 ret_val, pnvme_fcreq);
@@ -1596,8 +1612,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 		return;
 	}
 
-	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
-			 "6138 Transport Abort NVME Request Issued for\n"
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS,
+			 "6138 Transport Abort NVME Request Issued for "
 			 "ox_id x%x on reqtag x%x\n",
 			 nvmereq_wqe->sli4_xritag,
 			 abts_buf->iotag);
@@ -1626,7 +1642,7 @@ static struct nvme_fc_port_template lpfc_nvme_template = {
 	.local_priv_sz = sizeof(struct lpfc_nvme_lport),
 	.remote_priv_sz = sizeof(struct lpfc_nvme_rport),
 	.lsrqst_priv_sz = 0,
-	.fcprqst_priv_sz = 0,
+	.fcprqst_priv_sz = sizeof(struct lpfc_nvme_fcpreq_priv),
 };
 
 /**
@@ -1821,10 +1837,10 @@ lpfc_post_nvme_sgl_list(struct lpfc_hba *phba,
 						pdma_phys_sgl1, cur_xritag);
 				if (status) {
 					/* failure, put on abort nvme list */
-					lpfc_ncmd->exch_busy = 1;
+					lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
 				} else {
 					/* success, put on NVME buffer list */
-					lpfc_ncmd->exch_busy = 0;
+					lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
 					lpfc_ncmd->status = IOSTAT_SUCCESS;
 					num_posted++;
 				}
@@ -1854,10 +1870,10 @@ lpfc_post_nvme_sgl_list(struct lpfc_hba *phba,
 					 struct lpfc_nvme_buf, list);
 			if (status) {
 				/* failure, put on abort nvme list */
-				lpfc_ncmd->exch_busy = 1;
+				lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
 			} else {
 				/* success, put on NVME buffer list */
-				lpfc_ncmd->exch_busy = 0;
+				lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
 				lpfc_ncmd->status = IOSTAT_SUCCESS;
 				num_posted++;
 			}
@@ -2057,7 +2073,7 @@ lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 		if (lpfc_test_rrq_active(phba, ndlp,
 					 lpfc_ncmd->cur_iocbq.sli4_lxritag))
 			continue;
-		list_del(&lpfc_ncmd->list);
+		list_del_init(&lpfc_ncmd->list);
 		found = 1;
 		break;
 	}
@@ -2072,7 +2088,7 @@ lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 			if (lpfc_test_rrq_active(
 				phba, ndlp, lpfc_ncmd->cur_iocbq.sli4_lxritag))
 				continue;
-			list_del(&lpfc_ncmd->list);
+			list_del_init(&lpfc_ncmd->list);
 			found = 1;
 			break;
 		}
@@ -2099,7 +2115,13 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
 	unsigned long iflag = 0;
 
 	lpfc_ncmd->nonsg_phys = 0;
-	if (lpfc_ncmd->exch_busy) {
+	if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+				"6310 XB release deferred for "
+				"ox_id x%x on reqtag x%x\n",
+				lpfc_ncmd->cur_iocbq.sli4_xritag,
+				lpfc_ncmd->cur_iocbq.iotag);
+
 		spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock,
 					iflag);
 		lpfc_ncmd->nvmeCmd = NULL;
@@ -2135,11 +2157,12 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
 int
 lpfc_nvme_create_localport(struct lpfc_vport *vport)
 {
+	int ret = 0;
 	struct lpfc_hba  *phba = vport->phba;
 	struct nvme_fc_port_info nfcp_info;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
-	int len, ret = 0;
+	int len;
 
 	/* Initialize this localport instance.  The vport wwn usage ensures
 	 * that NPIV is accounted for.
@@ -2149,15 +2172,29 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
 	nfcp_info.node_name = wwn_to_u64(vport->fc_nodename.u.wwn);
 	nfcp_info.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
 
-	/* For now need + 1 to get around NVME transport logic */
-	lpfc_nvme_template.max_sgl_segments = phba->cfg_sg_seg_cnt + 1;
+	/* Limit to LPFC_MAX_NVME_SEG_CNT.
+	 * For now need + 1 to get around NVME transport logic.
+	 */
+	if (phba->cfg_sg_seg_cnt > LPFC_MAX_NVME_SEG_CNT) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_INIT,
+				 "6300 Reducing sg segment cnt to %d\n",
+				 LPFC_MAX_NVME_SEG_CNT);
+		phba->cfg_nvme_seg_cnt = LPFC_MAX_NVME_SEG_CNT;
+	} else {
+		phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt;
+	}
+	lpfc_nvme_template.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1;
 	lpfc_nvme_template.max_hw_queues = phba->cfg_nvme_io_channel;
 
 	/* localport is allocated from the stack, but the registration
 	 * call allocates heap memory as well as the private area.
 	 */
+#if (IS_ENABLED(CONFIG_NVME_FC))
 	ret = nvme_fc_register_localport(&nfcp_info, &lpfc_nvme_template,
 					 &vport->phba->pcidev->dev, &localport);
+#else
+	ret = -ENOMEM;
+#endif
 	if (!ret) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_NVME_DISC,
 				 "6005 Successfully registered local "
@@ -2173,10 +2210,10 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
 		lport->vport = vport;
 		INIT_LIST_HEAD(&lport->rport_list);
 		vport->nvmei_support = 1;
+		len  = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
+		vport->phba->total_nvme_bufs += len;
 	}
 
-	len  = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
-	vport->phba->total_nvme_bufs += len;
 	return ret;
 }
 
@@ -2193,6 +2230,7 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
 void
 lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 {
+#if (IS_ENABLED(CONFIG_NVME_FC))
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_nvme_rport *rport = NULL, *rport_next = NULL;
@@ -2208,7 +2246,6 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
 			 "6011 Destroying NVME localport %p\n",
 			 localport);
-
 	list_for_each_entry_safe(rport, rport_next, &lport->rport_list, list) {
 		/* The last node ref has to get released now before the rport
 		 * private memory area is released by the transport.
@@ -2222,6 +2259,7 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 					 "6008 rport fail destroy %x\n", ret);
 		wait_for_completion_timeout(&rport->rport_unreg_done, 5);
 	}
+
 	/* lport's rport list is clear.  Unregister
 	 * lport and release resources.
 	 */
@@ -2245,17 +2283,29 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 				 "Failed, status x%x\n",
 				 ret);
 	}
+#endif
 }
 
 void
 lpfc_nvme_update_localport(struct lpfc_vport *vport)
 {
+#if (IS_ENABLED(CONFIG_NVME_FC))
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
 
 	localport = vport->localport;
+	if (!localport) {
+		lpfc_printf_vlog(vport, KERN_WARNING, LOG_NVME,
+				 "6710 Update NVME fail. No localport\n");
+		return;
+	}
 	lport = (struct lpfc_nvme_lport *)localport->private;
-
+	if (!lport) {
+		lpfc_printf_vlog(vport, KERN_WARNING, LOG_NVME,
+				 "6171 Update NVME fail. localP %p, No lport\n",
+				 localport);
+		return;
+	}
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
 			 "6012 Update NVME lport %p did x%x\n",
 			 localport, vport->fc_myDID);
@@ -2269,12 +2319,13 @@ lpfc_nvme_update_localport(struct lpfc_vport *vport)
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 			 "6030 bound lport %p to DID x%06x\n",
 			 lport, localport->port_id);
-
+#endif
 }
 
 int
 lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
+#if (IS_ENABLED(CONFIG_NVME_FC))
 	int ret = 0;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
@@ -2348,7 +2399,6 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 			rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR;
 		rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
 		rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
-
 		ret = nvme_fc_register_remoteport(localport, &rpinfo,
 						  &remote_port);
 		if (!ret) {
@@ -2384,6 +2434,9 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				 ndlp->nlp_type, ndlp->nlp_DID, ndlp);
 	}
 	return ret;
+#else
+	return 0;
+#endif
 }
 
 /* lpfc_nvme_unregister_port - unbind the DID and port_role from this rport.
@@ -2401,11 +2454,13 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 void
 lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
+#if (IS_ENABLED(CONFIG_NVME_FC))
 	int ret;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_nvme_rport *rport;
 	struct nvme_fc_remote_port *remoteport;
+	unsigned long wait_tmo;
 
 	localport = vport->localport;
 
@@ -2448,17 +2503,82 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		 * before proceeding.  This guarantees the transport and driver
 		 * have completed the unreg process.
 		 */
-		ret = wait_for_completion_timeout(&rport->rport_unreg_done, 5);
+		wait_tmo = msecs_to_jiffies(5000);
+		ret = wait_for_completion_timeout(&rport->rport_unreg_done,
+						  wait_tmo);
 		if (ret == 0) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
-					 "6169 Unreg nvme wait failed %d\n",
-					 ret);
+					 "6169 Unreg nvme wait timeout\n");
 		}
 	}
 	return;
 
  input_err:
+#endif
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
-			 "6168: State error: lport %p, rport%p FCID x%06x\n",
+			 "6168 State error: lport %p, rport%p FCID x%06x\n",
 			 vport->localport, ndlp->rport, ndlp->nlp_DID);
 }
+
+/**
+ * lpfc_sli4_nvme_xri_aborted - Fast-path process of NVME xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @axri: pointer to the fcp xri abort wcqe structure.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * FCP aborted xri.
+ **/
+void
+lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
+			   struct sli4_wcqe_xri_aborted *axri)
+{
+	uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri);
+	uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+	struct lpfc_nvme_buf *lpfc_ncmd, *next_lpfc_ncmd;
+	struct lpfc_nodelist *ndlp;
+	unsigned long iflag = 0;
+	int rrq_empty = 0;
+
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+		return;
+	spin_lock_irqsave(&phba->hbalock, iflag);
+	spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	list_for_each_entry_safe(lpfc_ncmd, next_lpfc_ncmd,
+				 &phba->sli4_hba.lpfc_abts_nvme_buf_list,
+				 list) {
+		if (lpfc_ncmd->cur_iocbq.sli4_xritag == xri) {
+			list_del_init(&lpfc_ncmd->list);
+			lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
+			lpfc_ncmd->status = IOSTAT_SUCCESS;
+			spin_unlock(
+				&phba->sli4_hba.abts_nvme_buf_list_lock);
+
+			rrq_empty = list_empty(&phba->active_rrq_list);
+			spin_unlock_irqrestore(&phba->hbalock, iflag);
+			ndlp = lpfc_ncmd->ndlp;
+			if (ndlp) {
+				lpfc_set_rrq_active(
+					phba, ndlp,
+					lpfc_ncmd->cur_iocbq.sli4_lxritag,
+					rxid, 1);
+				lpfc_sli4_abts_err_handler(phba, ndlp, axri);
+			}
+
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+					"6311 XRI Aborted xri x%x tag x%x "
+					"released\n",
+					xri, lpfc_ncmd->cur_iocbq.iotag);
+
+			lpfc_release_nvme_buf(phba, lpfc_ncmd);
+			if (rrq_empty)
+				lpfc_worker_wake_up(phba);
+			return;
+		}
+	}
+	spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6312 XRI Aborted xri x%x not found\n", xri);
+
+}
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index b2fae5e813f8..ec32f45daa66 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -21,12 +21,7 @@
  * included with this package.                                     *
  ********************************************************************/
 
-#define LPFC_NVME_MIN_SEGS		16
-#define LPFC_NVME_DEFAULT_SEGS		66	/* 256K IOs - 64 + 2 */
-#define LPFC_NVME_MAX_SEGS		510
-#define LPFC_NVMET_MIN_POSTBUF		16
-#define LPFC_NVMET_DEFAULT_POSTBUF	1024
-#define LPFC_NVMET_MAX_POSTBUF		4096
+#define LPFC_NVME_DEFAULT_SEGS		(64 + 1)	/* 256K IOs */
 #define LPFC_NVME_WQSIZE		256
 
 #define LPFC_NVME_ERSP_LEN		0x20
@@ -57,6 +52,7 @@ struct lpfc_nvme_buf {
 	struct list_head list;
 	struct nvmefc_fcp_req *nvmeCmd;
 	struct lpfc_nvme_rport *nrport;
+	struct lpfc_nodelist *ndlp;
 
 	uint32_t timeout;
 
@@ -101,3 +97,7 @@ struct lpfc_nvme_buf {
 	uint64_t ts_data_nvme;
 #endif
 };
+
+struct lpfc_nvme_fcpreq_priv {
+	struct lpfc_nvme_buf *nvme_buf;
+};
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index c421e1738ee9..94434e621c33 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -71,6 +71,26 @@ static int lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *,
 					   struct lpfc_nvmet_rcv_ctx *,
 					   uint32_t, uint16_t);
 
+void
+lpfc_nvmet_defer_release(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp)
+{
+	unsigned long iflag;
+
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+			"6313 NVMET Defer ctx release xri x%x flg x%x\n",
+			ctxp->oxid, ctxp->flag);
+
+	spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock, iflag);
+	if (ctxp->flag & LPFC_NVMET_CTX_RLS) {
+		spin_unlock_irqrestore(&phba->sli4_hba.abts_nvme_buf_list_lock,
+				       iflag);
+		return;
+	}
+	ctxp->flag |= LPFC_NVMET_CTX_RLS;
+	list_add_tail(&ctxp->list, &phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+	spin_unlock_irqrestore(&phba->sli4_hba.abts_nvme_buf_list_lock, iflag);
+}
+
 /**
  * lpfc_nvmet_xmt_ls_rsp_cmp - Completion handler for LS Response
  * @phba: Pointer to HBA context object.
@@ -139,6 +159,11 @@ lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
 		   struct lpfc_dmabuf *mp)
 {
 	if (ctxp) {
+		if (ctxp->flag)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+				"6314 rq_post ctx xri x%x flag x%x\n",
+				ctxp->oxid, ctxp->flag);
+
 		if (ctxp->txrdy) {
 			pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
 				      ctxp->txrdy_phys);
@@ -337,39 +362,55 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 #endif
 
 	ctxp = cmdwqe->context2;
+	ctxp->flag &= ~LPFC_NVMET_IO_INP;
+
 	rsp = &ctxp->ctx.fcp_req;
 	op = rsp->op;
-	ctxp->flag &= ~LPFC_NVMET_IO_INP;
 
 	status = bf_get(lpfc_wcqe_c_status, wcqe);
 	result = wcqe->parameter;
 
-	if (!phba->targetport)
-		goto out;
+	if (phba->targetport)
+		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	else
+		tgtp = NULL;
 
 	lpfc_nvmeio_data(phba, "NVMET FCP CMPL: xri x%x op x%x status x%x\n",
 			 ctxp->oxid, op, status);
 
-	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	if (status) {
 		rsp->fcp_error = NVME_SC_DATA_XFER_ERROR;
 		rsp->transferred_length = 0;
-		atomic_inc(&tgtp->xmt_fcp_rsp_error);
+		if (tgtp)
+			atomic_inc(&tgtp->xmt_fcp_rsp_error);
+
+		/* pick up SLI4 exhange busy condition */
+		if (bf_get(lpfc_wcqe_c_xb, wcqe)) {
+			ctxp->flag |= LPFC_NVMET_XBUSY;
+
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+					"6315 IO Cmpl XBUSY: xri x%x: %x/%x\n",
+					ctxp->oxid, status, result);
+		} else {
+			ctxp->flag &= ~LPFC_NVMET_XBUSY;
+		}
+
 	} else {
 		rsp->fcp_error = NVME_SC_SUCCESS;
 		if (op == NVMET_FCOP_RSP)
 			rsp->transferred_length = rsp->rsplen;
 		else
 			rsp->transferred_length = rsp->transfer_length;
-		atomic_inc(&tgtp->xmt_fcp_rsp_cmpl);
+		if (tgtp)
+			atomic_inc(&tgtp->xmt_fcp_rsp_cmpl);
 	}
 
-out:
 	if ((op == NVMET_FCOP_READDATA_RSP) ||
 	    (op == NVMET_FCOP_RSP)) {
 		/* Sanity check */
 		ctxp->state = LPFC_NVMET_STE_DONE;
 		ctxp->entry_cnt++;
+
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 		if (phba->ktime_on) {
 			if (rsp->op == NVMET_FCOP_READDATA_RSP) {
@@ -408,9 +449,7 @@ out:
 		if (phba->ktime_on)
 			lpfc_nvmet_ktime(phba, ctxp);
 #endif
-		/* Let Abort cmpl repost the context */
-		if (!(ctxp->flag & LPFC_NVMET_ABORT_OP))
-			lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+		/* lpfc_nvmet_xmt_fcp_release() will recycle the context */
 	} else {
 		ctxp->entry_cnt++;
 		start_clean = offsetof(struct lpfc_iocbq, wqe);
@@ -519,8 +558,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 		container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
 	struct lpfc_hba *phba = ctxp->phba;
 	struct lpfc_iocbq *nvmewqeq;
-	unsigned long iflags;
-	int rc, id;
+	int rc;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	if (phba->ktime_on) {
@@ -530,7 +568,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 			ctxp->ts_nvme_data = ktime_get_ns();
 	}
 	if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
-		id = smp_processor_id();
+		int id = smp_processor_id();
 		ctxp->cpu = id;
 		if (id < LPFC_CHECK_CPU_CNT)
 			phba->cpucheck_xmt_io[id]++;
@@ -544,33 +582,14 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	}
 #endif
 
-	if (rsp->op == NVMET_FCOP_ABORT) {
-		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-				"6103 Abort op: oxri x%x %d cnt %d\n",
-				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
-
-		lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
-				 "xri x%x state x%x cnt x%x\n",
-				 ctxp->oxid, ctxp->state, ctxp->entry_cnt);
-
-		atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
-		ctxp->entry_cnt++;
-		ctxp->flag |= LPFC_NVMET_ABORT_OP;
-		if (ctxp->flag & LPFC_NVMET_IO_INP)
-			lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
-						       ctxp->oxid);
-		else
-			lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
-							 ctxp->oxid);
-		return 0;
-	}
-
 	/* Sanity check */
-	if (ctxp->state == LPFC_NVMET_STE_ABORT) {
+	if ((ctxp->flag & LPFC_NVMET_ABTS_RCV) ||
+	    (ctxp->state == LPFC_NVMET_STE_ABORT)) {
 		atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6102 Bad state IO x%x aborted\n",
+				"6102 IO xri x%x aborted\n",
 				ctxp->oxid);
+		rc = -ENXIO;
 		goto aerr;
 	}
 
@@ -580,6 +599,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6152 FCP Drop IO x%x: Prep\n",
 				ctxp->oxid);
+		rc = -ENXIO;
 		goto aerr;
 	}
 
@@ -592,10 +612,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	lpfc_nvmeio_data(phba, "NVMET FCP CMND: xri x%x op x%x len x%x\n",
 			 ctxp->oxid, rsp->op, rsp->rsplen);
 
-	/* For now we take hbalock */
-	spin_lock_irqsave(&phba->hbalock, iflags);
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, nvmewqeq);
-	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	if (rc == WQE_SUCCESS) {
 		ctxp->flag |= LPFC_NVMET_IO_INP;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
@@ -618,8 +635,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	ctxp->wqeq->hba_wqidx = 0;
 	nvmewqeq->context2 = NULL;
 	nvmewqeq->context3 = NULL;
+	rc = -EBUSY;
 aerr:
-	return -ENXIO;
+	return rc;
 }
 
 static void
@@ -631,10 +649,79 @@ lpfc_nvmet_targetport_delete(struct nvmet_fc_target_port *targetport)
 	complete(&tport->tport_unreg_done);
 }
 
+static void
+lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport,
+			 struct nvmefc_tgt_fcp_req *req)
+{
+	struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
+	struct lpfc_nvmet_rcv_ctx *ctxp =
+		container_of(req, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+	struct lpfc_hba *phba = ctxp->phba;
+	unsigned long flags;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6103 Abort op: oxri x%x flg x%x cnt %d\n",
+			ctxp->oxid, ctxp->flag, ctxp->entry_cnt);
+
+	lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
+			 "xri x%x flg x%x cnt x%x\n",
+			 ctxp->oxid, ctxp->flag, ctxp->entry_cnt);
+
+	atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
+	ctxp->entry_cnt++;
+	spin_lock_irqsave(&ctxp->ctxlock, flags);
+
+	/* Since iaab/iaar are NOT set, we need to check
+	 * if the firmware is in process of aborting IO
+	 */
+	if (ctxp->flag & LPFC_NVMET_XBUSY) {
+		spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+		return;
+	}
+	ctxp->flag |= LPFC_NVMET_ABORT_OP;
+	if (ctxp->flag & LPFC_NVMET_IO_INP)
+		lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+					       ctxp->oxid);
+	else
+		lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+						 ctxp->oxid);
+	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+}
+
+static void
+lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
+			   struct nvmefc_tgt_fcp_req *rsp)
+{
+	struct lpfc_nvmet_rcv_ctx *ctxp =
+		container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+	struct lpfc_hba *phba = ctxp->phba;
+	unsigned long flags;
+	bool aborting = false;
+
+	spin_lock_irqsave(&ctxp->ctxlock, flags);
+	if ((ctxp->flag & LPFC_NVMET_ABORT_OP) ||
+	    (ctxp->flag & LPFC_NVMET_XBUSY)) {
+		aborting = true;
+		/* let the abort path do the real release */
+		lpfc_nvmet_defer_release(phba, ctxp);
+	}
+	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
+	lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d\n", ctxp->oxid,
+			 ctxp->state, 0);
+
+	if (aborting)
+		return;
+
+	lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+}
+
 static struct nvmet_fc_target_template lpfc_tgttemplate = {
 	.targetport_delete = lpfc_nvmet_targetport_delete,
 	.xmt_ls_rsp     = lpfc_nvmet_xmt_ls_rsp,
 	.fcp_op         = lpfc_nvmet_xmt_fcp_op,
+	.fcp_abort      = lpfc_nvmet_xmt_fcp_abort,
+	.fcp_req_release = lpfc_nvmet_xmt_fcp_release,
 
 	.max_hw_queues  = 1,
 	.max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS,
@@ -663,14 +750,31 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
 	pinfo.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
 	pinfo.port_id = vport->fc_myDID;
 
+	/* Limit to LPFC_MAX_NVME_SEG_CNT.
+	 * For now need + 1 to get around NVME transport logic.
+	 */
+	if (phba->cfg_sg_seg_cnt > LPFC_MAX_NVME_SEG_CNT) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME | LOG_INIT,
+				"6400 Reducing sg segment cnt to %d\n",
+				LPFC_MAX_NVME_SEG_CNT);
+		phba->cfg_nvme_seg_cnt = LPFC_MAX_NVME_SEG_CNT;
+	} else {
+		phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt;
+	}
+	lpfc_tgttemplate.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1;
 	lpfc_tgttemplate.max_hw_queues = phba->cfg_nvme_io_channel;
-	lpfc_tgttemplate.max_sgl_segments = phba->cfg_sg_seg_cnt;
 	lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
-					   NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED;
+					   NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
+					   NVMET_FCTGTFEAT_CMD_IN_ISR |
+					   NVMET_FCTGTFEAT_OPDONE_IN_ISR;
 
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
 	error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate,
 					     &phba->pcidev->dev,
 					     &phba->targetport);
+#else
+	error = -ENOMEM;
+#endif
 	if (error) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
 				"6025 Cannot register NVME targetport "
@@ -731,9 +835,138 @@ lpfc_nvmet_update_targetport(struct lpfc_hba *phba)
 	return 0;
 }
 
+/**
+ * lpfc_sli4_nvmet_xri_aborted - Fast-path process of nvmet xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @axri: pointer to the nvmet xri abort wcqe structure.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * NVMET aborted xri.
+ **/
+void
+lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
+			    struct sli4_wcqe_xri_aborted *axri)
+{
+	uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri);
+	uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+	struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
+	struct lpfc_nodelist *ndlp;
+	unsigned long iflag = 0;
+	int rrq_empty = 0;
+	bool released = false;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6317 XB aborted xri x%x rxid x%x\n", xri, rxid);
+
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+		return;
+	spin_lock_irqsave(&phba->hbalock, iflag);
+	spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	list_for_each_entry_safe(ctxp, next_ctxp,
+				 &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+				 list) {
+		if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+			continue;
+
+		/* Check if we already received a free context call
+		 * and we have completed processing an abort situation.
+		 */
+		if (ctxp->flag & LPFC_NVMET_CTX_RLS &&
+		    !(ctxp->flag & LPFC_NVMET_ABORT_OP)) {
+			list_del(&ctxp->list);
+			released = true;
+		}
+		ctxp->flag &= ~LPFC_NVMET_XBUSY;
+		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+
+		rrq_empty = list_empty(&phba->active_rrq_list);
+		spin_unlock_irqrestore(&phba->hbalock, iflag);
+		ndlp = lpfc_findnode_did(phba->pport, ctxp->sid);
+		if (ndlp && NLP_CHK_NODE_ACT(ndlp) &&
+		    (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE ||
+		     ndlp->nlp_state == NLP_STE_MAPPED_NODE)) {
+			lpfc_set_rrq_active(phba, ndlp,
+				ctxp->rqb_buffer->sglq->sli4_lxritag,
+				rxid, 1);
+			lpfc_sli4_abts_err_handler(phba, ndlp, axri);
+		}
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+				"6318 XB aborted %x flg x%x (%x)\n",
+				ctxp->oxid, ctxp->flag, released);
+		if (released)
+			lpfc_nvmet_rq_post(phba, ctxp,
+					   &ctxp->rqb_buffer->hbuf);
+		if (rrq_empty)
+			lpfc_worker_wake_up(phba);
+		return;
+	}
+	spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	spin_unlock_irqrestore(&phba->hbalock, iflag);
+}
+
+int
+lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
+			   struct fc_frame_header *fc_hdr)
+
+{
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
+	struct nvmefc_tgt_fcp_req *rsp;
+	uint16_t xri;
+	unsigned long iflag = 0;
+
+	xri = be16_to_cpu(fc_hdr->fh_ox_id);
+
+	spin_lock_irqsave(&phba->hbalock, iflag);
+	spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	list_for_each_entry_safe(ctxp, next_ctxp,
+				 &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+				 list) {
+		if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+			continue;
+
+		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+		spin_lock_irqsave(&ctxp->ctxlock, iflag);
+		ctxp->flag |= LPFC_NVMET_ABTS_RCV;
+		spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
+
+		lpfc_nvmeio_data(phba,
+			"NVMET ABTS RCV: xri x%x CPU %02x rjt %d\n",
+			xri, smp_processor_id(), 0);
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+				"6319 NVMET Rcv ABTS:acc xri x%x\n", xri);
+
+		rsp = &ctxp->ctx.fcp_req;
+		nvmet_fc_rcv_fcp_abort(phba->targetport, rsp);
+
+		/* Respond with BA_ACC accordingly */
+		lpfc_sli4_seq_abort_rsp(vport, fc_hdr, 1);
+		return 0;
+	}
+	spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+	lpfc_nvmeio_data(phba, "NVMET ABTS RCV: xri x%x CPU %02x rjt %d\n",
+			 xri, smp_processor_id(), 1);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6320 NVMET Rcv ABTS:rjt xri x%x\n", xri);
+
+	/* Respond with BA_RJT accordingly */
+	lpfc_sli4_seq_abort_rsp(vport, fc_hdr, 0);
+#endif
+	return 0;
+}
+
 void
 lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
 {
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
 	struct lpfc_nvmet_tgtport *tgtp;
 
 	if (phba->nvmet_support == 0)
@@ -745,6 +978,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
 		wait_for_completion_timeout(&tgtp->tport_unreg_done, 5);
 	}
 	phba->targetport = NULL;
+#endif
 }
 
 /**
@@ -764,6 +998,7 @@ static void
 lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			   struct hbq_dmabuf *nvmebuf)
 {
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct fc_frame_header *fc_hdr;
 	struct lpfc_nvmet_rcv_ctx *ctxp;
@@ -844,6 +1079,7 @@ dropit:
 
 	atomic_inc(&tgtp->xmt_ls_abort);
 	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid);
+#endif
 }
 
 /**
@@ -865,6 +1101,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 			    struct rqb_dmabuf *nvmebuf,
 			    uint64_t isr_timestamp)
 {
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct fc_frame_header *fc_hdr;
@@ -913,6 +1150,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	ctxp->rqb_buffer = nvmebuf;
 	ctxp->entry_cnt = 1;
 	ctxp->flag = 0;
+	spin_lock_init(&ctxp->ctxlock);
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	if (phba->ktime_on) {
@@ -935,8 +1173,8 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	}
 #endif
 
-	lpfc_nvmeio_data(phba, "NVMET FCP  RCV: xri x%x sz %d from %06x\n",
-			 oxid, size, sid);
+	lpfc_nvmeio_data(phba, "NVMET FCP  RCV: xri x%x sz %d CPU %02x\n",
+			 oxid, size, smp_processor_id());
 
 	atomic_inc(&tgtp->rcv_fcp_cmd_in);
 	/*
@@ -955,7 +1193,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 
 	atomic_inc(&tgtp->rcv_fcp_cmd_drop);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-			"6159 FCP Drop IO x%x: nvmet_fc_rcv_fcp_req x%x\n",
+			"6159 FCP Drop IO x%x: err x%x\n",
 			ctxp->oxid, rc);
 dropit:
 	lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n",
@@ -970,6 +1208,7 @@ dropit:
 		/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
 		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
 	}
+#endif
 }
 
 /**
@@ -1114,7 +1353,7 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
 	bf_set(wqe_dfctl, &wqe->xmit_sequence.wge_ctl, 0);
 	bf_set(wqe_ls, &wqe->xmit_sequence.wge_ctl, 1);
 	bf_set(wqe_la, &wqe->xmit_sequence.wge_ctl, 0);
-	bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_DD_SOL_CTL);
+	bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_ELS4_REP);
 	bf_set(wqe_type, &wqe->xmit_sequence.wge_ctl, FC_TYPE_NVME);
 
 	/* Word 6 */
@@ -1209,11 +1448,11 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		return NULL;
 	}
 
-	if (rsp->sg_cnt > phba->cfg_sg_seg_cnt) {
+	if (rsp->sg_cnt > phba->cfg_nvme_seg_cnt) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6109 lpfc_nvmet_prep_fcp_wqe: seg cnt err: "
-				"NPORT x%x oxid:x%x\n",
-				ctxp->sid, ctxp->oxid);
+				"NPORT x%x oxid:x%x cnt %d\n",
+				ctxp->sid, ctxp->oxid, phba->cfg_nvme_seg_cnt);
 		return NULL;
 	}
 
@@ -1445,7 +1684,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 
 	case NVMET_FCOP_RSP:
 		/* Words 0 - 2 */
-		sgel = &rsp->sg[0];
 		physaddr = rsp->rspdma;
 		wqe->fcp_trsp.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
 		wqe->fcp_trsp.bde.tus.f.bdeSize = rsp->rsplen;
@@ -1566,6 +1804,8 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	uint32_t status, result;
+	unsigned long flags;
+	bool released = false;
 
 	ctxp = cmdwqe->context2;
 	status = bf_get(lpfc_wcqe_c_status, wcqe);
@@ -1574,21 +1814,46 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	atomic_inc(&tgtp->xmt_abort_cmpl);
 
+	ctxp->state = LPFC_NVMET_STE_DONE;
+
+	/* Check if we already received a free context call
+	 * and we have completed processing an abort situation.
+	 */
+	spin_lock_irqsave(&ctxp->ctxlock, flags);
+	if ((ctxp->flag & LPFC_NVMET_CTX_RLS) &&
+	    !(ctxp->flag & LPFC_NVMET_XBUSY)) {
+		list_del(&ctxp->list);
+		released = true;
+	}
+	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
-			"6165 Abort cmpl: xri x%x WCQE: %08x %08x %08x %08x\n",
-			ctxp->oxid, wcqe->word0, wcqe->total_data_placed,
+			"6165 ABORT cmpl: xri x%x flg x%x (%d) "
+			"WCQE: %08x %08x %08x %08x\n",
+			ctxp->oxid, ctxp->flag, released,
+			wcqe->word0, wcqe->total_data_placed,
 			result, wcqe->word3);
 
-	ctxp->state = LPFC_NVMET_STE_DONE;
-	lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+	/*
+	 * if transport has released ctx, then can reuse it. Otherwise,
+	 * will be recycled by transport release call.
+	 */
+	if (released)
+		lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
 
 	cmdwqe->context2 = NULL;
 	cmdwqe->context3 = NULL;
 	lpfc_sli_release_iocbq(phba, cmdwqe);
+
+	/* Since iaab/iaar are NOT set, there is no work left.
+	 * For LPFC_NVMET_XBUSY, lpfc_sli4_nvmet_xri_aborted
+	 * should have been called already.
+	 */
 }
 
 /**
- * lpfc_nvmet_xmt_fcp_abort_cmp - Completion handler for ABTS
+ * lpfc_nvmet_unsol_fcp_abort_cmp - Completion handler for ABTS
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
  * @wcqe: Pointer to driver response CQE object.
@@ -1598,12 +1863,14 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  * The function frees memory resources used for the NVME commands.
  **/
 static void
-lpfc_nvmet_xmt_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			     struct lpfc_wcqe_complete *wcqe)
+lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+			       struct lpfc_wcqe_complete *wcqe)
 {
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
+	unsigned long flags;
 	uint32_t status, result;
+	bool released = false;
 
 	ctxp = cmdwqe->context2;
 	status = bf_get(lpfc_wcqe_c_status, wcqe);
@@ -1612,23 +1879,55 @@ lpfc_nvmet_xmt_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	atomic_inc(&tgtp->xmt_abort_cmpl);
 
+	if (!ctxp) {
+		/* if context is clear, related io alrady complete */
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+				"6070 ABTS cmpl: WCQE: %08x %08x %08x %08x\n",
+				wcqe->word0, wcqe->total_data_placed,
+				result, wcqe->word3);
+		return;
+	}
+
+	/* Sanity check */
+	if (ctxp->state != LPFC_NVMET_STE_ABORT) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+				"6112 ABTS Wrong state:%d oxid x%x\n",
+				ctxp->state, ctxp->oxid);
+	}
+
+	/* Check if we already received a free context call
+	 * and we have completed processing an abort situation.
+	 */
+	ctxp->state = LPFC_NVMET_STE_DONE;
+	spin_lock_irqsave(&ctxp->ctxlock, flags);
+	if ((ctxp->flag & LPFC_NVMET_CTX_RLS) &&
+	    !(ctxp->flag & LPFC_NVMET_XBUSY)) {
+		list_del(&ctxp->list);
+		released = true;
+	}
+	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-			"6070 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
-			ctxp, wcqe->word0, wcqe->total_data_placed,
+			"6316 ABTS cmpl xri x%x flg x%x (%x) "
+			"WCQE: %08x %08x %08x %08x\n",
+			ctxp->oxid, ctxp->flag, released,
+			wcqe->word0, wcqe->total_data_placed,
 			result, wcqe->word3);
-
-	if (ctxp) {
-		/* Sanity check */
-		if (ctxp->state != LPFC_NVMET_STE_ABORT) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
-					"6112 ABORT Wrong state:%d oxid x%x\n",
-					ctxp->state, ctxp->oxid);
-		}
-		ctxp->state = LPFC_NVMET_STE_DONE;
+	/*
+	 * if transport has released ctx, then can reuse it. Otherwise,
+	 * will be recycled by transport release call.
+	 */
+	if (released)
 		lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
-		cmdwqe->context2 = NULL;
-		cmdwqe->context3 = NULL;
-	}
+
+	cmdwqe->context2 = NULL;
+	cmdwqe->context3 = NULL;
+
+	/* Since iaab/iaar are NOT set, there is no work left.
+	 * For LPFC_NVMET_XBUSY, lpfc_sli4_nvmet_xri_aborted
+	 * should have been called already.
+	 */
 }
 
 /**
@@ -1681,10 +1980,14 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 	struct lpfc_nodelist *ndlp;
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-			"6067 %s: Entrypoint: sid %x xri %x\n", __func__,
-			sid, xri);
+			"6067 ABTS: sid %x xri x%x/x%x\n",
+			sid, xri, ctxp->wqeq->sli4_xritag);
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if (!ctxp->wqeq) {
+		ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+		ctxp->wqeq->hba_wqidx = 0;
+	}
 
 	ndlp = lpfc_findnode_did(phba->pport, sid);
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
@@ -1693,7 +1996,7 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
 				"6134 Drop ABTS - wrong NDLP state x%x.\n",
-				ndlp->nlp_state);
+				(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
 
 		/* No failure to an ABTS request. */
 		return 0;
@@ -1790,10 +2093,11 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
-				"6160 Drop ABTS - wrong NDLP state x%x.\n",
-				ndlp->nlp_state);
+				"6160 Drop ABORT - wrong NDLP state x%x.\n",
+				(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
 
 		/* No failure to an ABTS request. */
+		ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 		return 0;
 	}
 
@@ -1801,9 +2105,10 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	ctxp->abort_wqeq = lpfc_sli_get_iocbq(phba);
 	if (!ctxp->abort_wqeq) {
 		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
-				"6161 Abort failed: No wqeqs: "
+				"6161 ABORT failed: No wqeqs: "
 				"xri: x%x\n", ctxp->oxid);
 		/* No failure to an ABTS request. */
+		ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 		return 0;
 	}
 	abts_wqeq = ctxp->abort_wqeq;
@@ -1811,8 +2116,8 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	ctxp->state = LPFC_NVMET_STE_ABORT;
 
 	/* Announce entry to new IO submit field. */
-	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
-			"6162 Abort Request to rport DID x%06x "
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6162 ABORT Request to rport DID x%06x "
 			"for xri x%x x%x\n",
 			ctxp->sid, ctxp->oxid, ctxp->wqeq->sli4_xritag);
 
@@ -1828,6 +2133,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 				"NVME Req now. hba_flag x%x oxid x%x\n",
 				phba->hba_flag, ctxp->oxid);
 		lpfc_sli_release_iocbq(phba, abts_wqeq);
+		ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 		return 0;
 	}
 
@@ -1839,6 +2145,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 				"still pending on oxid x%x\n",
 				ctxp->oxid);
 		lpfc_sli_release_iocbq(phba, abts_wqeq);
+		ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 		return 0;
 	}
 
@@ -1886,9 +2193,10 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	if (rc == WQE_SUCCESS)
 		return 0;
 
+	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	lpfc_sli_release_iocbq(phba, abts_wqeq);
-	lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
-			"6166 Failed abts issue_wqe with status x%x "
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+			"6166 Failed ABORT issue_wqe with status x%x "
 			"for oxid x%x.\n",
 			rc, ctxp->oxid);
 	return 1;
@@ -1917,8 +2225,8 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 
 	spin_lock_irqsave(&phba->hbalock, flags);
 	abts_wqeq = ctxp->wqeq;
-	abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_fcp_abort_cmp;
-	abts_wqeq->iocb_cmpl = 0;
+	abts_wqeq->wqe_cmpl = lpfc_nvmet_unsol_fcp_abort_cmp;
+	abts_wqeq->iocb_cmpl = NULL;
 	abts_wqeq->iocb_flag |= LPFC_IO_NVMET;
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
@@ -1928,7 +2236,7 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 	}
 
 aerr:
-	lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
 			"6135 Failed to Issue ABTS for oxid x%x. Status x%x\n",
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index ca96f05c1604..128759fe6650 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -21,9 +21,7 @@
  * included with this package.                                     *
  ********************************************************************/
 
-#define LPFC_NVMET_MIN_SEGS		16
-#define LPFC_NVMET_DEFAULT_SEGS		64	/* 256K IOs */
-#define LPFC_NVMET_MAX_SEGS		510
+#define LPFC_NVMET_DEFAULT_SEGS		(64 + 1)	/* 256K IOs */
 #define LPFC_NVMET_SUCCESS_LEN	12
 
 /* Used for NVME Target */
@@ -77,10 +75,12 @@ struct lpfc_nvmet_rcv_ctx {
 		struct nvmefc_tgt_ls_req ls_req;
 		struct nvmefc_tgt_fcp_req fcp_req;
 	} ctx;
+	struct list_head list;
 	struct lpfc_hba *phba;
 	struct lpfc_iocbq *wqeq;
 	struct lpfc_iocbq *abort_wqeq;
 	dma_addr_t txrdy_phys;
+	spinlock_t ctxlock; /* protect flag access */
 	uint32_t *txrdy;
 	uint32_t sid;
 	uint32_t offset;
@@ -97,8 +97,11 @@ struct lpfc_nvmet_rcv_ctx {
 #define LPFC_NVMET_STE_RSP		4
 #define LPFC_NVMET_STE_DONE		5
 	uint16_t flag;
-#define LPFC_NVMET_IO_INP		1
-#define LPFC_NVMET_ABORT_OP		2
+#define LPFC_NVMET_IO_INP		0x1  /* IO is in progress on exchange */
+#define LPFC_NVMET_ABORT_OP		0x2  /* Abort WQE issued on exchange */
+#define LPFC_NVMET_XBUSY		0x4  /* XB bit set on IO cmpl */
+#define LPFC_NVMET_CTX_RLS		0x8  /* ctx free requested */
+#define LPFC_NVMET_ABTS_RCV		0x10  /* ABTS received on exchange */
 	struct rqb_dmabuf *rqb_buffer;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 9d6384af9fce..54fd0c81ceaf 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5953,12 +5953,13 @@ struct scsi_host_template lpfc_template_nvme = {
 	.track_queue_depth	= 0,
 };
 
-struct scsi_host_template lpfc_template_s3 = {
+struct scsi_host_template lpfc_template_no_hr = {
 	.module			= THIS_MODULE,
 	.name			= LPFC_DRIVER_NAME,
 	.proc_name		= LPFC_DRIVER_NAME,
 	.info			= lpfc_info,
 	.queuecommand		= lpfc_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= lpfc_abort_handler,
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
@@ -6015,7 +6016,6 @@ struct scsi_host_template lpfc_vport_template = {
 	.eh_abort_handler	= lpfc_abort_handler,
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
-	.eh_bus_reset_handler	= lpfc_bus_reset_handler,
 	.slave_alloc		= lpfc_slave_alloc,
 	.slave_configure	= lpfc_slave_configure,
 	.slave_destroy		= lpfc_slave_destroy,
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index e43e5e23c24b..cf19f4976f5f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1,3 +1,4 @@
+
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
@@ -952,7 +953,7 @@ __lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 	start_sglq = sglq;
 	while (!found) {
 		if (!sglq)
-			return NULL;
+			break;
 		if (ndlp && ndlp->active_rrqs_xri_bitmap &&
 		    test_bit(sglq->sli4_lxritag,
 		    ndlp->active_rrqs_xri_bitmap)) {
@@ -6337,7 +6338,7 @@ lpfc_sli4_get_allocated_extnts(struct lpfc_hba *phba, uint16_t type,
 }
 
 /**
- * lpfc_sli4_repost_sgl_list - Repsot the buffers sgl pages as block
+ * lpfc_sli4_repost_sgl_list - Repost the buffers sgl pages as block
  * @phba: pointer to lpfc hba data structure.
  * @pring: Pointer to driver SLI ring object.
  * @sgl_list: linked link of sgl buffers to post
@@ -12213,6 +12214,41 @@ void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *phba)
 }
 
 /**
+ * lpfc_sli4_nvme_xri_abort_event_proc - Process nvme xri abort event
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked by the worker thread to process all the pending
+ * SLI4 NVME abort XRI events.
+ **/
+void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba)
+{
+	struct lpfc_cq_event *cq_event;
+
+	/* First, declare the fcp xri abort event has been handled */
+	spin_lock_irq(&phba->hbalock);
+	phba->hba_flag &= ~NVME_XRI_ABORT_EVENT;
+	spin_unlock_irq(&phba->hbalock);
+	/* Now, handle all the fcp xri abort events */
+	while (!list_empty(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue)) {
+		/* Get the first event from the head of the event queue */
+		spin_lock_irq(&phba->hbalock);
+		list_remove_head(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue,
+				 cq_event, struct lpfc_cq_event, list);
+		spin_unlock_irq(&phba->hbalock);
+		/* Notify aborted XRI for NVME work queue */
+		if (phba->nvmet_support) {
+			lpfc_sli4_nvmet_xri_aborted(phba,
+						    &cq_event->cqe.wcqe_axri);
+		} else {
+			lpfc_sli4_nvme_xri_aborted(phba,
+						   &cq_event->cqe.wcqe_axri);
+		}
+		/* Free the event processed back to the free pool */
+		lpfc_sli4_cq_event_release(phba, cq_event);
+	}
+}
+
+/**
  * lpfc_sli4_els_xri_abort_event_proc - Process els xri abort event
  * @phba: pointer to lpfc hba data structure.
  *
@@ -12709,10 +12745,22 @@ lpfc_sli4_sp_handle_abort_xri_wcqe(struct lpfc_hba *phba,
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		workposted = true;
 		break;
+	case LPFC_NVME:
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		list_add_tail(&cq_event->list,
+			      &phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
+		/* Set the nvme xri abort event flag */
+		phba->hba_flag |= NVME_XRI_ABORT_EVENT;
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+		workposted = true;
+		break;
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-				"0603 Invalid work queue CQE subtype (x%x)\n",
-				cq->subtype);
+				"0603 Invalid CQ subtype %d: "
+				"%08x %08x %08x %08x\n",
+				cq->subtype, wcqe->word0, wcqe->parameter,
+				wcqe->word2, wcqe->word3);
+		lpfc_sli4_cq_event_release(phba, cq_event);
 		workposted = false;
 		break;
 	}
@@ -13710,7 +13758,10 @@ lpfc_sli4_queue_free(struct lpfc_queue *queue)
 		lpfc_free_rq_buffer(queue->phba, queue);
 		kfree(queue->rqbp);
 	}
-	kfree(queue->pring);
+
+	if (!list_empty(&queue->wq_list))
+		list_del(&queue->wq_list);
+
 	kfree(queue);
 	return;
 }
@@ -13827,6 +13878,8 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
  * @startq: The starting FCP EQ to modify
  *
  * This function sends an MODIFY_EQ_DELAY mailbox command to the HBA.
+ * The command allows up to LPFC_MAX_EQ_DELAY_EQID_CNT EQ ID's to be
+ * updated in one mailbox command.
  *
  * The @phba struct is used to send mailbox command to HBA. The @startq
  * is used to get the starting FCP EQ to change.
@@ -13879,7 +13932,7 @@ lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq)
 		eq_delay->u.request.eq[cnt].phase = 0;
 		eq_delay->u.request.eq[cnt].delay_multi = dmult;
 		cnt++;
-		if (cnt >= LPFC_MAX_EQ_DELAY)
+		if (cnt >= LPFC_MAX_EQ_DELAY_EQID_CNT)
 			break;
 	}
 	eq_delay->u.request.num_eq = cnt;
@@ -14688,6 +14741,9 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 	case LPFC_Q_CREATE_VERSION_1:
 		bf_set(lpfc_mbx_wq_create_wqe_count, &wq_create->u.request_1,
 		       wq->entry_count);
+		bf_set(lpfc_mbox_hdr_version, &shdr->request,
+		       LPFC_Q_CREATE_VERSION_1);
+
 		switch (wq->entry_size) {
 		default:
 		case 64:
@@ -15185,17 +15241,17 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 		drq = drqp[idx];
 		cq  = cqp[idx];
 
-		if (hrq->entry_count != drq->entry_count) {
-			status = -EINVAL;
-			goto out;
-		}
-
 		/* sanity check on queue memory */
 		if (!hrq || !drq || !cq) {
 			status = -ENODEV;
 			goto out;
 		}
 
+		if (hrq->entry_count != drq->entry_count) {
+			status = -EINVAL;
+			goto out;
+		}
+
 		if (idx == 0) {
 			bf_set(lpfc_mbx_rq_create_num_pages,
 			       &rq_create->u.request,
@@ -15511,6 +15567,8 @@ lpfc_wq_destroy(struct lpfc_hba *phba, struct lpfc_queue *wq)
 	}
 	/* Remove wq from any list */
 	list_del_init(&wq->list);
+	kfree(wq->pring);
+	wq->pring = NULL;
 	mempool_free(mbox, wq->phba->mbox_mem_pool);
 	return status;
 }
@@ -16463,7 +16521,7 @@ lpfc_sli4_xri_inrange(struct lpfc_hba *phba,
  * This function sends a basic response to a previous unsol sequence abort
  * event after aborting the sequence handling.
  **/
-static void
+void
 lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
 			struct fc_frame_header *fc_hdr, bool aborted)
 {
@@ -16484,14 +16542,13 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
 
 	ndlp = lpfc_findnode_did(vport, sid);
 	if (!ndlp) {
-		ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+		ndlp = lpfc_nlp_init(vport, sid);
 		if (!ndlp) {
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS,
 					 "1268 Failed to allocate ndlp for "
 					 "oxid:x%x SID:x%x\n", oxid, sid);
 			return;
 		}
-		lpfc_nlp_init(vport, ndlp, sid);
 		/* Put ndlp onto pport node list */
 		lpfc_enqueue_node(vport, ndlp);
 	} else if (!NLP_CHK_NODE_ACT(ndlp)) {
@@ -16640,6 +16697,11 @@ lpfc_sli4_handle_unsol_abort(struct lpfc_vport *vport,
 	}
 	lpfc_in_buf_free(phba, &dmabuf->dbuf);
 
+	if (phba->nvmet_support) {
+		lpfc_nvmet_rcv_unsol_abort(vport, &fc_hdr);
+		return;
+	}
+
 	/* Respond with BA_ACC or BA_RJT accordingly */
 	lpfc_sli4_seq_abort_rsp(vport, &fc_hdr, aborted);
 }
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 91153c9f6d18..da46471337c8 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -620,7 +620,7 @@ struct lpfc_sli4_hba {
 	struct list_head lpfc_els_sgl_list;
 	struct list_head lpfc_abts_els_sgl_list;
 	struct list_head lpfc_nvmet_sgl_list;
-	struct list_head lpfc_abts_nvmet_sgl_list;
+	struct list_head lpfc_abts_nvmet_ctx_list;
 	struct list_head lpfc_abts_scsi_buf_list;
 	struct list_head lpfc_abts_nvme_buf_list;
 	struct lpfc_sglq **lpfc_sglq_active_list;
@@ -642,6 +642,7 @@ struct lpfc_sli4_hba {
 	struct list_head sp_asynce_work_queue;
 	struct list_head sp_fcp_xri_aborted_work_queue;
 	struct list_head sp_els_xri_aborted_work_queue;
+	struct list_head sp_nvme_xri_aborted_work_queue;
 	struct list_head sp_unsol_work_queue;
 	struct lpfc_sli4_link link_state;
 	struct lpfc_sli4_lnk_info lnk_info;
@@ -794,9 +795,14 @@ void lpfc_sli4_fcf_redisc_event_proc(struct lpfc_hba *);
 int lpfc_sli4_resume_rpi(struct lpfc_nodelist *,
 			void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *);
 void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *);
+void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba);
 void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *);
 void lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *,
 			       struct sli4_wcqe_xri_aborted *);
+void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
+				struct sli4_wcqe_xri_aborted *axri);
+void lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
+				 struct sli4_wcqe_xri_aborted *axri);
 void lpfc_sli4_els_xri_aborted(struct lpfc_hba *,
 			       struct sli4_wcqe_xri_aborted *);
 void lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *);
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 86c6c9b26b82..1c26dc67151b 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.7"
+#define LPFC_DRIVER_VERSION "11.2.0.12"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 9a0339dbc024..c714482bf4c5 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -738,10 +738,9 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
 		ndlp = lpfc_findnode_did(vport, Fabric_DID);
 		if (!ndlp) {
 			/* Cannot find existing Fabric ndlp, allocate one */
-			ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+			ndlp = lpfc_nlp_init(vport, Fabric_DID);
 			if (!ndlp)
 				goto skip_logo;
-			lpfc_nlp_init(vport, ndlp, Fabric_DID);
 			/* Indicate free memory when release */
 			NLP_SET_FREE_REQ(ndlp);
 		} else {
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index e7e5974e1a2c..2b209bbb4c91 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"07.701.16.00-rc1"
-#define MEGASAS_RELDATE				"February 2, 2017"
+#define MEGASAS_VERSION				"07.701.17.00-rc1"
+#define MEGASAS_RELDATE				"March 2, 2017"
 
 /*
  * Device IDs
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 7ac9a9ee9bd4..0016f12cc563 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1963,6 +1963,9 @@ scan_target:
 	if (!mr_device_priv_data)
 		return -ENOMEM;
 	sdev->hostdata = mr_device_priv_data;
+
+	atomic_set(&mr_device_priv_data->r1_ldio_hint,
+		   instance->r1_ldio_hint_default);
 	return 0;
 }
 
@@ -5034,10 +5037,12 @@ megasas_setup_irqs_msix(struct megasas_instance *instance, u8 is_probe)
 					 &instance->irq_context[j]);
 			/* Retry irq register for IO_APIC*/
 			instance->msix_vectors = 0;
-			if (is_probe)
+			if (is_probe) {
+				pci_free_irq_vectors(instance->pdev);
 				return megasas_setup_irqs_ioapic(instance);
-			else
+			} else {
 				return -1;
+			}
 		}
 	}
 	return 0;
@@ -5277,9 +5282,11 @@ static int megasas_init_fw(struct megasas_instance *instance)
 			MPI2_REPLY_POST_HOST_INDEX_OFFSET);
 	}
 
-	i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
-	if (i < 0)
-		goto fail_setup_irqs;
+	if (!instance->msix_vectors) {
+		i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
+		if (i < 0)
+			goto fail_setup_irqs;
+	}
 
 	dev_info(&instance->pdev->dev,
 		"firmware supports msix\t: (%d)", fw_msix_count);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 29650ba669da..f990ab4d45e1 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2159,7 +2159,7 @@ megasas_set_raidflag_cpu_affinity(union RAID_CONTEXT_UNION *praid_context,
 				cpu_sel = MR_RAID_CTX_CPUSEL_1;
 
 			if (is_stream_detected(rctx_g35) &&
-			    (raid->level == 5) &&
+			    ((raid->level == 5) || (raid->level == 6)) &&
 			    (raid->writeMode == MR_RL_WRITE_THROUGH_MODE) &&
 			    (cpu_sel == MR_RAID_CTX_CPUSEL_FCFS))
 				cpu_sel = MR_RAID_CTX_CPUSEL_0;
@@ -2338,7 +2338,7 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 				fp_possible = false;
 				atomic_dec(&instance->fw_outstanding);
 			} else if ((scsi_buff_len > MR_LARGE_IO_MIN_SIZE) ||
-				   atomic_dec_if_positive(&mrdev_priv->r1_ldio_hint)) {
+				   (atomic_dec_if_positive(&mrdev_priv->r1_ldio_hint) > 0)) {
 				fp_possible = false;
 				atomic_dec(&instance->fw_outstanding);
 				if (scsi_buff_len > MR_LARGE_IO_MIN_SIZE)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 7fe7e6ed595b..8981806fb13f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1442,9 +1442,6 @@ void mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc,
 	u64 sas_address, u16 handle, u8 phy_number, u8 link_rate);
 extern struct sas_function_template mpt3sas_transport_functions;
 extern struct scsi_transport_template *mpt3sas_transport_template;
-extern int scsi_internal_device_block(struct scsi_device *sdev);
-extern int scsi_internal_device_unblock(struct scsi_device *sdev,
-				enum scsi_device_state new_state);
 /* trigger data externs */
 void mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
 	struct SL_WH_TRIGGERS_EVENT_DATA_T *event_data);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 46e866c36c8a..919ba2bb15f1 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2859,7 +2859,7 @@ _scsih_internal_device_block(struct scsi_device *sdev,
 	    sas_device_priv_data->sas_target->handle);
 	sas_device_priv_data->block = 1;
 
-	r = scsi_internal_device_block(sdev);
+	r = scsi_internal_device_block(sdev, false);
 	if (r == -EINVAL)
 		sdev_printk(KERN_WARNING, sdev,
 		    "device_block failed with return(%d) for handle(0x%04x)\n",
@@ -2895,7 +2895,7 @@ _scsih_internal_device_unblock(struct scsi_device *sdev,
 		    "performing a block followed by an unblock\n",
 		    r, sas_device_priv_data->sas_target->handle);
 		sas_device_priv_data->block = 1;
-		r = scsi_internal_device_block(sdev);
+		r = scsi_internal_device_block(sdev, false);
 		if (r)
 			sdev_printk(KERN_WARNING, sdev, "retried device_block "
 			    "failed with return(%d) for handle(0x%04x)\n",
@@ -4677,7 +4677,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
-	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 
@@ -4742,20 +4741,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
-
-	/* In case of bogus fw or device, we could end up having
-	 * unaligned partial completion. We can force alignment here,
-	 * then scsi-ml does not need to handle this misbehavior.
-	 */
-	sector_sz = scmd->device->sector_size;
-	if (unlikely(!blk_rq_is_passthrough(scmd->request) && sector_sz &&
-		     xfer_cnt % sector_sz)) {
-		sdev_printk(KERN_INFO, scmd->device,
-		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
-			    xfer_cnt, sector_sz);
-		xfer_cnt = round_down(xfer_cnt, sector_sz);
-	}
-
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 6903f03c88af..8a1b94816419 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -477,7 +477,7 @@ static void _set_error_resid(struct osd_request *or, struct request *req,
 			     int error)
 {
 	or->async_error = error;
-	or->req_errors = req->errors ? : error;
+	or->req_errors = scsi_req(req)->result ? : error;
 	or->sense_len = scsi_req(req)->sense_len;
 	if (or->sense_len)
 		memcpy(or->sense, scsi_req(req)->sense, or->sense_len);
@@ -489,7 +489,10 @@ static void _set_error_resid(struct osd_request *or, struct request *req,
 
 int osd_execute_request(struct osd_request *or)
 {
-	int error = blk_execute_rq(or->request->q, NULL, or->request, 0);
+	int error;
+
+	blk_execute_rq(or->request->q, NULL, or->request, 0);
+	error = scsi_req(or->request)->result ? -EIO : 0;
 
 	_set_error_resid(or, or->request, error);
 	return error;
@@ -1602,7 +1605,7 @@ static int _init_blk_request(struct osd_request *or,
 	req->rq_flags |= RQF_QUIET;
 
 	req->timeout = or->timeout;
-	req->retries = or->retries;
+	scsi_req(req)->retries = or->retries;
 
 	if (has_out) {
 		or->out.req = req;
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index c47f4b349bac..67cbed92f07d 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -327,7 +327,7 @@ static void osst_end_async(struct request *req, int update)
 	struct osst_tape *STp = SRpnt->stp;
 	struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
 
-	STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
+	STp->buffer->cmdstat.midlevel_result = SRpnt->result = rq->result;
 #if DEBUG
 	STp->write_pending = 0;
 #endif
@@ -414,7 +414,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
 	memcpy(rq->cmd, cmd, rq->cmd_len);
 	req->timeout = timeout;
-	req->retries = retries;
+	rq->retries = retries;
 	req->end_io_data = SRpnt;
 
 	blk_execute_rq_nowait(req->q, NULL, req, 1, osst_end_async);
diff --git a/drivers/scsi/qedf/Makefile b/drivers/scsi/qedf/Makefile
index 64e9f507ce32..414f2a772a5f 100644
--- a/drivers/scsi/qedf/Makefile
+++ b/drivers/scsi/qedf/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_QEDF) := qedf.o
 qedf-y = qedf_dbg.o qedf_main.o qedf_io.o qedf_fip.o \
-	 qedf_attr.o qedf_els.o
+	 qedf_attr.o qedf_els.o drv_scsi_fw_funcs.o drv_fcoe_fw_funcs.o
 
 qedf-$(CONFIG_DEBUG_FS) += qedf_debugfs.o
diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c
new file mode 100644
index 000000000000..8c65e3b034dc
--- /dev/null
+++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c
@@ -0,0 +1,190 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#include "drv_fcoe_fw_funcs.h"
+#include "drv_scsi_fw_funcs.h"
+
+#define FCOE_RX_ID (0xFFFFu)
+
+static inline void init_common_sqe(struct fcoe_task_params *task_params,
+				   enum fcoe_sqe_request_type request_type)
+{
+	memset(task_params->sqe, 0, sizeof(*(task_params->sqe)));
+	SET_FIELD(task_params->sqe->flags, FCOE_WQE_REQ_TYPE,
+		  request_type);
+	task_params->sqe->task_id = task_params->itid;
+}
+
+int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params,
+				struct scsi_sgl_task_params *sgl_task_params,
+				struct regpair sense_data_buffer_phys_addr,
+				u32 task_retry_id,
+				u8 fcp_cmd_payload[32])
+{
+	struct fcoe_task_context *ctx = task_params->context;
+	struct ystorm_fcoe_task_st_ctx *y_st_ctx;
+	struct tstorm_fcoe_task_st_ctx *t_st_ctx;
+	struct ustorm_fcoe_task_ag_ctx *u_ag_ctx;
+	struct mstorm_fcoe_task_st_ctx *m_st_ctx;
+	u32 io_size, val;
+	bool slow_sgl;
+
+	memset(ctx, 0, sizeof(*(ctx)));
+	slow_sgl = scsi_is_slow_sgl(sgl_task_params->num_sges,
+				    sgl_task_params->small_mid_sge);
+	io_size = (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR ?
+		   task_params->tx_io_size : task_params->rx_io_size);
+
+	/* Ystorm ctx */
+	y_st_ctx = &ctx->ystorm_st_context;
+	y_st_ctx->data_2_trns_rem = cpu_to_le32(io_size);
+	y_st_ctx->task_rety_identifier = cpu_to_le32(task_retry_id);
+	y_st_ctx->task_type = task_params->task_type;
+	memcpy(&y_st_ctx->tx_info_union.fcp_cmd_payload,
+	       fcp_cmd_payload, sizeof(struct fcoe_fcp_cmd_payload));
+
+	/* Tstorm ctx */
+	t_st_ctx = &ctx->tstorm_st_context;
+	t_st_ctx->read_only.dev_type = (task_params->is_tape_device == 1 ?
+					FCOE_TASK_DEV_TYPE_TAPE :
+					FCOE_TASK_DEV_TYPE_DISK);
+	t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid);
+	val = cpu_to_le32(task_params->cq_rss_number);
+	t_st_ctx->read_only.glbl_q_num = val;
+	t_st_ctx->read_only.fcp_cmd_trns_size = cpu_to_le32(io_size);
+	t_st_ctx->read_only.task_type = task_params->task_type;
+	SET_FIELD(t_st_ctx->read_write.flags,
+		  FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1);
+	t_st_ctx->read_write.rx_id = cpu_to_le16(FCOE_RX_ID);
+
+	/* Ustorm ctx */
+	u_ag_ctx = &ctx->ustorm_ag_context;
+	u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number);
+
+	/* Mstorm buffer for sense/rsp data placement */
+	m_st_ctx = &ctx->mstorm_st_context;
+	val = cpu_to_le32(sense_data_buffer_phys_addr.hi);
+	m_st_ctx->rsp_buf_addr.hi = val;
+	val = cpu_to_le32(sense_data_buffer_phys_addr.lo);
+	m_st_ctx->rsp_buf_addr.lo = val;
+
+	if (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
+		/* Ystorm ctx */
+		y_st_ctx->expect_first_xfer = 1;
+
+		/* Set the amount of super SGEs. Can be up to 4. */
+		SET_FIELD(y_st_ctx->sgl_mode,
+			  YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+			  (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+		init_scsi_sgl_context(&y_st_ctx->sgl_params,
+				      &y_st_ctx->data_desc,
+				      sgl_task_params);
+
+		/* Mstorm ctx */
+		SET_FIELD(m_st_ctx->flags,
+			  MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+			  (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+	} else {
+		/* Tstorm ctx */
+		SET_FIELD(t_st_ctx->read_write.flags,
+			  FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
+			  (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+
+		/* Mstorm ctx */
+		m_st_ctx->data_2_trns_rem = cpu_to_le32(io_size);
+		init_scsi_sgl_context(&m_st_ctx->sgl_params,
+				      &m_st_ctx->data_desc,
+				      sgl_task_params);
+	}
+
+	init_common_sqe(task_params, SEND_FCOE_CMD);
+	return 0;
+}
+
+int init_initiator_midpath_unsolicited_fcoe_task(
+	struct fcoe_task_params *task_params,
+	struct fcoe_tx_mid_path_params *mid_path_fc_header,
+	struct scsi_sgl_task_params *tx_sgl_task_params,
+	struct scsi_sgl_task_params *rx_sgl_task_params,
+	u8 fw_to_place_fc_header)
+{
+	struct fcoe_task_context *ctx = task_params->context;
+	struct ystorm_fcoe_task_st_ctx *y_st_ctx;
+	struct tstorm_fcoe_task_st_ctx *t_st_ctx;
+	struct ustorm_fcoe_task_ag_ctx *u_ag_ctx;
+	struct mstorm_fcoe_task_st_ctx *m_st_ctx;
+	u32 val;
+
+	memset(ctx, 0, sizeof(*(ctx)));
+
+	/* Init Ystorm */
+	y_st_ctx = &ctx->ystorm_st_context;
+	init_scsi_sgl_context(&y_st_ctx->sgl_params,
+			      &y_st_ctx->data_desc,
+			      tx_sgl_task_params);
+	SET_FIELD(y_st_ctx->sgl_mode,
+		  YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, SCSI_FAST_SGL);
+	y_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->tx_io_size);
+	y_st_ctx->task_type = task_params->task_type;
+	memcpy(&y_st_ctx->tx_info_union.tx_params.mid_path,
+	       mid_path_fc_header, sizeof(struct fcoe_tx_mid_path_params));
+
+	/* Init Mstorm */
+	m_st_ctx = &ctx->mstorm_st_context;
+	init_scsi_sgl_context(&m_st_ctx->sgl_params,
+			      &m_st_ctx->data_desc,
+			      rx_sgl_task_params);
+	SET_FIELD(m_st_ctx->flags,
+		  MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER,
+		  fw_to_place_fc_header);
+	m_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->rx_io_size);
+
+	/* Init Tstorm */
+	t_st_ctx = &ctx->tstorm_st_context;
+	t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid);
+	val = cpu_to_le32(task_params->cq_rss_number);
+	t_st_ctx->read_only.glbl_q_num = val;
+	t_st_ctx->read_only.task_type = task_params->task_type;
+	SET_FIELD(t_st_ctx->read_write.flags,
+		  FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1);
+	t_st_ctx->read_write.rx_id = cpu_to_le16(FCOE_RX_ID);
+
+	/* Init Ustorm */
+	u_ag_ctx = &ctx->ustorm_ag_context;
+	u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number);
+
+	/* Init SQE */
+	init_common_sqe(task_params, SEND_FCOE_MIDPATH);
+	task_params->sqe->additional_info_union.burst_length =
+				    tx_sgl_task_params->total_buffer_size;
+	SET_FIELD(task_params->sqe->flags,
+		  FCOE_WQE_NUM_SGES, tx_sgl_task_params->num_sges);
+	SET_FIELD(task_params->sqe->flags, FCOE_WQE_SGL_MODE,
+		  SCSI_FAST_SGL);
+
+	return 0;
+}
+
+int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params)
+{
+	init_common_sqe(task_params, SEND_FCOE_ABTS_REQUEST);
+	return 0;
+}
+
+int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params)
+{
+	init_common_sqe(task_params, FCOE_EXCHANGE_CLEANUP);
+	return 0;
+}
+
+int init_initiator_sequence_recovery_fcoe_task(
+	struct fcoe_task_params *task_params, u32 off)
+{
+	init_common_sqe(task_params, FCOE_SEQUENCE_RECOVERY);
+	task_params->sqe->additional_info_union.seq_rec_updated_offset = off;
+	return 0;
+}
diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h
new file mode 100644
index 000000000000..617529b058f4
--- /dev/null
+++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h
@@ -0,0 +1,93 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#ifndef _FCOE_FW_FUNCS_H
+#define _FCOE_FW_FUNCS_H
+#include "drv_scsi_fw_funcs.h"
+#include "qedf_hsi.h"
+#include <linux/qed/qed_if.h>
+
+struct fcoe_task_params {
+	/* Output parameter [set/filled by the HSI function] */
+	struct fcoe_task_context *context;
+
+	/* Output parameter [set/filled by the HSI function] */
+	struct fcoe_wqe *sqe;
+	enum fcoe_task_type task_type;
+	u32 tx_io_size; /* in bytes */
+	u32 rx_io_size; /* in bytes */
+	u32 conn_cid;
+	u16 itid;
+	u8 cq_rss_number;
+
+	 /* Whether it's Tape device or not (0=Disk, 1=Tape) */
+	u8 is_tape_device;
+};
+
+/**
+ * @brief init_initiator_rw_fcoe_task - Initializes FCoE task context for
+ * read/write task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param sgl_task_params - Pointer to SGL task params
+ * @param sense_data_buffer_phys_addr - Pointer to sense data buffer
+ * @param task_retry_id - retry identification - Used only for Tape device
+ * @param fcp_cmnd_payload - FCP CMD Payload
+ */
+int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params,
+	struct scsi_sgl_task_params *sgl_task_params,
+	struct regpair sense_data_buffer_phys_addr,
+	u32 task_retry_id,
+	u8 fcp_cmd_payload[32]);
+
+/**
+ * @brief init_initiator_midpath_fcoe_task - Initializes FCoE task context for
+ * midpath/unsolicited task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param mid_path_fc_header - FC header
+ * @param tx_sgl_task_params - Pointer to Tx SGL task params
+ * @param rx_sgl_task_params - Pointer to Rx SGL task params
+ * @param fw_to_place_fc_header	- Indication if the FW will place the FC header
+ * in addition to the data arrives.
+ */
+int init_initiator_midpath_unsolicited_fcoe_task(
+	struct fcoe_task_params *task_params,
+	struct fcoe_tx_mid_path_params *mid_path_fc_header,
+	struct scsi_sgl_task_params *tx_sgl_task_params,
+	struct scsi_sgl_task_params *rx_sgl_task_params,
+	u8 fw_to_place_fc_header);
+
+/**
+ * @brief init_initiator_abort_fcoe_task - Initializes FCoE task context for
+ * abort task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params);
+
+/**
+ * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for
+ * cleanup task types and init fcoe_sqe
+ *
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params);
+
+/**
+ * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for
+ * sequence recovery task types and init fcoe_sqe
+ *
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param desired_offset - The desired offest the task will be re-sent from
+ */
+int init_initiator_sequence_recovery_fcoe_task(
+	struct fcoe_task_params *task_params,
+	u32 desired_offset);
+#endif
diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.c b/drivers/scsi/qedf/drv_scsi_fw_funcs.c
new file mode 100644
index 000000000000..11e0cc082ec0
--- /dev/null
+++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.c
@@ -0,0 +1,44 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#include "drv_scsi_fw_funcs.h"
+
+#define SCSI_NUM_SGES_IN_CACHE 0x4
+
+bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge)
+{
+	return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge);
+}
+
+void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params,
+			   struct scsi_cached_sges *ctx_data_desc,
+			   struct scsi_sgl_task_params *sgl_task_params)
+{
+	/* no need to check for sgl_task_params->sgl validity */
+	u8 num_sges_to_init = sgl_task_params->num_sges >
+			      SCSI_NUM_SGES_IN_CACHE ? SCSI_NUM_SGES_IN_CACHE :
+			      sgl_task_params->num_sges;
+	u8 sge_index;
+	u32 val;
+
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo);
+	ctx_sgl_params->sgl_addr.lo = val;
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi);
+	ctx_sgl_params->sgl_addr.hi = val;
+	val = cpu_to_le32(sgl_task_params->total_buffer_size);
+	ctx_sgl_params->sgl_total_length = val;
+	ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges);
+
+	for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) {
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo);
+		ctx_data_desc->sge[sge_index].sge_addr.lo = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi);
+		ctx_data_desc->sge[sge_index].sge_addr.hi = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len);
+		ctx_data_desc->sge[sge_index].sge_len = val;
+	}
+}
diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.h b/drivers/scsi/qedf/drv_scsi_fw_funcs.h
new file mode 100644
index 000000000000..9cb45410bc45
--- /dev/null
+++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.h
@@ -0,0 +1,85 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#ifndef _SCSI_FW_FUNCS_H
+#define _SCSI_FW_FUNCS_H
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/storage_common.h>
+#include <linux/qed/fcoe_common.h>
+
+struct scsi_sgl_task_params {
+	struct scsi_sge *sgl;
+	struct regpair sgl_phys_addr;
+	u32 total_buffer_size;
+	u16 num_sges;
+
+	 /* true if SGL contains a small (< 4KB) SGE in middle(not 1st or last)
+	  * -> relevant for tx only
+	  */
+	bool small_mid_sge;
+};
+
+struct scsi_dif_task_params {
+	u32 initial_ref_tag;
+	bool initial_ref_tag_is_valid;
+	u16 application_tag;
+	u16 application_tag_mask;
+	u16 dif_block_size_log;
+	bool dif_on_network;
+	bool dif_on_host;
+	u8 host_guard_type;
+	u8 protection_type;
+	u8 ref_tag_mask;
+	bool crc_seed;
+
+	 /* Enable Connection error upon DIF error (segments with DIF errors are
+	  * dropped)
+	  */
+	bool tx_dif_conn_err_en;
+	bool ignore_app_tag;
+	bool keep_ref_tag_const;
+	bool validate_guard;
+	bool validate_app_tag;
+	bool validate_ref_tag;
+	bool forward_guard;
+	bool forward_app_tag;
+	bool forward_ref_tag;
+	bool forward_app_tag_with_mask;
+	bool forward_ref_tag_with_mask;
+};
+
+struct scsi_initiator_cmd_params {
+	 /* for cdb_size > default CDB size (extended CDB > 16 bytes) ->
+	  * pointer to the CDB buffer SGE
+	  */
+	struct scsi_sge extended_cdb_sge;
+
+	/* Physical address of sense data buffer for sense data - 256B buffer */
+	struct regpair sense_data_buffer_phys_addr;
+};
+
+/**
+ * @brief scsi_is_slow_sgl - checks for slow SGL
+ *
+ * @param num_sges - number of sges in SGL
+ * @param small_mid_sge - True is the SGL contains an SGE which is smaller than
+ * 4KB and its not the 1st or last SGE in the SGL
+ */
+bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge);
+
+/**
+ * @brief init_scsi_sgl_context - initializes SGL task context
+ *
+ * @param sgl_params - SGL context parameters to initialize (output parameter)
+ * @param data_desc - context struct containing SGEs array to set (output
+ * parameter)
+ * @param sgl_task_params - SGL parameters (input)
+ */
+void init_scsi_sgl_context(struct scsi_sgl_params *sgl_params,
+	struct scsi_cached_sges *ctx_data_desc,
+	struct scsi_sgl_task_params *sgl_task_params);
+#endif
diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
index 96346a1b1515..40aeb6bb96a2 100644
--- a/drivers/scsi/qedf/qedf.h
+++ b/drivers/scsi/qedf/qedf.h
@@ -26,6 +26,7 @@
 #include <linux/qed/qed_ll2_if.h>
 #include "qedf_version.h"
 #include "qedf_dbg.h"
+#include "drv_fcoe_fw_funcs.h"
 
 /* Helpers to extract upper and lower 32-bits of pointer */
 #define U64_HI(val) ((u32)(((u64)(val)) >> 32))
@@ -59,19 +60,17 @@
 #define UPSTREAM_KEEP		1
 
 struct qedf_mp_req {
-	uint8_t tm_flags;
-
 	uint32_t req_len;
 	void *req_buf;
 	dma_addr_t req_buf_dma;
-	struct fcoe_sge *mp_req_bd;
+	struct scsi_sge *mp_req_bd;
 	dma_addr_t mp_req_bd_dma;
 	struct fc_frame_header req_fc_hdr;
 
 	uint32_t resp_len;
 	void *resp_buf;
 	dma_addr_t resp_buf_dma;
-	struct fcoe_sge *mp_resp_bd;
+	struct scsi_sge *mp_resp_bd;
 	dma_addr_t mp_resp_bd_dma;
 	struct fc_frame_header resp_fc_hdr;
 };
@@ -119,6 +118,7 @@ struct qedf_ioreq {
 #define QEDF_CMD_IN_CLEANUP		0x2
 #define QEDF_CMD_SRR_SENT		0x3
 	u8 io_req_flags;
+	uint8_t tm_flags;
 	struct qedf_rport *fcport;
 	unsigned long flags;
 	enum qedf_ioreq_event event;
@@ -130,6 +130,8 @@ struct qedf_ioreq {
 	struct completion tm_done;
 	struct completion abts_done;
 	struct fcoe_task_context *task;
+	struct fcoe_task_params *task_params;
+	struct scsi_sgl_task_params *sgl_task_params;
 	int idx;
 /*
  * Need to allocate enough room for both sense data and FCP response data
@@ -199,8 +201,8 @@ struct qedf_rport {
 	dma_addr_t sq_pbl_dma;
 	u32 sq_pbl_size;
 	u32 sid;
-#define	QEDF_RPORT_TYPE_DISK		1
-#define	QEDF_RPORT_TYPE_TAPE		2
+#define	QEDF_RPORT_TYPE_DISK		0
+#define	QEDF_RPORT_TYPE_TAPE		1
 	uint dev_type; /* Disk or tape */
 	struct list_head peers;
 };
@@ -391,7 +393,7 @@ struct qedf_ctx {
 
 struct io_bdt {
 	struct qedf_ioreq *io_req;
-	struct fcoe_sge *bd_tbl;
+	struct scsi_sge *bd_tbl;
 	dma_addr_t bd_tbl_dma;
 	u16 bd_valid;
 };
@@ -400,7 +402,7 @@ struct qedf_cmd_mgr {
 	struct qedf_ctx *qedf;
 	u16 idx;
 	struct io_bdt **io_bdt_pool;
-#define FCOE_PARAMS_NUM_TASKS		4096
+#define FCOE_PARAMS_NUM_TASKS		2048
 	struct qedf_ioreq cmds[FCOE_PARAMS_NUM_TASKS];
 	spinlock_t lock;
 	atomic_t free_list_cnt;
@@ -465,9 +467,8 @@ extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
 	unsigned int timer_msec);
 extern int qedf_init_mp_req(struct qedf_ioreq *io_req);
 extern void qedf_init_mp_task(struct qedf_ioreq *io_req,
-	struct fcoe_task_context *task_ctx);
-extern void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid,
-	u32 ptu_invalidate, enum fcoe_task_type req_type, u32 offset);
+	struct fcoe_task_context *task_ctx, struct fcoe_wqe *wqe);
+extern u16 qedf_get_sqe_idx(struct qedf_rport *fcport);
 extern void qedf_ring_doorbell(struct qedf_rport *fcport);
 extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 	struct qedf_ioreq *els_req);
diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h
index 23bd70628a2f..7d173f48a81e 100644
--- a/drivers/scsi/qedf/qedf_dbg.h
+++ b/drivers/scsi/qedf/qedf_dbg.h
@@ -81,14 +81,17 @@ struct qedf_dbg_ctx {
 #define QEDF_INFO(pdev, level, fmt, ...)	\
 		qedf_dbg_info(pdev, __func__, __LINE__, level, fmt,	\
 			      ## __VA_ARGS__)
-
-extern void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(4, 5)
+void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
 			  const char *fmt, ...);
-extern void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(4, 5)
+void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
 			   const char *, ...);
-extern void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
+__printf(4, 5)
+void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
 			    u32 line, const char *, ...);
-extern void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(5, 6)
+void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
 			  u32 info, const char *fmt, ...);
 
 /* GRC Dump related defines */
diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c
index 59f3e5c73a13..c505d41f6dc8 100644
--- a/drivers/scsi/qedf/qedf_els.c
+++ b/drivers/scsi/qedf/qedf_els.c
@@ -25,6 +25,9 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op,
 	uint16_t xid;
 	uint32_t start_time = jiffies / HZ;
 	uint32_t current_time;
+	struct fcoe_wqe *sqe;
+	unsigned long flags;
+	u16 sqe_idx;
 
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending ELS\n");
 
@@ -113,20 +116,25 @@ retry_els:
 	/* Obtain exchange id */
 	xid = els_req->xid;
 
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+
 	/* Initialize task context for this IO request */
 	task = qedf_get_task_mem(&qedf->tasks, xid);
-	qedf_init_mp_task(els_req, task);
+	qedf_init_mp_task(els_req, task, sqe);
 
 	/* Put timer on original I/O request */
 	if (timer_msec)
 		qedf_cmd_timer_set(qedf, els_req, timer_msec);
 
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
-
 	/* Ring doorbell */
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Ringing doorbell for ELS "
 		   "req\n");
 	qedf_ring_doorbell(fcport);
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
 els_err:
 	return rc;
 }
@@ -604,6 +612,8 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
 	struct qedf_rport *fcport;
 	unsigned long flags;
 	struct qedf_els_cb_arg *cb_arg;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	fcport = orig_io_req->fcport;
 
@@ -631,8 +641,13 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
 
 	spin_lock_irqsave(&fcport->rport_lock, flags);
 
-	qedf_add_to_sq(fcport, orig_io_req->xid, 0,
-	    FCOE_TASK_TYPE_SEQUENCE_CLEANUP, offset);
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+	orig_io_req->task_params->sqe = sqe;
+
+	init_initiator_sequence_recovery_fcoe_task(orig_io_req->task_params,
+						   offset);
 	qedf_ring_doorbell(fcport);
 
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
diff --git a/drivers/scsi/qedf/qedf_fip.c b/drivers/scsi/qedf/qedf_fip.c
index 868d423380d1..e10b91cc3c62 100644
--- a/drivers/scsi/qedf/qedf_fip.c
+++ b/drivers/scsi/qedf/qedf_fip.c
@@ -99,7 +99,8 @@ static void qedf_fcoe_process_vlan_resp(struct qedf_ctx *qedf,
 		qedf_set_vlan_id(qedf, vid);
 
 		/* Inform waiter that it's ok to call fcoe_ctlr_link up() */
-		complete(&qedf->fipvlan_compl);
+		if (!completion_done(&qedf->fipvlan_compl))
+			complete(&qedf->fipvlan_compl);
 	}
 }
 
@@ -203,7 +204,7 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
 			case FIP_DT_MAC:
 				mp = (struct fip_mac_desc *)desc;
 				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
-				    "fd_mac=%pM.\n", __func__, mp->fd_mac);
+				    "fd_mac=%pM\n", mp->fd_mac);
 				ether_addr_copy(cvl_mac, mp->fd_mac);
 				break;
 			case FIP_DT_NAME:
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index ee0dcf9d3aba..1d7f90d0adc1 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -96,7 +96,7 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr)
 	if (!cmgr->io_bdt_pool)
 		goto free_cmd_pool;
 
-	bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge);
+	bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge);
 	for (i = 0; i < num_ios; i++) {
 		bdt_info = cmgr->io_bdt_pool[i];
 		if (bdt_info->bd_tbl) {
@@ -119,6 +119,8 @@ free_cmd_pool:
 
 	for (i = 0; i < num_ios; i++) {
 		io_req = &cmgr->cmds[i];
+		kfree(io_req->sgl_task_params);
+		kfree(io_req->task_params);
 		/* Make sure we free per command sense buffer */
 		if (io_req->sense_buffer)
 			dma_free_coherent(&qedf->pdev->dev,
@@ -178,7 +180,7 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 	spin_lock_init(&cmgr->lock);
 
 	/*
-	 * Initialize list of qedf_ioreq.
+	 * Initialize I/O request fields.
 	 */
 	xid = QEDF_MIN_XID;
 
@@ -196,6 +198,29 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 		    GFP_KERNEL);
 		if (!io_req->sense_buffer)
 			goto mem_err;
+
+		/* Allocate task parameters to pass to f/w init funcions */
+		io_req->task_params = kzalloc(sizeof(*io_req->task_params),
+					      GFP_KERNEL);
+		if (!io_req->task_params) {
+			QEDF_ERR(&(qedf->dbg_ctx),
+				 "Failed to allocate task_params for xid=0x%x\n",
+				 i);
+			goto mem_err;
+		}
+
+		/*
+		 * Allocate scatter/gather list info to pass to f/w init
+		 * functions.
+		 */
+		io_req->sgl_task_params = kzalloc(
+		    sizeof(struct scsi_sgl_task_params), GFP_KERNEL);
+		if (!io_req->sgl_task_params) {
+			QEDF_ERR(&(qedf->dbg_ctx),
+				 "Failed to allocate sgl_task_params for xid=0x%x\n",
+				 i);
+			goto mem_err;
+		}
 	}
 
 	/* Allocate pool of io_bdts - one for each qedf_ioreq */
@@ -211,8 +236,8 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 		cmgr->io_bdt_pool[i] = kmalloc(sizeof(struct io_bdt),
 		    GFP_KERNEL);
 		if (!cmgr->io_bdt_pool[i]) {
-			QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
-				   "io_bdt_pool[%d].\n", i);
+			QEDF_WARN(&(qedf->dbg_ctx),
+				  "Failed to alloc io_bdt_pool[%d].\n", i);
 			goto mem_err;
 		}
 	}
@@ -220,11 +245,11 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 	for (i = 0; i < num_ios; i++) {
 		bdt_info = cmgr->io_bdt_pool[i];
 		bdt_info->bd_tbl = dma_alloc_coherent(&qedf->pdev->dev,
-		    QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge),
+		    QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge),
 		    &bdt_info->bd_tbl_dma, GFP_KERNEL);
 		if (!bdt_info->bd_tbl) {
-			QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
-				   "bdt_tbl[%d].\n", i);
+			QEDF_WARN(&(qedf->dbg_ctx),
+				  "Failed to alloc bdt_tbl[%d].\n", i);
 			goto mem_err;
 		}
 	}
@@ -318,6 +343,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type)
 	}
 	bd_tbl->io_req = io_req;
 	io_req->cmd_type = cmd_type;
+	io_req->tm_flags = 0;
 
 	/* Reset sequence offset data */
 	io_req->rx_buf_off = 0;
@@ -336,10 +362,9 @@ static void qedf_free_mp_resc(struct qedf_ioreq *io_req)
 {
 	struct qedf_mp_req *mp_req = &(io_req->mp_req);
 	struct qedf_ctx *qedf = io_req->fcport->qedf;
-	uint64_t sz = sizeof(struct fcoe_sge);
+	uint64_t sz = sizeof(struct scsi_sge);
 
 	/* clear tm flags */
-	mp_req->tm_flags = 0;
 	if (mp_req->mp_req_bd) {
 		dma_free_coherent(&qedf->pdev->dev, sz,
 		    mp_req->mp_req_bd, mp_req->mp_req_bd_dma);
@@ -387,7 +412,7 @@ void qedf_release_cmd(struct kref *ref)
 static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
 	int bd_index)
 {
-	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
 	int frag_size, sg_frags;
 
 	sg_frags = 0;
@@ -398,7 +423,7 @@ static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
 			frag_size = sg_len;
 		bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr);
 		bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr);
-		bd[bd_index + sg_frags].size = (uint16_t)frag_size;
+		bd[bd_index + sg_frags].sge_len = (uint16_t)frag_size;
 
 		addr += (u64)frag_size;
 		sg_frags++;
@@ -413,7 +438,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 	struct Scsi_Host *host = sc->device->host;
 	struct fc_lport *lport = shost_priv(host);
 	struct qedf_ctx *qedf = lport_priv(lport);
-	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
 	struct scatterlist *sg;
 	int byte_count = 0;
 	int sg_count = 0;
@@ -439,7 +464,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 
 		bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
 		bd[bd_count].sge_addr.hi = (addr >> 32);
-		bd[bd_count].size = (u16)sg_len;
+		bd[bd_count].sge_len = (u16)sg_len;
 
 		return ++bd_count;
 	}
@@ -480,7 +505,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 			sg_frags = 1;
 			bd[bd_count].sge_addr.lo = U64_LO(addr);
 			bd[bd_count].sge_addr.hi  = U64_HI(addr);
-			bd[bd_count].size = (uint16_t)sg_len;
+			bd[bd_count].sge_len = (uint16_t)sg_len;
 		}
 
 		bd_count += sg_frags;
@@ -498,7 +523,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
 {
 	struct scsi_cmnd *sc = io_req->sc_cmd;
-	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
 	int bd_count;
 
 	if (scsi_sg_count(sc)) {
@@ -508,7 +533,7 @@ static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
 	} else {
 		bd_count = 0;
 		bd[0].sge_addr.lo = bd[0].sge_addr.hi = 0;
-		bd[0].size = 0;
+		bd[0].sge_len = 0;
 	}
 	io_req->bd_tbl->bd_valid = bd_count;
 
@@ -529,430 +554,223 @@ static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req,
 
 	/* 4 bytes: flag info */
 	fcp_cmnd->fc_pri_ta = 0;
-	fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags;
+	fcp_cmnd->fc_tm_flags = io_req->tm_flags;
 	fcp_cmnd->fc_flags = io_req->io_req_flags;
 	fcp_cmnd->fc_cmdref = 0;
 
 	/* Populate data direction */
-	if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
-		fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
-	else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+	if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) {
 		fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+	} else {
+		if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
+			fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
+		else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+			fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+	}
 
 	fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
 
 	/* 16 bytes: CDB information */
-	memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
+	if (io_req->cmd_type != QEDF_TASK_MGMT_CMD)
+		memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
 
 	/* 4 bytes: FCP data length */
 	fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len);
-
 }
 
 static void  qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport,
-	struct qedf_ioreq *io_req, u32 *ptu_invalidate,
-	struct fcoe_task_context *task_ctx)
+	struct qedf_ioreq *io_req, struct fcoe_task_context *task_ctx,
+	struct fcoe_wqe *sqe)
 {
 	enum fcoe_task_type task_type;
 	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
 	struct io_bdt *bd_tbl = io_req->bd_tbl;
-	union fcoe_data_desc_ctx *data_desc;
-	u32 *fcp_cmnd;
+	u8 fcp_cmnd[32];
 	u32 tmp_fcp_cmnd[8];
-	int cnt, i;
-	int bd_count;
+	int bd_count = 0;
 	struct qedf_ctx *qedf = fcport->qedf;
 	uint16_t cq_idx = smp_processor_id() % qedf->num_queues;
-	u8 tmp_sgl_mode = 0;
-	u8 mst_sgl_mode = 0;
+	struct regpair sense_data_buffer_phys_addr;
+	u32 tx_io_size = 0;
+	u32 rx_io_size = 0;
+	int i, cnt;
 
-	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	/* Note init_initiator_rw_fcoe_task memsets the task context */
 	io_req->task = task_ctx;
+	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	memset(io_req->task_params, 0, sizeof(struct fcoe_task_params));
+	memset(io_req->sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
 
-	if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
-		task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
-	else
+	/* Set task type bassed on DMA directio of command */
+	if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) {
 		task_type = FCOE_TASK_TYPE_READ_INITIATOR;
-
-	/* Y Storm context */
-	task_ctx->ystorm_st_context.expect_first_xfer = 1;
-	task_ctx->ystorm_st_context.data_2_trns_rem = io_req->data_xfer_len;
-	/* Check if this is required */
-	task_ctx->ystorm_st_context.ox_id = io_req->xid;
-	task_ctx->ystorm_st_context.task_rety_identifier =
-	    io_req->task_retry_identifier;
-
-	/* T Storm ag context */
-	SET_FIELD(task_ctx->tstorm_ag_context.flags0,
-	    TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, PROTOCOLID_FCOE);
-	task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
-
-	/* T Storm st context */
-	SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
-	    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
-	    1);
-	task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
-
-	task_ctx->tstorm_st_context.read_only.dev_type =
-	    FCOE_TASK_DEV_TYPE_DISK;
-	task_ctx->tstorm_st_context.read_only.conf_supported = 0;
-	task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
-
-	/* Completion queue for response. */
-	task_ctx->tstorm_st_context.read_only.glbl_q_num = cq_idx;
-	task_ctx->tstorm_st_context.read_only.fcp_cmd_trns_size =
-	    io_req->data_xfer_len;
-	task_ctx->tstorm_st_context.read_write.e_d_tov_exp_timeout_val =
-	    lport->e_d_tov;
-
-	task_ctx->ustorm_ag_context.global_cq_num = cq_idx;
-	io_req->fp_idx = cq_idx;
-
-	bd_count = bd_tbl->bd_valid;
-	if (task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
-		/* Setup WRITE task */
-		struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
-
-		task_ctx->ystorm_st_context.task_type =
-		    FCOE_TASK_TYPE_WRITE_INITIATOR;
-		data_desc = &task_ctx->ystorm_st_context.data_desc;
-
-		if (io_req->use_slowpath) {
-			SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
-			    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
-			    FCOE_SLOW_SGL);
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(bd_tbl->bd_tbl_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(bd_tbl->bd_tbl_dma);
-			data_desc->slow.remainder_num_sges = bd_count;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
-			qedf->slow_sge_ios++;
-			io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
-		} else {
-			SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
-			    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
-			    (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
-			    FCOE_MUL_FAST_SGES);
-
-			if (bd_count == 1) {
-				data_desc->single_sge.sge_addr.lo =
-				    fcoe_bd_tbl->sge_addr.lo;
-				data_desc->single_sge.sge_addr.hi =
-				    fcoe_bd_tbl->sge_addr.hi;
-				data_desc->single_sge.size =
-				    fcoe_bd_tbl->size;
-				data_desc->single_sge.is_valid_sge = 0;
-				qedf->single_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
-			} else {
-				data_desc->fast.sgl_start_addr.lo =
-				    U64_LO(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_start_addr.hi =
-				    U64_HI(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_byte_offset =
-				    data_desc->fast.sgl_start_addr.lo &
-				    (QEDF_PAGE_SIZE - 1);
-				if (data_desc->fast.sgl_byte_offset > 0)
-					QEDF_ERR(&(qedf->dbg_ctx),
-					    "byte_offset=%u for xid=0x%x.\n",
-					    io_req->xid,
-					    data_desc->fast.sgl_byte_offset);
-				data_desc->fast.task_reuse_cnt =
-				    io_req->reuse_count;
-				io_req->reuse_count++;
-				if (io_req->reuse_count == QEDF_MAX_REUSE) {
-					*ptu_invalidate = 1;
-					io_req->reuse_count = 0;
-				}
-				qedf->fast_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_FAST_SGE;
-			}
-		}
-
-		/* T Storm context */
-		task_ctx->tstorm_st_context.read_only.task_type =
-		    FCOE_TASK_TYPE_WRITE_INITIATOR;
-
-		/* M Storm context */
-		tmp_sgl_mode = GET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
-		    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE);
-		SET_FIELD(task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-		    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE,
-		    tmp_sgl_mode);
-
 	} else {
-		/* Setup READ task */
-
-		/* M Storm context */
-		struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
-
-		data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
-		task_ctx->mstorm_st_context.fp.data_2_trns_rem =
-		    io_req->data_xfer_len;
-
-		if (io_req->use_slowpath) {
-			SET_FIELD(
-			    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-			    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
-			    FCOE_SLOW_SGL);
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(bd_tbl->bd_tbl_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(bd_tbl->bd_tbl_dma);
-			data_desc->slow.remainder_num_sges =
-			    bd_count;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
-			qedf->slow_sge_ios++;
-			io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+		if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
+			task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
+			tx_io_size = io_req->data_xfer_len;
 		} else {
-			SET_FIELD(
-			    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-			    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
-			    (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
-			    FCOE_MUL_FAST_SGES);
-
-			if (bd_count == 1) {
-				data_desc->single_sge.sge_addr.lo =
-				    fcoe_bd_tbl->sge_addr.lo;
-				data_desc->single_sge.sge_addr.hi =
-				    fcoe_bd_tbl->sge_addr.hi;
-				data_desc->single_sge.size =
-				    fcoe_bd_tbl->size;
-				data_desc->single_sge.is_valid_sge = 0;
-				qedf->single_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
-			} else {
-				data_desc->fast.sgl_start_addr.lo =
-				    U64_LO(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_start_addr.hi =
-				    U64_HI(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_byte_offset = 0;
-				data_desc->fast.task_reuse_cnt =
-				    io_req->reuse_count;
-				io_req->reuse_count++;
-				if (io_req->reuse_count == QEDF_MAX_REUSE) {
-					*ptu_invalidate = 1;
-					io_req->reuse_count = 0;
-				}
-				qedf->fast_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_FAST_SGE;
-			}
+			task_type = FCOE_TASK_TYPE_READ_INITIATOR;
+			rx_io_size = io_req->data_xfer_len;
 		}
-
-		/* Y Storm context */
-		task_ctx->ystorm_st_context.expect_first_xfer = 0;
-		task_ctx->ystorm_st_context.task_type =
-		    FCOE_TASK_TYPE_READ_INITIATOR;
-
-		/* T Storm context */
-		task_ctx->tstorm_st_context.read_only.task_type =
-		    FCOE_TASK_TYPE_READ_INITIATOR;
-		mst_sgl_mode = GET_FIELD(
-		    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-		    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE);
-		SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
-		    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
-		    mst_sgl_mode);
 	}
 
+	/* Setup the fields for fcoe_task_params */
+	io_req->task_params->context = task_ctx;
+	io_req->task_params->sqe = sqe;
+	io_req->task_params->task_type = task_type;
+	io_req->task_params->tx_io_size = tx_io_size;
+	io_req->task_params->rx_io_size = rx_io_size;
+	io_req->task_params->conn_cid = fcport->fw_cid;
+	io_req->task_params->itid = io_req->xid;
+	io_req->task_params->cq_rss_number = cq_idx;
+	io_req->task_params->is_tape_device = fcport->dev_type;
+
+	/* Fill in information for scatter/gather list */
+	if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) {
+		bd_count = bd_tbl->bd_valid;
+		io_req->sgl_task_params->sgl = bd_tbl->bd_tbl;
+		io_req->sgl_task_params->sgl_phys_addr.lo =
+			U64_LO(bd_tbl->bd_tbl_dma);
+		io_req->sgl_task_params->sgl_phys_addr.hi =
+			U64_HI(bd_tbl->bd_tbl_dma);
+		io_req->sgl_task_params->num_sges = bd_count;
+		io_req->sgl_task_params->total_buffer_size =
+		    scsi_bufflen(io_req->sc_cmd);
+		io_req->sgl_task_params->small_mid_sge =
+			io_req->use_slowpath;
+	}
+
+	/* Fill in physical address of sense buffer */
+	sense_data_buffer_phys_addr.lo = U64_LO(io_req->sense_buffer_dma);
+	sense_data_buffer_phys_addr.hi = U64_HI(io_req->sense_buffer_dma);
+
 	/* fill FCP_CMND IU */
-	fcp_cmnd = (u32 *)task_ctx->ystorm_st_context.tx_info_union.fcp_cmd_payload.opaque;
-	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)&tmp_fcp_cmnd);
+	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tmp_fcp_cmnd);
 
 	/* Swap fcp_cmnd since FC is big endian */
 	cnt = sizeof(struct fcp_cmnd) / sizeof(u32);
-
 	for (i = 0; i < cnt; i++) {
-		*fcp_cmnd = cpu_to_be32(tmp_fcp_cmnd[i]);
-		fcp_cmnd++;
+		tmp_fcp_cmnd[i] = cpu_to_be32(tmp_fcp_cmnd[i]);
+	}
+	memcpy(fcp_cmnd, tmp_fcp_cmnd, sizeof(struct fcp_cmnd));
+
+	init_initiator_rw_fcoe_task(io_req->task_params,
+				    io_req->sgl_task_params,
+				    sense_data_buffer_phys_addr,
+				    io_req->task_retry_identifier, fcp_cmnd);
+
+	/* Increment SGL type counters */
+	if (bd_count == 1) {
+		qedf->single_sge_ios++;
+		io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
+	} else if (io_req->use_slowpath) {
+		qedf->slow_sge_ios++;
+		io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+	} else {
+		qedf->fast_sge_ios++;
+		io_req->sge_type = QEDF_IOREQ_FAST_SGE;
 	}
-
-	/* M Storm context - Sense buffer */
-	task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
-		U64_LO(io_req->sense_buffer_dma);
-	task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
-		U64_HI(io_req->sense_buffer_dma);
 }
 
 void qedf_init_mp_task(struct qedf_ioreq *io_req,
-	struct fcoe_task_context *task_ctx)
+	struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe)
 {
 	struct qedf_mp_req *mp_req = &(io_req->mp_req);
 	struct qedf_rport *fcport = io_req->fcport;
 	struct qedf_ctx *qedf = io_req->fcport->qedf;
 	struct fc_frame_header *fc_hdr;
-	enum fcoe_task_type task_type = 0;
-	union fcoe_data_desc_ctx *data_desc;
+	struct fcoe_tx_mid_path_params task_fc_hdr;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
 
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Initializing MP task "
-		   "for cmd_type = %d\n", io_req->cmd_type);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+		  "Initializing MP task for cmd_type=%d\n",
+		  io_req->cmd_type);
 
 	qedf->control_requests++;
 
-	/* Obtain task_type */
-	if ((io_req->cmd_type == QEDF_TASK_MGMT_CMD) ||
-	    (io_req->cmd_type == QEDF_ELS)) {
-		task_type = FCOE_TASK_TYPE_MIDPATH;
-	} else if (io_req->cmd_type == QEDF_ABTS) {
-		task_type = FCOE_TASK_TYPE_ABTS;
-	}
-
+	memset(&tx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
 	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	memset(&task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
 
 	/* Setup the task from io_req for easy reference */
 	io_req->task = task_ctx;
 
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "task type = %d\n",
-		   task_type);
-
-	/* YSTORM only */
-	{
-		/* Initialize YSTORM task context */
-		struct fcoe_tx_mid_path_params *task_fc_hdr =
-		    &task_ctx->ystorm_st_context.tx_info_union.tx_params.mid_path;
-		memset(task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
-		task_ctx->ystorm_st_context.task_rety_identifier =
-		    io_req->task_retry_identifier;
-
-		/* Init SGL parameters */
-		if ((task_type == FCOE_TASK_TYPE_MIDPATH) ||
-		    (task_type == FCOE_TASK_TYPE_UNSOLICITED)) {
-			data_desc = &task_ctx->ystorm_st_context.data_desc;
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(mp_req->mp_req_bd_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(mp_req->mp_req_bd_dma);
-			data_desc->slow.remainder_num_sges = 1;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
-		}
-
-		fc_hdr = &(mp_req->req_fc_hdr);
-		if (task_type == FCOE_TASK_TYPE_MIDPATH) {
-			fc_hdr->fh_ox_id = io_req->xid;
-			fc_hdr->fh_rx_id = htons(0xffff);
-		} else if (task_type == FCOE_TASK_TYPE_UNSOLICITED) {
-			fc_hdr->fh_rx_id = io_req->xid;
-		}
+	/* Setup the fields for fcoe_task_params */
+	io_req->task_params->context = task_ctx;
+	io_req->task_params->sqe = sqe;
+	io_req->task_params->task_type = FCOE_TASK_TYPE_MIDPATH;
+	io_req->task_params->tx_io_size = io_req->data_xfer_len;
+	/* rx_io_size tells the f/w how large a response buffer we have */
+	io_req->task_params->rx_io_size = PAGE_SIZE;
+	io_req->task_params->conn_cid = fcport->fw_cid;
+	io_req->task_params->itid = io_req->xid;
+	/* Return middle path commands on CQ 0 */
+	io_req->task_params->cq_rss_number = 0;
+	io_req->task_params->is_tape_device = fcport->dev_type;
+
+	fc_hdr = &(mp_req->req_fc_hdr);
+	/* Set OX_ID and RX_ID based on driver task id */
+	fc_hdr->fh_ox_id = io_req->xid;
+	fc_hdr->fh_rx_id = htons(0xffff);
+
+	/* Set up FC header information */
+	task_fc_hdr.parameter = fc_hdr->fh_parm_offset;
+	task_fc_hdr.r_ctl = fc_hdr->fh_r_ctl;
+	task_fc_hdr.type = fc_hdr->fh_type;
+	task_fc_hdr.cs_ctl = fc_hdr->fh_cs_ctl;
+	task_fc_hdr.df_ctl = fc_hdr->fh_df_ctl;
+	task_fc_hdr.rx_id = fc_hdr->fh_rx_id;
+	task_fc_hdr.ox_id = fc_hdr->fh_ox_id;
+
+	/* Set up s/g list parameters for request buffer */
+	tx_sgl_task_params.sgl = mp_req->mp_req_bd;
+	tx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_req_bd_dma);
+	tx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_req_bd_dma);
+	tx_sgl_task_params.num_sges = 1;
+	/* Set PAGE_SIZE for now since sg element is that size ??? */
+	tx_sgl_task_params.total_buffer_size = io_req->data_xfer_len;
+	tx_sgl_task_params.small_mid_sge = 0;
+
+	/* Set up s/g list parameters for request buffer */
+	rx_sgl_task_params.sgl = mp_req->mp_resp_bd;
+	rx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_resp_bd_dma);
+	rx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_resp_bd_dma);
+	rx_sgl_task_params.num_sges = 1;
+	/* Set PAGE_SIZE for now since sg element is that size ??? */
+	rx_sgl_task_params.total_buffer_size = PAGE_SIZE;
+	rx_sgl_task_params.small_mid_sge = 0;
 
-		/* Fill FC Header into middle path buffer */
-		task_fc_hdr->parameter = fc_hdr->fh_parm_offset;
-		task_fc_hdr->r_ctl = fc_hdr->fh_r_ctl;
-		task_fc_hdr->type = fc_hdr->fh_type;
-		task_fc_hdr->cs_ctl = fc_hdr->fh_cs_ctl;
-		task_fc_hdr->df_ctl = fc_hdr->fh_df_ctl;
-		task_fc_hdr->rx_id = fc_hdr->fh_rx_id;
-		task_fc_hdr->ox_id = fc_hdr->fh_ox_id;
-
-		task_ctx->ystorm_st_context.data_2_trns_rem =
-		    io_req->data_xfer_len;
-		task_ctx->ystorm_st_context.task_type = task_type;
-	}
-
-	/* TSTORM ONLY */
-	{
-		task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
-		task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
-		/* Always send middle-path repsonses on CQ #0 */
-		task_ctx->tstorm_st_context.read_only.glbl_q_num = 0;
-		io_req->fp_idx = 0;
-		SET_FIELD(task_ctx->tstorm_ag_context.flags0,
-		    TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE,
-		    PROTOCOLID_FCOE);
-		task_ctx->tstorm_st_context.read_only.task_type = task_type;
-		SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
-		    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
-		    1);
-		task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
-	}
-
-	/* MSTORM only */
-	{
-		if (task_type == FCOE_TASK_TYPE_MIDPATH) {
-			/* Initialize task context */
-			data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
-
-			/* Set cache sges address and length */
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(mp_req->mp_resp_bd_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(mp_req->mp_resp_bd_dma);
-			data_desc->slow.remainder_num_sges = 1;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
 
-			/*
-			 * Also need to fil in non-fastpath response address
-			 * for middle path commands.
-			 */
-			task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
-			    U64_LO(mp_req->mp_resp_bd_dma);
-			task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
-			    U64_HI(mp_req->mp_resp_bd_dma);
-		}
-	}
-
-	/* USTORM ONLY */
-	{
-		task_ctx->ustorm_ag_context.global_cq_num = 0;
-	}
+	/*
+	 * Last arg is 0 as previous code did not set that we wanted the
+	 * fc header information.
+	 */
+	init_initiator_midpath_unsolicited_fcoe_task(io_req->task_params,
+						     &task_fc_hdr,
+						     &tx_sgl_task_params,
+						     &rx_sgl_task_params, 0);
 
-	/* I/O stats. Middle path commands always use slow SGEs */
-	qedf->slow_sge_ios++;
-	io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+	/* Midpath requests always consume 1 SGE */
+	qedf->single_sge_ios++;
 }
 
-void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, u32 ptu_invalidate,
-	enum fcoe_task_type req_type, u32 offset)
+/* Presumed that fcport->rport_lock is held */
+u16 qedf_get_sqe_idx(struct qedf_rport *fcport)
 {
-	struct fcoe_wqe *sqe;
 	uint16_t total_sqe = (fcport->sq_mem_size)/(sizeof(struct fcoe_wqe));
+	u16 rval;
 
-	sqe = &fcport->sq[fcport->sq_prod_idx];
+	rval = fcport->sq_prod_idx;
 
+	/* Adjust ring index */
 	fcport->sq_prod_idx++;
 	fcport->fw_sq_prod_idx++;
 	if (fcport->sq_prod_idx == total_sqe)
 		fcport->sq_prod_idx = 0;
 
-	switch (req_type) {
-	case FCOE_TASK_TYPE_WRITE_INITIATOR:
-	case FCOE_TASK_TYPE_READ_INITIATOR:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_CMD);
-		if (ptu_invalidate)
-			SET_FIELD(sqe->flags, FCOE_WQE_INVALIDATE_PTU, 1);
-		break;
-	case FCOE_TASK_TYPE_MIDPATH:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_MIDPATH);
-		break;
-	case FCOE_TASK_TYPE_ABTS:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
-		    SEND_FCOE_ABTS_REQUEST);
-		break;
-	case FCOE_TASK_TYPE_EXCHANGE_CLEANUP:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
-		     FCOE_EXCHANGE_CLEANUP);
-		break;
-	case FCOE_TASK_TYPE_SEQUENCE_CLEANUP:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
-		    FCOE_SEQUENCE_RECOVERY);
-		/* NOTE: offset param only used for sequence recovery */
-		sqe->additional_info_union.seq_rec_updated_offset = offset;
-		break;
-	case FCOE_TASK_TYPE_UNSOLICITED:
-		break;
-	default:
-		break;
-	}
-
-	sqe->task_id = xid;
-
-	/* Make sure SQ data is coherent */
-	wmb();
-
+	return rval;
 }
 
 void qedf_ring_doorbell(struct qedf_rport *fcport)
@@ -1029,7 +847,8 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
 	struct fcoe_task_context *task_ctx;
 	u16 xid;
 	enum fcoe_task_type req_type = 0;
-	u32 ptu_invalidate = 0;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	/* Initialize rest of io_req fileds */
 	io_req->data_xfer_len = scsi_bufflen(sc_cmd);
@@ -1061,6 +880,16 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
 		return -EAGAIN;
 	}
 
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
+		kref_put(&io_req->refcount, qedf_release_cmd);
+	}
+
+	/* Obtain free SQE */
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+
 	/* Get the task context */
 	task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
 	if (!task_ctx) {
@@ -1070,15 +899,7 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
 		return -EINVAL;
 	}
 
-	qedf_init_task(fcport, lport, io_req, &ptu_invalidate, task_ctx);
-
-	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
-		QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
-		kref_put(&io_req->refcount, qedf_release_cmd);
-	}
-
-	/* Obtain free SQ entry */
-	qedf_add_to_sq(fcport, xid, ptu_invalidate, req_type, 0);
+	qedf_init_task(fcport, lport, io_req, task_ctx, sqe);
 
 	/* Ring doorbell */
 	qedf_ring_doorbell(fcport);
@@ -1342,7 +1163,7 @@ void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 		} else {
 			refcount = kref_read(&io_req->refcount);
 			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
-			    "%d:0:%d:%d xid=0x%0x op=0x%02x "
+			    "%d:0:%d:%lld xid=0x%0x op=0x%02x "
 			    "lba=%02x%02x%02x%02x cdb_status=%d "
 			    "fcp_resid=0x%x refcount=%d.\n",
 			    qedf->lport->host->host_no, sc_cmd->device->id,
@@ -1426,7 +1247,7 @@ void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
 
 	sc_cmd->result = result << 16;
 	refcount = kref_read(&io_req->refcount);
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%d: Completing "
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%lld: Completing "
 	    "sc_cmd=%p result=0x%08x op=0x%02x lba=0x%02x%02x%02x%02x, "
 	    "allowed=%d retries=%d refcount=%d.\n",
 	    qedf->lport->host->host_no, sc_cmd->device->id,
@@ -1661,6 +1482,8 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
 	u32 r_a_tov = 0;
 	int rc = 0;
 	unsigned long flags;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	r_a_tov = rdata->r_a_tov;
 	lport = qedf->lport;
@@ -1712,10 +1535,12 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
 
 	spin_lock_irqsave(&fcport->rport_lock, flags);
 
-	/* Add ABTS to send queue */
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_ABTS, 0);
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+	io_req->task_params->sqe = sqe;
 
-	/* Ring doorbell */
+	init_initiator_abort_fcoe_task(io_req->task_params);
 	qedf_ring_doorbell(fcport);
 
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
@@ -1784,8 +1609,8 @@ void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 int qedf_init_mp_req(struct qedf_ioreq *io_req)
 {
 	struct qedf_mp_req *mp_req;
-	struct fcoe_sge *mp_req_bd;
-	struct fcoe_sge *mp_resp_bd;
+	struct scsi_sge *mp_req_bd;
+	struct scsi_sge *mp_resp_bd;
 	struct qedf_ctx *qedf = io_req->fcport->qedf;
 	dma_addr_t addr;
 	uint64_t sz;
@@ -1819,7 +1644,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
 	}
 
 	/* Allocate and map mp_req_bd and mp_resp_bd */
-	sz = sizeof(struct fcoe_sge);
+	sz = sizeof(struct scsi_sge);
 	mp_req->mp_req_bd = dma_alloc_coherent(&qedf->pdev->dev, sz,
 	    &mp_req->mp_req_bd_dma, GFP_KERNEL);
 	if (!mp_req->mp_req_bd) {
@@ -1841,7 +1666,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
 	mp_req_bd = mp_req->mp_req_bd;
 	mp_req_bd->sge_addr.lo = U64_LO(addr);
 	mp_req_bd->sge_addr.hi = U64_HI(addr);
-	mp_req_bd->size = QEDF_PAGE_SIZE;
+	mp_req_bd->sge_len = QEDF_PAGE_SIZE;
 
 	/*
 	 * MP buffer is either a task mgmt command or an ELS.
@@ -1852,7 +1677,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
 	addr = mp_req->resp_buf_dma;
 	mp_resp_bd->sge_addr.lo = U64_LO(addr);
 	mp_resp_bd->sge_addr.hi = U64_HI(addr);
-	mp_resp_bd->size = QEDF_PAGE_SIZE;
+	mp_resp_bd->sge_len = QEDF_PAGE_SIZE;
 
 	return 0;
 }
@@ -1895,6 +1720,8 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
 	int tmo = 0;
 	int rc = SUCCESS;
 	unsigned long flags;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	fcport = io_req->fcport;
 	if (!fcport) {
@@ -1940,12 +1767,16 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
 
 	init_completion(&io_req->tm_done);
 
-	/* Obtain free SQ entry */
 	spin_lock_irqsave(&fcport->rport_lock, flags);
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_EXCHANGE_CLEANUP, 0);
 
-	/* Ring doorbell */
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+	io_req->task_params->sqe = sqe;
+
+	init_initiator_cleanup_fcoe_task(io_req->task_params);
 	qedf_ring_doorbell(fcport);
+
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
 
 	tmo = wait_for_completion_timeout(&io_req->tm_done,
@@ -1991,16 +1822,15 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 	uint8_t tm_flags)
 {
 	struct qedf_ioreq *io_req;
-	struct qedf_mp_req *tm_req;
 	struct fcoe_task_context *task;
-	struct fc_frame_header *fc_hdr;
-	struct fcp_cmnd *fcp_cmnd;
 	struct qedf_ctx *qedf = fcport->qedf;
+	struct fc_lport *lport = qedf->lport;
 	int rc = 0;
 	uint16_t xid;
-	uint32_t sid, did;
 	int tmo = 0;
 	unsigned long flags;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	if (!sc_cmd) {
 		QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n");
@@ -2031,36 +1861,14 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 	/* Set the return CPU to be the same as the request one */
 	io_req->cpu = smp_processor_id();
 
-	tm_req = (struct qedf_mp_req *)&(io_req->mp_req);
-
-	rc = qedf_init_mp_req(io_req);
-	if (rc == FAILED) {
-		QEDF_ERR(&(qedf->dbg_ctx), "Task mgmt MP request init "
-			  "failed\n");
-		kref_put(&io_req->refcount, qedf_release_cmd);
-		goto reset_tmf_err;
-	}
-
 	/* Set TM flags */
-	io_req->io_req_flags = 0;
-	tm_req->tm_flags = tm_flags;
+	io_req->io_req_flags = QEDF_READ;
+	io_req->data_xfer_len = 0;
+	io_req->tm_flags = tm_flags;
 
 	/* Default is to return a SCSI command when an error occurs */
 	io_req->return_scsi_cmd_on_abts = true;
 
-	/* Fill FCP_CMND */
-	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf);
-	fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf;
-	memset(fcp_cmnd->fc_cdb, 0, FCP_CMND_LEN);
-	fcp_cmnd->fc_dl = 0;
-
-	/* Fill FC header */
-	fc_hdr = &(tm_req->req_fc_hdr);
-	sid = fcport->sid;
-	did = fcport->rdata->ids.port_id;
-	__fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, sid, did,
-			   FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
-			   FC_FC_SEQ_INIT, 0);
 	/* Obtain exchange id */
 	xid = io_req->xid;
 
@@ -2069,16 +1877,18 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 
 	/* Initialize task context for this IO request */
 	task = qedf_get_task_mem(&qedf->tasks, xid);
-	qedf_init_mp_task(io_req, task);
 
 	init_completion(&io_req->tm_done);
 
-	/* Obtain free SQ entry */
 	spin_lock_irqsave(&fcport->rport_lock, flags);
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
 
-	/* Ring doorbell */
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+
+	qedf_init_task(fcport, lport, io_req, task, sqe);
 	qedf_ring_doorbell(fcport);
+
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
 
 	tmo = wait_for_completion_timeout(&io_req->tm_done,
@@ -2162,14 +1972,6 @@ void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 	struct qedf_ioreq *io_req)
 {
 	struct fcoe_cqe_rsp_info *fcp_rsp;
-	struct fcoe_cqe_midpath_info *mp_info;
-
-
-	/* Get TMF response length from CQE */
-	mp_info = &cqe->cqe_info.midpath_info;
-	io_req->mp_req.resp_len = mp_info->data_placement_size;
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
-	    "Response len is %d.\n", io_req->mp_req.resp_len);
 
 	fcp_rsp = &cqe->cqe_info.rsp_info;
 	qedf_parse_fcp_rsp(io_req, fcp_rsp);
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index d9d7a86b5f8b..cceddd995a4b 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -2456,8 +2456,8 @@ static int qedf_alloc_bdq(struct qedf_ctx *qedf)
 	}
 
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
-	    "BDQ PBL addr=0x%p dma=0x%llx.\n", qedf->bdq_pbl,
-	    qedf->bdq_pbl_dma);
+		  "BDQ PBL addr=0x%p dma=%pad\n",
+		  qedf->bdq_pbl, &qedf->bdq_pbl_dma);
 
 	/*
 	 * Populate BDQ PBL with physical and virtual address of individual
@@ -2803,6 +2803,7 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 		atomic_set(&qedf->num_offloads, 0);
 		qedf->stop_io_on_error = false;
 		pci_set_drvdata(pdev, qedf);
+		init_completion(&qedf->fipvlan_compl);
 
 		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_INFO,
 		   "QLogic FastLinQ FCoE Module qedf %s, "
diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile
index 2b3e16b24299..90a6925577cc 100644
--- a/drivers/scsi/qedi/Makefile
+++ b/drivers/scsi/qedi/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_QEDI) := qedi.o
 qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \
-	    qedi_dbg.o
+	    qedi_dbg.o qedi_fw_api.o
 
 qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o
diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c
index 955936274241..59417199bf36 100644
--- a/drivers/scsi/qedi/qedi_debugfs.c
+++ b/drivers/scsi/qedi/qedi_debugfs.c
@@ -14,7 +14,7 @@
 #include <linux/debugfs.h>
 #include <linux/module.h>
 
-int do_not_recover;
+int qedi_do_not_recover;
 static struct dentry *qedi_dbg_root;
 
 void
@@ -74,22 +74,22 @@ qedi_dbg_exit(void)
 static ssize_t
 qedi_dbg_do_not_recover_enable(struct qedi_dbg_ctx *qedi_dbg)
 {
-	if (!do_not_recover)
-		do_not_recover = 1;
+	if (!qedi_do_not_recover)
+		qedi_do_not_recover = 1;
 
 	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
-		  do_not_recover);
+		  qedi_do_not_recover);
 	return 0;
 }
 
 static ssize_t
 qedi_dbg_do_not_recover_disable(struct qedi_dbg_ctx *qedi_dbg)
 {
-	if (do_not_recover)
-		do_not_recover = 0;
+	if (qedi_do_not_recover)
+		qedi_do_not_recover = 0;
 
 	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
-		  do_not_recover);
+		  qedi_do_not_recover);
 	return 0;
 }
 
@@ -141,7 +141,7 @@ qedi_dbg_do_not_recover_cmd_read(struct file *filp, char __user *buffer,
 	if (*ppos)
 		return 0;
 
-	cnt = sprintf(buffer, "do_not_recover=%d\n", do_not_recover);
+	cnt = sprintf(buffer, "do_not_recover=%d\n", qedi_do_not_recover);
 	cnt = min_t(int, count, cnt - *ppos);
 	*ppos += cnt;
 	return cnt;
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index c9f0ef4e11b3..d6978cbc56f0 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -14,6 +14,8 @@
 #include "qedi.h"
 #include "qedi_iscsi.h"
 #include "qedi_gbl.h"
+#include "qedi_fw_iscsi.h"
+#include "qedi_fw_scsi.h"
 
 static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 			       struct iscsi_task *mtask);
@@ -53,8 +55,8 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi,
 	resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn);
 	resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn);
 
-	resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait);
-	resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain);
+	resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time_2_wait);
+	resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time_2_retain);
 
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
 		  "Freeing tid=0x%x for cid=0x%x\n",
@@ -975,81 +977,6 @@ exit_fp_process:
 	return;
 }
 
-static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task,
-			   u16 tid, uint16_t ptu_invalidate, int is_cleanup)
-{
-	struct iscsi_wqe *wqe;
-	struct iscsi_wqe_field *cont_field;
-	struct qedi_endpoint *ep;
-	struct scsi_cmnd *sc = task->sc;
-	struct iscsi_login_req *login_hdr;
-	struct qedi_cmd *cmd = task->dd_data;
-
-	login_hdr = (struct iscsi_login_req *)task->hdr;
-	ep = qedi_conn->ep;
-	wqe = &ep->sq[ep->sq_prod_idx];
-
-	memset(wqe, 0, sizeof(*wqe));
-
-	ep->sq_prod_idx++;
-	ep->fw_sq_prod_idx++;
-	if (ep->sq_prod_idx == QEDI_SQ_SIZE)
-		ep->sq_prod_idx = 0;
-
-	if (is_cleanup) {
-		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			  ISCSI_WQE_TYPE_TASK_CLEANUP);
-		wqe->task_id = tid;
-		return;
-	}
-
-	if (ptu_invalidate) {
-		SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE,
-			  ISCSI_WQE_SET_PTU_INVALIDATE);
-	}
-
-	cont_field = &wqe->cont_prevtid_union.cont_field;
-
-	switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
-	case ISCSI_OP_LOGIN:
-	case ISCSI_OP_TEXT:
-		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			  ISCSI_WQE_TYPE_MIDDLE_PATH);
-		SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
-			  1);
-		cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength);
-		break;
-	case ISCSI_OP_LOGOUT:
-	case ISCSI_OP_NOOP_OUT:
-	case ISCSI_OP_SCSI_TMFUNC:
-		 SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			   ISCSI_WQE_TYPE_NORMAL);
-		break;
-	default:
-		if (!sc)
-			break;
-
-		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			  ISCSI_WQE_TYPE_NORMAL);
-		cont_field->contlen_cdbsize_field =
-				(sc->sc_data_direction == DMA_TO_DEVICE) ?
-				scsi_bufflen(sc) : 0;
-		if (cmd->use_slowpath)
-			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0);
-		else
-			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
-				  (sc->sc_data_direction ==
-				   DMA_TO_DEVICE) ?
-				  min((u16)QEDI_FAST_SGE_COUNT,
-				      (u16)cmd->io_tbl.sge_valid) : 0);
-		break;
-	}
-
-	wqe->task_id = tid;
-	/* Make sure SQ data is coherent */
-	wmb();
-}
-
 static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 {
 	struct iscsi_db_data dbell = { 0 };
@@ -1076,96 +1003,116 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 		  qedi_conn->iscsi_conn_id);
 }
 
+static u16 qedi_get_wqe_idx(struct qedi_conn *qedi_conn)
+{
+	struct qedi_endpoint *ep;
+	u16 rval;
+
+	ep = qedi_conn->ep;
+	rval = ep->sq_prod_idx;
+
+	/* Increament SQ index */
+	ep->sq_prod_idx++;
+	ep->fw_sq_prod_idx++;
+	if (ep->sq_prod_idx == QEDI_SQ_SIZE)
+		ep->sq_prod_idx = 0;
+
+	return rval;
+}
+
 int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
 			  struct iscsi_task *task)
 {
-	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_login_req_hdr login_req_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
 	struct iscsi_task_context *fw_task_ctx;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_login_req *login_hdr;
-	struct iscsi_login_req_hdr *fw_login_req = NULL;
-	struct iscsi_cached_sge_ctx *cached_sge = NULL;
-	struct iscsi_sge *single_sge = NULL;
-	struct iscsi_sge *req_sge = NULL;
-	struct iscsi_sge *resp_sge = NULL;
+	struct scsi_sge *req_sge = NULL;
+	struct scsi_sge *resp_sge = NULL;
 	struct qedi_cmd *qedi_cmd;
-	s16 ptu_invalidate = 0;
+	struct qedi_endpoint *ep;
 	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	ep = qedi_conn->ep;
 	login_hdr = (struct iscsi_login_req *)task->hdr;
 
 	tid = qedi_get_task_idx(qedi);
 	if (tid == -1)
 		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
 
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req;
-	fw_login_req->opcode = login_hdr->opcode;
-	fw_login_req->version_min = login_hdr->min_version;
-	fw_login_req->version_max = login_hdr->max_version;
-	fw_login_req->flags_attr = login_hdr->flags;
-	fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2);
-	fw_login_req->isid_d = *((u32 *)login_hdr->isid);
-	fw_login_req->tsih = login_hdr->tsih;
-	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
-	fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_login_req->cid = qedi_conn->iscsi_conn_id;
-	fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn);
-	fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
-	fw_login_req->exp_stat_sn = 0;
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&login_req_pdu_header, 0, sizeof(login_req_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+	/* Update header info */
+	login_req_pdu_header.opcode = login_hdr->opcode;
+	login_req_pdu_header.version_min = login_hdr->min_version;
+	login_req_pdu_header.version_max = login_hdr->max_version;
+	login_req_pdu_header.flags_attr = login_hdr->flags;
+	login_req_pdu_header.isid_tabc = swab32p((u32 *)login_hdr->isid);
+	login_req_pdu_header.isid_d = swab16p((u16 *)&login_hdr->isid[4]);
+
+	login_req_pdu_header.tsih = login_hdr->tsih;
+	login_req_pdu_header.hdr_second_dword = ntoh24(login_hdr->dlength);
 
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
-	cached_sge =
-	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
-	cached_sge->sge.sge_len = req_sge->sge_len;
-	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
-	cached_sge->sge.sge_addr.hi =
-			     (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
-
-	/* Mstorm context */
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	fw_task_ctx->mstorm_st_context.task_type = 0x2;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SINGLE_SGE, 1);
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SLOW_IO, 0);
-	fw_task_ctx->mstorm_st_context.sgl_size = 1;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
-						ntoh24(login_hdr->dlength);
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-	fw_task_ctx->ustorm_st_context.task_type = 0x2;
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	fw_task_ctx->ustorm_ag_context.exp_data_acked =
-						 ntoh24(login_hdr->dlength);
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	login_req_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	login_req_pdu_header.cid = qedi_conn->iscsi_conn_id;
+	login_req_pdu_header.cmd_sn = be32_to_cpu(login_hdr->cmdsn);
+	login_req_pdu_header.exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
+	login_req_pdu_header.exp_stat_sn = 0;
+
+	/* Fill tx AHS and rx buffer */
+	tx_sgl_task_params.sgl =
+			       (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	tx_sgl_task_params.sgl_phys_addr.lo =
+					 (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	tx_sgl_task_params.sgl_phys_addr.hi =
+			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+	tx_sgl_task_params.total_buffer_size = ntoh24(login_hdr->dlength);
+	tx_sgl_task_params.num_sges = 1;
+
+	rx_sgl_task_params.sgl =
+			      (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	rx_sgl_task_params.sgl_phys_addr.lo =
+					(u32)(qedi_conn->gen_pdu.resp_dma_addr);
+	rx_sgl_task_params.sgl_phys_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+	rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+	rx_sgl_task_params.num_sges = 1;
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = ntoh24(login_hdr->dlength);
+	task_params.rx_io_size = resp_sge->sge_len;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_login_request_task(&task_params,
+						 &login_req_pdu_header,
+						 &tx_sgl_task_params,
+						 &rx_sgl_task_params);
+	if (rval)
+		return -1;
 
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1173,7 +1120,6 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
@@ -1181,65 +1127,64 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
 int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
 			   struct iscsi_task *task)
 {
-	struct qedi_ctx *qedi = qedi_conn->qedi;
-	struct iscsi_logout_req_hdr *fw_logout_req = NULL;
-	struct iscsi_task_context *fw_task_ctx = NULL;
+	struct iscsi_logout_req_hdr logout_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
+	struct iscsi_task_context *fw_task_ctx;
 	struct iscsi_logout *logout_hdr = NULL;
-	struct qedi_cmd *qedi_cmd = NULL;
-	s16  tid = 0;
-	s16 ptu_invalidate = 0;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_endpoint *ep;
+	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
 	logout_hdr = (struct iscsi_logout *)task->hdr;
+	ep = qedi_conn->ep;
 
 	tid = qedi_get_task_idx(qedi);
 	if (tid == -1)
 		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
-
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req;
-	fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST;
-	fw_logout_req->reason_code = 0x80 | logout_hdr->flags;
-	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
-	fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
-	fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&logout_pdu_header, 0, sizeof(logout_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
 
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						  qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
-	fw_logout_req->cid = qedi_conn->iscsi_conn_id;
-	fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
-
-	/* Mstorm context */
-	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, 0);
-
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	/* Update header info */
+	logout_pdu_header.opcode = logout_hdr->opcode;
+	logout_pdu_header.reason_code = 0x80 | logout_hdr->flags;
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	logout_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	logout_pdu_header.exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
+	logout_pdu_header.cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+	logout_pdu_header.cid = qedi_conn->iscsi_conn_id;
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = 0;
+	task_params.rx_io_size = 0;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+
+	rval = init_initiator_logout_request_task(&task_params,
+						  &logout_pdu_header,
+						  NULL, NULL);
+	if (rval)
+		return -1;
 
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1247,9 +1192,7 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
-
 	return 0;
 }
 
@@ -1461,9 +1404,9 @@ static void qedi_tmf_work(struct work_struct *work)
 		  get_itt(tmf_hdr->rtt), get_itt(ctask->itt), cmd->task_id,
 		  qedi_conn->iscsi_conn_id);
 
-	if (do_not_recover) {
+	if (qedi_do_not_recover) {
 		QEDI_ERR(&qedi->dbg_ctx, "DONT SEND CLEANUP/ABORT %d\n",
-			 do_not_recover);
+			 qedi_do_not_recover);
 		goto abort_ret;
 	}
 
@@ -1533,47 +1476,46 @@ ldel_exit:
 static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 			       struct iscsi_task *mtask)
 {
-	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_tmf_request_hdr tmf_pdu_header;
+	struct iscsi_task_params task_params;
 	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_tmf_request_hdr *fw_tmf_request;
-	struct iscsi_sge *single_sge;
-	struct qedi_cmd *qedi_cmd;
-	struct qedi_cmd *cmd;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
 	struct iscsi_task *ctask;
 	struct iscsi_tm *tmf_hdr;
-	struct iscsi_sge *req_sge;
-	struct iscsi_sge *resp_sge;
-	u32 lun[2];
-	s16 tid = 0, ptu_invalidate = 0;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_cmd *cmd;
+	struct qedi_endpoint *ep;
+	u32 scsi_lun[2];
+	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
-	qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
 	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+	qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+	ep = qedi_conn->ep;
 
-	tid = qedi_cmd->task_id;
-	qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
 
-	fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request;
-	fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt));
-	fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+	qedi_cmd->task_id = tid;
 
-	memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
-	fw_tmf_request->lun.lo = be32_to_cpu(lun[0]);
-	fw_tmf_request->lun.hi = be32_to_cpu(lun[1]);
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&tmf_pdu_header, 0, sizeof(tmf_pdu_header));
 
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
+	/* Update header info */
+	qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+	tmf_pdu_header.itt = qedi_set_itt(tid, get_itt(mtask->itt));
+	tmf_pdu_header.cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+
+	memcpy(scsi_lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
+	tmf_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+	tmf_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
 
 	if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
 	     ISCSI_TM_FUNC_ABORT_TASK) {
@@ -1584,53 +1526,34 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 			return 0;
 		}
 		cmd = (struct qedi_cmd *)ctask->dd_data;
-		fw_tmf_request->rtt =
+		tmf_pdu_header.rtt =
 				qedi_set_itt(cmd->task_id,
 					     get_itt(tmf_hdr->rtt));
 	} else {
-		fw_tmf_request->rtt = ISCSI_RESERVED_TAG;
+		tmf_pdu_header.rtt = ISCSI_RESERVED_TAG;
 	}
 
-	fw_tmf_request->opcode = tmf_hdr->opcode;
-	fw_tmf_request->function = tmf_hdr->flags;
-	fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength);
-	fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
-
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SINGLE_SGE, 1);
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SLOW_IO, 0);
-	fw_task_ctx->mstorm_st_context.sgl_size = 1;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, 0);
-
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
-	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+	tmf_pdu_header.opcode = tmf_hdr->opcode;
+	tmf_pdu_header.function = tmf_hdr->flags;
+	tmf_pdu_header.hdr_second_dword = ntoh24(tmf_hdr->dlength);
+	tmf_pdu_header.ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
 
-	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
-		  "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n",
-		  tid,  mtask->itt, qedi_conn->iscsi_conn_id);
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = 0;
+	task_params.rx_io_size = 0;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_tmf_request_task(&task_params,
+					       &tmf_pdu_header);
+	if (rval)
+		return -1;
 
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1638,7 +1561,6 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
@@ -1689,101 +1611,98 @@ int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
 int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
 			 struct iscsi_task *task)
 {
-	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_text_request_hdr text_request_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_text_request_hdr *fw_text_request;
-	struct iscsi_cached_sge_ctx *cached_sge;
-	struct iscsi_sge *single_sge;
-	struct qedi_cmd *qedi_cmd;
-	/* For 6.5 hdr iscsi_hdr */
+	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_text *text_hdr;
-	struct iscsi_sge *req_sge;
-	struct iscsi_sge *resp_sge;
-	s16 ptu_invalidate = 0;
+	struct scsi_sge *req_sge = NULL;
+	struct scsi_sge *resp_sge = NULL;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_endpoint *ep;
 	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
 	text_hdr = (struct iscsi_text *)task->hdr;
+	ep = qedi_conn->ep;
 
 	tid = qedi_get_task_idx(qedi);
 	if (tid == -1)
 		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
 
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_text_request =
-			&fw_task_ctx->ystorm_st_context.pdu_hdr.text_request;
-	fw_text_request->opcode = text_hdr->opcode;
-	fw_text_request->flags_attr = text_hdr->flags;
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&text_request_pdu_header, 0, sizeof(text_request_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+
+	/* Update header info */
+	text_request_pdu_header.opcode = text_hdr->opcode;
+	text_request_pdu_header.flags_attr = text_hdr->flags;
 
 	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
-	fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_text_request->ttt = text_hdr->ttt;
-	fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn);
-	fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
-	fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength);
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						     qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						   qedi->tid_reuse_count[tid]++;
-
-	cached_sge =
-	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
-	cached_sge->sge.sge_len = req_sge->sge_len;
-	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
-	cached_sge->sge.sge_addr.hi =
+	text_request_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	text_request_pdu_header.ttt = text_hdr->ttt;
+	text_request_pdu_header.cmd_sn = be32_to_cpu(text_hdr->cmdsn);
+	text_request_pdu_header.exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
+	text_request_pdu_header.hdr_second_dword = ntoh24(text_hdr->dlength);
+
+	/* Fill tx AHS and rx buffer */
+	tx_sgl_task_params.sgl =
+			       (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	tx_sgl_task_params.sgl_phys_addr.lo =
+					 (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	tx_sgl_task_params.sgl_phys_addr.hi =
 			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+	tx_sgl_task_params.total_buffer_size = req_sge->sge_len;
+	tx_sgl_task_params.num_sges = 1;
+
+	rx_sgl_task_params.sgl =
+			      (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	rx_sgl_task_params.sgl_phys_addr.lo =
+					(u32)(qedi_conn->gen_pdu.resp_dma_addr);
+	rx_sgl_task_params.sgl_phys_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+	rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+	rx_sgl_task_params.num_sges = 1;
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = ntoh24(text_hdr->dlength);
+	task_params.rx_io_size = resp_sge->sge_len;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_text_request_task(&task_params,
+						&text_request_pdu_header,
+						&tx_sgl_task_params,
+						&rx_sgl_task_params);
+	if (rval)
+		return -1;
 
-	/* Mstorm context */
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	fw_task_ctx->mstorm_st_context.task_type = 0x2;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SINGLE_SGE, 1);
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SLOW_IO, 0);
-	fw_task_ctx->mstorm_st_context.sgl_size = 1;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_ag_context.exp_data_acked =
-						      ntoh24(text_hdr->dlength);
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
-						      ntoh24(text_hdr->dlength);
-	fw_task_ctx->ustorm_st_context.exp_data_sn =
-					      be32_to_cpu(text_hdr->exp_statsn);
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-	fw_task_ctx->ustorm_st_context.task_type = 0x2;
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-
-	/*  Add command in active command list */
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
 	qedi_cmd->io_cmd_in_list = true;
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
-
 	return 0;
 }
 
@@ -1791,58 +1710,62 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
 			   struct iscsi_task *task,
 			   char *datap, int data_len, int unsol)
 {
+	struct iscsi_nop_out_hdr nop_out_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
 	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_nop_out_hdr *fw_nop_out;
-	struct qedi_cmd *qedi_cmd;
-	/* For 6.5 hdr iscsi_hdr */
 	struct iscsi_nopout *nopout_hdr;
-	struct iscsi_cached_sge_ctx *cached_sge;
-	struct iscsi_sge *single_sge;
-	struct iscsi_sge *req_sge;
-	struct iscsi_sge *resp_sge;
-	u32 lun[2];
-	s16 ptu_invalidate = 0;
+	struct scsi_sge *req_sge = NULL;
+	struct scsi_sge *resp_sge = NULL;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_endpoint *ep;
+	u32 scsi_lun[2];
 	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
 	nopout_hdr = (struct iscsi_nopout *)task->hdr;
+	ep = qedi_conn->ep;
 
 	tid = qedi_get_task_idx(qedi);
-	if (tid == -1) {
-		QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n");
+	if (tid == -1)
 		return -ENOMEM;
-	}
-
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
 
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out;
-	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
-	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&nop_out_pdu_header, 0, sizeof(nop_out_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+
+	/* Update header info */
+	nop_out_pdu_header.opcode = nopout_hdr->opcode;
+	SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
+	SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
 
-	memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
-	fw_nop_out->lun.lo = be32_to_cpu(lun[0]);
-	fw_nop_out->lun.hi = be32_to_cpu(lun[1]);
+	memcpy(scsi_lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
+	nop_out_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+	nop_out_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
+	nop_out_pdu_header.cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
+	nop_out_pdu_header.exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
 
 	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
 
 	if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) {
-		fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt);
-		fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt);
-		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
-		fw_task_ctx->ystorm_st_context.state.local_comp = 1;
-		SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-			  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+		nop_out_pdu_header.itt = be32_to_cpu(nopout_hdr->itt);
+		nop_out_pdu_header.ttt = be32_to_cpu(nopout_hdr->ttt);
 	} else {
-		fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt));
-		fw_nop_out->ttt = ISCSI_TTT_ALL_ONES;
-		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+		nop_out_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+		nop_out_pdu_header.ttt = ISCSI_TTT_ALL_ONES;
 
 		spin_lock(&qedi_conn->list_lock);
 		list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1851,53 +1774,46 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
 		spin_unlock(&qedi_conn->list_lock);
 	}
 
-	fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT;
-	fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
-	fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
-
-	cached_sge =
-	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
-	cached_sge->sge.sge_len = req_sge->sge_len;
-	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
-	cached_sge->sge.sge_addr.hi =
-			(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
-
-	/* Mstorm context */
-	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len;
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, 0);
-
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-
-	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
-	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
-
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	/* Fill tx AHS and rx buffer */
+	if (data_len) {
+		tx_sgl_task_params.sgl =
+			       (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+		tx_sgl_task_params.sgl_phys_addr.lo =
+					 (u32)(qedi_conn->gen_pdu.req_dma_addr);
+		tx_sgl_task_params.sgl_phys_addr.hi =
+			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+		tx_sgl_task_params.total_buffer_size = data_len;
+		tx_sgl_task_params.num_sges = 1;
+
+		rx_sgl_task_params.sgl =
+			      (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+		rx_sgl_task_params.sgl_phys_addr.lo =
+					(u32)(qedi_conn->gen_pdu.resp_dma_addr);
+		rx_sgl_task_params.sgl_phys_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+		rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+		rx_sgl_task_params.num_sges = 1;
+	}
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = data_len;
+	task_params.rx_io_size = resp_sge->sge_len;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_nop_out_task(&task_params,
+					   &nop_out_pdu_header,
+					   &tx_sgl_task_params,
+					   &rx_sgl_task_params);
+	if (rval)
+		return -1;
+
 	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
@@ -1905,7 +1821,7 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
 static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
 			 int bd_index)
 {
-	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
 	int frag_size, sg_frags;
 
 	sg_frags = 0;
@@ -1938,7 +1854,7 @@ static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
 static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd)
 {
 	struct scsi_cmnd *sc = cmd->scsi_cmd;
-	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
 	struct scatterlist *sg;
 	int byte_count = 0;
 	int bd_count = 0;
@@ -2040,7 +1956,7 @@ static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd)
 		if (bd_count == 0)
 			return;
 	} else {
-		struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+		struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
 
 		bd[0].sge_addr.lo = 0;
 		bd[0].sge_addr.hi = 0;
@@ -2136,244 +2052,182 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task)
 	struct qedi_conn *qedi_conn = conn->dd_data;
 	struct qedi_cmd *cmd = task->dd_data;
 	struct scsi_cmnd *sc = task->sc;
+	struct iscsi_cmd_hdr cmd_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct scsi_sgl_task_params *prx_sgl = NULL;
+	struct scsi_sgl_task_params *ptx_sgl = NULL;
+	struct iscsi_task_params task_params;
+	struct iscsi_conn_params conn_params;
+	struct scsi_initiator_cmd_params cmd_params;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_cached_sge_ctx *cached_sge;
-	struct iscsi_phys_sgl_ctx *phys_sgl;
-	struct iscsi_virt_sgl_ctx *virt_sgl;
-	struct ystorm_iscsi_task_st_ctx *yst_cxt;
-	struct mstorm_iscsi_task_st_ctx *mst_cxt;
-	struct iscsi_sgl *sgl_struct;
-	struct iscsi_sge *single_sge;
+	struct iscsi_cls_conn *cls_conn;
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
-	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
-	enum iscsi_task_type task_type;
-	struct iscsi_cmd_hdr *fw_cmd;
-	u32 lun[2];
-	u32 exp_data;
-	u16 cq_idx = smp_processor_id() % qedi->num_queues;
-	s16 ptu_invalidate = 0;
+	enum iscsi_task_type task_type = MAX_ISCSI_TASK_TYPE;
+	struct qedi_endpoint *ep;
+	u32 scsi_lun[2];
 	s16 tid = 0;
-	u8 num_fast_sgs;
+	u16 sq_idx = 0;
+	u16 cq_idx;
+	int rval = 0;
 
-	tid = qedi_get_task_idx(qedi);
-	if (tid == -1)
-		return -ENOMEM;
+	ep = qedi_conn->ep;
+	cls_conn = qedi_conn->cls_conn;
+	conn = cls_conn->dd_data;
 
 	qedi_iscsi_map_sg_list(cmd);
+	int_to_scsilun(sc->device->lun, (struct scsi_lun *)scsi_lun);
 
-	int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun);
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
 
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
-	cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd;
-	SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE);
+	cmd->task_id = tid;
 
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&cmd_pdu_header, 0, sizeof(cmd_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+	memset(&conn_params, 0, sizeof(conn_params));
+	memset(&cmd_params, 0, sizeof(cmd_params));
+
+	cq_idx = smp_processor_id() % qedi->num_queues;
+	/* Update header info */
+	SET_FIELD(cmd_pdu_header.flags_attr, ISCSI_CMD_HDR_ATTR,
+		  ISCSI_ATTR_SIMPLE);
 	if (sc->sc_data_direction == DMA_TO_DEVICE) {
-		if (conn->session->initial_r2t_en) {
-			exp_data = min((conn->session->imm_data_en *
-					conn->max_xmit_dlength),
-				       conn->session->first_burst);
-			exp_data = min(exp_data, scsi_bufflen(sc));
-			fw_task_ctx->ustorm_ag_context.exp_data_acked =
-							  cpu_to_le32(exp_data);
-		} else {
-			fw_task_ctx->ustorm_ag_context.exp_data_acked =
-			      min(conn->session->first_burst, scsi_bufflen(sc));
-		}
-
-		SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1);
+		SET_FIELD(cmd_pdu_header.flags_attr,
+			  ISCSI_CMD_HDR_WRITE, 1);
 		task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE;
 	} else {
-		if (scsi_bufflen(sc))
-			SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1);
+		SET_FIELD(cmd_pdu_header.flags_attr,
+			  ISCSI_CMD_HDR_READ, 1);
 		task_type = ISCSI_TASK_TYPE_INITIATOR_READ;
 	}
 
-	fw_cmd->lun.lo = be32_to_cpu(lun[0]);
-	fw_cmd->lun.hi = be32_to_cpu(lun[1]);
+	cmd_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+	cmd_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
 
 	qedi_update_itt_map(qedi, tid, task->itt, cmd);
-	fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_cmd->expected_transfer_length = scsi_bufflen(sc);
-	fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn);
-	fw_cmd->opcode = hdr->opcode;
-	qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb);
-
-	/* Mstorm context */
-	fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma;
-	fw_task_ctx->mstorm_st_context.sense_db.hi =
-					(u32)((u64)cmd->sense_buffer_dma >> 32);
-	fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id;
-	fw_task_ctx->mstorm_st_context.task_type = task_type;
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						     qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						   qedi->tid_reuse_count[tid]++;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc);
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc);
-	fw_task_ctx->ustorm_st_context.exp_data_sn =
-						   be32_to_cpu(hdr->exp_statsn);
-	fw_task_ctx->ustorm_st_context.task_type = task_type;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx;
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-
-	num_fast_sgs = (cmd->io_tbl.sge_valid ?
-			min((u16)QEDI_FAST_SGE_COUNT,
-			    (u16)cmd->io_tbl.sge_valid) : 0);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs);
-
-	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
-	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
-
-	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n",
-		  cmd->io_tbl.sge_valid);
-
-	yst_cxt = &fw_task_ctx->ystorm_st_context;
-	mst_cxt = &fw_task_ctx->mstorm_st_context;
-	/* Tx path */
+	cmd_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	cmd_pdu_header.expected_transfer_length = cpu_to_be32(hdr->data_length);
+	cmd_pdu_header.hdr_second_dword = ntoh24(hdr->dlength);
+	cmd_pdu_header.cmd_sn = be32_to_cpu(hdr->cmdsn);
+	cmd_pdu_header.opcode = hdr->opcode;
+	qedi_cpy_scsi_cdb(sc, (u32 *)cmd_pdu_header.cdb);
+
+	/* Fill tx AHS and rx buffer */
 	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
-		/* not considering  superIO or FastIO */
-		if (cmd->io_tbl.sge_valid == 1) {
-			cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge;
-			cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo;
-			cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi;
-			cached_sge->sge.sge_len = bd[0].sge_len;
-			qedi->cached_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 1);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES, 0);
-			phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl;
-			phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
-			phys_sgl->sgl_base.hi =
-				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			phys_sgl->sgl_size = cmd->io_tbl.sge_valid;
-			qedi->slow_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 0);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES,
-				  min((u16)QEDI_FAST_SGE_COUNT,
-				      (u16)cmd->io_tbl.sge_valid));
-			virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl;
-			virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
-			virt_sgl->sgl_base.hi =
+		tx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl;
+		tx_sgl_task_params.sgl_phys_addr.lo =
+						 (u32)(cmd->io_tbl.sge_tbl_dma);
+		tx_sgl_task_params.sgl_phys_addr.hi =
 				      (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			virt_sgl->sgl_initial_offset =
-				 (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
-			qedi->fast_sgls++;
-		}
-		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
-		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
-	} else {
-	/* Rx path */
-		if (cmd->io_tbl.sge_valid == 1) {
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 0);
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SINGLE_SGE, 1);
-			single_sge = &mst_cxt->sgl_union.single_sge;
-			single_sge->sge_addr.lo = bd[0].sge_addr.lo;
-			single_sge->sge_addr.hi = bd[0].sge_addr.hi;
-			single_sge->sge_len = bd[0].sge_len;
-			qedi->cached_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
-			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
-			sgl_struct->sgl_addr.lo =
-						(u32)(cmd->io_tbl.sge_tbl_dma);
-			sgl_struct->sgl_addr.hi =
-				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 1);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES, 0);
-			sgl_struct->updated_sge_size = 0;
-			sgl_struct->updated_sge_offset = 0;
-			qedi->slow_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
-			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
-			sgl_struct->sgl_addr.lo =
-						(u32)(cmd->io_tbl.sge_tbl_dma);
-			sgl_struct->sgl_addr.hi =
-				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			sgl_struct->byte_offset =
-				(u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 0);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES, 0);
-			sgl_struct->updated_sge_size = 0;
-			sgl_struct->updated_sge_offset = 0;
-			qedi->fast_sgls++;
-		}
-		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
-		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
-	}
-
-	if (cmd->io_tbl.sge_valid == 1)
-		/* Singel-SGL */
-		qedi->use_cached_sge = true;
-	else {
+		tx_sgl_task_params.total_buffer_size = scsi_bufflen(sc);
+		tx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid;
 		if (cmd->use_slowpath)
-			qedi->use_slow_sge = true;
-		else
-			qedi->use_fast_sge = true;
-	}
+			tx_sgl_task_params.small_mid_sge = true;
+	} else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) {
+		rx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl;
+		rx_sgl_task_params.sgl_phys_addr.lo =
+						 (u32)(cmd->io_tbl.sge_tbl_dma);
+		rx_sgl_task_params.sgl_phys_addr.hi =
+				      (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+		rx_sgl_task_params.total_buffer_size = scsi_bufflen(sc);
+		rx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid;
+	}
+
+	/* Add conn param */
+	conn_params.first_burst_length = conn->session->first_burst;
+	conn_params.max_send_pdu_length = conn->max_xmit_dlength;
+	conn_params.max_burst_length = conn->session->max_burst;
+	if (conn->session->initial_r2t_en)
+		conn_params.initial_r2t = true;
+	if (conn->session->imm_data_en)
+		conn_params.immediate_data = true;
+
+	/* Add cmd params */
+	cmd_params.sense_data_buffer_phys_addr.lo = (u32)cmd->sense_buffer_dma;
+	cmd_params.sense_data_buffer_phys_addr.hi =
+					(u32)((u64)cmd->sense_buffer_dma >> 32);
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = cq_idx;
+	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE)
+		task_params.tx_io_size = scsi_bufflen(sc);
+	else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ)
+		task_params.rx_io_size = scsi_bufflen(sc);
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
-		  "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x",
+		  "%s: %s-SGL: sg_len=0x%x num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x\n",
 		  (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ?
 		  "Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ?
 		  "Single" : (cmd->use_slowpath ? "SLOW" : "FAST"),
-		  (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma),
+		  (u16)cmd->io_tbl.sge_valid, scsi_bufflen(sc),
+		  (u32)(cmd->io_tbl.sge_tbl_dma),
 		  (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32));
 
-	/*  Add command in active command list */
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+
+	if (task_params.tx_io_size != 0)
+		ptx_sgl = &tx_sgl_task_params;
+	if (task_params.rx_io_size != 0)
+		prx_sgl = &rx_sgl_task_params;
+
+	rval = init_initiator_rw_iscsi_task(&task_params, &conn_params,
+					    &cmd_params, &cmd_pdu_header,
+					    ptx_sgl, prx_sgl,
+					    NULL);
+	if (rval)
+		return -1;
+
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list);
 	cmd->io_cmd_in_list = true;
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
-	if (qedi_io_tracing)
-		qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ);
-
 	return 0;
 }
 
 int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted)
 {
+	struct iscsi_task_params task_params;
+	struct qedi_endpoint *ep;
 	struct iscsi_conn *conn = task->conn;
 	struct qedi_conn *qedi_conn = conn->dd_data;
 	struct qedi_cmd *cmd = task->dd_data;
-	s16 ptu_invalidate = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
 	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
 		  "issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n",
 		  cmd->task_id, get_itt(task->itt), task->state,
 		  cmd->state, qedi_conn->iscsi_conn_id);
 
-	qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true);
-	qedi_ring_doorbell(qedi_conn);
+	memset(&task_params, 0, sizeof(task_params));
+	ep = qedi_conn->ep;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+
+	task_params.sqe = &ep->sq[sq_idx];
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	task_params.itid = cmd->task_id;
 
+	rval = init_cleanup_task(&task_params);
+	if (rval)
+		return rval;
+
+	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c
new file mode 100644
index 000000000000..fd354d4e03eb
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_api.c
@@ -0,0 +1,781 @@
+/* QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+
+#include "qedi_fw_iscsi.h"
+#include "qedi_fw_scsi.h"
+
+#define SCSI_NUM_SGES_IN_CACHE 0x4
+
+static bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge)
+{
+	return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge);
+}
+
+static
+void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params,
+			   struct scsi_cached_sges *ctx_data_desc,
+			   struct scsi_sgl_task_params *sgl_task_params)
+{
+	u8 sge_index;
+	u8 num_sges;
+	u32 val;
+
+	num_sges = (sgl_task_params->num_sges > SCSI_NUM_SGES_IN_CACHE) ?
+			     SCSI_NUM_SGES_IN_CACHE : sgl_task_params->num_sges;
+
+	/* sgl params */
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo);
+	ctx_sgl_params->sgl_addr.lo = val;
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi);
+	ctx_sgl_params->sgl_addr.hi = val;
+	val = cpu_to_le32(sgl_task_params->total_buffer_size);
+	ctx_sgl_params->sgl_total_length = val;
+	ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges);
+
+	for (sge_index = 0; sge_index < num_sges; sge_index++) {
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo);
+		ctx_data_desc->sge[sge_index].sge_addr.lo = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi);
+		ctx_data_desc->sge[sge_index].sge_addr.hi = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len);
+		ctx_data_desc->sge[sge_index].sge_len = val;
+	}
+}
+
+static u32 calc_rw_task_size(struct iscsi_task_params *task_params,
+			     enum iscsi_task_type task_type,
+			     struct scsi_sgl_task_params *sgl_task_params,
+			     struct scsi_dif_task_params *dif_task_params)
+{
+	u32 io_size;
+
+	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE ||
+	    task_type == ISCSI_TASK_TYPE_TARGET_READ)
+		io_size = task_params->tx_io_size;
+	else
+		io_size = task_params->rx_io_size;
+
+	if (!io_size)
+		return 0;
+
+	if (!dif_task_params)
+		return io_size;
+
+	return !dif_task_params->dif_on_network ?
+	       io_size : sgl_task_params->total_buffer_size;
+}
+
+static void
+init_dif_context_flags(struct iscsi_dif_flags *ctx_dif_flags,
+		       struct scsi_dif_task_params *dif_task_params)
+{
+	if (!dif_task_params)
+		return;
+
+	SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG,
+		  dif_task_params->dif_block_size_log);
+	SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_DIF_TO_PEER,
+		  dif_task_params->dif_on_network ? 1 : 0);
+	SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_HOST_INTERFACE,
+		  dif_task_params->dif_on_host ? 1 : 0);
+}
+
+static void init_sqe(struct iscsi_task_params *task_params,
+		     struct scsi_sgl_task_params *sgl_task_params,
+		     struct scsi_dif_task_params *dif_task_params,
+		     struct iscsi_common_hdr *pdu_header,
+		     struct scsi_initiator_cmd_params *cmd_params,
+		     enum iscsi_task_type task_type,
+		     bool is_cleanup)
+{
+	if (!task_params->sqe)
+		return;
+
+	memset(task_params->sqe, 0, sizeof(*task_params->sqe));
+	task_params->sqe->task_id = cpu_to_le16(task_params->itid);
+	if (is_cleanup) {
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_TASK_CLEANUP);
+		return;
+	}
+
+	switch (task_type) {
+	case ISCSI_TASK_TYPE_INITIATOR_WRITE:
+	{
+		u32 buf_size = 0;
+		u32 num_sges = 0;
+
+		init_dif_context_flags(&task_params->sqe->prot_flags,
+				       dif_task_params);
+
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_NORMAL);
+
+		if (task_params->tx_io_size) {
+			buf_size = calc_rw_task_size(task_params, task_type,
+						     sgl_task_params,
+						     dif_task_params);
+
+		if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+				     sgl_task_params->small_mid_sge))
+			num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
+		else
+			num_sges = min(sgl_task_params->num_sges,
+				       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
+	}
+
+	SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges);
+	SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
+		  buf_size);
+
+	if (GET_FIELD(pdu_header->hdr_second_dword,
+		      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+		SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE,
+			  cmd_params->extended_cdb_sge.sge_len);
+	}
+		break;
+	case ISCSI_TASK_TYPE_INITIATOR_READ:
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_NORMAL);
+
+		if (GET_FIELD(pdu_header->hdr_second_dword,
+			      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+			SET_FIELD(task_params->sqe->contlen_cdbsize,
+				  ISCSI_WQE_CDB_SIZE,
+				  cmd_params->extended_cdb_sge.sge_len);
+		break;
+	case ISCSI_TASK_TYPE_LOGIN_RESPONSE:
+	case ISCSI_TASK_TYPE_MIDPATH:
+	{
+		bool advance_statsn = true;
+
+		if (task_type == ISCSI_TASK_TYPE_LOGIN_RESPONSE)
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+				  ISCSI_WQE_TYPE_LOGIN);
+		else
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+				  ISCSI_WQE_TYPE_MIDDLE_PATH);
+
+		if (task_type == ISCSI_TASK_TYPE_MIDPATH) {
+			u8 opcode = GET_FIELD(pdu_header->hdr_first_byte,
+					      ISCSI_COMMON_HDR_OPCODE);
+
+			if (opcode != ISCSI_OPCODE_TEXT_RESPONSE &&
+			    (opcode != ISCSI_OPCODE_NOP_IN ||
+			    pdu_header->itt == ISCSI_TTT_ALL_ONES))
+				advance_statsn = false;
+		}
+
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_RESPONSE,
+			  advance_statsn ? 1 : 0);
+
+		if (task_params->tx_io_size) {
+			SET_FIELD(task_params->sqe->contlen_cdbsize,
+				  ISCSI_WQE_CONT_LEN, task_params->tx_io_size);
+
+		if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+				     sgl_task_params->small_mid_sge))
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+				  ISCSI_WQE_NUM_SGES_SLOWIO);
+		else
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+				  min(sgl_task_params->num_sges,
+				      (u16)SCSI_NUM_SGES_SLOW_SGL_THR));
+		}
+	}
+		break;
+	default:
+		break;
+	}
+}
+
+static void init_default_iscsi_task(struct iscsi_task_params *task_params,
+				    struct data_hdr *pdu_header,
+				    enum iscsi_task_type task_type)
+{
+	struct iscsi_task_context *context;
+	u16 index;
+	u32 val;
+
+	context = task_params->context;
+	memset(context, 0, sizeof(*context));
+
+	for (index = 0; index <
+	     ARRAY_SIZE(context->ystorm_st_context.pdu_hdr.data.data);
+	     index++) {
+		val = cpu_to_le32(pdu_header->data[index]);
+		context->ystorm_st_context.pdu_hdr.data.data[index] = val;
+	}
+
+	context->mstorm_st_context.task_type = task_type;
+	context->mstorm_ag_context.task_cid =
+					    cpu_to_le16(task_params->conn_icid);
+
+	SET_FIELD(context->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	context->ustorm_st_context.task_type = task_type;
+	context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number;
+	context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid);
+}
+
+static
+void init_initiator_rw_cdb_ystorm_context(struct ystorm_iscsi_task_st_ctx *ystc,
+					  struct scsi_initiator_cmd_params *cmd)
+{
+	union iscsi_task_hdr *ctx_pdu_hdr = &ystc->pdu_hdr;
+	u32 val;
+
+	if (!cmd->extended_cdb_sge.sge_len)
+		return;
+
+	SET_FIELD(ctx_pdu_hdr->ext_cdb_cmd.hdr_second_dword,
+		  ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE,
+		  cmd->extended_cdb_sge.sge_len);
+	val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.lo);
+	ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.lo = val;
+	val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.hi);
+	ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.hi = val;
+	val = cpu_to_le32(cmd->extended_cdb_sge.sge_len);
+	ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_len  = val;
+}
+
+static
+void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt,
+			       struct ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt,
+			       u32 remaining_recv_len,
+			       u32 expected_data_transfer_len,
+			       u8 num_sges, bool tx_dif_conn_err_en)
+{
+	u32 val;
+
+	ustorm_st_cxt->rem_rcv_len = cpu_to_le32(remaining_recv_len);
+	ustorm_ag_cxt->exp_data_acked = cpu_to_le32(expected_data_transfer_len);
+	val = cpu_to_le32(expected_data_transfer_len);
+	ustorm_st_cxt->exp_data_transfer_len = val;
+	SET_FIELD(ustorm_st_cxt->reg1.reg1_map, ISCSI_REG1_NUM_SGES, num_sges);
+	SET_FIELD(ustorm_ag_cxt->flags2,
+		  USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN,
+		  tx_dif_conn_err_en ? 1 : 0);
+}
+
+static
+void set_rw_exp_data_acked_and_cont_len(struct iscsi_task_context *context,
+					struct iscsi_conn_params  *conn_params,
+					enum iscsi_task_type task_type,
+					u32 task_size,
+					u32 exp_data_transfer_len,
+					u8 total_ahs_length)
+{
+	u32 max_unsolicited_data = 0, val;
+
+	if (total_ahs_length &&
+	    (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE ||
+	     task_type == ISCSI_TASK_TYPE_INITIATOR_READ))
+		SET_FIELD(context->ustorm_st_context.flags2,
+			  USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST, 1);
+
+	switch (task_type) {
+	case ISCSI_TASK_TYPE_INITIATOR_WRITE:
+		if (!conn_params->initial_r2t)
+			max_unsolicited_data = conn_params->first_burst_length;
+		else if (conn_params->immediate_data)
+			max_unsolicited_data =
+					  min(conn_params->first_burst_length,
+					      conn_params->max_send_pdu_length);
+
+		context->ustorm_ag_context.exp_data_acked =
+				   cpu_to_le32(total_ahs_length == 0 ?
+						min(exp_data_transfer_len,
+						    max_unsolicited_data) :
+						((u32)(total_ahs_length +
+						       ISCSI_AHS_CNTL_SIZE)));
+		break;
+	case ISCSI_TASK_TYPE_TARGET_READ:
+		val = cpu_to_le32(exp_data_transfer_len);
+		context->ustorm_ag_context.exp_data_acked = val;
+		break;
+	case ISCSI_TASK_TYPE_INITIATOR_READ:
+		context->ustorm_ag_context.exp_data_acked =
+					cpu_to_le32((total_ahs_length == 0 ? 0 :
+						     total_ahs_length +
+						     ISCSI_AHS_CNTL_SIZE));
+		break;
+	case ISCSI_TASK_TYPE_TARGET_WRITE:
+		val = cpu_to_le32(task_size);
+		context->ustorm_ag_context.exp_cont_len = val;
+		break;
+	default:
+		break;
+	}
+}
+
+static
+void init_rtdif_task_context(struct rdif_task_context *rdif_context,
+			     struct tdif_task_context *tdif_context,
+			     struct scsi_dif_task_params *dif_task_params,
+			     enum iscsi_task_type task_type)
+{
+	u32 val;
+
+	if (!dif_task_params->dif_on_network || !dif_task_params->dif_on_host)
+		return;
+
+	if (task_type == ISCSI_TASK_TYPE_TARGET_WRITE ||
+	    task_type == ISCSI_TASK_TYPE_INITIATOR_READ) {
+		rdif_context->app_tag_value =
+				  cpu_to_le16(dif_task_params->application_tag);
+		rdif_context->partial_crc_value = cpu_to_le16(0xffff);
+		val = cpu_to_le32(dif_task_params->initial_ref_tag);
+		rdif_context->initial_ref_tag = val;
+		rdif_context->app_tag_mask =
+			     cpu_to_le16(dif_task_params->application_tag_mask);
+		SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_CRC_SEED,
+			  dif_task_params->crc_seed ? 1 : 0);
+		SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_HOSTGUARDTYPE,
+			  dif_task_params->host_guard_type);
+		SET_FIELD(rdif_context->flags0,
+			  RDIF_TASK_CONTEXT_PROTECTIONTYPE,
+			  dif_task_params->protection_type);
+		SET_FIELD(rdif_context->flags0,
+			  RDIF_TASK_CONTEXT_INITIALREFTAGVALID, 1);
+		SET_FIELD(rdif_context->flags0,
+			  RDIF_TASK_CONTEXT_KEEPREFTAGCONST,
+			  dif_task_params->keep_ref_tag_const ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_VALIDATEAPPTAG,
+			  (dif_task_params->validate_app_tag &&
+			  dif_task_params->dif_on_network) ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_VALIDATEGUARD,
+			  (dif_task_params->validate_guard &&
+			  dif_task_params->dif_on_network) ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_VALIDATEREFTAG,
+			  (dif_task_params->validate_ref_tag &&
+			  dif_task_params->dif_on_network) ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_HOSTINTERFACE,
+			  dif_task_params->dif_on_host ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_NETWORKINTERFACE,
+			  dif_task_params->dif_on_network ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDGUARD,
+			  dif_task_params->forward_guard ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDAPPTAG,
+			  dif_task_params->forward_app_tag ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDREFTAG,
+			  dif_task_params->forward_ref_tag ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK,
+			  dif_task_params->forward_app_tag_with_mask ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK,
+			  dif_task_params->forward_ref_tag_with_mask ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_INTERVALSIZE,
+			  dif_task_params->dif_block_size_log - 9);
+		SET_FIELD(rdif_context->state,
+			  RDIF_TASK_CONTEXT_REFTAGMASK,
+			  dif_task_params->ref_tag_mask);
+		SET_FIELD(rdif_context->state, RDIF_TASK_CONTEXT_IGNOREAPPTAG,
+			  dif_task_params->ignore_app_tag);
+	}
+
+	if (task_type == ISCSI_TASK_TYPE_TARGET_READ ||
+	    task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
+		tdif_context->app_tag_value =
+				  cpu_to_le16(dif_task_params->application_tag);
+		tdif_context->partial_crc_valueB =
+		       cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000);
+		tdif_context->partial_crc_value_a =
+		       cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000);
+		SET_FIELD(tdif_context->flags0, TDIF_TASK_CONTEXT_CRC_SEED,
+			  dif_task_params->crc_seed ? 1 : 0);
+
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_SETERRORWITHEOP,
+			  dif_task_params->tx_dif_conn_err_en ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDGUARD,
+			  dif_task_params->forward_guard   ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDAPPTAG,
+			  dif_task_params->forward_app_tag ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDREFTAG,
+			  dif_task_params->forward_ref_tag ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_INTERVALSIZE,
+			  dif_task_params->dif_block_size_log - 9);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_HOSTINTERFACE,
+			  dif_task_params->dif_on_host    ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_NETWORKINTERFACE,
+			  dif_task_params->dif_on_network ? 1 : 0);
+		val = cpu_to_le32(dif_task_params->initial_ref_tag);
+		tdif_context->initial_ref_tag = val;
+		tdif_context->app_tag_mask =
+			     cpu_to_le16(dif_task_params->application_tag_mask);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_HOSTGUARDTYPE,
+			  dif_task_params->host_guard_type);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_PROTECTIONTYPE,
+			  dif_task_params->protection_type);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_INITIALREFTAGVALID,
+			  dif_task_params->initial_ref_tag_is_valid ? 1 : 0);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_KEEPREFTAGCONST,
+			  dif_task_params->keep_ref_tag_const ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_VALIDATEGUARD,
+			  (dif_task_params->validate_guard &&
+			   dif_task_params->dif_on_host) ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_VALIDATEAPPTAG,
+			  (dif_task_params->validate_app_tag &&
+			  dif_task_params->dif_on_host) ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_VALIDATEREFTAG,
+			  (dif_task_params->validate_ref_tag &&
+			   dif_task_params->dif_on_host) ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK,
+			  dif_task_params->forward_app_tag_with_mask ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK,
+			  dif_task_params->forward_ref_tag_with_mask ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_REFTAGMASK,
+			  dif_task_params->ref_tag_mask);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_IGNOREAPPTAG,
+			  dif_task_params->ignore_app_tag ? 1 : 0);
+	}
+}
+
+static void set_local_completion_context(struct iscsi_task_context *context)
+{
+	SET_FIELD(context->ystorm_st_context.state.flags,
+		  YSTORM_ISCSI_TASK_STATE_LOCAL_COMP, 1);
+	SET_FIELD(context->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+}
+
+static int init_rw_iscsi_task(struct iscsi_task_params *task_params,
+			      enum iscsi_task_type task_type,
+			      struct iscsi_conn_params *conn_params,
+			      struct iscsi_common_hdr *pdu_header,
+			      struct scsi_sgl_task_params *sgl_task_params,
+			      struct scsi_initiator_cmd_params *cmd_params,
+			      struct scsi_dif_task_params *dif_task_params)
+{
+	u32 exp_data_transfer_len = conn_params->max_burst_length;
+	struct iscsi_task_context *cxt;
+	bool slow_io = false;
+	u32 task_size, val;
+	u8 num_sges = 0;
+
+	task_size = calc_rw_task_size(task_params, task_type, sgl_task_params,
+				      dif_task_params);
+
+	init_default_iscsi_task(task_params, (struct data_hdr *)pdu_header,
+				task_type);
+
+	cxt = task_params->context;
+
+	val = cpu_to_le32(task_size);
+	cxt->ystorm_st_context.pdu_hdr.cmd.expected_transfer_length = val;
+	init_initiator_rw_cdb_ystorm_context(&cxt->ystorm_st_context,
+					     cmd_params);
+	val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.lo);
+	cxt->mstorm_st_context.sense_db.lo = val;
+
+	val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.hi);
+	cxt->mstorm_st_context.sense_db.hi = val;
+
+	if (task_params->tx_io_size) {
+		init_dif_context_flags(&cxt->ystorm_st_context.state.dif_flags,
+				       dif_task_params);
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      sgl_task_params);
+
+		slow_io = scsi_is_slow_sgl(sgl_task_params->num_sges,
+					   sgl_task_params->small_mid_sge);
+
+		num_sges = !slow_io ? min_t(u16, sgl_task_params->num_sges,
+					    (u16)SCSI_NUM_SGES_SLOW_SGL_THR) :
+				      ISCSI_WQE_NUM_SGES_SLOWIO;
+
+		if (slow_io) {
+			SET_FIELD(cxt->ystorm_st_context.state.flags,
+				  YSTORM_ISCSI_TASK_STATE_SLOW_IO, 1);
+		}
+	} else if (task_params->rx_io_size) {
+		init_dif_context_flags(&cxt->mstorm_st_context.dif_flags,
+				       dif_task_params);
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      sgl_task_params);
+		num_sges = !scsi_is_slow_sgl(sgl_task_params->num_sges,
+				sgl_task_params->small_mid_sge) ?
+				min_t(u16, sgl_task_params->num_sges,
+				      (u16)SCSI_NUM_SGES_SLOW_SGL_THR) :
+				ISCSI_WQE_NUM_SGES_SLOWIO;
+		cxt->mstorm_st_context.rem_task_size = cpu_to_le32(task_size);
+	}
+
+	if (exp_data_transfer_len > task_size  ||
+	    task_type != ISCSI_TASK_TYPE_TARGET_WRITE)
+		exp_data_transfer_len = task_size;
+
+	init_ustorm_task_contexts(&task_params->context->ustorm_st_context,
+				  &task_params->context->ustorm_ag_context,
+				  task_size, exp_data_transfer_len, num_sges,
+				  dif_task_params ?
+				  dif_task_params->tx_dif_conn_err_en : false);
+
+	set_rw_exp_data_acked_and_cont_len(task_params->context, conn_params,
+					   task_type, task_size,
+					   exp_data_transfer_len,
+					GET_FIELD(pdu_header->hdr_second_dword,
+						  ISCSI_CMD_HDR_TOTAL_AHS_LEN));
+
+	if (dif_task_params)
+		init_rtdif_task_context(&task_params->context->rdif_context,
+					&task_params->context->tdif_context,
+					dif_task_params, task_type);
+
+	init_sqe(task_params, sgl_task_params, dif_task_params, pdu_header,
+		 cmd_params, task_type, false);
+
+	return 0;
+}
+
+int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params,
+				 struct iscsi_conn_params *conn_params,
+				 struct scsi_initiator_cmd_params *cmd_params,
+				 struct iscsi_cmd_hdr *cmd_header,
+				 struct scsi_sgl_task_params *tx_sgl_params,
+				 struct scsi_sgl_task_params *rx_sgl_params,
+				 struct scsi_dif_task_params *dif_task_params)
+{
+	if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_WRITE))
+		return init_rw_iscsi_task(task_params,
+					  ISCSI_TASK_TYPE_INITIATOR_WRITE,
+					  conn_params,
+					  (struct iscsi_common_hdr *)cmd_header,
+					  tx_sgl_params, cmd_params,
+					  dif_task_params);
+	else if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_READ))
+		return init_rw_iscsi_task(task_params,
+					  ISCSI_TASK_TYPE_INITIATOR_READ,
+					  conn_params,
+					  (struct iscsi_common_hdr *)cmd_header,
+					  rx_sgl_params, cmd_params,
+					  dif_task_params);
+	else
+		return -1;
+}
+
+int init_initiator_login_request_task(struct iscsi_task_params *task_params,
+				      struct iscsi_login_req_hdr  *login_header,
+				      struct scsi_sgl_task_params *tx_params,
+				      struct scsi_sgl_task_params *rx_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)login_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_params->total_buffer_size : 0, 0,
+				  0);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_params);
+
+	cxt->mstorm_st_context.rem_task_size =
+			cpu_to_le32(task_params->rx_io_size ?
+				    rx_params->total_buffer_size : 0);
+
+	init_sqe(task_params, tx_params, NULL,
+		 (struct iscsi_common_hdr *)login_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_nop_out_task(struct iscsi_task_params *task_params,
+				struct iscsi_nop_out_hdr *nop_out_pdu_header,
+				struct scsi_sgl_task_params *tx_sgl_task_params,
+				struct scsi_sgl_task_params *rx_sgl_task_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)nop_out_pdu_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	if (nop_out_pdu_header->itt == ISCSI_ITT_ALL_ONES)
+		set_local_completion_context(task_params->context);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_sgl_task_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_sgl_task_params);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_sgl_task_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_sgl_task_params->total_buffer_size : 0,
+				  0, 0);
+
+	cxt->mstorm_st_context.rem_task_size =
+				cpu_to_le32(task_params->rx_io_size ?
+					rx_sgl_task_params->total_buffer_size :
+					0);
+
+	init_sqe(task_params, tx_sgl_task_params, NULL,
+		 (struct iscsi_common_hdr *)nop_out_pdu_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_logout_request_task(struct iscsi_task_params *task_params,
+				       struct iscsi_logout_req_hdr *logout_hdr,
+				       struct scsi_sgl_task_params *tx_params,
+				       struct scsi_sgl_task_params *rx_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)logout_hdr,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_params);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_params->total_buffer_size : 0,
+				  0, 0);
+
+	cxt->mstorm_st_context.rem_task_size =
+					cpu_to_le32(task_params->rx_io_size ?
+					rx_params->total_buffer_size : 0);
+
+	init_sqe(task_params, tx_params, NULL,
+		 (struct iscsi_common_hdr *)logout_hdr, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_tmf_request_task(struct iscsi_task_params *task_params,
+				    struct iscsi_tmf_request_hdr *tmf_header)
+{
+	init_default_iscsi_task(task_params, (struct data_hdr *)tmf_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	init_sqe(task_params, NULL, NULL,
+		 (struct iscsi_common_hdr *)tmf_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_text_request_task(struct iscsi_task_params *task_params,
+				     struct iscsi_text_request_hdr *text_header,
+				     struct scsi_sgl_task_params *tx_params,
+				     struct scsi_sgl_task_params *rx_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)text_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_params);
+
+	cxt->mstorm_st_context.rem_task_size =
+				cpu_to_le32(task_params->rx_io_size ?
+					rx_params->total_buffer_size : 0);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_params->total_buffer_size : 0, 0, 0);
+
+	init_sqe(task_params, tx_params, NULL,
+		 (struct iscsi_common_hdr *)text_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_cleanup_task(struct iscsi_task_params *task_params)
+{
+	init_sqe(task_params, NULL, NULL, NULL, NULL, ISCSI_TASK_TYPE_MIDPATH,
+		 true);
+	return 0;
+}
diff --git a/drivers/scsi/qedi/qedi_fw_iscsi.h b/drivers/scsi/qedi/qedi_fw_iscsi.h
new file mode 100644
index 000000000000..b6f24f91849d
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_iscsi.h
@@ -0,0 +1,117 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_FW_ISCSI_H_
+#define _QEDI_FW_ISCSI_H_
+
+#include "qedi_fw_scsi.h"
+
+struct iscsi_task_params {
+	struct iscsi_task_context *context;
+	struct iscsi_wqe	  *sqe;
+	u32			  tx_io_size;
+	u32			  rx_io_size;
+	u16			  conn_icid;
+	u16			  itid;
+	u8			  cq_rss_number;
+};
+
+struct iscsi_conn_params {
+	u32	first_burst_length;
+	u32	max_send_pdu_length;
+	u32	max_burst_length;
+	bool	initial_r2t;
+	bool	immediate_data;
+};
+
+/* @brief init_initiator_read_iscsi_task - initializes iSCSI Initiator Read
+ * task context.
+ *
+ * @param task_params	  - Pointer to task parameters struct
+ * @param conn_params	  - Connection Parameters
+ * @param cmd_params	  - command specific parameters
+ * @param cmd_pdu_header  - PDU Header Parameters
+ * @param sgl_task_params - Pointer to SGL task params
+ * @param dif_task_params - Pointer to DIF parameters struct
+ */
+int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params,
+				 struct iscsi_conn_params *conn_params,
+				 struct scsi_initiator_cmd_params *cmd_params,
+				 struct iscsi_cmd_hdr *cmd_pdu_header,
+				 struct scsi_sgl_task_params *tx_sgl_params,
+				 struct scsi_sgl_task_params *rx_sgl_params,
+				 struct scsi_dif_task_params *dif_task_params);
+
+/* @brief init_initiator_login_request_task - initializes iSCSI Initiator Login
+ * Request task context.
+ *
+ * @param task_params		  - Pointer to task parameters struct
+ * @param login_req_pdu_header    - PDU Header Parameters
+ * @param tx_sgl_task_params	  - Pointer to SGL task params
+ * @param rx_sgl_task_params	  - Pointer to SGL task params
+ */
+int init_initiator_login_request_task(struct iscsi_task_params *task_params,
+				      struct iscsi_login_req_hdr *login_header,
+				      struct scsi_sgl_task_params *tx_params,
+				      struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_initiator_nop_out_task - initializes iSCSI Initiator NOP Out
+ * task context.
+ *
+ * @param task_params		- Pointer to task parameters struct
+ * @param nop_out_pdu_header    - PDU Header Parameters
+ * @param tx_sgl_task_params	- Pointer to SGL task params
+ * @param rx_sgl_task_params	- Pointer to SGL task params
+ */
+int init_initiator_nop_out_task(struct iscsi_task_params *task_params,
+				struct iscsi_nop_out_hdr *nop_out_pdu_header,
+				struct scsi_sgl_task_params *tx_sgl_params,
+				struct scsi_sgl_task_params *rx_sgl_params);
+
+/* @brief init_initiator_logout_request_task - initializes iSCSI Initiator
+ * Logout Request task context.
+ *
+ * @param task_params		- Pointer to task parameters struct
+ * @param logout_pdu_header  - PDU Header Parameters
+ * @param tx_sgl_task_params	- Pointer to SGL task params
+ * @param rx_sgl_task_params	- Pointer to SGL task params
+ */
+int init_initiator_logout_request_task(struct iscsi_task_params *task_params,
+				       struct iscsi_logout_req_hdr *logout_hdr,
+				       struct scsi_sgl_task_params *tx_params,
+				       struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_initiator_tmf_request_task - initializes iSCSI Initiator TMF
+ * task context.
+ *
+ * @param task_params	- Pointer to task parameters struct
+ * @param tmf_pdu_header - PDU Header Parameters
+ */
+int init_initiator_tmf_request_task(struct iscsi_task_params *task_params,
+				    struct iscsi_tmf_request_hdr *tmf_header);
+
+/* @brief init_initiator_text_request_task - initializes iSCSI Initiator Text
+ * Request task context.
+ *
+ * @param task_params		     - Pointer to task parameters struct
+ * @param text_request_pdu_header    - PDU Header Parameters
+ * @param tx_sgl_task_params	     - Pointer to Tx SGL task params
+ * @param rx_sgl_task_params	     - Pointer to Rx SGL task params
+ */
+int init_initiator_text_request_task(struct iscsi_task_params *task_params,
+				     struct iscsi_text_request_hdr *text_header,
+				     struct scsi_sgl_task_params *tx_params,
+				     struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_cleanup_task - initializes Clean task (SQE)
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_cleanup_task(struct iscsi_task_params *task_params);
+#endif
diff --git a/drivers/scsi/qedi/qedi_fw_scsi.h b/drivers/scsi/qedi/qedi_fw_scsi.h
new file mode 100644
index 000000000000..cdaf918f1019
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_scsi.h
@@ -0,0 +1,55 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_FW_SCSI_H_
+#define _QEDI_FW_SCSI_H_
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+
+struct scsi_sgl_task_params {
+	struct scsi_sge	*sgl;
+	struct regpair	sgl_phys_addr;
+	u32		total_buffer_size;
+	u16		num_sges;
+	bool		small_mid_sge;
+};
+
+struct scsi_dif_task_params {
+	u32	initial_ref_tag;
+	bool	initial_ref_tag_is_valid;
+	u16	application_tag;
+	u16	application_tag_mask;
+	u16	dif_block_size_log;
+	bool	dif_on_network;
+	bool	dif_on_host;
+	u8	host_guard_type;
+	u8	protection_type;
+	u8	ref_tag_mask;
+	bool	crc_seed;
+	bool	tx_dif_conn_err_en;
+	bool	ignore_app_tag;
+	bool	keep_ref_tag_const;
+	bool	validate_guard;
+	bool	validate_app_tag;
+	bool	validate_ref_tag;
+	bool	forward_guard;
+	bool	forward_app_tag;
+	bool	forward_ref_tag;
+	bool	forward_app_tag_with_mask;
+	bool	forward_ref_tag_with_mask;
+};
+
+struct scsi_initiator_cmd_params {
+	struct scsi_sge	extended_cdb_sge;
+	struct regpair	sense_data_buffer_phys_addr;
+};
+#endif
diff --git a/drivers/scsi/qedi/qedi_gbl.h b/drivers/scsi/qedi/qedi_gbl.h
index 8e488de88ece..63d793f46064 100644
--- a/drivers/scsi/qedi/qedi_gbl.h
+++ b/drivers/scsi/qedi/qedi_gbl.h
@@ -12,8 +12,14 @@
 
 #include "qedi_iscsi.h"
 
+#ifdef CONFIG_DEBUG_FS
+extern int qedi_do_not_recover;
+#else
+#define qedi_do_not_recover (0)
+#endif
+
 extern uint qedi_io_tracing;
-extern int do_not_recover;
+
 extern struct scsi_host_template qedi_host_template;
 extern struct iscsi_transport qedi_iscsi_transport;
 extern const struct qed_iscsi_ops *qedi_ops;
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index b9f79d36142d..d1de172bebac 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -175,7 +175,7 @@ static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi,
 		if (cmd->io_tbl.sge_tbl)
 			dma_free_coherent(&qedi->pdev->dev,
 					  QEDI_ISCSI_MAX_BDS_PER_CMD *
-					  sizeof(struct iscsi_sge),
+					  sizeof(struct scsi_sge),
 					  cmd->io_tbl.sge_tbl,
 					  cmd->io_tbl.sge_tbl_dma);
 
@@ -191,7 +191,7 @@ static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session,
 			   struct qedi_cmd *cmd)
 {
 	struct qedi_io_bdt *io = &cmd->io_tbl;
-	struct iscsi_sge *sge;
+	struct scsi_sge *sge;
 
 	io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev,
 					 QEDI_ISCSI_MAX_BDS_PER_CMD *
@@ -708,22 +708,20 @@ static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn,
 
 static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn)
 {
-	struct iscsi_sge *bd_tbl;
+	struct scsi_sge *bd_tbl;
 
-	bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
 
 	bd_tbl->sge_addr.hi =
 		(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
 	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr;
 	bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr -
 				qedi_conn->gen_pdu.req_buf;
-	bd_tbl->reserved0 = 0;
-	bd_tbl = (struct iscsi_sge  *)qedi_conn->gen_pdu.resp_bd_tbl;
+	bd_tbl = (struct scsi_sge  *)qedi_conn->gen_pdu.resp_bd_tbl;
 	bd_tbl->sge_addr.hi =
 			(u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
 	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr;
 	bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN;
-	bd_tbl->reserved0 = 0;
 }
 
 static int qedi_iscsi_send_generic_request(struct iscsi_task *task)
@@ -833,7 +831,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr,
 		return ERR_PTR(ret);
 	}
 
-	if (do_not_recover) {
+	if (qedi_do_not_recover) {
 		ret = -ENOMEM;
 		return ERR_PTR(ret);
 	}
@@ -957,7 +955,7 @@ static int qedi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
 	struct qedi_endpoint *qedi_ep;
 	int ret = 0;
 
-	if (do_not_recover)
+	if (qedi_do_not_recover)
 		return 1;
 
 	qedi_ep = ep->dd_data;
@@ -1025,7 +1023,7 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 		}
 
 		if (test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
-			if (do_not_recover) {
+			if (qedi_do_not_recover) {
 				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
 					  "Do not recover cid=0x%x\n",
 					  qedi_ep->iscsi_cid);
@@ -1039,7 +1037,7 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 		}
 	}
 
-	if (do_not_recover)
+	if (qedi_do_not_recover)
 		goto ep_exit_recover;
 
 	switch (qedi_ep->state) {
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
index d3c06bbddb4e..3247287cb0e7 100644
--- a/drivers/scsi/qedi/qedi_iscsi.h
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -102,7 +102,7 @@ struct qedi_endpoint {
 #define QEDI_SQ_WQES_MIN	16
 
 struct qedi_io_bdt {
-	struct iscsi_sge *sge_tbl;
+	struct scsi_sge *sge_tbl;
 	dma_addr_t sge_tbl_dma;
 	u16 sge_valid;
 };
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 5eda21d903e9..92775a8b74b1 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1805,7 +1805,7 @@ static int __qedi_probe(struct pci_dev *pdev, int mode)
 	 */
 	qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
 
-	qedi_setup_int(qedi);
+	rc = qedi_setup_int(qedi);
 	if (rc)
 		goto stop_iscsi_func;
 
@@ -2007,6 +2007,7 @@ static void qedi_remove(struct pci_dev *pdev)
 
 static struct pci_device_id qedi_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165E) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x8084) },
 	{ 0 },
 };
 MODULE_DEVICE_TABLE(pci, qedi_pci_tbl);
diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h
index 9543a1b139d4..d61e3ac22e67 100644
--- a/drivers/scsi/qedi/qedi_version.h
+++ b/drivers/scsi/qedi/qedi_version.h
@@ -7,8 +7,8 @@
  * this source tree.
  */
 
-#define QEDI_MODULE_VERSION	"8.10.3.0"
+#define QEDI_MODULE_VERSION	"8.10.4.0"
 #define QEDI_DRIVER_MAJOR_VER		8
 #define QEDI_DRIVER_MINOR_VER		10
-#define QEDI_DRIVER_REV_VER		3
+#define QEDI_DRIVER_REV_VER		4
 #define QEDI_DRIVER_ENG_VER		0
diff --git a/drivers/scsi/qla2xxx/Kconfig b/drivers/scsi/qla2xxx/Kconfig
index 67c0d5aa3212..de952935b5d2 100644
--- a/drivers/scsi/qla2xxx/Kconfig
+++ b/drivers/scsi/qla2xxx/Kconfig
@@ -3,6 +3,7 @@ config SCSI_QLA_FC
 	depends on PCI && SCSI
 	depends on SCSI_FC_ATTRS
 	select FW_LOADER
+	select BTREE
 	---help---
 	This qla2xxx driver supports all QLogic Fibre Channel
 	PCI and PCIe host adapters.
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index f610103994af..435ff7fd6384 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2154,8 +2154,6 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 		    "Timer for the VP[%d] has stopped\n", vha->vp_idx);
 	}
 
-	BUG_ON(atomic_read(&vha->vref_count));
-
 	qla2x00_free_fcports(vha);
 
 	mutex_lock(&ha->vport_lock);
@@ -2166,7 +2164,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	dma_free_coherent(&ha->pdev->dev, vha->gnl.size, vha->gnl.l,
 	    vha->gnl.ldma);
 
-	if (vha->qpair->vp_idx == vha->vp_idx) {
+	if (vha->qpair && vha->qpair->vp_idx == vha->vp_idx) {
 		if (qla2xxx_delete_qpair(vha, vha->qpair) != QLA_SUCCESS)
 			ql_log(ql_log_warn, vha, 0x7087,
 			    "Queue Pair delete failed.\n");
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 84c9098cc089..b6e40fd4c3c1 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -2553,13 +2553,13 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
 						ql_log(ql_log_warn, vha, 0x7089,
 						    "mbx abort_command "
 						    "failed.\n");
-						bsg_job->req->errors =
+						scsi_req(bsg_job->req)->result =
 						bsg_reply->result = -EIO;
 					} else {
 						ql_dbg(ql_dbg_user, vha, 0x708a,
 						    "mbx abort_command "
 						    "success.\n");
-						bsg_job->req->errors =
+						scsi_req(bsg_job->req)->result =
 						bsg_reply->result = 0;
 					}
 					spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -2570,7 +2570,7 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	ql_log(ql_log_info, vha, 0x708b, "SRB not found to abort.\n");
-	bsg_job->req->errors = bsg_reply->result = -ENXIO;
+	scsi_req(bsg_job->req)->result = bsg_reply->result = -ENXIO;
 	return 0;
 
 done:
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 21d9fb7fc887..51b4179469d1 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -2707,13 +2707,9 @@ ql_dump_buffer(uint32_t level, scsi_qla_host_t *vha, int32_t id,
 	    "%-+5d  0  1  2  3  4  5  6  7  8  9  A  B  C  D  E  F\n", size);
 	ql_dbg(level, vha, id,
 	    "----- -----------------------------------------------\n");
-	for (cnt = 0; cnt < size; cnt++, buf++) {
-		if (cnt % 16 == 0)
-			ql_dbg(level, vha, id, "%04x:", cnt & ~0xFU);
-		printk(" %02x", *buf);
-		if (cnt % 16 == 15)
-			printk("\n");
+	for (cnt = 0; cnt < size; cnt += 16) {
+		ql_dbg(level, vha, id, "%04x: ", cnt);
+		print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1,
+			       buf + cnt, min(16U, size - cnt), false);
 	}
-	if (cnt % 16 != 0)
-		printk("\n");
 }
diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h
index e1fc4e66966a..c6bffe929fe7 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.h
+++ b/drivers/scsi/qla2xxx/qla_dbg.h
@@ -348,6 +348,7 @@ ql_log_pci(uint32_t, struct pci_dev *pdev, int32_t, const char *fmt, ...);
 #define ql_dbg_tgt	0x00004000 /* Target mode */
 #define ql_dbg_tgt_mgt	0x00002000 /* Target mode management */
 #define ql_dbg_tgt_tmr	0x00001000 /* Target mode task management */
+#define ql_dbg_tgt_dif  0x00000800 /* Target mode dif */
 
 extern int qla27xx_dump_mpi_ram(struct qla_hw_data *, uint32_t, uint32_t *,
 	uint32_t, void **);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 625d438e3cce..ae119018dfaa 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -25,6 +25,7 @@
 #include <linux/firmware.h>
 #include <linux/aer.h>
 #include <linux/mutex.h>
+#include <linux/btree.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
@@ -395,11 +396,15 @@ struct srb_iocb {
 			struct completion comp;
 		} abt;
 		struct ct_arg ctarg;
+#define MAX_IOCB_MB_REG 28
+#define SIZEOF_IOCB_MB_REG (MAX_IOCB_MB_REG * sizeof(uint16_t))
 		struct {
-			__le16 in_mb[28]; 	/* fr fw */
-			__le16 out_mb[28];	/* to fw */
+			__le16 in_mb[MAX_IOCB_MB_REG];	/* from FW */
+			__le16 out_mb[MAX_IOCB_MB_REG];	/* to FW */
 			void *out, *in;
 			dma_addr_t out_dma, in_dma;
+			struct completion comp;
+			int rc;
 		} mbx;
 		struct {
 			struct imm_ntfy_from_isp *ntfy;
@@ -437,7 +442,7 @@ typedef struct srb {
 	uint32_t handle;
 	uint16_t flags;
 	uint16_t type;
-	char *name;
+	const char *name;
 	int iocbs;
 	struct qla_qpair *qpair;
 	u32 gen1;	/* scratch */
@@ -2300,6 +2305,8 @@ typedef struct fc_port {
 	struct ct_sns_desc ct_desc;
 	enum discovery_state disc_state;
 	enum login_state fw_login_state;
+	unsigned long plogi_nack_done_deadline;
+
 	u32 login_gen, last_login_gen;
 	u32 rscn_gen, last_rscn_gen;
 	u32 chip_reset;
@@ -3106,6 +3113,16 @@ struct qla_chip_state_84xx {
 	uint32_t gold_fw_version;
 };
 
+struct qla_dif_statistics {
+	uint64_t dif_input_bytes;
+	uint64_t dif_output_bytes;
+	uint64_t dif_input_requests;
+	uint64_t dif_output_requests;
+	uint32_t dif_guard_err;
+	uint32_t dif_ref_tag_err;
+	uint32_t dif_app_tag_err;
+};
+
 struct qla_statistics {
 	uint32_t total_isp_aborts;
 	uint64_t input_bytes;
@@ -3118,6 +3135,8 @@ struct qla_statistics {
 	uint32_t stat_max_pend_cmds;
 	uint32_t stat_max_qfull_cmds_alloc;
 	uint32_t stat_max_qfull_cmds_dropped;
+
+	struct qla_dif_statistics qla_dif_stats;
 };
 
 struct bidi_statistics {
@@ -3125,6 +3144,16 @@ struct bidi_statistics {
 	unsigned long long transfer_bytes;
 };
 
+struct qla_tc_param {
+	struct scsi_qla_host *vha;
+	uint32_t blk_sz;
+	uint32_t bufflen;
+	struct scatterlist *sg;
+	struct scatterlist *prot_sg;
+	struct crc_context *ctx;
+	uint8_t *ctx_dsd_alloced;
+};
+
 /* Multi queue support */
 #define MBC_INITIALIZE_MULTIQ 0x1f
 #define QLA_QUE_PAGE 0X1000
@@ -3272,6 +3301,8 @@ struct qlt_hw_data {
 	uint8_t tgt_node_name[WWN_SIZE];
 
 	struct dentry *dfs_tgt_sess;
+	struct dentry *dfs_tgt_port_database;
+
 	struct list_head q_full_list;
 	uint32_t num_pend_cmds;
 	uint32_t num_qfull_cmds_alloc;
@@ -3281,6 +3312,7 @@ struct qlt_hw_data {
 	spinlock_t sess_lock;
 	int rspq_vector_cpuid;
 	spinlock_t atio_lock ____cacheline_aligned;
+	struct btree_head32 host_map;
 };
 
 #define MAX_QFULL_CMDS_ALLOC	8192
@@ -3290,6 +3322,10 @@ struct qlt_hw_data {
 
 #define LEAK_EXCHG_THRESH_HOLD_PERCENT 75	/* 75 percent */
 
+#define QLA_EARLY_LINKUP(_ha) \
+	((_ha->flags.n2n_ae || _ha->flags.lip_ae) && \
+	 _ha->flags.fw_started && !_ha->flags.fw_init_done)
+
 /*
  * Qlogic host adapter specific data structure.
 */
@@ -3339,7 +3375,11 @@ struct qla_hw_data {
 		uint32_t	fawwpn_enabled:1;
 		uint32_t	exlogins_enabled:1;
 		uint32_t	exchoffld_enabled:1;
-		/* 35 bits */
+
+		uint32_t	lip_ae:1;
+		uint32_t	n2n_ae:1;
+		uint32_t	fw_started:1;
+		uint32_t	fw_init_done:1;
 	} flags;
 
 	/* This spinlock is used to protect "io transactions", you must
@@ -3432,7 +3472,6 @@ struct qla_hw_data {
 #define P2P_LOOP  3
 	uint8_t		interrupts_on;
 	uint32_t	isp_abort_cnt;
-
 #define PCI_DEVICE_ID_QLOGIC_ISP2532    0x2532
 #define PCI_DEVICE_ID_QLOGIC_ISP8432    0x8432
 #define PCI_DEVICE_ID_QLOGIC_ISP8001	0x8001
@@ -3913,6 +3952,7 @@ typedef struct scsi_qla_host {
 	struct list_head vp_fcports;	/* list of fcports */
 	struct list_head work_list;
 	spinlock_t work_lock;
+	struct work_struct iocb_work;
 
 	/* Commonly used flags and state information. */
 	struct Scsi_Host *host;
@@ -4076,6 +4116,7 @@ typedef struct scsi_qla_host {
 	/* Count of active session/fcport */
 	int fcport_count;
 	wait_queue_head_t fcport_waitQ;
+	wait_queue_head_t vref_waitq;
 } scsi_qla_host_t;
 
 struct qla27xx_image_status {
@@ -4131,14 +4172,17 @@ struct qla2_sgx {
 	mb();						\
 	if (__vha->flags.delete_progress) {		\
 		atomic_dec(&__vha->vref_count);		\
+		wake_up(&__vha->vref_waitq);		\
 		__bail = 1;				\
 	} else {					\
 		__bail = 0;				\
 	}						\
 } while (0)
 
-#define QLA_VHA_MARK_NOT_BUSY(__vha)			\
+#define QLA_VHA_MARK_NOT_BUSY(__vha) do {		\
 	atomic_dec(&__vha->vref_count);			\
+	wake_up(&__vha->vref_waitq);			\
+} while (0)						\
 
 #define QLA_QPAIR_MARK_BUSY(__qpair, __bail) do {	\
 	atomic_inc(&__qpair->ref_count);		\
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index b48cce696bac..989e17b0758c 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -19,11 +19,11 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused)
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
 	struct fc_port *sess = NULL;
-	struct qla_tgt *tgt= vha->vha_tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 
-	seq_printf(s, "%s\n",vha->host_str);
+	seq_printf(s, "%s\n", vha->host_str);
 	if (tgt) {
-		seq_printf(s, "Port ID   Port Name                Handle\n");
+		seq_puts(s, "Port ID   Port Name                Handle\n");
 
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 		list_for_each_entry(sess, &vha->vp_fcports, list)
@@ -44,7 +44,6 @@ qla2x00_dfs_tgt_sess_open(struct inode *inode, struct file *file)
 	return single_open(file, qla2x00_dfs_tgt_sess_show, vha);
 }
 
-
 static const struct file_operations dfs_tgt_sess_ops = {
 	.open		= qla2x00_dfs_tgt_sess_open,
 	.read		= seq_read,
@@ -53,6 +52,78 @@ static const struct file_operations dfs_tgt_sess_ops = {
 };
 
 static int
+qla2x00_dfs_tgt_port_database_show(struct seq_file *s, void *unused)
+{
+	scsi_qla_host_t *vha = s->private;
+	struct qla_hw_data *ha = vha->hw;
+	struct gid_list_info *gid_list;
+	dma_addr_t gid_list_dma;
+	fc_port_t fc_port;
+	char *id_iter;
+	int rc, i;
+	uint16_t entries, loop_id;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+
+	seq_printf(s, "%s\n", vha->host_str);
+	if (tgt) {
+		gid_list = dma_alloc_coherent(&ha->pdev->dev,
+		    qla2x00_gid_list_size(ha),
+		    &gid_list_dma, GFP_KERNEL);
+		if (!gid_list) {
+			ql_dbg(ql_dbg_user, vha, 0x705c,
+			    "DMA allocation failed for %u\n",
+			     qla2x00_gid_list_size(ha));
+			return 0;
+		}
+
+		rc = qla24xx_gidlist_wait(vha, gid_list, gid_list_dma,
+		    &entries);
+		if (rc != QLA_SUCCESS)
+			goto out_free_id_list;
+
+		id_iter = (char *)gid_list;
+
+		seq_puts(s, "Port Name	Port ID 	Loop ID\n");
+
+		for (i = 0; i < entries; i++) {
+			struct gid_list_info *gid =
+			    (struct gid_list_info *)id_iter;
+			loop_id = le16_to_cpu(gid->loop_id);
+			memset(&fc_port, 0, sizeof(fc_port_t));
+
+			fc_port.loop_id = loop_id;
+
+			rc = qla24xx_gpdb_wait(vha, &fc_port, 0);
+			seq_printf(s, "%8phC  %02x%02x%02x  %d\n",
+				fc_port.port_name, fc_port.d_id.b.domain,
+				fc_port.d_id.b.area, fc_port.d_id.b.al_pa,
+				fc_port.loop_id);
+			id_iter += ha->gid_list_info_size;
+		}
+out_free_id_list:
+		dma_free_coherent(&ha->pdev->dev, qla2x00_gid_list_size(ha),
+		    gid_list, gid_list_dma);
+	}
+
+	return 0;
+}
+
+static int
+qla2x00_dfs_tgt_port_database_open(struct inode *inode, struct file *file)
+{
+	scsi_qla_host_t *vha = inode->i_private;
+
+	return single_open(file, qla2x00_dfs_tgt_port_database_show, vha);
+}
+
+static const struct file_operations dfs_tgt_port_database_ops = {
+	.open		= qla2x00_dfs_tgt_port_database_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int
 qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused)
 {
 	struct scsi_qla_host *vha = s->private;
@@ -114,6 +185,21 @@ qla_dfs_tgt_counters_show(struct seq_file *s, void *unused)
 	seq_printf(s, "num Q full sent = %lld\n",
 		vha->tgt_counters.num_q_full_sent);
 
+	/* DIF stats */
+	seq_printf(s, "DIF Inp Bytes = %lld\n",
+		vha->qla_stats.qla_dif_stats.dif_input_bytes);
+	seq_printf(s, "DIF Outp Bytes = %lld\n",
+		vha->qla_stats.qla_dif_stats.dif_output_bytes);
+	seq_printf(s, "DIF Inp Req = %lld\n",
+		vha->qla_stats.qla_dif_stats.dif_input_requests);
+	seq_printf(s, "DIF Outp Req = %lld\n",
+		vha->qla_stats.qla_dif_stats.dif_output_requests);
+	seq_printf(s, "DIF Guard err = %d\n",
+		vha->qla_stats.qla_dif_stats.dif_guard_err);
+	seq_printf(s, "DIF Ref tag err = %d\n",
+		vha->qla_stats.qla_dif_stats.dif_ref_tag_err);
+	seq_printf(s, "DIF App tag err = %d\n",
+		vha->qla_stats.qla_dif_stats.dif_app_tag_err);
 	return 0;
 }
 
@@ -281,6 +367,14 @@ create_nodes:
 		goto out;
 	}
 
+	ha->tgt.dfs_tgt_port_database = debugfs_create_file("tgt_port_database",
+	    S_IRUSR,  ha->dfs_dir, vha, &dfs_tgt_port_database_ops);
+	if (!ha->tgt.dfs_tgt_port_database) {
+		ql_log(ql_log_warn, vha, 0xffff,
+		    "Unable to create debugFS tgt_port_database node.\n");
+		goto out;
+	}
+
 	ha->dfs_fce = debugfs_create_file("fce", S_IRUSR, ha->dfs_dir, vha,
 	    &dfs_fce_ops);
 	if (!ha->dfs_fce) {
@@ -311,6 +405,11 @@ qla2x00_dfs_remove(scsi_qla_host_t *vha)
 		ha->tgt.dfs_tgt_sess = NULL;
 	}
 
+	if (ha->tgt.dfs_tgt_port_database) {
+		debugfs_remove(ha->tgt.dfs_tgt_port_database);
+		ha->tgt.dfs_tgt_port_database = NULL;
+	}
+
 	if (ha->dfs_fw_resource_cnt) {
 		debugfs_remove(ha->dfs_fw_resource_cnt);
 		ha->dfs_fw_resource_cnt = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index b3d6441d1d90..5b2451745e9f 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -193,6 +193,7 @@ extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *);
 void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
 	uint16_t *);
 int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
+int qla24xx_async_abort_cmd(srb_t *);
 
 /*
  * Global Functions in qla_mid.c source file.
@@ -256,11 +257,11 @@ extern unsigned long qla2x00_get_async_timeout(struct scsi_qla_host *);
 extern void *qla2x00_alloc_iocbs(scsi_qla_host_t *, srb_t *);
 extern int qla2x00_issue_marker(scsi_qla_host_t *, int);
 extern int qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *, srb_t *,
-	uint32_t *, uint16_t, struct qla_tgt_cmd *);
+	uint32_t *, uint16_t, struct qla_tc_param *);
 extern int qla24xx_walk_and_build_sglist(struct qla_hw_data *, srb_t *,
-	uint32_t *, uint16_t, struct qla_tgt_cmd *);
+	uint32_t *, uint16_t, struct qla_tc_param *);
 extern int qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *, srb_t *,
-	uint32_t *, uint16_t, struct qla_tgt_cmd *);
+	uint32_t *, uint16_t, struct qla_tc_param *);
 extern int qla24xx_get_one_block_sg(uint32_t, struct qla2_sgx *, uint32_t *);
 extern int qla24xx_configure_prot_mode(srb_t *, uint16_t *);
 extern int qla24xx_build_scsi_crc_2_iocbs(srb_t *,
@@ -368,7 +369,7 @@ qla2x00_get_link_status(scsi_qla_host_t *, uint16_t, struct link_statistics *,
 
 extern int
 qla24xx_get_isp_stats(scsi_qla_host_t *, struct link_statistics *,
-    dma_addr_t, uint);
+    dma_addr_t, uint16_t);
 
 extern int qla24xx_abort_command(srb_t *);
 extern int qla24xx_async_abort_command(srb_t *);
@@ -472,6 +473,13 @@ qla2x00_dump_mctp_data(scsi_qla_host_t *, dma_addr_t, uint32_t, uint32_t);
 extern int
 qla26xx_dport_diagnostics(scsi_qla_host_t *, void *, uint, uint);
 
+int qla24xx_send_mb_cmd(struct scsi_qla_host *, mbx_cmd_t *);
+int qla24xx_gpdb_wait(struct scsi_qla_host *, fc_port_t *, u8);
+int qla24xx_gidlist_wait(struct scsi_qla_host *, void *, dma_addr_t,
+    uint16_t *);
+int __qla24xx_parse_gpdb(struct scsi_qla_host *, fc_port_t *,
+	struct port_database_24xx *);
+
 /*
  * Global Function Prototypes in qla_isr.c source file.
  */
@@ -846,5 +854,7 @@ extern struct fc_port *qlt_find_sess_invalidate_other(scsi_qla_host_t *,
 	uint64_t wwn, port_id_t port_id, uint16_t loop_id, struct fc_port **);
 void qla24xx_delete_sess_fn(struct work_struct *);
 void qlt_unknown_atio_work_fn(struct work_struct *);
+void qlt_update_host_map(struct scsi_qla_host *, port_id_t);
+void qlt_remove_target_resources(struct qla_hw_data *);
 
 #endif /* _QLA_GBL_H */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 32fb9007f137..f9d2fe7b1ade 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -629,7 +629,6 @@ void qla24xx_async_gpdb_sp_done(void *s, int res)
 	struct srb *sp = s;
 	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
-	uint64_t zero = 0;
 	struct port_database_24xx *pd;
 	fc_port_t *fcport = sp->fcport;
 	u16 *mb = sp->u.iocb_cmd.u.mbx.in_mb;
@@ -649,48 +648,7 @@ void qla24xx_async_gpdb_sp_done(void *s, int res)
 
 	pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in;
 
-	/* Check for logged in state. */
-	if (pd->current_login_state != PDS_PRLI_COMPLETE &&
-	    pd->last_login_state != PDS_PRLI_COMPLETE) {
-		ql_dbg(ql_dbg_mbx, vha, 0xffff,
-		    "Unable to verify login-state (%x/%x) for "
-		    "loop_id %x.\n", pd->current_login_state,
-		    pd->last_login_state, fcport->loop_id);
-		rval = QLA_FUNCTION_FAILED;
-		goto gpd_error_out;
-	}
-
-	if (fcport->loop_id == FC_NO_LOOP_ID ||
-	    (memcmp(fcport->port_name, (uint8_t *)&zero, 8) &&
-		memcmp(fcport->port_name, pd->port_name, 8))) {
-		/* We lost the device mid way. */
-		rval = QLA_NOT_LOGGED_IN;
-		goto gpd_error_out;
-	}
-
-	/* Names are little-endian. */
-	memcpy(fcport->node_name, pd->node_name, WWN_SIZE);
-
-	/* Get port_id of device. */
-	fcport->d_id.b.domain = pd->port_id[0];
-	fcport->d_id.b.area = pd->port_id[1];
-	fcport->d_id.b.al_pa = pd->port_id[2];
-	fcport->d_id.b.rsvd_1 = 0;
-
-	/* If not target must be initiator or unknown type. */
-	if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0)
-		fcport->port_type = FCT_INITIATOR;
-	else
-		fcport->port_type = FCT_TARGET;
-
-	/* Passback COS information. */
-	fcport->supported_classes = (pd->flags & PDF_CLASS_2) ?
-		FC_COS_CLASS2 : FC_COS_CLASS3;
-
-	if (pd->prli_svc_param_word_3[0] & BIT_7) {
-		fcport->flags |= FCF_CONF_COMP_SUPPORTED;
-		fcport->conf_compl_supported = 1;
-	}
+	rval = __qla24xx_parse_gpdb(vha, fcport, pd);
 
 gpd_error_out:
 	memset(&ea, 0, sizeof(ea));
@@ -876,10 +834,14 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 	fcport->login_retry--;
 
 	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
-	    (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
 	    (fcport->fw_login_state == DSC_LS_PRLI_PEND))
 		return 0;
 
+	if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
+		if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline))
+			return 0;
+	}
+
 	/* for pure Target Mode. Login will not be initiated */
 	if (vha->host->active_mode == MODE_TARGET)
 		return 0;
@@ -1041,10 +1003,14 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 		fcport->flags);
 
 	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
-	    (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
 	    (fcport->fw_login_state == DSC_LS_PRLI_PEND))
 		return;
 
+	if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
+		if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline))
+			return;
+	}
+
 	if (fcport->flags & FCF_ASYNC_SENT) {
 		fcport->login_retry++;
 		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
@@ -1258,7 +1224,7 @@ qla24xx_abort_sp_done(void *ptr, int res)
 	complete(&abt->u.abt.comp);
 }
 
-static int
+int
 qla24xx_async_abort_cmd(srb_t *cmd_sp)
 {
 	scsi_qla_host_t *vha = cmd_sp->vha;
@@ -3212,6 +3178,7 @@ next_check:
 	} else {
 		ql_dbg(ql_dbg_init, vha, 0x00d3,
 		    "Init Firmware -- success.\n");
+		ha->flags.fw_started = 1;
 	}
 
 	return (rval);
@@ -3374,8 +3341,8 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 	uint8_t       domain;
 	char		connect_type[22];
 	struct qla_hw_data *ha = vha->hw;
-	unsigned long flags;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
+	port_id_t id;
 
 	/* Get host addresses. */
 	rval = qla2x00_get_adapter_id(vha,
@@ -3453,13 +3420,11 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 
 	/* Save Host port and loop ID. */
 	/* byte order - Big Endian */
-	vha->d_id.b.domain = domain;
-	vha->d_id.b.area = area;
-	vha->d_id.b.al_pa = al_pa;
-
-	spin_lock_irqsave(&ha->vport_slock, flags);
-	qlt_update_vp_map(vha, SET_AL_PA);
-	spin_unlock_irqrestore(&ha->vport_slock, flags);
+	id.b.domain = domain;
+	id.b.area = area;
+	id.b.al_pa = al_pa;
+	id.b.rsvd_1 = 0;
+	qlt_update_host_map(vha, id);
 
 	if (!vha->flags.init_done)
 		ql_log(ql_log_info, vha, 0x2010,
@@ -4036,6 +4001,7 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 			atomic_set(&vha->loop_state, LOOP_READY);
 			ql_dbg(ql_dbg_disc, vha, 0x2069,
 			    "LOOP READY.\n");
+			ha->flags.fw_init_done = 1;
 
 			/*
 			 * Process any ATIO queue entries that came in
@@ -5148,6 +5114,7 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha)
 			}
 		}
 		atomic_dec(&vha->vref_count);
+		wake_up(&vha->vref_waitq);
 	}
 	spin_unlock_irqrestore(&ha->vport_slock, flags);
 }
@@ -5526,6 +5493,11 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	if (!(IS_P3P_TYPE(ha)))
 		ha->isp_ops->reset_chip(vha);
 
+	ha->flags.n2n_ae = 0;
+	ha->flags.lip_ae = 0;
+	ha->current_topology = 0;
+	ha->flags.fw_started = 0;
+	ha->flags.fw_init_done = 0;
 	ha->chip_reset++;
 
 	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
@@ -6802,6 +6774,8 @@ qla2x00_try_to_stop_firmware(scsi_qla_host_t *vha)
 		return;
 	if (!ha->fw_major_version)
 		return;
+	if (!ha->flags.fw_started)
+		return;
 
 	ret = qla2x00_stop_firmware(vha);
 	for (retries = 5; ret != QLA_SUCCESS && ret != QLA_FUNCTION_TIMEOUT &&
@@ -6815,6 +6789,9 @@ qla2x00_try_to_stop_firmware(scsi_qla_host_t *vha)
 		    "Attempting retry of stop-firmware command.\n");
 		ret = qla2x00_stop_firmware(vha);
 	}
+
+	ha->flags.fw_started = 0;
+	ha->flags.fw_init_done = 0;
 }
 
 int
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 535079280288..ea027f6a7fd4 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -889,7 +889,7 @@ qla24xx_get_one_block_sg(uint32_t blk_sz, struct qla2_sgx *sgx,
 
 int
 qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
-	uint32_t *dsd, uint16_t tot_dsds, struct qla_tgt_cmd *tc)
+	uint32_t *dsd, uint16_t tot_dsds, struct qla_tc_param *tc)
 {
 	void *next_dsd;
 	uint8_t avail_dsds = 0;
@@ -898,7 +898,6 @@ qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
 	struct scatterlist *sg_prot;
 	uint32_t *cur_dsd = dsd;
 	uint16_t	used_dsds = tot_dsds;
-
 	uint32_t	prot_int; /* protection interval */
 	uint32_t	partial;
 	struct qla2_sgx sgx;
@@ -966,7 +965,7 @@ alloc_and_fill:
 			} else {
 				list_add_tail(&dsd_ptr->list,
 				    &(tc->ctx->dsd_list));
-				tc->ctx_dsd_alloced = 1;
+				*tc->ctx_dsd_alloced = 1;
 			}
 
 
@@ -1005,7 +1004,7 @@ alloc_and_fill:
 
 int
 qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
-	uint16_t tot_dsds, struct qla_tgt_cmd *tc)
+	uint16_t tot_dsds, struct qla_tc_param *tc)
 {
 	void *next_dsd;
 	uint8_t avail_dsds = 0;
@@ -1066,7 +1065,7 @@ qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
 			} else {
 				list_add_tail(&dsd_ptr->list,
 				    &(tc->ctx->dsd_list));
-				tc->ctx_dsd_alloced = 1;
+				*tc->ctx_dsd_alloced = 1;
 			}
 
 			/* add new list to cmd iocb or last list */
@@ -1092,7 +1091,7 @@ qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
 
 int
 qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
-	uint32_t *dsd, uint16_t tot_dsds, struct qla_tgt_cmd *tc)
+	uint32_t *dsd, uint16_t tot_dsds, struct qla_tc_param *tc)
 {
 	void *next_dsd;
 	uint8_t avail_dsds = 0;
@@ -1158,7 +1157,7 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
 			} else {
 				list_add_tail(&dsd_ptr->list,
 				    &(tc->ctx->dsd_list));
-				tc->ctx_dsd_alloced = 1;
+				*tc->ctx_dsd_alloced = 1;
 			}
 
 			/* add new list to cmd iocb or last list */
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 3c66ea29de27..3203367a4f42 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -708,6 +708,8 @@ skip_rio:
 		    "mbx7=%xh.\n", mb[1], mb[2], mb[3], mbx);
 
 		ha->isp_ops->fw_dump(vha, 1);
+		ha->flags.fw_init_done = 0;
+		ha->flags.fw_started = 0;
 
 		if (IS_FWI2_CAPABLE(ha)) {
 			if (mb[1] == 0 && mb[2] == 0) {
@@ -761,6 +763,9 @@ skip_rio:
 		break;
 
 	case MBA_LIP_OCCURRED:		/* Loop Initialization Procedure */
+		ha->flags.lip_ae = 1;
+		ha->flags.n2n_ae = 0;
+
 		ql_dbg(ql_dbg_async, vha, 0x5009,
 		    "LIP occurred (%x).\n", mb[1]);
 
@@ -797,6 +802,10 @@ skip_rio:
 		break;
 
 	case MBA_LOOP_DOWN:		/* Loop Down Event */
+		ha->flags.n2n_ae = 0;
+		ha->flags.lip_ae = 0;
+		ha->current_topology = 0;
+
 		mbx = (IS_QLA81XX(ha) || IS_QLA8031(ha))
 			? RD_REG_WORD(&reg24->mailbox4) : 0;
 		mbx = (IS_P3P_TYPE(ha)) ? RD_REG_WORD(&reg82->mailbox_out[4])
@@ -866,6 +875,9 @@ skip_rio:
 
 	/* case MBA_DCBX_COMPLETE: */
 	case MBA_POINT_TO_POINT:	/* Point-to-Point */
+		ha->flags.lip_ae = 0;
+		ha->flags.n2n_ae = 1;
+
 		if (IS_QLA2100(ha))
 			break;
 
@@ -1620,9 +1632,9 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 		QLA_LOGIO_LOGIN_RETRIED : 0;
 	if (logio->entry_status) {
 		ql_log(ql_log_warn, fcport->vha, 0x5034,
-		    "Async-%s error entry - hdl=%x"
+		    "Async-%s error entry - %8phC hdl=%x"
 		    "portid=%02x%02x%02x entry-status=%x.\n",
-		    type, sp->handle, fcport->d_id.b.domain,
+		    type, fcport->port_name, sp->handle, fcport->d_id.b.domain,
 		    fcport->d_id.b.area, fcport->d_id.b.al_pa,
 		    logio->entry_status);
 		ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x504d,
@@ -1633,8 +1645,9 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 
 	if (le16_to_cpu(logio->comp_status) == CS_COMPLETE) {
 		ql_dbg(ql_dbg_async, fcport->vha, 0x5036,
-		    "Async-%s complete - hdl=%x portid=%02x%02x%02x "
-		    "iop0=%x.\n", type, sp->handle, fcport->d_id.b.domain,
+		    "Async-%s complete - %8phC hdl=%x portid=%02x%02x%02x "
+		    "iop0=%x.\n", type, fcport->port_name, sp->handle,
+		    fcport->d_id.b.domain,
 		    fcport->d_id.b.area, fcport->d_id.b.al_pa,
 		    le32_to_cpu(logio->io_parameter[0]));
 
@@ -1674,6 +1687,17 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 	case LSC_SCODE_NPORT_USED:
 		data[0] = MBS_LOOP_ID_USED;
 		break;
+	case LSC_SCODE_CMD_FAILED:
+		if (iop[1] == 0x0606) {
+			/*
+			 * PLOGI/PRLI Completed. We must have Recv PLOGI/PRLI,
+			 * Target side acked.
+			 */
+			data[0] = MBS_COMMAND_COMPLETE;
+			goto logio_done;
+		}
+		data[0] = MBS_COMMAND_ERROR;
+		break;
 	case LSC_SCODE_NOXCB:
 		vha->hw->exch_starvation++;
 		if (vha->hw->exch_starvation > 5) {
@@ -1695,8 +1719,9 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 	}
 
 	ql_dbg(ql_dbg_async, fcport->vha, 0x5037,
-	    "Async-%s failed - hdl=%x portid=%02x%02x%02x comp=%x "
-	    "iop0=%x iop1=%x.\n", type, sp->handle, fcport->d_id.b.domain,
+	    "Async-%s failed - %8phC hdl=%x portid=%02x%02x%02x comp=%x "
+	    "iop0=%x iop1=%x.\n", type, fcport->port_name,
+		sp->handle, fcport->d_id.b.domain,
 	    fcport->d_id.b.area, fcport->d_id.b.al_pa,
 	    le16_to_cpu(logio->comp_status),
 	    le32_to_cpu(logio->io_parameter[0]),
@@ -2679,7 +2704,7 @@ qla24xx_abort_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 		return;
 
 	abt = &sp->u.iocb_cmd;
-	abt->u.abt.comp_status = le32_to_cpu(pkt->nport_handle);
+	abt->u.abt.comp_status = le16_to_cpu(pkt->nport_handle);
 	sp->done(sp, 0);
 }
 
@@ -2693,7 +2718,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	struct sts_entry_24xx *pkt;
 	struct qla_hw_data *ha = vha->hw;
 
-	if (!vha->flags.online)
+	if (!ha->flags.fw_started)
 		return;
 
 	while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 35079f417417..a113ab3592a7 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -10,6 +10,28 @@
 #include <linux/delay.h>
 #include <linux/gfp.h>
 
+static struct mb_cmd_name {
+	uint16_t cmd;
+	const char *str;
+} mb_str[] = {
+	{MBC_GET_PORT_DATABASE,		"GPDB"},
+	{MBC_GET_ID_LIST,		"GIDList"},
+	{MBC_GET_LINK_PRIV_STATS,	"Stats"},
+};
+
+static const char *mb_to_str(uint16_t cmd)
+{
+	int i;
+	struct mb_cmd_name *e;
+
+	for (i = 0; i < ARRAY_SIZE(mb_str); i++) {
+		e = mb_str + i;
+		if (cmd == e->cmd)
+			return e->str;
+	}
+	return "unknown";
+}
+
 static struct rom_cmd {
 	uint16_t cmd;
 } rom_cmds[] = {
@@ -2818,7 +2840,7 @@ qla2x00_get_link_status(scsi_qla_host_t *vha, uint16_t loop_id,
 
 int
 qla24xx_get_isp_stats(scsi_qla_host_t *vha, struct link_statistics *stats,
-    dma_addr_t stats_dma, uint options)
+    dma_addr_t stats_dma, uint16_t options)
 {
 	int rval;
 	mbx_cmd_t mc;
@@ -2828,19 +2850,17 @@ qla24xx_get_isp_stats(scsi_qla_host_t *vha, struct link_statistics *stats,
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1088,
 	    "Entered %s.\n", __func__);
 
-	mcp->mb[0] = MBC_GET_LINK_PRIV_STATS;
-	mcp->mb[2] = MSW(stats_dma);
-	mcp->mb[3] = LSW(stats_dma);
-	mcp->mb[6] = MSW(MSD(stats_dma));
-	mcp->mb[7] = LSW(MSD(stats_dma));
-	mcp->mb[8] = sizeof(struct link_statistics) / 4;
-	mcp->mb[9] = vha->vp_idx;
-	mcp->mb[10] = options;
-	mcp->out_mb = MBX_10|MBX_9|MBX_8|MBX_7|MBX_6|MBX_3|MBX_2|MBX_0;
-	mcp->in_mb = MBX_2|MBX_1|MBX_0;
-	mcp->tov = MBX_TOV_SECONDS;
-	mcp->flags = IOCTL_CMD;
-	rval = qla2x00_mailbox_command(vha, mcp);
+	memset(&mc, 0, sizeof(mc));
+	mc.mb[0] = MBC_GET_LINK_PRIV_STATS;
+	mc.mb[2] = MSW(stats_dma);
+	mc.mb[3] = LSW(stats_dma);
+	mc.mb[6] = MSW(MSD(stats_dma));
+	mc.mb[7] = LSW(MSD(stats_dma));
+	mc.mb[8] = sizeof(struct link_statistics) / 4;
+	mc.mb[9] = cpu_to_le16(vha->vp_idx);
+	mc.mb[10] = cpu_to_le16(options);
+
+	rval = qla24xx_send_mb_cmd(vha, &mc);
 
 	if (rval == QLA_SUCCESS) {
 		if (mcp->mb[0] != MBS_COMMAND_COMPLETE) {
@@ -3603,6 +3623,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 	scsi_qla_host_t *vp = NULL;
 	unsigned long   flags;
 	int found;
+	port_id_t id;
 
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b6,
 	    "Entered %s.\n", __func__);
@@ -3610,28 +3631,27 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 	if (rptid_entry->entry_status != 0)
 		return;
 
+	id.b.domain = rptid_entry->port_id[2];
+	id.b.area   = rptid_entry->port_id[1];
+	id.b.al_pa  = rptid_entry->port_id[0];
+	id.b.rsvd_1 = 0;
+
 	if (rptid_entry->format == 0) {
 		/* loop */
-		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b7,
+		ql_dbg(ql_dbg_async, vha, 0x10b7,
 		    "Format 0 : Number of VPs setup %d, number of "
 		    "VPs acquired %d.\n", rptid_entry->vp_setup,
 		    rptid_entry->vp_acquired);
-		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b8,
+		ql_dbg(ql_dbg_async, vha, 0x10b8,
 		    "Primary port id %02x%02x%02x.\n",
 		    rptid_entry->port_id[2], rptid_entry->port_id[1],
 		    rptid_entry->port_id[0]);
 
-		vha->d_id.b.domain = rptid_entry->port_id[2];
-		vha->d_id.b.area = rptid_entry->port_id[1];
-		vha->d_id.b.al_pa = rptid_entry->port_id[0];
-
-		spin_lock_irqsave(&ha->vport_slock, flags);
-		qlt_update_vp_map(vha, SET_AL_PA);
-		spin_unlock_irqrestore(&ha->vport_slock, flags);
+		qlt_update_host_map(vha, id);
 
 	} else if (rptid_entry->format == 1) {
 		/* fabric */
-		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b9,
+		ql_dbg(ql_dbg_async, vha, 0x10b9,
 		    "Format 1: VP[%d] enabled - status %d - with "
 		    "port id %02x%02x%02x.\n", rptid_entry->vp_idx,
 			rptid_entry->vp_status,
@@ -3653,12 +3673,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 					    WWN_SIZE);
 				}
 
-				vha->d_id.b.domain = rptid_entry->port_id[2];
-				vha->d_id.b.area = rptid_entry->port_id[1];
-				vha->d_id.b.al_pa = rptid_entry->port_id[0];
-				spin_lock_irqsave(&ha->vport_slock, flags);
-				qlt_update_vp_map(vha, SET_AL_PA);
-				spin_unlock_irqrestore(&ha->vport_slock, flags);
+				qlt_update_host_map(vha, id);
 			}
 
 			fc_host_port_name(vha->host) =
@@ -3694,12 +3709,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 			if (!found)
 				return;
 
-			vp->d_id.b.domain = rptid_entry->port_id[2];
-			vp->d_id.b.area =  rptid_entry->port_id[1];
-			vp->d_id.b.al_pa = rptid_entry->port_id[0];
-			spin_lock_irqsave(&ha->vport_slock, flags);
-			qlt_update_vp_map(vp, SET_AL_PA);
-			spin_unlock_irqrestore(&ha->vport_slock, flags);
+			qlt_update_host_map(vp, id);
 
 			/*
 			 * Cannot configure here as we are still sitting on the
@@ -5827,3 +5837,225 @@ qla26xx_dport_diagnostics(scsi_qla_host_t *vha,
 
 	return rval;
 }
+
+static void qla2x00_async_mb_sp_done(void *s, int res)
+{
+	struct srb *sp = s;
+
+	sp->u.iocb_cmd.u.mbx.rc = res;
+
+	complete(&sp->u.iocb_cmd.u.mbx.comp);
+	/* don't free sp here. Let the caller do the free */
+}
+
+/*
+ * This mailbox uses the iocb interface to send MB command.
+ * This allows non-critial (non chip setup) command to go
+ * out in parrallel.
+ */
+int qla24xx_send_mb_cmd(struct scsi_qla_host *vha, mbx_cmd_t *mcp)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	srb_t *sp;
+	struct srb_iocb *c;
+
+	if (!vha->hw->flags.fw_started)
+		goto done;
+
+	sp = qla2x00_get_sp(vha, NULL, GFP_KERNEL);
+	if (!sp)
+		goto done;
+
+	sp->type = SRB_MB_IOCB;
+	sp->name = mb_to_str(mcp->mb[0]);
+
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
+
+	memcpy(sp->u.iocb_cmd.u.mbx.out_mb, mcp->mb, SIZEOF_IOCB_MB_REG);
+
+	c = &sp->u.iocb_cmd;
+	c->timeout = qla2x00_async_iocb_timeout;
+	init_completion(&c->u.mbx.comp);
+
+	sp->done = qla2x00_async_mb_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_mbx, vha, 0xffff,
+		    "%s: %s Failed submission. %x.\n",
+		    __func__, sp->name, rval);
+		goto done_free_sp;
+	}
+
+	ql_dbg(ql_dbg_mbx, vha, 0xffff, "MB:%s hndl %x submitted\n",
+	    sp->name, sp->handle);
+
+	wait_for_completion(&c->u.mbx.comp);
+	memcpy(mcp->mb, sp->u.iocb_cmd.u.mbx.in_mb, SIZEOF_IOCB_MB_REG);
+
+	rval = c->u.mbx.rc;
+	switch (rval) {
+	case QLA_FUNCTION_TIMEOUT:
+		ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %s Timeout. %x.\n",
+		    __func__, sp->name, rval);
+		break;
+	case  QLA_SUCCESS:
+		ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %s done.\n",
+		    __func__, sp->name);
+		sp->free(sp);
+		break;
+	default:
+		ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %s Failed. %x.\n",
+		    __func__, sp->name, rval);
+		sp->free(sp);
+		break;
+	}
+
+	return rval;
+
+done_free_sp:
+	sp->free(sp);
+done:
+	return rval;
+}
+
+/*
+ * qla24xx_gpdb_wait
+ * NOTE: Do not call this routine from DPC thread
+ */
+int qla24xx_gpdb_wait(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	dma_addr_t pd_dma;
+	struct port_database_24xx *pd;
+	struct qla_hw_data *ha = vha->hw;
+	mbx_cmd_t mc;
+
+	if (!vha->hw->flags.fw_started)
+		goto done;
+
+	pd = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &pd_dma);
+	if (pd  == NULL) {
+		ql_log(ql_log_warn, vha, 0xffff,
+			"Failed to allocate port database structure.\n");
+		goto done_free_sp;
+	}
+	memset(pd, 0, max(PORT_DATABASE_SIZE, PORT_DATABASE_24XX_SIZE));
+
+	memset(&mc, 0, sizeof(mc));
+	mc.mb[0] = MBC_GET_PORT_DATABASE;
+	mc.mb[1] = cpu_to_le16(fcport->loop_id);
+	mc.mb[2] = MSW(pd_dma);
+	mc.mb[3] = LSW(pd_dma);
+	mc.mb[6] = MSW(MSD(pd_dma));
+	mc.mb[7] = LSW(MSD(pd_dma));
+	mc.mb[9] = cpu_to_le16(vha->vp_idx);
+	mc.mb[10] = cpu_to_le16((uint16_t)opt);
+
+	rval = qla24xx_send_mb_cmd(vha, &mc);
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_mbx, vha, 0xffff,
+		    "%s: %8phC fail\n", __func__, fcport->port_name);
+		goto done_free_sp;
+	}
+
+	rval = __qla24xx_parse_gpdb(vha, fcport, pd);
+
+	ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %8phC done\n",
+	    __func__, fcport->port_name);
+
+done_free_sp:
+	if (pd)
+		dma_pool_free(ha->s_dma_pool, pd, pd_dma);
+done:
+	return rval;
+}
+
+int __qla24xx_parse_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport,
+    struct port_database_24xx *pd)
+{
+	int rval = QLA_SUCCESS;
+	uint64_t zero = 0;
+
+	/* Check for logged in state. */
+	if (pd->current_login_state != PDS_PRLI_COMPLETE &&
+		pd->last_login_state != PDS_PRLI_COMPLETE) {
+		ql_dbg(ql_dbg_mbx, vha, 0xffff,
+			   "Unable to verify login-state (%x/%x) for "
+			   "loop_id %x.\n", pd->current_login_state,
+			   pd->last_login_state, fcport->loop_id);
+		rval = QLA_FUNCTION_FAILED;
+		goto gpd_error_out;
+	}
+
+	if (fcport->loop_id == FC_NO_LOOP_ID ||
+	    (memcmp(fcport->port_name, (uint8_t *)&zero, 8) &&
+	     memcmp(fcport->port_name, pd->port_name, 8))) {
+		/* We lost the device mid way. */
+		rval = QLA_NOT_LOGGED_IN;
+		goto gpd_error_out;
+	}
+
+	/* Names are little-endian. */
+	memcpy(fcport->node_name, pd->node_name, WWN_SIZE);
+	memcpy(fcport->port_name, pd->port_name, WWN_SIZE);
+
+	/* Get port_id of device. */
+	fcport->d_id.b.domain = pd->port_id[0];
+	fcport->d_id.b.area = pd->port_id[1];
+	fcport->d_id.b.al_pa = pd->port_id[2];
+	fcport->d_id.b.rsvd_1 = 0;
+
+	/* If not target must be initiator or unknown type. */
+	if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0)
+		fcport->port_type = FCT_INITIATOR;
+	else
+		fcport->port_type = FCT_TARGET;
+
+	/* Passback COS information. */
+	fcport->supported_classes = (pd->flags & PDF_CLASS_2) ?
+		FC_COS_CLASS2 : FC_COS_CLASS3;
+
+	if (pd->prli_svc_param_word_3[0] & BIT_7) {
+		fcport->flags |= FCF_CONF_COMP_SUPPORTED;
+		fcport->conf_compl_supported = 1;
+	}
+
+gpd_error_out:
+	return rval;
+}
+
+/*
+ * qla24xx_gidlist__wait
+ * NOTE: don't call this routine from DPC thread.
+ */
+int qla24xx_gidlist_wait(struct scsi_qla_host *vha,
+	void *id_list, dma_addr_t id_list_dma, uint16_t *entries)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	mbx_cmd_t mc;
+
+	if (!vha->hw->flags.fw_started)
+		goto done;
+
+	memset(&mc, 0, sizeof(mc));
+	mc.mb[0] = MBC_GET_ID_LIST;
+	mc.mb[2] = MSW(id_list_dma);
+	mc.mb[3] = LSW(id_list_dma);
+	mc.mb[6] = MSW(MSD(id_list_dma));
+	mc.mb[7] = LSW(MSD(id_list_dma));
+	mc.mb[8] = 0;
+	mc.mb[9] = cpu_to_le16(vha->vp_idx);
+
+	rval = qla24xx_send_mb_cmd(vha, &mc);
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_mbx, vha, 0xffff,
+			"%s:  fail\n", __func__);
+	} else {
+		*entries = mc.mb[1];
+		ql_dbg(ql_dbg_mbx, vha, 0xffff,
+			"%s:  done\n", __func__);
+	}
+done:
+	return rval;
+}
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c6d6f0d912ff..09a490c98763 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -74,13 +74,14 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
 	 * ensures no active vp_list traversal while the vport is removed
 	 * from the queue)
 	 */
-	spin_lock_irqsave(&ha->vport_slock, flags);
-	while (atomic_read(&vha->vref_count)) {
-		spin_unlock_irqrestore(&ha->vport_slock, flags);
-
-		msleep(500);
+	wait_event_timeout(vha->vref_waitq, atomic_read(&vha->vref_count),
+	    10*HZ);
 
-		spin_lock_irqsave(&ha->vport_slock, flags);
+	spin_lock_irqsave(&ha->vport_slock, flags);
+	if (atomic_read(&vha->vref_count)) {
+		ql_dbg(ql_dbg_vport, vha, 0xfffa,
+		    "vha->vref_count=%u timeout\n", vha->vref_count.counter);
+		vha->vref_count = (atomic_t)ATOMIC_INIT(0);
 	}
 	list_del(&vha->list);
 	qlt_update_vp_map(vha, RESET_VP_IDX);
@@ -269,6 +270,7 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb)
 
 			spin_lock_irqsave(&ha->vport_slock, flags);
 			atomic_dec(&vha->vref_count);
+			wake_up(&vha->vref_waitq);
 		}
 		i++;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1fed235a1b4a..83d61d2142e9 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1160,8 +1160,13 @@ static inline
 uint32_t qla2x00_isp_reg_stat(struct qla_hw_data *ha)
 {
 	struct device_reg_24xx __iomem *reg = &ha->iobase->isp24;
+	struct device_reg_82xx __iomem *reg82 = &ha->iobase->isp82;
 
-	return ((RD_REG_DWORD(&reg->host_status)) == ISP_REG_DISCONNECT);
+	if (IS_P3P_TYPE(ha))
+		return ((RD_REG_DWORD(&reg82->host_int)) == ISP_REG_DISCONNECT);
+	else
+		return ((RD_REG_DWORD(&reg->host_status)) ==
+			ISP_REG_DISCONNECT);
 }
 
 /**************************************************************************
@@ -1651,7 +1656,8 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 				/* Don't abort commands in adapter during EEH
 				 * recovery as it's not accessible/responding.
 				 */
-				if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
+				if (GET_CMD_SP(sp) && !ha->flags.eeh_busy &&
+				    (sp->type == SRB_SCSI_CMD)) {
 					/* Get a reference to the sp and drop the lock.
 					 * The reference ensures this sp->done() call
 					 * - and not the call in qla2xxx_eh_abort() -
@@ -2560,6 +2566,20 @@ qla2xxx_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	return atomic_read(&vha->loop_state) == LOOP_READY;
 }
 
+static void qla2x00_iocb_work_fn(struct work_struct *work)
+{
+	struct scsi_qla_host *vha = container_of(work,
+		struct scsi_qla_host, iocb_work);
+	int cnt = 0;
+
+	while (!list_empty(&vha->work_list)) {
+		qla2x00_do_work(vha);
+		cnt++;
+		if (cnt > 10)
+			break;
+	}
+}
+
 /*
  * PCI driver interface
  */
@@ -3078,6 +3098,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	 */
 	qla2xxx_wake_dpc(base_vha);
 
+	INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn);
 	INIT_WORK(&ha->board_disable, qla2x00_disable_board_on_pci_error);
 
 	if (IS_QLA8031(ha) || IS_MCTP_CAPABLE(ha)) {
@@ -3469,6 +3490,7 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	qla2x00_free_sysfs_attr(base_vha, true);
 
 	fc_remove_host(base_vha->host);
+	qlt_remove_target_resources(ha);
 
 	scsi_remove_host(base_vha->host);
 
@@ -4268,6 +4290,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	spin_lock_init(&vha->work_lock);
 	spin_lock_init(&vha->cmd_list_lock);
 	init_waitqueue_head(&vha->fcport_waitQ);
+	init_waitqueue_head(&vha->vref_waitq);
 
 	vha->gnl.size = sizeof(struct get_name_list_extended) *
 			(ha->max_loop_id + 1);
@@ -4319,7 +4342,11 @@ qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e)
 	spin_lock_irqsave(&vha->work_lock, flags);
 	list_add_tail(&e->list, &vha->work_list);
 	spin_unlock_irqrestore(&vha->work_lock, flags);
-	qla2xxx_wake_dpc(vha);
+
+	if (QLA_EARLY_LINKUP(vha->hw))
+		schedule_work(&vha->iocb_work);
+	else
+		qla2xxx_wake_dpc(vha);
 
 	return QLA_SUCCESS;
 }
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 45f5077684f0..0e03ca2ab3e5 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -130,6 +130,9 @@ static void qlt_send_term_imm_notif(struct scsi_qla_host *vha,
 static struct fc_port *qlt_create_sess(struct scsi_qla_host *vha,
 	fc_port_t *fcport, bool local);
 void qlt_unreg_sess(struct fc_port *sess);
+static void qlt_24xx_handle_abts(struct scsi_qla_host *,
+	struct abts_recv_from_24xx *);
+
 /*
  * Global Variables
  */
@@ -140,6 +143,20 @@ static struct workqueue_struct *qla_tgt_wq;
 static DEFINE_MUTEX(qla_tgt_mutex);
 static LIST_HEAD(qla_tgt_glist);
 
+static const char *prot_op_str(u32 prot_op)
+{
+	switch (prot_op) {
+	case TARGET_PROT_NORMAL:	return "NORMAL";
+	case TARGET_PROT_DIN_INSERT:	return "DIN_INSERT";
+	case TARGET_PROT_DOUT_INSERT:	return "DOUT_INSERT";
+	case TARGET_PROT_DIN_STRIP:	return "DIN_STRIP";
+	case TARGET_PROT_DOUT_STRIP:	return "DOUT_STRIP";
+	case TARGET_PROT_DIN_PASS:	return "DIN_PASS";
+	case TARGET_PROT_DOUT_PASS:	return "DOUT_PASS";
+	default:			return "UNKNOWN";
+	}
+}
+
 /* This API intentionally takes dest as a parameter, rather than returning
  * int value to avoid caller forgetting to issue wmb() after the store */
 void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest)
@@ -170,21 +187,23 @@ static inline
 struct scsi_qla_host *qlt_find_host_by_d_id(struct scsi_qla_host *vha,
 	uint8_t *d_id)
 {
-	struct qla_hw_data *ha = vha->hw;
-	uint8_t vp_idx;
-
-	if ((vha->d_id.b.area != d_id[1]) || (vha->d_id.b.domain != d_id[0]))
-		return NULL;
+	struct scsi_qla_host *host;
+	uint32_t key = 0;
 
-	if (vha->d_id.b.al_pa == d_id[2])
+	if ((vha->d_id.b.area == d_id[1]) && (vha->d_id.b.domain == d_id[0]) &&
+	    (vha->d_id.b.al_pa == d_id[2]))
 		return vha;
 
-	BUG_ON(ha->tgt.tgt_vp_map == NULL);
-	vp_idx = ha->tgt.tgt_vp_map[d_id[2]].idx;
-	if (likely(test_bit(vp_idx, ha->vp_idx_map)))
-		return ha->tgt.tgt_vp_map[vp_idx].vha;
+	key  = (uint32_t)d_id[0] << 16;
+	key |= (uint32_t)d_id[1] <<  8;
+	key |= (uint32_t)d_id[2];
 
-	return NULL;
+	host = btree_lookup32(&vha->hw->tgt.host_map, key);
+	if (!host)
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			   "Unable to find host %06x\n", key);
+
+	return host;
 }
 
 static inline
@@ -389,6 +408,8 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 			(struct abts_recv_from_24xx *)atio;
 		struct scsi_qla_host *host = qlt_find_host_by_vp_idx(vha,
 			entry->vp_index);
+		unsigned long flags;
+
 		if (unlikely(!host)) {
 			ql_dbg(ql_dbg_tgt, vha, 0xffff,
 			    "qla_target(%d): Response pkt (ABTS_RECV_24XX) "
@@ -396,9 +417,12 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 			    vha->vp_idx, entry->vp_index);
 			break;
 		}
-		qlt_response_pkt(host, (response_t *)atio);
+		if (!ha_locked)
+			spin_lock_irqsave(&host->hw->hardware_lock, flags);
+		qlt_24xx_handle_abts(host, (struct abts_recv_from_24xx *)atio);
+		if (!ha_locked)
+			spin_unlock_irqrestore(&host->hw->hardware_lock, flags);
 		break;
-
 	}
 
 	/* case PUREX_IOCB_TYPE: ql2xmvasynctoatio */
@@ -554,6 +578,7 @@ void qla2x00_async_nack_sp_done(void *s, int res)
 		sp->fcport->login_gen++;
 		sp->fcport->fw_login_state = DSC_LS_PLOGI_COMP;
 		sp->fcport->logout_on_delete = 1;
+		sp->fcport->plogi_nack_done_deadline = jiffies + HZ;
 		break;
 
 	case SRB_NACK_PRLI:
@@ -613,6 +638,7 @@ int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport,
 		break;
 	case SRB_NACK_PRLI:
 		fcport->fw_login_state = DSC_LS_PRLI_PEND;
+		fcport->deleted = 0;
 		c = "PRLI";
 		break;
 	case SRB_NACK_LOGO:
@@ -1215,7 +1241,7 @@ static int qla24xx_get_loop_id(struct scsi_qla_host *vha, const uint8_t *s_id,
 	}
 
 	/* Get list of logged in devices */
-	rc = qla2x00_get_id_list(vha, gid_list, gid_list_dma, &entries);
+	rc = qla24xx_gidlist_wait(vha, gid_list, gid_list_dma, &entries);
 	if (rc != QLA_SUCCESS) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf045,
 		    "qla_target(%d): get_id_list() failed: %x\n",
@@ -1551,6 +1577,9 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha,
 	request_t *pkt;
 	struct nack_to_isp *nack;
 
+	if (!ha->flags.fw_started)
+		return;
+
 	ql_dbg(ql_dbg_tgt, vha, 0xe004, "Sending NOTIFY_ACK (ha=%p)\n", ha);
 
 	/* Send marker if required */
@@ -2013,6 +2042,70 @@ void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *mcmd)
 }
 EXPORT_SYMBOL(qlt_free_mcmd);
 
+/*
+ * ha->hardware_lock supposed to be held on entry. Might drop it, then
+ * reacquire
+ */
+void qlt_send_resp_ctio(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
+    uint8_t scsi_status, uint8_t sense_key, uint8_t asc, uint8_t ascq)
+{
+	struct atio_from_isp *atio = &cmd->atio;
+	struct ctio7_to_24xx *ctio;
+	uint16_t temp;
+
+	ql_dbg(ql_dbg_tgt_dif, vha, 0x3066,
+	    "Sending response CTIO7 (vha=%p, atio=%p, scsi_status=%02x, "
+	    "sense_key=%02x, asc=%02x, ascq=%02x",
+	    vha, atio, scsi_status, sense_key, asc, ascq);
+
+	ctio = (struct ctio7_to_24xx *)qla2x00_alloc_iocbs(vha, NULL);
+	if (!ctio) {
+		ql_dbg(ql_dbg_async, vha, 0x3067,
+		    "qla2x00t(%ld): %s failed: unable to allocate request packet",
+		    vha->host_no, __func__);
+		goto out;
+	}
+
+	ctio->entry_type = CTIO_TYPE7;
+	ctio->entry_count = 1;
+	ctio->handle = QLA_TGT_SKIP_HANDLE;
+	ctio->nport_handle = cmd->sess->loop_id;
+	ctio->timeout = cpu_to_le16(QLA_TGT_TIMEOUT);
+	ctio->vp_index = vha->vp_idx;
+	ctio->initiator_id[0] = atio->u.isp24.fcp_hdr.s_id[2];
+	ctio->initiator_id[1] = atio->u.isp24.fcp_hdr.s_id[1];
+	ctio->initiator_id[2] = atio->u.isp24.fcp_hdr.s_id[0];
+	ctio->exchange_addr = atio->u.isp24.exchange_addr;
+	ctio->u.status1.flags = (atio->u.isp24.attr << 9) |
+	    cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_1 | CTIO7_FLAGS_SEND_STATUS);
+	temp = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+	ctio->u.status1.ox_id = cpu_to_le16(temp);
+	ctio->u.status1.scsi_status =
+	    cpu_to_le16(SS_RESPONSE_INFO_LEN_VALID | scsi_status);
+	ctio->u.status1.response_len = cpu_to_le16(18);
+	ctio->u.status1.residual = cpu_to_le32(get_datalen_for_atio(atio));
+
+	if (ctio->u.status1.residual != 0)
+		ctio->u.status1.scsi_status |=
+		    cpu_to_le16(SS_RESIDUAL_UNDER);
+
+	/* Response code and sense key */
+	put_unaligned_le32(((0x70 << 24) | (sense_key << 8)),
+	    (&ctio->u.status1.sense_data)[0]);
+	/* Additional sense length */
+	put_unaligned_le32(0x0a, (&ctio->u.status1.sense_data)[1]);
+	/* ASC and ASCQ */
+	put_unaligned_le32(((asc << 24) | (ascq << 16)),
+	    (&ctio->u.status1.sense_data)[3]);
+
+	/* Memory Barrier */
+	wmb();
+
+	qla2x00_start_iocbs(vha, vha->req);
+out:
+	return;
+}
+
 /* callback from target fabric module code */
 void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 {
@@ -2261,7 +2354,7 @@ static int qlt_24xx_build_ctio_pkt(struct qla_tgt_prm *prm,
 		 */
 		return -EAGAIN;
 	} else
-		ha->tgt.cmds[h-1] = prm->cmd;
+		ha->tgt.cmds[h - 1] = prm->cmd;
 
 	pkt->handle = h | CTIO_COMPLETION_HANDLE_MARK;
 	pkt->nport_handle = prm->cmd->loop_id;
@@ -2391,6 +2484,50 @@ static inline int qlt_has_data(struct qla_tgt_cmd *cmd)
 	return cmd->bufflen > 0;
 }
 
+static void qlt_print_dif_err(struct qla_tgt_prm *prm)
+{
+	struct qla_tgt_cmd *cmd;
+	struct scsi_qla_host *vha;
+
+	/* asc 0x10=dif error */
+	if (prm->sense_buffer && (prm->sense_buffer[12] == 0x10)) {
+		cmd = prm->cmd;
+		vha = cmd->vha;
+		/* ASCQ */
+		switch (prm->sense_buffer[13]) {
+		case 1:
+			ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			    "BE detected Guard TAG ERR: lba[0x%llx|%lld] len[0x%x] "
+			    "se_cmd=%p tag[%x]",
+			    cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+			    cmd->atio.u.isp24.exchange_addr);
+			break;
+		case 2:
+			ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			    "BE detected APP TAG ERR: lba[0x%llx|%lld] len[0x%x] "
+			    "se_cmd=%p tag[%x]",
+			    cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+			    cmd->atio.u.isp24.exchange_addr);
+			break;
+		case 3:
+			ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			    "BE detected REF TAG ERR: lba[0x%llx|%lld] len[0x%x] "
+			    "se_cmd=%p tag[%x]",
+			    cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+			    cmd->atio.u.isp24.exchange_addr);
+			break;
+		default:
+			ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			    "BE detected Dif ERR: lba[%llx|%lld] len[%x] "
+			    "se_cmd=%p tag[%x]",
+			    cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+			    cmd->atio.u.isp24.exchange_addr);
+			break;
+		}
+		ql_dump_buffer(ql_dbg_tgt_dif, vha, 0xffff, cmd->cdb, 16);
+	}
+}
+
 /*
  * Called without ha->hardware_lock held
  */
@@ -2512,18 +2649,9 @@ skip_explict_conf:
 		for (i = 0; i < prm->sense_buffer_len/4; i++)
 			((uint32_t *)ctio->u.status1.sense_data)[i] =
 				cpu_to_be32(((uint32_t *)prm->sense_buffer)[i]);
-#if 0
-		if (unlikely((prm->sense_buffer_len % 4) != 0)) {
-			static int q;
-			if (q < 10) {
-				ql_dbg(ql_dbg_tgt, vha, 0xe04f,
-				    "qla_target(%d): %d bytes of sense "
-				    "lost", prm->tgt->ha->vp_idx,
-				    prm->sense_buffer_len % 4);
-				q++;
-			}
-		}
-#endif
+
+		qlt_print_dif_err(prm);
+
 	} else {
 		ctio->u.status1.flags &=
 		    ~cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_0);
@@ -2537,19 +2665,9 @@ skip_explict_conf:
 	/* Sense with len > 24, is it possible ??? */
 }
 
-
-
-/* diff  */
 static inline int
 qlt_hba_err_chk_enabled(struct se_cmd *se_cmd)
 {
-	/*
-	 * Uncomment when corresponding SCSI changes are done.
-	 *
-	 if (!sp->cmd->prot_chk)
-	 return 0;
-	 *
-	 */
 	switch (se_cmd->prot_op) {
 	case TARGET_PROT_DOUT_INSERT:
 	case TARGET_PROT_DIN_STRIP:
@@ -2570,16 +2688,38 @@ qlt_hba_err_chk_enabled(struct se_cmd *se_cmd)
 	return 0;
 }
 
+static inline int
+qla_tgt_ref_mask_check(struct se_cmd *se_cmd)
+{
+	switch (se_cmd->prot_op) {
+	case TARGET_PROT_DIN_INSERT:
+	case TARGET_PROT_DOUT_INSERT:
+	case TARGET_PROT_DIN_STRIP:
+	case TARGET_PROT_DOUT_STRIP:
+	case TARGET_PROT_DIN_PASS:
+	case TARGET_PROT_DOUT_PASS:
+	    return 1;
+	default:
+	    return 0;
+	}
+	return 0;
+}
+
 /*
- * qla24xx_set_t10dif_tags_from_cmd - Extract Ref and App tags from SCSI command
- *
+ * qla_tgt_set_dif_tags - Extract Ref and App tags from SCSI command
  */
-static inline void
-qlt_set_t10dif_tags(struct se_cmd *se_cmd, struct crc_context *ctx)
+static void
+qla_tgt_set_dif_tags(struct qla_tgt_cmd *cmd, struct crc_context *ctx,
+    uint16_t *pfw_prot_opts)
 {
+	struct se_cmd *se_cmd = &cmd->se_cmd;
 	uint32_t lba = 0xffffffff & se_cmd->t_task_lba;
+	scsi_qla_host_t *vha = cmd->tgt->vha;
+	struct qla_hw_data *ha = vha->hw;
+	uint32_t t32 = 0;
 
-	/* wait til Mode Sense/Select cmd, modepage Ah, subpage 2
+	/*
+	 * wait till Mode Sense/Select cmd, modepage Ah, subpage 2
 	 * have been immplemented by TCM, before AppTag is avail.
 	 * Look for modesense_handlers[]
 	 */
@@ -2587,65 +2727,73 @@ qlt_set_t10dif_tags(struct se_cmd *se_cmd, struct crc_context *ctx)
 	ctx->app_tag_mask[0] = 0x0;
 	ctx->app_tag_mask[1] = 0x0;
 
+	if (IS_PI_UNINIT_CAPABLE(ha)) {
+		if ((se_cmd->prot_type == TARGET_DIF_TYPE1_PROT) ||
+		    (se_cmd->prot_type == TARGET_DIF_TYPE2_PROT))
+			*pfw_prot_opts |= PO_DIS_VALD_APP_ESC;
+		else if (se_cmd->prot_type == TARGET_DIF_TYPE3_PROT)
+			*pfw_prot_opts |= PO_DIS_VALD_APP_REF_ESC;
+	}
+
+	t32 = ha->tgt.tgt_ops->get_dif_tags(cmd, pfw_prot_opts);
+
 	switch (se_cmd->prot_type) {
 	case TARGET_DIF_TYPE0_PROT:
 		/*
-		 * No check for ql2xenablehba_err_chk, as it would be an
-		 * I/O error if hba tag generation is not done.
+		 * No check for ql2xenablehba_err_chk, as it
+		 * would be an I/O error if hba tag generation
+		 * is not done.
 		 */
 		ctx->ref_tag = cpu_to_le32(lba);
-
-		if (!qlt_hba_err_chk_enabled(se_cmd))
-			break;
-
 		/* enable ALL bytes of the ref tag */
 		ctx->ref_tag_mask[0] = 0xff;
 		ctx->ref_tag_mask[1] = 0xff;
 		ctx->ref_tag_mask[2] = 0xff;
 		ctx->ref_tag_mask[3] = 0xff;
 		break;
-	/*
-	 * For TYpe 1 protection: 16 bit GUARD tag, 32 bit REF tag, and
-	 * 16 bit app tag.
-	 */
 	case TARGET_DIF_TYPE1_PROT:
-		ctx->ref_tag = cpu_to_le32(lba);
-
-		if (!qlt_hba_err_chk_enabled(se_cmd))
-			break;
-
-		/* enable ALL bytes of the ref tag */
-		ctx->ref_tag_mask[0] = 0xff;
-		ctx->ref_tag_mask[1] = 0xff;
-		ctx->ref_tag_mask[2] = 0xff;
-		ctx->ref_tag_mask[3] = 0xff;
-		break;
-	/*
-	 * For TYPE 2 protection: 16 bit GUARD + 32 bit REF tag has to
-	 * match LBA in CDB + N
-	 */
+	    /*
+	     * For TYPE 1 protection: 16 bit GUARD tag, 32 bit
+	     * REF tag, and 16 bit app tag.
+	     */
+	    ctx->ref_tag = cpu_to_le32(lba);
+	    if (!qla_tgt_ref_mask_check(se_cmd) ||
+		!(ha->tgt.tgt_ops->chk_dif_tags(t32))) {
+		    *pfw_prot_opts |= PO_DIS_REF_TAG_VALD;
+		    break;
+	    }
+	    /* enable ALL bytes of the ref tag */
+	    ctx->ref_tag_mask[0] = 0xff;
+	    ctx->ref_tag_mask[1] = 0xff;
+	    ctx->ref_tag_mask[2] = 0xff;
+	    ctx->ref_tag_mask[3] = 0xff;
+	    break;
 	case TARGET_DIF_TYPE2_PROT:
-		ctx->ref_tag = cpu_to_le32(lba);
-
-		if (!qlt_hba_err_chk_enabled(se_cmd))
-			break;
-
-		/* enable ALL bytes of the ref tag */
-		ctx->ref_tag_mask[0] = 0xff;
-		ctx->ref_tag_mask[1] = 0xff;
-		ctx->ref_tag_mask[2] = 0xff;
-		ctx->ref_tag_mask[3] = 0xff;
-		break;
-
-	/* For Type 3 protection: 16 bit GUARD only */
+	    /*
+	     * For TYPE 2 protection: 16 bit GUARD + 32 bit REF
+	     * tag has to match LBA in CDB + N
+	     */
+	    ctx->ref_tag = cpu_to_le32(lba);
+	    if (!qla_tgt_ref_mask_check(se_cmd) ||
+		!(ha->tgt.tgt_ops->chk_dif_tags(t32))) {
+		    *pfw_prot_opts |= PO_DIS_REF_TAG_VALD;
+		    break;
+	    }
+	    /* enable ALL bytes of the ref tag */
+	    ctx->ref_tag_mask[0] = 0xff;
+	    ctx->ref_tag_mask[1] = 0xff;
+	    ctx->ref_tag_mask[2] = 0xff;
+	    ctx->ref_tag_mask[3] = 0xff;
+	    break;
 	case TARGET_DIF_TYPE3_PROT:
-		ctx->ref_tag_mask[0] = ctx->ref_tag_mask[1] =
-			ctx->ref_tag_mask[2] = ctx->ref_tag_mask[3] = 0x00;
-		break;
+	    /* For TYPE 3 protection: 16 bit GUARD only */
+	    *pfw_prot_opts |= PO_DIS_REF_TAG_VALD;
+	    ctx->ref_tag_mask[0] = ctx->ref_tag_mask[1] =
+		ctx->ref_tag_mask[2] = ctx->ref_tag_mask[3] = 0x00;
+	    break;
 	}
 }
 
-
 static inline int
 qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 {
@@ -2664,6 +2812,7 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 	struct se_cmd		*se_cmd = &cmd->se_cmd;
 	uint32_t h;
 	struct atio_from_isp *atio = &prm->cmd->atio;
+	struct qla_tc_param	tc;
 	uint16_t t16;
 
 	ha = vha->hw;
@@ -2689,16 +2838,15 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 	case TARGET_PROT_DIN_INSERT:
 	case TARGET_PROT_DOUT_STRIP:
 		transfer_length = data_bytes;
-		data_bytes += dif_bytes;
+		if (cmd->prot_sg_cnt)
+			data_bytes += dif_bytes;
 		break;
-
 	case TARGET_PROT_DIN_STRIP:
 	case TARGET_PROT_DOUT_INSERT:
 	case TARGET_PROT_DIN_PASS:
 	case TARGET_PROT_DOUT_PASS:
 		transfer_length = data_bytes + dif_bytes;
 		break;
-
 	default:
 		BUG();
 		break;
@@ -2734,7 +2882,6 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 		break;
 	}
 
-
 	/* ---- PKT ---- */
 	/* Update entry type to indicate Command Type CRC_2 IOCB */
 	pkt->entry_type  = CTIO_CRC2;
@@ -2752,9 +2899,8 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 	} else
 		ha->tgt.cmds[h-1] = prm->cmd;
 
-
 	pkt->handle  = h | CTIO_COMPLETION_HANDLE_MARK;
-	pkt->nport_handle = prm->cmd->loop_id;
+	pkt->nport_handle = cpu_to_le16(prm->cmd->loop_id);
 	pkt->timeout = cpu_to_le16(QLA_TGT_TIMEOUT);
 	pkt->initiator_id[0] = atio->u.isp24.fcp_hdr.s_id[2];
 	pkt->initiator_id[1] = atio->u.isp24.fcp_hdr.s_id[1];
@@ -2775,12 +2921,10 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 	else if (cmd->dma_data_direction == DMA_FROM_DEVICE)
 		pkt->flags = cpu_to_le16(CTIO7_FLAGS_DATA_OUT);
 
-
 	pkt->dseg_count = prm->tot_dsds;
 	/* Fibre channel byte count */
 	pkt->transfer_length = cpu_to_le32(transfer_length);
 
-
 	/* ----- CRC context -------- */
 
 	/* Allocate CRC context from global pool */
@@ -2800,13 +2944,12 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 	/* Set handle */
 	crc_ctx_pkt->handle = pkt->handle;
 
-	qlt_set_t10dif_tags(se_cmd, crc_ctx_pkt);
+	qla_tgt_set_dif_tags(cmd, crc_ctx_pkt, &fw_prot_opts);
 
 	pkt->crc_context_address[0] = cpu_to_le32(LSD(crc_ctx_dma));
 	pkt->crc_context_address[1] = cpu_to_le32(MSD(crc_ctx_dma));
 	pkt->crc_context_len = CRC_CONTEXT_LEN_FW;
 
-
 	if (!bundling) {
 		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.nobundling.data_address;
 	} else {
@@ -2827,16 +2970,24 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 	crc_ctx_pkt->byte_count = cpu_to_le32(data_bytes);
 	crc_ctx_pkt->guard_seed = cpu_to_le16(0);
 
+	memset((uint8_t *)&tc, 0 , sizeof(tc));
+	tc.vha = vha;
+	tc.blk_sz = cmd->blk_sz;
+	tc.bufflen = cmd->bufflen;
+	tc.sg = cmd->sg;
+	tc.prot_sg = cmd->prot_sg;
+	tc.ctx = crc_ctx_pkt;
+	tc.ctx_dsd_alloced = &cmd->ctx_dsd_alloced;
 
 	/* Walks data segments */
 	pkt->flags |= cpu_to_le16(CTIO7_FLAGS_DSD_PTR);
 
 	if (!bundling && prm->prot_seg_cnt) {
 		if (qla24xx_walk_and_build_sglist_no_difb(ha, NULL, cur_dsd,
-			prm->tot_dsds, cmd))
+			prm->tot_dsds, &tc))
 			goto crc_queuing_error;
 	} else if (qla24xx_walk_and_build_sglist(ha, NULL, cur_dsd,
-		(prm->tot_dsds - prm->prot_seg_cnt), cmd))
+		(prm->tot_dsds - prm->prot_seg_cnt), &tc))
 		goto crc_queuing_error;
 
 	if (bundling && prm->prot_seg_cnt) {
@@ -2845,18 +2996,18 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
 
 		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.bundling.dif_address;
 		if (qla24xx_walk_and_build_prot_sglist(ha, NULL, cur_dsd,
-			prm->prot_seg_cnt, cmd))
+			prm->prot_seg_cnt, &tc))
 			goto crc_queuing_error;
 	}
 	return QLA_SUCCESS;
 
 crc_queuing_error:
 	/* Cleanup will be performed by the caller */
+	vha->hw->tgt.cmds[h - 1] = NULL;
 
 	return QLA_FUNCTION_FAILED;
 }
 
-
 /*
  * Callback to setup response of xmit_type of QLA_TGT_XMIT_DATA and *
  * QLA_TGT_XMIT_STATUS for >= 24xx silicon
@@ -2906,7 +3057,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	else
 		vha->tgt_counters.core_qla_que_buf++;
 
-	if (!vha->flags.online || cmd->reset_count != ha->chip_reset) {
+	if (!ha->flags.fw_started || cmd->reset_count != ha->chip_reset) {
 		/*
 		 * Either the port is not online or this request was from
 		 * previous life, just abort the processing.
@@ -3047,7 +3198,7 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
-	if (!vha->flags.online || (cmd->reset_count != ha->chip_reset) ||
+	if (!ha->flags.fw_started || (cmd->reset_count != ha->chip_reset) ||
 	    (cmd->sess && cmd->sess->deleted)) {
 		/*
 		 * Either the port is not online or this request was from
@@ -3104,139 +3255,113 @@ EXPORT_SYMBOL(qlt_rdy_to_xfer);
 
 
 /*
- * Checks the guard or meta-data for the type of error
- * detected by the HBA.
+ * it is assumed either hardware_lock or qpair lock is held.
  */
-static inline int
+static void
 qlt_handle_dif_error(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd,
-		struct ctio_crc_from_fw *sts)
+	struct ctio_crc_from_fw *sts)
 {
 	uint8_t		*ap = &sts->actual_dif[0];
 	uint8_t		*ep = &sts->expected_dif[0];
-	uint32_t	e_ref_tag, a_ref_tag;
-	uint16_t	e_app_tag, a_app_tag;
-	uint16_t	e_guard, a_guard;
 	uint64_t	lba = cmd->se_cmd.t_task_lba;
+	uint8_t scsi_status, sense_key, asc, ascq;
+	unsigned long flags;
 
-	a_guard   = be16_to_cpu(*(uint16_t *)(ap + 0));
-	a_app_tag = be16_to_cpu(*(uint16_t *)(ap + 2));
-	a_ref_tag = be32_to_cpu(*(uint32_t *)(ap + 4));
-
-	e_guard   = be16_to_cpu(*(uint16_t *)(ep + 0));
-	e_app_tag = be16_to_cpu(*(uint16_t *)(ep + 2));
-	e_ref_tag = be32_to_cpu(*(uint32_t *)(ep + 4));
-
-	ql_dbg(ql_dbg_tgt, vha, 0xe075,
-	    "iocb(s) %p Returned STATUS.\n", sts);
-
-	ql_dbg(ql_dbg_tgt, vha, 0xf075,
-	    "dif check TGT cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x]\n",
-	    cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
-	    a_ref_tag, e_ref_tag, a_app_tag, e_app_tag, a_guard, e_guard);
-
-	/*
-	 * Ignore sector if:
-	 * For type     3: ref & app tag is all 'f's
-	 * For type 0,1,2: app tag is all 'f's
-	 */
-	if ((a_app_tag == 0xffff) &&
-	    ((cmd->se_cmd.prot_type != TARGET_DIF_TYPE3_PROT) ||
-	     (a_ref_tag == 0xffffffff))) {
-		uint32_t blocks_done;
-
-		/* 2TB boundary case covered automatically with this */
-		blocks_done = e_ref_tag - (uint32_t)lba + 1;
-		cmd->se_cmd.bad_sector = e_ref_tag;
-		cmd->se_cmd.pi_err = 0;
-		ql_dbg(ql_dbg_tgt, vha, 0xf074,
-			"need to return scsi good\n");
-
-		/* Update protection tag */
-		if (cmd->prot_sg_cnt) {
-			uint32_t i, k = 0, num_ent;
-			struct scatterlist *sg, *sgl;
-
-
-			sgl = cmd->prot_sg;
-
-			/* Patch the corresponding protection tags */
-			for_each_sg(sgl, sg, cmd->prot_sg_cnt, i) {
-				num_ent = sg_dma_len(sg) / 8;
-				if (k + num_ent < blocks_done) {
-					k += num_ent;
-					continue;
-				}
-				k = blocks_done;
-				break;
-			}
+	cmd->trc_flags |= TRC_DIF_ERR;
 
-			if (k != blocks_done) {
-				ql_log(ql_log_warn, vha, 0xf076,
-				    "unexpected tag values tag:lba=%u:%llu)\n",
-				    e_ref_tag, (unsigned long long)lba);
-				goto out;
-			}
+	cmd->a_guard   = be16_to_cpu(*(uint16_t *)(ap + 0));
+	cmd->a_app_tag = be16_to_cpu(*(uint16_t *)(ap + 2));
+	cmd->a_ref_tag = be32_to_cpu(*(uint32_t *)(ap + 4));
 
-#if 0
-			struct sd_dif_tuple *spt;
-			/* TODO:
-			 * This section came from initiator. Is it valid here?
-			 * should ulp be override with actual val???
-			 */
-			spt = page_address(sg_page(sg)) + sg->offset;
-			spt += j;
+	cmd->e_guard   = be16_to_cpu(*(uint16_t *)(ep + 0));
+	cmd->e_app_tag = be16_to_cpu(*(uint16_t *)(ep + 2));
+	cmd->e_ref_tag = be32_to_cpu(*(uint32_t *)(ep + 4));
 
-			spt->app_tag = 0xffff;
-			if (cmd->se_cmd.prot_type == SCSI_PROT_DIF_TYPE3)
-				spt->ref_tag = 0xffffffff;
-#endif
-		}
+	ql_dbg(ql_dbg_tgt_dif, vha, 0xf075,
+	    "%s: aborted %d state %d\n", __func__, cmd->aborted, cmd->state);
 
-		return 0;
-	}
+	scsi_status = sense_key = asc = ascq = 0;
 
-	/* check guard */
-	if (e_guard != a_guard) {
-		cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED;
-		cmd->se_cmd.bad_sector = cmd->se_cmd.t_task_lba;
-
-		ql_log(ql_log_warn, vha, 0xe076,
-		    "Guard ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
-		    cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
-		    a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
-		    a_guard, e_guard, cmd);
-		goto out;
+	/* check appl tag */
+	if (cmd->e_app_tag != cmd->a_app_tag) {
+		ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			"App Tag ERR: cdb[%x] lba[%llx %llx] blks[%x] [Actual|Expected] "
+			"Ref[%x|%x], App[%x|%x], "
+			"Guard [%x|%x] cmd=%p ox_id[%04x]",
+			cmd->cdb[0], lba, (lba+cmd->num_blks), cmd->num_blks,
+			cmd->a_ref_tag, cmd->e_ref_tag,
+			cmd->a_app_tag, cmd->e_app_tag,
+			cmd->a_guard, cmd->e_guard,
+			cmd, cmd->atio.u.isp24.fcp_hdr.ox_id);
+
+		cmd->dif_err_code = DIF_ERR_APP;
+		scsi_status = SAM_STAT_CHECK_CONDITION;
+		sense_key = ABORTED_COMMAND;
+		asc = 0x10;
+		ascq = 0x2;
 	}
 
 	/* check ref tag */
-	if (e_ref_tag != a_ref_tag) {
-		cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
-		cmd->se_cmd.bad_sector = e_ref_tag;
-
-		ql_log(ql_log_warn, vha, 0xe077,
-			"Ref Tag ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
-			cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
-			a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
-			a_guard, e_guard, cmd);
+	if (cmd->e_ref_tag != cmd->a_ref_tag) {
+		ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			"Ref Tag ERR: cdb[%x] lba[%llx %llx] blks[%x] [Actual|Expected] "
+			"Ref[%x|%x], App[%x|%x], "
+			"Guard[%x|%x] cmd=%p ox_id[%04x] ",
+			cmd->cdb[0], lba, (lba+cmd->num_blks), cmd->num_blks,
+			cmd->a_ref_tag, cmd->e_ref_tag,
+			cmd->a_app_tag, cmd->e_app_tag,
+			cmd->a_guard, cmd->e_guard,
+			cmd, cmd->atio.u.isp24.fcp_hdr.ox_id);
+
+		cmd->dif_err_code = DIF_ERR_REF;
+		scsi_status = SAM_STAT_CHECK_CONDITION;
+		sense_key = ABORTED_COMMAND;
+		asc = 0x10;
+		ascq = 0x3;
 		goto out;
 	}
 
-	/* check appl tag */
-	if (e_app_tag != a_app_tag) {
-		cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED;
-		cmd->se_cmd.bad_sector = cmd->se_cmd.t_task_lba;
-
-		ql_log(ql_log_warn, vha, 0xe078,
-			"App Tag ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
-			cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
-			a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
-			a_guard, e_guard, cmd);
-		goto out;
+	/* check guard */
+	if (cmd->e_guard != cmd->a_guard) {
+		ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+			"Guard ERR: cdb[%x] lba[%llx %llx] blks[%x] [Actual|Expected] "
+			"Ref[%x|%x], App[%x|%x], "
+			"Guard [%x|%x] cmd=%p ox_id[%04x]",
+			cmd->cdb[0], lba, (lba+cmd->num_blks), cmd->num_blks,
+			cmd->a_ref_tag, cmd->e_ref_tag,
+			cmd->a_app_tag, cmd->e_app_tag,
+			cmd->a_guard, cmd->e_guard,
+			cmd, cmd->atio.u.isp24.fcp_hdr.ox_id);
+		cmd->dif_err_code = DIF_ERR_GRD;
+		scsi_status = SAM_STAT_CHECK_CONDITION;
+		sense_key = ABORTED_COMMAND;
+		asc = 0x10;
+		ascq = 0x1;
 	}
 out:
-	return 1;
-}
+	switch (cmd->state) {
+	case QLA_TGT_STATE_NEED_DATA:
+		/* handle_data will load DIF error code  */
+		cmd->state = QLA_TGT_STATE_DATA_IN;
+		vha->hw->tgt.tgt_ops->handle_data(cmd);
+		break;
+	default:
+		spin_lock_irqsave(&cmd->cmd_lock, flags);
+		if (cmd->aborted) {
+			spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+			vha->hw->tgt.tgt_ops->free_cmd(cmd);
+			break;
+		}
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
+		qlt_send_resp_ctio(vha, cmd, scsi_status, sense_key, asc, ascq);
+		/* assume scsi status gets out on the wire.
+		 * Will not wait for completion.
+		 */
+		vha->hw->tgt.tgt_ops->free_cmd(cmd);
+		break;
+	}
+}
 
 /* If hardware_lock held on entry, might drop it, then reaquire */
 /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
@@ -3251,7 +3376,7 @@ static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
 	ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c,
 	    "Sending TERM ELS CTIO (ha=%p)\n", ha);
 
-	pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL);
+	pkt = (request_t *)qla2x00_alloc_iocbs(vha, NULL);
 	if (pkt == NULL) {
 		ql_dbg(ql_dbg_tgt, vha, 0xe080,
 		    "qla_target(%d): %s failed: unable to allocate "
@@ -3543,6 +3668,16 @@ static int qlt_term_ctio_exchange(struct scsi_qla_host *vha, void *ctio,
 {
 	int term = 0;
 
+	if (cmd->se_cmd.prot_op)
+		ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+		    "Term DIF cmd: lba[0x%llx|%lld] len[0x%x] "
+		    "se_cmd=%p tag[%x] op %#x/%s",
+		     cmd->lba, cmd->lba,
+		     cmd->num_blks, &cmd->se_cmd,
+		     cmd->atio.u.isp24.exchange_addr,
+		     cmd->se_cmd.prot_op,
+		     prot_op_str(cmd->se_cmd.prot_op));
+
 	if (ctio != NULL) {
 		struct ctio7_from_24xx *c = (struct ctio7_from_24xx *)ctio;
 		term = !(c->flags &
@@ -3760,32 +3895,15 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 			struct ctio_crc_from_fw *crc =
 				(struct ctio_crc_from_fw *)ctio;
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf073,
-			    "qla_target(%d): CTIO with DIF_ERROR status %x received (state %x, se_cmd %p) actual_dif[0x%llx] expect_dif[0x%llx]\n",
+			    "qla_target(%d): CTIO with DIF_ERROR status %x "
+			    "received (state %x, ulp_cmd %p) actual_dif[0x%llx] "
+			    "expect_dif[0x%llx]\n",
 			    vha->vp_idx, status, cmd->state, se_cmd,
 			    *((u64 *)&crc->actual_dif[0]),
 			    *((u64 *)&crc->expected_dif[0]));
 
-			if (qlt_handle_dif_error(vha, cmd, ctio)) {
-				if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
-					/* scsi Write/xfer rdy complete */
-					goto skip_term;
-				} else {
-					/* scsi read/xmit respond complete
-					 * call handle dif to send scsi status
-					 * rather than terminate exchange.
-					 */
-					cmd->state = QLA_TGT_STATE_PROCESSED;
-					ha->tgt.tgt_ops->handle_dif_err(cmd);
-					return;
-				}
-			} else {
-				/* Need to generate a SCSI good completion.
-				 * because FW did not send scsi status.
-				 */
-				status = 0;
-				goto skip_term;
-			}
-			break;
+			qlt_handle_dif_error(vha, cmd, ctio);
+			return;
 		}
 		default:
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05b,
@@ -3808,7 +3926,6 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 				return;
 		}
 	}
-skip_term:
 
 	if (cmd->state == QLA_TGT_STATE_PROCESSED) {
 		cmd->trc_flags |= TRC_CTIO_DONE;
@@ -4584,7 +4701,8 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		}
 
 		if (sess != NULL) {
-			if (sess->fw_login_state == DSC_LS_PLOGI_PEND) {
+			if (sess->fw_login_state != DSC_LS_PLOGI_PEND &&
+			    sess->fw_login_state != DSC_LS_PLOGI_COMP) {
 				/*
 				 * Impatient initiator sent PRLI before last
 				 * PLOGI could finish. Will force him to re-try,
@@ -4623,15 +4741,23 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 
 		/* Make session global (not used in fabric mode) */
 		if (ha->current_topology != ISP_CFG_F) {
-			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
-			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
-			qla2xxx_wake_dpc(vha);
+			if (sess) {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "%s %d %8phC post nack\n",
+				    __func__, __LINE__, sess->port_name);
+				qla24xx_post_nack_work(vha, sess, iocb,
+					SRB_NACK_PRLI);
+				res = 0;
+			} else {
+				set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+				set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+				qla2xxx_wake_dpc(vha);
+			}
 		} else {
 			if (sess) {
 				ql_dbg(ql_dbg_disc, vha, 0xffff,
-					   "%s %d %8phC post nack\n",
-					   __func__, __LINE__, sess->port_name);
-
+				    "%s %d %8phC post nack\n",
+				    __func__, __LINE__, sess->port_name);
 				qla24xx_post_nack_work(vha, sess, iocb,
 					SRB_NACK_PRLI);
 				res = 0;
@@ -4639,7 +4765,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		}
 		break;
 
-
 	case ELS_TPRLO:
 		if (le16_to_cpu(iocb->u.isp24.flags) &
 			NOTIFY24XX_FLAGS_GLOBAL_TPRLO) {
@@ -5079,16 +5204,22 @@ qlt_send_busy(struct scsi_qla_host *vha,
 
 static int
 qlt_chk_qfull_thresh_hold(struct scsi_qla_host *vha,
-	struct atio_from_isp *atio)
+	struct atio_from_isp *atio, bool ha_locked)
 {
 	struct qla_hw_data *ha = vha->hw;
 	uint16_t status;
+	unsigned long flags;
 
 	if (ha->tgt.num_pend_cmds < Q_FULL_THRESH_HOLD(ha))
 		return 0;
 
+	if (!ha_locked)
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	status = temp_sam_status;
 	qlt_send_busy(vha, atio, status);
+	if (!ha_locked)
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	return 1;
 }
 
@@ -5103,7 +5234,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 	unsigned long flags;
 
 	if (unlikely(tgt == NULL)) {
-		ql_dbg(ql_dbg_io, vha, 0x3064,
+		ql_dbg(ql_dbg_tgt, vha, 0x3064,
 		    "ATIO pkt, but no tgt (ha %p)", ha);
 		return;
 	}
@@ -5133,7 +5264,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 
 
 		if (likely(atio->u.isp24.fcp_cmnd.task_mgmt_flags == 0)) {
-			rc = qlt_chk_qfull_thresh_hold(vha, atio);
+			rc = qlt_chk_qfull_thresh_hold(vha, atio, ha_locked);
 			if (rc != 0) {
 				tgt->atio_irq_cmd_count--;
 				return;
@@ -5256,7 +5387,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 			break;
 		}
 
-		rc = qlt_chk_qfull_thresh_hold(vha, atio);
+		rc = qlt_chk_qfull_thresh_hold(vha, atio, true);
 		if (rc != 0) {
 			tgt->irq_cmd_count--;
 			return;
@@ -5531,7 +5662,7 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
 
 	fcport->loop_id = loop_id;
 
-	rc = qla2x00_get_port_database(vha, fcport, 0);
+	rc = qla24xx_gpdb_wait(vha, fcport, 0);
 	if (rc != QLA_SUCCESS) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf070,
 		    "qla_target(%d): Failed to retrieve fcport "
@@ -5713,30 +5844,23 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 		}
 	}
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-
-	if (tgt->tgt_stop)
-		goto out_term;
-
 	rc = __qlt_24xx_handle_abts(vha, &prm->abts, sess);
+	ha->tgt.tgt_ops->put_sess(sess);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
+
 	if (rc != 0)
 		goto out_term;
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	if (sess)
-		ha->tgt.tgt_ops->put_sess(sess);
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
 	return;
 
 out_term2:
-	spin_lock_irqsave(&ha->hardware_lock, flags);
+	if (sess)
+		ha->tgt.tgt_ops->put_sess(sess);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
 
 out_term:
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
-	if (sess)
-		ha->tgt.tgt_ops->put_sess(sess);
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
 }
 
 static void qlt_tmr_work(struct qla_tgt *tgt,
@@ -5756,7 +5880,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 
 	if (tgt->tgt_stop)
-		goto out_term;
+		goto out_term2;
 
 	s_id = prm->tm_iocb2.u.isp24.fcp_hdr.s_id;
 	sess = ha->tgt.tgt_ops->find_sess_by_s_id(vha, s_id);
@@ -5768,11 +5892,11 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 		if (!sess)
-			goto out_term;
+			goto out_term2;
 	} else {
 		if (sess->deleted) {
 			sess = NULL;
-			goto out_term;
+			goto out_term2;
 		}
 
 		if (!kref_get_unless_zero(&sess->sess_kref)) {
@@ -5780,7 +5904,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 			    "%s: kref_get fail %8phC\n",
 			     __func__, sess->port_name);
 			sess = NULL;
-			goto out_term;
+			goto out_term2;
 		}
 	}
 
@@ -5790,17 +5914,19 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	unpacked_lun = scsilun_to_int((struct scsi_lun *)&lun);
 
 	rc = qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
-	if (rc != 0)
-		goto out_term;
-
 	ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
+	if (rc != 0)
+		goto out_term;
 	return;
 
+out_term2:
+	if (sess)
+		ha->tgt.tgt_ops->put_sess(sess);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 out_term:
 	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
-	ha->tgt.tgt_ops->put_sess(sess);
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 }
 
 static void qlt_sess_work_fn(struct work_struct *work)
@@ -5893,13 +6019,13 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 	tgt->datasegs_per_cmd = QLA_TGT_DATASEGS_PER_CMD_24XX;
 	tgt->datasegs_per_cont = QLA_TGT_DATASEGS_PER_CONT_24XX;
 
-	if (base_vha->fc_vport)
-		return 0;
-
 	mutex_lock(&qla_tgt_mutex);
 	list_add_tail(&tgt->tgt_list_entry, &qla_tgt_glist);
 	mutex_unlock(&qla_tgt_mutex);
 
+	if (ha->tgt.tgt_ops && ha->tgt.tgt_ops->add_target)
+		ha->tgt.tgt_ops->add_target(base_vha);
+
 	return 0;
 }
 
@@ -5928,6 +6054,17 @@ int qlt_remove_target(struct qla_hw_data *ha, struct scsi_qla_host *vha)
 	return 0;
 }
 
+void qlt_remove_target_resources(struct qla_hw_data *ha)
+{
+	struct scsi_qla_host *node;
+	u32 key = 0;
+
+	btree_for_each_safe32(&ha->tgt.host_map, key, node)
+		btree_remove32(&ha->tgt.host_map, key);
+
+	btree_destroy32(&ha->tgt.host_map);
+}
+
 static void qlt_lport_dump(struct scsi_qla_host *vha, u64 wwpn,
 	unsigned char *b)
 {
@@ -6234,7 +6371,7 @@ qlt_24xx_process_atio_queue(struct scsi_qla_host *vha, uint8_t ha_locked)
 	struct atio_from_isp *pkt;
 	int cnt, i;
 
-	if (!vha->flags.online)
+	if (!ha->flags.fw_started)
 		return;
 
 	while ((ha->tgt.atio_ring_ptr->signature != ATIO_PROCESSED) ||
@@ -6581,6 +6718,8 @@ qlt_modify_vp_config(struct scsi_qla_host *vha,
 void
 qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
 {
+	int rc;
+
 	if (!QLA_TGT_MODE_ENABLED())
 		return;
 
@@ -6600,6 +6739,13 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
 	    qlt_unknown_atio_work_fn);
 
 	qlt_clear_mode(base_vha);
+
+	rc = btree_init32(&ha->tgt.host_map);
+	if (rc)
+		ql_log(ql_log_info, base_vha, 0xffff,
+		    "Unable to initialize ha->host_map btree\n");
+
+	qlt_update_vp_map(base_vha, SET_VP_IDX);
 }
 
 irqreturn_t
@@ -6642,6 +6788,8 @@ qlt_handle_abts_recv_work(struct work_struct *work)
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	qlt_response_pkt_all_vps(vha, (response_t *)&op->atio);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
+	kfree(op);
 }
 
 void
@@ -6706,25 +6854,69 @@ qlt_mem_free(struct qla_hw_data *ha)
 void
 qlt_update_vp_map(struct scsi_qla_host *vha, int cmd)
 {
+	void *slot;
+	u32 key;
+	int rc;
+
 	if (!QLA_TGT_MODE_ENABLED())
 		return;
 
+	key = vha->d_id.b24;
+
 	switch (cmd) {
 	case SET_VP_IDX:
 		vha->hw->tgt.tgt_vp_map[vha->vp_idx].vha = vha;
 		break;
 	case SET_AL_PA:
-		vha->hw->tgt.tgt_vp_map[vha->d_id.b.al_pa].idx = vha->vp_idx;
+		slot = btree_lookup32(&vha->hw->tgt.host_map, key);
+		if (!slot) {
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			    "Save vha in host_map %p %06x\n", vha, key);
+			rc = btree_insert32(&vha->hw->tgt.host_map,
+				key, vha, GFP_ATOMIC);
+			if (rc)
+				ql_log(ql_log_info, vha, 0xffff,
+				    "Unable to insert s_id into host_map: %06x\n",
+				    key);
+			return;
+		}
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			"replace existing vha in host_map %p %06x\n", vha, key);
+		btree_update32(&vha->hw->tgt.host_map, key, vha);
 		break;
 	case RESET_VP_IDX:
 		vha->hw->tgt.tgt_vp_map[vha->vp_idx].vha = NULL;
 		break;
 	case RESET_AL_PA:
-		vha->hw->tgt.tgt_vp_map[vha->d_id.b.al_pa].idx = 0;
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+		   "clear vha in host_map %p %06x\n", vha, key);
+		slot = btree_lookup32(&vha->hw->tgt.host_map, key);
+		if (slot)
+			btree_remove32(&vha->hw->tgt.host_map, key);
+		vha->d_id.b24 = 0;
 		break;
 	}
 }
 
+void qlt_update_host_map(struct scsi_qla_host *vha, port_id_t id)
+{
+	unsigned long flags;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (!vha->d_id.b24) {
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		vha->d_id = id;
+		qlt_update_vp_map(vha, SET_AL_PA);
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
+	} else if (vha->d_id.b24 != id.b24) {
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		qlt_update_vp_map(vha, RESET_AL_PA);
+		vha->d_id = id;
+		qlt_update_vp_map(vha, SET_AL_PA);
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
+	}
+}
+
 static int __init qlt_parse_ini_mode(void)
 {
 	if (strcasecmp(qlini_mode, QLA2XXX_INI_MODE_STR_EXCLUSIVE) == 0)
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index a7f90dcaae37..d64420251194 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -378,6 +378,14 @@ static inline void adjust_corrupted_atio(struct atio_from_isp *atio)
 	atio->u.isp24.fcp_cmnd.add_cdb_len = 0;
 }
 
+static inline int get_datalen_for_atio(struct atio_from_isp *atio)
+{
+	int len = atio->u.isp24.fcp_cmnd.add_cdb_len;
+
+	return (be32_to_cpu(get_unaligned((uint32_t *)
+	    &atio->u.isp24.fcp_cmnd.add_cdb[len * 4])));
+}
+
 #define CTIO_TYPE7 0x12 /* Continue target I/O entry (for 24xx) */
 
 /*
@@ -667,7 +675,6 @@ struct qla_tgt_func_tmpl {
 	int (*handle_cmd)(struct scsi_qla_host *, struct qla_tgt_cmd *,
 			unsigned char *, uint32_t, int, int, int);
 	void (*handle_data)(struct qla_tgt_cmd *);
-	void (*handle_dif_err)(struct qla_tgt_cmd *);
 	int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint16_t,
 			uint32_t);
 	void (*free_cmd)(struct qla_tgt_cmd *);
@@ -684,6 +691,9 @@ struct qla_tgt_func_tmpl {
 	void (*clear_nacl_from_fcport_map)(struct fc_port *);
 	void (*put_sess)(struct fc_port *);
 	void (*shutdown_sess)(struct fc_port *);
+	int (*get_dif_tags)(struct qla_tgt_cmd *cmd, uint16_t *pfw_prot_opts);
+	int (*chk_dif_tags)(uint32_t tag);
+	void (*add_target)(struct scsi_qla_host *);
 };
 
 int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
@@ -720,8 +730,8 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
 #define QLA_TGT_ABORT_ALL               0xFFFE
 #define QLA_TGT_NEXUS_LOSS_SESS         0xFFFD
 #define QLA_TGT_NEXUS_LOSS              0xFFFC
-#define QLA_TGT_ABTS					0xFFFB
-#define QLA_TGT_2G_ABORT_TASK			0xFFFA
+#define QLA_TGT_ABTS			0xFFFB
+#define QLA_TGT_2G_ABORT_TASK		0xFFFA
 
 /* Notify Acknowledge flags */
 #define NOTIFY_ACK_RES_COUNT        BIT_8
@@ -845,6 +855,7 @@ enum trace_flags {
 	TRC_CMD_FREE = BIT_17,
 	TRC_DATA_IN = BIT_18,
 	TRC_ABORT = BIT_19,
+	TRC_DIF_ERR = BIT_20,
 };
 
 struct qla_tgt_cmd {
@@ -862,7 +873,6 @@ struct qla_tgt_cmd {
 	unsigned int sg_mapped:1;
 	unsigned int free_sg:1;
 	unsigned int write_data_transferred:1;
-	unsigned int ctx_dsd_alloced:1;
 	unsigned int q_full:1;
 	unsigned int term_exchg:1;
 	unsigned int cmd_sent_to_fw:1;
@@ -885,11 +895,25 @@ struct qla_tgt_cmd {
 	struct list_head cmd_list;
 
 	struct atio_from_isp atio;
-	/* t10dif */
+
+	uint8_t ctx_dsd_alloced;
+
+	/* T10-DIF */
+#define DIF_ERR_NONE 0
+#define DIF_ERR_GRD 1
+#define DIF_ERR_REF 2
+#define DIF_ERR_APP 3
+	int8_t dif_err_code;
 	struct scatterlist *prot_sg;
 	uint32_t prot_sg_cnt;
-	uint32_t blk_sz;
+	uint32_t blk_sz, num_blks;
+	uint8_t scsi_status, sense_key, asc, ascq;
+
 	struct crc_context *ctx;
+	uint8_t		*cdb;
+	uint64_t	lba;
+	uint16_t	a_guard, e_guard, a_app_tag, e_app_tag;
+	uint32_t	a_ref_tag, e_ref_tag;
 
 	uint64_t jiffies_at_alloc;
 	uint64_t jiffies_at_free;
@@ -1053,4 +1077,7 @@ extern int qlt_free_qfull_cmds(struct scsi_qla_host *);
 extern void qlt_logo_completion_handler(fc_port_t *, int);
 extern void qlt_do_generation_tick(struct scsi_qla_host *, int *);
 
+void qlt_send_resp_ctio(scsi_qla_host_t *, struct qla_tgt_cmd *, uint8_t,
+    uint8_t, uint8_t, uint8_t);
+
 #endif /* __QLA_TARGET_H */
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 3cb1964b7786..45bc84e8e3bf 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,9 +7,9 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "8.07.00.38-k"
+#define QLA2XXX_VERSION      "9.00.00.00-k"
 
-#define QLA_DRIVER_MAJOR_VER	8
-#define QLA_DRIVER_MINOR_VER	7
+#define QLA_DRIVER_MAJOR_VER	9
+#define QLA_DRIVER_MINOR_VER	0
 #define QLA_DRIVER_PATCH_VER	0
 #define QLA_DRIVER_BETA_VER	0
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 8e8ab0fa9672..7443e4efa3ae 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -531,6 +531,24 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 			return;
 		}
 
+		switch (cmd->dif_err_code) {
+		case DIF_ERR_GRD:
+			cmd->se_cmd.pi_err =
+			    TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED;
+			break;
+		case DIF_ERR_REF:
+			cmd->se_cmd.pi_err =
+			    TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
+			break;
+		case DIF_ERR_APP:
+			cmd->se_cmd.pi_err =
+			    TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED;
+			break;
+		case DIF_ERR_NONE:
+		default:
+			break;
+		}
+
 		if (cmd->se_cmd.pi_err)
 			transport_generic_request_failure(&cmd->se_cmd,
 				cmd->se_cmd.pi_err);
@@ -555,25 +573,23 @@ static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd)
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
 }
 
-static void tcm_qla2xxx_handle_dif_work(struct work_struct *work)
+static int tcm_qla2xxx_chk_dif_tags(uint32_t tag)
 {
-	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
-
-	/* take an extra kref to prevent cmd free too early.
-	 * need to wait for SCSI status/check condition to
-	 * finish responding generate by transport_generic_request_failure.
-	 */
-	kref_get(&cmd->se_cmd.cmd_kref);
-	transport_generic_request_failure(&cmd->se_cmd, cmd->se_cmd.pi_err);
+	return 0;
 }
 
-/*
- * Called from qla_target.c:qlt_do_ctio_completion()
- */
-static void tcm_qla2xxx_handle_dif_err(struct qla_tgt_cmd *cmd)
+static int tcm_qla2xxx_dif_tags(struct qla_tgt_cmd *cmd,
+    uint16_t *pfw_prot_opts)
 {
-	INIT_WORK(&cmd->work, tcm_qla2xxx_handle_dif_work);
-	queue_work(tcm_qla2xxx_free_wq, &cmd->work);
+	struct se_cmd *se_cmd = &cmd->se_cmd;
+
+	if (!(se_cmd->prot_checks & TARGET_DIF_CHECK_GUARD))
+		*pfw_prot_opts |= PO_DISABLE_GUARD_CHECK;
+
+	if (!(se_cmd->prot_checks & TARGET_DIF_CHECK_APPTAG))
+		*pfw_prot_opts |= PO_DIS_APP_TAG_VALD;
+
+	return 0;
 }
 
 /*
@@ -1610,7 +1626,6 @@ static void tcm_qla2xxx_update_sess(struct fc_port *sess, port_id_t s_id,
 static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
 	.handle_cmd		= tcm_qla2xxx_handle_cmd,
 	.handle_data		= tcm_qla2xxx_handle_data,
-	.handle_dif_err		= tcm_qla2xxx_handle_dif_err,
 	.handle_tmr		= tcm_qla2xxx_handle_tmr,
 	.free_cmd		= tcm_qla2xxx_free_cmd,
 	.free_mcmd		= tcm_qla2xxx_free_mcmd,
@@ -1622,6 +1637,8 @@ static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
 	.clear_nacl_from_fcport_map = tcm_qla2xxx_clear_nacl_from_fcport_map,
 	.put_sess		= tcm_qla2xxx_put_sess,
 	.shutdown_sess		= tcm_qla2xxx_shutdown_sess,
+	.get_dif_tags		= tcm_qla2xxx_dif_tags,
+	.chk_dif_tags		= tcm_qla2xxx_chk_dif_tags,
 };
 
 static int tcm_qla2xxx_init_lport(struct tcm_qla2xxx_lport *lport)
diff --git a/drivers/scsi/scsi_debugfs.c b/drivers/scsi/scsi_debugfs.c
new file mode 100644
index 000000000000..a97c9507103d
--- /dev/null
+++ b/drivers/scsi/scsi_debugfs.c
@@ -0,0 +1,13 @@
+#include <linux/seq_file.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_dbg.h>
+#include "scsi_debugfs.h"
+
+void scsi_show_rq(struct seq_file *m, struct request *rq)
+{
+	struct scsi_cmnd *cmd = container_of(scsi_req(rq), typeof(*cmd), req);
+	char buf[80];
+
+	__scsi_format_command(buf, sizeof(buf), cmd->cmnd, cmd->cmd_len);
+	seq_printf(m, ", .cmd=%s", buf);
+}
diff --git a/drivers/scsi/scsi_debugfs.h b/drivers/scsi/scsi_debugfs.h
new file mode 100644
index 000000000000..951b043e82d0
--- /dev/null
+++ b/drivers/scsi/scsi_debugfs.h
@@ -0,0 +1,4 @@
+struct request;
+struct seq_file;
+
+void scsi_show_rq(struct seq_file *m, struct request *rq);
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f2cafae150bc..2db412dd4b44 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1988,7 +1988,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 
 	req->rq_flags |= RQF_QUIET;
 	req->timeout = 10 * HZ;
-	req->retries = 5;
+	rq->retries = 5;
 
 	blk_execute_rq_nowait(req->q, NULL, req, 1, eh_lock_door_done);
 }
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ba2286652ff6..1c3e87d6c48f 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -34,6 +34,7 @@
 
 #include <trace/events/scsi.h>
 
+#include "scsi_debugfs.h"
 #include "scsi_priv.h"
 #include "scsi_logging.h"
 
@@ -229,8 +230,8 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
  * @rq_flags:	flags for ->rq_flags
  * @resid:	optional residual length
  *
- * returns the req->errors value which is the scsi_cmnd result
- * field.
+ * Returns the scsi_cmnd result field if a command was executed, or a negative
+ * Linux error code if we didn't get that far.
  */
 int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
@@ -256,7 +257,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	rq->cmd_len = COMMAND_SIZE(cmd[0]);
 	memcpy(rq->cmd, cmd, rq->cmd_len);
-	req->retries = retries;
+	rq->retries = retries;
 	req->timeout = timeout;
 	req->cmd_flags |= flags;
 	req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT;
@@ -281,7 +282,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
 	if (sshdr)
 		scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
-	ret = req->errors;
+	ret = rq->result;
  out:
 	blk_put_request(req);
 
@@ -496,7 +497,7 @@ static void scsi_run_queue(struct request_queue *q)
 		scsi_starved_list_run(sdev->host);
 
 	if (q->mq_ops)
-		blk_mq_start_stopped_hw_queues(q, false);
+		blk_mq_run_hw_queues(q, false);
 	else
 		blk_run_queue(q);
 }
@@ -667,7 +668,7 @@ static bool scsi_end_request(struct request *req, int error,
 		    !list_empty(&sdev->host->starved_list))
 			kblockd_schedule_work(&sdev->requeue_work);
 		else
-			blk_mq_start_stopped_hw_queues(q, true);
+			blk_mq_run_hw_queues(q, true);
 	} else {
 		unsigned long flags;
 
@@ -797,8 +798,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		/*
 		 * __scsi_error_from_host_byte may have reset the host_byte
 		 */
-		req->errors = cmd->result;
-
+		scsi_req(req)->result = cmd->result;
 		scsi_req(req)->resid_len = scsi_get_resid(cmd);
 
 		if (scsi_bidi_cmnd(cmd)) {
@@ -835,7 +835,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	/*
 	 * Recovered errors need reporting, but they're always treated as
 	 * success, so fiddle the result code here.  For passthrough requests
-	 * we already took a copy of the original into rq->errors which
+	 * we already took a copy of the original into sreq->result which
 	 * is what gets returned to the user
 	 */
 	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
@@ -1061,10 +1061,10 @@ int scsi_init_io(struct scsi_cmnd *cmd)
 	struct scsi_device *sdev = cmd->device;
 	struct request *rq = cmd->request;
 	bool is_mq = (rq->mq_ctx != NULL);
-	int error;
+	int error = BLKPREP_KILL;
 
 	if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq)))
-		return -EINVAL;
+		goto err_exit;
 
 	error = scsi_init_sgtable(rq, &cmd->sdb);
 	if (error)
@@ -1177,7 +1177,7 @@ static int scsi_setup_scsi_cmnd(struct scsi_device *sdev, struct request *req)
 	cmd->cmd_len = scsi_req(req)->cmd_len;
 	cmd->cmnd = scsi_req(req)->cmd;
 	cmd->transfersize = blk_rq_bytes(req);
-	cmd->allowed = req->retries;
+	cmd->allowed = scsi_req(req)->retries;
 	return BLKPREP_OK;
 }
 
@@ -1281,7 +1281,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 	switch (ret) {
 	case BLKPREP_KILL:
 	case BLKPREP_INVALID:
-		req->errors = DID_NO_CONNECT << 16;
+		scsi_req(req)->result = DID_NO_CONNECT << 16;
 		/* release the command and kill it */
 		if (req->special) {
 			struct scsi_cmnd *cmd = req->special;
@@ -1905,7 +1905,7 @@ static int scsi_mq_prep_fn(struct request *req)
 static void scsi_mq_done(struct scsi_cmnd *cmd)
 {
 	trace_scsi_dispatch_cmd_done(cmd);
-	blk_mq_complete_request(cmd->request, cmd->request->errors);
+	blk_mq_complete_request(cmd->request);
 }
 
 static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -1974,7 +1974,7 @@ out:
 	case BLK_MQ_RQ_QUEUE_BUSY:
 		if (atomic_read(&sdev->device_busy) == 0 &&
 		    !scsi_device_blocked(sdev))
-			blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);
+			blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY);
 		break;
 	case BLK_MQ_RQ_QUEUE_ERROR:
 		/*
@@ -2154,10 +2154,13 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
 	return q;
 }
 
-static struct blk_mq_ops scsi_mq_ops = {
+static const struct blk_mq_ops scsi_mq_ops = {
 	.queue_rq	= scsi_queue_rq,
 	.complete	= scsi_softirq_done,
 	.timeout	= scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.show_rq	= scsi_show_rq,
+#endif
 	.init_request	= scsi_init_request,
 	.exit_request	= scsi_exit_request,
 	.map_queues	= scsi_map_queues,
@@ -2932,6 +2935,8 @@ EXPORT_SYMBOL(scsi_target_resume);
 /**
  * scsi_internal_device_block - internal function to put a device temporarily into the SDEV_BLOCK state
  * @sdev:	device to block
+ * @wait:	Whether or not to wait until ongoing .queuecommand() /
+ *		.queue_rq() calls have finished.
  *
  * Block request made by scsi lld's to temporarily stop all
  * scsi commands on the specified device. May sleep.
@@ -2949,7 +2954,7 @@ EXPORT_SYMBOL(scsi_target_resume);
  * remove the rport mutex lock and unlock calls from srp_queuecommand().
  */
 int
-scsi_internal_device_block(struct scsi_device *sdev)
+scsi_internal_device_block(struct scsi_device *sdev, bool wait)
 {
 	struct request_queue *q = sdev->request_queue;
 	unsigned long flags;
@@ -2969,12 +2974,16 @@ scsi_internal_device_block(struct scsi_device *sdev)
 	 * request queue. 
 	 */
 	if (q->mq_ops) {
-		blk_mq_quiesce_queue(q);
+		if (wait)
+			blk_mq_quiesce_queue(q);
+		else
+			blk_mq_stop_hw_queues(q);
 	} else {
 		spin_lock_irqsave(q->queue_lock, flags);
 		blk_stop_queue(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
-		scsi_wait_for_queuecommand(sdev);
+		if (wait)
+			scsi_wait_for_queuecommand(sdev);
 	}
 
 	return 0;
@@ -3036,7 +3045,7 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_unblock);
 static void
 device_block(struct scsi_device *sdev, void *data)
 {
-	scsi_internal_device_block(sdev);
+	scsi_internal_device_block(sdev, true);
 }
 
 static int
diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c
index 109802f776ed..50e624fb8307 100644
--- a/drivers/scsi/scsi_netlink.c
+++ b/drivers/scsi/scsi_netlink.c
@@ -111,7 +111,7 @@ scsi_nl_rcv_msg(struct sk_buff *skb)
 
 next_msg:
 		if ((err) || (nlh->nlmsg_flags & NLM_F_ACK))
-			netlink_ack(skb, nlh, err);
+			netlink_ack(skb, nlh, err, NULL);
 
 		skb_pull(skb, rlen);
 	}
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 99bfc985e190..f11bd102d6d5 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -188,8 +188,5 @@ static inline void scsi_dh_remove_device(struct scsi_device *sdev) { }
  */
 
 #define SCSI_DEVICE_BLOCK_MAX_TIMEOUT	600	/* units in seconds */
-extern int scsi_internal_device_block(struct scsi_device *sdev);
-extern int scsi_internal_device_unblock(struct scsi_device *sdev,
-					enum scsi_device_state new_state);
 
 #endif /* _SCSI_PRIV_H */
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index cdbb293aca08..9fdbd50c31b4 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -184,9 +184,9 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost,
 				blk_rq_bytes(req->next_rq);
 		handler = to_sas_internal(shost->transportt)->f->smp_handler;
 		ret = handler(shost, rphy, req);
-		req->errors = ret;
+		scsi_req(req)->result = ret;
 
-		blk_end_request_all(req, ret);
+		blk_end_request_all(req, 0);
 
 		spin_lock_irq(q->queue_lock);
 	}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c7839f6c35cc..0dc95e102e69 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -418,6 +418,46 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(provisioning_mode);
 
+static const char *zeroing_mode[] = {
+	[SD_ZERO_WRITE]		= "write",
+	[SD_ZERO_WS]		= "writesame",
+	[SD_ZERO_WS16_UNMAP]	= "writesame_16_unmap",
+	[SD_ZERO_WS10_UNMAP]	= "writesame_10_unmap",
+};
+
+static ssize_t
+zeroing_mode_show(struct device *dev, struct device_attribute *attr,
+		  char *buf)
+{
+	struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+	return snprintf(buf, 20, "%s\n", zeroing_mode[sdkp->zeroing_mode]);
+}
+
+static ssize_t
+zeroing_mode_store(struct device *dev, struct device_attribute *attr,
+		   const char *buf, size_t count)
+{
+	struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!strncmp(buf, zeroing_mode[SD_ZERO_WRITE], 20))
+		sdkp->zeroing_mode = SD_ZERO_WRITE;
+	else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS], 20))
+		sdkp->zeroing_mode = SD_ZERO_WS;
+	else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS16_UNMAP], 20))
+		sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+	else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS10_UNMAP], 20))
+		sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+	else
+		return -EINVAL;
+
+	return count;
+}
+static DEVICE_ATTR_RW(zeroing_mode);
+
 static ssize_t
 max_medium_access_timeouts_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
@@ -496,6 +536,7 @@ static struct attribute *sd_disk_attrs[] = {
 	&dev_attr_app_tag_own.attr,
 	&dev_attr_thin_provisioning.attr,
 	&dev_attr_provisioning_mode.attr,
+	&dev_attr_zeroing_mode.attr,
 	&dev_attr_max_write_same_blocks.attr,
 	&dev_attr_max_medium_access_timeouts.attr,
 	NULL,
@@ -644,26 +685,11 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	unsigned int logical_block_size = sdkp->device->sector_size;
 	unsigned int max_blocks = 0;
 
-	q->limits.discard_zeroes_data = 0;
-
-	/*
-	 * When LBPRZ is reported, discard alignment and granularity
-	 * must be fixed to the logical block size. Otherwise the block
-	 * layer will drop misaligned portions of the request which can
-	 * lead to data corruption. If LBPRZ is not set, we honor the
-	 * device preference.
-	 */
-	if (sdkp->lbprz) {
-		q->limits.discard_alignment = 0;
-		q->limits.discard_granularity = logical_block_size;
-	} else {
-		q->limits.discard_alignment = sdkp->unmap_alignment *
-			logical_block_size;
-		q->limits.discard_granularity =
-			max(sdkp->physical_block_size,
-			    sdkp->unmap_granularity * logical_block_size);
-	}
-
+	q->limits.discard_alignment =
+		sdkp->unmap_alignment * logical_block_size;
+	q->limits.discard_granularity =
+		max(sdkp->physical_block_size,
+		    sdkp->unmap_granularity * logical_block_size);
 	sdkp->provisioning_mode = mode;
 
 	switch (mode) {
@@ -681,19 +707,16 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	case SD_LBP_WS16:
 		max_blocks = min_not_zero(sdkp->max_ws_blocks,
 					  (u32)SD_MAX_WS16_BLOCKS);
-		q->limits.discard_zeroes_data = sdkp->lbprz;
 		break;
 
 	case SD_LBP_WS10:
 		max_blocks = min_not_zero(sdkp->max_ws_blocks,
 					  (u32)SD_MAX_WS10_BLOCKS);
-		q->limits.discard_zeroes_data = sdkp->lbprz;
 		break;
 
 	case SD_LBP_ZERO:
 		max_blocks = min_not_zero(sdkp->max_ws_blocks,
 					  (u32)SD_MAX_WS10_BLOCKS);
-		q->limits.discard_zeroes_data = 1;
 		break;
 	}
 
@@ -701,93 +724,122 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
-/**
- * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
- * @sdp: scsi device to operate on
- * @rq: Request to prepare
- *
- * Will issue either UNMAP or WRITE SAME(16) depending on preference
- * indicated by target device.
- **/
-static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
+static int sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
 {
-	struct request *rq = cmd->request;
 	struct scsi_device *sdp = cmd->device;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
-	sector_t sector = blk_rq_pos(rq);
-	unsigned int nr_sectors = blk_rq_sectors(rq);
-	unsigned int len;
-	int ret;
+	struct request *rq = cmd->request;
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	unsigned int data_len = 24;
 	char *buf;
-	struct page *page;
 
-	sector >>= ilog2(sdp->sector_size) - 9;
-	nr_sectors >>= ilog2(sdp->sector_size) - 9;
-
-	page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
-	if (!page)
+	rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+	if (!rq->special_vec.bv_page)
 		return BLKPREP_DEFER;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = data_len;
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
-	switch (sdkp->provisioning_mode) {
-	case SD_LBP_UNMAP:
-		buf = page_address(page);
+	cmd->cmd_len = 10;
+	cmd->cmnd[0] = UNMAP;
+	cmd->cmnd[8] = 24;
 
-		cmd->cmd_len = 10;
-		cmd->cmnd[0] = UNMAP;
-		cmd->cmnd[8] = 24;
+	buf = page_address(rq->special_vec.bv_page);
+	put_unaligned_be16(6 + 16, &buf[0]);
+	put_unaligned_be16(16, &buf[2]);
+	put_unaligned_be64(sector, &buf[8]);
+	put_unaligned_be32(nr_sectors, &buf[16]);
 
-		put_unaligned_be16(6 + 16, &buf[0]);
-		put_unaligned_be16(16, &buf[2]);
-		put_unaligned_be64(sector, &buf[8]);
-		put_unaligned_be32(nr_sectors, &buf[16]);
+	cmd->allowed = SD_MAX_RETRIES;
+	cmd->transfersize = data_len;
+	rq->timeout = SD_TIMEOUT;
+	scsi_req(rq)->resid_len = data_len;
 
-		len = 24;
-		break;
+	return scsi_init_io(cmd);
+}
 
-	case SD_LBP_WS16:
-		cmd->cmd_len = 16;
-		cmd->cmnd[0] = WRITE_SAME_16;
+static int sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+	struct scsi_device *sdp = cmd->device;
+	struct request *rq = cmd->request;
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 data_len = sdp->sector_size;
+
+	rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+	if (!rq->special_vec.bv_page)
+		return BLKPREP_DEFER;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = data_len;
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+	cmd->cmd_len = 16;
+	cmd->cmnd[0] = WRITE_SAME_16;
+	if (unmap)
 		cmd->cmnd[1] = 0x8; /* UNMAP */
-		put_unaligned_be64(sector, &cmd->cmnd[2]);
-		put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
+	put_unaligned_be64(sector, &cmd->cmnd[2]);
+	put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
 
-		len = sdkp->device->sector_size;
-		break;
+	cmd->allowed = SD_MAX_RETRIES;
+	cmd->transfersize = data_len;
+	rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+	scsi_req(rq)->resid_len = data_len;
 
-	case SD_LBP_WS10:
-	case SD_LBP_ZERO:
-		cmd->cmd_len = 10;
-		cmd->cmnd[0] = WRITE_SAME;
-		if (sdkp->provisioning_mode == SD_LBP_WS10)
-			cmd->cmnd[1] = 0x8; /* UNMAP */
-		put_unaligned_be32(sector, &cmd->cmnd[2]);
-		put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
+	return scsi_init_io(cmd);
+}
 
-		len = sdkp->device->sector_size;
-		break;
+static int sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+	struct scsi_device *sdp = cmd->device;
+	struct request *rq = cmd->request;
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 data_len = sdp->sector_size;
 
-	default:
-		ret = BLKPREP_INVALID;
-		goto out;
-	}
+	rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+	if (!rq->special_vec.bv_page)
+		return BLKPREP_DEFER;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = data_len;
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
-	rq->timeout = SD_TIMEOUT;
+	cmd->cmd_len = 10;
+	cmd->cmnd[0] = WRITE_SAME;
+	if (unmap)
+		cmd->cmnd[1] = 0x8; /* UNMAP */
+	put_unaligned_be32(sector, &cmd->cmnd[2]);
+	put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
 
-	cmd->transfersize = len;
 	cmd->allowed = SD_MAX_RETRIES;
+	cmd->transfersize = data_len;
+	rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+	scsi_req(rq)->resid_len = data_len;
 
-	rq->special_vec.bv_page = page;
-	rq->special_vec.bv_offset = 0;
-	rq->special_vec.bv_len = len;
+	return scsi_init_io(cmd);
+}
 
-	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
-	scsi_req(rq)->resid_len = len;
+static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
+{
+	struct request *rq = cmd->request;
+	struct scsi_device *sdp = cmd->device;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+
+	if (!(rq->cmd_flags & REQ_NOUNMAP)) {
+		switch (sdkp->zeroing_mode) {
+		case SD_ZERO_WS16_UNMAP:
+			return sd_setup_write_same16_cmnd(cmd, true);
+		case SD_ZERO_WS10_UNMAP:
+			return sd_setup_write_same10_cmnd(cmd, true);
+		}
+	}
 
-	ret = scsi_init_io(cmd);
-out:
-	if (ret != BLKPREP_OK)
-		__free_page(page);
-	return ret;
+	if (sdp->no_write_same)
+		return BLKPREP_INVALID;
+	if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
+		return sd_setup_write_same16_cmnd(cmd, false);
+	return sd_setup_write_same10_cmnd(cmd, false);
 }
 
 static void sd_config_write_same(struct scsi_disk *sdkp)
@@ -816,9 +868,20 @@ static void sd_config_write_same(struct scsi_disk *sdkp)
 		sdkp->max_ws_blocks = 0;
 	}
 
+	if (sdkp->lbprz && sdkp->lbpws)
+		sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+	else if (sdkp->lbprz && sdkp->lbpws10)
+		sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+	else if (sdkp->max_ws_blocks)
+		sdkp->zeroing_mode = SD_ZERO_WS;
+	else
+		sdkp->zeroing_mode = SD_ZERO_WRITE;
+
 out:
 	blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
 					 (logical_block_size >> 9));
+	blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks *
+					 (logical_block_size >> 9));
 }
 
 /**
@@ -1155,7 +1218,20 @@ static int sd_init_command(struct scsi_cmnd *cmd)
 
 	switch (req_op(rq)) {
 	case REQ_OP_DISCARD:
-		return sd_setup_discard_cmnd(cmd);
+		switch (scsi_disk(rq->rq_disk)->provisioning_mode) {
+		case SD_LBP_UNMAP:
+			return sd_setup_unmap_cmnd(cmd);
+		case SD_LBP_WS16:
+			return sd_setup_write_same16_cmnd(cmd, true);
+		case SD_LBP_WS10:
+			return sd_setup_write_same10_cmnd(cmd, true);
+		case SD_LBP_ZERO:
+			return sd_setup_write_same10_cmnd(cmd, false);
+		default:
+			return BLKPREP_INVALID;
+		}
+	case REQ_OP_WRITE_ZEROES:
+		return sd_setup_write_zeroes_cmnd(cmd);
 	case REQ_OP_WRITE_SAME:
 		return sd_setup_write_same_cmnd(cmd);
 	case REQ_OP_FLUSH:
@@ -1783,6 +1859,8 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 {
 	int result = SCpnt->result;
 	unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt);
+	unsigned int sector_size = SCpnt->device->sector_size;
+	unsigned int resid;
 	struct scsi_sense_hdr sshdr;
 	struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk);
 	struct request *req = SCpnt->request;
@@ -1793,6 +1871,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 
 	switch (req_op(req)) {
 	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE_SAME:
 	case REQ_OP_ZONE_RESET:
 		if (!result) {
@@ -1813,6 +1892,21 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 			scsi_set_resid(SCpnt, blk_rq_bytes(req));
 		}
 		break;
+	default:
+		/*
+		 * In case of bogus fw or device, we could end up having
+		 * an unaligned partial completion. Check this here and force
+		 * alignment.
+		 */
+		resid = scsi_get_resid(SCpnt);
+		if (resid & (sector_size - 1)) {
+			sd_printk(KERN_INFO, sdkp,
+				"Unaligned partial completion (resid=%u, sector_sz=%u)\n",
+				resid, sector_size);
+			resid = min(scsi_bufflen(SCpnt),
+				    round_up(resid, sector_size));
+			scsi_set_resid(SCpnt, resid);
+		}
 	}
 
 	if (result) {
@@ -2085,6 +2179,22 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
 
 #define READ_CAPACITY_RETRIES_ON_RESET	10
 
+/*
+ * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set
+ * and the reported logical block size is bigger than 512 bytes. Note
+ * that last_sector is a u64 and therefore logical_to_sectors() is not
+ * applicable.
+ */
+static bool sd_addressable_capacity(u64 lba, unsigned int sector_size)
+{
+	u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9);
+
+	if (sizeof(sector_t) == 4 && last_sector > U32_MAX)
+		return false;
+
+	return true;
+}
+
 static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 						unsigned char *buffer)
 {
@@ -2150,7 +2260,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 		return -ENODEV;
 	}
 
-	if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) {
+	if (!sd_addressable_capacity(lba, sector_size)) {
 		sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
 			"kernel compiled with support for large block "
 			"devices.\n");
@@ -2239,7 +2349,7 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp,
 		return sector_size;
 	}
 
-	if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) {
+	if (!sd_addressable_capacity(lba, sector_size)) {
 		sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
 			"kernel compiled with support for large block "
 			"devices.\n");
@@ -2735,7 +2845,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 				sd_config_discard(sdkp, SD_LBP_WS16);
 
 		} else {	/* LBP VPD page tells us what to use */
-			if (sdkp->lbpu && sdkp->max_unmap_blocks && !sdkp->lbprz)
+			if (sdkp->lbpu && sdkp->max_unmap_blocks)
 				sd_config_discard(sdkp, SD_LBP_UNMAP);
 			else if (sdkp->lbpws)
 				sd_config_discard(sdkp, SD_LBP_WS16);
@@ -2939,7 +3049,8 @@ static int sd_revalidate_disk(struct gendisk *disk)
 		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
 		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
 	} else
-		rw_max = BLK_DEF_MAX_SECTORS;
+		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
+				      (sector_t)BLK_DEF_MAX_SECTORS);
 
 	/* Combine with controller limits */
 	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
@@ -3075,23 +3186,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 	put_device(&sdkp->dev);
 }
 
-struct sd_devt {
-	int idx;
-	struct disk_devt disk_devt;
-};
-
-static void sd_devt_release(struct disk_devt *disk_devt)
-{
-	struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt,
-			disk_devt);
-
-	spin_lock(&sd_index_lock);
-	ida_remove(&sd_index_ida, sd_devt->idx);
-	spin_unlock(&sd_index_lock);
-
-	kfree(sd_devt);
-}
-
 /**
  *	sd_probe - called during driver initialization and whenever a
  *	new scsi device is attached to the system. It is called once
@@ -3113,7 +3207,6 @@ static void sd_devt_release(struct disk_devt *disk_devt)
 static int sd_probe(struct device *dev)
 {
 	struct scsi_device *sdp = to_scsi_device(dev);
-	struct sd_devt *sd_devt;
 	struct scsi_disk *sdkp;
 	struct gendisk *gd;
 	int index;
@@ -3139,13 +3232,9 @@ static int sd_probe(struct device *dev)
 	if (!sdkp)
 		goto out;
 
-	sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL);
-	if (!sd_devt)
-		goto out_free;
-
 	gd = alloc_disk(SD_MINORS);
 	if (!gd)
-		goto out_free_devt;
+		goto out_free;
 
 	do {
 		if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
@@ -3161,11 +3250,6 @@ static int sd_probe(struct device *dev)
 		goto out_put;
 	}
 
-	atomic_set(&sd_devt->disk_devt.count, 1);
-	sd_devt->disk_devt.release = sd_devt_release;
-	sd_devt->idx = index;
-	gd->disk_devt = &sd_devt->disk_devt;
-
 	error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
 	if (error) {
 		sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n");
@@ -3205,12 +3289,11 @@ static int sd_probe(struct device *dev)
 	return 0;
 
  out_free_index:
-	put_disk_devt(&sd_devt->disk_devt);
-	sd_devt = NULL;
+	spin_lock(&sd_index_lock);
+	ida_remove(&sd_index_ida, index);
+	spin_unlock(&sd_index_lock);
  out_put:
 	put_disk(gd);
- out_free_devt:
-	kfree(sd_devt);
  out_free:
 	kfree(sdkp);
  out:
@@ -3271,7 +3354,10 @@ static void scsi_disk_release(struct device *dev)
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 	struct gendisk *disk = sdkp->disk;
 	
-	put_disk_devt(disk->disk_devt);
+	spin_lock(&sd_index_lock);
+	ida_remove(&sd_index_ida, sdkp->index);
+	spin_unlock(&sd_index_lock);
+
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4dac35e96a75..a2c4b5c35379 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -59,6 +59,13 @@ enum {
 	SD_LBP_DISABLE,		/* Discard disabled due to failed cmd */
 };
 
+enum {
+	SD_ZERO_WRITE = 0,	/* Use WRITE(10/16) command */
+	SD_ZERO_WS,		/* Use WRITE SAME(10/16) command */
+	SD_ZERO_WS16_UNMAP,	/* Use WRITE SAME(16) with UNMAP */
+	SD_ZERO_WS10_UNMAP,	/* Use WRITE SAME(10) with UNMAP */
+};
+
 struct scsi_disk {
 	struct scsi_driver *driver;	/* always &sd_template */
 	struct scsi_device *device;
@@ -89,6 +96,7 @@ struct scsi_disk {
 	u8		write_prot;
 	u8		protection_type;/* Data Integrity Field */
 	u8		provisioning_mode;
+	u8		zeroing_mode;
 	unsigned	ATO : 1;	/* state of disk ATO bit */
 	unsigned	cache_override : 1; /* temp override of WCE,RCD */
 	unsigned	WCE : 1;	/* state of disk WCE bit */
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 92620c8ea8ad..1994f7799fce 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -329,6 +329,7 @@ void sd_zbc_complete(struct scsi_cmnd *cmd,
 
 	switch (req_op(rq)) {
 	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE_SAME:
 	case REQ_OP_ZONE_RESET:
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 29b86505f796..0b60245bd740 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -581,7 +581,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	sg_io_hdr_t *hp;
 	unsigned char cmnd[SG_MAX_CDB_SIZE];
 
-	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+	if (unlikely(uaccess_kernel()))
 		return -EINVAL;
 
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
@@ -996,6 +996,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		result = get_user(val, ip);
 		if (result)
 			return result;
+		if (val > SG_MAX_CDB_SIZE)
+			return -ENOMEM;
 		sfp->next_cmd_len = (val > 0) ? val : 0;
 		return 0;
 	case SG_GET_VERSION_NUM:
@@ -1298,7 +1300,7 @@ sg_rq_end_io(struct request *rq, int uptodate)
 		pr_info("%s: device detaching\n", __func__);
 
 	sense = req->sense;
-	result = rq->errors;
+	result = req->result;
 	resid = req->resid_len;
 
 	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
@@ -1716,7 +1718,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 
 	srp->rq = rq;
 	rq->end_io_data = srp;
-	rq->retries = SG_DEFAULT_RETRIES;
+	req->retries = SG_DEFAULT_RETRIES;
 
 	if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE))
 		return 0;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 0b29b9329b1c..a8f630213a1a 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -836,6 +836,7 @@ static void get_capabilities(struct scsi_cd *cd)
 	unsigned char *buffer;
 	struct scsi_mode_data data;
 	struct scsi_sense_hdr sshdr;
+	unsigned int ms_len = 128;
 	int rc, n;
 
 	static const char *loadmech[] =
@@ -862,10 +863,11 @@ static void get_capabilities(struct scsi_cd *cd)
 	scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr);
 
 	/* ask for mode page 0x2a */
-	rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, 128,
+	rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len,
 			     SR_TIMEOUT, 3, &data, NULL);
 
-	if (!scsi_status_is_good(rc)) {
+	if (!scsi_status_is_good(rc) || data.length > ms_len ||
+	    data.header_length + data.block_descriptor_length > data.length) {
 		/* failed, drive doesn't have capabilities mode page */
 		cd->cdi.speed = 1;
 		cd->cdi.mask |= (CDC_CD_R | CDC_CD_RW | CDC_DVD_R |
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e5ef78a6848e..1ea34d6f5437 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -480,7 +480,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_write_time);
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
 		atomic64_inc(&STp->stats->write_cnt);
-		if (req->errors) {
+		if (scsi_req(req)->result) {
 			atomic64_add(atomic_read(&STp->stats->last_write_size)
 				- STp->buffer->cmdstat.residual,
 				&STp->stats->write_byte_cnt);
@@ -494,7 +494,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_read_time);
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
 		atomic64_inc(&STp->stats->read_cnt);
-		if (req->errors) {
+		if (scsi_req(req)->result) {
 			atomic64_add(atomic_read(&STp->stats->last_read_size)
 				- STp->buffer->cmdstat.residual,
 				&STp->stats->read_byte_cnt);
@@ -518,7 +518,7 @@ static void st_scsi_execute_end(struct request *req, int uptodate)
 	struct scsi_tape *STp = SRpnt->stp;
 	struct bio *tmp;
 
-	STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
+	STp->buffer->cmdstat.midlevel_result = SRpnt->result = rq->result;
 	STp->buffer->cmdstat.residual = rq->resid_len;
 
 	st_do_stats(STp, req);
@@ -579,7 +579,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 	memset(rq->cmd, 0, BLK_MAX_CDB);
 	memcpy(rq->cmd, cmd, rq->cmd_len);
 	req->timeout = timeout;
-	req->retries = retries;
+	rq->retries = retries;
 	req->end_io_data = SRpnt;
 
 	blk_execute_rq_nowait(req->q, NULL, req, 1, st_scsi_execute_end);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 638e5f427c90..016639d7fef1 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -400,8 +400,6 @@ MODULE_PARM_DESC(storvsc_vcpus_per_sub_channel, "Ratio of VCPUs to subchannels")
  */
 static int storvsc_timeout = 180;
 
-static int msft_blist_flags = BLIST_TRY_VPD_PAGES;
-
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 static struct scsi_transport_template *fc_transport_template;
 #endif
@@ -1383,6 +1381,22 @@ static int storvsc_do_io(struct hv_device *device,
 	return ret;
 }
 
+static int storvsc_device_alloc(struct scsi_device *sdevice)
+{
+	/*
+	 * Set blist flag to permit the reading of the VPD pages even when
+	 * the target may claim SPC-2 compliance. MSFT targets currently
+	 * claim SPC-2 compliance while they implement post SPC-2 features.
+	 * With this flag we can correctly handle WRITE_SAME_16 issues.
+	 *
+	 * Hypervisor reports SCSI_UNKNOWN type for DVD ROM device but
+	 * still supports REPORT LUN.
+	 */
+	sdevice->sdev_bflags = BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES;
+
+	return 0;
+}
+
 static int storvsc_device_configure(struct scsi_device *sdevice)
 {
 
@@ -1396,14 +1410,6 @@ static int storvsc_device_configure(struct scsi_device *sdevice)
 	sdevice->no_write_same = 1;
 
 	/*
-	 * Add blist flags to permit the reading of the VPD pages even when
-	 * the target may claim SPC-2 compliance. MSFT targets currently
-	 * claim SPC-2 compliance while they implement post SPC-2 features.
-	 * With this patch we can correctly handle WRITE_SAME_16 issues.
-	 */
-	sdevice->sdev_bflags |= msft_blist_flags;
-
-	/*
 	 * If the host is WIN8 or WIN8 R2, claim conformance to SPC-3
 	 * if the device is a MSFT virtual device.  If the host is
 	 * WIN10 or newer, allow write_same.
@@ -1661,6 +1667,7 @@ static struct scsi_host_template scsi_driver = {
 	.eh_host_reset_handler =	storvsc_host_reset_handler,
 	.proc_name =		"storvsc_host",
 	.eh_timed_out =		storvsc_eh_timed_out,
+	.slave_alloc =		storvsc_device_alloc,
 	.slave_configure =	storvsc_device_configure,
 	.cmd_per_lun =		255,
 	.this_id =		-1,
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 318e4a1f76c9..54deeb754db5 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -146,7 +146,7 @@ enum attr_idn {
 /* Descriptor idn for Query requests */
 enum desc_idn {
 	QUERY_DESC_IDN_DEVICE		= 0x0,
-	QUERY_DESC_IDN_CONFIGURAION	= 0x1,
+	QUERY_DESC_IDN_CONFIGURATION	= 0x1,
 	QUERY_DESC_IDN_UNIT		= 0x2,
 	QUERY_DESC_IDN_RFU_0		= 0x3,
 	QUERY_DESC_IDN_INTERCONNECT	= 0x4,
@@ -162,19 +162,13 @@ enum desc_header_offset {
 	QUERY_DESC_DESC_TYPE_OFFSET	= 0x01,
 };
 
-enum ufs_desc_max_size {
-	QUERY_DESC_DEVICE_MAX_SIZE		= 0x40,
-	QUERY_DESC_CONFIGURAION_MAX_SIZE	= 0x90,
-	QUERY_DESC_UNIT_MAX_SIZE		= 0x23,
-	QUERY_DESC_INTERCONNECT_MAX_SIZE	= 0x06,
-	/*
-	 * Max. 126 UNICODE characters (2 bytes per character) plus 2 bytes
-	 * of descriptor header.
-	 */
-	QUERY_DESC_STRING_MAX_SIZE		= 0xFE,
-	QUERY_DESC_GEOMETRY_MAX_SIZE		= 0x44,
-	QUERY_DESC_POWER_MAX_SIZE		= 0x62,
-	QUERY_DESC_RFU_MAX_SIZE			= 0x00,
+enum ufs_desc_def_size {
+	QUERY_DESC_DEVICE_DEF_SIZE		= 0x40,
+	QUERY_DESC_CONFIGURATION_DEF_SIZE	= 0x90,
+	QUERY_DESC_UNIT_DEF_SIZE		= 0x23,
+	QUERY_DESC_INTERCONNECT_DEF_SIZE	= 0x06,
+	QUERY_DESC_GEOMETRY_DEF_SIZE		= 0x44,
+	QUERY_DESC_POWER_DEF_SIZE		= 0x62,
 };
 
 /* Unit descriptor parameters offsets in bytes*/
diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c
index a72a4ba78125..8e5e6c04c035 100644
--- a/drivers/scsi/ufs/ufshcd-pltfrm.c
+++ b/drivers/scsi/ufs/ufshcd-pltfrm.c
@@ -309,8 +309,8 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mmio_base = devm_ioremap_resource(dev, mem_res);
-	if (IS_ERR(*(void **)&mmio_base)) {
-		err = PTR_ERR(*(void **)&mmio_base);
+	if (IS_ERR(mmio_base)) {
+		err = PTR_ERR(mmio_base);
 		goto out;
 	}
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index dc6efbd1be8e..096e95b911bd 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -100,19 +100,6 @@
 #define ufshcd_hex_dump(prefix_str, buf, len) \
 print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
 
-static u32 ufs_query_desc_max_size[] = {
-	QUERY_DESC_DEVICE_MAX_SIZE,
-	QUERY_DESC_CONFIGURAION_MAX_SIZE,
-	QUERY_DESC_UNIT_MAX_SIZE,
-	QUERY_DESC_RFU_MAX_SIZE,
-	QUERY_DESC_INTERCONNECT_MAX_SIZE,
-	QUERY_DESC_STRING_MAX_SIZE,
-	QUERY_DESC_RFU_MAX_SIZE,
-	QUERY_DESC_GEOMETRY_MAX_SIZE,
-	QUERY_DESC_POWER_MAX_SIZE,
-	QUERY_DESC_RFU_MAX_SIZE,
-};
-
 enum {
 	UFSHCD_MAX_CHANNEL	= 0,
 	UFSHCD_MAX_ID		= 1,
@@ -2857,7 +2844,7 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba,
 		goto out;
 	}
 
-	if (*buf_len <= QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) {
+	if (*buf_len < QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) {
 		dev_err(hba->dev, "%s: descriptor buffer size (%d) is out of range\n",
 				__func__, *buf_len);
 		err = -EINVAL;
@@ -2938,6 +2925,92 @@ static int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
 }
 
 /**
+ * ufshcd_read_desc_length - read the specified descriptor length from header
+ * @hba: Pointer to adapter instance
+ * @desc_id: descriptor idn value
+ * @desc_index: descriptor index
+ * @desc_length: pointer to variable to read the length of descriptor
+ *
+ * Return 0 in case of success, non-zero otherwise
+ */
+static int ufshcd_read_desc_length(struct ufs_hba *hba,
+	enum desc_idn desc_id,
+	int desc_index,
+	int *desc_length)
+{
+	int ret;
+	u8 header[QUERY_DESC_HDR_SIZE];
+	int header_len = QUERY_DESC_HDR_SIZE;
+
+	if (desc_id >= QUERY_DESC_IDN_MAX)
+		return -EINVAL;
+
+	ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC,
+					desc_id, desc_index, 0, header,
+					&header_len);
+
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed to get descriptor header id %d",
+			__func__, desc_id);
+		return ret;
+	} else if (desc_id != header[QUERY_DESC_DESC_TYPE_OFFSET]) {
+		dev_warn(hba->dev, "%s: descriptor header id %d and desc_id %d mismatch",
+			__func__, header[QUERY_DESC_DESC_TYPE_OFFSET],
+			desc_id);
+		ret = -EINVAL;
+	}
+
+	*desc_length = header[QUERY_DESC_LENGTH_OFFSET];
+	return ret;
+
+}
+
+/**
+ * ufshcd_map_desc_id_to_length - map descriptor IDN to its length
+ * @hba: Pointer to adapter instance
+ * @desc_id: descriptor idn value
+ * @desc_len: mapped desc length (out)
+ *
+ * Return 0 in case of success, non-zero otherwise
+ */
+int ufshcd_map_desc_id_to_length(struct ufs_hba *hba,
+	enum desc_idn desc_id, int *desc_len)
+{
+	switch (desc_id) {
+	case QUERY_DESC_IDN_DEVICE:
+		*desc_len = hba->desc_size.dev_desc;
+		break;
+	case QUERY_DESC_IDN_POWER:
+		*desc_len = hba->desc_size.pwr_desc;
+		break;
+	case QUERY_DESC_IDN_GEOMETRY:
+		*desc_len = hba->desc_size.geom_desc;
+		break;
+	case QUERY_DESC_IDN_CONFIGURATION:
+		*desc_len = hba->desc_size.conf_desc;
+		break;
+	case QUERY_DESC_IDN_UNIT:
+		*desc_len = hba->desc_size.unit_desc;
+		break;
+	case QUERY_DESC_IDN_INTERCONNECT:
+		*desc_len = hba->desc_size.interc_desc;
+		break;
+	case QUERY_DESC_IDN_STRING:
+		*desc_len = QUERY_DESC_MAX_SIZE;
+		break;
+	case QUERY_DESC_IDN_RFU_0:
+	case QUERY_DESC_IDN_RFU_1:
+		*desc_len = 0;
+		break;
+	default:
+		*desc_len = 0;
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ufshcd_map_desc_id_to_length);
+
+/**
  * ufshcd_read_desc_param - read the specified descriptor parameter
  * @hba: Pointer to adapter instance
  * @desc_id: descriptor idn value
@@ -2951,42 +3024,49 @@ static int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
 static int ufshcd_read_desc_param(struct ufs_hba *hba,
 				  enum desc_idn desc_id,
 				  int desc_index,
-				  u32 param_offset,
+				  u8 param_offset,
 				  u8 *param_read_buf,
-				  u32 param_size)
+				  u8 param_size)
 {
 	int ret;
 	u8 *desc_buf;
-	u32 buff_len;
+	int buff_len;
 	bool is_kmalloc = true;
 
-	/* safety checks */
-	if (desc_id >= QUERY_DESC_IDN_MAX)
+	/* Safety check */
+	if (desc_id >= QUERY_DESC_IDN_MAX || !param_size)
 		return -EINVAL;
 
-	buff_len = ufs_query_desc_max_size[desc_id];
-	if ((param_offset + param_size) > buff_len)
-		return -EINVAL;
+	/* Get the max length of descriptor from structure filled up at probe
+	 * time.
+	 */
+	ret = ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len);
 
-	if (!param_offset && (param_size == buff_len)) {
-		/* memory space already available to hold full descriptor */
-		desc_buf = param_read_buf;
-		is_kmalloc = false;
-	} else {
-		/* allocate memory to hold full descriptor */
+	/* Sanity checks */
+	if (ret || !buff_len) {
+		dev_err(hba->dev, "%s: Failed to get full descriptor length",
+			__func__);
+		return ret;
+	}
+
+	/* Check whether we need temp memory */
+	if (param_offset != 0 || param_size < buff_len) {
 		desc_buf = kmalloc(buff_len, GFP_KERNEL);
 		if (!desc_buf)
 			return -ENOMEM;
+	} else {
+		desc_buf = param_read_buf;
+		is_kmalloc = false;
 	}
 
+	/* Request for full descriptor */
 	ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC,
-					desc_id, desc_index, 0, desc_buf,
-					&buff_len);
+					desc_id, desc_index, 0,
+					desc_buf, &buff_len);
 
 	if (ret) {
 		dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d",
 			__func__, desc_id, desc_index, param_offset, ret);
-
 		goto out;
 	}
 
@@ -2998,25 +3078,9 @@ static int ufshcd_read_desc_param(struct ufs_hba *hba,
 		goto out;
 	}
 
-	/*
-	 * While reading variable size descriptors (like string descriptor),
-	 * some UFS devices may report the "LENGTH" (field in "Transaction
-	 * Specific fields" of Query Response UPIU) same as what was requested
-	 * in Query Request UPIU instead of reporting the actual size of the
-	 * variable size descriptor.
-	 * Although it's safe to ignore the "LENGTH" field for variable size
-	 * descriptors as we can always derive the length of the descriptor from
-	 * the descriptor header fields. Hence this change impose the length
-	 * match check only for fixed size descriptors (for which we always
-	 * request the correct size as part of Query Request UPIU).
-	 */
-	if ((desc_id != QUERY_DESC_IDN_STRING) &&
-	    (buff_len != desc_buf[QUERY_DESC_LENGTH_OFFSET])) {
-		dev_err(hba->dev, "%s: desc_buf length mismatch: buff_len %d, buff_len(desc_header) %d",
-			__func__, buff_len, desc_buf[QUERY_DESC_LENGTH_OFFSET]);
-		ret = -EINVAL;
-		goto out;
-	}
+	/* Check wherher we will not copy more data, than available */
+	if (is_kmalloc && param_size > buff_len)
+		param_size = buff_len;
 
 	if (is_kmalloc)
 		memcpy(param_read_buf, &desc_buf[param_offset], param_size);
@@ -4598,8 +4662,6 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 		}
 		if (ufshcd_is_clkscaling_supported(hba))
 			hba->clk_scaling.active_reqs--;
-		if (ufshcd_is_clkscaling_supported(hba))
-			hba->clk_scaling.active_reqs--;
 	}
 
 	/* clear corresponding bits of completed commands */
@@ -5919,8 +5981,8 @@ static int ufshcd_set_icc_levels_attr(struct ufs_hba *hba, u32 icc_level)
 static void ufshcd_init_icc_levels(struct ufs_hba *hba)
 {
 	int ret;
-	int buff_len = QUERY_DESC_POWER_MAX_SIZE;
-	u8 desc_buf[QUERY_DESC_POWER_MAX_SIZE];
+	int buff_len = hba->desc_size.pwr_desc;
+	u8 desc_buf[hba->desc_size.pwr_desc];
 
 	ret = ufshcd_read_power_desc(hba, desc_buf, buff_len);
 	if (ret) {
@@ -6017,11 +6079,10 @@ static int ufs_get_device_desc(struct ufs_hba *hba,
 {
 	int err;
 	u8 model_index;
-	u8 str_desc_buf[QUERY_DESC_STRING_MAX_SIZE + 1] = {0};
-	u8 desc_buf[QUERY_DESC_DEVICE_MAX_SIZE];
+	u8 str_desc_buf[QUERY_DESC_MAX_SIZE + 1] = {0};
+	u8 desc_buf[hba->desc_size.dev_desc];
 
-	err = ufshcd_read_device_desc(hba, desc_buf,
-					QUERY_DESC_DEVICE_MAX_SIZE);
+	err = ufshcd_read_device_desc(hba, desc_buf, hba->desc_size.dev_desc);
 	if (err) {
 		dev_err(hba->dev, "%s: Failed reading Device Desc. err = %d\n",
 			__func__, err);
@@ -6038,14 +6099,14 @@ static int ufs_get_device_desc(struct ufs_hba *hba,
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
 
 	err = ufshcd_read_string_desc(hba, model_index, str_desc_buf,
-					QUERY_DESC_STRING_MAX_SIZE, ASCII_STD);
+				QUERY_DESC_MAX_SIZE, ASCII_STD);
 	if (err) {
 		dev_err(hba->dev, "%s: Failed reading Product Name. err = %d\n",
 			__func__, err);
 		goto out;
 	}
 
-	str_desc_buf[QUERY_DESC_STRING_MAX_SIZE] = '\0';
+	str_desc_buf[QUERY_DESC_MAX_SIZE] = '\0';
 	strlcpy(dev_desc->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
 		min_t(u8, str_desc_buf[QUERY_DESC_LENGTH_OFFSET],
 		      MAX_MODEL_LEN));
@@ -6251,6 +6312,51 @@ static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
 	hba->req_abort_count = 0;
 }
 
+static void ufshcd_init_desc_sizes(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_DEVICE, 0,
+		&hba->desc_size.dev_desc);
+	if (err)
+		hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_POWER, 0,
+		&hba->desc_size.pwr_desc);
+	if (err)
+		hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_INTERCONNECT, 0,
+		&hba->desc_size.interc_desc);
+	if (err)
+		hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_CONFIGURATION, 0,
+		&hba->desc_size.conf_desc);
+	if (err)
+		hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_UNIT, 0,
+		&hba->desc_size.unit_desc);
+	if (err)
+		hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_GEOMETRY, 0,
+		&hba->desc_size.geom_desc);
+	if (err)
+		hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+}
+
+static void ufshcd_def_desc_sizes(struct ufs_hba *hba)
+{
+	hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
+	hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
+	hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
+	hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
+	hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
+	hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+}
+
 /**
  * ufshcd_probe_hba - probe hba to detect device and initialize
  * @hba: per-adapter instance
@@ -6285,6 +6391,9 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	if (ret)
 		goto out;
 
+	/* Init check for device descriptor sizes */
+	ufshcd_init_desc_sizes(hba);
+
 	ret = ufs_get_device_desc(hba, &card);
 	if (ret) {
 		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
@@ -6320,6 +6429,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 
 	/* set the state as operational after switching to desired gear */
 	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+
 	/*
 	 * If we are in error handling context or in power management callbacks
 	 * context, no need to scan the host
@@ -7530,7 +7640,7 @@ static inline ssize_t ufshcd_pm_lvl_store(struct device *dev,
 	if (kstrtoul(buf, 0, &value))
 		return -EINVAL;
 
-	if ((value < UFS_PM_LVL_0) || (value >= UFS_PM_LVL_MAX))
+	if (value >= UFS_PM_LVL_MAX)
 		return -EINVAL;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
@@ -7774,6 +7884,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	hba->mmio_base = mmio_base;
 	hba->irq = irq;
 
+	/* Set descriptor lengths to specification defaults */
+	ufshcd_def_desc_sizes(hba);
+
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 7630600217a2..cdc8bd05f7df 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -220,6 +220,15 @@ struct ufs_dev_cmd {
 	struct ufs_query query;
 };
 
+struct ufs_desc_size {
+	int dev_desc;
+	int pwr_desc;
+	int geom_desc;
+	int interc_desc;
+	int unit_desc;
+	int conf_desc;
+};
+
 /**
  * struct ufs_clk_info - UFS clock related info
  * @list: list headed by hba->clk_list_head
@@ -483,6 +492,7 @@ struct ufs_stats {
  * @clk_list_head: UFS host controller clocks list node head
  * @pwr_info: holds current power mode
  * @max_pwr_info: keeps the device max valid pwm
+ * @desc_size: descriptor sizes reported by device
  * @urgent_bkops_lvl: keeps track of urgent bkops level for device
  * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
  *  device is known or not.
@@ -666,6 +676,7 @@ struct ufs_hba {
 	bool is_urgent_bkops_lvl_checked;
 
 	struct rw_semaphore clk_scaling_lock;
+	struct ufs_desc_size desc_size;
 };
 
 /* Returns true if clocks can be gated. Otherwise false */
@@ -832,6 +843,10 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	enum flag_idn idn, bool *flag_res);
 int ufshcd_hold(struct ufs_hba *hba, bool async);
 void ufshcd_release(struct ufs_hba *hba);
+
+int ufshcd_map_desc_id_to_length(struct ufs_hba *hba, enum desc_idn desc_id,
+	int *desc_length);
+
 u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba);
 
 /* Wrapper functions for safely calling variant operations */
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index ef474a748744..c374e3b5c678 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -1487,7 +1487,7 @@ static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		irq_flag &= ~PCI_IRQ_MSI;
 
 	error = pci_alloc_irq_vectors(adapter->dev, 1, 1, irq_flag);
-	if (error)
+	if (error < 0)
 		goto out_reset_adapter;
 
 	adapter->use_req_threshold = pvscsi_setup_req_threshold(adapter, true);
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 6f509f68085e..3d891db57ee6 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -2019,8 +2019,7 @@ out:
 	return ret;
 }
 
-static int qman_query_fq_np(struct qman_fq *fq,
-			    struct qm_mcr_queryfq_np *np)
+int qman_query_fq_np(struct qman_fq *fq, struct qm_mcr_queryfq_np *np)
 {
 	union qm_mc_command *mcc;
 	union qm_mc_result *mcr;
@@ -2046,6 +2045,7 @@ out:
 	put_affine_portal();
 	return ret;
 }
+EXPORT_SYMBOL(qman_query_fq_np);
 
 static int qman_query_cgr(struct qman_cgr *cgr,
 			  struct qm_mcr_querycgr *cgrd)
diff --git a/drivers/soc/fsl/qbman/qman_ccsr.c b/drivers/soc/fsl/qbman/qman_ccsr.c
index f4e6e70de259..90bc40c48675 100644
--- a/drivers/soc/fsl/qbman/qman_ccsr.c
+++ b/drivers/soc/fsl/qbman/qman_ccsr.c
@@ -34,6 +34,8 @@ u16 qman_ip_rev;
 EXPORT_SYMBOL(qman_ip_rev);
 u16 qm_channel_pool1 = QMAN_CHANNEL_POOL1;
 EXPORT_SYMBOL(qm_channel_pool1);
+u16 qm_channel_caam = QMAN_CHANNEL_CAAM;
+EXPORT_SYMBOL(qm_channel_caam);
 
 /* Register offsets */
 #define REG_QCSP_LIO_CFG(n)	(0x0000 + ((n) * 0x10))
@@ -720,8 +722,10 @@ static int fsl_qman_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	if ((qman_ip_rev & 0xff00) >= QMAN_REV30)
+	if ((qman_ip_rev & 0xff00) >= QMAN_REV30) {
 		qm_channel_pool1 = QMAN_CHANNEL_POOL1_REV3;
+		qm_channel_caam = QMAN_CHANNEL_CAAM_REV3;
+	}
 
 	ret = zero_priv_mem(dev, node, fqd_a, fqd_sz);
 	WARN_ON(ret);
diff --git a/drivers/soc/fsl/qbman/qman_priv.h b/drivers/soc/fsl/qbman/qman_priv.h
index 53685b59718e..22725bdc6f15 100644
--- a/drivers/soc/fsl/qbman/qman_priv.h
+++ b/drivers/soc/fsl/qbman/qman_priv.h
@@ -89,67 +89,6 @@ static inline u64 qm_mcr_querycgr_a_get64(const struct qm_mcr_querycgr *q)
 	return ((u64)q->a_bcnt_hi << 32) | be32_to_cpu(q->a_bcnt_lo);
 }
 
-/* "Query FQ Non-Programmable Fields" */
-
-struct qm_mcr_queryfq_np {
-	u8 verb;
-	u8 result;
-	u8 __reserved1;
-	u8 state;		/* QM_MCR_NP_STATE_*** */
-	u32 fqd_link;		/* 24-bit, _res2[24-31] */
-	u16 odp_seq;		/* 14-bit, _res3[14-15] */
-	u16 orp_nesn;		/* 14-bit, _res4[14-15] */
-	u16 orp_ea_hseq;	/* 15-bit, _res5[15] */
-	u16 orp_ea_tseq;	/* 15-bit, _res6[15] */
-	u32 orp_ea_hptr;	/* 24-bit, _res7[24-31] */
-	u32 orp_ea_tptr;	/* 24-bit, _res8[24-31] */
-	u32 pfdr_hptr;		/* 24-bit, _res9[24-31] */
-	u32 pfdr_tptr;		/* 24-bit, _res10[24-31] */
-	u8 __reserved2[5];
-	u8 is;			/* 1-bit, _res12[1-7] */
-	u16 ics_surp;
-	u32 byte_cnt;
-	u32 frm_cnt;		/* 24-bit, _res13[24-31] */
-	u32 __reserved3;
-	u16 ra1_sfdr;		/* QM_MCR_NP_RA1_*** */
-	u16 ra2_sfdr;		/* QM_MCR_NP_RA2_*** */
-	u16 __reserved4;
-	u16 od1_sfdr;		/* QM_MCR_NP_OD1_*** */
-	u16 od2_sfdr;		/* QM_MCR_NP_OD2_*** */
-	u16 od3_sfdr;		/* QM_MCR_NP_OD3_*** */
-} __packed;
-
-#define QM_MCR_NP_STATE_FE		0x10
-#define QM_MCR_NP_STATE_R		0x08
-#define QM_MCR_NP_STATE_MASK		0x07	/* Reads FQD::STATE; */
-#define QM_MCR_NP_STATE_OOS		0x00
-#define QM_MCR_NP_STATE_RETIRED		0x01
-#define QM_MCR_NP_STATE_TEN_SCHED	0x02
-#define QM_MCR_NP_STATE_TRU_SCHED	0x03
-#define QM_MCR_NP_STATE_PARKED		0x04
-#define QM_MCR_NP_STATE_ACTIVE		0x05
-#define QM_MCR_NP_PTR_MASK		0x07ff	/* for RA[12] & OD[123] */
-#define QM_MCR_NP_RA1_NRA(v)		(((v) >> 14) & 0x3)	/* FQD::NRA */
-#define QM_MCR_NP_RA2_IT(v)		(((v) >> 14) & 0x1)	/* FQD::IT */
-#define QM_MCR_NP_OD1_NOD(v)		(((v) >> 14) & 0x3)	/* FQD::NOD */
-#define QM_MCR_NP_OD3_NPC(v)		(((v) >> 14) & 0x3)	/* FQD::NPC */
-
-enum qm_mcr_queryfq_np_masks {
-	qm_mcr_fqd_link_mask = BIT(24)-1,
-	qm_mcr_odp_seq_mask = BIT(14)-1,
-	qm_mcr_orp_nesn_mask = BIT(14)-1,
-	qm_mcr_orp_ea_hseq_mask = BIT(15)-1,
-	qm_mcr_orp_ea_tseq_mask = BIT(15)-1,
-	qm_mcr_orp_ea_hptr_mask = BIT(24)-1,
-	qm_mcr_orp_ea_tptr_mask = BIT(24)-1,
-	qm_mcr_pfdr_hptr_mask = BIT(24)-1,
-	qm_mcr_pfdr_tptr_mask = BIT(24)-1,
-	qm_mcr_is_mask = BIT(1)-1,
-	qm_mcr_frm_cnt_mask = BIT(24)-1,
-};
-#define qm_mcr_np_get(np, field) \
-	((np)->field & (qm_mcr_##field##_mask))
-
 /* Congestion Groups */
 
 /*
@@ -271,42 +210,6 @@ const struct qm_portal_config *qman_destroy_affine_portal(void);
  */
 int qman_query_fq(struct qman_fq *fq, struct qm_fqd *fqd);
 
-/*
- * For qman_volatile_dequeue(); Choose one PRECEDENCE. EXACT is optional. Use
- * NUMFRAMES(n) (6-bit) or NUMFRAMES_TILLEMPTY to fill in the frame-count. Use
- * FQID(n) to fill in the frame queue ID.
- */
-#define QM_VDQCR_PRECEDENCE_VDQCR	0x0
-#define QM_VDQCR_PRECEDENCE_SDQCR	0x80000000
-#define QM_VDQCR_EXACT			0x40000000
-#define QM_VDQCR_NUMFRAMES_MASK		0x3f000000
-#define QM_VDQCR_NUMFRAMES_SET(n)	(((n) & 0x3f) << 24)
-#define QM_VDQCR_NUMFRAMES_GET(n)	(((n) >> 24) & 0x3f)
-#define QM_VDQCR_NUMFRAMES_TILLEMPTY	QM_VDQCR_NUMFRAMES_SET(0)
-
-#define QMAN_VOLATILE_FLAG_WAIT	     0x00000001 /* wait if VDQCR is in use */
-#define QMAN_VOLATILE_FLAG_WAIT_INT  0x00000002 /* if wait, interruptible? */
-#define QMAN_VOLATILE_FLAG_FINISH    0x00000004 /* wait till VDQCR completes */
-
-/*
- * qman_volatile_dequeue - Issue a volatile dequeue command
- * @fq: the frame queue object to dequeue from
- * @flags: a bit-mask of QMAN_VOLATILE_FLAG_*** options
- * @vdqcr: bit mask of QM_VDQCR_*** options, as per qm_dqrr_vdqcr_set()
- *
- * Attempts to lock access to the portal's VDQCR volatile dequeue functionality.
- * The function will block and sleep if QMAN_VOLATILE_FLAG_WAIT is specified and
- * the VDQCR is already in use, otherwise returns non-zero for failure. If
- * QMAN_VOLATILE_FLAG_FINISH is specified, the function will only return once
- * the VDQCR command has finished executing (ie. once the callback for the last
- * DQRR entry resulting from the VDQCR command has been called). If not using
- * the FINISH flag, completion can be determined either by detecting the
- * presence of the QM_DQRR_STAT_UNSCHEDULED and QM_DQRR_STAT_DQCR_EXPIRED bits
- * in the "stat" parameter passed to the FQ's dequeue callback, or by waiting
- * for the QMAN_FQ_STATE_VDQCR bit to disappear.
- */
-int qman_volatile_dequeue(struct qman_fq *fq, u32 flags, u32 vdqcr);
-
 int qman_alloc_fq_table(u32 num_fqids);
 
 /*   QMan s/w corenet portal, low-level i/face	 */
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 78b1bb7bcf20..9fca977ef18d 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -33,17 +33,10 @@ config QCOM_SMEM
 	  The driver provides an interface to items in a heap shared among all
 	  processors in a Qualcomm platform.
 
-config QCOM_SMD
-	tristate "Qualcomm Shared Memory Driver (SMD)"
-	depends on QCOM_SMEM
-	help
-	  Say y here to enable support for the Qualcomm Shared Memory Driver
-	  providing communication channels to remote processors in Qualcomm
-	  platforms.
-
 config QCOM_SMD_RPM
 	tristate "Qualcomm Resource Power Manager (RPM) over SMD"
-	depends on QCOM_SMD && OF
+	depends on ARCH_QCOM
+	depends on RPMSG && OF
 	help
 	  If you say yes to this option, support will be included for the
 	  Resource Power Manager system found in the Qualcomm 8974 based
@@ -76,7 +69,8 @@ config QCOM_SMSM
 
 config QCOM_WCNSS_CTRL
 	tristate "Qualcomm WCNSS control driver"
-	depends on QCOM_SMD
+	depends on ARCH_QCOM
+	depends on RPMSG
 	help
 	  Client driver for the WCNSS_CTRL SMD channel, used to download nv
 	  firmware to a newly booted WCNSS chip.
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 1f30260b06b8..414f0de274fa 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,7 +1,6 @@
 obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
 obj-$(CONFIG_QCOM_MDT_LOADER)	+= mdt_loader.o
 obj-$(CONFIG_QCOM_PM)	+=	spm.o
-obj-$(CONFIG_QCOM_SMD) +=	smd.o
 obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
 obj-$(CONFIG_QCOM_SMEM) +=	smem.o
 obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
diff --git a/drivers/soc/qcom/smd-rpm.c b/drivers/soc/qcom/smd-rpm.c
index 6609d7e0edb0..c2346752b3ea 100644
--- a/drivers/soc/qcom/smd-rpm.c
+++ b/drivers/soc/qcom/smd-rpm.c
@@ -19,7 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/smd-rpm.h>
 
 #define RPM_REQUEST_TIMEOUT     (5 * HZ)
@@ -32,7 +32,7 @@
  * @ack_status:		result of the rpm request
  */
 struct qcom_smd_rpm {
-	struct qcom_smd_channel *rpm_channel;
+	struct rpmsg_endpoint *rpm_channel;
 	struct device *dev;
 
 	struct completion ack;
@@ -133,7 +133,7 @@ int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm,
 	pkt->req.data_len = cpu_to_le32(count);
 	memcpy(pkt->payload, buf, count);
 
-	ret = qcom_smd_send(rpm->rpm_channel, pkt, size);
+	ret = rpmsg_send(rpm->rpm_channel, pkt, size);
 	if (ret)
 		goto out;
 
@@ -150,14 +150,16 @@ out:
 }
 EXPORT_SYMBOL(qcom_rpm_smd_write);
 
-static int qcom_smd_rpm_callback(struct qcom_smd_channel *channel,
-				 const void *data,
-				 size_t count)
+static int qcom_smd_rpm_callback(struct rpmsg_device *rpdev,
+				 void *data,
+				 int count,
+				 void *priv,
+				 u32 addr)
 {
 	const struct qcom_rpm_header *hdr = data;
 	size_t hdr_length = le32_to_cpu(hdr->length);
 	const struct qcom_rpm_message *msg;
-	struct qcom_smd_rpm *rpm = qcom_smd_get_drvdata(channel);
+	struct qcom_smd_rpm *rpm = dev_get_drvdata(&rpdev->dev);
 	const u8 *buf = data + sizeof(struct qcom_rpm_header);
 	const u8 *end = buf + hdr_length;
 	char msgbuf[32];
@@ -196,59 +198,57 @@ static int qcom_smd_rpm_callback(struct qcom_smd_channel *channel,
 	return 0;
 }
 
-static int qcom_smd_rpm_probe(struct qcom_smd_device *sdev)
+static int qcom_smd_rpm_probe(struct rpmsg_device *rpdev)
 {
 	struct qcom_smd_rpm *rpm;
 
-	rpm = devm_kzalloc(&sdev->dev, sizeof(*rpm), GFP_KERNEL);
+	rpm = devm_kzalloc(&rpdev->dev, sizeof(*rpm), GFP_KERNEL);
 	if (!rpm)
 		return -ENOMEM;
 
 	mutex_init(&rpm->lock);
 	init_completion(&rpm->ack);
 
-	rpm->dev = &sdev->dev;
-	rpm->rpm_channel = sdev->channel;
-	qcom_smd_set_drvdata(sdev->channel, rpm);
+	rpm->dev = &rpdev->dev;
+	rpm->rpm_channel = rpdev->ept;
+	dev_set_drvdata(&rpdev->dev, rpm);
 
-	dev_set_drvdata(&sdev->dev, rpm);
-
-	return of_platform_populate(sdev->dev.of_node, NULL, NULL, &sdev->dev);
+	return of_platform_populate(rpdev->dev.of_node, NULL, NULL, &rpdev->dev);
 }
 
-static void qcom_smd_rpm_remove(struct qcom_smd_device *sdev)
+static void qcom_smd_rpm_remove(struct rpmsg_device *rpdev)
 {
-	of_platform_depopulate(&sdev->dev);
+	of_platform_depopulate(&rpdev->dev);
 }
 
 static const struct of_device_id qcom_smd_rpm_of_match[] = {
 	{ .compatible = "qcom,rpm-apq8084" },
 	{ .compatible = "qcom,rpm-msm8916" },
 	{ .compatible = "qcom,rpm-msm8974" },
+	{ .compatible = "qcom,rpm-msm8996" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, qcom_smd_rpm_of_match);
 
-static struct qcom_smd_driver qcom_smd_rpm_driver = {
+static struct rpmsg_driver qcom_smd_rpm_driver = {
 	.probe = qcom_smd_rpm_probe,
 	.remove = qcom_smd_rpm_remove,
 	.callback = qcom_smd_rpm_callback,
-	.driver  = {
+	.drv  = {
 		.name  = "qcom_smd_rpm",
-		.owner = THIS_MODULE,
 		.of_match_table = qcom_smd_rpm_of_match,
 	},
 };
 
 static int __init qcom_smd_rpm_init(void)
 {
-	return qcom_smd_driver_register(&qcom_smd_rpm_driver);
+	return register_rpmsg_driver(&qcom_smd_rpm_driver);
 }
 arch_initcall(qcom_smd_rpm_init);
 
 static void __exit qcom_smd_rpm_exit(void)
 {
-	qcom_smd_driver_unregister(&qcom_smd_rpm_driver);
+	unregister_rpmsg_driver(&qcom_smd_rpm_driver);
 }
 module_exit(qcom_smd_rpm_exit);
 
diff --git a/drivers/soc/qcom/smd.c b/drivers/soc/qcom/smd.c
deleted file mode 100644
index 322034ab9d37..000000000000
--- a/drivers/soc/qcom/smd.c
+++ /dev/null
@@ -1,1560 +0,0 @@
-/*
- * Copyright (c) 2015, Sony Mobile Communications AB.
- * Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/mfd/syscon.h>
-#include <linux/module.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
-#include <linux/soc/qcom/smem.h>
-#include <linux/wait.h>
-
-/*
- * The Qualcomm Shared Memory communication solution provides point-to-point
- * channels for clients to send and receive streaming or packet based data.
- *
- * Each channel consists of a control item (channel info) and a ring buffer
- * pair. The channel info carry information related to channel state, flow
- * control and the offsets within the ring buffer.
- *
- * All allocated channels are listed in an allocation table, identifying the
- * pair of items by name, type and remote processor.
- *
- * Upon creating a new channel the remote processor allocates channel info and
- * ring buffer items from the smem heap and populate the allocation table. An
- * interrupt is sent to the other end of the channel and a scan for new
- * channels should be done. A channel never goes away, it will only change
- * state.
- *
- * The remote processor signals it intent for bring up the communication
- * channel by setting the state of its end of the channel to "opening" and
- * sends out an interrupt. We detect this change and register a smd device to
- * consume the channel. Upon finding a consumer we finish the handshake and the
- * channel is up.
- *
- * Upon closing a channel, the remote processor will update the state of its
- * end of the channel and signal us, we will then unregister any attached
- * device and close our end of the channel.
- *
- * Devices attached to a channel can use the qcom_smd_send function to push
- * data to the channel, this is done by copying the data into the tx ring
- * buffer, updating the pointers in the channel info and signaling the remote
- * processor.
- *
- * The remote processor does the equivalent when it transfer data and upon
- * receiving the interrupt we check the channel info for new data and delivers
- * this to the attached device. If the device is not ready to receive the data
- * we leave it in the ring buffer for now.
- */
-
-struct smd_channel_info;
-struct smd_channel_info_pair;
-struct smd_channel_info_word;
-struct smd_channel_info_word_pair;
-
-#define SMD_ALLOC_TBL_COUNT	2
-#define SMD_ALLOC_TBL_SIZE	64
-
-/*
- * This lists the various smem heap items relevant for the allocation table and
- * smd channel entries.
- */
-static const struct {
-	unsigned alloc_tbl_id;
-	unsigned info_base_id;
-	unsigned fifo_base_id;
-} smem_items[SMD_ALLOC_TBL_COUNT] = {
-	{
-		.alloc_tbl_id = 13,
-		.info_base_id = 14,
-		.fifo_base_id = 338
-	},
-	{
-		.alloc_tbl_id = 266,
-		.info_base_id = 138,
-		.fifo_base_id = 202,
-	},
-};
-
-/**
- * struct qcom_smd_edge - representing a remote processor
- * @dev:		device for this edge
- * @of_node:		of_node handle for information related to this edge
- * @edge_id:		identifier of this edge
- * @remote_pid:		identifier of remote processor
- * @irq:		interrupt for signals on this edge
- * @ipc_regmap:		regmap handle holding the outgoing ipc register
- * @ipc_offset:		offset within @ipc_regmap of the register for ipc
- * @ipc_bit:		bit in the register at @ipc_offset of @ipc_regmap
- * @channels:		list of all channels detected on this edge
- * @channels_lock:	guard for modifications of @channels
- * @allocated:		array of bitmaps representing already allocated channels
- * @smem_available:	last available amount of smem triggering a channel scan
- * @scan_work:		work item for discovering new channels
- * @state_work:		work item for edge state changes
- */
-struct qcom_smd_edge {
-	struct device dev;
-
-	struct device_node *of_node;
-	unsigned edge_id;
-	unsigned remote_pid;
-
-	int irq;
-
-	struct regmap *ipc_regmap;
-	int ipc_offset;
-	int ipc_bit;
-
-	struct list_head channels;
-	spinlock_t channels_lock;
-
-	DECLARE_BITMAP(allocated[SMD_ALLOC_TBL_COUNT], SMD_ALLOC_TBL_SIZE);
-
-	unsigned smem_available;
-
-	wait_queue_head_t new_channel_event;
-
-	struct work_struct scan_work;
-	struct work_struct state_work;
-};
-
-#define to_smd_edge(d) container_of(d, struct qcom_smd_edge, dev)
-
-/*
- * SMD channel states.
- */
-enum smd_channel_state {
-	SMD_CHANNEL_CLOSED,
-	SMD_CHANNEL_OPENING,
-	SMD_CHANNEL_OPENED,
-	SMD_CHANNEL_FLUSHING,
-	SMD_CHANNEL_CLOSING,
-	SMD_CHANNEL_RESET,
-	SMD_CHANNEL_RESET_OPENING
-};
-
-/**
- * struct qcom_smd_channel - smd channel struct
- * @edge:		qcom_smd_edge this channel is living on
- * @qsdev:		reference to a associated smd client device
- * @name:		name of the channel
- * @state:		local state of the channel
- * @remote_state:	remote state of the channel
- * @info:		byte aligned outgoing/incoming channel info
- * @info_word:		word aligned outgoing/incoming channel info
- * @tx_lock:		lock to make writes to the channel mutually exclusive
- * @fblockread_event:	wakeup event tied to tx fBLOCKREADINTR
- * @tx_fifo:		pointer to the outgoing ring buffer
- * @rx_fifo:		pointer to the incoming ring buffer
- * @fifo_size:		size of each ring buffer
- * @bounce_buffer:	bounce buffer for reading wrapped packets
- * @cb:			callback function registered for this channel
- * @recv_lock:		guard for rx info modifications and cb pointer
- * @pkt_size:		size of the currently handled packet
- * @list:		lite entry for @channels in qcom_smd_edge
- */
-struct qcom_smd_channel {
-	struct qcom_smd_edge *edge;
-
-	struct qcom_smd_device *qsdev;
-
-	char *name;
-	enum smd_channel_state state;
-	enum smd_channel_state remote_state;
-
-	struct smd_channel_info_pair *info;
-	struct smd_channel_info_word_pair *info_word;
-
-	struct mutex tx_lock;
-	wait_queue_head_t fblockread_event;
-
-	void *tx_fifo;
-	void *rx_fifo;
-	int fifo_size;
-
-	void *bounce_buffer;
-	qcom_smd_cb_t cb;
-
-	spinlock_t recv_lock;
-
-	int pkt_size;
-
-	void *drvdata;
-
-	struct list_head list;
-};
-
-/*
- * Format of the smd_info smem items, for byte aligned channels.
- */
-struct smd_channel_info {
-	__le32 state;
-	u8  fDSR;
-	u8  fCTS;
-	u8  fCD;
-	u8  fRI;
-	u8  fHEAD;
-	u8  fTAIL;
-	u8  fSTATE;
-	u8  fBLOCKREADINTR;
-	__le32 tail;
-	__le32 head;
-};
-
-struct smd_channel_info_pair {
-	struct smd_channel_info tx;
-	struct smd_channel_info rx;
-};
-
-/*
- * Format of the smd_info smem items, for word aligned channels.
- */
-struct smd_channel_info_word {
-	__le32 state;
-	__le32 fDSR;
-	__le32 fCTS;
-	__le32 fCD;
-	__le32 fRI;
-	__le32 fHEAD;
-	__le32 fTAIL;
-	__le32 fSTATE;
-	__le32 fBLOCKREADINTR;
-	__le32 tail;
-	__le32 head;
-};
-
-struct smd_channel_info_word_pair {
-	struct smd_channel_info_word tx;
-	struct smd_channel_info_word rx;
-};
-
-#define GET_RX_CHANNEL_FLAG(channel, param)				     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u8)); \
-		channel->info_word ?					     \
-			le32_to_cpu(channel->info_word->rx.param) :	     \
-			channel->info->rx.param;			     \
-	})
-
-#define GET_RX_CHANNEL_INFO(channel, param)				      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u32)); \
-		le32_to_cpu(channel->info_word ?			      \
-			channel->info_word->rx.param :			      \
-			channel->info->rx.param);			      \
-	})
-
-#define SET_RX_CHANNEL_FLAG(channel, param, value)			     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u8)); \
-		if (channel->info_word)					     \
-			channel->info_word->rx.param = cpu_to_le32(value);   \
-		else							     \
-			channel->info->rx.param = value;		     \
-	})
-
-#define SET_RX_CHANNEL_INFO(channel, param, value)			      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u32)); \
-		if (channel->info_word)					      \
-			channel->info_word->rx.param = cpu_to_le32(value);    \
-		else							      \
-			channel->info->rx.param = cpu_to_le32(value);	      \
-	})
-
-#define GET_TX_CHANNEL_FLAG(channel, param)				     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u8)); \
-		channel->info_word ?					     \
-			le32_to_cpu(channel->info_word->tx.param) :          \
-			channel->info->tx.param;			     \
-	})
-
-#define GET_TX_CHANNEL_INFO(channel, param)				      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u32)); \
-		le32_to_cpu(channel->info_word ?			      \
-			channel->info_word->tx.param :			      \
-			channel->info->tx.param);			      \
-	})
-
-#define SET_TX_CHANNEL_FLAG(channel, param, value)			     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u8)); \
-		if (channel->info_word)					     \
-			channel->info_word->tx.param = cpu_to_le32(value);   \
-		else							     \
-			channel->info->tx.param = value;		     \
-	})
-
-#define SET_TX_CHANNEL_INFO(channel, param, value)			      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u32)); \
-		if (channel->info_word)					      \
-			channel->info_word->tx.param = cpu_to_le32(value);   \
-		else							      \
-			channel->info->tx.param = cpu_to_le32(value);	      \
-	})
-
-/**
- * struct qcom_smd_alloc_entry - channel allocation entry
- * @name:	channel name
- * @cid:	channel index
- * @flags:	channel flags and edge id
- * @ref_count:	reference count of the channel
- */
-struct qcom_smd_alloc_entry {
-	u8 name[20];
-	__le32 cid;
-	__le32 flags;
-	__le32 ref_count;
-} __packed;
-
-#define SMD_CHANNEL_FLAGS_EDGE_MASK	0xff
-#define SMD_CHANNEL_FLAGS_STREAM	BIT(8)
-#define SMD_CHANNEL_FLAGS_PACKET	BIT(9)
-
-/*
- * Each smd packet contains a 20 byte header, with the first 4 being the length
- * of the packet.
- */
-#define SMD_PACKET_HEADER_LEN	20
-
-/*
- * Signal the remote processor associated with 'channel'.
- */
-static void qcom_smd_signal_channel(struct qcom_smd_channel *channel)
-{
-	struct qcom_smd_edge *edge = channel->edge;
-
-	regmap_write(edge->ipc_regmap, edge->ipc_offset, BIT(edge->ipc_bit));
-}
-
-/*
- * Initialize the tx channel info
- */
-static void qcom_smd_channel_reset(struct qcom_smd_channel *channel)
-{
-	SET_TX_CHANNEL_INFO(channel, state, SMD_CHANNEL_CLOSED);
-	SET_TX_CHANNEL_FLAG(channel, fDSR, 0);
-	SET_TX_CHANNEL_FLAG(channel, fCTS, 0);
-	SET_TX_CHANNEL_FLAG(channel, fCD, 0);
-	SET_TX_CHANNEL_FLAG(channel, fRI, 0);
-	SET_TX_CHANNEL_FLAG(channel, fHEAD, 0);
-	SET_TX_CHANNEL_FLAG(channel, fTAIL, 0);
-	SET_TX_CHANNEL_FLAG(channel, fSTATE, 1);
-	SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 1);
-	SET_TX_CHANNEL_INFO(channel, head, 0);
-	SET_RX_CHANNEL_INFO(channel, tail, 0);
-
-	qcom_smd_signal_channel(channel);
-
-	channel->state = SMD_CHANNEL_CLOSED;
-	channel->pkt_size = 0;
-}
-
-/*
- * Set the callback for a channel, with appropriate locking
- */
-static void qcom_smd_channel_set_callback(struct qcom_smd_channel *channel,
-					  qcom_smd_cb_t cb)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&channel->recv_lock, flags);
-	channel->cb = cb;
-	spin_unlock_irqrestore(&channel->recv_lock, flags);
-};
-
-/*
- * Calculate the amount of data available in the rx fifo
- */
-static size_t qcom_smd_channel_get_rx_avail(struct qcom_smd_channel *channel)
-{
-	unsigned head;
-	unsigned tail;
-
-	head = GET_RX_CHANNEL_INFO(channel, head);
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-
-	return (head - tail) & (channel->fifo_size - 1);
-}
-
-/*
- * Set tx channel state and inform the remote processor
- */
-static void qcom_smd_channel_set_state(struct qcom_smd_channel *channel,
-				       int state)
-{
-	struct qcom_smd_edge *edge = channel->edge;
-	bool is_open = state == SMD_CHANNEL_OPENED;
-
-	if (channel->state == state)
-		return;
-
-	dev_dbg(&edge->dev, "set_state(%s, %d)\n", channel->name, state);
-
-	SET_TX_CHANNEL_FLAG(channel, fDSR, is_open);
-	SET_TX_CHANNEL_FLAG(channel, fCTS, is_open);
-	SET_TX_CHANNEL_FLAG(channel, fCD, is_open);
-
-	SET_TX_CHANNEL_INFO(channel, state, state);
-	SET_TX_CHANNEL_FLAG(channel, fSTATE, 1);
-
-	channel->state = state;
-	qcom_smd_signal_channel(channel);
-}
-
-/*
- * Copy count bytes of data using 32bit accesses, if that's required.
- */
-static void smd_copy_to_fifo(void __iomem *dst,
-			     const void *src,
-			     size_t count,
-			     bool word_aligned)
-{
-	if (word_aligned) {
-		__iowrite32_copy(dst, src, count / sizeof(u32));
-	} else {
-		memcpy_toio(dst, src, count);
-	}
-}
-
-/*
- * Copy count bytes of data using 32bit accesses, if that is required.
- */
-static void smd_copy_from_fifo(void *dst,
-			       const void __iomem *src,
-			       size_t count,
-			       bool word_aligned)
-{
-	if (word_aligned) {
-		__ioread32_copy(dst, src, count / sizeof(u32));
-	} else {
-		memcpy_fromio(dst, src, count);
-	}
-}
-
-/*
- * Read count bytes of data from the rx fifo into buf, but don't advance the
- * tail.
- */
-static size_t qcom_smd_channel_peek(struct qcom_smd_channel *channel,
-				    void *buf, size_t count)
-{
-	bool word_aligned;
-	unsigned tail;
-	size_t len;
-
-	word_aligned = channel->info_word;
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-
-	len = min_t(size_t, count, channel->fifo_size - tail);
-	if (len) {
-		smd_copy_from_fifo(buf,
-				   channel->rx_fifo + tail,
-				   len,
-				   word_aligned);
-	}
-
-	if (len != count) {
-		smd_copy_from_fifo(buf + len,
-				   channel->rx_fifo,
-				   count - len,
-				   word_aligned);
-	}
-
-	return count;
-}
-
-/*
- * Advance the rx tail by count bytes.
- */
-static void qcom_smd_channel_advance(struct qcom_smd_channel *channel,
-				     size_t count)
-{
-	unsigned tail;
-
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-	tail += count;
-	tail &= (channel->fifo_size - 1);
-	SET_RX_CHANNEL_INFO(channel, tail, tail);
-}
-
-/*
- * Read out a single packet from the rx fifo and deliver it to the device
- */
-static int qcom_smd_channel_recv_single(struct qcom_smd_channel *channel)
-{
-	unsigned tail;
-	size_t len;
-	void *ptr;
-	int ret;
-
-	if (!channel->cb)
-		return 0;
-
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-
-	/* Use bounce buffer if the data wraps */
-	if (tail + channel->pkt_size >= channel->fifo_size) {
-		ptr = channel->bounce_buffer;
-		len = qcom_smd_channel_peek(channel, ptr, channel->pkt_size);
-	} else {
-		ptr = channel->rx_fifo + tail;
-		len = channel->pkt_size;
-	}
-
-	ret = channel->cb(channel, ptr, len);
-	if (ret < 0)
-		return ret;
-
-	/* Only forward the tail if the client consumed the data */
-	qcom_smd_channel_advance(channel, len);
-
-	channel->pkt_size = 0;
-
-	return 0;
-}
-
-/*
- * Per channel interrupt handling
- */
-static bool qcom_smd_channel_intr(struct qcom_smd_channel *channel)
-{
-	bool need_state_scan = false;
-	int remote_state;
-	__le32 pktlen;
-	int avail;
-	int ret;
-
-	/* Handle state changes */
-	remote_state = GET_RX_CHANNEL_INFO(channel, state);
-	if (remote_state != channel->remote_state) {
-		channel->remote_state = remote_state;
-		need_state_scan = true;
-	}
-	/* Indicate that we have seen any state change */
-	SET_RX_CHANNEL_FLAG(channel, fSTATE, 0);
-
-	/* Signal waiting qcom_smd_send() about the interrupt */
-	if (!GET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR))
-		wake_up_interruptible(&channel->fblockread_event);
-
-	/* Don't consume any data until we've opened the channel */
-	if (channel->state != SMD_CHANNEL_OPENED)
-		goto out;
-
-	/* Indicate that we've seen the new data */
-	SET_RX_CHANNEL_FLAG(channel, fHEAD, 0);
-
-	/* Consume data */
-	for (;;) {
-		avail = qcom_smd_channel_get_rx_avail(channel);
-
-		if (!channel->pkt_size && avail >= SMD_PACKET_HEADER_LEN) {
-			qcom_smd_channel_peek(channel, &pktlen, sizeof(pktlen));
-			qcom_smd_channel_advance(channel, SMD_PACKET_HEADER_LEN);
-			channel->pkt_size = le32_to_cpu(pktlen);
-		} else if (channel->pkt_size && avail >= channel->pkt_size) {
-			ret = qcom_smd_channel_recv_single(channel);
-			if (ret)
-				break;
-		} else {
-			break;
-		}
-	}
-
-	/* Indicate that we have seen and updated tail */
-	SET_RX_CHANNEL_FLAG(channel, fTAIL, 1);
-
-	/* Signal the remote that we've consumed the data (if requested) */
-	if (!GET_RX_CHANNEL_FLAG(channel, fBLOCKREADINTR)) {
-		/* Ensure ordering of channel info updates */
-		wmb();
-
-		qcom_smd_signal_channel(channel);
-	}
-
-out:
-	return need_state_scan;
-}
-
-/*
- * The edge interrupts are triggered by the remote processor on state changes,
- * channel info updates or when new channels are created.
- */
-static irqreturn_t qcom_smd_edge_intr(int irq, void *data)
-{
-	struct qcom_smd_edge *edge = data;
-	struct qcom_smd_channel *channel;
-	unsigned available;
-	bool kick_scanner = false;
-	bool kick_state = false;
-
-	/*
-	 * Handle state changes or data on each of the channels on this edge
-	 */
-	spin_lock(&edge->channels_lock);
-	list_for_each_entry(channel, &edge->channels, list) {
-		spin_lock(&channel->recv_lock);
-		kick_state |= qcom_smd_channel_intr(channel);
-		spin_unlock(&channel->recv_lock);
-	}
-	spin_unlock(&edge->channels_lock);
-
-	/*
-	 * Creating a new channel requires allocating an smem entry, so we only
-	 * have to scan if the amount of available space in smem have changed
-	 * since last scan.
-	 */
-	available = qcom_smem_get_free_space(edge->remote_pid);
-	if (available != edge->smem_available) {
-		edge->smem_available = available;
-		kick_scanner = true;
-	}
-
-	if (kick_scanner)
-		schedule_work(&edge->scan_work);
-	if (kick_state)
-		schedule_work(&edge->state_work);
-
-	return IRQ_HANDLED;
-}
-
-/*
- * Delivers any outstanding packets in the rx fifo, can be used after probe of
- * the clients to deliver any packets that wasn't delivered before the client
- * was setup.
- */
-static void qcom_smd_channel_resume(struct qcom_smd_channel *channel)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&channel->recv_lock, flags);
-	qcom_smd_channel_intr(channel);
-	spin_unlock_irqrestore(&channel->recv_lock, flags);
-}
-
-/*
- * Calculate how much space is available in the tx fifo.
- */
-static size_t qcom_smd_get_tx_avail(struct qcom_smd_channel *channel)
-{
-	unsigned head;
-	unsigned tail;
-	unsigned mask = channel->fifo_size - 1;
-
-	head = GET_TX_CHANNEL_INFO(channel, head);
-	tail = GET_TX_CHANNEL_INFO(channel, tail);
-
-	return mask - ((head - tail) & mask);
-}
-
-/*
- * Write count bytes of data into channel, possibly wrapping in the ring buffer
- */
-static int qcom_smd_write_fifo(struct qcom_smd_channel *channel,
-			       const void *data,
-			       size_t count)
-{
-	bool word_aligned;
-	unsigned head;
-	size_t len;
-
-	word_aligned = channel->info_word;
-	head = GET_TX_CHANNEL_INFO(channel, head);
-
-	len = min_t(size_t, count, channel->fifo_size - head);
-	if (len) {
-		smd_copy_to_fifo(channel->tx_fifo + head,
-				 data,
-				 len,
-				 word_aligned);
-	}
-
-	if (len != count) {
-		smd_copy_to_fifo(channel->tx_fifo,
-				 data + len,
-				 count - len,
-				 word_aligned);
-	}
-
-	head += count;
-	head &= (channel->fifo_size - 1);
-	SET_TX_CHANNEL_INFO(channel, head, head);
-
-	return count;
-}
-
-/**
- * qcom_smd_send - write data to smd channel
- * @channel:	channel handle
- * @data:	buffer of data to write
- * @len:	number of bytes to write
- *
- * This is a blocking write of len bytes into the channel's tx ring buffer and
- * signal the remote end. It will sleep until there is enough space available
- * in the tx buffer, utilizing the fBLOCKREADINTR signaling mechanism to avoid
- * polling.
- */
-int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len)
-{
-	__le32 hdr[5] = { cpu_to_le32(len), };
-	int tlen = sizeof(hdr) + len;
-	int ret;
-
-	/* Word aligned channels only accept word size aligned data */
-	if (channel->info_word && len % 4)
-		return -EINVAL;
-
-	/* Reject packets that are too big */
-	if (tlen >= channel->fifo_size)
-		return -EINVAL;
-
-	ret = mutex_lock_interruptible(&channel->tx_lock);
-	if (ret)
-		return ret;
-
-	while (qcom_smd_get_tx_avail(channel) < tlen) {
-		if (channel->state != SMD_CHANNEL_OPENED) {
-			ret = -EPIPE;
-			goto out;
-		}
-
-		SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 0);
-
-		ret = wait_event_interruptible(channel->fblockread_event,
-				       qcom_smd_get_tx_avail(channel) >= tlen ||
-				       channel->state != SMD_CHANNEL_OPENED);
-		if (ret)
-			goto out;
-
-		SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 1);
-	}
-
-	SET_TX_CHANNEL_FLAG(channel, fTAIL, 0);
-
-	qcom_smd_write_fifo(channel, hdr, sizeof(hdr));
-	qcom_smd_write_fifo(channel, data, len);
-
-	SET_TX_CHANNEL_FLAG(channel, fHEAD, 1);
-
-	/* Ensure ordering of channel info updates */
-	wmb();
-
-	qcom_smd_signal_channel(channel);
-
-out:
-	mutex_unlock(&channel->tx_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL(qcom_smd_send);
-
-static struct qcom_smd_device *to_smd_device(struct device *dev)
-{
-	return container_of(dev, struct qcom_smd_device, dev);
-}
-
-static struct qcom_smd_driver *to_smd_driver(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-
-	return container_of(qsdev->dev.driver, struct qcom_smd_driver, driver);
-}
-
-static int qcom_smd_dev_match(struct device *dev, struct device_driver *drv)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-	struct qcom_smd_driver *qsdrv = container_of(drv, struct qcom_smd_driver, driver);
-	const struct qcom_smd_id *match = qsdrv->smd_match_table;
-	const char *name = qsdev->channel->name;
-
-	if (match) {
-		while (match->name[0]) {
-			if (!strcmp(match->name, name))
-				return 1;
-			match++;
-		}
-	}
-
-	return of_driver_match_device(dev, drv);
-}
-
-/*
- * Helper for opening a channel
- */
-static int qcom_smd_channel_open(struct qcom_smd_channel *channel,
-				 qcom_smd_cb_t cb)
-{
-	size_t bb_size;
-
-	/*
-	 * Packets are maximum 4k, but reduce if the fifo is smaller
-	 */
-	bb_size = min(channel->fifo_size, SZ_4K);
-	channel->bounce_buffer = kmalloc(bb_size, GFP_KERNEL);
-	if (!channel->bounce_buffer)
-		return -ENOMEM;
-
-	qcom_smd_channel_set_callback(channel, cb);
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_OPENING);
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_OPENED);
-
-	return 0;
-}
-
-/*
- * Helper for closing and resetting a channel
- */
-static void qcom_smd_channel_close(struct qcom_smd_channel *channel)
-{
-	qcom_smd_channel_set_callback(channel, NULL);
-
-	kfree(channel->bounce_buffer);
-	channel->bounce_buffer = NULL;
-
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_CLOSED);
-	qcom_smd_channel_reset(channel);
-}
-
-/*
- * Probe the smd client.
- *
- * The remote side have indicated that it want the channel to be opened, so
- * complete the state handshake and probe our client driver.
- */
-static int qcom_smd_dev_probe(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-	struct qcom_smd_driver *qsdrv = to_smd_driver(dev);
-	struct qcom_smd_channel *channel = qsdev->channel;
-	int ret;
-
-	ret = qcom_smd_channel_open(channel, qsdrv->callback);
-	if (ret)
-		return ret;
-
-	ret = qsdrv->probe(qsdev);
-	if (ret)
-		goto err;
-
-	qcom_smd_channel_resume(channel);
-
-	return 0;
-
-err:
-	dev_err(&qsdev->dev, "probe failed\n");
-
-	qcom_smd_channel_close(channel);
-	return ret;
-}
-
-/*
- * Remove the smd client.
- *
- * The channel is going away, for some reason, so remove the smd client and
- * reset the channel state.
- */
-static int qcom_smd_dev_remove(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-	struct qcom_smd_driver *qsdrv = to_smd_driver(dev);
-	struct qcom_smd_channel *channel = qsdev->channel;
-
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_CLOSING);
-
-	/*
-	 * Make sure we don't race with the code receiving data.
-	 */
-	qcom_smd_channel_set_callback(channel, NULL);
-
-	/* Wake up any sleepers in qcom_smd_send() */
-	wake_up_interruptible(&channel->fblockread_event);
-
-	/*
-	 * We expect that the client might block in remove() waiting for any
-	 * outstanding calls to qcom_smd_send() to wake up and finish.
-	 */
-	if (qsdrv->remove)
-		qsdrv->remove(qsdev);
-
-	/* The client is now gone, close the primary channel */
-	qcom_smd_channel_close(channel);
-	channel->qsdev = NULL;
-
-	return 0;
-}
-
-static struct bus_type qcom_smd_bus = {
-	.name = "qcom_smd",
-	.match = qcom_smd_dev_match,
-	.probe = qcom_smd_dev_probe,
-	.remove = qcom_smd_dev_remove,
-};
-
-/*
- * Release function for the qcom_smd_device object.
- */
-static void qcom_smd_release_device(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-
-	kfree(qsdev);
-}
-
-/*
- * Finds the device_node for the smd child interested in this channel.
- */
-static struct device_node *qcom_smd_match_channel(struct device_node *edge_node,
-						  const char *channel)
-{
-	struct device_node *child;
-	const char *name;
-	const char *key;
-	int ret;
-
-	for_each_available_child_of_node(edge_node, child) {
-		key = "qcom,smd-channels";
-		ret = of_property_read_string(child, key, &name);
-		if (ret)
-			continue;
-
-		if (strcmp(name, channel) == 0)
-			return child;
-	}
-
-	return NULL;
-}
-
-/*
- * Create a smd client device for channel that is being opened.
- */
-static int qcom_smd_create_device(struct qcom_smd_channel *channel)
-{
-	struct qcom_smd_device *qsdev;
-	struct qcom_smd_edge *edge = channel->edge;
-	struct device_node *node;
-	int ret;
-
-	if (channel->qsdev)
-		return -EEXIST;
-
-	dev_dbg(&edge->dev, "registering '%s'\n", channel->name);
-
-	qsdev = kzalloc(sizeof(*qsdev), GFP_KERNEL);
-	if (!qsdev)
-		return -ENOMEM;
-
-	node = qcom_smd_match_channel(edge->of_node, channel->name);
-	dev_set_name(&qsdev->dev, "%s.%s",
-		     edge->of_node->name,
-		     node ? node->name : channel->name);
-
-	qsdev->dev.parent = &edge->dev;
-	qsdev->dev.bus = &qcom_smd_bus;
-	qsdev->dev.release = qcom_smd_release_device;
-	qsdev->dev.of_node = node;
-
-	qsdev->channel = channel;
-
-	channel->qsdev = qsdev;
-
-	ret = device_register(&qsdev->dev);
-	if (ret) {
-		dev_err(&edge->dev, "device_register failed: %d\n", ret);
-		put_device(&qsdev->dev);
-	}
-
-	return ret;
-}
-
-/*
- * Destroy a smd client device for a channel that's going away.
- */
-static void qcom_smd_destroy_device(struct qcom_smd_channel *channel)
-{
-	struct device *dev;
-
-	BUG_ON(!channel->qsdev);
-
-	dev = &channel->qsdev->dev;
-
-	device_unregister(dev);
-	of_node_put(dev->of_node);
-	put_device(dev);
-}
-
-/**
- * qcom_smd_driver_register - register a smd driver
- * @qsdrv:	qcom_smd_driver struct
- */
-int qcom_smd_driver_register(struct qcom_smd_driver *qsdrv)
-{
-	qsdrv->driver.bus = &qcom_smd_bus;
-	return driver_register(&qsdrv->driver);
-}
-EXPORT_SYMBOL(qcom_smd_driver_register);
-
-void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel)
-{
-	return channel->drvdata;
-}
-EXPORT_SYMBOL(qcom_smd_get_drvdata);
-
-void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data)
-{
-	channel->drvdata = data;
-}
-EXPORT_SYMBOL(qcom_smd_set_drvdata);
-
-/**
- * qcom_smd_driver_unregister - unregister a smd driver
- * @qsdrv:	qcom_smd_driver struct
- */
-void qcom_smd_driver_unregister(struct qcom_smd_driver *qsdrv)
-{
-	driver_unregister(&qsdrv->driver);
-}
-EXPORT_SYMBOL(qcom_smd_driver_unregister);
-
-static struct qcom_smd_channel *
-qcom_smd_find_channel(struct qcom_smd_edge *edge, const char *name)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_channel *ret = NULL;
-	unsigned long flags;
-	unsigned state;
-
-	spin_lock_irqsave(&edge->channels_lock, flags);
-	list_for_each_entry(channel, &edge->channels, list) {
-		if (strcmp(channel->name, name))
-			continue;
-
-		state = GET_RX_CHANNEL_INFO(channel, state);
-		if (state != SMD_CHANNEL_OPENING &&
-		    state != SMD_CHANNEL_OPENED)
-			continue;
-
-		ret = channel;
-		break;
-	}
-	spin_unlock_irqrestore(&edge->channels_lock, flags);
-
-	return ret;
-}
-
-/**
- * qcom_smd_open_channel() - claim additional channels on the same edge
- * @sdev:	smd_device handle
- * @name:	channel name
- * @cb:		callback method to use for incoming data
- *
- * Returns a channel handle on success, or -EPROBE_DEFER if the channel isn't
- * ready.
- *
- * Any channels returned must be closed with a call to qcom_smd_close_channel()
- */
-struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *parent,
-					       const char *name,
-					       qcom_smd_cb_t cb)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_device *sdev = parent->qsdev;
-	struct qcom_smd_edge *edge = parent->edge;
-	int ret;
-
-	/* Wait up to HZ for the channel to appear */
-	ret = wait_event_interruptible_timeout(edge->new_channel_event,
-			(channel = qcom_smd_find_channel(edge, name)) != NULL,
-			HZ);
-	if (!ret)
-		return ERR_PTR(-ETIMEDOUT);
-
-	if (channel->state != SMD_CHANNEL_CLOSED) {
-		dev_err(&sdev->dev, "channel %s is busy\n", channel->name);
-		return ERR_PTR(-EBUSY);
-	}
-
-	channel->qsdev = sdev;
-	ret = qcom_smd_channel_open(channel, cb);
-	if (ret) {
-		channel->qsdev = NULL;
-		return ERR_PTR(ret);
-	}
-
-	return channel;
-}
-EXPORT_SYMBOL(qcom_smd_open_channel);
-
-/**
- * qcom_smd_close_channel() - close an additionally opened channel
- * @channel:	channel handle, returned by qcom_smd_open_channel()
- */
-void qcom_smd_close_channel(struct qcom_smd_channel *channel)
-{
-	qcom_smd_channel_close(channel);
-	channel->qsdev = NULL;
-}
-EXPORT_SYMBOL(qcom_smd_close_channel);
-
-/*
- * Allocate the qcom_smd_channel object for a newly found smd channel,
- * retrieving and validating the smem items involved.
- */
-static struct qcom_smd_channel *qcom_smd_create_channel(struct qcom_smd_edge *edge,
-							unsigned smem_info_item,
-							unsigned smem_fifo_item,
-							char *name)
-{
-	struct qcom_smd_channel *channel;
-	size_t fifo_size;
-	size_t info_size;
-	void *fifo_base;
-	void *info;
-	int ret;
-
-	channel = devm_kzalloc(&edge->dev, sizeof(*channel), GFP_KERNEL);
-	if (!channel)
-		return ERR_PTR(-ENOMEM);
-
-	channel->edge = edge;
-	channel->name = devm_kstrdup(&edge->dev, name, GFP_KERNEL);
-	if (!channel->name)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&channel->tx_lock);
-	spin_lock_init(&channel->recv_lock);
-	init_waitqueue_head(&channel->fblockread_event);
-
-	info = qcom_smem_get(edge->remote_pid, smem_info_item, &info_size);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto free_name_and_channel;
-	}
-
-	/*
-	 * Use the size of the item to figure out which channel info struct to
-	 * use.
-	 */
-	if (info_size == 2 * sizeof(struct smd_channel_info_word)) {
-		channel->info_word = info;
-	} else if (info_size == 2 * sizeof(struct smd_channel_info)) {
-		channel->info = info;
-	} else {
-		dev_err(&edge->dev,
-			"channel info of size %zu not supported\n", info_size);
-		ret = -EINVAL;
-		goto free_name_and_channel;
-	}
-
-	fifo_base = qcom_smem_get(edge->remote_pid, smem_fifo_item, &fifo_size);
-	if (IS_ERR(fifo_base)) {
-		ret =  PTR_ERR(fifo_base);
-		goto free_name_and_channel;
-	}
-
-	/* The channel consist of a rx and tx fifo of equal size */
-	fifo_size /= 2;
-
-	dev_dbg(&edge->dev, "new channel '%s' info-size: %zu fifo-size: %zu\n",
-			  name, info_size, fifo_size);
-
-	channel->tx_fifo = fifo_base;
-	channel->rx_fifo = fifo_base + fifo_size;
-	channel->fifo_size = fifo_size;
-
-	qcom_smd_channel_reset(channel);
-
-	return channel;
-
-free_name_and_channel:
-	devm_kfree(&edge->dev, channel->name);
-	devm_kfree(&edge->dev, channel);
-
-	return ERR_PTR(ret);
-}
-
-/*
- * Scans the allocation table for any newly allocated channels, calls
- * qcom_smd_create_channel() to create representations of these and add
- * them to the edge's list of channels.
- */
-static void qcom_channel_scan_worker(struct work_struct *work)
-{
-	struct qcom_smd_edge *edge = container_of(work, struct qcom_smd_edge, scan_work);
-	struct qcom_smd_alloc_entry *alloc_tbl;
-	struct qcom_smd_alloc_entry *entry;
-	struct qcom_smd_channel *channel;
-	unsigned long flags;
-	unsigned fifo_id;
-	unsigned info_id;
-	int tbl;
-	int i;
-	u32 eflags, cid;
-
-	for (tbl = 0; tbl < SMD_ALLOC_TBL_COUNT; tbl++) {
-		alloc_tbl = qcom_smem_get(edge->remote_pid,
-				    smem_items[tbl].alloc_tbl_id, NULL);
-		if (IS_ERR(alloc_tbl))
-			continue;
-
-		for (i = 0; i < SMD_ALLOC_TBL_SIZE; i++) {
-			entry = &alloc_tbl[i];
-			eflags = le32_to_cpu(entry->flags);
-			if (test_bit(i, edge->allocated[tbl]))
-				continue;
-
-			if (entry->ref_count == 0)
-				continue;
-
-			if (!entry->name[0])
-				continue;
-
-			if (!(eflags & SMD_CHANNEL_FLAGS_PACKET))
-				continue;
-
-			if ((eflags & SMD_CHANNEL_FLAGS_EDGE_MASK) != edge->edge_id)
-				continue;
-
-			cid = le32_to_cpu(entry->cid);
-			info_id = smem_items[tbl].info_base_id + cid;
-			fifo_id = smem_items[tbl].fifo_base_id + cid;
-
-			channel = qcom_smd_create_channel(edge, info_id, fifo_id, entry->name);
-			if (IS_ERR(channel))
-				continue;
-
-			spin_lock_irqsave(&edge->channels_lock, flags);
-			list_add(&channel->list, &edge->channels);
-			spin_unlock_irqrestore(&edge->channels_lock, flags);
-
-			dev_dbg(&edge->dev, "new channel found: '%s'\n", channel->name);
-			set_bit(i, edge->allocated[tbl]);
-
-			wake_up_interruptible(&edge->new_channel_event);
-		}
-	}
-
-	schedule_work(&edge->state_work);
-}
-
-/*
- * This per edge worker scans smem for any new channels and register these. It
- * then scans all registered channels for state changes that should be handled
- * by creating or destroying smd client devices for the registered channels.
- *
- * LOCKING: edge->channels_lock only needs to cover the list operations, as the
- * worker is killed before any channels are deallocated
- */
-static void qcom_channel_state_worker(struct work_struct *work)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_edge *edge = container_of(work,
-						  struct qcom_smd_edge,
-						  state_work);
-	unsigned remote_state;
-	unsigned long flags;
-
-	/*
-	 * Register a device for any closed channel where the remote processor
-	 * is showing interest in opening the channel.
-	 */
-	spin_lock_irqsave(&edge->channels_lock, flags);
-	list_for_each_entry(channel, &edge->channels, list) {
-		if (channel->state != SMD_CHANNEL_CLOSED)
-			continue;
-
-		remote_state = GET_RX_CHANNEL_INFO(channel, state);
-		if (remote_state != SMD_CHANNEL_OPENING &&
-		    remote_state != SMD_CHANNEL_OPENED)
-			continue;
-
-		spin_unlock_irqrestore(&edge->channels_lock, flags);
-		qcom_smd_create_device(channel);
-		spin_lock_irqsave(&edge->channels_lock, flags);
-	}
-
-	/*
-	 * Unregister the device for any channel that is opened where the
-	 * remote processor is closing the channel.
-	 */
-	list_for_each_entry(channel, &edge->channels, list) {
-		if (channel->state != SMD_CHANNEL_OPENING &&
-		    channel->state != SMD_CHANNEL_OPENED)
-			continue;
-
-		remote_state = GET_RX_CHANNEL_INFO(channel, state);
-		if (remote_state == SMD_CHANNEL_OPENING ||
-		    remote_state == SMD_CHANNEL_OPENED)
-			continue;
-
-		spin_unlock_irqrestore(&edge->channels_lock, flags);
-		qcom_smd_destroy_device(channel);
-		spin_lock_irqsave(&edge->channels_lock, flags);
-	}
-	spin_unlock_irqrestore(&edge->channels_lock, flags);
-}
-
-/*
- * Parses an of_node describing an edge.
- */
-static int qcom_smd_parse_edge(struct device *dev,
-			       struct device_node *node,
-			       struct qcom_smd_edge *edge)
-{
-	struct device_node *syscon_np;
-	const char *key;
-	int irq;
-	int ret;
-
-	INIT_LIST_HEAD(&edge->channels);
-	spin_lock_init(&edge->channels_lock);
-
-	INIT_WORK(&edge->scan_work, qcom_channel_scan_worker);
-	INIT_WORK(&edge->state_work, qcom_channel_state_worker);
-
-	edge->of_node = of_node_get(node);
-
-	key = "qcom,smd-edge";
-	ret = of_property_read_u32(node, key, &edge->edge_id);
-	if (ret) {
-		dev_err(dev, "edge missing %s property\n", key);
-		return -EINVAL;
-	}
-
-	edge->remote_pid = QCOM_SMEM_HOST_ANY;
-	key = "qcom,remote-pid";
-	of_property_read_u32(node, key, &edge->remote_pid);
-
-	syscon_np = of_parse_phandle(node, "qcom,ipc", 0);
-	if (!syscon_np) {
-		dev_err(dev, "no qcom,ipc node\n");
-		return -ENODEV;
-	}
-
-	edge->ipc_regmap = syscon_node_to_regmap(syscon_np);
-	if (IS_ERR(edge->ipc_regmap))
-		return PTR_ERR(edge->ipc_regmap);
-
-	key = "qcom,ipc";
-	ret = of_property_read_u32_index(node, key, 1, &edge->ipc_offset);
-	if (ret < 0) {
-		dev_err(dev, "no offset in %s\n", key);
-		return -EINVAL;
-	}
-
-	ret = of_property_read_u32_index(node, key, 2, &edge->ipc_bit);
-	if (ret < 0) {
-		dev_err(dev, "no bit in %s\n", key);
-		return -EINVAL;
-	}
-
-	irq = irq_of_parse_and_map(node, 0);
-	if (irq < 0) {
-		dev_err(dev, "required smd interrupt missing\n");
-		return -EINVAL;
-	}
-
-	ret = devm_request_irq(dev, irq,
-			       qcom_smd_edge_intr, IRQF_TRIGGER_RISING,
-			       node->name, edge);
-	if (ret) {
-		dev_err(dev, "failed to request smd irq\n");
-		return ret;
-	}
-
-	edge->irq = irq;
-
-	return 0;
-}
-
-/*
- * Release function for an edge.
- * Reset the state of each associated channel and free the edge context.
- */
-static void qcom_smd_edge_release(struct device *dev)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_edge *edge = to_smd_edge(dev);
-
-	list_for_each_entry(channel, &edge->channels, list) {
-		SET_RX_CHANNEL_INFO(channel, state, SMD_CHANNEL_CLOSED);
-		SET_RX_CHANNEL_INFO(channel, head, 0);
-		SET_RX_CHANNEL_INFO(channel, tail, 0);
-	}
-
-	kfree(edge);
-}
-
-/**
- * qcom_smd_register_edge() - register an edge based on an device_node
- * @parent:	parent device for the edge
- * @node:	device_node describing the edge
- *
- * Returns an edge reference, or negative ERR_PTR() on failure.
- */
-struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
-					     struct device_node *node)
-{
-	struct qcom_smd_edge *edge;
-	int ret;
-
-	edge = kzalloc(sizeof(*edge), GFP_KERNEL);
-	if (!edge)
-		return ERR_PTR(-ENOMEM);
-
-	init_waitqueue_head(&edge->new_channel_event);
-
-	edge->dev.parent = parent;
-	edge->dev.release = qcom_smd_edge_release;
-	dev_set_name(&edge->dev, "%s:%s", dev_name(parent), node->name);
-	ret = device_register(&edge->dev);
-	if (ret) {
-		pr_err("failed to register smd edge\n");
-		return ERR_PTR(ret);
-	}
-
-	ret = qcom_smd_parse_edge(&edge->dev, node, edge);
-	if (ret) {
-		dev_err(&edge->dev, "failed to parse smd edge\n");
-		goto unregister_dev;
-	}
-
-	schedule_work(&edge->scan_work);
-
-	return edge;
-
-unregister_dev:
-	put_device(&edge->dev);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL(qcom_smd_register_edge);
-
-static int qcom_smd_remove_device(struct device *dev, void *data)
-{
-	device_unregister(dev);
-	of_node_put(dev->of_node);
-	put_device(dev);
-
-	return 0;
-}
-
-/**
- * qcom_smd_unregister_edge() - release an edge and its children
- * @edge:	edge reference acquired from qcom_smd_register_edge
- */
-int qcom_smd_unregister_edge(struct qcom_smd_edge *edge)
-{
-	int ret;
-
-	disable_irq(edge->irq);
-	cancel_work_sync(&edge->scan_work);
-	cancel_work_sync(&edge->state_work);
-
-	ret = device_for_each_child(&edge->dev, NULL, qcom_smd_remove_device);
-	if (ret)
-		dev_warn(&edge->dev, "can't remove smd device: %d\n", ret);
-
-	device_unregister(&edge->dev);
-
-	return 0;
-}
-EXPORT_SYMBOL(qcom_smd_unregister_edge);
-
-static int qcom_smd_probe(struct platform_device *pdev)
-{
-	struct device_node *node;
-	void *p;
-
-	/* Wait for smem */
-	p = qcom_smem_get(QCOM_SMEM_HOST_ANY, smem_items[0].alloc_tbl_id, NULL);
-	if (PTR_ERR(p) == -EPROBE_DEFER)
-		return PTR_ERR(p);
-
-	for_each_available_child_of_node(pdev->dev.of_node, node)
-		qcom_smd_register_edge(&pdev->dev, node);
-
-	return 0;
-}
-
-static int qcom_smd_remove_edge(struct device *dev, void *data)
-{
-	struct qcom_smd_edge *edge = to_smd_edge(dev);
-
-	return qcom_smd_unregister_edge(edge);
-}
-
-/*
- * Shut down all smd clients by making sure that each edge stops processing
- * events and scanning for new channels, then call destroy on the devices.
- */
-static int qcom_smd_remove(struct platform_device *pdev)
-{
-	int ret;
-
-	ret = device_for_each_child(&pdev->dev, NULL, qcom_smd_remove_edge);
-	if (ret)
-		dev_warn(&pdev->dev, "can't remove smd device: %d\n", ret);
-
-	return ret;
-}
-
-static const struct of_device_id qcom_smd_of_match[] = {
-	{ .compatible = "qcom,smd" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, qcom_smd_of_match);
-
-static struct platform_driver qcom_smd_driver = {
-	.probe = qcom_smd_probe,
-	.remove = qcom_smd_remove,
-	.driver = {
-		.name = "qcom-smd",
-		.of_match_table = qcom_smd_of_match,
-	},
-};
-
-static int __init qcom_smd_init(void)
-{
-	int ret;
-
-	ret = bus_register(&qcom_smd_bus);
-	if (ret) {
-		pr_err("failed to register smd bus: %d\n", ret);
-		return ret;
-	}
-
-	return platform_driver_register(&qcom_smd_driver);
-}
-postcore_initcall(qcom_smd_init);
-
-static void __exit qcom_smd_exit(void)
-{
-	platform_driver_unregister(&qcom_smd_driver);
-	bus_unregister(&qcom_smd_bus);
-}
-module_exit(qcom_smd_exit);
-
-MODULE_AUTHOR("Bjorn Andersson <bjorn.andersson@sonymobile.com>");
-MODULE_DESCRIPTION("Qualcomm Shared Memory Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/wcnss_ctrl.c b/drivers/soc/qcom/wcnss_ctrl.c
index 520aedd29965..b9069184df19 100644
--- a/drivers/soc/qcom/wcnss_ctrl.c
+++ b/drivers/soc/qcom/wcnss_ctrl.c
@@ -14,10 +14,10 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
 #include <linux/io.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
 
 #define WCNSS_REQUEST_TIMEOUT	(5 * HZ)
@@ -40,7 +40,7 @@
  */
 struct wcnss_ctrl {
 	struct device *dev;
-	struct qcom_smd_channel *channel;
+	struct rpmsg_endpoint *channel;
 
 	struct completion ack;
 	struct completion cbc;
@@ -122,11 +122,13 @@ struct wcnss_download_nv_resp {
  *
  * Handles any incoming packets from the remote WCNSS_CTRL service.
  */
-static int wcnss_ctrl_smd_callback(struct qcom_smd_channel *channel,
-				   const void *data,
-				   size_t count)
+static int wcnss_ctrl_smd_callback(struct rpmsg_device *rpdev,
+				   void *data,
+				   int count,
+				   void *priv,
+				   u32 addr)
 {
-	struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(channel);
+	struct wcnss_ctrl *wcnss = dev_get_drvdata(&rpdev->dev);
 	const struct wcnss_download_nv_resp *nvresp;
 	const struct wcnss_version_resp *version;
 	const struct wcnss_msg_hdr *hdr = data;
@@ -180,7 +182,7 @@ static int wcnss_request_version(struct wcnss_ctrl *wcnss)
 
 	msg.type = WCNSS_VERSION_REQ;
 	msg.len = sizeof(msg);
-	ret = qcom_smd_send(wcnss->channel, &msg, sizeof(msg));
+	ret = rpmsg_send(wcnss->channel, &msg, sizeof(msg));
 	if (ret < 0)
 		return ret;
 
@@ -238,7 +240,7 @@ static int wcnss_download_nv(struct wcnss_ctrl *wcnss, bool *expect_cbc)
 
 		memcpy(req->fragment, data, req->frag_size);
 
-		ret = qcom_smd_send(wcnss->channel, req, req->hdr.len);
+		ret = rpmsg_send(wcnss->channel, req, req->hdr.len);
 		if (ret < 0) {
 			dev_err(wcnss->dev, "failed to send smd packet\n");
 			goto release_fw;
@@ -274,11 +276,16 @@ free_req:
  * @name:	SMD channel name
  * @cb:		callback to handle incoming data on the channel
  */
-struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name, rpmsg_rx_cb_t cb, void *priv)
 {
+	struct rpmsg_channel_info chinfo;
 	struct wcnss_ctrl *_wcnss = wcnss;
 
-	return qcom_smd_open_channel(_wcnss->channel, name, cb);
+	strncpy(chinfo.name, name, sizeof(chinfo.name));
+	chinfo.src = RPMSG_ADDR_ANY;
+	chinfo.dst = RPMSG_ADDR_ANY;
+
+	return rpmsg_create_ept(_wcnss->channel->rpdev, cb, priv, chinfo);
 }
 EXPORT_SYMBOL(qcom_wcnss_open_channel);
 
@@ -306,35 +313,34 @@ static void wcnss_async_probe(struct work_struct *work)
 	of_platform_populate(wcnss->dev->of_node, NULL, NULL, wcnss->dev);
 }
 
-static int wcnss_ctrl_probe(struct qcom_smd_device *sdev)
+static int wcnss_ctrl_probe(struct rpmsg_device *rpdev)
 {
 	struct wcnss_ctrl *wcnss;
 
-	wcnss = devm_kzalloc(&sdev->dev, sizeof(*wcnss), GFP_KERNEL);
+	wcnss = devm_kzalloc(&rpdev->dev, sizeof(*wcnss), GFP_KERNEL);
 	if (!wcnss)
 		return -ENOMEM;
 
-	wcnss->dev = &sdev->dev;
-	wcnss->channel = sdev->channel;
+	wcnss->dev = &rpdev->dev;
+	wcnss->channel = rpdev->ept;
 
 	init_completion(&wcnss->ack);
 	init_completion(&wcnss->cbc);
 	INIT_WORK(&wcnss->probe_work, wcnss_async_probe);
 
-	qcom_smd_set_drvdata(sdev->channel, wcnss);
-	dev_set_drvdata(&sdev->dev, wcnss);
+	dev_set_drvdata(&rpdev->dev, wcnss);
 
 	schedule_work(&wcnss->probe_work);
 
 	return 0;
 }
 
-static void wcnss_ctrl_remove(struct qcom_smd_device *sdev)
+static void wcnss_ctrl_remove(struct rpmsg_device *rpdev)
 {
-	struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(sdev->channel);
+	struct wcnss_ctrl *wcnss = dev_get_drvdata(&rpdev->dev);
 
 	cancel_work_sync(&wcnss->probe_work);
-	of_platform_depopulate(&sdev->dev);
+	of_platform_depopulate(&rpdev->dev);
 }
 
 static const struct of_device_id wcnss_ctrl_of_match[] = {
@@ -342,18 +348,18 @@ static const struct of_device_id wcnss_ctrl_of_match[] = {
 	{}
 };
 
-static struct qcom_smd_driver wcnss_ctrl_driver = {
+static struct rpmsg_driver wcnss_ctrl_driver = {
 	.probe = wcnss_ctrl_probe,
 	.remove = wcnss_ctrl_remove,
 	.callback = wcnss_ctrl_smd_callback,
-	.driver  = {
+	.drv  = {
 		.name  = "qcom_wcnss_ctrl",
 		.owner = THIS_MODULE,
 		.of_match_table = wcnss_ctrl_of_match,
 	},
 };
 
-module_qcom_smd_driver(wcnss_ctrl_driver);
+module_rpmsg_driver(wcnss_ctrl_driver);
 
 MODULE_DESCRIPTION("Qualcomm WCNSS control driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 7cbad0d45b9c..6ba270e0494d 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -409,6 +409,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 			ret = PTR_ERR(vmfile);
 			goto out;
 		}
+		vmfile->f_mode |= FMODE_LSEEK;
 		asma->file = vmfile;
 	}
 	get_file(asma->file);
diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c
index b7b87ecefcdf..9fca8d225ee0 100644
--- a/drivers/staging/lustre/lnet/lnet/lib-socket.c
+++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c
@@ -532,7 +532,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock)
 
 	newsock->ops = sock->ops;
 
-	rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+	rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
 	if (rc == -EAGAIN) {
 		/* Nothing ready, so wait for activity */
 		init_waitqueue_entry(&wait, current);
@@ -540,7 +540,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock)
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule();
 		remove_wait_queue(sk_sleep(sock->sk), &wait);
-		rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+		rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
 	}
 
 	if (rc)
diff --git a/drivers/staging/lustre/lustre/include/lustre_disk.h b/drivers/staging/lustre/lustre/include/lustre_disk.h
index 8886458748c1..a676bccabd43 100644
--- a/drivers/staging/lustre/lustre/include/lustre_disk.h
+++ b/drivers/staging/lustre/lustre/include/lustre_disk.h
@@ -133,13 +133,9 @@ struct lustre_sb_info {
 	struct obd_export	 *lsi_osd_exp;
 	char			  lsi_osd_type[16];
 	char			  lsi_fstype[16];
-	struct backing_dev_info   lsi_bdi;     /* each client mountpoint needs
-						* own backing_dev_info
-						*/
 };
 
 #define LSI_UMOUNT_FAILOVER	      0x00200000
-#define LSI_BDI_INITIALIZED	      0x00400000
 
 #define     s2lsi(sb)	((struct lustre_sb_info *)((sb)->s_fs_info))
 #define     s2lsi_nocast(sb) ((sb)->s_fs_info)
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index b229cbc7bb33..d483c44aafe5 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -863,15 +863,6 @@ void ll_lli_init(struct ll_inode_info *lli)
 	mutex_init(&lli->lli_layout_mutex);
 }
 
-static inline int ll_bdi_register(struct backing_dev_info *bdi)
-{
-	static atomic_t ll_bdi_num = ATOMIC_INIT(0);
-
-	bdi->name = "lustre";
-	return bdi_register(bdi, NULL, "lustre-%d",
-			    atomic_inc_return(&ll_bdi_num));
-}
-
 int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
 {
 	struct lustre_profile *lprof = NULL;
@@ -881,6 +872,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
 	char  *profilenm = get_profile_name(sb);
 	struct config_llog_instance *cfg;
 	int    err;
+	static atomic_t ll_bdi_num = ATOMIC_INIT(0);
 
 	CDEBUG(D_VFSTRACE, "VFS Op: sb %p\n", sb);
 
@@ -903,16 +895,11 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
 	if (err)
 		goto out_free;
 
-	err = bdi_init(&lsi->lsi_bdi);
-	if (err)
-		goto out_free;
-	lsi->lsi_flags |= LSI_BDI_INITIALIZED;
-	lsi->lsi_bdi.capabilities = 0;
-	err = ll_bdi_register(&lsi->lsi_bdi);
+	err = super_setup_bdi_name(sb, "lustre-%d",
+				   atomic_inc_return(&ll_bdi_num));
 	if (err)
 		goto out_free;
 
-	sb->s_bdi = &lsi->lsi_bdi;
 	/* kernel >= 2.6.38 store dentry operations in sb->s_d_op. */
 	sb->s_d_op = &ll_d_ops;
 
@@ -1033,11 +1020,6 @@ void ll_put_super(struct super_block *sb)
 	if (profilenm)
 		class_del_profile(profilenm);
 
-	if (lsi->lsi_flags & LSI_BDI_INITIALIZED) {
-		bdi_destroy(&lsi->lsi_bdi);
-		lsi->lsi_flags &= ~LSI_BDI_INITIALIZED;
-	}
-
 	ll_free_sbi(sb);
 	lsi->lsi_llsbi = NULL;
 
diff --git a/drivers/staging/most/hdm-usb/hdm_usb.c b/drivers/staging/most/hdm-usb/hdm_usb.c
index 65211d1824b7..2bfea9b48366 100644
--- a/drivers/staging/most/hdm-usb/hdm_usb.c
+++ b/drivers/staging/most/hdm-usb/hdm_usb.c
@@ -490,7 +490,7 @@ static void hdm_write_completion(struct urb *urb)
  * disconnect.  In the interval before the hub driver starts disconnect
  * processing, devices may receive such fault reports for every request.
  *
- * See <https://www.kernel.org/doc/Documentation/usb/error-codes.txt>
+ * See <https://www.kernel.org/doc/Documentation/driver-api/usb/error-codes.rst>
  */
 static void hdm_read_completion(struct urb *urb)
 {
diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c
index 7f8cf875157c..65a285631994 100644
--- a/drivers/staging/octeon/ethernet-rx.c
+++ b/drivers/staging/octeon/ethernet-rx.c
@@ -336,7 +336,6 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 		if (likely((port < TOTAL_NUMBER_OF_PORTS) &&
 			   cvm_oct_device[port])) {
 			struct net_device *dev = cvm_oct_device[port];
-			struct octeon_ethernet *priv = netdev_priv(dev);
 
 			/*
 			 * Only accept packets for devices that are
diff --git a/drivers/staging/vc04_services/Kconfig b/drivers/staging/vc04_services/Kconfig
index e61e4ca064a8..74094fff4367 100644
--- a/drivers/staging/vc04_services/Kconfig
+++ b/drivers/staging/vc04_services/Kconfig
@@ -1,6 +1,7 @@
 config BCM2835_VCHIQ
 	tristate "Videocore VCHIQ"
 	depends on HAS_DMA
+	depends on OF
 	depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE)
 	default y
 	help
diff --git a/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c b/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c
index 7961d1c56847..2b4536318ca6 100644
--- a/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c
+++ b/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c
@@ -1837,7 +1837,7 @@ static int set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int change_virtual_intf(struct wiphy *wiphy, struct net_device *dev,
-			       enum nl80211_iftype type, u32 *flags, struct vif_params *params)
+			       enum nl80211_iftype type, struct vif_params *params)
 {
 	struct wilc_priv *priv;
 	struct wilc_vif *vif;
@@ -2099,7 +2099,6 @@ static struct wireless_dev *add_virtual_intf(struct wiphy *wiphy,
 					     const char *name,
 					     unsigned char name_assign_type,
 					     enum nl80211_iftype type,
-					     u32 *flags,
 					     struct vif_params *params)
 {
 	struct wilc_vif *vif;
diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c
index 11870cb3f254..178f6f5d4613 100644
--- a/drivers/staging/wlan-ng/cfg80211.c
+++ b/drivers/staging/wlan-ng/cfg80211.c
@@ -100,7 +100,7 @@ static int prism2_domibset_pstr32(struct wlandevice *wlandev,
 /* The interface functions, called by the cfg80211 layer */
 static int prism2_change_virtual_intf(struct wiphy *wiphy,
 				      struct net_device *dev,
-				      enum nl80211_iftype type, u32 *flags,
+				      enum nl80211_iftype type,
 				      struct vif_params *params)
 {
 	struct wlandevice *wlandev = dev->ml_priv;
@@ -666,8 +666,11 @@ void prism2_disconnected(struct wlandevice *wlandev)
 
 void prism2_roamed(struct wlandevice *wlandev)
 {
-	cfg80211_roamed(wlandev->netdev, NULL, wlandev->bssid,
-			NULL, 0, NULL, 0, GFP_KERNEL);
+	struct cfg80211_roam_info roam_info = {
+		.bssid = wlandev->bssid,
+	};
+
+	cfg80211_roamed(wlandev->netdev, &roam_info, GFP_KERNEL);
 }
 
 /* Structures for declaring wiphy interface */
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index a91802432f2f..e3f9ed3690b7 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -485,8 +485,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *);
 
 int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 {
-	iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
-	return 0;
+	return iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
 }
 EXPORT_SYMBOL(iscsit_queue_rsp);
 
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index bf40f03755dd..5798810197ec 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -167,10 +167,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
 	struct iscsi_portal_group *tpg;
 	struct iscsi_tpg_np *tpg_np;
 	char *str, *str2, *ip_str, *port_str;
-	struct sockaddr_storage sockaddr;
-	struct sockaddr_in *sock_in;
-	struct sockaddr_in6 *sock_in6;
-	unsigned long port;
+	struct sockaddr_storage sockaddr = { };
 	int ret;
 	char buf[MAX_PORTAL_LEN + 1];
 
@@ -182,21 +179,19 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
 	memset(buf, 0, MAX_PORTAL_LEN + 1);
 	snprintf(buf, MAX_PORTAL_LEN + 1, "%s", name);
 
-	memset(&sockaddr, 0, sizeof(struct sockaddr_storage));
-
 	str = strstr(buf, "[");
 	if (str) {
-		const char *end;
-
 		str2 = strstr(str, "]");
 		if (!str2) {
 			pr_err("Unable to locate trailing \"]\""
 				" in IPv6 iSCSI network portal address\n");
 			return ERR_PTR(-EINVAL);
 		}
-		str++; /* Skip over leading "[" */
+
+		ip_str = str + 1; /* Skip over leading "[" */
 		*str2 = '\0'; /* Terminate the unbracketed IPv6 address */
 		str2++; /* Skip over the \0 */
+
 		port_str = strstr(str2, ":");
 		if (!port_str) {
 			pr_err("Unable to locate \":port\""
@@ -205,23 +200,8 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
 		}
 		*port_str = '\0'; /* Terminate string for IP */
 		port_str++; /* Skip over ":" */
-
-		ret = kstrtoul(port_str, 0, &port);
-		if (ret < 0) {
-			pr_err("kstrtoul() failed for port_str: %d\n", ret);
-			return ERR_PTR(ret);
-		}
-		sock_in6 = (struct sockaddr_in6 *)&sockaddr;
-		sock_in6->sin6_family = AF_INET6;
-		sock_in6->sin6_port = htons((unsigned short)port);
-		ret = in6_pton(str, -1,
-				(void *)&sock_in6->sin6_addr.in6_u, -1, &end);
-		if (ret <= 0) {
-			pr_err("in6_pton returned: %d\n", ret);
-			return ERR_PTR(-EINVAL);
-		}
 	} else {
-		str = ip_str = &buf[0];
+		ip_str = &buf[0];
 		port_str = strstr(ip_str, ":");
 		if (!port_str) {
 			pr_err("Unable to locate \":port\""
@@ -230,17 +210,15 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
 		}
 		*port_str = '\0'; /* Terminate string for IP */
 		port_str++; /* Skip over ":" */
+	}
 
-		ret = kstrtoul(port_str, 0, &port);
-		if (ret < 0) {
-			pr_err("kstrtoul() failed for port_str: %d\n", ret);
-			return ERR_PTR(ret);
-		}
-		sock_in = (struct sockaddr_in *)&sockaddr;
-		sock_in->sin_family = AF_INET;
-		sock_in->sin_port = htons((unsigned short)port);
-		sock_in->sin_addr.s_addr = in_aton(ip_str);
+	ret = inet_pton_with_scope(&init_net, AF_UNSPEC, ip_str,
+			port_str, &sockaddr);
+	if (ret) {
+		pr_err("malformed ip/port passed: %s\n", name);
+		return ERR_PTR(ret);
 	}
+
 	tpg = container_of(se_tpg, struct iscsi_portal_group, tpg_se_tpg);
 	ret = iscsit_get_tpg(tpg);
 	if (ret < 0)
@@ -1398,11 +1376,10 @@ static u32 lio_sess_get_initiator_sid(
 static int lio_queue_data_in(struct se_cmd *se_cmd)
 {
 	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+	struct iscsi_conn *conn = cmd->conn;
 
 	cmd->i_state = ISTATE_SEND_DATAIN;
-	cmd->conn->conn_transport->iscsit_queue_data_in(cmd->conn, cmd);
-
-	return 0;
+	return conn->conn_transport->iscsit_queue_data_in(conn, cmd);
 }
 
 static int lio_write_pending(struct se_cmd *se_cmd)
@@ -1431,16 +1408,14 @@ static int lio_write_pending_status(struct se_cmd *se_cmd)
 static int lio_queue_status(struct se_cmd *se_cmd)
 {
 	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+	struct iscsi_conn *conn = cmd->conn;
 
 	cmd->i_state = ISTATE_SEND_STATUS;
 
 	if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
-		iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
-		return 0;
+		return iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
 	}
-	cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
-
-	return 0;
+	return conn->conn_transport->iscsit_queue_status(conn, cmd);
 }
 
 static void lio_queue_tm_rsp(struct se_cmd *se_cmd)
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e65bf78ceef3..fce627628200 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -782,22 +782,6 @@ static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param)
 		if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH))
 			SET_PSTATE_REPLY_OPTIONAL(param);
 		/*
-		 * The GlobalSAN iSCSI Initiator for MacOSX does
-		 * not respond to MaxBurstLength, FirstBurstLength,
-		 * DefaultTime2Wait or DefaultTime2Retain parameter keys.
-		 * So, we set them to 'reply optional' here, and assume the
-		 * the defaults from iscsi_parameters.h if the initiator
-		 * is not RFC compliant and the keys are not negotiated.
-		 */
-		if (!strcmp(param->name, MAXBURSTLENGTH))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		if (!strcmp(param->name, FIRSTBURSTLENGTH))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		if (!strcmp(param->name, DEFAULTTIME2WAIT))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		if (!strcmp(param->name, DEFAULTTIME2RETAIN))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		/*
 		 * Required for gPXE iSCSI boot client
 		 */
 		if (!strcmp(param->name, MAXCONNECTIONS))
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 5041a9c8bdcb..7d3e2fcc26a0 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -567,7 +567,7 @@ static void iscsit_remove_cmd_from_immediate_queue(
 	}
 }
 
-void iscsit_add_cmd_to_response_queue(
+int iscsit_add_cmd_to_response_queue(
 	struct iscsi_cmd *cmd,
 	struct iscsi_conn *conn,
 	u8 state)
@@ -578,7 +578,7 @@ void iscsit_add_cmd_to_response_queue(
 	if (!qr) {
 		pr_err("Unable to allocate memory for"
 			" struct iscsi_queue_req\n");
-		return;
+		return -ENOMEM;
 	}
 	INIT_LIST_HEAD(&qr->qr_list);
 	qr->cmd = cmd;
@@ -590,6 +590,7 @@ void iscsit_add_cmd_to_response_queue(
 	spin_unlock_bh(&conn->response_queue_lock);
 
 	wake_up(&conn->queues_wq);
+	return 0;
 }
 
 struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *conn)
@@ -737,21 +738,23 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
 {
 	struct se_cmd *se_cmd = NULL;
 	int rc;
+	bool op_scsi = false;
 	/*
 	 * Determine if a struct se_cmd is associated with
 	 * this struct iscsi_cmd.
 	 */
 	switch (cmd->iscsi_opcode) {
 	case ISCSI_OP_SCSI_CMD:
-		se_cmd = &cmd->se_cmd;
-		__iscsit_free_cmd(cmd, true, shutdown);
+		op_scsi = true;
 		/*
 		 * Fallthrough
 		 */
 	case ISCSI_OP_SCSI_TMFUNC:
-		rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
-		if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
-			__iscsit_free_cmd(cmd, true, shutdown);
+		se_cmd = &cmd->se_cmd;
+		__iscsit_free_cmd(cmd, op_scsi, shutdown);
+		rc = transport_generic_free_cmd(se_cmd, shutdown);
+		if (!rc && shutdown && se_cmd->se_sess) {
+			__iscsit_free_cmd(cmd, op_scsi, shutdown);
 			target_put_sess_cmd(se_cmd);
 		}
 		break;
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index 8ff08856516a..9e4197af8708 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -31,7 +31,7 @@ extern int iscsit_find_cmd_for_recovery(struct iscsi_session *, struct iscsi_cmd
 			struct iscsi_conn_recovery **, itt_t);
 extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
 extern struct iscsi_queue_req *iscsit_get_cmd_from_immediate_queue(struct iscsi_conn *);
-extern void iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
+extern int iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
 extern struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *);
 extern void iscsit_remove_cmd_from_tx_queues(struct iscsi_cmd *, struct iscsi_conn *);
 extern bool iscsit_conn_all_queues_empty(struct iscsi_conn *);
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index f5e330099bfc..fc4a9c303d55 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -43,7 +43,7 @@
 #include "target_core_ua.h"
 
 static sense_reason_t core_alua_check_transition(int state, int valid,
-						 int *primary);
+						 int *primary, int explicit);
 static int core_alua_set_tg_pt_secondary_state(
 		struct se_lun *lun, int explicit, int offline);
 
@@ -197,8 +197,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 		/*
 		 * Set the ASYMMETRIC ACCESS State
 		 */
-		buf[off++] |= (atomic_read(
-			&tg_pt_gp->tg_pt_gp_alua_access_state) & 0xff);
+		buf[off++] |= tg_pt_gp->tg_pt_gp_alua_access_state & 0xff;
 		/*
 		 * Set supported ASYMMETRIC ACCESS State bits
 		 */
@@ -335,8 +334,8 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 		 * the state is a primary or secondary target port asymmetric
 		 * access state.
 		 */
-		rc = core_alua_check_transition(alua_access_state,
-						valid_states, &primary);
+		rc = core_alua_check_transition(alua_access_state, valid_states,
+						&primary, 1);
 		if (rc) {
 			/*
 			 * If the SET TARGET PORT GROUPS attempts to establish
@@ -691,7 +690,7 @@ target_alua_state_check(struct se_cmd *cmd)
 
 	if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
 		return 0;
-	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
+	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA)
 		return 0;
 
 	/*
@@ -710,7 +709,7 @@ target_alua_state_check(struct se_cmd *cmd)
 
 	spin_lock(&lun->lun_tg_pt_gp_lock);
 	tg_pt_gp = lun->lun_tg_pt_gp;
-	out_alua_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
+	out_alua_state = tg_pt_gp->tg_pt_gp_alua_access_state;
 	nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs;
 
 	// XXX: keeps using tg_pt_gp witout reference after unlock
@@ -762,7 +761,7 @@ target_alua_state_check(struct se_cmd *cmd)
  * Check implicit and explicit ALUA state change request.
  */
 static sense_reason_t
-core_alua_check_transition(int state, int valid, int *primary)
+core_alua_check_transition(int state, int valid, int *primary, int explicit)
 {
 	/*
 	 * OPTIMIZED, NON-OPTIMIZED, STANDBY and UNAVAILABLE are
@@ -804,11 +803,14 @@ core_alua_check_transition(int state, int valid, int *primary)
 		*primary = 0;
 		break;
 	case ALUA_ACCESS_STATE_TRANSITION:
-		/*
-		 * Transitioning is set internally, and
-		 * cannot be selected manually.
-		 */
-		goto not_supported;
+		if (!(valid & ALUA_T_SUP) || explicit)
+			/*
+			 * Transitioning is set internally and by tcmu daemon,
+			 * and cannot be selected through a STPG.
+			 */
+			goto not_supported;
+		*primary = 0;
+		break;
 	default:
 		pr_err("Unknown ALUA access state: 0x%02x\n", state);
 		return TCM_INVALID_PARAMETER_LIST;
@@ -908,7 +910,7 @@ static int core_alua_write_tpg_metadata(
 }
 
 /*
- * Called with tg_pt_gp->tg_pt_gp_md_mutex held
+ * Called with tg_pt_gp->tg_pt_gp_transition_mutex held
  */
 static int core_alua_update_tpg_primary_metadata(
 	struct t10_alua_tg_pt_gp *tg_pt_gp)
@@ -931,7 +933,7 @@ static int core_alua_update_tpg_primary_metadata(
 			"alua_access_state=0x%02x\n"
 			"alua_access_status=0x%02x\n",
 			tg_pt_gp->tg_pt_gp_id,
-			tg_pt_gp->tg_pt_gp_alua_pending_state,
+			tg_pt_gp->tg_pt_gp_alua_access_state,
 			tg_pt_gp->tg_pt_gp_alua_access_status);
 
 	snprintf(path, ALUA_METADATA_PATH_LEN,
@@ -1010,100 +1012,42 @@ static void core_alua_queue_state_change_ua(struct t10_alua_tg_pt_gp *tg_pt_gp)
 	spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 }
 
-static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
-{
-	struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
-		struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work.work);
-	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
-	bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
-			 ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
-
-	/*
-	 * Update the ALUA metadata buf that has been allocated in
-	 * core_alua_do_port_transition(), this metadata will be written
-	 * to struct file.
-	 *
-	 * Note that there is the case where we do not want to update the
-	 * metadata when the saved metadata is being parsed in userspace
-	 * when setting the existing port access state and access status.
-	 *
-	 * Also note that the failure to write out the ALUA metadata to
-	 * struct file does NOT affect the actual ALUA transition.
-	 */
-	if (tg_pt_gp->tg_pt_gp_write_metadata) {
-		mutex_lock(&tg_pt_gp->tg_pt_gp_md_mutex);
-		core_alua_update_tpg_primary_metadata(tg_pt_gp);
-		mutex_unlock(&tg_pt_gp->tg_pt_gp_md_mutex);
-	}
-	/*
-	 * Set the current primary ALUA access state to the requested new state
-	 */
-	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
-		   tg_pt_gp->tg_pt_gp_alua_pending_state);
-
-	pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
-		" from primary access state %s to %s\n", (explicit) ? "explicit" :
-		"implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
-		tg_pt_gp->tg_pt_gp_id,
-		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_previous_state),
-		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
-
-	core_alua_queue_state_change_ua(tg_pt_gp);
-
-	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
-	atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
-	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
-
-	if (tg_pt_gp->tg_pt_gp_transition_complete)
-		complete(tg_pt_gp->tg_pt_gp_transition_complete);
-}
-
 static int core_alua_do_transition_tg_pt(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	int new_state,
 	int explicit)
 {
-	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
-	DECLARE_COMPLETION_ONSTACK(wait);
+	int prev_state;
 
+	mutex_lock(&tg_pt_gp->tg_pt_gp_transition_mutex);
 	/* Nothing to be done here */
-	if (atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) == new_state)
+	if (tg_pt_gp->tg_pt_gp_alua_access_state == new_state) {
+		mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
 		return 0;
+	}
 
-	if (new_state == ALUA_ACCESS_STATE_TRANSITION)
+	if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION) {
+		mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
 		return -EAGAIN;
-
-	/*
-	 * Flush any pending transitions
-	 */
-	if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs &&
-	    atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) ==
-	    ALUA_ACCESS_STATE_TRANSITION) {
-		/* Just in case */
-		tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
-		tg_pt_gp->tg_pt_gp_transition_complete = &wait;
-		flush_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work);
-		wait_for_completion(&wait);
-		tg_pt_gp->tg_pt_gp_transition_complete = NULL;
-		return 0;
 	}
 
 	/*
 	 * Save the old primary ALUA access state, and set the current state
 	 * to ALUA_ACCESS_STATE_TRANSITION.
 	 */
-	tg_pt_gp->tg_pt_gp_alua_previous_state =
-		atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
-	tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
-
-	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
-			ALUA_ACCESS_STATE_TRANSITION);
+	prev_state = tg_pt_gp->tg_pt_gp_alua_access_state;
+	tg_pt_gp->tg_pt_gp_alua_access_state = ALUA_ACCESS_STATE_TRANSITION;
 	tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
 				ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
 				ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
 
 	core_alua_queue_state_change_ua(tg_pt_gp);
 
+	if (new_state == ALUA_ACCESS_STATE_TRANSITION) {
+		mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
+		return 0;
+	}
+
 	/*
 	 * Check for the optional ALUA primary state transition delay
 	 */
@@ -1111,27 +1055,36 @@ static int core_alua_do_transition_tg_pt(
 		msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs);
 
 	/*
-	 * Take a reference for workqueue item
+	 * Set the current primary ALUA access state to the requested new state
 	 */
-	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
-	atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
-	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+	tg_pt_gp->tg_pt_gp_alua_access_state = new_state;
 
-	if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs) {
-		unsigned long transition_tmo;
-
-		transition_tmo = tg_pt_gp->tg_pt_gp_implicit_trans_secs * HZ;
-		queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq,
-				   &tg_pt_gp->tg_pt_gp_transition_work,
-				   transition_tmo);
-	} else {
-		tg_pt_gp->tg_pt_gp_transition_complete = &wait;
-		queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq,
-				   &tg_pt_gp->tg_pt_gp_transition_work, 0);
-		wait_for_completion(&wait);
-		tg_pt_gp->tg_pt_gp_transition_complete = NULL;
+	/*
+	 * Update the ALUA metadata buf that has been allocated in
+	 * core_alua_do_port_transition(), this metadata will be written
+	 * to struct file.
+	 *
+	 * Note that there is the case where we do not want to update the
+	 * metadata when the saved metadata is being parsed in userspace
+	 * when setting the existing port access state and access status.
+	 *
+	 * Also note that the failure to write out the ALUA metadata to
+	 * struct file does NOT affect the actual ALUA transition.
+	 */
+	if (tg_pt_gp->tg_pt_gp_write_metadata) {
+		core_alua_update_tpg_primary_metadata(tg_pt_gp);
 	}
 
+	pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
+		" from primary access state %s to %s\n", (explicit) ? "explicit" :
+		"implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+		tg_pt_gp->tg_pt_gp_id,
+		core_alua_dump_state(prev_state),
+		core_alua_dump_state(new_state));
+
+	core_alua_queue_state_change_ua(tg_pt_gp);
+
+	mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
 	return 0;
 }
 
@@ -1149,8 +1102,12 @@ int core_alua_do_port_transition(
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	int primary, valid_states, rc = 0;
 
+	if (l_dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA)
+		return -ENODEV;
+
 	valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states;
-	if (core_alua_check_transition(new_state, valid_states, &primary) != 0)
+	if (core_alua_check_transition(new_state, valid_states, &primary,
+				       explicit) != 0)
 		return -EINVAL;
 
 	local_lu_gp_mem = l_dev->dev_alua_lu_gp_mem;
@@ -1692,14 +1649,12 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev,
 	}
 	INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_list);
 	INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_lun_list);
-	mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
+	mutex_init(&tg_pt_gp->tg_pt_gp_transition_mutex);
 	spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
 	atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
-	INIT_DELAYED_WORK(&tg_pt_gp->tg_pt_gp_transition_work,
-			  core_alua_do_transition_tg_pt_work);
 	tg_pt_gp->tg_pt_gp_dev = dev;
-	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
-		ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED);
+	tg_pt_gp->tg_pt_gp_alua_access_state =
+			ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED;
 	/*
 	 * Enable both explicit and implicit ALUA support by default
 	 */
@@ -1804,8 +1759,6 @@ void core_alua_free_tg_pt_gp(
 	dev->t10_alua.alua_tg_pt_gps_counter--;
 	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
-	flush_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work);
-
 	/*
 	 * Allow a struct t10_alua_tg_pt_gp_member * referenced by
 	 * core_alua_get_tg_pt_gp_by_name() in
@@ -1945,8 +1898,8 @@ ssize_t core_alua_show_tg_pt_gp_info(struct se_lun *lun, char *page)
 			"Primary Access Status: %s\nTG Port Secondary Access"
 			" State: %s\nTG Port Secondary Access Status: %s\n",
 			config_item_name(tg_pt_ci), tg_pt_gp->tg_pt_gp_id,
-			core_alua_dump_state(atomic_read(
-					&tg_pt_gp->tg_pt_gp_alua_access_state)),
+			core_alua_dump_state(
+				tg_pt_gp->tg_pt_gp_alua_access_state),
 			core_alua_dump_status(
 				tg_pt_gp->tg_pt_gp_alua_access_status),
 			atomic_read(&lun->lun_tg_pt_secondary_offline) ?
@@ -1973,7 +1926,7 @@ ssize_t core_alua_store_tg_pt_gp_info(
 	unsigned char buf[TG_PT_GROUP_NAME_BUF];
 	int move = 0;
 
-	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH ||
+	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA ||
 	    (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		return -ENODEV;
 
@@ -2230,7 +2183,7 @@ ssize_t core_alua_store_offline_bit(
 	unsigned long tmp;
 	int ret;
 
-	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH ||
+	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA ||
 	    (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		return -ENODEV;
 
@@ -2316,7 +2269,8 @@ ssize_t core_alua_store_secondary_write_metadata(
 
 int core_setup_alua(struct se_device *dev)
 {
-	if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
+	if (!(dev->transport->transport_flags &
+	     TRANSPORT_FLAG_PASSTHROUGH_ALUA) &&
 	    !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
 		struct t10_alua_lu_gp_member *lu_gp_mem;
 
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 54b36c9835be..70657fd56440 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -421,6 +421,10 @@ static int target_fabric_tf_ops_check(const struct target_core_fabric_ops *tfo)
 		pr_err("Missing tfo->aborted_task()\n");
 		return -EINVAL;
 	}
+	if (!tfo->check_stop_free) {
+		pr_err("Missing tfo->check_stop_free()\n");
+		return -EINVAL;
+	}
 	/*
 	 * We at least require tfo->fabric_make_wwn(), tfo->fabric_drop_wwn()
 	 * tfo->fabric_make_tpg() and tfo->fabric_drop_tpg() in
@@ -2388,7 +2392,7 @@ static ssize_t target_tg_pt_gp_alua_access_state_show(struct config_item *item,
 		char *page)
 {
 	return sprintf(page, "%d\n",
-		atomic_read(&to_tg_pt_gp(item)->tg_pt_gp_alua_access_state));
+		       to_tg_pt_gp(item)->tg_pt_gp_alua_access_state);
 }
 
 static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item,
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index c754ae33bf7b..d2f089cfa9ae 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -851,7 +851,7 @@ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 	attrib->unmap_granularity = q->limits.discard_granularity / block_size;
 	attrib->unmap_granularity_alignment = q->limits.discard_alignment /
 								block_size;
-	attrib->unmap_zeroes_data = q->limits.discard_zeroes_data;
+	attrib->unmap_zeroes_data = 0;
 	return true;
 }
 EXPORT_SYMBOL(target_configure_unmap_from_queue);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index d8a16ca6baa5..d1e6cab8e3d3 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -92,6 +92,11 @@ static int target_fabric_mappedlun_link(
 		pr_err("Source se_lun->lun_se_dev does not exist\n");
 		return -EINVAL;
 	}
+	if (lun->lun_shutdown) {
+		pr_err("Unable to create mappedlun symlink because"
+			" lun->lun_shutdown=true\n");
+		return -EINVAL;
+	}
 	se_tpg = lun->lun_tpg;
 
 	nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index a8f8e53f2f57..a93d94e68ab5 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -154,7 +154,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 
 	buf = kzalloc(12, GFP_KERNEL);
 	if (!buf)
-		return;
+		goto out_free;
 
 	memset(cdb, 0, MAX_COMMAND_SIZE);
 	cdb[0] = MODE_SENSE;
@@ -169,9 +169,10 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 	 * If MODE_SENSE still returns zero, set the default value to 1024.
 	 */
 	sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]);
+out_free:
 	if (!sdev->sector_size)
 		sdev->sector_size = 1024;
-out_free:
+
 	kfree(buf);
 }
 
@@ -314,9 +315,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
 				sd->lun, sd->queue_depth);
 	}
 
-	dev->dev_attrib.hw_block_size = sd->sector_size;
+	dev->dev_attrib.hw_block_size =
+		min_not_zero((int)sd->sector_size, 512);
 	dev->dev_attrib.hw_max_sectors =
-		min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q));
+		min_not_zero(sd->host->max_sectors, queue_max_hw_sectors(q));
 	dev->dev_attrib.hw_queue_depth = sd->queue_depth;
 
 	/*
@@ -339,8 +341,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
 	/*
 	 * For TYPE_TAPE, attempt to determine blocksize with MODE_SENSE.
 	 */
-	if (sd->type == TYPE_TAPE)
+	if (sd->type == TYPE_TAPE) {
 		pscsi_tape_read_blocksize(dev, sd);
+		dev->dev_attrib.hw_block_size = sd->sector_size;
+	}
 	return 0;
 }
 
@@ -406,7 +410,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 /*
  * Called with struct Scsi_Host->host_lock called.
  */
-static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
+static int pscsi_create_type_nondisk(struct se_device *dev, struct scsi_device *sd)
 	__releases(sh->host_lock)
 {
 	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
@@ -433,28 +437,6 @@ static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
 	return 0;
 }
 
-/*
- * Called with struct Scsi_Host->host_lock called.
- */
-static int pscsi_create_type_other(struct se_device *dev,
-		struct scsi_device *sd)
-	__releases(sh->host_lock)
-{
-	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
-	struct Scsi_Host *sh = sd->host;
-	int ret;
-
-	spin_unlock_irq(sh->host_lock);
-	ret = pscsi_add_device_to_list(dev, sd);
-	if (ret)
-		return ret;
-
-	pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%llu\n",
-		phv->phv_host_id, scsi_device_type(sd->type), sh->host_no,
-		sd->channel, sd->id, sd->lun);
-	return 0;
-}
-
 static int pscsi_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
@@ -542,11 +524,8 @@ static int pscsi_configure_device(struct se_device *dev)
 		case TYPE_DISK:
 			ret = pscsi_create_type_disk(dev, sd);
 			break;
-		case TYPE_ROM:
-			ret = pscsi_create_type_rom(dev, sd);
-			break;
 		default:
-			ret = pscsi_create_type_other(dev, sd);
+			ret = pscsi_create_type_nondisk(dev, sd);
 			break;
 		}
 
@@ -611,8 +590,7 @@ static void pscsi_free_device(struct se_device *dev)
 		else if (pdv->pdv_lld_host)
 			scsi_host_put(pdv->pdv_lld_host);
 
-		if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
-			scsi_device_put(sd);
+		scsi_device_put(sd);
 
 		pdv->pdv_sd = NULL;
 	}
@@ -1030,7 +1008,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 		req->timeout = PS_TIMEOUT_DISK;
 	else
 		req->timeout = PS_TIMEOUT_OTHER;
-	req->retries = PS_RETRY;
+	scsi_req(req)->retries = PS_RETRY;
 
 	blk_execute_rq_nowait(pdv->pdv_sd->request_queue, NULL, req,
 			(cmd->sam_task_attr == TCM_HEAD_TAG),
@@ -1064,7 +1042,6 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 	if (pdv->pdv_bd && pdv->pdv_bd->bd_part)
 		return pdv->pdv_bd->bd_part->nr_sects;
 
-	dump_stack();
 	return 0;
 }
 
@@ -1073,7 +1050,7 @@ static void pscsi_req_done(struct request *req, int uptodate)
 	struct se_cmd *cmd = req->end_io_data;
 	struct pscsi_plugin_task *pt = cmd->priv;
 
-	pt->pscsi_result = req->errors;
+	pt->pscsi_result = scsi_req(req)->result;
 	pt->pscsi_resid = scsi_req(req)->resid_len;
 
 	cmd->scsi_status = status_byte(pt->pscsi_result) << 1;
@@ -1103,7 +1080,8 @@ static void pscsi_req_done(struct request *req, int uptodate)
 static const struct target_backend_ops pscsi_ops = {
 	.name			= "pscsi",
 	.owner			= THIS_MODULE,
-	.transport_flags	= TRANSPORT_FLAG_PASSTHROUGH,
+	.transport_flags	= TRANSPORT_FLAG_PASSTHROUGH |
+				  TRANSPORT_FLAG_PASSTHROUGH_ALUA,
 	.attach_hba		= pscsi_attach_hba,
 	.detach_hba		= pscsi_detach_hba,
 	.pmode_enable_hba	= pscsi_pmode_enable_hba,
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 68d8aef7ab78..c194063f169b 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1105,9 +1105,15 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			return ret;
 		break;
 	case VERIFY:
+	case VERIFY_16:
 		size = 0;
-		sectors = transport_get_sectors_10(cdb);
-		cmd->t_task_lba = transport_lba_32(cdb);
+		if (cdb[0] == VERIFY) {
+			sectors = transport_get_sectors_10(cdb);
+			cmd->t_task_lba = transport_lba_32(cdb);
+		} else {
+			sectors = transport_get_sectors_16(cdb);
+			cmd->t_task_lba = transport_lba_64(cdb);
+		}
 		cmd->execute_cmd = sbc_emulate_noop;
 		goto check_lba;
 	case REZERO_UNIT:
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index c0dbfa016575..dfaef4d3b2d2 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -602,7 +602,8 @@ int core_tpg_add_lun(
 	if (ret)
 		goto out_kill_ref;
 
-	if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
+	if (!(dev->transport->transport_flags &
+	     TRANSPORT_FLAG_PASSTHROUGH_ALUA) &&
 	    !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		target_attach_tg_pt_gp(lun, dev->t10_alua.default_tg_pt_gp);
 
@@ -641,6 +642,8 @@ void core_tpg_remove_lun(
 	 */
 	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
 
+	lun->lun_shutdown = true;
+
 	core_clear_lun_from_tpg(lun, tpg);
 	/*
 	 * Wait for any active I/O references to percpu se_lun->lun_ref to
@@ -662,6 +665,8 @@ void core_tpg_remove_lun(
 	}
 	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		hlist_del_rcu(&lun->link);
+
+	lun->lun_shutdown = false;
 	mutex_unlock(&tpg->tpg_lun_mutex);
 
 	percpu_ref_exit(&lun->lun_ref);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 434d9d693989..a0cd56ee5fe9 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -64,8 +64,9 @@ struct kmem_cache *t10_alua_lba_map_cache;
 struct kmem_cache *t10_alua_lba_map_mem_cache;
 
 static void transport_complete_task_attr(struct se_cmd *cmd);
+static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
 static void transport_handle_queue_full(struct se_cmd *cmd,
-		struct se_device *dev);
+		struct se_device *dev, int err, bool write_pending);
 static int transport_put_cmd(struct se_cmd *cmd);
 static void target_complete_ok_work(struct work_struct *work);
 
@@ -636,8 +637,7 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 	 * Fabric modules are expected to return '1' here if the se_cmd being
 	 * passed is released at this point, or zero if not being released.
 	 */
-	return cmd->se_tfo->check_stop_free ? cmd->se_tfo->check_stop_free(cmd)
-		: 0;
+	return cmd->se_tfo->check_stop_free(cmd);
 }
 
 static void transport_lun_remove_cmd(struct se_cmd *cmd)
@@ -805,7 +805,8 @@ void target_qf_do_work(struct work_struct *work)
 
 		if (cmd->t_state == TRANSPORT_COMPLETE_QF_WP)
 			transport_write_pending_qf(cmd);
-		else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK)
+		else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK ||
+			 cmd->t_state == TRANSPORT_COMPLETE_QF_ERR)
 			transport_complete_qf(cmd);
 	}
 }
@@ -1720,7 +1721,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 		}
 		trace_target_cmd_complete(cmd);
 		ret = cmd->se_tfo->queue_status(cmd);
-		if (ret == -EAGAIN || ret == -ENOMEM)
+		if (ret)
 			goto queue_full;
 		goto check_stop;
 	default:
@@ -1731,7 +1732,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 	}
 
 	ret = transport_send_check_condition_and_sense(cmd, sense_reason, 0);
-	if (ret == -EAGAIN || ret == -ENOMEM)
+	if (ret)
 		goto queue_full;
 
 check_stop:
@@ -1740,8 +1741,7 @@ check_stop:
 	return;
 
 queue_full:
-	cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
-	transport_handle_queue_full(cmd, cmd->se_dev);
+	transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 }
 EXPORT_SYMBOL(transport_generic_request_failure);
 
@@ -1978,13 +1978,29 @@ static void transport_complete_qf(struct se_cmd *cmd)
 	int ret = 0;
 
 	transport_complete_task_attr(cmd);
+	/*
+	 * If a fabric driver ->write_pending() or ->queue_data_in() callback
+	 * has returned neither -ENOMEM or -EAGAIN, assume it's fatal and
+	 * the same callbacks should not be retried.  Return CHECK_CONDITION
+	 * if a scsi_status is not already set.
+	 *
+	 * If a fabric driver ->queue_status() has returned non zero, always
+	 * keep retrying no matter what..
+	 */
+	if (cmd->t_state == TRANSPORT_COMPLETE_QF_ERR) {
+		if (cmd->scsi_status)
+			goto queue_status;
 
-	if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
-		trace_target_cmd_complete(cmd);
-		ret = cmd->se_tfo->queue_status(cmd);
-		goto out;
+		cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
+		cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+		cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
+		translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
+		goto queue_status;
 	}
 
+	if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE)
+		goto queue_status;
+
 	switch (cmd->data_direction) {
 	case DMA_FROM_DEVICE:
 		if (cmd->scsi_status)
@@ -2008,19 +2024,33 @@ queue_status:
 		break;
 	}
 
-out:
 	if (ret < 0) {
-		transport_handle_queue_full(cmd, cmd->se_dev);
+		transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 		return;
 	}
 	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
-static void transport_handle_queue_full(
-	struct se_cmd *cmd,
-	struct se_device *dev)
+static void transport_handle_queue_full(struct se_cmd *cmd, struct se_device *dev,
+					int err, bool write_pending)
 {
+	/*
+	 * -EAGAIN or -ENOMEM signals retry of ->write_pending() and/or
+	 * ->queue_data_in() callbacks from new process context.
+	 *
+	 * Otherwise for other errors, transport_complete_qf() will send
+	 * CHECK_CONDITION via ->queue_status() instead of attempting to
+	 * retry associated fabric driver data-transfer callbacks.
+	 */
+	if (err == -EAGAIN || err == -ENOMEM) {
+		cmd->t_state = (write_pending) ? TRANSPORT_COMPLETE_QF_WP :
+						 TRANSPORT_COMPLETE_QF_OK;
+	} else {
+		pr_warn_ratelimited("Got unknown fabric queue status: %d\n", err);
+		cmd->t_state = TRANSPORT_COMPLETE_QF_ERR;
+	}
+
 	spin_lock_irq(&dev->qf_cmd_lock);
 	list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list);
 	atomic_inc_mb(&dev->dev_qf_count);
@@ -2084,7 +2114,7 @@ static void target_complete_ok_work(struct work_struct *work)
 		WARN_ON(!cmd->scsi_status);
 		ret = transport_send_check_condition_and_sense(
 					cmd, 0, 1);
-		if (ret == -EAGAIN || ret == -ENOMEM)
+		if (ret)
 			goto queue_full;
 
 		transport_lun_remove_cmd(cmd);
@@ -2110,7 +2140,7 @@ static void target_complete_ok_work(struct work_struct *work)
 		} else if (rc) {
 			ret = transport_send_check_condition_and_sense(cmd,
 						rc, 0);
-			if (ret == -EAGAIN || ret == -ENOMEM)
+			if (ret)
 				goto queue_full;
 
 			transport_lun_remove_cmd(cmd);
@@ -2135,7 +2165,7 @@ queue_rsp:
 		if (target_read_prot_action(cmd)) {
 			ret = transport_send_check_condition_and_sense(cmd,
 						cmd->pi_err, 0);
-			if (ret == -EAGAIN || ret == -ENOMEM)
+			if (ret)
 				goto queue_full;
 
 			transport_lun_remove_cmd(cmd);
@@ -2145,7 +2175,7 @@ queue_rsp:
 
 		trace_target_cmd_complete(cmd);
 		ret = cmd->se_tfo->queue_data_in(cmd);
-		if (ret == -EAGAIN || ret == -ENOMEM)
+		if (ret)
 			goto queue_full;
 		break;
 	case DMA_TO_DEVICE:
@@ -2158,7 +2188,7 @@ queue_rsp:
 			atomic_long_add(cmd->data_length,
 					&cmd->se_lun->lun_stats.tx_data_octets);
 			ret = cmd->se_tfo->queue_data_in(cmd);
-			if (ret == -EAGAIN || ret == -ENOMEM)
+			if (ret)
 				goto queue_full;
 			break;
 		}
@@ -2167,7 +2197,7 @@ queue_rsp:
 queue_status:
 		trace_target_cmd_complete(cmd);
 		ret = cmd->se_tfo->queue_status(cmd);
-		if (ret == -EAGAIN || ret == -ENOMEM)
+		if (ret)
 			goto queue_full;
 		break;
 	default:
@@ -2181,8 +2211,8 @@ queue_status:
 queue_full:
 	pr_debug("Handling complete_ok QUEUE_FULL: se_cmd: %p,"
 		" data_direction: %d\n", cmd, cmd->data_direction);
-	cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
-	transport_handle_queue_full(cmd, cmd->se_dev);
+
+	transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 }
 
 void target_free_sgl(struct scatterlist *sgl, int nents)
@@ -2450,18 +2480,14 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
 	ret = cmd->se_tfo->write_pending(cmd);
-	if (ret == -EAGAIN || ret == -ENOMEM)
+	if (ret)
 		goto queue_full;
 
-	/* fabric drivers should only return -EAGAIN or -ENOMEM as error */
-	WARN_ON(ret);
-
-	return (!ret) ? 0 : TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	return 0;
 
 queue_full:
 	pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd);
-	cmd->t_state = TRANSPORT_COMPLETE_QF_WP;
-	transport_handle_queue_full(cmd, cmd->se_dev);
+	transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
 	return 0;
 }
 EXPORT_SYMBOL(transport_generic_new_cmd);
@@ -2471,10 +2497,10 @@ static void transport_write_pending_qf(struct se_cmd *cmd)
 	int ret;
 
 	ret = cmd->se_tfo->write_pending(cmd);
-	if (ret == -EAGAIN || ret == -ENOMEM) {
+	if (ret) {
 		pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n",
 			 cmd);
-		transport_handle_queue_full(cmd, cmd->se_dev);
+		transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
 	}
 }
 
@@ -3012,6 +3038,8 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
 	__releases(&cmd->t_state_lock)
 	__acquires(&cmd->t_state_lock)
 {
+	int ret;
+
 	assert_spin_locked(&cmd->t_state_lock);
 	WARN_ON_ONCE(!irqs_disabled());
 
@@ -3035,7 +3063,9 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
 	trace_target_cmd_complete(cmd);
 
 	spin_unlock_irq(&cmd->t_state_lock);
-	cmd->se_tfo->queue_status(cmd);
+	ret = cmd->se_tfo->queue_status(cmd);
+	if (ret)
+		transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 	spin_lock_irq(&cmd->t_state_lock);
 
 	return 1;
@@ -3056,6 +3086,7 @@ EXPORT_SYMBOL(transport_check_aborted_status);
 void transport_send_task_abort(struct se_cmd *cmd)
 {
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	if (cmd->se_cmd_flags & (SCF_SENT_CHECK_CONDITION)) {
@@ -3091,7 +3122,9 @@ send_abort:
 		 cmd->t_task_cdb[0], cmd->tag);
 
 	trace_target_cmd_complete(cmd);
-	cmd->se_tfo->queue_status(cmd);
+	ret = cmd->se_tfo->queue_status(cmd);
+	if (ret)
+		transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 }
 
 static void target_tmr_work(struct work_struct *work)
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index c3adefe95e50..f615c3bbb73e 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -28,6 +28,7 @@
 #include <linux/stringify.h>
 #include <linux/bitops.h>
 #include <linux/highmem.h>
+#include <linux/configfs.h>
 #include <net/genetlink.h>
 #include <scsi/scsi_common.h>
 #include <scsi/scsi_proto.h>
@@ -112,6 +113,7 @@ struct tcmu_dev {
 	spinlock_t commands_lock;
 
 	struct timer_list timeout;
+	unsigned int cmd_time_out;
 
 	char dev_config[TCMU_CONFIG_LEN];
 };
@@ -172,7 +174,9 @@ static struct tcmu_cmd *tcmu_alloc_cmd(struct se_cmd *se_cmd)
 
 	tcmu_cmd->se_cmd = se_cmd;
 	tcmu_cmd->tcmu_dev = udev;
-	tcmu_cmd->deadline = jiffies + msecs_to_jiffies(TCMU_TIME_OUT);
+	if (udev->cmd_time_out)
+		tcmu_cmd->deadline = jiffies +
+					msecs_to_jiffies(udev->cmd_time_out);
 
 	idr_preload(GFP_KERNEL);
 	spin_lock_irq(&udev->commands_lock);
@@ -307,24 +311,50 @@ static void free_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd)
 		   DATA_BLOCK_BITS);
 }
 
-static void gather_data_area(struct tcmu_dev *udev, unsigned long *cmd_bitmap,
-		struct scatterlist *data_sg, unsigned int data_nents)
+static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
+			     bool bidi)
 {
+	struct se_cmd *se_cmd = cmd->se_cmd;
 	int i, block;
 	int block_remaining = 0;
 	void *from, *to;
 	size_t copy_bytes, from_offset;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *data_sg;
+	unsigned int data_nents;
+	DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
+
+	bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
+
+	if (!bidi) {
+		data_sg = se_cmd->t_data_sg;
+		data_nents = se_cmd->t_data_nents;
+	} else {
+		uint32_t count;
+
+		/*
+		 * For bidi case, the first count blocks are for Data-Out
+		 * buffer blocks, and before gathering the Data-In buffer
+		 * the Data-Out buffer blocks should be discarded.
+		 */
+		count = DIV_ROUND_UP(se_cmd->data_length, DATA_BLOCK_SIZE);
+		while (count--) {
+			block = find_first_bit(bitmap, DATA_BLOCK_BITS);
+			clear_bit(block, bitmap);
+		}
+
+		data_sg = se_cmd->t_bidi_data_sg;
+		data_nents = se_cmd->t_bidi_data_nents;
+	}
 
 	for_each_sg(data_sg, sg, data_nents, i) {
 		int sg_remaining = sg->length;
 		to = kmap_atomic(sg_page(sg)) + sg->offset;
 		while (sg_remaining > 0) {
 			if (block_remaining == 0) {
-				block = find_first_bit(cmd_bitmap,
+				block = find_first_bit(bitmap,
 						DATA_BLOCK_BITS);
 				block_remaining = DATA_BLOCK_SIZE;
-				clear_bit(block, cmd_bitmap);
+				clear_bit(block, bitmap);
 			}
 			copy_bytes = min_t(size_t, sg_remaining,
 					block_remaining);
@@ -390,6 +420,27 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, size_t cmd_size, size_t d
 	return true;
 }
 
+static inline size_t tcmu_cmd_get_data_length(struct tcmu_cmd *tcmu_cmd)
+{
+	struct se_cmd *se_cmd = tcmu_cmd->se_cmd;
+	size_t data_length = round_up(se_cmd->data_length, DATA_BLOCK_SIZE);
+
+	if (se_cmd->se_cmd_flags & SCF_BIDI) {
+		BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
+		data_length += round_up(se_cmd->t_bidi_data_sg->length,
+				DATA_BLOCK_SIZE);
+	}
+
+	return data_length;
+}
+
+static inline uint32_t tcmu_cmd_get_block_cnt(struct tcmu_cmd *tcmu_cmd)
+{
+	size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
+
+	return data_length / DATA_BLOCK_SIZE;
+}
+
 static sense_reason_t
 tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 {
@@ -403,7 +454,7 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 	uint32_t cmd_head;
 	uint64_t cdb_off;
 	bool copy_to_data_area;
-	size_t data_length;
+	size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
 	DECLARE_BITMAP(old_bitmap, DATA_BLOCK_BITS);
 
 	if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
@@ -417,8 +468,7 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 	 * expensive to tell how many regions are freed in the bitmap
 	*/
 	base_command_size = max(offsetof(struct tcmu_cmd_entry,
-				req.iov[se_cmd->t_bidi_data_nents +
-					se_cmd->t_data_nents]),
+				req.iov[tcmu_cmd_get_block_cnt(tcmu_cmd)]),
 				sizeof(struct tcmu_cmd_entry));
 	command_size = base_command_size
 		+ round_up(scsi_command_size(se_cmd->t_task_cdb), TCMU_OP_ALIGN_SIZE);
@@ -429,11 +479,6 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 
 	mb = udev->mb_addr;
 	cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */
-	data_length = se_cmd->data_length;
-	if (se_cmd->se_cmd_flags & SCF_BIDI) {
-		BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
-		data_length += se_cmd->t_bidi_data_sg->length;
-	}
 	if ((command_size > (udev->cmdr_size / 2)) ||
 	    data_length > udev->data_size) {
 		pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu "
@@ -451,7 +496,11 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 
 		pr_debug("sleeping for ring space\n");
 		spin_unlock_irq(&udev->cmdr_lock);
-		ret = schedule_timeout(msecs_to_jiffies(TCMU_TIME_OUT));
+		if (udev->cmd_time_out)
+			ret = schedule_timeout(
+					msecs_to_jiffies(udev->cmd_time_out));
+		else
+			ret = schedule_timeout(msecs_to_jiffies(TCMU_TIME_OUT));
 		finish_wait(&udev->wait_cmdr, &__wait);
 		if (!ret) {
 			pr_warn("tcmu: command timed out\n");
@@ -503,11 +552,14 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 	entry->req.iov_dif_cnt = 0;
 
 	/* Handle BIDI commands */
-	iov_cnt = 0;
-	alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
-		se_cmd->t_bidi_data_nents, &iov, &iov_cnt, false);
-	entry->req.iov_bidi_cnt = iov_cnt;
-
+	if (se_cmd->se_cmd_flags & SCF_BIDI) {
+		iov_cnt = 0;
+		iov++;
+		alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
+				se_cmd->t_bidi_data_nents, &iov, &iov_cnt,
+				false);
+		entry->req.iov_bidi_cnt = iov_cnt;
+	}
 	/* cmd's data_bitmap is what changed in process */
 	bitmap_xor(tcmu_cmd->data_bitmap, old_bitmap, udev->data_bitmap,
 			DATA_BLOCK_BITS);
@@ -526,8 +578,9 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 	/* TODO: only if FLUSH and FUA? */
 	uio_event_notify(&udev->uio_info);
 
-	mod_timer(&udev->timeout,
-		round_jiffies_up(jiffies + msecs_to_jiffies(TCMU_TIME_OUT)));
+	if (udev->cmd_time_out)
+		mod_timer(&udev->timeout, round_jiffies_up(jiffies +
+			  msecs_to_jiffies(udev->cmd_time_out)));
 
 	return TCM_NO_SENSE;
 }
@@ -583,19 +636,11 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *
 			       se_cmd->scsi_sense_length);
 		free_data_area(udev, cmd);
 	} else if (se_cmd->se_cmd_flags & SCF_BIDI) {
-		DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
-
 		/* Get Data-In buffer before clean up */
-		bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
-		gather_data_area(udev, bitmap,
-			se_cmd->t_bidi_data_sg, se_cmd->t_bidi_data_nents);
+		gather_data_area(udev, cmd, true);
 		free_data_area(udev, cmd);
 	} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
-		DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
-
-		bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
-		gather_data_area(udev, bitmap,
-			se_cmd->t_data_sg, se_cmd->t_data_nents);
+		gather_data_area(udev, cmd, false);
 		free_data_area(udev, cmd);
 	} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
 		free_data_area(udev, cmd);
@@ -742,6 +787,7 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	}
 
 	udev->hba = hba;
+	udev->cmd_time_out = TCMU_TIME_OUT;
 
 	init_waitqueue_head(&udev->wait_cmdr);
 	spin_lock_init(&udev->cmdr_lock);
@@ -960,7 +1006,8 @@ static int tcmu_configure_device(struct se_device *dev)
 	if (dev->dev_attrib.hw_block_size == 0)
 		dev->dev_attrib.hw_block_size = 512;
 	/* Other attributes can be configured in userspace */
-	dev->dev_attrib.hw_max_sectors = 128;
+	if (!dev->dev_attrib.hw_max_sectors)
+		dev->dev_attrib.hw_max_sectors = 128;
 	dev->dev_attrib.hw_queue_depth = 128;
 
 	ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name,
@@ -997,6 +1044,11 @@ static void tcmu_dev_call_rcu(struct rcu_head *p)
 	kfree(udev);
 }
 
+static bool tcmu_dev_configured(struct tcmu_dev *udev)
+{
+	return udev->uio_info.uio_dev ? true : false;
+}
+
 static void tcmu_free_device(struct se_device *dev)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
@@ -1018,8 +1070,7 @@ static void tcmu_free_device(struct se_device *dev)
 	spin_unlock_irq(&udev->commands_lock);
 	WARN_ON(!all_expired);
 
-	/* Device was configured */
-	if (udev->uio_info.uio_dev) {
+	if (tcmu_dev_configured(udev)) {
 		tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name,
 				   udev->uio_info.uio_dev->minor);
 
@@ -1031,16 +1082,42 @@ static void tcmu_free_device(struct se_device *dev)
 }
 
 enum {
-	Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_err,
+	Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_hw_max_sectors,
+	Opt_err,
 };
 
 static match_table_t tokens = {
 	{Opt_dev_config, "dev_config=%s"},
 	{Opt_dev_size, "dev_size=%u"},
 	{Opt_hw_block_size, "hw_block_size=%u"},
+	{Opt_hw_max_sectors, "hw_max_sectors=%u"},
 	{Opt_err, NULL}
 };
 
+static int tcmu_set_dev_attrib(substring_t *arg, u32 *dev_attrib)
+{
+	unsigned long tmp_ul;
+	char *arg_p;
+	int ret;
+
+	arg_p = match_strdup(arg);
+	if (!arg_p)
+		return -ENOMEM;
+
+	ret = kstrtoul(arg_p, 0, &tmp_ul);
+	kfree(arg_p);
+	if (ret < 0) {
+		pr_err("kstrtoul() failed for dev attrib\n");
+		return ret;
+	}
+	if (!tmp_ul) {
+		pr_err("dev attrib must be nonzero\n");
+		return -EINVAL;
+	}
+	*dev_attrib = tmp_ul;
+	return 0;
+}
+
 static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 		const char *page, ssize_t count)
 {
@@ -1048,7 +1125,6 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 	char *orig, *ptr, *opts, *arg_p;
 	substring_t args[MAX_OPT_ARGS];
 	int ret = 0, token;
-	unsigned long tmp_ul;
 
 	opts = kstrdup(page, GFP_KERNEL);
 	if (!opts)
@@ -1082,26 +1158,19 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 				pr_err("kstrtoul() failed for dev_size=\n");
 			break;
 		case Opt_hw_block_size:
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoul(arg_p, 0, &tmp_ul);
-			kfree(arg_p);
-			if (ret < 0) {
-				pr_err("kstrtoul() failed for hw_block_size=\n");
-				break;
-			}
-			if (!tmp_ul) {
-				pr_err("hw_block_size must be nonzero\n");
-				break;
-			}
-			dev->dev_attrib.hw_block_size = tmp_ul;
+			ret = tcmu_set_dev_attrib(&args[0],
+					&(dev->dev_attrib.hw_block_size));
+			break;
+		case Opt_hw_max_sectors:
+			ret = tcmu_set_dev_attrib(&args[0],
+					&(dev->dev_attrib.hw_max_sectors));
 			break;
 		default:
 			break;
 		}
+
+		if (ret)
+			break;
 	}
 
 	kfree(orig);
@@ -1134,7 +1203,43 @@ tcmu_parse_cdb(struct se_cmd *cmd)
 	return passthrough_parse_cdb(cmd, tcmu_queue_cmd);
 }
 
-static const struct target_backend_ops tcmu_ops = {
+static ssize_t tcmu_cmd_time_out_show(struct config_item *item, char *page)
+{
+	struct se_dev_attrib *da = container_of(to_config_group(item),
+					struct se_dev_attrib, da_group);
+	struct tcmu_dev *udev = container_of(da->da_dev,
+					struct tcmu_dev, se_dev);
+
+	return snprintf(page, PAGE_SIZE, "%lu\n", udev->cmd_time_out / MSEC_PER_SEC);
+}
+
+static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *page,
+				       size_t count)
+{
+	struct se_dev_attrib *da = container_of(to_config_group(item),
+					struct se_dev_attrib, da_group);
+	struct tcmu_dev *udev = container_of(da->da_dev,
+					struct tcmu_dev, se_dev);
+	u32 val;
+	int ret;
+
+	if (da->da_dev->export_count) {
+		pr_err("Unable to set tcmu cmd_time_out while exports exist\n");
+		return -EINVAL;
+	}
+
+	ret = kstrtou32(page, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	udev->cmd_time_out = val * MSEC_PER_SEC;
+	return count;
+}
+CONFIGFS_ATTR(tcmu_, cmd_time_out);
+
+static struct configfs_attribute **tcmu_attrs;
+
+static struct target_backend_ops tcmu_ops = {
 	.name			= "user",
 	.owner			= THIS_MODULE,
 	.transport_flags	= TRANSPORT_FLAG_PASSTHROUGH,
@@ -1148,12 +1253,12 @@ static const struct target_backend_ops tcmu_ops = {
 	.show_configfs_dev_params = tcmu_show_configfs_dev_params,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= tcmu_get_blocks,
-	.tb_dev_attrib_attrs	= passthrough_attrib_attrs,
+	.tb_dev_attrib_attrs	= NULL,
 };
 
 static int __init tcmu_module_init(void)
 {
-	int ret;
+	int ret, i, len = 0;
 
 	BUILD_BUG_ON((sizeof(struct tcmu_cmd_entry) % TCMU_OP_ALIGN_SIZE) != 0);
 
@@ -1175,12 +1280,31 @@ static int __init tcmu_module_init(void)
 		goto out_unreg_device;
 	}
 
+	for (i = 0; passthrough_attrib_attrs[i] != NULL; i++) {
+		len += sizeof(struct configfs_attribute *);
+	}
+	len += sizeof(struct configfs_attribute *) * 2;
+
+	tcmu_attrs = kzalloc(len, GFP_KERNEL);
+	if (!tcmu_attrs) {
+		ret = -ENOMEM;
+		goto out_unreg_genl;
+	}
+
+	for (i = 0; passthrough_attrib_attrs[i] != NULL; i++) {
+		tcmu_attrs[i] = passthrough_attrib_attrs[i];
+	}
+	tcmu_attrs[i] = &tcmu_attr_cmd_time_out;
+	tcmu_ops.tb_dev_attrib_attrs = tcmu_attrs;
+
 	ret = transport_backend_register(&tcmu_ops);
 	if (ret)
-		goto out_unreg_genl;
+		goto out_attrs;
 
 	return 0;
 
+out_attrs:
+	kfree(tcmu_attrs);
 out_unreg_genl:
 	genl_unregister_family(&tcmu_genl_family);
 out_unreg_device:
@@ -1194,6 +1318,7 @@ out_free_cache:
 static void __exit tcmu_module_exit(void)
 {
 	target_backend_unregister(&tcmu_ops);
+	kfree(tcmu_attrs);
 	genl_unregister_family(&tcmu_genl_family);
 	root_device_unregister(tcmu_root_device);
 	kmem_cache_destroy(tcmu_cmd_cache);
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 776b34396144..0a16cf4bed39 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -291,18 +291,6 @@ config ARMADA_THERMAL
 	  Enable this option if you want to have support for thermal management
 	  controller present in Armada 370 and Armada XP SoC.
 
-config DB8500_CPUFREQ_COOLING
-	tristate "DB8500 cpufreq cooling"
-	depends on ARCH_U8500 || COMPILE_TEST
-	depends on HAS_IOMEM
-	depends on CPU_THERMAL
-	default y
-	help
-	  Adds DB8500 cpufreq cooling devices, and these cooling devices can be
-	  bound to thermal zone trip points. When a trip point reached, the
-	  bound cpufreq cooling device turns active to set CPU frequency low to
-	  cool down the CPU.
-
 config INTEL_POWERCLAMP
 	tristate "Intel PowerClamp idle injection driver"
 	depends on THERMAL
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 7adae2029355..c2372f10dae5 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -41,7 +41,6 @@ obj-$(CONFIG_TANGO_THERMAL)	+= tango_thermal.o
 obj-$(CONFIG_IMX_THERMAL)	+= imx_thermal.o
 obj-$(CONFIG_MAX77620_THERMAL)	+= max77620_thermal.o
 obj-$(CONFIG_QORIQ_THERMAL)	+= qoriq_thermal.o
-obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
 obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
 obj-$(CONFIG_X86_PKG_TEMP_THERMAL)	+= x86_pkg_temp_thermal.o
 obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE)	+= intel_soc_dts_iosf.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 91048eeca28b..69d0f430b2d1 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -107,8 +107,6 @@ struct cpufreq_cooling_device {
 };
 static DEFINE_IDA(cpufreq_ida);
 
-static unsigned int cpufreq_dev_count;
-
 static DEFINE_MUTEX(cooling_list_lock);
 static LIST_HEAD(cpufreq_dev_list);
 
@@ -395,13 +393,20 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
 
 	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
 					 true);
+	if (IS_ERR(opp)) {
+		dev_warn_ratelimited(cpufreq_device->cpu_dev,
+				     "Failed to find OPP for frequency %lu: %ld\n",
+				     freq_hz, PTR_ERR(opp));
+		return -EINVAL;
+	}
+
 	voltage = dev_pm_opp_get_voltage(opp);
 	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
-		dev_warn_ratelimited(cpufreq_device->cpu_dev,
-				     "Failed to get voltage for frequency %lu: %ld\n",
-				     freq_hz, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		dev_err_ratelimited(cpufreq_device->cpu_dev,
+				    "Failed to get voltage for frequency %lu\n",
+				    freq_hz);
 		return -EINVAL;
 	}
 
@@ -693,9 +698,9 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
 
 	*state = cpufreq_cooling_get_level(cpu, target_freq);
 	if (*state == THERMAL_CSTATE_INVALID) {
-		dev_warn_ratelimited(&cdev->device,
-				     "Failed to convert %dKHz for cpu %d into a cdev state\n",
-				     target_freq, cpu);
+		dev_err_ratelimited(&cdev->device,
+				    "Failed to convert %dKHz for cpu %d into a cdev state\n",
+				    target_freq, cpu);
 		return -EINVAL;
 	}
 
@@ -771,6 +776,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	unsigned int freq, i, num_cpus;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
+	bool first;
 
 	if (!alloc_cpumask_var(&temp_mask, GFP_KERNEL))
 		return ERR_PTR(-ENOMEM);
@@ -874,13 +880,14 @@ __cpufreq_cooling_register(struct device_node *np,
 	cpufreq_dev->cool_dev = cool_dev;
 
 	mutex_lock(&cooling_list_lock);
+	/* Register the notifier for first cpufreq cooling device */
+	first = list_empty(&cpufreq_dev_list);
 	list_add(&cpufreq_dev->node, &cpufreq_dev_list);
+	mutex_unlock(&cooling_list_lock);
 
-	/* Register the notifier for first cpufreq cooling device */
-	if (!cpufreq_dev_count++)
+	if (first)
 		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
 					  CPUFREQ_POLICY_NOTIFIER);
-	mutex_unlock(&cooling_list_lock);
 
 	goto put_policy;
 
@@ -1021,6 +1028,7 @@ EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
 	struct cpufreq_cooling_device *cpufreq_dev;
+	bool last;
 
 	if (!cdev)
 		return;
@@ -1028,14 +1036,15 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	cpufreq_dev = cdev->devdata;
 
 	mutex_lock(&cooling_list_lock);
+	list_del(&cpufreq_dev->node);
 	/* Unregister the notifier for the last cpufreq cooling device */
-	if (!--cpufreq_dev_count)
+	last = list_empty(&cpufreq_dev_list);
+	mutex_unlock(&cooling_list_lock);
+
+	if (last)
 		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
 					    CPUFREQ_POLICY_NOTIFIER);
 
-	list_del(&cpufreq_dev->node);
-	mutex_unlock(&cooling_list_lock);
-
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	ida_simple_remove(&cpufreq_ida, cpufreq_dev->id);
 	kfree(cpufreq_dev->dyn_power_table);
diff --git a/drivers/thermal/db8500_cpufreq_cooling.c b/drivers/thermal/db8500_cpufreq_cooling.c
deleted file mode 100644
index e58bd0b658b5..000000000000
--- a/drivers/thermal/db8500_cpufreq_cooling.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * db8500_cpufreq_cooling.c - DB8500 cpufreq works as cooling device.
- *
- * Copyright (C) 2012 ST-Ericsson
- * Copyright (C) 2012 Linaro Ltd.
- *
- * Author: Hongbo Zhang <hongbo.zhang@linaro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/cpu_cooling.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-static int db8500_cpufreq_cooling_probe(struct platform_device *pdev)
-{
-	struct thermal_cooling_device *cdev;
-
-	cdev = cpufreq_cooling_register(cpu_present_mask);
-	if (IS_ERR(cdev)) {
-		int ret = PTR_ERR(cdev);
-
-		if (ret != -EPROBE_DEFER)
-			dev_err(&pdev->dev,
-				"Failed to register cooling device %d\n",
-				ret);
-				
-		return ret;
-	}
-
-	platform_set_drvdata(pdev, cdev);
-
-	dev_info(&pdev->dev, "Cooling device registered: %s\n",	cdev->type);
-
-	return 0;
-}
-
-static int db8500_cpufreq_cooling_remove(struct platform_device *pdev)
-{
-	struct thermal_cooling_device *cdev = platform_get_drvdata(pdev);
-
-	cpufreq_cooling_unregister(cdev);
-
-	return 0;
-}
-
-static int db8500_cpufreq_cooling_suspend(struct platform_device *pdev,
-		pm_message_t state)
-{
-	return -ENOSYS;
-}
-
-static int db8500_cpufreq_cooling_resume(struct platform_device *pdev)
-{
-	return -ENOSYS;
-}
-
-#ifdef CONFIG_OF
-static const struct of_device_id db8500_cpufreq_cooling_match[] = {
-	{ .compatible = "stericsson,db8500-cpufreq-cooling" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, db8500_cpufreq_cooling_match);
-#endif
-
-static struct platform_driver db8500_cpufreq_cooling_driver = {
-	.driver = {
-		.name = "db8500-cpufreq-cooling",
-		.of_match_table = of_match_ptr(db8500_cpufreq_cooling_match),
-	},
-	.probe = db8500_cpufreq_cooling_probe,
-	.suspend = db8500_cpufreq_cooling_suspend,
-	.resume = db8500_cpufreq_cooling_resume,
-	.remove = db8500_cpufreq_cooling_remove,
-};
-
-static int __init db8500_cpufreq_cooling_init(void)
-{
-	return platform_driver_register(&db8500_cpufreq_cooling_driver);
-}
-
-static void __exit db8500_cpufreq_cooling_exit(void)
-{
-	platform_driver_unregister(&db8500_cpufreq_cooling_driver);
-}
-
-/* Should be later than db8500_cpufreq_register */
-late_initcall(db8500_cpufreq_cooling_init);
-module_exit(db8500_cpufreq_cooling_exit);
-
-MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>");
-MODULE_DESCRIPTION("DB8500 cpufreq cooling driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 7743a78d4723..4bf4ad58cffd 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -186,16 +186,22 @@ get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
 		return 0;
 
 	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
-	if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
+	if (PTR_ERR(opp) == -ERANGE)
 		opp = dev_pm_opp_find_freq_exact(dev, freq, false);
 
+	if (IS_ERR(opp)) {
+		dev_err_ratelimited(dev, "Failed to find OPP for frequency %lu: %ld\n",
+				    freq, PTR_ERR(opp));
+		return 0;
+	}
+
 	voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
 	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
-		dev_warn_ratelimited(dev,
-				     "Failed to get voltage for frequency %lu: %ld\n",
-				     freq, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		dev_err_ratelimited(dev,
+				    "Failed to get voltage for frequency %lu\n",
+				    freq);
 		return 0;
 	}
 
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index 1bacbc3b19a0..e94aea8c0d05 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -114,7 +114,7 @@
 #define DEFAULT_TX_BUF_COUNT 3
 
 struct n_hdlc_buf {
-	struct n_hdlc_buf *link;
+	struct list_head  list_item;
 	int		  count;
 	char		  buf[1];
 };
@@ -122,8 +122,7 @@ struct n_hdlc_buf {
 #define	N_HDLC_BUF_SIZE	(sizeof(struct n_hdlc_buf) + maxframe)
 
 struct n_hdlc_buf_list {
-	struct n_hdlc_buf *head;
-	struct n_hdlc_buf *tail;
+	struct list_head  list;
 	int		  count;
 	spinlock_t	  spinlock;
 };
@@ -136,7 +135,6 @@ struct n_hdlc_buf_list {
  * @backup_tty - TTY to use if tty gets closed
  * @tbusy - reentrancy flag for tx wakeup code
  * @woke_up - FIXME: describe this field
- * @tbuf - currently transmitting tx buffer
  * @tx_buf_list - list of pending transmit frame buffers
  * @rx_buf_list - list of received frame buffers
  * @tx_free_buf_list - list unused transmit frame buffers
@@ -149,7 +147,6 @@ struct n_hdlc {
 	struct tty_struct	*backup_tty;
 	int			tbusy;
 	int			woke_up;
-	struct n_hdlc_buf	*tbuf;
 	struct n_hdlc_buf_list	tx_buf_list;
 	struct n_hdlc_buf_list	rx_buf_list;
 	struct n_hdlc_buf_list	tx_free_buf_list;
@@ -159,6 +156,8 @@ struct n_hdlc {
 /*
  * HDLC buffer list manipulation functions
  */
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+						struct n_hdlc_buf *buf);
 static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
 			   struct n_hdlc_buf *buf);
 static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list);
@@ -208,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty)
 {
 	struct n_hdlc *n_hdlc = tty2n_hdlc(tty);
 	struct n_hdlc_buf *buf;
-	unsigned long flags;
 
 	while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list)))
 		n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf);
- 	spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags);
-	if (n_hdlc->tbuf) {
-		n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf);
-		n_hdlc->tbuf = NULL;
-	}
-	spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
 }
 
 static struct tty_ldisc_ops n_hdlc_ldisc = {
@@ -283,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc)
 		} else
 			break;
 	}
-	kfree(n_hdlc->tbuf);
 	kfree(n_hdlc);
 	
 }	/* end of n_hdlc_release() */
@@ -402,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 	n_hdlc->woke_up = 0;
 	spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
 
-	/* get current transmit buffer or get new transmit */
-	/* buffer from list of pending transmit buffers */
-		
-	tbuf = n_hdlc->tbuf;
-	if (!tbuf)
-		tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
-		
+	tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
 	while (tbuf) {
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d)sending frame %p, count=%d\n",
@@ -420,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 
 		/* rollback was possible and has been done */
 		if (actual == -ERESTARTSYS) {
-			n_hdlc->tbuf = tbuf;
+			n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
 			break;
 		}
 		/* if transmit error, throw frame away by */
@@ -435,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 					
 			/* free current transmit buffer */
 			n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf);
-			
-			/* this tx buffer is done */
-			n_hdlc->tbuf = NULL;
-			
+
 			/* wait up sleeping writers */
 			wake_up_interruptible(&tty->write_wait);
 	
@@ -448,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 			if (debuglevel >= DEBUG_LEVEL_INFO)	
 				printk("%s(%d)frame %p pending\n",
 					__FILE__,__LINE__,tbuf);
-					
-			/* buffer not accepted by driver */
-			/* set this buffer as pending buffer */
-			n_hdlc->tbuf = tbuf;
+
+			/*
+			 * the buffer was not accepted by driver,
+			 * return it back into tx queue
+			 */
+			n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
 			break;
 		}
 	}
@@ -749,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 	int error = 0;
 	int count;
 	unsigned long flags;
-	
+	struct n_hdlc_buf *buf = NULL;
+
 	if (debuglevel >= DEBUG_LEVEL_INFO)	
 		printk("%s(%d)n_hdlc_tty_ioctl() called %d\n",
 			__FILE__,__LINE__,cmd);
@@ -763,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		/* report count of read data available */
 		/* in next available frame (if any) */
 		spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags);
-		if (n_hdlc->rx_buf_list.head)
-			count = n_hdlc->rx_buf_list.head->count;
+		buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list,
+						struct n_hdlc_buf, list_item);
+		if (buf)
+			count = buf->count;
 		else
 			count = 0;
 		spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags);
@@ -776,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		count = tty_chars_in_buffer(tty);
 		/* add size of next output frame in queue */
 		spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags);
-		if (n_hdlc->tx_buf_list.head)
-			count += n_hdlc->tx_buf_list.head->count;
+		buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list,
+						struct n_hdlc_buf, list_item);
+		if (buf)
+			count += buf->count;
 		spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags);
 		error = put_user(count, (int __user *)arg);
 		break;
@@ -825,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
 		poll_wait(filp, &tty->write_wait, wait);
 
 		/* set bits for operations that won't block */
-		if (n_hdlc->rx_buf_list.head)
+		if (!list_empty(&n_hdlc->rx_buf_list.list))
 			mask |= POLLIN | POLLRDNORM;	/* readable */
 		if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
 			mask |= POLLHUP;
 		if (tty_hung_up_p(filp))
 			mask |= POLLHUP;
 		if (!tty_is_writelocked(tty) &&
-				n_hdlc->tx_free_buf_list.head)
+				!list_empty(&n_hdlc->tx_free_buf_list.list))
 			mask |= POLLOUT | POLLWRNORM;	/* writable */
 	}
 	return mask;
@@ -856,7 +845,12 @@ static struct n_hdlc *n_hdlc_alloc(void)
 	spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock);
 	spin_lock_init(&n_hdlc->rx_buf_list.spinlock);
 	spin_lock_init(&n_hdlc->tx_buf_list.spinlock);
-	
+
+	INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list);
+
 	/* allocate free rx buffer list */
 	for(i=0;i<DEFAULT_RX_BUF_COUNT;i++) {
 		buf = kmalloc(N_HDLC_BUF_SIZE, GFP_KERNEL);
@@ -884,53 +878,65 @@ static struct n_hdlc *n_hdlc_alloc(void)
 }	/* end of n_hdlc_alloc() */
 
 /**
+ * n_hdlc_buf_return - put the HDLC buffer after the head of the specified list
+ * @buf_list - pointer to the buffer list
+ * @buf - pointer to the buffer
+ */
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+						struct n_hdlc_buf *buf)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	list_add(&buf->list_item, &buf_list->list);
+	buf_list->count++;
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
+}
+
+/**
  * n_hdlc_buf_put - add specified HDLC buffer to tail of specified list
- * @list - pointer to buffer list
+ * @buf_list - pointer to buffer list
  * @buf	- pointer to buffer
  */
-static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
+static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list,
 			   struct n_hdlc_buf *buf)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&list->spinlock,flags);
-	
-	buf->link=NULL;
-	if (list->tail)
-		list->tail->link = buf;
-	else
-		list->head = buf;
-	list->tail = buf;
-	(list->count)++;
-	
-	spin_unlock_irqrestore(&list->spinlock,flags);
-	
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	list_add_tail(&buf->list_item, &buf_list->list);
+	buf_list->count++;
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
 }	/* end of n_hdlc_buf_put() */
 
 /**
  * n_hdlc_buf_get - remove and return an HDLC buffer from list
- * @list - pointer to HDLC buffer list
+ * @buf_list - pointer to HDLC buffer list
  * 
  * Remove and return an HDLC buffer from the head of the specified HDLC buffer
  * list.
  * Returns a pointer to HDLC buffer if available, otherwise %NULL.
  */
-static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list)
+static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list)
 {
 	unsigned long flags;
 	struct n_hdlc_buf *buf;
-	spin_lock_irqsave(&list->spinlock,flags);
-	
-	buf = list->head;
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	buf = list_first_entry_or_null(&buf_list->list,
+						struct n_hdlc_buf, list_item);
 	if (buf) {
-		list->head = buf->link;
-		(list->count)--;
+		list_del(&buf->list_item);
+		buf_list->count--;
 	}
-	if (!list->head)
-		list->tail = NULL;
-	
-	spin_unlock_irqrestore(&list->spinlock,flags);
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
 	return buf;
-	
 }	/* end of n_hdlc_buf_get() */
 
 static char hdlc_banner[] __initdata =
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index f4c6c90add78..1e1cbae3a0ea 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -173,6 +173,39 @@ void serdev_device_set_flow_control(struct serdev_device *serdev, bool enable)
 }
 EXPORT_SYMBOL_GPL(serdev_device_set_flow_control);
 
+void serdev_device_wait_until_sent(struct serdev_device *serdev, long timeout)
+{
+	struct serdev_controller *ctrl = serdev->ctrl;
+
+	if (!ctrl || !ctrl->ops->wait_until_sent)
+		return;
+
+	ctrl->ops->wait_until_sent(ctrl, timeout);
+}
+EXPORT_SYMBOL_GPL(serdev_device_wait_until_sent);
+
+int serdev_device_get_tiocm(struct serdev_device *serdev)
+{
+	struct serdev_controller *ctrl = serdev->ctrl;
+
+	if (!ctrl || !ctrl->ops->get_tiocm)
+		return -ENOTSUPP;
+
+	return ctrl->ops->get_tiocm(ctrl);
+}
+EXPORT_SYMBOL_GPL(serdev_device_get_tiocm);
+
+int serdev_device_set_tiocm(struct serdev_device *serdev, int set, int clear)
+{
+	struct serdev_controller *ctrl = serdev->ctrl;
+
+	if (!ctrl || !ctrl->ops->set_tiocm)
+		return -ENOTSUPP;
+
+	return ctrl->ops->set_tiocm(ctrl, set, clear);
+}
+EXPORT_SYMBOL_GPL(serdev_device_set_tiocm);
+
 static int serdev_drv_probe(struct device *dev)
 {
 	const struct serdev_device_driver *sdrv = to_serdev_device_driver(dev->driver);
diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index d05393594f15..487c88f6aa0e 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -14,6 +14,7 @@
 #include <linux/serdev.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
+#include <linux/poll.h>
 
 #define SERPORT_ACTIVE		1
 
@@ -46,11 +47,11 @@ static void ttyport_write_wakeup(struct tty_port *port)
 	struct serdev_controller *ctrl = port->client_data;
 	struct serport *serport = serdev_controller_get_drvdata(ctrl);
 
-	if (!test_and_clear_bit(TTY_DO_WRITE_WAKEUP, &port->tty->flags))
-		return;
-
-	if (test_bit(SERPORT_ACTIVE, &serport->flags))
+	if (test_and_clear_bit(TTY_DO_WRITE_WAKEUP, &port->tty->flags) &&
+	    test_bit(SERPORT_ACTIVE, &serport->flags))
 		serdev_controller_write_wakeup(ctrl);
+
+	wake_up_interruptible_poll(&port->tty->write_wait, POLLOUT);
 }
 
 static const struct tty_port_client_operations client_ops = {
@@ -167,6 +168,36 @@ static void ttyport_set_flow_control(struct serdev_controller *ctrl, bool enable
 	tty_set_termios(tty, &ktermios);
 }
 
+static void ttyport_wait_until_sent(struct serdev_controller *ctrl, long timeout)
+{
+	struct serport *serport = serdev_controller_get_drvdata(ctrl);
+	struct tty_struct *tty = serport->tty;
+
+	tty_wait_until_sent(tty, timeout);
+}
+
+static int ttyport_get_tiocm(struct serdev_controller *ctrl)
+{
+	struct serport *serport = serdev_controller_get_drvdata(ctrl);
+	struct tty_struct *tty = serport->tty;
+
+	if (!tty->ops->tiocmget)
+		return -ENOTSUPP;
+
+	return tty->driver->ops->tiocmget(tty);
+}
+
+static int ttyport_set_tiocm(struct serdev_controller *ctrl, unsigned int set, unsigned int clear)
+{
+	struct serport *serport = serdev_controller_get_drvdata(ctrl);
+	struct tty_struct *tty = serport->tty;
+
+	if (!tty->ops->tiocmset)
+		return -ENOTSUPP;
+
+	return tty->driver->ops->tiocmset(tty, set, clear);
+}
+
 static const struct serdev_controller_ops ctrl_ops = {
 	.write_buf = ttyport_write_buf,
 	.write_flush = ttyport_write_flush,
@@ -175,6 +206,9 @@ static const struct serdev_controller_ops ctrl_ops = {
 	.close = ttyport_close,
 	.set_flow_control = ttyport_set_flow_control,
 	.set_baudrate = ttyport_set_baudrate,
+	.wait_until_sent = ttyport_wait_until_sent,
+	.get_tiocm = ttyport_get_tiocm,
+	.set_tiocm = ttyport_set_tiocm,
 };
 
 struct device *serdev_tty_port_register(struct tty_port *port,
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 6ee55a2d47bb..e65808c482f1 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -257,7 +257,7 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
 {
 	unsigned int baud = tty_termios_baud_rate(termios);
 	struct dw8250_data *d = p->private_data;
-	unsigned int rate;
+	long rate;
 	int ret;
 
 	if (IS_ERR(d->clk) || !old)
@@ -265,7 +265,12 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
 
 	clk_disable_unprepare(d->clk);
 	rate = clk_round_rate(d->clk, baud * 16);
-	ret = clk_set_rate(d->clk, rate);
+	if (rate < 0)
+		ret = rate;
+	else if (rate == 0)
+		ret = -ENOENT;
+	else
+		ret = clk_set_rate(d->clk, rate);
 	clk_prepare_enable(d->clk);
 
 	if (!ret)
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index a65fb8197aec..0e3f529d50e9 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -128,9 +128,13 @@ config SERIAL_8250_PCI
 	  by the parport_serial driver, enabled with CONFIG_PARPORT_SERIAL.
 
 config SERIAL_8250_EXAR
-        tristate "8250/16550 PCI device support"
-        depends on SERIAL_8250_PCI
+	tristate "8250/16550 Exar/Commtech PCI/PCIe device support"
+	depends on SERIAL_8250_PCI
 	default SERIAL_8250
+	help
+	  This builds support for XR17C1xx, XR17V3xx and some Commtech
+	  422x PCIe serial cards that are not covered by the more generic
+	  SERIAL_8250_PCI option.
 
 config SERIAL_8250_HP300
 	tristate
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 8789ea423ccf..b0a377725d63 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2373,7 +2373,7 @@ static int __init pl011_console_match(struct console *co, char *name, int idx,
 	if (strcmp(name, "qdf2400_e44") == 0) {
 		pr_info_once("UART: Working around QDF2400 SoC erratum 44");
 		qdf2400_e44_present = true;
-	} else if (strcmp(name, "pl011") != 0 || strcmp(name, "ttyAMA") != 0) {
+	} else if (strcmp(name, "pl011") != 0) {
 		return -ENODEV;
 	}
 
@@ -2452,18 +2452,37 @@ static void pl011_early_write(struct console *con, const char *s, unsigned n)
 	uart_console_write(&dev->port, s, n, pl011_putc);
 }
 
+/*
+ * On non-ACPI systems, earlycon is enabled by specifying
+ * "earlycon=pl011,<address>" on the kernel command line.
+ *
+ * On ACPI ARM64 systems, an "early" console is enabled via the SPCR table,
+ * by specifying only "earlycon" on the command line.  Because it requires
+ * SPCR, the console starts after ACPI is parsed, which is later than a
+ * traditional early console.
+ *
+ * To get the traditional early console that starts before ACPI is parsed,
+ * specify the full "earlycon=pl011,<address>" option.
+ */
 static int __init pl011_early_console_setup(struct earlycon_device *device,
 					    const char *opt)
 {
 	if (!device->port.membase)
 		return -ENODEV;
 
-	device->con->write = qdf2400_e44_present ?
-				qdf2400_e44_early_write : pl011_early_write;
+	/* On QDF2400 SOCs affected by Erratum 44, the "qdf2400_e44" must
+	 * also be specified, e.g. "earlycon=pl011,<address>,qdf2400_e44".
+	 */
+	if (!strcmp(device->options, "qdf2400_e44"))
+		device->con->write = qdf2400_e44_early_write;
+	else
+		device->con->write = pl011_early_write;
+
 	return 0;
 }
 OF_EARLYCON_DECLARE(pl011, "arm,pl011", pl011_early_console_setup);
 OF_EARLYCON_DECLARE(pl011, "arm,sbsa-uart", pl011_early_console_setup);
+EARLYCON_DECLARE(qdf2400_e44, pl011_early_console_setup);
 
 #else
 #define AMBA_CONSOLE	NULL
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index dcebb28ffbc4..1f50a83ef958 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1951,6 +1951,11 @@ static void atmel_flush_buffer(struct uart_port *port)
 		atmel_uart_writel(port, ATMEL_PDC_TCR, 0);
 		atmel_port->pdc_tx.ofs = 0;
 	}
+	/*
+	 * in uart_flush_buffer(), the xmit circular buffer has just
+	 * been cleared, so we have to reset tx_len accordingly.
+	 */
+	atmel_port->tx_len = 0;
 }
 
 /*
@@ -2483,6 +2488,9 @@ static void atmel_console_write(struct console *co, const char *s, u_int count)
 	pdc_tx = atmel_uart_readl(port, ATMEL_PDC_PTSR) & ATMEL_PDC_TXTEN;
 	atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTDIS);
 
+	/* Make sure that tx path is actually able to send characters */
+	atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN);
+
 	uart_console_write(port, s, count, atmel_console_putchar);
 
 	/*
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 6989b227d134..be94246b6fcc 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -1088,7 +1088,7 @@ static void mxs_auart_settermios(struct uart_port *u,
 					AUART_LINECTRL_BAUD_DIV_MAX);
 		baud_max = u->uartclk * 32 / AUART_LINECTRL_BAUD_DIV_MIN;
 		baud = uart_get_baud_rate(u, termios, old, baud_min, baud_max);
-		div = u->uartclk * 32 / baud;
+		div = DIV_ROUND_CLOSEST(u->uartclk * 32, baud);
 	}
 
 	ctrl |= AUART_LINECTRL_BAUD_DIVFRAC(div & 0x3F);
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 6c6f82ad8d5c..a4734649a0f0 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1597,6 +1597,9 @@ static struct omap_uart_port_info *of_get_uart_port_info(struct device *dev)
 
 	of_property_read_u32(dev->of_node, "clock-frequency",
 					 &omap_up_info->uartclk);
+
+	omap_up_info->flags = UPF_BOOT_AUTOCONF;
+
 	return omap_up_info;
 }
 
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index b4f86c219db1..7a17aedbf902 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -1031,8 +1031,10 @@ static int s3c64xx_serial_startup(struct uart_port *port)
 	if (ourport->dma) {
 		ret = s3c24xx_serial_request_dma(ourport);
 		if (ret < 0) {
-			dev_warn(port->dev, "DMA request failed\n");
-			return ret;
+			dev_warn(port->dev,
+				 "DMA request failed, DMA will not be used\n");
+			devm_kfree(port->dev, ourport->dma);
+			ourport->dma = NULL;
 		}
 	}
 
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index bcf1d33e6ffe..c334bcc59c64 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -575,12 +575,13 @@ static void asc_set_termios(struct uart_port *port, struct ktermios *termios,
 			pinctrl_select_state(ascport->pinctrl,
 					     ascport->states[NO_HW_FLOWCTRL]);
 
-			gpiod =	devm_get_gpiod_from_child(port->dev, "rts",
-							  &np->fwnode);
-			if (!IS_ERR(gpiod)) {
-				gpiod_direction_output(gpiod, 0);
+			gpiod = devm_fwnode_get_gpiod_from_child(port->dev,
+								 "rts",
+								 &np->fwnode,
+								 GPIOD_OUT_LOW,
+								 np->name);
+			if (!IS_ERR(gpiod))
 				ascport->rts = gpiod;
-			}
 		}
 	}
 
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index c6fc7141d7b2..677f0ddc986c 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -446,7 +446,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
 	 */
 	NULL,				/* a */
 	&sysrq_reboot_op,		/* b */
-	&sysrq_crash_op,		/* c & ibm_emac driver debug */
+	&sysrq_crash_op,		/* c */
 	&sysrq_showlocks_op,		/* d */
 	&sysrq_term_op,			/* e */
 	&sysrq_moom_op,			/* f */
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 68947f6de5ad..e4603b09863a 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -271,10 +271,13 @@ const struct file_operations tty_ldiscs_proc_fops = {
 
 struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty)
 {
+	struct tty_ldisc *ld;
+
 	ldsem_down_read(&tty->ldisc_sem, MAX_SCHEDULE_TIMEOUT);
-	if (!tty->ldisc)
+	ld = tty->ldisc;
+	if (!ld)
 		ldsem_up_read(&tty->ldisc_sem);
-	return tty->ldisc;
+	return ld;
 }
 EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
 
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index c5f0fc906136..8af8d9542663 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
-#include <linux/sched/debug.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/mm.h>
diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile
index 7791af6c102c..53d1356bbd06 100644
--- a/drivers/usb/Makefile
+++ b/drivers/usb/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_USB_MICROTEK)	+= image/
 obj-$(CONFIG_USB_SERIAL)	+= serial/
 
 obj-$(CONFIG_USB)		+= misc/
-obj-$(CONFIG_EARLY_PRINTK_DBGP)	+= early/
+obj-$(CONFIG_EARLY_PRINTK_USB)	+= early/
 
 obj-$(CONFIG_USB_ATM)		+= atm/
 obj-$(CONFIG_USB_SPEEDTOUCH)	+= atm/
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index f03692ec5520..8fb309a0ff6b 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -1381,7 +1381,7 @@ static int usbtmc_probe(struct usb_interface *intf,
 
 	dev_dbg(&intf->dev, "%s called\n", __func__);
 
-	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
@@ -1444,6 +1444,13 @@ static int usbtmc_probe(struct usb_interface *intf,
 			break;
 		}
 	}
+
+	if (!data->bulk_out || !data->bulk_in) {
+		dev_err(&intf->dev, "bulk endpoints not found\n");
+		retcode = -ENODEV;
+		goto err_put;
+	}
+
 	/* Find int endpoint */
 	for (n = 0; n < iface_desc->desc.bNumEndpoints; n++) {
 		endpoint = &iface_desc->endpoint[n].desc;
@@ -1469,8 +1476,10 @@ static int usbtmc_probe(struct usb_interface *intf,
 	if (data->iin_ep_present) {
 		/* allocate int urb */
 		data->iin_urb = usb_alloc_urb(0, GFP_KERNEL);
-		if (!data->iin_urb)
+		if (!data->iin_urb) {
+			retcode = -ENOMEM;
 			goto error_register;
+		}
 
 		/* Protect interrupt in endpoint data until iin_urb is freed */
 		kref_get(&data->kref);
@@ -1478,8 +1487,10 @@ static int usbtmc_probe(struct usb_interface *intf,
 		/* allocate buffer for interrupt in */
 		data->iin_buffer = kmalloc(data->iin_wMaxPacketSize,
 					GFP_KERNEL);
-		if (!data->iin_buffer)
+		if (!data->iin_buffer) {
+			retcode = -ENOMEM;
 			goto error_register;
+		}
 
 		/* fill interrupt urb */
 		usb_fill_int_urb(data->iin_urb, data->usb_dev,
@@ -1512,6 +1523,7 @@ error_register:
 	sysfs_remove_group(&intf->dev.kobj, &capability_attr_grp);
 	sysfs_remove_group(&intf->dev.kobj, &data_attr_grp);
 	usbtmc_free_int(data);
+err_put:
 	kref_put(&data->kref, usbtmc_delete);
 	return retcode;
 }
diff --git a/drivers/usb/core/Kconfig b/drivers/usb/core/Kconfig
index 0e5a889742b3..4d75d9a80001 100644
--- a/drivers/usb/core/Kconfig
+++ b/drivers/usb/core/Kconfig
@@ -26,7 +26,7 @@ config USB_DEFAULT_PERSIST
 	  unplugged, causing any mounted filesystems to be lost.  The
 	  persist feature can still be enabled for individual devices
 	  through the power/persist sysfs node. See
-	  Documentation/usb/persist.txt for more info.
+	  Documentation/driver-api/usb/persist.rst for more info.
 
 	  If you have any questions about this, say Y here, only say N
 	  if you know exactly what you are doing.
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 25dbd8c7aec7..4be52c602e9b 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -280,6 +280,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 
 			/*
 			 * Adjust bInterval for quirked devices.
+			 */
+			/*
+			 * This quirk fixes bIntervals reported in ms.
+			 */
+			if (to_usb_device(ddev)->quirks &
+				USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
+				n = clamp(fls(d->bInterval) + 3, i, j);
+				i = j = n;
+			}
+			/*
 			 * This quirk fixes bIntervals reported in
 			 * linear microframes.
 			 */
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 612fab6e54fb..79bdca5cb9c7 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -520,8 +520,10 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
 	 */
 	tbuf_size =  max_t(u16, sizeof(struct usb_hub_descriptor), wLength);
 	tbuf = kzalloc(tbuf_size, GFP_KERNEL);
-	if (!tbuf)
-		return -ENOMEM;
+	if (!tbuf) {
+		status = -ENOMEM;
+		goto err_alloc;
+	}
 
 	bufp = tbuf;
 
@@ -734,6 +736,7 @@ error:
 	}
 
 	kfree(tbuf);
+ err_alloc:
 
 	/* any errors get returned through the urb completion */
 	spin_lock_irq(&hcd_root_hub_lock);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index f0dd08198d74..5286bf67869a 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4275,7 +4275,7 @@ static void hub_set_initial_usb2_lpm_policy(struct usb_device *udev)
 	struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
 	int connect_type = USB_PORT_CONNECT_TYPE_UNKNOWN;
 
-	if (!udev->usb2_hw_lpm_capable)
+	if (!udev->usb2_hw_lpm_capable || !udev->bos)
 		return;
 
 	if (hub)
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 2184ef40a82a..4c38ea41ae96 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -474,6 +474,7 @@ EXPORT_SYMBOL_GPL(usb_sg_init);
  * significantly improve USB throughput.
  *
  * There are three kinds of completion for this function.
+ *
  * (1) success, where io->status is zero.  The number of io->bytes
  *     transferred is as requested.
  * (2) error, where io->status is a negative errno value.  The number
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 24f9f98968a5..96b21b0dac1e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -170,6 +170,14 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* M-Systems Flash Disk Pioneers */
 	{ USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Baum Vario Ultra */
+	{ USB_DEVICE(0x0904, 0x6101), .driver_info =
+			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+	{ USB_DEVICE(0x0904, 0x6102), .driver_info =
+			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
+			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 2092e46b1380..f8d0747810e7 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -250,6 +250,7 @@ static void dwc3_omap_set_mailbox(struct dwc3_omap *omap,
 		val = dwc3_omap_read_utmi_ctrl(omap);
 		val |= USBOTGSS_UTMI_OTG_CTRL_IDDIG;
 		dwc3_omap_write_utmi_ctrl(omap, val);
+		break;
 
 	case OMAP_DWC3_VBUS_OFF:
 		val = dwc3_omap_read_utmi_ctrl(omap);
@@ -392,7 +393,7 @@ static void dwc3_omap_set_utmi_mode(struct dwc3_omap *omap)
 {
 	u32			reg;
 	struct device_node	*node = omap->dev->of_node;
-	int			utmi_mode = 0;
+	u32			utmi_mode = 0;
 
 	reg = dwc3_omap_read_utmi_ctrl(omap);
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4db97ecae885..79e7a3480d51 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -171,6 +171,7 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 		int status)
 {
 	struct dwc3			*dwc = dep->dwc;
+	unsigned int			unmap_after_complete = false;
 
 	req->started = false;
 	list_del(&req->list);
@@ -180,11 +181,19 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 	if (req->request.status == -EINPROGRESS)
 		req->request.status = status;
 
-	if (dwc->ep0_bounced && dep->number <= 1)
+	/*
+	 * NOTICE we don't want to unmap before calling ->complete() if we're
+	 * dealing with a bounced ep0 request. If we unmap it here, we would end
+	 * up overwritting the contents of req->buf and this could confuse the
+	 * gadget driver.
+	 */
+	if (dwc->ep0_bounced && dep->number <= 1) {
 		dwc->ep0_bounced = false;
-
-	usb_gadget_unmap_request_by_dev(dwc->sysdev,
-			&req->request, req->direction);
+		unmap_after_complete = true;
+	} else {
+		usb_gadget_unmap_request_by_dev(dwc->sysdev,
+				&req->request, req->direction);
+	}
 
 	trace_dwc3_gadget_giveback(req);
 
@@ -192,6 +201,10 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 	usb_gadget_giveback_request(&dep->endpoint, &req->request);
 	spin_lock(&dwc->lock);
 
+	if (unmap_after_complete)
+		usb_gadget_unmap_request_by_dev(dwc->sysdev,
+				&req->request, req->direction);
+
 	if (dep->number > 1)
 		pm_runtime_put(dwc->dev);
 }
@@ -1342,6 +1355,68 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 		if (r == req) {
 			/* wait until it is processed */
 			dwc3_stop_active_transfer(dwc, dep->number, true);
+
+			/*
+			 * If request was already started, this means we had to
+			 * stop the transfer. With that we also need to ignore
+			 * all TRBs used by the request, however TRBs can only
+			 * be modified after completion of END_TRANSFER
+			 * command. So what we do here is that we wait for
+			 * END_TRANSFER completion and only after that, we jump
+			 * over TRBs by clearing HWO and incrementing dequeue
+			 * pointer.
+			 *
+			 * Note that we have 2 possible types of transfers here:
+			 *
+			 * i) Linear buffer request
+			 * ii) SG-list based request
+			 *
+			 * SG-list based requests will have r->num_pending_sgs
+			 * set to a valid number (> 0). Linear requests,
+			 * normally use a single TRB.
+			 *
+			 * For each of these two cases, if r->unaligned flag is
+			 * set, one extra TRB has been used to align transfer
+			 * size to wMaxPacketSize.
+			 *
+			 * All of these cases need to be taken into
+			 * consideration so we don't mess up our TRB ring
+			 * pointers.
+			 */
+			wait_event_lock_irq(dep->wait_end_transfer,
+					!(dep->flags & DWC3_EP_END_TRANSFER_PENDING),
+					dwc->lock);
+
+			if (!r->trb)
+				goto out1;
+
+			if (r->num_pending_sgs) {
+				struct dwc3_trb *trb;
+				int i = 0;
+
+				for (i = 0; i < r->num_pending_sgs; i++) {
+					trb = r->trb + i;
+					trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+					dwc3_ep_inc_deq(dep);
+				}
+
+				if (r->unaligned) {
+					trb = r->trb + r->num_pending_sgs + 1;
+					trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+					dwc3_ep_inc_deq(dep);
+				}
+			} else {
+				struct dwc3_trb *trb = r->trb;
+
+				trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+				dwc3_ep_inc_deq(dep);
+
+				if (r->unaligned) {
+					trb = r->trb + 1;
+					trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+					dwc3_ep_inc_deq(dep);
+				}
+			}
 			goto out1;
 		}
 		dev_err(dwc->dev, "request %p was not queued to %s\n",
@@ -1352,6 +1427,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 
 out1:
 	/* giveback the request */
+	dep->queued_requests--;
 	dwc3_gadget_giveback(dep, req, -ECONNRESET);
 
 out0:
@@ -2126,12 +2202,12 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
 		return 1;
 	}
 
-	if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
-		return 1;
-
 	count = trb->size & DWC3_TRB_SIZE_MASK;
 	req->remaining += count;
 
+	if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
+		return 1;
+
 	if (dep->direction) {
 		if (count) {
 			trb_status = DWC3_TRB_SIZE_TRBSTS(trb->size);
@@ -3228,15 +3304,10 @@ void dwc3_gadget_exit(struct dwc3 *dwc)
 
 int dwc3_gadget_suspend(struct dwc3 *dwc)
 {
-	int ret;
-
 	if (!dwc->gadget_driver)
 		return 0;
 
-	ret = dwc3_gadget_run_stop(dwc, false, false);
-	if (ret < 0)
-		return ret;
-
+	dwc3_gadget_run_stop(dwc, false, false);
 	dwc3_disconnect_gadget(dwc);
 	__dwc3_gadget_stop(dwc);
 
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 3129bcf74d7d..265e223ab645 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -28,23 +28,23 @@ struct dwc3;
 #define gadget_to_dwc(g)	(container_of(g, struct dwc3, gadget))
 
 /* DEPCFG parameter 1 */
-#define DWC3_DEPCFG_INT_NUM(n)		((n) << 0)
+#define DWC3_DEPCFG_INT_NUM(n)		(((n) & 0x1f) << 0)
 #define DWC3_DEPCFG_XFER_COMPLETE_EN	(1 << 8)
 #define DWC3_DEPCFG_XFER_IN_PROGRESS_EN	(1 << 9)
 #define DWC3_DEPCFG_XFER_NOT_READY_EN	(1 << 10)
 #define DWC3_DEPCFG_FIFO_ERROR_EN	(1 << 11)
 #define DWC3_DEPCFG_STREAM_EVENT_EN	(1 << 13)
-#define DWC3_DEPCFG_BINTERVAL_M1(n)	((n) << 16)
+#define DWC3_DEPCFG_BINTERVAL_M1(n)	(((n) & 0xff) << 16)
 #define DWC3_DEPCFG_STREAM_CAPABLE	(1 << 24)
-#define DWC3_DEPCFG_EP_NUMBER(n)	((n) << 25)
+#define DWC3_DEPCFG_EP_NUMBER(n)	(((n) & 0x1f) << 25)
 #define DWC3_DEPCFG_BULK_BASED		(1 << 30)
 #define DWC3_DEPCFG_FIFO_BASED		(1 << 31)
 
 /* DEPCFG parameter 0 */
-#define DWC3_DEPCFG_EP_TYPE(n)		((n) << 1)
-#define DWC3_DEPCFG_MAX_PACKET_SIZE(n)	((n) << 3)
-#define DWC3_DEPCFG_FIFO_NUMBER(n)	((n) << 17)
-#define DWC3_DEPCFG_BURST_SIZE(n)	((n) << 22)
+#define DWC3_DEPCFG_EP_TYPE(n)		(((n) & 0x3) << 1)
+#define DWC3_DEPCFG_MAX_PACKET_SIZE(n)	(((n) & 0x7ff) << 3)
+#define DWC3_DEPCFG_FIFO_NUMBER(n)	(((n) & 0x1f) << 17)
+#define DWC3_DEPCFG_BURST_SIZE(n)	(((n) & 0xf) << 22)
 #define DWC3_DEPCFG_DATA_SEQ_NUM(n)	((n) << 26)
 /* This applies for core versions earlier than 1.94a */
 #define DWC3_DEPCFG_IGN_SEQ_NUM		(1 << 31)
diff --git a/drivers/usb/early/Makefile b/drivers/usb/early/Makefile
index 24bbe519c737..fcde2286da1c 100644
--- a/drivers/usb/early/Makefile
+++ b/drivers/usb/early/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-$(CONFIG_EARLY_PRINTK_DBGP) += ehci-dbgp.o
+obj-$(CONFIG_EARLY_PRINTK_USB_XDBC) += xhci-dbc.o
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
new file mode 100644
index 000000000000..1268818e2263
--- /dev/null
+++ b/drivers/usb/early/xhci-dbc.c
@@ -0,0 +1,1014 @@
+/**
+ * xhci-dbc.c - xHCI debug capability early driver
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ":%s: " fmt, __func__
+
+#include <linux/console.h>
+#include <linux/pci_regs.h>
+#include <linux/pci_ids.h>
+#include <linux/bootmem.h>
+#include <linux/io.h>
+#include <asm/pci-direct.h>
+#include <asm/fixmap.h>
+#include <linux/bcd.h>
+#include <linux/export.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+
+#include "../host/xhci.h"
+#include "xhci-dbc.h"
+
+static struct xdbc_state xdbc;
+static bool early_console_keep;
+
+#define XDBC_TRACE
+#ifdef XDBC_TRACE
+#define	xdbc_trace	trace_printk
+#else
+static inline void xdbc_trace(const char *fmt, ...) { }
+#endif /* XDBC_TRACE */
+
+static void __iomem * __init xdbc_map_pci_mmio(u32 bus, u32 dev, u32 func)
+{
+	u64 val64, sz64, mask64;
+	void __iomem *base;
+	u32 val, sz;
+	u8 byte;
+
+	val = read_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0);
+	write_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0, ~0);
+	sz = read_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0);
+	write_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0, val);
+
+	if (val == 0xffffffff || sz == 0xffffffff) {
+		pr_notice("invalid mmio bar\n");
+		return NULL;
+	}
+
+	val64	= val & PCI_BASE_ADDRESS_MEM_MASK;
+	sz64	= sz & PCI_BASE_ADDRESS_MEM_MASK;
+	mask64	= PCI_BASE_ADDRESS_MEM_MASK;
+
+	if ((val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) == PCI_BASE_ADDRESS_MEM_TYPE_64) {
+		val = read_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0 + 4);
+		write_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0 + 4, ~0);
+		sz = read_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0 + 4);
+		write_pci_config(bus, dev, func, PCI_BASE_ADDRESS_0 + 4, val);
+
+		val64	|= (u64)val << 32;
+		sz64	|= (u64)sz << 32;
+		mask64	|= ~0ULL << 32;
+	}
+
+	sz64 &= mask64;
+
+	if (!sz64) {
+		pr_notice("invalid mmio address\n");
+		return NULL;
+	}
+
+	sz64 = 1ULL << __ffs64(sz64);
+
+	/* Check if the mem space is enabled: */
+	byte = read_pci_config_byte(bus, dev, func, PCI_COMMAND);
+	if (!(byte & PCI_COMMAND_MEMORY)) {
+		byte |= PCI_COMMAND_MEMORY;
+		write_pci_config_byte(bus, dev, func, PCI_COMMAND, byte);
+	}
+
+	xdbc.xhci_start = val64;
+	xdbc.xhci_length = sz64;
+	base = early_ioremap(val64, sz64);
+
+	return base;
+}
+
+static void * __init xdbc_get_page(dma_addr_t *dma_addr)
+{
+	void *virt;
+
+	virt = alloc_bootmem_pages_nopanic(PAGE_SIZE);
+	if (!virt)
+		return NULL;
+
+	if (dma_addr)
+		*dma_addr = (dma_addr_t)__pa(virt);
+
+	return virt;
+}
+
+static u32 __init xdbc_find_dbgp(int xdbc_num, u32 *b, u32 *d, u32 *f)
+{
+	u32 bus, dev, func, class;
+
+	for (bus = 0; bus < XDBC_PCI_MAX_BUSES; bus++) {
+		for (dev = 0; dev < XDBC_PCI_MAX_DEVICES; dev++) {
+			for (func = 0; func < XDBC_PCI_MAX_FUNCTION; func++) {
+
+				class = read_pci_config(bus, dev, func, PCI_CLASS_REVISION);
+				if ((class >> 8) != PCI_CLASS_SERIAL_USB_XHCI)
+					continue;
+
+				if (xdbc_num-- != 0)
+					continue;
+
+				*b = bus;
+				*d = dev;
+				*f = func;
+
+				return 0;
+			}
+		}
+	}
+
+	return -1;
+}
+
+static int handshake(void __iomem *ptr, u32 mask, u32 done, int wait, int delay)
+{
+	u32 result;
+
+	do {
+		result = readl(ptr);
+		result &= mask;
+		if (result == done)
+			return 0;
+		udelay(delay);
+		wait -= delay;
+	} while (wait > 0);
+
+	return -ETIMEDOUT;
+}
+
+static void __init xdbc_bios_handoff(void)
+{
+	int offset, timeout;
+	u32 val;
+
+	offset = xhci_find_next_ext_cap(xdbc.xhci_base, 0, XHCI_EXT_CAPS_LEGACY);
+	val = readl(xdbc.xhci_base + offset);
+
+	if (val & XHCI_HC_BIOS_OWNED) {
+		writel(val | XHCI_HC_OS_OWNED, xdbc.xhci_base + offset);
+		timeout = handshake(xdbc.xhci_base + offset, XHCI_HC_BIOS_OWNED, 0, 5000, 10);
+
+		if (timeout) {
+			pr_notice("failed to hand over xHCI control from BIOS\n");
+			writel(val & ~XHCI_HC_BIOS_OWNED, xdbc.xhci_base + offset);
+		}
+	}
+
+	/* Disable BIOS SMIs and clear all SMI events: */
+	val = readl(xdbc.xhci_base + offset + XHCI_LEGACY_CONTROL_OFFSET);
+	val &= XHCI_LEGACY_DISABLE_SMI;
+	val |= XHCI_LEGACY_SMI_EVENTS;
+	writel(val, xdbc.xhci_base + offset + XHCI_LEGACY_CONTROL_OFFSET);
+}
+
+static int __init
+xdbc_alloc_ring(struct xdbc_segment *seg, struct xdbc_ring *ring)
+{
+	seg->trbs = xdbc_get_page(&seg->dma);
+	if (!seg->trbs)
+		return -ENOMEM;
+
+	ring->segment = seg;
+
+	return 0;
+}
+
+static void __init xdbc_free_ring(struct xdbc_ring *ring)
+{
+	struct xdbc_segment *seg = ring->segment;
+
+	if (!seg)
+		return;
+
+	free_bootmem(seg->dma, PAGE_SIZE);
+	ring->segment = NULL;
+}
+
+static void xdbc_reset_ring(struct xdbc_ring *ring)
+{
+	struct xdbc_segment *seg = ring->segment;
+	struct xdbc_trb *link_trb;
+
+	memset(seg->trbs, 0, PAGE_SIZE);
+
+	ring->enqueue = seg->trbs;
+	ring->dequeue = seg->trbs;
+	ring->cycle_state = 1;
+
+	if (ring != &xdbc.evt_ring) {
+		link_trb = &seg->trbs[XDBC_TRBS_PER_SEGMENT - 1];
+		link_trb->field[0] = cpu_to_le32(lower_32_bits(seg->dma));
+		link_trb->field[1] = cpu_to_le32(upper_32_bits(seg->dma));
+		link_trb->field[3] = cpu_to_le32(TRB_TYPE(TRB_LINK)) | cpu_to_le32(LINK_TOGGLE);
+	}
+}
+
+static inline void xdbc_put_utf16(u16 *s, const char *c, size_t size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		s[i] = cpu_to_le16(c[i]);
+}
+
+static void xdbc_mem_init(void)
+{
+	struct xdbc_ep_context *ep_in, *ep_out;
+	struct usb_string_descriptor *s_desc;
+	struct xdbc_erst_entry *entry;
+	struct xdbc_strings *strings;
+	struct xdbc_context *ctx;
+	unsigned int max_burst;
+	u32 string_length;
+	int index = 0;
+	u32 dev_info;
+
+	xdbc_reset_ring(&xdbc.evt_ring);
+	xdbc_reset_ring(&xdbc.in_ring);
+	xdbc_reset_ring(&xdbc.out_ring);
+	memset(xdbc.table_base, 0, PAGE_SIZE);
+	memset(xdbc.out_buf, 0, PAGE_SIZE);
+
+	/* Initialize event ring segment table: */
+	xdbc.erst_size	= 16;
+	xdbc.erst_base	= xdbc.table_base + index * XDBC_TABLE_ENTRY_SIZE;
+	xdbc.erst_dma	= xdbc.table_dma + index * XDBC_TABLE_ENTRY_SIZE;
+
+	index += XDBC_ERST_ENTRY_NUM;
+	entry = (struct xdbc_erst_entry *)xdbc.erst_base;
+
+	entry->seg_addr		= cpu_to_le64(xdbc.evt_seg.dma);
+	entry->seg_size		= cpu_to_le32(XDBC_TRBS_PER_SEGMENT);
+	entry->__reserved_0	= 0;
+
+	/* Initialize ERST registers: */
+	writel(1, &xdbc.xdbc_reg->ersts);
+	xdbc_write64(xdbc.erst_dma, &xdbc.xdbc_reg->erstba);
+	xdbc_write64(xdbc.evt_seg.dma, &xdbc.xdbc_reg->erdp);
+
+	/* Debug capability contexts: */
+	xdbc.dbcc_size	= 64 * 3;
+	xdbc.dbcc_base	= xdbc.table_base + index * XDBC_TABLE_ENTRY_SIZE;
+	xdbc.dbcc_dma	= xdbc.table_dma + index * XDBC_TABLE_ENTRY_SIZE;
+
+	index += XDBC_DBCC_ENTRY_NUM;
+
+	/* Popluate the strings: */
+	xdbc.string_size = sizeof(struct xdbc_strings);
+	xdbc.string_base = xdbc.table_base + index * XDBC_TABLE_ENTRY_SIZE;
+	xdbc.string_dma	 = xdbc.table_dma + index * XDBC_TABLE_ENTRY_SIZE;
+	strings		 = (struct xdbc_strings *)xdbc.string_base;
+
+	index += XDBC_STRING_ENTRY_NUM;
+
+	/* Serial string: */
+	s_desc			= (struct usb_string_descriptor *)strings->serial;
+	s_desc->bLength		= (strlen(XDBC_STRING_SERIAL) + 1) * 2;
+	s_desc->bDescriptorType	= USB_DT_STRING;
+
+	xdbc_put_utf16(s_desc->wData, XDBC_STRING_SERIAL, strlen(XDBC_STRING_SERIAL));
+	string_length = s_desc->bLength;
+	string_length <<= 8;
+
+	/* Product string: */
+	s_desc			= (struct usb_string_descriptor *)strings->product;
+	s_desc->bLength		= (strlen(XDBC_STRING_PRODUCT) + 1) * 2;
+	s_desc->bDescriptorType	= USB_DT_STRING;
+
+	xdbc_put_utf16(s_desc->wData, XDBC_STRING_PRODUCT, strlen(XDBC_STRING_PRODUCT));
+	string_length += s_desc->bLength;
+	string_length <<= 8;
+
+	/* Manufacture string: */
+	s_desc			= (struct usb_string_descriptor *)strings->manufacturer;
+	s_desc->bLength		= (strlen(XDBC_STRING_MANUFACTURER) + 1) * 2;
+	s_desc->bDescriptorType	= USB_DT_STRING;
+
+	xdbc_put_utf16(s_desc->wData, XDBC_STRING_MANUFACTURER, strlen(XDBC_STRING_MANUFACTURER));
+	string_length += s_desc->bLength;
+	string_length <<= 8;
+
+	/* String0: */
+	strings->string0[0]	= 4;
+	strings->string0[1]	= USB_DT_STRING;
+	strings->string0[2]	= 0x09;
+	strings->string0[3]	= 0x04;
+
+	string_length += 4;
+
+	/* Populate info Context: */
+	ctx = (struct xdbc_context *)xdbc.dbcc_base;
+
+	ctx->info.string0	= cpu_to_le64(xdbc.string_dma);
+	ctx->info.manufacturer	= cpu_to_le64(xdbc.string_dma + XDBC_MAX_STRING_LENGTH);
+	ctx->info.product	= cpu_to_le64(xdbc.string_dma + XDBC_MAX_STRING_LENGTH * 2);
+	ctx->info.serial	= cpu_to_le64(xdbc.string_dma + XDBC_MAX_STRING_LENGTH * 3);
+	ctx->info.length	= cpu_to_le32(string_length);
+
+	/* Populate bulk out endpoint context: */
+	max_burst = DEBUG_MAX_BURST(readl(&xdbc.xdbc_reg->control));
+	ep_out = (struct xdbc_ep_context *)&ctx->out;
+
+	ep_out->ep_info1	= 0;
+	ep_out->ep_info2	= cpu_to_le32(EP_TYPE(BULK_OUT_EP) | MAX_PACKET(1024) | MAX_BURST(max_burst));
+	ep_out->deq		= cpu_to_le64(xdbc.out_seg.dma | xdbc.out_ring.cycle_state);
+
+	/* Populate bulk in endpoint context: */
+	ep_in = (struct xdbc_ep_context *)&ctx->in;
+
+	ep_in->ep_info1		= 0;
+	ep_in->ep_info2		= cpu_to_le32(EP_TYPE(BULK_OUT_EP) | MAX_PACKET(1024) | MAX_BURST(max_burst));
+	ep_in->deq		= cpu_to_le64(xdbc.in_seg.dma | xdbc.in_ring.cycle_state);
+
+	/* Set DbC context and info registers: */
+	xdbc_write64(xdbc.dbcc_dma, &xdbc.xdbc_reg->dccp);
+
+	dev_info = cpu_to_le32((XDBC_VENDOR_ID << 16) | XDBC_PROTOCOL);
+	writel(dev_info, &xdbc.xdbc_reg->devinfo1);
+
+	dev_info = cpu_to_le32((XDBC_DEVICE_REV << 16) | XDBC_PRODUCT_ID);
+	writel(dev_info, &xdbc.xdbc_reg->devinfo2);
+
+	xdbc.in_buf = xdbc.out_buf + XDBC_MAX_PACKET;
+	xdbc.in_dma = xdbc.out_dma + XDBC_MAX_PACKET;
+}
+
+static void xdbc_do_reset_debug_port(u32 id, u32 count)
+{
+	void __iomem *ops_reg;
+	void __iomem *portsc;
+	u32 val, cap_length;
+	int i;
+
+	cap_length = readl(xdbc.xhci_base) & 0xff;
+	ops_reg = xdbc.xhci_base + cap_length;
+
+	id--;
+	for (i = id; i < (id + count); i++) {
+		portsc = ops_reg + 0x400 + i * 0x10;
+		val = readl(portsc);
+		if (!(val & PORT_CONNECT))
+			writel(val | PORT_RESET, portsc);
+	}
+}
+
+static void xdbc_reset_debug_port(void)
+{
+	u32 val, port_offset, port_count;
+	int offset = 0;
+
+	do {
+		offset = xhci_find_next_ext_cap(xdbc.xhci_base, offset, XHCI_EXT_CAPS_PROTOCOL);
+		if (!offset)
+			break;
+
+		val = readl(xdbc.xhci_base + offset);
+		if (XHCI_EXT_PORT_MAJOR(val) != 0x3)
+			continue;
+
+		val = readl(xdbc.xhci_base + offset + 8);
+		port_offset = XHCI_EXT_PORT_OFF(val);
+		port_count = XHCI_EXT_PORT_COUNT(val);
+
+		xdbc_do_reset_debug_port(port_offset, port_count);
+	} while (1);
+}
+
+static void
+xdbc_queue_trb(struct xdbc_ring *ring, u32 field1, u32 field2, u32 field3, u32 field4)
+{
+	struct xdbc_trb *trb, *link_trb;
+
+	trb = ring->enqueue;
+	trb->field[0] = cpu_to_le32(field1);
+	trb->field[1] = cpu_to_le32(field2);
+	trb->field[2] = cpu_to_le32(field3);
+	trb->field[3] = cpu_to_le32(field4);
+
+	++(ring->enqueue);
+	if (ring->enqueue >= &ring->segment->trbs[TRBS_PER_SEGMENT - 1]) {
+		link_trb = ring->enqueue;
+		if (ring->cycle_state)
+			link_trb->field[3] |= cpu_to_le32(TRB_CYCLE);
+		else
+			link_trb->field[3] &= cpu_to_le32(~TRB_CYCLE);
+
+		ring->enqueue = ring->segment->trbs;
+		ring->cycle_state ^= 1;
+	}
+}
+
+static void xdbc_ring_doorbell(int target)
+{
+	writel(DOOR_BELL_TARGET(target), &xdbc.xdbc_reg->doorbell);
+}
+
+static int xdbc_start(void)
+{
+	u32 ctrl, status;
+	int ret;
+
+	ctrl = readl(&xdbc.xdbc_reg->control);
+	writel(ctrl | CTRL_DBC_ENABLE | CTRL_PORT_ENABLE, &xdbc.xdbc_reg->control);
+	ret = handshake(&xdbc.xdbc_reg->control, CTRL_DBC_ENABLE, CTRL_DBC_ENABLE, 100000, 100);
+	if (ret) {
+		xdbc_trace("failed to initialize hardware\n");
+		return ret;
+	}
+
+	/* Reset port to avoid bus hang: */
+	if (xdbc.vendor == PCI_VENDOR_ID_INTEL)
+		xdbc_reset_debug_port();
+
+	/* Wait for port connection: */
+	ret = handshake(&xdbc.xdbc_reg->portsc, PORTSC_CONN_STATUS, PORTSC_CONN_STATUS, 5000000, 100);
+	if (ret) {
+		xdbc_trace("waiting for connection timed out\n");
+		return ret;
+	}
+
+	/* Wait for debug device to be configured: */
+	ret = handshake(&xdbc.xdbc_reg->control, CTRL_DBC_RUN, CTRL_DBC_RUN, 5000000, 100);
+	if (ret) {
+		xdbc_trace("waiting for device configuration timed out\n");
+		return ret;
+	}
+
+	/* Check port number: */
+	status = readl(&xdbc.xdbc_reg->status);
+	if (!DCST_DEBUG_PORT(status)) {
+		xdbc_trace("invalid root hub port number\n");
+		return -ENODEV;
+	}
+
+	xdbc.port_number = DCST_DEBUG_PORT(status);
+
+	xdbc_trace("DbC is running now, control 0x%08x port ID %d\n",
+		   readl(&xdbc.xdbc_reg->control), xdbc.port_number);
+
+	return 0;
+}
+
+static int xdbc_bulk_transfer(void *data, int size, bool read)
+{
+	struct xdbc_ring *ring;
+	struct xdbc_trb *trb;
+	u32 length, control;
+	u32 cycle;
+	u64 addr;
+
+	if (size > XDBC_MAX_PACKET) {
+		xdbc_trace("bad parameter, size %d\n", size);
+		return -EINVAL;
+	}
+
+	if (!(xdbc.flags & XDBC_FLAGS_INITIALIZED) ||
+	    !(xdbc.flags & XDBC_FLAGS_CONFIGURED) ||
+	    (!read && (xdbc.flags & XDBC_FLAGS_OUT_STALL)) ||
+	    (read && (xdbc.flags & XDBC_FLAGS_IN_STALL))) {
+
+		xdbc_trace("connection not ready, flags %08x\n", xdbc.flags);
+		return -EIO;
+	}
+
+	ring = (read ? &xdbc.in_ring : &xdbc.out_ring);
+	trb = ring->enqueue;
+	cycle = ring->cycle_state;
+	length = TRB_LEN(size);
+	control = TRB_TYPE(TRB_NORMAL) | TRB_IOC;
+
+	if (cycle)
+		control &= cpu_to_le32(~TRB_CYCLE);
+	else
+		control |= cpu_to_le32(TRB_CYCLE);
+
+	if (read) {
+		memset(xdbc.in_buf, 0, XDBC_MAX_PACKET);
+		addr = xdbc.in_dma;
+		xdbc.flags |= XDBC_FLAGS_IN_PROCESS;
+	} else {
+		memset(xdbc.out_buf, 0, XDBC_MAX_PACKET);
+		memcpy(xdbc.out_buf, data, size);
+		addr = xdbc.out_dma;
+		xdbc.flags |= XDBC_FLAGS_OUT_PROCESS;
+	}
+
+	xdbc_queue_trb(ring, lower_32_bits(addr), upper_32_bits(addr), length, control);
+
+	/*
+	 * Add a barrier between writes of trb fields and flipping
+	 * the cycle bit:
+	 */
+	wmb();
+	if (cycle)
+		trb->field[3] |= cpu_to_le32(cycle);
+	else
+		trb->field[3] &= cpu_to_le32(~TRB_CYCLE);
+
+	xdbc_ring_doorbell(read ? IN_EP_DOORBELL : OUT_EP_DOORBELL);
+
+	return size;
+}
+
+static int xdbc_handle_external_reset(void)
+{
+	int ret = 0;
+
+	xdbc.flags = 0;
+	writel(0, &xdbc.xdbc_reg->control);
+	ret = handshake(&xdbc.xdbc_reg->control, CTRL_DBC_ENABLE, 0, 100000, 10);
+	if (ret)
+		goto reset_out;
+
+	xdbc_mem_init();
+
+	mmiowb();
+
+	ret = xdbc_start();
+	if (ret < 0)
+		goto reset_out;
+
+	xdbc_trace("dbc recovered\n");
+
+	xdbc.flags |= XDBC_FLAGS_INITIALIZED | XDBC_FLAGS_CONFIGURED;
+
+	xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true);
+
+	return 0;
+
+reset_out:
+	xdbc_trace("failed to recover from external reset\n");
+	return ret;
+}
+
+static int __init xdbc_early_setup(void)
+{
+	int ret;
+
+	writel(0, &xdbc.xdbc_reg->control);
+	ret = handshake(&xdbc.xdbc_reg->control, CTRL_DBC_ENABLE, 0, 100000, 100);
+	if (ret)
+		return ret;
+
+	/* Allocate the table page: */
+	xdbc.table_base = xdbc_get_page(&xdbc.table_dma);
+	if (!xdbc.table_base)
+		return -ENOMEM;
+
+	/* Get and store the transfer buffer: */
+	xdbc.out_buf = xdbc_get_page(&xdbc.out_dma);
+	if (!xdbc.out_buf)
+		return -ENOMEM;
+
+	/* Allocate the event ring: */
+	ret = xdbc_alloc_ring(&xdbc.evt_seg, &xdbc.evt_ring);
+	if (ret < 0)
+		return ret;
+
+	/* Allocate IN/OUT endpoint transfer rings: */
+	ret = xdbc_alloc_ring(&xdbc.in_seg, &xdbc.in_ring);
+	if (ret < 0)
+		return ret;
+
+	ret = xdbc_alloc_ring(&xdbc.out_seg, &xdbc.out_ring);
+	if (ret < 0)
+		return ret;
+
+	xdbc_mem_init();
+
+	mmiowb();
+
+	ret = xdbc_start();
+	if (ret < 0) {
+		writel(0, &xdbc.xdbc_reg->control);
+		return ret;
+	}
+
+	xdbc.flags |= XDBC_FLAGS_INITIALIZED | XDBC_FLAGS_CONFIGURED;
+
+	xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true);
+
+	return 0;
+}
+
+int __init early_xdbc_parse_parameter(char *s)
+{
+	unsigned long dbgp_num = 0;
+	u32 bus, dev, func, offset;
+	int ret;
+
+	if (!early_pci_allowed())
+		return -EPERM;
+
+	if (strstr(s, "keep"))
+		early_console_keep = true;
+
+	if (xdbc.xdbc_reg)
+		return 0;
+
+	if (*s && kstrtoul(s, 0, &dbgp_num))
+		dbgp_num = 0;
+
+	pr_notice("dbgp_num: %lu\n", dbgp_num);
+
+	/* Locate the host controller: */
+	ret = xdbc_find_dbgp(dbgp_num, &bus, &dev, &func);
+	if (ret) {
+		pr_notice("failed to locate xhci host\n");
+		return -ENODEV;
+	}
+
+	xdbc.vendor	= read_pci_config_16(bus, dev, func, PCI_VENDOR_ID);
+	xdbc.device	= read_pci_config_16(bus, dev, func, PCI_DEVICE_ID);
+	xdbc.bus	= bus;
+	xdbc.dev	= dev;
+	xdbc.func	= func;
+
+	/* Map the IO memory: */
+	xdbc.xhci_base = xdbc_map_pci_mmio(bus, dev, func);
+	if (!xdbc.xhci_base)
+		return -EINVAL;
+
+	/* Locate DbC registers: */
+	offset = xhci_find_next_ext_cap(xdbc.xhci_base, 0, XHCI_EXT_CAPS_DEBUG);
+	if (!offset) {
+		pr_notice("xhci host doesn't support debug capability\n");
+		early_iounmap(xdbc.xhci_base, xdbc.xhci_length);
+		xdbc.xhci_base = NULL;
+		xdbc.xhci_length = 0;
+
+		return -ENODEV;
+	}
+	xdbc.xdbc_reg = (struct xdbc_regs __iomem *)(xdbc.xhci_base + offset);
+
+	return 0;
+}
+
+int __init early_xdbc_setup_hardware(void)
+{
+	int ret;
+
+	if (!xdbc.xdbc_reg)
+		return -ENODEV;
+
+	xdbc_bios_handoff();
+
+	raw_spin_lock_init(&xdbc.lock);
+
+	ret = xdbc_early_setup();
+	if (ret) {
+		pr_notice("failed to setup the connection to host\n");
+
+		xdbc_free_ring(&xdbc.evt_ring);
+		xdbc_free_ring(&xdbc.out_ring);
+		xdbc_free_ring(&xdbc.in_ring);
+
+		if (xdbc.table_dma)
+			free_bootmem(xdbc.table_dma, PAGE_SIZE);
+
+		if (xdbc.out_dma)
+			free_bootmem(xdbc.out_dma, PAGE_SIZE);
+
+		xdbc.table_base = NULL;
+		xdbc.out_buf = NULL;
+	}
+
+	return ret;
+}
+
+static void xdbc_handle_port_status(struct xdbc_trb *evt_trb)
+{
+	u32 port_reg;
+
+	port_reg = readl(&xdbc.xdbc_reg->portsc);
+	if (port_reg & PORTSC_CONN_CHANGE) {
+		xdbc_trace("connect status change event\n");
+
+		/* Check whether cable unplugged: */
+		if (!(port_reg & PORTSC_CONN_STATUS)) {
+			xdbc.flags = 0;
+			xdbc_trace("cable unplugged\n");
+		}
+	}
+
+	if (port_reg & PORTSC_RESET_CHANGE)
+		xdbc_trace("port reset change event\n");
+
+	if (port_reg & PORTSC_LINK_CHANGE)
+		xdbc_trace("port link status change event\n");
+
+	if (port_reg & PORTSC_CONFIG_CHANGE)
+		xdbc_trace("config error change\n");
+
+	/* Write back the value to clear RW1C bits: */
+	writel(port_reg, &xdbc.xdbc_reg->portsc);
+}
+
+static void xdbc_handle_tx_event(struct xdbc_trb *evt_trb)
+{
+	size_t remain_length;
+	u32 comp_code;
+	int ep_id;
+
+	comp_code	= GET_COMP_CODE(le32_to_cpu(evt_trb->field[2]));
+	remain_length	= EVENT_TRB_LEN(le32_to_cpu(evt_trb->field[2]));
+	ep_id		= TRB_TO_EP_ID(le32_to_cpu(evt_trb->field[3]));
+
+	switch (comp_code) {
+	case COMP_SUCCESS:
+		remain_length = 0;
+	case COMP_SHORT_PACKET:
+		break;
+	case COMP_TRB_ERROR:
+	case COMP_BABBLE_DETECTED_ERROR:
+	case COMP_USB_TRANSACTION_ERROR:
+	case COMP_STALL_ERROR:
+	default:
+		if (ep_id == XDBC_EPID_OUT)
+			xdbc.flags |= XDBC_FLAGS_OUT_STALL;
+		if (ep_id == XDBC_EPID_IN)
+			xdbc.flags |= XDBC_FLAGS_IN_STALL;
+
+		xdbc_trace("endpoint %d stalled\n", ep_id);
+		break;
+	}
+
+	if (ep_id == XDBC_EPID_IN) {
+		xdbc.flags &= ~XDBC_FLAGS_IN_PROCESS;
+		xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true);
+	} else if (ep_id == XDBC_EPID_OUT) {
+		xdbc.flags &= ~XDBC_FLAGS_OUT_PROCESS;
+	} else {
+		xdbc_trace("invalid endpoint id %d\n", ep_id);
+	}
+}
+
+static void xdbc_handle_events(void)
+{
+	struct xdbc_trb *evt_trb;
+	bool update_erdp = false;
+	u32 reg;
+	u8 cmd;
+
+	cmd = read_pci_config_byte(xdbc.bus, xdbc.dev, xdbc.func, PCI_COMMAND);
+	if (!(cmd & PCI_COMMAND_MASTER)) {
+		cmd |= PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY;
+		write_pci_config_byte(xdbc.bus, xdbc.dev, xdbc.func, PCI_COMMAND, cmd);
+	}
+
+	if (!(xdbc.flags & XDBC_FLAGS_INITIALIZED))
+		return;
+
+	/* Handle external reset events: */
+	reg = readl(&xdbc.xdbc_reg->control);
+	if (!(reg & CTRL_DBC_ENABLE)) {
+		if (xdbc_handle_external_reset()) {
+			xdbc_trace("failed to recover connection\n");
+			return;
+		}
+	}
+
+	/* Handle configure-exit event: */
+	reg = readl(&xdbc.xdbc_reg->control);
+	if (reg & CTRL_DBC_RUN_CHANGE) {
+		writel(reg, &xdbc.xdbc_reg->control);
+		if (reg & CTRL_DBC_RUN)
+			xdbc.flags |= XDBC_FLAGS_CONFIGURED;
+		else
+			xdbc.flags &= ~XDBC_FLAGS_CONFIGURED;
+	}
+
+	/* Handle endpoint stall event: */
+	reg = readl(&xdbc.xdbc_reg->control);
+	if (reg & CTRL_HALT_IN_TR) {
+		xdbc.flags |= XDBC_FLAGS_IN_STALL;
+	} else {
+		xdbc.flags &= ~XDBC_FLAGS_IN_STALL;
+		if (!(xdbc.flags & XDBC_FLAGS_IN_PROCESS))
+			xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true);
+	}
+
+	if (reg & CTRL_HALT_OUT_TR)
+		xdbc.flags |= XDBC_FLAGS_OUT_STALL;
+	else
+		xdbc.flags &= ~XDBC_FLAGS_OUT_STALL;
+
+	/* Handle the events in the event ring: */
+	evt_trb = xdbc.evt_ring.dequeue;
+	while ((le32_to_cpu(evt_trb->field[3]) & TRB_CYCLE) == xdbc.evt_ring.cycle_state) {
+		/*
+		 * Add a barrier between reading the cycle flag and any
+		 * reads of the event's flags/data below:
+		 */
+		rmb();
+
+		switch ((le32_to_cpu(evt_trb->field[3]) & TRB_TYPE_BITMASK)) {
+		case TRB_TYPE(TRB_PORT_STATUS):
+			xdbc_handle_port_status(evt_trb);
+			break;
+		case TRB_TYPE(TRB_TRANSFER):
+			xdbc_handle_tx_event(evt_trb);
+			break;
+		default:
+			break;
+		}
+
+		++(xdbc.evt_ring.dequeue);
+		if (xdbc.evt_ring.dequeue == &xdbc.evt_seg.trbs[TRBS_PER_SEGMENT]) {
+			xdbc.evt_ring.dequeue = xdbc.evt_seg.trbs;
+			xdbc.evt_ring.cycle_state ^= 1;
+		}
+
+		evt_trb = xdbc.evt_ring.dequeue;
+		update_erdp = true;
+	}
+
+	/* Update event ring dequeue pointer: */
+	if (update_erdp)
+		xdbc_write64(__pa(xdbc.evt_ring.dequeue), &xdbc.xdbc_reg->erdp);
+}
+
+static int xdbc_bulk_write(const char *bytes, int size)
+{
+	int ret, timeout = 0;
+	unsigned long flags;
+
+retry:
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&xdbc.lock, flags))
+			return -EAGAIN;
+	} else {
+		raw_spin_lock_irqsave(&xdbc.lock, flags);
+	}
+
+	xdbc_handle_events();
+
+	/* Check completion of the previous request: */
+	if ((xdbc.flags & XDBC_FLAGS_OUT_PROCESS) && (timeout < 2000000)) {
+		raw_spin_unlock_irqrestore(&xdbc.lock, flags);
+		udelay(100);
+		timeout += 100;
+		goto retry;
+	}
+
+	if (xdbc.flags & XDBC_FLAGS_OUT_PROCESS) {
+		raw_spin_unlock_irqrestore(&xdbc.lock, flags);
+		xdbc_trace("previous transfer not completed yet\n");
+
+		return -ETIMEDOUT;
+	}
+
+	ret = xdbc_bulk_transfer((void *)bytes, size, false);
+	raw_spin_unlock_irqrestore(&xdbc.lock, flags);
+
+	return ret;
+}
+
+static void early_xdbc_write(struct console *con, const char *str, u32 n)
+{
+	static char buf[XDBC_MAX_PACKET];
+	int chunk, ret;
+	int use_cr = 0;
+
+	if (!xdbc.xdbc_reg)
+		return;
+	memset(buf, 0, XDBC_MAX_PACKET);
+	while (n > 0) {
+		for (chunk = 0; chunk < XDBC_MAX_PACKET && n > 0; str++, chunk++, n--) {
+
+			if (!use_cr && *str == '\n') {
+				use_cr = 1;
+				buf[chunk] = '\r';
+				str--;
+				n++;
+				continue;
+			}
+
+			if (use_cr)
+				use_cr = 0;
+			buf[chunk] = *str;
+		}
+
+		if (chunk > 0) {
+			ret = xdbc_bulk_write(buf, chunk);
+			if (ret < 0)
+				xdbc_trace("missed message {%s}\n", buf);
+		}
+	}
+}
+
+static struct console early_xdbc_console = {
+	.name		= "earlyxdbc",
+	.write		= early_xdbc_write,
+	.flags		= CON_PRINTBUFFER,
+	.index		= -1,
+};
+
+void __init early_xdbc_register_console(void)
+{
+	if (early_console)
+		return;
+
+	early_console = &early_xdbc_console;
+	if (early_console_keep)
+		early_console->flags &= ~CON_BOOT;
+	else
+		early_console->flags |= CON_BOOT;
+	register_console(early_console);
+}
+
+static void xdbc_unregister_console(void)
+{
+	if (early_xdbc_console.flags & CON_ENABLED)
+		unregister_console(&early_xdbc_console);
+}
+
+static int xdbc_scrub_function(void *ptr)
+{
+	unsigned long flags;
+
+	while (true) {
+		raw_spin_lock_irqsave(&xdbc.lock, flags);
+		xdbc_handle_events();
+
+		if (!(xdbc.flags & XDBC_FLAGS_INITIALIZED)) {
+			raw_spin_unlock_irqrestore(&xdbc.lock, flags);
+			break;
+		}
+
+		raw_spin_unlock_irqrestore(&xdbc.lock, flags);
+		schedule_timeout_interruptible(1);
+	}
+
+	xdbc_unregister_console();
+	writel(0, &xdbc.xdbc_reg->control);
+	xdbc_trace("dbc scrub function exits\n");
+
+	return 0;
+}
+
+static int __init xdbc_init(void)
+{
+	unsigned long flags;
+	void __iomem *base;
+	int ret = 0;
+	u32 offset;
+
+	if (!(xdbc.flags & XDBC_FLAGS_INITIALIZED))
+		return 0;
+
+	/*
+	 * It's time to shut down the DbC, so that the debug
+	 * port can be reused by the host controller:
+	 */
+	if (early_xdbc_console.index == -1 ||
+	    (early_xdbc_console.flags & CON_BOOT)) {
+		xdbc_trace("hardware not used anymore\n");
+		goto free_and_quit;
+	}
+
+	base = ioremap_nocache(xdbc.xhci_start, xdbc.xhci_length);
+	if (!base) {
+		xdbc_trace("failed to remap the io address\n");
+		ret = -ENOMEM;
+		goto free_and_quit;
+	}
+
+	raw_spin_lock_irqsave(&xdbc.lock, flags);
+	early_iounmap(xdbc.xhci_base, xdbc.xhci_length);
+	xdbc.xhci_base = base;
+	offset = xhci_find_next_ext_cap(xdbc.xhci_base, 0, XHCI_EXT_CAPS_DEBUG);
+	xdbc.xdbc_reg = (struct xdbc_regs __iomem *)(xdbc.xhci_base + offset);
+	raw_spin_unlock_irqrestore(&xdbc.lock, flags);
+
+	kthread_run(xdbc_scrub_function, NULL, "%s", "xdbc");
+
+	return 0;
+
+free_and_quit:
+	xdbc_free_ring(&xdbc.evt_ring);
+	xdbc_free_ring(&xdbc.out_ring);
+	xdbc_free_ring(&xdbc.in_ring);
+	free_bootmem(xdbc.table_dma, PAGE_SIZE);
+	free_bootmem(xdbc.out_dma, PAGE_SIZE);
+	writel(0, &xdbc.xdbc_reg->control);
+	early_iounmap(xdbc.xhci_base, xdbc.xhci_length);
+
+	return ret;
+}
+subsys_initcall(xdbc_init);
diff --git a/drivers/usb/early/xhci-dbc.h b/drivers/usb/early/xhci-dbc.h
new file mode 100644
index 000000000000..2df0f6e613fe
--- /dev/null
+++ b/drivers/usb/early/xhci-dbc.h
@@ -0,0 +1,211 @@
+/*
+ * xhci-dbc.h - xHCI debug capability early driver
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_XHCI_DBC_H
+#define __LINUX_XHCI_DBC_H
+
+#include <linux/types.h>
+#include <linux/usb/ch9.h>
+
+/*
+ * xHCI Debug Capability Register interfaces:
+ */
+struct xdbc_regs {
+	__le32	capability;
+	__le32	doorbell;
+	__le32	ersts;		/* Event Ring Segment Table Size*/
+	__le32	__reserved_0;	/* 0c~0f reserved bits */
+	__le64	erstba;		/* Event Ring Segment Table Base Address */
+	__le64	erdp;		/* Event Ring Dequeue Pointer */
+	__le32	control;
+	__le32	status;
+	__le32	portsc;		/* Port status and control */
+	__le32	__reserved_1;	/* 2b~28 reserved bits */
+	__le64	dccp;		/* Debug Capability Context Pointer */
+	__le32	devinfo1;	/* Device Descriptor Info Register 1 */
+	__le32	devinfo2;	/* Device Descriptor Info Register 2 */
+};
+
+#define DEBUG_MAX_BURST(p)	(((p) >> 16) & 0xff)
+
+#define CTRL_DBC_RUN		BIT(0)
+#define CTRL_PORT_ENABLE	BIT(1)
+#define CTRL_HALT_OUT_TR	BIT(2)
+#define CTRL_HALT_IN_TR		BIT(3)
+#define CTRL_DBC_RUN_CHANGE	BIT(4)
+#define CTRL_DBC_ENABLE		BIT(31)
+
+#define DCST_DEBUG_PORT(p)	(((p) >> 24) & 0xff)
+
+#define PORTSC_CONN_STATUS	BIT(0)
+#define PORTSC_CONN_CHANGE	BIT(17)
+#define PORTSC_RESET_CHANGE	BIT(21)
+#define PORTSC_LINK_CHANGE	BIT(22)
+#define PORTSC_CONFIG_CHANGE	BIT(23)
+
+/*
+ * xHCI Debug Capability data structures:
+ */
+struct xdbc_trb {
+	__le32 field[4];
+};
+
+struct xdbc_erst_entry {
+	__le64	seg_addr;
+	__le32	seg_size;
+	__le32	__reserved_0;
+};
+
+struct xdbc_info_context {
+	__le64	string0;
+	__le64	manufacturer;
+	__le64	product;
+	__le64	serial;
+	__le32	length;
+	__le32	__reserved_0[7];
+};
+
+struct xdbc_ep_context {
+	__le32	ep_info1;
+	__le32	ep_info2;
+	__le64	deq;
+	__le32	tx_info;
+	__le32	__reserved_0[11];
+};
+
+struct xdbc_context {
+	struct xdbc_info_context	info;
+	struct xdbc_ep_context		out;
+	struct xdbc_ep_context		in;
+};
+
+#define XDBC_INFO_CONTEXT_SIZE		48
+#define XDBC_MAX_STRING_LENGTH		64
+#define XDBC_STRING_MANUFACTURER	"Linux"
+#define XDBC_STRING_PRODUCT		"Remote GDB"
+#define XDBC_STRING_SERIAL		"0001"
+
+struct xdbc_strings {
+	char	string0[XDBC_MAX_STRING_LENGTH];
+	char	manufacturer[XDBC_MAX_STRING_LENGTH];
+	char	product[XDBC_MAX_STRING_LENGTH];
+	char	serial[XDBC_MAX_STRING_LENGTH];
+};
+
+#define XDBC_PROTOCOL		1	/* GNU Remote Debug Command Set */
+#define XDBC_VENDOR_ID		0x1d6b	/* Linux Foundation 0x1d6b */
+#define XDBC_PRODUCT_ID		0x0004	/* __le16 idProduct; device 0004 */
+#define XDBC_DEVICE_REV		0x0010	/* 0.10 */
+
+/*
+ * xHCI Debug Capability software state structures:
+ */
+struct xdbc_segment {
+	struct xdbc_trb		*trbs;
+	dma_addr_t		dma;
+};
+
+#define XDBC_TRBS_PER_SEGMENT	256
+
+struct xdbc_ring {
+	struct xdbc_segment	*segment;
+	struct xdbc_trb		*enqueue;
+	struct xdbc_trb		*dequeue;
+	u32			cycle_state;
+};
+
+#define XDBC_EPID_OUT		2
+#define XDBC_EPID_IN		3
+
+struct xdbc_state {
+	u16			vendor;
+	u16			device;
+	u32			bus;
+	u32			dev;
+	u32			func;
+	void __iomem		*xhci_base;
+	u64			xhci_start;
+	size_t			xhci_length;
+	int			port_number;
+
+	/* DbC register base */
+	struct xdbc_regs __iomem *xdbc_reg;
+
+	/* DbC table page */
+	dma_addr_t		table_dma;
+	void			*table_base;
+
+	/* event ring segment table */
+	dma_addr_t		erst_dma;
+	size_t			erst_size;
+	void			*erst_base;
+
+	/* event ring segments */
+	struct xdbc_ring	evt_ring;
+	struct xdbc_segment	evt_seg;
+
+	/* debug capability contexts */
+	dma_addr_t		dbcc_dma;
+	size_t			dbcc_size;
+	void			*dbcc_base;
+
+	/* descriptor strings */
+	dma_addr_t		string_dma;
+	size_t			string_size;
+	void			*string_base;
+
+	/* bulk OUT endpoint */
+	struct xdbc_ring	out_ring;
+	struct xdbc_segment	out_seg;
+	void			*out_buf;
+	dma_addr_t		out_dma;
+
+	/* bulk IN endpoint */
+	struct xdbc_ring	in_ring;
+	struct xdbc_segment	in_seg;
+	void			*in_buf;
+	dma_addr_t		in_dma;
+
+	u32			flags;
+
+	/* spinlock for early_xdbc_write() reentrancy */
+	raw_spinlock_t		lock;
+};
+
+#define XDBC_PCI_MAX_BUSES	256
+#define XDBC_PCI_MAX_DEVICES	32
+#define XDBC_PCI_MAX_FUNCTION	8
+
+#define XDBC_TABLE_ENTRY_SIZE	64
+#define XDBC_ERST_ENTRY_NUM	1
+#define XDBC_DBCC_ENTRY_NUM	3
+#define XDBC_STRING_ENTRY_NUM	4
+
+/* Bits definitions for xdbc_state.flags: */
+#define XDBC_FLAGS_INITIALIZED	BIT(0)
+#define XDBC_FLAGS_IN_STALL	BIT(1)
+#define XDBC_FLAGS_OUT_STALL	BIT(2)
+#define XDBC_FLAGS_IN_PROCESS	BIT(3)
+#define XDBC_FLAGS_OUT_PROCESS	BIT(4)
+#define XDBC_FLAGS_CONFIGURED	BIT(5)
+
+#define XDBC_MAX_PACKET		1024
+
+/* Door bell target: */
+#define OUT_EP_DOORBELL		0
+#define IN_EP_DOORBELL		1
+#define DOOR_BELL_TARGET(p)	(((p) & 0xff) << 8)
+
+#define xdbc_read64(regs)	xhci_read_64(NULL, (regs))
+#define xdbc_write64(val, regs)	xhci_write_64(NULL, (val), (regs))
+
+#endif /* __LINUX_XHCI_DBC_H */
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 78c44979dde3..cbff3b02840d 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -269,6 +269,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
 		ret = unregister_gadget(gi);
 		if (ret)
 			goto err;
+		kfree(name);
 	} else {
 		if (gi->composite.gadget_driver.udc_name) {
 			ret = -EBUSY;
diff --git a/drivers/usb/gadget/function/f_acm.c b/drivers/usb/gadget/function/f_acm.c
index a30766ca4226..5e3828d9dac7 100644
--- a/drivers/usb/gadget/function/f_acm.c
+++ b/drivers/usb/gadget/function/f_acm.c
@@ -535,13 +535,15 @@ static int acm_notify_serial_state(struct f_acm *acm)
 {
 	struct usb_composite_dev *cdev = acm->port.func.config->cdev;
 	int			status;
+	__le16			serial_state;
 
 	spin_lock(&acm->lock);
 	if (acm->notify_req) {
 		dev_dbg(&cdev->gadget->dev, "acm ttyGS%d serial state %04x\n",
 			acm->port_num, acm->serial_state);
+		serial_state = cpu_to_le16(acm->serial_state);
 		status = acm_cdc_notify(acm, USB_CDC_NOTIFY_SERIAL_STATE,
-				0, &acm->serial_state, sizeof(acm->serial_state));
+				0, &serial_state, sizeof(acm->serial_state));
 	} else {
 		acm->pending = true;
 		status = 0;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index a5b7cd615698..a0085571824d 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1834,11 +1834,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
 	spin_lock_irqsave(&func->ffs->eps_lock, flags);
 	while(count--) {
 		struct usb_endpoint_descriptor *ds;
+		struct usb_ss_ep_comp_descriptor *comp_desc = NULL;
+		int needs_comp_desc = false;
 		int desc_idx;
 
-		if (ffs->gadget->speed == USB_SPEED_SUPER)
+		if (ffs->gadget->speed == USB_SPEED_SUPER) {
 			desc_idx = 2;
-		else if (ffs->gadget->speed == USB_SPEED_HIGH)
+			needs_comp_desc = true;
+		} else if (ffs->gadget->speed == USB_SPEED_HIGH)
 			desc_idx = 1;
 		else
 			desc_idx = 0;
@@ -1855,6 +1858,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
 
 		ep->ep->driver_data = ep;
 		ep->ep->desc = ds;
+
+		comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds +
+				USB_DT_ENDPOINT_SIZE);
+		ep->ep->maxburst = comp_desc->bMaxBurst + 1;
+
+		if (needs_comp_desc)
+			ep->ep->comp_desc = comp_desc;
+
 		ret = usb_ep_enable(ep->ep);
 		if (likely(!ret)) {
 			epfile->ep = ep;
@@ -2253,7 +2264,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 
 		if (len < sizeof(*d) ||
 		    d->bFirstInterfaceNumber >= ffs->interfaces_count ||
-		    d->Reserved1)
+		    !d->Reserved1)
 			return -EINVAL;
 		for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i)
 			if (d->Reserved2[i])
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 89b48bcc377a..5eea44823ca0 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -367,7 +367,7 @@ try_again:
 	count  = min_t(unsigned, count, hidg->report_length);
 
 	spin_unlock_irqrestore(&hidg->write_spinlock, flags);
-	status = copy_from_user(hidg->req->buf, buffer, count);
+	status = copy_from_user(req->buf, buffer, count);
 
 	if (status != 0) {
 		ERROR(hidg->func.config->cdev,
@@ -378,9 +378,9 @@ try_again:
 
 	spin_lock_irqsave(&hidg->write_spinlock, flags);
 
-	/* we our function has been disabled by host */
+	/* when our function has been disabled by host */
 	if (!hidg->req) {
-		free_ep_req(hidg->in_ep, hidg->req);
+		free_ep_req(hidg->in_ep, req);
 		/*
 		 * TODO
 		 * Should we fail with error here?
@@ -394,7 +394,7 @@ try_again:
 	req->complete = f_hidg_req_complete;
 	req->context  = hidg;
 
-	status = usb_ep_queue(hidg->in_ep, hidg->req, GFP_ATOMIC);
+	status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC);
 	if (status < 0) {
 		ERROR(hidg->func.config->cdev,
 			"usb_ep_queue error on int endpoint %zd\n", status);
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 224717e63a53..864819ff9a7d 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index d2351139342f..a82e2bd5ea34 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -373,7 +373,7 @@ static void bot_cleanup_old_alt(struct f_uas *fu)
 	usb_ep_free_request(fu->ep_in, fu->bot_req_in);
 	usb_ep_free_request(fu->ep_out, fu->bot_req_out);
 	usb_ep_free_request(fu->ep_out, fu->cmd.req);
-	usb_ep_free_request(fu->ep_out, fu->bot_status.req);
+	usb_ep_free_request(fu->ep_in, fu->bot_status.req);
 
 	kfree(fu->cmd.buf);
 
diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 27ed51b5082f..f8a1881609a2 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -258,13 +258,6 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 	memcpy(&uvc_event->req, ctrl, sizeof(uvc_event->req));
 	v4l2_event_queue(&uvc->vdev, &v4l2_event);
 
-	/* Pass additional setup data to userspace */
-	if (uvc->event_setup_out && uvc->event_length) {
-		uvc->control_req->length = uvc->event_length;
-		return usb_ep_queue(uvc->func.config->cdev->gadget->ep0,
-			uvc->control_req, GFP_ATOMIC);
-	}
-
 	return 0;
 }
 
@@ -601,6 +594,14 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	opts->streaming_maxpacket = clamp(opts->streaming_maxpacket, 1U, 3072U);
 	opts->streaming_maxburst = min(opts->streaming_maxburst, 15U);
 
+	/* For SS, wMaxPacketSize has to be 1024 if bMaxBurst is not 0 */
+	if (opts->streaming_maxburst &&
+	    (opts->streaming_maxpacket % 1024) != 0) {
+		opts->streaming_maxpacket = roundup(opts->streaming_maxpacket, 1024);
+		INFO(cdev, "overriding streaming_maxpacket to %d\n",
+		     opts->streaming_maxpacket);
+	}
+
 	/* Fill in the FS/HS/SS Video Streaming specific descriptors from the
 	 * module parameters.
 	 *
@@ -632,7 +633,7 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	uvc_ss_streaming_comp.bMaxBurst = opts->streaming_maxburst;
 	uvc_ss_streaming_comp.wBytesPerInterval =
 		cpu_to_le16(max_packet_size * max_packet_mult *
-			    opts->streaming_maxburst);
+			    (opts->streaming_maxburst + 1));
 
 	/* Allocate endpoints. */
 	ep = usb_ep_autoconfig(cdev->gadget, &uvc_control_ep);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index a2615d64d07c..a2c916869293 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -84,8 +84,7 @@ static int ep_open(struct inode *, struct file *);
 
 /* /dev/gadget/$CHIP represents ep0 and the whole device */
 enum ep0_state {
-	/* DISBLED is the initial state.
-	 */
+	/* DISABLED is the initial state. */
 	STATE_DEV_DISABLED = 0,
 
 	/* Only one open() of /dev/gadget/$CHIP; only one file tracks
@@ -1782,8 +1781,10 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 
 	spin_lock_irq (&dev->lock);
 	value = -EINVAL;
-	if (dev->buf)
+	if (dev->buf) {
+		kfree(kbuf);
 		goto fail;
+	}
 	dev->buf = kbuf;
 
 	/* full or low speed config */
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 11bbce28bc23..2035906b8ced 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -610,7 +610,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
 {
 	struct usba_ep *ep = to_usba_ep(_ep);
 	struct usba_udc *udc = ep->udc;
-	unsigned long flags, ept_cfg, maxpacket;
+	unsigned long flags, maxpacket;
 	unsigned int nr_trans;
 
 	DBG(DBG_GADGET, "%s: ep_enable: desc=%p\n", ep->ep.name, desc);
@@ -630,7 +630,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
 	ep->is_in = 0;
 
 	DBG(DBG_ERR, "%s: EPT_CFG = 0x%lx (maxpacket = %lu)\n",
-			ep->ep.name, ept_cfg, maxpacket);
+			ep->ep.name, ep->ept_cfg, maxpacket);
 
 	if (usb_endpoint_dir_in(desc)) {
 		ep->is_in = 1;
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index c60abe3a68f9..8cabc5944d5f 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1031,6 +1031,8 @@ static int dummy_udc_probe(struct platform_device *pdev)
 	int		rc;
 
 	dum = *((void **)dev_get_platdata(&pdev->dev));
+	/* Clear usb_gadget region for new registration to udc-core */
+	memzero_explicit(&dum->gadget, sizeof(struct usb_gadget));
 	dum->gadget.name = gadget_name;
 	dum->gadget.ops = &dummy_ops;
 	dum->gadget.max_speed = USB_SPEED_SUPER;
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index 85504419ab31..3828c2ec8623 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -1146,15 +1146,15 @@ static int scan_dma_completions(struct net2280_ep *ep)
 	 */
 	while (!list_empty(&ep->queue)) {
 		struct net2280_request	*req;
-		u32			tmp;
+		u32 req_dma_count;
 
 		req = list_entry(ep->queue.next,
 				struct net2280_request, queue);
 		if (!req->valid)
 			break;
 		rmb();
-		tmp = le32_to_cpup(&req->td->dmacount);
-		if ((tmp & BIT(VALID_BIT)) != 0)
+		req_dma_count = le32_to_cpup(&req->td->dmacount);
+		if ((req_dma_count & BIT(VALID_BIT)) != 0)
 			break;
 
 		/* SHORT_PACKET_TRANSFERRED_INTERRUPT handles "usb-short"
@@ -1163,40 +1163,41 @@ static int scan_dma_completions(struct net2280_ep *ep)
 		 */
 		if (unlikely(req->td->dmadesc == 0)) {
 			/* paranoia */
-			tmp = readl(&ep->dma->dmacount);
-			if (tmp & DMA_BYTE_COUNT_MASK)
+			u32 const ep_dmacount = readl(&ep->dma->dmacount);
+
+			if (ep_dmacount & DMA_BYTE_COUNT_MASK)
 				break;
 			/* single transfer mode */
-			dma_done(ep, req, tmp, 0);
+			dma_done(ep, req, req_dma_count, 0);
 			num_completed++;
 			break;
 		} else if (!ep->is_in &&
 			   (req->req.length % ep->ep.maxpacket) &&
 			   !(ep->dev->quirks & PLX_PCIE)) {
 
-			tmp = readl(&ep->regs->ep_stat);
+			u32 const ep_stat = readl(&ep->regs->ep_stat);
 			/* AVOID TROUBLE HERE by not issuing short reads from
 			 * your gadget driver.  That helps avoids errata 0121,
 			 * 0122, and 0124; not all cases trigger the warning.
 			 */
-			if ((tmp & BIT(NAK_OUT_PACKETS)) == 0) {
+			if ((ep_stat & BIT(NAK_OUT_PACKETS)) == 0) {
 				ep_warn(ep->dev, "%s lost packet sync!\n",
 						ep->ep.name);
 				req->req.status = -EOVERFLOW;
 			} else {
-				tmp = readl(&ep->regs->ep_avail);
-				if (tmp) {
+				u32 const ep_avail = readl(&ep->regs->ep_avail);
+				if (ep_avail) {
 					/* fifo gets flushed later */
 					ep->out_overflow = 1;
 					ep_dbg(ep->dev,
 						"%s dma, discard %d len %d\n",
-						ep->ep.name, tmp,
+						ep->ep.name, ep_avail,
 						req->req.length);
 					req->req.status = -EOVERFLOW;
 				}
 			}
 		}
-		dma_done(ep, req, tmp, 0);
+		dma_done(ep, req, req_dma_count, 0);
 		num_completed++;
 	}
 
diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index a97da645c1b9..8a365aad66fe 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -1523,7 +1523,6 @@ static void pch_udc_free_dma_chain(struct pch_udc_dev *dev,
 		td = phys_to_virt(addr);
 		addr2 = (dma_addr_t)td->next;
 		pci_pool_free(dev->data_requests, td, addr);
-		td->next = 0x00;
 		addr = addr2;
 	}
 	req->chain_len = 1;
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index e1335ad5bce9..832c4fdbe985 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -2534,9 +2534,10 @@ static int pxa_udc_remove(struct platform_device *_dev)
 	usb_del_gadget_udc(&udc->gadget);
 	pxa_cleanup_debugfs(udc);
 
-	if (!IS_ERR_OR_NULL(udc->transceiver))
+	if (!IS_ERR_OR_NULL(udc->transceiver)) {
 		usb_unregister_notifier(udc->transceiver, &pxa27x_udc_phy);
-	usb_put_phy(udc->transceiver);
+		usb_put_phy(udc->transceiver);
+	}
 
 	udc->transceiver = NULL;
 	the_controller = NULL;
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 414e3c376dbb..5302f988e7e6 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -350,7 +350,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 
 		case USB_PORT_FEAT_SUSPEND:
 			dev_dbg(hcd->self.controller, "SetPortFeat: SUSPEND\n");
-			if (valid_port(wIndex)) {
+			if (valid_port(wIndex) && ohci_at91->sfr_regmap) {
 				ohci_at91_port_suspend(ohci_at91->sfr_regmap,
 						       1);
 				return 0;
@@ -393,7 +393,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 
 		case USB_PORT_FEAT_SUSPEND:
 			dev_dbg(hcd->self.controller, "ClearPortFeature: SUSPEND\n");
-			if (valid_port(wIndex)) {
+			if (valid_port(wIndex) && ohci_at91->sfr_regmap) {
 				ohci_at91_port_suspend(ohci_at91->sfr_regmap,
 						       0);
 				return 0;
diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index 363d125300ea..2b4a00fa735d 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -109,7 +109,7 @@ static void xhci_print_cap_regs(struct xhci_hcd *xhci)
 	xhci_dbg(xhci, "RTSOFF 0x%x:\n", temp & RTSOFF_MASK);
 
 	/* xhci 1.1 controllers have the HCCPARAMS2 register */
-	if (hci_version > 100) {
+	if (hci_version > 0x100) {
 		temp = readl(&xhci->cap_regs->hcc_params2);
 		xhci_dbg(xhci, "HCC PARAMS2 0x%x:\n", (unsigned int) temp);
 		xhci_dbg(xhci, "  HC %s Force save context capability",
diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 9066ec9e0c2e..67d5dc79b6b5 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -382,7 +382,6 @@ static int usb_wakeup_of_property_parse(struct xhci_hcd_mtk *mtk,
 
 static int xhci_mtk_setup(struct usb_hcd *hcd);
 static const struct xhci_driver_overrides xhci_mtk_overrides __initconst = {
-	.extra_priv_size = sizeof(struct xhci_hcd),
 	.reset = xhci_mtk_setup,
 };
 
@@ -678,13 +677,13 @@ static int xhci_mtk_probe(struct platform_device *pdev)
 		goto power_off_phys;
 	}
 
-	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
-		xhci->shared_hcd->can_do_streams = 1;
-
 	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto put_usb3_hcd;
 
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
 	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto dealloc_usb2_hcd;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 6d33b42ffcf5..6ed468fa7d5e 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -286,6 +286,8 @@ static int xhci_plat_remove(struct platform_device *dev)
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct clk *clk = xhci->clk;
 
+	xhci->xhc_state |= XHCI_STATE_REMOVING;
+
 	usb_remove_hcd(xhci->shared_hcd);
 	usb_phy_shutdown(hcd->usb_phy);
 
@@ -342,6 +344,7 @@ MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match);
 static struct platform_driver usb_xhci_driver = {
 	.probe	= xhci_plat_probe,
 	.remove	= xhci_plat_remove,
+	.shutdown	= usb_hcd_platform_shutdown,
 	.driver	= {
 		.name = "xhci-hcd",
 		.pm = DEV_PM_OPS,
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index d9936c771fa0..a3309aa02993 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1989,6 +1989,9 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
 		case TRB_NORMAL:
 			td->urb->actual_length = requested - remaining;
 			goto finish_td;
+		case TRB_STATUS:
+			td->urb->actual_length = requested;
+			goto finish_td;
 		default:
 			xhci_warn(xhci, "WARN: unexpected TRB Type %d\n",
 				  trb_type);
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index a59fafb4b329..74436f8ca538 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1308,7 +1308,6 @@ static int tegra_xhci_setup(struct usb_hcd *hcd)
 }
 
 static const struct xhci_driver_overrides tegra_xhci_overrides __initconst = {
-	.extra_priv_size = sizeof(struct xhci_hcd),
 	.reset = tegra_xhci_setup,
 };
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6d6c46000e56..953fd8f62df0 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -868,7 +868,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
 
 	spin_lock_irqsave(&xhci->lock, flags);
 
-	/* disble usb3 ports Wake bits*/
+	/* disable usb3 ports Wake bits */
 	port_index = xhci->num_usb3_ports;
 	port_array = xhci->usb3_ports;
 	while (port_index--) {
@@ -879,7 +879,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
 			writel(t2, port_array[port_index]);
 	}
 
-	/* disble usb2 ports Wake bits*/
+	/* disable usb2 ports Wake bits */
 	port_index = xhci->num_usb2_ports;
 	port_array = xhci->usb2_ports;
 	while (port_index--) {
@@ -1477,6 +1477,7 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 	struct xhci_ring *ep_ring;
 	struct xhci_virt_ep *ep;
 	struct xhci_command *command;
+	struct xhci_virt_device *vdev;
 
 	xhci = hcd_to_xhci(hcd);
 	spin_lock_irqsave(&xhci->lock, flags);
@@ -1485,15 +1486,27 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 
 	/* Make sure the URB hasn't completed or been unlinked already */
 	ret = usb_hcd_check_unlink_urb(hcd, urb, status);
-	if (ret || !urb->hcpriv)
+	if (ret)
 		goto done;
+
+	/* give back URB now if we can't queue it for cancel */
+	vdev = xhci->devs[urb->dev->slot_id];
+	urb_priv = urb->hcpriv;
+	if (!vdev || !urb_priv)
+		goto err_giveback;
+
+	ep_index = xhci_get_endpoint_index(&urb->ep->desc);
+	ep = &vdev->eps[ep_index];
+	ep_ring = xhci_urb_to_transfer_ring(xhci, urb);
+	if (!ep || !ep_ring)
+		goto err_giveback;
+
 	temp = readl(&xhci->op_regs->status);
 	if (temp == 0xffffffff || (xhci->xhc_state & XHCI_STATE_HALTED)) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 				"HW died, freeing TD.");
-		urb_priv = urb->hcpriv;
 		for (i = urb_priv->num_tds_done;
-		     i < urb_priv->num_tds && xhci->devs[urb->dev->slot_id];
+		     i < urb_priv->num_tds;
 		     i++) {
 			td = &urb_priv->td[i];
 			if (!list_empty(&td->td_list))
@@ -1501,23 +1514,9 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 			if (!list_empty(&td->cancelled_td_list))
 				list_del_init(&td->cancelled_td_list);
 		}
-
-		usb_hcd_unlink_urb_from_ep(hcd, urb);
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		usb_hcd_giveback_urb(hcd, urb, -ESHUTDOWN);
-		xhci_urb_free_priv(urb_priv);
-		return ret;
+		goto err_giveback;
 	}
 
-	ep_index = xhci_get_endpoint_index(&urb->ep->desc);
-	ep = &xhci->devs[urb->dev->slot_id]->eps[ep_index];
-	ep_ring = xhci_urb_to_transfer_ring(xhci, urb);
-	if (!ep_ring) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	urb_priv = urb->hcpriv;
 	i = urb_priv->num_tds_done;
 	if (i < urb_priv->num_tds)
 		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
@@ -1554,6 +1553,14 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 done:
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	return ret;
+
+err_giveback:
+	if (urb_priv)
+		xhci_urb_free_priv(urb_priv);
+	usb_hcd_unlink_urb_from_ep(hcd, urb);
+	spin_unlock_irqrestore(&xhci->lock, flags);
+	usb_hcd_giveback_urb(hcd, urb, -ESHUTDOWN);
+	return ret;
 }
 
 /* Drop an endpoint from a new bandwidth configuration for this device.
diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c
index 8b9fd7534f69..502bfe30a077 100644
--- a/drivers/usb/misc/idmouse.c
+++ b/drivers/usb/misc/idmouse.c
@@ -347,6 +347,9 @@ static int idmouse_probe(struct usb_interface *interface,
 	if (iface_desc->desc.bInterfaceClass != 0x0A)
 		return -ENODEV;
 
+	if (iface_desc->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	/* allocate memory for our device state and initialize it */
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (dev == NULL)
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 095778ff984d..37c63cb39714 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -781,12 +781,6 @@ static int iowarrior_probe(struct usb_interface *interface,
 	iface_desc = interface->cur_altsetting;
 	dev->product_id = le16_to_cpu(udev->descriptor.idProduct);
 
-	if (iface_desc->desc.bNumEndpoints < 1) {
-		dev_err(&interface->dev, "Invalid number of endpoints\n");
-		retval = -EINVAL;
-		goto error;
-	}
-
 	/* set up the endpoint information */
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		endpoint = &iface_desc->endpoint[i].desc;
@@ -797,6 +791,21 @@ static int iowarrior_probe(struct usb_interface *interface,
 			/* this one will match for the IOWarrior56 only */
 			dev->int_out_endpoint = endpoint;
 	}
+
+	if (!dev->int_in_endpoint) {
+		dev_err(&interface->dev, "no interrupt-in endpoint found\n");
+		retval = -ENODEV;
+		goto error;
+	}
+
+	if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+		if (!dev->int_out_endpoint) {
+			dev_err(&interface->dev, "no interrupt-out endpoint found\n");
+			retval = -ENODEV;
+			goto error;
+		}
+	}
+
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c
index 77176511658f..d3d124753266 100644
--- a/drivers/usb/misc/lvstest.c
+++ b/drivers/usb/misc/lvstest.c
@@ -366,6 +366,10 @@ static int lvs_rh_probe(struct usb_interface *intf,
 
 	hdev = interface_to_usbdev(intf);
 	desc = intf->cur_altsetting;
+
+	if (desc->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	endpoint = &desc->endpoint[0].desc;
 
 	/* valid only for SS root hub */
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index 4e18600dc9b4..91f66d68bcb7 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -375,18 +375,24 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 	if (of_get_property(np, "dynamic-power-switching", NULL))
 		hub->conf_data2 |= BIT(7);
 
-	if (of_get_property(np, "oc-delay-100us", NULL)) {
-		hub->conf_data2 &= ~BIT(5);
-		hub->conf_data2 &= ~BIT(4);
-	} else if (of_get_property(np, "oc-delay-4ms", NULL)) {
-		hub->conf_data2 &= ~BIT(5);
-		hub->conf_data2 |= BIT(4);
-	} else if (of_get_property(np, "oc-delay-8ms", NULL)) {
-		hub->conf_data2 |= BIT(5);
-		hub->conf_data2 &= ~BIT(4);
-	} else if (of_get_property(np, "oc-delay-16ms", NULL)) {
-		hub->conf_data2 |= BIT(5);
-		hub->conf_data2 |= BIT(4);
+	if (!of_property_read_u32(np, "oc-delay-us", property_u32)) {
+		if (*property_u32 == 100) {
+			/* 100 us*/
+			hub->conf_data2 &= ~BIT(5);
+			hub->conf_data2 &= ~BIT(4);
+		} else if (*property_u32 == 4000) {
+			/* 4 ms */
+			hub->conf_data2 &= ~BIT(5);
+			hub->conf_data2 |= BIT(4);
+		} else if (*property_u32 == 16000) {
+			/* 16 ms */
+			hub->conf_data2 |= BIT(5);
+			hub->conf_data2 |= BIT(4);
+		} else {
+			/* 8 ms (DEFAULT) */
+			hub->conf_data2 |= BIT(5);
+			hub->conf_data2 &= ~BIT(4);
+		}
 	}
 
 	if (of_get_property(np, "compound-device", NULL))
@@ -432,30 +438,9 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 		}
 	}
 
-	hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
-	if (!of_property_read_u32(np, "max-sp-power", property_u32))
-		hub->max_power_sp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					  250);
-
-	hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS;
-	if (!of_property_read_u32(np, "max-bp-power", property_u32))
-		hub->max_power_bp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					  250);
-
-	hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF;
-	if (!of_property_read_u32(np, "max-sp-current", property_u32))
-		hub->max_current_sp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					    250);
-
-	hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS;
-	if (!of_property_read_u32(np, "max-bp-current", property_u32))
-		hub->max_current_bp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					    250);
-
 	hub->power_on_time = USB251XB_DEF_POWER_ON_TIME;
-	if (!of_property_read_u32(np, "power-on-time", property_u32))
-		hub->power_on_time = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					   255);
+	if (!of_property_read_u32(np, "power-on-time-ms", property_u32))
+		hub->power_on_time = min_t(u8, *property_u32 / 2, 255);
 
 	if (of_property_read_u16_array(np, "language-id", &hub->lang_id, 1))
 		hub->lang_id = USB251XB_DEF_LANGUAGE_ID;
@@ -492,6 +477,10 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 	/* The following parameters are currently not exposed to devicetree, but
 	 * may be as soon as needed.
 	 */
+	hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
+	hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS;
+	hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF;
+	hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS;
 	hub->bat_charge_en = USB251XB_DEF_BATTERY_CHARGING_ENABLE;
 	hub->boost_up = USB251XB_DEF_BOOST_UP;
 	hub->boost_x = USB251XB_DEF_BOOST_X;
diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index e45a3a680db8..07014cad6dbe 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -709,6 +709,11 @@ static int uss720_probe(struct usb_interface *intf,
 
 	interface = intf->cur_altsetting;
 
+	if (interface->desc.bNumEndpoints < 3) {
+		usb_put_dev(usbdev);
+		return -ENODEV;
+	}
+
 	/*
 	 * Allocate parport interface 
 	 */
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index d8bae6ca8904..0c3664ab705e 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2490,8 +2490,8 @@ static int musb_remove(struct platform_device *pdev)
 	musb_host_cleanup(musb);
 	musb_gadget_cleanup(musb);
 
-	spin_lock_irqsave(&musb->lock, flags);
 	musb_platform_disable(musb);
+	spin_lock_irqsave(&musb->lock, flags);
 	musb_disable_interrupts(musb);
 	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
 	spin_unlock_irqrestore(&musb->lock, flags);
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index 00e272bfee39..355655f8a3fb 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -238,8 +238,27 @@ static void cppi41_dma_callback(void *private_data,
 			transferred < cppi41_channel->packet_sz)
 		cppi41_channel->prog_len = 0;
 
-	if (cppi41_channel->is_tx)
-		empty = musb_is_tx_fifo_empty(hw_ep);
+	if (cppi41_channel->is_tx) {
+		u8 type;
+
+		if (is_host_active(musb))
+			type = hw_ep->out_qh->type;
+		else
+			type = hw_ep->ep_in.type;
+
+		if (type == USB_ENDPOINT_XFER_ISOC)
+			/*
+			 * Don't use the early-TX-interrupt workaround below
+			 * for Isoch transfter. Since Isoch are periodic
+			 * transfer, by the time the next transfer is
+			 * scheduled, the current one should be done already.
+			 *
+			 * This avoids audio playback underrun issue.
+			 */
+			empty = true;
+		else
+			empty = musb_is_tx_fifo_empty(hw_ep);
+	}
 
 	if (!cppi41_channel->is_tx || empty) {
 		cppi41_trans_done(cppi41_channel);
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 7c047c4a2565..9c7ee26ef388 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -933,7 +933,7 @@ static int dsps_probe(struct platform_device *pdev)
 	if (usb_get_dr_mode(&pdev->dev) == USB_DR_MODE_PERIPHERAL) {
 		ret = dsps_setup_optional_vbus_irq(pdev, glue);
 		if (ret)
-			return ret;
+			goto err_iounmap;
 	}
 
 	platform_set_drvdata(pdev, glue);
@@ -946,6 +946,8 @@ static int dsps_probe(struct platform_device *pdev)
 
 err:
 	pm_runtime_disable(&pdev->dev);
+err_iounmap:
+	iounmap(glue->usbss_base);
 	return ret;
 }
 
@@ -956,6 +958,7 @@ static int dsps_remove(struct platform_device *pdev)
 	platform_device_unregister(glue->musb);
 
 	pm_runtime_disable(&pdev->dev);
+	iounmap(glue->usbss_base);
 
 	return 0;
 }
diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c
index db68156568e6..f333024660b4 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -33,6 +33,12 @@ static const struct i2c_device_id isp1301_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, isp1301_id);
 
+static const struct of_device_id isp1301_of_match[] = {
+	{.compatible = "nxp,isp1301" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, isp1301_of_match);
+
 static struct i2c_client *isp1301_i2c_client;
 
 static int __isp1301_write(struct isp1301 *isp, u8 reg, u8 value, u8 clear)
@@ -130,6 +136,7 @@ static int isp1301_remove(struct i2c_client *client)
 static struct i2c_driver isp1301_driver = {
 	.driver = {
 		.name = DRV_NAME,
+		.of_match_table = isp1301_of_match,
 	},
 	.probe = isp1301_probe,
 	.remove = isp1301_remove,
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index ab78111e0968..6537d3ca2797 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -1500,7 +1500,7 @@ static int digi_read_oob_callback(struct urb *urb)
 		return -1;
 
 	/* handle each oob command */
-	for (i = 0; i < urb->actual_length - 4; i += 4) {
+	for (i = 0; i < urb->actual_length - 3; i += 4) {
 		opcode = buf[i];
 		line = buf[i + 1];
 		status = buf[i + 2];
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index ceaeebaa6f90..a76b95d32157 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -1674,6 +1674,12 @@ static void edge_interrupt_callback(struct urb *urb)
 	function    = TIUMP_GET_FUNC_FROM_CODE(data[0]);
 	dev_dbg(dev, "%s - port_number %d, function %d, info 0x%x\n", __func__,
 		port_number, function, data[1]);
+
+	if (port_number >= edge_serial->serial->num_ports) {
+		dev_err(dev, "bad port number %d\n", port_number);
+		goto exit;
+	}
+
 	port = edge_serial->serial->port[port_number];
 	edge_port = usb_get_serial_port_data(port);
 	if (!edge_port) {
@@ -1755,7 +1761,7 @@ static void edge_bulk_in_callback(struct urb *urb)
 
 	port_number = edge_port->port->port_number;
 
-	if (edge_port->lsr_event) {
+	if (urb->actual_length > 0 && edge_port->lsr_event) {
 		edge_port->lsr_event = 0;
 		dev_dbg(dev, "%s ===== Port %u LSR Status = %02x, Data = %02x ======\n",
 			__func__, port_number, edge_port->lsr_mask, *data);
diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index a180b17d2432..dd706953b466 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -31,7 +31,6 @@
 #define BT_IGNITIONPRO_ID	0x2000
 
 /* function prototypes */
-static int  omninet_open(struct tty_struct *tty, struct usb_serial_port *port);
 static void omninet_process_read_urb(struct urb *urb);
 static void omninet_write_bulk_callback(struct urb *urb);
 static int  omninet_write(struct tty_struct *tty, struct usb_serial_port *port,
@@ -60,7 +59,6 @@ static struct usb_serial_driver zyxel_omninet_device = {
 	.attach =		omninet_attach,
 	.port_probe =		omninet_port_probe,
 	.port_remove =		omninet_port_remove,
-	.open =			omninet_open,
 	.write =		omninet_write,
 	.write_room =		omninet_write_room,
 	.write_bulk_callback =	omninet_write_bulk_callback,
@@ -140,17 +138,6 @@ static int omninet_port_remove(struct usb_serial_port *port)
 	return 0;
 }
 
-static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port)
-{
-	struct usb_serial	*serial = port->serial;
-	struct usb_serial_port	*wport;
-
-	wport = serial->port[1];
-	tty_port_tty_set(&wport->port, tty);
-
-	return usb_serial_generic_open(tty, port);
-}
-
 #define OMNINET_HEADERLEN	4
 #define OMNINET_BULKOUTSIZE	64
 #define OMNINET_PAYLOADSIZE	(OMNINET_BULKOUTSIZE - OMNINET_HEADERLEN)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 42cc72e54c05..af67a0de6b5d 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -233,6 +233,14 @@ static void option_instat_callback(struct urb *urb);
 #define BANDRICH_PRODUCT_1012			0x1012
 
 #define QUALCOMM_VENDOR_ID			0x05C6
+/* These Quectel products use Qualcomm's vendor ID */
+#define QUECTEL_PRODUCT_UC20			0x9003
+#define QUECTEL_PRODUCT_UC15			0x9090
+
+#define QUECTEL_VENDOR_ID			0x2c7c
+/* These Quectel products use Quectel's vendor ID */
+#define QUECTEL_PRODUCT_EC21			0x0121
+#define QUECTEL_PRODUCT_EC25			0x0125
 
 #define CMOTECH_VENDOR_ID			0x16d8
 #define CMOTECH_PRODUCT_6001			0x6001
@@ -1161,7 +1169,14 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
-	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */
+	/* Quectel products using Qualcomm vendor ID */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	/* Quectel products using Quectel vendor ID */
+	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 696458db7e3c..38b3f0d8cd58 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -169,6 +169,8 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81a9)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81b1)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+	{DEVICE_SWI(0x413c, 0x81b5)},	/* Dell Wireless 5811e QDL */
+	{DEVICE_SWI(0x413c, 0x81b6)},	/* Dell Wireless 5811e QDL */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c
index 93c6c9b08daa..8a069aa154ed 100644
--- a/drivers/usb/serial/safe_serial.c
+++ b/drivers/usb/serial/safe_serial.c
@@ -200,6 +200,11 @@ static void safe_process_read_urb(struct urb *urb)
 	if (!safe)
 		goto out;
 
+	if (length < 2) {
+		dev_err(&port->dev, "malformed packet\n");
+		return;
+	}
+
 	fcs = fcs_compute10(data, length, CRC10_INITFCS);
 	if (fcs) {
 		dev_err(&port->dev, "%s - bad CRC %x\n", __func__, fcs);
diff --git a/drivers/usb/serial/usb_debug.c b/drivers/usb/serial/usb_debug.c
index ca2fa5bbe17e..92f7e5c21162 100644
--- a/drivers/usb/serial/usb_debug.c
+++ b/drivers/usb/serial/usb_debug.c
@@ -32,7 +32,18 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x0525, 0x127a) },
 	{ },
 };
-MODULE_DEVICE_TABLE(usb, id_table);
+
+static const struct usb_device_id dbc_id_table[] = {
+	{ USB_DEVICE(0x1d6b, 0x0004) },
+	{ },
+};
+
+static const struct usb_device_id id_table_combined[] = {
+	{ USB_DEVICE(0x0525, 0x127a) },
+	{ USB_DEVICE(0x1d6b, 0x0004) },
+	{ },
+};
+MODULE_DEVICE_TABLE(usb, id_table_combined);
 
 /* This HW really does not support a serial break, so one will be
  * emulated when ever the break state is set to true.
@@ -71,9 +82,20 @@ static struct usb_serial_driver debug_device = {
 	.process_read_urb =	usb_debug_process_read_urb,
 };
 
+static struct usb_serial_driver dbc_device = {
+	.driver = {
+		.owner =	THIS_MODULE,
+		.name =		"xhci_dbc",
+	},
+	.id_table =		dbc_id_table,
+	.num_ports =		1,
+	.break_ctl =		usb_debug_break_ctl,
+	.process_read_urb =	usb_debug_process_read_urb,
+};
+
 static struct usb_serial_driver * const serial_drivers[] = {
-	&debug_device, NULL
+	&debug_device, &dbc_device, NULL
 };
 
-module_usb_serial_driver(serial_drivers, id_table);
+module_usb_serial_driver(serial_drivers, id_table_combined);
 MODULE_LICENSE("GPL");
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 16cc18369111..9129f6cb8230 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2071,6 +2071,20 @@ UNUSUAL_DEV(  0x1370, 0x6828, 0x0110, 0x0110,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/*
+ * Reported by Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
+ * The INIC-3619 bridge is used in the StarTech SLSODDU33B
+ * SATA-USB enclosure for slimline optical drives.
+ *
+ * The quirk enables MakeMKV to properly exchange keys with
+ * an installed BD drive.
+ */
+UNUSUAL_DEV(  0x13fd, 0x3609, 0x0209, 0x0209,
+		"Initio Corporation",
+		"INIC-3619",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* Reported by Qinglin Ye <yestyle@gmail.com> */
 UNUSUAL_DEV(  0x13fe, 0x3600, 0x0100, 0x0100,
 		"Kingston",
diff --git a/drivers/usb/wusbcore/wa-hc.c b/drivers/usb/wusbcore/wa-hc.c
index 252c7bd9218a..d01496fd27fe 100644
--- a/drivers/usb/wusbcore/wa-hc.c
+++ b/drivers/usb/wusbcore/wa-hc.c
@@ -39,6 +39,9 @@ int wa_create(struct wahc *wa, struct usb_interface *iface,
 	int result;
 	struct device *dev = &iface->dev;
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 3)
+		return -ENODEV;
+
 	result = wa_rpipes_create(wa);
 	if (result < 0)
 		goto error_rpipes_create;
diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c
index 0aa6c3c29d17..35a1e777b449 100644
--- a/drivers/uwb/hwa-rc.c
+++ b/drivers/uwb/hwa-rc.c
@@ -823,6 +823,9 @@ static int hwarc_probe(struct usb_interface *iface,
 	struct hwarc *hwarc;
 	struct device *dev = &iface->dev;
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	result = -ENOMEM;
 	uwb_rc = uwb_rc_alloc();
 	if (uwb_rc == NULL) {
diff --git a/drivers/uwb/i1480/dfu/usb.c b/drivers/uwb/i1480/dfu/usb.c
index 2bfc846ac071..6345e85822a4 100644
--- a/drivers/uwb/i1480/dfu/usb.c
+++ b/drivers/uwb/i1480/dfu/usb.c
@@ -362,6 +362,9 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id)
 				 result);
 	}
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	result = -ENOMEM;
 	i1480_usb = kzalloc(sizeof(*i1480_usb), GFP_KERNEL);
 	if (i1480_usb == NULL) {
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 609f4f982c74..561084ab387f 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -403,6 +403,7 @@ static void vfio_group_release(struct kref *kref)
 	struct iommu_group *iommu_group = group->iommu_group;
 
 	WARN_ON(!list_empty(&group->device_list));
+	WARN_ON(group->notifier.head);
 
 	list_for_each_entry_safe(unbound, tmp,
 				 &group->unbound_list, unbound_next) {
@@ -1573,6 +1574,10 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep)
 		return -EBUSY;
 	}
 
+	/* Warn if previous user didn't cleanup and re-init to drop them */
+	if (WARN_ON(group->notifier.head))
+		BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
+
 	filep->private_data = group;
 
 	return 0;
@@ -1584,9 +1589,6 @@ static int vfio_group_fops_release(struct inode *inode, struct file *filep)
 
 	filep->private_data = NULL;
 
-	/* Any user didn't unregister? */
-	WARN_ON(group->notifier.head);
-
 	vfio_group_try_dissolve_container(group);
 
 	atomic_dec(&group->opened);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c26fa1f3ed86..32d2633092a3 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1182,8 +1182,7 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
-static bool vfio_iommu_has_resv_msi(struct iommu_group *group,
-				    phys_addr_t *base)
+static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base)
 {
 	struct list_head group_resv_regions;
 	struct iommu_resv_region *region, *next;
@@ -1192,7 +1191,7 @@ static bool vfio_iommu_has_resv_msi(struct iommu_group *group,
 	INIT_LIST_HEAD(&group_resv_regions);
 	iommu_get_group_resv_regions(group, &group_resv_regions);
 	list_for_each_entry(region, &group_resv_regions, list) {
-		if (region->type & IOMMU_RESV_MSI) {
+		if (region->type == IOMMU_RESV_SW_MSI) {
 			*base = region->start;
 			ret = true;
 			goto out;
@@ -1283,7 +1282,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_domain;
 
-	resv_msi = vfio_iommu_has_resv_msi(iommu_group, &resv_msi_base);
+	resv_msi = vfio_iommu_has_sw_msi(iommu_group, &resv_msi_base);
 
 	INIT_LIST_HEAD(&domain->group_list);
 	list_add(&group->next, &domain->group_list);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ce5e63d2c66a..d939ac1a4997 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -176,6 +176,11 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 				restart_tx = true;
 		}
 
+		/* Deliver to monitoring devices all correctly transmitted
+		 * packets.
+		 */
+		virtio_transport_deliver_tap_pkt(pkt);
+
 		virtio_transport_free_pkt(pkt);
 	}
 	if (added)
@@ -223,6 +228,46 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 	return len;
 }
 
+static int
+vhost_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+	struct vhost_vsock *vsock;
+	struct virtio_vsock_pkt *pkt, *n;
+	int cnt = 0;
+	LIST_HEAD(freeme);
+
+	/* Find the vhost_vsock according to guest context id  */
+	vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
+	if (!vsock)
+		return -ENODEV;
+
+	spin_lock_bh(&vsock->send_pkt_list_lock);
+	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+		if (pkt->vsk != vsk)
+			continue;
+		list_move(&pkt->list, &freeme);
+	}
+	spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+	list_for_each_entry_safe(pkt, n, &freeme, list) {
+		if (pkt->reply)
+			cnt++;
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	if (cnt) {
+		struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
+		int new_cnt;
+
+		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
+		if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
+			vhost_poll_queue(&tx_vq->poll);
+	}
+
+	return 0;
+}
+
 static struct virtio_vsock_pkt *
 vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		      unsigned int out, unsigned int in)
@@ -343,6 +388,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 
 		len = pkt->len;
 
+		/* Deliver to monitoring devices all received packets */
+		virtio_transport_deliver_tap_pkt(pkt);
+
 		/* Only accept correctly addressed packets */
 		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
 			virtio_transport_recv_pkt(pkt);
@@ -675,6 +723,7 @@ static struct virtio_transport vhost_transport = {
 		.release                  = virtio_transport_release,
 		.connect                  = virtio_transport_connect,
 		.shutdown                 = virtio_transport_shutdown,
+		.cancel_pkt               = vhost_transport_cancel_pkt,
 
 		.dgram_enqueue            = virtio_transport_dgram_enqueue,
 		.dgram_dequeue            = virtio_transport_dgram_dequeue,
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index d7efcb632f7d..002f1ce22bd0 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -297,14 +297,15 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	}
 
 	/*
-	 * If the GPIO is configured as input, change the direction to output
-	 * and set the GPIO as active.
+	 * If the GPIO is not known to be already configured as output, that
+	 * is, if gpiod_get_direction returns either GPIOF_DIR_IN or -EINVAL,
+	 * change the direction to output and set the GPIO as active.
 	 * Do not force the GPIO to active when it was already output as it
 	 * could cause backlight flickering or we would enable the backlight too
 	 * early. Leave the decision of the initial backlight state for later.
 	 */
 	if (pb->enable_gpio &&
-	    gpiod_get_direction(pb->enable_gpio) == GPIOF_DIR_IN)
+	    gpiod_get_direction(pb->enable_gpio) != GPIOF_DIR_OUT)
 		gpiod_direction_output(pb->enable_gpio, 1);
 
 	pb->power_supply = devm_regulator_get(&pdev->dev, "power");
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 8c4dc1e1f94f..b827a8113e26 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/errno.h>
 #include <linux/fb.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/screen_info.h>
 #include <video/vga.h>
@@ -143,6 +144,8 @@ static struct attribute *efifb_attrs[] = {
 };
 ATTRIBUTE_GROUPS(efifb);
 
+static bool pci_dev_disabled;	/* FB base matches BAR of a disabled device */
+
 static int efifb_probe(struct platform_device *dev)
 {
 	struct fb_info *info;
@@ -152,7 +155,7 @@ static int efifb_probe(struct platform_device *dev)
 	unsigned int size_total;
 	char *option = NULL;
 
-	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
+	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
 		return -ENODEV;
 
 	if (fb_get_options("efifb", &option))
@@ -360,3 +363,64 @@ static struct platform_driver efifb_driver = {
 };
 
 builtin_platform_driver(efifb_driver);
+
+#if defined(CONFIG_PCI) && !defined(CONFIG_X86)
+
+static bool pci_bar_found;	/* did we find a BAR matching the efifb base? */
+
+static void claim_efifb_bar(struct pci_dev *dev, int idx)
+{
+	u16 word;
+
+	pci_bar_found = true;
+
+	pci_read_config_word(dev, PCI_COMMAND, &word);
+	if (!(word & PCI_COMMAND_MEMORY)) {
+		pci_dev_disabled = true;
+		dev_err(&dev->dev,
+			"BAR %d: assigned to efifb but device is disabled!\n",
+			idx);
+		return;
+	}
+
+	if (pci_claim_resource(dev, idx)) {
+		pci_dev_disabled = true;
+		dev_err(&dev->dev,
+			"BAR %d: failed to claim resource for efifb!\n", idx);
+		return;
+	}
+
+	dev_info(&dev->dev, "BAR %d: assigned to efifb\n", idx);
+}
+
+static void efifb_fixup_resources(struct pci_dev *dev)
+{
+	u64 base = screen_info.lfb_base;
+	u64 size = screen_info.lfb_size;
+	int i;
+
+	if (pci_bar_found || screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
+		return;
+
+	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)screen_info.ext_lfb_base << 32;
+
+	if (!base)
+		return;
+
+	for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+		struct resource *res = &dev->resource[i];
+
+		if (!(res->flags & IORESOURCE_MEM))
+			continue;
+
+		if (res->start <= base && res->end >= base + size - 1) {
+			claim_efifb_bar(dev, i);
+			break;
+		}
+	}
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY,
+			       16, efifb_fixup_resources);
+
+#endif
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index 1abba07b84b3..f4cbfb3b8a09 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -1608,19 +1608,6 @@ static int omapfb_find_ctrl(struct omapfb_device *fbdev)
 	return 0;
 }
 
-static void check_required_callbacks(struct omapfb_device *fbdev)
-{
-#define _C(x) (fbdev->ctrl->x != NULL)
-#define _P(x) (fbdev->panel->x != NULL)
-	BUG_ON(fbdev->ctrl == NULL || fbdev->panel == NULL);
-	BUG_ON(!(_C(init) && _C(cleanup) && _C(get_caps) &&
-		 _C(set_update_mode) && _C(setup_plane) && _C(enable_plane) &&
-		 _P(init) && _P(cleanup) && _P(enable) && _P(disable) &&
-		 _P(get_caps)));
-#undef _P
-#undef _C
-}
-
 /*
  * Called by LDM binding to probe and attach a new device.
  * Initialization sequence:
@@ -1705,8 +1692,6 @@ static int omapfb_do_probe(struct platform_device *pdev,
 		omapfb_ops.fb_mmap = omapfb_mmap;
 	init_state++;
 
-	check_required_callbacks(fbdev);
-
 	r = planes_init(fbdev);
 	if (r)
 		goto cleanup;
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index bd017b57c47f..f599520374dd 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -578,10 +578,14 @@ static int ssd1307fb_probe(struct i2c_client *client,
 
 	par->vbat_reg = devm_regulator_get_optional(&client->dev, "vbat");
 	if (IS_ERR(par->vbat_reg)) {
-		dev_err(&client->dev, "failed to get VBAT regulator: %ld\n",
-			PTR_ERR(par->vbat_reg));
 		ret = PTR_ERR(par->vbat_reg);
-		goto fb_alloc_error;
+		if (ret == -ENODEV) {
+			par->vbat_reg = NULL;
+		} else {
+			dev_err(&client->dev, "failed to get VBAT regulator: %d\n",
+				ret);
+			goto fb_alloc_error;
+		}
 	}
 
 	if (of_property_read_u32(node, "solomon,width", &par->width))
@@ -668,10 +672,13 @@ static int ssd1307fb_probe(struct i2c_client *client,
 		udelay(4);
 	}
 
-	ret = regulator_enable(par->vbat_reg);
-	if (ret) {
-		dev_err(&client->dev, "failed to enable VBAT: %d\n", ret);
-		goto reset_oled_error;
+	if (par->vbat_reg) {
+		ret = regulator_enable(par->vbat_reg);
+		if (ret) {
+			dev_err(&client->dev, "failed to enable VBAT: %d\n",
+				ret);
+			goto reset_oled_error;
+		}
 	}
 
 	ret = ssd1307fb_init(par);
@@ -710,7 +717,8 @@ panel_init_error:
 		pwm_put(par->pwm);
 	};
 regulator_enable_error:
-	regulator_disable(par->vbat_reg);
+	if (par->vbat_reg)
+		regulator_disable(par->vbat_reg);
 reset_oled_error:
 	fb_deferred_io_cleanup(info);
 fb_alloc_error:
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index d0115a7af0a9..3ee309c50b2d 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -643,7 +643,6 @@ static void xenfb_backend_changed(struct xenbus_device *dev,
 		break;
 
 	case XenbusStateInitWait:
-InitWait:
 		xenbus_switch_state(dev, XenbusStateConnected);
 		break;
 
@@ -654,7 +653,8 @@ InitWait:
 		 * get Connected twice here.
 		 */
 		if (dev->state != XenbusStateConnected)
-			goto InitWait; /* no InitWait seen yet, fudge it */
+			/* no InitWait seen yet, fudge it */
+			xenbus_switch_state(dev, XenbusStateConnected);
 
 		if (xenbus_read_unsigned(info->xbdev->otherend,
 					 "request-update", 0))
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 400d70b69379..48230a5e12f2 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -232,6 +232,12 @@ static int virtio_dev_probe(struct device *_d)
 		if (device_features & (1ULL << i))
 			__virtio_set_bit(dev, i);
 
+	if (drv->validate) {
+		err = drv->validate(dev);
+		if (err)
+			goto err;
+	}
+
 	err = virtio_finalize_features(dev);
 	if (err)
 		goto err;
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 4e1191508228..34adf9b9c053 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -242,11 +242,11 @@ static inline void update_stat(struct virtio_balloon *vb, int idx,
 
 #define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
 
-static void update_balloon_stats(struct virtio_balloon *vb)
+static unsigned int update_balloon_stats(struct virtio_balloon *vb)
 {
 	unsigned long events[NR_VM_EVENT_ITEMS];
 	struct sysinfo i;
-	int idx = 0;
+	unsigned int idx = 0;
 	long available;
 
 	all_vm_events(events);
@@ -254,18 +254,22 @@ static void update_balloon_stats(struct virtio_balloon *vb)
 
 	available = si_mem_available();
 
+#ifdef CONFIG_VM_EVENT_COUNTERS
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
 				pages_to_bytes(events[PSWPIN]));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
 				pages_to_bytes(events[PSWPOUT]));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
+#endif
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
 				pages_to_bytes(i.freeram));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
 				pages_to_bytes(i.totalram));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
 				pages_to_bytes(available));
+
+	return idx;
 }
 
 /*
@@ -291,14 +295,14 @@ static void stats_handle_request(struct virtio_balloon *vb)
 {
 	struct virtqueue *vq;
 	struct scatterlist sg;
-	unsigned int len;
+	unsigned int len, num_stats;
 
-	update_balloon_stats(vb);
+	num_stats = update_balloon_stats(vb);
 
 	vq = vb->stats_vq;
 	if (!virtqueue_get_buf(vq, &len))
 		return;
-	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+	sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
 	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
 	virtqueue_kick(vq);
 }
@@ -423,13 +427,16 @@ static int init_vqs(struct virtio_balloon *vb)
 	vb->deflate_vq = vqs[1];
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
 		struct scatterlist sg;
+		unsigned int num_stats;
 		vb->stats_vq = vqs[2];
 
 		/*
 		 * Prime this virtqueue with one buffer so the hypervisor can
 		 * use it to signal us later (it can't be broken yet!).
 		 */
-		sg_init_one(&sg, vb->stats, sizeof vb->stats);
+		num_stats = update_balloon_stats(vb);
+
+		sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
 		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
 		    < 0)
 			BUG();
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index df548a6fb844..698d5d06fa03 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -33,8 +33,10 @@ void vp_synchronize_vectors(struct virtio_device *vdev)
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i;
 
-	synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0));
-	for (i = 1; i < vp_dev->msix_vectors; i++)
+	if (vp_dev->intx_enabled)
+		synchronize_irq(vp_dev->pci_dev->irq);
+
+	for (i = 0; i < vp_dev->msix_vectors; ++i)
 		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
 }
 
@@ -60,13 +62,16 @@ static irqreturn_t vp_config_changed(int irq, void *opaque)
 static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
 {
 	struct virtio_pci_device *vp_dev = opaque;
+	struct virtio_pci_vq_info *info;
 	irqreturn_t ret = IRQ_NONE;
-	struct virtqueue *vq;
+	unsigned long flags;
 
-	list_for_each_entry(vq, &vp_dev->vdev.vqs, list) {
-		if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED)
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_for_each_entry(info, &vp_dev->virtqueues, node) {
+		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
 	}
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
 	return ret;
 }
@@ -97,185 +102,244 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
 	return vp_vring_interrupt(irq, opaque);
 }
 
-static void vp_remove_vqs(struct virtio_device *vdev)
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+				   bool per_vq_vectors, struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtqueue *vq, *n;
+	const char *name = dev_name(&vp_dev->vdev.dev);
+	unsigned i, v;
+	int err = -ENOMEM;
 
-	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
-		if (vp_dev->msix_vector_map) {
-			int v = vp_dev->msix_vector_map[vq->index];
+	vp_dev->msix_vectors = nvectors;
 
-			if (v != VIRTIO_MSI_NO_VECTOR)
-				free_irq(pci_irq_vector(vp_dev->pci_dev, v),
-					vq);
-		}
-		vp_dev->del_vq(vq);
+	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
+				     GFP_KERNEL);
+	if (!vp_dev->msix_names)
+		goto error;
+	vp_dev->msix_affinity_masks
+		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+			  GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto error;
+	for (i = 0; i < nvectors; ++i)
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+					GFP_KERNEL))
+			goto error;
+
+	err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
+					     nvectors, PCI_IRQ_MSIX |
+					     (desc ? PCI_IRQ_AFFINITY : 0),
+					     desc);
+	if (err < 0)
+		goto error;
+	vp_dev->msix_enabled = 1;
+
+	/* Set the vector used for configuration */
+	v = vp_dev->msix_used_vectors;
+	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+		 "%s-config", name);
+	err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+			  vp_config_changed, 0, vp_dev->msix_names[v],
+			  vp_dev);
+	if (err)
+		goto error;
+	++vp_dev->msix_used_vectors;
+
+	v = vp_dev->config_vector(vp_dev, v);
+	/* Verify we had enough resources to assign the vector */
+	if (v == VIRTIO_MSI_NO_VECTOR) {
+		err = -EBUSY;
+		goto error;
 	}
+
+	if (!per_vq_vectors) {
+		/* Shared vector for all VQs */
+		v = vp_dev->msix_used_vectors;
+		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+			 "%s-virtqueues", name);
+		err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
+				  vp_dev);
+		if (err)
+			goto error;
+		++vp_dev->msix_used_vectors;
+	}
+	return 0;
+error:
+	return err;
+}
+
+static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
+				     void (*callback)(struct virtqueue *vq),
+				     const char *name,
+				     u16 msix_vec)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
+	struct virtqueue *vq;
+	unsigned long flags;
+
+	/* fill out our structure that represents an active queue */
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name,
+			      msix_vec);
+	if (IS_ERR(vq))
+		goto out_info;
+
+	info->vq = vq;
+	if (callback) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		list_add(&info->node, &vp_dev->virtqueues);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	} else {
+		INIT_LIST_HEAD(&info->node);
+	}
+
+	vp_dev->vqs[index] = info;
+	return vq;
+
+out_info:
+	kfree(info);
+	return vq;
+}
+
+static void vp_del_vq(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	vp_dev->del_vq(info);
+	kfree(info);
 }
 
 /* the config->del_vqs() implementation */
 void vp_del_vqs(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq, *n;
 	int i;
 
-	if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs)))
-		return;
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		if (vp_dev->per_vq_vectors) {
+			int v = vp_dev->vqs[vq->index]->msix_vector;
 
-	vp_remove_vqs(vdev);
+			if (v != VIRTIO_MSI_NO_VECTOR) {
+				int irq = pci_irq_vector(vp_dev->pci_dev, v);
+
+				irq_set_affinity_hint(irq, NULL);
+				free_irq(irq, vq);
+			}
+		}
+		vp_del_vq(vq);
+	}
+	vp_dev->per_vq_vectors = false;
+
+	if (vp_dev->intx_enabled) {
+		free_irq(vp_dev->pci_dev->irq, vp_dev);
+		vp_dev->intx_enabled = 0;
+	}
 
-	if (vp_dev->pci_dev->msix_enabled) {
-		for (i = 0; i < vp_dev->msix_vectors; i++)
+	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+		free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
+
+	for (i = 0; i < vp_dev->msix_vectors; i++)
+		if (vp_dev->msix_affinity_masks[i])
 			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
 
+	if (vp_dev->msix_enabled) {
 		/* Disable the vector used for configuration */
 		vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
 
-		kfree(vp_dev->msix_affinity_masks);
-		kfree(vp_dev->msix_names);
-		kfree(vp_dev->msix_vector_map);
+		pci_free_irq_vectors(vp_dev->pci_dev);
+		vp_dev->msix_enabled = 0;
 	}
 
-	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
-	pci_free_irq_vectors(vp_dev->pci_dev);
+	vp_dev->msix_vectors = 0;
+	vp_dev->msix_used_vectors = 0;
+	kfree(vp_dev->msix_names);
+	vp_dev->msix_names = NULL;
+	kfree(vp_dev->msix_affinity_masks);
+	vp_dev->msix_affinity_masks = NULL;
+	kfree(vp_dev->vqs);
+	vp_dev->vqs = NULL;
 }
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], struct irq_affinity *desc)
+		const char * const names[], bool per_vq_vectors,
+		struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	const char *name = dev_name(&vp_dev->vdev.dev);
-	int i, err = -ENOMEM, allocated_vectors, nvectors;
-	unsigned flags = PCI_IRQ_MSIX;
-	bool shared = false;
 	u16 msix_vec;
+	int i, err, nvectors, allocated_vectors;
 
-	if (desc) {
-		flags |= PCI_IRQ_AFFINITY;
-		desc->pre_vectors++; /* virtio config vector */
-	}
-
-	nvectors = 1;
-	for (i = 0; i < nvqs; i++)
-		if (callbacks[i])
-			nvectors++;
-
-	/* Try one vector per queue first. */
-	err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
-			nvectors, flags, desc);
-	if (err < 0) {
-		/* Fallback to one vector for config, one shared for queues. */
-		shared = true;
-		err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2,
-				PCI_IRQ_MSIX);
-		if (err < 0)
-			return err;
-	}
-	if (err < 0)
-		return err;
-
-	vp_dev->msix_vectors = nvectors;
-	vp_dev->msix_names = kmalloc_array(nvectors,
-			sizeof(*vp_dev->msix_names), GFP_KERNEL);
-	if (!vp_dev->msix_names)
-		goto out_free_irq_vectors;
-
-	vp_dev->msix_affinity_masks = kcalloc(nvectors,
-			sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL);
-	if (!vp_dev->msix_affinity_masks)
-		goto out_free_msix_names;
+	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
+	if (!vp_dev->vqs)
+		return -ENOMEM;
 
-	for (i = 0; i < nvectors; ++i) {
-		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
-				GFP_KERNEL))
-			goto out_free_msix_affinity_masks;
+	if (per_vq_vectors) {
+		/* Best option: one for change interrupt, one per vq. */
+		nvectors = 1;
+		for (i = 0; i < nvqs; ++i)
+			if (callbacks[i])
+				++nvectors;
+	} else {
+		/* Second best: one for change, shared for all vqs. */
+		nvectors = 2;
 	}
 
-	/* Set the vector used for configuration */
-	snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names),
-		 "%s-config", name);
-	err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed,
-			0, vp_dev->msix_names[0], vp_dev);
+	err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors,
+				      per_vq_vectors ? desc : NULL);
 	if (err)
-		goto out_free_msix_affinity_masks;
+		goto error_find;
 
-	/* Verify we had enough resources to assign the vector */
-	if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) {
-		err = -EBUSY;
-		goto out_free_config_irq;
-	}
-
-	vp_dev->msix_vector_map = kmalloc_array(nvqs,
-			sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
-	if (!vp_dev->msix_vector_map)
-		goto out_disable_config_irq;
-
-	allocated_vectors = 1; /* vector 0 is the config interrupt */
+	vp_dev->per_vq_vectors = per_vq_vectors;
+	allocated_vectors = vp_dev->msix_used_vectors;
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
 			continue;
 		}
 
-		if (callbacks[i])
-			msix_vec = allocated_vectors;
-		else
+		if (!callbacks[i])
 			msix_vec = VIRTIO_MSI_NO_VECTOR;
-
-		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
-				msix_vec);
+		else if (vp_dev->per_vq_vectors)
+			msix_vec = allocated_vectors++;
+		else
+			msix_vec = VP_MSIX_VQ_VECTOR;
+		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+				     msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
-			goto out_remove_vqs;
+			goto error_find;
 		}
 
-		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
-			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
+		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
 			continue;
-		}
 
-		snprintf(vp_dev->msix_names[i + 1],
-			 sizeof(*vp_dev->msix_names), "%s-%s",
+		/* allocate per-vq irq if available and necessary */
+		snprintf(vp_dev->msix_names[msix_vec],
+			 sizeof *vp_dev->msix_names,
+			 "%s-%s",
 			 dev_name(&vp_dev->vdev.dev), names[i]);
 		err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
-				  vring_interrupt, IRQF_SHARED,
-				  vp_dev->msix_names[i + 1], vqs[i]);
-		if (err) {
-			/* don't free this irq on error */
-			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
-			goto out_remove_vqs;
-		}
-		vp_dev->msix_vector_map[i] = msix_vec;
-
-		/*
-		 * Use a different vector for each queue if they are available,
-		 * else share the same vector for all VQs.
-		 */
-		if (!shared)
-			allocated_vectors++;
+				  vring_interrupt, 0,
+				  vp_dev->msix_names[msix_vec],
+				  vqs[i]);
+		if (err)
+			goto error_find;
 	}
-
 	return 0;
 
-out_remove_vqs:
-	vp_remove_vqs(vdev);
-	kfree(vp_dev->msix_vector_map);
-out_disable_config_irq:
-	vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
-out_free_config_irq:
-	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
-out_free_msix_affinity_masks:
-	for (i = 0; i < nvectors; i++) {
-		if (vp_dev->msix_affinity_masks[i])
-			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
-	}
-	kfree(vp_dev->msix_affinity_masks);
-out_free_msix_names:
-	kfree(vp_dev->msix_names);
-out_free_irq_vectors:
-	pci_free_irq_vectors(vp_dev->pci_dev);
+error_find:
+	vp_del_vqs(vdev);
 	return err;
 }
 
@@ -286,29 +350,33 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err;
 
+	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
+	if (!vp_dev->vqs)
+		return -ENOMEM;
+
 	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vp_dev);
 	if (err)
-		return err;
+		goto out_del_vqs;
 
+	vp_dev->intx_enabled = 1;
+	vp_dev->per_vq_vectors = false;
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
 			continue;
 		}
-		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
-				VIRTIO_MSI_NO_VECTOR);
+		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+				     VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
-			goto out_remove_vqs;
+			goto out_del_vqs;
 		}
 	}
 
 	return 0;
-
-out_remove_vqs:
-	vp_remove_vqs(vdev);
-	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+out_del_vqs:
+	vp_del_vqs(vdev);
 	return err;
 }
 
@@ -319,9 +387,15 @@ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 {
 	int err;
 
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc);
+	/* Try MSI-X with one vector per queue. */
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, desc);
 	if (!err)
 		return 0;
+	/* Fallback: MSI-X with one vector for config, one shared for queues. */
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, desc);
+	if (!err)
+		return 0;
+	/* Finally fall back to regular interrupts. */
 	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
 }
 
@@ -341,15 +415,16 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 {
 	struct virtio_device *vdev = vq->vdev;
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+	struct cpumask *mask;
+	unsigned int irq;
 
 	if (!vq->callback)
 		return -EINVAL;
 
-	if (vp_dev->pci_dev->msix_enabled) {
-		int vec = vp_dev->msix_vector_map[vq->index];
-		struct cpumask *mask = vp_dev->msix_affinity_masks[vec];
-		unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec);
-
+	if (vp_dev->msix_enabled) {
+		mask = vp_dev->msix_affinity_masks[info->msix_vector];
+		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
 		if (cpu == -1)
 			irq_set_affinity_hint(irq, NULL);
 		else {
@@ -364,12 +439,13 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	unsigned int *map = vp_dev->msix_vector_map;
 
-	if (!map || map[index] == VIRTIO_MSI_NO_VECTOR)
+	if (!vp_dev->per_vq_vectors ||
+	    vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR)
 		return NULL;
 
-	return pci_irq_get_affinity(vp_dev->pci_dev, map[index]);
+	return pci_irq_get_affinity(vp_dev->pci_dev,
+				    vp_dev->vqs[index]->msix_vector);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -440,6 +516,8 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	vp_dev->vdev.dev.parent = &pci_dev->dev;
 	vp_dev->vdev.dev.release = virtio_pci_release_dev;
 	vp_dev->pci_dev = pci_dev;
+	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	spin_lock_init(&vp_dev->lock);
 
 	/* enable the device */
 	rc = pci_enable_device(pci_dev);
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index ac8c9d788964..e96334aec1e0 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -31,6 +31,17 @@
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 
+struct virtio_pci_vq_info {
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the list node for the virtqueues list */
+	struct list_head node;
+
+	/* MSI-X vector (or none) */
+	unsigned msix_vector;
+};
+
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -64,25 +75,47 @@ struct virtio_pci_device {
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
 
+	/* a list of queues so we can dispatch IRQs */
+	spinlock_t lock;
+	struct list_head virtqueues;
+
+	/* array of all queues for house-keeping */
+	struct virtio_pci_vq_info **vqs;
+
+	/* MSI-X support */
+	int msix_enabled;
+	int intx_enabled;
 	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
 	char (*msix_names)[256];
-	/* Total Number of MSI-X vectors (including per-VQ ones). */
-	int msix_vectors;
-	/* Map of per-VQ MSI-X vectors, may be NULL */
-	unsigned *msix_vector_map;
+	/* Number of available vectors */
+	unsigned msix_vectors;
+	/* Vectors allocated, excluding per-vq vectors if any */
+	unsigned msix_used_vectors;
+
+	/* Whether we have vector per vq */
+	bool per_vq_vectors;
 
 	struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
+				      struct virtio_pci_vq_info *info,
 				      unsigned idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
 				      u16 msix_vec);
-	void (*del_vq)(struct virtqueue *vq);
+	void (*del_vq)(struct virtio_pci_vq_info *info);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
 };
 
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+	VP_MSIX_CONFIG_VECTOR = 0,
+	VP_MSIX_VQ_VECTOR = 1,
+};
+
 /* Convert a generic virtio device to our structure */
 static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 {
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index f7362c5fe18a..4bfa48fb1324 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -112,6 +112,7 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -129,6 +130,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
 		return ERR_PTR(-ENOENT);
 
+	info->msix_vector = msix_vec;
+
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
@@ -159,13 +162,14 @@ out_deactivate:
 	return ERR_PTR(err);
 }
 
-static void del_vq(struct virtqueue *vq)
+static void del_vq(struct virtio_pci_vq_info *info)
 {
+	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
-	if (vp_dev->pci_dev->msix_enabled) {
+	if (vp_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
 			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
 		/* Flush the write out to device */
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 7bc3004b840e..8978f109d2d7 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -293,6 +293,7 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -322,6 +323,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* get offset of notification word for this vq */
 	off = vp_ioread16(&cfg->queue_notify_off);
 
+	info->msix_vector = msix_vec;
+
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
@@ -405,13 +408,14 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	return 0;
 }
 
-static void del_vq(struct virtqueue *vq)
+static void del_vq(struct virtio_pci_vq_info *info)
 {
+	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	vp_iowrite16(vq->index, &vp_dev->common->queue_select);
 
-	if (vp_dev->pci_dev->msix_enabled) {
+	if (vp_dev->msix_enabled) {
 		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
 			     &vp_dev->common->queue_msix_vector);
 		/* Flush the write out to device */
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index c77a0751a311..f3bf8f4e2d6c 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -36,6 +36,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/highmem.h>
+#include <linux/refcount.h>
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -86,7 +87,7 @@ struct grant_map {
 	int index;
 	int count;
 	int flags;
-	atomic_t users;
+	refcount_t users;
 	struct unmap_notify notify;
 	struct ioctl_gntdev_grant_ref *grants;
 	struct gnttab_map_grant_ref   *map_ops;
@@ -166,7 +167,7 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 
 	add->index = 0;
 	add->count = count;
-	atomic_set(&add->users, 1);
+	refcount_set(&add->users, 1);
 
 	return add;
 
@@ -212,7 +213,7 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 	if (!map)
 		return;
 
-	if (!atomic_dec_and_test(&map->users))
+	if (!refcount_dec_and_test(&map->users))
 		return;
 
 	atomic_sub(map->count, &pages_mapped);
@@ -400,7 +401,7 @@ static void gntdev_vma_open(struct vm_area_struct *vma)
 	struct grant_map *map = vma->vm_private_data;
 
 	pr_debug("gntdev_vma_open %p\n", vma);
-	atomic_inc(&map->users);
+	refcount_inc(&map->users);
 }
 
 static void gntdev_vma_close(struct vm_area_struct *vma)
@@ -1004,7 +1005,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		goto unlock_out;
 	}
 
-	atomic_inc(&map->users);
+	refcount_inc(&map->users);
 
 	vma->vm_ops = &gntdev_vmops;
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f8afc6dcc29f..e8cef1ad0fe3 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -681,3 +681,50 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->mmap)
+		return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+						    dma_addr, size, attrs);
+#endif
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
+
+/*
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t handle, size_t size,
+			unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->get_sgtable) {
+#if 0
+	/*
+	 * This check verifies that the page belongs to the current domain and
+	 * is not one mapped from another domain.
+	 * This check is for debug only, and should not go to production build
+	 */
+		unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
+		BUG_ON (!page_is_ram(bfn));
+#endif
+		return __generic_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
+							   handle, size, attrs);
+	}
+#endif
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_get_sgtable);
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 4ce10bcca18b..23e391d3ec01 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -27,10 +27,10 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/syscore_ops.h>
 #include <linux/acpi.h>
 #include <acpi/processor.h>
 #include <xen/xen.h>
-#include <xen/xen-ops.h>
 #include <xen/interface/platform.h>
 #include <asm/xen/hypercall.h>
 
@@ -408,7 +408,7 @@ static int check_acpi_ids(struct acpi_processor *pr_backup)
 	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
 			    ACPI_UINT32_MAX,
 			    read_acpi_id, NULL, NULL, NULL);
-	acpi_get_devices("ACPI0007", read_acpi_id, NULL, NULL);
+	acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, read_acpi_id, NULL, NULL);
 
 upload:
 	if (!bitmap_equal(acpi_id_present, acpi_ids_done, nr_acpi_bits)) {
@@ -466,15 +466,33 @@ static int xen_upload_processor_pm_data(void)
 	return rc;
 }
 
-static int xen_acpi_processor_resume(struct notifier_block *nb,
-				     unsigned long action, void *data)
+static void xen_acpi_processor_resume_worker(struct work_struct *dummy)
 {
+	int rc;
+
 	bitmap_zero(acpi_ids_done, nr_acpi_bits);
-	return xen_upload_processor_pm_data();
+
+	rc = xen_upload_processor_pm_data();
+	if (rc != 0)
+		pr_info("ACPI data upload failed, error = %d\n", rc);
+}
+
+static void xen_acpi_processor_resume(void)
+{
+	static DECLARE_WORK(wq, xen_acpi_processor_resume_worker);
+
+	/*
+	 * xen_upload_processor_pm_data() calls non-atomic code.
+	 * However, the context for xen_acpi_processor_resume is syscore
+	 * with only the boot CPU online and in an atomic context.
+	 *
+	 * So defer the upload for some point safer.
+	 */
+	schedule_work(&wq);
 }
 
-struct notifier_block xen_acpi_processor_resume_nb = {
-	.notifier_call = xen_acpi_processor_resume,
+static struct syscore_ops xap_syscore_ops = {
+	.resume	= xen_acpi_processor_resume,
 };
 
 static int __init xen_acpi_processor_init(void)
@@ -527,7 +545,7 @@ static int __init xen_acpi_processor_init(void)
 	if (rc)
 		goto err_unregister;
 
-	xen_resume_notifier_register(&xen_acpi_processor_resume_nb);
+	register_syscore_ops(&xap_syscore_ops);
 
 	return 0;
 err_unregister:
@@ -544,7 +562,7 @@ static void __exit xen_acpi_processor_exit(void)
 {
 	int i;
 
-	xen_resume_notifier_unregister(&xen_acpi_processor_resume_nb);
+	unregister_syscore_ops(&xap_syscore_ops);
 	kfree(acpi_ids_done);
 	kfree(acpi_id_present);
 	kfree(acpi_id_cst_present);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 4d343eed08f5..f3b089b7c0b6 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,7 +55,6 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/miscdevice.h>
-#include <linux/init.h>
 
 #include <xen/xenbus.h>
 #include <xen/xen.h>
@@ -443,8 +442,10 @@ static int xenbus_write_transaction(unsigned msg_type,
 		return xenbus_command_reply(u, XS_ERROR, "ENOENT");
 
 	rc = xenbus_dev_request_and_reply(&u->u.msg, u);
-	if (rc)
+	if (rc && trans) {
+		list_del(&trans->list);
 		kfree(trans);
+	}
 
 out:
 	return rc;
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index a89f3cfe3c7d..c202930086ed 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -333,10 +333,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		goto err_names;
 	init_rwsem(&v9ses->rename_sem);
 
-	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
-	if (rc)
-		goto err_names;
-
 	v9ses->uid = INVALID_UID;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
@@ -345,7 +341,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	if (IS_ERR(v9ses->clnt)) {
 		rc = PTR_ERR(v9ses->clnt);
 		p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
-		goto err_bdi;
+		goto err_names;
 	}
 
 	v9ses->flags = V9FS_ACCESS_USER;
@@ -415,8 +411,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 
 err_clnt:
 	p9_client_destroy(v9ses->clnt);
-err_bdi:
-	bdi_destroy(&v9ses->bdi);
 err_names:
 	kfree(v9ses->uname);
 	kfree(v9ses->aname);
@@ -445,8 +439,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 	kfree(v9ses->uname);
 	kfree(v9ses->aname);
 
-	bdi_destroy(&v9ses->bdi);
-
 	spin_lock(&v9fs_sessionlist_lock);
 	list_del(&v9ses->slist);
 	spin_unlock(&v9fs_sessionlist_lock);
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 443d12e02043..76eaf49abd3a 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -114,7 +114,6 @@ struct v9fs_session_info {
 	kuid_t uid;		/* if ACCESS_SINGLE, the uid that has access */
 	struct p9_client *clnt;	/* 9p client */
 	struct list_head slist; /* list of sessions registered with v9fs */
-	struct backing_dev_info bdi;
 	struct rw_semaphore rename_sem;
 };
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index de3ed8629196..a0965fb587a5 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -72,10 +72,12 @@ static int v9fs_set_super(struct super_block *s, void *data)
  *
  */
 
-static void
+static int
 v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		int flags, void *data)
 {
+	int ret;
+
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
 	sb->s_blocksize = 1 << sb->s_blocksize_bits;
@@ -85,7 +87,11 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		sb->s_xattr = v9fs_xattr_handlers;
 	} else
 		sb->s_op = &v9fs_super_ops;
-	sb->s_bdi = &v9ses->bdi;
+
+	ret = super_setup_bdi(sb);
+	if (ret)
+		return ret;
+
 	if (v9ses->cache)
 		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
 
@@ -99,6 +105,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 #endif
 
 	save_mount_options(sb, data);
+	return 0;
 }
 
 /**
@@ -138,7 +145,9 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		retval = PTR_ERR(sb);
 		goto clunk_fid;
 	}
-	v9fs_fill_super(sb, v9ses, flags, data);
+	retval = v9fs_fill_super(sb, v9ses, flags, data);
+	if (retval)
+		goto release_sb;
 
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		sb->s_d_op = &v9fs_cached_dentry_operations;
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index b29447e03ede..25d404d22cae 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -362,7 +362,7 @@ static void afs_callback_updater(struct work_struct *work)
 {
 	struct afs_server *server;
 	struct afs_vnode *vnode, *xvnode;
-	time_t now;
+	time64_t now;
 	long timeout;
 	int ret;
 
@@ -370,7 +370,7 @@ static void afs_callback_updater(struct work_struct *work)
 
 	_enter("");
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	/* find the first vnode to update */
 	spin_lock(&server->cb_lock);
@@ -424,7 +424,8 @@ static void afs_callback_updater(struct work_struct *work)
 
 	/* and then reschedule */
 	_debug("reschedule");
-	vnode->update_at = get_seconds() + afs_vnode_update_timeout;
+	vnode->update_at = ktime_get_real_seconds() +
+			afs_vnode_update_timeout;
 
 	spin_lock(&server->cb_lock);
 
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 2edbdcbf6432..3062cceb5c2a 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -187,7 +187,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 	struct afs_callback *cb;
 	struct afs_server *server;
 	__be32 *bp;
-	u32 tmp;
 	int ret, loop;
 
 	_enter("{%u}", call->unmarshall);
@@ -249,9 +248,9 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		if (ret < 0)
 			return ret;
 
-		tmp = ntohl(call->tmp);
-		_debug("CB count: %u", tmp);
-		if (tmp != call->count && tmp != 0)
+		call->count2 = ntohl(call->tmp);
+		_debug("CB count: %u", call->count2);
+		if (call->count2 != call->count && call->count2 != 0)
 			return -EBADMSG;
 		call->offset = 0;
 		call->unmarshall++;
@@ -259,14 +258,14 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 	case 4:
 		_debug("extract CB array");
 		ret = afs_extract_data(call, call->buffer,
-				       call->count * 3 * 4, false);
+				       call->count2 * 3 * 4, false);
 		if (ret < 0)
 			return ret;
 
 		_debug("unmarshall CB array");
 		cb = call->request;
 		bp = call->buffer;
-		for (loop = call->count; loop > 0; loop--, cb++) {
+		for (loop = call->count2; loop > 0; loop--, cb++) {
 			cb->version	= ntohl(*bp++);
 			cb->expiry	= ntohl(*bp++);
 			cb->type	= ntohl(*bp++);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index ba7b71fba34b..0d5b8508869b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -30,6 +30,7 @@ static int afs_readpages(struct file *filp, struct address_space *mapping,
 
 const struct file_operations afs_file_operations = {
 	.open		= afs_open,
+	.flush		= afs_flush,
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
@@ -184,10 +185,13 @@ int afs_page_filler(void *data, struct page *page)
 		if (!req)
 			goto enomem;
 
+		/* We request a full page.  If the page is a partial one at the
+		 * end of the file, the server will return a short read and the
+		 * unmarshalling code will clear the unfilled space.
+		 */
 		atomic_set(&req->usage, 1);
 		req->pos = (loff_t)page->index << PAGE_SHIFT;
-		req->len = min_t(size_t, i_size_read(inode) - req->pos,
-				 PAGE_SIZE);
+		req->len = PAGE_SIZE;
 		req->nr_pages = 1;
 		req->pages[0] = page;
 		get_page(page);
@@ -208,7 +212,13 @@ int afs_page_filler(void *data, struct page *page)
 			fscache_uncache_page(vnode->cache, page);
 #endif
 			BUG_ON(PageFsCache(page));
-			goto error;
+
+			if (ret == -EINTR ||
+			    ret == -ENOMEM ||
+			    ret == -ERESTARTSYS ||
+			    ret == -EAGAIN)
+				goto error;
+			goto io_error;
 		}
 
 		SetPageUptodate(page);
@@ -227,10 +237,12 @@ int afs_page_filler(void *data, struct page *page)
 	_leave(" = 0");
 	return 0;
 
+io_error:
+	SetPageError(page);
+	goto error;
 enomem:
 	ret = -ENOMEM;
 error:
-	SetPageError(page);
 	unlock_page(page);
 	_leave(" = %d", ret);
 	return ret;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index ac8e766978dc..19f76ae36982 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -17,6 +17,12 @@
 #include "afs_fs.h"
 
 /*
+ * We need somewhere to discard into in case the server helpfully returns more
+ * than we asked for in FS.FetchData{,64}.
+ */
+static u8 afs_discard_buffer[64];
+
+/*
  * decode an AFSFid block
  */
 static void xdr_decode_AFSFid(const __be32 **_bp, struct afs_fid *fid)
@@ -105,7 +111,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 			vnode->vfs_inode.i_mode = mode;
 		}
 
-		vnode->vfs_inode.i_ctime.tv_sec	= status->mtime_server;
+		vnode->vfs_inode.i_ctime.tv_sec	= status->mtime_client;
 		vnode->vfs_inode.i_mtime	= vnode->vfs_inode.i_ctime;
 		vnode->vfs_inode.i_atime	= vnode->vfs_inode.i_ctime;
 		vnode->vfs_inode.i_version	= data_version;
@@ -139,7 +145,7 @@ static void xdr_decode_AFSCallBack(const __be32 **_bp, struct afs_vnode *vnode)
 	vnode->cb_version	= ntohl(*bp++);
 	vnode->cb_expiry	= ntohl(*bp++);
 	vnode->cb_type		= ntohl(*bp++);
-	vnode->cb_expires	= vnode->cb_expiry + get_seconds();
+	vnode->cb_expires	= vnode->cb_expiry + ktime_get_real_seconds();
 	*_bp = bp;
 }
 
@@ -315,7 +321,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 	void *buffer;
 	int ret;
 
-	_enter("{%u,%zu/%u;%u/%llu}",
+	_enter("{%u,%zu/%u;%llu/%llu}",
 	       call->unmarshall, call->offset, call->count,
 	       req->remain, req->actual_len);
 
@@ -353,12 +359,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 
 		req->actual_len |= ntohl(call->tmp);
 		_debug("DATA length: %llu", req->actual_len);
-		/* Check that the server didn't want to send us extra.  We
-		 * might want to just discard instead, but that requires
-		 * cooperation from AF_RXRPC.
-		 */
-		if (req->actual_len > req->len)
-			return -EBADMSG;
 
 		req->remain = req->actual_len;
 		call->offset = req->pos & (PAGE_SIZE - 1);
@@ -368,6 +368,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		call->unmarshall++;
 
 	begin_page:
+		ASSERTCMP(req->index, <, req->nr_pages);
 		if (req->remain > PAGE_SIZE - call->offset)
 			size = PAGE_SIZE - call->offset;
 		else
@@ -378,7 +379,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 
 		/* extract the returned data */
 	case 3:
-		_debug("extract data %u/%llu %zu/%u",
+		_debug("extract data %llu/%llu %zu/%u",
 		       req->remain, req->actual_len, call->offset, call->count);
 
 		buffer = kmap(req->pages[req->index]);
@@ -389,19 +390,40 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (call->offset == PAGE_SIZE) {
 			if (req->page_done)
 				req->page_done(call, req);
+			req->index++;
 			if (req->remain > 0) {
-				req->index++;
 				call->offset = 0;
+				if (req->index >= req->nr_pages) {
+					call->unmarshall = 4;
+					goto begin_discard;
+				}
 				goto begin_page;
 			}
 		}
+		goto no_more_data;
+
+		/* Discard any excess data the server gave us */
+	begin_discard:
+	case 4:
+		size = min_t(loff_t, sizeof(afs_discard_buffer), req->remain);
+		call->count = size;
+		_debug("extract discard %llu/%llu %zu/%u",
+		       req->remain, req->actual_len, call->offset, call->count);
+
+		call->offset = 0;
+		ret = afs_extract_data(call, afs_discard_buffer, call->count, true);
+		req->remain -= call->offset;
+		if (ret < 0)
+			return ret;
+		if (req->remain > 0)
+			goto begin_discard;
 
 	no_more_data:
 		call->offset = 0;
-		call->unmarshall++;
+		call->unmarshall = 5;
 
 		/* extract the metadata */
-	case 4:
+	case 5:
 		ret = afs_extract_data(call, call->buffer,
 				       (21 + 3 + 6) * 4, false);
 		if (ret < 0)
@@ -416,16 +438,17 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		call->offset = 0;
 		call->unmarshall++;
 
-	case 5:
+	case 6:
 		break;
 	}
 
-	if (call->count < PAGE_SIZE) {
-		buffer = kmap(req->pages[req->index]);
-		memset(buffer + call->count, 0, PAGE_SIZE - call->count);
-		kunmap(req->pages[req->index]);
+	for (; req->index < req->nr_pages; req->index++) {
+		if (call->count < PAGE_SIZE)
+			zero_user_segment(req->pages[req->index],
+					  call->count, PAGE_SIZE);
 		if (req->page_done)
 			req->page_done(call, req);
+		call->count = 0;
 	}
 
 	_leave(" = 0 [done]");
@@ -711,8 +734,8 @@ int afs_fs_create(struct afs_server *server,
 		memset(bp, 0, padsz);
 		bp = (void *) bp + padsz;
 	}
-	*bp++ = htonl(AFS_SET_MODE);
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME);
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = htonl(mode & S_IALLUGO); /* unix mode */
@@ -980,8 +1003,8 @@ int afs_fs_symlink(struct afs_server *server,
 		memset(bp, 0, c_padsz);
 		bp = (void *) bp + c_padsz;
 	}
-	*bp++ = htonl(AFS_SET_MODE);
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME);
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = htonl(S_IRWXUGO); /* unix mode */
@@ -1180,8 +1203,8 @@ static int afs_fs_store_data64(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	*bp++ = 0; /* mask */
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MTIME); /* mask */
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = 0; /* unix mode */
@@ -1213,7 +1236,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 	_enter(",%x,{%x:%u},,",
 	       key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode);
 
-	size = to - offset;
+	size = (loff_t)to - (loff_t)offset;
 	if (first != last)
 		size += (loff_t)(last - first) << PAGE_SHIFT;
 	pos = (loff_t)first << PAGE_SHIFT;
@@ -1257,8 +1280,8 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	*bp++ = 0; /* mask */
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MTIME); /* mask */
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = 0; /* unix mode */
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 1e4897a048d2..aae55dd15108 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -54,8 +54,21 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 		inode->i_fop	= &afs_dir_file_operations;
 		break;
 	case AFS_FTYPE_SYMLINK:
-		inode->i_mode	= S_IFLNK | vnode->status.mode;
-		inode->i_op	= &page_symlink_inode_operations;
+		/* Symlinks with a mode of 0644 are actually mountpoints. */
+		if ((vnode->status.mode & 0777) == 0644) {
+			inode->i_flags |= S_AUTOMOUNT;
+
+			spin_lock(&vnode->lock);
+			set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+			spin_unlock(&vnode->lock);
+
+			inode->i_mode	= S_IFDIR | 0555;
+			inode->i_op	= &afs_mntpt_inode_operations;
+			inode->i_fop	= &afs_mntpt_file_operations;
+		} else {
+			inode->i_mode	= S_IFLNK | vnode->status.mode;
+			inode->i_op	= &page_symlink_inode_operations;
+		}
 		inode_nohighmem(inode);
 		break;
 	default:
@@ -70,27 +83,15 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 
 	set_nlink(inode, vnode->status.nlink);
 	inode->i_uid		= vnode->status.owner;
-	inode->i_gid		= GLOBAL_ROOT_GID;
+	inode->i_gid            = vnode->status.group;
 	inode->i_size		= vnode->status.size;
-	inode->i_ctime.tv_sec	= vnode->status.mtime_server;
+	inode->i_ctime.tv_sec	= vnode->status.mtime_client;
 	inode->i_ctime.tv_nsec	= 0;
 	inode->i_atime		= inode->i_mtime = inode->i_ctime;
 	inode->i_blocks		= 0;
 	inode->i_generation	= vnode->fid.unique;
 	inode->i_version	= vnode->status.data_version;
 	inode->i_mapping->a_ops	= &afs_fs_aops;
-
-	/* check to see whether a symbolic link is really a mountpoint */
-	if (vnode->status.type == AFS_FTYPE_SYMLINK) {
-		afs_mntpt_check_symlink(vnode, key);
-
-		if (test_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags)) {
-			inode->i_mode	= S_IFDIR | vnode->status.mode;
-			inode->i_op	= &afs_mntpt_inode_operations;
-			inode->i_fop	= &afs_mntpt_file_operations;
-		}
-	}
-
 	return 0;
 }
 
@@ -245,12 +246,13 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 			vnode->cb_version = 0;
 			vnode->cb_expiry = 0;
 			vnode->cb_type = 0;
-			vnode->cb_expires = get_seconds();
+			vnode->cb_expires = ktime_get_real_seconds();
 		} else {
 			vnode->cb_version = cb->version;
 			vnode->cb_expiry = cb->expiry;
 			vnode->cb_type = cb->type;
-			vnode->cb_expires = vnode->cb_expiry + get_seconds();
+			vnode->cb_expires = vnode->cb_expiry +
+				ktime_get_real_seconds();
 		}
 	}
 
@@ -323,7 +325,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	    !test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags) &&
 	    !test_bit(AFS_VNODE_MODIFIED, &vnode->flags) &&
 	    !test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
-		if (vnode->cb_expires < get_seconds() + 10) {
+		if (vnode->cb_expires < ktime_get_real_seconds() + 10) {
 			_debug("callback expired");
 			set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
 		} else {
@@ -444,7 +446,7 @@ void afs_evict_inode(struct inode *inode)
 
 	mutex_lock(&vnode->permits_lock);
 	permits = vnode->permits;
-	rcu_assign_pointer(vnode->permits, NULL);
+	RCU_INIT_POINTER(vnode->permits, NULL);
 	mutex_unlock(&vnode->permits_lock);
 	if (permits)
 		call_rcu(&permits->rcu, afs_zap_permits);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5dfa56903a2d..393672997cc2 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -11,6 +11,7 @@
 
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/ktime.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/rxrpc.h>
@@ -90,7 +91,10 @@ struct afs_call {
 	unsigned		request_size;	/* size of request data */
 	unsigned		reply_max;	/* maximum size of reply */
 	unsigned		first_offset;	/* offset into mapping[first] */
-	unsigned		last_to;	/* amount of mapping[last] */
+	union {
+		unsigned	last_to;	/* amount of mapping[last] */
+		unsigned	count2;		/* count used in unmarshalling */
+	};
 	unsigned char		unmarshall;	/* unmarshalling phase */
 	bool			incoming;	/* T if incoming call */
 	bool			send_pages;	/* T if data from mapping should be sent */
@@ -127,12 +131,11 @@ struct afs_call_type {
  */
 struct afs_read {
 	loff_t			pos;		/* Where to start reading */
-	loff_t			len;		/* How much to read */
+	loff_t			len;		/* How much we're asking for */
 	loff_t			actual_len;	/* How much we're actually getting */
+	loff_t			remain;		/* Amount remaining */
 	atomic_t		usage;
-	unsigned int		remain;		/* Amount remaining */
 	unsigned int		index;		/* Which page we're reading into */
-	unsigned int		pg_offset;	/* Offset in page we're at */
 	unsigned int		nr_pages;
 	void (*page_done)(struct afs_call *, struct afs_read *);
 	struct page		*pages[];
@@ -247,7 +250,7 @@ struct afs_cache_vhash {
  */
 struct afs_vlocation {
 	atomic_t		usage;
-	time_t			time_of_death;	/* time at which put reduced usage to 0 */
+	time64_t		time_of_death;	/* time at which put reduced usage to 0 */
 	struct list_head	link;		/* link in cell volume location list */
 	struct list_head	grave;		/* link in master graveyard list */
 	struct list_head	update;		/* link in master update list */
@@ -258,7 +261,7 @@ struct afs_vlocation {
 	struct afs_cache_vlocation vldb;	/* volume information DB record */
 	struct afs_volume	*vols[3];	/* volume access record pointer (index by type) */
 	wait_queue_head_t	waitq;		/* status change waitqueue */
-	time_t			update_at;	/* time at which record should be updated */
+	time64_t		update_at;	/* time at which record should be updated */
 	spinlock_t		lock;		/* access lock */
 	afs_vlocation_state_t	state;		/* volume location state */
 	unsigned short		upd_rej_cnt;	/* ENOMEDIUM count during update */
@@ -271,7 +274,7 @@ struct afs_vlocation {
  */
 struct afs_server {
 	atomic_t		usage;
-	time_t			time_of_death;	/* time at which put reduced usage to 0 */
+	time64_t		time_of_death;	/* time at which put reduced usage to 0 */
 	struct in_addr		addr;		/* server address */
 	struct afs_cell		*cell;		/* cell in which server resides */
 	struct list_head	link;		/* link in cell's server list */
@@ -315,7 +318,6 @@ struct afs_volume {
 	unsigned short		rjservers;	/* number of servers discarded due to -ENOMEDIUM */
 	struct afs_server	*servers[8];	/* servers on which volume resides (ordered) */
 	struct rw_semaphore	server_sem;	/* lock for accessing current server */
-	struct backing_dev_info	bdi;
 };
 
 /*
@@ -374,8 +376,8 @@ struct afs_vnode {
 	struct rb_node		server_rb;	/* link in server->fs_vnodes */
 	struct rb_node		cb_promise;	/* link in server->cb_promises */
 	struct work_struct	cb_broken_work;	/* work to be done on callback break */
-	time_t			cb_expires;	/* time at which callback expires */
-	time_t			cb_expires_at;	/* time used to order cb_promise */
+	time64_t		cb_expires;	/* time at which callback expires */
+	time64_t		cb_expires_at;	/* time used to order cb_promise */
 	unsigned		cb_version;	/* callback version */
 	unsigned		cb_expiry;	/* callback expiry time */
 	afs_callback_type_t	cb_type;	/* type of callback */
@@ -557,7 +559,6 @@ extern const struct inode_operations afs_autocell_inode_operations;
 extern const struct file_operations afs_mntpt_file_operations;
 
 extern struct vfsmount *afs_d_automount(struct path *);
-extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *);
 extern void afs_mntpt_kill_timer(void);
 
 /*
@@ -718,6 +719,7 @@ extern int afs_writepages(struct address_space *, struct writeback_control *);
 extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
 extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_writeback_all(struct afs_vnode *);
+extern int afs_flush(struct file *, fl_owner_t);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 
 
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 91ea1aa0d8b3..100b207efc9e 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -84,6 +84,8 @@ int afs_abort_to_error(u32 abort_code)
 	case RXKADDATALEN:	return -EKEYREJECTED;
 	case RXKADILLEGALLEVEL:	return -EKEYREJECTED;
 
+	case RXGEN_OPCODE:	return -ENOTSUPP;
+
 	default:		return -EREMOTEIO;
 	}
 }
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index d4fb0afc0097..bd3b65cde282 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -47,59 +47,6 @@ static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out);
 static unsigned long afs_mntpt_expiry_timeout = 10 * 60;
 
 /*
- * check a symbolic link to see whether it actually encodes a mountpoint
- * - sets the AFS_VNODE_MOUNTPOINT flag on the vnode appropriately
- */
-int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
-{
-	struct page *page;
-	size_t size;
-	char *buf;
-	int ret;
-
-	_enter("{%x:%u,%u}",
-	       vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
-
-	/* read the contents of the symlink into the pagecache */
-	page = read_cache_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0,
-			       afs_page_filler, key);
-	if (IS_ERR(page)) {
-		ret = PTR_ERR(page);
-		goto out;
-	}
-
-	ret = -EIO;
-	if (PageError(page))
-		goto out_free;
-
-	buf = kmap(page);
-
-	/* examine the symlink's contents */
-	size = vnode->status.size;
-	_debug("symlink to %*.*s", (int) size, (int) size, buf);
-
-	if (size > 2 &&
-	    (buf[0] == '%' || buf[0] == '#') &&
-	    buf[size - 1] == '.'
-	    ) {
-		_debug("symlink is a mountpoint");
-		spin_lock(&vnode->lock);
-		set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
-		vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
-		spin_unlock(&vnode->lock);
-	}
-
-	ret = 0;
-
-	kunmap(page);
-out_free:
-	put_page(page);
-out:
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
  * no valid lookup procedure on this sort of dir
  */
 static struct dentry *afs_mntpt_lookup(struct inode *dir,
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 419ef05dcb5e..d5990eb160bd 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -259,67 +259,74 @@ void afs_flat_call_destructor(struct afs_call *call)
 	call->buffer = NULL;
 }
 
+#define AFS_BVEC_MAX 8
+
+/*
+ * Load the given bvec with the next few pages.
+ */
+static void afs_load_bvec(struct afs_call *call, struct msghdr *msg,
+			  struct bio_vec *bv, pgoff_t first, pgoff_t last,
+			  unsigned offset)
+{
+	struct page *pages[AFS_BVEC_MAX];
+	unsigned int nr, n, i, to, bytes = 0;
+
+	nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX);
+	n = find_get_pages_contig(call->mapping, first, nr, pages);
+	ASSERTCMP(n, ==, nr);
+
+	msg->msg_flags |= MSG_MORE;
+	for (i = 0; i < nr; i++) {
+		to = PAGE_SIZE;
+		if (first + i >= last) {
+			to = call->last_to;
+			msg->msg_flags &= ~MSG_MORE;
+		}
+		bv[i].bv_page = pages[i];
+		bv[i].bv_len = to - offset;
+		bv[i].bv_offset = offset;
+		bytes += to - offset;
+		offset = 0;
+	}
+
+	iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes);
+}
+
 /*
  * attach the data from a bunch of pages on an inode to a call
  */
 static int afs_send_pages(struct afs_call *call, struct msghdr *msg)
 {
-	struct page *pages[8];
-	unsigned count, n, loop, offset, to;
+	struct bio_vec bv[AFS_BVEC_MAX];
+	unsigned int bytes, nr, loop, offset;
 	pgoff_t first = call->first, last = call->last;
 	int ret;
 
-	_enter("");
-
 	offset = call->first_offset;
 	call->first_offset = 0;
 
 	do {
-		_debug("attach %lx-%lx", first, last);
-
-		count = last - first + 1;
-		if (count > ARRAY_SIZE(pages))
-			count = ARRAY_SIZE(pages);
-		n = find_get_pages_contig(call->mapping, first, count, pages);
-		ASSERTCMP(n, ==, count);
-
-		loop = 0;
-		do {
-			struct bio_vec bvec = {.bv_page = pages[loop],
-					       .bv_offset = offset};
-			msg->msg_flags = 0;
-			to = PAGE_SIZE;
-			if (first + loop >= last)
-				to = call->last_to;
-			else
-				msg->msg_flags = MSG_MORE;
-			bvec.bv_len = to - offset;
-			offset = 0;
-
-			_debug("- range %u-%u%s",
-			       offset, to, msg->msg_flags ? " [more]" : "");
-			iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC,
-				      &bvec, 1, to - offset);
-
-			/* have to change the state *before* sending the last
-			 * packet as RxRPC might give us the reply before it
-			 * returns from sending the request */
-			if (first + loop >= last)
-				call->state = AFS_CALL_AWAIT_REPLY;
-			ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
-						     msg, to - offset);
-			if (ret < 0)
-				break;
-		} while (++loop < count);
-		first += count;
-
-		for (loop = 0; loop < count; loop++)
-			put_page(pages[loop]);
+		afs_load_bvec(call, msg, bv, first, last, offset);
+		offset = 0;
+		bytes = msg->msg_iter.count;
+		nr = msg->msg_iter.nr_segs;
+
+		/* Have to change the state *before* sending the last
+		 * packet as RxRPC might give us the reply before it
+		 * returns from sending the request.
+		 */
+		if (first + nr - 1 >= last)
+			call->state = AFS_CALL_AWAIT_REPLY;
+		ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
+					     msg, bytes);
+		for (loop = 0; loop < nr; loop++)
+			put_page(bv[loop].bv_page);
 		if (ret < 0)
 			break;
+
+		first += nr;
 	} while (first <= last);
 
-	_leave(" = %d", ret);
 	return ret;
 }
 
@@ -333,6 +340,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
 	struct kvec iov[1];
+	size_t offset;
+	u32 abort_code;
 	int ret;
 
 	_enter("%x,{%d},", addr->s_addr, ntohs(call->port));
@@ -381,9 +390,11 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= (call->send_pages ? MSG_MORE : 0);
 
-	/* have to change the state *before* sending the last packet as RxRPC
-	 * might give us the reply before it returns from sending the
-	 * request */
+	/* We have to change the state *before* sending the last packet as
+	 * rxrpc might give us the reply before it returns from sending the
+	 * request.  Further, if the send fails, we may already have been given
+	 * a notification and may have collected it.
+	 */
 	if (!call->send_pages)
 		call->state = AFS_CALL_AWAIT_REPLY;
 	ret = rxrpc_kernel_send_data(afs_socket, rxcall,
@@ -405,7 +416,17 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	return afs_wait_for_call_to_complete(call);
 
 error_do_abort:
-	rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD");
+	call->state = AFS_CALL_COMPLETE;
+	if (ret != -ECONNABORTED) {
+		rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT,
+					ret, "KSD");
+	} else {
+		abort_code = 0;
+		offset = 0;
+		rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset,
+				       false, &abort_code);
+		ret = call->type->abort_to_error(abort_code);
+	}
 error_kill_call:
 	afs_put_call(call);
 	_leave(" = %d", ret);
@@ -452,16 +473,18 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -EINPROGRESS:
 		case -EAGAIN:
 			goto out;
+		case -ECONNABORTED:
+			goto call_complete;
 		case -ENOTCONN:
 			abort_code = RX_CALL_DEAD;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, -ret, "KNC");
-			goto do_abort;
+						abort_code, ret, "KNC");
+			goto save_error;
 		case -ENOTSUPP:
-			abort_code = RX_INVALID_OPERATION;
+			abort_code = RXGEN_OPCODE;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, -ret, "KIV");
-			goto do_abort;
+						abort_code, ret, "KIV");
+			goto save_error;
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
@@ -470,8 +493,8 @@ static void afs_deliver_to_call(struct afs_call *call)
 			if (call->state != AFS_CALL_AWAIT_REPLY)
 				abort_code = RXGEN_SS_UNMARSHAL;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, EBADMSG, "KUM");
-			goto do_abort;
+						abort_code, -EBADMSG, "KUM");
+			goto save_error;
 		}
 	}
 
@@ -482,8 +505,9 @@ out:
 	_leave("");
 	return;
 
-do_abort:
+save_error:
 	call->error = ret;
+call_complete:
 	call->state = AFS_CALL_COMPLETE;
 	goto done;
 }
@@ -493,7 +517,6 @@ do_abort:
  */
 static int afs_wait_for_call_to_complete(struct afs_call *call)
 {
-	const char *abort_why;
 	int ret;
 
 	DECLARE_WAITQUEUE(myself, current);
@@ -512,13 +535,8 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
 			continue;
 		}
 
-		abort_why = "KWC";
-		ret = call->error;
-		if (call->state == AFS_CALL_COMPLETE)
-			break;
-		abort_why = "KWI";
-		ret = -EINTR;
-		if (signal_pending(current))
+		if (call->state == AFS_CALL_COMPLETE ||
+		    signal_pending(current))
 			break;
 		schedule();
 	}
@@ -526,13 +544,14 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
 	remove_wait_queue(&call->waitq, &myself);
 	__set_current_state(TASK_RUNNING);
 
-	/* kill the call */
+	/* Kill off the call if it's still live. */
 	if (call->state < AFS_CALL_COMPLETE) {
-		_debug("call incomplete");
+		_debug("call interrupted");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_CALL_DEAD, -ret, abort_why);
+					RX_USER_ABORT, -EINTR, "KWI");
 	}
 
+	ret = call->error;
 	_debug("call complete");
 	afs_put_call(call);
 	_leave(" = %d", ret);
@@ -735,7 +754,7 @@ void afs_send_empty_reply(struct afs_call *call)
 	case -ENOMEM:
 		_debug("oom");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_USER_ABORT, ENOMEM, "KOO");
+					RX_USER_ABORT, -ENOMEM, "KOO");
 	default:
 		_leave(" [error]");
 		return;
@@ -773,7 +792,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	if (n == -ENOMEM) {
 		_debug("oom");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_USER_ABORT, ENOMEM, "KOO");
+					RX_USER_ABORT, -ENOMEM, "KOO");
 	}
 	_leave(" [error]");
 }
diff --git a/fs/afs/security.c b/fs/afs/security.c
index 8d010422dc89..ecb86a670180 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -114,7 +114,7 @@ void afs_clear_permits(struct afs_vnode *vnode)
 
 	mutex_lock(&vnode->permits_lock);
 	permits = vnode->permits;
-	rcu_assign_pointer(vnode->permits, NULL);
+	RCU_INIT_POINTER(vnode->permits, NULL);
 	mutex_unlock(&vnode->permits_lock);
 
 	if (permits)
@@ -340,17 +340,22 @@ int afs_permission(struct inode *inode, int mask)
 	} else {
 		if (!(access & AFS_ACE_LOOKUP))
 			goto permission_denied;
+		if ((mask & MAY_EXEC) && !(inode->i_mode & S_IXUSR))
+			goto permission_denied;
 		if (mask & (MAY_EXEC | MAY_READ)) {
 			if (!(access & AFS_ACE_READ))
 				goto permission_denied;
+			if (!(inode->i_mode & S_IRUSR))
+				goto permission_denied;
 		} else if (mask & MAY_WRITE) {
 			if (!(access & AFS_ACE_WRITE))
 				goto permission_denied;
+			if (!(inode->i_mode & S_IWUSR))
+				goto permission_denied;
 		}
 	}
 
 	key_put(key);
-	ret = generic_permission(inode, mask);
 	_leave(" = %d", ret);
 	return ret;
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index d4066ab7dd55..c001b1f2455f 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -242,7 +242,7 @@ void afs_put_server(struct afs_server *server)
 	spin_lock(&afs_server_graveyard_lock);
 	if (atomic_read(&server->usage) == 0) {
 		list_move_tail(&server->grave, &afs_server_graveyard);
-		server->time_of_death = get_seconds();
+		server->time_of_death = ktime_get_real_seconds();
 		queue_delayed_work(afs_wq, &afs_server_reaper,
 				   afs_server_timeout * HZ);
 	}
@@ -277,9 +277,9 @@ static void afs_reap_server(struct work_struct *work)
 	LIST_HEAD(corpses);
 	struct afs_server *server;
 	unsigned long delay, expiry;
-	time_t now;
+	time64_t now;
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	spin_lock(&afs_server_graveyard_lock);
 
 	while (!list_empty(&afs_server_graveyard)) {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index fbdb022b75a2..c79633e5cfd8 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -319,7 +319,10 @@ static int afs_fill_super(struct super_block *sb,
 	sb->s_blocksize_bits	= PAGE_SHIFT;
 	sb->s_magic		= AFS_FS_MAGIC;
 	sb->s_op		= &afs_super_ops;
-	sb->s_bdi		= &as->volume->bdi;
+	ret = super_setup_bdi(sb);
+	if (ret)
+		return ret;
+	sb->s_bdi->ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 	strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id));
 
 	/* allocate the root inode and dentry */
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index d7d8dd8c0b31..37b7c3b342a6 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -340,7 +340,8 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl)
 	struct afs_vlocation *xvl;
 
 	/* wait at least 10 minutes before updating... */
-	vl->update_at = get_seconds() + afs_vlocation_update_timeout;
+	vl->update_at = ktime_get_real_seconds() +
+			afs_vlocation_update_timeout;
 
 	spin_lock(&afs_vlocation_updates_lock);
 
@@ -506,7 +507,7 @@ void afs_put_vlocation(struct afs_vlocation *vl)
 	if (atomic_read(&vl->usage) == 0) {
 		_debug("buried");
 		list_move_tail(&vl->grave, &afs_vlocation_graveyard);
-		vl->time_of_death = get_seconds();
+		vl->time_of_death = ktime_get_real_seconds();
 		queue_delayed_work(afs_wq, &afs_vlocation_reap,
 				   afs_vlocation_timeout * HZ);
 
@@ -543,11 +544,11 @@ static void afs_vlocation_reaper(struct work_struct *work)
 	LIST_HEAD(corpses);
 	struct afs_vlocation *vl;
 	unsigned long delay, expiry;
-	time_t now;
+	time64_t now;
 
 	_enter("");
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	spin_lock(&afs_vlocation_graveyard_lock);
 
 	while (!list_empty(&afs_vlocation_graveyard)) {
@@ -622,13 +623,13 @@ static void afs_vlocation_updater(struct work_struct *work)
 {
 	struct afs_cache_vlocation vldb;
 	struct afs_vlocation *vl, *xvl;
-	time_t now;
+	time64_t now;
 	long timeout;
 	int ret;
 
 	_enter("");
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	/* find a record to update */
 	spin_lock(&afs_vlocation_updates_lock);
@@ -684,7 +685,8 @@ static void afs_vlocation_updater(struct work_struct *work)
 
 	/* and then reschedule */
 	_debug("reschedule");
-	vl->update_at = get_seconds() + afs_vlocation_update_timeout;
+	vl->update_at = ktime_get_real_seconds() +
+			afs_vlocation_update_timeout;
 
 	spin_lock(&afs_vlocation_updates_lock);
 
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 546f9d01710b..db73d6dad02b 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -106,11 +106,6 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	volume->cell		= params->cell;
 	volume->vid		= vlocation->vldb.vid[params->type];
 
-	volume->bdi.ra_pages	= VM_MAX_READAHEAD*1024/PAGE_SIZE; 
-	ret = bdi_setup_and_register(&volume->bdi, "afs");
-	if (ret)
-		goto error_bdi;
-
 	init_rwsem(&volume->server_sem);
 
 	/* look up all the applicable server records */
@@ -156,8 +151,6 @@ error:
 	return ERR_PTR(ret);
 
 error_discard:
-	bdi_destroy(&volume->bdi);
-error_bdi:
 	up_write(&params->cell->vl_sem);
 
 	for (loop = volume->nservers - 1; loop >= 0; loop--)
@@ -207,7 +200,6 @@ void afs_put_volume(struct afs_volume *volume)
 	for (loop = volume->nservers - 1; loop >= 0; loop--)
 		afs_put_server(volume->servers[loop]);
 
-	bdi_destroy(&volume->bdi);
 	kfree(volume);
 
 	_leave(" [destroyed]");
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c83c1a0e851f..2d2fccd5044b 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -84,10 +84,9 @@ void afs_put_writeback(struct afs_writeback *wb)
  * partly or wholly fill a page that's under preparation for writing
  */
 static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
-			 loff_t pos, struct page *page)
+			 loff_t pos, unsigned int len, struct page *page)
 {
 	struct afs_read *req;
-	loff_t i_size;
 	int ret;
 
 	_enter(",,%llu", (unsigned long long)pos);
@@ -99,14 +98,10 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
 
 	atomic_set(&req->usage, 1);
 	req->pos = pos;
+	req->len = len;
 	req->nr_pages = 1;
 	req->pages[0] = page;
-
-	i_size = i_size_read(&vnode->vfs_inode);
-	if (pos + PAGE_SIZE > i_size)
-		req->len = i_size - pos;
-	else
-		req->len = PAGE_SIZE;
+	get_page(page);
 
 	ret = afs_vnode_fetch_data(vnode, key, req);
 	afs_put_read(req);
@@ -159,12 +154,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 		kfree(candidate);
 		return -ENOMEM;
 	}
-	*pagep = page;
-	/* page won't leak in error case: it eventually gets cleaned off LRU */
 
 	if (!PageUptodate(page) && len != PAGE_SIZE) {
-		ret = afs_fill_page(vnode, key, index << PAGE_SHIFT, page);
+		ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page);
 		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			kfree(candidate);
 			_leave(" = %d [prep]", ret);
 			return ret;
@@ -172,6 +167,9 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 		SetPageUptodate(page);
 	}
 
+	/* page won't leak in error case: it eventually gets cleaned off LRU */
+	*pagep = page;
+
 try_again:
 	spin_lock(&vnode->writeback_lock);
 
@@ -233,7 +231,7 @@ flush_conflicting_wb:
 	if (wb->state == AFS_WBACK_PENDING)
 		wb->state = AFS_WBACK_CONFLICTING;
 	spin_unlock(&vnode->writeback_lock);
-	if (PageDirty(page)) {
+	if (clear_page_dirty_for_io(page)) {
 		ret = afs_write_back_from_locked_page(wb, page);
 		if (ret < 0) {
 			afs_put_writeback(candidate);
@@ -257,7 +255,9 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		  struct page *page, void *fsdata)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+	struct key *key = file->private_data;
 	loff_t i_size, maybe_i_size;
+	int ret;
 
 	_enter("{%x:%u},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, page->index);
@@ -273,6 +273,20 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		spin_unlock(&vnode->writeback_lock);
 	}
 
+	if (!PageUptodate(page)) {
+		if (copied < len) {
+			/* Try and load any missing data from the server.  The
+			 * unmarshalling routine will take care of clearing any
+			 * bits that are beyond the EOF.
+			 */
+			ret = afs_fill_page(vnode, key, pos + copied,
+					    len - copied, page);
+			if (ret < 0)
+				return ret;
+		}
+		SetPageUptodate(page);
+	}
+
 	set_page_dirty(page);
 	if (PageDirty(page))
 		_debug("dirtied");
@@ -307,10 +321,14 @@ static void afs_kill_pages(struct afs_vnode *vnode, bool error,
 		ASSERTCMP(pv.nr, ==, count);
 
 		for (loop = 0; loop < count; loop++) {
-			ClearPageUptodate(pv.pages[loop]);
+			struct page *page = pv.pages[loop];
+			ClearPageUptodate(page);
 			if (error)
-				SetPageError(pv.pages[loop]);
-			end_page_writeback(pv.pages[loop]);
+				SetPageError(page);
+			if (PageWriteback(page))
+				end_page_writeback(page);
+			if (page->index >= first)
+				first = page->index + 1;
 		}
 
 		__pagevec_release(&pv);
@@ -335,8 +353,6 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb,
 	_enter(",%lx", primary_page->index);
 
 	count = 1;
-	if (!clear_page_dirty_for_io(primary_page))
-		BUG();
 	if (test_set_page_writeback(primary_page))
 		BUG();
 
@@ -502,17 +518,17 @@ static int afs_writepages_region(struct address_space *mapping,
 		 */
 		lock_page(page);
 
-		if (page->mapping != mapping) {
+		if (page->mapping != mapping || !PageDirty(page)) {
 			unlock_page(page);
 			put_page(page);
 			continue;
 		}
 
-		if (wbc->sync_mode != WB_SYNC_NONE)
-			wait_on_page_writeback(page);
-
-		if (PageWriteback(page) || !PageDirty(page)) {
+		if (PageWriteback(page)) {
 			unlock_page(page);
+			if (wbc->sync_mode != WB_SYNC_NONE)
+				wait_on_page_writeback(page);
+			put_page(page);
 			continue;
 		}
 
@@ -523,6 +539,8 @@ static int afs_writepages_region(struct address_space *mapping,
 		wb->state = AFS_WBACK_WRITING;
 		spin_unlock(&wb->vnode->writeback_lock);
 
+		if (!clear_page_dirty_for_io(page))
+			BUG();
 		ret = afs_write_back_from_locked_page(wb, page);
 		unlock_page(page);
 		put_page(page);
@@ -746,6 +764,20 @@ out:
 }
 
 /*
+ * Flush out all outstanding writes on a file opened for writing when it is
+ * closed.
+ */
+int afs_flush(struct file *file, fl_owner_t id)
+{
+	_enter("");
+
+	if ((file->f_mode & FMODE_WRITE) == 0)
+		return 0;
+
+	return vfs_fsync(file, 0);
+}
+
+/*
  * notification that a previously read-only page is about to become writable
  * - if it returns an error, the caller will deliver a bus error signal
  */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2eca00ec4370..9ccabe3bb7de 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -885,6 +885,8 @@ static void bdev_evict_inode(struct inode *inode)
 	spin_lock(&bdev_lock);
 	list_del_init(&bdev->bd_list);
 	spin_unlock(&bdev_lock);
+	/* Detach inode from wb early as bdi_put() may free bdi->wb */
+	inode_detach_wb(inode);
 	if (bdev->bd_bdi != &noop_backing_dev_info) {
 		bdi_put(bdev->bd_bdi);
 		bdev->bd_bdi = &noop_backing_dev_info;
@@ -1451,7 +1453,6 @@ int revalidate_disk(struct gendisk *disk)
 
 	if (disk->fops->revalidate_disk)
 		ret = disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	bdev = bdget_disk(disk, 0);
 	if (!bdev)
 		return ret;
@@ -1556,8 +1557,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		if (bdev->bd_bdi == &noop_backing_dev_info)
-			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 
 		if (!partno) {
 			ret = -ENXIO;
@@ -1622,6 +1621,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
+
+		if (bdev->bd_bdi == &noop_backing_dev_info)
+			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 	} else {
 		if (bdev->bd_contains == bdev) {
 			ret = 0;
@@ -1653,8 +1655,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_queue = NULL;
-	bdi_put(bdev->bd_bdi);
-	bdev->bd_bdi = &noop_backing_dev_info;
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
@@ -1876,12 +1876,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		kill_bdev(bdev);
 
 		bdev_write_inode(bdev);
-		/*
-		 * Detaching bdev inode from its wb in __destroy_inode()
-		 * is too late: the queue which embeds its bdi (along with
-		 * root wb) can be gone as soon as we put_disk() below.
-		 */
-		inode_detach_wb(bdev->bd_inode);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
@@ -2074,7 +2068,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
 {
 	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct address_space *mapping;
 	loff_t end = start + len - 1;
 	loff_t isize;
@@ -2110,18 +2103,13 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	case FALLOC_FL_ZERO_RANGE:
 	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
 		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
-					    GFP_KERNEL, false);
+					    GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
-		/* Only punch if the device can do zeroing discard. */
-		if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data)
-			return -EOPNOTSUPP;
-		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
-					     GFP_KERNEL, 0);
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
-		if (!blk_queue_discard(q))
-			return -EOPNOTSUPP;
 		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
 					     GFP_KERNEL, 0);
 		break;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 29b7fc28c607..3e21211e99c3 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -810,7 +810,6 @@ struct btrfs_fs_info {
 	struct btrfs_super_block *super_for_commit;
 	struct super_block *sb;
 	struct inode *btree_inode;
-	struct backing_dev_info bdi;
 	struct mutex tree_log_mutex;
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
@@ -1259,7 +1258,7 @@ struct btrfs_root {
 	atomic_t will_be_snapshoted;
 
 	/* For qgroup metadata space reserve */
-	atomic_t qgroup_meta_rsv;
+	atomic64_t qgroup_meta_rsv;
 };
 static inline u32 btrfs_inode_sectorsize(const struct inode *inode)
 {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08b74daf35d0..061c1d1f774f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1342,7 +1342,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	atomic_set(&root->orphan_inodes, 0);
 	atomic_set(&root->refs, 1);
 	atomic_set(&root->will_be_snapshoted, 0);
-	atomic_set(&root->qgroup_meta_rsv, 0);
+	atomic64_set(&root->qgroup_meta_rsv, 0);
 	root->log_transid = 0;
 	root->log_transid_committed = -1;
 	root->last_log_commit = 0;
@@ -1808,21 +1808,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	return ret;
 }
 
-static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
-{
-	int err;
-
-	err = bdi_setup_and_register(bdi, "btrfs");
-	if (err)
-		return err;
-
-	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
-	bdi->congested_fn	= btrfs_congested_fn;
-	bdi->congested_data	= info;
-	bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
-	return 0;
-}
-
 /*
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
@@ -2601,16 +2586,10 @@ int open_ctree(struct super_block *sb,
 		goto fail;
 	}
 
-	ret = setup_bdi(fs_info, &fs_info->bdi);
-	if (ret) {
-		err = ret;
-		goto fail_srcu;
-	}
-
 	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
-		goto fail_bdi;
+		goto fail_srcu;
 	}
 	fs_info->dirty_metadata_batch = PAGE_SIZE *
 					(1 + ilog2(nr_cpu_ids));
@@ -2718,7 +2697,6 @@ int open_ctree(struct super_block *sb,
 
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
-	sb->s_bdi = &fs_info->bdi;
 
 	btrfs_init_btree_inode(fs_info);
 
@@ -2915,9 +2893,12 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
-	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
-	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
-				    SZ_4M / PAGE_SIZE);
+	sb->s_bdi->congested_fn = btrfs_congested_fn;
+	sb->s_bdi->congested_data = fs_info;
+	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
+	sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
+	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
@@ -3285,8 +3266,6 @@ fail_delalloc_bytes:
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
 fail_dirty_metadata_bytes:
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
-fail_bdi:
-	bdi_destroy(&fs_info->bdi);
 fail_srcu:
 	cleanup_srcu_struct(&fs_info->subvol_srcu);
 fail:
@@ -4007,7 +3986,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
 	percpu_counter_destroy(&fs_info->bio_counter);
-	bdi_destroy(&fs_info->bdi);
 	cleanup_srcu_struct(&fs_info->subvol_srcu);
 
 	btrfs_free_stripe_hash_table(fs_info);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 28e81922a21c..27fdb250b446 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1714,7 +1714,8 @@ static int __process_pages_contig(struct address_space *mapping,
 			 * can we find nothing at @index.
 			 */
 			ASSERT(page_ops & PAGE_LOCK);
-			return ret;
+			err = -EAGAIN;
+			goto out;
 		}
 
 		for (i = 0; i < ret; i++) {
@@ -2583,26 +2584,36 @@ static void end_bio_extent_readpage(struct bio *bio)
 
 		if (tree->ops) {
 			ret = tree->ops->readpage_io_failed_hook(page, mirror);
-			if (!ret && !bio->bi_error)
-				uptodate = 1;
-		} else {
+			if (ret == -EAGAIN) {
+				/*
+				 * Data inode's readpage_io_failed_hook() always
+				 * returns -EAGAIN.
+				 *
+				 * The generic bio_readpage_error handles errors
+				 * the following way: If possible, new read
+				 * requests are created and submitted and will
+				 * end up in end_bio_extent_readpage as well (if
+				 * we're lucky, not in the !uptodate case). In
+				 * that case it returns 0 and we just go on with
+				 * the next page in our bio. If it can't handle
+				 * the error it will return -EIO and we remain
+				 * responsible for that page.
+				 */
+				ret = bio_readpage_error(bio, offset, page,
+							 start, end, mirror);
+				if (ret == 0) {
+					uptodate = !bio->bi_error;
+					offset += len;
+					continue;
+				}
+			}
+
 			/*
-			 * The generic bio_readpage_error handles errors the
-			 * following way: If possible, new read requests are
-			 * created and submitted and will end up in
-			 * end_bio_extent_readpage as well (if we're lucky, not
-			 * in the !uptodate case). In that case it returns 0 and
-			 * we just go on with the next page in our bio. If it
-			 * can't handle the error it will return -EIO and we
-			 * remain responsible for that page.
+			 * metadata's readpage_io_failed_hook() always returns
+			 * -EIO and fixes nothing.  -EIO is also returned if
+			 * data inode error could not be fixed.
 			 */
-			ret = bio_readpage_error(bio, offset, page, start, end,
-						 mirror);
-			if (ret == 0) {
-				uptodate = !bio->bi_error;
-				offset += len;
-				continue;
-			}
+			ASSERT(ret == -EIO);
 		}
 readpage_ok:
 		if (likely(uptodate)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c40060cc481f..5e71f1ea3391 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6709,6 +6709,20 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	max_size = min_t(unsigned long, PAGE_SIZE, max_size);
 	ret = btrfs_decompress(compress_type, tmp, page,
 			       extent_offset, inline_size, max_size);
+
+	/*
+	 * decompression code contains a memset to fill in any space between the end
+	 * of the uncompressed data and the end of max_size in case the decompressed
+	 * data ends up shorter than ram_bytes.  That doesn't cover the hole between
+	 * the end of an inline extent and the beginning of the next block, so we
+	 * cover that region here.
+	 */
+
+	if (max_size + pg_offset < PAGE_SIZE) {
+		char *map = kmap(page);
+		memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset);
+		kunmap(page);
+	}
 	kfree(tmp);
 	return ret;
 }
@@ -7896,7 +7910,6 @@ struct btrfs_retry_complete {
 static void btrfs_retry_endio_nocsum(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
-	struct inode *inode;
 	struct bio_vec *bvec;
 	int i;
 
@@ -7904,12 +7917,12 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 		goto end;
 
 	ASSERT(bio->bi_vcnt == 1);
-	inode = bio->bi_io_vec->bv_page->mapping->host;
-	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
 
 	done->uptodate = 1;
 	bio_for_each_segment_all(bvec, bio, i)
-	clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0);
+		clean_io_failure(BTRFS_I(done->inode), done->start,
+				 bvec->bv_page, 0);
 end:
 	complete(&done->done);
 	bio_put(bio);
@@ -7959,8 +7972,10 @@ next_block_or_try_again:
 
 		start += sectorsize;
 
-		if (nr_sectors--) {
+		nr_sectors--;
+		if (nr_sectors) {
 			pgoff += sectorsize;
+			ASSERT(pgoff < PAGE_SIZE);
 			goto next_block_or_try_again;
 		}
 	}
@@ -7972,9 +7987,7 @@ static void btrfs_retry_endio(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
-	struct inode *inode;
 	struct bio_vec *bvec;
-	u64 start;
 	int uptodate;
 	int ret;
 	int i;
@@ -7984,11 +7997,8 @@ static void btrfs_retry_endio(struct bio *bio)
 
 	uptodate = 1;
 
-	start = done->start;
-
 	ASSERT(bio->bi_vcnt == 1);
-	inode = bio->bi_io_vec->bv_page->mapping->host;
-	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		ret = __readpage_endio_check(done->inode, io_bio, i,
@@ -8066,8 +8076,10 @@ next:
 
 		ASSERT(nr_sectors);
 
-		if (--nr_sectors) {
+		nr_sectors--;
+		if (nr_sectors) {
 			pgoff += sectorsize;
+			ASSERT(pgoff < PAGE_SIZE);
 			goto next_block;
 		}
 	}
@@ -10509,9 +10521,9 @@ out_inode:
 }
 
 __attribute__((const))
-static int dummy_readpage_io_failed_hook(struct page *page, int failed_mirror)
+static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
 {
-	return 0;
+	return -EAGAIN;
 }
 
 static const struct inode_operations btrfs_dir_inode_operations = {
@@ -10556,7 +10568,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
 	.merge_bio_hook = btrfs_merge_bio_hook,
-	.readpage_io_failed_hook = dummy_readpage_io_failed_hook,
+	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
 
 	/* optional callbacks */
 	.fill_delalloc = run_delalloc_range,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index a5da750c1087..afbea61d957e 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1042,9 +1042,12 @@ static void report_reserved_underflow(struct btrfs_fs_info *fs_info,
 				      struct btrfs_qgroup *qgroup,
 				      u64 num_bytes)
 {
-	btrfs_warn(fs_info,
+#ifdef CONFIG_BTRFS_DEBUG
+	WARN_ON(qgroup->reserved < num_bytes);
+	btrfs_debug(fs_info,
 		"qgroup %llu reserved space underflow, have: %llu, to free: %llu",
 		qgroup->qgroupid, qgroup->reserved, num_bytes);
+#endif
 	qgroup->reserved = 0;
 }
 /*
@@ -1075,7 +1078,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 	qgroup->excl += sign * num_bytes;
 	qgroup->excl_cmpr += sign * num_bytes;
 	if (sign > 0) {
-		if (WARN_ON(qgroup->reserved < num_bytes))
+		if (qgroup->reserved < num_bytes)
 			report_reserved_underflow(fs_info, qgroup, num_bytes);
 		else
 			qgroup->reserved -= num_bytes;
@@ -1100,7 +1103,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 		WARN_ON(sign < 0 && qgroup->excl < num_bytes);
 		qgroup->excl += sign * num_bytes;
 		if (sign > 0) {
-			if (WARN_ON(qgroup->reserved < num_bytes))
+			if (qgroup->reserved < num_bytes)
 				report_reserved_underflow(fs_info, qgroup,
 							  num_bytes);
 			else
@@ -2469,7 +2472,7 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 
 		qg = unode_aux_to_qgroup(unode);
 
-		if (WARN_ON(qg->reserved < num_bytes))
+		if (qg->reserved < num_bytes)
 			report_reserved_underflow(fs_info, qg, num_bytes);
 		else
 			qg->reserved -= num_bytes;
@@ -2948,20 +2951,20 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 	ret = qgroup_reserve(root, num_bytes, enforce);
 	if (ret < 0)
 		return ret;
-	atomic_add(num_bytes, &root->qgroup_meta_rsv);
+	atomic64_add(num_bytes, &root->qgroup_meta_rsv);
 	return ret;
 }
 
 void btrfs_qgroup_free_meta_all(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	int reserved;
+	u64 reserved;
 
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
 	    !is_fstree(root->objectid))
 		return;
 
-	reserved = atomic_xchg(&root->qgroup_meta_rsv, 0);
+	reserved = atomic64_xchg(&root->qgroup_meta_rsv, 0);
 	if (reserved == 0)
 		return;
 	btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved);
@@ -2976,8 +2979,8 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
 		return;
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
-	WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes);
-	atomic_sub(num_bytes, &root->qgroup_meta_rsv);
+	WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes);
+	atomic64_sub(num_bytes, &root->qgroup_meta_rsv);
 	btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes);
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 456c8901489b..a60d5bfb8a49 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6305,8 +6305,13 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
+	/*
+	 * Check that we don't overflow at later allocations, we request
+	 * clone_sources_count + 1 items, and compare to unsigned long inside
+	 * access_ok.
+	 */
 	if (arg->clone_sources_count >
-	    ULLONG_MAX / sizeof(*arg->clone_sources)) {
+	    ULONG_MAX / sizeof(struct clone_root) - 1) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index da687dc79cce..72a053c9a7f0 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -549,16 +549,19 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_ssd:
 			btrfs_set_and_info(info, SSD,
 					   "use ssd allocation scheme");
+			btrfs_clear_opt(info->mount_opt, NOSSD);
 			break;
 		case Opt_ssd_spread:
 			btrfs_set_and_info(info, SSD_SPREAD,
 					   "use spread ssd allocation scheme");
 			btrfs_set_opt(info->mount_opt, SSD);
+			btrfs_clear_opt(info->mount_opt, NOSSD);
 			break;
 		case Opt_nossd:
 			btrfs_set_and_info(info, NOSSD,
 					     "not using ssd allocation scheme");
 			btrfs_clear_opt(info->mount_opt, SSD);
+			btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
 			break;
 		case Opt_barrier:
 			btrfs_clear_and_info(info, NOBARRIER,
@@ -1133,6 +1136,13 @@ static int btrfs_fill_super(struct super_block *sb,
 #endif
 	sb->s_flags |= MS_I_VERSION;
 	sb->s_iflags |= SB_I_CGROUPWB;
+
+	err = super_setup_bdi(sb);
+	if (err) {
+		btrfs_err(fs_info, "super_setup_bdi failed");
+		return err;
+	}
+
 	err = open_ctree(sb, fs_devices, (char *)data);
 	if (err) {
 		btrfs_err(fs_info, "open_ctree failed");
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 73d56eef5e60..ab8a66d852f9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6213,7 +6213,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
 		dev = bbio->stripes[dev_nr].dev;
 		if (!dev || !dev->bdev ||
-		    (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) {
+		    (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) {
 			bbio_error(bbio, first_bio, logical);
 			continue;
 		}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1a3e1b40799a..9ecb2fd348cb 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -578,7 +578,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
 	if (writeback_stat >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
-		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -700,7 +700,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 			if (atomic_long_dec_return(&fsc->writeback_count) <
 			     CONGESTION_OFF_THRESH(
 					fsc->mount_options->congestion_kb))
-				clear_bdi_congested(&fsc->backing_dev_info,
+				clear_bdi_congested(inode_to_bdi(inode),
 						    BLK_RW_ASYNC);
 
 			if (rc < 0)
@@ -979,7 +979,7 @@ get_more_pages:
 			if (atomic_long_inc_return(&fsc->writeback_count) >
 			    CONGESTION_ON_THRESH(
 				    fsc->mount_options->congestion_kb)) {
-				set_bdi_congested(&fsc->backing_dev_info,
+				set_bdi_congested(inode_to_bdi(inode),
 						  BLK_RW_ASYNC);
 			}
 
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index f2ae393e2c31..3ef11bc8d728 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -251,7 +251,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 		goto out;
 
 	snprintf(name, sizeof(name), "../../bdi/%s",
-		 dev_name(fsc->backing_dev_info.dev));
+		 dev_name(fsc->sb->s_bdi->dev));
 	fsc->debugfs_bdi =
 		debugfs_create_symlink("bdi",
 				       fsc->client->debugfs_dir,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d449e1c03cbd..d3119fe3ab45 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2071,11 +2071,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
-	if (ia_valid & ATTR_MODE) {
-		err = posix_acl_chmod(inode, attr->ia_mode);
-		if (err)
-			goto out_put;
-	}
 
 	if (mask) {
 		req->r_inode = inode;
@@ -2089,13 +2084,11 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	     ceph_cap_string(dirtied), mask);
 
 	ceph_mdsc_put_request(req);
-	if (mask & CEPH_SETATTR_SIZE)
-		__ceph_do_pending_vmtruncate(inode);
-	ceph_free_cap_flush(prealloc_cf);
-	return err;
-out_put:
-	ceph_mdsc_put_request(req);
 	ceph_free_cap_flush(prealloc_cf);
+
+	if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+		__ceph_do_pending_vmtruncate(inode);
+
 	return err;
 }
 
@@ -2114,7 +2107,12 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err != 0)
 		return err;
 
-	return __ceph_setattr(inode, attr);
+	err = __ceph_setattr(inode, attr);
+
+	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+		err = posix_acl_chmod(inode, attr->ia_mode);
+
+	return err;
 }
 
 /*
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 0ec8d0114e57..a8c81b2052ca 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -579,10 +579,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 
 	atomic_long_set(&fsc->writeback_count, 0);
 
-	err = bdi_init(&fsc->backing_dev_info);
-	if (err < 0)
-		goto fail_client;
-
 	err = -ENOMEM;
 	/*
 	 * The number of concurrent works can be high but they don't need
@@ -590,7 +586,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	 */
 	fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1);
 	if (fsc->wb_wq == NULL)
-		goto fail_bdi;
+		goto fail_client;
 	fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1);
 	if (fsc->pg_inv_wq == NULL)
 		goto fail_wb_wq;
@@ -624,8 +620,6 @@ fail_pg_inv_wq:
 	destroy_workqueue(fsc->pg_inv_wq);
 fail_wb_wq:
 	destroy_workqueue(fsc->wb_wq);
-fail_bdi:
-	bdi_destroy(&fsc->backing_dev_info);
 fail_client:
 	ceph_destroy_client(fsc->client);
 fail:
@@ -643,8 +637,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 	destroy_workqueue(fsc->pg_inv_wq);
 	destroy_workqueue(fsc->trunc_wq);
 
-	bdi_destroy(&fsc->backing_dev_info);
-
 	mempool_destroy(fsc->wb_pagevec_pool);
 
 	destroy_mount_options(fsc->mount_options);
@@ -937,33 +929,32 @@ static int ceph_compare_super(struct super_block *sb, void *data)
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb,
-			     struct ceph_fs_client *fsc)
+static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
 {
 	int err;
 
+	err = super_setup_bdi_name(sb, "ceph-%ld",
+				   atomic_long_inc_return(&bdi_seq));
+	if (err)
+		return err;
+
 	/* set ra_pages based on rasize mount option? */
 	if (fsc->mount_options->rasize >= PAGE_SIZE)
-		fsc->backing_dev_info.ra_pages =
+		sb->s_bdi->ra_pages =
 			(fsc->mount_options->rasize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else
-		fsc->backing_dev_info.ra_pages =
-			VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+		sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 
 	if (fsc->mount_options->rsize > fsc->mount_options->rasize &&
 	    fsc->mount_options->rsize >= PAGE_SIZE)
-		fsc->backing_dev_info.io_pages =
+		sb->s_bdi->io_pages =
 			(fsc->mount_options->rsize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else if (fsc->mount_options->rsize == 0)
-		fsc->backing_dev_info.io_pages = ULONG_MAX;
+		sb->s_bdi->io_pages = ULONG_MAX;
 
-	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
-			   atomic_long_inc_return(&bdi_seq));
-	if (!err)
-		sb->s_bdi = &fsc->backing_dev_info;
-	return err;
+	return 0;
 }
 
 static struct dentry *ceph_mount(struct file_system_type *fs_type,
@@ -1018,7 +1009,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 		dout("get_sb got existing client %p\n", fsc);
 	} else {
 		dout("get_sb using new client %p\n", fsc);
-		err = ceph_register_bdi(sb, fsc);
+		err = ceph_setup_bdi(sb, fsc);
 		if (err < 0) {
 			res = ERR_PTR(err);
 			goto out_splat;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fe6b9cfc4013..176186b12457 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -92,8 +92,6 @@ struct ceph_fs_client {
 	struct workqueue_struct *trunc_wq;
 	atomic_long_t writeback_count;
 
-	struct backing_dev_info backing_dev_info;
-
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 07ed81cf1552..cbd216b57239 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -68,7 +68,6 @@ struct cifs_sb_info {
 	umode_t	mnt_dir_mode;
 	unsigned int mnt_cifs_flags;
 	char   *mountdata; /* options received at mount time or via DFS refs */
-	struct backing_dev_info bdi;
 	struct delayed_work prune_tlinks;
 	struct rcu_head rcu;
 	char *prepath;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 15e1db8738ae..d0d11b73b2af 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -37,6 +37,7 @@
 #include <linux/freezer.h>
 #include <linux/namei.h>
 #include <linux/random.h>
+#include <linux/uuid.h>
 #include <linux/xattr.h>
 #include <net/ipv6.h>
 #include "cifsfs.h"
@@ -138,7 +139,12 @@ cifs_read_super(struct super_block *sb)
 	sb->s_magic = CIFS_MAGIC_NUMBER;
 	sb->s_op = &cifs_super_ops;
 	sb->s_xattr = cifs_xattr_handlers;
-	sb->s_bdi = &cifs_sb->bdi;
+	rc = super_setup_bdi(sb);
+	if (rc)
+		goto out_no_root;
+	/* tune readahead according to rsize */
+	sb->s_bdi->ra_pages = cifs_sb->rsize / PAGE_SIZE;
+
 	sb->s_blocksize = CIFS_MAX_MSGSIZE;
 	sb->s_blocksize_bits = 14;	/* default 2**14 = CIFS_MAX_MSGSIZE */
 	inode = cifs_root_iget(sb);
@@ -972,6 +978,86 @@ out:
 	return rc;
 }
 
+ssize_t cifs_file_copychunk_range(unsigned int xid,
+				struct file *src_file, loff_t off,
+				struct file *dst_file, loff_t destoff,
+				size_t len, unsigned int flags)
+{
+	struct inode *src_inode = file_inode(src_file);
+	struct inode *target_inode = file_inode(dst_file);
+	struct cifsFileInfo *smb_file_src;
+	struct cifsFileInfo *smb_file_target;
+	struct cifs_tcon *src_tcon;
+	struct cifs_tcon *target_tcon;
+	ssize_t rc;
+
+	cifs_dbg(FYI, "copychunk range\n");
+
+	if (src_inode == target_inode) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (!src_file->private_data || !dst_file->private_data) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+		goto out;
+	}
+
+	rc = -EXDEV;
+	smb_file_target = dst_file->private_data;
+	smb_file_src = src_file->private_data;
+	src_tcon = tlink_tcon(smb_file_src->tlink);
+	target_tcon = tlink_tcon(smb_file_target->tlink);
+
+	if (src_tcon->ses != target_tcon->ses) {
+		cifs_dbg(VFS, "source and target of copy not on same server\n");
+		goto out;
+	}
+
+	/*
+	 * Note: cifs case is easier than btrfs since server responsible for
+	 * checks for proper open modes and file type and if it wants
+	 * server could even support copy of range where source = target
+	 */
+	lock_two_nondirectories(target_inode, src_inode);
+
+	cifs_dbg(FYI, "about to flush pages\n");
+	/* should we flush first and last page first */
+	truncate_inode_pages(&target_inode->i_data, 0);
+
+	if (target_tcon->ses->server->ops->copychunk_range)
+		rc = target_tcon->ses->server->ops->copychunk_range(xid,
+			smb_file_src, smb_file_target, off, len, destoff);
+	else
+		rc = -EOPNOTSUPP;
+
+	/* force revalidate of size and timestamps of target file now
+	 * that target is updated on the server
+	 */
+	CIFS_I(target_inode)->time = 0;
+	/* although unlocking in the reverse order from locking is not
+	 * strictly necessary here it is a little cleaner to be consistent
+	 */
+	unlock_two_nondirectories(src_inode, target_inode);
+
+out:
+	return rc;
+}
+
+static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
+				struct file *dst_file, loff_t destoff,
+				size_t len, unsigned int flags)
+{
+	unsigned int xid = get_xid();
+	ssize_t rc;
+
+	rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
+					len, flags);
+	free_xid(xid);
+	return rc;
+}
+
 const struct file_operations cifs_file_ops = {
 	.read_iter = cifs_loose_read_iter,
 	.write_iter = cifs_file_write_iter,
@@ -984,6 +1070,7 @@ const struct file_operations cifs_file_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1001,6 +1088,7 @@ const struct file_operations cifs_file_strict_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1018,6 +1106,7 @@ const struct file_operations cifs_file_direct_ops = {
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.unlocked_ioctl  = cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
@@ -1035,6 +1124,7 @@ const struct file_operations cifs_file_nobrl_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1051,6 +1141,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1067,6 +1158,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.unlocked_ioctl  = cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
@@ -1078,6 +1170,7 @@ const struct file_operations cifs_dir_ops = {
 	.release = cifs_closedir,
 	.read    = generic_read_dir,
 	.unlocked_ioctl  = cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = generic_file_llseek,
 };
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index da717fee3026..30bf89b1fd9a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -139,6 +139,11 @@ extern ssize_t	cifs_listxattr(struct dentry *, char *, size_t);
 # define cifs_listxattr NULL
 #endif
 
+extern ssize_t cifs_file_copychunk_range(unsigned int xid,
+					struct file *src_file, loff_t off,
+					struct file *dst_file, loff_t destoff,
+					size_t len, unsigned int flags);
+
 extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_CIFS_NFSD_EXPORT
 extern const struct export_operations cifs_export_ops;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index d42dd3288647..37f5a41cc50c 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -243,6 +243,7 @@ struct smb_version_operations {
 	/* verify the message */
 	int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+	int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
 	void (*downgrade_oplock)(struct TCP_Server_Info *,
 					struct cifsInodeInfo *, bool);
 	/* process transaction2 response */
@@ -407,9 +408,10 @@ struct smb_version_operations {
 	char * (*create_lease_buf)(u8 *, u8);
 	/* parse lease context buffer and return oplock/epoch info */
 	__u8 (*parse_lease_buf)(void *, unsigned int *);
-	int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
-			struct cifsFileInfo *target_file, u64 src_off, u64 len,
-			u64 dest_off);
+	ssize_t (*copychunk_range)(const unsigned int,
+			struct cifsFileInfo *src_file,
+			struct cifsFileInfo *target_file,
+			u64 src_off, u64 len, u64 dest_off);
 	int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src,
 			struct cifsFileInfo *target_file, u64 src_off, u64 len,
 			u64 dest_off);
@@ -946,7 +948,6 @@ struct cifs_tcon {
 	bool use_persistent:1; /* use persistent instead of durable handles */
 #ifdef CONFIG_CIFS_SMB2
 	bool print:1;		/* set if connection to printer share */
-	bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
 	__le32 capabilities;
 	__u32 share_flags;
 	__u32 maximal_access;
@@ -1343,6 +1344,7 @@ struct mid_q_entry {
 	void *callback_data;	  /* general purpose pointer for callback */
 	void *resp_buf;		/* pointer to received SMB header */
 	int mid_state;	/* wish this were enum but can not pass to wait_event */
+	unsigned int mid_flags;
 	__le16 command;		/* smb command code */
 	bool large_buf:1;	/* if valid response, is pointer to large buf */
 	bool multiRsp:1;	/* multiple trans2 responses for one request  */
@@ -1350,6 +1352,12 @@ struct mid_q_entry {
 	bool decrypted:1;	/* decrypted entry */
 };
 
+struct close_cancelled_open {
+	struct cifs_fid         fid;
+	struct cifs_tcon        *tcon;
+	struct work_struct      work;
+};
+
 /*	Make code in transport.c a little cleaner by moving
 	update of optional stats into function below */
 #ifdef CONFIG_CIFS_STATS2
@@ -1481,6 +1489,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   MID_RESPONSE_MALFORMED 0x10
 #define   MID_SHUTDOWN		 0x20
 
+/* Flags */
+#define   MID_WAIT_CANCELLED	 1 /* Cancelled while waiting for response */
+
 /* Types of response buffer returned from SendReceive2 */
 #define   CIFS_NO_BUFFER        0    /* Response buffer not returned */
 #define   CIFS_SMALL_BUFFER     1
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 066950671929..5d21f00ae341 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1428,6 +1428,8 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	length = cifs_discard_remaining_data(server);
 	dequeue_mid(mid, rdata->result);
+	mid->resp_buf = server->smallbuf;
+	server->smallbuf = NULL;
 	return length;
 }
 
@@ -1541,6 +1543,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return cifs_readv_discard(server, mid);
 
 	dequeue_mid(mid, false);
+	mid->resp_buf = server->smallbuf;
+	server->smallbuf = NULL;
 	return length;
 }
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 9ae695ae3ed7..9bc0b4d6d065 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -35,6 +35,7 @@
 #include <linux/pagevec.h>
 #include <linux/freezer.h>
 #include <linux/namei.h>
+#include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <linux/inet.h>
@@ -904,10 +905,19 @@ cifs_demultiplex_thread(void *p)
 
 		server->lstrp = jiffies;
 		if (mid_entry != NULL) {
+			if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+			     mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+					server->ops->handle_cancelled_mid)
+				server->ops->handle_cancelled_mid(
+							mid_entry->resp_buf,
+							server);
+
 			if (!mid_entry->multiRsp || mid_entry->multiEnd)
 				mid_entry->callback(mid_entry);
-		} else if (!server->ops->is_oplock_break ||
-			   !server->ops->is_oplock_break(buf, server)) {
+		} else if (server->ops->is_oplock_break &&
+			   server->ops->is_oplock_break(buf, server)) {
+			cifs_dbg(FYI, "Received oplock break\n");
+		} else {
 			cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
 				 atomic_read(&midCount));
 			cifs_dump_mem("Received Data is: ", buf,
@@ -2903,16 +2913,14 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 {
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
+	bool old_set = old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH;
+	bool new_set = new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH;
 
-	if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) {
-		if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH))
-			return 0;
-		/* The prepath should be null terminated strings */
-		if (strcmp(new->prepath, old->prepath))
-			return 0;
-
+	if (old_set && new_set && !strcmp(new->prepath, old->prepath))
 		return 1;
-	}
+	else if (!old_set && !new_set)
+		return 1;
+
 	return 0;
 }
 
@@ -3683,10 +3691,6 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 	int referral_walks_count = 0;
 #endif
 
-	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
-	if (rc)
-		return rc;
-
 #ifdef CONFIG_CIFS_DFS_UPCALL
 try_mount_again:
 	/* cleanup activities if we're chasing a referral */
@@ -3714,7 +3718,6 @@ try_mount_again:
 	server = cifs_get_tcp_session(volume_info);
 	if (IS_ERR(server)) {
 		rc = PTR_ERR(server);
-		bdi_destroy(&cifs_sb->bdi);
 		goto out;
 	}
 	if ((volume_info->max_credits < 20) ||
@@ -3744,6 +3747,9 @@ try_mount_again:
 	if (IS_ERR(tcon)) {
 		rc = PTR_ERR(tcon);
 		tcon = NULL;
+		if (rc == -EACCES)
+			goto mount_fail_check;
+
 		goto remote_path_check;
 	}
 
@@ -3768,9 +3774,6 @@ try_mount_again:
 	cifs_sb->wsize = server->ops->negotiate_wsize(tcon, volume_info);
 	cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info);
 
-	/* tune readahead according to rsize */
-	cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_SIZE;
-
 remote_path_check:
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	/*
@@ -3887,7 +3890,6 @@ mount_fail_check:
 			cifs_put_smb_ses(ses);
 		else
 			cifs_put_tcp_session(server, 0);
-		bdi_destroy(&cifs_sb->bdi);
 	}
 
 out:
@@ -4090,7 +4092,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb)
 	}
 	spin_unlock(&cifs_sb->tlink_tree_lock);
 
-	bdi_destroy(&cifs_sb->bdi);
 	kfree(cifs_sb->mountdata);
 	kfree(cifs_sb->prepath);
 	call_rcu(&cifs_sb->rcu, delayed_free);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index aa3debbba826..21d404535739 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2597,7 +2597,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		wdata->credits = credits;
 
 		if (!wdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(wdata->cfile, false))
+		    !(rc = cifs_reopen_file(wdata->cfile, false)))
 			rc = server->ops->async_writev(wdata,
 					cifs_uncached_writedata_release);
 		if (rc) {
@@ -3022,7 +3022,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->credits = credits;
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 error:
 		if (rc) {
@@ -3617,7 +3617,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		}
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 		if (rc) {
 			add_credits_and_wake_if(server, rdata->credits, 0);
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 001528781b6b..7f4bba574930 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -34,71 +34,14 @@
 #include "cifs_ioctl.h"
 #include <linux/btrfs.h>
 
-static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
-			  struct file *dst_file)
-{
-	struct inode *src_inode = file_inode(src_file);
-	struct inode *target_inode = file_inode(dst_file);
-	struct cifsFileInfo *smb_file_src;
-	struct cifsFileInfo *smb_file_target;
-	struct cifs_tcon *src_tcon;
-	struct cifs_tcon *target_tcon;
-	int rc;
-
-	cifs_dbg(FYI, "ioctl clone range\n");
-
-	if (!src_file->private_data || !dst_file->private_data) {
-		rc = -EBADF;
-		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
-		goto out;
-	}
-
-	rc = -EXDEV;
-	smb_file_target = dst_file->private_data;
-	smb_file_src = src_file->private_data;
-	src_tcon = tlink_tcon(smb_file_src->tlink);
-	target_tcon = tlink_tcon(smb_file_target->tlink);
-
-	if (src_tcon->ses != target_tcon->ses) {
-		cifs_dbg(VFS, "source and target of copy not on same server\n");
-		goto out;
-	}
-
-	/*
-	 * Note: cifs case is easier than btrfs since server responsible for
-	 * checks for proper open modes and file type and if it wants
-	 * server could even support copy of range where source = target
-	 */
-	lock_two_nondirectories(target_inode, src_inode);
-
-	cifs_dbg(FYI, "about to flush pages\n");
-	/* should we flush first and last page first */
-	truncate_inode_pages(&target_inode->i_data, 0);
-
-	if (target_tcon->ses->server->ops->clone_range)
-		rc = target_tcon->ses->server->ops->clone_range(xid,
-			smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
-	else
-		rc = -EOPNOTSUPP;
-
-	/* force revalidate of size and timestamps of target file now
-	   that target is updated on the server */
-	CIFS_I(target_inode)->time = 0;
-	/* although unlocking in the reverse order from locking is not
-	   strictly necessary here it is a little cleaner to be consistent */
-	unlock_two_nondirectories(src_inode, target_inode);
-out:
-	return rc;
-}
-
-static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
+static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
 			unsigned long srcfd)
 {
 	int rc;
 	struct fd src_file;
 	struct inode *src_inode;
 
-	cifs_dbg(FYI, "ioctl clone range\n");
+	cifs_dbg(FYI, "ioctl copychunk range\n");
 	/* the destination must be opened for writing */
 	if (!(dst_file->f_mode & FMODE_WRITE)) {
 		cifs_dbg(FYI, "file target not open for write\n");
@@ -129,8 +72,10 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 	if (S_ISDIR(src_inode->i_mode))
 		goto out_fput;
 
-	rc = cifs_file_clone_range(xid, src_file.file, dst_file);
-
+	rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0,
+					src_inode->i_size, 0);
+	if (rc > 0)
+		rc = 0;
 out_fput:
 	fdput(src_file);
 out_drop_write:
@@ -251,7 +196,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 			}
 			break;
 		case CIFS_IOC_COPYCHUNK_FILE:
-			rc = cifs_ioctl_clone(xid, filep, arg);
+			rc = cifs_ioctl_copychunk(xid, filep, arg);
 			break;
 		case CIFS_IOC_SET_INTEGRITY:
 			if (pSMBFile == NULL)
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index d3fb11529ed9..843787850435 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -167,13 +167,11 @@ cifs_buf_get(void)
 
 	/* clear the first few header bytes */
 	/* for most paths, more is cleared in header_assemble */
-	if (ret_buf) {
-		memset(ret_buf, 0, buf_size + 3);
-		atomic_inc(&bufAllocCount);
+	memset(ret_buf, 0, buf_size + 3);
+	atomic_inc(&bufAllocCount);
 #ifdef CONFIG_CIFS_STATS2
-		atomic_inc(&totBufAllocCount);
+	atomic_inc(&totBufAllocCount);
 #endif /* CONFIG_CIFS_STATS2 */
-	}
 
 	return ret_buf;
 }
@@ -201,15 +199,13 @@ cifs_small_buf_get(void)
    albeit slightly larger than necessary and maxbuffersize
    defaults to this and can not be bigger */
 	ret_buf = mempool_alloc(cifs_sm_req_poolp, GFP_NOFS);
-	if (ret_buf) {
 	/* No need to clear memory here, cleared in header assemble */
 	/*	memset(ret_buf, 0, sizeof(struct smb_hdr) + 27);*/
-		atomic_inc(&smBufAllocCount);
+	atomic_inc(&smBufAllocCount);
 #ifdef CONFIG_CIFS_STATS2
-		atomic_inc(&totSmBufAllocCount);
+	atomic_inc(&totSmBufAllocCount);
 #endif /* CONFIG_CIFS_STATS2 */
 
-	}
 	return ret_buf;
 }
 
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index cc93ba4da9b5..27bc360c7ffd 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile)
 	return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
 }
 
+static bool
+cifs_can_echo(struct TCP_Server_Info *server)
+{
+	if (server->tcpStatus == CifsGood)
+		return true;
+
+	return false;
+}
+
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = {
 	.get_dfs_refer = CIFSGetDFSRefer,
 	.qfs_tcon = cifs_qfs_tcon,
 	.is_path_accessible = cifs_is_path_accessible,
+	.can_echo = cifs_can_echo,
 	.query_path_info = cifs_query_path_info,
 	.query_file_info = cifs_query_file_info,
 	.get_srv_inum = cifs_get_srv_inum,
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index fd516ea8b8f8..1a04b3a5beb1 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -659,3 +659,49 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
 	return false;
 }
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+	struct close_cancelled_open *cancelled = container_of(work,
+					struct close_cancelled_open, work);
+
+	cifs_dbg(VFS, "Close unmatched open\n");
+
+	SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+		   cancelled->fid.volatile_fid);
+	cifs_put_tcon(cancelled->tcon);
+	kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+	struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+	struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+	struct cifs_tcon *tcon;
+	struct close_cancelled_open *cancelled;
+
+	if (sync_hdr->Command != SMB2_CREATE ||
+	    sync_hdr->Status != STATUS_SUCCESS)
+		return 0;
+
+	cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+	if (!cancelled)
+		return -ENOMEM;
+
+	tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
+				  sync_hdr->TreeId);
+	if (!tcon) {
+		kfree(cancelled);
+		return -ENOENT;
+	}
+
+	cancelled->fid.persistent_fid = rsp->PersistentFileId;
+	cancelled->fid.volatile_fid = rsp->VolatileFileId;
+	cancelled->tcon = tcon;
+	INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+	queue_work(cifsiod_wq, &cancelled->work);
+
+	return 0;
+}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 0231108d9387..152e37f2ad92 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -21,6 +21,7 @@
 #include <linux/vfs.h>
 #include <linux/falloc.h>
 #include <linux/scatterlist.h>
+#include <linux/uuid.h>
 #include <crypto/aead.h>
 #include "cifsglob.h"
 #include "smb2pdu.h"
@@ -592,8 +593,8 @@ req_res_key_exit:
 	return rc;
 }
 
-static int
-smb2_clone_range(const unsigned int xid,
+static ssize_t
+smb2_copychunk_range(const unsigned int xid,
 			struct cifsFileInfo *srcfile,
 			struct cifsFileInfo *trgtfile, u64 src_off,
 			u64 len, u64 dest_off)
@@ -605,13 +606,14 @@ smb2_clone_range(const unsigned int xid,
 	struct cifs_tcon *tcon;
 	int chunks_copied = 0;
 	bool chunk_sizes_updated = false;
+	ssize_t bytes_written, total_bytes_written = 0;
 
 	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
 
 	if (pcchunk == NULL)
 		return -ENOMEM;
 
-	cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n");
+	cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n");
 	/* Request a key from the server to identify the source of the copy */
 	rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink),
 				srcfile->fid.persistent_fid,
@@ -669,14 +671,16 @@ smb2_clone_range(const unsigned int xid,
 			}
 			chunks_copied++;
 
-			src_off += le32_to_cpu(retbuf->TotalBytesWritten);
-			dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
-			len -= le32_to_cpu(retbuf->TotalBytesWritten);
+			bytes_written = le32_to_cpu(retbuf->TotalBytesWritten);
+			src_off += bytes_written;
+			dest_off += bytes_written;
+			len -= bytes_written;
+			total_bytes_written += bytes_written;
 
-			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n",
 				le32_to_cpu(retbuf->ChunksWritten),
 				le32_to_cpu(retbuf->ChunkBytesWritten),
-				le32_to_cpu(retbuf->TotalBytesWritten));
+				bytes_written);
 		} else if (rc == -EINVAL) {
 			if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
 				goto cchunk_out;
@@ -713,7 +717,10 @@ smb2_clone_range(const unsigned int xid,
 cchunk_out:
 	kfree(pcchunk);
 	kfree(retbuf);
-	return rc;
+	if (rc)
+		return rc;
+	else
+		return total_bytes_written;
 }
 
 static int
@@ -2322,6 +2329,7 @@ struct smb_version_operations smb20_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -2377,7 +2385,7 @@ struct smb_version_operations smb20_operations = {
 	.set_oplock_level = smb2_set_oplock_level,
 	.create_lease_buf = smb2_create_lease_buf,
 	.parse_lease_buf = smb2_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.get_dfs_refer = smb2_get_dfs_refer,
@@ -2404,6 +2412,7 @@ struct smb_version_operations smb21_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -2459,7 +2468,7 @@ struct smb_version_operations smb21_operations = {
 	.set_oplock_level = smb21_set_oplock_level,
 	.create_lease_buf = smb2_create_lease_buf,
 	.parse_lease_buf = smb2_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.enum_snapshots = smb3_enum_snapshots,
@@ -2488,6 +2497,7 @@ struct smb_version_operations smb30_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -2545,7 +2555,7 @@ struct smb_version_operations smb30_operations = {
 	.set_oplock_level = smb3_set_oplock_level,
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.duplicate_extents = smb2_duplicate_extents,
 	.validate_negotiate = smb3_validate_negotiate,
 	.wp_retry_size = smb2_wp_retry_size,
@@ -2582,6 +2592,7 @@ struct smb_version_operations smb311_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -2639,7 +2650,7 @@ struct smb_version_operations smb311_operations = {
 	.set_oplock_level = smb3_set_oplock_level,
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.duplicate_extents = smb2_duplicate_extents,
 /*	.validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */
 	.wp_retry_size = smb2_wp_retry_size,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7446496850a3..fb0da096c2ce 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -33,6 +33,7 @@
 #include <linux/vfs.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/uaccess.h>
+#include <linux/uuid.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include "smb2pdu.h"
@@ -562,8 +563,10 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	 * but for time being this is our only auth choice so doesn't matter.
 	 * We just found a server which sets blob length to zero expecting raw.
 	 */
-	if (blob_length == 0)
+	if (blob_length == 0) {
 		cifs_dbg(FYI, "missing security blob on negprot\n");
+		server->sec_ntlmssp = true;
+	}
 
 	rc = cifs_enable_signing(server, ses->sign);
 	if (rc)
@@ -1171,9 +1174,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	else
 		return -EIO;
 
-	if (tcon && tcon->bad_network_name)
-		return -ENOENT;
-
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -1185,6 +1185,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		return -EINVAL;
 	}
 
+	/* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+	if (tcon)
+		tcon->tid = 0;
+
 	rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
 	if (rc) {
 		kfree(unc_path);
@@ -1273,8 +1277,6 @@ tcon_exit:
 tcon_error_exit:
 	if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
-		if (tcon)
-			tcon->bad_network_name = true;
 	}
 	goto tcon_exit;
 }
@@ -2177,6 +2179,9 @@ void smb2_reconnect_server(struct work_struct *work)
 	struct cifs_tcon *tcon, *tcon2;
 	struct list_head tmp_list;
 	int tcon_exist = false;
+	int rc;
+	int resched = false;
+
 
 	/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
 	mutex_lock(&server->reconnect_mutex);
@@ -2204,13 +2209,18 @@ void smb2_reconnect_server(struct work_struct *work)
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
-		if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon))
+		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon);
+		if (!rc)
 			cifs_reopen_persistent_handles(tcon);
+		else
+			resched = true;
 		list_del_init(&tcon->rlist);
 		cifs_put_tcon(tcon);
 	}
 
 	cifs_dbg(FYI, "Reconnecting tcons finished\n");
+	if (resched)
+		queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ);
 	mutex_unlock(&server->reconnect_mutex);
 
 	/* now we can safely release srv struct */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 69e35873b1de..6853454fc871 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -48,6 +48,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses,
 			      struct smb_rqst *rqst);
 extern struct mid_q_entry *smb2_setup_async_request(
 			struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+					   __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+						__u64 ses_id, __u32  tid);
 extern int smb2_calc_signature(struct smb_rqst *rqst,
 				struct TCP_Server_Info *server);
 extern int smb3_calc_signature(struct smb_rqst *rqst,
@@ -164,6 +168,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 			     const u64 persistent_fid, const u64 volatile_fid,
 			     const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+					struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 7c3bb1bd7eed..c69ec96e92ac 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -115,23 +115,70 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
 	return 0;
 }
 
-struct cifs_ses *
-smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+static struct cifs_ses *
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
 {
 	struct cifs_ses *ses;
 
-	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
 		if (ses->Suid != ses_id)
 			continue;
-		spin_unlock(&cifs_tcp_ses_lock);
 		return ses;
 	}
+
+	return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+	struct cifs_ses *ses;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	ses = smb2_find_smb_ses_unlocked(server, ses_id);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32  tid)
+{
+	struct cifs_tcon *tcon;
+
+	list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+		if (tcon->tid != tid)
+			continue;
+		++tcon->tc_count;
+		return tcon;
+	}
+
 	return NULL;
 }
 
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32  tid)
+{
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	ses = smb2_find_smb_ses_unlocked(server, ses_id);
+	if (!ses) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return NULL;
+	}
+	tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	return tcon;
+}
+
 int
 smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
@@ -491,23 +538,19 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
 	}
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
-	if (temp == NULL)
-		return temp;
-	else {
-		memset(temp, 0, sizeof(struct mid_q_entry));
-		temp->mid = le64_to_cpu(shdr->MessageId);
-		temp->pid = current->pid;
-		temp->command = shdr->Command; /* Always LE */
-		temp->when_alloc = jiffies;
-		temp->server = server;
-
-		/*
-		 * The default is for the mid to be synchronous, so the
-		 * default callback just wakes up the current task.
-		 */
-		temp->callback = cifs_wake_up_task;
-		temp->callback_data = current;
-	}
+	memset(temp, 0, sizeof(struct mid_q_entry));
+	temp->mid = le64_to_cpu(shdr->MessageId);
+	temp->pid = current->pid;
+	temp->command = shdr->Command; /* Always LE */
+	temp->when_alloc = jiffies;
+	temp->server = server;
+
+	/*
+	 * The default is for the mid to be synchronous, so the
+	 * default callback just wakes up the current task.
+	 */
+	temp->callback = cifs_wake_up_task;
+	temp->callback_data = current;
 
 	atomic_inc(&midCount);
 	temp->mid_state = MID_REQUEST_ALLOCATED;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 526f0533cb4e..4d64b5b8fc9c 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -55,26 +55,22 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	}
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
-	if (temp == NULL)
-		return temp;
-	else {
-		memset(temp, 0, sizeof(struct mid_q_entry));
-		temp->mid = get_mid(smb_buffer);
-		temp->pid = current->pid;
-		temp->command = cpu_to_le16(smb_buffer->Command);
-		cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command);
+	memset(temp, 0, sizeof(struct mid_q_entry));
+	temp->mid = get_mid(smb_buffer);
+	temp->pid = current->pid;
+	temp->command = cpu_to_le16(smb_buffer->Command);
+	cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command);
 	/*	do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */
-		/* when mid allocated can be before when sent */
-		temp->when_alloc = jiffies;
-		temp->server = server;
+	/* when mid allocated can be before when sent */
+	temp->when_alloc = jiffies;
+	temp->server = server;
 
-		/*
-		 * The default is for the mid to be synchronous, so the
-		 * default callback just wakes up the current task.
-		 */
-		temp->callback = cifs_wake_up_task;
-		temp->callback_data = current;
-	}
+	/*
+	 * The default is for the mid to be synchronous, so the
+	 * default callback just wakes up the current task.
+	 */
+	temp->callback = cifs_wake_up_task;
+	temp->callback_data = current;
 
 	atomic_inc(&midCount);
 	temp->mid_state = MID_REQUEST_ALLOCATED;
@@ -752,9 +748,11 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
+		cifs_dbg(FYI, "Cancelling wait for mid %llu\n",	midQ->mid);
 		send_cancel(ses->server, rqst, midQ);
 		spin_lock(&GlobalMid_Lock);
 		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+			midQ->mid_flags |= MID_WAIT_CANCELLED;
 			midQ->callback = DeleteMidQEntry;
 			spin_unlock(&GlobalMid_Lock);
 			add_credits(ses->server, 1, optype);
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 2dea594da199..6058df380cc0 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -183,10 +183,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 		goto unlock_out;
 	}
 
-	error = bdi_setup_and_register(&vc->bdi, "coda");
-	if (error)
-		goto unlock_out;
-
 	vc->vc_sb = sb;
 	mutex_unlock(&vc->vc_mutex);
 
@@ -197,7 +193,10 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_magic = CODA_SUPER_MAGIC;
 	sb->s_op = &coda_super_operations;
 	sb->s_d_op = &coda_dentry_operations;
-	sb->s_bdi = &vc->bdi;
+
+	error = super_setup_bdi(sb);
+	if (error)
+		goto error;
 
 	/* get root fid from Venus: this needs the root inode */
 	error = venus_rootfid(sb, &fid);
@@ -228,7 +227,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 
 error:
 	mutex_lock(&vc->vc_mutex);
-	bdi_destroy(&vc->bdi);
 	vc->vc_sb = NULL;
 	sb->s_fs_info = NULL;
 unlock_out:
@@ -240,7 +238,6 @@ static void coda_put_super(struct super_block *sb)
 {
 	struct venus_comm *vcp = coda_vcp(sb);
 	mutex_lock(&vcp->vc_mutex);
-	bdi_destroy(&vcp->bdi);
 	vcp->vc_sb = NULL;
 	sb->s_fs_info = NULL;
 	mutex_unlock(&vcp->vc_mutex);
diff --git a/fs/compat.c b/fs/compat.c
index c61b506f5bc9..190b38b39d9e 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -15,555 +15,14 @@
  *  published by the Free Software Foundation.
  */
 
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/linkage.h>
 #include <linux/compat.h>
-#include <linux/errno.h>
-#include <linux/time.h>
-#include <linux/cred.h>
-#include <linux/fs.h>
-#include <linux/fcntl.h>
-#include <linux/namei.h>
-#include <linux/file.h>
-#include <linux/fdtable.h>
-#include <linux/vfs.h>
-#include <linux/ioctl.h>
-#include <linux/init.h>
 #include <linux/ncp_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/syscalls.h>
-#include <linux/ctype.h>
-#include <linux/dirent.h>
-#include <linux/fsnotify.h>
-#include <linux/highuid.h>
-#include <linux/personality.h>
-#include <linux/rwsem.h>
-#include <linux/tsacct_kern.h>
-#include <linux/security.h>
-#include <linux/highmem.h>
-#include <linux/signal.h>
-#include <linux/poll.h>
-#include <linux/mm.h>
-#include <linux/fs_struct.h>
 #include <linux/slab.h>
-#include <linux/pagemap.h>
-#include <linux/aio.h>
-
 #include <linux/uaccess.h>
-#include <asm/mmu_context.h>
-#include <asm/ioctls.h>
 #include "internal.h"
 
-/*
- * Not all architectures have sys_utime, so implement this in terms
- * of sys_utimes.
- */
-COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
-		       struct compat_utimbuf __user *, t)
-{
-	struct timespec tv[2];
-
-	if (t) {
-		if (get_user(tv[0].tv_sec, &t->actime) ||
-		    get_user(tv[1].tv_sec, &t->modtime))
-			return -EFAULT;
-		tv[0].tv_nsec = 0;
-		tv[1].tv_nsec = 0;
-	}
-	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
-}
-
-COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
-{
-	struct timespec tv[2];
-
-	if  (t) {
-		if (compat_get_timespec(&tv[0], &t[0]) ||
-		    compat_get_timespec(&tv[1], &t[1]))
-			return -EFAULT;
-
-		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
-			return 0;
-	}
-	return do_utimes(dfd, filename, t ? tv : NULL, flags);
-}
-
-COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
-{
-	struct timespec tv[2];
-
-	if (t) {
-		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
-		    get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
-		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
-		    get_user(tv[1].tv_nsec, &t[1].tv_usec))
-			return -EFAULT;
-		if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
-		    tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
-			return -EINVAL;
-		tv[0].tv_nsec *= 1000;
-		tv[1].tv_nsec *= 1000;
-	}
-	return do_utimes(dfd, filename, t ? tv : NULL, 0);
-}
-
-COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
-{
-	return compat_sys_futimesat(AT_FDCWD, filename, t);
-}
-
-static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
-{
-	struct compat_stat tmp;
-
-	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
-		return -EOVERFLOW;
-
-	memset(&tmp, 0, sizeof(tmp));
-	tmp.st_dev = old_encode_dev(stat->dev);
-	tmp.st_ino = stat->ino;
-	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
-		return -EOVERFLOW;
-	tmp.st_mode = stat->mode;
-	tmp.st_nlink = stat->nlink;
-	if (tmp.st_nlink != stat->nlink)
-		return -EOVERFLOW;
-	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
-	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
-	tmp.st_rdev = old_encode_dev(stat->rdev);
-	if ((u64) stat->size > MAX_NON_LFS)
-		return -EOVERFLOW;
-	tmp.st_size = stat->size;
-	tmp.st_atime = stat->atime.tv_sec;
-	tmp.st_atime_nsec = stat->atime.tv_nsec;
-	tmp.st_mtime = stat->mtime.tv_sec;
-	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
-	tmp.st_ctime = stat->ctime.tv_sec;
-	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
-	tmp.st_blocks = stat->blocks;
-	tmp.st_blksize = stat->blksize;
-	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
-}
-
-COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
-		       struct compat_stat __user *, statbuf)
-{
-	struct kstat stat;
-	int error;
-
-	error = vfs_stat(filename, &stat);
-	if (error)
-		return error;
-	return cp_compat_stat(&stat, statbuf);
-}
-
-COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
-		       struct compat_stat __user *, statbuf)
-{
-	struct kstat stat;
-	int error;
-
-	error = vfs_lstat(filename, &stat);
-	if (error)
-		return error;
-	return cp_compat_stat(&stat, statbuf);
-}
-
-#ifndef __ARCH_WANT_STAT64
-COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
-		       const char __user *, filename,
-		       struct compat_stat __user *, statbuf, int, flag)
-{
-	struct kstat stat;
-	int error;
-
-	error = vfs_fstatat(dfd, filename, &stat, flag);
-	if (error)
-		return error;
-	return cp_compat_stat(&stat, statbuf);
-}
-#endif
-
-COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
-		       struct compat_stat __user *, statbuf)
-{
-	struct kstat stat;
-	int error = vfs_fstat(fd, &stat);
-
-	if (!error)
-		error = cp_compat_stat(&stat, statbuf);
-	return error;
-}
-
-static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf)
-{
-	
-	if (sizeof ubuf->f_blocks == 4) {
-		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
-		     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
-			return -EOVERFLOW;
-		/* f_files and f_ffree may be -1; it's okay
-		 * to stuff that into 32 bits */
-		if (kbuf->f_files != 0xffffffffffffffffULL
-		 && (kbuf->f_files & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-		if (kbuf->f_ffree != 0xffffffffffffffffULL
-		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-	}
-	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
-	    __put_user(kbuf->f_type, &ubuf->f_type) ||
-	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
-	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
-	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
-	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
-	    __put_user(kbuf->f_files, &ubuf->f_files) ||
-	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
-	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
-	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
-	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
-	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
-	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
-	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
-		return -EFAULT;
-	return 0;
-}
-
-/*
- * The following statfs calls are copies of code from fs/statfs.c and
- * should be checked against those from time to time
- */
-COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
-{
-	struct kstatfs tmp;
-	int error = user_statfs(pathname, &tmp);
-	if (!error)
-		error = put_compat_statfs(buf, &tmp);
-	return error;
-}
-
-COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
-{
-	struct kstatfs tmp;
-	int error = fd_statfs(fd, &tmp);
-	if (!error)
-		error = put_compat_statfs(buf, &tmp);
-	return error;
-}
-
-static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
-{
-	if (sizeof(ubuf->f_bsize) == 4) {
-		if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
-		     kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
-			return -EOVERFLOW;
-		/* f_files and f_ffree may be -1; it's okay
-		 * to stuff that into 32 bits */
-		if (kbuf->f_files != 0xffffffffffffffffULL
-		 && (kbuf->f_files & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-		if (kbuf->f_ffree != 0xffffffffffffffffULL
-		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-	}
-	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
-	    __put_user(kbuf->f_type, &ubuf->f_type) ||
-	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
-	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
-	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
-	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
-	    __put_user(kbuf->f_files, &ubuf->f_files) ||
-	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
-	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
-	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
-	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
-	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
-	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
-	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
-		return -EFAULT;
-	return 0;
-}
-
-COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
-{
-	struct kstatfs tmp;
-	int error;
-
-	if (sz != sizeof(*buf))
-		return -EINVAL;
-
-	error = user_statfs(pathname, &tmp);
-	if (!error)
-		error = put_compat_statfs64(buf, &tmp);
-	return error;
-}
-
-COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
-{
-	struct kstatfs tmp;
-	int error;
-
-	if (sz != sizeof(*buf))
-		return -EINVAL;
-
-	error = fd_statfs(fd, &tmp);
-	if (!error)
-		error = put_compat_statfs64(buf, &tmp);
-	return error;
-}
-
-/*
- * This is a copy of sys_ustat, just dealing with a structure layout.
- * Given how simple this syscall is that apporach is more maintainable
- * than the various conversion hacks.
- */
-COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
-{
-	struct compat_ustat tmp;
-	struct kstatfs sbuf;
-	int err = vfs_ustat(new_decode_dev(dev), &sbuf);
-	if (err)
-		return err;
-
-	memset(&tmp, 0, sizeof(struct compat_ustat));
-	tmp.f_tfree = sbuf.f_bfree;
-	tmp.f_tinode = sbuf.f_ffree;
-	if (copy_to_user(u, &tmp, sizeof(struct compat_ustat)))
-		return -EFAULT;
-	return 0;
-}
-
-static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
-{
-	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
-	    __get_user(kfl->l_type, &ufl->l_type) ||
-	    __get_user(kfl->l_whence, &ufl->l_whence) ||
-	    __get_user(kfl->l_start, &ufl->l_start) ||
-	    __get_user(kfl->l_len, &ufl->l_len) ||
-	    __get_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-
-static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
-{
-	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
-	    __put_user(kfl->l_type, &ufl->l_type) ||
-	    __put_user(kfl->l_whence, &ufl->l_whence) ||
-	    __put_user(kfl->l_start, &ufl->l_start) ||
-	    __put_user(kfl->l_len, &ufl->l_len) ||
-	    __put_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-
-#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64
-static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
-{
-	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
-	    __get_user(kfl->l_type, &ufl->l_type) ||
-	    __get_user(kfl->l_whence, &ufl->l_whence) ||
-	    __get_user(kfl->l_start, &ufl->l_start) ||
-	    __get_user(kfl->l_len, &ufl->l_len) ||
-	    __get_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-#endif
-
-#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64
-static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
-{
-	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
-	    __put_user(kfl->l_type, &ufl->l_type) ||
-	    __put_user(kfl->l_whence, &ufl->l_whence) ||
-	    __put_user(kfl->l_start, &ufl->l_start) ||
-	    __put_user(kfl->l_len, &ufl->l_len) ||
-	    __put_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-#endif
-
-static unsigned int
-convert_fcntl_cmd(unsigned int cmd)
-{
-	switch (cmd) {
-	case F_GETLK64:
-		return F_GETLK;
-	case F_SETLK64:
-		return F_SETLK;
-	case F_SETLKW64:
-		return F_SETLKW;
-	}
-
-	return cmd;
-}
-
-COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
-		       compat_ulong_t, arg)
-{
-	mm_segment_t old_fs;
-	struct flock f;
-	long ret;
-	unsigned int conv_cmd;
-
-	switch (cmd) {
-	case F_GETLK:
-	case F_SETLK:
-	case F_SETLKW:
-		ret = get_compat_flock(&f, compat_ptr(arg));
-		if (ret != 0)
-			break;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		ret = sys_fcntl(fd, cmd, (unsigned long)&f);
-		set_fs(old_fs);
-		if (cmd == F_GETLK && ret == 0) {
-			/* GETLK was successful and we need to return the data...
-			 * but it needs to fit in the compat structure.
-			 * l_start shouldn't be too big, unless the original
-			 * start + end is greater than COMPAT_OFF_T_MAX, in which
-			 * case the app was asking for trouble, so we return
-			 * -EOVERFLOW in that case.
-			 * l_len could be too big, in which case we just truncate it,
-			 * and only allow the app to see that part of the conflicting
-			 * lock that might make sense to it anyway
-			 */
-
-			if (f.l_start > COMPAT_OFF_T_MAX)
-				ret = -EOVERFLOW;
-			if (f.l_len > COMPAT_OFF_T_MAX)
-				f.l_len = COMPAT_OFF_T_MAX;
-			if (ret == 0)
-				ret = put_compat_flock(&f, compat_ptr(arg));
-		}
-		break;
-
-	case F_GETLK64:
-	case F_SETLK64:
-	case F_SETLKW64:
-	case F_OFD_GETLK:
-	case F_OFD_SETLK:
-	case F_OFD_SETLKW:
-		ret = get_compat_flock64(&f, compat_ptr(arg));
-		if (ret != 0)
-			break;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		conv_cmd = convert_fcntl_cmd(cmd);
-		ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f);
-		set_fs(old_fs);
-		if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) {
-			/* need to return lock information - see above for commentary */
-			if (f.l_start > COMPAT_LOFF_T_MAX)
-				ret = -EOVERFLOW;
-			if (f.l_len > COMPAT_LOFF_T_MAX)
-				f.l_len = COMPAT_LOFF_T_MAX;
-			if (ret == 0)
-				ret = put_compat_flock64(&f, compat_ptr(arg));
-		}
-		break;
-
-	default:
-		ret = sys_fcntl(fd, cmd, arg);
-		break;
-	}
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
-		       compat_ulong_t, arg)
-{
-	switch (cmd) {
-	case F_GETLK64:
-	case F_SETLK64:
-	case F_SETLKW64:
-	case F_OFD_GETLK:
-	case F_OFD_SETLK:
-	case F_OFD_SETLKW:
-		return -EINVAL;
-	}
-	return compat_sys_fcntl64(fd, cmd, arg);
-}
-
-/* A write operation does a read from user space and vice versa */
-#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
-
-ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector, unsigned long nr_segs,
-		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer)
-{
-	compat_ssize_t tot_len;
-	struct iovec *iov = *ret_pointer = fast_pointer;
-	ssize_t ret = 0;
-	int seg;
-
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0)
-		goto out;
-
-	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV)
-		goto out;
-	if (nr_segs > fast_segs) {
-		ret = -ENOMEM;
-		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL)
-			goto out;
-	}
-	*ret_pointer = iov;
-
-	ret = -EFAULT;
-	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	/*
-	 * Single unix specification:
-	 * We should -EINVAL if an element length is not >= 0 and fitting an
-	 * ssize_t.
-	 *
-	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
-	 * no overflow possibility.
-	 */
-	tot_len = 0;
-	ret = -EINVAL;
-	for (seg = 0; seg < nr_segs; seg++) {
-		compat_uptr_t buf;
-		compat_ssize_t len;
-
-		if (__get_user(len, &uvector->iov_len) ||
-		   __get_user(buf, &uvector->iov_base)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
-			goto out;
-		if (type >= 0 &&
-		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - tot_len)
-			len = MAX_RW_COUNT - tot_len;
-		tot_len += len;
-		iov->iov_base = compat_ptr(buf);
-		iov->iov_len = (compat_size_t) len;
-		uvector++;
-		iov++;
-	}
-	ret = tot_len;
-
-out:
-	return ret;
-}
-
 struct compat_ncp_mount_data {
 	compat_int_t version;
 	compat_uint_t ncp_fd;
@@ -744,653 +203,3 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
  out:
 	return retval;
 }
-
-struct compat_old_linux_dirent {
-	compat_ulong_t	d_ino;
-	compat_ulong_t	d_offset;
-	unsigned short	d_namlen;
-	char		d_name[1];
-};
-
-struct compat_readdir_callback {
-	struct dir_context ctx;
-	struct compat_old_linux_dirent __user *dirent;
-	int result;
-};
-
-static int compat_fillonedir(struct dir_context *ctx, const char *name,
-			     int namlen, loff_t offset, u64 ino,
-			     unsigned int d_type)
-{
-	struct compat_readdir_callback *buf =
-		container_of(ctx, struct compat_readdir_callback, ctx);
-	struct compat_old_linux_dirent __user *dirent;
-	compat_ulong_t d_ino;
-
-	if (buf->result)
-		return -EINVAL;
-	d_ino = ino;
-	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
-		buf->result = -EOVERFLOW;
-		return -EOVERFLOW;
-	}
-	buf->result++;
-	dirent = buf->dirent;
-	if (!access_ok(VERIFY_WRITE, dirent,
-			(unsigned long)(dirent->d_name + namlen + 1) -
-				(unsigned long)dirent))
-		goto efault;
-	if (	__put_user(d_ino, &dirent->d_ino) ||
-		__put_user(offset, &dirent->d_offset) ||
-		__put_user(namlen, &dirent->d_namlen) ||
-		__copy_to_user(dirent->d_name, name, namlen) ||
-		__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	return 0;
-efault:
-	buf->result = -EFAULT;
-	return -EFAULT;
-}
-
-COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
-		struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
-{
-	int error;
-	struct fd f = fdget_pos(fd);
-	struct compat_readdir_callback buf = {
-		.ctx.actor = compat_fillonedir,
-		.dirent = dirent
-	};
-
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
-	if (buf.result)
-		error = buf.result;
-
-	fdput_pos(f);
-	return error;
-}
-
-struct compat_linux_dirent {
-	compat_ulong_t	d_ino;
-	compat_ulong_t	d_off;
-	unsigned short	d_reclen;
-	char		d_name[1];
-};
-
-struct compat_getdents_callback {
-	struct dir_context ctx;
-	struct compat_linux_dirent __user *current_dir;
-	struct compat_linux_dirent __user *previous;
-	int count;
-	int error;
-};
-
-static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
-		loff_t offset, u64 ino, unsigned int d_type)
-{
-	struct compat_linux_dirent __user * dirent;
-	struct compat_getdents_callback *buf =
-		container_of(ctx, struct compat_getdents_callback, ctx);
-	compat_ulong_t d_ino;
-	int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
-		namlen + 2, sizeof(compat_long_t));
-
-	buf->error = -EINVAL;	/* only used if we fail.. */
-	if (reclen > buf->count)
-		return -EINVAL;
-	d_ino = ino;
-	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
-		buf->error = -EOVERFLOW;
-		return -EOVERFLOW;
-	}
-	dirent = buf->previous;
-	if (dirent) {
-		if (signal_pending(current))
-			return -EINTR;
-		if (__put_user(offset, &dirent->d_off))
-			goto efault;
-	}
-	dirent = buf->current_dir;
-	if (__put_user(d_ino, &dirent->d_ino))
-		goto efault;
-	if (__put_user(reclen, &dirent->d_reclen))
-		goto efault;
-	if (copy_to_user(dirent->d_name, name, namlen))
-		goto efault;
-	if (__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	if (__put_user(d_type, (char  __user *) dirent + reclen - 1))
-		goto efault;
-	buf->previous = dirent;
-	dirent = (void __user *)dirent + reclen;
-	buf->current_dir = dirent;
-	buf->count -= reclen;
-	return 0;
-efault:
-	buf->error = -EFAULT;
-	return -EFAULT;
-}
-
-COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
-		struct compat_linux_dirent __user *, dirent, unsigned int, count)
-{
-	struct fd f;
-	struct compat_linux_dirent __user * lastdirent;
-	struct compat_getdents_callback buf = {
-		.ctx.actor = compat_filldir,
-		.current_dir = dirent,
-		.count = count
-	};
-	int error;
-
-	if (!access_ok(VERIFY_WRITE, dirent, count))
-		return -EFAULT;
-
-	f = fdget_pos(fd);
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
-	if (error >= 0)
-		error = buf.error;
-	lastdirent = buf.previous;
-	if (lastdirent) {
-		if (put_user(buf.ctx.pos, &lastdirent->d_off))
-			error = -EFAULT;
-		else
-			error = count - buf.count;
-	}
-	fdput_pos(f);
-	return error;
-}
-
-#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64
-
-struct compat_getdents_callback64 {
-	struct dir_context ctx;
-	struct linux_dirent64 __user *current_dir;
-	struct linux_dirent64 __user *previous;
-	int count;
-	int error;
-};
-
-static int compat_filldir64(struct dir_context *ctx, const char *name,
-			    int namlen, loff_t offset, u64 ino,
-			    unsigned int d_type)
-{
-	struct linux_dirent64 __user *dirent;
-	struct compat_getdents_callback64 *buf =
-		container_of(ctx, struct compat_getdents_callback64, ctx);
-	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
-		sizeof(u64));
-	u64 off;
-
-	buf->error = -EINVAL;	/* only used if we fail.. */
-	if (reclen > buf->count)
-		return -EINVAL;
-	dirent = buf->previous;
-
-	if (dirent) {
-		if (signal_pending(current))
-			return -EINTR;
-		if (__put_user_unaligned(offset, &dirent->d_off))
-			goto efault;
-	}
-	dirent = buf->current_dir;
-	if (__put_user_unaligned(ino, &dirent->d_ino))
-		goto efault;
-	off = 0;
-	if (__put_user_unaligned(off, &dirent->d_off))
-		goto efault;
-	if (__put_user(reclen, &dirent->d_reclen))
-		goto efault;
-	if (__put_user(d_type, &dirent->d_type))
-		goto efault;
-	if (copy_to_user(dirent->d_name, name, namlen))
-		goto efault;
-	if (__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	buf->previous = dirent;
-	dirent = (void __user *)dirent + reclen;
-	buf->current_dir = dirent;
-	buf->count -= reclen;
-	return 0;
-efault:
-	buf->error = -EFAULT;
-	return -EFAULT;
-}
-
-COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd,
-		struct linux_dirent64 __user *, dirent, unsigned int, count)
-{
-	struct fd f;
-	struct linux_dirent64 __user * lastdirent;
-	struct compat_getdents_callback64 buf = {
-		.ctx.actor = compat_filldir64,
-		.current_dir = dirent,
-		.count = count
-	};
-	int error;
-
-	if (!access_ok(VERIFY_WRITE, dirent, count))
-		return -EFAULT;
-
-	f = fdget_pos(fd);
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
-	if (error >= 0)
-		error = buf.error;
-	lastdirent = buf.previous;
-	if (lastdirent) {
-		typeof(lastdirent->d_off) d_off = buf.ctx.pos;
-		if (__put_user_unaligned(d_off, &lastdirent->d_off))
-			error = -EFAULT;
-		else
-			error = count - buf.count;
-	}
-	fdput_pos(f);
-	return error;
-}
-#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */
-
-/*
- * Exactly like fs/open.c:sys_open(), except that it doesn't set the
- * O_LARGEFILE flag.
- */
-COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
-{
-	return do_sys_open(AT_FDCWD, filename, flags, mode);
-}
-
-/*
- * Exactly like fs/open.c:sys_openat(), except that it doesn't set the
- * O_LARGEFILE flag.
- */
-COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
-{
-	return do_sys_open(dfd, filename, flags, mode);
-}
-
-#define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
-
-static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
-				      int timeval, int ret)
-{
-	struct timespec ts;
-
-	if (!p)
-		return ret;
-
-	if (current->personality & STICKY_TIMEOUTS)
-		goto sticky;
-
-	/* No update for zero timeout */
-	if (!end_time->tv_sec && !end_time->tv_nsec)
-		return ret;
-
-	ktime_get_ts(&ts);
-	ts = timespec_sub(*end_time, ts);
-	if (ts.tv_sec < 0)
-		ts.tv_sec = ts.tv_nsec = 0;
-
-	if (timeval) {
-		struct compat_timeval rtv;
-
-		rtv.tv_sec = ts.tv_sec;
-		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-
-		if (!copy_to_user(p, &rtv, sizeof(rtv)))
-			return ret;
-	} else {
-		struct compat_timespec rts;
-
-		rts.tv_sec = ts.tv_sec;
-		rts.tv_nsec = ts.tv_nsec;
-
-		if (!copy_to_user(p, &rts, sizeof(rts)))
-			return ret;
-	}
-	/*
-	 * If an application puts its timeval in read-only memory, we
-	 * don't want the Linux-specific update to the timeval to
-	 * cause a fault after the select has completed
-	 * successfully. However, because we're not updating the
-	 * timeval, we can't restart the system call.
-	 */
-
-sticky:
-	if (ret == -ERESTARTNOHAND)
-		ret = -EINTR;
-	return ret;
-}
-
-/*
- * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
- * 64-bit unsigned longs.
- */
-static
-int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
-			unsigned long *fdset)
-{
-	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
-	if (ufdset) {
-		unsigned long odd;
-
-		if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t)))
-			return -EFAULT;
-
-		odd = nr & 1UL;
-		nr &= ~1UL;
-		while (nr) {
-			unsigned long h, l;
-			if (__get_user(l, ufdset) || __get_user(h, ufdset+1))
-				return -EFAULT;
-			ufdset += 2;
-			*fdset++ = h << 32 | l;
-			nr -= 2;
-		}
-		if (odd && __get_user(*fdset, ufdset))
-			return -EFAULT;
-	} else {
-		/* Tricky, must clear full unsigned long in the
-		 * kernel fdset at the end, this makes sure that
-		 * actually happens.
-		 */
-		memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t));
-	}
-	return 0;
-}
-
-static
-int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
-		      unsigned long *fdset)
-{
-	unsigned long odd;
-	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
-
-	if (!ufdset)
-		return 0;
-
-	odd = nr & 1UL;
-	nr &= ~1UL;
-	while (nr) {
-		unsigned long h, l;
-		l = *fdset++;
-		h = l >> 32;
-		if (__put_user(l, ufdset) || __put_user(h, ufdset+1))
-			return -EFAULT;
-		ufdset += 2;
-		nr -= 2;
-	}
-	if (odd && __put_user(*fdset, ufdset))
-		return -EFAULT;
-	return 0;
-}
-
-
-/*
- * This is a virtual copy of sys_select from fs/select.c and probably
- * should be compared to it from time to time
- */
-
-/*
- * We can actually return ERESTARTSYS instead of EINTR, but I'd
- * like to be certain this leads to no problems. So I return
- * EINTR just for safety.
- *
- * Update: ERESTARTSYS breaks at least the xview clock binary, so
- * I'm trying ERESTARTNOHAND which restart only when you want to.
- */
-int compat_core_sys_select(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-	struct timespec *end_time)
-{
-	fd_set_bits fds;
-	void *bits;
-	int size, max_fds, ret = -EINVAL;
-	struct fdtable *fdt;
-	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
-
-	if (n < 0)
-		goto out_nofds;
-
-	/* max_fds can increase, so grab it once to avoid race */
-	rcu_read_lock();
-	fdt = files_fdtable(current->files);
-	max_fds = fdt->max_fds;
-	rcu_read_unlock();
-	if (n > max_fds)
-		n = max_fds;
-
-	/*
-	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
-	 * since we used fdset we need to allocate memory in units of
-	 * long-words.
-	 */
-	size = FDS_BYTES(n);
-	bits = stack_fds;
-	if (size > sizeof(stack_fds) / 6) {
-		bits = kmalloc(6 * size, GFP_KERNEL);
-		ret = -ENOMEM;
-		if (!bits)
-			goto out_nofds;
-	}
-	fds.in      = (unsigned long *)  bits;
-	fds.out     = (unsigned long *) (bits +   size);
-	fds.ex      = (unsigned long *) (bits + 2*size);
-	fds.res_in  = (unsigned long *) (bits + 3*size);
-	fds.res_out = (unsigned long *) (bits + 4*size);
-	fds.res_ex  = (unsigned long *) (bits + 5*size);
-
-	if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
-	    (ret = compat_get_fd_set(n, outp, fds.out)) ||
-	    (ret = compat_get_fd_set(n, exp, fds.ex)))
-		goto out;
-	zero_fd_set(n, fds.res_in);
-	zero_fd_set(n, fds.res_out);
-	zero_fd_set(n, fds.res_ex);
-
-	ret = do_select(n, &fds, end_time);
-
-	if (ret < 0)
-		goto out;
-	if (!ret) {
-		ret = -ERESTARTNOHAND;
-		if (signal_pending(current))
-			goto out;
-		ret = 0;
-	}
-
-	if (compat_set_fd_set(n, inp, fds.res_in) ||
-	    compat_set_fd_set(n, outp, fds.res_out) ||
-	    compat_set_fd_set(n, exp, fds.res_ex))
-		ret = -EFAULT;
-out:
-	if (bits != stack_fds)
-		kfree(bits);
-out_nofds:
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
-	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
-	struct compat_timeval __user *, tvp)
-{
-	struct timespec end_time, *to = NULL;
-	struct compat_timeval tv;
-	int ret;
-
-	if (tvp) {
-		if (copy_from_user(&tv, tvp, sizeof(tv)))
-			return -EFAULT;
-
-		to = &end_time;
-		if (poll_select_set_timeout(to,
-				tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
-				(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
-			return -EINVAL;
-	}
-
-	ret = compat_core_sys_select(n, inp, outp, exp, to);
-	ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
-
-	return ret;
-}
-
-struct compat_sel_arg_struct {
-	compat_ulong_t n;
-	compat_uptr_t inp;
-	compat_uptr_t outp;
-	compat_uptr_t exp;
-	compat_uptr_t tvp;
-};
-
-COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
-{
-	struct compat_sel_arg_struct a;
-
-	if (copy_from_user(&a, arg, sizeof(a)))
-		return -EFAULT;
-	return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp),
-				 compat_ptr(a.exp), compat_ptr(a.tvp));
-}
-
-static long do_compat_pselect(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
-	compat_size_t sigsetsize)
-{
-	compat_sigset_t ss32;
-	sigset_t ksigmask, sigsaved;
-	struct compat_timespec ts;
-	struct timespec end_time, *to = NULL;
-	int ret;
-
-	if (tsp) {
-		if (copy_from_user(&ts, tsp, sizeof(ts)))
-			return -EFAULT;
-
-		to = &end_time;
-		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
-			return -EINVAL;
-	}
-
-	if (sigmask) {
-		if (sigsetsize != sizeof(compat_sigset_t))
-			return -EINVAL;
-		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
-			return -EFAULT;
-		sigset_from_compat(&ksigmask, &ss32);
-
-		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
-		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
-	}
-
-	ret = compat_core_sys_select(n, inp, outp, exp, to);
-	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
-
-	if (ret == -ERESTARTNOHAND) {
-		/*
-		 * Don't restore the signal mask yet. Let do_signal() deliver
-		 * the signal on the way back to userspace, before the signal
-		 * mask is restored.
-		 */
-		if (sigmask) {
-			memcpy(&current->saved_sigmask, &sigsaved,
-					sizeof(sigsaved));
-			set_restore_sigmask();
-		}
-	} else if (sigmask)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
-	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
-	struct compat_timespec __user *, tsp, void __user *, sig)
-{
-	compat_size_t sigsetsize = 0;
-	compat_uptr_t up = 0;
-
-	if (sig) {
-		if (!access_ok(VERIFY_READ, sig,
-				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
-		    	__get_user(up, (compat_uptr_t __user *)sig) ||
-		    	__get_user(sigsetsize,
-				(compat_size_t __user *)(sig+sizeof(up))))
-			return -EFAULT;
-	}
-	return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up),
-				 sigsetsize);
-}
-
-COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
-	unsigned int,  nfds, struct compat_timespec __user *, tsp,
-	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
-{
-	compat_sigset_t ss32;
-	sigset_t ksigmask, sigsaved;
-	struct compat_timespec ts;
-	struct timespec end_time, *to = NULL;
-	int ret;
-
-	if (tsp) {
-		if (copy_from_user(&ts, tsp, sizeof(ts)))
-			return -EFAULT;
-
-		to = &end_time;
-		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
-			return -EINVAL;
-	}
-
-	if (sigmask) {
-		if (sigsetsize != sizeof(compat_sigset_t))
-			return -EINVAL;
-		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
-			return -EFAULT;
-		sigset_from_compat(&ksigmask, &ss32);
-
-		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
-		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
-	}
-
-	ret = do_sys_poll(ufds, nfds, to);
-
-	/* We can restart this syscall, usually */
-	if (ret == -EINTR) {
-		/*
-		 * Don't restore the signal mask yet. Let do_signal() deliver
-		 * the signal on the way back to userspace, before the signal
-		 * mask is restored.
-		 */
-		if (sigmask) {
-			memcpy(&current->saved_sigmask, &sigsaved,
-				sizeof(sigsaved));
-			set_restore_sigmask();
-		}
-		ret = -ERESTARTNOHAND;
-	} else if (sigmask)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-
-	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
-
-	return ret;
-}
-
-#ifdef CONFIG_FHANDLE
-/*
- * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
- * doesn't set the O_LARGEFILE flag.
- */
-COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
-			     struct file_handle __user *, handle, int, flags)
-{
-	return do_handle_open(mountdirfd, handle, flags);
-}
-#endif
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 02a7a9286449..6d6eca394d4d 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -327,7 +327,6 @@ EXPORT_SYMBOL(fscrypt_decrypt_page);
 static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *dir;
-	struct fscrypt_info *ci;
 	int dir_has_key, cached_with_key;
 
 	if (flags & LOOKUP_RCU)
@@ -339,18 +338,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 		return 0;
 	}
 
-	ci = d_inode(dir)->i_crypt_info;
-	if (ci && ci->ci_keyring_key &&
-	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					  (1 << KEY_FLAG_REVOKED) |
-					  (1 << KEY_FLAG_DEAD))))
-		ci = NULL;
-
 	/* this should eventually be an flag in d_flags */
 	spin_lock(&dentry->d_lock);
 	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
 	spin_unlock(&dentry->d_lock);
-	dir_has_key = (ci != NULL);
+	dir_has_key = (d_inode(dir)->i_crypt_info != NULL);
 	dput(dir);
 
 	/*
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 13052b85c393..37b49894c762 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -350,7 +350,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = fscrypt_get_crypt_info(dir);
+	ret = fscrypt_get_encryption_info(dir);
 	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index fdbb8af32eaf..e39696e64494 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -67,7 +67,6 @@ struct fscrypt_info {
 	u8 ci_filename_mode;
 	u8 ci_flags;
 	struct crypto_skcipher *ci_ctfm;
-	struct key *ci_keyring_key;
 	u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
 };
 
@@ -101,7 +100,4 @@ extern int fscrypt_do_page_crypto(const struct inode *inode,
 extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
 					      gfp_t gfp_flags);
 
-/* keyinfo.c */
-extern int fscrypt_get_crypt_info(struct inode *);
-
 #endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index d5d896fa5a71..8cdfddce2b34 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -95,6 +95,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
 	kfree(description);
 	if (IS_ERR(keyring_key))
 		return PTR_ERR(keyring_key);
+	down_read(&keyring_key->sem);
 
 	if (keyring_key->type != &key_type_logon) {
 		printk_once(KERN_WARNING
@@ -102,11 +103,9 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
 		res = -ENOKEY;
 		goto out;
 	}
-	down_read(&keyring_key->sem);
 	ukp = user_key_payload_locked(keyring_key);
 	if (ukp->datalen != sizeof(struct fscrypt_key)) {
 		res = -EINVAL;
-		up_read(&keyring_key->sem);
 		goto out;
 	}
 	master_key = (struct fscrypt_key *)ukp->data;
@@ -117,17 +116,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
 				"%s: key size incorrect: %d\n",
 				__func__, master_key->size);
 		res = -ENOKEY;
-		up_read(&keyring_key->sem);
 		goto out;
 	}
 	res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
-	up_read(&keyring_key->sem);
-	if (res)
-		goto out;
-
-	crypt_info->ci_keyring_key = keyring_key;
-	return 0;
 out:
+	up_read(&keyring_key->sem);
 	key_put(keyring_key);
 	return res;
 }
@@ -169,12 +162,11 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	if (!ci)
 		return;
 
-	key_put(ci->ci_keyring_key);
 	crypto_free_skcipher(ci->ci_ctfm);
 	kmem_cache_free(fscrypt_info_cachep, ci);
 }
 
-int fscrypt_get_crypt_info(struct inode *inode)
+int fscrypt_get_encryption_info(struct inode *inode)
 {
 	struct fscrypt_info *crypt_info;
 	struct fscrypt_context ctx;
@@ -184,21 +176,15 @@ int fscrypt_get_crypt_info(struct inode *inode)
 	u8 *raw_key = NULL;
 	int res;
 
+	if (inode->i_crypt_info)
+		return 0;
+
 	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
 	if (res)
 		return res;
 
 	if (!inode->i_sb->s_cop->get_context)
 		return -EOPNOTSUPP;
-retry:
-	crypt_info = ACCESS_ONCE(inode->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-				key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		fscrypt_put_encryption_info(inode, crypt_info);
-		goto retry;
-	}
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
@@ -229,7 +215,6 @@ retry:
 	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
 	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
 	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
 	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
 				sizeof(crypt_info->ci_master_key));
 
@@ -273,14 +258,8 @@ retry:
 	if (res)
 		goto out;
 
-	kzfree(raw_key);
-	raw_key = NULL;
-	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
-		put_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
-
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
+		crypt_info = NULL;
 out:
 	if (res == -ENOKEY)
 		res = 0;
@@ -288,6 +267,7 @@ out:
 	kzfree(raw_key);
 	return res;
 }
+EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
 void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
 {
@@ -305,17 +285,3 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
 	put_crypt_info(ci);
 }
 EXPORT_SYMBOL(fscrypt_put_encryption_info);
-
-int fscrypt_get_encryption_info(struct inode *inode)
-{
-	struct fscrypt_info *ci = inode->i_crypt_info;
-
-	if (!ci ||
-		(ci->ci_keyring_key &&
-		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					       (1 << KEY_FLAG_REVOKED) |
-					       (1 << KEY_FLAG_DEAD)))))
-		return fscrypt_get_crypt_info(inode);
-	return 0;
-}
-EXPORT_SYMBOL(fscrypt_get_encryption_info);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 14b76da71269..4908906d54d5 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -33,17 +33,10 @@ static int create_encryption_context_from_policy(struct inode *inode,
 				const struct fscrypt_policy *policy)
 {
 	struct fscrypt_context ctx;
-	int res;
 
 	if (!inode->i_sb->s_cop->set_context)
 		return -EOPNOTSUPP;
 
-	if (inode->i_sb->s_cop->prepare_context) {
-		res = inode->i_sb->s_cop->prepare_context(inode);
-		if (res)
-			return res;
-	}
-
 	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
 	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
 					FS_KEY_DESCRIPTOR_SIZE);
diff --git a/fs/dax.c b/fs/dax.c
index de622d4282a6..6433650be833 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -373,6 +373,22 @@ restart:
 		}
 		spin_lock_irq(&mapping->tree_lock);
 
+		if (!entry) {
+			/*
+			 * We needed to drop the page_tree lock while calling
+			 * radix_tree_preload() and we didn't have an entry to
+			 * lock.  See if another thread inserted an entry at
+			 * our index during this time.
+			 */
+			entry = __radix_tree_lookup(&mapping->page_tree, index,
+					NULL, &slot);
+			if (entry) {
+				radix_tree_preload_end();
+				spin_unlock_irq(&mapping->tree_lock);
+				goto restart;
+			}
+		}
+
 		if (pmd_downgrade) {
 			radix_tree_delete(&mapping->page_tree, index);
 			mapping->nrexceptional--;
@@ -388,19 +404,12 @@ restart:
 		if (err) {
 			spin_unlock_irq(&mapping->tree_lock);
 			/*
-			 * Someone already created the entry?  This is a
-			 * normal failure when inserting PMDs in a range
-			 * that already contains PTEs.  In that case we want
-			 * to return -EEXIST immediately.
-			 */
-			if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD))
-				goto restart;
-			/*
-			 * Our insertion of a DAX PMD entry failed, most
-			 * likely because it collided with a PTE sized entry
-			 * at a different index in the PMD range.  We haven't
-			 * inserted anything into the radix tree and have no
-			 * waiters to wake.
+			 * Our insertion of a DAX entry failed, most likely
+			 * because we were inserting a PMD entry and it
+			 * collided with a PTE sized entry at a different
+			 * index in the PMD range.  We haven't inserted
+			 * anything into the radix tree and have no waiters to
+			 * wake.
 			 */
 			return ERR_PTR(err);
 		}
@@ -982,7 +991,7 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
 		sector_t start_sector = dax.sector + (offset >> 9);
 
 		return blkdev_issue_zeroout(bdev, start_sector,
-				length >> 9, GFP_NOFS, true);
+				length >> 9, GFP_NOFS, 0);
 	} else {
 		if (dax_map_atomic(bdev, &dax) < 0)
 			return PTR_ERR(dax.addr);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 7d398d300e97..9382db998ec9 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con)
 	newsock->type = con->sock->type;
 	newsock->ops = con->sock->ops;
 
-	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
+	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true);
 	if (result < 0)
 		goto accept_err;
 
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 95c1c8d34539..9c351bf757b2 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -349,7 +349,6 @@ struct ecryptfs_mount_crypt_stat {
 struct ecryptfs_sb_info {
 	struct super_block *wsi_sb;
 	struct ecryptfs_mount_crypt_stat mount_crypt_stat;
-	struct backing_dev_info bdi;
 };
 
 /* file private data. */
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 151872dcc1f4..9014479d0160 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -519,12 +519,11 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
+	rc = super_setup_bdi(s);
 	if (rc)
 		goto out1;
 
 	ecryptfs_set_superblock_private(s, sbi);
-	s->s_bdi = &sbi->bdi;
 
 	/* ->kill_sb() will take care of sbi after that point */
 	sbi = NULL;
@@ -633,7 +632,6 @@ static void ecryptfs_kill_block_super(struct super_block *sb)
 	if (!sb_info)
 		return;
 	ecryptfs_destroy_mount_crypt_stat(&sb_info->mount_crypt_stat);
-	bdi_destroy(&sb_info->bdi);
 	kmem_cache_free(ecryptfs_sb_info_cache, sb_info);
 }
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 341251421ced..5420767c9b68 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -42,6 +42,7 @@
 #include <linux/seq_file.h>
 #include <linux/compat.h>
 #include <linux/rculist.h>
+#include <net/busy_poll.h>
 
 /*
  * LOCKING:
@@ -224,6 +225,11 @@ struct eventpoll {
 	/* used to optimize loop detection check */
 	int visited;
 	struct list_head visited_list_link;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* used to track busy poll napi_id */
+	unsigned int napi_id;
+#endif
 };
 
 /* Wait structure used by the poll hooks */
@@ -384,6 +390,77 @@ static inline int ep_events_available(struct eventpoll *ep)
 	return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
 }
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static bool ep_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct eventpoll *ep = p;
+
+	return ep_events_available(ep) || busy_loop_timeout(start_time);
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/*
+ * Busy poll if globally on and supporting sockets found && no events,
+ * busy loop will return if need_resched or ep_events_available.
+ *
+ * we must do our busy polling with irqs enabled
+ */
+static void ep_busy_loop(struct eventpoll *ep, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
+#endif
+}
+
+static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (ep->napi_id)
+		ep->napi_id = 0;
+#endif
+}
+
+/*
+ * Set epoll busy poll NAPI ID from sk.
+ */
+static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct eventpoll *ep;
+	unsigned int napi_id;
+	struct socket *sock;
+	struct sock *sk;
+	int err;
+
+	if (!net_busy_loop_on())
+		return;
+
+	sock = sock_from_file(epi->ffd.file, &err);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+	ep = epi->ep;
+
+	/* Non-NAPI IDs can be rejected
+	 *	or
+	 * Nothing to do if we already have this ID
+	 */
+	if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
+		return;
+
+	/* record NAPI ID for use in next busy poll */
+	ep->napi_id = napi_id;
+#endif
+}
+
 /**
  * ep_call_nested - Perform a bound (possibly) nested call, by checking
  *                  that the recursion limit is not exceeded, and that
@@ -1022,6 +1099,8 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 
 	spin_lock_irqsave(&ep->lock, flags);
 
+	ep_set_busy_poll_napi_id(epi);
+
 	/*
 	 * If the event mask does not contain any poll(2) event, we consider the
 	 * descriptor to be disabled. This condition is likely the effect of the
@@ -1363,6 +1442,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	/* We have to drop the new item inside our item list to keep track of it */
 	spin_lock_irqsave(&ep->lock, flags);
 
+	/* record NAPI ID of new item if present */
+	ep_set_busy_poll_napi_id(epi);
+
 	/* If the file is already "ready" we drop it inside the ready list */
 	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1637,10 +1719,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	}
 
 fetch_events:
+
+	if (!ep_events_available(ep))
+		ep_busy_loop(ep, timed_out);
+
 	spin_lock_irqsave(&ep->lock, flags);
 
 	if (!ep_events_available(ep)) {
 		/*
+		 * Busy poll timed out.  Drop NAPI ID for now, we can add
+		 * it back in when we have moved a socket with a valid NAPI
+		 * ID onto the ready list.
+		 */
+		ep_reset_busy_poll_napi_id(ep);
+
+		/*
 		 * We don't have any available event to return to the caller.
 		 * We need to sleep here, and we will be wake up by
 		 * ep_poll_callback() when events will become available.
diff --git a/fs/exec.c b/fs/exec.c
index 65145a3df065..72934df68471 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1320,6 +1320,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	else
 		set_dumpable(current->mm, suid_dumpable);
 
+	arch_setup_new_exec();
 	perf_event_exec();
 	__set_task_comm(current, kbasename(bprm->filename), true);
 
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 2e86086bc940..5dc392404559 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -64,7 +64,6 @@ struct exofs_dev {
  * our extension to the in-memory superblock
  */
 struct exofs_sb_info {
-	struct backing_dev_info bdi;		/* register our bdi with VFS  */
 	struct exofs_sb_stats s_ess;		/* Written often, pre-allocate*/
 	int		s_timeout;		/* timeout for OSD operations */
 	uint64_t	s_nextid;		/* highest object ID used     */
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 1076a4233b39..819624cfc8da 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -464,7 +464,6 @@ static void exofs_put_super(struct super_block *sb)
 			    sbi->one_comp.obj.partition);
 
 	exofs_sysfs_sb_del(sbi);
-	bdi_destroy(&sbi->bdi);
 	exofs_free_sbi(sbi);
 	sb->s_fs_info = NULL;
 }
@@ -809,8 +808,12 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 	__sbi_read_stats(sbi);
 
 	/* set up operation vectors */
-	sbi->bdi.ra_pages = __ra_pages(&sbi->layout);
-	sb->s_bdi = &sbi->bdi;
+	ret = super_setup_bdi(sb);
+	if (ret) {
+		EXOFS_DBGMSG("Failed to super_setup_bdi\n");
+		goto free_sbi;
+	}
+	sb->s_bdi->ra_pages = __ra_pages(&sbi->layout);
 	sb->s_fs_info = sbi;
 	sb->s_op = &exofs_sops;
 	sb->s_export_op = &exofs_export_ops;
@@ -836,14 +839,6 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	ret = bdi_setup_and_register(&sbi->bdi, "exofs");
-	if (ret) {
-		EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
-		dput(sb->s_root);
-		sb->s_root = NULL;
-		goto free_sbi;
-	}
-
 	exofs_sysfs_dbg_print();
 	_exofs_print_device("Mounting", opts->dev_name,
 			    ore_comp_dev(&sbi->oc, 0),
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f493af666591..fb69ee2388db 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2466,6 +2466,7 @@ extern int  ext4_setattr(struct dentry *, struct iattr *);
 extern int  ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern void ext4_evict_inode(struct inode *);
 extern void ext4_clear_inode(struct inode *);
+extern int  ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8210c1f43556..cefa9835f275 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -744,7 +744,7 @@ const struct file_operations ext4_file_operations = {
 
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
-	.getattr	= ext4_getattr,
+	.getattr	= ext4_file_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 30a9f210d1e3..375fb1c05d49 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1169,10 +1169,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	set_buffer_uptodate(dir_block);
 	err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
 	if (err)
-		goto out;
+		return err;
 	set_buffer_verified(dir_block);
-out:
-	return err;
+	return ext4_mark_inode_dirty(handle, inode);
 }
 
 static int ext4_convert_inline_data_nolock(handle_t *handle,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7385e6a6b6cb..b9ffa9f4191f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5390,17 +5390,52 @@ err_out:
 int ext4_getattr(const struct path *path, struct kstat *stat,
 		 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode;
-	unsigned long long delalloc_blocks;
+	struct inode *inode = d_inode(path->dentry);
+	struct ext4_inode *raw_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int flags;
+
+	if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+		stat->result_mask |= STATX_BTIME;
+		stat->btime.tv_sec = ei->i_crtime.tv_sec;
+		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
+	}
+
+	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+	if (flags & EXT4_APPEND_FL)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (flags & EXT4_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (flags & EXT4_ENCRYPT_FL)
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	if (flags & EXT4_IMMUTABLE_FL)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (flags & EXT4_NODUMP_FL)
+		stat->attributes |= STATX_ATTR_NODUMP;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_ENCRYPTED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
 
-	inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
+	return 0;
+}
+
+int ext4_file_getattr(const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	u64 delalloc_blocks;
+
+	ext4_getattr(path, stat, request_mask, query_flags);
 
 	/*
 	 * If there is inline data in the inode, the inode will normally not
 	 * have data blocks allocated (it may have an external xattr block).
 	 * Report at least one sector for such files, so tools like tar, rsync,
-	 * others doen't incorrectly think the file is completely sparse.
+	 * others don't incorrectly think the file is completely sparse.
 	 */
 	if (unlikely(ext4_has_inline_data(inode)))
 		stat->blocks += (stat->size + 511) >> 9;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 578f8c33fb44..c992ef2c2f94 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -511,7 +511,7 @@ mext_check_arguments(struct inode *orig_inode,
 	if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
 	    (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
 		ext4_debug("ext4 move extent: orig and donor's start "
-			"offset are not alligned [ino:orig %lu, donor %lu]\n",
+			"offsets are not aligned [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 6ad612c576fc..07e5e1405771 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3912,6 +3912,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.tmpfile	= ext4_tmpfile,
 	.rename		= ext4_rename2,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
@@ -3920,6 +3921,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 
 const struct inode_operations ext4_special_inode_operations = {
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2e03a0a88d92..a9448db1cf7e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1120,17 +1120,16 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
 				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
 }
 
-static int ext4_prepare_context(struct inode *inode)
-{
-	return ext4_convert_inline_data(inode);
-}
-
 static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 							void *fs_data)
 {
 	handle_t *handle = fs_data;
 	int res, res2, retries = 0;
 
+	res = ext4_convert_inline_data(inode);
+	if (res)
+		return res;
+
 	/*
 	 * If a journal handle was specified, then the encryption context is
 	 * being set on a new inode via inheritance and is part of a larger
@@ -1196,7 +1195,6 @@ static unsigned ext4_max_namelen(struct inode *inode)
 static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
-	.prepare_context	= ext4_prepare_context,
 	.set_context		= ext4_set_context,
 	.dummy_context		= ext4_dummy_context,
 	.is_encrypted		= ext4_encrypted_inode,
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 73b184d161fc..5c8fc53cb0e5 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -85,17 +85,20 @@ errout:
 const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 	.get_link	= ext4_encrypted_get_link,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 };
 
 const struct inode_operations ext4_symlink_inode_operations = {
 	.get_link	= page_get_link,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 };
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.get_link	= simple_get_link,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 };
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 67636acf7624..996e7900d4c8 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -131,31 +131,26 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 }
 
 static int ext4_xattr_block_csum_verify(struct inode *inode,
-					sector_t block_nr,
-					struct ext4_xattr_header *hdr)
+					struct buffer_head *bh)
 {
-	if (ext4_has_metadata_csum(inode->i_sb) &&
-	    (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
-		return 0;
-	return 1;
-}
-
-static void ext4_xattr_block_csum_set(struct inode *inode,
-				      sector_t block_nr,
-				      struct ext4_xattr_header *hdr)
-{
-	if (!ext4_has_metadata_csum(inode->i_sb))
-		return;
+	struct ext4_xattr_header *hdr = BHDR(bh);
+	int ret = 1;
 
-	hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
+	if (ext4_has_metadata_csum(inode->i_sb)) {
+		lock_buffer(bh);
+		ret = (hdr->h_checksum == ext4_xattr_block_csum(inode,
+							bh->b_blocknr, hdr));
+		unlock_buffer(bh);
+	}
+	return ret;
 }
 
-static inline int ext4_handle_dirty_xattr_block(handle_t *handle,
-						struct inode *inode,
-						struct buffer_head *bh)
+static void ext4_xattr_block_csum_set(struct inode *inode,
+				      struct buffer_head *bh)
 {
-	ext4_xattr_block_csum_set(inode, bh->b_blocknr, BHDR(bh));
-	return ext4_handle_dirty_metadata(handle, inode, bh);
+	if (ext4_has_metadata_csum(inode->i_sb))
+		BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode,
+						bh->b_blocknr, BHDR(bh));
 }
 
 static inline const struct xattr_handler *
@@ -233,7 +228,7 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1))
 		return -EFSCORRUPTED;
-	if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
+	if (!ext4_xattr_block_csum_verify(inode, bh))
 		return -EFSBADCRC;
 	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
 				       bh->b_data);
@@ -618,23 +613,22 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 			}
 		}
 
+		ext4_xattr_block_csum_set(inode, bh);
 		/*
 		 * Beware of this ugliness: Releasing of xattr block references
 		 * from different inodes can race and so we have to protect
 		 * from a race where someone else frees the block (and releases
 		 * its journal_head) before we are done dirtying the buffer. In
 		 * nojournal mode this race is harmless and we actually cannot
-		 * call ext4_handle_dirty_xattr_block() with locked buffer as
+		 * call ext4_handle_dirty_metadata() with locked buffer as
 		 * that function can call sync_dirty_buffer() so for that case
 		 * we handle the dirtying after unlocking the buffer.
 		 */
 		if (ext4_handle_valid(handle))
-			error = ext4_handle_dirty_xattr_block(handle, inode,
-							      bh);
+			error = ext4_handle_dirty_metadata(handle, inode, bh);
 		unlock_buffer(bh);
 		if (!ext4_handle_valid(handle))
-			error = ext4_handle_dirty_xattr_block(handle, inode,
-							      bh);
+			error = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 		dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -863,13 +857,14 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 				ext4_xattr_cache_insert(ext4_mb_cache,
 					bs->bh);
 			}
+			ext4_xattr_block_csum_set(inode, bs->bh);
 			unlock_buffer(bs->bh);
 			if (error == -EFSCORRUPTED)
 				goto bad_block;
 			if (!error)
-				error = ext4_handle_dirty_xattr_block(handle,
-								      inode,
-								      bs->bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   bs->bh);
 			if (error)
 				goto cleanup;
 			goto inserted;
@@ -967,10 +962,11 @@ inserted:
 					ce->e_reusable = 0;
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					  ref);
+				ext4_xattr_block_csum_set(inode, new_bh);
 				unlock_buffer(new_bh);
-				error = ext4_handle_dirty_xattr_block(handle,
-								      inode,
-								      new_bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   new_bh);
 				if (error)
 					goto cleanup_dquot;
 			}
@@ -1020,11 +1016,12 @@ getblk_failed:
 				goto getblk_failed;
 			}
 			memcpy(new_bh->b_data, s->base, new_bh->b_size);
+			ext4_xattr_block_csum_set(inode, new_bh);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
 			ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
-			error = ext4_handle_dirty_xattr_block(handle,
-							      inode, new_bh);
+			error = ext4_handle_dirty_metadata(handle, inode,
+							   new_bh);
 			if (error)
 				goto cleanup;
 		}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index a77df377e2e8..ee2d0a485fc3 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -196,6 +196,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
 	si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
 	si->base_mem += NM_I(sbi)->nat_blocks / 8;
+	si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
 
 get_cache:
 	si->cache_mem = 0;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4650c9b85de7..8d5c62b07b28 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -750,7 +750,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	dentry_blk = page_address(page);
 	bit_pos = dentry - dentry_blk->dentry;
 	for (i = 0; i < slots; i++)
-		clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+		__clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
 
 	/* Let's check and deallocate this dentry page */
 	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e849f83d6114..0a6e115562f6 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -561,6 +561,8 @@ struct f2fs_nm_info {
 	struct mutex build_lock;	/* lock for build free nids */
 	unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE];
 	unsigned char *nat_block_bitmap;
+	unsigned short *free_nid_count;	/* free nid count of NAT block */
+	spinlock_t free_nid_lock;	/* protect updating of nid count */
 
 	/* for checkpoint */
 	char *nat_bitmap;		/* NAT bitmap pointer */
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 94967171dee8..481aa8dc79f4 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -338,9 +338,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 		set_nat_flag(e, IS_CHECKPOINTED, false);
 	__set_nat_cache_dirty(nm_i, e);
 
-	if (enabled_nat_bits(sbi, NULL) && new_blkaddr == NEW_ADDR)
-		clear_bit_le(NAT_BLOCK_OFFSET(ni->nid), nm_i->empty_nat_bits);
-
 	/* update fsync_mark if its inode nat entry is still alive */
 	if (ni->nid != ni->ino)
 		e = __lookup_nat_cache(nm_i, ni->ino);
@@ -1823,7 +1820,8 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
 		kmem_cache_free(free_nid_slab, i);
 }
 
-void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set)
+static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
+			bool set, bool build, bool locked)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid);
@@ -1833,9 +1831,18 @@ void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set)
 		return;
 
 	if (set)
-		set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+		__set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
 	else
-		clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+		__clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+
+	if (!locked)
+		spin_lock(&nm_i->free_nid_lock);
+	if (set)
+		nm_i->free_nid_count[nat_ofs]++;
+	else if (!build)
+		nm_i->free_nid_count[nat_ofs]--;
+	if (!locked)
+		spin_unlock(&nm_i->free_nid_lock);
 }
 
 static void scan_nat_page(struct f2fs_sb_info *sbi,
@@ -1847,7 +1854,10 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 	unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid);
 	int i;
 
-	set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
+	if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+		return;
+
+	__set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
 
 	i = start_nid % NAT_ENTRY_PER_BLOCK;
 
@@ -1861,7 +1871,7 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 		f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
 		if (blk_addr == NULL_ADDR)
 			freed = add_free_nid(sbi, start_nid, true);
-		update_free_nid_bitmap(sbi, start_nid, freed);
+		update_free_nid_bitmap(sbi, start_nid, freed, true, false);
 	}
 }
 
@@ -1877,6 +1887,8 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
 	for (i = 0; i < nm_i->nat_blocks; i++) {
 		if (!test_bit_le(i, nm_i->nat_block_bitmap))
 			continue;
+		if (!nm_i->free_nid_count[i])
+			continue;
 		for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
 			nid_t nid;
 
@@ -1907,58 +1919,6 @@ out:
 	up_read(&nm_i->nat_tree_lock);
 }
 
-static int scan_nat_bits(struct f2fs_sb_info *sbi)
-{
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	struct page *page;
-	unsigned int i = 0;
-	nid_t nid;
-
-	if (!enabled_nat_bits(sbi, NULL))
-		return -EAGAIN;
-
-	down_read(&nm_i->nat_tree_lock);
-check_empty:
-	i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
-	if (i >= nm_i->nat_blocks) {
-		i = 0;
-		goto check_partial;
-	}
-
-	for (nid = i * NAT_ENTRY_PER_BLOCK; nid < (i + 1) * NAT_ENTRY_PER_BLOCK;
-									nid++) {
-		if (unlikely(nid >= nm_i->max_nid))
-			break;
-		add_free_nid(sbi, nid, true);
-	}
-
-	if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
-		goto out;
-	i++;
-	goto check_empty;
-
-check_partial:
-	i = find_next_zero_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
-	if (i >= nm_i->nat_blocks) {
-		disable_nat_bits(sbi, true);
-		up_read(&nm_i->nat_tree_lock);
-		return -EINVAL;
-	}
-
-	nid = i * NAT_ENTRY_PER_BLOCK;
-	page = get_current_nat_page(sbi, nid);
-	scan_nat_page(sbi, page, nid);
-	f2fs_put_page(page, 1);
-
-	if (nm_i->nid_cnt[FREE_NID_LIST] < MAX_FREE_NIDS) {
-		i++;
-		goto check_partial;
-	}
-out:
-	up_read(&nm_i->nat_tree_lock);
-	return 0;
-}
-
 static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -1980,21 +1940,6 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 
 		if (nm_i->nid_cnt[FREE_NID_LIST])
 			return;
-
-		/* try to find free nids with nat_bits */
-		if (!scan_nat_bits(sbi) && nm_i->nid_cnt[FREE_NID_LIST])
-			return;
-	}
-
-	/* find next valid candidate */
-	if (enabled_nat_bits(sbi, NULL)) {
-		int idx = find_next_zero_bit_le(nm_i->full_nat_bits,
-					nm_i->nat_blocks, 0);
-
-		if (idx >= nm_i->nat_blocks)
-			set_sbi_flag(sbi, SBI_NEED_FSCK);
-		else
-			nid = idx * NAT_ENTRY_PER_BLOCK;
 	}
 
 	/* readahead nat pages to be scanned */
@@ -2081,7 +2026,7 @@ retry:
 		__insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
 		nm_i->available_nids--;
 
-		update_free_nid_bitmap(sbi, *nid, false);
+		update_free_nid_bitmap(sbi, *nid, false, false, false);
 
 		spin_unlock(&nm_i->nid_list_lock);
 		return true;
@@ -2137,7 +2082,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 
 	nm_i->available_nids++;
 
-	update_free_nid_bitmap(sbi, nid, true);
+	update_free_nid_bitmap(sbi, nid, true, false, false);
 
 	spin_unlock(&nm_i->nid_list_lock);
 
@@ -2383,7 +2328,7 @@ add_out:
 	list_add_tail(&nes->set_list, head);
 }
 
-void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 						struct page *page)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -2402,16 +2347,16 @@ void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 			valid++;
 	}
 	if (valid == 0) {
-		set_bit_le(nat_index, nm_i->empty_nat_bits);
-		clear_bit_le(nat_index, nm_i->full_nat_bits);
+		__set_bit_le(nat_index, nm_i->empty_nat_bits);
+		__clear_bit_le(nat_index, nm_i->full_nat_bits);
 		return;
 	}
 
-	clear_bit_le(nat_index, nm_i->empty_nat_bits);
+	__clear_bit_le(nat_index, nm_i->empty_nat_bits);
 	if (valid == NAT_ENTRY_PER_BLOCK)
-		set_bit_le(nat_index, nm_i->full_nat_bits);
+		__set_bit_le(nat_index, nm_i->full_nat_bits);
 	else
-		clear_bit_le(nat_index, nm_i->full_nat_bits);
+		__clear_bit_le(nat_index, nm_i->full_nat_bits);
 }
 
 static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
@@ -2467,11 +2412,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 			add_free_nid(sbi, nid, false);
 			spin_lock(&NM_I(sbi)->nid_list_lock);
 			NM_I(sbi)->available_nids++;
-			update_free_nid_bitmap(sbi, nid, true);
+			update_free_nid_bitmap(sbi, nid, true, false, false);
 			spin_unlock(&NM_I(sbi)->nid_list_lock);
 		} else {
 			spin_lock(&NM_I(sbi)->nid_list_lock);
-			update_free_nid_bitmap(sbi, nid, false);
+			update_free_nid_bitmap(sbi, nid, false, false, false);
 			spin_unlock(&NM_I(sbi)->nid_list_lock);
 		}
 	}
@@ -2577,6 +2522,40 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 	return 0;
 }
 
+inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int i = 0;
+	nid_t nid, last_nid;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return;
+
+	for (i = 0; i < nm_i->nat_blocks; i++) {
+		i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
+		if (i >= nm_i->nat_blocks)
+			break;
+
+		__set_bit_le(i, nm_i->nat_block_bitmap);
+
+		nid = i * NAT_ENTRY_PER_BLOCK;
+		last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
+
+		spin_lock(&nm_i->free_nid_lock);
+		for (; nid < last_nid; nid++)
+			update_free_nid_bitmap(sbi, nid, true, true, true);
+		spin_unlock(&nm_i->free_nid_lock);
+	}
+
+	for (i = 0; i < nm_i->nat_blocks; i++) {
+		i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
+		if (i >= nm_i->nat_blocks)
+			break;
+
+		__set_bit_le(i, nm_i->nat_block_bitmap);
+	}
+}
+
 static int init_node_manager(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
@@ -2638,7 +2617,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	return 0;
 }
 
-int init_free_nid_cache(struct f2fs_sb_info *sbi)
+static int init_free_nid_cache(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
@@ -2651,6 +2630,14 @@ int init_free_nid_cache(struct f2fs_sb_info *sbi)
 								GFP_KERNEL);
 	if (!nm_i->nat_block_bitmap)
 		return -ENOMEM;
+
+	nm_i->free_nid_count = f2fs_kvzalloc(nm_i->nat_blocks *
+					sizeof(unsigned short), GFP_KERNEL);
+	if (!nm_i->free_nid_count)
+		return -ENOMEM;
+
+	spin_lock_init(&nm_i->free_nid_lock);
+
 	return 0;
 }
 
@@ -2670,6 +2657,9 @@ int build_node_manager(struct f2fs_sb_info *sbi)
 	if (err)
 		return err;
 
+	/* load free nid status from nat_bits table */
+	load_free_nid_bitmap(sbi);
+
 	build_free_nids(sbi, true, true);
 	return 0;
 }
@@ -2730,6 +2720,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 
 	kvfree(nm_i->nat_block_bitmap);
 	kvfree(nm_i->free_nid_bitmap);
+	kvfree(nm_i->free_nid_count);
 
 	kfree(nm_i->nat_bitmap);
 	kfree(nm_i->nat_bits);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4bd7a8b19332..29ef7088c558 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1163,6 +1163,12 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 		if (f2fs_discard_en(sbi) &&
 			!f2fs_test_and_set_bit(offset, se->discard_map))
 			sbi->discard_blks--;
+
+		/* don't overwrite by SSR to keep node chain */
+		if (se->type == CURSEG_WARM_NODE) {
+			if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+				se->ckpt_valid_blocks++;
+		}
 	} else {
 		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) {
 #ifdef CONFIG_F2FS_CHECK_FS
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 338d2f73eb29..a2c05f2ada6d 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1359,6 +1359,16 @@ out:
 	return 0;
 }
 
+static void fat_dummy_inode_init(struct inode *inode)
+{
+	/* Initialize this dummy inode to work as no-op. */
+	MSDOS_I(inode)->mmu_private = 0;
+	MSDOS_I(inode)->i_start = 0;
+	MSDOS_I(inode)->i_logstart = 0;
+	MSDOS_I(inode)->i_attrs = 0;
+	MSDOS_I(inode)->i_pos = 0;
+}
+
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	MSDOS_I(fat_inode)->i_pos = 0;
+	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
+	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index be8fbe289087..8bd81c2e89b2 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -23,6 +23,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/shmem_fs.h>
+#include <linux/compat.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -420,6 +421,162 @@ out:
 }
 #endif
 
+#ifdef CONFIG_COMPAT
+static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
+{
+	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
+	    __get_user(kfl->l_type, &ufl->l_type) ||
+	    __get_user(kfl->l_whence, &ufl->l_whence) ||
+	    __get_user(kfl->l_start, &ufl->l_start) ||
+	    __get_user(kfl->l_len, &ufl->l_len) ||
+	    __get_user(kfl->l_pid, &ufl->l_pid))
+		return -EFAULT;
+	return 0;
+}
+
+static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
+{
+	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
+	    __put_user(kfl->l_type, &ufl->l_type) ||
+	    __put_user(kfl->l_whence, &ufl->l_whence) ||
+	    __put_user(kfl->l_start, &ufl->l_start) ||
+	    __put_user(kfl->l_len, &ufl->l_len) ||
+	    __put_user(kfl->l_pid, &ufl->l_pid))
+		return -EFAULT;
+	return 0;
+}
+
+#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64
+static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
+{
+	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
+	    __get_user(kfl->l_type, &ufl->l_type) ||
+	    __get_user(kfl->l_whence, &ufl->l_whence) ||
+	    __get_user(kfl->l_start, &ufl->l_start) ||
+	    __get_user(kfl->l_len, &ufl->l_len) ||
+	    __get_user(kfl->l_pid, &ufl->l_pid))
+		return -EFAULT;
+	return 0;
+}
+#endif
+
+#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64
+static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
+{
+	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
+	    __put_user(kfl->l_type, &ufl->l_type) ||
+	    __put_user(kfl->l_whence, &ufl->l_whence) ||
+	    __put_user(kfl->l_start, &ufl->l_start) ||
+	    __put_user(kfl->l_len, &ufl->l_len) ||
+	    __put_user(kfl->l_pid, &ufl->l_pid))
+		return -EFAULT;
+	return 0;
+}
+#endif
+
+static unsigned int
+convert_fcntl_cmd(unsigned int cmd)
+{
+	switch (cmd) {
+	case F_GETLK64:
+		return F_GETLK;
+	case F_SETLK64:
+		return F_SETLK;
+	case F_SETLKW64:
+		return F_SETLKW;
+	}
+
+	return cmd;
+}
+
+COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
+{
+	mm_segment_t old_fs;
+	struct flock f;
+	long ret;
+	unsigned int conv_cmd;
+
+	switch (cmd) {
+	case F_GETLK:
+	case F_SETLK:
+	case F_SETLKW:
+		ret = get_compat_flock(&f, compat_ptr(arg));
+		if (ret != 0)
+			break;
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		ret = sys_fcntl(fd, cmd, (unsigned long)&f);
+		set_fs(old_fs);
+		if (cmd == F_GETLK && ret == 0) {
+			/* GETLK was successful and we need to return the data...
+			 * but it needs to fit in the compat structure.
+			 * l_start shouldn't be too big, unless the original
+			 * start + end is greater than COMPAT_OFF_T_MAX, in which
+			 * case the app was asking for trouble, so we return
+			 * -EOVERFLOW in that case.
+			 * l_len could be too big, in which case we just truncate it,
+			 * and only allow the app to see that part of the conflicting
+			 * lock that might make sense to it anyway
+			 */
+
+			if (f.l_start > COMPAT_OFF_T_MAX)
+				ret = -EOVERFLOW;
+			if (f.l_len > COMPAT_OFF_T_MAX)
+				f.l_len = COMPAT_OFF_T_MAX;
+			if (ret == 0)
+				ret = put_compat_flock(&f, compat_ptr(arg));
+		}
+		break;
+
+	case F_GETLK64:
+	case F_SETLK64:
+	case F_SETLKW64:
+	case F_OFD_GETLK:
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+		ret = get_compat_flock64(&f, compat_ptr(arg));
+		if (ret != 0)
+			break;
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		conv_cmd = convert_fcntl_cmd(cmd);
+		ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f);
+		set_fs(old_fs);
+		if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) {
+			/* need to return lock information - see above for commentary */
+			if (f.l_start > COMPAT_LOFF_T_MAX)
+				ret = -EOVERFLOW;
+			if (f.l_len > COMPAT_LOFF_T_MAX)
+				f.l_len = COMPAT_LOFF_T_MAX;
+			if (ret == 0)
+				ret = put_compat_flock64(&f, compat_ptr(arg));
+		}
+		break;
+
+	default:
+		ret = sys_fcntl(fd, cmd, arg);
+		break;
+	}
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
+{
+	switch (cmd) {
+	case F_GETLK64:
+	case F_SETLK64:
+	case F_SETLKW64:
+	case F_OFD_GETLK:
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+		return -EINVAL;
+	}
+	return compat_sys_fcntl64(fd, cmd, arg);
+}
+#endif
+
 /* Table to convert sigio signal codes into poll band bitmaps */
 
 static const long band_table[NSIGPOLL] = {
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 5559168d5637..58a61f55e0d0 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -9,6 +9,7 @@
 #include <linux/fsnotify.h>
 #include <linux/personality.h>
 #include <linux/uaccess.h>
+#include <linux/compat.h>
 #include "internal.h"
 #include "mount.h"
 
@@ -264,3 +265,15 @@ SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
 	ret = do_handle_open(mountdirfd, handle, flags);
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+			     struct file_handle __user *, handle, int, flags)
+{
+	return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ef600591d96f..63ee2940775c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -173,19 +173,33 @@ static void wb_wakeup(struct bdi_writeback *wb)
 	spin_unlock_bh(&wb->work_lock);
 }
 
+static void finish_writeback_work(struct bdi_writeback *wb,
+				  struct wb_writeback_work *work)
+{
+	struct wb_completion *done = work->done;
+
+	if (work->auto_free)
+		kfree(work);
+	if (done && atomic_dec_and_test(&done->cnt))
+		wake_up_all(&wb->bdi->wb_waitq);
+}
+
 static void wb_queue_work(struct bdi_writeback *wb,
 			  struct wb_writeback_work *work)
 {
 	trace_writeback_queue(wb, work);
 
-	spin_lock_bh(&wb->work_lock);
-	if (!test_bit(WB_registered, &wb->state))
-		goto out_unlock;
 	if (work->done)
 		atomic_inc(&work->done->cnt);
-	list_add_tail(&work->list, &wb->work_list);
-	mod_delayed_work(bdi_wq, &wb->dwork, 0);
-out_unlock:
+
+	spin_lock_bh(&wb->work_lock);
+
+	if (test_bit(WB_registered, &wb->state)) {
+		list_add_tail(&work->list, &wb->work_list);
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	} else
+		finish_writeback_work(wb, work);
+
 	spin_unlock_bh(&wb->work_lock);
 }
 
@@ -1873,16 +1887,9 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 
 	set_bit(WB_writeback_running, &wb->state);
 	while ((work = get_next_work_item(wb)) != NULL) {
-		struct wb_completion *done = work->done;
-
 		trace_writeback_exec(wb, work);
-
 		wrote += wb_writeback(wb, work);
-
-		if (work->auto_free)
-			kfree(work);
-		if (done && atomic_dec_and_test(&done->cnt))
-			wake_up_all(&wb->bdi->wb_waitq);
+		finish_writeback_work(wb, work);
 	}
 
 	/*
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index b681b43c766e..c2d7f3a92679 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -382,9 +382,9 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 			wake_up(&fc->blocked_waitq);
 
 		if (fc->num_background == fc->congestion_threshold &&
-		    fc->connected && fc->bdi_initialized) {
-			clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
-			clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
+		    fc->connected && fc->sb) {
+			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
 		}
 		fc->num_background--;
 		fc->active_background--;
@@ -573,10 +573,9 @@ void fuse_request_send_background_locked(struct fuse_conn *fc,
 	fc->num_background++;
 	if (fc->num_background == fc->max_background)
 		fc->blocked = 1;
-	if (fc->num_background == fc->congestion_threshold &&
-	    fc->bdi_initialized) {
-		set_bdi_congested(&fc->bdi, BLK_RW_SYNC);
-		set_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
+	if (fc->num_background == fc->congestion_threshold && fc->sb) {
+		set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+		set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
 	}
 	list_add_tail(&req->list, &fc->bg_queue);
 	flush_bg_queue(fc);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 32ac2c9b09c0..f33341d9501a 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -527,9 +527,6 @@ struct fuse_conn {
 	/** Filesystem supports NFS exporting.  Only set in INIT */
 	unsigned export_support:1;
 
-	/** Set if bdi is valid */
-	unsigned bdi_initialized:1;
-
 	/** write-back cache policy (default is write-through) */
 	unsigned writeback_cache:1;
 
@@ -631,9 +628,6 @@ struct fuse_conn {
 	/** Negotiated minor version */
 	unsigned minor;
 
-	/** Backing dev info */
-	struct backing_dev_info bdi;
-
 	/** Entry on the fuse_conn_list */
 	struct list_head entry;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6fe6a88ecb4a..73cf05135252 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -386,12 +386,6 @@ static void fuse_send_destroy(struct fuse_conn *fc)
 	}
 }
 
-static void fuse_bdi_destroy(struct fuse_conn *fc)
-{
-	if (fc->bdi_initialized)
-		bdi_destroy(&fc->bdi);
-}
-
 static void fuse_put_super(struct super_block *sb)
 {
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
@@ -403,7 +397,6 @@ static void fuse_put_super(struct super_block *sb)
 	list_del(&fc->entry);
 	fuse_ctl_remove_conn(fc);
 	mutex_unlock(&fuse_mutex);
-	fuse_bdi_destroy(fc);
 
 	fuse_conn_put(fc);
 }
@@ -928,7 +921,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 			fc->no_flock = 1;
 		}
 
-		fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
+		fc->sb->s_bdi->ra_pages =
+				min(fc->sb->s_bdi->ra_pages, ra_pages);
 		fc->minor = arg->minor;
 		fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
 		fc->max_write = max_t(unsigned, 4096, fc->max_write);
@@ -944,7 +938,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 
 	arg->major = FUSE_KERNEL_VERSION;
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
-	arg->max_readahead = fc->bdi.ra_pages * PAGE_SIZE;
+	arg->max_readahead = fc->sb->s_bdi->ra_pages * PAGE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
 		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
 		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
@@ -976,27 +970,18 @@ static void fuse_free_conn(struct fuse_conn *fc)
 static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 {
 	int err;
+	char *suffix = "";
 
-	fc->bdi.name = "fuse";
-	fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
-	/* fuse does it's own writeback accounting */
-	fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
-
-	err = bdi_init(&fc->bdi);
+	if (sb->s_bdev)
+		suffix = "-fuseblk";
+	err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev),
+				   MINOR(fc->dev), suffix);
 	if (err)
 		return err;
 
-	fc->bdi_initialized = 1;
-
-	if (sb->s_bdev) {
-		err =  bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
-				    MAJOR(fc->dev), MINOR(fc->dev));
-	} else {
-		err = bdi_register_dev(&fc->bdi, fc->dev);
-	}
-
-	if (err)
-		return err;
+	sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+	/* fuse does it's own writeback accounting */
+	sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
 
 	/*
 	 * For a single fuse filesystem use max 1% of dirty +
@@ -1010,7 +995,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 	 *
 	 *    /sys/class/bdi/<bdi>/max_ratio
 	 */
-	bdi_set_max_ratio(&fc->bdi, 1);
+	bdi_set_max_ratio(sb->s_bdi, 1);
 
 	return 0;
 }
@@ -1113,8 +1098,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto err_dev_free;
 
-	sb->s_bdi = &fc->bdi;
-
 	/* Handle umasking inside the fuse code */
 	if (sb->s_flags & MS_POSIXACL)
 		fc->dont_mask = 1;
@@ -1182,7 +1165,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
  err_dev_free:
 	fuse_dev_free(fud);
  err_put_conn:
-	fuse_bdi_destroy(fc);
 	fuse_conn_put(fc);
  err_fput:
 	fput(file);
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index c45084ac642d..511e1ed7e2de 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -207,7 +207,7 @@ struct lm_lockname {
 	struct gfs2_sbd *ln_sbd;
 	u64 ln_number;
 	unsigned int ln_type;
-};
+} __packed __aligned(sizeof(int));
 
 #define lm_name_equal(name1, name2) \
         (((name1)->ln_number == (name2)->ln_number) &&	\
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b108e7ba81af..ed67548b286c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -23,6 +23,7 @@
 #include <linux/quotaops.h>
 #include <linux/lockdep.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -1222,12 +1223,7 @@ static int set_gfs2_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
-
-	/*
-	 * We set the bdi here to the queue backing, file systems can
-	 * overwrite this in ->fill_super()
-	 */
-	s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
+	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 	return 0;
 }
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8f96461236f6..dde861387a40 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -136,17 +136,26 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
 	vma->vm_ops = &hugetlb_vm_ops;
 
+	/*
+	 * Offset passed to mmap (before page shift) could have been
+	 * negative when represented as a (l)off_t.
+	 */
+	if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
+		return -EINVAL;
+
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
+	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	/* check for overflow */
+	if (len < vma_len)
+		return -EINVAL;
 
 	inode_lock(inode);
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-
 	if (hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
@@ -155,7 +164,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = 0;
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
-		inode->i_size = len;
+		i_size_write(inode, len);
 out:
 	inode_unlock(inode);
 
@@ -695,14 +704,11 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 
 	inode = new_inode(sb);
 	if (inode) {
-		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode->i_mode = S_IFDIR | config->mode;
 		inode->i_uid = config->uid;
 		inode->i_gid = config->gid;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-		info = HUGETLBFS_I(inode);
-		mpol_shared_policy_init(&info->policy, NULL);
 		inode->i_op = &hugetlbfs_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -733,7 +739,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 
 	inode = new_inode(sb);
 	if (inode) {
-		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
@@ -741,15 +746,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inode->i_mapping->private_data = resv_map;
-		info = HUGETLBFS_I(inode);
-		/*
-		 * The policy is initialized here even if we are creating a
-		 * private inode because initialization simply creates an
-		 * an empty rb tree and calls rwlock_init(), later when we
-		 * call mpol_free_shared_policy() it will just return because
-		 * the rb tree will still be empty.
-		 */
-		mpol_shared_policy_init(&info->policy, NULL);
 		switch (mode & S_IFMT) {
 		default:
 			init_special_inode(inode, mode, dev);
@@ -937,6 +933,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 		hugetlbfs_inc_free_inodes(sbinfo);
 		return NULL;
 	}
+
+	/*
+	 * Any time after allocation, hugetlbfs_destroy_inode can be called
+	 * for the inode.  mpol_free_shared_policy is unconditionally called
+	 * as part of hugetlbfs_destroy_inode.  So, initialize policy here
+	 * in case of a quick call to destroy.
+	 *
+	 * Note that the policy is initialized even if we are creating a
+	 * private inode.  This simplifies hugetlbfs_destroy_inode.
+	 */
+	mpol_shared_policy_init(&p->policy, NULL);
+
 	return &p->vfs_inode;
 }
 
diff --git a/fs/internal.h b/fs/internal.h
index 11c6d89dce9c..076751d90ba2 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -108,8 +108,6 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname,
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *);
 
-extern long do_handle_open(int mountdirfd,
-			   struct file_handle __user *ufh, int open_flag);
 extern int open_check_o_direct(struct file *f);
 extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file *filp_clone_open(struct file *);
diff --git a/fs/iomap.c b/fs/iomap.c
index 3ca1a8e44135..141c3cd55a8b 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	size_t count = iov_iter_count(iter);
-	loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0;
+	loff_t pos = iocb->ki_pos, start = pos;
+	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
 	struct blk_plug plug;
 	struct iomap_dio *dio;
@@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		ret = filemap_write_and_wait_range(mapping, start, end);
 		if (ret)
 			goto out_free_dio;
 
 		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
@@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
+	ret = iomap_dio_complete(dio);
+
 	/*
 	 * Try again to invalidate clean pages which might have been cached by
 	 * non-direct readahead, or faulted in by get_user_pages() if the source
@@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	 * this invalidation fails, tough, the write still worked...
 	 */
 	if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
+		int err = invalidate_inode_pages2_range(mapping,
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
 	}
 
-	return iomap_dio_complete(dio);
+	return ret;
 
 out_free_dio:
 	kfree(dio);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a1a359bfcc9c..5adc2fb62b0f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1125,10 +1125,8 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 	/* Set up a default-sized revoke table for the new mount. */
 	err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
-	if (err) {
-		kfree(journal);
-		return NULL;
-	}
+	if (err)
+		goto err_cleanup;
 
 	spin_lock_init(&journal->j_history_lock);
 
@@ -1145,23 +1143,25 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_wbufsize = n;
 	journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
 					GFP_KERNEL);
-	if (!journal->j_wbuf) {
-		kfree(journal);
-		return NULL;
-	}
+	if (!journal->j_wbuf)
+		goto err_cleanup;
 
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
 			__func__);
-		kfree(journal->j_wbuf);
-		kfree(journal);
-		return NULL;
+		goto err_cleanup;
 	}
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
 
 	return journal;
+
+err_cleanup:
+	kfree(journal->j_wbuf);
+	jbd2_journal_destroy_revoke(journal);
+	kfree(journal);
+	return NULL;
 }
 
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index cfc38b552118..f9aefcda5854 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -280,6 +280,7 @@ int jbd2_journal_init_revoke(journal_t *journal, int hash_size)
 
 fail1:
 	jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]);
+	journal->j_revoke_table[0] = NULL;
 fail0:
 	return -ENOMEM;
 }
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 8e4dc7ab584c..ac2dfe0c5a9c 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -809,7 +809,8 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
 		if (kn->flags & KERNFS_HAS_MMAP)
 			unmap_mapping_range(inode->i_mapping, 0, 0, 1);
 
-		kernfs_release_file(kn, of);
+		if (kn->flags & KERNFS_HAS_RELEASE)
+			kernfs_release_file(kn, of);
 	}
 
 	mutex_unlock(&kernfs_open_file_mutex);
diff --git a/fs/namei.c b/fs/namei.c
index d41fab78798b..19dcf62133cc 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2145,6 +2145,9 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	int retval = 0;
 	const char *s = nd->name->name;
 
+	if (!*s)
+		flags &= ~LOOKUP_RCU;
+
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
 	nd->depth = 0;
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index d5606099712a..6d0f14c86099 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -554,12 +554,11 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	sb->s_magic = NCP_SUPER_MAGIC;
 	sb->s_op = &ncp_sops;
 	sb->s_d_op = &ncp_dentry_operations;
-	sb->s_bdi = &server->bdi;
 
 	server = NCP_SBP(sb);
 	memset(server, 0, sizeof(*server));
 
-	error = bdi_setup_and_register(&server->bdi, "ncpfs");
+	error = super_setup_bdi(sb);
 	if (error)
 		goto out_fput;
 
@@ -568,7 +567,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	if (data.info_fd != -1) {
 		struct socket *info_sock = sockfd_lookup(data.info_fd, &error);
 		if (!info_sock)
-			goto out_bdi;
+			goto out_fput;
 		server->info_sock = info_sock;
 		error = -EBADFD;
 		if (info_sock->type != SOCK_STREAM)
@@ -746,8 +745,6 @@ out_nls:
 out_fput2:
 	if (server->info_sock)
 		sockfd_put(server->info_sock);
-out_bdi:
-	bdi_destroy(&server->bdi);
 out_fput:
 	sockfd_put(sock);
 out:
@@ -788,7 +785,6 @@ static void ncp_put_super(struct super_block *sb)
 	kill_pid(server->m.wdog_pid, SIGTERM, 1);
 	put_pid(server->m.wdog_pid);
 
-	bdi_destroy(&server->bdi);
 	kfree(server->priv.data);
 	kfree(server->auth.object_name);
 	vfree(server->rxbuf);
diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h
index 55e26fd80886..366fd63cc506 100644
--- a/fs/ncpfs/ncp_fs_sb.h
+++ b/fs/ncpfs/ncp_fs_sb.h
@@ -143,7 +143,6 @@ struct ncp_server {
 		size_t len;
 		__u8 data[128];
 	} unexpected_packet;
-	struct backing_dev_info bdi;
 };
 
 extern void ncp_tcp_rcv_proc(struct work_struct *work);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index bb79972dc638..773774531aff 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -232,12 +232,12 @@ static struct svc_serv_ops nfs41_cb_sv_ops = {
 	.svo_module		= THIS_MODULE,
 };
 
-struct svc_serv_ops *nfs4_cb_sv_ops[] = {
+static struct svc_serv_ops *nfs4_cb_sv_ops[] = {
 	[0] = &nfs40_cb_sv_ops,
 	[1] = &nfs41_cb_sv_ops,
 };
 #else
-struct svc_serv_ops *nfs4_cb_sv_ops[] = {
+static struct svc_serv_ops *nfs4_cb_sv_ops[] = {
 	[0] = &nfs40_cb_sv_ops,
 	[1] = NULL,
 };
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 91a8d610ba0f..04d15a0045e3 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -325,10 +325,33 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 	return NULL;
 }
 
-static bool nfs_client_init_is_complete(const struct nfs_client *clp)
+/*
+ * Return true if @clp is done initializing, false if still working on it.
+ *
+ * Use nfs_client_init_status to check if it was successful.
+ */
+bool nfs_client_init_is_complete(const struct nfs_client *clp)
 {
 	return clp->cl_cons_state <= NFS_CS_READY;
 }
+EXPORT_SYMBOL_GPL(nfs_client_init_is_complete);
+
+/*
+ * Return 0 if @clp was successfully initialized, -errno otherwise.
+ *
+ * This must be called *after* nfs_client_init_is_complete() returns true,
+ * otherwise it will pop WARN_ON_ONCE and return -EINVAL
+ */
+int nfs_client_init_status(const struct nfs_client *clp)
+{
+	/* called without checking nfs_client_init_is_complete */
+	if (clp->cl_cons_state > NFS_CS_READY) {
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+	return clp->cl_cons_state;
+}
+EXPORT_SYMBOL_GPL(nfs_client_init_status);
 
 int nfs_wait_client_init_complete(const struct nfs_client *clp)
 {
@@ -738,9 +761,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->rsize = NFS_MAX_FILE_IO_SIZE;
 	server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	server->backing_dev_info.name = "nfs";
-	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
-
 	if (server->wsize > max_rpc_payload)
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
@@ -894,12 +914,6 @@ struct nfs_server *nfs_alloc_server(void)
 		return NULL;
 	}
 
-	if (bdi_init(&server->backing_dev_info)) {
-		nfs_free_iostats(server->io_stats);
-		kfree(server);
-		return NULL;
-	}
-
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
@@ -930,7 +944,6 @@ void nfs_free_server(struct nfs_server *server)
 	ida_destroy(&server->lockowner_id);
 	ida_destroy(&server->openowner_id);
 	nfs_free_iostats(server->io_stats);
-	bdi_destroy(&server->backing_dev_info);
 	kfree(server);
 	nfs_release_automount_timer();
 	dprintk("<-- nfs_free_server()\n");
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index fb499a3f21b5..f92ba8d6c556 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2055,7 +2055,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
 	struct inode *old_inode = d_inode(old_dentry);
 	struct inode *new_inode = d_inode(new_dentry);
-	struct dentry *dentry = NULL, *rehash = NULL;
+	struct dentry *dentry = NULL;
 	struct rpc_task *task;
 	int error = -EBUSY;
 
@@ -2078,10 +2078,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 * To prevent any new references to the target during the
 		 * rename, we unhash the dentry in advance.
 		 */
-		if (!d_unhashed(new_dentry)) {
+		if (!d_unhashed(new_dentry))
 			d_drop(new_dentry);
-			rehash = new_dentry;
-		}
 
 		if (d_count(new_dentry) > 2) {
 			int err;
@@ -2098,7 +2096,6 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				goto out;
 
 			new_dentry = dentry;
-			rehash = NULL;
 			new_inode = NULL;
 		}
 	}
@@ -2119,8 +2116,6 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		error = task->tk_status;
 	rpc_put_task(task);
 out:
-	if (rehash)
-		d_rehash(rehash);
 	trace_nfs_rename_exit(old_dir, old_dentry,
 			new_dir, new_dentry, error);
 	/* new dentry created? */
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index aab32fc3d6a8..c1b5fed7c863 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -537,7 +537,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 
 	if (put_dreq(dreq))
 		nfs_direct_complete(dreq);
-	return 0;
+	return requested_bytes;
 }
 
 /**
@@ -566,7 +566,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	struct nfs_direct_req *dreq;
 	struct nfs_lock_context *l_ctx;
-	ssize_t result = -EINVAL;
+	ssize_t result = -EINVAL, requested;
 	size_t count = iov_iter_count(iter);
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
 
@@ -600,14 +600,19 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	nfs_start_io_direct(inode);
 
 	NFS_I(inode)->read_io += count;
-	result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
+	requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
 
 	nfs_end_io_direct(inode);
 
-	if (!result) {
+	if (requested > 0) {
 		result = nfs_direct_wait(dreq);
-		if (result > 0)
+		if (result > 0) {
+			requested -= result;
 			iocb->ki_pos += result;
+		}
+		iov_iter_revert(iter, requested);
+	} else {
+		result = requested;
 	}
 
 out_release:
@@ -954,7 +959,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 	if (put_dreq(dreq))
 		nfs_direct_write_complete(dreq);
-	return 0;
+	return requested_bytes;
 }
 
 /**
@@ -979,7 +984,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	ssize_t result = -EINVAL;
+	ssize_t result = -EINVAL, requested;
 	size_t count;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -1022,7 +1027,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 
 	nfs_start_io_direct(inode);
 
-	result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+	requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
 
 	if (mapping->nrpages) {
 		invalidate_inode_pages2_range(mapping,
@@ -1031,13 +1036,17 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 
 	nfs_end_io_direct(inode);
 
-	if (!result) {
+	if (requested > 0) {
 		result = nfs_direct_wait(dreq);
 		if (result > 0) {
+			requested -= result;
 			iocb->ki_pos = pos + result;
 			/* XXX: should check the generic_write_sync retval */
 			generic_write_sync(iocb, result);
 		}
+		iov_iter_revert(iter, requested);
+	} else {
+		result = requested;
 	}
 out_release:
 	nfs_direct_req_release(dreq);
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 44347f4bdc15..acd30baca461 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -202,10 +202,10 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 			task->tk_status);
 		nfs4_mark_deviceid_unavailable(devid);
 		pnfs_error_mark_layout_for_return(inode, lseg);
-		pnfs_set_lo_fail(lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:
+		pnfs_set_lo_fail(lseg);
 reset:
 		dprintk("%s Retry through MDS. Error %d\n", __func__,
 			task->tk_status);
@@ -560,6 +560,50 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	return PNFS_ATTEMPTED;
 }
 
+static int
+filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
+			  struct nfs4_filelayout_segment *fl,
+			  gfp_t gfp_flags)
+{
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *dsaddr;
+	int status = -EINVAL;
+
+	/* find and reference the deviceid */
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid,
+			lo->plh_lc_cred, gfp_flags);
+	if (d == NULL)
+		goto out;
+
+	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	/* Found deviceid is unavailable */
+	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
+		goto out_put;
+
+	fl->dsaddr = dsaddr;
+
+	if (fl->first_stripe_index >= dsaddr->stripe_count) {
+		dprintk("%s Bad first_stripe_index %u\n",
+				__func__, fl->first_stripe_index);
+		goto out_put;
+	}
+
+	if ((fl->stripe_type == STRIPE_SPARSE &&
+	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
+	    (fl->stripe_type == STRIPE_DENSE &&
+	    fl->num_fh != dsaddr->stripe_count)) {
+		dprintk("%s num_fh %u not valid for given packing\n",
+			__func__, fl->num_fh);
+		goto out_put;
+	}
+	status = 0;
+out:
+	return status;
+out_put:
+	nfs4_fl_put_deviceid(dsaddr);
+	goto out;
+}
+
 /*
  * filelayout_check_layout()
  *
@@ -572,11 +616,8 @@ static int
 filelayout_check_layout(struct pnfs_layout_hdr *lo,
 			struct nfs4_filelayout_segment *fl,
 			struct nfs4_layoutget_res *lgr,
-			struct nfs4_deviceid *id,
 			gfp_t gfp_flags)
 {
-	struct nfs4_deviceid_node *d;
-	struct nfs4_file_layout_dsaddr *dsaddr;
 	int status = -EINVAL;
 
 	dprintk("--> %s\n", __func__);
@@ -601,41 +642,10 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 		goto out;
 	}
 
-	/* find and reference the deviceid */
-	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id,
-			lo->plh_lc_cred, gfp_flags);
-	if (d == NULL)
-		goto out;
-
-	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
-	/* Found deviceid is unavailable */
-	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
-		goto out_put;
-
-	fl->dsaddr = dsaddr;
-
-	if (fl->first_stripe_index >= dsaddr->stripe_count) {
-		dprintk("%s Bad first_stripe_index %u\n",
-				__func__, fl->first_stripe_index);
-		goto out_put;
-	}
-
-	if ((fl->stripe_type == STRIPE_SPARSE &&
-	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
-	    (fl->stripe_type == STRIPE_DENSE &&
-	    fl->num_fh != dsaddr->stripe_count)) {
-		dprintk("%s num_fh %u not valid for given packing\n",
-			__func__, fl->num_fh);
-		goto out_put;
-	}
-
 	status = 0;
 out:
 	dprintk("--> %s returns %d\n", __func__, status);
 	return status;
-out_put:
-	nfs4_fl_put_deviceid(dsaddr);
-	goto out;
 }
 
 static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
@@ -657,7 +667,6 @@ static int
 filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			 struct nfs4_filelayout_segment *fl,
 			 struct nfs4_layoutget_res *lgr,
-			 struct nfs4_deviceid *id,
 			 gfp_t gfp_flags)
 {
 	struct xdr_stream stream;
@@ -682,9 +691,9 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	if (unlikely(!p))
 		goto out_err;
 
-	memcpy(id, p, sizeof(*id));
+	memcpy(&fl->deviceid, p, sizeof(fl->deviceid));
 	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
-	nfs4_print_deviceid(id);
+	nfs4_print_deviceid(&fl->deviceid);
 
 	nfl_util = be32_to_cpup(p++);
 	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
@@ -831,15 +840,14 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 {
 	struct nfs4_filelayout_segment *fl;
 	int rc;
-	struct nfs4_deviceid id;
 
 	dprintk("--> %s\n", __func__);
 	fl = kzalloc(sizeof(*fl), gfp_flags);
 	if (!fl)
 		return NULL;
 
-	rc = filelayout_decode_layout(layoutid, fl, lgr, &id, gfp_flags);
-	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id, gfp_flags)) {
+	rc = filelayout_decode_layout(layoutid, fl, lgr, gfp_flags);
+	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, gfp_flags)) {
 		_filelayout_free_lseg(fl);
 		return NULL;
 	}
@@ -888,18 +896,51 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	return min(stripe_unit - (unsigned int)stripe_offset, size);
 }
 
+static struct pnfs_layout_segment *
+fl_pnfs_update_layout(struct inode *ino,
+		      struct nfs_open_context *ctx,
+		      loff_t pos,
+		      u64 count,
+		      enum pnfs_iomode iomode,
+		      bool strict_iomode,
+		      gfp_t gfp_flags)
+{
+	struct pnfs_layout_segment *lseg = NULL;
+	struct pnfs_layout_hdr *lo;
+	struct nfs4_filelayout_segment *fl;
+	int status;
+
+	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
+				  gfp_flags);
+	if (!lseg)
+		lseg = ERR_PTR(-ENOMEM);
+	if (IS_ERR(lseg))
+		goto out;
+
+	lo = NFS_I(ino)->layout;
+	fl = FILELAYOUT_LSEG(lseg);
+
+	status = filelayout_check_deviceid(lo, fl, gfp_flags);
+	if (status)
+		lseg = ERR_PTR(status);
+out:
+	if (IS_ERR(lseg))
+		pnfs_put_lseg(lseg);
+	return lseg;
+}
+
 static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
 	if (!pgio->pg_lseg) {
-		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   0,
-					   NFS4_MAX_UINT64,
-					   IOMODE_READ,
-					   false,
-					   GFP_KERNEL);
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      req->wb_context,
+						      0,
+						      NFS4_MAX_UINT64,
+						      IOMODE_READ,
+						      false,
+						      GFP_KERNEL);
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;
@@ -919,13 +960,13 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	int status;
 
 	if (!pgio->pg_lseg) {
-		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   0,
-					   NFS4_MAX_UINT64,
-					   IOMODE_RW,
-					   false,
-					   GFP_NOFS);
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      req->wb_context,
+						      0,
+						      NFS4_MAX_UINT64,
+						      IOMODE_RW,
+						      false,
+						      GFP_NOFS);
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
index 2896cb833a11..79323b5dab0c 100644
--- a/fs/nfs/filelayout/filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -55,15 +55,16 @@ struct nfs4_file_layout_dsaddr {
 };
 
 struct nfs4_filelayout_segment {
-	struct pnfs_layout_segment generic_hdr;
-	u32 stripe_type;
-	u32 commit_through_mds;
-	u32 stripe_unit;
-	u32 first_stripe_index;
-	u64 pattern_offset;
-	struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
-	unsigned int num_fh;
-	struct nfs_fh **fh_array;
+	struct pnfs_layout_segment	generic_hdr;
+	u32				stripe_type;
+	u32				commit_through_mds;
+	u32				stripe_unit;
+	u32				first_stripe_index;
+	u64				pattern_offset;
+	struct nfs4_deviceid		deviceid;
+	struct nfs4_file_layout_dsaddr	*dsaddr; /* Point to GETDEVINFO data */
+	unsigned int			num_fh;
+	struct nfs_fh			**fh_array;
 };
 
 struct nfs4_filelayout {
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index f956ca20a8a3..d913e818858f 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -266,6 +266,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs4_pnfs_ds *ret = ds;
 	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
+	int status;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
@@ -277,9 +278,14 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	if (ds->ds_clp)
 		goto out_test_devid;
 
-	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+	status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
 			     dataserver_retrans, 4,
 			     s->nfs_client->cl_minorversion);
+	if (status) {
+		nfs4_mark_deviceid_unavailable(devid);
+		ret = NULL;
+		goto out;
+	}
 
 out_test_devid:
 	if (ret->ds_clp == NULL ||
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f4f39b0ab09b..98b34c9b0564 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -175,7 +175,19 @@ ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg)
 static inline bool
 ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
 {
-	return nfs4_test_deviceid_unavailable(node);
+	/*
+	 * Flexfiles should never mark a DS unavailable, but if it does
+	 * print a (ratelimited) warning as this can affect performance.
+	 */
+	if (nfs4_test_deviceid_unavailable(node)) {
+		u32 *p = (u32 *)node->deviceid.data;
+
+		pr_warn_ratelimited("NFS: flexfiles layout referencing an "
+				"unavailable device [%x%x%x%x]\n",
+				p[0], p[1], p[2], p[3]);
+		return true;
+	}
+	return false;
 }
 
 static inline int
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e5a6f248697b..457cfeb1d5c1 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -208,6 +208,10 @@ static bool ff_layout_mirror_valid(struct pnfs_layout_segment *lseg,
 		} else
 			goto outerr;
 	}
+
+	if (IS_ERR(mirror->mirror_ds))
+		goto outerr;
+
 	if (mirror->mirror_ds->ds == NULL) {
 		struct nfs4_deviceid_node *devid;
 		devid = &mirror->mirror_ds->id_node;
@@ -384,6 +388,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
+	int status;
 
 	if (!ff_layout_mirror_valid(lseg, mirror, true)) {
 		pr_err_ratelimited("NFS: %s: No data server for offset index %d\n",
@@ -404,7 +409,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 	/* FIXME: For now we assume the server sent only one version of NFS
 	 * to use for the DS.
 	 */
-	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+	status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
 			     dataserver_retrans,
 			     mirror->mirror_ds->ds_versions[0].version,
 			     mirror->mirror_ds->ds_versions[0].minor_version);
@@ -420,11 +425,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 			mirror->mirror_ds->ds_versions[0].wsize = max_payload;
 		goto out;
 	}
+out_fail:
 	ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
 				 mirror, lseg->pls_range.offset,
 				 lseg->pls_range.length, NFS4ERR_NXIO,
 				 OP_ILLEGAL, GFP_NOIO);
-out_fail:
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
 	ds = NULL;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 09ca5095c04e..9dc65d7ae754 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -139,7 +139,7 @@ struct nfs_mount_request {
 };
 
 struct nfs_mount_info {
-	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	int (*fill_super)(struct super_block *, struct nfs_mount_info *);
 	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
 	struct nfs_parsed_mount_data *parsed;
 	struct nfs_clone_mount *cloned;
@@ -186,6 +186,8 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
 					   struct nfs_fattr *,
 					   rpc_authflavor_t);
+extern bool nfs_client_init_is_complete(const struct nfs_client *clp);
+extern int nfs_client_init_status(const struct nfs_client *clp);
 extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
 extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
 extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
@@ -405,7 +407,7 @@ struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *
 struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
 		const char *, struct nfs_mount_info *);
 void nfs_kill_super(struct super_block *);
-void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
+int nfs_fill_super(struct super_block *, struct nfs_mount_info *);
 
 extern struct rpc_stat nfs_rpcstat;
 
@@ -456,7 +458,7 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 
 /* super.c */
-void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+int nfs_clone_super(struct super_block *, struct nfs_mount_info *);
 void nfs_umount_begin(struct super_block *);
 int  nfs_statfs(struct dentry *, struct kstatfs *);
 int  nfs_show_options(struct seq_file *, struct dentry *);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 5ae9d64ea08b..8346ccbf2d52 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1023,9 +1023,9 @@ static void nfs4_session_set_rwsize(struct nfs_server *server)
 	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
 	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
 
-	if (server->rsize > server_resp_sz)
+	if (!server->rsize || server->rsize > server_resp_sz)
 		server->rsize = server_resp_sz;
-	if (server->wsize > server_rqst_sz)
+	if (!server->wsize || server->wsize > server_rqst_sz)
 		server->wsize = server_rqst_sz;
 #endif /* CONFIG_NFS_V4_1 */
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1b183686c6d4..201ca3f2c4ba 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2258,8 +2258,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
 		return 0;
 
-	/* even though OPEN succeeded, access is denied. Close the file */
-	nfs4_close_state(state, fmode);
 	return -EACCES;
 }
 
@@ -2444,17 +2442,14 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state)
 	}
 
 	nfs4_stateid_copy(&stateid, &delegation->stateid);
-	if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
+	if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) ||
+		!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
+			&delegation->flags)) {
 		rcu_read_unlock();
 		nfs_finish_clear_delegation_stateid(state, &stateid);
 		return;
 	}
 
-	if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) {
-		rcu_read_unlock();
-		return;
-	}
-
 	cred = get_rpccred(delegation->cred);
 	rcu_read_unlock();
 	status = nfs41_test_and_free_expired_stateid(server, &stateid, cred);
@@ -7427,11 +7422,11 @@ static void nfs4_exchange_id_release(void *data)
 	struct nfs41_exchange_id_data *cdata =
 					(struct nfs41_exchange_id_data *)data;
 
-	nfs_put_client(cdata->args.client);
 	if (cdata->xprt) {
 		xprt_put(cdata->xprt);
 		rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient);
 	}
+	nfs_put_client(cdata->args.client);
 	kfree(cdata->res.impl_id);
 	kfree(cdata->res.server_scope);
 	kfree(cdata->res.server_owner);
@@ -7538,10 +7533,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 	task_setup_data.callback_data = calldata;
 
 	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task)) {
-	status = PTR_ERR(task);
-		goto out_impl_id;
-	}
+	if (IS_ERR(task))
+		return PTR_ERR(task);
 
 	if (!xprt) {
 		status = rpc_wait_for_completion_task(task);
@@ -7569,6 +7562,7 @@ out_server_owner:
 	kfree(calldata->res.server_owner);
 out_calldata:
 	kfree(calldata);
+	nfs_put_client(clp);
 	goto out;
 }
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index f0369e362753..80ce289eea05 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3942,7 +3942,7 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
 		if (len <= 0)
 			goto out;
 		dprintk("%s: name=%s\n", __func__, group_name->data);
-		return NFS_ATTR_FATTR_OWNER_NAME;
+		return NFS_ATTR_FATTR_GROUP_NAME;
 	} else {
 		len = xdr_stream_decode_opaque_inline(xdr, (void **)&p,
 				XDR_MAX_NETOBJ);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 63f77b49a586..590e1e35781f 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -367,7 +367,7 @@ void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
 struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
 void nfs4_pnfs_v3_ds_connect_unload(void);
-void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
 			  unsigned int retrans, u32 version, u32 minor_version);
 struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 9414b492439f..7250b95549ec 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -745,15 +745,17 @@ out:
 /*
  * Create an rpc connection to the nfs4_pnfs_ds data server.
  * Currently only supports IPv4 and IPv6 addresses.
- * If connection fails, make devid unavailable.
+ * If connection fails, make devid unavailable and return a -errno.
  */
-void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
 			  unsigned int retrans, u32 version, u32 minor_version)
 {
-	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
-		int err = 0;
+	int err;
 
+again:
+	err = 0;
+	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		if (version == 3) {
 			err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
 						       retrans);
@@ -766,12 +768,29 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			err = -EPROTONOSUPPORT;
 		}
 
-		if (err)
-			nfs4_mark_deviceid_unavailable(devid);
 		nfs4_clear_ds_conn_bit(ds);
 	} else {
 		nfs4_wait_ds_connect(ds);
+
+		/* what was waited on didn't connect AND didn't mark unavail */
+		if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid))
+			goto again;
 	}
+
+	/*
+	 * At this point the ds->ds_clp should be ready, but it might have
+	 * hit an error.
+	 */
+	if (!err) {
+		if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) {
+			WARN_ON_ONCE(ds->ds_clp ||
+				!nfs4_test_deviceid_unavailable(devid));
+			return -EINVAL;
+		}
+		err = nfs_client_init_status(ds->ds_clp);
+	}
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 54e0f9f2dd94..dc69314d455e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2315,18 +2315,17 @@ inline void nfs_initialise_sb(struct super_block *sb)
 		sb->s_blocksize = nfs_block_bits(server->wsize,
 						 &sb->s_blocksize_bits);
 
-	sb->s_bdi = &server->backing_dev_info;
-
 	nfs_super_set_maxbytes(sb, server->maxfilesize);
 }
 
 /*
  * Finish setting up an NFS2/3 superblock
  */
-void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+int nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
+	int ret;
 
 	sb->s_blocksize_bits = 0;
 	sb->s_blocksize = 0;
@@ -2344,13 +2343,21 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 	}
 
  	nfs_initialise_sb(sb);
+
+	ret = super_setup_bdi_name(sb, "%u:%u", MAJOR(server->s_dev),
+				   MINOR(server->s_dev));
+	if (ret)
+		return ret;
+	sb->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
+	return 0;
+
 }
 EXPORT_SYMBOL_GPL(nfs_fill_super);
 
 /*
  * Finish setting up a cloned NFS2/3/4 superblock
  */
-void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+int nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2370,6 +2377,10 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 	}
 
  	nfs_initialise_sb(sb);
+
+	sb->s_bdi = bdi_get(old_sb->s_bdi);
+
+	return 0;
 }
 
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
@@ -2522,11 +2533,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
 }
 #endif
 
-static int nfs_bdi_register(struct nfs_server *server)
-{
-	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
-}
-
 int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
 			struct nfs_mount_info *mount_info)
 {
@@ -2594,17 +2600,14 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		nfs_free_server(server);
 		server = NULL;
 	} else {
-		error = nfs_bdi_register(server);
-		if (error) {
-			mntroot = ERR_PTR(error);
-			goto error_splat_super;
-		}
 		server->super = s;
 	}
 
 	if (!s->s_root) {
 		/* initial superblock/root creation */
-		mount_info->fill_super(s, mount_info);
+		error = mount_info->fill_super(s, mount_info);
+		if (error)
+			goto error_splat_super;
 		nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
 	}
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e75b056f46f4..cc341fc7fd44 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -263,16 +263,15 @@ int nfs_congestion_kb;
 
 static void nfs_set_page_writeback(struct page *page)
 {
-	struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host);
+	struct inode *inode = page_file_mapping(page)->host;
+	struct nfs_server *nfss = NFS_SERVER(inode);
 	int ret = test_set_page_writeback(page);
 
 	WARN_ON_ONCE(ret != 0);
 
 	if (atomic_long_inc_return(&nfss->writeback) >
-			NFS_CONGESTION_ON_THRESH) {
-		set_bdi_congested(&nfss->backing_dev_info,
-					BLK_RW_ASYNC);
-	}
+			NFS_CONGESTION_ON_THRESH)
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 }
 
 static void nfs_end_page_writeback(struct nfs_page *req)
@@ -285,7 +284,7 @@ static void nfs_end_page_writeback(struct nfs_page *req)
 
 	end_page_writeback(req->wb_page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+		clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 }
 
 
@@ -1784,7 +1783,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 			(long long)req_offset(req));
 		if (status < 0) {
 			nfs_context_set_write_error(req->wb_context, status);
-			nfs_inode_remove_request(req);
+			if (req->wb_page)
+				nfs_inode_remove_request(req);
 			dprintk_cont(", error = %d\n", status);
 			goto next;
 		}
@@ -1793,7 +1793,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		 * returned by the server against all stored verfs. */
 		if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
 			/* We have a match */
-			nfs_inode_remove_request(req);
+			if (req->wb_page)
+				nfs_inode_remove_request(req);
 			dprintk_cont(" OK\n");
 			goto next;
 		}
@@ -1806,7 +1807,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 	}
 	nfss = NFS_SERVER(data->inode);
 	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+		clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC);
 
 	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
 	nfs_commit_end(cinfo.mds);
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 92b4b41d19d2..fb5213afc854 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -242,10 +242,11 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 	req->cmd[4] = bufflen & 0xff;
 	req->cmd_len = COMMAND_SIZE(INQUIRY);
 
-	error = blk_execute_rq(rq->q, NULL, rq, 1);
-	if (error) {
+	blk_execute_rq(rq->q, NULL, rq, 1);
+	if (req->result) {
 		pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
-			rq->errors);
+			req->result);
+		error = -EIO;
 		goto out_put_request;
 	}
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index dba2ff8eaa68..452334694a5d 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -358,6 +358,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 {
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
+	struct kvec *head = rqstp->rq_arg.head;
+	struct kvec *tail = rqstp->rq_arg.tail;
 
 	p = decode_fh(p, &args->fh);
 	if (!p)
@@ -367,6 +369,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	args->count = ntohl(*p++);
 	args->stable = ntohl(*p++);
 	len = args->len = ntohl(*p++);
+	if ((void *)p > head->iov_base + head->iov_len)
+		return 0;
 	/*
 	 * The count must equal the amount of data passed.
 	 */
@@ -377,9 +381,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		+ rqstp->rq_arg.tail[0].iov_len - hdr;
+	hdr = (void*)p - head->iov_base;
+	dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr;
 	/*
 	 * Round the length of the data which was specified up to
 	 * the next multiple of XDR units and then compare that
@@ -396,7 +399,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		len = args->len = max_blocksize;
 	}
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
@@ -471,6 +474,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 	/* first copy and check from the first page */
 	old = (char*)p;
 	vec = &rqstp->rq_arg.head[0];
+	if ((void *)old > vec->iov_base + vec->iov_len)
+		return 0;
 	avail = vec->iov_len - (old - (char*)vec->iov_base);
 	while (len && avail && *old) {
 		*new++ = *old++;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index cbeeda1e94a2..d86031b6ad79 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2489,7 +2489,7 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
 
 int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	if (op->opnum == OP_ILLEGAL)
+	if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp)
 		return op_encode_hdr_size * sizeof(__be32);
 
 	BUG_ON(OPDESC(op)->op_rsize_bop == NULL);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 73e75ac90525..8bf8f667a8cf 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -538,13 +538,21 @@ out_free:
 
 static ssize_t
 nfsd_print_version_support(char *buf, int remaining, const char *sep,
-		unsigned vers, unsigned minor)
+		unsigned vers, int minor)
 {
-	const char *format = (minor == 0) ? "%s%c%u" : "%s%c%u.%u";
+	const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u";
 	bool supported = !!nfsd_vers(vers, NFSD_TEST);
 
-	if (vers == 4 && !nfsd_minorversion(minor, NFSD_TEST))
+	if (vers == 4 && minor >= 0 &&
+	    !nfsd_minorversion(minor, NFSD_TEST))
 		supported = false;
+	if (minor == 0 && supported)
+		/*
+		 * special case for backward compatability.
+		 * +4.0 is never reported, it is implied by
+		 * +4, unless -4.0 is present.
+		 */
+		return 0;
 	return snprintf(buf, remaining, format, sep,
 			supported ? '+' : '-', vers, minor);
 }
@@ -554,7 +562,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 	char *mesg = buf;
 	char *vers, *minorp, sign;
 	int len, num, remaining;
-	unsigned minor;
 	ssize_t tlen = 0;
 	char *sep;
 	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
@@ -575,6 +582,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 		if (len <= 0) return -EINVAL;
 		do {
 			enum vers_op cmd;
+			unsigned minor;
 			sign = *vers;
 			if (sign == '+' || sign == '-')
 				num = simple_strtol((vers+1), &minorp, 0);
@@ -585,8 +593,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 					return -EINVAL;
 				if (kstrtouint(minorp+1, 0, &minor) < 0)
 					return -EINVAL;
-			} else
-				minor = 0;
+			}
+
 			cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET;
 			switch(num) {
 			case 2:
@@ -594,8 +602,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 				nfsd_vers(num, cmd);
 				break;
 			case 4:
-				if (nfsd_minorversion(minor, cmd) >= 0)
-					break;
+				if (*minorp == '.') {
+					if (nfsd_minorversion(minor, cmd) < 0)
+						return -EINVAL;
+				} else if ((cmd == NFSD_SET) != nfsd_vers(num, NFSD_TEST)) {
+					/*
+					 * Either we have +4 and no minors are enabled,
+					 * or we have -4 and at least one minor is enabled.
+					 * In either case, propagate 'cmd' to all minors.
+					 */
+					minor = 0;
+					while (nfsd_minorversion(minor, cmd) >= 0)
+						minor++;
+				}
+				break;
 			default:
 				return -EINVAL;
 			}
@@ -612,9 +632,11 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 	sep = "";
 	remaining = SIMPLE_TRANSACTION_LIMIT;
 	for (num=2 ; num <= 4 ; num++) {
+		int minor;
 		if (!nfsd_vers(num, NFSD_AVAIL))
 			continue;
-		minor = 0;
+
+		minor = -1;
 		do {
 			len = nfsd_print_version_support(buf, remaining,
 					sep, num, minor);
@@ -624,7 +646,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 			buf += len;
 			tlen += len;
 			minor++;
-			sep = " ";
+			if (len)
+				sep = " ";
 		} while (num == 4 && minor <= NFSD_SUPPORTED_MINOR_VERSION);
 	}
 out:
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index fa82b7707e85..03a7e9da4da0 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -786,6 +786,7 @@ nfserrno (int errno)
 		{ nfserr_serverfault, -ESERVERFAULT },
 		{ nfserr_serverfault, -ENFILE },
 		{ nfserr_io, -EUCLEAN },
+		{ nfserr_perm, -ENOKEY },
 	};
 	int	i;
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 786a4a2cb2d7..59979f0bbd4b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -167,7 +167,8 @@ nfsd_adjust_nfsd_versions4(void)
 
 int nfsd_minorversion(u32 minorversion, enum vers_op change)
 {
-	if (minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+	if (minorversion > NFSD_SUPPORTED_MINOR_VERSION &&
+	    change != NFSD_AVAIL)
 		return -1;
 	switch(change) {
 	case NFSD_SET:
@@ -415,23 +416,20 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 
 void nfsd_reset_versions(void)
 {
-	int found_one = 0;
 	int i;
 
-	for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) {
-		if (nfsd_program.pg_vers[i])
-			found_one = 1;
-	}
+	for (i = 0; i < NFSD_NRVERS; i++)
+		if (nfsd_vers(i, NFSD_TEST))
+			return;
 
-	if (!found_one) {
-		for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++)
-			nfsd_program.pg_vers[i] = nfsd_version[i];
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
-		for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++)
-			nfsd_acl_program.pg_vers[i] =
-				nfsd_acl_version[i];
-#endif
-	}
+	for (i = 0; i < NFSD_NRVERS; i++)
+		if (i != 4)
+			nfsd_vers(i, NFSD_SET);
+		else {
+			int minor = 0;
+			while (nfsd_minorversion(minor, NFSD_SET) >= 0)
+				minor++;
+		}
 }
 
 /*
@@ -749,6 +747,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
 	return nfserr;
 }
 
+/*
+ * A write procedure can have a large argument, and a read procedure can
+ * have a large reply, but no NFSv2 or NFSv3 procedure has argument and
+ * reply that can both be larger than a page.  The xdr code has taken
+ * advantage of this assumption to be a sloppy about bounds checking in
+ * some cases.  Pending a rewrite of the NFSv2/v3 xdr code to fix that
+ * problem, we enforce these assumptions here:
+ */
+static bool nfs_request_too_big(struct svc_rqst *rqstp,
+				struct svc_procedure *proc)
+{
+	/*
+	 * The ACL code has more careful bounds-checking and is not
+	 * susceptible to this problem:
+	 */
+	if (rqstp->rq_prog != NFS_PROGRAM)
+		return false;
+	/*
+	 * Ditto NFSv4 (which can in theory have argument and reply both
+	 * more than a page):
+	 */
+	if (rqstp->rq_vers >= 4)
+		return false;
+	/* The reply will be small, we're OK: */
+	if (proc->pc_xdrressize > 0 &&
+	    proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE))
+		return false;
+
+	return rqstp->rq_arg.len > PAGE_SIZE;
+}
+
 int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
@@ -761,6 +790,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 				rqstp->rq_vers, rqstp->rq_proc);
 	proc = rqstp->rq_procinfo;
 
+	if (nfs_request_too_big(rqstp, proc)) {
+		dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
+		*statp = rpc_garbage_args;
+		return 1;
+	}
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
 	 * (necessary in the NFSv4.0 compound case)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 41b468a6a90f..de07ff625777 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd_writeargs *args)
 {
 	unsigned int len, hdr, dlen;
+	struct kvec *head = rqstp->rq_arg.head;
 	int v;
 
 	p = decode_fh(p, &args->fh);
@@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	if (hdr > head->iov_len)
+		return 0;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 
 	/*
 	 * Round the length of the data which was specified up to
@@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		return 0;
 
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 19d50f600e8d..9aaf6ca77569 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1004,7 +1004,7 @@ out_nfserr:
 	else
 		err = nfserrno(host_err);
 	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
-		tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
+		current_restore_flags(pflags, PF_LESS_THROTTLE);
 	return err;
 }
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index e1872f36147f..926682981d61 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info;
+	sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi);
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 1656843e87d2..323f492e0822 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -91,6 +91,7 @@ slow:
 		return ERR_PTR(-ENOMEM);
 	}
 	d_instantiate(dentry, inode);
+	dentry->d_flags |= DCACHE_RCUACCESS;
 	dentry->d_fsdata = (void *)ns->ops;
 	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
 	if (d) {
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 4348027384f5..5b51c31c892d 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1460,27 +1460,10 @@ static void o2net_rx_until_empty(struct work_struct *work)
 
 static int o2net_set_nodelay(struct socket *sock)
 {
-	int ret, val = 1;
-	mm_segment_t oldfs;
+	int val = 1;
 
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-
-	/*
-	 * Dear unsuspecting programmer,
-	 *
-	 * Don't use sock_setsockopt() for SOL_TCP.  It doesn't check its level
-	 * argument and assumes SOL_SOCKET so, say, your TCP_NODELAY will
-	 * silently turn into SO_DEBUG.
-	 *
-	 * Yours,
-	 * Keeper of hilariously fragile interfaces.
-	 */
-	ret = sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY,
-				    (char __user *)&val, sizeof(val));
-
-	set_fs(oldfs);
-	return ret;
+	return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+				    (void *)&val, sizeof(val));
 }
 
 static int o2net_set_usertimeout(struct socket *sock)
@@ -1488,7 +1471,7 @@ static int o2net_set_usertimeout(struct socket *sock)
 	int user_timeout = O2NET_TCP_USER_TIMEOUT;
 
 	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-				(char *)&user_timeout, sizeof(user_timeout));
+				(void *)&user_timeout, sizeof(user_timeout));
 }
 
 static void o2net_initialize_handshake(void)
@@ -1863,7 +1846,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
 	if (ret < 0)
 		goto out;
 
diff --git a/fs/open.c b/fs/open.c
index 949cef29c3bb..4d23f729dcc6 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1078,6 +1078,26 @@ SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
 	return do_sys_open(dfd, filename, flags, mode);
 }
 
+#ifdef CONFIG_COMPAT
+/*
+ * Exactly like sys_open(), except that it doesn't set the
+ * O_LARGEFILE flag.
+ */
+COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
+{
+	return do_sys_open(AT_FDCWD, filename, flags, mode);
+}
+
+/*
+ * Exactly like sys_openat(), except that it doesn't set the
+ * O_LARGEFILE flag.
+ */
+COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
+{
+	return do_sys_open(dfd, filename, flags, mode);
+}
+#endif
+
 #ifndef __alpha__
 
 /*
diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c
index c4ab6fdf17a0..e1534c9bab16 100644
--- a/fs/orangefs/devorangefs-req.c
+++ b/fs/orangefs/devorangefs-req.c
@@ -208,14 +208,19 @@ restart:
 				continue;
 			/*
 			 * Skip ops whose filesystem we don't know about unless
-			 * it is being mounted.
+			 * it is being mounted or unmounted.  It is possible for
+			 * a filesystem we don't know about to be unmounted if
+			 * it fails to mount in the kernel after userspace has
+			 * been sent the mount request.
 			 */
 			/* XXX: is there a better way to detect this? */
 			} else if (ret == -1 &&
 				   !(op->upcall.type ==
 					ORANGEFS_VFS_OP_FS_MOUNT ||
 				     op->upcall.type ==
-					ORANGEFS_VFS_OP_GETATTR)) {
+					ORANGEFS_VFS_OP_GETATTR ||
+				     op->upcall.type ==
+					ORANGEFS_VFS_OP_FS_UMOUNT)) {
 				gossip_debug(GOSSIP_DEV_DEBUG,
 				    "orangefs: skipping op tag %llu %s\n",
 				    llu(op->tag), get_opname_string(op));
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index e6bbc8083d77..1cd37ebc4f25 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -114,7 +114,6 @@ static ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inod
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
 	struct orangefs_kernel_op_s *new_op = NULL;
-	struct iov_iter saved = *iter;
 	int buffer_index = -1;
 	ssize_t ret;
 
@@ -193,7 +192,7 @@ populate_shared_memory:
 		orangefs_bufmap_put(buffer_index);
 		buffer_index = -1;
 		if (type == ORANGEFS_IO_WRITE)
-			*iter = saved;
+			iov_iter_revert(iter, total_size);
 		gossip_debug(GOSSIP_FILE_DEBUG,
 			     "%s:going to repopulate_shared_memory.\n",
 			     __func__);
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
index 6333cbbdfef7..83b506020718 100644
--- a/fs/orangefs/orangefs-bufmap.c
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -521,13 +521,11 @@ int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter,
 		size_t n = size;
 		if (n > PAGE_SIZE)
 			n = PAGE_SIZE;
-		n = copy_page_from_iter(page, 0, n, iter);
-		if (!n)
+		if (copy_page_from_iter(page, 0, n, iter) != n)
 			return -EFAULT;
 		size -= n;
 	}
 	return 0;
-
 }
 
 /*
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 5e48a0be9761..8afac46fcc87 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -249,6 +249,7 @@ struct orangefs_sb_info_s {
 	char devname[ORANGEFS_MAX_SERVER_ADDR_LEN];
 	struct super_block *sb;
 	int mount_pending;
+	int no_list;
 	struct list_head list;
 };
 
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 67c24351a67f..629d8c917fa6 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -263,8 +263,13 @@ int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb)
 		if (!new_op)
 			return -ENOMEM;
 		new_op->upcall.req.features.features = 0;
-		ret = service_operation(new_op, "orangefs_features", 0);
-		orangefs_features = new_op->downcall.resp.features.features;
+		ret = service_operation(new_op, "orangefs_features",
+		    ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+		if (!ret)
+			orangefs_features =
+			    new_op->downcall.resp.features.features;
+		else
+			orangefs_features = 0;
 		op_release(new_op);
 	} else {
 		orangefs_features = 0;
@@ -488,7 +493,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 
 	if (ret) {
 		d = ERR_PTR(ret);
-		goto free_op;
+		goto free_sb_and_op;
 	}
 
 	/*
@@ -514,6 +519,9 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 	spin_unlock(&orangefs_superblocks_lock);
 	op_release(new_op);
 
+	/* Must be removed from the list now. */
+	ORANGEFS_SB(sb)->no_list = 0;
+
 	if (orangefs_userspace_version >= 20906) {
 		new_op = op_alloc(ORANGEFS_VFS_OP_FEATURES);
 		if (!new_op)
@@ -528,6 +536,10 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 
 	return dget(sb->s_root);
 
+free_sb_and_op:
+	/* Will call orangefs_kill_sb with sb not in list. */
+	ORANGEFS_SB(sb)->no_list = 1;
+	deactivate_locked_super(sb);
 free_op:
 	gossip_err("orangefs_mount: mount request failed with %d\n", ret);
 	if (ret == -EINVAL) {
@@ -553,12 +565,14 @@ void orangefs_kill_sb(struct super_block *sb)
 	 */
 	 orangefs_unmount_sb(sb);
 
-	/* remove the sb from our list of orangefs specific sb's */
-
-	spin_lock(&orangefs_superblocks_lock);
-	__list_del_entry(&ORANGEFS_SB(sb)->list);	/* not list_del_init */
-	ORANGEFS_SB(sb)->list.prev = NULL;
-	spin_unlock(&orangefs_superblocks_lock);
+	if (!ORANGEFS_SB(sb)->no_list) {
+		/* remove the sb from our list of orangefs specific sb's */
+		spin_lock(&orangefs_superblocks_lock);
+		/* not list_del_init */
+		__list_del_entry(&ORANGEFS_SB(sb)->list);
+		ORANGEFS_SB(sb)->list.prev = NULL;
+		spin_unlock(&orangefs_superblocks_lock);
+	}
 
 	/*
 	 * make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 1953986ee6bc..6e610a205e15 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -12,7 +12,6 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/xattr.h>
-#include <linux/sched/signal.h>
 #include "overlayfs.h"
 #include "ovl_entry.h"
 
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 8f91ec66baa3..d04ea4349909 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1074,6 +1074,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
 
 		if ((table->proc_handler == proc_dostring) ||
 		    (table->proc_handler == proc_dointvec) ||
+		    (table->proc_handler == proc_douintvec) ||
 		    (table->proc_handler == proc_dointvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_jiffies) ||
 		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f08bd31c1081..312578089544 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -900,7 +900,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
-	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+	pmd_t pmd = *pmdp;
+
+	/* See comment in change_huge_pmd() */
+	pmdp_invalidate(vma, addr, pmdp);
+	if (pmd_dirty(*pmdp))
+		pmd = pmd_mkdirty(pmd);
+	if (pmd_young(*pmdp))
+		pmd = pmd_mkyoung(pmd);
 
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
index 899d0ba0bd6c..06aab07b6bb7 100644
--- a/fs/pstore/ftrace.c
+++ b/fs/pstore/ftrace.c
@@ -37,6 +37,12 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 {
 	unsigned long flags;
 	struct pstore_ftrace_record rec = {};
+	struct pstore_record record = {
+		.type = PSTORE_TYPE_FTRACE,
+		.buf = (char *)&rec,
+		.size = sizeof(rec),
+		.psi = psinfo,
+	};
 
 	if (unlikely(oops_in_progress))
 		return;
@@ -47,8 +53,7 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 	rec.parent_ip = parent_ip;
 	pstore_ftrace_write_timestamp(&rec, pstore_ftrace_stamp++);
 	pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id());
-	psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec,
-			  0, sizeof(rec), psinfo);
+	psinfo->write(&record);
 
 	local_irq_restore(flags);
 }
@@ -117,7 +122,7 @@ void pstore_register_ftrace(void)
 {
 	struct dentry *file;
 
-	if (!psinfo->write_buf)
+	if (!psinfo->write)
 		return;
 
 	pstore_ftrace_dir = debugfs_create_dir("pstore", NULL);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 57c0646479f5..792a4e5f9226 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -47,12 +47,8 @@ static LIST_HEAD(allpstore);
 
 struct pstore_private {
 	struct list_head list;
-	struct pstore_info *psi;
-	enum pstore_type_id type;
-	u64	id;
-	int	count;
-	ssize_t	size;
-	char	data[];
+	struct pstore_record *record;
+	size_t total_size;
 };
 
 struct pstore_ftrace_seq_data {
@@ -63,6 +59,17 @@ struct pstore_ftrace_seq_data {
 
 #define REC_SIZE sizeof(struct pstore_ftrace_record)
 
+static void free_pstore_private(struct pstore_private *private)
+{
+	if (!private)
+		return;
+	if (private->record) {
+		kfree(private->record->buf);
+		kfree(private->record);
+	}
+	kfree(private);
+}
+
 static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct pstore_private *ps = s->private;
@@ -72,9 +79,9 @@ static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
 	if (!data)
 		return NULL;
 
-	data->off = ps->size % REC_SIZE;
+	data->off = ps->total_size % REC_SIZE;
 	data->off += *pos * REC_SIZE;
-	if (data->off + REC_SIZE > ps->size) {
+	if (data->off + REC_SIZE > ps->total_size) {
 		kfree(data);
 		return NULL;
 	}
@@ -94,7 +101,7 @@ static void *pstore_ftrace_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	struct pstore_ftrace_seq_data *data = v;
 
 	data->off += REC_SIZE;
-	if (data->off + REC_SIZE > ps->size)
+	if (data->off + REC_SIZE > ps->total_size)
 		return NULL;
 
 	(*pos)++;
@@ -105,7 +112,9 @@ static int pstore_ftrace_seq_show(struct seq_file *s, void *v)
 {
 	struct pstore_private *ps = s->private;
 	struct pstore_ftrace_seq_data *data = v;
-	struct pstore_ftrace_record *rec = (void *)(ps->data + data->off);
+	struct pstore_ftrace_record *rec;
+
+	rec = (struct pstore_ftrace_record *)(ps->record->buf + data->off);
 
 	seq_printf(s, "CPU:%d ts:%llu %08lx  %08lx  %pf <- %pF\n",
 		   pstore_ftrace_decode_cpu(rec),
@@ -125,7 +134,7 @@ static const struct seq_operations pstore_ftrace_seq_ops = {
 
 static int pstore_check_syslog_permissions(struct pstore_private *ps)
 {
-	switch (ps->type) {
+	switch (ps->record->type) {
 	case PSTORE_TYPE_DMESG:
 	case PSTORE_TYPE_CONSOLE:
 		return check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
@@ -141,9 +150,10 @@ static ssize_t pstore_file_read(struct file *file, char __user *userbuf,
 	struct seq_file *sf = file->private_data;
 	struct pstore_private *ps = sf->private;
 
-	if (ps->type == PSTORE_TYPE_FTRACE)
+	if (ps->record->type == PSTORE_TYPE_FTRACE)
 		return seq_read(file, userbuf, count, ppos);
-	return simple_read_from_buffer(userbuf, count, ppos, ps->data, ps->size);
+	return simple_read_from_buffer(userbuf, count, ppos,
+				       ps->record->buf, ps->total_size);
 }
 
 static int pstore_file_open(struct inode *inode, struct file *file)
@@ -157,7 +167,7 @@ static int pstore_file_open(struct inode *inode, struct file *file)
 	if (err)
 		return err;
 
-	if (ps->type == PSTORE_TYPE_FTRACE)
+	if (ps->record->type == PSTORE_TYPE_FTRACE)
 		sops = &pstore_ftrace_seq_ops;
 
 	err = seq_open(file, sops);
@@ -193,20 +203,19 @@ static const struct file_operations pstore_file_operations = {
 static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct pstore_private *p = d_inode(dentry)->i_private;
+	struct pstore_record *record = p->record;
 	int err;
 
 	err = pstore_check_syslog_permissions(p);
 	if (err)
 		return err;
 
-	if (p->psi->erase) {
-		mutex_lock(&p->psi->read_mutex);
-		p->psi->erase(p->type, p->id, p->count,
-			      d_inode(dentry)->i_ctime, p->psi);
-		mutex_unlock(&p->psi->read_mutex);
-	} else {
+	if (!record->psi->erase)
 		return -EPERM;
-	}
+
+	mutex_lock(&record->psi->read_mutex);
+	record->psi->erase(record);
+	mutex_unlock(&record->psi->read_mutex);
 
 	return simple_unlink(dir, dentry);
 }
@@ -221,7 +230,7 @@ static void pstore_evict_inode(struct inode *inode)
 		spin_lock_irqsave(&allpstore_lock, flags);
 		list_del(&p->list);
 		spin_unlock_irqrestore(&allpstore_lock, flags);
-		kfree(p);
+		free_pstore_private(p);
 	}
 }
 
@@ -302,23 +311,23 @@ bool pstore_is_mounted(void)
  * Load it up with "size" bytes of data from "buf".
  * Set the mtime & ctime to the date that this record was originally stored.
  */
-int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
-		  char *data, bool compressed, size_t size,
-		  struct timespec time, struct pstore_info *psi)
+int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 {
-	struct dentry		*root = pstore_sb->s_root;
 	struct dentry		*dentry;
 	struct inode		*inode;
 	int			rc = 0;
 	char			name[PSTORE_NAMELEN];
 	struct pstore_private	*private, *pos;
 	unsigned long		flags;
+	size_t			size = record->size + record->ecc_notice_size;
+
+	WARN_ON(!inode_is_locked(d_inode(root)));
 
 	spin_lock_irqsave(&allpstore_lock, flags);
 	list_for_each_entry(pos, &allpstore, list) {
-		if (pos->type == type &&
-		    pos->id == id &&
-		    pos->psi == psi) {
+		if (pos->record->type == record->type &&
+		    pos->record->id == record->id &&
+		    pos->record->psi == record->psi) {
 			rc = -EEXIST;
 			break;
 		}
@@ -328,72 +337,74 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 		return rc;
 
 	rc = -ENOMEM;
-	inode = pstore_get_inode(pstore_sb);
+	inode = pstore_get_inode(root->d_sb);
 	if (!inode)
 		goto fail;
 	inode->i_mode = S_IFREG | 0444;
 	inode->i_fop = &pstore_file_operations;
-	private = kmalloc(sizeof *private + size, GFP_KERNEL);
+	private = kzalloc(sizeof(*private), GFP_KERNEL);
 	if (!private)
 		goto fail_alloc;
-	private->type = type;
-	private->id = id;
-	private->count = count;
-	private->psi = psi;
+	private->record = record;
 
-	switch (type) {
+	switch (record->type) {
 	case PSTORE_TYPE_DMESG:
 		scnprintf(name, sizeof(name), "dmesg-%s-%lld%s",
-			  psname, id, compressed ? ".enc.z" : "");
+			  record->psi->name, record->id,
+			  record->compressed ? ".enc.z" : "");
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		scnprintf(name, sizeof(name), "console-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "console-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		scnprintf(name, sizeof(name), "ftrace-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "ftrace-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_MCE:
-		scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "mce-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_RTAS:
-		scnprintf(name, sizeof(name), "rtas-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "rtas-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_OF:
 		scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld",
-			  psname, id);
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_COMMON:
 		scnprintf(name, sizeof(name), "powerpc-common-%s-%lld",
-			  psname, id);
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PMSG:
-		scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "pmsg-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_OPAL:
-		sprintf(name, "powerpc-opal-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "powerpc-opal-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_UNKNOWN:
-		scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "unknown-%s-%lld",
+			  record->psi->name, record->id);
 		break;
 	default:
 		scnprintf(name, sizeof(name), "type%d-%s-%lld",
-			  type, psname, id);
+			  record->type, record->psi->name, record->id);
 		break;
 	}
 
-	inode_lock(d_inode(root));
-
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
-		goto fail_lockedalloc;
+		goto fail_private;
 
-	memcpy(private->data, data, size);
-	inode->i_size = private->size = size;
+	inode->i_size = private->total_size = size;
 
 	inode->i_private = private;
 
-	if (time.tv_sec)
-		inode->i_mtime = inode->i_ctime = time;
+	if (record->time.tv_sec)
+		inode->i_mtime = inode->i_ctime = record->time;
 
 	d_add(dentry, inode);
 
@@ -401,13 +412,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 	list_add(&private->list, &allpstore);
 	spin_unlock_irqrestore(&allpstore_lock, flags);
 
-	inode_unlock(d_inode(root));
-
 	return 0;
 
-fail_lockedalloc:
-	inode_unlock(d_inode(root));
-	kfree(private);
+fail_private:
+	free_pstore_private(private);
 fail_alloc:
 	iput(inode);
 
@@ -415,6 +423,27 @@ fail:
 	return rc;
 }
 
+/*
+ * Read all the records from the persistent store. Create
+ * files in our filesystem.  Don't warn about -EEXIST errors
+ * when we are re-scanning the backing store looking to add new
+ * error records.
+ */
+void pstore_get_records(int quiet)
+{
+	struct pstore_info *psi = psinfo;
+	struct dentry *root;
+
+	if (!psi || !pstore_sb)
+		return;
+
+	root = pstore_sb->s_root;
+
+	inode_lock(d_inode(root));
+	pstore_get_backend_records(psi, root, quiet);
+	inode_unlock(d_inode(root));
+}
+
 static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct inode *inode;
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index da416e6591c9..c416e653dc4f 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -25,10 +25,10 @@ extern struct pstore_info *psinfo;
 
 extern void	pstore_set_kmsg_bytes(int);
 extern void	pstore_get_records(int);
-extern int	pstore_mkfile(enum pstore_type_id, char *psname, u64 id,
-			      int count, char *data, bool compressed,
-			      size_t size, struct timespec time,
-			      struct pstore_info *psi);
+extern void	pstore_get_backend_records(struct pstore_info *psi,
+					   struct dentry *root, int quiet);
+extern int	pstore_mkfile(struct dentry *root,
+			      struct pstore_record *record);
 extern bool	pstore_is_mounted(void);
 
 #endif
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index efab7b64925b..d468eec9b8a6 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -267,7 +267,7 @@ static void free_zlib(void)
 	big_oops_buf_sz = 0;
 }
 
-static struct pstore_zbackend backend_zlib = {
+static const struct pstore_zbackend backend_zlib = {
 	.compress	= compress_zlib,
 	.decompress	= decompress_zlib,
 	.allocate	= allocate_zlib,
@@ -328,7 +328,7 @@ static void free_lzo(void)
 	big_oops_buf_sz = 0;
 }
 
-static struct pstore_zbackend backend_lzo = {
+static const struct pstore_zbackend backend_lzo = {
 	.compress	= compress_lzo,
 	.decompress	= decompress_lzo,
 	.allocate	= allocate_lzo,
@@ -393,7 +393,7 @@ static void free_lz4(void)
 	big_oops_buf_sz = 0;
 }
 
-static struct pstore_zbackend backend_lz4 = {
+static const struct pstore_zbackend backend_lz4 = {
 	.compress	= compress_lz4,
 	.decompress	= decompress_lz4,
 	.allocate	= allocate_lz4,
@@ -402,7 +402,7 @@ static struct pstore_zbackend backend_lz4 = {
 };
 #endif
 
-static struct pstore_zbackend *zbackend =
+static const struct pstore_zbackend *zbackend =
 #if defined(CONFIG_PSTORE_ZLIB_COMPRESS)
 	&backend_zlib;
 #elif defined(CONFIG_PSTORE_LZO_COMPRESS)
@@ -484,7 +484,6 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 {
 	unsigned long	total = 0;
 	const char	*why;
-	u64		id;
 	unsigned int	part = 1;
 	unsigned long	flags = 0;
 	int		is_locked;
@@ -506,48 +505,59 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 	oopscount++;
 	while (total < kmsg_bytes) {
 		char *dst;
-		unsigned long size;
-		int hsize;
+		size_t dst_size;
+		int header_size;
 		int zipped_len = -1;
-		size_t len;
-		bool compressed = false;
-		size_t total_len;
+		size_t dump_size;
+		struct pstore_record record = {
+			.type = PSTORE_TYPE_DMESG,
+			.count = oopscount,
+			.reason = reason,
+			.part = part,
+			.compressed = false,
+			.buf = psinfo->buf,
+			.psi = psinfo,
+		};
 
 		if (big_oops_buf && is_locked) {
 			dst = big_oops_buf;
-			size = big_oops_buf_sz;
+			dst_size = big_oops_buf_sz;
 		} else {
 			dst = psinfo->buf;
-			size = psinfo->bufsize;
+			dst_size = psinfo->bufsize;
 		}
 
-		hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount, part);
-		size -= hsize;
+		/* Write dump header. */
+		header_size = snprintf(dst, dst_size, "%s#%d Part%u\n", why,
+				 oopscount, part);
+		dst_size -= header_size;
 
-		if (!kmsg_dump_get_buffer(dumper, true, dst + hsize,
-					  size, &len))
+		/* Write dump contents. */
+		if (!kmsg_dump_get_buffer(dumper, true, dst + header_size,
+					  dst_size, &dump_size))
 			break;
 
 		if (big_oops_buf && is_locked) {
 			zipped_len = pstore_compress(dst, psinfo->buf,
-						hsize + len, psinfo->bufsize);
+						header_size + dump_size,
+						psinfo->bufsize);
 
 			if (zipped_len > 0) {
-				compressed = true;
-				total_len = zipped_len;
+				record.compressed = true;
+				record.size = zipped_len;
 			} else {
-				total_len = copy_kmsg_to_buffer(hsize, len);
+				record.size = copy_kmsg_to_buffer(header_size,
+								  dump_size);
 			}
 		} else {
-			total_len = hsize + len;
+			record.size = header_size + dump_size;
 		}
 
-		ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part,
-				    oopscount, compressed, total_len, psinfo);
+		ret = psinfo->write(&record);
 		if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted())
 			pstore_new_entry = 1;
 
-		total += total_len;
+		total += record.size;
 		part++;
 	}
 	if (is_locked)
@@ -577,8 +587,11 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 	const char *e = s + c;
 
 	while (s < e) {
+		struct pstore_record record = {
+			.type = PSTORE_TYPE_CONSOLE,
+			.psi = psinfo,
+		};
 		unsigned long flags;
-		u64 id;
 
 		if (c > psinfo->bufsize)
 			c = psinfo->bufsize;
@@ -589,8 +602,9 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 		} else {
 			spin_lock_irqsave(&psinfo->buf_lock, flags);
 		}
-		psinfo->write_buf(PSTORE_TYPE_CONSOLE, 0, &id, 0,
-				  s, 0, c, psinfo);
+		record.buf = (char *)s;
+		record.size = c;
+		psinfo->write(&record);
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 		s += c;
 		c = e - s;
@@ -618,48 +632,30 @@ static void pstore_register_console(void) {}
 static void pstore_unregister_console(void) {}
 #endif
 
-static int pstore_write_compat(enum pstore_type_id type,
-			       enum kmsg_dump_reason reason,
-			       u64 *id, unsigned int part, int count,
-			       bool compressed, size_t size,
-			       struct pstore_info *psi)
-{
-	return psi->write_buf(type, reason, id, part, psinfo->buf, compressed,
-			     size, psi);
-}
-
-static int pstore_write_buf_user_compat(enum pstore_type_id type,
-			       enum kmsg_dump_reason reason,
-			       u64 *id, unsigned int part,
-			       const char __user *buf,
-			       bool compressed, size_t size,
-			       struct pstore_info *psi)
-{
-	unsigned long flags = 0;
-	size_t i, bufsize = size;
-	long ret = 0;
-
-	if (unlikely(!access_ok(VERIFY_READ, buf, size)))
-		return -EFAULT;
-	if (bufsize > psinfo->bufsize)
-		bufsize = psinfo->bufsize;
-	spin_lock_irqsave(&psinfo->buf_lock, flags);
-	for (i = 0; i < size; ) {
-		size_t c = min(size - i, bufsize);
-
-		ret = __copy_from_user(psinfo->buf, buf + i, c);
-		if (unlikely(ret != 0)) {
-			ret = -EFAULT;
-			break;
-		}
-		ret = psi->write_buf(type, reason, id, part, psinfo->buf,
-				     compressed, c, psi);
-		if (unlikely(ret < 0))
-			break;
-		i += c;
+static int pstore_write_user_compat(struct pstore_record *record,
+				    const char __user *buf)
+{
+	int ret = 0;
+
+	if (record->buf)
+		return -EINVAL;
+
+	record->buf = kmalloc(record->size, GFP_KERNEL);
+	if (!record->buf)
+		return -ENOMEM;
+
+	if (unlikely(copy_from_user(record->buf, buf, record->size))) {
+		ret = -EFAULT;
+		goto out;
 	}
-	spin_unlock_irqrestore(&psinfo->buf_lock, flags);
-	return unlikely(ret < 0) ? ret : size;
+
+	ret = record->psi->write(record);
+
+out:
+	kfree(record->buf);
+	record->buf = NULL;
+
+	return unlikely(ret < 0) ? ret : record->size;
 }
 
 /*
@@ -673,19 +669,35 @@ int pstore_register(struct pstore_info *psi)
 {
 	struct module *owner = psi->owner;
 
-	if (backend && strcmp(backend, psi->name))
+	if (backend && strcmp(backend, psi->name)) {
+		pr_warn("ignoring unexpected backend '%s'\n", psi->name);
 		return -EPERM;
+	}
+
+	/* Sanity check flags. */
+	if (!psi->flags) {
+		pr_warn("backend '%s' must support at least one frontend\n",
+			psi->name);
+		return -EINVAL;
+	}
+
+	/* Check for required functions. */
+	if (!psi->read || !psi->write) {
+		pr_warn("backend '%s' must implement read() and write()\n",
+			psi->name);
+		return -EINVAL;
+	}
 
 	spin_lock(&pstore_lock);
 	if (psinfo) {
+		pr_warn("backend '%s' already loaded: ignoring '%s'\n",
+			psinfo->name, psi->name);
 		spin_unlock(&pstore_lock);
 		return -EBUSY;
 	}
 
-	if (!psi->write)
-		psi->write = pstore_write_compat;
-	if (!psi->write_buf_user)
-		psi->write_buf_user = pstore_write_buf_user_compat;
+	if (!psi->write_user)
+		psi->write_user = pstore_write_user_compat;
 	psinfo = psi;
 	mutex_init(&psinfo->read_mutex);
 	spin_unlock(&pstore_lock);
@@ -709,6 +721,7 @@ int pstore_register(struct pstore_info *psi)
 	if (psi->flags & PSTORE_FLAGS_PMSG)
 		pstore_register_pmsg();
 
+	/* Start watching for new records, if desired. */
 	if (pstore_update_ms >= 0) {
 		pstore_timer.expires = jiffies +
 			msecs_to_jiffies(pstore_update_ms);
@@ -721,16 +734,21 @@ int pstore_register(struct pstore_info *psi)
 	 */
 	backend = psi->name;
 
-	module_put(owner);
-
 	pr_info("Registered %s as persistent store backend\n", psi->name);
 
+	module_put(owner);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pstore_register);
 
 void pstore_unregister(struct pstore_info *psi)
 {
+	/* Stop timer and make sure all work has finished. */
+	pstore_update_ms = -1;
+	del_timer_sync(&pstore_timer);
+	flush_work(&pstore_work);
+
 	if (psi->flags & PSTORE_FLAGS_PMSG)
 		pstore_unregister_pmsg();
 	if (psi->flags & PSTORE_FLAGS_FTRACE)
@@ -747,66 +765,99 @@ void pstore_unregister(struct pstore_info *psi)
 }
 EXPORT_SYMBOL_GPL(pstore_unregister);
 
+static void decompress_record(struct pstore_record *record)
+{
+	int unzipped_len;
+	char *decompressed;
+
+	/* Only PSTORE_TYPE_DMESG support compression. */
+	if (!record->compressed || record->type != PSTORE_TYPE_DMESG) {
+		pr_warn("ignored compressed record type %d\n", record->type);
+		return;
+	}
+
+	/* No compression method has created the common buffer. */
+	if (!big_oops_buf) {
+		pr_warn("no decompression buffer allocated\n");
+		return;
+	}
+
+	unzipped_len = pstore_decompress(record->buf, big_oops_buf,
+					 record->size, big_oops_buf_sz);
+	if (unzipped_len <= 0) {
+		pr_err("decompression failed: %d\n", unzipped_len);
+		return;
+	}
+
+	/* Build new buffer for decompressed contents. */
+	decompressed = kmalloc(unzipped_len + record->ecc_notice_size,
+			       GFP_KERNEL);
+	if (!decompressed) {
+		pr_err("decompression ran out of memory\n");
+		return;
+	}
+	memcpy(decompressed, big_oops_buf, unzipped_len);
+
+	/* Append ECC notice to decompressed buffer. */
+	memcpy(decompressed + unzipped_len, record->buf + record->size,
+	       record->ecc_notice_size);
+
+	/* Swap out compresed contents with decompressed contents. */
+	kfree(record->buf);
+	record->buf = decompressed;
+	record->size = unzipped_len;
+	record->compressed = false;
+}
+
 /*
- * Read all the records from the persistent store. Create
+ * Read all the records from one persistent store backend. Create
  * files in our filesystem.  Don't warn about -EEXIST errors
  * when we are re-scanning the backing store looking to add new
  * error records.
  */
-void pstore_get_records(int quiet)
-{
-	struct pstore_info *psi = psinfo;
-	char			*buf = NULL;
-	ssize_t			size;
-	u64			id;
-	int			count;
-	enum pstore_type_id	type;
-	struct timespec		time;
-	int			failed = 0, rc;
-	bool			compressed;
-	int			unzipped_len = -1;
-	ssize_t			ecc_notice_size = 0;
-
-	if (!psi)
+void pstore_get_backend_records(struct pstore_info *psi,
+				struct dentry *root, int quiet)
+{
+	int failed = 0;
+
+	if (!psi || !root)
 		return;
 
 	mutex_lock(&psi->read_mutex);
 	if (psi->open && psi->open(psi))
 		goto out;
 
-	while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed,
-				 &ecc_notice_size, psi)) > 0) {
-		if (compressed && (type == PSTORE_TYPE_DMESG)) {
-			if (big_oops_buf)
-				unzipped_len = pstore_decompress(buf,
-							big_oops_buf, size,
-							big_oops_buf_sz);
-
-			if (unzipped_len > 0) {
-				if (ecc_notice_size)
-					memcpy(big_oops_buf + unzipped_len,
-					       buf + size, ecc_notice_size);
-				kfree(buf);
-				buf = big_oops_buf;
-				size = unzipped_len;
-				compressed = false;
-			} else {
-				pr_err("decompression failed;returned %d\n",
-				       unzipped_len);
-				compressed = true;
-			}
+	/*
+	 * Backend callback read() allocates record.buf. decompress_record()
+	 * may reallocate record.buf. On success, pstore_mkfile() will keep
+	 * the record.buf, so free it only on failure.
+	 */
+	for (;;) {
+		struct pstore_record *record;
+		int rc;
+
+		record = kzalloc(sizeof(*record), GFP_KERNEL);
+		if (!record) {
+			pr_err("out of memory creating record\n");
+			break;
+		}
+		record->psi = psi;
+
+		record->size = psi->read(record);
+
+		/* No more records left in backend? */
+		if (record->size <= 0)
+			break;
+
+		decompress_record(record);
+		rc = pstore_mkfile(root, record);
+		if (rc) {
+			/* pstore_mkfile() did not take record, so free it. */
+			kfree(record->buf);
+			kfree(record);
+			if (rc != -EEXIST || !quiet)
+				failed++;
 		}
-		rc = pstore_mkfile(type, psi->name, id, count, buf,
-				   compressed, size + ecc_notice_size,
-				   time, psi);
-		if (unzipped_len < 0) {
-			/* Free buffer other than big oops */
-			kfree(buf);
-			buf = NULL;
-		} else
-			unzipped_len = -1;
-		if (rc && (rc != -EEXIST || !quiet))
-			failed++;
 	}
 	if (psi->close)
 		psi->close(psi);
@@ -830,7 +881,9 @@ static void pstore_timefunc(unsigned long dummy)
 		schedule_work(&pstore_work);
 	}
 
-	mod_timer(&pstore_timer, jiffies + msecs_to_jiffies(pstore_update_ms));
+	if (pstore_update_ms >= 0)
+		mod_timer(&pstore_timer,
+			  jiffies + msecs_to_jiffies(pstore_update_ms));
 }
 
 module_param(backend, charp, 0444);
diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c
index 78f6176c020f..209755e0d7c8 100644
--- a/fs/pstore/pmsg.c
+++ b/fs/pstore/pmsg.c
@@ -15,7 +15,6 @@
 #include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include "internal.h"
 
 static DEFINE_MUTEX(pmsg_lock);
@@ -23,19 +22,22 @@ static DEFINE_MUTEX(pmsg_lock);
 static ssize_t write_pmsg(struct file *file, const char __user *buf,
 			  size_t count, loff_t *ppos)
 {
-	u64 id;
+	struct pstore_record record = {
+		.type = PSTORE_TYPE_PMSG,
+		.size = count,
+		.psi = psinfo,
+	};
 	int ret;
 
 	if (!count)
 		return 0;
 
-	/* check outside lock, page in any data. write_buf_user also checks */
+	/* check outside lock, page in any data. write_user also checks */
 	if (!access_ok(VERIFY_READ, buf, count))
 		return -EFAULT;
 
 	mutex_lock(&pmsg_lock);
-	ret = psinfo->write_buf_user(PSTORE_TYPE_PMSG, 0, &id, 0, buf, 0, count,
-				     psinfo);
+	ret = psinfo->write_user(&record, buf);
 	mutex_unlock(&pmsg_lock);
 	return ret ? ret : count;
 }
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 11f918d34b1e..5523df7f17ef 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -235,35 +235,34 @@ static ssize_t ftrace_log_combine(struct persistent_ram_zone *dest,
 	return 0;
 }
 
-static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
-				   int *count, struct timespec *time,
-				   char **buf, bool *compressed,
-				   ssize_t *ecc_notice_size,
-				   struct pstore_info *psi)
+static ssize_t ramoops_pstore_read(struct pstore_record *record)
 {
 	ssize_t size = 0;
-	struct ramoops_context *cxt = psi->data;
+	struct ramoops_context *cxt = record->psi->data;
 	struct persistent_ram_zone *prz = NULL;
 	int header_length = 0;
 	bool free_prz = false;
 
-	/* Ramoops headers provide time stamps for PSTORE_TYPE_DMESG, but
+	/*
+	 * Ramoops headers provide time stamps for PSTORE_TYPE_DMESG, but
 	 * PSTORE_TYPE_CONSOLE and PSTORE_TYPE_FTRACE don't currently have
 	 * valid time stamps, so it is initialized to zero.
 	 */
-	time->tv_sec = 0;
-	time->tv_nsec = 0;
-	*compressed = false;
+	record->time.tv_sec = 0;
+	record->time.tv_nsec = 0;
+	record->compressed = false;
 
 	/* Find the next valid persistent_ram_zone for DMESG */
 	while (cxt->dump_read_cnt < cxt->max_dump_cnt && !prz) {
 		prz = ramoops_get_next_prz(cxt->dprzs, &cxt->dump_read_cnt,
-					   cxt->max_dump_cnt, id, type,
+					   cxt->max_dump_cnt, &record->id,
+					   &record->type,
 					   PSTORE_TYPE_DMESG, 1);
 		if (!prz_ok(prz))
 			continue;
 		header_length = ramoops_read_kmsg_hdr(persistent_ram_old(prz),
-						      time, compressed);
+						      &record->time,
+						      &record->compressed);
 		/* Clear and skip this DMESG record if it has no valid header */
 		if (!header_length) {
 			persistent_ram_free_old(prz);
@@ -274,18 +273,20 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 
 	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt,
-					   1, id, type, PSTORE_TYPE_CONSOLE, 0);
+					   1, &record->id, &record->type,
+					   PSTORE_TYPE_CONSOLE, 0);
 
 	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt,
-					   1, id, type, PSTORE_TYPE_PMSG, 0);
+					   1, &record->id, &record->type,
+					   PSTORE_TYPE_PMSG, 0);
 
 	/* ftrace is last since it may want to dynamically allocate memory. */
 	if (!prz_ok(prz)) {
 		if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) {
 			prz = ramoops_get_next_prz(cxt->fprzs,
-					&cxt->ftrace_read_cnt, 1, id, type,
-					PSTORE_TYPE_FTRACE, 0);
+					&cxt->ftrace_read_cnt, 1, &record->id,
+					&record->type, PSTORE_TYPE_FTRACE, 0);
 		} else {
 			/*
 			 * Build a new dummy record which combines all the
@@ -302,8 +303,10 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 			while (cxt->ftrace_read_cnt < cxt->max_ftrace_cnt) {
 				prz_next = ramoops_get_next_prz(cxt->fprzs,
 						&cxt->ftrace_read_cnt,
-						cxt->max_ftrace_cnt, id,
-						type, PSTORE_TYPE_FTRACE, 0);
+						cxt->max_ftrace_cnt,
+						&record->id,
+						&record->type,
+						PSTORE_TYPE_FTRACE, 0);
 
 				if (!prz_ok(prz_next))
 					continue;
@@ -316,7 +319,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 				if (size)
 					goto out;
 			}
-			*id = 0;
+			record->id = 0;
 			prz = tmp_prz;
 		}
 	}
@@ -329,17 +332,19 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 	size = persistent_ram_old_size(prz) - header_length;
 
 	/* ECC correction notice */
-	*ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0);
+	record->ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0);
 
-	*buf = kmalloc(size + *ecc_notice_size + 1, GFP_KERNEL);
-	if (*buf == NULL) {
+	record->buf = kmalloc(size + record->ecc_notice_size + 1, GFP_KERNEL);
+	if (record->buf == NULL) {
 		size = -ENOMEM;
 		goto out;
 	}
 
-	memcpy(*buf, (char *)persistent_ram_old(prz) + header_length, size);
+	memcpy(record->buf, (char *)persistent_ram_old(prz) + header_length,
+	       size);
 
-	persistent_ram_ecc_string(prz, *buf + size, *ecc_notice_size + 1);
+	persistent_ram_ecc_string(prz, record->buf + size,
+				  record->ecc_notice_size + 1);
 
 out:
 	if (free_prz) {
@@ -373,23 +378,18 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz,
 	return len;
 }
 
-static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
-					    enum kmsg_dump_reason reason,
-					    u64 *id, unsigned int part,
-					    const char *buf,
-					    bool compressed, size_t size,
-					    struct pstore_info *psi)
+static int notrace ramoops_pstore_write(struct pstore_record *record)
 {
-	struct ramoops_context *cxt = psi->data;
+	struct ramoops_context *cxt = record->psi->data;
 	struct persistent_ram_zone *prz;
-	size_t hlen;
+	size_t size, hlen;
 
-	if (type == PSTORE_TYPE_CONSOLE) {
+	if (record->type == PSTORE_TYPE_CONSOLE) {
 		if (!cxt->cprz)
 			return -ENOMEM;
-		persistent_ram_write(cxt->cprz, buf, size);
+		persistent_ram_write(cxt->cprz, record->buf, record->size);
 		return 0;
-	} else if (type == PSTORE_TYPE_FTRACE) {
+	} else if (record->type == PSTORE_TYPE_FTRACE) {
 		int zonenum;
 
 		if (!cxt->fprzs)
@@ -402,33 +402,36 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 		else
 			zonenum = 0;
 
-		persistent_ram_write(cxt->fprzs[zonenum], buf, size);
+		persistent_ram_write(cxt->fprzs[zonenum], record->buf,
+				     record->size);
 		return 0;
-	} else if (type == PSTORE_TYPE_PMSG) {
+	} else if (record->type == PSTORE_TYPE_PMSG) {
 		pr_warn_ratelimited("PMSG shouldn't call %s\n", __func__);
 		return -EINVAL;
 	}
 
-	if (type != PSTORE_TYPE_DMESG)
+	if (record->type != PSTORE_TYPE_DMESG)
 		return -EINVAL;
 
-	/* Out of the various dmesg dump types, ramoops is currently designed
+	/*
+	 * Out of the various dmesg dump types, ramoops is currently designed
 	 * to only store crash logs, rather than storing general kernel logs.
 	 */
-	if (reason != KMSG_DUMP_OOPS &&
-	    reason != KMSG_DUMP_PANIC)
+	if (record->reason != KMSG_DUMP_OOPS &&
+	    record->reason != KMSG_DUMP_PANIC)
 		return -EINVAL;
 
 	/* Skip Oopes when configured to do so. */
-	if (reason == KMSG_DUMP_OOPS && !cxt->dump_oops)
+	if (record->reason == KMSG_DUMP_OOPS && !cxt->dump_oops)
 		return -EINVAL;
 
-	/* Explicitly only take the first part of any new crash.
+	/*
+	 * Explicitly only take the first part of any new crash.
 	 * If our buffer is larger than kmsg_bytes, this can never happen,
 	 * and if our buffer is smaller than kmsg_bytes, we don't want the
 	 * report split across multiple records.
 	 */
-	if (part != 1)
+	if (record->part != 1)
 		return -ENOSPC;
 
 	if (!cxt->dprzs)
@@ -436,53 +439,50 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 
 	prz = cxt->dprzs[cxt->dump_write_cnt];
 
-	hlen = ramoops_write_kmsg_hdr(prz, compressed);
+	/* Build header and append record contents. */
+	hlen = ramoops_write_kmsg_hdr(prz, record->compressed);
+	size = record->size;
 	if (size + hlen > prz->buffer_size)
 		size = prz->buffer_size - hlen;
-	persistent_ram_write(prz, buf, size);
+	persistent_ram_write(prz, record->buf, size);
 
 	cxt->dump_write_cnt = (cxt->dump_write_cnt + 1) % cxt->max_dump_cnt;
 
 	return 0;
 }
 
-static int notrace ramoops_pstore_write_buf_user(enum pstore_type_id type,
-						 enum kmsg_dump_reason reason,
-						 u64 *id, unsigned int part,
-						 const char __user *buf,
-						 bool compressed, size_t size,
-						 struct pstore_info *psi)
+static int notrace ramoops_pstore_write_user(struct pstore_record *record,
+					     const char __user *buf)
 {
-	if (type == PSTORE_TYPE_PMSG) {
-		struct ramoops_context *cxt = psi->data;
+	if (record->type == PSTORE_TYPE_PMSG) {
+		struct ramoops_context *cxt = record->psi->data;
 
 		if (!cxt->mprz)
 			return -ENOMEM;
-		return persistent_ram_write_user(cxt->mprz, buf, size);
+		return persistent_ram_write_user(cxt->mprz, buf, record->size);
 	}
 
 	return -EINVAL;
 }
 
-static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count,
-				struct timespec time, struct pstore_info *psi)
+static int ramoops_pstore_erase(struct pstore_record *record)
 {
-	struct ramoops_context *cxt = psi->data;
+	struct ramoops_context *cxt = record->psi->data;
 	struct persistent_ram_zone *prz;
 
-	switch (type) {
+	switch (record->type) {
 	case PSTORE_TYPE_DMESG:
-		if (id >= cxt->max_dump_cnt)
+		if (record->id >= cxt->max_dump_cnt)
 			return -EINVAL;
-		prz = cxt->dprzs[id];
+		prz = cxt->dprzs[record->id];
 		break;
 	case PSTORE_TYPE_CONSOLE:
 		prz = cxt->cprz;
 		break;
 	case PSTORE_TYPE_FTRACE:
-		if (id >= cxt->max_ftrace_cnt)
+		if (record->id >= cxt->max_ftrace_cnt)
 			return -EINVAL;
-		prz = cxt->fprzs[id];
+		prz = cxt->fprzs[record->id];
 		break;
 	case PSTORE_TYPE_PMSG:
 		prz = cxt->mprz;
@@ -503,8 +503,8 @@ static struct ramoops_context oops_cxt = {
 		.name	= "ramoops",
 		.open	= ramoops_pstore_open,
 		.read	= ramoops_pstore_read,
-		.write_buf	= ramoops_pstore_write_buf,
-		.write_buf_user	= ramoops_pstore_write_buf_user,
+		.write	= ramoops_pstore_write,
+		.write_user	= ramoops_pstore_write_user,
 		.erase	= ramoops_pstore_erase,
 	},
 };
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index bc927e30bdcc..e11672aa4575 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -532,7 +532,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 	}
 
 	/* Initialize general buffer state. */
-	prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock);
+	raw_spin_lock_init(&prz->buffer_lock);
 	prz->flags = flags;
 
 	ret = persistent_ram_buffer_map(start, size, prz, memtype);
diff --git a/fs/read_write.c b/fs/read_write.c
index c4f88afbc67f..47c1d4484df9 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -841,6 +841,81 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_COMPAT
+ssize_t compat_rw_copy_check_uvector(int type,
+		const struct compat_iovec __user *uvector, unsigned long nr_segs,
+		unsigned long fast_segs, struct iovec *fast_pointer,
+		struct iovec **ret_pointer)
+{
+	compat_ssize_t tot_len;
+	struct iovec *iov = *ret_pointer = fast_pointer;
+	ssize_t ret = 0;
+	int seg;
+
+	/*
+	 * SuS says "The readv() function *may* fail if the iovcnt argument
+	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+	 * traditionally returned zero for zero segments, so...
+	 */
+	if (nr_segs == 0)
+		goto out;
+
+	ret = -EINVAL;
+	if (nr_segs > UIO_MAXIOV)
+		goto out;
+	if (nr_segs > fast_segs) {
+		ret = -ENOMEM;
+		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
+		if (iov == NULL)
+			goto out;
+	}
+	*ret_pointer = iov;
+
+	ret = -EFAULT;
+	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+		goto out;
+
+	/*
+	 * Single unix specification:
+	 * We should -EINVAL if an element length is not >= 0 and fitting an
+	 * ssize_t.
+	 *
+	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
+	 * no overflow possibility.
+	 */
+	tot_len = 0;
+	ret = -EINVAL;
+	for (seg = 0; seg < nr_segs; seg++) {
+		compat_uptr_t buf;
+		compat_ssize_t len;
+
+		if (__get_user(len, &uvector->iov_len) ||
+		   __get_user(buf, &uvector->iov_base)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
+			goto out;
+		if (type >= 0 &&
+		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len > MAX_RW_COUNT - tot_len)
+			len = MAX_RW_COUNT - tot_len;
+		tot_len += len;
+		iov->iov_base = compat_ptr(buf);
+		iov->iov_len = (compat_size_t) len;
+		uvector++;
+		iov++;
+	}
+	ret = tot_len;
+
+out:
+	return ret;
+}
+#endif
+
 static ssize_t __do_readv_writev(int type, struct file *file,
 				 struct iov_iter *iter, loff_t *pos, int flags)
 {
diff --git a/fs/readdir.c b/fs/readdir.c
index 0e8a7f355f7a..89659549c09d 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -18,6 +18,7 @@
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
+#include <linux/compat.h>
 
 #include <linux/uaccess.h>
 
@@ -324,3 +325,167 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	fdput_pos(f);
 	return error;
 }
+
+#ifdef CONFIG_COMPAT
+struct compat_old_linux_dirent {
+	compat_ulong_t	d_ino;
+	compat_ulong_t	d_offset;
+	unsigned short	d_namlen;
+	char		d_name[1];
+};
+
+struct compat_readdir_callback {
+	struct dir_context ctx;
+	struct compat_old_linux_dirent __user *dirent;
+	int result;
+};
+
+static int compat_fillonedir(struct dir_context *ctx, const char *name,
+			     int namlen, loff_t offset, u64 ino,
+			     unsigned int d_type)
+{
+	struct compat_readdir_callback *buf =
+		container_of(ctx, struct compat_readdir_callback, ctx);
+	struct compat_old_linux_dirent __user *dirent;
+	compat_ulong_t d_ino;
+
+	if (buf->result)
+		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
+		buf->result = -EOVERFLOW;
+		return -EOVERFLOW;
+	}
+	buf->result++;
+	dirent = buf->dirent;
+	if (!access_ok(VERIFY_WRITE, dirent,
+			(unsigned long)(dirent->d_name + namlen + 1) -
+				(unsigned long)dirent))
+		goto efault;
+	if (	__put_user(d_ino, &dirent->d_ino) ||
+		__put_user(offset, &dirent->d_offset) ||
+		__put_user(namlen, &dirent->d_namlen) ||
+		__copy_to_user(dirent->d_name, name, namlen) ||
+		__put_user(0, dirent->d_name + namlen))
+		goto efault;
+	return 0;
+efault:
+	buf->result = -EFAULT;
+	return -EFAULT;
+}
+
+COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
+		struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
+{
+	int error;
+	struct fd f = fdget_pos(fd);
+	struct compat_readdir_callback buf = {
+		.ctx.actor = compat_fillonedir,
+		.dirent = dirent
+	};
+
+	if (!f.file)
+		return -EBADF;
+
+	error = iterate_dir(f.file, &buf.ctx);
+	if (buf.result)
+		error = buf.result;
+
+	fdput_pos(f);
+	return error;
+}
+
+struct compat_linux_dirent {
+	compat_ulong_t	d_ino;
+	compat_ulong_t	d_off;
+	unsigned short	d_reclen;
+	char		d_name[1];
+};
+
+struct compat_getdents_callback {
+	struct dir_context ctx;
+	struct compat_linux_dirent __user *current_dir;
+	struct compat_linux_dirent __user *previous;
+	int count;
+	int error;
+};
+
+static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
+		loff_t offset, u64 ino, unsigned int d_type)
+{
+	struct compat_linux_dirent __user * dirent;
+	struct compat_getdents_callback *buf =
+		container_of(ctx, struct compat_getdents_callback, ctx);
+	compat_ulong_t d_ino;
+	int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
+		namlen + 2, sizeof(compat_long_t));
+
+	buf->error = -EINVAL;	/* only used if we fail.. */
+	if (reclen > buf->count)
+		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
+		buf->error = -EOVERFLOW;
+		return -EOVERFLOW;
+	}
+	dirent = buf->previous;
+	if (dirent) {
+		if (signal_pending(current))
+			return -EINTR;
+		if (__put_user(offset, &dirent->d_off))
+			goto efault;
+	}
+	dirent = buf->current_dir;
+	if (__put_user(d_ino, &dirent->d_ino))
+		goto efault;
+	if (__put_user(reclen, &dirent->d_reclen))
+		goto efault;
+	if (copy_to_user(dirent->d_name, name, namlen))
+		goto efault;
+	if (__put_user(0, dirent->d_name + namlen))
+		goto efault;
+	if (__put_user(d_type, (char  __user *) dirent + reclen - 1))
+		goto efault;
+	buf->previous = dirent;
+	dirent = (void __user *)dirent + reclen;
+	buf->current_dir = dirent;
+	buf->count -= reclen;
+	return 0;
+efault:
+	buf->error = -EFAULT;
+	return -EFAULT;
+}
+
+COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
+		struct compat_linux_dirent __user *, dirent, unsigned int, count)
+{
+	struct fd f;
+	struct compat_linux_dirent __user * lastdirent;
+	struct compat_getdents_callback buf = {
+		.ctx.actor = compat_filldir,
+		.current_dir = dirent,
+		.count = count
+	};
+	int error;
+
+	if (!access_ok(VERIFY_WRITE, dirent, count))
+		return -EFAULT;
+
+	f = fdget_pos(fd);
+	if (!f.file)
+		return -EBADF;
+
+	error = iterate_dir(f.file, &buf.ctx);
+	if (error >= 0)
+		error = buf.error;
+	lastdirent = buf.previous;
+	if (lastdirent) {
+		if (put_user(buf.ctx.pos, &lastdirent->d_off))
+			error = -EFAULT;
+		else
+			error = count - buf.count;
+	}
+	fdput_pos(f);
+	return error;
+}
+#endif
diff --git a/fs/select.c b/fs/select.c
index e2112270d75a..bd4b2ccfd346 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -338,6 +338,53 @@ sticky:
 	return ret;
 }
 
+/*
+ * Scalable version of the fd_set.
+ */
+
+typedef struct {
+	unsigned long *in, *out, *ex;
+	unsigned long *res_in, *res_out, *res_ex;
+} fd_set_bits;
+
+/*
+ * How many longwords for "nr" bits?
+ */
+#define FDS_BITPERLONG	(8*sizeof(long))
+#define FDS_LONGS(nr)	(((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
+#define FDS_BYTES(nr)	(FDS_LONGS(nr)*sizeof(long))
+
+/*
+ * We do a VERIFY_WRITE here even though we are only reading this time:
+ * we'll write to it eventually..
+ *
+ * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
+ */
+static inline
+int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
+{
+	nr = FDS_BYTES(nr);
+	if (ufdset)
+		return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
+
+	memset(fdset, 0, nr);
+	return 0;
+}
+
+static inline unsigned long __must_check
+set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
+{
+	if (ufdset)
+		return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
+	return 0;
+}
+
+static inline
+void zero_fd_set(unsigned long nr, unsigned long *fdset)
+{
+	memset(fdset, 0, FDS_BYTES(nr));
+}
+
 #define FDS_IN(fds, n)		(fds->in + n)
 #define FDS_OUT(fds, n)		(fds->out + n)
 #define FDS_EX(fds, n)		(fds->ex + n)
@@ -401,7 +448,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
 		wait->_key |= POLLOUT_SET;
 }
 
-int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
+static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 {
 	ktime_t expire, *to = NULL;
 	struct poll_wqueues table;
@@ -409,7 +456,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 	int retval, i, timed_out = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	rcu_read_lock();
 	retval = max_select_fd(n, fds);
@@ -512,11 +559,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
@@ -800,7 +847,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 	int timed_out = 0, count = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	/* Optimise the no-wait case */
 	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -853,11 +900,11 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
@@ -881,7 +928,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list))  / \
 			sizeof(struct pollfd))
 
-int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
+static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 		struct timespec64 *end_time)
 {
 	struct poll_wqueues table;
@@ -1053,3 +1100,373 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+#define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
+
+static
+int compat_poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+				      int timeval, int ret)
+{
+	struct timespec ts;
+
+	if (!p)
+		return ret;
+
+	if (current->personality & STICKY_TIMEOUTS)
+		goto sticky;
+
+	/* No update for zero timeout */
+	if (!end_time->tv_sec && !end_time->tv_nsec)
+		return ret;
+
+	ktime_get_ts(&ts);
+	ts = timespec_sub(*end_time, ts);
+	if (ts.tv_sec < 0)
+		ts.tv_sec = ts.tv_nsec = 0;
+
+	if (timeval) {
+		struct compat_timeval rtv;
+
+		rtv.tv_sec = ts.tv_sec;
+		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+		if (!copy_to_user(p, &rtv, sizeof(rtv)))
+			return ret;
+	} else {
+		struct compat_timespec rts;
+
+		rts.tv_sec = ts.tv_sec;
+		rts.tv_nsec = ts.tv_nsec;
+
+		if (!copy_to_user(p, &rts, sizeof(rts)))
+			return ret;
+	}
+	/*
+	 * If an application puts its timeval in read-only memory, we
+	 * don't want the Linux-specific update to the timeval to
+	 * cause a fault after the select has completed
+	 * successfully. However, because we're not updating the
+	 * timeval, we can't restart the system call.
+	 */
+
+sticky:
+	if (ret == -ERESTARTNOHAND)
+		ret = -EINTR;
+	return ret;
+}
+
+/*
+ * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
+ * 64-bit unsigned longs.
+ */
+static
+int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
+			unsigned long *fdset)
+{
+	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
+	if (ufdset) {
+		unsigned long odd;
+
+		if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t)))
+			return -EFAULT;
+
+		odd = nr & 1UL;
+		nr &= ~1UL;
+		while (nr) {
+			unsigned long h, l;
+			if (__get_user(l, ufdset) || __get_user(h, ufdset+1))
+				return -EFAULT;
+			ufdset += 2;
+			*fdset++ = h << 32 | l;
+			nr -= 2;
+		}
+		if (odd && __get_user(*fdset, ufdset))
+			return -EFAULT;
+	} else {
+		/* Tricky, must clear full unsigned long in the
+		 * kernel fdset at the end, this makes sure that
+		 * actually happens.
+		 */
+		memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t));
+	}
+	return 0;
+}
+
+static
+int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
+		      unsigned long *fdset)
+{
+	unsigned long odd;
+	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
+
+	if (!ufdset)
+		return 0;
+
+	odd = nr & 1UL;
+	nr &= ~1UL;
+	while (nr) {
+		unsigned long h, l;
+		l = *fdset++;
+		h = l >> 32;
+		if (__put_user(l, ufdset) || __put_user(h, ufdset+1))
+			return -EFAULT;
+		ufdset += 2;
+		nr -= 2;
+	}
+	if (odd && __put_user(*fdset, ufdset))
+		return -EFAULT;
+	return 0;
+}
+
+
+/*
+ * This is a virtual copy of sys_select from fs/select.c and probably
+ * should be compared to it from time to time
+ */
+
+/*
+ * We can actually return ERESTARTSYS instead of EINTR, but I'd
+ * like to be certain this leads to no problems. So I return
+ * EINTR just for safety.
+ *
+ * Update: ERESTARTSYS breaks at least the xview clock binary, so
+ * I'm trying ERESTARTNOHAND which restart only when you want to.
+ */
+static int compat_core_sys_select(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct timespec *end_time)
+{
+	fd_set_bits fds;
+	void *bits;
+	int size, max_fds, ret = -EINVAL;
+	struct fdtable *fdt;
+	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
+
+	if (n < 0)
+		goto out_nofds;
+
+	/* max_fds can increase, so grab it once to avoid race */
+	rcu_read_lock();
+	fdt = files_fdtable(current->files);
+	max_fds = fdt->max_fds;
+	rcu_read_unlock();
+	if (n > max_fds)
+		n = max_fds;
+
+	/*
+	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
+	 * since we used fdset we need to allocate memory in units of
+	 * long-words.
+	 */
+	size = FDS_BYTES(n);
+	bits = stack_fds;
+	if (size > sizeof(stack_fds) / 6) {
+		bits = kmalloc(6 * size, GFP_KERNEL);
+		ret = -ENOMEM;
+		if (!bits)
+			goto out_nofds;
+	}
+	fds.in      = (unsigned long *)  bits;
+	fds.out     = (unsigned long *) (bits +   size);
+	fds.ex      = (unsigned long *) (bits + 2*size);
+	fds.res_in  = (unsigned long *) (bits + 3*size);
+	fds.res_out = (unsigned long *) (bits + 4*size);
+	fds.res_ex  = (unsigned long *) (bits + 5*size);
+
+	if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
+	    (ret = compat_get_fd_set(n, outp, fds.out)) ||
+	    (ret = compat_get_fd_set(n, exp, fds.ex)))
+		goto out;
+	zero_fd_set(n, fds.res_in);
+	zero_fd_set(n, fds.res_out);
+	zero_fd_set(n, fds.res_ex);
+
+	ret = do_select(n, &fds, end_time);
+
+	if (ret < 0)
+		goto out;
+	if (!ret) {
+		ret = -ERESTARTNOHAND;
+		if (signal_pending(current))
+			goto out;
+		ret = 0;
+	}
+
+	if (compat_set_fd_set(n, inp, fds.res_in) ||
+	    compat_set_fd_set(n, outp, fds.res_out) ||
+	    compat_set_fd_set(n, exp, fds.res_ex))
+		ret = -EFAULT;
+out:
+	if (bits != stack_fds)
+		kfree(bits);
+out_nofds:
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timeval __user *, tvp)
+{
+	struct timespec end_time, *to = NULL;
+	struct compat_timeval tv;
+	int ret;
+
+	if (tvp) {
+		if (copy_from_user(&tv, tvp, sizeof(tv)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to,
+				tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
+				(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
+			return -EINVAL;
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = compat_poll_select_copy_remaining(&end_time, tvp, 1, ret);
+
+	return ret;
+}
+
+struct compat_sel_arg_struct {
+	compat_ulong_t n;
+	compat_uptr_t inp;
+	compat_uptr_t outp;
+	compat_uptr_t exp;
+	compat_uptr_t tvp;
+};
+
+COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
+{
+	struct compat_sel_arg_struct a;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		return -EFAULT;
+	return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp),
+				 compat_ptr(a.exp), compat_ptr(a.tvp));
+}
+
+static long do_compat_pselect(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
+	compat_size_t sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
+
+	if (ret == -ERESTARTNOHAND) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+					sizeof(sigsaved));
+			set_restore_sigmask();
+		}
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timespec __user *, tsp, void __user *, sig)
+{
+	compat_size_t sigsetsize = 0;
+	compat_uptr_t up = 0;
+
+	if (sig) {
+		if (!access_ok(VERIFY_READ, sig,
+				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
+		    	__get_user(up, (compat_uptr_t __user *)sig) ||
+		    	__get_user(sigsetsize,
+				(compat_size_t __user *)(sig+sizeof(up))))
+			return -EFAULT;
+	}
+	return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up),
+				 sigsetsize);
+}
+
+COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
+	unsigned int,  nfds, struct compat_timespec __user *, tsp,
+	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_sys_poll(ufds, nfds, to);
+
+	/* We can restart this syscall, usually */
+	if (ret == -EINTR) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+				sizeof(sigsaved));
+			set_restore_sigmask();
+		}
+		ret = -ERESTARTNOHAND;
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
+
+	return ret;
+}
+#endif
diff --git a/fs/splice.c b/fs/splice.c
index 006ba50f4ece..540c4a44756c 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -247,11 +247,6 @@ ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
 }
 EXPORT_SYMBOL(add_to_pipe);
 
-void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
-{
-	put_page(spd->pages[i]);
-}
-
 /*
  * Check if we need to grow the arrays holding pages and partial page
  * descriptions.
@@ -393,7 +388,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	struct iov_iter to;
 	struct page **pages;
 	unsigned int nr_pages;
-	size_t offset, dummy, copied = 0;
+	size_t offset, base, copied = 0;
 	ssize_t res;
 	int i;
 
@@ -408,12 +403,11 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 
 	iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset);
 
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &dummy);
+	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
 	if (res <= 0)
 		return -ENOMEM;
 
-	BUG_ON(dummy);
-	nr_pages = DIV_ROUND_UP(res, PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
 
 	vec = __vec;
 	if (nr_pages > PIPE_DEF_BUFFERS) {
@@ -1359,6 +1353,8 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov,
 	struct fd f;
 	long error;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
 	if (unlikely(nr_segs > UIO_MAXIOV))
 		return -EINVAL;
 	else if (unlikely(!nr_segs))
@@ -1409,6 +1405,9 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	if (unlikely(!len))
 		return 0;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	error = -EBADF;
 	in = fdget(fd_in);
 	if (in.file) {
@@ -1737,6 +1736,9 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 	struct fd in;
 	int error;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	if (unlikely(!len))
 		return 0;
 
diff --git a/fs/stat.c b/fs/stat.c
index fa0be59340cc..f494b182c7c7 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -15,6 +15,7 @@
 #include <linux/cred.h>
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
+#include <linux/compat.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -130,9 +131,13 @@ EXPORT_SYMBOL(vfs_getattr);
 int vfs_statx_fd(unsigned int fd, struct kstat *stat,
 		 u32 request_mask, unsigned int query_flags)
 {
-	struct fd f = fdget_raw(fd);
+	struct fd f;
 	int error = -EBADF;
 
+	if (query_flags & ~KSTAT_QUERY_FLAGS)
+		return -EINVAL;
+
+	f = fdget_raw(fd);
 	if (f.file) {
 		error = vfs_getattr(&f.file->f_path, stat,
 				    request_mask, query_flags);
@@ -155,9 +160,6 @@ EXPORT_SYMBOL(vfs_statx_fd);
  * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
  * at the given name from being referenced.
  *
- * The caller must have preset stat->request_mask as for vfs_getattr().  The
- * flags are also used to load up stat->query_flags.
- *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
 int vfs_statx(int dfd, const char __user *filename, int flags,
@@ -509,58 +511,50 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
-static inline int __put_timestamp(struct timespec *kts,
-				  struct statx_timestamp __user *uts)
+static noinline_for_stack int
+cp_statx(const struct kstat *stat, struct statx __user *buffer)
 {
-	return (__put_user(kts->tv_sec,		&uts->tv_sec		) ||
-		__put_user(kts->tv_nsec,	&uts->tv_nsec		) ||
-		__put_user(0,			&uts->__reserved	));
-}
-
-/*
- * Set the statx results.
- */
-static long statx_set_result(struct kstat *stat, struct statx __user *buffer)
-{
-	uid_t uid = from_kuid_munged(current_user_ns(), stat->uid);
-	gid_t gid = from_kgid_munged(current_user_ns(), stat->gid);
-
-	if (__put_user(stat->result_mask,	&buffer->stx_mask	) ||
-	    __put_user(stat->mode,		&buffer->stx_mode	) ||
-	    __clear_user(&buffer->__spare0, sizeof(buffer->__spare0))	  ||
-	    __put_user(stat->nlink,		&buffer->stx_nlink	) ||
-	    __put_user(uid,			&buffer->stx_uid	) ||
-	    __put_user(gid,			&buffer->stx_gid	) ||
-	    __put_user(stat->attributes,	&buffer->stx_attributes	) ||
-	    __put_user(stat->blksize,		&buffer->stx_blksize	) ||
-	    __put_user(MAJOR(stat->rdev),	&buffer->stx_rdev_major	) ||
-	    __put_user(MINOR(stat->rdev),	&buffer->stx_rdev_minor	) ||
-	    __put_user(MAJOR(stat->dev),	&buffer->stx_dev_major	) ||
-	    __put_user(MINOR(stat->dev),	&buffer->stx_dev_minor	) ||
-	    __put_timestamp(&stat->atime,	&buffer->stx_atime	) ||
-	    __put_timestamp(&stat->btime,	&buffer->stx_btime	) ||
-	    __put_timestamp(&stat->ctime,	&buffer->stx_ctime	) ||
-	    __put_timestamp(&stat->mtime,	&buffer->stx_mtime	) ||
-	    __put_user(stat->ino,		&buffer->stx_ino	) ||
-	    __put_user(stat->size,		&buffer->stx_size	) ||
-	    __put_user(stat->blocks,		&buffer->stx_blocks	) ||
-	    __clear_user(&buffer->__spare1, sizeof(buffer->__spare1))	  ||
-	    __clear_user(&buffer->__spare2, sizeof(buffer->__spare2)))
-		return -EFAULT;
-
-	return 0;
+	struct statx tmp;
+
+	memset(&tmp, 0, sizeof(tmp));
+
+	tmp.stx_mask = stat->result_mask;
+	tmp.stx_blksize = stat->blksize;
+	tmp.stx_attributes = stat->attributes;
+	tmp.stx_nlink = stat->nlink;
+	tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
+	tmp.stx_mode = stat->mode;
+	tmp.stx_ino = stat->ino;
+	tmp.stx_size = stat->size;
+	tmp.stx_blocks = stat->blocks;
+	tmp.stx_attributes_mask = stat->attributes_mask;
+	tmp.stx_atime.tv_sec = stat->atime.tv_sec;
+	tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
+	tmp.stx_btime.tv_sec = stat->btime.tv_sec;
+	tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
+	tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
+	tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
+	tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
+	tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
+	tmp.stx_rdev_major = MAJOR(stat->rdev);
+	tmp.stx_rdev_minor = MINOR(stat->rdev);
+	tmp.stx_dev_major = MAJOR(stat->dev);
+	tmp.stx_dev_minor = MINOR(stat->dev);
+
+	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
 /**
  * sys_statx - System call to get enhanced stats
  * @dfd: Base directory to pathwalk from *or* fd to stat.
- * @filename: File to stat *or* NULL.
+ * @filename: File to stat or "" with AT_EMPTY_PATH
  * @flags: AT_* flags to control pathwalk.
  * @mask: Parts of statx struct actually required.
  * @buffer: Result buffer.
  *
- * Note that if filename is NULL, then it does the equivalent of fstat() using
- * dfd to indicate the file of interest.
+ * Note that fstat() can be emulated by setting dfd to the fd of interest,
+ * supplying "" as the filename and setting AT_EMPTY_PATH in the flags.
  */
 SYSCALL_DEFINE5(statx,
 		int, dfd, const char __user *, filename, unsigned, flags,
@@ -570,20 +564,103 @@ SYSCALL_DEFINE5(statx,
 	struct kstat stat;
 	int error;
 
+	if (mask & STATX__RESERVED)
+		return -EINVAL;
 	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
 		return -EINVAL;
-	if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer)))
-		return -EFAULT;
 
-	if (filename)
-		error = vfs_statx(dfd, filename, flags, &stat, mask);
-	else
-		error = vfs_statx_fd(dfd, &stat, mask, flags);
+	error = vfs_statx(dfd, filename, flags, &stat, mask);
 	if (error)
 		return error;
-	return statx_set_result(&stat, buffer);
+
+	return cp_statx(&stat, buffer);
+}
+
+#ifdef CONFIG_COMPAT
+static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
+{
+	struct compat_stat tmp;
+
+	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
+		return -EOVERFLOW;
+
+	memset(&tmp, 0, sizeof(tmp));
+	tmp.st_dev = old_encode_dev(stat->dev);
+	tmp.st_ino = stat->ino;
+	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
+		return -EOVERFLOW;
+	tmp.st_mode = stat->mode;
+	tmp.st_nlink = stat->nlink;
+	if (tmp.st_nlink != stat->nlink)
+		return -EOVERFLOW;
+	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
+	tmp.st_rdev = old_encode_dev(stat->rdev);
+	if ((u64) stat->size > MAX_NON_LFS)
+		return -EOVERFLOW;
+	tmp.st_size = stat->size;
+	tmp.st_atime = stat->atime.tv_sec;
+	tmp.st_atime_nsec = stat->atime.tv_nsec;
+	tmp.st_mtime = stat->mtime.tv_sec;
+	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
+	tmp.st_ctime = stat->ctime.tv_sec;
+	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
+	tmp.st_blocks = stat->blocks;
+	tmp.st_blksize = stat->blksize;
+	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
+COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
+		       struct compat_stat __user *, statbuf)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_stat(filename, &stat);
+	if (error)
+		return error;
+	return cp_compat_stat(&stat, statbuf);
+}
+
+COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
+		       struct compat_stat __user *, statbuf)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_lstat(filename, &stat);
+	if (error)
+		return error;
+	return cp_compat_stat(&stat, statbuf);
+}
+
+#ifndef __ARCH_WANT_STAT64
+COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
+		       const char __user *, filename,
+		       struct compat_stat __user *, statbuf, int, flag)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_fstatat(dfd, filename, &stat, flag);
+	if (error)
+		return error;
+	return cp_compat_stat(&stat, statbuf);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
+		       struct compat_stat __user *, statbuf)
+{
+	struct kstat stat;
+	int error = vfs_fstat(fd, &stat);
+
+	if (!error)
+		error = cp_compat_stat(&stat, statbuf);
+	return error;
+}
+#endif
+
 /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
 void __inode_add_bytes(struct inode *inode, loff_t bytes)
 {
diff --git a/fs/statfs.c b/fs/statfs.c
index 13ae259d4879..4e4623c7a126 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -7,6 +7,7 @@
 #include <linux/statfs.h>
 #include <linux/security.h>
 #include <linux/uaccess.h>
+#include <linux/compat.h>
 #include "internal.h"
 
 static int flags_by_mnt(int mnt_flags)
@@ -239,3 +240,142 @@ SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf)
 
 	return copy_to_user(ubuf, &tmp, sizeof(struct ustat)) ? -EFAULT : 0;
 }
+
+#ifdef CONFIG_COMPAT
+static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf)
+{
+	if (sizeof ubuf->f_blocks == 4) {
+		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
+		     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
+			return -EOVERFLOW;
+		/* f_files and f_ffree may be -1; it's okay
+		 * to stuff that into 32 bits */
+		if (kbuf->f_files != 0xffffffffffffffffULL
+		 && (kbuf->f_files & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+		if (kbuf->f_ffree != 0xffffffffffffffffULL
+		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+	}
+	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
+	    __put_user(kbuf->f_type, &ubuf->f_type) ||
+	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
+	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
+	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
+	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
+	    __put_user(kbuf->f_files, &ubuf->f_files) ||
+	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
+	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
+	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
+	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
+	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
+	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
+	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
+		return -EFAULT;
+	return 0;
+}
+
+/*
+ * The following statfs calls are copies of code from fs/statfs.c and
+ * should be checked against those from time to time
+ */
+COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
+{
+	struct kstatfs tmp;
+	int error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
+	return error;
+}
+
+COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
+{
+	struct kstatfs tmp;
+	int error = fd_statfs(fd, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
+	return error;
+}
+
+static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
+{
+	if (sizeof(ubuf->f_bsize) == 4) {
+		if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
+		     kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
+			return -EOVERFLOW;
+		/* f_files and f_ffree may be -1; it's okay
+		 * to stuff that into 32 bits */
+		if (kbuf->f_files != 0xffffffffffffffffULL
+		 && (kbuf->f_files & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+		if (kbuf->f_ffree != 0xffffffffffffffffULL
+		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+	}
+	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
+	    __put_user(kbuf->f_type, &ubuf->f_type) ||
+	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
+	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
+	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
+	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
+	    __put_user(kbuf->f_files, &ubuf->f_files) ||
+	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
+	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
+	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
+	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
+	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
+	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
+	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
+		return -EFAULT;
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	struct kstatfs tmp;
+	int error;
+
+	if (sz != sizeof(*buf))
+		return -EINVAL;
+
+	error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
+	return error;
+}
+
+COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	struct kstatfs tmp;
+	int error;
+
+	if (sz != sizeof(*buf))
+		return -EINVAL;
+
+	error = fd_statfs(fd, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
+	return error;
+}
+
+/*
+ * This is a copy of sys_ustat, just dealing with a structure layout.
+ * Given how simple this syscall is that apporach is more maintainable
+ * than the various conversion hacks.
+ */
+COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
+{
+	struct compat_ustat tmp;
+	struct kstatfs sbuf;
+	int err = vfs_ustat(new_decode_dev(dev), &sbuf);
+	if (err)
+		return err;
+
+	memset(&tmp, 0, sizeof(struct compat_ustat));
+	tmp.f_tfree = sbuf.f_bfree;
+	tmp.f_tinode = sbuf.f_ffree;
+	if (copy_to_user(u, &tmp, sizeof(struct compat_ustat)))
+		return -EFAULT;
+	return 0;
+}
+#endif
diff --git a/fs/super.c b/fs/super.c
index b8b6a086c03b..adb0c0de428c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -446,6 +446,10 @@ void generic_shutdown_super(struct super_block *sb)
 	hlist_del_init(&sb->s_instances);
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
+	if (sb->s_bdi != &noop_backing_dev_info) {
+		bdi_put(sb->s_bdi);
+		sb->s_bdi = &noop_backing_dev_info;
+	}
 }
 
 EXPORT_SYMBOL(generic_shutdown_super);
@@ -1049,12 +1053,8 @@ static int set_bdev_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
+	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 
-	/*
-	 * We set the bdi here to the queue backing, file systems can
-	 * overwrite this in ->fill_super()
-	 */
-	s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
@@ -1256,6 +1256,49 @@ out:
 }
 
 /*
+ * Setup private BDI for given superblock. It gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
+{
+	struct backing_dev_info *bdi;
+	int err;
+	va_list args;
+
+	bdi = bdi_alloc(GFP_KERNEL);
+	if (!bdi)
+		return -ENOMEM;
+
+	bdi->name = sb->s_type->name;
+
+	va_start(args, fmt);
+	err = bdi_register_va(bdi, fmt, args);
+	va_end(args);
+	if (err) {
+		bdi_put(bdi);
+		return err;
+	}
+	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
+	sb->s_bdi = bdi;
+
+	return 0;
+}
+EXPORT_SYMBOL(super_setup_bdi_name);
+
+/*
+ * Setup private BDI for given superblock. I gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi(struct super_block *sb)
+{
+	static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
+	return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
+				    atomic_long_inc_return(&bdi_seq));
+}
+EXPORT_SYMBOL(super_setup_bdi);
+
+/*
  * This is an internal function, please use sb_end_{write,pagefault,intwrite}
  * instead.
  */
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b803213d1307..39c75a86c67f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	struct kobject *kobj = of->kn->parent->priv;
-	size_t len;
+	ssize_t len;
 
 	/*
 	 * If buf != of->prealloc_buf, we don't know how
@@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 	if (WARN_ON_ONCE(buf != of->prealloc_buf))
 		return 0;
 	len = ops->show(kobj, of->kn->priv, buf);
+	if (len < 0)
+		return len;
 	if (pos) {
 		if (len <= pos)
 			return 0;
 		len -= pos;
 		memmove(buf, buf + pos, len);
 	}
-	return min(count, len);
+	return min_t(ssize_t, count, len);
 }
 
 /* kernfs write callback for regular sysfs files */
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 384fa759a563..c543cdb5f8ed 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -400,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	     clockid != CLOCK_BOOTTIME_ALARM))
 		return -EINVAL;
 
-	if (!capable(CAP_WAKE_ALARM) &&
-	    (clockid == CLOCK_REALTIME_ALARM ||
-	     clockid == CLOCK_BOOTTIME_ALARM))
+	if ((clockid == CLOCK_REALTIME_ALARM ||
+	     clockid == CLOCK_BOOTTIME_ALARM) &&
+	    !capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -449,7 +449,7 @@ static int do_timerfd_settime(int ufd, int flags,
 		return ret;
 	ctx = f.file->private_data;
 
-	if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) {
+	if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) {
 		fdput(f);
 		return -EPERM;
 	}
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 1e712a364680..718b749fa11a 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -32,6 +32,7 @@
 #include <linux/math64.h>
 #include <linux/uaccess.h>
 #include <linux/random.h>
+#include <linux/ctype.h>
 #include "ubifs.h"
 
 static DEFINE_SPINLOCK(dbg_lock);
@@ -286,8 +287,10 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode)
 			break;
 		}
 
-		pr_err("\t%d: %s (%s)\n",
-		       count++, dent->name, get_dent_type(dent->type));
+		pr_err("\t%d: inode %llu, type %s, len %d\n",
+		       count++, (unsigned long long) le64_to_cpu(dent->inum),
+		       get_dent_type(dent->type),
+		       le16_to_cpu(dent->nlen));
 
 		fname_name(&nm) = dent->name;
 		fname_len(&nm) = le16_to_cpu(dent->nlen);
@@ -464,7 +467,8 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node)
 			pr_err("(bad name length, not printing, bad or corrupted node)");
 		else {
 			for (i = 0; i < nlen && dent->name[i]; i++)
-				pr_cont("%c", dent->name[i]);
+				pr_cont("%c", isprint(dent->name[i]) ?
+					dent->name[i] : '?');
 		}
 		pr_cont("\n");
 
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 30825d882aa9..b777bddaa1dd 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -606,8 +606,8 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	while (1) {
-		dbg_gen("feed '%s', ino %llu, new f_pos %#x",
-			dent->name, (unsigned long long)le64_to_cpu(dent->inum),
+		dbg_gen("ino %llu, new f_pos %#x",
+			(unsigned long long)le64_to_cpu(dent->inum),
 			key_hash_flash(c, &dent->key));
 		ubifs_assert(le64_to_cpu(dent->ch.sqnum) >
 			     ubifs_inode(dir)->creat_sqnum);
@@ -748,6 +748,11 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 		goto out_fname;
 
 	lock_2_inodes(dir, inode);
+
+	/* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */
+	if (inode->i_nlink == 0)
+		ubifs_delete_orphan(c, inode->i_ino);
+
 	inc_nlink(inode);
 	ihold(inode);
 	inode->i_ctime = ubifs_current_time(inode);
@@ -768,6 +773,8 @@ out_cancel:
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
 	drop_nlink(inode);
+	if (inode->i_nlink == 0)
+		ubifs_add_orphan(c, inode->i_ino);
 	unlock_2_inodes(dir, inode);
 	ubifs_release_budget(c, &req);
 	iput(inode);
@@ -1068,8 +1075,10 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
-	if (err)
+	if (err) {
+		kfree(dev);
 		goto out_budg;
+	}
 
 	sz_change = CALC_DENT_SIZE(fname_len(&nm));
 
@@ -1316,9 +1325,6 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 	unsigned int uninitialized_var(saved_nlink);
 	struct fscrypt_name old_nm, new_nm;
 
-	if (flags & ~RENAME_NOREPLACE)
-		return -EINVAL;
-
 	/*
 	 * Budget request settings: deletion direntry, new direntry, removing
 	 * the old inode, and changing old and new parent directory inodes.
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index b73811bd7676..cf4cc99b75b5 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1827,7 +1827,6 @@ static void ubifs_put_super(struct super_block *sb)
 	}
 
 	ubifs_umount(c);
-	bdi_destroy(&c->bdi);
 	ubi_close_volume(c->ubi);
 	mutex_unlock(&c->umount_mutex);
 }
@@ -2019,29 +2018,25 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out;
 	}
 
+	err = ubifs_parse_options(c, data, 0);
+	if (err)
+		goto out_close;
+
 	/*
 	 * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
 	 * UBIFS, I/O is not deferred, it is done immediately in readpage,
 	 * which means the user would have to wait not just for their own I/O
 	 * but the read-ahead I/O as well i.e. completely pointless.
 	 *
-	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
+	 * Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also
+	 * @sb->s_bdi->capabilities are initialized to 0 so there won't be any
+	 * writeback happening.
 	 */
-	c->bdi.name = "ubifs",
-	c->bdi.capabilities = 0;
-	err  = bdi_init(&c->bdi);
+	err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num,
+				   c->vi.vol_id);
 	if (err)
 		goto out_close;
-	err = bdi_register(&c->bdi, NULL, "ubifs_%d_%d",
-			   c->vi.ubi_num, c->vi.vol_id);
-	if (err)
-		goto out_bdi;
-
-	err = ubifs_parse_options(c, data, 0);
-	if (err)
-		goto out_bdi;
 
-	sb->s_bdi = &c->bdi;
 	sb->s_fs_info = c;
 	sb->s_magic = UBIFS_SUPER_MAGIC;
 	sb->s_blocksize = UBIFS_BLOCK_SIZE;
@@ -2080,8 +2075,6 @@ out_umount:
 	ubifs_umount(c);
 out_unlock:
 	mutex_unlock(&c->umount_mutex);
-out_bdi:
-	bdi_destroy(&c->bdi);
 out_close:
 	ubi_close_volume(c->ubi);
 out:
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 4d57e488038e..4da10a6d702a 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -972,7 +972,6 @@ struct ubifs_debug_info;
  * struct ubifs_info - UBIFS file-system description data structure
  * (per-superblock).
  * @vfs_sb: VFS @struct super_block object
- * @bdi: backing device info object to make VFS happy and disable read-ahead
  *
  * @highest_inum: highest used inode number
  * @max_sqnum: current global sequence number
@@ -1220,7 +1219,6 @@ struct ubifs_debug_info;
  */
 struct ubifs_info {
 	struct super_block *vfs_sb;
-	struct backing_dev_info bdi;
 
 	ino_t highest_inum;
 	unsigned long long max_sqnum;
@@ -1461,7 +1459,6 @@ extern const struct inode_operations ubifs_file_inode_operations;
 extern const struct file_operations ubifs_dir_operations;
 extern const struct inode_operations ubifs_dir_inode_operations;
 extern const struct inode_operations ubifs_symlink_inode_operations;
-extern struct backing_dev_info ubifs_backing_dev_info;
 extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
 
 /* io.c */
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 973607df579d..f7555fc25877 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -138,8 +138,6 @@ out:
  * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
  * context.
  * @ctx: [in] Pointer to the userfaultfd context.
- *
- * Returns: In case of success, returns not zero.
  */
 static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
 {
@@ -267,6 +265,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 {
 	struct mm_struct *mm = ctx->mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
@@ -277,7 +276,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
 		goto out;
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto out;
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto out;
 	pmd = pmd_offset(pud, address);
@@ -490,7 +492,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 			 * in such case.
 			 */
 			down_read(&mm->mmap_sem);
-			ret = 0;
+			ret = VM_FAULT_NOPAGE;
 		}
 	}
 
@@ -527,10 +529,11 @@ out:
 	return ret;
 }
 
-static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
-					     struct userfaultfd_wait_queue *ewq)
+static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
+					      struct userfaultfd_wait_queue *ewq)
 {
-	int ret = 0;
+	if (WARN_ON_ONCE(current->flags & PF_EXITING))
+		goto out;
 
 	ewq->ctx = ctx;
 	init_waitqueue_entry(&ewq->wq, current);
@@ -547,8 +550,16 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 			break;
 		if (ACCESS_ONCE(ctx->released) ||
 		    fatal_signal_pending(current)) {
-			ret = -1;
 			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
+			if (ewq->msg.event == UFFD_EVENT_FORK) {
+				struct userfaultfd_ctx *new;
+
+				new = (struct userfaultfd_ctx *)
+					(unsigned long)
+					ewq->msg.arg.reserved.reserved1;
+
+				userfaultfd_ctx_put(new);
+			}
 			break;
 		}
 
@@ -566,9 +577,8 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	 * ctx may go away after this if the userfault pseudo fd is
 	 * already released.
 	 */
-
+out:
 	userfaultfd_ctx_put(ctx);
-	return ret;
 }
 
 static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
@@ -626,7 +636,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 	return 0;
 }
 
-static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
+static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
 {
 	struct userfaultfd_ctx *ctx = fctx->orig;
 	struct userfaultfd_wait_queue ewq;
@@ -636,17 +646,15 @@ static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
 	ewq.msg.event = UFFD_EVENT_FORK;
 	ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
 
-	return userfaultfd_event_wait_completion(ctx, &ewq);
+	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
 void dup_userfaultfd_complete(struct list_head *fcs)
 {
-	int ret = 0;
 	struct userfaultfd_fork_ctx *fctx, *n;
 
 	list_for_each_entry_safe(fctx, n, fcs, list) {
-		if (!ret)
-			ret = dup_fctx(fctx);
+		dup_fctx(fctx);
 		list_del(&fctx->list);
 		kfree(fctx);
 	}
@@ -689,8 +697,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
-void userfaultfd_remove(struct vm_area_struct *vma,
-			struct vm_area_struct **prev,
+bool userfaultfd_remove(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -699,13 +706,11 @@ void userfaultfd_remove(struct vm_area_struct *vma,
 
 	ctx = vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
-		return;
+		return true;
 
 	userfaultfd_ctx_get(ctx);
 	up_read(&mm->mmap_sem);
 
-	*prev = NULL; /* We wait for ACK w/o the mmap semaphore */
-
 	msg_init(&ewq.msg);
 
 	ewq.msg.event = UFFD_EVENT_REMOVE;
@@ -714,7 +719,7 @@ void userfaultfd_remove(struct vm_area_struct *vma,
 
 	userfaultfd_event_wait_completion(ctx, &ewq);
 
-	down_read(&mm->mmap_sem);
+	return false;
 }
 
 static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
@@ -775,34 +780,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
 	}
 }
 
-void userfaultfd_exit(struct mm_struct *mm)
-{
-	struct vm_area_struct *vma = mm->mmap;
-
-	/*
-	 * We can do the vma walk without locking because the caller
-	 * (exit_mm) knows it now has exclusive access
-	 */
-	while (vma) {
-		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
-
-		if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) {
-			struct userfaultfd_wait_queue ewq;
-
-			userfaultfd_ctx_get(ctx);
-
-			msg_init(&ewq.msg);
-			ewq.msg.event = UFFD_EVENT_EXIT;
-
-			userfaultfd_event_wait_completion(ctx, &ewq);
-
-			ctx->features &= ~UFFD_FEATURE_EVENT_EXIT;
-		}
-
-		vma = vma->vm_next;
-	}
-}
-
 static int userfaultfd_release(struct inode *inode, struct file *file)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
@@ -1779,7 +1756,7 @@ static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
 	 *	protocols: aa:... bb:...
 	 */
 	seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
-		   pending, total, UFFD_API, UFFD_API_FEATURES,
+		   pending, total, UFFD_API, ctx->features,
 		   UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
 }
 #endif
diff --git a/fs/utimes.c b/fs/utimes.c
index 32b15b3f6629..6571d8c848a0 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -1,14 +1,10 @@
-#include <linux/compiler.h>
 #include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/linkage.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/sched.h>
-#include <linux/stat.h>
 #include <linux/utime.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/compat.h>
 #include <asm/unistd.h>
 
 #ifdef __ARCH_WANT_SYS_UTIME
@@ -219,3 +215,63 @@ SYSCALL_DEFINE2(utimes, char __user *, filename,
 {
 	return sys_futimesat(AT_FDCWD, filename, utimes);
 }
+
+#ifdef CONFIG_COMPAT
+/*
+ * Not all architectures have sys_utime, so implement this in terms
+ * of sys_utimes.
+ */
+COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
+		       struct compat_utimbuf __user *, t)
+{
+	struct timespec tv[2];
+
+	if (t) {
+		if (get_user(tv[0].tv_sec, &t->actime) ||
+		    get_user(tv[1].tv_sec, &t->modtime))
+			return -EFAULT;
+		tv[0].tv_nsec = 0;
+		tv[1].tv_nsec = 0;
+	}
+	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
+}
+
+COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
+{
+	struct timespec tv[2];
+
+	if  (t) {
+		if (compat_get_timespec(&tv[0], &t[0]) ||
+		    compat_get_timespec(&tv[1], &t[1]))
+			return -EFAULT;
+
+		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
+			return 0;
+	}
+	return do_utimes(dfd, filename, t ? tv : NULL, flags);
+}
+
+COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
+{
+	struct timespec tv[2];
+
+	if (t) {
+		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
+		    get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
+		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
+		    get_user(tv[1].tv_nsec, &t[1].tv_usec))
+			return -EFAULT;
+		if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
+		    tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
+			return -EINVAL;
+		tv[0].tv_nsec *= 1000;
+		tv[1].tv_nsec *= 1000;
+	}
+	return do_utimes(dfd, filename, t ? tv : NULL, 0);
+}
+
+COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
+{
+	return compat_sys_futimesat(AT_FDCWD, filename, t);
+}
+#endif
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 2dfdc62f795e..70a5b55e0870 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -25,24 +25,6 @@
 #include "kmem.h"
 #include "xfs_message.h"
 
-/*
- * Greedy allocation.  May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
-	void		*ptr;
-	size_t		kmsize = maxsize;
-
-	while (!(ptr = vzalloc(kmsize))) {
-		if ((kmsize >>= 1) <= minsize)
-			kmsize = minsize;
-	}
-	if (ptr)
-		*size = kmsize;
-	return ptr;
-}
-
 void *
 kmem_alloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 689f746224e7..f0fc84fcaac2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -69,8 +69,6 @@ static inline void  kmem_free(const void *ptr)
 }
 
 
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
 static inline void *
 kmem_zalloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a9c66d47757a..9bd104f32908 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree(
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
 	} else if (dfops->dop_low) {
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
 		args.fsbno = *firstblock;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -790,13 +790,17 @@ try_another_ag:
 	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
 	    args.fsbno == NULLFSBLOCK &&
 	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		dfops->dop_low = true;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		goto try_another_ag;
 	}
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+		xfs_iroot_realloc(ip, -1, whichfork);
+		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+		return -ENOSPC;
+	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(*firstblock == NULLFSBLOCK ||
 	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
 	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
@@ -4150,6 +4154,19 @@ xfs_bmapi_read(
 	return 0;
 }
 
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
 int
 xfs_bmapi_reserve_delalloc(
 	struct xfs_inode	*ip,
@@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc(
 	got->br_startblock = nullstartblock(indlen);
 	got->br_blockcount = alen;
 	got->br_state = XFS_EXT_NORM;
-	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
-	/*
-	 * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
-	 * might have merged it into one of the neighbouring ones.
-	 */
-	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
+	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
 	/*
 	 * Tag the inode if blocks were preallocated. Note that COW fork
@@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc(
 	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
 		xfs_inode_set_cowblocks_tag(ip);
 
-	ASSERT(got->br_startoff <= aoff);
-	ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen);
-	ASSERT(isnullstartblock(got->br_startblock));
-	ASSERT(got->br_state == XFS_EXT_NORM);
 	return 0;
 
 out_unreserve_blocks:
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index f93072b58a58..fd55db479385 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -447,8 +447,8 @@ xfs_bmbt_alloc_block(
 
 	if (args.fsbno == NULLFSBLOCK) {
 		args.fsbno = be64_to_cpu(start->l);
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
 		/*
 		 * Make sure there is sufficient room left in the AG to
 		 * complete a full tree split for an extent insert.  If
@@ -488,8 +488,8 @@ try_another_ag:
 	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
 	    args.fsbno == NULLFSBLOCK &&
 	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		cur->bc_private.b.dfops->dop_low = true;
 		args.fsbno = cur->bc_private.b.firstblock;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		goto try_another_ag;
 	}
 
@@ -506,7 +506,7 @@ try_another_ag:
 			goto error0;
 		cur->bc_private.b.dfops->dop_low = true;
 	}
-	if (args.fsbno == NULLFSBLOCK) {
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 		*stat = 0;
 		return 0;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index d04547fcf274..39f8604f764e 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -125,6 +125,7 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
 extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
+extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
 
 /* xfs_dir2_readdir.c */
 extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index c6809ff41197..e84af093b2ab 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -629,6 +629,112 @@ xfs_dir2_sf_check(
 }
 #endif	/* DEBUG */
 
+/* Verify the consistency of an inline directory. */
+int
+xfs_dir2_sf_verify(
+	struct xfs_inode		*ip)
+{
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_dir2_sf_hdr		*sfp;
+	struct xfs_dir2_sf_entry	*sfep;
+	struct xfs_dir2_sf_entry	*next_sfep;
+	char				*endp;
+	const struct xfs_dir_ops	*dops;
+	struct xfs_ifork		*ifp;
+	xfs_ino_t			ino;
+	int				i;
+	int				i8count;
+	int				offset;
+	int				size;
+	int				error;
+	__uint8_t			filetype;
+
+	ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
+	/*
+	 * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops,
+	 * so we can only trust the mountpoint to have the right pointer.
+	 */
+	dops = xfs_dir_get_ops(mp, NULL);
+
+	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+	size = ifp->if_bytes;
+
+	/*
+	 * Give up if the directory is way too short.
+	 */
+	if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) ||
+	    size < xfs_dir2_sf_hdr_size(sfp->i8count))
+		return -EFSCORRUPTED;
+
+	endp = (char *)sfp + size;
+
+	/* Check .. entry */
+	ino = dops->sf_get_parent_ino(sfp);
+	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
+	error = xfs_dir_ino_validate(mp, ino);
+	if (error)
+		return error;
+	offset = dops->data_first_offset;
+
+	/* Check all reported entries */
+	sfep = xfs_dir2_sf_firstentry(sfp);
+	for (i = 0; i < sfp->count; i++) {
+		/*
+		 * struct xfs_dir2_sf_entry has a variable length.
+		 * Check the fixed-offset parts of the structure are
+		 * within the data buffer.
+		 */
+		if (((char *)sfep + sizeof(*sfep)) >= endp)
+			return -EFSCORRUPTED;
+
+		/* Don't allow names with known bad length. */
+		if (sfep->namelen == 0)
+			return -EFSCORRUPTED;
+
+		/*
+		 * Check that the variable-length part of the structure is
+		 * within the data buffer.  The next entry starts after the
+		 * name component, so nextentry is an acceptable test.
+		 */
+		next_sfep = dops->sf_nextentry(sfp, sfep);
+		if (endp < (char *)next_sfep)
+			return -EFSCORRUPTED;
+
+		/* Check that the offsets always increase. */
+		if (xfs_dir2_sf_get_offset(sfep) < offset)
+			return -EFSCORRUPTED;
+
+		/* Check the inode number. */
+		ino = dops->sf_get_ino(sfp, sfep);
+		i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
+		error = xfs_dir_ino_validate(mp, ino);
+		if (error)
+			return error;
+
+		/* Check the file type. */
+		filetype = dops->sf_get_ftype(sfep);
+		if (filetype >= XFS_DIR3_FT_MAX)
+			return -EFSCORRUPTED;
+
+		offset = xfs_dir2_sf_get_offset(sfep) +
+				dops->data_entsize(sfep->namelen);
+
+		sfep = next_sfep;
+	}
+	if (i8count != sfp->i8count)
+		return -EFSCORRUPTED;
+	if ((void *)sfep != (void *)endp)
+		return -EFSCORRUPTED;
+
+	/* Make sure this whole thing ought to be in local format. */
+	if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+	    (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
 /*
  * Create a new (shortform) directory.
  */
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 25c1e078aef6..8a37efe04de3 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -33,6 +33,8 @@
 #include "xfs_trace.h"
 #include "xfs_attr_sf.h"
 #include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
 
 kmem_zone_t *xfs_ifork_zone;
 
@@ -210,6 +212,16 @@ xfs_iformat_fork(
 	if (error)
 		return error;
 
+	/* Check inline dir contents. */
+	if (S_ISDIR(VFS_I(ip)->i_mode) &&
+	    dip->di_format == XFS_DINODE_FMT_LOCAL) {
+		error = xfs_dir2_sf_verify(ip);
+		if (error) {
+			xfs_idestroy_fork(ip, XFS_DATA_FORK);
+			return error;
+		}
+	}
+
 	if (xfs_is_reflink_inode(ip)) {
 		ASSERT(ip->i_cowfp == NULL);
 		xfs_ifork_init_cow(ip);
@@ -320,7 +332,6 @@ xfs_iformat_local(
 	int		whichfork,
 	int		size)
 {
-
 	/*
 	 * If the size is unreasonable, then something
 	 * is wrong and we just bail out rather than crash in
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index bf65a9ea8642..61494295d92f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -274,54 +274,49 @@ xfs_end_io(
 	struct xfs_ioend	*ioend =
 		container_of(work, struct xfs_ioend, io_work);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	xfs_off_t		offset = ioend->io_offset;
+	size_t			size = ioend->io_size;
 	int			error = ioend->io_bio->bi_error;
 
 	/*
-	 * Set an error if the mount has shut down and proceed with end I/O
-	 * processing so it can perform whatever cleanups are necessary.
+	 * Just clean up the in-memory strutures if the fs has been shut down.
 	 */
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		error = -EIO;
+		goto done;
+	}
 
 	/*
-	 * For a CoW extent, we need to move the mapping from the CoW fork
-	 * to the data fork.  If instead an error happened, just dump the
-	 * new blocks.
+	 * Clean up any COW blocks on an I/O error.
 	 */
-	if (ioend->io_type == XFS_IO_COW) {
-		if (error)
-			goto done;
-		if (ioend->io_bio->bi_error) {
-			error = xfs_reflink_cancel_cow_range(ip,
-					ioend->io_offset, ioend->io_size);
-			goto done;
+	if (unlikely(error)) {
+		switch (ioend->io_type) {
+		case XFS_IO_COW:
+			xfs_reflink_cancel_cow_range(ip, offset, size, true);
+			break;
 		}
-		error = xfs_reflink_end_cow(ip, ioend->io_offset,
-				ioend->io_size);
-		if (error)
-			goto done;
+
+		goto done;
 	}
 
 	/*
-	 * For unwritten extents we need to issue transactions to convert a
-	 * range to normal written extens after the data I/O has finished.
-	 * Detecting and handling completion IO errors is done individually
-	 * for each case as different cleanup operations need to be performed
-	 * on error.
+	 * Success:  commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_type == XFS_IO_UNWRITTEN) {
-		if (error)
-			goto done;
-		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
-						  ioend->io_size);
-	} else if (ioend->io_append_trans) {
-		error = xfs_setfilesize_ioend(ioend, error);
-	} else {
-		ASSERT(!xfs_ioend_is_append(ioend) ||
-		       ioend->io_type == XFS_IO_COW);
+	switch (ioend->io_type) {
+	case XFS_IO_COW:
+		error = xfs_reflink_end_cow(ip, offset, size);
+		break;
+	case XFS_IO_UNWRITTEN:
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+		break;
+	default:
+		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+		break;
 	}
 
 done:
+	if (ioend->io_append_trans)
+		error = xfs_setfilesize_ioend(ioend, error);
 	xfs_destroy_ioend(ioend, error);
 }
 
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 8b75dcea5966..8795e9cd867c 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -81,7 +81,7 @@ xfs_zero_extent(
 	return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
 		block << (mp->m_super->s_blocksize_bits - 9),
 		count_fsb << (mp->m_super->s_blocksize_bits - 9),
-		GFP_NOFS, true);
+		GFP_NOFS, 0);
 }
 
 int
@@ -1311,8 +1311,16 @@ xfs_free_file_space(
 	/*
 	 * Now that we've unmap all full blocks we'll have to zero out any
 	 * partial block at the beginning and/or end.  xfs_zero_range is
-	 * smart enough to skip any holes, including those we just created.
+	 * smart enough to skip any holes, including those we just created,
+	 * but we must take care not to zero beyond EOF and enlarge i_size.
 	 */
+
+	if (offset >= XFS_ISIZE(ip))
+		return 0;
+
+	if (offset + len > XFS_ISIZE(ip))
+		len = XFS_ISIZE(ip) - offset;
+
 	return xfs_zero_range(ip, offset, len, NULL);
 }
 
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 003a99b83bd8..ad9396e516f6 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -71,22 +71,11 @@ xfs_dir2_sf_getdents(
 	struct xfs_da_geometry	*geo = args->geo;
 
 	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	/*
-	 * Give up if the directory is way too short.
-	 */
-	if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
-		ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount));
-		return -EIO;
-	}
-
 	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 
-	if (dp->i_d.di_size < xfs_dir2_sf_hdr_size(sfp->i8count))
-		return -EFSCORRUPTED;
-
 	/*
 	 * If the block number in the offset is out of range, we're done.
 	 */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 7234b9748c36..3531f8f72fa5 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks(
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 
-	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index edfa6a55b064..7605d8396596 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -50,6 +50,7 @@
 #include "xfs_log.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_dir2_priv.h"
 
 kmem_zone_t *xfs_inode_zone;
 
@@ -1615,7 +1616,7 @@ xfs_itruncate_extents(
 
 	/* Remove all pending CoW reservations. */
 	error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block,
-			last_block);
+			last_block, true);
 	if (error)
 		goto out;
 
@@ -3546,6 +3547,12 @@ xfs_iflush_int(
 	if (ip->i_d.di_version < 3)
 		ip->i_d.di_flushiter++;
 
+	/* Check the inline directory data. */
+	if (S_ISDIR(VFS_I(ip)->i_mode) &&
+	    ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
+	    xfs_dir2_sf_verify(ip))
+		goto corrupt_out;
+
 	/*
 	 * Copy the dirty parts of the inode into the on-disk inode.  We always
 	 * copy out the core of the inode, because if the inode is dirty at all
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 41662fb14e87..288ee5b840d7 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -630,6 +630,11 @@ retry:
 		goto out_unlock;
 	}
 
+	/*
+	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+	 * them out if the write happens to fail.
+	 */
+	iomap->flags = IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc(
 	struct xfs_inode	*ip,
 	loff_t			offset,
 	loff_t			length,
-	ssize_t			written)
+	ssize_t			written,
+	struct iomap		*iomap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_fsb;
 	xfs_fileoff_t		end_fsb;
 	int			error = 0;
 
-	/* behave as if the write failed if drop writes is enabled */
-	if (xfs_mp_drop_writes(mp))
+	/*
+	 * Behave as if the write failed if drop writes is enabled. Set the NEW
+	 * flag to force delalloc cleanup.
+	 */
+	if (xfs_mp_drop_writes(mp)) {
+		iomap->flags |= IOMAP_F_NEW;
 		written = 0;
+	}
 
 	/*
 	 * start_fsb refers to the first unused block after a short write. If
@@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc(
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
 	/*
-	 * Trim back delalloc blocks if we didn't manage to write the whole
-	 * range reserved.
+	 * Trim delalloc blocks if they were allocated by this write and we
+	 * didn't manage to write the whole range.
 	 *
 	 * We don't need to care about racing delalloc as we hold i_mutex
 	 * across the reserve/allocate/unreserve calls. If there are delalloc
 	 * blocks in the range, they are ours.
 	 */
-	if (start_fsb < end_fsb) {
+	if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
 		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
 					 XFS_FSB_TO_B(mp, end_fsb) - 1);
 
@@ -1131,7 +1142,7 @@ xfs_file_iomap_end(
 {
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
-				length, written);
+				length, written, iomap);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 229cc6a6d8ef..ebfc13350f9a 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -516,6 +516,20 @@ xfs_vn_getattr(
 	stat->blocks =
 		XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
 
+	if (ip->i_d.di_version == 3) {
+		if (request_mask & STATX_BTIME) {
+			stat->result_mask |= STATX_BTIME;
+			stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
+			stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+		}
+	}
+
+	if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+		stat->attributes |= STATX_ATTR_NODUMP;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFBLK:
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 66e881790c17..26d67ce3c18d 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -361,7 +361,6 @@ xfs_bulkstat(
 	xfs_agino_t		agino;	/* inode # in allocation group */
 	xfs_agnumber_t		agno;	/* allocation group number */
 	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
-	size_t			irbsize; /* size of irec buffer in bytes */
 	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
 	int			nirbuf;	/* size of irbuf */
 	int			ubcount; /* size of user's buffer */
@@ -388,11 +387,10 @@ xfs_bulkstat(
 	*ubcountp = 0;
 	*done = 0;
 
-	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
+	irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP);
 	if (!irbuf)
 		return -ENOMEM;
-
-	nirbuf = irbsize / sizeof(*irbuf);
+	nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf);
 
 	/*
 	 * Loop over the allocation groups, starting from the last
@@ -585,7 +583,7 @@ xfs_inumbers(
 		return error;
 
 	bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
-	buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+	buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
 	do {
 		struct xfs_inobt_rec_incore	r;
 		int				stat;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 450bde68bb75..688ebff1f663 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -513,8 +513,7 @@ STATIC void
 xfs_set_inoalignment(xfs_mount_t *mp)
 {
 	if (xfs_sb_version_hasalign(&mp->m_sb) &&
-	    mp->m_sb.sb_inoalignmt >=
-	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
+		mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
 		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
 	else
 		mp->m_inoalign_mask = 0;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index da6d08fb359c..4a84c5ea266d 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow(
 }
 
 /*
- * Cancel all pending CoW reservations for some block range of an inode.
+ * Cancel CoW reservations for some block range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_blocks(
 	struct xfs_inode		*ip,
 	struct xfs_trans		**tpp,
 	xfs_fileoff_t			offset_fsb,
-	xfs_fileoff_t			end_fsb)
+	xfs_fileoff_t			end_fsb,
+	bool				cancel_real)
 {
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
@@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks(
 					&idx, &got, &del);
 			if (error)
 				break;
-		} else {
+		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
@@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks(
 }
 
 /*
- * Cancel all pending CoW reservations for some byte range of an inode.
+ * Cancel CoW reservations for some byte range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_range(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		count)
+	xfs_off_t		count,
+	bool			cancel_real)
 {
 	struct xfs_trans	*tp;
 	xfs_fileoff_t		offset_fsb;
@@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	/* Scrape out the old CoW reservations */
-	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb);
+	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
+			cancel_real);
 	if (error)
 		goto out_cancel;
 
@@ -1450,7 +1459,7 @@ next:
 	 * We didn't find any shared blocks so turn off the reflink flag.
 	 * First, get rid of any leftover CoW mappings.
 	 */
-	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF);
+	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 33ac9b8db683..d29a7967f029 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
-		xfs_fileoff_t end_fsb);
+		xfs_fileoff_t end_fsb, bool cancel_real);
 extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
-		xfs_off_t count);
+		xfs_off_t count, bool cancel_real);
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 890862f2447c..685c042a120f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -953,7 +953,7 @@ xfs_fs_destroy_inode(
 	XFS_STATS_INC(ip->i_mount, vn_remove);
 
 	if (xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 		if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount))
 			xfs_warn(ip->i_mount,
 "Error %d while evicting CoW blocks for inode %llu.",
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index ef0ae8aaa567..2fc678e08d8d 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -88,6 +88,7 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const u8 *uuid, u64 rev, u64 func,
 	}
 
 bool acpi_dev_found(const char *hid);
+bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
 
 #ifdef CONFIG_ACPI
 
@@ -386,6 +387,7 @@ struct acpi_data_node {
 	const char *name;
 	acpi_handle handle;
 	struct fwnode_handle fwnode;
+	struct fwnode_handle *parent;
 	struct acpi_device_data data;
 	struct list_head sibling;
 	struct kobject kobj;
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 427a7c3e6c75..2010c0516f27 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -103,6 +103,7 @@ struct cppc_perf_caps {
 	u32 highest_perf;
 	u32 nominal_perf;
 	u32 lowest_perf;
+	u32 lowest_nonlinear_perf;
 };
 
 struct cppc_perf_ctrls {
@@ -115,7 +116,7 @@ struct cppc_perf_fb_ctrs {
 	u64 reference;
 	u64 delivered;
 	u64 reference_perf;
-	u64 ctr_wrap_time;
+	u64 wraparound_time;
 };
 
 /* Per CPU container for runtime CPPC management. */
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 5bdab6bffd23..928fd66b1271 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -15,7 +15,6 @@
 	((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \
  		NULL: pmd_offset(pud, address))
 
-#define pud_alloc(mm, pgd, address)	(pgd)
 #define pud_offset(pgd, start)		(pgd)
 #define pud_none(pud)			0
 #define pud_bad(pud)			0
@@ -35,4 +34,6 @@
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)		(end)
 
+#include <asm-generic/5level-fixup.h>
+
 #endif
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
new file mode 100644
index 000000000000..b5ca82dc4175
--- /dev/null
+++ b/include/asm-generic/5level-fixup.h
@@ -0,0 +1,41 @@
+#ifndef _5LEVEL_FIXUP_H
+#define _5LEVEL_FIXUP_H
+
+#define __ARCH_HAS_5LEVEL_HACK
+#define __PAGETABLE_P4D_FOLDED
+
+#define P4D_SHIFT			PGDIR_SHIFT
+#define P4D_SIZE			PGDIR_SIZE
+#define P4D_MASK			PGDIR_MASK
+#define PTRS_PER_P4D			1
+
+#define p4d_t				pgd_t
+
+#define pud_alloc(mm, p4d, address) \
+	((unlikely(pgd_none(*(p4d))) && __pud_alloc(mm, p4d, address)) ? \
+		NULL : pud_offset(p4d, address))
+
+#define p4d_alloc(mm, pgd, address)	(pgd)
+#define p4d_offset(pgd, start)		(pgd)
+#define p4d_none(p4d)			0
+#define p4d_bad(p4d)			0
+#define p4d_present(p4d)		1
+#define p4d_ERROR(p4d)			do { } while (0)
+#define p4d_clear(p4d)			pgd_clear(p4d)
+#define p4d_val(p4d)			pgd_val(p4d)
+#define p4d_populate(mm, p4d, pud)	pgd_populate(mm, p4d, pud)
+#define p4d_page(p4d)			pgd_page(p4d)
+#define p4d_page_vaddr(p4d)		pgd_page_vaddr(p4d)
+
+#define __p4d(x)			__pgd(x)
+#define set_p4d(p4dp, p4d)		set_pgd(p4dp, p4d)
+
+#undef p4d_free_tlb
+#define p4d_free_tlb(tlb, x, addr)	do { } while (0)
+#define p4d_free(mm, x)			do { } while (0)
+#define __p4d_free_tlb(tlb, x, addr)	do { } while (0)
+
+#undef  p4d_addr_end
+#define p4d_addr_end(addr, end)		(end)
+
+#endif
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 6f96247226a4..d6f4aed479a1 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -5,7 +5,9 @@
 
 #ifdef CONFIG_GENERIC_BUG
 #define BUGFLAG_WARNING		(1 << 0)
-#define BUGFLAG_TAINT(taint)	(BUGFLAG_WARNING | ((taint) << 8))
+#define BUGFLAG_ONCE		(1 << 1)
+#define BUGFLAG_DONE		(1 << 2)
+#define BUGFLAG_TAINT(taint)	((taint) << 8)
 #define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
 #endif
 
@@ -55,6 +57,18 @@ struct bug_entry {
 #define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
 #endif
 
+#ifdef __WARN_FLAGS
+#define __WARN_TAINT(taint)		__WARN_FLAGS(BUGFLAG_TAINT(taint))
+#define __WARN_ONCE_TAINT(taint)	__WARN_FLAGS(BUGFLAG_ONCE|BUGFLAG_TAINT(taint))
+
+#define WARN_ON_ONCE(condition) ({				\
+	int __ret_warn_on = !!(condition);			\
+	if (unlikely(__ret_warn_on))				\
+		__WARN_ONCE_TAINT(TAINT_WARN);			\
+	unlikely(__ret_warn_on);				\
+})
+#endif
+
 /*
  * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report
  * significant issues that need prompt attention if they should ever
@@ -97,7 +111,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 #endif
 
 #ifndef WARN
-#define WARN(condition, format...) ({						\
+#define WARN(condition, format...) ({					\
 	int __ret_warn_on = !!(condition);				\
 	if (unlikely(__ret_warn_on))					\
 		__WARN_printf(format);					\
@@ -112,6 +126,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 	unlikely(__ret_warn_on);					\
 })
 
+#ifndef WARN_ON_ONCE
 #define WARN_ON_ONCE(condition)	({				\
 	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
@@ -122,6 +137,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 	}							\
 	unlikely(__ret_warn_once);				\
 })
+#endif
 
 #define WARN_ONCE(condition, format...)	({			\
 	static bool __section(.data.unlikely) __warned;		\
diff --git a/include/asm-generic/extable.h b/include/asm-generic/extable.h
new file mode 100644
index 000000000000..ca14c6664027
--- /dev/null
+++ b/include/asm-generic/extable.h
@@ -0,0 +1,26 @@
+#ifndef __ASM_GENERIC_EXTABLE_H
+#define __ASM_GENERIC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	unsigned long insn, fixup;
+};
+
+
+struct pt_regs;
+extern int fixup_exception(struct pt_regs *regs);
+
+#endif
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
index cc5d9a1405df..41e5b6784b97 100644
--- a/include/asm-generic/mm_hooks.h
+++ b/include/asm-generic/mm_hooks.h
@@ -32,10 +32,4 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	/* by default, allow everything */
 	return true;
 }
-
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
-	/* by default, allow everything */
-	return true;
-}
 #endif	/* _ASM_GENERIC_MM_HOOKS_H */
diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h
new file mode 100644
index 000000000000..752fb7511750
--- /dev/null
+++ b/include/asm-generic/pgtable-nop4d-hack.h
@@ -0,0 +1,62 @@
+#ifndef _PGTABLE_NOP4D_HACK_H
+#define _PGTABLE_NOP4D_HACK_H
+
+#ifndef __ASSEMBLY__
+#include <asm-generic/5level-fixup.h>
+
+#define __PAGETABLE_PUD_FOLDED
+
+/*
+ * Having the pud type consist of a pgd gets the size right, and allows
+ * us to conceptually access the pgd entry that this pud is folded into
+ * without casting.
+ */
+typedef struct { pgd_t pgd; } pud_t;
+
+#define PUD_SHIFT	PGDIR_SHIFT
+#define PTRS_PER_PUD	1
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pud is never bad, and a pud always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+static inline void pgd_clear(pgd_t *pgd)	{ }
+#define pud_ERROR(pud)				(pgd_ERROR((pud).pgd))
+
+#define pgd_populate(mm, pgd, pud)		do { } while (0)
+/*
+ * (puds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval)	set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+	return (pud_t *)pgd;
+}
+
+#define pud_val(x)				(pgd_val((x).pgd))
+#define __pud(x)				((pud_t) { __pgd(x) })
+
+#define pgd_page(pgd)				(pud_page((pud_t){ pgd }))
+#define pgd_page_vaddr(pgd)			(pud_page_vaddr((pud_t){ pgd }))
+
+/*
+ * allocating and freeing a pud is trivial: the 1-entry pud is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define pud_alloc_one(mm, address)		NULL
+#define pud_free(mm, x)				do { } while (0)
+#define __pud_free_tlb(tlb, x, a)		do { } while (0)
+
+#undef  pud_addr_end
+#define pud_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOP4D_HACK_H */
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
new file mode 100644
index 000000000000..de364ecb8df6
--- /dev/null
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -0,0 +1,56 @@
+#ifndef _PGTABLE_NOP4D_H
+#define _PGTABLE_NOP4D_H
+
+#ifndef __ASSEMBLY__
+
+#define __PAGETABLE_P4D_FOLDED
+
+typedef struct { pgd_t pgd; } p4d_t;
+
+#define P4D_SHIFT	PGDIR_SHIFT
+#define PTRS_PER_P4D	1
+#define P4D_SIZE	(1UL << P4D_SHIFT)
+#define P4D_MASK	(~(P4D_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the p4d is never bad, and a p4d always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+static inline void pgd_clear(pgd_t *pgd)	{ }
+#define p4d_ERROR(p4d)				(pgd_ERROR((p4d).pgd))
+
+#define pgd_populate(mm, pgd, p4d)		do { } while (0)
+/*
+ * (p4ds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval)	set_p4d((p4d_t *)(pgdptr), (p4d_t) { pgdval })
+
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	return (p4d_t *)pgd;
+}
+
+#define p4d_val(x)				(pgd_val((x).pgd))
+#define __p4d(x)				((p4d_t) { __pgd(x) })
+
+#define pgd_page(pgd)				(p4d_page((p4d_t){ pgd }))
+#define pgd_page_vaddr(pgd)			(p4d_page_vaddr((p4d_t){ pgd }))
+
+/*
+ * allocating and freeing a p4d is trivial: the 1-entry p4d is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define p4d_alloc_one(mm, address)		NULL
+#define p4d_free(mm, x)				do { } while (0)
+#define __p4d_free_tlb(tlb, x, a)		do { } while (0)
+
+#undef  p4d_addr_end
+#define p4d_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOP4D_H */
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 810431d8351b..c2b9b96d6268 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -3,52 +3,57 @@
 
 #ifndef __ASSEMBLY__
 
+#ifdef __ARCH_USE_5LEVEL_HACK
+#include <asm-generic/pgtable-nop4d-hack.h>
+#else
+#include <asm-generic/pgtable-nop4d.h>
+
 #define __PAGETABLE_PUD_FOLDED
 
 /*
- * Having the pud type consist of a pgd gets the size right, and allows
- * us to conceptually access the pgd entry that this pud is folded into
+ * Having the pud type consist of a p4d gets the size right, and allows
+ * us to conceptually access the p4d entry that this pud is folded into
  * without casting.
  */
-typedef struct { pgd_t pgd; } pud_t;
+typedef struct { p4d_t p4d; } pud_t;
 
-#define PUD_SHIFT	PGDIR_SHIFT
+#define PUD_SHIFT	P4D_SHIFT
 #define PTRS_PER_PUD	1
 #define PUD_SIZE  	(1UL << PUD_SHIFT)
 #define PUD_MASK  	(~(PUD_SIZE-1))
 
 /*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * The "p4d_xxx()" functions here are trivial for a folded two-level
  * setup: the pud is never bad, and a pud always exists (as it's folded
- * into the pgd entry)
+ * into the p4d entry)
  */
-static inline int pgd_none(pgd_t pgd)		{ return 0; }
-static inline int pgd_bad(pgd_t pgd)		{ return 0; }
-static inline int pgd_present(pgd_t pgd)	{ return 1; }
-static inline void pgd_clear(pgd_t *pgd)	{ }
-#define pud_ERROR(pud)				(pgd_ERROR((pud).pgd))
+static inline int p4d_none(p4d_t p4d)		{ return 0; }
+static inline int p4d_bad(p4d_t p4d)		{ return 0; }
+static inline int p4d_present(p4d_t p4d)	{ return 1; }
+static inline void p4d_clear(p4d_t *p4d)	{ }
+#define pud_ERROR(pud)				(p4d_ERROR((pud).p4d))
 
-#define pgd_populate(mm, pgd, pud)		do { } while (0)
+#define p4d_populate(mm, p4d, pud)		do { } while (0)
 /*
- * (puds are folded into pgds so this doesn't get actually called,
+ * (puds are folded into p4ds so this doesn't get actually called,
  * but the define is needed for a generic inline function.)
  */
-#define set_pgd(pgdptr, pgdval)			set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+#define set_p4d(p4dptr, p4dval)	set_pud((pud_t *)(p4dptr), (pud_t) { p4dval })
 
-static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 {
-	return (pud_t *)pgd;
+	return (pud_t *)p4d;
 }
 
-#define pud_val(x)				(pgd_val((x).pgd))
-#define __pud(x)				((pud_t) { __pgd(x) } )
+#define pud_val(x)				(p4d_val((x).p4d))
+#define __pud(x)				((pud_t) { __p4d(x) })
 
-#define pgd_page(pgd)				(pud_page((pud_t){ pgd }))
-#define pgd_page_vaddr(pgd)			(pud_page_vaddr((pud_t){ pgd }))
+#define p4d_page(p4d)				(pud_page((pud_t){ p4d }))
+#define p4d_page_vaddr(p4d)			(pud_page_vaddr((pud_t){ p4d }))
 
 /*
  * allocating and freeing a pud is trivial: the 1-entry pud is
- * inside the pgd, so has no extra memory associated with it.
+ * inside the p4d, so has no extra memory associated with it.
  */
 #define pud_alloc_one(mm, address)		NULL
 #define pud_free(mm, x)				do { } while (0)
@@ -58,4 +63,5 @@ static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
 #define pud_addr_end(addr, end)			(end)
 
 #endif /* __ASSEMBLY__ */
+#endif /* !__ARCH_USE_5LEVEL_HACK */
 #endif /* _PGTABLE_NOPUD_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f4ca23b158b3..7dfa767dc680 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -10,9 +10,9 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 
-#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \
-	CONFIG_PGTABLE_LEVELS
-#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED
+#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
+	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
+#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
 #endif
 
 /*
@@ -341,6 +341,31 @@ static inline int pte_unused(pte_t pte)
 }
 #endif
 
+#ifndef pte_access_permitted
+#define pte_access_permitted(pte, write) \
+	(pte_present(pte) && (!(write) || pte_write(pte)))
+#endif
+
+#ifndef pmd_access_permitted
+#define pmd_access_permitted(pmd, write) \
+	(pmd_present(pmd) && (!(write) || pmd_write(pmd)))
+#endif
+
+#ifndef pud_access_permitted
+#define pud_access_permitted(pud, write) \
+	(pud_present(pud) && (!(write) || pud_write(pud)))
+#endif
+
+#ifndef p4d_access_permitted
+#define p4d_access_permitted(p4d, write) \
+	(p4d_present(p4d) && (!(write) || p4d_write(p4d)))
+#endif
+
+#ifndef pgd_access_permitted
+#define pgd_access_permitted(pgd, write) \
+	(pgd_present(pgd) && (!(write) || pgd_write(pgd)))
+#endif
+
 #ifndef __HAVE_ARCH_PMD_SAME
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
@@ -424,6 +449,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#ifndef p4d_addr_end
+#define p4d_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK;	\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+#endif
+
 #ifndef pud_addr_end
 #define pud_addr_end(addr, end)						\
 ({	unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK;	\
@@ -444,6 +476,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
  * Do the tests inline, but report and clear the bad entry in mm/memory.c.
  */
 void pgd_clear_bad(pgd_t *);
+void p4d_clear_bad(p4d_t *);
 void pud_clear_bad(pud_t *);
 void pmd_clear_bad(pmd_t *);
 
@@ -458,6 +491,17 @@ static inline int pgd_none_or_clear_bad(pgd_t *pgd)
 	return 0;
 }
 
+static inline int p4d_none_or_clear_bad(p4d_t *p4d)
+{
+	if (p4d_none(*p4d))
+		return 1;
+	if (unlikely(p4d_bad(*p4d))) {
+		p4d_clear_bad(p4d);
+		return 1;
+	}
+	return 0;
+}
+
 static inline int pud_none_or_clear_bad(pud_t *pud)
 {
 	if (pud_none(*pud))
@@ -844,11 +888,30 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+
+#ifndef __PAGETABLE_P4D_FOLDED
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
+int p4d_clear_huge(p4d_t *p4d);
+#else
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
+#endif /* !__PAGETABLE_P4D_FOLDED */
+
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
 static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
@@ -857,6 +920,10 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
 static inline int pud_clear_huge(pud_t *pud)
 {
 	return 0;
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 4df64a1fc09e..532372c6cf15 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -14,8 +14,8 @@
  * [_sdata, _edata]: contains .data.* sections, may also contain .rodata.*
  *                   and/or .init.* sections.
  * [__start_rodata, __end_rodata]: contains .rodata.* sections
- * [__start_data_ro_after_init, __end_data_ro_after_init]:
- *		     contains data.ro_after_init section
+ * [__start_ro_after_init, __end_ro_after_init]:
+ *		     contains .data..ro_after_init section
  * [__init_begin, __init_end]: contains .init.* sections, but .init.text.*
  *                   may be out of this range on some architectures.
  * [_sinittext, _einittext]: contains .init.text.* sections
@@ -33,7 +33,7 @@ extern char _data[], _sdata[], _edata[];
 extern char __bss_start[], __bss_stop[];
 extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
-extern char __start_data_ro_after_init[], __end_data_ro_after_init[];
+extern char __start_ro_after_init[], __end_ro_after_init[];
 extern char _end[];
 extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 4329bc6ef04b..8afa4335e5b2 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -270,6 +270,12 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 
+#define pmd_free_tlb(tlb, pmdp, address)			\
+	do {							\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__pmd_free_tlb(tlb, pmdp, address);		\
+	} while (0)
+
 #ifndef __ARCH_HAS_4LEVEL_HACK
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
@@ -278,11 +284,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 	} while (0)
 #endif
 
-#define pmd_free_tlb(tlb, pmdp, address)			\
+#ifndef __ARCH_HAS_5LEVEL_HACK
+#define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		__pmd_free_tlb(tlb, pmdp, address);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
+#endif
 
 #define tlb_migrate_finish(mm) do {} while (0)
 
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index cc6bb319e464..bbe4bb438e39 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -6,7 +6,6 @@
  * on any machine that has kernel and user data in the same
  * address space, e.g. all NOMMU machines.
  */
-#include <linux/sched.h>
 #include <linux/string.h>
 
 #include <asm/segment.h>
@@ -35,9 +34,6 @@ static inline void set_fs(mm_segment_t fs)
 #define segment_eq(a, b) ((a).seg == (b).seg)
 #endif
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr),(size))
 
 /*
@@ -52,87 +48,6 @@ static inline int __access_ok(unsigned long addr, unsigned long size)
 #endif
 
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-/*
- * architectures with an MMU should override these two
- */
-#ifndef __copy_from_user
-static inline __must_check long __copy_from_user(void *to,
-		const void __user * from, unsigned long n)
-{
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 *)to = *(u8 __force *)from;
-			return 0;
-		case 2:
-			*(u16 *)to = *(u16 __force *)from;
-			return 0;
-		case 4:
-			*(u32 *)to = *(u32 __force *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 *)to = *(u64 __force *)from;
-			return 0;
-#endif
-		default:
-			break;
-		}
-	}
-
-	memcpy(to, (const void __force *)from, n);
-	return 0;
-}
-#endif
-
-#ifndef __copy_to_user
-static inline __must_check long __copy_to_user(void __user *to,
-		const void *from, unsigned long n)
-{
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 __force *)to = *(u8 *)from;
-			return 0;
-		case 2:
-			*(u16 __force *)to = *(u16 *)from;
-			return 0;
-		case 4:
-			*(u32 __force *)to = *(u32 *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 __force *)to = *(u64 *)from;
-			return 0;
-#endif
-		default:
-			break;
-		}
-	}
-
-	memcpy((void __force *)to, from, n);
-	return 0;
-}
-#endif
-
-/*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.
  * This version just falls back to copy_{from,to}_user, which should
@@ -171,8 +86,7 @@ static inline __must_check long __copy_to_user(void __user *to,
 
 static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
 {
-	size = __copy_to_user(ptr, x, size);
-	return size ? -EFAULT : size;
+	return unlikely(raw_copy_to_user(ptr, x, size)) ? -EFAULT : 0;
 }
 
 #define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
@@ -187,28 +101,28 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 	__chk_user_ptr(ptr);					\
 	switch (sizeof(*(ptr))) {				\
 	case 1: {						\
-		unsigned char __x;				\
+		unsigned char __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 2: {						\
-		unsigned short __x;				\
+		unsigned short __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 4: {						\
-		unsigned int __x;				\
+		unsigned int __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 8: {						\
-		unsigned long long __x;				\
+		unsigned long long __x = 0;			\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
@@ -233,12 +147,7 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 #ifndef __get_user_fn
 static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 {
-	size_t n = __copy_from_user(x, ptr, size);
-	if (unlikely(n)) {
-		memset(x + (size - n), 0, n);
-		return -EFAULT;
-	}
-	return 0;
+	return unlikely(raw_copy_from_user(x, ptr, size)) ? -EFAULT : 0;
 }
 
 #define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
@@ -247,36 +156,6 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 
 extern int __get_user_bad(void) __attribute__((noreturn));
 
-#ifndef __copy_from_user_inatomic
-#define __copy_from_user_inatomic __copy_from_user
-#endif
-
-#ifndef __copy_to_user_inatomic
-#define __copy_to_user_inatomic __copy_to_user
-#endif
-
-static inline long copy_from_user(void *to,
-		const void __user * from, unsigned long n)
-{
-	unsigned long res = n;
-	might_fault();
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		res = __copy_from_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
-}
-
-static inline long copy_to_user(void __user *to,
-		const void *from, unsigned long n)
-{
-	might_fault();
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_to_user(to, from, n);
-	else
-		return n;
-}
-
 /*
  * Copy a null terminated string from userspace.
  */
@@ -348,4 +227,6 @@ clear_user(void __user *to, unsigned long n)
 	return __clear_user(to, n);
 }
 
+#include <asm/extable.h>
+
 #endif /* __ASM_GENERIC_UACCESS_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0968d13b3885..3558f4eb1a86 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -173,6 +173,7 @@
 	KEEP(*(__##name##_of_table_end))
 
 #define CLKSRC_OF_TABLES()	OF_TABLE(CONFIG_CLKSRC_OF, clksrc)
+#define CLKEVT_OF_TABLES()	OF_TABLE(CONFIG_CLKEVT_OF, clkevt)
 #define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip)
 #define CLK_OF_TABLES()		OF_TABLE(CONFIG_COMMON_CLK, clk)
 #define IOMMU_OF_TABLES()	OF_TABLE(CONFIG_OF_IOMMU, iommu)
@@ -260,9 +261,9 @@
  */
 #ifndef RO_AFTER_INIT_DATA
 #define RO_AFTER_INIT_DATA						\
-	__start_data_ro_after_init = .;					\
+	VMLINUX_SYMBOL(__start_ro_after_init) = .;			\
 	*(.data..ro_after_init)						\
-	__end_data_ro_after_init = .;
+	VMLINUX_SYMBOL(__end_ro_after_init) = .;
 #endif
 
 /*
@@ -286,8 +287,6 @@
 		*(.rodata1)						\
 	}								\
 									\
-	BUG_TABLE							\
-									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
@@ -559,6 +558,7 @@
 	CLK_OF_TABLES()							\
 	RESERVEDMEM_OF_TABLES()						\
 	CLKSRC_OF_TABLES()						\
+	CLKEVT_OF_TABLES()						\
 	IOMMU_OF_TABLES()						\
 	CPU_METHOD_OF_TABLES()						\
 	CPUIDLE_METHOD_OF_TABLES()					\
@@ -855,7 +855,8 @@
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\
 		CONSTRUCTORS						\
-	}
+	}								\
+	BUG_TABLE
 
 #define INIT_TEXT_SECTION(inittext_align)				\
 	. = ALIGN(inittext_align);					\
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index caedb74c9210..cc805b72994a 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -16,9 +16,13 @@
 #ifndef __CLKSOURCE_ARM_ARCH_TIMER_H
 #define __CLKSOURCE_ARM_ARCH_TIMER_H
 
+#include <linux/bitops.h>
 #include <linux/timecounter.h>
 #include <linux/types.h>
 
+#define ARCH_TIMER_TYPE_CP15		BIT(0)
+#define ARCH_TIMER_TYPE_MEM		BIT(1)
+
 #define ARCH_TIMER_CTRL_ENABLE		(1 << 0)
 #define ARCH_TIMER_CTRL_IT_MASK		(1 << 1)
 #define ARCH_TIMER_CTRL_IT_STAT		(1 << 2)
@@ -34,11 +38,27 @@ enum arch_timer_reg {
 	ARCH_TIMER_REG_TVAL,
 };
 
+enum arch_timer_ppi_nr {
+	ARCH_TIMER_PHYS_SECURE_PPI,
+	ARCH_TIMER_PHYS_NONSECURE_PPI,
+	ARCH_TIMER_VIRT_PPI,
+	ARCH_TIMER_HYP_PPI,
+	ARCH_TIMER_MAX_TIMER_PPI
+};
+
+enum arch_timer_spi_nr {
+	ARCH_TIMER_PHYS_SPI,
+	ARCH_TIMER_VIRT_SPI,
+	ARCH_TIMER_MAX_TIMER_SPI
+};
+
 #define ARCH_TIMER_PHYS_ACCESS		0
 #define ARCH_TIMER_VIRT_ACCESS		1
 #define ARCH_TIMER_MEM_PHYS_ACCESS	2
 #define ARCH_TIMER_MEM_VIRT_ACCESS	3
 
+#define ARCH_TIMER_MEM_MAX_FRAMES	8
+
 #define ARCH_TIMER_USR_PCT_ACCESS_EN	(1 << 0) /* physical counter */
 #define ARCH_TIMER_USR_VCT_ACCESS_EN	(1 << 1) /* virtual counter */
 #define ARCH_TIMER_VIRT_EVT_EN		(1 << 2)
@@ -54,6 +74,20 @@ struct arch_timer_kvm_info {
 	int virtual_irq;
 };
 
+struct arch_timer_mem_frame {
+	bool valid;
+	phys_addr_t cntbase;
+	size_t size;
+	int phys_irq;
+	int virt_irq;
+};
+
+struct arch_timer_mem {
+	phys_addr_t cntctlbase;
+	size_t size;
+	struct arch_timer_mem_frame frame[ARCH_TIMER_MEM_MAX_FRAMES];
+};
+
 #ifdef CONFIG_ARM_ARCH_TIMER
 
 extern u32 arch_timer_get_rate(void);
diff --git a/include/crypto/gf128mul.h b/include/crypto/gf128mul.h
index 592d47e565a8..0977fb18ff68 100644
--- a/include/crypto/gf128mul.h
+++ b/include/crypto/gf128mul.h
@@ -43,12 +43,13 @@
  ---------------------------------------------------------------------------
  Issue Date: 31/01/2006
 
- An implementation of field multiplication in Galois Field GF(128)
+ An implementation of field multiplication in Galois Field GF(2^128)
 */
 
 #ifndef _CRYPTO_GF128MUL_H
 #define _CRYPTO_GF128MUL_H
 
+#include <asm/byteorder.h>
 #include <crypto/b128ops.h>
 #include <linux/slab.h>
 
@@ -65,7 +66,7 @@
  * are left and the lsb's are right. char b[16] is an array and b[0] is
  * the first octet.
  *
- * 80000000 00000000 00000000 00000000 .... 00000000 00000000 00000000
+ * 10000000 00000000 00000000 00000000 .... 00000000 00000000 00000000
  *   b[0]     b[1]     b[2]     b[3]          b[13]    b[14]    b[15]
  *
  * Every bit is a coefficient of some power of X. We can store the bits
@@ -85,15 +86,17 @@
  * Both of the above formats are easy to implement on big-endian
  * machines.
  *
- * EME (which is patent encumbered) uses the ble format (bits are stored
- * in big endian order and the bytes in little endian). The above buffer
- * represents X^7 in this case and the primitive polynomial is b[0] = 0x87.
+ * XTS and EME (the latter of which is patent encumbered) use the ble
+ * format (bits are stored in big endian order and the bytes in little
+ * endian). The above buffer represents X^7 in this case and the
+ * primitive polynomial is b[0] = 0x87.
  *
  * The common machine word-size is smaller than 128 bits, so to make
  * an efficient implementation we must split into machine word sizes.
- * This file uses one 32bit for the moment. Machine endianness comes into
- * play. The lle format in relation to machine endianness is discussed
- * below by the original author of gf128mul Dr Brian Gladman.
+ * This implementation uses 64-bit words for the moment. Machine
+ * endianness comes into play. The lle format in relation to machine
+ * endianness is discussed below by the original author of gf128mul Dr
+ * Brian Gladman.
  *
  * Let's look at the bbe and ble format on a little endian machine.
  *
@@ -127,10 +130,10 @@
  * machines this will automatically aligned to wordsize and on a 64-bit
  * machine also.
  */
-/*	Multiply a GF128 field element by x. Field elements are held in arrays
-    of bytes in which field bits 8n..8n + 7 are held in byte[n], with lower
-    indexed bits placed in the more numerically significant bit positions
-    within bytes.
+/*	Multiply a GF(2^128) field element by x. Field elements are
+    held in arrays of bytes in which field bits 8n..8n + 7 are held in
+    byte[n], with lower indexed bits placed in the more numerically
+    significant bit positions within bytes.
 
     On little endian machines the bit indexes translate into the bit
     positions within four 32-bit words in the following way
@@ -161,8 +164,58 @@ void gf128mul_lle(be128 *a, const be128 *b);
 
 void gf128mul_bbe(be128 *a, const be128 *b);
 
-/* multiply by x in ble format, needed by XTS */
-void gf128mul_x_ble(be128 *a, const be128 *b);
+/*
+ * The following functions multiply a field element by x in
+ * the polynomial field representation.  They use 64-bit word operations
+ * to gain speed but compensate for machine endianness and hence work
+ * correctly on both styles of machine.
+ *
+ * They are defined here for performance.
+ */
+
+static inline u64 gf128mul_mask_from_bit(u64 x, int which)
+{
+	/* a constant-time version of 'x & ((u64)1 << which) ? (u64)-1 : 0' */
+	return ((s64)(x << (63 - which)) >> 63);
+}
+
+static inline void gf128mul_x_lle(be128 *r, const be128 *x)
+{
+	u64 a = be64_to_cpu(x->a);
+	u64 b = be64_to_cpu(x->b);
+
+	/* equivalent to gf128mul_table_le[(b << 7) & 0xff] << 48
+	 * (see crypto/gf128mul.c): */
+	u64 _tt = gf128mul_mask_from_bit(b, 0) & ((u64)0xe1 << 56);
+
+	r->b = cpu_to_be64((b >> 1) | (a << 63));
+	r->a = cpu_to_be64((a >> 1) ^ _tt);
+}
+
+static inline void gf128mul_x_bbe(be128 *r, const be128 *x)
+{
+	u64 a = be64_to_cpu(x->a);
+	u64 b = be64_to_cpu(x->b);
+
+	/* equivalent to gf128mul_table_be[a >> 63] (see crypto/gf128mul.c): */
+	u64 _tt = gf128mul_mask_from_bit(a, 63) & 0x87;
+
+	r->a = cpu_to_be64((a << 1) | (b >> 63));
+	r->b = cpu_to_be64((b << 1) ^ _tt);
+}
+
+/* needed by XTS */
+static inline void gf128mul_x_ble(le128 *r, const le128 *x)
+{
+	u64 a = le64_to_cpu(x->a);
+	u64 b = le64_to_cpu(x->b);
+
+	/* equivalent to gf128mul_table_be[b >> 63] (see crypto/gf128mul.c): */
+	u64 _tt = gf128mul_mask_from_bit(a, 63) & 0x87;
+
+	r->a = cpu_to_le64((a << 1) | (b >> 63));
+	r->b = cpu_to_le64((b << 1) ^ _tt);
+}
 
 /* 4k table optimization */
 
@@ -172,8 +225,8 @@ struct gf128mul_4k {
 
 struct gf128mul_4k *gf128mul_init_4k_lle(const be128 *g);
 struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g);
-void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t);
-void gf128mul_4k_bbe(be128 *a, struct gf128mul_4k *t);
+void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t);
+void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t);
 
 static inline void gf128mul_free_4k(struct gf128mul_4k *t)
 {
@@ -194,6 +247,6 @@ struct gf128mul_64k {
  */
 struct gf128mul_64k *gf128mul_init_64k_bbe(const be128 *g);
 void gf128mul_free_64k(struct gf128mul_64k *t);
-void gf128mul_64k_bbe(be128 *a, struct gf128mul_64k *t);
+void gf128mul_64k_bbe(be128 *a, const struct gf128mul_64k *t);
 
 #endif /* _CRYPTO_GF128MUL_H */
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index a2bfd7843f18..e2b9c6fe2714 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -73,7 +73,7 @@ int af_alg_unregister_type(const struct af_alg_type *type);
 
 int af_alg_release(struct socket *sock);
 void af_alg_release_parent(struct sock *sk);
-int af_alg_accept(struct sock *sk, struct socket *newsock);
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern);
 
 int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len);
 void af_alg_free_sg(struct af_alg_sgl *sgl);
diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h
index 1de2b5af12d7..51052f65cefc 100644
--- a/include/crypto/internal/acompress.h
+++ b/include/crypto/internal/acompress.h
@@ -78,4 +78,7 @@ int crypto_register_acomp(struct acomp_alg *alg);
  */
 int crypto_unregister_acomp(struct acomp_alg *alg);
 
+int crypto_register_acomps(struct acomp_alg *algs, int count);
+void crypto_unregister_acomps(struct acomp_alg *algs, int count);
+
 #endif
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 1d4f365d8f03..f6d9af3efa45 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -166,6 +166,16 @@ static inline struct ahash_instance *ahash_alloc_instance(
 	return crypto_alloc_instance2(name, alg, ahash_instance_headroom());
 }
 
+static inline void ahash_request_complete(struct ahash_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
+static inline u32 ahash_request_flags(struct ahash_request *req)
+{
+	return req->base.flags;
+}
+
 static inline struct crypto_ahash *crypto_spawn_ahash(
 	struct crypto_ahash_spawn *spawn)
 {
diff --git a/include/crypto/internal/scompress.h b/include/crypto/internal/scompress.h
index 3fda3c5655a0..ccad9b2c9bd6 100644
--- a/include/crypto/internal/scompress.h
+++ b/include/crypto/internal/scompress.h
@@ -133,4 +133,7 @@ int crypto_register_scomp(struct scomp_alg *alg);
  */
 int crypto_unregister_scomp(struct scomp_alg *alg);
 
+int crypto_register_scomps(struct scomp_alg *algs, int count);
+void crypto_unregister_scomps(struct scomp_alg *algs, int count);
+
 #endif
diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h
index 4307a2f2365f..ce8e1f79374b 100644
--- a/include/crypto/kpp.h
+++ b/include/crypto/kpp.h
@@ -74,7 +74,7 @@ struct crypto_kpp {
  * @base:		Common crypto API algorithm data structure
  */
 struct kpp_alg {
-	int (*set_secret)(struct crypto_kpp *tfm, void *buffer,
+	int (*set_secret)(struct crypto_kpp *tfm, const void *buffer,
 			  unsigned int len);
 	int (*generate_public_key)(struct kpp_request *req);
 	int (*compute_shared_secret)(struct kpp_request *req);
@@ -273,8 +273,8 @@ struct kpp_secret {
  *
  * Return: zero on success; error code in case of error
  */
-static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, void *buffer,
-					unsigned int len)
+static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm,
+					const void *buffer, unsigned int len)
 {
 	struct kpp_alg *alg = crypto_kpp_alg(tfm);
 
diff --git a/include/crypto/xts.h b/include/crypto/xts.h
index 77b630672b2c..c0bde308b28a 100644
--- a/include/crypto/xts.h
+++ b/include/crypto/xts.h
@@ -11,7 +11,7 @@ struct blkcipher_desc;
 #define XTS_BLOCK_SIZE 16
 
 struct xts_crypt_req {
-	be128 *tbuf;
+	le128 *tbuf;
 	unsigned int tbuflen;
 
 	void *tweak_ctx;
diff --git a/include/drm/ttm/ttm_object.h b/include/drm/ttm/ttm_object.h
index ed953f98f0e1..1487011fe057 100644
--- a/include/drm/ttm/ttm_object.h
+++ b/include/drm/ttm/ttm_object.h
@@ -229,6 +229,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base);
  * @ref_type: The type of reference.
  * @existed: Upon completion, indicates that an identical reference object
  * already existed, and the refcount was upped on that object instead.
+ * @require_existed: Fail with -EPERM if an identical ref object didn't
+ * already exist.
  *
  * Checks that the base object is shareable and adds a ref object to it.
  *
@@ -243,7 +245,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base);
  */
 extern int ttm_ref_object_add(struct ttm_object_file *tfile,
 			      struct ttm_base_object *base,
-			      enum ttm_ref_type ref_type, bool *existed);
+			      enum ttm_ref_type ref_type, bool *existed,
+			      bool require_existed);
 
 extern bool ttm_ref_object_exists(struct ttm_object_file *tfile,
 				  struct ttm_base_object *base);
diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h
index 692846c7941b..63f4c2c44a1f 100644
--- a/include/dt-bindings/clock/gxbb-clkc.h
+++ b/include/dt-bindings/clock/gxbb-clkc.h
@@ -12,9 +12,10 @@
 #define CLKID_FCLK_DIV4		6
 #define CLKID_CLK81		12
 #define CLKID_MPLL2		15
-#define CLKID_SPI		34
 #define CLKID_I2C		22
 #define CLKID_SAR_ADC		23
+#define CLKID_RNG0		25
+#define CLKID_SPI		34
 #define CLKID_ETH		36
 #define CLKID_USB0		50
 #define CLKID_USB1		51
diff --git a/include/dt-bindings/pinctrl/mt7623-pinfunc.h b/include/dt-bindings/pinctrl/mt7623-pinfunc.h
index 2f00bdc42442..436a87be864a 100644
--- a/include/dt-bindings/pinctrl/mt7623-pinfunc.h
+++ b/include/dt-bindings/pinctrl/mt7623-pinfunc.h
@@ -185,6 +185,12 @@
 #define MT7623_PIN_56_SPI0_MO_FUNC_SPI0_MO (MTK_PIN_NO(56) | 1)
 #define MT7623_PIN_56_SPI0_MO_FUNC_SPI0_MI (MTK_PIN_NO(56) | 2)
 
+#define MT7623_PIN_57_SDA1_FUNC_GPIO57 (MTK_PIN_NO(57) | 0)
+#define MT7623_PIN_57_SDA1_FUNC_SDA1 (MTK_PIN_NO(57) | 1)
+
+#define MT7623_PIN_58_SCL1_FUNC_GPIO58 (MTK_PIN_NO(58) | 0)
+#define MT7623_PIN_58_SCL1_FUNC_SCL1 (MTK_PIN_NO(58) | 1)
+
 #define MT7623_PIN_60_WB_RSTB_FUNC_GPIO60 (MTK_PIN_NO(60) | 0)
 #define MT7623_PIN_60_WB_RSTB_FUNC_WB_RSTB (MTK_PIN_NO(60) | 1)
 
@@ -244,6 +250,22 @@
 #define MT7623_PIN_76_SCL0_FUNC_GPIO76 (MTK_PIN_NO(76) | 0)
 #define MT7623_PIN_76_SCL0_FUNC_SCL0 (MTK_PIN_NO(76) | 1)
 
+#define MT7623_PIN_79_URXD0_FUNC_GPIO79 (MTK_PIN_NO(79) | 0)
+#define MT7623_PIN_79_URXD0_FUNC_URXD0 (MTK_PIN_NO(79) | 1)
+#define MT7623_PIN_79_URXD0_FUNC_UTXD0 (MTK_PIN_NO(79) | 2)
+
+#define MT7623_PIN_80_UTXD0_FUNC_GPIO80 (MTK_PIN_NO(80) | 0)
+#define MT7623_PIN_80_UTXD0_FUNC_UTXD0 (MTK_PIN_NO(80) | 1)
+#define MT7623_PIN_80_UTXD0_FUNC_URXD0 (MTK_PIN_NO(80) | 2)
+
+#define MT7623_PIN_81_URXD1_FUNC_GPIO81 (MTK_PIN_NO(81) | 0)
+#define MT7623_PIN_81_URXD1_FUNC_URXD1 (MTK_PIN_NO(81) | 1)
+#define MT7623_PIN_81_URXD1_FUNC_UTXD1 (MTK_PIN_NO(81) | 2)
+
+#define MT7623_PIN_82_UTXD1_FUNC_GPIO82 (MTK_PIN_NO(82) | 0)
+#define MT7623_PIN_82_UTXD1_FUNC_UTXD1 (MTK_PIN_NO(82) | 1)
+#define MT7623_PIN_82_UTXD1_FUNC_URXD1 (MTK_PIN_NO(82) | 2)
+
 #define MT7623_PIN_83_LCM_RST_FUNC_GPIO83 (MTK_PIN_NO(83) | 0)
 #define MT7623_PIN_83_LCM_RST_FUNC_LCM_RST (MTK_PIN_NO(83) | 1)
 
@@ -351,10 +373,10 @@
 #define MT7623_PIN_122_GPIO122_FUNC_SDA2 (MTK_PIN_NO(122) | 4)
 #define MT7623_PIN_122_GPIO122_FUNC_URXD0 (MTK_PIN_NO(122) | 5)
 
-#define MT7623_PIN_123_GPIO123_FUNC_GPIO123 (MTK_PIN_NO(123) | 0)
-#define MT7623_PIN_123_GPIO123_FUNC_TEST (MTK_PIN_NO(123) | 1)
-#define MT7623_PIN_123_GPIO123_FUNC_SCL2 (MTK_PIN_NO(123) | 4)
-#define MT7623_PIN_123_GPIO123_FUNC_UTXD0 (MTK_PIN_NO(123) | 5)
+#define MT7623_PIN_123_HTPLG_FUNC_GPIO123 (MTK_PIN_NO(123) | 0)
+#define MT7623_PIN_123_HTPLG_FUNC_HTPLG (MTK_PIN_NO(123) | 1)
+#define MT7623_PIN_123_HTPLG_FUNC_SCL2 (MTK_PIN_NO(123) | 4)
+#define MT7623_PIN_123_HTPLG_FUNC_UTXD0 (MTK_PIN_NO(123) | 5)
 
 #define MT7623_PIN_124_GPIO124_FUNC_GPIO124 (MTK_PIN_NO(124) | 0)
 #define MT7623_PIN_124_GPIO124_FUNC_TEST (MTK_PIN_NO(124) | 1)
diff --git a/include/dt-bindings/sound/cs42l42.h b/include/dt-bindings/sound/cs42l42.h
index 399a123aed58..db69d84ed7d1 100644
--- a/include/dt-bindings/sound/cs42l42.h
+++ b/include/dt-bindings/sound/cs42l42.h
@@ -20,7 +20,7 @@
 #define CS42L42_HPOUT_LOAD_1NF		0
 #define CS42L42_HPOUT_LOAD_10NF		1
 
-/* HPOUT Clamp to GND Overide */
+/* HPOUT Clamp to GND Override */
 #define CS42L42_HPOUT_CLAMP_EN		0
 #define CS42L42_HPOUT_CLAMP_DIS		1
 
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index b72dd2ad5f44..c0b3d999c266 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -295,6 +295,7 @@ void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vgic_map_resources(struct kvm *kvm);
 int kvm_vgic_hyp_init(void);
+void kvm_vgic_init_cpu_hardware(void);
 
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
 			bool level);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 673acda012af..f729adaac18b 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -233,10 +233,6 @@ int acpi_numa_init (void);
 
 int acpi_table_init (void);
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
-int __init acpi_parse_entries(char *id, unsigned long table_size,
-			      acpi_tbl_entry_handler handler,
-			      struct acpi_table_header *table_header,
-			      int entry_id, unsigned int max_entries);
 int __init acpi_table_parse_entries(char *id, unsigned long table_size,
 			      int entry_id,
 			      acpi_tbl_entry_handler handler,
@@ -287,18 +283,15 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id)
 }
 
 /* Validate the processor object's proc_id */
-bool acpi_processor_validate_proc_id(int proc_id);
+bool acpi_duplicate_processor_id(int proc_id);
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
 int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
 		 int *pcpu);
 int acpi_unmap_cpu(int cpu);
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
-void acpi_set_processor_mapping(void);
-
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
 int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr);
 #endif
@@ -598,6 +591,13 @@ enum acpi_reconfig_event  {
 int acpi_reconfig_notifier_register(struct notifier_block *nb);
 int acpi_reconfig_notifier_unregister(struct notifier_block *nb);
 
+#ifdef CONFIG_ACPI_GTDT
+int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count);
+int acpi_gtdt_map_ppi(int type);
+bool acpi_gtdt_c3stop(int type);
+int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count);
+#endif
+
 #else	/* !CONFIG_ACPI */
 
 #define acpi_disabled 1
@@ -614,6 +614,11 @@ static inline bool acpi_dev_found(const char *hid)
 	return false;
 }
 
+static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
+{
+	return false;
+}
+
 static inline bool is_acpi_node(struct fwnode_handle *fwnode)
 {
 	return false;
@@ -1000,8 +1005,16 @@ int acpi_node_prop_read(struct fwnode_handle *fwnode, const char *propname,
 int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
 		       enum dev_prop_type proptype, void *val, size_t nval);
 
-struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
-					    struct fwnode_handle *subnode);
+struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode,
+					    struct fwnode_handle *child);
+struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode);
+
+struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+						   struct fwnode_handle *prev);
+int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
+				   struct fwnode_handle **remote,
+				   struct fwnode_handle **port,
+				   struct fwnode_handle **endpoint);
 
 struct acpi_probe_entry;
 typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *,
@@ -1118,12 +1131,34 @@ static inline int acpi_dev_prop_read(struct acpi_device *adev,
 	return -ENXIO;
 }
 
-static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
-						struct fwnode_handle *subnode)
+static inline struct fwnode_handle *
+acpi_get_next_subnode(struct fwnode_handle *fwnode, struct fwnode_handle *child)
 {
 	return NULL;
 }
 
+static inline struct fwnode_handle *
+acpi_node_get_parent(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
+static inline struct fwnode_handle *
+acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+			     struct fwnode_handle *prev)
+{
+	return ERR_PTR(-ENXIO);
+}
+
+static inline int
+acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
+			       struct fwnode_handle **remote,
+			       struct fwnode_handle **port,
+			       struct fwnode_handle **endpoint)
+{
+	return -ENXIO;
+}
+
 #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \
 	static const void * __acpi_table_##name[]			\
 		__attribute__((unused))					\
diff --git a/include/linux/ata.h b/include/linux/ata.h
index af6859b3a93d..ad7d9ee89ff0 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -817,11 +817,6 @@ static inline bool ata_id_sct_error_recovery_ctrl(const u16 *id)
 	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 3) ? true : false;
 }
 
-static inline bool ata_id_sct_write_same(const u16 *id)
-{
-	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 2) ? true : false;
-}
-
 static inline bool ata_id_sct_long_sector_access(const u16 *id)
 {
 	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 1) ? true : false;
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index e71835bf60a9..c56be7410130 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -423,6 +423,29 @@
 #endif
 #endif /* atomic_cmpxchg_relaxed */
 
+#ifndef atomic_try_cmpxchg
+
+#define __atomic_try_cmpxchg(type, _p, _po, _n)				\
+({									\
+	typeof(_po) __po = (_po);					\
+	typeof(*(_po)) __r, __o = *__po;				\
+	__r = atomic_cmpxchg##type((_p), __o, (_n));			\
+	if (unlikely(__r != __o))					\
+		*__po = __r;						\
+	likely(__r == __o);						\
+})
+
+#define atomic_try_cmpxchg(_p, _po, _n)		__atomic_try_cmpxchg(, _p, _po, _n)
+#define atomic_try_cmpxchg_relaxed(_p, _po, _n)	__atomic_try_cmpxchg(_relaxed, _p, _po, _n)
+#define atomic_try_cmpxchg_acquire(_p, _po, _n)	__atomic_try_cmpxchg(_acquire, _p, _po, _n)
+#define atomic_try_cmpxchg_release(_p, _po, _n)	__atomic_try_cmpxchg(_release, _p, _po, _n)
+
+#else /* atomic_try_cmpxchg */
+#define atomic_try_cmpxchg_relaxed	atomic_try_cmpxchg
+#define atomic_try_cmpxchg_acquire	atomic_try_cmpxchg
+#define atomic_try_cmpxchg_release	atomic_try_cmpxchg
+#endif /* atomic_try_cmpxchg */
+
 /* cmpxchg_relaxed */
 #ifndef cmpxchg_relaxed
 #define  cmpxchg_relaxed		cmpxchg
@@ -996,6 +1019,29 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_cmpxchg_relaxed */
 
+#ifndef atomic64_try_cmpxchg
+
+#define __atomic64_try_cmpxchg(type, _p, _po, _n)			\
+({									\
+	typeof(_po) __po = (_po);					\
+	typeof(*(_po)) __r, __o = *__po;				\
+	__r = atomic64_cmpxchg##type((_p), __o, (_n));			\
+	if (unlikely(__r != __o))					\
+		*__po = __r;						\
+	likely(__r == __o);						\
+})
+
+#define atomic64_try_cmpxchg(_p, _po, _n)		__atomic64_try_cmpxchg(, _p, _po, _n)
+#define atomic64_try_cmpxchg_relaxed(_p, _po, _n)	__atomic64_try_cmpxchg(_relaxed, _p, _po, _n)
+#define atomic64_try_cmpxchg_acquire(_p, _po, _n)	__atomic64_try_cmpxchg(_acquire, _p, _po, _n)
+#define atomic64_try_cmpxchg_release(_p, _po, _n)	__atomic64_try_cmpxchg(_release, _p, _po, _n)
+
+#else /* atomic64_try_cmpxchg */
+#define atomic64_try_cmpxchg_relaxed	atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg_acquire	atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
+#endif /* atomic64_try_cmpxchg */
+
 #ifndef atomic64_andnot
 static inline void atomic64_andnot(long long i, atomic64_t *v)
 {
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ad955817916d..866c433e7d32 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -21,6 +21,7 @@ struct dentry;
  */
 enum wb_state {
 	WB_registered,		/* bdi_register() was done */
+	WB_shutting_down,	/* wb_shutdown() in progress */
 	WB_writeback_running,	/* Writeback is in progress */
 	WB_has_dirty_io,	/* Dirty inodes on ->b_{dirty|io|more_io} */
 };
@@ -54,7 +55,9 @@ struct bdi_writeback_congested {
 	atomic_t refcnt;		/* nr of attached wb's and blkg */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
-	struct backing_dev_info *bdi;	/* the associated bdi */
+	struct backing_dev_info *__bdi;	/* the associated bdi, set to NULL
+					 * on bdi unregistration. For memcg-wb
+					 * internal use only! */
 	int blkcg_id;			/* ID of the associated blkcg */
 	struct rb_node rb_node;		/* on bdi->cgwb_congestion_tree */
 #endif
@@ -143,7 +146,7 @@ struct backing_dev_info {
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
 
-	char *name;
+	const char *name;
 
 	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
@@ -161,7 +164,6 @@ struct backing_dev_info {
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */
-	atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */
 #else
 	struct bdi_writeback_congested *wb_congested;
 #endif
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c52a48cb9a66..557d84063934 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -17,8 +17,6 @@
 #include <linux/backing-dev-defs.h>
 #include <linux/slab.h>
 
-int __must_check bdi_init(struct backing_dev_info *bdi);
-
 static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
 {
 	kref_get(&bdi->refcnt);
@@ -27,16 +25,18 @@ static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
 
 void bdi_put(struct backing_dev_info *bdi);
 
-__printf(3, 4)
-int bdi_register(struct backing_dev_info *bdi, struct device *parent,
-		const char *fmt, ...);
-int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
+__printf(2, 3)
+int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...);
+int bdi_register_va(struct backing_dev_info *bdi, const char *fmt,
+		    va_list args);
 int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);
 void bdi_unregister(struct backing_dev_info *bdi);
 
-int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
-void bdi_destroy(struct backing_dev_info *bdi);
 struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
+static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask)
+{
+	return bdi_alloc_node(gfp_mask, NUMA_NO_NODE);
+}
 
 void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
 			bool range_cyclic, enum wb_reason reason);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 8e521194f6fc..4931756d86d9 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -383,7 +383,7 @@ extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 extern mempool_t *biovec_create_pool(int pool_entries);
 
-extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
+extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
 extern void bio_put(struct bio *);
 
 extern void __bio_clone_fast(struct bio *, struct bio *);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b296a9006117..f3e5e1de1bdb 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -15,7 +15,7 @@ struct blk_mq_hw_ctx {
 		unsigned long		state;		/* BLK_MQ_S_* flags */
 	} ____cacheline_aligned_in_smp;
 
-	struct work_struct	run_work;
+	struct delayed_work	run_work;
 	cpumask_var_t		cpumask;
 	int			next_cpu;
 	int			next_cpu_batch;
@@ -51,8 +51,6 @@ struct blk_mq_hw_ctx {
 
 	atomic_t		nr_active;
 
-	struct delayed_work	delay_work;
-
 	struct hlist_node	cpuhp_dead;
 	struct kobject		kobj;
 
@@ -81,7 +79,6 @@ struct blk_mq_tag_set {
 
 struct blk_mq_queue_data {
 	struct request *rq;
-	struct list_head *list;
 	bool last;
 };
 
@@ -142,6 +139,14 @@ struct blk_mq_ops {
 	reinit_request_fn	*reinit_request;
 
 	map_queues_fn		*map_queues;
+
+#ifdef CONFIG_BLK_DEBUG_FS
+	/*
+	 * Used by the debugfs implementation to show driver-specific
+	 * information about a request.
+	 */
+	void (*show_rq)(struct seq_file *m, struct request *rq);
+#endif
 };
 
 enum {
@@ -152,7 +157,6 @@ enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_SHARED	= 1 << 1,
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
-	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
@@ -162,6 +166,7 @@ enum {
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 	BLK_MQ_S_SCHED_RESTART	= 2,
 	BLK_MQ_S_TAG_WAITING	= 3,
+	BLK_MQ_S_START_ON_RUN	= 4,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -229,7 +234,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_abort_requeue_list(struct request_queue *q);
-void blk_mq_complete_request(struct request *rq, int error);
+void blk_mq_complete_request(struct request *rq);
 
 bool blk_mq_queue_stopped(struct request_queue *q);
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
@@ -238,13 +243,15 @@ void blk_mq_stop_hw_queues(struct request_queue *q);
 void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
-void blk_mq_freeze_queue_start(struct request_queue *q);
+void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d703acb55d0f..61339bc44400 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -17,6 +17,10 @@ struct io_context;
 struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 
+struct blk_issue_stat {
+	u64 stat;
+};
+
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
  * stacking drivers)
@@ -29,7 +33,7 @@ struct bio {
 						 * top bits REQ_OP. Use
 						 * accessors.
 						 */
-	unsigned short		bi_flags;	/* status, command, etc */
+	unsigned short		bi_flags;	/* status, etc and bvec pool number */
 	unsigned short		bi_ioprio;
 
 	struct bvec_iter	bi_iter;
@@ -58,6 +62,10 @@ struct bio {
 	 */
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	void			*bi_cg_private;
+	struct blk_issue_stat	bi_issue_stat;
+#endif
 #endif
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
@@ -102,12 +110,9 @@ struct bio {
 #define BIO_REFFED	8	/* bio has elevated ->bi_cnt */
 #define BIO_THROTTLED	9	/* This bio has already been subjected to
 				 * throttling rules. Don't do it again. */
-
-/*
- * Flags starting here get preserved by bio_reset() - this includes
- * BVEC_POOL_IDX()
- */
-#define BIO_RESET_BITS	10
+#define BIO_TRACE_COMPLETION 10	/* bio_endio() should trace the final completion
+				 * of this bio. */
+/* See BVEC_POOL_OFFSET below before adding new flags */
 
 /*
  * We support 6 different bvec pools, the last one is magic in that it
@@ -117,13 +122,22 @@ struct bio {
 #define BVEC_POOL_MAX		(BVEC_POOL_NR - 1)
 
 /*
- * Top 4 bits of bio flags indicate the pool the bvecs came from.  We add
+ * Top 3 bits of bio flags indicate the pool the bvecs came from.  We add
  * 1 to the actual index so that 0 indicates that there are no bvecs to be
  * freed.
  */
-#define BVEC_POOL_BITS		(4)
+#define BVEC_POOL_BITS		(3)
 #define BVEC_POOL_OFFSET	(16 - BVEC_POOL_BITS)
 #define BVEC_POOL_IDX(bio)	((bio)->bi_flags >> BVEC_POOL_OFFSET)
+#if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1)
+# error "BVEC_POOL_BITS is too small"
+#endif
+
+/*
+ * Flags starting here get preserved by bio_reset() - this includes
+ * only BVEC_POOL_IDX()
+ */
+#define BIO_RESET_BITS	BVEC_POOL_OFFSET
 
 /*
  * Operations and flags common to the bio and request structures.
@@ -160,7 +174,7 @@ enum req_opf {
 	/* write the same sector many times */
 	REQ_OP_WRITE_SAME	= 7,
 	/* write the zero filled sector many times */
-	REQ_OP_WRITE_ZEROES	= 8,
+	REQ_OP_WRITE_ZEROES	= 9,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
@@ -187,6 +201,10 @@ enum req_flag_bits {
 	__REQ_PREFLUSH,		/* request for cache flush */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
 	__REQ_BACKGROUND,	/* background IO */
+
+	/* command specific flags for REQ_OP_WRITE_ZEROES: */
+	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
+
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -204,6 +222,8 @@ enum req_flag_bits {
 #define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
 #define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
 
+#define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
+
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 
@@ -283,12 +303,6 @@ static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
 	return (cookie & BLK_QC_T_INTERNAL) != 0;
 }
 
-struct blk_issue_stat {
-	u64 time;
-};
-
-#define BLK_RQ_STAT_BATCH	64
-
 struct blk_rq_stat {
 	s64 mean;
 	u64 min;
@@ -296,7 +310,6 @@ struct blk_rq_stat {
 	s32 nr_samples;
 	s32 nr_batch;
 	u64 batch;
-	s64 time;
 };
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 796016e63c1d..83d28623645f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -40,15 +40,20 @@ struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
 struct rq_wb;
+struct blk_queue_stats;
+struct blk_stat_callback;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
 
+/* Must be consisitent with blk_mq_poll_stats_bkt() */
+#define BLK_MQ_POLL_STATS_BKTS 16
+
 /*
  * Maximum number of blkcg policies allowed to be registered concurrently.
  * Defined here to simplify include dependency.
  */
-#define BLKCG_MAX_POLS		2
+#define BLKCG_MAX_POLS		3
 
 typedef void (rq_end_io_fn)(struct request *, int);
 
@@ -173,6 +178,7 @@ struct request {
 		struct rb_node rb_node;	/* sort/lookup */
 		struct bio_vec special_vec;
 		void *completion_data;
+		int error_count; /* for legacy drivers, don't use */
 	};
 
 	/*
@@ -213,16 +219,14 @@ struct request {
 
 	unsigned short ioprio;
 
-	void *special;		/* opaque pointer available for LLD use */
+	unsigned int timeout;
 
-	int errors;
+	void *special;		/* opaque pointer available for LLD use */
 
 	unsigned int extra_len;	/* length of alignment and padding */
 
 	unsigned long deadline;
 	struct list_head timeout_list;
-	unsigned int timeout;
-	int retries;
 
 	/*
 	 * completion callback.
@@ -337,7 +341,6 @@ struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		cluster;
-	unsigned char		discard_zeroes_data;
 	unsigned char		raid_partial_stripes_expensive;
 	enum blk_zoned_model	zoned;
 };
@@ -388,6 +391,7 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
+	struct blk_queue_stats	*stats;
 	struct rq_wb		*rq_wb;
 
 	/*
@@ -435,7 +439,6 @@ struct request_queue {
 	struct delayed_work	delay_work;
 
 	struct backing_dev_info	*backing_dev_info;
-	struct disk_devt	*disk_devt;
 
 	/*
 	 * The queue owner gets to use this for whatever they like.
@@ -506,8 +509,6 @@ struct request_queue {
 	unsigned int		nr_sorted;
 	unsigned int		in_flight[2];
 
-	struct blk_rq_stat	rq_stats[2];
-
 	/*
 	 * Number of active block driver functions for which blk_drain_queue()
 	 * must wait. Must be incremented around functions that unlock the
@@ -517,6 +518,10 @@ struct request_queue {
 
 	unsigned int		rq_timeout;
 	int			poll_nsec;
+
+	struct blk_stat_callback	*poll_cb;
+	struct blk_rq_stat	poll_stat[BLK_MQ_POLL_STATS_BKTS];
+
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 	struct list_head	timeout_list;
@@ -611,7 +616,8 @@ struct request_queue {
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
 #define QUEUE_FLAG_DAX         26	/* device supports DAX */
 #define QUEUE_FLAG_STATS       27	/* track rq completion times */
-#define QUEUE_FLAG_RESTART     28	/* queue needs restart at completion */
+#define QUEUE_FLAG_POLL_STATS  28	/* collecting stats for hybrid polling */
+#define QUEUE_FLAG_REGISTERED  29	/* queue has been registered to a disk */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -920,6 +926,7 @@ extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 extern blk_qc_t generic_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
+extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
@@ -965,7 +972,7 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
 			       struct rq_map_data *, const struct iov_iter *,
 			       gfp_t);
-extern int blk_execute_rq(struct request_queue *, struct gendisk *,
+extern void blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
@@ -1083,20 +1090,6 @@ static inline unsigned int blk_rq_count_bios(struct request *rq)
 }
 
 /*
- * blk_rq_set_prio - associate a request with prio from ioc
- * @rq: request of interest
- * @ioc: target iocontext
- *
- * Assocate request prio with ioc prio so request based drivers
- * can leverage priority information.
- */
-static inline void blk_rq_set_prio(struct request *rq, struct io_context *ioc)
-{
-	if (ioc)
-		rq->ioprio = ioc->ioprio;
-}
-
-/*
  * Request issue related functions.
  */
 extern struct request *blk_peek_request(struct request_queue *q);
@@ -1122,13 +1115,10 @@ extern void blk_finish_request(struct request *rq, int error);
 extern bool blk_end_request(struct request *rq, int error,
 			    unsigned int nr_bytes);
 extern void blk_end_request_all(struct request *rq, int error);
-extern bool blk_end_request_cur(struct request *rq, int error);
-extern bool blk_end_request_err(struct request *rq, int error);
 extern bool __blk_end_request(struct request *rq, int error,
 			      unsigned int nr_bytes);
 extern void __blk_end_request_all(struct request *rq, int error);
 extern bool __blk_end_request_cur(struct request *rq, int error);
-extern bool __blk_end_request_err(struct request *rq, int error);
 
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
@@ -1331,23 +1321,27 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 	return bqt->tag_index[tag];
 }
 
+extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
+extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 
 #define BLKDEV_DISCARD_SECURE	(1 << 0)	/* issue a secure erase */
-#define BLKDEV_DISCARD_ZERO	(1 << 1)	/* must reliably zero data */
 
-extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, int flags,
 		struct bio **biop);
-extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
+
+#define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
+#define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
+
 extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
-		bool discard);
+		unsigned flags);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, bool discard);
+		sector_t nr_sects, gfp_t gfp_mask, unsigned flags);
+
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
@@ -1361,7 +1355,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 	return blkdev_issue_zeroout(sb->s_bdev,
 				    block << (sb->s_blocksize_bits - 9),
 				    nr_blocks << (sb->s_blocksize_bits - 9),
-				    gfp_mask, true);
+				    gfp_mask, 0);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
@@ -1531,19 +1525,6 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 	return q->limits.discard_alignment;
 }
 
-static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
-{
-	if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)
-		return 1;
-
-	return 0;
-}
-
-static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
-{
-	return queue_discard_zeroes_data(bdev_get_queue(bdev));
-}
-
 static inline unsigned int bdev_write_same(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -1674,12 +1655,36 @@ static inline bool bios_segs_mergeable(struct request_queue *q,
 	return true;
 }
 
-static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
-			 struct bio *next)
+static inline bool bio_will_gap(struct request_queue *q,
+				struct request *prev_rq,
+				struct bio *prev,
+				struct bio *next)
 {
 	if (bio_has_data(prev) && queue_virt_boundary(q)) {
 		struct bio_vec pb, nb;
 
+		/*
+		 * don't merge if the 1st bio starts with non-zero
+		 * offset, otherwise it is quite difficult to respect
+		 * sg gap limit. We work hard to merge a huge number of small
+		 * single bios in case of mkfs.
+		 */
+		if (prev_rq)
+			bio_get_first_bvec(prev_rq->bio, &pb);
+		else
+			bio_get_first_bvec(prev, &pb);
+		if (pb.bv_offset)
+			return true;
+
+		/*
+		 * We don't need to worry about the situation that the
+		 * merged segment ends in unaligned virt boundary:
+		 *
+		 * - if 'pb' ends aligned, the merged segment ends aligned
+		 * - if 'pb' ends unaligned, the next bio must include
+		 *   one single bvec of 'nb', otherwise the 'nb' can't
+		 *   merge with 'pb'
+		 */
 		bio_get_last_bvec(prev, &pb);
 		bio_get_first_bvec(next, &nb);
 
@@ -1692,18 +1697,19 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 
 static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
 {
-	return bio_will_gap(req->q, req->biotail, bio);
+	return bio_will_gap(req->q, req, req->biotail, bio);
 }
 
 static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
 {
-	return bio_will_gap(req->q, bio, req->bio);
+	return bio_will_gap(req->q, NULL, bio, req->bio);
 }
 
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_schedule_work_on(int cpu, struct work_struct *work);
 int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay);
 int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
+int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
 /*
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 909fc033173a..6bb38d76faf4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -35,6 +35,7 @@ struct bpf_map_ops {
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
 	void (*map_fd_put_ptr)(void *ptr);
+	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 };
 
 struct bpf_map {
@@ -49,12 +50,7 @@ struct bpf_map {
 	const struct bpf_map_ops *ops;
 	struct work_struct work;
 	atomic_t usercnt;
-};
-
-struct bpf_map_type_list {
-	struct list_head list_node;
-	const struct bpf_map_ops *ops;
-	enum bpf_map_type type;
+	struct bpf_map *inner_map_meta;
 };
 
 /* function argument constraints */
@@ -167,12 +163,8 @@ struct bpf_verifier_ops {
 				  const struct bpf_insn *src,
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog);
-};
-
-struct bpf_prog_type_list {
-	struct list_head list_node;
-	const struct bpf_verifier_ops *ops;
-	enum bpf_prog_type type;
+	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
+			union bpf_attr __user *uattr);
 };
 
 struct bpf_prog_aux {
@@ -231,11 +223,21 @@ typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
 
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 
-void bpf_register_prog_type(struct bpf_prog_type_list *tl);
-void bpf_register_map_type(struct bpf_map_type_list *tl);
+#define BPF_PROG_TYPE(_id, _ops) \
+	extern const struct bpf_verifier_ops _ops;
+#define BPF_MAP_TYPE(_id, _ops) \
+	extern const struct bpf_map_ops _ops;
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
 struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
@@ -275,6 +277,8 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 				 void *key, void *value, u64 map_flags);
 void bpf_fd_array_map_clear(struct bpf_map *map);
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+				void *key, void *value, u64 map_flags);
 
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
@@ -295,10 +299,6 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 /* verify correctness of eBPF program */
 int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
 #else
-static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl)
-{
-}
-
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
 	return ERR_PTR(-EOPNOTSUPP);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
new file mode 100644
index 000000000000..03bf223f18be
--- /dev/null
+++ b/include/linux/bpf_types.h
@@ -0,0 +1,36 @@
+/* internal file - do not include directly */
+
+#ifdef CONFIG_NET
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops)
+#endif
+#ifdef CONFIG_BPF_EVENTS
+BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops)
+#endif
+
+BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_PROG_ARRAY, prog_array_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops)
+#ifdef CONFIG_CGROUPS
+BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
+#endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops)
+#ifdef CONFIG_PERF_EVENTS
+BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops)
+#endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index a13b031dc6b8..5efb4db44e1e 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -66,7 +66,10 @@ struct bpf_verifier_state_list {
 };
 
 struct bpf_insn_aux_data {
-	enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
+	union {
+		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
+		struct bpf_map *map_ptr;	/* pointer for call insn into lookup_elem */
+	};
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 55e517130311..abcda9b458ab 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -25,6 +25,9 @@
 #define PHY_ID_BCM57780			0x03625d90
 
 #define PHY_ID_BCM7250			0xae025280
+#define PHY_ID_BCM7260			0xae025190
+#define PHY_ID_BCM7268			0xae025090
+#define PHY_ID_BCM7271			0xae0253b0
 #define PHY_ID_BCM7278			0xae0251a0
 #define PHY_ID_BCM7364			0xae025260
 #define PHY_ID_BCM7366			0x600d8490
diff --git a/include/linux/bug.h b/include/linux/bug.h
index 5828489309bb..687b557fc5eb 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -105,7 +105,7 @@ static inline int is_warning_bug(const struct bug_entry *bug)
 	return bug->flags & BUGFLAG_WARNING;
 }
 
-const struct bug_entry *find_bug(unsigned long bugaddr);
+struct bug_entry *find_bug(unsigned long bugaddr);
 
 enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs);
 
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index df08a41d5be5..c9a17bb1221c 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -5,7 +5,7 @@
  *
  * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
  *          Urs Thuermann   <urs.thuermann@volkswagen.de>
- * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2017 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  */
@@ -17,7 +17,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 
-#define CAN_VERSION "20120528"
+#define CAN_VERSION "20170425"
 
 /* increment this number each time you change some user-space interface */
 #define CAN_ABI_VERSION "9"
@@ -45,12 +45,13 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+int can_rx_register(struct net *net, struct net_device *dev,
+		    canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *),
 		    void *data, char *ident, struct sock *sk);
 
-extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
-			      canid_t mask,
+extern void can_rx_unregister(struct net *net, struct net_device *dev,
+			      canid_t can_id, canid_t mask,
 			      void (*func)(struct sk_buff *, void *),
 			      void *data);
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/include/linux/can/dev/peak_canfd.h
index 2147678f0225..46dceef2cfa6 100644
--- a/drivers/net/can/usb/peak_usb/pcan_ucan.h
+++ b/include/linux/can/dev/peak_canfd.h
@@ -23,11 +23,14 @@
 #define PUCAN_CMD_LISTEN_ONLY_MODE	0x003
 #define PUCAN_CMD_TIMING_SLOW		0x004
 #define PUCAN_CMD_TIMING_FAST		0x005
+#define PUCAN_CMD_SET_STD_FILTER	0x006
+#define PUCAN_CMD_RESERVED2		0x007
 #define PUCAN_CMD_FILTER_STD		0x008
 #define PUCAN_CMD_TX_ABORT		0x009
 #define PUCAN_CMD_WR_ERR_CNT		0x00a
 #define PUCAN_CMD_SET_EN_OPTION		0x00b
 #define PUCAN_CMD_CLR_DIS_OPTION	0x00c
+#define PUCAN_CMD_RX_BARRIER		0x010
 #define PUCAN_CMD_END_OF_COLLECTION	0x3ff
 
 /* uCAN received messages list */
@@ -35,6 +38,10 @@
 #define PUCAN_MSG_ERROR			0x0002
 #define PUCAN_MSG_STATUS		0x0003
 #define PUCAN_MSG_BUSLOAD		0x0004
+
+#define PUCAN_MSG_CACHE_CRITICAL	0x0102
+
+/* uCAN transmitted messages */
 #define PUCAN_MSG_CAN_TX		0x1000
 
 /* uCAN command common header */
@@ -43,6 +50,12 @@ struct __packed pucan_command {
 	u16	args[3];
 };
 
+/* return the opcode from the opcode_channel field of a command */
+static inline u16 pucan_cmd_get_opcode(struct pucan_command *c)
+{
+	return le16_to_cpu(c->opcode_channel) & 0x3ff;
+}
+
 #define PUCAN_TSLOW_BRP_BITS		10
 #define PUCAN_TSLOW_TSGEG1_BITS		8
 #define PUCAN_TSLOW_TSGEG2_BITS		7
@@ -108,6 +121,27 @@ struct __packed pucan_filter_std {
 	__le32	mask;		/* CAN-ID bitmask in idx range */
 };
 
+#define PUCAN_FLTSTD_ROW_IDX_MAX	((1 << PUCAN_FLTSTD_ROW_IDX_BITS) - 1)
+
+/* uCAN SET_STD_FILTER command fields */
+struct __packed pucan_std_filter {
+	__le16	opcode_channel;
+
+	u8	unused;
+	u8	idx;
+	__le32	mask;		/* CAN-ID bitmask in idx range */
+};
+
+/* uCAN TX_ABORT commands fields */
+#define PUCAN_TX_ABORT_FLUSH		0x0001
+
+struct __packed pucan_tx_abort {
+	__le16	opcode_channel;
+
+	__le16	flags;
+	u32	unused;
+};
+
 /* uCAN WR_ERR_CNT command fields */
 #define PUCAN_WRERRCNT_TE		0x4000	/* Tx error cntr write Enable */
 #define PUCAN_WRERRCNT_RE		0x8000	/* Rx error cntr write Enable */
@@ -184,6 +218,12 @@ struct __packed pucan_error_msg {
 	u8	rx_err_cnt;
 };
 
+static inline int pucan_error_get_channel(const struct pucan_error_msg *msg)
+{
+	return msg->channel_type_d & 0x0f;
+}
+
+#define PUCAN_RX_BARRIER		0x10
 #define PUCAN_BUS_PASSIVE		0x20
 #define PUCAN_BUS_WARNING		0x40
 #define PUCAN_BUS_BUSOFF		0x80
@@ -197,6 +237,31 @@ struct __packed pucan_status_msg {
 	u8	unused[3];
 };
 
+static inline int pucan_status_get_channel(const struct pucan_status_msg *msg)
+{
+	return msg->channel_p_w_b & 0x0f;
+}
+
+static inline int pucan_status_is_rx_barrier(const struct pucan_status_msg *msg)
+{
+	return msg->channel_p_w_b & PUCAN_RX_BARRIER;
+}
+
+static inline int pucan_status_is_passive(const struct pucan_status_msg *msg)
+{
+	return msg->channel_p_w_b & PUCAN_BUS_PASSIVE;
+}
+
+static inline int pucan_status_is_warning(const struct pucan_status_msg *msg)
+{
+	return msg->channel_p_w_b & PUCAN_BUS_WARNING;
+}
+
+static inline int pucan_status_is_busoff(const struct pucan_status_msg *msg)
+{
+	return msg->channel_p_w_b & PUCAN_BUS_BUSOFF;
+}
+
 /* uCAN transmitted message format */
 #define PUCAN_MSG_CHANNEL_DLC(c, d)	(((c) & 0xf) | ((d) << 4))
 
@@ -213,32 +278,31 @@ struct __packed pucan_tx_msg {
 };
 
 /* build the cmd opcode_channel field with respect to the correct endianness */
-static inline __le16 pucan_cmd_opcode_channel(struct peak_usb_device *dev,
-					      int opcode)
+static inline __le16 pucan_cmd_opcode_channel(int index, int opcode)
 {
-	return cpu_to_le16(((dev->ctrl_idx) << 12) | ((opcode) & 0x3ff));
+	return cpu_to_le16(((index) << 12) | ((opcode) & 0x3ff));
 }
 
 /* return the channel number part from any received message channel_dlc field */
-static inline int pucan_msg_get_channel(struct pucan_rx_msg *rm)
+static inline int pucan_msg_get_channel(const struct pucan_rx_msg *msg)
 {
-	return rm->channel_dlc & 0xf;
+	return msg->channel_dlc & 0xf;
 }
 
 /* return the dlc value from any received message channel_dlc field */
-static inline int pucan_msg_get_dlc(struct pucan_rx_msg *rm)
+static inline int pucan_msg_get_dlc(const struct pucan_rx_msg *msg)
 {
-	return rm->channel_dlc >> 4;
+	return msg->channel_dlc >> 4;
 }
 
-static inline int pucan_ermsg_get_channel(struct pucan_error_msg *em)
+static inline int pucan_ermsg_get_channel(const struct pucan_error_msg *msg)
 {
-	return em->channel_type_d & 0x0f;
+	return msg->channel_type_d & 0x0f;
 }
 
-static inline int pucan_stmsg_get_channel(struct pucan_status_msg *sm)
+static inline int pucan_stmsg_get_channel(const struct pucan_status_msg *msg)
 {
-	return sm->channel_p_w_b & 0x0f;
+	return msg->channel_p_w_b & 0x0f;
 }
 
 #endif
diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h
deleted file mode 100644
index a52f47ca6c8a..000000000000
--- a/include/linux/can/platform/ti_hecc.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _CAN_PLATFORM_TI_HECC_H
-#define _CAN_PLATFORM_TI_HECC_H
-
-/*
- * TI HECC (High End CAN Controller) driver platform header
- *
- * Copyright (C) 2009 Texas Instruments Incorporated - http://www.ti.com/
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed as is WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-/**
- * struct hecc_platform_data - HECC Platform Data
- *
- * @scc_hecc_offset:	mostly 0 - should really never change
- * @scc_ram_offset:	SCC RAM offset
- * @hecc_ram_offset:	HECC RAM offset
- * @mbx_offset:		Mailbox RAM offset
- * @int_line:		Interrupt line to use - 0 or 1
- * @version:		version for future use
- * @transceiver_switch:	platform specific callback fn for transceiver control
- *
- * Platform data structure to get all platform specific settings.
- * this structure also accounts the fact that the IP may have different
- * RAM and mailbox offsets for different SOC's
- */
-struct ti_hecc_platform_data {
-	u32 scc_hecc_offset;
-	u32 scc_ram_offset;
-	u32 hecc_ram_offset;
-	u32 mbx_offset;
-	u32 int_line;
-	u32 version;
-	void (*transceiver_switch) (int);
-};
-#endif /* !_CAN_PLATFORM_TI_HECC_H */
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index c71dd8fa5764..3285c944194a 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -123,6 +123,10 @@ enum ccp_aes_mode {
 	CCP_AES_MODE_CFB,
 	CCP_AES_MODE_CTR,
 	CCP_AES_MODE_CMAC,
+	CCP_AES_MODE_GHASH,
+	CCP_AES_MODE_GCTR,
+	CCP_AES_MODE_GCM,
+	CCP_AES_MODE_GMAC,
 	CCP_AES_MODE__LAST,
 };
 
@@ -137,6 +141,9 @@ enum ccp_aes_action {
 	CCP_AES_ACTION_ENCRYPT,
 	CCP_AES_ACTION__LAST,
 };
+/* Overloaded field */
+#define	CCP_AES_GHASHAAD	CCP_AES_ACTION_DECRYPT
+#define	CCP_AES_GHASHFINAL	CCP_AES_ACTION_ENCRYPT
 
 /**
  * struct ccp_aes_engine - CCP AES operation
@@ -181,6 +188,8 @@ struct ccp_aes_engine {
 	struct scatterlist *cmac_key;	/* K1/K2 cmac key required for
 					 * final cmac cmd */
 	u32 cmac_key_len;	/* In bytes */
+
+	u32 aad_len;		/* In bytes */
 };
 
 /***** XTS-AES engine *****/
@@ -249,6 +258,8 @@ enum ccp_sha_type {
 	CCP_SHA_TYPE_1 = 1,
 	CCP_SHA_TYPE_224,
 	CCP_SHA_TYPE_256,
+	CCP_SHA_TYPE_384,
+	CCP_SHA_TYPE_512,
 	CCP_SHA_TYPE__LAST,
 };
 
@@ -290,6 +301,60 @@ struct ccp_sha_engine {
 				 * final sha cmd */
 };
 
+/***** 3DES engine *****/
+enum ccp_des3_mode {
+	CCP_DES3_MODE_ECB = 0,
+	CCP_DES3_MODE_CBC,
+	CCP_DES3_MODE_CFB,
+	CCP_DES3_MODE__LAST,
+};
+
+enum ccp_des3_type {
+	CCP_DES3_TYPE_168 = 1,
+	CCP_DES3_TYPE__LAST,
+	};
+
+enum ccp_des3_action {
+	CCP_DES3_ACTION_DECRYPT = 0,
+	CCP_DES3_ACTION_ENCRYPT,
+	CCP_DES3_ACTION__LAST,
+};
+
+/**
+ * struct ccp_des3_engine - CCP SHA operation
+ * @type: Type of 3DES operation
+ * @mode: cipher mode
+ * @action: 3DES operation (decrypt/encrypt)
+ * @key: key to be used for this 3DES operation
+ * @key_len: length of key (in bytes)
+ * @iv: IV to be used for this AES operation
+ * @iv_len: length in bytes of iv
+ * @src: input data to be used for this operation
+ * @src_len: length of input data used for this operation (in bytes)
+ * @dst: output data produced by this operation
+ *
+ * Variables required to be set when calling ccp_enqueue_cmd():
+ *   - type, mode, action, key, key_len, src, dst, src_len
+ *   - iv, iv_len for any mode other than ECB
+ *
+ * The iv variable is used as both input and output. On completion of the
+ * 3DES operation the new IV overwrites the old IV.
+ */
+struct ccp_des3_engine {
+	enum ccp_des3_type type;
+	enum ccp_des3_mode mode;
+	enum ccp_des3_action action;
+
+	struct scatterlist *key;
+	u32 key_len;	    /* In bytes */
+
+	struct scatterlist *iv;
+	u32 iv_len;	     /* In bytes */
+
+	struct scatterlist *src, *dst;
+	u64 src_len;	    /* In bytes */
+};
+
 /***** RSA engine *****/
 /**
  * struct ccp_rsa_engine - CCP RSA operation
@@ -539,7 +604,7 @@ struct ccp_ecc_engine {
 enum ccp_engine {
 	CCP_ENGINE_AES = 0,
 	CCP_ENGINE_XTS_AES_128,
-	CCP_ENGINE_RSVD1,
+	CCP_ENGINE_DES3,
 	CCP_ENGINE_SHA,
 	CCP_ENGINE_RSA,
 	CCP_ENGINE_PASSTHRU,
@@ -556,7 +621,7 @@ enum ccp_engine {
  * struct ccp_cmd - CCP operation request
  * @entry: list element (ccp driver use only)
  * @work: work element used for callbacks (ccp driver use only)
- * @ccp: CCP device to be run on (ccp driver use only)
+ * @ccp: CCP device to be run on
  * @ret: operation return code (ccp driver use only)
  * @flags: cmd processing flags
  * @engine: CCP operation to perform
@@ -587,6 +652,7 @@ struct ccp_cmd {
 	union {
 		struct ccp_aes_engine aes;
 		struct ccp_xts_aes_engine xts;
+		struct ccp_des3_engine des3;
 		struct ccp_sha_engine sha;
 		struct ccp_rsa_engine rsa;
 		struct ccp_passthru_engine passthru;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 1816c5e26581..88cd5dc8e238 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -48,6 +48,7 @@ struct ceph_options {
 	unsigned long mount_timeout;		/* jiffies */
 	unsigned long osd_idle_ttl;		/* jiffies */
 	unsigned long osd_keepalive_timeout;	/* jiffies */
+	unsigned long osd_request_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -68,6 +69,7 @@ struct ceph_options {
 #define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
 #define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
 #define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
+#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0  /* no timeout */
 
 #define CEPH_MONC_HUNT_INTERVAL		msecs_to_jiffies(3 * 1000)
 #define CEPH_MONC_PING_INTERVAL		msecs_to_jiffies(10 * 1000)
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 2ea0c282f3dc..c125b5d9e13c 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -189,6 +189,7 @@ struct ceph_osd_request {
 
 	/* internal */
 	unsigned long r_stamp;                /* jiffies, send or check time */
+	unsigned long r_start_stamp;          /* jiffies */
 	int r_attempts;
 	struct ceph_eversion r_replay_version; /* aka reassert_version */
 	u32 r_last_force_resend;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 6a3f850cabab..21745946cae1 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -13,6 +13,7 @@
 #include <linux/wait.h>
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
+#include <linux/refcount.h>
 #include <linux/percpu-refcount.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/workqueue.h>
@@ -106,9 +107,6 @@ struct cgroup_subsys_state {
 	/* reference count - access via css_[try]get() and css_put() */
 	struct percpu_ref refcnt;
 
-	/* PI: the parent css */
-	struct cgroup_subsys_state *parent;
-
 	/* siblings list anchored at the parent's ->children */
 	struct list_head sibling;
 	struct list_head children;
@@ -138,6 +136,12 @@ struct cgroup_subsys_state {
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
+
+	/*
+	 * PI: the parent css.	Placed here for cache proximity to following
+	 * fields of the containing structure.
+	 */
+	struct cgroup_subsys_state *parent;
 };
 
 /*
@@ -156,7 +160,7 @@ struct css_set {
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
 
 	/* reference count */
-	atomic_t refcount;
+	refcount_t refcount;
 
 	/* the default cgroup associated with this css_set */
 	struct cgroup *dfl_cgrp;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f6b43fbb141c..ed2573e149fa 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -17,11 +17,11 @@
 #include <linux/seq_file.h>
 #include <linux/kernfs.h>
 #include <linux/jump_label.h>
-#include <linux/nsproxy.h>
 #include <linux/types.h>
 #include <linux/ns_common.h>
 #include <linux/nsproxy.h>
 #include <linux/user_namespace.h>
+#include <linux/refcount.h>
 
 #include <linux/cgroup-defs.h>
 
@@ -570,6 +570,25 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
+static inline void cgroup_init_kthreadd(void)
+{
+	/*
+	 * kthreadd is inherited by all kthreads, keep it in the root so
+	 * that the new kthreads are guaranteed to stay in the root until
+	 * initialization is finished.
+	 */
+	current->no_cgroup_migration = 1;
+}
+
+static inline void cgroup_kthread_ready(void)
+{
+	/*
+	 * This kthread finished initialization.  The creator should have
+	 * set PF_NO_SETAFFINITY if this kthread should stay in the root.
+	 */
+	current->no_cgroup_migration = 0;
+}
+
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
@@ -590,6 +609,8 @@ static inline void cgroup_free(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
+static inline void cgroup_init_kthreadd(void) {}
+static inline void cgroup_kthread_ready(void) {}
 
 static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 					       struct cgroup *ancestor)
@@ -640,7 +661,7 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 #endif	/* CONFIG_CGROUP_DATA */
 
 struct cgroup_namespace {
-	atomic_t		count;
+	refcount_t		count;
 	struct ns_common	ns;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
@@ -675,12 +696,12 @@ copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
 static inline void get_cgroup_ns(struct cgroup_namespace *ns)
 {
 	if (ns)
-		atomic_inc(&ns->count);
+		refcount_inc(&ns->count);
 }
 
 static inline void put_cgroup_ns(struct cgroup_namespace *ns)
 {
-	if (ns && atomic_dec_and_test(&ns->count))
+	if (ns && refcount_dec_and_test(&ns->count))
 		free_cgroup_ns(ns);
 }
 
diff --git a/include/linux/clk.h b/include/linux/clk.h
index e9d36b3e49de..024cd07870d0 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -132,8 +132,8 @@ int clk_get_phase(struct clk *clk);
  * @q: clk compared against p
  *
  * Returns true if the two struct clk pointers both point to the same hardware
- * clock node. Put differently, returns true if struct clk *p and struct clk *q
- * share the same struct clk_core object.
+ * clock node. Put differently, returns true if @p and @q
+ * share the same &struct clk_core object.
  *
  * Returns false otherwise. Note that two NULL clks are treated as matching.
  */
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 5d3053c34fb3..acc9ce05e5f0 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -182,7 +182,6 @@ extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *e
 extern void clockevents_register_device(struct clock_event_device *dev);
 extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu);
 
-extern void clockevents_config(struct clock_event_device *dev, u32 freq);
 extern void clockevents_config_and_register(struct clock_event_device *dev,
 					    u32 freq, unsigned long min_delta,
 					    unsigned long max_delta);
@@ -229,7 +228,7 @@ static inline void tick_setup_hrtimer_broadcast(void) { }
 
 #ifdef CONFIG_CLKEVT_PROBE
 extern int clockevent_probe(void);
-#els
+#else
 static inline int clockevent_probe(void) { return 0; }
 #endif
 
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index cfc75848a35d..f2b10d9ebd04 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -120,7 +120,7 @@ struct clocksource {
 #define CLOCK_SOURCE_RESELECT			0x100
 
 /* simplify initialization of mask field */
-#define CLOCKSOURCE_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
+#define CLOCKSOURCE_MASK(bits) GENMASK_ULL((bits) - 1, 0)
 
 static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from)
 {
diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h
index 5b8721efa948..31e4e1f1547c 100644
--- a/include/linux/coda_psdev.h
+++ b/include/linux/coda_psdev.h
@@ -15,7 +15,6 @@ struct venus_comm {
 	struct list_head    vc_processing;
 	int                 vc_inuse;
 	struct super_block *vc_sb;
-	struct backing_dev_info bdi;
 	struct mutex	    vc_mutex;
 };
 
diff --git a/include/linux/compat.h b/include/linux/compat.h
index aef47be2a5c1..8172b03685f9 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -528,11 +528,6 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd,
 asmlinkage long compat_sys_getdents(unsigned int fd,
 				    struct compat_linux_dirent __user *dirent,
 				    unsigned int count);
-#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64
-asmlinkage long compat_sys_getdents64(unsigned int fd,
-				      struct linux_dirent64 __user *dirent,
-				      unsigned int count);
-#endif
 asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *,
 				    unsigned int nr_segs, unsigned int flags);
 asmlinkage long compat_sys_open(const char __user *filename, int flags,
@@ -723,6 +718,8 @@ asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32,
 					    int, const char __user *);
 
+asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2);
+
 /*
  * For most but not all architectures, "am I in a compat syscall?" and
  * "am I a compat task?" are the same question.  For architectures on which
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 2a5982c37dfb..035c16c9a505 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -201,7 +201,7 @@ struct coresight_ops_sink {
 			  void *sink_config);
 	unsigned long (*reset_buffer)(struct coresight_device *csdev,
 				      struct perf_output_handle *handle,
-				      void *sink_config, bool *lost);
+				      void *sink_config);
 	void (*update_buffer)(struct coresight_device *csdev,
 			      struct perf_output_handle *handle,
 			      void *sink_config);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 87165f06a307..a5ce0bbeadb5 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -120,6 +120,13 @@ struct cpufreq_policy {
 	bool			fast_switch_possible;
 	bool			fast_switch_enabled;
 
+	/*
+	 * Preferred average time interval between consecutive invocations of
+	 * the driver to set the frequency for this policy.  To be set by the
+	 * scaling driver (0, which is the default, means no preference).
+	 */
+	unsigned int		transition_delay_us;
+
 	 /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
 	unsigned int cached_target_freq;
 	int cached_resolved_idx;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 96f1e88b767c..1a675604b17d 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -667,6 +667,11 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
 
+static inline bool cpumask_available(cpumask_var_t mask)
+{
+	return mask != NULL;
+}
+
 #else
 typedef struct cpumask cpumask_var_t[1];
 
@@ -708,6 +713,11 @@ static inline void free_cpumask_var(cpumask_var_t mask)
 static inline void free_bootmem_cpumask_var(cpumask_var_t mask)
 {
 }
+
+static inline bool cpumask_available(cpumask_var_t mask)
+{
+	return true;
+}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
 /* It's common to want to use cpu_all_mask in struct member initializers,
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 611fce58d670..119a3f9604b0 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -42,7 +42,7 @@ static inline void cpuset_dec(void)
 
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
-extern void cpuset_update_active_cpus(bool cpu_online);
+extern void cpuset_update_active_cpus(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -155,7 +155,7 @@ static inline bool cpusets_enabled(void) { return false; }
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
 
-static inline void cpuset_update_active_cpus(bool cpu_online)
+static inline void cpuset_update_active_cpus(void)
 {
 	partition_sched_domains(1, NULL, NULL);
 }
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index c0b0cf3d2d2f..84da9978e951 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -123,7 +123,7 @@
 /*
  * Miscellaneous stuff.
  */
-#define CRYPTO_MAX_ALG_NAME		64
+#define CRYPTO_MAX_ALG_NAME		128
 
 /*
  * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual
diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h
index 3252799832cf..df4d3e943d28 100644
--- a/include/linux/cryptohash.h
+++ b/include/linux/cryptohash.h
@@ -10,9 +10,4 @@
 void sha_init(__u32 *buf);
 void sha_transform(__u32 *digest, const char *data, __u32 *W);
 
-#define MD5_DIGEST_WORDS 4
-#define MD5_MESSAGE_BYTES 64
-
-void md5_transform(__u32 *hash, __u32 const *in);
-
 #endif
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 61d042bbbf60..68449293c4b6 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -163,6 +163,7 @@ struct dccp_request_sock {
 	__u64			 dreq_isr;
 	__u64			 dreq_gsr;
 	__be32			 dreq_service;
+	spinlock_t		 dreq_lock;
 	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;
diff --git a/include/linux/dell-led.h b/include/linux/dell-led.h
index 7009b8bec77b..3f033c48071e 100644
--- a/include/linux/dell-led.h
+++ b/include/linux/dell-led.h
@@ -1,10 +1,6 @@
 #ifndef __DELL_LED_H__
 #define __DELL_LED_H__
 
-enum {
-	DELL_LED_MICMUTE,
-};
-
-int dell_app_wmi_led_set(int whichled, int on);
+int dell_micmute_led_set(int on);
 
 #endif
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index e0acb0e5243b..6c220e4ebb6b 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -27,6 +27,7 @@
 #define DEVFREQ_POSTCHANGE		(1)
 
 struct devfreq;
+struct devfreq_governor;
 
 /**
  * struct devfreq_dev_status - Data given from devfreq user device to
@@ -101,35 +102,6 @@ struct devfreq_dev_profile {
 };
 
 /**
- * struct devfreq_governor - Devfreq policy governor
- * @node:		list node - contains registered devfreq governors
- * @name:		Governor's name
- * @immutable:		Immutable flag for governor. If the value is 1,
- *			this govenror is never changeable to other governor.
- * @get_target_freq:	Returns desired operating frequency for the device.
- *			Basically, get_target_freq will run
- *			devfreq_dev_profile.get_dev_status() to get the
- *			status of the device (load = busy_time / total_time).
- *			If no_central_polling is set, this callback is called
- *			only with update_devfreq() notified by OPP.
- * @event_handler:      Callback for devfreq core framework to notify events
- *                      to governors. Events include per device governor
- *                      init and exit, opp changes out of devfreq, suspend
- *                      and resume of per device devfreq during device idle.
- *
- * Note that the callbacks are called with devfreq->lock locked by devfreq.
- */
-struct devfreq_governor {
-	struct list_head node;
-
-	const char name[DEVFREQ_NAME_LEN];
-	const unsigned int immutable;
-	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
-	int (*event_handler)(struct devfreq *devfreq,
-				unsigned int event, void *data);
-};
-
-/**
  * struct devfreq - Device devfreq structure
  * @node:	list node - contains the devices with devfreq that have been
  *		registered.
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index a7e6903866fd..c7ea33e38fb9 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -255,6 +255,12 @@ struct dm_target {
 	unsigned num_write_same_bios;
 
 	/*
+	 * The number of WRITE ZEROES bios that will be submitted to the target.
+	 * The bio number can be accessed with dm_bio_get_target_bio_nr.
+	 */
+	unsigned num_write_zeroes_bios;
+
+	/*
 	 * The minimum number of extra bytes allocated in each io for the
 	 * target to use.
 	 */
@@ -290,11 +296,6 @@ struct dm_target {
 	 * on max_io_len boundary.
 	 */
 	bool split_discard_bios:1;
-
-	/*
-	 * Set if this target does not return zeroes on discarded blocks.
-	 */
-	bool discard_zeroes_data_unsupported:1;
 };
 
 /* Each target can link one of these into the table */
diff --git a/include/linux/device.h b/include/linux/device.h
index 30c4570e928d..9ef518af5515 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1140,7 +1140,6 @@ static inline bool device_supports_offline(struct device *dev)
 extern void lock_device_hotplug(void);
 extern void unlock_device_hotplug(void);
 extern int lock_device_hotplug_sysfs(void);
-void assert_held_device_hotplug(void);
 extern int device_offline(struct device *dev);
 extern int device_online(struct device *dev);
 extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 5b6adf964248..8ae0f45fafd6 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -28,12 +28,10 @@ struct device;
 #define EDAC_OPSTATE_INT	2
 
 extern int edac_op_state;
-extern int edac_err_assert;
-extern atomic_t edac_handlers;
 
-extern int edac_handler_set(void);
-extern void edac_atomic_assert_error(void);
-extern struct bus_type *edac_get_sysfs_subsys(void);
+struct bus_type *edac_get_sysfs_subsys(void);
+int edac_get_report_status(void);
+void edac_set_report_status(int new);
 
 enum {
 	EDAC_REPORTING_ENABLED,
@@ -41,28 +39,6 @@ enum {
 	EDAC_REPORTING_FORCE
 };
 
-extern int edac_report_status;
-#ifdef CONFIG_EDAC
-static inline int get_edac_report_status(void)
-{
-	return edac_report_status;
-}
-
-static inline void set_edac_report_status(int new)
-{
-	edac_report_status = new;
-}
-#else
-static inline int get_edac_report_status(void)
-{
-	return EDAC_REPORTING_DISABLED;
-}
-
-static inline void set_edac_report_status(int new)
-{
-}
-#endif
-
 static inline void opstate_init(void)
 {
 	switch (edac_op_state) {
diff --git a/include/linux/efi-bgrt.h b/include/linux/efi-bgrt.h
index 2fd3993c370b..e6f624b53c3d 100644
--- a/include/linux/efi-bgrt.h
+++ b/include/linux/efi-bgrt.h
@@ -6,6 +6,7 @@
 #ifdef CONFIG_ACPI_BGRT
 
 void efi_bgrt_init(struct acpi_table_header *table);
+int __init acpi_parse_bgrt(struct acpi_table_header *table);
 
 /* The BGRT data itself; only valid if bgrt_image != NULL. */
 extern size_t bgrt_image_size;
@@ -14,6 +15,10 @@ extern struct acpi_table_bgrt bgrt_tab;
 #else /* !CONFIG_ACPI_BGRT */
 
 static inline void efi_bgrt_init(struct acpi_table_header *table) {}
+static inline int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+	return 0;
+}
 
 #endif /* !CONFIG_ACPI_BGRT */
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 94d34e0be24f..ec36f42a2add 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1435,9 +1435,6 @@ static inline int efi_runtime_map_copy(void *buf, size_t bufsz)
 
 /* prototypes shared between arch specific and generic stub code */
 
-#define pr_efi(sys_table, msg)     efi_printk(sys_table, "EFI stub: "msg)
-#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
-
 void efi_printk(efi_system_table_t *sys_table_arg, char *str);
 
 void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
@@ -1471,7 +1468,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 				  unsigned long *load_addr,
 				  unsigned long *load_size);
 
-efi_status_t efi_parse_options(char *cmdline);
+efi_status_t efi_parse_options(char const *cmdline);
 
 efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg,
 			   struct screen_info *si, efi_guid_t *proto,
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index aebecc4ed088..3a216318ae73 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -93,6 +93,8 @@ struct blk_mq_hw_ctx;
 struct elevator_mq_ops {
 	int (*init_sched)(struct request_queue *, struct elevator_type *);
 	void (*exit_sched)(struct elevator_queue *);
+	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 
 	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
 	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
@@ -104,7 +106,7 @@ struct elevator_mq_ops {
 	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
 	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
 	bool (*has_work)(struct blk_mq_hw_ctx *);
-	void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
+	void (*completed_request)(struct request *);
 	void (*started_request)(struct request *);
 	void (*requeue_request)(struct request *);
 	struct request *(*former_request)(struct request_queue *, struct request *);
@@ -211,7 +213,7 @@ extern ssize_t elv_iosched_show(struct request_queue *, char *);
 extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 
 extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct elevator_queue *);
+extern void elevator_exit(struct request_queue *, struct elevator_queue *);
 extern int elevator_change(struct request_queue *, const char *);
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h
index 9ca23fcfb5d7..6fdfc884fdeb 100644
--- a/include/linux/errqueue.h
+++ b/include/linux/errqueue.h
@@ -20,6 +20,8 @@ struct sock_exterr_skb {
 	struct sock_extended_err	ee;
 	u16				addr_offset;
 	__be16				port;
+	u8				opt_stats:1,
+					unused:7;
 };
 
 #endif
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index c62b709b1ce0..2d9f80848d4b 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -447,21 +447,6 @@ static inline void eth_addr_dec(u8 *addr)
 }
 
 /**
- * ether_addr_greater - Compare two Ethernet addresses
- * @addr1: Pointer to a six-byte array containing the Ethernet address
- * @addr2: Pointer other six-byte array containing the Ethernet address
- *
- * Compare two Ethernet addresses, returns true addr1 is greater than addr2
- */
-static inline bool ether_addr_greater(const u8 *addr1, const u8 *addr2)
-{
-	u64 u1 = ether_addr_to_u64(addr1);
-	u64 u2 = ether_addr_to_u64(addr2);
-
-	return u1 > u2;
-}
-
-/**
  * is_etherdev_addr - Tell if given Ethernet address belongs to the device.
  * @dev: Pointer to a device structure
  * @addr: Pointer to a six-byte array containing the Ethernet address
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 9ded8c6d8176..83cc9863444b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -60,6 +60,7 @@ enum ethtool_phys_id_state {
 enum {
 	ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */
 	ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */
+	ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */
 
 	/*
 	 * Add your fresh new hash function bits above and remember to update
@@ -73,6 +74,7 @@ enum {
 
 #define ETH_RSS_HASH_TOP	__ETH_RSS_HASH(TOP)
 #define ETH_RSS_HASH_XOR	__ETH_RSS_HASH(XOR)
+#define ETH_RSS_HASH_CRC32	__ETH_RSS_HASH(CRC32)
 
 #define ETH_RSS_HASH_UNKNOWN	0
 #define ETH_RSS_HASH_NO_CHANGE	0
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 7010fb01a81a..7e206a9f88db 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -236,11 +236,11 @@ extern int extcon_set_property_capability(struct extcon_dev *edev,
 				unsigned int id, unsigned int prop);
 
 /*
- * Following APIs are to monitor every action of a notifier.
- * Registrar gets notified for every external port of a connection device.
- * Probably this could be used to debug an action of notifier; however,
- * we do not recommend to use this for normal 'notifiee' device drivers who
- * want to be notified by a specific external port of the notifier.
+ * Following APIs are to monitor the status change of the external connectors.
+ * extcon_register_notifier(*edev, id, *nb) : Register a notifier block
+ *			for specific external connector of the extcon.
+ * extcon_register_notifier_all(*edev, *nb) : Register a notifier block
+ *			for all supported external connectors of the extcon.
  */
 extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id,
 				    struct notifier_block *nb);
@@ -253,6 +253,17 @@ extern void devm_extcon_unregister_notifier(struct device *dev,
 				struct extcon_dev *edev, unsigned int id,
 				struct notifier_block *nb);
 
+extern int extcon_register_notifier_all(struct extcon_dev *edev,
+				struct notifier_block *nb);
+extern int extcon_unregister_notifier_all(struct extcon_dev *edev,
+				struct notifier_block *nb);
+extern int devm_extcon_register_notifier_all(struct device *dev,
+				struct extcon_dev *edev,
+				struct notifier_block *nb);
+extern void devm_extcon_unregister_notifier_all(struct device *dev,
+				struct extcon_dev *edev,
+				struct notifier_block *nb);
+
 /*
  * Following API get the extcon device from devicetree.
  * This function use phandle of devicetree to get extcon device directly.
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0c167fdee5f7..9a7786db14fa 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -7,6 +7,7 @@
 #include <stdarg.h>
 
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
 #include <linux/linkage.h>
@@ -409,10 +410,10 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	kmemcheck_bitfield_begin(meta);
 	u16			jited:1,	/* Is our filter JIT'ed? */
+				locked:1,	/* Program image locked? */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
-				dst_needed:1,	/* Do we need dst entry? */
-				xdp_adjust_head:1; /* Adjusting pkt head? */
+				dst_needed:1;	/* Do we need dst entry? */
 	kmemcheck_bitfield_end(meta);
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	u32			len;		/* Number of filter blocks */
@@ -429,7 +430,7 @@ struct bpf_prog {
 };
 
 struct sk_filter {
-	atomic_t	refcnt;
+	refcount_t	refcnt;
 	struct rcu_head	rcu;
 	struct bpf_prog	*prog;
 };
@@ -554,22 +555,29 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog)
 #ifdef CONFIG_ARCH_HAS_SET_MEMORY
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	set_memory_ro((unsigned long)fp, fp->pages);
+	fp->locked = 1;
+	WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
-	set_memory_rw((unsigned long)fp, fp->pages);
+	if (fp->locked) {
+		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
+		/* In case set_memory_rw() fails, we want to be the first
+		 * to crash here instead of some random place later on.
+		 */
+		fp->locked = 0;
+	}
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-	set_memory_ro((unsigned long)hdr, hdr->pages);
+	WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
-	set_memory_rw((unsigned long)hdr, hdr->pages);
+	WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
 }
 #else
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
@@ -685,6 +693,11 @@ static inline bool bpf_jit_is_ebpf(void)
 # endif
 }
 
+static inline bool ebpf_jit_enabled(void)
+{
+	return bpf_jit_enable && bpf_jit_is_ebpf();
+}
+
 static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
 {
 	return fp->jited && bpf_jit_is_ebpf();
@@ -745,6 +758,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp);
 
 #else /* CONFIG_BPF_JIT */
 
+static inline bool ebpf_jit_enabled(void)
+{
+	return false;
+}
+
 static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
 {
 	return false;
diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h
index b6efb0c64408..11366b3ff0b4 100644
--- a/include/linux/flex_array.h
+++ b/include/linux/flex_array.h
@@ -61,16 +61,83 @@ struct flex_array {
 			FLEX_ARRAY_ELEMENTS_PER_PART(__element_size));	\
 	}
 
+/**
+ * flex_array_alloc() - Creates a flexible array.
+ * @element_size:	individual object size.
+ * @total:		maximum number of objects which can be stored.
+ * @flags:		GFP flags
+ *
+ * Return:		Returns an object of structure flex_array.
+ */
 struct flex_array *flex_array_alloc(int element_size, unsigned int total,
 		gfp_t flags);
+
+/**
+ * flex_array_prealloc() - Ensures that memory for the elements indexed in the
+ * range defined by start and nr_elements has been allocated.
+ * @fa:			array to allocate memory to.
+ * @start:		start address
+ * @nr_elements:	number of elements to be allocated.
+ * @flags:		GFP flags
+ *
+ */
 int flex_array_prealloc(struct flex_array *fa, unsigned int start,
 		unsigned int nr_elements, gfp_t flags);
+
+/**
+ * flex_array_free() - Removes all elements of a flexible array.
+ * @fa:		array to be freed.
+ */
 void flex_array_free(struct flex_array *fa);
+
+/**
+ * flex_array_free_parts() - Removes all elements of a flexible array, but
+ * leaves the array itself in place.
+ * @fa:		array to be emptied.
+ */
 void flex_array_free_parts(struct flex_array *fa);
+
+/**
+ * flex_array_put() - Stores data into a flexible array.
+ * @fa:		array where element is to be stored.
+ * @element_nr:	position to copy, must be less than the maximum specified when
+ *		the array was created.
+ * @src:	data source to be copied into the array.
+ * @flags:	GFP flags
+ *
+ * Return:	Returns zero on success, a negative error code otherwise.
+ */
 int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
 		gfp_t flags);
+
+/**
+ * flex_array_clear() - Clears an individual element in the array, sets the
+ * given element to FLEX_ARRAY_FREE.
+ * @element_nr:	element position to clear.
+ * @fa:		array to which element to be cleared belongs.
+ *
+ * Return:	Returns zero on success, -EINVAL otherwise.
+ */
 int flex_array_clear(struct flex_array *fa, unsigned int element_nr);
+
+/**
+ * flex_array_get() - Retrieves data into a flexible array.
+ *
+ * @element_nr:	Element position to retrieve data from.
+ * @fa:		array from which data is to be retrieved.
+ *
+ * Return:	Returns a pointer to the data element, or NULL if that
+ *		particular element has never been allocated.
+ */
 void *flex_array_get(struct flex_array *fa, unsigned int element_nr);
+
+/**
+ * flex_array_shrink() - Reduces the allocated size of an array.
+ * @fa:		array to shrink.
+ *
+ * Return:	Returns number of pages of memory actually freed.
+ *
+ */
 int flex_array_shrink(struct flex_array *fa);
 
 #define flex_array_put_ptr(fa, nr, src, gfp) \
diff --git a/include/linux/fs.h b/include/linux/fs.h
index aad3fd0ff5f8..30e5c14bd743 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2121,6 +2121,9 @@ extern int vfs_ustat(dev_t, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
 extern bool our_mnt(struct vfsmount *mnt);
+extern __printf(2, 3)
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
+extern int super_setup_bdi(struct super_block *sb);
 
 extern int current_umask(void);
 
@@ -2678,7 +2681,7 @@ static const char * const kernel_read_file_str[] = {
 
 static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 {
-	if (id < 0 || id >= READING_MAX_ID)
+	if ((unsigned)id >= READING_MAX_ID)
 		return kernel_read_file_str[READING_UNKNOWN];
 
 	return kernel_read_file_str[id];
diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h
index 547f81592ba1..10c1abfbac6c 100644
--- a/include/linux/fscrypt_common.h
+++ b/include/linux/fscrypt_common.h
@@ -87,7 +87,6 @@ struct fscrypt_operations {
 	unsigned int flags;
 	const char *key_prefix;
 	int (*get_context)(struct inode *, void *, size_t);
-	int (*prepare_context)(struct inode *);
 	int (*set_context)(struct inode *, const void *, size_t, void *);
 	int (*dummy_context)(struct inode *);
 	bool (*is_encrypted)(struct inode *);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 8bd28ce6d76e..3dff2398a5f0 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -27,4 +27,16 @@ struct fwnode_handle {
 	struct fwnode_handle *secondary;
 };
 
+/**
+ * struct fwnode_endpoint - Fwnode graph endpoint
+ * @port: Port number
+ * @id: Endpoint id
+ * @local_fwnode: reference to the related fwnode
+ */
+struct fwnode_endpoint {
+	unsigned int port;
+	unsigned int id;
+	const struct fwnode_handle *local_fwnode;
+};
+
 #endif
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a999d281a2f1..acff9437e5c3 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -159,21 +159,14 @@ struct badblocks;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 struct blk_integrity {
-	struct blk_integrity_profile	*profile;
-	unsigned char			flags;
-	unsigned char			tuple_size;
-	unsigned char			interval_exp;
-	unsigned char			tag_size;
+	const struct blk_integrity_profile	*profile;
+	unsigned char				flags;
+	unsigned char				tuple_size;
+	unsigned char				interval_exp;
+	unsigned char				tag_size;
 };
 
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
-struct disk_devt {
-	atomic_t count;
-	void (*release)(struct disk_devt *disk_devt);
-};
-
-void put_disk_devt(struct disk_devt *disk_devt);
-void get_disk_devt(struct disk_devt *disk_devt);
 
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
@@ -183,7 +176,6 @@ struct gendisk {
 	int first_minor;
 	int minors;                     /* maximum number of minors, =1 for
                                          * disks that can't be partitioned. */
-	struct disk_devt *disk_devt;
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, umode_t *mode);
@@ -730,11 +722,9 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 extern void blk_integrity_add(struct gendisk *);
 extern void blk_integrity_del(struct gendisk *);
-extern void blk_integrity_revalidate(struct gendisk *);
 #else	/* CONFIG_BLK_DEV_INTEGRITY */
 static inline void blk_integrity_add(struct gendisk *disk) { }
 static inline void blk_integrity_del(struct gendisk *disk) { }
-static inline void blk_integrity_revalidate(struct gendisk *disk) { }
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
 
 #else /* CONFIG_BLOCK */
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 2484b2fcc6eb..933d93656605 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -143,15 +143,6 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev,
 						struct fwnode_handle *child,
 						enum gpiod_flags flags,
 						const char *label);
-/* FIXME: delete this helper when users are switched over */
-static inline struct gpio_desc *devm_get_gpiod_from_child(struct device *dev,
-			  const char *con_id, struct fwnode_handle *child)
-{
-	return devm_fwnode_get_index_gpiod_from_child(dev, con_id,
-						      0, child,
-						      GPIOD_ASIS,
-						      "?");
-}
 
 #else /* CONFIG_GPIOLIB */
 
@@ -444,13 +435,6 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev,
 	return ERR_PTR(-ENOSYS);
 }
 
-/* FIXME: delete this when all users are switched over */
-static inline struct gpio_desc *devm_get_gpiod_from_child(struct device *dev,
-			  const char *con_id, struct fwnode_handle *child)
-{
-	return ERR_PTR(-ENOSYS);
-}
-
 #endif /* CONFIG_GPIOLIB */
 
 static inline
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 28f38e2b8f30..5be325d890d9 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -268,6 +268,8 @@ struct hid_item {
 #define HID_CP_APPLICATIONLAUNCHBUTTONS	0x000c0180
 #define HID_CP_GENERICGUIAPPLICATIONCONTROLS	0x000c0200
 
+#define HID_DG_DEVICECONFIG	0x000d000e
+#define HID_DG_DEVICESETTINGS	0x000d0023
 #define HID_DG_CONFIDENCE	0x000d0047
 #define HID_DG_WIDTH		0x000d0048
 #define HID_DG_HEIGHT		0x000d0049
@@ -322,7 +324,7 @@ struct hid_item {
 #define HID_QUIRK_MULTI_INPUT			0x00000040
 #define HID_QUIRK_HIDINPUT_FORCE		0x00000080
 #define HID_QUIRK_NO_EMPTY_INPUT		0x00000100
-#define HID_QUIRK_NO_INIT_INPUT_REPORTS		0x00000200
+/* 0x00000200 reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */
 #define HID_QUIRK_ALWAYS_POLL			0x00000400
 #define HID_QUIRK_SKIP_OUTPUT_REPORTS		0x00010000
 #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID		0x00020000
@@ -541,7 +543,6 @@ struct hid_device {							/* device report descriptor */
 	struct list_head inputs;					/* The list of inputs */
 	void *hiddev;							/* The hiddev structure */
 	void *hidraw;
-	int minor;							/* Hiddev minor number */
 
 	int open;							/* is the device open by anyone? */
 	char name[128];							/* Device name */
diff --git a/include/linux/hiddev.h b/include/linux/hiddev.h
index a5dd8148660b..921622222957 100644
--- a/include/linux/hiddev.h
+++ b/include/linux/hiddev.h
@@ -32,6 +32,18 @@
  * In-kernel definitions.
  */
 
+struct hiddev {
+	int minor;
+	int exist;
+	int open;
+	struct mutex existancelock;
+	wait_queue_head_t wait;
+	struct hid_device *hid;
+	struct list_head list;
+	spinlock_t list_lock;
+	bool initialized;
+};
+
 struct hid_device;
 struct hid_usage;
 struct hid_field;
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 249e579ecd4c..8c5b10eb7265 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -276,8 +276,6 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 	return timer->base->cpu_base->hres_active;
 }
 
-extern void hrtimer_peek_ahead_timers(void);
-
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -300,8 +298,6 @@ extern unsigned int hrtimer_resolution;
 
 #define hrtimer_resolution	(unsigned int)LOW_RES_NSEC
 
-static inline void hrtimer_peek_ahead_timers(void) { }
-
 static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 {
 	return 0;
@@ -456,7 +452,7 @@ static inline u64 hrtimer_forward_now(struct hrtimer *timer,
 }
 
 /* Precise sleep: */
-extern long hrtimer_nanosleep(struct timespec *rqtp,
+extern long hrtimer_nanosleep(struct timespec64 *rqtp,
 			      struct timespec __user *rmtp,
 			      const enum hrtimer_mode mode,
 			      const clockid_t clockid);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 503099d8aada..b857fc8cc2ec 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -122,7 +122,7 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
 int pmd_huge(pmd_t pmd);
-int pud_huge(pud_t pmd);
+int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
@@ -197,6 +197,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 #ifndef pgd_huge
 #define pgd_huge(x)	0
 #endif
+#ifndef p4d_huge
+#define p4d_huge(x)	0
+#endif
 
 #ifndef pgd_write
 static inline int pgd_write(pgd_t pgd)
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 78d59dba563e..ceb751987c40 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -88,6 +88,7 @@ enum hwmon_temp_attributes {
 #define HWMON_T_CRIT_HYST	BIT(hwmon_temp_crit_hyst)
 #define HWMON_T_EMERGENCY	BIT(hwmon_temp_emergency)
 #define HWMON_T_EMERGENCY_HYST	BIT(hwmon_temp_emergency_hyst)
+#define HWMON_T_ALARM		BIT(hwmon_temp_alarm)
 #define HWMON_T_MIN_ALARM	BIT(hwmon_temp_min_alarm)
 #define HWMON_T_MAX_ALARM	BIT(hwmon_temp_max_alarm)
 #define HWMON_T_CRIT_ALARM	BIT(hwmon_temp_crit_alarm)
@@ -336,7 +337,7 @@ struct hwmon_ops {
 	int (*read)(struct device *dev, enum hwmon_sensor_types type,
 		    u32 attr, int channel, long *val);
 	int (*read_string)(struct device *dev, enum hwmon_sensor_types type,
-		    u32 attr, int channel, char **str);
+		    u32 attr, int channel, const char **str);
 	int (*write)(struct device *dev, enum hwmon_sensor_types type,
 		     u32 attr, int channel, long val);
 };
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 62bbf3c1aa4a..0c170a3f0d8b 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -845,6 +845,13 @@ struct vmbus_channel {
 	 * link up channels based on their CPU affinity.
 	 */
 	struct list_head percpu_list;
+
+	/*
+	 * Defer freeing channel until after all cpu's have
+	 * gone through grace period.
+	 */
+	struct rcu_head rcu;
+
 	/*
 	 * For performance critical channels (storage, networking
 	 * etc,), Hyper-V has a mechanism to enhance the throughput
@@ -1430,9 +1437,6 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
 				const int *srv_version, int srv_vercnt,
 				int *nego_fw_version, int *nego_srv_version);
 
-void hv_event_tasklet_disable(struct vmbus_channel *channel);
-void hv_event_tasklet_enable(struct vmbus_channel *channel);
-
 void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
 
 void vmbus_setevent(struct vmbus_channel *channel);
@@ -1504,14 +1508,6 @@ static inline  void hv_signal_on_read(struct vmbus_channel *channel)
 	return;
 }
 
-static inline void
-init_cached_read_index(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *rbi = &channel->inbound;
-
-	rbi->cached_read_index = rbi->ring_buffer->read_index;
-}
-
 /*
  * Mask off host interrupt callback notifications
  */
@@ -1545,76 +1541,48 @@ static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi)
 /*
  * An API to support in-place processing of incoming VMBUS packets.
  */
-#define VMBUS_PKT_TRAILER	8
 
-static inline struct vmpacket_descriptor *
-get_next_pkt_raw(struct vmbus_channel *channel)
+/* Get data payload associated with descriptor */
+static inline void *hv_pkt_data(const struct vmpacket_descriptor *desc)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 priv_read_loc = ring_info->priv_read_index;
-	void *ring_buffer = hv_get_ring_buffer(ring_info);
-	u32 dsize = ring_info->ring_datasize;
-	/*
-	 * delta is the difference between what is available to read and
-	 * what was already consumed in place. We commit read index after
-	 * the whole batch is processed.
-	 */
-	u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ?
-		priv_read_loc - ring_info->ring_buffer->read_index :
-		(dsize - ring_info->ring_buffer->read_index) + priv_read_loc;
-	u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
-
-	if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
-		return NULL;
-
-	return ring_buffer + priv_read_loc;
+	return (void *)((unsigned long)desc + (desc->offset8 << 3));
 }
 
-/*
- * A helper function to step through packets "in-place"
- * This API is to be called after each successful call
- * get_next_pkt_raw().
- */
-static inline void put_pkt_raw(struct vmbus_channel *channel,
-				struct vmpacket_descriptor *desc)
+/* Get data size associated with descriptor */
+static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 packetlen = desc->len8 << 3;
-	u32 dsize = ring_info->ring_datasize;
-
-	/*
-	 * Include the packet trailer.
-	 */
-	ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
-	ring_info->priv_read_index %= dsize;
+	return (desc->len8 << 3) - (desc->offset8 << 3);
 }
 
+
+struct vmpacket_descriptor *
+hv_pkt_iter_first(struct vmbus_channel *channel);
+
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+		   const struct vmpacket_descriptor *pkt);
+
+void hv_pkt_iter_close(struct vmbus_channel *channel);
+
 /*
- * This call commits the read index and potentially signals the host.
- * Here is the pattern for using the "in-place" consumption APIs:
- *
- * init_cached_read_index();
- *
- * while (get_next_pkt_raw() {
- *	process the packet "in-place";
- *	put_pkt_raw();
- * }
- * if (packets processed in place)
- *	commit_rd_index();
+ * Get next packet descriptor from iterator
+ * If at end of list, return NULL and update host.
  */
-static inline void commit_rd_index(struct vmbus_channel *channel)
+static inline struct vmpacket_descriptor *
+hv_pkt_iter_next(struct vmbus_channel *channel,
+		 const struct vmpacket_descriptor *pkt)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	/*
-	 * Make sure all reads are done before we update the read index since
-	 * the writer may start writing to the read area once the read index
-	 * is updated.
-	 */
-	virt_rmb();
-	ring_info->ring_buffer->read_index = ring_info->priv_read_index;
+	struct vmpacket_descriptor *nxt;
+
+	nxt = __hv_pkt_iter_next(channel, pkt);
+	if (!nxt)
+		hv_pkt_iter_close(channel);
 
-	hv_signal_on_read(channel);
+	return nxt;
 }
 
+#define foreach_vmbus_pkt(pkt, channel) \
+	for (pkt = hv_pkt_iter_first(channel); pkt; \
+	    pkt = hv_pkt_iter_next(channel, pkt))
 
 #endif /* _HYPERV_H */
diff --git a/include/linux/i2c/i2c-hid.h b/include/linux/i2c/i2c-hid.h
index 7aa901d92058..1fb088239d12 100644
--- a/include/linux/i2c/i2c-hid.h
+++ b/include/linux/i2c/i2c-hid.h
@@ -14,9 +14,13 @@
 
 #include <linux/types.h>
 
+struct regulator;
+
 /**
  * struct i2chid_platform_data - used by hid over i2c implementation.
  * @hid_descriptor_address: i2c register where the HID descriptor is stored.
+ * @supply: regulator for powering on the device.
+ * @post_power_delay_ms: delay after powering on before device is usable.
  *
  * Note that it is the responsibility of the platform driver (or the acpi 5.0
  * driver, or the flattened device tree) to setup the irq related to the gpio in
@@ -31,6 +35,8 @@
  */
 struct i2c_hid_platform_data {
 	u16 hid_descriptor_address;
+	struct regulator *supply;
+	int post_power_delay_ms;
 };
 
 #endif /* __LINUX_I2C_HID_H */
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 2f51c1724b5a..6980ca322074 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -88,7 +88,7 @@ static inline bool ata_pm_request(struct request *rq)
 		 ide_req(rq)->type == ATA_PRIV_PM_RESUME);
 }
 
-/* Error codes returned in rq->errors to the higher part of the driver. */
+/* Error codes returned in result to the higher part of the driver. */
 enum {
 	IDE_DRV_ERROR_GENERAL	= 101,
 	IDE_DRV_ERROR_FILEMARK	= 102,
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 0dd9498c694f..69033353d0d1 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -7,7 +7,7 @@
  * Copyright (c) 2005, Devicescape Software, Inc.
  * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
  * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright (c) 2016 Intel Deutschland GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -1411,6 +1411,8 @@ struct ieee80211_ht_operation {
 #define		IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED	3
 #define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT		0x0004
 #define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT		0x0010
+#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT		5
+#define IEEE80211_HT_OP_MODE_CCFS2_MASK			0x1fe0
 
 /* for stbc_param */
 #define IEEE80211_HT_STBC_PARAM_DUAL_BEACON		0x0040
@@ -1525,14 +1527,14 @@ enum ieee80211_vht_chanwidth {
  * This structure is the "VHT operation element" as
  * described in 802.11ac D3.0 8.4.2.161
  * @chan_width: Operating channel width
+ * @center_freq_seg0_idx: center freq segment 0 index
  * @center_freq_seg1_idx: center freq segment 1 index
- * @center_freq_seg2_idx: center freq segment 2 index
  * @basic_mcs_set: VHT Basic MCS rate set
  */
 struct ieee80211_vht_operation {
 	u8 chan_width;
+	u8 center_freq_seg0_idx;
 	u8 center_freq_seg1_idx;
-	u8 center_freq_seg2_idx;
 	__le16 basic_mcs_set;
 } __packed;
 
@@ -1721,6 +1723,9 @@ enum ieee80211_statuscode {
 	WLAN_STATUS_REJECT_DSE_BAND = 96,
 	WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99,
 	WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103,
+	/* 802.11ai */
+	WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108,
+	WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109,
 };
 
 
@@ -2102,6 +2107,12 @@ enum ieee80211_key_len {
 #define FILS_NONCE_LEN			16
 #define FILS_MAX_KEK_LEN		64
 
+#define FILS_ERP_MAX_USERNAME_LEN	16
+#define FILS_ERP_MAX_REALM_LEN		253
+#define FILS_ERP_MAX_RRK_LEN		64
+
+#define PMK_MAX_LEN			48
+
 /* Public action codes */
 enum ieee80211_pub_actioncode {
 	WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4,
@@ -2166,37 +2177,37 @@ enum ieee80211_tdls_actioncode {
 #define WLAN_BSS_COEX_INFORMATION_REQUEST	BIT(0)
 
 /**
- * enum - mesh synchronization method identifier
+ * enum ieee80211_mesh_sync_method - mesh synchronization method identifier
  *
  * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method
  * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method
  *	that will be specified in a vendor specific information element
  */
-enum {
+enum ieee80211_mesh_sync_method {
 	IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1,
 	IEEE80211_SYNC_METHOD_VENDOR = 255,
 };
 
 /**
- * enum - mesh path selection protocol identifier
+ * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier
  *
  * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol
  * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will
  *	be specified in a vendor specific information element
  */
-enum {
+enum ieee80211_mesh_path_protocol {
 	IEEE80211_PATH_PROTOCOL_HWMP = 1,
 	IEEE80211_PATH_PROTOCOL_VENDOR = 255,
 };
 
 /**
- * enum - mesh path selection metric identifier
+ * enum ieee80211_mesh_path_metric - mesh path selection metric identifier
  *
  * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric
  * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be
  *	specified in a vendor specific information element
  */
-enum {
+enum ieee80211_mesh_path_metric {
 	IEEE80211_PATH_METRIC_AIRTIME = 1,
 	IEEE80211_PATH_METRIC_VENDOR = 255,
 };
@@ -2305,6 +2316,32 @@ struct ieee80211_timeout_interval_ie {
 	__le32 value;
 } __packed;
 
+/**
+ * enum ieee80211_idle_options - BSS idle options
+ * @WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE: the station should send an RSN
+ *	protected frame to the AP to reset the idle timer at the AP for
+ *	the station.
+ */
+enum ieee80211_idle_options {
+	WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE = BIT(0),
+};
+
+/**
+ * struct ieee80211_bss_max_idle_period_ie
+ *
+ * This structure refers to "BSS Max idle period element"
+ *
+ * @max_idle_period: indicates the time period during which a station can
+ *	refrain from transmitting frames to its associated AP without being
+ *	disassociated. In units of 1000 TUs.
+ * @idle_options: indicates the options associated with the BSS idle capability
+ *	as specified in &enum ieee80211_idle_options.
+ */
+struct ieee80211_bss_max_idle_period_ie {
+	__le16 max_idle_period;
+	u8 idle_options;
+} __packed;
+
 /* BACK action code */
 enum ieee80211_back_actioncode {
 	WLAN_ACTION_ADDBA_REQ = 0,
@@ -2345,13 +2382,21 @@ enum ieee80211_sa_query_action {
 #define WLAN_CIPHER_SUITE_SMS4		SUITE(0x001472, 1)
 
 /* AKM suite selectors */
-#define WLAN_AKM_SUITE_8021X		SUITE(0x000FAC, 1)
-#define WLAN_AKM_SUITE_PSK		SUITE(0x000FAC, 2)
-#define WLAN_AKM_SUITE_8021X_SHA256	SUITE(0x000FAC, 5)
-#define WLAN_AKM_SUITE_PSK_SHA256	SUITE(0x000FAC, 6)
-#define WLAN_AKM_SUITE_TDLS		SUITE(0x000FAC, 7)
-#define WLAN_AKM_SUITE_SAE		SUITE(0x000FAC, 8)
-#define WLAN_AKM_SUITE_FT_OVER_SAE	SUITE(0x000FAC, 9)
+#define WLAN_AKM_SUITE_8021X			SUITE(0x000FAC, 1)
+#define WLAN_AKM_SUITE_PSK			SUITE(0x000FAC, 2)
+#define WLAN_AKM_SUITE_FT_8021X			SUITE(0x000FAC, 3)
+#define WLAN_AKM_SUITE_FT_PSK			SUITE(0x000FAC, 4)
+#define WLAN_AKM_SUITE_8021X_SHA256		SUITE(0x000FAC, 5)
+#define WLAN_AKM_SUITE_PSK_SHA256		SUITE(0x000FAC, 6)
+#define WLAN_AKM_SUITE_TDLS			SUITE(0x000FAC, 7)
+#define WLAN_AKM_SUITE_SAE			SUITE(0x000FAC, 8)
+#define WLAN_AKM_SUITE_FT_OVER_SAE		SUITE(0x000FAC, 9)
+#define WLAN_AKM_SUITE_8021X_SUITE_B		SUITE(0x000FAC, 11)
+#define WLAN_AKM_SUITE_8021X_SUITE_B_192	SUITE(0x000FAC, 12)
+#define WLAN_AKM_SUITE_FILS_SHA256		SUITE(0x000FAC, 14)
+#define WLAN_AKM_SUITE_FILS_SHA384		SUITE(0x000FAC, 15)
+#define WLAN_AKM_SUITE_FT_FILS_SHA256		SUITE(0x000FAC, 16)
+#define WLAN_AKM_SUITE_FT_FILS_SHA384		SUITE(0x000FAC, 17)
 
 #define WLAN_MAX_KEY_LEN		32
 
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index c5847dc75a93..0c16866a7aac 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -48,6 +48,7 @@ struct br_ip_list {
 #define BR_MCAST_FLOOD		BIT(11)
 #define BR_MULTICAST_TO_UNICAST	BIT(12)
 #define BR_VLAN_TUNNEL		BIT(13)
+#define BR_BCAST_FLOOD		BIT(14)
 
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
diff --git a/include/linux/iio/sw_device.h b/include/linux/iio/sw_device.h
index 23ca41515527..fa7931933067 100644
--- a/include/linux/iio/sw_device.h
+++ b/include/linux/iio/sw_device.h
@@ -62,7 +62,7 @@ void iio_swd_group_init_type_name(struct iio_sw_device *d,
 				  const char *name,
 				  struct config_item_type *type)
 {
-#ifdef CONFIG_CONFIGFS_FS
+#if IS_ENABLED(CONFIG_CONFIGFS_FS)
 	config_group_init_type_name(&d->group, name, type);
 #endif
 }
diff --git a/include/linux/inet.h b/include/linux/inet.h
index 4cca05c9678e..636ebe87e6f8 100644
--- a/include/linux/inet.h
+++ b/include/linux/inet.h
@@ -43,6 +43,8 @@
 #define _LINUX_INET_H
 
 #include <linux/types.h>
+#include <net/net_namespace.h>
+#include <linux/socket.h>
 
 /*
  * These mimic similar macros defined in user-space for inet_ntop(3).
@@ -54,4 +56,8 @@
 extern __be32 in_aton(const char *str);
 extern int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end);
 extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end);
+
+extern int inet_pton_with_scope(struct net *net, unsigned short af,
+		const char *src, const char *port, struct sockaddr_storage *addr);
+
 #endif	/* _LINUX_INET_H */
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ee971f335a8b..a2e9d6ea1349 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -153,8 +153,8 @@ struct in_ifaddr {
 int register_inetaddr_notifier(struct notifier_block *nb);
 int unregister_inetaddr_notifier(struct notifier_block *nb);
 
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				 struct ipv4_devconf *devconf);
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+				 int ifindex, struct ipv4_devconf *devconf);
 
 struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
 static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5a791055b176..82be96564266 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -182,6 +182,7 @@ extern struct cred init_cred;
 #ifdef CONFIG_RT_MUTEXES
 # define INIT_RT_MUTEXES(tsk)						\
 	.pi_waiters = RB_ROOT,						\
+	.pi_top_task = NULL,						\
 	.pi_waiters_leftmost = NULL,
 #else
 # define INIT_RT_MUTEXES(tsk)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 6a6de187ddc0..2e4de0deee53 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -125,9 +125,16 @@ enum iommu_attr {
 };
 
 /* These are the possible reserved region types */
-#define IOMMU_RESV_DIRECT	(1 << 0)
-#define IOMMU_RESV_RESERVED	(1 << 1)
-#define IOMMU_RESV_MSI		(1 << 2)
+enum iommu_resv_type {
+	/* Memory regions which must be mapped 1:1 at all times */
+	IOMMU_RESV_DIRECT,
+	/* Arbitrary "never map this or give it to a device" address ranges */
+	IOMMU_RESV_RESERVED,
+	/* Hardware MSI region (untranslated) */
+	IOMMU_RESV_MSI,
+	/* Software-managed MSI translation window */
+	IOMMU_RESV_SW_MSI,
+};
 
 /**
  * struct iommu_resv_region - descriptor for a reserved memory region
@@ -142,7 +149,7 @@ struct iommu_resv_region {
 	phys_addr_t		start;
 	size_t			length;
 	int			prot;
-	int			type;
+	enum iommu_resv_type	type;
 };
 
 #ifdef CONFIG_IOMMU_API
@@ -288,7 +295,8 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
 extern struct iommu_resv_region *
-iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, int type);
+iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot,
+			enum iommu_resv_type type);
 extern int iommu_get_group_resv_regions(struct iommu_group *group,
 					struct list_head *head);
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 71be5b330d21..e1b442996f81 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -37,6 +37,7 @@ struct ipv6_devconf {
 	__s32		accept_ra_rtr_pref;
 	__s32		rtr_probe_interval;
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	__s32		accept_ra_rt_info_min_plen;
 	__s32		accept_ra_rt_info_max_plen;
 #endif
 #endif
@@ -70,6 +71,7 @@ struct ipv6_devconf {
 #endif
 	__u32		enhanced_dad;
 	__u32		addr_gen_mode;
+	__s32		disable_policy;
 
 	struct ctl_table_header *sysctl_header;
 };
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 672cfef72fc8..97cbca19430d 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -373,6 +373,8 @@
 #define ICC_IGRPEN0_EL1_MASK		(1 << ICC_IGRPEN0_EL1_SHIFT)
 #define ICC_IGRPEN1_EL1_SHIFT		0
 #define ICC_IGRPEN1_EL1_MASK		(1 << ICC_IGRPEN1_EL1_SHIFT)
+#define ICC_SRE_EL1_DIB			(1U << 2)
+#define ICC_SRE_EL1_DFB			(1U << 1)
 #define ICC_SRE_EL1_SRE			(1U << 0)
 
 /*
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index eafc965b3eb8..dc30f3d057eb 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -96,6 +96,9 @@
 #define GICH_MISR_EOI			(1 << 0)
 #define GICH_MISR_U			(1 << 1)
 
+#define GICV_PMR_PRIORITY_SHIFT		3
+#define GICV_PMR_PRIORITY_MASK		(0x1f << GICV_PMR_PRIORITY_SHIFT)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/irqdomain.h>
diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h
index 7b49c71c968b..2b0e56619e53 100644
--- a/include/linux/irqchip/mips-gic.h
+++ b/include/linux/irqchip/mips-gic.h
@@ -258,7 +258,6 @@ extern unsigned int gic_present;
 extern void gic_init(unsigned long gic_base_addr,
 	unsigned long gic_addrspace_size, unsigned int cpu_vec,
 	unsigned int irqbase);
-extern void gic_clocksource_init(unsigned int);
 extern u64 gic_read_count(void);
 extern unsigned int gic_get_count_width(void);
 extern u64 gic_read_compare(void);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 188eced6813e..9f3616085423 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -524,6 +524,10 @@ static inline struct irq_domain *irq_find_matching_fwnode(
 {
 	return NULL;
 }
+static inline bool irq_domain_check_msi_remap(void)
+{
+	return false;
+}
 #endif /* !CONFIG_IRQ_DOMAIN */
 
 #endif /* _LINUX_IRQDOMAIN_H */
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8e06d758ee48..2afd74b9d844 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -90,6 +90,13 @@ extern bool static_key_initialized;
 struct static_key {
 	atomic_t enabled;
 /*
+ * Note:
+ *   To make anonymous unions work with old compilers, the static
+ *   initialization of them requires brackets. This creates a dependency
+ *   on the order of the struct with the initializers. If any fields
+ *   are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need
+ *   to be modified.
+ *
  * bit 0 => 1 if key is initially true
  *	    0 if initially false
  * bit 1 => 1 if points to struct static_key_mod
@@ -166,10 +173,10 @@ extern void static_key_disable(struct static_key *key);
  */
 #define STATIC_KEY_INIT_TRUE					\
 	{ .enabled = { 1 },					\
-	  .entries = (void *)JUMP_TYPE_TRUE }
+	  { .entries = (void *)JUMP_TYPE_TRUE } }
 #define STATIC_KEY_INIT_FALSE					\
 	{ .enabled = { 0 },					\
-	  .entries = (void *)JUMP_TYPE_FALSE }
+	  { .entries = (void *)JUMP_TYPE_FALSE } }
 
 #else  /* !HAVE_JUMP_LABEL */
 
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index ceb3fe78a0d3..a5c7046f26b4 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -6,6 +6,7 @@
 struct kmem_cache;
 struct page;
 struct vm_struct;
+struct task_struct;
 
 #ifdef CONFIG_KASAN
 
@@ -18,6 +19,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE];
 extern pte_t kasan_zero_pte[PTRS_PER_PTE];
 extern pmd_t kasan_zero_pmd[PTRS_PER_PMD];
 extern pud_t kasan_zero_pud[PTRS_PER_PUD];
+extern p4d_t kasan_zero_p4d[PTRS_PER_P4D];
 
 void kasan_populate_zero_shadow(const void *shadow_start,
 				const void *shadow_end);
@@ -74,6 +76,9 @@ size_t ksize(const void *);
 static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
 size_t kasan_metadata_size(struct kmem_cache *cache);
 
+bool kasan_save_enable_multi_shot(void);
+void kasan_restore_multi_shot(bool enabled);
+
 #else /* CONFIG_KASAN */
 
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4c26dc3a8295..13bc08aba704 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -47,6 +47,7 @@
 
 /* @a is a power of 2 value */
 #define ALIGN(x, a)		__ALIGN_KERNEL((x), (a))
+#define ALIGN_DOWN(x, a)	__ALIGN_KERNEL((x) - ((a) - 1), (a))
 #define __ALIGN_MASK(x, mask)	__ALIGN_KERNEL_MASK((x), (mask))
 #define PTR_ALIGN(p, a)		((typeof(p))ALIGN((unsigned long)(p), (a)))
 #define IS_ALIGNED(x, a)		(((x) & ((typeof(x))(a) - 1)) == 0)
@@ -438,6 +439,7 @@ extern int get_option(char **str, int *pint);
 extern char *get_options(const char *str, int nints, int *ints);
 extern unsigned long long memparse(const char *ptr, char **retptr);
 extern bool parse_option_str(const char *str, const char *option);
+extern char *next_arg(char *args, char **param, char **val);
 
 extern int core_kernel_text(unsigned long addr);
 extern int core_kernel_data(unsigned long addr);
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index e6284591599e..ca85cb80e99a 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -108,6 +108,8 @@ extern int __must_check kobject_rename(struct kobject *, const char *new_name);
 extern int __must_check kobject_move(struct kobject *, struct kobject *);
 
 extern struct kobject *kobject_get(struct kobject *kobj);
+extern struct kobject * __must_check kobject_get_unless_zero(
+						struct kobject *kobj);
 extern void kobject_put(struct kobject *kobj);
 
 extern const void *kobject_namespace(struct kobject *kobj);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index c328e4f7dcad..47e4da5b4fa2 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -267,6 +267,8 @@ extern int arch_init_kprobes(void);
 extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
+extern bool arch_function_offset_within_entry(unsigned long offset);
+extern bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
 
 extern bool within_kprobe_blacklist(unsigned long addr);
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2c14ad9809da..d0250744507a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -162,8 +162,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val);
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev);
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			      struct kvm_io_device *dev);
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			       struct kvm_io_device *dev);
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 					 gpa_t addr);
 
diff --git a/include/linux/leds-pca9532.h b/include/linux/leds-pca9532.h
index d215b4561180..5e240b2b4d58 100644
--- a/include/linux/leds-pca9532.h
+++ b/include/linux/leds-pca9532.h
@@ -22,7 +22,8 @@ enum pca9532_state {
 	PCA9532_OFF  = 0x0,
 	PCA9532_ON   = 0x1,
 	PCA9532_PWM0 = 0x2,
-	PCA9532_PWM1 = 0x3
+	PCA9532_PWM1 = 0x3,
+	PCA9532_KEEP = 0xff,
 };
 
 struct pca9532_led {
@@ -44,4 +45,3 @@ struct pca9532_platform_data {
 };
 
 #endif /* __LINUX_PCA9532_H */
-
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 38c0bd7ca107..64c56d454f7d 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -122,10 +122,16 @@ struct led_classdev {
 	struct mutex		led_access;
 };
 
-extern int led_classdev_register(struct device *parent,
-				 struct led_classdev *led_cdev);
-extern int devm_led_classdev_register(struct device *parent,
-				      struct led_classdev *led_cdev);
+extern int of_led_classdev_register(struct device *parent,
+				    struct device_node *np,
+				    struct led_classdev *led_cdev);
+#define led_classdev_register(parent, led_cdev)				\
+	of_led_classdev_register(parent, NULL, led_cdev)
+extern int devm_of_led_classdev_register(struct device *parent,
+					 struct device_node *np,
+					 struct led_classdev *led_cdev);
+#define devm_led_classdev_register(parent, led_cdev)			\
+	devm_of_led_classdev_register(parent, NULL, led_cdev)
 extern void led_classdev_unregister(struct led_classdev *led_cdev);
 extern void devm_led_classdev_unregister(struct device *parent,
 					 struct led_classdev *led_cdev);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index ca45e4a088a9..7dfa56ebbc6d 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -56,7 +56,6 @@ typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
 typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *);
 typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int);
 typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
 typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
 typedef void (nvm_destroy_dma_pool_fn)(void *);
 typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
@@ -70,7 +69,6 @@ struct nvm_dev_ops {
 	nvm_op_set_bb_fn	*set_bb_tbl;
 
 	nvm_submit_io_fn	*submit_io;
-	nvm_erase_blk_fn	*erase_block;
 
 	nvm_create_dma_pool_fn	*create_dma_pool;
 	nvm_destroy_dma_pool_fn	*destroy_dma_pool;
@@ -125,7 +123,7 @@ enum {
 	/* NAND Access Modes */
 	NVM_IO_SUSPEND		= 0x80,
 	NVM_IO_SLC_MODE		= 0x100,
-	NVM_IO_SCRAMBLE_DISABLE	= 0x200,
+	NVM_IO_SCRAMBLE_ENABLE	= 0x200,
 
 	/* Block Types */
 	NVM_BLK_T_FREE		= 0x0,
@@ -438,7 +436,8 @@ static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2)
 
 typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
 typedef sector_t (nvm_tgt_capacity_fn)(void *);
-typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *);
+typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
+				int flags);
 typedef void (nvm_tgt_exit_fn)(void *);
 typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
 typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
@@ -479,10 +478,10 @@ extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *,
 			      int, int);
 extern int nvm_max_phys_sects(struct nvm_tgt_dev *);
 extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *);
-extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *,
+extern int nvm_erase_sync(struct nvm_tgt_dev *, struct ppa_addr *, int);
+extern int nvm_set_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *,
 					const struct ppa_addr *, int, int);
-extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *);
-extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int);
+extern void nvm_free_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *);
 extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *,
 			   void *);
 extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t);
diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index b01fe1009084..87ff4f58a2f0 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -29,6 +29,11 @@ struct hlist_nulls_node {
 	((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls))
 
 #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_nulls_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \
+	})
 /**
  * ptr_is_a_nulls - Test if a ptr is a nulls
  * @ptr: ptr to be tested
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 1e327bb80838..fffe49f188e6 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -361,6 +361,8 @@ static inline void lock_set_subclass(struct lockdep_map *lock,
 	lock_set_class(lock, lock->name, lock->key, subclass, ip);
 }
 
+extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip);
+
 extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
 extern void lockdep_clear_current_reclaim_state(void);
 extern void lockdep_trace_alloc(gfp_t mask);
@@ -411,6 +413,7 @@ static inline void lockdep_on(void)
 
 # define lock_acquire(l, s, t, r, c, n, i)	do { } while (0)
 # define lock_release(l, n, i)			do { } while (0)
+# define lock_downgrade(l, i)			do { } while (0)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_set_current_reclaim_state(g)	do { } while (0)
diff --git a/include/linux/mailbox/brcm-message.h b/include/linux/mailbox/brcm-message.h
index 6b55c938b401..c20b4843fc2d 100644
--- a/include/linux/mailbox/brcm-message.h
+++ b/include/linux/mailbox/brcm-message.h
@@ -16,6 +16,7 @@
 
 enum brcm_message_type {
 	BRCM_MESSAGE_UNKNOWN = 0,
+	BRCM_MESSAGE_BATCH,
 	BRCM_MESSAGE_SPU,
 	BRCM_MESSAGE_SBA,
 	BRCM_MESSAGE_MAX,
@@ -23,24 +24,29 @@ enum brcm_message_type {
 
 struct brcm_sba_command {
 	u64 cmd;
+	u64 *cmd_dma;
+	dma_addr_t cmd_dma_addr;
 #define BRCM_SBA_CMD_TYPE_A		BIT(0)
 #define BRCM_SBA_CMD_TYPE_B		BIT(1)
 #define BRCM_SBA_CMD_TYPE_C		BIT(2)
 #define BRCM_SBA_CMD_HAS_RESP		BIT(3)
 #define BRCM_SBA_CMD_HAS_OUTPUT		BIT(4)
 	u64 flags;
-	dma_addr_t input;
-	size_t input_len;
 	dma_addr_t resp;
 	size_t resp_len;
-	dma_addr_t output;
-	size_t output_len;
+	dma_addr_t data;
+	size_t data_len;
 };
 
 struct brcm_message {
 	enum brcm_message_type type;
 	union {
 		struct {
+			struct brcm_message *msgs;
+			unsigned int msgs_queued;
+			unsigned int msgs_count;
+		} batch;
+		struct {
 			struct scatterlist *src;
 			struct scatterlist *dst;
 		} spu;
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5af377303880..bb7250c45cb8 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -740,6 +740,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait)
 	return false;
 }
 
+static inline void mem_cgroup_update_page_stat(struct page *page,
+					       enum mem_cgroup_stat_index idx,
+					       int nr)
+{
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 7a01c94496f1..3eef9fb9968a 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -35,10 +35,11 @@
  * Max bus-specific overhead incurred by request/responses.
  * I2C requires 1 additional byte for requests.
  * I2C requires 2 additional bytes for responses.
+ * SPI requires up to 32 additional bytes for responses.
  * */
 #define EC_PROTO_VERSION_UNKNOWN	0
 #define EC_MAX_REQUEST_OVERHEAD		1
-#define EC_MAX_RESPONSE_OVERHEAD	2
+#define EC_MAX_RESPONSE_OVERHEAD	32
 
 /*
  * Command interface between EC and AP, for LPC, I2C and SPI interfaces.
diff --git a/include/linux/mfd/motorola-cpcap.h b/include/linux/mfd/motorola-cpcap.h
index b4031c2b2214..53758a7d7c32 100644
--- a/include/linux/mfd/motorola-cpcap.h
+++ b/include/linux/mfd/motorola-cpcap.h
@@ -14,6 +14,9 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/device.h>
+#include <linux/regmap.h>
+
 #define CPCAP_VENDOR_ST		0
 #define CPCAP_VENDOR_TI		1
 
diff --git a/include/linux/mg_disk.h b/include/linux/mg_disk.h
deleted file mode 100644
index e11f4d9f1c2e..000000000000
--- a/include/linux/mg_disk.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- *  include/linux/mg_disk.c
- *
- *  Private data for mflash platform driver
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-
-#ifndef __MG_DISK_H__
-#define __MG_DISK_H__
-
-/* name for platform device */
-#define MG_DEV_NAME "mg_disk"
-
-/* names of GPIO resource */
-#define MG_RST_PIN	"mg_rst"
-/* except MG_BOOT_DEV, reset-out pin should be assigned */
-#define MG_RSTOUT_PIN	"mg_rstout"
-
-/* device attribution */
-/* use mflash as boot device */
-#define MG_BOOT_DEV		(1 << 0)
-/* use mflash as storage device */
-#define MG_STORAGE_DEV		(1 << 1)
-/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
-#define MG_STORAGE_DEV_SKIP_RST	(1 << 2)
-
-/* private driver data */
-struct mg_drv_data {
-	/* disk resource */
-	u32 use_polling;
-
-	/* device attribution */
-	u32 dev_attr;
-
-	/* internally used */
-	void *host;
-};
-
-#endif
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7e66e4f62858..1beb1ec2fbdf 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -476,6 +476,7 @@ enum {
 enum {
 	MLX4_INTERFACE_STATE_UP		= 1 << 0,
 	MLX4_INTERFACE_STATE_DELETION	= 1 << 1,
+	MLX4_INTERFACE_STATE_NOWAIT	= 1 << 2,
 };
 
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2fcff6b4503f..3fece51dcf13 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -540,6 +540,7 @@ struct mlx5_fc_stats {
 	struct workqueue_struct *wq;
 	struct delayed_work work;
 	unsigned long next_query;
+	unsigned long sampling_interval; /* jiffies */
 };
 
 struct mlx5_eswitch;
@@ -728,6 +729,7 @@ struct mlx5e_resources {
 	u32                        pdn;
 	struct mlx5_td             td;
 	struct mlx5_core_mkey      mkey;
+	struct mlx5_sq_bfreg       bfreg;
 };
 
 struct mlx5_core_dev {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 949b24b6c479..1b166d2e19c5 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -104,12 +104,18 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 				    u32 level,
 				    u32 flags);
 
+struct mlx5_flow_table_attr {
+	int prio;
+	int max_fte;
+	u32 level;
+	u32 flags;
+	u32 underlay_qpn;
+};
+
 struct mlx5_flow_table *
 mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
-		       int prio,
-		       int num_flow_table_entries,
-		       u32 level,
-		       u32 flags);
+		       struct mlx5_flow_table_attr *ft_attr);
+
 struct mlx5_flow_table *
 mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
 			     int prio,
@@ -134,8 +140,13 @@ struct mlx5_flow_act {
 	u32 action;
 	u32 flow_tag;
 	u32 encap_id;
+	u32 modify_id;
 };
 
+#define MLX5_DECLARE_FLOW_ACT(name) \
+	struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
+				     MLX5_FS_DEFAULT_FLOW_TAG, 0, 0}
+
 /* Single destination per rule.
  * Group ID is implied by the match criteria.
  */
@@ -156,5 +167,4 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
 void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse);
-
 #endif
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 838242697541..7c50bd39b297 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -227,6 +227,8 @@ enum {
 	MLX5_CMD_OP_MODIFY_FLOW_TABLE             = 0x93c,
 	MLX5_CMD_OP_ALLOC_ENCAP_HEADER            = 0x93d,
 	MLX5_CMD_OP_DEALLOC_ENCAP_HEADER          = 0x93e,
+	MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT   = 0x940,
+	MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941,
 	MLX5_CMD_OP_MAX
 };
 
@@ -302,7 +304,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
-	u8         reserved_at_28[0x10];
+	u8         log_max_modify_header_context[0x8];
+	u8         max_modify_header_actions[0x8];
 	u8         max_ft_level[0x8];
 
 	u8         reserved_at_40[0x20];
@@ -869,7 +872,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         compact_address_vector[0x1];
 	u8         striding_rq[0x1];
-	u8         reserved_at_202[0x2];
+	u8         reserved_at_202[0x1];
+	u8         ipoib_enhanced_offloads[0x1];
 	u8         ipoib_basic_offloads[0x1];
 	u8         reserved_at_205[0xa];
 	u8         drain_sigerr[0x1];
@@ -2190,6 +2194,7 @@ enum {
 	MLX5_FLOW_CONTEXT_ACTION_COUNT     = 0x8,
 	MLX5_FLOW_CONTEXT_ACTION_ENCAP     = 0x10,
 	MLX5_FLOW_CONTEXT_ACTION_DECAP     = 0x20,
+	MLX5_FLOW_CONTEXT_ACTION_MOD_HDR   = 0x40,
 };
 
 struct mlx5_ifc_flow_context_bits {
@@ -2211,7 +2216,9 @@ struct mlx5_ifc_flow_context_bits {
 
 	u8         encap_id[0x20];
 
-	u8         reserved_at_e0[0x120];
+	u8         modify_header_id[0x20];
+
+	u8         reserved_at_100[0x100];
 
 	struct mlx5_ifc_fte_match_param_bits match_value;
 
@@ -2287,7 +2294,9 @@ struct mlx5_ifc_tisc_bits {
 	u8         reserved_at_120[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_at_140[0x3c0];
+	u8         reserved_at_140[0x8];
+	u8         underlay_qpn[0x18];
+	u8         reserved_at_160[0x3a0];
 };
 
 enum {
@@ -4534,6 +4543,109 @@ struct mlx5_ifc_dealloc_encap_header_in_bits {
 	u8         reserved_60[0x20];
 };
 
+struct mlx5_ifc_set_action_in_bits {
+	u8         action_type[0x4];
+	u8         field[0xc];
+	u8         reserved_at_10[0x3];
+	u8         offset[0x5];
+	u8         reserved_at_18[0x3];
+	u8         length[0x5];
+
+	u8         data[0x20];
+};
+
+struct mlx5_ifc_add_action_in_bits {
+	u8         action_type[0x4];
+	u8         field[0xc];
+	u8         reserved_at_10[0x10];
+
+	u8         data[0x20];
+};
+
+union mlx5_ifc_set_action_in_add_action_in_auto_bits {
+	struct mlx5_ifc_set_action_in_bits set_action_in;
+	struct mlx5_ifc_add_action_in_bits add_action_in;
+	u8         reserved_at_0[0x40];
+};
+
+enum {
+	MLX5_ACTION_TYPE_SET   = 0x1,
+	MLX5_ACTION_TYPE_ADD   = 0x2,
+};
+
+enum {
+	MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16    = 0x1,
+	MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0     = 0x2,
+	MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE     = 0x3,
+	MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16    = 0x4,
+	MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0     = 0x5,
+	MLX5_ACTION_IN_FIELD_OUT_IP_DSCP       = 0x6,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS     = 0x7,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT     = 0x8,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT     = 0x9,
+	MLX5_ACTION_IN_FIELD_OUT_IP_TTL        = 0xa,
+	MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT     = 0xb,
+	MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT     = 0xc,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96  = 0xd,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64   = 0xe,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32   = 0xf,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0    = 0x10,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96  = 0x11,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64   = 0x12,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32   = 0x13,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0    = 0x14,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV4         = 0x15,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV4         = 0x16,
+};
+
+struct mlx5_ifc_alloc_modify_header_context_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         modify_header_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_alloc_modify_header_context_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x20];
+
+	u8         table_type[0x8];
+	u8         reserved_at_68[0x10];
+	u8         num_of_actions[0x8];
+
+	union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0];
+};
+
+struct mlx5_ifc_dealloc_modify_header_context_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_modify_header_context_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         modify_header_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_query_dct_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -5013,6 +5125,7 @@ struct mlx5_ifc_modify_rq_out_bits {
 
 enum {
 	MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD = 1ULL << 1,
+	MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS = 1ULL << 2,
 	MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID = 1ULL << 3,
 };
 
@@ -8108,7 +8221,9 @@ struct mlx5_ifc_set_flow_table_root_in_bits {
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_at_c0[0x140];
+	u8         reserved_at_c0[0x8];
+	u8         underlay_qpn[0x18];
+	u8         reserved_at_e0[0x120];
 };
 
 enum {
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 3096370fe831..bef80d0a0e30 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -295,6 +295,16 @@ struct mlx5_av {
 	u8	rgid[16];
 };
 
+struct mlx5_ib_ah {
+	struct ib_ah		ibah;
+	struct mlx5_av		av;
+};
+
+static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah)
+{
+	return container_of(ibah, struct mlx5_ib_ah, ibah);
+}
+
 struct mlx5_wqe_datagram_seg {
 	struct mlx5_av	av;
 };
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0d65dd72c0f4..695da2a19b4c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -32,6 +32,8 @@ struct user_struct;
 struct writeback_control;
 struct bdi_writeback;
 
+void init_mm_internals(void);
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES	/* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
 
@@ -430,6 +432,10 @@ static inline int pud_devmap(pud_t pud)
 {
 	return 0;
 }
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -756,19 +762,11 @@ static inline enum zone_type page_zonenum(const struct page *page)
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-void get_zone_device_page(struct page *page);
-void put_zone_device_page(struct page *page);
 static inline bool is_zone_device_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_DEVICE;
 }
 #else
-static inline void get_zone_device_page(struct page *page)
-{
-}
-static inline void put_zone_device_page(struct page *page)
-{
-}
 static inline bool is_zone_device_page(const struct page *page)
 {
 	return false;
@@ -784,9 +782,6 @@ static inline void get_page(struct page *page)
 	 */
 	VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
 	page_ref_inc(page);
-
-	if (unlikely(is_zone_device_page(page)))
-		get_zone_device_page(page);
 }
 
 static inline void put_page(struct page *page)
@@ -795,9 +790,6 @@ static inline void put_page(struct page *page)
 
 	if (put_page_testzero(page))
 		__put_page(page);
-
-	if (unlikely(is_zone_device_page(page)))
-		put_zone_device_page(page);
 }
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
@@ -1560,14 +1552,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
 	return ptep;
 }
 
+#ifdef __PAGETABLE_P4D_FOLDED
+static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+						unsigned long address)
+{
+	return 0;
+}
+#else
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+#endif
+
 #ifdef __PAGETABLE_PUD_FOLDED
-static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
+static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
 						unsigned long address)
 {
 	return 0;
 }
 #else
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
 #endif
 
 #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
@@ -1619,11 +1621,22 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
  * Remove it when 4level-fixup.h has been removed.
  */
 #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
-static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+
+#ifndef __ARCH_HAS_5LEVEL_HACK
+static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+		unsigned long address)
+{
+	return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ?
+		NULL : p4d_offset(pgd, address);
+}
+
+static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
+		unsigned long address)
 {
-	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
-		NULL: pud_offset(pgd, address);
+	return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ?
+		NULL : pud_offset(p4d, address);
 }
+#endif /* !__ARCH_HAS_5LEVEL_HACK */
 
 static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 {
@@ -2385,7 +2398,8 @@ void sparse_mem_maps_populate_node(struct page **map_map,
 
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
-pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
+p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
+pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f60f45fe226f..45cdb27791a3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -367,6 +367,11 @@ struct mm_struct {
 #endif
 	unsigned long mmap_base;		/* base of mmap area */
 	unsigned long mmap_legacy_base;         /* base of mmap area in bottom-up allocations */
+#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
+	/* Base adresses for compatible mmap() */
+	unsigned long mmap_compat_base;
+	unsigned long mmap_compat_legacy_base;
+#endif
 	unsigned long task_size;		/* size of task vm space */
 	unsigned long highest_vm_end;		/* highest vma end address */
 	pgd_t * pgd;
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 77e61e0a216a..aad015e0152b 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -89,6 +89,7 @@ struct mmc_ext_csd {
 	unsigned int		boot_ro_lock;		/* ro lock support */
 	bool			boot_ro_lockable;
 	bool			ffu_capable;	/* Firmware upgrade support */
+	bool			cmdq_en;	/* Command Queue enabled */
 	bool			cmdq_support;	/* Command Queue supported */
 	unsigned int		cmdq_depth;	/* Command Queue depth */
 #define MMC_FIRMWARE_LEN 8
@@ -208,6 +209,7 @@ struct sdio_cis {
 struct mmc_host;
 struct sdio_func;
 struct sdio_func_tuple;
+struct mmc_queue_req;
 
 #define SDIO_MAX_FUNCS		7
 
@@ -267,6 +269,8 @@ struct mmc_card {
 #define MMC_QUIRK_TRIM_BROKEN	(1<<12)		/* Skip trim */
 #define MMC_QUIRK_BROKEN_HPI	(1<<13)		/* Disable broken HPI support */
 
+	bool			reenable_cmdq;	/* Re-enable Command Queue */
+
 	unsigned int		erase_size;	/* erase size in sectors */
  	unsigned int		erase_shift;	/* if erase unit is power 2 */
  	unsigned int		pref_erase;	/* in sectors */
@@ -300,6 +304,10 @@ struct mmc_card {
 	struct dentry		*debugfs_root;
 	struct mmc_part	part[MMC_NUM_PHY_PARTITION]; /* physical partitions */
 	unsigned int    nr_parts;
+
+	struct mmc_queue_req	*mqrq;		/* Shared queue structure */
+	unsigned int		bouncesz;	/* Bounce buffer size */
+	int			qdepth;		/* Shared queue depth */
 };
 
 static inline bool mmc_large_sector(struct mmc_card *card)
@@ -307,6 +315,8 @@ static inline bool mmc_large_sector(struct mmc_card *card)
 	return card->ext_csd.data_sector_size == 4096;
 }
 
+bool mmc_card_is_blockaddr(struct mmc_card *card);
+
 #define mmc_card_mmc(c)		((c)->type == MMC_TYPE_MMC)
 #define mmc_card_sd(c)		((c)->type == MMC_TYPE_SD)
 #define mmc_card_sdio(c)	((c)->type == MMC_TYPE_SDIO)
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 83f1c4a9f03b..21385ac0c9b1 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -17,6 +17,7 @@
 #include <linux/mmc/core.h>
 #include <linux/mmc/card.h>
 #include <linux/mmc/pm.h>
+#include <linux/dma-direction.h>
 
 struct mmc_ios {
 	unsigned int	clock;			/* clock rate */
@@ -499,6 +500,11 @@ static inline bool mmc_can_retune(struct mmc_host *host)
 	return host->can_retune == 1;
 }
 
+static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data)
+{
+	return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+}
+
 int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error);
 int mmc_abort_tuning(struct mmc_host *host, u32 opcode);
 
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index aab032a6ae61..97ca105347a6 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -53,7 +53,7 @@ struct sdio_func {
 	unsigned int		state;		/* function state */
 #define SDIO_STATE_PRESENT	(1<<0)		/* present in sysfs */
 
-	u8			tmpbuf[4];	/* DMA:able scratch buffer */
+	u8			*tmpbuf;	/* DMA:able scratch buffer */
 
 	unsigned		num_info;	/* number of info strings */
 	const char		**info;		/* info strings */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 51891fb0d3ce..c91b3bcd158f 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -394,18 +394,6 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	___pud;								\
 })
 
-#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd)		\
-({									\
-	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
-	pmd_t ___pmd;							\
-									\
-	___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd);		\
-	mmu_notifier_invalidate_range(__mm, ___haddr,			\
-				      ___haddr + HPAGE_PMD_SIZE);	\
-									\
-	___pmd;								\
-})
-
 /*
  * set_pte_at_notify() sets the pte _after_ running the notifier.
  * This is safe to start by updating the secondary MMUs, because the primary MMU
@@ -489,7 +477,6 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 #define	ptep_clear_flush_notify ptep_clear_flush
 #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
 #define pudp_huge_clear_flush_notify pudp_huge_clear_flush
-#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear
 #define set_pte_at_notify set_pte_at
 
 #endif /* CONFIG_MMU_NOTIFIER */
diff --git a/include/linux/module.h b/include/linux/module.h
index 0297c5cd7cdf..9ad68561d8c2 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -493,6 +493,7 @@ static inline int module_is_live(struct module *mod)
 struct module *__module_text_address(unsigned long addr);
 struct module *__module_address(unsigned long addr);
 bool is_module_address(unsigned long addr);
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr);
 bool is_module_percpu_address(unsigned long addr);
 bool is_module_text_address(unsigned long addr);
 
@@ -660,6 +661,11 @@ static inline bool is_module_percpu_address(unsigned long addr)
 	return false;
 }
 
+static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+	return false;
+}
+
 static inline bool is_module_text_address(unsigned long addr)
 {
 	return false;
diff --git a/include/linux/mpls.h b/include/linux/mpls.h
index 9999145bc190..384fb22b6c43 100644
--- a/include/linux/mpls.h
+++ b/include/linux/mpls.h
@@ -3,4 +3,9 @@
 
 #include <uapi/linux/mpls.h>
 
+#define MPLS_TTL_MASK		(MPLS_LS_TTL_MASK >> MPLS_LS_TTL_SHIFT)
+#define MPLS_BOS_MASK		(MPLS_LS_S_MASK >> MPLS_LS_S_SHIFT)
+#define MPLS_TC_MASK		(MPLS_LS_TC_MASK >> MPLS_LS_TC_SHIFT)
+#define MPLS_LABEL_MASK		(MPLS_LS_LABEL_MASK >> MPLS_LS_LABEL_SHIFT)
+
 #endif  /* _LINUX_MPLS_H */
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index eebdc63cf6af..79b176eca04a 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -334,11 +334,6 @@ struct mtd_info {
 	int (*_get_device) (struct mtd_info *mtd);
 	void (*_put_device) (struct mtd_info *mtd);
 
-	/* Backing device capabilities for this device
-	 * - provides mmap capabilities
-	 */
-	struct backing_dev_info *backing_dev_info;
-
 	struct notifier_block reboot_notifier;  /* default mode before reboot */
 
 	/* ECC status information */
diff --git a/include/linux/net.h b/include/linux/net.h
index cd0c8bd0a1de..abcfa46a2bd9 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -146,7 +146,7 @@ struct proto_ops {
 	int		(*socketpair)(struct socket *sock1,
 				      struct socket *sock2);
 	int		(*accept)    (struct socket *sock,
-				      struct socket *newsock, int flags);
+				      struct socket *newsock, int flags, bool kern);
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int *sockaddr_len, int peer);
@@ -298,6 +298,9 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
 int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how);
 
+/* Routine returns the IP overhead imposed by a (caller-protected) socket. */
+u32 kernel_sock_ip_overhead(struct sock *sk);
+
 #define MODULE_ALIAS_NETPROTO(proto) \
 	MODULE_ALIAS("net-pf-" __stringify(proto))
 
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 9a0419594e84..1d4737cffc71 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -54,8 +54,9 @@ enum {
 					 */
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	NETIF_F_GSO_SCTP_BIT,		/* ... SCTP fragmentation */
+	NETIF_F_GSO_ESP_BIT,		/* ... ESP with TSO */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_SCTP_BIT,
+		NETIF_F_GSO_ESP_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
@@ -73,6 +74,8 @@ enum {
 	NETIF_F_HW_L2FW_DOFFLOAD_BIT,	/* Allow L2 Forwarding in Hardware */
 
 	NETIF_F_HW_TC_BIT,		/* Offload TC infrastructure */
+	NETIF_F_HW_ESP_BIT,		/* Hardware ESP transformation offload */
+	NETIF_F_HW_ESP_TX_CSUM_BIT,	/* ESP with TX checksum offload */
 
 	/*
 	 * Add your fresh new feature above and remember to update
@@ -129,11 +132,14 @@ enum {
 #define NETIF_F_GSO_PARTIAL	 __NETIF_F(GSO_PARTIAL)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_GSO_SCTP	__NETIF_F(GSO_SCTP)
+#define NETIF_F_GSO_ESP		__NETIF_F(GSO_ESP)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
 #define NETIF_F_HW_L2FW_DOFFLOAD	__NETIF_F(HW_L2FW_DOFFLOAD)
 #define NETIF_F_HW_TC		__NETIF_F(HW_TC)
+#define NETIF_F_HW_ESP		__NETIF_F(HW_ESP)
+#define NETIF_F_HW_ESP_TX_CSUM	__NETIF_F(HW_ESP_TX_CSUM)
 
 #define for_each_netdev_feature(mask_addr, bit)	\
 	for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97456b2539e4..9c23bd2efb56 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -41,7 +41,6 @@
 
 #include <linux/ethtool.h>
 #include <net/net_namespace.h>
-#include <net/dsa.h>
 #ifdef CONFIG_DCB
 #include <net/dcbnl.h>
 #endif
@@ -57,6 +56,8 @@
 struct netpoll_info;
 struct device;
 struct phy_device;
+struct dsa_switch_tree;
+
 /* 802.11 specific */
 struct wireless_dev;
 /* 802.15.4 specific */
@@ -236,8 +237,7 @@ struct netdev_hw_addr_list {
 	netdev_hw_addr_list_for_each(ha, &(dev)->mc)
 
 struct hh_cache {
-	u16		hh_len;
-	u16		__pad;
+	unsigned int	hh_len;
 	seqlock_t	hh_lock;
 
 	/* cached hardware header; allow for machine alignment needs.        */
@@ -786,11 +786,11 @@ struct tc_cls_u32_offload;
 struct tc_to_netdev {
 	unsigned int type;
 	union {
-		u8 tc;
 		struct tc_cls_u32_offload *cls_u32;
 		struct tc_cls_flower_offload *cls_flower;
 		struct tc_cls_matchall_offload *cls_mall;
 		struct tc_cls_bpf_offload *cls_bpf;
+		struct tc_mqprio_qopt *mqprio;
 	};
 	bool egress_dev;
 };
@@ -813,16 +813,31 @@ enum xdp_netdev_command {
 	XDP_QUERY_PROG,
 };
 
+struct netlink_ext_ack;
+
 struct netdev_xdp {
 	enum xdp_netdev_command command;
 	union {
 		/* XDP_SETUP_PROG */
-		struct bpf_prog *prog;
+		struct {
+			struct bpf_prog *prog;
+			struct netlink_ext_ack *extack;
+		};
 		/* XDP_QUERY_PROG */
 		bool prog_attached;
 	};
 };
 
+#ifdef CONFIG_XFRM_OFFLOAD
+struct xfrmdev_ops {
+	int	(*xdo_dev_state_add) (struct xfrm_state *x);
+	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
+	void	(*xdo_dev_state_free) (struct xfrm_state *x);
+	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
+				       struct xfrm_state *x);
+};
+#endif
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1696,6 +1711,10 @@ struct net_device {
 	const struct ndisc_ops *ndisc_ops;
 #endif
 
+#ifdef CONFIG_XFRM
+	const struct xfrmdev_ops *xfrmdev_ops;
+#endif
+
 	const struct header_ops *header_ops;
 
 	unsigned int		flags;
@@ -1715,7 +1734,7 @@ struct net_device {
 	unsigned int		max_mtu;
 	unsigned short		type;
 	unsigned short		hard_header_len;
-	unsigned short		min_header_len;
+	unsigned char		min_header_len;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -1776,6 +1795,7 @@ struct net_device {
 	unsigned int		real_num_rx_queues;
 #endif
 
+	struct bpf_prog __rcu	*xdp_prog;
 	unsigned long		gro_flush_timeout;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
@@ -1894,6 +1914,13 @@ struct net_device {
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
+static inline bool netif_elide_gro(const struct net_device *dev)
+{
+	if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog)
+		return true;
+	return false;
+}
+
 #define	NETDEV_ALIGN		32
 
 static inline
@@ -2004,15 +2031,6 @@ void dev_net_set(struct net_device *dev, struct net *net)
 	write_pnet(&dev->nd_net, net);
 }
 
-static inline bool netdev_uses_dsa(struct net_device *dev)
-{
-#if IS_ENABLED(CONFIG_NET_DSA)
-	if (dev->dsa_ptr != NULL)
-		return dsa_uses_tagged_protocol(dev->dsa_ptr);
-#endif
-	return false;
-}
-
 /**
  *	netdev_priv - access network device private data
  *	@dev: network device
@@ -3278,7 +3296,8 @@ int dev_get_phys_port_id(struct net_device *dev,
 int dev_get_phys_port_name(struct net_device *dev,
 			   char *name, size_t len);
 int dev_change_proto_down(struct net_device *dev, bool proto_down);
-int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags);
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+		      int fd, u32 flags);
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
@@ -3305,6 +3324,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
 void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 
 extern int		netdev_budget;
+extern unsigned int	netdev_budget_usecs;
 
 /* Called by rtnetlink.c:rtnl_unlock() */
 void netdev_run_todo(void);
@@ -3394,10 +3414,10 @@ static inline void netif_dormant_off(struct net_device *dev)
 }
 
 /**
- *	netif_dormant - test if carrier present
+ *	netif_dormant - test if device is dormant
  *	@dev: network device
  *
- * Check if carrier is present on device
+ * Check if device is dormant.
  */
 static inline bool netif_dormant(const struct net_device *dev)
 {
@@ -4078,6 +4098,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_SCTP    != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
@@ -4180,6 +4201,11 @@ static inline bool netif_is_ovs_master(const struct net_device *dev)
 	return dev->priv_flags & IFF_OPENVSWITCH;
 }
 
+static inline bool netif_is_ovs_port(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_OVS_DATAPATH;
+}
+
 static inline bool netif_is_team_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_TEAM;
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 1b49209dd5c7..996711d8a7b4 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -41,6 +41,11 @@ int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
 int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
 		      int flags);
 
+static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type)
+{
+	return subsys << 8 | msg_type;
+}
+
 void nfnl_lock(__u8 subsys_id);
 void nfnl_unlock(__u8 subsys_id);
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index 984b2112c77b..a30efb437e6d 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -109,8 +109,10 @@ struct ebt_table {
 #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \
 		     ~(__alignof__(struct _xt_align)-1))
 extern struct ebt_table *ebt_register_table(struct net *net,
-					    const struct ebt_table *table);
-extern void ebt_unregister_table(struct net *net, struct ebt_table *table);
+					    const struct ebt_table *table,
+					    const struct nf_hook_ops *);
+extern void ebt_unregister_table(struct net *net, struct ebt_table *table,
+				 const struct nf_hook_ops *);
 extern unsigned int ebt_do_table(struct sk_buff *skb,
 				 const struct nf_hook_state *state,
 				 struct ebt_table *table);
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index da14ab61f363..c20395edf2de 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -62,11 +62,50 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg)
 	return __netlink_kernel_create(net, unit, THIS_MODULE, cfg);
 }
 
+/* this can be increased when necessary - don't expose to userland */
+#define NETLINK_MAX_COOKIE_LEN	20
+
+/**
+ * struct netlink_ext_ack - netlink extended ACK report struct
+ * @_msg: message string to report - don't access directly, use
+ *	%NL_SET_ERR_MSG
+ * @bad_attr: attribute with error
+ * @cookie: cookie data to return to userspace (for success)
+ * @cookie_len: actual cookie data length
+ */
+struct netlink_ext_ack {
+	const char *_msg;
+	const struct nlattr *bad_attr;
+	u8 cookie[NETLINK_MAX_COOKIE_LEN];
+	u8 cookie_len;
+};
+
+/* Always use this macro, this allows later putting the
+ * message into a separate section or such for things
+ * like translation or listing all possible messages.
+ * Currently string formatting is not supported (due
+ * to the lack of an output buffer.)
+ */
+#define NL_SET_ERR_MSG(extack, msg) do {	\
+	static const char _msg[] = (msg);	\
+						\
+	(extack)->_msg = _msg;			\
+} while (0)
+
+#define NL_MOD_TRY_SET_ERR_MSG(extack, msg) do {		\
+	static const char _msg[] = KBUILD_MODNAME ": " msg;	\
+	struct netlink_ext_ack *_extack = (extack);		\
+								\
+	if (_extack)						\
+		_extack->_msg = _msg;				\
+} while (0)
+
 extern void netlink_kernel_release(struct sock *sk);
 extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
 extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
 extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group);
-extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
+extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
+			const struct netlink_ext_ack *extack);
 extern int netlink_has_listeners(struct sock *sk, unsigned int group);
 
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b34097c67848..e1502c55741e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -133,7 +133,6 @@ struct nfs_server {
 	struct rpc_clnt *	client_acl;	/* ACL RPC client handle */
 	struct nlm_host		*nlm_host;	/* NLM client handle */
 	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
-	struct backing_dev_info	backing_dev_info;
 	atomic_long_t		writeback;	/* number of writeback pages */
 	int			flags;		/* various flags */
 	unsigned int		caps;		/* server capabilities */
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index f21471f7ee40..0db37158a61d 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -137,9 +137,9 @@ enum nvmefc_fcp_datadir {
  *             transferred. Should equal payload_length on success.
  * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @status:    Completion status of the FCP operation. must be 0 upon success,
- *             NVME_SC_FC_xxx value upon failure. Note: this is NOT a
- *             reflection of the NVME CQE completion status. Only the status
- *             of the FCP operation at the NVME-FC level.
+ *             negative errno value upon failure (ex: -EIO). Note: this is
+ *             NOT a reflection of the NVME CQE completion status. Only the
+ *             status of the FCP operation at the NVME-FC level.
  */
 struct nvmefc_fcp_req {
 	void			*cmdaddr;
@@ -533,9 +533,6 @@ enum {
 					 * rsp as well
 					 */
 	NVMET_FCOP_RSP		= 4,	/* send rsp frame */
-	NVMET_FCOP_ABORT	= 5,	/* abort exchange via ABTS */
-	NVMET_FCOP_BA_ACC	= 6,	/* send BA_ACC */
-	NVMET_FCOP_BA_RJT	= 7,	/* send BA_RJT */
 };
 
 /**
@@ -572,8 +569,6 @@ enum {
  *     upon compeletion of the operation.  The nvmet-fc layer will also set a
  *     private pointer for its own use in the done routine.
  *
- * Note: the LLDD must never fail a NVMET_FCOP_ABORT request !!
- *
  * Values set by the NVMET-FC layer prior to calling the LLDD fcp_op
  * entrypoint.
  * @op:       Indicates the FCP IU operation to perform (see NVMET_FCOP_xxx)
@@ -655,6 +650,22 @@ enum {
 		 * on. The transport should pick a cpu to schedule the work
 		 * on.
 		 */
+	NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 2),
+		/* Bit 2: When 0, the LLDD is calling the cmd rcv handler
+		 * in a non-isr context, allowing the transport to finish
+		 * op completion in the calling context. When 1, the LLDD
+		 * is calling the cmd rcv handler in an ISR context,
+		 * requiring the transport to transition to a workqueue
+		 * for op completion.
+		 */
+	NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 3),
+		/* Bit 3: When 0, the LLDD is calling the op done handler
+		 * in a non-isr context, allowing the transport to finish
+		 * op completion in the calling context. When 1, the LLDD
+		 * is calling the op done handler in an ISR context,
+		 * requiring the transport to transition to a workqueue
+		 * for op completion.
+		 */
 };
 
 
@@ -725,12 +736,12 @@ struct nvmet_fc_target_port {
  *       be freed/released.
  *       Entrypoint is Mandatory.
  *
- * @fcp_op:  Called to perform a data transfer, transmit a response, or
- *       abort an FCP opertion. The nvmefc_tgt_fcp_req structure is the same
- *       LLDD-supplied exchange structure specified in the
- *       nvmet_fc_rcv_fcp_req() call made when the FCP CMD IU was received.
- *       The op field in the structure shall indicate the operation for
- *       the LLDD to perform relative to the io.
+ * @fcp_op:  Called to perform a data transfer or transmit a response.
+ *       The nvmefc_tgt_fcp_req structure is the same LLDD-supplied
+ *       exchange structure specified in the nvmet_fc_rcv_fcp_req() call
+ *       made when the FCP CMD IU was received. The op field in the
+ *       structure shall indicate the operation for the LLDD to perform
+ *       relative to the io.
  *         NVMET_FCOP_READDATA operation: the LLDD is to send the
  *           payload data (described by sglist) to the host in 1 or
  *           more FC sequences (preferrably 1).  Note: the fc-nvme layer
@@ -752,29 +763,31 @@ struct nvmet_fc_target_port {
  *           successfully, the LLDD is to update the nvmefc_tgt_fcp_req
  *           transferred_length field and may subsequently transmit the
  *           FCP_RSP iu payload (described by rspbuf, rspdma, rsplen).
- *           The LLDD is to await FCP_CONF reception to confirm the RSP
- *           reception by the host. The LLDD may retramsit the FCP_RSP iu
- *           if necessary per FC-NVME. Upon reception of FCP_CONF, or upon
- *           FCP_CONF failure, the LLDD is to set the nvmefc_tgt_fcp_req
- *           fcp_error field and consider the operation complete..
+ *           If FCP_CONF is supported, the LLDD is to await FCP_CONF
+ *           reception to confirm the RSP reception by the host. The LLDD
+ *           may retramsit the FCP_RSP iu if necessary per FC-NVME. Upon
+ *           transmission of the FCP_RSP iu if FCP_CONF is not supported,
+ *           or upon success/failure of FCP_CONF if it is supported, the
+ *           LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and
+ *           consider the operation complete.
  *         NVMET_FCOP_RSP: the LLDD is to transmit the FCP_RSP iu payload
- *           (described by rspbuf, rspdma, rsplen).  The LLDD is to await
- *           FCP_CONF reception to confirm the RSP reception by the host.
- *           The LLDD may retramsit the FCP_RSP iu if necessary per FC-NVME.
- *           Upon reception of FCP_CONF, or upon FCP_CONF failure, the
+ *           (described by rspbuf, rspdma, rsplen). If FCP_CONF is
+ *           supported, the LLDD is to await FCP_CONF reception to confirm
+ *           the RSP reception by the host. The LLDD may retramsit the
+ *           FCP_RSP iu if FCP_CONF is not received per FC-NVME. Upon
+ *           transmission of the FCP_RSP iu if FCP_CONF is not supported,
+ *           or upon success/failure of FCP_CONF if it is supported, the
  *           LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and
- *           consider the operation complete..
- *         NVMET_FCOP_ABORT: the LLDD is to terminate the exchange
- *           corresponding to the fcp operation. The LLDD shall send
- *           ABTS and follow FC exchange abort-multi rules, including
- *           ABTS retries and possible logout.
+ *           consider the operation complete.
  *       Upon completing the indicated operation, the LLDD is to set the
  *       status fields for the operation (tranferred_length and fcp_error
- *       status) in the request, then all the "done" routine
- *       indicated in the fcp request.  Upon return from the "done"
- *       routine for either a NVMET_FCOP_RSP or NVMET_FCOP_ABORT operation
- *       the fc-nvme layer will not longer reference the fcp request,
- *       allowing the LLDD to free/release the fcp request.
+ *       status) in the request, then call the "done" routine
+ *       indicated in the fcp request. After the operation completes,
+ *       regardless of whether the FCP_RSP iu was successfully transmit,
+ *       the LLDD-supplied exchange structure must remain valid until the
+ *       transport calls the fcp_req_release() callback to return ownership
+ *       of the exchange structure back to the LLDD so that it may be used
+ *       for another fcp command.
  *       Note: when calling the done routine for READDATA or WRITEDATA
  *       operations, the fc-nvme layer may immediate convert, in the same
  *       thread and before returning to the LLDD, the fcp operation to
@@ -786,6 +799,22 @@ struct nvmet_fc_target_port {
  *       Returns 0 on success, -<errno> on failure (Ex: -EIO)
  *       Entrypoint is Mandatory.
  *
+ * @fcp_abort:  Called by the transport to abort an active command.
+ *       The command may be in-between operations (nothing active in LLDD)
+ *       or may have an active WRITEDATA operation pending. The LLDD is to
+ *       initiate the ABTS process for the command and return from the
+ *       callback. The ABTS does not need to be complete on the command.
+ *       The fcp_abort callback inherently cannot fail. After the
+ *       fcp_abort() callback completes, the transport will wait for any
+ *       outstanding operation (if there was one) to complete, then will
+ *       call the fcp_req_release() callback to return the command's
+ *       exchange context back to the LLDD.
+ *
+ * @fcp_req_release:  Called by the transport to return a nvmefc_tgt_fcp_req
+ *       to the LLDD after all operations on the fcp operation are complete.
+ *       This may be due to the command completing or upon completion of
+ *       abort cleanup.
+ *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.
  *       Value is Mandatory. Must be at least 1.
@@ -820,7 +849,11 @@ struct nvmet_fc_target_template {
 	int (*xmt_ls_rsp)(struct nvmet_fc_target_port *tgtport,
 				struct nvmefc_tgt_ls_req *tls_req);
 	int (*fcp_op)(struct nvmet_fc_target_port *tgtport,
-				struct nvmefc_tgt_fcp_req *);
+				struct nvmefc_tgt_fcp_req *fcpreq);
+	void (*fcp_abort)(struct nvmet_fc_target_port *tgtport,
+				struct nvmefc_tgt_fcp_req *fcpreq);
+	void (*fcp_req_release)(struct nvmet_fc_target_port *tgtport,
+				struct nvmefc_tgt_fcp_req *fcpreq);
 
 	u32	max_hw_queues;
 	u16	max_sgl_segments;
@@ -848,4 +881,7 @@ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport,
 			struct nvmefc_tgt_fcp_req *fcpreq,
 			void *cmdiubuf, u32 cmdiubuf_len);
 
+void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport,
+			struct nvmefc_tgt_fcp_req *fcpreq);
+
 #endif /* _NVME_FC_DRIVER_H */
diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h
index 4b45226bd604..e997c4a49a88 100644
--- a/include/linux/nvme-fc.h
+++ b/include/linux/nvme-fc.h
@@ -16,8 +16,7 @@
  */
 
 /*
- * This file contains definitions relative to FC-NVME r1.11 and a few
- * newer items
+ * This file contains definitions relative to FC-NVME r1.14 (16-020vB).
  */
 
 #ifndef _NVME_FC_H
@@ -47,8 +46,15 @@ struct nvme_fc_cmd_iu {
 
 #define NVME_FC_SIZEOF_ZEROS_RSP	12
 
+enum {
+	FCNVME_SC_SUCCESS		= 0,
+	FCNVME_SC_INVALID_FIELD		= 1,
+	FCNVME_SC_INVALID_CONNID	= 2,
+};
+
 struct nvme_fc_ersp_iu {
-	__u8			rsvd0[2];
+	__u8			status_code;
+	__u8			rsvd1;
 	__be16			iu_len;
 	__be32			rsn;
 	__be32			xfrd_len;
@@ -58,7 +64,7 @@ struct nvme_fc_ersp_iu {
 };
 
 
-/* FC-NVME r1.03/16-119v0 NVME Link Services */
+/* FC-NVME Link Services */
 enum {
 	FCNVME_LS_RSVD			= 0,
 	FCNVME_LS_RJT			= 1,
@@ -68,7 +74,7 @@ enum {
 	FCNVME_LS_DISCONNECT		= 5,
 };
 
-/* FC-NVME r1.03/16-119v0 NVME Link Service Descriptors */
+/* FC-NVME Link Service Descriptors */
 enum {
 	FCNVME_LSDESC_RSVD		= 0x0,
 	FCNVME_LSDESC_RQST		= 0x1,
@@ -92,7 +98,6 @@ static inline __be32 fcnvme_lsdesc_len(size_t sz)
 	return cpu_to_be32(sz - (2 * sizeof(u32)));
 }
 
-
 struct fcnvme_ls_rqst_w0 {
 	u8	ls_cmd;			/* FCNVME_LS_xxx */
 	u8	zeros[3];
@@ -106,8 +111,53 @@ struct fcnvme_lsdesc_rqst {
 	__be32	rsvd12;
 };
 
+/* FC-NVME LS RJT reason_code values */
+enum fcnvme_ls_rjt_reason {
+	FCNVME_RJT_RC_NONE		= 0,
+	/* no reason - not to be sent */
+
+	FCNVME_RJT_RC_INVAL		= 0x01,
+	/* invalid NVMe_LS command code */
+
+	FCNVME_RJT_RC_LOGIC		= 0x03,
+	/* logical error */
+
+	FCNVME_RJT_RC_UNAB		= 0x09,
+	/* unable to perform command request */
+
+	FCNVME_RJT_RC_UNSUP		= 0x0b,
+	/* command not supported */
+
+	FCNVME_RJT_RC_INPROG		= 0x0e,
+	/* command already in progress */
 
+	FCNVME_RJT_RC_INV_ASSOC		= 0x40,
+	/* Invalid Association ID*/
 
+	FCNVME_RJT_RC_INV_CONN		= 0x41,
+	/* Invalid Connection ID*/
+
+	FCNVME_RJT_RC_VENDOR		= 0xff,
+	/* vendor specific error */
+};
+
+/* FC-NVME LS RJT reason_explanation values */
+enum fcnvme_ls_rjt_explan {
+	FCNVME_RJT_EXP_NONE		= 0x00,
+	/* No additional explanation */
+
+	FCNVME_RJT_EXP_OXID_RXID	= 0x17,
+	/* invalid OX_ID-RX_ID combination */
+
+	FCNVME_RJT_EXP_INSUF_RES	= 0x29,
+	/* insufficient resources */
+
+	FCNVME_RJT_EXP_UNAB_DATA	= 0x2a,
+	/* unable to supply requested data */
+
+	FCNVME_RJT_EXP_INV_LEN		= 0x2d,
+	/* Invalid payload length */
+};
 
 /* FCNVME_LSDESC_RJT */
 struct fcnvme_lsdesc_rjt {
@@ -119,15 +169,15 @@ struct fcnvme_lsdesc_rjt {
 	 * Reject reason and explanaction codes are generic
 	 * to ELs's from LS-3.
 	 */
-	u8	reason_code;
-	u8	reason_explanation;
+	u8	reason_code;		/* fcnvme_ls_rjt_reason */
+	u8	reason_explanation;	/* fcnvme_ls_rjt_explan */
 
 	u8	vendor;
 	__be32	rsvd12;
 };
 
 
-#define FCNVME_ASSOC_HOSTID_LEN		64
+#define FCNVME_ASSOC_HOSTID_LEN		16
 #define FCNVME_ASSOC_HOSTNQN_LEN	256
 #define FCNVME_ASSOC_SUBNQN_LEN		256
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index c43d435d4225..b625bacf37ef 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -64,26 +64,26 @@ enum {
  * RDMA_QPTYPE field
  */
 enum {
-	NVMF_RDMA_QPTYPE_CONNECTED	= 0, /* Reliable Connected */
-	NVMF_RDMA_QPTYPE_DATAGRAM	= 1, /* Reliable Datagram */
+	NVMF_RDMA_QPTYPE_CONNECTED	= 1, /* Reliable Connected */
+	NVMF_RDMA_QPTYPE_DATAGRAM	= 2, /* Reliable Datagram */
 };
 
 /* RDMA QP Service Type codes for Discovery Log Page entry TSAS
  * RDMA_QPTYPE field
  */
 enum {
-	NVMF_RDMA_PRTYPE_NOT_SPECIFIED	= 0, /* No Provider Specified */
-	NVMF_RDMA_PRTYPE_IB		= 1, /* InfiniBand */
-	NVMF_RDMA_PRTYPE_ROCE		= 2, /* InfiniBand RoCE */
-	NVMF_RDMA_PRTYPE_ROCEV2		= 3, /* InfiniBand RoCEV2 */
-	NVMF_RDMA_PRTYPE_IWARP		= 4, /* IWARP */
+	NVMF_RDMA_PRTYPE_NOT_SPECIFIED	= 1, /* No Provider Specified */
+	NVMF_RDMA_PRTYPE_IB		= 2, /* InfiniBand */
+	NVMF_RDMA_PRTYPE_ROCE		= 3, /* InfiniBand RoCE */
+	NVMF_RDMA_PRTYPE_ROCEV2		= 4, /* InfiniBand RoCEV2 */
+	NVMF_RDMA_PRTYPE_IWARP		= 5, /* IWARP */
 };
 
 /* RDMA Connection Management Service Type codes for Discovery Log Page
  * entry TSAS RDMA_CMS field
  */
 enum {
-	NVMF_RDMA_CMS_RDMA_CM	= 0, /* Sockets based enpoint addressing */
+	NVMF_RDMA_CMS_RDMA_CM	= 1, /* Sockets based endpoint addressing */
 };
 
 #define NVMF_AQ_DEPTH		32
@@ -245,6 +245,7 @@ enum {
 	NVME_CTRL_ONCS_WRITE_ZEROES		= 1 << 3,
 	NVME_CTRL_VWC_PRESENT			= 1 << 0,
 	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
+	NVME_CTRL_OACS_DBBUF_SUPP		= 1 << 7,
 };
 
 struct nvme_lbaf {
@@ -603,6 +604,7 @@ enum nvme_admin_opcode {
 	nvme_admin_download_fw		= 0x11,
 	nvme_admin_ns_attach		= 0x15,
 	nvme_admin_keep_alive		= 0x18,
+	nvme_admin_dbbuf		= 0x7C,
 	nvme_admin_format_nvm		= 0x80,
 	nvme_admin_security_send	= 0x81,
 	nvme_admin_security_recv	= 0x82,
@@ -874,6 +876,16 @@ struct nvmf_property_get_command {
 	__u8		resv4[16];
 };
 
+struct nvme_dbbuf {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__u32			rsvd1[5];
+	__le64			prp1;
+	__le64			prp2;
+	__u32			rsvd12[6];
+};
+
 struct nvme_command {
 	union {
 		struct nvme_common_command common;
@@ -893,6 +905,7 @@ struct nvme_command {
 		struct nvmf_connect_command connect;
 		struct nvmf_property_set_command prop_set;
 		struct nvmf_property_get_command prop_get;
+		struct nvme_dbbuf dbbuf;
 	};
 };
 
diff --git a/include/linux/of.h b/include/linux/of.h
index 21e6323de0f3..e5d4225fda35 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -159,6 +159,8 @@ static inline struct device_node *to_of_node(struct fwnode_handle *fwnode)
 		container_of(fwnode, struct device_node, fwnode) : NULL;
 }
 
+#define of_fwnode_handle(node) (&(node)->fwnode)
+
 static inline bool of_have_populated_dt(void)
 {
 	return of_root != NULL;
@@ -602,6 +604,8 @@ static inline struct device_node *of_find_node_with_property(
 	return NULL;
 }
 
+#define of_fwnode_handle(node) NULL
+
 static inline bool of_have_populated_dt(void)
 {
 	return false;
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index a58cca8bcb29..ba35ba520487 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -12,7 +12,7 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
-#ifdef CONFIG_OF
+#if IS_ENABLED(CONFIG_OF_MDIO)
 extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
 extern struct phy_device *of_phy_find_device(struct device_node *phy_np);
 extern struct phy_device *of_phy_connect(struct net_device *dev,
@@ -32,7 +32,7 @@ extern int of_phy_register_fixed_link(struct device_node *np);
 extern void of_phy_deregister_fixed_link(struct device_node *np);
 extern bool of_phy_is_fixed_link(struct device_node *np);
 
-#else /* CONFIG_OF */
+#else /* CONFIG_OF_MDIO */
 static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 {
 	/*
diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h
index 35d0fd7a4948..fd0de00c0d77 100644
--- a/include/linux/omap-gpmc.h
+++ b/include/linux/omap-gpmc.h
@@ -76,22 +76,12 @@ struct gpmc_timings;
 struct omap_nand_platform_data;
 struct omap_onenand_platform_data;
 
-#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2)
-extern int gpmc_nand_init(struct omap_nand_platform_data *d,
-			  struct gpmc_timings *gpmc_t);
-#else
-static inline int gpmc_nand_init(struct omap_nand_platform_data *d,
-				 struct gpmc_timings *gpmc_t)
-{
-	return 0;
-}
-#endif
-
 #if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2)
-extern void gpmc_onenand_init(struct omap_onenand_platform_data *d);
+extern int gpmc_onenand_init(struct omap_onenand_platform_data *d);
 #else
 #define board_onenand_data	NULL
-static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d)
+static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d)
 {
+	return 0;
 }
 #endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 84943e8057ef..316a19f6b635 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -148,7 +148,7 @@ static inline int page_cache_get_speculative(struct page *page)
 
 #ifdef CONFIG_TINY_RCU
 # ifdef CONFIG_PREEMPT_COUNT
-	VM_BUG_ON(!in_atomic());
+	VM_BUG_ON(!in_atomic() && !irqs_disabled());
 # endif
 	/*
 	 * Preempt must be disabled here - we rely on rcu_read_lock doing
@@ -186,7 +186,7 @@ static inline int page_cache_add_speculative(struct page *page, int count)
 
 #if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
 # ifdef CONFIG_PREEMPT_COUNT
-	VM_BUG_ON(!in_atomic());
+	VM_BUG_ON(!in_atomic() && !irqs_disabled());
 # endif
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
 	page_ref_add(page, count);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index eb3da1a04e6c..82dec36845e6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1300,7 +1300,6 @@ int pci_msi_vec_count(struct pci_dev *dev);
 void pci_msi_shutdown(struct pci_dev *dev);
 void pci_disable_msi(struct pci_dev *dev);
 int pci_msix_vec_count(struct pci_dev *dev);
-int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec);
 void pci_msix_shutdown(struct pci_dev *dev);
 void pci_disable_msix(struct pci_dev *dev);
 void pci_restore_msi_state(struct pci_dev *dev);
@@ -1330,9 +1329,6 @@ static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
 static inline void pci_msi_shutdown(struct pci_dev *dev) { }
 static inline void pci_disable_msi(struct pci_dev *dev) { }
 static inline int pci_msix_vec_count(struct pci_dev *dev) { return -ENOSYS; }
-static inline int pci_enable_msix(struct pci_dev *dev,
-				  struct msix_entry *entries, int nvec)
-{ return -ENOSYS; }
 static inline void pci_msix_shutdown(struct pci_dev *dev) { }
 static inline void pci_disable_msix(struct pci_dev *dev) { }
 static inline void pci_restore_msi_state(struct pci_dev *dev) { }
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 56939d3f6e53..491b3f5a5f8a 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -110,6 +110,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
 #endif
 
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
+extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
 #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 000fdb211c7d..24a635887f28 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -165,6 +165,13 @@ struct hw_perf_event {
 			struct list_head		bp_list;
 		};
 #endif
+		struct { /* amd_iommu */
+			u8	iommu_bank;
+			u8	iommu_cntr;
+			u16	padding;
+			u64	conf;
+			u64	conf1;
+		};
 	};
 	/*
 	 * If the event is a per task event, this will point to the task in
@@ -801,6 +808,7 @@ struct perf_output_handle {
 	struct ring_buffer		*rb;
 	unsigned long			wakeup;
 	unsigned long			size;
+	u64				aux_flags;
 	union {
 		void			*addr;
 		unsigned long		head;
@@ -849,10 +857,11 @@ perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
 extern void *perf_aux_output_begin(struct perf_output_handle *handle,
 				   struct perf_event *event);
 extern void perf_aux_output_end(struct perf_output_handle *handle,
-				unsigned long size, bool truncated);
+				unsigned long size);
 extern int perf_aux_output_skip(struct perf_output_handle *handle,
 				unsigned long size);
 extern void *perf_get_aux(struct perf_output_handle *handle);
+extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
 
 extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
 extern void perf_pmu_unregister(struct pmu *pmu);
@@ -1112,6 +1121,7 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 
 extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
+extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
 /* Callchains */
@@ -1267,8 +1277,8 @@ static inline void *
 perf_aux_output_begin(struct perf_output_handle *handle,
 		      struct perf_event *event)				{ return NULL; }
 static inline void
-perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
-		    bool truncated)					{ }
+perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
+									{ }
 static inline int
 perf_aux_output_skip(struct perf_output_handle *handle,
 		     unsigned long size)				{ return -EINVAL; }
@@ -1315,6 +1325,7 @@ static inline int perf_unregister_guest_info_callbacks
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
+static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 772476028a65..e76e4adbc7c7 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -217,6 +217,13 @@ struct mii_bus {
 	 * matching its address
 	 */
 	int irq[PHY_MAX_ADDR];
+
+	/* GPIO reset pulse width in microseconds */
+	int reset_delay_us;
+	/* Number of reset GPIOs */
+	int num_reset_gpios;
+	/* Array of RESET GPIO descriptors */
+	struct gpio_desc **reset_gpiod;
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
@@ -587,23 +594,29 @@ struct phy_driver {
 	 */
 	void (*link_change_notify)(struct phy_device *dev);
 
-	/* A function provided by a phy specific driver to override the
-	 * the PHY driver framework support for reading a MMD register
-	 * from the PHY. If not supported, return -1. This function is
-	 * optional for PHY specific drivers, if not provided then the
-	 * default MMD read function is used by the PHY framework.
+	/*
+	 * Phy specific driver override for reading a MMD register.
+	 * This function is optional for PHY specific drivers.  When
+	 * not provided, the default MMD read function will be used
+	 * by phy_read_mmd(), which will use either a direct read for
+	 * Clause 45 PHYs or an indirect read for Clause 22 PHYs.
+	 *  devnum is the MMD device number within the PHY device,
+	 *  regnum is the register within the selected MMD device.
 	 */
-	int (*read_mmd_indirect)(struct phy_device *dev, int ptrad,
-				 int devnum, int regnum);
-
-	/* A function provided by a phy specific driver to override the
-	 * the PHY driver framework support for writing a MMD register
-	 * from the PHY. This function is optional for PHY specific drivers,
-	 * if not provided then the default MMD read function is used by
-	 * the PHY framework.
+	int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
+
+	/*
+	 * Phy specific driver override for writing a MMD register.
+	 * This function is optional for PHY specific drivers.  When
+	 * not provided, the default MMD write function will be used
+	 * by phy_write_mmd(), which will use either a direct write for
+	 * Clause 45 PHYs, or an indirect write for Clause 22 PHYs.
+	 *  devnum is the MMD device number within the PHY device,
+	 *  regnum is the register within the selected MMD device.
+	 *  val is the value to be written.
 	 */
-	void (*write_mmd_indirect)(struct phy_device *dev, int ptrad,
-				   int devnum, int regnum, u32 val);
+	int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum,
+			 u16 val);
 
 	/* Get the size and type of the eeprom contained within a plug-in
 	 * module */
@@ -651,25 +664,7 @@ struct phy_fixup {
  *
  * Same rules as for phy_read();
  */
-static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
-{
-	if (!phydev->is_c45)
-		return -EOPNOTSUPP;
-
-	return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr,
-			    MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff));
-}
-
-/**
- * phy_read_mmd_indirect - reads data from the MMD registers
- * @phydev: The PHY device bus
- * @prtad: MMD Address
- * @addr: PHY address on the MII bus
- *
- * Description: it reads data from the MMD registers (clause 22 to access to
- * clause 45) of the specified phy address.
- */
-int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad);
+int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
 /**
  * phy_read - Convenience function for reading a given PHY register
@@ -752,35 +747,29 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev)
  *
  * Same rules as for phy_write();
  */
-static inline int phy_write_mmd(struct phy_device *phydev, int devad,
-				u32 regnum, u16 val)
-{
-	if (!phydev->is_c45)
-		return -EOPNOTSUPP;
-
-	regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff);
-
-	return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val);
-}
-
-/**
- * phy_write_mmd_indirect - writes data to the MMD registers
- * @phydev: The PHY device
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- * @data: data to write in the MMD register
- *
- * Description: Write data from the MMD registers of the specified
- * phy address.
- */
-void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
-			    int devad, u32 data);
+int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
 
 struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
+#if IS_ENABLED(CONFIG_PHYLIB)
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
 int phy_device_register(struct phy_device *phy);
+void phy_device_free(struct phy_device *phydev);
+#else
+static inline
+struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
+{
+	return NULL;
+}
+
+static inline int phy_device_register(struct phy_device *phy)
+{
+	return 0;
+}
+
+static inline void phy_device_free(struct phy_device *phydev) { }
+#endif /* CONFIG_PHYLIB */
 void phy_device_remove(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
@@ -837,6 +826,10 @@ int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
 int genphy_soft_reset(struct phy_device *phydev);
+static inline int genphy_no_soft_reset(struct phy_device *phydev)
+{
+	return 0;
+}
 void phy_driver_unregister(struct phy_driver *drv);
 void phy_drivers_unregister(struct phy_driver *drv, int n);
 int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
@@ -848,6 +841,7 @@ void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev, int new_link);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
+void phy_trigger_machine(struct phy_device *phydev, bool sync);
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_ksettings_get(struct phy_device *phydev,
@@ -857,7 +851,6 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd);
 int phy_start_interrupts(struct phy_device *phydev);
 void phy_print_status(struct phy_device *phydev);
-void phy_device_free(struct phy_device *phydev);
 int phy_set_max_speed(struct phy_device *phydev, u32 max_speed);
 
 int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
@@ -884,8 +877,10 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 				   const struct ethtool_link_ksettings *cmd);
 int phy_ethtool_nway_reset(struct net_device *ndev);
 
+#if IS_ENABLED(CONFIG_PHYLIB)
 int __init mdio_bus_init(void);
 void mdio_bus_exit(void);
+#endif
 
 extern struct bus_type mdio_bus_type;
 
@@ -896,7 +891,7 @@ struct mdio_board_info {
 	const void	*platform_data;
 };
 
-#if IS_ENABLED(CONFIG_PHYLIB)
+#if IS_ENABLED(CONFIG_MDIO_DEVICE)
 int mdiobus_register_board_info(const struct mdio_board_info *info,
 				unsigned int n);
 #else
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index 7620eb127cff..279e3c5326e3 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -42,6 +42,8 @@
  * @PIN_CONFIG_BIAS_PULL_UP: the pin will be pulled up (usually with high
  *	impedance to VDD). If the argument is != 0 pull-up is enabled,
  *	if it is 0, pull-up is total, i.e. the pin is connected to VDD.
+ * @PIN_CONFIG_BIDIRECTIONAL: the pin will be configured to allow simultaneous
+ *	input and output operations.
  * @PIN_CONFIG_DRIVE_OPEN_DRAIN: the pin will be driven with open drain (open
  *	collector) which means it is usually wired with other output ports
  *	which are then pulled up with an external resistor. Setting this
@@ -96,6 +98,7 @@ enum pin_config_param {
 	PIN_CONFIG_BIAS_PULL_DOWN,
 	PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
 	PIN_CONFIG_BIAS_PULL_UP,
+	PIN_CONFIG_BIDIRECTIONAL,
 	PIN_CONFIG_DRIVE_OPEN_DRAIN,
 	PIN_CONFIG_DRIVE_OPEN_SOURCE,
 	PIN_CONFIG_DRIVE_PUSH_PULL,
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 8ce2d87a238b..5e45385c5bdc 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -145,8 +145,9 @@ struct pinctrl_desc {
 extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
 				     struct device *dev, void *driver_data,
 				     struct pinctrl_dev **pctldev);
+extern int pinctrl_enable(struct pinctrl_dev *pctldev);
 
-/* Please use pinctrl_register_and_init() instead */
+/* Please use pinctrl_register_and_init() and pinctrl_enable() instead */
 extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
 				struct device *dev, void *driver_data);
 
diff --git a/include/linux/platform_data/pn544.h b/include/linux/platform_data/pn544.h
deleted file mode 100644
index 5ce1ab983f44..000000000000
--- a/include/linux/platform_data/pn544.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Driver include for the PN544 NFC chip.
- *
- * Copyright (C) Nokia Corporation
- *
- * Author: Jari Vanhala <ext-jari.vanhala@nokia.com>
- * Contact: Matti Aaltoenn <matti.j.aaltonen@nokia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _PN544_H_
-#define _PN544_H_
-
-#include <linux/i2c.h>
-
-enum {
-	NFC_GPIO_ENABLE,
-	NFC_GPIO_FW_RESET,
-	NFC_GPIO_IRQ
-};
-
-/* board config */
-struct pn544_nfc_platform_data {
-	int (*request_resources) (struct i2c_client *client);
-	void (*free_resources) (void);
-	void (*enable) (int fw);
-	int (*test) (void);
-	void (*disable) (void);
-	int (*get_gpio)(int type);
-};
-
-#endif /* _PN544_H_ */
diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h
deleted file mode 100644
index cc2bdafb0c69..000000000000
--- a/include/linux/platform_data/st21nfca.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * Driver include for the ST21NFCA NFC chip.
- *
- * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _ST21NFCA_HCI_H_
-#define _ST21NFCA_HCI_H_
-
-#include <linux/i2c.h>
-
-#define ST21NFCA_HCI_DRIVER_NAME "st21nfca_hci"
-
-struct st21nfca_nfc_platform_data {
-	unsigned int gpio_ena;
-	unsigned int irq_polarity;
-	bool is_ese_present;
-	bool is_uicc_present;
-};
-
-#endif /* _ST21NFCA_HCI_H_ */
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 5339ed5bd6f9..9b6abe632587 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -20,6 +20,7 @@
 /* Defines used for the flags field in the struct generic_pm_domain */
 #define GENPD_FLAG_PM_CLK	(1U << 0) /* PM domain uses PM clk */
 #define GENPD_FLAG_IRQ_SAFE	(1U << 1) /* PM domain operates in atomic */
+#define GENPD_FLAG_ALWAYS_ON	(1U << 2) /* PM domain is always powered on */
 
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
diff --git a/include/linux/poll.h b/include/linux/poll.h
index a46d6755035e..75ffc5729e4c 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -98,64 +98,8 @@ extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 				 ktime_t *expires, unsigned long slack);
 extern u64 select_estimate_accuracy(struct timespec64 *tv);
 
-
-static inline int poll_schedule(struct poll_wqueues *pwq, int state)
-{
-	return poll_schedule_timeout(pwq, state, NULL, 0);
-}
-
-/*
- * Scalable version of the fd_set.
- */
-
-typedef struct {
-	unsigned long *in, *out, *ex;
-	unsigned long *res_in, *res_out, *res_ex;
-} fd_set_bits;
-
-/*
- * How many longwords for "nr" bits?
- */
-#define FDS_BITPERLONG	(8*sizeof(long))
-#define FDS_LONGS(nr)	(((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
-#define FDS_BYTES(nr)	(FDS_LONGS(nr)*sizeof(long))
-
-/*
- * We do a VERIFY_WRITE here even though we are only reading this time:
- * we'll write to it eventually..
- *
- * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
- */
-static inline
-int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
-{
-	nr = FDS_BYTES(nr);
-	if (ufdset)
-		return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
-
-	memset(fdset, 0, nr);
-	return 0;
-}
-
-static inline unsigned long __must_check
-set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
-{
-	if (ufdset)
-		return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
-	return 0;
-}
-
-static inline
-void zero_fd_set(unsigned long nr, unsigned long *fdset)
-{
-	memset(fdset, 0, FDS_BYTES(nr));
-}
-
 #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
 
-extern int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time);
-extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
-		       struct timespec64 *end_time);
 extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 			   fd_set __user *exp, struct timespec64 *end_time);
 
diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
index 34c4498b800f..83b22ae9ae12 100644
--- a/include/linux/posix-clock.h
+++ b/include/linux/posix-clock.h
@@ -59,23 +59,23 @@ struct posix_clock_operations {
 
 	int  (*clock_adjtime)(struct posix_clock *pc, struct timex *tx);
 
-	int  (*clock_gettime)(struct posix_clock *pc, struct timespec *ts);
+	int  (*clock_gettime)(struct posix_clock *pc, struct timespec64 *ts);
 
-	int  (*clock_getres) (struct posix_clock *pc, struct timespec *ts);
+	int  (*clock_getres) (struct posix_clock *pc, struct timespec64 *ts);
 
 	int  (*clock_settime)(struct posix_clock *pc,
-			      const struct timespec *ts);
+			      const struct timespec64 *ts);
 
 	int  (*timer_create) (struct posix_clock *pc, struct k_itimer *kit);
 
 	int  (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit);
 
 	void (*timer_gettime)(struct posix_clock *pc,
-			      struct k_itimer *kit, struct itimerspec *tsp);
+			      struct k_itimer *kit, struct itimerspec64 *tsp);
 
 	int  (*timer_settime)(struct posix_clock *pc,
 			      struct k_itimer *kit, int flags,
-			      struct itimerspec *tsp, struct itimerspec *old);
+			      struct itimerspec64 *tsp, struct itimerspec64 *old);
 	/*
 	 * Optional character device methods:
 	 */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 64aa189efe21..8c1e43ab14a9 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -87,22 +87,22 @@ struct k_itimer {
 };
 
 struct k_clock {
-	int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
+	int (*clock_getres) (const clockid_t which_clock, struct timespec64 *tp);
 	int (*clock_set) (const clockid_t which_clock,
-			  const struct timespec *tp);
-	int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
+			  const struct timespec64 *tp);
+	int (*clock_get) (const clockid_t which_clock, struct timespec64 *tp);
 	int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
 	int (*timer_create) (struct k_itimer *timer);
 	int (*nsleep) (const clockid_t which_clock, int flags,
-		       struct timespec *, struct timespec __user *);
+		       struct timespec64 *, struct timespec __user *);
 	long (*nsleep_restart) (struct restart_block *restart_block);
-	int (*timer_set) (struct k_itimer * timr, int flags,
-			  struct itimerspec * new_setting,
-			  struct itimerspec * old_setting);
-	int (*timer_del) (struct k_itimer * timr);
+	int (*timer_set) (struct k_itimer *timr, int flags,
+			  struct itimerspec64 *new_setting,
+			  struct itimerspec64 *old_setting);
+	int (*timer_del) (struct k_itimer *timr);
 #define TIMER_RETRY 1
-	void (*timer_get) (struct k_itimer * timr,
-			   struct itimerspec * cur_setting);
+	void (*timer_get) (struct k_itimer *timr,
+			   struct itimerspec64 *cur_setting);
 };
 
 extern struct k_clock clock_posix_cpu;
diff --git a/include/linux/power/bq24190_charger.h b/include/linux/power/bq24190_charger.h
deleted file mode 100644
index 9f0283721cbc..000000000000
--- a/include/linux/power/bq24190_charger.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Platform data for the TI bq24190 battery charger driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _BQ24190_CHARGER_H_
-#define _BQ24190_CHARGER_H_
-
-struct bq24190_platform_data {
-	unsigned int	gpio_int;	/* GPIO pin that's connected to INT# */
-};
-
-#endif
diff --git a/include/linux/property.h b/include/linux/property.h
index 64e3a9c6d95f..2f482616a2f2 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -33,6 +33,8 @@ enum dev_dma_attr {
 	DEV_DMA_COHERENT,
 };
 
+struct fwnode_handle *dev_fwnode(struct device *dev);
+
 bool device_property_present(struct device *dev, const char *propname);
 int device_property_read_u8_array(struct device *dev, const char *propname,
 				  u8 *val, size_t nval);
@@ -70,6 +72,15 @@ int fwnode_property_read_string(struct fwnode_handle *fwnode,
 int fwnode_property_match_string(struct fwnode_handle *fwnode,
 				 const char *propname, const char *string);
 
+struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode,
+						 struct fwnode_handle *child);
+
+#define fwnode_for_each_child_node(fwnode, child)			\
+	for (child = fwnode_get_next_child_node(fwnode, NULL); child;	\
+	     child = fwnode_get_next_child_node(fwnode, child))
+
 struct fwnode_handle *device_get_next_child_node(struct device *dev,
 						 struct fwnode_handle *child);
 
@@ -77,9 +88,12 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev,
 	for (child = device_get_next_child_node(dev, NULL); child;	\
 	     child = device_get_next_child_node(dev, child))
 
+struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode,
+						  const char *childname);
 struct fwnode_handle *device_get_named_child_node(struct device *dev,
 						  const char *childname);
 
+void fwnode_handle_get(struct fwnode_handle *fwnode);
 void fwnode_handle_put(struct fwnode_handle *fwnode);
 
 unsigned int device_get_child_node_count(struct device *dev);
@@ -258,4 +272,16 @@ int device_get_phy_mode(struct device *dev);
 
 void *device_get_mac_address(struct device *dev, char *addr, int alen);
 
+struct fwnode_handle *fwnode_graph_get_next_endpoint(
+	struct fwnode_handle *fwnode, struct fwnode_handle *prev);
+struct fwnode_handle *fwnode_graph_get_remote_port_parent(
+	struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_graph_get_remote_port(
+	struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_graph_get_remote_endpoint(
+	struct fwnode_handle *fwnode);
+
+int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
+				struct fwnode_endpoint *endpoint);
+
 #endif /* _LINUX_PROPERTY_H_ */
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index 0da29cae009b..e2233f50f428 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -30,7 +30,9 @@
 #include <linux/time.h>
 #include <linux/types.h>
 
-/* types */
+struct module;
+
+/* pstore record types (see fs/pstore/inode.c for filename templates) */
 enum pstore_type_id {
 	PSTORE_TYPE_DMESG	= 0,
 	PSTORE_TYPE_MCE		= 1,
@@ -45,42 +47,146 @@ enum pstore_type_id {
 	PSTORE_TYPE_UNKNOWN	= 255
 };
 
-struct module;
+struct pstore_info;
+/**
+ * struct pstore_record - details of a pstore record entry
+ * @psi:	pstore backend driver information
+ * @type:	pstore record type
+ * @id:		per-type unique identifier for record
+ * @time:	timestamp of the record
+ * @buf:	pointer to record contents
+ * @size:	size of @buf
+ * @ecc_notice_size:
+ *		ECC information for @buf
+ *
+ * Valid for PSTORE_TYPE_DMESG @type:
+ *
+ * @count:	Oops count since boot
+ * @reason:	kdump reason for notification
+ * @part:	position in a multipart record
+ * @compressed:	whether the buffer is compressed
+ *
+ */
+struct pstore_record {
+	struct pstore_info	*psi;
+	enum pstore_type_id	type;
+	u64			id;
+	struct timespec		time;
+	char			*buf;
+	ssize_t			size;
+	ssize_t			ecc_notice_size;
 
+	int			count;
+	enum kmsg_dump_reason	reason;
+	unsigned int		part;
+	bool			compressed;
+};
+
+/**
+ * struct pstore_info - backend pstore driver structure
+ *
+ * @owner:	module which is repsonsible for this backend driver
+ * @name:	name of the backend driver
+ *
+ * @buf_lock:	spinlock to serialize access to @buf
+ * @buf:	preallocated crash dump buffer
+ * @bufsize:	size of @buf available for crash dump writes
+ *
+ * @read_mutex:	serializes @open, @read, @close, and @erase callbacks
+ * @flags:	bitfield of frontends the backend can accept writes for
+ * @data:	backend-private pointer passed back during callbacks
+ *
+ * Callbacks:
+ *
+ * @open:
+ *	Notify backend that pstore is starting a full read of backend
+ *	records. Followed by one or more @read calls, and a final @close.
+ *
+ *	@psi:	in: pointer to the struct pstore_info for the backend
+ *
+ *	Returns 0 on success, and non-zero on error.
+ *
+ * @close:
+ *	Notify backend that pstore has finished a full read of backend
+ *	records. Always preceded by an @open call and one or more @read
+ *	calls.
+ *
+ *	@psi:	in: pointer to the struct pstore_info for the backend
+ *
+ *	Returns 0 on success, and non-zero on error. (Though pstore will
+ *	ignore the error.)
+ *
+ * @read:
+ *	Read next available backend record. Called after a successful
+ *	@open.
+ *
+ *	@record:
+ *		pointer to record to populate. @buf should be allocated
+ *		by the backend and filled. At least @type and @id should
+ *		be populated, since these are used when creating pstorefs
+ *		file names.
+ *
+ *	Returns record size on success, zero when no more records are
+ *	available, or negative on error.
+ *
+ * @write:
+ *	A newly generated record needs to be written to backend storage.
+ *
+ *	@record:
+ *		pointer to record metadata. When @type is PSTORE_TYPE_DMESG,
+ *		@buf will be pointing to the preallocated @psi.buf, since
+ *		memory allocation may be broken during an Oops. Regardless,
+ *		@buf must be proccesed or copied before returning. The
+ *		backend is also expected to write @id with something that
+ 8		can help identify this record to a future @erase callback.
+ *
+ *	Returns 0 on success, and non-zero on error.
+ *
+ * @write_user:
+ *	Perform a frontend write to a backend record, using a specified
+ *	buffer that is coming directly from userspace, instead of the
+ *	@record @buf.
+ *
+ *	@record:	pointer to record metadata.
+ *	@buf:		pointer to userspace contents to write to backend
+ *
+ *	Returns 0 on success, and non-zero on error.
+ *
+ * @erase:
+ *	Delete a record from backend storage.  Different backends
+ *	identify records differently, so entire original record is
+ *	passed back to assist in identification of what the backend
+ *	should remove from storage.
+ *
+ *	@record:	pointer to record metadata.
+ *
+ *	Returns 0 on success, and non-zero on error.
+ *
+ */
 struct pstore_info {
 	struct module	*owner;
 	char		*name;
-	spinlock_t	buf_lock;	/* serialize access to 'buf' */
+
+	spinlock_t	buf_lock;
 	char		*buf;
 	size_t		bufsize;
-	struct mutex	read_mutex;	/* serialize open/read/close */
+
+	struct mutex	read_mutex;
+
 	int		flags;
+	void		*data;
+
 	int		(*open)(struct pstore_info *psi);
 	int		(*close)(struct pstore_info *psi);
-	ssize_t		(*read)(u64 *id, enum pstore_type_id *type,
-			int *count, struct timespec *time, char **buf,
-			bool *compressed, ssize_t *ecc_notice_size,
-			struct pstore_info *psi);
-	int		(*write)(enum pstore_type_id type,
-			enum kmsg_dump_reason reason, u64 *id,
-			unsigned int part, int count, bool compressed,
-			size_t size, struct pstore_info *psi);
-	int		(*write_buf)(enum pstore_type_id type,
-			enum kmsg_dump_reason reason, u64 *id,
-			unsigned int part, const char *buf, bool compressed,
-			size_t size, struct pstore_info *psi);
-	int		(*write_buf_user)(enum pstore_type_id type,
-			enum kmsg_dump_reason reason, u64 *id,
-			unsigned int part, const char __user *buf,
-			bool compressed, size_t size, struct pstore_info *psi);
-	int		(*erase)(enum pstore_type_id type, u64 id,
-			int count, struct timespec time,
-			struct pstore_info *psi);
-	void		*data;
+	ssize_t		(*read)(struct pstore_record *record);
+	int		(*write)(struct pstore_record *record);
+	int		(*write_user)(struct pstore_record *record,
+				      const char __user *buf);
+	int		(*erase)(struct pstore_record *record);
 };
 
+/* Supported frontends */
 #define PSTORE_FLAGS_DMESG	(1 << 0)
-#define PSTORE_FLAGS_FRAGILE	PSTORE_FLAGS_DMESG
 #define PSTORE_FLAGS_CONSOLE	(1 << 1)
 #define PSTORE_FLAGS_FTRACE	(1 << 2)
 #define PSTORE_FLAGS_PMSG	(1 << 3)
diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h
new file mode 100644
index 000000000000..d60d4e278609
--- /dev/null
+++ b/include/linux/purgatory.h
@@ -0,0 +1,23 @@
+#ifndef _LINUX_PURGATORY_H
+#define _LINUX_PURGATORY_H
+
+#include <linux/types.h>
+#include <crypto/sha.h>
+#include <uapi/linux/kexec.h>
+
+struct kexec_sha_region {
+	unsigned long start;
+	unsigned long len;
+};
+
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ *    lookup in kexec works
+ */
+extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
+extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
+
+#endif
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 52966b9bfde3..fbab6e0514f0 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -100,8 +100,8 @@
 #define MAX_NUM_LL2_TX_STATS_COUNTERS	32
 
 #define FW_MAJOR_VERSION	8
-#define FW_MINOR_VERSION	10
-#define FW_REVISION_VERSION	10
+#define FW_MINOR_VERSION	15
+#define FW_REVISION_VERSION	3
 #define FW_ENGINEERING_VERSION	0
 
 /***********************/
@@ -187,6 +187,9 @@
 
 /* DEMS */
 #define DQ_DEMS_LEGACY			0
+#define DQ_DEMS_TOE_MORE_TO_SEND	3
+#define DQ_DEMS_TOE_LOCAL_ADV_WND	4
+#define DQ_DEMS_ROCE_CQ_CONS		7
 
 /* XCM agg val selection */
 #define DQ_XCM_AGG_VAL_SEL_WORD2  0
@@ -214,6 +217,9 @@
 #define DQ_XCM_ISCSI_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3
 #define DQ_XCM_ISCSI_EXP_STAT_SN_CMD	DQ_XCM_AGG_VAL_SEL_REG6
 #define DQ_XCM_ROCE_SQ_PROD_CMD	DQ_XCM_AGG_VAL_SEL_WORD4
+#define DQ_XCM_TOE_TX_BD_PROD_CMD	DQ_XCM_AGG_VAL_SEL_WORD4
+#define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD	DQ_XCM_AGG_VAL_SEL_REG3
+#define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4
 
 /* UCM agg val selection (HW) */
 #define	DQ_UCM_AGG_VAL_SEL_WORD0	0
@@ -269,6 +275,8 @@
 #define DQ_XCM_ISCSI_DQ_FLUSH_CMD	BIT(DQ_XCM_AGG_FLG_SHIFT_CF19)
 #define DQ_XCM_ISCSI_SLOW_PATH_CMD	BIT(DQ_XCM_AGG_FLG_SHIFT_CF22)
 #define DQ_XCM_ISCSI_PROC_ONLY_CLEANUP_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23)
+#define DQ_XCM_TOE_DQ_FLUSH_CMD		BIT(DQ_XCM_AGG_FLG_SHIFT_CF19)
+#define DQ_XCM_TOE_SLOW_PATH_CMD	BIT(DQ_XCM_AGG_FLG_SHIFT_CF22)
 
 /* UCM agg counter flag selection (HW) */
 #define	DQ_UCM_AGG_FLG_SHIFT_CF0	0
@@ -285,6 +293,9 @@
 #define DQ_UCM_ETH_PMD_RX_ARM_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
 #define DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF4)
 #define DQ_UCM_ROCE_CQ_ARM_CF_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
+#define DQ_UCM_TOE_TIMER_STOP_ALL_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF3)
+#define DQ_UCM_TOE_SLOW_PATH_CF_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF4)
+#define DQ_UCM_TOE_DQ_CF_CMD		BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
 
 /* TCM agg counter flag selection (HW) */
 #define DQ_TCM_AGG_FLG_SHIFT_CF0	0
@@ -301,6 +312,9 @@
 #define DQ_TCM_FCOE_TIMER_STOP_ALL_CMD      BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
 #define DQ_TCM_ISCSI_FLUSH_Q0_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
 #define DQ_TCM_ISCSI_TIMER_STOP_ALL_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
+#define DQ_TCM_TOE_FLUSH_Q0_CMD		BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
+#define DQ_TCM_TOE_TIMER_STOP_ALL_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
+#define DQ_TCM_IWARP_POST_RQ_CF_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
 
 /* PWM address mapping */
 #define DQ_PWM_OFFSET_DPM_BASE	0x0
@@ -689,6 +703,16 @@ struct iscsi_eqe_data {
 #define ISCSI_EQE_DATA_RESERVED0_SHIFT			7
 };
 
+struct rdma_eqe_destroy_qp {
+	__le32 cid;
+	u8 reserved[4];
+};
+
+union rdma_eqe_data {
+	struct regpair async_handle;
+	struct rdma_eqe_destroy_qp rdma_destroy_qp_data;
+};
+
 struct malicious_vf_eqe_data {
 	u8 vf_id;
 	u8 err_id;
@@ -705,9 +729,9 @@ union event_ring_data {
 	u8 bytes[8];
 	struct vf_pf_channel_eqe_data vf_pf_channel;
 	struct iscsi_eqe_data iscsi_info;
+	union rdma_eqe_data rdma_data;
 	struct malicious_vf_eqe_data malicious_vf;
 	struct initial_cleanup_eqe_data vf_init_cleanup;
-	struct regpair roce_handle;
 };
 
 /* Event Ring Entry */
diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h
index 4b402fb0eaad..34d93eb5bfba 100644
--- a/include/linux/qed/eth_common.h
+++ b/include/linux/qed/eth_common.h
@@ -49,6 +49,9 @@
 #define ETH_RX_CQE_PAGE_SIZE_BYTES                      4096
 #define ETH_RX_NUM_NEXT_PAGE_BDS                        2
 
+#define ETH_MAX_TUNN_LSO_INNER_IPV4_OFFSET          253
+#define ETH_MAX_TUNN_LSO_INNER_IPV6_OFFSET          251
+
 #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT                          1
 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET                       18
 #define ETH_TX_MAX_BDS_PER_LSO_PACKET	255
diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h
index 2e417a45c5f7..947a635d04bb 100644
--- a/include/linux/qed/fcoe_common.h
+++ b/include/linux/qed/fcoe_common.h
@@ -109,13 +109,6 @@ struct fcoe_conn_terminate_ramrod_data {
 	struct regpair terminate_params_addr;
 };
 
-struct fcoe_fast_sgl_ctx {
-	struct regpair sgl_start_addr;
-	__le32 sgl_byte_offset;
-	__le16 task_reuse_cnt;
-	__le16 init_offset_in_first_sge;
-};
-
 struct fcoe_slow_sgl_ctx {
 	struct regpair base_sgl_addr;
 	__le16 curr_sge_off;
@@ -124,23 +117,16 @@ struct fcoe_slow_sgl_ctx {
 	__le16 reserved;
 };
 
-struct fcoe_sge {
-	struct regpair sge_addr;
-	__le16 size;
-	__le16 reserved0;
-	u8 reserved1[3];
-	u8 is_valid_sge;
-};
-
-union fcoe_data_desc_ctx {
-	struct fcoe_fast_sgl_ctx fast;
-	struct fcoe_slow_sgl_ctx slow;
-	struct fcoe_sge single_sge;
-};
-
 union fcoe_dix_desc_ctx {
 	struct fcoe_slow_sgl_ctx dix_sgl;
-	struct fcoe_sge cached_dix_sge;
+	struct scsi_sge cached_dix_sge;
+};
+
+struct fcoe_fast_sgl_ctx {
+	struct regpair sgl_start_addr;
+	__le32 sgl_byte_offset;
+	__le16 task_reuse_cnt;
+	__le16 init_offset_in_first_sge;
 };
 
 struct fcoe_fcp_cmd_payload {
@@ -172,57 +158,6 @@ enum fcoe_mode_type {
 	MAX_FCOE_MODE_TYPE
 };
 
-struct fcoe_mstorm_fcoe_task_st_ctx_fp {
-	__le16 flags;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_MASK                 0x7FFF
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_SHIFT                0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_MASK  0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_SHIFT 15
-	__le16 difDataResidue;
-	__le16 parent_id;
-	__le16 single_sge_saved_offset;
-	__le32 data_2_trns_rem;
-	__le32 offset_in_io;
-	union fcoe_dix_desc_ctx dix_desc;
-	union fcoe_data_desc_ctx data_desc;
-};
-
-struct fcoe_mstorm_fcoe_task_st_ctx_non_fp {
-	__le16 flags;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_MASK            0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_SHIFT           0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_MASK               0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_SHIFT              2
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_MASK      0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_SHIFT     3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_MASK         0xF
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_SHIFT        4
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_MASK            0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_SHIFT           8
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_MASK                  0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_SHIFT                 10
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_MASK  0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_SHIFT 11
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_MASK      0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_SHIFT     12
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_MASK        0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_SHIFT       13
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_MASK        0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_SHIFT       14
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_MASK             0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_SHIFT            15
-	u8 tx_rx_sgl_mode;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_MASK               0x7
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_SHIFT              0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_MASK               0x7
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_SHIFT              3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_MASK                     0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_SHIFT                    6
-	u8 rsrv2;
-	__le32 num_prm_zero_read;
-	struct regpair rsp_buf_addr;
-};
-
 struct fcoe_rx_stat {
 	struct regpair fcoe_rx_byte_cnt;
 	struct regpair fcoe_rx_data_pkt_cnt;
@@ -236,16 +171,6 @@ struct fcoe_rx_stat {
 	__le32 rsrv;
 };
 
-enum fcoe_sgl_mode {
-	FCOE_SLOW_SGL,
-	FCOE_SINGLE_FAST_SGE,
-	FCOE_2_FAST_SGE,
-	FCOE_3_FAST_SGE,
-	FCOE_4_FAST_SGE,
-	FCOE_MUL_FAST_SGES,
-	MAX_FCOE_SGL_MODE
-};
-
 struct fcoe_stat_ramrod_data {
 	struct regpair stat_params_addr;
 };
@@ -328,22 +253,24 @@ union fcoe_tx_info_union_ctx {
 struct ystorm_fcoe_task_st_ctx {
 	u8 task_type;
 	u8 sgl_mode;
-#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK  0x7
+#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK  0x1
 #define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 0
-#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK         0x1F
-#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT        3
+#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK         0x7F
+#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT        1
 	u8 cached_dix_sge;
 	u8 expect_first_xfer;
 	__le32 num_pbf_zero_write;
 	union protection_info_union_ctx protection_info_union;
 	__le32 data_2_trns_rem;
+	struct scsi_sgl_params sgl_params;
+	u8 reserved1[12];
 	union fcoe_tx_info_union_ctx tx_info_union;
 	union fcoe_dix_desc_ctx dix_desc;
-	union fcoe_data_desc_ctx data_desc;
+	struct scsi_cached_sges data_desc;
 	__le16 ox_id;
 	__le16 rx_id;
 	__le32 task_rety_identifier;
-	__le32 reserved1[2];
+	u8 reserved2[8];
 };
 
 struct ystorm_fcoe_task_ag_ctx {
@@ -484,22 +411,22 @@ struct tstorm_fcoe_task_ag_ctx {
 struct fcoe_tstorm_fcoe_task_st_ctx_read_write {
 	union fcoe_cleanup_addr_exp_ro_union cleanup_addr_exp_ro_union;
 	__le16 flags;
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK       0x7
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK       0x1
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_SHIFT      0
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_MASK   0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT  3
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT  1
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_MASK        0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT       4
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT       2
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_MASK       0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT      5
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT      3
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_MASK  0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 6
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 4
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_MASK   0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT  7
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT  5
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_MASK        0x3
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT       8
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK             0x3F
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT            10
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT       6
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK             0xFF
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT            8
 	__le16 seq_cnt;
 	u8 seq_id;
 	u8 ooo_rx_seq_id;
@@ -582,8 +509,34 @@ struct mstorm_fcoe_task_ag_ctx {
 };
 
 struct mstorm_fcoe_task_st_ctx {
-	struct fcoe_mstorm_fcoe_task_st_ctx_non_fp non_fp;
-	struct fcoe_mstorm_fcoe_task_st_ctx_fp fp;
+	struct regpair rsp_buf_addr;
+	__le32 rsrv[2];
+	struct scsi_sgl_params sgl_params;
+	__le32 data_2_trns_rem;
+	__le32 data_buffer_offset;
+	__le16 parent_id;
+	__le16 flags;
+#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_MASK     0xF
+#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_SHIFT    0
+#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_MASK        0x3
+#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_SHIFT       4
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_MASK           0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_SHIFT          6
+#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_MASK  0x1
+#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_SHIFT 7
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_MASK        0x3
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_SHIFT       8
+#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_MASK  0x1
+#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_SHIFT 10
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_MASK    0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_SHIFT   11
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_MASK         0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_SHIFT        12
+#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK           0x1
+#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT          13
+#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_MASK              0x3
+#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_SHIFT             14
+	struct scsi_cached_sges data_desc;
 };
 
 struct ustorm_fcoe_task_ag_ctx {
@@ -646,6 +599,7 @@ struct ustorm_fcoe_task_ag_ctx {
 
 struct fcoe_task_context {
 	struct ystorm_fcoe_task_st_ctx ystorm_st_context;
+	struct regpair ystorm_st_padding[2];
 	struct tdif_task_context tdif_context;
 	struct ystorm_fcoe_task_ag_ctx ystorm_ag_context;
 	struct tstorm_fcoe_task_ag_ctx tstorm_ag_context;
@@ -668,20 +622,20 @@ struct fcoe_tx_stat {
 struct fcoe_wqe {
 	__le16 task_id;
 	__le16 flags;
-#define FCOE_WQE_REQ_TYPE_MASK        0xF
-#define FCOE_WQE_REQ_TYPE_SHIFT       0
-#define FCOE_WQE_SGL_MODE_MASK        0x7
-#define FCOE_WQE_SGL_MODE_SHIFT       4
-#define FCOE_WQE_CONTINUATION_MASK    0x1
-#define FCOE_WQE_CONTINUATION_SHIFT   7
-#define FCOE_WQE_INVALIDATE_PTU_MASK  0x1
-#define FCOE_WQE_INVALIDATE_PTU_SHIFT 8
-#define FCOE_WQE_SUPER_IO_MASK        0x1
-#define FCOE_WQE_SUPER_IO_SHIFT       9
-#define FCOE_WQE_SEND_AUTO_RSP_MASK   0x1
-#define FCOE_WQE_SEND_AUTO_RSP_SHIFT  10
-#define FCOE_WQE_RESERVED0_MASK       0x1F
-#define FCOE_WQE_RESERVED0_SHIFT      11
+#define FCOE_WQE_REQ_TYPE_MASK       0xF
+#define FCOE_WQE_REQ_TYPE_SHIFT      0
+#define FCOE_WQE_SGL_MODE_MASK       0x1
+#define FCOE_WQE_SGL_MODE_SHIFT      4
+#define FCOE_WQE_CONTINUATION_MASK   0x1
+#define FCOE_WQE_CONTINUATION_SHIFT  5
+#define FCOE_WQE_SEND_AUTO_RSP_MASK  0x1
+#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 6
+#define FCOE_WQE_RESERVED_MASK       0x1
+#define FCOE_WQE_RESERVED_SHIFT      7
+#define FCOE_WQE_NUM_SGES_MASK       0xF
+#define FCOE_WQE_NUM_SGES_SHIFT      8
+#define FCOE_WQE_RESERVED1_MASK      0xF
+#define FCOE_WQE_RESERVED1_SHIFT     12
 	union fcoe_additional_info_union additional_info_union;
 };
 
diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h
index 4c5747babcf6..69949f8e354b 100644
--- a/include/linux/qed/iscsi_common.h
+++ b/include/linux/qed/iscsi_common.h
@@ -39,17 +39,9 @@
 /* iSCSI HSI constants */
 #define ISCSI_DEFAULT_MTU       (1500)
 
-/* Current iSCSI HSI version number composed of two fields (16 bit) */
-#define ISCSI_HSI_MAJOR_VERSION (0)
-#define ISCSI_HSI_MINOR_VERSION (0)
-
 /* KWQ (kernel work queue) layer codes */
 #define ISCSI_SLOW_PATH_LAYER_CODE   (6)
 
-/* CQE completion status */
-#define ISCSI_EQE_COMPLETION_SUCCESS (0x0)
-#define ISCSI_EQE_RST_CONN_RCVD (0x1)
-
 /* iSCSI parameter defaults */
 #define ISCSI_DEFAULT_HEADER_DIGEST         (0)
 #define ISCSI_DEFAULT_DATA_DIGEST           (0)
@@ -68,6 +60,10 @@
 #define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T   (1)
 #define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T   (0xff)
 
+#define ISCSI_AHS_CNTL_SIZE 4
+
+#define ISCSI_WQE_NUM_SGES_SLOWIO           (0xf)
+
 /* iSCSI reserved params */
 #define ISCSI_ITT_ALL_ONES	(0xffffffff)
 #define ISCSI_TTT_ALL_ONES	(0xffffffff)
@@ -173,19 +169,6 @@ struct iscsi_async_msg_hdr {
 	__le32 reserved7;
 };
 
-struct iscsi_sge {
-	struct regpair sge_addr;
-	__le16 sge_len;
-	__le16 reserved0;
-	__le32 reserved1;
-};
-
-struct iscsi_cached_sge_ctx {
-	struct iscsi_sge sge;
-	struct regpair reserved;
-	__le32 dsgl_curr_offset[2];
-};
-
 struct iscsi_cmd_hdr {
 	__le16 reserved1;
 	u8 flags_attr;
@@ -229,8 +212,13 @@ struct iscsi_common_hdr {
 #define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT  0
 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK  0xFF
 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24
-	__le32 lun_reserved[4];
-	__le32 data[6];
+	struct regpair lun_reserved;
+	__le32 itt;
+	__le32 ttt;
+	__le32 cmdstat_sn;
+	__le32 exp_statcmd_sn;
+	__le32 max_cmd_sn;
+	__le32 data[3];
 };
 
 struct iscsi_conn_offload_params {
@@ -246,8 +234,10 @@ struct iscsi_conn_offload_params {
 #define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0
 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK     0x1
 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT    1
-#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK       0x3F
-#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT      2
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK	0x1
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT	2
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK	0x1F
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT	3
 	u8 pbl_page_size_log;
 	u8 pbe_page_size_log;
 	u8 default_cq;
@@ -278,8 +268,12 @@ struct iscsi_conn_update_ramrod_params {
 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT    2
 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK  0x1
 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3
-#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK       0xF
-#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT      4
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_MASK  0x1
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_SHIFT 4
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_MASK  0x1
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_SHIFT 5
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK       0x3
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT      6
 	u8 reserved0[3];
 	__le32 max_seq_size;
 	__le32 max_send_pdu_length;
@@ -312,7 +306,7 @@ struct iscsi_ext_cdb_cmd_hdr {
 	__le32 expected_transfer_length;
 	__le32 cmd_sn;
 	__le32 exp_stat_sn;
-	struct iscsi_sge cdb_sge;
+	struct scsi_sge cdb_sge;
 };
 
 struct iscsi_login_req_hdr {
@@ -519,8 +513,8 @@ struct iscsi_logout_response_hdr {
 	__le32 exp_cmd_sn;
 	__le32 max_cmd_sn;
 	__le32 reserved4;
-	__le16 time2retain;
-	__le16 time2wait;
+	__le16 time_2_retain;
+	__le16 time_2_wait;
 	__le32 reserved5[1];
 };
 
@@ -602,7 +596,7 @@ struct iscsi_tmf_response_hdr {
 #define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24
 	struct regpair reserved0;
 	__le32 itt;
-	__le32 rtt;
+	__le32 reserved1;
 	__le32 stat_sn;
 	__le32 exp_cmd_sn;
 	__le32 max_cmd_sn;
@@ -641,7 +635,7 @@ struct iscsi_reject_hdr {
 #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK  0xFF
 #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24
 	struct regpair reserved0;
-	__le32 reserved1;
+	__le32 all_ones;
 	__le32 reserved2;
 	__le32 stat_sn;
 	__le32 exp_cmd_sn;
@@ -688,7 +682,9 @@ struct iscsi_cqe_solicited {
 	__le16 itid;
 	u8 task_type;
 	u8 fw_dbg_field;
-	__le32 reserved1[2];
+	u8 caused_conn_err;
+	u8 reserved0[3];
+	__le32 reserved1[1];
 	union iscsi_task_hdr iscsi_hdr;
 };
 
@@ -727,35 +723,6 @@ enum iscsi_cqe_unsolicited_type {
 	MAX_ISCSI_CQE_UNSOLICITED_TYPE
 };
 
-struct iscsi_virt_sgl_ctx {
-	struct regpair sgl_base;
-	struct regpair dsgl_base;
-	__le32 sgl_initial_offset;
-	__le32 dsgl_initial_offset;
-	__le32 dsgl_curr_offset[2];
-};
-
-struct iscsi_sgl_var_params {
-	u8 sgl_ptr;
-	u8 dsgl_ptr;
-	__le16 sge_offset;
-	__le16 dsge_offset;
-};
-
-struct iscsi_phys_sgl_ctx {
-	struct regpair sgl_base;
-	struct regpair dsgl_base;
-	u8 sgl_size;
-	u8 dsgl_size;
-	__le16 reserved;
-	struct iscsi_sgl_var_params var_params[2];
-};
-
-union iscsi_data_desc_ctx {
-	struct iscsi_virt_sgl_ctx virt_sgl;
-	struct iscsi_phys_sgl_ctx phys_sgl;
-	struct iscsi_cached_sge_ctx cached_sge;
-};
 
 struct iscsi_debug_modes {
 	u8 flags;
@@ -771,8 +738,10 @@ struct iscsi_debug_modes {
 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4
 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK              0x1
 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT             5
-#define ISCSI_DEBUG_MODES_RESERVED0_MASK                       0x3
-#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT                      6
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_MASK     0x1
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_SHIFT    6
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_MASK             0x1
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_SHIFT            7
 };
 
 struct iscsi_dif_flags {
@@ -806,7 +775,6 @@ enum iscsi_eqe_opcode {
 	ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2,
 	ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR,
 	ISCSI_EVENT_TYPE_TCP_CONN_ERROR,
-	ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES,
 	MAX_ISCSI_EQE_OPCODE
 };
 
@@ -856,31 +824,11 @@ enum iscsi_error_types {
 	ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX,
 	ISCSI_CONN_ERROR_SENSE_DATA_LENGTH,
 	ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR,
+	ISCSI_CONN_ERROR_INVALID_ITT,
 	ISCSI_ERROR_UNKNOWN,
 	MAX_ISCSI_ERROR_TYPES
 };
 
-struct iscsi_mflags {
-	u8 mflags;
-#define ISCSI_MFLAGS_SLOW_IO_MASK     0x1
-#define ISCSI_MFLAGS_SLOW_IO_SHIFT    0
-#define ISCSI_MFLAGS_SINGLE_SGE_MASK  0x1
-#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1
-#define ISCSI_MFLAGS_RESERVED_MASK    0x3F
-#define ISCSI_MFLAGS_RESERVED_SHIFT   2
-};
-
-struct iscsi_sgl {
-	struct regpair sgl_addr;
-	__le16 updated_sge_size;
-	__le16 updated_sge_offset;
-	__le32 byte_offset;
-};
-
-union iscsi_mstorm_sgl {
-	struct iscsi_sgl sgl_struct;
-	struct iscsi_sge single_sge;
-};
 
 enum iscsi_ramrod_cmd_id {
 	ISCSI_RAMROD_CMD_ID_UNUSED = 0,
@@ -896,10 +844,10 @@ enum iscsi_ramrod_cmd_id {
 
 struct iscsi_reg1 {
 	__le32 reg1_map;
-#define ISCSI_REG1_NUM_FAST_SGES_MASK  0x7
-#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0
-#define ISCSI_REG1_RESERVED1_MASK      0x1FFFFFFF
-#define ISCSI_REG1_RESERVED1_SHIFT     3
+#define ISCSI_REG1_NUM_SGES_MASK   0xF
+#define ISCSI_REG1_NUM_SGES_SHIFT  0
+#define ISCSI_REG1_RESERVED1_MASK  0xFFFFFFF
+#define ISCSI_REG1_RESERVED1_SHIFT 4
 };
 
 union iscsi_seq_num {
@@ -967,22 +915,33 @@ struct iscsi_spe_func_init {
 };
 
 struct ystorm_iscsi_task_state {
-	union iscsi_data_desc_ctx sgl_ctx_union;
-	__le32 buffer_offset[2];
-	__le16 bytes_nxt_dif;
-	__le16 rxmit_bytes_nxt_dif;
-	union iscsi_seq_num seq_num_union;
-	u8 dif_bytes_leftover;
-	u8 rxmit_dif_bytes_leftover;
-	__le16 reuse_count;
-	struct iscsi_dif_flags dif_flags;
-	u8 local_comp;
+	struct scsi_cached_sges data_desc;
+	struct scsi_sgl_params sgl_params;
 	__le32 exp_r2t_sn;
-	__le32 sgl_offset[2];
+	__le32 buffer_offset;
+	union iscsi_seq_num seq_num;
+	struct iscsi_dif_flags dif_flags;
+	u8 flags;
+#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_MASK  0x1
+#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_SHIFT 0
+#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_MASK     0x1
+#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_SHIFT    1
+#define YSTORM_ISCSI_TASK_STATE_RESERVED0_MASK   0x3F
+#define YSTORM_ISCSI_TASK_STATE_RESERVED0_SHIFT  2
+};
+
+struct ystorm_iscsi_task_rxmit_opt {
+	__le32 fast_rxmit_sge_offset;
+	__le32 scan_start_buffer_offset;
+	__le32 fast_rxmit_buffer_offset;
+	u8 scan_start_sgl_index;
+	u8 fast_rxmit_sgl_index;
+	__le16 reserved;
 };
 
 struct ystorm_iscsi_task_st_ctx {
 	struct ystorm_iscsi_task_state state;
+	struct ystorm_iscsi_task_rxmit_opt rxmit_opt;
 	union iscsi_task_hdr pdu_hdr;
 };
 
@@ -1152,25 +1111,16 @@ struct ustorm_iscsi_task_ag_ctx {
 };
 
 struct mstorm_iscsi_task_st_ctx {
-	union iscsi_mstorm_sgl sgl_union;
-	struct iscsi_dif_flags dif_flags;
-	struct iscsi_mflags flags;
-	u8 sgl_size;
-	u8 host_sge_index;
-	__le16 dix_cur_sge_offset;
-	__le16 dix_cur_sge_size;
-	__le32 data_offset_rtid;
-	u8 dif_offset;
-	u8 dix_sgl_size;
-	u8 dix_sge_index;
+	struct scsi_cached_sges data_desc;
+	struct scsi_sgl_params sgl_params;
+	__le32 rem_task_size;
+	__le32 data_buffer_offset;
 	u8 task_type;
+	struct iscsi_dif_flags dif_flags;
+	u8 reserved0[2];
 	struct regpair sense_db;
-	struct regpair dix_sgl_cur_sge;
-	__le32 rem_task_size;
-	__le16 reuse_count;
-	__le16 dif_data_residue;
-	u8 reserved0[4];
-	__le32 reserved1[1];
+	__le32 expected_itt;
+	__le32 reserved1;
 };
 
 struct ustorm_iscsi_task_st_ctx {
@@ -1184,7 +1134,7 @@ struct ustorm_iscsi_task_st_ctx {
 #define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT            0
 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK             0x7F
 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT            1
-	u8 reserved2;
+	struct iscsi_dif_flags dif_flags;
 	__le16 reserved3;
 	__le32 reserved4;
 	__le32 reserved5;
@@ -1207,10 +1157,10 @@ struct ustorm_iscsi_task_st_ctx {
 #define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT           2
 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK        0x1
 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT       3
-#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK   0x1
-#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT  4
-#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK        0x1
-#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT       5
+#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK  0x1
+#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4
+#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_MASK        0x1
+#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT       5
 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK         0x1
 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT        6
 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK             0x1
@@ -1220,7 +1170,6 @@ struct ustorm_iscsi_task_st_ctx {
 
 struct iscsi_task_context {
 	struct ystorm_iscsi_task_st_ctx ystorm_st_context;
-	struct regpair ystorm_st_padding[2];
 	struct ystorm_iscsi_task_ag_ctx ystorm_ag_context;
 	struct regpair ystorm_ag_padding[2];
 	struct tdif_task_context tdif_context;
@@ -1272,32 +1221,22 @@ struct iscsi_uhqe {
 #define ISCSI_UHQE_TASK_ID_LO_SHIFT         24
 };
 
-struct iscsi_wqe_field {
-	__le32 contlen_cdbsize_field;
-#define ISCSI_WQE_FIELD_CONT_LEN_MASK  0xFFFFFF
-#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0
-#define ISCSI_WQE_FIELD_CDB_SIZE_MASK  0xFF
-#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24
-};
-
-union iscsi_wqe_field_union {
-	struct iscsi_wqe_field cont_field;
-	__le32 prev_tid;
-};
 
 struct iscsi_wqe {
 	__le16 task_id;
 	u8 flags;
 #define ISCSI_WQE_WQE_TYPE_MASK        0x7
 #define ISCSI_WQE_WQE_TYPE_SHIFT       0
-#define ISCSI_WQE_NUM_FAST_SGES_MASK   0x7
-#define ISCSI_WQE_NUM_FAST_SGES_SHIFT  3
-#define ISCSI_WQE_PTU_INVALIDATE_MASK  0x1
-#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6
+#define ISCSI_WQE_NUM_SGES_MASK  0xF
+#define ISCSI_WQE_NUM_SGES_SHIFT 3
 #define ISCSI_WQE_RESPONSE_MASK        0x1
 #define ISCSI_WQE_RESPONSE_SHIFT       7
 	struct iscsi_dif_flags prot_flags;
-	union iscsi_wqe_field_union cont_prevtid_union;
+	__le32 contlen_cdbsize;
+#define ISCSI_WQE_CONT_LEN_MASK  0xFFFFFF
+#define ISCSI_WQE_CONT_LEN_SHIFT 0
+#define ISCSI_WQE_CDB_SIZE_MASK  0xFF
+#define ISCSI_WQE_CDB_SIZE_SHIFT 24
 };
 
 enum iscsi_wqe_type {
@@ -1318,17 +1257,15 @@ struct iscsi_xhqe {
 	u8 total_ahs_length;
 	u8 opcode;
 	u8 flags;
-#define ISCSI_XHQE_NUM_FAST_SGES_MASK  0x7
-#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0
-#define ISCSI_XHQE_FINAL_MASK          0x1
-#define ISCSI_XHQE_FINAL_SHIFT         3
-#define ISCSI_XHQE_SUPER_IO_MASK       0x1
-#define ISCSI_XHQE_SUPER_IO_SHIFT      4
-#define ISCSI_XHQE_STATUS_BIT_MASK     0x1
-#define ISCSI_XHQE_STATUS_BIT_SHIFT    5
-#define ISCSI_XHQE_RESERVED_MASK       0x3
-#define ISCSI_XHQE_RESERVED_SHIFT      6
-	union iscsi_seq_num seq_num_union;
+#define ISCSI_XHQE_FINAL_MASK       0x1
+#define ISCSI_XHQE_FINAL_SHIFT      0
+#define ISCSI_XHQE_STATUS_BIT_MASK  0x1
+#define ISCSI_XHQE_STATUS_BIT_SHIFT 1
+#define ISCSI_XHQE_NUM_SGES_MASK    0xF
+#define ISCSI_XHQE_NUM_SGES_SHIFT   2
+#define ISCSI_XHQE_RESERVED0_MASK   0x3
+#define ISCSI_XHQE_RESERVED0_SHIFT  6
+	union iscsi_seq_num seq_num;
 	__le16 reserved1;
 };
 
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 4cd1f0ccfa36..d66d16a559e1 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -158,15 +158,27 @@ struct qed_tunn_params {
 struct qed_eth_cb_ops {
 	struct qed_common_cb_ops common;
 	void (*force_mac) (void *dev, u8 *mac, bool forced);
+	void (*ports_update)(void *dev, u16 vxlan_port, u16 geneve_port);
 };
 
 #define QED_MAX_PHC_DRIFT_PPB   291666666
 
 enum qed_ptp_filter_type {
-	QED_PTP_FILTER_L2,
-	QED_PTP_FILTER_IPV4,
-	QED_PTP_FILTER_IPV4_IPV6,
-	QED_PTP_FILTER_L2_IPV4_IPV6
+	QED_PTP_FILTER_NONE,
+	QED_PTP_FILTER_ALL,
+	QED_PTP_FILTER_V1_L4_EVENT,
+	QED_PTP_FILTER_V1_L4_GEN,
+	QED_PTP_FILTER_V2_L4_EVENT,
+	QED_PTP_FILTER_V2_L4_GEN,
+	QED_PTP_FILTER_V2_L2_EVENT,
+	QED_PTP_FILTER_V2_L2_GEN,
+	QED_PTP_FILTER_V2_EVENT,
+	QED_PTP_FILTER_V2_GEN
+};
+
+enum qed_ptp_hwtstamp_tx_type {
+	QED_PTP_HWTSTAMP_TX_OFF,
+	QED_PTP_HWTSTAMP_TX_ON,
 };
 
 #ifdef CONFIG_DCB
@@ -229,8 +241,8 @@ struct qed_eth_dcbnl_ops {
 #endif
 
 struct qed_eth_ptp_ops {
-	int (*hwtstamp_tx_on)(struct qed_dev *);
-	int (*cfg_rx_filters)(struct qed_dev *, enum qed_ptp_filter_type);
+	int (*cfg_filters)(struct qed_dev *, enum qed_ptp_filter_type,
+			   enum qed_ptp_hwtstamp_tx_type);
 	int (*read_rx_ts)(struct qed_dev *, u64 *);
 	int (*read_tx_ts)(struct qed_dev *, u64 *);
 	int (*read_cc)(struct qed_dev *, u64 *);
@@ -301,6 +313,14 @@ struct qed_eth_ops {
 
 	int (*tunn_config)(struct qed_dev *cdev,
 			   struct qed_tunn_params *params);
+
+	int (*ntuple_filter_config)(struct qed_dev *cdev, void *cookie,
+				    dma_addr_t mapping, u16 length,
+				    u16 vport_id, u16 rx_queue_id,
+				    bool add_filter);
+
+	int (*configure_arfs_searcher)(struct qed_dev *cdev,
+				       bool en_searcher);
 };
 
 const struct qed_eth_ops *qed_get_eth_ops(void);
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index fde56c436f71..5544d7b2f2bb 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -144,6 +144,7 @@ struct qed_dcbx_operational_params {
 	bool enabled;
 	bool ieee;
 	bool cee;
+	bool local;
 	u32 err;
 };
 
@@ -178,6 +179,12 @@ struct qed_eth_pf_params {
 	 * to update_pf_params routine invoked before slowpath start
 	 */
 	u16 num_cons;
+
+	/* To enable arfs, previous to HW-init a positive number needs to be
+	 * set [as filters require allocated searcher ILT memory].
+	 * This will set the maximal number of configured steering-filters.
+	 */
+	u32 num_arfs_filters;
 };
 
 struct qed_fcoe_pf_params {
@@ -263,7 +270,6 @@ struct qed_rdma_pf_params {
 	 * the doorbell BAR).
 	 */
 	u32 min_dpis;		/* number of requested DPIs */
-	u32 num_mrs;		/* number of requested memory regions */
 	u32 num_qps;		/* number of requested Queue Pairs */
 	u32 num_srqs;		/* number of requested SRQ */
 	u8 roce_edpm_mode;	/* see QED_ROCE_EDPM_MODE_ENABLE */
@@ -300,6 +306,11 @@ struct qed_sb_info {
 	struct qed_dev		*cdev;
 };
 
+enum qed_dev_type {
+	QED_DEV_TYPE_BB,
+	QED_DEV_TYPE_AH,
+};
+
 struct qed_dev_info {
 	unsigned long	pci_mem_start;
 	unsigned long	pci_mem_end;
@@ -325,6 +336,13 @@ struct qed_dev_info {
 	u16		mtu;
 
 	bool wol_support;
+
+	enum qed_dev_type dev_type;
+
+	/* Output parameters for qede */
+	bool		vxlan_enable;
+	bool		gre_enable;
+	bool		geneve_enable;
 };
 
 enum qed_sb_type {
@@ -421,6 +439,7 @@ struct qed_int_info {
 };
 
 struct qed_common_cb_ops {
+	void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc);
 	void	(*link_update)(void			*dev,
 			       struct qed_link_output	*link);
 	void	(*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type);
@@ -752,7 +771,7 @@ enum qed_mf_mode {
 	QED_MF_NPAR,
 };
 
-struct qed_eth_stats {
+struct qed_eth_stats_common {
 	u64	no_buff_discards;
 	u64	packet_too_big_discard;
 	u64	ttl0_discard;
@@ -784,11 +803,6 @@ struct qed_eth_stats {
 	u64	rx_256_to_511_byte_packets;
 	u64	rx_512_to_1023_byte_packets;
 	u64	rx_1024_to_1518_byte_packets;
-	u64	rx_1519_to_1522_byte_packets;
-	u64	rx_1519_to_2047_byte_packets;
-	u64	rx_2048_to_4095_byte_packets;
-	u64	rx_4096_to_9216_byte_packets;
-	u64	rx_9217_to_16383_byte_packets;
 	u64	rx_crc_errors;
 	u64	rx_mac_crtl_frames;
 	u64	rx_pause_frames;
@@ -805,14 +819,8 @@ struct qed_eth_stats {
 	u64	tx_256_to_511_byte_packets;
 	u64	tx_512_to_1023_byte_packets;
 	u64	tx_1024_to_1518_byte_packets;
-	u64	tx_1519_to_2047_byte_packets;
-	u64	tx_2048_to_4095_byte_packets;
-	u64	tx_4096_to_9216_byte_packets;
-	u64	tx_9217_to_16383_byte_packets;
 	u64	tx_pause_frames;
 	u64	tx_pfc_frames;
-	u64	tx_lpi_entry_count;
-	u64	tx_total_collisions;
 	u64	brb_truncates;
 	u64	brb_discards;
 	u64	rx_mac_bytes;
@@ -827,6 +835,34 @@ struct qed_eth_stats {
 	u64	tx_mac_ctrl_frames;
 };
 
+struct qed_eth_stats_bb {
+	u64 rx_1519_to_1522_byte_packets;
+	u64 rx_1519_to_2047_byte_packets;
+	u64 rx_2048_to_4095_byte_packets;
+	u64 rx_4096_to_9216_byte_packets;
+	u64 rx_9217_to_16383_byte_packets;
+	u64 tx_1519_to_2047_byte_packets;
+	u64 tx_2048_to_4095_byte_packets;
+	u64 tx_4096_to_9216_byte_packets;
+	u64 tx_9217_to_16383_byte_packets;
+	u64 tx_lpi_entry_count;
+	u64 tx_total_collisions;
+};
+
+struct qed_eth_stats_ah {
+	u64 rx_1519_to_max_byte_packets;
+	u64 tx_1519_to_max_byte_packets;
+};
+
+struct qed_eth_stats {
+	struct qed_eth_stats_common common;
+
+	union {
+		struct qed_eth_stats_bb bb;
+		struct qed_eth_stats_ah ah;
+	};
+};
+
 #define QED_SB_IDX              0x0002
 
 #define RX_PI           0
diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h
index f70bb81b8b6a..3414649133d2 100644
--- a/include/linux/qed/qed_iscsi_if.h
+++ b/include/linux/qed/qed_iscsi_if.h
@@ -67,6 +67,8 @@ struct qed_dev_iscsi_info {
 
 	void __iomem *primary_dbq_rq_addr;
 	void __iomem *secondary_bdq_rq_addr;
+
+	u8 num_cqs;
 };
 
 struct qed_iscsi_id_params {
diff --git a/include/linux/qed/qed_roce_if.h b/include/linux/qed/qed_roce_if.h
index f742d4312c9d..cbb2ff0ce4bc 100644
--- a/include/linux/qed/qed_roce_if.h
+++ b/include/linux/qed/qed_roce_if.h
@@ -240,6 +240,7 @@ struct qed_rdma_add_user_out_params {
 	u64 dpi_addr;
 	u64 dpi_phys_addr;
 	u32 dpi_size;
+	u16 wid_count;
 };
 
 enum roce_mode {
@@ -533,6 +534,7 @@ enum qed_rdma_type {
 struct qed_dev_rdma_info {
 	struct qed_dev_info common;
 	enum qed_rdma_type rdma_type;
+	u8 user_dpm_enabled;
 };
 
 struct qed_rdma_ops {
diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h
index f773aa5e746f..72c770f9f666 100644
--- a/include/linux/qed/rdma_common.h
+++ b/include/linux/qed/rdma_common.h
@@ -52,7 +52,8 @@
 #define RDMA_MAX_PDS                            (64 * 1024)
 
 #define RDMA_NUM_STATISTIC_COUNTERS                     MAX_NUM_VPORTS
-#define RDMA_NUM_STATISTIC_COUNTERS_BB			MAX_NUM_VPORTS_BB
+#define RDMA_NUM_STATISTIC_COUNTERS_K2                  MAX_NUM_VPORTS_K2
+#define RDMA_NUM_STATISTIC_COUNTERS_BB                  MAX_NUM_VPORTS_BB
 
 #define RDMA_TASK_TYPE (PROTOCOLID_ROCE)
 
diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h
index bad02df213df..866f063026de 100644
--- a/include/linux/qed/roce_common.h
+++ b/include/linux/qed/roce_common.h
@@ -38,4 +38,21 @@
 
 #define ROCE_MAX_QPS	(32 * 1024)
 
+enum roce_async_events_type {
+	ROCE_ASYNC_EVENT_NONE = 0,
+	ROCE_ASYNC_EVENT_COMM_EST = 1,
+	ROCE_ASYNC_EVENT_SQ_DRAINED,
+	ROCE_ASYNC_EVENT_SRQ_LIMIT,
+	ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
+	ROCE_ASYNC_EVENT_CQ_ERR,
+	ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
+	ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
+	ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
+	ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
+	ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
+	ROCE_ASYNC_EVENT_SRQ_EMPTY,
+	ROCE_ASYNC_EVENT_DESTROY_QP_DONE,
+	MAX_ROCE_ASYNC_EVENTS_TYPE
+};
+
 #endif /* __ROCE_COMMON__ */
diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h
index 03f3e37ab059..08df82a096b6 100644
--- a/include/linux/qed/storage_common.h
+++ b/include/linux/qed/storage_common.h
@@ -40,6 +40,8 @@
 #define BDQ_ID_IMM_DATA          (1)
 #define BDQ_NUM_IDS          (2)
 
+#define SCSI_NUM_SGES_SLOW_SGL_THR      8
+
 #define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15)
 
 struct scsi_bd {
@@ -52,6 +54,16 @@ struct scsi_bdq_ram_drv_data {
 	__le16 reserved0[3];
 };
 
+struct scsi_sge {
+	struct regpair sge_addr;
+	__le32 sge_len;
+	__le32 reserved;
+};
+
+struct scsi_cached_sges {
+	struct scsi_sge sge[4];
+};
+
 struct scsi_drv_cmdq {
 	__le16 cmdq_cons;
 	__le16 reserved0;
@@ -99,11 +111,19 @@ struct scsi_ram_per_bdq_resource_drv_data {
 	struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS];
 };
 
-struct scsi_sge {
-	struct regpair sge_addr;
-	__le16 sge_len;
-	__le16 reserved0;
-	__le32 reserved1;
+enum scsi_sgl_mode {
+	SCSI_TX_SLOW_SGL,
+	SCSI_FAST_SGL,
+	MAX_SCSI_SGL_MODE
+};
+
+struct scsi_sgl_params {
+	struct regpair sgl_addr;
+	__le32 sgl_total_length;
+	__le32 sge_offset;
+	__le16 sgl_num_sges;
+	u8 sgl_index;
+	u8 reserved;
 };
 
 struct scsi_terminate_extra_params {
diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h
index 46fe7856f1b2..a5e843268f0e 100644
--- a/include/linux/qed/tcp_common.h
+++ b/include/linux/qed/tcp_common.h
@@ -173,6 +173,7 @@ enum tcp_seg_placement_event {
 	TCP_EVENT_ADD_ISLE_RIGHT,
 	TCP_EVENT_ADD_ISLE_LEFT,
 	TCP_EVENT_JOIN,
+	TCP_EVENT_DELETE_ISLES,
 	TCP_EVENT_NOP,
 	MAX_TCP_SEG_PLACEMENT_EVENT
 };
diff --git a/include/linux/random.h b/include/linux/random.h
index 7bd2403e4fef..ed5c3838780d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -37,14 +37,26 @@ extern void get_random_bytes(void *buf, int nbytes);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
 extern void del_random_ready_callback(struct random_ready_callback *rdy);
 extern void get_random_bytes_arch(void *buf, int nbytes);
-extern int random_int_secret_init(void);
 
 #ifndef MODULE
 extern const struct file_operations random_fops, urandom_fops;
 #endif
 
-unsigned int get_random_int(void);
-unsigned long get_random_long(void);
+u32 get_random_u32(void);
+u64 get_random_u64(void);
+static inline unsigned int get_random_int(void)
+{
+	return get_random_u32();
+}
+static inline unsigned long get_random_long(void)
+{
+#if BITS_PER_LONG == 64
+	return get_random_u64();
+#else
+	return get_random_u32();
+#endif
+}
+
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
 u32 prandom_u32(void);
diff --git a/include/linux/ras.h b/include/linux/ras.h
index 2aceeafd6fe5..ffb147185e8d 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -1,14 +1,25 @@
 #ifndef __RAS_H__
 #define __RAS_H__
 
+#include <asm/errno.h>
+
 #ifdef CONFIG_DEBUG_FS
 int ras_userspace_consumers(void);
 void ras_debugfs_init(void);
 int ras_add_daemon_trace(void);
 #else
 static inline int ras_userspace_consumers(void) { return 0; }
-static inline void ras_debugfs_init(void) { return; }
+static inline void ras_debugfs_init(void) { }
 static inline int ras_add_daemon_trace(void) { return 0; }
 #endif
 
+#ifdef CONFIG_RAS_CEC
+void __init cec_init(void);
+int __init parse_cec_param(char *str);
+int cec_add_elem(u64 pfn);
+#else
+static inline void __init cec_init(void)	{ }
+static inline int cec_add_elem(u64 pfn)		{ return -ENODEV; }
 #endif
+
+#endif /* __RAS_H__ */
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 4ae95f7e8597..a23a33153180 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -156,5 +156,19 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
 		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
 		pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
 
+/**
+ * hlist_nulls_for_each_entry_safe -
+ *   iterate over list of given type safe against removal of list entry
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_nulls_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_nulls_node within the struct.
+ */
+#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member)		\
+	for (({barrier();}),							\
+	     pos = rcu_dereference_raw(hlist_nulls_first_rcu(head));		\
+		(!is_a_nulls(pos)) &&						\
+		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member);	\
+		   pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });)
 #endif
 #endif
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 0023fee4bbbc..b34aa649d204 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -6,17 +6,36 @@
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
 
+/**
+ * refcount_t - variant of atomic_t specialized for reference counts
+ * @refs: atomic_t counter field
+ *
+ * The counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free bugs.
+ */
 typedef struct refcount_struct {
 	atomic_t refs;
 } refcount_t;
 
 #define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
 
+/**
+ * refcount_set - set a refcount's value
+ * @r: the refcount
+ * @n: value to which the refcount will be set
+ */
 static inline void refcount_set(refcount_t *r, unsigned int n)
 {
 	atomic_set(&r->refs, n);
 }
 
+/**
+ * refcount_read - get a refcount's value
+ * @r: the refcount
+ *
+ * Return: the refcount's value
+ */
 static inline unsigned int refcount_read(const refcount_t *r)
 {
 	return atomic_read(&r->refs);
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index ad3e5158e586..c9f795e9a2ee 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -65,7 +65,7 @@ struct regulator_state {
 	int uV;	/* suspend voltage */
 	unsigned int mode; /* suspend regulator operating mode */
 	int enabled; /* is regulator enabled in this suspend state */
-	int disabled; /* is the regulator disbled in this suspend state */
+	int disabled; /* is the regulator disabled in this suspend state */
 };
 
 /**
diff --git a/include/linux/reset.h b/include/linux/reset.h
index 86b4ed75359e..13d8681210d5 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -15,6 +15,9 @@ int reset_control_status(struct reset_control *rstc);
 struct reset_control *__of_reset_control_get(struct device_node *node,
 				     const char *id, int index, bool shared,
 				     bool optional);
+struct reset_control *__reset_control_get(struct device *dev, const char *id,
+					  int index, bool shared,
+					  bool optional);
 void reset_control_put(struct reset_control *rstc);
 struct reset_control *__devm_reset_control_get(struct device *dev,
 				     const char *id, int index, bool shared,
@@ -31,31 +34,26 @@ static inline int device_reset_optional(struct device *dev)
 
 static inline int reset_control_reset(struct reset_control *rstc)
 {
-	WARN_ON(1);
 	return 0;
 }
 
 static inline int reset_control_assert(struct reset_control *rstc)
 {
-	WARN_ON(1);
 	return 0;
 }
 
 static inline int reset_control_deassert(struct reset_control *rstc)
 {
-	WARN_ON(1);
 	return 0;
 }
 
 static inline int reset_control_status(struct reset_control *rstc)
 {
-	WARN_ON(1);
 	return 0;
 }
 
 static inline void reset_control_put(struct reset_control *rstc)
 {
-	WARN_ON(1);
 }
 
 static inline int __must_check device_reset(struct device *dev)
@@ -74,14 +72,21 @@ static inline struct reset_control *__of_reset_control_get(
 					const char *id, int index, bool shared,
 					bool optional)
 {
-	return ERR_PTR(-ENOTSUPP);
+	return optional ? NULL : ERR_PTR(-ENOTSUPP);
+}
+
+static inline struct reset_control *__reset_control_get(
+					struct device *dev, const char *id,
+					int index, bool shared, bool optional)
+{
+	return optional ? NULL : ERR_PTR(-ENOTSUPP);
 }
 
 static inline struct reset_control *__devm_reset_control_get(
 					struct device *dev, const char *id,
 					int index, bool shared, bool optional)
 {
-	return ERR_PTR(-ENOTSUPP);
+	return optional ? NULL : ERR_PTR(-ENOTSUPP);
 }
 
 #endif /* CONFIG_RESET_CONTROLLER */
@@ -107,8 +112,7 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id)
 #ifndef CONFIG_RESET_CONTROLLER
 	WARN_ON(1);
 #endif
-	return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, false,
-									false);
+	return __reset_control_get(dev, id, 0, false, false);
 }
 
 /**
@@ -136,22 +140,19 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id)
 static inline struct reset_control *reset_control_get_shared(
 					struct device *dev, const char *id)
 {
-	return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, true,
-									false);
+	return __reset_control_get(dev, id, 0, true, false);
 }
 
 static inline struct reset_control *reset_control_get_optional_exclusive(
 					struct device *dev, const char *id)
 {
-	return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, false,
-									true);
+	return __reset_control_get(dev, id, 0, false, true);
 }
 
 static inline struct reset_control *reset_control_get_optional_shared(
 					struct device *dev, const char *id)
 {
-	return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, true,
-									true);
+	return __reset_control_get(dev, id, 0, true, true);
 }
 
 /**
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 092292b6675e..7d56a7ea2b2e 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -49,6 +49,21 @@
 /* Base bits plus 1 bit for nulls marker */
 #define RHT_HASH_RESERVED_SPACE	(RHT_BASE_BITS + 1)
 
+/* Maximum chain length before rehash
+ *
+ * The maximum (not average) chain length grows with the size of the hash
+ * table, at a rate of (log N)/(log log N).
+ *
+ * The value of 16 is selected so that even if the hash table grew to
+ * 2^32 you would not expect the maximum chain length to exceed it
+ * unless we are under attack (or extremely unlucky).
+ *
+ * As this limit is only to detect attacks, we don't need to set it to a
+ * lower value as you'd need the chain length to vastly exceed 16 to have
+ * any real effect on the system.
+ */
+#define RHT_ELASTICITY	16u
+
 struct rhash_head {
 	struct rhash_head __rcu		*next;
 };
@@ -110,29 +125,25 @@ struct rhashtable;
  * @key_len: Length of key
  * @key_offset: Offset of key in struct to be hashed
  * @head_offset: Offset of rhash_head in struct to be hashed
- * @insecure_max_entries: Maximum number of entries (may be exceeded)
  * @max_size: Maximum size while expanding
  * @min_size: Minimum size while shrinking
- * @nulls_base: Base value to generate nulls marker
- * @insecure_elasticity: Set to true to disable chain length checks
- * @automatic_shrinking: Enable automatic shrinking of tables
  * @locks_mul: Number of bucket locks to allocate per cpu (default: 128)
+ * @automatic_shrinking: Enable automatic shrinking of tables
+ * @nulls_base: Base value to generate nulls marker
  * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
  * @obj_hashfn: Function to hash object
  * @obj_cmpfn: Function to compare key with object
  */
 struct rhashtable_params {
-	size_t			nelem_hint;
-	size_t			key_len;
-	size_t			key_offset;
-	size_t			head_offset;
-	unsigned int		insecure_max_entries;
+	u16			nelem_hint;
+	u16			key_len;
+	u16			key_offset;
+	u16			head_offset;
 	unsigned int		max_size;
-	unsigned int		min_size;
-	u32			nulls_base;
-	bool			insecure_elasticity;
+	u16			min_size;
 	bool			automatic_shrinking;
-	size_t			locks_mul;
+	u8			locks_mul;
+	u32			nulls_base;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
 	rht_obj_cmpfn_t		obj_cmpfn;
@@ -143,8 +154,8 @@ struct rhashtable_params {
  * @tbl: Bucket table
  * @nelems: Number of elements in table
  * @key_len: Key length for hashfn
- * @elasticity: Maximum chain length before rehash
  * @p: Configuration parameters
+ * @max_elems: Maximum number of elements in table
  * @rhlist: True if this is an rhltable
  * @run_work: Deferred worker to expand/shrink asynchronously
  * @mutex: Mutex to protect current/future table swapping
@@ -154,8 +165,8 @@ struct rhashtable {
 	struct bucket_table __rcu	*tbl;
 	atomic_t			nelems;
 	unsigned int			key_len;
-	unsigned int			elasticity;
 	struct rhashtable_params	p;
+	unsigned int			max_elems;
 	bool				rhlist;
 	struct work_struct		run_work;
 	struct mutex                    mutex;
@@ -318,8 +329,7 @@ static inline bool rht_grow_above_100(const struct rhashtable *ht,
 static inline bool rht_grow_above_max(const struct rhashtable *ht,
 				      const struct bucket_table *tbl)
 {
-	return ht->p.insecure_max_entries &&
-	       atomic_read(&ht->nelems) >= ht->p.insecure_max_entries;
+	return atomic_read(&ht->nelems) >= ht->max_elems;
 }
 
 /* The bucket lock is selected based on the hash and protects mutations
@@ -726,7 +736,7 @@ slow_path:
 		return rhashtable_insert_slow(ht, key, obj);
 	}
 
-	elasticity = ht->elasticity;
+	elasticity = RHT_ELASTICITY;
 	pprev = rht_bucket_insert(ht, tbl, hash);
 	data = ERR_PTR(-ENOMEM);
 	if (!pprev)
@@ -916,6 +926,28 @@ static inline int rhashtable_lookup_insert_fast(
 }
 
 /**
+ * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ * @params:	hash table parameters
+ *
+ * Just like rhashtable_lookup_insert_fast(), but this function returns the
+ * object if it exists, NULL if it did not and the insertion was successful,
+ * and an ERR_PTR otherwise.
+ */
+static inline void *rhashtable_lookup_get_insert_fast(
+	struct rhashtable *ht, struct rhash_head *obj,
+	const struct rhashtable_params params)
+{
+	const char *key = rht_obj(ht, obj);
+
+	BUG_ON(ht->p.obj_hashfn);
+
+	return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params,
+					false);
+}
+
+/**
  * rhashtable_lookup_insert_key - search and insert object to hash table
  *				  with explicit key
  * @ht:		hash table
diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h
index 8ec8b6439b25..f27917e0a101 100644
--- a/include/linux/rpmsg/qcom_smd.h
+++ b/include/linux/rpmsg/qcom_smd.h
@@ -6,7 +6,7 @@
 
 struct qcom_smd_edge;
 
-#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD) || IS_ENABLED(CONFIG_QCOM_SMD)
+#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD)
 
 struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
 					     struct device_node *node);
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index d4e0a204c118..a1904aadbc45 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -176,6 +176,25 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
 int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin);
 
 /**
+ * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
+ * limiting the depth used from each word.
+ * @sb: Bitmap to allocate from.
+ * @alloc_hint: Hint for where to start searching for a free bit.
+ * @shallow_depth: The maximum number of bits to allocate from a single word.
+ *
+ * This rather specific operation allows for having multiple users with
+ * different allocation limits. E.g., there can be a high-priority class that
+ * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
+ * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority
+ * class can only allocate half of the total bits in the bitmap, preventing it
+ * from starving out the high-priority class.
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
+			unsigned long shallow_depth);
+
+/**
  * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
  * @sb: Bitmap to check.
  *
@@ -326,6 +345,19 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
 int __sbitmap_queue_get(struct sbitmap_queue *sbq);
 
 /**
+ * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
+ * sbitmap_queue, limiting the depth used from each word, with preemption
+ * already disabled.
+ * @sbq: Bitmap queue to allocate from.
+ * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * See sbitmap_get_shallow().
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+				unsigned int shallow_depth);
+
+/**
  * sbitmap_queue_get() - Try to allocate a free bit from a &struct
  * sbitmap_queue.
  * @sbq: Bitmap queue to allocate from.
@@ -346,6 +378,29 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
 }
 
 /**
+ * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
+ * sbitmap_queue, limiting the depth used from each word.
+ * @sbq: Bitmap queue to allocate from.
+ * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
+ *       sbitmap_queue_clear()).
+ * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * See sbitmap_get_shallow().
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+					    unsigned int *cpu,
+					    unsigned int shallow_depth)
+{
+	int nr;
+
+	*cpu = get_cpu();
+	nr = __sbitmap_queue_get_shallow(sbq, shallow_depth);
+	put_cpu();
+	return nr;
+}
+
+/**
  * sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a
  * &struct sbitmap_queue.
  * @sbq: Bitmap to free from.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e11032010318..186dd6eae958 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -604,6 +604,10 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned			brk_randomized:1;
 #endif
+#ifdef CONFIG_CGROUPS
+	/* disallow userland-initiated cgroup migration */
+	unsigned			no_cgroup_migration:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -775,6 +779,8 @@ struct task_struct {
 	/* PI waiters blocked on a rt_mutex held by this task: */
 	struct rb_root			pi_waiters;
 	struct rb_node			*pi_waiters_leftmost;
+	/* Updated under owner's pi_lock and rq lock */
+	struct task_struct		*pi_top_task;
 	/* Deadlock detection and priority inheritance handling: */
 	struct rt_mutex_waiter		*pi_blocked_on;
 #endif
@@ -1289,10 +1295,10 @@ TASK_PFA_TEST(LMK_WAITING, lmk_waiting)
 TASK_PFA_SET(LMK_WAITING, lmk_waiting)
 
 static inline void
-tsk_restore_flags(struct task_struct *task, unsigned long orig_flags, unsigned long flags)
+current_restore_flags(unsigned long orig_flags, unsigned long flags)
 {
-	task->flags &= ~flags;
-	task->flags |= orig_flags & flags;
+	current->flags &= ~flags;
+	current->flags |= orig_flags & flags;
 }
 
 extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 4a68c6791207..34fe92ce1ebd 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -54,15 +54,16 @@ static inline u64 local_clock(void)
 }
 #else
 extern void sched_clock_init_late(void);
-/*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
- */
 extern int sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
+/*
+ * When sched_clock_stable(), __sched_clock_offset provides the offset
+ * between local_clock() and sched_clock().
+ */
+extern u64 __sched_clock_offset;
+
+
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 3bd668414f61..f93329aba31a 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -18,27 +18,20 @@ static inline int rt_task(struct task_struct *p)
 }
 
 #ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
-extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
+/*
+ * Must hold either p->pi_lock or task_rq(p)->lock.
+ */
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
+{
+	return p->pi_top_task;
+}
+extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
 {
 	return tsk->pi_blocked_on != NULL;
 }
 #else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
-	return p->normal_prio;
-}
-
-static inline int rt_mutex_get_effective_prio(struct task_struct *task,
-					      int newprio)
-{
-	return newprio;
-}
-
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index 9519da6253a8..37395b8eb8f1 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -15,6 +15,8 @@
 
 #include <linux/types.h>
 #include <linux/device.h>
+#include <linux/termios.h>
+#include <linux/delay.h>
 
 struct serdev_controller;
 struct serdev_device;
@@ -81,6 +83,9 @@ struct serdev_controller_ops {
 	void (*close)(struct serdev_controller *);
 	void (*set_flow_control)(struct serdev_controller *, bool);
 	unsigned int (*set_baudrate)(struct serdev_controller *, unsigned int);
+	void (*wait_until_sent)(struct serdev_controller *, long);
+	int (*get_tiocm)(struct serdev_controller *);
+	int (*set_tiocm)(struct serdev_controller *, unsigned int, unsigned int);
 };
 
 /**
@@ -186,6 +191,9 @@ int serdev_device_open(struct serdev_device *);
 void serdev_device_close(struct serdev_device *);
 unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int);
 void serdev_device_set_flow_control(struct serdev_device *, bool);
+void serdev_device_wait_until_sent(struct serdev_device *, long);
+int serdev_device_get_tiocm(struct serdev_device *);
+int serdev_device_set_tiocm(struct serdev_device *, int, int);
 int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t);
 void serdev_device_write_flush(struct serdev_device *);
 int serdev_device_write_room(struct serdev_device *);
@@ -223,6 +231,15 @@ static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev
 	return 0;
 }
 static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {}
+static inline void serdev_device_wait_until_sent(struct serdev_device *sdev, long timeout) {}
+static inline int serdev_device_get_tiocm(struct serdev_device *serdev)
+{
+	return -ENOTSUPP;
+}
+static inline int serdev_device_set_tiocm(struct serdev_device *serdev, int set, int clear)
+{
+	return -ENOTSUPP;
+}
 static inline int serdev_device_write_buf(struct serdev_device *sdev, const unsigned char *buf, size_t count)
 {
 	return -ENODEV;
@@ -238,6 +255,36 @@ static inline int serdev_device_write_room(struct serdev_device *sdev)
 
 #endif /* CONFIG_SERIAL_DEV_BUS */
 
+static inline bool serdev_device_get_cts(struct serdev_device *serdev)
+{
+	int status = serdev_device_get_tiocm(serdev);
+	return !!(status & TIOCM_CTS);
+}
+
+static inline int serdev_device_wait_for_cts(struct serdev_device *serdev, bool state, int timeout_ms)
+{
+	unsigned long timeout;
+	bool signal;
+
+	timeout = jiffies + msecs_to_jiffies(timeout_ms);
+	while (time_is_after_jiffies(timeout)) {
+		signal = serdev_device_get_cts(serdev);
+		if (signal == state)
+			return 0;
+		usleep_range(1000, 2000);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static inline int serdev_device_set_rts(struct serdev_device *serdev, bool enable)
+{
+	if (enable)
+		return serdev_device_set_tiocm(serdev, TIOCM_RTS, 0);
+	else
+		return serdev_device_set_tiocm(serdev, 0, TIOCM_RTS);
+}
+
 /*
  * serdev hooks into TTY core
  */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c776abd86937..a098d95b3d84 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -413,14 +413,15 @@ struct ubuf_info {
  * the end of the header data, ie. at skb->end.
  */
 struct skb_shared_info {
+	unsigned short	_unused;
 	unsigned char	nr_frags;
 	__u8		tx_flags;
 	unsigned short	gso_size;
 	/* Warning: this field is not always filled in (UFO)! */
 	unsigned short	gso_segs;
-	unsigned short  gso_type;
 	struct sk_buff	*frag_list;
 	struct skb_shared_hwtstamps hwtstamps;
+	unsigned int	gso_type;
 	u32		tskey;
 	__be32          ip6_frag_id;
 
@@ -491,6 +492,8 @@ enum {
 	SKB_GSO_TUNNEL_REMCSUM = 1 << 14,
 
 	SKB_GSO_SCTP = 1 << 15,
+
+	SKB_GSO_ESP = 1 << 16,
 };
 
 #if BITS_PER_LONG > 32
@@ -3113,7 +3116,7 @@ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
 
 static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
 {
-	return copy_from_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT;
+	return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT;
 }
 
 static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 8e0cb7a0f836..68123c1fe549 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -120,6 +120,13 @@ extern unsigned int setup_max_cpus;
 extern void __init setup_nr_cpu_ids(void);
 extern void __init smp_init(void);
 
+extern int __boot_cpu_id;
+
+static inline int get_boot_cpu_id(void)
+{
+	return __boot_cpu_id;
+}
+
 #else /* !SMP */
 
 static inline void smp_send_stop(void) { }
@@ -158,6 +165,11 @@ static inline void smp_init(void) { up_late_init(); }
 static inline void smp_init(void) { }
 #endif
 
+static inline int get_boot_cpu_id(void)
+{
+	return 0;
+}
+
 #endif /* !SMP */
 
 /*
diff --git a/include/linux/soc/qcom/smd.h b/include/linux/soc/qcom/smd.h
deleted file mode 100644
index f148e0ffbec7..000000000000
--- a/include/linux/soc/qcom/smd.h
+++ /dev/null
@@ -1,139 +0,0 @@
-#ifndef __QCOM_SMD_H__
-#define __QCOM_SMD_H__
-
-#include <linux/device.h>
-#include <linux/mod_devicetable.h>
-
-struct qcom_smd;
-struct qcom_smd_channel;
-struct qcom_smd_lookup;
-
-/**
- * struct qcom_smd_id - struct used for matching a smd device
- * @name:	name of the channel
- */
-struct qcom_smd_id {
-	char name[20];
-};
-
-/**
- * struct qcom_smd_device - smd device struct
- * @dev:	the device struct
- * @channel:	handle to the smd channel for this device
- */
-struct qcom_smd_device {
-	struct device dev;
-	struct qcom_smd_channel *channel;
-};
-
-typedef int (*qcom_smd_cb_t)(struct qcom_smd_channel *, const void *, size_t);
-
-/**
- * struct qcom_smd_driver - smd driver struct
- * @driver:	underlying device driver
- * @smd_match_table: static channel match table
- * @probe:	invoked when the smd channel is found
- * @remove:	invoked when the smd channel is closed
- * @callback:	invoked when an inbound message is received on the channel,
- *		should return 0 on success or -EBUSY if the data cannot be
- *		consumed at this time
- */
-struct qcom_smd_driver {
-	struct device_driver driver;
-	const struct qcom_smd_id *smd_match_table;
-
-	int (*probe)(struct qcom_smd_device *dev);
-	void (*remove)(struct qcom_smd_device *dev);
-	qcom_smd_cb_t callback;
-};
-
-#if IS_ENABLED(CONFIG_QCOM_SMD)
-
-int qcom_smd_driver_register(struct qcom_smd_driver *drv);
-void qcom_smd_driver_unregister(struct qcom_smd_driver *drv);
-
-struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *channel,
-					       const char *name,
-					       qcom_smd_cb_t cb);
-void qcom_smd_close_channel(struct qcom_smd_channel *channel);
-void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel);
-void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data);
-int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len);
-
-
-struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
-					     struct device_node *node);
-int qcom_smd_unregister_edge(struct qcom_smd_edge *edge);
-
-#else
-
-static inline int qcom_smd_driver_register(struct qcom_smd_driver *drv)
-{
-	return -ENXIO;
-}
-
-static inline void qcom_smd_driver_unregister(struct qcom_smd_driver *drv)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-}
-
-static inline struct qcom_smd_channel *
-qcom_smd_open_channel(struct qcom_smd_channel *channel,
-		      const char *name,
-		      qcom_smd_cb_t cb)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return NULL;
-}
-
-static inline void qcom_smd_close_channel(struct qcom_smd_channel *channel)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-}
-
-static inline void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return NULL;
-}
-
-static inline void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-}
-
-static inline int qcom_smd_send(struct qcom_smd_channel *channel,
-				const void *data, int len)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return -ENXIO;
-}
-
-static inline struct qcom_smd_edge *
-qcom_smd_register_edge(struct device *parent,
-		       struct device_node *node)
-{
-	return ERR_PTR(-ENXIO);
-}
-
-static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return -ENXIO;
-}
-
-#endif
-
-#define module_qcom_smd_driver(__smd_driver) \
-	module_driver(__smd_driver, qcom_smd_driver_register, \
-		      qcom_smd_driver_unregister)
-
-
-#endif
diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h
index eab64976a73b..a4dd4d7c711d 100644
--- a/include/linux/soc/qcom/wcnss_ctrl.h
+++ b/include/linux/soc/qcom/wcnss_ctrl.h
@@ -1,16 +1,19 @@
 #ifndef __WCNSS_CTRL_H__
 #define __WCNSS_CTRL_H__
 
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 
 #if IS_ENABLED(CONFIG_QCOM_WCNSS_CTRL)
 
-struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb);
+struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name,
+					       rpmsg_rx_cb_t cb, void *priv);
 
 #else
 
-static inline struct qcom_smd_channel*
-qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+static struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss,
+						      const char *name,
+						      rpmsg_rx_cb_t cb,
+						      void *priv)
 {
 	WARN_ON(1);
 	return ERR_PTR(-ENXIO);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index a0596ca0e80a..a2f8109bb215 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -24,6 +24,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
 void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 
+u64 sock_gen_cookie(struct sock *sk);
 int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
 void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
 
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 00a21166e268..db42746bdfea 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -20,6 +20,8 @@
 #define SPLICE_F_MORE	(0x04)	/* expect more data */
 #define SPLICE_F_GIFT	(0x08)	/* pages passed in are a gift */
 
+#define SPLICE_F_ALL (SPLICE_F_MOVE|SPLICE_F_NONBLOCK|SPLICE_F_MORE|SPLICE_F_GIFT)
+
 /*
  * Passed to the actors
  */
@@ -55,7 +57,6 @@ struct splice_pipe_desc {
 	struct partial_page *partial;	/* pages[] may not be contig */
 	int nr_pages;			/* number of populated pages in map */
 	unsigned int nr_pages_max;	/* pages[] & partial[] arrays size */
-	unsigned int flags;		/* splice flags */
 	const struct pipe_buf_operations *ops;/* ops associated with output pipe */
 	void (*spd_release)(struct splice_pipe_desc *, unsigned int);
 };
@@ -82,7 +83,6 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
  */
 extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *);
 extern void splice_shrink_spd(struct splice_pipe_desc *);
-extern void spd_release_page(struct splice_pipe_desc *, unsigned int);
 
 extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
 extern const struct pipe_buf_operations default_pipe_buf_ops;
diff --git a/include/linux/stat.h b/include/linux/stat.h
index c76e524fb34b..64b6b3aece21 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -26,6 +26,7 @@ struct kstat {
 	unsigned int	nlink;
 	uint32_t	blksize;	/* Preferred I/O size */
 	u64		attributes;
+	u64		attributes_mask;
 #define KSTAT_ATTR_FS_IOC_FLAGS				\
 	(STATX_ATTR_COMPRESSED |			\
 	 STATX_ATTR_IMMUTABLE |				\
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index fc273e9d5f67..3921cb9dfadb 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -28,6 +28,9 @@
 
 #include <linux/platform_device.h>
 
+#define MTL_MAX_RX_QUEUES	8
+#define MTL_MAX_TX_QUEUES	8
+
 #define STMMAC_RX_COE_NONE	0
 #define STMMAC_RX_COE_TYPE1	1
 #define STMMAC_RX_COE_TYPE2	2
@@ -44,6 +47,18 @@
 #define	STMMAC_CSR_150_250M	0x4	/* MDC = clk_scr_i/102 */
 #define	STMMAC_CSR_250_300M	0x5	/* MDC = clk_scr_i/122 */
 
+/* MTL algorithms identifiers */
+#define MTL_TX_ALGORITHM_WRR	0x0
+#define MTL_TX_ALGORITHM_WFQ	0x1
+#define MTL_TX_ALGORITHM_DWRR	0x2
+#define MTL_TX_ALGORITHM_SP	0x3
+#define MTL_RX_ALGORITHM_SP	0x4
+#define MTL_RX_ALGORITHM_WSP	0x5
+
+/* RX/TX Queue Mode */
+#define MTL_QUEUE_AVB		0x0
+#define MTL_QUEUE_DCB		0x1
+
 /* The MDC clock could be set higher than the IEEE 802.3
  * specified frequency limit 0f 2.5 MHz, by programming a clock divider
  * of value different than the above defined values. The resultant MDIO
@@ -109,6 +124,26 @@ struct stmmac_axi {
 	bool axi_rb;
 };
 
+struct stmmac_rxq_cfg {
+	u8 mode_to_use;
+	u8 chan;
+	u8 pkt_route;
+	bool use_prio;
+	u32 prio;
+};
+
+struct stmmac_txq_cfg {
+	u8 weight;
+	u8 mode_to_use;
+	/* Credit Base Shaper parameters */
+	u32 send_slope;
+	u32 idle_slope;
+	u32 high_credit;
+	u32 low_credit;
+	bool use_prio;
+	u32 prio;
+};
+
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
@@ -133,6 +168,12 @@ struct plat_stmmacenet_data {
 	int unicast_filter_entries;
 	int tx_fifo_size;
 	int rx_fifo_size;
+	u8 rx_queues_to_use;
+	u8 tx_queues_to_use;
+	u8 rx_sched_algorithm;
+	u8 tx_sched_algorithm;
+	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
+	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index 9fba9dd33544..9375d23a24e7 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -34,9 +34,9 @@ struct t10_pi_tuple {
 };
 
 
-extern struct blk_integrity_profile t10_pi_type1_crc;
-extern struct blk_integrity_profile t10_pi_type1_ip;
-extern struct blk_integrity_profile t10_pi_type3_crc;
-extern struct blk_integrity_profile t10_pi_type3_ip;
+extern const struct blk_integrity_profile t10_pi_type1_crc;
+extern const struct blk_integrity_profile t10_pi_type1_ip;
+extern const struct blk_integrity_profile t10_pi_type3_crc;
+extern const struct blk_integrity_profile t10_pi_type3_ip;
 
 #endif
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index cfc2d9506ce8..b6d5adcee8fc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -233,12 +233,14 @@ struct tcp_sock {
 	u8	syn_data:1,	/* SYN includes data */
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
+		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
 		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
 		save_syn:1,	/* Save headers of SYN packet */
 		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
 	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
 
 /* RTT measurement */
+	struct skb_mstamp tcp_mstamp; /* most recent packet received/sent */
 	u32	srtt_us;	/* smoothed round trip time << 3 in usecs */
 	u32	mdev_us;	/* medium deviation			*/
 	u32	mdev_max_us;	/* maximal mdev for the last rtt period	*/
@@ -331,16 +333,16 @@ struct tcp_sock {
 
 /* Receiver side RTT estimation */
 	struct {
-		u32	rtt;
-		u32	seq;
-		u32	time;
+		u32		rtt_us;
+		u32		seq;
+		struct skb_mstamp time;
 	} rcv_rtt_est;
 
 /* Receiver queue space */
 	struct {
-		int	space;
-		u32	seq;
-		u32	time;
+		int		space;
+		u32		seq;
+		struct skb_mstamp time;
 	} rcvq_space;
 
 /* TCP-specific MTU probe information. */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 58373875e8ee..d7d3ea637dd0 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -22,6 +22,18 @@
 #endif
 
 #include <linux/bitops.h>
+
+/*
+ * For per-arch arch_within_stack_frames() implementations, defined in
+ * asm/thread_info.h.
+ */
+enum {
+	BAD_STACK = -1,
+	NOT_STACK = 0,
+	GOOD_FRAME,
+	GOOD_STACK,
+};
+
 #include <asm/thread_info.h>
 
 #ifdef __KERNEL__
@@ -101,6 +113,10 @@ static inline void check_object_size(const void *ptr, unsigned long n,
 { }
 #endif /* CONFIG_HARDENED_USERCOPY */
 
+#ifndef arch_setup_new_exec
+static inline void arch_setup_new_exec(void) { }
+#endif
+
 #endif	/* __KERNEL__ */
 
 #endif /* _LINUX_THREAD_INFO_H */
diff --git a/include/linux/tick.h b/include/linux/tick.h
index a04fea19676f..fe01e68bf520 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -117,6 +117,7 @@ extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
+extern unsigned long tick_nohz_get_idle_calls(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
 #else /* !CONFIG_NO_HZ_COMMON */
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index b598cbc7b576..ddc229ff6d1e 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -19,21 +19,6 @@ extern void do_gettimeofday(struct timeval *tv);
 extern int do_settimeofday64(const struct timespec64 *ts);
 extern int do_sys_settimeofday64(const struct timespec64 *tv,
 				 const struct timezone *tz);
-static inline int do_sys_settimeofday(const struct timespec *tv,
-				      const struct timezone *tz)
-{
-	struct timespec64 ts64;
-
-	if (!tv)
-		return do_sys_settimeofday64(NULL, tz);
-
-	if (!timespec_valid(tv))
-		return -EINVAL;
-
-	ts64 = timespec_to_timespec64(*tv);
-	return do_sys_settimeofday64(&ts64, tz);
-}
-
 /*
  * Kernel time accessors
  */
@@ -273,6 +258,11 @@ static inline void timekeeping_clocktai(struct timespec *ts)
 	*ts = ktime_to_timespec(ktime_get_clocktai());
 }
 
+static inline void timekeeping_clocktai64(struct timespec64 *ts)
+{
+	*ts = ktime_to_timespec64(ktime_get_clocktai());
+}
+
 /*
  * RTC specific
  */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index f30c187ed785..e0cbfb09e60f 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,8 +2,199 @@
 #define __LINUX_UACCESS_H__
 
 #include <linux/sched.h>
+#include <linux/thread_info.h>
+#include <linux/kasan-checks.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
+
 #include <asm/uaccess.h>
 
+/*
+ * Architectures should provide two primitives (raw_copy_{to,from}_user())
+ * and get rid of their private instances of copy_{to,from}_user() and
+ * __copy_{to,from}_user{,_inatomic}().
+ *
+ * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and
+ * return the amount left to copy.  They should assume that access_ok() has
+ * already been checked (and succeeded); they should *not* zero-pad anything.
+ * No KASAN or object size checks either - those belong here.
+ *
+ * Both of these functions should attempt to copy size bytes starting at from
+ * into the area starting at to.  They must not fetch or store anything
+ * outside of those areas.  Return value must be between 0 (everything
+ * copied successfully) and size (nothing copied).
+ *
+ * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting
+ * at to must become equal to the bytes fetched from the corresponding area
+ * starting at from.  All data past to + size - N must be left unmodified.
+ *
+ * If copying succeeds, the return value must be 0.  If some data cannot be
+ * fetched, it is permitted to copy less than had been fetched; the only
+ * hard requirement is that not storing anything at all (i.e. returning size)
+ * should happen only when nothing could be copied.  In other words, you don't
+ * have to squeeze as much as possible - it is allowed, but not necessary.
+ *
+ * For raw_copy_from_user() to always points to kernel memory and no faults
+ * on store should happen.  Interpretation of from is affected by set_fs().
+ * For raw_copy_to_user() it's the other way round.
+ *
+ * Both can be inlined - it's up to architectures whether it wants to bother
+ * with that.  They should not be used directly; they are used to implement
+ * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic())
+ * that are used instead.  Out of those, __... ones are inlined.  Plain
+ * copy_{to,from}_user() might or might not be inlined.  If you want them
+ * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER.
+ *
+ * NOTE: only copy_from_user() zero-pads the destination in case of short copy.
+ * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything
+ * at all; their callers absolutely must check the return value.
+ *
+ * Biarch ones should also provide raw_copy_in_user() - similar to the above,
+ * but both source and destination are __user pointers (affected by set_fs()
+ * as usual) and both source and destination can trigger faults.
+ */
+
+static __always_inline unsigned long
+__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+	kasan_check_write(to, n);
+	check_object_size(to, n, false);
+	return raw_copy_from_user(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	might_fault();
+	kasan_check_write(to, n);
+	check_object_size(to, n, false);
+	return raw_copy_from_user(to, from, n);
+}
+
+/**
+ * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ * The caller should also make sure he pins the user space address
+ * so that we don't result in page fault and sleep.
+ */
+static __always_inline unsigned long
+__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
+{
+	kasan_check_read(from, n);
+	check_object_size(from, n, true);
+	return raw_copy_to_user(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	might_fault();
+	kasan_check_read(from, n);
+	check_object_size(from, n, true);
+	return raw_copy_to_user(to, from, n);
+}
+
+#ifdef INLINE_COPY_FROM_USER
+static inline unsigned long
+_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long res = n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = raw_copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
+}
+#else
+extern unsigned long
+_copy_from_user(void *, const void __user *, unsigned long);
+#endif
+
+#ifdef INLINE_COPY_TO_USER
+static inline unsigned long
+_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		n = raw_copy_to_user(to, from, n);
+	return n;
+}
+#else
+extern unsigned long
+_copy_to_user(void __user *, const void *, unsigned long);
+#endif
+
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
+static __always_inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	int sz = __compiletime_object_size(to);
+
+	might_fault();
+	kasan_check_write(to, n);
+
+	if (likely(sz < 0 || sz >= n)) {
+		check_object_size(to, n, false);
+		n = _copy_from_user(to, from, n);
+	} else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
+	else
+		__bad_copy_user();
+
+	return n;
+}
+
+static __always_inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	int sz = __compiletime_object_size(from);
+
+	kasan_check_read(from, n);
+	might_fault();
+
+	if (likely(sz < 0 || sz >= n)) {
+		check_object_size(from, n, true);
+		n = _copy_to_user(to, from, n);
+	} else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
+	else
+		__bad_copy_user();
+
+	return n;
+}
+#ifdef CONFIG_COMPAT
+static __always_inline unsigned long __must_check
+__copy_in_user(void __user *to, const void *from, unsigned long n)
+{
+	might_fault();
+	return raw_copy_in_user(to, from, n);
+}
+static __always_inline unsigned long __must_check
+copy_in_user(void __user *to, const void *from, unsigned long n)
+{
+	might_fault();
+	if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n))
+		n = raw_copy_in_user(to, from, n);
+	return n;
+}
+#endif
+
 static __always_inline void pagefault_disabled_inc(void)
 {
 	current->pagefault_disabled++;
@@ -67,12 +258,6 @@ static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
 	return __copy_from_user_inatomic(to, from, n);
 }
 
-static inline unsigned long __copy_from_user_nocache(void *to,
-				const void __user *from, unsigned long n)
-{
-	return __copy_from_user(to, from, n);
-}
-
 #endif		/* ARCH_HAS_NOCACHE_UACCESS */
 
 /*
diff --git a/include/linux/udp.h b/include/linux/udp.h
index c0f530809d1f..6cb4061a720d 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -115,6 +115,6 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 #define udp_portaddr_for_each_entry_rcu(__sk, list) \
 	hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node)
 
-#define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag)
+#define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE)
 
 #endif	/* _LINUX_UDP_H */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 804e34c6f981..f2d36a3d3005 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -39,7 +39,10 @@ struct iov_iter {
 	};
 	union {
 		unsigned long nr_segs;
-		int idx;
+		struct {
+			int idx;
+			int start_idx;
+		};
 	};
 };
 
@@ -81,6 +84,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
 size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
+void iov_iter_revert(struct iov_iter *i, size_t bytes);
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 4616a49a1c2e..f665d2ceac20 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -451,6 +451,7 @@ static inline struct usb_composite_driver *to_cdriver(
  * sure doing that won't hurt too much.
  *
  * One notion for how to handle Wireless USB devices involves:
+ *
  * (a) a second gadget here, discovery mechanism TBD, but likely
  *     needing separate "register/unregister WUSB gadget" calls;
  * (b) updates to usb_gadget to include flags "is it wireless",
@@ -503,8 +504,9 @@ struct usb_composite_dev {
 	/* protects deactivations and delayed_status counts*/
 	spinlock_t			lock;
 
-	unsigned			setup_pending:1;
-	unsigned			os_desc_pending:1;
+	/* public: */
+	unsigned int			setup_pending:1;
+	unsigned int			os_desc_pending:1;
 };
 
 extern int usb_string_id(struct usb_composite_dev *c);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index e4516e9ded0f..fbc22a39e7bc 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -188,7 +188,7 @@ struct usb_ep_caps {
  * @caps:The structure describing types and directions supported by endoint.
  * @maxpacket:The maximum packet size used on this endpoint.  The initial
  *	value can sometimes be reduced (hardware allowing), according to
- *      the endpoint descriptor used to configure the endpoint.
+ *	the endpoint descriptor used to configure the endpoint.
  * @maxpacket_limit:The maximum packet size value which can be handled by this
  *	endpoint. It's set once by UDC driver when endpoint is initialized, and
  *	should not be changed. Should not be confused with maxpacket.
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 1d0043dc34e4..de2a722fe3cf 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -50,4 +50,10 @@
 /* device can't handle Link Power Management */
 #define USB_QUIRK_NO_LPM			BIT(10)
 
+/*
+ * Device reports its bInterval as linear frames instead of the
+ * USB 2.0 calculation.
+ */
+#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL	BIT(11)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 6e0ce8c7b8cb..7dffa5624ea6 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -64,6 +64,8 @@ struct usbnet {
 	struct usb_anchor	deferred;
 	struct tasklet_struct	bh;
 
+	struct pcpu_sw_netstats __percpu *stats64;
+
 	struct work_struct	kevent;
 	unsigned long		flags;
 #		define EVENT_TX_HALT	0
@@ -261,10 +263,10 @@ extern void usbnet_pause_rx(struct usbnet *);
 extern void usbnet_resume_rx(struct usbnet *);
 extern void usbnet_purge_paused_rxq(struct usbnet *);
 
-extern int usbnet_get_settings(struct net_device *net,
-			       struct ethtool_cmd *cmd);
-extern int usbnet_set_settings(struct net_device *net,
-			       struct ethtool_cmd *cmd);
+extern int usbnet_get_link_ksettings(struct net_device *net,
+				     struct ethtool_link_ksettings *cmd);
+extern int usbnet_set_link_ksettings(struct net_device *net,
+				     const struct ethtool_link_ksettings *cmd);
 extern u32 usbnet_get_link(struct net_device *net);
 extern u32 usbnet_get_msglevel(struct net_device *);
 extern void usbnet_set_msglevel(struct net_device *, u32);
@@ -278,5 +280,7 @@ extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags);
 extern void usbnet_status_stop(struct usbnet *dev);
 
 extern void usbnet_update_max_qlen(struct usbnet *dev);
+extern void usbnet_get_stats64(struct net_device *dev,
+			       struct rtnl_link_stats64 *stats);
 
 #endif /* __LINUX_USB_USBNET_H */
diff --git a/include/linux/usb/xhci-dbgp.h b/include/linux/usb/xhci-dbgp.h
new file mode 100644
index 000000000000..80c1cca1f529
--- /dev/null
+++ b/include/linux/usb/xhci-dbgp.h
@@ -0,0 +1,29 @@
+/*
+ * Standalone xHCI debug capability driver
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_XHCI_DBGP_H
+#define __LINUX_XHCI_DBGP_H
+
+#ifdef CONFIG_EARLY_PRINTK_USB_XDBC
+int __init early_xdbc_parse_parameter(char *s);
+int __init early_xdbc_setup_hardware(void);
+void __init early_xdbc_register_console(void);
+#else
+static inline int __init early_xdbc_setup_hardware(void)
+{
+	return -ENODEV;
+}
+static inline void __init early_xdbc_register_console(void)
+{
+}
+#endif /* CONFIG_EARLY_PRINTK_USB_XDBC */
+#endif /* __LINUX_XHCI_DBGP_H */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index be765234c0a2..32354b4b4b2b 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -72,7 +72,7 @@ struct ucounts {
 	struct hlist_node node;
 	struct user_namespace *ns;
 	kuid_t uid;
-	atomic_t count;
+	int count;
 	atomic_t ucount[UCOUNT_COUNTS];
 };
 
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 0468548acebf..48a3483dccb1 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -61,8 +61,7 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
 					unsigned long from, unsigned long to,
 					unsigned long len);
 
-extern void userfaultfd_remove(struct vm_area_struct *vma,
-			       struct vm_area_struct **prev,
+extern bool userfaultfd_remove(struct vm_area_struct *vma,
 			       unsigned long start,
 			       unsigned long end);
 
@@ -72,8 +71,6 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma,
 extern void userfaultfd_unmap_complete(struct mm_struct *mm,
 				       struct list_head *uf);
 
-extern void userfaultfd_exit(struct mm_struct *mm);
-
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -120,11 +117,11 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
 {
 }
 
-static inline void userfaultfd_remove(struct vm_area_struct *vma,
-				      struct vm_area_struct **prev,
+static inline bool userfaultfd_remove(struct vm_area_struct *vma,
 				      unsigned long start,
 				      unsigned long end)
 {
+	return true;
 }
 
 static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
@@ -139,10 +136,6 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
 {
 }
 
-static inline void userfaultfd_exit(struct mm_struct *mm)
-{
-}
-
 #endif /* CONFIG_USERFAULTFD */
 
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 04b0d3f95043..7edfbdb55a99 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -167,6 +167,7 @@ struct virtio_driver {
 	unsigned int feature_table_size;
 	const unsigned int *feature_table_legacy;
 	unsigned int feature_table_size_legacy;
+	int (*validate)(struct virtio_device *dev);
 	int (*probe)(struct virtio_device *dev);
 	void (*scan)(struct virtio_device *dev);
 	void (*remove)(struct virtio_device *dev);
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 9638bfeb0d1f..ab13f0743da8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -48,6 +48,8 @@ struct virtio_vsock_pkt {
 	struct virtio_vsock_hdr	hdr;
 	struct work_struct work;
 	struct list_head list;
+	/* socket refcnt not held, only use for cancellation */
+	struct vsock_sock *vsk;
 	void *buf;
 	u32 len;
 	u32 off;
@@ -56,6 +58,7 @@ struct virtio_vsock_pkt {
 
 struct virtio_vsock_pkt_info {
 	u32 remote_cid, remote_port;
+	struct vsock_sock *vsk;
 	struct msghdr *msg;
 	u32 pkt_len;
 	u16 type;
@@ -150,5 +153,6 @@ void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt);
 void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt);
 u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
 void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
+void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt);
 
 #endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 6aa1b6cb5828..a80b7b59cf33 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -79,6 +79,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_SPLIT_PAGE_FAILED,
 		THP_DEFERRED_SPLIT_PAGE,
 		THP_SPLIT_PMD,
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+		THP_SPLIT_PUD,
+#endif
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
diff --git a/include/linux/wait.h b/include/linux/wait.h
index aacb1282d19a..db076ca7f11d 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -620,30 +620,19 @@ do {									\
 	__ret;								\
 })
 
+extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *);
+extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
 
-#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \
+#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
 ({									\
-	int __ret = 0;							\
+	int __ret;							\
 	DEFINE_WAIT(__wait);						\
 	if (exclusive)							\
 		__wait.flags |= WQ_FLAG_EXCLUSIVE;			\
 	do {								\
-		if (likely(list_empty(&__wait.task_list)))		\
-			__add_wait_queue_tail(&(wq), &__wait);		\
-		set_current_state(TASK_INTERRUPTIBLE);			\
-		if (signal_pending(current)) {				\
-			__ret = -ERESTARTSYS;				\
+		__ret = fn(&(wq), &__wait);				\
+		if (__ret)						\
 			break;						\
-		}							\
-		if (irq)						\
-			spin_unlock_irq(&(wq).lock);			\
-		else							\
-			spin_unlock(&(wq).lock);			\
-		schedule();						\
-		if (irq)						\
-			spin_lock_irq(&(wq).lock);			\
-		else							\
-			spin_lock(&(wq).lock);				\
 	} while (!(condition));						\
 	__remove_wait_queue(&(wq), &__wait);				\
 	__set_current_state(TASK_RUNNING);				\
@@ -676,7 +665,7 @@ do {									\
  */
 #define wait_event_interruptible_locked(wq, condition)			\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
 
 /**
  * wait_event_interruptible_locked_irq - sleep until a condition gets true
@@ -703,7 +692,7 @@ do {									\
  */
 #define wait_event_interruptible_locked_irq(wq, condition)		\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
 
 /**
  * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true
@@ -734,7 +723,7 @@ do {									\
  */
 #define wait_event_interruptible_exclusive_locked(wq, condition)	\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
 
 /**
  * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true
@@ -765,7 +754,7 @@ do {									\
  */
 #define wait_event_interruptible_exclusive_locked_irq(wq, condition)	\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
 
 
 #define __wait_event_killable(wq, condition)				\
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index bde063cefd04..c102ef65cb64 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -608,8 +608,13 @@ static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 {
 	return fn(arg);
 }
+static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg)
+{
+	return fn(arg);
+}
 #else
 long work_on_cpu(int cpu, long (*fn)(void *), void *arg);
+long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg);
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a3c0cbd7c888..d5815794416c 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -237,6 +237,7 @@ static inline void inode_attach_wb(struct inode *inode, struct page *page)
 static inline void inode_detach_wb(struct inode *inode)
 {
 	if (inode->i_wb) {
+		WARN_ON_ONCE(!(inode->i_state & I_CLEAR));
 		wb_put(inode->i_wb);
 		inode->i_wb = NULL;
 	}
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
index 458b400373d4..38aac554dbba 100644
--- a/include/media/vsp1.h
+++ b/include/media/vsp1.h
@@ -20,8 +20,17 @@ struct device;
 
 int vsp1_du_init(struct device *dev);
 
-int vsp1_du_setup_lif(struct device *dev, unsigned int width,
-		      unsigned int height);
+/**
+ * struct vsp1_du_lif_config - VSP LIF configuration
+ * @width: output frame width
+ * @height: output frame height
+ */
+struct vsp1_du_lif_config {
+	unsigned int width;
+	unsigned int height;
+};
+
+int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg);
 
 struct vsp1_du_atomic_config {
 	u32 pixelformat;
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index 5ab4c9901ccc..a71378007e61 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -198,6 +198,21 @@ static inline void lowpan_iphc_uncompress_eui64_lladdr(struct in6_addr *ipaddr,
 	ipaddr->s6_addr[8] ^= 0x02;
 }
 
+static inline void lowpan_iphc_uncompress_eui48_lladdr(struct in6_addr *ipaddr,
+						       const void *lladdr)
+{
+	/* fe:80::XXXX:XXff:feXX:XXXX
+	 *        \_________________/
+	 *              hwaddr
+	 */
+	ipaddr->s6_addr[0] = 0xFE;
+	ipaddr->s6_addr[1] = 0x80;
+	memcpy(&ipaddr->s6_addr[8], lladdr, 3);
+	ipaddr->s6_addr[11] = 0xFF;
+	ipaddr->s6_addr[12] = 0xFE;
+	memcpy(&ipaddr->s6_addr[13], lladdr + 3, 3);
+}
+
 #ifdef DEBUG
 /* print data in line */
 static inline void raw_dump_inline(const char *caller, char *msg,
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 17c6fd84e287..1aeb25dd42a7 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -262,8 +262,8 @@ int register_inet6addr_notifier(struct notifier_block *nb);
 int unregister_inet6addr_notifier(struct notifier_block *nb);
 int inet6addr_notifier_call_chain(unsigned long val, void *v);
 
-void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				  struct ipv6_devconf *devconf);
+void inet6_netconf_notify_devconf(struct net *net, int event, int type,
+				  int ifindex, struct ipv6_devconf *devconf);
 
 /**
  * __in6_dev_get - get inet6_dev pointer from netdevice
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 1061a472a3e3..b5f5187f488c 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -39,7 +39,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 			   struct msghdr *, size_t);
 int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
 			   void *, size_t, size_t *, bool, u32 *);
-void rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
+bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 			     u32, int, const char *);
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f2758964ce6f..f9fb566e75cf 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -100,6 +100,9 @@ struct vsock_transport {
 	void (*destruct)(struct vsock_sock *);
 	void (*release)(struct vsock_sock *);
 
+	/* Cancel all pending packets sent on vsock. */
+	int (*cancel_pkt)(struct vsock_sock *vsk);
+
 	/* Connections. */
 	int (*connect)(struct vsock_sock *);
 
@@ -185,4 +188,17 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
 void vsock_remove_sock(struct vsock_sock *vsk);
 void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
 
+/**** TAP ****/
+
+struct vsock_tap {
+	struct net_device *dev;
+	struct module *module;
+	struct list_head list;
+};
+
+int vsock_init_tap(void);
+int vsock_add_tap(struct vsock_tap *vt);
+int vsock_remove_tap(struct vsock_tap *vt);
+void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque);
+
 #endif /* __AF_VSOCK_H__ */
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 5ee3c689c863..0697fd413087 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -282,7 +282,7 @@ struct l2cap_conn_rsp {
 #define L2CAP_CR_BAD_KEY_SIZE	0x0007
 #define L2CAP_CR_ENCRYPTION	0x0008
 #define L2CAP_CR_INVALID_SCID	0x0009
-#define L2CAP_CR_SCID_IN_USE	0x0010
+#define L2CAP_CR_SCID_IN_USE	0x000A
 
 /* connect/create channel status */
 #define L2CAP_CS_NO_INFO	0x0000
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 4190af53a46a..da4acefe39c8 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -21,6 +21,8 @@
    SOFTWARE IS DISCLAIMED.
 */
 
+#include <linux/refcount.h>
+
 #ifndef __RFCOMM_H
 #define __RFCOMM_H
 
@@ -174,7 +176,7 @@ struct rfcomm_dlc {
 	struct mutex  lock;
 	unsigned long state;
 	unsigned long flags;
-	atomic_t      refcnt;
+	refcount_t    refcnt;
 	u8            dlci;
 	u8            addr;
 	u8            priority;
@@ -247,12 +249,12 @@ struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel);
 
 static inline void rfcomm_dlc_hold(struct rfcomm_dlc *d)
 {
-	atomic_inc(&d->refcnt);
+	refcount_inc(&d->refcnt);
 }
 
 static inline void rfcomm_dlc_put(struct rfcomm_dlc *d)
 {
-	if (atomic_dec_and_test(&d->refcnt))
+	if (refcount_dec_and_test(&d->refcnt))
 		rfcomm_dlc_free(d);
 }
 
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 3c857778a6ca..b00508d22e0a 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -153,7 +153,8 @@ struct slave {
 	unsigned long last_link_up;
 	unsigned long last_rx;
 	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
-	s8     link;    /* one of BOND_LINK_XXXX */
+	s8     link;		/* one of BOND_LINK_XXXX */
+	s8     link_new_state;	/* one of BOND_LINK_XXXX */
 	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
@@ -165,7 +166,7 @@ struct slave {
 	u32    link_failure_count;
 	u32    speed;
 	u16    queue_id;
-	u8     perm_hwaddr[ETH_ALEN];
+	u8     perm_hwaddr[MAX_ADDR_LEN];
 	struct ad_slave_info *ad_info;
 	struct tlb_slave_info tlb_info;
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -401,6 +402,16 @@ static inline bool bond_slave_can_tx(struct slave *slave)
 	       bond_is_active_slave(slave);
 }
 
+static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len)
+{
+	if (len == ETH_ALEN) {
+		ether_addr_copy(dst, src);
+		return;
+	}
+
+	memcpy(dst, src, len);
+}
+
 #define BOND_PRI_RESELECT_ALWAYS	0
 #define BOND_PRI_RESELECT_BETTER	1
 #define BOND_PRI_RESELECT_FAILURE	2
@@ -504,13 +515,17 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
 	return slave->inactive;
 }
 
-static inline void bond_set_slave_link_state(struct slave *slave, int state,
-					     bool notify)
+static inline void bond_propose_link_state(struct slave *slave, int state)
 {
-	if (slave->link == state)
+	slave->link_new_state = state;
+}
+
+static inline void bond_commit_link_state(struct slave *slave, bool notify)
+{
+	if (slave->link == slave->link_new_state)
 		return;
 
-	slave->link = state;
+	slave->link = slave->link_new_state;
 	if (notify) {
 		bond_queue_slave_event(slave);
 		bond_lower_state_changed(slave);
@@ -523,6 +538,13 @@ static inline void bond_set_slave_link_state(struct slave *slave, int state,
 	}
 }
 
+static inline void bond_set_slave_link_state(struct slave *slave, int state,
+					     bool notify)
+{
+	bond_propose_link_state(slave, state);
+	bond_commit_link_state(slave, notify);
+}
+
 static inline void bond_slave_link_notify(struct bonding *bond)
 {
 	struct list_head *iter;
@@ -592,6 +614,7 @@ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,
 					      int level);
 int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave);
 void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay);
+void bond_work_init_all(struct bonding *bond);
 
 #ifdef CONFIG_PROC_FS
 void bond_create_proc_entry(struct bonding *bond);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c0452de83086..8ffd434676b7 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -35,83 +35,101 @@ struct napi_struct;
 extern unsigned int sysctl_net_busy_read __read_mostly;
 extern unsigned int sysctl_net_busy_poll __read_mostly;
 
+/*		0 - Reserved to indicate value not set
+ *     1..NR_CPUS - Reserved for sender_cpu
+ *  NR_CPUS+1..~0 - Region available for NAPI IDs
+ */
+#define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
+
 static inline bool net_busy_loop_on(void)
 {
 	return sysctl_net_busy_poll;
 }
 
-static inline u64 busy_loop_us_clock(void)
+static inline bool sk_can_busy_loop(const struct sock *sk)
 {
-	return local_clock() >> 10;
+	return sk->sk_ll_usec && !signal_pending(current);
 }
 
-static inline unsigned long sk_busy_loop_end_time(struct sock *sk)
-{
-	return busy_loop_us_clock() + ACCESS_ONCE(sk->sk_ll_usec);
-}
+bool sk_busy_loop_end(void *p, unsigned long start_time);
 
-/* in poll/select we use the global sysctl_net_ll_poll value */
-static inline unsigned long busy_loop_end_time(void)
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg);
+
+#else /* CONFIG_NET_RX_BUSY_POLL */
+static inline unsigned long net_busy_loop_on(void)
 {
-	return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll);
+	return 0;
 }
 
-static inline bool sk_can_busy_loop(const struct sock *sk)
+static inline bool sk_can_busy_loop(struct sock *sk)
 {
-	return sk->sk_ll_usec && sk->sk_napi_id && !signal_pending(current);
+	return false;
 }
 
+#endif /* CONFIG_NET_RX_BUSY_POLL */
 
-static inline bool busy_loop_timeout(unsigned long end_time)
+static inline unsigned long busy_loop_current_time(void)
 {
-	unsigned long now = busy_loop_us_clock();
-
-	return time_after(now, end_time);
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	return (unsigned long)(local_clock() >> 10);
+#else
+	return 0;
+#endif
 }
 
-bool sk_busy_loop(struct sock *sk, int nonblock);
-
-/* used in the NIC receive handler to mark the skb */
-static inline void skb_mark_napi_id(struct sk_buff *skb,
-				    struct napi_struct *napi)
+/* in poll/select we use the global sysctl_net_ll_poll value */
+static inline bool busy_loop_timeout(unsigned long start_time)
 {
-	skb->napi_id = napi->napi_id;
-}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll);
 
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
 
-#else /* CONFIG_NET_RX_BUSY_POLL */
-static inline unsigned long net_busy_loop_on(void)
-{
-	return 0;
+		return time_after(now, end_time);
+	}
+#endif
+	return true;
 }
 
-static inline unsigned long busy_loop_end_time(void)
+static inline bool sk_busy_loop_timeout(struct sock *sk,
+					unsigned long start_time)
 {
-	return 0;
-}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec);
 
-static inline bool sk_can_busy_loop(struct sock *sk)
-{
-	return false;
-}
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
 
-static inline void skb_mark_napi_id(struct sk_buff *skb,
-				    struct napi_struct *napi)
-{
+		return time_after(now, end_time);
+	}
+#endif
+	return true;
 }
 
-static inline bool busy_loop_timeout(unsigned long end_time)
+static inline void sk_busy_loop(struct sock *sk, int nonblock)
 {
-	return true;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
+
+	if (napi_id >= MIN_NAPI_ID)
+		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
+#endif
 }
 
-static inline bool sk_busy_loop(struct sock *sk, int nonblock)
+/* used in the NIC receive handler to mark the skb */
+static inline void skb_mark_napi_id(struct sk_buff *skb,
+				    struct napi_struct *napi)
 {
-	return false;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	skb->napi_id = napi->napi_id;
+#endif
 }
 
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
 /* used in the protocol hanlder to propagate the napi_id to the socket */
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ead1aa6d003e..6e90f1a4950f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -363,6 +363,8 @@ static inline void wiphy_read_of_freq_limits(struct wiphy *wiphy)
 
 /**
  * struct vif_params - describes virtual interface parameters
+ * @flags: monitor interface flags, unchanged if 0, otherwise
+ *	%MONITOR_FLAG_CHANGED will be set
  * @use_4addr: use 4-address frames
  * @macaddr: address to use for this virtual interface.
  *	If this parameter is set to zero address the driver may
@@ -370,13 +372,17 @@ static inline void wiphy_read_of_freq_limits(struct wiphy *wiphy)
  *	This feature is only fully supported by drivers that enable the
  *	%NL80211_FEATURE_MAC_ON_CREATE flag.  Others may support creating
  **	only p2p devices with specified MAC.
- * @vht_mumimo_groups: MU-MIMO groupID. used for monitoring only
- *	 packets belonging to that MU-MIMO groupID.
+ * @vht_mumimo_groups: MU-MIMO groupID, used for monitoring MU-MIMO packets
+ *	belonging to that MU-MIMO groupID; %NULL if not changed
+ * @vht_mumimo_follow_addr: MU-MIMO follow address, used for monitoring
+ *	MU-MIMO packets going to the specified station; %NULL if not changed
  */
 struct vif_params {
+	u32 flags;
 	int use_4addr;
 	u8 macaddr[ETH_ALEN];
-	u8 vht_mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN];
+	const u8 *vht_mumimo_groups;
+	const u8 *vht_mumimo_follow_addr;
 };
 
 /**
@@ -1211,6 +1217,7 @@ static inline int cfg80211_get_station(struct net_device *dev,
  * Monitor interface configuration flags. Note that these must be the bits
  * according to the nl80211 flags.
  *
+ * @MONITOR_FLAG_CHANGED: set if the flags were changed
  * @MONITOR_FLAG_FCSFAIL: pass frames with bad FCS
  * @MONITOR_FLAG_PLCPFAIL: pass frames with bad PLCP
  * @MONITOR_FLAG_CONTROL: pass control frames
@@ -1219,6 +1226,7 @@ static inline int cfg80211_get_station(struct net_device *dev,
  * @MONITOR_FLAG_ACTIVE: active monitor, ACKs frames on its MAC address
  */
 enum monitor_flags {
+	MONITOR_FLAG_CHANGED		= 1<<__NL80211_MNTR_FLAG_INVALID,
 	MONITOR_FLAG_FCSFAIL		= 1<<NL80211_MNTR_FLAG_FCSFAIL,
 	MONITOR_FLAG_PLCPFAIL		= 1<<NL80211_MNTR_FLAG_PLCPFAIL,
 	MONITOR_FLAG_CONTROL		= 1<<NL80211_MNTR_FLAG_CONTROL,
@@ -1605,11 +1613,15 @@ static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask)
 /**
  * struct cfg80211_match_set - sets of attributes to match
  *
- * @ssid: SSID to be matched; may be zero-length for no match (RSSI only)
+ * @ssid: SSID to be matched; may be zero-length in case of BSSID match
+ *	or no match (RSSI only)
+ * @bssid: BSSID to be matched; may be all-zero BSSID in case of SSID match
+ *	or no match (RSSI only)
  * @rssi_thold: don't report scan results below this threshold (in s32 dBm)
  */
 struct cfg80211_match_set {
 	struct cfg80211_ssid ssid;
+	u8 bssid[ETH_ALEN];
 	s32 rssi_thold;
 };
 
@@ -1641,6 +1653,7 @@ struct cfg80211_bss_select_adjust {
 /**
  * struct cfg80211_sched_scan_request - scheduled scan request description
  *
+ * @reqid: identifies this request.
  * @ssids: SSIDs to scan for (passed in the probe_reqs in active scans)
  * @n_ssids: number of SSIDs
  * @n_channels: total number of channels to scan
@@ -1653,6 +1666,7 @@ struct cfg80211_bss_select_adjust {
  * 	(others are filtered out).
  *	If ommited, all results are passed.
  * @n_match_sets: number of match sets
+ * @results_wk: worker for processing results notification.
  * @wiphy: the wiphy this was for
  * @dev: the interface
  * @scan_start: start time of the scheduled scan
@@ -1669,6 +1683,8 @@ struct cfg80211_bss_select_adjust {
  * @rcu_head: RCU callback used to free the struct
  * @owner_nlportid: netlink portid of owner (if this should is a request
  *	owned by a particular socket)
+ * @nl_owner_dead: netlink owner socket was closed - this request be freed
+ * @list: for keeping list of requests.
  * @delay: delay in seconds to use before starting the first scan
  *	cycle.  The driver may ignore this parameter and start
  *	immediately (or at any other time), if this feature is not
@@ -1685,6 +1701,7 @@ struct cfg80211_bss_select_adjust {
  *	comparisions.
  */
 struct cfg80211_sched_scan_request {
+	u64 reqid;
 	struct cfg80211_ssid *ssids;
 	int n_ssids;
 	u32 n_channels;
@@ -1710,8 +1727,11 @@ struct cfg80211_sched_scan_request {
 	struct wiphy *wiphy;
 	struct net_device *dev;
 	unsigned long scan_start;
+	bool report_results;
 	struct rcu_head rcu_head;
 	u32 owner_nlportid;
+	bool nl_owner_dead;
+	struct list_head list;
 
 	/* keep last */
 	struct ieee80211_channel *channels[0];
@@ -2073,6 +2093,19 @@ struct cfg80211_bss_selection {
  *	the BSSID of the current association, i.e., to the value that is
  *	included in the Current AP address field of the Reassociation Request
  *	frame.
+ * @fils_erp_username: EAP re-authentication protocol (ERP) username part of the
+ *	NAI or %NULL if not specified. This is used to construct FILS wrapped
+ *	data IE.
+ * @fils_erp_username_len: Length of @fils_erp_username in octets.
+ * @fils_erp_realm: EAP re-authentication protocol (ERP) realm part of NAI or
+ *	%NULL if not specified. This specifies the domain name of ER server and
+ *	is used to construct FILS wrapped data IE.
+ * @fils_erp_realm_len: Length of @fils_erp_realm in octets.
+ * @fils_erp_next_seq_num: The next sequence number to use in the FILS ERP
+ *	messages. This is also used to construct FILS wrapped data IE.
+ * @fils_erp_rrk: ERP re-authentication Root Key (rRK) used to derive additional
+ *	keys in FILS or %NULL if not specified.
+ * @fils_erp_rrk_len: Length of @fils_erp_rrk in octets.
  */
 struct cfg80211_connect_params {
 	struct ieee80211_channel *channel;
@@ -2098,6 +2131,13 @@ struct cfg80211_connect_params {
 	bool pbss;
 	struct cfg80211_bss_selection bss_select;
 	const u8 *prev_bssid;
+	const u8 *fils_erp_username;
+	size_t fils_erp_username_len;
+	const u8 *fils_erp_realm;
+	size_t fils_erp_realm_len;
+	u16 fils_erp_next_seq_num;
+	const u8 *fils_erp_rrk;
+	size_t fils_erp_rrk_len;
 };
 
 /**
@@ -2136,12 +2176,27 @@ enum wiphy_params_flags {
  * This structure is passed to the set/del_pmksa() method for PMKSA
  * caching.
  *
- * @bssid: The AP's BSSID.
- * @pmkid: The PMK material itself.
+ * @bssid: The AP's BSSID (may be %NULL).
+ * @pmkid: The identifier to refer a PMKSA.
+ * @pmk: The PMK for the PMKSA identified by @pmkid. This is used for key
+ *	derivation by a FILS STA. Otherwise, %NULL.
+ * @pmk_len: Length of the @pmk. The length of @pmk can differ depending on
+ *	the hash algorithm used to generate this.
+ * @ssid: SSID to specify the ESS within which a PMKSA is valid when using FILS
+ *	cache identifier (may be %NULL).
+ * @ssid_len: Length of the @ssid in octets.
+ * @cache_id: 2-octet cache identifier advertized by a FILS AP identifying the
+ *	scope of PMKSA. This is valid only if @ssid_len is non-zero (may be
+ *	%NULL).
  */
 struct cfg80211_pmksa {
 	const u8 *bssid;
 	const u8 *pmkid;
+	const u8 *pmk;
+	size_t pmk_len;
+	const u8 *ssid;
+	size_t ssid_len;
+	const u8 *cache_id;
 };
 
 /**
@@ -2633,8 +2688,7 @@ struct cfg80211_nan_func {
  *	indication of requesting reassociation.
  *	In both the driver-initiated and new connect() call initiated roaming
  *	cases, the result of roaming is indicated with a call to
- *	cfg80211_roamed() or cfg80211_roamed_bss().
- *	(invoked with the wireless_dev mutex held)
+ *	cfg80211_roamed(). (invoked with the wireless_dev mutex held)
  * @update_connect_params: Update the connect parameters while connected to a
  *	BSS. The updated parameters can be used by driver/firmware for
  *	subsequent BSS selection (roaming) decisions and to form the
@@ -2712,15 +2766,20 @@ struct cfg80211_nan_func {
  *	the current level is above/below the configured threshold; this may
  *	need some care when the configuration is changed (without first being
  *	disabled.)
+ * @set_cqm_rssi_range_config: Configure two RSSI thresholds in the
+ *	connection quality monitor.  An event is to be sent only when the
+ *	signal level is found to be outside the two values.  The driver should
+ *	set %NL80211_EXT_FEATURE_CQM_RSSI_LIST if this method is implemented.
+ *	If it is provided then there's no point providing @set_cqm_rssi_config.
  * @set_cqm_txe_config: Configure connection quality monitor TX error
  *	thresholds.
  * @sched_scan_start: Tell the driver to start a scheduled scan.
- * @sched_scan_stop: Tell the driver to stop an ongoing scheduled scan. This
- *	call must stop the scheduled scan and be ready for starting a new one
- *	before it returns, i.e. @sched_scan_start may be called immediately
- *	after that again and should not fail in that case. The driver should
- *	not call cfg80211_sched_scan_stopped() for a requested stop (when this
- *	method returns 0.)
+ * @sched_scan_stop: Tell the driver to stop an ongoing scheduled scan with
+ *	given request id. This call must stop the scheduled scan and be ready
+ *	for starting a new one before it returns, i.e. @sched_scan_start may be
+ *	called immediately after that again and should not fail in that case.
+ *	The driver should not call cfg80211_sched_scan_stopped() for a requested
+ *	stop (when this method returns 0).
  *
  * @mgmt_frame_register: Notify driver that a management frame type was
  *	registered. The callback is allowed to sleep.
@@ -2826,13 +2885,12 @@ struct cfg80211_ops {
 						  const char *name,
 						  unsigned char name_assign_type,
 						  enum nl80211_iftype type,
-						  u32 *flags,
 						  struct vif_params *params);
 	int	(*del_virtual_intf)(struct wiphy *wiphy,
 				    struct wireless_dev *wdev);
 	int	(*change_virtual_intf)(struct wiphy *wiphy,
 				       struct net_device *dev,
-				       enum nl80211_iftype type, u32 *flags,
+				       enum nl80211_iftype type,
 				       struct vif_params *params);
 
 	int	(*add_key)(struct wiphy *wiphy, struct net_device *netdev,
@@ -3001,6 +3059,10 @@ struct cfg80211_ops {
 				       struct net_device *dev,
 				       s32 rssi_thold, u32 rssi_hyst);
 
+	int	(*set_cqm_rssi_range_config)(struct wiphy *wiphy,
+					     struct net_device *dev,
+					     s32 rssi_low, s32 rssi_high);
+
 	int	(*set_cqm_txe_config)(struct wiphy *wiphy,
 				      struct net_device *dev,
 				      u32 rate, u32 pkts, u32 intvl);
@@ -3015,7 +3077,8 @@ struct cfg80211_ops {
 	int	(*sched_scan_start)(struct wiphy *wiphy,
 				struct net_device *dev,
 				struct cfg80211_sched_scan_request *request);
-	int	(*sched_scan_stop)(struct wiphy *wiphy, struct net_device *dev);
+	int	(*sched_scan_stop)(struct wiphy *wiphy, struct net_device *dev,
+				   u64 reqid);
 
 	int	(*set_rekey_data)(struct wiphy *wiphy, struct net_device *dev,
 				  struct cfg80211_gtk_rekey_data *data);
@@ -3160,7 +3223,7 @@ enum wiphy_flags {
 	WIPHY_FLAG_CONTROL_PORT_PROTOCOL	= BIT(7),
 	WIPHY_FLAG_IBSS_RSN			= BIT(8),
 	WIPHY_FLAG_MESH_AUTH			= BIT(10),
-	WIPHY_FLAG_SUPPORTS_SCHED_SCAN		= BIT(11),
+	/* use hole at 11 */
 	/* use hole at 12 */
 	WIPHY_FLAG_SUPPORTS_FW_ROAM		= BIT(13),
 	WIPHY_FLAG_AP_UAPSD			= BIT(14),
@@ -3498,6 +3561,8 @@ struct wiphy_iftype_ext_capab {
  *	this variable determines its size
  * @max_scan_ssids: maximum number of SSIDs the device can scan for in
  *	any given scan
+ * @max_sched_scan_reqs: maximum number of scheduled scan requests that
+ *	the device can run concurrently.
  * @max_sched_scan_ssids: maximum number of SSIDs the device can scan
  *	for in any given scheduled scan
  * @max_match_sets: maximum number of match sets the device can handle
@@ -3634,6 +3699,7 @@ struct wiphy {
 
 	int bss_priv_size;
 	u8 max_scan_ssids;
+	u8 max_sched_scan_reqs;
 	u8 max_sched_scan_ssids;
 	u8 max_match_sets;
 	u16 max_scan_ie_len;
@@ -3871,6 +3937,7 @@ void wiphy_free(struct wiphy *wiphy);
 struct cfg80211_conn;
 struct cfg80211_internal_bss;
 struct cfg80211_cached_keys;
+struct cfg80211_cqm_config;
 
 /**
  * struct wireless_dev - wireless device state
@@ -3934,6 +4001,8 @@ struct cfg80211_cached_keys;
  * @event_list: (private) list for internal event processing
  * @event_lock: (private) lock for event list
  * @owner_nlportid: (private) owner socket port ID
+ * @nl_owner_dead: (private) owner socket went away
+ * @cqm_config: (private) nl80211 RSSI monitor state
  */
 struct wireless_dev {
 	struct wiphy *wiphy;
@@ -3982,12 +4051,13 @@ struct wireless_dev {
 
 	u32 ap_unexpected_nlportid;
 
+	u32 owner_nlportid;
+	bool nl_owner_dead;
+
 	bool cac_started;
 	unsigned long cac_start_time;
 	unsigned int cac_time_ms;
 
-	u32 owner_nlportid;
-
 #ifdef CONFIG_CFG80211_WEXT
 	/* wext data */
 	struct {
@@ -4002,6 +4072,8 @@ struct wireless_dev {
 		bool prev_bssid_valid;
 	} wext;
 #endif
+
+	struct cfg80211_cqm_config *cqm_config;
 };
 
 static inline u8 *wdev_address(struct wireless_dev *wdev)
@@ -4494,31 +4566,34 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request,
  * cfg80211_sched_scan_results - notify that new scan results are available
  *
  * @wiphy: the wiphy which got scheduled scan results
+ * @reqid: identifier for the related scheduled scan request
  */
-void cfg80211_sched_scan_results(struct wiphy *wiphy);
+void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid);
 
 /**
  * cfg80211_sched_scan_stopped - notify that the scheduled scan has stopped
  *
  * @wiphy: the wiphy on which the scheduled scan stopped
+ * @reqid: identifier for the related scheduled scan request
  *
  * The driver can call this function to inform cfg80211 that the
  * scheduled scan had to be stopped, for whatever reason.  The driver
  * is then called back via the sched_scan_stop operation when done.
  */
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy);
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid);
 
 /**
  * cfg80211_sched_scan_stopped_rtnl - notify that the scheduled scan has stopped
  *
  * @wiphy: the wiphy on which the scheduled scan stopped
+ * @reqid: identifier for the related scheduled scan request
  *
  * The driver can call this function to inform cfg80211 that the
  * scheduled scan had to be stopped, for whatever reason.  The driver
  * is then called back via the sched_scan_stop operation when done.
  * This function should be called with rtnl locked.
  */
-void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy);
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy, u64 reqid);
 
 /**
  * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame
@@ -4651,12 +4726,22 @@ cfg80211_inform_bss(struct wiphy *wiphy,
 					gfp);
 }
 
+/**
+ * cfg80211_get_bss - get a BSS reference
+ * @wiphy: the wiphy this BSS struct belongs to
+ * @channel: the channel to search on (or %NULL)
+ * @bssid: the desired BSSID (or %NULL)
+ * @ssid: the desired SSID (or %NULL)
+ * @ssid_len: length of the SSID (or 0)
+ * @bss_type: type of BSS, see &enum ieee80211_bss_type
+ * @privacy: privacy filter, see &enum ieee80211_privacy
+ */
 struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 				      struct ieee80211_channel *channel,
 				      const u8 *bssid,
 				      const u8 *ssid, size_t ssid_len,
 				      enum ieee80211_bss_type bss_type,
-				      enum ieee80211_privacy);
+				      enum ieee80211_privacy privacy);
 static inline struct cfg80211_bss *
 cfg80211_get_ibss(struct wiphy *wiphy,
 		  struct ieee80211_channel *channel,
@@ -5123,6 +5208,78 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
 #endif
 
 /**
+ * struct cfg80211_connect_resp_params - Connection response params
+ * @status: Status code, %WLAN_STATUS_SUCCESS for successful connection, use
+ *	%WLAN_STATUS_UNSPECIFIED_FAILURE if your device cannot give you
+ *	the real status code for failures. If this call is used to report a
+ *	failure due to a timeout (e.g., not receiving an Authentication frame
+ *	from the AP) instead of an explicit rejection by the AP, -1 is used to
+ *	indicate that this is a failure, but without a status code.
+ *	@timeout_reason is used to report the reason for the timeout in that
+ *	case.
+ * @bssid: The BSSID of the AP (may be %NULL)
+ * @bss: Entry of bss to which STA got connected to, can be obtained through
+ *	cfg80211_get_bss() (may be %NULL). Only one parameter among @bssid and
+ *	@bss needs to be specified.
+ * @req_ie: Association request IEs (may be %NULL)
+ * @req_ie_len: Association request IEs length
+ * @resp_ie: Association response IEs (may be %NULL)
+ * @resp_ie_len: Association response IEs length
+ * @fils_kek: KEK derived from a successful FILS connection (may be %NULL)
+ * @fils_kek_len: Length of @fils_kek in octets
+ * @update_erp_next_seq_num: Boolean value to specify whether the value in
+ *	@fils_erp_next_seq_num is valid.
+ * @fils_erp_next_seq_num: The next sequence number to use in ERP message in
+ *	FILS Authentication. This value should be specified irrespective of the
+ *	status for a FILS connection.
+ * @pmk: A new PMK if derived from a successful FILS connection (may be %NULL).
+ * @pmk_len: Length of @pmk in octets
+ * @pmkid: A new PMKID if derived from a successful FILS connection or the PMKID
+ *	used for this FILS connection (may be %NULL).
+ * @timeout_reason: Reason for connection timeout. This is used when the
+ *	connection fails due to a timeout instead of an explicit rejection from
+ *	the AP. %NL80211_TIMEOUT_UNSPECIFIED is used when the timeout reason is
+ *	not known. This value is used only if @status < 0 to indicate that the
+ *	failure is due to a timeout and not due to explicit rejection by the AP.
+ *	This value is ignored in other cases (@status >= 0).
+ */
+struct cfg80211_connect_resp_params {
+	int status;
+	const u8 *bssid;
+	struct cfg80211_bss *bss;
+	const u8 *req_ie;
+	size_t req_ie_len;
+	const u8 *resp_ie;
+	size_t resp_ie_len;
+	const u8 *fils_kek;
+	size_t fils_kek_len;
+	bool update_erp_next_seq_num;
+	u16 fils_erp_next_seq_num;
+	const u8 *pmk;
+	size_t pmk_len;
+	const u8 *pmkid;
+	enum nl80211_timeout_reason timeout_reason;
+};
+
+/**
+ * cfg80211_connect_done - notify cfg80211 of connection result
+ *
+ * @dev: network device
+ * @params: connection response parameters
+ * @gfp: allocation flags
+ *
+ * It should be called by the underlying driver once execution of the connection
+ * request from connect() has been completed. This is similar to
+ * cfg80211_connect_bss(), but takes a structure pointer for connection response
+ * parameters. Only one of the functions among cfg80211_connect_bss(),
+ * cfg80211_connect_result(), cfg80211_connect_timeout(),
+ * and cfg80211_connect_done() should be called.
+ */
+void cfg80211_connect_done(struct net_device *dev,
+			   struct cfg80211_connect_resp_params *params,
+			   gfp_t gfp);
+
+/**
  * cfg80211_connect_bss - notify cfg80211 of connection result
  *
  * @dev: network device
@@ -5152,13 +5309,31 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
  * It should be called by the underlying driver once execution of the connection
  * request from connect() has been completed. This is similar to
  * cfg80211_connect_result(), but with the option of identifying the exact bss
- * entry for the connection. Only one of these functions should be called.
+ * entry for the connection. Only one of the functions among
+ * cfg80211_connect_bss(), cfg80211_connect_result(),
+ * cfg80211_connect_timeout(), and cfg80211_connect_done() should be called.
  */
-void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
-			  struct cfg80211_bss *bss, const u8 *req_ie,
-			  size_t req_ie_len, const u8 *resp_ie,
-			  size_t resp_ie_len, int status, gfp_t gfp,
-			  enum nl80211_timeout_reason timeout_reason);
+static inline void
+cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
+		     struct cfg80211_bss *bss, const u8 *req_ie,
+		     size_t req_ie_len, const u8 *resp_ie,
+		     size_t resp_ie_len, int status, gfp_t gfp,
+		     enum nl80211_timeout_reason timeout_reason)
+{
+	struct cfg80211_connect_resp_params params;
+
+	memset(&params, 0, sizeof(params));
+	params.status = status;
+	params.bssid = bssid;
+	params.bss = bss;
+	params.req_ie = req_ie;
+	params.req_ie_len = req_ie_len;
+	params.resp_ie = resp_ie;
+	params.resp_ie_len = resp_ie_len;
+	params.timeout_reason = timeout_reason;
+
+	cfg80211_connect_done(dev, &params, gfp);
+}
 
 /**
  * cfg80211_connect_result - notify cfg80211 of connection result
@@ -5177,7 +5352,8 @@ void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
  * It should be called by the underlying driver once execution of the connection
  * request from connect() has been completed. This is similar to
  * cfg80211_connect_bss() which allows the exact bss entry to be specified. Only
- * one of these functions should be called.
+ * one of the functions among cfg80211_connect_bss(), cfg80211_connect_result(),
+ * cfg80211_connect_timeout(), and cfg80211_connect_done() should be called.
  */
 static inline void
 cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
@@ -5204,7 +5380,9 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
  * in a sequence where no explicit authentication/association rejection was
  * received from the AP. This could happen, e.g., due to not being able to send
  * out the Authentication or Association Request frame or timing out while
- * waiting for the response.
+ * waiting for the response. Only one of the functions among
+ * cfg80211_connect_bss(), cfg80211_connect_result(),
+ * cfg80211_connect_timeout(), and cfg80211_connect_done() should be called.
  */
 static inline void
 cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid,
@@ -5216,51 +5394,46 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid,
 }
 
 /**
- * cfg80211_roamed - notify cfg80211 of roaming
+ * struct cfg80211_roam_info - driver initiated roaming information
  *
- * @dev: network device
  * @channel: the channel of the new AP
- * @bssid: the BSSID of the new AP
+ * @bss: entry of bss to which STA got roamed (may be %NULL if %bssid is set)
+ * @bssid: the BSSID of the new AP (may be %NULL if %bss is set)
  * @req_ie: association request IEs (maybe be %NULL)
  * @req_ie_len: association request IEs length
  * @resp_ie: association response IEs (may be %NULL)
  * @resp_ie_len: assoc response IEs length
- * @gfp: allocation flags
- *
- * It should be called by the underlying driver whenever it roamed
- * from one AP to another while connected.
  */
-void cfg80211_roamed(struct net_device *dev,
-		     struct ieee80211_channel *channel,
-		     const u8 *bssid,
-		     const u8 *req_ie, size_t req_ie_len,
-		     const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp);
+struct cfg80211_roam_info {
+	struct ieee80211_channel *channel;
+	struct cfg80211_bss *bss;
+	const u8 *bssid;
+	const u8 *req_ie;
+	size_t req_ie_len;
+	const u8 *resp_ie;
+	size_t resp_ie_len;
+};
 
 /**
- * cfg80211_roamed_bss - notify cfg80211 of roaming
+ * cfg80211_roamed - notify cfg80211 of roaming
  *
  * @dev: network device
- * @bss: entry of bss to which STA got roamed
- * @req_ie: association request IEs (maybe be %NULL)
- * @req_ie_len: association request IEs length
- * @resp_ie: association response IEs (may be %NULL)
- * @resp_ie_len: assoc response IEs length
+ * @info: information about the new BSS. struct &cfg80211_roam_info.
  * @gfp: allocation flags
  *
- * This is just a wrapper to notify cfg80211 of roaming event with driver
- * passing bss to avoid a race in timeout of the bss entry. It should be
- * called by the underlying driver whenever it roamed from one AP to another
- * while connected. Drivers which have roaming implemented in firmware
- * may use this function to avoid a race in bss entry timeout where the bss
- * entry of the new AP is seen in the driver, but gets timed out by the time
- * it is accessed in __cfg80211_roamed() due to delay in scheduling
+ * This function may be called with the driver passing either the BSSID of the
+ * new AP or passing the bss entry to avoid a race in timeout of the bss entry.
+ * It should be called by the underlying driver whenever it roamed from one AP
+ * to another while connected. Drivers which have roaming implemented in
+ * firmware should pass the bss entry to avoid a race in bss entry timeout where
+ * the bss entry of the new AP is seen in the driver, but gets timed out by the
+ * time it is accessed in __cfg80211_roamed() due to delay in scheduling
  * rdev->event_work. In case of any failures, the reference is released
- * either in cfg80211_roamed_bss() or in __cfg80211_romed(), Otherwise,
- * it will be released while diconneting from the current bss.
+ * either in cfg80211_roamed() or in __cfg80211_romed(), Otherwise, it will be
+ * released while diconneting from the current bss.
  */
-void cfg80211_roamed_bss(struct net_device *dev, struct cfg80211_bss *bss,
-			 const u8 *req_ie, size_t req_ie_len,
-			 const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp);
+void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
+		     gfp_t gfp);
 
 /**
  * cfg80211_disconnected - notify cfg80211 that connection was dropped
diff --git a/include/net/devlink.h b/include/net/devlink.h
index d29e5fc82582..ed7687bbf5d0 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -25,6 +25,8 @@ struct devlink {
 	struct list_head list;
 	struct list_head port_list;
 	struct list_head sb_list;
+	struct list_head dpipe_table_list;
+	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
 	possible_net_t _net;
@@ -49,6 +51,178 @@ struct devlink_sb_pool_info {
 	enum devlink_sb_threshold_type threshold_type;
 };
 
+/**
+ * struct devlink_dpipe_field - dpipe field object
+ * @name: field name
+ * @id: index inside the headers field array
+ * @bitwidth: bitwidth
+ * @mapping_type: mapping type
+ */
+struct devlink_dpipe_field {
+	const char *name;
+	unsigned int id;
+	unsigned int bitwidth;
+	enum devlink_dpipe_field_mapping_type mapping_type;
+};
+
+/**
+ * struct devlink_dpipe_header - dpipe header object
+ * @name: header name
+ * @id: index, global/local detrmined by global bit
+ * @fields: fields
+ * @fields_count: number of fields
+ * @global: indicates if header is shared like most protocol header
+ *	    or driver specific
+ */
+struct devlink_dpipe_header {
+	const char *name;
+	unsigned int id;
+	struct devlink_dpipe_field *fields;
+	unsigned int fields_count;
+	bool global;
+};
+
+/**
+ * struct devlink_dpipe_match - represents match operation
+ * @type: type of match
+ * @header_index: header index (packets can have several headers of same
+ *		  type like in case of tunnels)
+ * @header: header
+ * @fieled_id: field index
+ */
+struct devlink_dpipe_match {
+	enum devlink_dpipe_match_type type;
+	unsigned int header_index;
+	struct devlink_dpipe_header *header;
+	unsigned int field_id;
+};
+
+/**
+ * struct devlink_dpipe_action - represents action operation
+ * @type: type of action
+ * @header_index: header index (packets can have several headers of same
+ *		  type like in case of tunnels)
+ * @header: header
+ * @fieled_id: field index
+ */
+struct devlink_dpipe_action {
+	enum devlink_dpipe_action_type type;
+	unsigned int header_index;
+	struct devlink_dpipe_header *header;
+	unsigned int field_id;
+};
+
+/**
+ * struct devlink_dpipe_value - represents value of match/action
+ * @action: action
+ * @match: match
+ * @mapping_value: in case the field has some mapping this value
+ *                 specified the mapping value
+ * @mapping_valid: specify if mapping value is valid
+ * @value_size: value size
+ * @value: value
+ * @mask: bit mask
+ */
+struct devlink_dpipe_value {
+	union {
+		struct devlink_dpipe_action *action;
+		struct devlink_dpipe_match *match;
+	};
+	unsigned int mapping_value;
+	bool mapping_valid;
+	unsigned int value_size;
+	void *value;
+	void *mask;
+};
+
+/**
+ * struct devlink_dpipe_entry - table entry object
+ * @index: index of the entry in the table
+ * @match_values: match values
+ * @matche_values_count: count of matches tuples
+ * @action_values: actions values
+ * @action_values_count: count of actions values
+ * @counter: value of counter
+ * @counter_valid: Specify if value is valid from hardware
+ */
+struct devlink_dpipe_entry {
+	u64 index;
+	struct devlink_dpipe_value *match_values;
+	unsigned int match_values_count;
+	struct devlink_dpipe_value *action_values;
+	unsigned int action_values_count;
+	u64 counter;
+	bool counter_valid;
+};
+
+/**
+ * struct devlink_dpipe_dump_ctx - context provided to driver in order
+ *				   to dump
+ * @info: info
+ * @cmd: devlink command
+ * @skb: skb
+ * @nest: top attribute
+ * @hdr: hdr
+ */
+struct devlink_dpipe_dump_ctx {
+	struct genl_info *info;
+	enum devlink_command cmd;
+	struct sk_buff *skb;
+	struct nlattr *nest;
+	void *hdr;
+};
+
+struct devlink_dpipe_table_ops;
+
+/**
+ * struct devlink_dpipe_table - table object
+ * @priv: private
+ * @name: table name
+ * @size: maximum number of entries
+ * @counters_enabled: indicates if counters are active
+ * @counter_control_extern: indicates if counter control is in dpipe or
+ *			    external tool
+ * @table_ops: table operations
+ * @rcu: rcu
+ */
+struct devlink_dpipe_table {
+	void *priv;
+	struct list_head list;
+	const char *name;
+	u64 size;
+	bool counters_enabled;
+	bool counter_control_extern;
+	struct devlink_dpipe_table_ops *table_ops;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct devlink_dpipe_table_ops - dpipe_table ops
+ * @actions_dump - dumps all tables actions
+ * @matches_dump - dumps all tables matches
+ * @entries_dump - dumps all active entries in the table
+ * @counters_set_update - when changing the counter status hardware sync
+ *			  maybe needed to allocate/free counter related
+ *			  resources
+ */
+struct devlink_dpipe_table_ops {
+	int (*actions_dump)(void *priv, struct sk_buff *skb);
+	int (*matches_dump)(void *priv, struct sk_buff *skb);
+	int (*entries_dump)(void *priv, bool counters_enabled,
+			    struct devlink_dpipe_dump_ctx *dump_ctx);
+	int (*counters_set_update)(void *priv, bool enable);
+};
+
+/**
+ * struct devlink_dpipe_headers - dpipe headers
+ * @headers - header array can be shared (global bit) or driver specific
+ * @headers_count - count of headers
+ */
+struct devlink_dpipe_headers {
+	struct devlink_dpipe_header **headers;
+	unsigned int headers_count;
+};
+
 struct devlink_ops {
 	int (*port_type_set)(struct devlink_port *devlink_port,
 			     enum devlink_port_type port_type);
@@ -94,6 +268,8 @@ struct devlink_ops {
 	int (*eswitch_mode_set)(struct devlink *devlink, u16 mode);
 	int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode);
 	int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode);
+	int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode);
+	int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
@@ -132,6 +308,26 @@ int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u16 egress_pools_count, u16 ingress_tc_count,
 			u16 egress_tc_count);
 void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index);
+int devlink_dpipe_table_register(struct devlink *devlink,
+				 const char *table_name,
+				 struct devlink_dpipe_table_ops *table_ops,
+				 void *priv, u64 size,
+				 bool counter_control_extern);
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+				    const char *table_name);
+int devlink_dpipe_headers_register(struct devlink *devlink,
+				   struct devlink_dpipe_headers *dpipe_headers);
+void devlink_dpipe_headers_unregister(struct devlink *devlink);
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+					 const char *table_name);
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx);
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+				   struct devlink_dpipe_entry *entry);
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx);
+int devlink_dpipe_action_put(struct sk_buff *skb,
+			     struct devlink_dpipe_action *action);
+int devlink_dpipe_match_put(struct sk_buff *skb,
+			    struct devlink_dpipe_match *match);
 
 #else
 
@@ -200,6 +396,71 @@ static inline void devlink_sb_unregister(struct devlink *devlink,
 {
 }
 
+static inline int
+devlink_dpipe_table_register(struct devlink *devlink,
+			     const char *table_name,
+			     struct devlink_dpipe_table_ops *table_ops,
+			     void *priv, u64 size,
+			     bool counter_control_extern)
+{
+	return 0;
+}
+
+static inline void devlink_dpipe_table_unregister(struct devlink *devlink,
+						  const char *table_name)
+{
+}
+
+static inline int devlink_dpipe_headers_register(struct devlink *devlink,
+						 struct devlink_dpipe_headers *
+						 dpipe_headers)
+{
+	return 0;
+}
+
+static inline void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+}
+
+static inline bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+						       const char *table_name)
+{
+	return false;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+			       struct devlink_dpipe_entry *entry)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_action_put(struct sk_buff *skb,
+			 struct devlink_dpipe_action *action)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_match_put(struct sk_buff *skb,
+			struct devlink_dpipe_match *match)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4e13e695f025..8e24677b1c62 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -19,6 +19,7 @@
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/ethtool.h>
+#include <net/devlink.h>
 
 struct tc_action;
 struct phy_device;
@@ -31,6 +32,8 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_EDSA,
 	DSA_TAG_PROTO_BRCM,
 	DSA_TAG_PROTO_QCA,
+	DSA_TAG_PROTO_MTK,
+	DSA_TAG_PROTO_LAN9303,
 	DSA_TAG_LAST,		/* MUST BE LAST */
 };
 
@@ -122,7 +125,7 @@ struct dsa_switch_tree {
 	 * protocol to use.
 	 */
 	struct net_device	*master_netdev;
-	int			(*rcv)(struct sk_buff *skb,
+	struct sk_buff *	(*rcv)(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct packet_type *pt,
 				       struct net_device *orig_dev);
@@ -182,6 +185,7 @@ struct dsa_port {
 	unsigned int		ageing_time;
 	u8			stp_state;
 	struct net_device	*bridge_dev;
+	struct devlink_port	devlink_port;
 };
 
 struct dsa_switch {
@@ -233,6 +237,13 @@ struct dsa_switch {
 	u32			phys_mii_mask;
 	struct mii_bus		*slave_mii_bus;
 
+	/* Ageing Time limits in msecs */
+	unsigned int ageing_time_min;
+	unsigned int ageing_time_max;
+
+	/* devlink used to represent this switch device */
+	struct devlink		*devlink;
+
 	/* Dynamically allocated ports, keep last */
 	size_t num_ports;
 	struct dsa_port ports[];
@@ -248,6 +259,11 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
 	return !!((ds->dsa_port_mask) & (1 << p));
 }
 
+static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p)
+{
+	return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p);
+}
+
 static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
 {
 	return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev;
@@ -287,7 +303,7 @@ struct dsa_notifier_bridge_info {
 
 struct dsa_switch_ops {
 	/*
-	 * Probing and setup.
+	 * Legacy probing.
 	 */
 	const char	*(*probe)(struct device *dsa_dev,
 				  struct device *host_dev, int sw_addr,
@@ -442,6 +458,14 @@ struct dsa_switch_ops {
 				   bool ingress);
 	void	(*port_mirror_del)(struct dsa_switch *ds, int port,
 				   struct dsa_mall_mirror_tc_entry *mirror);
+
+	/*
+	 * Cross-chip operations
+	 */
+	int	(*crosschip_bridge_join)(struct dsa_switch *ds, int sw_index,
+					 int port, struct net_device *br);
+	void	(*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index,
+					  int port, struct net_device *br);
 };
 
 struct dsa_switch_driver {
@@ -449,9 +473,11 @@ struct dsa_switch_driver {
 	const struct dsa_switch_ops *ops;
 };
 
+/* Legacy driver registration */
 void register_switch_driver(struct dsa_switch_driver *type);
 void unregister_switch_driver(struct dsa_switch_driver *type);
 struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev);
+
 struct net_device *dsa_dev_to_net_device(struct device *dev);
 
 static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
@@ -459,6 +485,15 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
 	return dst->rcv != NULL;
 }
 
+static inline bool netdev_uses_dsa(struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	if (dev->dsa_ptr != NULL)
+		return dsa_uses_tagged_protocol(dev->dsa_ptr);
+#endif
+	return false;
+}
+
 struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n);
 void dsa_unregister_switch(struct dsa_switch *ds);
 int dsa_register_switch(struct dsa_switch *ds, struct device *dev);
diff --git a/include/net/esp.h b/include/net/esp.h
index a43be85aedc4..c41994d1bfef 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -10,4 +10,23 @@ static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb)
 	return (struct ip_esp_hdr *)skb_transport_header(skb);
 }
 
+struct esp_info {
+	struct	ip_esp_hdr *esph;
+	__be64	seqno;
+	int	tfclen;
+	int	tailen;
+	int	plen;
+	int	clen;
+	int 	len;
+	int 	nfrags;
+	__u8	proto;
+	bool	inplace;
+};
+
+int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp_input_done2(struct sk_buff *skb, int err);
+int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp);
+int esp6_input_done2(struct sk_buff *skb, int err);
 #endif
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 8dbfdf728cd8..76c7300626d6 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -141,7 +141,10 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
 		     struct fib_lookup_arg *);
 int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
 			 u32 flags);
+bool fib_rule_matchall(const struct fib_rule *rule);
 
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+		   struct netlink_ext_ack *extack);
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+		   struct netlink_ext_ack *extack);
 #endif
diff --git a/include/net/flow.h b/include/net/flow.h
index 6984f1913dc1..bae198b3039e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -202,7 +202,7 @@ static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
 
 typedef unsigned long flow_compare_t;
 
-static inline size_t flow_key_size(u16 family)
+static inline unsigned int flow_key_size(u16 family)
 {
 	switch (family) {
 	case AF_INET:
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index ac9703018a3a..8d21d448daa9 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -41,6 +41,13 @@ struct flow_dissector_key_vlan {
 	u16	padding;
 };
 
+struct flow_dissector_key_mpls {
+	u32	mpls_ttl:8,
+		mpls_bos:1,
+		mpls_tc:3,
+		mpls_label:20;
+};
+
 struct flow_dissector_key_keyid {
 	__be32	keyid;
 };
@@ -169,6 +176,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
 	FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */
 	FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */
+	FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };
diff --git a/include/net/flowcache.h b/include/net/flowcache.h
index 9caf3bfc8d2d..51eb971e8973 100644
--- a/include/net/flowcache.h
+++ b/include/net/flowcache.h
@@ -8,7 +8,7 @@
 
 struct flow_cache_percpu {
 	struct hlist_head		*hash_table;
-	int				hash_count;
+	unsigned int			hash_count;
 	u32				hash_rnd;
 	int				hash_rnd_recalc;
 	struct tasklet_struct		flush_tasklet;
@@ -18,8 +18,8 @@ struct flow_cache {
 	u32				hash_shift;
 	struct flow_cache_percpu __percpu *percpu;
 	struct hlist_node		node;
-	int				low_watermark;
-	int				high_watermark;
+	unsigned int			low_watermark;
+	unsigned int			high_watermark;
 	struct timer_list		rnd_timer;
 };
 #endif	/* _NET_FLOWCACHE_H */
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index a34275be3600..68b88192b00c 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -84,6 +84,7 @@ struct nlattr **genl_family_attrbuf(const struct genl_family *family);
  * @attrs: netlink attributes
  * @_net: network namespace
  * @user_ptr: user pointers
+ * @extack: extended ACK report struct
  */
 struct genl_info {
 	u32			snd_seq;
@@ -94,6 +95,7 @@ struct genl_info {
 	struct nlattr **	attrs;
 	possible_net_t		_net;
 	void *			user_ptr[2];
+	struct netlink_ext_ack *extack;
 };
 
 static inline struct net *genl_info_net(struct genl_info *info)
@@ -106,6 +108,16 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net)
 	write_pnet(&info->_net, net);
 }
 
+#define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg)
+
+static inline int genl_err_attr(struct genl_info *info, int err,
+				struct nlattr *attr)
+{
+	info->extack->bad_attr = attr;
+
+	return err;
+}
+
 /**
  * struct genl_ops - generic netlink operations
  * @cmd: command identifier
@@ -162,14 +174,16 @@ genlmsg_nlhdr(void *user_hdr, const struct genl_family *family)
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
- * */
+ * @extack: extended ACK report struct
+ */
 static inline int genlmsg_parse(const struct nlmsghdr *nlh,
 				const struct genl_family *family,
 				struct nlattr *tb[], int maxtype,
-				const struct nla_policy *policy)
+				const struct nla_policy *policy,
+				struct netlink_ext_ack *extack)
 {
 	return nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype,
-			   policy);
+			   policy, extack);
 }
 
 /**
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index b7952d55b9c0..f39ae697347f 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -20,7 +20,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 			  int addr_len, int flags, int is_sendmsg);
 int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags);
-int inet_accept(struct socket *sock, struct socket *newsock, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+		bool kern);
 int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
 ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
 		      size_t size, int flags);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 826f198374f8..c7a577976bec 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -258,7 +258,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
         return (unsigned long)min_t(u64, when, max_when);
 }
 
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
 
 int inet_csk_get_port(struct sock *sk, unsigned short snum);
 
diff --git a/include/net/ip.h b/include/net/ip.h
index bf264a8db1ce..821cedcc8e73 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,8 @@
 #include <net/flow.h>
 #include <net/flow_dissector.h>
 
+#define IPV4_MAX_PMTU		65535U		/* RFC 2675, Section 5.1 */
+
 struct sock;
 
 struct inet_skb_parm {
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 1b1cf33cbfb0..08fbc7f7d8d7 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -33,6 +33,8 @@ struct __ip6_tnl_parm {
 	__be16			o_flags;
 	__be32			i_key;
 	__be32			o_key;
+
+	__u32			fwmark;
 };
 
 /* IPv6 tunnel */
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 368bb4024b78..6692c5758b33 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -213,6 +213,11 @@ struct fib_entry_notifier_info {
 	u32 tb_id;
 };
 
+struct fib_rule_notifier_info {
+	struct fib_notifier_info info; /* must be first */
+	struct fib_rule *rule;
+};
+
 struct fib_nh_notifier_info {
 	struct fib_notifier_info info; /* must be first */
 	struct fib_nh *fib_nh;
@@ -232,9 +237,21 @@ enum fib_event_type {
 int register_fib_notifier(struct notifier_block *nb,
 			  void (*cb)(struct notifier_block *nb));
 int unregister_fib_notifier(struct notifier_block *nb);
+int call_fib_notifier(struct notifier_block *nb, struct net *net,
+		      enum fib_event_type event_type,
+		      struct fib_notifier_info *info);
 int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
 		       struct fib_notifier_info *info);
 
+void fib_notify(struct net *net, struct notifier_block *nb);
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+void fib_rules_notify(struct net *net, struct notifier_block *nb);
+#else
+static inline void fib_rules_notify(struct net *net, struct notifier_block *nb)
+{
+}
+#endif
+
 struct fib_table {
 	struct hlist_node	tb_hlist;
 	u32			tb_id;
@@ -299,6 +316,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 	return err;
 }
 
+static inline bool fib4_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
+
 #else /* CONFIG_IP_MULTIPLE_TABLES */
 int __net_init fib4_rules_init(struct net *net);
 void __net_exit fib4_rules_exit(struct net *net);
@@ -343,6 +365,8 @@ out:
 	return err;
 }
 
+bool fib4_rule_default(const struct fib_rule *rule);
+
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 /* Exported by fib_frontend.c */
@@ -371,17 +395,13 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
 int fib_sync_down_addr(struct net_device *dev, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 
-extern u32 fib_multipath_secret __read_mostly;
-
-static inline int fib_multipath_hash(__be32 saddr, __be32 daddr)
-{
-	return jhash_2words((__force u32)saddr, (__force u32)daddr,
-			    fib_multipath_secret) >> 1;
-}
-
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+		       const struct sk_buff *skb);
+#endif
 void fib_select_multipath(struct fib_result *res, int hash);
 void fib_select_path(struct net *net, struct fib_result *res,
-		     struct flowi4 *fl4, int mp_hash);
+		     struct flowi4 *fl4, const struct sk_buff *skb);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 95056796657c..520809912f03 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -132,6 +132,7 @@ struct ip_tunnel {
 	unsigned int		prl_count;	/* # of entries in PRL */
 	unsigned int		ip_tnl_net_id;
 	struct gro_cells	gro_cells;
+	__u32			fwmark;
 	bool			collect_md;
 	bool			ignore_df;
 };
@@ -273,9 +274,9 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error);
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
-			 struct ip_tunnel_parm *p);
+			 struct ip_tunnel_parm *p, __u32 fwmark);
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
-		      struct ip_tunnel_parm *p);
+		      struct ip_tunnel_parm *p, __u32 fwmark);
 void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
 
 struct ip_tunnel_encap_ops {
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7bdfa7d78363..4f4f786255ef 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -12,6 +12,8 @@
 #include <linux/list.h>                 /* for struct list_head */
 #include <linux/spinlock.h>             /* for struct rwlock_t */
 #include <linux/atomic.h>               /* for struct atomic_t */
+#include <linux/refcount.h>             /* for struct refcount_t */
+
 #include <linux/compiler.h>
 #include <linux/timer.h>
 #include <linux/bug.h>
@@ -525,7 +527,7 @@ struct ip_vs_conn {
 	struct netns_ipvs	*ipvs;
 
 	/* counter and timer */
-	atomic_t		refcnt;		/* reference count */
+	refcount_t		refcnt;		/* reference count */
 	struct timer_list	timer;		/* Expiration timer */
 	volatile unsigned long	timeout;	/* timeout */
 
@@ -667,7 +669,7 @@ struct ip_vs_dest {
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
 
-	atomic_t		refcnt;		/* reference counter */
+	refcount_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */
 	unsigned long		idle_start;	/* start time, jiffies */
 
@@ -1211,14 +1213,14 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
  */
 static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
 {
-	return atomic_inc_not_zero(&cp->refcnt);
+	return refcount_inc_not_zero(&cp->refcnt);
 }
 
 /* put back the conn without restarting its timer */
 static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 {
 	smp_mb__before_atomic();
-	atomic_dec(&cp->refcnt);
+	refcount_dec(&cp->refcnt);
 }
 void ip_vs_conn_put(struct ip_vs_conn *cp);
 void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
@@ -1347,8 +1349,6 @@ int ip_vs_protocol_init(void);
 void ip_vs_protocol_cleanup(void);
 void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
 int *ip_vs_create_timeout_table(int *table, int size);
-int ip_vs_set_state_timeout(int *table, int num, const char *const *names,
-			    const char *name, int to);
 void ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
 			       const struct sk_buff *skb, int offset,
 			       const char *msg);
@@ -1410,18 +1410,18 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
 {
-	atomic_inc(&dest->refcnt);
+	refcount_inc(&dest->refcnt);
 }
 
 static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
 {
 	smp_mb__before_atomic();
-	atomic_dec(&dest->refcnt);
+	refcount_dec(&dest->refcnt);
 }
 
 static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
 {
-	if (atomic_dec_and_test(&dest->refcnt))
+	if (refcount_dec_and_test(&dest->refcnt))
 		kfree(dest);
 }
 
@@ -1553,13 +1553,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-	if (!ct || !nf_ct_is_untracked(ct)) {
-		struct nf_conn *untracked;
-
+	if (ct) {
 		nf_conntrack_put(&ct->ct_general);
-		untracked = nf_ct_untracked_get();
-		nf_conntrack_get(&untracked->ct_general);
-		nf_ct_set(skb, untracked, IP_CT_NEW);
+		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 	}
 #endif
 }
@@ -1618,7 +1614,7 @@ static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
 	if (!(cp->flags & IP_VS_CONN_F_NFCT))
 		return false;
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct && !nf_ct_is_untracked(ct))
+	if (ct)
 		return true;
 #endif
 	return false;
diff --git a/include/net/irda/timer.h b/include/net/irda/timer.h
index cb2615ccf761..d784f242cf7b 100644
--- a/include/net/irda/timer.h
+++ b/include/net/irda/timer.h
@@ -59,7 +59,7 @@ struct lap_cb;
  *  Slot timer must never exceed 85 ms, and must always be at least 25 ms, 
  *  suggested to  75-85 msec by IrDA lite. This doesn't work with a lot of
  *  devices, and other stackes uses a lot more, so it's best we do it as well
- *  (Note : this is the default value and sysctl overides it - Jean II)
+ *  (Note : this is the default value and sysctl overrides it - Jean II)
  */
 #define SLOT_TIMEOUT            (90*HZ/1000)
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a3bab3c5ecfb..4d05a9443344 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5,7 +5,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -299,6 +299,8 @@ struct ieee80211_vif_chanctx_switch {
  *	context had been assigned.
  * @BSS_CHANGED_OCB: OCB join status changed
  * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed
+ * @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected
+ *	keep alive) changed.
  */
 enum ieee80211_bss_change {
 	BSS_CHANGED_ASSOC		= 1<<0,
@@ -325,6 +327,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_BANDWIDTH		= 1<<21,
 	BSS_CHANGED_OCB                 = 1<<22,
 	BSS_CHANGED_MU_GROUPS		= 1<<23,
+	BSS_CHANGED_KEEP_ALIVE		= 1<<24,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
@@ -501,6 +504,10 @@ struct ieee80211_mu_group_data {
  *	implies disabled. As with the cfg80211 callback, a change here should
  *	cause an event to be sent indicating where the current value is in
  *	relation to the newly configured threshold.
+ * @cqm_rssi_low: Connection quality monitor RSSI lower threshold, a zero value
+ *	implies disabled.  This is an alternative mechanism to the single
+ *	threshold event and can't be enabled simultaneously with it.
+ * @cqm_rssi_high: Connection quality monitor RSSI upper threshold.
  * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis
  * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The
  *	may filter ARP queries targeted for other addresses than listed here.
@@ -529,6 +536,13 @@ struct ieee80211_mu_group_data {
  * @allow_p2p_go_ps: indication for AP or P2P GO interface, whether it's allowed
  *	to use P2P PS mechanism or not. AP/P2P GO is not allowed to use P2P PS
  *	if it has associated clients without P2P PS support.
+ * @max_idle_period: the time period during which the station can refrain from
+ *	transmitting frames to its associated AP without being disassociated.
+ *	In units of 1000 TUs. Zero value indicates that the AP did not include
+ *	a (valid) BSS Max Idle Period Element.
+ * @protected_keep_alive: if set, indicates that the station should send an RSN
+ *	protected frame to the AP to reset the idle timer at the AP for the
+ *	station.
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -553,6 +567,8 @@ struct ieee80211_bss_conf {
 	u16 ht_operation_mode;
 	s32 cqm_rssi_thold;
 	u32 cqm_rssi_hyst;
+	s32 cqm_rssi_low;
+	s32 cqm_rssi_high;
 	struct cfg80211_chan_def chandef;
 	struct ieee80211_mu_group_data mu_group;
 	__be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
@@ -567,6 +583,8 @@ struct ieee80211_bss_conf {
 	enum nl80211_tx_power_setting txpower_type;
 	struct ieee80211_p2p_noa_attr p2p_noa_attr;
 	bool allow_p2p_go_ps;
+	u16 max_idle_period;
+	bool protected_keep_alive;
 };
 
 /**
@@ -943,6 +961,19 @@ struct ieee80211_tx_info {
 };
 
 /**
+ * struct ieee80211_tx_status - extended tx staus info for rate control
+ *
+ * @sta: Station that the packet was transmitted for
+ * @info: Basic tx status information
+ * @skb: Packet skb (can be NULL if not provided by the driver)
+ */
+struct ieee80211_tx_status {
+	struct ieee80211_sta *sta;
+	struct ieee80211_tx_info *info;
+	struct sk_buff *skb;
+};
+
+/**
  * struct ieee80211_scan_ies - descriptors for different blocks of IEs
  *
  * This structure is used to point to different blocks of IEs in HW scan
@@ -1039,16 +1070,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	(including FCS) was received.
  * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime
  *	field) is valid and contains the time the SYNC preamble was received.
- * @RX_FLAG_SHORTPRE: Short preamble was used for this frame
- * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index
- * @RX_FLAG_VHT: VHT MCS was used and rate_index is MCS index
- * @RX_FLAG_40MHZ: HT40 (40 MHz) was used
- * @RX_FLAG_SHORT_GI: Short guard interval was used
  * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present.
  *	Valid only for data frames (mainly A-MPDU)
- * @RX_FLAG_HT_GF: This frame was received in a HT-greenfield transmission, if
- *	the driver fills this value it should add %IEEE80211_RADIOTAP_MCS_HAVE_FMT
- *	to hw.radiotap_mcs_details to advertise that fact
  * @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference
  *	number (@ampdu_reference) must be populated and be a distinct number for
  *	each A-MPDU
@@ -1061,7 +1084,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	is stored in the @ampdu_delimiter_crc field)
  * @RX_FLAG_MIC_STRIPPED: The mic was stripped of this packet. Decryption was
  *	done by the hardware
- * @RX_FLAG_LDPC: LDPC was used
  * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without
  *	processing it in any regular way.
  *	This is useful if drivers offload some frames but still want to report
@@ -1070,9 +1092,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	monitor interfaces.
  *	This is useful if drivers offload some frames but still want to report
  *	them for sniffing purposes.
- * @RX_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3
- * @RX_FLAG_10MHZ: 10 MHz (half channel) was used
- * @RX_FLAG_5MHZ: 5 MHz (quarter channel) was used
  * @RX_FLAG_AMSDU_MORE: Some drivers may prefer to report separate A-MSDU
  *	subframes instead of a one huge frame for performance reasons.
  *	All, but the last MSDU from an A-MSDU should have this flag set. E.g.
@@ -1100,50 +1119,54 @@ enum mac80211_rx_flags {
 	RX_FLAG_FAILED_FCS_CRC		= BIT(5),
 	RX_FLAG_FAILED_PLCP_CRC 	= BIT(6),
 	RX_FLAG_MACTIME_START		= BIT(7),
-	RX_FLAG_SHORTPRE		= BIT(8),
-	RX_FLAG_HT			= BIT(9),
-	RX_FLAG_40MHZ			= BIT(10),
-	RX_FLAG_SHORT_GI		= BIT(11),
-	RX_FLAG_NO_SIGNAL_VAL		= BIT(12),
-	RX_FLAG_HT_GF			= BIT(13),
-	RX_FLAG_AMPDU_DETAILS		= BIT(14),
-	RX_FLAG_PN_VALIDATED		= BIT(15),
-	RX_FLAG_DUP_VALIDATED		= BIT(16),
-	RX_FLAG_AMPDU_LAST_KNOWN	= BIT(17),
-	RX_FLAG_AMPDU_IS_LAST		= BIT(18),
-	RX_FLAG_AMPDU_DELIM_CRC_ERROR	= BIT(19),
-	RX_FLAG_AMPDU_DELIM_CRC_KNOWN	= BIT(20),
-	RX_FLAG_MACTIME_END		= BIT(21),
-	RX_FLAG_VHT			= BIT(22),
-	RX_FLAG_LDPC			= BIT(23),
-	RX_FLAG_ONLY_MONITOR		= BIT(24),
-	RX_FLAG_SKIP_MONITOR		= BIT(25),
-	RX_FLAG_STBC_MASK		= BIT(26) | BIT(27),
-	RX_FLAG_10MHZ			= BIT(28),
-	RX_FLAG_5MHZ			= BIT(29),
-	RX_FLAG_AMSDU_MORE		= BIT(30),
-	RX_FLAG_RADIOTAP_VENDOR_DATA	= BIT(31),
-	RX_FLAG_MIC_STRIPPED		= BIT_ULL(32),
-	RX_FLAG_ALLOW_SAME_PN		= BIT_ULL(33),
-	RX_FLAG_ICV_STRIPPED		= BIT_ULL(34),
+	RX_FLAG_NO_SIGNAL_VAL		= BIT(8),
+	RX_FLAG_AMPDU_DETAILS		= BIT(9),
+	RX_FLAG_PN_VALIDATED		= BIT(10),
+	RX_FLAG_DUP_VALIDATED		= BIT(11),
+	RX_FLAG_AMPDU_LAST_KNOWN	= BIT(12),
+	RX_FLAG_AMPDU_IS_LAST		= BIT(13),
+	RX_FLAG_AMPDU_DELIM_CRC_ERROR	= BIT(14),
+	RX_FLAG_AMPDU_DELIM_CRC_KNOWN	= BIT(15),
+	RX_FLAG_MACTIME_END		= BIT(16),
+	RX_FLAG_ONLY_MONITOR		= BIT(17),
+	RX_FLAG_SKIP_MONITOR		= BIT(18),
+	RX_FLAG_AMSDU_MORE		= BIT(19),
+	RX_FLAG_RADIOTAP_VENDOR_DATA	= BIT(20),
+	RX_FLAG_MIC_STRIPPED		= BIT(21),
+	RX_FLAG_ALLOW_SAME_PN		= BIT(22),
+	RX_FLAG_ICV_STRIPPED		= BIT(23),
 };
 
-#define RX_FLAG_STBC_SHIFT		26
-
 /**
- * enum mac80211_rx_vht_flags - receive VHT flags
+ * enum mac80211_rx_encoding_flags - MCS & bandwidth flags
  *
- * These flags are used with the @vht_flag member of
- *	&struct ieee80211_rx_status.
- * @RX_VHT_FLAG_80MHZ: 80 MHz was used
- * @RX_VHT_FLAG_160MHZ: 160 MHz was used
- * @RX_VHT_FLAG_BF: packet was beamformed
- */
+ * @RX_ENC_FLAG_SHORTPRE: Short preamble was used for this frame
+ * @RX_ENC_FLAG_40MHZ: HT40 (40 MHz) was used
+ * @RX_ENC_FLAG_SHORT_GI: Short guard interval was used
+ * @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission,
+ *	if the driver fills this value it should add
+ *	%IEEE80211_RADIOTAP_MCS_HAVE_FMT
+ *	to hw.radiotap_mcs_details to advertise that fact
+ * @RX_ENC_FLAG_LDPC: LDPC was used
+ * @RX_ENC_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3
+ * @RX_ENC_FLAG_BF: packet was beamformed
+ */
+enum mac80211_rx_encoding_flags {
+	RX_ENC_FLAG_SHORTPRE		= BIT(0),
+	RX_ENC_FLAG_40MHZ		= BIT(1),
+	RX_ENC_FLAG_SHORT_GI		= BIT(2),
+	RX_ENC_FLAG_HT_GF		= BIT(3),
+	RX_ENC_FLAG_STBC_MASK		= BIT(4) | BIT(5),
+	RX_ENC_FLAG_LDPC		= BIT(6),
+	RX_ENC_FLAG_BF			= BIT(7),
+};
 
-enum mac80211_rx_vht_flags {
-	RX_VHT_FLAG_80MHZ		= BIT(0),
-	RX_VHT_FLAG_160MHZ		= BIT(1),
-	RX_VHT_FLAG_BF			= BIT(2),
+#define RX_ENC_FLAG_STBC_SHIFT		4
+
+enum mac80211_rx_encoding {
+	RX_ENC_LEGACY = 0,
+	RX_ENC_HT,
+	RX_ENC_VHT,
 };
 
 /**
@@ -1173,9 +1196,11 @@ enum mac80211_rx_vht_flags {
  * @antenna: antenna used
  * @rate_idx: index of data rate into band's supported rates or MCS index if
  *	HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT)
- * @vht_nss: number of streams (VHT only)
+ * @nss: number of streams (VHT and HE only)
  * @flag: %RX_FLAG_\*
- * @vht_flag: %RX_VHT_FLAG_\*
+ * @encoding: &enum mac80211_rx_encoding
+ * @bw: &enum rate_info_bw
+ * @enc_flags: uses bits from &enum mac80211_rx_encoding_flags
  * @rx_flags: internal RX flags for mac80211
  * @ampdu_reference: A-MPDU reference number, must be a different value for
  *	each A-MPDU but the same for each subframe within one A-MPDU
@@ -1186,11 +1211,12 @@ struct ieee80211_rx_status {
 	u64 boottime_ns;
 	u32 device_timestamp;
 	u32 ampdu_reference;
-	u64 flag;
+	u32 flag;
 	u16 freq;
-	u8 vht_flag;
+	u8 enc_flags;
+	u8 encoding:2, bw:3;
 	u8 rate_idx;
-	u8 vht_nss;
+	u8 nss;
 	u8 rx_flags;
 	u8 band;
 	u8 antenna;
@@ -4200,6 +4226,23 @@ void ieee80211_tx_status(struct ieee80211_hw *hw,
 			 struct sk_buff *skb);
 
 /**
+ * ieee80211_tx_status_ext - extended transmit status callback
+ *
+ * This function can be used as a replacement for ieee80211_tx_status
+ * in drivers that may want to provide extra information that does not
+ * fit into &struct ieee80211_tx_info.
+ *
+ * Calls to this function for a single hardware must be synchronized
+ * against each other. Calls to this function, ieee80211_tx_status_ni()
+ * and ieee80211_tx_status_irqsafe() may not be mixed for a single hardware.
+ *
+ * @hw: the hardware the frame was transmitted by
+ * @status: tx status information
+ */
+void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
+			     struct ieee80211_tx_status *status);
+
+/**
  * ieee80211_tx_status_noskb - transmit status callback without skb
  *
  * This function can be used as a replacement for ieee80211_tx_status
@@ -4215,9 +4258,17 @@ void ieee80211_tx_status(struct ieee80211_hw *hw,
  *	(NULL for multicast packets)
  * @info: tx status information
  */
-void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
-			       struct ieee80211_sta *sta,
-			       struct ieee80211_tx_info *info);
+static inline void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
+					     struct ieee80211_sta *sta,
+					     struct ieee80211_tx_info *info)
+{
+	struct ieee80211_tx_status status = {
+		.sta = sta,
+		.info = info,
+	};
+
+	ieee80211_tx_status_ext(hw, &status);
+}
 
 /**
  * ieee80211_tx_status_ni - transmit status callback (in process context)
@@ -5438,9 +5489,6 @@ void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif,
  *	RTS threshold
  * @short_preamble: whether mac80211 will request short-preamble transmission
  *	if the selected rate supports it
- * @max_rate_idx: user-requested maximum (legacy) rate
- *	(deprecated; this will be removed once drivers get updated to use
- *	rate_idx_mask)
  * @rate_idx_mask: user-requested (legacy) rate mask
  * @rate_idx_mcs_mask: user-requested MCS rate mask (NULL if not in use)
  * @bss: whether this frame is sent out in AP or IBSS mode
@@ -5452,7 +5500,6 @@ struct ieee80211_tx_rate_control {
 	struct sk_buff *skb;
 	struct ieee80211_tx_rate reported_rate;
 	bool rts, short_preamble;
-	u8 max_rate_idx;
 	u32 rate_idx_mask;
 	u8 *rate_idx_mcs_mask;
 	bool bss;
@@ -5474,10 +5521,9 @@ struct rate_control_ops {
 	void (*free_sta)(void *priv, struct ieee80211_sta *sta,
 			 void *priv_sta);
 
-	void (*tx_status_noskb)(void *priv,
-				struct ieee80211_supported_band *sband,
-				struct ieee80211_sta *sta, void *priv_sta,
-				struct ieee80211_tx_info *info);
+	void (*tx_status_ext)(void *priv,
+			      struct ieee80211_supported_band *sband,
+			      void *priv_sta, struct ieee80211_tx_status *st);
 	void (*tx_status)(void *priv, struct ieee80211_supported_band *sband,
 			  struct ieee80211_sta *sta, void *priv_sta,
 			  struct sk_buff *skb);
diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h
index 179253f9dcfd..9d22bf67ac86 100644
--- a/include/net/mpls_iptunnel.h
+++ b/include/net/mpls_iptunnel.h
@@ -14,11 +14,12 @@
 #ifndef _NET_MPLS_IPTUNNEL_H
 #define _NET_MPLS_IPTUNNEL_H 1
 
-#define MAX_NEW_LABELS 2
-
 struct mpls_iptunnel_encap {
-	u32	label[MAX_NEW_LABELS];
 	u8	labels;
+	u8	ttl_propagate;
+	u8	default_ttl;
+	u8	reserved1;
+	u32	label[0];
 };
 
 static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 8a0214654b6b..1036c902d2c9 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -439,8 +439,10 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
  *	IGMP
  */
 int igmp6_init(void);
+int igmp6_late_init(void);
 
 void igmp6_cleanup(void);
+void igmp6_late_cleanup(void);
 
 int igmp6_event_query(struct sk_buff *skb);
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 5ebf69491160..e4dd3a214034 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -314,7 +314,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl,
 }
 void neigh_destroy(struct neighbour *neigh);
 int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
-int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags);
+int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags,
+		 u32 nlmsg_pid);
 void __neigh_set_probe_once(struct neighbour *neigh);
 void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
 int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
@@ -449,7 +450,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
 {
 	unsigned int seq;
-	int hh_len;
+	unsigned int hh_len;
 
 	do {
 		seq = read_seqbegin(&hh->hh_lock);
@@ -458,7 +459,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 			/* this is inlined by gcc */
 			memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
 		} else {
-			int hh_alen = HH_DATA_ALIGN(hh_len);
+			unsigned int hh_alen = HH_DATA_ALIGN(hh_len);
 
 			memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
 		}
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index af8fe8a909dc..fe80bb48ab1f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -27,6 +27,7 @@
 #include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
 #include <net/netns/mpls.h>
+#include <net/netns/can.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
@@ -141,6 +142,9 @@ struct net {
 #if IS_ENABLED(CONFIG_MPLS)
 	struct netns_mpls	mpls;
 #endif
+#if IS_ENABLED(CONFIG_CAN)
+	struct netns_can	can;
+#endif
 	struct sock		*diag_nlsk;
 	atomic_t		fnhe_genid;
 };
diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
index 6ff32815641b..919e4e8af327 100644
--- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
@@ -14,7 +14,6 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
 
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;
 #ifdef CONFIG_NF_CT_PROTO_DCCP
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4;
diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
index c59b82456f89..eaea968f8657 100644
--- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
@@ -5,7 +5,6 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6;
 
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6;
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6;
 #ifdef CONFIG_NF_CT_PROTO_DCCP
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index f540f9ad2af4..8ece3612d0cd 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -50,25 +50,6 @@ union nf_conntrack_expect_proto {
 #define NF_CT_ASSERT(x)
 #endif
 
-struct nf_conntrack_helper;
-
-/* Must be kept in sync with the classes defined by helpers */
-#define NF_CT_MAX_EXPECT_CLASSES	4
-
-/* nf_conn feature for connections that have a helper */
-struct nf_conn_help {
-	/* Helper. if any */
-	struct nf_conntrack_helper __rcu *helper;
-
-	struct hlist_head expectations;
-
-	/* Current number of expected connections */
-	u8 expecting[NF_CT_MAX_EXPECT_CLASSES];
-
-	/* private helper information. */
-	char data[];
-};
-
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 
@@ -243,14 +224,6 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 			       enum ip_conntrack_dir dir,
 			       u32 seq);
 
-/* Fake conntrack entry for untracked connections */
-DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
-static inline struct nf_conn *nf_ct_untracked_get(void)
-{
-	return raw_cpu_ptr(&nf_conntrack_untracked);
-}
-void nf_ct_untracked_status_or(unsigned long bits);
-
 /* Iterate over all conntracks: if iter returns true, it's deleted. */
 void nf_ct_iterate_cleanup(struct net *net,
 			   int (*iter)(struct nf_conn *i, void *data),
@@ -281,11 +254,6 @@ static inline int nf_ct_is_dying(const struct nf_conn *ct)
 	return test_bit(IPS_DYING_BIT, &ct->status);
 }
 
-static inline int nf_ct_is_untracked(const struct nf_conn *ct)
-{
-	return test_bit(IPS_UNTRACKED_BIT, &ct->status);
-}
-
 /* Packet is received from loopback */
 static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 {
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 84ec7ca5f195..81d7f8a30945 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -65,7 +65,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
 	struct nf_conn *ct = (struct nf_conn *)skb_nfct(skb);
 	int ret = NF_ACCEPT;
 
-	if (ct && !nf_ct_is_untracked(ct)) {
+	if (ct) {
 		if (!nf_ct_is_confirmed(ct))
 			ret = __nf_conntrack_confirm(skb);
 		if (likely(ret == NF_ACCEPT))
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 12d967b58726..2a10c6570fcc 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -20,11 +20,11 @@ enum nf_ct_ecache_state {
 
 struct nf_conntrack_ecache {
 	unsigned long cache;		/* bitops want long */
-	unsigned long missed;		/* missed events */
+	u16 missed;			/* missed events */
 	u16 ctmask;			/* bitmask of ct events to be delivered */
 	u16 expmask;			/* bitmask of expect events to be delivered */
+	enum nf_ct_ecache_state state:8;/* ecache state */
 	u32 portid;			/* netlink portid of destroyer */
-	enum nf_ct_ecache_state state;	/* ecache state */
 };
 
 static inline struct nf_conntrack_ecache *
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 5ed33ea4718e..2ba54feaccd8 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -5,6 +5,8 @@
 #ifndef _NF_CONNTRACK_EXPECT_H
 #define _NF_CONNTRACK_EXPECT_H
 
+#include <linux/refcount.h>
+
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
@@ -37,7 +39,7 @@ struct nf_conntrack_expect {
 	struct timer_list timeout;
 
 	/* Usage count. */
-	atomic_t use;
+	refcount_t use;
 
 	/* Flags */
 	unsigned int flags;
@@ -71,6 +73,7 @@ struct nf_conntrack_expect_policy {
 };
 
 #define NF_CT_EXPECT_CLASS_DEFAULT	0
+#define NF_CT_EXPECT_MAX_CNT		255
 
 int nf_conntrack_expect_pernet_init(struct net *net);
 void nf_conntrack_expect_pernet_fini(struct net *net);
@@ -102,6 +105,7 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
 
 void nf_ct_remove_expectations(struct nf_conn *ct);
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp);
+bool nf_ct_remove_expect(struct nf_conntrack_expect *exp);
 
 /* Allocate space for an expectation: this is mandatory before calling
    nf_ct_expect_related.  You will have to call put afterwards. */
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 1c3035dda31f..4944bc9153cf 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -43,8 +43,8 @@ enum nf_ct_ext_id {
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
 	struct rcu_head rcu;
-	u16 offset[NF_CT_EXT_NUM];
-	u16 len;
+	u8 offset[NF_CT_EXT_NUM];
+	u8 len;
 	char data[0];
 };
 
@@ -69,12 +69,7 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)
 	((id##_TYPE *)__nf_ct_ext_find((ext), (id)))
 
 /* Destroy all relationships */
-void __nf_ct_ext_destroy(struct nf_conn *ct);
-static inline void nf_ct_ext_destroy(struct nf_conn *ct)
-{
-	if (ct->ext)
-		__nf_ct_ext_destroy(ct);
-}
+void nf_ct_ext_destroy(struct nf_conn *ct);
 
 /* Free operation. If you want to free a object referred from private area,
  * please implement __nf_ct_ext_free() and call it.
@@ -86,15 +81,7 @@ static inline void nf_ct_ext_free(struct nf_conn *ct)
 }
 
 /* Add this type, returns pointer to data or NULL. */
-void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
-			     size_t var_alloc_len, gfp_t gfp);
-
-#define nf_ct_ext_add(ct, id, gfp) \
-	((id##_TYPE *)__nf_ct_ext_add_length((ct), (id), 0, (gfp)))
-#define nf_ct_ext_add_length(ct, id, len, gfp) \
-	((id##_TYPE *)__nf_ct_ext_add_length((ct), (id), (len), (gfp)))
-
-#define NF_CT_EXT_F_PREALLOC	0x0001
+void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
 
 struct nf_ct_ext_type {
 	/* Destroys relationships (can be NULL). */
@@ -102,15 +89,11 @@ struct nf_ct_ext_type {
 
 	enum nf_ct_ext_id id;
 
-	unsigned int flags;
-
 	/* Length and min alignment. */
 	u8 len;
 	u8 align;
-	/* initial size of nf_ct_ext. */
-	u8 alloc_size;
 };
 
-int nf_ct_extend_register(struct nf_ct_ext_type *type);
-void nf_ct_extend_unregister(struct nf_ct_ext_type *type);
+int nf_ct_extend_register(const struct nf_ct_ext_type *type);
+void nf_ct_extend_unregister(const struct nf_ct_ext_type *type);
 #endif /* _NF_CONNTRACK_EXTEND_H */
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 1eaac1f4cd6a..e04fa7691e5d 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -29,9 +29,6 @@ struct nf_conntrack_helper {
 	struct module *me;		/* pointer to self */
 	const struct nf_conntrack_expect_policy *expect_policy;
 
-	/* length of internal data, ie. sizeof(struct nf_ct_*_master) */
-	size_t data_len;
-
 	/* Tuple of things we will help (compared against server response) */
 	struct nf_conntrack_tuple tuple;
 
@@ -49,9 +46,33 @@ struct nf_conntrack_helper {
 	unsigned int expect_class_max;
 
 	unsigned int flags;
-	unsigned int queue_num;		/* For user-space helpers. */
+
+	/* For user-space helpers: */
+	unsigned int queue_num;
+	/* length of userspace private data stored in nf_conn_help->data */
+	u16 data_len;
 };
 
+/* Must be kept in sync with the classes defined by helpers */
+#define NF_CT_MAX_EXPECT_CLASSES	4
+
+/* nf_conn feature for connections that have a helper */
+struct nf_conn_help {
+	/* Helper. if any */
+	struct nf_conntrack_helper __rcu *helper;
+
+	struct hlist_head expectations;
+
+	/* Current number of expected connections */
+	u8 expecting[NF_CT_MAX_EXPECT_CLASSES];
+
+	/* private helper information. */
+	char data[32] __aligned(8);
+};
+
+#define NF_CT_HELPER_BUILD_BUG_ON(structsize) \
+	BUILD_BUG_ON((structsize) > FIELD_SIZEOF(struct nf_conn_help, data))
+
 struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name,
 						       u16 l3num, u8 protonum);
 
@@ -62,7 +83,7 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 		       u16 l3num, u16 protonum, const char *name,
 		       u16 default_port, u16 spec_port, u32 id,
 		       const struct nf_conntrack_expect_policy *exp_pol,
-		       u32 expect_class_max, u32 data_len,
+		       u32 expect_class_max,
 		       int (*help)(struct sk_buff *skb, unsigned int protoff,
 				   struct nf_conn *ct,
 				   enum ip_conntrack_info ctinfo),
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 85e993e278d5..7032e044bbe2 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -58,6 +58,9 @@ struct nf_conntrack_l4proto {
 		     unsigned int dataoff,
 		     u_int8_t pf, unsigned int hooknum);
 
+	/* called by gc worker if table is full */
+	bool (*can_early_drop)(const struct nf_conn *ct);
+
 	/* Print out the per-protocol part of the tuple. Return like seq_* */
 	void (*print_tuple)(struct seq_file *s,
 			    const struct nf_conntrack_tuple *);
diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h
index b0ca402c1f72..a2fcb5271726 100644
--- a/include/net/netfilter/nf_conntrack_synproxy.h
+++ b/include/net/netfilter/nf_conntrack_synproxy.h
@@ -52,6 +52,8 @@ struct synproxy_stats {
 struct synproxy_net {
 	struct nf_conn			*tmpl;
 	struct synproxy_stats __percpu	*stats;
+	unsigned int			hook_ref4;
+	unsigned int			hook_ref6;
 };
 
 extern unsigned int synproxy_net_id;
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 5cc5e9e6171a..d40b89355fdd 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -4,6 +4,7 @@
 #include <net/net_namespace.h>
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <linux/refcount.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
@@ -12,7 +13,7 @@
 struct ctnl_timeout {
 	struct list_head	head;
 	struct rcu_head		rcu_head;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	char			name[CTNL_TIMEOUT_NAME_MAX];
 	__u16			l3num;
 	struct nf_conntrack_l4proto *l4proto;
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index c327a431a6f3..05c82a1a4267 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -67,7 +67,7 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum,
 {
 #if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \
     IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6)
-	return nat->masq_index && hooknum == NF_INET_POST_ROUTING &&
+	return nat && nat->masq_index && hooknum == NF_INET_POST_ROUTING &&
 	       CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL &&
 	       nat->masq_index != out->ifindex;
 #else
diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h
index 01bcc6bfbcc9..fbfa5acf4f14 100644
--- a/include/net/netfilter/nf_nat_helper.h
+++ b/include/net/netfilter/nf_nat_helper.h
@@ -7,31 +7,31 @@
 struct sk_buff;
 
 /* These return true or false. */
-int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct,
-			       enum ip_conntrack_info ctinfo,
-			       unsigned int protoff, unsigned int match_offset,
-			       unsigned int match_len, const char *rep_buffer,
-			       unsigned int rep_len, bool adjust);
+bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo,
+				unsigned int protoff, unsigned int match_offset,
+				unsigned int match_len, const char *rep_buffer,
+				unsigned int rep_len, bool adjust);
 
-static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb,
-					   struct nf_conn *ct,
-					   enum ip_conntrack_info ctinfo,
-					   unsigned int protoff,
-					   unsigned int match_offset,
-					   unsigned int match_len,
-					   const char *rep_buffer,
-					   unsigned int rep_len)
+static inline bool nf_nat_mangle_tcp_packet(struct sk_buff *skb,
+					    struct nf_conn *ct,
+					    enum ip_conntrack_info ctinfo,
+					    unsigned int protoff,
+					    unsigned int match_offset,
+					    unsigned int match_len,
+					    const char *rep_buffer,
+					    unsigned int rep_len)
 {
 	return __nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
 					  match_offset, match_len,
 					  rep_buffer, rep_len, true);
 }
 
-int nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct,
-			     enum ip_conntrack_info ctinfo,
-			     unsigned int protoff, unsigned int match_offset,
-			     unsigned int match_len, const char *rep_buffer,
-			     unsigned int rep_len);
+bool nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct,
+			      enum ip_conntrack_info ctinfo,
+			      unsigned int protoff, unsigned int match_offset,
+			      unsigned int match_len, const char *rep_buffer,
+			      unsigned int rep_len);
 
 /* Setup NAT on this expected conntrack so it follows master, but goes
  * to port ct->master->saved_proto. */
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 09948d10e38e..4454719ff849 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -24,8 +24,7 @@ struct nf_queue_entry {
 struct nf_queue_handler {
 	int		(*outfn)(struct nf_queue_entry *entry,
 				 unsigned int queuenum);
-	void		(*nf_hook_drop)(struct net *net,
-					const struct nf_hook_entry *hooks);
+	unsigned int	(*nf_hook_drop)(struct net *net);
 };
 
 void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2aa8a9d80fbe..028faec8fc27 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -103,6 +103,35 @@ struct nft_regs {
 	};
 };
 
+/* Store/load an u16 or u8 integer to/from the u32 data register.
+ *
+ * Note, when using concatenations, register allocation happens at 32-bit
+ * level. So for store instruction, pad the rest part with zero to avoid
+ * garbage values.
+ */
+
+static inline void nft_reg_store16(u32 *dreg, u16 val)
+{
+	*dreg = 0;
+	*(u16 *)dreg = val;
+}
+
+static inline void nft_reg_store8(u32 *dreg, u8 val)
+{
+	*dreg = 0;
+	*(u8 *)dreg = val;
+}
+
+static inline u16 nft_reg_load16(u32 *sreg)
+{
+	return *(u16 *)sreg;
+}
+
+static inline u8 nft_reg_load8(u32 *sreg)
+{
+	return *(u8 *)sreg;
+}
+
 static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
 				 unsigned int len)
 {
@@ -203,7 +232,6 @@ struct nft_set_elem {
 struct nft_set;
 struct nft_set_iter {
 	u8		genmask;
-	bool		flush;
 	unsigned int	count;
 	unsigned int	skip;
 	int		err;
@@ -385,10 +413,11 @@ static inline struct nft_set *nft_set_container_of(const void *priv)
 	return (void *)priv - offsetof(struct nft_set, data);
 }
 
-struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
-				     const struct nlattr *nla, u8 genmask);
-struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
-					  const struct nlattr *nla, u8 genmask);
+struct nft_set *nft_set_lookup(const struct net *net,
+			       const struct nft_table *table,
+			       const struct nlattr *nla_set_name,
+			       const struct nlattr *nla_set_id,
+			       u8 genmask);
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {
@@ -882,6 +911,11 @@ static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chai
 	return container_of(chain, struct nft_base_chain, chain);
 }
 
+static inline bool nft_is_base_chain(const struct nft_chain *chain)
+{
+	return chain->flags & NFT_BASE_CHAIN;
+}
+
 int __nft_release_basechain(struct nft_ctx *ctx);
 
 unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
@@ -1016,7 +1050,8 @@ struct nft_object_type {
 	unsigned int			maxattr;
 	struct module			*owner;
 	const struct nla_policy		*policy;
-	int				(*init)(const struct nlattr * const tb[],
+	int				(*init)(const struct nft_ctx *ctx,
+						const struct nlattr *const tb[],
 						struct nft_object *obj);
 	void				(*destroy)(struct nft_object *obj);
 	int				(*dump)(struct sk_buff *skb,
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index d150b5066201..97983d1c05e4 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -9,12 +9,13 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
 		     struct sk_buff *skb,
 		     const struct nf_hook_state *state)
 {
+	unsigned int flags = IP6_FH_F_AUTH;
 	int protohdr, thoff = 0;
 	unsigned short frag_off;
 
 	nft_set_pktinfo(pkt, skb, state);
 
-	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
+	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
 	if (protohdr < 0) {
 		nft_set_pktinfo_proto_unspec(pkt, skb);
 		return;
@@ -32,6 +33,7 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 				const struct nf_hook_state *state)
 {
 #if IS_ENABLED(CONFIG_IPV6)
+	unsigned int flags = IP6_FH_F_AUTH;
 	struct ipv6hdr *ip6h, _ip6h;
 	unsigned int thoff = 0;
 	unsigned short frag_off;
@@ -50,7 +52,7 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 	if (pkt_len + sizeof(*ip6h) > skb->len)
 		return -1;
 
-	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
+	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
 	if (protohdr < 0)
 		return -1;
 
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
index 5ceb2205e4e3..381af9469e6a 100644
--- a/include/net/netfilter/nft_fib.h
+++ b/include/net/netfilter/nft_fib.h
@@ -32,6 +32,6 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		   const struct nft_pktinfo *pkt);
 
-void nft_fib_store_result(void *reg, enum nft_fib_result r,
+void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 			  const struct nft_pktinfo *pkt, int index);
 #endif
diff --git a/include/net/netlink.h b/include/net/netlink.h
index b239fcd33d80..01709172b3d3 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -233,14 +233,17 @@ struct nl_info {
 };
 
 int netlink_rcv_skb(struct sk_buff *skb,
-		    int (*cb)(struct sk_buff *, struct nlmsghdr *));
+		    int (*cb)(struct sk_buff *, struct nlmsghdr *,
+			      struct netlink_ext_ack *));
 int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
 		 unsigned int group, int report, gfp_t flags);
 
 int nla_validate(const struct nlattr *head, int len, int maxtype,
-		 const struct nla_policy *policy);
+		 const struct nla_policy *policy,
+		 struct netlink_ext_ack *extack);
 int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
-	      int len, const struct nla_policy *policy);
+	      int len, const struct nla_policy *policy,
+	      struct netlink_ext_ack *extack);
 int nla_policy_len(const struct nla_policy *, int);
 struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
 size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize);
@@ -374,18 +377,20 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining)
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @extack: extended ACK report struct
  *
  * See nla_parse()
  */
 static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
 			      struct nlattr *tb[], int maxtype,
-			      const struct nla_policy *policy)
+			      const struct nla_policy *policy,
+			      struct netlink_ext_ack *extack)
 {
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
 		return -EINVAL;
 
 	return nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
-			 nlmsg_attrlen(nlh, hdrlen), policy);
+			 nlmsg_attrlen(nlh, hdrlen), policy, extack);
 }
 
 /**
@@ -409,16 +414,19 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
  * @hdrlen: length of familiy specific header
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @extack: extended ACK report struct
  */
 static inline int nlmsg_validate(const struct nlmsghdr *nlh,
 				 int hdrlen, int maxtype,
-				 const struct nla_policy *policy)
+				 const struct nla_policy *policy,
+				 struct netlink_ext_ack *extack)
 {
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
 		return -EINVAL;
 
 	return nla_validate(nlmsg_attrdata(nlh, hdrlen),
-			    nlmsg_attrlen(nlh, hdrlen), maxtype, policy);
+			    nlmsg_attrlen(nlh, hdrlen), maxtype, policy,
+			    extack);
 }
 
 /**
@@ -739,14 +747,17 @@ nla_find_nested(const struct nlattr *nla, int attrtype)
  * @maxtype: maximum attribute type to be expected
  * @nla: attribute containing the nested attributes
  * @policy: validation policy
+ * @extack: extended ACK report struct
  *
  * See nla_parse()
  */
 static inline int nla_parse_nested(struct nlattr *tb[], int maxtype,
 				   const struct nlattr *nla,
-				   const struct nla_policy *policy)
+				   const struct nla_policy *policy,
+				   struct netlink_ext_ack *extack)
 {
-	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
+			 extack);
 }
 
 /**
@@ -1252,6 +1263,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
  * @start: container attribute
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @extack: extended ACK report struct
  *
  * Validates all attributes in the nested attribute stream against the
  * specified policy. Attributes with a type exceeding maxtype will be
@@ -1260,9 +1272,11 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
  * Returns 0 on success or a negative error code.
  */
 static inline int nla_validate_nested(const struct nlattr *start, int maxtype,
-				      const struct nla_policy *policy)
+				      const struct nla_policy *policy,
+				      struct netlink_ext_ack *extack)
 {
-	return nla_validate(nla_data(start), nla_len(start), maxtype, policy);
+	return nla_validate(nla_data(start), nla_len(start), maxtype, policy,
+			    extack);
 }
 
 /**
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
new file mode 100644
index 000000000000..b106e6ae2e5b
--- /dev/null
+++ b/include/net/netns/can.h
@@ -0,0 +1,40 @@
+/*
+ * can in net namespaces
+ */
+
+#ifndef __NETNS_CAN_H__
+#define __NETNS_CAN_H__
+
+#include <linux/spinlock.h>
+
+struct dev_rcv_lists;
+struct s_stats;
+struct s_pstats;
+
+struct netns_can {
+#if IS_ENABLED(CONFIG_PROC_FS)
+	struct proc_dir_entry *proc_dir;
+	struct proc_dir_entry *pde_version;
+	struct proc_dir_entry *pde_stats;
+	struct proc_dir_entry *pde_reset_stats;
+	struct proc_dir_entry *pde_rcvlist_all;
+	struct proc_dir_entry *pde_rcvlist_fil;
+	struct proc_dir_entry *pde_rcvlist_inv;
+	struct proc_dir_entry *pde_rcvlist_sff;
+	struct proc_dir_entry *pde_rcvlist_eff;
+	struct proc_dir_entry *pde_rcvlist_err;
+	struct proc_dir_entry *bcmproc_dir;
+#endif
+
+	/* receive filters subscribed for 'all' CAN devices */
+	struct dev_rcv_lists *can_rx_alldev_list;
+	spinlock_t can_rcvlists_lock;
+	struct timer_list can_stattimer;/* timer for statistics update */
+	struct s_stats *can_stats;	/* packet statistics */
+	struct s_pstats *can_pstats;	/* receive list statistics */
+
+	/* CAN GW per-net gateway jobs */
+	struct hlist_head cgw_list;
+};
+
+#endif /* __NETNS_CAN_H__ */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 622d2da27135..cd686c4fb32d 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -33,7 +33,6 @@ struct inet_timewait_death_row {
 	atomic_t		tw_count;
 
 	struct inet_hashinfo 	*hashinfo ____cacheline_aligned_in_smp;
-	int			sysctl_tw_recycle;
 	int			sysctl_max_tw_buckets;
 };
 
@@ -96,6 +95,8 @@ struct netns_ipv4 {
 	/* Shall we try to damage output packets if routing dev changes? */
 	int sysctl_ip_dynaddr;
 	int sysctl_ip_early_demux;
+	int sysctl_tcp_early_demux;
+	int sysctl_udp_early_demux;
 
 	int sysctl_fwmark_reflect;
 	int sysctl_tcp_fwmark_accept;
@@ -152,6 +153,7 @@ struct netns_ipv4 {
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int sysctl_fib_multipath_use_neigh;
+	int sysctl_fib_multipath_hash_policy;
 #endif
 
 	unsigned int	fib_seq;	/* protected by rtnl_mutex */
diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h
index d29203651c01..6608b3693385 100644
--- a/include/net/netns/mpls.h
+++ b/include/net/netns/mpls.h
@@ -9,8 +9,11 @@ struct mpls_route;
 struct ctl_table_header;
 
 struct netns_mpls {
+	int ip_ttl_propagate;
+	int default_ttl;
 	size_t platform_labels;
 	struct mpls_route __rcu * __rcu *platform_label;
+
 	struct ctl_table_header *ctl;
 };
 
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 1a3de8b34ad2..bbdc73a3239d 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -27,6 +27,7 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 
+#define nfc_dbg(dev, fmt, ...) dev_dbg((dev), "NFC: " fmt, ##__VA_ARGS__)
 #define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__)
 #define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__)
 
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index f1b76b8e6d2d..bec46f63f10c 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -92,7 +92,7 @@ int unregister_qdisc(struct Qdisc_ops *qops);
 void qdisc_get_default(char *id, size_t len);
 int qdisc_set_default(const char *id);
 
-void qdisc_hash_add(struct Qdisc *q);
+void qdisc_hash_add(struct Qdisc *q, bool invisible);
 void qdisc_hash_del(struct Qdisc *q);
 struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
 struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle);
diff --git a/include/net/protocol.h b/include/net/protocol.h
index bf36ca34af7a..65ba335b0e7e 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -40,6 +40,7 @@
 /* This is used to register protocols. */
 struct net_protocol {
 	void			(*early_demux)(struct sk_buff *skb);
+	void                    (*early_demux_handler)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	unsigned int		no_policy:1,
@@ -54,7 +55,7 @@ struct net_protocol {
 #if IS_ENABLED(CONFIG_IPV6)
 struct inet6_protocol {
 	void	(*early_demux)(struct sk_buff *skb);
-
+	void    (*early_demux_handler)(struct sk_buff *skb);
 	int	(*handler)(struct sk_buff *skb);
 
 	void	(*err_handler)(struct sk_buff *skb,
@@ -92,12 +93,12 @@ struct inet_protosw {
 #define INET_PROTOSW_PERMANENT 0x02  /* Permanent protocols are unremovable. */
 #define INET_PROTOSW_ICSK      0x04  /* Is this an inet_connection_sock? */
 
-extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
+extern struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
 extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
 extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
 
 #if IS_ENABLED(CONFIG_IPV6)
-extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
+extern struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
 #endif
 
 int inet_add_protocol(const struct net_protocol *prot, unsigned char num);
diff --git a/include/net/route.h b/include/net/route.h
index c0874c87c173..2cc0e14c6359 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -113,13 +113,13 @@ struct in_device;
 int ip_rt_init(void);
 void rt_cache_flush(struct net *net);
 void rt_flush_dev(struct net_device *dev);
-struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp,
-					  int mp_hash);
+struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
+					  const struct sk_buff *skb);
 
 static inline struct rtable *__ip_route_output_key(struct net *net,
 						   struct flowi4 *flp)
 {
-	return __ip_route_output_key_hash(net, flp, -1);
+	return __ip_route_output_key_hash(net, flp, NULL);
 }
 
 struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 106de5f7bf06..78fa5fe32947 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -4,7 +4,8 @@
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
 
-typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *);
+typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,
+			      struct netlink_ext_ack *);
 typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *);
 
@@ -158,7 +159,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 int rtnl_delete_link(struct net_device *dev);
 int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
 
-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len);
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
+			struct netlink_ext_ack *exterr);
 
 #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind)
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index aeec4086afb2..22e52093bfda 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -66,6 +66,7 @@ struct Qdisc {
 #define TCQ_F_NOPARENT		0x40 /* root of its hierarchy :
 				      * qdisc_tree_decrease_qlen() should stop.
 				      */
+#define TCQ_F_INVISIBLE		0x80 /* invisible by default in dump */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
@@ -203,14 +204,14 @@ struct tcf_proto_ops {
 					    const struct tcf_proto *,
 					    struct tcf_result *);
 	int			(*init)(struct tcf_proto*);
-	bool			(*destroy)(struct tcf_proto*, bool);
+	void			(*destroy)(struct tcf_proto*);
 
 	unsigned long		(*get)(struct tcf_proto*, u32 handle);
 	int			(*change)(struct net *net, struct sk_buff *,
 					struct tcf_proto*, unsigned long,
 					u32 handle, struct nlattr **,
 					unsigned long *, bool);
-	int			(*delete)(struct tcf_proto*, unsigned long);
+	int			(*delete)(struct tcf_proto*, unsigned long, bool*);
 	void			(*walk)(struct tcf_proto*, struct tcf_walker *arg);
 
 	/* rtnetlink specific */
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 1f71ee5ab518..069582ee5d7f 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -448,10 +448,9 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
 	return frag;
 }
 
-static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc)
+static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
 {
-
-	sctp_assoc_sync_pmtu(sk, asoc);
+	sctp_assoc_sync_pmtu(asoc);
 	asoc->pmtu_pending = 0;
 }
 
@@ -596,12 +595,23 @@ static inline void sctp_v4_map_v6(union sctp_addr *addr)
  */
 static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
 {
-	if (t->dst && (!dst_check(t->dst, t->dst_cookie) ||
-		       t->pathmtu != max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
-					   SCTP_DEFAULT_MINSEGMENT)))
+	if (t->dst && !dst_check(t->dst, t->dst_cookie))
 		sctp_transport_dst_release(t);
 
 	return t->dst;
 }
 
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+	__u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
+			   SCTP_DEFAULT_MINSEGMENT);
+
+	if (t->pathmtu == pmtu)
+		return true;
+
+	t->pathmtu = pmtu;
+
+	return false;
+}
+
 #endif /* __net_sctp_h__ */
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index b6f682ec184a..47113f2c4b0a 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -293,6 +293,22 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 				struct sctp_association *asoc,
 				union sctp_params param,
 				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_tsnreq(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_addstrm_out(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_addstrm_in(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_resp(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
 
 /* Prototypes for statetable processing. */
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a244db5e5ff7..a8b38e123f97 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -83,6 +83,7 @@ struct sctp_bind_addr;
 struct sctp_ulpq;
 struct sctp_ep_common;
 struct crypto_shash;
+struct sctp_stream;
 
 
 #include <net/sctp/tsnmap.h>
@@ -376,7 +377,8 @@ typedef struct sctp_sender_hb_info {
 	__u64 hb_nonce;
 } sctp_sender_hb_info_t;
 
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp);
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp);
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp);
 void sctp_stream_free(struct sctp_stream *stream);
 void sctp_stream_clear(struct sctp_stream *stream);
 
@@ -476,7 +478,8 @@ struct sctp_pf {
 	int  (*send_verify) (struct sctp_sock *, union sctp_addr *);
 	int  (*supported_addrs)(const struct sctp_sock *, __be16 *);
 	struct sock *(*create_accept_sk) (struct sock *sk,
-					  struct sctp_association *asoc);
+					  struct sctp_association *asoc,
+					  bool kern);
 	int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr);
 	void (*to_sk_saddr)(union sctp_addr *, struct sock *sk);
 	void (*to_sk_daddr)(union sctp_addr *, struct sock *sk);
@@ -497,7 +500,6 @@ struct sctp_datamsg {
 	/* Did the messenge fail to send? */
 	int send_error;
 	u8 send_failed:1,
-	   force_delay:1,
 	   can_delay;	    /* should this message be Nagle delayed */
 };
 
@@ -752,6 +754,8 @@ struct sctp_transport {
 		/* Is the Path MTU update pending on this tranport */
 		pmtu_pending:1,
 
+		dst_pending_confirm:1,	/* need to confirm neighbour */
+
 		/* Has this transport moved the ctsn since we last sacked */
 		sack_generation:1;
 	u32 dst_cookie;
@@ -805,8 +809,6 @@ struct sctp_transport {
 
 	__u32 burst_limited;	/* Holds old cwnd when max.burst is applied */
 
-	__u32 dst_pending_confirm;	/* need to confirm neighbour */
-
 	/* Destination */
 	struct dst_entry *dst;
 	/* Source address. */
@@ -950,8 +952,8 @@ void sctp_transport_lower_cwnd(struct sctp_transport *, sctp_lower_cwnd_t);
 void sctp_transport_burst_limited(struct sctp_transport *);
 void sctp_transport_burst_reset(struct sctp_transport *);
 unsigned long sctp_transport_timeout(struct sctp_transport *);
-void sctp_transport_reset(struct sctp_transport *);
-void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32);
+void sctp_transport_reset(struct sctp_transport *t);
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
 void sctp_transport_immediate_rtx(struct sctp_transport *);
 void sctp_transport_dst_release(struct sctp_transport *t);
 void sctp_transport_dst_confirm(struct sctp_transport *t);
@@ -1313,6 +1315,8 @@ struct sctp_inithdr_host {
 struct sctp_stream_out {
 	__u16	ssn;
 	__u8	state;
+	__u64	abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
+	__u64	abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
 };
 
 struct sctp_stream_in {
@@ -1876,6 +1880,7 @@ struct sctp_association {
 
 	__u8 need_ecne:1,	/* Need to send an ECNE Chunk? */
 	     temp:1,		/* Is it a temporary association? */
+	     force_delay:1,
 	     prsctp_enable:1,
 	     reconf_enable:1;
 
@@ -1884,6 +1889,7 @@ struct sctp_association {
 
 	__u32 strreset_outseq; /* Update after receiving response */
 	__u32 strreset_inseq; /* Update after receiving request */
+	__u32 strreset_result[2]; /* save the results of last 2 responses */
 
 	struct sctp_chunk *strreset_chunk; /* save request chunk */
 
@@ -1951,7 +1957,7 @@ void sctp_assoc_update(struct sctp_association *old,
 
 __u32 sctp_association_get_next_tsn(struct sctp_association *);
 
-void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc);
 void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
 void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
 void sctp_assoc_set_primary(struct sctp_association *,
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 324b5965fc4d..1060494ac230 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -132,6 +132,14 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
 	const struct sctp_association *asoc, __u16 flags,
 	__u16 stream_num, __u16 *stream_list, gfp_t gfp);
 
+struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
+	const struct sctp_association *asoc, __u16 flags,
+	 __u32 local_tsn, __u32 remote_tsn, gfp_t gfp);
+
+struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event(
+	const struct sctp_association *asoc, __u16 flags,
+	__u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp);
+
 void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 				   struct msghdr *);
 void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 0caee631a836..fe236b3429f0 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -6,10 +6,10 @@
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+			     __be16 sport, __be16 dport, u32 *tsoff);
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
 			       __be16 sport, __be16 dport, u32 *tsoff);
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff);
 u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 				__be16 sport, __be16 dport);
 u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
diff --git a/include/net/sock.h b/include/net/sock.h
index 5e5997654db6..66349e49d468 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -236,6 +236,7 @@ struct sock_common {
   *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
   *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
   *	@sk_lock:	synchronizer
+  *	@sk_kern_sock: True if sock is using kernel lock classes
   *	@sk_rcvbuf: size of receive buffer in bytes
   *	@sk_wq: sock wait queue and async head
   *	@sk_rx_dst: receive input route used by early demux
@@ -430,7 +431,8 @@ struct sock {
 #endif
 
 	kmemcheck_bitfield_begin(flags);
-	unsigned int		sk_padding : 2,
+	unsigned int		sk_padding : 1,
+				sk_kern_sock : 1,
 				sk_no_check_tx : 1,
 				sk_no_check_rx : 1,
 				sk_userlocks : 4,
@@ -1015,7 +1017,8 @@ struct proto {
 					int addr_len);
 	int			(*disconnect)(struct sock *sk, int flags);
 
-	struct sock *		(*accept)(struct sock *sk, int flags, int *err);
+	struct sock *		(*accept)(struct sock *sk, int flags, int *err,
+					  bool kern);
 
 	int			(*ioctl)(struct sock *sk, int cmd,
 					 unsigned long arg);
@@ -1573,7 +1576,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 int sock_no_bind(struct socket *, struct sockaddr *, int);
 int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
-int sock_no_accept(struct socket *, struct socket *, int);
+int sock_no_accept(struct socket *, struct socket *, int, bool);
 int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
 unsigned int sock_no_poll(struct file *, struct socket *,
 			  struct poll_table_struct *);
@@ -1780,11 +1783,8 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 
 	sk_tx_queue_clear(sk);
 	sk->sk_dst_pending_confirm = 0;
-	/*
-	 * This can be called while sk is owned by the caller only,
-	 * with no state that can be checked in a rcu_dereference_check() cond
-	 */
-	old_dst = rcu_dereference_raw(sk->sk_dst_cache);
+	old_dst = rcu_dereference_protected(sk->sk_dst_cache,
+					    lockdep_sock_is_held(sk));
 	rcu_assign_pointer(sk->sk_dst_cache, dst);
 	dst_release(old_dst);
 }
@@ -2239,6 +2239,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 			      struct sk_buff *skb);
 
+#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
 static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 					  struct sk_buff *skb)
 {
@@ -2249,8 +2250,10 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
-	else
+	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sk->sk_stamp = skb->tstamp;
+	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+		sk->sk_stamp = 0;
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
@@ -2362,6 +2365,8 @@ bool sk_ns_capable(const struct sock *sk,
 bool sk_capable(const struct sock *sk, int cap);
 bool sk_net_capable(const struct sock *sk, int cap);
 
+void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
+
 extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index dfbd6ee0bc7c..a46c3f2ace70 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/include/net/tc_act/tc_pedit.h
@@ -2,6 +2,7 @@
 #define __NET_TC_PED_H
 
 #include <net/act_api.h>
+#include <linux/tc_act/tc_pedit.h>
 
 struct tcf_pedit_key_ex {
 	enum pedit_header_type htype;
@@ -17,4 +18,48 @@ struct tcf_pedit {
 };
 #define to_pedit(a) ((struct tcf_pedit *)a)
 
+static inline bool is_tcf_pedit(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	if (a->ops && a->ops->type == TCA_ACT_PEDIT)
+		return true;
+#endif
+	return false;
+}
+
+static inline int tcf_pedit_nkeys(const struct tc_action *a)
+{
+	return to_pedit(a)->tcfp_nkeys;
+}
+
+static inline u32 tcf_pedit_htype(const struct tc_action *a, int index)
+{
+	if (to_pedit(a)->tcfp_keys_ex)
+		return to_pedit(a)->tcfp_keys_ex[index].htype;
+
+	return TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
+}
+
+static inline u32 tcf_pedit_cmd(const struct tc_action *a, int index)
+{
+	if (to_pedit(a)->tcfp_keys_ex)
+		return to_pedit(a)->tcfp_keys_ex[index].cmd;
+
+	return __PEDIT_CMD_MAX;
+}
+
+static inline u32 tcf_pedit_mask(const struct tc_action *a, int index)
+{
+	return to_pedit(a)->tcfp_keys[index].mask;
+}
+
+static inline u32 tcf_pedit_val(const struct tc_action *a, int index)
+{
+	return to_pedit(a)->tcfp_keys[index].val;
+}
+
+static inline u32 tcf_pedit_offset(const struct tc_action *a, int index)
+{
+	return to_pedit(a)->tcfp_keys[index].off;
+}
 #endif /* __NET_TC_PED_H */
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 48cca321ee6c..c2090df944ff 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -13,9 +13,6 @@
 #include <net/act_api.h>
 #include <linux/tc_act/tc_vlan.h>
 
-#define VLAN_F_POP		0x1
-#define VLAN_F_PUSH		0x2
-
 struct tcf_vlan {
 	struct tc_action	common;
 	int			tcfv_action;
@@ -49,4 +46,9 @@ static inline __be16 tcf_vlan_push_proto(const struct tc_action *a)
 	return to_vlan(a)->tcfv_push_proto;
 }
 
+static inline u8 tcf_vlan_push_prio(const struct tc_action *a)
+{
+	return to_vlan(a)->tcfv_push_prio;
+}
+
 #endif /* __NET_TC_VLAN_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ec4ea652f3f..270e5cc43c99 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -78,6 +78,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* Maximal number of ACKs sent quickly to accelerate slow-start. */
 #define TCP_MAX_QUICKACKS	16U
 
+/* Maximal number of window scale according to RFC1323 */
+#define TCP_MAX_WSCALE		14U
+
 /* urg_data states */
 #define TCP_URG_VALID	0x0100
 #define TCP_URG_NOTYET	0x0200
@@ -406,11 +409,7 @@ void tcp_clear_retrans(struct tcp_sock *tp);
 void tcp_update_metrics(struct sock *sk);
 void tcp_init_metrics(struct sock *sk);
 void tcp_metrics_init(void);
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
-			bool paws_check, bool timestamps);
-bool tcp_remember_stamp(struct sock *sk);
-bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
-void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_disable_fack(struct tcp_sock *tp);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
@@ -1005,7 +1004,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
 void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 			    struct rate_sample *rs);
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct skb_mstamp *now, struct rate_sample *rs);
+		  struct rate_sample *rs);
 void tcp_rate_check_app_limited(struct sock *sk);
 
 /* These functions determine how the current flow behaves in respect of SACK
@@ -1252,9 +1251,11 @@ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
 
 static inline int tcp_win_from_space(int space)
 {
-	return sysctl_tcp_adv_win_scale<=0 ?
-		(space>>(-sysctl_tcp_adv_win_scale)) :
-		space - (space>>sysctl_tcp_adv_win_scale);
+	int tcp_adv_win_scale = sysctl_tcp_adv_win_scale;
+
+	return tcp_adv_win_scale <= 0 ?
+		(space>>(-tcp_adv_win_scale)) :
+		space - (space>>tcp_adv_win_scale);
 }
 
 /* Note: caller must be prepared to deal with negative returns */
@@ -1505,6 +1506,12 @@ struct tcp_fastopen_context {
 	struct rcu_head		rcu;
 };
 
+extern unsigned int sysctl_tcp_fastopen_blackhole_timeout;
+void tcp_fastopen_active_disable(struct sock *sk);
+bool tcp_fastopen_active_should_disable(struct sock *sk);
+void tcp_fastopen_active_disable_ofo_check(struct sock *sk);
+void tcp_fastopen_active_timeout_reset(void);
+
 /* Latencies incurred by various limits for a sender. They are
  * chronograph-like stats that are mutually exclusive.
  */
@@ -1814,9 +1821,8 @@ struct tcp_request_sock_ops {
 				 __u16 *mss);
 #endif
 	struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
-				       const struct request_sock *req,
-				       bool *strict);
-	__u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff);
+				       const struct request_sock *req);
+	__u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff);
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
@@ -1847,10 +1853,9 @@ void tcp_v4_init(void);
 void tcp_init(void);
 
 /* tcp_recovery.c */
-extern void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now);
+extern void tcp_rack_mark_lost(struct sock *sk);
 extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
-			     const struct skb_mstamp *xmit_time,
-			     const struct skb_mstamp *ack_time);
+			     const struct skb_mstamp *xmit_time);
 extern void tcp_rack_reo_timeout(struct sock *sk);
 
 /*
diff --git a/include/net/udp.h b/include/net/udp.h
index c9d8b8e848e0..3391dbd73959 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -372,4 +372,5 @@ void udp_encap_enable(void);
 #if IS_ENABLED(CONFIG_IPV6)
 void udpv6_encap_enable(void);
 #endif
+
 #endif	/* _UDP_H */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 14d82bf16692..6793a30c66b1 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -120,6 +120,13 @@ struct xfrm_state_walk {
 	struct xfrm_address_filter *filter;
 };
 
+struct xfrm_state_offload {
+	struct net_device	*dev;
+	unsigned long		offload_handle;
+	unsigned int		num_exthdrs;
+	u8			flags;
+};
+
 /* Full description of state of transformer. */
 struct xfrm_state {
 	possible_net_t		xs_net;
@@ -207,6 +214,8 @@ struct xfrm_state {
 	struct xfrm_lifetime_cur curlft;
 	struct tasklet_hrtimer	mtimer;
 
+	struct xfrm_state_offload xso;
+
 	/* used to fix curlft->add_time when changing date */
 	long		saved_tmo;
 
@@ -222,6 +231,8 @@ struct xfrm_state {
 	struct xfrm_mode	*inner_mode_iaf;
 	struct xfrm_mode	*outer_mode;
 
+	const struct xfrm_type_offload	*type_offload;
+
 	/* Security context */
 	struct xfrm_sec_ctx	*security;
 
@@ -314,12 +325,14 @@ void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 int __xfrm_state_delete(struct xfrm_state *x);
 
 struct xfrm_state_afinfo {
-	unsigned int		family;
-	unsigned int		proto;
-	__be16			eth_proto;
-	struct module		*owner;
-	const struct xfrm_type	*type_map[IPPROTO_MAX];
-	struct xfrm_mode	*mode_map[XFRM_MODE_MAX];
+	unsigned int			family;
+	unsigned int			proto;
+	__be16				eth_proto;
+	struct module			*owner;
+	const struct xfrm_type		*type_map[IPPROTO_MAX];
+	const struct xfrm_type_offload	*type_offload_map[IPPROTO_MAX];
+	struct xfrm_mode		*mode_map[XFRM_MODE_MAX];
+
 	int			(*init_flags)(struct xfrm_state *x);
 	void			(*init_tempsel)(struct xfrm_selector *sel,
 						const struct flowi *fl);
@@ -380,6 +393,18 @@ struct xfrm_type {
 int xfrm_register_type(const struct xfrm_type *type, unsigned short family);
 int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family);
 
+struct xfrm_type_offload {
+	char		*description;
+	struct module	*owner;
+	u8		proto;
+	void		(*encap)(struct xfrm_state *, struct sk_buff *pskb);
+	int		(*input_tail)(struct xfrm_state *x, struct sk_buff *skb);
+	int		(*xmit)(struct xfrm_state *, struct sk_buff *pskb, netdev_features_t features);
+};
+
+int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
+int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
+
 struct xfrm_mode {
 	/*
 	 * Remove encapsulation header.
@@ -428,6 +453,16 @@ struct xfrm_mode {
 	 */
 	int (*output)(struct xfrm_state *x, struct sk_buff *skb);
 
+	/*
+	 * Adjust pointers into the packet and do GSO segmentation.
+	 */
+	struct sk_buff *(*gso_segment)(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features);
+
+	/*
+	 * Adjust pointers into the packet when IPsec is done at layer2.
+	 */
+	void (*xmit)(struct xfrm_state *x, struct sk_buff *skb);
+
 	struct xfrm_state_afinfo *afinfo;
 	struct module *owner;
 	unsigned int encap;
@@ -586,7 +621,6 @@ struct xfrm_migrate {
 
 struct xfrm_mgr {
 	struct list_head	list;
-	char			*id;
 	int			(*notify)(struct xfrm_state *x, const struct km_event *c);
 	int			(*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp);
 	struct xfrm_policy	*(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir);
@@ -817,12 +851,12 @@ static inline void xfrm_state_hold(struct xfrm_state *x)
 }
 
 static inline bool addr_match(const void *token1, const void *token2,
-			      int prefixlen)
+			      unsigned int prefixlen)
 {
 	const __be32 *a1 = token1;
 	const __be32 *a2 = token2;
-	int pdw;
-	int pbi;
+	unsigned int pdw;
+	unsigned int pbi;
 
 	pdw = prefixlen >> 5;	  /* num of whole u32 in prefix */
 	pbi = prefixlen &  0x1f;  /* num of bits in incomplete u32 in prefix */
@@ -846,9 +880,9 @@ static inline bool addr_match(const void *token1, const void *token2,
 static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen)
 {
 	/* C99 6.5.7 (3): u32 << 32 is undefined behaviour */
-	if (prefixlen == 0)
+	if (sizeof(long) == 4 && prefixlen == 0)
 		return true;
-	return !((a1 ^ a2) & htonl(0xFFFFFFFFu << (32 - prefixlen)));
+	return !((a1 ^ a2) & htonl(~0UL << (32 - prefixlen)));
 }
 
 static __inline__
@@ -1533,6 +1567,7 @@ struct xfrmk_spdinfo {
 struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
 int xfrm_state_delete(struct xfrm_state *x);
 int xfrm_state_flush(struct net *net, u8 proto, bool task_valid);
+int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid);
 void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
@@ -1615,6 +1650,11 @@ static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 }
 #endif
 
+struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr,
+				    int family);
+
 struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);
 
 void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type);
@@ -1820,6 +1860,61 @@ static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb)
 }
 #endif
 
+#ifdef CONFIG_XFRM_OFFLOAD
+void __net_init xfrm_dev_init(void);
+int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features);
+int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
+		       struct xfrm_user_offload *xuo);
+bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
+
+static inline void xfrm_dev_state_delete(struct xfrm_state *x)
+{
+	struct xfrm_state_offload *xso = &x->xso;
+
+	if (xso->dev)
+		xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
+}
+
+static inline void xfrm_dev_state_free(struct xfrm_state *x)
+{
+	struct xfrm_state_offload *xso = &x->xso;
+	 struct net_device *dev = xso->dev;
+
+	if (dev && dev->xfrmdev_ops) {
+		dev->xfrmdev_ops->xdo_dev_state_free(x);
+		xso->dev = NULL;
+		dev_put(dev);
+	}
+}
+#else
+static inline void __net_init xfrm_dev_init(void)
+{
+}
+
+static inline int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features)
+{
+	return 0;
+}
+
+static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo)
+{
+	return 0;
+}
+
+static inline void xfrm_dev_state_delete(struct xfrm_state *x)
+{
+}
+
+static inline void xfrm_dev_state_free(struct xfrm_state *x)
+{
+}
+
+static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
+{
+	return false;
+}
+#endif
+
 static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m)
 {
 	if (attrs[XFRMA_MARK])
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
index 9b4c22a36931..66dbed0c146d 100644
--- a/include/rdma/ib.h
+++ b/include/rdma/ib.h
@@ -100,7 +100,7 @@ struct sockaddr_ib {
  */
 static inline bool ib_safe_file_access(struct file *filp)
 {
-	return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS);
+	return filp->f_cred == current_cred() && !uaccess_kernel();
 }
 
 #endif /* _RDMA_IB_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0f1813c13687..99e4423eb2b8 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1863,6 +1863,9 @@ struct ib_port_immutable {
 };
 
 struct ib_device {
+	/* Do not access @dma_device directly from ULP nor from HW drivers. */
+	struct device                *dma_device;
+
 	char                          name[IB_DEVICE_NAME_MAX];
 
 	struct list_head              event_handler_list;
@@ -3007,7 +3010,7 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt)
  */
 static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
 {
-	return dma_mapping_error(&dev->dev, dma_addr);
+	return dma_mapping_error(dev->dma_device, dma_addr);
 }
 
 /**
@@ -3021,7 +3024,7 @@ static inline u64 ib_dma_map_single(struct ib_device *dev,
 				    void *cpu_addr, size_t size,
 				    enum dma_data_direction direction)
 {
-	return dma_map_single(&dev->dev, cpu_addr, size, direction);
+	return dma_map_single(dev->dma_device, cpu_addr, size, direction);
 }
 
 /**
@@ -3035,7 +3038,7 @@ static inline void ib_dma_unmap_single(struct ib_device *dev,
 				       u64 addr, size_t size,
 				       enum dma_data_direction direction)
 {
-	dma_unmap_single(&dev->dev, addr, size, direction);
+	dma_unmap_single(dev->dma_device, addr, size, direction);
 }
 
 /**
@@ -3052,7 +3055,7 @@ static inline u64 ib_dma_map_page(struct ib_device *dev,
 				  size_t size,
 					 enum dma_data_direction direction)
 {
-	return dma_map_page(&dev->dev, page, offset, size, direction);
+	return dma_map_page(dev->dma_device, page, offset, size, direction);
 }
 
 /**
@@ -3066,7 +3069,7 @@ static inline void ib_dma_unmap_page(struct ib_device *dev,
 				     u64 addr, size_t size,
 				     enum dma_data_direction direction)
 {
-	dma_unmap_page(&dev->dev, addr, size, direction);
+	dma_unmap_page(dev->dma_device, addr, size, direction);
 }
 
 /**
@@ -3080,7 +3083,7 @@ static inline int ib_dma_map_sg(struct ib_device *dev,
 				struct scatterlist *sg, int nents,
 				enum dma_data_direction direction)
 {
-	return dma_map_sg(&dev->dev, sg, nents, direction);
+	return dma_map_sg(dev->dma_device, sg, nents, direction);
 }
 
 /**
@@ -3094,7 +3097,7 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev,
 				   struct scatterlist *sg, int nents,
 				   enum dma_data_direction direction)
 {
-	dma_unmap_sg(&dev->dev, sg, nents, direction);
+	dma_unmap_sg(dev->dma_device, sg, nents, direction);
 }
 
 static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
@@ -3102,7 +3105,8 @@ static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
 				      enum dma_data_direction direction,
 				      unsigned long dma_attrs)
 {
-	return dma_map_sg_attrs(&dev->dev, sg, nents, direction, dma_attrs);
+	return dma_map_sg_attrs(dev->dma_device, sg, nents, direction,
+				dma_attrs);
 }
 
 static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
@@ -3110,7 +3114,7 @@ static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
 					 enum dma_data_direction direction,
 					 unsigned long dma_attrs)
 {
-	dma_unmap_sg_attrs(&dev->dev, sg, nents, direction, dma_attrs);
+	dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs);
 }
 /**
  * ib_sg_dma_address - Return the DMA address from a scatter/gather entry
@@ -3152,7 +3156,7 @@ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev,
 					      size_t size,
 					      enum dma_data_direction dir)
 {
-	dma_sync_single_for_cpu(&dev->dev, addr, size, dir);
+	dma_sync_single_for_cpu(dev->dma_device, addr, size, dir);
 }
 
 /**
@@ -3167,7 +3171,7 @@ static inline void ib_dma_sync_single_for_device(struct ib_device *dev,
 						 size_t size,
 						 enum dma_data_direction dir)
 {
-	dma_sync_single_for_device(&dev->dev, addr, size, dir);
+	dma_sync_single_for_device(dev->dma_device, addr, size, dir);
 }
 
 /**
@@ -3182,7 +3186,7 @@ static inline void *ib_dma_alloc_coherent(struct ib_device *dev,
 					   dma_addr_t *dma_handle,
 					   gfp_t flag)
 {
-	return dma_alloc_coherent(&dev->dev, size, dma_handle, flag);
+	return dma_alloc_coherent(dev->dma_device, size, dma_handle, flag);
 }
 
 /**
@@ -3196,7 +3200,7 @@ static inline void ib_dma_free_coherent(struct ib_device *dev,
 					size_t size, void *cpu_addr,
 					dma_addr_t dma_handle)
 {
-	dma_free_coherent(&dev->dev, size, cpu_addr, dma_handle);
+	dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle);
 }
 
 /**
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index b0e275de6dec..583875ea136a 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -196,6 +196,7 @@ struct iscsi_conn {
 	struct iscsi_task	*task;		/* xmit task in progress */
 
 	/* xmit */
+	spinlock_t		taskqueuelock;  /* protects the next three lists */
 	struct list_head	mgmtqueue;	/* mgmt (control) xmit queue */
 	struct list_head	cmdqueue;	/* data-path cmd queue */
 	struct list_head	requeue;	/* tasks needing another run */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 6f22b39f1b0c..080c7ce9bae8 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -472,6 +472,10 @@ static inline int scsi_device_created(struct scsi_device *sdev)
 		sdev->sdev_state == SDEV_CREATED_BLOCK;
 }
 
+int scsi_internal_device_block(struct scsi_device *sdev, bool wait);
+int scsi_internal_device_unblock(struct scsi_device *sdev,
+				 enum scsi_device_state new_state);
+
 /* accessor functions for the SCSI parameters */
 static inline int scsi_device_sync(struct scsi_device *sdev)
 {
diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h
index ba0aeb980f7e..f0c76f9dc285 100644
--- a/include/scsi/scsi_request.h
+++ b/include/scsi/scsi_request.h
@@ -9,8 +9,10 @@ struct scsi_request {
 	unsigned char	__cmd[BLK_MAX_CDB];
 	unsigned char	*cmd;
 	unsigned short	cmd_len;
+	int		result;
 	unsigned int	sense_len;
 	unsigned int	resid_len;	/* residual count */
+	int		retries;
 	void		*sense;
 };
 
diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h
index 3d4df74a96de..d4dfefdee6c1 100644
--- a/include/soc/fsl/qman.h
+++ b/include/soc/fsl/qman.h
@@ -36,8 +36,11 @@
 /* Hardware constants */
 #define QM_CHANNEL_SWPORTAL0 0
 #define QMAN_CHANNEL_POOL1 0x21
+#define QMAN_CHANNEL_CAAM 0x80
 #define QMAN_CHANNEL_POOL1_REV3 0x401
+#define QMAN_CHANNEL_CAAM_REV3 0x840
 extern u16 qm_channel_pool1;
+extern u16 qm_channel_caam;
 
 /* Portal processing (interrupt) sources */
 #define QM_PIRQ_CSCI	0x00100000	/* Congestion State Change */
@@ -165,6 +168,7 @@ static inline void qm_fd_set_param(struct qm_fd *fd, enum qm_fd_format fmt,
 #define qm_fd_set_contig_big(fd, len) \
 	qm_fd_set_param(fd, qm_fd_contig_big, 0, len)
 #define qm_fd_set_sg_big(fd, len) qm_fd_set_param(fd, qm_fd_sg_big, 0, len)
+#define qm_fd_set_compound(fd, len) qm_fd_set_param(fd, qm_fd_compound, 0, len)
 
 static inline void qm_fd_clear_fd(struct qm_fd *fd)
 {
@@ -639,6 +643,7 @@ struct qm_mcc_initcgr {
 #define QM_CGR_WE_MODE			0x0001
 
 #define QMAN_CGR_FLAG_USE_INIT	     0x00000001
+#define QMAN_CGR_MODE_FRAME          0x00000001
 
 	/* Portal and Frame Queues */
 /* Represents a managed portal */
@@ -791,6 +796,84 @@ struct qman_cgr {
 #define QMAN_INITFQ_FLAG_SCHED	     0x00000001 /* schedule rather than park */
 #define QMAN_INITFQ_FLAG_LOCAL	     0x00000004 /* set dest portal */
 
+/*
+ * For qman_volatile_dequeue(); Choose one PRECEDENCE. EXACT is optional. Use
+ * NUMFRAMES(n) (6-bit) or NUMFRAMES_TILLEMPTY to fill in the frame-count. Use
+ * FQID(n) to fill in the frame queue ID.
+ */
+#define QM_VDQCR_PRECEDENCE_VDQCR	0x0
+#define QM_VDQCR_PRECEDENCE_SDQCR	0x80000000
+#define QM_VDQCR_EXACT			0x40000000
+#define QM_VDQCR_NUMFRAMES_MASK		0x3f000000
+#define QM_VDQCR_NUMFRAMES_SET(n)	(((n) & 0x3f) << 24)
+#define QM_VDQCR_NUMFRAMES_GET(n)	(((n) >> 24) & 0x3f)
+#define QM_VDQCR_NUMFRAMES_TILLEMPTY	QM_VDQCR_NUMFRAMES_SET(0)
+
+#define QMAN_VOLATILE_FLAG_WAIT	     0x00000001 /* wait if VDQCR is in use */
+#define QMAN_VOLATILE_FLAG_WAIT_INT  0x00000002 /* if wait, interruptible? */
+#define QMAN_VOLATILE_FLAG_FINISH    0x00000004 /* wait till VDQCR completes */
+
+/* "Query FQ Non-Programmable Fields" */
+struct qm_mcr_queryfq_np {
+	u8 verb;
+	u8 result;
+	u8 __reserved1;
+	u8 state;		/* QM_MCR_NP_STATE_*** */
+	u32 fqd_link;		/* 24-bit, _res2[24-31] */
+	u16 odp_seq;		/* 14-bit, _res3[14-15] */
+	u16 orp_nesn;		/* 14-bit, _res4[14-15] */
+	u16 orp_ea_hseq;	/* 15-bit, _res5[15] */
+	u16 orp_ea_tseq;	/* 15-bit, _res6[15] */
+	u32 orp_ea_hptr;	/* 24-bit, _res7[24-31] */
+	u32 orp_ea_tptr;	/* 24-bit, _res8[24-31] */
+	u32 pfdr_hptr;		/* 24-bit, _res9[24-31] */
+	u32 pfdr_tptr;		/* 24-bit, _res10[24-31] */
+	u8 __reserved2[5];
+	u8 is;			/* 1-bit, _res12[1-7] */
+	u16 ics_surp;
+	u32 byte_cnt;
+	u32 frm_cnt;		/* 24-bit, _res13[24-31] */
+	u32 __reserved3;
+	u16 ra1_sfdr;		/* QM_MCR_NP_RA1_*** */
+	u16 ra2_sfdr;		/* QM_MCR_NP_RA2_*** */
+	u16 __reserved4;
+	u16 od1_sfdr;		/* QM_MCR_NP_OD1_*** */
+	u16 od2_sfdr;		/* QM_MCR_NP_OD2_*** */
+	u16 od3_sfdr;		/* QM_MCR_NP_OD3_*** */
+} __packed;
+
+#define QM_MCR_NP_STATE_FE		0x10
+#define QM_MCR_NP_STATE_R		0x08
+#define QM_MCR_NP_STATE_MASK		0x07	/* Reads FQD::STATE; */
+#define QM_MCR_NP_STATE_OOS		0x00
+#define QM_MCR_NP_STATE_RETIRED		0x01
+#define QM_MCR_NP_STATE_TEN_SCHED	0x02
+#define QM_MCR_NP_STATE_TRU_SCHED	0x03
+#define QM_MCR_NP_STATE_PARKED		0x04
+#define QM_MCR_NP_STATE_ACTIVE		0x05
+#define QM_MCR_NP_PTR_MASK		0x07ff	/* for RA[12] & OD[123] */
+#define QM_MCR_NP_RA1_NRA(v)		(((v) >> 14) & 0x3)	/* FQD::NRA */
+#define QM_MCR_NP_RA2_IT(v)		(((v) >> 14) & 0x1)	/* FQD::IT */
+#define QM_MCR_NP_OD1_NOD(v)		(((v) >> 14) & 0x3)	/* FQD::NOD */
+#define QM_MCR_NP_OD3_NPC(v)		(((v) >> 14) & 0x3)	/* FQD::NPC */
+
+enum qm_mcr_queryfq_np_masks {
+	qm_mcr_fqd_link_mask = BIT(24) - 1,
+	qm_mcr_odp_seq_mask = BIT(14) - 1,
+	qm_mcr_orp_nesn_mask = BIT(14) - 1,
+	qm_mcr_orp_ea_hseq_mask = BIT(15) - 1,
+	qm_mcr_orp_ea_tseq_mask = BIT(15) - 1,
+	qm_mcr_orp_ea_hptr_mask = BIT(24) - 1,
+	qm_mcr_orp_ea_tptr_mask = BIT(24) - 1,
+	qm_mcr_pfdr_hptr_mask = BIT(24) - 1,
+	qm_mcr_pfdr_tptr_mask = BIT(24) - 1,
+	qm_mcr_is_mask = BIT(1) - 1,
+	qm_mcr_frm_cnt_mask = BIT(24) - 1,
+};
+
+#define qm_mcr_np_get(np, field) \
+	((np)->field & (qm_mcr_##field##_mask))
+
 	/* Portal Management */
 /**
  * qman_p_irqsource_add - add processing sources to be interrupt-driven
@@ -963,6 +1046,25 @@ int qman_retire_fq(struct qman_fq *fq, u32 *flags);
  */
 int qman_oos_fq(struct qman_fq *fq);
 
+/*
+ * qman_volatile_dequeue - Issue a volatile dequeue command
+ * @fq: the frame queue object to dequeue from
+ * @flags: a bit-mask of QMAN_VOLATILE_FLAG_*** options
+ * @vdqcr: bit mask of QM_VDQCR_*** options, as per qm_dqrr_vdqcr_set()
+ *
+ * Attempts to lock access to the portal's VDQCR volatile dequeue functionality.
+ * The function will block and sleep if QMAN_VOLATILE_FLAG_WAIT is specified and
+ * the VDQCR is already in use, otherwise returns non-zero for failure. If
+ * QMAN_VOLATILE_FLAG_FINISH is specified, the function will only return once
+ * the VDQCR command has finished executing (ie. once the callback for the last
+ * DQRR entry resulting from the VDQCR command has been called). If not using
+ * the FINISH flag, completion can be determined either by detecting the
+ * presence of the QM_DQRR_STAT_UNSCHEDULED and QM_DQRR_STAT_DQCR_EXPIRED bits
+ * in the "stat" parameter passed to the FQ's dequeue callback, or by waiting
+ * for the QMAN_FQ_STATE_VDQCR bit to disappear.
+ */
+int qman_volatile_dequeue(struct qman_fq *fq, u32 flags, u32 vdqcr);
+
 /**
  * qman_enqueue - Enqueue a frame to a frame queue
  * @fq: the frame queue object to enqueue to
@@ -994,6 +1096,13 @@ int qman_alloc_fqid_range(u32 *result, u32 count);
  */
 int qman_release_fqid(u32 fqid);
 
+/**
+ * qman_query_fq_np - Queries non-programmable FQD fields
+ * @fq: the frame queue object to be queried
+ * @np: storage for the queried FQD fields
+ */
+int qman_query_fq_np(struct qman_fq *fq, struct qm_mcr_queryfq_np *np);
+
 	/* Pool-channel management */
 /**
  * qman_alloc_pool_range - Allocate a contiguous range of pool-channel IDs
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index b54b98dc2d4a..1b0f447ce850 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -4,7 +4,12 @@
 #include <linux/types.h>
 #include <target/target_core_base.h>
 
-#define TRANSPORT_FLAG_PASSTHROUGH		1
+#define TRANSPORT_FLAG_PASSTHROUGH		0x1
+/*
+ * ALUA commands, state checks and setup operations are handled by the
+ * backend module.
+ */
+#define TRANSPORT_FLAG_PASSTHROUGH_ALUA		0x2
 
 struct request_queue;
 struct scatterlist;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 37c274e61acc..ccfad0e9c2cd 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -117,6 +117,7 @@ enum transport_state_table {
 	TRANSPORT_ISTATE_PROCESSING = 11,
 	TRANSPORT_COMPLETE_QF_WP = 18,
 	TRANSPORT_COMPLETE_QF_OK = 19,
+	TRANSPORT_COMPLETE_QF_ERR = 20,
 };
 
 /* Used for struct se_cmd->se_cmd_flags */
@@ -279,8 +280,6 @@ struct t10_alua_tg_pt_gp {
 	u16	tg_pt_gp_id;
 	int	tg_pt_gp_valid_id;
 	int	tg_pt_gp_alua_supported_states;
-	int	tg_pt_gp_alua_pending_state;
-	int	tg_pt_gp_alua_previous_state;
 	int	tg_pt_gp_alua_access_status;
 	int	tg_pt_gp_alua_access_type;
 	int	tg_pt_gp_nonop_delay_msecs;
@@ -289,18 +288,16 @@ struct t10_alua_tg_pt_gp {
 	int	tg_pt_gp_pref;
 	int	tg_pt_gp_write_metadata;
 	u32	tg_pt_gp_members;
-	atomic_t tg_pt_gp_alua_access_state;
+	int	tg_pt_gp_alua_access_state;
 	atomic_t tg_pt_gp_ref_cnt;
 	spinlock_t tg_pt_gp_lock;
-	struct mutex tg_pt_gp_md_mutex;
+	struct mutex tg_pt_gp_transition_mutex;
 	struct se_device *tg_pt_gp_dev;
 	struct config_group tg_pt_gp_group;
 	struct list_head tg_pt_gp_list;
 	struct list_head tg_pt_gp_lun_list;
 	struct se_lun *tg_pt_gp_alua_lun;
 	struct se_node_acl *tg_pt_gp_alua_nacl;
-	struct delayed_work tg_pt_gp_transition_work;
-	struct completion *tg_pt_gp_transition_complete;
 };
 
 struct t10_vpd {
@@ -705,6 +702,7 @@ struct se_lun {
 	u64			unpacked_lun;
 #define SE_LUN_LINK_MAGIC			0xffff7771
 	u32			lun_link_magic;
+	bool			lun_shutdown;
 	bool			lun_access_ro;
 	u32			lun_index;
 
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index a88ed13446ff..d0dbe60d8a6d 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -61,7 +61,16 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer,
 	TP_ARGS(bh)
 );
 
-DECLARE_EVENT_CLASS(block_rq_with_error,
+/**
+ * block_rq_requeue - place block IO request back on a queue
+ * @q: queue holding operation
+ * @rq: block IO operation request
+ *
+ * The block operation request @rq is being placed back into queue
+ * @q.  For some reason the request was not completed and needs to be
+ * put back in the queue.
+ */
+TRACE_EVENT(block_rq_requeue,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
@@ -71,7 +80,6 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 		__field(  dev_t,	dev			)
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
-		__field(  int,		errors			)
 		__array(  char,		rwbs,	RWBS_LEN	)
 		__dynamic_array( char,	cmd,	1		)
 	),
@@ -80,7 +88,6 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
-		__entry->errors    = rq->errors;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 		__get_str(cmd)[0] = '\0';
@@ -90,46 +97,13 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->rwbs, __get_str(cmd),
 		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->errors)
-);
-
-/**
- * block_rq_abort - abort block operation request
- * @q: queue containing the block operation request
- * @rq: block IO operation request
- *
- * Called immediately after pending block IO operation request @rq in
- * queue @q is aborted. The fields in the operation request @rq
- * can be examined to determine which device and sectors the pending
- * operation would access.
- */
-DEFINE_EVENT(block_rq_with_error, block_rq_abort,
-
-	TP_PROTO(struct request_queue *q, struct request *rq),
-
-	TP_ARGS(q, rq)
-);
-
-/**
- * block_rq_requeue - place block IO request back on a queue
- * @q: queue holding operation
- * @rq: block IO operation request
- *
- * The block operation request @rq is being placed back into queue
- * @q.  For some reason the request was not completed and needs to be
- * put back in the queue.
- */
-DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
-
-	TP_PROTO(struct request_queue *q, struct request *rq),
-
-	TP_ARGS(q, rq)
+		  __entry->nr_sector, 0)
 );
 
 /**
  * block_rq_complete - block IO operation completed by device driver
- * @q: queue containing the block operation request
  * @rq: block operations request
+ * @error: status code
  * @nr_bytes: number of completed bytes
  *
  * The block_rq_complete tracepoint event indicates that some portion
@@ -140,16 +114,15 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  */
 TRACE_EVENT(block_rq_complete,
 
-	TP_PROTO(struct request_queue *q, struct request *rq,
-		 unsigned int nr_bytes),
+	TP_PROTO(struct request *rq, int error, unsigned int nr_bytes),
 
-	TP_ARGS(q, rq, nr_bytes),
+	TP_ARGS(rq, error, nr_bytes),
 
 	TP_STRUCT__entry(
 		__field(  dev_t,	dev			)
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
-		__field(  int,		errors			)
+		__field(  int,		error			)
 		__array(  char,		rwbs,	RWBS_LEN	)
 		__dynamic_array( char,	cmd,	1		)
 	),
@@ -158,7 +131,7 @@ TRACE_EVENT(block_rq_complete,
 		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
 		__entry->sector    = blk_rq_pos(rq);
 		__entry->nr_sector = nr_bytes >> 9;
-		__entry->errors    = rq->errors;
+		__entry->error     = error;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
 		__get_str(cmd)[0] = '\0';
@@ -168,7 +141,7 @@ TRACE_EVENT(block_rq_complete,
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->rwbs, __get_str(cmd),
 		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->errors)
+		  __entry->nr_sector, __entry->error)
 );
 
 DECLARE_EVENT_CLASS(block_rq,
diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h
index c3a53fd47ff1..52c8425d144b 100644
--- a/include/trace/events/bpf.h
+++ b/include/trace/events/bpf.h
@@ -321,11 +321,14 @@ TRACE_EVENT(bpf_map_next_key,
 		__dynamic_array(u8, key, map->key_size)
 		__dynamic_array(u8, nxt, map->key_size)
 		__field(bool, key_trunc)
+		__field(bool, key_null)
 		__field(int, ufd)
 	),
 
 	TP_fast_assign(
-		memcpy(__get_dynamic_array(key), key, map->key_size);
+		if (key)
+			memcpy(__get_dynamic_array(key), key, map->key_size);
+		__entry->key_null = !key;
 		memcpy(__get_dynamic_array(nxt), key_next, map->key_size);
 		__entry->type      = map->map_type;
 		__entry->key_len   = min(map->key_size, 16U);
@@ -336,8 +339,9 @@ TRACE_EVENT(bpf_map_next_key,
 	TP_printk("map type=%s ufd=%d key=[%s%s] next=[%s%s]",
 		  __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB),
 		  __entry->ufd,
-		  __print_hex(__get_dynamic_array(key), __entry->key_len),
-		  __entry->key_trunc ? " ..." : "",
+		  __entry->key_null ? "NULL" : __print_hex(__get_dynamic_array(key),
+							   __entry->key_len),
+		  __entry->key_trunc && !__entry->key_null ? " ..." : "",
 		  __print_hex(__get_dynamic_array(nxt), __entry->key_len),
 		  __entry->key_trunc ? " ..." : "")
 );
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 39123c06a566..29a3d53a4015 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -683,6 +683,57 @@ TRACE_EVENT(rxrpc_rx_ack,
 		      __entry->n_acks)
 	    );
 
+TRACE_EVENT(rxrpc_rx_abort,
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+		     u32 abort_code),
+
+	    TP_ARGS(call, serial, abort_code),
+
+	    TP_STRUCT__entry(
+		    __field(struct rxrpc_call *,	call		)
+		    __field(rxrpc_serial_t,		serial		)
+		    __field(u32,			abort_code	)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call;
+		    __entry->serial = serial;
+		    __entry->abort_code = abort_code;
+			   ),
+
+	    TP_printk("c=%p ABORT %08x ac=%d",
+		      __entry->call,
+		      __entry->serial,
+		      __entry->abort_code)
+	    );
+
+TRACE_EVENT(rxrpc_rx_rwind_change,
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+		     u32 rwind, bool wake),
+
+	    TP_ARGS(call, serial, rwind, wake),
+
+	    TP_STRUCT__entry(
+		    __field(struct rxrpc_call *,	call		)
+		    __field(rxrpc_serial_t,		serial		)
+		    __field(u32,			rwind		)
+		    __field(bool,			wake		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call;
+		    __entry->serial = serial;
+		    __entry->rwind = rwind;
+		    __entry->wake = wake;
+			   ),
+
+	    TP_printk("c=%p %08x rw=%u%s",
+		      __entry->call,
+		      __entry->serial,
+		      __entry->rwind,
+		      __entry->wake ? " wake" : "")
+	    );
+
 TRACE_EVENT(rxrpc_tx_data,
 	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq,
 		     rxrpc_serial_t serial, u8 flags, bool retrans, bool lose),
@@ -1087,6 +1138,56 @@ TRACE_EVENT(rxrpc_improper_term,
 		      __entry->abort_code)
 	    );
 
+TRACE_EVENT(rxrpc_rx_eproto,
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+		     const char *why),
+
+	    TP_ARGS(call, serial, why),
+
+	    TP_STRUCT__entry(
+		    __field(struct rxrpc_call *,	call		)
+		    __field(rxrpc_serial_t,		serial		)
+		    __field(const char *,		why		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call;
+		    __entry->serial = serial;
+		    __entry->why = why;
+			   ),
+
+	    TP_printk("c=%p EPROTO %08x %s",
+		      __entry->call,
+		      __entry->serial,
+		      __entry->why)
+	    );
+
+TRACE_EVENT(rxrpc_connect_call,
+	    TP_PROTO(struct rxrpc_call *call),
+
+	    TP_ARGS(call),
+
+	    TP_STRUCT__entry(
+		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned long,		user_call_ID	)
+		    __field(u32,			cid		)
+		    __field(u32,			call_id		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call;
+		    __entry->user_call_ID = call->user_call_ID;
+		    __entry->cid = call->cid;
+		    __entry->call_id = call->call_id;
+			   ),
+
+	    TP_printk("c=%p u=%p %08x:%08x",
+		      __entry->call,
+		      (void *)__entry->user_call_ID,
+		      __entry->cid,
+		      __entry->call_id)
+	    );
+
 #endif /* _TRACE_RXRPC_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9e3ef6c99e4b..ae1409ffe99a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -70,7 +70,7 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
@@ -147,6 +147,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
+		/* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
@@ -181,7 +182,7 @@ TRACE_EVENT(sched_migrate_task,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
@@ -206,7 +207,7 @@ DECLARE_EVENT_CLASS(sched_process_template,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -253,7 +254,7 @@ TRACE_EVENT(sched_process_wait,
 	TP_fast_assign(
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 		__entry->pid		= pid_nr(pid);
-		__entry->prio		= current->prio;
+		__entry->prio		= current->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -413,9 +414,9 @@ DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
  */
 TRACE_EVENT(sched_pi_setprio,
 
-	TP_PROTO(struct task_struct *tsk, int newprio),
+	TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task),
 
-	TP_ARGS(tsk, newprio),
+	TP_ARGS(tsk, pi_task),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -428,7 +429,8 @@ TRACE_EVENT(sched_pi_setprio,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->oldprio	= tsk->prio;
-		__entry->newprio	= newprio;
+		__entry->newprio	= pi_task ? pi_task->prio : tsk->prio;
+		/* XXX SCHED_DEADLINE bits missing */
 	),
 
 	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 14e49c798135..b35533b94277 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -1,5 +1,6 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM raw_syscalls
+#undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE syscalls
 
 #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index bce990f5a35d..31acce9019a6 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -241,21 +241,21 @@ TRACE_EVENT(xen_mmu_set_pud,
 		      (int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
 	);
 
-TRACE_EVENT(xen_mmu_set_pgd,
-	    TP_PROTO(pgd_t *pgdp, pgd_t *user_pgdp, pgd_t pgdval),
-	    TP_ARGS(pgdp, user_pgdp, pgdval),
+TRACE_EVENT(xen_mmu_set_p4d,
+	    TP_PROTO(p4d_t *p4dp, p4d_t *user_p4dp, p4d_t p4dval),
+	    TP_ARGS(p4dp, user_p4dp, p4dval),
 	    TP_STRUCT__entry(
-		    __field(pgd_t *, pgdp)
-		    __field(pgd_t *, user_pgdp)
-		    __field(pgdval_t, pgdval)
-		    ),
-	    TP_fast_assign(__entry->pgdp = pgdp;
-			   __entry->user_pgdp = user_pgdp;
-			   __entry->pgdval = pgdval.pgd),
-	    TP_printk("pgdp %p user_pgdp %p pgdval %0*llx (raw %0*llx)",
-		      __entry->pgdp, __entry->user_pgdp,
-		      (int)sizeof(pgdval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->pgdval)),
-		      (int)sizeof(pgdval_t) * 2, (unsigned long long)__entry->pgdval)
+		    __field(p4d_t *, p4dp)
+		    __field(p4d_t *, user_p4dp)
+		    __field(p4dval_t, p4dval)
+		    ),
+	    TP_fast_assign(__entry->p4dp = p4dp;
+			   __entry->user_p4dp = user_p4dp;
+			   __entry->p4dval = p4d_val(p4dval)),
+	    TP_printk("p4dp %p user_p4dp %p p4dval %0*llx (raw %0*llx)",
+		      __entry->p4dp, __entry->user_p4dp,
+		      (int)sizeof(p4dval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->p4dval)),
+		      (int)sizeof(p4dval_t) * 2, (unsigned long long)__entry->p4dval)
 	);
 
 TRACE_EVENT(xen_mmu_pud_clear,
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 2c748ddad5f8..2b488565599d 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -94,4 +94,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 9b1462e38b82..061185a5eb51 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -194,8 +194,7 @@ __SYSCALL(__NR_quotactl, sys_quotactl)
 
 /* fs/readdir.c */
 #define __NR_getdents64 61
-#define __ARCH_WANT_COMPAT_SYS_GETDENTS64
-__SC_COMP(__NR_getdents64, sys_getdents64, compat_sys_getdents64)
+__SYSCALL(__NR_getdents64, sys_getdents64)
 
 /* fs/read_write.c */
 #define __NR3264_lseek 62
@@ -730,9 +729,11 @@ __SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
 __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 #define __NR_pkey_free 290
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx,     sys_statx)
 
 #undef __NR_syscalls
-#define __NR_syscalls 291
+#define __NR_syscalls 292
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/drm/omap_drm.h b/include/uapi/drm/omap_drm.h
index 407cb55df6ac..7fb97863c945 100644
--- a/include/uapi/drm/omap_drm.h
+++ b/include/uapi/drm/omap_drm.h
@@ -33,8 +33,8 @@ extern "C" {
 #define OMAP_PARAM_CHIPSET_ID	1	/* ie. 0x3430, 0x4430, etc */
 
 struct drm_omap_param {
-	uint64_t param;			/* in */
-	uint64_t value;			/* in (set_param), out (get_param) */
+	__u64 param;			/* in */
+	__u64 value;			/* in (set_param), out (get_param) */
 };
 
 #define OMAP_BO_SCANOUT		0x00000001	/* scanout capable (phys contiguous) */
@@ -53,18 +53,18 @@ struct drm_omap_param {
 #define OMAP_BO_TILED		(OMAP_BO_TILED_8 | OMAP_BO_TILED_16 | OMAP_BO_TILED_32)
 
 union omap_gem_size {
-	uint32_t bytes;		/* (for non-tiled formats) */
+	__u32 bytes;		/* (for non-tiled formats) */
 	struct {
-		uint16_t width;
-		uint16_t height;
+		__u16 width;
+		__u16 height;
 	} tiled;		/* (for tiled formats) */
 };
 
 struct drm_omap_gem_new {
 	union omap_gem_size size;	/* in */
-	uint32_t flags;			/* in */
-	uint32_t handle;		/* out */
-	uint32_t __pad;
+	__u32 flags;			/* in */
+	__u32 handle;			/* out */
+	__u32 __pad;
 };
 
 /* mask of operations: */
@@ -74,33 +74,33 @@ enum omap_gem_op {
 };
 
 struct drm_omap_gem_cpu_prep {
-	uint32_t handle;		/* buffer handle (in) */
-	uint32_t op;			/* mask of omap_gem_op (in) */
+	__u32 handle;			/* buffer handle (in) */
+	__u32 op;			/* mask of omap_gem_op (in) */
 };
 
 struct drm_omap_gem_cpu_fini {
-	uint32_t handle;		/* buffer handle (in) */
-	uint32_t op;			/* mask of omap_gem_op (in) */
+	__u32 handle;			/* buffer handle (in) */
+	__u32 op;			/* mask of omap_gem_op (in) */
 	/* TODO maybe here we pass down info about what regions are touched
 	 * by sw so we can be clever about cache ops?  For now a placeholder,
 	 * set to zero and we just do full buffer flush..
 	 */
-	uint32_t nregions;
-	uint32_t __pad;
+	__u32 nregions;
+	__u32 __pad;
 };
 
 struct drm_omap_gem_info {
-	uint32_t handle;		/* buffer handle (in) */
-	uint32_t pad;
-	uint64_t offset;		/* mmap offset (out) */
+	__u32 handle;			/* buffer handle (in) */
+	__u32 pad;
+	__u64 offset;			/* mmap offset (out) */
 	/* note: in case of tiled buffers, the user virtual size can be
 	 * different from the physical size (ie. how many pages are needed
 	 * to back the object) which is returned in DRM_IOCTL_GEM_OPEN..
 	 * This size here is the one that should be used if you want to
 	 * mmap() the buffer:
 	 */
-	uint32_t size;			/* virtual size for mmap'ing (out) */
-	uint32_t __pad;
+	__u32 size;			/* virtual size for mmap'ing (out) */
+	__u32 __pad;
 };
 
 #define DRM_OMAP_GET_PARAM		0x00
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index dd9820b1c779..6b0e2758585f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -445,6 +445,7 @@ header-y += unistd.h
 header-y += unix_diag.h
 header-y += usbdevice_fs.h
 header-y += usbip.h
+header-y += userio.h
 header-y += utime.h
 header-y += utsname.h
 header-y += uuid.h
@@ -476,6 +477,7 @@ header-y += virtio_types.h
 header-y += virtio_vsock.h
 header-y += virtio_crypto.h
 header-y += vm_sockets.h
+header-y += vsockmon.h
 header-y += vt.h
 header-y += vtpm_proxy.h
 header-y += wait.h
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0539a0ceef38..945a1f5f63c5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -81,6 +81,7 @@ enum bpf_cmd {
 	BPF_OBJ_GET,
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
+	BPF_PROG_TEST_RUN,
 };
 
 enum bpf_map_type {
@@ -96,6 +97,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_LRU_HASH,
 	BPF_MAP_TYPE_LRU_PERCPU_HASH,
 	BPF_MAP_TYPE_LPM_TRIE,
+	BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	BPF_MAP_TYPE_HASH_OF_MAPS,
 };
 
 enum bpf_prog_type {
@@ -152,6 +155,7 @@ union bpf_attr {
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
 		__u32	map_flags;	/* prealloc or not */
+		__u32	inner_map_fd;	/* fd pointing to the inner map */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -186,6 +190,17 @@ union bpf_attr {
 		__u32		attach_type;
 		__u32		attach_flags;
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+		__u32		prog_fd;
+		__u32		retval;
+		__u32		data_size_in;
+		__u32		data_size_out;
+		__aligned_u64	data_in;
+		__aligned_u64	data_out;
+		__u32		repeat;
+		__u32		duration;
+	} test;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -456,6 +471,17 @@ union bpf_attr {
  *     Return:
  *       > 0 length of the string including the trailing NUL on success
  *       < 0 error
+ *
+ * u64 bpf_get_socket_cookie(skb)
+ *     Get the cookie for the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ *     field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ *     Get the owner uid of the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: uid of the socket owner on success or overflowuid if failed.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -503,7 +529,9 @@ union bpf_attr {
 	FN(get_numa_node_id),		\
 	FN(skb_change_head),		\
 	FN(xdp_adjust_head),		\
-	FN(probe_read_str),
+	FN(probe_read_str),		\
+	FN(get_socket_cookie),		\
+	FN(get_socket_uid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -574,6 +602,7 @@ struct __sk_buff {
 	__u32 tc_classid;
 	__u32 data;
 	__u32 data_end;
+	__u32 napi_id;
 };
 
 struct bpf_tunnel_key {
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index db4c253f8011..dcfc3a5a9cb1 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -713,33 +713,6 @@ enum btrfs_err_code {
 	BTRFS_ERROR_DEV_ONLY_WRITABLE,
 	BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS
 };
-/* An error code to error string mapping for the kernel
-*  error codes
-*/
-static inline char *btrfs_err_str(enum btrfs_err_code err_code)
-{
-	switch (err_code) {
-		case BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET:
-			return "unable to go below two devices on raid1";
-		case BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET:
-			return "unable to go below four devices on raid10";
-		case BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET:
-			return "unable to go below two devices on raid5";
-		case BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET:
-			return "unable to go below three devices on raid6";
-		case BTRFS_ERROR_DEV_TGT_REPLACE:
-			return "unable to remove the dev_replace target dev";
-		case BTRFS_ERROR_DEV_MISSING_NOT_FOUND:
-			return "no missing devices found to remove";
-		case BTRFS_ERROR_DEV_ONLY_WRITABLE:
-			return "unable to remove the only writeable device";
-		case BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS:
-			return "add/delete/balance/replace/resize operation "\
-				"in progress";
-		default:
-			return NULL;
-	}
-}
 
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h
new file mode 100644
index 000000000000..ffb0b7156f7e
--- /dev/null
+++ b/include/uapi/linux/can/vxcan.h
@@ -0,0 +1,12 @@
+#ifndef _UAPI_CAN_VXCAN_H
+#define _UAPI_CAN_VXCAN_H
+
+enum {
+	VXCAN_INFO_UNSPEC,
+	VXCAN_INFO_PEER,
+
+	__VXCAN_INFO_MAX
+#define VXCAN_INFO_MAX	(__VXCAN_INFO_MAX - 1)
+};
+
+#endif
diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h
index 11d21fce14d6..b4def5c630e7 100644
--- a/include/uapi/linux/cryptouser.h
+++ b/include/uapi/linux/cryptouser.h
@@ -31,7 +31,7 @@ enum {
 #define CRYPTO_MSG_MAX (__CRYPTO_MSG_MAX - 1)
 #define CRYPTO_NR_MSGTYPES (CRYPTO_MSG_MAX + 1 - CRYPTO_MSG_BASE)
 
-#define CRYPTO_MAX_NAME CRYPTO_MAX_ALG_NAME
+#define CRYPTO_MAX_NAME 64
 
 /* Netlink message attributes.  */
 enum crypto_attr_type_t {
@@ -53,9 +53,9 @@ enum crypto_attr_type_t {
 };
 
 struct crypto_user_alg {
-	char cru_name[CRYPTO_MAX_ALG_NAME];
-	char cru_driver_name[CRYPTO_MAX_ALG_NAME];
-	char cru_module_name[CRYPTO_MAX_ALG_NAME];
+	char cru_name[CRYPTO_MAX_NAME];
+	char cru_driver_name[CRYPTO_MAX_NAME];
+	char cru_module_name[CRYPTO_MAX_NAME];
 	__u32 cru_type;
 	__u32 cru_mask;
 	__u32 cru_refcnt;
@@ -73,7 +73,7 @@ struct crypto_report_hash {
 };
 
 struct crypto_report_cipher {
-	char type[CRYPTO_MAX_ALG_NAME];
+	char type[CRYPTO_MAX_NAME];
 	unsigned int blocksize;
 	unsigned int min_keysize;
 	unsigned int max_keysize;
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 0f1f3a12e23c..b0e807ac53bb 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -65,8 +65,12 @@ enum devlink_command {
 #define DEVLINK_CMD_ESWITCH_MODE_SET /* obsolete, never use this! */ \
 	DEVLINK_CMD_ESWITCH_SET
 
-	/* add new commands above here */
+	DEVLINK_CMD_DPIPE_TABLE_GET,
+	DEVLINK_CMD_DPIPE_ENTRIES_GET,
+	DEVLINK_CMD_DPIPE_HEADERS_GET,
+	DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
 
+	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
 };
@@ -115,6 +119,11 @@ enum devlink_eswitch_inline_mode {
 	DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT,
 };
 
+enum devlink_eswitch_encap_mode {
+	DEVLINK_ESWITCH_ENCAP_MODE_NONE,
+	DEVLINK_ESWITCH_ENCAP_MODE_BASIC,
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -148,10 +157,73 @@ enum devlink_attr {
 	DEVLINK_ATTR_ESWITCH_MODE,		/* u16 */
 	DEVLINK_ATTR_ESWITCH_INLINE_MODE,	/* u8 */
 
+	DEVLINK_ATTR_DPIPE_TABLES,		/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE,		/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE_NAME,		/* string */
+	DEVLINK_ATTR_DPIPE_TABLE_SIZE,		/* u64 */
+	DEVLINK_ATTR_DPIPE_TABLE_MATCHES,	/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE_ACTIONS,	/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,	/* u8 */
+
+	DEVLINK_ATTR_DPIPE_ENTRIES,		/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY,		/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY_INDEX,		/* u64 */
+	DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES,	/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES,	/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,	/* u64 */
+
+	DEVLINK_ATTR_DPIPE_MATCH,		/* nested */
+	DEVLINK_ATTR_DPIPE_MATCH_VALUE,		/* nested */
+	DEVLINK_ATTR_DPIPE_MATCH_TYPE,		/* u32 */
+
+	DEVLINK_ATTR_DPIPE_ACTION,		/* nested */
+	DEVLINK_ATTR_DPIPE_ACTION_VALUE,	/* nested */
+	DEVLINK_ATTR_DPIPE_ACTION_TYPE,		/* u32 */
+
+	DEVLINK_ATTR_DPIPE_VALUE,
+	DEVLINK_ATTR_DPIPE_VALUE_MASK,
+	DEVLINK_ATTR_DPIPE_VALUE_MAPPING,	/* u32 */
+
+	DEVLINK_ATTR_DPIPE_HEADERS,		/* nested */
+	DEVLINK_ATTR_DPIPE_HEADER,		/* nested */
+	DEVLINK_ATTR_DPIPE_HEADER_NAME,		/* string */
+	DEVLINK_ATTR_DPIPE_HEADER_ID,		/* u32 */
+	DEVLINK_ATTR_DPIPE_HEADER_FIELDS,	/* nested */
+	DEVLINK_ATTR_DPIPE_HEADER_GLOBAL,	/* u8 */
+	DEVLINK_ATTR_DPIPE_HEADER_INDEX,	/* u32 */
+
+	DEVLINK_ATTR_DPIPE_FIELD,		/* nested */
+	DEVLINK_ATTR_DPIPE_FIELD_NAME,		/* string */
+	DEVLINK_ATTR_DPIPE_FIELD_ID,		/* u32 */
+	DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH,	/* u32 */
+	DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE,	/* u32 */
+
+	DEVLINK_ATTR_PAD,
+
+	DEVLINK_ATTR_ESWITCH_ENCAP_MODE,	/* u8 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
 	DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
 };
 
+/* Mapping between internal resource described by the field and system
+ * structure
+ */
+enum devlink_dpipe_field_mapping_type {
+	DEVLINK_DPIPE_FIELD_MAPPING_TYPE_NONE,
+	DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+};
+
+/* Match type - specify the type of the match */
+enum devlink_dpipe_match_type {
+	DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT,
+};
+
+/* Action type - specify the action type */
+enum devlink_dpipe_action_type {
+	DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY,
+};
+
 #endif /* _UAPI_LINUX_DEVLINK_H_ */
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index cb5d1a519202..9cd1de954c0a 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -42,7 +42,6 @@
 #define EM_TILEGX	191	/* Tilera TILE-Gx */
 #define EM_BPF		247	/* Linux BPF - in-kernel virtual machine */
 #define EM_FRV		0x5441	/* Fujitsu FR-V */
-#define EM_AVR32	0x18ad	/* Atmel AVR32 */
 
 /*
  * This is an interim value that we will use until the committee comes
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index b59ee077a596..176b6cb1008d 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -409,6 +409,8 @@ typedef struct elf64_shdr {
 #define NT_S390_TDB	0x308		/* s390 transaction diagnostic block */
 #define NT_S390_VXRS_LOW	0x309	/* s390 vector registers 0-15 upper half */
 #define NT_S390_VXRS_HIGH	0x30a	/* s390 vector registers 16-31 */
+#define NT_S390_GS_CB	0x30b		/* s390 guarded storage registers */
+#define NT_S390_GS_BC	0x30c		/* s390 guarded storage broadcast control block */
 #define NT_ARM_VFP	0x400		/* ARM VFP/NEON registers */
 #define NT_ARM_TLS	0x401		/* ARM TLS register */
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 3dc91a46e8b8..5f4ea28eabe4 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1487,6 +1487,7 @@ enum ethtool_link_mode_bit_indices {
  */
 
 /* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. */
+/* Update drivers/net/phy/phy.c:phy_speed_to_str() when adding new values */
 #define SPEED_10		10
 #define SPEED_100		100
 #define SPEED_1000		1000
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index 72a04a0e8cce..57d1edb8efd9 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -19,7 +19,8 @@ enum gtp_attrs {
 	GTPA_LINK,
 	GTPA_VERSION,
 	GTPA_TID,	/* for GTPv0 only */
-	GTPA_SGSN_ADDRESS,
+	GTPA_PEER_ADDRESS,	/* Remote GSN peer, either SGSN or GGSN */
+#define GTPA_SGSN_ADDRESS GTPA_PEER_ADDRESS /* maintain legacy attr name */
 	GTPA_MS_ADDRESS,
 	GTPA_FLOW,
 	GTPA_NET_NS_FD,
diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h
index 4d024d75d64b..cf73510b9238 100644
--- a/include/uapi/linux/if_arp.h
+++ b/include/uapi/linux/if_arp.h
@@ -95,6 +95,7 @@
 #define ARPHRD_IP6GRE	823		/* GRE over IPv6		*/
 #define ARPHRD_NETLINK	824		/* Netlink header		*/
 #define ARPHRD_6LOWPAN	825		/* IPv6 over LoWPAN             */
+#define ARPHRD_VSOCKMON	826		/* Vsock monitor header		*/
 
 #define ARPHRD_VOID	  0xFFFF	/* Void type, nothing is known */
 #define ARPHRD_NONE	  0xFFFE	/* zero header length */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 320fc1e747ee..8e56ac70e0d1 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -323,6 +323,7 @@ enum {
 	IFLA_BRPORT_MCAST_FLOOD,
 	IFLA_BRPORT_MCAST_TO_UCAST,
 	IFLA_BRPORT_VLAN_TUNNEL,
+	IFLA_BRPORT_BCAST_FLOOD,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -538,11 +539,18 @@ enum {
 #define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
 
 /* GTP section */
+
+enum ifla_gtp_role {
+	GTP_ROLE_GGSN = 0,
+	GTP_ROLE_SGSN,
+};
+
 enum {
 	IFLA_GTP_UNSPEC,
 	IFLA_GTP_FD0,
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
+	IFLA_GTP_ROLE,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -880,7 +888,9 @@ enum {
 /* XDP section */
 
 #define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
-#define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST)
+#define XDP_FLAGS_SKB_MODE		(2U << 0)
+#define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
+					 XDP_FLAGS_SKB_MODE)
 
 enum {
 	IFLA_XDP_UNSPEC,
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 9e7edfd8141e..4df96a7dd4fa 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -66,6 +66,7 @@ struct sockaddr_ll {
 #define PACKET_FANOUT_CBPF		6
 #define PACKET_FANOUT_EBPF		7
 #define PACKET_FANOUT_FLAG_ROLLOVER	0x1000
+#define PACKET_FANOUT_FLAG_UNIQUEID	0x2000
 #define PACKET_FANOUT_FLAG_DEFRAG	0x8000
 
 struct tpacket_stats {
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 92f3c8677523..6792d1967d31 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -75,6 +75,7 @@ enum {
 	IFLA_IPTUN_ENCAP_SPORT,
 	IFLA_IPTUN_ENCAP_DPORT,
 	IFLA_IPTUN_COLLECT_METADATA,
+	IFLA_IPTUN_FWMARK,
 	__IFLA_IPTUN_MAX,
 };
 #define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
@@ -132,6 +133,7 @@ enum {
 	IFLA_GRE_ENCAP_DPORT,
 	IFLA_GRE_COLLECT_METADATA,
 	IFLA_GRE_IGNORE_DF,
+	IFLA_GRE_FWMARK,
 	__IFLA_GRE_MAX,
 };
 
@@ -147,6 +149,7 @@ enum {
 	IFLA_VTI_OKEY,
 	IFLA_VTI_LOCAL,
 	IFLA_VTI_REMOTE,
+	IFLA_VTI_FWMARK,
 	__IFLA_VTI_MAX,
 };
 
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 3af60ee69053..f5a8d96e1e09 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -641,6 +641,7 @@
  * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.)
  */
 #define KEY_DATA			0x277
+#define KEY_ONSCREEN_KEYBOARD		0x278
 
 #define BTN_TRIGGER_HAPPY		0x2c0
 #define BTN_TRIGGER_HAPPY1		0x2c0
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index e794f7bee22f..f561c0eb7d63 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -61,9 +61,14 @@ struct input_id {
  * Note that input core does not clamp reported values to the
  * [minimum, maximum] limits, such task is left to userspace.
  *
- * Resolution for main axes (ABS_X, ABS_Y, ABS_Z) is reported in
- * units per millimeter (units/mm), resolution for rotational axes
- * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian.
+ * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z)
+ * is reported in units per millimeter (units/mm), resolution
+ * for rotational axes (ABS_RX, ABS_RY, ABS_RZ) is reported
+ * in units per radian.
+ * When INPUT_PROP_ACCELEROMETER is set the resolution changes.
+ * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in
+ * in units per g (units/g) and in units per degree per second
+ * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ).
  */
 struct input_absinfo {
 	__s32 value;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 8ef9e75e004e..2ae59178189d 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -183,6 +183,8 @@ enum {
 	DEVCONF_SEG6_REQUIRE_HMAC,
 	DEVCONF_ENHANCED_DAD,
 	DEVCONF_ADDR_GEN_MODE,
+	DEVCONF_DISABLE_POLICY,
+	DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN,
 	DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index 85bbb1799df3..d496c02e14bc 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -35,7 +35,7 @@
 #define RTF_PREF(pref)	((pref) << 27)
 #define RTF_PREF_MASK	0x18000000
 
-#define RTF_PCPU	0x40000000
+#define RTF_PCPU	0x40000000	/* read-only: can not be set by user */
 #define RTF_LOCAL	0x80000000
 
 
diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h
index fd19f36b3129..c8aec4b9e73b 100644
--- a/include/uapi/linux/lightnvm.h
+++ b/include/uapi/linux/lightnvm.h
@@ -85,6 +85,10 @@ struct nvm_ioctl_create_conf {
 	};
 };
 
+enum {
+	NVM_TARGET_FACTORY = 1 << 0,	/* Init target in factory mode */
+};
+
 struct nvm_ioctl_create {
 	char dev[DISK_NAME_LEN];		/* open-channel SSD device */
 	char tgttype[NVM_TTYPE_NAME_MAX];	/* target type name */
diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h
index d80a0498f77e..f5e45095b0bb 100644
--- a/include/uapi/linux/mpls_iptunnel.h
+++ b/include/uapi/linux/mpls_iptunnel.h
@@ -16,11 +16,13 @@
 /* MPLS tunnel attributes
  * [RTA_ENCAP] = {
  *     [MPLS_IPTUNNEL_DST]
+ *     [MPLS_IPTUNNEL_TTL]
  * }
  */
 enum {
 	MPLS_IPTUNNEL_UNSPEC,
 	MPLS_IPTUNNEL_DST,
+	MPLS_IPTUNNEL_TTL,
 	__MPLS_IPTUNNEL_MAX,
 };
 #define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
diff --git a/include/uapi/linux/nbd-netlink.h b/include/uapi/linux/nbd-netlink.h
new file mode 100644
index 000000000000..6f7ca3d63a65
--- /dev/null
+++ b/include/uapi/linux/nbd-netlink.h
@@ -0,0 +1,98 @@
+/*
+ * Copyright (C) 2017 Facebook.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+#ifndef _UAPILINUX_NBD_NETLINK_H
+#define _UAPILINUX_NBD_NETLINK_H
+
+#define NBD_GENL_FAMILY_NAME		"nbd"
+#define NBD_GENL_VERSION		0x1
+#define NBD_GENL_MCAST_GROUP_NAME	"nbd_mc_group"
+
+/* Configuration policy attributes, used for CONNECT */
+enum {
+	NBD_ATTR_UNSPEC,
+	NBD_ATTR_INDEX,
+	NBD_ATTR_SIZE_BYTES,
+	NBD_ATTR_BLOCK_SIZE_BYTES,
+	NBD_ATTR_TIMEOUT,
+	NBD_ATTR_SERVER_FLAGS,
+	NBD_ATTR_CLIENT_FLAGS,
+	NBD_ATTR_SOCKETS,
+	NBD_ATTR_DEAD_CONN_TIMEOUT,
+	NBD_ATTR_DEVICE_LIST,
+	__NBD_ATTR_MAX,
+};
+#define NBD_ATTR_MAX (__NBD_ATTR_MAX - 1)
+
+/*
+ * This is the format for multiple devices with NBD_ATTR_DEVICE_LIST
+ *
+ * [NBD_ATTR_DEVICE_LIST]
+ *   [NBD_DEVICE_ITEM]
+ *     [NBD_DEVICE_INDEX]
+ *     [NBD_DEVICE_CONNECTED]
+ */
+enum {
+	NBD_DEVICE_ITEM_UNSPEC,
+	NBD_DEVICE_ITEM,
+	__NBD_DEVICE_ITEM_MAX,
+};
+#define NBD_DEVICE_ITEM_MAX (__NBD_DEVICE_ITEM_MAX - 1)
+
+enum {
+	NBD_DEVICE_UNSPEC,
+	NBD_DEVICE_INDEX,
+	NBD_DEVICE_CONNECTED,
+	__NBD_DEVICE_MAX,
+};
+#define NBD_DEVICE_ATTR_MAX (__NBD_DEVICE_MAX - 1)
+
+/*
+ * This is the format for multiple sockets with NBD_ATTR_SOCKETS
+ *
+ * [NBD_ATTR_SOCKETS]
+ *   [NBD_SOCK_ITEM]
+ *     [NBD_SOCK_FD]
+ *   [NBD_SOCK_ITEM]
+ *     [NBD_SOCK_FD]
+ */
+enum {
+	NBD_SOCK_ITEM_UNSPEC,
+	NBD_SOCK_ITEM,
+	__NBD_SOCK_ITEM_MAX,
+};
+#define NBD_SOCK_ITEM_MAX (__NBD_SOCK_ITEM_MAX - 1)
+
+enum {
+	NBD_SOCK_UNSPEC,
+	NBD_SOCK_FD,
+	__NBD_SOCK_MAX,
+};
+#define NBD_SOCK_MAX (__NBD_SOCK_MAX - 1)
+
+enum {
+	NBD_CMD_UNSPEC,
+	NBD_CMD_CONNECT,
+	NBD_CMD_DISCONNECT,
+	NBD_CMD_RECONFIGURE,
+	NBD_CMD_LINK_DEAD,
+	NBD_CMD_STATUS,
+	__NBD_CMD_MAX,
+};
+#define NBD_CMD_MAX	(__NBD_CMD_MAX - 1)
+
+#endif /* _UAPILINUX_NBD_NETLINK_H */
diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h
index c91c642ea900..155e33f81913 100644
--- a/include/uapi/linux/nbd.h
+++ b/include/uapi/linux/nbd.h
@@ -37,7 +37,7 @@ enum {
 	NBD_CMD_TRIM = 4
 };
 
-/* values for flags field */
+/* values for flags field, these are server interaction specific. */
 #define NBD_FLAG_HAS_FLAGS	(1 << 0) /* nbd-server supports flags */
 #define NBD_FLAG_READ_ONLY	(1 << 1) /* device is read-only */
 #define NBD_FLAG_SEND_FLUSH	(1 << 2) /* can flush writeback cache */
@@ -45,6 +45,10 @@ enum {
 #define NBD_FLAG_SEND_TRIM	(1 << 5) /* send trim/discard */
 #define NBD_FLAG_CAN_MULTI_CONN	(1 << 8)	/* Server supports multiple connections per export. */
 
+/* These are client behavior specific flags. */
+#define NBD_CFLAG_DESTROY_ON_DISCONNECT	(1 << 0) /* delete the nbd device on
+						    disconnect. */
+
 /* userspace doesn't need the nbd_device structure */
 
 /* These are sent over the network in the request/reply magic fields */
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 6a8e33dd4ecb..a8072cc7fa0b 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -28,12 +28,14 @@ enum ip_conntrack_info {
 	/* only for userspace compatibility */
 #ifndef __KERNEL__
 	IP_CT_NEW_REPLY = IP_CT_NUMBER,
+#else
+	IP_CT_UNTRACKED = 7,
 #endif
 };
 
 #define NF_CT_STATE_INVALID_BIT			(1 << 0)
 #define NF_CT_STATE_BIT(ctinfo)			(1 << ((ctinfo) % IP_CT_IS_REPLY + 1))
-#define NF_CT_STATE_UNTRACKED_BIT		(1 << (IP_CT_NUMBER + 1))
+#define NF_CT_STATE_UNTRACKED_BIT		(1 << (IP_CT_UNTRACKED + 1))
 
 /* Bitset representing status of connection. */
 enum ip_conntrack_status {
@@ -94,7 +96,7 @@ enum ip_conntrack_status {
 	IPS_TEMPLATE_BIT = 11,
 	IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT),
 
-	/* Conntrack is a fake untracked entry */
+	/* Conntrack is a fake untracked entry.  Obsolete and not used anymore */
 	IPS_UNTRACKED_BIT = 12,
 	IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
 
@@ -117,6 +119,9 @@ enum ip_conntrack_events {
 	IPCT_NATSEQADJ = IPCT_SEQADJ,
 	IPCT_SECMARK,		/* new security mark has been set */
 	IPCT_LABEL,		/* new connlabel has been set */
+#ifdef __KERNEL__
+	__IPCT_MAX
+#endif
 };
 
 enum ip_conntrack_expect_events {
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 05215d30fe5c..683f6f88fcac 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -816,6 +816,17 @@ enum nft_rt_keys {
 };
 
 /**
+ * enum nft_hash_types - nf_tables hash expression types
+ *
+ * @NFT_HASH_JENKINS: Jenkins Hash
+ * @NFT_HASH_SYM: Symmetric Hash
+ */
+enum nft_hash_types {
+	NFT_HASH_JENKINS,
+	NFT_HASH_SYM,
+};
+
+/**
  * enum nft_hash_attributes - nf_tables hash expression netlink attributes
  *
  * @NFTA_HASH_SREG: source register (NLA_U32)
@@ -824,6 +835,7 @@ enum nft_rt_keys {
  * @NFTA_HASH_MODULUS: modulus value (NLA_U32)
  * @NFTA_HASH_SEED: seed value (NLA_U32)
  * @NFTA_HASH_OFFSET: add this offset value to hash result (NLA_U32)
+ * @NFTA_HASH_TYPE: hash operation (NLA_U32: nft_hash_types)
  */
 enum nft_hash_attributes {
 	NFTA_HASH_UNSPEC,
@@ -833,6 +845,7 @@ enum nft_hash_attributes {
 	NFTA_HASH_MODULUS,
 	NFTA_HASH_SEED,
 	NFTA_HASH_OFFSET,
+	NFTA_HASH_TYPE,
 	__NFTA_HASH_MAX,
 };
 #define NFTA_HASH_MAX	(__NFTA_HASH_MAX - 1)
@@ -888,6 +901,7 @@ enum nft_rt_attributes {
  * @NFT_CT_BYTES: conntrack bytes
  * @NFT_CT_AVGPKT: conntrack average bytes per packet
  * @NFT_CT_ZONE: conntrack zone
+ * @NFT_CT_EVENTMASK: ctnetlink events to be generated for this conntrack
  */
 enum nft_ct_keys {
 	NFT_CT_STATE,
@@ -908,6 +922,7 @@ enum nft_ct_keys {
 	NFT_CT_BYTES,
 	NFT_CT_AVGPKT,
 	NFT_CT_ZONE,
+	NFT_CT_EVENTMASK,
 };
 
 /**
@@ -1244,12 +1259,23 @@ enum nft_fib_flags {
 	NFTA_FIB_F_MARK		= 1 << 2,	/* use skb->mark */
 	NFTA_FIB_F_IIF		= 1 << 3,	/* restrict to iif */
 	NFTA_FIB_F_OIF		= 1 << 4,	/* restrict to oif */
+	NFTA_FIB_F_PRESENT	= 1 << 5,	/* check existence only */
+};
+
+enum nft_ct_helper_attributes {
+	NFTA_CT_HELPER_UNSPEC,
+	NFTA_CT_HELPER_NAME,
+	NFTA_CT_HELPER_L3PROTO,
+	NFTA_CT_HELPER_L4PROTO,
+	__NFTA_CT_HELPER_MAX,
 };
+#define NFTA_CT_HELPER_MAX	(__NFTA_CT_HELPER_MAX - 1)
 
 #define NFT_OBJECT_UNSPEC	0
 #define NFT_OBJECT_COUNTER	1
 #define NFT_OBJECT_QUOTA	2
-#define __NFT_OBJECT_MAX	3
+#define NFT_OBJECT_CT_HELPER	3
+#define __NFT_OBJECT_MAX	4
 #define NFT_OBJECT_MAX		(__NFT_OBJECT_MAX - 1)
 
 /**
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index f3946a27bd07..f86127a46cfc 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -50,12 +50,12 @@ struct nlmsghdr {
 
 /* Flags values */
 
-#define NLM_F_REQUEST		1	/* It is request message. 	*/
-#define NLM_F_MULTI		2	/* Multipart message, terminated by NLMSG_DONE */
-#define NLM_F_ACK		4	/* Reply with ack, with zero or error code */
-#define NLM_F_ECHO		8	/* Echo this request 		*/
-#define NLM_F_DUMP_INTR		16	/* Dump was inconsistent due to sequence change */
-#define NLM_F_DUMP_FILTERED	32	/* Dump was filtered as requested */
+#define NLM_F_REQUEST		0x01	/* It is request message. 	*/
+#define NLM_F_MULTI		0x02	/* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK		0x04	/* Reply with ack, with zero or error code */
+#define NLM_F_ECHO		0x08	/* Echo this request 		*/
+#define NLM_F_DUMP_INTR		0x10	/* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED	0x20	/* Dump was filtered as requested */
 
 /* Modifiers to GET request */
 #define NLM_F_ROOT	0x100	/* specify tree	root	*/
@@ -69,6 +69,10 @@ struct nlmsghdr {
 #define NLM_F_CREATE	0x400	/* Create, if it does not exist	*/
 #define NLM_F_APPEND	0x800	/* Add to end of list		*/
 
+/* Flags for ACK message */
+#define NLM_F_CAPPED	0x100	/* request was capped */
+#define NLM_F_ACK_TLVS	0x200	/* extended ACK TVLs were included */
+
 /*
    4.4BSD ADD		NLM_F_CREATE|NLM_F_EXCL
    4.4BSD CHANGE	NLM_F_REPLACE
@@ -101,6 +105,37 @@ struct nlmsghdr {
 struct nlmsgerr {
 	int		error;
 	struct nlmsghdr msg;
+	/*
+	 * followed by the message contents unless NETLINK_CAP_ACK was set
+	 * or the ACK indicates success (error == 0)
+	 * message length is aligned with NLMSG_ALIGN()
+	 */
+	/*
+	 * followed by TLVs defined in enum nlmsgerr_attrs
+	 * if NETLINK_EXT_ACK was set
+	 */
+};
+
+/**
+ * enum nlmsgerr_attrs - nlmsgerr attributes
+ * @NLMSGERR_ATTR_UNUSED: unused
+ * @NLMSGERR_ATTR_MSG: error message string (string)
+ * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original
+ *	 message, counting from the beginning of the header (u32)
+ * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
+ *	be used - in the success case - to identify a created
+ *	object or operation or similar (binary)
+ * @__NLMSGERR_ATTR_MAX: number of attributes
+ * @NLMSGERR_ATTR_MAX: highest attribute number
+ */
+enum nlmsgerr_attrs {
+	NLMSGERR_ATTR_UNUSED,
+	NLMSGERR_ATTR_MSG,
+	NLMSGERR_ATTR_OFFS,
+	NLMSGERR_ATTR_COOKIE,
+
+	__NLMSGERR_ATTR_MAX,
+	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
 };
 
 #define NETLINK_ADD_MEMBERSHIP		1
@@ -115,6 +150,7 @@ struct nlmsgerr {
 #define NETLINK_LISTEN_ALL_NSID		8
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
+#define NETLINK_EXT_ACK			11
 
 struct nl_pktinfo {
 	__u32	group;
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index 76b4d87c83a8..6dcd4de3397b 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -38,6 +38,7 @@ enum {
 	NETLINK_DIAG_GROUPS,
 	NETLINK_DIAG_RX_RING,
 	NETLINK_DIAG_TX_RING,
+	NETLINK_DIAG_FLAGS,
 
 	__NETLINK_DIAG_MAX,
 };
@@ -52,5 +53,14 @@ enum {
 /* deprecated since 4.6 */
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
 #endif
+#define NDIAG_SHOW_FLAGS	0x00000008 /* show flags of a netlink socket */
+
+/* flags */
+#define NDIAG_FLAG_CB_RUNNING		0x00000001
+#define NDIAG_FLAG_PKTINFO		0x00000002
+#define NDIAG_FLAG_BROADCAST_ERROR	0x00000004
+#define NDIAG_FLAG_NO_ENOBUFS		0x00000008
+#define NDIAG_FLAG_LISTEN_ALL_NSID	0x00000010
+#define NDIAG_FLAG_CAP_ACK		0x00000020
 
 #endif
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 5ed257c4cd4e..b8c44b98f12d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -173,6 +173,42 @@
  */
 
 /**
+ * DOC: FILS shared key authentication offload
+ *
+ * FILS shared key authentication offload can be advertized by drivers by
+ * setting @NL80211_EXT_FEATURE_FILS_SK_OFFLOAD flag. The drivers that support
+ * FILS shared key authentication offload should be able to construct the
+ * authentication and association frames for FILS shared key authentication and
+ * eventually do a key derivation as per IEEE 802.11ai. The below additional
+ * parameters should be given to driver in %NL80211_CMD_CONNECT.
+ *	%NL80211_ATTR_FILS_ERP_USERNAME - used to construct keyname_nai
+ *	%NL80211_ATTR_FILS_ERP_REALM - used to construct keyname_nai
+ *	%NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM - used to construct erp message
+ *	%NL80211_ATTR_FILS_ERP_RRK - used to generate the rIK and rMSK
+ * rIK should be used to generate an authentication tag on the ERP message and
+ * rMSK should be used to derive a PMKSA.
+ * rIK, rMSK should be generated and keyname_nai, sequence number should be used
+ * as specified in IETF RFC 6696.
+ *
+ * When FILS shared key authentication is completed, driver needs to provide the
+ * below additional parameters to userspace.
+ *	%NL80211_ATTR_FILS_KEK - used for key renewal
+ *	%NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM - used in further EAP-RP exchanges
+ *	%NL80211_ATTR_PMKID - used to identify the PMKSA used/generated
+ *	%Nl80211_ATTR_PMK - used to update PMKSA cache in userspace
+ * The PMKSA can be maintained in userspace persistently so that it can be used
+ * later after reboots or wifi turn off/on also.
+ *
+ * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertized by a FILS
+ * capable AP supporting PMK caching. It specifies the scope within which the
+ * PMKSAs are cached in an ESS. %NL80211_CMD_SET_PMKSA and
+ * %NL80211_CMD_DEL_PMKSA are enhanced to allow support for PMKSA caching based
+ * on FILS cache identifier. Additionally %NL80211_ATTR_PMK is used with
+ * %NL80211_SET_PMKSA to specify the PMK corresponding to a PMKSA for driver to
+ * use in a FILS shared key connection with PMKSA caching.
+ */
+
+/**
  * enum nl80211_commands - supported nl80211 commands
  *
  * @NL80211_CMD_UNSPEC: unspecified command to catch errors
@@ -351,7 +387,9 @@
  *	are used.  Extra IEs can also be passed from the userspace by
  *	using the %NL80211_ATTR_IE attribute.  The first cycle of the
  *	scheduled scan can be delayed by %NL80211_ATTR_SCHED_SCAN_DELAY
- *	is supplied.
+ *	is supplied. If the device supports multiple concurrent scheduled
+ *	scans, it will allow such when the caller provides the flag attribute
+ *	%NL80211_ATTR_SCHED_SCAN_MULTI to indicate user-space support for it.
  * @NL80211_CMD_STOP_SCHED_SCAN: stop a scheduled scan. Returns -ENOENT if
  *	scheduled scan is not running. The caller may assume that as soon
  *	as the call returns, it is safe to start a new scheduled scan again.
@@ -370,10 +408,18 @@
  * @NL80211_CMD_NEW_SURVEY_RESULTS: survey data notification (as a reply to
  *	NL80211_CMD_GET_SURVEY and on the "scan" multicast group)
  *
- * @NL80211_CMD_SET_PMKSA: Add a PMKSA cache entry, using %NL80211_ATTR_MAC
- *	(for the BSSID) and %NL80211_ATTR_PMKID.
+ * @NL80211_CMD_SET_PMKSA: Add a PMKSA cache entry using %NL80211_ATTR_MAC
+ *	(for the BSSID), %NL80211_ATTR_PMKID, and optionally %NL80211_ATTR_PMK
+ *	(PMK is used for PTKSA derivation in case of FILS shared key offload) or
+ *	using %NL80211_ATTR_SSID, %NL80211_ATTR_FILS_CACHE_ID,
+ *	%NL80211_ATTR_PMKID, and %NL80211_ATTR_PMK in case of FILS
+ *	authentication where %NL80211_ATTR_FILS_CACHE_ID is the identifier
+ *	advertized by a FILS capable AP identifying the scope of PMKSA in an
+ *	ESS.
  * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC
- *	(for the BSSID) and %NL80211_ATTR_PMKID.
+ *	(for the BSSID) and %NL80211_ATTR_PMKID or using %NL80211_ATTR_SSID,
+ *	%NL80211_ATTR_FILS_CACHE_ID, and %NL80211_ATTR_PMKID in case of FILS
+ *	authentication.
  * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries.
  *
  * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain
@@ -2012,6 +2058,36 @@ enum nl80211_commands {
  *	u32 attribute with an &enum nl80211_timeout_reason value. This is used,
  *	e.g., with %NL80211_CMD_CONNECT event.
  *
+ * @NL80211_ATTR_FILS_ERP_USERNAME: EAP Re-authentication Protocol (ERP)
+ *	username part of NAI used to refer keys rRK and rIK. This is used with
+ *	%NL80211_CMD_CONNECT.
+ *
+ * @NL80211_ATTR_FILS_ERP_REALM: EAP Re-authentication Protocol (ERP) realm part
+ *	of NAI specifying the domain name of the ER server. This is used with
+ *	%NL80211_CMD_CONNECT.
+ *
+ * @NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM: Unsigned 16-bit ERP next sequence number
+ *	to use in ERP messages. This is used in generating the FILS wrapped data
+ *	for FILS authentication and is used with %NL80211_CMD_CONNECT.
+ *
+ * @NL80211_ATTR_FILS_ERP_RRK: ERP re-authentication Root Key (rRK) for the
+ *	NAI specified by %NL80211_ATTR_FILS_ERP_USERNAME and
+ *	%NL80211_ATTR_FILS_ERP_REALM. This is used for generating rIK and rMSK
+ *	from successful FILS authentication and is used with
+ *	%NL80211_CMD_CONNECT.
+ *
+ * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertized by a FILS AP
+ *	identifying the scope of PMKSAs. This is used with
+ *	@NL80211_CMD_SET_PMKSA and @NL80211_CMD_DEL_PMKSA.
+ *
+ * @NL80211_ATTR_PMK: PMK for the PMKSA identified by %NL80211_ATTR_PMKID.
+ *	This is used with @NL80211_CMD_SET_PMKSA.
+ *
+ * @NL80211_ATTR_SCHED_SCAN_MULTI: flag attribute which user-space shall use to
+ *	indicate that it supports multiple active scheduled scan requests.
+ * @NL80211_ATTR_SCHED_SCAN_MAX_REQS: indicates maximum number of scheduled
+ *	scan request that may be active for the device (u32).
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2423,6 +2499,17 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_TIMEOUT_REASON,
 
+	NL80211_ATTR_FILS_ERP_USERNAME,
+	NL80211_ATTR_FILS_ERP_REALM,
+	NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM,
+	NL80211_ATTR_FILS_ERP_RRK,
+	NL80211_ATTR_FILS_CACHE_ID,
+
+	NL80211_ATTR_PMK,
+
+	NL80211_ATTR_SCHED_SCAN_MULTI,
+	NL80211_ATTR_SCHED_SCAN_MAX_REQS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -3107,6 +3194,7 @@ enum nl80211_reg_rule_attr {
  * @__NL80211_SCHED_SCAN_MATCH_ATTR_INVALID: attribute number 0 is reserved
  * @NL80211_SCHED_SCAN_MATCH_ATTR_SSID: SSID to be used for matching,
  *	only report BSS with matching SSID.
+ *	(This cannot be used together with BSSID.)
  * @NL80211_SCHED_SCAN_MATCH_ATTR_RSSI: RSSI threshold (in dBm) for reporting a
  *	BSS in scan results. Filtering is turned off if not specified. Note that
  *	if this attribute is in a match set of its own, then it is treated as
@@ -3122,6 +3210,8 @@ enum nl80211_reg_rule_attr {
  *	BSS-es in the specified band is to be adjusted before doing
  *	RSSI-based BSS selection. The attribute value is a packed structure
  *	value as specified by &struct nl80211_bss_select_rssi_adjust.
+ * @NL80211_SCHED_SCAN_MATCH_ATTR_BSSID: BSSID to be used for matching
+ *	(this cannot be used together with SSID).
  * @NL80211_SCHED_SCAN_MATCH_ATTR_MAX: highest scheduled scan filter
  *	attribute number currently defined
  * @__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST: internal use
@@ -3133,6 +3223,7 @@ enum nl80211_sched_scan_match_attr {
 	NL80211_SCHED_SCAN_MATCH_ATTR_RSSI,
 	NL80211_SCHED_SCAN_MATCH_ATTR_RELATIVE_RSSI,
 	NL80211_SCHED_SCAN_MATCH_ATTR_RSSI_ADJUST,
+	NL80211_SCHED_SCAN_MATCH_ATTR_BSSID,
 
 	/* keep last */
 	__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST,
@@ -3942,7 +4033,10 @@ enum nl80211_ps_state {
  * @__NL80211_ATTR_CQM_INVALID: invalid
  * @NL80211_ATTR_CQM_RSSI_THOLD: RSSI threshold in dBm. This value specifies
  *	the threshold for the RSSI level at which an event will be sent. Zero
- *	to disable.
+ *	to disable.  Alternatively, if %NL80211_EXT_FEATURE_CQM_RSSI_LIST is
+ *	set, multiple values can be supplied as a low-to-high sorted array of
+ *	threshold values in dBm.  Events will be sent when the RSSI value
+ *	crosses any of the thresholds.
  * @NL80211_ATTR_CQM_RSSI_HYST: RSSI hysteresis in dBm. This value specifies
  *	the minimum amount the RSSI level must change after an event before a
  *	new event may be issued (to reduce effects of RSSI oscillation).
@@ -4753,6 +4847,11 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_SCHED_SCAN_RELATIVE_RSSI: The driver supports sched_scan
  *	for reporting BSSs with better RSSI than the current connected BSS
  *	(%NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI).
+ * @NL80211_EXT_FEATURE_CQM_RSSI_LIST: With this driver the
+ *	%NL80211_ATTR_CQM_RSSI_THOLD attribute accepts a list of zero or more
+ *	RSSI threshold values to monitor rather than exactly one threshold.
+ * @NL80211_EXT_FEATURE_FILS_SK_OFFLOAD: Driver SME supports FILS shared key
+ *	authentication with %NL80211_CMD_CONNECT.
  *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
@@ -4771,6 +4870,8 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA,
 	NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED,
 	NL80211_EXT_FEATURE_SCHED_SCAN_RELATIVE_RSSI,
+	NL80211_EXT_FEATURE_CQM_RSSI_LIST,
+	NL80211_EXT_FEATURE_FILS_SK_OFFLOAD,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
@@ -4906,12 +5007,17 @@ enum nl80211_smps_mode {
  *	change to the channel status.
  * @NL80211_RADAR_NOP_FINISHED: The Non-Occupancy Period for this channel is
  *	over, channel becomes usable.
+ * @NL80211_RADAR_PRE_CAC_EXPIRED: Channel Availability Check done on this
+ *	non-operating channel is expired and no longer valid. New CAC must
+ *	be done on this channel before starting the operation. This is not
+ *	applicable for ETSI dfs domain where pre-CAC is valid for ever.
  */
 enum nl80211_radar_event {
 	NL80211_RADAR_DETECTED,
 	NL80211_RADAR_CAC_FINISHED,
 	NL80211_RADAR_CAC_ABORTED,
 	NL80211_RADAR_NOP_FINISHED,
+	NL80211_RADAR_PRE_CAC_EXPIRED,
 };
 
 /**
diff --git a/include/uapi/linux/nubus.h b/include/uapi/linux/nubus.h
index 77513d2b5638..ac516064f0ee 100644
--- a/include/uapi/linux/nubus.h
+++ b/include/uapi/linux/nubus.h
@@ -113,13 +113,15 @@ enum nubus_drhw {
 	NUBUS_DRHW_SIGMA_CLRMAX   = 0x0007, /* Sigma Design ColorMax */
 	NUBUS_DRHW_APPLE_SE30     = 0x0009, /* Apple SE/30 video */
 	NUBUS_DRHW_APPLE_HRVC     = 0x0013, /* Mac II High-Res Video Card */
+	NUBUS_DRHW_APPLE_MVC      = 0x0014, /* Mac II Monochrome Video Card */
 	NUBUS_DRHW_APPLE_PVC      = 0x0017, /* Mac II Portrait Video Card */
 	NUBUS_DRHW_APPLE_RBV1     = 0x0018, /* IIci RBV video */
 	NUBUS_DRHW_APPLE_MDC      = 0x0019, /* Macintosh Display Card */
+	NUBUS_DRHW_APPLE_VSC      = 0x0020, /* Duo MiniDock ViSC framebuffer */
 	NUBUS_DRHW_APPLE_SONORA   = 0x0022, /* Sonora built-in video */
+	NUBUS_DRHW_APPLE_JET      = 0x0029, /* Jet framebuffer (DuoDock) */
 	NUBUS_DRHW_APPLE_24AC     = 0x002b, /* Mac 24AC Video Card */
 	NUBUS_DRHW_APPLE_VALKYRIE = 0x002e,
-	NUBUS_DRHW_APPLE_JET      = 0x0029, /* Jet framebuffer (DuoDock) */
 	NUBUS_DRHW_SMAC_GFX       = 0x0105, /* SuperMac GFX */
 	NUBUS_DRHW_RASTER_CB264   = 0x013B, /* RasterOps ColorBoard 264 */
 	NUBUS_DRHW_MICRON_XCEED   = 0x0146, /* Micron Exceed color */
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 7f41f7d0000f..61b7d36dfe34 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -578,10 +578,25 @@ enum ovs_sample_attr {
 	OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */
 	OVS_SAMPLE_ATTR_ACTIONS,     /* Nested OVS_ACTION_ATTR_* attributes. */
 	__OVS_SAMPLE_ATTR_MAX,
+
+#ifdef __KERNEL__
+	OVS_SAMPLE_ATTR_ARG          /* struct sample_arg  */
+#endif
 };
 
 #define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1)
 
+#ifdef __KERNEL__
+struct sample_arg {
+	bool exec;                   /* When true, actions in sample will not
+				      * change flow keys. False otherwise.
+				      */
+	u32  probability;            /* Same value as
+				      * 'OVS_SAMPLE_ATTR_PROBABILITY'.
+				      */
+};
+#endif
+
 /**
  * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action.
  * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION
@@ -678,6 +693,17 @@ struct ovs_action_hash {
  * nothing if the connection is already committed will check that the current
  * packet is in conntrack entry's original direction.  If directionality does
  * not match, will delete the existing conntrack entry and commit a new one.
+ * @OVS_CT_ATTR_EVENTMASK: Mask of bits indicating which conntrack event types
+ * (enum ip_conntrack_events IPCT_*) should be reported.  For any bit set to
+ * zero, the corresponding event type is not generated.  Default behavior
+ * depends on system configuration, but typically all event types are
+ * generated, hence listening on NFNLGRP_CONNTRACK_UPDATE events may get a lot
+ * of events.  Explicitly passing this attribute allows limiting the updates
+ * received to the events of interest.  The bit 1 << IPCT_NEW, 1 <<
+ * IPCT_RELATED, and 1 << IPCT_DESTROY must be set to ones for those events to
+ * be received on NFNLGRP_CONNTRACK_NEW and NFNLGRP_CONNTRACK_DESTROY groups,
+ * respectively.  Remaining bits control the changes for which an event is
+ * delivered on the NFNLGRP_CONNTRACK_UPDATE group.
  */
 enum ovs_ct_attr {
 	OVS_CT_ATTR_UNSPEC,
@@ -689,6 +715,7 @@ enum ovs_ct_attr {
 				   related connections. */
 	OVS_CT_ATTR_NAT,        /* Nested OVS_NAT_ATTR_* */
 	OVS_CT_ATTR_FORCE_COMMIT,  /* No argument */
+	OVS_CT_ATTR_EVENTMASK,  /* u32 mask of IPCT_* events. */
 	__OVS_CT_ATTR_MAX
 };
 
diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index d08c63f3dd6f..0c5d5dd61b6a 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -64,7 +64,7 @@ struct packet_diag_mclist {
 	__u32	pdmc_count;
 	__u16	pdmc_type;
 	__u16	pdmc_alen;
-	__u8	pdmc_addr[MAX_ADDR_LEN];
+	__u8	pdmc_addr[32]; /* MAX_ADDR_LEN */
 };
 
 struct packet_diag_ring {
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index c66a485a24ac..d09a9cd021b1 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -344,7 +344,8 @@ struct perf_event_attr {
 				use_clockid    :  1, /* use @clockid for time fields */
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
-				__reserved_1   : 36;
+				namespaces     :  1, /* include namespaces data */
+				__reserved_1   : 35;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -610,6 +611,23 @@ struct perf_event_header {
 	__u16	size;
 };
 
+struct perf_ns_link_info {
+	__u64	dev;
+	__u64	ino;
+};
+
+enum {
+	NET_NS_INDEX		= 0,
+	UTS_NS_INDEX		= 1,
+	IPC_NS_INDEX		= 2,
+	PID_NS_INDEX		= 3,
+	USER_NS_INDEX		= 4,
+	MNT_NS_INDEX		= 5,
+	CGROUP_NS_INDEX		= 6,
+
+	NR_NAMESPACES,		/* number of available namespaces */
+};
+
 enum perf_event_type {
 
 	/*
@@ -862,6 +880,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 *	u64				nr_namespaces;
+	 *	{ u64				dev, inode; } [nr_namespaces];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_NAMESPACES			= 16,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -885,6 +915,7 @@ enum perf_callchain_context {
  */
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
+#define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 7a69f2a4ca0c..d613be3b3239 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -37,7 +37,20 @@ enum {
 #define TC_ACT_QUEUED		5
 #define TC_ACT_REPEAT		6
 #define TC_ACT_REDIRECT		7
-#define TC_ACT_JUMP		0x10000000
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_CMP(combined, opcode) \
+	(((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
 
 /* Action type identifiers*/
 enum {
@@ -432,6 +445,11 @@ enum {
 	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
 	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
 
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
 	__TCA_FLOWER_MAX,
 };
 
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index df7451d35131..099bf5528fed 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -617,6 +617,14 @@ struct tc_drr_stats {
 #define TC_QOPT_BITMASK 15
 #define TC_QOPT_MAX_QUEUE 16
 
+enum {
+	TC_MQPRIO_HW_OFFLOAD_NONE,	/* no offload requested */
+	TC_MQPRIO_HW_OFFLOAD_TCS,	/* offload TCs, no queue counts */
+	__TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
 struct tc_mqprio_qopt {
 	__u8	num_tc;
 	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 6546917d605a..cce061382e40 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -122,6 +122,8 @@ enum {
 
 	RTM_NEWNETCONF = 80,
 #define RTM_NEWNETCONF RTM_NEWNETCONF
+	RTM_DELNETCONF,
+#define RTM_DELNETCONF RTM_DELNETCONF
 	RTM_GETNETCONF = 82,
 #define RTM_GETNETCONF RTM_GETNETCONF
 
@@ -319,6 +321,7 @@ enum rtattr_type_t {
 	RTA_EXPIRES,
 	RTA_PAD,
 	RTA_UID,
+	RTA_TTL_PROPAGATE,
 	__RTA_MAX
 };
 
@@ -545,6 +548,7 @@ enum {
 	TCA_STATS2,
 	TCA_STAB,
 	TCA_PAD,
+	TCA_DUMP_INVISIBLE,
 	__TCA_MAX
 };
 
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index d3ae381fcf33..ced9d8b97426 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -115,6 +115,8 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_PR_SUPPORTED	113
 #define SCTP_DEFAULT_PRINFO	114
 #define SCTP_PR_ASSOC_STATUS	115
+#define SCTP_PR_STREAM_STATUS	116
+#define SCTP_RECONFIG_SUPPORTED	117
 #define SCTP_ENABLE_STREAM_RESET	118
 #define SCTP_RESET_STREAMS	119
 #define SCTP_RESET_ASSOC	120
@@ -502,6 +504,28 @@ struct sctp_stream_reset_event {
 	__u16 strreset_stream_list[];
 };
 
+#define SCTP_ASSOC_RESET_DENIED		0x0004
+#define SCTP_ASSOC_RESET_FAILED		0x0008
+struct sctp_assoc_reset_event {
+	__u16 assocreset_type;
+	__u16 assocreset_flags;
+	__u32 assocreset_length;
+	sctp_assoc_t assocreset_assoc_id;
+	__u32 assocreset_local_tsn;
+	__u32 assocreset_remote_tsn;
+};
+
+#define SCTP_ASSOC_CHANGE_DENIED	0x0004
+#define SCTP_ASSOC_CHANGE_FAILED	0x0008
+struct sctp_stream_change_event {
+	__u16 strchange_type;
+	__u16 strchange_flags;
+	__u32 strchange_length;
+	sctp_assoc_t strchange_assoc_id;
+	__u16 strchange_instrms;
+	__u16 strchange_outstrms;
+};
+
 /*
  * Described in Section 7.3
  *   Ancillary Data and Notification Interest Options
@@ -518,6 +542,8 @@ struct sctp_event_subscribe {
 	__u8 sctp_authentication_event;
 	__u8 sctp_sender_dry_event;
 	__u8 sctp_stream_reset_event;
+	__u8 sctp_assoc_reset_event;
+	__u8 sctp_stream_change_event;
 };
 
 /*
@@ -543,6 +569,8 @@ union sctp_notification {
 	struct sctp_authkey_event sn_authkey_event;
 	struct sctp_sender_dry_event sn_sender_dry_event;
 	struct sctp_stream_reset_event sn_strreset_event;
+	struct sctp_assoc_reset_event sn_assocreset_event;
+	struct sctp_stream_change_event sn_strchange_event;
 };
 
 /* Section 5.3.1
@@ -572,6 +600,10 @@ enum sctp_sn_type {
 #define SCTP_SENDER_DRY_EVENT		SCTP_SENDER_DRY_EVENT
 	SCTP_STREAM_RESET_EVENT,
 #define SCTP_STREAM_RESET_EVENT		SCTP_STREAM_RESET_EVENT
+	SCTP_ASSOC_RESET_EVENT,
+#define SCTP_ASSOC_RESET_EVENT		SCTP_ASSOC_RESET_EVENT
+	SCTP_STREAM_CHANGE_EVENT,
+#define SCTP_STREAM_CHANGE_EVENT	SCTP_STREAM_CHANGE_EVENT
 };
 
 /* Notification error codes used to fill up the error fields in some
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 3b2bed7ca9a4..95cffcb21dfd 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -177,7 +177,6 @@ enum
 	LINUX_MIB_TIMEWAITED,			/* TimeWaited */
 	LINUX_MIB_TIMEWAITRECYCLED,		/* TimeWaitRecycled */
 	LINUX_MIB_TIMEWAITKILLED,		/* TimeWaitKilled */
-	LINUX_MIB_PAWSPASSIVEREJECTED,		/* PAWSPassiveRejected */
 	LINUX_MIB_PAWSACTIVEREJECTED,		/* PAWSActiveRejected */
 	LINUX_MIB_PAWSESTABREJECTED,		/* PAWSEstabRejected */
 	LINUX_MIB_DELAYEDACKS,			/* DelayedACKs */
@@ -260,6 +259,7 @@ enum
 	LINUX_MIB_TCPFASTOPENPASSIVEFAIL,	/* TCPFastOpenPassiveFail */
 	LINUX_MIB_TCPFASTOPENLISTENOVERFLOW,	/* TCPFastOpenListenOverflow */
 	LINUX_MIB_TCPFASTOPENCOOKIEREQD,	/* TCPFastOpenCookieReqd */
+	LINUX_MIB_TCPFASTOPENBLACKHOLE,		/* TCPFastOpenBlackholeDetect */
 	LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
 	LINUX_MIB_BUSYPOLLRXPACKETS,		/* BusyPollRxPackets */
 	LINUX_MIB_TCPAUTOCORKING,		/* TCPAutoCorking */
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 51a6b86e3700..17b10304c393 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -48,17 +48,13 @@
  * tv_sec holds the number of seconds before (negative) or after (positive)
  * 00:00:00 1st January 1970 UTC.
  *
- * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
- * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
- *
- * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
- * either be both positive or both negative.
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
  *
  * __reserved is held in case we need a yet finer resolution.
  */
 struct statx_timestamp {
 	__s64	tv_sec;
-	__s32	tv_nsec;
+	__u32	tv_nsec;
 	__s32	__reserved;
 };
 
@@ -114,7 +110,7 @@ struct statx {
 	__u64	stx_ino;	/* Inode number */
 	__u64	stx_size;	/* File size */
 	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
-	__u64	__spare1[1];
+	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
 	/* 0x40 */
 	struct statx_timestamp	stx_atime;	/* Last access time */
 	struct statx_timestamp	stx_btime;	/* File creation time */
@@ -152,9 +148,10 @@ struct statx {
 #define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_ALL		0x00000fffU	/* All currently supported flags */
+#define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
 /*
- * Attributes to be found in stx_attributes
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
  *
  * These give information about the features or the state of a file that might
  * be of use to ordinary userspace programs such as GUIs or ls rather than
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index d2b12152e358..e13d48058b8d 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -568,6 +568,7 @@ enum {
 	NET_IPV6_PROXY_NDP=23,
 	NET_IPV6_ACCEPT_SOURCE_ROUTE=25,
 	NET_IPV6_ACCEPT_RA_FROM_LOCAL=26,
+	NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27,
 	__NET_IPV6_MAX
 };
 
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index c055947c5c98..3b059530dac9 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -18,8 +18,7 @@
  * means the userland is reading).
  */
 #define UFFD_API ((__u64)0xAA)
-#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT |		\
-			   UFFD_FEATURE_EVENT_FORK |		\
+#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |		\
 			   UFFD_FEATURE_EVENT_REMAP |		\
 			   UFFD_FEATURE_EVENT_REMOVE |	\
 			   UFFD_FEATURE_EVENT_UNMAP |		\
@@ -113,7 +112,6 @@ struct uffd_msg {
 #define UFFD_EVENT_REMAP	0x14
 #define UFFD_EVENT_REMOVE	0x15
 #define UFFD_EVENT_UNMAP	0x16
-#define UFFD_EVENT_EXIT		0x17
 
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
@@ -163,7 +161,6 @@ struct uffdio_api {
 #define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
 #define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
 #define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
-#define UFFD_FEATURE_EVENT_EXIT			(1<<7)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 519eff362c1c..ae461050661a 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -198,6 +198,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_PCI	(1 << 1)	/* vfio-pci device */
 #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2)	/* vfio-platform device */
 #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)	/* vfio-amba device */
+#define VFIO_DEVICE_FLAGS_CCW	(1 << 4)	/* vfio-ccw device */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 };
@@ -212,6 +213,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_API_PCI_STRING		"vfio-pci"
 #define VFIO_DEVICE_API_PLATFORM_STRING		"vfio-platform"
 #define VFIO_DEVICE_API_AMBA_STRING		"vfio-amba"
+#define VFIO_DEVICE_API_CCW_STRING		"vfio-ccw"
 
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
@@ -446,6 +448,22 @@ enum {
 	VFIO_PCI_NUM_IRQS
 };
 
+/*
+ * The vfio-ccw bus driver makes use of the following fixed region and
+ * IRQ index mapping. Unimplemented regions return a size of zero.
+ * Unimplemented IRQ types return a count of zero.
+ */
+
+enum {
+	VFIO_CCW_CONFIG_REGION_INDEX,
+	VFIO_CCW_NUM_REGIONS
+};
+
+enum {
+	VFIO_CCW_IO_IRQ_INDEX,
+	VFIO_CCW_NUM_IRQS
+};
+
 /**
  * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12,
  *					      struct vfio_pci_hot_reset_info)
diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h
new file mode 100644
index 000000000000..34a7f6f9e065
--- /dev/null
+++ b/include/uapi/linux/vfio_ccw.h
@@ -0,0 +1,24 @@
+/*
+ * Interfaces for vfio-ccw
+ *
+ * Copyright IBM Corp. 2017
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ */
+
+#ifndef _VFIO_CCW_H_
+#define _VFIO_CCW_H_
+
+#include <linux/types.h>
+
+struct ccw_io_region {
+#define ORB_AREA_SIZE 12
+	__u8	orb_area[ORB_AREA_SIZE];
+#define SCSW_AREA_SIZE 12
+	__u8	scsw_area[SCSW_AREA_SIZE];
+#define IRB_AREA_SIZE 96
+	__u8	irb_area[IRB_AREA_SIZE];
+	__u32	ret_code;
+} __packed;
+
+#endif
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 15b4385a2be1..90007a1abcab 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -79,7 +79,7 @@
  * configuration space */
 #define VIRTIO_PCI_CONFIG_OFF(msix_enabled)	((msix_enabled) ? 24 : 20)
 /* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */
-#define VIRTIO_PCI_CONFIG(dev)	VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled)
+#define VIRTIO_PCI_CONFIG(dev)	VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled)
 
 /* Virtio ABI version, this must match exactly */
 #define VIRTIO_PCI_ABI_VERSION		0
diff --git a/include/uapi/linux/vsockmon.h b/include/uapi/linux/vsockmon.h
new file mode 100644
index 000000000000..a08b522ef597
--- /dev/null
+++ b/include/uapi/linux/vsockmon.h
@@ -0,0 +1,60 @@
+#ifndef _UAPI_VSOCKMON_H
+#define _UAPI_VSOCKMON_H
+
+#include <linux/virtio_vsock.h>
+
+/*
+ * vsockmon is the AF_VSOCK packet capture device.  Packets captured have the
+ * following layout:
+ *
+ *   +-----------------------------------+
+ *   |           vsockmon header         |
+ *   |      (struct af_vsockmon_hdr)     |
+ *   +-----------------------------------+
+ *   |          transport header         |
+ *   | (af_vsockmon_hdr->len bytes long) |
+ *   +-----------------------------------+
+ *   |              payload              |
+ *   |       (until end of packet)       |
+ *   +-----------------------------------+
+ *
+ * The vsockmon header is a transport-independent description of the packet.
+ * It duplicates some of the information from the transport header so that
+ * no transport-specific knowledge is necessary to process packets.
+ *
+ * The transport header is useful for low-level transport-specific packet
+ * analysis.  Transport type is given in af_vsockmon_hdr->transport and
+ * transport header length is given in af_vsockmon_hdr->len.
+ *
+ * If af_vsockmon_hdr->op is AF_VSOCK_OP_PAYLOAD then the payload follows the
+ * transport header.  Other ops do not have a payload.
+ */
+
+struct af_vsockmon_hdr {
+	__le64 src_cid;
+	__le64 dst_cid;
+	__le32 src_port;
+	__le32 dst_port;
+	__le16 op;			/* enum af_vsockmon_op */
+	__le16 transport;		/* enum af_vsockmon_transport */
+	__le16 len;			/* Transport header length */
+	__u8 reserved[2];
+};
+
+enum af_vsockmon_op {
+	AF_VSOCK_OP_UNKNOWN = 0,
+	AF_VSOCK_OP_CONNECT = 1,
+	AF_VSOCK_OP_DISCONNECT = 2,
+	AF_VSOCK_OP_CONTROL = 3,
+	AF_VSOCK_OP_PAYLOAD = 4,
+};
+
+enum af_vsockmon_transport {
+	AF_VSOCK_TRANSPORT_UNKNOWN = 0,
+	AF_VSOCK_TRANSPORT_NO_INFO = 1,	/* No transport information */
+
+	/* Transport header type: struct virtio_vsock_hdr */
+	AF_VSOCK_TRANSPORT_VIRTIO = 2,
+};
+
+#endif
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 1fc62b239f1b..2b384ff09fa0 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -303,6 +303,7 @@ enum xfrm_attr_type_t {
 	XFRMA_PROTO,		/* __u8 */
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
+	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
 	__XFRMA_MAX
 
 #define XFRMA_MAX (__XFRMA_MAX - 1)
@@ -494,6 +495,13 @@ struct xfrm_address_filter {
 	__u8				dplen;
 };
 
+struct xfrm_user_offload {
+	int				ifindex;
+	__u8				flags;
+};
+#define XFRM_OFFLOAD_IPV6	1
+#define XFRM_OFFLOAD_INBOUND	2
+
 #ifndef __KERNEL__
 /* backwards compatibility for userspace */
 #define XFRMGRP_ACQUIRE		1
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index da7cd62bace7..0b3d30837a9f 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -34,6 +34,7 @@
 #define MLX5_ABI_USER_H
 
 #include <linux/types.h>
+#include <linux/if_ether.h>	/* For ETH_ALEN. */
 
 enum {
 	MLX5_QP_FLAG_SIGNATURE		= 1 << 0,
@@ -66,7 +67,7 @@ struct mlx5_ib_alloc_ucontext_req {
 };
 
 enum mlx5_lib_caps {
-	MLX5_LIB_CAP_4K_UAR	= (u64)1 << 0,
+	MLX5_LIB_CAP_4K_UAR	= (__u64)1 << 0,
 };
 
 struct mlx5_ib_alloc_ucontext_req_v2 {
diff --git a/include/video/exynos5433_decon.h b/include/video/exynos5433_decon.h
index ef8e2a8ad0af..6b083d327e98 100644
--- a/include/video/exynos5433_decon.h
+++ b/include/video/exynos5433_decon.h
@@ -46,6 +46,7 @@
 #define DECON_FRAMEFIFO_STATUS		0x0524
 #define DECON_CMU			0x1404
 #define DECON_UPDATE			0x1410
+#define DECON_CRFMID			0x1414
 #define DECON_UPDATE_SCHEME		0x1438
 #define DECON_VIDCON1			0x2000
 #define DECON_VIDCON2			0x2004
@@ -126,6 +127,10 @@
 
 /* VIDINTCON0 */
 #define VIDINTCON0_FRAMEDONE		(1 << 17)
+#define VIDINTCON0_FRAMESEL_BP		(0 << 15)
+#define VIDINTCON0_FRAMESEL_VS		(1 << 15)
+#define VIDINTCON0_FRAMESEL_AC		(2 << 15)
+#define VIDINTCON0_FRAMESEL_FP		(3 << 15)
 #define VIDINTCON0_INTFRMEN		(1 << 12)
 #define VIDINTCON0_INTEN		(1 << 0)
 
@@ -142,6 +147,13 @@
 #define STANDALONE_UPDATE_F		(1 << 0)
 
 /* DECON_VIDCON1 */
+#define VIDCON1_LINECNT_MASK		(0x0fff << 16)
+#define VIDCON1_I80_ACTIVE		(1 << 15)
+#define VIDCON1_VSTATUS_MASK		(0x3 << 13)
+#define VIDCON1_VSTATUS_VS		(0 << 13)
+#define VIDCON1_VSTATUS_BP		(1 << 13)
+#define VIDCON1_VSTATUS_AC		(2 << 13)
+#define VIDCON1_VSTATUS_FP		(3 << 13)
 #define VIDCON1_VCLK_MASK		(0x3 << 9)
 #define VIDCON1_VCLK_RUN_VDEN_DISABLE	(0x3 << 9)
 #define VIDCON1_VCLK_HOLD		(0x0 << 9)
diff --git a/include/video/udlfb.h b/include/video/udlfb.h
index f9466fa54ba4..3ea90aea5617 100644
--- a/include/video/udlfb.h
+++ b/include/video/udlfb.h
@@ -92,6 +92,6 @@ struct dlfb_data {
 
 /* remove these once align.h patch is taken into kernel */
 #define DL_ALIGN_UP(x, a) ALIGN(x, a)
-#define DL_ALIGN_DOWN(x, a) ALIGN(x-(a-1), a)
+#define DL_ALIGN_DOWN(x, a) ALIGN_DOWN(x, a)
 
 #endif
diff --git a/include/xen/page.h b/include/xen/page.h
index 9dc46cb8a0fd..064194f6453e 100644
--- a/include/xen/page.h
+++ b/include/xen/page.h
@@ -38,7 +38,7 @@ struct xen_memory_region {
 	unsigned long n_pfns;
 };
 
-#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820MAX */
+#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820_MAX_ENTRIES_ZEROPAGE */
 
 extern __initdata
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS];
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index a0083be5d529..1f6d78f044b6 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -2,6 +2,7 @@
 #define __LINUX_SWIOTLB_XEN_H
 
 #include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
 #include <linux/swiotlb.h>
 
 extern int xen_swiotlb_init(int verbose, bool early);
@@ -55,4 +56,14 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
 
 extern int
 xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs);
+
+extern int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t handle, size_t size,
+			unsigned long attrs);
 #endif /* __LINUX_SWIOTLB_XEN_H */
diff --git a/init/main.c b/init/main.c
index eae2f15657c6..b0c11cbf5ddf 100644
--- a/init/main.c
+++ b/init/main.c
@@ -882,7 +882,6 @@ static void __init do_basic_setup(void)
 	do_ctors();
 	usermodehelper_enable();
 	do_initcalls();
-	random_int_secret_init();
 }
 
 static void __init do_pre_smp_initcalls(void)
@@ -1023,6 +1022,8 @@ static noinline void __init kernel_init_freeable(void)
 
 	workqueue_init();
 
+	init_mm_internals();
+
 	do_pre_smp_initcalls();
 	lockup_detector_init();
 
diff --git a/ipc/util.c b/ipc/util.c
index 798cad18dd87..3459a16a9df9 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -474,7 +474,7 @@ void ipc_rcu_free(struct rcu_head *head)
  * Check user, group, other permissions for access
  * to ipc resources. return 0 if allowed
  *
- * @flag will most probably be 0 or S_...UGO from <linux/stat.h>
+ * @flag will most probably be 0 or ``S_...UGO`` from <linux/stat.h>
  */
 int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag)
 {
@@ -672,10 +672,12 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
  *
  * This function does some common audit and permissions check for some IPC_XXX
  * cmd and is called from semctl_down, shmctl_down and msgctl_down.
- * It must be called without any lock held and
- *  - retrieves the ipc with the given id in the given table.
- *  - performs some audit and permission check, depending on the given cmd
- *  - returns a pointer to the ipc object or otherwise, the corresponding error.
+ * It must be called without any lock held and:
+ *
+ *   - retrieves the ipc with the given id in the given table.
+ *   - performs some audit and permission check, depending on the given cmd
+ *   - returns a pointer to the ipc object or otherwise, the corresponding
+ *     error.
  *
  * Call holding the both the rwsem and the rcu read lock.
  */
diff --git a/kernel/audit.c b/kernel/audit.c
index e794544f5e63..dc202d582aa1 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -54,6 +54,10 @@
 #include <linux/kthread.h>
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
+#include <linux/spinlock.h>
+#include <linux/rcupdate.h>
+#include <linux/mutex.h>
+#include <linux/gfp.h>
 
 #include <linux/audit.h>
 
@@ -90,13 +94,34 @@ static u32	audit_default;
 /* If auditing cannot proceed, audit_failure selects what happens. */
 static u32	audit_failure = AUDIT_FAIL_PRINTK;
 
-/*
- * If audit records are to be written to the netlink socket, audit_pid
- * contains the pid of the auditd process and audit_nlk_portid contains
- * the portid to use to send netlink messages to that process.
+/* private audit network namespace index */
+static unsigned int audit_net_id;
+
+/**
+ * struct audit_net - audit private network namespace data
+ * @sk: communication socket
  */
-int		audit_pid;
-static __u32	audit_nlk_portid;
+struct audit_net {
+	struct sock *sk;
+};
+
+/**
+ * struct auditd_connection - kernel/auditd connection state
+ * @pid: auditd PID
+ * @portid: netlink portid
+ * @net: the associated network namespace
+ * @lock: spinlock to protect write access
+ *
+ * Description:
+ * This struct is RCU protected; you must either hold the RCU lock for reading
+ * or the included spinlock for writing.
+ */
+static struct auditd_connection {
+	int pid;
+	u32 portid;
+	struct net *net;
+	spinlock_t lock;
+} auditd_conn;
 
 /* If audit_rate_limit is non-zero, limit the rate of sending audit records
  * to that number per second.  This prevents DoS attacks, but results in
@@ -123,10 +148,6 @@ u32		audit_sig_sid = 0;
 */
 static atomic_t	audit_lost = ATOMIC_INIT(0);
 
-/* The netlink socket. */
-static struct sock *audit_sock;
-static unsigned int audit_net_id;
-
 /* Hash for inode-based rules */
 struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
 
@@ -192,6 +213,43 @@ struct audit_reply {
 	struct sk_buff *skb;
 };
 
+/**
+ * auditd_test_task - Check to see if a given task is an audit daemon
+ * @task: the task to check
+ *
+ * Description:
+ * Return 1 if the task is a registered audit daemon, 0 otherwise.
+ */
+int auditd_test_task(const struct task_struct *task)
+{
+	int rc;
+
+	rcu_read_lock();
+	rc = (auditd_conn.pid && task->tgid == auditd_conn.pid ? 1 : 0);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+/**
+ * audit_get_sk - Return the audit socket for the given network namespace
+ * @net: the destination network namespace
+ *
+ * Description:
+ * Returns the sock pointer if valid, NULL otherwise.  The caller must ensure
+ * that a reference is held for the network namespace while the sock is in use.
+ */
+static struct sock *audit_get_sk(const struct net *net)
+{
+	struct audit_net *aunet;
+
+	if (!net)
+		return NULL;
+
+	aunet = net_generic(net, audit_net_id);
+	return aunet->sk;
+}
+
 static void audit_set_portid(struct audit_buffer *ab, __u32 portid)
 {
 	if (ab) {
@@ -210,9 +268,7 @@ void audit_panic(const char *message)
 			pr_err("%s\n", message);
 		break;
 	case AUDIT_FAIL_PANIC:
-		/* test audit_pid since printk is always losey, why bother? */
-		if (audit_pid)
-			panic("audit: %s\n", message);
+		panic("audit: %s\n", message);
 		break;
 	}
 }
@@ -370,21 +426,60 @@ static int audit_set_failure(u32 state)
 	return audit_do_config_change("audit_failure", &audit_failure, state);
 }
 
-/*
- * For one reason or another this nlh isn't getting delivered to the userspace
- * audit daemon, just send it to printk.
+/**
+ * auditd_set - Set/Reset the auditd connection state
+ * @pid: auditd PID
+ * @portid: auditd netlink portid
+ * @net: auditd network namespace pointer
+ *
+ * Description:
+ * This function will obtain and drop network namespace references as
+ * necessary.
+ */
+static void auditd_set(int pid, u32 portid, struct net *net)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&auditd_conn.lock, flags);
+	auditd_conn.pid = pid;
+	auditd_conn.portid = portid;
+	if (auditd_conn.net)
+		put_net(auditd_conn.net);
+	if (net)
+		auditd_conn.net = get_net(net);
+	else
+		auditd_conn.net = NULL;
+	spin_unlock_irqrestore(&auditd_conn.lock, flags);
+}
+
+/**
+ * kauditd_print_skb - Print the audit record to the ring buffer
+ * @skb: audit record
+ *
+ * Whatever the reason, this packet may not make it to the auditd connection
+ * so write it via printk so the information isn't completely lost.
  */
 static void kauditd_printk_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 	char *data = nlmsg_data(nlh);
 
-	if (nlh->nlmsg_type != AUDIT_EOE) {
-		if (printk_ratelimit())
-			pr_notice("type=%d %s\n", nlh->nlmsg_type, data);
-		else
-			audit_log_lost("printk limit exceeded");
-	}
+	if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit())
+		pr_notice("type=%d %s\n", nlh->nlmsg_type, data);
+}
+
+/**
+ * kauditd_rehold_skb - Handle a audit record send failure in the hold queue
+ * @skb: audit record
+ *
+ * Description:
+ * This should only be used by the kauditd_thread when it fails to flush the
+ * hold queue.
+ */
+static void kauditd_rehold_skb(struct sk_buff *skb)
+{
+	/* put the record back in the queue at the same place */
+	skb_queue_head(&audit_hold_queue, skb);
 }
 
 /**
@@ -444,65 +539,163 @@ static void kauditd_retry_skb(struct sk_buff *skb)
  * auditd_reset - Disconnect the auditd connection
  *
  * Description:
- * Break the auditd/kauditd connection and move all the records in the retry
- * queue into the hold queue in case auditd reconnects.  The audit_cmd_mutex
- * must be held when calling this function.
+ * Break the auditd/kauditd connection and move all the queued records into the
+ * hold queue in case auditd reconnects.
  */
 static void auditd_reset(void)
 {
 	struct sk_buff *skb;
 
-	/* break the connection */
-	if (audit_sock) {
-		sock_put(audit_sock);
-		audit_sock = NULL;
-	}
-	audit_pid = 0;
-	audit_nlk_portid = 0;
+	/* if it isn't already broken, break the connection */
+	rcu_read_lock();
+	if (auditd_conn.pid)
+		auditd_set(0, 0, NULL);
+	rcu_read_unlock();
 
-	/* flush all of the retry queue to the hold queue */
+	/* flush all of the main and retry queues to the hold queue */
 	while ((skb = skb_dequeue(&audit_retry_queue)))
 		kauditd_hold_skb(skb);
+	while ((skb = skb_dequeue(&audit_queue)))
+		kauditd_hold_skb(skb);
 }
 
 /**
- * kauditd_send_unicast_skb - Send a record via unicast to auditd
+ * auditd_send_unicast_skb - Send a record via unicast to auditd
  * @skb: audit record
+ *
+ * Description:
+ * Send a skb to the audit daemon, returns positive/zero values on success and
+ * negative values on failure; in all cases the skb will be consumed by this
+ * function.  If the send results in -ECONNREFUSED the connection with auditd
+ * will be reset.  This function may sleep so callers should not hold any locks
+ * where this would cause a problem.
  */
-static int kauditd_send_unicast_skb(struct sk_buff *skb)
+static int auditd_send_unicast_skb(struct sk_buff *skb)
 {
 	int rc;
+	u32 portid;
+	struct net *net;
+	struct sock *sk;
+
+	/* NOTE: we can't call netlink_unicast while in the RCU section so
+	 *       take a reference to the network namespace and grab local
+	 *       copies of the namespace, the sock, and the portid; the
+	 *       namespace and sock aren't going to go away while we hold a
+	 *       reference and if the portid does become invalid after the RCU
+	 *       section netlink_unicast() should safely return an error */
+
+	rcu_read_lock();
+	if (!auditd_conn.pid) {
+		rcu_read_unlock();
+		rc = -ECONNREFUSED;
+		goto err;
+	}
+	net = auditd_conn.net;
+	get_net(net);
+	sk = audit_get_sk(net);
+	portid = auditd_conn.portid;
+	rcu_read_unlock();
 
-	/* if we know nothing is connected, don't even try the netlink call */
-	if (!audit_pid)
-		return -ECONNREFUSED;
+	rc = netlink_unicast(sk, skb, portid, 0);
+	put_net(net);
+	if (rc < 0)
+		goto err;
 
-	/* get an extra skb reference in case we fail to send */
-	skb_get(skb);
-	rc = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0);
-	if (rc >= 0) {
-		consume_skb(skb);
-		rc = 0;
-	}
+	return rc;
 
+err:
+	if (rc == -ECONNREFUSED)
+		auditd_reset();
 	return rc;
 }
 
+/**
+ * kauditd_send_queue - Helper for kauditd_thread to flush skb queues
+ * @sk: the sending sock
+ * @portid: the netlink destination
+ * @queue: the skb queue to process
+ * @retry_limit: limit on number of netlink unicast failures
+ * @skb_hook: per-skb hook for additional processing
+ * @err_hook: hook called if the skb fails the netlink unicast send
+ *
+ * Description:
+ * Run through the given queue and attempt to send the audit records to auditd,
+ * returns zero on success, negative values on failure.  It is up to the caller
+ * to ensure that the @sk is valid for the duration of this function.
+ *
+ */
+static int kauditd_send_queue(struct sock *sk, u32 portid,
+			      struct sk_buff_head *queue,
+			      unsigned int retry_limit,
+			      void (*skb_hook)(struct sk_buff *skb),
+			      void (*err_hook)(struct sk_buff *skb))
+{
+	int rc = 0;
+	struct sk_buff *skb;
+	static unsigned int failed = 0;
+
+	/* NOTE: kauditd_thread takes care of all our locking, we just use
+	 *       the netlink info passed to us (e.g. sk and portid) */
+
+	while ((skb = skb_dequeue(queue))) {
+		/* call the skb_hook for each skb we touch */
+		if (skb_hook)
+			(*skb_hook)(skb);
+
+		/* can we send to anyone via unicast? */
+		if (!sk) {
+			if (err_hook)
+				(*err_hook)(skb);
+			continue;
+		}
+
+		/* grab an extra skb reference in case of error */
+		skb_get(skb);
+		rc = netlink_unicast(sk, skb, portid, 0);
+		if (rc < 0) {
+			/* fatal failure for our queue flush attempt? */
+			if (++failed >= retry_limit ||
+			    rc == -ECONNREFUSED || rc == -EPERM) {
+				/* yes - error processing for the queue */
+				sk = NULL;
+				if (err_hook)
+					(*err_hook)(skb);
+				if (!skb_hook)
+					goto out;
+				/* keep processing with the skb_hook */
+				continue;
+			} else
+				/* no - requeue to preserve ordering */
+				skb_queue_head(queue, skb);
+		} else {
+			/* it worked - drop the extra reference and continue */
+			consume_skb(skb);
+			failed = 0;
+		}
+	}
+
+out:
+	return (rc >= 0 ? 0 : rc);
+}
+
 /*
  * kauditd_send_multicast_skb - Send a record to any multicast listeners
  * @skb: audit record
  *
  * Description:
- * This function doesn't consume an skb as might be expected since it has to
- * copy it anyways.
+ * Write a multicast message to anyone listening in the initial network
+ * namespace.  This function doesn't consume an skb as might be expected since
+ * it has to copy it anyways.
  */
 static void kauditd_send_multicast_skb(struct sk_buff *skb)
 {
 	struct sk_buff *copy;
-	struct audit_net *aunet = net_generic(&init_net, audit_net_id);
-	struct sock *sock = aunet->nlsk;
+	struct sock *sock = audit_get_sk(&init_net);
 	struct nlmsghdr *nlh;
 
+	/* NOTE: we are not taking an additional reference for init_net since
+	 *       we don't have to worry about it going away */
+
 	if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG))
 		return;
 
@@ -526,149 +719,79 @@ static void kauditd_send_multicast_skb(struct sk_buff *skb)
 }
 
 /**
- * kauditd_wake_condition - Return true when it is time to wake kauditd_thread
- *
- * Description:
- * This function is for use by the wait_event_freezable() call in
- * kauditd_thread().
+ * kauditd_thread - Worker thread to send audit records to userspace
+ * @dummy: unused
  */
-static int kauditd_wake_condition(void)
-{
-	static int pid_last = 0;
-	int rc;
-	int pid = audit_pid;
-
-	/* wake on new messages or a change in the connected auditd */
-	rc = skb_queue_len(&audit_queue) || (pid && pid != pid_last);
-	if (rc)
-		pid_last = pid;
-
-	return rc;
-}
-
 static int kauditd_thread(void *dummy)
 {
 	int rc;
-	int auditd = 0;
-	int reschedule = 0;
-	struct sk_buff *skb;
-	struct nlmsghdr *nlh;
+	u32 portid = 0;
+	struct net *net = NULL;
+	struct sock *sk = NULL;
 
 #define UNICAST_RETRIES 5
-#define AUDITD_BAD(x,y) \
-	((x) == -ECONNREFUSED || (x) == -EPERM || ++(y) >= UNICAST_RETRIES)
-
-	/* NOTE: we do invalidate the auditd connection flag on any sending
-	 * errors, but we only "restore" the connection flag at specific places
-	 * in the loop in order to help ensure proper ordering of audit
-	 * records */
 
 	set_freezable();
 	while (!kthread_should_stop()) {
-		/* NOTE: possible area for future improvement is to look at
-		 *       the hold and retry queues, since only this thread
-		 *       has access to these queues we might be able to do
-		 *       our own queuing and skip some/all of the locking */
-
-		/* NOTE: it might be a fun experiment to split the hold and
-		 *       retry queue handling to another thread, but the
-		 *       synchronization issues and other overhead might kill
-		 *       any performance gains */
+		/* NOTE: see the lock comments in auditd_send_unicast_skb() */
+		rcu_read_lock();
+		if (!auditd_conn.pid) {
+			rcu_read_unlock();
+			goto main_queue;
+		}
+		net = auditd_conn.net;
+		get_net(net);
+		sk = audit_get_sk(net);
+		portid = auditd_conn.portid;
+		rcu_read_unlock();
 
 		/* attempt to flush the hold queue */
-		while (auditd && (skb = skb_dequeue(&audit_hold_queue))) {
-			rc = kauditd_send_unicast_skb(skb);
-			if (rc) {
-				/* requeue to the same spot */
-				skb_queue_head(&audit_hold_queue, skb);
-
-				auditd = 0;
-				if (AUDITD_BAD(rc, reschedule)) {
-					mutex_lock(&audit_cmd_mutex);
-					auditd_reset();
-					mutex_unlock(&audit_cmd_mutex);
-					reschedule = 0;
-				}
-			} else
-				/* we were able to send successfully */
-				reschedule = 0;
+		rc = kauditd_send_queue(sk, portid,
+					&audit_hold_queue, UNICAST_RETRIES,
+					NULL, kauditd_rehold_skb);
+		if (rc < 0) {
+			sk = NULL;
+			auditd_reset();
+			goto main_queue;
 		}
 
 		/* attempt to flush the retry queue */
-		while (auditd && (skb = skb_dequeue(&audit_retry_queue))) {
-			rc = kauditd_send_unicast_skb(skb);
-			if (rc) {
-				auditd = 0;
-				if (AUDITD_BAD(rc, reschedule)) {
-					kauditd_hold_skb(skb);
-					mutex_lock(&audit_cmd_mutex);
-					auditd_reset();
-					mutex_unlock(&audit_cmd_mutex);
-					reschedule = 0;
-				} else
-					/* temporary problem (we hope), queue
-					 * to the same spot and retry */
-					skb_queue_head(&audit_retry_queue, skb);
-			} else
-				/* we were able to send successfully */
-				reschedule = 0;
+		rc = kauditd_send_queue(sk, portid,
+					&audit_retry_queue, UNICAST_RETRIES,
+					NULL, kauditd_hold_skb);
+		if (rc < 0) {
+			sk = NULL;
+			auditd_reset();
+			goto main_queue;
 		}
 
-		/* standard queue processing, try to be as quick as possible */
-quick_loop:
-		skb = skb_dequeue(&audit_queue);
-		if (skb) {
-			/* setup the netlink header, see the comments in
-			 * kauditd_send_multicast_skb() for length quirks */
-			nlh = nlmsg_hdr(skb);
-			nlh->nlmsg_len = skb->len - NLMSG_HDRLEN;
-
-			/* attempt to send to any multicast listeners */
-			kauditd_send_multicast_skb(skb);
-
-			/* attempt to send to auditd, queue on failure */
-			if (auditd) {
-				rc = kauditd_send_unicast_skb(skb);
-				if (rc) {
-					auditd = 0;
-					if (AUDITD_BAD(rc, reschedule)) {
-						mutex_lock(&audit_cmd_mutex);
-						auditd_reset();
-						mutex_unlock(&audit_cmd_mutex);
-						reschedule = 0;
-					}
-
-					/* move to the retry queue */
-					kauditd_retry_skb(skb);
-				} else
-					/* everything is working so go fast! */
-					goto quick_loop;
-			} else if (reschedule)
-				/* we are currently having problems, move to
-				 * the retry queue */
-				kauditd_retry_skb(skb);
-			else
-				/* dump the message via printk and hold it */
-				kauditd_hold_skb(skb);
-		} else {
-			/* we have flushed the backlog so wake everyone */
-			wake_up(&audit_backlog_wait);
-
-			/* if everything is okay with auditd (if present), go
-			 * to sleep until there is something new in the queue
-			 * or we have a change in the connected auditd;
-			 * otherwise simply reschedule to give things a chance
-			 * to recover */
-			if (reschedule) {
-				set_current_state(TASK_INTERRUPTIBLE);
-				schedule();
-			} else
-				wait_event_freezable(kauditd_wait,
-						     kauditd_wake_condition());
-
-			/* update the auditd connection status */
-			auditd = (audit_pid ? 1 : 0);
+main_queue:
+		/* process the main queue - do the multicast send and attempt
+		 * unicast, dump failed record sends to the retry queue; if
+		 * sk == NULL due to previous failures we will just do the
+		 * multicast send and move the record to the retry queue */
+		rc = kauditd_send_queue(sk, portid, &audit_queue, 1,
+					kauditd_send_multicast_skb,
+					kauditd_retry_skb);
+		if (sk == NULL || rc < 0)
+			auditd_reset();
+		sk = NULL;
+
+		/* drop our netns reference, no auditd sends past this line */
+		if (net) {
+			put_net(net);
+			net = NULL;
 		}
+
+		/* we have processed all the queues so wake everyone */
+		wake_up(&audit_backlog_wait);
+
+		/* NOTE: we want to wake up if there is anything on the queue,
+		 *       regardless of if an auditd is connected, as we need to
+		 *       do the multicast send and rotate records from the
+		 *       main queue to the retry/hold queues */
+		wait_event_freezable(kauditd_wait,
+				     (skb_queue_len(&audit_queue) ? 1 : 0));
 	}
 
 	return 0;
@@ -678,17 +801,16 @@ int audit_send_list(void *_dest)
 {
 	struct audit_netlink_list *dest = _dest;
 	struct sk_buff *skb;
-	struct net *net = dest->net;
-	struct audit_net *aunet = net_generic(net, audit_net_id);
+	struct sock *sk = audit_get_sk(dest->net);
 
 	/* wait for parent to finish and send an ACK */
 	mutex_lock(&audit_cmd_mutex);
 	mutex_unlock(&audit_cmd_mutex);
 
 	while ((skb = __skb_dequeue(&dest->q)) != NULL)
-		netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
+		netlink_unicast(sk, skb, dest->portid, 0);
 
-	put_net(net);
+	put_net(dest->net);
 	kfree(dest);
 
 	return 0;
@@ -722,16 +844,15 @@ out_kfree_skb:
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
-	struct net *net = reply->net;
-	struct audit_net *aunet = net_generic(net, audit_net_id);
+	struct sock *sk = audit_get_sk(reply->net);
 
 	mutex_lock(&audit_cmd_mutex);
 	mutex_unlock(&audit_cmd_mutex);
 
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
-	netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
-	put_net(net);
+	netlink_unicast(sk, reply->skb, reply->portid, 0);
+	put_net(reply->net);
 	kfree(reply);
 	return 0;
 }
@@ -949,12 +1070,12 @@ static int audit_set_feature(struct sk_buff *skb)
 
 static int audit_replace(pid_t pid)
 {
-	struct sk_buff *skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0,
-					       &pid, sizeof(pid));
+	struct sk_buff *skb;
 
+	skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0, &pid, sizeof(pid));
 	if (!skb)
 		return -ENOMEM;
-	return netlink_unicast(audit_sock, skb, audit_nlk_portid, 0);
+	return auditd_send_unicast_skb(skb);
 }
 
 static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -981,7 +1102,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		memset(&s, 0, sizeof(s));
 		s.enabled		= audit_enabled;
 		s.failure		= audit_failure;
-		s.pid			= audit_pid;
+		rcu_read_lock();
+		s.pid			= auditd_conn.pid;
+		rcu_read_unlock();
 		s.rate_limit		= audit_rate_limit;
 		s.backlog_limit		= audit_backlog_limit;
 		s.lost			= atomic_read(&audit_lost);
@@ -1014,30 +1137,44 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			 *       from the initial pid namespace, but something
 			 *       to keep in mind if this changes */
 			int new_pid = s.pid;
+			pid_t auditd_pid;
 			pid_t requesting_pid = task_tgid_vnr(current);
 
-			if ((!new_pid) && (requesting_pid != audit_pid)) {
-				audit_log_config_change("audit_pid", new_pid, audit_pid, 0);
+			/* test the auditd connection */
+			audit_replace(requesting_pid);
+
+			rcu_read_lock();
+			auditd_pid = auditd_conn.pid;
+			/* only the current auditd can unregister itself */
+			if ((!new_pid) && (requesting_pid != auditd_pid)) {
+				rcu_read_unlock();
+				audit_log_config_change("audit_pid", new_pid,
+							auditd_pid, 0);
 				return -EACCES;
 			}
-			if (audit_pid && new_pid &&
-			    audit_replace(requesting_pid) != -ECONNREFUSED) {
-				audit_log_config_change("audit_pid", new_pid, audit_pid, 0);
+			/* replacing a healthy auditd is not allowed */
+			if (auditd_pid && new_pid) {
+				rcu_read_unlock();
+				audit_log_config_change("audit_pid", new_pid,
+							auditd_pid, 0);
 				return -EEXIST;
 			}
+			rcu_read_unlock();
+
 			if (audit_enabled != AUDIT_OFF)
-				audit_log_config_change("audit_pid", new_pid, audit_pid, 1);
+				audit_log_config_change("audit_pid", new_pid,
+							auditd_pid, 1);
+
 			if (new_pid) {
-				if (audit_sock)
-					sock_put(audit_sock);
-				audit_pid = new_pid;
-				audit_nlk_portid = NETLINK_CB(skb).portid;
-				sock_hold(skb->sk);
-				audit_sock = skb->sk;
-			} else {
+				/* register a new auditd connection */
+				auditd_set(new_pid,
+					   NETLINK_CB(skb).portid,
+					   sock_net(NETLINK_CB(skb).sk));
+				/* try to process any backlog */
+				wake_up_interruptible(&kauditd_wait);
+			} else
+				/* unregister the auditd connection */
 				auditd_reset();
-			}
-			wake_up_interruptible(&kauditd_wait);
 		}
 		if (s.mask & AUDIT_STATUS_RATE_LIMIT) {
 			err = audit_set_rate_limit(s.rate_limit);
@@ -1090,7 +1227,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				if (err)
 					break;
 			}
-			mutex_unlock(&audit_cmd_mutex);
 			audit_log_common_recv_msg(&ab, msg_type);
 			if (msg_type != AUDIT_USER_TTY)
 				audit_log_format(ab, " msg='%.*s'",
@@ -1108,7 +1244,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			}
 			audit_set_portid(ab, NETLINK_CB(skb).portid);
 			audit_log_end(ab);
-			mutex_lock(&audit_cmd_mutex);
 		}
 		break;
 	case AUDIT_ADD_RULE:
@@ -1264,7 +1399,7 @@ static void audit_receive_skb(struct sk_buff *skb)
 		err = audit_receive_msg(skb, nlh);
 		/* if err or if this message says it wants a response */
 		if (err || (nlh->nlmsg_flags & NLM_F_ACK))
-			netlink_ack(skb, nlh, err);
+			netlink_ack(skb, nlh, err, NULL);
 
 		nlh = nlmsg_next(nlh, &len);
 	}
@@ -1298,26 +1433,26 @@ static int __net_init audit_net_init(struct net *net)
 
 	struct audit_net *aunet = net_generic(net, audit_net_id);
 
-	aunet->nlsk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
-	if (aunet->nlsk == NULL) {
+	aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
+	if (aunet->sk == NULL) {
 		audit_panic("cannot initialize netlink socket in namespace");
 		return -ENOMEM;
 	}
-	aunet->nlsk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+
 	return 0;
 }
 
 static void __net_exit audit_net_exit(struct net *net)
 {
 	struct audit_net *aunet = net_generic(net, audit_net_id);
-	struct sock *sock = aunet->nlsk;
-	mutex_lock(&audit_cmd_mutex);
-	if (sock == audit_sock)
+
+	rcu_read_lock();
+	if (net == auditd_conn.net)
 		auditd_reset();
-	mutex_unlock(&audit_cmd_mutex);
+	rcu_read_unlock();
 
-	netlink_kernel_release(sock);
-	aunet->nlsk = NULL;
+	netlink_kernel_release(aunet->sk);
 }
 
 static struct pernet_operations audit_net_ops __net_initdata = {
@@ -1335,20 +1470,24 @@ static int __init audit_init(void)
 	if (audit_initialized == AUDIT_DISABLED)
 		return 0;
 
-	pr_info("initializing netlink subsys (%s)\n",
-		audit_default ? "enabled" : "disabled");
-	register_pernet_subsys(&audit_net_ops);
+	memset(&auditd_conn, 0, sizeof(auditd_conn));
+	spin_lock_init(&auditd_conn.lock);
 
 	skb_queue_head_init(&audit_queue);
 	skb_queue_head_init(&audit_retry_queue);
 	skb_queue_head_init(&audit_hold_queue);
-	audit_initialized = AUDIT_INITIALIZED;
-	audit_enabled = audit_default;
-	audit_ever_enabled |= !!audit_default;
 
 	for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
 		INIT_LIST_HEAD(&audit_inode_hash[i]);
 
+	pr_info("initializing netlink subsys (%s)\n",
+		audit_default ? "enabled" : "disabled");
+	register_pernet_subsys(&audit_net_ops);
+
+	audit_initialized = AUDIT_INITIALIZED;
+	audit_enabled = audit_default;
+	audit_ever_enabled |= !!audit_default;
+
 	kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd");
 	if (IS_ERR(kauditd_task)) {
 		int err = PTR_ERR(kauditd_task);
@@ -1519,20 +1658,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE)))
 		return NULL;
 
-	/* don't ever fail/sleep on these two conditions:
+	/* NOTE: don't ever fail/sleep on these two conditions:
 	 * 1. auditd generated record - since we need auditd to drain the
 	 *    queue; also, when we are checking for auditd, compare PIDs using
 	 *    task_tgid_vnr() since auditd_pid is set in audit_receive_msg()
 	 *    using a PID anchored in the caller's namespace
-	 * 2. audit command message - record types 1000 through 1099 inclusive
-	 *    are command messages/records used to manage the kernel subsystem
-	 *    and the audit userspace, blocking on these messages could cause
-	 *    problems under load so don't do it (note: not all of these
-	 *    command types are valid as record types, but it is quicker to
-	 *    just check two ints than a series of ints in a if/switch stmt) */
-	if (!((audit_pid && audit_pid == task_tgid_vnr(current)) ||
-	      (type >= 1000 && type <= 1099))) {
-		long sleep_time = audit_backlog_wait_time;
+	 * 2. generator holding the audit_cmd_mutex - we don't want to block
+	 *    while holding the mutex */
+	if (!(auditd_test_task(current) ||
+	      (current == __mutex_owner(&audit_cmd_mutex)))) {
+		long stime = audit_backlog_wait_time;
 
 		while (audit_backlog_limit &&
 		       (skb_queue_len(&audit_queue) > audit_backlog_limit)) {
@@ -1541,14 +1676,13 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			/* sleep if we are allowed and we haven't exhausted our
 			 * backlog wait limit */
-			if ((gfp_mask & __GFP_DIRECT_RECLAIM) &&
-			    (sleep_time > 0)) {
+			if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) {
 				DECLARE_WAITQUEUE(wait, current);
 
 				add_wait_queue_exclusive(&audit_backlog_wait,
 							 &wait);
 				set_current_state(TASK_UNINTERRUPTIBLE);
-				sleep_time = schedule_timeout(sleep_time);
+				stime = schedule_timeout(stime);
 				remove_wait_queue(&audit_backlog_wait, &wait);
 			} else {
 				if (audit_rate_check() && printk_ratelimit())
@@ -2127,15 +2261,27 @@ out:
  */
 void audit_log_end(struct audit_buffer *ab)
 {
+	struct sk_buff *skb;
+	struct nlmsghdr *nlh;
+
 	if (!ab)
 		return;
-	if (!audit_rate_check()) {
-		audit_log_lost("rate limit exceeded");
-	} else {
-		skb_queue_tail(&audit_queue, ab->skb);
-		wake_up_interruptible(&kauditd_wait);
+
+	if (audit_rate_check()) {
+		skb = ab->skb;
 		ab->skb = NULL;
-	}
+
+		/* setup the netlink header, see the comments in
+		 * kauditd_send_multicast_skb() for length quirks */
+		nlh = nlmsg_hdr(skb);
+		nlh->nlmsg_len = skb->len - NLMSG_HDRLEN;
+
+		/* queue the netlink packet and poke the kauditd thread */
+		skb_queue_tail(&audit_queue, skb);
+		wake_up_interruptible(&kauditd_wait);
+	} else
+		audit_log_lost("rate limit exceeded");
+
 	audit_buffer_free(ab);
 }
 
diff --git a/kernel/audit.h b/kernel/audit.h
index ca579880303a..0d87f8ab8778 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -218,7 +218,7 @@ extern void audit_log_name(struct audit_context *context,
 			   struct audit_names *n, const struct path *path,
 			   int record_num, int *call_panic);
 
-extern int audit_pid;
+extern int auditd_test_task(const struct task_struct *task);
 
 #define AUDIT_INODE_BUCKETS	32
 extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@@ -250,10 +250,6 @@ struct audit_netlink_list {
 
 int audit_send_list(void *);
 
-struct audit_net {
-	struct sock *nlsk;
-};
-
 extern int selinux_audit_rule_update(void);
 
 extern struct mutex audit_filter_mutex;
@@ -337,14 +333,7 @@ extern u32 audit_sig_sid;
 extern int audit_filter(int msgtype, unsigned int listtype);
 
 #ifdef CONFIG_AUDITSYSCALL
-extern int __audit_signal_info(int sig, struct task_struct *t);
-static inline int audit_signal_info(int sig, struct task_struct *t)
-{
-	if (unlikely((audit_pid && t->tgid == audit_pid) ||
-		     (audit_signals && !audit_dummy_context())))
-		return __audit_signal_info(sig, t);
-	return 0;
-}
+extern int audit_signal_info(int sig, struct task_struct *t);
 extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
 extern struct list_head *audit_killed_trees(void);
 #else
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index d6a8de5f8fa3..1c2333155893 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -762,7 +762,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 	struct audit_entry *e;
 	enum audit_state state;
 
-	if (audit_pid && tsk->tgid == audit_pid)
+	if (auditd_test_task(tsk))
 		return AUDIT_DISABLED;
 
 	rcu_read_lock();
@@ -816,7 +816,7 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
 {
 	struct audit_names *n;
 
-	if (audit_pid && tsk->tgid == audit_pid)
+	if (auditd_test_task(tsk))
 		return;
 
 	rcu_read_lock();
@@ -2249,26 +2249,27 @@ void __audit_ptrace(struct task_struct *t)
  * If the audit subsystem is being terminated, record the task (pid)
  * and uid that is doing that.
  */
-int __audit_signal_info(int sig, struct task_struct *t)
+int audit_signal_info(int sig, struct task_struct *t)
 {
 	struct audit_aux_data_pids *axp;
 	struct task_struct *tsk = current;
 	struct audit_context *ctx = tsk->audit_context;
 	kuid_t uid = current_uid(), t_uid = task_uid(t);
 
-	if (audit_pid && t->tgid == audit_pid) {
-		if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
-			audit_sig_pid = task_tgid_nr(tsk);
-			if (uid_valid(tsk->loginuid))
-				audit_sig_uid = tsk->loginuid;
-			else
-				audit_sig_uid = uid;
-			security_task_getsecid(tsk, &audit_sig_sid);
-		}
-		if (!audit_signals || audit_dummy_context())
-			return 0;
+	if (auditd_test_task(t) &&
+	    (sig == SIGTERM || sig == SIGHUP ||
+	     sig == SIGUSR1 || sig == SIGUSR2)) {
+		audit_sig_pid = task_tgid_nr(tsk);
+		if (uid_valid(tsk->loginuid))
+			audit_sig_uid = tsk->loginuid;
+		else
+			audit_sig_uid = uid;
+		security_task_getsecid(tsk, &audit_sig_sid);
 	}
 
+	if (!audit_signals || audit_dummy_context())
+		return 0;
+
 	/* optimize the common case by putting first signal recipient directly
 	 * in audit_context */
 	if (!ctx->target_pid) {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e1ce4f4fd7fd..e1e5e658f2db 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,7 +1,7 @@
 obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 6b6f41f0b211..5e00b2333c26 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1,4 +1,5 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016,2017 Facebook
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -16,6 +17,8 @@
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 
+#include "map_in_map.h"
+
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
@@ -113,6 +116,30 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	return array->value + array->elem_size * index;
 }
 
+/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
+static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+	u32 elem_size = round_up(map->value_size, 8);
+	const int ret = BPF_REG_0;
+	const int map_ptr = BPF_REG_1;
+	const int index = BPF_REG_2;
+
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+
+	if (is_power_of_2(elem_size)) {
+		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+	} else {
+		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+	}
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+	return insn - insn_buf;
+}
+
 /* Called from eBPF program */
 static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -155,7 +182,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
 static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	u32 index = *(u32 *)key;
+	u32 index = key ? *(u32 *)key : U32_MAX;
 	u32 *next = (u32 *)next_key;
 
 	if (index >= array->map.max_entries) {
@@ -260,21 +287,17 @@ static void array_map_free(struct bpf_map *map)
 	bpf_map_area_free(array);
 }
 
-static const struct bpf_map_ops array_ops = {
+const struct bpf_map_ops array_map_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
+	.map_gen_lookup = array_map_gen_lookup,
 };
 
-static struct bpf_map_type_list array_type __ro_after_init = {
-	.ops = &array_ops,
-	.type = BPF_MAP_TYPE_ARRAY,
-};
-
-static const struct bpf_map_ops percpu_array_ops = {
+const struct bpf_map_ops percpu_array_map_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -283,19 +306,6 @@ static const struct bpf_map_ops percpu_array_ops = {
 	.map_delete_elem = array_map_delete_elem,
 };
 
-static struct bpf_map_type_list percpu_array_type __ro_after_init = {
-	.ops = &percpu_array_ops,
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-};
-
-static int __init register_array_map(void)
-{
-	bpf_register_map_type(&array_type);
-	bpf_register_map_type(&percpu_array_type);
-	return 0;
-}
-late_initcall(register_array_map);
-
 static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
 {
 	/* only file descriptors can be stored in this type of map */
@@ -399,7 +409,7 @@ void bpf_fd_array_map_clear(struct bpf_map *map)
 		fd_array_map_delete_elem(map, &i);
 }
 
-static const struct bpf_map_ops prog_array_ops = {
+const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc = fd_array_map_alloc,
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -409,18 +419,6 @@ static const struct bpf_map_ops prog_array_ops = {
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 };
 
-static struct bpf_map_type_list prog_array_type __ro_after_init = {
-	.ops = &prog_array_ops,
-	.type = BPF_MAP_TYPE_PROG_ARRAY,
-};
-
-static int __init register_prog_array_map(void)
-{
-	bpf_register_map_type(&prog_array_type);
-	return 0;
-}
-late_initcall(register_prog_array_map);
-
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
 						   struct file *map_file)
 {
@@ -511,7 +509,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	rcu_read_unlock();
 }
 
-static const struct bpf_map_ops perf_event_array_ops = {
+const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_alloc = fd_array_map_alloc,
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -522,18 +520,6 @@ static const struct bpf_map_ops perf_event_array_ops = {
 	.map_release = perf_event_fd_array_release,
 };
 
-static struct bpf_map_type_list perf_event_array_type __ro_after_init = {
-	.ops = &perf_event_array_ops,
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-};
-
-static int __init register_perf_event_array_map(void)
-{
-	bpf_register_map_type(&perf_event_array_type);
-	return 0;
-}
-late_initcall(register_perf_event_array_map);
-
 #ifdef CONFIG_CGROUPS
 static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 				     struct file *map_file /* not used */,
@@ -554,7 +540,7 @@ static void cgroup_fd_array_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
-static const struct bpf_map_ops cgroup_array_ops = {
+const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_alloc = fd_array_map_alloc,
 	.map_free = cgroup_fd_array_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -563,16 +549,53 @@ static const struct bpf_map_ops cgroup_array_ops = {
 	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
 	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
 };
+#endif
 
-static struct bpf_map_type_list cgroup_array_type __ro_after_init = {
-	.ops = &cgroup_array_ops,
-	.type = BPF_MAP_TYPE_CGROUP_ARRAY,
-};
+static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map, *inner_map_meta;
+
+	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+	if (IS_ERR(inner_map_meta))
+		return inner_map_meta;
 
-static int __init register_cgroup_array_map(void)
+	map = fd_array_map_alloc(attr);
+	if (IS_ERR(map)) {
+		bpf_map_meta_free(inner_map_meta);
+		return map;
+	}
+
+	map->inner_map_meta = inner_map_meta;
+
+	return map;
+}
+
+static void array_of_map_free(struct bpf_map *map)
 {
-	bpf_register_map_type(&cgroup_array_type);
-	return 0;
+	/* map->inner_map_meta is only accessed by syscall which
+	 * is protected by fdget/fdput.
+	 */
+	bpf_map_meta_free(map->inner_map_meta);
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
 }
-late_initcall(register_cgroup_array_map);
-#endif
+
+static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map = array_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+const struct bpf_map_ops array_of_maps_map_ops = {
+	.map_alloc = array_of_map_alloc,
+	.map_free = array_of_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = array_of_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+};
diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
index f62d1d56f41d..e6ef4401a138 100644
--- a/kernel/bpf/bpf_lru_list.c
+++ b/kernel/bpf/bpf_lru_list.c
@@ -13,7 +13,7 @@
 #define LOCAL_FREE_TARGET		(128)
 #define LOCAL_NR_SCANS			LOCAL_FREE_TARGET
 
-#define PERCPU_FREE_TARGET		(16)
+#define PERCPU_FREE_TARGET		(4)
 #define PERCPU_NR_SCANS			PERCPU_FREE_TARGET
 
 /* Helpers to get the local list index */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index da0f53690295..ea6033cba947 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -154,7 +154,7 @@ int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
 
 /**
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
- * @sk: The socken sending or receiving traffic
+ * @sk: The socket sending or receiving traffic
  * @skb: The skb that is being sent or received
  * @type: The type of program to be exectuted
  *
@@ -189,10 +189,13 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	prog = rcu_dereference(cgrp->bpf.effective[type]);
 	if (prog) {
 		unsigned int offset = skb->data - skb_network_header(skb);
+		struct sock *save_sk = skb->sk;
 
+		skb->sk = sk;
 		__skb_push(skb, offset);
 		ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM;
 		__skb_pull(skb, offset);
+		skb->sk = save_sk;
 	}
 
 	rcu_read_unlock();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f45827e205d3..6f81e0f5a0fa 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -394,27 +394,23 @@ static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
 
 void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 {
-	unsigned long flags;
-
 	if (!bpf_prog_kallsyms_candidate(fp) ||
 	    !capable(CAP_SYS_ADMIN))
 		return;
 
-	spin_lock_irqsave(&bpf_lock, flags);
+	spin_lock_bh(&bpf_lock);
 	bpf_prog_ksym_node_add(fp->aux);
-	spin_unlock_irqrestore(&bpf_lock, flags);
+	spin_unlock_bh(&bpf_lock);
 }
 
 void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 {
-	unsigned long flags;
-
 	if (!bpf_prog_kallsyms_candidate(fp))
 		return;
 
-	spin_lock_irqsave(&bpf_lock, flags);
+	spin_lock_bh(&bpf_lock);
 	bpf_prog_ksym_node_del(fp->aux);
-	spin_unlock_irqrestore(&bpf_lock, flags);
+	spin_unlock_bh(&bpf_lock);
 }
 
 static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
@@ -1162,12 +1158,12 @@ out:
 	LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
 		off = IMM;
 load_word:
-		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
-		 * only appearing in the programs where ctx ==
-		 * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
-		 * == BPF_R6, bpf_convert_filter() saves it in BPF_R6,
-		 * internal BPF verifier will check that BPF_R6 ==
-		 * ctx.
+		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
+		 * appearing in the programs where ctx == skb
+		 * (see may_access_skb() in the verifier). All programs
+		 * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6,
+		 * bpf_convert_filter() saves it in BPF_R6, internal BPF
+		 * verifier will check that BPF_R6 == ctx.
 		 *
 		 * BPF_ABS and BPF_IND are wrappers of function calls,
 		 * so they scratch BPF_R1-BPF_R5 registers, preserve
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ea87fb19a94..004334ea13ba 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,11 +13,13 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
+#include <linux/rculist_nulls.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
+#include "map_in_map.h"
 
 struct bucket {
-	struct hlist_head head;
+	struct hlist_nulls_head head;
 	raw_spinlock_t lock;
 };
 
@@ -29,28 +31,26 @@ struct bpf_htab {
 		struct pcpu_freelist freelist;
 		struct bpf_lru lru;
 	};
-	void __percpu *extra_elems;
+	struct htab_elem *__percpu *extra_elems;
 	atomic_t count;	/* number of elements in this hashtable */
 	u32 n_buckets;	/* number of hash buckets */
 	u32 elem_size;	/* size of each element in bytes */
 };
 
-enum extra_elem_state {
-	HTAB_NOT_AN_EXTRA_ELEM = 0,
-	HTAB_EXTRA_ELEM_FREE,
-	HTAB_EXTRA_ELEM_USED
-};
-
 /* each htab element is struct htab_elem + key + value */
 struct htab_elem {
 	union {
-		struct hlist_node hash_node;
-		struct bpf_htab *htab;
-		struct pcpu_freelist_node fnode;
+		struct hlist_nulls_node hash_node;
+		struct {
+			void *padding;
+			union {
+				struct bpf_htab *htab;
+				struct pcpu_freelist_node fnode;
+			};
+		};
 	};
 	union {
 		struct rcu_head rcu;
-		enum extra_elem_state state;
 		struct bpf_lru_node lru_node;
 	};
 	u32 hash;
@@ -71,6 +71,11 @@ static bool htab_is_percpu(const struct bpf_htab *htab)
 		htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
 }
 
+static bool htab_is_prealloc(const struct bpf_htab *htab)
+{
+	return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
+}
+
 static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
 				     void __percpu *pptr)
 {
@@ -82,6 +87,11 @@ static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size
 	return *(void __percpu **)(l->key + key_size);
 }
 
+static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
+{
+	return *(void **)(l->key + roundup(map->key_size, 8));
+}
+
 static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
 {
 	return (struct htab_elem *) (htab->elems + i * htab->elem_size);
@@ -122,17 +132,20 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 
 static int prealloc_init(struct bpf_htab *htab)
 {
+	u32 num_entries = htab->map.max_entries;
 	int err = -ENOMEM, i;
 
-	htab->elems = bpf_map_area_alloc(htab->elem_size *
-					 htab->map.max_entries);
+	if (!htab_is_percpu(htab) && !htab_is_lru(htab))
+		num_entries += num_possible_cpus();
+
+	htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries);
 	if (!htab->elems)
 		return -ENOMEM;
 
 	if (!htab_is_percpu(htab))
 		goto skip_percpu_elems;
 
-	for (i = 0; i < htab->map.max_entries; i++) {
+	for (i = 0; i < num_entries; i++) {
 		u32 size = round_up(htab->map.value_size, 8);
 		void __percpu *pptr;
 
@@ -160,10 +173,11 @@ skip_percpu_elems:
 	if (htab_is_lru(htab))
 		bpf_lru_populate(&htab->lru, htab->elems,
 				 offsetof(struct htab_elem, lru_node),
-				 htab->elem_size, htab->map.max_entries);
+				 htab->elem_size, num_entries);
 	else
-		pcpu_freelist_populate(&htab->freelist, htab->elems,
-				       htab->elem_size, htab->map.max_entries);
+		pcpu_freelist_populate(&htab->freelist,
+				       htab->elems + offsetof(struct htab_elem, fnode),
+				       htab->elem_size, num_entries);
 
 	return 0;
 
@@ -184,16 +198,22 @@ static void prealloc_destroy(struct bpf_htab *htab)
 
 static int alloc_extra_elems(struct bpf_htab *htab)
 {
-	void __percpu *pptr;
+	struct htab_elem *__percpu *pptr, *l_new;
+	struct pcpu_freelist_node *l;
 	int cpu;
 
-	pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN);
+	pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8,
+				  GFP_USER | __GFP_NOWARN);
 	if (!pptr)
 		return -ENOMEM;
 
 	for_each_possible_cpu(cpu) {
-		((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state =
-			HTAB_EXTRA_ELEM_FREE;
+		l = pcpu_freelist_pop(&htab->freelist);
+		/* pop will succeed, since prealloc_init()
+		 * preallocated extra num_possible_cpus elements
+		 */
+		l_new = container_of(l, struct htab_elem, fnode);
+		*per_cpu_ptr(pptr, cpu) = l_new;
 	}
 	htab->extra_elems = pptr;
 	return 0;
@@ -217,6 +237,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	int err, i;
 	u64 cost;
 
+	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
+		     offsetof(struct htab_elem, hash_node.pprev));
+	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
+		     offsetof(struct htab_elem, hash_node.pprev));
+
 	if (lru && !capable(CAP_SYS_ADMIN))
 		/* LRU implementation is much complicated than other
 		 * maps.  Hence, limit to CAP_SYS_ADMIN for now.
@@ -326,29 +351,29 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		goto free_htab;
 
 	for (i = 0; i < htab->n_buckets; i++) {
-		INIT_HLIST_HEAD(&htab->buckets[i].head);
+		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
 		raw_spin_lock_init(&htab->buckets[i].lock);
 	}
 
-	if (!percpu && !lru) {
-		/* lru itself can remove the least used element, so
-		 * there is no need for an extra elem during map_update.
-		 */
-		err = alloc_extra_elems(htab);
-		if (err)
-			goto free_buckets;
-	}
-
 	if (prealloc) {
 		err = prealloc_init(htab);
 		if (err)
-			goto free_extra_elems;
+			goto free_buckets;
+
+		if (!percpu && !lru) {
+			/* lru itself can remove the least used element, so
+			 * there is no need for an extra elem during map_update.
+			 */
+			err = alloc_extra_elems(htab);
+			if (err)
+				goto free_prealloc;
+		}
 	}
 
 	return &htab->map;
 
-free_extra_elems:
-	free_percpu(htab->extra_elems);
+free_prealloc:
+	prealloc_destroy(htab);
 free_buckets:
 	bpf_map_area_free(htab->buckets);
 free_htab:
@@ -366,28 +391,56 @@ static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
 	return &htab->buckets[hash & (htab->n_buckets - 1)];
 }
 
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
 {
 	return &__select_bucket(htab, hash)->head;
 }
 
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
+/* this lookup function can only be called with bucket lock taken */
+static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
 					 void *key, u32 key_size)
 {
+	struct hlist_nulls_node *n;
 	struct htab_elem *l;
 
-	hlist_for_each_entry_rcu(l, head, hash_node)
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l->hash == hash && !memcmp(&l->key, key, key_size))
 			return l;
 
 	return NULL;
 }
 
-/* Called from syscall or from eBPF program */
+/* can be called without bucket lock. it will repeat the loop in
+ * the unlikely event when elements moved from one bucket into another
+ * while link list is being walked
+ */
+static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
+					       u32 hash, void *key,
+					       u32 key_size, u32 n_buckets)
+{
+	struct hlist_nulls_node *n;
+	struct htab_elem *l;
+
+again:
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+
+	if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
+		goto again;
+
+	return NULL;
+}
+
+/* Called from syscall or from eBPF program directly, so
+ * arguments have to match bpf_map_lookup_elem() exactly.
+ * The return value is adjusted by BPF instructions
+ * in htab_map_gen_lookup().
+ */
 static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct htab_elem *l;
 	u32 hash, key_size;
 
@@ -400,7 +453,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 
 	head = select_bucket(htab, hash);
 
-	l = lookup_elem_raw(head, hash, key, key_size);
+	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
 	return l;
 }
@@ -415,6 +468,30 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
 	return NULL;
 }
 
+/* inline bpf_map_lookup_elem() call.
+ * Instead of:
+ * bpf_prog
+ *   bpf_map_lookup_elem
+ *     map->ops->map_lookup_elem
+ *       htab_map_lookup_elem
+ *         __htab_map_lookup_elem
+ * do:
+ * bpf_prog
+ *   __htab_map_lookup_elem
+ */
+static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+	const int ret = BPF_REG_0;
+
+	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+				offsetof(struct htab_elem, key) +
+				round_up(map->key_size, 8));
+	return insn - insn_buf;
+}
+
 static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
@@ -433,8 +510,9 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 {
 	struct bpf_htab *htab = (struct bpf_htab *)arg;
-	struct htab_elem *l, *tgt_l;
-	struct hlist_head *head;
+	struct htab_elem *l = NULL, *tgt_l;
+	struct hlist_nulls_head *head;
+	struct hlist_nulls_node *n;
 	unsigned long flags;
 	struct bucket *b;
 
@@ -444,9 +522,9 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 
 	raw_spin_lock_irqsave(&b->lock, flags);
 
-	hlist_for_each_entry_rcu(l, head, hash_node)
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
-			hlist_del_rcu(&l->hash_node);
+			hlist_nulls_del_rcu(&l->hash_node);
 			break;
 		}
 
@@ -459,29 +537,30 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct htab_elem *l, *next_l;
 	u32 hash, key_size;
-	int i;
+	int i = 0;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	key_size = map->key_size;
 
+	if (!key)
+		goto find_first_elem;
+
 	hash = htab_map_hash(key, key_size);
 
 	head = select_bucket(htab, hash);
 
 	/* lookup the key */
-	l = lookup_elem_raw(head, hash, key, key_size);
+	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
-	if (!l) {
-		i = 0;
+	if (!l)
 		goto find_first_elem;
-	}
 
 	/* key was found, get next key in the same bucket */
-	next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+	next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
 				  struct htab_elem, hash_node);
 
 	if (next_l) {
@@ -500,7 +579,7 @@ find_first_elem:
 		head = select_bucket(htab, i);
 
 		/* pick first element in the bucket */
-		next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+		next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)),
 					  struct htab_elem, hash_node);
 		if (next_l) {
 			/* if it's not empty, just return it */
@@ -538,12 +617,15 @@ static void htab_elem_free_rcu(struct rcu_head *head)
 
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
-	if (l->state == HTAB_EXTRA_ELEM_USED) {
-		l->state = HTAB_EXTRA_ELEM_FREE;
-		return;
+	struct bpf_map *map = &htab->map;
+
+	if (map->ops->map_fd_put_ptr) {
+		void *ptr = fd_htab_map_get_ptr(map, l);
+
+		map->ops->map_fd_put_ptr(ptr);
 	}
 
-	if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) {
+	if (htab_is_prealloc(htab)) {
 		pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		atomic_dec(&htab->count);
@@ -573,43 +655,43 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 					 void *value, u32 key_size, u32 hash,
 					 bool percpu, bool onallcpus,
-					 bool old_elem_exists)
+					 struct htab_elem *old_elem)
 {
 	u32 size = htab->map.value_size;
-	bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC);
-	struct htab_elem *l_new;
+	bool prealloc = htab_is_prealloc(htab);
+	struct htab_elem *l_new, **pl_new;
 	void __percpu *pptr;
-	int err = 0;
 
 	if (prealloc) {
-		l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
-		if (!l_new)
-			err = -E2BIG;
-	} else {
-		if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
-			atomic_dec(&htab->count);
-			err = -E2BIG;
+		if (old_elem) {
+			/* if we're updating the existing element,
+			 * use per-cpu extra elems to avoid freelist_pop/push
+			 */
+			pl_new = this_cpu_ptr(htab->extra_elems);
+			l_new = *pl_new;
+			*pl_new = old_elem;
 		} else {
-			l_new = kmalloc(htab->elem_size,
-					GFP_ATOMIC | __GFP_NOWARN);
-			if (!l_new)
-				return ERR_PTR(-ENOMEM);
-		}
-	}
-
-	if (err) {
-		if (!old_elem_exists)
-			return ERR_PTR(err);
+			struct pcpu_freelist_node *l;
 
-		/* if we're updating the existing element and the hash table
-		 * is full, use per-cpu extra elems
-		 */
-		l_new = this_cpu_ptr(htab->extra_elems);
-		if (l_new->state != HTAB_EXTRA_ELEM_FREE)
-			return ERR_PTR(-E2BIG);
-		l_new->state = HTAB_EXTRA_ELEM_USED;
+			l = pcpu_freelist_pop(&htab->freelist);
+			if (!l)
+				return ERR_PTR(-E2BIG);
+			l_new = container_of(l, struct htab_elem, fnode);
+		}
 	} else {
-		l_new->state = HTAB_NOT_AN_EXTRA_ELEM;
+		if (atomic_inc_return(&htab->count) > htab->map.max_entries)
+			if (!old_elem) {
+				/* when map is full and update() is replacing
+				 * old element, it's ok to allocate, since
+				 * old element will be freed immediately.
+				 * Otherwise return an error
+				 */
+				atomic_dec(&htab->count);
+				return ERR_PTR(-E2BIG);
+			}
+		l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+		if (!l_new)
+			return ERR_PTR(-ENOMEM);
 	}
 
 	memcpy(l_new->key, key, key_size);
@@ -661,7 +743,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -690,7 +772,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		goto err;
 
 	l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
-				!!l_old);
+				l_old);
 	if (IS_ERR(l_new)) {
 		/* all pre-allocated elements are in use or memory exhausted */
 		ret = PTR_ERR(l_new);
@@ -700,10 +782,11 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
 	 */
-	hlist_add_head_rcu(&l_new->hash_node, head);
+	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
-		hlist_del_rcu(&l_old->hash_node);
-		free_htab_elem(htab, l_old);
+		hlist_nulls_del_rcu(&l_old->hash_node);
+		if (!htab_is_prealloc(htab))
+			free_htab_elem(htab, l_old);
 	}
 	ret = 0;
 err:
@@ -716,7 +799,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new, *l_old = NULL;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -757,10 +840,10 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
 	 */
-	hlist_add_head_rcu(&l_new->hash_node, head);
+	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
 		bpf_lru_node_set_ref(&l_new->lru_node);
-		hlist_del_rcu(&l_old->hash_node);
+		hlist_nulls_del_rcu(&l_old->hash_node);
 	}
 	ret = 0;
 
@@ -781,7 +864,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -815,12 +898,12 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 				value, onallcpus);
 	} else {
 		l_new = alloc_htab_elem(htab, key, value, key_size,
-					hash, true, onallcpus, false);
+					hash, true, onallcpus, NULL);
 		if (IS_ERR(l_new)) {
 			ret = PTR_ERR(l_new);
 			goto err;
 		}
-		hlist_add_head_rcu(&l_new->hash_node, head);
+		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	}
 	ret = 0;
 err:
@@ -834,7 +917,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -882,7 +965,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	} else {
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
 				value, onallcpus);
-		hlist_add_head_rcu(&l_new->hash_node, head);
+		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;
 	}
 	ret = 0;
@@ -910,7 +993,7 @@ static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 static int htab_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct bucket *b;
 	struct htab_elem *l;
 	unsigned long flags;
@@ -930,7 +1013,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
-		hlist_del_rcu(&l->hash_node);
+		hlist_nulls_del_rcu(&l->hash_node);
 		free_htab_elem(htab, l);
 		ret = 0;
 	}
@@ -942,7 +1025,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct bucket *b;
 	struct htab_elem *l;
 	unsigned long flags;
@@ -962,7 +1045,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
-		hlist_del_rcu(&l->hash_node);
+		hlist_nulls_del_rcu(&l->hash_node);
 		ret = 0;
 	}
 
@@ -977,17 +1060,17 @@ static void delete_all_elements(struct bpf_htab *htab)
 	int i;
 
 	for (i = 0; i < htab->n_buckets; i++) {
-		struct hlist_head *head = select_bucket(htab, i);
-		struct hlist_node *n;
+		struct hlist_nulls_head *head = select_bucket(htab, i);
+		struct hlist_nulls_node *n;
 		struct htab_elem *l;
 
-		hlist_for_each_entry_safe(l, n, head, hash_node) {
-			hlist_del_rcu(&l->hash_node);
-			if (l->state != HTAB_EXTRA_ELEM_USED)
-				htab_elem_free(htab, l);
+		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+			hlist_nulls_del_rcu(&l->hash_node);
+			htab_elem_free(htab, l);
 		}
 	}
 }
+
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void htab_map_free(struct bpf_map *map)
 {
@@ -1004,7 +1087,7 @@ static void htab_map_free(struct bpf_map *map)
 	 * not have executed. Wait for them.
 	 */
 	rcu_barrier();
-	if (htab->map.map_flags & BPF_F_NO_PREALLOC)
+	if (!htab_is_prealloc(htab))
 		delete_all_elements(htab);
 	else
 		prealloc_destroy(htab);
@@ -1014,21 +1097,17 @@ static void htab_map_free(struct bpf_map *map)
 	kfree(htab);
 }
 
-static const struct bpf_map_ops htab_ops = {
+const struct bpf_map_ops htab_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_map_lookup_elem,
 	.map_update_elem = htab_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
+	.map_gen_lookup = htab_map_gen_lookup,
 };
 
-static struct bpf_map_type_list htab_type __ro_after_init = {
-	.ops = &htab_ops,
-	.type = BPF_MAP_TYPE_HASH,
-};
-
-static const struct bpf_map_ops htab_lru_ops = {
+const struct bpf_map_ops htab_lru_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1037,11 +1116,6 @@ static const struct bpf_map_ops htab_lru_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 };
 
-static struct bpf_map_type_list htab_lru_type __ro_after_init = {
-	.ops = &htab_lru_ops,
-	.type = BPF_MAP_TYPE_LRU_HASH,
-};
-
 /* Called from eBPF program */
 static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -1115,7 +1189,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 	return ret;
 }
 
-static const struct bpf_map_ops htab_percpu_ops = {
+const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1124,12 +1198,7 @@ static const struct bpf_map_ops htab_percpu_ops = {
 	.map_delete_elem = htab_map_delete_elem,
 };
 
-static struct bpf_map_type_list htab_percpu_type __ro_after_init = {
-	.ops = &htab_percpu_ops,
-	.type = BPF_MAP_TYPE_PERCPU_HASH,
-};
-
-static const struct bpf_map_ops htab_lru_percpu_ops = {
+const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1138,17 +1207,102 @@ static const struct bpf_map_ops htab_lru_percpu_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 };
 
-static struct bpf_map_type_list htab_lru_percpu_type __ro_after_init = {
-	.ops = &htab_lru_percpu_ops,
-	.type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
-};
+static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map;
+
+	if (attr->value_size != sizeof(u32))
+		return ERR_PTR(-EINVAL);
+
+	/* pointer is stored internally */
+	attr->value_size = sizeof(void *);
+	map = htab_map_alloc(attr);
+	attr->value_size = sizeof(u32);
+
+	return map;
+}
 
-static int __init register_htab_map(void)
+static void fd_htab_map_free(struct bpf_map *map)
 {
-	bpf_register_map_type(&htab_type);
-	bpf_register_map_type(&htab_percpu_type);
-	bpf_register_map_type(&htab_lru_type);
-	bpf_register_map_type(&htab_lru_percpu_type);
-	return 0;
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_node *n;
+	struct hlist_nulls_head *head;
+	struct htab_elem *l;
+	int i;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		head = select_bucket(htab, i);
+
+		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+			void *ptr = fd_htab_map_get_ptr(map, l);
+
+			map->ops->map_fd_put_ptr(ptr);
+		}
+	}
+
+	htab_map_free(map);
 }
-late_initcall(register_htab_map);
+
+/* only called from syscall */
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+				void *key, void *value, u64 map_flags)
+{
+	void *ptr;
+	int ret;
+	u32 ufd = *(u32 *)value;
+
+	ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	if (ret)
+		map->ops->map_fd_put_ptr(ptr);
+
+	return ret;
+}
+
+static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map, *inner_map_meta;
+
+	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+	if (IS_ERR(inner_map_meta))
+		return inner_map_meta;
+
+	map = fd_htab_map_alloc(attr);
+	if (IS_ERR(map)) {
+		bpf_map_meta_free(inner_map_meta);
+		return map;
+	}
+
+	map->inner_map_meta = inner_map_meta;
+
+	return map;
+}
+
+static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map  = htab_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+static void htab_of_map_free(struct bpf_map *map)
+{
+	bpf_map_meta_free(map->inner_map_meta);
+	fd_htab_map_free(map);
+}
+
+const struct bpf_map_ops htab_of_maps_map_ops = {
+	.map_alloc = htab_of_map_alloc,
+	.map_free = htab_of_map_free,
+	.map_get_next_key = htab_map_get_next_key,
+	.map_lookup_elem = htab_of_map_lookup_elem,
+	.map_delete_elem = htab_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+};
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 8bfe0afaee10..39cfafd895b8 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -500,22 +500,16 @@ unlock:
 	raw_spin_unlock(&trie->lock);
 }
 
-static const struct bpf_map_ops trie_ops = {
+static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+const struct bpf_map_ops trie_map_ops = {
 	.map_alloc = trie_alloc,
 	.map_free = trie_free,
+	.map_get_next_key = trie_get_next_key,
 	.map_lookup_elem = trie_lookup_elem,
 	.map_update_elem = trie_update_elem,
 	.map_delete_elem = trie_delete_elem,
 };
-
-static struct bpf_map_type_list trie_type __ro_after_init = {
-	.ops = &trie_ops,
-	.type = BPF_MAP_TYPE_LPM_TRIE,
-};
-
-static int __init register_trie_map(void)
-{
-	bpf_register_map_type(&trie_type);
-	return 0;
-}
-late_initcall(register_trie_map);
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
new file mode 100644
index 000000000000..59bcdf821ae4
--- /dev/null
+++ b/kernel/bpf/map_in_map.c
@@ -0,0 +1,97 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/slab.h>
+#include <linux/bpf.h>
+
+#include "map_in_map.h"
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
+{
+	struct bpf_map *inner_map, *inner_map_meta;
+	struct fd f;
+
+	f = fdget(inner_map_ufd);
+	inner_map = __bpf_map_get(f);
+	if (IS_ERR(inner_map))
+		return inner_map;
+
+	/* prog_array->owner_prog_type and owner_jited
+	 * is a runtime binding.  Doing static check alone
+	 * in the verifier is not enough.
+	 */
+	if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+		fdput(f);
+		return ERR_PTR(-ENOTSUPP);
+	}
+
+	/* Does not support >1 level map-in-map */
+	if (inner_map->inner_map_meta) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	inner_map_meta = kzalloc(sizeof(*inner_map_meta), GFP_USER);
+	if (!inner_map_meta) {
+		fdput(f);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inner_map_meta->map_type = inner_map->map_type;
+	inner_map_meta->key_size = inner_map->key_size;
+	inner_map_meta->value_size = inner_map->value_size;
+	inner_map_meta->map_flags = inner_map->map_flags;
+	inner_map_meta->ops = inner_map->ops;
+	inner_map_meta->max_entries = inner_map->max_entries;
+
+	fdput(f);
+	return inner_map_meta;
+}
+
+void bpf_map_meta_free(struct bpf_map *map_meta)
+{
+	kfree(map_meta);
+}
+
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1)
+{
+	/* No need to compare ops because it is covered by map_type */
+	return meta0->map_type == meta1->map_type &&
+		meta0->key_size == meta1->key_size &&
+		meta0->value_size == meta1->value_size &&
+		meta0->map_flags == meta1->map_flags &&
+		meta0->max_entries == meta1->max_entries;
+}
+
+void *bpf_map_fd_get_ptr(struct bpf_map *map,
+			 struct file *map_file /* not used */,
+			 int ufd)
+{
+	struct bpf_map *inner_map;
+	struct fd f;
+
+	f = fdget(ufd);
+	inner_map = __bpf_map_get(f);
+	if (IS_ERR(inner_map))
+		return inner_map;
+
+	if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
+		inner_map = bpf_map_inc(inner_map, false);
+	else
+		inner_map = ERR_PTR(-EINVAL);
+
+	fdput(f);
+	return inner_map;
+}
+
+void bpf_map_fd_put_ptr(void *ptr)
+{
+	/* ptr->ops->map_free() has to go through one
+	 * rcu grace period by itself.
+	 */
+	bpf_map_put(ptr);
+}
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
new file mode 100644
index 000000000000..177fadb689dc
--- /dev/null
+++ b/kernel/bpf/map_in_map.h
@@ -0,0 +1,23 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __MAP_IN_MAP_H__
+#define __MAP_IN_MAP_H__
+
+#include <linux/types.h>
+
+struct file;
+struct bpf_map;
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
+void bpf_map_meta_free(struct bpf_map *map_meta);
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1);
+void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
+			 int ufd);
+void bpf_map_fd_put_ptr(void *ptr);
+
+#endif
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 22aa45cd0324..4dfd6f2ec2f9 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -264,7 +264,7 @@ static void stack_map_free(struct bpf_map *map)
 	put_callchain_buffers();
 }
 
-static const struct bpf_map_ops stack_map_ops = {
+const struct bpf_map_ops stack_map_ops = {
 	.map_alloc = stack_map_alloc,
 	.map_free = stack_map_free,
 	.map_get_next_key = stack_map_get_next_key,
@@ -272,15 +272,3 @@ static const struct bpf_map_ops stack_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 };
-
-static struct bpf_map_type_list stack_map_type __ro_after_init = {
-	.ops = &stack_map_ops,
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-};
-
-static int __init register_stack_map(void)
-{
-	bpf_register_map_type(&stack_map_type);
-	return 0;
-}
-late_initcall(register_stack_map);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7af0dcc5d755..13642c73dca0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -27,30 +27,29 @@ DEFINE_PER_CPU(int, bpf_prog_active);
 
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
-static LIST_HEAD(bpf_map_types);
+static const struct bpf_map_ops * const bpf_map_types[] = {
+#define BPF_PROG_TYPE(_id, _ops)
+#define BPF_MAP_TYPE(_id, _ops) \
+	[_id] = &_ops,
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
 
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 {
-	struct bpf_map_type_list *tl;
 	struct bpf_map *map;
 
-	list_for_each_entry(tl, &bpf_map_types, list_node) {
-		if (tl->type == attr->map_type) {
-			map = tl->ops->map_alloc(attr);
-			if (IS_ERR(map))
-				return map;
-			map->ops = tl->ops;
-			map->map_type = attr->map_type;
-			return map;
-		}
-	}
-	return ERR_PTR(-EINVAL);
-}
+	if (attr->map_type >= ARRAY_SIZE(bpf_map_types) ||
+	    !bpf_map_types[attr->map_type])
+		return ERR_PTR(-EINVAL);
 
-/* boot time registration of different map implementations */
-void bpf_register_map_type(struct bpf_map_type_list *tl)
-{
-	list_add(&tl->list_node, &bpf_map_types);
+	map = bpf_map_types[attr->map_type]->map_alloc(attr);
+	if (IS_ERR(map))
+		return map;
+	map->ops = bpf_map_types[attr->map_type];
+	map->map_type = attr->map_type;
+	return map;
 }
 
 void *bpf_map_area_alloc(size_t size)
@@ -215,7 +214,7 @@ int bpf_map_new_fd(struct bpf_map *map)
 		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
 		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
 
-#define BPF_MAP_CREATE_LAST_FIELD map_flags
+#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -352,6 +351,9 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = bpf_percpu_array_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
 		err = bpf_stackmap_copy(map, key, value);
+	} else if (map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+		   map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+		err = -ENOTSUPP;
 	} else {
 		rcu_read_lock();
 		ptr = map->ops->map_lookup_elem(map, key);
@@ -438,11 +440,17 @@ static int map_update_elem(union bpf_attr *attr)
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
 		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
-		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) {
+		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) {
 		rcu_read_lock();
 		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
 						   attr->flags);
 		rcu_read_unlock();
+	} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+		rcu_read_lock();
+		err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
+						  attr->flags);
+		rcu_read_unlock();
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -528,14 +536,18 @@ static int map_get_next_key(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
-	err = -ENOMEM;
-	key = kmalloc(map->key_size, GFP_USER);
-	if (!key)
-		goto err_put;
+	if (ukey) {
+		err = -ENOMEM;
+		key = kmalloc(map->key_size, GFP_USER);
+		if (!key)
+			goto err_put;
 
-	err = -EFAULT;
-	if (copy_from_user(key, ukey, map->key_size) != 0)
-		goto free_key;
+		err = -EFAULT;
+		if (copy_from_user(key, ukey, map->key_size) != 0)
+			goto free_key;
+	} else {
+		key = NULL;
+	}
 
 	err = -ENOMEM;
 	next_key = kmalloc(map->key_size, GFP_USER);
@@ -564,79 +576,23 @@ err_put:
 	return err;
 }
 
-static LIST_HEAD(bpf_prog_types);
+static const struct bpf_verifier_ops * const bpf_prog_types[] = {
+#define BPF_PROG_TYPE(_id, _ops) \
+	[_id] = &_ops,
+#define BPF_MAP_TYPE(_id, _ops)
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
 
 static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 {
-	struct bpf_prog_type_list *tl;
-
-	list_for_each_entry(tl, &bpf_prog_types, list_node) {
-		if (tl->type == type) {
-			prog->aux->ops = tl->ops;
-			prog->type = type;
-			return 0;
-		}
-	}
-
-	return -EINVAL;
-}
-
-void bpf_register_prog_type(struct bpf_prog_type_list *tl)
-{
-	list_add(&tl->list_node, &bpf_prog_types);
-}
-
-/* fixup insn->imm field of bpf_call instructions:
- * if (insn->imm == BPF_FUNC_map_lookup_elem)
- *      insn->imm = bpf_map_lookup_elem - __bpf_call_base;
- * else if (insn->imm == BPF_FUNC_map_update_elem)
- *      insn->imm = bpf_map_update_elem - __bpf_call_base;
- * else ...
- *
- * this function is called after eBPF program passed verification
- */
-static void fixup_bpf_calls(struct bpf_prog *prog)
-{
-	const struct bpf_func_proto *fn;
-	int i;
+	if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
+		return -EINVAL;
 
-	for (i = 0; i < prog->len; i++) {
-		struct bpf_insn *insn = &prog->insnsi[i];
-
-		if (insn->code == (BPF_JMP | BPF_CALL)) {
-			/* we reach here when program has bpf_call instructions
-			 * and it passed bpf_check(), means that
-			 * ops->get_func_proto must have been supplied, check it
-			 */
-			BUG_ON(!prog->aux->ops->get_func_proto);
-
-			if (insn->imm == BPF_FUNC_get_route_realm)
-				prog->dst_needed = 1;
-			if (insn->imm == BPF_FUNC_get_prandom_u32)
-				bpf_user_rnd_init_once();
-			if (insn->imm == BPF_FUNC_xdp_adjust_head)
-				prog->xdp_adjust_head = 1;
-			if (insn->imm == BPF_FUNC_tail_call) {
-				/* mark bpf_tail_call as different opcode
-				 * to avoid conditional branch in
-				 * interpeter for every normal call
-				 * and to prevent accidental JITing by
-				 * JIT compiler that doesn't support
-				 * bpf_tail_call yet
-				 */
-				insn->imm = 0;
-				insn->code |= BPF_X;
-				continue;
-			}
-
-			fn = prog->aux->ops->get_func_proto(insn->imm);
-			/* all functions that have prototype and verifier allowed
-			 * programs to call them, must be real in-kernel functions
-			 */
-			BUG_ON(!fn->func);
-			insn->imm = fn->func - __bpf_call_base;
-		}
-	}
+	prog->aux->ops = bpf_prog_types[type];
+	prog->type = type;
+	return 0;
 }
 
 /* drop refcnt on maps used by eBPF program and free auxilary data */
@@ -892,9 +848,6 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (err < 0)
 		goto free_used_maps;
 
-	/* fixup BPF_CALL->imm field */
-	fixup_bpf_calls(prog);
-
 	/* eBPF program is ready to be JITed */
 	prog = bpf_prog_select_runtime(prog, &err);
 	if (err < 0)
@@ -1020,6 +973,28 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 }
 #endif /* CONFIG_CGROUP_BPF */
 
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+
+static int bpf_prog_test_run(const union bpf_attr *attr,
+			     union bpf_attr __user *uattr)
+{
+	struct bpf_prog *prog;
+	int ret = -ENOTSUPP;
+
+	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->test.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->aux->ops->test_run)
+		ret = prog->aux->ops->test_run(prog, attr, uattr);
+
+	bpf_prog_put(prog);
+	return ret;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -1086,7 +1061,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_OBJ_GET:
 		err = bpf_obj_get(&attr);
 		break;
-
 #ifdef CONFIG_CGROUP_BPF
 	case BPF_PROG_ATTACH:
 		err = bpf_prog_attach(&attr);
@@ -1095,7 +1069,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_prog_detach(&attr);
 		break;
 #endif
-
+	case BPF_PROG_TEST_RUN:
+		err = bpf_prog_test_run(&attr, uattr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 796b68d00119..c2ff608c1984 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -143,6 +143,8 @@ struct bpf_verifier_stack_elem {
 #define BPF_COMPLEXITY_LIMIT_INSNS	65536
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
+#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
+
 struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
@@ -765,38 +767,56 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 	}
 }
 
-static int check_ptr_alignment(struct bpf_verifier_env *env,
-			       struct bpf_reg_state *reg, int off, int size)
+static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
+				   int off, int size)
 {
-	if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) {
-		if (off % size != 0) {
-			verbose("misaligned access off %d size %d\n",
-				off, size);
-			return -EACCES;
-		} else {
-			return 0;
-		}
-	}
-
-	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
-		/* misaligned access to packet is ok on x86,arm,arm64 */
-		return 0;
-
 	if (reg->id && size != 1) {
-		verbose("Unknown packet alignment. Only byte-sized access allowed\n");
+		verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
 		return -EACCES;
 	}
 
 	/* skb->data is NET_IP_ALIGN-ed */
-	if (reg->type == PTR_TO_PACKET &&
-	    (NET_IP_ALIGN + reg->off + off) % size != 0) {
+	if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
 		verbose("misaligned packet access off %d+%d+%d size %d\n",
 			NET_IP_ALIGN, reg->off, off, size);
 		return -EACCES;
 	}
+
 	return 0;
 }
 
+static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
+				   int size)
+{
+	if (size != 1) {
+		verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+static int check_ptr_alignment(const struct bpf_reg_state *reg,
+			       int off, int size)
+{
+	switch (reg->type) {
+	case PTR_TO_PACKET:
+		return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+		       check_pkt_ptr_alignment(reg, off, size);
+	case PTR_TO_MAP_VALUE_ADJ:
+		return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+		       check_val_ptr_alignment(reg, size);
+	default:
+		if (off % size != 0) {
+			verbose("misaligned access off %d size %d\n",
+				off, size);
+			return -EACCES;
+		}
+
+		return 0;
+	}
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -818,7 +838,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 	if (size < 0)
 		return size;
 
-	err = check_ptr_alignment(env, reg, off, size);
+	err = check_ptr_alignment(reg, off, size);
 	if (err)
 		return err;
 
@@ -1197,6 +1217,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		    func_id != BPF_FUNC_current_task_under_cgroup)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		if (func_id != BPF_FUNC_map_lookup_elem)
+			goto error;
 	default:
 		break;
 	}
@@ -1273,7 +1297,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 	}
 }
 
-static int check_call(struct bpf_verifier_env *env, int func_id)
+static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 {
 	struct bpf_verifier_state *state = &env->cur_state;
 	const struct bpf_func_proto *fn = NULL;
@@ -1357,6 +1381,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 	} else if (fn->ret_type == RET_VOID) {
 		regs[BPF_REG_0].type = NOT_INIT;
 	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
+		struct bpf_insn_aux_data *insn_aux;
+
 		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
 		regs[BPF_REG_0].max_value = regs[BPF_REG_0].min_value = 0;
 		/* remember map_ptr, so that check_map_access()
@@ -1369,6 +1395,11 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
 		regs[BPF_REG_0].id = ++env->id_gen;
+		insn_aux = &env->insn_aux_data[insn_idx];
+		if (!insn_aux->map_ptr)
+			insn_aux->map_ptr = meta.map_ptr;
+		else if (insn_aux->map_ptr != meta.map_ptr)
+			insn_aux->map_ptr = BPF_MAP_PTR_POISON;
 	} else {
 		verbose("unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
@@ -1893,6 +1924,17 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return 0;
 		} else if (opcode == BPF_ADD &&
 			   BPF_CLASS(insn->code) == BPF_ALU64 &&
+			   dst_reg->type == PTR_TO_STACK &&
+			   ((BPF_SRC(insn->code) == BPF_X &&
+			     regs[insn->src_reg].type == CONST_IMM) ||
+			    BPF_SRC(insn->code) == BPF_K)) {
+			if (BPF_SRC(insn->code) == BPF_X)
+				dst_reg->imm += regs[insn->src_reg].imm;
+			else
+				dst_reg->imm += insn->imm;
+			return 0;
+		} else if (opcode == BPF_ADD &&
+			   BPF_CLASS(insn->code) == BPF_ALU64 &&
 			   (dst_reg->type == PTR_TO_PACKET ||
 			    (BPF_SRC(insn->code) == BPF_X &&
 			     regs[insn->src_reg].type == PTR_TO_PACKET))) {
@@ -1925,6 +1967,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		 * register as unknown.
 		 */
 		if (env->allow_ptr_leaks &&
+		    BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD &&
 		    (dst_reg->type == PTR_TO_MAP_VALUE ||
 		     dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
 			dst_reg->type = PTR_TO_MAP_VALUE_ADJ;
@@ -1973,14 +2016,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
-			regs[i].range = dst_reg->off;
+			/* keep the maximum range already checked */
+			regs[i].range = max(regs[i].range, dst_reg->off);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = dst_reg->off;
+			reg->range = max(reg->range, dst_reg->off);
 	}
 }
 
@@ -2092,14 +2136,19 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
 	struct bpf_reg_state *reg = &regs[regno];
 
 	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
-		reg->type = type;
+		if (type == UNKNOWN_VALUE) {
+			__mark_reg_unknown_value(regs, regno);
+		} else if (reg->map_ptr->inner_map_meta) {
+			reg->type = CONST_PTR_TO_MAP;
+			reg->map_ptr = reg->map_ptr->inner_map_meta;
+		} else {
+			reg->type = type;
+		}
 		/* We don't need id from this point onwards anymore, thus we
 		 * should better reset it, so that state pruning has chances
 		 * to take effect.
 		 */
 		reg->id = 0;
-		if (type == UNKNOWN_VALUE)
-			__mark_reg_unknown_value(regs, regno);
 	}
 }
 
@@ -2940,7 +2989,7 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EINVAL;
 				}
 
-				err = check_call(env, insn->imm);
+				err = check_call(env, insn->imm, insn_idx);
 				if (err)
 					return err;
 
@@ -3024,16 +3073,33 @@ process_bpf_exit:
 	return 0;
 }
 
+static int check_map_prealloc(struct bpf_map *map)
+{
+	return (map->map_type != BPF_MAP_TYPE_HASH &&
+		map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
+		map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
+		!(map->map_flags & BPF_F_NO_PREALLOC);
+}
+
 static int check_map_prog_compatibility(struct bpf_map *map,
 					struct bpf_prog *prog)
 
 {
-	if (prog->type == BPF_PROG_TYPE_PERF_EVENT &&
-	    (map->map_type == BPF_MAP_TYPE_HASH ||
-	     map->map_type == BPF_MAP_TYPE_PERCPU_HASH) &&
-	    (map->map_flags & BPF_F_NO_PREALLOC)) {
-		verbose("perf_event programs can only use preallocated hash map\n");
-		return -EINVAL;
+	/* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
+	 * preallocated hash maps, since doing memory allocation
+	 * in overflow_handler can crash depending on where nmi got
+	 * triggered.
+	 */
+	if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
+		if (!check_map_prealloc(map)) {
+			verbose("perf_event programs can only use preallocated hash map\n");
+			return -EINVAL;
+		}
+		if (map->inner_map_meta &&
+		    !check_map_prealloc(map->inner_map_meta)) {
+			verbose("perf_event programs can only use preallocated inner hash map\n");
+			return -EINVAL;
+		}
 	}
 	return 0;
 }
@@ -3162,6 +3228,41 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
 			insn->src_reg = 0;
 }
 
+/* single env->prog->insni[off] instruction was replaced with the range
+ * insni[off, off + cnt).  Adjust corresponding insn_aux_data by copying
+ * [0, off) and [off, end) to new locations, so the patched range stays zero
+ */
+static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
+				u32 off, u32 cnt)
+{
+	struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
+
+	if (cnt == 1)
+		return 0;
+	new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len);
+	if (!new_data)
+		return -ENOMEM;
+	memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
+	memcpy(new_data + off + cnt - 1, old_data + off,
+	       sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
+	env->insn_aux_data = new_data;
+	vfree(old_data);
+	return 0;
+}
+
+static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
+					    const struct bpf_insn *patch, u32 len)
+{
+	struct bpf_prog *new_prog;
+
+	new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
+	if (!new_prog)
+		return NULL;
+	if (adjust_insn_aux_data(env, new_prog->len, off, len))
+		return NULL;
+	return new_prog;
+}
+
 /* convert load instructions that access fields of 'struct __sk_buff'
  * into sequence of instructions that access fields of 'struct sk_buff'
  */
@@ -3181,10 +3282,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			verbose("bpf verifier is misconfigured\n");
 			return -EINVAL;
 		} else if (cnt) {
-			new_prog = bpf_patch_insn_single(env->prog, 0,
-							 insn_buf, cnt);
+			new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
 			if (!new_prog)
 				return -ENOMEM;
+
 			env->prog = new_prog;
 			delta += cnt - 1;
 		}
@@ -3209,7 +3310,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		else
 			continue;
 
-		if (env->insn_aux_data[i].ptr_type != PTR_TO_CTX)
+		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
 			continue;
 
 		cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog);
@@ -3218,8 +3319,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			return -EINVAL;
 		}
 
-		new_prog = bpf_patch_insn_single(env->prog, i + delta, insn_buf,
-						 cnt);
+		new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
 		if (!new_prog)
 			return -ENOMEM;
 
@@ -3233,6 +3333,89 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 	return 0;
 }
 
+/* fixup insn->imm field of bpf_call instructions
+ * and inline eligible helpers as explicit sequence of BPF instructions
+ *
+ * this function is called after eBPF program passed verification
+ */
+static int fixup_bpf_calls(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	struct bpf_insn *insn = prog->insnsi;
+	const struct bpf_func_proto *fn;
+	const int insn_cnt = prog->len;
+	struct bpf_insn insn_buf[16];
+	struct bpf_prog *new_prog;
+	struct bpf_map *map_ptr;
+	int i, cnt, delta = 0;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (insn->code != (BPF_JMP | BPF_CALL))
+			continue;
+
+		if (insn->imm == BPF_FUNC_get_route_realm)
+			prog->dst_needed = 1;
+		if (insn->imm == BPF_FUNC_get_prandom_u32)
+			bpf_user_rnd_init_once();
+		if (insn->imm == BPF_FUNC_tail_call) {
+			/* If we tail call into other programs, we
+			 * cannot make any assumptions since they can
+			 * be replaced dynamically during runtime in
+			 * the program array.
+			 */
+			prog->cb_access = 1;
+
+			/* mark bpf_tail_call as different opcode to avoid
+			 * conditional branch in the interpeter for every normal
+			 * call and to prevent accidental JITing by JIT compiler
+			 * that doesn't support bpf_tail_call yet
+			 */
+			insn->imm = 0;
+			insn->code |= BPF_X;
+			continue;
+		}
+
+		if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) {
+			map_ptr = env->insn_aux_data[i + delta].map_ptr;
+			if (map_ptr == BPF_MAP_PTR_POISON ||
+			    !map_ptr->ops->map_gen_lookup)
+				goto patch_call_imm;
+
+			cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
+			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+				verbose("bpf verifier is misconfigured\n");
+				return -EINVAL;
+			}
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
+						       cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta += cnt - 1;
+
+			/* keep walking new program and skip insns we just inserted */
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
+patch_call_imm:
+		fn = prog->aux->ops->get_func_proto(insn->imm);
+		/* all functions that have prototype and verifier allowed
+		 * programs to call them, must be real in-kernel functions
+		 */
+		if (!fn->func) {
+			verbose("kernel subsystem misconfigured func %s#%d\n",
+				func_id_name(insn->imm), insn->imm);
+			return -EFAULT;
+		}
+		insn->imm = fn->func - __bpf_call_base;
+	}
+
+	return 0;
+}
+
 static void free_states(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state_list *sl, *sln;
@@ -3328,6 +3511,9 @@ skip_full_check:
 		/* program is valid, convert *(u32*)(ctx + off) accesses */
 		ret = convert_ctx_accesses(env);
 
+	if (ret == 0)
+		ret = fixup_bpf_calls(env);
+
 	if (log_level && log_len >= log_size - 1) {
 		BUG_ON(log_len >= log_size);
 		/* verifier log exceeded user supplied buffer */
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 9203bfb05603..00f4d6bf048f 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -5,6 +5,7 @@
 #include <linux/kernfs.h>
 #include <linux/workqueue.h>
 #include <linux/list.h>
+#include <linux/refcount.h>
 
 /*
  * A cgroup can be associated with multiple css_sets as different tasks may
@@ -134,7 +135,7 @@ static inline void put_css_set(struct css_set *cset)
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
 	 * rwlock
 	 */
-	if (atomic_add_unless(&cset->refcount, -1, 1))
+	if (refcount_dec_not_one(&cset->refcount))
 		return;
 
 	spin_lock_irqsave(&css_set_lock, flags);
@@ -147,7 +148,7 @@ static inline void put_css_set(struct css_set *cset)
  */
 static inline void get_css_set(struct css_set *cset)
 {
-	atomic_inc(&cset->refcount);
+	refcount_inc(&cset->refcount);
 }
 
 bool cgroup_ssid_enabled(int ssid);
@@ -163,7 +164,7 @@ int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
 
 void cgroup_free_root(struct cgroup_root *root);
 void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts);
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags);
 int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
 struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 			       struct cgroup_root *root, unsigned long magic,
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 56eba9caa632..85d75152402d 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -346,7 +346,7 @@ static int cgroup_task_count(const struct cgroup *cgrp)
 
 	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
-		count += atomic_read(&link->cset->refcount);
+		count += refcount_read(&link->cset->refcount);
 	spin_unlock_irq(&css_set_lock);
 	return count;
 }
@@ -1072,6 +1072,7 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 	struct cgroup_subsys *ss;
 	struct dentry *dentry;
 	int i, ret;
+	bool new_root = false;
 
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
@@ -1181,10 +1182,11 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		ret = -ENOMEM;
 		goto out_unlock;
 	}
+	new_root = true;
 
 	init_cgroup_root(root, &opts);
 
-	ret = cgroup_setup_root(root, opts.subsys_mask);
+	ret = cgroup_setup_root(root, opts.subsys_mask, PERCPU_REF_INIT_DEAD);
 	if (ret)
 		cgroup_free_root(root);
 
@@ -1201,6 +1203,18 @@ out_free:
 				 CGROUP_SUPER_MAGIC, ns);
 
 	/*
+	 * There's a race window after we release cgroup_mutex and before
+	 * allocating a superblock. Make sure a concurrent process won't
+	 * be able to re-use the root during this window by delaying the
+	 * initialization of root refcnt.
+	 */
+	if (new_root) {
+		mutex_lock(&cgroup_mutex);
+		percpu_ref_reinit(&root->cgrp.self.refcnt);
+		mutex_unlock(&cgroup_mutex);
+	}
+
+	/*
 	 * If @pinned_sb, we're reusing an existing root and holding an
 	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
 	 */
@@ -1286,7 +1300,7 @@ static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
 	u64 count;
 
 	rcu_read_lock();
-	count = atomic_read(&task_css_set(current)->refcount);
+	count = refcount_read(&task_css_set(current)->refcount);
 	rcu_read_unlock();
 	return count;
 }
@@ -1329,7 +1343,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 		struct task_struct *task;
 		int count = 0;
 
-		seq_printf(seq, "css_set %p\n", cset);
+		seq_printf(seq, "css_set %pK\n", cset);
 
 		list_for_each_entry(task, &cset->tasks, cg_list) {
 			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0125589c7428..c3c9a0e1b3c9 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -189,7 +189,7 @@ static u16 have_canfork_callback __read_mostly;
 
 /* cgroup namespace for init task */
 struct cgroup_namespace init_cgroup_ns = {
-	.count		= { .counter = 2, },
+	.count		= REFCOUNT_INIT(2),
 	.user_ns	= &init_user_ns,
 	.ns.ops		= &cgroupns_operations,
 	.ns.inum	= PROC_CGROUP_INIT_INO,
@@ -436,7 +436,12 @@ out_unlock:
 	return css;
 }
 
-static void cgroup_get(struct cgroup *cgrp)
+static void __maybe_unused cgroup_get(struct cgroup *cgrp)
+{
+	css_get(&cgrp->self);
+}
+
+static void cgroup_get_live(struct cgroup *cgrp)
 {
 	WARN_ON_ONCE(cgroup_is_dead(cgrp));
 	css_get(&cgrp->self);
@@ -554,7 +559,7 @@ EXPORT_SYMBOL_GPL(of_css);
  * haven't been created.
  */
 struct css_set init_css_set = {
-	.refcount		= ATOMIC_INIT(1),
+	.refcount		= REFCOUNT_INIT(1),
 	.tasks			= LIST_HEAD_INIT(init_css_set.tasks),
 	.mg_tasks		= LIST_HEAD_INIT(init_css_set.mg_tasks),
 	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
@@ -724,7 +729,7 @@ void put_css_set_locked(struct css_set *cset)
 
 	lockdep_assert_held(&css_set_lock);
 
-	if (!atomic_dec_and_test(&cset->refcount))
+	if (!refcount_dec_and_test(&cset->refcount))
 		return;
 
 	/* This css_set is dead. unlink it and release cgroup and css refs */
@@ -932,7 +937,7 @@ static void link_css_set(struct list_head *tmp_links, struct css_set *cset,
 	list_add_tail(&link->cgrp_link, &cset->cgrp_links);
 
 	if (cgroup_parent(cgrp))
-		cgroup_get(cgrp);
+		cgroup_get_live(cgrp);
 }
 
 /**
@@ -977,7 +982,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 		return NULL;
 	}
 
-	atomic_set(&cset->refcount, 1);
+	refcount_set(&cset->refcount, 1);
 	INIT_LIST_HEAD(&cset->tasks);
 	INIT_LIST_HEAD(&cset->mg_tasks);
 	INIT_LIST_HEAD(&cset->task_iters);
@@ -1640,7 +1645,7 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
@@ -1656,8 +1661,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	root_cgrp->id = ret;
 	root_cgrp->ancestor_ids[0] = ret;
 
-	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
-			      GFP_KERNEL);
+	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
+			      ref_flags, GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -1802,7 +1807,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			return ERR_PTR(-EINVAL);
 		}
 		cgrp_dfl_visible = true;
-		cgroup_get(&cgrp_dfl_root.cgrp);
+		cgroup_get_live(&cgrp_dfl_root.cgrp);
 
 		dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root,
 					 CGROUP2_SUPER_MAGIC, ns);
@@ -2425,11 +2430,12 @@ ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 		tsk = tsk->group_leader;
 
 	/*
-	 * Workqueue threads may acquire PF_NO_SETAFFINITY and become
-	 * trapped in a cpuset, or RT worker may be born in a cgroup
-	 * with no rt_runtime allocated.  Just say no.
+	 * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+	 * If userland migrates such a kthread to a non-root cgroup, it can
+	 * become trapped in a cpuset, or RT kthread may be born in a
+	 * cgroup with no rt_runtime allocated.  Just say no.
 	 */
-	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+	if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		goto out_unlock_rcu;
 	}
@@ -2575,7 +2581,7 @@ restart:
 			if (!css || !percpu_ref_is_dying(&css->refcnt))
 				continue;
 
-			cgroup_get(dsct);
+			cgroup_get_live(dsct);
 			prepare_to_wait(&dsct->offline_waitq, &wait,
 					TASK_UNINTERRUPTIBLE);
 
@@ -2669,7 +2675,7 @@ static bool css_visible(struct cgroup_subsys_state *css)
  *
  * Returns 0 on success, -errno on failure.  On failure, csses which have
  * been processed already aren't cleaned up.  The caller is responsible for
- * cleaning up with cgroup_apply_control_disble().
+ * cleaning up with cgroup_apply_control_disable().
  */
 static int cgroup_apply_control_enable(struct cgroup *cgrp)
 {
@@ -3946,7 +3952,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 {
 	lockdep_assert_held(&cgroup_mutex);
 
-	cgroup_get(cgrp);
+	cgroup_get_live(cgrp);
 
 	memset(css, 0, sizeof(*css));
 	css->cgroup = cgrp;
@@ -4122,7 +4128,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	/* allocation complete, commit to creation */
 	list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
 	atomic_inc(&root->nr_cgrps);
-	cgroup_get(parent);
+	cgroup_get_live(parent);
 
 	/*
 	 * @cgrp is now fully operational.  If something fails after this
@@ -4512,7 +4518,7 @@ int __init cgroup_init(void)
 	hash_add(css_set_table, &init_css_set.hlist,
 		 css_set_hash(init_css_set.subsys));
 
-	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
+	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));
 
 	mutex_unlock(&cgroup_mutex);
 
@@ -4946,7 +4952,7 @@ struct cgroup *cgroup_get_from_path(const char *path)
 	if (kn) {
 		if (kernfs_type(kn) == KERNFS_DIR) {
 			cgrp = kn->priv;
-			cgroup_get(cgrp);
+			cgroup_get_live(cgrp);
 		} else {
 			cgrp = ERR_PTR(-ENOTDIR);
 		}
@@ -5026,6 +5032,11 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 
 	/* Socket clone path */
 	if (skcd->val) {
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
 		cgroup_get(sock_cgroup_ptr(skcd));
 		return;
 	}
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 0f41292be0fb..f6501f4f6040 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2121,10 +2121,8 @@ int __init cpuset_init(void)
 {
 	int err = 0;
 
-	if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL))
-		BUG();
-	if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
-		BUG();
+	BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
@@ -2139,8 +2137,7 @@ int __init cpuset_init(void)
 	if (err < 0)
 		return err;
 
-	if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL))
-		BUG();
+	BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL));
 
 	return 0;
 }
@@ -2354,7 +2351,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 		rebuild_sched_domains();
 }
 
-void cpuset_update_active_cpus(bool cpu_online)
+void cpuset_update_active_cpus(void)
 {
 	/*
 	 * We're inside cpu hotplug critical region which usually nests
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index 96d38dab6fb2..66129eb4371d 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -31,7 +31,7 @@ static struct cgroup_namespace *alloc_cgroup_ns(void)
 		kfree(new_ns);
 		return ERR_PTR(ret);
 	}
-	atomic_set(&new_ns->count, 1);
+	refcount_set(&new_ns->count, 1);
 	new_ns->ns.ops = &cgroupns_operations;
 	return new_ns;
 }
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index e756dae49300..2237201d66d5 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -229,7 +229,7 @@ static int pids_can_fork(struct task_struct *task)
 		/* Only log the first time events_limit is incremented. */
 		if (atomic64_inc_return(&pids->events_limit) == 1) {
 			pr_info("cgroup: fork rejected by pids controller in ");
-			pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id));
+			pr_cont_cgroup_path(css->cgroup);
 			pr_cont("\n");
 		}
 		cgroup_file_notify(&pids->events_file);
diff --git a/kernel/compat.c b/kernel/compat.c
index 19aec5d98108..933bcb31ae10 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -108,8 +108,8 @@ COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv,
 COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv,
 		       struct timezone __user *, tz)
 {
+	struct timespec64 new_ts;
 	struct timeval user_tv;
-	struct timespec	new_ts;
 	struct timezone new_tz;
 
 	if (tv) {
@@ -123,7 +123,7 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv,
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
+	return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
 static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
@@ -240,18 +240,20 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 		       struct compat_timespec __user *, rmtp)
 {
 	struct timespec tu, rmt;
+	struct timespec64 tu64;
 	mm_segment_t oldfs;
 	long ret;
 
 	if (compat_get_timespec(&tu, rqtp))
 		return -EFAULT;
 
-	if (!timespec_valid(&tu))
+	tu64 = timespec_to_timespec64(tu);
+	if (!timespec64_valid(&tu64))
 		return -EINVAL;
 
 	oldfs = get_fs();
 	set_fs(KERNEL_DS);
-	ret = hrtimer_nanosleep(&tu,
+	ret = hrtimer_nanosleep(&tu64,
 				rmtp ? (struct timespec __user *)&rmt : NULL,
 				HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 	set_fs(oldfs);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f7c063239fa5..9ae6fbe5b5cf 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1125,6 +1125,8 @@ core_initcall(cpu_hotplug_pm_sync_init);
 
 #endif /* CONFIG_PM_SLEEP_SMP */
 
+int __boot_cpu_id;
+
 #endif /* CONFIG_SMP */
 
 /* Boot processor state steps */
@@ -1335,26 +1337,21 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
 	struct cpuhp_step *sp;
 	int ret = 0;
 
-	mutex_lock(&cpuhp_state_mutex);
-
 	if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) {
 		ret = cpuhp_reserve_state(state);
 		if (ret < 0)
-			goto out;
+			return ret;
 		state = ret;
 	}
 	sp = cpuhp_get_step(state);
-	if (name && sp->name) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (name && sp->name)
+		return -EBUSY;
+
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
-out:
-	mutex_unlock(&cpuhp_state_mutex);
 	return ret;
 }
 
@@ -1428,6 +1425,7 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 		return -EINVAL;
 
 	get_online_cpus();
+	mutex_lock(&cpuhp_state_mutex);
 
 	if (!invoke || !sp->startup.multi)
 		goto add_node;
@@ -1447,16 +1445,14 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 		if (ret) {
 			if (sp->teardown.multi)
 				cpuhp_rollback_install(cpu, state, node);
-			goto err;
+			goto unlock;
 		}
 	}
 add_node:
 	ret = 0;
-	mutex_lock(&cpuhp_state_mutex);
 	hlist_add_head(node, &sp->list);
+unlock:
 	mutex_unlock(&cpuhp_state_mutex);
-
-err:
 	put_online_cpus();
 	return ret;
 }
@@ -1491,6 +1487,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		return -EINVAL;
 
 	get_online_cpus();
+	mutex_lock(&cpuhp_state_mutex);
 
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
 				    multi_instance);
@@ -1524,6 +1521,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		}
 	}
 out:
+	mutex_unlock(&cpuhp_state_mutex);
 	put_online_cpus();
 	/*
 	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
@@ -1547,6 +1545,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 		return -EINVAL;
 
 	get_online_cpus();
+	mutex_lock(&cpuhp_state_mutex);
+
 	if (!invoke || !cpuhp_get_teardown_cb(state))
 		goto remove;
 	/*
@@ -1563,7 +1563,6 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 	}
 
 remove:
-	mutex_lock(&cpuhp_state_mutex);
 	hlist_del(node);
 	mutex_unlock(&cpuhp_state_mutex);
 	put_online_cpus();
@@ -1571,6 +1570,7 @@ remove:
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
+
 /**
  * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
  * @state:	The state to remove
@@ -1589,6 +1589,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 
 	get_online_cpus();
 
+	mutex_lock(&cpuhp_state_mutex);
 	if (sp->multi_instance) {
 		WARN(!hlist_empty(&sp->list),
 		     "Error: Removing state %d which has instances left.\n",
@@ -1613,6 +1614,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 	}
 remove:
 	cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
+	mutex_unlock(&cpuhp_state_mutex);
 	put_online_cpus();
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);
@@ -1815,6 +1817,10 @@ void __init boot_cpu_init(void)
 	set_cpu_active(cpu, true);
 	set_cpu_present(cpu, true);
 	set_cpu_possible(cpu, true);
+
+#ifdef CONFIG_SMP
+	__boot_cpu_id = cpu;
+#endif
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6f41548f2e32..6e75a5c9412d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -48,6 +48,8 @@
 #include <linux/parser.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/mm.h>
+#include <linux/proc_ns.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -379,6 +381,7 @@ static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
+static atomic_t nr_namespaces_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
@@ -998,7 +1001,7 @@ list_update_cgroup_event(struct perf_event *event,
  */
 #define PERF_CPU_HRTIMER (1000 / HZ)
 /*
- * function must be called with interrupts disbled
+ * function must be called with interrupts disabled
  */
 static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
@@ -3991,6 +3994,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_mmap_events);
 	if (event->attr.comm)
 		atomic_dec(&nr_comm_events);
+	if (event->attr.namespaces)
+		atomic_dec(&nr_namespaces_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
@@ -4256,7 +4261,7 @@ int perf_event_release_kernel(struct perf_event *event)
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * Mark this even as STATE_DEAD, there is no external reference to it
+	 * Mark this event as STATE_DEAD, there is no external reference to it
 	 * anymore.
 	 *
 	 * Anybody acquiring event->child_mutex after the below loop _must_
@@ -6491,6 +6496,7 @@ static void perf_event_task(struct task_struct *task,
 void perf_event_fork(struct task_struct *task)
 {
 	perf_event_task(task, NULL, 1);
+	perf_event_namespaces(task);
 }
 
 /*
@@ -6593,6 +6599,132 @@ void perf_event_comm(struct task_struct *task, bool exec)
 }
 
 /*
+ * namespaces tracking
+ */
+
+struct perf_namespaces_event {
+	struct task_struct		*task;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+		u64				nr_namespaces;
+		struct perf_ns_link_info	link_info[NR_NAMESPACES];
+	} event_id;
+};
+
+static int perf_event_namespaces_match(struct perf_event *event)
+{
+	return event->attr.namespaces;
+}
+
+static void perf_event_namespaces_output(struct perf_event *event,
+					 void *data)
+{
+	struct perf_namespaces_event *namespaces_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_namespaces_match(event))
+		return;
+
+	perf_event_header__init_id(&namespaces_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				namespaces_event->event_id.header.size);
+	if (ret)
+		return;
+
+	namespaces_event->event_id.pid = perf_event_pid(event,
+							namespaces_event->task);
+	namespaces_event->event_id.tid = perf_event_tid(event,
+							namespaces_event->task);
+
+	perf_output_put(&handle, namespaces_event->event_id);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
+				   struct task_struct *task,
+				   const struct proc_ns_operations *ns_ops)
+{
+	struct path ns_path;
+	struct inode *ns_inode;
+	void *error;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (!error) {
+		ns_inode = ns_path.dentry->d_inode;
+		ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev);
+		ns_link_info->ino = ns_inode->i_ino;
+	}
+}
+
+void perf_event_namespaces(struct task_struct *task)
+{
+	struct perf_namespaces_event namespaces_event;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!atomic_read(&nr_namespaces_events))
+		return;
+
+	namespaces_event = (struct perf_namespaces_event){
+		.task	= task,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_NAMESPACES,
+				.misc = 0,
+				.size = sizeof(namespaces_event.event_id),
+			},
+			/* .pid */
+			/* .tid */
+			.nr_namespaces = NR_NAMESPACES,
+			/* .link_info[NR_NAMESPACES] */
+		},
+	};
+
+	ns_link_info = namespaces_event.event_id.link_info;
+
+	perf_fill_ns_link_info(&ns_link_info[MNT_NS_INDEX],
+			       task, &mntns_operations);
+
+#ifdef CONFIG_USER_NS
+	perf_fill_ns_link_info(&ns_link_info[USER_NS_INDEX],
+			       task, &userns_operations);
+#endif
+#ifdef CONFIG_NET_NS
+	perf_fill_ns_link_info(&ns_link_info[NET_NS_INDEX],
+			       task, &netns_operations);
+#endif
+#ifdef CONFIG_UTS_NS
+	perf_fill_ns_link_info(&ns_link_info[UTS_NS_INDEX],
+			       task, &utsns_operations);
+#endif
+#ifdef CONFIG_IPC_NS
+	perf_fill_ns_link_info(&ns_link_info[IPC_NS_INDEX],
+			       task, &ipcns_operations);
+#endif
+#ifdef CONFIG_PID_NS
+	perf_fill_ns_link_info(&ns_link_info[PID_NS_INDEX],
+			       task, &pidns_operations);
+#endif
+#ifdef CONFIG_CGROUPS
+	perf_fill_ns_link_info(&ns_link_info[CGROUP_NS_INDEX],
+			       task, &cgroupns_operations);
+#endif
+
+	perf_iterate_sb(perf_event_namespaces_output,
+			&namespaces_event,
+			NULL);
+}
+
+/*
  * mmap tracking
  */
 
@@ -9146,6 +9278,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_mmap_events);
 	if (event->attr.comm)
 		atomic_inc(&nr_comm_events);
+	if (event->attr.namespaces)
+		atomic_inc(&nr_namespaces_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
 	if (event->attr.freq)
@@ -9691,6 +9825,11 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EACCES;
 	}
 
+	if (attr.namespaces) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+	}
+
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;
@@ -10417,21 +10556,22 @@ void perf_event_free_task(struct task_struct *task)
 			continue;
 
 		mutex_lock(&ctx->mutex);
-again:
-		list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
-				group_entry)
-			perf_free_event(event, ctx);
+		raw_spin_lock_irq(&ctx->lock);
+		/*
+		 * Destroy the task <-> ctx relation and mark the context dead.
+		 *
+		 * This is important because even though the task hasn't been
+		 * exposed yet the context has been (through child_list).
+		 */
+		RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], NULL);
+		WRITE_ONCE(ctx->task, TASK_TOMBSTONE);
+		put_task_struct(task); /* cannot be last */
+		raw_spin_unlock_irq(&ctx->lock);
 
-		list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
-				group_entry)
+		list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry)
 			perf_free_event(event, ctx);
 
-		if (!list_empty(&ctx->pinned_groups) ||
-				!list_empty(&ctx->flexible_groups))
-			goto again;
-
 		mutex_unlock(&ctx->mutex);
-
 		put_ctx(ctx);
 	}
 }
@@ -10469,7 +10609,12 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 }
 
 /*
- * inherit a event from parent task to child task:
+ * Inherit a event from parent task to child task.
+ *
+ * Returns:
+ *  - valid pointer on success
+ *  - NULL for orphaned events
+ *  - IS_ERR() on error
  */
 static struct perf_event *
 inherit_event(struct perf_event *parent_event,
@@ -10563,6 +10708,16 @@ inherit_event(struct perf_event *parent_event,
 	return child_event;
 }
 
+/*
+ * Inherits an event group.
+ *
+ * This will quietly suppress orphaned events; !inherit_event() is not an error.
+ * This matches with perf_event_release_kernel() removing all child events.
+ *
+ * Returns:
+ *  - 0 on success
+ *  - <0 on error
+ */
 static int inherit_group(struct perf_event *parent_event,
 	      struct task_struct *parent,
 	      struct perf_event_context *parent_ctx,
@@ -10577,6 +10732,11 @@ static int inherit_group(struct perf_event *parent_event,
 				 child, NULL, child_ctx);
 	if (IS_ERR(leader))
 		return PTR_ERR(leader);
+	/*
+	 * @leader can be NULL here because of is_orphaned_event(). In this
+	 * case inherit_event() will create individual events, similar to what
+	 * perf_group_detach() would do anyway.
+	 */
 	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
 		child_ctr = inherit_event(sub, parent, parent_ctx,
 					    child, leader, child_ctx);
@@ -10586,6 +10746,17 @@ static int inherit_group(struct perf_event *parent_event,
 	return 0;
 }
 
+/*
+ * Creates the child task context and tries to inherit the event-group.
+ *
+ * Clears @inherited_all on !attr.inherited or error. Note that we'll leave
+ * inherited_all set when we 'fail' to inherit an orphaned event; this is
+ * consistent with perf_event_release_kernel() removing all child events.
+ *
+ * Returns:
+ *  - 0 on success
+ *  - <0 on error
+ */
 static int
 inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		   struct perf_event_context *parent_ctx,
@@ -10608,7 +10779,6 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		 * First allocate and initialize a context for the
 		 * child.
 		 */
-
 		child_ctx = alloc_perf_context(parent_ctx->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;
@@ -10670,7 +10840,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	/*
@@ -10686,7 +10856,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -10714,6 +10884,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 	}
 
 	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 257fa460b846..2831480c63a2 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -297,6 +297,19 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->paused = 1;
 }
 
+void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)
+{
+	/*
+	 * OVERWRITE is determined by perf_aux_output_end() and can't
+	 * be passed in directly.
+	 */
+	if (WARN_ON_ONCE(flags & PERF_AUX_FLAG_OVERWRITE))
+		return;
+
+	handle->aux_flags |= flags;
+}
+EXPORT_SYMBOL_GPL(perf_aux_output_flag);
+
 /*
  * This is called before hardware starts writing to the AUX area to
  * obtain an output handle and make sure there's room in the buffer.
@@ -360,6 +373,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	handle->event = event;
 	handle->head = aux_head;
 	handle->size = 0;
+	handle->aux_flags = 0;
 
 	/*
 	 * In overwrite mode, AUX data stores do not depend on aux_tail,
@@ -408,34 +422,32 @@ err:
  * of the AUX buffer management code is that after pmu::stop(), the AUX
  * transaction must be stopped and therefore drop the AUX reference count.
  */
-void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
-			 bool truncated)
+void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 {
+	bool wakeup = !!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED);
 	struct ring_buffer *rb = handle->rb;
-	bool wakeup = truncated;
 	unsigned long aux_head;
-	u64 flags = 0;
-
-	if (truncated)
-		flags |= PERF_AUX_FLAG_TRUNCATED;
 
 	/* in overwrite mode, driver provides aux_head via handle */
 	if (rb->aux_overwrite) {
-		flags |= PERF_AUX_FLAG_OVERWRITE;
+		handle->aux_flags |= PERF_AUX_FLAG_OVERWRITE;
 
 		aux_head = handle->head;
 		local_set(&rb->aux_head, aux_head);
 	} else {
+		handle->aux_flags &= ~PERF_AUX_FLAG_OVERWRITE;
+
 		aux_head = local_read(&rb->aux_head);
 		local_add(size, &rb->aux_head);
 	}
 
-	if (size || flags) {
+	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size, flags);
+		perf_event_aux_event(handle->event, aux_head, size,
+		                     handle->aux_flags);
 	}
 
 	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
@@ -446,7 +458,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 	}
 
 	if (wakeup) {
-		if (truncated)
+		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
 			handle->event->pending_disable = 1;
 		perf_output_wakeup(handle);
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index e126ebf2400c..516acdb0e0ec 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -554,7 +554,6 @@ static void exit_mm(void)
 	enter_lazy_tlb(mm, current);
 	task_unlock(current);
 	mm_update_next_owner(mm);
-	userfaultfd_exit(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
 		exit_oom_victim();
diff --git a/kernel/fork.c b/kernel/fork.c
index 942cbcd07c18..56d85fd81411 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1439,6 +1439,7 @@ static void rt_mutex_init_task(struct task_struct *p)
 #ifdef CONFIG_RT_MUTEXES
 	p->pi_waiters = RB_ROOT;
 	p->pi_waiters_leftmost = NULL;
+	p->pi_top_task = NULL;
 	p->pi_blocked_on = NULL;
 #endif
 }
@@ -2355,6 +2356,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 		}
 	}
 
+	perf_event_namespaces(current);
+
 bad_unshare_cleanup_cred:
 	if (new_cred)
 		put_cred(new_cred);
diff --git a/kernel/futex.c b/kernel/futex.c
index 229a744b1781..357348a6cf6b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -802,7 +802,7 @@ static int refill_pi_state_cache(void)
 	return 0;
 }
 
-static struct futex_pi_state * alloc_pi_state(void)
+static struct futex_pi_state *alloc_pi_state(void)
 {
 	struct futex_pi_state *pi_state = current->pi_state_cache;
 
@@ -812,6 +812,11 @@ static struct futex_pi_state * alloc_pi_state(void)
 	return pi_state;
 }
 
+static void get_pi_state(struct futex_pi_state *pi_state)
+{
+	WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
+}
+
 /*
  * Drops a reference to the pi_state object and frees or caches it
  * when the last reference is gone.
@@ -856,7 +861,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
  * Look up the task based on what TID userspace gave us.
  * We dont trust it.
  */
-static struct task_struct * futex_find_get_task(pid_t pid)
+static struct task_struct *futex_find_get_task(pid_t pid)
 {
 	struct task_struct *p;
 
@@ -916,10 +921,12 @@ void exit_pi_state_list(struct task_struct *curr)
 		pi_state->owner = NULL;
 		raw_spin_unlock_irq(&curr->pi_lock);
 
-		rt_mutex_unlock(&pi_state->pi_mutex);
-
+		get_pi_state(pi_state);
 		spin_unlock(&hb->lock);
 
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
+		put_pi_state(pi_state);
+
 		raw_spin_lock_irq(&curr->pi_lock);
 	}
 	raw_spin_unlock_irq(&curr->pi_lock);
@@ -973,6 +980,39 @@ void exit_pi_state_list(struct task_struct *curr)
  *
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
+ *
+ *
+ * Serialization and lifetime rules:
+ *
+ * hb->lock:
+ *
+ *	hb -> futex_q, relation
+ *	futex_q -> pi_state, relation
+ *
+ *	(cannot be raw because hb can contain arbitrary amount
+ *	 of futex_q's)
+ *
+ * pi_mutex->wait_lock:
+ *
+ *	{uval, pi_state}
+ *
+ *	(and pi_mutex 'obviously')
+ *
+ * p->pi_lock:
+ *
+ *	p->pi_state_list -> pi_state->list, relation
+ *
+ * pi_state->refcount:
+ *
+ *	pi_state lifetime
+ *
+ *
+ * Lock order:
+ *
+ *   hb->lock
+ *     pi_mutex->wait_lock
+ *       p->pi_lock
+ *
  */
 
 /*
@@ -980,10 +1020,13 @@ void exit_pi_state_list(struct task_struct *curr)
  * the pi_state against the user space value. If correct, attach to
  * it.
  */
-static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+			      struct futex_pi_state *pi_state,
 			      struct futex_pi_state **ps)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
+	u32 uval2;
+	int ret;
 
 	/*
 	 * Userspace might have messed up non-PI and PI futexes [3]
@@ -991,9 +1034,39 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 	if (unlikely(!pi_state))
 		return -EINVAL;
 
+	/*
+	 * We get here with hb->lock held, and having found a
+	 * futex_top_waiter(). This means that futex_lock_pi() of said futex_q
+	 * has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
+	 * which in turn means that futex_lock_pi() still has a reference on
+	 * our pi_state.
+	 *
+	 * The waiter holding a reference on @pi_state also protects against
+	 * the unlocked put_pi_state() in futex_unlock_pi(), futex_lock_pi()
+	 * and futex_wait_requeue_pi() as it cannot go to 0 and consequently
+	 * free pi_state before we can take a reference ourselves.
+	 */
 	WARN_ON(!atomic_read(&pi_state->refcount));
 
 	/*
+	 * Now that we have a pi_state, we can acquire wait_lock
+	 * and do the state validation.
+	 */
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	/*
+	 * Since {uval, pi_state} is serialized by wait_lock, and our current
+	 * uval was read without holding it, it can have changed. Verify it
+	 * still is what we expect it to be, otherwise retry the entire
+	 * operation.
+	 */
+	if (get_futex_value_locked(&uval2, uaddr))
+		goto out_efault;
+
+	if (uval != uval2)
+		goto out_eagain;
+
+	/*
 	 * Handle the owner died case:
 	 */
 	if (uval & FUTEX_OWNER_DIED) {
@@ -1008,11 +1081,11 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 			 * is not 0. Inconsistent state. [5]
 			 */
 			if (pid)
-				return -EINVAL;
+				goto out_einval;
 			/*
 			 * Take a ref on the state and return success. [4]
 			 */
-			goto out_state;
+			goto out_attach;
 		}
 
 		/*
@@ -1024,14 +1097,14 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 		 * Take a ref on the state and return success. [6]
 		 */
 		if (!pid)
-			goto out_state;
+			goto out_attach;
 	} else {
 		/*
 		 * If the owner died bit is not set, then the pi_state
 		 * must have an owner. [7]
 		 */
 		if (!pi_state->owner)
-			return -EINVAL;
+			goto out_einval;
 	}
 
 	/*
@@ -1040,11 +1113,29 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 	 * user space TID. [9/10]
 	 */
 	if (pid != task_pid_vnr(pi_state->owner))
-		return -EINVAL;
-out_state:
-	atomic_inc(&pi_state->refcount);
+		goto out_einval;
+
+out_attach:
+	get_pi_state(pi_state);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	*ps = pi_state;
 	return 0;
+
+out_einval:
+	ret = -EINVAL;
+	goto out_error;
+
+out_eagain:
+	ret = -EAGAIN;
+	goto out_error;
+
+out_efault:
+	ret = -EFAULT;
+	goto out_error;
+
+out_error:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	return ret;
 }
 
 /*
@@ -1095,6 +1186,9 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 
 	/*
 	 * No existing pi state. First waiter. [2]
+	 *
+	 * This creates pi_state, we have hb->lock held, this means nothing can
+	 * observe this state, wait_lock is irrelevant.
 	 */
 	pi_state = alloc_pi_state();
 
@@ -1119,17 +1213,18 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 	return 0;
 }
 
-static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+static int lookup_pi_state(u32 __user *uaddr, u32 uval,
+			   struct futex_hash_bucket *hb,
 			   union futex_key *key, struct futex_pi_state **ps)
 {
-	struct futex_q *match = futex_top_waiter(hb, key);
+	struct futex_q *top_waiter = futex_top_waiter(hb, key);
 
 	/*
 	 * If there is a waiter on that futex, validate it and
 	 * attach to the pi_state when the validation succeeds.
 	 */
-	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+	if (top_waiter)
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
 
 	/*
 	 * We are the first waiter - try to look up the owner based on
@@ -1148,7 +1243,7 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 
-	/*If user space value changed, let the caller retry */
+	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
 }
 
@@ -1176,7 +1271,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct task_struct *task, int set_waiters)
 {
 	u32 uval, newval, vpid = task_pid_vnr(task);
-	struct futex_q *match;
+	struct futex_q *top_waiter;
 	int ret;
 
 	/*
@@ -1202,9 +1297,9 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 * Lookup existing state first. If it exists, try to attach to
 	 * its pi_state.
 	 */
-	match = futex_top_waiter(hb, key);
-	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+	top_waiter = futex_top_waiter(hb, key);
+	if (top_waiter)
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
 
 	/*
 	 * No waiter and user TID is 0. We are here because the
@@ -1285,50 +1380,44 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 	wake_q_add(wake_q, p);
 	__unqueue_futex(q);
 	/*
-	 * The waiting task can free the futex_q as soon as
-	 * q->lock_ptr = NULL is written, without taking any locks. A
-	 * memory barrier is required here to prevent the following
-	 * store to lock_ptr from getting ahead of the plist_del.
+	 * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
+	 * is written, without taking any locks. This is possible in the event
+	 * of a spurious wakeup, for example. A memory barrier is required here
+	 * to prevent the following store to lock_ptr from getting ahead of the
+	 * plist_del in __unqueue_futex().
 	 */
-	smp_wmb();
-	q->lock_ptr = NULL;
+	smp_store_release(&q->lock_ptr, NULL);
 }
 
-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
-			 struct futex_hash_bucket *hb)
+/*
+ * Caller must hold a reference on @pi_state.
+ */
+static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
 {
-	struct task_struct *new_owner;
-	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
+	struct task_struct *new_owner;
+	bool postunlock = false;
 	DEFINE_WAKE_Q(wake_q);
-	bool deboost;
 	int ret = 0;
 
-	if (!pi_state)
-		return -EINVAL;
-
-	/*
-	 * If current does not own the pi_state then the futex is
-	 * inconsistent and user space fiddled with the futex value.
-	 */
-	if (pi_state->owner != current)
-		return -EINVAL;
-
-	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
+	if (WARN_ON_ONCE(!new_owner)) {
+		/*
+		 * As per the comment in futex_unlock_pi() this should not happen.
+		 *
+		 * When this happens, give up our locks and try again, giving
+		 * the futex_lock_pi() instance time to complete, either by
+		 * waiting on the rtmutex or removing itself from the futex
+		 * queue.
+		 */
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
 
 	/*
-	 * It is possible that the next waiter (the one that brought
-	 * this owner to the kernel) timed out and is no longer
-	 * waiting on the lock.
-	 */
-	if (!new_owner)
-		new_owner = this->task;
-
-	/*
-	 * We pass it to the next owner. The WAITERS bit is always
-	 * kept enabled while there is PI state around. We cleanup the
-	 * owner died bit, because we are the owner.
+	 * We pass it to the next owner. The WAITERS bit is always kept
+	 * enabled while there is PI state around. We cleanup the owner
+	 * died bit, because we are the owner.
 	 */
 	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
@@ -1337,6 +1426,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 
 	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
+
 	} else if (curval != uval) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
@@ -1349,10 +1439,14 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 		else
 			ret = -EINVAL;
 	}
-	if (ret) {
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-		return ret;
-	}
+
+	if (ret)
+		goto out_unlock;
+
+	/*
+	 * This is a point of no return; once we modify the uval there is no
+	 * going back and subsequent operations must not fail.
+	 */
 
 	raw_spin_lock(&pi_state->owner->pi_lock);
 	WARN_ON(list_empty(&pi_state->list));
@@ -1365,22 +1459,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	pi_state->owner = new_owner;
 	raw_spin_unlock(&new_owner->pi_lock);
 
-	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
 
-	deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+out_unlock:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
-	/*
-	 * First unlock HB so the waiter does not spin on it once he got woken
-	 * up. Second wake up the waiter before the priority is adjusted. If we
-	 * deboost first (and lose our higher priority), then the task might get
-	 * scheduled away before the wake up can take place.
-	 */
-	spin_unlock(&hb->lock);
-	wake_up_q(&wake_q);
-	if (deboost)
-		rt_mutex_adjust_prio(current);
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -1826,7 +1913,7 @@ retry_private:
 			 * If that call succeeds then we have pi_state and an
 			 * initial refcount on it.
 			 */
-			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
+			ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
@@ -1909,7 +1996,7 @@ retry_private:
 			 * refcount on the pi_state and store the pointer in
 			 * the futex_q object of the waiter.
 			 */
-			atomic_inc(&pi_state->refcount);
+			get_pi_state(pi_state);
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
@@ -2009,20 +2096,7 @@ queue_unlock(struct futex_hash_bucket *hb)
 	hb_waiters_dec(hb);
 }
 
-/**
- * queue_me() - Enqueue the futex_q on the futex_hash_bucket
- * @q:	The futex_q to enqueue
- * @hb:	The destination hash bucket
- *
- * The hb->lock must be held by the caller, and is released here. A call to
- * queue_me() is typically paired with exactly one call to unqueue_me().  The
- * exceptions involve the PI related operations, which may use unqueue_me_pi()
- * or nothing if the unqueue is done as part of the wake process and the unqueue
- * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
- * an example).
- */
-static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
-	__releases(&hb->lock)
+static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
 	int prio;
 
@@ -2039,6 +2113,24 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 	plist_node_init(&q->list, prio);
 	plist_add(&q->list, &hb->chain);
 	q->task = current;
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q:	The futex_q to enqueue
+ * @hb:	The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me().  The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
+static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
+{
+	__queue_me(q, hb);
 	spin_unlock(&hb->lock);
 }
 
@@ -2125,10 +2217,13 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
-	struct task_struct *oldowner = pi_state->owner;
 	u32 uval, uninitialized_var(curval), newval;
+	struct task_struct *oldowner;
 	int ret;
 
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	oldowner = pi_state->owner;
 	/* Owner died? */
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
@@ -2136,7 +2231,8 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	/*
 	 * We are here either because we stole the rtmutex from the
 	 * previous highest priority waiter or we are the highest priority
-	 * waiter but failed to get the rtmutex the first time.
+	 * waiter but have failed to get the rtmutex the first time.
+	 *
 	 * We have to replace the newowner TID in the user space variable.
 	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
@@ -2144,17 +2240,16 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	 * because we can fault here. Imagine swapped out pages or a fork
 	 * that marked all the anonymous memory readonly for cow.
 	 *
-	 * Modifying pi_state _before_ the user space value would
-	 * leave the pi_state in an inconsistent state when we fault
-	 * here, because we need to drop the hash bucket lock to
-	 * handle the fault. This might be observed in the PID check
-	 * in lookup_pi_state.
+	 * Modifying pi_state _before_ the user space value would leave the
+	 * pi_state in an inconsistent state when we fault here, because we
+	 * need to drop the locks to handle the fault. This might be observed
+	 * in the PID check in lookup_pi_state.
 	 */
 retry:
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;
 
-	while (1) {
+	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
 		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
@@ -2169,47 +2264,60 @@ retry:
 	 * itself.
 	 */
 	if (pi_state->owner != NULL) {
-		raw_spin_lock_irq(&pi_state->owner->pi_lock);
+		raw_spin_lock(&pi_state->owner->pi_lock);
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
-		raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+		raw_spin_unlock(&pi_state->owner->pi_lock);
 	}
 
 	pi_state->owner = newowner;
 
-	raw_spin_lock_irq(&newowner->pi_lock);
+	raw_spin_lock(&newowner->pi_lock);
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &newowner->pi_state_list);
-	raw_spin_unlock_irq(&newowner->pi_lock);
+	raw_spin_unlock(&newowner->pi_lock);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+
 	return 0;
 
 	/*
-	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the highest priority
-	 * waiter itself or the task which stole the rtmutex) the
-	 * chance to try the fixup of the pi_state. So once we are
-	 * back from handling the fault we need to check the pi_state
-	 * after reacquiring the hash bucket lock and before trying to
-	 * do another fixup. When the fixup has been done already we
-	 * simply return.
+	 * To handle the page fault we need to drop the locks here. That gives
+	 * the other task (either the highest priority waiter itself or the
+	 * task which stole the rtmutex) the chance to try the fixup of the
+	 * pi_state. So once we are back from handling the fault we need to
+	 * check the pi_state after reacquiring the locks and before trying to
+	 * do another fixup. When the fixup has been done already we simply
+	 * return.
+	 *
+	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
+	 * drop hb->lock since the caller owns the hb -> futex_q relation.
+	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
 handle_fault:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
 	ret = fault_in_user_writeable(uaddr);
 
 	spin_lock(q->lock_ptr);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*
 	 * Check if someone else fixed it for us:
 	 */
-	if (pi_state->owner != oldowner)
-		return 0;
+	if (pi_state->owner != oldowner) {
+		ret = 0;
+		goto out_unlock;
+	}
 
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	goto retry;
+
+out_unlock:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	return ret;
 }
 
 static long futex_wait_restart(struct restart_block *restart);
@@ -2231,13 +2339,16 @@ static long futex_wait_restart(struct restart_block *restart);
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	struct task_struct *owner;
 	int ret = 0;
 
 	if (locked) {
 		/*
 		 * Got the lock. We might not be the anticipated owner if we
 		 * did a lock-steal - fix up the PI-state in that case:
+		 *
+		 * We can safely read pi_state->owner without holding wait_lock
+		 * because we now own the rt_mutex, only the owner will attempt
+		 * to change it.
 		 */
 		if (q->pi_state->owner != current)
 			ret = fixup_pi_state_owner(uaddr, q, current);
@@ -2245,43 +2356,15 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	}
 
 	/*
-	 * Catch the rare case, where the lock was released when we were on the
-	 * way back before we locked the hash bucket.
-	 */
-	if (q->pi_state->owner == current) {
-		/*
-		 * Try to get the rt_mutex now. This might fail as some other
-		 * task acquired the rt_mutex after we removed ourself from the
-		 * rt_mutex waiters list.
-		 */
-		if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
-			locked = 1;
-			goto out;
-		}
-
-		/*
-		 * pi_state is incorrect, some other task did a lock steal and
-		 * we returned due to timeout or signal without taking the
-		 * rt_mutex. Too late.
-		 */
-		raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
-		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
-		if (!owner)
-			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
-		ret = fixup_pi_state_owner(uaddr, q, owner);
-		goto out;
-	}
-
-	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
 	 * the owner of the rt_mutex.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
 				"pi-state %p\n", ret,
 				q->pi_state->pi_mutex.owner,
 				q->pi_state->owner);
+	}
 
 out:
 	return ret ? ret : locked;
@@ -2505,6 +2588,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			 ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
+	struct futex_pi_state *pi_state = NULL;
+	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
 	int res, ret;
@@ -2557,25 +2642,68 @@ retry_private:
 		}
 	}
 
+	WARN_ON(!q.pi_state);
+
 	/*
 	 * Only actually queue now that the atomic ops are done:
 	 */
-	queue_me(&q, hb);
+	__queue_me(&q, hb);
 
-	WARN_ON(!q.pi_state);
-	/*
-	 * Block on the PI mutex:
-	 */
-	if (!trylock) {
-		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
-	} else {
-		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
+	if (trylock) {
+		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
+		goto no_block;
 	}
 
+	rt_mutex_init_waiter(&rt_waiter);
+
+	/*
+	 * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
+	 * hold it while doing rt_mutex_start_proxy(), because then it will
+	 * include hb->lock in the blocking chain, even through we'll not in
+	 * fact hold it while blocking. This will lead it to report -EDEADLK
+	 * and BUG when futex_unlock_pi() interleaves with this.
+	 *
+	 * Therefore acquire wait_lock while holding hb->lock, but drop the
+	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
+	 * serializes against futex_unlock_pi() as that does the exact same
+	 * lock handoff sequence.
+	 */
+	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+	spin_unlock(q.lock_ptr);
+	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+
+	if (ret) {
+		if (ret == 1)
+			ret = 0;
+
+		spin_lock(q.lock_ptr);
+		goto no_block;
+	}
+
+
+	if (unlikely(to))
+		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
+
+	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+
 	spin_lock(q.lock_ptr);
 	/*
+	 * If we failed to acquire the lock (signal/timeout), we must
+	 * first acquire the hb->lock before removing the lock from the
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
+	 * wait lists consistent.
+	 *
+	 * In particular; it is important that futex_unlock_pi() can not
+	 * observe this inconsistency.
+	 */
+	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+		ret = 0;
+
+no_block:
+	/*
 	 * Fixup the pi_state owner and possibly acquire the lock if we
 	 * haven't already.
 	 */
@@ -2591,12 +2719,19 @@ retry_private:
 	 * If fixup_owner() faulted and was unable to handle the fault, unlock
 	 * it and return the fault to userspace.
 	 */
-	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
-		rt_mutex_unlock(&q.pi_state->pi_mutex);
+	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
+		pi_state = q.pi_state;
+		get_pi_state(pi_state);
+	}
 
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
+	if (pi_state) {
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
+		put_pi_state(pi_state);
+	}
+
 	goto out_put_key;
 
 out_unlock_put_key:
@@ -2605,8 +2740,10 @@ out_unlock_put_key:
 out_put_key:
 	put_futex_key(&q.key);
 out:
-	if (to)
+	if (to) {
+		hrtimer_cancel(&to->timer);
 		destroy_hrtimer_on_stack(&to->timer);
+	}
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
@@ -2633,7 +2770,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb;
-	struct futex_q *match;
+	struct futex_q *top_waiter;
 	int ret;
 
 retry:
@@ -2657,12 +2794,37 @@ retry:
 	 * all and we at least want to know if user space fiddled
 	 * with the futex value instead of blindly unlocking.
 	 */
-	match = futex_top_waiter(hb, &key);
-	if (match) {
-		ret = wake_futex_pi(uaddr, uval, match, hb);
+	top_waiter = futex_top_waiter(hb, &key);
+	if (top_waiter) {
+		struct futex_pi_state *pi_state = top_waiter->pi_state;
+
+		ret = -EINVAL;
+		if (!pi_state)
+			goto out_unlock;
+
+		/*
+		 * If current does not own the pi_state then the futex is
+		 * inconsistent and user space fiddled with the futex value.
+		 */
+		if (pi_state->owner != current)
+			goto out_unlock;
+
+		get_pi_state(pi_state);
 		/*
-		 * In case of success wake_futex_pi dropped the hash
-		 * bucket lock.
+		 * By taking wait_lock while still holding hb->lock, we ensure
+		 * there is no point where we hold neither; and therefore
+		 * wake_futex_pi() must observe a state consistent with what we
+		 * observed.
+		 */
+		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		spin_unlock(&hb->lock);
+
+		ret = wake_futex_pi(uaddr, uval, pi_state);
+
+		put_pi_state(pi_state);
+
+		/*
+		 * Success, we're done! No tricky corner cases.
 		 */
 		if (!ret)
 			goto out_putkey;
@@ -2677,7 +2839,6 @@ retry:
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
 		if (ret == -EAGAIN) {
-			spin_unlock(&hb->lock);
 			put_futex_key(&key);
 			goto retry;
 		}
@@ -2685,7 +2846,7 @@ retry:
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */
-		goto out_unlock;
+		goto out_putkey;
 	}
 
 	/*
@@ -2695,8 +2856,10 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+		spin_unlock(&hb->lock);
 		goto pi_faulted;
+	}
 
 	/*
 	 * If uval has changed, let user space handle it.
@@ -2710,7 +2873,6 @@ out_putkey:
 	return ret;
 
 pi_faulted:
-	spin_unlock(&hb->lock);
 	put_futex_key(&key);
 
 	ret = fault_in_user_writeable(uaddr);
@@ -2814,8 +2976,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				 u32 __user *uaddr2)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
+	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct rt_mutex *pi_mutex = NULL;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
@@ -2841,10 +3003,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * The waiter is allocated on our stack, manipulated by the requeue
 	 * code while we sleep on uaddr.
 	 */
-	debug_rt_mutex_init_waiter(&rt_waiter);
-	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&rt_waiter.tree_entry);
-	rt_waiter.task = NULL;
+	rt_mutex_init_waiter(&rt_waiter);
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
@@ -2899,6 +3058,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
+				pi_state = q.pi_state;
+				get_pi_state(pi_state);
+			}
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
@@ -2907,6 +3070,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
+		struct rt_mutex *pi_mutex;
+
 		/*
 		 * We have been woken up by futex_unlock_pi(), a timeout, or a
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2914,10 +3079,13 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
-		debug_rt_mutex_free_waiter(&rt_waiter);
+		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
 
 		spin_lock(q.lock_ptr);
+		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+			ret = 0;
+
+		debug_rt_mutex_free_waiter(&rt_waiter);
 		/*
 		 * Fixup the pi_state owner and possibly acquire the lock if we
 		 * haven't already.
@@ -2930,18 +3098,26 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
+		/*
+		 * If fixup_pi_state_owner() faulted and was unable to handle
+		 * the fault, unlock the rt_mutex and return the fault to
+		 * userspace.
+		 */
+		if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
+			pi_state = q.pi_state;
+			get_pi_state(pi_state);
+		}
+
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock the rt_mutex and return the fault to userspace.
-	 */
-	if (ret == -EFAULT) {
-		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
-	} else if (ret == -EINTR) {
+	if (pi_state) {
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
+		put_pi_state(pi_state);
+	}
+
+	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
 		 * futex_lock_pi() directly. We could restart this syscall, but
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 4544b115f5eb..e2d356dd7581 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -59,7 +59,7 @@ static int get_nodes_in_cpumask(const struct cpumask *mask, nodemask_t *nodemsk)
 struct cpumask *
 irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 {
-	int n, nodes, vecs_per_node, cpus_per_vec, extra_vecs, curvec;
+	int n, nodes, cpus_per_vec, extra_vecs, curvec;
 	int affv = nvecs - affd->pre_vectors - affd->post_vectors;
 	int last_affv = affv + affd->pre_vectors;
 	nodemask_t nodemsk = NODE_MASK_NONE;
@@ -94,19 +94,21 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 		goto done;
 	}
 
-	/* Spread the vectors per node */
-	vecs_per_node = affv / nodes;
-	/* Account for rounding errors */
-	extra_vecs = affv - (nodes * vecs_per_node);
-
 	for_each_node_mask(n, nodemsk) {
-		int ncpus, v, vecs_to_assign = vecs_per_node;
+		int ncpus, v, vecs_to_assign, vecs_per_node;
+
+		/* Spread the vectors per node */
+		vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes;
 
 		/* Get the cpus on this node which are in the mask */
 		cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n));
 
 		/* Calculate the number of cpus per vector */
 		ncpus = cpumask_weight(nmsk);
+		vecs_to_assign = min(vecs_per_node, ncpus);
+
+		/* Account for rounding errors */
+		extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign);
 
 		for (v = 0; curvec < last_affv && v < vecs_to_assign;
 		     curvec++, v++) {
@@ -115,14 +117,14 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 			/* Account for extra vectors to compensate rounding errors */
 			if (extra_vecs) {
 				cpus_per_vec++;
-				if (!--extra_vecs)
-					vecs_per_node++;
+				--extra_vecs;
 			}
 			irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
 		}
 
 		if (curvec >= last_affv)
 			break;
+		--nodes;
 	}
 
 done:
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index be3c34e4f2ac..686be4b73018 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -348,7 +348,10 @@ void handle_nested_irq(unsigned int irq)
 	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
 	raw_spin_unlock_irq(&desc->lock);
 
-	action_ret = action->thread_fn(action->irq, action->dev_id);
+	action_ret = IRQ_NONE;
+	for_each_action_of_desc(desc, action)
+		action_ret |= action->thread_fn(action->irq, action->dev_id);
+
 	if (!noirqdebug)
 		note_interrupt(desc, action_ret);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a4afe5cc5af1..ae1c90f20381 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -852,7 +852,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 	 * This code is triggered unconditionally. Check the affinity
 	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
 	 */
-	if (desc->irq_common_data.affinity)
+	if (cpumask_available(desc->irq_common_data.affinity))
 		cpumask_copy(mask, desc->irq_common_data.affinity);
 	else
 		valid = false;
@@ -1212,8 +1212,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * set the trigger type must match. Also all must
 		 * agree on ONESHOT.
 		 */
+		unsigned int oldtype = irqd_get_trigger_type(&desc->irq_data);
+
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
-		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
+		    (oldtype != (new->flags & IRQF_TRIGGER_MASK)) ||
 		    ((old->flags ^ new->flags) & IRQF_ONESHOT))
 			goto mismatch;
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b56a558e406d..b118735fea9d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image)
 		ret = crypto_shash_final(desc, digest);
 		if (ret)
 			goto out_free_digest;
-		ret = kexec_purgatory_get_set_symbol(image, "sha_regions",
-						sha_regions, sha_region_sz, 0);
+		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
+						     sha_regions, sha_region_sz, 0);
 		if (ret)
 			goto out_free_digest;
 
-		ret = kexec_purgatory_get_set_symbol(image, "sha256_digest",
-						digest, SHA256_DIGEST_SIZE, 0);
+		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
+						     digest, SHA256_DIGEST_SIZE, 0);
 		if (ret)
 			goto out_free_digest;
 	}
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 4cef7e4706b0..799a8a452187 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image,
 extern struct mutex kexec_mutex;
 
 #ifdef CONFIG_KEXEC_FILE
-struct kexec_sha_region {
-	unsigned long start;
-	unsigned long len;
-};
-
+#include <linux/purgatory.h>
 void kimage_file_post_load_cleanup(struct kimage *image);
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 699c5bc51a92..d733479a10ee 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1391,21 +1391,19 @@ bool within_kprobe_blacklist(unsigned long addr)
  * This returns encoded errors if it fails to look up symbol or invalid
  * combination of parameters.
  */
-static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
+			const char *symbol_name, unsigned int offset)
 {
-	kprobe_opcode_t *addr = p->addr;
-
-	if ((p->symbol_name && p->addr) ||
-	    (!p->symbol_name && !p->addr))
+	if ((symbol_name && addr) || (!symbol_name && !addr))
 		goto invalid;
 
-	if (p->symbol_name) {
-		kprobe_lookup_name(p->symbol_name, addr);
+	if (symbol_name) {
+		kprobe_lookup_name(symbol_name, addr);
 		if (!addr)
 			return ERR_PTR(-ENOENT);
 	}
 
-	addr = (kprobe_opcode_t *)(((char *)addr) + p->offset);
+	addr = (kprobe_opcode_t *)(((char *)addr) + offset);
 	if (addr)
 		return addr;
 
@@ -1413,6 +1411,11 @@ invalid:
 	return ERR_PTR(-EINVAL);
 }
 
+static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+{
+	return _kprobe_addr(p->addr, p->symbol_name, p->offset);
+}
+
 /* Check passed kprobe is valid and return kprobe in kprobe_table. */
 static struct kprobe *__get_valid_kprobe(struct kprobe *p)
 {
@@ -1740,11 +1743,12 @@ void unregister_kprobes(struct kprobe **kps, int num)
 }
 EXPORT_SYMBOL_GPL(unregister_kprobes);
 
-int __weak __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-					      unsigned long val, void *data)
+int __weak kprobe_exceptions_notify(struct notifier_block *self,
+					unsigned long val, void *data)
 {
 	return NOTIFY_DONE;
 }
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
 static struct notifier_block kprobe_exceptions_nb = {
 	.notifier_call = kprobe_exceptions_notify,
@@ -1875,6 +1879,25 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(pre_handler_kretprobe);
 
+bool __weak arch_function_offset_within_entry(unsigned long offset)
+{
+	return !offset;
+}
+
+bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+{
+	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
+
+	if (IS_ERR(kp_addr))
+		return false;
+
+	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
+						!arch_function_offset_within_entry(offset))
+		return false;
+
+	return true;
+}
+
 int register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
@@ -1882,6 +1905,9 @@ int register_kretprobe(struct kretprobe *rp)
 	int i;
 	void *addr;
 
+	if (!function_offset_within_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
+		return -EINVAL;
+
 	if (kretprobe_blacklist_size) {
 		addr = kprobe_addr(&rp->kp);
 		if (IS_ERR(addr))
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2f26adea0f84..26db528c1d88 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -20,6 +20,7 @@
 #include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
+#include <linux/cgroup.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -225,6 +226,7 @@ static int kthread(void *_create)
 
 	ret = -EINTR;
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
+		cgroup_kthread_ready();
 		__kthread_parkme(self);
 		ret = threadfn(data);
 	}
@@ -538,6 +540,7 @@ int kthreadd(void *unused)
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
+	cgroup_init_kthreadd();
 
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 12e38c213b70..98dd6231d43b 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -660,6 +660,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 	struct lockdep_subclass_key *key;
 	struct hlist_head *hash_head;
 	struct lock_class *class;
+	bool is_static = false;
 
 	if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
 		debug_locks_off();
@@ -673,10 +674,23 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 
 	/*
 	 * Static locks do not have their class-keys yet - for them the key
-	 * is the lock object itself:
+	 * is the lock object itself. If the lock is in the per cpu area,
+	 * the canonical address of the lock (per cpu offset removed) is
+	 * used.
 	 */
-	if (unlikely(!lock->key))
-		lock->key = (void *)lock;
+	if (unlikely(!lock->key)) {
+		unsigned long can_addr, addr = (unsigned long)lock;
+
+		if (__is_kernel_percpu_address(addr, &can_addr))
+			lock->key = (void *)can_addr;
+		else if (__is_module_percpu_address(addr, &can_addr))
+			lock->key = (void *)can_addr;
+		else if (static_obj(lock))
+			lock->key = (void *)lock;
+		else
+			return ERR_PTR(-EINVAL);
+		is_static = true;
+	}
 
 	/*
 	 * NOTE: the class-key must be unique. For dynamic locks, a static
@@ -708,7 +722,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 		}
 	}
 
-	return NULL;
+	return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL);
 }
 
 /*
@@ -726,19 +740,18 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
 	class = look_up_lock_class(lock, subclass);
-	if (likely(class))
+	if (likely(!IS_ERR_OR_NULL(class)))
 		goto out_set_class_cache;
 
 	/*
 	 * Debug-check: all keys must be persistent!
- 	 */
-	if (!static_obj(lock->key)) {
+	 */
+	if (IS_ERR(class)) {
 		debug_locks_off();
 		printk("INFO: trying to register non-static key.\n");
 		printk("the code is fine but needs lockdep annotation.\n");
 		printk("turning off the locking correctness validator.\n");
 		dump_stack();
-
 		return NULL;
 	}
 
@@ -3262,10 +3275,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (depth) {
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
-			if (hlock->references)
+			if (hlock->references) {
+				/*
+				 * Check: unsigned int references:12, overflow.
+				 */
+				if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+					return 0;
+
 				hlock->references++;
-			else
+			} else {
 				hlock->references = 2;
+			}
 
 			return 1;
 		}
@@ -3412,7 +3432,7 @@ static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
 		 * Clearly if the lock hasn't been acquired _ever_, we're not
 		 * holding it either, so report failure.
 		 */
-		if (!class)
+		if (IS_ERR_OR_NULL(class))
 			return 0;
 
 		/*
@@ -3430,13 +3450,67 @@ static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
 	return 0;
 }
 
+/* @depth must not be zero */
+static struct held_lock *find_held_lock(struct task_struct *curr,
+					struct lockdep_map *lock,
+					unsigned int depth, int *idx)
+{
+	struct held_lock *ret, *hlock, *prev_hlock;
+	int i;
+
+	i = depth - 1;
+	hlock = curr->held_locks + i;
+	ret = hlock;
+	if (match_held_lock(hlock, lock))
+		goto out;
+
+	ret = NULL;
+	for (i--, prev_hlock = hlock--;
+	     i >= 0;
+	     i--, prev_hlock = hlock--) {
+		/*
+		 * We must not cross into another context:
+		 */
+		if (prev_hlock->irq_context != hlock->irq_context) {
+			ret = NULL;
+			break;
+		}
+		if (match_held_lock(hlock, lock)) {
+			ret = hlock;
+			break;
+		}
+	}
+
+out:
+	*idx = i;
+	return ret;
+}
+
+static int reacquire_held_locks(struct task_struct *curr, unsigned int depth,
+			      int idx)
+{
+	struct held_lock *hlock;
+
+	for (hlock = curr->held_locks + idx; idx < depth; idx++, hlock++) {
+		if (!__lock_acquire(hlock->instance,
+				    hlock_class(hlock)->subclass,
+				    hlock->trylock,
+				    hlock->read, hlock->check,
+				    hlock->hardirqs_off,
+				    hlock->nest_lock, hlock->acquire_ip,
+				    hlock->references, hlock->pin_count))
+			return 1;
+	}
+	return 0;
+}
+
 static int
 __lock_set_class(struct lockdep_map *lock, const char *name,
 		 struct lock_class_key *key, unsigned int subclass,
 		 unsigned long ip)
 {
 	struct task_struct *curr = current;
-	struct held_lock *hlock, *prev_hlock;
+	struct held_lock *hlock;
 	struct lock_class *class;
 	unsigned int depth;
 	int i;
@@ -3449,21 +3523,10 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 	if (DEBUG_LOCKS_WARN_ON(!depth))
 		return 0;
 
-	prev_hlock = NULL;
-	for (i = depth-1; i >= 0; i--) {
-		hlock = curr->held_locks + i;
-		/*
-		 * We must not cross into another context:
-		 */
-		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
-			break;
-		if (match_held_lock(hlock, lock))
-			goto found_it;
-		prev_hlock = hlock;
-	}
-	return print_unlock_imbalance_bug(curr, lock, ip);
+	hlock = find_held_lock(curr, lock, depth, &i);
+	if (!hlock)
+		return print_unlock_imbalance_bug(curr, lock, ip);
 
-found_it:
 	lockdep_init_map(lock, name, key, 0);
 	class = register_lock_class(lock, subclass, 0);
 	hlock->class_idx = class - lock_classes + 1;
@@ -3471,15 +3534,46 @@ found_it:
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
-	for (; i < depth; i++) {
-		hlock = curr->held_locks + i;
-		if (!__lock_acquire(hlock->instance,
-			hlock_class(hlock)->subclass, hlock->trylock,
-				hlock->read, hlock->check, hlock->hardirqs_off,
-				hlock->nest_lock, hlock->acquire_ip,
-				hlock->references, hlock->pin_count))
-			return 0;
-	}
+	if (reacquire_held_locks(curr, depth, i))
+		return 0;
+
+	/*
+	 * I took it apart and put it back together again, except now I have
+	 * these 'spare' parts.. where shall I put them.
+	 */
+	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+		return 0;
+	return 1;
+}
+
+static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
+{
+	struct task_struct *curr = current;
+	struct held_lock *hlock;
+	unsigned int depth;
+	int i;
+
+	depth = curr->lockdep_depth;
+	/*
+	 * This function is about (re)setting the class of a held lock,
+	 * yet we're not actually holding any locks. Naughty user!
+	 */
+	if (DEBUG_LOCKS_WARN_ON(!depth))
+		return 0;
+
+	hlock = find_held_lock(curr, lock, depth, &i);
+	if (!hlock)
+		return print_unlock_imbalance_bug(curr, lock, ip);
+
+	curr->lockdep_depth = i;
+	curr->curr_chain_key = hlock->prev_chain_key;
+
+	WARN(hlock->read, "downgrading a read lock");
+	hlock->read = 1;
+	hlock->acquire_ip = ip;
+
+	if (reacquire_held_locks(curr, depth, i))
+		return 0;
 
 	/*
 	 * I took it apart and put it back together again, except now I have
@@ -3501,7 +3595,7 @@ static int
 __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 {
 	struct task_struct *curr = current;
-	struct held_lock *hlock, *prev_hlock;
+	struct held_lock *hlock;
 	unsigned int depth;
 	int i;
 
@@ -3520,21 +3614,10 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 	 * Check whether the lock exists in the current stack
 	 * of held locks:
 	 */
-	prev_hlock = NULL;
-	for (i = depth-1; i >= 0; i--) {
-		hlock = curr->held_locks + i;
-		/*
-		 * We must not cross into another context:
-		 */
-		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
-			break;
-		if (match_held_lock(hlock, lock))
-			goto found_it;
-		prev_hlock = hlock;
-	}
-	return print_unlock_imbalance_bug(curr, lock, ip);
+	hlock = find_held_lock(curr, lock, depth, &i);
+	if (!hlock)
+		return print_unlock_imbalance_bug(curr, lock, ip);
 
-found_it:
 	if (hlock->instance == lock)
 		lock_release_holdtime(hlock);
 
@@ -3561,15 +3644,8 @@ found_it:
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
-	for (i++; i < depth; i++) {
-		hlock = curr->held_locks + i;
-		if (!__lock_acquire(hlock->instance,
-			hlock_class(hlock)->subclass, hlock->trylock,
-				hlock->read, hlock->check, hlock->hardirqs_off,
-				hlock->nest_lock, hlock->acquire_ip,
-				hlock->references, hlock->pin_count))
-			return 0;
-	}
+	if (reacquire_held_locks(curr, depth, i + 1))
+		return 0;
 
 	/*
 	 * We had N bottles of beer on the wall, we drank one, but now
@@ -3734,6 +3810,23 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 }
 EXPORT_SYMBOL_GPL(lock_set_class);
 
+void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
+{
+	unsigned long flags;
+
+	if (unlikely(current->lockdep_recursion))
+		return;
+
+	raw_local_irq_save(flags);
+	current->lockdep_recursion = 1;
+	check_flags(flags);
+	if (__lock_downgrade(lock, ip))
+		check_chain_key(current);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lock_downgrade);
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
@@ -3896,7 +3989,7 @@ static void
 __lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
-	struct held_lock *hlock, *prev_hlock;
+	struct held_lock *hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
 	int i, contention_point, contending_point;
@@ -3909,22 +4002,12 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!depth))
 		return;
 
-	prev_hlock = NULL;
-	for (i = depth-1; i >= 0; i--) {
-		hlock = curr->held_locks + i;
-		/*
-		 * We must not cross into another context:
-		 */
-		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
-			break;
-		if (match_held_lock(hlock, lock))
-			goto found_it;
-		prev_hlock = hlock;
+	hlock = find_held_lock(curr, lock, depth, &i);
+	if (!hlock) {
+		print_lock_contention_bug(curr, lock, ip);
+		return;
 	}
-	print_lock_contention_bug(curr, lock, ip);
-	return;
 
-found_it:
 	if (hlock->instance != lock)
 		return;
 
@@ -3948,7 +4031,7 @@ static void
 __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
-	struct held_lock *hlock, *prev_hlock;
+	struct held_lock *hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
 	u64 now, waittime = 0;
@@ -3962,22 +4045,12 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!depth))
 		return;
 
-	prev_hlock = NULL;
-	for (i = depth-1; i >= 0; i--) {
-		hlock = curr->held_locks + i;
-		/*
-		 * We must not cross into another context:
-		 */
-		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
-			break;
-		if (match_held_lock(hlock, lock))
-			goto found_it;
-		prev_hlock = hlock;
+	hlock = find_held_lock(curr, lock, depth, &i);
+	if (!hlock) {
+		print_lock_contention_bug(curr, lock, _RET_IP_);
+		return;
 	}
-	print_lock_contention_bug(curr, lock, _RET_IP_);
-	return;
 
-found_it:
 	if (hlock->instance != lock)
 		return;
 
@@ -4165,7 +4238,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 		 * If the class exists we look it up and zap it:
 		 */
 		class = look_up_lock_class(lock, j);
-		if (class)
+		if (!IS_ERR_OR_NULL(class))
 			zap_class(class);
 	}
 	/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index c2b88490d857..c08fbd2f5ba9 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -46,13 +46,13 @@ enum {
 		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
 
 /*
- * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text,
+ * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
  * .data and .bss to fit in required 32MB limit for the kernel. With
- * PROVE_LOCKING we could go over this limit and cause system boot-up problems.
+ * CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems.
  * So, reduce the static allocations for lockdeps related structures so that
  * everything fits in current required size limit.
  */
-#ifdef CONFIG_PROVE_LOCKING_SMALL
+#ifdef CONFIG_LOCKDEP_SMALL
 /*
  * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies
  * we track.
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 97ee9df32e0f..32fe775a2eaf 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -174,12 +174,3 @@ void debug_rt_mutex_init(struct rt_mutex *lock, const char *name)
 	lock->name = name;
 }
 
-void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task)
-{
-}
-
-void rt_mutex_deadlock_account_unlock(struct task_struct *task)
-{
-}
-
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index d0519c3432b6..b585af9a1b50 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -9,9 +9,6 @@
  * This file contains macros used solely by rtmutex.c. Debug version.
  */
 
-extern void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task);
-extern void rt_mutex_deadlock_account_unlock(struct task_struct *task);
 extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
 extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter);
 extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 6edc32ecd9c5..b95509416909 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -224,6 +224,12 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
 }
 #endif
 
+/*
+ * Only use with rt_mutex_waiter_{less,equal}()
+ */
+#define task_to_waiter(p)	\
+	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+
 static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 		     struct rt_mutex_waiter *right)
@@ -238,12 +244,30 @@ rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 	 * then right waiter has a dl_prio() too.
 	 */
 	if (dl_prio(left->prio))
-		return dl_time_before(left->task->dl.deadline,
-				      right->task->dl.deadline);
+		return dl_time_before(left->deadline, right->deadline);
 
 	return 0;
 }
 
+static inline int
+rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
+		      struct rt_mutex_waiter *right)
+{
+	if (left->prio != right->prio)
+		return 0;
+
+	/*
+	 * If both waiters have dl_prio(), we check the deadlines of the
+	 * associated tasks.
+	 * If left waiter has a dl_prio(), and we didn't return 0 above,
+	 * then right waiter has a dl_prio() too.
+	 */
+	if (dl_prio(left->prio))
+		return left->deadline == right->deadline;
+
+	return 1;
+}
+
 static void
 rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 {
@@ -322,72 +346,16 @@ rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
 	RB_CLEAR_NODE(&waiter->pi_tree_entry);
 }
 
-/*
- * Calculate task priority from the waiter tree priority
- *
- * Return task->normal_prio when the waiter tree is empty or when
- * the waiter is not allowed to do priority boosting
- */
-int rt_mutex_getprio(struct task_struct *task)
-{
-	if (likely(!task_has_pi_waiters(task)))
-		return task->normal_prio;
-
-	return min(task_top_pi_waiter(task)->prio,
-		   task->normal_prio);
-}
-
-struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+static void rt_mutex_adjust_prio(struct task_struct *p)
 {
-	if (likely(!task_has_pi_waiters(task)))
-		return NULL;
-
-	return task_top_pi_waiter(task)->task;
-}
+	struct task_struct *pi_task = NULL;
 
-/*
- * Called by sched_setscheduler() to get the priority which will be
- * effective after the change.
- */
-int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
-{
-	if (!task_has_pi_waiters(task))
-		return newprio;
+	lockdep_assert_held(&p->pi_lock);
 
-	if (task_top_pi_waiter(task)->task->prio <= newprio)
-		return task_top_pi_waiter(task)->task->prio;
-	return newprio;
-}
+	if (task_has_pi_waiters(p))
+		pi_task = task_top_pi_waiter(p)->task;
 
-/*
- * Adjust the priority of a task, after its pi_waiters got modified.
- *
- * This can be both boosting and unboosting. task->pi_lock must be held.
- */
-static void __rt_mutex_adjust_prio(struct task_struct *task)
-{
-	int prio = rt_mutex_getprio(task);
-
-	if (task->prio != prio || dl_prio(prio))
-		rt_mutex_setprio(task, prio);
-}
-
-/*
- * Adjust task priority (undo boosting). Called from the exit path of
- * rt_mutex_slowunlock() and rt_mutex_slowlock().
- *
- * (Note: We do this outside of the protection of lock->wait_lock to
- * allow the lock to be taken while or before we readjust the priority
- * of task. We do not use the spin_xx_mutex() variants here as we are
- * outside of the debug path.)
- */
-void rt_mutex_adjust_prio(struct task_struct *task)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	__rt_mutex_adjust_prio(task);
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	rt_mutex_setprio(p, pi_task);
 }
 
 /*
@@ -610,7 +578,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * enabled we continue, but stop the requeueing in the chain
 	 * walk.
 	 */
-	if (waiter->prio == task->prio) {
+	if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		if (!detect_deadlock)
 			goto out_unlock_pi;
 		else
@@ -706,7 +674,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* [7] Requeue the waiter in the lock waiter tree. */
 	rt_mutex_dequeue(lock, waiter);
+
+	/*
+	 * Update the waiter prio fields now that we're dequeued.
+	 *
+	 * These values can have changed through either:
+	 *
+	 *   sys_sched_set_scheduler() / sys_sched_setattr()
+	 *
+	 * or
+	 *
+	 *   DL CBS enforcement advancing the effective deadline.
+	 *
+	 * Even though pi_waiters also uses these fields, and that tree is only
+	 * updated in [11], we can do this here, since we hold [L], which
+	 * serializes all pi_waiters access and rb_erase() does not care about
+	 * the values of the node being removed.
+	 */
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
+
 	rt_mutex_enqueue(lock, waiter);
 
 	/* [8] Release the task */
@@ -747,7 +734,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 */
 		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
 		rt_mutex_enqueue_pi(task, waiter);
-		__rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(task);
 
 	} else if (prerequeue_top_waiter == waiter) {
 		/*
@@ -763,7 +750,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
 		rt_mutex_enqueue_pi(task, waiter);
-		__rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(task);
 	} else {
 		/*
 		 * Nothing changed. No need to do any priority
@@ -833,6 +820,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 				struct rt_mutex_waiter *waiter)
 {
+	lockdep_assert_held(&lock->wait_lock);
+
 	/*
 	 * Before testing whether we can acquire @lock, we set the
 	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
@@ -892,7 +881,8 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 			 * the top waiter priority (kernel view),
 			 * @task lost.
 			 */
-			if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+			if (!rt_mutex_waiter_less(task_to_waiter(task),
+						  rt_mutex_top_waiter(lock)))
 				return 0;
 
 			/*
@@ -938,8 +928,6 @@ takeit:
 	 */
 	rt_mutex_set_owner(lock, task);
 
-	rt_mutex_deadlock_account_lock(lock, task);
-
 	return 1;
 }
 
@@ -960,6 +948,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	/*
 	 * Early deadlock detection. We really don't want the task to
 	 * enqueue on itself just to untangle the mess later. It's not
@@ -973,10 +963,11 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		return -EDEADLK;
 
 	raw_spin_lock(&task->pi_lock);
-	__rt_mutex_adjust_prio(task);
+	rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
@@ -995,7 +986,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
 
-		__rt_mutex_adjust_prio(owner);
+		rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
 	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
@@ -1047,12 +1038,14 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	waiter = rt_mutex_top_waiter(lock);
 
 	/*
-	 * Remove it from current->pi_waiters. We do not adjust a
-	 * possible priority boost right now. We execute wakeup in the
-	 * boosted mode and go back to normal after releasing
-	 * lock->wait_lock.
+	 * Remove it from current->pi_waiters and deboost.
+	 *
+	 * We must in fact deboost here in order to ensure we call
+	 * rt_mutex_setprio() to update p->pi_top_task before the
+	 * task unblocks.
 	 */
 	rt_mutex_dequeue_pi(current, waiter);
+	rt_mutex_adjust_prio(current);
 
 	/*
 	 * As we are waking up the top waiter, and the waiter stays
@@ -1064,9 +1057,19 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	 */
 	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
-	raw_spin_unlock(&current->pi_lock);
-
+	/*
+	 * We deboosted before waking the top waiter task such that we don't
+	 * run two tasks with the 'same' priority (and ensure the
+	 * p->pi_top_task pointer points to a blocked task). This however can
+	 * lead to priority inversion if we would get preempted after the
+	 * deboost but before waking our donor task, hence the preempt_disable()
+	 * before unlock.
+	 *
+	 * Pairs with preempt_enable() in rt_mutex_postunlock();
+	 */
+	preempt_disable();
 	wake_q_add(wake_q, waiter->task);
+	raw_spin_unlock(&current->pi_lock);
 }
 
 /*
@@ -1082,6 +1085,8 @@ static void remove_waiter(struct rt_mutex *lock,
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	raw_spin_lock(&current->pi_lock);
 	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
@@ -1101,7 +1106,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	if (rt_mutex_has_waiters(lock))
 		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-	__rt_mutex_adjust_prio(owner);
+	rt_mutex_adjust_prio(owner);
 
 	/* Store the lock on which owner is blocked or NULL */
 	next_lock = task_blocked_on_lock(owner);
@@ -1140,8 +1145,7 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || (waiter->prio == task->prio &&
-			!dl_prio(task->prio))) {
+	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
@@ -1155,6 +1159,14 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 				   next_lock, NULL, task);
 }
 
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+	waiter->task = NULL;
+}
+
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
@@ -1237,9 +1249,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	unsigned long flags;
 	int ret = 0;
 
-	debug_rt_mutex_init_waiter(&waiter);
-	RB_CLEAR_NODE(&waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&waiter.tree_entry);
+	rt_mutex_init_waiter(&waiter);
 
 	/*
 	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
@@ -1330,7 +1340,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 
 /*
  * Slow path to release a rt-mutex.
- * Return whether the current task needs to undo a potential priority boosting.
+ *
+ * Return whether the current task needs to call rt_mutex_postunlock().
  */
 static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 					struct wake_q_head *wake_q)
@@ -1342,8 +1353,6 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 
 	debug_rt_mutex_unlock(lock);
 
-	rt_mutex_deadlock_account_unlock(current);
-
 	/*
 	 * We must be careful here if the fast path is enabled. If we
 	 * have no waiters queued we cannot set owner to NULL here
@@ -1390,11 +1399,9 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 * Queue the next waiter for wakeup once we release the wait_lock.
 	 */
 	mark_wakeup_next_waiter(wake_q, lock);
-
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	/* check PI boosting */
-	return true;
+	return true; /* call rt_mutex_postunlock() */
 }
 
 /*
@@ -1409,11 +1416,10 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
 				enum rtmutex_chainwalk chwalk))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+
+	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
 }
 
 static inline int
@@ -1425,24 +1431,33 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
 				      enum rtmutex_chainwalk chwalk))
 {
 	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
-	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, timeout, chwalk);
+
+	return slowfn(lock, state, timeout, chwalk);
 }
 
 static inline int
 rt_mutex_fasttrylock(struct rt_mutex *lock,
 		     int (*slowfn)(struct rt_mutex *lock))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 1;
-	}
+
 	return slowfn(lock);
 }
 
+/*
+ * Performs the wakeup of the the top-waiter and re-enables preemption.
+ */
+void rt_mutex_postunlock(struct wake_q_head *wake_q)
+{
+	wake_up_q(wake_q);
+
+	/* Pairs with preempt_disable() in rt_mutex_slowunlock() */
+	preempt_enable();
+}
+
 static inline void
 rt_mutex_fastunlock(struct rt_mutex *lock,
 		    bool (*slowfn)(struct rt_mutex *lock,
@@ -1450,18 +1465,11 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 {
 	DEFINE_WAKE_Q(wake_q);
 
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
-
-	} else {
-		bool deboost = slowfn(lock, &wake_q);
-
-		wake_up_q(&wake_q);
+	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+		return;
 
-		/* Undo pi boosting if necessary: */
-		if (deboost)
-			rt_mutex_adjust_prio(current);
-	}
+	if (slowfn(lock, &wake_q))
+		rt_mutex_postunlock(&wake_q);
 }
 
 /**
@@ -1495,16 +1503,11 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
 /*
- * Futex variant with full deadlock detection.
+ * Futex variant, must not use fastpath.
  */
-int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
-			      struct hrtimer_sleeper *timeout)
+int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
 {
-	might_sleep();
-
-	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       RT_MUTEX_FULL_CHAINWALK,
-				       rt_mutex_slowlock);
+	return rt_mutex_slowtrylock(lock);
 }
 
 /**
@@ -1563,20 +1566,43 @@ void __sched rt_mutex_unlock(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
 /**
- * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock
- * @lock: the rt_mutex to be unlocked
- *
- * Returns: true/false indicating whether priority adjustment is
- * required or not.
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
  */
-bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock,
-				   struct wake_q_head *wqh)
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				    struct wake_q_head *wake_q)
 {
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
-		return false;
+	lockdep_assert_held(&lock->wait_lock);
+
+	debug_rt_mutex_unlock(lock);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		return false; /* done */
 	}
-	return rt_mutex_slowunlock(lock, wqh);
+
+	/*
+	 * We've already deboosted, mark_wakeup_next_waiter() will
+	 * retain preempt_disabled when we drop the wait_lock, to
+	 * avoid inversion prior to the wakeup.  preempt_disable()
+	 * therein pairs with rt_mutex_postunlock().
+	 */
+	mark_wakeup_next_waiter(wake_q, lock);
+
+	return true; /* call postunlock() */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+	DEFINE_WAKE_Q(wake_q);
+	bool postunlock;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q);
 }
 
 /**
@@ -1637,7 +1663,6 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 	__rt_mutex_init(lock, NULL);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
 	rt_mutex_set_owner(lock, proxy_owner);
-	rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
 /**
@@ -1657,34 +1682,16 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 {
 	debug_rt_mutex_proxy_unlock(lock);
 	rt_mutex_set_owner(lock, NULL);
-	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
-/**
- * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
- * @lock:		the rt_mutex to take
- * @waiter:		the pre-initialized rt_mutex_waiter
- * @task:		the task to prepare
- *
- * Returns:
- *  0 - task blocked on lock
- *  1 - acquired the lock for task, caller should wake it up
- * <0 - error
- *
- * Special API call for FUTEX_REQUEUE_PI support.
- */
-int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
-	raw_spin_lock_irq(&lock->wait_lock);
-
-	if (try_to_take_rt_mutex(lock, task, NULL)) {
-		raw_spin_unlock_irq(&lock->wait_lock);
+	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
-	}
 
 	/* We enforce deadlock detection for futexes */
 	ret = task_blocks_on_rt_mutex(lock, waiter, task,
@@ -1703,14 +1710,38 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (unlikely(ret))
 		remove_waiter(lock, waiter);
 
-	raw_spin_unlock_irq(&lock->wait_lock);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
 }
 
 /**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+			      struct rt_mutex_waiter *waiter,
+			      struct task_struct *task)
+{
+	int ret;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
  * rt_mutex_next_owner - return the next owner of the lock
  *
  * @lock: the rt lock query
@@ -1731,21 +1762,23 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
 }
 
 /**
- * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
  * @lock:		the rt_mutex we were woken on
  * @to:			the timeout, null if none. hrtimer should already have
  *			been started.
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Complete the lock acquisition started our behalf by another thread.
+ * Wait for the the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
  *
  * Returns:
  *  0 - success
  * <0 - error, one of -EINTR, -ETIMEDOUT
  *
- * Special API call for PI-futex requeue support
+ * Special API call for PI-futex support
  */
-int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
 			       struct rt_mutex_waiter *waiter)
 {
@@ -1758,8 +1791,45 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 	/* sleep on the mutex */
 	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
 
-	if (unlikely(ret))
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ *
+ * Unless we acquired the lock; we're still enqueued on the wait-list and can
+ * in fact still be granted ownership until we're removed. Therefore we can
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ *  true  - did the cleanup, we done.
+ *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ *          caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter)
+{
+	bool cleanup = false;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	/*
+	 * Unless we're the owner; we're still enqueued on the wait_list.
+	 * So check if we became owner, if not, take us off the wait_list.
+	 */
+	if (rt_mutex_owner(lock) != current) {
 		remove_waiter(lock, waiter);
+		fixup_rt_mutex_waiters(lock);
+		cleanup = true;
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
@@ -1769,5 +1839,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_unlock_irq(&lock->wait_lock);
 
-	return ret;
+	return cleanup;
 }
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index c4060584c407..6607802efa8b 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -11,8 +11,6 @@
  */
 
 #define rt_mutex_deadlock_check(l)			(0)
-#define rt_mutex_deadlock_account_lock(m, t)		do { } while (0)
-#define rt_mutex_deadlock_account_unlock(l)		do { } while (0)
 #define debug_rt_mutex_init_waiter(w)			do { } while (0)
 #define debug_rt_mutex_free_waiter(w)			do { } while (0)
 #define debug_rt_mutex_lock(l)				do { } while (0)
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 856dfff5c33a..72ad45a9a794 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -34,6 +34,7 @@ struct rt_mutex_waiter {
 	struct rt_mutex		*deadlock_lock;
 #endif
 	int prio;
+	u64 deadline;
 };
 
 /*
@@ -103,16 +104,26 @@ extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
+extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
-extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
-				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter);
-extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
-extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
-				  struct wake_q_head *wqh);
-extern void rt_mutex_adjust_prio(struct task_struct *task);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter);
+
+extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+
+extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				 struct wake_q_head *wqh);
+
+extern void rt_mutex_postunlock(struct wake_q_head *wake_q);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 7bc24d477805..c65f7989f850 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -213,10 +213,9 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 		 */
 		if (sem->count == 0)
 			break;
-		if (signal_pending_state(state, current)) {
-			ret = -EINTR;
-			goto out;
-		}
+		if (signal_pending_state(state, current))
+			goto out_nolock;
+
 		set_current_state(state);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
@@ -224,12 +223,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 	}
 	/* got the lock */
 	sem->count = -1;
-out:
 	list_del(&waiter.list);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return ret;
+
+out_nolock:
+	list_del(&waiter.list);
+	if (!list_empty(&sem->wait_list))
+		__rwsem_do_wake(sem, 1);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return -EINTR;
 }
 
 void __sched __down_write(struct rw_semaphore *sem)
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 90a74ccd85a4..4d48b1c4870d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -124,10 +124,8 @@ EXPORT_SYMBOL(up_write);
  */
 void downgrade_write(struct rw_semaphore *sem)
 {
-	/*
-	 * lockdep: a downgraded write will live on as a write
-	 * dependency.
-	 */
+	lock_downgrade(&sem->dep_map, _RET_IP_);
+
 	rwsem_set_reader_owned(sem);
 	__downgrade_write(sem);
 }
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index da6c9a34f62f..39f56c870051 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work)
 
 	if (mtx->flags & TEST_MTX_TRY) {
 		while (!ww_mutex_trylock(&mtx->mutex))
-			cpu_relax();
+			cond_resched();
 	} else {
 		ww_mutex_lock(&mtx->mutex, NULL);
 	}
@@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags)
 				ret = -EINVAL;
 				break;
 			}
-			cpu_relax();
+			cond_resched();
 		} while (time_before(jiffies, timeout));
 	} else {
 		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
@@ -353,8 +353,8 @@ static int test_cycle(unsigned int ncpus)
 struct stress {
 	struct work_struct work;
 	struct ww_mutex *locks;
+	unsigned long timeout;
 	int nlocks;
-	int nloops;
 };
 
 static int *get_random_order(int count)
@@ -398,12 +398,11 @@ static void stress_inorder_work(struct work_struct *work)
 	if (!order)
 		return;
 
-	ww_acquire_init(&ctx, &ww_class);
-
 	do {
 		int contended = -1;
 		int n, err;
 
+		ww_acquire_init(&ctx, &ww_class);
 retry:
 		err = 0;
 		for (n = 0; n < nlocks; n++) {
@@ -433,9 +432,9 @@ retry:
 				    __func__, err);
 			break;
 		}
-	} while (--stress->nloops);
 
-	ww_acquire_fini(&ctx);
+		ww_acquire_fini(&ctx);
+	} while (!time_after(jiffies, stress->timeout));
 
 	kfree(order);
 	kfree(stress);
@@ -470,9 +469,9 @@ static void stress_reorder_work(struct work_struct *work)
 	kfree(order);
 	order = NULL;
 
-	ww_acquire_init(&ctx, &ww_class);
-
 	do {
+		ww_acquire_init(&ctx, &ww_class);
+
 		list_for_each_entry(ll, &locks, link) {
 			err = ww_mutex_lock(ll->lock, &ctx);
 			if (!err)
@@ -495,9 +494,9 @@ static void stress_reorder_work(struct work_struct *work)
 		dummy_load(stress);
 		list_for_each_entry(ll, &locks, link)
 			ww_mutex_unlock(ll->lock);
-	} while (--stress->nloops);
 
-	ww_acquire_fini(&ctx);
+		ww_acquire_fini(&ctx);
+	} while (!time_after(jiffies, stress->timeout));
 
 out:
 	list_for_each_entry_safe(ll, ln, &locks, link)
@@ -523,7 +522,7 @@ static void stress_one_work(struct work_struct *work)
 				    __func__, err);
 			break;
 		}
-	} while (--stress->nloops);
+	} while (!time_after(jiffies, stress->timeout));
 
 	kfree(stress);
 }
@@ -533,7 +532,7 @@ static void stress_one_work(struct work_struct *work)
 #define STRESS_ONE BIT(2)
 #define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE)
 
-static int stress(int nlocks, int nthreads, int nloops, unsigned int flags)
+static int stress(int nlocks, int nthreads, unsigned int flags)
 {
 	struct ww_mutex *locks;
 	int n;
@@ -575,7 +574,7 @@ static int stress(int nlocks, int nthreads, int nloops, unsigned int flags)
 		INIT_WORK(&stress->work, fn);
 		stress->locks = locks;
 		stress->nlocks = nlocks;
-		stress->nloops = nloops;
+		stress->timeout = jiffies + 2*HZ;
 
 		queue_work(wq, &stress->work);
 		nthreads--;
@@ -619,15 +618,15 @@ static int __init test_ww_mutex_init(void)
 	if (ret)
 		return ret;
 
-	ret = stress(16, 2*ncpus, 1<<10, STRESS_INORDER);
+	ret = stress(16, 2*ncpus, STRESS_INORDER);
 	if (ret)
 		return ret;
 
-	ret = stress(16, 2*ncpus, 1<<10, STRESS_REORDER);
+	ret = stress(16, 2*ncpus, STRESS_REORDER);
 	if (ret)
 		return ret;
 
-	ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+	ret = stress(4095, hweight32(STRESS_ALL)*ncpus, STRESS_ALL);
 	if (ret)
 		return ret;
 
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 06123234f118..23a6483c3666 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -182,18 +182,6 @@ struct page_map {
 	struct vmem_altmap altmap;
 };
 
-void get_zone_device_page(struct page *page)
-{
-	percpu_ref_get(page->pgmap->ref);
-}
-EXPORT_SYMBOL(get_zone_device_page);
-
-void put_zone_device_page(struct page *page)
-{
-	put_dev_pagemap(page->pgmap);
-}
-EXPORT_SYMBOL(put_zone_device_page);
-
 static void pgmap_radix_release(struct resource *res)
 {
 	resource_size_t key, align_start, align_size, align_end;
@@ -237,6 +225,10 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	struct resource *res = &page_map->res;
 	resource_size_t align_start, align_size;
 	struct dev_pagemap *pgmap = &page_map->pgmap;
+	unsigned long pfn;
+
+	for_each_device_pfn(pfn, page_map)
+		put_page(pfn_to_page(pfn));
 
 	if (percpu_ref_tryget_live(pgmap->ref)) {
 		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
@@ -247,11 +239,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 
-	lock_device_hotplug();
 	mem_hotplug_begin();
 	arch_remove_memory(align_start, align_size);
 	mem_hotplug_done();
-	unlock_device_hotplug();
 
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
@@ -279,7 +269,10 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
  *
  * Notes:
  * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
- *    (or devm release event).
+ *    (or devm release event). The expected order of events is that @ref has
+ *    been through percpu_ref_kill() before devm_memremap_pages_release(). The
+ *    wait for the completion of all references being dropped and
+ *    percpu_ref_exit() must occur after devm_memremap_pages_release().
  *
  * 2/ @res is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
@@ -364,11 +357,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (error)
 		goto err_pfn_remap;
 
-	lock_device_hotplug();
 	mem_hotplug_begin();
 	error = arch_add_memory(nid, align_start, align_size, true);
 	mem_hotplug_done();
-	unlock_device_hotplug();
 	if (error)
 		goto err_add_memory;
 
@@ -383,6 +374,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		 */
 		list_del(&page->lru);
 		page->pgmap = pgmap;
+		percpu_ref_get(ref);
 	}
 	devres_add(dev, page_map);
 	return __va(res->start);
diff --git a/kernel/module.c b/kernel/module.c
index 7eba6dea4f41..6d9988031c5b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -665,16 +665,7 @@ static void percpu_modcopy(struct module *mod,
 		memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
 }
 
-/**
- * is_module_percpu_address - test whether address is from module static percpu
- * @addr: address to test
- *
- * Test whether @addr belongs to module static percpu area.
- *
- * RETURNS:
- * %true if @addr is from module static percpu area
- */
-bool is_module_percpu_address(unsigned long addr)
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
 {
 	struct module *mod;
 	unsigned int cpu;
@@ -688,9 +679,15 @@ bool is_module_percpu_address(unsigned long addr)
 			continue;
 		for_each_possible_cpu(cpu) {
 			void *start = per_cpu_ptr(mod->percpu, cpu);
-
-			if ((void *)addr >= start &&
-			    (void *)addr < start + mod->percpu_size) {
+			void *va = (void *)addr;
+
+			if (va >= start && va < start + mod->percpu_size) {
+				if (can_addr) {
+					*can_addr = (unsigned long) (va - start);
+					*can_addr += (unsigned long)
+						per_cpu_ptr(mod->percpu,
+							    get_boot_cpu_id());
+				}
 				preempt_enable();
 				return true;
 			}
@@ -701,6 +698,20 @@ bool is_module_percpu_address(unsigned long addr)
 	return false;
 }
 
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+	return __is_module_percpu_address(addr, NULL);
+}
+
 #else /* ... !CONFIG_SMP */
 
 static inline void __percpu *mod_percpu(struct module *mod)
@@ -732,6 +743,11 @@ bool is_module_percpu_address(unsigned long addr)
 	return false;
 }
 
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 #define MODINFO_ATTR(field)	\
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 782102e59eed..f6c5d330059a 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/syscalls.h>
 #include <linux/cgroup.h>
+#include <linux/perf_event.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
@@ -262,6 +263,8 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 		goto out;
 	}
 	switch_task_namespaces(tsk, new_nsproxy);
+
+	perf_event_namespaces(tsk);
 out:
 	fput(file);
 	return err;
diff --git a/kernel/padata.c b/kernel/padata.c
index 05316c9f32da..ac8f1e524836 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -154,8 +154,6 @@ EXPORT_SYMBOL(padata_do_parallel);
  * A pointer to the control struct of the next object that needs
  * serialization, if present in one of the percpu reorder queues.
  *
- * NULL, if all percpu reorder queues are empty.
- *
  * -EINPROGRESS, if the next object that needs serialization will
  *  be parallel processed by another cpu and is not yet present in
  *  the cpu's reorder queue.
@@ -182,23 +180,22 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
 	cpu = padata_index_to_cpu(pd, next_index);
 	next_queue = per_cpu_ptr(pd->pqueue, cpu);
 
-	padata = NULL;
-
 	reorder = &next_queue->reorder;
 
+	spin_lock(&reorder->lock);
 	if (!list_empty(&reorder->list)) {
 		padata = list_entry(reorder->list.next,
 				    struct padata_priv, list);
 
-		spin_lock(&reorder->lock);
 		list_del_init(&padata->list);
 		atomic_dec(&pd->reorder_objects);
-		spin_unlock(&reorder->lock);
 
 		pd->processed++;
 
+		spin_unlock(&reorder->lock);
 		goto out;
 	}
+	spin_unlock(&reorder->lock);
 
 	if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
 		padata = ERR_PTR(-ENODATA);
@@ -234,12 +231,11 @@ static void padata_reorder(struct parallel_data *pd)
 		padata = padata_get_next(pd);
 
 		/*
-		 * All reorder queues are empty, or the next object that needs
-		 * serialization is parallel processed by another cpu and is
-		 * still on it's way to the cpu's reorder queue, nothing to
-		 * do for now.
+		 * If the next object that needs serialization is parallel
+		 * processed by another cpu and is still on it's way to the
+		 * cpu's reorder queue, nothing to do for now.
 		 */
-		if (!padata || PTR_ERR(padata) == -EINPROGRESS)
+		if (PTR_ERR(padata) == -EINPROGRESS)
 			break;
 
 		/*
@@ -353,7 +349,7 @@ static int padata_setup_cpumasks(struct parallel_data *pd,
 
 	cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask);
 	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
-		free_cpumask_var(pd->cpumask.cbcpu);
+		free_cpumask_var(pd->cpumask.pcpu);
 		return -ENOMEM;
 	}
 
diff --git a/kernel/params.c b/kernel/params.c
index a6d6149c0fe6..60b2d8101355 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -160,58 +160,6 @@ static int parse_one(char *param,
 	return -ENOENT;
 }
 
-/* You can use " around spaces, but can't escape ". */
-/* Hyphens and underscores equivalent in parameter names. */
-static char *next_arg(char *args, char **param, char **val)
-{
-	unsigned int i, equals = 0;
-	int in_quote = 0, quoted = 0;
-	char *next;
-
-	if (*args == '"') {
-		args++;
-		in_quote = 1;
-		quoted = 1;
-	}
-
-	for (i = 0; args[i]; i++) {
-		if (isspace(args[i]) && !in_quote)
-			break;
-		if (equals == 0) {
-			if (args[i] == '=')
-				equals = i;
-		}
-		if (args[i] == '"')
-			in_quote = !in_quote;
-	}
-
-	*param = args;
-	if (!equals)
-		*val = NULL;
-	else {
-		args[equals] = '\0';
-		*val = args + equals + 1;
-
-		/* Don't include quotes in value. */
-		if (**val == '"') {
-			(*val)++;
-			if (args[i-1] == '"')
-				args[i-1] = '\0';
-		}
-	}
-	if (quoted && args[i-1] == '"')
-		args[i-1] = '\0';
-
-	if (args[i]) {
-		args[i] = '\0';
-		next = args + i + 1;
-	} else
-		next = args + i;
-
-	/* Chew up trailing spaces. */
-	return skip_spaces(next);
-}
-
 /* Args looks like "foo=bar,bar2 baz=fuz wiz". */
 char *parse_args(const char *doing,
 		 char *args,
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0af928712174..266ddcc1d8bb 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -184,11 +184,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task)
 
 	WARN_ON(!task->ptrace || task->parent != current);
 
+	/*
+	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+	 * Recheck state under the lock to close this race.
+	 */
 	spin_lock_irq(&task->sighand->siglock);
-	if (__fatal_signal_pending(task))
-		wake_up_state(task, __TASK_TRACED);
-	else
-		task->state = TASK_TRACED;
+	if (task->state == __TASK_TRACED) {
+		if (__fatal_signal_pending(task))
+			wake_up_state(task, __TASK_TRACED);
+		else
+			task->state = TASK_TRACED;
+	}
 	spin_unlock_irq(&task->sighand->siglock);
 }
 
diff --git a/kernel/relay.c b/kernel/relay.c
index 0e413d9eec8a..39a9dfc69486 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1212,7 +1212,6 @@ static ssize_t subbuf_splice_actor(struct file *in,
 		.nr_pages = 0,
 		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.partial = partial,
-		.flags = flags,
 		.ops = &relay_pipe_buf_ops,
 		.spd_release = relay_page_release,
 	};
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index a08795e21628..00a45c45beca 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -96,10 +96,10 @@ static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
 static int __sched_clock_stable_early = 1;
 
 /*
- * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset
  */
-static __read_mostly u64 raw_offset;
-static __read_mostly u64 gtod_offset;
+__read_mostly u64 __sched_clock_offset;
+static __read_mostly u64 __gtod_offset;
 
 struct sched_clock_data {
 	u64			tick_raw;
@@ -131,17 +131,24 @@ static void __set_sched_clock_stable(void)
 	/*
 	 * Attempt to make the (initial) unstable->stable transition continuous.
 	 */
-	raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
+	__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
 
 	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
-			scd->tick_gtod, gtod_offset,
-			scd->tick_raw,  raw_offset);
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
 
 	static_branch_enable(&__sched_clock_stable);
 	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
-static void __clear_sched_clock_stable(struct work_struct *work)
+static void __sched_clock_work(struct work_struct *work)
+{
+	static_branch_disable(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __sched_clock_work);
+
+static void __clear_sched_clock_stable(void)
 {
 	struct sched_clock_data *scd = this_scd();
 
@@ -154,17 +161,17 @@ static void __clear_sched_clock_stable(struct work_struct *work)
 	 *
 	 * Still do what we can.
 	 */
-	gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod);
 
 	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
-			scd->tick_gtod, gtod_offset,
-			scd->tick_raw,  raw_offset);
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
 
-	static_branch_disable(&__sched_clock_stable);
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-}
 
-static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+	if (sched_clock_stable())
+		schedule_work(&sched_clock_work);
+}
 
 void clear_sched_clock_stable(void)
 {
@@ -173,7 +180,7 @@ void clear_sched_clock_stable(void)
 	smp_mb(); /* matches sched_clock_init_late() */
 
 	if (sched_clock_running == 2)
-		schedule_work(&sched_clock_work);
+		__clear_sched_clock_stable();
 }
 
 void sched_clock_init_late(void)
@@ -214,7 +221,7 @@ static inline u64 wrap_max(u64 x, u64 y)
  */
 static u64 sched_clock_local(struct sched_clock_data *scd)
 {
-	u64 now, clock, old_clock, min_clock, max_clock;
+	u64 now, clock, old_clock, min_clock, max_clock, gtod;
 	s64 delta;
 
 again:
@@ -231,9 +238,10 @@ again:
 	 *		      scd->tick_gtod + TICK_NSEC);
 	 */
 
-	clock = scd->tick_gtod + gtod_offset + delta;
-	min_clock = wrap_max(scd->tick_gtod, old_clock);
-	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
+	gtod = scd->tick_gtod + __gtod_offset;
+	clock = gtod + delta;
+	min_clock = wrap_max(gtod, old_clock);
+	max_clock = wrap_max(old_clock, gtod + TICK_NSEC);
 
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
@@ -317,7 +325,7 @@ u64 sched_clock_cpu(int cpu)
 	u64 clock;
 
 	if (sched_clock_stable())
-		return sched_clock() + raw_offset;
+		return sched_clock() + __sched_clock_offset;
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 956383844116..c51147a1204c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -86,21 +86,6 @@ int sysctl_sched_rt_runtime = 950000;
 cpumask_var_t cpu_isolated_map;
 
 /*
- * this_rq_lock - lock this runqueue and disable interrupts.
- */
-static struct rq *this_rq_lock(void)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	local_irq_disable();
-	rq = this_rq();
-	raw_spin_lock(&rq->lock);
-
-	return rq;
-}
-
-/*
  * __task_rq_lock - lock the rq @p resides on.
  */
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -233,8 +218,11 @@ void update_rq_clock(struct rq *rq)
 		return;
 
 #ifdef CONFIG_SCHED_DEBUG
+	if (sched_feat(WARN_DOUBLE_CLOCK))
+		SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
 	rq->clock_update_flags |= RQCF_UPDATED;
 #endif
+
 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
 	if (delta < 0)
 		return;
@@ -261,13 +249,14 @@ static void hrtick_clear(struct rq *rq)
 static enum hrtimer_restart hrtick(struct hrtimer *timer)
 {
 	struct rq *rq = container_of(timer, struct rq, hrtick_timer);
+	struct rq_flags rf;
 
 	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 
 	return HRTIMER_NORESTART;
 }
@@ -287,11 +276,12 @@ static void __hrtick_restart(struct rq *rq)
 static void __hrtick_start(void *arg)
 {
 	struct rq *rq = arg;
+	struct rq_flags rf;
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	__hrtick_restart(rq);
 	rq->hrtick_csd_pending = 0;
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
@@ -762,17 +752,23 @@ static void set_load_weight(struct task_struct *p)
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_rq_clock(rq);
+	if (!(flags & ENQUEUE_NOCLOCK))
+		update_rq_clock(rq);
+
 	if (!(flags & ENQUEUE_RESTORE))
 		sched_info_queued(rq, p);
+
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
 static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_rq_clock(rq);
+	if (!(flags & DEQUEUE_NOCLOCK))
+		update_rq_clock(rq);
+
 	if (!(flags & DEQUEUE_SAVE))
 		sched_info_dequeued(rq, p);
+
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
@@ -946,18 +942,19 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
  *
  * Returns (locked) new rq. Old rq's lock is released.
  */
-static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
+static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
+				   struct task_struct *p, int new_cpu)
 {
 	lockdep_assert_held(&rq->lock);
 
 	p->on_rq = TASK_ON_RQ_MIGRATING;
-	dequeue_task(rq, p, 0);
+	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, rf);
 
 	rq = cpu_rq(new_cpu);
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
 	enqueue_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -980,7 +977,8 @@ struct migration_arg {
  * So we race with normal scheduler movements, but that's OK, as long
  * as the task is no longer on this CPU.
  */
-static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
+static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
+				 struct task_struct *p, int dest_cpu)
 {
 	if (unlikely(!cpu_active(dest_cpu)))
 		return rq;
@@ -989,7 +987,8 @@ static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_
 	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
 		return rq;
 
-	rq = move_queued_task(rq, p, dest_cpu);
+	update_rq_clock(rq);
+	rq = move_queued_task(rq, rf, p, dest_cpu);
 
 	return rq;
 }
@@ -1004,6 +1003,7 @@ static int migration_cpu_stop(void *data)
 	struct migration_arg *arg = data;
 	struct task_struct *p = arg->task;
 	struct rq *rq = this_rq();
+	struct rq_flags rf;
 
 	/*
 	 * The original target CPU might have gone down and we might
@@ -1018,7 +1018,7 @@ static int migration_cpu_stop(void *data)
 	sched_ttwu_pending();
 
 	raw_spin_lock(&p->pi_lock);
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	/*
 	 * If task_rq(p) != rq, it cannot be migrated here, because we're
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
@@ -1026,11 +1026,11 @@ static int migration_cpu_stop(void *data)
 	 */
 	if (task_rq(p) == rq) {
 		if (task_on_rq_queued(p))
-			rq = __migrate_task(rq, p, arg->dest_cpu);
+			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
 		else
 			p->wake_cpu = arg->dest_cpu;
 	}
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 	raw_spin_unlock(&p->pi_lock);
 
 	local_irq_enable();
@@ -1063,7 +1063,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		 * holding rq->lock.
 		 */
 		lockdep_assert_held(&rq->lock);
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	}
 	if (running)
 		put_prev_task(rq, p);
@@ -1071,7 +1071,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	p->sched_class->set_cpus_allowed(p, new_mask);
 
 	if (queued)
-		enqueue_task(rq, p, ENQUEUE_RESTORE);
+		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 	if (running)
 		set_curr_task(rq, p);
 }
@@ -1150,9 +1150,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		 * OK, since we're going to drop the lock immediately
 		 * afterwards anyway.
 		 */
-		rq_unpin_lock(rq, &rf);
-		rq = move_queued_task(rq, p, dest_cpu);
-		rq_repin_lock(rq, &rf);
+		rq = move_queued_task(rq, &rf, p, dest_cpu);
 	}
 out:
 	task_rq_unlock(rq, p, &rf);
@@ -1217,16 +1215,24 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
+		struct rq_flags srf, drf;
 
 		src_rq = task_rq(p);
 		dst_rq = cpu_rq(cpu);
 
+		rq_pin_lock(src_rq, &srf);
+		rq_pin_lock(dst_rq, &drf);
+
 		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
 		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
+
+		rq_unpin_lock(dst_rq, &drf);
+		rq_unpin_lock(src_rq, &srf);
+
 	} else {
 		/*
 		 * Task isn't running anymore; make it appear like we migrated
@@ -1680,7 +1686,7 @@ static void
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		 struct rq_flags *rf)
 {
-	int en_flags = ENQUEUE_WAKEUP;
+	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
 
 	lockdep_assert_held(&rq->lock);
 
@@ -1726,14 +1732,13 @@ void sched_ttwu_pending(void)
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
 	struct task_struct *p;
-	unsigned long flags;
 	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	rq_pin_lock(rq, &rf);
+	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
 
 	while (llist) {
 		int wake_flags = 0;
@@ -1747,8 +1752,7 @@ void sched_ttwu_pending(void)
 		ttwu_do_activate(rq, p, wake_flags, &rf);
 	}
 
-	rq_unpin_lock(rq, &rf);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 }
 
 void scheduler_ipi(void)
@@ -1806,7 +1810,7 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
 void wake_up_if_idle(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
+	struct rq_flags rf;
 
 	rcu_read_lock();
 
@@ -1816,11 +1820,11 @@ void wake_up_if_idle(int cpu)
 	if (set_nr_if_polling(rq->idle)) {
 		trace_sched_wake_idle_without_ipi(cpu);
 	} else {
-		raw_spin_lock_irqsave(&rq->lock, flags);
+		rq_lock_irqsave(rq, &rf);
 		if (is_idle_task(rq->curr))
 			smp_send_reschedule(cpu);
 		/* Else CPU is not idle, do nothing here: */
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		rq_unlock_irqrestore(rq, &rf);
 	}
 
 out:
@@ -1846,11 +1850,10 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 	}
 #endif
 
-	raw_spin_lock(&rq->lock);
-	rq_pin_lock(rq, &rf);
+	rq_lock(rq, &rf);
+	update_rq_clock(rq);
 	ttwu_do_activate(rq, p, wake_flags, &rf);
-	rq_unpin_lock(rq, &rf);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
@@ -2097,11 +2100,9 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 		 * disabled avoiding further scheduler activity on it and we've
 		 * not yet picked a replacement task.
 		 */
-		rq_unpin_lock(rq, rf);
-		raw_spin_unlock(&rq->lock);
+		rq_unlock(rq, rf);
 		raw_spin_lock(&p->pi_lock);
-		raw_spin_lock(&rq->lock);
-		rq_repin_lock(rq, rf);
+		rq_relock(rq, rf);
 	}
 
 	if (!(p->state & TASK_NORMAL))
@@ -2114,7 +2115,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 			delayacct_blkio_end();
 			atomic_dec(&rq->nr_iowait);
 		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
 	}
 
 	ttwu_do_wakeup(rq, p, 0, rf);
@@ -2555,7 +2556,7 @@ void wake_up_new_task(struct task_struct *p)
 	update_rq_clock(rq);
 	post_init_entity_util_avg(&p->se);
 
-	activate_task(rq, p, 0);
+	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
@@ -3093,15 +3094,18 @@ void scheduler_tick(void)
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *curr = rq->curr;
+	struct rq_flags rf;
 
 	sched_clock_tick();
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
+
 	update_rq_clock(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
 	cpu_load_update_active(rq);
 	calc_global_load_tick(rq);
-	raw_spin_unlock(&rq->lock);
+
+	rq_unlock(rq, &rf);
 
 	perf_event_task_tick();
 
@@ -3287,10 +3291,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *p;
 
 	/*
-	 * Optimization: we know that if all tasks are in
-	 * the fair class we can call that function directly:
+	 * Optimization: we know that if all tasks are in the fair class we can
+	 * call that function directly, but only if the @prev task wasn't of a
+	 * higher scheduling class, because otherwise those loose the
+	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+	if (likely((prev->sched_class == &idle_sched_class ||
+		    prev->sched_class == &fair_sched_class) &&
+		   rq->nr_running == rq->cfs.h_nr_running)) {
+
 		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto again;
@@ -3381,18 +3390,18 @@ static void __sched notrace __schedule(bool preempt)
 	 * done by the caller to avoid the race with signal_wake_up().
 	 */
 	smp_mb__before_spinlock();
-	raw_spin_lock(&rq->lock);
-	rq_pin_lock(rq, &rf);
+	rq_lock(rq, &rf);
 
 	/* Promote REQ to ACT */
 	rq->clock_update_flags <<= 1;
+	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
 	if (!preempt && prev->state) {
 		if (unlikely(signal_pending_state(prev->state, prev))) {
 			prev->state = TASK_RUNNING;
 		} else {
-			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
@@ -3416,9 +3425,6 @@ static void __sched notrace __schedule(bool preempt)
 		switch_count = &prev->nvcsw;
 	}
 
-	if (task_on_rq_queued(prev))
-		update_rq_clock(rq);
-
 	next = pick_next_task(rq, prev, &rf);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
@@ -3434,8 +3440,7 @@ static void __sched notrace __schedule(bool preempt)
 		rq = context_switch(rq, prev, next, &rf);
 	} else {
 		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-		rq_unpin_lock(rq, &rf);
-		raw_spin_unlock_irq(&rq->lock);
+		rq_unlock_irq(rq, &rf);
 	}
 
 	balance_callback(rq);
@@ -3666,10 +3671,25 @@ EXPORT_SYMBOL(default_wake_function);
 
 #ifdef CONFIG_RT_MUTEXES
 
+static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
+{
+	if (pi_task)
+		prio = min(prio, pi_task->prio);
+
+	return prio;
+}
+
+static inline int rt_effective_prio(struct task_struct *p, int prio)
+{
+	struct task_struct *pi_task = rt_mutex_get_top_task(p);
+
+	return __rt_effective_prio(pi_task, prio);
+}
+
 /*
  * rt_mutex_setprio - set the current priority of a task
- * @p: task
- * @prio: prio value (kernel-internal form)
+ * @p: task to boost
+ * @pi_task: donor task
  *
  * This function changes the 'effective' priority of a task. It does
  * not touch ->normal_prio like __setscheduler().
@@ -3677,17 +3697,42 @@ EXPORT_SYMBOL(default_wake_function);
  * Used by the rt_mutex code to implement priority inheritance
  * logic. Call site only calls if the priority of the task changed.
  */
-void rt_mutex_setprio(struct task_struct *p, int prio)
+void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 {
-	int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE;
+	int prio, oldprio, queued, running, queue_flag =
+		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	const struct sched_class *prev_class;
 	struct rq_flags rf;
 	struct rq *rq;
 
-	BUG_ON(prio > MAX_PRIO);
+	/* XXX used to be waiter->prio, not waiter->task->prio */
+	prio = __rt_effective_prio(pi_task, p->normal_prio);
+
+	/*
+	 * If nothing changed; bail early.
+	 */
+	if (p->pi_top_task == pi_task && prio == p->prio && !dl_prio(prio))
+		return;
 
 	rq = __task_rq_lock(p, &rf);
 	update_rq_clock(rq);
+	/*
+	 * Set under pi_lock && rq->lock, such that the value can be used under
+	 * either lock.
+	 *
+	 * Note that there is loads of tricky to make this pointer cache work
+	 * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
+	 * ensure a task is de-boosted (pi_task is set to NULL) before the
+	 * task is allowed to run again (and can exit). This ensures the pointer
+	 * points to a blocked task -- which guaratees the task is present.
+	 */
+	p->pi_top_task = pi_task;
+
+	/*
+	 * For FIFO/RR we only need to set prio, if that matches we're done.
+	 */
+	if (prio == p->prio && !dl_prio(prio))
+		goto out_unlock;
 
 	/*
 	 * Idle task boosting is a nono in general. There is one
@@ -3707,7 +3752,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		goto out_unlock;
 	}
 
-	trace_sched_pi_setprio(p, prio);
+	trace_sched_pi_setprio(p, pi_task);
 	oldprio = p->prio;
 
 	if (oldprio == prio)
@@ -3731,7 +3776,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	 *          running task
 	 */
 	if (dl_prio(prio)) {
-		struct task_struct *pi_task = rt_mutex_get_top_task(p);
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
@@ -3769,6 +3813,11 @@ out_unlock:
 	balance_callback(rq);
 	preempt_enable();
 }
+#else
+static inline int rt_effective_prio(struct task_struct *p, int prio)
+{
+	return prio;
+}
 #endif
 
 void set_user_nice(struct task_struct *p, long nice)
@@ -3800,7 +3849,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	if (running)
 		put_prev_task(rq, p);
 
@@ -3811,7 +3860,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	delta = p->prio - old_prio;
 
 	if (queued) {
-		enqueue_task(rq, p, ENQUEUE_RESTORE);
+		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -4015,10 +4064,9 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 	 * Keep a potential priority boosting if called from
 	 * sched_setscheduler().
 	 */
+	p->prio = normal_prio(p);
 	if (keep_boost)
-		p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
-	else
-		p->prio = normal_prio(p);
+		p->prio = rt_effective_prio(p, p->prio);
 
 	if (dl_prio(p->prio))
 		p->sched_class = &dl_sched_class;
@@ -4121,7 +4169,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	const struct sched_class *prev_class;
 	struct rq_flags rf;
 	int reset_on_fork;
-	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
 
 	/* May grab non-irq protected spin_locks: */
@@ -4305,7 +4353,7 @@ change:
 		 * the runqueue. This will be done when the task deboost
 		 * itself.
 		 */
-		new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
+		new_effective_prio = rt_effective_prio(p, newprio);
 		if (new_effective_prio == oldprio)
 			queue_flags &= ~DEQUEUE_MOVE;
 	}
@@ -4918,7 +4966,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
  */
 SYSCALL_DEFINE0(sched_yield)
 {
-	struct rq *rq = this_rq_lock();
+	struct rq_flags rf;
+	struct rq *rq;
+
+	local_irq_disable();
+	rq = this_rq();
+	rq_lock(rq, &rf);
 
 	schedstat_inc(rq->yld_count);
 	current->sched_class->yield_task(rq);
@@ -4927,9 +4980,8 @@ SYSCALL_DEFINE0(sched_yield)
 	 * Since we are going to call schedule() anyway, there's
 	 * no need to preempt or enable interrupts:
 	 */
-	__release(rq->lock);
-	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
-	do_raw_spin_unlock(&rq->lock);
+	preempt_disable();
+	rq_unlock(rq, &rf);
 	sched_preempt_enable_no_resched();
 
 	schedule();
@@ -5509,7 +5561,7 @@ void sched_setnuma(struct task_struct *p, int nid)
 	p->numa_preferred_nid = nid;
 
 	if (queued)
-		enqueue_task(rq, p, ENQUEUE_RESTORE);
+		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 	if (running)
 		set_curr_task(rq, p);
 	task_rq_unlock(rq, p, &rf);
@@ -5574,11 +5626,11 @@ static struct task_struct fake_task = {
  * there's no concurrency possible, we hold the required locks anyway
  * because of lock validation efforts.
  */
-static void migrate_tasks(struct rq *dead_rq)
+static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
 {
 	struct rq *rq = dead_rq;
 	struct task_struct *next, *stop = rq->stop;
-	struct rq_flags rf;
+	struct rq_flags orf = *rf;
 	int dest_cpu;
 
 	/*
@@ -5597,9 +5649,7 @@ static void migrate_tasks(struct rq *dead_rq)
 	 * class method both need to have an up-to-date
 	 * value of rq->clock[_task]
 	 */
-	rq_pin_lock(rq, &rf);
 	update_rq_clock(rq);
-	rq_unpin_lock(rq, &rf);
 
 	for (;;) {
 		/*
@@ -5612,8 +5662,7 @@ static void migrate_tasks(struct rq *dead_rq)
 		/*
 		 * pick_next_task() assumes pinned rq->lock:
 		 */
-		rq_repin_lock(rq, &rf);
-		next = pick_next_task(rq, &fake_task, &rf);
+		next = pick_next_task(rq, &fake_task, rf);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
@@ -5626,10 +5675,9 @@ static void migrate_tasks(struct rq *dead_rq)
 		 * because !cpu_active at this point, which means load-balance
 		 * will not interfere. Also, stop-machine.
 		 */
-		rq_unpin_lock(rq, &rf);
-		raw_spin_unlock(&rq->lock);
+		rq_unlock(rq, rf);
 		raw_spin_lock(&next->pi_lock);
-		raw_spin_lock(&rq->lock);
+		rq_relock(rq, rf);
 
 		/*
 		 * Since we're inside stop-machine, _nothing_ should have
@@ -5643,12 +5691,12 @@ static void migrate_tasks(struct rq *dead_rq)
 
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
-
-		rq = __migrate_task(rq, next, dest_cpu);
+		rq = __migrate_task(rq, rf, next, dest_cpu);
 		if (rq != dead_rq) {
-			raw_spin_unlock(&rq->lock);
+			rq_unlock(rq, rf);
 			rq = dead_rq;
-			raw_spin_lock(&rq->lock);
+			*rf = orf;
+			rq_relock(rq, rf);
 		}
 		raw_spin_unlock(&next->pi_lock);
 	}
@@ -5727,7 +5775,7 @@ static void cpuset_cpu_active(void)
 		 * cpuset configurations.
 		 */
 	}
-	cpuset_update_active_cpus(true);
+	cpuset_update_active_cpus();
 }
 
 static int cpuset_cpu_inactive(unsigned int cpu)
@@ -5750,7 +5798,7 @@ static int cpuset_cpu_inactive(unsigned int cpu)
 
 		if (overflow)
 			return -EBUSY;
-		cpuset_update_active_cpus(false);
+		cpuset_update_active_cpus();
 	} else {
 		num_cpus_frozen++;
 		partition_sched_domains(1, NULL, NULL);
@@ -5761,7 +5809,7 @@ static int cpuset_cpu_inactive(unsigned int cpu)
 int sched_cpu_activate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
+	struct rq_flags rf;
 
 	set_cpu_active(cpu, true);
 
@@ -5779,12 +5827,12 @@ int sched_cpu_activate(unsigned int cpu)
 	 * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
 	 *    domains.
 	 */
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_online(rq);
 	}
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 
 	update_max_interval();
 
@@ -5842,18 +5890,20 @@ int sched_cpu_starting(unsigned int cpu)
 int sched_cpu_dying(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
+	struct rq_flags rf;
 
 	/* Handle pending wakeups and then migrate everything off */
 	sched_ttwu_pending();
-	raw_spin_lock_irqsave(&rq->lock, flags);
+
+	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_offline(rq);
 	}
-	migrate_tasks(rq);
+	migrate_tasks(rq, &rf);
 	BUG_ON(rq->nr_running != 1);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
+
 	calc_load_migrate(rq);
 	update_max_interval();
 	nohz_balance_exit_idle(cpu);
@@ -6407,7 +6457,8 @@ static void sched_change_group(struct task_struct *tsk, int type)
  */
 void sched_move_task(struct task_struct *tsk)
 {
-	int queued, running;
+	int queued, running, queue_flags =
+		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -6418,14 +6469,14 @@ void sched_move_task(struct task_struct *tsk)
 	queued = task_on_rq_queued(tsk);
 
 	if (queued)
-		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
+		dequeue_task(rq, tsk, queue_flags);
 	if (running)
 		put_prev_task(rq, tsk);
 
 	sched_change_group(tsk, TASK_MOVE_GROUP);
 
 	if (queued)
-		enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
+		enqueue_task(rq, tsk, queue_flags);
 	if (running)
 		set_curr_task(rq, tsk);
 
@@ -7003,14 +7054,15 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	for_each_online_cpu(i) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
 		struct rq *rq = cfs_rq->rq;
+		struct rq_flags rf;
 
-		raw_spin_lock_irq(&rq->lock);
+		rq_lock_irq(rq, &rf);
 		cfs_rq->runtime_enabled = runtime_enabled;
 		cfs_rq->runtime_remaining = 0;
 
 		if (cfs_rq->throttled)
 			unthrottle_cfs_rq(cfs_rq);
-		raw_spin_unlock_irq(&rq->lock);
+		rq_unlock_irq(rq, &rf);
 	}
 	if (runtime_was_enabled && !runtime_enabled)
 		cfs_bandwidth_usage_dec();
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 8f8de3d4d6b7..76877a62b5fa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -36,6 +36,7 @@ struct sugov_policy {
 	u64 last_freq_update_time;
 	s64 freq_update_delay_ns;
 	unsigned int next_freq;
+	unsigned int cached_raw_freq;
 
 	/* The next fields are only needed if fast switch cannot be used. */
 	struct irq_work irq_work;
@@ -52,7 +53,6 @@ struct sugov_cpu {
 	struct update_util_data update_util;
 	struct sugov_policy *sg_policy;
 
-	unsigned int cached_raw_freq;
 	unsigned long iowait_boost;
 	unsigned long iowait_boost_max;
 	u64 last_update;
@@ -61,6 +61,11 @@ struct sugov_cpu {
 	unsigned long util;
 	unsigned long max;
 	unsigned int flags;
+
+	/* The field below is for single-CPU policies only. */
+#ifdef CONFIG_NO_HZ_COMMON
+	unsigned long saved_idle_calls;
+#endif
 };
 
 static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
@@ -93,22 +98,23 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 {
 	struct cpufreq_policy *policy = sg_policy->policy;
 
+	if (sg_policy->next_freq == next_freq)
+		return;
+
+	if (sg_policy->next_freq > next_freq)
+		next_freq = (sg_policy->next_freq + next_freq) >> 1;
+
+	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
 
 	if (policy->fast_switch_enabled) {
-		if (sg_policy->next_freq == next_freq) {
-			trace_cpu_frequency(policy->cur, smp_processor_id());
-			return;
-		}
-		sg_policy->next_freq = next_freq;
 		next_freq = cpufreq_driver_fast_switch(policy, next_freq);
 		if (next_freq == CPUFREQ_ENTRY_INVALID)
 			return;
 
 		policy->cur = next_freq;
 		trace_cpu_frequency(next_freq, smp_processor_id());
-	} else if (sg_policy->next_freq != next_freq) {
-		sg_policy->next_freq = next_freq;
+	} else {
 		sg_policy->work_in_progress = true;
 		irq_work_queue(&sg_policy->irq_work);
 	}
@@ -116,7 +122,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 
 /**
  * get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
  * @util: Current CPU utilization.
  * @max: CPU capacity.
  *
@@ -136,19 +142,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
  * next_freq (as calculated above) is returned, subject to policy min/max and
  * cpufreq driver limitations.
  */
-static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
-				  unsigned long max)
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+				  unsigned long util, unsigned long max)
 {
-	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
 	unsigned int freq = arch_scale_freq_invariant() ?
 				policy->cpuinfo.max_freq : policy->cur;
 
 	freq = (freq + (freq >> 2)) * util / max;
 
-	if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+	if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
 		return sg_policy->next_freq;
-	sg_cpu->cached_raw_freq = freq;
+	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
@@ -193,6 +198,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
 	sg_cpu->iowait_boost >>= 1;
 }
 
+#ifdef CONFIG_NO_HZ_COMMON
+static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+{
+	unsigned long idle_calls = tick_nohz_get_idle_calls();
+	bool ret = idle_calls == sg_cpu->saved_idle_calls;
+
+	sg_cpu->saved_idle_calls = idle_calls;
+	return ret;
+}
+#else
+static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+#endif /* CONFIG_NO_HZ_COMMON */
+
 static void sugov_update_single(struct update_util_data *hook, u64 time,
 				unsigned int flags)
 {
@@ -201,6 +219,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	struct cpufreq_policy *policy = sg_policy->policy;
 	unsigned long util, max;
 	unsigned int next_f;
+	bool busy;
 
 	sugov_set_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
@@ -208,40 +227,37 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
+	busy = sugov_cpu_is_busy(sg_cpu);
+
 	if (flags & SCHED_CPUFREQ_RT_DL) {
 		next_f = policy->cpuinfo.max_freq;
 	} else {
 		sugov_get_util(&util, &max);
 		sugov_iowait_boost(sg_cpu, &util, &max);
-		next_f = get_next_freq(sg_cpu, util, max);
+		next_f = get_next_freq(sg_policy, util, max);
+		/*
+		 * Do not reduce the frequency if the CPU has not been idle
+		 * recently, as the reduction is likely to be premature then.
+		 */
+		if (busy && next_f < sg_policy->next_freq)
+			next_f = sg_policy->next_freq;
 	}
 	sugov_update_commit(sg_policy, time, next_f);
 }
 
-static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
-					   unsigned long util, unsigned long max,
-					   unsigned int flags)
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned int max_f = policy->cpuinfo.max_freq;
 	u64 last_freq_update_time = sg_policy->last_freq_update_time;
+	unsigned long util = 0, max = 1;
 	unsigned int j;
 
-	if (flags & SCHED_CPUFREQ_RT_DL)
-		return max_f;
-
-	sugov_iowait_boost(sg_cpu, &util, &max);
-
 	for_each_cpu(j, policy->cpus) {
-		struct sugov_cpu *j_sg_cpu;
+		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 		s64 delta_ns;
 
-		if (j == smp_processor_id())
-			continue;
-
-		j_sg_cpu = &per_cpu(sugov_cpu, j);
 		/*
 		 * If the CPU utilization was last updated before the previous
 		 * frequency update and the time elapsed between the last update
@@ -255,7 +271,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 			continue;
 		}
 		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
-			return max_f;
+			return policy->cpuinfo.max_freq;
 
 		j_util = j_sg_cpu->util;
 		j_max = j_sg_cpu->max;
@@ -267,7 +283,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 		sugov_iowait_boost(j_sg_cpu, &util, &max);
 	}
 
-	return get_next_freq(sg_cpu, util, max);
+	return get_next_freq(sg_policy, util, max);
 }
 
 static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -290,7 +306,11 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
 	sg_cpu->last_update = time;
 
 	if (sugov_should_update_freq(sg_policy, time)) {
-		next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
+		if (flags & SCHED_CPUFREQ_RT_DL)
+			next_f = sg_policy->policy->cpuinfo.max_freq;
+		else
+			next_f = sugov_next_freq_shared(sg_cpu);
+
 		sugov_update_commit(sg_policy, time, next_f);
 	}
 
@@ -474,7 +494,6 @@ static int sugov_init(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy;
 	struct sugov_tunables *tunables;
-	unsigned int lat;
 	int ret = 0;
 
 	/* State should be equivalent to EXIT */
@@ -513,10 +532,16 @@ static int sugov_init(struct cpufreq_policy *policy)
 		goto stop_kthread;
 	}
 
-	tunables->rate_limit_us = LATENCY_MULTIPLIER;
-	lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
-	if (lat)
-		tunables->rate_limit_us *= lat;
+	if (policy->transition_delay_us) {
+		tunables->rate_limit_us = policy->transition_delay_us;
+	} else {
+		unsigned int lat;
+
+		tunables->rate_limit_us = LATENCY_MULTIPLIER;
+		lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+		if (lat)
+			tunables->rate_limit_us *= lat;
+	}
 
 	policy->governor_data = sg_policy;
 	sg_policy->tunables = tunables;
@@ -580,25 +605,19 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->next_freq = UINT_MAX;
 	sg_policy->work_in_progress = false;
 	sg_policy->need_freq_update = false;
+	sg_policy->cached_raw_freq = 0;
 
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
+		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->sg_policy = sg_policy;
-		if (policy_is_shared(policy)) {
-			sg_cpu->util = 0;
-			sg_cpu->max = 0;
-			sg_cpu->flags = SCHED_CPUFREQ_RT;
-			sg_cpu->last_update = 0;
-			sg_cpu->cached_raw_freq = 0;
-			sg_cpu->iowait_boost = 0;
-			sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
-			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-						     sugov_update_shared);
-		} else {
-			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-						     sugov_update_single);
-		}
+		sg_cpu->flags = SCHED_CPUFREQ_RT;
+		sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
+		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+					     policy_is_shared(policy) ?
+							sugov_update_shared :
+							sugov_update_single);
 	}
 	return 0;
 }
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f3778e2b46c8..aea3135c5d90 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -34,6 +34,18 @@ void disable_sched_clock_irqtime(void)
 	sched_clock_irqtime = 0;
 }
 
+static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
+				  enum cpu_usage_stat idx)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	u64_stats_update_begin(&irqtime->sync);
+	cpustat[idx] += delta;
+	irqtime->total += delta;
+	irqtime->tick_delta += delta;
+	u64_stats_update_end(&irqtime->sync);
+}
+
 /*
  * Called before incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
@@ -41,7 +53,6 @@ void disable_sched_clock_irqtime(void)
 void irqtime_account_irq(struct task_struct *curr)
 {
 	struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
-	u64 *cpustat = kcpustat_this_cpu->cpustat;
 	s64 delta;
 	int cpu;
 
@@ -52,22 +63,16 @@ void irqtime_account_irq(struct task_struct *curr)
 	delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
 	irqtime->irq_start_time += delta;
 
-	u64_stats_update_begin(&irqtime->sync);
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
 	 * We want to continue accounting softirq time to ksoftirqd thread
 	 * in that case, so as not to confuse scheduler with a special task
 	 * that do not consume any time, but still wants to run.
 	 */
-	if (hardirq_count()) {
-		cpustat[CPUTIME_IRQ] += delta;
-		irqtime->tick_delta += delta;
-	} else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
-		cpustat[CPUTIME_SOFTIRQ] += delta;
-		irqtime->tick_delta += delta;
-	}
-
-	u64_stats_update_end(&irqtime->sync);
+	if (hardirq_count())
+		irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+		irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
 }
 EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 99b2c33a9fbc..a2ce59015642 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  *
  * This function returns true if:
  *
- *   runtime / (deadline - t) > dl_runtime / dl_period ,
+ *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
  *
  * IOW we can't recycle current parameters.
  *
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
  * task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
  */
 static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 			       struct sched_dl_entity *pi_se, u64 t)
@@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
 		(pi_se->dl_runtime >> DL_SCALE);
 
@@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	}
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer
@@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p)
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
 	 */
-	act = ns_to_ktime(dl_se->deadline);
+	act = ns_to_ktime(dl_next_period(dl_se));
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);
@@ -638,6 +643,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
 		rf.cookie = lockdep_pin_lock(&rq->lock);
+		update_rq_clock(rq);
 
 		/*
 		 * Now that the task has been migrated to the new RQ and we
@@ -689,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 	timer->function = dl_task_timer;
 }
 
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+			return;
+		dl_se->dl_throttled = 1;
+	}
+}
+
 static
 int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 {
@@ -922,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 	__dequeue_dl_entity(dl_se);
 }
 
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_deadline < dl_se->dl_period;
+}
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -948,6 +990,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	}
 
 	/*
+	 * Check if a constrained deadline task was activated
+	 * after the deadline but before the next period.
+	 * If that is the case, the task will be throttled and
+	 * the replenishment timer will be set to the next period.
+	 */
+	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+		dl_check_constrained_dl(&p->dl);
+
+	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
 	 * its rq, the bandwidth timer callback (which clearly has not
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3e88b35ac157..a903276fcb62 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -717,18 +717,12 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
+
+#include "sched-pelt.h"
+
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
-/*
- * We choose a half-life close to 1 scheduling period.
- * Note: The tables runnable_avg_yN_inv and runnable_avg_yN_sum are
- * dependent on this value.
- */
-#define LOAD_AVG_PERIOD 32
-#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
-#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_AVG_MAX */
-
 /* Give new sched_entity start runnable values to heavy its load in infant time */
 void init_entity_runnable_average(struct sched_entity *se)
 {
@@ -2733,47 +2727,15 @@ static inline void update_cfs_shares(struct sched_entity *se)
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_SMP
-/* Precomputed fixed inverse multiplies for multiplication by y^n */
-static const u32 runnable_avg_yN_inv[] = {
-	0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
-	0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
-	0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
-	0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
-	0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
-	0x85aac367, 0x82cd8698,
-};
-
-/*
- * Precomputed \Sum y^k { 1<=k<=n }.  These are floor(true_value) to prevent
- * over-estimates when re-combining.
- */
-static const u32 runnable_avg_yN_sum[] = {
-	    0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103,
-	 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082,
-	17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371,
-};
-
-/*
- * Precomputed \Sum y^k { 1<=k<=n, where n%32=0). Values are rolled down to
- * lower integers. See Documentation/scheduler/sched-avg.txt how these
- * were generated:
- */
-static const u32 __accumulated_sum_N32[] = {
-	    0, 23371, 35056, 40899, 43820, 45281,
-	46011, 46376, 46559, 46650, 46696, 46719,
-};
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
  */
-static __always_inline u64 decay_load(u64 val, u64 n)
+static u64 decay_load(u64 val, u64 n)
 {
 	unsigned int local_n;
 
-	if (!n)
-		return val;
-	else if (unlikely(n > LOAD_AVG_PERIOD * 63))
+	if (unlikely(n > LOAD_AVG_PERIOD * 63))
 		return 0;
 
 	/* after bounds checking we can collapse to 32-bit */
@@ -2795,30 +2757,97 @@ static __always_inline u64 decay_load(u64 val, u64 n)
 	return val;
 }
 
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+	u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+	/*
+	 * c1 = d1 y^p
+	 */
+	c1 = decay_load((u64)d1, periods);
+
+	/*
+	 *            p-1
+	 * c2 = 1024 \Sum y^n
+	 *            n=1
+	 *
+	 *              inf        inf
+	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+	 *              n=0        n=p
+	 */
+	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+	return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
 /*
- * For updates fully spanning n periods, the contribution to runnable
- * average will be: \Sum 1024*y^n
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ *           d1          d2           d3
+ *           ^           ^            ^
+ *           |           |            |
+ *         |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ *                           p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ *                           n=1
  *
- * We can compute this reasonably efficiently by combining:
- *   y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for  n <PERIOD}
+ *    = u y^p +					(Step 1)
+ *
+ *                     p-1
+ *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
+ *                     n=1
  */
-static u32 __compute_runnable_contrib(u64 n)
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+	       unsigned long weight, int running, struct cfs_rq *cfs_rq)
 {
-	u32 contrib = 0;
+	unsigned long scale_freq, scale_cpu;
+	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+	u64 periods;
 
-	if (likely(n <= LOAD_AVG_PERIOD))
-		return runnable_avg_yN_sum[n];
-	else if (unlikely(n >= LOAD_AVG_MAX_N))
-		return LOAD_AVG_MAX;
+	scale_freq = arch_scale_freq_capacity(NULL, cpu);
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
 
-	/* Since n < LOAD_AVG_MAX_N, n/LOAD_AVG_PERIOD < 11 */
-	contrib = __accumulated_sum_N32[n/LOAD_AVG_PERIOD];
-	n %= LOAD_AVG_PERIOD;
-	contrib = decay_load(contrib, n);
-	return contrib + runnable_avg_yN_sum[n];
-}
+	delta += sa->period_contrib;
+	periods = delta / 1024; /* A period is 1024us (~1ms) */
 
-#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+	/*
+	 * Step 1: decay old *_sum if we crossed period boundaries.
+	 */
+	if (periods) {
+		sa->load_sum = decay_load(sa->load_sum, periods);
+		if (cfs_rq) {
+			cfs_rq->runnable_load_sum =
+				decay_load(cfs_rq->runnable_load_sum, periods);
+		}
+		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+		/*
+		 * Step 2
+		 */
+		delta %= 1024;
+		contrib = __accumulate_pelt_segments(periods,
+				1024 - sa->period_contrib, delta);
+	}
+	sa->period_contrib = delta;
+
+	contrib = cap_scale(contrib, scale_freq);
+	if (weight) {
+		sa->load_sum += weight * contrib;
+		if (cfs_rq)
+			cfs_rq->runnable_load_sum += weight * contrib;
+	}
+	if (running)
+		sa->util_sum += contrib * scale_cpu;
+
+	return periods;
+}
 
 /*
  * We can represent the historical contribution to runnable average as the
@@ -2849,13 +2878,10 @@ static u32 __compute_runnable_contrib(u64 n)
  *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
  */
 static __always_inline int
-__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
+___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		  unsigned long weight, int running, struct cfs_rq *cfs_rq)
 {
-	u64 delta, scaled_delta, periods;
-	u32 contrib;
-	unsigned int delta_w, scaled_delta_w, decayed = 0;
-	unsigned long scale_freq, scale_cpu;
+	u64 delta;
 
 	delta = now - sa->last_update_time;
 	/*
@@ -2874,83 +2900,52 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	delta >>= 10;
 	if (!delta)
 		return 0;
-	sa->last_update_time = now;
-
-	scale_freq = arch_scale_freq_capacity(NULL, cpu);
-	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
-	/* delta_w is the amount already accumulated against our next period */
-	delta_w = sa->period_contrib;
-	if (delta + delta_w >= 1024) {
-		decayed = 1;
 
-		/* how much left for next period will start over, we don't know yet */
-		sa->period_contrib = 0;
+	sa->last_update_time += delta << 10;
 
-		/*
-		 * Now that we know we're crossing a period boundary, figure
-		 * out how much from delta we need to complete the current
-		 * period and accrue it.
-		 */
-		delta_w = 1024 - delta_w;
-		scaled_delta_w = cap_scale(delta_w, scale_freq);
-		if (weight) {
-			sa->load_sum += weight * scaled_delta_w;
-			if (cfs_rq) {
-				cfs_rq->runnable_load_sum +=
-						weight * scaled_delta_w;
-			}
-		}
-		if (running)
-			sa->util_sum += scaled_delta_w * scale_cpu;
-
-		delta -= delta_w;
-
-		/* Figure out how many additional periods this update spans */
-		periods = delta / 1024;
-		delta %= 1024;
+	/*
+	 * Now we know we crossed measurement unit boundaries. The *_avg
+	 * accrues by two steps:
+	 *
+	 * Step 1: accumulate *_sum since last_update_time. If we haven't
+	 * crossed period boundaries, finish.
+	 */
+	if (!accumulate_sum(delta, cpu, sa, weight, running, cfs_rq))
+		return 0;
 
-		sa->load_sum = decay_load(sa->load_sum, periods + 1);
-		if (cfs_rq) {
-			cfs_rq->runnable_load_sum =
-				decay_load(cfs_rq->runnable_load_sum, periods + 1);
-		}
-		sa->util_sum = decay_load((u64)(sa->util_sum), periods + 1);
-
-		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
-		contrib = __compute_runnable_contrib(periods);
-		contrib = cap_scale(contrib, scale_freq);
-		if (weight) {
-			sa->load_sum += weight * contrib;
-			if (cfs_rq)
-				cfs_rq->runnable_load_sum += weight * contrib;
-		}
-		if (running)
-			sa->util_sum += contrib * scale_cpu;
+	/*
+	 * Step 2: update *_avg.
+	 */
+	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+	if (cfs_rq) {
+		cfs_rq->runnable_load_avg =
+			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
 	}
+	sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
 
-	/* Remainder of delta accrued against u_0` */
-	scaled_delta = cap_scale(delta, scale_freq);
-	if (weight) {
-		sa->load_sum += weight * scaled_delta;
-		if (cfs_rq)
-			cfs_rq->runnable_load_sum += weight * scaled_delta;
-	}
-	if (running)
-		sa->util_sum += scaled_delta * scale_cpu;
+	return 1;
+}
 
-	sa->period_contrib += delta;
+static int
+__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+	return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL);
+}
 
-	if (decayed) {
-		sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
-		if (cfs_rq) {
-			cfs_rq->runnable_load_avg =
-				div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
-		}
-		sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
-	}
+static int
+__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	return ___update_load_avg(now, cpu, &se->avg,
+				  se->on_rq * scale_load_down(se->load.weight),
+				  cfs_rq->curr == se, NULL);
+}
 
-	return decayed;
+static int
+__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+	return ___update_load_avg(now, cpu, &cfs_rq->avg,
+			scale_load_down(cfs_rq->load.weight),
+			cfs_rq->curr != NULL, cfs_rq);
 }
 
 /*
@@ -3014,6 +3009,9 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 void set_task_rq_fair(struct sched_entity *se,
 		      struct cfs_rq *prev, struct cfs_rq *next)
 {
+	u64 p_last_update_time;
+	u64 n_last_update_time;
+
 	if (!sched_feat(ATTACH_AGE_LOAD))
 		return;
 
@@ -3024,11 +3022,11 @@ void set_task_rq_fair(struct sched_entity *se,
 	 * time. This will result in the wakee task is less decayed, but giving
 	 * the wakee more load sounds not bad.
 	 */
-	if (se->avg.last_update_time && prev) {
-		u64 p_last_update_time;
-		u64 n_last_update_time;
+	if (!(se->avg.last_update_time && prev))
+		return;
 
 #ifndef CONFIG_64BIT
+	{
 		u64 p_last_update_time_copy;
 		u64 n_last_update_time_copy;
 
@@ -3043,14 +3041,13 @@ void set_task_rq_fair(struct sched_entity *se,
 
 		} while (p_last_update_time != p_last_update_time_copy ||
 			 n_last_update_time != n_last_update_time_copy);
+	}
 #else
-		p_last_update_time = prev->avg.last_update_time;
-		n_last_update_time = next->avg.last_update_time;
+	p_last_update_time = prev->avg.last_update_time;
+	n_last_update_time = next->avg.last_update_time;
 #endif
-		__update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
-				  &se->avg, 0, 0, NULL);
-		se->avg.last_update_time = n_last_update_time;
-	}
+	__update_load_avg_blocked_se(p_last_update_time, cpu_of(rq_of(prev)), se);
+	se->avg.last_update_time = n_last_update_time;
 }
 
 /* Take into account change of utilization of a child task group */
@@ -3173,6 +3170,36 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 	return 1;
 }
 
+/*
+ * Check if we need to update the load and the utilization of a blocked
+ * group_entity:
+ */
+static inline bool skip_blocked_update(struct sched_entity *se)
+{
+	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+
+	/*
+	 * If sched_entity still have not zero load or utilization, we have to
+	 * decay it:
+	 */
+	if (se->avg.load_avg || se->avg.util_avg)
+		return false;
+
+	/*
+	 * If there is a pending propagation, we have to update the load and
+	 * the utilization of the sched_entity:
+	 */
+	if (gcfs_rq->propagate_avg)
+		return false;
+
+	/*
+	 * Otherwise, the load and the utilization of the sched_entity is
+	 * already zero and there is no pending propagation, so it will be a
+	 * waste of time to try to decay it:
+	 */
+	return true;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
@@ -3265,8 +3292,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 		set_tg_cfs_propagate(cfs_rq);
 	}
 
-	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
-		scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq);
+	decayed = __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
 
 #ifndef CONFIG_64BIT
 	smp_wmb();
@@ -3298,11 +3324,8 @@ static inline void update_load_avg(struct sched_entity *se, int flags)
 	 * Track task load average for carrying it to new CPU after migrated, and
 	 * track group sched_entity load average for task_h_load calc in migration
 	 */
-	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
-		__update_load_avg(now, cpu, &se->avg,
-			  se->on_rq * scale_load_down(se->load.weight),
-			  cfs_rq->curr == se, NULL);
-	}
+	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
+		__update_load_avg_se(now, cpu, cfs_rq, se);
 
 	decayed  = update_cfs_rq_load_avg(now, cfs_rq, true);
 	decayed |= propagate_entity_load_avg(se);
@@ -3407,7 +3430,7 @@ void sync_entity_load_avg(struct sched_entity *se)
 	u64 last_update_time;
 
 	last_update_time = cfs_rq_last_update_time(cfs_rq);
-	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+	__update_load_avg_blocked_se(last_update_time, cpu_of(rq_of(cfs_rq)), se);
 }
 
 /*
@@ -4271,8 +4294,9 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
 				throttled_list) {
 		struct rq *rq = rq_of(cfs_rq);
+		struct rq_flags rf;
 
-		raw_spin_lock(&rq->lock);
+		rq_lock(rq, &rf);
 		if (!cfs_rq_throttled(cfs_rq))
 			goto next;
 
@@ -4289,7 +4313,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
 			unthrottle_cfs_rq(cfs_rq);
 
 next:
-		raw_spin_unlock(&rq->lock);
+		rq_unlock(rq, &rf);
 
 		if (!remaining)
 			break;
@@ -5097,15 +5121,16 @@ void cpu_load_update_nohz_stop(void)
 	unsigned long curr_jiffies = READ_ONCE(jiffies);
 	struct rq *this_rq = this_rq();
 	unsigned long load;
+	struct rq_flags rf;
 
 	if (curr_jiffies == this_rq->last_load_update_tick)
 		return;
 
 	load = weighted_cpuload(cpu_of(this_rq));
-	raw_spin_lock(&this_rq->lock);
+	rq_lock(this_rq, &rf);
 	update_rq_clock(this_rq);
 	cpu_load_update_nohz(this_rq, curr_jiffies, load);
-	raw_spin_unlock(&this_rq->lock);
+	rq_unlock(this_rq, &rf);
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 static inline void cpu_load_update_nohz(struct rq *this_rq,
@@ -5799,7 +5824,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if ((avg_idle / 512) < avg_cost)
+	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
 		return -1;
 
 	time = local_clock();
@@ -6769,7 +6794,7 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
 	lockdep_assert_held(&env->src_rq->lock);
 
 	p->on_rq = TASK_ON_RQ_MIGRATING;
-	deactivate_task(env->src_rq, p, 0);
+	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, env->dst_cpu);
 }
 
@@ -6902,7 +6927,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 	lockdep_assert_held(&rq->lock);
 
 	BUG_ON(task_rq(p) != rq);
-	activate_task(rq, p, 0);
+	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
@@ -6913,9 +6938,12 @@ static void attach_task(struct rq *rq, struct task_struct *p)
  */
 static void attach_one_task(struct rq *rq, struct task_struct *p)
 {
-	raw_spin_lock(&rq->lock);
+	struct rq_flags rf;
+
+	rq_lock(rq, &rf);
+	update_rq_clock(rq);
 	attach_task(rq, p);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
@@ -6926,8 +6954,10 @@ static void attach_tasks(struct lb_env *env)
 {
 	struct list_head *tasks = &env->tasks;
 	struct task_struct *p;
+	struct rq_flags rf;
 
-	raw_spin_lock(&env->dst_rq->lock);
+	rq_lock(env->dst_rq, &rf);
+	update_rq_clock(env->dst_rq);
 
 	while (!list_empty(tasks)) {
 		p = list_first_entry(tasks, struct task_struct, se.group_node);
@@ -6936,7 +6966,7 @@ static void attach_tasks(struct lb_env *env)
 		attach_task(env->dst_rq, p);
 	}
 
-	raw_spin_unlock(&env->dst_rq->lock);
+	rq_unlock(env->dst_rq, &rf);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6944,9 +6974,9 @@ static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq;
-	unsigned long flags;
+	struct rq_flags rf;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
 	/*
@@ -6954,6 +6984,8 @@ static void update_blocked_averages(int cpu)
 	 * list_add_leaf_cfs_rq() for details.
 	 */
 	for_each_leaf_cfs_rq(rq, cfs_rq) {
+		struct sched_entity *se;
+
 		/* throttled entities do not contribute to load */
 		if (throttled_hierarchy(cfs_rq))
 			continue;
@@ -6961,11 +6993,12 @@ static void update_blocked_averages(int cpu)
 		if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true))
 			update_tg_load_avg(cfs_rq, 0);
 
-		/* Propagate pending load changes to the parent */
-		if (cfs_rq->tg->se[cpu])
-			update_load_avg(cfs_rq->tg->se[cpu], 0);
+		/* Propagate pending load changes to the parent, if any: */
+		se = cfs_rq->tg->se[cpu];
+		if (se && !skip_blocked_update(se))
+			update_load_avg(se, 0);
 	}
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 }
 
 /*
@@ -7019,12 +7052,12 @@ static inline void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
-	unsigned long flags;
+	struct rq_flags rf;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 }
 
 static unsigned long task_h_load(struct task_struct *p)
@@ -7525,6 +7558,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 {
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
+	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
 	int load_idx, prefer_sibling = 0;
 	bool overload = false;
@@ -7541,7 +7575,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
 		if (local_group) {
 			sds->local = sg;
-			sgs = &sds->local_stat;
+			sgs = local;
 
 			if (env->idle != CPU_NEWLY_IDLE ||
 			    time_after_eq(jiffies, sg->sgc->next_update))
@@ -7565,8 +7599,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		 * the tasks on the system).
 		 */
 		if (prefer_sibling && sds->local &&
-		    group_has_capacity(env, &sds->local_stat) &&
-		    (sgs->sum_nr_running > 1)) {
+		    group_has_capacity(env, local) &&
+		    (sgs->sum_nr_running > local->sum_nr_running + 1)) {
 			sgs->group_no_capacity = 1;
 			sgs->group_type = group_classify(sg, sgs);
 		}
@@ -8042,7 +8076,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	struct sched_domain *sd_parent = sd->parent;
 	struct sched_group *group;
 	struct rq *busiest;
-	unsigned long flags;
+	struct rq_flags rf;
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
 
 	struct lb_env env = {
@@ -8105,7 +8139,7 @@ redo:
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
-		raw_spin_lock_irqsave(&busiest->lock, flags);
+		rq_lock_irqsave(busiest, &rf);
 		update_rq_clock(busiest);
 
 		/*
@@ -8122,14 +8156,14 @@ more_balance:
 		 * See task_rq_lock() family for the details.
 		 */
 
-		raw_spin_unlock(&busiest->lock);
+		rq_unlock(busiest, &rf);
 
 		if (cur_ld_moved) {
 			attach_tasks(&env);
 			ld_moved += cur_ld_moved;
 		}
 
-		local_irq_restore(flags);
+		local_irq_restore(rf.flags);
 
 		if (env.flags & LBF_NEED_BREAK) {
 			env.flags &= ~LBF_NEED_BREAK;
@@ -8207,6 +8241,8 @@ more_balance:
 			sd->nr_balance_failed++;
 
 		if (need_active_balance(&env)) {
+			unsigned long flags;
+
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
 			/* don't kick the active_load_balance_cpu_stop,
@@ -8444,8 +8480,9 @@ static int active_load_balance_cpu_stop(void *data)
 	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
 	struct task_struct *p = NULL;
+	struct rq_flags rf;
 
-	raw_spin_lock_irq(&busiest_rq->lock);
+	rq_lock_irq(busiest_rq, &rf);
 
 	/* make sure the requested cpu hasn't gone down in the meantime */
 	if (unlikely(busiest_cpu != smp_processor_id() ||
@@ -8496,7 +8533,7 @@ static int active_load_balance_cpu_stop(void *data)
 	rcu_read_unlock();
 out_unlock:
 	busiest_rq->active_balance = 0;
-	raw_spin_unlock(&busiest_rq->lock);
+	rq_unlock(busiest_rq, &rf);
 
 	if (p)
 		attach_one_task(target_rq, p);
@@ -8794,10 +8831,13 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 		 * do the balance.
 		 */
 		if (time_after_eq(jiffies, rq->next_balance)) {
-			raw_spin_lock_irq(&rq->lock);
+			struct rq_flags rf;
+
+			rq_lock_irq(rq, &rf);
 			update_rq_clock(rq);
 			cpu_load_update_idle(rq);
-			raw_spin_unlock_irq(&rq->lock);
+			rq_unlock_irq(rq, &rf);
+
 			rebalance_domains(rq, CPU_IDLE);
 		}
 
@@ -8988,8 +9028,9 @@ static void task_fork_fair(struct task_struct *p)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se, *curr;
 	struct rq *rq = this_rq();
+	struct rq_flags rf;
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 
 	cfs_rq = task_cfs_rq(current);
@@ -9010,7 +9051,7 @@ static void task_fork_fair(struct task_struct *p)
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
@@ -9372,7 +9413,6 @@ static DEFINE_MUTEX(shares_mutex);
 int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 {
 	int i;
-	unsigned long flags;
 
 	/*
 	 * We can't change the weight of the root cgroup.
@@ -9389,19 +9429,17 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	tg->shares = shares;
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
-		struct sched_entity *se;
+		struct sched_entity *se = tg->se[i];
+		struct rq_flags rf;
 
-		se = tg->se[i];
 		/* Propagate contribution to hierarchy */
-		raw_spin_lock_irqsave(&rq->lock, flags);
-
-		/* Possible calls to update_curr() need rq clock */
+		rq_lock_irqsave(rq, &rf);
 		update_rq_clock(rq);
 		for_each_sched_entity(se) {
 			update_load_avg(se, UPDATE_TG);
 			update_cfs_shares(se);
 		}
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		rq_unlock_irqrestore(rq, &rf);
 	}
 
 done:
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa46c2f..11192e0cb122 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -51,6 +51,18 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
  */
 SCHED_FEAT(TTWU_QUEUE, true)
 
+/*
+ * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
+ */
+SCHED_FEAT(SIS_AVG_CPU, false)
+
+/*
+ * Issue a WARN when we do multiple update_rq_clock() calls
+ * in a single rq->lock section. Default disabled because the
+ * annotations are not complete.
+ */
+SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
+
 #ifdef HAVE_RT_PUSH_IPI
 /*
  * In order to avoid a thundering herd attack of CPUs that are
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 7296b7308eca..f15fb2bdbc0d 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void)
 	 * If the folding window started, make sure we start writing in the
 	 * next idle-delta.
 	 */
-	if (!time_before(jiffies, calc_load_update))
+	if (!time_before(jiffies, READ_ONCE(calc_load_update)))
 		idx++;
 
 	return idx & 1;
@@ -202,8 +202,9 @@ void calc_load_exit_idle(void)
 	struct rq *this_rq = this_rq();
 
 	/*
-	 * If we're still before the sample window, we're done.
+	 * If we're still before the pending sample window, we're done.
 	 */
+	this_rq->calc_load_update = READ_ONCE(calc_load_update);
 	if (time_before(jiffies, this_rq->calc_load_update))
 		return;
 
@@ -212,7 +213,6 @@ void calc_load_exit_idle(void)
 	 * accounted through the nohz accounting, so skip the entire deal and
 	 * sync up for the next window.
 	 */
-	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update + 10))
 		this_rq->calc_load_update += LOAD_FREQ;
 }
@@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp,
  */
 static void calc_global_nohz(void)
 {
+	unsigned long sample_window;
 	long delta, active, n;
 
-	if (!time_before(jiffies, calc_load_update + 10)) {
+	sample_window = READ_ONCE(calc_load_update);
+	if (!time_before(jiffies, sample_window + 10)) {
 		/*
 		 * Catch-up, fold however many we are behind still
 		 */
-		delta = jiffies - calc_load_update - 10;
+		delta = jiffies - sample_window - 10;
 		n = 1 + (delta / LOAD_FREQ);
 
 		active = atomic_long_read(&calc_load_tasks);
@@ -324,7 +326,7 @@ static void calc_global_nohz(void)
 		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
 		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-		calc_load_update += n * LOAD_FREQ;
+		WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ);
 	}
 
 	/*
@@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { }
  */
 void calc_global_load(unsigned long ticks)
 {
+	unsigned long sample_window;
 	long active, delta;
 
-	if (time_before(jiffies, calc_load_update + 10))
+	sample_window = READ_ONCE(calc_load_update);
+	if (time_before(jiffies, sample_window + 10))
 		return;
 
 	/*
@@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks)
 	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
 	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
 
-	calc_load_update += LOAD_FREQ;
+	WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
 	/*
 	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 9f3e40226dec..979b7341008a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1927,6 +1927,87 @@ static int find_next_push_cpu(struct rq *rq)
 #define RT_PUSH_IPI_EXECUTING		1
 #define RT_PUSH_IPI_RESTART		2
 
+/*
+ * When a high priority task schedules out from a CPU and a lower priority
+ * task is scheduled in, a check is made to see if there's any RT tasks
+ * on other CPUs that are waiting to run because a higher priority RT task
+ * is currently running on its CPU. In this case, the CPU with multiple RT
+ * tasks queued on it (overloaded) needs to be notified that a CPU has opened
+ * up that may be able to run one of its non-running queued RT tasks.
+ *
+ * On large CPU boxes, there's the case that several CPUs could schedule
+ * a lower priority task at the same time, in which case it will look for
+ * any overloaded CPUs that it could pull a task from. To do this, the runqueue
+ * lock must be taken from that overloaded CPU. Having 10s of CPUs all fighting
+ * for a single overloaded CPU's runqueue lock can produce a large latency.
+ * (This has actually been observed on large boxes running cyclictest).
+ * Instead of taking the runqueue lock of the overloaded CPU, each of the
+ * CPUs that scheduled a lower priority task simply sends an IPI to the
+ * overloaded CPU. An IPI is much cheaper than taking an runqueue lock with
+ * lots of contention. The overloaded CPU will look to push its non-running
+ * RT task off, and if it does, it can then ignore the other IPIs coming
+ * in, and just pass those IPIs off to any other overloaded CPU.
+ *
+ * When a CPU schedules a lower priority task, it only sends an IPI to
+ * the "next" CPU that has overloaded RT tasks. This prevents IPI storms,
+ * as having 10 CPUs scheduling lower priority tasks and 10 CPUs with
+ * RT overloaded tasks, would cause 100 IPIs to go out at once.
+ *
+ * The overloaded RT CPU, when receiving an IPI, will try to push off its
+ * overloaded RT tasks and then send an IPI to the next CPU that has
+ * overloaded RT tasks. This stops when all CPUs with overloaded RT tasks
+ * have completed. Just because a CPU may have pushed off its own overloaded
+ * RT task does not mean it should stop sending the IPI around to other
+ * overloaded CPUs. There may be another RT task waiting to run on one of
+ * those CPUs that are of higher priority than the one that was just
+ * pushed.
+ *
+ * An optimization that could possibly be made is to make a CPU array similar
+ * to the cpupri array mask of all running RT tasks, but for the overloaded
+ * case, then the IPI could be sent to only the CPU with the highest priority
+ * RT task waiting, and that CPU could send off further IPIs to the CPU with
+ * the next highest waiting task. Since the overloaded case is much less likely
+ * to happen, the complexity of this implementation may not be worth it.
+ * Instead, just send an IPI around to all overloaded CPUs.
+ *
+ * The rq->rt.push_flags holds the status of the IPI that is going around.
+ * A run queue can only send out a single IPI at a time. The possible flags
+ * for rq->rt.push_flags are:
+ *
+ *    (None or zero):		No IPI is going around for the current rq
+ *    RT_PUSH_IPI_EXECUTING:	An IPI for the rq is being passed around
+ *    RT_PUSH_IPI_RESTART:	The priority of the running task for the rq
+ *				has changed, and the IPI should restart
+ *				circulating the overloaded CPUs again.
+ *
+ * rq->rt.push_cpu contains the CPU that is being sent the IPI. It is updated
+ * before sending to the next CPU.
+ *
+ * Instead of having all CPUs that schedule a lower priority task send
+ * an IPI to the same "first" CPU in the RT overload mask, they send it
+ * to the next overloaded CPU after their own CPU. This helps distribute
+ * the work when there's more than one overloaded CPU and multiple CPUs
+ * scheduling in lower priority tasks.
+ *
+ * When a rq schedules a lower priority task than what was currently
+ * running, the next CPU with overloaded RT tasks is examined first.
+ * That is, if CPU 1 and 5 are overloaded, and CPU 3 schedules a lower
+ * priority task, it will send an IPI first to CPU 5, then CPU 5 will
+ * send to CPU 1 if it is still overloaded. CPU 1 will clear the
+ * rq->rt.push_flags if RT_PUSH_IPI_RESTART is not set.
+ *
+ * The first CPU to notice IPI_RESTART is set, will clear that flag and then
+ * send an IPI to the next overloaded CPU after the rq->cpu and not the next
+ * CPU after push_cpu. That is, if CPU 1, 4 and 5 are overloaded when CPU 3
+ * schedules a lower priority task, and the IPI_RESTART gets set while the
+ * handling is being done on CPU 5, it will clear the flag and send it back to
+ * CPU 4 instead of CPU 1.
+ *
+ * Note, the above logic can be disabled by turning off the sched_feature
+ * RT_PUSH_IPI. Then the rq lock of the overloaded CPU will simply be
+ * taken by the CPU requesting a pull and the waiting RT task will be pulled
+ * by that CPU. This may be fine for machines with few CPUs.
+ */
 static void tell_cpu_to_push(struct rq *rq)
 {
 	int cpu;
diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h
new file mode 100644
index 000000000000..cd200d16529e
--- /dev/null
+++ b/kernel/sched/sched-pelt.h
@@ -0,0 +1,13 @@
+/* Generated by Documentation/scheduler/sched-pelt; do not modify. */
+
+static const u32 runnable_avg_yN_inv[] = {
+	0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
+	0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
+	0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
+	0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
+	0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
+	0x85aac367, 0x82cd8698,
+};
+
+#define LOAD_AVG_PERIOD 32
+#define LOAD_AVG_MAX 47742
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5cbf92214ad8..7808ab050599 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1331,15 +1331,17 @@ extern const u32 sched_prio_to_wmult[40];
 #define DEQUEUE_SLEEP		0x01
 #define DEQUEUE_SAVE		0x02 /* matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK		0x08 /* matches ENQUEUE_NOCLOCK */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
 #define ENQUEUE_MOVE		0x04
+#define ENQUEUE_NOCLOCK		0x08
 
-#define ENQUEUE_HEAD		0x08
-#define ENQUEUE_REPLENISH	0x10
+#define ENQUEUE_HEAD		0x10
+#define ENQUEUE_REPLENISH	0x20
 #ifdef CONFIG_SMP
-#define ENQUEUE_MIGRATED	0x20
+#define ENQUEUE_MIGRATED	0x40
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
@@ -1624,6 +1626,7 @@ static inline void sched_avg_update(struct rq *rq) { }
 
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(rq->lock);
+
 struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(p->pi_lock)
 	__acquires(rq->lock);
@@ -1645,6 +1648,62 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock_irqsave(&rq->lock, rf->flags);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock_irq(&rq->lock);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock(&rq->lock);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock(&rq->lock);
+	rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock(&rq->lock);
+}
+
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PREEMPT
 
@@ -1869,6 +1928,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
+	u64			total;
 	u64			tick_delta;
 	u64			irq_start_time;
 	struct u64_stats_sync	sync;
@@ -1876,16 +1936,20 @@ struct irqtime {
 
 DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
 
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
 static inline u64 irq_time_read(int cpu)
 {
 	struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
-	u64 *cpustat = kcpustat_cpu(cpu).cpustat;
 	unsigned int seq;
 	u64 total;
 
 	do {
 		seq = __u64_stats_fetch_begin(&irqtime->sync);
-		total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
+		total = irqtime->total;
 	} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
 
 	return total;
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4d2ea6f25568..b8c84c6dee64 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_event);
 
+/*
+ * Note! These two wait functions are entered with the
+ * wait-queue lock held (and interrupts off in the _irq
+ * case), so there is no race with testing the wakeup
+ * condition in the caller before they add the wait
+ * entry to the wake queue.
+ */
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+	if (likely(list_empty(&wait->task_list)))
+		__add_wait_queue_tail(wq, wait);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (signal_pending(current))
+		return -ERESTARTSYS;
+
+	spin_unlock(&wq->lock);
+	schedule();
+	spin_lock(&wq->lock);
+	return 0;
+}
+EXPORT_SYMBOL(do_wait_intr);
+
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+	if (likely(list_empty(&wait->task_list)))
+		__add_wait_queue_tail(wq, wait);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (signal_pending(current))
+		return -ERESTARTSYS;
+
+	spin_unlock_irq(&wq->lock);
+	schedule();
+	spin_lock_irq(&wq->lock);
+	return 0;
+}
+EXPORT_SYMBOL(do_wait_intr_irq);
+
 /**
  * finish_wait - clean up after waiting in a queue
  * @q: waitqueue waited on
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 744fa611cae0..4e09821f9d9e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -309,7 +309,7 @@ restart:
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
-	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
+	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
 asmlinkage __visible void do_softirq(void)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index acf0a5a06da7..21343d110296 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1176,6 +1176,8 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= timer_migration_handler,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 #endif
 #ifdef CONFIG_BPF_SYSCALL
@@ -2133,9 +2135,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
 	if (write) {
 		if (*negp)
 			return -EINVAL;
+		if (*lvalp > UINT_MAX)
+			return -EINVAL;
 		*valp = *lvalp;
 	} else {
 		unsigned int val = *valp;
+		*negp = false;
 		*lvalp = (unsigned long)val;
 	}
 	return 0;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index ce3a31e8eb36..5cb5b0008d97 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -541,7 +541,7 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
  *
  * Returns the granularity of underlying alarm base clock
  */
-static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
 {
 	if (!alarmtimer_get_rtcdev())
 		return -EINVAL;
@@ -558,14 +558,14 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
  *
  * Provides the underlying alarm base time.
  */
-static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
+static int alarm_clock_get(clockid_t which_clock, struct timespec64 *tp)
 {
 	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
 
 	if (!alarmtimer_get_rtcdev())
 		return -EINVAL;
 
-	*tp = ktime_to_timespec(base->gettime());
+	*tp = ktime_to_timespec64(base->gettime());
 	return 0;
 }
 
@@ -598,19 +598,19 @@ static int alarm_timer_create(struct k_itimer *new_timer)
  * Copies out the current itimerspec data
  */
 static void alarm_timer_get(struct k_itimer *timr,
-				struct itimerspec *cur_setting)
+			    struct itimerspec64 *cur_setting)
 {
 	ktime_t relative_expiry_time =
 		alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
 
 	if (ktime_to_ns(relative_expiry_time) > 0) {
-		cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+		cur_setting->it_value = ktime_to_timespec64(relative_expiry_time);
 	} else {
 		cur_setting->it_value.tv_sec = 0;
 		cur_setting->it_value.tv_nsec = 0;
 	}
 
-	cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
+	cur_setting->it_interval = ktime_to_timespec64(timr->it.alarm.interval);
 }
 
 /**
@@ -640,8 +640,8 @@ static int alarm_timer_del(struct k_itimer *timr)
  * Sets the timer to new_setting, and starts the timer.
  */
 static int alarm_timer_set(struct k_itimer *timr, int flags,
-				struct itimerspec *new_setting,
-				struct itimerspec *old_setting)
+			   struct itimerspec64 *new_setting,
+			   struct itimerspec64 *old_setting)
 {
 	ktime_t exp;
 
@@ -659,8 +659,8 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 		return TIMER_RETRY;
 
 	/* start the timer */
-	timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
-	exp = timespec_to_ktime(new_setting->it_value);
+	timr->it.alarm.interval = timespec64_to_ktime(new_setting->it_interval);
+	exp = timespec64_to_ktime(new_setting->it_value);
 	/* Convert (if necessary) to absolute time */
 	if (flags != TIMER_ABSTIME) {
 		ktime_t now;
@@ -790,13 +790,14 @@ out:
  * Handles clock_nanosleep calls against _ALARM clockids
  */
 static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *tsreq, struct timespec __user *rmtp)
+			      struct timespec64 *tsreq,
+			      struct timespec __user *rmtp)
 {
 	enum  alarmtimer_type type = clock2alarm(which_clock);
+	struct restart_block *restart;
 	struct alarm alarm;
 	ktime_t exp;
 	int ret = 0;
-	struct restart_block *restart;
 
 	if (!alarmtimer_get_rtcdev())
 		return -ENOTSUPP;
@@ -809,7 +810,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 
 	alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
 
-	exp = timespec_to_ktime(*tsreq);
+	exp = timespec64_to_ktime(*tsreq);
 	/* Convert (if necessary) to absolute time */
 	if (flags != TIMER_ABSTIME) {
 		ktime_t now = alarm_bases[type].gettime();
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 97ac0951f164..4237e0744e26 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -468,7 +468,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
-void clockevents_config(struct clock_event_device *dev, u32 freq)
+static void clockevents_config(struct clock_event_device *dev, u32 freq)
 {
 	u64 sec;
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index ec08f527d7ee..a7560123617c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1368,10 +1368,7 @@ retry:
 		    ktime_to_ns(delta));
 }
 
-/*
- * local version of hrtimer_peek_ahead_timers() called with interrupts
- * disabled.
- */
+/* called with interrupts disabled */
 static inline void __hrtimer_peek_ahead_timers(void)
 {
 	struct tick_device *td;
@@ -1506,7 +1503,7 @@ out:
 	return ret;
 }
 
-long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
+long hrtimer_nanosleep(struct timespec64 *rqtp, struct timespec __user *rmtp,
 		       const enum hrtimer_mode mode, const clockid_t clockid)
 {
 	struct restart_block *restart;
@@ -1519,7 +1516,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
-	hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
+	hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
 	if (do_nanosleep(&t, mode))
 		goto out;
 
@@ -1550,15 +1547,17 @@ out:
 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
+	struct timespec64 tu64;
 	struct timespec tu;
 
 	if (copy_from_user(&tu, rqtp, sizeof(tu)))
 		return -EFAULT;
 
-	if (!timespec_valid(&tu))
+	tu64 = timespec_to_timespec64(tu);
+	if (!timespec64_valid(&tu64))
 		return -EINVAL;
 
-	return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+	return hrtimer_nanosleep(&tu64, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 }
 
 /*
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7906b3f0c41a..497719127bf9 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second)
 	shift_hz += cycles_per_tick/2;
 	do_div(shift_hz, cycles_per_tick);
 	/* Calculate nsec_per_tick using shift_hz */
-	nsec_per_tick = (u64)TICK_NSEC << 8;
+	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
 	nsec_per_tick += (u32)shift_hz/2;
 	do_div(nsec_per_tick, (u32)shift_hz);
 
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 9cff0ab82b63..31d588d37a17 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -297,7 +297,7 @@ out:
 	return err;
 }
 
-static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+static int pc_clock_gettime(clockid_t id, struct timespec64 *ts)
 {
 	struct posix_clock_desc cd;
 	int err;
@@ -316,7 +316,7 @@ static int pc_clock_gettime(clockid_t id, struct timespec *ts)
 	return err;
 }
 
-static int pc_clock_getres(clockid_t id, struct timespec *ts)
+static int pc_clock_getres(clockid_t id, struct timespec64 *ts)
 {
 	struct posix_clock_desc cd;
 	int err;
@@ -335,7 +335,7 @@ static int pc_clock_getres(clockid_t id, struct timespec *ts)
 	return err;
 }
 
-static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
 {
 	struct posix_clock_desc cd;
 	int err;
@@ -399,7 +399,7 @@ static int pc_timer_delete(struct k_itimer *kit)
 	return err;
 }
 
-static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec64 *ts)
 {
 	clockid_t id = kit->it_clock;
 	struct posix_clock_desc cd;
@@ -414,7 +414,7 @@ static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
 }
 
 static int pc_timer_settime(struct k_itimer *kit, int flags,
-			    struct itimerspec *ts, struct itimerspec *old)
+			    struct itimerspec64 *ts, struct itimerspec64 *old)
 {
 	clockid_t id = kit->it_clock;
 	struct posix_clock_desc cd;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 4513ad16a253..949e434d3536 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -116,7 +116,7 @@ static inline u64 virt_ticks(struct task_struct *p)
 }
 
 static int
-posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
 {
 	int error = check_clock(which_clock);
 	if (!error) {
@@ -135,7 +135,7 @@ posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 }
 
 static int
-posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec64 *tp)
 {
 	/*
 	 * You can never reset a CPU clock, but we check for other errors
@@ -261,7 +261,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 
 static int posix_cpu_clock_get_task(struct task_struct *tsk,
 				    const clockid_t which_clock,
-				    struct timespec *tp)
+				    struct timespec64 *tp)
 {
 	int err = -EINVAL;
 	u64 rtn;
@@ -275,13 +275,13 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk,
 	}
 
 	if (!err)
-		*tp = ns_to_timespec(rtn);
+		*tp = ns_to_timespec64(rtn);
 
 	return err;
 }
 
 
-static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
 	int err = -EINVAL;
@@ -562,7 +562,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
 static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
-			       struct itimerspec *new, struct itimerspec *old)
+			       struct itimerspec64 *new, struct itimerspec64 *old)
 {
 	unsigned long flags;
 	struct sighand_struct *sighand;
@@ -572,7 +572,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 
 	WARN_ON_ONCE(p == NULL);
 
-	new_expires = timespec_to_ns(&new->it_value);
+	new_expires = timespec64_to_ns(&new->it_value);
 
 	/*
 	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
@@ -633,7 +633,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			bump_cpu_timer(timer, val);
 			if (val < timer->it.cpu.expires) {
 				old_expires = timer->it.cpu.expires - val;
-				old->it_value = ns_to_timespec(old_expires);
+				old->it_value = ns_to_timespec64(old_expires);
 			} else {
 				old->it_value.tv_nsec = 1;
 				old->it_value.tv_sec = 0;
@@ -671,7 +671,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
 	 */
-	timer->it.cpu.incr = timespec_to_ns(&new->it_interval);
+	timer->it.cpu.incr = timespec64_to_ns(&new->it_interval);
 
 	/*
 	 * This acts as a modification timestamp for the timer,
@@ -695,12 +695,12 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	ret = 0;
  out:
 	if (old)
-		old->it_interval = ns_to_timespec(old_incr);
+		old->it_interval = ns_to_timespec64(old_incr);
 
 	return ret;
 }
 
-static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp)
 {
 	u64 now;
 	struct task_struct *p = timer->it.cpu.task;
@@ -710,7 +710,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	/*
 	 * Easy part: convert the reload time.
 	 */
-	itp->it_interval = ns_to_timespec(timer->it.cpu.incr);
+	itp->it_interval = ns_to_timespec64(timer->it.cpu.incr);
 
 	if (timer->it.cpu.expires == 0) {	/* Timer not armed at all.  */
 		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
@@ -739,7 +739,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			 * Call the timer disarmed, nothing else to do.
 			 */
 			timer->it.cpu.expires = 0;
-			itp->it_value = ns_to_timespec(timer->it.cpu.expires);
+			itp->it_value = ns_to_timespec64(timer->it.cpu.expires);
 			return;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
@@ -748,7 +748,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	}
 
 	if (now < timer->it.cpu.expires) {
-		itp->it_value = ns_to_timespec(timer->it.cpu.expires - now);
+		itp->it_value = ns_to_timespec64(timer->it.cpu.expires - now);
 	} else {
 		/*
 		 * The timer should have expired already, but the firing
@@ -825,6 +825,8 @@ static void check_thread_timers(struct task_struct *tsk,
 			 * At the hard limit, we just die.
 			 * No need to calculate anything else now.
 			 */
+			pr_info("CPU Watchdog Timeout (hard): %s[%d]\n",
+				tsk->comm, task_pid_nr(tsk));
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
@@ -836,8 +838,7 @@ static void check_thread_timers(struct task_struct *tsk,
 				soft += USEC_PER_SEC;
 				sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
 			}
-			printk(KERN_INFO
-				"RT Watchdog Timeout: %s[%d]\n",
+			pr_info("RT Watchdog Timeout (soft): %s[%d]\n",
 				tsk->comm, task_pid_nr(tsk));
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
 		}
@@ -935,6 +936,8 @@ static void check_process_timers(struct task_struct *tsk,
 			 * At the hard limit, we just die.
 			 * No need to calculate anything else now.
 			 */
+			pr_info("RT Watchdog Timeout (hard): %s[%d]\n",
+				tsk->comm, task_pid_nr(tsk));
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
@@ -942,6 +945,8 @@ static void check_process_timers(struct task_struct *tsk,
 			/*
 			 * At the soft limit, send a SIGXCPU every second.
 			 */
+			pr_info("CPU Watchdog Timeout (soft): %s[%d]\n",
+				tsk->comm, task_pid_nr(tsk));
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
 			if (soft < hard) {
 				soft++;
@@ -1214,7 +1219,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 }
 
 static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
-			    struct timespec *rqtp, struct itimerspec *it)
+			    struct timespec64 *rqtp, struct itimerspec64 *it)
 {
 	struct k_itimer timer;
 	int error;
@@ -1229,7 +1234,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 	error = posix_cpu_timer_create(&timer);
 	timer.it_process = current;
 	if (!error) {
-		static struct itimerspec zero_it;
+		static struct itimerspec64 zero_it;
 
 		memset(it, 0, sizeof *it);
 		it->it_value = *rqtp;
@@ -1264,7 +1269,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		/*
 		 * We were interrupted by a signal.
 		 */
-		*rqtp = ns_to_timespec(timer.it.cpu.expires);
+		*rqtp = ns_to_timespec64(timer.it.cpu.expires);
 		error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
 		if (!error) {
 			/*
@@ -1301,10 +1306,11 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
 
 static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-			    struct timespec *rqtp, struct timespec __user *rmtp)
+			    struct timespec64 *rqtp, struct timespec __user *rmtp)
 {
 	struct restart_block *restart_block = &current->restart_block;
-	struct itimerspec it;
+	struct itimerspec64 it;
+	struct timespec ts;
 	int error;
 
 	/*
@@ -1324,13 +1330,14 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 		/*
 		 * Report back to the user the time still remaining.
 		 */
-		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		ts = timespec64_to_timespec(it.it_value);
+		if (rmtp && copy_to_user(rmtp, &ts, sizeof(*rmtp)))
 			return -EFAULT;
 
 		restart_block->fn = posix_cpu_nsleep_restart;
 		restart_block->nanosleep.clockid = which_clock;
 		restart_block->nanosleep.rmtp = rmtp;
-		restart_block->nanosleep.expires = timespec_to_ns(rqtp);
+		restart_block->nanosleep.expires = timespec64_to_ns(rqtp);
 	}
 	return error;
 }
@@ -1338,11 +1345,12 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 {
 	clockid_t which_clock = restart_block->nanosleep.clockid;
-	struct timespec t;
-	struct itimerspec it;
+	struct itimerspec64 it;
+	struct timespec64 t;
+	struct timespec tmp;
 	int error;
 
-	t = ns_to_timespec(restart_block->nanosleep.expires);
+	t = ns_to_timespec64(restart_block->nanosleep.expires);
 
 	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
 
@@ -1351,10 +1359,11 @@ static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 		/*
 		 * Report back to the user the time still remaining.
 		 */
-		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 tmp = timespec64_to_timespec(it.it_value);
+		if (rmtp && copy_to_user(rmtp, &tmp, sizeof(*rmtp)))
 			return -EFAULT;
 
-		restart_block->nanosleep.expires = timespec_to_ns(&t);
+		restart_block->nanosleep.expires = timespec64_to_ns(&t);
 	}
 	return error;
 
@@ -1364,12 +1373,12 @@ static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 #define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
 
 static int process_cpu_clock_getres(const clockid_t which_clock,
-				    struct timespec *tp)
+				    struct timespec64 *tp)
 {
 	return posix_cpu_clock_getres(PROCESS_CLOCK, tp);
 }
 static int process_cpu_clock_get(const clockid_t which_clock,
-				 struct timespec *tp)
+				 struct timespec64 *tp)
 {
 	return posix_cpu_clock_get(PROCESS_CLOCK, tp);
 }
@@ -1379,7 +1388,7 @@ static int process_cpu_timer_create(struct k_itimer *timer)
 	return posix_cpu_timer_create(timer);
 }
 static int process_cpu_nsleep(const clockid_t which_clock, int flags,
-			      struct timespec *rqtp,
+			      struct timespec64 *rqtp,
 			      struct timespec __user *rmtp)
 {
 	return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
@@ -1389,12 +1398,12 @@ static long process_cpu_nsleep_restart(struct restart_block *restart_block)
 	return -EINVAL;
 }
 static int thread_cpu_clock_getres(const clockid_t which_clock,
-				   struct timespec *tp)
+				   struct timespec64 *tp)
 {
 	return posix_cpu_clock_getres(THREAD_CLOCK, tp);
 }
 static int thread_cpu_clock_get(const clockid_t which_clock,
-				struct timespec *tp)
+				struct timespec64 *tp)
 {
 	return posix_cpu_clock_get(THREAD_CLOCK, tp);
 }
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index cd6716e115e8..c0cd53eb018a 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -49,26 +49,32 @@ SYS_NI(alarm);
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
+	struct timespec64 new_tp64;
 	struct timespec new_tp;
 
 	if (which_clock != CLOCK_REALTIME)
 		return -EINVAL;
 	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
 		return -EFAULT;
-	return do_sys_settimeofday(&new_tp, NULL);
+
+	new_tp64 = timespec_to_timespec64(new_tp);
+	return do_sys_settimeofday64(&new_tp64, NULL);
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 		struct timespec __user *,tp)
 {
+	struct timespec64 kernel_tp64;
 	struct timespec kernel_tp;
 
 	switch (which_clock) {
-	case CLOCK_REALTIME: ktime_get_real_ts(&kernel_tp); break;
-	case CLOCK_MONOTONIC: ktime_get_ts(&kernel_tp); break;
-	case CLOCK_BOOTTIME: get_monotonic_boottime(&kernel_tp); break;
+	case CLOCK_REALTIME: ktime_get_real_ts64(&kernel_tp64); break;
+	case CLOCK_MONOTONIC: ktime_get_ts64(&kernel_tp64); break;
+	case CLOCK_BOOTTIME: get_monotonic_boottime64(&kernel_tp64); break;
 	default: return -EINVAL;
 	}
+
+	kernel_tp = timespec64_to_timespec(kernel_tp64);
 	if (copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
 		return -EFAULT;
 	return 0;
@@ -97,6 +103,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		const struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
+	struct timespec64 t64;
 	struct timespec t;
 
 	switch (which_clock) {
@@ -105,9 +112,10 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	case CLOCK_BOOTTIME:
 		if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
 			return -EFAULT;
-		if (!timespec_valid(&t))
+		t64 = timespec_to_timespec64(t);
+		if (!timespec64_valid(&t64))
 			return -EINVAL;
-		return hrtimer_nanosleep(&t, rmtp, flags & TIMER_ABSTIME ?
+		return hrtimer_nanosleep(&t64, rmtp, flags & TIMER_ABSTIME ?
 					 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 					 which_clock);
 	default:
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 50a6a47020de..4d7b2ce09c27 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -130,12 +130,12 @@ static struct k_clock posix_clocks[MAX_CLOCKS];
 /*
  * These ones are defined below.
  */
-static int common_nsleep(const clockid_t, int flags, struct timespec *t,
+static int common_nsleep(const clockid_t, int flags, struct timespec64 *t,
 			 struct timespec __user *rmtp);
 static int common_timer_create(struct k_itimer *new_timer);
-static void common_timer_get(struct k_itimer *, struct itimerspec *);
+static void common_timer_get(struct k_itimer *, struct itimerspec64 *);
 static int common_timer_set(struct k_itimer *, int,
-			    struct itimerspec *, struct itimerspec *);
+			    struct itimerspec64 *, struct itimerspec64 *);
 static int common_timer_del(struct k_itimer *timer);
 
 static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
@@ -204,17 +204,17 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 }
 
 /* Get clock_realtime */
-static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
+static int posix_clock_realtime_get(clockid_t which_clock, struct timespec64 *tp)
 {
-	ktime_get_real_ts(tp);
+	ktime_get_real_ts64(tp);
 	return 0;
 }
 
 /* Set clock_realtime */
 static int posix_clock_realtime_set(const clockid_t which_clock,
-				    const struct timespec *tp)
+				    const struct timespec64 *tp)
 {
-	return do_sys_settimeofday(tp, NULL);
+	return do_sys_settimeofday64(tp, NULL);
 }
 
 static int posix_clock_realtime_adj(const clockid_t which_clock,
@@ -226,54 +226,54 @@ static int posix_clock_realtime_adj(const clockid_t which_clock,
 /*
  * Get monotonic time for posix timers
  */
-static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
+static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
 {
-	ktime_get_ts(tp);
+	ktime_get_ts64(tp);
 	return 0;
 }
 
 /*
  * Get monotonic-raw time for posix timers
  */
-static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
 {
-	getrawmonotonic(tp);
+	getrawmonotonic64(tp);
 	return 0;
 }
 
 
-static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp)
+static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
 {
-	*tp = current_kernel_time();
+	*tp = current_kernel_time64();
 	return 0;
 }
 
 static int posix_get_monotonic_coarse(clockid_t which_clock,
-						struct timespec *tp)
+						struct timespec64 *tp)
 {
-	*tp = get_monotonic_coarse();
+	*tp = get_monotonic_coarse64();
 	return 0;
 }
 
-static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *tp)
 {
-	*tp = ktime_to_timespec(KTIME_LOW_RES);
+	*tp = ktime_to_timespec64(KTIME_LOW_RES);
 	return 0;
 }
 
-static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
 {
-	get_monotonic_boottime(tp);
+	get_monotonic_boottime64(tp);
 	return 0;
 }
 
-static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
+static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
 {
-	timekeeping_clocktai(tp);
+	timekeeping_clocktai64(tp);
 	return 0;
 }
 
-static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec *tp)
+static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
 {
 	tp->tv_sec = 0;
 	tp->tv_nsec = hrtimer_resolution;
@@ -734,18 +734,18 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
  * report.
  */
 static void
-common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
+common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 {
 	ktime_t now, remaining, iv;
 	struct hrtimer *timer = &timr->it.real.timer;
 
-	memset(cur_setting, 0, sizeof(struct itimerspec));
+	memset(cur_setting, 0, sizeof(*cur_setting));
 
 	iv = timr->it.real.interval;
 
 	/* interval timer ? */
 	if (iv)
-		cur_setting->it_interval = ktime_to_timespec(iv);
+		cur_setting->it_interval = ktime_to_timespec64(iv);
 	else if (!hrtimer_active(timer) &&
 		 (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
 		return;
@@ -771,13 +771,14 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 		if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
 			cur_setting->it_value.tv_nsec = 1;
 	} else
-		cur_setting->it_value = ktime_to_timespec(remaining);
+		cur_setting->it_value = ktime_to_timespec64(remaining);
 }
 
 /* Get the time remaining on a POSIX.1b interval timer. */
 SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 		struct itimerspec __user *, setting)
 {
+	struct itimerspec64 cur_setting64;
 	struct itimerspec cur_setting;
 	struct k_itimer *timr;
 	struct k_clock *kc;
@@ -792,10 +793,11 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	if (WARN_ON_ONCE(!kc || !kc->timer_get))
 		ret = -EINVAL;
 	else
-		kc->timer_get(timr, &cur_setting);
+		kc->timer_get(timr, &cur_setting64);
 
 	unlock_timer(timr, flags);
 
+	cur_setting = itimerspec64_to_itimerspec(&cur_setting64);
 	if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
 		return -EFAULT;
 
@@ -831,7 +833,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 /* timr->it_lock is taken. */
 static int
 common_timer_set(struct k_itimer *timr, int flags,
-		 struct itimerspec *new_setting, struct itimerspec *old_setting)
+		 struct itimerspec64 *new_setting, struct itimerspec64 *old_setting)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
 	enum hrtimer_mode mode;
@@ -860,10 +862,10 @@ common_timer_set(struct k_itimer *timr, int flags,
 	hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
 	timr->it.real.timer.function = posix_timer_fn;
 
-	hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value));
+	hrtimer_set_expires(timer, timespec64_to_ktime(new_setting->it_value));
 
 	/* Convert interval */
-	timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
+	timr->it.real.interval = timespec64_to_ktime(new_setting->it_interval);
 
 	/* SIGEV_NONE timers are not queued ! See common_timer_get */
 	if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
@@ -883,21 +885,23 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 		const struct itimerspec __user *, new_setting,
 		struct itimerspec __user *, old_setting)
 {
-	struct k_itimer *timr;
+	struct itimerspec64 new_spec64, old_spec64;
+	struct itimerspec64 *rtn = old_setting ? &old_spec64 : NULL;
 	struct itimerspec new_spec, old_spec;
-	int error = 0;
+	struct k_itimer *timr;
 	unsigned long flag;
-	struct itimerspec *rtn = old_setting ? &old_spec : NULL;
 	struct k_clock *kc;
+	int error = 0;
 
 	if (!new_setting)
 		return -EINVAL;
 
 	if (copy_from_user(&new_spec, new_setting, sizeof (new_spec)))
 		return -EFAULT;
+	new_spec64 = itimerspec_to_itimerspec64(&new_spec);
 
-	if (!timespec_valid(&new_spec.it_interval) ||
-	    !timespec_valid(&new_spec.it_value))
+	if (!timespec64_valid(&new_spec64.it_interval) ||
+	    !timespec64_valid(&new_spec64.it_value))
 		return -EINVAL;
 retry:
 	timr = lock_timer(timer_id, &flag);
@@ -908,7 +912,7 @@ retry:
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
 		error = -EINVAL;
 	else
-		error = kc->timer_set(timr, flags, &new_spec, rtn);
+		error = kc->timer_set(timr, flags, &new_spec64, rtn);
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
@@ -916,6 +920,7 @@ retry:
 		goto retry;
 	}
 
+	old_spec = itimerspec64_to_itimerspec(&old_spec64);
 	if (old_setting && !error &&
 	    copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
 		error = -EFAULT;
@@ -1014,6 +1019,7 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
 	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timespec64 new_tp64;
 	struct timespec new_tp;
 
 	if (!kc || !kc->clock_set)
@@ -1021,21 +1027,24 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 
 	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
 		return -EFAULT;
+	new_tp64 = timespec_to_timespec64(new_tp);
 
-	return kc->clock_set(which_clock, &new_tp);
+	return kc->clock_set(which_clock, &new_tp64);
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 		struct timespec __user *,tp)
 {
 	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timespec64 kernel_tp64;
 	struct timespec kernel_tp;
 	int error;
 
 	if (!kc)
 		return -EINVAL;
 
-	error = kc->clock_get(which_clock, &kernel_tp);
+	error = kc->clock_get(which_clock, &kernel_tp64);
+	kernel_tp = timespec64_to_timespec(kernel_tp64);
 
 	if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
 		error = -EFAULT;
@@ -1070,13 +1079,15 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 		struct timespec __user *, tp)
 {
 	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timespec64 rtn_tp64;
 	struct timespec rtn_tp;
 	int error;
 
 	if (!kc)
 		return -EINVAL;
 
-	error = kc->clock_getres(which_clock, &rtn_tp);
+	error = kc->clock_getres(which_clock, &rtn_tp64);
+	rtn_tp = timespec64_to_timespec(rtn_tp64);
 
 	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
 		error = -EFAULT;
@@ -1088,7 +1099,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
  * nanosleep for monotonic and realtime clocks
  */
 static int common_nsleep(const clockid_t which_clock, int flags,
-			 struct timespec *tsave, struct timespec __user *rmtp)
+			 struct timespec64 *tsave, struct timespec __user *rmtp)
 {
 	return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
@@ -1100,6 +1111,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		struct timespec __user *, rmtp)
 {
 	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timespec64 t64;
 	struct timespec t;
 
 	if (!kc)
@@ -1110,10 +1122,11 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
 		return -EFAULT;
 
-	if (!timespec_valid(&t))
+	t64 = timespec_to_timespec64(t);
+	if (!timespec64_valid(&t64))
 		return -EINVAL;
 
-	return kc->nsleep(which_clock, flags, &t, rmtp);
+	return kc->nsleep(which_clock, flags, &t64, rmtp);
 }
 
 /*
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index ea6b610c4c57..2d8f05aad442 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -206,6 +206,11 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 
 	update_clock_read_data(&rd);
 
+	if (sched_clock_timer.function != NULL) {
+		/* update timeout for clock wrap */
+		hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+	}
+
 	r = rate;
 	if (r >= 4000000) {
 		r /= 1000000;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7fe53be86077..64c97fc130c4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -993,6 +993,18 @@ ktime_t tick_nohz_get_sleep_length(void)
 	return ts->sleep_length;
 }
 
+/**
+ * tick_nohz_get_idle_calls - return the current idle calls counter value
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls(void)
+{
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
+
+	return ts->idle_calls;
+}
+
 static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
 {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 25bdd2504571..6574bba44b55 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -193,8 +193,8 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
 		struct timezone __user *, tz)
 {
+	struct timespec64 new_ts;
 	struct timeval user_tv;
-	struct timespec	new_ts;
 	struct timezone new_tz;
 
 	if (tv) {
@@ -212,7 +212,7 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
+	return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
 SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 5b63a2102c29..9652bc57fd09 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -996,8 +996,7 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 		return 0;
 
 	/* Interpolate shortest distance from beginning or end of history */
-	interp_forward = partial_history_cycles > total_history_cycles/2 ?
-		true : false;
+	interp_forward = partial_history_cycles > total_history_cycles / 2;
 	partial_history_cycles = interp_forward ?
 		total_history_cycles - partial_history_cycles :
 		partial_history_cycles;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 1dc0256bfb6e..cc6b6bdd1329 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -241,7 +241,7 @@ int timer_migration_handler(struct ctl_table *table, int write,
 	int ret;
 
 	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write)
 		timers_update_migration(false);
 	mutex_unlock(&mutex);
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ff8d5c13d04b..0e7f5428a148 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
+#include <linux/nmi.h>
 
 #include <linux/uaccess.h>
 
@@ -86,6 +87,9 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 
 next_one:
 	i = 0;
+
+	touch_nmi_watchdog();
+
 	raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
 
 	curr = timerqueue_getnext(&base->active);
@@ -197,6 +201,8 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 {
 	struct clock_event_device *dev = td->evtdev;
 
+	touch_nmi_watchdog();
+
 	SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
 	if (cpu < 0)
 		SEQ_printf(m, "Broadcast device\n");
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d5038005eb5d..9619b5768e4b 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
-config KPROBE_EVENT
+config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API
 	bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@ config KPROBE_EVENT
 	  This option is also required by perf-probe subcommand of perf tools.
 	  If you want to use perf tools, this option is strongly recommended.
 
-config UPROBE_EVENT
+config UPROBE_EVENTS
 	bool "Enable uprobes-based dynamic events"
 	depends on ARCH_SUPPORTS_UPROBES
 	depends on MMU
@@ -455,7 +455,7 @@ config UPROBE_EVENT
 	select UPROBES
 	select PROBE_EVENTS
 	select TRACING
-	default n
+	default y
 	help
 	  This allows the user to add tracing events on top of userspace
 	  dynamic events (similar to tracepoints) on the fly via the trace
@@ -466,7 +466,7 @@ config UPROBE_EVENT
 
 config BPF_EVENTS
 	depends on BPF_SYSCALL
-	depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+	depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
 	bool
 	default y
 	help
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e57980845549..90f2701d92a7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b2058a7f94bd..bd8ae8d5ae9c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -690,8 +690,8 @@ void blk_trace_shutdown(struct request_queue *q)
 
 /**
  * blk_add_trace_rq - Add a trace for a request oriented action
- * @q:		queue the io is for
  * @rq:		the source request
+ * @error:	return status to log
  * @nr_bytes:	number of completed bytes
  * @what:	the action
  *
@@ -699,10 +699,10 @@ void blk_trace_shutdown(struct request_queue *q)
  *     Records an action against a request. Will log the bio offset + size.
  *
  **/
-static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
+static void blk_add_trace_rq(struct request *rq, int error,
 			     unsigned int nr_bytes, u32 what)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt = rq->q->blk_trace;
 
 	if (likely(!bt))
 		return;
@@ -713,40 +713,32 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 		what |= BLK_TC_ACT(BLK_TC_FS);
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
-			rq->cmd_flags, what, rq->errors, 0, NULL);
-}
-
-static void blk_add_trace_rq_abort(void *ignore,
-				   struct request_queue *q, struct request *rq)
-{
-	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
+			rq->cmd_flags, what, error, 0, NULL);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
-static void blk_add_trace_rq_complete(void *ignore,
-				      struct request_queue *q,
-				      struct request *rq,
-				      unsigned int nr_bytes)
+static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
+			int error, unsigned int nr_bytes)
 {
-	blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
+	blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**
@@ -941,7 +933,7 @@ static void blk_add_trace_rq_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), 0, BLK_TA_REMAP, !!rq->errors,
+			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
 			sizeof(r), &r);
 }
 
@@ -966,7 +958,7 @@ void blk_add_driver_data(struct request_queue *q,
 		return;
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
-				BLK_TA_DRV_DATA, rq->errors, len, data);
+				BLK_TA_DRV_DATA, 0, len, data);
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
@@ -974,8 +966,6 @@ static void blk_register_tracepoints(void)
 {
 	int ret;
 
-	ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
-	WARN_ON(ret);
 	ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
@@ -1028,7 +1018,6 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
 	unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
-	unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
 
 	tracepoint_synchronize_unregister();
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index cee9802cf3e0..460a031c77e5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -96,7 +96,7 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	if (unlikely(in_interrupt() ||
 		     current->flags & (PF_KTHREAD | PF_EXITING)))
 		return -EPERM;
-	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+	if (unlikely(uaccess_kernel()))
 		return -EPERM;
 	if (!access_ok(VERIFY_WRITE, unsafe_ptr, size))
 		return -EPERM;
@@ -501,16 +501,11 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
 	return true;
 }
 
-static const struct bpf_verifier_ops kprobe_prog_ops = {
+const struct bpf_verifier_ops kprobe_prog_ops = {
 	.get_func_proto  = kprobe_prog_func_proto,
 	.is_valid_access = kprobe_prog_is_valid_access,
 };
 
-static struct bpf_prog_type_list kprobe_tl __ro_after_init = {
-	.ops	= &kprobe_prog_ops,
-	.type	= BPF_PROG_TYPE_KPROBE,
-};
-
 BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
@@ -584,16 +579,11 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type
 	return true;
 }
 
-static const struct bpf_verifier_ops tracepoint_prog_ops = {
+const struct bpf_verifier_ops tracepoint_prog_ops = {
 	.get_func_proto  = tp_prog_func_proto,
 	.is_valid_access = tp_prog_is_valid_access,
 };
 
-static struct bpf_prog_type_list tracepoint_tl __ro_after_init = {
-	.ops	= &tracepoint_prog_ops,
-	.type	= BPF_PROG_TYPE_TRACEPOINT,
-};
-
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    enum bpf_reg_type *reg_type)
 {
@@ -642,22 +632,8 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-static const struct bpf_verifier_ops perf_event_prog_ops = {
+const struct bpf_verifier_ops perf_event_prog_ops = {
 	.get_func_proto		= tp_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
-
-static struct bpf_prog_type_list perf_event_tl __ro_after_init = {
-	.ops	= &perf_event_prog_ops,
-	.type	= BPF_PROG_TYPE_PERF_EVENT,
-};
-
-static int __init register_kprobe_prog_ops(void)
-{
-	bpf_register_prog_type(&kprobe_tl);
-	bpf_register_prog_type(&tracepoint_tl);
-	bpf_register_prog_type(&perf_event_tl);
-	return 0;
-}
-late_initcall(register_kprobe_prog_ops);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0d1597c9ee30..dd3e91d68dc7 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3755,23 +3755,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
 	ftrace_probe_registered = 1;
 }
 
-static void __disable_ftrace_function_probe(void)
+static bool __disable_ftrace_function_probe(void)
 {
 	int i;
 
 	if (!ftrace_probe_registered)
-		return;
+		return false;
 
 	for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
 		struct hlist_head *hhd = &ftrace_func_hash[i];
 		if (hhd->first)
-			return;
+			return false;
 	}
 
 	/* no more funcs left */
 	ftrace_shutdown(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 0;
+	return true;
 }
 
 
@@ -3901,6 +3902,7 @@ static void
 __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				  void *data, int flags)
 {
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
@@ -3912,6 +3914,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
 	int i, ret;
+	bool disabled;
 
 	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
 		func_g.search = NULL;
@@ -3930,6 +3933,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
+	old_hash_ops.filter_hash = old_hash;
+	/* Probes only have filters */
+	old_hash_ops.notrace_hash = NULL;
+
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash)
 		/* Hmm, should report this somehow */
@@ -3967,12 +3974,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		}
 	}
 	mutex_lock(&ftrace_lock);
-	__disable_ftrace_function_probe();
+	disabled = __disable_ftrace_function_probe();
 	/*
 	 * Remove after the disable is called. Otherwise, if the last
 	 * probe is removed, a null hash means *all enabled*.
 	 */
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+	/* still need to update the function call sites */
+	if (ftrace_enabled && !disabled)
+		ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+				       &old_hash_ops);
 	synchronize_sched();
 	if (!ret)
 		free_ftrace_hash_rcu(old_hash);
@@ -4416,16 +4428,24 @@ static int __init set_graph_notrace_function(char *str)
 }
 __setup("ftrace_graph_notrace=", set_graph_notrace_function);
 
+static int __init set_graph_max_depth_function(char *str)
+{
+	if (!str)
+		return 0;
+	fgraph_max_depth = simple_strtoul(str, NULL, 0);
+	return 1;
+}
+__setup("ftrace_graph_max_depth=", set_graph_max_depth_function);
+
 static void __init set_ftrace_early_graph(char *buf, int enable)
 {
 	int ret;
 	char *func;
 	struct ftrace_hash *hash;
 
-	if (enable)
-		hash = ftrace_graph_hash;
-	else
-		hash = ftrace_graph_notrace_hash;
+	hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+	if (WARN_ON(!hash))
+		return;
 
 	while (buf) {
 		func = strsep(&buf, ",");
@@ -4435,6 +4455,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
 			printk(KERN_DEBUG "ftrace: function %s not "
 					  "traceable\n", func);
 	}
+
+	if (enable)
+		ftrace_graph_hash = hash;
+	else
+		ftrace_graph_notrace_hash = hash;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -5488,7 +5513,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
  * Normally the mcount trampoline will call the ops->func, but there
  * are times that it should not. For example, if the ops does not
  * have its own recursion protection, then it should call the
- * ftrace_ops_recurs_func() instead.
+ * ftrace_ops_assist_func() instead.
  *
  * Returns the function that the trampoline should call for @ops.
  */
@@ -5541,6 +5566,15 @@ static void clear_ftrace_pids(struct trace_array *tr)
 	trace_free_pid_list(pid_list);
 }
 
+void ftrace_clear_pids(struct trace_array *tr)
+{
+	mutex_lock(&ftrace_lock);
+
+	clear_ftrace_pids(tr);
+
+	mutex_unlock(&ftrace_lock);
+}
+
 static void ftrace_pid_reset(struct trace_array *tr)
 {
 	mutex_lock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 96fc3c043ad6..ca47a4fa2986 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3405,11 +3405,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *reader;
+	struct buffer_page *head_page;
+	struct buffer_page *commit_page;
+	unsigned commit;
 
 	cpu_buffer = iter->cpu_buffer;
 
-	return iter->head_page == cpu_buffer->commit_page &&
-		iter->head == rb_commit_index(cpu_buffer);
+	/* Remember, trace recording is off when iterator is in use */
+	reader = cpu_buffer->reader_page;
+	head_page = cpu_buffer->head_page;
+	commit_page = cpu_buffer->commit_page;
+	commit = rb_page_commit(commit_page);
+
+	return ((iter->head_page == commit_page && iter->head == commit) ||
+		(iter->head_page == reader && commit_page == head_page &&
+		 head_page->read == commit &&
+		 iter->head == rb_page_commit(cpu_buffer->reader_page)));
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
 
@@ -4826,9 +4838,9 @@ static __init int test_ringbuffer(void)
 		rb_data[cpu].cnt = cpu;
 		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
 						 "rbtester/%d", cpu);
-		if (WARN_ON(!rb_threads[cpu])) {
+		if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
 			pr_cont("FAILED\n");
-			ret = -1;
+			ret = PTR_ERR(rb_threads[cpu]);
 			goto out_free;
 		}
 
@@ -4838,9 +4850,9 @@ static __init int test_ringbuffer(void)
 
 	/* Now create the rb hammer! */
 	rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
-	if (WARN_ON(!rb_hammer)) {
+	if (WARN_ON(IS_ERR(rb_hammer))) {
 		pr_cont("FAILED\n");
-		ret = -1;
+		ret = PTR_ERR(rb_hammer);
 		goto out_free;
 	}
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445ceb7ef..0029fe62b245 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4341,22 +4341,23 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
 	"\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
 	"\t           -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+  "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"\t    place: <path>:<offset>\n"
 #endif
 	"\t     args: <name>=fetcharg[:type]\n"
@@ -5529,7 +5530,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.partial	= partial_def,
 		.nr_pages	= 0, /* This gets updated below. */
 		.nr_pages_max	= PIPE_DEF_BUFFERS,
-		.flags		= flags,
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
@@ -6427,7 +6427,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.pages		= pages_def,
 		.partial	= partial_def,
 		.nr_pages_max	= PIPE_DEF_BUFFERS,
-		.flags		= flags,
 		.ops		= &buffer_pipe_buf_ops,
 		.spd_release	= buffer_spd_release,
 	};
@@ -6733,11 +6732,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
 		return ret;
 
  out_reg:
-	ret = register_ftrace_function_probe(glob, ops, count);
+	ret = alloc_snapshot(&global_trace);
+	if (ret < 0)
+		goto out;
 
-	if (ret >= 0)
-		alloc_snapshot(&global_trace);
+	ret = register_ftrace_function_probe(glob, ops, count);
 
+ out:
 	return ret < 0 ? ret : 0;
 }
 
@@ -7402,6 +7403,7 @@ static int instance_rmdir(const char *name)
 
 	tracing_set_nop(tr);
 	event_trace_del_tracer(tr);
+	ftrace_clear_pids(tr);
 	ftrace_destroy_function_files(tr);
 	tracefs_remove_recursive(tr->dir);
 	free_trace_buffers(tr);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ae1cce91fead..d19d52d600d6 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -896,6 +896,7 @@ int using_ftrace_ops_list_func(void);
 void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
 void ftrace_init_tracefs_toplevel(struct trace_array *tr,
 				  struct dentry *d_tracer);
+void ftrace_clear_pids(struct trace_array *tr);
 #else
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
@@ -914,6 +915,7 @@ ftrace_init_global_array_ops(struct trace_array *tr) { }
 static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
 static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
 static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
+static inline void ftrace_clear_pids(struct trace_array *tr) { }
 /* ftace_func_t type is not defined, use macro instead of static inline */
 #define ftrace_init_array_ops(tr, func) do { } while (0)
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5f688cc724f0..013f4e7146d4 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -681,10 +681,6 @@ static int create_trace_kprobe(int argc, char **argv)
 		return -EINVAL;
 	}
 	if (isdigit(argv[1][0])) {
-		if (is_return) {
-			pr_info("Return probe point must be a symbol.\n");
-			return -EINVAL;
-		}
 		/* an address specified */
 		ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
 		if (ret) {
@@ -700,8 +696,9 @@ static int create_trace_kprobe(int argc, char **argv)
 			pr_info("Failed to parse symbol.\n");
 			return ret;
 		}
-		if (offset && is_return) {
-			pr_info("Return probe must be used without offset.\n");
+		if (offset && is_return &&
+		    !function_offset_within_entry(NULL, symbol, offset)) {
+			pr_info("Given offset is not valid for return probe.\n");
 			return -EINVAL;
 		}
 	}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54d44c6..903273c93e61 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define FETCH_TYPE_STRING	0
 #define FETCH_TYPE_STRSIZE	1
 
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
 	struct fetch_param	fetch;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 1d68b5b7ad41..5fb1f2c87e6b 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -65,7 +65,7 @@ void stack_trace_print(void)
 }
 
 /*
- * When arch-specific code overides this function, the following
+ * When arch-specific code overrides this function, the following
  * data should be filled up, assuming stack_trace_max_lock is held to
  * prevent concurrent updates.
  *     stack_trace_index[]
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 62630a40ab3a..b4eeee03934f 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 
 		new->ns = ns;
 		new->uid = uid;
-		atomic_set(&new->count, 0);
+		new->count = 0;
 
 		spin_lock_irq(&ucounts_lock);
 		ucounts = find_ucounts(ns, uid, hashent);
@@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 			ucounts = new;
 		}
 	}
-	if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
+	if (ucounts->count == INT_MAX)
 		ucounts = NULL;
+	else
+		ucounts->count += 1;
 	spin_unlock_irq(&ucounts_lock);
 	return ucounts;
 }
@@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts)
 {
 	unsigned long flags;
 
-	if (atomic_dec_and_test(&ucounts->count)) {
-		spin_lock_irqsave(&ucounts_lock, flags);
+	spin_lock_irqsave(&ucounts_lock, flags);
+	ucounts->count -= 1;
+	if (!ucounts->count)
 		hlist_del_init(&ucounts->node);
-		spin_unlock_irqrestore(&ucounts_lock, flags);
+	else
+		ucounts = NULL;
+	spin_unlock_irqrestore(&ucounts_lock, flags);
 
-		kfree(ucounts);
-	}
+	kfree(ucounts);
 }
 
 static inline bool atomic_inc_below(atomic_t *v, int u)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 072cbc9b175d..c74bf39ef764 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1507,6 +1507,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	struct timer_list *timer = &dwork->timer;
 	struct work_struct *work = &dwork->work;
 
+	WARN_ON_ONCE(!wq);
 	WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
 		     timer->data != (unsigned long)dwork);
 	WARN_ON_ONCE(timer_pending(timer));
@@ -3208,9 +3209,8 @@ static int init_worker_pool(struct worker_pool *pool)
 	INIT_LIST_HEAD(&pool->idle_list);
 	hash_init(pool->busy_hash);
 
-	init_timer_deferrable(&pool->idle_timer);
-	pool->idle_timer.function = idle_worker_timeout;
-	pool->idle_timer.data = (unsigned long)pool;
+	setup_deferrable_timer(&pool->idle_timer, idle_worker_timeout,
+			       (unsigned long)pool);
 
 	setup_timer(&pool->mayday_timer, pool_mayday_timeout,
 		    (unsigned long)pool);
@@ -4734,6 +4734,29 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);
+
+/**
+ * work_on_cpu_safe - run a function in thread context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn:  the function to run
+ * @arg: the function argument
+ *
+ * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold
+ * any locks which would prevent @fn from completing.
+ *
+ * Return: The value @fn returns.
+ */
+long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg)
+{
+	long ret = -ENODEV;
+
+	get_online_cpus();
+	if (cpu_online(cpu))
+		ret = work_on_cpu(cpu, fn, arg);
+	put_online_cpus();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu_safe);
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 97d62c2da6c2..e2a617e09ab7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -130,7 +130,8 @@ config DYNAMIC_DEBUG
 		nullarbor:~ # echo -n 'func svc_process -p' >
 						<debugfs>/dynamic_debug/control
 
-	  See Documentation/dynamic-debug-howto.txt for additional information.
+	  See Documentation/admin-guide/dynamic-debug-howto.rst for additional
+	  information.
 
 endmenu # "printk and dmesg options"
 
@@ -356,7 +357,7 @@ config FRAME_POINTER
 	bool "Compile the kernel with frame pointers"
 	depends on DEBUG_KERNEL && \
 		(CRIS || M68K || FRV || UML || \
-		 AVR32 || SUPERH || BLACKFIN || MN10300 || METAG) || \
+		 SUPERH || BLACKFIN || MN10300 || METAG) || \
 		ARCH_WANT_FRAME_POINTERS
 	default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS
 	help
@@ -404,8 +405,8 @@ config MAGIC_SYSRQ
 	  by pressing various keys while holding SysRq (Alt+PrintScreen). It
 	  also works on a serial console (on PC hardware at least), if you
 	  send a BREAK and then within 5 seconds a command keypress. The
-	  keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
-	  unless you really know what this hack does.
+	  keys are documented in <file:Documentation/admin-guide/sysrq.rst>.
+	  Don't say Y unless you really know what this hack does.
 
 config MAGIC_SYSRQ_DEFAULT_ENABLE
 	hex "Enable magic SysRq key functions by default"
@@ -414,7 +415,7 @@ config MAGIC_SYSRQ_DEFAULT_ENABLE
 	help
 	  Specifies which SysRq key functions are enabled by default.
 	  This may be set to 1 or 0 to enable or disable them all, or
-	  to a bitmask as described in Documentation/sysrq.txt.
+	  to a bitmask as described in Documentation/admin-guide/sysrq.rst.
 
 config MAGIC_SYSRQ_SERIAL
 	bool "Enable magic SysRq key over serial"
@@ -1103,9 +1104,6 @@ config PROVE_LOCKING
 
 	 For more details, see Documentation/locking/lockdep-design.txt.
 
-config PROVE_LOCKING_SMALL
-	bool
-
 config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -1114,6 +1112,9 @@ config LOCKDEP
 	select KALLSYMS
 	select KALLSYMS_ALL
 
+config LOCKDEP_SMALL
+	bool
+
 config LOCK_STAT
 	bool "Lock usage statistics"
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
diff --git a/lib/Makefile b/lib/Makefile
index 320ac46a8725..a155c73e3437 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -19,7 +19,7 @@ KCOV_INSTRUMENT_dynamic_debug.o := n
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o \
-	 sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
+	 sha1.o chacha20.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o \
@@ -41,7 +41,7 @@ obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
-	 once.o refcount.o
+	 once.o refcount.o usercopy.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += hexdump.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 0b66f0e5eb6b..08c6ef3a2b6f 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -502,11 +502,11 @@ EXPORT_SYMBOL(bitmap_print_to_pagebuf);
  * Syntax: range:used_size/group_size
  * Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769
  *
- * Returns 0 on success, -errno on invalid input strings.
- * Error values:
- *    %-EINVAL: second number in range smaller than first
- *    %-EINVAL: invalid character in string
- *    %-ERANGE: bit number specified too large for mask
+ * Returns: 0 on success, -errno on invalid input strings. Error values:
+ *
+ *   - ``-EINVAL``: second number in range smaller than first
+ *   - ``-EINVAL``: invalid character in string
+ *   - ``-ERANGE``: bit number specified too large for mask
  */
 static int __bitmap_parselist(const char *buf, unsigned int buflen,
 		int is_user, unsigned long *maskp,
@@ -864,14 +864,16 @@ EXPORT_SYMBOL(bitmap_bitremap);
  *  11 was set in @orig had no affect on @dst.
  *
  * Example [2] for bitmap_fold() + bitmap_onto():
- *  Let's say @relmap has these ten bits set:
+ *  Let's say @relmap has these ten bits set::
+ *
  *		40 41 42 43 45 48 53 61 74 95
+ *
  *  (for the curious, that's 40 plus the first ten terms of the
  *  Fibonacci sequence.)
  *
  *  Further lets say we use the following code, invoking
  *  bitmap_fold() then bitmap_onto, as suggested above to
- *  avoid the possibility of an empty @dst result:
+ *  avoid the possibility of an empty @dst result::
  *
  *	unsigned long *tmp;	// a temporary bitmap's bits
  *
@@ -882,22 +884,26 @@ EXPORT_SYMBOL(bitmap_bitremap);
  *  various @orig's.  I list the zero-based positions of each set bit.
  *  The tmp column shows the intermediate result, as computed by
  *  using bitmap_fold() to fold the @orig bitmap modulo ten
- *  (the weight of @relmap).
+ *  (the weight of @relmap):
  *
+ *      =============== ============== =================
  *      @orig           tmp            @dst
  *      0                0             40
  *      1                1             41
  *      9                9             95
- *      10               0             40 (*)
+ *      10               0             40 [#f1]_
  *      1 3 5 7          1 3 5 7       41 43 48 61
  *      0 1 2 3 4        0 1 2 3 4     40 41 42 43 45
  *      0 9 18 27        0 9 8 7       40 61 74 95
  *      0 10 20 30       0             40
  *      0 11 22 33       0 1 2 3       40 41 42 43
  *      0 12 24 36       0 2 4 6       40 42 45 53
- *      78 102 211       1 2 8         41 42 74 (*)
+ *      78 102 211       1 2 8         41 42 74 [#f1]_
+ *      =============== ============== =================
+ *
+ * .. [#f1]
  *
- * (*) For these marked lines, if we hadn't first done bitmap_fold()
+ *     For these marked lines, if we hadn't first done bitmap_fold()
  *     into tmp, then the @dst result would have been empty.
  *
  * If either of @orig or @relmap is empty (no set bits), then @dst
diff --git a/lib/bug.c b/lib/bug.c
index 06edbbef0623..a6a1137d06db 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -47,7 +47,7 @@
 #include <linux/sched.h>
 #include <linux/rculist.h>
 
-extern const struct bug_entry __start___bug_table[], __stop___bug_table[];
+extern struct bug_entry __start___bug_table[], __stop___bug_table[];
 
 static inline unsigned long bug_addr(const struct bug_entry *bug)
 {
@@ -62,10 +62,10 @@ static inline unsigned long bug_addr(const struct bug_entry *bug)
 /* Updates are protected by module mutex */
 static LIST_HEAD(module_bug_list);
 
-static const struct bug_entry *module_find_bug(unsigned long bugaddr)
+static struct bug_entry *module_find_bug(unsigned long bugaddr)
 {
 	struct module *mod;
-	const struct bug_entry *bug = NULL;
+	struct bug_entry *bug = NULL;
 
 	rcu_read_lock_sched();
 	list_for_each_entry_rcu(mod, &module_bug_list, bug_list) {
@@ -122,15 +122,15 @@ void module_bug_cleanup(struct module *mod)
 
 #else
 
-static inline const struct bug_entry *module_find_bug(unsigned long bugaddr)
+static inline struct bug_entry *module_find_bug(unsigned long bugaddr)
 {
 	return NULL;
 }
 #endif
 
-const struct bug_entry *find_bug(unsigned long bugaddr)
+struct bug_entry *find_bug(unsigned long bugaddr)
 {
-	const struct bug_entry *bug;
+	struct bug_entry *bug;
 
 	for (bug = __start___bug_table; bug < __stop___bug_table; ++bug)
 		if (bugaddr == bug_addr(bug))
@@ -141,9 +141,9 @@ const struct bug_entry *find_bug(unsigned long bugaddr)
 
 enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 {
-	const struct bug_entry *bug;
+	struct bug_entry *bug;
 	const char *file;
-	unsigned line, warning;
+	unsigned line, warning, once, done;
 
 	if (!is_valid_bugaddr(bugaddr))
 		return BUG_TRAP_TYPE_NONE;
@@ -164,6 +164,18 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 		line = bug->line;
 #endif
 		warning = (bug->flags & BUGFLAG_WARNING) != 0;
+		once = (bug->flags & BUGFLAG_ONCE) != 0;
+		done = (bug->flags & BUGFLAG_DONE) != 0;
+
+		if (warning && once) {
+			if (done)
+				return BUG_TRAP_TYPE_WARN;
+
+			/*
+			 * Since this is the only store, concurrency is not an issue.
+			 */
+			bug->flags |= BUGFLAG_DONE;
+		}
 	}
 
 	if (warning) {
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 8f13cf73c2ec..3c6432df7e63 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -15,6 +15,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/ctype.h>
 
 /*
  *	If a hyphen was found in get_option, this will handle the
@@ -189,3 +190,59 @@ bool parse_option_str(const char *str, const char *option)
 
 	return false;
 }
+
+/*
+ * Parse a string to get a param value pair.
+ * You can use " around spaces, but can't escape ".
+ * Hyphens and underscores equivalent in parameter names.
+ */
+char *next_arg(char *args, char **param, char **val)
+{
+	unsigned int i, equals = 0;
+	int in_quote = 0, quoted = 0;
+	char *next;
+
+	if (*args == '"') {
+		args++;
+		in_quote = 1;
+		quoted = 1;
+	}
+
+	for (i = 0; args[i]; i++) {
+		if (isspace(args[i]) && !in_quote)
+			break;
+		if (equals == 0) {
+			if (args[i] == '=')
+				equals = i;
+		}
+		if (args[i] == '"')
+			in_quote = !in_quote;
+	}
+
+	*param = args;
+	if (!equals)
+		*val = NULL;
+	else {
+		args[equals] = '\0';
+		*val = args + equals + 1;
+
+		/* Don't include quotes in value. */
+		if (**val == '"') {
+			(*val)++;
+			if (args[i-1] == '"')
+				args[i-1] = '\0';
+		}
+	}
+	if (quoted && args[i-1] == '"')
+		args[i-1] = '\0';
+
+	if (args[i]) {
+		args[i] = '\0';
+		next = args + i + 1;
+	} else
+		next = args + i;
+
+	/* Chew up trailing spaces. */
+	return skip_spaces(next);
+	//return next;
+}
diff --git a/lib/ioremap.c b/lib/ioremap.c
index a3e14ce92a56..4bb30206b942 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -14,6 +14,7 @@
 #include <asm/pgtable.h>
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+static int __read_mostly ioremap_p4d_capable;
 static int __read_mostly ioremap_pud_capable;
 static int __read_mostly ioremap_pmd_capable;
 static int __read_mostly ioremap_huge_disabled;
@@ -35,6 +36,11 @@ void __init ioremap_huge_init(void)
 	}
 }
 
+static inline int ioremap_p4d_enabled(void)
+{
+	return ioremap_p4d_capable;
+}
+
 static inline int ioremap_pud_enabled(void)
 {
 	return ioremap_pud_capable;
@@ -46,6 +52,7 @@ static inline int ioremap_pmd_enabled(void)
 }
 
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int ioremap_p4d_enabled(void) { return 0; }
 static inline int ioremap_pud_enabled(void) { return 0; }
 static inline int ioremap_pmd_enabled(void) { return 0; }
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
@@ -94,14 +101,14 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 	return 0;
 }
 
-static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
+static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
 	pud_t *pud;
 	unsigned long next;
 
 	phys_addr -= addr;
-	pud = pud_alloc(&init_mm, pgd, addr);
+	pud = pud_alloc(&init_mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -120,6 +127,32 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
+static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	phys_addr -= addr;
+	p4d = p4d_alloc(&init_mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (ioremap_p4d_enabled() &&
+		    ((next - addr) == P4D_SIZE) &&
+		    IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
+			if (p4d_set_huge(p4d, phys_addr + addr, prot))
+				continue;
+		}
+
+		if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 int ioremap_page_range(unsigned long addr,
 		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
@@ -135,7 +168,7 @@ int ioremap_page_range(unsigned long addr,
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot);
+		err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e68604ae3ced..4952311422c1 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -413,7 +413,7 @@ void iov_iter_init(struct iov_iter *i, int direction,
 			size_t count)
 {
 	/* It will get better.  Eventually... */
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (uaccess_kernel()) {
 		direction |= ITER_KVEC;
 		i->type = direction;
 		i->kvec = (struct kvec *)iov;
@@ -604,7 +604,7 @@ size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 		return 0;
 	}
 	iterate_and_advance(i, bytes, v,
-		__copy_from_user_nocache((to += v.iov_len) - v.iov_len,
+		__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
 					 v.iov_base, v.iov_len),
 		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
 				 v.bv_offset, v.bv_len),
@@ -625,7 +625,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
 	if (unlikely(i->count < bytes))
 		return false;
 	iterate_all_kinds(i, bytes, v, ({
-		if (__copy_from_user_nocache((to += v.iov_len) - v.iov_len,
+		if (__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
 					     v.iov_base, v.iov_len))
 			return false;
 		0;}),
@@ -786,6 +786,68 @@ void iov_iter_advance(struct iov_iter *i, size_t size)
 }
 EXPORT_SYMBOL(iov_iter_advance);
 
+void iov_iter_revert(struct iov_iter *i, size_t unroll)
+{
+	if (!unroll)
+		return;
+	i->count += unroll;
+	if (unlikely(i->type & ITER_PIPE)) {
+		struct pipe_inode_info *pipe = i->pipe;
+		int idx = i->idx;
+		size_t off = i->iov_offset;
+		while (1) {
+			size_t n = off - pipe->bufs[idx].offset;
+			if (unroll < n) {
+				off -= unroll;
+				break;
+			}
+			unroll -= n;
+			if (!unroll && idx == i->start_idx) {
+				off = 0;
+				break;
+			}
+			if (!idx--)
+				idx = pipe->buffers - 1;
+			off = pipe->bufs[idx].offset + pipe->bufs[idx].len;
+		}
+		i->iov_offset = off;
+		i->idx = idx;
+		pipe_truncate(i);
+		return;
+	}
+	if (unroll <= i->iov_offset) {
+		i->iov_offset -= unroll;
+		return;
+	}
+	unroll -= i->iov_offset;
+	if (i->type & ITER_BVEC) {
+		const struct bio_vec *bvec = i->bvec;
+		while (1) {
+			size_t n = (--bvec)->bv_len;
+			i->nr_segs++;
+			if (unroll <= n) {
+				i->bvec = bvec;
+				i->iov_offset = n - unroll;
+				return;
+			}
+			unroll -= n;
+		}
+	} else { /* same logics for iovec and kvec */
+		const struct iovec *iov = i->iov;
+		while (1) {
+			size_t n = (--iov)->iov_len;
+			i->nr_segs++;
+			if (unroll <= n) {
+				i->iov = iov;
+				i->iov_offset = n - unroll;
+				return;
+			}
+			unroll -= n;
+		}
+	}
+}
+EXPORT_SYMBOL(iov_iter_revert);
+
 /*
  * Return the count of just the current iov_iter segment.
  */
@@ -839,6 +901,7 @@ void iov_iter_pipe(struct iov_iter *i, int direction,
 	i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
 	i->iov_offset = 0;
 	i->count = count;
+	i->start_idx = i->idx;
 }
 EXPORT_SYMBOL(iov_iter_pipe);
 
diff --git a/lib/kobject.c b/lib/kobject.c
index 445dcaeb0f56..763d70a18941 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -601,12 +601,15 @@ struct kobject *kobject_get(struct kobject *kobj)
 }
 EXPORT_SYMBOL(kobject_get);
 
-static struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj)
+struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj)
 {
+	if (!kobj)
+		return NULL;
 	if (!kref_get_unless_zero(&kobj->kref))
 		kobj = NULL;
 	return kobj;
 }
+EXPORT_SYMBOL(kobject_get_unless_zero);
 
 /*
  * kobject_cleanup - free kobject resources.
diff --git a/lib/md5.c b/lib/md5.c
deleted file mode 100644
index bb0cd01d356d..000000000000
--- a/lib/md5.c
+++ /dev/null
@@ -1,95 +0,0 @@
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/cryptohash.h>
-
-#define F1(x, y, z)	(z ^ (x & (y ^ z)))
-#define F2(x, y, z)	F1(z, x, y)
-#define F3(x, y, z)	(x ^ y ^ z)
-#define F4(x, y, z)	(y ^ (x | ~z))
-
-#define MD5STEP(f, w, x, y, z, in, s) \
-	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
-
-void md5_transform(__u32 *hash, __u32 const *in)
-{
-	u32 a, b, c, d;
-
-	a = hash[0];
-	b = hash[1];
-	c = hash[2];
-	d = hash[3];
-
-	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
-	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
-	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
-	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
-	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
-	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
-	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
-	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
-	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
-	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
-	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
-	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
-	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
-	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
-	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
-	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
-
-	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
-	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
-	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
-	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
-	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
-	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
-	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
-	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
-	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
-	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
-	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
-	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
-	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
-	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
-	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
-	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
-
-	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
-	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
-	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
-	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
-	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
-	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
-	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
-	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
-	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
-	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
-	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
-	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
-	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
-	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
-	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
-	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
-
-	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
-	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
-	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
-	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
-	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
-	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
-	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
-	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
-	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
-	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
-	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
-	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
-	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
-	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
-	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
-	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
-
-	hash[0] += a;
-	hash[1] += b;
-	hash[2] += c;
-	hash[3] += d;
-}
-EXPORT_SYMBOL(md5_transform);
diff --git a/lib/nlattr.c b/lib/nlattr.c
index b42b8577fc23..a7e0b16078df 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -112,6 +112,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
  * @len: length of attribute stream
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @extack: extended ACK report struct
  *
  * Validates all attributes in the specified attribute stream against the
  * specified policy. Attributes with a type exceeding maxtype will be
@@ -120,20 +121,23 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
  * Returns 0 on success or a negative error code.
  */
 int nla_validate(const struct nlattr *head, int len, int maxtype,
-		 const struct nla_policy *policy)
+		 const struct nla_policy *policy,
+		 struct netlink_ext_ack *extack)
 {
 	const struct nlattr *nla;
-	int rem, err;
+	int rem;
 
 	nla_for_each_attr(nla, head, len, rem) {
-		err = validate_nla(nla, maxtype, policy);
-		if (err < 0)
-			goto errout;
+		int err = validate_nla(nla, maxtype, policy);
+
+		if (err < 0) {
+			if (extack)
+				extack->bad_attr = nla;
+			return err;
+		}
 	}
 
-	err = 0;
-errout:
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL(nla_validate);
 
@@ -180,7 +184,8 @@ EXPORT_SYMBOL(nla_policy_len);
  * Returns 0 on success or a negative error code.
  */
 int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
-	      int len, const struct nla_policy *policy)
+	      int len, const struct nla_policy *policy,
+	      struct netlink_ext_ack *extack)
 {
 	const struct nlattr *nla;
 	int rem, err;
@@ -193,8 +198,11 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
 		if (type > 0 && type <= maxtype) {
 			if (policy) {
 				err = validate_nla(nla, maxtype, policy);
-				if (err < 0)
+				if (err < 0) {
+					if (extack)
+						extack->bad_attr = nla;
 					goto errout;
+				}
 			}
 
 			tb[type] = (struct nlattr *)nla;
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 5ed506d648c4..691a9ad48497 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -2129,8 +2129,8 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
 		struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp);
 		if (!bitmap)
 			return 0;
-		bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap);
-		kfree(bitmap);
+		if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap))
+			kfree(bitmap);
 	}
 
 	return 1;
diff --git a/lib/refcount.c b/lib/refcount.c
index 1d33366189d1..f42124ccf295 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -37,11 +37,29 @@
 #include <linux/refcount.h>
 #include <linux/bug.h>
 
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
 bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 {
-	unsigned int old, new, val = atomic_read(&r->refs);
+	unsigned int new, val = atomic_read(&r->refs);
 
-	for (;;) {
+	do {
 		if (!val)
 			return false;
 
@@ -51,37 +69,54 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 		new = val + i;
 		if (new < val)
 			new = UINT_MAX;
-		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
-		if (old == val)
-			break;
 
-		val = old;
-	}
+	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
 
-	WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
 
 	return true;
 }
 EXPORT_SYMBOL_GPL(refcount_add_not_zero);
 
+/**
+ * refcount_add - add a value to a refcount
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_add(), but will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ */
 void refcount_add(unsigned int i, refcount_t *r)
 {
-	WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_add);
 
-/*
- * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+/**
+ * refcount_inc_not_zero - increment a refcount unless it is 0
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
  *
  * Provides no memory ordering, it is assumed the caller has guaranteed the
  * object memory to be stable (RCU, etc.). It does provide a control dependency
  * and thereby orders future stores. See the comment on top.
+ *
+ * Return: true if the increment was successful, false otherwise
  */
 bool refcount_inc_not_zero(refcount_t *r)
 {
-	unsigned int old, new, val = atomic_read(&r->refs);
+	unsigned int new, val = atomic_read(&r->refs);
 
-	for (;;) {
+	do {
 		new = val + 1;
 
 		if (!val)
@@ -90,63 +125,84 @@ bool refcount_inc_not_zero(refcount_t *r)
 		if (unlikely(!new))
 			return true;
 
-		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
+	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
 
-	WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
 
 	return true;
 }
 EXPORT_SYMBOL_GPL(refcount_inc_not_zero);
 
-/*
- * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+/**
+ * refcount_inc - increment a refcount
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
  *
  * Provides no memory ordering, it is assumed the caller already has a
- * reference on the object, will WARN when this is not so.
+ * reference on the object.
+ *
+ * Will WARN if the refcount is 0, as this represents a possible use-after-free
+ * condition.
  */
 void refcount_inc(refcount_t *r)
 {
-	WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_inc);
 
+/**
+ * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * @i: amount to subtract from the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec_and_test(), but it will WARN, return false and
+ * ultimately leak on underflow and will fail to decrement when saturated
+ * at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_dec(), or one of its variants, should instead be used to
+ * decrement a reference count.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
+ */
 bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 {
-	unsigned int old, new, val = atomic_read(&r->refs);
+	unsigned int new, val = atomic_read(&r->refs);
 
-	for (;;) {
+	do {
 		if (unlikely(val == UINT_MAX))
 			return false;
 
 		new = val - i;
 		if (new > val) {
-			WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
 			return false;
 		}
 
-		old = atomic_cmpxchg_release(&r->refs, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
+	} while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
 
 	return !new;
 }
 EXPORT_SYMBOL_GPL(refcount_sub_and_test);
 
-/*
+/**
+ * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * @r: the refcount
+ *
  * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
  * decrement when saturated at UINT_MAX.
  *
  * Provides release memory ordering, such that prior loads and stores are done
  * before, and provides a control dependency such that free() must come after.
  * See the comment on top.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
  */
 bool refcount_dec_and_test(refcount_t *r)
 {
@@ -154,21 +210,26 @@ bool refcount_dec_and_test(refcount_t *r)
 }
 EXPORT_SYMBOL_GPL(refcount_dec_and_test);
 
-/*
+/**
+ * refcount_dec - decrement a refcount
+ * @r: the refcount
+ *
  * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
  * when saturated at UINT_MAX.
  *
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-
 void refcount_dec(refcount_t *r)
 {
-	WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_dec);
 
-/*
+/**
+ * refcount_dec_if_one - decrement a refcount if it is 1
+ * @r: the refcount
+ *
  * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the
  * success thereof.
  *
@@ -178,24 +239,33 @@ EXPORT_SYMBOL_GPL(refcount_dec);
  * It can be used like a try-delete operator; this explicit case is provided
  * and not cmpxchg in generic, because that would allow implementing unsafe
  * operations.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
  */
 bool refcount_dec_if_one(refcount_t *r)
 {
-	return atomic_cmpxchg_release(&r->refs, 1, 0) == 1;
+	int val = 1;
+
+	return atomic_try_cmpxchg_release(&r->refs, &val, 0);
 }
 EXPORT_SYMBOL_GPL(refcount_dec_if_one);
 
-/*
+/**
+ * refcount_dec_not_one - decrement a refcount if it is not 1
+ * @r: the refcount
+ *
  * No atomic_t counterpart, it decrements unless the value is 1, in which case
  * it will return false.
  *
  * Was often done like: atomic_add_unless(&var, -1, 1)
+ *
+ * Return: true if the decrement operation was successful, false otherwise
  */
 bool refcount_dec_not_one(refcount_t *r)
 {
-	unsigned int old, new, val = atomic_read(&r->refs);
+	unsigned int new, val = atomic_read(&r->refs);
 
-	for (;;) {
+	do {
 		if (unlikely(val == UINT_MAX))
 			return true;
 
@@ -204,28 +274,31 @@ bool refcount_dec_not_one(refcount_t *r)
 
 		new = val - 1;
 		if (new > val) {
-			WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
 			return true;
 		}
 
-		old = atomic_cmpxchg_release(&r->refs, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
+	} while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
 
 	return true;
 }
 EXPORT_SYMBOL_GPL(refcount_dec_not_one);
 
-/*
+/**
+ * refcount_dec_and_mutex_lock - return holding mutex if able to decrement
+ *                               refcount to 0
+ * @r: the refcount
+ * @lock: the mutex to be locked
+ *
  * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail
  * to decrement when saturated at UINT_MAX.
  *
  * Provides release memory ordering, such that prior loads and stores are done
  * before, and provides a control dependency such that free() must come after.
  * See the comment on top.
+ *
+ * Return: true and hold mutex if able to decrement refcount to 0, false
+ *         otherwise
  */
 bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock)
 {
@@ -242,13 +315,21 @@ bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock)
 }
 EXPORT_SYMBOL_GPL(refcount_dec_and_mutex_lock);
 
-/*
+/**
+ * refcount_dec_and_lock - return holding spinlock if able to decrement
+ *                         refcount to 0
+ * @r: the refcount
+ * @lock: the spinlock to be locked
+ *
  * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to
  * decrement when saturated at UINT_MAX.
  *
  * Provides release memory ordering, such that prior loads and stores are done
  * before, and provides a control dependency such that free() must come after.
  * See the comment on top.
+ *
+ * Return: true and hold spinlock if able to decrement refcount to 0, false
+ *         otherwise
  */
 bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock)
 {
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index f8635fd57442..a930e436db5d 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -535,7 +535,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 	struct rhash_head *head;
 	int elasticity;
 
-	elasticity = ht->elasticity;
+	elasticity = RHT_ELASTICITY;
 	pprev = rht_bucket_var(tbl, hash);
 	rht_for_each_continue(head, *pprev, tbl, hash) {
 		struct rhlist_head *list;
@@ -958,35 +958,20 @@ int rhashtable_init(struct rhashtable *ht,
 	if (params->min_size)
 		ht->p.min_size = roundup_pow_of_two(params->min_size);
 
-	if (params->max_size)
-		ht->p.max_size = rounddown_pow_of_two(params->max_size);
+	/* Cap total entries at 2^31 to avoid nelems overflow. */
+	ht->max_elems = 1u << 31;
 
-	if (params->insecure_max_entries)
-		ht->p.insecure_max_entries =
-			rounddown_pow_of_two(params->insecure_max_entries);
-	else
-		ht->p.insecure_max_entries = ht->p.max_size * 2;
+	if (params->max_size) {
+		ht->p.max_size = rounddown_pow_of_two(params->max_size);
+		if (ht->p.max_size < ht->max_elems / 2)
+			ht->max_elems = ht->p.max_size * 2;
+	}
 
-	ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE);
+	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
 
 	if (params->nelem_hint)
 		size = rounded_hashtable_size(&ht->p);
 
-	/* The maximum (not average) chain length grows with the
-	 * size of the hash table, at a rate of (log N)/(log log N).
-	 * The value of 16 is selected so that even if the hash
-	 * table grew to 2^32 you would not expect the maximum
-	 * chain length to exceed it unless we are under attack
-	 * (or extremely unlucky).
-	 *
-	 * As this limit is only to detect attacks, we don't need
-	 * to set it to a lower value as you'd need the chain
-	 * length to vastly exceed 16 to have any real effect
-	 * on the system.
-	 */
-	if (!params->insecure_elasticity)
-		ht->elasticity = 16;
-
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
 	else
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 60e800e0b5a0..80aa8d5463fa 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -79,15 +79,15 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth)
 }
 EXPORT_SYMBOL_GPL(sbitmap_resize);
 
-static int __sbitmap_get_word(struct sbitmap_word *word, unsigned int hint,
-			      bool wrap)
+static int __sbitmap_get_word(unsigned long *word, unsigned long depth,
+			      unsigned int hint, bool wrap)
 {
 	unsigned int orig_hint = hint;
 	int nr;
 
 	while (1) {
-		nr = find_next_zero_bit(&word->word, word->depth, hint);
-		if (unlikely(nr >= word->depth)) {
+		nr = find_next_zero_bit(word, depth, hint);
+		if (unlikely(nr >= depth)) {
 			/*
 			 * We started with an offset, and we didn't reset the
 			 * offset to 0 in a failure case, so start from 0 to
@@ -100,11 +100,11 @@ static int __sbitmap_get_word(struct sbitmap_word *word, unsigned int hint,
 			return -1;
 		}
 
-		if (!test_and_set_bit(nr, &word->word))
+		if (!test_and_set_bit(nr, word))
 			break;
 
 		hint = nr + 1;
-		if (hint >= word->depth - 1)
+		if (hint >= depth - 1)
 			hint = 0;
 	}
 
@@ -119,7 +119,8 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin)
 	index = SB_NR_TO_INDEX(sb, alloc_hint);
 
 	for (i = 0; i < sb->map_nr; i++) {
-		nr = __sbitmap_get_word(&sb->map[index],
+		nr = __sbitmap_get_word(&sb->map[index].word,
+					sb->map[index].depth,
 					SB_NR_TO_BIT(sb, alloc_hint),
 					!round_robin);
 		if (nr != -1) {
@@ -141,6 +142,37 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin)
 }
 EXPORT_SYMBOL_GPL(sbitmap_get);
 
+int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
+			unsigned long shallow_depth)
+{
+	unsigned int i, index;
+	int nr = -1;
+
+	index = SB_NR_TO_INDEX(sb, alloc_hint);
+
+	for (i = 0; i < sb->map_nr; i++) {
+		nr = __sbitmap_get_word(&sb->map[index].word,
+					min(sb->map[index].depth, shallow_depth),
+					SB_NR_TO_BIT(sb, alloc_hint), true);
+		if (nr != -1) {
+			nr += index << sb->shift;
+			break;
+		}
+
+		/* Jump to next index. */
+		index++;
+		alloc_hint = index << sb->shift;
+
+		if (index >= sb->map_nr) {
+			index = 0;
+			alloc_hint = 0;
+		}
+	}
+
+	return nr;
+}
+EXPORT_SYMBOL_GPL(sbitmap_get_shallow);
+
 bool sbitmap_any_bit_set(const struct sbitmap *sb)
 {
 	unsigned int i;
@@ -342,6 +374,35 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq)
 }
 EXPORT_SYMBOL_GPL(__sbitmap_queue_get);
 
+int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+				unsigned int shallow_depth)
+{
+	unsigned int hint, depth;
+	int nr;
+
+	hint = this_cpu_read(*sbq->alloc_hint);
+	depth = READ_ONCE(sbq->sb.depth);
+	if (unlikely(hint >= depth)) {
+		hint = depth ? prandom_u32() % depth : 0;
+		this_cpu_write(*sbq->alloc_hint, hint);
+	}
+	nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth);
+
+	if (nr == -1) {
+		/* If the map is full, a hint won't do us much good. */
+		this_cpu_write(*sbq->alloc_hint, 0);
+	} else if (nr == hint || unlikely(sbq->round_robin)) {
+		/* Only update the hint if we used it. */
+		hint = nr + 1;
+		if (hint >= depth - 1)
+			hint = 0;
+		this_cpu_write(*sbq->alloc_hint, hint);
+	}
+
+	return nr;
+}
+EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow);
+
 static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 {
 	int i, wake_index;
diff --git a/lib/string.c b/lib/string.c
index ed83562a53ae..b5c9a1168d3a 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -131,7 +131,7 @@ EXPORT_SYMBOL(strncpy);
  * @src: Where to copy the string from
  * @size: size of destination buffer
  *
- * Compatible with *BSD: the result is always a valid
+ * Compatible with ``*BSD``: the result is always a valid
  * NUL-terminated string that fits in the buffer (unless,
  * of course, the buffer size is zero). It does not pad
  * out the result like strncpy() does.
diff --git a/lib/syscall.c b/lib/syscall.c
index 17d5ff5fa6a3..2c6cd1b5c3ea 100644
--- a/lib/syscall.c
+++ b/lib/syscall.c
@@ -12,6 +12,7 @@ static int collect_syscall(struct task_struct *target, long *callno,
 
 	if (!try_get_task_stack(target)) {
 		/* Task has no stack, so the task isn't in a syscall. */
+		*sp = *pc = 0;
 		*callno = -1;
 		return 0;
 	}
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 0362da0b66c3..a0f66280ea50 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -434,6 +434,41 @@ loop:
 	return 0;
 }
 
+static int __bpf_fill_stxdw(struct bpf_test *self, int size)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	insn[0] = BPF_ALU32_IMM(BPF_MOV, R0, 1);
+	insn[1] = BPF_ST_MEM(size, R10, -40, 42);
+
+	for (i = 2; i < len - 2; i++)
+		insn[i] = BPF_STX_XADD(size, R10, R0, -40);
+
+	insn[len - 2] = BPF_LDX_MEM(size, R0, R10, -40);
+	insn[len - 1] = BPF_EXIT_INSN();
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_stxw(struct bpf_test *self)
+{
+	return __bpf_fill_stxdw(self, BPF_W);
+}
+
+static int bpf_fill_stxdw(struct bpf_test *self)
+{
+	return __bpf_fill_stxdw(self, BPF_DW);
+}
+
 static struct bpf_test tests[] = {
 	{
 		"TAX",
@@ -4303,6 +4338,41 @@ static struct bpf_test tests[] = {
 		{ { 0, 0x22 } },
 	},
 	{
+		"STX_XADD_W: Test side-effects, r10: 0x12 + 0x10 = 0x22",
+		.u.insns_int = {
+			BPF_ALU64_REG(BPF_MOV, R1, R10),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x10),
+			BPF_STX_XADD(BPF_W, R10, R0, -40),
+			BPF_ALU64_REG(BPF_MOV, R0, R10),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+	},
+	{
+		"STX_XADD_W: Test side-effects, r0: 0x12 + 0x10 = 0x22",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x10),
+			BPF_STX_XADD(BPF_W, R10, R0, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x12 } },
+	},
+	{
+		"STX_XADD_W: X + 1 + 1 + 1 + ...",
+		{ },
+		INTERNAL,
+		{ },
+		{ { 0, 4134 } },
+		.fill_helper = bpf_fill_stxw,
+	},
+	{
 		"STX_XADD_DW: Test: 0x12 + 0x10 = 0x22",
 		.u.insns_int = {
 			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
@@ -4315,6 +4385,41 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x22 } },
 	},
+	{
+		"STX_XADD_DW: Test side-effects, r10: 0x12 + 0x10 = 0x22",
+		.u.insns_int = {
+			BPF_ALU64_REG(BPF_MOV, R1, R10),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
+			BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
+			BPF_STX_XADD(BPF_DW, R10, R0, -40),
+			BPF_ALU64_REG(BPF_MOV, R0, R10),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+	},
+	{
+		"STX_XADD_DW: Test side-effects, r0: 0x12 + 0x10 = 0x22",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
+			BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
+			BPF_STX_XADD(BPF_DW, R10, R0, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x12 } },
+	},
+	{
+		"STX_XADD_DW: X + 1 + 1 + 1 + ...",
+		{ },
+		INTERNAL,
+		{ },
+		{ { 0, 4134 } },
+		.fill_helper = bpf_fill_stxdw,
+	},
 	/* BPF_JMP | BPF_EXIT */
 	{
 		"JMP_EXIT",
@@ -4656,6 +4761,51 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{
+		/* Mainly testing JIT + imm64 here. */
+		"JMP_JGE_X: ldimm64 test 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 2),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xeeeeeeeeU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 0),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffffU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 3",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 4),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
 	/* BPF_JMP | BPF_JNE | BPF_X */
 	{
 		"JMP_JNE_X: if (3 != 2) return 1",
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 0b1d3140fbb8..a25c9763fce1 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -20,6 +20,7 @@
 #include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
+#include <linux/kasan.h>
 
 /*
  * Note: test functions are marked noinline so that their names appear in
@@ -474,6 +475,12 @@ static noinline void __init use_after_scope_test(void)
 
 static int __init kmalloc_tests_init(void)
 {
+	/*
+	 * Temporarily enable multi-shot mode. Otherwise, we'd only get a
+	 * report for the first case.
+	 */
+	bool multishot = kasan_save_enable_multi_shot();
+
 	kmalloc_oob_right();
 	kmalloc_oob_left();
 	kmalloc_node_oob_right();
@@ -499,6 +506,9 @@ static int __init kmalloc_tests_init(void)
 	ksize_unpoisons_memory();
 	copy_user_test();
 	use_after_scope_test();
+
+	kasan_restore_multi_shot(multishot);
+
 	return -EAGAIN;
 }
 
diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 1a8d71a68531..4621db801b23 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -31,7 +31,6 @@
  * their capability at compile-time, we just have to opt-out certain archs.
  */
 #if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \
-			    !defined(CONFIG_AVR32) &&		\
 			    !defined(CONFIG_BLACKFIN) &&	\
 			    !defined(CONFIG_M32R) &&		\
 			    !defined(CONFIG_M68K) &&		\
diff --git a/lib/usercopy.c b/lib/usercopy.c
new file mode 100644
index 000000000000..1b6010a3beb8
--- /dev/null
+++ b/lib/usercopy.c
@@ -0,0 +1,26 @@
+#include <linux/uaccess.h>
+
+/* out-of-line parts */
+
+#ifndef INLINE_COPY_FROM_USER
+unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long res = n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = raw_copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
+}
+EXPORT_SYMBOL(_copy_from_user);
+#endif
+
+#ifndef INLINE_COPY_TO_USER
+unsigned long _copy_to_user(void *to, const void __user *from, unsigned long n)
+{
+	if (likely(access_ok(VERIFY_WRITE, to, n)))
+		n = raw_copy_to_user(to, from, n);
+	return n;
+}
+EXPORT_SYMBOL(_copy_to_user);
+#endif
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index e3bf4e0f10b5..176641cc549d 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1954,13 +1954,13 @@ set_precision(struct printf_spec *spec, int prec)
  * This function generally follows C99 vsnprintf, but has some
  * extensions and a few limitations:
  *
- * %n is unsupported
- * %p* is handled by pointer()
+ *  - ``%n`` is unsupported
+ *  - ``%p*`` is handled by pointer()
  *
  * See pointer() or Documentation/printk-formats.txt for more
  * extensive description.
  *
- * ** Please update the documentation in both places when making changes **
+ * **Please update the documentation in both places when making changes**
  *
  * The return value is the number of characters which would
  * be generated for the given input, excluding the trailing
diff --git a/mm/Kconfig b/mm/Kconfig
index 9b8fccb969dc..beb7a455915d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -312,7 +312,6 @@ config NEED_BOUNCE_POOL
 config NR_QUICK
 	int
 	depends on QUICKLIST
-	default "2" if AVR32
 	default "1"
 
 config VIRT_TO_BUS
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6d861d090e9f..f028a9a472fd 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -12,8 +12,6 @@
 #include <linux/device.h>
 #include <trace/events/writeback.h>
 
-static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
@@ -242,6 +240,8 @@ static __init int bdi_class_init(void)
 }
 postcore_initcall(bdi_class_init);
 
+static int bdi_init(struct backing_dev_info *bdi);
+
 static int __init default_bdi_init(void)
 {
 	int err;
@@ -294,6 +294,8 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 
 	memset(wb, 0, sizeof(*wb));
 
+	if (wb != &bdi->wb)
+		bdi_get(bdi);
 	wb->bdi = bdi;
 	wb->last_old_flush = jiffies;
 	INIT_LIST_HEAD(&wb->b_dirty);
@@ -314,8 +316,10 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	wb->dirty_sleep = jiffies;
 
 	wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp);
-	if (!wb->congested)
-		return -ENOMEM;
+	if (!wb->congested) {
+		err = -ENOMEM;
+		goto out_put_bdi;
+	}
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
@@ -335,9 +339,14 @@ out_destroy_stat:
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:
 	wb_congested_put(wb->congested);
+out_put_bdi:
+	if (wb != &bdi->wb)
+		bdi_put(bdi);
 	return err;
 }
 
+static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
+
 /*
  * Remove bdi from the global list and shutdown any threads we have running
  */
@@ -347,10 +356,18 @@ static void wb_shutdown(struct bdi_writeback *wb)
 	spin_lock_bh(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
 		spin_unlock_bh(&wb->work_lock);
+		/*
+		 * Wait for wb shutdown to finish if someone else is just
+		 * running wb_shutdown(). Otherwise we could proceed to wb /
+		 * bdi destruction before wb_shutdown() is finished.
+		 */
+		wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
 		return;
 	}
+	set_bit(WB_shutting_down, &wb->state);
 	spin_unlock_bh(&wb->work_lock);
 
+	cgwb_remove_from_bdi_list(wb);
 	/*
 	 * Drain work list and shutdown the delayed_work.  !WB_registered
 	 * tells wb_workfn() that @wb is dying and its work_list needs to
@@ -359,6 +376,12 @@ static void wb_shutdown(struct bdi_writeback *wb)
 	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	flush_delayed_work(&wb->dwork);
 	WARN_ON(!list_empty(&wb->work_list));
+	/*
+	 * Make sure bit gets cleared after shutdown is finished. Matches with
+	 * the barrier provided by test_and_clear_bit() above.
+	 */
+	smp_wmb();
+	clear_bit(WB_shutting_down, &wb->state);
 }
 
 static void wb_exit(struct bdi_writeback *wb)
@@ -372,6 +395,8 @@ static void wb_exit(struct bdi_writeback *wb)
 
 	fprop_local_destroy_percpu(&wb->completions);
 	wb_congested_put(wb->congested);
+	if (wb != &wb->bdi->wb)
+		bdi_put(wb->bdi);
 }
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -381,11 +406,9 @@ static void wb_exit(struct bdi_writeback *wb)
 /*
  * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree,
  * blkcg->cgwb_list, and memcg->cgwb_list.  bdi->cgwb_tree is also RCU
- * protected.  cgwb_release_wait is used to wait for the completion of cgwb
- * releases from bdi destruction path.
+ * protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
-static DECLARE_WAIT_QUEUE_HEAD(cgwb_release_wait);
 
 /**
  * wb_congested_get_create - get or create a wb_congested
@@ -438,7 +461,7 @@ retry:
 		return NULL;
 
 	atomic_set(&new_congested->refcnt, 0);
-	new_congested->bdi = bdi;
+	new_congested->__bdi = bdi;
 	new_congested->blkcg_id = blkcg_id;
 	goto retry;
 
@@ -466,10 +489,10 @@ void wb_congested_put(struct bdi_writeback_congested *congested)
 	}
 
 	/* bdi might already have been destroyed leaving @congested unlinked */
-	if (congested->bdi) {
+	if (congested->__bdi) {
 		rb_erase(&congested->rb_node,
-			 &congested->bdi->cgwb_congested_tree);
-		congested->bdi = NULL;
+			 &congested->__bdi->cgwb_congested_tree);
+		congested->__bdi = NULL;
 	}
 
 	spin_unlock_irqrestore(&cgwb_lock, flags);
@@ -480,11 +503,6 @@ static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
-	struct backing_dev_info *bdi = wb->bdi;
-
-	spin_lock_irq(&cgwb_lock);
-	list_del_rcu(&wb->bdi_node);
-	spin_unlock_irq(&cgwb_lock);
 
 	wb_shutdown(wb);
 
@@ -495,9 +513,6 @@ static void cgwb_release_workfn(struct work_struct *work)
 	percpu_ref_exit(&wb->refcnt);
 	wb_exit(wb);
 	kfree_rcu(wb, rcu);
-
-	if (atomic_dec_and_test(&bdi->usage_cnt))
-		wake_up_all(&cgwb_release_wait);
 }
 
 static void cgwb_release(struct percpu_ref *refcnt)
@@ -517,6 +532,13 @@ static void cgwb_kill(struct bdi_writeback *wb)
 	percpu_ref_kill(&wb->refcnt);
 }
 
+static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb)
+{
+	spin_lock_irq(&cgwb_lock);
+	list_del_rcu(&wb->bdi_node);
+	spin_unlock_irq(&cgwb_lock);
+}
+
 static int cgwb_create(struct backing_dev_info *bdi,
 		       struct cgroup_subsys_state *memcg_css, gfp_t gfp)
 {
@@ -580,7 +602,6 @@ static int cgwb_create(struct backing_dev_info *bdi,
 		/* we might have raced another instance of this function */
 		ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb);
 		if (!ret) {
-			atomic_inc(&bdi->usage_cnt);
 			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
@@ -670,7 +691,6 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 
 	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
 	bdi->cgwb_congested_tree = RB_ROOT;
-	atomic_set(&bdi->usage_cnt, 1);
 
 	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
 	if (!ret) {
@@ -680,36 +700,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	return ret;
 }
 
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
 {
 	struct radix_tree_iter iter;
-	struct rb_node *rbn;
 	void **slot;
+	struct bdi_writeback *wb;
 
 	WARN_ON(test_bit(WB_registered, &bdi->wb.state));
 
 	spin_lock_irq(&cgwb_lock);
-
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
 
-	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
-		struct bdi_writeback_congested *congested =
-			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
-
-		rb_erase(rbn, &bdi->cgwb_congested_tree);
-		congested->bdi = NULL;	/* mark @congested unlinked */
+	while (!list_empty(&bdi->wb_list)) {
+		wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
+				      bdi_node);
+		spin_unlock_irq(&cgwb_lock);
+		wb_shutdown(wb);
+		spin_lock_irq(&cgwb_lock);
 	}
-
 	spin_unlock_irq(&cgwb_lock);
-
-	/*
-	 * All cgwb's and their congested states must be shutdown and
-	 * released before returning.  Drain the usage counter to wait for
-	 * all cgwb's and cgwb_congested's ever created on @bdi.
-	 */
-	atomic_dec(&bdi->usage_cnt);
-	wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt));
 }
 
 /**
@@ -749,6 +759,28 @@ void wb_blkcg_offline(struct blkcg *blkcg)
 	spin_unlock_irq(&cgwb_lock);
 }
 
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
+{
+	struct rb_node *rbn;
+
+	spin_lock_irq(&cgwb_lock);
+	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
+		struct bdi_writeback_congested *congested =
+			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
+
+		rb_erase(rbn, &bdi->cgwb_congested_tree);
+		congested->__bdi = NULL;	/* mark @congested unlinked */
+	}
+	spin_unlock_irq(&cgwb_lock);
+}
+
+static void cgwb_bdi_register(struct backing_dev_info *bdi)
+{
+	spin_lock_irq(&cgwb_lock);
+	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
+	spin_unlock_irq(&cgwb_lock);
+}
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static int cgwb_bdi_init(struct backing_dev_info *bdi)
@@ -769,14 +801,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	return 0;
 }
 
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { }
+
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
 {
 	wb_congested_put(bdi->wb_congested);
 }
 
+static void cgwb_bdi_register(struct backing_dev_info *bdi)
+{
+	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
+}
+
+static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb)
+{
+	list_del_rcu(&wb->bdi_node);
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
-int bdi_init(struct backing_dev_info *bdi)
+static int bdi_init(struct backing_dev_info *bdi)
 {
 	int ret;
 
@@ -792,11 +836,8 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	ret = cgwb_bdi_init(bdi);
 
-	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
-
 	return ret;
 }
-EXPORT_SYMBOL(bdi_init);
 
 struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id)
 {
@@ -813,22 +854,20 @@ struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id)
 	}
 	return bdi;
 }
+EXPORT_SYMBOL(bdi_alloc_node);
 
-int bdi_register(struct backing_dev_info *bdi, struct device *parent,
-		const char *fmt, ...)
+int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
 {
-	va_list args;
 	struct device *dev;
 
 	if (bdi->dev)	/* The driver needs to use separate queues per device */
 		return 0;
 
-	va_start(args, fmt);
-	dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
-	va_end(args);
+	dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args);
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
+	cgwb_bdi_register(bdi);
 	bdi->dev = dev;
 
 	bdi_debug_register(bdi, dev_name(dev));
@@ -841,22 +880,29 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 	trace_writeback_bdi_register(bdi);
 	return 0;
 }
-EXPORT_SYMBOL(bdi_register);
+EXPORT_SYMBOL(bdi_register_va);
 
-int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
+int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...)
 {
-	return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev));
+	va_list args;
+	int ret;
+
+	va_start(args, fmt);
+	ret = bdi_register_va(bdi, fmt, args);
+	va_end(args);
+	return ret;
 }
-EXPORT_SYMBOL(bdi_register_dev);
+EXPORT_SYMBOL(bdi_register);
 
 int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner)
 {
 	int rc;
 
-	rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt),
-			MINOR(owner->devt));
+	rc = bdi_register(bdi, "%u:%u", MAJOR(owner->devt), MINOR(owner->devt));
 	if (rc)
 		return rc;
+	/* Leaking owner reference... */
+	WARN_ON(bdi->owner);
 	bdi->owner = owner;
 	get_device(owner);
 	return 0;
@@ -880,7 +926,7 @@ void bdi_unregister(struct backing_dev_info *bdi)
 	/* make sure nobody finds us on the bdi_list anymore */
 	bdi_remove_from_list(bdi);
 	wb_shutdown(&bdi->wb);
-	cgwb_bdi_destroy(bdi);
+	cgwb_bdi_unregister(bdi);
 
 	if (bdi->dev) {
 		bdi_debug_unregister(bdi);
@@ -894,18 +940,16 @@ void bdi_unregister(struct backing_dev_info *bdi)
 	}
 }
 
-static void bdi_exit(struct backing_dev_info *bdi)
-{
-	WARN_ON_ONCE(bdi->dev);
-	wb_exit(&bdi->wb);
-}
-
 static void release_bdi(struct kref *ref)
 {
 	struct backing_dev_info *bdi =
 			container_of(ref, struct backing_dev_info, refcnt);
 
-	bdi_exit(bdi);
+	if (test_bit(WB_registered, &bdi->wb.state))
+		bdi_unregister(bdi);
+	WARN_ON_ONCE(bdi->dev);
+	wb_exit(&bdi->wb);
+	cgwb_bdi_exit(bdi);
 	kfree(bdi);
 }
 
@@ -913,38 +957,7 @@ void bdi_put(struct backing_dev_info *bdi)
 {
 	kref_put(&bdi->refcnt, release_bdi);
 }
-
-void bdi_destroy(struct backing_dev_info *bdi)
-{
-	bdi_unregister(bdi);
-	bdi_exit(bdi);
-}
-EXPORT_SYMBOL(bdi_destroy);
-
-/*
- * For use from filesystems to quickly init and register a bdi associated
- * with dirty writeback
- */
-int bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
-{
-	int err;
-
-	bdi->name = name;
-	bdi->capabilities = 0;
-	err = bdi_init(bdi);
-	if (err)
-		return err;
-
-	err = bdi_register(bdi, NULL, "%.28s-%ld", name,
-			   atomic_long_inc_return(&bdi_seq));
-	if (err) {
-		bdi_destroy(bdi);
-		return err;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(bdi_setup_and_register);
+EXPORT_SYMBOL(bdi_put);
 
 static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
diff --git a/mm/filemap.c b/mm/filemap.c
index 1694623a6289..dc59c5f35b37 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -519,7 +519,7 @@ EXPORT_SYMBOL(filemap_write_and_wait);
  *
  * Write out and wait upon file offsets lstart->lend, inclusive.
  *
- * Note that `lend' is inclusive (describes the last byte to be written) so
+ * Note that @lend is inclusive (describes the last byte to be written) so
  * that this function can be used to write to the very end-of-file (end = -1).
  */
 int filemap_write_and_wait_range(struct address_space *mapping,
@@ -1277,12 +1277,14 @@ EXPORT_SYMBOL(find_lock_entry);
  *
  * PCG flags modify how the page is returned.
  *
- * FGP_ACCESSED: the page will be marked accessed
- * FGP_LOCK: Page is return locked
- * FGP_CREAT: If page is not present then a new page is allocated using
- *		@gfp_mask and added to the page cache and the VM's LRU
- *		list. The page is returned locked and with an increased
- *		refcount. Otherwise, %NULL is returned.
+ * @fgp_flags can be:
+ *
+ * - FGP_ACCESSED: the page will be marked accessed
+ * - FGP_LOCK: Page is return locked
+ * - FGP_CREAT: If page is not present then a new page is allocated using
+ *   @gfp_mask and added to the page cache and the VM's LRU
+ *   list. The page is returned locked and with an increased
+ *   refcount. Otherwise, NULL is returned.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
@@ -2033,7 +2035,6 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
-		struct iov_iter data = *iter;
 		loff_t size;
 
 		size = i_size_read(inode);
@@ -2044,11 +2045,12 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 		file_accessed(file);
 
-		retval = mapping->a_ops->direct_IO(iocb, &data);
+		retval = mapping->a_ops->direct_IO(iocb, iter);
 		if (retval >= 0) {
 			iocb->ki_pos += retval;
-			iov_iter_advance(iter, retval);
+			count -= retval;
 		}
+		iov_iter_revert(iter, iov_iter_count(iter) - count);
 
 		/*
 		 * Btrfs can have a short DIO read if we encounter
@@ -2059,7 +2061,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		 * the rest of the read.  Buffered reads will not work for
 		 * DAX files, so don't bother trying.
 		 */
-		if (retval < 0 || !iov_iter_count(iter) || iocb->ki_pos >= size ||
+		if (retval < 0 || !count || iocb->ki_pos >= size ||
 		    IS_DAX(inode))
 			goto out;
 	}
@@ -2704,7 +2706,6 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t		written;
 	size_t		write_len;
 	pgoff_t		end;
-	struct iov_iter data;
 
 	write_len = iov_iter_count(from);
 	end = (pos + write_len - 1) >> PAGE_SHIFT;
@@ -2733,8 +2734,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 		}
 	}
 
-	data = *from;
-	written = mapping->a_ops->direct_IO(iocb, &data);
+	written = mapping->a_ops->direct_IO(iocb, from);
 
 	/*
 	 * Finally, try again to invalidate clean pages which might have been
@@ -2751,13 +2751,14 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 
 	if (written > 0) {
 		pos += written;
-		iov_iter_advance(from, written);
+		write_len -= written;
 		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
 			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
 		}
 		iocb->ki_pos = pos;
 	}
+	iov_iter_revert(from, write_len - iov_iter_count(from));
 out:
 	return written;
 }
@@ -3001,7 +3002,7 @@ EXPORT_SYMBOL(generic_file_write_iter);
  * @gfp_mask: memory allocation flags (and I/O mode)
  *
  * The address_space is to try to release any data against the page
- * (presumably at page->private).  If the release was successful, return `1'.
+ * (presumably at page->private).  If the release was successful, return '1'.
  * Otherwise return zero.
  *
  * This may also be called if PG_fscache is set on a page, indicating that the
diff --git a/mm/gup.c b/mm/gup.c
index 9c047e951aa3..527ec2c6cca3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned int *page_mask)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	spinlock_t *ptl;
@@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		return no_page_table(vma, flags);
-
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d))
+		return no_page_table(vma, flags);
+	BUILD_BUG_ON(p4d_huge(*p4d));
+	if (unlikely(p4d_bad(*p4d)))
+		return no_page_table(vma, flags);
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
@@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 		struct page **page)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 	else
 		pgd = pgd_offset_gate(mm, address);
 	BUG_ON(pgd_none(*pgd));
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	BUG_ON(p4d_none(*p4d));
+	pud = pud_offset(p4d, address);
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
@@ -1180,34 +1189,57 @@ struct page *get_dump_page(unsigned long addr)
  */
 #ifdef CONFIG_HAVE_GENERIC_RCU_GUP
 
+#ifndef gup_get_pte
+/*
+ * We assume that the PTE can be read atomically. If this is not the case for
+ * your architecture, please provide the helper.
+ */
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+	return READ_ONCE(*ptep);
+}
+#endif
+
+static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
+{
+	while ((*nr) - nr_start) {
+		struct page *page = pages[--(*nr)];
+
+		ClearPageReferenced(page);
+		put_page(page);
+	}
+}
+
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
 {
+	struct dev_pagemap *pgmap = NULL;
+	int nr_start = *nr, ret = 0;
 	pte_t *ptep, *ptem;
-	int ret = 0;
 
 	ptem = ptep = pte_offset_map(&pmd, addr);
 	do {
-		/*
-		 * In the line below we are assuming that the pte can be read
-		 * atomically. If this is not the case for your architecture,
-		 * please wrap this in a helper function!
-		 *
-		 * for an example see gup_get_pte in arch/x86/mm/gup.c
-		 */
-		pte_t pte = READ_ONCE(*ptep);
+		pte_t pte = gup_get_pte(ptep);
 		struct page *head, *page;
 
 		/*
 		 * Similar to the PMD case below, NUMA hinting must take slow
 		 * path using the pte_protnone check.
 		 */
-		if (!pte_present(pte) || pte_special(pte) ||
-			pte_protnone(pte) || (write && !pte_write(pte)))
+		if (pte_protnone(pte))
 			goto pte_unmap;
 
-		if (!arch_pte_access_permitted(pte, write))
+		if (!pte_access_permitted(pte, write))
+			goto pte_unmap;
+
+		if (pte_devmap(pte)) {
+			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
+			if (unlikely(!pgmap)) {
+				undo_dev_pagemap(nr, nr_start, pages);
+				goto pte_unmap;
+			}
+		} else if (pte_special(pte))
 			goto pte_unmap;
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
@@ -1223,6 +1255,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		}
 
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+
+		put_dev_pagemap(pgmap);
+		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
 
@@ -1252,15 +1287,76 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 }
 #endif /* __HAVE_ARCH_PTE_SPECIAL */
 
+#ifdef __HAVE_ARCH_PTE_DEVMAP
+static int __gup_device_huge(unsigned long pfn, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	int nr_start = *nr;
+	struct dev_pagemap *pgmap = NULL;
+
+	do {
+		struct page *page = pfn_to_page(pfn);
+
+		pgmap = get_dev_pagemap(pfn, pgmap);
+		if (unlikely(!pgmap)) {
+			undo_dev_pagemap(nr, nr_start, pages);
+			return 0;
+		}
+		SetPageReferenced(page);
+		pages[*nr] = page;
+		get_page(page);
+		put_dev_pagemap(pgmap);
+		(*nr)++;
+		pfn++;
+	} while (addr += PAGE_SIZE, addr != end);
+	return 1;
+}
+
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	unsigned long fault_pfn;
+
+	fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+}
+
+static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	unsigned long fault_pfn;
+
+	fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+}
+#else
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	BUILD_BUG();
+	return 0;
+}
+
+static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	BUILD_BUG();
+	return 0;
+}
+#endif
+
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	struct page *head, *page;
 	int refs;
 
-	if (write && !pmd_write(orig))
+	if (!pmd_access_permitted(orig, write))
 		return 0;
 
+	if (pmd_devmap(orig))
+		return __gup_device_huge_pmd(orig, addr, end, pages, nr);
+
 	refs = 0;
 	head = pmd_page(orig);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1284,6 +1380,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
+	SetPageReferenced(head);
 	return 1;
 }
 
@@ -1293,9 +1390,12 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	struct page *head, *page;
 	int refs;
 
-	if (write && !pud_write(orig))
+	if (!pud_access_permitted(orig, write))
 		return 0;
 
+	if (pud_devmap(orig))
+		return __gup_device_huge_pud(orig, addr, end, pages, nr);
+
 	refs = 0;
 	head = pud_page(orig);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
@@ -1319,6 +1419,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
+	SetPageReferenced(head);
 	return 1;
 }
 
@@ -1329,9 +1430,10 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 	int refs;
 	struct page *head, *page;
 
-	if (write && !pgd_write(orig))
+	if (!pgd_access_permitted(orig, write))
 		return 0;
 
+	BUILD_BUG_ON(pgd_devmap(orig));
 	refs = 0;
 	head = pgd_page(orig);
 	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
@@ -1355,6 +1457,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 	}
 
+	SetPageReferenced(head);
 	return 1;
 }
 
@@ -1400,13 +1503,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(&pgd, addr);
+	pudp = pud_offset(&p4d, addr);
 	do {
 		pud_t pud = READ_ONCE(*pudp);
 
@@ -1428,6 +1531,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	p4d_t *p4dp;
+
+	p4dp = p4d_offset(&pgd, addr);
+	do {
+		p4d_t p4d = READ_ONCE(*p4dp);
+
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(p4d))
+			return 0;
+		BUILD_BUG_ON(p4d_huge(p4d));
+		if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
+			if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
+					 P4D_SHIFT, next, write, pages, nr))
+				return 0;
+		} else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+			return 0;
+	} while (p4dp++, addr = next, addr != end);
+
+	return 1;
+}
+
 /*
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP. It will only return non-negative values.
@@ -1478,7 +1606,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
 					 PGDIR_SHIFT, next, write, pages, &nr))
 				break;
-		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		} else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);
@@ -1486,6 +1614,21 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	return nr;
 }
 
+#ifndef gup_fast_permitted
+/*
+ * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * we need to fall back to the slow version:
+ */
+bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	return end >= start;
+}
+#endif
+
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
@@ -1505,11 +1648,14 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
-	int nr, ret;
+	int nr = 0, ret = 0;
 
 	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	ret = nr;
+
+	if (gup_fast_permitted(start, nr_pages, write)) {
+		nr = __get_user_pages_fast(start, nr_pages, write, pages);
+		ret = nr;
+	}
 
 	if (nr < nr_pages) {
 		/* Try to get the remaining pages with get_user_pages */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d36b2af4d1bf..f3c4f9d22821 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -240,18 +240,18 @@ static ssize_t defrag_store(struct kobject *kobj,
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("defer", buf,
-		    min(sizeof("defer")-1, count))) {
-		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
-		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
-		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
-		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 	} else if (!memcmp("defer+madvise", buf,
 		    min(sizeof("defer+madvise")-1, count))) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("defer", buf,
+		    min(sizeof("defer")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 	} else if (!memcmp("madvise", buf,
 			   min(sizeof("madvise")-1, count))) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
@@ -1568,8 +1568,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		deactivate_page(page);
 
 	if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
-		orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
-			tlb->fullmm);
+		pmdp_invalidate(vma, addr, pmd);
 		orig_pmd = pmd_mkold(orig_pmd);
 		orig_pmd = pmd_mkclean(orig_pmd);
 
@@ -1724,37 +1723,69 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
-	int ret = 0;
+	pmd_t entry;
+	bool preserve_write;
+	int ret;
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
-	if (ptl) {
-		pmd_t entry;
-		bool preserve_write = prot_numa && pmd_write(*pmd);
-		ret = 1;
+	if (!ptl)
+		return 0;
 
-		/*
-		 * Avoid trapping faults against the zero page. The read-only
-		 * data is likely to be read-cached on the local CPU and
-		 * local/remote hits to the zero page are not interesting.
-		 */
-		if (prot_numa && is_huge_zero_pmd(*pmd)) {
-			spin_unlock(ptl);
-			return ret;
-		}
+	preserve_write = prot_numa && pmd_write(*pmd);
+	ret = 1;
 
-		if (!prot_numa || !pmd_protnone(*pmd)) {
-			entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
-			entry = pmd_modify(entry, newprot);
-			if (preserve_write)
-				entry = pmd_mk_savedwrite(entry);
-			ret = HPAGE_PMD_NR;
-			set_pmd_at(mm, addr, pmd, entry);
-			BUG_ON(vma_is_anonymous(vma) && !preserve_write &&
-					pmd_write(entry));
-		}
-		spin_unlock(ptl);
-	}
+	/*
+	 * Avoid trapping faults against the zero page. The read-only
+	 * data is likely to be read-cached on the local CPU and
+	 * local/remote hits to the zero page are not interesting.
+	 */
+	if (prot_numa && is_huge_zero_pmd(*pmd))
+		goto unlock;
+
+	if (prot_numa && pmd_protnone(*pmd))
+		goto unlock;
+
+	/*
+	 * In case prot_numa, we are under down_read(mmap_sem). It's critical
+	 * to not clear pmd intermittently to avoid race with MADV_DONTNEED
+	 * which is also under down_read(mmap_sem):
+	 *
+	 *	CPU0:				CPU1:
+	 *				change_huge_pmd(prot_numa=1)
+	 *				 pmdp_huge_get_and_clear_notify()
+	 * madvise_dontneed()
+	 *  zap_pmd_range()
+	 *   pmd_trans_huge(*pmd) == 0 (without ptl)
+	 *   // skip the pmd
+	 *				 set_pmd_at();
+	 *				 // pmd is re-established
+	 *
+	 * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
+	 * which may break userspace.
+	 *
+	 * pmdp_invalidate() is required to make sure we don't miss
+	 * dirty/young flags set by hardware.
+	 */
+	entry = *pmd;
+	pmdp_invalidate(vma, addr, pmd);
+
+	/*
+	 * Recover dirty/young flags.  It relies on pmdp_invalidate to not
+	 * corrupt them.
+	 */
+	if (pmd_dirty(*pmd))
+		entry = pmd_mkdirty(entry);
+	if (pmd_young(*pmd))
+		entry = pmd_mkyoung(entry);
 
+	entry = pmd_modify(entry, newprot);
+	if (preserve_write)
+		entry = pmd_mk_savedwrite(entry);
+	ret = HPAGE_PMD_NR;
+	set_pmd_at(mm, addr, pmd, entry);
+	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
+unlock:
+	spin_unlock(ptl);
 	return ret;
 }
 
@@ -1828,7 +1859,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
 	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
 
-	count_vm_event(THP_SPLIT_PMD);
+	count_vm_event(THP_SPLIT_PUD);
 
 	pudp_huge_clear_flush_notify(vma, haddr, pud);
 }
@@ -2048,6 +2079,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 		bool freeze, struct page *page)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -2055,7 +2087,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 	if (!pgd_present(*pgd))
 		return;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		return;
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		return;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a7aa811b7d14..e5828875f7bb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4403,7 +4403,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 	return 0;
 out_err:
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		region_abort(resv_map, from, to);
+		/* Don't call region_abort if region_chg failed */
+		if (chg >= 0)
+			region_abort(resv_map, from, to);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
@@ -4555,7 +4557,8 @@ out:
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	pgd_t *pgd = pgd_offset(mm, *addr);
-	pud_t *pud = pud_offset(pgd, *addr);
+	p4d_t *p4d = p4d_offset(pgd, *addr);
+	pud_t *pud = pud_offset(p4d, *addr);
 
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
 	if (page_count(virt_to_page(ptep)) == 1)
@@ -4586,11 +4589,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (pud) {
 		if (sz == PUD_SIZE) {
 			pte = (pte_t *)pud;
@@ -4610,18 +4615,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd = NULL;
+	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud)) {
-			if (pud_huge(*pud))
-				return (pte_t *)pud;
-			pmd = pmd_offset(pud, addr);
-		}
-	}
+	if (!pgd_present(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return NULL;
+	if (pud_huge(*pud))
+		return (pte_t *)pud;
+	pmd = pmd_offset(pud, addr);
 	return (pte_t *) pmd;
 }
 
@@ -4644,6 +4653,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
+	pte_t pte;
 retry:
 	ptl = pmd_lockptr(mm, pmd);
 	spin_lock(ptl);
@@ -4653,12 +4663,13 @@ retry:
 	 */
 	if (!pmd_huge(*pmd))
 		goto out;
-	if (pmd_present(*pmd)) {
+	pte = huge_ptep_get((pte_t *)pmd);
+	if (pte_present(pte)) {
 		page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
 		if (flags & FOLL_GET)
 			get_page(page);
 	} else {
-		if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
 			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
 			goto retry;
diff --git a/mm/internal.h b/mm/internal.h
index ccfc2a2969f4..266efaeaa370 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -481,6 +481,13 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 enum ttu_flags;
 struct tlbflush_unmap_batch;
 
+
+/*
+ * only for MM internal work items which do not depend on
+ * any allocations or locks which might depend on allocations
+ */
+extern struct workqueue_struct *mm_percpu_wq;
+
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 void try_to_unmap_flush(void);
 void try_to_unmap_flush_dirty(void);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 1c260e6b3b3c..dd2dea8eb077 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -96,11 +96,6 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 		<< KASAN_SHADOW_SCALE_SHIFT);
 }
 
-static inline bool kasan_report_enabled(void)
-{
-	return !current->kasan_depth;
-}
-
 void kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
 void kasan_report_double_free(struct kmem_cache *cache, void *object,
diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c
index 31238dad85fb..b96a5f773d88 100644
--- a/mm/kasan/kasan_init.c
+++ b/mm/kasan/kasan_init.c
@@ -30,6 +30,9 @@
  */
 unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
+#if CONFIG_PGTABLE_LEVELS > 4
+p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss;
+#endif
 #if CONFIG_PGTABLE_LEVELS > 3
 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
 #endif
@@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
+static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr,
 				unsigned long end)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	unsigned long next;
 
 	do {
@@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
 	} while (pud++, addr = next, addr != end);
 }
 
+static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr,
+				unsigned long end)
+{
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (p4d_none(*p4d)) {
+			p4d_populate(&init_mm, p4d,
+				early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+		}
+		zero_pud_populate(p4d, addr, next);
+	} while (p4d++, addr = next, addr != end);
+}
+
 /**
  * kasan_populate_zero_shadow - populate shadow memory region with
  *                               kasan_zero_page
@@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
 		next = pgd_addr_end(addr, end);
 
 		if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
+			p4d_t *p4d;
 			pud_t *pud;
 			pmd_t *pmd;
 
@@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
 			 * 3,2 - level page tables where we don't have
 			 * puds,pmds, so pgd_populate(), pud_populate()
 			 * is noops.
+			 *
+			 * The ifndef is required to avoid build breakage.
+			 *
+			 * With 5level-fixup.h, pgd_populate() is not nop and
+			 * we reference kasan_zero_p4d. It's not defined
+			 * unless 5-level paging enabled.
+			 *
+			 * The ifndef can be dropped once all KASAN-enabled
+			 * architectures will switch to pgtable-nop4d.h.
 			 */
-			pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud));
-			pud = pud_offset(pgd, addr);
+#ifndef __ARCH_HAS_5LEVEL_HACK
+			pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d));
+#endif
+			p4d = p4d_offset(pgd, addr);
+			p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud));
+			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd));
 			pmd = pmd_offset(pud, addr);
 			pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte));
@@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
 			pgd_populate(&init_mm, pgd,
 				early_alloc(PAGE_SIZE, NUMA_NO_NODE));
 		}
-		zero_pud_populate(pgd, addr, next);
+		zero_p4d_populate(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 6f1ed1630873..3a8ddf8baf7d 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -25,6 +25,7 @@
 #include <linux/printk.h>
 #include <linux/shrinker.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 #include <linux/string.h>
 #include <linux/types.h>
 
@@ -103,6 +104,7 @@ static int quarantine_tail;
 /* Total size of all objects in global_quarantine across all batches. */
 static unsigned long quarantine_size;
 static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
 
 /* Maximum size of the global queue. */
 static unsigned long quarantine_max_size;
@@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 	struct qlist_head *q;
 	struct qlist_head temp = QLIST_INIT;
 
+	/*
+	 * Note: irq must be disabled until after we move the batch to the
+	 * global quarantine. Otherwise quarantine_remove_cache() can miss
+	 * some objects belonging to the cache if they are in our local temp
+	 * list. quarantine_remove_cache() executes on_each_cpu() at the
+	 * beginning which ensures that it either sees the objects in per-cpu
+	 * lists or in the global quarantine.
+	 */
 	local_irq_save(flags);
 
 	q = this_cpu_ptr(&cpu_quarantine);
 	qlist_put(q, &info->quarantine_link, cache->size);
-	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
 		qlist_move_all(q, &temp);
 
-	local_irq_restore(flags);
-
-	if (unlikely(!qlist_empty(&temp))) {
-		spin_lock_irqsave(&quarantine_lock, flags);
+		spin_lock(&quarantine_lock);
 		WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
 		qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
 		if (global_quarantine[quarantine_tail].bytes >=
@@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 			if (new_tail != quarantine_head)
 				quarantine_tail = new_tail;
 		}
-		spin_unlock_irqrestore(&quarantine_lock, flags);
+		spin_unlock(&quarantine_lock);
 	}
+
+	local_irq_restore(flags);
 }
 
 void quarantine_reduce(void)
 {
 	size_t total_size, new_quarantine_size, percpu_quarantines;
 	unsigned long flags;
+	int srcu_idx;
 	struct qlist_head to_free = QLIST_INIT;
 
 	if (likely(READ_ONCE(quarantine_size) <=
 		   READ_ONCE(quarantine_max_size)))
 		return;
 
+	/*
+	 * srcu critical section ensures that quarantine_remove_cache()
+	 * will not miss objects belonging to the cache while they are in our
+	 * local to_free list. srcu is chosen because (1) it gives us private
+	 * grace period domain that does not interfere with anything else,
+	 * and (2) it allows synchronize_srcu() to return without waiting
+	 * if there are no pending read critical sections (which is the
+	 * expected case).
+	 */
+	srcu_idx = srcu_read_lock(&remove_cache_srcu);
 	spin_lock_irqsave(&quarantine_lock, flags);
 
 	/*
@@ -237,6 +257,7 @@ void quarantine_reduce(void)
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, NULL);
+	srcu_read_unlock(&remove_cache_srcu, srcu_idx);
 }
 
 static void qlist_move_cache(struct qlist_head *from,
@@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache)
 	unsigned long flags, i;
 	struct qlist_head to_free = QLIST_INIT;
 
+	/*
+	 * Must be careful to not miss any objects that are being moved from
+	 * per-cpu list to the global quarantine in quarantine_put(),
+	 * nor objects being freed in quarantine_reduce(). on_each_cpu()
+	 * achieves the first goal, while synchronize_srcu() achieves the
+	 * second.
+	 */
 	on_each_cpu(per_cpu_remove_cache, cache, 1);
 
 	spin_lock_irqsave(&quarantine_lock, flags);
-	for (i = 0; i < QUARANTINE_BATCHES; i++)
+	for (i = 0; i < QUARANTINE_BATCHES; i++) {
+		if (qlist_empty(&global_quarantine[i]))
+			continue;
 		qlist_move_cache(&global_quarantine[i], &to_free, cache);
+		/* Scanning whole quarantine can take a while. */
+		spin_unlock_irqrestore(&quarantine_lock, flags);
+		cond_resched();
+		spin_lock_irqsave(&quarantine_lock, flags);
+	}
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, cache);
+
+	synchronize_srcu(&remove_cache_srcu);
 }
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index f479365530b6..ab42a0803f16 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,7 +13,9 @@
  *
  */
 
+#include <linux/bitops.h>
 #include <linux/ftrace.h>
+#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/printk.h>
@@ -293,6 +295,40 @@ static void kasan_report_error(struct kasan_access_info *info)
 	kasan_end_report(&flags);
 }
 
+static unsigned long kasan_flags;
+
+#define KASAN_BIT_REPORTED	0
+#define KASAN_BIT_MULTI_SHOT	1
+
+bool kasan_save_enable_multi_shot(void)
+{
+	return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot);
+
+void kasan_restore_multi_shot(bool enabled)
+{
+	if (!enabled)
+		clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
+
+static int __init kasan_set_multi_shot(char *str)
+{
+	set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+	return 1;
+}
+__setup("kasan_multi_shot", kasan_set_multi_shot);
+
+static inline bool kasan_report_enabled(void)
+{
+	if (current->kasan_depth)
+		return false;
+	if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
+		return true;
+	return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
+}
+
 void kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip)
 {
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 26c874e90b12..20036d4f9f13 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1416,7 +1416,7 @@ static void kmemleak_scan(void)
 	/* data/bss scanning */
 	scan_large_block(_sdata, _edata);
 	scan_large_block(__bss_start, __bss_stop);
-	scan_large_block(__start_data_ro_after_init, __end_data_ro_after_init);
+	scan_large_block(__start_ro_after_init, __end_ro_after_init);
 
 #ifdef CONFIG_SMP
 	/* per-cpu sections scanning */
diff --git a/mm/madvise.c b/mm/madvise.c
index dc5927c812d3..7a2abf0127ae 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma,
 	if (!can_madv_dontneed_vma(vma))
 		return -EINVAL;
 
-	userfaultfd_remove(vma, prev, start, end);
+	if (!userfaultfd_remove(vma, start, end)) {
+		*prev = NULL; /* mmap_sem has been dropped, prev is stale */
+
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, start);
+		if (!vma)
+			return -ENOMEM;
+		if (start < vma->vm_start) {
+			/*
+			 * This "vma" under revalidation is the one
+			 * with the lowest vma->vm_start where start
+			 * is also < vma->vm_end. If start <
+			 * vma->vm_start it means an hole materialized
+			 * in the user address space within the
+			 * virtual range passed to MADV_DONTNEED.
+			 */
+			return -ENOMEM;
+		}
+		if (!can_madv_dontneed_vma(vma))
+			return -EINVAL;
+		if (end > vma->vm_end) {
+			/*
+			 * Don't fail if end > vma->vm_end. If the old
+			 * vma was splitted while the mmap_sem was
+			 * released the effect of the concurrent
+			 * operation may not cause MADV_DONTNEED to
+			 * have an undefined result. There may be an
+			 * adjacent next vma that we'll walk
+			 * next. userfaultfd_remove() will generate an
+			 * UFFD_EVENT_REMOVE repetition on the
+			 * end-vma->vm_end range, but the manager can
+			 * handle a repetition fine.
+			 */
+			end = vma->vm_end;
+		}
+		VM_WARN_ON(start >= end);
+	}
 	zap_page_range(vma, start, end - start);
 	return 0;
 }
@@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma,
 	 * mmap_sem.
 	 */
 	get_file(f);
-	userfaultfd_remove(vma, prev, start, end);
-	up_read(&current->mm->mmap_sem);
+	if (userfaultfd_remove(vma, start, end)) {
+		/* mmap_sem was not released by userfaultfd_remove() */
+		up_read(&current->mm->mmap_sem);
+	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
diff --git a/mm/memblock.c b/mm/memblock.c
index b64b47803e52..696f06d17c4e 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
 		}
 	} while (left < right);
 
-	return min(PHYS_PFN(type->regions[right].base), max_pfn);
+	if (right == type->cnt)
+		return max_pfn;
+	else
+		return min(PHYS_PFN(type->regions[right].base), max_pfn);
 }
 
 /**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c52ec893e241..2bd7541d7c11 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	struct mem_cgroup_tree_per_node *mctz;
 
 	mctz = soft_limit_tree_from_page(page);
+	if (!mctz)
+		return;
 	/*
 	 * Necessary to update all ancestors when hierarchy is used.
 	 * because their event counter is not touched.
@@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
 	for_each_node(nid) {
 		mz = mem_cgroup_nodeinfo(memcg, nid);
 		mctz = soft_limit_tree_node(nid);
-		mem_cgroup_remove_exceeded(mz, mctz);
+		if (mctz)
+			mem_cgroup_remove_exceeded(mz, mctz);
 	}
 }
 
@@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 	 * is empty. Do it lockless to prevent lock bouncing. Races
 	 * are acceptable as soft limit is best effort anyway.
 	 */
-	if (RB_EMPTY_ROOT(&mctz->rb_root))
+	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
 		return 0;
 
 	/*
@@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	kfree(memcg->nodeinfo[node]);
 }
 
-static void mem_cgroup_free(struct mem_cgroup *memcg)
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	memcg_wb_domain_exit(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->stat);
 	kfree(memcg);
 }
 
+static void mem_cgroup_free(struct mem_cgroup *memcg)
+{
+	memcg_wb_domain_exit(memcg);
+	__mem_cgroup_free(memcg);
+}
+
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
@@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 fail:
 	if (memcg->id.id > 0)
 		idr_remove(&mem_cgroup_idr, memcg->id.id);
-	mem_cgroup_free(memcg);
+	__mem_cgroup_free(memcg);
 	return NULL;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index a97a4cec2e1f..6ff5d729ded0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	mm_dec_nr_pmds(tlb->mm);
 }
 
-static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				unsigned long floor, unsigned long ceiling)
 {
@@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	unsigned long start;
 
 	start = addr;
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
 	} while (pud++, addr = next, addr != end);
 
+	start &= P4D_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= P4D_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pud = pud_offset(p4d, start);
+	p4d_clear(p4d);
+	pud_free_tlb(tlb, pud, start);
+}
+
+static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		free_pud_range(tlb, p4d, addr, next, floor, ceiling);
+	} while (p4d++, addr = next, addr != end);
+
 	start &= PGDIR_MASK;
 	if (start < floor)
 		return;
@@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	if (end - 1 > ceiling - 1)
 		return;
 
-	pud = pud_offset(pgd, start);
+	p4d = p4d_offset(pgd, start);
 	pgd_clear(pgd);
-	pud_free_tlb(tlb, pud, start);
+	p4d_free_tlb(tlb, p4d, start);
 }
 
 /*
@@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+		free_p4d_range(tlb, pgd, addr, next, floor, ceiling);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 			  pte_t pte, struct page *page)
 {
 	pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
-	pud_t *pud = pud_offset(pgd, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	pmd_t *pmd = pmd_offset(pud, addr);
 	struct address_space *mapping;
 	pgoff_t index;
@@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 }
 
 static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end)
 {
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
-	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+	dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
 	if (!dst_pud)
 		return -ENOMEM;
-	src_pud = pud_offset(src_pgd, addr);
+	src_pud = pud_offset(src_p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
@@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 	return 0;
 }
 
+static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end)
+{
+	p4d_t *src_p4d, *dst_p4d;
+	unsigned long next;
+
+	dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
+	if (!dst_p4d)
+		return -ENOMEM;
+	src_p4d = p4d_offset(src_pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(src_p4d))
+			continue;
+		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
+						vma, addr, next))
+			return -ENOMEM;
+	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
+	return 0;
+}
+
 int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		struct vm_area_struct *vma)
 {
@@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
 					    vma, addr, next))) {
 			ret = -ENOMEM;
 			break;
@@ -1267,14 +1323,14 @@ next:
 }
 
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
-				struct vm_area_struct *vma, pgd_t *pgd,
+				struct vm_area_struct *vma, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
@@ -1295,6 +1351,25 @@ next:
 	return addr;
 }
 
+static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				struct zap_details *details)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		next = zap_pud_range(tlb, vma, p4d, addr, next, details);
+	} while (p4d++, addr = next, addr != end);
+
+	return addr;
+}
+
 void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
@@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+		next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
 }
@@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
 pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			spinlock_t **ptl)
 {
-	pgd_t *pgd = pgd_offset(mm, addr);
-	pud_t *pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		pmd_t *pmd = pmd_alloc(mm, pud, addr);
-		if (pmd) {
-			VM_BUG_ON(pmd_trans_huge(*pmd));
-			return pte_alloc_map_lock(mm, pmd, addr, ptl);
-		}
-	}
-	return NULL;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+
+	VM_BUG_ON(pmd_trans_huge(*pmd));
+	return pte_alloc_map_lock(mm, pmd, addr, ptl);
 }
 
 /*
@@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	return 0;
 }
 
-static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
@@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	unsigned long next;
 
 	pfn -= addr >> PAGE_SHIFT;
-	pud = pud_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return 0;
 }
 
+static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end,
+			unsigned long pfn, pgprot_t prot)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	pfn -= addr >> PAGE_SHIFT;
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		if (remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 /**
  * remap_pfn_range - remap kernel memory to userspace
  * @vma: user vma to map to
@@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	flush_cache_range(vma, addr, end);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = remap_pud_range(mm, pgd, addr, next,
+		err = remap_p4d_range(mm, pgd, addr, next,
 				pfn + (addr >> PAGE_SHIFT), prot);
 		if (err)
 			break;
@@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	return err;
 }
 
-static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
 {
@@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	unsigned long next;
 	int err;
 
-	pud = pud_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return err;
 }
 
+static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+				     unsigned long addr, unsigned long end,
+				     pte_fn_t fn, void *data)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int err;
+
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+		if (err)
+			break;
+	} while (p4d++, addr = next, addr != end);
+	return err;
+}
+
 /*
  * Scan a region of virtual memory, filling in page tables as necessary
  * and calling a provided function on each leaf page table.
@@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
@@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	int ret;
 
 	pgd = pgd_offset(mm, address);
+	p4d = p4d_alloc(mm, pgd, address);
+	if (!p4d)
+		return VM_FAULT_OOM;
 
-	vmf.pud = pud_alloc(mm, pgd, address);
+	vmf.pud = pud_alloc(mm, p4d, address);
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
 	if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
@@ -3779,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);
 
+#ifndef __PAGETABLE_P4D_FOLDED
+/*
+ * Allocate p4d page table.
+ * We've already handled the fast-path in-line.
+ */
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+	p4d_t *new = p4d_alloc_one(mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	smp_wmb(); /* See comment in __pte_alloc */
+
+	spin_lock(&mm->page_table_lock);
+	if (pgd_present(*pgd))		/* Another has populated it */
+		p4d_free(mm, new);
+	else
+		pgd_populate(mm, pgd, new);
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+#endif /* __PAGETABLE_P4D_FOLDED */
+
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
  * Allocate page upper directory.
  * We've already handled the fast-path in-line.
  */
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
 {
 	pud_t *new = pud_alloc_one(mm, address);
 	if (!new)
@@ -3793,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	spin_lock(&mm->page_table_lock);
-	if (pgd_present(*pgd))		/* Another has populated it */
+#ifndef __ARCH_HAS_5LEVEL_HACK
+	if (p4d_present(*p4d))		/* Another has populated it */
 		pud_free(mm, new);
 	else
-		pgd_populate(mm, pgd, new);
+		p4d_populate(mm, p4d, new);
+#else
+	if (pgd_present(*p4d))		/* Another has populated it */
+		pud_free(mm, new);
+	else
+		pgd_populate(mm, p4d, new);
+#endif /* __ARCH_HAS_5LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -3839,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ptep;
@@ -3847,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
+		goto out;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
 		goto out;
 
@@ -4136,7 +4298,7 @@ void __might_fault(const char *file, int line)
 	 * get paged out, therefore we'll never actually fault, and the
 	 * below annotations will generate false positives.
 	 */
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (uaccess_kernel())
 		return;
 	if (pagefault_disabled())
 		return;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 295479b792ec..6fa7208bcd56 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -125,9 +125,12 @@ void put_online_mems(void)
 
 }
 
+/* Serializes write accesses to mem_hotplug.active_writer. */
+static DEFINE_MUTEX(memory_add_remove_lock);
+
 void mem_hotplug_begin(void)
 {
-	assert_held_device_hotplug();
+	mutex_lock(&memory_add_remove_lock);
 
 	mem_hotplug.active_writer = current;
 
@@ -147,6 +150,7 @@ void mem_hotplug_done(void)
 	mem_hotplug.active_writer = NULL;
 	mutex_unlock(&mem_hotplug.lock);
 	memhp_lock_release();
+	mutex_unlock(&memory_add_remove_lock);
 }
 
 /* add this memory to iomem resource */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 75b2745bac41..37d0b334bfe9 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1529,7 +1529,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
 		       compat_ulong_t, maxnode)
 {
-	long err = 0;
 	unsigned long __user *nm = NULL;
 	unsigned long nr_bits, alloc_size;
 	DECLARE_BITMAP(bm, MAX_NUMNODES);
@@ -1538,14 +1537,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
 	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
 
 	if (nmask) {
-		err = compat_get_bitmap(bm, nmask, nr_bits);
+		if (compat_get_bitmap(bm, nmask, nr_bits))
+			return -EFAULT;
 		nm = compat_alloc_user_space(alloc_size);
-		err |= copy_to_user(nm, bm, alloc_size);
+		if (copy_to_user(nm, bm, alloc_size))
+			return -EFAULT;
 	}
 
-	if (err)
-		return -EFAULT;
-
 	return sys_set_mempolicy(mode, nm, nr_bits+1);
 }
 
@@ -1553,7 +1551,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 		       compat_ulong_t, mode, compat_ulong_t __user *, nmask,
 		       compat_ulong_t, maxnode, compat_ulong_t, flags)
 {
-	long err = 0;
 	unsigned long __user *nm = NULL;
 	unsigned long nr_bits, alloc_size;
 	nodemask_t bm;
@@ -1562,14 +1559,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
 
 	if (nmask) {
-		err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
+		if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
+			return -EFAULT;
 		nm = compat_alloc_user_space(alloc_size);
-		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
+		if (copy_to_user(nm, nodes_addr(bm), alloc_size))
+			return -EFAULT;
 	}
 
-	if (err)
-		return -EFAULT;
-
 	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 9a0897a14d37..738f1d5f8350 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -184,9 +184,9 @@ void putback_movable_pages(struct list_head *l)
 			unlock_page(page);
 			put_page(page);
 		} else {
-			putback_lru_page(page);
 			dec_node_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
+			putback_lru_page(page);
 		}
 	}
 }
@@ -209,8 +209,11 @@ static int remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 	while (page_vma_mapped_walk(&pvmw)) {
-		new = page - pvmw.page->index +
-			linear_page_index(vma, pvmw.address);
+		if (PageKsm(page))
+			new = page;
+		else
+			new = page - pvmw.page->index +
+				linear_page_index(vma, pvmw.address);
 
 		get_page(new);
 		pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
diff --git a/mm/mlock.c b/mm/mlock.c
index 1050511f8b2b..0dd9ca18e19e 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
 	/* Make sure we do not cross the page table boundary */
 	end = pgd_addr_end(start, end);
+	end = p4d_addr_end(start, end);
 	end = pud_addr_end(start, end);
 	end = pmd_addr_end(start, end);
 
@@ -442,7 +443,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page;
-		unsigned int page_mask;
+		unsigned int page_mask = 0;
 		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
@@ -456,8 +457,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 		 * suits munlock very well (and if somehow an abnormal page
 		 * has sneaked into the range, we won't oops here: great).
 		 */
-		page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
-				&page_mask);
+		page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
 
 		if (page && !IS_ERR(page)) {
 			if (PageTransTail(page)) {
@@ -468,8 +468,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				/*
 				 * Any THP page found by follow_page_mask() may
 				 * have gotten split before reaching
-				 * munlock_vma_page(), so we need to recompute
-				 * the page_mask here.
+				 * munlock_vma_page(), so we need to compute
+				 * the page_mask here instead.
 				 */
 				page_mask = munlock_vma_page(page);
 				unlock_page(page);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 848e946b08e5..8edd0d576254 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 }
 
 static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
+		p4d_t *p4d, unsigned long addr, unsigned long end,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pud_t *pud;
 	unsigned long next;
 	unsigned long pages = 0;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 	return pages;
 }
 
+static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
+		pgd_t *pgd, unsigned long addr, unsigned long end,
+		pgprot_t newprot, int dirty_accountable, int prot_numa)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	unsigned long pages = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		pages += change_pud_range(vma, p4d, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+	} while (p4d++, addr = next, addr != end);
+
+	return pages;
+}
+
 static unsigned long change_protection_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable, int prot_numa)
@@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		pages += change_pud_range(vma, pgd, addr, next, newprot,
+		pages += change_p4d_range(vma, pgd, addr, next, newprot,
 				 dirty_accountable, prot_numa);
 	} while (pgd++, addr = next, addr != end);
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 8233b0105c82..cd8a1b199ef9 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -32,6 +32,7 @@
 static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	if (pgd_none_or_clear_bad(pgd))
 		return NULL;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none_or_clear_bad(p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, addr);
 	if (pud_none_or_clear_bad(pud))
 		return NULL;
 
@@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 			    unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return NULL;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eaa64d2ffdc5..bd01501efab9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -873,7 +873,8 @@ done_merging:
 		higher_page = page + (combined_pfn - pfn);
 		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
 		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
-		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
+		if (pfn_valid_within(buddy_pfn) &&
+		    page_is_buddy(higher_page, higher_buddy, order + 1)) {
 			list_add_tail(&page->lru,
 				&zone->free_area[order].free_list[migratetype]);
 			goto out;
@@ -1089,10 +1090,10 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 {
 	int migratetype = 0;
 	int batch_free = 0;
-	unsigned long nr_scanned, flags;
+	unsigned long nr_scanned;
 	bool isolated_pageblocks;
 
-	spin_lock_irqsave(&zone->lock, flags);
+	spin_lock(&zone->lock);
 	isolated_pageblocks = has_isolate_pageblock(zone);
 	nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
 	if (nr_scanned)
@@ -1141,7 +1142,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			trace_mm_page_pcpu_drain(page, 0, mt);
 		} while (--count && --batch_free && !list_empty(list));
 	}
-	spin_unlock_irqrestore(&zone->lock, flags);
+	spin_unlock(&zone->lock);
 }
 
 static void free_one_page(struct zone *zone,
@@ -1149,9 +1150,8 @@ static void free_one_page(struct zone *zone,
 				unsigned int order,
 				int migratetype)
 {
-	unsigned long nr_scanned, flags;
-	spin_lock_irqsave(&zone->lock, flags);
-	__count_vm_events(PGFREE, 1 << order);
+	unsigned long nr_scanned;
+	spin_lock(&zone->lock);
 	nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
 	if (nr_scanned)
 		__mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
@@ -1161,7 +1161,7 @@ static void free_one_page(struct zone *zone,
 		migratetype = get_pfnblock_migratetype(page, pfn);
 	}
 	__free_one_page(page, pfn, zone, order, migratetype);
-	spin_unlock_irqrestore(&zone->lock, flags);
+	spin_unlock(&zone->lock);
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
@@ -1239,6 +1239,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 
 static void __free_pages_ok(struct page *page, unsigned int order)
 {
+	unsigned long flags;
 	int migratetype;
 	unsigned long pfn = page_to_pfn(page);
 
@@ -1246,7 +1247,10 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
+	local_irq_save(flags);
+	__count_vm_events(PGFREE, 1 << order);
 	free_one_page(page_zone(page), page, pfn, order, migratetype);
+	local_irq_restore(flags);
 }
 
 static void __init __free_pages_boot_core(struct page *page, unsigned int order)
@@ -2218,9 +2222,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			int migratetype, bool cold)
 {
 	int i, alloced = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&zone->lock, flags);
+	spin_lock(&zone->lock);
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype);
 		if (unlikely(page == NULL))
@@ -2256,7 +2259,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 	 * pages added to the pcp list.
 	 */
 	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
-	spin_unlock_irqrestore(&zone->lock, flags);
+	spin_unlock(&zone->lock);
 	return alloced;
 }
 
@@ -2372,6 +2375,13 @@ void drain_all_pages(struct zone *zone)
 	 */
 	static cpumask_t cpus_with_pcps;
 
+	/*
+	 * Make sure nobody triggers this path before mm_percpu_wq is fully
+	 * initialized.
+	 */
+	if (WARN_ON_ONCE(!mm_percpu_wq))
+		return;
+
 	/* Workqueues cannot recurse */
 	if (current->flags & PF_WQ_WORKER)
 		return;
@@ -2421,7 +2431,7 @@ void drain_all_pages(struct zone *zone)
 	for_each_cpu(cpu, &cpus_with_pcps) {
 		struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
 		INIT_WORK(work, drain_local_pages_wq);
-		schedule_work_on(cpu, work);
+		queue_work_on(cpu, mm_percpu_wq, work);
 	}
 	for_each_cpu(cpu, &cpus_with_pcps)
 		flush_work(per_cpu_ptr(&pcpu_drain, cpu));
@@ -2477,20 +2487,17 @@ void free_hot_cold_page(struct page *page, bool cold)
 {
 	struct zone *zone = page_zone(page);
 	struct per_cpu_pages *pcp;
+	unsigned long flags;
 	unsigned long pfn = page_to_pfn(page);
 	int migratetype;
 
-	if (in_interrupt()) {
-		__free_pages_ok(page, 0);
-		return;
-	}
-
 	if (!free_pcp_prepare(page))
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_pcppage_migratetype(page, migratetype);
-	preempt_disable();
+	local_irq_save(flags);
+	__count_vm_event(PGFREE);
 
 	/*
 	 * We only track unmovable, reclaimable and movable on pcp lists.
@@ -2507,7 +2514,6 @@ void free_hot_cold_page(struct page *page, bool cold)
 		migratetype = MIGRATE_MOVABLE;
 	}
 
-	__count_vm_event(PGFREE);
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
 	if (!cold)
 		list_add(&page->lru, &pcp->lists[migratetype]);
@@ -2521,7 +2527,7 @@ void free_hot_cold_page(struct page *page, bool cold)
 	}
 
 out:
-	preempt_enable();
+	local_irq_restore(flags);
 }
 
 /*
@@ -2646,8 +2652,6 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
 {
 	struct page *page;
 
-	VM_BUG_ON(in_interrupt());
-
 	do {
 		if (list_empty(list)) {
 			pcp->count += rmqueue_bulk(zone, 0,
@@ -2678,8 +2682,9 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 	struct list_head *list;
 	bool cold = ((gfp_flags & __GFP_COLD) != 0);
 	struct page *page;
+	unsigned long flags;
 
-	preempt_disable();
+	local_irq_save(flags);
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
 	list = &pcp->lists[migratetype];
 	page = __rmqueue_pcplist(zone,  migratetype, cold, pcp, list);
@@ -2687,7 +2692,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 		zone_statistics(preferred_zone, zone);
 	}
-	preempt_enable();
+	local_irq_restore(flags);
 	return page;
 }
 
@@ -2703,7 +2708,7 @@ struct page *rmqueue(struct zone *preferred_zone,
 	unsigned long flags;
 	struct page *page;
 
-	if (likely(order == 0) && !in_interrupt()) {
+	if (likely(order == 0)) {
 		page = rmqueue_pcplist(preferred_zone, zone, order,
 				gfp_flags, migratetype);
 		goto out;
@@ -4242,7 +4247,8 @@ EXPORT_SYMBOL(free_pages_exact);
  * nr_free_zone_pages() counts the number of counts pages which are beyond the
  * high watermark within all zones at or below a given zone index.  For each
  * zone, the number of pages is calculated as:
- *     managed_pages - high_pages
+ *
+ *     nr_free_zone_pages = managed_pages - high_pages
  */
 static unsigned long nr_free_zone_pages(int offset)
 {
@@ -4518,13 +4524,13 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(node_page_state(pgdat, NR_FILE_MAPPED)),
 			K(node_page_state(pgdat, NR_FILE_DIRTY)),
 			K(node_page_state(pgdat, NR_WRITEBACK)),
+			K(node_page_state(pgdat, NR_SHMEM)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 			K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
 			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
 					* HPAGE_PMD_NR),
 			K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
 #endif
-			K(node_page_state(pgdat, NR_SHMEM)),
 			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
 			K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 			node_page_state(pgdat, NR_PAGES_SCANNED),
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index a23001a22c15..de9c40d7304a 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -104,18 +104,15 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	struct mm_struct *mm = pvmw->vma->vm_mm;
 	struct page *page = pvmw->page;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 
 	/* The only possible pmd mapping has been handled on last iteration */
 	if (pvmw->pmd && !pvmw->pte)
 		return not_found(pvmw);
 
-	/* Only for THP, seek to next pte entry makes sense */
-	if (pvmw->pte) {
-		if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
-			return not_found(pvmw);
+	if (pvmw->pte)
 		goto next_pte;
-	}
 
 	if (unlikely(PageHuge(pvmw->page))) {
 		/* when pud is not present, pte will be NULL */
@@ -133,7 +130,10 @@ restart:
 	pgd = pgd_offset(mm, pvmw->address);
 	if (!pgd_present(*pgd))
 		return false;
-	pud = pud_offset(pgd, pvmw->address);
+	p4d = p4d_offset(pgd, pvmw->address);
+	if (!p4d_present(*p4d))
+		return false;
+	pud = pud_offset(p4d, pvmw->address);
 	if (!pud_present(*pud))
 		return false;
 	pvmw->pmd = pmd_offset(pud, pvmw->address);
@@ -161,9 +161,14 @@ restart:
 	while (1) {
 		if (check_pte(pvmw))
 			return true;
-next_pte:	do {
+next_pte:
+		/* Seek to next pte only makes sense for THP */
+		if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+			return not_found(pvmw);
+		do {
 			pvmw->address += PAGE_SIZE;
-			if (pvmw->address >=
+			if (pvmw->address >= pvmw->vma->vm_end ||
+			    pvmw->address >=
 					__vma_address(pvmw->page, pvmw->vma) +
 					hpage_nr_pages(pvmw->page) * PAGE_SIZE)
 				return not_found(pvmw);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 03761577ae86..60f7856e508f 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -69,14 +69,14 @@ again:
 	return err;
 }
 
-static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
 	pud_t *pud;
 	unsigned long next;
 	int err = 0;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
  again:
 		next = pud_addr_end(addr, end);
@@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return err;
 }
 
+static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int err = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			continue;
+		}
+		if (walk->pmd_entry || walk->pte_entry)
+			err = walk_pud_range(p4d, addr, next, walk);
+		if (err)
+			break;
+	} while (p4d++, addr = next, addr != end);
+
+	return err;
+}
+
 static int walk_pgd_range(unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
@@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 			continue;
 		}
 		if (walk->pmd_entry || walk->pte_entry)
-			err = walk_pud_range(pgd, addr, next, walk);
+			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 538998a137d2..9ac639499bd1 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -21,7 +21,6 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
 
 /**
  * pcpu_get_pages - get temp pages array
- * @chunk: chunk of interest
  *
  * Returns pointer to array of pointers to struct page which can be indexed
  * with pcpu_page_idx().  Note that there is only one array and accesses
@@ -30,7 +29,7 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
  * RETURNS:
  * Pointer to temp pages array on success.
  */
-static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc)
+static struct page **pcpu_get_pages(void)
 {
 	static struct page **pages;
 	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
@@ -275,7 +274,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
 {
 	struct page **pages;
 
-	pages = pcpu_get_pages(chunk);
+	pages = pcpu_get_pages();
 	if (!pages)
 		return -ENOMEM;
 
@@ -313,7 +312,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	 * successful population attempt so the temp pages array must
 	 * be available now.
 	 */
-	pages = pcpu_get_pages(chunk);
+	pages = pcpu_get_pages();
 	BUG_ON(!pages);
 
 	/* unmap and free */
diff --git a/mm/percpu.c b/mm/percpu.c
index 5696039b5c07..e0aa8ae7bde7 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1011,8 +1011,11 @@ area_found:
 		mutex_unlock(&pcpu_alloc_mutex);
 	}
 
-	if (chunk != pcpu_reserved_chunk)
+	if (chunk != pcpu_reserved_chunk) {
+		spin_lock_irqsave(&pcpu_lock, flags);
 		pcpu_nr_empty_pop_pages -= occ_pages;
+		spin_unlock_irqrestore(&pcpu_lock, flags);
+	}
 
 	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
 		pcpu_schedule_balance_work();
@@ -1281,18 +1284,7 @@ void free_percpu(void __percpu *ptr)
 }
 EXPORT_SYMBOL_GPL(free_percpu);
 
-/**
- * is_kernel_percpu_address - test whether address is from static percpu area
- * @addr: address to test
- *
- * Test whether @addr belongs to in-kernel static percpu area.  Module
- * static percpu areas are not considered.  For those, use
- * is_module_percpu_address().
- *
- * RETURNS:
- * %true if @addr is from in-kernel static percpu area, %false otherwise.
- */
-bool is_kernel_percpu_address(unsigned long addr)
+bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr)
 {
 #ifdef CONFIG_SMP
 	const size_t static_size = __per_cpu_end - __per_cpu_start;
@@ -1301,16 +1293,39 @@ bool is_kernel_percpu_address(unsigned long addr)
 
 	for_each_possible_cpu(cpu) {
 		void *start = per_cpu_ptr(base, cpu);
+		void *va = (void *)addr;
 
-		if ((void *)addr >= start && (void *)addr < start + static_size)
+		if (va >= start && va < start + static_size) {
+			if (can_addr) {
+				*can_addr = (unsigned long) (va - start);
+				*can_addr += (unsigned long)
+					per_cpu_ptr(base, get_boot_cpu_id());
+			}
 			return true;
-        }
+		}
+	}
 #endif
 	/* on UP, can't distinguish from other static vars, always false */
 	return false;
 }
 
 /**
+ * is_kernel_percpu_address - test whether address is from static percpu area
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to in-kernel static percpu area.  Module
+ * static percpu areas are not considered.  For those, use
+ * is_module_percpu_address().
+ *
+ * RETURNS:
+ * %true if @addr is from in-kernel static percpu area, %false otherwise.
+ */
+bool is_kernel_percpu_address(unsigned long addr)
+{
+	return __is_kernel_percpu_address(addr, NULL);
+}
+
+/**
  * per_cpu_ptr_to_phys - convert translated percpu address to physical address
  * @addr: the address to be converted to physical address
  *
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4ed5908c65b0..c99d9512a45b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd)
 	pgd_clear(pgd);
 }
 
+void p4d_clear_bad(p4d_t *p4d)
+{
+	p4d_ERROR(*p4d);
+	p4d_clear(p4d);
+}
+
 void pud_clear_bad(pud_t *pud)
 {
 	pud_ERROR(*pud);
diff --git a/mm/rmap.c b/mm/rmap.c
index 2da487d6cea8..f6838015810f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd = NULL;
 	pmd_t pmde;
@@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 	if (!pgd_present(*pgd))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto out;
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto out;
 
@@ -1154,7 +1159,7 @@ void page_add_file_rmap(struct page *page, bool compound)
 			goto out;
 	}
 	__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr);
-	mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+	mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, nr);
 out:
 	unlock_page_memcg(page);
 }
@@ -1194,7 +1199,7 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
 	__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr);
-	mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+	mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, -nr);
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
@@ -1316,12 +1321,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	}
 
 	while (page_vma_mapped_walk(&pvmw)) {
-		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
-		address = pvmw.address;
-
-		/* Unexpected PMD-mapped THP? */
-		VM_BUG_ON_PAGE(!pvmw.pte, page);
-
 		/*
 		 * If the page is mlock()d, we cannot swap it out.
 		 * If it's recently referenced (perhaps page_referenced
@@ -1345,6 +1344,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				continue;
 		}
 
+		/* Unexpected PMD-mapped THP? */
+		VM_BUG_ON_PAGE(!pvmw.pte, page);
+
+		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		address = pvmw.address;
+
+
 		if (!(flags & TTU_IGNORE_ACCESS)) {
 			if (ptep_clear_flush_young_notify(vma, address,
 						pvmw.pte)) {
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 574c67b663fe..a56c3989f773 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 	return pmd;
 }
 
-pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
+pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
 		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
@@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
 	return pud;
 }
 
+p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
+{
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d)) {
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (!p)
+			return NULL;
+		p4d_populate(&init_mm, p4d, p);
+	}
+	return p4d;
+}
+
 pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 {
 	pgd_t *pgd = pgd_offset_k(addr);
@@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
 {
 	unsigned long addr = start;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
 		pgd = vmemmap_pgd_populate(addr, node);
 		if (!pgd)
 			return -ENOMEM;
-		pud = vmemmap_pud_populate(pgd, addr, node);
+		p4d = vmemmap_p4d_populate(pgd, addr, node);
+		if (!p4d)
+			return -ENOMEM;
+		pud = vmemmap_pud_populate(p4d, addr, node);
 		if (!pud)
 			return -ENOMEM;
 		pmd = vmemmap_pmd_populate(pud, addr, node);
diff --git a/mm/swap.c b/mm/swap.c
index c4910f14f957..d8d9ee9e311a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -97,6 +97,16 @@ static void __put_compound_page(struct page *page)
 
 void __put_page(struct page *page)
 {
+	if (is_zone_device_page(page)) {
+		put_dev_pagemap(page->pgmap);
+
+		/*
+		 * The page belongs to the device that created pgmap. Do
+		 * not return it to page allocator.
+		 */
+		return;
+	}
+
 	if (unlikely(PageCompound(page)))
 		__put_compound_page(page);
 	else
@@ -670,30 +680,19 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
-/*
- * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
- * workqueue, aiding in getting memory freed.
- */
-static struct workqueue_struct *lru_add_drain_wq;
-
-static int __init lru_init(void)
-{
-	lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
-
-	if (WARN(!lru_add_drain_wq,
-		"Failed to create workqueue lru_add_drain_wq"))
-		return -ENOMEM;
-
-	return 0;
-}
-early_initcall(lru_init);
-
 void lru_add_drain_all(void)
 {
 	static DEFINE_MUTEX(lock);
 	static struct cpumask has_work;
 	int cpu;
 
+	/*
+	 * Make sure nobody triggers this path before mm_percpu_wq is fully
+	 * initialized.
+	 */
+	if (WARN_ON(!mm_percpu_wq))
+		return;
+
 	mutex_lock(&lock);
 	get_online_cpus();
 	cpumask_clear(&has_work);
@@ -707,7 +706,7 @@ void lru_add_drain_all(void)
 		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
-			queue_work_on(cpu, lru_add_drain_wq, work);
+			queue_work_on(cpu, mm_percpu_wq, work);
 			cpumask_set_cpu(cpu, &has_work);
 		}
 	}
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index 310ac0b8f974..ac6318a064d3 100644
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -201,6 +201,8 @@ void swap_cgroup_swapoff(int type)
 			struct page *page = map[i];
 			if (page)
 				__free_page(page);
+			if (!(i % SWAP_CLUSTER_MAX))
+				cond_resched();
 		}
 		vfree(map);
 	}
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 9b5bc86f96ad..b1ccb58ad397 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -267,8 +267,6 @@ int free_swap_slot(swp_entry_t entry)
 {
 	struct swap_slots_cache *cache;
 
-	BUG_ON(!swap_slot_cache_initialized);
-
 	cache = &get_cpu_var(swp_slots);
 	if (use_swap_slot_cache && cache->slots_ret) {
 		spin_lock_irq(&cache->free_lock);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 521ef9b6064f..178130880b90 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	return 0;
 }
 
-static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				swp_entry_t entry, struct page *page)
 {
@@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 	unsigned long next;
 	int ret;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 	return 0;
 }
 
+static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				swp_entry_t entry, struct page *page)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int ret;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		ret = unuse_pud_range(vma, p4d, addr, next, entry, page);
+		if (ret)
+			return ret;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 static int unuse_vma(struct vm_area_struct *vma,
 				swp_entry_t entry, struct page *page)
 {
@@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
+		ret = unuse_p4d_range(vma, pgd, addr, next, entry, page);
 		if (ret)
 			return ret;
 	} while (pgd++, addr = next, addr != end);
diff --git a/mm/usercopy.c b/mm/usercopy.c
index d155e12563b1..a9852b24715d 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -19,15 +19,9 @@
 #include <linux/sched.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/thread_info.h>
 #include <asm/sections.h>
 
-enum {
-	BAD_STACK = -1,
-	NOT_STACK = 0,
-	GOOD_FRAME,
-	GOOD_STACK,
-};
-
 /*
  * Checks if a given pointer and length is contained by the current
  * stack frame (if possible).
@@ -206,17 +200,6 @@ static inline const char *check_heap_object(const void *ptr, unsigned long n,
 {
 	struct page *page;
 
-	/*
-	 * Some architectures (arm64) return true for virt_addr_valid() on
-	 * vmalloced addresses. Work around this by checking for vmalloc
-	 * first.
-	 *
-	 * We also need to check for module addresses explicitly since we
-	 * may copy static data from modules to userspace
-	 */
-	if (is_vmalloc_or_module_addr(ptr))
-		return NULL;
-
 	if (!virt_addr_valid(ptr))
 		return NULL;
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 479e631d43c2..8bcb501bce60 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -128,19 +128,22 @@ out_unlock:
 static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, address);
-	pud = pud_alloc(mm, pgd, address);
-	if (pud)
-		/*
-		 * Note that we didn't run this because the pmd was
-		 * missing, the *pmd may be already established and in
-		 * turn it may also be a trans_huge_pmd.
-		 */
-		pmd = pmd_alloc(mm, pud, address);
-	return pmd;
+	p4d = p4d_alloc(mm, pgd, address);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, address);
+	if (!pud)
+		return NULL;
+	/*
+	 * Note that we didn't run this because the pmd was
+	 * missing, the *pmd may be already established and in
+	 * turn it may also be a trans_huge_pmd.
+	 */
+	return pmd_alloc(mm, pud, address);
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b4024d688f38..b52aeed3f58e 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_clear_huge(pud))
@@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
 	} while (pud++, addr = next, addr != end);
 }
 
+static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_clear_huge(p4d))
+			continue;
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		vunmap_pud_range(p4d, addr, next);
+	} while (p4d++, addr = next, addr != end);
+}
+
 static void vunmap_page_range(unsigned long addr, unsigned long end)
 {
 	pgd_t *pgd;
@@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		vunmap_pud_range(pgd, addr, next);
+		vunmap_p4d_range(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
 	return 0;
 }
 
-static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_alloc(&init_mm, pgd, addr);
+	pud = pud_alloc(&init_mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_alloc(&init_mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 /*
  * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
  * will have pfns corresponding to the "pages" array.
@@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end,
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
+		err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
 		if (err)
 			return err;
 	} while (pgd++, addr = next, addr != end);
@@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	unsigned long addr = (unsigned long) vmalloc_addr;
 	struct page *page = NULL;
 	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *ptep, pte;
 
 	/*
 	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
@@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	 */
 	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
 
-	if (!pgd_none(*pgd)) {
-		pud_t *pud = pud_offset(pgd, addr);
-		if (!pud_none(*pud)) {
-			pmd_t *pmd = pmd_offset(pud, addr);
-			if (!pmd_none(*pmd)) {
-				pte_t *ptep, pte;
-
-				ptep = pte_offset_map(pmd, addr);
-				pte = *ptep;
-				if (pte_present(pte))
-					page = pte_page(pte);
-				pte_unmap(ptep);
-			}
-		}
-	}
+	if (pgd_none(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return NULL;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return NULL;
+
+	ptep = pte_offset_map(pmd, addr);
+	pte = *ptep;
+	if (pte_present(pte))
+		page = pte_page(pte);
+	pte_unmap(ptep);
 	return page;
 }
 EXPORT_SYMBOL(vmalloc_to_page);
@@ -1540,7 +1579,7 @@ void vfree_atomic(const void *addr)
  *	have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
  *	conventions for vfree() arch-depenedent would be a really bad idea)
  *
- *	NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
+ *	NOTE: assumes that the object at @addr has a size >= sizeof(llist_node)
  */
 void vfree(const void *addr)
 {
@@ -1644,7 +1683,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 		if (fatal_signal_pending(current)) {
 			area->nr_pages = i;
-			goto fail;
+			goto fail_no_warn;
 		}
 
 		if (node == NUMA_NO_NODE)
@@ -1670,6 +1709,7 @@ fail:
 	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure, allocated %ld of %ld bytes",
 			  (area->nr_pages*PAGE_SIZE), area->size);
+fail_no_warn:
 	vfree(area->addr);
 	return NULL;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 69f9aff39a2e..5a4f5c5a31e8 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = {
 	"thp_split_page_failed",
 	"thp_deferred_split_page",
 	"thp_split_pmd",
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	"thp_split_pud",
+#endif
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
@@ -1549,7 +1552,6 @@ static const struct file_operations proc_vmstat_file_operations = {
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SMP
-static struct workqueue_struct *vmstat_wq;
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
 
@@ -1620,7 +1622,7 @@ static void vmstat_update(struct work_struct *w)
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
 		 */
-		queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+		queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
 				this_cpu_ptr(&vmstat_work),
 				round_jiffies_relative(sysctl_stat_interval));
 	}
@@ -1699,7 +1701,7 @@ static void vmstat_shepherd(struct work_struct *w)
 		struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
 
 		if (!delayed_work_pending(dw) && need_update(cpu))
-			queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
+			queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
 	}
 	put_online_cpus();
 
@@ -1715,7 +1717,6 @@ static void __init start_shepherd_timer(void)
 		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
 			vmstat_update);
 
-	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
 }
@@ -1761,11 +1762,15 @@ static int vmstat_cpu_dead(unsigned int cpu)
 
 #endif
 
-static int __init setup_vmstat(void)
+struct workqueue_struct *mm_percpu_wq;
+
+void __init init_mm_internals(void)
 {
-#ifdef CONFIG_SMP
-	int ret;
+	int ret __maybe_unused;
 
+	mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0);
+
+#ifdef CONFIG_SMP
 	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
 					NULL, vmstat_cpu_dead);
 	if (ret < 0)
@@ -1789,9 +1794,7 @@ static int __init setup_vmstat(void)
 	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
 	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #endif
-	return 0;
 }
-module_init(setup_vmstat)
 
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
 
diff --git a/mm/workingset.c b/mm/workingset.c
index ac839fca0e76..eda05c71fa49 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -532,7 +532,7 @@ static int __init workingset_init(void)
 	pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
 	       timestamp_bits, max_order, bucket_order);
 
-	ret = list_lru_init_key(&shadow_nodes, &shadow_nodes_key);
+	ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key);
 	if (ret)
 		goto err;
 	ret = register_shrinker(&workingset_shadow_shrinker);
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 8970a2fd3b1a..54f63c4a809a 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -185,6 +185,12 @@ static inline void z3fold_page_lock(struct z3fold_header *zhdr)
 	spin_lock(&zhdr->page_lock);
 }
 
+/* Try to lock a z3fold page */
+static inline int z3fold_page_trylock(struct z3fold_header *zhdr)
+{
+	return spin_trylock(&zhdr->page_lock);
+}
+
 /* Unlock a z3fold page */
 static inline void z3fold_page_unlock(struct z3fold_header *zhdr)
 {
@@ -385,7 +391,7 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp,
 			spin_lock(&pool->lock);
 			zhdr = list_first_entry_or_null(&pool->unbuddied[i],
 						struct z3fold_header, buddy);
-			if (!zhdr) {
+			if (!zhdr || !z3fold_page_trylock(zhdr)) {
 				spin_unlock(&pool->lock);
 				continue;
 			}
@@ -394,7 +400,6 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp,
 			spin_unlock(&pool->lock);
 
 			page = virt_to_page(zhdr);
-			z3fold_page_lock(zhdr);
 			if (zhdr->first_chunks == 0) {
 				if (zhdr->middle_chunks != 0 &&
 				    chunks >= zhdr->start_middle)
@@ -667,6 +672,7 @@ next:
 			z3fold_page_unlock(zhdr);
 			spin_lock(&pool->lock);
 			if (kref_put(&zhdr->refcount, release_z3fold_page)) {
+				spin_unlock(&pool->lock);
 				atomic64_dec(&pool->pages_nr);
 				return 0;
 			}
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b7ee9c34dbd6..d41edd28298b 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -276,7 +276,7 @@ struct zs_pool {
 struct zspage {
 	struct {
 		unsigned int fullness:FULLNESS_BITS;
-		unsigned int class:CLASS_BITS;
+		unsigned int class:CLASS_BITS + 1;
 		unsigned int isolated:ISOLATED_BITS;
 		unsigned int magic:MAGIC_VAL_BITS;
 	};
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 5945f7e19c67..40d3d72beb53 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -23,10 +23,18 @@ int lowpan_register_netdevice(struct net_device *dev,
 {
 	int i, ret;
 
-	dev->addr_len = EUI64_ADDR_LEN;
+	switch (lltype) {
+	case LOWPAN_LLTYPE_IEEE802154:
+		dev->addr_len = EUI64_ADDR_LEN;
+		break;
+
+	case LOWPAN_LLTYPE_BTLE:
+		dev->addr_len = ETH_ALEN;
+		break;
+	}
+
 	dev->type = ARPHRD_6LOWPAN;
 	dev->mtu = IPV6_MIN_MTU;
-	dev->priv_flags |= IFF_NO_QUEUE;
 
 	lowpan_dev(dev)->lltype = lltype;
 
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 79f1fa22509a..6b1042e21656 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -278,6 +278,23 @@ lowpan_iphc_ctx_get_by_mcast_addr(const struct net_device *dev,
 	return ret;
 }
 
+static void lowpan_iphc_uncompress_lladdr(const struct net_device *dev,
+					  struct in6_addr *ipaddr,
+					  const void *lladdr)
+{
+	switch (dev->addr_len) {
+	case ETH_ALEN:
+		lowpan_iphc_uncompress_eui48_lladdr(ipaddr, lladdr);
+		break;
+	case EUI64_ADDR_LEN:
+		lowpan_iphc_uncompress_eui64_lladdr(ipaddr, lladdr);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
 /* Uncompress address function for source and
  * destination address(non-multicast).
  *
@@ -320,7 +337,7 @@ static int lowpan_iphc_uncompress_addr(struct sk_buff *skb,
 			lowpan_iphc_uncompress_802154_lladdr(ipaddr, lladdr);
 			break;
 		default:
-			lowpan_iphc_uncompress_eui64_lladdr(ipaddr, lladdr);
+			lowpan_iphc_uncompress_lladdr(dev, ipaddr, lladdr);
 			break;
 		}
 		break;
@@ -381,7 +398,7 @@ static int lowpan_iphc_uncompress_ctx_addr(struct sk_buff *skb,
 			lowpan_iphc_uncompress_802154_lladdr(ipaddr, lladdr);
 			break;
 		default:
-			lowpan_iphc_uncompress_eui64_lladdr(ipaddr, lladdr);
+			lowpan_iphc_uncompress_lladdr(dev, ipaddr, lladdr);
 			break;
 		}
 		ipv6_addr_prefix_copy(ipaddr, &ctx->pfx, ctx->plen);
@@ -666,6 +683,8 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev,
 
 	switch (iphc1 & (LOWPAN_IPHC_M | LOWPAN_IPHC_DAC)) {
 	case LOWPAN_IPHC_M | LOWPAN_IPHC_DAC:
+		skb->pkt_type = PACKET_BROADCAST;
+
 		spin_lock_bh(&lowpan_dev(dev)->ctx.lock);
 		ci = lowpan_iphc_ctx_get_by_id(dev, LOWPAN_IPHC_CID_DCI(cid));
 		if (!ci) {
@@ -681,11 +700,15 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev,
 		spin_unlock_bh(&lowpan_dev(dev)->ctx.lock);
 		break;
 	case LOWPAN_IPHC_M:
+		skb->pkt_type = PACKET_BROADCAST;
+
 		/* multicast */
 		err = lowpan_uncompress_multicast_daddr(skb, &hdr.daddr,
 							iphc1 & LOWPAN_IPHC_DAM_MASK);
 		break;
 	case LOWPAN_IPHC_DAC:
+		skb->pkt_type = PACKET_HOST;
+
 		spin_lock_bh(&lowpan_dev(dev)->ctx.lock);
 		ci = lowpan_iphc_ctx_get_by_id(dev, LOWPAN_IPHC_CID_DCI(cid));
 		if (!ci) {
@@ -701,6 +724,8 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev,
 		spin_unlock_bh(&lowpan_dev(dev)->ctx.lock);
 		break;
 	default:
+		skb->pkt_type = PACKET_HOST;
+
 		err = lowpan_iphc_uncompress_addr(skb, dev, &hdr.daddr,
 						  iphc1 & LOWPAN_IPHC_DAM_MASK,
 						  daddr);
@@ -802,6 +827,21 @@ lowpan_iphc_compress_ctx_802154_lladdr(const struct in6_addr *ipaddr,
 	return lladdr_compress;
 }
 
+static bool lowpan_iphc_addr_equal(const struct net_device *dev,
+				   const struct lowpan_iphc_ctx *ctx,
+				   const struct in6_addr *ipaddr,
+				   const void *lladdr)
+{
+	struct in6_addr tmp = {};
+
+	lowpan_iphc_uncompress_lladdr(dev, &tmp, lladdr);
+
+	if (ctx)
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+
+	return ipv6_addr_equal(&tmp, ipaddr);
+}
+
 static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct net_device *dev,
 				   const struct in6_addr *ipaddr,
 				   const struct lowpan_iphc_ctx *ctx,
@@ -819,13 +859,7 @@ static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct net_device *dev,
 		}
 		break;
 	default:
-		/* check for SAM/DAM = 11 */
-		memcpy(&tmp.s6_addr[8], lladdr, EUI64_ADDR_LEN);
-		/* second bit-flip (Universe/Local) is done according RFC2464 */
-		tmp.s6_addr[8] ^= 0x02;
-		/* context information are always used */
-		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
-		if (ipv6_addr_equal(&tmp, ipaddr)) {
+		if (lowpan_iphc_addr_equal(dev, ctx, ipaddr, lladdr)) {
 			dam = LOWPAN_IPHC_DAM_11;
 			goto out;
 		}
@@ -921,11 +955,12 @@ static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct net_device *dev,
 		}
 		break;
 	default:
-		if (is_addr_mac_addr_based(ipaddr, lladdr)) {
-			dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+		if (lowpan_iphc_addr_equal(dev, NULL, ipaddr, lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11;
 			pr_debug("address compression 0 bits\n");
 			goto out;
 		}
+
 		break;
 	}
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e97ab824e368..9ee5787634e5 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -562,8 +562,7 @@ static int vlan_dev_init(struct net_device *dev)
 			   NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
 			   NETIF_F_ALL_FCOE;
 
-	dev->features |= real_dev->vlan_features | NETIF_F_LLTX |
-			 NETIF_F_GSO_SOFTWARE;
+	dev->features |= dev->hw_features | NETIF_F_LLTX;
 	dev->gso_max_size = real_dev->gso_max_size;
 	dev->gso_max_segs = real_dev->gso_max_segs;
 	if (dev->features & NETIF_F_VLAN_FEATURES)
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 1270207f3d7c..9c94aad153b3 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -35,7 +35,8 @@ static inline int vlan_validate_qos_map(struct nlattr *attr)
 {
 	if (!attr)
 		return 0;
-	return nla_validate_nested(attr, IFLA_VLAN_QOS_MAX, vlan_map_policy);
+	return nla_validate_nested(attr, IFLA_VLAN_QOS_MAX, vlan_map_policy,
+				   NULL);
 }
 
 static int vlan_validate(struct nlattr *tb[], struct nlattr *data[])
diff --git a/net/9p/client.c b/net/9p/client.c
index 3ce672af1596..1218fb3b52da 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -592,9 +592,8 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		ename = &req->rc->sdata[req->rc->offset];
 		if (len > inline_len) {
 			/* We have error in external buffer */
-			err = copy_from_iter(ename + inline_len,
-					     len - inline_len, uidata);
-			if (err != len - inline_len) {
+			if (!copy_from_iter_full(ename + inline_len,
+					     len - inline_len, uidata)) {
 				err = -EFAULT;
 				goto out_err;
 			}
@@ -2101,6 +2100,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 		trace_9p_protocol_dump(clnt, req->rc);
 		goto free_and_error;
 	}
+	if (rsize < count) {
+		pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize);
+		count = rsize;
+	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count);
 
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 16d287565987..16e10680518c 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -74,7 +74,7 @@ pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size)
 {
 	size_t len = min(pdu->capacity - pdu->size, size);
 	struct iov_iter i = *from;
-	if (copy_from_iter(&pdu->sdata[pdu->size], len, &i) != len)
+	if (!copy_from_iter_full(&pdu->sdata[pdu->size], len, &i))
 		len = 0;
 
 	pdu->size += len;
diff --git a/net/Makefile b/net/Makefile
index 9b681550e3a3..9086ffbb5085 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_NET)		+= $(tmp-y)
 
 # LLC has to be linked before the files in net/802/
 obj-$(CONFIG_LLC)		+= llc/
-obj-$(CONFIG_NET)		+= ethernet/ 802/ sched/ netlink/
+obj-$(CONFIG_NET)		+= ethernet/ 802/ sched/ netlink/ bpf/
 obj-$(CONFIG_NETFILTER)		+= netfilter/
 obj-$(CONFIG_INET)		+= ipv4/
 obj-$(CONFIG_XFRM)		+= xfrm/
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 53b4ac09e7b7..ec527b62f79d 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -106,7 +106,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc)
 			entry->expires = jiffies - 1;
 			/* force resolution or expiration */
 			error = neigh_update(entry->neigh, NULL, NUD_NONE,
-					     NEIGH_UPDATE_F_ADMIN);
+					     NEIGH_UPDATE_F_ADMIN, 0);
 			if (error)
 				pr_crit("neigh_update failed with %d\n", error);
 			goto out;
@@ -481,7 +481,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 		link_vcc(clip_vcc, entry);
 	}
 	error = neigh_update(neigh, llc_oui, NUD_PERMANENT,
-			     NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN);
+			     NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0);
 	neigh_release(neigh);
 	return error;
 }
diff --git a/net/atm/common.c b/net/atm/common.c
index 9613381f5db0..f06422f4108d 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -62,21 +62,16 @@ static void vcc_remove_socket(struct sock *sk)
 	write_unlock_irq(&vcc_sklist_lock);
 }
 
-static struct sk_buff *alloc_tx(struct atm_vcc *vcc, unsigned int size)
+static bool vcc_tx_ready(struct atm_vcc *vcc, unsigned int size)
 {
-	struct sk_buff *skb;
 	struct sock *sk = sk_atm(vcc);
 
 	if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) {
 		pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n",
 			 sk_wmem_alloc_get(sk), size, sk->sk_sndbuf);
-		return NULL;
+		return false;
 	}
-	while (!(skb = alloc_skb(size, GFP_KERNEL)))
-		schedule();
-	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
-	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
-	return skb;
+	return true;
 }
 
 static void vcc_sock_destruct(struct sock *sk)
@@ -606,7 +601,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 	eff = (size+3) & ~3; /* align to word boundary */
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	error = 0;
-	while (!(skb = alloc_tx(vcc, eff))) {
+	while (!vcc_tx_ready(vcc, eff)) {
 		if (m->msg_flags & MSG_DONTWAIT) {
 			error = -EAGAIN;
 			break;
@@ -628,6 +623,15 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 	finish_wait(sk_sleep(sk), &wait);
 	if (error)
 		goto out;
+
+	skb = alloc_skb(eff, GFP_KERNEL);
+	if (!skb) {
+		error = -ENOMEM;
+		goto out;
+	}
+	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
+	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
+
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
diff --git a/net/atm/svc.c b/net/atm/svc.c
index db9794ec61d8..5589de7086af 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -318,7 +318,8 @@ out:
 	return error;
 }
 
-static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
+static int svc_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
@@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
 
 	lock_sock(sk);
 
-	error = svc_create(sock_net(sk), newsock, 0, 0);
+	error = svc_create(sock_net(sk), newsock, 0, kern);
 	if (error)
 		goto out;
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index a8e42cedf1db..b7c486752b3a 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1320,7 +1320,8 @@ out_release:
 	return err;
 }
 
-static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 7c3d994e90d8..495ba7cdcb04 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -679,15 +679,11 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	struct batadv_forw_packet *forw_packet_aggr;
+	struct sk_buff *skb;
 	unsigned char *skb_buff;
 	unsigned int skb_size;
 	atomic_t *queue_left = own_packet ? NULL : &bat_priv->batman_queue_left;
 
-	forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing,
-						    queue_left, bat_priv);
-	if (!forw_packet_aggr)
-		return;
-
 	if (atomic_read(&bat_priv->aggregated_ogms) &&
 	    packet_len < BATADV_MAX_AGGREGATION_BYTES)
 		skb_size = BATADV_MAX_AGGREGATION_BYTES;
@@ -696,9 +692,14 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 
 	skb_size += ETH_HLEN;
 
-	forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size);
-	if (!forw_packet_aggr->skb) {
-		batadv_forw_packet_free(forw_packet_aggr, true);
+	skb = netdev_alloc_skb_ip_align(NULL, skb_size);
+	if (!skb)
+		return;
+
+	forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing,
+						    queue_left, bat_priv, skb);
+	if (!forw_packet_aggr) {
+		kfree_skb(skb);
 		return;
 	}
 
@@ -2477,6 +2478,16 @@ static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface)
 	batadv_iv_ogm_schedule(hard_iface);
 }
 
+/**
+ * batadv_iv_init_sel_class - initialize GW selection class
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+static void batadv_iv_init_sel_class(struct batadv_priv *bat_priv)
+{
+	/* set default TQ difference threshold to 20 */
+	atomic_set(&bat_priv->gw.sel_class, 20);
+}
+
 static struct batadv_gw_node *
 batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 {
@@ -2823,6 +2834,7 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
 		.del_if = batadv_iv_ogm_orig_del_if,
 	},
 	.gw = {
+		.init_sel_class = batadv_iv_init_sel_class,
 		.get_best_gw_node = batadv_iv_gw_get_best_gw_node,
 		.is_eligible = batadv_iv_gw_is_eligible,
 #ifdef CONFIG_BATMAN_ADV_DEBUGFS
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 0acd081dd286..a36c8e7291d6 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -668,6 +668,16 @@ err_ifinfo1:
 	return ret;
 }
 
+/**
+ * batadv_v_init_sel_class - initialize GW selection class
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+static void batadv_v_init_sel_class(struct batadv_priv *bat_priv)
+{
+	/* set default throughput difference threshold to 5Mbps */
+	atomic_set(&bat_priv->gw.sel_class, 50);
+}
+
 static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv,
 					char *buff, size_t count)
 {
@@ -1052,6 +1062,7 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = {
 		.dump = batadv_v_orig_dump,
 	},
 	.gw = {
+		.init_sel_class = batadv_v_init_sel_class,
 		.store_sel_class = batadv_v_store_sel_class,
 		.show_sel_class = batadv_v_show_sel_class,
 		.get_best_gw_node = batadv_v_gw_get_best_gw_node,
@@ -1092,9 +1103,6 @@ int batadv_v_mesh_init(struct batadv_priv *bat_priv)
 	if (ret < 0)
 		return ret;
 
-	/* set default throughput difference threshold to 5Mbps */
-	atomic_set(&bat_priv->gw.sel_class, 50);
-
 	return 0;
 }
 
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ba8420d8a992..d07e89ec8467 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -395,7 +395,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 		ether_addr_copy(ethhdr->h_source, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): CLAIM %pM on vid %d\n", mac,
-			   BATADV_PRINT_VID(vid));
+			   batadv_print_vid(vid));
 		break;
 	case BATADV_CLAIM_TYPE_UNCLAIM:
 		/* unclaim frame
@@ -404,7 +404,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 		ether_addr_copy(hw_src, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac,
-			   BATADV_PRINT_VID(vid));
+			   batadv_print_vid(vid));
 		break;
 	case BATADV_CLAIM_TYPE_ANNOUNCE:
 		/* announcement frame
@@ -413,7 +413,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 		ether_addr_copy(hw_src, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): ANNOUNCE of %pM on vid %d\n",
-			   ethhdr->h_source, BATADV_PRINT_VID(vid));
+			   ethhdr->h_source, batadv_print_vid(vid));
 		break;
 	case BATADV_CLAIM_TYPE_REQUEST:
 		/* request frame
@@ -425,14 +425,14 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): REQUEST of %pM to %pM on vid %d\n",
 			   ethhdr->h_source, ethhdr->h_dest,
-			   BATADV_PRINT_VID(vid));
+			   batadv_print_vid(vid));
 		break;
 	case BATADV_CLAIM_TYPE_LOOPDETECT:
 		ether_addr_copy(ethhdr->h_source, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): LOOPDETECT of %pM to %pM on vid %d\n",
 			   ethhdr->h_source, ethhdr->h_dest,
-			   BATADV_PRINT_VID(vid));
+			   batadv_print_vid(vid));
 
 		break;
 	}
@@ -475,9 +475,9 @@ static void batadv_bla_loopdetect_report(struct work_struct *work)
 
 	batadv_info(bat_priv->soft_iface,
 		    "Possible loop on VLAN %d detected which can't be handled by BLA - please check your network setup!\n",
-		    BATADV_PRINT_VID(backbone_gw->vid));
+		    batadv_print_vid(backbone_gw->vid));
 	snprintf(vid_str, sizeof(vid_str), "%d",
-		 BATADV_PRINT_VID(backbone_gw->vid));
+		 batadv_print_vid(backbone_gw->vid));
 	vid_str[sizeof(vid_str) - 1] = 0;
 
 	batadv_throw_uevent(bat_priv, BATADV_UEV_BLA, BATADV_UEV_LOOPDETECT,
@@ -510,7 +510,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig,
 
 	batadv_dbg(BATADV_DBG_BLA, bat_priv,
 		   "bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n",
-		   orig, BATADV_PRINT_VID(vid));
+		   orig, batadv_print_vid(vid));
 
 	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry)
@@ -719,7 +719,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n",
-			   mac, BATADV_PRINT_VID(vid));
+			   mac, batadv_print_vid(vid));
 
 		kref_get(&claim->refcount);
 		hash_added = batadv_hash_add(bat_priv->bla.claim_hash,
@@ -739,8 +739,8 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 			goto claim_free_ref;
 
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
-			   "bla_add_claim(): changing ownership for %pM, vid %d\n",
-			   mac, BATADV_PRINT_VID(vid));
+			   "bla_add_claim(): changing ownership for %pM, vid %d to gw %pM\n",
+			   mac, batadv_print_vid(vid), backbone_gw->orig);
 
 		remove_crc = true;
 	}
@@ -809,7 +809,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 		return;
 
 	batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n",
-		   mac, BATADV_PRINT_VID(vid));
+		   mac, batadv_print_vid(vid));
 
 	batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim,
 			   batadv_choose_claim, claim);
@@ -849,7 +849,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
 
 	batadv_dbg(BATADV_DBG_BLA, bat_priv,
 		   "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n",
-		   BATADV_PRINT_VID(vid), backbone_gw->orig, crc);
+		   batadv_print_vid(vid), backbone_gw->orig, crc);
 
 	spin_lock_bh(&backbone_gw->crc_lock);
 	backbone_crc = backbone_gw->crc;
@@ -859,7 +859,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
 		batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv,
 			   "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n",
 			   backbone_gw->orig,
-			   BATADV_PRINT_VID(backbone_gw->vid),
+			   batadv_print_vid(backbone_gw->vid),
 			   backbone_crc, crc);
 
 		batadv_bla_send_request(backbone_gw);
@@ -904,7 +904,7 @@ static bool batadv_handle_request(struct batadv_priv *bat_priv,
 
 	batadv_dbg(BATADV_DBG_BLA, bat_priv,
 		   "handle_request(): REQUEST vid %d (sent by %pM)...\n",
-		   BATADV_PRINT_VID(vid), ethhdr->h_source);
+		   batadv_print_vid(vid), ethhdr->h_source);
 
 	batadv_bla_answer_request(bat_priv, primary_if, vid);
 	return true;
@@ -941,7 +941,7 @@ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv,
 	/* this must be an UNCLAIM frame */
 	batadv_dbg(BATADV_DBG_BLA, bat_priv,
 		   "handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n",
-		   claim_addr, BATADV_PRINT_VID(vid), backbone_gw->orig);
+		   claim_addr, batadv_print_vid(vid), backbone_gw->orig);
 
 	batadv_bla_del_claim(bat_priv, claim_addr, vid);
 	batadv_backbone_gw_put(backbone_gw);
@@ -1161,7 +1161,7 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv,
 	if (ret == 1)
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n",
-			   ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src,
+			   ethhdr->h_source, batadv_print_vid(vid), hw_src,
 			   hw_dst);
 
 	if (ret < 2)
@@ -1197,7 +1197,7 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv,
 
 	batadv_dbg(BATADV_DBG_BLA, bat_priv,
 		   "bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n",
-		   ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src, hw_dst);
+		   ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst);
 	return true;
 }
 
@@ -1295,10 +1295,13 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv,
 				goto skip;
 
 			batadv_dbg(BATADV_DBG_BLA, bat_priv,
-				   "bla_purge_claims(): %pM, vid %d, time out\n",
-				   claim->addr, claim->vid);
+				   "bla_purge_claims(): timed out.\n");
 
 purge_now:
+			batadv_dbg(BATADV_DBG_BLA, bat_priv,
+				   "bla_purge_claims(): %pM, vid %d\n",
+				   claim->addr, claim->vid);
+
 			batadv_handle_unclaim(bat_priv, primary_if,
 					      backbone_gw->orig,
 					      claim->addr, claim->vid);
@@ -1846,6 +1849,13 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		/* possible optimization: race for a claim */
 		/* No claim exists yet, claim it for us!
 		 */
+
+		batadv_dbg(BATADV_DBG_BLA, bat_priv,
+			   "bla_rx(): Unclaimed MAC %pM found. Claim it. Local: %s\n",
+			   ethhdr->h_source,
+			   batadv_is_my_client(bat_priv,
+					       ethhdr->h_source, vid) ?
+			   "yes" : "no");
 		batadv_handle_claim(bat_priv, primary_if,
 				    primary_if->net_dev->dev_addr,
 				    ethhdr->h_source, vid);
@@ -1963,10 +1973,22 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		/* if yes, the client has roamed and we have
 		 * to unclaim it.
 		 */
-		batadv_handle_unclaim(bat_priv, primary_if,
-				      primary_if->net_dev->dev_addr,
-				      ethhdr->h_source, vid);
-		goto allow;
+		if (batadv_has_timed_out(claim->lasttime, 100)) {
+			/* only unclaim if the last claim entry is
+			 * older than 100 ms to make sure we really
+			 * have a roaming client here.
+			 */
+			batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_tx(): Roaming client %pM detected. Unclaim it.\n",
+				   ethhdr->h_source);
+			batadv_handle_unclaim(bat_priv, primary_if,
+					      primary_if->net_dev->dev_addr,
+					      ethhdr->h_source, vid);
+			goto allow;
+		} else {
+			batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_tx(): Race for claim %pM detected. Drop packet.\n",
+				   ethhdr->h_source);
+			goto handled;
+		}
 	}
 
 	/* check if it is a multicast/broadcast frame */
@@ -2042,7 +2064,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset)
 			backbone_crc = backbone_gw->crc;
 			spin_unlock_bh(&backbone_gw->crc_lock);
 			seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n",
-				   claim->addr, BATADV_PRINT_VID(claim->vid),
+				   claim->addr, batadv_print_vid(claim->vid),
 				   backbone_gw->orig,
 				   (is_own ? 'x' : ' '),
 				   backbone_crc);
@@ -2274,7 +2296,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset)
 
 			seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n",
 				   backbone_gw->orig,
-				   BATADV_PRINT_VID(backbone_gw->vid), secs,
+				   batadv_print_vid(backbone_gw->vid), secs,
 				   msecs, backbone_crc);
 		}
 		rcu_read_unlock();
@@ -2449,3 +2471,52 @@ out:
 
 	return ret;
 }
+
+#ifdef CONFIG_BATMAN_ADV_DAT
+/**
+ * batadv_bla_check_claim - check if address is claimed
+ *
+ * @bat_priv: the bat priv with all the soft interface information
+ * @addr: mac address of which the claim status is checked
+ * @vid: the VLAN ID
+ *
+ * addr is checked if this address is claimed by the local device itself.
+ *
+ * Return: true if bla is disabled or the mac is claimed by the device,
+ * false if the device addr is already claimed by another gateway
+ */
+bool batadv_bla_check_claim(struct batadv_priv *bat_priv,
+			    u8 *addr, unsigned short vid)
+{
+	struct batadv_bla_claim search_claim;
+	struct batadv_bla_claim *claim = NULL;
+	struct batadv_hard_iface *primary_if = NULL;
+	bool ret = true;
+
+	if (!atomic_read(&bat_priv->bridge_loop_avoidance))
+		return ret;
+
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (!primary_if)
+		return ret;
+
+	/* First look if the mac address is claimed */
+	ether_addr_copy(search_claim.addr, addr);
+	search_claim.vid = vid;
+
+	claim = batadv_claim_hash_find(bat_priv, &search_claim);
+
+	/* If there is a claim and we are not owner of the claim,
+	 * return false.
+	 */
+	if (claim) {
+		if (!batadv_compare_eth(claim->backbone_gw->orig,
+					primary_if->net_dev->dev_addr))
+			ret = false;
+		batadv_claim_put(claim);
+	}
+
+	batadv_hardif_put(primary_if);
+	return ret;
+}
+#endif
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index e157986bd01c..234775748b8e 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -69,6 +69,10 @@ void batadv_bla_status_update(struct net_device *net_dev);
 int batadv_bla_init(struct batadv_priv *bat_priv);
 void batadv_bla_free(struct batadv_priv *bat_priv);
 int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb);
+#ifdef CONFIG_BATMAN_ADV_DAT
+bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
+			    unsigned short vid);
+#endif
 #define BATADV_BLA_CRC_INIT	0
 #else /* ifdef CONFIG_BATMAN_ADV_BLA */
 
@@ -145,6 +149,13 @@ static inline int batadv_bla_backbone_dump(struct sk_buff *msg,
 	return -EOPNOTSUPP;
 }
 
+static inline
+bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
+			    unsigned short vid)
+{
+	return true;
+}
+
 #endif /* ifdef CONFIG_BATMAN_ADV_BLA */
 
 #endif /* ifndef _NET_BATMAN_ADV_BLA_H_ */
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 1bfd1dbc2feb..013e970eff39 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -43,6 +43,7 @@
 #include <linux/workqueue.h>
 #include <net/arp.h>
 
+#include "bridge_loop_avoidance.h"
 #include "hard-interface.h"
 #include "hash.h"
 #include "log.h"
@@ -330,7 +331,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
 		batadv_dbg(BATADV_DBG_DAT, bat_priv,
 			   "Entry updated: %pI4 %pM (vid: %d)\n",
 			   &dat_entry->ip, dat_entry->mac_addr,
-			   BATADV_PRINT_VID(vid));
+			   batadv_print_vid(vid));
 		goto out;
 	}
 
@@ -356,7 +357,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
 	}
 
 	batadv_dbg(BATADV_DBG_DAT, bat_priv, "New entry added: %pI4 %pM (vid: %d)\n",
-		   &dat_entry->ip, dat_entry->mac_addr, BATADV_PRINT_VID(vid));
+		   &dat_entry->ip, dat_entry->mac_addr, batadv_print_vid(vid));
 
 out:
 	if (dat_entry)
@@ -835,7 +836,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset)
 
 			seq_printf(seq, " * %15pI4 %14pM %4i %6i:%02i\n",
 				   &dat_entry->ip, dat_entry->mac_addr,
-				   BATADV_PRINT_VID(dat_entry->vid),
+				   batadv_print_vid(dat_entry->vid),
 				   last_seen_mins, last_seen_secs);
 		}
 		rcu_read_unlock();
@@ -1002,6 +1003,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 	bool ret = false;
 	struct batadv_dat_entry *dat_entry = NULL;
 	struct sk_buff *skb_new;
+	struct net_device *soft_iface = bat_priv->soft_iface;
 	int hdr_size = 0;
 	unsigned short vid;
 
@@ -1040,16 +1042,30 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 			goto out;
 		}
 
+		/* If BLA is enabled, only send ARP replies if we have claimed
+		 * the destination for the ARP request or if no one else of
+		 * the backbone gws belonging to our backbone has claimed the
+		 * destination.
+		 */
+		if (!batadv_bla_check_claim(bat_priv,
+					    dat_entry->mac_addr, vid)) {
+			batadv_dbg(BATADV_DBG_DAT, bat_priv,
+				   "Device %pM claimed by another backbone gw. Don't send ARP reply!",
+				   dat_entry->mac_addr);
+			ret = true;
+			goto out;
+		}
+
 		skb_new = batadv_dat_arp_create_reply(bat_priv, ip_dst, ip_src,
 						      dat_entry->mac_addr,
 						      hw_src, vid);
 		if (!skb_new)
 			goto out;
 
-		skb_new->protocol = eth_type_trans(skb_new,
-						   bat_priv->soft_iface);
-		bat_priv->stats.rx_packets++;
-		bat_priv->stats.rx_bytes += skb->len + ETH_HLEN + hdr_size;
+		skb_new->protocol = eth_type_trans(skb_new, soft_iface);
+
+		soft_iface->stats.rx_packets++;
+		soft_iface->stats.rx_bytes += skb->len + ETH_HLEN + hdr_size;
 
 		netif_rx(skb_new);
 		batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n");
@@ -1188,6 +1204,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
 bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
 					 struct sk_buff *skb, int hdr_size)
 {
+	struct batadv_dat_entry *dat_entry = NULL;
 	u16 type;
 	__be32 ip_src, ip_dst;
 	u8 *hw_src, *hw_dst;
@@ -1210,12 +1227,41 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
 	hw_dst = batadv_arp_hw_dst(skb, hdr_size);
 	ip_dst = batadv_arp_ip_dst(skb, hdr_size);
 
+	/* If ip_dst is already in cache and has the right mac address,
+	 * drop this frame if this ARP reply is destined for us because it's
+	 * most probably an ARP reply generated by another node of the DHT.
+	 * We have most probably received already a reply earlier. Delivering
+	 * this frame would lead to doubled receive of an ARP reply.
+	 */
+	dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_src, vid);
+	if (dat_entry && batadv_compare_eth(hw_src, dat_entry->mac_addr)) {
+		batadv_dbg(BATADV_DBG_DAT, bat_priv, "Doubled ARP reply removed: ARP MSG = [src: %pM-%pI4 dst: %pM-%pI4]; dat_entry: %pM-%pI4\n",
+			   hw_src, &ip_src, hw_dst, &ip_dst,
+			   dat_entry->mac_addr,	&dat_entry->ip);
+		dropped = true;
+		goto out;
+	}
+
 	/* Update our internal cache with both the IP addresses the node got
 	 * within the ARP reply
 	 */
 	batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid);
 	batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid);
 
+	/* If BLA is enabled, only forward ARP replies if we have claimed the
+	 * source of the ARP reply or if no one else of the same backbone has
+	 * already claimed that client. This prevents that different gateways
+	 * to the same backbone all forward the ARP reply leading to multiple
+	 * replies in the backbone.
+	 */
+	if (!batadv_bla_check_claim(bat_priv, hw_src, vid)) {
+		batadv_dbg(BATADV_DBG_DAT, bat_priv,
+			   "Device %pM claimed by another backbone gw. Drop ARP reply.\n",
+			   hw_src);
+		dropped = true;
+		goto out;
+	}
+
 	/* if this REPLY is directed to a client of mine, let's deliver the
 	 * packet to the interface
 	 */
@@ -1228,6 +1274,8 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
 out:
 	if (dropped)
 		kfree_skb(skb);
+	if (dat_entry)
+		batadv_dat_entry_put(dat_entry);
 	/* if dropped == false -> deliver to the interface */
 	return dropped;
 }
@@ -1256,7 +1304,7 @@ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
 	/* If this packet is an ARP_REQUEST and the node already has the
 	 * information that it is going to ask, then the packet can be dropped
 	 */
-	if (forw_packet->num_packets)
+	if (batadv_forw_packet_is_rebroadcast(forw_packet))
 		goto out;
 
 	vid = batadv_dat_get_vid(forw_packet->skb, &hdr_size);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 11a23fd6e1a0..8f964beaac28 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -404,7 +404,7 @@ out:
  * batadv_frag_create - create a fragment from skb
  * @skb: skb to create fragment from
  * @frag_head: header to use in new fragment
- * @mtu: size of new fragment
+ * @fragment_size: size of new fragment
  *
  * Split the passed skb into two fragments: A new one with size matching the
  * passed mtu and the old one with the rest. The new skb contains data from the
@@ -414,11 +414,11 @@ out:
  */
 static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
 					  struct batadv_frag_packet *frag_head,
-					  unsigned int mtu)
+					  unsigned int fragment_size)
 {
 	struct sk_buff *skb_fragment;
 	unsigned int header_size = sizeof(*frag_head);
-	unsigned int fragment_size = mtu - header_size;
+	unsigned int mtu = fragment_size + header_size;
 
 	skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN);
 	if (!skb_fragment)
@@ -456,7 +456,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 	struct sk_buff *skb_fragment;
 	unsigned int mtu = neigh_node->if_incoming->net_dev->mtu;
 	unsigned int header_size = sizeof(frag_header);
-	unsigned int max_fragment_size, max_packet_size;
+	unsigned int max_fragment_size, num_fragments;
 	int ret;
 
 	/* To avoid merge and refragmentation at next-hops we never send
@@ -464,10 +464,15 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 	 */
 	mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE);
 	max_fragment_size = mtu - header_size;
-	max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS;
+
+	if (skb->len == 0 || max_fragment_size == 0)
+		return -EINVAL;
+
+	num_fragments = (skb->len - 1) / max_fragment_size + 1;
+	max_fragment_size = (skb->len - 1) / num_fragments + 1;
 
 	/* Don't even try to fragment, if we need more than 16 fragments */
-	if (skb->len > max_packet_size) {
+	if (num_fragments > BATADV_FRAG_MAX_FRAGMENTS) {
 		ret = -EAGAIN;
 		goto free_skb;
 	}
@@ -507,7 +512,8 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 			goto put_primary_if;
 		}
 
-		skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
+		skb_fragment = batadv_frag_create(skb, &frag_header,
+						  max_fragment_size);
 		if (!skb_fragment) {
 			ret = -ENOMEM;
 			goto put_primary_if;
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 5db2e43e3775..33940c5c74a8 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -253,6 +253,11 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
  */
 void batadv_gw_init(struct batadv_priv *bat_priv)
 {
+	if (bat_priv->algo_ops->gw.init_sel_class)
+		bat_priv->algo_ops->gw.init_sel_class(bat_priv);
+	else
+		atomic_set(&bat_priv->gw.sel_class, 1);
+
 	batadv_tvlv_handler_register(bat_priv, batadv_gw_tvlv_ogm_handler_v1,
 				     NULL, BATADV_TVLV_GW, 1,
 				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index 7a2b9f4da078..65ce97efa6b5 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -73,9 +73,10 @@ __printf(2, 3);
 /* possibly ratelimited debug output */
 #define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...)		\
 	do {								\
-		if (atomic_read(&(bat_priv)->log_level) & (type) &&	\
+		struct batadv_priv *__batpriv = (bat_priv);		\
+		if (atomic_read(&__batpriv->log_level) & (type) &&	\
 		    (!(ratelimited) || net_ratelimit()))		\
-			batadv_debug_log(bat_priv, fmt, ## arg);	\
+			batadv_debug_log(__batpriv, fmt, ## arg);	\
 	}								\
 	while (0)
 #else /* !CONFIG_BATMAN_ADV_DEBUG */
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 5000c540614d..fb381fb26a66 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -516,6 +516,9 @@ static void batadv_recv_handler_init(void)
 	BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12);
 	BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8);
 
+	i = FIELD_SIZEOF(struct sk_buff, cb);
+	BUILD_BUG_ON(sizeof(struct batadv_skb_cb) > i);
+
 	/* broadcast packet */
 	batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
 
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 57a8103dbce7..810f7d026f54 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2017.0"
+#define BATADV_SOURCE_VERSION "2017.1"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -193,6 +193,7 @@ enum batadv_uev_type {
 #include <linux/percpu.h>
 #include <linux/types.h>
 
+#include "packet.h"
 #include "types.h"
 
 struct net_device;
@@ -200,8 +201,19 @@ struct packet_type;
 struct seq_file;
 struct sk_buff;
 
-#define BATADV_PRINT_VID(vid) (((vid) & BATADV_VLAN_HAS_TAG) ? \
-			       (int)((vid) & VLAN_VID_MASK) : -1)
+/**
+ * batadv_print_vid - return printable version of vid information
+ * @vid: the VLAN identifier
+ *
+ * Return: -1 when no VLAN is used, VLAN id otherwise
+ */
+static inline int batadv_print_vid(unsigned short vid)
+{
+	if (vid & BATADV_VLAN_HAS_TAG)
+		return (int)(vid & VLAN_VID_MASK);
+	else
+		return -1;
+}
 
 extern struct list_head batadv_hardif_list;
 
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 952ba81a565b..d327670641ac 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -494,9 +494,8 @@ static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
 	if (!bridged)
 		goto update;
 
-#if !IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
-	pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
-#endif
+	if (!IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING))
+		pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
 
 	querier4.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP);
 	querier4.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP);
@@ -671,7 +670,6 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
 /**
  * batadv_mcast_is_report_ipv6 - check for MLD reports
  * @skb: the ethernet frame destined for the mesh
@@ -736,7 +734,6 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
 
 	return 0;
 }
-#endif
 
 /**
  * batadv_mcast_forw_mode_check - check for optimized forwarding potential
@@ -765,11 +762,12 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
 	case ETH_P_IP:
 		return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
 							 is_unsnoopable);
-#if IS_ENABLED(CONFIG_IPV6)
 	case ETH_P_IPV6:
+		if (!IS_ENABLED(CONFIG_IPV6))
+			return -EINVAL;
+
 		return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
 							 is_unsnoopable);
-#endif
 	default:
 		return -EINVAL;
 	}
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 7fd740b6e36d..e1ebe14ee2a6 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -941,15 +941,17 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
 	struct batadv_unicast_packet *unicast_packet;
 	struct batadv_unicast_4addr_packet *unicast_4addr_packet;
-	u8 *orig_addr;
-	struct batadv_orig_node *orig_node = NULL;
+	u8 *orig_addr, *orig_addr_gw;
+	struct batadv_orig_node *orig_node = NULL, *orig_node_gw = NULL;
 	int check, hdr_size = sizeof(*unicast_packet);
 	enum batadv_subtype subtype;
-	bool is4addr;
+	struct ethhdr *ethhdr;
 	int ret = NET_RX_DROP;
+	bool is4addr, is_gw;
 
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 	unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
+	ethhdr = eth_hdr(skb);
 
 	is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR;
 	/* the caller function should have already pulled 2 bytes */
@@ -972,6 +974,23 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 
 	/* packet for me */
 	if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) {
+		/* If this is a unicast packet from another backgone gw,
+		 * drop it.
+		 */
+		orig_addr_gw = ethhdr->h_source;
+		orig_node_gw = batadv_orig_hash_find(bat_priv, orig_addr_gw);
+		if (orig_node_gw) {
+			is_gw = batadv_bla_is_backbone_gw(skb, orig_node_gw,
+							  hdr_size);
+			batadv_orig_node_put(orig_node_gw);
+			if (is_gw) {
+				batadv_dbg(BATADV_DBG_BLA, bat_priv,
+					   "recv_unicast_packet(): Dropped unicast pkt received from another backbone gw %pM.\n",
+					   orig_addr_gw);
+				return NET_RX_DROP;
+			}
+		}
+
 		if (is4addr) {
 			subtype = unicast_4addr_packet->subtype;
 			batadv_dat_inc_counter(bat_priv, subtype);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 1489ec27daff..403df596a73d 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -482,6 +482,7 @@ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet,
  * @if_outgoing: The (optional) if_outgoing to be grabbed
  * @queue_left: The (optional) queue counter to decrease
  * @bat_priv: The bat_priv for the mesh of this forw_packet
+ * @skb: The raw packet this forwarding packet shall contain
  *
  * Allocates a forwarding packet and tries to get a reference to the
  * (optional) if_incoming, if_outgoing and queue_left. If queue_left
@@ -493,7 +494,8 @@ struct batadv_forw_packet *
 batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
 			 struct batadv_hard_iface *if_outgoing,
 			 atomic_t *queue_left,
-			 struct batadv_priv *bat_priv)
+			 struct batadv_priv *bat_priv,
+			 struct sk_buff *skb)
 {
 	struct batadv_forw_packet *forw_packet;
 	const char *qname;
@@ -525,7 +527,7 @@ batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
 
 	INIT_HLIST_NODE(&forw_packet->list);
 	INIT_HLIST_NODE(&forw_packet->cleanup_list);
-	forw_packet->skb = NULL;
+	forw_packet->skb = skb;
 	forw_packet->queue_left = queue_left;
 	forw_packet->if_incoming = if_incoming;
 	forw_packet->if_outgoing = if_outgoing;
@@ -756,22 +758,23 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
 	if (!primary_if)
 		goto err;
 
+	newskb = skb_copy(skb, GFP_ATOMIC);
+	if (!newskb) {
+		batadv_hardif_put(primary_if);
+		goto err;
+	}
+
 	forw_packet = batadv_forw_packet_alloc(primary_if, NULL,
 					       &bat_priv->bcast_queue_left,
-					       bat_priv);
+					       bat_priv, newskb);
 	batadv_hardif_put(primary_if);
 	if (!forw_packet)
-		goto err;
-
-	newskb = skb_copy(skb, GFP_ATOMIC);
-	if (!newskb)
 		goto err_packet_free;
 
 	/* as we have a copy now, it is safe to decrease the TTL */
 	bcast_packet = (struct batadv_bcast_packet *)newskb->data;
 	bcast_packet->ttl--;
 
-	forw_packet->skb = newskb;
 	forw_packet->own = own_packet;
 
 	INIT_DELAYED_WORK(&forw_packet->delayed_work,
@@ -781,11 +784,60 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
 	return NETDEV_TX_OK;
 
 err_packet_free:
-	batadv_forw_packet_free(forw_packet, true);
+	kfree_skb(newskb);
 err:
 	return NETDEV_TX_BUSY;
 }
 
+/**
+ * batadv_forw_packet_bcasts_left - check if a retransmission is necessary
+ * @forw_packet: the forwarding packet to check
+ * @hard_iface: the interface to check on
+ *
+ * Checks whether a given packet has any (re)transmissions left on the provided
+ * interface.
+ *
+ * hard_iface may be NULL: In that case the number of transmissions this skb had
+ * so far is compared with the maximum amount of retransmissions independent of
+ * any interface instead.
+ *
+ * Return: True if (re)transmissions are left, false otherwise.
+ */
+static bool
+batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet,
+			       struct batadv_hard_iface *hard_iface)
+{
+	unsigned int max;
+
+	if (hard_iface)
+		max = hard_iface->num_bcasts;
+	else
+		max = BATADV_NUM_BCASTS_MAX;
+
+	return BATADV_SKB_CB(forw_packet->skb)->num_bcasts < max;
+}
+
+/**
+ * batadv_forw_packet_bcasts_inc - increment retransmission counter of a packet
+ * @forw_packet: the packet to increase the counter for
+ */
+static void
+batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet)
+{
+	BATADV_SKB_CB(forw_packet->skb)->num_bcasts++;
+}
+
+/**
+ * batadv_forw_packet_is_rebroadcast - check packet for previous transmissions
+ * @forw_packet: the packet to check
+ *
+ * Return: True if this packet was transmitted before, false otherwise.
+ */
+bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet)
+{
+	return BATADV_SKB_CB(forw_packet->skb)->num_bcasts > 0;
+}
+
 static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 {
 	struct batadv_hard_iface *hard_iface;
@@ -826,7 +878,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 		if (hard_iface->soft_iface != soft_iface)
 			continue;
 
-		if (forw_packet->num_packets >= hard_iface->num_bcasts)
+		if (!batadv_forw_packet_bcasts_left(forw_packet, hard_iface))
 			continue;
 
 		if (forw_packet->own) {
@@ -884,10 +936,10 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 	}
 	rcu_read_unlock();
 
-	forw_packet->num_packets++;
+	batadv_forw_packet_bcasts_inc(forw_packet);
 
 	/* if we still have some more bcasts to send */
-	if (forw_packet->num_packets < BATADV_NUM_BCASTS_MAX) {
+	if (batadv_forw_packet_bcasts_left(forw_packet, NULL)) {
 		batadv_forw_packet_bcast_queue(bat_priv, forw_packet,
 					       send_time);
 		return;
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index f21166d10323..a16b34f473ef 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -34,11 +34,13 @@ struct batadv_forw_packet *
 batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
 			 struct batadv_hard_iface *if_outgoing,
 			 atomic_t *queue_left,
-			 struct batadv_priv *bat_priv);
+			 struct batadv_priv *bat_priv,
+			 struct sk_buff *skb);
 bool batadv_forw_packet_steal(struct batadv_forw_packet *packet, spinlock_t *l);
 void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv,
 				    struct batadv_forw_packet *forw_packet,
 				    unsigned long send_time);
+bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet);
 
 int batadv_send_skb_to_orig(struct sk_buff *skb,
 			    struct batadv_orig_node *orig_node,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5d099b2e6cfc..b25789abf7b9 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -64,28 +64,6 @@
 #include "sysfs.h"
 #include "translation-table.h"
 
-static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd);
-static void batadv_get_drvinfo(struct net_device *dev,
-			       struct ethtool_drvinfo *info);
-static u32 batadv_get_msglevel(struct net_device *dev);
-static void batadv_set_msglevel(struct net_device *dev, u32 value);
-static u32 batadv_get_link(struct net_device *dev);
-static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data);
-static void batadv_get_ethtool_stats(struct net_device *dev,
-				     struct ethtool_stats *stats, u64 *data);
-static int batadv_get_sset_count(struct net_device *dev, int stringset);
-
-static const struct ethtool_ops batadv_ethtool_ops = {
-	.get_settings = batadv_get_settings,
-	.get_drvinfo = batadv_get_drvinfo,
-	.get_msglevel = batadv_get_msglevel,
-	.set_msglevel = batadv_set_msglevel,
-	.get_link = batadv_get_link,
-	.get_strings = batadv_get_strings,
-	.get_ethtool_stats = batadv_get_ethtool_stats,
-	.get_sset_count = batadv_get_sset_count,
-};
-
 int batadv_skb_head_push(struct sk_buff *skb, unsigned int len)
 {
 	int result;
@@ -140,7 +118,7 @@ static u64 batadv_sum_counter(struct batadv_priv *bat_priv,  size_t idx)
 static struct net_device_stats *batadv_interface_stats(struct net_device *dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct net_device_stats *stats = &bat_priv->stats;
+	struct net_device_stats *stats = &dev->stats;
 
 	stats->tx_packets = batadv_sum_counter(bat_priv, BATADV_CNT_TX);
 	stats->tx_bytes = batadv_sum_counter(bat_priv, BATADV_CNT_TX_BYTES);
@@ -230,6 +208,9 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
 		goto dropped;
 
+	/* reset control block to avoid left overs from previous users */
+	memset(skb->cb, 0, sizeof(struct batadv_skb_cb));
+
 	netif_trans_update(soft_iface);
 	vid = batadv_get_vid(skb, 0);
 	ethhdr = eth_hdr(skb);
@@ -819,7 +800,6 @@ static int batadv_softif_init_late(struct net_device *dev)
 	atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
 #endif
 	atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF);
-	atomic_set(&bat_priv->gw.sel_class, 20);
 	atomic_set(&bat_priv->gw.bandwidth_down, 100);
 	atomic_set(&bat_priv->gw.bandwidth_up, 20);
 	atomic_set(&bat_priv->orig_interval, 1000);
@@ -948,6 +928,98 @@ static const struct net_device_ops batadv_netdev_ops = {
 	.ndo_del_slave = batadv_softif_slave_del,
 };
 
+static void batadv_get_drvinfo(struct net_device *dev,
+			       struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver));
+	strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version));
+	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
+	strlcpy(info->bus_info, "batman", sizeof(info->bus_info));
+}
+
+/* Inspired by drivers/net/ethernet/dlink/sundance.c:1702
+ * Declare each description string in struct.name[] to get fixed sized buffer
+ * and compile time checking for strings longer than ETH_GSTRING_LEN.
+ */
+static const struct {
+	const char name[ETH_GSTRING_LEN];
+} batadv_counters_strings[] = {
+	{ "tx" },
+	{ "tx_bytes" },
+	{ "tx_dropped" },
+	{ "rx" },
+	{ "rx_bytes" },
+	{ "forward" },
+	{ "forward_bytes" },
+	{ "mgmt_tx" },
+	{ "mgmt_tx_bytes" },
+	{ "mgmt_rx" },
+	{ "mgmt_rx_bytes" },
+	{ "frag_tx" },
+	{ "frag_tx_bytes" },
+	{ "frag_rx" },
+	{ "frag_rx_bytes" },
+	{ "frag_fwd" },
+	{ "frag_fwd_bytes" },
+	{ "tt_request_tx" },
+	{ "tt_request_rx" },
+	{ "tt_response_tx" },
+	{ "tt_response_rx" },
+	{ "tt_roam_adv_tx" },
+	{ "tt_roam_adv_rx" },
+#ifdef CONFIG_BATMAN_ADV_DAT
+	{ "dat_get_tx" },
+	{ "dat_get_rx" },
+	{ "dat_put_tx" },
+	{ "dat_put_rx" },
+	{ "dat_cached_reply_tx" },
+#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+	{ "nc_code" },
+	{ "nc_code_bytes" },
+	{ "nc_recode" },
+	{ "nc_recode_bytes" },
+	{ "nc_buffer" },
+	{ "nc_decode" },
+	{ "nc_decode_bytes" },
+	{ "nc_decode_failed" },
+	{ "nc_sniffed" },
+#endif
+};
+
+static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+	if (stringset == ETH_SS_STATS)
+		memcpy(data, batadv_counters_strings,
+		       sizeof(batadv_counters_strings));
+}
+
+static void batadv_get_ethtool_stats(struct net_device *dev,
+				     struct ethtool_stats *stats, u64 *data)
+{
+	struct batadv_priv *bat_priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < BATADV_CNT_NUM; i++)
+		data[i] = batadv_sum_counter(bat_priv, i);
+}
+
+static int batadv_get_sset_count(struct net_device *dev, int stringset)
+{
+	if (stringset == ETH_SS_STATS)
+		return BATADV_CNT_NUM;
+
+	return -EOPNOTSUPP;
+}
+
+static const struct ethtool_ops batadv_ethtool_ops = {
+	.get_drvinfo = batadv_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_strings = batadv_get_strings,
+	.get_ethtool_stats = batadv_get_ethtool_stats,
+	.get_sset_count = batadv_get_sset_count,
+};
+
 /**
  * batadv_softif_free - Deconstructor of batadv_soft_interface
  * @dev: Device to cleanup and remove
@@ -972,8 +1044,6 @@ static void batadv_softif_free(struct net_device *dev)
  */
 static void batadv_softif_init_early(struct net_device *dev)
 {
-	struct batadv_priv *priv = netdev_priv(dev);
-
 	ether_setup(dev);
 
 	dev->netdev_ops = &batadv_netdev_ops;
@@ -990,8 +1060,6 @@ static void batadv_softif_init_early(struct net_device *dev)
 	eth_hw_addr_random(dev);
 
 	dev->ethtool_ops = &batadv_ethtool_ops;
-
-	memset(priv, 0, sizeof(*priv));
 }
 
 struct net_device *batadv_softif_create(struct net *net, const char *name)
@@ -1084,118 +1152,3 @@ struct rtnl_link_ops batadv_link_ops __read_mostly = {
 	.setup		= batadv_softif_init_early,
 	.dellink	= batadv_softif_destroy_netlink,
 };
-
-/* ethtool */
-static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	cmd->supported = 0;
-	cmd->advertising = 0;
-	ethtool_cmd_speed_set(cmd, SPEED_10);
-	cmd->duplex = DUPLEX_FULL;
-	cmd->port = PORT_TP;
-	cmd->phy_address = 0;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->autoneg = AUTONEG_DISABLE;
-	cmd->maxtxpkt = 0;
-	cmd->maxrxpkt = 0;
-
-	return 0;
-}
-
-static void batadv_get_drvinfo(struct net_device *dev,
-			       struct ethtool_drvinfo *info)
-{
-	strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver));
-	strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version));
-	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
-	strlcpy(info->bus_info, "batman", sizeof(info->bus_info));
-}
-
-static u32 batadv_get_msglevel(struct net_device *dev)
-{
-	return -EOPNOTSUPP;
-}
-
-static void batadv_set_msglevel(struct net_device *dev, u32 value)
-{
-}
-
-static u32 batadv_get_link(struct net_device *dev)
-{
-	return 1;
-}
-
-/* Inspired by drivers/net/ethernet/dlink/sundance.c:1702
- * Declare each description string in struct.name[] to get fixed sized buffer
- * and compile time checking for strings longer than ETH_GSTRING_LEN.
- */
-static const struct {
-	const char name[ETH_GSTRING_LEN];
-} batadv_counters_strings[] = {
-	{ "tx" },
-	{ "tx_bytes" },
-	{ "tx_dropped" },
-	{ "rx" },
-	{ "rx_bytes" },
-	{ "forward" },
-	{ "forward_bytes" },
-	{ "mgmt_tx" },
-	{ "mgmt_tx_bytes" },
-	{ "mgmt_rx" },
-	{ "mgmt_rx_bytes" },
-	{ "frag_tx" },
-	{ "frag_tx_bytes" },
-	{ "frag_rx" },
-	{ "frag_rx_bytes" },
-	{ "frag_fwd" },
-	{ "frag_fwd_bytes" },
-	{ "tt_request_tx" },
-	{ "tt_request_rx" },
-	{ "tt_response_tx" },
-	{ "tt_response_rx" },
-	{ "tt_roam_adv_tx" },
-	{ "tt_roam_adv_rx" },
-#ifdef CONFIG_BATMAN_ADV_DAT
-	{ "dat_get_tx" },
-	{ "dat_get_rx" },
-	{ "dat_put_tx" },
-	{ "dat_put_rx" },
-	{ "dat_cached_reply_tx" },
-#endif
-#ifdef CONFIG_BATMAN_ADV_NC
-	{ "nc_code" },
-	{ "nc_code_bytes" },
-	{ "nc_recode" },
-	{ "nc_recode_bytes" },
-	{ "nc_buffer" },
-	{ "nc_decode" },
-	{ "nc_decode_bytes" },
-	{ "nc_decode_failed" },
-	{ "nc_sniffed" },
-#endif
-};
-
-static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data)
-{
-	if (stringset == ETH_SS_STATS)
-		memcpy(data, batadv_counters_strings,
-		       sizeof(batadv_counters_strings));
-}
-
-static void batadv_get_ethtool_stats(struct net_device *dev,
-				     struct ethtool_stats *stats, u64 *data)
-{
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	int i;
-
-	for (i = 0; i < BATADV_CNT_NUM; i++)
-		data[i] = batadv_sum_counter(bat_priv, i);
-}
-
-static int batadv_get_sset_count(struct net_device *dev, int stringset)
-{
-	if (stringset == ETH_SS_STATS)
-		return BATADV_CNT_NUM;
-
-	return -EOPNOTSUPP;
-}
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index c94ebdecdc3d..556f9a865ddf 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -873,8 +873,8 @@ static int batadv_tp_send(void *arg)
 		/* something went wrong during the preparation/transmission */
 		if (unlikely(err && err != BATADV_TP_REASON_CANT_SEND)) {
 			batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
-				   "Meter: batadv_tp_send() cannot send packets (%d)\n",
-				   err);
+				   "Meter: %s() cannot send packets (%d)\n",
+				   __func__, err);
 			/* ensure nobody else tries to stop the thread now */
 			if (atomic_dec_and_test(&tp_vars->sending))
 				tp_vars->reason = err;
@@ -979,7 +979,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
 	if (!tp_vars) {
 		spin_unlock_bh(&bat_priv->tp_list_lock);
 		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
-			   "Meter: batadv_tp_start cannot allocate list elements\n");
+			   "Meter: %s cannot allocate list elements\n",
+			   __func__);
 		batadv_tp_batctl_error_notify(BATADV_TP_REASON_MEMORY_ERROR,
 					      dst, bat_priv, session_cookie);
 		return;
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 6077a87d46f0..e75b4937b497 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -617,7 +617,7 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Deleting global tt entry %pM (vid: %d): %s\n",
 		   tt_global->common.addr,
-		   BATADV_PRINT_VID(tt_global->common.vid), message);
+		   batadv_print_vid(tt_global->common.vid), message);
 
 	batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt,
 			   batadv_choose_tt, &tt_global->common);
@@ -671,7 +671,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 		if (tt_local->common.flags & BATADV_TT_CLIENT_PENDING) {
 			batadv_dbg(BATADV_DBG_TT, bat_priv,
 				   "Re-adding pending client %pM (vid: %d)\n",
-				   addr, BATADV_PRINT_VID(vid));
+				   addr, batadv_print_vid(vid));
 			/* whatever the reason why the PENDING flag was set,
 			 * this is a client which was enqueued to be removed in
 			 * this orig_interval. Since it popped up again, the
@@ -684,7 +684,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 		if (tt_local->common.flags & BATADV_TT_CLIENT_ROAM) {
 			batadv_dbg(BATADV_DBG_TT, bat_priv,
 				   "Roaming client %pM (vid: %d) came back to its original location\n",
-				   addr, BATADV_PRINT_VID(vid));
+				   addr, batadv_print_vid(vid));
 			/* the ROAM flag is set because this client roamed away
 			 * and the node got a roaming_advertisement message. Now
 			 * that the client popped up again at its original
@@ -716,7 +716,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 	if (!vlan) {
 		net_ratelimited_function(batadv_info, soft_iface,
 					 "adding TT local entry %pM to non-existent VLAN %d\n",
-					 addr, BATADV_PRINT_VID(vid));
+					 addr, batadv_print_vid(vid));
 		kmem_cache_free(batadv_tl_cache, tt_local);
 		tt_local = NULL;
 		goto out;
@@ -724,7 +724,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n",
-		   addr, BATADV_PRINT_VID(vid),
+		   addr, batadv_print_vid(vid),
 		   (u8)atomic_read(&bat_priv->tt.vn));
 
 	ether_addr_copy(tt_local->common.addr, addr);
@@ -1097,7 +1097,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
 			seq_printf(seq,
 				   " * %pM %4i [%c%c%c%c%c%c] %3u.%03u   (%#.8x)\n",
 				   tt_common_entry->addr,
-				   BATADV_PRINT_VID(tt_common_entry->vid),
+				   batadv_print_vid(tt_common_entry->vid),
 				   ((tt_common_entry->flags &
 				     BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
 				   no_purge ? 'P' : '.',
@@ -1296,7 +1296,7 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv,
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Local tt entry (%pM, vid: %d) pending to be removed: %s\n",
 		   tt_local_entry->common.addr,
-		   BATADV_PRINT_VID(tt_local_entry->common.vid), message);
+		   batadv_print_vid(tt_local_entry->common.vid), message);
 }
 
 /**
@@ -1727,7 +1727,7 @@ add_orig_entry:
 
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Creating new global tt entry: %pM (vid: %d, via %pM)\n",
-		   common->addr, BATADV_PRINT_VID(common->vid),
+		   common->addr, batadv_print_vid(common->vid),
 		   orig_node->orig);
 	ret = true;
 
@@ -1835,7 +1835,7 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
 		if (!vlan) {
 			seq_printf(seq,
 				   " * Cannot retrieve VLAN %d for originator %pM\n",
-				   BATADV_PRINT_VID(tt_common_entry->vid),
+				   batadv_print_vid(tt_common_entry->vid),
 				   best_entry->orig_node->orig);
 			goto print_list;
 		}
@@ -1844,7 +1844,7 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
 		seq_printf(seq,
 			   " %c %pM %4i   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c%c]\n",
 			   '*', tt_global_entry->common.addr,
-			   BATADV_PRINT_VID(tt_global_entry->common.vid),
+			   batadv_print_vid(tt_global_entry->common.vid),
 			   best_entry->ttvn, best_entry->orig_node->orig,
 			   last_ttvn, vlan->tt.crc,
 			   ((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
@@ -1867,7 +1867,7 @@ print_list:
 		if (!vlan) {
 			seq_printf(seq,
 				   " + Cannot retrieve VLAN %d for originator %pM\n",
-				   BATADV_PRINT_VID(tt_common_entry->vid),
+				   batadv_print_vid(tt_common_entry->vid),
 				   orig_entry->orig_node->orig);
 			continue;
 		}
@@ -1876,7 +1876,7 @@ print_list:
 		seq_printf(seq,
 			   " %c %pM %4d   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c%c]\n",
 			   '+', tt_global_entry->common.addr,
-			   BATADV_PRINT_VID(tt_global_entry->common.vid),
+			   batadv_print_vid(tt_global_entry->common.vid),
 			   orig_entry->ttvn, orig_entry->orig_node->orig,
 			   last_ttvn, vlan->tt.crc,
 			   ((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
@@ -2213,7 +2213,7 @@ batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv,
 				   "Deleting %pM from global tt entry %pM (vid: %d): %s\n",
 				   orig_node->orig,
 				   tt_global_entry->common.addr,
-				   BATADV_PRINT_VID(vid), message);
+				   batadv_print_vid(vid), message);
 			_batadv_tt_global_del_orig_entry(tt_global_entry,
 							 orig_entry);
 		}
@@ -2253,12 +2253,13 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv,
 		/* its the last one, mark for roaming. */
 		tt_global_entry->common.flags |= BATADV_TT_CLIENT_ROAM;
 		tt_global_entry->roam_at = jiffies;
-	} else
+	} else {
 		/* there is another entry, we can simply delete this
 		 * one and can still use the other one.
 		 */
 		batadv_tt_global_del_orig_node(bat_priv, tt_global_entry,
 					       orig_node, message);
+	}
 }
 
 /**
@@ -2314,10 +2315,11 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv,
 		/* local entry exists, case 2: client roamed to us. */
 		batadv_tt_global_del_orig_list(tt_global_entry);
 		batadv_tt_global_free(bat_priv, tt_global_entry, message);
-	} else
+	} else {
 		/* no local entry exists, case 1: check for roaming */
 		batadv_tt_global_del_roaming(bat_priv, tt_global_entry,
 					     orig_node, message);
+	}
 
 out:
 	if (tt_global_entry)
@@ -2375,7 +2377,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 				batadv_dbg(BATADV_DBG_TT, bat_priv,
 					   "Deleting global tt entry %pM (vid: %d): %s\n",
 					   tt_global->common.addr,
-					   BATADV_PRINT_VID(vid), message);
+					   batadv_print_vid(vid), message);
 				hlist_del_rcu(&tt_common_entry->hash_entry);
 				batadv_tt_global_entry_put(tt_global);
 			}
@@ -2435,7 +2437,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv)
 			batadv_dbg(BATADV_DBG_TT, bat_priv,
 				   "Deleting global tt entry %pM (vid: %d): %s\n",
 				   tt_global->common.addr,
-				   BATADV_PRINT_VID(tt_global->common.vid),
+				   batadv_print_vid(tt_global->common.vid),
 				   msg);
 
 			hlist_del_rcu(&tt_common->hash_entry);
@@ -3650,7 +3652,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client,
 
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Sending ROAMING_ADV to %pM (client %pM, vid: %d)\n",
-		   orig_node->orig, client, BATADV_PRINT_VID(vid));
+		   orig_node->orig, client, batadv_print_vid(vid));
 
 	batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX);
 
@@ -3773,7 +3775,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 			batadv_dbg(BATADV_DBG_TT, bat_priv,
 				   "Deleting local tt entry (%pM, vid: %d): pending\n",
 				   tt_common->addr,
-				   BATADV_PRINT_VID(tt_common->vid));
+				   batadv_print_vid(tt_common->vid));
 
 			batadv_tt_local_size_dec(bat_priv, tt_common->vid);
 			hlist_del_rcu(&tt_common->hash_entry);
@@ -4017,7 +4019,7 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv,
 
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Added temporary global client (addr: %pM, vid: %d, orig: %pM)\n",
-		   addr, BATADV_PRINT_VID(vid), orig_node->orig);
+		   addr, batadv_print_vid(vid), orig_node->orig);
 	ret = true;
 out:
 	return ret;
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 66b25e410a41..ea43a6449247 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1000,7 +1000,6 @@ struct batadv_priv_bat_v {
  * struct batadv_priv - per mesh interface data
  * @mesh_state: current status of the mesh (inactive/active/deactivating)
  * @soft_iface: net device which holds this struct as private data
- * @stats: structure holding the data for the ndo_get_stats() call
  * @bat_counters: mesh internal traffic statistic counters (see batadv_counters)
  * @aggregated_ogms: bool indicating whether OGM aggregation is enabled
  * @bonding: bool indicating whether traffic bonding is enabled
@@ -1055,7 +1054,6 @@ struct batadv_priv_bat_v {
 struct batadv_priv {
 	atomic_t mesh_state;
 	struct net_device *soft_iface;
-	struct net_device_stats stats;
 	u64 __percpu *bat_counters; /* Per cpu counters */
 	atomic_t aggregated_ogms;
 	atomic_t bonding;
@@ -1377,9 +1375,11 @@ struct batadv_nc_packet {
  *  relevant to batman-adv in the skb->cb buffer in skbs.
  * @decoded: Marks a skb as decoded, which is checked when searching for coding
  *  opportunities in network-coding.c
+ * @num_bcasts: Counter for broadcast packet retransmissions
  */
 struct batadv_skb_cb {
 	bool decoded;
+	unsigned int num_bcasts;
 };
 
 /**
@@ -1392,7 +1392,7 @@ struct batadv_skb_cb {
  * @skb: bcast packet's skb buffer
  * @packet_len: size of aggregated OGM packet inside the skb buffer
  * @direct_link_flags: direct link flags for aggregated OGM packets
- * @num_packets: counter for bcast packet retransmission
+ * @num_packets: counter for aggregated OGMv1 packets
  * @delayed_work: work queue callback item for packet sending
  * @if_incoming: pointer to incoming hard-iface or primary iface if
  *  locally generated packet
@@ -1489,6 +1489,7 @@ struct batadv_algo_orig_ops {
 
 /**
  * struct batadv_algo_gw_ops - mesh algorithm callbacks (GW specific)
+ * @init_sel_class: initialize GW selection class (optional)
  * @store_sel_class: parse and stores a new GW selection class (optional)
  * @show_sel_class: prints the current GW selection class (optional)
  * @get_best_gw_node: select the best GW from the list of available nodes
@@ -1499,6 +1500,7 @@ struct batadv_algo_orig_ops {
  * @dump: dump gateways to a netlink socket (optional)
  */
 struct batadv_algo_gw_ops {
+	void (*init_sel_class)(struct batadv_priv *bat_priv);
 	ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff,
 				   size_t count);
 	ssize_t (*show_sel_class)(struct batadv_priv *bat_priv, char *buff);
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index d491529332f4..608959989f8e 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -20,6 +20,7 @@
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/addrconf.h>
+#include <net/pkt_sched.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -38,7 +39,6 @@ struct skb_cb {
 	struct in6_addr addr;
 	struct in6_addr gw;
 	struct l2cap_chan *chan;
-	int status;
 };
 #define lowpan_cb(skb) ((struct skb_cb *)((skb)->cb))
 
@@ -64,7 +64,7 @@ struct lowpan_peer {
 	struct l2cap_chan *chan;
 
 	/* peer addresses in various formats */
-	unsigned char eui64_addr[EUI64_ADDR_LEN];
+	unsigned char lladdr[ETH_ALEN];
 	struct in6_addr peer_addr;
 };
 
@@ -270,28 +270,20 @@ static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev)
 }
 
 static int iphc_decompress(struct sk_buff *skb, struct net_device *netdev,
-			   struct l2cap_chan *chan)
+			   struct lowpan_peer *peer)
 {
-	const u8 *saddr, *daddr;
+	const u8 *saddr;
 	struct lowpan_btle_dev *dev;
-	struct lowpan_peer *peer;
 
 	dev = lowpan_btle_dev(netdev);
 
-	rcu_read_lock();
-	peer = __peer_lookup_chan(dev, chan);
-	rcu_read_unlock();
-	if (!peer)
-		return -EINVAL;
-
-	saddr = peer->eui64_addr;
-	daddr = dev->netdev->dev_addr;
+	saddr = peer->lladdr;
 
-	return lowpan_header_decompress(skb, netdev, daddr, saddr);
+	return lowpan_header_decompress(skb, netdev, netdev->dev_addr, saddr);
 }
 
 static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
-		    struct l2cap_chan *chan)
+		    struct lowpan_peer *peer)
 {
 	struct sk_buff *local_skb;
 	int ret;
@@ -344,8 +336,9 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 
 		local_skb->dev = dev;
 
-		ret = iphc_decompress(local_skb, dev, chan);
+		ret = iphc_decompress(local_skb, dev, peer);
 		if (ret < 0) {
+			BT_DBG("iphc_decompress failed: %d", ret);
 			kfree_skb(local_skb);
 			goto drop;
 		}
@@ -365,6 +358,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 		consume_skb(local_skb);
 		consume_skb(skb);
 	} else {
+		BT_DBG("unknown packet type");
 		goto drop;
 	}
 
@@ -390,7 +384,7 @@ static int chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 	if (!dev || !dev->netdev)
 		return -ENOENT;
 
-	err = recv_pkt(skb, dev->netdev, chan);
+	err = recv_pkt(skb, dev->netdev, peer);
 	if (err) {
 		BT_DBG("recv pkt %d", err);
 		err = -EAGAIN;
@@ -399,37 +393,6 @@ static int chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 	return err;
 }
 
-static u8 get_addr_type_from_eui64(u8 byte)
-{
-	/* Is universal(0) or local(1) bit */
-	return ((byte & 0x02) ? BDADDR_LE_RANDOM : BDADDR_LE_PUBLIC);
-}
-
-static void copy_to_bdaddr(struct in6_addr *ip6_daddr, bdaddr_t *addr)
-{
-	u8 *eui64 = ip6_daddr->s6_addr + 8;
-
-	addr->b[0] = eui64[7];
-	addr->b[1] = eui64[6];
-	addr->b[2] = eui64[5];
-	addr->b[3] = eui64[2];
-	addr->b[4] = eui64[1];
-	addr->b[5] = eui64[0];
-}
-
-static void convert_dest_bdaddr(struct in6_addr *ip6_daddr,
-				bdaddr_t *addr, u8 *addr_type)
-{
-	copy_to_bdaddr(ip6_daddr, addr);
-
-	/* We need to toggle the U/L bit that we got from IPv6 address
-	 * so that we get the proper address and type of the BD address.
-	 */
-	addr->b[5] ^= 0x02;
-
-	*addr_type = get_addr_type_from_eui64(addr->b[5]);
-}
-
 static int setup_header(struct sk_buff *skb, struct net_device *netdev,
 			bdaddr_t *peer_addr, u8 *peer_addr_type)
 {
@@ -437,8 +400,7 @@ static int setup_header(struct sk_buff *skb, struct net_device *netdev,
 	struct ipv6hdr *hdr;
 	struct lowpan_btle_dev *dev;
 	struct lowpan_peer *peer;
-	bdaddr_t addr, *any = BDADDR_ANY;
-	u8 *daddr = any->b;
+	u8 *daddr;
 	int err, status = 0;
 
 	hdr = ipv6_hdr(skb);
@@ -449,34 +411,24 @@ static int setup_header(struct sk_buff *skb, struct net_device *netdev,
 
 	if (ipv6_addr_is_multicast(&ipv6_daddr)) {
 		lowpan_cb(skb)->chan = NULL;
+		daddr = NULL;
 	} else {
-		u8 addr_type;
+		BT_DBG("dest IP %pI6c", &ipv6_daddr);
 
-		/* Get destination BT device from skb.
-		 * If there is no such peer then discard the packet.
+		/* The packet might be sent to 6lowpan interface
+		 * because of routing (either via default route
+		 * or user set route) so get peer according to
+		 * the destination address.
 		 */
-		convert_dest_bdaddr(&ipv6_daddr, &addr, &addr_type);
-
-		BT_DBG("dest addr %pMR type %d IP %pI6c", &addr,
-		       addr_type, &ipv6_daddr);
-
-		peer = peer_lookup_ba(dev, &addr, addr_type);
+		peer = peer_lookup_dst(dev, &ipv6_daddr, skb);
 		if (!peer) {
-			/* The packet might be sent to 6lowpan interface
-			 * because of routing (either via default route
-			 * or user set route) so get peer according to
-			 * the destination address.
-			 */
-			peer = peer_lookup_dst(dev, &ipv6_daddr, skb);
-			if (!peer) {
-				BT_DBG("no such peer %pMR found", &addr);
-				return -ENOENT;
-			}
+			BT_DBG("no such peer");
+			return -ENOENT;
 		}
 
-		daddr = peer->eui64_addr;
-		*peer_addr = addr;
-		*peer_addr_type = addr_type;
+		daddr = peer->lladdr;
+		*peer_addr = peer->chan->dst;
+		*peer_addr_type = peer->chan->dst_type;
 		lowpan_cb(skb)->chan = peer->chan;
 
 		status = 1;
@@ -527,15 +479,8 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 		return 0;
 	}
 
-	if (!err)
-		err = lowpan_cb(skb)->status;
-
-	if (err < 0) {
-		if (err == -EAGAIN)
-			netdev->stats.tx_dropped++;
-		else
-			netdev->stats.tx_errors++;
-	}
+	if (err < 0)
+		netdev->stats.tx_errors++;
 
 	return err;
 }
@@ -647,9 +592,9 @@ static void netdev_setup(struct net_device *dev)
 {
 	dev->hard_header_len	= 0;
 	dev->needed_tailroom	= 0;
-	dev->flags		= IFF_RUNNING | IFF_POINTOPOINT |
-				  IFF_MULTICAST;
+	dev->flags		= IFF_RUNNING | IFF_MULTICAST;
 	dev->watchdog_timeo	= 0;
+	dev->tx_queue_len	= DEFAULT_TX_QUEUE_LEN;
 
 	dev->netdev_ops		= &netdev_ops;
 	dev->header_ops		= &header_ops;
@@ -660,34 +605,6 @@ static struct device_type bt_type = {
 	.name	= "bluetooth",
 };
 
-static void set_addr(u8 *eui, u8 *addr, u8 addr_type)
-{
-	/* addr is the BT address in little-endian format */
-	eui[0] = addr[5];
-	eui[1] = addr[4];
-	eui[2] = addr[3];
-	eui[3] = 0xFF;
-	eui[4] = 0xFE;
-	eui[5] = addr[2];
-	eui[6] = addr[1];
-	eui[7] = addr[0];
-
-	/* Universal/local bit set, BT 6lowpan draft ch. 3.2.1 */
-	if (addr_type == BDADDR_LE_PUBLIC)
-		eui[0] &= ~0x02;
-	else
-		eui[0] |= 0x02;
-
-	BT_DBG("type %d addr %*phC", addr_type, 8, eui);
-}
-
-static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr,
-		         u8 addr_type)
-{
-	netdev->addr_assign_type = NET_ADDR_PERM;
-	set_addr(netdev->dev_addr, addr->b, addr_type);
-}
-
 static void ifup(struct net_device *netdev)
 {
 	int err;
@@ -746,16 +663,9 @@ static struct l2cap_chan *chan_create(void)
 	return chan;
 }
 
-static void set_ip_addr_bits(u8 addr_type, u8 *addr)
-{
-	if (addr_type == BDADDR_LE_PUBLIC)
-		*addr |= 0x02;
-	else
-		*addr &= ~0x02;
-}
-
 static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan,
-					struct lowpan_btle_dev *dev)
+					struct lowpan_btle_dev *dev,
+					bool new_netdev)
 {
 	struct lowpan_peer *peer;
 
@@ -766,19 +676,9 @@ static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan,
 	peer->chan = chan;
 	memset(&peer->peer_addr, 0, sizeof(struct in6_addr));
 
-	/* RFC 2464 ch. 5 */
-	peer->peer_addr.s6_addr[0] = 0xFE;
-	peer->peer_addr.s6_addr[1] = 0x80;
-	set_addr((u8 *)&peer->peer_addr.s6_addr + 8, chan->dst.b,
-		 chan->dst_type);
-
-	memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8,
-	       EUI64_ADDR_LEN);
+	baswap((void *)peer->lladdr, &chan->dst);
 
-	/* IPv6 address needs to have the U/L bit set properly so toggle
-	 * it back here.
-	 */
-	set_ip_addr_bits(chan->dst_type, (u8 *)&peer->peer_addr.s6_addr + 8);
+	lowpan_iphc_uncompress_eui48_lladdr(&peer->peer_addr, peer->lladdr);
 
 	spin_lock(&devices_lock);
 	INIT_LIST_HEAD(&peer->list);
@@ -786,7 +686,8 @@ static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan,
 	spin_unlock(&devices_lock);
 
 	/* Notifying peers about us needs to be done without locks held */
-	INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers);
+	if (new_netdev)
+		INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers);
 	schedule_delayed_work(&dev->notify_peers, msecs_to_jiffies(100));
 
 	return peer->chan;
@@ -803,7 +704,8 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_btle_dev **dev)
 	if (!netdev)
 		return -ENOMEM;
 
-	set_dev_addr(netdev, &chan->src, chan->src_type);
+	netdev->addr_assign_type = NET_ADDR_PERM;
+	baswap((void *)netdev->dev_addr, &chan->src);
 
 	netdev->netdev_ops = &netdev_ops;
 	SET_NETDEV_DEV(netdev, &chan->conn->hcon->hdev->dev);
@@ -843,6 +745,7 @@ out:
 static inline void chan_ready_cb(struct l2cap_chan *chan)
 {
 	struct lowpan_btle_dev *dev;
+	bool new_netdev = false;
 
 	dev = lookup_dev(chan->conn);
 
@@ -853,12 +756,13 @@ static inline void chan_ready_cb(struct l2cap_chan *chan)
 			l2cap_chan_del(chan, -ENOENT);
 			return;
 		}
+		new_netdev = true;
 	}
 
 	if (!try_module_get(THIS_MODULE))
 		return;
 
-	add_peer_chan(chan, dev);
+	add_peer_chan(chan, dev, new_netdev);
 	ifup(dev->netdev);
 }
 
@@ -964,26 +868,28 @@ static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan,
 
 static void chan_suspend_cb(struct l2cap_chan *chan)
 {
-	struct sk_buff *skb = chan->data;
+	struct lowpan_btle_dev *dev;
 
-	BT_DBG("chan %p conn %p skb %p", chan, chan->conn, skb);
+	BT_DBG("chan %p suspend", chan);
 
-	if (!skb)
+	dev = lookup_dev(chan->conn);
+	if (!dev || !dev->netdev)
 		return;
 
-	lowpan_cb(skb)->status = -EAGAIN;
+	netif_stop_queue(dev->netdev);
 }
 
 static void chan_resume_cb(struct l2cap_chan *chan)
 {
-	struct sk_buff *skb = chan->data;
+	struct lowpan_btle_dev *dev;
 
-	BT_DBG("chan %p conn %p skb %p", chan, chan->conn, skb);
+	BT_DBG("chan %p resume", chan);
 
-	if (!skb)
+	dev = lookup_dev(chan->conn);
+	if (!dev || !dev->netdev)
 		return;
 
-	lowpan_cb(skb)->status = 0;
+	netif_wake_queue(dev->netdev);
 }
 
 static long chan_get_sndtimeo_cb(struct l2cap_chan *chan)
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index 06c31b9a68b0..68f951b3e85a 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -13,6 +13,7 @@ menuconfig BT
 	select CRYPTO_CMAC
 	select CRYPTO_ECB
 	select CRYPTO_SHA256
+	select CRYPTO_ECDH
 	help
 	  Bluetooth is low-cost, low-power, short-range wireless technology.
 	  It was designed as a replacement for cables and other short-range
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index 4bfaa19a5573..5d0a113e2e40 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -13,7 +13,7 @@ bluetooth_6lowpan-y := 6lowpan.o
 
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \
 	hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o lib.o \
-	ecc.o hci_request.o mgmt_util.o
+	ecdh_helper.o hci_request.o mgmt_util.o
 
 bluetooth-$(CONFIG_BT_BREDR) += sco.o
 bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 69e1f7d362a8..42d0997e2fbb 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -159,12 +159,17 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk)
 	BT_DBG("parent %p, sk %p", parent, sk);
 
 	sock_hold(sk);
+	lock_sock(sk);
 	list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q);
 	bt_sk(sk)->parent = parent;
+	release_sock(sk);
 	parent->sk_ack_backlog++;
 }
 EXPORT_SYMBOL(bt_accept_enqueue);
 
+/* Calling function must hold the sk lock.
+ * bt_sk(sk)->parent must be non-NULL meaning sk is in the parent list.
+ */
 void bt_accept_unlink(struct sock *sk)
 {
 	BT_DBG("sk %p state %d", sk, sk->sk_state);
@@ -183,11 +188,32 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock)
 
 	BT_DBG("parent %p", parent);
 
+restart:
 	list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) {
 		sk = (struct sock *)s;
 
+		/* Prevent early freeing of sk due to unlink and sock_kill */
+		sock_hold(sk);
 		lock_sock(sk);
 
+		/* Check sk has not already been unlinked via
+		 * bt_accept_unlink() due to serialisation caused by sk locking
+		 */
+		if (!bt_sk(sk)->parent) {
+			BT_DBG("sk %p, already unlinked", sk);
+			release_sock(sk);
+			sock_put(sk);
+
+			/* Restart the loop as sk is no longer in the list
+			 * and also avoid a potential infinite loop because
+			 * list_for_each_entry_safe() is not thread safe.
+			 */
+			goto restart;
+		}
+
+		/* sk is safely in the parent list so reduce reference count */
+		sock_put(sk);
+
 		/* FIXME: Is this check still needed */
 		if (sk->sk_state == BT_CLOSED) {
 			bt_accept_unlink(sk);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 02a4ccc04e1e..ebcab5bbadd7 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -263,7 +263,7 @@ void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle)
 	struct hci_cp_read_local_amp_assoc cp;
 	struct amp_assoc *loc_assoc = &hdev->loc_assoc;
 	struct hci_request req;
-	int err = 0;
+	int err;
 
 	BT_DBG("%s handle %d", hdev->name, phy_handle);
 
@@ -282,7 +282,7 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr)
 {
 	struct hci_cp_read_local_amp_assoc cp;
 	struct hci_request req;
-	int err = 0;
+	int err;
 
 	memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc));
 	memset(&cp, 0, sizeof(cp));
@@ -292,7 +292,7 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr)
 	set_bit(READ_LOC_AMP_ASSOC, &mgr->state);
 	hci_req_init(&req, hdev);
 	hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
-	hci_req_run_skb(&req, read_local_amp_assoc_complete);
+	err = hci_req_run_skb(&req, read_local_amp_assoc_complete);
 	if (err < 0)
 		a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID);
 }
@@ -303,7 +303,7 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
 	struct hci_cp_read_local_amp_assoc cp;
 	struct amp_mgr *mgr = hcon->amp_mgr;
 	struct hci_request req;
-	int err = 0;
+	int err;
 
 	cp.phy_handle = hcon->handle;
 	cp.len_so_far = cpu_to_le16(0);
@@ -314,7 +314,7 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
 	/* Read Local AMP Assoc final link information data */
 	hci_req_init(&req, hdev);
 	hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
-	hci_req_run_skb(&req, read_local_amp_assoc_complete);
+	err = hci_req_run_skb(&req, read_local_amp_assoc_complete);
 	if (err < 0)
 		a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID);
 }
diff --git a/net/bluetooth/ecc.c b/net/bluetooth/ecc.c
deleted file mode 100644
index e1709f8467ac..000000000000
--- a/net/bluetooth/ecc.c
+++ /dev/null
@@ -1,816 +0,0 @@
-/*
- * Copyright (c) 2013, Kenneth MacKay
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *  * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- *  * Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/random.h>
-
-#include "ecc.h"
-
-/* 256-bit curve */
-#define ECC_BYTES 32
-
-#define MAX_TRIES 16
-
-/* Number of u64's needed */
-#define NUM_ECC_DIGITS (ECC_BYTES / 8)
-
-struct ecc_point {
-	u64 x[NUM_ECC_DIGITS];
-	u64 y[NUM_ECC_DIGITS];
-};
-
-typedef struct {
-	u64 m_low;
-	u64 m_high;
-} uint128_t;
-
-#define CURVE_P_32 {	0xFFFFFFFFFFFFFFFFull, 0x00000000FFFFFFFFull, \
-			0x0000000000000000ull, 0xFFFFFFFF00000001ull }
-
-#define CURVE_G_32 { \
-		{	0xF4A13945D898C296ull, 0x77037D812DEB33A0ull,	\
-			0xF8BCE6E563A440F2ull, 0x6B17D1F2E12C4247ull }, \
-		{	0xCBB6406837BF51F5ull, 0x2BCE33576B315ECEull,	\
-			0x8EE7EB4A7C0F9E16ull, 0x4FE342E2FE1A7F9Bull }	\
-}
-
-#define CURVE_N_32 {	0xF3B9CAC2FC632551ull, 0xBCE6FAADA7179E84ull,	\
-			0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFF00000000ull }
-
-static u64 curve_p[NUM_ECC_DIGITS] = CURVE_P_32;
-static struct ecc_point curve_g = CURVE_G_32;
-static u64 curve_n[NUM_ECC_DIGITS] = CURVE_N_32;
-
-static void vli_clear(u64 *vli)
-{
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++)
-		vli[i] = 0;
-}
-
-/* Returns true if vli == 0, false otherwise. */
-static bool vli_is_zero(const u64 *vli)
-{
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++) {
-		if (vli[i])
-			return false;
-	}
-
-	return true;
-}
-
-/* Returns nonzero if bit bit of vli is set. */
-static u64 vli_test_bit(const u64 *vli, unsigned int bit)
-{
-	return (vli[bit / 64] & ((u64) 1 << (bit % 64)));
-}
-
-/* Counts the number of 64-bit "digits" in vli. */
-static unsigned int vli_num_digits(const u64 *vli)
-{
-	int i;
-
-	/* Search from the end until we find a non-zero digit.
-	 * We do it in reverse because we expect that most digits will
-	 * be nonzero.
-	 */
-	for (i = NUM_ECC_DIGITS - 1; i >= 0 && vli[i] == 0; i--);
-
-	return (i + 1);
-}
-
-/* Counts the number of bits required for vli. */
-static unsigned int vli_num_bits(const u64 *vli)
-{
-	unsigned int i, num_digits;
-	u64 digit;
-
-	num_digits = vli_num_digits(vli);
-	if (num_digits == 0)
-		return 0;
-
-	digit = vli[num_digits - 1];
-	for (i = 0; digit; i++)
-		digit >>= 1;
-
-	return ((num_digits - 1) * 64 + i);
-}
-
-/* Sets dest = src. */
-static void vli_set(u64 *dest, const u64 *src)
-{
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++)
-		dest[i] = src[i];
-}
-
-/* Returns sign of left - right. */
-static int vli_cmp(const u64 *left, const u64 *right)
-{
-    int i;
-
-    for (i = NUM_ECC_DIGITS - 1; i >= 0; i--) {
-	    if (left[i] > right[i])
-		    return 1;
-	    else if (left[i] < right[i])
-		    return -1;
-    }
-
-    return 0;
-}
-
-/* Computes result = in << c, returning carry. Can modify in place
- * (if result == in). 0 < shift < 64.
- */
-static u64 vli_lshift(u64 *result, const u64 *in,
-			   unsigned int shift)
-{
-	u64 carry = 0;
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++) {
-		u64 temp = in[i];
-
-		result[i] = (temp << shift) | carry;
-		carry = temp >> (64 - shift);
-	}
-
-	return carry;
-}
-
-/* Computes vli = vli >> 1. */
-static void vli_rshift1(u64 *vli)
-{
-	u64 *end = vli;
-	u64 carry = 0;
-
-	vli += NUM_ECC_DIGITS;
-
-	while (vli-- > end) {
-		u64 temp = *vli;
-		*vli = (temp >> 1) | carry;
-		carry = temp << 63;
-	}
-}
-
-/* Computes result = left + right, returning carry. Can modify in place. */
-static u64 vli_add(u64 *result, const u64 *left,
-			const u64 *right)
-{
-	u64 carry = 0;
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++) {
-		u64 sum;
-
-		sum = left[i] + right[i] + carry;
-		if (sum != left[i])
-			carry = (sum < left[i]);
-
-		result[i] = sum;
-	}
-
-	return carry;
-}
-
-/* Computes result = left - right, returning borrow. Can modify in place. */
-static u64 vli_sub(u64 *result, const u64 *left, const u64 *right)
-{
-	u64 borrow = 0;
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++) {
-		u64 diff;
-
-		diff = left[i] - right[i] - borrow;
-		if (diff != left[i])
-			borrow = (diff > left[i]);
-
-		result[i] = diff;
-	}
-
-	return borrow;
-}
-
-static uint128_t mul_64_64(u64 left, u64 right)
-{
-	u64 a0 = left & 0xffffffffull;
-	u64 a1 = left >> 32;
-	u64 b0 = right & 0xffffffffull;
-	u64 b1 = right >> 32;
-	u64 m0 = a0 * b0;
-	u64 m1 = a0 * b1;
-	u64 m2 = a1 * b0;
-	u64 m3 = a1 * b1;
-	uint128_t result;
-
-	m2 += (m0 >> 32);
-	m2 += m1;
-
-	/* Overflow */
-	if (m2 < m1)
-		m3 += 0x100000000ull;
-
-	result.m_low = (m0 & 0xffffffffull) | (m2 << 32);
-	result.m_high = m3 + (m2 >> 32);
-
-	return result;
-}
-
-static uint128_t add_128_128(uint128_t a, uint128_t b)
-{
-	uint128_t result;
-
-	result.m_low = a.m_low + b.m_low;
-	result.m_high = a.m_high + b.m_high + (result.m_low < a.m_low);
-
-	return result;
-}
-
-static void vli_mult(u64 *result, const u64 *left, const u64 *right)
-{
-	uint128_t r01 = { 0, 0 };
-	u64 r2 = 0;
-	unsigned int i, k;
-
-	/* Compute each digit of result in sequence, maintaining the
-	 * carries.
-	 */
-	for (k = 0; k < NUM_ECC_DIGITS * 2 - 1; k++) {
-		unsigned int min;
-
-		if (k < NUM_ECC_DIGITS)
-			min = 0;
-		else
-			min = (k + 1) - NUM_ECC_DIGITS;
-
-		for (i = min; i <= k && i < NUM_ECC_DIGITS; i++) {
-			uint128_t product;
-
-			product = mul_64_64(left[i], right[k - i]);
-
-			r01 = add_128_128(r01, product);
-			r2 += (r01.m_high < product.m_high);
-		}
-
-		result[k] = r01.m_low;
-		r01.m_low = r01.m_high;
-		r01.m_high = r2;
-		r2 = 0;
-	}
-
-	result[NUM_ECC_DIGITS * 2 - 1] = r01.m_low;
-}
-
-static void vli_square(u64 *result, const u64 *left)
-{
-	uint128_t r01 = { 0, 0 };
-	u64 r2 = 0;
-	int i, k;
-
-	for (k = 0; k < NUM_ECC_DIGITS * 2 - 1; k++) {
-		unsigned int min;
-
-		if (k < NUM_ECC_DIGITS)
-			min = 0;
-		else
-			min = (k + 1) - NUM_ECC_DIGITS;
-
-		for (i = min; i <= k && i <= k - i; i++) {
-			uint128_t product;
-
-			product = mul_64_64(left[i], left[k - i]);
-
-			if (i < k - i) {
-				r2 += product.m_high >> 63;
-				product.m_high = (product.m_high << 1) |
-						 (product.m_low >> 63);
-				product.m_low <<= 1;
-			}
-
-			r01 = add_128_128(r01, product);
-			r2 += (r01.m_high < product.m_high);
-		}
-
-		result[k] = r01.m_low;
-		r01.m_low = r01.m_high;
-		r01.m_high = r2;
-		r2 = 0;
-	}
-
-	result[NUM_ECC_DIGITS * 2 - 1] = r01.m_low;
-}
-
-/* Computes result = (left + right) % mod.
- * Assumes that left < mod and right < mod, result != mod.
- */
-static void vli_mod_add(u64 *result, const u64 *left, const u64 *right,
-			const u64 *mod)
-{
-	u64 carry;
-
-	carry = vli_add(result, left, right);
-
-	/* result > mod (result = mod + remainder), so subtract mod to
-	 * get remainder.
-	 */
-	if (carry || vli_cmp(result, mod) >= 0)
-		vli_sub(result, result, mod);
-}
-
-/* Computes result = (left - right) % mod.
- * Assumes that left < mod and right < mod, result != mod.
- */
-static void vli_mod_sub(u64 *result, const u64 *left, const u64 *right,
-			const u64 *mod)
-{
-	u64 borrow = vli_sub(result, left, right);
-
-	/* In this case, p_result == -diff == (max int) - diff.
-	 * Since -x % d == d - x, we can get the correct result from
-	 * result + mod (with overflow).
-	 */
-	if (borrow)
-		vli_add(result, result, mod);
-}
-
-/* Computes result = product % curve_p
-   from http://www.nsa.gov/ia/_files/nist-routines.pdf */
-static void vli_mmod_fast(u64 *result, const u64 *product)
-{
-	u64 tmp[NUM_ECC_DIGITS];
-	int carry;
-
-	/* t */
-	vli_set(result, product);
-
-	/* s1 */
-	tmp[0] = 0;
-	tmp[1] = product[5] & 0xffffffff00000000ull;
-	tmp[2] = product[6];
-	tmp[3] = product[7];
-	carry = vli_lshift(tmp, tmp, 1);
-	carry += vli_add(result, result, tmp);
-
-	/* s2 */
-	tmp[1] = product[6] << 32;
-	tmp[2] = (product[6] >> 32) | (product[7] << 32);
-	tmp[3] = product[7] >> 32;
-	carry += vli_lshift(tmp, tmp, 1);
-	carry += vli_add(result, result, tmp);
-
-	/* s3 */
-	tmp[0] = product[4];
-	tmp[1] = product[5] & 0xffffffff;
-	tmp[2] = 0;
-	tmp[3] = product[7];
-	carry += vli_add(result, result, tmp);
-
-	/* s4 */
-	tmp[0] = (product[4] >> 32) | (product[5] << 32);
-	tmp[1] = (product[5] >> 32) | (product[6] & 0xffffffff00000000ull);
-	tmp[2] = product[7];
-	tmp[3] = (product[6] >> 32) | (product[4] << 32);
-	carry += vli_add(result, result, tmp);
-
-	/* d1 */
-	tmp[0] = (product[5] >> 32) | (product[6] << 32);
-	tmp[1] = (product[6] >> 32);
-	tmp[2] = 0;
-	tmp[3] = (product[4] & 0xffffffff) | (product[5] << 32);
-	carry -= vli_sub(result, result, tmp);
-
-	/* d2 */
-	tmp[0] = product[6];
-	tmp[1] = product[7];
-	tmp[2] = 0;
-	tmp[3] = (product[4] >> 32) | (product[5] & 0xffffffff00000000ull);
-	carry -= vli_sub(result, result, tmp);
-
-	/* d3 */
-	tmp[0] = (product[6] >> 32) | (product[7] << 32);
-	tmp[1] = (product[7] >> 32) | (product[4] << 32);
-	tmp[2] = (product[4] >> 32) | (product[5] << 32);
-	tmp[3] = (product[6] << 32);
-	carry -= vli_sub(result, result, tmp);
-
-	/* d4 */
-	tmp[0] = product[7];
-	tmp[1] = product[4] & 0xffffffff00000000ull;
-	tmp[2] = product[5];
-	tmp[3] = product[6] & 0xffffffff00000000ull;
-	carry -= vli_sub(result, result, tmp);
-
-	if (carry < 0) {
-		do {
-			carry += vli_add(result, result, curve_p);
-		} while (carry < 0);
-	} else {
-		while (carry || vli_cmp(curve_p, result) != 1)
-			carry -= vli_sub(result, result, curve_p);
-	}
-}
-
-/* Computes result = (left * right) % curve_p. */
-static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right)
-{
-	u64 product[2 * NUM_ECC_DIGITS];
-
-	vli_mult(product, left, right);
-	vli_mmod_fast(result, product);
-}
-
-/* Computes result = left^2 % curve_p. */
-static void vli_mod_square_fast(u64 *result, const u64 *left)
-{
-	u64 product[2 * NUM_ECC_DIGITS];
-
-	vli_square(product, left);
-	vli_mmod_fast(result, product);
-}
-
-#define EVEN(vli) (!(vli[0] & 1))
-/* Computes result = (1 / p_input) % mod. All VLIs are the same size.
- * See "From Euclid's GCD to Montgomery Multiplication to the Great Divide"
- * https://labs.oracle.com/techrep/2001/smli_tr-2001-95.pdf
- */
-static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod)
-{
-	u64 a[NUM_ECC_DIGITS], b[NUM_ECC_DIGITS];
-	u64 u[NUM_ECC_DIGITS], v[NUM_ECC_DIGITS];
-	u64 carry;
-	int cmp_result;
-
-	if (vli_is_zero(input)) {
-		vli_clear(result);
-		return;
-	}
-
-	vli_set(a, input);
-	vli_set(b, mod);
-	vli_clear(u);
-	u[0] = 1;
-	vli_clear(v);
-
-	while ((cmp_result = vli_cmp(a, b)) != 0) {
-		carry = 0;
-
-		if (EVEN(a)) {
-			vli_rshift1(a);
-
-			if (!EVEN(u))
-				carry = vli_add(u, u, mod);
-
-			vli_rshift1(u);
-			if (carry)
-				u[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
-		} else if (EVEN(b)) {
-			vli_rshift1(b);
-
-			if (!EVEN(v))
-				carry = vli_add(v, v, mod);
-
-			vli_rshift1(v);
-			if (carry)
-				v[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
-		} else if (cmp_result > 0) {
-			vli_sub(a, a, b);
-			vli_rshift1(a);
-
-			if (vli_cmp(u, v) < 0)
-				vli_add(u, u, mod);
-
-			vli_sub(u, u, v);
-			if (!EVEN(u))
-				carry = vli_add(u, u, mod);
-
-			vli_rshift1(u);
-			if (carry)
-				u[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
-		} else {
-			vli_sub(b, b, a);
-			vli_rshift1(b);
-
-			if (vli_cmp(v, u) < 0)
-				vli_add(v, v, mod);
-
-			vli_sub(v, v, u);
-			if (!EVEN(v))
-				carry = vli_add(v, v, mod);
-
-			vli_rshift1(v);
-			if (carry)
-				v[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
-		}
-	}
-
-	vli_set(result, u);
-}
-
-/* ------ Point operations ------ */
-
-/* Returns true if p_point is the point at infinity, false otherwise. */
-static bool ecc_point_is_zero(const struct ecc_point *point)
-{
-	return (vli_is_zero(point->x) && vli_is_zero(point->y));
-}
-
-/* Point multiplication algorithm using Montgomery's ladder with co-Z
- * coordinates. From http://eprint.iacr.org/2011/338.pdf
- */
-
-/* Double in place */
-static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1)
-{
-	/* t1 = x, t2 = y, t3 = z */
-	u64 t4[NUM_ECC_DIGITS];
-	u64 t5[NUM_ECC_DIGITS];
-
-	if (vli_is_zero(z1))
-		return;
-
-	vli_mod_square_fast(t4, y1);   /* t4 = y1^2 */
-	vli_mod_mult_fast(t5, x1, t4); /* t5 = x1*y1^2 = A */
-	vli_mod_square_fast(t4, t4);   /* t4 = y1^4 */
-	vli_mod_mult_fast(y1, y1, z1); /* t2 = y1*z1 = z3 */
-	vli_mod_square_fast(z1, z1);   /* t3 = z1^2 */
-
-	vli_mod_add(x1, x1, z1, curve_p); /* t1 = x1 + z1^2 */
-	vli_mod_add(z1, z1, z1, curve_p); /* t3 = 2*z1^2 */
-	vli_mod_sub(z1, x1, z1, curve_p); /* t3 = x1 - z1^2 */
-	vli_mod_mult_fast(x1, x1, z1);    /* t1 = x1^2 - z1^4 */
-
-	vli_mod_add(z1, x1, x1, curve_p); /* t3 = 2*(x1^2 - z1^4) */
-	vli_mod_add(x1, x1, z1, curve_p); /* t1 = 3*(x1^2 - z1^4) */
-	if (vli_test_bit(x1, 0)) {
-		u64 carry = vli_add(x1, x1, curve_p);
-		vli_rshift1(x1);
-		x1[NUM_ECC_DIGITS - 1] |= carry << 63;
-	} else {
-		vli_rshift1(x1);
-	}
-	/* t1 = 3/2*(x1^2 - z1^4) = B */
-
-	vli_mod_square_fast(z1, x1);      /* t3 = B^2 */
-	vli_mod_sub(z1, z1, t5, curve_p); /* t3 = B^2 - A */
-	vli_mod_sub(z1, z1, t5, curve_p); /* t3 = B^2 - 2A = x3 */
-	vli_mod_sub(t5, t5, z1, curve_p); /* t5 = A - x3 */
-	vli_mod_mult_fast(x1, x1, t5);    /* t1 = B * (A - x3) */
-	vli_mod_sub(t4, x1, t4, curve_p); /* t4 = B * (A - x3) - y1^4 = y3 */
-
-	vli_set(x1, z1);
-	vli_set(z1, y1);
-	vli_set(y1, t4);
-}
-
-/* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */
-static void apply_z(u64 *x1, u64 *y1, u64 *z)
-{
-	u64 t1[NUM_ECC_DIGITS];
-
-	vli_mod_square_fast(t1, z);    /* z^2 */
-	vli_mod_mult_fast(x1, x1, t1); /* x1 * z^2 */
-	vli_mod_mult_fast(t1, t1, z);  /* z^3 */
-	vli_mod_mult_fast(y1, y1, t1); /* y1 * z^3 */
-}
-
-/* P = (x1, y1) => 2P, (x2, y2) => P' */
-static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
-				u64 *p_initial_z)
-{
-	u64 z[NUM_ECC_DIGITS];
-
-	vli_set(x2, x1);
-	vli_set(y2, y1);
-
-	vli_clear(z);
-	z[0] = 1;
-
-	if (p_initial_z)
-		vli_set(z, p_initial_z);
-
-	apply_z(x1, y1, z);
-
-	ecc_point_double_jacobian(x1, y1, z);
-
-	apply_z(x2, y2, z);
-}
-
-/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
- * Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3)
- * or P => P', Q => P + Q
- */
-static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2)
-{
-	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
-	u64 t5[NUM_ECC_DIGITS];
-
-	vli_mod_sub(t5, x2, x1, curve_p); /* t5 = x2 - x1 */
-	vli_mod_square_fast(t5, t5);      /* t5 = (x2 - x1)^2 = A */
-	vli_mod_mult_fast(x1, x1, t5);    /* t1 = x1*A = B */
-	vli_mod_mult_fast(x2, x2, t5);    /* t3 = x2*A = C */
-	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y2 - y1 */
-	vli_mod_square_fast(t5, y2);      /* t5 = (y2 - y1)^2 = D */
-
-	vli_mod_sub(t5, t5, x1, curve_p); /* t5 = D - B */
-	vli_mod_sub(t5, t5, x2, curve_p); /* t5 = D - B - C = x3 */
-	vli_mod_sub(x2, x2, x1, curve_p); /* t3 = C - B */
-	vli_mod_mult_fast(y1, y1, x2);    /* t2 = y1*(C - B) */
-	vli_mod_sub(x2, x1, t5, curve_p); /* t3 = B - x3 */
-	vli_mod_mult_fast(y2, y2, x2);    /* t4 = (y2 - y1)*(B - x3) */
-	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y3 */
-
-	vli_set(x2, t5);
-}
-
-/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
- * Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3)
- * or P => P - Q, Q => P + Q
- */
-static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2)
-{
-	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
-	u64 t5[NUM_ECC_DIGITS];
-	u64 t6[NUM_ECC_DIGITS];
-	u64 t7[NUM_ECC_DIGITS];
-
-	vli_mod_sub(t5, x2, x1, curve_p); /* t5 = x2 - x1 */
-	vli_mod_square_fast(t5, t5);      /* t5 = (x2 - x1)^2 = A */
-	vli_mod_mult_fast(x1, x1, t5);    /* t1 = x1*A = B */
-	vli_mod_mult_fast(x2, x2, t5);    /* t3 = x2*A = C */
-	vli_mod_add(t5, y2, y1, curve_p); /* t4 = y2 + y1 */
-	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y2 - y1 */
-
-	vli_mod_sub(t6, x2, x1, curve_p); /* t6 = C - B */
-	vli_mod_mult_fast(y1, y1, t6);    /* t2 = y1 * (C - B) */
-	vli_mod_add(t6, x1, x2, curve_p); /* t6 = B + C */
-	vli_mod_square_fast(x2, y2);      /* t3 = (y2 - y1)^2 */
-	vli_mod_sub(x2, x2, t6, curve_p); /* t3 = x3 */
-
-	vli_mod_sub(t7, x1, x2, curve_p); /* t7 = B - x3 */
-	vli_mod_mult_fast(y2, y2, t7);    /* t4 = (y2 - y1)*(B - x3) */
-	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y3 */
-
-	vli_mod_square_fast(t7, t5);      /* t7 = (y2 + y1)^2 = F */
-	vli_mod_sub(t7, t7, t6, curve_p); /* t7 = x3' */
-	vli_mod_sub(t6, t7, x1, curve_p); /* t6 = x3' - B */
-	vli_mod_mult_fast(t6, t6, t5);    /* t6 = (y2 + y1)*(x3' - B) */
-	vli_mod_sub(y1, t6, y1, curve_p); /* t2 = y3' */
-
-	vli_set(x1, t7);
-}
-
-static void ecc_point_mult(struct ecc_point *result,
-			   const struct ecc_point *point, u64 *scalar,
-			   u64 *initial_z, int num_bits)
-{
-	/* R0 and R1 */
-	u64 rx[2][NUM_ECC_DIGITS];
-	u64 ry[2][NUM_ECC_DIGITS];
-	u64 z[NUM_ECC_DIGITS];
-	int i, nb;
-
-	vli_set(rx[1], point->x);
-	vli_set(ry[1], point->y);
-
-	xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z);
-
-	for (i = num_bits - 2; i > 0; i--) {
-		nb = !vli_test_bit(scalar, i);
-		xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb]);
-		xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb]);
-	}
-
-	nb = !vli_test_bit(scalar, 0);
-	xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb]);
-
-	/* Find final 1/Z value. */
-	vli_mod_sub(z, rx[1], rx[0], curve_p); /* X1 - X0 */
-	vli_mod_mult_fast(z, z, ry[1 - nb]); /* Yb * (X1 - X0) */
-	vli_mod_mult_fast(z, z, point->x);   /* xP * Yb * (X1 - X0) */
-	vli_mod_inv(z, z, curve_p);          /* 1 / (xP * Yb * (X1 - X0)) */
-	vli_mod_mult_fast(z, z, point->y);   /* yP / (xP * Yb * (X1 - X0)) */
-	vli_mod_mult_fast(z, z, rx[1 - nb]); /* Xb * yP / (xP * Yb * (X1 - X0)) */
-	/* End 1/Z calculation */
-
-	xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb]);
-
-	apply_z(rx[0], ry[0], z);
-
-	vli_set(result->x, rx[0]);
-	vli_set(result->y, ry[0]);
-}
-
-static void ecc_bytes2native(const u8 bytes[ECC_BYTES],
-			     u64 native[NUM_ECC_DIGITS])
-{
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++) {
-		const u8 *digit = bytes + 8 * (NUM_ECC_DIGITS - 1 - i);
-
-		native[NUM_ECC_DIGITS - 1 - i] =
-				((u64) digit[0] << 0) |
-				((u64) digit[1] << 8) |
-				((u64) digit[2] << 16) |
-				((u64) digit[3] << 24) |
-				((u64) digit[4] << 32) |
-				((u64) digit[5] << 40) |
-				((u64) digit[6] << 48) |
-				((u64) digit[7] << 56);
-	}
-}
-
-static void ecc_native2bytes(const u64 native[NUM_ECC_DIGITS],
-			     u8 bytes[ECC_BYTES])
-{
-	int i;
-
-	for (i = 0; i < NUM_ECC_DIGITS; i++) {
-		u8 *digit = bytes + 8 * (NUM_ECC_DIGITS - 1 - i);
-
-		digit[0] = native[NUM_ECC_DIGITS - 1 - i] >> 0;
-		digit[1] = native[NUM_ECC_DIGITS - 1 - i] >> 8;
-		digit[2] = native[NUM_ECC_DIGITS - 1 - i] >> 16;
-		digit[3] = native[NUM_ECC_DIGITS - 1 - i] >> 24;
-		digit[4] = native[NUM_ECC_DIGITS - 1 - i] >> 32;
-		digit[5] = native[NUM_ECC_DIGITS - 1 - i] >> 40;
-		digit[6] = native[NUM_ECC_DIGITS - 1 - i] >> 48;
-		digit[7] = native[NUM_ECC_DIGITS - 1 - i] >> 56;
-	}
-}
-
-bool ecc_make_key(u8 public_key[64], u8 private_key[32])
-{
-	struct ecc_point pk;
-	u64 priv[NUM_ECC_DIGITS];
-	unsigned int tries = 0;
-
-	do {
-		if (tries++ >= MAX_TRIES)
-			return false;
-
-		get_random_bytes(priv, ECC_BYTES);
-
-		if (vli_is_zero(priv))
-			continue;
-
-		/* Make sure the private key is in the range [1, n-1]. */
-		if (vli_cmp(curve_n, priv) != 1)
-			continue;
-
-		ecc_point_mult(&pk, &curve_g, priv, NULL, vli_num_bits(priv));
-	} while (ecc_point_is_zero(&pk));
-
-	ecc_native2bytes(priv, private_key);
-	ecc_native2bytes(pk.x, public_key);
-	ecc_native2bytes(pk.y, &public_key[32]);
-
-	return true;
-}
-
-bool ecdh_shared_secret(const u8 public_key[64], const u8 private_key[32],
-		        u8 secret[32])
-{
-	u64 priv[NUM_ECC_DIGITS];
-	u64 rand[NUM_ECC_DIGITS];
-	struct ecc_point product, pk;
-
-	get_random_bytes(rand, ECC_BYTES);
-
-	ecc_bytes2native(public_key, pk.x);
-	ecc_bytes2native(&public_key[32], pk.y);
-	ecc_bytes2native(private_key, priv);
-
-	ecc_point_mult(&product, &pk, priv, rand, vli_num_bits(priv));
-
-	ecc_native2bytes(product.x, secret);
-
-	return !ecc_point_is_zero(&product);
-}
diff --git a/net/bluetooth/ecc.h b/net/bluetooth/ecc.h
deleted file mode 100644
index 8d6a2f4d1905..000000000000
--- a/net/bluetooth/ecc.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Copyright (c) 2013, Kenneth MacKay
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *  * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- *  * Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-/* Create a public/private key pair.
- * Outputs:
- *	public_key  - Will be filled in with the public key.
- *	private_key - Will be filled in with the private key.
- *
- * Returns true if the key pair was generated successfully, false
- * if an error occurred. The keys are with the LSB first.
- */
-bool ecc_make_key(u8 public_key[64], u8 private_key[32]);
-
-/* Compute a shared secret given your secret key and someone else's
- * public key.
- * Note: It is recommended that you hash the result of ecdh_shared_secret
- * before using it for symmetric encryption or HMAC.
- *
- * Inputs:
- *	public_key  - The public key of the remote party
- *	private_key - Your private key.
- *
- * Outputs:
- *	secret - Will be filled in with the shared secret value.
- *
- * Returns true if the shared secret was generated successfully, false
- * if an error occurred. Both input and output parameters are with the
- * LSB first.
- */
-bool ecdh_shared_secret(const u8 public_key[64], const u8 private_key[32],
-		        u8 secret[32]);
diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c
new file mode 100644
index 000000000000..24d4e60f8c48
--- /dev/null
+++ b/net/bluetooth/ecdh_helper.c
@@ -0,0 +1,231 @@
+/*
+ * ECDH helper functions - KPP wrappings
+ *
+ * Copyright (C) 2017 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation;
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+ * IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+ * CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ *
+ * ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+ * COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+ * SOFTWARE IS DISCLAIMED.
+ */
+#include "ecdh_helper.h"
+
+#include <linux/scatterlist.h>
+#include <crypto/kpp.h>
+#include <crypto/ecdh.h>
+
+struct ecdh_completion {
+	struct completion completion;
+	int err;
+};
+
+static void ecdh_complete(struct crypto_async_request *req, int err)
+{
+	struct ecdh_completion *res = req->data;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	res->err = err;
+	complete(&res->completion);
+}
+
+static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		out[i] = __swab64(in[ndigits - 1 - i]);
+}
+
+bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32],
+			 u8 secret[32])
+{
+	struct crypto_kpp *tfm;
+	struct kpp_request *req;
+	struct ecdh p;
+	struct ecdh_completion result;
+	struct scatterlist src, dst;
+	u8 *tmp, *buf;
+	unsigned int buf_len;
+	int err = -ENOMEM;
+
+	tmp = kmalloc(64, GFP_KERNEL);
+	if (!tmp)
+		return false;
+
+	tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+	if (IS_ERR(tfm)) {
+		pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n",
+		       PTR_ERR(tfm));
+		goto free_tmp;
+	}
+
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		goto free_kpp;
+
+	init_completion(&result.completion);
+
+	/* Security Manager Protocol holds digits in litte-endian order
+	 * while ECC API expect big-endian data
+	 */
+	swap_digits((u64 *)private_key, (u64 *)tmp, 4);
+	p.key = (char *)tmp;
+	p.key_size = 32;
+	/* Set curve_id */
+	p.curve_id = ECC_CURVE_NIST_P256;
+	buf_len = crypto_ecdh_key_len(&p);
+	buf = kmalloc(buf_len, GFP_KERNEL);
+	if (!buf) {
+		pr_err("alg: kpp: Failed to allocate %d bytes for buf\n",
+		       buf_len);
+		goto free_req;
+	}
+	crypto_ecdh_encode_key(buf, buf_len, &p);
+
+	/* Set A private Key */
+	err = crypto_kpp_set_secret(tfm, (void *)buf, buf_len);
+	if (err)
+		goto free_all;
+
+	swap_digits((u64 *)public_key, (u64 *)tmp, 4); /* x */
+	swap_digits((u64 *)&public_key[32], (u64 *)&tmp[32], 4); /* y */
+
+	sg_init_one(&src, tmp, 64);
+	sg_init_one(&dst, secret, 32);
+	kpp_request_set_input(req, &src, 64);
+	kpp_request_set_output(req, &dst, 32);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				 ecdh_complete, &result);
+	err = crypto_kpp_compute_shared_secret(req);
+	if (err == -EINPROGRESS) {
+		wait_for_completion(&result.completion);
+		err = result.err;
+	}
+	if (err < 0) {
+		pr_err("alg: ecdh: compute shared secret failed. err %d\n",
+		       err);
+		goto free_all;
+	}
+
+	swap_digits((u64 *)secret, (u64 *)tmp, 4);
+	memcpy(secret, tmp, 32);
+
+free_all:
+	kzfree(buf);
+free_req:
+	kpp_request_free(req);
+free_kpp:
+	crypto_free_kpp(tfm);
+free_tmp:
+	kfree(tmp);
+	return (err == 0);
+}
+
+bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32])
+{
+	struct crypto_kpp *tfm;
+	struct kpp_request *req;
+	struct ecdh p;
+	struct ecdh_completion result;
+	struct scatterlist dst;
+	u8 *tmp, *buf;
+	unsigned int buf_len;
+	int err = -ENOMEM;
+	const unsigned short max_tries = 16;
+	unsigned short tries = 0;
+
+	tmp = kmalloc(64, GFP_KERNEL);
+	if (!tmp)
+		return false;
+
+	tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+	if (IS_ERR(tfm)) {
+		pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n",
+		       PTR_ERR(tfm));
+		goto free_tmp;
+	}
+
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		goto free_kpp;
+
+	init_completion(&result.completion);
+
+	/* Set curve_id */
+	p.curve_id = ECC_CURVE_NIST_P256;
+	p.key_size = 32;
+	buf_len = crypto_ecdh_key_len(&p);
+	buf = kmalloc(buf_len, GFP_KERNEL);
+	if (!buf) {
+		pr_err("alg: kpp: Failed to allocate %d bytes for buf\n",
+		       buf_len);
+		goto free_req;
+	}
+
+	do {
+		if (tries++ >= max_tries)
+			goto free_all;
+
+		/* Set private Key */
+		p.key = (char *)private_key;
+		crypto_ecdh_encode_key(buf, buf_len, &p);
+		err = crypto_kpp_set_secret(tfm, buf, buf_len);
+		if (err)
+			goto free_all;
+
+		sg_init_one(&dst, tmp, 64);
+		kpp_request_set_input(req, NULL, 0);
+		kpp_request_set_output(req, &dst, 64);
+		kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					 ecdh_complete, &result);
+
+		err = crypto_kpp_generate_public_key(req);
+
+		if (err == -EINPROGRESS) {
+			wait_for_completion(&result.completion);
+			err = result.err;
+		}
+
+		/* Private key is not valid. Regenerate */
+		if (err == -EINVAL)
+			continue;
+
+		if (err < 0)
+			goto free_all;
+		else
+			break;
+
+	} while (true);
+
+	/* Keys are handed back in little endian as expected by Security
+	 * Manager Protocol
+	 */
+	swap_digits((u64 *)tmp, (u64 *)public_key, 4); /* x */
+	swap_digits((u64 *)&tmp[32], (u64 *)&public_key[32], 4); /* y */
+	swap_digits((u64 *)private_key, (u64 *)tmp, 4);
+	memcpy(private_key, tmp, 32);
+
+free_all:
+	kzfree(buf);
+free_req:
+	kpp_request_free(req);
+free_kpp:
+	crypto_free_kpp(tfm);
+free_tmp:
+	kfree(tmp);
+	return (err == 0);
+}
diff --git a/net/bluetooth/ecdh_helper.h b/net/bluetooth/ecdh_helper.h
new file mode 100644
index 000000000000..7a423faf76e5
--- /dev/null
+++ b/net/bluetooth/ecdh_helper.h
@@ -0,0 +1,27 @@
+/*
+ * ECDH helper functions - KPP wrappings
+ *
+ * Copyright (C) 2017 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation;
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+ * IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+ * CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ *
+ * ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+ * COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+ * SOFTWARE IS DISCLAIMED.
+ */
+#include <linux/types.h>
+
+bool compute_ecdh_secret(const u8 pub_a[64], const u8 priv_b[32],
+			 u8 secret[32]);
+bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32]);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 3ac89e9ace71..05686776a5fb 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2950,8 +2950,8 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->le_adv_max_interval = 0x0800;
 	hdev->le_scan_interval = 0x0060;
 	hdev->le_scan_window = 0x0030;
-	hdev->le_conn_min_interval = 0x0028;
-	hdev->le_conn_max_interval = 0x0038;
+	hdev->le_conn_min_interval = 0x0018;
+	hdev->le_conn_max_interval = 0x0028;
 	hdev->le_conn_latency = 0x0000;
 	hdev->le_supv_timeout = 0x002a;
 	hdev->le_def_tx_len = 0x001b;
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index f64d6566021f..638bf0e1a2e3 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1680,7 +1680,8 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_NOSIGNAL|MSG_ERRQUEUE))
+	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_NOSIGNAL|MSG_ERRQUEUE|
+			       MSG_CMSG_COMPAT))
 		return -EINVAL;
 
 	if (len < 4 || len > HCI_MAX_FRAME_SIZE)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fc7f321a3823..f88ac99528ce 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2425,6 +2425,22 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan,
 	return 0;
 }
 
+static void l2cap_le_flowctl_send(struct l2cap_chan *chan)
+{
+	int sent = 0;
+
+	BT_DBG("chan %p", chan);
+
+	while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) {
+		l2cap_do_send(chan, skb_dequeue(&chan->tx_q));
+		chan->tx_credits--;
+		sent++;
+	}
+
+	BT_DBG("Sent %d credits %u queued %u", sent, chan->tx_credits,
+	       skb_queue_len(&chan->tx_q));
+}
+
 int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 {
 	struct sk_buff *skb;
@@ -2458,9 +2474,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 		if (len > chan->omtu)
 			return -EMSGSIZE;
 
-		if (!chan->tx_credits)
-			return -EAGAIN;
-
 		__skb_queue_head_init(&seg_queue);
 
 		err = l2cap_segment_le_sdu(chan, &seg_queue, msg, len);
@@ -2475,10 +2488,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 
 		skb_queue_splice_tail_init(&seg_queue, &chan->tx_q);
 
-		while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) {
-			l2cap_do_send(chan, skb_dequeue(&chan->tx_q));
-			chan->tx_credits--;
-		}
+		l2cap_le_flowctl_send(chan);
 
 		if (!chan->tx_credits)
 			chan->ops->suspend(chan);
@@ -5570,10 +5580,8 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
 
 	chan->tx_credits += credits;
 
-	while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) {
-		l2cap_do_send(chan, skb_dequeue(&chan->tx_q));
-		chan->tx_credits--;
-	}
+	/* Resume sending */
+	l2cap_le_flowctl_send(chan);
 
 	if (chan->tx_credits)
 		chan->ops->resume(chan);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f307b145ea54..507b80d59dec 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -301,7 +301,7 @@ done:
 }
 
 static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
-			     int flags)
+			     int flags, bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index f7eb02f09b54..8ebca9033d60 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -311,7 +311,7 @@ struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio)
 
 	skb_queue_head_init(&d->tx_queue);
 	mutex_init(&d->lock);
-	atomic_set(&d->refcnt, 1);
+	refcount_set(&d->refcnt, 1);
 
 	rfcomm_dlc_clear_state(d);
 
@@ -342,7 +342,7 @@ static void rfcomm_dlc_unlink(struct rfcomm_dlc *d)
 {
 	struct rfcomm_session *s = d->session;
 
-	BT_DBG("dlc %p refcnt %d session %p", d, atomic_read(&d->refcnt), s);
+	BT_DBG("dlc %p refcnt %d session %p", d, refcount_read(&d->refcnt), s);
 
 	list_del(&d->list);
 	d->session = NULL;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index aa1a814ceddc..ac3c650cb234 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -471,7 +471,8 @@ done:
 	return err;
 }
 
-static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags,
+			      bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e4e9a2da1e7e..728e0c8dc8e7 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -627,7 +627,7 @@ done:
 }
 
 static int sco_sock_accept(struct socket *sock, struct socket *newsock,
-			   int flags)
+			   int flags, bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *ch;
diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c
index dc688f13e496..ee92c925ecc5 100644
--- a/net/bluetooth/selftest.c
+++ b/net/bluetooth/selftest.c
@@ -26,7 +26,7 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
-#include "ecc.h"
+#include "ecdh_helper.h"
 #include "smp.h"
 #include "selftest.h"
 
@@ -142,18 +142,30 @@ static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32],
 				   const u8 pub_a[64], const u8 pub_b[64],
 				   const u8 dhkey[32])
 {
-	u8 dhkey_a[32], dhkey_b[32];
+	u8 *tmp, *dhkey_a, *dhkey_b;
+	int ret = 0;
 
-	ecdh_shared_secret(pub_b, priv_a, dhkey_a);
-	ecdh_shared_secret(pub_a, priv_b, dhkey_b);
-
-	if (memcmp(dhkey_a, dhkey, 32))
+	tmp = kmalloc(64, GFP_KERNEL);
+	if (!tmp)
 		return -EINVAL;
 
+	dhkey_a = &tmp[0];
+	dhkey_b = &tmp[32];
+
+	compute_ecdh_secret(pub_b, priv_a, dhkey_a);
+	compute_ecdh_secret(pub_a, priv_b, dhkey_b);
+
+	if (memcmp(dhkey_a, dhkey, 32)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (memcmp(dhkey_b, dhkey, 32))
-		return -EINVAL;
+		ret = -EINVAL;
 
-	return 0;
+out:
+	kfree(dhkey_a);
+	return ret;
 }
 
 static char test_ecdh_buffer[32];
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index fae391f1871f..14585edc9439 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -31,7 +31,7 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
-#include "ecc.h"
+#include "ecdh_helper.h"
 #include "smp.h"
 
 #define SMP_DEV(hdev) \
@@ -569,8 +569,11 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
 		smp->debug_key = true;
 	} else {
 		while (true) {
+			/* Seed private key with random number */
+			get_random_bytes(smp->local_sk, 32);
+
 			/* Generate local key pair for Secure Connections */
-			if (!ecc_make_key(smp->local_pk, smp->local_sk))
+			if (!generate_ecdh_keys(smp->local_pk, smp->local_sk))
 				return -EIO;
 
 			/* This is unlikely, but we need to check that
@@ -1895,8 +1898,11 @@ static u8 sc_send_public_key(struct smp_chan *smp)
 		set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
 	} else {
 		while (true) {
+			/* Seed private key with random number */
+			get_random_bytes(smp->local_sk, 32);
+
 			/* Generate local key pair for Secure Connections */
-			if (!ecc_make_key(smp->local_pk, smp->local_sk))
+			if (!generate_ecdh_keys(smp->local_pk, smp->local_sk))
 				return SMP_UNSPECIFIED;
 
 			/* This is unlikely, but we need to check that
@@ -2670,7 +2676,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	SMP_DBG("Remote Public Key X: %32phN", smp->remote_pk);
 	SMP_DBG("Remote Public Key Y: %32phN", smp->remote_pk + 32);
 
-	if (!ecdh_shared_secret(smp->remote_pk, smp->local_sk, smp->dhkey))
+	if (!compute_ecdh_secret(smp->remote_pk, smp->local_sk, smp->dhkey))
 		return SMP_UNSPECIFIED;
 
 	SMP_DBG("DHKey %32phN", smp->dhkey);
@@ -3483,6 +3489,32 @@ void smp_unregister(struct hci_dev *hdev)
 
 #if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
 
+static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		out[i] = __swab64(in[ndigits - 1 - i]);
+}
+
+static int __init test_debug_key(void)
+{
+	u8 pk[64], sk[32];
+
+	swap_digits((u64 *)debug_sk, (u64 *)sk, 4);
+
+	if (!generate_ecdh_keys(pk, sk))
+		return -EINVAL;
+
+	if (memcmp(sk, debug_sk, 32))
+		return -EINVAL;
+
+	if (memcmp(pk, debug_pk, 64))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int __init test_ah(struct crypto_cipher *tfm_aes)
 {
 	const u8 irk[16] = {
@@ -3738,6 +3770,12 @@ static int __init run_selftests(struct crypto_cipher *tfm_aes,
 
 	calltime = ktime_get();
 
+	err = test_debug_key();
+	if (err) {
+		BT_ERR("debug_key test failed");
+		goto done;
+	}
+
 	err = test_ah(tfm_aes);
 	if (err) {
 		BT_ERR("smp_ah test failed");
diff --git a/net/bpf/Makefile b/net/bpf/Makefile
new file mode 100644
index 000000000000..27b2992a0692
--- /dev/null
+++ b/net/bpf/Makefile
@@ -0,0 +1 @@
+obj-y	:= test_run.o
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
new file mode 100644
index 000000000000..6be41a44d688
--- /dev/null
+++ b/net/bpf/test_run.c
@@ -0,0 +1,173 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
+#include <linux/filter.h>
+#include <linux/sched/signal.h>
+
+static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
+{
+	u32 ret;
+
+	preempt_disable();
+	rcu_read_lock();
+	ret = BPF_PROG_RUN(prog, ctx);
+	rcu_read_unlock();
+	preempt_enable();
+
+	return ret;
+}
+
+static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
+{
+	u64 time_start, time_spent = 0;
+	u32 ret = 0, i;
+
+	if (!repeat)
+		repeat = 1;
+	time_start = ktime_get_ns();
+	for (i = 0; i < repeat; i++) {
+		ret = bpf_test_run_one(prog, ctx);
+		if (need_resched()) {
+			if (signal_pending(current))
+				break;
+			time_spent += ktime_get_ns() - time_start;
+			cond_resched();
+			time_start = ktime_get_ns();
+		}
+	}
+	time_spent += ktime_get_ns() - time_start;
+	do_div(time_spent, repeat);
+	*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+
+	return ret;
+}
+
+static int bpf_test_finish(const union bpf_attr *kattr,
+			   union bpf_attr __user *uattr, const void *data,
+			   u32 size, u32 retval, u32 duration)
+{
+	void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
+	int err = -EFAULT;
+
+	if (data_out && copy_to_user(data_out, data, size))
+		goto out;
+	if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
+		goto out;
+	if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
+		goto out;
+	if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
+		goto out;
+	err = 0;
+out:
+	return err;
+}
+
+static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
+			   u32 headroom, u32 tailroom)
+{
+	void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+	void *data;
+
+	if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
+		return ERR_PTR(-EINVAL);
+
+	data = kzalloc(size + headroom + tailroom, GFP_USER);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(data + headroom, data_in, size)) {
+		kfree(data);
+		return ERR_PTR(-EFAULT);
+	}
+	return data;
+}
+
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr)
+{
+	bool is_l2 = false, is_direct_pkt_access = false;
+	u32 size = kattr->test.data_size_in;
+	u32 repeat = kattr->test.repeat;
+	u32 retval, duration;
+	struct sk_buff *skb;
+	void *data;
+	int ret;
+
+	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
+			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	switch (prog->type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+		is_l2 = true;
+		/* fall through */
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_XMIT:
+		is_direct_pkt_access = true;
+		break;
+	default:
+		break;
+	}
+
+	skb = build_skb(data, 0);
+	if (!skb) {
+		kfree(data);
+		return -ENOMEM;
+	}
+
+	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+	__skb_put(skb, size);
+	skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev);
+	skb_reset_network_header(skb);
+
+	if (is_l2)
+		__skb_push(skb, ETH_HLEN);
+	if (is_direct_pkt_access)
+		bpf_compute_data_end(skb);
+	retval = bpf_test_run(prog, skb, repeat, &duration);
+	if (!is_l2)
+		__skb_push(skb, ETH_HLEN);
+	size = skb->len;
+	/* bpf program can never convert linear skb to non-linear */
+	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
+		size = skb_headlen(skb);
+	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+	kfree_skb(skb);
+	return ret;
+}
+
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr)
+{
+	u32 size = kattr->test.data_size_in;
+	u32 repeat = kattr->test.repeat;
+	struct xdp_buff xdp = {};
+	u32 retval, duration;
+	void *data;
+	int ret;
+
+	data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	xdp.data_hard_start = data;
+	xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN;
+	xdp.data_end = xdp.data + size;
+
+	retval = bpf_test_run(prog, &xdp, repeat, &duration);
+	if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN)
+		size = xdp.data_end - xdp.data;
+	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+	kfree(data);
+	return ret;
+}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ea71513fca21..430b53e7d941 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -119,6 +119,16 @@ static int br_dev_init(struct net_device *dev)
 	return err;
 }
 
+static void br_dev_uninit(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	br_multicast_dev_del(br);
+	br_multicast_uninit_stats(br);
+	br_vlan_flush(br);
+	free_percpu(br->stats);
+}
+
 static int br_dev_open(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -332,6 +342,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_open		 = br_dev_open,
 	.ndo_stop		 = br_dev_stop,
 	.ndo_init		 = br_dev_init,
+	.ndo_uninit		 = br_dev_uninit,
 	.ndo_start_xmit		 = br_dev_xmit,
 	.ndo_get_stats64	 = br_get_stats64,
 	.ndo_set_mac_address	 = br_set_mac_address,
@@ -356,14 +367,6 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_features_check	 = passthru_features_check,
 };
 
-static void br_dev_free(struct net_device *dev)
-{
-	struct net_bridge *br = netdev_priv(dev);
-
-	free_percpu(br->stats);
-	free_netdev(dev);
-}
-
 static struct device_type br_type = {
 	.name	= "bridge",
 };
@@ -376,7 +379,7 @@ void br_dev_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &br_netdev_ops;
-	dev->destructor = br_dev_free;
+	dev->destructor = free_netdev;
 	dev->ethtool_ops = &br_ethtool_ops;
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 4f598dc2d916..ab0c7cc8448f 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -106,7 +106,7 @@ static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br,
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
 	struct net_bridge_fdb_entry *fdb;
 
-	WARN_ON_ONCE(!br_hash_lock_held(br));
+	lockdep_assert_held_once(&br->hash_lock);
 
 	rcu_read_lock();
 	fdb = fdb_find_rcu(head, addr, vid);
@@ -589,6 +589,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 			if (unlikely(source != fdb->dst)) {
 				fdb->dst = source;
 				fdb_modified = true;
+				/* Take over HW learned entry */
+				if (unlikely(fdb->added_by_external_learn))
+					fdb->added_by_external_learn = 0;
 			}
 			if (now != fdb->updated)
 				fdb->updated = now;
@@ -854,6 +857,8 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
 		br_fdb_update(br, p, addr, vid, true);
 		rcu_read_unlock();
 		local_bh_enable();
+	} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
+		err = br_fdb_external_learn_add(br, p, addr, vid);
 	} else {
 		spin_lock_bh(&br->hash_lock);
 		err = fdb_add_entry(br, p, addr, ndm->ndm_state,
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 902af6ba481c..48fb17417fac 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -183,13 +183,23 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 	struct net_bridge_port *p;
 
 	list_for_each_entry_rcu(p, &br->port_list, list) {
-		/* Do not flood unicast traffic to ports that turn it off */
-		if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD))
-			continue;
-		/* Do not flood if mc off, except for traffic we originate */
-		if (pkt_type == BR_PKT_MULTICAST &&
-		    !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
-			continue;
+		/* Do not flood unicast traffic to ports that turn it off, nor
+		 * other traffic if flood off, except for traffic we originate
+		 */
+		switch (pkt_type) {
+		case BR_PKT_UNICAST:
+			if (!(p->flags & BR_FLOOD))
+				continue;
+			break;
+		case BR_PKT_MULTICAST:
+			if (!(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
+				continue;
+			break;
+		case BR_PKT_BROADCAST:
+			if (!(p->flags & BR_BCAST_FLOOD) && skb->dev != br->dev)
+				continue;
+			break;
+		}
 
 		/* Do not flood to ports that enable proxy ARP */
 		if (p->flags & BR_PROXYARP)
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 8ac1770aa222..7f8d05cf9065 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -22,6 +22,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/if_ether.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include <net/sock.h>
 #include <linux/if_vlan.h>
 #include <net/switchdev.h>
@@ -311,8 +312,6 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
 
 	br_fdb_delete_by_port(br, NULL, 0, 1);
 
-	br_vlan_flush(br);
-	br_multicast_dev_del(br);
 	cancel_delayed_work_sync(&br->gc_work);
 
 	br_sysfs_delbr(br->dev);
@@ -362,7 +361,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br,
 	p->path_cost = port_cost(dev);
 	p->priority = 0x8000 >> BR_PORT_BITS;
 	p->port_no = index;
-	p->flags = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD;
+	p->flags = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD;
 	br_init_port(p);
 	br_set_state(p, BR_STATE_DISABLED);
 	br_stp_port_timer_init(p);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 236f34244dbe..013f2290bfa5 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -30,6 +30,7 @@ EXPORT_SYMBOL(br_should_route_hook);
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	br_drop_fake_rtable(skb);
 	return netif_receive_skb(skb);
 }
 
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 056e6ac49d8f..b0845480a3ae 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -464,7 +464,8 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_device *dev;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, NULL,
+			  NULL);
 	if (err < 0)
 		return err;
 
@@ -568,7 +569,8 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 	return ret;
 }
 
-static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
@@ -662,7 +664,8 @@ unlock:
 	return err;
 }
 
-static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index b760f2620abf..faa7261a992f 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2031,8 +2031,6 @@ void br_multicast_dev_del(struct net_bridge *br)
 
 out:
 	spin_unlock_bh(&br->multicast_lock);
-
-	free_percpu(br->mcast_stats);
 }
 
 int br_multicast_set_router(struct net_bridge *br, unsigned long val)
@@ -2531,6 +2529,11 @@ int br_multicast_init_stats(struct net_bridge *br)
 	return 0;
 }
 
+void br_multicast_uninit_stats(struct net_bridge *br)
+{
+	free_percpu(br->mcast_stats);
+}
+
 static void mcast_stats_add_dir(u64 *dst, u64 *src)
 {
 	dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 95087e6e8258..067cf0313449 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv,
 }
 
 
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one.  On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
-				   struct sk_buff *skb,
-				   const struct nf_hook_state *state)
-{
-	br_drop_fake_rtable(skb);
-	return NF_ACCEPT;
-}
-
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -721,18 +706,20 @@ static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 
 static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge;
-	unsigned int mtu_reserved;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+	unsigned int mtu, mtu_reserved;
 
 	mtu_reserved = nf_bridge_mtu_reduction(skb);
+	mtu = skb->dev->mtu;
 
-	if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) {
+	if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu)
+		mtu = nf_bridge->frag_max_size;
+
+	if (skb_is_gso(skb) || skb->len + mtu_reserved <= mtu) {
 		nf_bridge_info_free(skb);
 		return br_dev_queue_push_xmit(net, sk, skb);
 	}
 
-	nf_bridge = nf_bridge_info_get(skb);
-
 	/* This is wrong! We should preserve the original fragment
 	 * boundaries by preserving frag_list rather than refragmenting.
 	 */
@@ -908,12 +895,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 		.priority = NF_BR_PRI_BRNF,
 	},
 	{
-		.hook = br_nf_local_in,
-		.pf = NFPROTO_BRIDGE,
-		.hooknum = NF_BR_LOCAL_IN,
-		.priority = NF_BR_PRI_BRNF,
-	},
-	{
 		.hook = br_nf_forward_ip,
 		.pf = NFPROTO_BRIDGE,
 		.hooknum = NF_BR_FORWARD,
@@ -1016,13 +997,10 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
 	if (!elem)
 		return okfn(net, sk, skb);
 
-	/* We may already have this, but read-locks nest anyway */
-	rcu_read_lock();
 	nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
 			   sk, net, okfn);
 
 	ret = nf_hook_slow(skb, &state, elem);
-	rcu_read_unlock();
 	if (ret == 1)
 		ret = okfn(net, sk, skb);
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a8f6acd23e30..a572db710d4e 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -189,6 +189,8 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 		       !!(p->flags & BR_FLOOD)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD,
 		       !!(p->flags & BR_MCAST_FLOOD)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD,
+		       !!(p->flags & BR_BCAST_FLOOD)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI,
 		       !!(p->flags & BR_PROXYARP_WIFI)) ||
@@ -683,6 +685,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 	br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
 	br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD);
 	br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST);
+	br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD);
 	br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP);
 	br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI);
 
@@ -748,8 +751,8 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 
 	if (p && protinfo) {
 		if (protinfo->nla_type & NLA_F_NESTED) {
-			err = nla_parse_nested(tb, IFLA_BRPORT_MAX,
-					       protinfo, br_port_policy);
+			err = nla_parse_nested(tb, IFLA_BRPORT_MAX, protinfo,
+					       br_port_policy, NULL);
 			if (err)
 				return err;
 
@@ -1165,11 +1168,14 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
 		spin_unlock_bh(&br->lock);
 	}
 
-	err = br_changelink(dev, tb, data);
+	err = register_netdevice(dev);
 	if (err)
 		return err;
 
-	return register_netdevice(dev);
+	err = br_changelink(dev, tb, data);
+	if (err)
+		unregister_netdevice(dev);
+	return err;
 }
 
 static size_t br_get_size(const struct net_device *brdev)
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index c913491495ab..3712c7f0e00c 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -227,8 +227,8 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr,
 
 	memset(tinfo, 0, sizeof(*tinfo));
 
-	err = nla_parse_nested(tb, IFLA_BRIDGE_VLAN_TUNNEL_MAX,
-			       attr, vlan_tunnel_policy);
+	err = nla_parse_nested(tb, IFLA_BRIDGE_VLAN_TUNNEL_MAX, attr,
+			       vlan_tunnel_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2288fca7756c..0d177280aa84 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -531,15 +531,6 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
 int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
 			      const unsigned char *addr, u16 vid);
 
-static inline bool br_hash_lock_held(struct net_bridge *br)
-{
-#ifdef CONFIG_LOCKDEP
-	return lockdep_is_held(&br->hash_lock);
-#else
-	return true;
-#endif
-}
-
 /* br_forward.c */
 enum br_pkt_type {
 	BR_PKT_UNICAST,
@@ -629,6 +620,7 @@ void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
 void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
 			const struct sk_buff *skb, u8 type, u8 dir);
 int br_multicast_init_stats(struct net_bridge *br);
+void br_multicast_uninit_stats(struct net_bridge *br);
 void br_multicast_get_stats(const struct net_bridge *br,
 			    const struct net_bridge_port *p,
 			    struct br_mcast_stats *dest);
@@ -769,6 +761,10 @@ static inline int br_multicast_init_stats(struct net_bridge *br)
 	return 0;
 }
 
+static inline void br_multicast_uninit_stats(struct net_bridge *br)
+{
+}
+
 static inline int br_multicast_igmp_type(const struct sk_buff *skb)
 {
 	return 0;
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 79aee759aba5..5d5d413a6cf8 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -173,6 +173,7 @@ BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD);
 BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP);
 BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI);
 BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD);
+BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -221,6 +222,7 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_proxyarp,
 	&brport_attr_proxyarp_wifi,
 	&brport_attr_multicast_flood,
+	&brport_attr_broadcast_flood,
 	NULL
 };
 
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 98b9c8e8615e..707caea39743 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -62,10 +62,10 @@ print_ports(const struct sk_buff *skb, uint8_t protocol, int offset)
 		pptr = skb_header_pointer(skb, offset,
 					  sizeof(_ports), &_ports);
 		if (pptr == NULL) {
-			printk(" INCOMPLETE TCP/UDP header");
+			pr_cont(" INCOMPLETE TCP/UDP header");
 			return;
 		}
-		printk(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
+		pr_cont(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
 	}
 }
 
@@ -100,11 +100,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
 		if (ih == NULL) {
-			printk(" INCOMPLETE IP header");
+			pr_cont(" INCOMPLETE IP header");
 			goto out;
 		}
-		printk(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
-		       &ih->saddr, &ih->daddr, ih->tos, ih->protocol);
+		pr_cont(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
+			&ih->saddr, &ih->daddr, ih->tos, ih->protocol);
 		print_ports(skb, ih->protocol, ih->ihl*4);
 		goto out;
 	}
@@ -120,11 +120,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
 		if (ih == NULL) {
-			printk(" INCOMPLETE IPv6 header");
+			pr_cont(" INCOMPLETE IPv6 header");
 			goto out;
 		}
-		printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
-		       &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
+		pr_cont(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
+			&ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
 		nexthdr = ih->nexthdr;
 		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
 		if (offset_ph == -1)
@@ -142,12 +142,12 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 		ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
 		if (ah == NULL) {
-			printk(" INCOMPLETE ARP header");
+			pr_cont(" INCOMPLETE ARP header");
 			goto out;
 		}
-		printk(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
-		       ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
-		       ntohs(ah->ar_op));
+		pr_cont(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
+			ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
+			ntohs(ah->ar_op));
 
 		/* If it's for Ethernet and the lengths are OK,
 		 * then log the ARP payload
@@ -161,17 +161,17 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 			ap = skb_header_pointer(skb, sizeof(_arph),
 						sizeof(_arpp), &_arpp);
 			if (ap == NULL) {
-				printk(" INCOMPLETE ARP payload");
+				pr_cont(" INCOMPLETE ARP payload");
 				goto out;
 			}
-			printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
-					ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst);
+			pr_cont(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
+				ap->mac_src, ap->ip_src,
+				ap->mac_dst, ap->ip_dst);
 		}
 	}
 out:
-	printk("\n");
+	pr_cont("\n");
 	spin_unlock_bh(&ebt_log_lock);
-
 }
 
 static unsigned int
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 8fe36dc3aab2..2585b100ebbb 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -65,13 +65,13 @@ static int ebt_broute(struct sk_buff *skb)
 
 static int __net_init broute_net_init(struct net *net)
 {
-	net->xt.broute_table = ebt_register_table(net, &broute_table);
+	net->xt.broute_table = ebt_register_table(net, &broute_table, NULL);
 	return PTR_ERR_OR_ZERO(net->xt.broute_table);
 }
 
 static void __net_exit broute_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.broute_table);
+	ebt_unregister_table(net, net->xt.broute_table, NULL);
 }
 
 static struct pernet_operations broute_net_ops = {
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 593a1bdc079e..f22ef7c21913 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -93,13 +93,13 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
 
 static int __net_init frame_filter_net_init(struct net *net)
 {
-	net->xt.frame_filter = ebt_register_table(net, &frame_filter);
+	net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter);
 	return PTR_ERR_OR_ZERO(net->xt.frame_filter);
 }
 
 static void __net_exit frame_filter_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.frame_filter);
+	ebt_unregister_table(net, net->xt.frame_filter, ebt_ops_filter);
 }
 
 static struct pernet_operations frame_filter_net_ops = {
@@ -109,20 +109,11 @@ static struct pernet_operations frame_filter_net_ops = {
 
 static int __init ebtable_filter_init(void)
 {
-	int ret;
-
-	ret = register_pernet_subsys(&frame_filter_net_ops);
-	if (ret < 0)
-		return ret;
-	ret = nf_register_hooks(ebt_ops_filter, ARRAY_SIZE(ebt_ops_filter));
-	if (ret < 0)
-		unregister_pernet_subsys(&frame_filter_net_ops);
-	return ret;
+	return register_pernet_subsys(&frame_filter_net_ops);
 }
 
 static void __exit ebtable_filter_fini(void)
 {
-	nf_unregister_hooks(ebt_ops_filter, ARRAY_SIZE(ebt_ops_filter));
 	unregister_pernet_subsys(&frame_filter_net_ops);
 }
 
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index eb33919821ee..2f7a4f314406 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -93,13 +93,13 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
 
 static int __net_init frame_nat_net_init(struct net *net)
 {
-	net->xt.frame_nat = ebt_register_table(net, &frame_nat);
+	net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat);
 	return PTR_ERR_OR_ZERO(net->xt.frame_nat);
 }
 
 static void __net_exit frame_nat_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.frame_nat);
+	ebt_unregister_table(net, net->xt.frame_nat, ebt_ops_nat);
 }
 
 static struct pernet_operations frame_nat_net_ops = {
@@ -109,20 +109,11 @@ static struct pernet_operations frame_nat_net_ops = {
 
 static int __init ebtable_nat_init(void)
 {
-	int ret;
-
-	ret = register_pernet_subsys(&frame_nat_net_ops);
-	if (ret < 0)
-		return ret;
-	ret = nf_register_hooks(ebt_ops_nat, ARRAY_SIZE(ebt_ops_nat));
-	if (ret < 0)
-		unregister_pernet_subsys(&frame_nat_net_ops);
-	return ret;
+	return register_pernet_subsys(&frame_nat_net_ops);
 }
 
 static void __exit ebtable_nat_fini(void)
 {
-	nf_unregister_hooks(ebt_ops_nat, ARRAY_SIZE(ebt_ops_nat));
 	unregister_pernet_subsys(&frame_nat_net_ops);
 }
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 79b69917f521..9ec0c9f908fa 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1157,8 +1157,30 @@ free_newinfo:
 	return ret;
 }
 
+static void __ebt_unregister_table(struct net *net, struct ebt_table *table)
+{
+	int i;
+
+	mutex_lock(&ebt_mutex);
+	list_del(&table->list);
+	mutex_unlock(&ebt_mutex);
+	EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size,
+			  ebt_cleanup_entry, net, NULL);
+	if (table->private->nentries)
+		module_put(table->me);
+	vfree(table->private->entries);
+	if (table->private->chainstack) {
+		for_each_possible_cpu(i)
+			vfree(table->private->chainstack[i]);
+		vfree(table->private->chainstack);
+	}
+	vfree(table->private);
+	kfree(table);
+}
+
 struct ebt_table *
-ebt_register_table(struct net *net, const struct ebt_table *input_table)
+ebt_register_table(struct net *net, const struct ebt_table *input_table,
+		   const struct nf_hook_ops *ops)
 {
 	struct ebt_table_info *newinfo;
 	struct ebt_table *t, *table;
@@ -1238,6 +1260,16 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table)
 	}
 	list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]);
 	mutex_unlock(&ebt_mutex);
+
+	if (!ops)
+		return table;
+
+	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
+	if (ret) {
+		__ebt_unregister_table(net, table);
+		return ERR_PTR(ret);
+	}
+
 	return table;
 free_unlock:
 	mutex_unlock(&ebt_mutex);
@@ -1256,29 +1288,12 @@ out:
 	return ERR_PTR(ret);
 }
 
-void ebt_unregister_table(struct net *net, struct ebt_table *table)
+void ebt_unregister_table(struct net *net, struct ebt_table *table,
+			  const struct nf_hook_ops *ops)
 {
-	int i;
-
-	if (!table) {
-		BUGPRINT("Request to unregister NULL table!!!\n");
-		return;
-	}
-	mutex_lock(&ebt_mutex);
-	list_del(&table->list);
-	mutex_unlock(&ebt_mutex);
-	EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size,
-			  ebt_cleanup_entry, net, NULL);
-	if (table->private->nentries)
-		module_put(table->me);
-	vfree(table->private->entries);
-	if (table->private->chainstack) {
-		for_each_possible_cpu(i)
-			vfree(table->private->chainstack[i]);
-		vfree(table->private->chainstack);
-	}
-	vfree(table->private);
-	kfree(table);
+	if (ops)
+		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+	__ebt_unregister_table(net, table);
 }
 
 /* userspace just supplied us with counters */
@@ -1713,7 +1728,7 @@ static int compat_copy_entry_to_user(struct ebt_entry *e, void __user **dstptr,
 	if (*size < sizeof(*ce))
 		return -EINVAL;
 
-	ce = (struct ebt_entry __user *)*dstptr;
+	ce = *dstptr;
 	if (copy_to_user(ce, e, sizeof(*ce)))
 		return -EFAULT;
 
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 5974dbc1ea24..bb63c9aed55d 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -111,7 +111,7 @@ nft_meta_bridge_select_ops(const struct nft_ctx *ctx,
 static struct nft_expr_type nft_meta_bridge_type __read_mostly = {
 	.family         = NFPROTO_BRIDGE,
 	.name           = "meta",
-	.select_ops     = &nft_meta_bridge_select_ops,
+	.select_ops     = nft_meta_bridge_select_ops,
 	.policy         = nft_meta_policy,
 	.maxattr        = NFTA_META_MAX,
 	.owner          = THIS_MODULE,
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 206dc266ecd2..346ef6b00b8f 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -375,11 +375,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx,
 				  const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
-	int icmp_code, err;
-
-	err = nft_reject_bridge_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
+	int icmp_code;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 5488e4a6ccd0..b6406fe33c76 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -2,7 +2,7 @@
  * af_can.c - Protocol family CAN core module
  *            (used by different CAN protocol modules)
  *
- * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2017 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -75,20 +75,12 @@ static int stats_timer __read_mostly = 1;
 module_param(stats_timer, int, S_IRUGO);
 MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)");
 
-/* receive filters subscribed for 'all' CAN devices */
-struct dev_rcv_lists can_rx_alldev_list;
-static DEFINE_SPINLOCK(can_rcvlists_lock);
-
 static struct kmem_cache *rcv_cache __read_mostly;
 
 /* table of registered CAN protocols */
 static const struct can_proto *proto_tab[CAN_NPROTO] __read_mostly;
 static DEFINE_MUTEX(proto_tab_lock);
 
-struct timer_list can_stattimer;   /* timer for statistics update */
-struct s_stats    can_stats;       /* packet statistics */
-struct s_pstats   can_pstats;      /* receive list statistics */
-
 static atomic_t skbcounter = ATOMIC_INIT(0);
 
 /*
@@ -145,9 +137,6 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
 	if (protocol < 0 || protocol >= CAN_NPROTO)
 		return -EINVAL;
 
-	if (!net_eq(net, &init_net))
-		return -EAFNOSUPPORT;
-
 	cp = can_get_proto(protocol);
 
 #ifdef CONFIG_MODULES
@@ -228,6 +217,7 @@ int can_send(struct sk_buff *skb, int loop)
 {
 	struct sk_buff *newskb = NULL;
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
+	struct s_stats *can_stats = dev_net(skb->dev)->can.can_stats;
 	int err = -EINVAL;
 
 	if (skb->len == CAN_MTU) {
@@ -316,8 +306,8 @@ int can_send(struct sk_buff *skb, int loop)
 		netif_rx_ni(newskb);
 
 	/* update statistics */
-	can_stats.tx_frames++;
-	can_stats.tx_frames_delta++;
+	can_stats->tx_frames++;
+	can_stats->tx_frames_delta++;
 
 	return 0;
 
@@ -331,10 +321,11 @@ EXPORT_SYMBOL(can_send);
  * af_can rx path
  */
 
-static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev)
+static struct dev_rcv_lists *find_dev_rcv_lists(struct net *net,
+						struct net_device *dev)
 {
 	if (!dev)
-		return &can_rx_alldev_list;
+		return net->can.can_rx_alldev_list;
 	else
 		return (struct dev_rcv_lists *)dev->ml_priv;
 }
@@ -467,13 +458,14 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  *  -ENOMEM on missing cache mem to create subscription entry
  *  -ENODEV unknown device
  */
-int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
-		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident, struct sock *sk)
+int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
+		    canid_t mask, void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
 	struct dev_rcv_lists *d;
+	struct s_pstats *can_pstats = net->can.can_pstats;
 	int err = 0;
 
 	/* insert new receiver  (dev,canid,mask) -> (func,data) */
@@ -481,13 +473,16 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 	if (dev && dev->type != ARPHRD_CAN)
 		return -ENODEV;
 
+	if (dev && !net_eq(net, dev_net(dev)))
+		return -ENODEV;
+
 	r = kmem_cache_alloc(rcv_cache, GFP_KERNEL);
 	if (!r)
 		return -ENOMEM;
 
-	spin_lock(&can_rcvlists_lock);
+	spin_lock(&net->can.can_rcvlists_lock);
 
-	d = find_dev_rcv_lists(dev);
+	d = find_dev_rcv_lists(net, dev);
 	if (d) {
 		rl = find_rcv_list(&can_id, &mask, d);
 
@@ -502,15 +497,15 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		hlist_add_head_rcu(&r->list, rl);
 		d->entries++;
 
-		can_pstats.rcv_entries++;
-		if (can_pstats.rcv_entries_max < can_pstats.rcv_entries)
-			can_pstats.rcv_entries_max = can_pstats.rcv_entries;
+		can_pstats->rcv_entries++;
+		if (can_pstats->rcv_entries_max < can_pstats->rcv_entries)
+			can_pstats->rcv_entries_max = can_pstats->rcv_entries;
 	} else {
 		kmem_cache_free(rcv_cache, r);
 		err = -ENODEV;
 	}
 
-	spin_unlock(&can_rcvlists_lock);
+	spin_unlock(&net->can.can_rcvlists_lock);
 
 	return err;
 }
@@ -540,19 +535,24 @@ static void can_rx_delete_receiver(struct rcu_head *rp)
  * Description:
  *  Removes subscription entry depending on given (subscription) values.
  */
-void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
-		       void (*func)(struct sk_buff *, void *), void *data)
+void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
+		       canid_t mask, void (*func)(struct sk_buff *, void *),
+		       void *data)
 {
 	struct receiver *r = NULL;
 	struct hlist_head *rl;
+	struct s_pstats *can_pstats = net->can.can_pstats;
 	struct dev_rcv_lists *d;
 
 	if (dev && dev->type != ARPHRD_CAN)
 		return;
 
-	spin_lock(&can_rcvlists_lock);
+	if (dev && !net_eq(net, dev_net(dev)))
+		return;
+
+	spin_lock(&net->can.can_rcvlists_lock);
 
-	d = find_dev_rcv_lists(dev);
+	d = find_dev_rcv_lists(net, dev);
 	if (!d) {
 		pr_err("BUG: receive list not found for "
 		       "dev %s, id %03X, mask %03X\n",
@@ -588,8 +588,8 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	hlist_del_rcu(&r->list);
 	d->entries--;
 
-	if (can_pstats.rcv_entries > 0)
-		can_pstats.rcv_entries--;
+	if (can_pstats->rcv_entries > 0)
+		can_pstats->rcv_entries--;
 
 	/* remove device structure requested by NETDEV_UNREGISTER */
 	if (d->remove_on_zero_entries && !d->entries) {
@@ -598,7 +598,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	}
 
  out:
-	spin_unlock(&can_rcvlists_lock);
+	spin_unlock(&net->can.can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
 	if (r) {
@@ -683,11 +683,13 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb)
 static void can_receive(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dev_rcv_lists *d;
+	struct net *net = dev_net(dev);
+	struct s_stats *can_stats = net->can.can_stats;
 	int matches;
 
 	/* update statistics */
-	can_stats.rx_frames++;
-	can_stats.rx_frames_delta++;
+	can_stats->rx_frames++;
+	can_stats->rx_frames_delta++;
 
 	/* create non-zero unique skb identifier together with *skb */
 	while (!(can_skb_prv(skb)->skbcnt))
@@ -696,10 +698,10 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	rcu_read_lock();
 
 	/* deliver the packet to sockets listening on all devices */
-	matches = can_rcv_filter(&can_rx_alldev_list, skb);
+	matches = can_rcv_filter(net->can.can_rx_alldev_list, skb);
 
 	/* find receive list for this device */
-	d = find_dev_rcv_lists(dev);
+	d = find_dev_rcv_lists(net, dev);
 	if (d)
 		matches += can_rcv_filter(d, skb);
 
@@ -709,8 +711,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	consume_skb(skb);
 
 	if (matches > 0) {
-		can_stats.matches++;
-		can_stats.matches_delta++;
+		can_stats->matches++;
+		can_stats->matches_delta++;
 	}
 }
 
@@ -719,9 +721,6 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(!net_eq(dev_net(dev), &init_net)))
-		goto drop;
-
 	if (WARN_ONCE(dev->type != ARPHRD_CAN ||
 		      skb->len != CAN_MTU ||
 		      cfd->len > CAN_MAX_DLEN,
@@ -743,9 +742,6 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(!net_eq(dev_net(dev), &init_net)))
-		goto drop;
-
 	if (WARN_ONCE(dev->type != ARPHRD_CAN ||
 		      skb->len != CANFD_MTU ||
 		      cfd->len > CANFD_MAX_DLEN,
@@ -835,9 +831,6 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct dev_rcv_lists *d;
 
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
 	if (dev->type != ARPHRD_CAN)
 		return NOTIFY_DONE;
 
@@ -855,7 +848,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 		break;
 
 	case NETDEV_UNREGISTER:
-		spin_lock(&can_rcvlists_lock);
+		spin_lock(&dev_net(dev)->can.can_rcvlists_lock);
 
 		d = dev->ml_priv;
 		if (d) {
@@ -869,7 +862,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 			pr_err("can: notifier: receive list not found for dev "
 			       "%s\n", dev->name);
 
-		spin_unlock(&can_rcvlists_lock);
+		spin_unlock(&dev_net(dev)->can.can_rcvlists_lock);
 
 		break;
 	}
@@ -877,6 +870,59 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 	return NOTIFY_DONE;
 }
 
+static int can_pernet_init(struct net *net)
+{
+	net->can.can_rcvlists_lock =
+		__SPIN_LOCK_UNLOCKED(net->can.can_rcvlists_lock);
+	net->can.can_rx_alldev_list =
+		kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL);
+
+	net->can.can_stats = kzalloc(sizeof(struct s_stats), GFP_KERNEL);
+	net->can.can_pstats = kzalloc(sizeof(struct s_pstats), GFP_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROC_FS)) {
+		/* the statistics are updated every second (timer triggered) */
+		if (stats_timer) {
+			setup_timer(&net->can.can_stattimer, can_stat_update,
+				    (unsigned long)net);
+			mod_timer(&net->can.can_stattimer,
+				  round_jiffies(jiffies + HZ));
+		}
+		net->can.can_stats->jiffies_init = jiffies;
+		can_init_proc(net);
+	}
+
+	return 0;
+}
+
+static void can_pernet_exit(struct net *net)
+{
+	struct net_device *dev;
+
+	if (IS_ENABLED(CONFIG_PROC_FS)) {
+		can_remove_proc(net);
+		if (stats_timer)
+			del_timer_sync(&net->can.can_stattimer);
+	}
+
+	/* remove created dev_rcv_lists from still registered CAN devices */
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+			struct dev_rcv_lists *d = dev->ml_priv;
+
+			BUG_ON(d->entries);
+			kfree(d);
+			dev->ml_priv = NULL;
+		}
+	}
+	rcu_read_unlock();
+
+	kfree(net->can.can_rx_alldev_list);
+	kfree(net->can.can_stats);
+	kfree(net->can.can_pstats);
+}
+
 /*
  * af_can module init/exit functions
  */
@@ -902,6 +948,11 @@ static struct notifier_block can_netdev_notifier __read_mostly = {
 	.notifier_call = can_notifier,
 };
 
+static struct pernet_operations can_pernet_ops __read_mostly = {
+	.init = can_pernet_init,
+	.exit = can_pernet_exit,
+};
+
 static __init int can_init(void)
 {
 	/* check for correct padding to be able to use the structs similarly */
@@ -912,21 +963,12 @@ static __init int can_init(void)
 
 	pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
 
-	memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list));
-
 	rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver),
 				      0, 0, NULL);
 	if (!rcv_cache)
 		return -ENOMEM;
 
-	if (IS_ENABLED(CONFIG_PROC_FS)) {
-		if (stats_timer) {
-		/* the statistics are updated every second (timer triggered) */
-			setup_timer(&can_stattimer, can_stat_update, 0);
-			mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
-		}
-		can_init_proc();
-	}
+	register_pernet_subsys(&can_pernet_ops);
 
 	/* protocol register */
 	sock_register(&can_family_ops);
@@ -939,34 +981,13 @@ static __init int can_init(void)
 
 static __exit void can_exit(void)
 {
-	struct net_device *dev;
-
-	if (IS_ENABLED(CONFIG_PROC_FS)) {
-		if (stats_timer)
-			del_timer_sync(&can_stattimer);
-
-		can_remove_proc();
-	}
-
 	/* protocol unregister */
 	dev_remove_pack(&canfd_packet);
 	dev_remove_pack(&can_packet);
 	unregister_netdevice_notifier(&can_netdev_notifier);
 	sock_unregister(PF_CAN);
 
-	/* remove created dev_rcv_lists from still registered CAN devices */
-	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, dev) {
-		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
-
-			struct dev_rcv_lists *d = dev->ml_priv;
-
-			BUG_ON(d->entries);
-			kfree(d);
-			dev->ml_priv = NULL;
-		}
-	}
-	rcu_read_unlock();
+	unregister_pernet_subsys(&can_pernet_ops);
 
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index b86f5129e838..d0ef45bb2a72 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -110,18 +110,9 @@ struct s_pstats {
 	unsigned long rcv_entries_max;
 };
 
-/* receive filters subscribed for 'all' CAN devices */
-extern struct dev_rcv_lists can_rx_alldev_list;
-
 /* function prototypes for the CAN networklayer procfs (proc.c) */
-void can_init_proc(void);
-void can_remove_proc(void);
+void can_init_proc(struct net *net);
+void can_remove_proc(struct net *net);
 void can_stat_update(unsigned long data);
 
-/* structures and variables from af_can.c needed in proc.c for reading */
-extern struct timer_list can_stattimer;    /* timer for statistics update */
-extern struct s_stats    can_stats;        /* packet statistics */
-extern struct s_pstats   can_pstats;       /* receive list statistics */
-extern struct hlist_head can_rx_dev_list;  /* rx dispatcher structures */
-
 #endif /* AF_CAN_H */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 95d13b233c65..65432633a250 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1,7 +1,7 @@
 /*
  * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content
  *
- * Copyright (c) 2002-2016 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2017 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -77,7 +77,7 @@
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION "20161123"
+#define CAN_BCM_VERSION "20170425"
 
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -118,8 +118,6 @@ struct bcm_op {
 	struct net_device *rx_reg_dev;
 };
 
-static struct proc_dir_entry *proc_dir;
-
 struct bcm_sock {
 	struct sock sk;
 	int bound;
@@ -149,7 +147,8 @@ static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv)
 /*
  * procfs functions
  */
-static char *bcm_proc_getifname(char *result, int ifindex)
+#if IS_ENABLED(CONFIG_PROC_FS)
+static char *bcm_proc_getifname(struct net *net, char *result, int ifindex)
 {
 	struct net_device *dev;
 
@@ -157,7 +156,7 @@ static char *bcm_proc_getifname(char *result, int ifindex)
 		return "any";
 
 	rcu_read_lock();
-	dev = dev_get_by_index_rcu(&init_net, ifindex);
+	dev = dev_get_by_index_rcu(net, ifindex);
 	if (dev)
 		strcpy(result, dev->name);
 	else
@@ -170,7 +169,8 @@ static char *bcm_proc_getifname(char *result, int ifindex)
 static int bcm_proc_show(struct seq_file *m, void *v)
 {
 	char ifname[IFNAMSIZ];
-	struct sock *sk = (struct sock *)m->private;
+	struct net *net = m->private;
+	struct sock *sk = (struct sock *)PDE_DATA(m->file->f_inode);
 	struct bcm_sock *bo = bcm_sk(sk);
 	struct bcm_op *op;
 
@@ -178,7 +178,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, " / sk %pK", sk);
 	seq_printf(m, " / bo %pK", bo);
 	seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs);
-	seq_printf(m, " / bound %s", bcm_proc_getifname(ifname, bo->ifindex));
+	seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex));
 	seq_printf(m, " <<<\n");
 
 	list_for_each_entry(op, &bo->rx_ops, list) {
@@ -190,7 +190,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 			continue;
 
 		seq_printf(m, "rx_op: %03X %-5s ", op->can_id,
-			   bcm_proc_getifname(ifname, op->ifindex));
+			   bcm_proc_getifname(net, ifname, op->ifindex));
 
 		if (op->flags & CAN_FD_FRAME)
 			seq_printf(m, "(%u)", op->nframes);
@@ -219,7 +219,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 	list_for_each_entry(op, &bo->tx_ops, list) {
 
 		seq_printf(m, "tx_op: %03X %s ", op->can_id,
-			   bcm_proc_getifname(ifname, op->ifindex));
+			   bcm_proc_getifname(net, ifname, op->ifindex));
 
 		if (op->flags & CAN_FD_FRAME)
 			seq_printf(m, "(%u) ", op->nframes);
@@ -242,7 +242,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 static int bcm_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, bcm_proc_show, PDE_DATA(inode));
+	return single_open_net(inode, file, bcm_proc_show);
 }
 
 static const struct file_operations bcm_proc_fops = {
@@ -252,6 +252,7 @@ static const struct file_operations bcm_proc_fops = {
 	.llseek		= seq_lseek,
 	.release	= single_release,
 };
+#endif /* CONFIG_PROC_FS */
 
 /*
  * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface
@@ -267,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op)
 	if (!op->ifindex)
 		return;
 
-	dev = dev_get_by_index(&init_net, op->ifindex);
+	dev = dev_get_by_index(sock_net(op->sk), op->ifindex);
 	if (!dev) {
 		/* RFC: should this bcm_op remove itself here? */
 		return;
@@ -764,8 +765,8 @@ static void bcm_remove_op(struct bcm_op *op)
 static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 {
 	if (op->rx_reg_dev == dev) {
-		can_rx_unregister(dev, op->can_id, REGMASK(op->can_id),
-				  bcm_rx_handler, op);
+		can_rx_unregister(dev_net(dev), dev, op->can_id,
+				  REGMASK(op->can_id), bcm_rx_handler, op);
 
 		/* mark as removed subscription */
 		op->rx_reg_dev = NULL;
@@ -800,7 +801,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 				if (op->rx_reg_dev) {
 					struct net_device *dev;
 
-					dev = dev_get_by_index(&init_net,
+					dev = dev_get_by_index(sock_net(op->sk),
 							       op->ifindex);
 					if (dev) {
 						bcm_rx_unreg(dev, op);
@@ -808,7 +809,8 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 					}
 				}
 			} else
-				can_rx_unregister(NULL, op->can_id,
+				can_rx_unregister(sock_net(op->sk), NULL,
+						  op->can_id,
 						  REGMASK(op->can_id),
 						  bcm_rx_handler, op);
 
@@ -1220,9 +1222,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (ifindex) {
 			struct net_device *dev;
 
-			dev = dev_get_by_index(&init_net, ifindex);
+			dev = dev_get_by_index(sock_net(sk), ifindex);
 			if (dev) {
-				err = can_rx_register(dev, op->can_id,
+				err = can_rx_register(sock_net(sk), dev,
+						      op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
 						      "bcm", sk);
@@ -1232,7 +1235,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			}
 
 		} else
-			err = can_rx_register(NULL, op->can_id,
+			err = can_rx_register(sock_net(sk), NULL, op->can_id,
 					      REGMASK(op->can_id),
 					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
@@ -1272,7 +1275,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk,
 		return err;
 	}
 
-	dev = dev_get_by_index(&init_net, ifindex);
+	dev = dev_get_by_index(sock_net(sk), ifindex);
 	if (!dev) {
 		kfree_skb(skb);
 		return -ENODEV;
@@ -1337,7 +1340,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		if (ifindex) {
 			struct net_device *dev;
 
-			dev = dev_get_by_index(&init_net, ifindex);
+			dev = dev_get_by_index(sock_net(sk), ifindex);
 			if (!dev)
 				return -ENODEV;
 
@@ -1418,7 +1421,7 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg,
 	struct bcm_op *op;
 	int notify_enodev = 0;
 
-	if (!net_eq(dev_net(dev), &init_net))
+	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return NOTIFY_DONE;
 
 	if (dev->type != ARPHRD_CAN)
@@ -1490,6 +1493,7 @@ static int bcm_init(struct sock *sk)
 static int bcm_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
 	struct bcm_sock *bo;
 	struct bcm_op *op, *next;
 
@@ -1521,23 +1525,25 @@ static int bcm_release(struct socket *sock)
 			if (op->rx_reg_dev) {
 				struct net_device *dev;
 
-				dev = dev_get_by_index(&init_net, op->ifindex);
+				dev = dev_get_by_index(net, op->ifindex);
 				if (dev) {
 					bcm_rx_unreg(dev, op);
 					dev_put(dev);
 				}
 			}
 		} else
-			can_rx_unregister(NULL, op->can_id,
+			can_rx_unregister(net, NULL, op->can_id,
 					  REGMASK(op->can_id),
 					  bcm_rx_handler, op);
 
 		bcm_remove_op(op);
 	}
 
+#if IS_ENABLED(CONFIG_PROC_FS)
 	/* remove procfs entry */
-	if (proc_dir && bo->bcm_proc_read)
-		remove_proc_entry(bo->procname, proc_dir);
+	if (net->can.bcmproc_dir && bo->bcm_proc_read)
+		remove_proc_entry(bo->procname, net->can.bcmproc_dir);
+#endif /* CONFIG_PROC_FS */
 
 	/* remove device reference */
 	if (bo->bound) {
@@ -1560,6 +1566,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
 	struct sock *sk = sock->sk;
 	struct bcm_sock *bo = bcm_sk(sk);
+	struct net *net = sock_net(sk);
 	int ret = 0;
 
 	if (len < sizeof(*addr))
@@ -1576,7 +1583,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 	if (addr->can_ifindex) {
 		struct net_device *dev;
 
-		dev = dev_get_by_index(&init_net, addr->can_ifindex);
+		dev = dev_get_by_index(net, addr->can_ifindex);
 		if (!dev) {
 			ret = -ENODEV;
 			goto fail;
@@ -1595,17 +1602,19 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 		bo->ifindex = 0;
 	}
 
-	if (proc_dir) {
+#if IS_ENABLED(CONFIG_PROC_FS)
+	if (net->can.bcmproc_dir) {
 		/* unique socket address as filename */
 		sprintf(bo->procname, "%lu", sock_i_ino(sk));
 		bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
-						     proc_dir,
+						     net->can.bcmproc_dir,
 						     &bcm_proc_fops, sk);
 		if (!bo->bcm_proc_read) {
 			ret = -ENOMEM;
 			goto fail;
 		}
 	}
+#endif /* CONFIG_PROC_FS */
 
 	bo->bound = 1;
 
@@ -1686,6 +1695,30 @@ static const struct can_proto bcm_can_proto = {
 	.prot       = &bcm_proto,
 };
 
+static int canbcm_pernet_init(struct net *net)
+{
+#if IS_ENABLED(CONFIG_PROC_FS)
+	/* create /proc/net/can-bcm directory */
+	net->can.bcmproc_dir = proc_net_mkdir(net, "can-bcm", net->proc_net);
+#endif /* CONFIG_PROC_FS */
+
+	return 0;
+}
+
+static void canbcm_pernet_exit(struct net *net)
+{
+#if IS_ENABLED(CONFIG_PROC_FS)
+	/* remove /proc/net/can-bcm directory */
+	if (net->can.bcmproc_dir)
+		remove_proc_entry("can-bcm", net->proc_net);
+#endif /* CONFIG_PROC_FS */
+}
+
+static struct pernet_operations canbcm_pernet_ops __read_mostly = {
+	.init = canbcm_pernet_init,
+	.exit = canbcm_pernet_exit,
+};
+
 static int __init bcm_module_init(void)
 {
 	int err;
@@ -1698,17 +1731,14 @@ static int __init bcm_module_init(void)
 		return err;
 	}
 
-	/* create /proc/net/can-bcm directory */
-	proc_dir = proc_mkdir("can-bcm", init_net.proc_net);
+	register_pernet_subsys(&canbcm_pernet_ops);
 	return 0;
 }
 
 static void __exit bcm_module_exit(void)
 {
 	can_proto_unregister(&bcm_can_proto);
-
-	if (proc_dir)
-		remove_proc_entry("can-bcm", init_net.proc_net);
+	unregister_pernet_subsys(&canbcm_pernet_ops);
 }
 
 module_init(bcm_module_init);
diff --git a/net/can/gw.c b/net/can/gw.c
index 7056a1a2bb70..29748d844c3f 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -1,7 +1,7 @@
 /*
  * gw.c - CAN frame Gateway/Router/Bridge with netlink interface
  *
- * Copyright (c) 2011 Volkswagen Group Electronic Research
+ * Copyright (c) 2017 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -59,7 +59,7 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
-#define CAN_GW_VERSION "20130117"
+#define CAN_GW_VERSION "20170425"
 #define CAN_GW_NAME "can-gw"
 
 MODULE_DESCRIPTION("PF_CAN netlink gateway");
@@ -79,9 +79,7 @@ MODULE_PARM_DESC(max_hops,
 		 __stringify(CGW_MAX_HOPS) " hops, "
 		 "default: " __stringify(CGW_DEFAULT_HOPS) ")");
 
-static HLIST_HEAD(cgw_list);
 static struct notifier_block notifier;
-
 static struct kmem_cache *cgw_cache __read_mostly;
 
 /* structure that contains the (on-the-fly) CAN frame modifications */
@@ -438,16 +436,16 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 		gwj->handled_frames++;
 }
 
-static inline int cgw_register_filter(struct cgw_job *gwj)
+static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj)
 {
-	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
+	return can_rx_register(net, gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
 			       gwj, "gw", NULL);
 }
 
-static inline void cgw_unregister_filter(struct cgw_job *gwj)
+static inline void cgw_unregister_filter(struct net *net, struct cgw_job *gwj)
 {
-	can_rx_unregister(gwj->src.dev, gwj->ccgw.filter.can_id,
+	can_rx_unregister(net, gwj->src.dev, gwj->ccgw.filter.can_id,
 			  gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj);
 }
 
@@ -455,9 +453,8 @@ static int cgw_notifier(struct notifier_block *nb,
 			unsigned long msg, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
 
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
 	if (dev->type != ARPHRD_CAN)
 		return NOTIFY_DONE;
 
@@ -468,11 +465,11 @@ static int cgw_notifier(struct notifier_block *nb,
 
 		ASSERT_RTNL();
 
-		hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) {
+		hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) {
 
 			if (gwj->src.dev == dev || gwj->dst.dev == dev) {
 				hlist_del(&gwj->list);
-				cgw_unregister_filter(gwj);
+				cgw_unregister_filter(net, gwj);
 				kmem_cache_free(cgw_cache, gwj);
 			}
 		}
@@ -592,12 +589,13 @@ cancel:
 /* Dump information about all CAN gateway jobs, in response to RTM_GETROUTE */
 static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct net *net = sock_net(skb->sk);
 	struct cgw_job *gwj = NULL;
 	int idx = 0;
 	int s_idx = cb->args[0];
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(gwj, &cgw_list, list) {
+	hlist_for_each_entry_rcu(gwj, &net->can.cgw_list, list) {
 		if (idx < s_idx)
 			goto cont;
 
@@ -641,7 +639,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 	memset(mod, 0, sizeof(*mod));
 
 	err = nlmsg_parse(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX,
-			  cgw_policy);
+			  cgw_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -809,8 +807,10 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 	return 0;
 }
 
-static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
+static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
+	struct net *net = sock_net(skb->sk);
 	struct rtcanmsg *r;
 	struct cgw_job *gwj;
 	struct cf_mod mod;
@@ -841,7 +841,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 		ASSERT_RTNL();
 
 		/* check for updating an existing job with identical uid */
-		hlist_for_each_entry(gwj, &cgw_list, list) {
+		hlist_for_each_entry(gwj, &net->can.cgw_list, list) {
 
 			if (gwj->mod.uid != mod.uid)
 				continue;
@@ -879,7 +879,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 
 	err = -ENODEV;
 
-	gwj->src.dev = __dev_get_by_index(&init_net, gwj->ccgw.src_idx);
+	gwj->src.dev = __dev_get_by_index(net, gwj->ccgw.src_idx);
 
 	if (!gwj->src.dev)
 		goto out;
@@ -887,7 +887,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	if (gwj->src.dev->type != ARPHRD_CAN)
 		goto out;
 
-	gwj->dst.dev = __dev_get_by_index(&init_net, gwj->ccgw.dst_idx);
+	gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx);
 
 	if (!gwj->dst.dev)
 		goto out;
@@ -897,9 +897,9 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 
 	ASSERT_RTNL();
 
-	err = cgw_register_filter(gwj);
+	err = cgw_register_filter(net, gwj);
 	if (!err)
-		hlist_add_head_rcu(&gwj->list, &cgw_list);
+		hlist_add_head_rcu(&gwj->list, &net->can.cgw_list);
 out:
 	if (err)
 		kmem_cache_free(cgw_cache, gwj);
@@ -907,22 +907,24 @@ out:
 	return err;
 }
 
-static void cgw_remove_all_jobs(void)
+static void cgw_remove_all_jobs(struct net *net)
 {
 	struct cgw_job *gwj = NULL;
 	struct hlist_node *nx;
 
 	ASSERT_RTNL();
 
-	hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) {
+	hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) {
 		hlist_del(&gwj->list);
-		cgw_unregister_filter(gwj);
+		cgw_unregister_filter(net, gwj);
 		kmem_cache_free(cgw_cache, gwj);
 	}
 }
 
-static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
+	struct net *net = sock_net(skb->sk);
 	struct cgw_job *gwj = NULL;
 	struct hlist_node *nx;
 	struct rtcanmsg *r;
@@ -951,7 +953,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	/* two interface indices both set to 0 => remove all entries */
 	if (!ccgw.src_idx && !ccgw.dst_idx) {
-		cgw_remove_all_jobs();
+		cgw_remove_all_jobs(net);
 		return 0;
 	}
 
@@ -960,7 +962,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
 	ASSERT_RTNL();
 
 	/* remove only the first matching entry */
-	hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) {
+	hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) {
 
 		if (gwj->flags != r->flags)
 			continue;
@@ -983,7 +985,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
 			continue;
 
 		hlist_del(&gwj->list);
-		cgw_unregister_filter(gwj);
+		cgw_unregister_filter(net, gwj);
 		kmem_cache_free(cgw_cache, gwj);
 		err = 0;
 		break;
@@ -992,6 +994,24 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
 	return err;
 }
 
+static int __net_init cangw_pernet_init(struct net *net)
+{
+	INIT_HLIST_HEAD(&net->can.cgw_list);
+	return 0;
+}
+
+static void __net_exit cangw_pernet_exit(struct net *net)
+{
+	rtnl_lock();
+	cgw_remove_all_jobs(net);
+	rtnl_unlock();
+}
+
+static struct pernet_operations cangw_pernet_ops = {
+	.init = cangw_pernet_init,
+	.exit = cangw_pernet_exit,
+};
+
 static __init int cgw_module_init(void)
 {
 	/* sanitize given module parameter */
@@ -1000,6 +1020,7 @@ static __init int cgw_module_init(void)
 	pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n",
 		max_hops);
 
+	register_pernet_subsys(&cangw_pernet_ops);
 	cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job),
 				      0, 0, NULL);
 
@@ -1029,10 +1050,7 @@ static __exit void cgw_module_exit(void)
 
 	unregister_netdevice_notifier(&notifier);
 
-	rtnl_lock();
-	cgw_remove_all_jobs();
-	rtnl_unlock();
-
+	unregister_pernet_subsys(&cangw_pernet_ops);
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 
 	kmem_cache_destroy(cgw_cache);
diff --git a/net/can/proc.c b/net/can/proc.c
index 85ef7bb0f176..83045f00c63c 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -62,17 +62,6 @@
 #define CAN_PROC_RCVLIST_EFF "rcvlist_eff"
 #define CAN_PROC_RCVLIST_ERR "rcvlist_err"
 
-static struct proc_dir_entry *can_dir;
-static struct proc_dir_entry *pde_version;
-static struct proc_dir_entry *pde_stats;
-static struct proc_dir_entry *pde_reset_stats;
-static struct proc_dir_entry *pde_rcvlist_all;
-static struct proc_dir_entry *pde_rcvlist_fil;
-static struct proc_dir_entry *pde_rcvlist_inv;
-static struct proc_dir_entry *pde_rcvlist_sff;
-static struct proc_dir_entry *pde_rcvlist_eff;
-static struct proc_dir_entry *pde_rcvlist_err;
-
 static int user_reset;
 
 static const char rx_list_name[][8] = {
@@ -86,21 +75,23 @@ static const char rx_list_name[][8] = {
  * af_can statistics stuff
  */
 
-static void can_init_stats(void)
+static void can_init_stats(struct net *net)
 {
+	struct s_stats *can_stats = net->can.can_stats;
+	struct s_pstats *can_pstats = net->can.can_pstats;
 	/*
 	 * This memset function is called from a timer context (when
 	 * can_stattimer is active which is the default) OR in a process
 	 * context (reading the proc_fs when can_stattimer is disabled).
 	 */
-	memset(&can_stats, 0, sizeof(can_stats));
-	can_stats.jiffies_init = jiffies;
+	memset(can_stats, 0, sizeof(struct s_stats));
+	can_stats->jiffies_init = jiffies;
 
-	can_pstats.stats_reset++;
+	can_pstats->stats_reset++;
 
 	if (user_reset) {
 		user_reset = 0;
-		can_pstats.user_reset++;
+		can_pstats->user_reset++;
 	}
 }
 
@@ -126,64 +117,66 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif,
 
 void can_stat_update(unsigned long data)
 {
+	struct net *net = (struct net *)data;
+	struct s_stats *can_stats = net->can.can_stats;
 	unsigned long j = jiffies; /* snapshot */
 
 	/* restart counting in timer context on user request */
 	if (user_reset)
-		can_init_stats();
+		can_init_stats(net);
 
 	/* restart counting on jiffies overflow */
-	if (j < can_stats.jiffies_init)
-		can_init_stats();
+	if (j < can_stats->jiffies_init)
+		can_init_stats(net);
 
 	/* prevent overflow in calc_rate() */
-	if (can_stats.rx_frames > (ULONG_MAX / HZ))
-		can_init_stats();
+	if (can_stats->rx_frames > (ULONG_MAX / HZ))
+		can_init_stats(net);
 
 	/* prevent overflow in calc_rate() */
-	if (can_stats.tx_frames > (ULONG_MAX / HZ))
-		can_init_stats();
+	if (can_stats->tx_frames > (ULONG_MAX / HZ))
+		can_init_stats(net);
 
 	/* matches overflow - very improbable */
-	if (can_stats.matches > (ULONG_MAX / 100))
-		can_init_stats();
+	if (can_stats->matches > (ULONG_MAX / 100))
+		can_init_stats(net);
 
 	/* calc total values */
-	if (can_stats.rx_frames)
-		can_stats.total_rx_match_ratio = (can_stats.matches * 100) /
-			can_stats.rx_frames;
+	if (can_stats->rx_frames)
+		can_stats->total_rx_match_ratio = (can_stats->matches * 100) /
+			can_stats->rx_frames;
 
-	can_stats.total_tx_rate = calc_rate(can_stats.jiffies_init, j,
-					    can_stats.tx_frames);
-	can_stats.total_rx_rate = calc_rate(can_stats.jiffies_init, j,
-					    can_stats.rx_frames);
+	can_stats->total_tx_rate = calc_rate(can_stats->jiffies_init, j,
+					    can_stats->tx_frames);
+	can_stats->total_rx_rate = calc_rate(can_stats->jiffies_init, j,
+					    can_stats->rx_frames);
 
 	/* calc current values */
-	if (can_stats.rx_frames_delta)
-		can_stats.current_rx_match_ratio =
-			(can_stats.matches_delta * 100) /
-			can_stats.rx_frames_delta;
+	if (can_stats->rx_frames_delta)
+		can_stats->current_rx_match_ratio =
+			(can_stats->matches_delta * 100) /
+			can_stats->rx_frames_delta;
 
-	can_stats.current_tx_rate = calc_rate(0, HZ, can_stats.tx_frames_delta);
-	can_stats.current_rx_rate = calc_rate(0, HZ, can_stats.rx_frames_delta);
+	can_stats->current_tx_rate = calc_rate(0, HZ, can_stats->tx_frames_delta);
+	can_stats->current_rx_rate = calc_rate(0, HZ, can_stats->rx_frames_delta);
 
 	/* check / update maximum values */
-	if (can_stats.max_tx_rate < can_stats.current_tx_rate)
-		can_stats.max_tx_rate = can_stats.current_tx_rate;
+	if (can_stats->max_tx_rate < can_stats->current_tx_rate)
+		can_stats->max_tx_rate = can_stats->current_tx_rate;
 
-	if (can_stats.max_rx_rate < can_stats.current_rx_rate)
-		can_stats.max_rx_rate = can_stats.current_rx_rate;
+	if (can_stats->max_rx_rate < can_stats->current_rx_rate)
+		can_stats->max_rx_rate = can_stats->current_rx_rate;
 
-	if (can_stats.max_rx_match_ratio < can_stats.current_rx_match_ratio)
-		can_stats.max_rx_match_ratio = can_stats.current_rx_match_ratio;
+	if (can_stats->max_rx_match_ratio < can_stats->current_rx_match_ratio)
+		can_stats->max_rx_match_ratio = can_stats->current_rx_match_ratio;
 
 	/* clear values for 'current rate' calculation */
-	can_stats.tx_frames_delta = 0;
-	can_stats.rx_frames_delta = 0;
-	can_stats.matches_delta   = 0;
+	can_stats->tx_frames_delta = 0;
+	can_stats->rx_frames_delta = 0;
+	can_stats->matches_delta   = 0;
 
 	/* restart timer (one second) */
-	mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
+	mod_timer(&net->can.can_stattimer, round_jiffies(jiffies + HZ));
 }
 
 /*
@@ -217,57 +210,61 @@ static void can_print_recv_banner(struct seq_file *m)
 
 static int can_stats_proc_show(struct seq_file *m, void *v)
 {
+	struct net *net = m->private;
+	struct s_stats *can_stats = net->can.can_stats;
+	struct s_pstats *can_pstats = net->can.can_pstats;
+
 	seq_putc(m, '\n');
-	seq_printf(m, " %8ld transmitted frames (TXF)\n", can_stats.tx_frames);
-	seq_printf(m, " %8ld received frames (RXF)\n", can_stats.rx_frames);
-	seq_printf(m, " %8ld matched frames (RXMF)\n", can_stats.matches);
+	seq_printf(m, " %8ld transmitted frames (TXF)\n", can_stats->tx_frames);
+	seq_printf(m, " %8ld received frames (RXF)\n", can_stats->rx_frames);
+	seq_printf(m, " %8ld matched frames (RXMF)\n", can_stats->matches);
 
 	seq_putc(m, '\n');
 
-	if (can_stattimer.function == can_stat_update) {
+	if (net->can.can_stattimer.function == can_stat_update) {
 		seq_printf(m, " %8ld %% total match ratio (RXMR)\n",
-				can_stats.total_rx_match_ratio);
+				can_stats->total_rx_match_ratio);
 
 		seq_printf(m, " %8ld frames/s total tx rate (TXR)\n",
-				can_stats.total_tx_rate);
+				can_stats->total_tx_rate);
 		seq_printf(m, " %8ld frames/s total rx rate (RXR)\n",
-				can_stats.total_rx_rate);
+				can_stats->total_rx_rate);
 
 		seq_putc(m, '\n');
 
 		seq_printf(m, " %8ld %% current match ratio (CRXMR)\n",
-				can_stats.current_rx_match_ratio);
+				can_stats->current_rx_match_ratio);
 
 		seq_printf(m, " %8ld frames/s current tx rate (CTXR)\n",
-				can_stats.current_tx_rate);
+				can_stats->current_tx_rate);
 		seq_printf(m, " %8ld frames/s current rx rate (CRXR)\n",
-				can_stats.current_rx_rate);
+				can_stats->current_rx_rate);
 
 		seq_putc(m, '\n');
 
 		seq_printf(m, " %8ld %% max match ratio (MRXMR)\n",
-				can_stats.max_rx_match_ratio);
+				can_stats->max_rx_match_ratio);
 
 		seq_printf(m, " %8ld frames/s max tx rate (MTXR)\n",
-				can_stats.max_tx_rate);
+				can_stats->max_tx_rate);
 		seq_printf(m, " %8ld frames/s max rx rate (MRXR)\n",
-				can_stats.max_rx_rate);
+				can_stats->max_rx_rate);
 
 		seq_putc(m, '\n');
 	}
 
 	seq_printf(m, " %8ld current receive list entries (CRCV)\n",
-			can_pstats.rcv_entries);
+			can_pstats->rcv_entries);
 	seq_printf(m, " %8ld maximum receive list entries (MRCV)\n",
-			can_pstats.rcv_entries_max);
+			can_pstats->rcv_entries_max);
 
-	if (can_pstats.stats_reset)
+	if (can_pstats->stats_reset)
 		seq_printf(m, "\n %8ld statistic resets (STR)\n",
-				can_pstats.stats_reset);
+				can_pstats->stats_reset);
 
-	if (can_pstats.user_reset)
+	if (can_pstats->user_reset)
 		seq_printf(m, " %8ld user statistic resets (USTR)\n",
-				can_pstats.user_reset);
+				can_pstats->user_reset);
 
 	seq_putc(m, '\n');
 	return 0;
@@ -275,7 +272,7 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
 
 static int can_stats_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_stats_proc_show, NULL);
+	return single_open_net(inode, file, can_stats_proc_show);
 }
 
 static const struct file_operations can_stats_proc_fops = {
@@ -288,25 +285,28 @@ static const struct file_operations can_stats_proc_fops = {
 
 static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 {
+	struct net *net = m->private;
+	struct s_pstats *can_pstats = net->can.can_pstats;
+	struct s_stats *can_stats = net->can.can_stats;
+
 	user_reset = 1;
 
-	if (can_stattimer.function == can_stat_update) {
+	if (net->can.can_stattimer.function == can_stat_update) {
 		seq_printf(m, "Scheduled statistic reset #%ld.\n",
-				can_pstats.stats_reset + 1);
-
+				can_pstats->stats_reset + 1);
 	} else {
-		if (can_stats.jiffies_init != jiffies)
-			can_init_stats();
+		if (can_stats->jiffies_init != jiffies)
+			can_init_stats(net);
 
 		seq_printf(m, "Performed statistic reset #%ld.\n",
-				can_pstats.stats_reset);
+				can_pstats->stats_reset);
 	}
 	return 0;
 }
 
 static int can_reset_stats_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_reset_stats_proc_show, NULL);
+	return single_open_net(inode, file, can_reset_stats_proc_show);
 }
 
 static const struct file_operations can_reset_stats_proc_fops = {
@@ -325,7 +325,7 @@ static int can_version_proc_show(struct seq_file *m, void *v)
 
 static int can_version_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_version_proc_show, NULL);
+	return single_open_net(inode, file, can_version_proc_show);
 }
 
 static const struct file_operations can_version_proc_fops = {
@@ -351,20 +351,21 @@ static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
 static int can_rcvlist_proc_show(struct seq_file *m, void *v)
 {
 	/* double cast to prevent GCC warning */
-	int idx = (int)(long)m->private;
+	int idx = (int)(long)PDE_DATA(m->file->f_inode);
 	struct net_device *dev;
 	struct dev_rcv_lists *d;
+	struct net *net = m->private;
 
 	seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]);
 
 	rcu_read_lock();
 
 	/* receive list for 'all' CAN devices (dev == NULL) */
-	d = &can_rx_alldev_list;
+	d = net->can.can_rx_alldev_list;
 	can_rcvlist_proc_show_one(m, idx, NULL, d);
 
 	/* receive list for registered CAN devices */
-	for_each_netdev_rcu(&init_net, dev) {
+	for_each_netdev_rcu(net, dev) {
 		if (dev->type == ARPHRD_CAN && dev->ml_priv)
 			can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv);
 	}
@@ -377,7 +378,7 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v)
 
 static int can_rcvlist_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_rcvlist_proc_show, PDE_DATA(inode));
+	return single_open_net(inode, file, can_rcvlist_proc_show);
 }
 
 static const struct file_operations can_rcvlist_proc_fops = {
@@ -417,6 +418,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 {
 	struct net_device *dev;
 	struct dev_rcv_lists *d;
+	struct net *net = m->private;
 
 	/* RX_SFF */
 	seq_puts(m, "\nreceive list 'rx_sff':\n");
@@ -424,11 +426,11 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 	rcu_read_lock();
 
 	/* sff receive list for 'all' CAN devices (dev == NULL) */
-	d = &can_rx_alldev_list;
+	d = net->can.can_rx_alldev_list;
 	can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff));
 
 	/* sff receive list for registered CAN devices */
-	for_each_netdev_rcu(&init_net, dev) {
+	for_each_netdev_rcu(net, dev) {
 		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
 			d = dev->ml_priv;
 			can_rcvlist_proc_show_array(m, dev, d->rx_sff,
@@ -444,7 +446,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 
 static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_rcvlist_sff_proc_show, NULL);
+	return single_open_net(inode, file, can_rcvlist_sff_proc_show);
 }
 
 static const struct file_operations can_rcvlist_sff_proc_fops = {
@@ -460,6 +462,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 {
 	struct net_device *dev;
 	struct dev_rcv_lists *d;
+	struct net *net = m->private;
 
 	/* RX_EFF */
 	seq_puts(m, "\nreceive list 'rx_eff':\n");
@@ -467,11 +470,11 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 	rcu_read_lock();
 
 	/* eff receive list for 'all' CAN devices (dev == NULL) */
-	d = &can_rx_alldev_list;
+	d = net->can.can_rx_alldev_list;
 	can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff));
 
 	/* eff receive list for registered CAN devices */
-	for_each_netdev_rcu(&init_net, dev) {
+	for_each_netdev_rcu(net, dev) {
 		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
 			d = dev->ml_priv;
 			can_rcvlist_proc_show_array(m, dev, d->rx_eff,
@@ -487,7 +490,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 
 static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_rcvlist_eff_proc_show, NULL);
+	return single_open_net(inode, file, can_rcvlist_eff_proc_show);
 }
 
 static const struct file_operations can_rcvlist_eff_proc_fops = {
@@ -499,81 +502,85 @@ static const struct file_operations can_rcvlist_eff_proc_fops = {
 };
 
 /*
- * proc utility functions
- */
-
-static void can_remove_proc_readentry(const char *name)
-{
-	if (can_dir)
-		remove_proc_entry(name, can_dir);
-}
-
-/*
  * can_init_proc - create main CAN proc directory and procfs entries
  */
-void can_init_proc(void)
+void can_init_proc(struct net *net)
 {
 	/* create /proc/net/can directory */
-	can_dir = proc_mkdir("can", init_net.proc_net);
+	net->can.proc_dir = proc_net_mkdir(net, "can", net->proc_net);
 
-	if (!can_dir) {
-		pr_info("can: failed to create /proc/net/can.\n");
+	if (!net->can.proc_dir) {
+		printk(KERN_INFO "can: failed to create /proc/net/can . "
+			   "CONFIG_PROC_FS missing?\n");
 		return;
 	}
 
 	/* own procfs entries from the AF_CAN core */
-	pde_version     = proc_create(CAN_PROC_VERSION, 0644, can_dir,
-				      &can_version_proc_fops);
-	pde_stats       = proc_create(CAN_PROC_STATS, 0644, can_dir,
-				      &can_stats_proc_fops);
-	pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644, can_dir,
-				      &can_reset_stats_proc_fops);
-	pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_ERR);
-	pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_ALL);
-	pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_FIL);
-	pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_INV);
-	pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
-				      &can_rcvlist_eff_proc_fops);
-	pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir,
-				      &can_rcvlist_sff_proc_fops);
+	net->can.pde_version     = proc_create(CAN_PROC_VERSION, 0644,
+					       net->can.proc_dir,
+					       &can_version_proc_fops);
+	net->can.pde_stats       = proc_create(CAN_PROC_STATS, 0644,
+					       net->can.proc_dir,
+					       &can_stats_proc_fops);
+	net->can.pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644,
+					       net->can.proc_dir,
+					       &can_reset_stats_proc_fops);
+	net->can.pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_ERR);
+	net->can.pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_ALL);
+	net->can.pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_FIL);
+	net->can.pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_INV);
+	net->can.pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644,
+					       net->can.proc_dir,
+					       &can_rcvlist_eff_proc_fops);
+	net->can.pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644,
+					       net->can.proc_dir,
+					       &can_rcvlist_sff_proc_fops);
 }
 
 /*
  * can_remove_proc - remove procfs entries and main CAN proc directory
  */
-void can_remove_proc(void)
+void can_remove_proc(struct net *net)
 {
-	if (pde_version)
-		can_remove_proc_readentry(CAN_PROC_VERSION);
+	if (net->can.pde_version)
+		remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir);
 
-	if (pde_stats)
-		can_remove_proc_readentry(CAN_PROC_STATS);
+	if (net->can.pde_stats)
+		remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
 
-	if (pde_reset_stats)
-		can_remove_proc_readentry(CAN_PROC_RESET_STATS);
+	if (net->can.pde_reset_stats)
+		remove_proc_entry(CAN_PROC_RESET_STATS, net->can.proc_dir);
 
-	if (pde_rcvlist_err)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_ERR);
+	if (net->can.pde_rcvlist_err)
+		remove_proc_entry(CAN_PROC_RCVLIST_ERR, net->can.proc_dir);
 
-	if (pde_rcvlist_all)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_ALL);
+	if (net->can.pde_rcvlist_all)
+		remove_proc_entry(CAN_PROC_RCVLIST_ALL, net->can.proc_dir);
 
-	if (pde_rcvlist_fil)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_FIL);
+	if (net->can.pde_rcvlist_fil)
+		remove_proc_entry(CAN_PROC_RCVLIST_FIL, net->can.proc_dir);
 
-	if (pde_rcvlist_inv)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_INV);
+	if (net->can.pde_rcvlist_inv)
+		remove_proc_entry(CAN_PROC_RCVLIST_INV, net->can.proc_dir);
 
-	if (pde_rcvlist_eff)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_EFF);
+	if (net->can.pde_rcvlist_eff)
+		remove_proc_entry(CAN_PROC_RCVLIST_EFF, net->can.proc_dir);
 
-	if (pde_rcvlist_sff)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_SFF);
+	if (net->can.pde_rcvlist_sff)
+		remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
 
-	if (can_dir)
-		remove_proc_entry("can", init_net.proc_net);
+	if (net->can.proc_dir)
+		remove_proc_entry("can", net->proc_net);
 }
diff --git a/net/can/raw.c b/net/can/raw.c
index 6dc546a06673..864c80dbdb72 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -181,20 +181,21 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
 		kfree_skb(skb);
 }
 
-static int raw_enable_filters(struct net_device *dev, struct sock *sk,
-			      struct can_filter *filter, int count)
+static int raw_enable_filters(struct net *net, struct net_device *dev,
+			      struct sock *sk, struct can_filter *filter,
+			      int count)
 {
 	int err = 0;
 	int i;
 
 	for (i = 0; i < count; i++) {
-		err = can_rx_register(dev, filter[i].can_id,
+		err = can_rx_register(net, dev, filter[i].can_id,
 				      filter[i].can_mask,
 				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
-				can_rx_unregister(dev, filter[i].can_id,
+				can_rx_unregister(net, dev, filter[i].can_id,
 						  filter[i].can_mask,
 						  raw_rcv, sk);
 			break;
@@ -204,57 +205,62 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	return err;
 }
 
-static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
-				can_err_mask_t err_mask)
+static int raw_enable_errfilter(struct net *net, struct net_device *dev,
+				struct sock *sk, can_err_mask_t err_mask)
 {
 	int err = 0;
 
 	if (err_mask)
-		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
+		err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG,
 				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }
 
-static void raw_disable_filters(struct net_device *dev, struct sock *sk,
-			      struct can_filter *filter, int count)
+static void raw_disable_filters(struct net *net, struct net_device *dev,
+				struct sock *sk, struct can_filter *filter,
+				int count)
 {
 	int i;
 
 	for (i = 0; i < count; i++)
-		can_rx_unregister(dev, filter[i].can_id, filter[i].can_mask,
-				  raw_rcv, sk);
+		can_rx_unregister(net, dev, filter[i].can_id,
+				  filter[i].can_mask, raw_rcv, sk);
 }
 
-static inline void raw_disable_errfilter(struct net_device *dev,
+static inline void raw_disable_errfilter(struct net *net,
+					 struct net_device *dev,
 					 struct sock *sk,
 					 can_err_mask_t err_mask)
 
 {
 	if (err_mask)
-		can_rx_unregister(dev, 0, err_mask | CAN_ERR_FLAG,
+		can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG,
 				  raw_rcv, sk);
 }
 
-static inline void raw_disable_allfilters(struct net_device *dev,
+static inline void raw_disable_allfilters(struct net *net,
+					  struct net_device *dev,
 					  struct sock *sk)
 {
 	struct raw_sock *ro = raw_sk(sk);
 
-	raw_disable_filters(dev, sk, ro->filter, ro->count);
-	raw_disable_errfilter(dev, sk, ro->err_mask);
+	raw_disable_filters(net, dev, sk, ro->filter, ro->count);
+	raw_disable_errfilter(net, dev, sk, ro->err_mask);
 }
 
-static int raw_enable_allfilters(struct net_device *dev, struct sock *sk)
+static int raw_enable_allfilters(struct net *net, struct net_device *dev,
+				 struct sock *sk)
 {
 	struct raw_sock *ro = raw_sk(sk);
 	int err;
 
-	err = raw_enable_filters(dev, sk, ro->filter, ro->count);
+	err = raw_enable_filters(net, dev, sk, ro->filter, ro->count);
 	if (!err) {
-		err = raw_enable_errfilter(dev, sk, ro->err_mask);
+		err = raw_enable_errfilter(net, dev, sk, ro->err_mask);
 		if (err)
-			raw_disable_filters(dev, sk, ro->filter, ro->count);
+			raw_disable_filters(net, dev, sk, ro->filter,
+					    ro->count);
 	}
 
 	return err;
@@ -267,7 +273,7 @@ static int raw_notifier(struct notifier_block *nb,
 	struct raw_sock *ro = container_of(nb, struct raw_sock, notifier);
 	struct sock *sk = &ro->sk;
 
-	if (!net_eq(dev_net(dev), &init_net))
+	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return NOTIFY_DONE;
 
 	if (dev->type != ARPHRD_CAN)
@@ -282,7 +288,7 @@ static int raw_notifier(struct notifier_block *nb,
 		lock_sock(sk);
 		/* remove current filters & unregister */
 		if (ro->bound)
-			raw_disable_allfilters(dev, sk);
+			raw_disable_allfilters(dev_net(dev), dev, sk);
 
 		if (ro->count > 1)
 			kfree(ro->filter);
@@ -358,13 +364,13 @@ static int raw_release(struct socket *sock)
 		if (ro->ifindex) {
 			struct net_device *dev;
 
-			dev = dev_get_by_index(&init_net, ro->ifindex);
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
 			if (dev) {
-				raw_disable_allfilters(dev, sk);
+				raw_disable_allfilters(dev_net(dev), dev, sk);
 				dev_put(dev);
 			}
 		} else
-			raw_disable_allfilters(NULL, sk);
+			raw_disable_allfilters(sock_net(sk), NULL, sk);
 	}
 
 	if (ro->count > 1)
@@ -404,7 +410,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	if (addr->can_ifindex) {
 		struct net_device *dev;
 
-		dev = dev_get_by_index(&init_net, addr->can_ifindex);
+		dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
 		if (!dev) {
 			err = -ENODEV;
 			goto out;
@@ -420,13 +426,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 		ifindex = dev->ifindex;
 
 		/* filters set by default/setsockopt */
-		err = raw_enable_allfilters(dev, sk);
+		err = raw_enable_allfilters(sock_net(sk), dev, sk);
 		dev_put(dev);
 	} else {
 		ifindex = 0;
 
 		/* filters set by default/setsockopt */
-		err = raw_enable_allfilters(NULL, sk);
+		err = raw_enable_allfilters(sock_net(sk), NULL, sk);
 	}
 
 	if (!err) {
@@ -435,13 +441,15 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 			if (ro->ifindex) {
 				struct net_device *dev;
 
-				dev = dev_get_by_index(&init_net, ro->ifindex);
+				dev = dev_get_by_index(sock_net(sk),
+						       ro->ifindex);
 				if (dev) {
-					raw_disable_allfilters(dev, sk);
+					raw_disable_allfilters(dev_net(dev),
+							       dev, sk);
 					dev_put(dev);
 				}
 			} else
-				raw_disable_allfilters(NULL, sk);
+				raw_disable_allfilters(sock_net(sk), NULL, sk);
 		}
 		ro->ifindex = ifindex;
 		ro->bound = 1;
@@ -517,15 +525,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		lock_sock(sk);
 
 		if (ro->bound && ro->ifindex)
-			dev = dev_get_by_index(&init_net, ro->ifindex);
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
 
 		if (ro->bound) {
 			/* (try to) register the new filters */
 			if (count == 1)
-				err = raw_enable_filters(dev, sk, &sfilter, 1);
+				err = raw_enable_filters(sock_net(sk), dev, sk,
+							 &sfilter, 1);
 			else
-				err = raw_enable_filters(dev, sk, filter,
-							 count);
+				err = raw_enable_filters(sock_net(sk), dev, sk,
+							 filter, count);
 			if (err) {
 				if (count > 1)
 					kfree(filter);
@@ -533,7 +542,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 			}
 
 			/* remove old filter registrations */
-			raw_disable_filters(dev, sk, ro->filter, ro->count);
+			raw_disable_filters(sock_net(sk), dev, sk, ro->filter,
+					    ro->count);
 		}
 
 		/* remove old filter space */
@@ -569,18 +579,20 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		lock_sock(sk);
 
 		if (ro->bound && ro->ifindex)
-			dev = dev_get_by_index(&init_net, ro->ifindex);
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
 
 		/* remove current error mask */
 		if (ro->bound) {
 			/* (try to) register the new err_mask */
-			err = raw_enable_errfilter(dev, sk, err_mask);
+			err = raw_enable_errfilter(sock_net(sk), dev, sk,
+						   err_mask);
 
 			if (err)
 				goto out_err;
 
 			/* remove old err_mask registration */
-			raw_disable_errfilter(dev, sk, ro->err_mask);
+			raw_disable_errfilter(sock_net(sk), dev, sk,
+					      ro->err_mask);
 		}
 
 		/* link new err_mask to the socket */
@@ -741,7 +753,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			return -EINVAL;
 	}
 
-	dev = dev_get_by_index(&init_net, ifindex);
+	dev = dev_get_by_index(sock_net(sk), ifindex);
 	if (!dev)
 		return -ENXIO;
 
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 464e88599b9d..108533859a53 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -230,6 +230,7 @@ enum {
 	Opt_osdkeepalivetimeout,
 	Opt_mount_timeout,
 	Opt_osd_idle_ttl,
+	Opt_osd_request_timeout,
 	Opt_last_int,
 	/* int args above */
 	Opt_fsid,
@@ -256,6 +257,7 @@ static match_table_t opt_tokens = {
 	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
 	{Opt_mount_timeout, "mount_timeout=%d"},
 	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+	{Opt_osd_request_timeout, "osd_request_timeout=%d"},
 	/* int args above */
 	{Opt_fsid, "fsid=%s"},
 	{Opt_name, "name=%s"},
@@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name,
 	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
 	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
+	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
 
 	/* get mon ip(s) */
 	/* ip1[:port1][,ip2[:port2]...] */
@@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name,
 			}
 			opt->mount_timeout = msecs_to_jiffies(intval * 1000);
 			break;
+		case Opt_osd_request_timeout:
+			/* 0 is "wait forever" (i.e. infinite timeout) */
+			if (intval < 0 || intval > INT_MAX / 1000) {
+				pr_err("osd_request_timeout out of range\n");
+				err = -EINVAL;
+				goto out;
+			}
+			opt->osd_request_timeout = msecs_to_jiffies(intval * 1000);
+			break;
 
 		case Opt_share:
 			opt->flags &= ~CEPH_OPT_NOSHARE;
@@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
 	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
 		seq_printf(m, "osdkeepalivetimeout=%d,",
 		    jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
+	if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT)
+		seq_printf(m, "osd_request_timeout=%d,",
+			   jiffies_to_msecs(opt->osd_request_timeout) / 1000);
 
 	/* drop redundant comma */
 	if (m->count != pos)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 38dcf1eb427d..f76bb3332613 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -7,6 +7,7 @@
 #include <linux/kthread.h>
 #include <linux/net.h>
 #include <linux/nsproxy.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
@@ -469,11 +470,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 {
 	struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
 	struct socket *sock;
+	unsigned int noio_flag;
 	int ret;
 
 	BUG_ON(con->sock);
+
+	/* sock_create_kern() allocates with GFP_KERNEL */
+	noio_flag = memalloc_noio_save();
 	ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
 			       SOCK_STREAM, IPPROTO_TCP, &sock);
+	memalloc_noio_restore(noio_flag);
 	if (ret)
 		return ret;
 	sock->sk->sk_allocation = GFP_NOFS;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b65bbf9f45eb..e15ea9e4c495 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req)
 
 	req->r_flags |= CEPH_OSD_FLAG_ONDISK;
 	atomic_inc(&req->r_osdc->num_requests);
+
+	req->r_start_stamp = jiffies;
 }
 
 static void submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req)
 	ceph_osdc_put_request(req);
 }
 
+static void abort_request(struct ceph_osd_request *req, int err)
+{
+	dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);
+
+	cancel_map_check(req);
+	complete_request(req, err);
+}
+
 static void check_pool_dne(struct ceph_osd_request *req)
 {
 	struct ceph_osd_client *osdc = req->r_osdc;
@@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work)
 		container_of(work, struct ceph_osd_client, timeout_work.work);
 	struct ceph_options *opts = osdc->client->options;
 	unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
+	unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
 	LIST_HEAD(slow_osds);
 	struct rb_node *n, *p;
 
@@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work)
 		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
 		bool found = false;
 
-		for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+		for (p = rb_first(&osd->o_requests); p; ) {
 			struct ceph_osd_request *req =
 			    rb_entry(p, struct ceph_osd_request, r_node);
 
+			p = rb_next(p); /* abort_request() */
+
 			if (time_before(req->r_stamp, cutoff)) {
 				dout(" req %p tid %llu on osd%d is laggy\n",
 				     req, req->r_tid, osd->o_osd);
 				found = true;
 			}
+			if (opts->osd_request_timeout &&
+			    time_before(req->r_start_stamp, expiry_cutoff)) {
+				pr_err_ratelimited("tid %llu on osd%d timeout\n",
+				       req->r_tid, osd->o_osd);
+				abort_request(req, -ETIMEDOUT);
+			}
 		}
 		for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
 			struct ceph_osd_linger_request *lreq =
@@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work)
 			list_move_tail(&osd->o_keepalive_item, &slow_osds);
 	}
 
+	if (opts->osd_request_timeout) {
+		for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
+			struct ceph_osd_request *req =
+			    rb_entry(p, struct ceph_osd_request, r_node);
+
+			p = rb_next(p); /* abort_request() */
+
+			if (time_before(req->r_start_stamp, expiry_cutoff)) {
+				pr_err_ratelimited("tid %llu on osd%d timeout\n",
+				       req->r_tid, osdc->homeless_osd.o_osd);
+				abort_request(req, -ETIMEDOUT);
+			}
+		}
+	}
+
 	if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
 		maybe_request_map(osdc);
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 6824c0ec8373..ffe9e904d4d1 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_stable = %d\n",
 	     c->chooseleaf_stable);
 
-	crush_finalize(c);
-
 done:
+	crush_finalize(c);
 	dout("crush_decode success\n");
 	return c;
 
@@ -1380,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end,
 		if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
 		    (xorstate & CEPH_OSD_EXISTS)) {
 			pr_info("osd%d does not exist\n", osd);
-			map->osd_weight[osd] = CEPH_OSD_IN;
 			ret = set_primary_affinity(map, osd,
 						   CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
 			if (ret)
diff --git a/net/core/datagram.c b/net/core/datagram.c
index ea633342ab0d..db1866f2ffcf 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -256,8 +256,12 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 		}
 
 		spin_unlock_irqrestore(&queue->lock, cpu_flags);
-	} while (sk_can_busy_loop(sk) &&
-		 sk_busy_loop(sk, flags & MSG_DONTWAIT));
+
+		if (!sk_can_busy_loop(sk))
+			break;
+
+		sk_busy_loop(sk, flags & MSG_DONTWAIT);
+	} while (!skb_queue_empty(&sk->sk_receive_queue));
 
 	error = -EAGAIN;
 
@@ -398,7 +402,7 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 			   struct iov_iter *to, int len)
 {
 	int start = skb_headlen(skb);
-	int i, copy = start - offset;
+	int i, copy = start - offset, start_off = offset, n;
 	struct sk_buff *frag_iter;
 
 	trace_skb_copy_datagram_iovec(skb, len);
@@ -407,11 +411,12 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		if (copy_to_iter(skb->data + offset, copy, to) != copy)
+		n = copy_to_iter(skb->data + offset, copy, to);
+		offset += n;
+		if (n != copy)
 			goto short_copy;
 		if ((len -= copy) == 0)
 			return 0;
-		offset += copy;
 	}
 
 	/* Copy paged appendix. Hmm... why does this look so complicated? */
@@ -425,13 +430,14 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 		if ((copy = end - offset) > 0) {
 			if (copy > len)
 				copy = len;
-			if (copy_page_to_iter(skb_frag_page(frag),
+			n = copy_page_to_iter(skb_frag_page(frag),
 					      frag->page_offset + offset -
-					      start, copy, to) != copy)
+					      start, copy, to);
+			offset += n;
+			if (n != copy)
 				goto short_copy;
 			if (!(len -= copy))
 				return 0;
-			offset += copy;
 		}
 		start = end;
 	}
@@ -463,6 +469,7 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 	 */
 
 fault:
+	iov_iter_revert(to, offset - start_off);
 	return -EFAULT;
 
 short_copy:
@@ -613,7 +620,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      __wsum *csump)
 {
 	int start = skb_headlen(skb);
-	int i, copy = start - offset;
+	int i, copy = start - offset, start_off = offset;
 	struct sk_buff *frag_iter;
 	int pos = 0;
 	int n;
@@ -623,11 +630,11 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 		if (copy > len)
 			copy = len;
 		n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
+		offset += n;
 		if (n != copy)
 			goto fault;
 		if ((len -= copy) == 0)
 			return 0;
-		offset += copy;
 		pos = copy;
 	}
 
@@ -649,12 +656,12 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 						  offset - start, copy,
 						  &csum2, to);
 			kunmap(page);
+			offset += n;
 			if (n != copy)
 				goto fault;
 			*csump = csum_block_add(*csump, csum2, pos);
 			if (!(len -= copy))
 				return 0;
-			offset += copy;
 			pos += copy;
 		}
 		start = end;
@@ -687,6 +694,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 		return 0;
 
 fault:
+	iov_iter_revert(to, offset - start_off);
 	return -EFAULT;
 }
 
@@ -756,7 +764,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 
 	if (msg_data_left(msg) < chunk) {
 		if (__skb_checksum_complete(skb))
-			goto csum_error;
+			return -EINVAL;
 		if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
 			goto fault;
 	} else {
@@ -764,14 +772,16 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 		if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter,
 					       chunk, &csum))
 			goto fault;
-		if (csum_fold(csum))
-			goto csum_error;
+
+		if (csum_fold(csum)) {
+			iov_iter_revert(&msg->msg_iter, chunk);
+			return -EINVAL;
+		}
+
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
 	}
 	return 0;
-csum_error:
-	return -EINVAL;
 fault:
 	return -EFAULT;
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 8637b2b71f3d..d07aa5ffb511 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -95,6 +95,7 @@
 #include <linux/notifier.h>
 #include <linux/skbuff.h>
 #include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/busy_poll.h>
@@ -1304,6 +1305,7 @@ void netdev_notify_peers(struct net_device *dev)
 {
 	rtnl_lock();
 	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(netdev_notify_peers);
@@ -2449,6 +2451,9 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 {
 	unsigned long flags;
 
+	if (unlikely(!skb))
+		return;
+
 	if (likely(atomic_read(&skb->users) == 1)) {
 		smp_rmb();
 		atomic_set(&skb->users, 0);
@@ -2971,6 +2976,9 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 		    __skb_linearize(skb))
 			goto out_kfree_skb;
 
+		if (validate_xmit_xfrm(skb, features))
+			goto out_kfree_skb;
+
 		/* If packet is not checksummed and device does not
 		 * support checksumming for this protocol, complete
 		 * checksumming here.
@@ -3440,6 +3448,7 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
+unsigned int __read_mostly netdev_budget_usecs = 2000;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
@@ -4239,13 +4248,132 @@ static int __netif_receive_skb(struct sk_buff *skb)
 		 */
 		current->flags |= PF_MEMALLOC;
 		ret = __netif_receive_skb_core(skb, true);
-		tsk_restore_flags(current, pflags, PF_MEMALLOC);
+		current_restore_flags(pflags, PF_MEMALLOC);
 	} else
 		ret = __netif_receive_skb_core(skb, false);
 
 	return ret;
 }
 
+static struct static_key generic_xdp_needed __read_mostly;
+
+static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	struct bpf_prog *new = xdp->prog;
+	int ret = 0;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG: {
+		struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
+
+		rcu_assign_pointer(dev->xdp_prog, new);
+		if (old)
+			bpf_prog_put(old);
+
+		if (old && !new) {
+			static_key_slow_dec(&generic_xdp_needed);
+		} else if (new && !old) {
+			static_key_slow_inc(&generic_xdp_needed);
+			dev_disable_lro(dev);
+		}
+		break;
+	}
+
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = !!rcu_access_pointer(dev->xdp_prog);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct bpf_prog *xdp_prog)
+{
+	struct xdp_buff xdp;
+	u32 act = XDP_DROP;
+	void *orig_data;
+	int hlen, off;
+	u32 mac_len;
+
+	/* Reinjected packets coming from act_mirred or similar should
+	 * not get XDP generic processing.
+	 */
+	if (skb_cloned(skb))
+		return XDP_PASS;
+
+	if (skb_linearize(skb))
+		goto do_drop;
+
+	/* The XDP program wants to see the packet starting at the MAC
+	 * header.
+	 */
+	mac_len = skb->data - skb_mac_header(skb);
+	hlen = skb_headlen(skb) + mac_len;
+	xdp.data = skb->data - mac_len;
+	xdp.data_end = xdp.data + hlen;
+	xdp.data_hard_start = skb->data - skb_headroom(skb);
+	orig_data = xdp.data;
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	off = xdp.data - orig_data;
+	if (off > 0)
+		__skb_pull(skb, off);
+	else if (off < 0)
+		__skb_push(skb, -off);
+
+	switch (act) {
+	case XDP_TX:
+		__skb_push(skb, mac_len);
+		/* fall through */
+	case XDP_PASS:
+		break;
+
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(skb->dev, xdp_prog, act);
+		/* fall through */
+	case XDP_DROP:
+	do_drop:
+		kfree_skb(skb);
+		break;
+	}
+
+	return act;
+}
+
+/* When doing generic XDP we have to bypass the qdisc layer and the
+ * network taps in order to match in-driver-XDP behavior.
+ */
+static void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
+{
+	struct net_device *dev = skb->dev;
+	struct netdev_queue *txq;
+	bool free_skb = true;
+	int cpu, rc;
+
+	txq = netdev_pick_tx(dev, skb, NULL);
+	cpu = smp_processor_id();
+	HARD_TX_LOCK(dev, txq, cpu);
+	if (!netif_xmit_stopped(txq)) {
+		rc = netdev_start_xmit(skb, dev, txq, 0);
+		if (dev_xmit_complete(rc))
+			free_skb = false;
+	}
+	HARD_TX_UNLOCK(dev, txq);
+	if (free_skb) {
+		trace_xdp_exception(dev, xdp_prog, XDP_TX);
+		kfree_skb(skb);
+	}
+}
+
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
@@ -4257,6 +4385,21 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 
 	rcu_read_lock();
 
+	if (static_key_false(&generic_xdp_needed)) {
+		struct bpf_prog *xdp_prog = rcu_dereference(skb->dev->xdp_prog);
+
+		if (xdp_prog) {
+			u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+
+			if (act != XDP_PASS) {
+				rcu_read_unlock();
+				if (act == XDP_TX)
+					generic_xdp_tx(skb, xdp_prog);
+				return NET_RX_DROP;
+			}
+		}
+	}
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
@@ -4489,7 +4632,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	enum gro_result ret;
 	int grow;
 
-	if (!(skb->dev->features & NETIF_F_GRO))
+	if (netif_elide_gro(skb->dev))
 		goto normal;
 
 	if (skb->csum_bad)
@@ -5059,27 +5202,28 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 		do_softirq();
 }
 
-bool sk_busy_loop(struct sock *sk, int nonblock)
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg)
 {
-	unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
-	int rc;
 
 restart:
-	rc = false;
 	napi_poll = NULL;
 
 	rcu_read_lock();
 
-	napi = napi_by_id(sk->sk_napi_id);
+	napi = napi_by_id(napi_id);
 	if (!napi)
 		goto out;
 
 	preempt_disable();
 	for (;;) {
-		rc = 0;
+		int work = 0;
+
 		local_bh_disable();
 		if (!napi_poll) {
 			unsigned long val = READ_ONCE(napi->state);
@@ -5097,16 +5241,15 @@ restart:
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		rc = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, BUSY_POLL_BUDGET);
+		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
 count:
-		if (rc > 0)
-			__NET_ADD_STATS(sock_net(sk),
-					LINUX_MIB_BUSYPOLLRXPACKETS, rc);
+		if (work > 0)
+			__NET_ADD_STATS(dev_net(napi->dev),
+					LINUX_MIB_BUSYPOLLRXPACKETS, work);
 		local_bh_enable();
 
-		if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
-		    busy_loop_timeout(end_time))
+		if (!loop_end || loop_end(loop_end_arg, start_time))
 			break;
 
 		if (unlikely(need_resched())) {
@@ -5115,9 +5258,8 @@ count:
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
-			rc = !skb_queue_empty(&sk->sk_receive_queue);
-			if (rc || busy_loop_timeout(end_time))
-				return rc;
+			if (loop_end(loop_end_arg, start_time))
+				return;
 			goto restart;
 		}
 		cpu_relax();
@@ -5125,12 +5267,10 @@ count:
 	if (napi_poll)
 		busy_poll_stop(napi, have_poll_lock);
 	preempt_enable();
-	rc = !skb_queue_empty(&sk->sk_receive_queue);
 out:
 	rcu_read_unlock();
-	return rc;
 }
-EXPORT_SYMBOL(sk_busy_loop);
+EXPORT_SYMBOL(napi_busy_loop);
 
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
@@ -5142,10 +5282,10 @@ static void napi_hash_add(struct napi_struct *napi)
 
 	spin_lock(&napi_hash_lock);
 
-	/* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+	/* 0..NR_CPUS range is reserved for sender_cpu use */
 	do {
-		if (unlikely(++napi_gen_id < NR_CPUS + 1))
-			napi_gen_id = NR_CPUS + 1;
+		if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+			napi_gen_id = MIN_NAPI_ID;
 	} while (napi_by_id(napi_gen_id));
 	napi->napi_id = napi_gen_id;
 
@@ -5309,7 +5449,8 @@ out_unlock:
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
-	unsigned long time_limit = jiffies + 2;
+	unsigned long time_limit = jiffies +
+		usecs_to_jiffies(netdev_budget_usecs);
 	int budget = netdev_budget;
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
@@ -6713,13 +6854,16 @@ EXPORT_SYMBOL(dev_change_proto_down);
 /**
  *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
  *	@dev: device
+ *	@extack: netlink extended ack
  *	@fd: new program fd or negative value to clear
  *	@flags: xdp-related flags
  *
  *	Set or clear a bpf program for a device
  */
-int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+		      int fd, u32 flags)
 {
+	int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp);
 	const struct net_device_ops *ops = dev->netdev_ops;
 	struct bpf_prog *prog = NULL;
 	struct netdev_xdp xdp;
@@ -6727,14 +6871,16 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 
 	ASSERT_RTNL();
 
-	if (!ops->ndo_xdp)
-		return -EOPNOTSUPP;
+	xdp_op = ops->ndo_xdp;
+	if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
+		xdp_op = generic_xdp_install;
+
 	if (fd >= 0) {
 		if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) {
 			memset(&xdp, 0, sizeof(xdp));
 			xdp.command = XDP_QUERY_PROG;
 
-			err = ops->ndo_xdp(dev, &xdp);
+			err = xdp_op(dev, &xdp);
 			if (err < 0)
 				return err;
 			if (xdp.prog_attached)
@@ -6748,15 +6894,15 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 
 	memset(&xdp, 0, sizeof(xdp));
 	xdp.command = XDP_SETUP_PROG;
+	xdp.extack = extack;
 	xdp.prog = prog;
 
-	err = ops->ndo_xdp(dev, &xdp);
+	err = xdp_op(dev, &xdp);
 	if (err < 0 && prog)
 		bpf_prog_put(prog);
 
 	return err;
 }
-EXPORT_SYMBOL(dev_change_xdp_fd);
 
 /**
  *	dev_new_index	-	allocate an ifindex
@@ -7102,13 +7248,10 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 	else
 		netif_dormant_off(dev);
 
-	if (netif_carrier_ok(rootdev)) {
-		if (!netif_carrier_ok(dev))
-			netif_carrier_on(dev);
-	} else {
-		if (netif_carrier_ok(dev))
-			netif_carrier_off(dev);
-	}
+	if (netif_carrier_ok(rootdev))
+		netif_carrier_on(dev);
+	else
+		netif_carrier_off(dev);
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
@@ -7791,6 +7934,7 @@ EXPORT_SYMBOL(alloc_netdev_mqs);
 void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
+	struct bpf_prog *prog;
 
 	might_sleep();
 	netif_free_tx_queues(dev);
@@ -7809,6 +7953,12 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->pcpu_refcnt);
 	dev->pcpu_refcnt = NULL;
 
+	prog = rcu_dereference_protected(dev->xdp_prog, 1);
+	if (prog) {
+		bpf_prog_put(prog);
+		static_key_slow_dec(&generic_xdp_needed);
+	}
+
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e9c1e6acfb6d..b0b87a292e7c 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1397,10 +1397,10 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 				   u32 seq, int flags)
 {
 	const struct devlink_ops *ops = devlink->ops;
+	u8 inline_mode, encap_mode;
 	void *hdr;
 	int err = 0;
 	u16 mode;
-	u8 inline_mode;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
 	if (!hdr)
@@ -1429,6 +1429,15 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 			goto nla_put_failure;
 	}
 
+	if (ops->eswitch_encap_mode_get) {
+		err = ops->eswitch_encap_mode_get(devlink, &encap_mode);
+		if (err)
+			goto nla_put_failure;
+		err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode);
+		if (err)
+			goto nla_put_failure;
+	}
+
 	genlmsg_end(msg, hdr);
 	return 0;
 
@@ -1468,9 +1477,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	const struct devlink_ops *ops = devlink->ops;
-	u16 mode;
-	u8 inline_mode;
+	u8 inline_mode, encap_mode;
 	int err = 0;
+	u16 mode;
 
 	if (!ops)
 		return -EOPNOTSUPP;
@@ -1494,7 +1503,695 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 			return err;
 	}
 
+	if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) {
+		if (!ops->eswitch_encap_mode_set)
+			return -EOPNOTSUPP;
+		encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]);
+		err = ops->eswitch_encap_mode_set(devlink, encap_mode);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int devlink_dpipe_match_put(struct sk_buff *skb,
+			    struct devlink_dpipe_match *match)
+{
+	struct devlink_dpipe_header *header = match->header;
+	struct devlink_dpipe_field *field = &header->fields[match->field_id];
+	struct nlattr *match_attr;
+
+	match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH);
+	if (!match_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, match_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, match_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);
+
+static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *matches_attr;
+
+	matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
+	if (!matches_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->matches_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, matches_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, matches_attr);
+	return -EMSGSIZE;
+}
+
+int devlink_dpipe_action_put(struct sk_buff *skb,
+			     struct devlink_dpipe_action *action)
+{
+	struct devlink_dpipe_header *header = action->header;
+	struct devlink_dpipe_field *field = &header->fields[action->field_id];
+	struct nlattr *action_attr;
+
+	action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION);
+	if (!action_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, action_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, action_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);
+
+static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *actions_attr;
+
+	actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
+	if (!actions_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->actions_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, actions_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, actions_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_table_put(struct sk_buff *skb,
+				   struct devlink_dpipe_table *table)
+{
+	struct nlattr *table_attr;
+
+	table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE);
+	if (!table_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table->size,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
+		       table->counters_enabled))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_matches_put(table, skb))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_actions_put(table, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, table_attr);
 	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, table_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
+					    struct genl_info *info)
+{
+	int err;
+
+	if (*pskb) {
+		err = genlmsg_reply(*pskb, info);
+		if (err)
+			return err;
+	}
+	*pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!*pskb)
+		return -ENOMEM;
+	return 0;
+}
+
+static int devlink_dpipe_tables_fill(struct genl_info *info,
+				     enum devlink_command cmd, int flags,
+				     struct list_head *dpipe_tables,
+				     const char *table_name)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	struct nlattr *tables_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	bool incomplete;
+	void *hdr;
+	int i;
+	int err;
+
+	table = list_first_entry(dpipe_tables,
+				 struct devlink_dpipe_table, list);
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES);
+	if (!tables_attr)
+		goto nla_put_failure;
+
+	i = 0;
+	incomplete = false;
+	list_for_each_entry_from(table, dpipe_tables, list) {
+		if (!table_name) {
+			err = devlink_dpipe_table_put(skb, table);
+			if (err) {
+				if (!i)
+					goto err_table_put;
+				incomplete = true;
+				break;
+			}
+		} else {
+			if (!strcmp(table->name, table_name)) {
+				err = devlink_dpipe_table_put(skb, table);
+				if (err)
+					break;
+			}
+		}
+		i++;
+	}
+
+	nla_nest_end(skb, tables_attr);
+	genlmsg_end(skb, hdr);
+	if (incomplete)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name =  NULL;
+
+	if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+
+	return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0,
+					 &devlink->dpipe_table_list,
+					 table_name);
+}
+
+static int devlink_dpipe_value_put(struct sk_buff *skb,
+				   struct devlink_dpipe_value *value)
+{
+	if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE,
+		    value->value_size, value->value))
+		return -EMSGSIZE;
+	if (value->mask)
+		if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK,
+			    value->value_size, value->mask))
+			return -EMSGSIZE;
+	if (value->mapping_valid)
+		if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING,
+				value->mapping_value))
+			return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_value_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *value)
+{
+	if (!value->action)
+		return -EINVAL;
+	if (devlink_dpipe_action_put(skb, value->action))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_values_put(struct sk_buff *skb,
+					   struct devlink_dpipe_value *values,
+					   unsigned int values_count)
+{
+	struct nlattr *action_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		action_attr = nla_nest_start(skb,
+					     DEVLINK_ATTR_DPIPE_ACTION_VALUE);
+		if (!action_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_action_value_put(skb, &values[i]);
+		if (err)
+			goto err_action_value_put;
+		nla_nest_end(skb, action_attr);
+	}
+	return 0;
+
+err_action_value_put:
+	nla_nest_cancel(skb, action_attr);
+	return err;
+}
+
+static int devlink_dpipe_match_value_put(struct sk_buff *skb,
+					 struct devlink_dpipe_value *value)
+{
+	if (!value->match)
+		return -EINVAL;
+	if (devlink_dpipe_match_put(skb, value->match))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_match_values_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *values,
+					  unsigned int values_count)
+{
+	struct nlattr *match_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		match_attr = nla_nest_start(skb,
+					    DEVLINK_ATTR_DPIPE_MATCH_VALUE);
+		if (!match_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_match_value_put(skb, &values[i]);
+		if (err)
+			goto err_match_value_put;
+		nla_nest_end(skb, match_attr);
+	}
+	return 0;
+
+err_match_value_put:
+	nla_nest_cancel(skb, match_attr);
+	return err;
+}
+
+static int devlink_dpipe_entry_put(struct sk_buff *skb,
+				   struct devlink_dpipe_entry *entry)
+{
+	struct nlattr *entry_attr, *matches_attr, *actions_attr;
+	int err;
+
+	entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY);
+	if (!entry_attr)
+		return  -EMSGSIZE;
+
+	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (entry->counter_valid)
+		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,
+				      entry->counter, DEVLINK_ATTR_PAD))
+			goto nla_put_failure;
+
+	matches_attr = nla_nest_start(skb,
+				      DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
+	if (!matches_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_match_values_put(skb, entry->match_values,
+					     entry->match_values_count);
+	if (err) {
+		nla_nest_cancel(skb, matches_attr);
+		goto err_match_values_put;
+	}
+	nla_nest_end(skb, matches_attr);
+
+	actions_attr = nla_nest_start(skb,
+				      DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
+	if (!actions_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_action_values_put(skb, entry->action_values,
+					      entry->action_values_count);
+	if (err) {
+		nla_nest_cancel(skb, actions_attr);
+		goto err_action_values_put;
+	}
+	nla_nest_end(skb, actions_attr);
+
+	nla_nest_end(skb, entry_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_match_values_put:
+err_action_values_put:
+	nla_nest_cancel(skb, entry_attr);
+	return err;
+}
+
+static struct devlink_dpipe_table *
+devlink_dpipe_table_find(struct list_head *dpipe_tables,
+			 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	list_for_each_entry_rcu(table, dpipe_tables, list) {
+		if (!strcmp(table->name, table_name))
+			return table;
+	}
+	return NULL;
+}
+
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink *devlink;
+	int err;
+
+	err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb,
+					       dump_ctx->info);
+	if (err)
+		return err;
+
+	dump_ctx->hdr = genlmsg_put(dump_ctx->skb,
+				    dump_ctx->info->snd_portid,
+				    dump_ctx->info->snd_seq,
+				    &devlink_nl_family, NLM_F_MULTI,
+				    dump_ctx->cmd);
+	if (!dump_ctx->hdr)
+		goto nla_put_failure;
+
+	devlink = dump_ctx->info->user_ptr[0];
+	if (devlink_nl_put_handle(dump_ctx->skb, devlink))
+		goto nla_put_failure;
+	dump_ctx->nest = nla_nest_start(dump_ctx->skb,
+					DEVLINK_ATTR_DPIPE_ENTRIES);
+	if (!dump_ctx->nest)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr);
+	nlmsg_free(dump_ctx->skb);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare);
+
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+				   struct devlink_dpipe_entry *entry)
+{
+	return devlink_dpipe_entry_put(dump_ctx->skb, entry);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append);
+
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	nla_nest_end(dump_ctx->skb, dump_ctx->nest);
+	genlmsg_end(dump_ctx->skb, dump_ctx->hdr);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
+
+static int devlink_dpipe_entries_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_table *table)
+{
+	struct devlink_dpipe_dump_ctx dump_ctx;
+	struct nlmsghdr *nlh;
+	int err;
+
+	dump_ctx.skb = NULL;
+	dump_ctx.cmd = cmd;
+	dump_ctx.info = info;
+
+	err = table->table_ops->entries_dump(table->priv,
+					     table->counters_enabled,
+					     &dump_ctx);
+	if (err)
+		goto err_entries_dump;
+
+send_done:
+	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+	return genlmsg_reply(dump_ctx.skb, info);
+
+err_entries_dump:
+err_skb_send_alloc:
+	genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr);
+	nlmsg_free(dump_ctx.skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	const char *table_name;
+
+	if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		return -EINVAL;
+
+	if (!table->table_ops->entries_dump)
+		return -EINVAL;
+
+	return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET,
+					  0, table);
+}
+
+static int devlink_dpipe_fields_put(struct sk_buff *skb,
+				    const struct devlink_dpipe_header *header)
+{
+	struct devlink_dpipe_field *field;
+	struct nlattr *field_attr;
+	int i;
+
+	for (i = 0; i < header->fields_count; i++) {
+		field = &header->fields[i];
+		field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD);
+		if (!field_attr)
+			return -EMSGSIZE;
+		if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type))
+			goto nla_put_failure;
+		nla_nest_end(skb, field_attr);
+	}
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, field_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_header_put(struct sk_buff *skb,
+				    struct devlink_dpipe_header *header)
+{
+	struct nlattr *fields_attr, *header_attr;
+	int err;
+
+	header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER);
+	if (!header_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
+	if (!fields_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_fields_put(skb, header);
+	if (err) {
+		nla_nest_cancel(skb, fields_attr);
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, fields_attr);
+	nla_nest_end(skb, header_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+	nla_nest_cancel(skb, header_attr);
+	return err;
+}
+
+static int devlink_dpipe_headers_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_headers *
+				      dpipe_headers)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct nlattr *headers_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	void *hdr;
+	int i, j;
+	int err;
+
+	i = 0;
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS);
+	if (!headers_attr)
+		goto nla_put_failure;
+
+	j = 0;
+	for (; i < dpipe_headers->headers_count; i++) {
+		err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]);
+		if (err) {
+			if (!j)
+				goto err_table_put;
+			break;
+		}
+		j++;
+	}
+	nla_nest_end(skb, headers_attr);
+	genlmsg_end(skb, hdr);
+	if (i != dpipe_headers->headers_count)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (!devlink->dpipe_headers)
+		return -EOPNOTSUPP;
+	return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET,
+					  0, devlink->dpipe_headers);
+}
+
+static int devlink_dpipe_table_counters_set(struct devlink *devlink,
+					    const char *table_name,
+					    bool enable)
+{
+	struct devlink_dpipe_table *table;
+
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		return -EINVAL;
+
+	if (table->counter_control_extern)
+		return -EOPNOTSUPP;
+
+	if (!(table->counters_enabled ^ enable))
+		return 0;
+
+	table->counters_enabled = enable;
+	if (table->table_ops->counters_set_update)
+		table->table_ops->counters_set_update(table->priv, enable);
+	return 0;
+}
+
+static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
+						   struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name;
+	bool counters_enable;
+
+	if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME] ||
+	    !info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED])
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]);
+
+	return devlink_dpipe_table_counters_set(devlink, table_name,
+						counters_enable);
 }
 
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
@@ -1512,6 +2209,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -1644,6 +2344,34 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+		.doit = devlink_nl_cmd_dpipe_table_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.doit = devlink_nl_cmd_dpipe_entries_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.doit = devlink_nl_cmd_dpipe_headers_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.doit = devlink_nl_cmd_dpipe_table_counters_set,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
@@ -1680,6 +2408,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);
 	INIT_LIST_HEAD(&devlink->sb_list);
+	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	return devlink;
 }
 EXPORT_SYMBOL_GPL(devlink_alloc);
@@ -1880,6 +2609,133 @@ void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
 }
 EXPORT_SYMBOL_GPL(devlink_sb_unregister);
 
+/**
+ *	devlink_dpipe_headers_register - register dpipe headers
+ *
+ *	@devlink: devlink
+ *	@dpipe_headers: dpipe header array
+ *
+ *	Register the headers supported by hardware.
+ */
+int devlink_dpipe_headers_register(struct devlink *devlink,
+				   struct devlink_dpipe_headers *dpipe_headers)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dpipe_headers = dpipe_headers;
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_register);
+
+/**
+ *	devlink_dpipe_headers_unregister - unregister dpipe headers
+ *
+ *	@devlink: devlink
+ *
+ *	Unregister the headers supported by hardware.
+ */
+void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dpipe_headers = NULL;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_unregister);
+
+/**
+ *	devlink_dpipe_table_counter_enabled - check if counter allocation
+ *					      required
+ *	@devlink: devlink
+ *	@table_name: tables name
+ *
+ *	Used by driver to check if counter allocation is required.
+ *	After counter allocation is turned on the table entries
+ *	are updated to include counter statistics.
+ *
+ *	After that point on the driver must respect the counter
+ *	state so that each entry added to the table is added
+ *	with a counter.
+ */
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+					 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+	bool enabled;
+
+	rcu_read_lock();
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	enabled = false;
+	if (table)
+		enabled = table->counters_enabled;
+	rcu_read_unlock();
+	return enabled;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
+
+/**
+ *	devlink_dpipe_table_register - register dpipe table
+ *
+ *	@devlink: devlink
+ *	@table_name: table name
+ *	@table_ops: table ops
+ *	@priv: priv
+ *	@size: size
+ *	@counter_control_extern: external control for counters
+ */
+int devlink_dpipe_table_register(struct devlink *devlink,
+				 const char *table_name,
+				 struct devlink_dpipe_table_ops *table_ops,
+				 void *priv, u64 size,
+				 bool counter_control_extern)
+{
+	struct devlink_dpipe_table *table;
+
+	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
+		return -EEXIST;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	table->name = table_name;
+	table->table_ops = table_ops;
+	table->priv = priv;
+	table->size = size;
+	table->counter_control_extern = counter_control_extern;
+
+	mutex_lock(&devlink_mutex);
+	list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_register);
+
+/**
+ *	devlink_dpipe_table_unregister - unregister dpipe table
+ *
+ *	@devlink: devlink
+ *	@table_name: table name
+ */
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+				    const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	mutex_lock(&devlink_mutex);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		goto unlock;
+	list_del_rcu(&table->list);
+	mutex_unlock(&devlink_mutex);
+	kfree_rcu(table, rcu);
+	return;
+unlock:
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index fb55327dcfea..70ccda233bd1 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void)
 	for_each_possible_cpu(cpu) {
 		data = &per_cpu(dm_cpu_data, cpu);
 		INIT_WORK(&data->dm_alert_work, send_dm_alert);
-		init_timer(&data->send_timer);
-		data->send_timer.data = (unsigned long)data;
-		data->send_timer.function = sched_send_work;
+		setup_timer(&data->send_timer, sched_send_work,
+			    (unsigned long)data);
 		spin_lock_init(&data->lock);
 		reset_per_cpu_data(data);
 	}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index aecb2c7241b6..03111a2d6653 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -90,6 +90,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
 	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",
 	[NETIF_F_GSO_SCTP_BIT] =	 "tx-sctp-segmentation",
+	[NETIF_F_GSO_ESP_BIT] =		 "tx-esp-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",
@@ -103,12 +104,15 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_RXALL_BIT] =            "rx-all",
 	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
 	[NETIF_F_HW_TC_BIT] =		 "hw-tc-offload",
+	[NETIF_F_HW_ESP_BIT] =		 "esp-hw-offload",
+	[NETIF_F_HW_ESP_TX_CSUM_BIT] =	 "esp-tx-csum-hw-offload",
 };
 
 static const char
 rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
 	[ETH_RSS_HASH_TOP_BIT] =	"toeplitz",
 	[ETH_RSS_HASH_XOR_BIT] =	"xor",
+	[ETH_RSS_HASH_CRC32_BIT] =	"crc32",
 };
 
 static const char
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b6791d94841d..f21c4d3aeae0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = {
 	KUIDT_INIT(~0),
 };
 
+bool fib_rule_matchall(const struct fib_rule *rule)
+{
+	if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
+	    rule->flags)
+		return false;
+	if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
+		return false;
+	if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
+	    !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib_rule_matchall);
+
 int fib_default_rule_add(struct fib_rules_ops *ops,
 			 u32 pref, u32 table, u32 flags)
 {
@@ -354,7 +368,8 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 	return 0;
 }
 
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+		   struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -372,7 +387,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy);
+	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -425,6 +440,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (tb[FRA_TUN_ID])
 		rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
 
+	err = -EINVAL;
 	if (tb[FRA_L3MDEV]) {
 #ifdef CONFIG_NET_L3_MASTER_DEV
 		rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
@@ -446,7 +462,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	else
 		rule->suppress_ifgroup = -1;
 
-	err = -EINVAL;
 	if (tb[FRA_GOTO]) {
 		if (rule->action != FR_ACT_GOTO)
 			goto errout_free;
@@ -547,7 +562,8 @@ errout:
 }
 EXPORT_SYMBOL_GPL(fib_nl_newrule);
 
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+		   struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -566,7 +582,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy);
+	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -576,8 +592,10 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	if (tb[FRA_UID_RANGE]) {
 		range = nla_get_kuid_range(tb);
-		if (!uid_range_set(&range))
+		if (!uid_range_set(&range)) {
+			err = -EINVAL;
 			goto errout;
+		}
 	} else {
 		range = fib_kuid_range_unset;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2e46e8..a253a6197e6b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <linux/fcntl.h>
 #include <linux/socket.h>
+#include <linux/sock_diag.h>
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/netdevice.h>
@@ -52,6 +53,7 @@
 #include <net/dst_metadata.h>
 #include <net/dst.h>
 #include <net/sock_reuseport.h>
+#include <net/busy_poll.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -91,7 +93,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 	rcu_read_lock();
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
-		unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+		struct sock *save_sk = skb->sk;
+		unsigned int pkt_len;
+
+		skb->sk = sk;
+		pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+		skb->sk = save_sk;
 		err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
 	}
 	rcu_read_unlock();
@@ -348,7 +355,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
  *	@new_prog: buffer where converted program will be stored
  *	@new_len: pointer to store length of converted program
  *
- * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
+ * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
+ * style extended BPF (eBPF).
  * Conversion workflow:
  *
  * 1) First pass for calculating the new program length:
@@ -928,7 +936,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
  */
 static void sk_filter_release(struct sk_filter *fp)
 {
-	if (atomic_dec_and_test(&fp->refcnt))
+	if (refcount_dec_and_test(&fp->refcnt))
 		call_rcu(&fp->rcu, sk_filter_release_rcu);
 }
 
@@ -943,20 +951,27 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 /* try to charge the socket memory if there is space available
  * return true on success
  */
-bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= sysctl_optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
-		atomic_inc(&fp->refcnt);
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
 	return false;
 }
 
+bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+	bool ret = __sk_filter_charge(sk, fp);
+	if (ret)
+		refcount_inc(&fp->refcnt);
+	return ret;
+}
+
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 {
 	struct sock_filter *old_prog;
@@ -1179,12 +1194,12 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 
 	fp->prog = prog;
-	atomic_set(&fp->refcnt, 0);
 
-	if (!sk_filter_charge(sk, fp)) {
+	if (!__sk_filter_charge(sk, fp)) {
 		kfree(fp);
 		return -ENOMEM;
 	}
+	refcount_set(&fp->refcnt, 1);
 
 	old_fp = rcu_dereference_protected(sk->sk_filter,
 					   lockdep_sock_is_held(sk));
@@ -2599,6 +2614,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
+{
+	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
+	.func           = bpf_get_socket_cookie,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
+{
+	struct sock *sk = sk_to_full_sk(skb->sk);
+	kuid_t kuid;
+
+	if (!sk || !sk_fullsock(sk))
+		return overflowuid;
+	kuid = sock_net_uid(sock_net(sk), sk);
+	return from_kuid_munged(sock_net(sk)->user_ns, kuid);
+}
+
+static const struct bpf_func_proto bpf_get_socket_uid_proto = {
+	.func           = bpf_get_socket_uid,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -2633,6 +2678,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -2692,6 +2741,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -2715,12 +2768,7 @@ xdp_func_proto(enum bpf_func_id func_id)
 static const struct bpf_func_proto *
 cg_skb_func_proto(enum bpf_func_id func_id)
 {
-	switch (func_id) {
-	case BPF_FUNC_skb_load_bytes:
-		return &bpf_skb_load_bytes_proto;
-	default:
-		return bpf_base_func_proto(func_id);
-	}
+	return sk_filter_func_proto(func_id);
 }
 
 static const struct bpf_func_proto *
@@ -3156,6 +3204,19 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 			*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
 #endif
 		break;
+
+	case offsetof(struct __sk_buff, napi_id):
+#if defined(CONFIG_NET_RX_BUSY_POLL)
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, napi_id) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+				      offsetof(struct sk_buff, napi_id));
+		*insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1);
+		*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
+#else
+		*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
+#endif
+		break;
 	}
 
 	return insn - insn_buf;
@@ -3252,111 +3313,55 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-static const struct bpf_verifier_ops sk_filter_ops = {
+const struct bpf_verifier_ops sk_filter_prog_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
 
-static const struct bpf_verifier_ops tc_cls_act_ops = {
+const struct bpf_verifier_ops tc_cls_act_prog_ops = {
 	.get_func_proto		= tc_cls_act_func_proto,
 	.is_valid_access	= tc_cls_act_is_valid_access,
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops xdp_ops = {
+const struct bpf_verifier_ops xdp_prog_ops = {
 	.get_func_proto		= xdp_func_proto,
 	.is_valid_access	= xdp_is_valid_access,
 	.convert_ctx_access	= xdp_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_xdp,
 };
 
-static const struct bpf_verifier_ops cg_skb_ops = {
+const struct bpf_verifier_ops cg_skb_prog_ops = {
 	.get_func_proto		= cg_skb_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops lwt_inout_ops = {
+const struct bpf_verifier_ops lwt_inout_prog_ops = {
 	.get_func_proto		= lwt_inout_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops lwt_xmit_ops = {
+const struct bpf_verifier_ops lwt_xmit_prog_ops = {
 	.get_func_proto		= lwt_xmit_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
-static const struct bpf_verifier_ops cg_sock_ops = {
+const struct bpf_verifier_ops cg_sock_prog_ops = {
 	.get_func_proto		= bpf_base_func_proto,
 	.is_valid_access	= sock_filter_is_valid_access,
 	.convert_ctx_access	= sock_filter_convert_ctx_access,
 };
 
-static struct bpf_prog_type_list sk_filter_type __ro_after_init = {
-	.ops	= &sk_filter_ops,
-	.type	= BPF_PROG_TYPE_SOCKET_FILTER,
-};
-
-static struct bpf_prog_type_list sched_cls_type __ro_after_init = {
-	.ops	= &tc_cls_act_ops,
-	.type	= BPF_PROG_TYPE_SCHED_CLS,
-};
-
-static struct bpf_prog_type_list sched_act_type __ro_after_init = {
-	.ops	= &tc_cls_act_ops,
-	.type	= BPF_PROG_TYPE_SCHED_ACT,
-};
-
-static struct bpf_prog_type_list xdp_type __ro_after_init = {
-	.ops	= &xdp_ops,
-	.type	= BPF_PROG_TYPE_XDP,
-};
-
-static struct bpf_prog_type_list cg_skb_type __ro_after_init = {
-	.ops	= &cg_skb_ops,
-	.type	= BPF_PROG_TYPE_CGROUP_SKB,
-};
-
-static struct bpf_prog_type_list lwt_in_type __ro_after_init = {
-	.ops	= &lwt_inout_ops,
-	.type	= BPF_PROG_TYPE_LWT_IN,
-};
-
-static struct bpf_prog_type_list lwt_out_type __ro_after_init = {
-	.ops	= &lwt_inout_ops,
-	.type	= BPF_PROG_TYPE_LWT_OUT,
-};
-
-static struct bpf_prog_type_list lwt_xmit_type __ro_after_init = {
-	.ops	= &lwt_xmit_ops,
-	.type	= BPF_PROG_TYPE_LWT_XMIT,
-};
-
-static struct bpf_prog_type_list cg_sock_type __ro_after_init = {
-	.ops	= &cg_sock_ops,
-	.type	= BPF_PROG_TYPE_CGROUP_SOCK
-};
-
-static int __init register_sk_filter_ops(void)
-{
-	bpf_register_prog_type(&sk_filter_type);
-	bpf_register_prog_type(&sched_cls_type);
-	bpf_register_prog_type(&sched_act_type);
-	bpf_register_prog_type(&xdp_type);
-	bpf_register_prog_type(&cg_skb_type);
-	bpf_register_prog_type(&cg_sock_type);
-	bpf_register_prog_type(&lwt_in_type);
-	bpf_register_prog_type(&lwt_out_type);
-	bpf_register_prog_type(&lwt_xmit_type);
-
-	return 0;
-}
-late_initcall(register_sk_filter_ops);
-
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;
diff --git a/net/core/flow.c b/net/core/flow.c
index f765c11d8df5..f7f5d1932a27 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -47,7 +47,7 @@ struct flow_flush_info {
 
 static struct kmem_cache *flow_cachep __read_mostly;
 
-#define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
+#define flow_cache_hash_size(cache)	(1U << (cache)->hash_shift)
 #define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
 
 static void flow_cache_new_hashrnd(unsigned long arg)
@@ -99,7 +99,8 @@ static void flow_cache_gc_task(struct work_struct *work)
 }
 
 static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
-				     int deleted, struct list_head *gc_list,
+				     unsigned int deleted,
+				     struct list_head *gc_list,
 				     struct netns_xfrm *xfrm)
 {
 	if (deleted) {
@@ -114,17 +115,18 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
 
 static void __flow_cache_shrink(struct flow_cache *fc,
 				struct flow_cache_percpu *fcp,
-				int shrink_to)
+				unsigned int shrink_to)
 {
 	struct flow_cache_entry *fle;
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
-	int i, deleted = 0;
+	unsigned int deleted = 0;
 	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
 						flow_cache_global);
+	unsigned int i;
 
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
-		int saved = 0;
+		unsigned int saved = 0;
 
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
@@ -145,7 +147,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 static void flow_cache_shrink(struct flow_cache *fc,
 			      struct flow_cache_percpu *fcp)
 {
-	int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
+	unsigned int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
 
 	__flow_cache_shrink(fc, fcp, shrink_to);
 }
@@ -161,7 +163,7 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
 static u32 flow_hash_code(struct flow_cache *fc,
 			  struct flow_cache_percpu *fcp,
 			  const struct flowi *key,
-			  size_t keysize)
+			  unsigned int keysize)
 {
 	const u32 *k = (const u32 *) key;
 	const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
@@ -174,7 +176,7 @@ static u32 flow_hash_code(struct flow_cache *fc,
  * important assumptions that we can here, such as alignment.
  */
 static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
-			    size_t keysize)
+			    unsigned int keysize)
 {
 	const flow_compare_t *k1, *k1_lim, *k2;
 
@@ -199,7 +201,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle, *tfle;
 	struct flow_cache_object *flo;
-	size_t keysize;
+	unsigned int keysize;
 	unsigned int hash;
 
 	local_bh_disable();
@@ -295,9 +297,10 @@ static void flow_cache_flush_tasklet(unsigned long data)
 	struct flow_cache_entry *fle;
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
-	int i, deleted = 0;
+	unsigned int deleted = 0;
 	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
 						flow_cache_global);
+	unsigned int i;
 
 	fcp = this_cpu_ptr(fc->percpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
@@ -327,7 +330,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
 static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
 {
 	struct flow_cache_percpu *fcp;
-	int i;
+	unsigned int i;
 
 	fcp = per_cpu_ptr(fc->percpu, cpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++)
@@ -402,12 +405,12 @@ void flow_cache_flush_deferred(struct net *net)
 static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
 {
 	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
-	size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
+	unsigned int sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
 
 	if (!fcp->hash_table) {
 		fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
 		if (!fcp->hash_table) {
-			pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
+			pr_err("NET: failed to allocate flow cache sz %u\n", sz);
 			return -ENOMEM;
 		}
 		fcp->hash_rnd_recalc = 1;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c35aae13c8d2..28d94bce4df8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -113,6 +113,235 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 }
 EXPORT_SYMBOL(__skb_flow_get_ports);
 
+enum flow_dissect_ret {
+	FLOW_DISSECT_RET_OUT_GOOD,
+	FLOW_DISSECT_RET_OUT_BAD,
+	FLOW_DISSECT_RET_OUT_PROTO_AGAIN,
+};
+
+static enum flow_dissect_ret
+__skb_flow_dissect_mpls(const struct sk_buff *skb,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data, int nhoff, int hlen)
+{
+	struct flow_dissector_key_keyid *key_keyid;
+	struct mpls_label *hdr, _hdr[2];
+	u32 entry, label;
+
+	if (!dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_MPLS_ENTROPY) &&
+	    !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS))
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+				   hlen, &_hdr);
+	if (!hdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	entry = ntohl(hdr[0].entry);
+	label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) {
+		struct flow_dissector_key_mpls *key_mpls;
+
+		key_mpls = skb_flow_dissector_target(flow_dissector,
+						     FLOW_DISSECTOR_KEY_MPLS,
+						     target_container);
+		key_mpls->mpls_label = label;
+		key_mpls->mpls_ttl = (entry & MPLS_LS_TTL_MASK)
+					>> MPLS_LS_TTL_SHIFT;
+		key_mpls->mpls_tc = (entry & MPLS_LS_TC_MASK)
+					>> MPLS_LS_TC_SHIFT;
+		key_mpls->mpls_bos = (entry & MPLS_LS_S_MASK)
+					>> MPLS_LS_S_SHIFT;
+	}
+
+	if (label == MPLS_LABEL_ENTROPY) {
+		key_keyid = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
+						      target_container);
+		key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+	}
+	return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_arp(const struct sk_buff *skb,
+		       struct flow_dissector *flow_dissector,
+		       void *target_container, void *data, int nhoff, int hlen)
+{
+	struct flow_dissector_key_arp *key_arp;
+	struct {
+		unsigned char ar_sha[ETH_ALEN];
+		unsigned char ar_sip[4];
+		unsigned char ar_tha[ETH_ALEN];
+		unsigned char ar_tip[4];
+	} *arp_eth, _arp_eth;
+	const struct arphdr *arp;
+	struct arphdr _arp;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP))
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
+				   hlen, &_arp);
+	if (!arp)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
+	    arp->ar_pro != htons(ETH_P_IP) ||
+	    arp->ar_hln != ETH_ALEN ||
+	    arp->ar_pln != 4 ||
+	    (arp->ar_op != htons(ARPOP_REPLY) &&
+	     arp->ar_op != htons(ARPOP_REQUEST)))
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
+				       sizeof(_arp_eth), data,
+				       hlen, &_arp_eth);
+	if (!arp_eth)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	key_arp = skb_flow_dissector_target(flow_dissector,
+					    FLOW_DISSECTOR_KEY_ARP,
+					    target_container);
+
+	memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip));
+	memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip));
+
+	/* Only store the lower byte of the opcode;
+	 * this covers ARPOP_REPLY and ARPOP_REQUEST.
+	 */
+	key_arp->op = ntohs(arp->ar_op) & 0xff;
+
+	ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
+	ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
+
+	return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_gre(const struct sk_buff *skb,
+		       struct flow_dissector_key_control *key_control,
+		       struct flow_dissector *flow_dissector,
+		       void *target_container, void *data,
+		       __be16 *p_proto, int *p_nhoff, int *p_hlen,
+		       unsigned int flags)
+{
+	struct flow_dissector_key_keyid *key_keyid;
+	struct gre_base_hdr *hdr, _hdr;
+	int offset = 0;
+	u16 gre_ver;
+
+	hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr),
+				   data, *p_hlen, &_hdr);
+	if (!hdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	/* Only look inside GRE without routing */
+	if (hdr->flags & GRE_ROUTING)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	/* Only look inside GRE for version 0 and 1 */
+	gre_ver = ntohs(hdr->flags & GRE_VERSION);
+	if (gre_ver > 1)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	*p_proto = hdr->protocol;
+	if (gre_ver) {
+		/* Version1 must be PPTP, and check the flags */
+		if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
+			return FLOW_DISSECT_RET_OUT_GOOD;
+	}
+
+	offset += sizeof(struct gre_base_hdr);
+
+	if (hdr->flags & GRE_CSUM)
+		offset += sizeof(((struct gre_full_hdr *) 0)->csum) +
+			  sizeof(((struct gre_full_hdr *) 0)->reserved1);
+
+	if (hdr->flags & GRE_KEY) {
+		const __be32 *keyid;
+		__be32 _keyid;
+
+		keyid = __skb_header_pointer(skb, *p_nhoff + offset,
+					     sizeof(_keyid),
+					     data, *p_hlen, &_keyid);
+		if (!keyid)
+			return FLOW_DISSECT_RET_OUT_BAD;
+
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+			key_keyid = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_GRE_KEYID,
+							      target_container);
+			if (gre_ver == 0)
+				key_keyid->keyid = *keyid;
+			else
+				key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
+		}
+		offset += sizeof(((struct gre_full_hdr *) 0)->key);
+	}
+
+	if (hdr->flags & GRE_SEQ)
+		offset += sizeof(((struct pptp_gre_header *) 0)->seq);
+
+	if (gre_ver == 0) {
+		if (*p_proto == htons(ETH_P_TEB)) {
+			const struct ethhdr *eth;
+			struct ethhdr _eth;
+
+			eth = __skb_header_pointer(skb, *p_nhoff + offset,
+						   sizeof(_eth),
+						   data, *p_hlen, &_eth);
+			if (!eth)
+				return FLOW_DISSECT_RET_OUT_BAD;
+			*p_proto = eth->h_proto;
+			offset += sizeof(*eth);
+
+			/* Cap headers that we access via pointers at the
+			 * end of the Ethernet header as our maximum alignment
+			 * at that point is only 2 bytes.
+			 */
+			if (NET_IP_ALIGN)
+				*p_hlen = *p_nhoff + offset;
+		}
+	} else { /* version 1, must be PPTP */
+		u8 _ppp_hdr[PPP_HDRLEN];
+		u8 *ppp_hdr;
+
+		if (hdr->flags & GRE_ACK)
+			offset += sizeof(((struct pptp_gre_header *) 0)->ack);
+
+		ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset,
+					       sizeof(_ppp_hdr),
+					       data, *p_hlen, _ppp_hdr);
+		if (!ppp_hdr)
+			return FLOW_DISSECT_RET_OUT_BAD;
+
+		switch (PPP_PROTOCOL(ppp_hdr)) {
+		case PPP_IP:
+			*p_proto = htons(ETH_P_IP);
+			break;
+		case PPP_IPV6:
+			*p_proto = htons(ETH_P_IPV6);
+			break;
+		default:
+			/* Could probably catch some more like MPLS */
+			break;
+		}
+
+		offset += PPP_HDRLEN;
+	}
+
+	*p_nhoff += offset;
+	key_control->flags |= FLOW_DIS_ENCAPSULATION;
+	if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	return FLOW_DISSECT_RET_OUT_PROTO_AGAIN;
+}
+
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -138,12 +367,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_control *key_control;
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
-	struct flow_dissector_key_arp *key_arp;
 	struct flow_dissector_key_ports *key_ports;
 	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
-	struct flow_dissector_key_keyid *key_keyid;
 	bool skip_vlan = false;
 	u8 ip_proto = 0;
 	bool ret;
@@ -181,7 +408,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
 	}
 
-again:
+proto_again:
 	switch (proto) {
 	case htons(ETH_P_IP): {
 		const struct iphdr *iph;
@@ -284,7 +511,7 @@ ipv6:
 			proto = vlan->h_vlan_encapsulated_proto;
 			nhoff += sizeof(*vlan);
 			if (skip_vlan)
-				goto again;
+				goto proto_again;
 		}
 
 		skip_vlan = true;
@@ -307,7 +534,7 @@ ipv6:
 			}
 		}
 
-		goto again;
+		goto proto_again;
 	}
 	case htons(ETH_P_PPP_SES): {
 		struct {
@@ -349,31 +576,17 @@ ipv6:
 	}
 
 	case htons(ETH_P_MPLS_UC):
-	case htons(ETH_P_MPLS_MC): {
-		struct mpls_label *hdr, _hdr[2];
+	case htons(ETH_P_MPLS_MC):
 mpls:
-		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
-					   hlen, &_hdr);
-		if (!hdr)
-			goto out_bad;
-
-		if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
-		     MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
-			if (dissector_uses_key(flow_dissector,
-					       FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
-				key_keyid = skb_flow_dissector_target(flow_dissector,
-								      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
-								      target_container);
-				key_keyid->keyid = hdr[1].entry &
-					htonl(MPLS_LS_LABEL_MASK);
-			}
-
+		switch (__skb_flow_dissect_mpls(skb, flow_dissector,
+						target_container, data,
+						nhoff, hlen)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
 			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
+		default:
+			goto out_bad;
 		}
-
-		goto out_good;
-	}
-
 	case htons(ETH_P_FCOE):
 		if ((hlen - nhoff) < FCOE_HEADER_LEN)
 			goto out_bad;
@@ -382,177 +595,33 @@ mpls:
 		goto out_good;
 
 	case htons(ETH_P_ARP):
-	case htons(ETH_P_RARP): {
-		struct {
-			unsigned char ar_sha[ETH_ALEN];
-			unsigned char ar_sip[4];
-			unsigned char ar_tha[ETH_ALEN];
-			unsigned char ar_tip[4];
-		} *arp_eth, _arp_eth;
-		const struct arphdr *arp;
-		struct arphdr *_arp;
-
-		arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
-					   hlen, &_arp);
-		if (!arp)
-			goto out_bad;
-
-		if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
-		    arp->ar_pro != htons(ETH_P_IP) ||
-		    arp->ar_hln != ETH_ALEN ||
-		    arp->ar_pln != 4 ||
-		    (arp->ar_op != htons(ARPOP_REPLY) &&
-		     arp->ar_op != htons(ARPOP_REQUEST)))
-			goto out_bad;
-
-		arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
-					       sizeof(_arp_eth), data,
-					       hlen,
-					       &_arp_eth);
-		if (!arp_eth)
+	case htons(ETH_P_RARP):
+		switch (__skb_flow_dissect_arp(skb, flow_dissector,
+					       target_container, data,
+					       nhoff, hlen)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
+			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
+		default:
 			goto out_bad;
-
-		if (dissector_uses_key(flow_dissector,
-				       FLOW_DISSECTOR_KEY_ARP)) {
-
-			key_arp = skb_flow_dissector_target(flow_dissector,
-							    FLOW_DISSECTOR_KEY_ARP,
-							    target_container);
-
-			memcpy(&key_arp->sip, arp_eth->ar_sip,
-			       sizeof(key_arp->sip));
-			memcpy(&key_arp->tip, arp_eth->ar_tip,
-			       sizeof(key_arp->tip));
-
-			/* Only store the lower byte of the opcode;
-			 * this covers ARPOP_REPLY and ARPOP_REQUEST.
-			 */
-			key_arp->op = ntohs(arp->ar_op) & 0xff;
-
-			ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
-			ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
 		}
-
-		goto out_good;
-	}
-
 	default:
 		goto out_bad;
 	}
 
 ip_proto_again:
 	switch (ip_proto) {
-	case IPPROTO_GRE: {
-		struct gre_base_hdr *hdr, _hdr;
-		u16 gre_ver;
-		int offset = 0;
-
-		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
-		if (!hdr)
+	case IPPROTO_GRE:
+		switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector,
+					       target_container, data,
+					       &proto, &nhoff, &hlen, flags)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
+			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
 			goto out_bad;
-
-		/* Only look inside GRE without routing */
-		if (hdr->flags & GRE_ROUTING)
-			break;
-
-		/* Only look inside GRE for version 0 and 1 */
-		gre_ver = ntohs(hdr->flags & GRE_VERSION);
-		if (gre_ver > 1)
-			break;
-
-		proto = hdr->protocol;
-		if (gre_ver) {
-			/* Version1 must be PPTP, and check the flags */
-			if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
-				break;
-		}
-
-		offset += sizeof(struct gre_base_hdr);
-
-		if (hdr->flags & GRE_CSUM)
-			offset += sizeof(((struct gre_full_hdr *)0)->csum) +
-				  sizeof(((struct gre_full_hdr *)0)->reserved1);
-
-		if (hdr->flags & GRE_KEY) {
-			const __be32 *keyid;
-			__be32 _keyid;
-
-			keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid),
-						     data, hlen, &_keyid);
-			if (!keyid)
-				goto out_bad;
-
-			if (dissector_uses_key(flow_dissector,
-					       FLOW_DISSECTOR_KEY_GRE_KEYID)) {
-				key_keyid = skb_flow_dissector_target(flow_dissector,
-								      FLOW_DISSECTOR_KEY_GRE_KEYID,
-								      target_container);
-				if (gre_ver == 0)
-					key_keyid->keyid = *keyid;
-				else
-					key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
-			}
-			offset += sizeof(((struct gre_full_hdr *)0)->key);
-		}
-
-		if (hdr->flags & GRE_SEQ)
-			offset += sizeof(((struct pptp_gre_header *)0)->seq);
-
-		if (gre_ver == 0) {
-			if (proto == htons(ETH_P_TEB)) {
-				const struct ethhdr *eth;
-				struct ethhdr _eth;
-
-				eth = __skb_header_pointer(skb, nhoff + offset,
-							   sizeof(_eth),
-							   data, hlen, &_eth);
-				if (!eth)
-					goto out_bad;
-				proto = eth->h_proto;
-				offset += sizeof(*eth);
-
-				/* Cap headers that we access via pointers at the
-				 * end of the Ethernet header as our maximum alignment
-				 * at that point is only 2 bytes.
-				 */
-				if (NET_IP_ALIGN)
-					hlen = (nhoff + offset);
-			}
-		} else { /* version 1, must be PPTP */
-			u8 _ppp_hdr[PPP_HDRLEN];
-			u8 *ppp_hdr;
-
-			if (hdr->flags & GRE_ACK)
-				offset += sizeof(((struct pptp_gre_header *)0)->ack);
-
-			ppp_hdr = __skb_header_pointer(skb, nhoff + offset,
-						     sizeof(_ppp_hdr),
-						     data, hlen, _ppp_hdr);
-			if (!ppp_hdr)
-				goto out_bad;
-
-			switch (PPP_PROTOCOL(ppp_hdr)) {
-			case PPP_IP:
-				proto = htons(ETH_P_IP);
-				break;
-			case PPP_IPV6:
-				proto = htons(ETH_P_IPV6);
-				break;
-			default:
-				/* Could probably catch some more like MPLS */
-				break;
-			}
-
-			offset += PPP_HDRLEN;
+		case FLOW_DISSECT_RET_OUT_PROTO_AGAIN:
+			goto proto_again;
 		}
-
-		nhoff += offset;
-		key_control->flags |= FLOW_DIS_ENCAPSULATION;
-		if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
-			goto out_good;
-
-		goto again;
-	}
 	case NEXTHDR_HOP:
 	case NEXTHDR_ROUTING:
 	case NEXTHDR_DEST: {
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index c98bbfbd26b8..814e58a3ce8b 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -13,7 +13,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	struct gro_cell *cell;
 
-	if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO))
+	if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev))
 		return netif_rx(skb);
 
 	cell = this_cpu_ptr(gcells->cells);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 0cfe7b0216c3..b3bc0a31af9f 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -209,7 +209,8 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
 	int ret;
 	u32 fd;
 
-	ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy);
+	ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy,
+			       NULL);
 	if (ret < 0)
 		return ret;
 
@@ -249,7 +250,7 @@ static int bpf_build_state(struct nlattr *nla,
 	if (family != AF_INET && family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy);
+	ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 6df9f8fabf0c..cfae3d5fe11f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
 	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
 	struct nlattr *nla_entype;
 	struct nlattr *attrs;
-	struct nlattr *nla;
 	u16 encap_type;
 	int attrlen;
 
@@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
 			attrs = rtnh_attrs(rtnh);
-			nla = nla_find(attrs, attrlen, RTA_ENCAP);
 			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 
 			if (nla_entype) {
@@ -205,7 +203,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 {
 	const struct lwtunnel_encap_ops *ops;
 	struct nlattr *nest;
-	int ret = -EINVAL;
+	int ret;
 
 	if (!lwtstate)
 		return 0;
@@ -214,8 +212,11 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
 		return 0;
 
-	ret = -EOPNOTSUPP;
 	nest = nla_nest_start(skb, RTA_ENCAP);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
 	if (likely(ops && ops->fill_encap))
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e7c12caa20c8..58b0bcc125b5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -52,8 +52,9 @@ do {						\
 #define PNEIGH_HASHMASK		0xF
 
 static void neigh_timer_handler(unsigned long arg);
-static void __neigh_notify(struct neighbour *n, int type, int flags);
-static void neigh_update_notify(struct neighbour *neigh);
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+			   u32 pid);
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
 static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
 
 #ifdef CONFIG_PROC_FS
@@ -99,7 +100,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
 	if (neigh->parms->neigh_cleanup)
 		neigh->parms->neigh_cleanup(neigh);
 
-	__neigh_notify(neigh, RTM_DELNEIGH, 0);
+	__neigh_notify(neigh, RTM_DELNEIGH, 0, 0);
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
 	neigh_release(neigh);
 }
@@ -860,7 +861,8 @@ static void neigh_probe(struct neighbour *neigh)
 	if (skb)
 		skb = skb_clone(skb, GFP_ATOMIC);
 	write_unlock(&neigh->lock);
-	neigh->ops->solicit(neigh, skb);
+	if (neigh->ops->solicit)
+		neigh->ops->solicit(neigh, skb);
 	atomic_inc(&neigh->probes);
 	kfree_skb(skb);
 }
@@ -948,7 +950,7 @@ out:
 	}
 
 	if (notify)
-		neigh_update_notify(neigh);
+		neigh_update_notify(neigh, 0);
 
 	neigh_release(neigh);
 }
@@ -1072,7 +1074,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
  */
 
 int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
-		 u32 flags)
+		 u32 flags, u32 nlmsg_pid)
 {
 	u8 old;
 	int err;
@@ -1229,7 +1231,7 @@ out:
 	write_unlock_bh(&neigh->lock);
 
 	if (notify)
-		neigh_update_notify(neigh);
+		neigh_update_notify(neigh, nlmsg_pid);
 
 	return err;
 }
@@ -1260,7 +1262,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 						 lladdr || !dev->addr_len);
 	if (neigh)
 		neigh_update(neigh, lladdr, NUD_STALE,
-			     NEIGH_UPDATE_F_OVERRIDE);
+			     NEIGH_UPDATE_F_OVERRIDE, 0);
 	return neigh;
 }
 EXPORT_SYMBOL(neigh_event_ns);
@@ -1588,7 +1590,8 @@ static struct neigh_table *neigh_find_table(int family)
 	return tbl;
 }
 
-static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -1638,14 +1641,16 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	err = neigh_update(neigh, NULL, NUD_FAILED,
 			   NEIGH_UPDATE_F_OVERRIDE |
-			   NEIGH_UPDATE_F_ADMIN);
+			   NEIGH_UPDATE_F_ADMIN,
+			   NETLINK_CB(skb).portid);
 	neigh_release(neigh);
 
 out:
 	return err;
 }
 
-static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
+		     struct netlink_ext_ack *extack)
 {
 	int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
 	struct net *net = sock_net(skb->sk);
@@ -1658,7 +1663,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 
 	ASSERT_RTNL();
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
 	if (err < 0)
 		goto out;
 
@@ -1729,7 +1734,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		neigh_event_send(neigh, NULL);
 		err = 0;
 	} else
-		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+				   NETLINK_CB(skb).portid);
 	neigh_release(neigh);
 
 out:
@@ -1932,7 +1938,8 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_LOCKTIME]		= { .type = NLA_U64 },
 };
 
-static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct neigh_table *tbl;
@@ -1942,7 +1949,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err, tidx;
 
 	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
-			  nl_neightbl_policy);
+			  nl_neightbl_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -1980,7 +1987,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 		int i, ifindex = 0;
 
 		err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS],
-				       nl_ntbl_parm_policy);
+				       nl_ntbl_parm_policy, extack);
 		if (err < 0)
 			goto errout_tbl_lock;
 
@@ -2229,10 +2236,10 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void neigh_update_notify(struct neighbour *neigh)
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid)
 {
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
-	__neigh_notify(neigh, RTM_NEWNEIGH, 0);
+	__neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid);
 }
 
 static bool neigh_master_filtered(struct net_device *dev, int master_idx)
@@ -2271,7 +2278,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 	unsigned int flags = NLM_F_MULTI;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
 	if (!err) {
 		if (tb[NDA_IFINDEX])
 			filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
@@ -2830,7 +2837,8 @@ static inline size_t neigh_nlmsg_size(void)
 	       + nla_total_size(4); /* NDA_PROBES */
 }
 
-static void __neigh_notify(struct neighbour *n, int type, int flags)
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+			   u32 pid)
 {
 	struct net *net = dev_net(n->dev);
 	struct sk_buff *skb;
@@ -2840,7 +2848,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
 	if (skb == NULL)
 		goto errout;
 
-	err = neigh_fill_info(skb, n, 0, 0, type, flags);
+	err = neigh_fill_info(skb, n, pid, 0, type, flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in neigh_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2856,7 +2864,7 @@ errout:
 
 void neigh_app_ns(struct neighbour *n)
 {
-	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST);
+	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0);
 }
 EXPORT_SYMBOL(neigh_app_ns);
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 3945821e9c1f..65ea0ff4017c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -953,7 +953,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct kobject *kobj = &dev->_rx[i].kobj;
 
-		if (!list_empty(&dev_net(dev)->exit_list))
+		if (!atomic_read(&dev_net(dev)->count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1371,7 +1371,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct netdev_queue *queue = dev->_tx + i;
 
-		if (!list_empty(&dev_net(dev)->exit_list))
+		if (!atomic_read(&dev_net(dev)->count))
 			queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
 		sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1558,7 +1558,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
 {
 	struct device *dev = &(ndev->dev);
 
-	if (!list_empty(&dev_net(ndev)->exit_list))
+	if (!atomic_read(&dev_net(ndev)->count))
 		dev_set_uevent_suppress(dev, 1);
 
 	kobject_get(&dev->kobj);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 652468ff65b7..1934efd4a9d4 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -35,7 +35,8 @@ LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
 
 struct net init_net = {
-	.dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
+	.count		= ATOMIC_INIT(1),
+	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
 };
 EXPORT_SYMBOL(init_net);
 
@@ -571,7 +572,8 @@ static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
 	[NETNSA_FD]		= { .type = NLA_U32 },
 };
 
-static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[NETNSA_MAX + 1];
@@ -579,7 +581,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int nsid, err;
 
 	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-			  rtnl_net_policy);
+			  rtnl_net_policy, extack);
 	if (err < 0)
 		return err;
 	if (!tb[NETNSA_NSID])
@@ -644,7 +646,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[NETNSA_MAX + 1];
@@ -653,7 +656,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err, id;
 
 	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-			  rtnl_net_policy);
+			  rtnl_net_policy, extack);
 	if (err < 0)
 		return err;
 	if (tb[NETNSA_PID])
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6ae56037bb13..029a61ac6cdd 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -71,27 +71,17 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n)
 	return 0;
 }
 
-static void update_classid(struct cgroup_subsys_state *css, void *v)
+static void cgrp_attach(struct cgroup_taskset *tset)
 {
-	struct css_task_iter it;
+	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
-	css_task_iter_start(css, &it);
-	while ((p = css_task_iter_next(&it))) {
+	cgroup_taskset_for_each(p, css, tset) {
 		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock, v);
+		iterate_fd(p->files, 0, update_classid_sock,
+			   (void *)(unsigned long)css_cls_state(css)->classid);
 		task_unlock(p);
 	}
-	css_task_iter_end(&it);
-}
-
-static void cgrp_attach(struct cgroup_taskset *tset)
-{
-	struct cgroup_subsys_state *css;
-
-	cgroup_taskset_first(tset, &css);
-	update_classid(css,
-		       (void *)(unsigned long)css_cls_state(css)->classid);
 }
 
 static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -103,12 +93,22 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 			 u64 value)
 {
 	struct cgroup_cls_state *cs = css_cls_state(css);
+	struct css_task_iter it;
+	struct task_struct *p;
 
 	cgroup_sk_alloc_disable();
 
 	cs->classid = (u32)value;
 
-	update_classid(css, (void *)(unsigned long)cs->classid);
+	css_task_iter_start(css, &it);
+	while ((p = css_task_iter_next(&it))) {
+		task_lock(p);
+		iterate_fd(p->files, 0, update_classid_sock,
+			   (void *)(unsigned long)cs->classid);
+		task_unlock(p);
+	}
+	css_task_iter_end(&it);
+
 	return 0;
 }
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 9424673009c1..29be2466970c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work)
 	while ((skb = skb_dequeue(&npinfo->txq))) {
 		struct net_device *dev = skb->dev;
 		struct netdev_queue *txq;
+		unsigned int q_index;
 
 		if (!netif_device_present(dev) || !netif_running(dev)) {
 			kfree_skb(skb);
 			continue;
 		}
 
-		txq = skb_get_tx_queue(dev, skb);
-
 		local_irq_save(flags);
+		/* check if skb->queue_mapping is still valid */
+		q_index = skb_get_queue_mapping(skb);
+		if (unlikely(q_index >= dev->real_num_tx_queues)) {
+			q_index = q_index % dev->real_num_tx_queues;
+			skb_set_queue_mapping(skb, q_index);
+		}
+		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
 		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 0f9275ee5595..1c4810919a0a 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c4e84c558240..6e67315ec368 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -896,15 +896,13 @@ static size_t rtnl_port_size(const struct net_device *dev,
 		return port_self_size;
 }
 
-static size_t rtnl_xdp_size(const struct net_device *dev)
+static size_t rtnl_xdp_size(void)
 {
 	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
-			  nla_total_size(1);	/* XDP_ATTACHED */
+			  nla_total_size(1) +	/* XDP_ATTACHED */
+			  nla_total_size(4);	/* XDP_FLAGS */
 
-	if (!dev->netdev_ops->ndo_xdp)
-		return 0;
-	else
-		return xdp_size;
+	return xdp_size;
 }
 
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
@@ -943,7 +941,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
 	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
-	       + rtnl_xdp_size(dev) /* IFLA_XDP */
+	       + rtnl_xdp_size() /* IFLA_XDP */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
@@ -1251,23 +1249,35 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 {
-	struct netdev_xdp xdp_op = {};
 	struct nlattr *xdp;
+	u32 xdp_flags = 0;
+	u8 val = 0;
 	int err;
 
-	if (!dev->netdev_ops->ndo_xdp)
-		return 0;
 	xdp = nla_nest_start(skb, IFLA_XDP);
 	if (!xdp)
 		return -EMSGSIZE;
-	xdp_op.command = XDP_QUERY_PROG;
-	err = dev->netdev_ops->ndo_xdp(dev, &xdp_op);
-	if (err)
-		goto err_cancel;
-	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, xdp_op.prog_attached);
+	if (rcu_access_pointer(dev->xdp_prog)) {
+		xdp_flags = XDP_FLAGS_SKB_MODE;
+		val = 1;
+	} else if (dev->netdev_ops->ndo_xdp) {
+		struct netdev_xdp xdp_op = {};
+
+		xdp_op.command = XDP_QUERY_PROG;
+		err = dev->netdev_ops->ndo_xdp(dev, &xdp_op);
+		if (err)
+			goto err_cancel;
+		val = xdp_op.prog_attached;
+	}
+	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val);
 	if (err)
 		goto err_cancel;
 
+	if (xdp_flags) {
+		err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags);
+		if (err)
+			goto err_cancel;
+	}
 	nla_nest_end(skb, xdp);
 	return 0;
 
@@ -1515,7 +1525,8 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
 	const struct rtnl_link_ops *ops = NULL;
 	struct nlattr *linfo[IFLA_INFO_MAX + 1];
 
-	if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla, ifla_info_policy) < 0)
+	if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla,
+			     ifla_info_policy, NULL) < 0)
 		return NULL;
 
 	if (linfo[IFLA_INFO_KIND]) {
@@ -1592,8 +1603,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
 		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
-
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
+			ifla_policy, NULL) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 
@@ -1640,9 +1651,10 @@ out:
 	return skb->len;
 }
 
-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
+			struct netlink_ext_ack *exterr)
 {
-	return nla_parse(tb, IFLA_MAX, head, len, ifla_policy);
+	return nla_parse(tb, IFLA_MAX, head, len, ifla_policy, exterr);
 }
 EXPORT_SYMBOL(rtnl_nla_parse_ifla);
 
@@ -1907,6 +1919,7 @@ static int do_set_master(struct net_device *dev, int ifindex)
 #define DO_SETLINK_NOTIFY	0x03
 static int do_setlink(const struct sk_buff *skb,
 		      struct net_device *dev, struct ifinfomsg *ifm,
+		      struct netlink_ext_ack *extack,
 		      struct nlattr **tb, char *ifname, int status)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -2078,7 +2091,7 @@ static int do_setlink(const struct sk_buff *skb,
 				goto errout;
 			}
 			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
-					       ifla_vf_policy);
+					       ifla_vf_policy, NULL);
 			if (err < 0)
 				goto errout;
 			err = do_setvfinfo(dev, vfinfo);
@@ -2106,7 +2119,7 @@ static int do_setlink(const struct sk_buff *skb,
 				goto errout;
 			}
 			err = nla_parse_nested(port, IFLA_PORT_MAX, attr,
-					       ifla_port_policy);
+					       ifla_port_policy, NULL);
 			if (err < 0)
 				goto errout;
 			if (!port[IFLA_PORT_VF]) {
@@ -2126,7 +2139,8 @@ static int do_setlink(const struct sk_buff *skb,
 		struct nlattr *port[IFLA_PORT_MAX+1];
 
 		err = nla_parse_nested(port, IFLA_PORT_MAX,
-			tb[IFLA_PORT_SELF], ifla_port_policy);
+				       tb[IFLA_PORT_SELF], ifla_port_policy,
+				       NULL);
 		if (err < 0)
 			goto errout;
 
@@ -2170,7 +2184,7 @@ static int do_setlink(const struct sk_buff *skb,
 		u32 xdp_flags = 0;
 
 		err = nla_parse_nested(xdp, IFLA_XDP_MAX, tb[IFLA_XDP],
-				       ifla_xdp_policy);
+				       ifla_xdp_policy, NULL);
 		if (err < 0)
 			goto errout;
 
@@ -2188,7 +2202,7 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 
 		if (xdp[IFLA_XDP_FD]) {
-			err = dev_change_xdp_fd(dev,
+			err = dev_change_xdp_fd(dev, extack,
 						nla_get_s32(xdp[IFLA_XDP_FD]),
 						xdp_flags);
 			if (err)
@@ -2210,7 +2224,8 @@ errout:
 	return err;
 }
 
-static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2219,7 +2234,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	char ifname[IFNAMSIZ];
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -2246,7 +2262,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
-	err = do_setlink(skb, dev, ifm, tb, ifname, 0);
+	err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
 errout:
 	return err;
 }
@@ -2303,7 +2319,8 @@ int rtnl_delete_link(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(rtnl_delete_link);
 
-static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *dev;
@@ -2312,7 +2329,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2407,6 +2424,7 @@ EXPORT_SYMBOL(rtnl_create_link);
 static int rtnl_group_changelink(const struct sk_buff *skb,
 		struct net *net, int group,
 		struct ifinfomsg *ifm,
+		struct netlink_ext_ack *extack,
 		struct nlattr **tb)
 {
 	struct net_device *dev, *aux;
@@ -2414,7 +2432,7 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 
 	for_each_netdev_safe(net, dev, aux) {
 		if (dev->group == group) {
-			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
+			err = do_setlink(skb, dev, ifm, extack, tb, NULL, 0);
 			if (err < 0)
 				return err;
 		}
@@ -2423,7 +2441,8 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 	return 0;
 }
 
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
@@ -2441,7 +2460,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 #ifdef CONFIG_MODULES
 replay:
 #endif
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2472,7 +2491,8 @@ replay:
 
 	if (tb[IFLA_LINKINFO]) {
 		err = nla_parse_nested(linkinfo, IFLA_INFO_MAX,
-				       tb[IFLA_LINKINFO], ifla_info_policy);
+				       tb[IFLA_LINKINFO], ifla_info_policy,
+				       NULL);
 		if (err < 0)
 			return err;
 	} else
@@ -2497,7 +2517,7 @@ replay:
 			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
 				err = nla_parse_nested(attr, ops->maxtype,
 						       linkinfo[IFLA_INFO_DATA],
-						       ops->policy);
+						       ops->policy, NULL);
 				if (err < 0)
 					return err;
 				data = attr;
@@ -2515,7 +2535,8 @@ replay:
 				err = nla_parse_nested(slave_attr,
 						       m_ops->slave_maxtype,
 						       linkinfo[IFLA_INFO_SLAVE_DATA],
-						       m_ops->slave_policy);
+						       m_ops->slave_policy,
+						       NULL);
 				if (err < 0)
 					return err;
 				slave_data = slave_attr;
@@ -2557,14 +2578,15 @@ replay:
 				status |= DO_SETLINK_NOTIFY;
 			}
 
-			return do_setlink(skb, dev, ifm, tb, ifname, status);
+			return do_setlink(skb, dev, ifm, extack, tb, ifname,
+					  status);
 		}
 
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
 				return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
-						ifm, tb);
+						ifm, extack, tb);
 			return -ENODEV;
 		}
 
@@ -2673,7 +2695,8 @@ out_unregister:
 	}
 }
 
-static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2684,7 +2707,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
 	int err;
 	u32 ext_filter_mask = 0;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2734,7 +2757,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
 		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -2955,7 +2978,8 @@ static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
 	return 0;
 }
 
-static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -2965,7 +2989,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u16 vid;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -3055,7 +3079,8 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_del);
 
-static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -3068,7 +3093,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -3203,8 +3228,8 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int err = 0;
 	int fidx = 0;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) == 0) {
+	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
+			IFLA_MAX, ifla_policy, NULL) == 0) {
 		if (tb[IFLA_MASTER])
 			br_idx = nla_get_u32(tb[IFLA_MASTER]);
 	}
@@ -3498,7 +3523,8 @@ errout:
 	return err;
 }
 
-static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -3572,7 +3598,8 @@ out:
 	return err;
 }
 
-static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -3940,7 +3967,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
 	return size;
 }
 
-static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *dev = NULL;
@@ -4046,7 +4074,8 @@ out:
 
 /* Process one rtnetlink message. */
 
-static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	rtnl_doit_func doit;
@@ -4101,7 +4130,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (doit == NULL)
 		return -EOPNOTSUPP;
 
-	return doit(skb, nlh);
+	return doit(skb, nlh, extack);
 }
 
 static void rtnetlink_rcv(struct sk_buff *skb)
@@ -4116,22 +4145,16 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
 	switch (event) {
-	case NETDEV_UP:
-	case NETDEV_DOWN:
-	case NETDEV_PRE_UP:
-	case NETDEV_POST_INIT:
-	case NETDEV_REGISTER:
-	case NETDEV_CHANGE:
-	case NETDEV_PRE_TYPE_CHANGE:
-	case NETDEV_GOING_DOWN:
-	case NETDEV_UNREGISTER:
-	case NETDEV_UNREGISTER_FINAL:
-	case NETDEV_RELEASE:
-	case NETDEV_JOIN:
-	case NETDEV_BONDING_INFO:
+	case NETDEV_REBOOT:
+	case NETDEV_CHANGENAME:
+	case NETDEV_FEAT_CHANGE:
+	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_RESEND_IGMP:
+	case NETDEV_CHANGEINFODATA:
+		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	default:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	}
 	return NOTIFY_DONE;
@@ -4185,6 +4208,7 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
 	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL);
 
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 758f140b6bed..6bd2f8fb0476 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -20,9 +20,11 @@
 #include <net/tcp.h>
 
 static siphash_key_t net_secret __read_mostly;
+static siphash_key_t ts_secret __read_mostly;
 
 static __always_inline void net_secret_init(void)
 {
+	net_get_random_once(&ts_secret, sizeof(ts_secret));
 	net_get_random_once(&net_secret, sizeof(net_secret));
 }
 #endif
@@ -45,8 +47,25 @@ static u32 seq_scale(u32 seq)
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff)
+static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+{
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+	};
+
+	if (sysctl_tcp_timestamps != 1)
+		return 0;
+
+	return siphash(&combined, offsetofend(typeof(combined), daddr),
+		       &ts_secret);
+}
+
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
+			       __be16 sport, __be16 dport, u32 *tsoff)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -63,10 +82,10 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 	net_secret_init();
 	hash = siphash(&combined, offsetofend(typeof(combined), dport),
 		       &net_secret);
-	*tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+	*tsoff = secure_tcpv6_ts_off(saddr, daddr);
 	return seq_scale(hash);
 }
-EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff);
 
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
@@ -88,22 +107,29 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
+static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+{
+	if (sysctl_tcp_timestamps != 1)
+		return 0;
 
-/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
+	return siphash_2u32((__force u32)saddr, (__force u32)daddr,
+			    &ts_secret);
+}
+
+/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
  * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
  * it would be easy enough to have the former function use siphash_4u32, passing
  * the arguments as separate u32.
  */
-
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-			       __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+			     __be16 sport, __be16 dport, u32 *tsoff)
 {
 	u64 hash;
 	net_secret_init();
 	hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
 			    (__force u32)sport << 16 | (__force u32)dport,
 			    &net_secret);
-	*tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+	*tsoff = secure_tcp_ts_off(saddr, daddr);
 	return seq_scale(hash);
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f3557958e9bf..346d3e85dfbc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1576,6 +1576,8 @@ done:
 		skb_set_tail_pointer(skb, len);
 	}
 
+	if (!skb->sk || skb->destructor == sock_edemux)
+		skb_condense(skb);
 	return 0;
 }
 EXPORT_SYMBOL(___pskb_trim);
@@ -1980,7 +1982,6 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 		.pages = pages,
 		.partial = partial,
 		.nr_pages_max = MAX_SKB_FRAGS,
-		.flags = flags,
 		.ops = &nosteal_pipe_buf_ops,
 		.spd_release = sock_spd_release,
 	};
@@ -3082,22 +3083,32 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	if (sg && csum && (mss != GSO_BY_FRAGS))  {
 		if (!(features & NETIF_F_GSO_PARTIAL)) {
 			struct sk_buff *iter;
+			unsigned int frag_len;
 
 			if (!list_skb ||
 			    !net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
 				goto normal;
 
-			/* Split the buffer at the frag_list pointer.
-			 * This is based on the assumption that all
-			 * buffers in the chain excluding the last
-			 * containing the same amount of data.
+			/* If we get here then all the required
+			 * GSO features except frag_list are supported.
+			 * Try to split the SKB to multiple GSO SKBs
+			 * with no frag_list.
+			 * Currently we can do that only when the buffers don't
+			 * have a linear part and all the buffers except
+			 * the last are of the same length.
 			 */
+			frag_len = list_skb->len;
 			skb_walk_frags(head_skb, iter) {
-				if (skb_headlen(iter))
+				if (frag_len != iter->len && iter->next)
+					goto normal;
+				if (skb_headlen(iter) && !iter->head_frag)
 					goto normal;
 
 				len -= iter->len;
 			}
+
+			if (len != frag_len)
+				goto normal;
 		}
 
 		/* GSO partial only requires that we trim off any excess that
@@ -3694,6 +3705,15 @@ static void sock_rmem_free(struct sk_buff *skb)
 	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 }
 
+static void skb_set_err_queue(struct sk_buff *skb)
+{
+	/* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
+	 * So, it is safe to (mis)use it to mark skbs on the error queue.
+	 */
+	skb->pkt_type = PACKET_OUTGOING;
+	BUILD_BUG_ON(PACKET_OUTGOING == 0);
+}
+
 /*
  * Note: We dont mem charge error packets (no sk_forward_alloc changes)
  */
@@ -3707,6 +3727,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 	skb->sk = sk;
 	skb->destructor = sock_rmem_free;
 	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+	skb_set_err_queue(skb);
 
 	/* before exiting rcu section, make sure dst is refcounted */
 	skb_dst_force(skb);
@@ -3783,16 +3804,21 @@ EXPORT_SYMBOL(skb_clone_sk);
 
 static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 					struct sock *sk,
-					int tstype)
+					int tstype,
+					bool opt_stats)
 {
 	struct sock_exterr_skb *serr;
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb));
+
 	serr = SKB_EXT_ERR(skb);
 	memset(serr, 0, sizeof(*serr));
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
+	serr->opt_stats = opt_stats;
+	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&
@@ -3828,13 +3854,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	if (!skb_may_tx_timestamp(sk, false))
 		return;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	*skb_hwtstamps(skb) = *hwtstamps;
-	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
-	sock_put(sk);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		*skb_hwtstamps(skb) = *hwtstamps;
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
+		sock_put(sk);
+	}
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
@@ -3843,7 +3870,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct sock *sk, int tstype)
 {
 	struct sk_buff *skb;
-	bool tsonly;
+	bool tsonly, opt_stats = false;
 
 	if (!sk)
 		return;
@@ -3856,9 +3883,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 #ifdef CONFIG_INET
 		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
 		    sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM)
+		    sk->sk_type == SOCK_STREAM) {
 			skb = tcp_get_timestamping_opt_stats(sk);
-		else
+			opt_stats = true;
+		} else
 #endif
 			skb = alloc_skb(0, GFP_ATOMIC);
 	} else {
@@ -3877,7 +3905,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	else
 		skb->tstamp = ktime_get_real();
 
-	__skb_complete_tx_timestamp(skb, sk, tstype);
+	__skb_complete_tx_timestamp(skb, sk, tstype, opt_stats);
 }
 EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
 
@@ -3893,7 +3921,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 {
 	struct sock *sk = skb->sk;
 	struct sock_exterr_skb *serr;
-	int err;
+	int err = 1;
 
 	skb->wifi_acked_valid = 1;
 	skb->wifi_acked = acked;
@@ -3903,14 +3931,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	err = sock_queue_err_skb(sk, skb);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		err = sock_queue_err_skb(sk, skb);
+		sock_put(sk);
+	}
 	if (err)
 		kfree_skb(skb);
-
-	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index f6fd79f33097..b5baeb9cb0fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -197,73 +197,117 @@ EXPORT_SYMBOL(sk_net_capable);
 
 /*
  * Each address family might have different locking rules, so we have
- * one slock key per address family:
+ * one slock key per address family and separate keys for internal and
+ * userspace sockets.
  */
 static struct lock_class_key af_family_keys[AF_MAX];
+static struct lock_class_key af_family_kern_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
+static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
 
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket
  * locks is fast):
  */
+
+#define _sock_locks(x)						  \
+  x "AF_UNSPEC",	x "AF_UNIX"     ,	x "AF_INET"     , \
+  x "AF_AX25"  ,	x "AF_IPX"      ,	x "AF_APPLETALK", \
+  x "AF_NETROM",	x "AF_BRIDGE"   ,	x "AF_ATMPVC"   , \
+  x "AF_X25"   ,	x "AF_INET6"    ,	x "AF_ROSE"     , \
+  x "AF_DECnet",	x "AF_NETBEUI"  ,	x "AF_SECURITY" , \
+  x "AF_KEY"   ,	x "AF_NETLINK"  ,	x "AF_PACKET"   , \
+  x "AF_ASH"   ,	x "AF_ECONET"   ,	x "AF_ATMSVC"   , \
+  x "AF_RDS"   ,	x "AF_SNA"      ,	x "AF_IRDA"     , \
+  x "AF_PPPOX" ,	x "AF_WANPIPE"  ,	x "AF_LLC"      , \
+  x "27"       ,	x "28"          ,	x "AF_CAN"      , \
+  x "AF_TIPC"  ,	x "AF_BLUETOOTH",	x "IUCV"        , \
+  x "AF_RXRPC" ,	x "AF_ISDN"     ,	x "AF_PHONET"   , \
+  x "AF_IEEE802154",	x "AF_CAIF"	,	x "AF_ALG"      , \
+  x "AF_NFC"   ,	x "AF_VSOCK"    ,	x "AF_KCM"      , \
+  x "AF_QIPCRTR",	x "AF_SMC"	,	x "AF_MAX"
+
 static const char *const af_family_key_strings[AF_MAX+1] = {
-  "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX"     , "sk_lock-AF_INET"     ,
-  "sk_lock-AF_AX25"  , "sk_lock-AF_IPX"      , "sk_lock-AF_APPLETALK",
-  "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE"   , "sk_lock-AF_ATMPVC"   ,
-  "sk_lock-AF_X25"   , "sk_lock-AF_INET6"    , "sk_lock-AF_ROSE"     ,
-  "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI"  , "sk_lock-AF_SECURITY" ,
-  "sk_lock-AF_KEY"   , "sk_lock-AF_NETLINK"  , "sk_lock-AF_PACKET"   ,
-  "sk_lock-AF_ASH"   , "sk_lock-AF_ECONET"   , "sk_lock-AF_ATMSVC"   ,
-  "sk_lock-AF_RDS"   , "sk_lock-AF_SNA"      , "sk_lock-AF_IRDA"     ,
-  "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE"  , "sk_lock-AF_LLC"      ,
-  "sk_lock-27"       , "sk_lock-28"          , "sk_lock-AF_CAN"      ,
-  "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV"        ,
-  "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN"     , "sk_lock-AF_PHONET"   ,
-  "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG"      ,
-  "sk_lock-AF_NFC"   , "sk_lock-AF_VSOCK"    , "sk_lock-AF_KCM"      ,
-  "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC"     , "sk_lock-AF_MAX"
+	_sock_locks("sk_lock-")
 };
 static const char *const af_family_slock_key_strings[AF_MAX+1] = {
-  "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
-  "slock-AF_AX25"  , "slock-AF_IPX"      , "slock-AF_APPLETALK",
-  "slock-AF_NETROM", "slock-AF_BRIDGE"   , "slock-AF_ATMPVC"   ,
-  "slock-AF_X25"   , "slock-AF_INET6"    , "slock-AF_ROSE"     ,
-  "slock-AF_DECnet", "slock-AF_NETBEUI"  , "slock-AF_SECURITY" ,
-  "slock-AF_KEY"   , "slock-AF_NETLINK"  , "slock-AF_PACKET"   ,
-  "slock-AF_ASH"   , "slock-AF_ECONET"   , "slock-AF_ATMSVC"   ,
-  "slock-AF_RDS"   , "slock-AF_SNA"      , "slock-AF_IRDA"     ,
-  "slock-AF_PPPOX" , "slock-AF_WANPIPE"  , "slock-AF_LLC"      ,
-  "slock-27"       , "slock-28"          , "slock-AF_CAN"      ,
-  "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_IUCV"     ,
-  "slock-AF_RXRPC" , "slock-AF_ISDN"     , "slock-AF_PHONET"   ,
-  "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG"      ,
-  "slock-AF_NFC"   , "slock-AF_VSOCK"    ,"slock-AF_KCM"       ,
-  "slock-AF_QIPCRTR", "slock-AF_SMC"     , "slock-AF_MAX"
+	_sock_locks("slock-")
 };
 static const char *const af_family_clock_key_strings[AF_MAX+1] = {
-  "clock-AF_UNSPEC", "clock-AF_UNIX"     , "clock-AF_INET"     ,
-  "clock-AF_AX25"  , "clock-AF_IPX"      , "clock-AF_APPLETALK",
-  "clock-AF_NETROM", "clock-AF_BRIDGE"   , "clock-AF_ATMPVC"   ,
-  "clock-AF_X25"   , "clock-AF_INET6"    , "clock-AF_ROSE"     ,
-  "clock-AF_DECnet", "clock-AF_NETBEUI"  , "clock-AF_SECURITY" ,
-  "clock-AF_KEY"   , "clock-AF_NETLINK"  , "clock-AF_PACKET"   ,
-  "clock-AF_ASH"   , "clock-AF_ECONET"   , "clock-AF_ATMSVC"   ,
-  "clock-AF_RDS"   , "clock-AF_SNA"      , "clock-AF_IRDA"     ,
-  "clock-AF_PPPOX" , "clock-AF_WANPIPE"  , "clock-AF_LLC"      ,
-  "clock-27"       , "clock-28"          , "clock-AF_CAN"      ,
-  "clock-AF_TIPC"  , "clock-AF_BLUETOOTH", "clock-AF_IUCV"     ,
-  "clock-AF_RXRPC" , "clock-AF_ISDN"     , "clock-AF_PHONET"   ,
-  "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG"      ,
-  "clock-AF_NFC"   , "clock-AF_VSOCK"    , "clock-AF_KCM"      ,
-  "clock-AF_QIPCRTR", "clock-AF_SMC"     , "clock-AF_MAX"
+	_sock_locks("clock-")
+};
+
+static const char *const af_family_kern_key_strings[AF_MAX+1] = {
+	_sock_locks("k-sk_lock-")
+};
+static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
+	_sock_locks("k-slock-")
+};
+static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
+	_sock_locks("k-clock-")
+};
+static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
+  "rlock-AF_UNSPEC", "rlock-AF_UNIX"     , "rlock-AF_INET"     ,
+  "rlock-AF_AX25"  , "rlock-AF_IPX"      , "rlock-AF_APPLETALK",
+  "rlock-AF_NETROM", "rlock-AF_BRIDGE"   , "rlock-AF_ATMPVC"   ,
+  "rlock-AF_X25"   , "rlock-AF_INET6"    , "rlock-AF_ROSE"     ,
+  "rlock-AF_DECnet", "rlock-AF_NETBEUI"  , "rlock-AF_SECURITY" ,
+  "rlock-AF_KEY"   , "rlock-AF_NETLINK"  , "rlock-AF_PACKET"   ,
+  "rlock-AF_ASH"   , "rlock-AF_ECONET"   , "rlock-AF_ATMSVC"   ,
+  "rlock-AF_RDS"   , "rlock-AF_SNA"      , "rlock-AF_IRDA"     ,
+  "rlock-AF_PPPOX" , "rlock-AF_WANPIPE"  , "rlock-AF_LLC"      ,
+  "rlock-27"       , "rlock-28"          , "rlock-AF_CAN"      ,
+  "rlock-AF_TIPC"  , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV"     ,
+  "rlock-AF_RXRPC" , "rlock-AF_ISDN"     , "rlock-AF_PHONET"   ,
+  "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG"      ,
+  "rlock-AF_NFC"   , "rlock-AF_VSOCK"    , "rlock-AF_KCM"      ,
+  "rlock-AF_QIPCRTR", "rlock-AF_SMC"     , "rlock-AF_MAX"
+};
+static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
+  "wlock-AF_UNSPEC", "wlock-AF_UNIX"     , "wlock-AF_INET"     ,
+  "wlock-AF_AX25"  , "wlock-AF_IPX"      , "wlock-AF_APPLETALK",
+  "wlock-AF_NETROM", "wlock-AF_BRIDGE"   , "wlock-AF_ATMPVC"   ,
+  "wlock-AF_X25"   , "wlock-AF_INET6"    , "wlock-AF_ROSE"     ,
+  "wlock-AF_DECnet", "wlock-AF_NETBEUI"  , "wlock-AF_SECURITY" ,
+  "wlock-AF_KEY"   , "wlock-AF_NETLINK"  , "wlock-AF_PACKET"   ,
+  "wlock-AF_ASH"   , "wlock-AF_ECONET"   , "wlock-AF_ATMSVC"   ,
+  "wlock-AF_RDS"   , "wlock-AF_SNA"      , "wlock-AF_IRDA"     ,
+  "wlock-AF_PPPOX" , "wlock-AF_WANPIPE"  , "wlock-AF_LLC"      ,
+  "wlock-27"       , "wlock-28"          , "wlock-AF_CAN"      ,
+  "wlock-AF_TIPC"  , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV"     ,
+  "wlock-AF_RXRPC" , "wlock-AF_ISDN"     , "wlock-AF_PHONET"   ,
+  "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG"      ,
+  "wlock-AF_NFC"   , "wlock-AF_VSOCK"    , "wlock-AF_KCM"      ,
+  "wlock-AF_QIPCRTR", "wlock-AF_SMC"     , "wlock-AF_MAX"
+};
+static const char *const af_family_elock_key_strings[AF_MAX+1] = {
+  "elock-AF_UNSPEC", "elock-AF_UNIX"     , "elock-AF_INET"     ,
+  "elock-AF_AX25"  , "elock-AF_IPX"      , "elock-AF_APPLETALK",
+  "elock-AF_NETROM", "elock-AF_BRIDGE"   , "elock-AF_ATMPVC"   ,
+  "elock-AF_X25"   , "elock-AF_INET6"    , "elock-AF_ROSE"     ,
+  "elock-AF_DECnet", "elock-AF_NETBEUI"  , "elock-AF_SECURITY" ,
+  "elock-AF_KEY"   , "elock-AF_NETLINK"  , "elock-AF_PACKET"   ,
+  "elock-AF_ASH"   , "elock-AF_ECONET"   , "elock-AF_ATMSVC"   ,
+  "elock-AF_RDS"   , "elock-AF_SNA"      , "elock-AF_IRDA"     ,
+  "elock-AF_PPPOX" , "elock-AF_WANPIPE"  , "elock-AF_LLC"      ,
+  "elock-27"       , "elock-28"          , "elock-AF_CAN"      ,
+  "elock-AF_TIPC"  , "elock-AF_BLUETOOTH", "elock-AF_IUCV"     ,
+  "elock-AF_RXRPC" , "elock-AF_ISDN"     , "elock-AF_PHONET"   ,
+  "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG"      ,
+  "elock-AF_NFC"   , "elock-AF_VSOCK"    , "elock-AF_KCM"      ,
+  "elock-AF_QIPCRTR", "elock-AF_SMC"     , "elock-AF_MAX"
 };
 
 /*
- * sk_callback_lock locking rules are per-address-family,
+ * sk_callback_lock and sk queues locking rules are per-address-family,
  * so split the lock classes by using a per-AF key:
  */
 static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_rlock_keys[AF_MAX];
+static struct lock_class_key af_wlock_keys[AF_MAX];
+static struct lock_class_key af_elock_keys[AF_MAX];
+static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
 /* Take into consideration the size of the struct sk_buff overhead in the
  * determination of these values, since that is non-constant across
@@ -335,7 +379,7 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 
 	current->flags |= PF_MEMALLOC;
 	ret = sk->sk_backlog_rcv(sk, skb);
-	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+	current_restore_flags(pflags, PF_MEMALLOC);
 
 	return ret;
 }
@@ -1039,6 +1083,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 
 	union {
 		int val;
+		u64 val64;
 		struct linger ling;
 		struct timeval tm;
 	} v;
@@ -1269,6 +1314,40 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_incoming_cpu;
 		break;
 
+	case SO_MEMINFO:
+	{
+		u32 meminfo[SK_MEMINFO_VARS];
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		sk_get_meminfo(sk, meminfo);
+
+		len = min_t(unsigned int, len, sizeof(meminfo));
+		if (copy_to_user(optval, &meminfo, len))
+			return -EFAULT;
+
+		goto lenout;
+	}
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	case SO_INCOMING_NAPI_ID:
+		v.val = READ_ONCE(sk->sk_napi_id);
+
+		/* aggregate non-NAPI IDs down to 0 */
+		if (v.val < MIN_NAPI_ID)
+			v.val = 0;
+
+		break;
+#endif
+
+	case SO_COOKIE:
+		lv = sizeof(u64);
+		if (len < lv)
+			return -EINVAL;
+		v.val64 = sock_gen_cookie(sk);
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
@@ -1293,7 +1372,16 @@ lenout:
  */
 static inline void sock_lock_init(struct sock *sk)
 {
-	sock_lock_init_class_and_name(sk,
+	if (sk->sk_kern_sock)
+		sock_lock_init_class_and_name(
+			sk,
+			af_family_kern_slock_key_strings[sk->sk_family],
+			af_family_kern_slock_keys + sk->sk_family,
+			af_family_kern_key_strings[sk->sk_family],
+			af_family_kern_keys + sk->sk_family);
+	else
+		sock_lock_init_class_and_name(
+			sk,
 			af_family_slock_key_strings[sk->sk_family],
 			af_family_slock_keys + sk->sk_family,
 			af_family_key_strings[sk->sk_family],
@@ -1399,6 +1487,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		 * why we need sk_prot_creator -acme
 		 */
 		sk->sk_prot = sk->sk_prot_creator = prot;
+		sk->sk_kern_sock = kern;
 		sock_lock_init(sk);
 		sk->sk_net_refcnt = kern ? 0 : 1;
 		if (likely(sk->sk_net_refcnt))
@@ -1442,6 +1531,11 @@ static void __sk_destruct(struct rcu_head *head)
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+	}
+
 	if (sk->sk_peer_cred)
 		put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
@@ -1478,6 +1572,27 @@ void sk_free(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_free);
 
+static void sk_init_common(struct sock *sk)
+{
+	skb_queue_head_init(&sk->sk_receive_queue);
+	skb_queue_head_init(&sk->sk_write_queue);
+	skb_queue_head_init(&sk->sk_error_queue);
+
+	rwlock_init(&sk->sk_callback_lock);
+	lockdep_set_class_and_name(&sk->sk_receive_queue.lock,
+			af_rlock_keys + sk->sk_family,
+			af_family_rlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_write_queue.lock,
+			af_wlock_keys + sk->sk_family,
+			af_family_wlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_error_queue.lock,
+			af_elock_keys + sk->sk_family,
+			af_family_elock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_callback_lock,
+			af_callback_keys + sk->sk_family,
+			af_family_clock_key_strings[sk->sk_family]);
+}
+
 /**
  *	sk_clone_lock - clone a socket, and lock its clone
  *	@sk: the socket to clone
@@ -1511,13 +1626,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		atomic_set(&newsk->sk_wmem_alloc, 1);
 		atomic_set(&newsk->sk_omem_alloc, 0);
-		skb_queue_head_init(&newsk->sk_receive_queue);
-		skb_queue_head_init(&newsk->sk_write_queue);
-
-		rwlock_init(&newsk->sk_callback_lock);
-		lockdep_set_class_and_name(&newsk->sk_callback_lock,
-				af_callback_keys + newsk->sk_family,
-				af_family_clock_key_strings[newsk->sk_family]);
+		sk_init_common(newsk);
 
 		newsk->sk_dst_cache	= NULL;
 		newsk->sk_dst_pending_confirm = 0;
@@ -1528,7 +1637,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		skb_queue_head_init(&newsk->sk_error_queue);
 
 		filter = rcu_dereference_protected(newsk->sk_filter, 1);
 		if (filter != NULL)
@@ -1539,6 +1647,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+			/* We need to make sure that we don't uncharge the new
+			 * socket if we couldn't charge it in the first place
+			 * as otherwise we uncharge the parent's filter.
+			 */
+			if (!is_charged)
+				RCU_INIT_POINTER(newsk->sk_filter, NULL);
 			sk_free_unlock_clone(newsk);
 			newsk = NULL;
 			goto out;
@@ -2277,7 +2391,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
 }
 EXPORT_SYMBOL(sock_no_socketpair);
 
-int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
+int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
+		   bool kern)
 {
 	return -EOPNOTSUPP;
 }
@@ -2454,10 +2569,7 @@ EXPORT_SYMBOL(sk_stop_timer);
 
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
-	skb_queue_head_init(&sk->sk_receive_queue);
-	skb_queue_head_init(&sk->sk_write_queue);
-	skb_queue_head_init(&sk->sk_error_queue);
-
+	sk_init_common(sk);
 	sk->sk_send_head	=	NULL;
 
 	init_timer(&sk->sk_timer);
@@ -2481,7 +2593,14 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	}
 
 	rwlock_init(&sk->sk_callback_lock);
-	lockdep_set_class_and_name(&sk->sk_callback_lock,
+	if (sk->sk_kern_sock)
+		lockdep_set_class_and_name(
+			&sk->sk_callback_lock,
+			af_kern_callback_keys + sk->sk_family,
+			af_family_kern_clock_key_strings[sk->sk_family]);
+	else
+		lockdep_set_class_and_name(
+			&sk->sk_callback_lock,
 			af_callback_keys + sk->sk_family,
 			af_family_clock_key_strings[sk->sk_family]);
 
@@ -2502,7 +2621,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
-	sk->sk_stamp = ktime_set(-1L, 0);
+	sk->sk_stamp = SK_DEFAULT_STAMP;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
@@ -2779,15 +2898,25 @@ void sk_common_release(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
-		sk->sk_frag.page = NULL;
-	}
-
 	sock_put(sk);
 }
 EXPORT_SYMBOL(sk_common_release);
 
+void sk_get_meminfo(const struct sock *sk, u32 *mem)
+{
+	memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
+
+	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+}
+
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -3128,3 +3257,14 @@ static int __init proto_init(void)
 subsys_initcall(proto_init);
 
 #endif /* PROC_FS */
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+bool sk_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct sock *sk = p;
+
+	return !skb_queue_empty(&sk->sk_receive_queue) ||
+	       sk_busy_loop_timeout(sk, start_time);
+}
+EXPORT_SYMBOL(sk_busy_loop_end);
+#endif /* CONFIG_NET_RX_BUSY_POLL */
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 6b10573cc9fa..217f4e3b82f6 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
 
-static u64 sock_gen_cookie(struct sock *sk)
+u64 sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
@@ -59,15 +59,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 {
 	u32 mem[SK_MEMINFO_VARS];
 
-	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
-	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
-	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
-	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
-	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
-	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
-	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
-	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+	sk_get_meminfo(sk, mem);
 
 	return nla_put(skb, attrtype, sizeof(mem), &mem);
 }
@@ -246,7 +238,8 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
 	return err;
 }
 
-static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	int ret;
 
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 9a1a352fd1eb..eed1ebf7f29d 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -13,9 +13,9 @@
 
 static DEFINE_SPINLOCK(reuseport_lock);
 
-static struct sock_reuseport *__reuseport_alloc(u16 max_socks)
+static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
-	size_t size = sizeof(struct sock_reuseport) +
+	unsigned int size = sizeof(struct sock_reuseport) +
 		      sizeof(struct sock *) * max_socks;
 	struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC);
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 4ead336e14ea..ea23254b2457 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -408,14 +408,16 @@ static struct ctl_table net_core_table[] = {
 		.data		= &sysctl_net_busy_poll,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
 	},
 	{
 		.procname	= "busy_read",
 		.data		= &sysctl_net_busy_read,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
 	},
 #endif
 #ifdef CONFIG_NET_SCHED
@@ -450,6 +452,14 @@ static struct ctl_table net_core_table[] = {
 		.extra1		= &one,
 		.extra2		= &max_skb_frags,
 	},
+	{
+		.procname	= "netdev_budget_usecs",
+		.data		= &netdev_budget_usecs,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
 	{ }
 };
 
diff --git a/net/core/utils.c b/net/core/utils.c
index 6592d7bbed39..93066bd0305a 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -26,9 +26,11 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/ratelimit.h>
+#include <linux/socket.h>
 
 #include <net/sock.h>
 #include <net/net_ratelimit.h>
+#include <net/ipv6.h>
 
 #include <asm/byteorder.h>
 #include <linux/uaccess.h>
@@ -51,7 +53,7 @@ EXPORT_SYMBOL(net_ratelimit);
 
 __be32 in_aton(const char *str)
 {
-	unsigned long l;
+	unsigned int l;
 	unsigned int val;
 	int i;
 
@@ -300,6 +302,107 @@ out:
 }
 EXPORT_SYMBOL(in6_pton);
 
+static int inet4_pton(const char *src, u16 port_num,
+		struct sockaddr_storage *addr)
+{
+	struct sockaddr_in *addr4 = (struct sockaddr_in *)addr;
+	int srclen = strlen(src);
+
+	if (srclen > INET_ADDRSTRLEN)
+		return -EINVAL;
+
+	if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr,
+		     '\n', NULL) == 0)
+		return -EINVAL;
+
+	addr4->sin_family = AF_INET;
+	addr4->sin_port = htons(port_num);
+
+	return 0;
+}
+
+static int inet6_pton(struct net *net, const char *src, u16 port_num,
+		struct sockaddr_storage *addr)
+{
+	struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr;
+	const char *scope_delim;
+	int srclen = strlen(src);
+
+	if (srclen > INET6_ADDRSTRLEN)
+		return -EINVAL;
+
+	if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr,
+		     '%', &scope_delim) == 0)
+		return -EINVAL;
+
+	if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL &&
+	    src + srclen != scope_delim && *scope_delim == '%') {
+		struct net_device *dev;
+		char scope_id[16];
+		size_t scope_len = min_t(size_t, sizeof(scope_id) - 1,
+					 src + srclen - scope_delim - 1);
+
+		memcpy(scope_id, scope_delim + 1, scope_len);
+		scope_id[scope_len] = '\0';
+
+		dev = dev_get_by_name(net, scope_id);
+		if (dev) {
+			addr6->sin6_scope_id = dev->ifindex;
+			dev_put(dev);
+		} else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) {
+			return -EINVAL;
+		}
+	}
+
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = htons(port_num);
+
+	return 0;
+}
+
+/**
+ * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address
+ * @net: net namespace (used for scope handling)
+ * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either
+ * @src: the start of the address string
+ * @port: the start of the port string (or NULL for none)
+ * @addr: output socket address
+ *
+ * Return zero on success, return errno when any error occurs.
+ */
+int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af,
+		const char *src, const char *port, struct sockaddr_storage *addr)
+{
+	u16 port_num;
+	int ret = -EINVAL;
+
+	if (port) {
+		if (kstrtou16(port, 0, &port_num))
+			return -EINVAL;
+	} else {
+		port_num = 0;
+	}
+
+	switch (af) {
+	case AF_INET:
+		ret = inet4_pton(src, port_num, addr);
+		break;
+	case AF_INET6:
+		ret = inet6_pton(net, src, port_num, addr);
+		break;
+	case AF_UNSPEC:
+		ret = inet4_pton(src, port_num, addr);
+		if (ret)
+			ret = inet6_pton(net, src, port_num, addr);
+		break;
+	default:
+		pr_err("unexpected address family %d\n", af);
+	};
+
+	return ret;
+}
+EXPORT_SYMBOL(inet_pton_with_scope);
+
 void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
 			      __be32 from, __be32 to, bool pseudohdr)
 {
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 3202d75329b5..93106120f987 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -245,8 +245,7 @@ static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EOPNOTSUPP;
 
 	ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
-	                       tb[DCB_ATTR_PFC_CFG],
-	                       dcbnl_pfc_up_nest);
+			       tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -304,7 +303,7 @@ static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EOPNOTSUPP;
 
 	ret = nla_parse_nested(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP],
-	                       dcbnl_cap_nest);
+			       dcbnl_cap_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -348,7 +347,7 @@ static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EOPNOTSUPP;
 
 	ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
-	                       dcbnl_numtcs_nest);
+			       dcbnl_numtcs_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -393,7 +392,7 @@ static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EOPNOTSUPP;
 
 	ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
-	                       dcbnl_numtcs_nest);
+			       dcbnl_numtcs_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -452,7 +451,7 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EINVAL;
 
 	ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
-	                       dcbnl_app_nest);
+			       dcbnl_app_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -520,7 +519,7 @@ static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EINVAL;
 
 	ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
-	                       dcbnl_app_nest);
+			       dcbnl_app_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -577,8 +576,8 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->getpgbwgcfgrx)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
-	                       tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
+	ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG],
+			       dcbnl_pg_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -597,8 +596,8 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 			data = pg_tb[DCB_PG_ATTR_TC_ALL];
 		else
 			data = pg_tb[i];
-		ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
-				       data, dcbnl_tc_param_nest);
+		ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX, data,
+				       dcbnl_tc_param_nest, NULL);
 		if (ret)
 			goto err_pg;
 
@@ -735,8 +734,7 @@ static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
 		return -EOPNOTSUPP;
 
 	ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
-	                       tb[DCB_ATTR_PFC_CFG],
-	                       dcbnl_pfc_up_nest);
+			       tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -791,8 +789,8 @@ static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->setpgbwgcfgrx)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
-	                       tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
+	ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG],
+			       dcbnl_pg_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -801,7 +799,7 @@ static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 			continue;
 
 		ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
-		                       pg_tb[i], dcbnl_tc_param_nest);
+				       pg_tb[i], dcbnl_tc_param_nest, NULL);
 		if (ret)
 			return ret;
 
@@ -889,8 +887,8 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->getbcncfg)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX,
-	                       tb[DCB_ATTR_BCN], dcbnl_bcn_nest);
+	ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN],
+			       dcbnl_bcn_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -948,9 +946,8 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->setbcnrp)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX,
-	                       tb[DCB_ATTR_BCN],
-	                       dcbnl_pfc_up_nest);
+	ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN],
+			       dcbnl_pfc_up_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -1424,8 +1421,8 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_IEEE])
 		return -EINVAL;
 
-	err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX,
-			       tb[DCB_ATTR_IEEE], dcbnl_ieee_policy);
+	err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE],
+			       dcbnl_ieee_policy, NULL);
 	if (err)
 		return err;
 
@@ -1508,8 +1505,8 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_IEEE])
 		return -EINVAL;
 
-	err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX,
-			       tb[DCB_ATTR_IEEE], dcbnl_ieee_policy);
+	err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE],
+			       dcbnl_ieee_policy, NULL);
 	if (err)
 		return err;
 
@@ -1581,8 +1578,8 @@ static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_FEATCFG])
 		return -EINVAL;
 
-	ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
-			       dcbnl_featcfg_nest);
+	ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX,
+			       tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -1625,8 +1622,8 @@ static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_FEATCFG])
 		return -EINVAL;
 
-	ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
-			       dcbnl_featcfg_nest);
+	ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX,
+			       tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL);
 
 	if (ret)
 		goto err;
@@ -1699,7 +1696,8 @@ static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = {
 	[DCB_CMD_CEE_GET]	= { RTM_GETDCB, dcbnl_cee_get },
 };
 
-static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *netdev;
@@ -1715,7 +1713,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -EPERM;
 
 	ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
-			  dcbnl_rtnl_policy);
+			  dcbnl_rtnl_policy, extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198e730c..5e3a7302f774 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
 	hc->tx_seqbufc = 0;
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 409d0cfd3447..b99168b0fabf 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 233b57367758..d9b6a4e403e7 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index e267e6f4c9a5..abd07a443219 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -142,6 +142,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 	bool own_req;
 
+	/* TCP/DCCP listeners became lockless.
+	 * DCCP stores complex state in its request_sock, so we need
+	 * a protection for them, now this code runs without being protected
+	 * by the parent (listener) lock.
+	 */
+	spin_lock_bh(&dreq->dreq_lock);
+
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
 
@@ -156,7 +163,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
-		return NULL;
+		goto out;
 	}
 
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -182,20 +189,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
 							 req, &own_req);
-	if (!child)
-		goto listen_overflow;
-
-	return inet_csk_complete_hashdance(sk, child, req, own_req);
+	if (child) {
+		child = inet_csk_complete_hashdance(sk, child, req, own_req);
+		goto out;
+	}
 
-listen_overflow:
-	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
 drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	return NULL;
+out:
+	spin_unlock_bh(&dreq->dreq_lock);
+	return child;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -246,6 +253,7 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
+	spin_lock_init(&dreq->dreq_lock);
 	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
 	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
 	inet_rsk(req)->acked	   = 0;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index e6e79eda9763..9afa2a5030b2 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -132,6 +132,7 @@ Version 0.0.6    2.1.110   07-aug-98   Eduardo Marcelo Serrat
 #include <net/neighbour.h>
 #include <net/dst.h>
 #include <net/fib_rules.h>
+#include <net/tcp.h>
 #include <net/dn.h>
 #include <net/dn_nsp.h>
 #include <net/dn_dev.h>
@@ -1070,7 +1071,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
 	return skb == NULL ? ERR_PTR(err) : skb;
 }
 
-static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
+static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
+		     bool kern)
 {
 	struct sock *sk = sock->sk, *newsk;
 	struct sk_buff *skb = NULL;
@@ -1099,7 +1101,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
 
 	cb = DN_SKB_CB(skb);
 	sk->sk_ack_backlog--;
-	newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0);
+	newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern);
 	if (newsk == NULL) {
 		release_sock(sk);
 		kfree_skb(skb);
@@ -1468,18 +1470,18 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us
 	case DSO_NODELAY:
 		if (optlen != sizeof(int))
 			return -EINVAL;
-		if (scp->nonagle == 2)
+		if (scp->nonagle == TCP_NAGLE_CORK)
 			return -EINVAL;
-		scp->nonagle = (u.val == 0) ? 0 : 1;
+		scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF;
 		/* if (scp->nonagle == 1) { Push pending frames } */
 		break;
 
 	case DSO_CORK:
 		if (optlen != sizeof(int))
 			return -EINVAL;
-		if (scp->nonagle == 1)
+		if (scp->nonagle == TCP_NAGLE_OFF)
 			return -EINVAL;
-		scp->nonagle = (u.val == 0) ? 0 : 2;
+		scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK;
 		/* if (scp->nonagle == 0) { Push pending frames } */
 		break;
 
@@ -1607,14 +1609,14 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us
 	case DSO_NODELAY:
 		if (r_len > sizeof(int))
 			r_len = sizeof(int);
-		val = (scp->nonagle == 1);
+		val = (scp->nonagle == TCP_NAGLE_OFF);
 		r_data = &val;
 		break;
 
 	case DSO_CORK:
 		if (r_len > sizeof(int))
 			r_len = sizeof(int);
-		val = (scp->nonagle == 2);
+		val = (scp->nonagle == TCP_NAGLE_CORK);
 		r_data = &val;
 		break;
 
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 8fdd9f492b0e..9017a9a73ab5 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -565,7 +565,8 @@ static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = {
 	[IFA_FLAGS]		= { .type = NLA_U32 },
 };
 
-static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			 struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -581,7 +582,8 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!net_eq(net, &init_net))
 		goto errout;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -609,7 +611,8 @@ errout:
 	return err;
 }
 
-static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			 struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -625,7 +628,8 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 7af0ba6157a1..f9058ebeb635 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -501,7 +501,8 @@ static inline u32 rtm_get_table(struct nlattr *attrs[], u8 table)
 	return table;
 }
 
-static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct dn_fib_table *tb;
@@ -515,7 +516,8 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy);
+	err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
@@ -526,7 +528,8 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	return tb->delete(tb, r, attrs, nlh, &NETLINK_CB(skb));
 }
 
-static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct dn_fib_table *tb;
@@ -540,7 +543,8 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy);
+	err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index b1dc096d22f8..4b9518a0d248 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1640,7 +1640,8 @@ const struct nla_policy rtm_dn_policy[RTA_MAX + 1] = {
 /*
  * This is called by both endnodes and routers now.
  */
-static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
+static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm = nlmsg_data(nlh);
@@ -1654,7 +1655,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_dn_policy);
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_dn_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 85f2fdc360c2..1ed81ac6dd1a 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -96,7 +96,7 @@ static unsigned int dnrmg_hook(void *priv,
 }
 
 
-#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)
+#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err), NULL); return; } while (0)
 
 static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 {
@@ -134,7 +134,7 @@ static int __init dn_rtmsg_init(void)
 		return -ENOMEM;
 	}
 
-	rv = nf_register_hook(&dnrmg_ops);
+	rv = nf_register_net_hook(&init_net, &dnrmg_ops);
 	if (rv) {
 		netlink_kernel_release(dnrmg);
 	}
@@ -144,7 +144,7 @@ static int __init dn_rtmsg_init(void)
 
 static void __exit dn_rtmsg_fini(void)
 {
-	nf_unregister_hook(&dnrmg_ops);
+	nf_unregister_net_hook(&init_net, &dnrmg_ops);
 	netlink_kernel_release(dnrmg);
 }
 
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 9649238eef40..81a0868edb1d 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -6,7 +6,7 @@ config HAVE_NET_DSA
 
 config NET_DSA
 	tristate "Distributed Switch Architecture"
-	depends on HAVE_NET_DSA
+	depends on HAVE_NET_DSA && MAY_USE_DEVLINK
 	select NET_SWITCHDEV
 	select PHYLIB
 	---help---
@@ -31,4 +31,10 @@ config NET_DSA_TAG_TRAILER
 config NET_DSA_TAG_QCA
 	bool
 
+config NET_DSA_TAG_MTK
+	bool
+
+config NET_DSA_TAG_LAN9303
+	bool
+
 endif
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 31d343796251..0b747d75e65a 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -1,6 +1,6 @@
 # the core
 obj-$(CONFIG_NET_DSA) += dsa_core.o
-dsa_core-y += dsa.o slave.o dsa2.o switch.o
+dsa_core-y += dsa.o slave.o dsa2.o switch.o legacy.o
 
 # tagging formats
 dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
@@ -8,3 +8,5 @@ dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
 dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
 dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
 dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o
+dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o
+dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index b6d4f6a23f06..26130ae438da 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -14,15 +14,17 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <net/dsa.h>
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 #include <linux/of_net.h>
 #include <linux/of_gpio.h>
+#include <linux/netdevice.h>
 #include <linux/sysfs.h>
 #include <linux/phy_fixed.h>
 #include <linux/gpio/consumer.h>
+#include <linux/etherdevice.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
@@ -53,62 +55,15 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
 #ifdef CONFIG_NET_DSA_TAG_QCA
 	[DSA_TAG_PROTO_QCA] = &qca_netdev_ops,
 #endif
+#ifdef CONFIG_NET_DSA_TAG_MTK
+	[DSA_TAG_PROTO_MTK] = &mtk_netdev_ops,
+#endif
+#ifdef CONFIG_NET_DSA_TAG_LAN9303
+	[DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops,
+#endif
 	[DSA_TAG_PROTO_NONE] = &none_ops,
 };
 
-/* switch driver registration ***********************************************/
-static DEFINE_MUTEX(dsa_switch_drivers_mutex);
-static LIST_HEAD(dsa_switch_drivers);
-
-void register_switch_driver(struct dsa_switch_driver *drv)
-{
-	mutex_lock(&dsa_switch_drivers_mutex);
-	list_add_tail(&drv->list, &dsa_switch_drivers);
-	mutex_unlock(&dsa_switch_drivers_mutex);
-}
-EXPORT_SYMBOL_GPL(register_switch_driver);
-
-void unregister_switch_driver(struct dsa_switch_driver *drv)
-{
-	mutex_lock(&dsa_switch_drivers_mutex);
-	list_del_init(&drv->list);
-	mutex_unlock(&dsa_switch_drivers_mutex);
-}
-EXPORT_SYMBOL_GPL(unregister_switch_driver);
-
-static const struct dsa_switch_ops *
-dsa_switch_probe(struct device *parent, struct device *host_dev, int sw_addr,
-		 const char **_name, void **priv)
-{
-	const struct dsa_switch_ops *ret;
-	struct list_head *list;
-	const char *name;
-
-	ret = NULL;
-	name = NULL;
-
-	mutex_lock(&dsa_switch_drivers_mutex);
-	list_for_each(list, &dsa_switch_drivers) {
-		const struct dsa_switch_ops *ops;
-		struct dsa_switch_driver *drv;
-
-		drv = list_entry(list, struct dsa_switch_driver, list);
-		ops = drv->ops;
-
-		name = ops->probe(parent, host_dev, sw_addr, priv);
-		if (name != NULL) {
-			ret = ops;
-			break;
-		}
-	}
-	mutex_unlock(&dsa_switch_drivers_mutex);
-
-	*_name = name;
-
-	return ret;
-}
-
-/* basic switch operations **************************************************/
 int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev,
 		      struct dsa_port *dport, int port)
 {
@@ -140,23 +95,6 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev,
 	return 0;
 }
 
-static int dsa_cpu_dsa_setups(struct dsa_switch *ds, struct device *dev)
-{
-	struct dsa_port *dport;
-	int ret, port;
-
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
-			continue;
-
-		dport = &ds->ports[port];
-		ret = dsa_cpu_dsa_setup(ds, dev, dport, port);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
 const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
 {
 	const struct dsa_device_ops *ops;
@@ -206,168 +144,6 @@ void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds)
 	master->ethtool_ops = ds->dst->master_orig_ethtool_ops;
 }
 
-static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
-{
-	const struct dsa_switch_ops *ops = ds->ops;
-	struct dsa_switch_tree *dst = ds->dst;
-	struct dsa_chip_data *cd = ds->cd;
-	bool valid_name_found = false;
-	int index = ds->index;
-	int i, ret;
-
-	/*
-	 * Validate supplied switch configuration.
-	 */
-	for (i = 0; i < ds->num_ports; i++) {
-		char *name;
-
-		name = cd->port_names[i];
-		if (name == NULL)
-			continue;
-
-		if (!strcmp(name, "cpu")) {
-			if (dst->cpu_switch) {
-				netdev_err(dst->master_netdev,
-					   "multiple cpu ports?!\n");
-				return -EINVAL;
-			}
-			dst->cpu_switch = ds;
-			dst->cpu_port = i;
-			ds->cpu_port_mask |= 1 << i;
-		} else if (!strcmp(name, "dsa")) {
-			ds->dsa_port_mask |= 1 << i;
-		} else {
-			ds->enabled_port_mask |= 1 << i;
-		}
-		valid_name_found = true;
-	}
-
-	if (!valid_name_found && i == ds->num_ports)
-		return -EINVAL;
-
-	/* Make the built-in MII bus mask match the number of ports,
-	 * switch drivers can override this later
-	 */
-	ds->phys_mii_mask = ds->enabled_port_mask;
-
-	/*
-	 * If the CPU connects to this switch, set the switch tree
-	 * tagging protocol to the preferred tagging format of this
-	 * switch.
-	 */
-	if (dst->cpu_switch == ds) {
-		enum dsa_tag_protocol tag_protocol;
-
-		tag_protocol = ops->get_tag_protocol(ds);
-		dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
-		if (IS_ERR(dst->tag_ops))
-			return PTR_ERR(dst->tag_ops);
-
-		dst->rcv = dst->tag_ops->rcv;
-	}
-
-	memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable));
-
-	/*
-	 * Do basic register setup.
-	 */
-	ret = ops->setup(ds);
-	if (ret < 0)
-		return ret;
-
-	ret = dsa_switch_register_notifier(ds);
-	if (ret)
-		return ret;
-
-	if (ops->set_addr) {
-		ret = ops->set_addr(ds, dst->master_netdev->dev_addr);
-		if (ret < 0)
-			return ret;
-	}
-
-	if (!ds->slave_mii_bus && ops->phy_read) {
-		ds->slave_mii_bus = devm_mdiobus_alloc(parent);
-		if (!ds->slave_mii_bus)
-			return -ENOMEM;
-		dsa_slave_mii_bus_init(ds);
-
-		ret = mdiobus_register(ds->slave_mii_bus);
-		if (ret < 0)
-			return ret;
-	}
-
-	/*
-	 * Create network devices for physical switch ports.
-	 */
-	for (i = 0; i < ds->num_ports; i++) {
-		ds->ports[i].dn = cd->port_dn[i];
-
-		if (!(ds->enabled_port_mask & (1 << i)))
-			continue;
-
-		ret = dsa_slave_create(ds, parent, i, cd->port_names[i]);
-		if (ret < 0)
-			netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
-				   index, i, cd->port_names[i], ret);
-	}
-
-	/* Perform configuration of the CPU and DSA ports */
-	ret = dsa_cpu_dsa_setups(ds, parent);
-	if (ret < 0)
-		netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n",
-			   index);
-
-	ret = dsa_cpu_port_ethtool_setup(ds);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static struct dsa_switch *
-dsa_switch_setup(struct dsa_switch_tree *dst, int index,
-		 struct device *parent, struct device *host_dev)
-{
-	struct dsa_chip_data *cd = dst->pd->chip + index;
-	const struct dsa_switch_ops *ops;
-	struct dsa_switch *ds;
-	int ret;
-	const char *name;
-	void *priv;
-
-	/*
-	 * Probe for switch model.
-	 */
-	ops = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv);
-	if (!ops) {
-		netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n",
-			   index);
-		return ERR_PTR(-EINVAL);
-	}
-	netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n",
-		    index, name);
-
-
-	/*
-	 * Allocate and initialise switch state.
-	 */
-	ds = dsa_switch_alloc(parent, DSA_MAX_PORTS);
-	if (!ds)
-		return ERR_PTR(-ENOMEM);
-
-	ds->dst = dst;
-	ds->index = index;
-	ds->cd = cd;
-	ds->ops = ops;
-	ds->priv = priv;
-
-	ret = dsa_switch_setup_one(ds, parent);
-	if (ret)
-		return ERR_PTR(ret);
-
-	return ds;
-}
-
 void dsa_cpu_dsa_destroy(struct dsa_port *port)
 {
 	struct device_node *port_dn = port->dn;
@@ -376,86 +152,6 @@ void dsa_cpu_dsa_destroy(struct dsa_port *port)
 		of_phy_deregister_fixed_link(port_dn);
 }
 
-static void dsa_switch_destroy(struct dsa_switch *ds)
-{
-	int port;
-
-	/* Destroy network devices for physical switch ports. */
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!(ds->enabled_port_mask & (1 << port)))
-			continue;
-
-		if (!ds->ports[port].netdev)
-			continue;
-
-		dsa_slave_destroy(ds->ports[port].netdev);
-	}
-
-	/* Disable configuration of the CPU and DSA ports */
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
-			continue;
-		dsa_cpu_dsa_destroy(&ds->ports[port]);
-
-		/* Clearing a bit which is not set does no harm */
-		ds->cpu_port_mask |= ~(1 << port);
-		ds->dsa_port_mask |= ~(1 << port);
-	}
-
-	if (ds->slave_mii_bus && ds->ops->phy_read)
-		mdiobus_unregister(ds->slave_mii_bus);
-
-	dsa_switch_unregister_notifier(ds);
-}
-
-#ifdef CONFIG_PM_SLEEP
-int dsa_switch_suspend(struct dsa_switch *ds)
-{
-	int i, ret = 0;
-
-	/* Suspend slave network devices */
-	for (i = 0; i < ds->num_ports; i++) {
-		if (!dsa_is_port_initialized(ds, i))
-			continue;
-
-		ret = dsa_slave_suspend(ds->ports[i].netdev);
-		if (ret)
-			return ret;
-	}
-
-	if (ds->ops->suspend)
-		ret = ds->ops->suspend(ds);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dsa_switch_suspend);
-
-int dsa_switch_resume(struct dsa_switch *ds)
-{
-	int i, ret = 0;
-
-	if (ds->ops->resume)
-		ret = ds->ops->resume(ds);
-
-	if (ret)
-		return ret;
-
-	/* Resume slave network devices */
-	for (i = 0; i < ds->num_ports; i++) {
-		if (!dsa_is_port_initialized(ds, i))
-			continue;
-
-		ret = dsa_slave_resume(ds->ports[i].netdev);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dsa_switch_resume);
-#endif
-
-/* platform driver init and cleanup *****************************************/
 static int dev_is_class(struct device *dev, void *class)
 {
 	if (dev->class != NULL && !strcmp(dev->class->name, class))
@@ -474,24 +170,6 @@ static struct device *dev_find_class(struct device *parent, char *class)
 	return device_find_child(parent, class, dev_is_class);
 }
 
-struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev)
-{
-	struct device *d;
-
-	d = dev_find_class(dev, "mdio_bus");
-	if (d != NULL) {
-		struct mii_bus *bus;
-
-		bus = to_mii_bus(d);
-		put_device(d);
-
-		return bus;
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(dsa_host_dev_to_mii_bus);
-
 struct net_device *dsa_dev_to_net_device(struct device *dev)
 {
 	struct device *d;
@@ -511,456 +189,43 @@ struct net_device *dsa_dev_to_net_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dsa_dev_to_net_device);
 
-#ifdef CONFIG_OF
-static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
-					struct dsa_chip_data *cd,
-					int chip_index, int port_index,
-					struct device_node *link)
-{
-	const __be32 *reg;
-	int link_sw_addr;
-	struct device_node *parent_sw;
-	int len;
-
-	parent_sw = of_get_parent(link);
-	if (!parent_sw)
-		return -EINVAL;
-
-	reg = of_get_property(parent_sw, "reg", &len);
-	if (!reg || (len != sizeof(*reg) * 2))
-		return -EINVAL;
-
-	/*
-	 * Get the destination switch number from the second field of its 'reg'
-	 * property, i.e. for "reg = <0x19 1>" sw_addr is '1'.
-	 */
-	link_sw_addr = be32_to_cpup(reg + 1);
-
-	if (link_sw_addr >= pd->nr_chips)
-		return -EINVAL;
-
-	cd->rtable[link_sw_addr] = port_index;
-
-	return 0;
-}
-
-static int dsa_of_probe_links(struct dsa_platform_data *pd,
-			      struct dsa_chip_data *cd,
-			      int chip_index, int port_index,
-			      struct device_node *port,
-			      const char *port_name)
-{
-	struct device_node *link;
-	int link_index;
-	int ret;
-
-	for (link_index = 0;; link_index++) {
-		link = of_parse_phandle(port, "link", link_index);
-		if (!link)
-			break;
-
-		if (!strcmp(port_name, "dsa") && pd->nr_chips > 1) {
-			ret = dsa_of_setup_routing_table(pd, cd, chip_index,
-							 port_index, link);
-			if (ret)
-				return ret;
-		}
-	}
-	return 0;
-}
-
-static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
-{
-	int i;
-	int port_index;
-
-	for (i = 0; i < pd->nr_chips; i++) {
-		port_index = 0;
-		while (port_index < DSA_MAX_PORTS) {
-			kfree(pd->chip[i].port_names[port_index]);
-			port_index++;
-		}
-
-		/* Drop our reference to the MDIO bus device */
-		if (pd->chip[i].host_dev)
-			put_device(pd->chip[i].host_dev);
-	}
-	kfree(pd->chip);
-}
-
-static int dsa_of_probe(struct device *dev)
-{
-	struct device_node *np = dev->of_node;
-	struct device_node *child, *mdio, *ethernet, *port;
-	struct mii_bus *mdio_bus, *mdio_bus_switch;
-	struct net_device *ethernet_dev;
-	struct dsa_platform_data *pd;
-	struct dsa_chip_data *cd;
-	const char *port_name;
-	int chip_index, port_index;
-	const unsigned int *sw_addr, *port_reg;
-	u32 eeprom_len;
-	int ret;
-
-	mdio = of_parse_phandle(np, "dsa,mii-bus", 0);
-	if (!mdio)
-		return -EINVAL;
-
-	mdio_bus = of_mdio_find_bus(mdio);
-	if (!mdio_bus)
-		return -EPROBE_DEFER;
-
-	ethernet = of_parse_phandle(np, "dsa,ethernet", 0);
-	if (!ethernet) {
-		ret = -EINVAL;
-		goto out_put_mdio;
-	}
-
-	ethernet_dev = of_find_net_device_by_node(ethernet);
-	if (!ethernet_dev) {
-		ret = -EPROBE_DEFER;
-		goto out_put_mdio;
-	}
-
-	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
-	if (!pd) {
-		ret = -ENOMEM;
-		goto out_put_ethernet;
-	}
-
-	dev->platform_data = pd;
-	pd->of_netdev = ethernet_dev;
-	pd->nr_chips = of_get_available_child_count(np);
-	if (pd->nr_chips > DSA_MAX_SWITCHES)
-		pd->nr_chips = DSA_MAX_SWITCHES;
-
-	pd->chip = kcalloc(pd->nr_chips, sizeof(struct dsa_chip_data),
-			   GFP_KERNEL);
-	if (!pd->chip) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
-	chip_index = -1;
-	for_each_available_child_of_node(np, child) {
-		int i;
-
-		chip_index++;
-		cd = &pd->chip[chip_index];
-
-		cd->of_node = child;
-
-		/* Initialize the routing table */
-		for (i = 0; i < DSA_MAX_SWITCHES; ++i)
-			cd->rtable[i] = DSA_RTABLE_NONE;
-
-		/* When assigning the host device, increment its refcount */
-		cd->host_dev = get_device(&mdio_bus->dev);
-
-		sw_addr = of_get_property(child, "reg", NULL);
-		if (!sw_addr)
-			continue;
-
-		cd->sw_addr = be32_to_cpup(sw_addr);
-		if (cd->sw_addr >= PHY_MAX_ADDR)
-			continue;
-
-		if (!of_property_read_u32(child, "eeprom-length", &eeprom_len))
-			cd->eeprom_len = eeprom_len;
-
-		mdio = of_parse_phandle(child, "mii-bus", 0);
-		if (mdio) {
-			mdio_bus_switch = of_mdio_find_bus(mdio);
-			if (!mdio_bus_switch) {
-				ret = -EPROBE_DEFER;
-				goto out_free_chip;
-			}
-
-			/* Drop the mdio_bus device ref, replacing the host
-			 * device with the mdio_bus_switch device, keeping
-			 * the refcount from of_mdio_find_bus() above.
-			 */
-			put_device(cd->host_dev);
-			cd->host_dev = &mdio_bus_switch->dev;
-		}
-
-		for_each_available_child_of_node(child, port) {
-			port_reg = of_get_property(port, "reg", NULL);
-			if (!port_reg)
-				continue;
-
-			port_index = be32_to_cpup(port_reg);
-			if (port_index >= DSA_MAX_PORTS)
-				break;
-
-			port_name = of_get_property(port, "label", NULL);
-			if (!port_name)
-				continue;
-
-			cd->port_dn[port_index] = port;
-
-			cd->port_names[port_index] = kstrdup(port_name,
-					GFP_KERNEL);
-			if (!cd->port_names[port_index]) {
-				ret = -ENOMEM;
-				goto out_free_chip;
-			}
-
-			ret = dsa_of_probe_links(pd, cd, chip_index,
-						 port_index, port, port_name);
-			if (ret)
-				goto out_free_chip;
-
-		}
-	}
-
-	/* The individual chips hold their own refcount on the mdio bus,
-	 * so drop ours */
-	put_device(&mdio_bus->dev);
-
-	return 0;
-
-out_free_chip:
-	dsa_of_free_platform_data(pd);
-out_free:
-	kfree(pd);
-	dev->platform_data = NULL;
-out_put_ethernet:
-	put_device(&ethernet_dev->dev);
-out_put_mdio:
-	put_device(&mdio_bus->dev);
-	return ret;
-}
-
-static void dsa_of_remove(struct device *dev)
-{
-	struct dsa_platform_data *pd = dev->platform_data;
-
-	if (!dev->of_node)
-		return;
-
-	dsa_of_free_platform_data(pd);
-	put_device(&pd->of_netdev->dev);
-	kfree(pd);
-}
-#else
-static inline int dsa_of_probe(struct device *dev)
-{
-	return 0;
-}
-
-static inline void dsa_of_remove(struct device *dev)
-{
-}
-#endif
-
-static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
-			 struct device *parent, struct dsa_platform_data *pd)
-{
-	int i;
-	unsigned configured = 0;
-
-	dst->pd = pd;
-	dst->master_netdev = dev;
-	dst->cpu_port = -1;
-
-	for (i = 0; i < pd->nr_chips; i++) {
-		struct dsa_switch *ds;
-
-		ds = dsa_switch_setup(dst, i, parent, pd->chip[i].host_dev);
-		if (IS_ERR(ds)) {
-			netdev_err(dev, "[%d]: couldn't create dsa switch instance (error %ld)\n",
-				   i, PTR_ERR(ds));
-			continue;
-		}
-
-		dst->ds[i] = ds;
-
-		++configured;
-	}
-
-	/*
-	 * If no switch was found, exit cleanly
-	 */
-	if (!configured)
-		return -EPROBE_DEFER;
-
-	/*
-	 * If we use a tagging format that doesn't have an ethertype
-	 * field, make sure that all packets from this point on get
-	 * sent to the tag format's receive function.
-	 */
-	wmb();
-	dev->dsa_ptr = (void *)dst;
-
-	return 0;
-}
-
-static int dsa_probe(struct platform_device *pdev)
-{
-	struct dsa_platform_data *pd = pdev->dev.platform_data;
-	struct net_device *dev;
-	struct dsa_switch_tree *dst;
-	int ret;
-
-	if (pdev->dev.of_node) {
-		ret = dsa_of_probe(&pdev->dev);
-		if (ret)
-			return ret;
-
-		pd = pdev->dev.platform_data;
-	}
-
-	if (pd == NULL || (pd->netdev == NULL && pd->of_netdev == NULL))
-		return -EINVAL;
-
-	if (pd->of_netdev) {
-		dev = pd->of_netdev;
-		dev_hold(dev);
-	} else {
-		dev = dsa_dev_to_net_device(pd->netdev);
-	}
-	if (dev == NULL) {
-		ret = -EPROBE_DEFER;
-		goto out;
-	}
-
-	if (dev->dsa_ptr != NULL) {
-		dev_put(dev);
-		ret = -EEXIST;
-		goto out;
-	}
-
-	dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL);
-	if (dst == NULL) {
-		dev_put(dev);
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	platform_set_drvdata(pdev, dst);
-
-	ret = dsa_setup_dst(dst, dev, &pdev->dev, pd);
-	if (ret) {
-		dev_put(dev);
-		goto out;
-	}
-
-	return 0;
-
-out:
-	dsa_of_remove(&pdev->dev);
-
-	return ret;
-}
-
-static void dsa_remove_dst(struct dsa_switch_tree *dst)
-{
-	int i;
-
-	dst->master_netdev->dsa_ptr = NULL;
-
-	/* If we used a tagging format that doesn't have an ethertype
-	 * field, make sure that all packets from this point get sent
-	 * without the tag and go through the regular receive path.
-	 */
-	wmb();
-
-	for (i = 0; i < dst->pd->nr_chips; i++) {
-		struct dsa_switch *ds = dst->ds[i];
-
-		if (ds)
-			dsa_switch_destroy(ds);
-	}
-
-	dsa_cpu_port_ethtool_restore(dst->cpu_switch);
-
-	dev_put(dst->master_netdev);
-}
-
-static int dsa_remove(struct platform_device *pdev)
-{
-	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
-
-	dsa_remove_dst(dst);
-	dsa_of_remove(&pdev->dev);
-
-	return 0;
-}
-
-static void dsa_shutdown(struct platform_device *pdev)
-{
-}
-
 static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 			  struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct dsa_switch_tree *dst = dev->dsa_ptr;
+	struct sk_buff *nskb = NULL;
 
 	if (unlikely(dst == NULL)) {
 		kfree_skb(skb);
 		return 0;
 	}
 
-	return dst->rcv(skb, dev, pt, orig_dev);
-}
-
-static struct packet_type dsa_pack_type __read_mostly = {
-	.type	= cpu_to_be16(ETH_P_XDSA),
-	.func	= dsa_switch_rcv,
-};
-
-#ifdef CONFIG_PM_SLEEP
-static int dsa_suspend(struct device *d)
-{
-	struct platform_device *pdev = to_platform_device(d);
-	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
-	int i, ret = 0;
-
-	for (i = 0; i < dst->pd->nr_chips; i++) {
-		struct dsa_switch *ds = dst->ds[i];
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (!skb)
+		return 0;
 
-		if (ds != NULL)
-			ret = dsa_switch_suspend(ds);
+	nskb = dst->rcv(skb, dev, pt, orig_dev);
+	if (!nskb) {
+		kfree_skb(skb);
+		return 0;
 	}
 
-	return ret;
-}
-
-static int dsa_resume(struct device *d)
-{
-	struct platform_device *pdev = to_platform_device(d);
-	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
-	int i, ret = 0;
+	skb = nskb;
+	skb_push(skb, ETH_HLEN);
+	skb->pkt_type = PACKET_HOST;
+	skb->protocol = eth_type_trans(skb, skb->dev);
 
-	for (i = 0; i < dst->pd->nr_chips; i++) {
-		struct dsa_switch *ds = dst->ds[i];
+	skb->dev->stats.rx_packets++;
+	skb->dev->stats.rx_bytes += skb->len;
 
-		if (ds != NULL)
-			ret = dsa_switch_resume(ds);
-	}
+	netif_receive_skb(skb);
 
-	return ret;
+	return 0;
 }
-#endif
-
-static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume);
 
-static const struct of_device_id dsa_of_match_table[] = {
-	{ .compatible = "marvell,dsa", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, dsa_of_match_table);
-
-static struct platform_driver dsa_driver = {
-	.probe		= dsa_probe,
-	.remove		= dsa_remove,
-	.shutdown	= dsa_shutdown,
-	.driver = {
-		.name	= "dsa",
-		.of_match_table = dsa_of_match_table,
-		.pm	= &dsa_pm_ops,
-	},
+static struct packet_type dsa_pack_type __read_mostly = {
+	.type	= cpu_to_be16(ETH_P_XDSA),
+	.func	= dsa_switch_rcv,
 };
 
 static int __init dsa_init_module(void)
@@ -971,7 +236,7 @@ static int __init dsa_init_module(void)
 	if (rc)
 		return rc;
 
-	rc = platform_driver_register(&dsa_driver);
+	rc = dsa_legacy_register();
 	if (rc)
 		return rc;
 
@@ -985,7 +250,7 @@ static void __exit dsa_cleanup_module(void)
 {
 	dsa_slave_unregister_notifier();
 	dev_remove_pack(&dsa_pack_type);
-	platform_driver_unregister(&dsa_driver);
+	dsa_legacy_unregister();
 }
 module_exit(dsa_cleanup_module);
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 737be6470c7f..033b3bfb63dc 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -13,16 +13,20 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/list.h>
+#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
-#include <net/dsa.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 static LIST_HEAD(dsa_switch_trees);
 static DEFINE_MUTEX(dsa2_mutex);
 
+static const struct devlink_ops dsa_devlink_ops = {
+};
+
 static struct dsa_switch_tree *dsa_get_dst(u32 tree)
 {
 	struct dsa_switch_tree *dst;
@@ -222,12 +226,18 @@ static int dsa_dsa_port_apply(struct dsa_port *port, u32 index,
 		return err;
 	}
 
-	return 0;
+	memset(&ds->ports[index].devlink_port, 0,
+	       sizeof(ds->ports[index].devlink_port));
+
+	return devlink_port_register(ds->devlink,
+				     &ds->ports[index].devlink_port,
+				     index);
 }
 
 static void dsa_dsa_port_unapply(struct dsa_port *port, u32 index,
 				 struct dsa_switch *ds)
 {
+	devlink_port_unregister(&ds->ports[index].devlink_port);
 	dsa_cpu_dsa_destroy(port);
 }
 
@@ -245,12 +255,17 @@ static int dsa_cpu_port_apply(struct dsa_port *port, u32 index,
 
 	ds->cpu_port_mask |= BIT(index);
 
-	return 0;
+	memset(&ds->ports[index].devlink_port, 0,
+	       sizeof(ds->ports[index].devlink_port));
+	err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port,
+				    index);
+	return err;
 }
 
 static void dsa_cpu_port_unapply(struct dsa_port *port, u32 index,
 				 struct dsa_switch *ds)
 {
+	devlink_port_unregister(&ds->ports[index].devlink_port);
 	dsa_cpu_dsa_destroy(port);
 	ds->cpu_port_mask &= ~BIT(index);
 
@@ -275,12 +290,23 @@ static int dsa_user_port_apply(struct dsa_port *port, u32 index,
 		return err;
 	}
 
+	memset(&ds->ports[index].devlink_port, 0,
+	       sizeof(ds->ports[index].devlink_port));
+	err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port,
+				    index);
+	if (err)
+		return err;
+
+	devlink_port_type_eth_set(&ds->ports[index].devlink_port,
+				  ds->ports[index].netdev);
+
 	return 0;
 }
 
 static void dsa_user_port_unapply(struct dsa_port *port, u32 index,
 				  struct dsa_switch *ds)
 {
+	devlink_port_unregister(&ds->ports[index].devlink_port);
 	if (ds->ports[index].netdev) {
 		dsa_slave_destroy(ds->ports[index].netdev);
 		ds->ports[index].netdev = NULL;
@@ -301,6 +327,17 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 	 */
 	ds->phys_mii_mask = ds->enabled_port_mask;
 
+	/* Add the switch to devlink before calling setup, so that setup can
+	 * add dpipe tables
+	 */
+	ds->devlink = devlink_alloc(&dsa_devlink_ops, 0);
+	if (!ds->devlink)
+		return -ENOMEM;
+
+	err = devlink_register(ds->devlink, ds->dev);
+	if (err)
+		return err;
+
 	err = ds->ops->setup(ds);
 	if (err < 0)
 		return err;
@@ -381,6 +418,13 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 		mdiobus_unregister(ds->slave_mii_bus);
 
 	dsa_switch_unregister_notifier(ds);
+
+	if (ds->devlink) {
+		devlink_unregister(ds->devlink);
+		devlink_free(ds->devlink);
+		ds->devlink = NULL;
+	}
+
 }
 
 static int dsa_dst_apply(struct dsa_switch_tree *dst)
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 0706a511244e..f4a88e485213 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -17,8 +17,9 @@
 
 struct dsa_device_ops {
 	struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
-	int (*rcv)(struct sk_buff *skb, struct net_device *dev,
-		   struct packet_type *pt, struct net_device *orig_dev);
+	struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
+			       struct packet_type *pt,
+			       struct net_device *orig_dev);
 };
 
 struct dsa_slave_priv {
@@ -54,6 +55,10 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
 int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds);
 void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds);
 
+/* legacy.c */
+int dsa_legacy_register(void);
+void dsa_legacy_unregister(void);
+
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
@@ -85,4 +90,10 @@ extern const struct dsa_device_ops brcm_netdev_ops;
 /* tag_qca.c */
 extern const struct dsa_device_ops qca_netdev_ops;
 
+/* tag_mtk.c */
+extern const struct dsa_device_ops mtk_netdev_ops;
+
+/* tag_lan9303.c */
+extern const struct dsa_device_ops lan9303_netdev_ops;
+
 #endif
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
new file mode 100644
index 000000000000..ad345c8b0b06
--- /dev/null
+++ b/net/dsa/legacy.c
@@ -0,0 +1,818 @@
+/*
+ * net/dsa/legacy.c - Hardware switch handling
+ * Copyright (c) 2008-2009 Marvell Semiconductor
+ * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_platform.h>
+#include <linux/of_net.h>
+#include <linux/netdevice.h>
+#include <linux/sysfs.h>
+#include <linux/phy_fixed.h>
+#include <linux/etherdevice.h>
+#include <net/dsa.h>
+#include "dsa_priv.h"
+
+/* switch driver registration ***********************************************/
+static DEFINE_MUTEX(dsa_switch_drivers_mutex);
+static LIST_HEAD(dsa_switch_drivers);
+
+void register_switch_driver(struct dsa_switch_driver *drv)
+{
+	mutex_lock(&dsa_switch_drivers_mutex);
+	list_add_tail(&drv->list, &dsa_switch_drivers);
+	mutex_unlock(&dsa_switch_drivers_mutex);
+}
+EXPORT_SYMBOL_GPL(register_switch_driver);
+
+void unregister_switch_driver(struct dsa_switch_driver *drv)
+{
+	mutex_lock(&dsa_switch_drivers_mutex);
+	list_del_init(&drv->list);
+	mutex_unlock(&dsa_switch_drivers_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_switch_driver);
+
+static const struct dsa_switch_ops *
+dsa_switch_probe(struct device *parent, struct device *host_dev, int sw_addr,
+		 const char **_name, void **priv)
+{
+	const struct dsa_switch_ops *ret;
+	struct list_head *list;
+	const char *name;
+
+	ret = NULL;
+	name = NULL;
+
+	mutex_lock(&dsa_switch_drivers_mutex);
+	list_for_each(list, &dsa_switch_drivers) {
+		const struct dsa_switch_ops *ops;
+		struct dsa_switch_driver *drv;
+
+		drv = list_entry(list, struct dsa_switch_driver, list);
+		ops = drv->ops;
+
+		name = ops->probe(parent, host_dev, sw_addr, priv);
+		if (name != NULL) {
+			ret = ops;
+			break;
+		}
+	}
+	mutex_unlock(&dsa_switch_drivers_mutex);
+
+	*_name = name;
+
+	return ret;
+}
+
+/* basic switch operations **************************************************/
+static int dsa_cpu_dsa_setups(struct dsa_switch *ds, struct device *dev)
+{
+	struct dsa_port *dport;
+	int ret, port;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
+			continue;
+
+		dport = &ds->ports[port];
+		ret = dsa_cpu_dsa_setup(ds, dev, dport, port);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
+{
+	const struct dsa_switch_ops *ops = ds->ops;
+	struct dsa_switch_tree *dst = ds->dst;
+	struct dsa_chip_data *cd = ds->cd;
+	bool valid_name_found = false;
+	int index = ds->index;
+	int i, ret;
+
+	/*
+	 * Validate supplied switch configuration.
+	 */
+	for (i = 0; i < ds->num_ports; i++) {
+		char *name;
+
+		name = cd->port_names[i];
+		if (name == NULL)
+			continue;
+
+		if (!strcmp(name, "cpu")) {
+			if (dst->cpu_switch) {
+				netdev_err(dst->master_netdev,
+					   "multiple cpu ports?!\n");
+				return -EINVAL;
+			}
+			dst->cpu_switch = ds;
+			dst->cpu_port = i;
+			ds->cpu_port_mask |= 1 << i;
+		} else if (!strcmp(name, "dsa")) {
+			ds->dsa_port_mask |= 1 << i;
+		} else {
+			ds->enabled_port_mask |= 1 << i;
+		}
+		valid_name_found = true;
+	}
+
+	if (!valid_name_found && i == ds->num_ports)
+		return -EINVAL;
+
+	/* Make the built-in MII bus mask match the number of ports,
+	 * switch drivers can override this later
+	 */
+	ds->phys_mii_mask = ds->enabled_port_mask;
+
+	/*
+	 * If the CPU connects to this switch, set the switch tree
+	 * tagging protocol to the preferred tagging format of this
+	 * switch.
+	 */
+	if (dst->cpu_switch == ds) {
+		enum dsa_tag_protocol tag_protocol;
+
+		tag_protocol = ops->get_tag_protocol(ds);
+		dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
+		if (IS_ERR(dst->tag_ops))
+			return PTR_ERR(dst->tag_ops);
+
+		dst->rcv = dst->tag_ops->rcv;
+	}
+
+	memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable));
+
+	/*
+	 * Do basic register setup.
+	 */
+	ret = ops->setup(ds);
+	if (ret < 0)
+		return ret;
+
+	ret = dsa_switch_register_notifier(ds);
+	if (ret)
+		return ret;
+
+	if (ops->set_addr) {
+		ret = ops->set_addr(ds, dst->master_netdev->dev_addr);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (!ds->slave_mii_bus && ops->phy_read) {
+		ds->slave_mii_bus = devm_mdiobus_alloc(parent);
+		if (!ds->slave_mii_bus)
+			return -ENOMEM;
+		dsa_slave_mii_bus_init(ds);
+
+		ret = mdiobus_register(ds->slave_mii_bus);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * Create network devices for physical switch ports.
+	 */
+	for (i = 0; i < ds->num_ports; i++) {
+		ds->ports[i].dn = cd->port_dn[i];
+
+		if (!(ds->enabled_port_mask & (1 << i)))
+			continue;
+
+		ret = dsa_slave_create(ds, parent, i, cd->port_names[i]);
+		if (ret < 0)
+			netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
+				   index, i, cd->port_names[i], ret);
+	}
+
+	/* Perform configuration of the CPU and DSA ports */
+	ret = dsa_cpu_dsa_setups(ds, parent);
+	if (ret < 0)
+		netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n",
+			   index);
+
+	ret = dsa_cpu_port_ethtool_setup(ds);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static struct dsa_switch *
+dsa_switch_setup(struct dsa_switch_tree *dst, int index,
+		 struct device *parent, struct device *host_dev)
+{
+	struct dsa_chip_data *cd = dst->pd->chip + index;
+	const struct dsa_switch_ops *ops;
+	struct dsa_switch *ds;
+	int ret;
+	const char *name;
+	void *priv;
+
+	/*
+	 * Probe for switch model.
+	 */
+	ops = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv);
+	if (!ops) {
+		netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n",
+			   index);
+		return ERR_PTR(-EINVAL);
+	}
+	netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n",
+		    index, name);
+
+
+	/*
+	 * Allocate and initialise switch state.
+	 */
+	ds = dsa_switch_alloc(parent, DSA_MAX_PORTS);
+	if (!ds)
+		return ERR_PTR(-ENOMEM);
+
+	ds->dst = dst;
+	ds->index = index;
+	ds->cd = cd;
+	ds->ops = ops;
+	ds->priv = priv;
+
+	ret = dsa_switch_setup_one(ds, parent);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return ds;
+}
+
+static void dsa_switch_destroy(struct dsa_switch *ds)
+{
+	int port;
+
+	/* Destroy network devices for physical switch ports. */
+	for (port = 0; port < ds->num_ports; port++) {
+		if (!(ds->enabled_port_mask & (1 << port)))
+			continue;
+
+		if (!ds->ports[port].netdev)
+			continue;
+
+		dsa_slave_destroy(ds->ports[port].netdev);
+	}
+
+	/* Disable configuration of the CPU and DSA ports */
+	for (port = 0; port < ds->num_ports; port++) {
+		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
+			continue;
+		dsa_cpu_dsa_destroy(&ds->ports[port]);
+
+		/* Clearing a bit which is not set does no harm */
+		ds->cpu_port_mask |= ~(1 << port);
+		ds->dsa_port_mask |= ~(1 << port);
+	}
+
+	if (ds->slave_mii_bus && ds->ops->phy_read)
+		mdiobus_unregister(ds->slave_mii_bus);
+
+	dsa_switch_unregister_notifier(ds);
+}
+
+#ifdef CONFIG_PM_SLEEP
+int dsa_switch_suspend(struct dsa_switch *ds)
+{
+	int i, ret = 0;
+
+	/* Suspend slave network devices */
+	for (i = 0; i < ds->num_ports; i++) {
+		if (!dsa_is_port_initialized(ds, i))
+			continue;
+
+		ret = dsa_slave_suspend(ds->ports[i].netdev);
+		if (ret)
+			return ret;
+	}
+
+	if (ds->ops->suspend)
+		ret = ds->ops->suspend(ds);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dsa_switch_suspend);
+
+int dsa_switch_resume(struct dsa_switch *ds)
+{
+	int i, ret = 0;
+
+	if (ds->ops->resume)
+		ret = ds->ops->resume(ds);
+
+	if (ret)
+		return ret;
+
+	/* Resume slave network devices */
+	for (i = 0; i < ds->num_ports; i++) {
+		if (!dsa_is_port_initialized(ds, i))
+			continue;
+
+		ret = dsa_slave_resume(ds->ports[i].netdev);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dsa_switch_resume);
+#endif
+
+/* platform driver init and cleanup *****************************************/
+static int dev_is_class(struct device *dev, void *class)
+{
+	if (dev->class != NULL && !strcmp(dev->class->name, class))
+		return 1;
+
+	return 0;
+}
+
+static struct device *dev_find_class(struct device *parent, char *class)
+{
+	if (dev_is_class(parent, class)) {
+		get_device(parent);
+		return parent;
+	}
+
+	return device_find_child(parent, class, dev_is_class);
+}
+
+struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev)
+{
+	struct device *d;
+
+	d = dev_find_class(dev, "mdio_bus");
+	if (d != NULL) {
+		struct mii_bus *bus;
+
+		bus = to_mii_bus(d);
+		put_device(d);
+
+		return bus;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(dsa_host_dev_to_mii_bus);
+
+#ifdef CONFIG_OF
+static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
+					struct dsa_chip_data *cd,
+					int chip_index, int port_index,
+					struct device_node *link)
+{
+	const __be32 *reg;
+	int link_sw_addr;
+	struct device_node *parent_sw;
+	int len;
+
+	parent_sw = of_get_parent(link);
+	if (!parent_sw)
+		return -EINVAL;
+
+	reg = of_get_property(parent_sw, "reg", &len);
+	if (!reg || (len != sizeof(*reg) * 2))
+		return -EINVAL;
+
+	/*
+	 * Get the destination switch number from the second field of its 'reg'
+	 * property, i.e. for "reg = <0x19 1>" sw_addr is '1'.
+	 */
+	link_sw_addr = be32_to_cpup(reg + 1);
+
+	if (link_sw_addr >= pd->nr_chips)
+		return -EINVAL;
+
+	cd->rtable[link_sw_addr] = port_index;
+
+	return 0;
+}
+
+static int dsa_of_probe_links(struct dsa_platform_data *pd,
+			      struct dsa_chip_data *cd,
+			      int chip_index, int port_index,
+			      struct device_node *port,
+			      const char *port_name)
+{
+	struct device_node *link;
+	int link_index;
+	int ret;
+
+	for (link_index = 0;; link_index++) {
+		link = of_parse_phandle(port, "link", link_index);
+		if (!link)
+			break;
+
+		if (!strcmp(port_name, "dsa") && pd->nr_chips > 1) {
+			ret = dsa_of_setup_routing_table(pd, cd, chip_index,
+							 port_index, link);
+			if (ret)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
+{
+	int i;
+	int port_index;
+
+	for (i = 0; i < pd->nr_chips; i++) {
+		port_index = 0;
+		while (port_index < DSA_MAX_PORTS) {
+			kfree(pd->chip[i].port_names[port_index]);
+			port_index++;
+		}
+
+		/* Drop our reference to the MDIO bus device */
+		if (pd->chip[i].host_dev)
+			put_device(pd->chip[i].host_dev);
+	}
+	kfree(pd->chip);
+}
+
+static int dsa_of_probe(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *child, *mdio, *ethernet, *port;
+	struct mii_bus *mdio_bus, *mdio_bus_switch;
+	struct net_device *ethernet_dev;
+	struct dsa_platform_data *pd;
+	struct dsa_chip_data *cd;
+	const char *port_name;
+	int chip_index, port_index;
+	const unsigned int *sw_addr, *port_reg;
+	u32 eeprom_len;
+	int ret;
+
+	mdio = of_parse_phandle(np, "dsa,mii-bus", 0);
+	if (!mdio)
+		return -EINVAL;
+
+	mdio_bus = of_mdio_find_bus(mdio);
+	if (!mdio_bus)
+		return -EPROBE_DEFER;
+
+	ethernet = of_parse_phandle(np, "dsa,ethernet", 0);
+	if (!ethernet) {
+		ret = -EINVAL;
+		goto out_put_mdio;
+	}
+
+	ethernet_dev = of_find_net_device_by_node(ethernet);
+	if (!ethernet_dev) {
+		ret = -EPROBE_DEFER;
+		goto out_put_mdio;
+	}
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd) {
+		ret = -ENOMEM;
+		goto out_put_ethernet;
+	}
+
+	dev->platform_data = pd;
+	pd->of_netdev = ethernet_dev;
+	pd->nr_chips = of_get_available_child_count(np);
+	if (pd->nr_chips > DSA_MAX_SWITCHES)
+		pd->nr_chips = DSA_MAX_SWITCHES;
+
+	pd->chip = kcalloc(pd->nr_chips, sizeof(struct dsa_chip_data),
+			   GFP_KERNEL);
+	if (!pd->chip) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	chip_index = -1;
+	for_each_available_child_of_node(np, child) {
+		int i;
+
+		chip_index++;
+		cd = &pd->chip[chip_index];
+
+		cd->of_node = child;
+
+		/* Initialize the routing table */
+		for (i = 0; i < DSA_MAX_SWITCHES; ++i)
+			cd->rtable[i] = DSA_RTABLE_NONE;
+
+		/* When assigning the host device, increment its refcount */
+		cd->host_dev = get_device(&mdio_bus->dev);
+
+		sw_addr = of_get_property(child, "reg", NULL);
+		if (!sw_addr)
+			continue;
+
+		cd->sw_addr = be32_to_cpup(sw_addr);
+		if (cd->sw_addr >= PHY_MAX_ADDR)
+			continue;
+
+		if (!of_property_read_u32(child, "eeprom-length", &eeprom_len))
+			cd->eeprom_len = eeprom_len;
+
+		mdio = of_parse_phandle(child, "mii-bus", 0);
+		if (mdio) {
+			mdio_bus_switch = of_mdio_find_bus(mdio);
+			if (!mdio_bus_switch) {
+				ret = -EPROBE_DEFER;
+				goto out_free_chip;
+			}
+
+			/* Drop the mdio_bus device ref, replacing the host
+			 * device with the mdio_bus_switch device, keeping
+			 * the refcount from of_mdio_find_bus() above.
+			 */
+			put_device(cd->host_dev);
+			cd->host_dev = &mdio_bus_switch->dev;
+		}
+
+		for_each_available_child_of_node(child, port) {
+			port_reg = of_get_property(port, "reg", NULL);
+			if (!port_reg)
+				continue;
+
+			port_index = be32_to_cpup(port_reg);
+			if (port_index >= DSA_MAX_PORTS)
+				break;
+
+			port_name = of_get_property(port, "label", NULL);
+			if (!port_name)
+				continue;
+
+			cd->port_dn[port_index] = port;
+
+			cd->port_names[port_index] = kstrdup(port_name,
+					GFP_KERNEL);
+			if (!cd->port_names[port_index]) {
+				ret = -ENOMEM;
+				goto out_free_chip;
+			}
+
+			ret = dsa_of_probe_links(pd, cd, chip_index,
+						 port_index, port, port_name);
+			if (ret)
+				goto out_free_chip;
+
+		}
+	}
+
+	/* The individual chips hold their own refcount on the mdio bus,
+	 * so drop ours */
+	put_device(&mdio_bus->dev);
+
+	return 0;
+
+out_free_chip:
+	dsa_of_free_platform_data(pd);
+out_free:
+	kfree(pd);
+	dev->platform_data = NULL;
+out_put_ethernet:
+	put_device(&ethernet_dev->dev);
+out_put_mdio:
+	put_device(&mdio_bus->dev);
+	return ret;
+}
+
+static void dsa_of_remove(struct device *dev)
+{
+	struct dsa_platform_data *pd = dev->platform_data;
+
+	if (!dev->of_node)
+		return;
+
+	dsa_of_free_platform_data(pd);
+	put_device(&pd->of_netdev->dev);
+	kfree(pd);
+}
+#else
+static inline int dsa_of_probe(struct device *dev)
+{
+	return 0;
+}
+
+static inline void dsa_of_remove(struct device *dev)
+{
+}
+#endif
+
+static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
+			 struct device *parent, struct dsa_platform_data *pd)
+{
+	int i;
+	unsigned configured = 0;
+
+	dst->pd = pd;
+	dst->master_netdev = dev;
+	dst->cpu_port = -1;
+
+	for (i = 0; i < pd->nr_chips; i++) {
+		struct dsa_switch *ds;
+
+		ds = dsa_switch_setup(dst, i, parent, pd->chip[i].host_dev);
+		if (IS_ERR(ds)) {
+			netdev_err(dev, "[%d]: couldn't create dsa switch instance (error %ld)\n",
+				   i, PTR_ERR(ds));
+			continue;
+		}
+
+		dst->ds[i] = ds;
+
+		++configured;
+	}
+
+	/*
+	 * If no switch was found, exit cleanly
+	 */
+	if (!configured)
+		return -EPROBE_DEFER;
+
+	/*
+	 * If we use a tagging format that doesn't have an ethertype
+	 * field, make sure that all packets from this point on get
+	 * sent to the tag format's receive function.
+	 */
+	wmb();
+	dev->dsa_ptr = (void *)dst;
+
+	return 0;
+}
+
+static int dsa_probe(struct platform_device *pdev)
+{
+	struct dsa_platform_data *pd = pdev->dev.platform_data;
+	struct net_device *dev;
+	struct dsa_switch_tree *dst;
+	int ret;
+
+	if (pdev->dev.of_node) {
+		ret = dsa_of_probe(&pdev->dev);
+		if (ret)
+			return ret;
+
+		pd = pdev->dev.platform_data;
+	}
+
+	if (pd == NULL || (pd->netdev == NULL && pd->of_netdev == NULL))
+		return -EINVAL;
+
+	if (pd->of_netdev) {
+		dev = pd->of_netdev;
+		dev_hold(dev);
+	} else {
+		dev = dsa_dev_to_net_device(pd->netdev);
+	}
+	if (dev == NULL) {
+		ret = -EPROBE_DEFER;
+		goto out;
+	}
+
+	if (dev->dsa_ptr != NULL) {
+		dev_put(dev);
+		ret = -EEXIST;
+		goto out;
+	}
+
+	dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL);
+	if (dst == NULL) {
+		dev_put(dev);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	platform_set_drvdata(pdev, dst);
+
+	ret = dsa_setup_dst(dst, dev, &pdev->dev, pd);
+	if (ret) {
+		dev_put(dev);
+		goto out;
+	}
+
+	return 0;
+
+out:
+	dsa_of_remove(&pdev->dev);
+
+	return ret;
+}
+
+static void dsa_remove_dst(struct dsa_switch_tree *dst)
+{
+	int i;
+
+	dst->master_netdev->dsa_ptr = NULL;
+
+	/* If we used a tagging format that doesn't have an ethertype
+	 * field, make sure that all packets from this point get sent
+	 * without the tag and go through the regular receive path.
+	 */
+	wmb();
+
+	for (i = 0; i < dst->pd->nr_chips; i++) {
+		struct dsa_switch *ds = dst->ds[i];
+
+		if (ds)
+			dsa_switch_destroy(ds);
+	}
+
+	dsa_cpu_port_ethtool_restore(dst->cpu_switch);
+
+	dev_put(dst->master_netdev);
+}
+
+static int dsa_remove(struct platform_device *pdev)
+{
+	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+
+	dsa_remove_dst(dst);
+	dsa_of_remove(&pdev->dev);
+
+	return 0;
+}
+
+static void dsa_shutdown(struct platform_device *pdev)
+{
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int dsa_suspend(struct device *d)
+{
+	struct platform_device *pdev = to_platform_device(d);
+	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+	int i, ret = 0;
+
+	for (i = 0; i < dst->pd->nr_chips; i++) {
+		struct dsa_switch *ds = dst->ds[i];
+
+		if (ds != NULL)
+			ret = dsa_switch_suspend(ds);
+	}
+
+	return ret;
+}
+
+static int dsa_resume(struct device *d)
+{
+	struct platform_device *pdev = to_platform_device(d);
+	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+	int i, ret = 0;
+
+	for (i = 0; i < dst->pd->nr_chips; i++) {
+		struct dsa_switch *ds = dst->ds[i];
+
+		if (ds != NULL)
+			ret = dsa_switch_resume(ds);
+	}
+
+	return ret;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume);
+
+static const struct of_device_id dsa_of_match_table[] = {
+	{ .compatible = "marvell,dsa", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dsa_of_match_table);
+
+static struct platform_driver dsa_driver = {
+	.probe		= dsa_probe,
+	.remove		= dsa_remove,
+	.shutdown	= dsa_shutdown,
+	.driver = {
+		.name	= "dsa",
+		.of_match_table = dsa_of_match_table,
+		.pm	= &dsa_pm_ops,
+	},
+};
+
+int dsa_legacy_register(void)
+{
+	return platform_driver_register(&dsa_driver);
+}
+
+void dsa_legacy_unregister(void)
+{
+	platform_driver_unregister(&dsa_driver);
+}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index c34872e1febc..7693182df81e 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -17,6 +17,7 @@
 #include <linux/of_mdio.h>
 #include <linux/mdio.h>
 #include <linux/list.h>
+#include <net/dsa.h>
 #include <net/rtnetlink.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
@@ -419,8 +420,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev,
 	return 0;
 }
 
-static int dsa_fastest_ageing_time(struct dsa_switch *ds,
-				   unsigned int ageing_time)
+static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds,
+					    unsigned int ageing_time)
 {
 	int i;
 
@@ -443,9 +444,13 @@ static int dsa_slave_ageing_time(struct net_device *dev,
 	unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time);
 	unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies);
 
-	/* bridge skips -EOPNOTSUPP, so skip the prepare phase */
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_prepare(trans)) {
+		if (ds->ageing_time_min && ageing_time < ds->ageing_time_min)
+			return -ERANGE;
+		if (ds->ageing_time_max && ageing_time > ds->ageing_time_max)
+			return -ERANGE;
 		return 0;
+	}
 
 	/* Keep the fastest ageing time in case of multiple bridges */
 	p->dp->ageing_time = ageing_time;
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 6456dacf9ae9..ca6e26e514f0 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -1,7 +1,8 @@
 /*
  * Handling of a single switch chip, part of a switch fabric
  *
- * Copyright (c) 2017 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -19,9 +20,9 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds,
 	if (ds->index == info->sw_index && ds->ops->port_bridge_join)
 		return ds->ops->port_bridge_join(ds, info->port, info->br);
 
-	if (ds->index != info->sw_index)
-		dev_dbg(ds->dev, "crosschip DSA port %d.%d bridged to %s\n",
-			info->sw_index, info->port, netdev_name(info->br));
+	if (ds->index != info->sw_index && ds->ops->crosschip_bridge_join)
+		return ds->ops->crosschip_bridge_join(ds, info->sw_index,
+						      info->port, info->br);
 
 	return 0;
 }
@@ -32,9 +33,9 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 	if (ds->index == info->sw_index && ds->ops->port_bridge_leave)
 		ds->ops->port_bridge_leave(ds, info->port, info->br);
 
-	if (ds->index != info->sw_index)
-		dev_dbg(ds->dev, "crosschip DSA port %d.%d unbridged from %s\n",
-			info->sw_index, info->port, netdev_name(info->br));
+	if (ds->index != info->sw_index && ds->ops->crosschip_bridge_leave)
+		ds->ops->crosschip_bridge_leave(ds, info->sw_index, info->port,
+						info->br);
 
 	return 0;
 }
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 5d925b6b2bb1..2a9b52c5af86 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -12,6 +12,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 /* This tag length is 4 bytes, older ones were 6 bytes, we do not
@@ -91,23 +92,17 @@ out_free:
 	return NULL;
 }
 
-static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
-			struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+				    struct packet_type *pt,
+				    struct net_device *orig_dev)
 {
 	struct dsa_switch_tree *dst = dev->dsa_ptr;
 	struct dsa_switch *ds;
 	int source_port;
 	u8 *brcm_tag;
 
-	if (unlikely(dst == NULL))
-		goto out_drop;
-
 	ds = dst->cpu_switch;
 
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (skb == NULL)
-		goto out;
-
 	if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN)))
 		goto out_drop;
 
@@ -139,22 +134,12 @@ static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 		skb->data - ETH_HLEN - BRCM_TAG_LEN,
 		2 * ETH_ALEN);
 
-	skb_push(skb, ETH_HLEN);
-	skb->pkt_type = PACKET_HOST;
 	skb->dev = ds->ports[source_port].netdev;
-	skb->protocol = eth_type_trans(skb, skb->dev);
-
-	skb->dev->stats.rx_packets++;
-	skb->dev->stats.rx_bytes += skb->len;
 
-	netif_receive_skb(skb);
-
-	return 0;
+	return skb;
 
 out_drop:
-	kfree_skb(skb);
-out:
-	return 0;
+	return NULL;
 }
 
 const struct dsa_device_ops brcm_netdev_ops = {
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 72579ceea381..1c6633f0de01 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -11,6 +11,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 #define DSA_HLEN	4
@@ -67,8 +68,9 @@ out_free:
 	return NULL;
 }
 
-static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
-		   struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
+			       struct packet_type *pt,
+			       struct net_device *orig_dev)
 {
 	struct dsa_switch_tree *dst = dev->dsa_ptr;
 	struct dsa_switch *ds;
@@ -76,13 +78,6 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	int source_device;
 	int source_port;
 
-	if (unlikely(dst == NULL))
-		goto out_drop;
-
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (skb == NULL)
-		goto out;
-
 	if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
 		goto out_drop;
 
@@ -164,21 +159,11 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	skb->dev = ds->ports[source_port].netdev;
-	skb_push(skb, ETH_HLEN);
-	skb->pkt_type = PACKET_HOST;
-	skb->protocol = eth_type_trans(skb, skb->dev);
-
-	skb->dev->stats.rx_packets++;
-	skb->dev->stats.rx_bytes += skb->len;
 
-	netif_receive_skb(skb);
-
-	return 0;
+	return skb;
 
 out_drop:
-	kfree_skb(skb);
-out:
-	return 0;
+	return NULL;
 }
 
 const struct dsa_device_ops dsa_netdev_ops = {
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 648c051817a1..d9c668aa5e54 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -11,6 +11,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 #define DSA_HLEN	4
@@ -80,8 +81,9 @@ out_free:
 	return NULL;
 }
 
-static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
-		    struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
+				struct packet_type *pt,
+				struct net_device *orig_dev)
 {
 	struct dsa_switch_tree *dst = dev->dsa_ptr;
 	struct dsa_switch *ds;
@@ -89,13 +91,6 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	int source_device;
 	int source_port;
 
-	if (unlikely(dst == NULL))
-		goto out_drop;
-
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (skb == NULL)
-		goto out;
-
 	if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
 		goto out_drop;
 
@@ -183,21 +178,11 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	skb->dev = ds->ports[source_port].netdev;
-	skb_push(skb, ETH_HLEN);
-	skb->pkt_type = PACKET_HOST;
-	skb->protocol = eth_type_trans(skb, skb->dev);
-
-	skb->dev->stats.rx_packets++;
-	skb->dev->stats.rx_bytes += skb->len;
 
-	netif_receive_skb(skb);
-
-	return 0;
+	return skb;
 
 out_drop:
-	kfree_skb(skb);
-out:
-	return 0;
+	return NULL;
 }
 
 const struct dsa_device_ops edsa_netdev_ops = {
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
new file mode 100644
index 000000000000..70130ed5c21a
--- /dev/null
+++ b/net/dsa/tag_lan9303.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright (C) 2017 Pengutronix, Juergen Borleis <jbe@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/etherdevice.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <net/dsa.h>
+#include "dsa_priv.h"
+
+/* To define the outgoing port and to discover the incoming port a regular
+ * VLAN tag is used by the LAN9303. But its VID meaning is 'special':
+ *
+ *       Dest MAC       Src MAC        TAG    Type
+ * ...| 1 2 3 4 5 6 | 1 2 3 4 5 6 | 1 2 3 4 | 1 2 |...
+ *                                |<------->|
+ * TAG:
+ *    |<------------->|
+ *    |  1  2 | 3  4  |
+ *      TPID    VID
+ *     0x8100
+ *
+ * VID bit 3 indicates a request for an ALR lookup.
+ *
+ * If VID bit 3 is zero, then bits 0 and 1 specify the destination port
+ * (0, 1, 2) or broadcast (3) or the source port (1, 2).
+ *
+ * VID bit 4 is used to specify if the STP port state should be overridden.
+ * Required when no forwarding between the external ports should happen.
+ */
+
+#define LAN9303_TAG_LEN 4
+#define LAN9303_MAX_PORTS 3
+
+static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	u16 *lan9303_tag;
+
+	/* insert a special VLAN tag between the MAC addresses
+	 * and the current ethertype field.
+	 */
+	if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) {
+		dev_dbg(&dev->dev,
+			"Cannot make room for the special tag. Dropping packet\n");
+		goto out_free;
+	}
+
+	/* provide 'LAN9303_TAG_LEN' bytes additional space */
+	skb_push(skb, LAN9303_TAG_LEN);
+
+	/* make room between MACs and Ether-Type */
+	memmove(skb->data, skb->data + LAN9303_TAG_LEN, 2 * ETH_ALEN);
+
+	lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN);
+	lan9303_tag[0] = htons(ETH_P_8021Q);
+	lan9303_tag[1] = htons(p->dp->index | BIT(4));
+
+	return skb;
+out_free:
+	kfree_skb(skb);
+	return NULL;
+}
+
+static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
+			struct packet_type *pt, struct net_device *orig_dev)
+{
+	u16 *lan9303_tag;
+	struct dsa_switch_tree *dst = dev->dsa_ptr;
+	struct dsa_switch *ds;
+	unsigned int source_port;
+
+	ds = dst->ds[0];
+
+	if (unlikely(!ds)) {
+		dev_warn_ratelimited(&dev->dev, "Dropping packet, due to missing DSA switch device\n");
+		return NULL;
+	}
+
+	if (unlikely(!pskb_may_pull(skb, LAN9303_TAG_LEN))) {
+		dev_warn_ratelimited(&dev->dev,
+				     "Dropping packet, cannot pull\n");
+		return NULL;
+	}
+
+	/* '->data' points into the middle of our special VLAN tag information:
+	 *
+	 * ~ MAC src   | 0x81 | 0x00 | 0xyy | 0xzz | ether type
+	 *                           ^
+	 *                        ->data
+	 */
+	lan9303_tag = (u16 *)(skb->data - 2);
+
+	if (lan9303_tag[0] != htons(ETH_P_8021Q)) {
+		dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid VLAN marker\n");
+		return NULL;
+	}
+
+	source_port = ntohs(lan9303_tag[1]) & 0x3;
+
+	if (source_port >= LAN9303_MAX_PORTS) {
+		dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n");
+		return NULL;
+	}
+
+	if (!ds->ports[source_port].netdev) {
+		dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid netdev or device\n");
+		return NULL;
+	}
+
+	/* remove the special VLAN tag between the MAC addresses
+	 * and the current ethertype field.
+	 */
+	skb_pull_rcsum(skb, 2 + 2);
+	memmove(skb->data - ETH_HLEN, skb->data - (ETH_HLEN + LAN9303_TAG_LEN),
+		2 * ETH_ALEN);
+
+	/* forward the packet to the dedicated interface */
+	skb->dev = ds->ports[source_port].netdev;
+
+	return skb;
+}
+
+const struct dsa_device_ops lan9303_netdev_ops = {
+	.xmit = lan9303_xmit,
+	.rcv = lan9303_rcv,
+};
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
new file mode 100644
index 000000000000..837cdddb53f0
--- /dev/null
+++ b/net/dsa/tag_mtk.c
@@ -0,0 +1,100 @@
+/*
+ * Mediatek DSA Tag support
+ * Copyright (C) 2017 Landen Chao <landen.chao@mediatek.com>
+ *		      Sean Wang <sean.wang@mediatek.com>
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/etherdevice.h>
+#include <net/dsa.h>
+#include "dsa_priv.h"
+
+#define MTK_HDR_LEN		4
+#define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
+#define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
+
+static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	u8 *mtk_tag;
+
+	if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
+		goto out_free;
+
+	skb_push(skb, MTK_HDR_LEN);
+
+	memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
+
+	/* Build the tag after the MAC Source Address */
+	mtk_tag = skb->data + 2 * ETH_ALEN;
+	mtk_tag[0] = 0;
+	mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
+	mtk_tag[2] = 0;
+	mtk_tag[3] = 0;
+
+	return skb;
+
+out_free:
+	kfree_skb(skb);
+	return NULL;
+}
+
+static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+				   struct packet_type *pt,
+				   struct net_device *orig_dev)
+{
+	struct dsa_switch_tree *dst = dev->dsa_ptr;
+	struct dsa_switch *ds;
+	int port;
+	__be16 *phdr, hdr;
+
+	if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
+		goto out_drop;
+
+	/* The MTK header is added by the switch between src addr
+	 * and ethertype at this point, skb->data points to 2 bytes
+	 * after src addr so header should be 2 bytes right before.
+	 */
+	phdr = (__be16 *)(skb->data - 2);
+	hdr = ntohs(*phdr);
+
+	/* Remove MTK tag and recalculate checksum. */
+	skb_pull_rcsum(skb, MTK_HDR_LEN);
+
+	memmove(skb->data - ETH_HLEN,
+		skb->data - ETH_HLEN - MTK_HDR_LEN,
+		2 * ETH_ALEN);
+
+	/* This protocol doesn't support cascading multiple
+	 * switches so it's safe to assume the switch is first
+	 * in the tree.
+	 */
+	ds = dst->ds[0];
+	if (!ds)
+		goto out_drop;
+
+	/* Get source port information */
+	port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK);
+	if (!ds->ports[port].netdev)
+		goto out_drop;
+
+	skb->dev = ds->ports[port].netdev;
+
+	return skb;
+
+out_drop:
+	return NULL;
+}
+
+const struct dsa_device_ops mtk_netdev_ops = {
+	.xmit	= mtk_tag_xmit,
+	.rcv	= mtk_tag_rcv,
+};
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 30240f343aea..3ba3f59f7a34 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/etherdevice.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 #define QCA_HDR_LEN	2
@@ -65,8 +66,9 @@ out_free:
 	return NULL;
 }
 
-static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
-		       struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+				   struct packet_type *pt,
+				   struct net_device *orig_dev)
 {
 	struct dsa_switch_tree *dst = dev->dsa_ptr;
 	struct dsa_switch *ds;
@@ -74,13 +76,6 @@ static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	int port;
 	__be16 *phdr, hdr;
 
-	if (unlikely(!dst))
-		goto out_drop;
-
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (!skb)
-		goto out;
-
 	if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN)))
 		goto out_drop;
 
@@ -114,22 +109,12 @@ static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto out_drop;
 
 	/* Update skb & forward the frame accordingly */
-	skb_push(skb, ETH_HLEN);
-	skb->pkt_type = PACKET_HOST;
 	skb->dev = ds->ports[port].netdev;
-	skb->protocol = eth_type_trans(skb, skb->dev);
-
-	skb->dev->stats.rx_packets++;
-	skb->dev->stats.rx_bytes += skb->len;
 
-	netif_receive_skb(skb);
-
-	return 0;
+	return skb;
 
 out_drop:
-	kfree_skb(skb);
-out:
-	return 0;
+	return NULL;
 }
 
 const struct dsa_device_ops qca_netdev_ops = {
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 26f977176978..aafc2fc74c30 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -11,6 +11,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -57,22 +58,17 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 	return nskb;
 }
 
-static int trailer_rcv(struct sk_buff *skb, struct net_device *dev,
-		       struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
+				   struct packet_type *pt,
+				   struct net_device *orig_dev)
 {
 	struct dsa_switch_tree *dst = dev->dsa_ptr;
 	struct dsa_switch *ds;
 	u8 *trailer;
 	int source_port;
 
-	if (unlikely(dst == NULL))
-		goto out_drop;
 	ds = dst->cpu_switch;
 
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (skb == NULL)
-		goto out;
-
 	if (skb_linearize(skb))
 		goto out_drop;
 
@@ -88,21 +84,11 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 	pskb_trim_rcsum(skb, skb->len - 4);
 
 	skb->dev = ds->ports[source_port].netdev;
-	skb_push(skb, ETH_HLEN);
-	skb->pkt_type = PACKET_HOST;
-	skb->protocol = eth_type_trans(skb, skb->dev);
-
-	skb->dev->stats.rx_packets++;
-	skb->dev->stats.rx_bytes += skb->len;
 
-	netif_receive_skb(skb);
-
-	return 0;
+	return skb;
 
 out_drop:
-	kfree_skb(skb);
-out:
-	return 0;
+	return NULL;
 }
 
 const struct dsa_device_ops trailer_netdev_ops = {
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 1ab30e7d3f99..81dac16933fc 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -350,7 +350,7 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	return 0;
 
 invalid:
-	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL);
+	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
 
 nla_put_failure:
@@ -432,7 +432,7 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	return 0;
 
 invalid:
-	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL);
+	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
 
 nla_put_failure:
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index fc60cd061f39..99f6c254ea77 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -249,8 +249,7 @@ nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
 	if (!cb->args[0]) {
 		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize,
 				  genl_family_attrbuf(&nl802154_fam),
-				  nl802154_fam.maxattr,
-				  nl802154_policy);
+				  nl802154_fam.maxattr, nl802154_policy, NULL);
 		if (err)
 			goto out_unlock;
 
@@ -562,8 +561,8 @@ static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb,
 					struct nl802154_dump_wpan_phy_state *state)
 {
 	struct nlattr **tb = genl_family_attrbuf(&nl802154_fam);
-	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize,
-			      tb, nl802154_fam.maxattr, nl802154_policy);
+	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize, tb,
+			      nl802154_fam.maxattr, nl802154_policy, NULL);
 
 	/* TODO check if we can handle error here,
 	 * we have no backward compatibility
@@ -1308,7 +1307,7 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla,
 	struct nlattr *attrs[NL802154_DEV_ADDR_ATTR_MAX + 1];
 
 	if (!nla || nla_parse_nested(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla,
-				     nl802154_dev_addr_policy))
+				     nl802154_dev_addr_policy, NULL))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] ||
@@ -1348,7 +1347,7 @@ ieee802154_llsec_parse_key_id(struct nlattr *nla,
 	struct nlattr *attrs[NL802154_KEY_ID_ATTR_MAX + 1];
 
 	if (!nla || nla_parse_nested(attrs, NL802154_KEY_ID_ATTR_MAX, nla,
-				     nl802154_key_id_policy))
+				     nl802154_key_id_policy, NULL))
 		return -EINVAL;
 
 	if (!attrs[NL802154_KEY_ID_ATTR_MODE])
@@ -1565,7 +1564,7 @@ static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info)
 
 	if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX,
 			     info->attrs[NL802154_ATTR_SEC_KEY],
-			     nl802154_key_policy))
+			     nl802154_key_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] ||
@@ -1615,7 +1614,7 @@ static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info)
 
 	if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX,
 			     info->attrs[NL802154_ATTR_SEC_KEY],
-			     nl802154_key_policy))
+			     nl802154_key_policy, info->extack))
 		return -EINVAL;
 
 	if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)
@@ -1729,8 +1728,8 @@ ieee802154_llsec_parse_device(struct nlattr *nla,
 {
 	struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
 
-	if (!nla || nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX, nla,
-				     nl802154_dev_policy))
+	if (!nla || nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX,
+				     nla, nl802154_dev_policy, NULL))
 		return -EINVAL;
 
 	memset(dev, 0, sizeof(*dev));
@@ -1783,7 +1782,7 @@ static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info)
 
 	if (nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX,
 			     info->attrs[NL802154_ATTR_SEC_DEVICE],
-			     nl802154_dev_policy))
+			     nl802154_dev_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR])
@@ -1911,7 +1910,7 @@ static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 	if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
 	    nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX,
 			     info->attrs[NL802154_ATTR_SEC_DEVKEY],
-			     nl802154_devkey_policy) < 0)
+			     nl802154_devkey_policy, info->extack) < 0)
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER] ||
@@ -1943,7 +1942,7 @@ static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 
 	if (nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX,
 			     info->attrs[NL802154_ATTR_SEC_DEVKEY],
-			     nl802154_devkey_policy))
+			     nl802154_devkey_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR])
@@ -2063,8 +2062,8 @@ llsec_parse_seclevel(struct nlattr *nla, struct ieee802154_llsec_seclevel *sl)
 {
 	struct nlattr *attrs[NL802154_SECLEVEL_ATTR_MAX + 1];
 
-	if (!nla || nla_parse_nested(attrs, NL802154_SECLEVEL_ATTR_MAX, nla,
-				     nl802154_seclevel_policy))
+	if (!nla || nla_parse_nested(attrs, NL802154_SECLEVEL_ATTR_MAX,
+				     nla, nl802154_seclevel_policy, NULL))
 		return -EINVAL;
 
 	memset(sl, 0, sizeof(*sl));
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c6d4238ff94a..f83de23a30e7 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -11,7 +11,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     tcp_rate.o tcp_recovery.o \
 	     tcp_offload.o datagram.o raw.o udp.o udplite.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
-	     fib_frontend.o fib_semantics.o fib_trie.o \
+	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 602d40f43687..f3dad1661343 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect);
  *	Accept a pending connection. The TCP layer now gives BSD semantics.
  */
 
-int inet_accept(struct socket *sock, struct socket *newsock, int flags)
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+		bool kern)
 {
 	struct sock *sk1 = sock->sk;
 	int err = -EINVAL;
-	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);
+	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
 
 	if (!sk2)
 		goto do_err;
@@ -1342,6 +1343,9 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	if (*(u8 *)iph != 0x45)
 		goto out_unlock;
 
+	if (ip_is_fragment(iph))
+		goto out_unlock;
+
 	if (unlikely(ip_fast_csum((u8 *)iph, 5)))
 		goto out_unlock;
 
@@ -1487,8 +1491,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
@@ -1596,8 +1602,9 @@ static const struct net_protocol igmp_protocol = {
 };
 #endif
 
-static const struct net_protocol tcp_protocol = {
+static struct net_protocol tcp_protocol = {
 	.early_demux	=	tcp_v4_early_demux,
+	.early_demux_handler =  tcp_v4_early_demux,
 	.handler	=	tcp_v4_rcv,
 	.err_handler	=	tcp_v4_err,
 	.no_policy	=	1,
@@ -1605,8 +1612,9 @@ static const struct net_protocol tcp_protocol = {
 	.icmp_strict_tag_validation = 1,
 };
 
-static const struct net_protocol udp_protocol = {
+static struct net_protocol udp_protocol = {
 	.early_demux =	udp_v4_early_demux,
+	.early_demux_handler =	udp_v4_early_demux,
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
 	.no_policy =	1,
@@ -1717,6 +1725,8 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
 	net->ipv4.sysctl_ip_dynaddr = 0;
 	net->ipv4.sysctl_ip_early_demux = 1;
+	net->ipv4.sysctl_udp_early_demux = 1;
+	net->ipv4.sysctl_tcp_early_demux = 1;
 #ifdef CONFIG_SYSCTL
 	net->ipv4.sysctl_ip_prot_sock = PROT_SOCK;
 #endif
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 51b27ae09fbd..0937b34c27ca 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -872,7 +872,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 		    skb->pkt_type != PACKET_HOST)
 			state = NUD_STALE;
 		neigh_update(n, sha, state,
-			     override ? NEIGH_UPDATE_F_OVERRIDE : 0);
+			     override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0);
 		neigh_release(n);
 	}
 
@@ -1033,7 +1033,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 		err = neigh_update(neigh, (r->arp_flags & ATF_COM) ?
 				   r->arp_ha.sa_data : NULL, state,
 				   NEIGH_UPDATE_F_OVERRIDE |
-				   NEIGH_UPDATE_F_ADMIN);
+				   NEIGH_UPDATE_F_ADMIN, 0);
 		neigh_release(neigh);
 	}
 	return err;
@@ -1084,7 +1084,7 @@ static int arp_invalidate(struct net_device *dev, __be32 ip)
 		if (neigh->nud_state & ~NUD_NOARP)
 			err = neigh_update(neigh, NULL, NUD_FAILED,
 					   NEIGH_UPDATE_F_OVERRIDE|
-					   NEIGH_UPDATE_F_ADMIN);
+					   NEIGH_UPDATE_F_ADMIN, 0);
 		neigh_release(neigh);
 	}
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebedd545e5e..df14815a3b8c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -571,7 +571,8 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	return ret;
 }
 
-static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -582,7 +583,8 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -752,7 +754,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	struct in_device *in_dev;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
+			  NULL);
 	if (err < 0)
 		goto errout;
 
@@ -843,7 +846,8 @@ static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
 	return NULL;
 }
 
-static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct in_ifaddr *ifa;
@@ -1192,6 +1196,18 @@ out:
 	return done;
 }
 
+static __be32 in_dev_select_addr(const struct in_device *in_dev,
+				 int scope)
+{
+	for_primary_ifa(in_dev) {
+		if (ifa->ifa_scope != RT_SCOPE_LINK &&
+		    ifa->ifa_scope <= scope)
+			return ifa->ifa_local;
+	} endfor_ifa(in_dev);
+
+	return 0;
+}
+
 __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
 {
 	__be32 addr = 0;
@@ -1228,13 +1244,9 @@ no_in_dev:
 	if (master_idx &&
 	    (dev = dev_get_by_index_rcu(net, master_idx)) &&
 	    (in_dev = __in_dev_get_rcu(dev))) {
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_scope != RT_SCOPE_LINK &&
-			    ifa->ifa_scope <= scope) {
-				addr = ifa->ifa_local;
-				goto out_unlock;
-			}
-		} endfor_ifa(in_dev);
+		addr = in_dev_select_addr(in_dev, scope);
+		if (addr)
+			goto out_unlock;
 	}
 
 	/* Not loopback addresses on loopback should be preferred
@@ -1249,13 +1261,9 @@ no_in_dev:
 		if (!in_dev)
 			continue;
 
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_scope != RT_SCOPE_LINK &&
-			    ifa->ifa_scope <= scope) {
-				addr = ifa->ifa_local;
-				goto out_unlock;
-			}
-		} endfor_ifa(in_dev);
+		addr = in_dev_select_addr(in_dev, scope);
+		if (addr)
+			goto out_unlock;
 	}
 out_unlock:
 	rcu_read_unlock();
@@ -1713,7 +1721,7 @@ static int inet_validate_link_af(const struct net_device *dev,
 	if (dev && !__in_dev_get_rtnl(dev))
 		return -EAFNOSUPPORT;
 
-	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy);
+	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1741,7 +1749,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	if (!in_dev)
 		return -EAFNOSUPPORT;
 
-	if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL) < 0)
+	if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
 	if (tb[IFLA_INET_CONF]) {
@@ -1798,6 +1806,9 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
 		goto nla_put_failure;
 
+	if (!devconf)
+		goto out;
+
 	if ((all || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING,
 			IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
@@ -1819,6 +1830,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
 		goto nla_put_failure;
 
+out:
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1827,8 +1839,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				 struct ipv4_devconf *devconf)
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+				 int ifindex, struct ipv4_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -1838,7 +1850,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
 		goto errout;
 
 	err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
-					RTM_NEWNETCONF, 0, type);
+					event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -1861,7 +1873,8 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
-				    struct nlmsghdr *nlh)
+				    struct nlmsghdr *nlh,
+				    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
@@ -1874,7 +1887,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
-			  devconf_ipv4_policy);
+			  devconf_ipv4_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -2017,10 +2030,12 @@ static void inet_forward_change(struct net *net)
 
 	IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
 	IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
-	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+				    NETCONFA_FORWARDING,
 				    NETCONFA_IFINDEX_ALL,
 				    net->ipv4.devconf_all);
-	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+				    NETCONFA_FORWARDING,
 				    NETCONFA_IFINDEX_DEFAULT,
 				    net->ipv4.devconf_dflt);
 
@@ -2033,7 +2048,8 @@ static void inet_forward_change(struct net *net)
 		in_dev = __in_dev_get_rtnl(dev);
 		if (in_dev) {
 			IN_DEV_CONF_SET(in_dev, FORWARDING, on);
-			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_FORWARDING,
 						    dev->ifindex, &in_dev->cnf);
 		}
 	}
@@ -2078,19 +2094,22 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_RP_FILTER,
 						    ifindex, cnf);
 		}
 		if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_PROXY_NEIGH,
 						    ifindex, cnf);
 		}
 		if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						    ifindex, cnf);
 		}
 	}
@@ -2125,7 +2144,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 					container_of(cnf, struct in_device, cnf);
 				if (*valp)
 					dev_disable_lro(idev->dev);
-				inet_netconf_notify_devconf(net,
+				inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
 							    NETCONFA_FORWARDING,
 							    idev->dev->ifindex,
 							    cnf);
@@ -2133,7 +2152,8 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 			rtnl_unlock();
 			rt_cache_flush(net);
 		} else
-			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_FORWARDING,
 						    NETCONFA_IFINDEX_DEFAULT,
 						    net->ipv4.devconf_dflt);
 	}
@@ -2255,7 +2275,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
 
 	p->sysctl = t;
 
-	inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+				    ifindex, p);
 	return 0;
 
 free:
@@ -2264,16 +2285,18 @@ out:
 	return -ENOBUFS;
 }
 
-static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
+static void __devinet_sysctl_unregister(struct net *net,
+					struct ipv4_devconf *cnf, int ifindex)
 {
 	struct devinet_sysctl_table *t = cnf->sysctl;
 
-	if (!t)
-		return;
+	if (t) {
+		cnf->sysctl = NULL;
+		unregister_net_sysctl_table(t->sysctl_header);
+		kfree(t);
+	}
 
-	cnf->sysctl = NULL;
-	unregister_net_sysctl_table(t->sysctl_header);
-	kfree(t);
+	inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
 }
 
 static int devinet_sysctl_register(struct in_device *idev)
@@ -2295,7 +2318,9 @@ static int devinet_sysctl_register(struct in_device *idev)
 
 static void devinet_sysctl_unregister(struct in_device *idev)
 {
-	__devinet_sysctl_unregister(&idev->cnf);
+	struct net *net = dev_net(idev->dev);
+
+	__devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex);
 	neigh_sysctl_unregister(idev->arp_parms);
 }
 
@@ -2370,9 +2395,9 @@ static __net_init int devinet_init_net(struct net *net)
 
 #ifdef CONFIG_SYSCTL
 err_reg_ctl:
-	__devinet_sysctl_unregister(dflt);
+	__devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT);
 err_reg_dflt:
-	__devinet_sysctl_unregister(all);
+	__devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
 err_reg_all:
 	if (tbl != ctl_forward_entry)
 		kfree(tbl);
@@ -2394,8 +2419,10 @@ static __net_exit void devinet_exit_net(struct net *net)
 
 	tbl = net->ipv4.forw_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->ipv4.forw_hdr);
-	__devinet_sysctl_unregister(net->ipv4.devconf_dflt);
-	__devinet_sysctl_unregister(net->ipv4.devconf_all);
+	__devinet_sysctl_unregister(net, net->ipv4.devconf_dflt,
+				    NETCONFA_IFINDEX_DEFAULT);
+	__devinet_sysctl_unregister(net, net->ipv4.devconf_all,
+				    NETCONFA_IFINDEX_ALL);
 	kfree(tbl);
 #endif
 	kfree(net->ipv4.devconf_dflt);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b1e24446e297..65cc02bd82bc 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -152,21 +152,28 @@ static void esp_output_restore_header(struct sk_buff *skb)
 }
 
 static struct ip_esp_hdr *esp_output_set_extra(struct sk_buff *skb,
+					       struct xfrm_state *x,
 					       struct ip_esp_hdr *esph,
 					       struct esp_output_extra *extra)
 {
-	struct xfrm_state *x = skb_dst(skb)->xfrm;
-
 	/* For ESN we move the header forward by 4 bytes to
 	 * accomodate the high bits.  We will move it back after
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
+		__u32 seqhi;
+		struct xfrm_offload *xo = xfrm_offload(skb);
+
+		if (xo)
+			seqhi = xo->seq.hi;
+		else
+			seqhi = XFRM_SKB_CB(skb)->seq.output.hi;
+
 		extra->esphoff = (unsigned char *)esph -
 				 skb_transport_header(skb);
 		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
 		extra->seqhi = esph->spi;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		esph->seq_no = htonl(seqhi);
 	}
 
 	esph->spi = x->id.spi;
@@ -198,98 +205,56 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
 	tail[plen - 1] = proto;
 }
 
-static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
+static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
-	struct esp_output_extra *extra;
-	int err = -ENOMEM;
-	struct ip_esp_hdr *esph;
-	struct crypto_aead *aead;
-	struct aead_request *req;
-	struct scatterlist *sg, *dsg;
-	struct sk_buff *trailer;
-	struct page *page;
-	void *tmp;
-	u8 *iv;
-	u8 *tail;
-	u8 *vaddr;
-	int blksize;
-	int clen;
-	int alen;
-	int plen;
-	int ivlen;
-	int tfclen;
-	int nfrags;
-	int assoclen;
-	int extralen;
-	int tailen;
-	__be64 seqno;
-	__u8 proto = *skb_mac_header(skb);
-
-	/* skb is pure payload to encrypt */
-
-	aead = x->data;
-	alen = crypto_aead_authsize(aead);
-	ivlen = crypto_aead_ivsize(aead);
-
-	tfclen = 0;
-	if (x->tfcpad) {
-		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
-		u32 padto;
-
-		padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached));
-		if (skb->len < padto)
-			tfclen = padto - skb->len;
+	int encap_type;
+	struct udphdr *uh;
+	__be32 *udpdata32;
+	__be16 sport, dport;
+	struct xfrm_encap_tmpl *encap = x->encap;
+	struct ip_esp_hdr *esph = esp->esph;
+
+	spin_lock_bh(&x->lock);
+	sport = encap->encap_sport;
+	dport = encap->encap_dport;
+	encap_type = encap->encap_type;
+	spin_unlock_bh(&x->lock);
+
+	uh = (struct udphdr *)esph;
+	uh->source = sport;
+	uh->dest = dport;
+	uh->len = htons(skb->len + esp->tailen
+		  - skb_transport_offset(skb));
+	uh->check = 0;
+
+	switch (encap_type) {
+	default:
+	case UDP_ENCAP_ESPINUDP:
+		esph = (struct ip_esp_hdr *)(uh + 1);
+		break;
+	case UDP_ENCAP_ESPINUDP_NON_IKE:
+		udpdata32 = (__be32 *)(uh + 1);
+		udpdata32[0] = udpdata32[1] = 0;
+		esph = (struct ip_esp_hdr *)(udpdata32 + 2);
+		break;
 	}
-	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
-	clen = ALIGN(skb->len + 2 + tfclen, blksize);
-	plen = clen - skb->len - tfclen;
-	tailen = tfclen + plen + alen;
-	assoclen = sizeof(*esph);
-	extralen = 0;
 
-	if (x->props.flags & XFRM_STATE_ESN) {
-		extralen += sizeof(*extra);
-		assoclen += sizeof(__be32);
-	}
+	*skb_mac_header(skb) = IPPROTO_UDP;
+	esp->esph = esph;
+}
 
-	*skb_mac_header(skb) = IPPROTO_ESP;
-	esph = ip_esp_hdr(skb);
+int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+{
+	u8 *tail;
+	u8 *vaddr;
+	int nfrags;
+	struct page *page;
+	struct sk_buff *trailer;
+	int tailen = esp->tailen;
 
 	/* this is non-NULL only with UDP Encapsulation */
-	if (x->encap) {
-		struct xfrm_encap_tmpl *encap = x->encap;
-		struct udphdr *uh;
-		__be32 *udpdata32;
-		__be16 sport, dport;
-		int encap_type;
-
-		spin_lock_bh(&x->lock);
-		sport = encap->encap_sport;
-		dport = encap->encap_dport;
-		encap_type = encap->encap_type;
-		spin_unlock_bh(&x->lock);
-
-		uh = (struct udphdr *)esph;
-		uh->source = sport;
-		uh->dest = dport;
-		uh->len = htons(skb->len + tailen
-				- skb_transport_offset(skb));
-		uh->check = 0;
-
-		switch (encap_type) {
-		default:
-		case UDP_ENCAP_ESPINUDP:
-			esph = (struct ip_esp_hdr *)(uh + 1);
-			break;
-		case UDP_ENCAP_ESPINUDP_NON_IKE:
-			udpdata32 = (__be32 *)(uh + 1);
-			udpdata32[0] = udpdata32[1] = 0;
-			esph = (struct ip_esp_hdr *)(udpdata32 + 2);
-			break;
-		}
-
-		*skb_mac_header(skb) = IPPROTO_UDP;
-	}
+	if (x->encap)
+		esp_output_udp_encap(x, skb, esp);
 
 	if (!skb_cloned(skb)) {
 		if (tailen <= skb_availroom(skb)) {
@@ -304,6 +269,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 			struct sock *sk = skb->sk;
 			struct page_frag *pfrag = &x->xfrag;
 
+			esp->inplace = false;
+
 			allocsize = ALIGN(tailen, L1_CACHE_BYTES);
 
 			spin_lock_bh(&x->lock);
@@ -320,10 +287,12 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 			tail = vaddr + pfrag->offset;
 
-			esp_output_fill_trailer(tail, tfclen, plen, proto);
+			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
 			kunmap_atomic(vaddr);
 
+			spin_unlock_bh(&x->lock);
+
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
@@ -339,107 +308,113 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 			if (sk)
 				atomic_add(tailen, &sk->sk_wmem_alloc);
 
-			skb_push(skb, -skb_network_offset(skb));
-
-			esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
-			esph->spi = x->id.spi;
-
-			tmp = esp_alloc_tmp(aead, nfrags + 2, extralen);
-			if (!tmp) {
-				spin_unlock_bh(&x->lock);
-				err = -ENOMEM;
-				goto error;
-			}
-
-			extra = esp_tmp_extra(tmp);
-			iv = esp_tmp_iv(aead, tmp, extralen);
-			req = esp_tmp_req(aead, iv);
-			sg = esp_req_sg(aead, req);
-			dsg = &sg[nfrags];
-
-			esph = esp_output_set_extra(skb, esph, extra);
-
-			sg_init_table(sg, nfrags);
-			skb_to_sgvec(skb, sg,
-				     (unsigned char *)esph - skb->data,
-				     assoclen + ivlen + clen + alen);
-
-			allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
-
-			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
-				spin_unlock_bh(&x->lock);
-				err = -ENOMEM;
-				goto error;
-			}
-
-			skb_shinfo(skb)->nr_frags = 1;
-
-			page = pfrag->page;
-			get_page(page);
-			/* replace page frags in skb with new page */
-			__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
-			pfrag->offset = pfrag->offset + allocsize;
-
-			sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
-			skb_to_sgvec(skb, dsg,
-				     (unsigned char *)esph - skb->data,
-				     assoclen + ivlen + clen + alen);
-
-			spin_unlock_bh(&x->lock);
-
-			goto skip_cow2;
+			goto out;
 		}
 	}
 
 cow:
-	err = skb_cow_data(skb, tailen, &trailer);
-	if (err < 0)
-		goto error;
-	nfrags = err;
+	nfrags = skb_cow_data(skb, tailen, &trailer);
+	if (nfrags < 0)
+		goto out;
 	tail = skb_tail_pointer(trailer);
-	esph = ip_esp_hdr(skb);
+	esp->esph = ip_esp_hdr(skb);
 
 skip_cow:
-	esp_output_fill_trailer(tail, tfclen, plen, proto);
+	esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
+	pskb_put(skb, trailer, tailen);
 
-	pskb_put(skb, trailer, clen - skb->len + alen);
-	skb_push(skb, -skb_network_offset(skb));
-	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
-	esph->spi = x->id.spi;
+out:
+	return nfrags;
+}
+EXPORT_SYMBOL_GPL(esp_output_head);
 
-	tmp = esp_alloc_tmp(aead, nfrags, extralen);
-	if (!tmp) {
-		err = -ENOMEM;
-		goto error;
+int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+{
+	u8 *iv;
+	int alen;
+	void *tmp;
+	int ivlen;
+	int assoclen;
+	int extralen;
+	struct page *page;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct aead_request *req;
+	struct scatterlist *sg, *dsg;
+	struct esp_output_extra *extra;
+	int err = -ENOMEM;
+
+	assoclen = sizeof(struct ip_esp_hdr);
+	extralen = 0;
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		extralen += sizeof(*extra);
+		assoclen += sizeof(__be32);
 	}
 
+	aead = x->data;
+	alen = crypto_aead_authsize(aead);
+	ivlen = crypto_aead_ivsize(aead);
+
+	tmp = esp_alloc_tmp(aead, esp->nfrags + 2, extralen);
+	if (!tmp)
+		goto error;
+
 	extra = esp_tmp_extra(tmp);
 	iv = esp_tmp_iv(aead, tmp, extralen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
-	dsg = sg;
 
-	esph = esp_output_set_extra(skb, esph, extra);
+	if (esp->inplace)
+		dsg = sg;
+	else
+		dsg = &sg[esp->nfrags];
 
-	sg_init_table(sg, nfrags);
+	esph = esp_output_set_extra(skb, x, esp->esph, extra);
+	esp->esph = esph;
+
+	sg_init_table(sg, esp->nfrags);
 	skb_to_sgvec(skb, sg,
 		     (unsigned char *)esph - skb->data,
-		     assoclen + ivlen + clen + alen);
+		     assoclen + ivlen + esp->clen + alen);
+
+	if (!esp->inplace) {
+		int allocsize;
+		struct page_frag *pfrag = &x->xfrag;
+
+		allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
+
+		spin_lock_bh(&x->lock);
+		if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+			spin_unlock_bh(&x->lock);
+			goto error;
+		}
+
+		skb_shinfo(skb)->nr_frags = 1;
+
+		page = pfrag->page;
+		get_page(page);
+		/* replace page frags in skb with new page */
+		__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
+		pfrag->offset = pfrag->offset + allocsize;
+		spin_unlock_bh(&x->lock);
+
+		sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
+		skb_to_sgvec(skb, dsg,
+			     (unsigned char *)esph - skb->data,
+			     assoclen + ivlen + esp->clen + alen);
+	}
 
-skip_cow2:
 	if ((x->props.flags & XFRM_STATE_ESN))
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	else
 		aead_request_set_callback(req, 0, esp_output_done, skb);
 
-	aead_request_set_crypt(req, sg, dsg, ivlen + clen, iv);
+	aead_request_set_crypt(req, sg, dsg, ivlen + esp->clen, iv);
 	aead_request_set_ad(req, assoclen);
 
-	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
-			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
-
 	memset(iv, 0, ivlen);
-	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8),
+	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&esp->seqno + 8 - min(ivlen, 8),
 	       min(ivlen, 8));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
@@ -465,11 +440,63 @@ skip_cow2:
 error:
 	return err;
 }
+EXPORT_SYMBOL_GPL(esp_output_tail);
 
-static int esp_input_done2(struct sk_buff *skb, int err)
+static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int alen;
+	int blksize;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct esp_info esp;
+
+	esp.inplace = true;
+
+	esp.proto = *skb_mac_header(skb);
+	*skb_mac_header(skb) = IPPROTO_ESP;
+
+	/* skb is pure payload to encrypt */
+
+	aead = x->data;
+	alen = crypto_aead_authsize(aead);
+
+	esp.tfclen = 0;
+	if (x->tfcpad) {
+		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
+		u32 padto;
+
+		padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached));
+		if (skb->len < padto)
+			esp.tfclen = padto - skb->len;
+	}
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
+	esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
+	esp.plen = esp.clen - skb->len - esp.tfclen;
+	esp.tailen = esp.tfclen + esp.plen + alen;
+
+	esp.esph = ip_esp_hdr(skb);
+
+	esp.nfrags = esp_output_head(x, skb, &esp);
+	if (esp.nfrags < 0)
+		return esp.nfrags;
+
+	esph = esp.esph;
+	esph->spi = x->id.spi;
+
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+	esp.seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
+				 ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+
+	skb_push(skb, -skb_network_offset(skb));
+
+	return esp_output_tail(x, skb, &esp);
+}
+
+int esp_input_done2(struct sk_buff *skb, int err)
 {
 	const struct iphdr *iph;
 	struct xfrm_state *x = xfrm_input_state(skb);
+	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct crypto_aead *aead = x->data;
 	int alen = crypto_aead_authsize(aead);
 	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
@@ -478,7 +505,8 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 	u8 nexthdr[2];
 	int padlen;
 
-	kfree(ESP_SKB_CB(skb)->tmp);
+	if (!xo || (xo && !(xo->flags & CRYPTO_DONE)))
+		kfree(ESP_SKB_CB(skb)->tmp);
 
 	if (unlikely(err))
 		goto out;
@@ -549,6 +577,7 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 out:
 	return err;
 }
+EXPORT_SYMBOL_GPL(esp_input_done2);
 
 static void esp_input_done(struct crypto_async_request *base, int err)
 {
@@ -751,13 +780,17 @@ static int esp_init_aead(struct xfrm_state *x)
 	char aead_name[CRYPTO_MAX_ALG_NAME];
 	struct crypto_aead *aead;
 	int err;
+	u32 mask = 0;
 
 	err = -ENAMETOOLONG;
 	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
 		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
 		goto error;
 
-	aead = crypto_alloc_aead(aead_name, 0, 0);
+	if (x->xso.offload_handle)
+		mask |= CRYPTO_ALG_ASYNC;
+
+	aead = crypto_alloc_aead(aead_name, 0, mask);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -787,6 +820,7 @@ static int esp_init_authenc(struct xfrm_state *x)
 	char authenc_name[CRYPTO_MAX_ALG_NAME];
 	unsigned int keylen;
 	int err;
+	u32 mask = 0;
 
 	err = -EINVAL;
 	if (!x->ealg)
@@ -812,7 +846,10 @@ static int esp_init_authenc(struct xfrm_state *x)
 			goto error;
 	}
 
-	aead = crypto_alloc_aead(authenc_name, 0, 0);
+	if (x->xso.offload_handle)
+		mask |= CRYPTO_ALG_ASYNC;
+
+	aead = crypto_alloc_aead(authenc_name, 0, mask);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -931,7 +968,7 @@ static const struct xfrm_type esp_type =
 	.destructor	= esp_destroy,
 	.get_mtu	= esp4_get_mtu,
 	.input		= esp_input,
-	.output		= esp_output
+	.output		= esp_output,
 };
 
 static struct xfrm4_protocol esp4_protocol = {
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 1de442632406..e0666016a764 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -43,27 +43,31 @@ static struct sk_buff **esp4_gro_receive(struct sk_buff **head,
 	if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
 		goto out;
 
-	err = secpath_set(skb);
-	if (err)
-		goto out;
+	xo = xfrm_offload(skb);
+	if (!xo || !(xo->flags & CRYPTO_DONE)) {
+		err = secpath_set(skb);
+		if (err)
+			goto out;
 
-	if (skb->sp->len == XFRM_MAX_DEPTH)
-		goto out;
+		if (skb->sp->len == XFRM_MAX_DEPTH)
+			goto out;
 
-	x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
-			      (xfrm_address_t *)&ip_hdr(skb)->daddr,
-			      spi, IPPROTO_ESP, AF_INET);
-	if (!x)
-		goto out;
+		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
+				      (xfrm_address_t *)&ip_hdr(skb)->daddr,
+				      spi, IPPROTO_ESP, AF_INET);
+		if (!x)
+			goto out;
 
-	skb->sp->xvec[skb->sp->len++] = x;
-	skb->sp->olen++;
+		skb->sp->xvec[skb->sp->len++] = x;
+		skb->sp->olen++;
 
-	xo = xfrm_offload(skb);
-	if (!xo) {
-		xfrm_state_put(x);
-		goto out;
+		xo = xfrm_offload(skb);
+		if (!xo) {
+			xfrm_state_put(x);
+			goto out;
+		}
 	}
+
 	xo->flags |= XFRM_GRO;
 
 	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
@@ -84,19 +88,214 @@ out:
 	return NULL;
 }
 
+static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ip_esp_hdr *esph;
+	struct iphdr *iph = ip_hdr(skb);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	int proto = iph->protocol;
+
+	skb_push(skb, -skb_network_offset(skb));
+	esph = ip_esp_hdr(skb);
+	*skb_mac_header(skb) = IPPROTO_ESP;
+
+	esph->spi = x->id.spi;
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+
+	xo->proto = proto;
+}
+
+static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
+				        netdev_features_t features)
+{
+	__u32 seq;
+	int err = 0;
+	struct sk_buff *skb2;
+	struct xfrm_state *x;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	netdev_features_t esp_features = features;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (!xo)
+		goto out;
+
+	seq = xo->seq.low;
+
+	x = skb->sp->xvec[skb->sp->len - 1];
+	aead = x->data;
+	esph = ip_esp_hdr(skb);
+
+	if (esph->spi != x->id.spi)
+		goto out;
+
+	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
+		goto out;
+
+	__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));
+
+	skb->encap_hdr_csum = 1;
+
+	if (!(features & NETIF_F_HW_ESP))
+		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+
+	segs = x->outer_mode->gso_segment(x, skb, esp_features);
+	if (IS_ERR_OR_NULL(segs))
+		goto out;
+
+	__skb_pull(skb, skb->data - skb_mac_header(skb));
+
+	skb2 = segs;
+	do {
+		struct sk_buff *nskb = skb2->next;
+
+		xo = xfrm_offload(skb2);
+		xo->flags |= XFRM_GSO_SEGMENT;
+		xo->seq.low = seq;
+		xo->seq.hi = xfrm_replay_seqhi(x, seq);
+
+		if(!(features & NETIF_F_HW_ESP))
+			xo->flags |= CRYPTO_FALLBACK;
+
+		x->outer_mode->xmit(x, skb2);
+
+		err = x->type_offload->xmit(x, skb2, esp_features);
+		if (err) {
+			kfree_skb_list(segs);
+			return ERR_PTR(err);
+		}
+
+		if (!skb_is_gso(skb2))
+			seq++;
+		else
+			seq += skb_shinfo(skb2)->gso_segs;
+
+		skb_push(skb2, skb2->mac_len);
+		skb2 = nskb;
+	} while (skb2);
+
+out:
+	return segs;
+}
+
+static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct crypto_aead *aead = x->data;
+
+	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
+		return -EINVAL;
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	return esp_input_done2(skb, 0);
+}
+
+static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_t features)
+{
+	int err;
+	int alen;
+	int blksize;
+	struct xfrm_offload *xo;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct esp_info esp;
+	bool hw_offload = true;
+
+	esp.inplace = true;
+
+	xo = xfrm_offload(skb);
+
+	if (!xo)
+		return -EINVAL;
+
+	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
+	    (x->xso.dev != skb->dev)) {
+		xo->flags |= CRYPTO_FALLBACK;
+		hw_offload = false;
+	}
+
+	esp.proto = xo->proto;
+
+	/* skb is pure payload to encrypt */
+
+	aead = x->data;
+	alen = crypto_aead_authsize(aead);
+
+	esp.tfclen = 0;
+	/* XXX: Add support for tfc padding here. */
+
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
+	esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
+	esp.plen = esp.clen - skb->len - esp.tfclen;
+	esp.tailen = esp.tfclen + esp.plen + alen;
+
+	esp.esph = ip_esp_hdr(skb);
+
+
+	if (!hw_offload || (hw_offload && !skb_is_gso(skb))) {
+		esp.nfrags = esp_output_head(x, skb, &esp);
+		if (esp.nfrags < 0)
+			return esp.nfrags;
+	}
+
+	esph = esp.esph;
+	esph->spi = x->id.spi;
+
+	skb_push(skb, -skb_network_offset(skb));
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		esph->seq_no = htonl(xo->seq.low);
+	} else {
+		ip_hdr(skb)->tot_len = htons(skb->len);
+		ip_send_check(ip_hdr(skb));
+	}
+
+	if (hw_offload)
+		return 0;
+
+	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
+
+	err = esp_output_tail(x, skb, &esp);
+	if (err < 0)
+		return err;
+
+	secpath_reset(skb);
+
+	return 0;
+}
+
 static const struct net_offload esp4_offload = {
 	.callbacks = {
 		.gro_receive = esp4_gro_receive,
+		.gso_segment = esp4_gso_segment,
 	},
 };
 
+static const struct xfrm_type_offload esp_type_offload = {
+	.description	= "ESP4 OFFLOAD",
+	.owner		= THIS_MODULE,
+	.proto	     	= IPPROTO_ESP,
+	.input_tail	= esp_input_tail,
+	.xmit		= esp_xmit,
+	.encap		= esp4_gso_encap,
+};
+
 static int __init esp4_offload_init(void)
 {
+	if (xfrm_register_type_offload(&esp_type_offload, AF_INET) < 0) {
+		pr_info("%s: can't add xfrm type offload\n", __func__);
+		return -EAGAIN;
+	}
+
 	return inet_add_offload(&esp4_offload, IPPROTO_ESP);
 }
 
 static void __exit esp4_offload_exit(void)
 {
+	if (xfrm_unregister_type_offload(&esp_type_offload, AF_INET) < 0)
+		pr_info("%s: can't remove xfrm type offload\n", __func__);
+
 	inet_del_offload(&esp4_offload, IPPROTO_ESP);
 }
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 42bfd08109dd..39bd1edee676 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -632,7 +632,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 	int err, remaining;
 	struct rtmsg *rtm;
 
-	err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy);
+	err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy,
+			     NULL);
 	if (err < 0)
 		goto errout;
 
@@ -709,7 +710,8 @@ errout:
 	return err;
 }
 
-static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_config cfg;
@@ -731,7 +733,8 @@ errout:
 	return err;
 }
 
-static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_config cfg;
@@ -1083,7 +1086,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+	    skb->len < nlh->nlmsg_len ||
 	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
@@ -1126,7 +1130,8 @@ static void fib_disable_ip(struct net_device *dev, unsigned long event,
 {
 	if (fib_sync_down_dev(dev, event, force))
 		fib_flush(dev_net(dev));
-	rt_cache_flush(dev_net(dev));
+	else
+		rt_cache_flush(dev_net(dev));
 	arp_ifdown(dev);
 }
 
diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
new file mode 100644
index 000000000000..e0714d975947
--- /dev/null
+++ b/net/ipv4/fib_notifier.c
@@ -0,0 +1,86 @@
+#include <linux/rtnetlink.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <net/net_namespace.h>
+#include <net/netns/ipv4.h>
+#include <net/ip_fib.h>
+
+static ATOMIC_NOTIFIER_HEAD(fib_chain);
+
+int call_fib_notifier(struct notifier_block *nb, struct net *net,
+		      enum fib_event_type event_type,
+		      struct fib_notifier_info *info)
+{
+	info->net = net;
+	return nb->notifier_call(nb, event_type, info);
+}
+
+int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
+		       struct fib_notifier_info *info)
+{
+	net->ipv4.fib_seq++;
+	info->net = net;
+	return atomic_notifier_call_chain(&fib_chain, event_type, info);
+}
+
+static unsigned int fib_seq_sum(void)
+{
+	unsigned int fib_seq = 0;
+	struct net *net;
+
+	rtnl_lock();
+	for_each_net(net)
+		fib_seq += net->ipv4.fib_seq;
+	rtnl_unlock();
+
+	return fib_seq;
+}
+
+static bool fib_dump_is_consistent(struct notifier_block *nb,
+				   void (*cb)(struct notifier_block *nb),
+				   unsigned int fib_seq)
+{
+	atomic_notifier_chain_register(&fib_chain, nb);
+	if (fib_seq == fib_seq_sum())
+		return true;
+	atomic_notifier_chain_unregister(&fib_chain, nb);
+	if (cb)
+		cb(nb);
+	return false;
+}
+
+#define FIB_DUMP_MAX_RETRIES 5
+int register_fib_notifier(struct notifier_block *nb,
+			  void (*cb)(struct notifier_block *nb))
+{
+	int retries = 0;
+
+	do {
+		unsigned int fib_seq = fib_seq_sum();
+		struct net *net;
+
+		/* Mutex semantics guarantee that every change done to
+		 * FIB tries before we read the change sequence counter
+		 * is now visible to us.
+		 */
+		rcu_read_lock();
+		for_each_net_rcu(net) {
+			fib_rules_notify(net, nb);
+			fib_notify(net, nb);
+		}
+		rcu_read_unlock();
+
+		if (fib_dump_is_consistent(nb, cb, fib_seq))
+			return 0;
+	} while (++retries < FIB_DUMP_MAX_RETRIES);
+
+	return -EBUSY;
+}
+EXPORT_SYMBOL(register_fib_notifier);
+
+int unregister_fib_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&fib_chain, nb);
+}
+EXPORT_SYMBOL(unregister_fib_notifier);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 2e50062f642d..778ecf977eb2 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,6 +47,27 @@ struct fib4_rule {
 #endif
 };
 
+static bool fib4_rule_matchall(const struct fib_rule *rule)
+{
+	struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
+
+	if (r->dst_len || r->src_len || r->tos)
+		return false;
+	return fib_rule_matchall(rule);
+}
+
+bool fib4_rule_default(const struct fib_rule *rule)
+{
+	if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+	    rule->l3mdev)
+		return false;
+	if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
+	    rule->table != RT_TABLE_DEFAULT)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib4_rule_default);
+
 int __fib_lookup(struct net *net, struct flowi4 *flp,
 		 struct fib_result *res, unsigned int flags)
 {
@@ -164,12 +185,36 @@ static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
+static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
+				  enum fib_event_type event_type,
+				  struct fib_rule *rule)
+{
+	struct fib_rule_notifier_info info = {
+		.rule = rule,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
 static int call_fib_rule_notifiers(struct net *net,
-				   enum fib_event_type event_type)
+				   enum fib_event_type event_type,
+				   struct fib_rule *rule)
+{
+	struct fib_rule_notifier_info info = {
+		.rule = rule,
+	};
+
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
+/* Called with rcu_read_lock() */
+void fib_rules_notify(struct net *net, struct notifier_block *nb)
 {
-	struct fib_notifier_info info;
+	struct fib_rules_ops *ops = net->ipv4.rules_ops;
+	struct fib_rule *rule;
 
-	return call_fib_notifiers(net, event_type, &info);
+	list_for_each_entry_rcu(rule, &ops->rules_list, list)
+		call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule);
 }
 
 static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
@@ -228,7 +273,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule);
 
 	err = 0;
 errout:
@@ -250,7 +295,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule);
 errout:
 	return err;
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 317026a39cfa..da449ddb8cc1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -57,7 +57,6 @@ static unsigned int fib_info_cnt;
 static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-u32 fib_multipath_secret __read_mostly;
 
 #define for_nexthops(fi) {						\
 	int nhsel; const struct fib_nh *nh;				\
@@ -576,9 +575,6 @@ static void fib_rebalance(struct fib_info *fi)
 
 		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
 	} endfor_nexthops(fi);
-
-	net_get_random_once(&fib_multipath_secret,
-			    sizeof(fib_multipath_secret));
 }
 
 static inline void fib_add_weight(struct fib_info *fi,
@@ -1641,7 +1637,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
 #endif
 
 void fib_select_path(struct net *net, struct fib_result *res,
-		     struct flowi4 *fl4, int mp_hash)
+		     struct flowi4 *fl4, const struct sk_buff *skb)
 {
 	bool oif_check;
 
@@ -1650,10 +1646,9 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1 && oif_check) {
-		if (mp_hash < 0)
-			mp_hash = get_hash_from_flowi4(fl4) >> 1;
+		int h = fib_multipath_hash(res->fi, fl4, skb);
 
-		fib_select_multipath(res, mp_hash);
+		fib_select_multipath(res, h);
 	}
 	else
 #endif
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 2f0d8233950f..1201409ba1dc 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -84,43 +84,6 @@
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
-static unsigned int fib_seq_sum(void)
-{
-	unsigned int fib_seq = 0;
-	struct net *net;
-
-	rtnl_lock();
-	for_each_net(net)
-		fib_seq += net->ipv4.fib_seq;
-	rtnl_unlock();
-
-	return fib_seq;
-}
-
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-static int call_fib_notifier(struct notifier_block *nb, struct net *net,
-			     enum fib_event_type event_type,
-			     struct fib_notifier_info *info)
-{
-	info->net = net;
-	return nb->notifier_call(nb, event_type, info);
-}
-
-static void fib_rules_notify(struct net *net, struct notifier_block *nb,
-			     enum fib_event_type event_type)
-{
-#ifdef CONFIG_IP_MULTIPLE_TABLES
-	struct fib_notifier_info info;
-
-	if (net->ipv4.fib_has_custom_rules)
-		call_fib_notifier(nb, net, event_type, &info);
-#endif
-}
-
-static void fib_notify(struct net *net, struct notifier_block *nb,
-		       enum fib_event_type event_type);
-
 static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 				   enum fib_event_type event_type, u32 dst,
 				   int dst_len, struct fib_info *fi,
@@ -137,62 +100,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 	return call_fib_notifier(nb, net, event_type, &info.info);
 }
 
-static bool fib_dump_is_consistent(struct notifier_block *nb,
-				   void (*cb)(struct notifier_block *nb),
-				   unsigned int fib_seq)
-{
-	atomic_notifier_chain_register(&fib_chain, nb);
-	if (fib_seq == fib_seq_sum())
-		return true;
-	atomic_notifier_chain_unregister(&fib_chain, nb);
-	if (cb)
-		cb(nb);
-	return false;
-}
-
-#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
-			  void (*cb)(struct notifier_block *nb))
-{
-	int retries = 0;
-
-	do {
-		unsigned int fib_seq = fib_seq_sum();
-		struct net *net;
-
-		/* Mutex semantics guarantee that every change done to
-		 * FIB tries before we read the change sequence counter
-		 * is now visible to us.
-		 */
-		rcu_read_lock();
-		for_each_net_rcu(net) {
-			fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD);
-			fib_notify(net, nb, FIB_EVENT_ENTRY_ADD);
-		}
-		rcu_read_unlock();
-
-		if (fib_dump_is_consistent(nb, cb, fib_seq))
-			return 0;
-	} while (++retries < FIB_DUMP_MAX_RETRIES);
-
-	return -EBUSY;
-}
-EXPORT_SYMBOL(register_fib_notifier);
-
-int unregister_fib_notifier(struct notifier_block *nb)
-{
-	return atomic_notifier_chain_unregister(&fib_chain, nb);
-}
-EXPORT_SYMBOL(unregister_fib_notifier);
-
-int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
-		       struct fib_notifier_info *info)
-{
-	net->ipv4.fib_seq++;
-	info->net = net;
-	return atomic_notifier_call_chain(&fib_chain, event_type, info);
-}
-
 static int call_fib_entry_notifiers(struct net *net,
 				    enum fib_event_type event_type, u32 dst,
 				    int dst_len, struct fib_info *fi,
@@ -1995,8 +1902,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 }
 
 static void fib_leaf_notify(struct net *net, struct key_vector *l,
-			    struct fib_table *tb, struct notifier_block *nb,
-			    enum fib_event_type event_type)
+			    struct fib_table *tb, struct notifier_block *nb)
 {
 	struct fib_alias *fa;
 
@@ -2012,22 +1918,21 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
 		if (tb->tb_id != fa->tb_id)
 			continue;
 
-		call_fib_entry_notifier(nb, net, event_type, l->key,
+		call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
 					KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
 					fa->fa_type, fa->tb_id);
 	}
 }
 
 static void fib_table_notify(struct net *net, struct fib_table *tb,
-			     struct notifier_block *nb,
-			     enum fib_event_type event_type)
+			     struct notifier_block *nb)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *l, *tp = t->kv;
 	t_key key = 0;
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		fib_leaf_notify(net, l, tb, nb, event_type);
+		fib_leaf_notify(net, l, tb, nb);
 
 		key = l->key + 1;
 		/* stop in case of wrap around */
@@ -2036,8 +1941,7 @@ static void fib_table_notify(struct net *net, struct fib_table *tb,
 	}
 }
 
-static void fib_notify(struct net *net, struct notifier_block *nb,
-		       enum fib_event_type event_type)
+void fib_notify(struct net *net, struct notifier_block *nb)
 {
 	unsigned int h;
 
@@ -2046,7 +1950,7 @@ static void fib_notify(struct net *net, struct notifier_block *nb,
 		struct fib_table *tb;
 
 		hlist_for_each_entry_rcu(tb, head, tb_hlist)
-			fib_table_notify(net, tb, nb, event_type);
+			fib_table_notify(net, tb, nb);
 	}
 }
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fc310db2708b..43318b5f5647 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -464,22 +464,6 @@ out_bh_enable:
 	local_bh_enable();
 }
 
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-
-/* Source and destination is swapped. See ip_multipath_icmp_hash */
-static int icmp_multipath_hash_skb(const struct sk_buff *skb)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-
-	return fib_multipath_hash(iph->daddr, iph->saddr);
-}
-
-#else
-
-#define icmp_multipath_hash_skb(skb) (-1)
-
-#endif
-
 static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
@@ -505,8 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
-	rt = __ip_route_output_key_hash(net, fl4,
-					icmp_multipath_hash_skb(skb_in));
+	rt = __ip_route_output_key_hash(net, fl4, skb_in);
 	if (IS_ERR(rt))
 		return rt;
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4d5980ade3b..5e313c1ac94f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
 /*
  * This will accept the next outstanding connection.
  */
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbe7f72db9c1..b3cdeec85f1f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -198,6 +198,7 @@ static void ip_expire(unsigned long arg)
 	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
 
+	rcu_read_lock();
 	spin_lock(&qp->q.lock);
 
 	if (qp->q.flags & INET_FRAG_COMPLETE)
@@ -207,7 +208,7 @@ static void ip_expire(unsigned long arg)
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 
 	if (!inet_frag_evicting(&qp->q)) {
-		struct sk_buff *head = qp->q.fragments;
+		struct sk_buff *clone, *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
 
@@ -216,32 +217,40 @@ static void ip_expire(unsigned long arg)
 		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
 			goto out;
 
-		rcu_read_lock();
 		head->dev = dev_get_by_index_rcu(net, qp->iif);
 		if (!head->dev)
-			goto out_rcu_unlock;
+			goto out;
+
 
 		/* skb has no dst, perform route lookup again */
 		iph = ip_hdr(head);
 		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
 		if (err)
-			goto out_rcu_unlock;
+			goto out;
 
 		/* Only an end host needs to send an ICMP
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (frag_expire_skip_icmp(qp->user) &&
 		    (skb_rtable(head)->rt_type != RTN_LOCAL))
-			goto out_rcu_unlock;
+			goto out;
+
+		clone = skb_clone(head, GFP_ATOMIC);
 
 		/* Send an ICMP "Fragment Reassembly Timeout" message. */
-		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
-out_rcu_unlock:
-		rcu_read_unlock();
+		if (clone) {
+			spin_unlock(&qp->q.lock);
+			icmp_send(clone, ICMP_TIME_EXCEEDED,
+				  ICMP_EXC_FRAGTIME, 0);
+			consume_skb(clone);
+			goto out_rcu_unlock;
+		}
 	}
 out:
 	spin_unlock(&qp->q.lock);
+out_rcu_unlock:
+	rcu_read_unlock();
 	ipq_put(qp);
 }
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c9c1cb635d9a..e90c80a548ad 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -829,7 +829,8 @@ out:
 static int ipgre_netlink_parms(struct net_device *dev,
 				struct nlattr *data[],
 				struct nlattr *tb[],
-				struct ip_tunnel_parm *parms)
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
 
@@ -886,6 +887,9 @@ static int ipgre_netlink_parms(struct net_device *dev,
 		t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]);
 	}
 
+	if (data[IFLA_GRE_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
+
 	return 0;
 }
 
@@ -957,6 +961,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	__u32 fwmark = 0;
 	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
@@ -967,31 +972,32 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	err = ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
-	return ip_tunnel_newlink(dev, tb, &p);
+	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
 static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[])
 {
+	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	__u32 fwmark = t->fwmark;
 	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
-		struct ip_tunnel *t = netdev_priv(dev);
 		err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	err = ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
-	return ip_tunnel_changelink(dev, tb, &p);
+	return ip_tunnel_changelink(dev, tb, &p, fwmark);
 }
 
 static size_t ipgre_get_size(const struct net_device *dev)
@@ -1029,6 +1035,8 @@ static size_t ipgre_get_size(const struct net_device *dev)
 		nla_total_size(0) +
 		/* IFLA_GRE_IGNORE_DF */
 		nla_total_size(1) +
+		/* IFLA_GRE_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1049,7 +1057,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) ||
 	    nla_put_u8(skb, IFLA_GRE_PMTUDISC,
-		       !!(p->iph.frag_off & htons(IP_DF))))
+		       !!(p->iph.frag_off & htons(IP_DF))) ||
+	    nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -1093,6 +1102,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_ENCAP_DPORT]	= { .type = NLA_U16 },
 	[IFLA_GRE_COLLECT_METADATA]	= { .type = NLA_FLAG },
 	[IFLA_GRE_IGNORE_DF]	= { .type = NLA_U8 },
+	[IFLA_GRE_FWMARK]	= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d6feabb03516..fa2dc8f692c6 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -313,6 +313,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct net_device *dev = skb->dev;
+	void (*edemux)(struct sk_buff *skb);
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -329,8 +330,8 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 		int protocol = iph->protocol;
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
-		if (ipprot && ipprot->early_demux) {
-			ipprot->early_demux(skb);
+		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
+			edemux(skb);
 			/* must reload iph, skb->head might have changed */
 			iph = ip_hdr(skb);
 		}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 737ce826d7ec..7a3fd25e8913 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk,
 	cork->length += length;
 	if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ebd953bc5607..ec4fe3d4b5c9 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -330,7 +330,6 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
    sent to multicast group to reach destination designated router.
  */
 struct ip_ra_chain __rcu *ip_ra_chain;
-static DEFINE_SPINLOCK(ip_ra_lock);
 
 
 static void ip_ra_destroy_rcu(struct rcu_head *head)
@@ -352,21 +351,17 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 
 	new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
-	spin_lock_bh(&ip_ra_lock);
 	for (rap = &ip_ra_chain;
-	     (ra = rcu_dereference_protected(*rap,
-			lockdep_is_held(&ip_ra_lock))) != NULL;
+	     (ra = rtnl_dereference(*rap)) != NULL;
 	     rap = &ra->next) {
 		if (ra->sk == sk) {
 			if (on) {
-				spin_unlock_bh(&ip_ra_lock);
 				kfree(new_ra);
 				return -EADDRINUSE;
 			}
 			/* dont let ip_call_ra_chain() use sk again */
 			ra->sk = NULL;
 			RCU_INIT_POINTER(*rap, ra->next);
-			spin_unlock_bh(&ip_ra_lock);
 
 			if (ra->destructor)
 				ra->destructor(sk);
@@ -380,17 +375,14 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 			return 0;
 		}
 	}
-	if (!new_ra) {
-		spin_unlock_bh(&ip_ra_lock);
+	if (!new_ra)
 		return -ENOBUFS;
-	}
 	new_ra->sk = sk;
 	new_ra->destructor = destructor;
 
 	RCU_INIT_POINTER(new_ra->next, ra);
 	rcu_assign_pointer(*rap, new_ra);
 	sock_hold(sk);
-	spin_unlock_bh(&ip_ra_lock);
 
 	return 0;
 }
@@ -488,16 +480,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
 		return false;
 
 	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
-	 * timestamp with egress dev. Not possible for packets without dev
+	 * timestamp with egress dev. Not possible for packets without iif
 	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
 	 */
-	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
-	    (!skb->dev))
+	info = PKTINFO_SKB_CB(skb);
+	if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+	    !info->ipi_ifindex)
 		return false;
 
-	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
-	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
 }
 
@@ -591,6 +582,7 @@ static bool setsockopt_needs_rtnl(int optname)
 	case MCAST_LEAVE_GROUP:
 	case MCAST_LEAVE_SOURCE_GROUP:
 	case MCAST_UNBLOCK_SOURCE:
+	case IP_ROUTER_ALERT:
 		return true;
 	}
 	return false;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 823abaef006b..b878ecbc0608 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -293,7 +293,8 @@ failed:
 static inline void init_tunnel_flow(struct flowi4 *fl4,
 				    int proto,
 				    __be32 daddr, __be32 saddr,
-				    __be32 key, __u8 tos, int oif)
+				    __be32 key, __u8 tos, int oif,
+				    __u32 mark)
 {
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_oif = oif;
@@ -302,6 +303,7 @@ static inline void init_tunnel_flow(struct flowi4 *fl4,
 	fl4->flowi4_tos = tos;
 	fl4->flowi4_proto = proto;
 	fl4->fl4_gre_key = key;
+	fl4->flowi4_mark = mark;
 }
 
 static int ip_tunnel_bind_dev(struct net_device *dev)
@@ -322,7 +324,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
 				 iph->saddr, tunnel->parms.o_key,
-				 RT_TOS(iph->tos), tunnel->parms.link);
+				 RT_TOS(iph->tos), tunnel->parms.link,
+				 tunnel->fwmark);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -578,7 +581,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 	}
 	init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
-			 RT_TOS(tos), tunnel->parms.link);
+			 RT_TOS(tos), tunnel->parms.link, tunnel->fwmark);
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 	rt = ip_route_output_key(tunnel->net, &fl4);
@@ -707,7 +710,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
-			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
+			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+			 tunnel->fwmark);
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
 		goto tx_error;
@@ -795,7 +799,8 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 			     struct ip_tunnel *t,
 			     struct net_device *dev,
 			     struct ip_tunnel_parm *p,
-			     bool set_mtu)
+			     bool set_mtu,
+			     __u32 fwmark)
 {
 	ip_tunnel_del(itn, t);
 	t->parms.iph.saddr = p->iph.saddr;
@@ -812,10 +817,11 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 	t->parms.iph.tos = p->iph.tos;
 	t->parms.iph.frag_off = p->iph.frag_off;
 
-	if (t->parms.link != p->link) {
+	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		int mtu;
 
 		t->parms.link = p->link;
+		t->fwmark = fwmark;
 		mtu = ip_tunnel_bind_dev(dev);
 		if (set_mtu)
 			dev->mtu = mtu;
@@ -893,7 +899,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 
 		if (t) {
 			err = 0;
-			ip_tunnel_update(itn, t, dev, p, true);
+			ip_tunnel_update(itn, t, dev, p, true, 0);
 		} else {
 			err = -ENOENT;
 		}
@@ -1066,7 +1072,7 @@ void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
 EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
 
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
-		      struct ip_tunnel_parm *p)
+		      struct ip_tunnel_parm *p, __u32 fwmark)
 {
 	struct ip_tunnel *nt;
 	struct net *net = dev_net(dev);
@@ -1087,6 +1093,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	nt->net = net;
 	nt->parms = *p;
+	nt->fwmark = fwmark;
 	err = register_netdevice(dev);
 	if (err)
 		goto out;
@@ -1105,7 +1112,7 @@ out:
 EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
 
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
-			 struct ip_tunnel_parm *p)
+			 struct ip_tunnel_parm *p, __u32 fwmark)
 {
 	struct ip_tunnel *t;
 	struct ip_tunnel *tunnel = netdev_priv(dev);
@@ -1137,7 +1144,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
-	ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU]);
+	ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_changelink);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index a31f47ccaad9..baf196eaf1d8 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -235,7 +235,7 @@ static int ip_tun_build_state(struct nlattr *attr,
 	struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy);
+	err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -332,7 +332,8 @@ static int ip6_tun_build_state(struct nlattr *attr,
 	struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy);
+	err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 8b14f1404c8f..40977413fd48 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -471,7 +471,8 @@ static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
 }
 
 static void vti_netlink_parms(struct nlattr *data[],
-			      struct ip_tunnel_parm *parms)
+			      struct ip_tunnel_parm *parms,
+			      __u32 *fwmark)
 {
 	memset(parms, 0, sizeof(*parms));
 
@@ -497,24 +498,29 @@ static void vti_netlink_parms(struct nlattr *data[],
 	if (data[IFLA_VTI_REMOTE])
 		parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]);
 
+	if (data[IFLA_VTI_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
 }
 
 static int vti_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct ip_tunnel_parm parms;
+	__u32 fwmark = 0;
 
-	vti_netlink_parms(data, &parms);
-	return ip_tunnel_newlink(dev, tb, &parms);
+	vti_netlink_parms(data, &parms, &fwmark);
+	return ip_tunnel_newlink(dev, tb, &parms, fwmark);
 }
 
 static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
 			  struct nlattr *data[])
 {
+	struct ip_tunnel *t = netdev_priv(dev);
+	__u32 fwmark = t->fwmark;
 	struct ip_tunnel_parm p;
 
-	vti_netlink_parms(data, &p);
-	return ip_tunnel_changelink(dev, tb, &p);
+	vti_netlink_parms(data, &p, &fwmark);
+	return ip_tunnel_changelink(dev, tb, &p, fwmark);
 }
 
 static size_t vti_get_size(const struct net_device *dev)
@@ -530,6 +536,8 @@ static size_t vti_get_size(const struct net_device *dev)
 		nla_total_size(4) +
 		/* IFLA_VTI_REMOTE */
 		nla_total_size(4) +
+		/* IFLA_VTI_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -543,6 +551,7 @@ static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key);
 	nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr);
 	nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr);
+	nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark);
 
 	return 0;
 }
@@ -553,6 +562,7 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
 	[IFLA_VTI_OKEY]		= { .type = NLA_U32 },
 	[IFLA_VTI_LOCAL]	= { .len = FIELD_SIZEOF(struct iphdr, saddr) },
 	[IFLA_VTI_REMOTE]	= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+	[IFLA_VTI_FWMARK]	= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops vti_link_ops __read_mostly = {
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index fd9f34bbd740..c3b12b1c7162 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -57,6 +57,7 @@
 #include <linux/export.h>
 #include <net/net_namespace.h>
 #include <net/arp.h>
+#include <net/dsa.h>
 #include <net/ip.h>
 #include <net/ipconfig.h>
 #include <net/route.h>
@@ -306,7 +307,7 @@ static void __init ic_close_devs(void)
 	while ((d = next)) {
 		next = d->next;
 		dev = d->dev;
-		if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) {
+		if (d != ic_dev && !netdev_uses_dsa(dev)) {
 			pr_debug("IP-Config: Downing %s\n", dev->name);
 			dev_change_flags(dev, d->flags);
 		}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 00d4229b6954..1e441c6f2160 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -390,7 +390,8 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
 }
 
 static void ipip_netlink_parms(struct nlattr *data[],
-			       struct ip_tunnel_parm *parms, bool *collect_md)
+			       struct ip_tunnel_parm *parms, bool *collect_md,
+			       __u32 *fwmark)
 {
 	memset(parms, 0, sizeof(*parms));
 
@@ -428,6 +429,9 @@ static void ipip_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_COLLECT_METADATA])
 		*collect_md = true;
+
+	if (data[IFLA_IPTUN_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
 /* This function returns true when ENCAP attributes are present in the nl msg */
@@ -470,6 +474,7 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev,
 	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	__u32 fwmark = 0;
 
 	if (ipip_netlink_encap_parms(data, &ipencap)) {
 		int err = ip_tunnel_encap_setup(t, &ipencap);
@@ -478,26 +483,27 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	ipip_netlink_parms(data, &p, &t->collect_md);
-	return ip_tunnel_newlink(dev, tb, &p);
+	ipip_netlink_parms(data, &p, &t->collect_md, &fwmark);
+	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
 static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
 			   struct nlattr *data[])
 {
+	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
 	bool collect_md;
+	__u32 fwmark = t->fwmark;
 
 	if (ipip_netlink_encap_parms(data, &ipencap)) {
-		struct ip_tunnel *t = netdev_priv(dev);
 		int err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	ipip_netlink_parms(data, &p, &collect_md);
+	ipip_netlink_parms(data, &p, &collect_md, &fwmark);
 	if (collect_md)
 		return -EINVAL;
 
@@ -505,7 +511,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
 	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
 		return -EINVAL;
 
-	return ip_tunnel_changelink(dev, tb, &p);
+	return ip_tunnel_changelink(dev, tb, &p, fwmark);
 }
 
 static size_t ipip_get_size(const struct net_device *dev)
@@ -535,6 +541,8 @@ static size_t ipip_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_IPTUN_COLLECT_METADATA */
 		nla_total_size(0) +
+		/* IFLA_IPTUN_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -550,7 +558,8 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
-		       !!(parm->iph.frag_off & htons(IP_DF))))
+		       !!(parm->iph.frag_off & htons(IP_DF))) ||
+	    nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
@@ -585,6 +594,7 @@ static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_COLLECT_METADATA]	= { .type = NLA_FLAG },
+	[IFLA_IPTUN_FWMARK]		= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops ipip_link_ops __read_mostly = {
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c0317c940bcd..3a02d52ed50e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -631,7 +631,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev) {
 		IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--;
-		inet_netconf_notify_devconf(dev_net(dev),
+		inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					    NETCONFA_MC_FORWARDING,
 					    dev->ifindex, &in_dev->cnf);
 		ip_rt_multicast_event(in_dev);
@@ -820,8 +820,8 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		return -EADDRNOTAVAIL;
 	}
 	IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++;
-	inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex,
-				    &in_dev->cnf);
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING,
+				    dev->ifindex, &in_dev->cnf);
 	ip_rt_multicast_event(in_dev);
 
 	/* Fill in the VIF structures */
@@ -1278,18 +1278,18 @@ static void mrtsock_destruct(struct sock *sk)
 	struct net *net = sock_net(sk);
 	struct mr_table *mrt;
 
-	rtnl_lock();
+	ASSERT_RTNL();
 	ipmr_for_each_table(mrt, net) {
 		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
-			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_MC_FORWARDING,
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
 			mroute_clean_tables(mrt, false);
 		}
 	}
-	rtnl_unlock();
 }
 
 /* Socket options and virtual interface manipulation. The whole
@@ -1344,7 +1344,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 		if (ret == 0) {
 			rcu_assign_pointer(mrt->mroute_sk, sk);
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
-			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_MC_FORWARDING,
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 		}
@@ -1353,13 +1354,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 		if (sk != rcu_access_pointer(mrt->mroute_sk)) {
 			ret = -EACCES;
 		} else {
-			/* We need to unlock here because mrtsock_destruct takes
-			 * care of rtnl itself and we can't change that due to
-			 * the IP_ROUTER_ALERT setsockopt which runs without it.
-			 */
-			rtnl_unlock();
 			ret = ip_ra_control(sk, 0, NULL);
-			goto out;
+			goto out_unlock;
 		}
 		break;
 	case MRT_ADD_VIF:
@@ -1470,7 +1466,6 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 	}
 out_unlock:
 	rtnl_unlock();
-out:
 	return ret;
 }
 
@@ -2428,7 +2423,8 @@ static int ipmr_nla_get_ttls(const struct nlattr *nla, struct mfcctl *mfcc)
 /* returns < 0 on error, 0 for ADD_MFC and 1 for ADD_MFC_PROXY */
 static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 			    struct mfcctl *mfcc, int *mrtsock,
-			    struct mr_table **mrtret)
+			    struct mr_table **mrtret,
+			    struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = NULL;
 	u32 tblid = RT_TABLE_DEFAULT;
@@ -2437,7 +2433,8 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 	struct rtmsg *rtm;
 	int ret, rem;
 
-	ret = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy);
+	ret = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy,
+			     extack);
 	if (ret < 0)
 		goto out;
 	rtm = nlmsg_data(nlh);
@@ -2496,7 +2493,8 @@ out:
 }
 
 /* takes care of both newroute and delroute */
-static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	int ret, mrtsock, parent;
@@ -2505,7 +2503,7 @@ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	mrtsock = 0;
 	tbl = NULL;
-	ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl);
+	ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl, extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6241a81fd7f5..0bc3c3d73e61 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -309,8 +309,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 	 */
 	for (hook = 0; hook < NF_ARP_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
-		struct arpt_entry *e
-			= (struct arpt_entry *)(entry0 + pos);
+		struct arpt_entry *e = entry0 + pos;
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
@@ -354,14 +353,12 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					if (pos == oldpos)
 						goto next;
 
-					e = (struct arpt_entry *)
-						(entry0 + pos);
+					e = entry0 + pos;
 				} while (oldpos == pos + e->next_offset);
 
 				/* Move along one */
 				size = e->next_offset;
-				e = (struct arpt_entry *)
-					(entry0 + pos + size);
+				e = entry0 + pos + size;
 				if (pos + size >= newinfo->size)
 					return 0;
 				e->counters.pcnt = pos;
@@ -376,16 +373,14 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					if (!xt_find_jump_offset(offsets, newpos,
 								 newinfo->number))
 						return 0;
-					e = (struct arpt_entry *)
-						(entry0 + newpos);
+					e = entry0 + newpos;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
 					if (newpos >= newinfo->size)
 						return 0;
 				}
-				e = (struct arpt_entry *)
-					(entry0 + newpos);
+				e = entry0 + newpos;
 				e->counters.pcnt = pos;
 				pos = newpos;
 			}
@@ -562,8 +557,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		    XT_ERROR_TARGET) == 0)
 			++newinfo->stacksize;
 	}
-	if (ret != 0)
-		goto out_free;
 
 	ret = -EINVAL;
 	if (i != repl->num_entries)
@@ -683,7 +676,7 @@ static int copy_entries_to_user(unsigned int total_size,
 	for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){
 		const struct xt_entry_target *t;
 
-		e = (struct arpt_entry *)(loc_cpu_entry + off);
+		e = loc_cpu_entry + off;
 		if (copy_to_user(userptr + off, e, sizeof(*e))) {
 			ret = -EFAULT;
 			goto free_counters;
@@ -1130,7 +1123,7 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 	int h;
 
 	origsize = *size;
-	de = (struct arpt_entry *)*dstptr;
+	de = *dstptr;
 	memcpy(de, e, sizeof(struct arpt_entry));
 	memcpy(&de->counters, &e->counters, sizeof(e->counters));
 
@@ -1324,7 +1317,7 @@ static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr,
 	int ret;
 
 	origsize = *size;
-	ce = (struct compat_arpt_entry __user *)*dstptr;
+	ce = *dstptr;
 	if (copy_to_user(ce, e, sizeof(struct arpt_entry)) != 0 ||
 	    copy_to_user(&ce->counters, &counters[i],
 	    sizeof(counters[i])) != 0)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 384b85713e06..2a55a40211cb 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -382,7 +382,7 @@ mark_source_chains(const struct xt_table_info *newinfo,
 	   to 0 as we leave), and comefrom to save source hook bitmask */
 	for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
-		struct ipt_entry *e = (struct ipt_entry *)(entry0 + pos);
+		struct ipt_entry *e = entry0 + pos;
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
@@ -424,14 +424,12 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					if (pos == oldpos)
 						goto next;
 
-					e = (struct ipt_entry *)
-						(entry0 + pos);
+					e = entry0 + pos;
 				} while (oldpos == pos + e->next_offset);
 
 				/* Move along one */
 				size = e->next_offset;
-				e = (struct ipt_entry *)
-					(entry0 + pos + size);
+				e = entry0 + pos + size;
 				if (pos + size >= newinfo->size)
 					return 0;
 				e->counters.pcnt = pos;
@@ -446,16 +444,14 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					if (!xt_find_jump_offset(offsets, newpos,
 								 newinfo->number))
 						return 0;
-					e = (struct ipt_entry *)
-						(entry0 + newpos);
+					e = entry0 + newpos;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
 					if (newpos >= newinfo->size)
 						return 0;
 				}
-				e = (struct ipt_entry *)
-					(entry0 + newpos);
+				e = entry0 + newpos;
 				e->counters.pcnt = pos;
 				pos = newpos;
 			}
@@ -834,7 +830,7 @@ copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_match *m;
 		const struct xt_entry_target *t;
 
-		e = (struct ipt_entry *)(loc_cpu_entry + off);
+		e = loc_cpu_entry + off;
 		if (copy_to_user(userptr + off, e, sizeof(*e))) {
 			ret = -EFAULT;
 			goto free_counters;
@@ -1229,7 +1225,7 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
 	int ret = 0;
 
 	origsize = *size;
-	ce = (struct compat_ipt_entry __user *)*dstptr;
+	ce = *dstptr;
 	if (copy_to_user(ce, e, sizeof(struct ipt_entry)) != 0 ||
 	    copy_to_user(&ce->counters, &counters[i],
 	    sizeof(counters[i])) != 0)
@@ -1366,7 +1362,7 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	struct xt_entry_match *ematch;
 
 	origsize = *size;
-	de = (struct ipt_entry *)*dstptr;
+	de = *dstptr;
 	memcpy(de, e, sizeof(struct ipt_entry));
 	memcpy(&de->counters, &e->counters, sizeof(e->counters));
 
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 52f26459efc3..038f293c2376 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -22,6 +22,7 @@
 #include <linux/icmp.h>
 #include <linux/if_arp.h>
 #include <linux/seq_file.h>
+#include <linux/refcount.h>
 #include <linux/netfilter_arp.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
@@ -40,8 +41,8 @@ MODULE_DESCRIPTION("Xtables: CLUSTERIP target");
 
 struct clusterip_config {
 	struct list_head list;			/* list of all configs */
-	atomic_t refcount;			/* reference count */
-	atomic_t entries;			/* number of entries/rules
+	refcount_t refcount;			/* reference count */
+	refcount_t entries;			/* number of entries/rules
 						 * referencing us */
 
 	__be32 clusterip;			/* the IP address */
@@ -77,7 +78,7 @@ struct clusterip_net {
 static inline void
 clusterip_config_get(struct clusterip_config *c)
 {
-	atomic_inc(&c->refcount);
+	refcount_inc(&c->refcount);
 }
 
 
@@ -89,7 +90,7 @@ static void clusterip_config_rcu_free(struct rcu_head *head)
 static inline void
 clusterip_config_put(struct clusterip_config *c)
 {
-	if (atomic_dec_and_test(&c->refcount))
+	if (refcount_dec_and_test(&c->refcount))
 		call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
 }
 
@@ -103,7 +104,7 @@ clusterip_config_entry_put(struct clusterip_config *c)
 	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
 
 	local_bh_disable();
-	if (atomic_dec_and_lock(&c->entries, &cn->lock)) {
+	if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
 		list_del_rcu(&c->list);
 		spin_unlock(&cn->lock);
 		local_bh_enable();
@@ -149,10 +150,10 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 			c = NULL;
 		else
 #endif
-		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
+		if (unlikely(!refcount_inc_not_zero(&c->refcount)))
 			c = NULL;
 		else if (entry)
-			atomic_inc(&c->entries);
+			refcount_inc(&c->entries);
 	}
 	rcu_read_unlock_bh();
 
@@ -188,8 +189,8 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 	clusterip_config_init_nodelist(c, i);
 	c->hash_mode = i->hash_mode;
 	c->hash_initval = i->hash_initval;
-	atomic_set(&c->refcount, 1);
-	atomic_set(&c->entries, 1);
+	refcount_set(&c->refcount, 1);
+	refcount_set(&c->entries, 1);
 
 	spin_lock_bh(&cn->lock);
 	if (__clusterip_config_find(net, ip)) {
@@ -461,7 +462,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par)
 
 	clusterip_config_put(cipinfo->config);
 
-	nf_ct_netns_get(par->net, par->family);
+	nf_ct_netns_put(par->net, par->family);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 3240a2614e82..af2b69b6895f 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -293,12 +293,16 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 					  XT_SYNPROXY_OPT_ECN);
 
 		synproxy_send_client_synack(net, skb, th, &opts);
-		return NF_DROP;
-
+		consume_skb(skb);
+		return NF_STOLEN;
 	} else if (th->ack && !(th->fin || th->rst || th->syn)) {
 		/* ACK from client */
-		synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq));
-		return NF_DROP;
+		if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq))) {
+			consume_skb(skb);
+			return NF_STOLEN;
+		} else {
+			return NF_DROP;
+		}
 	}
 
 	return XT_CONTINUE;
@@ -367,10 +371,13 @@ static unsigned int ipv4_synproxy_hook(void *priv,
 			 * number match the one of first SYN.
 			 */
 			if (synproxy_recv_client_ack(net, skb, th, &opts,
-						     ntohl(th->seq) + 1))
+						     ntohl(th->seq) + 1)) {
 				this_cpu_inc(snet->stats->cookie_retrans);
-
-			return NF_DROP;
+				consume_skb(skb);
+				return NF_STOLEN;
+			} else {
+				return NF_DROP;
+			}
 		}
 
 		synproxy->isn = ntohl(th->ack_seq);
@@ -409,19 +416,56 @@ static unsigned int ipv4_synproxy_hook(void *priv,
 	return NF_ACCEPT;
 }
 
+static struct nf_hook_ops ipv4_synproxy_ops[] __read_mostly = {
+	{
+		.hook		= ipv4_synproxy_hook,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
+	},
+	{
+		.hook		= ipv4_synproxy_hook,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
+	},
+};
+
 static int synproxy_tg4_check(const struct xt_tgchk_param *par)
 {
+	struct synproxy_net *snet = synproxy_pernet(par->net);
 	const struct ipt_entry *e = par->entryinfo;
+	int err;
 
 	if (e->ip.proto != IPPROTO_TCP ||
 	    e->ip.invflags & XT_INV_PROTO)
 		return -EINVAL;
 
-	return nf_ct_netns_get(par->net, par->family);
+	err = nf_ct_netns_get(par->net, par->family);
+	if (err)
+		return err;
+
+	if (snet->hook_ref4 == 0) {
+		err = nf_register_net_hooks(par->net, ipv4_synproxy_ops,
+					    ARRAY_SIZE(ipv4_synproxy_ops));
+		if (err) {
+			nf_ct_netns_put(par->net, par->family);
+			return err;
+		}
+	}
+
+	snet->hook_ref4++;
+	return err;
 }
 
 static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par)
 {
+	struct synproxy_net *snet = synproxy_pernet(par->net);
+
+	snet->hook_ref4--;
+	if (snet->hook_ref4 == 0)
+		nf_unregister_net_hooks(par->net, ipv4_synproxy_ops,
+					ARRAY_SIZE(ipv4_synproxy_ops));
 	nf_ct_netns_put(par->net, par->family);
 }
 
@@ -436,46 +480,14 @@ static struct xt_target synproxy_tg4_reg __read_mostly = {
 	.me		= THIS_MODULE,
 };
 
-static struct nf_hook_ops ipv4_synproxy_ops[] __read_mostly = {
-	{
-		.hook		= ipv4_synproxy_hook,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
-	},
-	{
-		.hook		= ipv4_synproxy_hook,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
-	},
-};
-
 static int __init synproxy_tg4_init(void)
 {
-	int err;
-
-	err = nf_register_hooks(ipv4_synproxy_ops,
-				ARRAY_SIZE(ipv4_synproxy_ops));
-	if (err < 0)
-		goto err1;
-
-	err = xt_register_target(&synproxy_tg4_reg);
-	if (err < 0)
-		goto err2;
-
-	return 0;
-
-err2:
-	nf_unregister_hooks(ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops));
-err1:
-	return err;
+	return xt_register_target(&synproxy_tg4_reg);
 }
 
 static void __exit synproxy_tg4_exit(void)
 {
 	xt_unregister_target(&synproxy_tg4_reg);
-	nf_unregister_hooks(ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops));
 }
 
 module_init(synproxy_tg4_init);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index bc1486f2c064..2e14ed11a35c 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -165,6 +165,10 @@ static unsigned int ipv4_conntrack_local(void *priv,
 	if (skb->len < sizeof(struct iphdr) ||
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
+
+	if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+		return NF_ACCEPT;
+
 	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
 }
 
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index f0dbff05fc28..39895b9ddeb9 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -69,8 +69,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	/* Avoid counting cloned packets towards the original connection. */
 	nf_reset(skb);
-	nf_ct_set(skb, nf_ct_untracked_get(), IP_CT_NEW);
-	nf_conntrack_get(skb_nfct(skb));
+	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 #endif
 	/*
 	 * If we are in PREROUTING/INPUT, decrease the TTL to mitigate potential
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index f8aad03d674b..feedd759ca80 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -255,11 +255,6 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 	/* maniptype == SRC for postrouting. */
 	enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
 
-	/* We never see fragments: conntrack defrags on pre-routing
-	 * and local-out, and nf_nat_out protects post-routing.
-	 */
-	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
 	ct = nf_ct_get(skb, &ctinfo);
 	/* Can't track?  It's not due to stress, or conntrack would
 	 * have dropped it.  Hence it's the user's responsibilty to
@@ -269,13 +264,7 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 	if (!ct)
 		return NF_ACCEPT;
 
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
+	nat = nfct_nat(ct);
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index ea91058b5f6f..dc1dea15c1b4 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -37,7 +37,6 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 	NF_CT_ASSERT(hooknum == NF_INET_POST_ROUTING);
 
 	ct = nf_ct_get(skb, &ctinfo);
-	nat = nfct_nat(ct);
 
 	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
 			    ctinfo == IP_CT_RELATED_REPLY));
@@ -56,7 +55,9 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 		return NF_DROP;
 	}
 
-	nat->masq_index = out->ifindex;
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat)
+		nat->masq_index = out->ifindex;
 
 	/* Transfer from original range. */
 	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index b3ca21b2ba9b..8a69363b4884 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -49,9 +49,14 @@ static void pptp_nat_expected(struct nf_conn *ct,
 	const struct nf_ct_pptp_master *ct_pptp_info;
 	const struct nf_nat_pptp *nat_pptp_info;
 	struct nf_nat_range range;
+	struct nf_conn_nat *nat;
 
+	nat = nf_ct_nat_ext_add(ct);
+	if (WARN_ON_ONCE(!nat))
+		return;
+
+	nat_pptp_info = &nat->help.nat_pptp_info;
 	ct_pptp_info = nfct_help_data(master);
-	nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info;
 
 	/* And here goes the grand finale of corrosion... */
 	if (exp->dir == IP_CT_DIR_ORIGINAL) {
@@ -120,13 +125,17 @@ pptp_outbound_pkt(struct sk_buff *skb,
 
 {
 	struct nf_ct_pptp_master *ct_pptp_info;
+	struct nf_conn_nat *nat = nfct_nat(ct);
 	struct nf_nat_pptp *nat_pptp_info;
 	u_int16_t msg;
 	__be16 new_callid;
 	unsigned int cid_off;
 
+	if (WARN_ON_ONCE(!nat))
+		return NF_DROP;
+
+	nat_pptp_info = &nat->help.nat_pptp_info;
 	ct_pptp_info = nfct_help_data(ct);
-	nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info;
 
 	new_callid = ct_pptp_info->pns_call_id;
 
@@ -177,11 +186,11 @@ pptp_outbound_pkt(struct sk_buff *skb,
 		 ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid));
 
 	/* mangle packet */
-	if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
-				     cid_off + sizeof(struct pptp_pkt_hdr) +
-				     sizeof(struct PptpControlHeader),
-				     sizeof(new_callid), (char *)&new_callid,
-				     sizeof(new_callid)) == 0)
+	if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
+				      cid_off + sizeof(struct pptp_pkt_hdr) +
+				      sizeof(struct PptpControlHeader),
+				      sizeof(new_callid), (char *)&new_callid,
+				      sizeof(new_callid)))
 		return NF_DROP;
 	return NF_ACCEPT;
 }
@@ -191,11 +200,15 @@ pptp_exp_gre(struct nf_conntrack_expect *expect_orig,
 	     struct nf_conntrack_expect *expect_reply)
 {
 	const struct nf_conn *ct = expect_orig->master;
+	struct nf_conn_nat *nat = nfct_nat(ct);
 	struct nf_ct_pptp_master *ct_pptp_info;
 	struct nf_nat_pptp *nat_pptp_info;
 
+	if (WARN_ON_ONCE(!nat))
+		return;
+
+	nat_pptp_info = &nat->help.nat_pptp_info;
 	ct_pptp_info = nfct_help_data(ct);
-	nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info;
 
 	/* save original PAC call ID in nat_info */
 	nat_pptp_info->pac_call_id = ct_pptp_info->pac_call_id;
@@ -223,11 +236,15 @@ pptp_inbound_pkt(struct sk_buff *skb,
 		 union pptp_ctrl_union *pptpReq)
 {
 	const struct nf_nat_pptp *nat_pptp_info;
+	struct nf_conn_nat *nat = nfct_nat(ct);
 	u_int16_t msg;
 	__be16 new_pcid;
 	unsigned int pcid_off;
 
-	nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info;
+	if (WARN_ON_ONCE(!nat))
+		return NF_DROP;
+
+	nat_pptp_info = &nat->help.nat_pptp_info;
 	new_pcid = nat_pptp_info->pns_call_id;
 
 	switch (msg = ntohs(ctlh->messageType)) {
@@ -271,11 +288,11 @@ pptp_inbound_pkt(struct sk_buff *skb,
 	pr_debug("altering peer call id from 0x%04x to 0x%04x\n",
 		 ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid));
 
-	if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
-				     pcid_off + sizeof(struct pptp_pkt_hdr) +
-				     sizeof(struct PptpControlHeader),
-				     sizeof(new_pcid), (char *)&new_pcid,
-				     sizeof(new_pcid)) == 0)
+	if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
+				      pcid_off + sizeof(struct pptp_pkt_hdr) +
+				      sizeof(struct PptpControlHeader),
+				      sizeof(new_pcid), (char *)&new_pcid,
+				      sizeof(new_pcid)))
 		return NF_DROP;
 	return NF_ACCEPT;
 }
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index c9b52c361da2..d5b1e0b3f687 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -827,8 +827,8 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx,
 	return 1;
 }
 
-static unsigned char snmp_request_decode(struct asn1_ctx *ctx,
-					 struct snmp_request *request)
+static unsigned char noinline_for_stack
+snmp_request_decode(struct asn1_ctx *ctx, struct snmp_request *request)
 {
 	unsigned int cls, con, tag;
 	unsigned char *end;
@@ -920,10 +920,10 @@ static inline void mangle_address(unsigned char *begin,
 	}
 }
 
-static unsigned char snmp_trap_decode(struct asn1_ctx *ctx,
-				      struct snmp_v1_trap *trap,
-				      const struct oct1_map *map,
-				      __sum16 *check)
+static unsigned char noinline_for_stack
+snmp_trap_decode(struct asn1_ctx *ctx, struct snmp_v1_trap *trap,
+		 const struct oct1_map *map,
+		 __sum16 *check)
 {
 	unsigned int cls, con, tag, len;
 	unsigned char *end;
@@ -998,18 +998,6 @@ err_id_free:
  *
  *****************************************************************************/
 
-static void hex_dump(const unsigned char *buf, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len; i++) {
-		if (i && !(i % 16))
-			printk("\n");
-		printk("%02x ", *(buf + i));
-	}
-	printk("\n");
-}
-
 /*
  * Parse and mangle SNMP message according to mapping.
  * (And this is the fucking 'basic' method).
@@ -1026,7 +1014,8 @@ static int snmp_parse_mangle(unsigned char *msg,
 	struct snmp_object *obj;
 
 	if (debug > 1)
-		hex_dump(msg, len);
+		print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 16, 1,
+			       msg, len, 0);
 
 	asn1_open(&ctx, msg, len);
 
@@ -1260,16 +1249,6 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = {
 	.timeout	= 180,
 };
 
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
-	.me			= THIS_MODULE,
-	.help			= help,
-	.expect_policy		= &snmp_exp_policy,
-	.name			= "snmp",
-	.tuple.src.l3num	= AF_INET,
-	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
-	.tuple.dst.protonum	= IPPROTO_UDP,
-};
-
 static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
 	.me			= THIS_MODULE,
 	.help			= help,
@@ -1288,22 +1267,16 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
 
 static int __init nf_nat_snmp_basic_init(void)
 {
-	int ret = 0;
-
 	BUG_ON(nf_nat_snmp_hook != NULL);
 	RCU_INIT_POINTER(nf_nat_snmp_hook, help);
 
-	ret = nf_conntrack_helper_register(&snmp_trap_helper);
-	if (ret < 0) {
-		nf_conntrack_helper_unregister(&snmp_helper);
-		return ret;
-	}
-	return ret;
+	return nf_conntrack_helper_register(&snmp_trap_helper);
 }
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
 	RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+	synchronize_rcu();
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 146d86105183..7cd8d0d918f8 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -104,7 +104,6 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
 void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 {
 	struct sk_buff *nskb;
-	const struct iphdr *oiph;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
 	struct tcphdr _oth;
@@ -116,8 +115,6 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
 		return;
 
-	oiph = ip_hdr(oldskb);
-
 	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
 			 LL_MAX_HEADER, GFP_ATOMIC);
 	if (!nskb)
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index a83d558e1aae..e9293bdebba0 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -139,7 +139,7 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
 	 * SNAT-ted connection.
 	 */
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct && !nf_ct_is_untracked(ct) &&
+	if (ct &&
 	    ((iph->protocol != IPPROTO_ICMP &&
 	      ctinfo == IP_CT_ESTABLISHED_REPLY) ||
 	     (iph->protocol == IPPROTO_ICMP &&
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 2981291910dd..de3681df2ce7 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -90,7 +90,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
 	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
-		nft_fib_store_result(dest, priv->result, pkt,
+		nft_fib_store_result(dest, priv, pkt,
 				     nft_in(pkt)->ifindex);
 		return;
 	}
@@ -99,7 +99,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (ipv4_is_zeronet(iph->saddr)) {
 		if (ipv4_is_lbcast(iph->daddr) ||
 		    ipv4_is_local_multicast(iph->daddr)) {
-			nft_fib_store_result(dest, priv->result, pkt,
+			nft_fib_store_result(dest, priv, pkt,
 					     get_ifindex(pkt->skb->dev));
 			return;
 		}
@@ -212,7 +212,7 @@ nft_fib4_select_ops(const struct nft_ctx *ctx,
 
 static struct nft_expr_type nft_fib4_type __read_mostly = {
 	.name		= "fib",
-	.select_ops	= &nft_fib4_select_ops,
+	.select_ops	= nft_fib4_select_ops,
 	.policy		= nft_fib_policy,
 	.maxattr	= NFTA_FIB_MAX,
 	.family		= NFPROTO_IPV4,
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index a0ea8aad1bf1..f18677277119 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -26,10 +26,10 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
 	memset(&range, 0, sizeof(range));
 	range.flags = priv->flags;
 	if (priv->sreg_proto_min) {
-		range.min_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min];
-		range.max_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 	}
 	regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
 						    &range, nft_out(pkt));
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index 1650ed23c15d..5120be1d3118 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -26,10 +26,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
 
 	memset(&mr, 0, sizeof(mr));
 	if (priv->sreg_proto_min) {
-		mr.range[0].min.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min];
-		mr.range[0].max.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		mr.range[0].min.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		mr.range[0].max.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2af6244b83e2..ccfbce13a633 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
 void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
+
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	write_lock_bh(&ping_table.lock);
 	if (sk_hashed(sk)) {
-		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
 		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-		write_unlock_bh(&ping_table.lock);
 	}
+	write_unlock_bh(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_unhash);
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 69cf49e8356d..fa44e752a9a3 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -199,7 +199,6 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED),
 	SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED),
 	SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
-	SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED),
 	SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
 	SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
 	SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS),
@@ -282,6 +281,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
 	SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
 	SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
+	SNMP_MIB_ITEM("TCPFastOpenBlackhole", LINUX_MIB_TCPFASTOPENBLACKHOLE),
 	SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
 	SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
 	SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING),
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 4b7c0ec65251..32a691b7ce2c 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -28,7 +28,7 @@
 #include <linux/spinlock.h>
 #include <net/protocol.h>
 
-const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
 const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
 EXPORT_SYMBOL(inet_offloads);
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8119e1f66e03..9d943974de2b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -682,7 +682,9 @@ static void raw_close(struct sock *sk, long timeout)
 	/*
 	 * Raw sockets may have direct kernel references. Kill them.
 	 */
+	rtnl_lock();
 	ip_ra_control(sk, 0, NULL);
+	rtnl_unlock();
 
 	sk_common_release(sk);
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8471dd116771..655d9eebe43e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1250,15 +1250,11 @@ static void set_class_tag(struct rtable *rt, u32 tag)
 
 static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 {
-	unsigned int advmss = dst_metric_raw(dst, RTAX_ADVMSS);
+	unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
+	unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size,
+				    ip_rt_min_advmss);
 
-	if (advmss == 0) {
-		advmss = max_t(unsigned int, dst->dev->mtu - 40,
-			       ip_rt_min_advmss);
-		if (advmss > 65535 - 40)
-			advmss = 65535 - 40;
-	}
-	return advmss;
+	return min(advmss, IPV4_MAX_PMTU - header_size);
 }
 
 static unsigned int ipv4_mtu(const struct dst_entry *dst)
@@ -1734,45 +1730,97 @@ out:
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-
 /* To make ICMP packets follow the right flow, the multipath hash is
- * calculated from the inner IP addresses in reverse order.
+ * calculated from the inner IP addresses.
  */
-static int ip_multipath_icmp_hash(struct sk_buff *skb)
+static void ip_multipath_l3_keys(const struct sk_buff *skb,
+				 struct flow_keys *hash_keys)
 {
 	const struct iphdr *outer_iph = ip_hdr(skb);
-	struct icmphdr _icmph;
+	const struct iphdr *inner_iph;
 	const struct icmphdr *icmph;
 	struct iphdr _inner_iph;
-	const struct iphdr *inner_iph;
+	struct icmphdr _icmph;
+
+	hash_keys->addrs.v4addrs.src = outer_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = outer_iph->daddr;
+	if (likely(outer_iph->protocol != IPPROTO_ICMP))
+		return;
 
 	if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
-		goto standard_hash;
+		return;
 
 	icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
 				   &_icmph);
 	if (!icmph)
-		goto standard_hash;
+		return;
 
 	if (icmph->type != ICMP_DEST_UNREACH &&
 	    icmph->type != ICMP_REDIRECT &&
 	    icmph->type != ICMP_TIME_EXCEEDED &&
-	    icmph->type != ICMP_PARAMETERPROB) {
-		goto standard_hash;
-	}
+	    icmph->type != ICMP_PARAMETERPROB)
+		return;
 
 	inner_iph = skb_header_pointer(skb,
 				       outer_iph->ihl * 4 + sizeof(_icmph),
 				       sizeof(_inner_iph), &_inner_iph);
 	if (!inner_iph)
-		goto standard_hash;
+		return;
+	hash_keys->addrs.v4addrs.src = inner_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = inner_iph->daddr;
+}
 
-	return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
+/* if skb is set it will be used and fl4 can be NULL */
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+		       const struct sk_buff *skb)
+{
+	struct net *net = fi->fib_net;
+	struct flow_keys hash_keys;
+	u32 mhash;
 
-standard_hash:
-	return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
-}
+	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+	case 0:
+		memset(&hash_keys, 0, sizeof(hash_keys));
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		if (skb) {
+			ip_multipath_l3_keys(skb, &hash_keys);
+		} else {
+			hash_keys.addrs.v4addrs.src = fl4->saddr;
+			hash_keys.addrs.v4addrs.dst = fl4->daddr;
+		}
+		break;
+	case 1:
+		/* skb is currently provided only when forwarding */
+		if (skb) {
+			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+			struct flow_keys keys;
+
+			/* short-circuit if we already have L4 hash present */
+			if (skb->l4_hash)
+				return skb_get_hash_raw(skb) >> 1;
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			skb_flow_dissect_flow_keys(skb, &keys, flag);
+			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+			hash_keys.ports.src = keys.ports.src;
+			hash_keys.ports.dst = keys.ports.dst;
+			hash_keys.basic.ip_proto = keys.basic.ip_proto;
+		} else {
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+			hash_keys.addrs.v4addrs.src = fl4->saddr;
+			hash_keys.addrs.v4addrs.dst = fl4->daddr;
+			hash_keys.ports.src = fl4->fl4_sport;
+			hash_keys.ports.dst = fl4->fl4_dport;
+			hash_keys.basic.ip_proto = fl4->flowi4_proto;
+		}
+		break;
+	}
+	mhash = flow_hash_from_keys(&hash_keys);
 
+	return mhash >> 1;
+}
+EXPORT_SYMBOL_GPL(fib_multipath_hash);
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
 static int ip_mkroute_input(struct sk_buff *skb,
@@ -1782,12 +1830,8 @@ static int ip_mkroute_input(struct sk_buff *skb,
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h;
+		int h = fib_multipath_hash(res->fi, NULL, skb);
 
-		if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP))
-			h = ip_multipath_icmp_hash(skb);
-		else
-			h = fib_multipath_hash(saddr, daddr);
 		fib_select_multipath(res, h);
 	}
 #endif
@@ -2203,7 +2247,7 @@ add:
  */
 
 struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
-					  int mp_hash)
+					  const struct sk_buff *skb)
 {
 	struct net_device *dev_out = NULL;
 	__u8 tos = RT_FL_TOS(fl4);
@@ -2359,13 +2403,14 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 		}
 
 		/* L3 master device is the loopback for that domain */
-		dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev;
+		dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
+			net->loopback_dev;
 		fl4->flowi4_oif = dev_out->ifindex;
 		flags |= RTCF_LOCAL;
 		goto make_route;
 	}
 
-	fib_select_path(net, &res, fl4, mp_hash);
+	fib_select_path(net, &res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(res);
 	fl4->flowi4_oif = dev_out->ifindex;
@@ -2585,7 +2630,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
+static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm;
@@ -2601,7 +2647,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	u32 table_id = RT_TABLE_MAIN;
 	kuid_t uid;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -2619,10 +2666,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
 
-	/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
-	ip_hdr(skb)->protocol = IPPROTO_ICMP;
-	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
-
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
 	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
@@ -2632,6 +2675,15 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	else
 		uid = (iif ? INVALID_UID : current_uid());
 
+	/* Bugfix: need to give ip_route_input enough of an IP header to
+	 * not gag.
+	 */
+	ip_hdr(skb)->protocol = IPPROTO_UDP;
+	ip_hdr(skb)->saddr = src;
+	ip_hdr(skb)->daddr = dst;
+
+	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
+
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
 	fl4.saddr = src;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d6880a6149ee..86957e9cd6c6 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -24,6 +24,7 @@
 #include <net/cipso_ipv4.h>
 #include <net/inet_frag.h>
 #include <net/ping.h>
+#include <net/protocol.h>
 
 static int zero;
 static int one = 1;
@@ -294,6 +295,74 @@ bad_key:
 	return ret;
 }
 
+static void proc_configure_early_demux(int enabled, int protocol)
+{
+	struct net_protocol *ipprot;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet6_protocol *ip6prot;
+#endif
+
+	rcu_read_lock();
+
+	ipprot = rcu_dereference(inet_protos[protocol]);
+	if (ipprot)
+		ipprot->early_demux = enabled ? ipprot->early_demux_handler :
+						NULL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	ip6prot = rcu_dereference(inet6_protos[protocol]);
+	if (ip6prot)
+		ip6prot->early_demux = enabled ? ip6prot->early_demux_handler :
+						 NULL;
+#endif
+	rcu_read_unlock();
+}
+
+static int proc_tcp_early_demux(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = 0;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (write && !ret) {
+		int enabled = init_net.ipv4.sysctl_tcp_early_demux;
+
+		proc_configure_early_demux(enabled, IPPROTO_TCP);
+	}
+
+	return ret;
+}
+
+static int proc_udp_early_demux(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = 0;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (write && !ret) {
+		int enabled = init_net.ipv4.sysctl_udp_early_demux;
+
+		proc_configure_early_demux(enabled, IPPROTO_UDP);
+	}
+
+	return ret;
+}
+
+static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
+					     int write,
+					     void __user *buffer,
+					     size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		tcp_fastopen_active_timeout_reset();
+	return ret;
+}
+
 static struct ctl_table ipv4_table[] = {
 	{
 		.procname	= "tcp_timestamps",
@@ -344,6 +413,14 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_tcp_fastopen_key,
 	},
 	{
+		.procname	= "tcp_fastopen_blackhole_timeout_sec",
+		.data		= &sysctl_tcp_fastopen_blackhole_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_tfo_blackhole_detect_timeout,
+		.extra1		= &zero,
+	},
+	{
 		.procname	= "tcp_abort_on_overflow",
 		.data		= &sysctl_tcp_abort_on_overflow,
 		.maxlen		= sizeof(int),
@@ -750,6 +827,20 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname       = "udp_early_demux",
+		.data           = &init_net.ipv4.sysctl_udp_early_demux,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_udp_early_demux
+	},
+	{
+		.procname       = "tcp_early_demux",
+		.data           = &init_net.ipv4.sysctl_tcp_early_demux,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_tcp_early_demux
+	},
+	{
 		.procname	= "ip_default_ttl",
 		.data		= &init_net.ipv4.sysctl_ip_default_ttl,
 		.maxlen		= sizeof(int),
@@ -981,13 +1072,6 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_tw_recycle",
-		.data		= &init_net.ipv4.tcp_death_row.sysctl_tw_recycle,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_max_syn_backlog",
 		.data		= &init_net.ipv4.sysctl_max_syn_backlog,
 		.maxlen		= sizeof(int),
@@ -1004,6 +1088,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+	{
+		.procname	= "fib_multipath_hash_policy",
+		.data		= &init_net.ipv4.sysctl_fib_multipath_hash_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif
 	{
 		.procname	= "ip_unprivileged_port_start",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf4555581282..1e4c76d2b827 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -533,7 +533,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
-	} else if (sk->sk_state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
 		/* Active TCP fastopen socket with defer_connect
 		 * Return POLLOUT so application can call write()
 		 * in order for kernel to generate SYN+data
@@ -2296,6 +2296,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_clear_xmit_timers(sk);
 	__skb_queue_purge(&sk->sk_receive_queue);
 	tcp_write_queue_purge(sk);
+	tcp_fastopen_active_disable_ofo_check(sk);
 	skb_rbtree_purge(&tp->out_of_order_queue);
 
 	inet->inet_dport = 0;
@@ -2322,6 +2323,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	tcp_saved_syn_free(tp);
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -2393,7 +2395,7 @@ static int tcp_repair_options_est(struct tcp_sock *tp,
 				u16 snd_wscale = opt.opt_val & 0xFFFF;
 				u16 rcv_wscale = opt.opt_val >> 16;
 
-				if (snd_wscale > 14 || rcv_wscale > 14)
+				if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE)
 					return -EFBIG;
 
 				tp->rx_opt.snd_wscale = snd_wscale;
@@ -2470,7 +2472,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		/* Values greater than interface MTU won't take effect. However
 		 * at the point when this call is done we typically don't yet
 		 * know which interface is going to be used */
-		if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
+		if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) {
 			err = -EINVAL;
 			break;
 		}
@@ -2770,7 +2772,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 {
 	const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 now = tcp_time_stamp, intv;
+	u32 now, intv;
 	u64 rate64;
 	bool slow;
 	u32 rate;
@@ -2839,6 +2841,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_retrans = tp->retrans_out;
 	info->tcpi_fackets = tp->fackets_out;
 
+	now = tcp_time_stamp;
 	info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
 	info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
 	info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
@@ -2850,7 +2853,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_snd_ssthresh = tp->snd_ssthresh;
 	info->tcpi_advmss = tp->advmss;
 
-	info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
+	info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3;
 	info->tcpi_rcv_space = tp->rcvq_space.space;
 
 	info->tcpi_total_retrans = tp->total_retrans;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 79c4817abc94..6e3c512054a6 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -168,12 +168,8 @@ void tcp_assign_congestion_control(struct sock *sk)
 	}
 out:
 	rcu_read_unlock();
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	/* Clear out private data before diag gets it and
-	 * the ca has not been initialized.
-	 */
-	if (ca->get_info)
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	if (ca->flags & TCP_CONG_NEEDS_ECN)
 		INET_ECN_xmit(sk);
 	else
@@ -200,11 +196,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
 	icsk->icsk_ca_setsockopt = 1;
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE) {
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	if (sk->sk_state != TCP_CLOSE)
 		tcp_init_congestion_control(sk);
-	}
 }
 
 /* Manage refcounts on socket close. */
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index c99230efcd52..0683ba447d77 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -72,7 +72,7 @@ MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness");
 module_param(hystart, int, 0644);
 MODULE_PARM_DESC(hystart, "turn on/off hybrid slow start algorithm");
 module_param(hystart_detect, int, 0644);
-MODULE_PARM_DESC(hystart_detect, "hyrbrid slow start detection mechanisms"
+MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms"
 		 " 1: packet-train 2: delay 3: both packet-train and delay");
 module_param(hystart_low_window, int, 0644);
 MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start");
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 8ea4e9787f82..4af82b914dd4 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -341,6 +341,13 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 		cookie->len = -1;
 		return false;
 	}
+
+	/* Firewall blackhole issue check */
+	if (tcp_fastopen_active_should_disable(sk)) {
+		cookie->len = -1;
+		return false;
+	}
+
 	if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
 		cookie->len = -1;
 		return true;
@@ -380,3 +387,98 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
 	return false;
 }
 EXPORT_SYMBOL(tcp_fastopen_defer_connect);
+
+/*
+ * The following code block is to deal with middle box issues with TFO:
+ * Middlebox firewall issues can potentially cause server's data being
+ * blackholed after a successful 3WHS using TFO.
+ * The proposed solution is to disable active TFO globally under the
+ * following circumstances:
+ *   1. client side TFO socket receives out of order FIN
+ *   2. client side TFO socket receives out of order RST
+ * We disable active side TFO globally for 1hr at first. Then if it
+ * happens again, we disable it for 2h, then 4h, 8h, ...
+ * And we reset the timeout back to 1hr when we see a successful active
+ * TFO connection with data exchanges.
+ */
+
+/* Default to 1hr */
+unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60;
+static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0);
+static unsigned long tfo_active_disable_stamp __read_mostly;
+
+/* Disable active TFO and record current jiffies and
+ * tfo_active_disable_times
+ */
+void tcp_fastopen_active_disable(struct sock *sk)
+{
+	atomic_inc(&tfo_active_disable_times);
+	tfo_active_disable_stamp = jiffies;
+	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE);
+}
+
+/* Reset tfo_active_disable_times to 0 */
+void tcp_fastopen_active_timeout_reset(void)
+{
+	atomic_set(&tfo_active_disable_times, 0);
+}
+
+/* Calculate timeout for tfo active disable
+ * Return true if we are still in the active TFO disable period
+ * Return false if timeout already expired and we should use active TFO
+ */
+bool tcp_fastopen_active_should_disable(struct sock *sk)
+{
+	int tfo_da_times = atomic_read(&tfo_active_disable_times);
+	int multiplier;
+	unsigned long timeout;
+
+	if (!tfo_da_times)
+		return false;
+
+	/* Limit timout to max: 2^6 * initial timeout */
+	multiplier = 1 << min(tfo_da_times - 1, 6);
+	timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ;
+	if (time_before(jiffies, tfo_active_disable_stamp + timeout))
+		return true;
+
+	/* Mark check bit so we can check for successful active TFO
+	 * condition and reset tfo_active_disable_times
+	 */
+	tcp_sk(sk)->syn_fastopen_ch = 1;
+	return false;
+}
+
+/* Disable active TFO if FIN is the only packet in the ofo queue
+ * and no data is received.
+ * Also check if we can reset tfo_active_disable_times if data is
+ * received successfully on a marked active TFO sockets opened on
+ * a non-loopback interface
+ */
+void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct rb_node *p;
+	struct sk_buff *skb;
+	struct dst_entry *dst;
+
+	if (!tp->syn_fastopen)
+		return;
+
+	if (!tp->data_segs_in) {
+		p = rb_first(&tp->out_of_order_queue);
+		if (p && !rb_next(p)) {
+			skb = rb_entry(p, struct sk_buff, rbnode);
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
+				tcp_fastopen_active_disable(sk);
+				return;
+			}
+		}
+	} else if (tp->syn_fastopen_ch &&
+		   atomic_read(&tfo_active_disable_times)) {
+		dst = sk_dst_get(sk);
+		if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
+			tcp_fastopen_active_timeout_reset();
+		dst_release(dst);
+	}
+}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 39c393cc0fd3..9739962bfb3f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -126,7 +126,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 #define REXMIT_LOST	1 /* retransmit packets marked lost */
 #define REXMIT_NEW	2 /* FRTO-style transmit of unsent/new packets */
 
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
+			     unsigned int len)
 {
 	static bool __once __read_mostly;
 
@@ -137,8 +138,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
 
 		rcu_read_lock();
 		dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
-		pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
-			dev ? dev->name : "Unknown driver");
+		if (!dev || len >= dev->mtu)
+			pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+				dev ? dev->name : "Unknown driver");
 		rcu_read_unlock();
 	}
 }
@@ -161,8 +163,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	if (len >= icsk->icsk_ack.rcv_mss) {
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
-		if (unlikely(icsk->icsk_ack.rcv_mss != len))
-			tcp_gro_dev_warn(sk, skb);
+		/* Account for possibly-removed options */
+		if (unlikely(len > icsk->icsk_ack.rcv_mss +
+				   MAX_TCP_OPTION_SPACE))
+			tcp_gro_dev_warn(sk, skb, len);
 	} else {
 		/* Otherwise, we make more careful check taking into account,
 		 * that SACKs block is variable.
@@ -438,7 +442,8 @@ void tcp_init_buffer_space(struct sock *sk)
 		tcp_sndbuf_expand(sk);
 
 	tp->rcvq_space.space = tp->rcv_wnd;
-	tp->rcvq_space.time = tcp_time_stamp;
+	skb_mstamp_get(&tp->tcp_mstamp);
+	tp->rcvq_space.time = tp->tcp_mstamp;
 	tp->rcvq_space.seq = tp->copied_seq;
 
 	maxwin = tcp_full_space(sk);
@@ -514,7 +519,7 @@ EXPORT_SYMBOL(tcp_initialize_rcv_mss);
  */
 static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 {
-	u32 new_sample = tp->rcv_rtt_est.rtt;
+	u32 new_sample = tp->rcv_rtt_est.rtt_us;
 	long m = sample;
 
 	if (m == 0)
@@ -544,21 +549,23 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 		new_sample = m << 3;
 	}
 
-	if (tp->rcv_rtt_est.rtt != new_sample)
-		tp->rcv_rtt_est.rtt = new_sample;
+	tp->rcv_rtt_est.rtt_us = new_sample;
 }
 
 static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
 {
-	if (tp->rcv_rtt_est.time == 0)
+	u32 delta_us;
+
+	if (tp->rcv_rtt_est.time.v64 == 0)
 		goto new_measure;
 	if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
 		return;
-	tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1);
+	delta_us = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcv_rtt_est.time);
+	tcp_rcv_rtt_update(tp, delta_us, 1);
 
 new_measure:
 	tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
-	tp->rcv_rtt_est.time = tcp_time_stamp;
+	tp->rcv_rtt_est.time = tp->tcp_mstamp;
 }
 
 static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
@@ -568,7 +575,10 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 	if (tp->rx_opt.rcv_tsecr &&
 	    (TCP_SKB_CB(skb)->end_seq -
 	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss))
-		tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0);
+		tcp_rcv_rtt_update(tp,
+				   jiffies_to_usecs(tcp_time_stamp -
+						    tp->rx_opt.rcv_tsecr),
+				   0);
 }
 
 /*
@@ -581,8 +591,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	int time;
 	int copied;
 
-	time = tcp_time_stamp - tp->rcvq_space.time;
-	if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0)
+	time = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcvq_space.time);
+	if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
 		return;
 
 	/* Number of bytes copied to user in last RTT */
@@ -638,7 +648,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 new_measure:
 	tp->rcvq_space.seq = tp->copied_seq;
-	tp->rcvq_space.time = tcp_time_stamp;
+	tp->rcvq_space.time = tp->tcp_mstamp;
 }
 
 /* There is something which you must keep in mind when you analyze the
@@ -874,22 +884,11 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 				  const int ts)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	if (metric > tp->reordering) {
-		int mib_idx;
+	int mib_idx;
 
+	if (metric > tp->reordering) {
 		tp->reordering = min(sysctl_tcp_max_reordering, metric);
 
-		/* This exciting event is worth to be remembered. 8) */
-		if (ts)
-			mib_idx = LINUX_MIB_TCPTSREORDER;
-		else if (tcp_is_reno(tp))
-			mib_idx = LINUX_MIB_TCPRENOREORDER;
-		else if (tcp_is_fack(tp))
-			mib_idx = LINUX_MIB_TCPFACKREORDER;
-		else
-			mib_idx = LINUX_MIB_TCPSACKREORDER;
-
-		NET_INC_STATS(sock_net(sk), mib_idx);
 #if FASTRETRANS_DEBUG > 1
 		pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
 			 tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
@@ -902,6 +901,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 	}
 
 	tp->rack.reord = 1;
+
+	/* This exciting event is worth to be remembered. 8) */
+	if (ts)
+		mib_idx = LINUX_MIB_TCPTSREORDER;
+	else if (tcp_is_reno(tp))
+		mib_idx = LINUX_MIB_TCPRENOREORDER;
+	else if (tcp_is_fack(tp))
+		mib_idx = LINUX_MIB_TCPFACKREORDER;
+	else
+		mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+	NET_INC_STATS(sock_net(sk), mib_idx);
 }
 
 /* This must be called before lost_out is incremented */
@@ -1126,7 +1137,6 @@ struct tcp_sacktag_state {
 	 */
 	struct skb_mstamp first_sackt;
 	struct skb_mstamp last_sackt;
-	struct skb_mstamp ack_time; /* Timestamp when the S/ACK was received */
 	struct rate_sample *rate;
 	int	flag;
 };
@@ -1209,8 +1219,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
 		return sacked;
 
 	if (!(sacked & TCPCB_SACKED_ACKED)) {
-		tcp_rack_advance(tp, sacked, end_seq,
-				 xmit_time, &state->ack_time);
+		tcp_rack_advance(tp, sacked, end_seq, xmit_time);
 
 		if (sacked & TCPCB_SACKED_RETRANS) {
 			/* If the segment is not tagged as lost,
@@ -1930,6 +1939,7 @@ void tcp_enter_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb;
+	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
 	bool mark_lost;
 
@@ -1989,15 +1999,18 @@ void tcp_enter_loss(struct sock *sk)
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
 
-	/* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
-	 * if a previous recovery is underway, otherwise it may incorrectly
-	 * call a timeout spurious if some previously retransmitted packets
-	 * are s/acked (sec 3.2). We do not apply that retriction since
-	 * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
-	 * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
-	 * on PTMU discovery to avoid sending new data.
+	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+	 * loss recovery is underway except recurring timeout(s) on
+	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
+	 *
+	 * In theory F-RTO can be used repeatedly during loss recovery.
+	 * In practice this interacts badly with broken middle-boxes that
+	 * falsely raise the receive window, which results in repeated
+	 * timeouts and stop-and-go behavior.
 	 */
-	tp->frto = sysctl_tcp_frto && !inet_csk(sk)->icsk_mtup.probe_size;
+	tp->frto = sysctl_tcp_frto &&
+		   (new_recovery || icsk->icsk_retransmits) &&
+		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
 
 /* If ACK arrived pointing to a remembered SACK, it means that our
@@ -2751,8 +2764,7 @@ static bool tcp_try_undo_partial(struct sock *sk, const int acked)
 	return false;
 }
 
-static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag,
-				   const struct skb_mstamp *ack_time)
+static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2760,7 +2772,7 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag,
 	if (sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
 		u32 prior_retrans = tp->retrans_out;
 
-		tcp_rack_mark_lost(sk, ack_time);
+		tcp_rack_mark_lost(sk);
 		if (prior_retrans > tp->retrans_out)
 			*ack_flag |= FLAG_LOST_RETRANS;
 	}
@@ -2779,8 +2791,7 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag,
  * tcp_xmit_retransmit_queue().
  */
 static void tcp_fastretrans_alert(struct sock *sk, const int acked,
-				  bool is_dupack, int *ack_flag, int *rexmit,
-				  const struct skb_mstamp *ack_time)
+				  bool is_dupack, int *ack_flag, int *rexmit)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2848,11 +2859,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 			tcp_try_keep_open(sk);
 			return;
 		}
-		tcp_rack_identify_loss(sk, ack_flag, ack_time);
+		tcp_rack_identify_loss(sk, ack_flag);
 		break;
 	case TCP_CA_Loss:
 		tcp_process_loss(sk, flag, is_dupack, rexmit);
-		tcp_rack_identify_loss(sk, ack_flag, ack_time);
+		tcp_rack_identify_loss(sk, ack_flag);
 		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
 		      (*ack_flag & FLAG_LOST_RETRANS)))
 			return;
@@ -2868,7 +2879,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
 			tcp_try_undo_dsack(sk);
 
-		tcp_rack_identify_loss(sk, ack_flag, ack_time);
+		tcp_rack_identify_loss(sk, ack_flag);
 		if (!tcp_time_to_recover(sk, flag)) {
 			tcp_try_to_open(sk, flag);
 			return;
@@ -3050,8 +3061,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct skb_mstamp first_ackt, last_ackt;
-	struct skb_mstamp *now = &sack->ack_time;
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct skb_mstamp *now = &tp->tcp_mstamp;
 	u32 prior_sacked = tp->sacked_out;
 	u32 reord = tp->packets_out;
 	bool fully_acked = true;
@@ -3111,8 +3122,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			tp->delivered += acked_pcount;
 			if (!tcp_skb_spurious_retrans(tp, skb))
 				tcp_rack_advance(tp, sacked, scb->end_seq,
-						 &skb->skb_mstamp,
-						 &sack->ack_time);
+						 &skb->skb_mstamp);
 		}
 		if (sacked & TCPCB_LOST)
 			tp->lost_out -= acked_pcount;
@@ -3567,8 +3577,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (after(ack, tp->snd_nxt))
 		goto invalid_ack;
 
-	skb_mstamp_get(&sack_state.ack_time);
-
 	if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
 
@@ -3638,8 +3646,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
-		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit,
-				      &sack_state.ack_time);
+		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
 	}
 	if (tp->tlp_high_seq)
 		tcp_process_tlp_ack(sk, ack, flag);
@@ -3651,8 +3658,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_schedule_loss_probe(sk);
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
-	tcp_rate_gen(sk, delivered, lost, &sack_state.ack_time,
-		     sack_state.rate);
+	tcp_rate_gen(sk, delivered, lost, sack_state.rate);
 	tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
 	tcp_xmit_recovery(sk, rexmit);
 	return 1;
@@ -3660,8 +3666,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
 	if (flag & FLAG_DSACKING_ACK)
-		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit,
-				      &sack_state.ack_time);
+		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
 	/* If this ack opens up a zero window, clear backoff.  It was
 	 * being used to time the probes, and is probably far higher than
 	 * it needs to be for normal retransmission.
@@ -3682,11 +3687,9 @@ old_ack:
 	 * If data was DSACKed, see if we can undo a cwnd reduction.
 	 */
 	if (TCP_SKB_CB(skb)->sacked) {
-		skb_mstamp_get(&sack_state.ack_time);
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 						&sack_state);
-		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit,
-				      &sack_state.ack_time);
+		tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
 		tcp_xmit_recovery(sk, rexmit);
 	}
 
@@ -3759,11 +3762,12 @@ void tcp_parse_options(const struct sk_buff *skb,
 				    !estab && sysctl_tcp_window_scaling) {
 					__u8 snd_wscale = *(__u8 *)ptr;
 					opt_rx->wscale_ok = 1;
-					if (snd_wscale > 14) {
-						net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n",
+					if (snd_wscale > TCP_MAX_WSCALE) {
+						net_info_ratelimited("%s: Illegal window scaling value %d > %u received\n",
 								     __func__,
-								     snd_wscale);
-						snd_wscale = 14;
+								     snd_wscale,
+								     TCP_MAX_WSCALE);
+						snd_wscale = TCP_MAX_WSCALE;
 					}
 					opt_rx->snd_wscale = snd_wscale;
 				}
@@ -3998,10 +4002,10 @@ void tcp_reset(struct sock *sk)
 	/* This barrier is coupled with smp_rmb() in tcp_poll() */
 	smp_wmb();
 
+	tcp_done(sk);
+
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_error_report(sk);
-
-	tcp_done(sk);
 }
 
 /*
@@ -5290,8 +5294,16 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 		if (rst_seq_match)
 			tcp_reset(sk);
-		else
+		else {
+			/* Disable TFO if RST is out-of-order
+			 * and no data has been received
+			 * for current active TFO socket
+			 */
+			if (tp->syn_fastopen && !tp->data_segs_in &&
+			    sk->sk_state == TCP_ESTABLISHED)
+				tcp_fastopen_active_disable(sk);
 			tcp_send_challenge_ack(sk, skb);
+		}
 		goto discard;
 	}
 
@@ -5344,6 +5356,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	skb_mstamp_get(&tp->tcp_mstamp);
 	if (unlikely(!sk->sk_rx_dst))
 		inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
 	/*
@@ -5541,6 +5554,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
+	icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5569,10 +5583,6 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	else
 		tp->pred_flags = 0;
 
-	if (!sock_flag(sk, SOCK_DEAD)) {
-		sk->sk_state_change(sk);
-		sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
-	}
 }
 
 static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
@@ -5641,6 +5651,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_cookie foc = { .len = -1 };
 	int saved_clamp = tp->rx_opt.mss_clamp;
+	bool fastopen_fail;
 
 	tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
 	if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
@@ -5744,10 +5755,15 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 
 		tcp_finish_connect(sk, skb);
 
-		if ((tp->syn_fastopen || tp->syn_data) &&
-		    tcp_rcv_fastopen_synack(sk, skb, &foc))
-			return -1;
+		fastopen_fail = (tp->syn_fastopen || tp->syn_data) &&
+				tcp_rcv_fastopen_synack(sk, skb, &foc);
 
+		if (!sock_flag(sk, SOCK_DEAD)) {
+			sk->sk_state_change(sk);
+			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
+		}
+		if (fastopen_fail)
+			return -1;
 		if (sk->sk_write_pending ||
 		    icsk->icsk_accept_queue.rskq_defer_accept ||
 		    icsk->icsk_ack.pingpong) {
@@ -5759,7 +5775,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 			tcp_enter_quickack_mode(sk);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
@@ -5902,6 +5917,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	case TCP_SYN_SENT:
 		tp->rx_opt.saw_tstamp = 0;
+		skb_mstamp_get(&tp->tcp_mstamp);
 		queued = tcp_rcv_synsent_state_process(sk, skb, th);
 		if (queued >= 0)
 			return queued;
@@ -5913,6 +5929,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		return 0;
 	}
 
+	skb_mstamp_get(&tp->tcp_mstamp);
 	tp->rx_opt.saw_tstamp = 0;
 	req = tp->fastopen_rsk;
 	if (req) {
@@ -6032,9 +6049,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			break;
 		}
 
-		if (tp->linger2 < 0 ||
-		    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
-		     after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
+		if (tp->linger2 < 0) {
+			tcp_done(sk);
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
+			return 1;
+		}
+		if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
+		    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
+			/* Receive out of order FIN after close() */
+			if (tp->syn_fastopen && th->fin)
+				tcp_fastopen_active_disable(sk);
 			tcp_done(sk);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
 			return 1;
@@ -6324,36 +6348,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		goto drop_and_free;
 
 	if (isn && tmp_opt.tstamp_ok)
-		af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+		af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
 
 	if (!want_cookie && !isn) {
-		/* VJ's idea. We save last timestamp seen
-		 * from the destination in peer table, when entering
-		 * state TIME-WAIT, and check against it before
-		 * accepting new connection request.
-		 *
-		 * If "isn" is not zero, this request hit alive
-		 * timewait bucket, so that all the necessary checks
-		 * are made in the function processing timewait state.
-		 */
-		if (net->ipv4.tcp_death_row.sysctl_tw_recycle) {
-			bool strict;
-
-			dst = af_ops->route_req(sk, &fl, req, &strict);
-
-			if (dst && strict &&
-			    !tcp_peer_is_proven(req, dst, true,
-						tmp_opt.saw_tstamp)) {
-				NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
-				goto drop_and_release;
-			}
-		}
 		/* Kill the following clause, if you dislike this way. */
-		else if (!net->ipv4.sysctl_tcp_syncookies &&
-			 (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
-			  (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
-			 !tcp_peer_is_proven(req, dst, false,
-					     tmp_opt.saw_tstamp)) {
+		if (!net->ipv4.sysctl_tcp_syncookies &&
+		    (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+		     (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
+		    !tcp_peer_is_proven(req, dst)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.
@@ -6366,10 +6368,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_release;
 		}
 
-		isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+		isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
 	}
 	if (!dst) {
-		dst = af_ops->route_req(sk, &fl, req, NULL);
+		dst = af_ops->route_req(sk, &fl, req);
 		if (!dst)
 			goto drop_and_free;
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9a89b8deafae..cbbafe546c0f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -94,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
 {
-	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
-					  ip_hdr(skb)->saddr,
-					  tcp_hdr(skb)->dest,
-					  tcp_hdr(skb)->source, tsoff);
+	return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr,
+					ip_hdr(skb)->saddr,
+					tcp_hdr(skb)->dest,
+					tcp_hdr(skb)->source, tsoff);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 			tp->write_seq	   = 0;
 	}
 
-	if (tcp_death_row->sysctl_tw_recycle &&
-	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
-		tcp_fetch_timewait_stamp(sk, &rt->dst);
-
 	inet->inet_dport = usin->sin_port;
 	sk_daddr_set(sk, daddr);
 
@@ -236,11 +232,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = NULL;
 
 	if (likely(!tp->repair)) {
-		seq = secure_tcp_sequence_number(inet->inet_saddr,
-						 inet->inet_daddr,
-						 inet->inet_sport,
-						 usin->sin_port,
-						 &tp->tsoffset);
+		seq = secure_tcp_seq_and_tsoff(inet->inet_saddr,
+					       inet->inet_daddr,
+					       inet->inet_sport,
+					       usin->sin_port,
+					       &tp->tsoffset);
 		if (!tp->write_seq)
 			tp->write_seq = seq;
 	}
@@ -279,10 +275,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
@@ -428,7 +427,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
@@ -1213,19 +1213,9 @@ static void tcp_v4_init_req(struct request_sock *req,
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
 					  struct flowi *fl,
-					  const struct request_sock *req,
-					  bool *strict)
+					  const struct request_sock *req)
 {
-	struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req);
-
-	if (strict) {
-		if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr)
-			*strict = true;
-		else
-			*strict = false;
-	}
-
-	return dst;
+	return inet_csk_route_req(sk, &fl->u.ip4, req);
 }
 
 struct request_sock_ops tcp_request_sock_ops __read_mostly = {
@@ -1249,7 +1239,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.cookie_init_seq =	cookie_v4_init_sequence,
 #endif
 	.route_req	=	tcp_v4_route_req,
-	.init_seq	=	tcp_v4_init_sequence,
+	.init_seq_tsoff	=	tcp_v4_init_seq_and_tsoff,
 	.send_synack	=	tcp_v4_send_synack,
 };
 
@@ -1419,8 +1409,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 		if (!nsk)
 			goto discard;
 		if (nsk != sk) {
-			sock_rps_save_rxhash(nsk, skb);
-			sk_mark_napi_id(nsk, skb);
 			if (tcp_child_process(sk, nsk, skb)) {
 				rsk = nsk;
 				goto reset;
@@ -1867,6 +1855,9 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	/* Cleanup up the write buffer. */
 	tcp_write_queue_purge(sk);
 
+	/* Check if we want to disable active TFO */
+	tcp_fastopen_active_disable_ofo_check(sk);
+
 	/* Cleans up our, hopefully empty, out_of_order_queue. */
 	skb_rbtree_purge(&tp->out_of_order_queue);
 
@@ -2462,7 +2453,6 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_tw_reuse = 0;
 
 	cnt = tcp_hashinfo.ehash_mask + 1;
-	net->ipv4.tcp_death_row.sysctl_tw_recycle = 0;
 	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 046fd3910873..d6fb6c067af4 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -264,13 +264,15 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct lp *lp = inet_csk_ca(sk);
+	u32 delta;
 
 	if (sample->rtt_us > 0)
 		tcp_lp_rtt_sample(sk, sample->rtt_us);
 
 	/* calc inference */
-	if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
-		lp->inference = 3 * (tcp_time_stamp - tp->rx_opt.rcv_tsecr);
+	delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+	if ((s32)delta > 0)
+		lp->inference = 3 * delta;
 
 	/* test if within inference */
 	if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference))
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0f46e5fe31ad..9d0d4f39e42b 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -45,8 +45,6 @@ struct tcp_metrics_block {
 	struct inetpeer_addr		tcpm_saddr;
 	struct inetpeer_addr		tcpm_daddr;
 	unsigned long			tcpm_stamp;
-	u32				tcpm_ts;
-	u32				tcpm_ts_stamp;
 	u32				tcpm_lock;
 	u32				tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];
 	struct tcp_fastopen_metrics	tcpm_fastopen;
@@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
 	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
 	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
-	tm->tcpm_ts = 0;
-	tm->tcpm_ts_stamp = 0;
 	if (fastopen_clear) {
 		tm->tcpm_fastopen.mss = 0;
 		tm->tcpm_fastopen.syn_loss = 0;
@@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	return tm;
 }
 
-static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
-{
-	struct tcp_metrics_block *tm;
-	struct inetpeer_addr saddr, daddr;
-	unsigned int hash;
-	struct net *net;
-
-	if (tw->tw_family == AF_INET) {
-		inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
-		inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
-		hash = ipv4_addr_hash(tw->tw_daddr);
-	}
-#if IS_ENABLED(CONFIG_IPV6)
-	else if (tw->tw_family == AF_INET6) {
-		if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {
-			inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
-			inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
-			hash = ipv4_addr_hash(tw->tw_daddr);
-		} else {
-			inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr);
-			inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr);
-			hash = ipv6_addr_hash(&tw->tw_v6_daddr);
-		}
-	}
-#endif
-	else
-		return NULL;
-
-	net = twsk_net(tw);
-	hash ^= net_hash_mix(net);
-	hash = hash_32(hash, tcp_metrics_hash_log);
-
-	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
-	     tm = rcu_dereference(tm->tcpm_next)) {
-		if (addr_same(&tm->tcpm_saddr, &saddr) &&
-		    addr_same(&tm->tcpm_daddr, &daddr) &&
-		    net_eq(tm_net(tm), net))
-			break;
-	}
-	return tm;
-}
-
 static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 						 struct dst_entry *dst,
 						 bool create)
@@ -573,8 +527,7 @@ reset:
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 }
 
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
-			bool paws_check, bool timestamps)
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
 {
 	struct tcp_metrics_block *tm;
 	bool ret;
@@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
 
 	rcu_read_lock();
 	tm = __tcp_get_metrics_req(req, dst);
-	if (paws_check) {
-		if (tm &&
-		    (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&
-		    ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW ||
-		     !timestamps))
-			ret = false;
-		else
-			ret = true;
-	} else {
-		if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp)
-			ret = true;
-		else
-			ret = false;
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst)
-{
-	struct tcp_metrics_block *tm;
-
-	rcu_read_lock();
-	tm = tcp_get_metrics(sk, dst, true);
-	if (tm) {
-		struct tcp_sock *tp = tcp_sk(sk);
-
-		if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) {
-			tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp;
-			tp->rx_opt.ts_recent = tm->tcpm_ts;
-		}
-	}
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp);
-
-/* VJ's idea. Save last timestamp seen from this destination and hold
- * it at least for normal timewait interval to use for duplicate
- * segment detection in subsequent connections, before they enter
- * synchronized state.
- */
-bool tcp_remember_stamp(struct sock *sk)
-{
-	struct dst_entry *dst = __sk_dst_get(sk);
-	bool ret = false;
-
-	if (dst) {
-		struct tcp_metrics_block *tm;
-
-		rcu_read_lock();
-		tm = tcp_get_metrics(sk, dst, true);
-		if (tm) {
-			struct tcp_sock *tp = tcp_sk(sk);
-
-			if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 ||
-			    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
-			     tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
-				tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
-				tm->tcpm_ts = tp->rx_opt.ts_recent;
-			}
-			ret = true;
-		}
-		rcu_read_unlock();
-	}
-	return ret;
-}
-
-bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
-{
-	struct tcp_metrics_block *tm;
-	bool ret = false;
-
-	rcu_read_lock();
-	tm = __tcp_get_metrics_tw(tw);
-	if (tm) {
-		const struct tcp_timewait_sock *tcptw;
-		struct sock *sk = (struct sock *) tw;
-
-		tcptw = tcp_twsk(sk);
-		if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 ||
-		    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
-		     tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
-			tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
-			tm->tcpm_ts	   = tcptw->tw_ts_recent;
-		}
+	if (tm && tcp_metric_get(tm, TCP_METRIC_RTT))
 		ret = true;
-	}
+	else
+		ret = false;
 	rcu_read_unlock();
 
 	return ret;
@@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 			  jiffies - tm->tcpm_stamp,
 			  TCP_METRICS_ATTR_PAD) < 0)
 		goto nla_put_failure;
-	if (tm->tcpm_ts_stamp) {
-		if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP,
-				(s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0)
-			goto nla_put_failure;
-		if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL,
-				tm->tcpm_ts) < 0)
-			goto nla_put_failure;
-	}
 
 	{
 		int n = 0;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7e16243cdb58..8f6373b0cd77 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -26,6 +26,7 @@
 #include <net/tcp.h>
 #include <net/inet_common.h>
 #include <net/xfrm.h>
+#include <net/busy_poll.h>
 
 int sysctl_tcp_abort_on_overflow __read_mostly;
 
@@ -94,7 +95,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	struct tcp_options_received tmp_opt;
 	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 	bool paws_reject = false;
-	struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row;
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
@@ -149,12 +149,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
 		}
 
-		if (tcp_death_row->sysctl_tw_recycle &&
-		    tcptw->tw_ts_recent_stamp &&
-		    tcp_tw_remember_stamp(tw))
-			inet_twsk_reschedule(tw, tw->tw_timeout);
-		else
-			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
+		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		return TCP_TW_ACK;
 	}
 
@@ -259,12 +254,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_timewait_sock *tw;
-	bool recycle_ok = false;
 	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
-	if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
-		recycle_ok = tcp_remember_stamp(sk);
-
 	tw = inet_twsk_alloc(sk, tcp_death_row, state);
 
 	if (tw) {
@@ -317,13 +308,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		if (timeo < rto)
 			timeo = rto;
 
-		if (recycle_ok) {
-			tw->tw_timeout = rto;
-		} else {
-			tw->tw_timeout = TCP_TIMEWAIT_LEN;
-			if (state == TCP_TIME_WAIT)
-				timeo = TCP_TIMEWAIT_LEN;
-		}
+		tw->tw_timeout = TCP_TIMEWAIT_LEN;
+		if (state == TCP_TIME_WAIT)
+			timeo = TCP_TIMEWAIT_LEN;
 
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
@@ -460,6 +447,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+		newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
@@ -812,6 +800,9 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
+	/* record NAPI ID of child */
+	sk_mark_napi_id(child, skb);
+
 	tcp_segs_in(tcp_sk(child), skb);
 	if (!sock_owned_by_user(child)) {
 		ret = tcp_rcv_state_process(child, skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 22548b5f05cb..60111a0fc201 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -212,12 +212,12 @@ void tcp_select_initial_window(int __space, __u32 mss,
 
 	/* If no clamp set the clamp to the max possible scaled window */
 	if (*window_clamp == 0)
-		(*window_clamp) = (65535 << 14);
+		(*window_clamp) = (U16_MAX << TCP_MAX_WSCALE);
 	space = min(*window_clamp, space);
 
 	/* Quantize space offering to a multiple of mss if possible. */
 	if (space > mss)
-		space = (space / mss) * mss;
+		space = rounddown(space, mss);
 
 	/* NOTE: offering an initial window larger than 32767
 	 * will break some buggy TCP stacks. If the admin tells us
@@ -234,13 +234,11 @@ void tcp_select_initial_window(int __space, __u32 mss,
 
 	(*rcv_wscale) = 0;
 	if (wscale_ok) {
-		/* Set window scaling on max possible window
-		 * See RFC1323 for an explanation of the limit to 14
-		 */
+		/* Set window scaling on max possible window */
 		space = max_t(u32, space, sysctl_tcp_rmem[2]);
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
-		while (space > 65535 && (*rcv_wscale) < 14) {
+		while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) {
 			space >>= 1;
 			(*rcv_wscale)++;
 		}
@@ -253,7 +251,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
 	}
 
 	/* Set the clamp no higher than max representable value */
-	(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
+	(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
 }
 EXPORT_SYMBOL(tcp_select_initial_window);
 
@@ -1267,7 +1265,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
  * eventually). The difference is that pulled data not copied, but
  * immediately discarded.
  */
-static void __pskb_trim_head(struct sk_buff *skb, int len)
+static int __pskb_trim_head(struct sk_buff *skb, int len)
 {
 	struct skb_shared_info *shinfo;
 	int i, k, eat;
@@ -1277,7 +1275,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 		__skb_pull(skb, eat);
 		len -= eat;
 		if (!len)
-			return;
+			return 0;
 	}
 	eat = len;
 	k = 0;
@@ -1303,23 +1301,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	skb_reset_tail_pointer(skb);
 	skb->data_len -= len;
 	skb->len = skb->data_len;
+	return len;
 }
 
 /* Remove acked data from a packet in the transmit queue. */
 int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
+	u32 delta_truesize;
+
 	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
-	__pskb_trim_head(skb, len);
+	delta_truesize = __pskb_trim_head(skb, len);
 
 	TCP_SKB_CB(skb)->seq += len;
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
-	skb->truesize	     -= len;
-	sk->sk_wmem_queued   -= len;
-	sk_mem_uncharge(sk, len);
-	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	if (delta_truesize) {
+		skb->truesize	   -= delta_truesize;
+		sk->sk_wmem_queued -= delta_truesize;
+		sk_mem_uncharge(sk, delta_truesize);
+		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
 	if (tcp_skb_pcount(skb) > 1)
@@ -2561,7 +2564,6 @@ u32 __tcp_select_window(struct sock *sk)
 	/* Don't do rounding if we are using window scaling, since the
 	 * scaled window will not line up with the MSS boundary anyway.
 	 */
-	window = tp->rcv_wnd;
 	if (tp->rx_opt.rcv_wscale) {
 		window = free_space;
 
@@ -2569,10 +2571,9 @@ u32 __tcp_select_window(struct sock *sk)
 		 * Import case: prevent zero window announcement if
 		 * 1<<rcv_wscale > mss.
 		 */
-		if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window)
-			window = (((window >> tp->rx_opt.rcv_wscale) + 1)
-				  << tp->rx_opt.rcv_wscale);
+		window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale));
 	} else {
+		window = tp->rcv_wnd;
 		/* Get the largest window that is a nice multiple of mss.
 		 * Window clamp already applied above.
 		 * If our current window offering is within 1 mss of the
@@ -2582,7 +2583,7 @@ u32 __tcp_select_window(struct sock *sk)
 		 * is too small.
 		 */
 		if (window <= free_space - mss || window > free_space)
-			window = (free_space / mss) * mss;
+			window = rounddown(free_space, mss);
 		else if (mss == full_space &&
 			 free_space > window + (full_space >> 1))
 			window = free_space;
@@ -2999,6 +3000,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 {
 	struct sk_buff *skb;
 
+	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
+
 	/* NOTE: No TCP options attached and we never retransmit this. */
 	skb = alloc_skb(MAX_TCP_HEADER, priority);
 	if (!skb) {
@@ -3014,8 +3017,6 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-
-	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
 }
 
 /* Send a crossed SYN-ACK during socket establishment.
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 9be1581a5a08..c6a9fa894646 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 
 /* Update the connection delivery information and generate a rate sample. */
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct skb_mstamp *now, struct rate_sample *rs)
+		  struct rate_sample *rs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 snd_us, ack_us;
@@ -120,7 +120,7 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
 	 * to carry current time, flags, stats like "tcp_sacktag_state".
 	 */
 	if (delivered)
-		tp->delivered_mstamp = *now;
+		tp->delivered_mstamp = tp->tcp_mstamp;
 
 	rs->acked_sacked = delivered;	/* freshly ACKed or SACKed */
 	rs->losses = lost;		/* freshly marked lost */
@@ -138,7 +138,8 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
 	 * longer phase.
 	 */
 	snd_us = rs->interval_us;				/* send phase */
-	ack_us = skb_mstamp_us_delta(now, &rs->prior_mstamp);	/* ack phase */
+	ack_us = skb_mstamp_us_delta(&tp->tcp_mstamp,
+				     &rs->prior_mstamp); /* ack phase */
 	rs->interval_us = max(snd_us, ack_us);
 
 	/* Normally we expect interval_us >= min-rtt.
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 4ecb38ae8504..362b8c75bfab 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -12,7 +12,8 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 		/* Account for retransmits that are lost again */
 		TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
 		tp->retrans_out -= tcp_skb_pcount(skb);
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
+		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+			      tcp_skb_pcount(skb));
 	}
 }
 
@@ -44,8 +45,7 @@ static bool tcp_rack_sent_after(const struct skb_mstamp *t1,
  * or tcp_time_to_recover()'s "Trick#1: the loss is proven" code path will
  * make us enter the CA_Recovery state.
  */
-static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now,
-				 u32 *reo_timeout)
+static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
@@ -78,7 +78,7 @@ static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now,
 			 * A packet is lost if its elapsed time is beyond
 			 * the recent RTT plus the reordering window.
 			 */
-			u32 elapsed = skb_mstamp_us_delta(now,
+			u32 elapsed = skb_mstamp_us_delta(&tp->tcp_mstamp,
 							  &skb->skb_mstamp);
 			s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed;
 
@@ -104,7 +104,7 @@ static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now,
 	}
 }
 
-void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now)
+void tcp_rack_mark_lost(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 timeout;
@@ -114,7 +114,7 @@ void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now)
 
 	/* Reset the advanced flag to avoid unnecessary queue scanning */
 	tp->rack.advanced = 0;
-	tcp_rack_detect_loss(sk, now, &timeout);
+	tcp_rack_detect_loss(sk, &timeout);
 	if (timeout) {
 		timeout = usecs_to_jiffies(timeout + TCP_REO_TIMEOUT_MIN);
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
@@ -127,8 +127,7 @@ void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now)
  * draft-cheng-tcpm-rack-00.txt
  */
 void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
-		      const struct skb_mstamp *xmit_time,
-		      const struct skb_mstamp *ack_time)
+		      const struct skb_mstamp *xmit_time)
 {
 	u32 rtt_us;
 
@@ -137,7 +136,7 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
 				 end_seq, tp->rack.end_seq))
 		return;
 
-	rtt_us = skb_mstamp_us_delta(ack_time, xmit_time);
+	rtt_us = skb_mstamp_us_delta(&tp->tcp_mstamp, xmit_time);
 	if (sacked & TCPCB_RETRANS) {
 		/* If the sacked packet was retransmitted, it's ambiguous
 		 * whether the retransmission or the original (or the prior
@@ -164,12 +163,11 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
 void tcp_rack_reo_timeout(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct skb_mstamp now;
 	u32 timeout, prior_inflight;
 
-	skb_mstamp_get(&now);
 	prior_inflight = tcp_packets_in_flight(tp);
-	tcp_rack_detect_loss(sk, &now, &timeout);
+	skb_mstamp_get(&tp->tcp_mstamp);
+	tcp_rack_detect_loss(sk, &timeout);
 	if (prior_inflight != tcp_packets_in_flight(tp)) {
 		if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
 			tcp_enter_recovery(sk, false);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 40d893556e67..14672543cf0b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -201,11 +201,10 @@ static int tcp_write_timeout(struct sock *sk)
 		if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) {
 			/* Some middle-boxes may black-hole Fast Open _after_
 			 * the handshake. Therefore we conservatively disable
-			 * Fast Open on this path on recurring timeouts with
-			 * few or zero bytes acked after Fast Open.
+			 * Fast Open on this path on recurring timeouts after
+			 * successful Fast Open.
 			 */
-			if (tp->syn_data_acked &&
-			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+			if (tp->syn_data_acked) {
 				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
 				if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1)
 					NET_INC_STATS(sock_net(sk),
@@ -249,7 +248,8 @@ void tcp_delack_timer_handler(struct sock *sk)
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +552,8 @@ void tcp_write_timer_handler(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index fed66dc0e0f5..9775453b8d17 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -265,8 +265,8 @@ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr,
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
 		info->vegas.tcpv_enabled = 1;
 		info->vegas.tcpv_rttcnt	= 0;
-		info->vegas.tcpv_rtt	= jiffies_to_usecs(ca->rtt),
-		info->vegas.tcpv_minrtt	= jiffies_to_usecs(ca->rtt_min),
+		info->vegas.tcpv_rtt	= jiffies_to_usecs(ca->rtt);
+		info->vegas.tcpv_minrtt	= jiffies_to_usecs(ca->rtt_min);
 
 		*attr = INET_DIAG_VEGASINFO;
 		return sizeof(struct tcpvegas_info);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b2be1d9757ef..781250151d40 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	u16 mac_len = skb->mac_len;
 	int udp_offset, outer_hlen;
 	__wsum partial;
+	bool need_ipsec;
 
 	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
 		goto out;
@@ -62,8 +63,10 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 
 	ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
 
+	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
 	/* Try to offload checksum if possible */
 	offload_csum = !!(need_csum &&
+			  !need_ipsec &&
 			  (skb->dev->features &
 			   (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
 				      (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 4acc0508c5eb..3d36644890bb 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -12,6 +12,7 @@
 #include <net/dst.h>
 #include <net/ip.h>
 #include <net/xfrm.h>
+#include <net/protocol.h>
 
 /* Add encapsulation header.
  *
@@ -23,6 +24,8 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct iphdr *iph = ip_hdr(skb);
 	int ihl = iph->ihl * 4;
 
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
 			  offsetof(struct iphdr, protocol);
@@ -56,9 +59,40 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
+static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
+						   struct sk_buff *skb,
+						   netdev_features_t features)
+{
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb->transport_header += x->props.header_len;
+	ops = rcu_dereference(inet_offloads[xo->proto]);
+	if (likely(ops && ops->callbacks.gso_segment))
+		segs = ops->callbacks.gso_segment(skb, features);
+
+	return segs;
+}
+
+static void xfrm4_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + sizeof(struct iphdr) + x->props.header_len);
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		 skb_reset_transport_header(skb);
+		 skb->transport_header -= x->props.header_len;
+	}
+}
+
 static struct xfrm_mode xfrm4_transport_mode = {
 	.input = xfrm4_transport_input,
 	.output = xfrm4_transport_output,
+	.gso_segment = xfrm4_transport_gso_segment,
+	.xmit = xfrm4_transport_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
 };
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 35feda676464..e6265e2c274e 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -33,6 +33,9 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct iphdr *top_iph;
 	int flags;
 
+	skb_set_inner_network_header(skb, skb_network_offset(skb));
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
 			  offsetof(struct iphdr, protocol);
@@ -96,11 +99,36 @@ out:
 	return err;
 }
 
+static struct sk_buff *xfrm4_mode_tunnel_gso_segment(struct xfrm_state *x,
+						     struct sk_buff *skb,
+						     netdev_features_t features)
+{
+	__skb_push(skb, skb->mac_len);
+	return skb_mac_gso_segment(skb, features);
+
+}
+
+static void xfrm4_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		skb->network_header = skb->network_header - x->props.header_len;
+		skb->transport_header = skb->network_header +
+					sizeof(struct iphdr);
+	}
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + x->props.header_len);
+}
+
 static struct xfrm_mode xfrm4_tunnel_mode = {
 	.input2 = xfrm4_mode_tunnel_input,
 	.input = xfrm_prepare_input,
 	.output2 = xfrm4_mode_tunnel_output,
 	.output = xfrm4_prepare_output,
+	.gso_segment = xfrm4_mode_tunnel_gso_segment,
+	.xmit = xfrm4_mode_tunnel_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 7ee6518afa86..94b8702603bc 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -29,7 +29,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 		goto out;
 
 	mtu = dst_mtu(skb_dst(skb));
-	if (skb->len > mtu) {
+	if ((!skb_is_gso(skb) && skb->len > mtu) ||
+	    (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) {
 		skb->protocol = htons(ETH_P_IP);
 
 		if (skb->sk)
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index e2afe677a9d9..48c452959d2c 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -307,6 +307,7 @@ config IPV6_SEG6_LWTUNNEL
 	bool "IPv6: Segment Routing Header encapsulation support"
 	depends on IPV6
 	select LWTUNNEL
+	select DST_CACHE
 	---help---
 	  Support for encapsulation of packets within an outer IPv6
 	  header and a Segment Routing Header using the lightweight
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 363172527e43..b09ac38d8dc4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -224,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.accept_ra_rtr_pref	= 1,
 	.rtr_probe_interval	= 60 * HZ,
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	.accept_ra_rt_info_min_plen = 0,
 	.accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
@@ -245,6 +246,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 #endif
 	.enhanced_dad           = 1,
 	.addr_gen_mode		= IN6_ADDR_GEN_MODE_EUI64,
+	.disable_policy		= 0,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -276,6 +278,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.accept_ra_rtr_pref	= 1,
 	.rtr_probe_interval	= 60 * HZ,
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	.accept_ra_rt_info_min_plen = 0,
 	.accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
@@ -297,6 +300,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 #endif
 	.enhanced_dad           = 1,
 	.addr_gen_mode		= IN6_ADDR_GEN_MODE_EUI64,
+	.disable_policy		= 0,
 };
 
 /* Check if a valid qdisc is available */
@@ -545,6 +549,9 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
 		goto nla_put_failure;
 
+	if (!devconf)
+		goto out;
+
 	if ((all || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
 		goto nla_put_failure;
@@ -563,6 +570,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			devconf->ignore_routes_with_linkdown) < 0)
 		goto nla_put_failure;
 
+out:
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -571,8 +579,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				  struct ipv6_devconf *devconf)
+void inet6_netconf_notify_devconf(struct net *net, int event, int type,
+				  int ifindex, struct ipv6_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -582,7 +590,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
 		goto errout;
 
 	err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
-					 RTM_NEWNETCONF, 0, type);
+					 event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -603,7 +611,8 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
 };
 
 static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
-				     struct nlmsghdr *nlh)
+				     struct nlmsghdr *nlh,
+				     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
@@ -616,7 +625,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
-			  devconf_ipv6_policy);
+			  devconf_ipv6_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -765,7 +774,8 @@ static void dev_forward_change(struct inet6_dev *idev)
 		else
 			addrconf_leave_anycast(ifa);
 	}
-	inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING,
+	inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
+				     NETCONFA_FORWARDING,
 				     dev->ifindex, &idev->cnf);
 }
 
@@ -800,7 +810,8 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 
 	if (p == &net->ipv6.devconf_dflt->forwarding) {
 		if ((!newf) ^ (!old))
-			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORWARDING,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
 		rtnl_unlock();
@@ -812,13 +823,15 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 
 		net->ipv6.devconf_dflt->forwarding = newf;
 		if ((!newf) ^ (!old_dflt))
-			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORWARDING,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
 
 		addrconf_forward_change(net, newf);
 		if ((!newf) ^ (!old))
-			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORWARDING,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
 	} else if ((!newf) ^ (!old))
@@ -843,6 +856,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf)
 			idev->cnf.ignore_routes_with_linkdown = newf;
 			if (changed)
 				inet6_netconf_notify_devconf(dev_net(dev),
+							     RTM_NEWNETCONF,
 							     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 							     dev->ifindex,
 							     &idev->cnf);
@@ -865,6 +879,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
 	if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) {
 		if ((!newf) ^ (!old))
 			inet6_netconf_notify_devconf(net,
+						     RTM_NEWNETCONF,
 						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
@@ -877,6 +892,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
 		addrconf_linkdown_change(net, newf);
 		if ((!newf) ^ (!old))
 			inet6_netconf_notify_devconf(net,
+						     RTM_NEWNETCONF,
 						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
@@ -944,6 +960,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	      const struct in6_addr *peer_addr, int pfxlen,
 	      int scope, u32 flags, u32 valid_lft, u32 prefered_lft)
 {
+	struct net *net = dev_net(idev->dev);
 	struct inet6_ifaddr *ifa = NULL;
 	struct rt6_info *rt;
 	unsigned int hash;
@@ -990,6 +1007,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 		goto out;
 	}
 
+	if (net->ipv6.devconf_all->disable_policy ||
+	    idev->cnf.disable_policy)
+		rt->dst.flags |= DST_NOPOLICY;
+
 	neigh_parms_data_state_setall(idev->nd_parms);
 
 	ifa->addr = *addr;
@@ -2053,12 +2074,23 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 	__ipv6_dev_ac_dec(ifp->idev, &addr);
 }
 
-static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev)
+static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev)
 {
-	if (dev->addr_len != EUI64_ADDR_LEN)
+	switch (dev->addr_len) {
+	case ETH_ALEN:
+		memcpy(eui, dev->dev_addr, 3);
+		eui[3] = 0xFF;
+		eui[4] = 0xFE;
+		memcpy(eui + 5, dev->dev_addr + 3, 3);
+		break;
+	case EUI64_ADDR_LEN:
+		memcpy(eui, dev->dev_addr, EUI64_ADDR_LEN);
+		eui[0] ^= 2;
+		break;
+	default:
 		return -1;
-	memcpy(eui, dev->dev_addr, EUI64_ADDR_LEN);
-	eui[0] ^= 2;
+	}
+
 	return 0;
 }
 
@@ -2150,7 +2182,7 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev)
 	case ARPHRD_TUNNEL:
 		return addrconf_ifid_gre(eui, dev);
 	case ARPHRD_6LOWPAN:
-		return addrconf_ifid_eui64(eui, dev);
+		return addrconf_ifid_6lowpan(eui, dev);
 	case ARPHRD_IEEE1394:
 		return addrconf_ifid_ieee1394(eui, dev);
 	case ARPHRD_TUNNEL6:
@@ -3271,14 +3303,24 @@ static void addrconf_gre_config(struct net_device *dev)
 static int fixup_permanent_addr(struct inet6_dev *idev,
 				struct inet6_ifaddr *ifp)
 {
-	if (!ifp->rt) {
-		struct rt6_info *rt;
+	/* rt6i_ref == 0 means the host route was removed from the
+	 * FIB, for example, if 'lo' device is taken down. In that
+	 * case regenerate the host route.
+	 */
+	if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) {
+		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
 		if (unlikely(IS_ERR(rt)))
 			return PTR_ERR(rt);
 
+		/* ifp->rt can be accessed outside of rtnl */
+		spin_lock(&ifp->lock);
+		prev = ifp->rt;
 		ifp->rt = rt;
+		spin_unlock(&ifp->lock);
+
+		ip6_rt_put(prev);
 	}
 
 	if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
@@ -3626,14 +3668,19 @@ restart:
 	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
 		struct rt6_info *rt = NULL;
+		bool keep;
 
 		addrconf_del_dad_work(ifa);
 
+		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+			!addr_is_local(&ifa->addr);
+		if (!keep)
+			list_move(&ifa->if_list, &del_list);
+
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
 
-		if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
-		    !addr_is_local(&ifa->addr)) {
+		if (keep) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
 			ifa->state = 0;
@@ -3645,8 +3692,6 @@ restart:
 		} else {
 			state = ifa->state;
 			ifa->state = INET6_IFADDR_STATE_DEAD;
-
-			list_move(&ifa->if_list, &del_list);
 		}
 
 		spin_unlock_bh(&ifa->lock);
@@ -4379,7 +4424,8 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = {
 };
 
 static int
-inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
+inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
+		  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrmsg *ifm;
@@ -4388,7 +4434,8 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u32 ifa_flags;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
@@ -4488,7 +4535,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 }
 
 static int
-inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
+inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
+		  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrmsg *ifm;
@@ -4500,7 +4548,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u32 ifa_flags;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
@@ -4850,7 +4899,8 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
 	return inet6_dump_addr(skb, cb, type);
 }
 
-static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
+static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct ifaddrmsg *ifm;
@@ -4861,7 +4911,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	struct sk_buff *skb;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
@@ -4972,6 +5023,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_RTR_PROBE_INTERVAL] =
 		jiffies_to_msecs(cnf->rtr_probe_interval);
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen;
 	array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
 #endif
 #endif
@@ -5003,6 +5055,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 #endif
 	array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad;
 	array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode;
+	array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -5229,7 +5282,8 @@ static int inet6_validate_link_af(const struct net_device *dev,
 	if (dev && !__in6_dev_get(dev))
 		return -EAFNOSUPPORT;
 
-	return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy);
+	return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy,
+				NULL);
 }
 
 static int check_addr_gen_mode(int mode)
@@ -5261,7 +5315,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	if (!idev)
 		return -EAFNOSUPPORT;
 
-	if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL) < 0)
+	if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
 	if (tb[IFLA_INET6_TOKEN]) {
@@ -5664,17 +5718,20 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
 			return restart_syscall();
 
 		if (valp == &net->ipv6.devconf_dflt->proxy_ndp)
-			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_PROXY_NEIGH,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
 		else if (valp == &net->ipv6.devconf_all->proxy_ndp)
-			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_PROXY_NEIGH,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
 		else {
 			struct inet6_dev *idev = ctl->extra1;
 
-			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_PROXY_NEIGH,
 						     idev->dev->ifindex,
 						     &idev->cnf);
 		}
@@ -5827,6 +5884,105 @@ int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl,
 	return ret;
 }
 
+static
+void addrconf_set_nopolicy(struct rt6_info *rt, int action)
+{
+	if (rt) {
+		if (action)
+			rt->dst.flags |= DST_NOPOLICY;
+		else
+			rt->dst.flags &= ~DST_NOPOLICY;
+	}
+}
+
+static
+void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
+{
+	struct inet6_ifaddr *ifa;
+
+	read_lock_bh(&idev->lock);
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		spin_lock(&ifa->lock);
+		if (ifa->rt) {
+			struct rt6_info *rt = ifa->rt;
+			struct fib6_table *table = rt->rt6i_table;
+			int cpu;
+
+			read_lock(&table->tb6_lock);
+			addrconf_set_nopolicy(ifa->rt, val);
+			if (rt->rt6i_pcpu) {
+				for_each_possible_cpu(cpu) {
+					struct rt6_info **rtp;
+
+					rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+					addrconf_set_nopolicy(*rtp, val);
+				}
+			}
+			read_unlock(&table->tb6_lock);
+		}
+		spin_unlock(&ifa->lock);
+	}
+	read_unlock_bh(&idev->lock);
+}
+
+static
+int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val)
+{
+	struct inet6_dev *idev;
+	struct net *net;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	*valp = val;
+
+	net = (struct net *)ctl->extra2;
+	if (valp == &net->ipv6.devconf_dflt->disable_policy) {
+		rtnl_unlock();
+		return 0;
+	}
+
+	if (valp == &net->ipv6.devconf_all->disable_policy)  {
+		struct net_device *dev;
+
+		for_each_netdev(net, dev) {
+			idev = __in6_dev_get(dev);
+			if (idev)
+				addrconf_disable_policy_idev(idev, val);
+		}
+	} else {
+		idev = (struct inet6_dev *)ctl->extra1;
+		addrconf_disable_policy_idev(idev, val);
+	}
+
+	rtnl_unlock();
+	return 0;
+}
+
+static
+int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	int *valp = ctl->data;
+	int val = *valp;
+	loff_t pos = *ppos;
+	struct ctl_table lctl;
+	int ret;
+
+	lctl = *ctl;
+	lctl.data = &val;
+	ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+
+	if (write && (*valp != val))
+		ret = addrconf_disable_policy(ctl, valp, val);
+
+	if (ret)
+		*ppos = pos;
+
+	return ret;
+}
+
 static int minus_one = -1;
 static const int one = 1;
 static const int two_five_five = 255;
@@ -6015,6 +6171,13 @@ static const struct ctl_table addrconf_sysctl[] = {
 	},
 #ifdef CONFIG_IPV6_ROUTE_INFO
 	{
+		.procname	= "accept_ra_rt_info_min_plen",
+		.data		= &ipv6_devconf.accept_ra_rt_info_min_plen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "accept_ra_rt_info_max_plen",
 		.data		= &ipv6_devconf.accept_ra_rt_info_max_plen,
 		.maxlen		= sizeof(int),
@@ -6185,6 +6348,13 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.proc_handler	= addrconf_sysctl_addr_gen_mode,
 	},
 	{
+		.procname       = "disable_policy",
+		.data           = &ipv6_devconf.disable_policy,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = addrconf_sysctl_disable_policy,
+	},
+	{
 		/* sentinel */
 	}
 };
@@ -6224,7 +6394,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
 		ifindex = NETCONFA_IFINDEX_DEFAULT;
 	else
 		ifindex = idev->dev->ifindex;
-	inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+	inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+				     ifindex, p);
 	return 0;
 
 free:
@@ -6233,7 +6404,8 @@ out:
 	return -ENOBUFS;
 }
 
-static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
+static void __addrconf_sysctl_unregister(struct net *net,
+					 struct ipv6_devconf *p, int ifindex)
 {
 	struct ctl_table *table;
 
@@ -6244,6 +6416,8 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
 	unregister_net_sysctl_table(p->sysctl_header);
 	p->sysctl_header = NULL;
 	kfree(table);
+
+	inet6_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
 }
 
 static int addrconf_sysctl_register(struct inet6_dev *idev)
@@ -6267,7 +6441,8 @@ static int addrconf_sysctl_register(struct inet6_dev *idev)
 
 static void addrconf_sysctl_unregister(struct inet6_dev *idev)
 {
-	__addrconf_sysctl_unregister(&idev->cnf);
+	__addrconf_sysctl_unregister(dev_net(idev->dev), &idev->cnf,
+				     idev->dev->ifindex);
 	neigh_sysctl_unregister(idev->nd_parms);
 }
 
@@ -6310,7 +6485,7 @@ static int __net_init addrconf_init_net(struct net *net)
 
 #ifdef CONFIG_SYSCTL
 err_reg_dflt:
-	__addrconf_sysctl_unregister(all);
+	__addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
 err_reg_all:
 	kfree(dflt);
 #endif
@@ -6323,8 +6498,10 @@ err_alloc_all:
 static void __net_exit addrconf_exit_net(struct net *net)
 {
 #ifdef CONFIG_SYSCTL
-	__addrconf_sysctl_unregister(net->ipv6.devconf_dflt);
-	__addrconf_sysctl_unregister(net->ipv6.devconf_all);
+	__addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt,
+				     NETCONFA_IFINDEX_DEFAULT);
+	__addrconf_sysctl_unregister(net, net->ipv6.devconf_all,
+				     NETCONFA_IFINDEX_ALL);
 #endif
 	kfree(net->ipv6.devconf_dflt);
 	kfree(net->ipv6.devconf_all);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index a8f6986dcbe5..07cd7d248bb6 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -404,7 +404,8 @@ static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
 	[IFAL_LABEL]		= { .len = sizeof(u32), },
 };
 
-static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrlblmsg *ifal;
@@ -413,7 +414,8 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u32 label;
 	int err = 0;
 
-	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
@@ -521,7 +523,8 @@ static inline int ip6addrlbl_msgsize(void)
 		+ nla_total_size(4);	/* IFAL_LABEL */
 }
 
-static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
+static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct ifaddrlblmsg *ifal;
@@ -532,7 +535,8 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	struct ip6addrlbl_entry *p;
 	struct sk_buff *skb;
 
-	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 04db40620ea6..a88b5b5b7955 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -920,12 +920,12 @@ static int __init inet6_init(void)
 	err = register_pernet_subsys(&inet6_net_ops);
 	if (err)
 		goto register_pernet_fail;
-	err = icmpv6_init();
-	if (err)
-		goto icmp_fail;
 	err = ip6_mr_init();
 	if (err)
 		goto ipmr_fail;
+	err = icmpv6_init();
+	if (err)
+		goto icmp_fail;
 	err = ndisc_init();
 	if (err)
 		goto ndisc_fail;
@@ -933,8 +933,6 @@ static int __init inet6_init(void)
 	if (err)
 		goto igmp_fail;
 
-	ipv6_stub = &ipv6_stub_impl;
-
 	err = ipv6_netfilter_init();
 	if (err)
 		goto netfilter_fail;
@@ -1005,18 +1003,28 @@ static int __init inet6_init(void)
 	if (err)
 		goto seg6_fail;
 
+	err = igmp6_late_init();
+	if (err)
+		goto igmp6_late_err;
+
 #ifdef CONFIG_SYSCTL
 	err = ipv6_sysctl_register();
 	if (err)
 		goto sysctl_fail;
 #endif
+
+	/* ensure that ipv6 stubs are visible only after ipv6 is ready */
+	wmb();
+	ipv6_stub = &ipv6_stub_impl;
 out:
 	return err;
 
 #ifdef CONFIG_SYSCTL
 sysctl_fail:
-	seg6_exit();
+	igmp6_late_cleanup();
 #endif
+igmp6_late_err:
+	seg6_exit();
 seg6_fail:
 	calipso_exit();
 calipso_fail:
@@ -1061,10 +1069,10 @@ igmp_fail:
 	ndisc_cleanup();
 ndisc_fail:
 	ip6_mr_cleanup();
-ipmr_fail:
-	icmpv6_cleanup();
 icmp_fail:
 	unregister_pernet_subsys(&inet6_net_ops);
+ipmr_fail:
+	icmpv6_cleanup();
 register_pernet_fail:
 	sock_unregister(PF_INET6);
 	rtnl_unregister_all(PF_INET6);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index eec27f87efac..e011122ebd43 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -405,9 +405,6 @@ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
  * errors. This is no longer true, but the test remained, so the v6 stack,
  * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
- *
- * Timestamp code paths do not initialize the fields expected by cmsg:
- * the PKTINFO fields in skb->cb[]. Fill those in here.
  */
 static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 				      struct sock_exterr_skb *serr)
@@ -419,14 +416,9 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
 		return false;
 
-	if (!skb->dev)
+	if (!IP6CB(skb)->iif)
 		return false;
 
-	if (skb->protocol == htons(ETH_P_IPV6))
-		IP6CB(skb)->iif = skb->dev->ifindex;
-	else
-		PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
-
 	return true;
 }
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index ff54faa75631..1fe99ba8066c 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -170,19 +170,23 @@ static void esp_output_restore_header(struct sk_buff *skb)
 }
 
 static struct ip_esp_hdr *esp_output_set_esn(struct sk_buff *skb,
+					     struct xfrm_state *x,
 					     struct ip_esp_hdr *esph,
 					     __be32 *seqhi)
 {
-	struct xfrm_state *x = skb_dst(skb)->xfrm;
-
 	/* For ESN we move the header forward by 4 bytes to
 	 * accomodate the high bits.  We will move it back after
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
+		struct xfrm_offload *xo = xfrm_offload(skb);
+
 		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
 		*seqhi = esph->spi;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		if (xo)
+			esph->seq_no = htonl(xo->seq.hi);
+		else
+			esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
 	}
 
 	esph->spi = x->id.spi;
@@ -214,61 +218,16 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
 	tail[plen - 1] = proto;
 }
 
-static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
+int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
-	int err;
-	struct ip_esp_hdr *esph;
-	struct crypto_aead *aead;
-	struct aead_request *req;
-	struct scatterlist *sg, *dsg;
-	struct sk_buff *trailer;
-	struct page *page;
-	void *tmp;
-	int blksize;
-	int clen;
-	int alen;
-	int plen;
-	int ivlen;
-	int tfclen;
-	int nfrags;
-	int assoclen;
-	int seqhilen;
-	int tailen;
-	u8 *iv;
 	u8 *tail;
 	u8 *vaddr;
-	__be32 *seqhi;
-	__be64 seqno;
-	__u8 proto = *skb_mac_header(skb);
-
-	/* skb is pure payload to encrypt */
-	aead = x->data;
-	alen = crypto_aead_authsize(aead);
-	ivlen = crypto_aead_ivsize(aead);
-
-	tfclen = 0;
-	if (x->tfcpad) {
-		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
-		u32 padto;
-
-		padto = min(x->tfcpad, esp6_get_mtu(x, dst->child_mtu_cached));
-		if (skb->len < padto)
-			tfclen = padto - skb->len;
-	}
-	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
-	clen = ALIGN(skb->len + 2 + tfclen, blksize);
-	plen = clen - skb->len - tfclen;
-	tailen = tfclen + plen + alen;
-
-	assoclen = sizeof(*esph);
-	seqhilen = 0;
-
-	if (x->props.flags & XFRM_STATE_ESN) {
-		seqhilen += sizeof(__be32);
-		assoclen += seqhilen;
-	}
+	int nfrags;
+	struct page *page;
+	struct ip_esp_hdr *esph;
+	struct sk_buff *trailer;
+	int tailen = esp->tailen;
 
-	*skb_mac_header(skb) = IPPROTO_ESP;
 	esph = ip_esp_hdr(skb);
 
 	if (!skb_cloned(skb)) {
@@ -284,6 +243,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 			struct sock *sk = skb->sk;
 			struct page_frag *pfrag = &x->xfrag;
 
+			esp->inplace = false;
+
 			allocsize = ALIGN(tailen, L1_CACHE_BYTES);
 
 			spin_lock_bh(&x->lock);
@@ -300,10 +261,12 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 
 			tail = vaddr + pfrag->offset;
 
-			esp_output_fill_trailer(tail, tfclen, plen, proto);
+			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
 			kunmap_atomic(vaddr);
 
+			spin_unlock_bh(&x->lock);
+
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
@@ -319,108 +282,111 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 			if (sk)
 				atomic_add(tailen, &sk->sk_wmem_alloc);
 
-			skb_push(skb, -skb_network_offset(skb));
-
-			esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
-			esph->spi = x->id.spi;
-
-			tmp = esp_alloc_tmp(aead, nfrags + 2, seqhilen);
-			if (!tmp) {
-				spin_unlock_bh(&x->lock);
-				err = -ENOMEM;
-				goto error;
-			}
-			seqhi = esp_tmp_seqhi(tmp);
-			iv = esp_tmp_iv(aead, tmp, seqhilen);
-			req = esp_tmp_req(aead, iv);
-			sg = esp_req_sg(aead, req);
-			dsg = &sg[nfrags];
-
-			esph = esp_output_set_esn(skb, esph, seqhi);
-
-			sg_init_table(sg, nfrags);
-			skb_to_sgvec(skb, sg,
-				     (unsigned char *)esph - skb->data,
-				     assoclen + ivlen + clen + alen);
-
-			allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
-
-			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
-				spin_unlock_bh(&x->lock);
-				err = -ENOMEM;
-				goto error;
-			}
-
-			skb_shinfo(skb)->nr_frags = 1;
-
-			page = pfrag->page;
-			get_page(page);
-			/* replace page frags in skb with new page */
-			__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
-			pfrag->offset = pfrag->offset + allocsize;
-
-			sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
-			skb_to_sgvec(skb, dsg,
-				     (unsigned char *)esph - skb->data,
-				     assoclen + ivlen + clen + alen);
-
-			spin_unlock_bh(&x->lock);
-
-			goto skip_cow2;
+			goto out;
 		}
 	}
 
 cow:
-	err = skb_cow_data(skb, tailen, &trailer);
-	if (err < 0)
-		goto error;
-	nfrags = err;
-
+	nfrags = skb_cow_data(skb, tailen, &trailer);
+	if (nfrags < 0)
+		goto out;
 	tail = skb_tail_pointer(trailer);
-	esph = ip_esp_hdr(skb);
 
 skip_cow:
-	esp_output_fill_trailer(tail, tfclen, plen, proto);
+	esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
+	pskb_put(skb, trailer, tailen);
 
-	pskb_put(skb, trailer, clen - skb->len + alen);
-	skb_push(skb, -skb_network_offset(skb));
+out:
+	return nfrags;
+}
+EXPORT_SYMBOL_GPL(esp6_output_head);
 
-	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
-	esph->spi = x->id.spi;
+int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+{
+	u8 *iv;
+	int alen;
+	void *tmp;
+	int ivlen;
+	int assoclen;
+	int seqhilen;
+	__be32 *seqhi;
+	struct page *page;
+	struct ip_esp_hdr *esph;
+	struct aead_request *req;
+	struct crypto_aead *aead;
+	struct scatterlist *sg, *dsg;
+	int err = -ENOMEM;
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
-	if (!tmp) {
-		err = -ENOMEM;
-		goto error;
+	assoclen = sizeof(struct ip_esp_hdr);
+	seqhilen = 0;
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		seqhilen += sizeof(__be32);
+		assoclen += sizeof(__be32);
 	}
 
+	aead = x->data;
+	alen = crypto_aead_authsize(aead);
+	ivlen = crypto_aead_ivsize(aead);
+
+	tmp = esp_alloc_tmp(aead, esp->nfrags + 2, seqhilen);
+	if (!tmp)
+		goto error;
+
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
-	dsg = sg;
 
-	esph = esp_output_set_esn(skb, esph, seqhi);
+	if (esp->inplace)
+		dsg = sg;
+	else
+		dsg = &sg[esp->nfrags];
 
-	sg_init_table(sg, nfrags);
+	esph = esp_output_set_esn(skb, x, ip_esp_hdr(skb), seqhi);
+
+	sg_init_table(sg, esp->nfrags);
 	skb_to_sgvec(skb, sg,
 		     (unsigned char *)esph - skb->data,
-		     assoclen + ivlen + clen + alen);
+		     assoclen + ivlen + esp->clen + alen);
+
+	if (!esp->inplace) {
+		int allocsize;
+		struct page_frag *pfrag = &x->xfrag;
+
+		allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
+
+		spin_lock_bh(&x->lock);
+		if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+			spin_unlock_bh(&x->lock);
+			goto error;
+		}
+
+		skb_shinfo(skb)->nr_frags = 1;
+
+		page = pfrag->page;
+		get_page(page);
+		/* replace page frags in skb with new page */
+		__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
+		pfrag->offset = pfrag->offset + allocsize;
+		spin_unlock_bh(&x->lock);
+
+		sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
+		skb_to_sgvec(skb, dsg,
+			     (unsigned char *)esph - skb->data,
+			     assoclen + ivlen + esp->clen + alen);
+	}
 
-skip_cow2:
 	if ((x->props.flags & XFRM_STATE_ESN))
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	else
 		aead_request_set_callback(req, 0, esp_output_done, skb);
 
-	aead_request_set_crypt(req, sg, dsg, ivlen + clen, iv);
+	aead_request_set_crypt(req, sg, dsg, ivlen + esp->clen, iv);
 	aead_request_set_ad(req, assoclen);
 
-	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
-			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
-
 	memset(iv, 0, ivlen);
-	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8),
+	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&esp->seqno + 8 - min(ivlen, 8),
 	       min(ivlen, 8));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
@@ -446,10 +412,60 @@ skip_cow2:
 error:
 	return err;
 }
+EXPORT_SYMBOL_GPL(esp6_output_tail);
 
-static int esp_input_done2(struct sk_buff *skb, int err)
+static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int alen;
+	int blksize;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct esp_info esp;
+
+	esp.inplace = true;
+
+	esp.proto = *skb_mac_header(skb);
+	*skb_mac_header(skb) = IPPROTO_ESP;
+
+	/* skb is pure payload to encrypt */
+
+	aead = x->data;
+	alen = crypto_aead_authsize(aead);
+
+	esp.tfclen = 0;
+	if (x->tfcpad) {
+		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
+		u32 padto;
+
+		padto = min(x->tfcpad, esp6_get_mtu(x, dst->child_mtu_cached));
+		if (skb->len < padto)
+			esp.tfclen = padto - skb->len;
+	}
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
+	esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
+	esp.plen = esp.clen - skb->len - esp.tfclen;
+	esp.tailen = esp.tfclen + esp.plen + alen;
+
+	esp.nfrags = esp6_output_head(x, skb, &esp);
+	if (esp.nfrags < 0)
+		return esp.nfrags;
+
+	esph = ip_esp_hdr(skb);
+	esph->spi = x->id.spi;
+
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+	esp.seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
+			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+
+	skb_push(skb, -skb_network_offset(skb));
+
+	return esp6_output_tail(x, skb, &esp);
+}
+
+int esp6_input_done2(struct sk_buff *skb, int err)
 {
 	struct xfrm_state *x = xfrm_input_state(skb);
+	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct crypto_aead *aead = x->data;
 	int alen = crypto_aead_authsize(aead);
 	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
@@ -458,7 +474,8 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 	int padlen;
 	u8 nexthdr[2];
 
-	kfree(ESP_SKB_CB(skb)->tmp);
+	if (!xo || (xo && !(xo->flags & CRYPTO_DONE)))
+		kfree(ESP_SKB_CB(skb)->tmp);
 
 	if (unlikely(err))
 		goto out;
@@ -492,12 +509,13 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 out:
 	return err;
 }
+EXPORT_SYMBOL_GPL(esp6_input_done2);
 
 static void esp_input_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
 
-	xfrm_input_resume(skb, esp_input_done2(skb, err));
+	xfrm_input_resume(skb, esp6_input_done2(skb, err));
 }
 
 static void esp_input_restore_header(struct sk_buff *skb)
@@ -619,7 +637,7 @@ skip_cow:
 	if ((x->props.flags & XFRM_STATE_ESN))
 		esp_input_restore_header(skb);
 
-	ret = esp_input_done2(skb, ret);
+	ret = esp6_input_done2(skb, ret);
 
 out:
 	return ret;
@@ -682,13 +700,17 @@ static int esp_init_aead(struct xfrm_state *x)
 	char aead_name[CRYPTO_MAX_ALG_NAME];
 	struct crypto_aead *aead;
 	int err;
+	u32 mask = 0;
 
 	err = -ENAMETOOLONG;
 	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
 		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
 		goto error;
 
-	aead = crypto_alloc_aead(aead_name, 0, 0);
+	if (x->xso.offload_handle)
+		mask |= CRYPTO_ALG_ASYNC;
+
+	aead = crypto_alloc_aead(aead_name, 0, mask);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -718,6 +740,7 @@ static int esp_init_authenc(struct xfrm_state *x)
 	char authenc_name[CRYPTO_MAX_ALG_NAME];
 	unsigned int keylen;
 	int err;
+	u32 mask = 0;
 
 	err = -EINVAL;
 	if (!x->ealg)
@@ -743,7 +766,10 @@ static int esp_init_authenc(struct xfrm_state *x)
 			goto error;
 	}
 
-	aead = crypto_alloc_aead(authenc_name, 0, 0);
+	if (x->xso.offload_handle)
+		mask |= CRYPTO_ALG_ASYNC;
+
+	aead = crypto_alloc_aead(authenc_name, 0, mask);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d914eb93204a..d950d43ba255 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -45,27 +45,31 @@ static struct sk_buff **esp6_gro_receive(struct sk_buff **head,
 	if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
 		goto out;
 
-	err = secpath_set(skb);
-	if (err)
-		goto out;
+	xo = xfrm_offload(skb);
+	if (!xo || !(xo->flags & CRYPTO_DONE)) {
+		err = secpath_set(skb);
+		if (err)
+			goto out;
 
-	if (skb->sp->len == XFRM_MAX_DEPTH)
-		goto out;
+		if (skb->sp->len == XFRM_MAX_DEPTH)
+			goto out;
 
-	x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
-			      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
-			      spi, IPPROTO_ESP, AF_INET6);
-	if (!x)
-		goto out;
+		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
+				      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
+				      spi, IPPROTO_ESP, AF_INET6);
+		if (!x)
+			goto out;
 
-	skb->sp->xvec[skb->sp->len++] = x;
-	skb->sp->olen++;
+		skb->sp->xvec[skb->sp->len++] = x;
+		skb->sp->olen++;
 
-	xo = xfrm_offload(skb);
-	if (!xo) {
-		xfrm_state_put(x);
-		goto out;
+		xo = xfrm_offload(skb);
+		if (!xo) {
+			xfrm_state_put(x);
+			goto out;
+		}
 	}
+
 	xo->flags |= XFRM_GRO;
 
 	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
@@ -86,19 +90,216 @@ out:
 	return NULL;
 }
 
+static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ip_esp_hdr *esph;
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	int proto = iph->nexthdr;
+
+	skb_push(skb, -skb_network_offset(skb));
+	esph = ip_esp_hdr(skb);
+	*skb_mac_header(skb) = IPPROTO_ESP;
+
+	esph->spi = x->id.spi;
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+
+	xo->proto = proto;
+}
+
+static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
+				        netdev_features_t features)
+{
+	__u32 seq;
+	int err = 0;
+	struct sk_buff *skb2;
+	struct xfrm_state *x;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	netdev_features_t esp_features = features;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (!xo)
+		goto out;
+
+	seq = xo->seq.low;
+
+	x = skb->sp->xvec[skb->sp->len - 1];
+	aead = x->data;
+	esph = ip_esp_hdr(skb);
+
+	if (esph->spi != x->id.spi)
+		goto out;
+
+	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
+		goto out;
+
+	__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));
+
+	skb->encap_hdr_csum = 1;
+
+	if (!(features & NETIF_F_HW_ESP))
+		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+
+	segs = x->outer_mode->gso_segment(x, skb, esp_features);
+	if (IS_ERR_OR_NULL(segs))
+		goto out;
+
+	__skb_pull(skb, skb->data - skb_mac_header(skb));
+
+	skb2 = segs;
+	do {
+		struct sk_buff *nskb = skb2->next;
+
+		xo = xfrm_offload(skb2);
+		xo->flags |= XFRM_GSO_SEGMENT;
+		xo->seq.low = seq;
+		xo->seq.hi = xfrm_replay_seqhi(x, seq);
+
+		if(!(features & NETIF_F_HW_ESP))
+			xo->flags |= CRYPTO_FALLBACK;
+
+		x->outer_mode->xmit(x, skb2);
+
+		err = x->type_offload->xmit(x, skb2, esp_features);
+		if (err) {
+			kfree_skb_list(segs);
+			return ERR_PTR(err);
+		}
+
+		if (!skb_is_gso(skb2))
+			seq++;
+		else
+			seq += skb_shinfo(skb2)->gso_segs;
+
+		skb_push(skb2, skb2->mac_len);
+		skb2 = nskb;
+	} while (skb2);
+
+out:
+	return segs;
+}
+
+static int esp6_input_tail(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct crypto_aead *aead = x->data;
+
+	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
+		return -EINVAL;
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	return esp6_input_done2(skb, 0);
+}
+
+static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_t features)
+{
+	int err;
+	int alen;
+	int blksize;
+	struct xfrm_offload *xo;
+	struct ip_esp_hdr *esph;
+	struct crypto_aead *aead;
+	struct esp_info esp;
+	bool hw_offload = true;
+
+	esp.inplace = true;
+
+	xo = xfrm_offload(skb);
+
+	if (!xo)
+		return -EINVAL;
+
+	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
+	    (x->xso.dev != skb->dev)) {
+		xo->flags |= CRYPTO_FALLBACK;
+		hw_offload = false;
+	}
+
+	esp.proto = xo->proto;
+
+	/* skb is pure payload to encrypt */
+
+	aead = x->data;
+	alen = crypto_aead_authsize(aead);
+
+	esp.tfclen = 0;
+	/* XXX: Add support for tfc padding here. */
+
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
+	esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
+	esp.plen = esp.clen - skb->len - esp.tfclen;
+	esp.tailen = esp.tfclen + esp.plen + alen;
+
+	if (!hw_offload || (hw_offload && !skb_is_gso(skb))) {
+		esp.nfrags = esp6_output_head(x, skb, &esp);
+		if (esp.nfrags < 0)
+			return esp.nfrags;
+	}
+
+	esph = ip_esp_hdr(skb);
+	esph->spi = x->id.spi;
+
+	skb_push(skb, -skb_network_offset(skb));
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		esph->seq_no = htonl(xo->seq.low);
+	} else {
+		int len;
+
+		len = skb->len - sizeof(struct ipv6hdr);
+		if (len > IPV6_MAXPLEN)
+			len = 0;
+
+		ipv6_hdr(skb)->payload_len = htons(len);
+	}
+
+	if (hw_offload)
+		return 0;
+
+	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
+
+	err = esp6_output_tail(x, skb, &esp);
+	if (err < 0)
+		return err;
+
+	secpath_reset(skb);
+
+	return 0;
+}
+
 static const struct net_offload esp6_offload = {
 	.callbacks = {
 		.gro_receive = esp6_gro_receive,
+		.gso_segment = esp6_gso_segment,
 	},
 };
 
+static const struct xfrm_type_offload esp6_type_offload = {
+	.description	= "ESP6 OFFLOAD",
+	.owner		= THIS_MODULE,
+	.proto	     	= IPPROTO_ESP,
+	.input_tail	= esp6_input_tail,
+	.xmit		= esp6_xmit,
+	.encap		= esp6_gso_encap,
+};
+
 static int __init esp6_offload_init(void)
 {
+	if (xfrm_register_type_offload(&esp6_type_offload, AF_INET6) < 0) {
+		pr_info("%s: can't add xfrm type offload\n", __func__);
+		return -EAGAIN;
+	}
+
 	return inet6_add_offload(&esp6_offload, IPPROTO_ESP);
 }
 
 static void __exit esp6_offload_exit(void)
 {
+	if (xfrm_unregister_type_offload(&esp6_type_offload, AF_INET6) < 0)
+		pr_info("%s: can't remove xfrm type offload\n", __func__);
+
 	inet6_del_offload(&esp6_offload, IPPROTO_ESP);
 }
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 275cac628a95..b636f1da9aec 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -388,7 +388,6 @@ looped_back:
 		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
 				  ((&hdr->segments_left) -
 				   skb_network_header(skb)));
-		kfree_skb(skb);
 		return -1;
 	}
 
@@ -910,6 +909,8 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
 {
 	switch (opt->type) {
 	case IPV6_SRCRT_TYPE_0:
+	case IPV6_SRCRT_STRICT:
+	case IPV6_SRCRT_TYPE_2:
 		ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
 		break;
 	case IPV6_SRCRT_TYPE_4:
@@ -945,13 +946,13 @@ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
 	if (opt->hopopt)
 		ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt);
 }
-EXPORT_SYMBOL(ipv6_push_nfrag_opts);
 
 void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto)
 {
 	if (opt->dst1opt)
 		ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt);
 }
+EXPORT_SYMBOL(ipv6_push_frag_opts);
 
 struct ipv6_txoptions *
 ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
@@ -1164,6 +1165,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
 
 	switch (opt->srcrt->type) {
 	case IPV6_SRCRT_TYPE_0:
+	case IPV6_SRCRT_STRICT:
+	case IPV6_SRCRT_TYPE_2:
 		fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
 		break;
 	case IPV6_SRCRT_TYPE_4:
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ce1aae4a7fc8..b3df03e3faa0 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -146,8 +146,7 @@ static int ila_build_state(struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla,
-			       ila_nl_policy);
+	ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e4266746e4a2..d4bf2c68a545 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -923,6 +923,8 @@ add:
 			ins = &rt->dst.rt6_next;
 			iter = *ins;
 			while (iter) {
+				if (iter->rt6i_metric > rt->rt6i_metric)
+					break;
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 6fcb7cb49bb2..8d128ba79b66 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -544,6 +544,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 					  & IPV6_TCLASS_MASK;
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
+	else
+		fl6.flowi6_mark = t->parms.fwmark;
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
 
@@ -603,6 +605,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowlabel |= ip6_flowlabel(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
+	else
+		fl6.flowi6_mark = t->parms.fwmark;
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
 
@@ -780,6 +784,7 @@ static int ip6gre_tnl_change(struct ip6_tnl *t,
 	t->parms.o_key = p->o_key;
 	t->parms.i_flags = p->i_flags;
 	t->parms.o_flags = p->o_flags;
+	t->parms.fwmark = p->fwmark;
 	dst_cache_reset(&t->dst_cache);
 	ip6gre_tnl_link_config(t, set_mtu);
 	return 0;
@@ -1249,6 +1254,9 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_GRE_FLAGS])
 		parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]);
+
+	if (data[IFLA_GRE_FWMARK])
+		parms->fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
 }
 
 static int ip6gre_tap_init(struct net_device *dev)
@@ -1470,6 +1478,8 @@ static size_t ip6gre_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_GRE_ENCAP_DPORT */
 		nla_total_size(2) +
+		/* IFLA_GRE_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1490,7 +1500,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) ||
 	    nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
 	    nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
-	    nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags))
+	    nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) ||
+	    nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -1525,6 +1536,7 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_ENCAP_FLAGS]  = { .type = NLA_U16 },
 	[IFLA_GRE_ENCAP_SPORT]  = { .type = NLA_U16 },
 	[IFLA_GRE_ENCAP_DPORT]  = { .type = NLA_U16 },
+	[IFLA_GRE_FWMARK]       = { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index aacfb4bce153..9ee208a348f5 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -49,6 +49,8 @@
 
 int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	void (*edemux)(struct sk_buff *skb);
+
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
 	 */
@@ -60,8 +62,8 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 		const struct inet6_protocol *ipprot;
 
 		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
-		if (ipprot && ipprot->early_demux)
-			ipprot->early_demux(skb);
+		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
+			edemux(skb);
 	}
 	if (!skb_valid_dst(skb))
 		ip6_route_input(skb);
@@ -122,11 +124,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 			max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
 	/*
 	 * RFC4291 2.5.3
+	 * The loopback address must not be used as the source address in IPv6
+	 * packets that are sent outside of a single node. [..]
 	 * A packet received on an interface with a destination address
 	 * of loopback must be dropped.
 	 */
-	if (!(dev->flags & IFF_LOOPBACK) &&
-	    ipv6_addr_loopback(&hdr->daddr))
+	if ((ipv6_addr_loopback(&hdr->saddr) ||
+	     ipv6_addr_loopback(&hdr->daddr)) &&
+	     !(dev->flags & IFF_LOOPBACK))
 		goto err;
 
 	/* RFC4291 Errata ID: 3480
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 0838e6d01d2e..93e58a5e1837 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 528b3c1f3fde..58f6288e9ba5 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,13 +768,14 @@ slow_path:
 	 *	Fragment the datagram.
 	 */
 
-	*prevhdr = NEXTHDR_FRAGMENT;
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 	while (left > 0)	{
+		u8 *fragnexthdr_offset;
+
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
@@ -819,6 +820,10 @@ slow_path:
 		 */
 		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
 
+		fragnexthdr_offset = skb_network_header(frag);
+		fragnexthdr_offset += prevhdr - skb_network_header(skb);
+		*fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
 		/*
 		 *	Build fragment header.
 		 */
@@ -1385,7 +1390,7 @@ emsgsize:
 	if ((((length + fragheaderlen) > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen, exthdrlen,
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 75fac933c209..6eb2ae507500 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -954,7 +954,7 @@ static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit)
 	opt->dst_opt[5] = IPV6_TLV_PADN;
 	opt->dst_opt[6] = 1;
 
-	opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt;
+	opt->ops.dst1opt = (struct ipv6_opt_hdr *) opt->dst_opt;
 	opt->ops.opt_nflen = 8;
 }
 
@@ -1037,7 +1037,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
@@ -1057,26 +1057,28 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
-		struct in6_addr *addr6;
-		struct neighbour *neigh;
-		int addr_type;
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct in6_addr *addr6;
+			struct neighbour *neigh;
+			int addr_type;
 
-		if (!skb_dst(skb))
-			goto tx_err_link_failure;
+			if (!skb_dst(skb))
+				goto tx_err_link_failure;
 
-		neigh = dst_neigh_lookup(skb_dst(skb),
-					 &ipv6_hdr(skb)->daddr);
-		if (!neigh)
-			goto tx_err_link_failure;
+			neigh = dst_neigh_lookup(skb_dst(skb),
+						 &ipv6_hdr(skb)->daddr);
+			if (!neigh)
+				goto tx_err_link_failure;
 
-		addr6 = (struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
+			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr_type = ipv6_addr_type(addr6);
 
-		if (addr_type == IPV6_ADDR_ANY)
-			addr6 = &ipv6_hdr(skb)->daddr;
+			if (addr_type == IPV6_ADDR_ANY)
+				addr6 = &ipv6_hdr(skb)->daddr;
 
-		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
-		neigh_release(neigh);
+			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+			neigh_release(neigh);
+		}
 	} else if (!(t->parms.flags &
 		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
 		/* enable the cache only only if the routing decision does
@@ -1176,7 +1178,7 @@ route_lookup:
 
 	if (encap_limit >= 0) {
 		init_tel_txopt(&opt, encap_limit);
-		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL, NULL);
+		ipv6_push_frag_opts(skb, &opt.ops, &proto);
 	}
 
 	/* Calculate max headroom for all the headers and adjust
@@ -1256,6 +1258,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 					 & IPV6_TCLASS_MASK;
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 			fl6.flowi6_mark = skb->mark;
+		else
+			fl6.flowi6_mark = t->parms.fwmark;
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
@@ -1338,6 +1342,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 			fl6.flowlabel |= ip6_flowlabel(ipv6h);
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 			fl6.flowi6_mark = skb->mark;
+		else
+			fl6.flowi6_mark = t->parms.fwmark;
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
@@ -1467,6 +1473,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 	t->parms.flowinfo = p->flowinfo;
 	t->parms.link = p->link;
 	t->parms.proto = p->proto;
+	t->parms.fwmark = p->fwmark;
 	dst_cache_reset(&t->dst_cache);
 	ip6_tnl_link_config(t);
 	return 0;
@@ -1918,6 +1925,9 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_COLLECT_METADATA])
 		parms->collect_md = true;
+
+	if (data[IFLA_IPTUN_FWMARK])
+		parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
 static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[],
@@ -2054,6 +2064,8 @@ static size_t ip6_tnl_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_IPTUN_COLLECT_METADATA */
 		nla_total_size(0) +
+		/* IFLA_IPTUN_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -2069,7 +2081,8 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
 	    nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
 	    nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) ||
-	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto))
+	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto) ||
+	    nla_put_u32(skb, IFLA_IPTUN_FWMARK, parm->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) ||
@@ -2081,6 +2094,7 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	if (parm->collect_md)
 		if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA))
 			goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -2109,6 +2123,7 @@ static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_COLLECT_METADATA]	= { .type = NLA_FLAG },
+	[IFLA_IPTUN_FWMARK]		= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops ip6_link_ops __read_mostly = {
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 644ba59fbd9d..d67ef56454b2 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -485,11 +485,15 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	if (!skb->ignore_df && skb->len > mtu) {
 		skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
 
-		if (skb->protocol == htons(ETH_P_IPV6))
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			if (mtu < IPV6_MIN_MTU)
+				mtu = IPV6_MIN_MTU;
+
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-		else
+		} else {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
+		}
 
 		return -EMSGSIZE;
 	}
@@ -653,6 +657,7 @@ vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 	t->parms.i_key = p->i_key;
 	t->parms.o_key = p->o_key;
 	t->parms.proto = p->proto;
+	t->parms.fwmark = p->fwmark;
 	dst_cache_reset(&t->dst_cache);
 	vti6_link_config(t);
 	return 0;
@@ -929,6 +934,9 @@ static void vti6_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_VTI_OKEY])
 		parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);
+
+	if (data[IFLA_VTI_FWMARK])
+		parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
 }
 
 static int vti6_newlink(struct net *src_net, struct net_device *dev,
@@ -994,6 +1002,8 @@ static size_t vti6_get_size(const struct net_device *dev)
 		nla_total_size(4) +
 		/* IFLA_VTI_OKEY */
 		nla_total_size(4) +
+		/* IFLA_VTI_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1006,7 +1016,8 @@ static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) ||
 	    nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) ||
 	    nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) ||
-	    nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key))
+	    nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key) ||
+	    nla_put_u32(skb, IFLA_VTI_FWMARK, parm->fwmark))
 		goto nla_put_failure;
 	return 0;
 
@@ -1020,6 +1031,7 @@ static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = {
 	[IFLA_VTI_REMOTE]	= { .len = sizeof(struct in6_addr) },
 	[IFLA_VTI_IKEY]		= { .type = NLA_U32 },
 	[IFLA_VTI_OKEY]		= { .type = NLA_U32 },
+	[IFLA_VTI_FWMARK]	= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops vti6_link_ops __read_mostly = {
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6ba6c900ebcf..374997d26488 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -774,7 +774,8 @@ failure:
  *	Delete a VIF entry
  */
 
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+		       struct list_head *head)
 {
 	struct mif_device *v;
 	struct net_device *dev;
@@ -815,12 +816,12 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
 	in6_dev = __in6_dev_get(dev);
 	if (in6_dev) {
 		in6_dev->cnf.mc_forwarding--;
-		inet6_netconf_notify_devconf(dev_net(dev),
+		inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					     NETCONFA_MC_FORWARDING,
 					     dev->ifindex, &in6_dev->cnf);
 	}
 
-	if (v->flags & MIFF_REGISTER)
+	if ((v->flags & MIFF_REGISTER) && !notify)
 		unregister_netdevice_queue(dev, head);
 
 	dev_put(dev);
@@ -974,7 +975,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
 	in6_dev = __in6_dev_get(dev);
 	if (in6_dev) {
 		in6_dev->cnf.mc_forwarding++;
-		inet6_netconf_notify_devconf(dev_net(dev),
+		inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					     NETCONFA_MC_FORWARDING,
 					     dev->ifindex, &in6_dev->cnf);
 	}
@@ -1331,7 +1332,6 @@ static int ip6mr_device_event(struct notifier_block *this,
 	struct mr6_table *mrt;
 	struct mif_device *v;
 	int ct;
-	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
@@ -1340,10 +1340,9 @@ static int ip6mr_device_event(struct notifier_block *this,
 		v = &mrt->vif6_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
-				mif6_delete(mrt, ct, &list);
+				mif6_delete(mrt, ct, 1, NULL);
 		}
 	}
-	unregister_netdevice_many(&list);
 
 	return NOTIFY_DONE;
 }
@@ -1552,7 +1551,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 	for (i = 0; i < mrt->maxvif; i++) {
 		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
 			continue;
-		mif6_delete(mrt, i, &list);
+		mif6_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1599,7 +1598,8 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
 	write_unlock_bh(&mrt_lock);
 
 	if (!err)
-		inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+		inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+					     NETCONFA_MC_FORWARDING,
 					     NETCONFA_IFINDEX_ALL,
 					     net->ipv6.devconf_all);
 	rtnl_unlock();
@@ -1620,7 +1620,7 @@ int ip6mr_sk_done(struct sock *sk)
 			mrt->mroute6_sk = NULL;
 			net->ipv6.devconf_all->mc_forwarding--;
 			write_unlock_bh(&mrt_lock);
-			inet6_netconf_notify_devconf(net,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
 						     NETCONFA_MC_FORWARDING,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
@@ -1707,7 +1707,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
 			return -EFAULT;
 		rtnl_lock();
-		ret = mif6_delete(mrt, mifi, NULL);
+		ret = mif6_delete(mrt, mifi, 0, NULL);
 		rtnl_unlock();
 		return ret;
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1bdc703cb966..07403fa164e1 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2463,7 +2463,6 @@ static void mld_ifc_event(struct inet6_dev *idev)
 	mld_ifc_start_timer(idev, 1);
 }
 
-
 static void igmp6_timer_handler(unsigned long data)
 {
 	struct ifmcaddr6 *ma = (struct ifmcaddr6 *) data;
@@ -2599,6 +2598,44 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 	write_unlock_bh(&idev->lock);
 }
 
+static void ipv6_mc_rejoin_groups(struct inet6_dev *idev)
+{
+	struct ifmcaddr6 *pmc;
+
+	ASSERT_RTNL();
+
+	if (mld_in_v1_mode(idev)) {
+		read_lock_bh(&idev->lock);
+		for (pmc = idev->mc_list; pmc; pmc = pmc->next)
+			igmp6_join_group(pmc);
+		read_unlock_bh(&idev->lock);
+	} else
+		mld_send_report(idev, NULL);
+}
+
+static int ipv6_mc_netdev_event(struct notifier_block *this,
+				unsigned long event,
+				void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct inet6_dev *idev = __in6_dev_get(dev);
+
+	switch (event) {
+	case NETDEV_RESEND_IGMP:
+		if (idev)
+			ipv6_mc_rejoin_groups(idev);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block igmp6_netdev_notifier = {
+	.notifier_call = ipv6_mc_netdev_event,
+};
+
 #ifdef CONFIG_PROC_FS
 struct igmp6_mc_iter_state {
 	struct seq_net_private p;
@@ -2970,7 +3007,17 @@ int __init igmp6_init(void)
 	return register_pernet_subsys(&igmp6_net_ops);
 }
 
+int __init igmp6_late_init(void)
+{
+	return register_netdevice_notifier(&igmp6_netdev_notifier);
+}
+
 void igmp6_cleanup(void)
 {
 	unregister_pernet_subsys(&igmp6_net_ops);
 }
+
+void igmp6_late_cleanup(void)
+{
+	unregister_netdevice_notifier(&igmp6_netdev_notifier);
+}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 7ebac630d3c6..d310dc41209a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -732,7 +732,7 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
 		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
 		  struct ndisc_options *ndopts)
 {
-	neigh_update(neigh, lladdr, new, flags);
+	neigh_update(neigh, lladdr, new, flags, 0);
 	/* report ndisc ops about neighbour update */
 	ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
 }
@@ -1418,6 +1418,8 @@ skip_linkparms:
 			if (ri->prefix_len == 0 &&
 			    !in6_dev->cnf.accept_ra_defrtr)
 				continue;
+			if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
+				continue;
 			if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
 				continue;
 			rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
@@ -1746,10 +1748,13 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGEADDR:
 		neigh_changeaddr(&nd_tbl, dev);
 		fib6_run_gc(0, net, false);
+		/* fallthrough */
+	case NETDEV_UP:
 		idev = in6_dev_get(dev);
 		if (!idev)
 			break;
-		if (idev->cnf.ndisc_notify)
+		if (idev->cnf.ndisc_notify ||
+		    net->ipv6.devconf_all->ndisc_notify)
 			ndisc_send_unsol_na(dev);
 		in6_dev_put(idev);
 		break;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 1e15c54fd5e2..1f90644056ac 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -51,15 +51,6 @@ void *ip6t_alloc_initial_table(const struct xt_table *info)
 }
 EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table);
 
-/*
-   We keep a set of rules for each CPU, so we can avoid write-locking
-   them in the softirq when updating the counters and therefore
-   only need to read-lock in the softirq; doing a write_lock_bh() in user
-   context stops packets coming through and allows user context to read
-   the counters or update the rules.
-
-   Hence the start of any table is given by get_table() below.  */
-
 /* Returns whether matches rule or not. */
 /* Performance critical - called for every packet */
 static inline bool
@@ -411,7 +402,7 @@ mark_source_chains(const struct xt_table_info *newinfo,
 	   to 0 as we leave), and comefrom to save source hook bitmask */
 	for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
-		struct ip6t_entry *e = (struct ip6t_entry *)(entry0 + pos);
+		struct ip6t_entry *e = entry0 + pos;
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
@@ -453,14 +444,12 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					if (pos == oldpos)
 						goto next;
 
-					e = (struct ip6t_entry *)
-						(entry0 + pos);
+					e = entry0 + pos;
 				} while (oldpos == pos + e->next_offset);
 
 				/* Move along one */
 				size = e->next_offset;
-				e = (struct ip6t_entry *)
-					(entry0 + pos + size);
+				e = entry0 + pos + size;
 				if (pos + size >= newinfo->size)
 					return 0;
 				e->counters.pcnt = pos;
@@ -475,16 +464,14 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					if (!xt_find_jump_offset(offsets, newpos,
 								 newinfo->number))
 						return 0;
-					e = (struct ip6t_entry *)
-						(entry0 + newpos);
+					e = entry0 + newpos;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
 					if (newpos >= newinfo->size)
 						return 0;
 				}
-				e = (struct ip6t_entry *)
-					(entry0 + newpos);
+				e = entry0 + newpos;
 				e->counters.pcnt = pos;
 				pos = newpos;
 			}
@@ -863,7 +850,7 @@ copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_match *m;
 		const struct xt_entry_target *t;
 
-		e = (struct ip6t_entry *)(loc_cpu_entry + off);
+		e = loc_cpu_entry + off;
 		if (copy_to_user(userptr + off, e, sizeof(*e))) {
 			ret = -EFAULT;
 			goto free_counters;
@@ -1258,7 +1245,7 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr,
 	int ret = 0;
 
 	origsize = *size;
-	ce = (struct compat_ip6t_entry __user *)*dstptr;
+	ce = *dstptr;
 	if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 ||
 	    copy_to_user(&ce->counters, &counters[i],
 	    sizeof(counters[i])) != 0)
@@ -1394,7 +1381,7 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 	struct xt_entry_match *ematch;
 
 	origsize = *size;
-	de = (struct ip6t_entry *)*dstptr;
+	de = *dstptr;
 	memcpy(de, e, sizeof(struct ip6t_entry));
 	memcpy(&de->counters, &e->counters, sizeof(e->counters));
 
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 4ef1ddd4bbbd..d3c4daa708b9 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -307,12 +307,17 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 					  XT_SYNPROXY_OPT_ECN);
 
 		synproxy_send_client_synack(net, skb, th, &opts);
-		return NF_DROP;
+		consume_skb(skb);
+		return NF_STOLEN;
 
 	} else if (th->ack && !(th->fin || th->rst || th->syn)) {
 		/* ACK from client */
-		synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq));
-		return NF_DROP;
+		if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq))) {
+			consume_skb(skb);
+			return NF_STOLEN;
+		} else {
+			return NF_DROP;
+		}
 	}
 
 	return XT_CONTINUE;
@@ -388,10 +393,13 @@ static unsigned int ipv6_synproxy_hook(void *priv,
 			 * number match the one of first SYN.
 			 */
 			if (synproxy_recv_client_ack(net, skb, th, &opts,
-						     ntohl(th->seq) + 1))
+						     ntohl(th->seq) + 1)) {
 				this_cpu_inc(snet->stats->cookie_retrans);
-
-			return NF_DROP;
+				consume_skb(skb);
+				return NF_STOLEN;
+			} else {
+				return NF_DROP;
+			}
 		}
 
 		synproxy->isn = ntohl(th->ack_seq);
@@ -430,20 +438,57 @@ static unsigned int ipv6_synproxy_hook(void *priv,
 	return NF_ACCEPT;
 }
 
+static struct nf_hook_ops ipv6_synproxy_ops[] __read_mostly = {
+	{
+		.hook		= ipv6_synproxy_hook,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
+	},
+	{
+		.hook		= ipv6_synproxy_hook,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
+	},
+};
+
 static int synproxy_tg6_check(const struct xt_tgchk_param *par)
 {
+	struct synproxy_net *snet = synproxy_pernet(par->net);
 	const struct ip6t_entry *e = par->entryinfo;
+	int err;
 
 	if (!(e->ipv6.flags & IP6T_F_PROTO) ||
 	    e->ipv6.proto != IPPROTO_TCP ||
 	    e->ipv6.invflags & XT_INV_PROTO)
 		return -EINVAL;
 
-	return nf_ct_netns_get(par->net, par->family);
+	err = nf_ct_netns_get(par->net, par->family);
+	if (err)
+		return err;
+
+	if (snet->hook_ref6 == 0) {
+		err = nf_register_net_hooks(par->net, ipv6_synproxy_ops,
+					    ARRAY_SIZE(ipv6_synproxy_ops));
+		if (err) {
+			nf_ct_netns_put(par->net, par->family);
+			return err;
+		}
+	}
+
+	snet->hook_ref6++;
+	return err;
 }
 
 static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par)
 {
+	struct synproxy_net *snet = synproxy_pernet(par->net);
+
+	snet->hook_ref6--;
+	if (snet->hook_ref6 == 0)
+		nf_unregister_net_hooks(par->net, ipv6_synproxy_ops,
+					ARRAY_SIZE(ipv6_synproxy_ops));
 	nf_ct_netns_put(par->net, par->family);
 }
 
@@ -458,46 +503,14 @@ static struct xt_target synproxy_tg6_reg __read_mostly = {
 	.me		= THIS_MODULE,
 };
 
-static struct nf_hook_ops ipv6_synproxy_ops[] __read_mostly = {
-	{
-		.hook		= ipv6_synproxy_hook,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
-	},
-	{
-		.hook		= ipv6_synproxy_hook,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM - 1,
-	},
-};
-
 static int __init synproxy_tg6_init(void)
 {
-	int err;
-
-	err = nf_register_hooks(ipv6_synproxy_ops,
-				ARRAY_SIZE(ipv6_synproxy_ops));
-	if (err < 0)
-		goto err1;
-
-	err = xt_register_target(&synproxy_tg6_reg);
-	if (err < 0)
-		goto err2;
-
-	return 0;
-
-err2:
-	nf_unregister_hooks(ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops));
-err1:
-	return err;
+	return xt_register_target(&synproxy_tg6_reg);
 }
 
 static void __exit synproxy_tg6_exit(void)
 {
 	xt_unregister_target(&synproxy_tg6_reg);
-	nf_unregister_hooks(ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops));
 }
 
 module_init(synproxy_tg6_init);
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index d2c2ccbfbe72..d5f028e33f65 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -221,8 +221,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl,
 	type = icmp6h->icmp6_type - 130;
 	if (type >= 0 && type < sizeof(noct_valid_new) &&
 	    noct_valid_new[type]) {
-		nf_ct_set(skb, nf_ct_untracked_get(), IP_CT_NEW);
-		nf_conntrack_get(skb_nfct(skb));
+		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 		return NF_ACCEPT;
 	}
 
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 888ecd106e5f..4a7ddeddbaab 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -58,8 +58,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_reset(skb);
-	nf_ct_set(skb, nf_ct_untracked_get(), IP_CT_NEW);
-	nf_conntrack_get(skb_nfct(skb));
+	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 #endif
 	if (hooknum == NF_INET_PRE_ROUTING ||
 	    hooknum == NF_INET_LOCAL_IN) {
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index e0be97e636a4..bf3ad3e7b647 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -273,13 +273,7 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb,
 	if (!ct)
 		return NF_ACCEPT;
 
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
+	nat = nfct_nat(ct);
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 051b6a6bfff6..2297c9f073ba 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -30,6 +30,7 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
 		       const struct net_device *out)
 {
 	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
 	struct in6_addr src;
 	struct nf_conn *ct;
 	struct nf_nat_range newrange;
@@ -42,7 +43,9 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
 			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
 		return NF_DROP;
 
-	nfct_nat(ct)->masq_index = out->ifindex;
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat)
+		nat->masq_index = out->ifindex;
 
 	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
 	newrange.min_addr.in6	= src;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 765facf03d45..43f91d9b086c 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -159,7 +159,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
 	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
-		nft_fib_store_result(dest, priv->result, pkt,
+		nft_fib_store_result(dest, priv, pkt,
 				     nft_in(pkt)->ifindex);
 		return;
 	}
@@ -246,7 +246,7 @@ nft_fib6_select_ops(const struct nft_ctx *ctx,
 
 static struct nft_expr_type nft_fib6_type __read_mostly = {
 	.name		= "fib",
-	.select_ops	= &nft_fib6_select_ops,
+	.select_ops	= nft_fib6_select_ops,
 	.policy		= nft_fib_policy,
 	.maxattr	= NFTA_FIB_MAX,
 	.family		= NFPROTO_IPV6,
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index 6c5b5b1830a7..4146536e9c15 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -27,10 +27,10 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
 	memset(&range, 0, sizeof(range));
 	range.flags = priv->flags;
 	if (priv->sreg_proto_min) {
-		range.min_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min];
-		range.max_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 	}
 	regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range,
 						    nft_out(pkt));
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index f5ac080fc084..a27e424f690d 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -26,10 +26,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
 
 	memset(&range, 0, sizeof(range));
 	if (priv->sreg_proto_min) {
-		range.min_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min],
-		range.max_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max],
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index e3770abe688a..b5d54d4f995c 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -26,7 +26,7 @@
 #include <net/protocol.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
+struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
 EXPORT_SYMBOL(inet6_protos);
 
 int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index f174e76e6505..0da6a12b5472 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1178,8 +1178,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb_tail_pointer(skb) -
-				skb_transport_header(skb);
+			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 229bfcc451ef..a1bf426c959b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1854,6 +1854,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 	int addr_type;
 	int err = -EINVAL;
 
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU)
+		goto out;
+
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
 		goto out;
 #ifndef CONFIG_IPV6_SUBTREES
@@ -2906,7 +2910,8 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int pref;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
+			  NULL);
 	if (err < 0)
 		goto errout;
 
@@ -3259,7 +3264,8 @@ static int ip6_route_multipath_del(struct fib6_config *cfg)
 	return last_err;
 }
 
-static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
 	struct fib6_config cfg;
 	int err;
@@ -3276,7 +3282,8 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 }
 
-static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
 	struct fib6_config cfg;
 	int err;
@@ -3299,7 +3306,6 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
 		nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
 			    + NLA_ALIGN(sizeof(struct rtnexthop))
 			    + nla_total_size(16) /* RTA_GATEWAY */
-			    + nla_total_size(4)  /* RTA_OIF */
 			    + lwtunnel_get_encap_size(rt->dst.lwtstate);
 
 		nexthop_len *= rt->rt6i_nsiblings;
@@ -3323,7 +3329,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
 }
 
 static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
-			    unsigned int *flags)
+			    unsigned int *flags, bool skip_oif)
 {
 	if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
 		*flags |= RTNH_F_LINKDOWN;
@@ -3336,7 +3342,8 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
 			goto nla_put_failure;
 	}
 
-	if (rt->dst.dev &&
+	/* not needed for multipath encoding b/c it has a rtnexthop struct */
+	if (!skip_oif && rt->dst.dev &&
 	    nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
 		goto nla_put_failure;
 
@@ -3350,6 +3357,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+/* add multipath next hop */
 static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
 {
 	struct rtnexthop *rtnh;
@@ -3362,7 +3370,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
 	rtnh->rtnh_hops = 0;
 	rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
 
-	if (rt6_nexthop_info(skb, rt, &flags) < 0)
+	if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
 		goto nla_put_failure;
 
 	rtnh->rtnh_flags = flags;
@@ -3422,6 +3430,8 @@ static int rt6_fill_node(struct net *net,
 	}
 	else if (rt->rt6i_flags & RTF_LOCAL)
 		rtm->rtm_type = RTN_LOCAL;
+	else if (rt->rt6i_flags & RTF_ANYCAST)
+		rtm->rtm_type = RTN_ANYCAST;
 	else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
 		rtm->rtm_type = RTN_LOCAL;
 	else
@@ -3515,7 +3525,7 @@ static int rt6_fill_node(struct net *net,
 
 		nla_nest_end(skb, mp);
 	} else {
-		if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0)
+		if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0)
 			goto nla_put_failure;
 	}
 
@@ -3561,7 +3571,8 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
 		     NLM_F_MULTI);
 }
 
-static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
+static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[RTA_MAX+1];
@@ -3571,7 +3582,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	struct flowi6 fl6;
 	int err, iif = 0, oif = 0;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
+			  extack);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index a855eb325b03..5f44ffed2576 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -53,6 +53,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
 		struct sr6_tlv *tlv;
 		unsigned int tlv_len;
 
+		if (trailing < sizeof(*tlv))
+			return false;
+
 		tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset);
 		tlv_len = sizeof(*tlv) + tlv->len;
 
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 85582257d3af..6a495490d43e 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -26,17 +26,13 @@
 #include <linux/seg6_iptunnel.h>
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
-#ifdef CONFIG_DST_CACHE
 #include <net/dst_cache.h>
-#endif
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
 
 struct seg6_lwt {
-#ifdef CONFIG_DST_CACHE
 	struct dst_cache cache;
-#endif
 	struct seg6_iptunnel_encap tuninfo[0];
 };
 
@@ -105,7 +101,7 @@ static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 	hdrlen = (osrh->hdrlen + 1) << 3;
 	tot_len = hdrlen + sizeof(*hdr);
 
-	err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC);
+	err = skb_cow_head(skb, tot_len);
 	if (unlikely(err))
 		return err;
 
@@ -156,7 +152,7 @@ static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 
 	hdrlen = (osrh->hdrlen + 1) << 3;
 
-	err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC);
+	err = skb_cow_head(skb, hdrlen);
 	if (unlikely(err))
 		return err;
 
@@ -237,6 +233,9 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 static int seg6_input(struct sk_buff *skb)
 {
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct dst_entry *dst = NULL;
+	struct seg6_lwt *slwt;
 	int err;
 
 	err = seg6_do_srh(skb);
@@ -245,8 +244,30 @@ static int seg6_input(struct sk_buff *skb)
 		return err;
 	}
 
+	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+
+	preempt_disable();
+	dst = dst_cache_get(&slwt->cache);
+	preempt_enable();
+
 	skb_dst_drop(skb);
-	ip6_route_input(skb);
+
+	if (!dst) {
+		ip6_route_input(skb);
+		dst = skb_dst(skb);
+		if (!dst->error) {
+			preempt_disable();
+			dst_cache_set_ip6(&slwt->cache, dst,
+					  &ipv6_hdr(skb)->saddr);
+			preempt_enable();
+		}
+	} else {
+		skb_dst_set(skb, dst);
+	}
+
+	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+	if (unlikely(err))
+		return err;
 
 	return dst_input(skb);
 }
@@ -264,11 +285,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
-#ifdef CONFIG_DST_CACHE
 	preempt_disable();
 	dst = dst_cache_get(&slwt->cache);
 	preempt_enable();
-#endif
 
 	if (unlikely(!dst)) {
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -287,16 +306,18 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 		}
 
-#ifdef CONFIG_DST_CACHE
 		preempt_disable();
 		dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
 		preempt_enable();
-#endif
 	}
 
 	skb_dst_drop(skb);
 	skb_dst_set(skb, dst);
 
+	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+	if (unlikely(err))
+		goto drop;
+
 	return dst_output(net, sk, skb);
 drop:
 	kfree_skb(skb);
@@ -315,7 +336,7 @@ static int seg6_build_state(struct nlattr *nla,
 	int err;
 
 	err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla,
-			       seg6_iptunnel_policy);
+			       seg6_iptunnel_policy, NULL);
 
 	if (err < 0)
 		return err;
@@ -355,13 +376,11 @@ static int seg6_build_state(struct nlattr *nla,
 
 	slwt = seg6_lwt_lwtunnel(newts);
 
-#ifdef CONFIG_DST_CACHE
 	err = dst_cache_init(&slwt->cache, GFP_KERNEL);
 	if (err) {
 		kfree(newts);
 		return err;
 	}
-#endif
 
 	memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
 
@@ -375,12 +394,10 @@ static int seg6_build_state(struct nlattr *nla,
 	return 0;
 }
 
-#ifdef CONFIG_DST_CACHE
 static void seg6_destroy_state(struct lwtunnel_state *lwt)
 {
 	dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
 }
-#endif
 
 static int seg6_fill_encap_info(struct sk_buff *skb,
 				struct lwtunnel_state *lwtstate)
@@ -414,9 +431,7 @@ static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
 
 static const struct lwtunnel_encap_ops seg6_iptun_ops = {
 	.build_state = seg6_build_state,
-#ifdef CONFIG_DST_CACHE
 	.destroy_state = seg6_destroy_state,
-#endif
 	.output = seg6_output,
 	.input = seg6_input,
 	.fill_encap = seg6_fill_encap_info,
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 99853c6e33a8..61e5902f0687 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -881,11 +881,12 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			goto tx_error;
 	}
 
-	rt = ip_route_output_ports(tunnel->net, &fl4, NULL,
-				   dst, tiph->saddr,
-				   0, 0,
-				   IPPROTO_IPV6, RT_TOS(tos),
-				   tunnel->parms.link);
+	flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark,
+			   RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6,
+			   0, dst, tiph->saddr, 0, 0,
+			   sock_net_uid(tunnel->net, NULL));
+	rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
+
 	if (IS_ERR(rt)) {
 		dev->stats.tx_carrier_errors++;
 		goto tx_error_icmp;
@@ -1071,7 +1072,8 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	}
 }
 
-static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
+static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p,
+				__u32 fwmark)
 {
 	struct net *net = t->net;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
@@ -1085,8 +1087,9 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 	ipip6_tunnel_link(sitn, t);
 	t->parms.iph.ttl = p->iph.ttl;
 	t->parms.iph.tos = p->iph.tos;
-	if (t->parms.link != p->link) {
+	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		t->parms.link = p->link;
+		t->fwmark = fwmark;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
 	dst_cache_reset(&t->dst_cache);
@@ -1220,7 +1223,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 				t = netdev_priv(dev);
 			}
 
-			ipip6_tunnel_update(t, &p);
+			ipip6_tunnel_update(t, &p, t->fwmark);
 		}
 
 		if (t) {
@@ -1418,7 +1421,8 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
 }
 
 static void ipip6_netlink_parms(struct nlattr *data[],
-				struct ip_tunnel_parm *parms)
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
 {
 	memset(parms, 0, sizeof(*parms));
 
@@ -1457,6 +1461,8 @@ static void ipip6_netlink_parms(struct nlattr *data[],
 	if (data[IFLA_IPTUN_PROTO])
 		parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
 
+	if (data[IFLA_IPTUN_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
 /* This function returns true when ENCAP attributes are present in the nl msg */
@@ -1549,7 +1555,7 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	ipip6_netlink_parms(data, &nt->parms);
+	ipip6_netlink_parms(data, &nt->parms, &nt->fwmark);
 
 	if (ipip6_tunnel_locate(net, &nt->parms, 0))
 		return -EEXIST;
@@ -1577,6 +1583,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
+	__u32 fwmark = t->fwmark;
 	int err;
 
 	if (dev == sitn->fb_tunnel_dev)
@@ -1588,7 +1595,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 			return err;
 	}
 
-	ipip6_netlink_parms(data, &p);
+	ipip6_netlink_parms(data, &p, &fwmark);
 
 	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
 	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
@@ -1602,7 +1609,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 	} else
 		t = netdev_priv(dev);
 
-	ipip6_tunnel_update(t, &p);
+	ipip6_tunnel_update(t, &p, fwmark);
 
 #ifdef CONFIG_IPV6_SIT_6RD
 	if (ipip6_netlink_6rd_parms(data, &ip6rd))
@@ -1649,6 +1656,8 @@ static size_t ipip6_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_IPTUN_ENCAP_DPORT */
 		nla_total_size(2) +
+		/* IFLA_IPTUN_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1665,7 +1674,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
 		       !!(parm->iph.frag_off & htons(IP_DF))) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
-	    nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags))
+	    nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) ||
+	    nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark))
 		goto nla_put_failure;
 
 #ifdef CONFIG_IPV6_SIT_6RD
@@ -1715,6 +1725,7 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_FWMARK]		= { .type = NLA_U32 },
 };
 
 static void ipip6_dellink(struct net_device *dev, struct list_head *head)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 60a5295a7de6..8e42e8f54b70 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
 {
-	return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
-					    ipv6_hdr(skb)->saddr.s6_addr32,
-					    tcp_hdr(skb)->dest,
-					    tcp_hdr(skb)->source, tsoff);
+	return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32,
+					  ipv6_hdr(skb)->saddr.s6_addr32,
+					  tcp_hdr(skb)->dest,
+					  tcp_hdr(skb)->source, tsoff);
 }
 
 static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
@@ -265,11 +265,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk->sk_gso_type = SKB_GSO_TCPV6;
 	ip6_dst_store(sk, dst, NULL, NULL);
 
-	if (tcp_death_row->sysctl_tw_recycle &&
-	    !tp->rx_opt.ts_recent_stamp &&
-	    ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
-		tcp_fetch_timewait_stamp(sk, dst);
-
 	icsk->icsk_ext_hdr_len = 0;
 	if (opt)
 		icsk->icsk_ext_hdr_len = opt->opt_flen +
@@ -287,11 +282,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk_set_txhash(sk);
 
 	if (likely(!tp->repair)) {
-		seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-						   sk->sk_v6_daddr.s6_addr32,
-						   inet->inet_sport,
-						   inet->inet_dport,
-						   &tp->tsoffset);
+		seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32,
+						 sk->sk_v6_daddr.s6_addr32,
+						 inet->inet_sport,
+						 inet->inet_dport,
+						 &tp->tsoffset);
 		if (!tp->write_seq)
 			tp->write_seq = seq;
 	}
@@ -391,10 +386,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
@@ -725,11 +722,8 @@ static void tcp_v6_init_req(struct request_sock *req,
 
 static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
 					  struct flowi *fl,
-					  const struct request_sock *req,
-					  bool *strict)
+					  const struct request_sock *req)
 {
-	if (strict)
-		*strict = true;
 	return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
 }
 
@@ -755,7 +749,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.cookie_init_seq =	cookie_v6_init_sequence,
 #endif
 	.route_req	=	tcp_v6_route_req,
-	.init_seq	=	tcp_v6_init_sequence,
+	.init_seq_tsoff	=	tcp_v6_init_seq_and_tsoff,
 	.send_synack	=	tcp_v6_send_synack,
 };
 
@@ -1299,8 +1293,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 			goto discard;
 
 		if (nsk != sk) {
-			sock_rps_save_rxhash(nsk, skb);
-			sk_mark_napi_id(nsk, skb);
 			if (tcp_child_process(sk, nsk, skb))
 				goto reset;
 			if (opt_skb)
@@ -1931,8 +1923,9 @@ struct proto tcpv6_prot = {
 	.diag_destroy		= tcp_abort,
 };
 
-static const struct inet6_protocol tcpv6_protocol = {
+static struct inet6_protocol tcpv6_protocol = {
 	.early_demux	=	tcp_v6_early_demux,
+	.early_demux_handler =  tcp_v6_early_demux,
 	.handler	=	tcp_v6_rcv,
 	.err_handler	=	tcp_v6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4e4c401e3bc6..04862abfe4ec 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
 #include <net/tcp_states.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
+#include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
 #include <net/busy_poll.h>
 #include <net/sock_reuseport.h>
@@ -864,6 +865,69 @@ discard:
 	return 0;
 }
 
+
+static struct sock *__udp6_lib_demux_lookup(struct net *net,
+			__be16 loc_port, const struct in6_addr *loc_addr,
+			__be16 rmt_port, const struct in6_addr *rmt_addr,
+			int dif)
+{
+	unsigned short hnum = ntohs(loc_port);
+	unsigned int hash2 = udp6_portaddr_hash(net, loc_addr, hnum);
+	unsigned int slot2 = hash2 & udp_table.mask;
+	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
+	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+	struct sock *sk;
+
+	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
+		if (INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif))
+			return sk;
+		/* Only check first socket in chain */
+		break;
+	}
+	return NULL;
+}
+
+static void udp_v6_early_demux(struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	const struct udphdr *uh;
+	struct sock *sk;
+	struct dst_entry *dst;
+	int dif = skb->dev->ifindex;
+
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) +
+	    sizeof(struct udphdr)))
+		return;
+
+	uh = udp_hdr(skb);
+
+	if (skb->pkt_type == PACKET_HOST)
+		sk = __udp6_lib_demux_lookup(net, uh->dest,
+					     &ipv6_hdr(skb)->daddr,
+					     uh->source, &ipv6_hdr(skb)->saddr,
+					     dif);
+	else
+		return;
+
+	if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2))
+		return;
+
+	skb->sk = sk;
+	skb->destructor = sock_efree;
+	dst = READ_ONCE(sk->sk_rx_dst);
+
+	if (dst)
+		dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
+	if (dst) {
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
+}
+
 static __inline__ int udpv6_rcv(struct sk_buff *skb)
 {
 	return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
@@ -1035,6 +1099,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.hlimit = -1;
 	ipc6.tclass = -1;
 	ipc6.dontfrag = -1;
+	sockc.tsflags = sk->sk_tsflags;
 
 	/* destination address check */
 	if (sin6) {
@@ -1159,7 +1224,6 @@ do_udp_sendmsg:
 
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.flowi6_uid = sk->sk_uid;
-	sockc.tsflags = sk->sk_tsflags;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
@@ -1378,7 +1442,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 }
 #endif
 
-static const struct inet6_protocol udpv6_protocol = {
+static struct inet6_protocol udpv6_protocol = {
+	.early_demux	=	udp_v6_early_demux,
+	.early_demux_handler =  udp_v6_early_demux,
 	.handler	=	udpv6_rcv,
 	.err_handler	=	udpv6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 4439ee44c8b0..7a92c0f31912 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -13,6 +13,7 @@
 #include <net/dst.h>
 #include <net/ipv6.h>
 #include <net/xfrm.h>
+#include <net/protocol.h>
 
 /* Add encapsulation header.
  *
@@ -26,6 +27,7 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	int hdr_len;
 
 	iph = ipv6_hdr(skb);
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
 
 	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
 	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
@@ -61,9 +63,41 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
+static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
+						   struct sk_buff *skb,
+						   netdev_features_t features)
+{
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb->transport_header += x->props.header_len;
+	ops = rcu_dereference(inet6_offloads[xo->proto]);
+	if (likely(ops && ops->callbacks.gso_segment))
+		segs = ops->callbacks.gso_segment(skb, features);
+
+	return segs;
+}
+
+static void xfrm6_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + sizeof(struct ipv6hdr) + x->props.header_len);
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		 skb_reset_transport_header(skb);
+		 skb->transport_header -= x->props.header_len;
+	}
+}
+
+
 static struct xfrm_mode xfrm6_transport_mode = {
 	.input = xfrm6_transport_input,
 	.output = xfrm6_transport_output,
+	.gso_segment = xfrm4_transport_gso_segment,
+	.xmit = xfrm6_transport_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
 };
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 372855eeaf42..02556e356f87 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -36,6 +36,9 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct ipv6hdr *top_iph;
 	int dsfield;
 
+	skb_set_inner_network_header(skb, skb_network_offset(skb));
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
 			  offsetof(struct ipv6hdr, nexthdr);
@@ -96,11 +99,35 @@ out:
 	return err;
 }
 
+static struct sk_buff *xfrm6_mode_tunnel_gso_segment(struct xfrm_state *x,
+						     struct sk_buff *skb,
+						     netdev_features_t features)
+{
+	__skb_push(skb, skb->mac_len);
+	return skb_mac_gso_segment(skb, features);
+
+}
+
+static void xfrm6_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		skb->network_header = skb->network_header - x->props.header_len;
+		skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
+	}
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + x->props.header_len);
+}
+
 static struct xfrm_mode xfrm6_tunnel_mode = {
 	.input2 = xfrm6_mode_tunnel_input,
 	.input = xfrm_prepare_input,
 	.output2 = xfrm6_mode_tunnel_output,
 	.output = xfrm6_prepare_output,
+	.gso_segment = xfrm6_mode_tunnel_gso_segment,
+	.xmit = xfrm6_mode_tunnel_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 4d09ce6fa90e..8ae87d4ec5ff 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -73,11 +73,16 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 	int mtu, ret = 0;
 	struct dst_entry *dst = skb_dst(skb);
 
+	if (skb->ignore_df)
+		goto out;
+
 	mtu = dst_mtu(dst);
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (!skb->ignore_df && skb->len > mtu) {
+	if ((!skb_is_gso(skb) && skb->len > mtu) ||
+	    (skb_is_gso(skb) &&
+	     skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) {
 		skb->dev = dst->dev;
 		skb->protocol = htons(ETH_P_IPV6);
 
@@ -89,7 +94,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		ret = -EMSGSIZE;
 	}
-
+out:
 	return ret;
 }
 
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 8a9219ff2e77..fa31ef29e3fa 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1168,11 +1168,10 @@ static int ipxitf_ioctl(unsigned int cmd, void __user *arg)
 		sipx->sipx_network	= ipxif->if_netnum;
 		memcpy(sipx->sipx_node, ipxif->if_node,
 			sizeof(sipx->sipx_node));
-		rc = -EFAULT;
+		rc = 0;
 		if (copy_to_user(arg, &ifr, sizeof(ifr)))
-			break;
+			rc = -EFAULT;
 		ipxitf_put(ipxif);
-		rc = 0;
 		break;
 	}
 	case SIOCAIPXITFCRT:
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 81adc29a448d..8d77ad5cadaf 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -828,7 +828,8 @@ out:
  *    Wait for incoming connection
  *
  */
-static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
+static int irda_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *new, *self = irda_sk(sk);
@@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct sk_buff *skb = NULL;
 	int err;
 
-	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
+	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern);
 	if (err)
 		return err;
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 89bbde1081ce..84de7b6326dc 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -938,7 +938,7 @@ done:
 
 /* Accept a pending connection */
 static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
-			    int flags)
+			    int flags, bool kern)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *nsk;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 309062f3debe..deca20fb2ce2 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1687,7 +1687,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_attach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_attach_ioctl(sock, &info);
 
@@ -1697,7 +1697,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_unattach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_unattach_ioctl(sock, &info);
 
@@ -1707,11 +1707,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_clone info;
 		struct socket *newsock = NULL;
 
-		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
-
 		err = kcm_clone(sock, &info, &newsock);
-
 		if (!err) {
 			if (copy_to_user((void __user *)arg, &info,
 					 sizeof(info))) {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index c6252ed42c1d..c1950bb14735 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -63,8 +63,13 @@ struct pfkey_sock {
 		} u;
 		struct sk_buff	*skb;
 	} dump;
+	struct mutex dump_lock;
 };
 
+static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
+			       xfrm_address_t *saddr, xfrm_address_t *daddr,
+			       u16 *family);
+
 static inline struct pfkey_sock *pfkey_sk(struct sock *sk)
 {
 	return (struct pfkey_sock *)sk;
@@ -139,6 +144,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
 	struct sock *sk;
+	struct pfkey_sock *pfk;
 	int err;
 
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -153,6 +159,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 	if (sk == NULL)
 		goto out;
 
+	pfk = pfkey_sk(sk);
+	mutex_init(&pfk->dump_lock);
+
 	sock->ops = &pfkey_ops;
 	sock_init_data(sock, sk);
 
@@ -281,13 +290,23 @@ static int pfkey_do_dump(struct pfkey_sock *pfk)
 	struct sadb_msg *hdr;
 	int rc;
 
+	mutex_lock(&pfk->dump_lock);
+	if (!pfk->dump.dump) {
+		rc = 0;
+		goto out;
+	}
+
 	rc = pfk->dump.dump(pfk);
-	if (rc == -ENOBUFS)
-		return 0;
+	if (rc == -ENOBUFS) {
+		rc = 0;
+		goto out;
+	}
 
 	if (pfk->dump.skb) {
-		if (!pfkey_can_dump(&pfk->sk))
-			return 0;
+		if (!pfkey_can_dump(&pfk->sk)) {
+			rc = 0;
+			goto out;
+		}
 
 		hdr = (struct sadb_msg *) pfk->dump.skb->data;
 		hdr->sadb_msg_seq = 0;
@@ -298,6 +317,9 @@ static int pfkey_do_dump(struct pfkey_sock *pfk)
 	}
 
 	pfkey_terminate_dump(pfk);
+
+out:
+	mutex_unlock(&pfk->dump_lock);
 	return rc;
 }
 
@@ -1793,19 +1815,26 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	struct xfrm_address_filter *filter = NULL;
 	struct pfkey_sock *pfk = pfkey_sk(sk);
 
-	if (pfk->dump.dump != NULL)
+	mutex_lock(&pfk->dump_lock);
+	if (pfk->dump.dump != NULL) {
+		mutex_unlock(&pfk->dump_lock);
 		return -EBUSY;
+	}
 
 	proto = pfkey_satype2proto(hdr->sadb_msg_satype);
-	if (proto == 0)
+	if (proto == 0) {
+		mutex_unlock(&pfk->dump_lock);
 		return -EINVAL;
+	}
 
 	if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
 		struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
 
 		filter = kmalloc(sizeof(*filter), GFP_KERNEL);
-		if (filter == NULL)
+		if (filter == NULL) {
+			mutex_unlock(&pfk->dump_lock);
 			return -ENOMEM;
+		}
 
 		memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr,
 		       sizeof(xfrm_address_t));
@@ -1821,6 +1850,7 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	pfk->dump.dump = pfkey_dump_sa;
 	pfk->dump.done = pfkey_dump_sa_done;
 	xfrm_state_walk_init(&pfk->dump.u.state, proto, filter);
+	mutex_unlock(&pfk->dump_lock);
 
 	return pfkey_do_dump(pfk);
 }
@@ -1913,19 +1943,14 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
 
 	/* addresses present only in tunnel mode */
 	if (t->mode == XFRM_MODE_TUNNEL) {
-		u8 *sa = (u8 *) (rq + 1);
-		int family, socklen;
+		int err;
 
-		family = pfkey_sockaddr_extract((struct sockaddr *)sa,
-						&t->saddr);
-		if (!family)
-			return -EINVAL;
-
-		socklen = pfkey_sockaddr_len(family);
-		if (pfkey_sockaddr_extract((struct sockaddr *)(sa + socklen),
-					   &t->id.daddr) != family)
-			return -EINVAL;
-		t->encap_family = family;
+		err = parse_sockaddr_pair(
+			(struct sockaddr *)(rq + 1),
+			rq->sadb_x_ipsecrequest_len - sizeof(*rq),
+			&t->saddr, &t->id.daddr, &t->encap_family);
+		if (err)
+			return err;
 	} else
 		t->encap_family = xp->family;
 
@@ -1945,7 +1970,11 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol)
 	if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy))
 		return -EINVAL;
 
-	while (len >= sizeof(struct sadb_x_ipsecrequest)) {
+	while (len >= sizeof(*rq)) {
+		if (len < rq->sadb_x_ipsecrequest_len ||
+		    rq->sadb_x_ipsecrequest_len < sizeof(*rq))
+			return -EINVAL;
+
 		if ((err = parse_ipsecrequest(xp, rq)) < 0)
 			return err;
 		len -= rq->sadb_x_ipsecrequest_len;
@@ -2408,7 +2437,6 @@ out:
 	return err;
 }
 
-#ifdef CONFIG_NET_KEY_MIGRATE
 static int pfkey_sockaddr_pair_size(sa_family_t family)
 {
 	return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2);
@@ -2420,7 +2448,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
 {
 	int af, socklen;
 
-	if (ext_len < pfkey_sockaddr_pair_size(sa->sa_family))
+	if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family))
 		return -EINVAL;
 
 	af = pfkey_sockaddr_extract(sa, saddr);
@@ -2436,6 +2464,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
 	return 0;
 }
 
+#ifdef CONFIG_NET_KEY_MIGRATE
 static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 				    struct xfrm_migrate *m)
 {
@@ -2443,13 +2472,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 	struct sadb_x_ipsecrequest *rq2;
 	int mode;
 
-	if (len <= sizeof(struct sadb_x_ipsecrequest) ||
-	    len < rq1->sadb_x_ipsecrequest_len)
+	if (len < sizeof(*rq1) ||
+	    len < rq1->sadb_x_ipsecrequest_len ||
+	    rq1->sadb_x_ipsecrequest_len < sizeof(*rq1))
 		return -EINVAL;
 
 	/* old endoints */
 	err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1),
-				  rq1->sadb_x_ipsecrequest_len,
+				  rq1->sadb_x_ipsecrequest_len - sizeof(*rq1),
 				  &m->old_saddr, &m->old_daddr,
 				  &m->old_family);
 	if (err)
@@ -2458,13 +2488,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 	rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len);
 	len -= rq1->sadb_x_ipsecrequest_len;
 
-	if (len <= sizeof(struct sadb_x_ipsecrequest) ||
-	    len < rq2->sadb_x_ipsecrequest_len)
+	if (len <= sizeof(*rq2) ||
+	    len < rq2->sadb_x_ipsecrequest_len ||
+	    rq2->sadb_x_ipsecrequest_len < sizeof(*rq2))
 		return -EINVAL;
 
 	/* new endpoints */
 	err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1),
-				  rq2->sadb_x_ipsecrequest_len,
+				  rq2->sadb_x_ipsecrequest_len - sizeof(*rq2),
 				  &m->new_saddr, &m->new_daddr,
 				  &m->new_family);
 	if (err)
@@ -2679,14 +2710,18 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb
 {
 	struct pfkey_sock *pfk = pfkey_sk(sk);
 
-	if (pfk->dump.dump != NULL)
+	mutex_lock(&pfk->dump_lock);
+	if (pfk->dump.dump != NULL) {
+		mutex_unlock(&pfk->dump_lock);
 		return -EBUSY;
+	}
 
 	pfk->dump.msg_version = hdr->sadb_msg_version;
 	pfk->dump.msg_portid = hdr->sadb_msg_pid;
 	pfk->dump.dump = pfkey_dump_sp;
 	pfk->dump.done = pfkey_dump_sp_done;
 	xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN);
+	mutex_unlock(&pfk->dump_lock);
 
 	return pfkey_do_dump(pfk);
 }
@@ -3792,7 +3827,6 @@ static inline void pfkey_exit_proc(struct net *net)
 
 static struct xfrm_mgr pfkeyv2_mgr =
 {
-	.id		= "pfkeyv2",
 	.notify		= pfkey_send_notify,
 	.acquire	= pfkey_send_acquire,
 	.compile_policy	= pfkey_compile_policy,
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 8adab6335ced..fa0342574b89 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -120,7 +120,7 @@ static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
 	return sk->sk_user_data;
 }
 
-static inline struct l2tp_net *l2tp_pernet(struct net *net)
+static inline struct l2tp_net *l2tp_pernet(const struct net *net)
 {
 	BUG_ON(!net);
 
@@ -217,27 +217,6 @@ static void l2tp_tunnel_sock_put(struct sock *sk)
 	sock_put(sk);
 }
 
-/* Lookup a session by id in the global session list
- */
-static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
-{
-	struct l2tp_net *pn = l2tp_pernet(net);
-	struct hlist_head *session_list =
-		l2tp_session_id_hash_2(pn, session_id);
-	struct l2tp_session *session;
-
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu(session, session_list, global_hlist) {
-		if (session->session_id == session_id) {
-			rcu_read_unlock_bh();
-			return session;
-		}
-	}
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-
 /* Session hash list.
  * The session_id SHOULD be random according to RFC2661, but several
  * L2TP implementations (Cisco and Microsoft) use incrementing
@@ -250,25 +229,46 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
 	return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)];
 }
 
-/* Lookup a session by id
+/* Lookup a session. A new reference is held on the returned session.
+ * Optionally calls session->ref() too if do_ref is true.
  */
-struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id)
+struct l2tp_session *l2tp_session_get(const struct net *net,
+				      struct l2tp_tunnel *tunnel,
+				      u32 session_id, bool do_ref)
 {
 	struct hlist_head *session_list;
 	struct l2tp_session *session;
 
-	/* In L2TPv3, session_ids are unique over all tunnels and we
-	 * sometimes need to look them up before we know the
-	 * tunnel.
-	 */
-	if (tunnel == NULL)
-		return l2tp_session_find_2(net, session_id);
+	if (!tunnel) {
+		struct l2tp_net *pn = l2tp_pernet(net);
+
+		session_list = l2tp_session_id_hash_2(pn, session_id);
+
+		rcu_read_lock_bh();
+		hlist_for_each_entry_rcu(session, session_list, global_hlist) {
+			if (session->session_id == session_id) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
+				rcu_read_unlock_bh();
+
+				return session;
+			}
+		}
+		rcu_read_unlock_bh();
+
+		return NULL;
+	}
 
 	session_list = l2tp_session_id_hash(tunnel, session_id);
 	read_lock_bh(&tunnel->hlist_lock);
 	hlist_for_each_entry(session, session_list, hlist) {
 		if (session->session_id == session_id) {
+			l2tp_session_inc_refcount(session);
+			if (do_ref && session->ref)
+				session->ref(session);
 			read_unlock_bh(&tunnel->hlist_lock);
+
 			return session;
 		}
 	}
@@ -276,9 +276,10 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find);
+EXPORT_SYMBOL_GPL(l2tp_session_get);
 
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref)
 {
 	int hash;
 	struct l2tp_session *session;
@@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
 			}
@@ -298,12 +302,14 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
 
 /* Lookup a session by interface name.
  * This is very inefficient but is only used by management interfaces.
  */
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
+struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
+						const char *ifname,
+						bool do_ref)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 	int hash;
@@ -313,7 +319,11 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
 	for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
 		hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
 			if (!strcmp(session->ifname, ifname)) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
 				rcu_read_unlock_bh();
+
 				return session;
 			}
 		}
@@ -323,11 +333,53 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find_by_ifname);
+EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
+
+static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
+				      struct l2tp_session *session)
+{
+	struct l2tp_session *session_walk;
+	struct hlist_head *g_head;
+	struct hlist_head *head;
+	struct l2tp_net *pn;
+
+	head = l2tp_session_id_hash(tunnel, session->session_id);
+
+	write_lock_bh(&tunnel->hlist_lock);
+	hlist_for_each_entry(session_walk, head, hlist)
+		if (session_walk->session_id == session->session_id)
+			goto exist;
+
+	if (tunnel->version == L2TP_HDR_VER_3) {
+		pn = l2tp_pernet(tunnel->l2tp_net);
+		g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net),
+						session->session_id);
+
+		spin_lock_bh(&pn->l2tp_session_hlist_lock);
+		hlist_for_each_entry(session_walk, g_head, global_hlist)
+			if (session_walk->session_id == session->session_id)
+				goto exist_glob;
+
+		hlist_add_head_rcu(&session->global_hlist, g_head);
+		spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+	}
+
+	hlist_add_head(&session->hlist, head);
+	write_unlock_bh(&tunnel->hlist_lock);
+
+	return 0;
+
+exist_glob:
+	spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+exist:
+	write_unlock_bh(&tunnel->hlist_lock);
+
+	return -EEXIST;
+}
 
 /* Lookup a tunnel by id
  */
-struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id)
+struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id)
 {
 	struct l2tp_tunnel *tunnel;
 	struct l2tp_net *pn = l2tp_pernet(net);
@@ -345,7 +397,7 @@ struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_find);
 
-struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth)
+struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 	struct l2tp_tunnel *tunnel;
@@ -633,6 +685,9 @@ discard:
  * a data (not control) frame before coming here. Fields up to the
  * session-id have already been parsed and ptr points to the data
  * after the session-id.
+ *
+ * session->ref() must have been called prior to l2tp_recv_common().
+ * session->deref() will be called automatically after skb is processed.
  */
 void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      unsigned char *ptr, unsigned char *optr, u16 hdrflags,
@@ -642,14 +697,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 	int offset;
 	u32 ns, nr;
 
-	/* The ref count is increased since we now hold a pointer to
-	 * the session. Take care to decrement the refcnt when exiting
-	 * this function from now on...
-	 */
-	l2tp_session_inc_refcount(session);
-	if (session->ref)
-		(*session->ref)(session);
-
 	/* Parse and check optional cookie */
 	if (session->peer_cookie_len > 0) {
 		if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
@@ -802,8 +849,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 	/* Try to dequeue as many skbs from reorder_q as we can. */
 	l2tp_recv_dequeue(session);
 
-	l2tp_session_dec_refcount(session);
-
 	return;
 
 discard:
@@ -812,8 +857,6 @@ discard:
 
 	if (session->deref)
 		(*session->deref)(session);
-
-	l2tp_session_dec_refcount(session);
 }
 EXPORT_SYMBOL(l2tp_recv_common);
 
@@ -920,8 +963,14 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 	}
 
 	/* Find the session context */
-	session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id);
+	session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true);
 	if (!session || !session->recv_skb) {
+		if (session) {
+			if (session->deref)
+				session->deref(session);
+			l2tp_session_dec_refcount(session);
+		}
+
 		/* Not found? Pass to userspace to deal with */
 		l2tp_info(tunnel, L2TP_MSG_DATA,
 			  "%s: no session found (%u/%u). Passing up.\n",
@@ -930,6 +979,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 	}
 
 	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
+	l2tp_session_dec_refcount(session);
 
 	return 0;
 
@@ -1738,6 +1788,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
 struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
 {
 	struct l2tp_session *session;
+	int err;
 
 	session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
 	if (session != NULL) {
@@ -1793,6 +1844,13 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 
 		l2tp_session_set_header_len(session, tunnel->version);
 
+		err = l2tp_session_add_to_tunnel(tunnel, session);
+		if (err) {
+			kfree(session);
+
+			return ERR_PTR(err);
+		}
+
 		/* Bump the reference count. The session context is deleted
 		 * only when this drops to zero.
 		 */
@@ -1802,28 +1860,14 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 		/* Ensure tunnel socket isn't deleted */
 		sock_hold(tunnel->sock);
 
-		/* Add session to the tunnel's hash list */
-		write_lock_bh(&tunnel->hlist_lock);
-		hlist_add_head(&session->hlist,
-			       l2tp_session_id_hash(tunnel, session_id));
-		write_unlock_bh(&tunnel->hlist_lock);
-
-		/* And to the global session list if L2TPv3 */
-		if (tunnel->version != L2TP_HDR_VER_2) {
-			struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
-
-			spin_lock_bh(&pn->l2tp_session_hlist_lock);
-			hlist_add_head_rcu(&session->global_hlist,
-					   l2tp_session_id_hash_2(pn, session_id));
-			spin_unlock_bh(&pn->l2tp_session_hlist_lock);
-		}
-
 		/* Ignore management session in session count value */
 		if (session->session_id != 0)
 			atomic_inc(&l2tp_session_count);
+
+		return session;
 	}
 
-	return session;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(l2tp_session_create);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index aebf281d09ee..eec5ad2ebb93 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -230,13 +230,16 @@ out:
 	return tunnel;
 }
 
-struct l2tp_session *l2tp_session_find(struct net *net,
-				       struct l2tp_tunnel *tunnel,
-				       u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
+struct l2tp_session *l2tp_session_get(const struct net *net,
+				      struct l2tp_tunnel *tunnel,
+				      u32 session_id, bool do_ref);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref);
+struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
+						const char *ifname,
+						bool do_ref);
+struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id);
+struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 2d6760a2ae34..d100aed3d06f 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v)
 	}
 
 	/* Show the tunnel or session context */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		l2tp_dfs_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 8bf18a5f66e0..8b21af7321b9 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -30,6 +30,9 @@
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
 
 #include "l2tp_core.h"
 
@@ -127,8 +130,13 @@ static const struct net_device_ops l2tp_eth_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 };
 
+static struct device_type l2tpeth_type = {
+	.name = "l2tpeth",
+};
+
 static void l2tp_eth_dev_setup(struct net_device *dev)
 {
+	SET_NETDEV_DEVTYPE(dev, &l2tpeth_type);
 	ether_setup(dev);
 	dev->priv_flags		&= ~IFF_TX_SKB_SHARING;
 	dev->features		|= NETIF_F_LLTX;
@@ -204,8 +212,58 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
 }
 #endif
 
+static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
+				struct l2tp_session *session,
+				struct net_device *dev)
+{
+	unsigned int overhead = 0;
+	struct dst_entry *dst;
+	u32 l3_overhead = 0;
+
+	/* if the encap is UDP, account for UDP header size */
+	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
+		overhead += sizeof(struct udphdr);
+		dev->needed_headroom += sizeof(struct udphdr);
+	}
+	if (session->mtu != 0) {
+		dev->mtu = session->mtu;
+		dev->needed_headroom += session->hdr_len;
+		return;
+	}
+	lock_sock(tunnel->sock);
+	l3_overhead = kernel_sock_ip_overhead(tunnel->sock);
+	release_sock(tunnel->sock);
+	if (l3_overhead == 0) {
+		/* L3 Overhead couldn't be identified, this could be
+		 * because tunnel->sock was NULL or the socket's
+		 * address family was not IPv4 or IPv6,
+		 * dev mtu stays at 1500.
+		 */
+		return;
+	}
+	/* Adjust MTU, factor overhead - underlay L3, overlay L2 hdr
+	 * UDP overhead, if any, was already factored in above.
+	 */
+	overhead += session->hdr_len + ETH_HLEN + l3_overhead;
+
+	/* If PMTU discovery was enabled, use discovered MTU on L2TP device */
+	dst = sk_dst_get(tunnel->sock);
+	if (dst) {
+		/* dst_mtu will use PMTU if found, else fallback to intf MTU */
+		u32 pmtu = dst_mtu(dst);
+
+		if (pmtu != 0)
+			dev->mtu = pmtu;
+		dst_release(dst);
+	}
+	session->mtu = dev->mtu - overhead;
+	dev->mtu = session->mtu;
+	dev->needed_headroom += session->hdr_len;
+}
+
 static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
 {
+	unsigned char name_assign_type;
 	struct net_device *dev;
 	char name[IFNAMSIZ];
 	struct l2tp_tunnel *tunnel;
@@ -221,31 +279,22 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 		goto out;
 	}
 
-	session = l2tp_session_find(net, tunnel, session_id);
-	if (session) {
-		rc = -EEXIST;
-		goto out;
-	}
-
 	if (cfg->ifname) {
-		dev = dev_get_by_name(net, cfg->ifname);
-		if (dev) {
-			dev_put(dev);
-			rc = -EEXIST;
-			goto out;
-		}
 		strlcpy(name, cfg->ifname, IFNAMSIZ);
-	} else
+		name_assign_type = NET_NAME_USER;
+	} else {
 		strcpy(name, L2TP_ETH_DEV_NAME);
+		name_assign_type = NET_NAME_ENUM;
+	}
 
 	session = l2tp_session_create(sizeof(*spriv), tunnel, session_id,
 				      peer_session_id, cfg);
-	if (!session) {
-		rc = -ENOMEM;
+	if (IS_ERR(session)) {
+		rc = PTR_ERR(session);
 		goto out;
 	}
 
-	dev = alloc_netdev(sizeof(*priv), name, NET_NAME_UNKNOWN,
+	dev = alloc_netdev(sizeof(*priv), name, name_assign_type,
 			   l2tp_eth_dev_setup);
 	if (!dev) {
 		rc = -ENOMEM;
@@ -253,12 +302,9 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 	}
 
 	dev_net_set(dev, net);
-	if (session->mtu == 0)
-		session->mtu = dev->mtu - session->hdr_len;
-	dev->mtu = session->mtu;
-	dev->needed_headroom += session->hdr_len;
 	dev->min_mtu = 0;
 	dev->max_mtu = ETH_MAX_MTU;
+	l2tp_eth_adjust_mtu(tunnel, session, dev);
 
 	priv = netdev_priv(dev);
 	priv->dev = dev;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index d25038cfd64e..4d322c1b7233 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -143,19 +143,19 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_find(net, NULL, session_id);
-	if (session == NULL)
+	session = l2tp_session_get(net, NULL, session_id, true);
+	if (!session)
 		goto discard;
 
 	tunnel = session->tunnel;
-	if (tunnel == NULL)
-		goto discard;
+	if (!tunnel)
+		goto discard_sess;
 
 	/* Trace packet contents, if enabled */
 	if (tunnel->debug & L2TP_MSG_DATA) {
 		length = min(32u, skb->len);
 		if (!pskb_may_pull(skb, length))
-			goto discard;
+			goto discard_sess;
 
 		/* Point to L2TP header */
 		optr = ptr = skb->data;
@@ -165,6 +165,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	}
 
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+	l2tp_session_dec_refcount(session);
 
 	return 0;
 
@@ -178,9 +179,10 @@ pass_up:
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
 
 		read_lock_bh(&l2tp_ip_lock);
@@ -202,6 +204,12 @@ pass_up:
 
 	return sk_receive_skb(sk, skb, 1);
 
+discard_sess:
+	if (session->deref)
+		session->deref(session);
+	l2tp_session_dec_refcount(session);
+	goto discard;
+
 discard_put:
 	sock_put(sk);
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a4abcbc4c09a..88b397c30d86 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -156,19 +156,19 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_find(net, NULL, session_id);
-	if (session == NULL)
+	session = l2tp_session_get(net, NULL, session_id, true);
+	if (!session)
 		goto discard;
 
 	tunnel = session->tunnel;
-	if (tunnel == NULL)
-		goto discard;
+	if (!tunnel)
+		goto discard_sess;
 
 	/* Trace packet contents, if enabled */
 	if (tunnel->debug & L2TP_MSG_DATA) {
 		length = min(32u, skb->len);
 		if (!pskb_may_pull(skb, length))
-			goto discard;
+			goto discard_sess;
 
 		/* Point to L2TP header */
 		optr = ptr = skb->data;
@@ -179,6 +179,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
 			 tunnel->recv_payload_hook);
+	l2tp_session_dec_refcount(session);
+
 	return 0;
 
 pass_up:
@@ -191,9 +193,10 @@ pass_up:
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		read_lock_bh(&l2tp_ip6_lock);
@@ -215,6 +218,12 @@ pass_up:
 
 	return sk_receive_skb(sk, skb, 1);
 
+discard_sess:
+	if (session->deref)
+		session->deref(session);
+	l2tp_session_dec_refcount(session);
+	goto discard;
+
 discard_put:
 	sock_put(sk);
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 3620fba31786..12cfcd0ca807 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -48,7 +48,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq,
 /* Accessed under genl lock */
 static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
 
-static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
+static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info,
+						bool do_ref)
 {
 	u32 tunnel_id;
 	u32 session_id;
@@ -59,14 +60,15 @@ static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
 
 	if (info->attrs[L2TP_ATTR_IFNAME]) {
 		ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
-		session = l2tp_session_find_by_ifname(net, ifname);
+		session = l2tp_session_get_by_ifname(net, ifname, do_ref);
 	} else if ((info->attrs[L2TP_ATTR_SESSION_ID]) &&
 		   (info->attrs[L2TP_ATTR_CONN_ID])) {
 		tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
 		session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
 		tunnel = l2tp_tunnel_find(net, tunnel_id);
 		if (tunnel)
-			session = l2tp_session_find(net, tunnel, session_id);
+			session = l2tp_session_get(net, tunnel, session_id,
+						   do_ref);
 	}
 
 	return session;
@@ -519,11 +521,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 		goto out;
 	}
 	session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
-	session = l2tp_session_find(net, tunnel, session_id);
-	if (session) {
-		ret = -EEXIST;
-		goto out;
-	}
 
 	if (!info->attrs[L2TP_ATTR_PEER_SESSION_ID]) {
 		ret = -EINVAL;
@@ -642,10 +639,12 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 			session_id, peer_session_id, &cfg);
 
 	if (ret >= 0) {
-		session = l2tp_session_find(net, tunnel, session_id);
-		if (session)
+		session = l2tp_session_get(net, tunnel, session_id, false);
+		if (session) {
 			ret = l2tp_session_notify(&l2tp_nl_family, info, session,
 						  L2TP_CMD_SESSION_CREATE);
+			l2tp_session_dec_refcount(session);
+		}
 	}
 
 out:
@@ -658,7 +657,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 	struct l2tp_session *session;
 	u16 pw_type;
 
-	session = l2tp_nl_session_find(info);
+	session = l2tp_nl_session_get(info, true);
 	if (session == NULL) {
 		ret = -ENODEV;
 		goto out;
@@ -672,6 +671,10 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 		if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
 			ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session);
 
+	if (session->deref)
+		session->deref(session);
+	l2tp_session_dec_refcount(session);
+
 out:
 	return ret;
 }
@@ -681,7 +684,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	int ret = 0;
 	struct l2tp_session *session;
 
-	session = l2tp_nl_session_find(info);
+	session = l2tp_nl_session_get(info, false);
 	if (session == NULL) {
 		ret = -ENODEV;
 		goto out;
@@ -716,6 +719,8 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	ret = l2tp_session_notify(&l2tp_nl_family, info,
 				  session, L2TP_CMD_SESSION_MODIFY);
 
+	l2tp_session_dec_refcount(session);
+
 out:
 	return ret;
 }
@@ -811,29 +816,34 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *msg;
 	int ret;
 
-	session = l2tp_nl_session_find(info);
+	session = l2tp_nl_session_get(info, false);
 	if (session == NULL) {
 		ret = -ENODEV;
-		goto out;
+		goto err;
 	}
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg) {
 		ret = -ENOMEM;
-		goto out;
+		goto err_ref;
 	}
 
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
 				   0, session, L2TP_CMD_SESSION_GET);
 	if (ret < 0)
-		goto err_out;
+		goto err_ref_msg;
 
-	return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
+	ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
 
-err_out:
-	nlmsg_free(msg);
+	l2tp_session_dec_refcount(session);
 
-out:
+	return ret;
+
+err_ref_msg:
+	nlmsg_free(msg);
+err_ref:
+	l2tp_session_dec_refcount(session);
+err:
 	return ret;
 }
 
@@ -852,7 +862,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 				goto out;
 		}
 
-		session = l2tp_session_find_nth(tunnel, si);
+		session = l2tp_session_get_nth(tunnel, si, false);
 		if (session == NULL) {
 			ti++;
 			tunnel = NULL;
@@ -862,8 +872,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session, L2TP_CMD_SESSION_GET) < 0)
+					 session, L2TP_CMD_SESSION_GET) < 0) {
+			l2tp_session_dec_refcount(session);
 			break;
+		}
+		l2tp_session_dec_refcount(session);
 
 		si++;
 	}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 36cc56fd0418..32ea0f3d868c 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -450,6 +450,10 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 static void pppol2tp_session_destruct(struct sock *sk)
 {
 	struct l2tp_session *session = sk->sk_user_data;
+
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge(&sk->sk_write_queue);
+
 	if (session) {
 		sk->sk_user_data = NULL;
 		BUG_ON(session->magic != L2TP_SESSION_MAGIC);
@@ -488,9 +492,6 @@ static int pppol2tp_release(struct socket *sock)
 		l2tp_session_queue_purge(session);
 		sock_put(sk);
 	}
-	skb_queue_purge(&sk->sk_receive_queue);
-	skb_queue_purge(&sk->sk_write_queue);
-
 	release_sock(sk);
 
 	/* This will delete the session context via
@@ -582,6 +583,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	int error = 0;
 	u32 tunnel_id, peer_tunnel_id;
 	u32 session_id, peer_session_id;
+	bool drop_refcnt = false;
 	int ver = 2;
 	int fd;
 
@@ -683,36 +685,36 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	if (tunnel->peer_tunnel_id == 0)
 		tunnel->peer_tunnel_id = peer_tunnel_id;
 
-	/* Create session if it doesn't already exist. We handle the
-	 * case where a session was previously created by the netlink
-	 * interface by checking that the session doesn't already have
-	 * a socket and its tunnel socket are what we expect. If any
-	 * of those checks fail, return EEXIST to the caller.
-	 */
-	session = l2tp_session_find(sock_net(sk), tunnel, session_id);
-	if (session == NULL) {
-		/* Default MTU must allow space for UDP/L2TP/PPP
-		 * headers.
+	session = l2tp_session_get(sock_net(sk), tunnel, session_id, false);
+	if (session) {
+		drop_refcnt = true;
+		ps = l2tp_session_priv(session);
+
+		/* Using a pre-existing session is fine as long as it hasn't
+		 * been connected yet.
 		 */
-		cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+		if (ps->sock) {
+			error = -EEXIST;
+			goto end;
+		}
 
-		/* Allocate and initialize a new session context. */
-		session = l2tp_session_create(sizeof(struct pppol2tp_session),
-					      tunnel, session_id,
-					      peer_session_id, &cfg);
-		if (session == NULL) {
-			error = -ENOMEM;
+		/* consistency checks */
+		if (ps->tunnel_sock != tunnel->sock) {
+			error = -EEXIST;
 			goto end;
 		}
 	} else {
-		ps = l2tp_session_priv(session);
-		error = -EEXIST;
-		if (ps->sock != NULL)
-			goto end;
+		/* Default MTU must allow space for UDP/L2TP/PPP headers */
+		cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+		cfg.mru = cfg.mtu;
 
-		/* consistency checks */
-		if (ps->tunnel_sock != tunnel->sock)
+		session = l2tp_session_create(sizeof(struct pppol2tp_session),
+					      tunnel, session_id,
+					      peer_session_id, &cfg);
+		if (IS_ERR(session)) {
+			error = PTR_ERR(session);
 			goto end;
+		}
 	}
 
 	/* Associate session with its PPPoL2TP socket */
@@ -777,6 +779,8 @@ out_no_ppp:
 		  session->name);
 
 end:
+	if (drop_refcnt)
+		l2tp_session_dec_refcount(session);
 	release_sock(sk);
 
 	return error;
@@ -804,12 +808,6 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i
 	if (tunnel->sock == NULL)
 		goto out;
 
-	/* Check that this session doesn't already exist */
-	error = -EEXIST;
-	session = l2tp_session_find(net, tunnel, session_id);
-	if (session != NULL)
-		goto out;
-
 	/* Default MTU values. */
 	if (cfg->mtu == 0)
 		cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
@@ -817,12 +815,13 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i
 		cfg->mru = cfg->mtu;
 
 	/* Allocate and initialize a new session context. */
-	error = -ENOMEM;
 	session = l2tp_session_create(sizeof(struct pppol2tp_session),
 				      tunnel, session_id,
 				      peer_session_id, cfg);
-	if (session == NULL)
+	if (IS_ERR(session)) {
+		error = PTR_ERR(session);
 		goto out;
+	}
 
 	ps = l2tp_session_priv(session);
 	ps->tunnel_sock = tunnel->sock;
@@ -1140,11 +1139,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 		if (stats.session_id != 0) {
 			/* resend to session ioctl handler */
 			struct l2tp_session *session =
-				l2tp_session_find(sock_net(sk), tunnel, stats.session_id);
-			if (session != NULL)
-				err = pppol2tp_session_ioctl(session, cmd, arg);
-			else
+				l2tp_session_get(sock_net(sk), tunnel,
+						 stats.session_id, true);
+
+			if (session) {
+				err = pppol2tp_session_ioctl(session, cmd,
+							     arg);
+				if (session->deref)
+					session->deref(session);
+				l2tp_session_dec_refcount(session);
+			} else {
 				err = -EBADR;
+			}
 			break;
 		}
 #ifdef CONFIG_XFRM
@@ -1377,8 +1383,6 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	} else
 		err = pppol2tp_session_setsockopt(sk, session, optname, val);
 
-	err = 0;
-
 end_put_sess:
 	sock_put(sk);
 end:
@@ -1501,8 +1505,13 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 
 		err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
 		sock_put(ps->tunnel_sock);
-	} else
+		if (err)
+			goto end_put_sess;
+	} else {
 		err = pppol2tp_session_getsockopt(sk, session, optname, &val);
+		if (err)
+			goto end_put_sess;
+	}
 
 	err = -EFAULT;
 	if (put_user(len, optlen))
@@ -1554,7 +1563,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 
 static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -1681,10 +1690,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v)
 
 	/* Show the tunnel or session context.
 	 */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		pppol2tp_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		pppol2tp_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
@@ -1843,4 +1856,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(PPPOL2TP_DRV_VERSION);
 MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 06186d608a27..cb4fff785cbf 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
  *	@sock: Socket which connections arrive on.
  *	@newsock: Socket to move incoming connection to.
  *	@flags: User specified operational flags.
+ *	@kern: If the socket is kernel internal
  *
  *	Accept a new incoming connection.
  *	Returns 0 upon success, negative otherwise.
  */
-static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags)
+static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags,
+			 bool kern)
 {
 	struct sock *sk = sock->sk, *newsk;
 	struct llc_sock *llc, *newllc;
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 4456559cb056..1b7a4daf283c 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -357,14 +357,14 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	spin_lock_init(&tid_agg_rx->reorder_lock);
 
 	/* rx timer */
-	tid_agg_rx->session_timer.function = sta_rx_agg_session_timer_expired;
-	tid_agg_rx->session_timer.data = (unsigned long)&sta->timer_to_tid[tid];
-	init_timer_deferrable(&tid_agg_rx->session_timer);
+	setup_deferrable_timer(&tid_agg_rx->session_timer,
+			       sta_rx_agg_session_timer_expired,
+			       (unsigned long)&sta->timer_to_tid[tid]);
 
 	/* rx reorder timer */
-	tid_agg_rx->reorder_timer.function = sta_rx_agg_reorder_timer_expired;
-	tid_agg_rx->reorder_timer.data = (unsigned long)&sta->timer_to_tid[tid];
-	init_timer(&tid_agg_rx->reorder_timer);
+	setup_timer(&tid_agg_rx->reorder_timer,
+		    sta_rx_agg_reorder_timer_expired,
+		    (unsigned long)&sta->timer_to_tid[tid]);
 
 	/* prepare reordering buffer */
 	tid_agg_rx->reorder_buf =
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 45319cc01121..60e2a62f7bef 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -670,14 +670,14 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
 	tid_tx->timeout = timeout;
 
 	/* response timer */
-	tid_tx->addba_resp_timer.function = sta_addba_resp_timer_expired;
-	tid_tx->addba_resp_timer.data = (unsigned long)&sta->timer_to_tid[tid];
-	init_timer(&tid_tx->addba_resp_timer);
+	setup_timer(&tid_tx->addba_resp_timer,
+		    sta_addba_resp_timer_expired,
+		    (unsigned long)&sta->timer_to_tid[tid]);
 
 	/* tx timer */
-	tid_tx->session_timer.function = sta_tx_agg_session_timer_expired;
-	tid_tx->session_timer.data = (unsigned long)&sta->timer_to_tid[tid];
-	init_timer_deferrable(&tid_tx->session_timer);
+	setup_deferrable_timer(&tid_tx->session_timer,
+			       sta_tx_agg_session_timer_expired,
+			       (unsigned long)&sta->timer_to_tid[tid]);
 
 	/* assign a dialog token */
 	sta->ampdu_mlme.dialog_token_allocator++;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ac879bb17870..6c2e6060cd54 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3,7 +3,7 @@
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
- * Copyright (C) 2015-2016 Intel Deutschland GmbH
+ * Copyright (C) 2015-2017 Intel Deutschland GmbH
  *
  * This file is GPLv2 as found in COPYING.
  */
@@ -22,11 +22,98 @@
 #include "mesh.h"
 #include "wme.h"
 
+static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata,
+					 struct vif_params *params)
+{
+	bool mu_mimo_groups = false;
+	bool mu_mimo_follow = false;
+
+	if (params->vht_mumimo_groups) {
+		u64 membership;
+
+		BUILD_BUG_ON(sizeof(membership) != WLAN_MEMBERSHIP_LEN);
+
+		memcpy(sdata->vif.bss_conf.mu_group.membership,
+		       params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN);
+		memcpy(sdata->vif.bss_conf.mu_group.position,
+		       params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN,
+		       WLAN_USER_POSITION_LEN);
+		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_MU_GROUPS);
+		/* don't care about endianness - just check for 0 */
+		memcpy(&membership, params->vht_mumimo_groups,
+		       WLAN_MEMBERSHIP_LEN);
+		mu_mimo_groups = membership != 0;
+	}
+
+	if (params->vht_mumimo_follow_addr) {
+		mu_mimo_follow =
+			is_valid_ether_addr(params->vht_mumimo_follow_addr);
+		ether_addr_copy(sdata->u.mntr.mu_follow_addr,
+				params->vht_mumimo_follow_addr);
+	}
+
+	sdata->vif.mu_mimo_owner = mu_mimo_groups || mu_mimo_follow;
+}
+
+static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata,
+				     struct vif_params *params)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *monitor_sdata;
+
+	/* check flags first */
+	if (params->flags && ieee80211_sdata_running(sdata)) {
+		u32 mask = MONITOR_FLAG_COOK_FRAMES | MONITOR_FLAG_ACTIVE;
+
+		/*
+		 * Prohibit MONITOR_FLAG_COOK_FRAMES and
+		 * MONITOR_FLAG_ACTIVE to be changed while the
+		 * interface is up.
+		 * Else we would need to add a lot of cruft
+		 * to update everything:
+		 *	cooked_mntrs, monitor and all fif_* counters
+		 *	reconfigure hardware
+		 */
+		if ((params->flags & mask) != (sdata->u.mntr.flags & mask))
+			return -EBUSY;
+	}
+
+	/* also validate MU-MIMO change */
+	monitor_sdata = rtnl_dereference(local->monitor_sdata);
+
+	if (!monitor_sdata &&
+	    (params->vht_mumimo_groups || params->vht_mumimo_follow_addr))
+		return -EOPNOTSUPP;
+
+	/* apply all changes now - no failures allowed */
+
+	if (monitor_sdata)
+		ieee80211_set_mu_mimo_follow(monitor_sdata, params);
+
+	if (params->flags) {
+		if (ieee80211_sdata_running(sdata)) {
+			ieee80211_adjust_monitor_flags(sdata, -1);
+			sdata->u.mntr.flags = params->flags;
+			ieee80211_adjust_monitor_flags(sdata, 1);
+
+			ieee80211_configure_filter(local);
+		} else {
+			/*
+			 * Because the interface is down, ieee80211_do_stop
+			 * and ieee80211_do_open take care of "everything"
+			 * mentioned in the comment above.
+			 */
+			sdata->u.mntr.flags = params->flags;
+		}
+	}
+
+	return 0;
+}
+
 static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy,
 						const char *name,
 						unsigned char name_assign_type,
 						enum nl80211_iftype type,
-						u32 *flags,
 						struct vif_params *params)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
@@ -38,9 +125,14 @@ static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy,
 	if (err)
 		return ERR_PTR(err);
 
-	if (type == NL80211_IFTYPE_MONITOR && flags) {
-		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
-		sdata->u.mntr.flags = *flags;
+	sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+
+	if (type == NL80211_IFTYPE_MONITOR) {
+		err = ieee80211_set_mon_options(sdata, params);
+		if (err) {
+			ieee80211_if_remove(sdata);
+			return NULL;
+		}
 	}
 
 	return wdev;
@@ -55,7 +147,7 @@ static int ieee80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev)
 
 static int ieee80211_change_iface(struct wiphy *wiphy,
 				  struct net_device *dev,
-				  enum nl80211_iftype type, u32 *flags,
+				  enum nl80211_iftype type,
 				  struct vif_params *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -75,58 +167,9 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
 	}
 
 	if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
-		struct ieee80211_local *local = sdata->local;
-		struct ieee80211_sub_if_data *monitor_sdata;
-		u32 mu_mntr_cap_flag = NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER;
-
-		monitor_sdata = rtnl_dereference(local->monitor_sdata);
-		if (monitor_sdata &&
-		    wiphy_ext_feature_isset(wiphy, mu_mntr_cap_flag)) {
-			memcpy(monitor_sdata->vif.bss_conf.mu_group.membership,
-			       params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN);
-			memcpy(monitor_sdata->vif.bss_conf.mu_group.position,
-			       params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN,
-			       WLAN_USER_POSITION_LEN);
-			monitor_sdata->vif.mu_mimo_owner = true;
-			ieee80211_bss_info_change_notify(monitor_sdata,
-							 BSS_CHANGED_MU_GROUPS);
-
-			ether_addr_copy(monitor_sdata->u.mntr.mu_follow_addr,
-					params->macaddr);
-		}
-
-		if (!flags)
-			return 0;
-
-		if (ieee80211_sdata_running(sdata)) {
-			u32 mask = MONITOR_FLAG_COOK_FRAMES |
-				   MONITOR_FLAG_ACTIVE;
-
-			/*
-			 * Prohibit MONITOR_FLAG_COOK_FRAMES and
-			 * MONITOR_FLAG_ACTIVE to be changed while the
-			 * interface is up.
-			 * Else we would need to add a lot of cruft
-			 * to update everything:
-			 *	cooked_mntrs, monitor and all fif_* counters
-			 *	reconfigure hardware
-			 */
-			if ((*flags & mask) != (sdata->u.mntr.flags & mask))
-				return -EBUSY;
-
-			ieee80211_adjust_monitor_flags(sdata, -1);
-			sdata->u.mntr.flags = *flags;
-			ieee80211_adjust_monitor_flags(sdata, 1);
-
-			ieee80211_configure_filter(local);
-		} else {
-			/*
-			 * Because the interface is down, ieee80211_do_stop
-			 * and ieee80211_do_open take care of "everything"
-			 * mentioned in the comment above.
-			 */
-			sdata->u.mntr.flags = *flags;
-		}
+		ret = ieee80211_set_mon_options(sdata, params);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -617,10 +660,11 @@ void sta_set_rate_info_tx(struct sta_info *sta,
 		int shift = ieee80211_vif_get_shift(&sta->sdata->vif);
 		u16 brate;
 
-		sband = sta->local->hw.wiphy->bands[
-				ieee80211_get_sdata_band(sta->sdata)];
-		brate = sband->bitrates[rate->idx].bitrate;
-		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
+		sband = ieee80211_get_sband(sta->sdata);
+		if (sband) {
+			brate = sband->bitrates[rate->idx].bitrate;
+			rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
+		}
 	}
 	if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
 		rinfo->bw = RATE_INFO_BW_40;
@@ -696,11 +740,8 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 		return 0;
 
 	mutex_lock(&local->mtx);
-	mutex_lock(&local->iflist_mtx);
 	if (local->use_chanctx) {
-		sdata = rcu_dereference_protected(
-				local->monitor_sdata,
-				lockdep_is_held(&local->iflist_mtx));
+		sdata = rtnl_dereference(local->monitor_sdata);
 		if (sdata) {
 			ieee80211_vif_release_channel(sdata);
 			ret = ieee80211_vif_use_channel(sdata, chandef,
@@ -713,7 +754,6 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 
 	if (ret == 0)
 		local->monitor_chandef = *chandef;
-	mutex_unlock(&local->iflist_mtx);
 	mutex_unlock(&local->mtx);
 
 	return ret;
@@ -1214,10 +1254,11 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 	int ret = 0;
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
 	u32 mask, set;
 
-	sband = local->hw.wiphy->bands[band];
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return -EINVAL;
 
 	mask = params->sta_flags_mask;
 	set = params->sta_flags_set;
@@ -1350,7 +1391,7 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 		ieee80211_parse_bitrates(&sdata->vif.bss_conf.chandef,
 					 sband, params->supported_rates,
 					 params->supported_rates_len,
-					 &sta->sta.supp_rates[band]);
+					 &sta->sta.supp_rates[sband->band]);
 	}
 
 	if (params->ht_capa)
@@ -1366,8 +1407,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 		/* returned value is only needed for rc update, but the
 		 * rc isn't initialized here yet, so ignore it
 		 */
-		__ieee80211_vht_handle_opmode(sdata, sta,
-					      params->opmode_notif, band);
+		__ieee80211_vht_handle_opmode(sdata, sta, params->opmode_notif,
+					      sband->band);
 	}
 
 	if (params->support_p2p_ps >= 0)
@@ -2005,13 +2046,15 @@ static int ieee80211_change_bss(struct wiphy *wiphy,
 				struct bss_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	enum nl80211_band band;
+	struct ieee80211_supported_band *sband;
 	u32 changed = 0;
 
 	if (!sdata_dereference(sdata->u.ap.beacon, sdata))
 		return -ENOENT;
 
-	band = ieee80211_get_sdata_band(sdata);
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return -EINVAL;
 
 	if (params->use_cts_prot >= 0) {
 		sdata->vif.bss_conf.use_cts_prot = params->use_cts_prot;
@@ -2024,7 +2067,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy,
 	}
 
 	if (!sdata->vif.bss_conf.use_short_slot &&
-	    band == NL80211_BAND_5GHZ) {
+	    sband->band == NL80211_BAND_5GHZ) {
 		sdata->vif.bss_conf.use_short_slot = true;
 		changed |= BSS_CHANGED_ERP_SLOT;
 	}
@@ -2037,11 +2080,12 @@ static int ieee80211_change_bss(struct wiphy *wiphy,
 
 	if (params->basic_rates) {
 		ieee80211_parse_bitrates(&sdata->vif.bss_conf.chandef,
-					 wiphy->bands[band],
+					 wiphy->bands[sband->band],
 					 params->basic_rates,
 					 params->basic_rates_len,
 					 &sdata->vif.bss_conf.basic_rates);
 		changed |= BSS_CHANGED_BASIC_RATES;
+		ieee80211_check_rate_mask(sdata);
 	}
 
 	if (params->ap_isolate >= 0) {
@@ -2198,7 +2242,8 @@ ieee80211_sched_scan_start(struct wiphy *wiphy,
 }
 
 static int
-ieee80211_sched_scan_stop(struct wiphy *wiphy, struct net_device *dev)
+ieee80211_sched_scan_stop(struct wiphy *wiphy, struct net_device *dev,
+			  u64 reqid)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 
@@ -2630,6 +2675,33 @@ static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy,
 
 	bss_conf->cqm_rssi_thold = rssi_thold;
 	bss_conf->cqm_rssi_hyst = rssi_hyst;
+	bss_conf->cqm_rssi_low = 0;
+	bss_conf->cqm_rssi_high = 0;
+	sdata->u.mgd.last_cqm_event_signal = 0;
+
+	/* tell the driver upon association, unless already associated */
+	if (sdata->u.mgd.associated &&
+	    sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)
+		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_CQM);
+
+	return 0;
+}
+
+static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy,
+					       struct net_device *dev,
+					       s32 rssi_low, s32 rssi_high)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_vif *vif = &sdata->vif;
+	struct ieee80211_bss_conf *bss_conf = &vif->bss_conf;
+
+	if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)
+		return -EOPNOTSUPP;
+
+	bss_conf->cqm_rssi_low = rssi_low;
+	bss_conf->cqm_rssi_high = rssi_high;
+	bss_conf->cqm_rssi_thold = 0;
+	bss_conf->cqm_rssi_hyst = 0;
 	sdata->u.mgd.last_cqm_event_signal = 0;
 
 	/* tell the driver upon association, unless already associated */
@@ -2658,6 +2730,21 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 			return ret;
 	}
 
+	/*
+	 * If active validate the setting and reject it if it doesn't leave
+	 * at least one basic rate usable, since we really have to be able
+	 * to send something, and if we're an AP we have to be able to do
+	 * so at a basic rate so that all clients can receive it.
+	 */
+	if (rcu_access_pointer(sdata->vif.chanctx_conf) &&
+	    sdata->vif.bss_conf.chandef.chan) {
+		u32 basic_rates = sdata->vif.bss_conf.basic_rates;
+		enum nl80211_band band = sdata->vif.bss_conf.chandef.chan->band;
+
+		if (!(mask->control[band].legacy & basic_rates))
+			return -EINVAL;
+	}
+
 	for (i = 0; i < NUM_NL80211_BANDS; i++) {
 		struct ieee80211_supported_band *sband = wiphy->bands[i];
 		int j;
@@ -3639,6 +3726,7 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.mgmt_tx = ieee80211_mgmt_tx,
 	.mgmt_tx_cancel_wait = ieee80211_mgmt_tx_cancel_wait,
 	.set_cqm_rssi_config = ieee80211_set_cqm_rssi_config,
+	.set_cqm_rssi_range_config = ieee80211_set_cqm_rssi_range_config,
 	.mgmt_frame_register = ieee80211_mgmt_frame_register,
 	.set_antenna = ieee80211_set_antenna,
 	.get_antenna = ieee80211_get_antenna,
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 98999d3d5262..6db09fa18269 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -425,7 +425,7 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	case NL80211_CHAN_WIDTH_5:
 	case NL80211_CHAN_WIDTH_10:
 		cfg80211_chandef_create(&chandef, cbss->channel,
-					NL80211_CHAN_WIDTH_20_NOHT);
+					NL80211_CHAN_NO_HT);
 		chandef.width = sdata->u.ibss.chandef.width;
 		break;
 	case NL80211_CHAN_WIDTH_80:
@@ -437,7 +437,7 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	default:
 		/* fall back to 20 MHz for unsupported modes */
 		cfg80211_chandef_create(&chandef, cbss->channel,
-					NL80211_CHAN_WIDTH_20_NOHT);
+					NL80211_CHAN_NO_HT);
 		break;
 	}
 
@@ -992,7 +992,7 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 	enum nl80211_band band = rx_status->band;
 	enum nl80211_bss_scan_width scan_width;
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
+	struct ieee80211_supported_band *sband;
 	bool rates_updated = false;
 	u32 supp_rates = 0;
 
@@ -1002,6 +1002,10 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 	if (!ether_addr_equal(mgmt->bssid, sdata->u.ibss.bssid))
 		return;
 
+	sband = local->hw.wiphy->bands[band];
+	if (WARN_ON(!sband))
+		return;
+
 	rcu_read_lock();
 	sta = sta_info_get(sdata, mgmt->sa);
 
@@ -1014,9 +1018,9 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 			prev_rates = sta->sta.supp_rates[band];
 			/* make sure mandatory rates are always added */
 			scan_width = NL80211_BSS_CHAN_WIDTH_20;
-			if (rx_status->flag & RX_FLAG_5MHZ)
+			if (rx_status->bw == RATE_INFO_BW_5)
 				scan_width = NL80211_BSS_CHAN_WIDTH_5;
-			if (rx_status->flag & RX_FLAG_10MHZ)
+			else if (rx_status->bw == RATE_INFO_BW_10)
 				scan_width = NL80211_BSS_CHAN_WIDTH_10;
 
 			sta->sta.supp_rates[band] = supp_rates |
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 0e718437d080..f8f6c148f554 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -839,6 +839,8 @@ struct txq_info {
 struct ieee80211_if_mntr {
 	u32 flags;
 	u8 mu_follow_addr[ETH_ALEN] __aligned(2);
+
+	struct list_head list;
 };
 
 /**
@@ -999,21 +1001,6 @@ sdata_assert_lock(struct ieee80211_sub_if_data *sdata)
 	lockdep_assert_held(&sdata->wdev.mtx);
 }
 
-static inline enum nl80211_band
-ieee80211_get_sdata_band(struct ieee80211_sub_if_data *sdata)
-{
-	enum nl80211_band band = NL80211_BAND_2GHZ;
-	struct ieee80211_chanctx_conf *chanctx_conf;
-
-	rcu_read_lock();
-	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-	if (!WARN_ON(!chanctx_conf))
-		band = chanctx_conf->def.chan->band;
-	rcu_read_unlock();
-
-	return band;
-}
-
 static inline int
 ieee80211_chandef_get_shift(struct cfg80211_chan_def *chandef)
 {
@@ -1259,6 +1246,7 @@ struct ieee80211_local {
 
 	/* see iface.c */
 	struct list_head interfaces;
+	struct list_head mon_list; /* only that are IFF_UP && !cooked */
 	struct mutex iflist_mtx;
 
 	/*
@@ -1418,6 +1406,27 @@ IEEE80211_WDEV_TO_SUB_IF(struct wireless_dev *wdev)
 	return container_of(wdev, struct ieee80211_sub_if_data, wdev);
 }
 
+static inline struct ieee80211_supported_band *
+ieee80211_get_sband(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *chanctx_conf;
+	enum nl80211_band band;
+
+	rcu_read_lock();
+	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+
+	if (WARN_ON(!chanctx_conf)) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	band = chanctx_conf->def.chan->band;
+	rcu_read_unlock();
+
+	return local->hw.wiphy->bands[band];
+}
+
 /* this struct represents 802.11n's RA/TID combination */
 struct ieee80211_ra_tid {
 	u8 ra[ETH_ALEN];
@@ -1474,6 +1483,7 @@ struct ieee802_11_elems {
 	const u8 *opmode_notif;
 	const struct ieee80211_sec_chan_offs_ie *sec_chan_offs;
 	const struct ieee80211_mesh_chansw_params_ie *mesh_chansw_params_ie;
+	const struct ieee80211_bss_max_idle_period_ie *max_idle_period_ie;
 
 	/* length of them, respectively */
 	u8 ext_capab_len;
@@ -1527,9 +1537,9 @@ ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
 		     status->flag & RX_FLAG_MACTIME_END);
 	if (status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END))
 		return true;
-	/* can't handle HT/VHT preamble yet */
+	/* can't handle non-legacy preamble yet */
 	if (status->flag & RX_FLAG_MACTIME_PLCP_START &&
-	    !(status->flag & (RX_FLAG_HT | RX_FLAG_VHT)))
+	    status->encoding != RX_ENC_LEGACY)
 		return true;
 	return false;
 }
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 40813dd3301c..3bd5b81f5d81 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -676,7 +676,8 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 
 	set_bit(SDATA_STATE_RUNNING, &sdata->state);
 
-	if (sdata->vif.type == NL80211_IFTYPE_WDS) {
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_WDS:
 		/* Create STA entry for the WDS peer */
 		sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr,
 				     GFP_KERNEL);
@@ -697,8 +698,17 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 
 		rate_control_rate_init(sta);
 		netif_carrier_on(dev);
-	} else if (sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE) {
+		break;
+	case NL80211_IFTYPE_P2P_DEVICE:
 		rcu_assign_pointer(local->p2p_sdata, sdata);
+		break;
+	case NL80211_IFTYPE_MONITOR:
+		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
+			break;
+		list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list);
+		break;
+	default:
+		break;
 	}
 
 	/*
@@ -718,7 +728,8 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 	ieee80211_recalc_ps(local);
 
 	if (sdata->vif.type == NL80211_IFTYPE_MONITOR ||
-	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+	    local->ops->wake_tx_queue) {
 		/* XXX: for AP_VLAN, actually track AP queues */
 		netif_tx_start_all_queues(dev);
 	} else if (dev) {
@@ -816,6 +827,11 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP:
 		cancel_work_sync(&sdata->u.ap.request_smps_work);
 		break;
+	case NL80211_IFTYPE_MONITOR:
+		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
+			break;
+		list_del_rcu(&sdata->u.mntr.list);
+		break;
 	default:
 		break;
 	}
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 56fb47953b72..8aa1f5b6a051 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -253,6 +253,7 @@ static void ieee80211_restart_work(struct work_struct *work)
 	WARN(test_bit(SCAN_HW_SCANNING, &local->scanning),
 	     "%s called with hardware scan in progress\n", __func__);
 
+	flush_work(&local->radar_detected_work);
 	rtnl_lock();
 	list_for_each_entry(sdata, &local->interfaces, list)
 		flush_delayed_work(&sdata->dec_tailroom_needed_wk);
@@ -603,6 +604,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
 		ARRAY_SIZE(local->ext_capa);
 
 	INIT_LIST_HEAD(&local->interfaces);
+	INIT_LIST_HEAD(&local->mon_list);
 
 	__hw_addr_init(&local->mc_list);
 
@@ -1186,6 +1188,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 	cancel_work_sync(&local->reconfig_filter);
 	cancel_work_sync(&local->tdls_chsw_work);
 	flush_work(&local->sched_scan_stopped_work);
+	flush_work(&local->radar_detected_work);
 
 	ieee80211_clear_tx_pending(local);
 	rate_control_deinitialize(local);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 6e7b6a07b7d5..737e1f082b0d 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -63,6 +63,7 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	u32 basic_rates = 0;
 	struct cfg80211_chan_def sta_chan_def;
+	struct ieee80211_supported_band *sband;
 
 	/*
 	 * As support for each feature is added, check for matching
@@ -83,7 +84,11 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
 	     (ifmsh->mesh_auth_id == ie->mesh_config->meshconf_auth)))
 		return false;
 
-	ieee80211_sta_get_rates(sdata, ie, ieee80211_get_sdata_band(sdata),
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return false;
+
+	ieee80211_sta_get_rates(sdata, ie, sband->band,
 				&basic_rates);
 
 	if (sdata->vif.bss_conf.basic_rates != basic_rates)
@@ -399,12 +404,13 @@ static int mesh_add_ds_params_ie(struct ieee80211_sub_if_data *sdata,
 int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata,
 		       struct sk_buff *skb)
 {
-	struct ieee80211_local *local = sdata->local;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
 	struct ieee80211_supported_band *sband;
 	u8 *pos;
 
-	sband = local->hw.wiphy->bands[band];
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return -EINVAL;
+
 	if (!sband->ht_cap.ht_supported ||
 	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
 	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
@@ -462,12 +468,13 @@ int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata,
 int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata,
 			struct sk_buff *skb)
 {
-	struct ieee80211_local *local = sdata->local;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
 	struct ieee80211_supported_band *sband;
 	u8 *pos;
 
-	sband = local->hw.wiphy->bands[band];
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return -EINVAL;
+
 	if (!sband->vht_cap.vht_supported ||
 	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
 	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
@@ -916,12 +923,16 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 	struct cfg80211_csa_settings params;
 	struct ieee80211_csa_ie csa_ie;
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
+	struct ieee80211_supported_band *sband;
 	int err;
 	u32 sta_flags;
 
 	sdata_assert_lock(sdata);
 
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return false;
+
 	sta_flags = IEEE80211_STA_DISABLE_VHT;
 	switch (sdata->vif.bss_conf.chandef.width) {
 	case NL80211_CHAN_WIDTH_20_NOHT:
@@ -935,7 +946,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 
 	memset(&params, 0, sizeof(params));
 	memset(&csa_ie, 0, sizeof(csa_ie));
-	err = ieee80211_parse_ch_switch_ie(sdata, elems, band,
+	err = ieee80211_parse_ch_switch_ie(sdata, elems, sband->band,
 					   sta_flags, sdata->vif.addr,
 					   &csa_ie);
 	if (err < 0)
@@ -1100,8 +1111,14 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
 		return;
 
-	if (mesh_matches_local(sdata, &elems))
-		mesh_neighbour_update(sdata, mgmt->sa, &elems);
+	if (mesh_matches_local(sdata, &elems)) {
+		mpl_dbg(sdata, "rssi_threshold=%d,rx_status->signal=%d\n",
+			sdata->u.mesh.mshcfg.rssi_threshold, rx_status->signal);
+		if (!sdata->u.mesh.user_mpm ||
+		    sdata->u.mesh.mshcfg.rssi_threshold == 0 ||
+		    sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal)
+			mesh_neighbour_update(sdata, mgmt->sa, &elems);
+	}
 
 	if (ifmsh->sync_ops)
 		ifmsh->sync_ops->rx_bcn_presp(sdata,
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index b747c9645e43..4005edd71fe8 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -16,6 +16,7 @@
 #define TEST_FRAME_LEN	8192
 #define MAX_METRIC	0xffffffff
 #define ARITH_SHIFT	8
+#define LINK_FAIL_THRESH 95
 
 #define MAX_PREQ_QUEUE_LEN	64
 
@@ -307,10 +308,12 @@ void ieee80211s_update_metric(struct ieee80211_local *local,
 
 	failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK);
 
-	/* moving average, scaled to 100 */
-	sta->mesh->fail_avg =
-		((80 * sta->mesh->fail_avg + 5) / 100 + 20 * failed);
-	if (sta->mesh->fail_avg > 95)
+	/* moving average, scaled to 100.
+	 * feed failure as 100 and success as 0
+	 */
+	ewma_mesh_fail_avg_add(&sta->mesh->fail_avg, failed * 100);
+	if (ewma_mesh_fail_avg_read(&sta->mesh->fail_avg) >
+			LINK_FAIL_THRESH)
 		mesh_plink_broken(sta);
 }
 
@@ -325,6 +328,8 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local,
 	int rate, err;
 	u32 tx_time, estimated_retx;
 	u64 result;
+	unsigned long fail_avg =
+		ewma_mesh_fail_avg_read(&sta->mesh->fail_avg);
 
 	/* Try to get rate based on HW/SW RC algorithm.
 	 * Rate is returned in units of Kbps, correct this
@@ -336,7 +341,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local,
 	if (rate) {
 		err = 0;
 	} else {
-		if (sta->mesh->fail_avg >= 100)
+		if (fail_avg > LINK_FAIL_THRESH)
 			return MAX_METRIC;
 
 		sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo);
@@ -344,7 +349,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local,
 		if (WARN_ON(!rate))
 			return MAX_METRIC;
 
-		err = (sta->mesh->fail_avg << ARITH_SHIFT) / 100;
+		err = (fail_avg << ARITH_SHIFT) / 100;
 	}
 
 	/* bitrate is in units of 100 Kbps, while we need rate in units of
@@ -484,6 +489,9 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata,
 					  ?  mpath->exp_time : exp_time;
 			mesh_path_activate(mpath);
 			spin_unlock_bh(&mpath->state_lock);
+			ewma_mesh_fail_avg_init(&sta->mesh->fail_avg);
+			/* init it at a low value - 0 start is tricky */
+			ewma_mesh_fail_avg_add(&sta->mesh->fail_avg, 1);
 			mesh_path_tx_pending(mpath);
 			/* draft says preq_id should be saved to, but there does
 			 * not seem to be any use for it, skipping by now
@@ -522,6 +530,9 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata,
 					  ?  mpath->exp_time : exp_time;
 			mesh_path_activate(mpath);
 			spin_unlock_bh(&mpath->state_lock);
+			ewma_mesh_fail_avg_init(&sta->mesh->fail_avg);
+			/* init it at a low value - 0 start is tricky */
+			ewma_mesh_fail_avg_add(&sta->mesh->fail_avg, 1);
 			mesh_path_tx_pending(mpath);
 		} else
 			spin_unlock_bh(&mpath->state_lock);
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index f0e6175a9821..97269caafecd 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -397,11 +397,10 @@ struct mesh_path *mesh_path_new(struct ieee80211_sub_if_data *sdata,
 	new_mpath->sdata = sdata;
 	new_mpath->flags = 0;
 	skb_queue_head_init(&new_mpath->frame_queue);
-	new_mpath->timer.data = (unsigned long) new_mpath;
-	new_mpath->timer.function = mesh_path_timer;
 	new_mpath->exp_time = jiffies;
 	spin_lock_init(&new_mpath->state_lock);
-	init_timer(&new_mpath->timer);
+	setup_timer(&new_mpath->timer, mesh_path_timer,
+		    (unsigned long) new_mpath);
 
 	return new_mpath;
 }
@@ -829,6 +828,9 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop)
 	mpath->flags = MESH_PATH_FIXED | MESH_PATH_SN_VALID;
 	mesh_path_activate(mpath);
 	spin_unlock_bh(&mpath->state_lock);
+	ewma_mesh_fail_avg_init(&next_hop->mesh->fail_avg);
+	/* init it at a low value - 0 start is tricky */
+	ewma_mesh_fail_avg_add(&next_hop->mesh->fail_avg, 1);
 	mesh_path_tx_pending(mpath);
 }
 
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 953d71e784a9..1131cd504a15 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -95,19 +95,23 @@ static inline void mesh_plink_fsm_restart(struct sta_info *sta)
 static u32 mesh_set_short_slot_time(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
+	struct ieee80211_supported_band *sband;
 	struct sta_info *sta;
 	u32 erp_rates = 0, changed = 0;
 	int i;
 	bool short_slot = false;
 
-	if (band == NL80211_BAND_5GHZ) {
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return changed;
+
+	if (sband->band == NL80211_BAND_5GHZ) {
 		/* (IEEE 802.11-2012 19.4.5) */
 		short_slot = true;
 		goto out;
-	} else if (band != NL80211_BAND_2GHZ)
+	} else if (sband->band != NL80211_BAND_2GHZ) {
 		goto out;
+	}
 
 	for (i = 0; i < sband->n_bitrates; i++)
 		if (sband->bitrates[i].flags & IEEE80211_RATE_ERP_G)
@@ -123,7 +127,7 @@ static u32 mesh_set_short_slot_time(struct ieee80211_sub_if_data *sdata)
 			continue;
 
 		short_slot = false;
-		if (erp_rates & sta->sta.supp_rates[band])
+		if (erp_rates & sta->sta.supp_rates[sband->band])
 			short_slot = true;
 		 else
 			break;
@@ -249,7 +253,15 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata,
 	mgmt->u.action.u.self_prot.action_code = action;
 
 	if (action != WLAN_SP_MESH_PEERING_CLOSE) {
-		enum nl80211_band band = ieee80211_get_sdata_band(sdata);
+		struct ieee80211_supported_band *sband;
+		enum nl80211_band band;
+
+		sband = ieee80211_get_sband(sdata);
+		if (!sband) {
+			err = -EINVAL;
+			goto free;
+		}
+		band = sband->band;
 
 		/* capability info */
 		pos = skb_put(skb, 2);
@@ -395,13 +407,16 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
 			       struct ieee802_11_elems *elems, bool insert)
 {
 	struct ieee80211_local *local = sdata->local;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
 	struct ieee80211_supported_band *sband;
 	u32 rates, basic_rates = 0, changed = 0;
 	enum ieee80211_sta_rx_bandwidth bw = sta->sta.bandwidth;
 
-	sband = local->hw.wiphy->bands[band];
-	rates = ieee80211_sta_get_rates(sdata, elems, band, &basic_rates);
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return;
+
+	rates = ieee80211_sta_get_rates(sdata, elems, sband->band,
+					&basic_rates);
 
 	spin_lock_bh(&sta->mesh->plink_lock);
 	sta->rx_stats.last_rx = jiffies;
@@ -412,9 +427,9 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	sta->mesh->processed_beacon = true;
 
-	if (sta->sta.supp_rates[band] != rates)
+	if (sta->sta.supp_rates[sband->band] != rates)
 		changed |= IEEE80211_RC_SUPP_RATES_CHANGED;
-	sta->sta.supp_rates[band] = rates;
+	sta->sta.supp_rates[sband->band] = rates;
 
 	if (ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
 					      elems->ht_cap_elem, sta))
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 6e90301154d5..89dff563b1ec 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -6,7 +6,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -1855,11 +1855,16 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata,
 					   u16 capab, bool erp_valid, u8 erp)
 {
 	struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf;
+	struct ieee80211_supported_band *sband;
 	u32 changed = 0;
 	bool use_protection;
 	bool use_short_preamble;
 	bool use_short_slot;
 
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return changed;
+
 	if (erp_valid) {
 		use_protection = (erp & WLAN_ERP_USE_PROTECTION) != 0;
 		use_short_preamble = (erp & WLAN_ERP_BARKER_PREAMBLE) == 0;
@@ -1869,7 +1874,7 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata,
 	}
 
 	use_short_slot = !!(capab & WLAN_CAPABILITY_SHORT_SLOT_TIME);
-	if (ieee80211_get_sdata_band(sdata) == NL80211_BAND_5GHZ)
+	if (sband->band == NL80211_BAND_5GHZ)
 		use_short_slot = true;
 
 	if (use_protection != bss_conf->use_cts_prot) {
@@ -1908,6 +1913,8 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
 	sdata->u.mgd.associated = cbss;
 	memcpy(sdata->u.mgd.bssid, cbss->bssid, ETH_ALEN);
 
+	ieee80211_check_rate_mask(sdata);
+
 	sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE;
 
 	if (sdata->vif.p2p ||
@@ -2797,8 +2804,9 @@ static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code);
 
-	sdata_info(sdata, "disassociated from %pM (Reason: %u)\n",
-		   mgmt->sa, reason_code);
+	sdata_info(sdata, "disassociated from %pM (Reason: %u=%s)\n",
+		   mgmt->sa, reason_code,
+		   ieee80211_get_reason_code_string(reason_code));
 
 	ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
 
@@ -2822,15 +2830,15 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
 			*have_higher_than_11mbit = true;
 
 		/*
-		 * BSS_MEMBERSHIP_SELECTOR_HT_PHY is defined in 802.11n-2009
-		 * 7.3.2.2 as a magic value instead of a rate. Hence, skip it.
+		 * Skip HT and VHT BSS membership selectors since they're not
+		 * rates.
 		 *
-		 * Note: Even through the membership selector and the basic
+		 * Note: Even though the membership selector and the basic
 		 *	 rate flag share the same bit, they are not exactly
 		 *	 the same.
 		 */
-		if (!!(supp_rates[i] & 0x80) &&
-		    (supp_rates[i] & 0x7f) == BSS_MEMBERSHIP_SELECTOR_HT_PHY)
+		if (supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HT_PHY) ||
+		    supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_VHT_PHY))
 			continue;
 
 		for (j = 0; j < sband->n_bitrates; j++) {
@@ -3001,7 +3009,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
-	sband = local->hw.wiphy->bands[ieee80211_get_sdata_band(sdata)];
+	sband = ieee80211_get_sband(sdata);
+	if (!sband) {
+		mutex_unlock(&sdata->local->sta_mtx);
+		ret = false;
+		goto out;
+	}
 
 	/* Set up internal HT/VHT capabilities */
 	if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT))
@@ -3085,6 +3098,18 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	}
 	changed |= BSS_CHANGED_QOS;
 
+	if (elems.max_idle_period_ie) {
+		bss_conf->max_idle_period =
+			le16_to_cpu(elems.max_idle_period_ie->max_idle_period);
+		bss_conf->protected_keep_alive =
+			!!(elems.max_idle_period_ie->idle_options &
+			   WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE);
+		changed |= BSS_CHANGED_KEEP_ALIVE;
+	} else {
+		bss_conf->max_idle_period = 0;
+		bss_conf->protected_keep_alive = false;
+	}
+
 	/* set AID and assoc capability,
 	 * ieee80211_set_associated() will tell the driver */
 	bss_conf->aid = aid;
@@ -3430,6 +3455,30 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	if (bss_conf->cqm_rssi_low &&
+	    ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT) {
+		int sig = -ewma_beacon_signal_read(&ifmgd->ave_beacon_signal);
+		int last_event = ifmgd->last_cqm_event_signal;
+		int low = bss_conf->cqm_rssi_low;
+		int high = bss_conf->cqm_rssi_high;
+
+		if (sig < low &&
+		    (last_event == 0 || last_event >= low)) {
+			ifmgd->last_cqm_event_signal = sig;
+			ieee80211_cqm_rssi_notify(
+				&sdata->vif,
+				NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW,
+				sig, GFP_KERNEL);
+		} else if (sig > high &&
+			   (last_event == 0 || last_event <= high)) {
+			ifmgd->last_cqm_event_signal = sig;
+			ieee80211_cqm_rssi_notify(
+				&sdata->vif,
+				NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH,
+				sig, GFP_KERNEL);
+		}
+	}
+
 	if (ifmgd->flags & IEEE80211_STA_CONNECTION_POLL) {
 		mlme_dbg_ratelimited(sdata,
 				     "cancelling AP probe due to a received beacon\n");
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 76a8bcd8ef11..a87d195c4a61 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -10,7 +10,7 @@ static void ieee80211_sched_scan_cancel(struct ieee80211_local *local)
 {
 	if (ieee80211_request_sched_scan_stop(local))
 		return;
-	cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
+	cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy, 0);
 }
 
 int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 206698bc93f4..ea1f4315c521 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -2,6 +2,7 @@
  * Copyright 2002-2005, Instant802 Networks, Inc.
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
+ * Copyright 2017	Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -61,6 +62,28 @@ void rate_control_rate_init(struct sta_info *sta)
 	set_sta_flag(sta, WLAN_STA_RATE_CONTROL);
 }
 
+void rate_control_tx_status(struct ieee80211_local *local,
+			    struct ieee80211_supported_band *sband,
+			    struct ieee80211_tx_status *st)
+{
+	struct rate_control_ref *ref = local->rate_ctrl;
+	struct sta_info *sta = container_of(st->sta, struct sta_info, sta);
+	void *priv_sta = sta->rate_ctrl_priv;
+
+	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
+		return;
+
+	spin_lock_bh(&sta->rate_ctrl_lock);
+	if (ref->ops->tx_status_ext)
+		ref->ops->tx_status_ext(ref->priv, sband, priv_sta, st);
+	else if (st->skb)
+		ref->ops->tx_status(ref->priv, sband, st->sta, priv_sta, st->skb);
+	else
+		WARN_ON_ONCE(1);
+
+	spin_unlock_bh(&sta->rate_ctrl_lock);
+}
+
 void rate_control_rate_update(struct ieee80211_local *local,
 				    struct ieee80211_supported_band *sband,
 				    struct sta_info *sta, u32 changed)
@@ -173,9 +196,11 @@ ieee80211_rate_control_ops_get(const char *name)
 		/* try default if specific alg requested but not found */
 		ops = ieee80211_try_rate_control_ops_get(ieee80211_default_rc_algo);
 
-	/* try built-in one if specific alg requested but not found */
-	if (!ops && strlen(CONFIG_MAC80211_RC_DEFAULT))
+	/* Note: check for > 0 is intentional to avoid clang warning */
+	if (!ops && (strlen(CONFIG_MAC80211_RC_DEFAULT) > 0))
+		/* try built-in one if specific alg requested but not found */
 		ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT);
+
 	kernel_param_unlock(THIS_MODULE);
 
 	return ops;
@@ -208,7 +233,6 @@ static struct rate_control_ref *rate_control_alloc(const char *name,
 	ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL);
 	if (!ref)
 		return NULL;
-	ref->local = local;
 	ref->ops = ieee80211_rate_control_ops_get(name);
 	if (!ref->ops)
 		goto free;
@@ -229,18 +253,45 @@ free:
 	return NULL;
 }
 
-static void rate_control_free(struct rate_control_ref *ctrl_ref)
+static void rate_control_free(struct ieee80211_local *local,
+			      struct rate_control_ref *ctrl_ref)
 {
 	ctrl_ref->ops->free(ctrl_ref->priv);
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-	debugfs_remove_recursive(ctrl_ref->local->debugfs.rcdir);
-	ctrl_ref->local->debugfs.rcdir = NULL;
+	debugfs_remove_recursive(local->debugfs.rcdir);
+	local->debugfs.rcdir = NULL;
 #endif
 
 	kfree(ctrl_ref);
 }
 
+void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_supported_band *sband;
+	u32 user_mask, basic_rates = sdata->vif.bss_conf.basic_rates;
+	enum nl80211_band band;
+
+	if (WARN_ON(!sdata->vif.bss_conf.chandef.chan))
+		return;
+
+	if (WARN_ON_ONCE(!basic_rates))
+		return;
+
+	band = sdata->vif.bss_conf.chandef.chan->band;
+	user_mask = sdata->rc_rateidx_mask[band];
+	sband = local->hw.wiphy->bands[band];
+
+	if (user_mask & basic_rates)
+		return;
+
+	sdata_dbg(sdata,
+		  "no overlap between basic rates (0x%x) and user mask (0x%x on band %d) - clearing the latter",
+		  basic_rates, user_mask, band);
+	sdata->rc_rateidx_mask[band] = (1 << sband->n_bitrates) - 1;
+}
+
 static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc)
 {
 	struct sk_buff *skb = txrc->skb;
@@ -875,7 +926,9 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 	struct ieee80211_sta_rates *old;
 	struct ieee80211_supported_band *sband;
 
-	sband = hw->wiphy->bands[ieee80211_get_sdata_band(sta->sdata)];
+	sband = ieee80211_get_sband(sta->sdata);
+	if (!sband)
+		return -EINVAL;
 	rate_control_apply_mask_ratetbl(sta, sband, rates);
 	/*
 	 * mac80211 guarantees that this function will not be called
@@ -936,6 +989,6 @@ void rate_control_deinitialize(struct ieee80211_local *local)
 		return;
 
 	local->rate_ctrl = NULL;
-	rate_control_free(ref);
+	rate_control_free(local, ref);
 }
 
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index 8d3260785b94..8212bfeb71d6 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -20,7 +20,6 @@
 #include "driver-ops.h"
 
 struct rate_control_ref {
-	struct ieee80211_local *local;
 	const struct rate_control_ops *ops;
 	void *priv;
 };
@@ -29,47 +28,9 @@ void rate_control_get_rate(struct ieee80211_sub_if_data *sdata,
 			   struct sta_info *sta,
 			   struct ieee80211_tx_rate_control *txrc);
 
-static inline void rate_control_tx_status(struct ieee80211_local *local,
-					  struct ieee80211_supported_band *sband,
-					  struct sta_info *sta,
-					  struct sk_buff *skb)
-{
-	struct rate_control_ref *ref = local->rate_ctrl;
-	struct ieee80211_sta *ista = &sta->sta;
-	void *priv_sta = sta->rate_ctrl_priv;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-
-	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
-		return;
-
-	spin_lock_bh(&sta->rate_ctrl_lock);
-	if (ref->ops->tx_status)
-		ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb);
-	else
-		ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
-	spin_unlock_bh(&sta->rate_ctrl_lock);
-}
-
-static inline void
-rate_control_tx_status_noskb(struct ieee80211_local *local,
-			     struct ieee80211_supported_band *sband,
-			     struct sta_info *sta,
-			     struct ieee80211_tx_info *info)
-{
-	struct rate_control_ref *ref = local->rate_ctrl;
-	struct ieee80211_sta *ista = &sta->sta;
-	void *priv_sta = sta->rate_ctrl_priv;
-
-	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
-		return;
-
-	if (WARN_ON_ONCE(!ref->ops->tx_status_noskb))
-		return;
-
-	spin_lock_bh(&sta->rate_ctrl_lock);
-	ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
-	spin_unlock_bh(&sta->rate_ctrl_lock);
-}
+void rate_control_tx_status(struct ieee80211_local *local,
+			    struct ieee80211_supported_band *sband,
+			    struct ieee80211_tx_status *st);
 
 void rate_control_rate_init(struct sta_info *sta);
 void rate_control_rate_update(struct ieee80211_local *local,
@@ -111,6 +72,8 @@ static inline void rate_control_remove_sta_debugfs(struct sta_info *sta)
 #endif
 }
 
+void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata);
+
 /* Get a reference to the rate control algorithm. If `name' is NULL, get the
  * first available algorithm. */
 int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local,
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 3ebe4405a2d4..9766c1cc4b0a 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -264,9 +264,9 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 
 static void
 minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
-		   struct ieee80211_sta *sta, void *priv_sta,
-		   struct ieee80211_tx_info *info)
+		   void *priv_sta, struct ieee80211_tx_status *st)
 {
+	struct ieee80211_tx_info *info = st->info;
 	struct minstrel_priv *mp = priv;
 	struct minstrel_sta_info *mi = priv_sta;
 	struct ieee80211_tx_rate *ar = info->status.rates;
@@ -726,7 +726,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta)
 
 const struct rate_control_ops mac80211_minstrel = {
 	.name = "minstrel",
-	.tx_status_noskb = minstrel_tx_status,
+	.tx_status_ext = minstrel_tx_status,
 	.get_rate = minstrel_get_rate,
 	.rate_init = minstrel_rate_init,
 	.alloc = minstrel_alloc,
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 8e783e197e93..4a5bdad9f303 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -678,9 +678,9 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb)
 
 static void
 minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
-                      struct ieee80211_sta *sta, void *priv_sta,
-                      struct ieee80211_tx_info *info)
+                      void *priv_sta, struct ieee80211_tx_status *st)
 {
+	struct ieee80211_tx_info *info = st->info;
 	struct minstrel_ht_sta_priv *msp = priv_sta;
 	struct minstrel_ht_sta *mi = &msp->ht;
 	struct ieee80211_tx_rate *ar = info->status.rates;
@@ -690,8 +690,8 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
 	int i;
 
 	if (!msp->is_ht)
-		return mac80211_minstrel.tx_status_noskb(priv, sband, sta,
-							 &msp->legacy, info);
+		return mac80211_minstrel.tx_status_ext(priv, sband,
+						       &msp->legacy, st);
 
 	/* This packet was aggregated but doesn't carry status info */
 	if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
@@ -1374,7 +1374,7 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta)
 
 static const struct rate_control_ops mac80211_minstrel_ht = {
 	.name = "minstrel_ht",
-	.tx_status_noskb = minstrel_ht_tx_status,
+	.tx_status_ext = minstrel_ht_tx_status,
 	.get_rate = minstrel_ht_get_rate,
 	.rate_init = minstrel_ht_rate_init,
 	.rate_update = minstrel_ht_rate_update,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index e48724a6725e..35f4c7d7a500 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -95,24 +95,13 @@ static u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
  * This function cleans up the SKB, i.e. it removes all the stuff
  * only useful for monitoring.
  */
-static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
-					   struct sk_buff *skb,
-					   unsigned int rtap_vendor_space)
+static void remove_monitor_info(struct sk_buff *skb,
+				unsigned int present_fcs_len,
+				unsigned int rtap_vendor_space)
 {
-	if (ieee80211_hw_check(&local->hw, RX_INCLUDES_FCS)) {
-		if (likely(skb->len > FCS_LEN))
-			__pskb_trim(skb, skb->len - FCS_LEN);
-		else {
-			/* driver bug */
-			WARN_ON(1);
-			dev_kfree_skb(skb);
-			return NULL;
-		}
-	}
-
+	if (present_fcs_len)
+		__pskb_trim(skb, skb->len - present_fcs_len);
 	__pskb_pull(skb, rtap_vendor_space);
-
-	return skb;
 }
 
 static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len,
@@ -167,7 +156,7 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
 	/* padding for RX_FLAGS if necessary */
 	len = ALIGN(len, 2);
 
-	if (status->flag & RX_FLAG_HT) /* HT info */
+	if (status->encoding == RX_ENC_HT) /* HT info */
 		len += 3;
 
 	if (status->flag & RX_FLAG_AMPDU_DETAILS) {
@@ -175,7 +164,7 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
 		len += 8;
 	}
 
-	if (status->flag & RX_FLAG_VHT) {
+	if (status->encoding == RX_ENC_VHT) {
 		len = ALIGN(len, 2);
 		len += 12;
 	}
@@ -208,6 +197,51 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
 	return len;
 }
 
+static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata,
+					 struct sk_buff *skb,
+					 int rtap_vendor_space)
+{
+	struct {
+		struct ieee80211_hdr_3addr hdr;
+		u8 category;
+		u8 action_code;
+	} __packed action;
+
+	if (!sdata)
+		return;
+
+	BUILD_BUG_ON(sizeof(action) != IEEE80211_MIN_ACTION_SIZE + 1);
+
+	if (skb->len < rtap_vendor_space + sizeof(action) +
+		       VHT_MUMIMO_GROUPS_DATA_LEN)
+		return;
+
+	if (!is_valid_ether_addr(sdata->u.mntr.mu_follow_addr))
+		return;
+
+	skb_copy_bits(skb, rtap_vendor_space, &action, sizeof(action));
+
+	if (!ieee80211_is_action(action.hdr.frame_control))
+		return;
+
+	if (action.category != WLAN_CATEGORY_VHT)
+		return;
+
+	if (action.action_code != WLAN_VHT_ACTION_GROUPID_MGMT)
+		return;
+
+	if (!ether_addr_equal(action.hdr.addr1, sdata->u.mntr.mu_follow_addr))
+		return;
+
+	skb = skb_copy(skb, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME;
+	skb_queue_tail(&sdata->skb_queue, skb);
+	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+}
+
 /*
  * ieee80211_add_rx_radiotap_header - add radiotap header
  *
@@ -295,12 +329,12 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos |= IEEE80211_RADIOTAP_F_FCS;
 	if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC))
 		*pos |= IEEE80211_RADIOTAP_F_BADFCS;
-	if (status->flag & RX_FLAG_SHORTPRE)
+	if (status->enc_flags & RX_ENC_FLAG_SHORTPRE)
 		*pos |= IEEE80211_RADIOTAP_F_SHORTPRE;
 	pos++;
 
 	/* IEEE80211_RADIOTAP_RATE */
-	if (!rate || status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) {
+	if (!rate || status->encoding != RX_ENC_LEGACY) {
 		/*
 		 * Without rate information don't add it. If we have,
 		 * MCS information is a separate field in radiotap,
@@ -311,9 +345,9 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	} else {
 		int shift = 0;
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_RATE);
-		if (status->flag & RX_FLAG_10MHZ)
+		if (status->bw == RATE_INFO_BW_10)
 			shift = 1;
-		else if (status->flag & RX_FLAG_5MHZ)
+		else if (status->bw == RATE_INFO_BW_5)
 			shift = 2;
 		*pos = DIV_ROUND_UP(rate->bitrate, 5 * (1 << shift));
 	}
@@ -322,14 +356,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	/* IEEE80211_RADIOTAP_CHANNEL */
 	put_unaligned_le16(status->freq, pos);
 	pos += 2;
-	if (status->flag & RX_FLAG_10MHZ)
+	if (status->bw == RATE_INFO_BW_10)
 		channel_flags |= IEEE80211_CHAN_HALF;
-	else if (status->flag & RX_FLAG_5MHZ)
+	else if (status->bw == RATE_INFO_BW_5)
 		channel_flags |= IEEE80211_CHAN_QUARTER;
 
 	if (status->band == NL80211_BAND_5GHZ)
 		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ;
-	else if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT))
+	else if (status->encoding != RX_ENC_LEGACY)
 		channel_flags |= IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ;
 	else if (rate && rate->flags & IEEE80211_RATE_ERP_G)
 		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
@@ -368,21 +402,21 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	put_unaligned_le16(rx_flags, pos);
 	pos += 2;
 
-	if (status->flag & RX_FLAG_HT) {
+	if (status->encoding == RX_ENC_HT) {
 		unsigned int stbc;
 
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS);
 		*pos++ = local->hw.radiotap_mcs_details;
 		*pos = 0;
-		if (status->flag & RX_FLAG_SHORT_GI)
+		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			*pos |= IEEE80211_RADIOTAP_MCS_SGI;
-		if (status->flag & RX_FLAG_40MHZ)
+		if (status->bw == RATE_INFO_BW_40)
 			*pos |= IEEE80211_RADIOTAP_MCS_BW_40;
-		if (status->flag & RX_FLAG_HT_GF)
+		if (status->enc_flags & RX_ENC_FLAG_HT_GF)
 			*pos |= IEEE80211_RADIOTAP_MCS_FMT_GF;
-		if (status->flag & RX_FLAG_LDPC)
+		if (status->enc_flags & RX_ENC_FLAG_LDPC)
 			*pos |= IEEE80211_RADIOTAP_MCS_FEC_LDPC;
-		stbc = (status->flag & RX_FLAG_STBC_MASK) >> RX_FLAG_STBC_SHIFT;
+		stbc = (status->enc_flags & RX_ENC_FLAG_STBC_MASK) >> RX_ENC_FLAG_STBC_SHIFT;
 		*pos |= stbc << IEEE80211_RADIOTAP_MCS_STBC_SHIFT;
 		pos++;
 		*pos++ = status->rate_idx;
@@ -415,35 +449,40 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos++ = 0;
 	}
 
-	if (status->flag & RX_FLAG_VHT) {
+	if (status->encoding == RX_ENC_VHT) {
 		u16 known = local->hw.radiotap_vht_details;
 
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT);
 		put_unaligned_le16(known, pos);
 		pos += 2;
 		/* flags */
-		if (status->flag & RX_FLAG_SHORT_GI)
+		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI;
 		/* in VHT, STBC is binary */
-		if (status->flag & RX_FLAG_STBC_MASK)
+		if (status->enc_flags & RX_ENC_FLAG_STBC_MASK)
 			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_STBC;
-		if (status->vht_flag & RX_VHT_FLAG_BF)
+		if (status->enc_flags & RX_ENC_FLAG_BF)
 			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_BEAMFORMED;
 		pos++;
 		/* bandwidth */
-		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
+		switch (status->bw) {
+		case RATE_INFO_BW_80:
 			*pos++ = 4;
-		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
+			break;
+		case RATE_INFO_BW_160:
 			*pos++ = 11;
-		else if (status->flag & RX_FLAG_40MHZ)
+			break;
+		case RATE_INFO_BW_40:
 			*pos++ = 1;
-		else /* 20 MHz */
+			break;
+		default:
 			*pos++ = 0;
+		}
 		/* MCS/NSS */
-		*pos = (status->rate_idx << 4) | status->vht_nss;
+		*pos = (status->rate_idx << 4) | status->nss;
 		pos += 4;
 		/* coding field */
-		if (status->flag & RX_FLAG_LDPC)
+		if (status->enc_flags & RX_ENC_FLAG_LDPC)
 			*pos |= IEEE80211_RADIOTAP_CODING_LDPC_USER0;
 		pos++;
 		/* group ID */
@@ -499,6 +538,59 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	}
 }
 
+static struct sk_buff *
+ieee80211_make_monitor_skb(struct ieee80211_local *local,
+			   struct sk_buff **origskb,
+			   struct ieee80211_rate *rate,
+			   int rtap_vendor_space, bool use_origskb)
+{
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(*origskb);
+	int rt_hdrlen, needed_headroom;
+	struct sk_buff *skb;
+
+	/* room for the radiotap header based on driver features */
+	rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, *origskb);
+	needed_headroom = rt_hdrlen - rtap_vendor_space;
+
+	if (use_origskb) {
+		/* only need to expand headroom if necessary */
+		skb = *origskb;
+		*origskb = NULL;
+
+		/*
+		 * This shouldn't trigger often because most devices have an
+		 * RX header they pull before we get here, and that should
+		 * be big enough for our radiotap information. We should
+		 * probably export the length to drivers so that we can have
+		 * them allocate enough headroom to start with.
+		 */
+		if (skb_headroom(skb) < needed_headroom &&
+		    pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC)) {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
+	} else {
+		/*
+		 * Need to make a copy and possibly remove radiotap header
+		 * and FCS from the original.
+		 */
+		skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC);
+
+		if (!skb)
+			return NULL;
+	}
+
+	/* prepend radiotap information */
+	ieee80211_add_rx_radiotap_header(local, skb, rate, rt_hdrlen, true);
+
+	skb_reset_mac_header(skb);
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	skb->pkt_type = PACKET_OTHERHOST;
+	skb->protocol = htons(ETH_P_802_2);
+
+	return skb;
+}
+
 /*
  * This function copies a received frame to all monitor interfaces and
  * returns a cleaned-up SKB that no longer includes the FCS nor the
@@ -510,14 +602,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(origskb);
 	struct ieee80211_sub_if_data *sdata;
-	int rt_hdrlen, needed_headroom;
-	struct sk_buff *skb, *skb2;
-	struct net_device *prev_dev = NULL;
+	struct sk_buff *monskb = NULL;
 	int present_fcs_len = 0;
 	unsigned int rtap_vendor_space = 0;
-	struct ieee80211_mgmt *mgmt;
 	struct ieee80211_sub_if_data *monitor_sdata =
 		rcu_dereference(local->monitor_sdata);
+	bool only_monitor = false;
 
 	if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) {
 		struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data;
@@ -534,8 +624,15 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	 * the SKB because it has a bad FCS/PLCP checksum.
 	 */
 
-	if (ieee80211_hw_check(&local->hw, RX_INCLUDES_FCS))
+	if (ieee80211_hw_check(&local->hw, RX_INCLUDES_FCS)) {
+		if (unlikely(origskb->len <= FCS_LEN)) {
+			/* driver bug */
+			WARN_ON(1);
+			dev_kfree_skb(origskb);
+			return NULL;
+		}
 		present_fcs_len = FCS_LEN;
+	}
 
 	/* ensure hdr->frame_control and vendor radiotap data are in skb head */
 	if (!pskb_may_pull(origskb, 2 + rtap_vendor_space)) {
@@ -543,104 +640,62 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 		return NULL;
 	}
 
+	only_monitor = should_drop_frame(origskb, present_fcs_len,
+					 rtap_vendor_space);
+
 	if (!local->monitors || (status->flag & RX_FLAG_SKIP_MONITOR)) {
-		if (should_drop_frame(origskb, present_fcs_len,
-				      rtap_vendor_space)) {
+		if (only_monitor) {
 			dev_kfree_skb(origskb);
 			return NULL;
 		}
 
-		return remove_monitor_info(local, origskb, rtap_vendor_space);
-	}
-
-	/* room for the radiotap header based on driver features */
-	rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, origskb);
-	needed_headroom = rt_hdrlen - rtap_vendor_space;
-
-	if (should_drop_frame(origskb, present_fcs_len, rtap_vendor_space)) {
-		/* only need to expand headroom if necessary */
-		skb = origskb;
-		origskb = NULL;
-
-		/*
-		 * This shouldn't trigger often because most devices have an
-		 * RX header they pull before we get here, and that should
-		 * be big enough for our radiotap information. We should
-		 * probably export the length to drivers so that we can have
-		 * them allocate enough headroom to start with.
-		 */
-		if (skb_headroom(skb) < needed_headroom &&
-		    pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC)) {
-			dev_kfree_skb(skb);
-			return NULL;
-		}
-	} else {
-		/*
-		 * Need to make a copy and possibly remove radiotap header
-		 * and FCS from the original.
-		 */
-		skb = skb_copy_expand(origskb, needed_headroom, 0, GFP_ATOMIC);
-
-		origskb = remove_monitor_info(local, origskb,
-					      rtap_vendor_space);
-
-		if (!skb)
-			return origskb;
+		remove_monitor_info(origskb, present_fcs_len,
+				    rtap_vendor_space);
+		return origskb;
 	}
 
-	/* prepend radiotap information */
-	ieee80211_add_rx_radiotap_header(local, skb, rate, rt_hdrlen, true);
+	ieee80211_handle_mu_mimo_mon(monitor_sdata, origskb, rtap_vendor_space);
 
-	skb_reset_mac_header(skb);
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	skb->pkt_type = PACKET_OTHERHOST;
-	skb->protocol = htons(ETH_P_802_2);
+	list_for_each_entry_rcu(sdata, &local->mon_list, u.mntr.list) {
+		bool last_monitor = list_is_last(&sdata->u.mntr.list,
+						 &local->mon_list);
 
-	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
-		if (sdata->vif.type != NL80211_IFTYPE_MONITOR)
-			continue;
+		if (!monskb)
+			monskb = ieee80211_make_monitor_skb(local, &origskb,
+							    rate,
+							    rtap_vendor_space,
+							    only_monitor &&
+							    last_monitor);
 
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
-			continue;
+		if (monskb) {
+			struct sk_buff *skb;
 
-		if (!ieee80211_sdata_running(sdata))
-			continue;
+			if (last_monitor) {
+				skb = monskb;
+				monskb = NULL;
+			} else {
+				skb = skb_clone(monskb, GFP_ATOMIC);
+			}
 
-		if (prev_dev) {
-			skb2 = skb_clone(skb, GFP_ATOMIC);
-			if (skb2) {
-				skb2->dev = prev_dev;
-				netif_receive_skb(skb2);
+			if (skb) {
+				skb->dev = sdata->dev;
+				ieee80211_rx_stats(skb->dev, skb->len);
+				netif_receive_skb(skb);
 			}
 		}
 
-		prev_dev = sdata->dev;
-		ieee80211_rx_stats(sdata->dev, skb->len);
+		if (last_monitor)
+			break;
 	}
 
-	mgmt = (void *)skb->data;
-	if (monitor_sdata &&
-	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + VHT_MUMIMO_GROUPS_DATA_LEN &&
-	    ieee80211_is_action(mgmt->frame_control) &&
-	    mgmt->u.action.category == WLAN_CATEGORY_VHT &&
-	    mgmt->u.action.u.vht_group_notif.action_code == WLAN_VHT_ACTION_GROUPID_MGMT &&
-	    is_valid_ether_addr(monitor_sdata->u.mntr.mu_follow_addr) &&
-	    ether_addr_equal(mgmt->da, monitor_sdata->u.mntr.mu_follow_addr)) {
-		struct sk_buff *mu_skb = skb_copy(skb, GFP_ATOMIC);
-
-		if (mu_skb) {
-			mu_skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME;
-			skb_queue_tail(&monitor_sdata->skb_queue, mu_skb);
-			ieee80211_queue_work(&local->hw, &monitor_sdata->work);
-		}
-	}
+	/* this happens if last_monitor was erroneously false */
+	dev_kfree_skb(monskb);
 
-	if (prev_dev) {
-		skb->dev = prev_dev;
-		netif_receive_skb(skb);
-	} else
-		dev_kfree_skb(skb);
+	/* ditto */
+	if (!origskb)
+		return NULL;
 
+	remove_monitor_info(origskb, present_fcs_len, rtap_vendor_space);
 	return origskb;
 }
 
@@ -3286,8 +3341,8 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx,
 		status = IEEE80211_SKB_RXCB((rx->skb));
 
 		sband = rx->local->hw.wiphy->bands[status->band];
-		if (!(status->flag & RX_FLAG_HT) &&
-		    !(status->flag & RX_FLAG_VHT))
+		if (!(status->encoding == RX_ENC_HT) &&
+		    !(status->encoding == RX_ENC_VHT))
 			rate = &sband->bitrates[status->rate_idx];
 
 		ieee80211_rx_cooked_monitor(rx, rate);
@@ -3524,7 +3579,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type);
-	int multicast = is_multicast_ether_addr(hdr->addr1);
+	bool multicast = is_multicast_ether_addr(hdr->addr1);
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_STATION:
@@ -3548,7 +3603,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 			return false;
 		if (!rx->sta) {
 			int rate_idx;
-			if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT))
+			if (status->encoding != RX_ENC_LEGACY)
 				rate_idx = 0; /* TODO: HT/VHT rates */
 			else
 				rate_idx = status->rate_idx;
@@ -3568,7 +3623,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 			return false;
 		if (!rx->sta) {
 			int rate_idx;
-			if (status->flag & RX_FLAG_HT)
+			if (status->encoding != RX_ENC_LEGACY)
 				rate_idx = 0; /* TODO: HT rates */
 			else
 				rate_idx = status->rate_idx;
@@ -3610,6 +3665,27 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 			    !ether_addr_equal(bssid, hdr->addr1))
 				return false;
 		}
+
+		/*
+		 * 802.11-2016 Table 9-26 says that for data frames, A1 must be
+		 * the BSSID - we've checked that already but may have accepted
+		 * the wildcard (ff:ff:ff:ff:ff:ff).
+		 *
+		 * It also says:
+		 *	The BSSID of the Data frame is determined as follows:
+		 *	a) If the STA is contained within an AP or is associated
+		 *	   with an AP, the BSSID is the address currently in use
+		 *	   by the STA contained in the AP.
+		 *
+		 * So we should not accept data frames with an address that's
+		 * multicast.
+		 *
+		 * Accepting it also opens a security problem because stations
+		 * could encrypt it with the GTK and inject traffic that way.
+		 */
+		if (ieee80211_is_data(hdr->frame_control) && multicast)
+			return false;
+
 		return true;
 	case NL80211_IFTYPE_WDS:
 		if (bssid || !ieee80211_is_data(hdr->frame_control))
@@ -4210,7 +4286,8 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 		 * we probably can't have a valid rate here anyway.
 		 */
 
-		if (status->flag & RX_FLAG_HT) {
+		switch (status->encoding) {
+		case RX_ENC_HT:
 			/*
 			 * rate_idx is MCS index, which can be [0-76]
 			 * as documented on:
@@ -4228,14 +4305,19 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 				 status->rate_idx,
 				 status->rate_idx))
 				goto drop;
-		} else if (status->flag & RX_FLAG_VHT) {
+			break;
+		case RX_ENC_VHT:
 			if (WARN_ONCE(status->rate_idx > 9 ||
-				      !status->vht_nss ||
-				      status->vht_nss > 8,
+				      !status->nss ||
+				      status->nss > 8,
 				      "Rate marked as a VHT rate but data is invalid: MCS: %d, NSS: %d\n",
-				      status->rate_idx, status->vht_nss))
+				      status->rate_idx, status->nss))
 				goto drop;
-		} else {
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			/* fall through */
+		case RX_ENC_LEGACY:
 			if (WARN_ON(status->rate_idx >= sband->n_bitrates))
 				goto drop;
 			rate = &sband->bitrates[status->rate_idx];
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index faab3c490d2b..47d2ed570470 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -79,9 +79,9 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 		bss_meta.signal = (rx_status->signal * 100) / local->hw.max_signal;
 
 	bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_20;
-	if (rx_status->flag & RX_FLAG_5MHZ)
+	if (rx_status->bw == RATE_INFO_BW_5)
 		bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_5;
-	if (rx_status->flag & RX_FLAG_10MHZ)
+	else if (rx_status->bw == RATE_INFO_BW_10)
 		bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_10;
 
 	bss_meta.chan = channel;
@@ -174,8 +174,8 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 	if (beacon) {
 		struct ieee80211_supported_band *sband =
 			local->hw.wiphy->bands[rx_status->band];
-		if (!(rx_status->flag & RX_FLAG_HT) &&
-		    !(rx_status->flag & RX_FLAG_VHT))
+		if (!(rx_status->encoding == RX_ENC_HT) &&
+		    !(rx_status->encoding == RX_ENC_VHT))
 			bss->beacon_rate =
 				&sband->bitrates[rx_status->rate_idx];
 	}
@@ -1219,7 +1219,7 @@ void ieee80211_sched_scan_results(struct ieee80211_hw *hw)
 
 	trace_api_sched_scan_results(local);
 
-	cfg80211_sched_scan_results(hw->wiphy);
+	cfg80211_sched_scan_results(hw->wiphy, 0);
 }
 EXPORT_SYMBOL(ieee80211_sched_scan_results);
 
@@ -1239,7 +1239,7 @@ void ieee80211_sched_scan_end(struct ieee80211_local *local)
 
 	mutex_unlock(&local->mtx);
 
-	cfg80211_sched_scan_stopped(local->hw.wiphy);
+	cfg80211_sched_scan_stopped(local->hw.wiphy, 0);
 }
 
 void ieee80211_sched_scan_stopped_work(struct work_struct *work)
diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c
index 97f4c9d6b54c..0782e486fe89 100644
--- a/net/mac80211/spectmgmt.c
+++ b/net/mac80211/spectmgmt.c
@@ -132,9 +132,9 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
 		struct ieee80211_vht_operation vht_oper = {
 			.chan_width =
 				wide_bw_chansw_ie->new_channel_width,
-			.center_freq_seg1_idx =
+			.center_freq_seg0_idx =
 				wide_bw_chansw_ie->new_center_freq_seg0,
-			.center_freq_seg2_idx =
+			.center_freq_seg1_idx =
 				wide_bw_chansw_ie->new_center_freq_seg1,
 			/* .basic_mcs_set doesn't matter */
 		};
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 3323a2fb289b..7cdf7a835bb0 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2,7 +2,7 @@
  * Copyright 2002-2005, Instant802 Networks, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -395,10 +395,15 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	sta->sta.smps_mode = IEEE80211_SMPS_OFF;
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
 	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
-		struct ieee80211_supported_band *sband =
-			hw->wiphy->bands[ieee80211_get_sdata_band(sdata)];
-		u8 smps = (sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >>
-				IEEE80211_HT_CAP_SM_PS_SHIFT;
+		struct ieee80211_supported_band *sband;
+		u8 smps;
+
+		sband = ieee80211_get_sband(sdata);
+		if (!sband)
+			goto free_txq;
+
+		smps = (sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >>
+			IEEE80211_HT_CAP_SM_PS_SHIFT;
 		/*
 		 * Assume that hostapd advertises our caps in the beacon and
 		 * this is the known_smps_mode for a station that just assciated
@@ -1957,24 +1962,32 @@ sta_get_last_rx_stats(struct sta_info *sta)
 static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate,
 				  struct rate_info *rinfo)
 {
-	rinfo->bw = (rate & STA_STATS_RATE_BW_MASK) >>
-		STA_STATS_RATE_BW_SHIFT;
+	rinfo->bw = STA_STATS_GET(BW, rate);
 
-	if (rate & STA_STATS_RATE_VHT) {
+	switch (STA_STATS_GET(TYPE, rate)) {
+	case STA_STATS_RATE_TYPE_VHT:
 		rinfo->flags = RATE_INFO_FLAGS_VHT_MCS;
-		rinfo->mcs = rate & 0xf;
-		rinfo->nss = (rate & 0xf0) >> 4;
-	} else if (rate & STA_STATS_RATE_HT) {
+		rinfo->mcs = STA_STATS_GET(VHT_MCS, rate);
+		rinfo->nss = STA_STATS_GET(VHT_NSS, rate);
+		if (STA_STATS_GET(SGI, rate))
+			rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+		break;
+	case STA_STATS_RATE_TYPE_HT:
 		rinfo->flags = RATE_INFO_FLAGS_MCS;
-		rinfo->mcs = rate & 0xff;
-	} else if (rate & STA_STATS_RATE_LEGACY) {
+		rinfo->mcs = STA_STATS_GET(HT_MCS, rate);
+		if (STA_STATS_GET(SGI, rate))
+			rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+		break;
+	case STA_STATS_RATE_TYPE_LEGACY: {
 		struct ieee80211_supported_band *sband;
 		u16 brate;
 		unsigned int shift;
+		int band = STA_STATS_GET(LEGACY_BAND, rate);
+		int rate_idx = STA_STATS_GET(LEGACY_IDX, rate);
 
 		rinfo->flags = 0;
-		sband = local->hw.wiphy->bands[(rate >> 4) & 0xf];
-		brate = sband->bitrates[rate & 0xf].bitrate;
+		sband = local->hw.wiphy->bands[band];
+		brate = sband->bitrates[rate_idx].bitrate;
 		if (rinfo->bw == RATE_INFO_BW_5)
 			shift = 2;
 		else if (rinfo->bw == RATE_INFO_BW_10)
@@ -1982,10 +1995,9 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate,
 		else
 			shift = 0;
 		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
+		break;
+		}
 	}
-
-	if (rate & STA_STATS_RATE_SGI)
-		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
 }
 
 static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo)
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index e65cda34d2bc..5609cacb20d5 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -1,7 +1,7 @@
 /*
  * Copyright 2002-2005, Devicescape Software, Inc.
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright(c) 2015-2016 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -16,6 +16,7 @@
 #include <linux/if_ether.h>
 #include <linux/workqueue.h>
 #include <linux/average.h>
+#include <linux/bitfield.h>
 #include <linux/etherdevice.h>
 #include <linux/rhashtable.h>
 #include <linux/u64_stats_sync.h>
@@ -324,6 +325,9 @@ struct ieee80211_fast_rx {
 	struct rcu_head rcu_head;
 };
 
+/* we use only values in the range 0-100, so pick a large precision */
+DECLARE_EWMA(mesh_fail_avg, 20, 8)
+
 /**
  * struct mesh_sta - mesh STA information
  * @plink_lock: serialize access to plink fields
@@ -369,7 +373,7 @@ struct mesh_sta {
 	enum nl80211_mesh_power_mode nonpeer_pm;
 
 	/* moving percentage of failed MSDUs */
-	unsigned int fail_avg;
+	struct ewma_mesh_fail_avg fail_avg;
 };
 
 DECLARE_EWMA(signal, 10, 8)
@@ -724,40 +728,55 @@ void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta);
 
 unsigned long ieee80211_sta_last_active(struct sta_info *sta);
 
+enum sta_stats_type {
+	STA_STATS_RATE_TYPE_INVALID = 0,
+	STA_STATS_RATE_TYPE_LEGACY,
+	STA_STATS_RATE_TYPE_HT,
+	STA_STATS_RATE_TYPE_VHT,
+};
+
+#define STA_STATS_FIELD_HT_MCS		GENMASK( 7,  0)
+#define STA_STATS_FIELD_LEGACY_IDX	GENMASK( 3,  0)
+#define STA_STATS_FIELD_LEGACY_BAND	GENMASK( 7,  4)
+#define STA_STATS_FIELD_VHT_MCS		GENMASK( 3,  0)
+#define STA_STATS_FIELD_VHT_NSS		GENMASK( 7,  4)
+#define STA_STATS_FIELD_BW		GENMASK(11,  8)
+#define STA_STATS_FIELD_SGI		GENMASK(12, 12)
+#define STA_STATS_FIELD_TYPE		GENMASK(15, 13)
+
+#define STA_STATS_FIELD(_n, _v)		FIELD_PREP(STA_STATS_FIELD_ ## _n, _v)
+#define STA_STATS_GET(_n, _v)		FIELD_GET(STA_STATS_FIELD_ ## _n, _v)
+
 #define STA_STATS_RATE_INVALID		0
-#define STA_STATS_RATE_VHT		0x8000
-#define STA_STATS_RATE_HT		0x4000
-#define STA_STATS_RATE_LEGACY		0x2000
-#define STA_STATS_RATE_SGI		0x1000
-#define STA_STATS_RATE_BW_SHIFT		9
-#define STA_STATS_RATE_BW_MASK		(0x7 << STA_STATS_RATE_BW_SHIFT)
-
-static inline u16 sta_stats_encode_rate(struct ieee80211_rx_status *s)
+
+static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s)
 {
-	u16 r = s->rate_idx;
-
-	if (s->vht_flag & RX_VHT_FLAG_80MHZ)
-		r |= RATE_INFO_BW_80 << STA_STATS_RATE_BW_SHIFT;
-	else if (s->vht_flag & RX_VHT_FLAG_160MHZ)
-		r |= RATE_INFO_BW_160 << STA_STATS_RATE_BW_SHIFT;
-	else if (s->flag & RX_FLAG_40MHZ)
-		r |= RATE_INFO_BW_40 << STA_STATS_RATE_BW_SHIFT;
-	else if (s->flag & RX_FLAG_10MHZ)
-		r |= RATE_INFO_BW_10 << STA_STATS_RATE_BW_SHIFT;
-	else if (s->flag & RX_FLAG_5MHZ)
-		r |= RATE_INFO_BW_5 << STA_STATS_RATE_BW_SHIFT;
-	else
-		r |= RATE_INFO_BW_20 << STA_STATS_RATE_BW_SHIFT;
-
-	if (s->flag & RX_FLAG_SHORT_GI)
-		r |= STA_STATS_RATE_SGI;
-
-	if (s->flag & RX_FLAG_VHT)
-		r |= STA_STATS_RATE_VHT | (s->vht_nss << 4);
-	else if (s->flag & RX_FLAG_HT)
-		r |= STA_STATS_RATE_HT;
-	else
-		r |= STA_STATS_RATE_LEGACY | (s->band << 4);
+	u16 r;
+
+	r = STA_STATS_FIELD(BW, s->bw);
+
+	if (s->enc_flags & RX_ENC_FLAG_SHORT_GI)
+		r |= STA_STATS_FIELD(SGI, 1);
+
+	switch (s->encoding) {
+	case RX_ENC_VHT:
+		r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_VHT);
+		r |= STA_STATS_FIELD(VHT_NSS, s->nss);
+		r |= STA_STATS_FIELD(VHT_MCS, s->rate_idx);
+		break;
+	case RX_ENC_HT:
+		r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HT);
+		r |= STA_STATS_FIELD(HT_MCS, s->rate_idx);
+		break;
+	case RX_ENC_LEGACY:
+		r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_LEGACY);
+		r |= STA_STATS_FIELD(LEGACY_BAND, s->band);
+		r |= STA_STATS_FIELD(LEGACY_IDX, s->rate_idx);
+		break;
+	default:
+		WARN_ON(1);
+		return STA_STATS_RATE_INVALID;
+	}
 
 	return r;
 }
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 83b8b11f24ea..be47ac5cd8c8 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -200,6 +200,7 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb)
 	}
 
 	if (ieee80211_is_action(mgmt->frame_control) &&
+	    !ieee80211_has_protected(mgmt->frame_control) &&
 	    mgmt->u.action.category == WLAN_CATEGORY_HT &&
 	    mgmt->u.action.u.ht_smps.action == WLAN_HT_ACTION_SMPS &&
 	    ieee80211_sdata_running(sdata)) {
@@ -630,61 +631,6 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw,
 	return rates_idx;
 }
 
-void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
-			       struct ieee80211_sta *pubsta,
-			       struct ieee80211_tx_info *info)
-{
-	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_supported_band *sband;
-	int retry_count;
-	bool acked, noack_success;
-
-	ieee80211_tx_get_rates(hw, info, &retry_count);
-
-	sband = hw->wiphy->bands[info->band];
-
-	acked = !!(info->flags & IEEE80211_TX_STAT_ACK);
-	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
-
-	if (pubsta) {
-		struct sta_info *sta;
-
-		sta = container_of(pubsta, struct sta_info, sta);
-
-		if (!acked)
-			sta->status_stats.retry_failed++;
-		sta->status_stats.retry_count += retry_count;
-
-		if (acked) {
-			sta->status_stats.last_ack = jiffies;
-
-			if (sta->status_stats.lost_packets)
-				sta->status_stats.lost_packets = 0;
-
-			/* Track when last TDLS packet was ACKed */
-			if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
-				sta->status_stats.last_tdls_pkt_time = jiffies;
-		} else {
-			ieee80211_lost_packet(sta, info);
-		}
-
-		rate_control_tx_status_noskb(local, sband, sta, info);
-	}
-
-	if (acked || noack_success) {
-		I802_DEBUG_INC(local->dot11TransmittedFrameCount);
-		if (!pubsta)
-			I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount);
-		if (retry_count > 0)
-			I802_DEBUG_INC(local->dot11RetryCount);
-		if (retry_count > 1)
-			I802_DEBUG_INC(local->dot11MultipleRetryCount);
-	} else {
-		I802_DEBUG_INC(local->dot11FailedCount);
-	}
-}
-EXPORT_SYMBOL(ieee80211_tx_status_noskb);
-
 void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
 			  struct ieee80211_supported_band *sband,
 			  int retry_count, int shift, bool send_to_cooked)
@@ -742,15 +688,16 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
 	dev_kfree_skb(skb);
 }
 
-void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void __ieee80211_tx_status(struct ieee80211_hw *hw,
+				  struct ieee80211_tx_status *status)
 {
+	struct sk_buff *skb = status->skb;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_info *info = status->info;
+	struct sta_info *sta;
 	__le16 fc;
 	struct ieee80211_supported_band *sband;
-	struct rhlist_head *tmp;
-	struct sta_info *sta;
 	int retry_count;
 	int rates_idx;
 	bool send_to_cooked;
@@ -761,16 +708,11 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
 
-	rcu_read_lock();
-
 	sband = local->hw.wiphy->bands[info->band];
 	fc = hdr->frame_control;
 
-	for_each_sta_info(local, hdr->addr1, sta, tmp) {
-		/* skip wrong virtual interface */
-		if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr))
-			continue;
-
+	if (status->sta) {
+		sta = container_of(status->sta, struct sta_info, sta);
 		shift = ieee80211_vif_get_shift(&sta->sdata->vif);
 
 		if (info->flags & IEEE80211_TX_STATUS_EOSP)
@@ -790,7 +732,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			 * that this TX packet failed because of that.
 			 */
 			ieee80211_handle_filtered_frame(local, sta, skb);
-			rcu_read_unlock();
 			return;
 		}
 
@@ -840,7 +781,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 		if (info->flags & IEEE80211_TX_STAT_TX_FILTERED) {
 			ieee80211_handle_filtered_frame(local, sta, skb);
-			rcu_read_unlock();
 			return;
 		} else {
 			if (!acked)
@@ -856,7 +796,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			}
 		}
 
-		rate_control_tx_status(local, sband, sta, skb);
+		rate_control_tx_status(local, sband, status);
 		if (ieee80211_vif_is_mesh(&sta->sdata->vif))
 			ieee80211s_update_metric(local, sta, skb);
 
@@ -883,8 +823,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 		}
 	}
 
-	rcu_read_unlock();
-
 	ieee80211_led_tx(local);
 
 	/* SNMP counters
@@ -949,8 +887,96 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	/* send to monitor interfaces */
 	ieee80211_tx_monitor(local, skb, sband, retry_count, shift, send_to_cooked);
 }
+
+void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_tx_status status = {
+		.skb = skb,
+		.info = IEEE80211_SKB_CB(skb),
+	};
+	struct rhlist_head *tmp;
+	struct sta_info *sta;
+
+	rcu_read_lock();
+
+	for_each_sta_info(local, hdr->addr1, sta, tmp) {
+		/* skip wrong virtual interface */
+		if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr))
+			continue;
+
+		status.sta = &sta->sta;
+		break;
+	}
+
+	__ieee80211_tx_status(hw, &status);
+	rcu_read_unlock();
+}
 EXPORT_SYMBOL(ieee80211_tx_status);
 
+void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
+			     struct ieee80211_tx_status *status)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_tx_info *info = status->info;
+	struct ieee80211_sta *pubsta = status->sta;
+	struct ieee80211_supported_band *sband;
+	int retry_count;
+	bool acked, noack_success;
+
+	if (status->skb)
+		return __ieee80211_tx_status(hw, status);
+
+	if (!status->sta)
+		return;
+
+	ieee80211_tx_get_rates(hw, info, &retry_count);
+
+	sband = hw->wiphy->bands[info->band];
+
+	acked = !!(info->flags & IEEE80211_TX_STAT_ACK);
+	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
+
+	if (pubsta) {
+		struct sta_info *sta;
+
+		sta = container_of(pubsta, struct sta_info, sta);
+
+		if (!acked)
+			sta->status_stats.retry_failed++;
+		sta->status_stats.retry_count += retry_count;
+
+		if (acked) {
+			sta->status_stats.last_ack = jiffies;
+
+			if (sta->status_stats.lost_packets)
+				sta->status_stats.lost_packets = 0;
+
+			/* Track when last TDLS packet was ACKed */
+			if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
+				sta->status_stats.last_tdls_pkt_time = jiffies;
+		} else {
+			ieee80211_lost_packet(sta, info);
+		}
+
+		rate_control_tx_status(local, sband, status);
+	}
+
+	if (acked || noack_success) {
+		I802_DEBUG_INC(local->dot11TransmittedFrameCount);
+		if (!pubsta)
+			I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount);
+		if (retry_count > 0)
+			I802_DEBUG_INC(local->dot11RetryCount);
+		if (retry_count > 1)
+			I802_DEBUG_INC(local->dot11MultipleRetryCount);
+	} else {
+		I802_DEBUG_INC(local->dot11FailedCount);
+	}
+}
+EXPORT_SYMBOL(ieee80211_tx_status_ext);
+
 void ieee80211_report_low_ack(struct ieee80211_sta *pubsta, u32 num_packets)
 {
 	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index afca7d103684..f20dcf1b1830 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -47,8 +47,7 @@ static void ieee80211_tdls_add_ext_capab(struct ieee80211_sub_if_data *sdata,
 			   NL80211_FEATURE_TDLS_CHANNEL_SWITCH;
 	bool wider_band = ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) &&
 			  !ifmgd->tdls_wider_bw_prohibited;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
+	struct ieee80211_supported_band *sband = ieee80211_get_sband(sdata);
 	bool vht = sband && sband->vht_cap.vht_supported;
 	u8 *pos = (void *)skb_put(skb, 10);
 
@@ -180,11 +179,14 @@ static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb)
 static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata,
 					u16 status_code)
 {
+	struct ieee80211_supported_band *sband;
+
 	/* The capability will be 0 when sending a failure code */
 	if (status_code != 0)
 		return 0;
 
-	if (ieee80211_get_sdata_band(sdata) == NL80211_BAND_2GHZ) {
+	sband = ieee80211_get_sband(sdata);
+	if (sband && sband->band == NL80211_BAND_2GHZ) {
 		return WLAN_CAPABILITY_SHORT_SLOT_TIME |
 		       WLAN_CAPABILITY_SHORT_PREAMBLE;
 	}
@@ -358,17 +360,20 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 				   u8 action_code, bool initiator,
 				   const u8 *extra_ies, size_t extra_ies_len)
 {
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_supported_band *sband;
+	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_sta_ht_cap ht_cap;
 	struct ieee80211_sta_vht_cap vht_cap;
 	struct sta_info *sta = NULL;
 	size_t offset = 0, noffset;
 	u8 *pos;
 
-	ieee80211_add_srates_ie(sdata, skb, false, band);
-	ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return;
+
+	ieee80211_add_srates_ie(sdata, skb, false, sband->band);
+	ieee80211_add_ext_srates_ie(sdata, skb, false, sband->band);
 	ieee80211_tdls_add_supp_channels(sdata, skb);
 
 	/* add any custom IEs that go before Extended Capabilities */
@@ -439,7 +444,6 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 	 * the same on all bands. The specification limits the setup to a
 	 * single HT-cap, so use the current band for now.
 	 */
-	sband = local->hw.wiphy->bands[band];
 	memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap));
 
 	if ((action_code == WLAN_TDLS_SETUP_REQUEST ||
@@ -545,9 +549,13 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	size_t offset = 0, noffset;
 	struct sta_info *sta, *ap_sta;
-	enum nl80211_band band = ieee80211_get_sdata_band(sdata);
+	struct ieee80211_supported_band *sband;
 	u8 *pos;
 
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return;
+
 	mutex_lock(&local->sta_mtx);
 
 	sta = sta_info_get(sdata, peer);
@@ -612,7 +620,8 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
 
 	/* only include VHT-operation if not on the 2.4GHz band */
-	if (band != NL80211_BAND_2GHZ && sta->sta.vht_cap.vht_supported) {
+	if (sband->band != NL80211_BAND_2GHZ &&
+	    sta->sta.vht_cap.vht_supported) {
 		/*
 		 * if both peers support WIDER_BW, we can expand the chandef to
 		 * a wider compatible one, up to 80MHz
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index ba8d7db0a071..04b22f8982fe 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -682,10 +682,6 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
 	txrc.skb = tx->skb;
 	txrc.reported_rate.idx = -1;
 	txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band];
-	if (txrc.rate_idx_mask == (1 << sband->n_bitrates) - 1)
-		txrc.max_rate_idx = -1;
-	else
-		txrc.max_rate_idx = fls(txrc.rate_idx_mask) - 1;
 
 	if (tx->sdata->rc_has_mcs_mask[info->band])
 		txrc.rate_idx_mcs_mask =
@@ -4249,10 +4245,6 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 	txrc.skb = skb;
 	txrc.reported_rate.idx = -1;
 	txrc.rate_idx_mask = sdata->rc_rateidx_mask[band];
-	if (txrc.rate_idx_mask == (1 << txrc.sband->n_bitrates) - 1)
-		txrc.max_rate_idx = -1;
-	else
-		txrc.max_rate_idx = fls(txrc.rate_idx_mask) - 1;
 	txrc.bss = true;
 	rate_control_get_rate(sdata, NULL, &txrc);
 
@@ -4305,7 +4297,10 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		return bcn;
 
 	shift = ieee80211_vif_get_shift(vif);
-	sband = hw->wiphy->bands[ieee80211_get_sdata_band(vif_to_sdata(vif))];
+	sband = ieee80211_get_sband(vif_to_sdata(vif));
+	if (!sband)
+		return bcn;
+
 	ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false);
 
 	return bcn;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ac59fbd280df..ac9ac6c35594 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -4,7 +4,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2015-2016	Intel Deutschland GmbH
+ * Copyright (C) 2015-2017	Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -828,6 +828,7 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_EXT_CAPABILITY:
 		case WLAN_EID_CHAN_SWITCH_TIMING:
 		case WLAN_EID_LINK_ID:
+		case WLAN_EID_BSS_MAX_IDLE_PERIOD:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
 		 * that if the content gets bigger it might be needed more than once
@@ -1089,6 +1090,10 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			else
 				elem_parse_failed = true;
 			break;
+		case WLAN_EID_BSS_MAX_IDLE_PERIOD:
+			if (elen >= sizeof(*elems->max_idle_period_ie))
+				elems->max_idle_period_ie = (void *)pos;
+			break;
 		default:
 			break;
 		}
@@ -1590,14 +1595,14 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 	size_t num_rates;
 	u32 supp_rates, rate_flags;
 	int i, j, shift;
+
 	sband = sdata->local->hw.wiphy->bands[band];
+	if (WARN_ON(!sband))
+		return 1;
 
 	rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef);
 	shift = ieee80211_vif_get_shift(&sdata->vif);
 
-	if (WARN_ON(!sband))
-		return 1;
-
 	num_rates = sband->n_bitrates;
 	supp_rates = 0;
 	for (i = 0; i < elems->supp_rates_len +
@@ -1983,6 +1988,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			if (sdata->u.mgd.have_beacon)
 				changed |= BSS_CHANGED_BEACON_INFO;
 
+			if (sdata->vif.bss_conf.max_idle_period ||
+			    sdata->vif.bss_conf.protected_keep_alive)
+				changed |= BSS_CHANGED_KEEP_ALIVE;
+
 			sdata_lock(sdata);
 			ieee80211_bss_info_change_notify(sdata, changed);
 			sdata_unlock(sdata);
@@ -2103,7 +2112,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	mutex_unlock(&local->mtx);
 
 	if (sched_scan_stopped)
-		cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy, 0);
 
  wake_up:
 	if (local->in_reconfig) {
@@ -2413,13 +2422,13 @@ u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 	*pos++ = WLAN_EID_VHT_OPERATION;
 	*pos++ = sizeof(struct ieee80211_vht_operation);
 	vht_oper = (struct ieee80211_vht_operation *)pos;
-	vht_oper->center_freq_seg1_idx = ieee80211_frequency_to_channel(
+	vht_oper->center_freq_seg0_idx = ieee80211_frequency_to_channel(
 							chandef->center_freq1);
 	if (chandef->center_freq2)
-		vht_oper->center_freq_seg2_idx =
+		vht_oper->center_freq_seg1_idx =
 			ieee80211_frequency_to_channel(chandef->center_freq2);
 	else
-		vht_oper->center_freq_seg2_idx = 0x00;
+		vht_oper->center_freq_seg1_idx = 0x00;
 
 	switch (chandef->width) {
 	case NL80211_CHAN_WIDTH_160:
@@ -2428,11 +2437,11 @@ u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 		 * workaround.
 		 */
 		vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ;
-		vht_oper->center_freq_seg2_idx = vht_oper->center_freq_seg1_idx;
+		vht_oper->center_freq_seg1_idx = vht_oper->center_freq_seg0_idx;
 		if (chandef->chan->center_freq < chandef->center_freq1)
-			vht_oper->center_freq_seg1_idx -= 8;
+			vht_oper->center_freq_seg0_idx -= 8;
 		else
-			vht_oper->center_freq_seg1_idx += 8;
+			vht_oper->center_freq_seg0_idx += 8;
 		break;
 	case NL80211_CHAN_WIDTH_80P80:
 		/*
@@ -2491,9 +2500,9 @@ bool ieee80211_chandef_vht_oper(const struct ieee80211_vht_operation *oper,
 	if (!oper)
 		return false;
 
-	cf1 = ieee80211_channel_to_frequency(oper->center_freq_seg1_idx,
+	cf1 = ieee80211_channel_to_frequency(oper->center_freq_seg0_idx,
 					     chandef->chan->band);
-	cf2 = ieee80211_channel_to_frequency(oper->center_freq_seg2_idx,
+	cf2 = ieee80211_channel_to_frequency(oper->center_freq_seg1_idx,
 					     chandef->chan->band);
 
 	switch (oper->chan_width) {
@@ -2503,11 +2512,11 @@ bool ieee80211_chandef_vht_oper(const struct ieee80211_vht_operation *oper,
 		new.width = NL80211_CHAN_WIDTH_80;
 		new.center_freq1 = cf1;
 		/* If needed, adjust based on the newer interop workaround. */
-		if (oper->center_freq_seg2_idx) {
+		if (oper->center_freq_seg1_idx) {
 			unsigned int diff;
 
-			diff = abs(oper->center_freq_seg2_idx -
-				   oper->center_freq_seg1_idx);
+			diff = abs(oper->center_freq_seg1_idx -
+				   oper->center_freq_seg0_idx);
 			if (diff == 8) {
 				new.width = NL80211_CHAN_WIDTH_160;
 				new.center_freq1 = cf2;
@@ -2715,42 +2724,39 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 	memset(&ri, 0, sizeof(ri));
 
 	/* Fill cfg80211 rate info */
-	if (status->flag & RX_FLAG_HT) {
+	switch (status->encoding) {
+	case RX_ENC_HT:
 		ri.mcs = status->rate_idx;
 		ri.flags |= RATE_INFO_FLAGS_MCS;
-		if (status->flag & RX_FLAG_40MHZ)
-			ri.bw = RATE_INFO_BW_40;
-		else
-			ri.bw = RATE_INFO_BW_20;
-		if (status->flag & RX_FLAG_SHORT_GI)
+		ri.bw = status->bw;
+		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
-	} else if (status->flag & RX_FLAG_VHT) {
+		break;
+	case RX_ENC_VHT:
 		ri.flags |= RATE_INFO_FLAGS_VHT_MCS;
 		ri.mcs = status->rate_idx;
-		ri.nss = status->vht_nss;
-		if (status->flag & RX_FLAG_40MHZ)
-			ri.bw = RATE_INFO_BW_40;
-		else if (status->vht_flag & RX_VHT_FLAG_80MHZ)
-			ri.bw = RATE_INFO_BW_80;
-		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
-			ri.bw = RATE_INFO_BW_160;
-		else
-			ri.bw = RATE_INFO_BW_20;
-		if (status->flag & RX_FLAG_SHORT_GI)
+		ri.nss = status->nss;
+		ri.bw = status->bw;
+		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
-	} else {
+		break;
+	default:
+		WARN_ON(1);
+		/* fall through */
+	case RX_ENC_LEGACY: {
 		struct ieee80211_supported_band *sband;
 		int shift = 0;
 		int bitrate;
 
-		if (status->flag & RX_FLAG_10MHZ) {
+		ri.bw = status->bw;
+
+		switch (status->bw) {
+		case RATE_INFO_BW_10:
 			shift = 1;
-			ri.bw = RATE_INFO_BW_10;
-		} else if (status->flag & RX_FLAG_5MHZ) {
+			break;
+		case RATE_INFO_BW_5:
 			shift = 2;
-			ri.bw = RATE_INFO_BW_5;
-		} else {
-			ri.bw = RATE_INFO_BW_20;
+			break;
 		}
 
 		sband = local->hw.wiphy->bands[status->band];
@@ -2762,19 +2768,21 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 			if (status->band == NL80211_BAND_5GHZ) {
 				ts += 20 << shift;
 				mpdu_offset += 2;
-			} else if (status->flag & RX_FLAG_SHORTPRE) {
+			} else if (status->enc_flags & RX_ENC_FLAG_SHORTPRE) {
 				ts += 96;
 			} else {
 				ts += 192;
 			}
 		}
+		break;
+		}
 	}
 
 	rate = cfg80211_calculate_bitrate(&ri);
 	if (WARN_ONCE(!rate,
 		      "Invalid bitrate: flags=0x%llx, idx=%d, vht_nss=%d\n",
 		      (unsigned long long)status->flag, status->rate_idx,
-		      status->vht_nss))
+		      status->nss))
 		return 0;
 
 	/* rewind from end of MPDU */
@@ -2791,8 +2799,10 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 	struct ieee80211_sub_if_data *sdata;
 	struct cfg80211_chan_def chandef;
 
+	/* for interface list, to avoid linking iflist_mtx and chanctx_mtx */
+	ASSERT_RTNL();
+
 	mutex_lock(&local->mtx);
-	mutex_lock(&local->iflist_mtx);
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		/* it might be waiting for the local->mtx, but then
 		 * by the time it gets it, sdata->wdev.cac_started
@@ -2809,7 +2819,6 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 					   GFP_KERNEL);
 		}
 	}
-	mutex_unlock(&local->iflist_mtx);
 	mutex_unlock(&local->mtx);
 }
 
@@ -2831,7 +2840,9 @@ void ieee80211_dfs_radar_detected_work(struct work_struct *work)
 	}
 	mutex_unlock(&local->chanctx_mtx);
 
+	rtnl_lock();
 	ieee80211_dfs_cac_cancel(local);
+	rtnl_unlock();
 
 	if (num_chanctx > 1)
 		/* XXX: multi-channel is not supported yet */
@@ -2846,7 +2857,7 @@ void ieee80211_radar_detected(struct ieee80211_hw *hw)
 
 	trace_api_radar_detected(local);
 
-	ieee80211_queue_work(hw, &local->radar_detected_work);
+	schedule_work(&local->radar_detected_work);
 }
 EXPORT_SYMBOL(ieee80211_radar_detected);
 
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 56ccffa3f2bf..62141dcec2d6 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -19,6 +19,7 @@
 #ifndef __IEEE802154_I_H
 #define __IEEE802154_I_H
 
+#include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/hrtimer.h>
 #include <net/cfg802154.h>
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 3818686182b2..088e2b459d0f 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -24,6 +24,9 @@
 #include <net/nexthop.h>
 #include "internal.h"
 
+/* max memory we will use for mpls_route */
+#define MAX_MPLS_ROUTE_MEM	4096
+
 /* Maximum number of labels to look ahead at when selecting a path of
  * a multipath route
  */
@@ -32,7 +35,9 @@
 #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1)
 
 static int zero = 0;
+static int one = 1;
 static int label_limit = (1 << 20) - 1;
+static int ttl_max = 255;
 
 static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
 		       struct nlmsghdr *nlh, struct net *net, u32 portid,
@@ -58,10 +63,7 @@ EXPORT_SYMBOL_GPL(mpls_output_possible);
 
 static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh)
 {
-	u8 *nh0_via = PTR_ALIGN((u8 *)&rt->rt_nh[rt->rt_nhn], VIA_ALEN_ALIGN);
-	int nh_index = nh - rt->rt_nh;
-
-	return nh0_via + rt->rt_max_alen * nh_index;
+	return (u8 *)nh + rt->rt_via_offset;
 }
 
 static const u8 *mpls_nh_via(const struct mpls_route *rt,
@@ -187,21 +189,32 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
 	return hash;
 }
 
+static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index)
+{
+	return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size);
+}
+
+/* number of alive nexthops (rt->rt_nhn_alive) and the flags for
+ * a next hop (nh->nh_flags) are modified by netdev event handlers.
+ * Since those fields can change at any moment, use READ_ONCE to
+ * access both.
+ */
 static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 					     struct sk_buff *skb)
 {
-	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
 	u32 hash = 0;
 	int nh_index = 0;
 	int n = 0;
+	u8 alive;
 
 	/* No need to look further into packet if there's only
 	 * one path
 	 */
 	if (rt->rt_nhn == 1)
-		goto out;
+		return rt->rt_nh;
 
-	if (alive <= 0)
+	alive = READ_ONCE(rt->rt_nhn_alive);
+	if (alive == 0)
 		return NULL;
 
 	hash = mpls_multipath_hash(rt, skb);
@@ -209,7 +222,9 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 	if (alive == rt->rt_nhn)
 		goto out;
 	for_nexthops(rt) {
-		if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+		unsigned int nh_flags = READ_ONCE(nh->nh_flags);
+
+		if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
 			continue;
 		if (n == nh_index)
 			return nh;
@@ -217,11 +232,11 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 	} endfor_nexthops(rt);
 
 out:
-	return &rt->rt_nh[nh_index];
+	return mpls_get_nexthop(rt, nh_index);
 }
 
-static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
-			struct mpls_entry_decoded dec)
+static bool mpls_egress(struct net *net, struct mpls_route *rt,
+			struct sk_buff *skb, struct mpls_entry_decoded dec)
 {
 	enum mpls_payload_type payload_type;
 	bool success = false;
@@ -246,22 +261,46 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
 	switch (payload_type) {
 	case MPT_IPV4: {
 		struct iphdr *hdr4 = ip_hdr(skb);
+		u8 new_ttl;
 		skb->protocol = htons(ETH_P_IP);
+
+		/* If propagating TTL, take the decremented TTL from
+		 * the incoming MPLS header, otherwise decrement the
+		 * TTL, but only if not 0 to avoid underflow.
+		 */
+		if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
+		    (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+		     net->mpls.ip_ttl_propagate))
+			new_ttl = dec.ttl;
+		else
+			new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0;
+
 		csum_replace2(&hdr4->check,
 			      htons(hdr4->ttl << 8),
-			      htons(dec.ttl << 8));
-		hdr4->ttl = dec.ttl;
+			      htons(new_ttl << 8));
+		hdr4->ttl = new_ttl;
 		success = true;
 		break;
 	}
 	case MPT_IPV6: {
 		struct ipv6hdr *hdr6 = ipv6_hdr(skb);
 		skb->protocol = htons(ETH_P_IPV6);
-		hdr6->hop_limit = dec.ttl;
+
+		/* If propagating TTL, take the decremented TTL from
+		 * the incoming MPLS header, otherwise decrement the
+		 * hop limit, but only if not 0 to avoid underflow.
+		 */
+		if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
+		    (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+		     net->mpls.ip_ttl_propagate))
+			hdr6->hop_limit = dec.ttl;
+		else if (hdr6->hop_limit)
+			hdr6->hop_limit = hdr6->hop_limit - 1;
 		success = true;
 		break;
 	}
 	case MPT_UNSPEC:
+		/* Should have decided which protocol it is by now */
 		break;
 	}
 
@@ -361,7 +400,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 
 	if (unlikely(!new_header_size && dec.bos)) {
 		/* Penultimate hop popping */
-		if (!mpls_egress(rt, skb, dec))
+		if (!mpls_egress(dev_net(out_dev), rt, skb, dec))
 			goto err;
 	} else {
 		bool bos;
@@ -412,6 +451,7 @@ static struct packet_type mpls_packet_type __read_mostly = {
 static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
 	[RTA_DST]		= { .type = NLA_U32 },
 	[RTA_OIF]		= { .type = NLA_U32 },
+	[RTA_TTL_PROPAGATE]	= { .type = NLA_U8 },
 };
 
 struct mpls_route_config {
@@ -421,6 +461,7 @@ struct mpls_route_config {
 	u8			rc_via_alen;
 	u8			rc_via[MAX_VIA_ALEN];
 	u32			rc_label;
+	u8			rc_ttl_propagate;
 	u8			rc_output_labels;
 	u32			rc_output_label[MAX_NEW_LABELS];
 	u32			rc_nlflags;
@@ -430,20 +471,27 @@ struct mpls_route_config {
 	int			rc_mp_len;
 };
 
-static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen)
+/* all nexthops within a route have the same size based on max
+ * number of labels and max via length for a hop
+ */
+static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels)
 {
-	u8 max_alen_aligned = ALIGN(max_alen, VIA_ALEN_ALIGN);
+	u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen);
 	struct mpls_route *rt;
+	size_t size;
 
-	rt = kzalloc(ALIGN(sizeof(*rt) + num_nh * sizeof(*rt->rt_nh),
-			   VIA_ALEN_ALIGN) +
-		     num_nh * max_alen_aligned,
-		     GFP_KERNEL);
-	if (rt) {
-		rt->rt_nhn = num_nh;
-		rt->rt_nhn_alive = num_nh;
-		rt->rt_max_alen = max_alen_aligned;
-	}
+	size = sizeof(*rt) + num_nh * nh_size;
+	if (size > MAX_MPLS_ROUTE_MEM)
+		return ERR_PTR(-EINVAL);
+
+	rt = kzalloc(size, GFP_KERNEL);
+	if (!rt)
+		return ERR_PTR(-ENOMEM);
+
+	rt->rt_nhn = num_nh;
+	rt->rt_nhn_alive = num_nh;
+	rt->rt_nh_size = nh_size;
+	rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels);
 
 	return rt;
 }
@@ -648,9 +696,6 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
 		return -ENOMEM;
 
 	err = -EINVAL;
-	/* Ensure only a supported number of labels are present */
-	if (cfg->rc_output_labels > MAX_NEW_LABELS)
-		goto errout;
 
 	nh->nh_labels = cfg->rc_output_labels;
 	for (i = 0; i < nh->nh_labels; i++)
@@ -675,7 +720,7 @@ errout:
 
 static int mpls_nh_build(struct net *net, struct mpls_route *rt,
 			 struct mpls_nh *nh, int oif, struct nlattr *via,
-			 struct nlattr *newdst)
+			 struct nlattr *newdst, u8 max_labels)
 {
 	int err = -ENOMEM;
 
@@ -683,7 +728,7 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt,
 		goto errout;
 
 	if (newdst) {
-		err = nla_get_labels(newdst, MAX_NEW_LABELS,
+		err = nla_get_labels(newdst, max_labels,
 				     &nh->nh_labels, nh->nh_label);
 		if (err)
 			goto errout;
@@ -708,22 +753,20 @@ errout:
 	return err;
 }
 
-static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
-			       u8 cfg_via_alen, u8 *max_via_alen)
+static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len,
+			      u8 cfg_via_alen, u8 *max_via_alen,
+			      u8 *max_labels)
 {
-	int nhs = 0;
 	int remaining = len;
-
-	if (!rtnh) {
-		*max_via_alen = cfg_via_alen;
-		return 1;
-	}
+	u8 nhs = 0;
 
 	*max_via_alen = 0;
+	*max_labels = 0;
 
 	while (rtnh_ok(rtnh, remaining)) {
 		struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 		int attrlen;
+		u8 n_labels = 0;
 
 		attrlen = rtnh_attrlen(rtnh);
 		nla = nla_find(attrs, attrlen, RTA_VIA);
@@ -737,7 +780,20 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
 						      via_alen);
 		}
 
+		nla = nla_find(attrs, attrlen, RTA_NEWDST);
+		if (nla &&
+		    nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL) != 0)
+			return 0;
+
+		*max_labels = max_t(u8, *max_labels, n_labels);
+
+		/* number of nexthops is tracked by a u8.
+		 * Check for overflow.
+		 */
+		if (nhs == 255)
+			return 0;
 		nhs++;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -746,13 +802,13 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
 }
 
 static int mpls_nh_build_multi(struct mpls_route_config *cfg,
-			       struct mpls_route *rt)
+			       struct mpls_route *rt, u8 max_labels)
 {
 	struct rtnexthop *rtnh = cfg->rc_mp;
 	struct nlattr *nla_via, *nla_newdst;
 	int remaining = cfg->rc_mp_len;
-	int nhs = 0;
 	int err = 0;
+	u8 nhs = 0;
 
 	change_nexthops(rt) {
 		int attrlen;
@@ -779,7 +835,8 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg,
 		}
 
 		err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
-				    rtnh->rtnh_ifindex, nla_via, nla_newdst);
+				    rtnh->rtnh_ifindex, nla_via, nla_newdst,
+				    max_labels);
 		if (err)
 			goto errout;
 
@@ -806,7 +863,8 @@ static int mpls_route_add(struct mpls_route_config *cfg)
 	int err = -EINVAL;
 	u8 max_via_alen;
 	unsigned index;
-	int nhs;
+	u8 max_labels;
+	u8 nhs;
 
 	index = cfg->rc_label;
 
@@ -844,21 +902,32 @@ static int mpls_route_add(struct mpls_route_config *cfg)
 		goto errout;
 
 	err = -EINVAL;
-	nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
-				  cfg->rc_via_alen, &max_via_alen);
+	if (cfg->rc_mp) {
+		nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
+					  cfg->rc_via_alen, &max_via_alen,
+					  &max_labels);
+	} else {
+		max_via_alen = cfg->rc_via_alen;
+		max_labels = cfg->rc_output_labels;
+		nhs = 1;
+	}
+
 	if (nhs == 0)
 		goto errout;
 
 	err = -ENOMEM;
-	rt = mpls_rt_alloc(nhs, max_via_alen);
-	if (!rt)
+	rt = mpls_rt_alloc(nhs, max_via_alen, max_labels);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
 		goto errout;
+	}
 
 	rt->rt_protocol = cfg->rc_protocol;
 	rt->rt_payload_type = cfg->rc_payload_type;
+	rt->rt_ttl_propagate = cfg->rc_ttl_propagate;
 
 	if (cfg->rc_mp)
-		err = mpls_nh_build_multi(cfg, rt);
+		err = mpls_nh_build_multi(cfg, rt, max_labels);
 	else
 		err = mpls_nh_build_from_cfg(cfg, rt);
 	if (err)
@@ -1011,8 +1080,8 @@ static int mpls_netconf_msgsize_devconf(int type)
 	return size;
 }
 
-static void mpls_netconf_notify_devconf(struct net *net, int type,
-					struct mpls_dev *mdev)
+static void mpls_netconf_notify_devconf(struct net *net, int event,
+					int type, struct mpls_dev *mdev)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -1021,8 +1090,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int type,
 	if (!skb)
 		goto errout;
 
-	err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, RTM_NEWNETCONF,
-					0, type);
+	err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -1042,7 +1110,8 @@ static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = {
 };
 
 static int mpls_netconf_get_devconf(struct sk_buff *in_skb,
-				    struct nlmsghdr *nlh)
+				    struct nlmsghdr *nlh,
+				    struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX + 1];
@@ -1054,7 +1123,7 @@ static int mpls_netconf_get_devconf(struct sk_buff *in_skb,
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
-			  devconf_mpls_policy);
+			  devconf_mpls_policy, NULL);
 	if (err < 0)
 		goto errout;
 
@@ -1155,9 +1224,8 @@ static int mpls_conf_proc(struct ctl_table *ctl, int write,
 
 		if (i == offsetof(struct mpls_dev, input_enabled) &&
 		    val != oval) {
-			mpls_netconf_notify_devconf(net,
-						    NETCONFA_INPUT,
-						    mdev);
+			mpls_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_INPUT, mdev);
 		}
 	}
 
@@ -1198,10 +1266,11 @@ static int mpls_dev_sysctl_register(struct net_device *dev,
 
 	snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);
 
-	mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
+	mdev->sysctl = register_net_sysctl(net, path, table);
 	if (!mdev->sysctl)
 		goto free;
 
+	mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev);
 	return 0;
 
 free:
@@ -1210,13 +1279,17 @@ out:
 	return -ENOBUFS;
 }
 
-static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
+static void mpls_dev_sysctl_unregister(struct net_device *dev,
+				       struct mpls_dev *mdev)
 {
+	struct net *net = dev_net(dev);
 	struct ctl_table *table;
 
 	table = mdev->sysctl->ctl_table_arg;
 	unregister_net_sysctl_table(mdev->sysctl);
 	kfree(table);
+
+	mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev);
 }
 
 static struct mpls_dev *mpls_add_dev(struct net_device *dev)
@@ -1242,11 +1315,12 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
 		u64_stats_init(&mpls_stats->syncp);
 	}
 
+	mdev->dev = dev;
+
 	err = mpls_dev_sysctl_register(dev, mdev);
 	if (err)
 		goto free;
 
-	mdev->dev = dev;
 	rcu_assign_pointer(dev->mpls_ptr, mdev);
 
 	return mdev;
@@ -1269,6 +1343,7 @@ static void mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
+	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
@@ -1278,31 +1353,49 @@ static void mpls_ifdown(struct net_device *dev, int event)
 		if (!rt)
 			continue;
 
+		alive = 0;
+		deleted = 0;
 		change_nexthops(rt) {
+			unsigned int nh_flags = nh->nh_flags;
+
 			if (rtnl_dereference(nh->nh_dev) != dev)
-				continue;
+				goto next;
+
 			switch (event) {
 			case NETDEV_DOWN:
 			case NETDEV_UNREGISTER:
-				nh->nh_flags |= RTNH_F_DEAD;
+				nh_flags |= RTNH_F_DEAD;
 				/* fall through */
 			case NETDEV_CHANGE:
-				nh->nh_flags |= RTNH_F_LINKDOWN;
-				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				nh_flags |= RTNH_F_LINKDOWN;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
 				RCU_INIT_POINTER(nh->nh_dev, NULL);
+
+			if (nh->nh_flags != nh_flags)
+				WRITE_ONCE(nh->nh_flags, nh_flags);
+next:
+			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
+				alive++;
+			if (!rtnl_dereference(nh->nh_dev))
+				deleted++;
 		} endfor_nexthops(rt);
+
+		WRITE_ONCE(rt->rt_nhn_alive, alive);
+
+		/* if there are no more nexthops, delete the route */
+		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
+			mpls_route_update(net, index, NULL, NULL);
 	}
 }
 
-static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
+static void mpls_ifup(struct net_device *dev, unsigned int flags)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
 	unsigned index;
-	int alive;
+	u8 alive;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
@@ -1313,20 +1406,22 @@ static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
 
 		alive = 0;
 		change_nexthops(rt) {
+			unsigned int nh_flags = nh->nh_flags;
 			struct net_device *nh_dev =
 				rtnl_dereference(nh->nh_dev);
 
-			if (!(nh->nh_flags & nh_flags)) {
+			if (!(nh_flags & flags)) {
 				alive++;
 				continue;
 			}
 			if (nh_dev != dev)
 				continue;
 			alive++;
-			nh->nh_flags &= ~nh_flags;
+			nh_flags &= ~flags;
+			WRITE_ONCE(nh->nh_flags, flags);
 		} endfor_nexthops(rt);
 
-		ACCESS_ONCE(rt->rt_nhn_alive) = alive;
+		WRITE_ONCE(rt->rt_nhn_alive, alive);
 	}
 }
 
@@ -1377,7 +1472,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		mpls_ifdown(dev, event);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			mpls_dev_sysctl_unregister(mdev);
+			mpls_dev_sysctl_unregister(dev, mdev);
 			RCU_INIT_POINTER(dev->mpls_ptr, NULL);
 			call_rcu(&mdev->rcu, mpls_dev_destroy_rcu);
 		}
@@ -1387,7 +1482,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		if (mdev) {
 			int err;
 
-			mpls_dev_sysctl_unregister(mdev);
+			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)
 				return notifier_from_errno(err);
@@ -1447,16 +1542,18 @@ int nla_put_labels(struct sk_buff *skb, int attrtype,
 EXPORT_SYMBOL_GPL(nla_put_labels);
 
 int nla_get_labels(const struct nlattr *nla,
-		   u32 max_labels, u8 *labels, u32 label[])
+		   u8 max_labels, u8 *labels, u32 label[])
 {
 	unsigned len = nla_len(nla);
-	unsigned nla_labels;
 	struct mpls_shim_hdr *nla_label;
+	u8 nla_labels;
 	bool bos;
 	int i;
 
-	/* len needs to be an even multiple of 4 (the label size) */
-	if (len & 3)
+	/* len needs to be an even multiple of 4 (the label size). Number
+	 * of labels is a u8 so check for overflow.
+	 */
+	if (len & 3 || len / 4 > 255)
 		return -EINVAL;
 
 	/* Limit the number of new labels allowed */
@@ -1464,6 +1561,10 @@ int nla_get_labels(const struct nlattr *nla,
 	if (nla_labels > max_labels)
 		return -EINVAL;
 
+	/* when label == NULL, caller wants number of labels */
+	if (!label)
+		goto out;
+
 	nla_label = nla_data(nla);
 	bos = true;
 	for (i = nla_labels - 1; i >= 0; i--, bos = false) {
@@ -1487,6 +1588,7 @@ int nla_get_labels(const struct nlattr *nla,
 
 		label[i] = dec.label;
 	}
+out:
 	*labels = nla_labels;
 	return 0;
 }
@@ -1542,13 +1644,13 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	int index;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy);
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy,
+			  NULL);
 	if (err < 0)
 		goto errout;
 
 	err = -EINVAL;
 	rtm = nlmsg_data(nlh);
-	memset(cfg, 0, sizeof(*cfg));
 
 	if (rtm->rtm_family != AF_MPLS)
 		goto errout;
@@ -1576,6 +1678,7 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	cfg->rc_label		= LABEL_NOT_SPECIFIED;
 	cfg->rc_protocol	= rtm->rtm_protocol;
 	cfg->rc_via_table	= MPLS_NEIGH_TABLE_UNSPEC;
+	cfg->rc_ttl_propagate	= MPLS_TTL_PROP_DEFAULT;
 	cfg->rc_nlflags		= nlh->nlmsg_flags;
 	cfg->rc_nlinfo.portid	= NETLINK_CB(skb).portid;
 	cfg->rc_nlinfo.nlh	= nlh;
@@ -1622,6 +1725,17 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 			cfg->rc_mp_len = nla_len(nla);
 			break;
 		}
+		case RTA_TTL_PROPAGATE:
+		{
+			u8 ttl_propagate = nla_get_u8(nla);
+
+			if (ttl_propagate > 1)
+				goto errout;
+			cfg->rc_ttl_propagate = ttl_propagate ?
+				MPLS_TTL_PROP_ENABLED :
+				MPLS_TTL_PROP_DISABLED;
+			break;
+		}
 		default:
 			/* Unsupported attribute */
 			goto errout;
@@ -1633,29 +1747,47 @@ errout:
 	return err;
 }
 
-static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	struct mpls_route_config cfg;
+	struct mpls_route_config *cfg;
 	int err;
 
-	err = rtm_to_route_config(skb, nlh, &cfg);
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	err = rtm_to_route_config(skb, nlh, cfg);
 	if (err < 0)
-		return err;
+		goto out;
 
-	return mpls_route_del(&cfg);
+	err = mpls_route_del(cfg);
+out:
+	kfree(cfg);
+
+	return err;
 }
 
 
-static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	struct mpls_route_config cfg;
+	struct mpls_route_config *cfg;
 	int err;
 
-	err = rtm_to_route_config(skb, nlh, &cfg);
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	err = rtm_to_route_config(skb, nlh, cfg);
 	if (err < 0)
-		return err;
+		goto out;
 
-	return mpls_route_add(&cfg);
+	err = mpls_route_add(cfg);
+out:
+	kfree(cfg);
+
+	return err;
 }
 
 static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
@@ -1682,6 +1814,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 
 	if (nla_put_labels(skb, RTA_DST, 1, &label))
 		goto nla_put_failure;
+
+	if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) {
+		bool ttl_propagate =
+			rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED;
+
+		if (nla_put_u8(skb, RTA_TTL_PROPAGATE,
+			       ttl_propagate))
+			goto nla_put_failure;
+	}
 	if (rt->rt_nhn == 1) {
 		const struct mpls_nh *nh = rt->rt_nh;
 
@@ -1703,21 +1844,23 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	} else {
 		struct rtnexthop *rtnh;
 		struct nlattr *mp;
-		int dead = 0;
-		int linkdown = 0;
+		u8 linkdown = 0;
+		u8 dead = 0;
 
 		mp = nla_nest_start(skb, RTA_MULTIPATH);
 		if (!mp)
 			goto nla_put_failure;
 
 		for_nexthops(rt) {
+			dev = rtnl_dereference(nh->nh_dev);
+			if (!dev)
+				continue;
+
 			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
 			if (!rtnh)
 				goto nla_put_failure;
 
-			dev = rtnl_dereference(nh->nh_dev);
-			if (dev)
-				rtnh->rtnh_ifindex = dev->ifindex;
+			rtnh->rtnh_ifindex = dev->ifindex;
 			if (nh->nh_flags & RTNH_F_LINKDOWN) {
 				rtnh->rtnh_flags |= RTNH_F_LINKDOWN;
 				linkdown++;
@@ -1792,7 +1935,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
 {
 	size_t payload =
 		NLMSG_ALIGN(sizeof(struct rtmsg))
-		+ nla_total_size(4);			/* RTA_DST */
+		+ nla_total_size(4)			/* RTA_DST */
+		+ nla_total_size(1);			/* RTA_TTL_PROPAGATE */
 
 	if (rt->rt_nhn == 1) {
 		struct mpls_nh *nh = rt->rt_nh;
@@ -1808,6 +1952,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
 		size_t nhsize = 0;
 
 		for_nexthops(rt) {
+			if (!rtnl_dereference(nh->nh_dev))
+				continue;
 			nhsize += nla_total_size(sizeof(struct rtnexthop));
 			/* RTA_VIA */
 			if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC)
@@ -1870,12 +2016,13 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 	/* In case the predefined labels need to be populated */
 	if (limit > MPLS_LABEL_IPV4NULL) {
 		struct net_device *lo = net->loopback_dev;
-		rt0 = mpls_rt_alloc(1, lo->addr_len);
-		if (!rt0)
+		rt0 = mpls_rt_alloc(1, lo->addr_len, 0);
+		if (IS_ERR(rt0))
 			goto nort0;
 		RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo);
 		rt0->rt_protocol = RTPROT_KERNEL;
 		rt0->rt_payload_type = MPT_IPV4;
+		rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
 		rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
 		rt0->rt_nh->nh_via_alen = lo->addr_len;
 		memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr,
@@ -1883,12 +2030,13 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 	}
 	if (limit > MPLS_LABEL_IPV6NULL) {
 		struct net_device *lo = net->loopback_dev;
-		rt2 = mpls_rt_alloc(1, lo->addr_len);
-		if (!rt2)
+		rt2 = mpls_rt_alloc(1, lo->addr_len, 0);
+		if (IS_ERR(rt2))
 			goto nort2;
 		RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo);
 		rt2->rt_protocol = RTPROT_KERNEL;
 		rt2->rt_payload_type = MPT_IPV6;
+		rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
 		rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
 		rt2->rt_nh->nh_via_alen = lo->addr_len;
 		memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr,
@@ -1970,6 +2118,9 @@ static int mpls_platform_labels(struct ctl_table *table, int write,
 	return ret;
 }
 
+#define MPLS_NS_SYSCTL_OFFSET(field)		\
+	(&((struct net *)0)->field)
+
 static const struct ctl_table mpls_table[] = {
 	{
 		.procname	= "platform_labels",
@@ -1978,21 +2129,47 @@ static const struct ctl_table mpls_table[] = {
 		.mode		= 0644,
 		.proc_handler	= mpls_platform_labels,
 	},
+	{
+		.procname	= "ip_ttl_propagate",
+		.data		= MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate),
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.procname	= "default_ttl",
+		.data		= MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl),
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &ttl_max,
+	},
 	{ }
 };
 
 static int mpls_net_init(struct net *net)
 {
 	struct ctl_table *table;
+	int i;
 
 	net->mpls.platform_labels = 0;
 	net->mpls.platform_label = NULL;
+	net->mpls.ip_ttl_propagate = 1;
+	net->mpls.default_ttl = 255;
 
 	table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL);
 	if (table == NULL)
 		return -ENOMEM;
 
-	table[0].data = net;
+	/* Table data contains only offsets relative to the base of
+	 * the mdev at this point, so make them absolute.
+	 */
+	for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++)
+		table[i].data = (char *)net + (uintptr_t)table[i].data;
+
 	net->mpls.ctl = register_net_sysctl(net, "net/mpls", table);
 	if (net->mpls.ctl == NULL) {
 		kfree(table);
@@ -2028,6 +2205,7 @@ static void mpls_net_exit(struct net *net)
 	for (index = 0; index < platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
 		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_notify_route(net, index, rt, NULL, NULL);
 		mpls_rt_free(rt);
 	}
 	rtnl_unlock();
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index 76360d8b9579..4db6a5971322 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -2,6 +2,11 @@
 #define MPLS_INTERNAL_H
 #include <net/mpls.h>
 
+/* put a reasonable limit on the number of labels
+ * we will accept from userspace
+ */
+#define MAX_NEW_LABELS 30
+
 struct mpls_entry_decoded {
 	u32 label;
 	u8 ttl;
@@ -64,7 +69,6 @@ struct mpls_dev {
 struct sk_buff;
 
 #define LABEL_NOT_SPECIFIED (1 << 20)
-#define MAX_NEW_LABELS 2
 
 /* This maximum ha length copied from the definition of struct neighbour */
 #define VIA_ALEN_ALIGN sizeof(unsigned long)
@@ -83,11 +87,35 @@ enum mpls_payload_type {
 
 struct mpls_nh { /* next hop label forwarding entry */
 	struct net_device __rcu *nh_dev;
+
+	/* nh_flags is accessed under RCU in the packet path; it is
+	 * modified handling netdev events with rtnl lock held
+	 */
 	unsigned int		nh_flags;
-	u32			nh_label[MAX_NEW_LABELS];
 	u8			nh_labels;
 	u8			nh_via_alen;
 	u8			nh_via_table;
+	u8			nh_reserved1;
+
+	u32			nh_label[0];
+};
+
+/* offset of via from beginning of mpls_nh */
+#define MPLS_NH_VIA_OFF(num_labels) \
+		ALIGN(sizeof(struct mpls_nh) + (num_labels) * sizeof(u32), \
+		      VIA_ALEN_ALIGN)
+
+/* all nexthops within a route have the same size based on the
+ * max number of labels and max via length across all nexthops
+ */
+#define MPLS_NH_SIZE(num_labels, max_via_alen)		\
+		(MPLS_NH_VIA_OFF((num_labels)) +	\
+		ALIGN((max_via_alen), VIA_ALEN_ALIGN))
+
+enum mpls_ttl_propagation {
+	MPLS_TTL_PROP_DEFAULT,
+	MPLS_TTL_PROP_ENABLED,
+	MPLS_TTL_PROP_DISABLED,
 };
 
 /* The route, nexthops and vias are stored together in the same memory
@@ -98,16 +126,16 @@ struct mpls_nh { /* next hop label forwarding entry */
  * +----------------------+
  * | mpls_nh 0            |
  * +----------------------+
- * | ...                  |
- * +----------------------+
- * | mpls_nh n-1          |
- * +----------------------+
- * | alignment padding    |
+ * | alignment padding    |   4 bytes for odd number of labels
  * +----------------------+
  * | via[rt_max_alen] 0   |
  * +----------------------+
+ * | alignment padding    |   via's aligned on sizeof(unsigned long)
+ * +----------------------+
  * | ...                  |
  * +----------------------+
+ * | mpls_nh n-1          |
+ * +----------------------+
  * | via[rt_max_alen] n-1 |
  * +----------------------+
  */
@@ -116,22 +144,30 @@ struct mpls_route { /* next hop label forwarding entry */
 	u8			rt_protocol;
 	u8			rt_payload_type;
 	u8			rt_max_alen;
-	unsigned int		rt_nhn;
-	unsigned int		rt_nhn_alive;
+	u8			rt_ttl_propagate;
+	u8			rt_nhn;
+	/* rt_nhn_alive is accessed under RCU in the packet path; it
+	 * is modified handling netdev events with rtnl lock held
+	 */
+	u8			rt_nhn_alive;
+	u8			rt_nh_size;
+	u8			rt_via_offset;
+	u8			rt_reserved1;
 	struct mpls_nh		rt_nh[0];
 };
 
 #define for_nexthops(rt) {						\
-	int nhsel; struct mpls_nh *nh;			\
-	for (nhsel = 0, nh = (rt)->rt_nh;				\
+	int nhsel; struct mpls_nh *nh;  u8 *__nh;			\
+	for (nhsel = 0, nh = (rt)->rt_nh, __nh = (u8 *)((rt)->rt_nh);	\
 	     nhsel < (rt)->rt_nhn;					\
-	     nh++, nhsel++)
+	     __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++)
 
 #define change_nexthops(rt) {						\
-	int nhsel; struct mpls_nh *nh;				\
-	for (nhsel = 0,	nh = (struct mpls_nh *)((rt)->rt_nh);	\
+	int nhsel; struct mpls_nh *nh; u8 *__nh;			\
+	for (nhsel = 0, nh = (struct mpls_nh *)((rt)->rt_nh),		\
+			__nh = (u8 *)((rt)->rt_nh);			\
 	     nhsel < (rt)->rt_nhn;					\
-	     nh++, nhsel++)
+	     __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++)
 
 #define endfor_nexthops(rt) }
 
@@ -166,7 +202,7 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
 
 int nla_put_labels(struct sk_buff *skb, int attrtype,  u8 labels,
 		   const u32 label[]);
-int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels,
+int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels,
 		   u32 label[]);
 int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
 		u8 via[]);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index e4e4424f9eb1..369c7a23c86c 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -29,6 +29,7 @@
 
 static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = {
 	[MPLS_IPTUNNEL_DST]	= { .type = NLA_U32 },
+	[MPLS_IPTUNNEL_TTL]	= { .type = NLA_U8 },
 };
 
 static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en)
@@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb)
 	struct rtable *rt = NULL;
 	struct rt6_info *rt6 = NULL;
 	struct mpls_dev *out_mdev;
+	struct net *net;
 	int err = 0;
 	bool bos;
 	int i;
@@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb)
 
 	/* Find the output device */
 	out_dev = dst->dev;
-
-	/* Obtain the ttl */
-	if (dst->ops->family == AF_INET) {
-		ttl = ip_hdr(skb)->ttl;
-		rt = (struct rtable *)dst;
-	} else if (dst->ops->family == AF_INET6) {
-		ttl = ipv6_hdr(skb)->hop_limit;
-		rt6 = (struct rt6_info *)dst;
-	} else {
-		goto drop;
-	}
+	net = dev_net(out_dev);
 
 	skb_orphan(skb);
 
@@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb)
 
 	tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate);
 
+	/* Obtain the ttl using the following set of rules.
+	 *
+	 * LWT ttl propagation setting:
+	 *  - disabled => use default TTL value from LWT
+	 *  - enabled  => use TTL value from IPv4/IPv6 header
+	 *  - default  =>
+	 *   Global ttl propagation setting:
+	 *    - disabled => use default TTL value from global setting
+	 *    - enabled => use TTL value from IPv4/IPv6 header
+	 */
+	if (dst->ops->family == AF_INET) {
+		if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
+			ttl = tun_encap_info->default_ttl;
+		else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+			 !net->mpls.ip_ttl_propagate)
+			ttl = net->mpls.default_ttl;
+		else
+			ttl = ip_hdr(skb)->ttl;
+		rt = (struct rtable *)dst;
+	} else if (dst->ops->family == AF_INET6) {
+		if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
+			ttl = tun_encap_info->default_ttl;
+		else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+			 !net->mpls.ip_ttl_propagate)
+			ttl = net->mpls.default_ttl;
+		else
+			ttl = ipv6_hdr(skb)->hop_limit;
+		rt6 = (struct rt6_info *)dst;
+	} else {
+		goto drop;
+	}
+
 	/* Verify the destination can hold the packet */
 	new_header_size = mpls_encap_size(tun_encap_info);
 	mtu = mpls_dev_mtu(out_dev);
@@ -140,10 +164,11 @@ static int mpls_build_state(struct nlattr *nla,
 	struct mpls_iptunnel_encap *tun_encap_info;
 	struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1];
 	struct lwtunnel_state *newts;
+	u8 n_labels;
 	int ret;
 
 	ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla,
-			       mpls_iptunnel_policy);
+			       mpls_iptunnel_policy, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -151,15 +176,32 @@ static int mpls_build_state(struct nlattr *nla,
 		return -EINVAL;
 
 
-	newts = lwtunnel_state_alloc(sizeof(*tun_encap_info));
+	/* determine number of labels */
+	if (nla_get_labels(tb[MPLS_IPTUNNEL_DST],
+			   MAX_NEW_LABELS, &n_labels, NULL))
+		return -EINVAL;
+
+	newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) +
+				     n_labels * sizeof(u32));
 	if (!newts)
 		return -ENOMEM;
 
 	tun_encap_info = mpls_lwtunnel_encap(newts);
-	ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS,
+	ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels,
 			     &tun_encap_info->labels, tun_encap_info->label);
 	if (ret)
 		goto errout;
+
+	tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT;
+
+	if (tb[MPLS_IPTUNNEL_TTL]) {
+		tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]);
+		/* TTL 0 implies propagate from IP header */
+		tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ?
+			MPLS_TTL_PROP_DISABLED :
+			MPLS_TTL_PROP_ENABLED;
+	}
+
 	newts->type = LWTUNNEL_ENCAP_MPLS;
 	newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
 	newts->headroom = mpls_encap_size(tun_encap_info);
@@ -186,6 +228,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb,
 			   tun_encap_info->label))
 		goto nla_put_failure;
 
+	if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT &&
+	    nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -195,10 +241,16 @@ nla_put_failure:
 static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate)
 {
 	struct mpls_iptunnel_encap *tun_encap_info;
+	int nlsize;
 
 	tun_encap_info = mpls_lwtunnel_encap(lwtstate);
 
-	return nla_total_size(tun_encap_info->labels * 4);
+	nlsize = nla_total_size(tun_encap_info->labels * 4);
+
+	if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT)
+		nlsize += nla_total_size(1);
+
+	return nlsize;
 }
 
 static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
@@ -207,10 +259,12 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
 	struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b);
 	int l;
 
-	if (a_hdr->labels != b_hdr->labels)
+	if (a_hdr->labels != b_hdr->labels ||
+	    a_hdr->ttl_propagate != b_hdr->ttl_propagate ||
+	    a_hdr->default_ttl != b_hdr->default_ttl)
 		return 1;
 
-	for (l = 0; l < MAX_NEW_LABELS; l++)
+	for (l = 0; l < a_hdr->labels; l++)
 		if (a_hdr->label[l] != b_hdr->label[l])
 			return 1;
 	return 0;
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index a87a6f8a74d8..552d606e57ca 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -126,14 +126,15 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
 }
 EXPORT_SYMBOL(nf_register_net_hook);
 
-void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
+static struct nf_hook_entry *
+__nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
 {
 	struct nf_hook_entry __rcu **pp;
 	struct nf_hook_entry *p;
 
 	pp = nf_hook_entry_head(net, reg);
 	if (WARN_ON_ONCE(!pp))
-		return;
+		return NULL;
 
 	mutex_lock(&nf_hook_mutex);
 	for (; (p = nf_entry_dereference(*pp)) != NULL; pp = &p->next) {
@@ -145,7 +146,7 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
 	mutex_unlock(&nf_hook_mutex);
 	if (!p) {
 		WARN(1, "nf_unregister_net_hook: hook not found!\n");
-		return;
+		return NULL;
 	}
 #ifdef CONFIG_NETFILTER_INGRESS
 	if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
@@ -154,10 +155,24 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
 #ifdef HAVE_JUMP_LABEL
 	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
+
+	return p;
+}
+
+void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
+{
+	struct nf_hook_entry *p = __nf_unregister_net_hook(net, reg);
+	unsigned int nfq;
+
+	if (!p)
+		return;
+
 	synchronize_net();
-	nf_queue_nf_hook_drop(net, p);
+
 	/* other cpu might still process nfqueue verdict that used reg */
-	synchronize_net();
+	nfq = nf_queue_nf_hook_drop(net);
+	if (nfq)
+		synchronize_net();
 	kfree(p);
 }
 EXPORT_SYMBOL(nf_unregister_net_hook);
@@ -183,10 +198,32 @@ err:
 EXPORT_SYMBOL(nf_register_net_hooks);
 
 void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
-			     unsigned int n)
+			     unsigned int hookcount)
 {
-	while (n-- > 0)
-		nf_unregister_net_hook(net, &reg[n]);
+	struct nf_hook_entry *to_free[16];
+	unsigned int i, n, nfq;
+
+	do {
+		n = min_t(unsigned int, hookcount, ARRAY_SIZE(to_free));
+
+		for (i = 0; i < n; i++)
+			to_free[i] = __nf_unregister_net_hook(net, &reg[i]);
+
+		synchronize_net();
+
+		/* need 2nd synchronize_net() if nfqueue is used, skb
+		 * can get reinjected right before nf_queue_hook_drop()
+		 */
+		nfq = nf_queue_nf_hook_drop(net);
+		if (nfq)
+			synchronize_net();
+
+		for (i = 0; i < n; i++)
+			kfree(to_free[i]);
+
+		reg += n;
+		hookcount -= n;
+	} while (hookcount > 0);
 }
 EXPORT_SYMBOL(nf_unregister_net_hooks);
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 6f09a99298cd..8ad2b52a0b32 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -232,7 +232,7 @@ mtype_list(const struct ip_set *set,
 		if (!test_bit(id, map->members) ||
 		    (SET_WITH_TIMEOUT(set) &&
 #ifdef IP_SET_BITMAP_STORED_TIMEOUT
-		     mtype_is_filled((const struct mtype_elem *)x) &&
+		     mtype_is_filled(x) &&
 #endif
 		     ip_set_timeout_expired(ext_timeout(x, set))))
 			continue;
@@ -248,8 +248,7 @@ mtype_list(const struct ip_set *set,
 		}
 		if (mtype_do_list(skb, map, id, set->dsize))
 			goto nla_put_failure;
-		if (ip_set_put_extensions(skb, set, x,
-		    mtype_is_filled((const struct mtype_elem *)x)))
+		if (ip_set_put_extensions(skb, set, x, mtype_is_filled(x)))
 			goto nla_put_failure;
 		ipset_nest_end(skb, nested);
 	}
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index c296f9b606d4..ba6a5516dc7c 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -295,7 +295,8 @@ ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr)
 
 	if (unlikely(!flag_nested(nla)))
 		return -IPSET_ERR_PROTOCOL;
-	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy))
+	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
+			     ipaddr_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4)))
 		return -IPSET_ERR_PROTOCOL;
@@ -313,7 +314,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
 	if (unlikely(!flag_nested(nla)))
 		return -IPSET_ERR_PROTOCOL;
 
-	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy))
+	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
+			     ipaddr_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6)))
 		return -IPSET_ERR_PROTOCOL;
@@ -501,14 +503,6 @@ __ip_set_put(struct ip_set *set)
  * a separate reference counter
  */
 static inline void
-__ip_set_get_netlink(struct ip_set *set)
-{
-	write_lock_bh(&ip_set_ref_lock);
-	set->ref_netlink++;
-	write_unlock_bh(&ip_set_ref_lock);
-}
-
-static inline void
 __ip_set_put_netlink(struct ip_set *set)
 {
 	write_lock_bh(&ip_set_ref_lock);
@@ -769,7 +763,7 @@ start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags,
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd | (NFNL_SUBSYS_IPSET << 8),
+	nlh = nlmsg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd),
 			sizeof(*nfmsg), flags);
 	if (!nlh)
 		return NULL;
@@ -906,7 +900,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 	/* Without holding any locks, create private part. */
 	if (attr[IPSET_ATTR_DATA] &&
 	    nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA],
-			     set->type->create_policy)) {
+			     set->type->create_policy, NULL)) {
 		ret = -IPSET_ERR_PROTOCOL;
 		goto put_out;
 	}
@@ -1257,8 +1251,8 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 	ip_set_id_t index;
 
 	/* Second pass, so parser can't fail */
-	nla_parse(cda, IPSET_ATTR_CMD_MAX,
-		  attr, nlh->nlmsg_len - min_len, ip_set_setname_policy);
+	nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, nlh->nlmsg_len - min_len,
+		  ip_set_setname_policy, NULL);
 
 	if (cda[IPSET_ATTR_SETNAME]) {
 		struct ip_set *set;
@@ -1305,7 +1299,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 			 * manually :-(
 			 */
 			if (nlh->nlmsg_flags & NLM_F_ACK)
-				netlink_ack(cb->skb, nlh, ret);
+				netlink_ack(cb->skb, nlh, ret, NULL);
 			return ret;
 		}
 	}
@@ -1501,9 +1495,8 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 		memcpy(&errmsg->msg, nlh, nlh->nlmsg_len);
 		cmdattr = (void *)&errmsg->msg + min_len;
 
-		nla_parse(cda, IPSET_ATTR_CMD_MAX,
-			  cmdattr, nlh->nlmsg_len - min_len,
-			  ip_set_adt_policy);
+		nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr,
+			  nlh->nlmsg_len - min_len, ip_set_adt_policy, NULL);
 
 		errline = nla_data(cda[IPSET_ATTR_LINENO]);
 
@@ -1549,7 +1542,7 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	if (attr[IPSET_ATTR_DATA]) {
 		if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX,
 				     attr[IPSET_ATTR_DATA],
-				     set->type->adt_policy))
+				     set->type->adt_policy, NULL))
 			return -IPSET_ERR_PROTOCOL;
 		ret = call_ad(ctnl, skb, set, tb, IPSET_ADD, flags,
 			      use_lineno);
@@ -1561,7 +1554,7 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 			if (nla_type(nla) != IPSET_ATTR_DATA ||
 			    !flag_nested(nla) ||
 			    nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
-					     set->type->adt_policy))
+					     set->type->adt_policy, NULL))
 				return -IPSET_ERR_PROTOCOL;
 			ret = call_ad(ctnl, skb, set, tb, IPSET_ADD,
 				      flags, use_lineno);
@@ -1603,7 +1596,7 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	if (attr[IPSET_ATTR_DATA]) {
 		if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX,
 				     attr[IPSET_ATTR_DATA],
-				     set->type->adt_policy))
+				     set->type->adt_policy, NULL))
 			return -IPSET_ERR_PROTOCOL;
 		ret = call_ad(ctnl, skb, set, tb, IPSET_DEL, flags,
 			      use_lineno);
@@ -1615,7 +1608,7 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 			if (nla_type(nla) != IPSET_ATTR_DATA ||
 			    !flag_nested(nla) ||
 			    nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
-					     set->type->adt_policy))
+					     set->type->adt_policy, NULL))
 				return -IPSET_ERR_PROTOCOL;
 			ret = call_ad(ctnl, skb, set, tb, IPSET_DEL,
 				      flags, use_lineno);
@@ -1646,7 +1639,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 		return -ENOENT;
 
 	if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA],
-			     set->type->adt_policy))
+			     set->type->adt_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 
 	rcu_read_lock_bh();
@@ -1915,7 +1908,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		ret = -EFAULT;
 		goto done;
 	}
-	op = (unsigned int *)data;
+	op = data;
 
 	if (*op < IP_SET_OP_VERSION) {
 		/* Check the version at the beginning of operations */
@@ -2013,7 +2006,7 @@ static struct nf_sockopt_ops so_set __read_mostly = {
 	.pf		= PF_INET,
 	.get_optmin	= SO_IP_SET,
 	.get_optmax	= SO_IP_SET + 1,
-	.get		= &ip_set_sockfn_get,
+	.get		= ip_set_sockfn_get,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e6a2753dff9e..3d2ac71a83ec 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -181,7 +181,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
 
 	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
 		cp->flags |= IP_VS_CONN_F_HASHED;
-		atomic_inc(&cp->refcnt);
+		refcount_inc(&cp->refcnt);
 		hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]);
 		ret = 1;
 	} else {
@@ -215,7 +215,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
 		hlist_del_rcu(&cp->c_list);
 		cp->flags &= ~IP_VS_CONN_F_HASHED;
-		atomic_dec(&cp->refcnt);
+		refcount_dec(&cp->refcnt);
 		ret = 1;
 	} else
 		ret = 0;
@@ -242,13 +242,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
 		ret = false;
 		/* Decrease refcnt and unlink conn only if we are last user */
-		if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) {
+		if (refcount_dec_if_one(&cp->refcnt)) {
 			hlist_del_rcu(&cp->c_list);
 			cp->flags &= ~IP_VS_CONN_F_HASHED;
 			ret = true;
 		}
 	} else
-		ret = atomic_read(&cp->refcnt) ? false : true;
+		ret = refcount_read(&cp->refcnt) ? false : true;
 
 	spin_unlock(&cp->lock);
 	ct_write_unlock_bh(hash);
@@ -475,7 +475,7 @@ static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp)
 void ip_vs_conn_put(struct ip_vs_conn *cp)
 {
 	if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) &&
-	    (atomic_read(&cp->refcnt) == 1) &&
+	    (refcount_read(&cp->refcnt) == 1) &&
 	    !timer_pending(&cp->timer))
 		/* expire connection immediately */
 		__ip_vs_conn_put_notimer(cp);
@@ -617,8 +617,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      ip_vs_fwd_tag(cp), cp->state,
-		      cp->flags, atomic_read(&cp->refcnt),
-		      atomic_read(&dest->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt),
+		      refcount_read(&dest->refcnt));
 
 	/* Update the connection counters */
 	if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -714,8 +714,8 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      ip_vs_fwd_tag(cp), cp->state,
-		      cp->flags, atomic_read(&cp->refcnt),
-		      atomic_read(&dest->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt),
+		      refcount_read(&dest->refcnt));
 
 	/* Update the connection counters */
 	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -863,10 +863,10 @@ static void ip_vs_conn_expire(unsigned long data)
 
   expire_later:
 	IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n",
-		  atomic_read(&cp->refcnt),
+		  refcount_read(&cp->refcnt),
 		  atomic_read(&cp->n_control));
 
-	atomic_inc(&cp->refcnt);
+	refcount_inc(&cp->refcnt);
 	cp->timeout = 60*HZ;
 
 	if (ipvs->sync_state & IP_VS_STATE_MASTER)
@@ -941,7 +941,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 	 * it in the table, so that other thread run ip_vs_random_dropentry
 	 * but cannot drop this entry.
 	 */
-	atomic_set(&cp->refcnt, 1);
+	refcount_set(&cp->refcnt, 1);
 
 	cp->control = NULL;
 	atomic_set(&cp->n_control, 0);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index db40050f8785..d2d7bdf1d510 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -542,7 +542,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
-		      cp->flags, atomic_read(&cp->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt));
 
 	ip_vs_conn_stats(cp, svc);
 	return cp;
@@ -1193,7 +1193,7 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
 		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
-		      cp->flags, atomic_read(&cp->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt));
 	LeaveFunction(12);
 	return cp;
 }
@@ -2200,6 +2200,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 static int __net_init __ip_vs_init(struct net *net)
 {
 	struct netns_ipvs *ipvs;
+	int ret;
 
 	ipvs = net_generic(net, ip_vs_net_id);
 	if (ipvs == NULL)
@@ -2231,13 +2232,17 @@ static int __net_init __ip_vs_init(struct net *net)
 	if (ip_vs_sync_net_init(ipvs) < 0)
 		goto sync_fail;
 
-	printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
-			 sizeof(struct netns_ipvs), ipvs->gen);
+	ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+	if (ret < 0)
+		goto hook_fail;
+
 	return 0;
 /*
  * Error handling
  */
 
+hook_fail:
+	ip_vs_sync_net_cleanup(ipvs);
 sync_fail:
 	ip_vs_conn_net_cleanup(ipvs);
 conn_fail:
@@ -2257,6 +2262,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	ip_vs_service_net_cleanup(ipvs);	/* ip_vs_flush() with locks */
 	ip_vs_conn_net_cleanup(ipvs);
 	ip_vs_app_net_cleanup(ipvs);
@@ -2317,24 +2323,16 @@ static int __init ip_vs_init(void)
 	if (ret < 0)
 		goto cleanup_sub;
 
-	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
-	if (ret < 0) {
-		pr_err("can't register hooks.\n");
-		goto cleanup_dev;
-	}
-
 	ret = ip_vs_register_nl_ioctl();
 	if (ret < 0) {
 		pr_err("can't register netlink/ioctl.\n");
-		goto cleanup_hooks;
+		goto cleanup_dev;
 	}
 
 	pr_info("ipvs loaded.\n");
 
 	return ret;
 
-cleanup_hooks:
-	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 cleanup_dev:
 	unregister_pernet_device(&ipvs_core_dev_ops);
 cleanup_sub:
@@ -2351,7 +2349,6 @@ exit:
 static void __exit ip_vs_cleanup(void)
 {
 	ip_vs_unregister_nl_ioctl();
-	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	unregister_pernet_device(&ipvs_core_dev_ops);
 	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	ip_vs_conn_cleanup();
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5aeb0dde6ccc..668d9643f0cc 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -699,7 +699,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
 			      dest->vfwmark,
 			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
-			      atomic_read(&dest->refcnt));
+			      refcount_read(&dest->refcnt));
 		if (dest->af == dest_af &&
 		    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
 		    dest->port == dport &&
@@ -934,7 +934,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 	atomic_set(&dest->activeconns, 0);
 	atomic_set(&dest->inactconns, 0);
 	atomic_set(&dest->persistconns, 0);
-	atomic_set(&dest->refcnt, 1);
+	refcount_set(&dest->refcnt, 1);
 
 	INIT_HLIST_NODE(&dest->d_list);
 	spin_lock_init(&dest->dst_lock);
@@ -998,7 +998,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
 			      "dest->refcnt=%d, service %u/%s:%u\n",
 			      IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
-			      atomic_read(&dest->refcnt),
+			      refcount_read(&dest->refcnt),
 			      dest->vfwmark,
 			      IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
 			      ntohs(dest->vport));
@@ -1074,7 +1074,7 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
 	spin_lock_bh(&ipvs->dest_trash_lock);
 	IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
 		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
-		      atomic_read(&dest->refcnt));
+		      refcount_read(&dest->refcnt));
 	if (list_empty(&ipvs->dest_trash) && !cleanup)
 		mod_timer(&ipvs->dest_trash_timer,
 			  jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
@@ -1157,7 +1157,7 @@ static void ip_vs_dest_trash_expire(unsigned long data)
 
 	spin_lock(&ipvs->dest_trash_lock);
 	list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
-		if (atomic_read(&dest->refcnt) > 1)
+		if (refcount_read(&dest->refcnt) > 1)
 			continue;
 		if (dest->idle_start) {
 			if (time_before(now, dest->idle_start +
@@ -1545,7 +1545,7 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
 			      dev->name,
 			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
-			      atomic_read(&dest->refcnt));
+			      refcount_read(&dest->refcnt));
 		__ip_vs_dst_cache_reset(dest);
 	}
 	spin_unlock_bh(&dest->dst_lock);
@@ -1774,13 +1774,13 @@ static struct ctl_table vs_vars[] = {
 		.procname	= "sync_version",
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_do_sync_mode,
+		.proc_handler	= proc_do_sync_mode,
 	},
 	{
 		.procname	= "sync_ports",
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_do_sync_ports,
+		.proc_handler	= proc_do_sync_ports,
 	},
 	{
 		.procname	= "sync_persist_mode",
@@ -2130,8 +2130,8 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		 "   Total Incoming Outgoing         Incoming         Outgoing\n");
-	seq_printf(seq,
-		   "   Conns  Packets  Packets            Bytes            Bytes\n");
+	seq_puts(seq,
+		 "   Conns  Packets  Packets            Bytes            Bytes\n");
 
 	ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
 	seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n",
@@ -2178,8 +2178,8 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		 "       Total Incoming Outgoing         Incoming         Outgoing\n");
-	seq_printf(seq,
-		   "CPU    Conns  Packets  Packets            Bytes            Bytes\n");
+	seq_puts(seq,
+		 "CPU    Conns  Packets  Packets            Bytes            Bytes\n");
 
 	for_each_possible_cpu(i) {
 		struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
@@ -3089,7 +3089,8 @@ static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
 
 	/* Parse mandatory identifying service fields first */
 	if (nla == NULL ||
-	    nla_parse_nested(attrs, IPVS_SVC_ATTR_MAX, nla, ip_vs_svc_policy))
+	    nla_parse_nested(attrs, IPVS_SVC_ATTR_MAX, nla,
+			     ip_vs_svc_policy, NULL))
 		return -EINVAL;
 
 	nla_af		= attrs[IPVS_SVC_ATTR_AF];
@@ -3251,8 +3252,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 	mutex_lock(&__ip_vs_mutex);
 
 	/* Try to find the service for which to dump destinations */
-	if (nlmsg_parse(cb->nlh, GENL_HDRLEN, attrs,
-			IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy))
+	if (nlmsg_parse(cb->nlh, GENL_HDRLEN, attrs, IPVS_CMD_ATTR_MAX,
+			ip_vs_cmd_policy, NULL))
 		goto out_err;
 
 
@@ -3288,7 +3289,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 
 	/* Parse mandatory identifying destination fields first */
 	if (nla == NULL ||
-	    nla_parse_nested(attrs, IPVS_DEST_ATTR_MAX, nla, ip_vs_dest_policy))
+	    nla_parse_nested(attrs, IPVS_DEST_ATTR_MAX, nla,
+			     ip_vs_dest_policy, NULL))
 		return -EINVAL;
 
 	nla_addr	= attrs[IPVS_DEST_ATTR_ADDR];
@@ -3530,7 +3532,7 @@ static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info)
 		if (!info->attrs[IPVS_CMD_ATTR_DAEMON] ||
 		    nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX,
 				     info->attrs[IPVS_CMD_ATTR_DAEMON],
-				     ip_vs_daemon_policy))
+				     ip_vs_daemon_policy, info->extack))
 			goto out;
 
 		if (cmd == IPVS_CMD_NEW_DAEMON)
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index d30c327bb578..fb780be76d15 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -260,7 +260,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		buf_len = strlen(buf);
 
 		ct = nf_ct_get(skb, &ctinfo);
-		if (ct && !nf_ct_is_untracked(ct) && nfct_nat(ct)) {
+		if (ct && (ct->status & IPS_NAT_MASK)) {
+			bool mangled;
+
 			/* If mangling fails this function will return 0
 			 * which will cause the packet to be dropped.
 			 * Mangling can only fail under memory pressure,
@@ -268,12 +270,13 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			 * packet.
 			 */
 			rcu_read_lock();
-			ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
-						       iph->ihl * 4,
-						       start-data, end-start,
-						       buf, buf_len);
+			mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+							   iph->ihl * 4,
+							   start - data,
+							   end - start,
+							   buf, buf_len);
 			rcu_read_unlock();
-			if (ret) {
+			if (mangled) {
 				ip_vs_nfct_expect_related(skb, ct, n_cp,
 							  IPPROTO_TCP, 0, 0);
 				if (skb->ip_summed == CHECKSUM_COMPLETE)
@@ -482,11 +485,8 @@ static struct pernet_operations ip_vs_ftp_ops = {
 
 static int __init ip_vs_ftp_init(void)
 {
-	int rv;
-
-	rv = register_pernet_subsys(&ip_vs_ftp_ops);
 	/* rcu_barrier() is called by netns on error */
-	return rv;
+	return register_pernet_subsys(&ip_vs_ftp_ops);
 }
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 5824927cf8e0..b6aa4a970c6e 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -448,7 +448,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 703f11877bee..c13ff575f9f7 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -204,7 +204,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 	return least;
 }
@@ -249,7 +249,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
 		      __func__,
 		      IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port),
 		      atomic_read(&most->activeconns),
-		      atomic_read(&most->refcnt),
+		      refcount_read(&most->refcnt),
 		      atomic_read(&most->weight), moh);
 	return most;
 }
@@ -612,7 +612,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index fc230d99aa3b..6cf3fd81a5ec 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -85,7 +85,7 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 	struct nf_conntrack_tuple new_tuple;
 
-	if (ct == NULL || nf_ct_is_confirmed(ct) || nf_ct_is_untracked(ct) ||
+	if (ct == NULL || nf_ct_is_confirmed(ct) ||
 	    nf_ct_is_dying(ct))
 		return;
 
@@ -232,7 +232,7 @@ void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
 {
 	struct nf_conntrack_expect *exp;
 
-	if (ct == NULL || nf_ct_is_untracked(ct))
+	if (ct == NULL)
 		return;
 
 	exp = nf_ct_expect_alloc(ct);
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index a8b63401e773..7d9d4ac596ca 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -110,7 +110,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 8ae480715cea..ca880a3ad033 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -193,28 +193,6 @@ ip_vs_create_timeout_table(int *table, int size)
 }
 
 
-/*
- *	Set timeout value for state specified by name
- */
-int
-ip_vs_set_state_timeout(int *table, int num, const char *const *names,
-			const char *name, int to)
-{
-	int i;
-
-	if (!table || !name || !to)
-		return -EINVAL;
-
-	for (i = 0; i < num; i++) {
-		if (strcmp(names[i], name))
-			continue;
-		table[i] = to * HZ;
-		return 0;
-	}
-	return -ENOENT;
-}
-
-
 const char * ip_vs_state_name(__u16 proto, int state)
 {
 	struct ip_vs_protocol *pp = ip_vs_proto_get(proto);
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index d952d67f904d..56f8e4b204ff 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -447,7 +447,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 				ntohs(cp->cport),
 				sctp_state_name(cp->state),
 				sctp_state_name(next_state),
-				atomic_read(&cp->refcnt));
+				refcount_read(&cp->refcnt));
 		if (dest) {
 			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
 				(next_state != IP_VS_SCTP_S_ESTABLISHED)) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 5117bcb7d2f0..12dc8d5bc37d 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -557,7 +557,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 			      ntohs(cp->cport),
 			      tcp_state_name(cp->state),
 			      tcp_state_name(new_state),
-			      atomic_read(&cp->refcnt));
+			      refcount_read(&cp->refcnt));
 
 		if (dest) {
 			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 58bacfc461ee..ee0530d14c5f 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -97,7 +97,7 @@ stop:
 		      "activeconns %d refcnt %d weight %d\n",
 		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
 		      atomic_read(&dest->activeconns),
-		      atomic_read(&dest->refcnt), atomic_read(&dest->weight));
+		      refcount_read(&dest->refcnt), atomic_read(&dest->weight));
 
 	return dest;
 }
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index f8e2d00f528b..ab23cf203437 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -111,7 +111,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index b03c28084f81..0e5b64a75da0 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -520,7 +520,7 @@ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs,
 		if (!(cp->flags & IP_VS_CONN_F_TEMPLATE) &&
 		    pkts % sync_period != sysctl_sync_threshold(ipvs))
 			return 0;
-	} else if (sync_refresh_period <= 0 &&
+	} else if (!sync_refresh_period &&
 		   pkts != sysctl_sync_threshold(ipvs))
 		return 0;
 
@@ -1849,7 +1849,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	if (state == IP_VS_STATE_MASTER) {
 		struct ipvs_master_sync_state *ms;
 
-		ipvs->ms = kzalloc(count * sizeof(ipvs->ms[0]), GFP_KERNEL);
+		ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
 		if (!ipvs->ms)
 			goto out;
 		ms = ipvs->ms;
@@ -1862,7 +1862,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 			ms->ipvs = ipvs;
 		}
 	} else {
-		array = kzalloc(count * sizeof(struct task_struct *),
+		array = kcalloc(count, sizeof(struct task_struct *),
 				GFP_KERNEL);
 		if (!array)
 			goto out;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index 6b366fd90554..6add39e0ec20 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -83,7 +83,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 17e6d4406ca7..62258dd457ac 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -218,7 +218,7 @@ found:
 		      "activeconns %d refcnt %d weight %d\n",
 		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
 		      atomic_read(&dest->activeconns),
-		      atomic_read(&dest->refcnt),
+		      refcount_read(&dest->refcnt),
 		      atomic_read(&dest->weight));
 	mark->cl = dest;
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 4e1a98fcc8c3..2eab1e0400f4 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -775,7 +775,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-		if (ct && !nf_ct_is_untracked(ct)) {
+		if (ct) {
 			IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, ipvsh->off,
 					 "ip_vs_nat_xmit(): "
 					 "stopping DNAT to local address");
@@ -866,7 +866,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-		if (ct && !nf_ct_is_untracked(ct)) {
+		if (ct) {
 			IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, ipvsh->off,
 					 "ip_vs_nat_xmit_v6(): "
 					 "stopping DNAT to local address");
@@ -1338,7 +1338,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-		if (ct && !nf_ct_is_untracked(ct)) {
+		if (ct) {
 			IP_VS_DBG(10, "%s(): "
 				  "stopping DNAT to local address %pI4\n",
 				  __func__, &cp->daddr.ip);
@@ -1429,7 +1429,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-		if (ct && !nf_ct_is_untracked(ct)) {
+		if (ct) {
 			IP_VS_DBG(10, "%s(): "
 				  "stopping DNAT to local address %pI6\n",
 				  __func__, &cp->daddr.in6);
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index 45da11afa785..866916712905 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -55,7 +55,7 @@ seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
 };
 EXPORT_SYMBOL_GPL(seq_print_acct);
 
-static struct nf_ct_ext_type acct_extend __read_mostly = {
+static const struct nf_ct_ext_type acct_extend = {
 	.len	= sizeof(struct nf_conn_acct),
 	.align	= __alignof__(struct nf_conn_acct),
 	.id	= NF_CT_EXT_ACCT,
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index 57a26cc90c9f..03d2ccffa9fa 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -207,6 +207,8 @@ static int __init nf_conntrack_amanda_init(void)
 {
 	int ret, i;
 
+	NF_CT_HELPER_BUILD_BUG_ON(0);
+
 	for (i = 0; i < ARRAY_SIZE(search); i++) {
 		search[i].ts = textsearch_prepare(ts_algo, search[i].string,
 						  search[i].len,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 071b97fcbefb..f9245dbfe435 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -76,6 +76,7 @@ struct conntrack_gc_work {
 	struct delayed_work	dwork;
 	u32			last_bucket;
 	bool			exiting;
+	bool			early_drop;
 	long			next_gc_run;
 };
 
@@ -180,10 +181,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
 
 unsigned int nf_conntrack_max __read_mostly;
 seqcount_t nf_conntrack_generation __read_mostly;
-
-DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
-EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
-
 static unsigned int nf_conntrack_hash_rnd __read_mostly;
 
 static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
@@ -702,7 +699,7 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
 
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto->allow_clash &&
-	    !nfct_nat(ct) &&
+	    ((ct->status & IPS_NAT_DONE_MASK) == 0) &&
 	    !nf_ct_is_dying(ct) &&
 	    atomic_inc_not_zero(&ct->ct_general.use)) {
 		enum ip_conntrack_info oldinfo;
@@ -955,10 +952,30 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 	return false;
 }
 
+static bool gc_worker_skip_ct(const struct nf_conn *ct)
+{
+	return !nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct);
+}
+
+static bool gc_worker_can_early_drop(const struct nf_conn *ct)
+{
+	const struct nf_conntrack_l4proto *l4proto;
+
+	if (!test_bit(IPS_ASSURED_BIT, &ct->status))
+		return true;
+
+	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
+	if (l4proto->can_early_drop && l4proto->can_early_drop(ct))
+		return true;
+
+	return false;
+}
+
 static void gc_worker(struct work_struct *work)
 {
 	unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
 	unsigned int i, goal, buckets = 0, expired_count = 0;
+	unsigned int nf_conntrack_max95 = 0;
 	struct conntrack_gc_work *gc_work;
 	unsigned int ratio, scanned = 0;
 	unsigned long next_run;
@@ -967,6 +984,8 @@ static void gc_worker(struct work_struct *work)
 
 	goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;
 	i = gc_work->last_bucket;
+	if (gc_work->early_drop)
+		nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;
 
 	do {
 		struct nf_conntrack_tuple_hash *h;
@@ -983,6 +1002,8 @@ static void gc_worker(struct work_struct *work)
 			i = 0;
 
 		hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
+			struct net *net;
+
 			tmp = nf_ct_tuplehash_to_ctrack(h);
 
 			scanned++;
@@ -991,6 +1012,27 @@ static void gc_worker(struct work_struct *work)
 				expired_count++;
 				continue;
 			}
+
+			if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
+				continue;
+
+			net = nf_ct_net(tmp);
+			if (atomic_read(&net->ct.count) < nf_conntrack_max95)
+				continue;
+
+			/* need to take reference to avoid possible races */
+			if (!atomic_inc_not_zero(&tmp->ct_general.use))
+				continue;
+
+			if (gc_worker_skip_ct(tmp)) {
+				nf_ct_put(tmp);
+				continue;
+			}
+
+			if (gc_worker_can_early_drop(tmp))
+				nf_ct_kill(tmp);
+
+			nf_ct_put(tmp);
 		}
 
 		/* could check get_nulls_value() here and restart if ct
@@ -1036,6 +1078,7 @@ static void gc_worker(struct work_struct *work)
 
 	next_run = gc_work->next_gc_run;
 	gc_work->last_bucket = i;
+	gc_work->early_drop = false;
 	queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
 }
 
@@ -1061,6 +1104,8 @@ __nf_conntrack_alloc(struct net *net,
 	if (nf_conntrack_max &&
 	    unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
 		if (!early_drop(net, hash)) {
+			if (!conntrack_gc_work.early_drop)
+				conntrack_gc_work.early_drop = true;
 			atomic_dec(&net->ct.count);
 			net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
 			return ERR_PTR(-ENOMEM);
@@ -1129,7 +1174,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free);
 
 /* Allocate a new conntrack: we return -ENOMEM if classification
    failed due to stress.  Otherwise it really is unclassifiable. */
-static struct nf_conntrack_tuple_hash *
+static noinline struct nf_conntrack_tuple_hash *
 init_conntrack(struct net *net, struct nf_conn *tmpl,
 	       const struct nf_conntrack_tuple *tuple,
 	       struct nf_conntrack_l3proto *l3proto,
@@ -1237,21 +1282,20 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
 }
 
-/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */
-static inline struct nf_conn *
+/* On success, returns 0, sets skb->_nfct | ctinfo */
+static int
 resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  struct sk_buff *skb,
 		  unsigned int dataoff,
 		  u_int16_t l3num,
 		  u_int8_t protonum,
 		  struct nf_conntrack_l3proto *l3proto,
-		  struct nf_conntrack_l4proto *l4proto,
-		  int *set_reply,
-		  enum ip_conntrack_info *ctinfo)
+		  struct nf_conntrack_l4proto *l4proto)
 {
 	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
+	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_zone tmp;
 	struct nf_conn *ct;
 	u32 hash;
@@ -1260,7 +1304,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 			     dataoff, l3num, protonum, net, &tuple, l3proto,
 			     l4proto)) {
 		pr_debug("Can't get tuple\n");
-		return NULL;
+		return 0;
 	}
 
 	/* look for tuple match */
@@ -1271,33 +1315,30 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
 				   skb, dataoff, hash);
 		if (!h)
-			return NULL;
+			return 0;
 		if (IS_ERR(h))
-			return (void *)h;
+			return PTR_ERR(h);
 	}
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	/* It exists; we have (non-exclusive) reference. */
 	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
-		*ctinfo = IP_CT_ESTABLISHED_REPLY;
-		/* Please set reply bit if this packet OK */
-		*set_reply = 1;
+		ctinfo = IP_CT_ESTABLISHED_REPLY;
 	} else {
 		/* Once we've had two way comms, always ESTABLISHED. */
 		if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
 			pr_debug("normal packet for %p\n", ct);
-			*ctinfo = IP_CT_ESTABLISHED;
+			ctinfo = IP_CT_ESTABLISHED;
 		} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
 			pr_debug("related packet for %p\n", ct);
-			*ctinfo = IP_CT_RELATED;
+			ctinfo = IP_CT_RELATED;
 		} else {
 			pr_debug("new packet for %p\n", ct);
-			*ctinfo = IP_CT_NEW;
+			ctinfo = IP_CT_NEW;
 		}
-		*set_reply = 0;
 	}
-	nf_ct_set(skb, ct, *ctinfo);
-	return ct;
+	nf_ct_set(skb, ct, ctinfo);
+	return 0;
 }
 
 unsigned int
@@ -1311,13 +1352,13 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	unsigned int *timeouts;
 	unsigned int dataoff;
 	u_int8_t protonum;
-	int set_reply = 0;
 	int ret;
 
 	tmpl = nf_ct_get(skb, &ctinfo);
-	if (tmpl) {
+	if (tmpl || ctinfo == IP_CT_UNTRACKED) {
 		/* Previously seen (loopback or untracked)?  Ignore. */
-		if (!nf_ct_is_template(tmpl)) {
+		if ((tmpl && !nf_ct_is_template(tmpl)) ||
+		     ctinfo == IP_CT_UNTRACKED) {
 			NF_CT_STAT_INC_ATOMIC(net, ignore);
 			return NF_ACCEPT;
 		}
@@ -1354,23 +1395,22 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			goto out;
 	}
 repeat:
-	ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
-			       l3proto, l4proto, &set_reply, &ctinfo);
-	if (!ct) {
-		/* Not valid part of a connection */
-		NF_CT_STAT_INC_ATOMIC(net, invalid);
-		ret = NF_ACCEPT;
-		goto out;
-	}
-
-	if (IS_ERR(ct)) {
+	ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
+				l3proto, l4proto);
+	if (ret < 0) {
 		/* Too stressed to deal. */
 		NF_CT_STAT_INC_ATOMIC(net, drop);
 		ret = NF_DROP;
 		goto out;
 	}
 
-	NF_CT_ASSERT(skb_nfct(skb));
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct) {
+		/* Not valid part of a connection */
+		NF_CT_STAT_INC_ATOMIC(net, invalid);
+		ret = NF_ACCEPT;
+		goto out;
+	}
 
 	/* Decide what timeout policy we want to apply to this flow. */
 	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
@@ -1395,7 +1435,8 @@ repeat:
 		goto out;
 	}
 
-	if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
+	if (ctinfo == IP_CT_ESTABLISHED_REPLY &&
+	    !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
 		nf_conntrack_event_cache(IPCT_REPLY, ct);
 out:
 	if (tmpl)
@@ -1630,18 +1671,6 @@ void nf_ct_free_hashtable(void *hash, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
-static int untrack_refs(void)
-{
-	int cnt = 0, cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
-
-		cnt += atomic_read(&ct->ct_general.use) - 1;
-	}
-	return cnt;
-}
-
 void nf_conntrack_cleanup_start(void)
 {
 	conntrack_gc_work.exiting = true;
@@ -1651,8 +1680,6 @@ void nf_conntrack_cleanup_start(void)
 void nf_conntrack_cleanup_end(void)
 {
 	RCU_INIT_POINTER(nf_ct_destroy, NULL);
-	while (untrack_refs() > 0)
-		schedule();
 
 	cancel_delayed_work_sync(&conntrack_gc_work.dwork);
 	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
@@ -1826,20 +1853,44 @@ EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
 module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
 		  &nf_conntrack_htable_size, 0600);
 
-void nf_ct_untracked_status_or(unsigned long bits)
+static unsigned int total_extension_size(void)
 {
-	int cpu;
+	/* remember to add new extensions below */
+	BUILD_BUG_ON(NF_CT_EXT_NUM > 9);
 
-	for_each_possible_cpu(cpu)
-		per_cpu(nf_conntrack_untracked, cpu).status |= bits;
-}
-EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
+	return sizeof(struct nf_ct_ext) +
+	       sizeof(struct nf_conn_help)
+#if IS_ENABLED(CONFIG_NF_NAT)
+		+ sizeof(struct nf_conn_nat)
+#endif
+		+ sizeof(struct nf_conn_seqadj)
+		+ sizeof(struct nf_conn_acct)
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+		+ sizeof(struct nf_conntrack_ecache)
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+		+ sizeof(struct nf_conn_tstamp)
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+		+ sizeof(struct nf_conn_timeout)
+#endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+		+ sizeof(struct nf_conn_labels)
+#endif
+#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY)
+		+ sizeof(struct nf_conn_synproxy)
+#endif
+	;
+};
 
 int nf_conntrack_init_start(void)
 {
 	int max_factor = 8;
 	int ret = -ENOMEM;
-	int i, cpu;
+	int i;
+
+	/* struct nf_ct_ext uses u8 to store offsets/size */
+	BUILD_BUG_ON(total_extension_size() > 255u);
 
 	seqcount_init(&nf_conntrack_generation);
 
@@ -1922,15 +1973,6 @@ int nf_conntrack_init_start(void)
 	if (ret < 0)
 		goto err_proto;
 
-	/* Set up fake conntrack: to never be deleted, not in any hashes */
-	for_each_possible_cpu(cpu) {
-		struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
-		write_pnet(&ct->ct_net, &init_net);
-		atomic_set(&ct->ct_general.use, 1);
-	}
-	/*  - and look it like as a confirmed connection */
-	nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
-
 	conntrack_gc_work_init(&conntrack_gc_work);
 	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);
 
@@ -1978,6 +2020,7 @@ int nf_conntrack_init_net(struct net *net)
 	int ret = -ENOMEM;
 	int cpu;
 
+	BUILD_BUG_ON(IP_CT_UNTRACKED == IP_CT_NUMBER);
 	atomic_set(&net->ct.count, 0);
 
 	net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index da9df2d56e66..caac41ad9483 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -195,7 +195,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct)
 
 	events = xchg(&e->cache, 0);
 
-	if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct) || !events)
+	if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct))
 		goto out_unlock;
 
 	/* We make a copy of the missed event cache without taking
@@ -212,7 +212,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct)
 
 	ret = notify->fcn(events | missed, &item);
 
-	if (likely(ret >= 0 && !missed))
+	if (likely(ret == 0 && !missed))
 		goto out_unlock;
 
 	spin_lock_bh(&ct->lock);
@@ -290,6 +290,7 @@ void nf_conntrack_unregister_notifier(struct net *net,
 	BUG_ON(notify != new);
 	RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
+	/* synchronize_rcu() is called from ctnetlink_exit. */
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
 
@@ -326,6 +327,7 @@ void nf_ct_expect_unregister_notifier(struct net *net,
 	BUG_ON(notify != new);
 	RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
+	/* synchronize_rcu() is called from ctnetlink_exit. */
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
 
@@ -345,7 +347,7 @@ static struct ctl_table event_sysctl_table[] = {
 };
 #endif /* CONFIG_SYSCTL */
 
-static struct nf_ct_ext_type event_extend __read_mostly = {
+static const struct nf_ct_ext_type event_extend = {
 	.len	= sizeof(struct nf_conntrack_ecache),
 	.align	= __alignof__(struct nf_conntrack_ecache),
 	.id	= NF_CT_EXT_ECACHE,
@@ -418,6 +420,9 @@ int nf_conntrack_ecache_init(void)
 	int ret = nf_ct_extend_register(&event_extend);
 	if (ret < 0)
 		pr_err("nf_ct_event: Unable to register event extension.\n");
+
+	BUILD_BUG_ON(__IPCT_MAX >= 16);	/* ctmask, missed use u16 */
+
 	return ret;
 }
 
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4b2e1fb28bb4..e03d16ed550d 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -57,7 +57,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 	hlist_del_rcu(&exp->hnode);
 	net->ct.expect_count--;
 
-	hlist_del(&exp->lnode);
+	hlist_del_rcu(&exp->lnode);
 	master_help->expecting[exp->class]--;
 
 	nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
@@ -103,6 +103,17 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
 	       nf_ct_zone_equal_any(i->master, zone);
 }
 
+bool nf_ct_remove_expect(struct nf_conntrack_expect *exp)
+{
+	if (del_timer(&exp->timeout)) {
+		nf_ct_unlink_expect(exp);
+		nf_ct_expect_put(exp);
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(nf_ct_remove_expect);
+
 struct nf_conntrack_expect *
 __nf_ct_expect_find(struct net *net,
 		    const struct nf_conntrack_zone *zone,
@@ -133,7 +144,7 @@ nf_ct_expect_find_get(struct net *net,
 
 	rcu_read_lock();
 	i = __nf_ct_expect_find(net, zone, tuple);
-	if (i && !atomic_inc_not_zero(&i->use))
+	if (i && !refcount_inc_not_zero(&i->use))
 		i = NULL;
 	rcu_read_unlock();
 
@@ -186,7 +197,7 @@ nf_ct_find_expectation(struct net *net,
 		return NULL;
 
 	if (exp->flags & NF_CT_EXPECT_PERMANENT) {
-		atomic_inc(&exp->use);
+		refcount_inc(&exp->use);
 		return exp;
 	} else if (del_timer(&exp->timeout)) {
 		nf_ct_unlink_expect(exp);
@@ -211,10 +222,7 @@ void nf_ct_remove_expectations(struct nf_conn *ct)
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
-		if (del_timer(&exp->timeout)) {
-			nf_ct_unlink_expect(exp);
-			nf_ct_expect_put(exp);
-		}
+		nf_ct_remove_expect(exp);
 	}
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
@@ -255,10 +263,7 @@ static inline int expect_matches(const struct nf_conntrack_expect *a,
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
 {
 	spin_lock_bh(&nf_conntrack_expect_lock);
-	if (del_timer(&exp->timeout)) {
-		nf_ct_unlink_expect(exp);
-		nf_ct_expect_put(exp);
-	}
+	nf_ct_remove_expect(exp);
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);
@@ -275,7 +280,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
 		return NULL;
 
 	new->master = me;
-	atomic_set(&new->use, 1);
+	refcount_set(&new->use, 1);
 	return new;
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_alloc);
@@ -348,7 +353,7 @@ static void nf_ct_expect_free_rcu(struct rcu_head *head)
 
 void nf_ct_expect_put(struct nf_conntrack_expect *exp)
 {
-	if (atomic_dec_and_test(&exp->use))
+	if (refcount_dec_and_test(&exp->use))
 		call_rcu(&exp->rcu, nf_ct_expect_free_rcu);
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_put);
@@ -361,9 +366,9 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);
 
 	/* two references : one for hash insert, one for the timer */
-	atomic_add(2, &exp->use);
+	refcount_add(2, &exp->use);
 
-	hlist_add_head(&exp->lnode, &master_help->expectations);
+	hlist_add_head_rcu(&exp->lnode, &master_help->expectations);
 	master_help->expecting[exp->class]++;
 
 	hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
@@ -394,10 +399,8 @@ static void evict_oldest_expect(struct nf_conn *master,
 			last = exp;
 	}
 
-	if (last && del_timer(&last->timeout)) {
-		nf_ct_unlink_expect(last);
-		nf_ct_expect_put(last);
-	}
+	if (last)
+		nf_ct_remove_expect(last);
 }
 
 static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
@@ -419,11 +422,8 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	h = nf_ct_expect_dst_hash(net, &expect->tuple);
 	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
 		if (expect_matches(i, expect)) {
-			if (del_timer(&i->timeout)) {
-				nf_ct_unlink_expect(i);
-				nf_ct_expect_put(i);
+			if (nf_ct_remove_expect(expect))
 				break;
-			}
 		} else if (expect_clash(i, expect)) {
 			ret = -EBUSY;
 			goto out;
@@ -549,7 +549,7 @@ static int exp_seq_show(struct seq_file *s, void *v)
 		seq_printf(s, "%ld ", timer_pending(&expect->timeout)
 			   ? (long)(expect->timeout.expires - jiffies)/HZ : 0);
 	else
-		seq_printf(s, "- ");
+		seq_puts(s, "- ");
 	seq_printf(s, "l3proto = %u proto=%u ",
 		   expect->tuple.src.l3num,
 		   expect->tuple.dst.protonum);
@@ -559,7 +559,7 @@ static int exp_seq_show(struct seq_file *s, void *v)
 				       expect->tuple.dst.protonum));
 
 	if (expect->flags & NF_CT_EXPECT_PERMANENT) {
-		seq_printf(s, "PERMANENT");
+		seq_puts(s, "PERMANENT");
 		delim = ",";
 	}
 	if (expect->flags & NF_CT_EXPECT_INACTIVE) {
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 02bcf00c2492..6c605e88ebae 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -18,17 +18,14 @@
 
 static struct nf_ct_ext_type __rcu *nf_ct_ext_types[NF_CT_EXT_NUM];
 static DEFINE_MUTEX(nf_ct_ext_type_mutex);
+#define NF_CT_EXT_PREALLOC	128u /* conntrack events are on by default */
 
-void __nf_ct_ext_destroy(struct nf_conn *ct)
+void nf_ct_ext_destroy(struct nf_conn *ct)
 {
 	unsigned int i;
 	struct nf_ct_ext_type *t;
-	struct nf_ct_ext *ext = ct->ext;
 
 	for (i = 0; i < NF_CT_EXT_NUM; i++) {
-		if (!__nf_ct_ext_exist(ext, i))
-			continue;
-
 		rcu_read_lock();
 		t = rcu_dereference(nf_ct_ext_types[i]);
 
@@ -41,64 +38,47 @@ void __nf_ct_ext_destroy(struct nf_conn *ct)
 		rcu_read_unlock();
 	}
 }
-EXPORT_SYMBOL(__nf_ct_ext_destroy);
-
-static void *
-nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id,
-		 size_t var_alloc_len, gfp_t gfp)
-{
-	unsigned int off, len;
-	struct nf_ct_ext_type *t;
-	size_t alloc_size;
-
-	rcu_read_lock();
-	t = rcu_dereference(nf_ct_ext_types[id]);
-	BUG_ON(t == NULL);
-	off = ALIGN(sizeof(struct nf_ct_ext), t->align);
-	len = off + t->len + var_alloc_len;
-	alloc_size = t->alloc_size + var_alloc_len;
-	rcu_read_unlock();
-
-	*ext = kzalloc(alloc_size, gfp);
-	if (!*ext)
-		return NULL;
-
-	(*ext)->offset[id] = off;
-	(*ext)->len = len;
-
-	return (void *)(*ext) + off;
-}
+EXPORT_SYMBOL(nf_ct_ext_destroy);
 
-void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
-			     size_t var_alloc_len, gfp_t gfp)
+void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 {
+	unsigned int newlen, newoff, oldlen, alloc;
 	struct nf_ct_ext *old, *new;
-	int newlen, newoff;
 	struct nf_ct_ext_type *t;
 
 	/* Conntrack must not be confirmed to avoid races on reallocation. */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 
 	old = ct->ext;
-	if (!old)
-		return nf_ct_ext_create(&ct->ext, id, var_alloc_len, gfp);
 
-	if (__nf_ct_ext_exist(old, id))
-		return NULL;
+	if (old) {
+		if (__nf_ct_ext_exist(old, id))
+			return NULL;
+		oldlen = old->len;
+	} else {
+		oldlen = sizeof(*new);
+	}
 
 	rcu_read_lock();
 	t = rcu_dereference(nf_ct_ext_types[id]);
-	BUG_ON(t == NULL);
+	if (!t) {
+		rcu_read_unlock();
+		return NULL;
+	}
 
-	newoff = ALIGN(old->len, t->align);
-	newlen = newoff + t->len + var_alloc_len;
+	newoff = ALIGN(oldlen, t->align);
+	newlen = newoff + t->len;
 	rcu_read_unlock();
 
-	new = __krealloc(old, newlen, gfp);
+	alloc = max(newlen, NF_CT_EXT_PREALLOC);
+	new = __krealloc(old, alloc, gfp);
 	if (!new)
 		return NULL;
 
-	if (new != old) {
+	if (!old) {
+		memset(new->offset, 0, sizeof(new->offset));
+		ct->ext = new;
+	} else if (new != old) {
 		kfree_rcu(old, rcu);
 		rcu_assign_pointer(ct->ext, new);
 	}
@@ -108,45 +88,10 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
 	memset((void *)new + newoff, 0, newlen - newoff);
 	return (void *)new + newoff;
 }
-EXPORT_SYMBOL(__nf_ct_ext_add_length);
-
-static void update_alloc_size(struct nf_ct_ext_type *type)
-{
-	int i, j;
-	struct nf_ct_ext_type *t1, *t2;
-	enum nf_ct_ext_id min = 0, max = NF_CT_EXT_NUM - 1;
-
-	/* unnecessary to update all types */
-	if ((type->flags & NF_CT_EXT_F_PREALLOC) == 0) {
-		min = type->id;
-		max = type->id;
-	}
-
-	/* This assumes that extended areas in conntrack for the types
-	   whose NF_CT_EXT_F_PREALLOC bit set are allocated in order */
-	for (i = min; i <= max; i++) {
-		t1 = rcu_dereference_protected(nf_ct_ext_types[i],
-				lockdep_is_held(&nf_ct_ext_type_mutex));
-		if (!t1)
-			continue;
-
-		t1->alloc_size = ALIGN(sizeof(struct nf_ct_ext), t1->align) +
-				 t1->len;
-		for (j = 0; j < NF_CT_EXT_NUM; j++) {
-			t2 = rcu_dereference_protected(nf_ct_ext_types[j],
-				lockdep_is_held(&nf_ct_ext_type_mutex));
-			if (t2 == NULL || t2 == t1 ||
-			    (t2->flags & NF_CT_EXT_F_PREALLOC) == 0)
-				continue;
-
-			t1->alloc_size = ALIGN(t1->alloc_size, t2->align)
-					 + t2->len;
-		}
-	}
-}
+EXPORT_SYMBOL(nf_ct_ext_add);
 
 /* This MUST be called in process context. */
-int nf_ct_extend_register(struct nf_ct_ext_type *type)
+int nf_ct_extend_register(const struct nf_ct_ext_type *type)
 {
 	int ret = 0;
 
@@ -156,12 +101,7 @@ int nf_ct_extend_register(struct nf_ct_ext_type *type)
 		goto out;
 	}
 
-	/* This ensures that nf_ct_ext_create() can allocate enough area
-	   before updating alloc_size */
-	type->alloc_size = ALIGN(sizeof(struct nf_ct_ext), type->align)
-			   + type->len;
 	rcu_assign_pointer(nf_ct_ext_types[type->id], type);
-	update_alloc_size(type);
 out:
 	mutex_unlock(&nf_ct_ext_type_mutex);
 	return ret;
@@ -169,12 +109,11 @@ out:
 EXPORT_SYMBOL_GPL(nf_ct_extend_register);
 
 /* This MUST be called in process context. */
-void nf_ct_extend_unregister(struct nf_ct_ext_type *type)
+void nf_ct_extend_unregister(const struct nf_ct_ext_type *type)
 {
 	mutex_lock(&nf_ct_ext_type_mutex);
 	RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL);
-	update_alloc_size(type);
 	mutex_unlock(&nf_ct_ext_type_mutex);
-	rcu_barrier(); /* Wait for completion of call_rcu()'s */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 4aecef4a89fb..f0e9a7511e1a 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -577,6 +577,8 @@ static int __init nf_conntrack_ftp_init(void)
 {
 	int i, ret = 0;
 
+	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_ftp_master));
+
 	ftp_buffer = kmalloc(65536, GFP_KERNEL);
 	if (!ftp_buffer)
 		return -ENOMEM;
@@ -589,12 +591,10 @@ static int __init nf_conntrack_ftp_init(void)
 	for (i = 0; i < ports_c; i++) {
 		nf_ct_helper_init(&ftp[2 * i], AF_INET, IPPROTO_TCP, "ftp",
 				  FTP_PORT, ports[i], ports[i], &ftp_exp_policy,
-				  0, sizeof(struct nf_ct_ftp_master), help,
-				  nf_ct_ftp_from_nlattr, THIS_MODULE);
+				  0, help, nf_ct_ftp_from_nlattr, THIS_MODULE);
 		nf_ct_helper_init(&ftp[2 * i + 1], AF_INET6, IPPROTO_TCP, "ftp",
 				  FTP_PORT, ports[i], ports[i], &ftp_exp_policy,
-				  0, sizeof(struct nf_ct_ftp_master), help,
-				  nf_ct_ftp_from_nlattr, THIS_MODULE);
+				  0, help, nf_ct_ftp_from_nlattr, THIS_MODULE);
 	}
 
 	ret = nf_conntrack_helpers_register(ftp, ports_c * 2);
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index f65d93639d12..3bcdc718484e 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -637,7 +637,6 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = {
 static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = {
 	.name			= "H.245",
 	.me			= THIS_MODULE,
-	.data_len		= sizeof(struct nf_ct_h323_master),
 	.tuple.src.l3num	= AF_UNSPEC,
 	.tuple.dst.protonum	= IPPROTO_UDP,
 	.help			= h245_help,
@@ -1215,7 +1214,6 @@ static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = {
 	{
 		.name			= "Q.931",
 		.me			= THIS_MODULE,
-		.data_len		= sizeof(struct nf_ct_h323_master),
 		.tuple.src.l3num	= AF_INET,
 		.tuple.src.u.tcp.port	= cpu_to_be16(Q931_PORT),
 		.tuple.dst.protonum	= IPPROTO_TCP,
@@ -1800,7 +1798,6 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = {
 	{
 		.name			= "RAS",
 		.me			= THIS_MODULE,
-		.data_len		= sizeof(struct nf_ct_h323_master),
 		.tuple.src.l3num	= AF_INET,
 		.tuple.src.u.udp.port	= cpu_to_be16(RAS_PORT),
 		.tuple.dst.protonum	= IPPROTO_UDP,
@@ -1810,7 +1807,6 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = {
 	{
 		.name			= "RAS",
 		.me			= THIS_MODULE,
-		.data_len		= sizeof(struct nf_ct_h323_master),
 		.tuple.src.l3num	= AF_INET6,
 		.tuple.src.u.udp.port	= cpu_to_be16(RAS_PORT),
 		.tuple.dst.protonum	= IPPROTO_UDP,
@@ -1836,6 +1832,8 @@ static int __init nf_conntrack_h323_init(void)
 {
 	int ret;
 
+	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_h323_master));
+
 	h323_buffer = kmalloc(65536, GFP_KERNEL);
 	if (!h323_buffer)
 		return -ENOMEM;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 6dc44d9b4190..4b9dfe3eef62 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -158,16 +158,25 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum)
 {
 	struct nf_conntrack_helper *h;
 
+	rcu_read_lock();
+
 	h = __nf_conntrack_helper_find(name, l3num, protonum);
 #ifdef CONFIG_MODULES
 	if (h == NULL) {
-		if (request_module("nfct-helper-%s", name) == 0)
+		rcu_read_unlock();
+		if (request_module("nfct-helper-%s", name) == 0) {
+			rcu_read_lock();
 			h = __nf_conntrack_helper_find(name, l3num, protonum);
+		} else {
+			return h;
+		}
 	}
 #endif
 	if (h != NULL && !try_module_get(h->me))
 		h = NULL;
 
+	rcu_read_unlock();
+
 	return h;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get);
@@ -178,8 +187,7 @@ nf_ct_helper_ext_add(struct nf_conn *ct,
 {
 	struct nf_conn_help *help;
 
-	help = nf_ct_ext_add_length(ct, NF_CT_EXT_HELPER,
-				    helper->data_len, gfp);
+	help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp);
 	if (help)
 		INIT_HLIST_HEAD(&help->expectations);
 	else
@@ -311,38 +319,36 @@ void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n)
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister);
 
+/* Caller should hold the rcu lock */
 struct nf_ct_helper_expectfn *
 nf_ct_helper_expectfn_find_by_name(const char *name)
 {
 	struct nf_ct_helper_expectfn *cur;
 	bool found = false;
 
-	rcu_read_lock();
 	list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) {
 		if (!strcmp(cur->name, name)) {
 			found = true;
 			break;
 		}
 	}
-	rcu_read_unlock();
 	return found ? cur : NULL;
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name);
 
+/* Caller should hold the rcu lock */
 struct nf_ct_helper_expectfn *
 nf_ct_helper_expectfn_find_by_symbol(const void *symbol)
 {
 	struct nf_ct_helper_expectfn *cur;
 	bool found = false;
 
-	rcu_read_lock();
 	list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) {
 		if (cur->expectfn == symbol) {
 			found = true;
 			break;
 		}
 	}
-	rcu_read_unlock();
 	return found ? cur : NULL;
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol);
@@ -385,6 +391,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 	BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
 	BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1);
 
+	if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
+		return -EINVAL;
+
 	mutex_lock(&nf_ct_helper_mutex);
 	hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
 		if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) {
@@ -448,11 +457,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 			if ((rcu_dereference_protected(
 					help->helper,
 					lockdep_is_held(&nf_conntrack_expect_lock)
-					) == me || exp->helper == me) &&
-			    del_timer(&exp->timeout)) {
-				nf_ct_unlink_expect(exp);
-				nf_ct_expect_put(exp);
-			}
+					) == me || exp->helper == me))
+				nf_ct_remove_expect(exp);
 		}
 	}
 	spin_unlock_bh(&nf_conntrack_expect_lock);
@@ -484,7 +490,7 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 		       u16 l3num, u16 protonum, const char *name,
 		       u16 default_port, u16 spec_port, u32 id,
 		       const struct nf_conntrack_expect_policy *exp_pol,
-		       u32 expect_class_max, u32 data_len,
+		       u32 expect_class_max,
 		       int (*help)(struct sk_buff *skb, unsigned int protoff,
 				   struct nf_conn *ct,
 				   enum ip_conntrack_info ctinfo),
@@ -497,7 +503,6 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 	helper->tuple.src.u.all = htons(spec_port);
 	helper->expect_policy = exp_pol;
 	helper->expect_class_max = expect_class_max;
-	helper->data_len = data_len;
 	helper->help = help;
 	helper->from_nlattr = from_nlattr;
 	helper->me = module;
@@ -537,7 +542,7 @@ void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper,
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister);
 
-static struct nf_ct_ext_type helper_extend __read_mostly = {
+static const struct nf_ct_ext_type helper_extend = {
 	.len	= sizeof(struct nf_conn_help),
 	.align	= __alignof__(struct nf_conn_help),
 	.id	= NF_CT_EXT_HELPER,
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 1972a149f958..5523acce9d69 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -243,6 +243,12 @@ static int __init nf_conntrack_irc_init(void)
 		return -EINVAL;
 	}
 
+	if (max_dcc_channels > NF_CT_EXPECT_MAX_CNT) {
+		pr_err("max_dcc_channels must not be more than %u\n",
+		       NF_CT_EXPECT_MAX_CNT);
+		return -EINVAL;
+	}
+
 	irc_exp_policy.max_expected = max_dcc_channels;
 	irc_exp_policy.timeout = dcc_timeout;
 
@@ -257,7 +263,7 @@ static int __init nf_conntrack_irc_init(void)
 	for (i = 0; i < ports_c; i++) {
 		nf_ct_helper_init(&irc[i], AF_INET, IPPROTO_TCP, "irc",
 				  IRC_PORT, ports[i], i, &irc_exp_policy,
-				  0, 0, help, NULL, THIS_MODULE);
+				  0, help, NULL, THIS_MODULE);
 	}
 
 	ret = nf_conntrack_helpers_register(&irc[0], ports_c);
diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c
index bcab8bde7312..adf219859901 100644
--- a/net/netfilter/nf_conntrack_labels.c
+++ b/net/netfilter/nf_conntrack_labels.c
@@ -82,7 +82,7 @@ void nf_connlabels_put(struct net *net)
 }
 EXPORT_SYMBOL_GPL(nf_connlabels_put);
 
-static struct nf_ct_ext_type labels_extend __read_mostly = {
+static const struct nf_ct_ext_type labels_extend = {
 	.len    = sizeof(struct nf_conn_labels),
 	.align  = __alignof__(struct nf_conn_labels),
 	.id     = NF_CT_EXT_LABELS,
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index 4c8f30a3d6d2..496ce173f0c1 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -58,6 +58,8 @@ static struct nf_conntrack_helper helper __read_mostly = {
 
 static int __init nf_conntrack_netbios_ns_init(void)
 {
+	NF_CT_HELPER_BUILD_BUG_ON(0);
+
 	exp_policy.timeout = timeout;
 	return nf_conntrack_helper_register(&helper);
 }
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 6806b5e73567..5f6f2f388928 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -467,7 +467,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	struct nlattr *nest_parms;
 	unsigned int flags = portid ? NLM_F_MULTI : 0, event;
 
-	event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_NEW);
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -627,10 +627,6 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 	unsigned int flags = 0, group;
 	int err;
 
-	/* ignore our fake conntrack entry */
-	if (nf_ct_is_untracked(ct))
-		return 0;
-
 	if (events & (1 << IPCT_DESTROY)) {
 		type = IPCTNL_MSG_CT_DELETE;
 		group = NFNLGRP_CONNTRACK_DESTROY;
@@ -652,7 +648,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 	if (skb == NULL)
 		goto errout;
 
-	type |= NFNL_SUBSYS_CTNETLINK << 8;
+	type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type);
 	nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -908,7 +904,7 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
 	struct nf_conntrack_l3proto *l3proto;
 	int ret = 0;
 
-	ret = nla_parse_nested(tb, CTA_IP_MAX, attr, NULL);
+	ret = nla_parse_nested(tb, CTA_IP_MAX, attr, NULL, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -917,7 +913,7 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
 
 	if (likely(l3proto->nlattr_to_tuple)) {
 		ret = nla_validate_nested(attr, CTA_IP_MAX,
-					  l3proto->nla_policy);
+					  l3proto->nla_policy, NULL);
 		if (ret == 0)
 			ret = l3proto->nlattr_to_tuple(tb, tuple);
 	}
@@ -938,7 +934,8 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
 	struct nf_conntrack_l4proto *l4proto;
 	int ret = 0;
 
-	ret = nla_parse_nested(tb, CTA_PROTO_MAX, attr, proto_nla_policy);
+	ret = nla_parse_nested(tb, CTA_PROTO_MAX, attr, proto_nla_policy,
+			       NULL);
 	if (ret < 0)
 		return ret;
 
@@ -951,7 +948,7 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
 
 	if (likely(l4proto->nlattr_to_tuple)) {
 		ret = nla_validate_nested(attr, CTA_PROTO_MAX,
-					  l4proto->nla_policy);
+					  l4proto->nla_policy, NULL);
 		if (ret == 0)
 			ret = l4proto->nlattr_to_tuple(tb, tuple);
 	}
@@ -1015,7 +1012,8 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 
 	memset(tuple, 0, sizeof(*tuple));
 
-	err = nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy);
+	err = nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
@@ -1065,7 +1063,7 @@ static int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name,
 	int err;
 	struct nlattr *tb[CTA_HELP_MAX+1];
 
-	err = nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy);
+	err = nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1488,11 +1486,16 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
 		 * treat the second attempt as a no-op instead of returning
 		 * an error.
 		 */
-		if (help && help->helper &&
-		    !strcmp(help->helper->name, helpname))
-			return 0;
-		else
-			return -EBUSY;
+		err = -EBUSY;
+		if (help) {
+			rcu_read_lock();
+			helper = rcu_dereference(help->helper);
+			if (helper && !strcmp(helper->name, helpname))
+				err = 0;
+			rcu_read_unlock();
+		}
+
+		return err;
 	}
 
 	if (!strcmp(helpname, "")) {
@@ -1566,7 +1569,8 @@ static int ctnetlink_change_protoinfo(struct nf_conn *ct,
 	struct nf_conntrack_l4proto *l4proto;
 	int err = 0;
 
-	err = nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy);
+	err = nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
@@ -1591,7 +1595,7 @@ static int change_seq_adj(struct nf_ct_seqadj *seq,
 	int err;
 	struct nlattr *cda[CTA_SEQADJ_MAX+1];
 
-	err = nla_parse_nested(cda, CTA_SEQADJ_MAX, attr, seqadj_policy);
+	err = nla_parse_nested(cda, CTA_SEQADJ_MAX, attr, seqadj_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1929,9 +1933,9 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl,
 
 			err = 0;
 			if (test_bit(IPS_EXPECTED_BIT, &ct->status))
-				events = IPCT_RELATED;
+				events = 1 << IPCT_RELATED;
 			else
-				events = IPCT_NEW;
+				events = 1 << IPCT_NEW;
 
 			if (cda[CTA_LABELS] &&
 			    ctnetlink_attach_labels(ct, cda) == 0)
@@ -1983,7 +1987,8 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = portid ? NLM_F_MULTI : 0, event;
 
-	event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS_CPU);
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK,
+			      IPCTNL_MSG_CT_GET_STATS_CPU);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -2066,7 +2071,7 @@ ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	unsigned int flags = portid ? NLM_F_MULTI : 0, event;
 	unsigned int nr_conntracks = atomic_read(&net->ct.count);
 
-	event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS);
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -2172,13 +2177,7 @@ ctnetlink_glue_build_size(const struct nf_conn *ct)
 static struct nf_conn *ctnetlink_glue_get_ct(const struct sk_buff *skb,
 					     enum ip_conntrack_info *ctinfo)
 {
-	struct nf_conn *ct;
-
-	ct = nf_ct_get(skb, ctinfo);
-	if (ct && nf_ct_is_untracked(ct))
-		ct = NULL;
-
-	return ct;
+	return nf_ct_get(skb, ctinfo);
 }
 
 static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
@@ -2348,7 +2347,7 @@ ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct)
 	struct nlattr *cda[CTA_MAX+1];
 	int ret;
 
-	ret = nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy);
+	ret = nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -2385,7 +2384,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 	struct nf_conntrack_expect *exp;
 	int err;
 
-	err = nla_parse_nested(cda, CTA_EXPECT_MAX, attr, exp_nla_policy);
+	err = nla_parse_nested(cda, CTA_EXPECT_MAX, attr, exp_nla_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
@@ -2576,7 +2576,7 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
 
-	event |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -2627,7 +2627,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item)
 	if (skb == NULL)
 		goto errout;
 
-	type |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
+	type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type);
 	nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -2675,8 +2675,8 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	last = (struct nf_conntrack_expect *)cb->args[1];
 	for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) {
 restart:
-		hlist_for_each_entry(exp, &nf_ct_expect_hash[cb->args[0]],
-				     hnode) {
+		hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]],
+					 hnode) {
 			if (l3proto && exp->tuple.src.l3num != l3proto)
 				continue;
 
@@ -2693,7 +2693,7 @@ restart:
 						    cb->nlh->nlmsg_seq,
 						    IPCTNL_MSG_EXP_NEW,
 						    exp) < 0) {
-				if (!atomic_inc_not_zero(&exp->use))
+				if (!refcount_inc_not_zero(&exp->use))
 					continue;
 				cb->args[1] = (unsigned long)exp;
 				goto out;
@@ -2727,7 +2727,7 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	last = (struct nf_conntrack_expect *)cb->args[1];
 restart:
-	hlist_for_each_entry(exp, &help->expectations, lnode) {
+	hlist_for_each_entry_rcu(exp, &help->expectations, lnode) {
 		if (l3proto && exp->tuple.src.l3num != l3proto)
 			continue;
 		if (cb->args[1]) {
@@ -2739,7 +2739,7 @@ restart:
 					    cb->nlh->nlmsg_seq,
 					    IPCTNL_MSG_EXP_NEW,
 					    exp) < 0) {
-			if (!atomic_inc_not_zero(&exp->use))
+			if (!refcount_inc_not_zero(&exp->use))
 				continue;
 			cb->args[1] = (unsigned long)exp;
 			goto out;
@@ -2789,6 +2789,12 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl,
 		return -ENOENT;
 
 	ct = nf_ct_tuplehash_to_ctrack(h);
+	/* No expectation linked to this connection tracking. */
+	if (!nfct_help(ct)) {
+		nf_ct_put(ct);
+		return 0;
+	}
+
 	c.data = ct;
 
 	err = netlink_dump_start(ctnl, skb, nlh, &c);
@@ -3004,7 +3010,8 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 	struct nf_conntrack_tuple nat_tuple = {};
 	int err;
 
-	err = nla_parse_nested(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy);
+	err = nla_parse_nested(tb, CTA_EXPECT_NAT_MAX, attr,
+			       exp_nat_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -3038,6 +3045,10 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 	struct nf_conn_help *help;
 	int err;
 
+	help = nfct_help(ct);
+	if (!help)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (cda[CTA_EXPECT_CLASS] && helper) {
 		class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS]));
 		if (class > helper->expect_class_max)
@@ -3047,26 +3058,11 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 	if (!exp)
 		return ERR_PTR(-ENOMEM);
 
-	help = nfct_help(ct);
-	if (!help) {
-		if (!cda[CTA_EXPECT_TIMEOUT]) {
-			err = -EINVAL;
-			goto err_out;
-		}
-		exp->timeout.expires =
-		  jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ;
-
-		exp->flags = NF_CT_EXPECT_USERSPACE;
-		if (cda[CTA_EXPECT_FLAGS]) {
-			exp->flags |=
-				ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS]));
-		}
+	if (cda[CTA_EXPECT_FLAGS]) {
+		exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS]));
+		exp->flags &= ~NF_CT_EXPECT_USERSPACE;
 	} else {
-		if (cda[CTA_EXPECT_FLAGS]) {
-			exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS]));
-			exp->flags &= ~NF_CT_EXPECT_USERSPACE;
-		} else
-			exp->flags = 0;
+		exp->flags = 0;
 	}
 	if (cda[CTA_EXPECT_FN]) {
 		const char *name = nla_data(cda[CTA_EXPECT_FN]);
@@ -3133,23 +3129,27 @@ ctnetlink_create_expect(struct net *net,
 		return -ENOENT;
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
+	rcu_read_lock();
 	if (cda[CTA_EXPECT_HELP_NAME]) {
 		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
 
 		helper = __nf_conntrack_helper_find(helpname, u3,
 						    nf_ct_protonum(ct));
 		if (helper == NULL) {
+			rcu_read_unlock();
 #ifdef CONFIG_MODULES
 			if (request_module("nfct-helper-%s", helpname) < 0) {
 				err = -EOPNOTSUPP;
 				goto err_ct;
 			}
+			rcu_read_lock();
 			helper = __nf_conntrack_helper_find(helpname, u3,
 							    nf_ct_protonum(ct));
 			if (helper) {
 				err = -EAGAIN;
-				goto err_ct;
+				goto err_rcu;
 			}
+			rcu_read_unlock();
 #endif
 			err = -EOPNOTSUPP;
 			goto err_ct;
@@ -3159,11 +3159,13 @@ ctnetlink_create_expect(struct net *net,
 	exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask);
 	if (IS_ERR(exp)) {
 		err = PTR_ERR(exp);
-		goto err_ct;
+		goto err_rcu;
 	}
 
 	err = nf_ct_expect_related_report(exp, portid, report);
 	nf_ct_expect_put(exp);
+err_rcu:
+	rcu_read_unlock();
 err_ct:
 	nf_ct_put(ct);
 	return err;
@@ -3223,7 +3225,8 @@ ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu,
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = portid ? NLM_F_MULTI : 0, event;
 
-	event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_EXP_GET_STATS_CPU);
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK,
+			      IPCTNL_MSG_EXP_GET_STATS_CPU);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -3442,6 +3445,7 @@ static void __exit ctnetlink_exit(void)
 #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT
 	RCU_INIT_POINTER(nfnl_ct_hook, NULL);
 #endif
+	synchronize_rcu();
 }
 
 module_init(ctnetlink_init);
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index f60a4755d71e..6959e93063d4 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -263,7 +263,7 @@ out_unexpect_orig:
 	goto out_put_both;
 }
 
-static inline int
+static int
 pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		 struct PptpControlHeader *ctlh,
 		 union pptp_ctrl_union *pptpReq,
@@ -391,7 +391,7 @@ invalid:
 	return NF_ACCEPT;
 }
 
-static inline int
+static int
 pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		  struct PptpControlHeader *ctlh,
 		  union pptp_ctrl_union *pptpReq,
@@ -523,6 +523,14 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff,
 	int ret;
 	u_int16_t msg;
 
+#if IS_ENABLED(CONFIG_NF_NAT)
+	if (!nf_ct_is_confirmed(ct) && (ct->status & IPS_NAT_MASK)) {
+		struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT);
+
+		if (!nat && !nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC))
+			return NF_DROP;
+	}
+#endif
 	/* don't do any tracking before tcp handshake complete */
 	if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
 		return NF_ACCEPT;
@@ -596,7 +604,6 @@ static const struct nf_conntrack_expect_policy pptp_exp_policy = {
 static struct nf_conntrack_helper pptp __read_mostly = {
 	.name			= "pptp",
 	.me			= THIS_MODULE,
-	.data_len		= sizeof(struct nf_ct_pptp_master),
 	.tuple.src.l3num	= AF_INET,
 	.tuple.src.u.tcp.port	= cpu_to_be16(PPTP_CONTROL_PORT),
 	.tuple.dst.protonum	= IPPROTO_TCP,
@@ -607,6 +614,8 @@ static struct nf_conntrack_helper pptp __read_mostly = {
 
 static int __init nf_conntrack_pptp_init(void)
 {
+	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_pptp_master));
+
 	return nf_conntrack_helper_register(&pptp);
 }
 
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 2d6ee1803415..2de6c1fe3261 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -202,7 +202,7 @@ static int kill_l3proto(struct nf_conn *i, void *data)
 static int kill_l4proto(struct nf_conn *i, void *data)
 {
 	struct nf_conntrack_l4proto *l4proto;
-	l4proto = (struct nf_conntrack_l4proto *)data;
+	l4proto = data;
 	return nf_ct_protonum(i) == l4proto->l4proto &&
 	       nf_ct_l3num(i) == l4proto->l3proto;
 }
@@ -441,9 +441,8 @@ EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one);
 void nf_ct_l4proto_pernet_unregister_one(struct net *net,
 					 struct nf_conntrack_l4proto *l4proto)
 {
-	struct nf_proto_net *pn = NULL;
+	struct nf_proto_net *pn = nf_ct_l4proto_net(net, l4proto);
 
-	pn = nf_ct_l4proto_net(net, l4proto);
 	if (pn == NULL)
 		return;
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 93dd1c5b7bff..b553fdd68816 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -609,6 +609,20 @@ out_invalid:
 	return -NF_ACCEPT;
 }
 
+static bool dccp_can_early_drop(const struct nf_conn *ct)
+{
+	switch (ct->proto.dccp.state) {
+	case CT_DCCP_CLOSEREQ:
+	case CT_DCCP_CLOSING:
+	case CT_DCCP_TIMEWAIT:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
 static void dccp_print_tuple(struct seq_file *s,
 			     const struct nf_conntrack_tuple *tuple)
 {
@@ -665,7 +679,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
 		return 0;
 
 	err = nla_parse_nested(tb, CTA_PROTOINFO_DCCP_MAX, attr,
-			       dccp_nla_policy);
+			       dccp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -868,6 +882,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 __read_mostly = {
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,
 	.error			= dccp_error,
+	.can_early_drop		= dccp_can_early_drop,
 	.print_tuple		= dccp_print_tuple,
 	.print_conntrack	= dccp_print_conntrack,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
@@ -902,6 +917,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 __read_mostly = {
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,
 	.error			= dccp_error,
+	.can_early_drop		= dccp_can_early_drop,
 	.print_tuple		= dccp_print_tuple,
 	.print_conntrack	= dccp_print_conntrack,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 33279aab583d..13875d599a85 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -535,6 +535,20 @@ out_invalid:
 	return -NF_ACCEPT;
 }
 
+static bool sctp_can_early_drop(const struct nf_conn *ct)
+{
+	switch (ct->proto.sctp.state) {
+	case SCTP_CONNTRACK_SHUTDOWN_SENT:
+	case SCTP_CONNTRACK_SHUTDOWN_RECD:
+	case SCTP_CONNTRACK_SHUTDOWN_ACK_SENT:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
@@ -584,10 +598,8 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct)
 	if (!attr)
 		return 0;
 
-	err = nla_parse_nested(tb,
-			       CTA_PROTOINFO_SCTP_MAX,
-			       attr,
-			       sctp_nla_policy);
+	err = nla_parse_nested(tb, CTA_PROTOINFO_SCTP_MAX, attr,
+			       sctp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -783,6 +795,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
 	.get_timeouts		= sctp_get_timeouts,
 	.new 			= sctp_new,
 	.error			= sctp_error,
+	.can_early_drop		= sctp_can_early_drop,
 	.me 			= THIS_MODULE,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= sctp_to_nlattr,
@@ -818,6 +831,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
 	.get_timeouts		= sctp_get_timeouts,
 	.new 			= sctp_new,
 	.error			= sctp_error,
+	.can_early_drop		= sctp_can_early_drop,
 	.me 			= THIS_MODULE,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= sctp_to_nlattr,
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index b122e9dacfed..9758a7dfd83e 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -419,10 +419,9 @@ static void tcp_options(const struct sk_buff *skb,
 				 && opsize == TCPOLEN_WINDOW) {
 				state->td_scale = *(u_int8_t *)ptr;
 
-				if (state->td_scale > 14) {
-					/* See RFC1323 */
-					state->td_scale = 14;
-				}
+				if (state->td_scale > TCP_MAX_WSCALE)
+					state->td_scale = TCP_MAX_WSCALE;
+
 				state->flags |=
 					IP_CT_TCP_FLAG_WINDOW_SCALE;
 			}
@@ -1172,6 +1171,22 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	return true;
 }
 
+static bool tcp_can_early_drop(const struct nf_conn *ct)
+{
+	switch (ct->proto.tcp.state) {
+	case TCP_CONNTRACK_FIN_WAIT:
+	case TCP_CONNTRACK_LAST_ACK:
+	case TCP_CONNTRACK_TIME_WAIT:
+	case TCP_CONNTRACK_CLOSE:
+	case TCP_CONNTRACK_CLOSE_WAIT:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
@@ -1234,7 +1249,8 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
 	if (!pattr)
 		return 0;
 
-	err = nla_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, pattr, tcp_nla_policy);
+	err = nla_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, pattr,
+			       tcp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1549,6 +1565,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
 	.get_timeouts		= tcp_get_timeouts,
 	.new 			= tcp_new,
 	.error			= tcp_error,
+	.can_early_drop		= tcp_can_early_drop,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= tcp_to_nlattr,
 	.nlattr_size		= tcp_nlattr_size,
@@ -1586,6 +1603,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
 	.get_timeouts		= tcp_get_timeouts,
 	.new 			= tcp_new,
 	.error			= tcp_error,
+	.can_early_drop		= tcp_can_early_drop,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= tcp_to_nlattr,
 	.nlattr_size		= tcp_nlattr_size,
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 9dcb9ee9b97d..ae457f39d5ce 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -184,6 +184,8 @@ static int __init nf_conntrack_sane_init(void)
 {
 	int i, ret = 0;
 
+	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_sane_master));
+
 	sane_buffer = kmalloc(65536, GFP_KERNEL);
 	if (!sane_buffer)
 		return -ENOMEM;
@@ -196,13 +198,11 @@ static int __init nf_conntrack_sane_init(void)
 	for (i = 0; i < ports_c; i++) {
 		nf_ct_helper_init(&sane[2 * i], AF_INET, IPPROTO_TCP, "sane",
 				  SANE_PORT, ports[i], ports[i],
-				  &sane_exp_policy, 0,
-				  sizeof(struct nf_ct_sane_master), help, NULL,
+				  &sane_exp_policy, 0, help, NULL,
 				  THIS_MODULE);
 		nf_ct_helper_init(&sane[2 * i + 1], AF_INET6, IPPROTO_TCP, "sane",
 				  SANE_PORT, ports[i], ports[i],
-				  &sane_exp_policy, 0,
-				  sizeof(struct nf_ct_sane_master), help, NULL,
+				  &sane_exp_policy, 0, help, NULL,
 				  THIS_MODULE);
 	}
 
diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index ef7063eced7c..a975efd6b8c3 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -231,7 +231,7 @@ s32 nf_ct_seq_offset(const struct nf_conn *ct,
 }
 EXPORT_SYMBOL_GPL(nf_ct_seq_offset);
 
-static struct nf_ct_ext_type nf_ct_seqadj_extend __read_mostly = {
+static const struct nf_ct_ext_type nf_ct_seqadj_extend = {
 	.len	= sizeof(struct nf_conn_seqadj),
 	.align	= __alignof__(struct nf_conn_seqadj),
 	.id	= NF_CT_EXT_SEQADJ,
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 0d17894798b5..d38af4274335 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -829,10 +829,8 @@ static void flush_expectations(struct nf_conn *ct, bool media)
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media)
 			continue;
-		if (!del_timer(&exp->timeout))
+		if (!nf_ct_remove_expect(exp))
 			continue;
-		nf_ct_unlink_expect(exp);
-		nf_ct_expect_put(exp);
 		if (!media)
 			break;
 	}
@@ -1624,29 +1622,27 @@ static int __init nf_conntrack_sip_init(void)
 {
 	int i, ret;
 
+	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_sip_master));
+
 	if (ports_c == 0)
 		ports[ports_c++] = SIP_PORT;
 
 	for (i = 0; i < ports_c; i++) {
 		nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP, "sip",
 				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX,
-				  sizeof(struct nf_ct_sip_master), sip_help_udp,
+				  SIP_EXPECT_MAX, sip_help_udp,
 				  NULL, THIS_MODULE);
 		nf_ct_helper_init(&sip[4 * i + 1], AF_INET, IPPROTO_TCP, "sip",
 				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX,
-				  sizeof(struct nf_ct_sip_master), sip_help_tcp,
+				  SIP_EXPECT_MAX, sip_help_tcp,
 				  NULL, THIS_MODULE);
 		nf_ct_helper_init(&sip[4 * i + 2], AF_INET6, IPPROTO_UDP, "sip",
 				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX,
-				  sizeof(struct nf_ct_sip_master), sip_help_udp,
+				  SIP_EXPECT_MAX, sip_help_udp,
 				  NULL, THIS_MODULE);
 		nf_ct_helper_init(&sip[4 * i + 3], AF_INET6, IPPROTO_TCP, "sip",
 				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX,
-				  sizeof(struct nf_ct_sip_master), sip_help_tcp,
+				  SIP_EXPECT_MAX, sip_help_tcp,
 				  NULL, THIS_MODULE);
 	}
 
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 2256147dcaad..ccb5cb9043e0 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -250,7 +250,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		goto release;
 
 	if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
-		seq_printf(s, "[UNREPLIED] ");
+		seq_puts(s, "[UNREPLIED] ");
 
 	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 		    l3proto, l4proto);
@@ -261,7 +261,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		goto release;
 
 	if (test_bit(IPS_ASSURED_BIT, &ct->status))
-		seq_printf(s, "[ASSURED] ");
+		seq_puts(s, "[ASSURED] ");
 
 	if (seq_has_overflowed(s))
 		goto release;
@@ -350,7 +350,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
 	const struct ip_conntrack_stat *st = v;
 
 	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq, "entries  searched found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error  expect_new expect_create expect_delete search_restart\n");
+		seq_puts(seq, "entries  searched found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error  expect_new expect_create expect_delete search_restart\n");
 		return 0;
 	}
 
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index b1227dc6f75e..0ec6779fd5d9 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -113,16 +113,18 @@ static int __init nf_conntrack_tftp_init(void)
 {
 	int i, ret;
 
+	NF_CT_HELPER_BUILD_BUG_ON(0);
+
 	if (ports_c == 0)
 		ports[ports_c++] = TFTP_PORT;
 
 	for (i = 0; i < ports_c; i++) {
 		nf_ct_helper_init(&tftp[2 * i], AF_INET, IPPROTO_UDP, "tftp",
 				  TFTP_PORT, ports[i], i, &tftp_exp_policy,
-				  0, 0, tftp_help, NULL, THIS_MODULE);
+				  0, tftp_help, NULL, THIS_MODULE);
 		nf_ct_helper_init(&tftp[2 * i + 1], AF_INET6, IPPROTO_UDP, "tftp",
 				  TFTP_PORT, ports[i], i, &tftp_exp_policy,
-				  0, 0, tftp_help, NULL, THIS_MODULE);
+				  0, tftp_help, NULL, THIS_MODULE);
 	}
 
 	ret = nf_conntrack_helpers_register(tftp, ports_c * 2);
diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c
index 26e742006c48..46aee65f339b 100644
--- a/net/netfilter/nf_conntrack_timeout.c
+++ b/net/netfilter/nf_conntrack_timeout.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook);
 void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook);
 
-static struct nf_ct_ext_type timeout_extend __read_mostly = {
+static const struct nf_ct_ext_type timeout_extend = {
 	.len	= sizeof(struct nf_conn_timeout),
 	.align	= __alignof__(struct nf_conn_timeout),
 	.id	= NF_CT_EXT_TIMEOUT,
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
index 7a394df0deb7..4c4734b78318 100644
--- a/net/netfilter/nf_conntrack_timestamp.c
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -33,7 +33,7 @@ static struct ctl_table tstamp_sysctl_table[] = {
 };
 #endif /* CONFIG_SYSCTL */
 
-static struct nf_ct_ext_type tstamp_extend __read_mostly = {
+static const struct nf_ct_ext_type tstamp_extend = {
 	.len	= sizeof(struct nf_conn_tstamp),
 	.align	= __alignof__(struct nf_conn_tstamp),
 	.id	= NF_CT_EXT_TSTAMP,
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index c46d214d5323..bfa742da83af 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -14,7 +14,7 @@
 /* nf_queue.c */
 int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
 	     struct nf_hook_entry **entryp, unsigned int verdict);
-void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry);
+unsigned int nf_queue_nf_hook_drop(struct net *net);
 int __init netfilter_queue_init(void);
 
 /* nf_log.c */
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 8d85a0598b60..8bb152a7cca4 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -71,7 +71,6 @@ void nf_log_unset(struct net *net, const struct nf_logger *logger)
 			RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL);
 	}
 	mutex_unlock(&nf_log_mutex);
-	synchronize_rcu();
 }
 EXPORT_SYMBOL(nf_log_unset);
 
@@ -376,13 +375,13 @@ static int seq_show(struct seq_file *s, void *v)
 		logger = nft_log_dereference(loggers[*pos][i]);
 		seq_printf(s, "%s", logger->name);
 		if (i == 0 && loggers[*pos][i + 1] != NULL)
-			seq_printf(s, ",");
+			seq_puts(s, ",");
 
 		if (seq_has_overflowed(s))
 			return -ENOSPC;
 	}
 
-	seq_printf(s, ")\n");
+	seq_puts(s, ")\n");
 
 	if (seq_has_overflowed(s))
 		return -ENOSPC;
diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c
index eb772380a202..e4d61a7a5258 100644
--- a/net/netfilter/nf_nat_amanda.c
+++ b/net/netfilter/nf_nat_amanda.c
@@ -33,7 +33,6 @@ static unsigned int help(struct sk_buff *skb,
 {
 	char buffer[sizeof("65535")];
 	u_int16_t port;
-	unsigned int ret;
 
 	/* Connection comes from client. */
 	exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
@@ -63,14 +62,14 @@ static unsigned int help(struct sk_buff *skb,
 	}
 
 	sprintf(buffer, "%u", port);
-	ret = nf_nat_mangle_udp_packet(skb, exp->master, ctinfo,
-				       protoff, matchoff, matchlen,
-				       buffer, strlen(buffer));
-	if (ret != NF_ACCEPT) {
+	if (!nf_nat_mangle_udp_packet(skb, exp->master, ctinfo,
+				      protoff, matchoff, matchlen,
+				      buffer, strlen(buffer))) {
 		nf_ct_helper_log(skb, exp->master, "cannot mangle packet");
 		nf_ct_unexpect_related(exp);
+		return NF_DROP;
 	}
-	return ret;
+	return NF_ACCEPT;
 }
 
 static void __exit nf_nat_amanda_fini(void)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 94b14c5a8b17..b48d6b5aae8a 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -71,11 +71,10 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 	if (ct == NULL)
 		return;
 
-	family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
-	rcu_read_lock();
+	family = nf_ct_l3num(ct);
 	l3proto = __nf_nat_l3proto_find(family);
 	if (l3proto == NULL)
-		goto out;
+		return;
 
 	dir = CTINFO2DIR(ctinfo);
 	if (dir == IP_CT_DIR_ORIGINAL)
@@ -84,8 +83,6 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 		statusbit = IPS_SRC_NAT;
 
 	l3proto->decode_session(skb, ct, dir, statusbit, fl);
-out:
-	rcu_read_unlock();
 }
 
 int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family)
@@ -411,12 +408,6 @@ nf_nat_setup_info(struct nf_conn *ct,
 		  enum nf_nat_manip_type maniptype)
 {
 	struct nf_conntrack_tuple curr_tuple, new_tuple;
-	struct nf_conn_nat *nat;
-
-	/* nat helper or nfctnetlink also setup binding */
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
 
 	NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
 		     maniptype == NF_NAT_MANIP_DST);
@@ -549,10 +540,6 @@ struct nf_nat_proto_clean {
 static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 {
 	const struct nf_nat_proto_clean *clean = data;
-	struct nf_conn_nat *nat = nfct_nat(i);
-
-	if (!nat)
-		return 0;
 
 	if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) ||
 	    (clean->l4proto && nf_ct_protonum(i) != clean->l4proto))
@@ -563,12 +550,10 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 
 static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
 {
-	struct nf_conn_nat *nat = nfct_nat(ct);
-
 	if (nf_nat_proto_remove(ct, data))
 		return 1;
 
-	if (!nat)
+	if ((ct->status & IPS_SRC_NAT_DONE) == 0)
 		return 0;
 
 	/* This netns is being destroyed, and conntrack has nat null binding.
@@ -716,13 +701,9 @@ EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister);
 /* No one using conntrack by the time this called. */
 static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
 {
-	struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT);
-
-	if (!nat)
-		return;
-
-	rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource,
-			nf_nat_bysource_params);
+	if (ct->status & IPS_SRC_NAT_DONE)
+		rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource,
+				nf_nat_bysource_params);
 }
 
 static struct nf_ct_ext_type nat_extend __read_mostly = {
@@ -730,7 +711,6 @@ static struct nf_ct_ext_type nat_extend __read_mostly = {
 	.align		= __alignof__(struct nf_conn_nat),
 	.destroy	= nf_nat_cleanup_conntrack,
 	.id		= NF_CT_EXT_NAT,
-	.flags		= NF_CT_EXT_F_PREALLOC,
 };
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
@@ -751,7 +731,8 @@ static int nfnetlink_parse_nat_proto(struct nlattr *attr,
 	const struct nf_nat_l4proto *l4proto;
 	int err;
 
-	err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy);
+	err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr,
+			       protonat_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -780,7 +761,7 @@ nfnetlink_parse_nat(const struct nlattr *nat,
 
 	memset(range, 0, sizeof(*range));
 
-	err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy);
+	err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -819,7 +800,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
 
 	/* No NAT information has been passed, allocate the null-binding */
 	if (attr == NULL)
-		return __nf_nat_alloc_null_binding(ct, manip);
+		return __nf_nat_alloc_null_binding(ct, manip) == NF_DROP ? -ENOMEM : 0;
 
 	err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
 	if (err < 0)
@@ -874,9 +855,6 @@ static int __init nf_nat_init(void)
 
 	nf_ct_helper_expectfn_register(&follow_master_nat);
 
-	/* Initialize fake conntrack so that NAT will skip it */
-	nf_ct_untracked_status_or(IPS_NAT_DONE_MASK);
-
 	BUG_ON(nfnetlink_parse_nat_setup_hook != NULL);
 	RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook,
 			   nfnetlink_parse_nat_setup);
@@ -903,6 +881,8 @@ static void __exit nf_nat_cleanup(void)
 #ifdef CONFIG_XFRM
 	RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL);
 #endif
+	synchronize_rcu();
+
 	for (i = 0; i < NFPROTO_NUMPROTO; i++)
 		kfree(nf_nat_l4protos[i]);
 
diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c
index 211661cb2c90..607a373379b4 100644
--- a/net/netfilter/nf_nat_helper.c
+++ b/net/netfilter/nf_nat_helper.c
@@ -70,15 +70,15 @@ static void mangle_contents(struct sk_buff *skb,
 }
 
 /* Unusual, but possible case. */
-static int enlarge_skb(struct sk_buff *skb, unsigned int extra)
+static bool enlarge_skb(struct sk_buff *skb, unsigned int extra)
 {
 	if (skb->len + extra > 65535)
-		return 0;
+		return false;
 
 	if (pskb_expand_head(skb, 0, extra - skb_tailroom(skb), GFP_ATOMIC))
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 /* Generic function for mangling variable-length address changes inside
@@ -89,26 +89,26 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra)
  * skb enlargement, ...
  *
  * */
-int __nf_nat_mangle_tcp_packet(struct sk_buff *skb,
-			       struct nf_conn *ct,
-			       enum ip_conntrack_info ctinfo,
-			       unsigned int protoff,
-			       unsigned int match_offset,
-			       unsigned int match_len,
-			       const char *rep_buffer,
-			       unsigned int rep_len, bool adjust)
+bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo,
+				unsigned int protoff,
+				unsigned int match_offset,
+				unsigned int match_len,
+				const char *rep_buffer,
+				unsigned int rep_len, bool adjust)
 {
 	const struct nf_nat_l3proto *l3proto;
 	struct tcphdr *tcph;
 	int oldlen, datalen;
 
 	if (!skb_make_writable(skb, skb->len))
-		return 0;
+		return false;
 
 	if (rep_len > match_len &&
 	    rep_len - match_len > skb_tailroom(skb) &&
 	    !enlarge_skb(skb, rep_len - match_len))
-		return 0;
+		return false;
 
 	SKB_LINEAR_ASSERT(skb);
 
@@ -128,7 +128,7 @@ int __nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 		nf_ct_seqadj_set(ct, ctinfo, tcph->seq,
 				 (int)rep_len - (int)match_len);
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL(__nf_nat_mangle_tcp_packet);
 
@@ -142,7 +142,7 @@ EXPORT_SYMBOL(__nf_nat_mangle_tcp_packet);
  * XXX - This function could be merged with nf_nat_mangle_tcp_packet which
  *       should be fairly easy to do.
  */
-int
+bool
 nf_nat_mangle_udp_packet(struct sk_buff *skb,
 			 struct nf_conn *ct,
 			 enum ip_conntrack_info ctinfo,
@@ -157,12 +157,12 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb,
 	int datalen, oldlen;
 
 	if (!skb_make_writable(skb, skb->len))
-		return 0;
+		return false;
 
 	if (rep_len > match_len &&
 	    rep_len - match_len > skb_tailroom(skb) &&
 	    !enlarge_skb(skb, rep_len - match_len))
-		return 0;
+		return false;
 
 	udph = (void *)skb->data + protoff;
 
@@ -176,13 +176,13 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb,
 
 	/* fix udp checksum if udp checksum was previously calculated */
 	if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL)
-		return 1;
+		return true;
 
 	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
 	l3proto->csum_recalc(skb, IPPROTO_UDP, udph, &udph->check,
 			     datalen, oldlen);
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL(nf_nat_mangle_udp_packet);
 
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index 1fb2258c3535..0648cb096bd8 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -37,7 +37,6 @@ static unsigned int help(struct sk_buff *skb,
 	struct nf_conn *ct = exp->master;
 	union nf_inet_addr newaddr;
 	u_int16_t port;
-	unsigned int ret;
 
 	/* Reply comes from server. */
 	newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3;
@@ -83,14 +82,14 @@ static unsigned int help(struct sk_buff *skb,
 	pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n",
 		 buffer, &newaddr.ip, port);
 
-	ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
-				       matchlen, buffer, strlen(buffer));
-	if (ret != NF_ACCEPT) {
+	if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
+				      matchlen, buffer, strlen(buffer))) {
 		nf_ct_helper_log(skb, ct, "cannot mangle packet");
 		nf_ct_unexpect_related(exp);
+		return NF_DROP;
 	}
 
-	return ret;
+	return NF_ACCEPT;
 }
 
 static void __exit nf_nat_irc_fini(void)
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index 31d358691af0..804e8a0ab36e 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -33,8 +33,16 @@ sctp_manip_pkt(struct sk_buff *skb,
 	       enum nf_nat_manip_type maniptype)
 {
 	sctp_sctphdr_t *hdr;
+	int hdrsize = 8;
 
-	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+	/* This could be an inner header returned in imcp packet; in such
+	 * cases we cannot update the checksum field since it is outside
+	 * of the 8 bytes of transport layer headers we are guaranteed.
+	 */
+	if (skb->len >= hdroff + sizeof(*hdr))
+		hdrsize = sizeof(*hdr);
+
+	if (!skb_make_writable(skb, hdroff + hdrsize))
 		return false;
 
 	hdr = (struct sctphdr *)(skb->data + hdroff);
@@ -47,6 +55,9 @@ sctp_manip_pkt(struct sk_buff *skb,
 		hdr->dest = tuple->dst.u.sctp.port;
 	}
 
+	if (hdrsize < sizeof(*hdr))
+		return true;
+
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
 		hdr->checksum = sctp_compute_cksum(skb, hdroff);
 		skb->ip_summed = CHECKSUM_NONE;
diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c
index d43869879fcf..86067560a318 100644
--- a/net/netfilter/nf_nat_redirect.c
+++ b/net/netfilter/nf_nat_redirect.c
@@ -101,11 +101,13 @@ nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
 		rcu_read_lock();
 		idev = __in6_dev_get(skb->dev);
 		if (idev != NULL) {
+			read_lock_bh(&idev->lock);
 			list_for_each_entry(ifa, &idev->addr_list, if_list) {
 				newdst = ifa->addr;
 				addr = true;
 				break;
 			}
+			read_unlock_bh(&idev->lock);
 		}
 		rcu_read_unlock();
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 4a7662486f44..043850c9d154 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -96,15 +96,18 @@ void nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 }
 EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
 
-void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry)
+unsigned int nf_queue_nf_hook_drop(struct net *net)
 {
 	const struct nf_queue_handler *qh;
+	unsigned int count = 0;
 
 	rcu_read_lock();
 	qh = rcu_dereference(net->nf.queue_handler);
 	if (qh)
-		qh->nf_hook_drop(net, entry);
+		count = qh->nf_hook_drop(net);
 	rcu_read_unlock();
+
+	return count;
 }
 
 static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 7c6d1fbe38b9..a504e87c6ddf 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -66,8 +66,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff,
 			case TCPOPT_WINDOW:
 				if (opsize == TCPOLEN_WINDOW) {
 					opts->wscale = *ptr;
-					if (opts->wscale > 14)
-						opts->wscale = 14;
+					if (opts->wscale > TCP_MAX_WSCALE)
+						opts->wscale = TCP_MAX_WSCALE;
 					opts->options |= XT_SYNPROXY_OPT_WSCALE;
 				}
 				break;
@@ -287,9 +287,9 @@ static int synproxy_cpu_seq_show(struct seq_file *seq, void *v)
 	struct synproxy_stats *stats = v;
 
 	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq, "entries\t\tsyn_received\t"
-				"cookie_invalid\tcookie_valid\t"
-				"cookie_retrans\tconn_reopened\n");
+		seq_puts(seq, "entries\t\tsyn_received\t"
+			      "cookie_invalid\tcookie_valid\t"
+			      "cookie_retrans\tconn_reopened\n");
 		return 0;
 	}
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5e0ccfd5bb37..1c6482d2c4dc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -144,7 +144,7 @@ static int nf_tables_register_hooks(struct net *net,
 				    unsigned int hook_nops)
 {
 	if (table->flags & NFT_TABLE_F_DORMANT ||
-	    !(chain->flags & NFT_BASE_CHAIN))
+	    !nft_is_base_chain(chain))
 		return 0;
 
 	return nf_register_net_hooks(net, nft_base_chain(chain)->ops,
@@ -157,7 +157,7 @@ static void nf_tables_unregister_hooks(struct net *net,
 				       unsigned int hook_nops)
 {
 	if (table->flags & NFT_TABLE_F_DORMANT ||
-	    !(chain->flags & NFT_BASE_CHAIN))
+	    !nft_is_base_chain(chain))
 		return;
 
 	nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, hook_nops);
@@ -438,7 +438,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 
-	event |= NFNL_SUBSYS_NFTABLES << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
 	if (nlh == NULL)
 		goto nla_put_failure;
@@ -587,7 +587,7 @@ static void _nf_tables_table_disable(struct net *net,
 	list_for_each_entry(chain, &table->chains, list) {
 		if (!nft_is_active_next(net, chain))
 			continue;
-		if (!(chain->flags & NFT_BASE_CHAIN))
+		if (!nft_is_base_chain(chain))
 			continue;
 
 		if (cnt && i++ == cnt)
@@ -608,7 +608,7 @@ static int nf_tables_table_enable(struct net *net,
 	list_for_each_entry(chain, &table->chains, list) {
 		if (!nft_is_active_next(net, chain))
 			continue;
-		if (!(chain->flags & NFT_BASE_CHAIN))
+		if (!nft_is_base_chain(chain))
 			continue;
 
 		err = nf_register_net_hooks(net, nft_base_chain(chain)->ops,
@@ -989,7 +989,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 
-	event |= NFNL_SUBSYS_NFTABLES << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
 	if (nlh == NULL)
 		goto nla_put_failure;
@@ -1007,7 +1007,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_string(skb, NFTA_CHAIN_NAME, chain->name))
 		goto nla_put_failure;
 
-	if (chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(chain)) {
 		const struct nft_base_chain *basechain = nft_base_chain(chain);
 		const struct nf_hook_ops *ops = &basechain->ops[0];
 		struct nlattr *nest;
@@ -1182,7 +1182,8 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
 	struct nft_stats *stats;
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy);
+	err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy,
+			       NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 
@@ -1226,7 +1227,7 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
 {
 	BUG_ON(chain->use > 0);
 
-	if (chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(chain)) {
 		struct nft_base_chain *basechain = nft_base_chain(chain);
 
 		module_put(basechain->type->owner);
@@ -1257,7 +1258,7 @@ static int nft_chain_parse_hook(struct net *net,
 	int err;
 
 	err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
-			       nft_hook_policy);
+			       nft_hook_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1364,8 +1365,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 	}
 
 	if (nla[NFTA_CHAIN_POLICY]) {
-		if ((chain != NULL &&
-		    !(chain->flags & NFT_BASE_CHAIN)))
+		if (chain != NULL &&
+		    !nft_is_base_chain(chain))
 			return -EOPNOTSUPP;
 
 		if (chain == NULL &&
@@ -1396,7 +1397,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 			struct nft_chain_hook hook;
 			struct nf_hook_ops *ops;
 
-			if (!(chain->flags & NFT_BASE_CHAIN))
+			if (!nft_is_base_chain(chain))
 				return -EBUSY;
 
 			err = nft_chain_parse_hook(net, nla, afi, &hook,
@@ -1433,7 +1434,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 		}
 
 		if (nla[NFTA_CHAIN_COUNTERS]) {
-			if (!(chain->flags & NFT_BASE_CHAIN))
+			if (!nft_is_base_chain(chain))
 				return -EOPNOTSUPP;
 
 			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
@@ -1724,7 +1725,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_EXPR_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_EXPR_MAX, nla, nft_expr_policy);
+	err = nla_parse_nested(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1734,7 +1735,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 
 	if (tb[NFTA_EXPR_DATA]) {
 		err = nla_parse_nested(info->tb, type->maxattr,
-				       tb[NFTA_EXPR_DATA], type->policy);
+				       tb[NFTA_EXPR_DATA], type->policy, NULL);
 		if (err < 0)
 			goto err1;
 	} else
@@ -1772,8 +1773,19 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx,
 			goto err1;
 	}
 
+	if (ops->validate) {
+		const struct nft_data *data = NULL;
+
+		err = ops->validate(ctx, expr, &data);
+		if (err < 0)
+			goto err2;
+	}
+
 	return 0;
 
+err2:
+	if (ops->destroy)
+		ops->destroy(ctx, expr);
 err1:
 	expr->ops = NULL;
 	return err;
@@ -1874,10 +1886,9 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 	const struct nft_expr *expr, *next;
 	struct nlattr *list;
 	const struct nft_rule *prule;
-	int type = event | NFNL_SUBSYS_NFTABLES << 8;
+	u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 
-	nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg),
-			flags);
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags);
 	if (nlh == NULL)
 		goto nla_put_failure;
 
@@ -1895,7 +1906,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	if ((event != NFT_MSG_DELRULE) && (rule->list.prev != &chain->rules)) {
-		prule = list_entry(rule->list.prev, struct nft_rule, list);
+		prule = list_prev_entry(rule, list);
 		if (nla_put_be64(skb, NFTA_RULE_POSITION,
 				 cpu_to_be64(prule->handle),
 				 NFTA_RULE_PAD))
@@ -2523,8 +2534,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
 	return 0;
 }
 
-struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
-				     const struct nlattr *nla, u8 genmask)
+static struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
+					    const struct nlattr *nla, u8 genmask)
 {
 	struct nft_set *set;
 
@@ -2538,11 +2549,10 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
 	}
 	return ERR_PTR(-ENOENT);
 }
-EXPORT_SYMBOL_GPL(nf_tables_set_lookup);
 
-struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
-					  const struct nlattr *nla,
-					  u8 genmask)
+static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
+						 const struct nlattr *nla,
+						 u8 genmask)
 {
 	struct nft_trans *trans;
 	u32 id = ntohl(nla_get_be32(nla));
@@ -2557,7 +2567,25 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
 	}
 	return ERR_PTR(-ENOENT);
 }
-EXPORT_SYMBOL_GPL(nf_tables_set_lookup_byid);
+
+struct nft_set *nft_set_lookup(const struct net *net,
+			       const struct nft_table *table,
+			       const struct nlattr *nla_set_name,
+			       const struct nlattr *nla_set_id,
+			       u8 genmask)
+{
+	struct nft_set *set;
+
+	set = nf_tables_set_lookup(table, nla_set_name, genmask);
+	if (IS_ERR(set)) {
+		if (!nla_set_id)
+			return set;
+
+		set = nf_tables_set_lookup_byid(net, nla_set_id, genmask);
+	}
+	return set;
+}
+EXPORT_SYMBOL_GPL(nft_set_lookup);
 
 static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 				    const char *name)
@@ -2617,7 +2645,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	u32 portid = ctx->portid;
 	u32 seq = ctx->seq;
 
-	event |= NFNL_SUBSYS_NFTABLES << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
 			flags);
 	if (nlh == NULL)
@@ -2851,7 +2879,8 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
 	struct nlattr *da[NFTA_SET_DESC_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(da, NFTA_SET_DESC_MAX, nla, nft_set_desc_policy);
+	err = nla_parse_nested(da, NFTA_SET_DESC_MAX, nla,
+			       nft_set_desc_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -3145,7 +3174,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		iter.count	= 0;
 		iter.err	= 0;
 		iter.fn		= nf_tables_bind_check_setelem;
-		iter.flush	= false;
 
 		set->ops->walk(ctx, set, &iter);
 		if (iter.err < 0)
@@ -3354,7 +3382,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	int event, err;
 
 	err = nlmsg_parse(cb->nlh, sizeof(struct nfgenmsg), nla,
-			  NFTA_SET_ELEM_LIST_MAX, nft_set_elem_list_policy);
+			  NFTA_SET_ELEM_LIST_MAX, nft_set_elem_list_policy,
+			  NULL);
 	if (err < 0)
 		return err;
 
@@ -3368,8 +3397,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
-	event  = NFT_MSG_NEWSETELEM;
-	event |= NFNL_SUBSYS_NFTABLES << 8;
+	event  = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWSETELEM);
 	portid = NETLINK_CB(cb->skb).portid;
 	seq    = cb->nlh->nlmsg_seq;
 
@@ -3399,7 +3427,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	args.iter.count		= 0;
 	args.iter.err		= 0;
 	args.iter.fn		= nf_tables_dump_setelem;
-	args.iter.flush		= false;
 	set->ops->walk(&ctx, set, &args.iter);
 
 	nla_nest_end(skb, nest);
@@ -3455,7 +3482,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 	struct nlattr *nest;
 	int err;
 
-	event |= NFNL_SUBSYS_NFTABLES << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
 			flags);
 	if (nlh == NULL)
@@ -3614,7 +3641,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	int err;
 
 	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
-			       nft_set_elem_policy);
+			       nft_set_elem_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -3844,7 +3871,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	int err;
 
 	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
-			       nft_set_elem_policy);
+			       nft_set_elem_policy, NULL);
 	if (err < 0)
 		goto err1;
 
@@ -3963,7 +3990,6 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
 		struct nft_set_iter iter = {
 			.genmask	= genmask,
 			.fn		= nft_flush_set,
-			.flush		= true,
 		};
 		set->ops->walk(&ctx, set, &iter);
 
@@ -4067,7 +4093,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 };
 
-static struct nft_object *nft_obj_init(const struct nft_object_type *type,
+static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
+				       const struct nft_object_type *type,
 				       const struct nlattr *attr)
 {
 	struct nlattr *tb[type->maxattr + 1];
@@ -4075,7 +4102,8 @@ static struct nft_object *nft_obj_init(const struct nft_object_type *type,
 	int err;
 
 	if (attr) {
-		err = nla_parse_nested(tb, type->maxattr, attr, type->policy);
+		err = nla_parse_nested(tb, type->maxattr, attr, type->policy,
+				       NULL);
 		if (err < 0)
 			goto err1;
 	} else {
@@ -4087,7 +4115,7 @@ static struct nft_object *nft_obj_init(const struct nft_object_type *type,
 	if (obj == NULL)
 		goto err1;
 
-	err = type->init((const struct nlattr * const *)tb, obj);
+	err = type->init(ctx, (const struct nlattr * const *)tb, obj);
 	if (err < 0)
 		goto err2;
 
@@ -4195,7 +4223,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
-	obj = nft_obj_init(type, nla[NFTA_OBJ_DATA]);
+	obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto err1;
@@ -4227,7 +4255,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 	struct nfgenmsg *nfmsg;
 	struct nlmsghdr *nlh;
 
-	event |= NFNL_SUBSYS_NFTABLES << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
 	if (nlh == NULL)
 		goto nla_put_failure;
@@ -4409,8 +4437,6 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 err:
 	kfree_skb(skb2);
 	return err;
-
-	return 0;
 }
 
 static void nft_obj_destroy(struct nft_object *obj)
@@ -4500,7 +4526,7 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
-	int event = (NFNL_SUBSYS_NFTABLES << 8) | NFT_MSG_NEWGEN;
+	int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN);
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0);
 	if (nlh == NULL)
@@ -4682,7 +4708,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
 	if (nft_trans_chain_name(trans)[0])
 		strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
 
-	if (!(trans->ctx.chain->flags & NFT_BASE_CHAIN))
+	if (!nft_is_base_chain(trans->ctx.chain))
 		return;
 
 	basechain = nft_base_chain(trans->ctx.chain);
@@ -4996,7 +5022,7 @@ int nft_chain_validate_dependency(const struct nft_chain *chain,
 {
 	const struct nft_base_chain *basechain;
 
-	if (chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(chain)) {
 		basechain = nft_base_chain(chain);
 		if (basechain->type->type != type)
 			return -EOPNOTSUPP;
@@ -5010,7 +5036,7 @@ int nft_chain_validate_hooks(const struct nft_chain *chain,
 {
 	struct nft_base_chain *basechain;
 
-	if (chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(chain)) {
 		basechain = nft_base_chain(chain);
 
 		if ((1 << basechain->ops[0].hooknum) & hook_flags)
@@ -5114,7 +5140,6 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 			iter.count	= 0;
 			iter.err	= 0;
 			iter.fn		= nf_tables_loop_check_setelem;
-			iter.flush	= false;
 
 			set->ops->walk(ctx, set, &iter);
 			if (iter.err < 0)
@@ -5289,7 +5314,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	struct nft_chain *chain;
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy);
+	err = nla_parse_nested(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
@@ -5320,7 +5346,7 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 					       tb[NFTA_VERDICT_CHAIN], genmask);
 		if (IS_ERR(chain))
 			return PTR_ERR(chain);
-		if (chain->flags & NFT_BASE_CHAIN)
+		if (nft_is_base_chain(chain))
 			return -EOPNOTSUPP;
 
 		chain->use++;
@@ -5419,7 +5445,7 @@ int nft_data_init(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_DATA_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_DATA_MAX, nla, nft_data_policy);
+	err = nla_parse_nested(tb, NFTA_DATA_MAX, nla, nft_data_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -5493,7 +5519,7 @@ int __nft_release_basechain(struct nft_ctx *ctx)
 {
 	struct nft_rule *rule, *nr;
 
-	BUG_ON(!(ctx->chain->flags & NFT_BASE_CHAIN));
+	BUG_ON(!nft_is_base_chain(ctx->chain));
 
 	nf_tables_unregister_hooks(ctx->net, ctx->chain->table, ctx->chain,
 				   ctx->afi->nops);
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index 9e2ae424b640..403432988313 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -128,7 +128,7 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 		list_for_each_entry(table, &afi->tables, list) {
 			ctx.table = table;
 			list_for_each_entry_safe(chain, nr, &table->chains, list) {
-				if (!(chain->flags & NFT_BASE_CHAIN))
+				if (!nft_is_base_chain(chain))
 					continue;
 
 				ctx.chain = chain;
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index 12eb9041dca2..e1b15e7a5793 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -169,7 +169,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
 	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
 	unsigned int size;
-	int event = (NFNL_SUBSYS_NFTABLES << 8) | NFT_MSG_TRACE;
+	u16 event;
 
 	if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE))
 		return;
@@ -198,6 +198,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
 	if (!skb)
 		return;
 
+	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_TRACE);
 	nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct nfgenmsg), 0);
 	if (!nlh)
 		goto nla_put_failure;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 68eda920160e..80f5ecf2c3d7 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -148,7 +148,8 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
 EXPORT_SYMBOL_GPL(nfnetlink_unicast);
 
 /* Process one complete nfnetlink message. */
-static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct nfnl_callback *nc;
@@ -191,8 +192,8 @@ replay:
 		int attrlen = nlh->nlmsg_len - min_len;
 		__u8 subsys_id = NFNL_SUBSYS_ID(type);
 
-		err = nla_parse(cda, ss->cb[cb_id].attr_count,
-				attr, attrlen, ss->cb[cb_id].policy);
+		err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen,
+				ss->cb[cb_id].policy, extack);
 		if (err < 0) {
 			rcu_read_unlock();
 			return err;
@@ -261,7 +262,7 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb)
 	struct nfnl_err *nfnl_err, *next;
 
 	list_for_each_entry_safe(nfnl_err, next, err_list, head) {
-		netlink_ack(skb, nfnl_err->nlh, nfnl_err->err);
+		netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, NULL);
 		nfnl_err_del(nfnl_err);
 	}
 }
@@ -284,13 +285,13 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 
 	if (subsys_id >= NFNL_SUBSYS_COUNT)
-		return netlink_ack(skb, nlh, -EINVAL);
+		return netlink_ack(skb, nlh, -EINVAL, NULL);
 replay:
 	status = 0;
 
 	skb = netlink_skb_clone(oskb, GFP_KERNEL);
 	if (!skb)
-		return netlink_ack(oskb, nlh, -ENOMEM);
+		return netlink_ack(oskb, nlh, -ENOMEM, NULL);
 
 	nfnl_lock(subsys_id);
 	ss = nfnl_dereference_protected(subsys_id);
@@ -304,20 +305,20 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			netlink_ack(oskb, nlh, -EOPNOTSUPP);
+			netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
 			return kfree_skb(skb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		netlink_ack(oskb, nlh, -EOPNOTSUPP);
+		netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
 		return kfree_skb(skb);
 	}
 
 	if (genid && ss->valid_genid && !ss->valid_genid(net, genid)) {
 		nfnl_unlock(subsys_id);
-		netlink_ack(oskb, nlh, -ERESTART);
+		netlink_ack(oskb, nlh, -ERESTART, NULL);
 		return kfree_skb(skb);
 	}
 
@@ -376,8 +377,8 @@ replay:
 			struct nlattr *attr = (void *)nlh + min_len;
 			int attrlen = nlh->nlmsg_len - min_len;
 
-			err = nla_parse(cda, ss->cb[cb_id].attr_count,
-					attr, attrlen, ss->cb[cb_id].policy);
+			err = nla_parse(cda, ss->cb[cb_id].attr_count, attr,
+					attrlen, ss->cb[cb_id].policy, NULL);
 			if (err < 0)
 				goto ack;
 
@@ -407,7 +408,8 @@ ack:
 				 * pointing to the batch header.
 				 */
 				nfnl_err_reset(&err_list);
-				netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM);
+				netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM,
+					    NULL);
 				status |= NFNL_BATCH_FAILURE;
 				goto done;
 			}
@@ -465,9 +467,10 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh)
 	    skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg))
 		return;
 
-	err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy);
+	err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy,
+			NULL);
 	if (err < 0) {
-		netlink_ack(skb, nlh, err);
+		netlink_ack(skb, nlh, err, NULL);
 		return;
 	}
 	if (cda[NFNL_BATCH_GENID])
@@ -493,14 +496,14 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 		return;
 
 	if (!netlink_net_capable(skb, CAP_NET_ADMIN)) {
-		netlink_ack(skb, nlh, -EPERM);
+		netlink_ack(skb, nlh, -EPERM, NULL);
 		return;
 	}
 
 	if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN)
 		nfnetlink_rcv_skb_batch(skb, nlh);
 	else
-		netlink_rcv_skb(skb, &nfnetlink_rcv_msg);
+		netlink_rcv_skb(skb, nfnetlink_rcv_msg);
 }
 
 #ifdef CONFIG_MODULES
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index d44d89b56127..9898fb4d0512 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/slab.h>
@@ -32,7 +33,7 @@ struct nf_acct {
 	atomic64_t		bytes;
 	unsigned long		flags;
 	struct list_head	head;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	char			name[NFACCT_NAME_MAX];
 	struct rcu_head		rcu_head;
 	char			data[0];
@@ -123,7 +124,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 		atomic64_set(&nfacct->pkts,
 			     be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS])));
 	}
-	atomic_set(&nfacct->refcnt, 1);
+	refcount_set(&nfacct->refcnt, 1);
 	list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list);
 	return 0;
 }
@@ -138,7 +139,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	u64 pkts, bytes;
 	u32 old_flags;
 
-	event |= NFNL_SUBSYS_ACCT << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_ACCT, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -166,7 +167,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 			 NFACCT_PAD) ||
 	    nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes),
 			 NFACCT_PAD) ||
-	    nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt))))
+	    nla_put_be32(skb, NFACCT_USE, htonl(refcount_read(&acct->refcnt))))
 		goto nla_put_failure;
 	if (acct->flags & NFACCT_F_QUOTA) {
 		u64 *quota = (u64 *)acct->data;
@@ -243,7 +244,8 @@ nfacct_filter_alloc(const struct nlattr * const attr)
 	struct nlattr *tb[NFACCT_FILTER_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFACCT_FILTER_MAX, attr, filter_policy);
+	err = nla_parse_nested(tb, NFACCT_FILTER_MAX, attr, filter_policy,
+			       NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 
@@ -329,7 +331,7 @@ static int nfnl_acct_try_del(struct nf_acct *cur)
 	/* We want to avoid races with nfnl_acct_put. So only when the current
 	 * refcnt is 1, we decrease it to 0.
 	 */
-	if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) {
+	if (refcount_dec_if_one(&cur->refcnt)) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&cur->head);
 		kfree_rcu(cur, rcu_head);
@@ -413,7 +415,7 @@ struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name)
 		if (!try_module_get(THIS_MODULE))
 			goto err;
 
-		if (!atomic_inc_not_zero(&cur->refcnt)) {
+		if (!refcount_inc_not_zero(&cur->refcnt)) {
 			module_put(THIS_MODULE);
 			goto err;
 		}
@@ -429,7 +431,7 @@ EXPORT_SYMBOL_GPL(nfnl_acct_find_get);
 
 void nfnl_acct_put(struct nf_acct *acct)
 {
-	if (atomic_dec_and_test(&acct->refcnt))
+	if (refcount_dec_and_test(&acct->refcnt))
 		kfree_rcu(acct, rcu_head);
 
 	module_put(THIS_MODULE);
@@ -502,7 +504,7 @@ static void __net_exit nfnl_acct_net_exit(struct net *net)
 	list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) {
 		list_del_rcu(&cur->head);
 
-		if (atomic_dec_and_test(&cur->refcnt))
+		if (refcount_dec_and_test(&cur->refcnt))
 			kfree_rcu(cur, rcu_head);
 	}
 }
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index de8782345c86..950bf6eadc65 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -32,6 +32,13 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
 MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
 
+struct nfnl_cthelper {
+	struct list_head		list;
+	struct nf_conntrack_helper	helper;
+};
+
+static LIST_HEAD(nfnl_cthelper_list);
+
 static int
 nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
 			struct nf_conn *ct, enum ip_conntrack_info ctinfo)
@@ -70,7 +77,8 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	int err;
 	struct nlattr *tb[NFCTH_TUPLE_MAX+1];
 
-	err = nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr, nfnl_cthelper_tuple_pol);
+	err = nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr,
+			       nfnl_cthelper_tuple_pol, NULL);
 	if (err < 0)
 		return err;
 
@@ -97,7 +105,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	memcpy(help->data, nla_data(attr), help->helper->data_len);
+	nla_memcpy(help->data, nla_data(attr), sizeof(help->data));
 	return 0;
 }
 
@@ -130,7 +138,8 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 	int err;
 	struct nlattr *tb[NFCTH_POLICY_MAX+1];
 
-	err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, nfnl_cthelper_expect_pol);
+	err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
+			       nfnl_cthelper_expect_pol, NULL);
 	if (err < 0)
 		return err;
 
@@ -143,6 +152,9 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 		nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN);
 	expect_policy->max_expected =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+	if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
+		return -EINVAL;
+
 	expect_policy->timeout =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
 
@@ -161,28 +173,28 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
 	int i, ret;
 	struct nf_conntrack_expect_policy *expect_policy;
 	struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
+	unsigned int class_max;
 
 	ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
-			       nfnl_cthelper_expect_policy_set);
+			       nfnl_cthelper_expect_policy_set, NULL);
 	if (ret < 0)
 		return ret;
 
 	if (!tb[NFCTH_POLICY_SET_NUM])
 		return -EINVAL;
 
-	helper->expect_class_max =
-		ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
-
-	if (helper->expect_class_max != 0 &&
-	    helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES)
+	class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+	if (class_max == 0)
+		return -EINVAL;
+	if (class_max > NF_CT_MAX_EXPECT_CLASSES)
 		return -EOVERFLOW;
 
 	expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) *
-				helper->expect_class_max, GFP_KERNEL);
+				class_max, GFP_KERNEL);
 	if (expect_policy == NULL)
 		return -ENOMEM;
 
-	for (i=0; i<helper->expect_class_max; i++) {
+	for (i = 0; i < class_max; i++) {
 		if (!tb[NFCTH_POLICY_SET+i])
 			goto err;
 
@@ -191,6 +203,8 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
 		if (ret < 0)
 			goto err;
 	}
+
+	helper->expect_class_max = class_max - 1;
 	helper->expect_policy = expect_policy;
 	return 0;
 err:
@@ -203,21 +217,29 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 		     struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_helper *helper;
+	struct nfnl_cthelper *nfcth;
+	unsigned int size;
 	int ret;
 
 	if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
 		return -EINVAL;
 
-	helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL);
-	if (helper == NULL)
+	nfcth = kzalloc(sizeof(*nfcth), GFP_KERNEL);
+	if (nfcth == NULL)
 		return -ENOMEM;
+	helper = &nfcth->helper;
 
 	ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
 	if (ret < 0)
-		goto err;
+		goto err1;
 
 	strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
-	helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
+	size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
+	if (size > FIELD_SIZEOF(struct nf_conn_help, data)) {
+		ret = -ENOMEM;
+		goto err2;
+	}
+
 	helper->flags |= NF_CT_HELPER_F_USERSPACE;
 	memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple));
 
@@ -245,15 +267,104 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 
 	ret = nf_conntrack_helper_register(helper);
 	if (ret < 0)
-		goto err;
+		goto err2;
 
+	list_add_tail(&nfcth->list, &nfnl_cthelper_list);
 	return 0;
-err:
-	kfree(helper);
+err2:
+	kfree(helper->expect_policy);
+err1:
+	kfree(nfcth);
 	return ret;
 }
 
 static int
+nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
+				struct nf_conntrack_expect_policy *new_policy,
+				const struct nlattr *attr)
+{
+	struct nlattr *tb[NFCTH_POLICY_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
+			       nfnl_cthelper_expect_pol, NULL);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFCTH_POLICY_NAME] ||
+	    !tb[NFCTH_POLICY_EXPECT_MAX] ||
+	    !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
+		return -EINVAL;
+
+	if (nla_strcmp(tb[NFCTH_POLICY_NAME], policy->name))
+		return -EBUSY;
+
+	new_policy->max_expected =
+		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+	if (new_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
+		return -EINVAL;
+
+	new_policy->timeout =
+		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
+
+	return 0;
+}
+
+static int nfnl_cthelper_update_policy_all(struct nlattr *tb[],
+					   struct nf_conntrack_helper *helper)
+{
+	struct nf_conntrack_expect_policy new_policy[helper->expect_class_max + 1];
+	struct nf_conntrack_expect_policy *policy;
+	int i, err;
+
+	/* Check first that all policy attributes are well-formed, so we don't
+	 * leave things in inconsistent state on errors.
+	 */
+	for (i = 0; i < helper->expect_class_max + 1; i++) {
+
+		if (!tb[NFCTH_POLICY_SET + i])
+			return -EINVAL;
+
+		err = nfnl_cthelper_update_policy_one(&helper->expect_policy[i],
+						      &new_policy[i],
+						      tb[NFCTH_POLICY_SET + i]);
+		if (err < 0)
+			return err;
+	}
+	/* Now we can safely update them. */
+	for (i = 0; i < helper->expect_class_max + 1; i++) {
+		policy = (struct nf_conntrack_expect_policy *)
+				&helper->expect_policy[i];
+		policy->max_expected = new_policy->max_expected;
+		policy->timeout	= new_policy->timeout;
+	}
+
+	return 0;
+}
+
+static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper,
+				       const struct nlattr *attr)
+{
+	struct nlattr *tb[NFCTH_POLICY_SET_MAX + 1];
+	unsigned int class_max;
+	int err;
+
+	err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
+			       nfnl_cthelper_expect_policy_set, NULL);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFCTH_POLICY_SET_NUM])
+		return -EINVAL;
+
+	class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+	if (helper->expect_class_max + 1 != class_max)
+		return -EBUSY;
+
+	return nfnl_cthelper_update_policy_all(tb, helper);
+}
+
+static int
 nfnl_cthelper_update(const struct nlattr * const tb[],
 		     struct nf_conntrack_helper *helper)
 {
@@ -263,8 +374,7 @@ nfnl_cthelper_update(const struct nlattr * const tb[],
 		return -EBUSY;
 
 	if (tb[NFCTH_POLICY]) {
-		ret = nfnl_cthelper_parse_expect_policy(helper,
-							tb[NFCTH_POLICY]);
+		ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);
 		if (ret < 0)
 			return ret;
 	}
@@ -293,7 +403,8 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl,
 	const char *helper_name;
 	struct nf_conntrack_helper *cur, *helper = NULL;
 	struct nf_conntrack_tuple tuple;
-	int ret = 0, i;
+	struct nfnl_cthelper *nlcth;
+	int ret = 0;
 
 	if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
 		return -EINVAL;
@@ -304,31 +415,22 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl,
 	if (ret < 0)
 		return ret;
 
-	rcu_read_lock();
-	for (i = 0; i < nf_ct_helper_hsize && !helper; i++) {
-		hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+	list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
 
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
+		if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+			continue;
 
-			if (strncmp(cur->name, helper_name,
-					NF_CT_HELPER_NAME_LEN) != 0)
-				continue;
+		if ((tuple.src.l3num != cur->tuple.src.l3num ||
+		     tuple.dst.protonum != cur->tuple.dst.protonum))
+			continue;
 
-			if ((tuple.src.l3num != cur->tuple.src.l3num ||
-			     tuple.dst.protonum != cur->tuple.dst.protonum))
-				continue;
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
 
-			if (nlh->nlmsg_flags & NLM_F_EXCL) {
-				ret = -EEXIST;
-				goto err;
-			}
-			helper = cur;
-			break;
-		}
+		helper = cur;
+		break;
 	}
-	rcu_read_unlock();
 
 	if (helper == NULL)
 		ret = nfnl_cthelper_create(tb, &tuple);
@@ -336,9 +438,6 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl,
 		ret = nfnl_cthelper_update(tb, helper);
 
 	return ret;
-err:
-	rcu_read_unlock();
-	return ret;
 }
 
 static int
@@ -377,10 +476,10 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM,
-			 htonl(helper->expect_class_max)))
+			 htonl(helper->expect_class_max + 1)))
 		goto nla_put_failure;
 
-	for (i=0; i<helper->expect_class_max; i++) {
+	for (i = 0; i < helper->expect_class_max + 1; i++) {
 		nest_parms2 = nla_nest_start(skb,
 				(NFCTH_POLICY_SET+i) | NLA_F_NESTED);
 		if (nest_parms2 == NULL)
@@ -416,7 +515,7 @@ nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
 	int status;
 
-	event |= NFNL_SUBSYS_CTHELPER << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_CTHELPER, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -502,11 +601,12 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl,
 			     struct sk_buff *skb, const struct nlmsghdr *nlh,
 			     const struct nlattr * const tb[])
 {
-	int ret = -ENOENT, i;
+	int ret = -ENOENT;
 	struct nf_conntrack_helper *cur;
 	struct sk_buff *skb2;
 	char *helper_name = NULL;
 	struct nf_conntrack_tuple tuple;
+	struct nfnl_cthelper *nlcth;
 	bool tuple_set = false;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
@@ -527,45 +627,39 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl,
 		tuple_set = true;
 	}
 
-	for (i = 0; i < nf_ct_helper_hsize; i++) {
-		hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+	list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
+		if (helper_name &&
+		    strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+			continue;
 
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
+		if (tuple_set &&
+		    (tuple.src.l3num != cur->tuple.src.l3num ||
+		     tuple.dst.protonum != cur->tuple.dst.protonum))
+			continue;
 
-			if (helper_name && strncmp(cur->name, helper_name,
-						NF_CT_HELPER_NAME_LEN) != 0) {
-				continue;
-			}
-			if (tuple_set &&
-			    (tuple.src.l3num != cur->tuple.src.l3num ||
-			     tuple.dst.protonum != cur->tuple.dst.protonum))
-				continue;
-
-			skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-			if (skb2 == NULL) {
-				ret = -ENOMEM;
-				break;
-			}
+		skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+		if (skb2 == NULL) {
+			ret = -ENOMEM;
+			break;
+		}
 
-			ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
-						nlh->nlmsg_seq,
-						NFNL_MSG_TYPE(nlh->nlmsg_type),
-						NFNL_MSG_CTHELPER_NEW, cur);
-			if (ret <= 0) {
-				kfree_skb(skb2);
-				break;
-			}
+		ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
+					      nlh->nlmsg_seq,
+					      NFNL_MSG_TYPE(nlh->nlmsg_type),
+					      NFNL_MSG_CTHELPER_NEW, cur);
+		if (ret <= 0) {
+			kfree_skb(skb2);
+			break;
+		}
 
-			ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
-						MSG_DONTWAIT);
-			if (ret > 0)
-				ret = 0;
+		ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
+				      MSG_DONTWAIT);
+		if (ret > 0)
+			ret = 0;
 
-			/* this avoids a loop in nfnetlink. */
-			return ret == -EAGAIN ? -ENOBUFS : ret;
-		}
+		/* this avoids a loop in nfnetlink. */
+		return ret == -EAGAIN ? -ENOBUFS : ret;
 	}
 	return ret;
 }
@@ -576,10 +670,10 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl,
 {
 	char *helper_name = NULL;
 	struct nf_conntrack_helper *cur;
-	struct hlist_node *tmp;
 	struct nf_conntrack_tuple tuple;
 	bool tuple_set = false, found = false;
-	int i, j = 0, ret;
+	struct nfnl_cthelper *nlcth, *n;
+	int j = 0, ret;
 
 	if (tb[NFCTH_NAME])
 		helper_name = nla_data(tb[NFCTH_NAME]);
@@ -592,28 +686,27 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl,
 		tuple_set = true;
 	}
 
-	for (i = 0; i < nf_ct_helper_hsize; i++) {
-		hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
-								hnode) {
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
+	list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
+		j++;
 
-			j++;
+		if (helper_name &&
+		    strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+			continue;
 
-			if (helper_name && strncmp(cur->name, helper_name,
-						NF_CT_HELPER_NAME_LEN) != 0) {
-				continue;
-			}
-			if (tuple_set &&
-			    (tuple.src.l3num != cur->tuple.src.l3num ||
-			     tuple.dst.protonum != cur->tuple.dst.protonum))
-				continue;
+		if (tuple_set &&
+		    (tuple.src.l3num != cur->tuple.src.l3num ||
+		     tuple.dst.protonum != cur->tuple.dst.protonum))
+			continue;
 
-			found = true;
-			nf_conntrack_helper_unregister(cur);
-		}
+		found = true;
+		nf_conntrack_helper_unregister(cur);
+		kfree(cur->expect_policy);
+
+		list_del(&nlcth->list);
+		kfree(nlcth);
 	}
+
 	/* Make sure we return success if we flush and there is no helpers */
 	return (found || j == 0) ? 0 : -ENOENT;
 }
@@ -662,20 +755,16 @@ err_out:
 static void __exit nfnl_cthelper_exit(void)
 {
 	struct nf_conntrack_helper *cur;
-	struct hlist_node *tmp;
-	int i;
+	struct nfnl_cthelper *nlcth, *n;
 
 	nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
 
-	for (i=0; i<nf_ct_helper_hsize; i++) {
-		hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
-									hnode) {
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
+	list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
 
-			nf_conntrack_helper_unregister(cur);
-		}
+		nf_conntrack_helper_unregister(cur);
+		kfree(cur->expect_policy);
+		kfree(nlcth);
 	}
 }
 
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 139e0867e56e..a3e7bb54d96a 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -56,7 +56,8 @@ ctnl_timeout_parse_policy(void *timeouts, struct nf_conntrack_l4proto *l4proto,
 		struct nlattr *tb[l4proto->ctnl_timeout.nlattr_max+1];
 
 		ret = nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max,
-				       attr, l4proto->ctnl_timeout.nla_policy);
+				       attr, l4proto->ctnl_timeout.nla_policy,
+				       NULL);
 		if (ret < 0)
 			return ret;
 
@@ -138,7 +139,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl,
 	strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
 	timeout->l3num = l3num;
 	timeout->l4proto = l4proto;
-	atomic_set(&timeout->refcnt, 1);
+	refcount_set(&timeout->refcnt, 1);
 	list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list);
 
 	return 0;
@@ -158,7 +159,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
 	struct nf_conntrack_l4proto *l4proto = timeout->l4proto;
 
-	event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -172,7 +173,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	    nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) ||
 	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) ||
 	    nla_put_be32(skb, CTA_TIMEOUT_USE,
-			 htonl(atomic_read(&timeout->refcnt))))
+			 htonl(refcount_read(&timeout->refcnt))))
 		goto nla_put_failure;
 
 	if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
@@ -339,7 +340,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
 	/* We want to avoid races with ctnl_timeout_put. So only when the
 	 * current refcnt is 1, we decrease it to 0.
 	 */
-	if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) {
+	if (refcount_dec_if_one(&timeout->refcnt)) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&timeout->head);
 		nf_ct_l4proto_put(timeout->l4proto);
@@ -431,7 +432,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
 
-	event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
@@ -536,7 +537,7 @@ ctnl_timeout_find_get(struct net *net, const char *name)
 		if (!try_module_get(THIS_MODULE))
 			goto err;
 
-		if (!atomic_inc_not_zero(&timeout->refcnt)) {
+		if (!refcount_inc_not_zero(&timeout->refcnt)) {
 			module_put(THIS_MODULE);
 			goto err;
 		}
@@ -550,7 +551,7 @@ err:
 
 static void ctnl_timeout_put(struct ctnl_timeout *timeout)
 {
-	if (atomic_dec_and_test(&timeout->refcnt))
+	if (refcount_dec_and_test(&timeout->refcnt))
 		kfree_rcu(timeout, rcu_head);
 
 	module_put(THIS_MODULE);
@@ -601,7 +602,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 		list_del_rcu(&cur->head);
 		nf_ct_l4proto_put(cur->l4proto);
 
-		if (atomic_dec_and_test(&cur->refcnt))
+		if (refcount_dec_and_test(&cur->refcnt))
 			kfree_rcu(cur, rcu_head);
 	}
 }
@@ -646,8 +647,8 @@ static void __exit cttimeout_exit(void)
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL);
 	RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL);
+	synchronize_rcu();
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
-	rcu_barrier();
 }
 
 module_init(cttimeout_init);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 08247bf7d7b8..da9704971a83 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -40,6 +40,8 @@
 #include <net/netfilter/nfnetlink_log.h>
 
 #include <linux/atomic.h>
+#include <linux/refcount.h>
+
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include "../bridge/br_private.h"
@@ -57,7 +59,7 @@
 struct nfulnl_instance {
 	struct hlist_node hlist;	/* global list of instances */
 	spinlock_t lock;
-	atomic_t use;			/* use count */
+	refcount_t use;			/* use count */
 
 	unsigned int qlen;		/* number of nlmsgs in skb */
 	struct sk_buff *skb;		/* pre-allocatd skb */
@@ -115,7 +117,7 @@ __instance_lookup(struct nfnl_log_net *log, u_int16_t group_num)
 static inline void
 instance_get(struct nfulnl_instance *inst)
 {
-	atomic_inc(&inst->use);
+	refcount_inc(&inst->use);
 }
 
 static struct nfulnl_instance *
@@ -125,7 +127,7 @@ instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num)
 
 	rcu_read_lock_bh();
 	inst = __instance_lookup(log, group_num);
-	if (inst && !atomic_inc_not_zero(&inst->use))
+	if (inst && !refcount_inc_not_zero(&inst->use))
 		inst = NULL;
 	rcu_read_unlock_bh();
 
@@ -145,7 +147,7 @@ static void nfulnl_instance_free_rcu(struct rcu_head *head)
 static void
 instance_put(struct nfulnl_instance *inst)
 {
-	if (inst && atomic_dec_and_test(&inst->use))
+	if (inst && refcount_dec_and_test(&inst->use))
 		call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu);
 }
 
@@ -180,7 +182,7 @@ instance_create(struct net *net, u_int16_t group_num,
 	INIT_HLIST_NODE(&inst->hlist);
 	spin_lock_init(&inst->lock);
 	/* needs to be two, since we _put() after creation */
-	atomic_set(&inst->use, 2);
+	refcount_set(&inst->use, 2);
 
 	setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst);
 
@@ -409,7 +411,7 @@ __build_packet_message(struct nfnl_log_net *log,
 	const unsigned char *hwhdrp;
 
 	nlh = nlmsg_put(inst->skb, 0, 0,
-			NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET,
+			nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET),
 			sizeof(struct nfgenmsg), 0);
 	if (!nlh)
 		return -1;
@@ -801,7 +803,7 @@ static int nfulnl_recv_unsupp(struct net *net, struct sock *ctnl,
 static struct nf_logger nfulnl_logger __read_mostly = {
 	.name	= "nfnetlink_log",
 	.type	= NF_LOG_TYPE_ULOG,
-	.logfn	= &nfulnl_log_packet,
+	.logfn	= nfulnl_log_packet,
 	.me	= THIS_MODULE,
 };
 
@@ -1031,7 +1033,7 @@ static int seq_show(struct seq_file *s, void *v)
 		   inst->group_num,
 		   inst->peer_portid, inst->qlen,
 		   inst->copy_mode, inst->copy_range,
-		   inst->flushtimeout, atomic_read(&inst->use));
+		   inst->flushtimeout, refcount_read(&inst->use));
 
 	return 0;
 }
@@ -1138,10 +1140,10 @@ out:
 
 static void __exit nfnetlink_log_fini(void)
 {
-	nf_log_unregister(&nfulnl_logger);
 	nfnetlink_subsys_unregister(&nfulnl_subsys);
 	netlink_unregister_notifier(&nfulnl_rtnl_notifier);
 	unregister_pernet_subsys(&nfnl_log_net_ops);
+	nf_log_unregister(&nfulnl_logger);
 }
 
 MODULE_DESCRIPTION("netfilter userspace logging");
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 3ee0b8a000a4..8a0f218b7938 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -443,16 +443,16 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	skb = alloc_skb(size, GFP_ATOMIC);
 	if (!skb) {
 		skb_tx_error(entskb);
-		return NULL;
+		goto nlmsg_failure;
 	}
 
 	nlh = nlmsg_put(skb, 0, 0,
-			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
+			nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET),
 			sizeof(struct nfgenmsg), 0);
 	if (!nlh) {
 		skb_tx_error(entskb);
 		kfree_skb(skb);
-		return NULL;
+		goto nlmsg_failure;
 	}
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family = entry->state.pf;
@@ -598,12 +598,17 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	}
 
 	nlh->nlmsg_len = skb->len;
+	if (seclen)
+		security_release_secctx(secdata, seclen);
 	return skb;
 
 nla_put_failure:
 	skb_tx_error(entskb);
 	kfree_skb(skb);
 	net_err_ratelimited("nf_queue: error creating packet message\n");
+nlmsg_failure:
+	if (seclen)
+		security_release_secctx(secdata, seclen);
 	return NULL;
 }
 
@@ -917,16 +922,10 @@ static struct notifier_block nfqnl_dev_notifier = {
 	.notifier_call	= nfqnl_rcv_dev_event,
 };
 
-static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long entry_ptr)
-{
-	return rcu_access_pointer(entry->hook) ==
-		(struct nf_hook_entry *)entry_ptr;
-}
-
-static void nfqnl_nf_hook_drop(struct net *net,
-			       const struct nf_hook_entry *hook)
+static unsigned int nfqnl_nf_hook_drop(struct net *net)
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(net);
+	unsigned int instances = 0;
 	int i;
 
 	rcu_read_lock();
@@ -934,10 +933,14 @@ static void nfqnl_nf_hook_drop(struct net *net,
 		struct nfqnl_instance *inst;
 		struct hlist_head *head = &q->instance_table[i];
 
-		hlist_for_each_entry_rcu(inst, head, hlist)
-			nfqnl_flush(inst, nf_hook_cmp, (unsigned long)hook);
+		hlist_for_each_entry_rcu(inst, head, hlist) {
+			nfqnl_flush(inst, NULL, 0);
+			instances++;
+		}
 	}
 	rcu_read_unlock();
+
+	return instances;
 }
 
 static int
@@ -1104,7 +1107,7 @@ static int nfqa_parse_bridge(struct nf_queue_entry *entry,
 		int err;
 
 		err = nla_parse_nested(tb, NFQA_VLAN_MAX, nfqa[NFQA_VLAN],
-				       nfqa_vlan_policy);
+				       nfqa_vlan_policy, NULL);
 		if (err < 0)
 			return err;
 
@@ -1208,8 +1211,8 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 };
 
 static const struct nf_queue_handler nfqh = {
-	.outfn		= &nfqnl_enqueue_packet,
-	.nf_hook_drop	= &nfqnl_nf_hook_drop,
+	.outfn		= nfqnl_enqueue_packet,
+	.nf_hook_drop	= nfqnl_nf_hook_drop,
 };
 
 static int nfqnl_recv_config(struct net *net, struct sock *ctnl,
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index c21e7eb8dce0..f753ec69f790 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -42,7 +42,8 @@ static int nft_compat_chain_validate_dependency(const char *tablename,
 {
 	const struct nft_base_chain *basechain;
 
-	if (!tablename || !(chain->flags & NFT_BASE_CHAIN))
+	if (!tablename ||
+	    !nft_is_base_chain(chain))
 		return 0;
 
 	basechain = nft_base_chain(chain);
@@ -165,7 +166,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
 	par->entryinfo	= entry;
 	par->target	= target;
 	par->targinfo	= info;
-	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
 		const struct nf_hook_ops *ops = &basechain->ops[0];
@@ -200,7 +201,7 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 	int err;
 
 	err = nla_parse_nested(tb, NFTA_RULE_COMPAT_MAX, attr,
-			       nft_rule_compat_policy);
+			       nft_rule_compat_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -230,10 +231,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	union nft_entry e = {};
 	int ret;
 
-	ret = nft_compat_chain_validate_dependency(target->table, ctx->chain);
-	if (ret < 0)
-		goto err;
-
 	target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info);
 
 	if (ctx->nla[NFTA_RULE_COMPAT]) {
@@ -302,7 +299,7 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 	unsigned int hook_mask = 0;
 	int ret;
 
-	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
 		const struct nf_hook_ops *ops = &basechain->ops[0];
@@ -383,7 +380,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
 	par->entryinfo	= entry;
 	par->match	= match;
 	par->matchinfo	= info;
-	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
 		const struct nf_hook_ops *ops = &basechain->ops[0];
@@ -419,10 +416,6 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	union nft_entry e = {};
 	int ret;
 
-	ret = nft_compat_chain_validate_dependency(match->table, ctx->chain);
-	if (ret < 0)
-		goto err;
-
 	match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info);
 
 	if (ctx->nla[NFTA_RULE_COMPAT]) {
@@ -485,7 +478,7 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 	unsigned int hook_mask = 0;
 	int ret;
 
-	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
 		const struct nf_hook_ops *ops = &basechain->ops[0];
@@ -511,7 +504,7 @@ nfnl_compat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
 
-	event |= NFNL_SUBSYS_NFT_COMPAT << 8;
+	event = nfnl_msg_type(NFNL_SUBSYS_NFT_COMPAT, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
 		goto nlmsg_failure;
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 7f8422213341..67a710ebde09 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -82,7 +82,8 @@ static int nft_counter_do_init(const struct nlattr * const tb[],
 	return 0;
 }
 
-static int nft_counter_obj_init(const struct nlattr * const tb[],
+static int nft_counter_obj_init(const struct nft_ctx *ctx,
+				const struct nlattr * const tb[],
 				struct nft_object *obj)
 {
 	struct nft_counter_percpu_priv *priv = nft_obj_data(obj);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index bf548a7a71ec..a34ceb38fc55 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -32,6 +32,12 @@ struct nft_ct {
 	};
 };
 
+struct nft_ct_helper_obj  {
+	struct nf_conntrack_helper *helper4;
+	struct nf_conntrack_helper *helper6;
+	u8 l4proto;
+};
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template);
 static unsigned int nft_ct_pcpu_template_refcnt __read_mostly;
@@ -66,12 +72,12 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 
 	switch (priv->key) {
 	case NFT_CT_STATE:
-		if (ct == NULL)
-			state = NF_CT_STATE_INVALID_BIT;
-		else if (nf_ct_is_untracked(ct))
+		if (ct)
+			state = NF_CT_STATE_BIT(ctinfo);
+		else if (ctinfo == IP_CT_UNTRACKED)
 			state = NF_CT_STATE_UNTRACKED_BIT;
 		else
-			state = NF_CT_STATE_BIT(ctinfo);
+			state = NF_CT_STATE_INVALID_BIT;
 		*dest = state;
 		return;
 	default:
@@ -83,7 +89,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 
 	switch (priv->key) {
 	case NFT_CT_DIRECTION:
-		*dest = CTINFO2DIR(ctinfo);
+		nft_reg_store8(dest, CTINFO2DIR(ctinfo));
 		return;
 	case NFT_CT_STATUS:
 		*dest = ct->status;
@@ -151,20 +157,22 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		return;
 	}
 	case NFT_CT_L3PROTOCOL:
-		*dest = nf_ct_l3num(ct);
+		nft_reg_store8(dest, nf_ct_l3num(ct));
 		return;
 	case NFT_CT_PROTOCOL:
-		*dest = nf_ct_protonum(ct);
+		nft_reg_store8(dest, nf_ct_protonum(ct));
 		return;
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	case NFT_CT_ZONE: {
 		const struct nf_conntrack_zone *zone = nf_ct_zone(ct);
+		u16 zoneid;
 
 		if (priv->dir < IP_CT_DIR_MAX)
-			*dest = nf_ct_zone_id(zone, priv->dir);
+			zoneid = nf_ct_zone_id(zone, priv->dir);
 		else
-			*dest = zone->id;
+			zoneid = zone->id;
 
+		nft_reg_store16(dest, zoneid);
 		return;
 	}
 #endif
@@ -183,10 +191,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
 		return;
 	case NFT_CT_PROTO_SRC:
-		*dest = (__force __u16)tuple->src.u.all;
+		nft_reg_store16(dest, (__force u16)tuple->src.u.all);
 		return;
 	case NFT_CT_PROTO_DST:
-		*dest = (__force __u16)tuple->dst.u.all;
+		nft_reg_store16(dest, (__force u16)tuple->dst.u.all);
 		return;
 	default:
 		break;
@@ -205,7 +213,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 	const struct nft_ct *priv = nft_expr_priv(expr);
 	struct sk_buff *skb = pkt->skb;
 	enum ip_conntrack_info ctinfo;
-	u16 value = regs->data[priv->sreg];
+	u16 value = nft_reg_load16(&regs->data[priv->sreg]);
 	struct nf_conn *ct;
 
 	ct = nf_ct_get(skb, &ctinfo);
@@ -256,7 +264,7 @@ static void nft_ct_set_eval(const struct nft_expr *expr,
 	struct nf_conn *ct;
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL)
+	if (ct == NULL || nf_ct_is_template(ct))
 		return;
 
 	switch (priv->key) {
@@ -276,6 +284,22 @@ static void nft_ct_set_eval(const struct nft_expr *expr,
 				      NF_CT_LABELS_MAX_SIZE / sizeof(u32));
 		break;
 #endif
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	case NFT_CT_EVENTMASK: {
+		struct nf_conntrack_ecache *e = nf_ct_ecache_find(ct);
+		u32 ctmask = regs->data[priv->sreg];
+
+		if (e) {
+			if (e->ctmask != ctmask)
+				e->ctmask = ctmask;
+			break;
+		}
+
+		if (ctmask && !nf_ct_is_confirmed(ct))
+			nf_ct_ecache_ext_add(ct, ctmask, 0, GFP_ATOMIC);
+		break;
+	}
+#endif
 	default:
 		break;
 	}
@@ -531,6 +555,13 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
 		len = sizeof(u16);
 		break;
 #endif
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	case NFT_CT_EVENTMASK:
+		if (tb[NFTA_CT_DIRECTION])
+			return -EINVAL;
+		len = sizeof(u32);
+		break;
+#endif
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -542,7 +573,8 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
 		case IP_CT_DIR_REPLY:
 			break;
 		default:
-			return -EINVAL;
+			err = -EINVAL;
+			goto err1;
 		}
 	}
 
@@ -693,7 +725,7 @@ nft_ct_select_ops(const struct nft_ctx *ctx,
 
 static struct nft_expr_type nft_ct_type __read_mostly = {
 	.name		= "ct",
-	.select_ops	= &nft_ct_select_ops,
+	.select_ops	= nft_ct_select_ops,
 	.policy		= nft_ct_policy,
 	.maxattr	= NFTA_CT_MAX,
 	.owner		= THIS_MODULE,
@@ -709,12 +741,10 @@ static void nft_notrack_eval(const struct nft_expr *expr,
 
 	ct = nf_ct_get(pkt->skb, &ctinfo);
 	/* Previously seen (loopback or untracked)?  Ignore. */
-	if (ct)
+	if (ct || ctinfo == IP_CT_UNTRACKED)
 		return;
 
-	ct = nf_ct_untracked_get();
-	atomic_inc(&ct->ct_general.use);
-	nf_ct_set(skb, ct, IP_CT_NEW);
+	nf_ct_set(skb, ct, IP_CT_UNTRACKED);
 }
 
 static struct nft_expr_type nft_notrack_type;
@@ -730,6 +760,162 @@ static struct nft_expr_type nft_notrack_type __read_mostly = {
 	.owner		= THIS_MODULE,
 };
 
+static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
+				  const struct nlattr * const tb[],
+				  struct nft_object *obj)
+{
+	struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+	struct nf_conntrack_helper *help4, *help6;
+	char name[NF_CT_HELPER_NAME_LEN];
+	int family = ctx->afi->family;
+
+	if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO])
+		return -EINVAL;
+
+	priv->l4proto = nla_get_u8(tb[NFTA_CT_HELPER_L4PROTO]);
+	if (!priv->l4proto)
+		return -ENOENT;
+
+	nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+
+	if (tb[NFTA_CT_HELPER_L3PROTO])
+		family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
+
+	help4 = NULL;
+	help6 = NULL;
+
+	switch (family) {
+	case NFPROTO_IPV4:
+		if (ctx->afi->family == NFPROTO_IPV6)
+			return -EINVAL;
+
+		help4 = nf_conntrack_helper_try_module_get(name, family,
+							   priv->l4proto);
+		break;
+	case NFPROTO_IPV6:
+		if (ctx->afi->family == NFPROTO_IPV4)
+			return -EINVAL;
+
+		help6 = nf_conntrack_helper_try_module_get(name, family,
+							   priv->l4proto);
+		break;
+	case NFPROTO_NETDEV: /* fallthrough */
+	case NFPROTO_BRIDGE: /* same */
+	case NFPROTO_INET:
+		help4 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV4,
+							   priv->l4proto);
+		help6 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV6,
+							   priv->l4proto);
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	/* && is intentional; only error if INET found neither ipv4 or ipv6 */
+	if (!help4 && !help6)
+		return -ENOENT;
+
+	priv->helper4 = help4;
+	priv->helper6 = help6;
+
+	return 0;
+}
+
+static void nft_ct_helper_obj_destroy(struct nft_object *obj)
+{
+	struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+
+	if (priv->helper4)
+		module_put(priv->helper4->me);
+	if (priv->helper6)
+		module_put(priv->helper6->me);
+}
+
+static void nft_ct_helper_obj_eval(struct nft_object *obj,
+				   struct nft_regs *regs,
+				   const struct nft_pktinfo *pkt)
+{
+	const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+	struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb);
+	struct nf_conntrack_helper *to_assign = NULL;
+	struct nf_conn_help *help;
+
+	if (!ct ||
+	    nf_ct_is_confirmed(ct) ||
+	    nf_ct_is_template(ct) ||
+	    priv->l4proto != nf_ct_protonum(ct))
+		return;
+
+	switch (nf_ct_l3num(ct)) {
+	case NFPROTO_IPV4:
+		to_assign = priv->helper4;
+		break;
+	case NFPROTO_IPV6:
+		to_assign = priv->helper6;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	if (!to_assign)
+		return;
+
+	if (test_bit(IPS_HELPER_BIT, &ct->status))
+		return;
+
+	help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC);
+	if (help) {
+		rcu_assign_pointer(help->helper, to_assign);
+		set_bit(IPS_HELPER_BIT, &ct->status);
+	}
+}
+
+static int nft_ct_helper_obj_dump(struct sk_buff *skb,
+				  struct nft_object *obj, bool reset)
+{
+	const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+	const struct nf_conntrack_helper *helper = priv->helper4;
+	u16 family;
+
+	if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name))
+		return -1;
+
+	if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto))
+		return -1;
+
+	if (priv->helper4 && priv->helper6)
+		family = NFPROTO_INET;
+	else if (priv->helper6)
+		family = NFPROTO_IPV6;
+	else
+		family = NFPROTO_IPV4;
+
+	if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family)))
+		return -1;
+
+	return 0;
+}
+
+static const struct nla_policy nft_ct_helper_policy[NFTA_CT_HELPER_MAX + 1] = {
+	[NFTA_CT_HELPER_NAME] = { .type = NLA_STRING,
+				  .len = NF_CT_HELPER_NAME_LEN - 1 },
+	[NFTA_CT_HELPER_L3PROTO] = { .type = NLA_U16 },
+	[NFTA_CT_HELPER_L4PROTO] = { .type = NLA_U8 },
+};
+
+static struct nft_object_type nft_ct_helper_obj __read_mostly = {
+	.type		= NFT_OBJECT_CT_HELPER,
+	.size		= sizeof(struct nft_ct_helper_obj),
+	.maxattr	= NFTA_CT_HELPER_MAX,
+	.policy		= nft_ct_helper_policy,
+	.eval		= nft_ct_helper_obj_eval,
+	.init		= nft_ct_helper_obj_init,
+	.destroy	= nft_ct_helper_obj_destroy,
+	.dump		= nft_ct_helper_obj_dump,
+	.owner		= THIS_MODULE,
+};
+
 static int __init nft_ct_module_init(void)
 {
 	int err;
@@ -744,7 +930,14 @@ static int __init nft_ct_module_init(void)
 	if (err < 0)
 		goto err1;
 
+	err = nft_register_obj(&nft_ct_helper_obj);
+	if (err < 0)
+		goto err2;
+
 	return 0;
+
+err2:
+	nft_unregister_expr(&nft_notrack_type);
 err1:
 	nft_unregister_expr(&nft_ct_type);
 	return err;
@@ -752,6 +945,7 @@ err1:
 
 static void __exit nft_ct_module_exit(void)
 {
+	nft_unregister_obj(&nft_ct_helper_obj);
 	nft_unregister_expr(&nft_notrack_type);
 	nft_unregister_expr(&nft_ct_type);
 }
@@ -763,3 +957,4 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
 MODULE_ALIAS_NFT_EXPR("ct");
 MODULE_ALIAS_NFT_EXPR("notrack");
+MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER);
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 049ad2d9ee66..3948da380259 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -133,16 +133,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			priv->invert = true;
 	}
 
-	set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME],
-				   genmask);
-	if (IS_ERR(set)) {
-		if (tb[NFTA_DYNSET_SET_ID])
-			set = nf_tables_set_lookup_byid(ctx->net,
-							tb[NFTA_DYNSET_SET_ID],
-							genmask);
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME],
+			     tb[NFTA_DYNSET_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (set->ops->update == NULL)
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index c308920b194c..1ec49fe5845f 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -98,14 +98,21 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
 			goto err;
 
 		offset = i + priv->offset;
-		dest[priv->len / NFT_REG32_SIZE] = 0;
-		memcpy(dest, opt + offset, priv->len);
+		if (priv->flags & NFT_EXTHDR_F_PRESENT) {
+			*dest = 1;
+		} else {
+			dest[priv->len / NFT_REG32_SIZE] = 0;
+			memcpy(dest, opt + offset, priv->len);
+		}
 
 		return;
 	}
 
 err:
-	regs->verdict.code = NFT_BREAK;
+	if (priv->flags & NFT_EXTHDR_F_PRESENT)
+		*dest = 0;
+	else
+		regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
@@ -225,7 +232,7 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 
 static struct nft_expr_type nft_exthdr_type __read_mostly = {
 	.name		= "exthdr",
-	.select_ops	= &nft_exthdr_select_ops,
+	.select_ops	= nft_exthdr_select_ops,
 	.policy		= nft_exthdr_policy,
 	.maxattr	= NFTA_EXTHDR_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 29a4906adc27..21df8cccea65 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -24,7 +24,8 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = {
 EXPORT_SYMBOL(nft_fib_policy);
 
 #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \
-			NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)
+			NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \
+			NFTA_FIB_F_PRESENT)
 
 int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		     const struct nft_data **data)
@@ -112,7 +113,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (err < 0)
 		return err;
 
-	return nft_fib_validate(ctx, expr, NULL);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nft_fib_init);
 
@@ -133,19 +134,22 @@ int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr)
 }
 EXPORT_SYMBOL_GPL(nft_fib_dump);
 
-void nft_fib_store_result(void *reg, enum nft_fib_result r,
+void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 			  const struct nft_pktinfo *pkt, int index)
 {
 	struct net_device *dev;
 	u32 *dreg = reg;
 
-	switch (r) {
+	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
-		*dreg = index;
+		*dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index;
 		break;
 	case NFT_FIB_RESULT_OIFNAME:
 		dev = dev_get_by_index_rcu(nft_net(pkt), index);
-		strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
+		if (priv->flags & NFTA_FIB_F_PRESENT)
+			*dreg = !!dev;
+		else
+			strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
 		break;
 	default:
 		WARN_ON_ONCE(1);
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index eb2721af898d..24f2f7567ddb 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -17,20 +17,21 @@
 #include <net/netfilter/nf_tables_core.h>
 #include <linux/jhash.h>
 
-struct nft_hash {
+struct nft_jhash {
 	enum nft_registers      sreg:8;
 	enum nft_registers      dreg:8;
 	u8			len;
+	bool			autogen_seed:1;
 	u32			modulus;
 	u32			seed;
 	u32			offset;
 };
 
-static void nft_hash_eval(const struct nft_expr *expr,
-			  struct nft_regs *regs,
-			  const struct nft_pktinfo *pkt)
+static void nft_jhash_eval(const struct nft_expr *expr,
+			   struct nft_regs *regs,
+			   const struct nft_pktinfo *pkt)
 {
-	struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_jhash *priv = nft_expr_priv(expr);
 	const void *data = &regs->data[priv->sreg];
 	u32 h;
 
@@ -38,6 +39,25 @@ static void nft_hash_eval(const struct nft_expr *expr,
 	regs->data[priv->dreg] = h + priv->offset;
 }
 
+struct nft_symhash {
+	enum nft_registers      dreg:8;
+	u32			modulus;
+	u32			offset;
+};
+
+static void nft_symhash_eval(const struct nft_expr *expr,
+			     struct nft_regs *regs,
+			     const struct nft_pktinfo *pkt)
+{
+	struct nft_symhash *priv = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 h;
+
+	h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus);
+
+	regs->data[priv->dreg] = h + priv->offset;
+}
+
 static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
 	[NFTA_HASH_SREG]	= { .type = NLA_U32 },
 	[NFTA_HASH_DREG]	= { .type = NLA_U32 },
@@ -45,13 +65,14 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
 	[NFTA_HASH_MODULUS]	= { .type = NLA_U32 },
 	[NFTA_HASH_SEED]	= { .type = NLA_U32 },
 	[NFTA_HASH_OFFSET]	= { .type = NLA_U32 },
+	[NFTA_HASH_TYPE]	= { .type = NLA_U32 },
 };
 
-static int nft_hash_init(const struct nft_ctx *ctx,
-			 const struct nft_expr *expr,
-			 const struct nlattr * const tb[])
+static int nft_jhash_init(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr,
+			  const struct nlattr * const tb[])
 {
-	struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_jhash *priv = nft_expr_priv(expr);
 	u32 len;
 	int err;
 
@@ -82,20 +103,48 @@ static int nft_hash_init(const struct nft_ctx *ctx,
 	if (priv->offset + priv->modulus - 1 < priv->offset)
 		return -EOVERFLOW;
 
-	if (tb[NFTA_HASH_SEED])
+	if (tb[NFTA_HASH_SEED]) {
 		priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED]));
-	else
+	} else {
+		priv->autogen_seed = true;
 		get_random_bytes(&priv->seed, sizeof(priv->seed));
+	}
 
 	return nft_validate_register_load(priv->sreg, len) &&
 	       nft_validate_register_store(ctx, priv->dreg, NULL,
 					   NFT_DATA_VALUE, sizeof(u32));
 }
 
-static int nft_hash_dump(struct sk_buff *skb,
-			 const struct nft_expr *expr)
+static int nft_symhash_init(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nlattr * const tb[])
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_symhash *priv = nft_expr_priv(expr);
+
+	if (!tb[NFTA_HASH_DREG]    ||
+	    !tb[NFTA_HASH_MODULUS])
+		return -EINVAL;
+
+	if (tb[NFTA_HASH_OFFSET])
+		priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET]));
+
+	priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]);
+
+	priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
+	if (priv->modulus <= 1)
+		return -ERANGE;
+
+	if (priv->offset + priv->modulus - 1 < priv->offset)
+		return -EOVERFLOW;
+
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, sizeof(u32));
+}
+
+static int nft_jhash_dump(struct sk_buff *skb,
+			  const struct nft_expr *expr)
+{
+	const struct nft_jhash *priv = nft_expr_priv(expr);
 
 	if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg))
 		goto nla_put_failure;
@@ -105,11 +154,34 @@ static int nft_hash_dump(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
+	if (!priv->autogen_seed &&
+	    nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
 		goto nla_put_failure;
 	if (priv->offset != 0)
 		if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
 			goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_symhash_dump(struct sk_buff *skb,
+			    const struct nft_expr *expr)
+{
+	const struct nft_symhash *priv = nft_expr_priv(expr);
+
+	if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
+		goto nla_put_failure;
+	if (priv->offset != 0)
+		if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
+			goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM)))
+		goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
@@ -117,17 +189,46 @@ nla_put_failure:
 }
 
 static struct nft_expr_type nft_hash_type;
-static const struct nft_expr_ops nft_hash_ops = {
+static const struct nft_expr_ops nft_jhash_ops = {
 	.type		= &nft_hash_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_hash)),
-	.eval		= nft_hash_eval,
-	.init		= nft_hash_init,
-	.dump		= nft_hash_dump,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_jhash)),
+	.eval		= nft_jhash_eval,
+	.init		= nft_jhash_init,
+	.dump		= nft_jhash_dump,
 };
 
+static const struct nft_expr_ops nft_symhash_ops = {
+	.type		= &nft_hash_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_symhash)),
+	.eval		= nft_symhash_eval,
+	.init		= nft_symhash_init,
+	.dump		= nft_symhash_dump,
+};
+
+static const struct nft_expr_ops *
+nft_hash_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	u32 type;
+
+	if (!tb[NFTA_HASH_TYPE])
+		return &nft_jhash_ops;
+
+	type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE]));
+	switch (type) {
+	case NFT_HASH_SYM:
+		return &nft_symhash_ops;
+	case NFT_HASH_JENKINS:
+		return &nft_jhash_ops;
+	default:
+		break;
+	}
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static struct nft_expr_type nft_hash_type __read_mostly = {
 	.name		= "hash",
-	.ops		= &nft_hash_ops,
+	.select_ops	= nft_hash_select_ops,
 	.policy		= nft_hash_policy,
 	.maxattr	= NFTA_HASH_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index c6baf412236d..18dd57a52651 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -17,9 +17,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
-static DEFINE_SPINLOCK(limit_lock);
-
 struct nft_limit {
+	spinlock_t	lock;
 	u64		last;
 	u64		tokens;
 	u64		tokens_max;
@@ -34,7 +33,7 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
 	u64 now, tokens;
 	s64 delta;
 
-	spin_lock_bh(&limit_lock);
+	spin_lock_bh(&limit->lock);
 	now = ktime_get_ns();
 	tokens = limit->tokens + now - limit->last;
 	if (tokens > limit->tokens_max)
@@ -44,11 +43,11 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
 	delta = tokens - cost;
 	if (delta >= 0) {
 		limit->tokens = delta;
-		spin_unlock_bh(&limit_lock);
+		spin_unlock_bh(&limit->lock);
 		return limit->invert;
 	}
 	limit->tokens = tokens;
-	spin_unlock_bh(&limit_lock);
+	spin_unlock_bh(&limit->lock);
 	return !limit->invert;
 }
 
@@ -86,6 +85,7 @@ static int nft_limit_init(struct nft_limit *limit,
 			limit->invert = true;
 	}
 	limit->last = ktime_get_ns();
+	spin_lock_init(&limit->lock);
 
 	return 0;
 }
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index e21aea7e5ec8..475570e89ede 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -71,16 +71,10 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	    tb[NFTA_LOOKUP_SREG] == NULL)
 		return -EINVAL;
 
-	set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET], genmask);
-	if (IS_ERR(set)) {
-		if (tb[NFTA_LOOKUP_SET_ID]) {
-			set = nf_tables_set_lookup_byid(ctx->net,
-							tb[NFTA_LOOKUP_SET_ID],
-							genmask);
-		}
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
+			     tb[NFTA_LOOKUP_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (set->flags & NFT_SET_EVAL)
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 11ce016cd479..6ac03d4266c9 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -46,10 +46,6 @@ int nft_masq_init(const struct nft_ctx *ctx,
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_masq_validate(ctx, expr, NULL);
-	if (err)
-		return err;
-
 	if (tb[NFTA_MASQ_FLAGS]) {
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
 		if (priv->flags & ~NF_NAT_RANGE_MASK)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e1f5ca9b423b..5a60eb23a7ed 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -45,16 +45,15 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		*dest = skb->len;
 		break;
 	case NFT_META_PROTOCOL:
-		*dest = 0;
-		*(__be16 *)dest = skb->protocol;
+		nft_reg_store16(dest, (__force u16)skb->protocol);
 		break;
 	case NFT_META_NFPROTO:
-		*dest = nft_pf(pkt);
+		nft_reg_store8(dest, nft_pf(pkt));
 		break;
 	case NFT_META_L4PROTO:
 		if (!pkt->tprot_set)
 			goto err;
-		*dest = pkt->tprot;
+		nft_reg_store8(dest, pkt->tprot);
 		break;
 	case NFT_META_PRIORITY:
 		*dest = skb->priority;
@@ -85,14 +84,12 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 	case NFT_META_IIFTYPE:
 		if (in == NULL)
 			goto err;
-		*dest = 0;
-		*(u16 *)dest = in->type;
+		nft_reg_store16(dest, in->type);
 		break;
 	case NFT_META_OIFTYPE:
 		if (out == NULL)
 			goto err;
-		*dest = 0;
-		*(u16 *)dest = out->type;
+		nft_reg_store16(dest, out->type);
 		break;
 	case NFT_META_SKUID:
 		sk = skb_to_full_sk(skb);
@@ -142,19 +139,19 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 #endif
 	case NFT_META_PKTTYPE:
 		if (skb->pkt_type != PACKET_LOOPBACK) {
-			*dest = skb->pkt_type;
+			nft_reg_store8(dest, skb->pkt_type);
 			break;
 		}
 
 		switch (nft_pf(pkt)) {
 		case NFPROTO_IPV4:
 			if (ipv4_is_multicast(ip_hdr(skb)->daddr))
-				*dest = PACKET_MULTICAST;
+				nft_reg_store8(dest, PACKET_MULTICAST);
 			else
-				*dest = PACKET_BROADCAST;
+				nft_reg_store8(dest, PACKET_BROADCAST);
 			break;
 		case NFPROTO_IPV6:
-			*dest = PACKET_MULTICAST;
+			nft_reg_store8(dest, PACKET_MULTICAST);
 			break;
 		case NFPROTO_NETDEV:
 			switch (skb->protocol) {
@@ -168,14 +165,14 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 					goto err;
 
 				if (ipv4_is_multicast(iph->daddr))
-					*dest = PACKET_MULTICAST;
+					nft_reg_store8(dest, PACKET_MULTICAST);
 				else
-					*dest = PACKET_BROADCAST;
+					nft_reg_store8(dest, PACKET_BROADCAST);
 
 				break;
 			}
 			case htons(ETH_P_IPV6):
-				*dest = PACKET_MULTICAST;
+				nft_reg_store8(dest, PACKET_MULTICAST);
 				break;
 			default:
 				WARN_ON_ONCE(1);
@@ -230,7 +227,9 @@ void nft_meta_set_eval(const struct nft_expr *expr,
 {
 	const struct nft_meta *meta = nft_expr_priv(expr);
 	struct sk_buff *skb = pkt->skb;
-	u32 value = regs->data[meta->sreg];
+	u32 *sreg = &regs->data[meta->sreg];
+	u32 value = *sreg;
+	u8 pkt_type;
 
 	switch (meta->key) {
 	case NFT_META_MARK:
@@ -240,9 +239,12 @@ void nft_meta_set_eval(const struct nft_expr *expr,
 		skb->priority = value;
 		break;
 	case NFT_META_PKTTYPE:
-		if (skb->pkt_type != value &&
-		    skb_pkt_type_ok(value) && skb_pkt_type_ok(skb->pkt_type))
-			skb->pkt_type = value;
+		pkt_type = nft_reg_load8(sreg);
+
+		if (skb->pkt_type != pkt_type &&
+		    skb_pkt_type_ok(pkt_type) &&
+		    skb_pkt_type_ok(skb->pkt_type))
+			skb->pkt_type = pkt_type;
 		break;
 	case NFT_META_NFTRACE:
 		skb->nf_trace = !!value;
@@ -370,10 +372,6 @@ int nft_meta_set_init(const struct nft_ctx *ctx,
 		return -EOPNOTSUPP;
 	}
 
-	err = nft_meta_set_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
-
 	priv->sreg = nft_parse_register(tb[NFTA_META_SREG]);
 	err = nft_validate_register_load(priv->sreg, len);
 	if (err < 0)
@@ -469,7 +467,7 @@ nft_meta_select_ops(const struct nft_ctx *ctx,
 
 static struct nft_expr_type nft_meta_type __read_mostly = {
 	.name		= "meta",
-	.select_ops	= &nft_meta_select_ops,
+	.select_ops	= nft_meta_select_ops,
 	.policy		= nft_meta_policy,
 	.maxattr	= NFTA_META_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 19a7bf3236f9..ed548d06b6dd 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr,
 	}
 
 	if (priv->sreg_proto_min) {
-		range.min_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min];
-		range.max_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
@@ -138,10 +138,6 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		return -EINVAL;
 	}
 
-	err = nft_nat_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
-
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		return -EINVAL;
 
diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index a66b36097b8f..5a3a52c71545 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -188,7 +188,7 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 
 static struct nft_expr_type nft_ng_type __read_mostly = {
 	.name		= "numgen",
-	.select_ops	= &nft_ng_select_ops,
+	.select_ops	= nft_ng_select_ops,
 	.policy		= nft_ng_policy,
 	.maxattr	= NFTA_NG_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 1ae8c49ca4a1..1dd428fbaaa3 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -116,16 +116,10 @@ static int nft_objref_map_init(const struct nft_ctx *ctx,
 	struct nft_set *set;
 	int err;
 
-	set = nf_tables_set_lookup(ctx->table, tb[NFTA_OBJREF_SET_NAME], genmask);
-	if (IS_ERR(set)) {
-		if (tb[NFTA_OBJREF_SET_ID]) {
-			set = nf_tables_set_lookup_byid(ctx->net,
-							tb[NFTA_OBJREF_SET_ID],
-							genmask);
-		}
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME],
+			     tb[NFTA_OBJREF_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (!(set->flags & NFT_SET_OBJECT))
 		return -EINVAL;
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index dbb6aaff67ec..98613658d4ac 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -197,7 +197,7 @@ nft_queue_select_ops(const struct nft_ctx *ctx,
 
 static struct nft_expr_type nft_queue_type __read_mostly = {
 	.name		= "queue",
-	.select_ops	= &nft_queue_select_ops,
+	.select_ops	= nft_queue_select_ops,
 	.policy		= nft_queue_policy,
 	.maxattr	= NFTA_QUEUE_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c
index 2d6fe3559912..25e33159be57 100644
--- a/net/netfilter/nft_quota.c
+++ b/net/netfilter/nft_quota.c
@@ -99,7 +99,8 @@ static int nft_quota_do_init(const struct nlattr * const tb[],
 	return 0;
 }
 
-static int nft_quota_obj_init(const struct nlattr * const tb[],
+static int nft_quota_obj_init(const struct nft_ctx *ctx,
+			      const struct nlattr * const tb[],
 			      struct nft_object *obj)
 {
 	struct nft_quota *priv = nft_obj_data(obj);
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 40dcd05146d5..1e66538bf0ff 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -47,10 +47,6 @@ int nft_redir_init(const struct nft_ctx *ctx,
 	unsigned int plen;
 	int err;
 
-	err = nft_redir_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
-
 	plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all);
 	if (tb[NFTA_REDIR_REG_PROTO_MIN]) {
 		priv->sreg_proto_min =
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index c64de3f7379d..29f5bd2377b0 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -42,11 +42,6 @@ int nft_reject_init(const struct nft_ctx *ctx,
 		    const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
-	int err;
-
-	err = nft_reject_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 9e90a02cb104..5a7fb5ff867d 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -66,11 +66,7 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx,
 				const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
-	int icmp_code, err;
-
-	err = nft_reject_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
+	int icmp_code;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 152d226552c1..8ebbc2940f4c 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -15,6 +15,11 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
+struct nft_bitmap_elem {
+	struct list_head	head;
+	struct nft_set_ext	ext;
+};
+
 /* This bitmap uses two bits to represent one element. These two bits determine
  * the element state in the current and the future generation.
  *
@@ -41,13 +46,22 @@
  *      restore its previous state.
  */
 struct nft_bitmap {
-	u16	bitmap_size;
-	u8	bitmap[];
+	struct	list_head	list;
+	u16			bitmap_size;
+	u8			bitmap[];
 };
 
-static inline void nft_bitmap_location(u32 key, u32 *idx, u32 *off)
+static inline void nft_bitmap_location(const struct nft_set *set,
+				       const void *key,
+				       u32 *idx, u32 *off)
 {
-	u32 k = (key << 1);
+	u32 k;
+
+	if (set->klen == 2)
+		k = *(u16 *)key;
+	else
+		k = *(u8 *)key;
+	k <<= 1;
 
 	*idx = k / BITS_PER_BYTE;
 	*off = k % BITS_PER_BYTE;
@@ -69,26 +83,48 @@ static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
 	u8 genmask = nft_genmask_cur(net);
 	u32 idx, off;
 
-	nft_bitmap_location(*key, &idx, &off);
+	nft_bitmap_location(set, key, &idx, &off);
 
 	return nft_bitmap_active(priv->bitmap, idx, off, genmask);
 }
 
+static struct nft_bitmap_elem *
+nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this,
+		     u8 genmask)
+{
+	const struct nft_bitmap *priv = nft_set_priv(set);
+	struct nft_bitmap_elem *be;
+
+	list_for_each_entry_rcu(be, &priv->list, head) {
+		if (memcmp(nft_set_ext_key(&be->ext),
+			   nft_set_ext_key(&this->ext), set->klen) ||
+		    !nft_set_elem_active(&be->ext, genmask))
+			continue;
+
+		return be;
+	}
+	return NULL;
+}
+
 static int nft_bitmap_insert(const struct net *net, const struct nft_set *set,
 			     const struct nft_set_elem *elem,
-			     struct nft_set_ext **_ext)
+			     struct nft_set_ext **ext)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
-	struct nft_set_ext *ext = elem->priv;
+	struct nft_bitmap_elem *new = elem->priv, *be;
 	u8 genmask = nft_genmask_next(net);
 	u32 idx, off;
 
-	nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
-	if (nft_bitmap_active(priv->bitmap, idx, off, genmask))
+	be = nft_bitmap_elem_find(set, new, genmask);
+	if (be) {
+		*ext = &be->ext;
 		return -EEXIST;
+	}
 
+	nft_bitmap_location(set, nft_set_ext_key(&new->ext), &idx, &off);
 	/* Enter 01 state. */
 	priv->bitmap[idx] |= (genmask << off);
+	list_add_tail_rcu(&new->head, &priv->list);
 
 	return 0;
 }
@@ -98,13 +134,14 @@ static void nft_bitmap_remove(const struct net *net,
 			      const struct nft_set_elem *elem)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
-	struct nft_set_ext *ext = elem->priv;
+	struct nft_bitmap_elem *be = elem->priv;
 	u8 genmask = nft_genmask_next(net);
 	u32 idx, off;
 
-	nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
+	nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
 	/* Enter 00 state. */
 	priv->bitmap[idx] &= ~(genmask << off);
+	list_del_rcu(&be->head);
 }
 
 static void nft_bitmap_activate(const struct net *net,
@@ -112,74 +149,52 @@ static void nft_bitmap_activate(const struct net *net,
 				const struct nft_set_elem *elem)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
-	struct nft_set_ext *ext = elem->priv;
+	struct nft_bitmap_elem *be = elem->priv;
 	u8 genmask = nft_genmask_next(net);
 	u32 idx, off;
 
-	nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
+	nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
 	/* Enter 11 state. */
 	priv->bitmap[idx] |= (genmask << off);
+	nft_set_elem_change_active(net, set, &be->ext);
 }
 
 static bool nft_bitmap_flush(const struct net *net,
-			     const struct nft_set *set, void *ext)
+			     const struct nft_set *set, void *_be)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_next(net);
+	struct nft_bitmap_elem *be = _be;
 	u32 idx, off;
 
-	nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
+	nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
 	/* Enter 10 state, similar to deactivation. */
 	priv->bitmap[idx] &= ~(genmask << off);
+	nft_set_elem_change_active(net, set, &be->ext);
 
 	return true;
 }
 
-static struct nft_set_ext *nft_bitmap_ext_alloc(const struct nft_set *set,
-						const struct nft_set_elem *elem)
-{
-	struct nft_set_ext_tmpl tmpl;
-	struct nft_set_ext *ext;
-
-	nft_set_ext_prepare(&tmpl);
-	nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
-
-	ext = kzalloc(tmpl.len, GFP_KERNEL);
-	if (!ext)
-		return NULL;
-
-	nft_set_ext_init(ext, &tmpl);
-	memcpy(nft_set_ext_key(ext), elem->key.val.data, set->klen);
-
-	return ext;
-}
-
 static void *nft_bitmap_deactivate(const struct net *net,
 				   const struct nft_set *set,
 				   const struct nft_set_elem *elem)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
+	struct nft_bitmap_elem *this = elem->priv, *be;
 	u8 genmask = nft_genmask_next(net);
-	struct nft_set_ext *ext;
-	u32 idx, off, key = 0;
-
-	memcpy(&key, elem->key.val.data, set->klen);
-	nft_bitmap_location(key, &idx, &off);
+	u32 idx, off;
 
-	if (!nft_bitmap_active(priv->bitmap, idx, off, genmask))
-		return NULL;
+	nft_bitmap_location(set, elem->key.val.data, &idx, &off);
 
-	/* We have no real set extension since this is a bitmap, allocate this
-	 * dummy object that is released from the commit/abort path.
-	 */
-	ext = nft_bitmap_ext_alloc(set, elem);
-	if (!ext)
+	be = nft_bitmap_elem_find(set, this, genmask);
+	if (!be)
 		return NULL;
 
 	/* Enter 10 state. */
 	priv->bitmap[idx] &= ~(genmask << off);
+	nft_set_elem_change_active(net, set, &be->ext);
 
-	return ext;
+	return be;
 }
 
 static void nft_bitmap_walk(const struct nft_ctx *ctx,
@@ -187,47 +202,23 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
 			    struct nft_set_iter *iter)
 {
 	const struct nft_bitmap *priv = nft_set_priv(set);
-	struct nft_set_ext_tmpl tmpl;
+	struct nft_bitmap_elem *be;
 	struct nft_set_elem elem;
-	struct nft_set_ext *ext;
-	int idx, off;
-	u16 key;
-
-	nft_set_ext_prepare(&tmpl);
-	nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
-
-	for (idx = 0; idx < priv->bitmap_size; idx++) {
-		for (off = 0; off < BITS_PER_BYTE; off += 2) {
-			if (iter->count < iter->skip)
-				goto cont;
-
-			if (!nft_bitmap_active(priv->bitmap, idx, off,
-					       iter->genmask))
-				goto cont;
-
-			ext = kzalloc(tmpl.len, GFP_KERNEL);
-			if (!ext) {
-				iter->err = -ENOMEM;
-				return;
-			}
-			nft_set_ext_init(ext, &tmpl);
-			key = ((idx * BITS_PER_BYTE) + off) >> 1;
-			memcpy(nft_set_ext_key(ext), &key, set->klen);
-
-			elem.priv = ext;
-			iter->err = iter->fn(ctx, set, iter, &elem);
-
-			/* On set flush, this dummy extension object is released
-			 * from the commit/abort path.
-			 */
-			if (!iter->flush)
-				kfree(ext);
-
-			if (iter->err < 0)
-				return;
+
+	list_for_each_entry_rcu(be, &priv->list, head) {
+		if (iter->count < iter->skip)
+			goto cont;
+		if (!nft_set_elem_active(&be->ext, iter->genmask))
+			goto cont;
+
+		elem.priv = be;
+
+		iter->err = iter->fn(ctx, set, iter, &elem);
+
+		if (iter->err < 0)
+			return;
 cont:
-			iter->count++;
-		}
+		iter->count++;
 	}
 }
 
@@ -258,6 +249,7 @@ static int nft_bitmap_init(const struct nft_set *set,
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
 
+	INIT_LIST_HEAD(&priv->list);
 	priv->bitmap_size = nft_bitmap_size(set->klen);
 
 	return 0;
@@ -283,6 +275,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
 
 static struct nft_set_ops nft_bitmap_ops __read_mostly = {
 	.privsize	= nft_bitmap_privsize,
+	.elemsize	= offsetof(struct nft_bitmap_elem, ext),
 	.estimate	= nft_bitmap_estimate,
 	.init		= nft_bitmap_init,
 	.destroy	= nft_bitmap_destroy,
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 5f652720fc78..8ec086b6b56b 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -352,7 +352,7 @@ static int nft_hash_init(const struct nft_set *set,
 
 static void nft_hash_elem_destroy(void *ptr, void *arg)
 {
-	nft_set_elem_destroy((const struct nft_set *)arg, ptr, true);
+	nft_set_elem_destroy(arg, ptr, true);
 }
 
 static void nft_hash_destroy(const struct nft_set *set)
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 78dfbf9588b3..e97e2fb53f0a 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -18,9 +18,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
-static DEFINE_SPINLOCK(nft_rbtree_lock);
-
 struct nft_rbtree {
+	rwlock_t		lock;
 	struct rb_root		root;
 };
 
@@ -44,14 +43,14 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
 static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			      const u32 *key, const struct nft_set_ext **ext)
 {
-	const struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;
 	u8 genmask = nft_genmask_cur(net);
 	const struct rb_node *parent;
 	const void *this;
 	int d;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	read_lock_bh(&priv->lock);
 	parent = priv->root.rb_node;
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
@@ -75,7 +74,7 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			}
 			if (nft_rbtree_interval_end(rbe))
 				goto out;
-			spin_unlock_bh(&nft_rbtree_lock);
+			read_unlock_bh(&priv->lock);
 
 			*ext = &rbe->ext;
 			return true;
@@ -85,12 +84,12 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
 	    !nft_rbtree_interval_end(interval)) {
-		spin_unlock_bh(&nft_rbtree_lock);
+		read_unlock_bh(&priv->lock);
 		*ext = &interval->ext;
 		return true;
 	}
 out:
-	spin_unlock_bh(&nft_rbtree_lock);
+	read_unlock_bh(&priv->lock);
 	return false;
 }
 
@@ -140,12 +139,13 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			     const struct nft_set_elem *elem,
 			     struct nft_set_ext **ext)
 {
+	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe = elem->priv;
 	int err;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	write_lock_bh(&priv->lock);
 	err = __nft_rbtree_insert(net, set, rbe, ext);
-	spin_unlock_bh(&nft_rbtree_lock);
+	write_unlock_bh(&priv->lock);
 
 	return err;
 }
@@ -157,9 +157,9 @@ static void nft_rbtree_remove(const struct net *net,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe = elem->priv;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	write_lock_bh(&priv->lock);
 	rb_erase(&rbe->node, &priv->root);
-	spin_unlock_bh(&nft_rbtree_lock);
+	write_unlock_bh(&priv->lock);
 }
 
 static void nft_rbtree_activate(const struct net *net,
@@ -224,12 +224,12 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 			    struct nft_set *set,
 			    struct nft_set_iter *iter)
 {
-	const struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
 	struct nft_set_elem elem;
 	struct rb_node *node;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	read_lock_bh(&priv->lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 
@@ -242,13 +242,13 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0) {
-			spin_unlock_bh(&nft_rbtree_lock);
+			read_unlock_bh(&priv->lock);
 			return;
 		}
 cont:
 		iter->count++;
 	}
-	spin_unlock_bh(&nft_rbtree_lock);
+	read_unlock_bh(&priv->lock);
 }
 
 static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
@@ -262,6 +262,7 @@ static int nft_rbtree_init(const struct nft_set *set,
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 
+	rwlock_init(&priv->lock);
 	priv->root = RB_ROOT;
 	return 0;
 }
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index b008db0184b8..3cbe1bcf6a74 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -26,11 +26,12 @@ static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct)
 	if (skb->_nfct != 0)
 		return XT_CONTINUE;
 
-	/* special case the untracked ct : we want the percpu object */
-	if (!ct)
-		ct = nf_ct_untracked_get();
-	atomic_inc(&ct->ct_general.use);
-	nf_ct_set(skb, ct, IP_CT_NEW);
+	if (ct) {
+		atomic_inc(&ct->ct_general.use);
+		nf_ct_set(skb, ct, IP_CT_NEW);
+	} else {
+		nf_ct_set(skb, ct, IP_CT_UNTRACKED);
+	}
 
 	return XT_CONTINUE;
 }
@@ -335,7 +336,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
 	struct nf_conn *ct = info->ct;
 	struct nf_conn_help *help;
 
-	if (ct && !nf_ct_is_untracked(ct)) {
+	if (ct) {
 		help = nfct_help(ct);
 		if (help)
 			module_put(help->helper->me);
@@ -412,8 +413,7 @@ notrack_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	if (skb->_nfct != 0)
 		return XT_CONTINUE;
 
-	nf_ct_set(skb, nf_ct_untracked_get(), IP_CT_NEW);
-	nf_conntrack_get(skb_nfct(skb));
+	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 
 	return XT_CONTINUE;
 }
diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c
index 02afaf48a729..60e6dbe12460 100644
--- a/net/netfilter/xt_HMARK.c
+++ b/net/netfilter/xt_HMARK.c
@@ -84,7 +84,7 @@ hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t,
 	struct nf_conntrack_tuple *otuple;
 	struct nf_conntrack_tuple *rtuple;
 
-	if (ct == NULL || nf_ct_is_untracked(ct))
+	if (ct == NULL)
 		return -1;
 
 	otuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 27241a767f17..c64aca611ac5 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -104,7 +104,7 @@ tcpmss_mangle_packet(struct sk_buff *skb,
 	tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
 	tcp_hdrlen = tcph->doff * 4;
 
-	if (len < tcp_hdrlen)
+	if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr))
 		return -1;
 
 	if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
@@ -152,6 +152,10 @@ tcpmss_mangle_packet(struct sk_buff *skb,
 	if (len > tcp_hdrlen)
 		return 0;
 
+	/* tcph->doff has 4 bits, do not wrap it to 0 */
+	if (tcp_hdrlen >= 15 * 4)
+		return 0;
+
 	/*
 	 * MSS Option not found ?! add it..
 	 */
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 80cb7babeb64..df7f1df00330 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -393,7 +393,8 @@ tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
 
 	rcu_read_lock();
 	indev = __in6_dev_get(skb->dev);
-	if (indev)
+	if (indev) {
+		read_lock_bh(&indev->lock);
 		list_for_each_entry(ifa, &indev->addr_list, if_list) {
 			if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
 				continue;
@@ -401,6 +402,8 @@ tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
 			laddr = &ifa->addr;
 			break;
 		}
+		read_unlock_bh(&indev->lock);
+	}
 	rcu_read_unlock();
 
 	return laddr ? laddr : daddr;
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 9a9884a39c0e..57ef175dfbfa 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -121,9 +121,6 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	if (ct == NULL)
 		return false;
 
-	if (nf_ct_is_untracked(ct))
-		return false;
-
 	if (ct->master)
 		hash = xt_cluster_hash(ct->master, info);
 	else
diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c
index 7827128d5a95..23372879e6e3 100644
--- a/net/netfilter/xt_connlabel.c
+++ b/net/netfilter/xt_connlabel.c
@@ -29,7 +29,7 @@ connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	bool invert = info->options & XT_CONNLABEL_OP_INVERT;
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL || nf_ct_is_untracked(ct))
+	if (ct == NULL)
 		return invert;
 
 	labels = nf_ct_labels_find(ct);
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 9935d5029b0e..ec377cc6a369 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -44,7 +44,7 @@ connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	u_int32_t newmark;
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL || nf_ct_is_untracked(ct))
+	if (ct == NULL)
 		return XT_CONTINUE;
 
 	switch (info->mode) {
@@ -97,7 +97,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	const struct nf_conn *ct;
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL || nf_ct_is_untracked(ct))
+	if (ct == NULL)
 		return false;
 
 	return ((ct->mark & info->mask) == info->mark) ^ info->invert;
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index c0fb217bc649..39cf1d019240 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -172,12 +172,11 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
 
 	ct = nf_ct_get(skb, &ctinfo);
 
-	if (ct) {
-		if (nf_ct_is_untracked(ct))
-			statebit = XT_CONNTRACK_STATE_UNTRACKED;
-		else
-			statebit = XT_CONNTRACK_STATE_BIT(ctinfo);
-	} else
+	if (ct)
+		statebit = XT_CONNTRACK_STATE_BIT(ctinfo);
+	else if (ctinfo == IP_CT_UNTRACKED)
+		statebit = XT_CONNTRACK_STATE_UNTRACKED;
+	else
 		statebit = XT_CONNTRACK_STATE_INVALID;
 
 	if (info->match_flags & XT_CONNTRACK_STATE) {
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 2a6dfe8b74d3..762e1874f28b 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -119,7 +119,7 @@ static int
 cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision)
 {
 	if (revision == 1) {
-		struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from;
+		struct hashlimit_cfg1 *cfg = from;
 
 		to->mode = cfg->mode;
 		to->avg = cfg->avg;
@@ -895,7 +895,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos)
 static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct xt_hashlimit_htable *htable = s->private;
-	unsigned int *bucket = (unsigned int *)v;
+	unsigned int *bucket = v;
 
 	*pos = ++(*bucket);
 	if (*pos >= htable->cfg.size) {
@@ -909,7 +909,7 @@ static void dl_seq_stop(struct seq_file *s, void *v)
 	__releases(htable->lock)
 {
 	struct xt_hashlimit_htable *htable = s->private;
-	unsigned int *bucket = (unsigned int *)v;
+	unsigned int *bucket = v;
 
 	if (!IS_ERR(bucket))
 		kfree(bucket);
@@ -980,7 +980,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
 static int dl_seq_show_v1(struct seq_file *s, void *v)
 {
 	struct xt_hashlimit_htable *htable = s->private;
-	unsigned int *bucket = (unsigned int *)v;
+	unsigned int *bucket = v;
 	struct dsthash_ent *ent;
 
 	if (!hlist_empty(&htable->hash[*bucket])) {
@@ -994,7 +994,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v)
 static int dl_seq_show(struct seq_file *s, void *v)
 {
 	struct xt_hashlimit_htable *htable = s->private;
-	unsigned int *bucket = (unsigned int *)v;
+	unsigned int *bucket = v;
 	struct dsthash_ent *ent;
 
 	if (!hlist_empty(&htable->hash[*bucket])) {
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
index 0fdc89064488..42540d26c2b8 100644
--- a/net/netfilter/xt_ipvs.c
+++ b/net/netfilter/xt_ipvs.c
@@ -116,7 +116,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-		if (ct == NULL || nf_ct_is_untracked(ct)) {
+		if (ct == NULL) {
 			match = false;
 			goto out_put_cp;
 		}
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index dab962df1787..d27b5f1ea619 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -18,6 +18,7 @@
 #include <linux/netfilter/xt_limit.h>
 
 struct xt_limit_priv {
+	spinlock_t lock;
 	unsigned long prev;
 	uint32_t credit;
 };
@@ -32,8 +33,6 @@ MODULE_ALIAS("ip6t_limit");
  * see net/sched/sch_tbf.c in the linux source tree
  */
 
-static DEFINE_SPINLOCK(limit_lock);
-
 /* Rusty: This is my (non-mathematically-inclined) understanding of
    this algorithm.  The `average rate' in jiffies becomes your initial
    amount of credit `credit' and the most credit you can ever have
@@ -72,7 +71,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	struct xt_limit_priv *priv = r->master;
 	unsigned long now = jiffies;
 
-	spin_lock_bh(&limit_lock);
+	spin_lock_bh(&priv->lock);
 	priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY;
 	if (priv->credit > r->credit_cap)
 		priv->credit = r->credit_cap;
@@ -80,11 +79,11 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	if (priv->credit >= r->cost) {
 		/* We're not limited. */
 		priv->credit -= r->cost;
-		spin_unlock_bh(&limit_lock);
+		spin_unlock_bh(&priv->lock);
 		return true;
 	}
 
-	spin_unlock_bh(&limit_lock);
+	spin_unlock_bh(&priv->lock);
 	return false;
 }
 
@@ -126,6 +125,8 @@ static int limit_mt_check(const struct xt_mtchk_param *par)
 		r->credit_cap = priv->credit; /* Credits full. */
 		r->cost = user2credits(r->avg);
 	}
+	spin_lock_init(&priv->lock);
+
 	return 0;
 }
 
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 1d89a4eaf841..37d581a31cff 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -532,7 +532,7 @@ static int recent_seq_show(struct seq_file *seq, void *v)
 			   &e->addr.in6, e->ttl, e->stamps[i], e->index);
 	for (i = 0; i < e->nstamps; i++)
 		seq_printf(seq, "%s %lu", i ? "," : "", e->stamps[i]);
-	seq_printf(seq, "\n");
+	seq_putc(seq, '\n');
 	return 0;
 }
 
diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c
index 5746a33789a5..5fbd79194d21 100644
--- a/net/netfilter/xt_state.c
+++ b/net/netfilter/xt_state.c
@@ -28,14 +28,13 @@ state_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	unsigned int statebit;
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-	if (!ct)
+	if (ct)
+		statebit = XT_STATE_BIT(ctinfo);
+	else if (ctinfo == IP_CT_UNTRACKED)
+		statebit = XT_STATE_UNTRACKED;
+	else
 		statebit = XT_STATE_INVALID;
-	else {
-		if (nf_ct_is_untracked(ct))
-			statebit = XT_STATE_UNTRACKED;
-		else
-			statebit = XT_STATE_BIT(ctinfo);
-	}
+
 	return (sinfo->statemask & statebit);
 }
 
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 4149d3e63589..9aacf2da3d98 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -101,7 +101,7 @@ static int netlbl_cipsov4_add_common(struct genl_info *info,
 
 	if (nla_validate_nested(info->attrs[NLBL_CIPSOV4_A_TAGLST],
 				NLBL_CIPSOV4_A_MAX,
-				netlbl_cipsov4_genl_policy) != 0)
+				netlbl_cipsov4_genl_policy, NULL) != 0)
 		return -EINVAL;
 
 	nla_for_each_nested(nla, info->attrs[NLBL_CIPSOV4_A_TAGLST], nla_rem)
@@ -148,7 +148,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 
 	if (nla_validate_nested(info->attrs[NLBL_CIPSOV4_A_MLSLVLLST],
 				NLBL_CIPSOV4_A_MAX,
-				netlbl_cipsov4_genl_policy) != 0)
+				netlbl_cipsov4_genl_policy, NULL) != 0)
 		return -EINVAL;
 
 	doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL);
@@ -170,10 +170,10 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 			    info->attrs[NLBL_CIPSOV4_A_MLSLVLLST],
 			    nla_a_rem)
 		if (nla_type(nla_a) == NLBL_CIPSOV4_A_MLSLVL) {
-			if (nla_validate_nested(nla_a,
-					    NLBL_CIPSOV4_A_MAX,
-					    netlbl_cipsov4_genl_policy) != 0)
-					goto add_std_failure;
+			if (nla_validate_nested(nla_a, NLBL_CIPSOV4_A_MAX,
+						netlbl_cipsov4_genl_policy,
+						NULL) != 0)
+				goto add_std_failure;
 			nla_for_each_nested(nla_b, nla_a, nla_b_rem)
 				switch (nla_type(nla_b)) {
 				case NLBL_CIPSOV4_A_MLSLVLLOC:
@@ -236,7 +236,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 	if (info->attrs[NLBL_CIPSOV4_A_MLSCATLST]) {
 		if (nla_validate_nested(info->attrs[NLBL_CIPSOV4_A_MLSCATLST],
 					NLBL_CIPSOV4_A_MAX,
-					netlbl_cipsov4_genl_policy) != 0)
+					netlbl_cipsov4_genl_policy, NULL) != 0)
 			goto add_std_failure;
 
 		nla_for_each_nested(nla_a,
@@ -244,8 +244,9 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 				    nla_a_rem)
 			if (nla_type(nla_a) == NLBL_CIPSOV4_A_MLSCAT) {
 				if (nla_validate_nested(nla_a,
-					      NLBL_CIPSOV4_A_MAX,
-					      netlbl_cipsov4_genl_policy) != 0)
+							NLBL_CIPSOV4_A_MAX,
+							netlbl_cipsov4_genl_policy,
+							NULL) != 0)
 					goto add_std_failure;
 				nla_for_each_nested(nla_b, nla_a, nla_b_rem)
 					switch (nla_type(nla_b)) {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7b73c7c161a9..ee841f00a6ec 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -78,14 +78,6 @@ struct listeners {
 /* state bits */
 #define NETLINK_S_CONGESTED		0x0
 
-/* flags */
-#define NETLINK_F_KERNEL_SOCKET		0x1
-#define NETLINK_F_RECV_PKTINFO		0x2
-#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
-#define NETLINK_F_RECV_NO_ENOBUFS	0x8
-#define NETLINK_F_LISTEN_ALL_NSID	0x10
-#define NETLINK_F_CAP_ACK		0x20
-
 static inline int netlink_is_kernel(struct sock *sk)
 {
 	return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
@@ -96,6 +88,44 @@ EXPORT_SYMBOL_GPL(nl_table);
 
 static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
 
+static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS];
+
+static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = {
+	"nlk_cb_mutex-ROUTE",
+	"nlk_cb_mutex-1",
+	"nlk_cb_mutex-USERSOCK",
+	"nlk_cb_mutex-FIREWALL",
+	"nlk_cb_mutex-SOCK_DIAG",
+	"nlk_cb_mutex-NFLOG",
+	"nlk_cb_mutex-XFRM",
+	"nlk_cb_mutex-SELINUX",
+	"nlk_cb_mutex-ISCSI",
+	"nlk_cb_mutex-AUDIT",
+	"nlk_cb_mutex-FIB_LOOKUP",
+	"nlk_cb_mutex-CONNECTOR",
+	"nlk_cb_mutex-NETFILTER",
+	"nlk_cb_mutex-IP6_FW",
+	"nlk_cb_mutex-DNRTMSG",
+	"nlk_cb_mutex-KOBJECT_UEVENT",
+	"nlk_cb_mutex-GENERIC",
+	"nlk_cb_mutex-17",
+	"nlk_cb_mutex-SCSITRANSPORT",
+	"nlk_cb_mutex-ECRYPTFS",
+	"nlk_cb_mutex-RDMA",
+	"nlk_cb_mutex-CRYPTO",
+	"nlk_cb_mutex-SMC",
+	"nlk_cb_mutex-23",
+	"nlk_cb_mutex-24",
+	"nlk_cb_mutex-25",
+	"nlk_cb_mutex-26",
+	"nlk_cb_mutex-27",
+	"nlk_cb_mutex-28",
+	"nlk_cb_mutex-29",
+	"nlk_cb_mutex-30",
+	"nlk_cb_mutex-31",
+	"nlk_cb_mutex-MAX_LINKS"
+};
+
 static int netlink_dump(struct sock *sk);
 static void netlink_skb_destructor(struct sk_buff *skb);
 
@@ -585,6 +615,9 @@ static int __netlink_create(struct net *net, struct socket *sock,
 	} else {
 		nlk->cb_mutex = &nlk->cb_def_mutex;
 		mutex_init(nlk->cb_mutex);
+		lockdep_set_class_and_name(nlk->cb_mutex,
+					   nlk_cb_mutex_keys + protocol,
+					   nlk_cb_mutex_key_strings[protocol]);
 	}
 	init_waitqueue_head(&nlk->wait);
 
@@ -1619,6 +1652,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			nlk->flags &= ~NETLINK_F_CAP_ACK;
 		err = 0;
 		break;
+	case NETLINK_EXT_ACK:
+		if (val)
+			nlk->flags |= NETLINK_F_EXT_ACK;
+		else
+			nlk->flags &= ~NETLINK_F_EXT_ACK;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1703,6 +1743,15 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 			return -EFAULT;
 		err = 0;
 		break;
+	case NETLINK_EXT_ACK:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_F_EXT_ACK ? 1 : 0;
+		if (put_user(len, optlen) || put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2234,21 +2283,44 @@ error_free:
 }
 EXPORT_SYMBOL(__netlink_dump_start);
 
-void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
+void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
+		 const struct netlink_ext_ack *extack)
 {
 	struct sk_buff *skb;
 	struct nlmsghdr *rep;
 	struct nlmsgerr *errmsg;
 	size_t payload = sizeof(*errmsg);
+	size_t tlvlen = 0;
 	struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk);
+	unsigned int flags = 0;
 
 	/* Error messages get the original request appened, unless the user
-	 * requests to cap the error message.
+	 * requests to cap the error message, and get extra error data if
+	 * requested.
 	 */
-	if (!(nlk->flags & NETLINK_F_CAP_ACK) && err)
-		payload += nlmsg_len(nlh);
+	if (err) {
+		if (!(nlk->flags & NETLINK_F_CAP_ACK))
+			payload += nlmsg_len(nlh);
+		else
+			flags |= NLM_F_CAPPED;
+		if (nlk->flags & NETLINK_F_EXT_ACK && extack) {
+			if (extack->_msg)
+				tlvlen += nla_total_size(strlen(extack->_msg) + 1);
+			if (extack->bad_attr)
+				tlvlen += nla_total_size(sizeof(u32));
+		}
+	} else {
+		flags |= NLM_F_CAPPED;
 
-	skb = nlmsg_new(payload, GFP_KERNEL);
+		if (nlk->flags & NETLINK_F_EXT_ACK &&
+		    extack && extack->cookie_len)
+			tlvlen += nla_total_size(extack->cookie_len);
+	}
+
+	if (tlvlen)
+		flags |= NLM_F_ACK_TLVS;
+
+	skb = nlmsg_new(payload + tlvlen, GFP_KERNEL);
 	if (!skb) {
 		struct sock *sk;
 
@@ -2264,17 +2336,42 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 	}
 
 	rep = __nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-			  NLMSG_ERROR, payload, 0);
+			  NLMSG_ERROR, payload, flags);
 	errmsg = nlmsg_data(rep);
 	errmsg->error = err;
 	memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh));
+
+	if (nlk->flags & NETLINK_F_EXT_ACK && extack) {
+		if (err) {
+			if (extack->_msg)
+				WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG,
+						       extack->_msg));
+			if (extack->bad_attr &&
+			    !WARN_ON((u8 *)extack->bad_attr < in_skb->data ||
+				     (u8 *)extack->bad_attr >= in_skb->data +
+							       in_skb->len))
+				WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS,
+						    (u8 *)extack->bad_attr -
+						    in_skb->data));
+		} else {
+			if (extack->cookie_len)
+				WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
+						extack->cookie_len,
+						extack->cookie));
+		}
+	}
+
+	nlmsg_end(skb, rep);
+
 	netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT);
 }
 EXPORT_SYMBOL(netlink_ack);
 
 int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
-						     struct nlmsghdr *))
+						   struct nlmsghdr *,
+						   struct netlink_ext_ack *))
 {
+	struct netlink_ext_ack extack = {};
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2295,13 +2392,13 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
 		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
 			goto ack;
 
-		err = cb(skb, nlh);
+		err = cb(skb, nlh, &extack);
 		if (err == -EINTR)
 			goto skip;
 
 ack:
 		if (nlh->nlmsg_flags & NLM_F_ACK || err)
-			netlink_ack(skb, nlh, err);
+			netlink_ack(skb, nlh, err, &extack);
 
 skip:
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 4fdb38318977..3490f2430532 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -6,6 +6,15 @@
 #include <linux/workqueue.h>
 #include <net/sock.h>
 
+/* flags */
+#define NETLINK_F_KERNEL_SOCKET		0x1
+#define NETLINK_F_RECV_PKTINFO		0x2
+#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
+#define NETLINK_F_RECV_NO_ENOBUFS	0x8
+#define NETLINK_F_LISTEN_ALL_NSID	0x10
+#define NETLINK_F_CAP_ACK		0x20
+#define NETLINK_F_EXT_ACK		0x40
+
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
 #define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index a5546249fb10..8faa20b4d457 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -19,6 +19,27 @@ static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
 		       nlk->groups);
 }
 
+static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	u32 flags = 0;
+
+	if (nlk->cb_running)
+		flags |= NDIAG_FLAG_CB_RUNNING;
+	if (nlk->flags & NETLINK_F_RECV_PKTINFO)
+		flags |= NDIAG_FLAG_PKTINFO;
+	if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
+		flags |= NDIAG_FLAG_BROADCAST_ERROR;
+	if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)
+		flags |= NDIAG_FLAG_NO_ENOBUFS;
+	if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+		flags |= NDIAG_FLAG_LISTEN_ALL_NSID;
+	if (nlk->flags & NETLINK_F_CAP_ACK)
+		flags |= NDIAG_FLAG_CAP_ACK;
+
+	return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags);
+}
+
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			struct netlink_diag_req *req,
 			u32 portid, u32 seq, u32 flags, int sk_ino)
@@ -52,6 +73,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
+	if ((req->ndiag_show & NDIAG_SHOW_FLAGS) &&
+	    sk_diag_put_flags(sk, skb))
+		goto out_nlmsg_trim;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index fb6e10fdb217..10f8b4cff40a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -497,7 +497,8 @@ static int genl_lock_done(struct netlink_callback *cb)
 
 static int genl_family_rcv_msg(const struct genl_family *family,
 			       struct sk_buff *skb,
-			       struct nlmsghdr *nlh)
+			       struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
 {
 	const struct genl_ops *ops;
 	struct net *net = sock_net(skb->sk);
@@ -573,7 +574,7 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 
 	if (attrbuf) {
 		err = nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
-				  ops->policy);
+				  ops->policy, extack);
 		if (err < 0)
 			goto out;
 	}
@@ -584,6 +585,7 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 	info.genlhdr = nlmsg_data(nlh);
 	info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN;
 	info.attrs = attrbuf;
+	info.extack = extack;
 	genl_info_net_set(&info, net);
 	memset(&info.user_ptr, 0, sizeof(info.user_ptr));
 
@@ -605,7 +607,8 @@ out:
 	return err;
 }
 
-static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
 {
 	const struct genl_family *family;
 	int err;
@@ -617,7 +620,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!family->parallel_ops)
 		genl_lock();
 
-	err = genl_family_rcv_msg(family, skb, nlh);
+	err = genl_family_rcv_msg(family, skb, nlh, extack);
 
 	if (!family->parallel_ops)
 		genl_unlock();
@@ -783,8 +786,10 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
 
 		if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid,
 				   cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				   skb, CTRL_CMD_NEWFAMILY) < 0)
+				   skb, CTRL_CMD_NEWFAMILY) < 0) {
+			n--;
 			break;
+		}
 	}
 
 	cb->args[0] = n;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 4bbf4526b885..ebf16f7f9089 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -765,7 +765,8 @@ out_release:
 	return err;
 }
 
-static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
+static int nr_accept(struct socket *sock, struct socket *newsock, int flags,
+		     bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 879885b31cce..2ffb18e73df6 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent,
 }
 
 static int llcp_sock_accept(struct socket *sock, struct socket *newsock,
-			    int flags)
+			    int flags, bool kern)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *new_sk;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 03f3d5c7beb8..6b0850e63e09 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -119,7 +119,8 @@ static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb)
 	u32 idx;
 
 	rc = nlmsg_parse(cb->nlh, GENL_HDRLEN + nfc_genl_family.hdrsize,
-			 attrbuf, nfc_genl_family.maxattr, nfc_genl_policy);
+			 attrbuf, nfc_genl_family.maxattr, nfc_genl_policy,
+			 NULL);
 	if (rc < 0)
 		return ERR_PTR(rc);
 
@@ -303,6 +304,17 @@ free_msg:
 	return -EMSGSIZE;
 }
 
+static int nfc_genl_setup_device_added(struct nfc_dev *dev, struct sk_buff *msg)
+{
+	if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) ||
+	    nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) ||
+	    nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) ||
+	    nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up) ||
+	    nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode))
+		return -1;
+	return 0;
+}
+
 int nfc_genl_device_added(struct nfc_dev *dev)
 {
 	struct sk_buff *msg;
@@ -317,10 +329,7 @@ int nfc_genl_device_added(struct nfc_dev *dev)
 	if (!hdr)
 		goto free_msg;
 
-	if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) ||
-	    nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) ||
-	    nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) ||
-	    nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up))
+	if (nfc_genl_setup_device_added(dev, msg))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -596,11 +605,7 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev,
 	if (cb)
 		genl_dump_check_consistent(cb, hdr, &nfc_genl_family);
 
-	if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) ||
-	    nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) ||
-	    nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) ||
-	    nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up) ||
-	    nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode))
+	if (nfc_genl_setup_device_added(dev, msg))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -918,7 +923,7 @@ static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info)
 	rc = nfc_activate_target(dev, target_idx, protocol);
 
 	nfc_put_device(dev);
-	return 0;
+	return rc;
 }
 
 static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info)
@@ -1161,7 +1166,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 
 	nla_for_each_nested(attr, info->attrs[NFC_ATTR_LLC_SDP], rem) {
 		rc = nla_parse_nested(sdp_attrs, NFC_SDP_ATTR_MAX, attr,
-				      nfc_sdp_genl_policy);
+				      nfc_sdp_genl_policy, info->extack);
 
 		if (rc != 0) {
 			rc = -EINVAL;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index c82301ce3fff..e4610676299b 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2014 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -44,13 +44,10 @@
 #include "conntrack.h"
 #include "vport.h"
 
-static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
-			      struct sw_flow_key *key,
-			      const struct nlattr *attr, int len);
-
 struct deferred_action {
 	struct sk_buff *skb;
 	const struct nlattr *actions;
+	int actions_len;
 
 	/* Store pkt_key clone when creating deferred action. */
 	struct sw_flow_key pkt_key;
@@ -82,14 +79,31 @@ struct action_fifo {
 	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
 };
 
-struct recirc_keys {
+struct action_flow_keys {
 	struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
 };
 
 static struct action_fifo __percpu *action_fifos;
-static struct recirc_keys __percpu *recirc_keys;
+static struct action_flow_keys __percpu *flow_keys;
 static DEFINE_PER_CPU(int, exec_actions_level);
 
+/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
+ * space. Return NULL if out of key spaces.
+ */
+static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
+{
+	struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
+	int level = this_cpu_read(exec_actions_level);
+	struct sw_flow_key *key = NULL;
+
+	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
+		key = &keys->key[level - 1];
+		*key = *key_;
+	}
+
+	return key;
+}
+
 static void action_fifo_init(struct action_fifo *fifo)
 {
 	fifo->head = 0;
@@ -119,8 +133,9 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
 
 /* Return true if fifo is not full */
 static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
-						    const struct sw_flow_key *key,
-						    const struct nlattr *attr)
+				    const struct sw_flow_key *key,
+				    const struct nlattr *actions,
+				    const int actions_len)
 {
 	struct action_fifo *fifo;
 	struct deferred_action *da;
@@ -129,7 +144,8 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 	da = action_fifo_put(fifo);
 	if (da) {
 		da->skb = skb;
-		da->actions = attr;
+		da->actions = actions;
+		da->actions_len = actions_len;
 		da->pkt_key = *key;
 	}
 
@@ -146,6 +162,12 @@ static bool is_flow_key_valid(const struct sw_flow_key *key)
 	return !(key->mac_proto & SW_FLOW_KEY_INVALID);
 }
 
+static int clone_execute(struct datapath *dp, struct sk_buff *skb,
+			 struct sw_flow_key *key,
+			 u32 recirc_id,
+			 const struct nlattr *actions, int len,
+			 bool last, bool clone_flow_key);
+
 static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
 {
@@ -908,72 +930,35 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
+/* When 'last' is true, sample() should always consume the 'skb'.
+ * Otherwise, sample() should keep 'skb' intact regardless what
+ * actions are executed within sample().
+ */
 static int sample(struct datapath *dp, struct sk_buff *skb,
 		  struct sw_flow_key *key, const struct nlattr *attr,
-		  const struct nlattr *actions, int actions_len)
+		  bool last)
 {
-	const struct nlattr *acts_list = NULL;
-	const struct nlattr *a;
-	int rem;
-	u32 cutlen = 0;
-
-	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
-		 a = nla_next(a, &rem)) {
-		u32 probability;
-
-		switch (nla_type(a)) {
-		case OVS_SAMPLE_ATTR_PROBABILITY:
-			probability = nla_get_u32(a);
-			if (!probability || prandom_u32() > probability)
-				return 0;
-			break;
-
-		case OVS_SAMPLE_ATTR_ACTIONS:
-			acts_list = a;
-			break;
-		}
-	}
-
-	rem = nla_len(acts_list);
-	a = nla_data(acts_list);
-
-	/* Actions list is empty, do nothing */
-	if (unlikely(!rem))
+	struct nlattr *actions;
+	struct nlattr *sample_arg;
+	int rem = nla_len(attr);
+	const struct sample_arg *arg;
+	bool clone_flow_key;
+
+	/* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
+	sample_arg = nla_data(attr);
+	arg = nla_data(sample_arg);
+	actions = nla_next(sample_arg, &rem);
+
+	if ((arg->probability != U32_MAX) &&
+	    (!arg->probability || prandom_u32() > arg->probability)) {
+		if (last)
+			consume_skb(skb);
 		return 0;
-
-	/* The only known usage of sample action is having a single user-space
-	 * action, or having a truncate action followed by a single user-space
-	 * action. Treat this usage as a special case.
-	 * The output_userspace() should clone the skb to be sent to the
-	 * user space. This skb will be consumed by its caller.
-	 */
-	if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) {
-		struct ovs_action_trunc *trunc = nla_data(a);
-
-		if (skb->len > trunc->max_len)
-			cutlen = skb->len - trunc->max_len;
-
-		a = nla_next(a, &rem);
 	}
 
-	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
-		   nla_is_last(a, rem)))
-		return output_userspace(dp, skb, key, a, actions,
-					actions_len, cutlen);
-
-	skb = skb_clone(skb, GFP_ATOMIC);
-	if (!skb)
-		/* Skip the sample action when out of memory. */
-		return 0;
-
-	if (!add_deferred_actions(skb, key, a)) {
-		if (net_ratelimit())
-			pr_warn("%s: deferred actions limit reached, dropping sample action\n",
-				ovs_dp_name(dp));
-
-		kfree_skb(skb);
-	}
-	return 0;
+	clone_flow_key = !arg->exec;
+	return clone_execute(dp, skb, key, 0, actions, rem, last,
+			     clone_flow_key);
 }
 
 static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
@@ -1084,10 +1069,9 @@ static int execute_masked_set_action(struct sk_buff *skb,
 
 static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 			  struct sw_flow_key *key,
-			  const struct nlattr *a, int rem)
+			  const struct nlattr *a, bool last)
 {
-	struct deferred_action *da;
-	int level;
+	u32 recirc_id;
 
 	if (!is_flow_key_valid(key)) {
 		int err;
@@ -1098,43 +1082,8 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 	}
 	BUG_ON(!is_flow_key_valid(key));
 
-	if (!nla_is_last(a, rem)) {
-		/* Recirc action is the not the last action
-		 * of the action list, need to clone the skb.
-		 */
-		skb = skb_clone(skb, GFP_ATOMIC);
-
-		/* Skip the recirc action when out of memory, but
-		 * continue on with the rest of the action list.
-		 */
-		if (!skb)
-			return 0;
-	}
-
-	level = this_cpu_read(exec_actions_level);
-	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
-		struct recirc_keys *rks = this_cpu_ptr(recirc_keys);
-		struct sw_flow_key *recirc_key = &rks->key[level - 1];
-
-		*recirc_key = *key;
-		recirc_key->recirc_id = nla_get_u32(a);
-		ovs_dp_process_packet(skb, recirc_key);
-
-		return 0;
-	}
-
-	da = add_deferred_actions(skb, key, NULL);
-	if (da) {
-		da->pkt_key.recirc_id = nla_get_u32(a);
-	} else {
-		kfree_skb(skb);
-
-		if (net_ratelimit())
-			pr_warn("%s: deferred action limit reached, drop recirc action\n",
-				ovs_dp_name(dp));
-	}
-
-	return 0;
+	recirc_id = nla_get_u32(a);
+	return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
 }
 
 /* Execute a list of actions against 'skb'. */
@@ -1206,9 +1155,11 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = pop_vlan(skb, key);
 			break;
 
-		case OVS_ACTION_ATTR_RECIRC:
-			err = execute_recirc(dp, skb, key, a, rem);
-			if (nla_is_last(a, rem)) {
+		case OVS_ACTION_ATTR_RECIRC: {
+			bool last = nla_is_last(a, rem);
+
+			err = execute_recirc(dp, skb, key, a, last);
+			if (last) {
 				/* If this is the last action, the skb has
 				 * been consumed or freed.
 				 * Return immediately.
@@ -1216,6 +1167,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 				return err;
 			}
 			break;
+		}
 
 		case OVS_ACTION_ATTR_SET:
 			err = execute_set_action(skb, key, nla_data(a));
@@ -1226,9 +1178,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = execute_masked_set_action(skb, key, nla_data(a));
 			break;
 
-		case OVS_ACTION_ATTR_SAMPLE:
-			err = sample(dp, skb, key, a, attr, len);
+		case OVS_ACTION_ATTR_SAMPLE: {
+			bool last = nla_is_last(a, rem);
+
+			err = sample(dp, skb, key, a, last);
+			if (last)
+				return err;
+
 			break;
+		}
 
 		case OVS_ACTION_ATTR_CT:
 			if (!is_flow_key_valid(key)) {
@@ -1264,6 +1222,79 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	return 0;
 }
 
+/* Execute the actions on the clone of the packet. The effect of the
+ * execution does not affect the original 'skb' nor the original 'key'.
+ *
+ * The execution may be deferred in case the actions can not be executed
+ * immediately.
+ */
+static int clone_execute(struct datapath *dp, struct sk_buff *skb,
+			 struct sw_flow_key *key, u32 recirc_id,
+			 const struct nlattr *actions, int len,
+			 bool last, bool clone_flow_key)
+{
+	struct deferred_action *da;
+	struct sw_flow_key *clone;
+
+	skb = last ? skb : skb_clone(skb, GFP_ATOMIC);
+	if (!skb) {
+		/* Out of memory, skip this action.
+		 */
+		return 0;
+	}
+
+	/* When clone_flow_key is false, the 'key' will not be change
+	 * by the actions, then the 'key' can be used directly.
+	 * Otherwise, try to clone key from the next recursion level of
+	 * 'flow_keys'. If clone is successful, execute the actions
+	 * without deferring.
+	 */
+	clone = clone_flow_key ? clone_key(key) : key;
+	if (clone) {
+		int err = 0;
+
+		if (actions) { /* Sample action */
+			if (clone_flow_key)
+				__this_cpu_inc(exec_actions_level);
+
+			err = do_execute_actions(dp, skb, clone,
+						 actions, len);
+
+			if (clone_flow_key)
+				__this_cpu_dec(exec_actions_level);
+		} else { /* Recirc action */
+			clone->recirc_id = recirc_id;
+			ovs_dp_process_packet(skb, clone);
+		}
+		return err;
+	}
+
+	/* Out of 'flow_keys' space. Defer actions */
+	da = add_deferred_actions(skb, key, actions, len);
+	if (da) {
+		if (!actions) { /* Recirc action */
+			key = &da->pkt_key;
+			key->recirc_id = recirc_id;
+		}
+	} else {
+		/* Out of per CPU action FIFO space. Drop the 'skb' and
+		 * log an error.
+		 */
+		kfree_skb(skb);
+
+		if (net_ratelimit()) {
+			if (actions) { /* Sample action */
+				pr_warn("%s: deferred action limit reached, drop sample action\n",
+					ovs_dp_name(dp));
+			} else {  /* Recirc action */
+				pr_warn("%s: deferred action limit reached, drop recirc action\n",
+					ovs_dp_name(dp));
+			}
+		}
+	}
+	return 0;
+}
+
 static void process_deferred_actions(struct datapath *dp)
 {
 	struct action_fifo *fifo = this_cpu_ptr(action_fifos);
@@ -1278,10 +1309,10 @@ static void process_deferred_actions(struct datapath *dp)
 		struct sk_buff *skb = da->skb;
 		struct sw_flow_key *key = &da->pkt_key;
 		const struct nlattr *actions = da->actions;
+		int actions_len = da->actions_len;
 
 		if (actions)
-			do_execute_actions(dp, skb, key, actions,
-					   nla_len(actions));
+			do_execute_actions(dp, skb, key, actions, actions_len);
 		else
 			ovs_dp_process_packet(skb, key);
 	} while (!action_fifo_is_empty(fifo));
@@ -1323,8 +1354,8 @@ int action_fifos_init(void)
 	if (!action_fifos)
 		return -ENOMEM;
 
-	recirc_keys = alloc_percpu(struct recirc_keys);
-	if (!recirc_keys) {
+	flow_keys = alloc_percpu(struct action_flow_keys);
+	if (!flow_keys) {
 		free_percpu(action_fifos);
 		return -ENOMEM;
 	}
@@ -1335,5 +1366,5 @@ int action_fifos_init(void)
 void action_fifos_exit(void)
 {
 	free_percpu(action_fifos);
-	free_percpu(recirc_keys);
+	free_percpu(flow_keys);
 }
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e0a87776a010..42a95919df09 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -66,7 +66,9 @@ struct ovs_conntrack_info {
 	u8 commit : 1;
 	u8 nat : 3;                 /* enum ovs_ct_nat */
 	u8 force : 1;
+	u8 have_eventmask : 1;
 	u16 family;
+	u32 eventmask;              /* Mask of 1 << IPCT_*. */
 	struct md_mark mark;
 	struct md_labels labels;
 #ifdef CONFIG_NF_NAT_NEEDED
@@ -373,7 +375,7 @@ static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key,
 	}
 
 	/* Labels are included in the IPCTNL_MSG_CT_NEW event only if the
-	 * IPCT_LABEL bit it set in the event cache.
+	 * IPCT_LABEL bit is set in the event cache.
 	 */
 	nf_conntrack_event_cache(IPCT_LABEL, ct);
 
@@ -643,8 +645,8 @@ static bool skb_nfct_cached(struct net *net,
 		 */
 		if (nf_ct_is_confirmed(ct))
 			nf_ct_delete(ct, 0, 0);
-		else
-			nf_conntrack_put(&ct->ct_general);
+
+		nf_conntrack_put(&ct->ct_general);
 		nf_ct_set(skb, NULL, 0);
 		return false;
 	}
@@ -795,11 +797,6 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	enum nf_nat_manip_type maniptype;
 	int err;
 
-	if (nf_ct_is_untracked(ct)) {
-		/* A NAT action may only be performed on tracked packets. */
-		return NF_ACCEPT;
-	}
-
 	/* Add NAT extension if not confirmed yet. */
 	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
 		return NF_ACCEPT;   /* Can't NAT. */
@@ -1007,6 +1004,20 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 	if (!ct)
 		return 0;
 
+	/* Set the conntrack event mask if given.  NEW and DELETE events have
+	 * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener
+	 * typically would receive many kinds of updates.  Setting the event
+	 * mask allows those events to be filtered.  The set event mask will
+	 * remain in effect for the lifetime of the connection unless changed
+	 * by a further CT action with both the commit flag and the eventmask
+	 * option. */
+	if (info->have_eventmask) {
+		struct nf_conntrack_ecache *cache = nf_ct_ecache_find(ct);
+
+		if (cache)
+			cache->ctmask = info->eventmask;
+	}
+
 	/* Apply changes before confirming the connection so that the initial
 	 * conntrack NEW netlink event carries the values given in the CT
 	 * action.
@@ -1238,6 +1249,8 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
 	/* NAT length is checked when parsing the nested attributes. */
 	[OVS_CT_ATTR_NAT]	= { .minlen = 0, .maxlen = INT_MAX },
 #endif
+	[OVS_CT_ATTR_EVENTMASK]	= { .minlen = sizeof(u32),
+				    .maxlen = sizeof(u32) },
 };
 
 static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
@@ -1316,6 +1329,11 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 			break;
 		}
 #endif
+		case OVS_CT_ATTR_EVENTMASK:
+			info->have_eventmask = true;
+			info->eventmask = nla_get_u32(a);
+			break;
+
 		default:
 			OVS_NLERR(log, "Unknown conntrack attr (%d)",
 				  type);
@@ -1515,6 +1533,10 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 				   ct_info->helper->name))
 			return -EMSGSIZE;
 	}
+	if (ct_info->have_eventmask &&
+	    nla_put_u32(skb, OVS_CT_ATTR_EVENTMASK, ct_info->eventmask))
+		return -EMSGSIZE;
+
 #ifdef CONFIG_NF_NAT_NEEDED
 	if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
 		return -EMSGSIZE;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 9c62b6325f7a..7b17da9a94a0 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1353,7 +1353,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int err;
 
 	err = genlmsg_parse(cb->nlh, &dp_flow_genl_family, a,
-			    OVS_FLOW_ATTR_MAX, flow_policy);
+			    OVS_FLOW_ATTR_MAX, flow_policy, NULL);
 	if (err)
 		return err;
 	ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 1c6e9377436d..da931bdef8a7 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -34,8 +34,6 @@
 #define DP_MAX_PORTS           USHRT_MAX
 #define DP_VPORT_HASH_BUCKETS  1024
 
-#define SAMPLE_ACTION_DEPTH 3
-
 /**
  * struct dp_stats_percpu - per-cpu packet processing statistics for a given
  * datapath.
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d4bb8eb63f2..3f76cb765e5b 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -527,7 +527,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 	/* Link layer. */
 	clear_vlan(key);
-	if (key->mac_proto == MAC_PROTO_NONE) {
+	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
 		if (unlikely(eth_type_vlan(skb->protocol)))
 			return -EINVAL;
 
@@ -745,7 +745,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	return key_extract(skb, key);
+	int res;
+
+	res = key_extract(skb, key);
+	if (!res)
+		key->mac_proto &= ~SW_FLOW_KEY_INVALID;
+
+	return res;
 }
 
 static int key_extract_mac_proto(struct sk_buff *skb)
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 6f5fa50f716d..7e1d8a2afa63 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2014 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -59,6 +59,39 @@ struct ovs_len_tbl {
 #define OVS_ATTR_NESTED -1
 #define OVS_ATTR_VARIABLE -2
 
+static bool actions_may_change_flow(const struct nlattr *actions)
+{
+	struct nlattr *nla;
+	int rem;
+
+	nla_for_each_nested(nla, actions, rem) {
+		u16 action = nla_type(nla);
+
+		switch (action) {
+		case OVS_ACTION_ATTR_OUTPUT:
+		case OVS_ACTION_ATTR_RECIRC:
+		case OVS_ACTION_ATTR_TRUNC:
+		case OVS_ACTION_ATTR_USERSPACE:
+			break;
+
+		case OVS_ACTION_ATTR_CT:
+		case OVS_ACTION_ATTR_HASH:
+		case OVS_ACTION_ATTR_POP_ETH:
+		case OVS_ACTION_ATTR_POP_MPLS:
+		case OVS_ACTION_ATTR_POP_VLAN:
+		case OVS_ACTION_ATTR_PUSH_ETH:
+		case OVS_ACTION_ATTR_PUSH_MPLS:
+		case OVS_ACTION_ATTR_PUSH_VLAN:
+		case OVS_ACTION_ATTR_SAMPLE:
+		case OVS_ACTION_ATTR_SET:
+		case OVS_ACTION_ATTR_SET_MASKED:
+		default:
+			return true;
+		}
+	}
+	return false;
+}
+
 static void update_range(struct sw_flow_match *match,
 			 size_t offset, size_t size, bool is_mask)
 {
@@ -604,7 +637,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			ipv4 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
-			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
 					nla_get_in6_addr(a), is_mask);
 			ipv6 = true;
 			break;
@@ -665,6 +698,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_VXLAN_OPT;
 			opts_type = type;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_PAD:
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
@@ -2021,18 +2056,20 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
-				  int depth, struct sw_flow_actions **sfa,
+				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci, bool log);
 
 static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
-				    const struct sw_flow_key *key, int depth,
+				    const struct sw_flow_key *key,
 				    struct sw_flow_actions **sfa,
-				    __be16 eth_type, __be16 vlan_tci, bool log)
+				    __be16 eth_type, __be16 vlan_tci,
+				    bool log, bool last)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
 	const struct nlattr *a;
-	int rem, start, err, st_acts;
+	int rem, start, err;
+	struct sample_arg arg;
 
 	memset(attrs, 0, sizeof(attrs));
 	nla_for_each_nested(a, attr, rem) {
@@ -2056,20 +2093,32 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
 	if (start < 0)
 		return start;
-	err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
-				 nla_data(probability), sizeof(u32), log);
+
+	/* When both skb and flow may be changed, put the sample
+	 * into a deferred fifo. On the other hand, if only skb
+	 * may be modified, the actions can be executed in place.
+	 *
+	 * Do this analysis at the flow installation time.
+	 * Set 'clone_action->exec' to true if the actions can be
+	 * executed without being deferred.
+	 *
+	 * If the sample is the last action, it can always be excuted
+	 * rather than deferred.
+	 */
+	arg.exec = last || !actions_may_change_flow(actions);
+	arg.probability = nla_get_u32(probability);
+
+	err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg),
+				 log);
 	if (err)
 		return err;
-	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
-	if (st_acts < 0)
-		return st_acts;
 
-	err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa,
+	err = __ovs_nla_copy_actions(net, actions, key, sfa,
 				     eth_type, vlan_tci, log);
+
 	if (err)
 		return err;
 
-	add_nested_action_end(*sfa, st_acts);
 	add_nested_action_end(*sfa, start);
 
 	return 0;
@@ -2378,8 +2427,8 @@ static int validate_userspace(const struct nlattr *attr)
 	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
 	int error;
 
-	error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
-				 attr, userspace_policy);
+	error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX, attr,
+				 userspace_policy, NULL);
 	if (error)
 		return error;
 
@@ -2406,16 +2455,13 @@ static int copy_action(const struct nlattr *from,
 
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
-				  int depth, struct sw_flow_actions **sfa,
+				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci, bool log)
 {
 	u8 mac_proto = ovs_key_mac_proto(key);
 	const struct nlattr *a;
 	int rem, err;
 
-	if (depth >= SAMPLE_ACTION_DEPTH)
-		return -EOVERFLOW;
-
 	nla_for_each_nested(a, attr, rem) {
 		/* Expected argument lengths, (u32)-1 for variable length. */
 		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -2553,13 +2599,17 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return err;
 			break;
 
-		case OVS_ACTION_ATTR_SAMPLE:
-			err = validate_and_copy_sample(net, a, key, depth, sfa,
-						       eth_type, vlan_tci, log);
+		case OVS_ACTION_ATTR_SAMPLE: {
+			bool last = nla_is_last(a, rem);
+
+			err = validate_and_copy_sample(net, a, key, sfa,
+						       eth_type, vlan_tci,
+						       log, last);
 			if (err)
 				return err;
 			skip_copy = true;
 			break;
+		}
 
 		case OVS_ACTION_ATTR_CT:
 			err = ovs_ct_copy_action(net, a, key, sfa, log);
@@ -2613,7 +2663,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		return PTR_ERR(*sfa);
 
 	(*sfa)->orig_len = nla_len(attr);
-	err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type,
+	err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
 				     key->eth.vlan.tci, log);
 	if (err)
 		ovs_nla_free_flow_actions(*sfa);
@@ -2621,39 +2671,44 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 	return err;
 }
 
-static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
+static int sample_action_to_attr(const struct nlattr *attr,
+				 struct sk_buff *skb)
 {
-	const struct nlattr *a;
-	struct nlattr *start;
-	int err = 0, rem;
+	struct nlattr *start, *ac_start = NULL, *sample_arg;
+	int err = 0, rem = nla_len(attr);
+	const struct sample_arg *arg;
+	struct nlattr *actions;
 
 	start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
 	if (!start)
 		return -EMSGSIZE;
 
-	nla_for_each_nested(a, attr, rem) {
-		int type = nla_type(a);
-		struct nlattr *st_sample;
+	sample_arg = nla_data(attr);
+	arg = nla_data(sample_arg);
+	actions = nla_next(sample_arg, &rem);
 
-		switch (type) {
-		case OVS_SAMPLE_ATTR_PROBABILITY:
-			if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY,
-				    sizeof(u32), nla_data(a)))
-				return -EMSGSIZE;
-			break;
-		case OVS_SAMPLE_ATTR_ACTIONS:
-			st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
-			if (!st_sample)
-				return -EMSGSIZE;
-			err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
-			if (err)
-				return err;
-			nla_nest_end(skb, st_sample);
-			break;
-		}
+	if (nla_put_u32(skb, OVS_SAMPLE_ATTR_PROBABILITY, arg->probability)) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
+	if (!ac_start) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	err = ovs_nla_put_actions(actions, rem, skb);
+
+out:
+	if (err) {
+		nla_nest_cancel(skb, ac_start);
+		nla_nest_cancel(skb, start);
+	} else {
+		nla_nest_end(skb, ac_start);
+		nla_nest_end(skb, start);
 	}
 
-	nla_nest_end(skb, start);
 	return err;
 }
 
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 7eb955e453e6..869acb3b3d3f 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -70,7 +70,8 @@ static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr,
 	if (nla_len(attr) < sizeof(struct nlattr))
 		return -EINVAL;
 
-	err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy);
+	err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a0dbe7ca8f72..f4001763134d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1496,6 +1496,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 DEFINE_MUTEX(fanout_mutex);
 EXPORT_SYMBOL_GPL(fanout_mutex);
 static LIST_HEAD(fanout_list);
+static u16 fanout_next_id;
 
 static void __fanout_link(struct sock *sk, struct packet_sock *po)
 {
@@ -1629,6 +1630,36 @@ static void fanout_release_data(struct packet_fanout *f)
 	};
 }
 
+static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id)
+{
+	struct packet_fanout *f;
+
+	list_for_each_entry(f, &fanout_list, list) {
+		if (f->id == candidate_id &&
+		    read_pnet(&f->net) == sock_net(sk)) {
+			return false;
+		}
+	}
+	return true;
+}
+
+static bool fanout_find_new_id(struct sock *sk, u16 *new_id)
+{
+	u16 id = fanout_next_id;
+
+	do {
+		if (__fanout_id_is_free(sk, id)) {
+			*new_id = id;
+			fanout_next_id = id + 1;
+			return true;
+		}
+
+		id++;
+	} while (id != fanout_next_id);
+
+	return false;
+}
+
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
 	struct packet_rollover *rollover = NULL;
@@ -1676,6 +1707,19 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		po->rollover = rollover;
 	}
 
+	if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) {
+		if (id != 0) {
+			err = -EINVAL;
+			goto out;
+		}
+		if (!fanout_find_new_id(sk, &id)) {
+			err = -ENOMEM;
+			goto out;
+		}
+		/* ephemeral flag for the first socket in the group: drop it */
+		flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8);
+	}
+
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -3665,6 +3709,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
+		if (val > INT_MAX)
+			return -EINVAL;
 		po->tp_reserve = val;
 		return 0;
 	}
@@ -3834,6 +3880,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	case PACKET_HDRLEN:
 		if (len > sizeof(int))
 			len = sizeof(int);
+		if (len < sizeof(int))
+			return -EINVAL;
 		if (copy_from_user(&val, optval, len))
 			return -EFAULT;
 		switch (val) {
@@ -4193,8 +4241,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
 		if (po->tp_version >= TPACKET_V3 &&
-		    (int)(req->tp_block_size -
-			  BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+		    req->tp_block_size <=
+			  BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
 			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
@@ -4205,6 +4253,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
+		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
 			goto out;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 222bedcd9575..e81537991ddf 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout)
 	sock_put(sk);
 }
 
-static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
+static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
+				    bool kern)
 {
 	struct pep_sock *pn = pep_sk(sk), *newpn;
 	struct sock *newsk = NULL;
@@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
 	}
 
 	/* Create a new to-be-accepted sock */
-	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0);
+	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot,
+			 kern);
 	if (!newsk) {
 		pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
 		err = -ENOBUFS;
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index bc5ee5fbe6ae..45b3af3080d8 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -61,7 +61,8 @@ static const struct nla_policy ifa_phonet_policy[IFA_MAX+1] = {
 	[IFA_LOCAL] = { .type = NLA_U8 },
 };
 
-static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+		     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -78,7 +79,8 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_phonet_policy);
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_phonet_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
@@ -226,7 +228,8 @@ static const struct nla_policy rtm_phonet_policy[RTA_MAX+1] = {
 	[RTA_OIF] = { .type = NLA_U32 },
 };
 
-static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[RTA_MAX+1];
@@ -243,7 +246,8 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_phonet_policy);
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_phonet_policy,
+			  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index a6c8da3ee893..64634e3ec2fc 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -305,7 +305,7 @@ out:
 }
 
 static int pn_socket_accept(struct socket *sock, struct socket *newsock,
-				int flags)
+			    int flags, bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *newsk;
@@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock,
 	if (unlikely(sk->sk_state != TCP_LISTEN))
 		return -EINVAL;
 
-	newsk = sk->sk_prot->accept(sk, flags, &err);
+	newsk = sk->sk_prot->accept(sk, flags, &err, kern);
 	if (!newsk)
 		return err;
 
diff --git a/net/qrtr/Kconfig b/net/qrtr/Kconfig
index b83c6807a5ae..326fd97444f5 100644
--- a/net/qrtr/Kconfig
+++ b/net/qrtr/Kconfig
@@ -16,7 +16,7 @@ if QRTR
 
 config QRTR_SMD
 	tristate "SMD IPC Router channels"
-	depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+	depends on RPMSG || (COMPILE_TEST && RPMSG=n)
 	---help---
 	  Say Y here to support SMD based ipcrouter channels.  SMD is the
 	  most common transport for IPC Router.
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index ae5ac175b2be..a9a8c7d5a4a9 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -658,7 +658,9 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	}
 
 	if (plen != len) {
-		skb_pad(skb, plen - len);
+		rc = skb_pad(skb, plen - len);
+		if (rc)
+			goto out_node;
 		skb_put(skb, plen - len);
 	}
 
@@ -943,7 +945,8 @@ static const struct nla_policy qrtr_policy[IFA_MAX + 1] = {
 	[IFA_LOCAL] = { .type = NLA_U32 },
 };
 
-static int qrtr_addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int qrtr_addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[IFA_MAX + 1];
 	struct ifaddrmsg *ifm;
@@ -957,7 +960,7 @@ static int qrtr_addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ASSERT_RTNL();
 
-	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, qrtr_policy);
+	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, qrtr_policy, extack);
 	if (rc < 0)
 		return rc;
 
diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c
index 0d11132b3370..50615d5efac1 100644
--- a/net/qrtr/smd.c
+++ b/net/qrtr/smd.c
@@ -14,21 +14,21 @@
 
 #include <linux/module.h>
 #include <linux/skbuff.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 
 #include "qrtr.h"
 
 struct qrtr_smd_dev {
 	struct qrtr_endpoint ep;
-	struct qcom_smd_channel *channel;
+	struct rpmsg_endpoint *channel;
 	struct device *dev;
 };
 
 /* from smd to qrtr */
-static int qcom_smd_qrtr_callback(struct qcom_smd_channel *channel,
-				  const void *data, size_t len)
+static int qcom_smd_qrtr_callback(struct rpmsg_device *rpdev,
+				  void *data, int len, void *priv, u32 addr)
 {
-	struct qrtr_smd_dev *qdev = qcom_smd_get_drvdata(channel);
+	struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev);
 	int rc;
 
 	if (!qdev)
@@ -54,7 +54,7 @@ static int qcom_smd_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
 	if (rc)
 		goto out;
 
-	rc = qcom_smd_send(qdev->channel, skb->data, skb->len);
+	rc = rpmsg_send(qdev->channel, skb->data, skb->len);
 
 out:
 	if (rc)
@@ -64,57 +64,55 @@ out:
 	return rc;
 }
 
-static int qcom_smd_qrtr_probe(struct qcom_smd_device *sdev)
+static int qcom_smd_qrtr_probe(struct rpmsg_device *rpdev)
 {
 	struct qrtr_smd_dev *qdev;
 	int rc;
 
-	qdev = devm_kzalloc(&sdev->dev, sizeof(*qdev), GFP_KERNEL);
+	qdev = devm_kzalloc(&rpdev->dev, sizeof(*qdev), GFP_KERNEL);
 	if (!qdev)
 		return -ENOMEM;
 
-	qdev->channel = sdev->channel;
-	qdev->dev = &sdev->dev;
+	qdev->channel = rpdev->ept;
+	qdev->dev = &rpdev->dev;
 	qdev->ep.xmit = qcom_smd_qrtr_send;
 
 	rc = qrtr_endpoint_register(&qdev->ep, QRTR_EP_NID_AUTO);
 	if (rc)
 		return rc;
 
-	qcom_smd_set_drvdata(sdev->channel, qdev);
-	dev_set_drvdata(&sdev->dev, qdev);
+	dev_set_drvdata(&rpdev->dev, qdev);
 
-	dev_dbg(&sdev->dev, "Qualcomm SMD QRTR driver probed\n");
+	dev_dbg(&rpdev->dev, "Qualcomm SMD QRTR driver probed\n");
 
 	return 0;
 }
 
-static void qcom_smd_qrtr_remove(struct qcom_smd_device *sdev)
+static void qcom_smd_qrtr_remove(struct rpmsg_device *rpdev)
 {
-	struct qrtr_smd_dev *qdev = dev_get_drvdata(&sdev->dev);
+	struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev);
 
 	qrtr_endpoint_unregister(&qdev->ep);
 
-	dev_set_drvdata(&sdev->dev, NULL);
+	dev_set_drvdata(&rpdev->dev, NULL);
 }
 
-static const struct qcom_smd_id qcom_smd_qrtr_smd_match[] = {
+static const struct rpmsg_device_id qcom_smd_qrtr_smd_match[] = {
 	{ "IPCRTR" },
 	{}
 };
 
-static struct qcom_smd_driver qcom_smd_qrtr_driver = {
+static struct rpmsg_driver qcom_smd_qrtr_driver = {
 	.probe = qcom_smd_qrtr_probe,
 	.remove = qcom_smd_qrtr_remove,
 	.callback = qcom_smd_qrtr_callback,
-	.smd_match_table = qcom_smd_qrtr_smd_match,
-	.driver = {
+	.id_table = qcom_smd_qrtr_smd_match,
+	.drv = {
 		.name = "qcom_smd_qrtr",
-		.owner = THIS_MODULE,
 	},
 };
 
-module_qcom_smd_driver(qcom_smd_qrtr_driver);
+module_rpmsg_driver(qcom_smd_qrtr_driver);
 
 MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver");
 MODULE_LICENSE("GPL v2");
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 0e04dcceb1d4..6a5ebdea7d2e 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -333,11 +333,19 @@ void rds_conn_shutdown(struct rds_conn_path *cp)
 		rds_conn_path_reset(cp);
 
 		if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING,
+					      RDS_CONN_DOWN) &&
+		    !rds_conn_path_transition(cp, RDS_CONN_ERROR,
 					      RDS_CONN_DOWN)) {
 			/* This can happen - eg when we're in the middle of tearing
 			 * down the connection, and someone unloads the rds module.
-			 * Quite reproduceable with loopback connections.
+			 * Quite reproducible with loopback connections.
 			 * Mostly harmless.
+			 *
+			 * Note that this also happens with rds-tcp because
+			 * we could have triggered rds_conn_path_drop in irq
+			 * mode from rds_tcp_state change on the receipt of
+			 * a FIN, thus we need to recheck for RDS_CONN_ERROR
+			 * here.
 			 */
 			rds_conn_path_error(cp, "%s: failed to transition "
 					    "to state DOWN, current state "
@@ -429,6 +437,7 @@ void rds_conn_destroy(struct rds_connection *conn)
 	 */
 	rds_cong_remove_conn(conn);
 
+	put_net(conn->c_net);
 	kmem_cache_free(rds_conn_slab, conn);
 
 	spin_lock_irqsave(&rds_conn_lock, flags);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index ce3775abc6e7..80fb6f63e768 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -442,7 +442,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 		ic->i_send_cq = NULL;
 		ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
 		rdsdebug("ib_create_cq send failed: %d\n", ret);
-		goto out;
+		goto rds_ibdev_out;
 	}
 
 	ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
@@ -456,19 +456,19 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 		ic->i_recv_cq = NULL;
 		ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
 		rdsdebug("ib_create_cq recv failed: %d\n", ret);
-		goto out;
+		goto send_cq_out;
 	}
 
 	ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
 	if (ret) {
 		rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
-		goto out;
+		goto recv_cq_out;
 	}
 
 	ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
 	if (ret) {
 		rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
-		goto out;
+		goto recv_cq_out;
 	}
 
 	/* XXX negotiate max send/recv with remote? */
@@ -494,7 +494,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
 	if (ret) {
 		rdsdebug("rdma_create_qp failed: %d\n", ret);
-		goto out;
+		goto recv_cq_out;
 	}
 
 	ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
@@ -504,7 +504,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	if (!ic->i_send_hdrs) {
 		ret = -ENOMEM;
 		rdsdebug("ib_dma_alloc_coherent send failed\n");
-		goto out;
+		goto qp_out;
 	}
 
 	ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
@@ -514,7 +514,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	if (!ic->i_recv_hdrs) {
 		ret = -ENOMEM;
 		rdsdebug("ib_dma_alloc_coherent recv failed\n");
-		goto out;
+		goto send_hdrs_dma_out;
 	}
 
 	ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
@@ -522,7 +522,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	if (!ic->i_ack) {
 		ret = -ENOMEM;
 		rdsdebug("ib_dma_alloc_coherent ack failed\n");
-		goto out;
+		goto recv_hdrs_dma_out;
 	}
 
 	ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
@@ -530,7 +530,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	if (!ic->i_sends) {
 		ret = -ENOMEM;
 		rdsdebug("send allocation failed\n");
-		goto out;
+		goto ack_dma_out;
 	}
 
 	ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
@@ -538,7 +538,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	if (!ic->i_recvs) {
 		ret = -ENOMEM;
 		rdsdebug("recv allocation failed\n");
-		goto out;
+		goto sends_out;
 	}
 
 	rds_ib_recv_init_ack(ic);
@@ -546,8 +546,33 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
 		 ic->i_send_cq, ic->i_recv_cq);
 
-out:
+	return ret;
+
+sends_out:
+	vfree(ic->i_sends);
+ack_dma_out:
+	ib_dma_free_coherent(dev, sizeof(struct rds_header),
+			     ic->i_ack, ic->i_ack_dma);
+recv_hdrs_dma_out:
+	ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr *
+					sizeof(struct rds_header),
+					ic->i_recv_hdrs, ic->i_recv_hdrs_dma);
+send_hdrs_dma_out:
+	ib_dma_free_coherent(dev, ic->i_send_ring.w_nr *
+					sizeof(struct rds_header),
+					ic->i_send_hdrs, ic->i_send_hdrs_dma);
+qp_out:
+	rdma_destroy_qp(ic->i_cm_id);
+recv_cq_out:
+	if (!ib_destroy_cq(ic->i_recv_cq))
+		ic->i_recv_cq = NULL;
+send_cq_out:
+	if (!ib_destroy_cq(ic->i_send_cq))
+		ic->i_send_cq = NULL;
+rds_ibdev_out:
+	rds_ib_remove_conn(rds_ibdev, conn);
 	rds_ib_dev_put(rds_ibdev);
+
 	return ret;
 }
 
@@ -677,9 +702,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 		event->param.conn.initiator_depth);
 
 	/* rdma_accept() calls rdma_reject() internally if it fails */
-	err = rdma_accept(cm_id, &conn_param);
-	if (err)
-		rds_ib_conn_error(conn, "rdma_accept failed (%d)\n", err);
+	if (rdma_accept(cm_id, &conn_param))
+		rds_ib_conn_error(conn, "rdma_accept failed\n");
 
 out:
 	if (conn)
diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index 4fe8f4fec4ee..86ef907067bb 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -78,17 +78,15 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
 	return ibmr;
 
 out_no_cigar:
-	if (ibmr) {
-		if (fmr->fmr)
-			ib_dealloc_fmr(fmr->fmr);
-		kfree(ibmr);
-	}
+	kfree(ibmr);
 	atomic_dec(&pool->item_count);
+
 	return ERR_PTR(err);
 }
 
-int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
-		   struct scatterlist *sg, unsigned int nents)
+static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev,
+			  struct rds_ib_mr *ibmr, struct scatterlist *sg,
+			  unsigned int nents)
 {
 	struct ib_device *dev = rds_ibdev->dev;
 	struct rds_ib_fmr *fmr = &ibmr->u.fmr;
@@ -114,29 +112,39 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
 		u64 dma_addr = ib_sg_dma_address(dev, &scat[i]);
 
 		if (dma_addr & ~PAGE_MASK) {
-			if (i > 0)
+			if (i > 0) {
+				ib_dma_unmap_sg(dev, sg, nents,
+						DMA_BIDIRECTIONAL);
 				return -EINVAL;
-			else
+			} else {
 				++page_cnt;
+			}
 		}
 		if ((dma_addr + dma_len) & ~PAGE_MASK) {
-			if (i < sg_dma_len - 1)
+			if (i < sg_dma_len - 1) {
+				ib_dma_unmap_sg(dev, sg, nents,
+						DMA_BIDIRECTIONAL);
 				return -EINVAL;
-			else
+			} else {
 				++page_cnt;
+			}
 		}
 
 		len += dma_len;
 	}
 
 	page_cnt += len >> PAGE_SHIFT;
-	if (page_cnt > ibmr->pool->fmr_attr.max_pages)
+	if (page_cnt > ibmr->pool->fmr_attr.max_pages) {
+		ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
 		return -EINVAL;
+	}
 
 	dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC,
 				 rdsibdev_to_node(rds_ibdev));
-	if (!dma_pages)
+	if (!dma_pages) {
+		ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
 		return -ENOMEM;
+	}
 
 	page_cnt = 0;
 	for (i = 0; i < sg_dma_len; ++i) {
@@ -149,8 +157,10 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
 	}
 
 	ret = ib_map_phys_fmr(fmr->fmr, dma_pages, page_cnt, io_addr);
-	if (ret)
+	if (ret) {
+		ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
 		goto out;
+	}
 
 	/* Success - we successfully remapped the MR, so we can
 	 * safely tear down the old mapping.
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 5d6e98a79a5e..0ea4ab017a8c 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -125,8 +125,6 @@ void rds_ib_mr_exit(void);
 void __rds_ib_teardown_mr(struct rds_ib_mr *);
 void rds_ib_teardown_mr(struct rds_ib_mr *);
 struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *, int);
-int rds_ib_map_fmr(struct rds_ib_device *, struct rds_ib_mr *,
-		   struct scatterlist *, unsigned int);
 struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *);
 int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *, int, struct rds_ib_mr **);
 struct rds_ib_mr *rds_ib_reg_fmr(struct rds_ib_device *, struct scatterlist *,
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 39518ef7af4d..82d38ccf5e8b 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -147,7 +147,7 @@ struct rds_connection {
 
 	/* Protocol version */
 	unsigned int		c_version;
-	possible_net_t		c_net;
+	struct net		*c_net;
 
 	struct list_head	c_map_item;
 	unsigned long		c_map_queued;
@@ -162,13 +162,13 @@ struct rds_connection {
 static inline
 struct net *rds_conn_net(struct rds_connection *conn)
 {
-	return read_pnet(&conn->c_net);
+	return conn->c_net;
 }
 
 static inline
 void rds_conn_net_set(struct rds_connection *conn, struct net *net)
 {
-	write_pnet(&conn->c_net, net);
+	conn->c_net = get_net(net);
 }
 
 #define RDS_FLAG_CONG_BITMAP	0x01
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 8b7e7b7f2c2d..c70c32cb05f5 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -594,7 +594,6 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		goto out;
 
 	while (1) {
-		struct iov_iter save;
 		/* If there are pending notifications, do those - and nothing else */
 		if (!list_empty(&rs->rs_notify_queue)) {
 			ret = rds_notify_queue_get(rs, msg);
@@ -630,7 +629,6 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		rdsdebug("copying inc %p from %pI4:%u to user\n", inc,
 			 &inc->i_conn->c_faddr,
 			 ntohs(inc->i_hdr.h_sport));
-		save = msg->msg_iter;
 		ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter);
 		if (ret < 0)
 			break;
@@ -644,7 +642,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 			rds_inc_put(inc);
 			inc = NULL;
 			rds_stats_inc(s_recv_deliver_raced);
-			msg->msg_iter = save;
+			iov_iter_revert(&msg->msg_iter, ret);
 			continue;
 		}
 
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index a973d3b4dff0..431404dbdad1 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -84,13 +84,10 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 /* doing it this way avoids calling tcp_sk() */
 void rds_tcp_nonagle(struct socket *sock)
 {
-	mm_segment_t oldfs = get_fs();
 	int val = 1;
 
-	set_fs(KERNEL_DS);
-	sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY, (char __user *)&val,
+	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (void *)&val,
 			      sizeof(val));
-	set_fs(oldfs);
 }
 
 u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc)
@@ -484,9 +481,10 @@ static void __net_exit rds_tcp_exit_net(struct net *net)
 	 * we do need to clean up the listen socket here.
 	 */
 	if (rtn->rds_tcp_listen_sock) {
-		rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+		struct socket *lsock = rtn->rds_tcp_listen_sock;
+
 		rtn->rds_tcp_listen_sock = NULL;
-		flush_work(&rtn->rds_tcp_accept_w);
+		rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
 	}
 }
 
@@ -523,13 +521,13 @@ static void rds_tcp_kill_sock(struct net *net)
 	struct rds_tcp_connection *tc, *_tc;
 	LIST_HEAD(tmp_list);
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+	struct socket *lsock = rtn->rds_tcp_listen_sock;
 
-	rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
 	rtn->rds_tcp_listen_sock = NULL;
-	flush_work(&rtn->rds_tcp_accept_w);
+	rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
 	spin_lock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
-		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+		struct net *c_net = tc->t_cpath->cp_conn->c_net;
 
 		if (net != c_net || !tc->t_sock)
 			continue;
@@ -546,8 +544,12 @@ static void rds_tcp_kill_sock(struct net *net)
 void *rds_tcp_listen_sock_def_readable(struct net *net)
 {
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+	struct socket *lsock = rtn->rds_tcp_listen_sock;
+
+	if (!lsock)
+		return NULL;
 
-	return rtn->rds_tcp_listen_sock->sk->sk_user_data;
+	return lsock->sk->sk_user_data;
 }
 
 static int rds_tcp_dev_event(struct notifier_block *this,
@@ -584,7 +586,7 @@ static void rds_tcp_sysctl_reset(struct net *net)
 
 	spin_lock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
-		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+		struct net *c_net = tc->t_cpath->cp_conn->c_net;
 
 		if (net != c_net || !tc->t_sock)
 			continue;
@@ -638,19 +640,19 @@ static int rds_tcp_init(void)
 		goto out;
 	}
 
-	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
-	if (ret) {
-		pr_warn("could not register rds_tcp_dev_notifier\n");
+	ret = rds_tcp_recv_init();
+	if (ret)
 		goto out_slab;
-	}
 
 	ret = register_pernet_subsys(&rds_tcp_net_ops);
 	if (ret)
-		goto out_notifier;
+		goto out_recv;
 
-	ret = rds_tcp_recv_init();
-	if (ret)
+	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
+	if (ret) {
+		pr_warn("could not register rds_tcp_dev_notifier\n");
 		goto out_pernet;
+	}
 
 	rds_trans_register(&rds_tcp_transport);
 
@@ -660,9 +662,8 @@ static int rds_tcp_init(void)
 
 out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
-out_notifier:
-	if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
-		pr_warn("could not unregister rds_tcp_dev_notifier\n");
+out_recv:
+	rds_tcp_recv_exit();
 out_slab:
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 9a1cc8906576..56ea6620fcf9 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -66,7 +66,7 @@ void rds_tcp_state_change(struct sock *sk);
 
 /* tcp_listen.c */
 struct socket *rds_tcp_listen_init(struct net *);
-void rds_tcp_listen_stop(struct socket *);
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
 void rds_tcp_listen_data_ready(struct sock *sk);
 int rds_tcp_accept_one(struct socket *sock);
 int rds_tcp_keepalive(struct socket *sock);
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 67d0929c7d3d..507678853e6c 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true);
 	if (ret < 0)
 		goto out;
 
@@ -223,6 +223,9 @@ void rds_tcp_listen_data_ready(struct sock *sk)
 	 * before it has been accepted and the accepter has set up their
 	 * data_ready.. we only want to queue listen work for our listening
 	 * socket
+	 *
+	 * (*ready)() may be null if we are racing with netns delete, and
+	 * the listen socket is being torn down.
 	 */
 	if (sk->sk_state == TCP_LISTEN)
 		rds_tcp_accept_work(sk);
@@ -231,7 +234,8 @@ void rds_tcp_listen_data_ready(struct sock *sk)
 
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
-	ready(sk);
+	if (ready)
+		ready(sk);
 }
 
 struct socket *rds_tcp_listen_init(struct net *net)
@@ -271,7 +275,7 @@ out:
 	return NULL;
 }
 
-void rds_tcp_listen_stop(struct socket *sock)
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor)
 {
 	struct sock *sk;
 
@@ -292,5 +296,6 @@ void rds_tcp_listen_stop(struct socket *sock)
 
 	/* wait for accepts to stop and close the socket */
 	flush_workqueue(rds_wq);
+	flush_work(acceptor);
 	sock_release(sock);
 }
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index dcf4742083ea..52d11d7725c8 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -40,13 +40,7 @@
 
 static void rds_tcp_cork(struct socket *sock, int val)
 {
-	mm_segment_t oldfs;
-
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	sock->ops->setsockopt(sock, SOL_TCP, TCP_CORK, (char __user *)&val,
-			      sizeof(val));
-	set_fs(oldfs);
+	kernel_setsockopt(sock, SOL_TCP, TCP_CORK, (void *)&val, sizeof(val));
 }
 
 void rds_tcp_xmit_path_prepare(struct rds_conn_path *cp)
diff --git a/net/rds/threads.c b/net/rds/threads.c
index e36e333a0aa0..3e447d056d09 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -156,7 +156,7 @@ void rds_connect_worker(struct work_struct *work)
 	struct rds_connection *conn = cp->cp_conn;
 	int ret;
 
-	if (cp->cp_index > 1 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr)
+	if (cp->cp_index > 0 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr)
 		return;
 	clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
 	ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index b8a1df2c9785..4a9729257023 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -871,7 +871,8 @@ out_release:
 	return err;
 }
 
-static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rose_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 26a7b1db1361..7486926e60a8 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -740,6 +740,25 @@ static inline bool rxrpc_abort_call(const char *why, struct rxrpc_call *call,
 }
 
 /*
+ * Abort a call due to a protocol error.
+ */
+static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call,
+					struct sk_buff *skb,
+					const char *eproto_why,
+					const char *why,
+					u32 abort_code)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why);
+	return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO);
+}
+
+#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \
+	__rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \
+			     (abort_why), (abort_code))
+
+/*
  * conn_client.c
  */
 extern unsigned int rxrpc_max_client_connections;
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 0ed181f53f32..1752fcf8e8f1 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -413,11 +413,11 @@ found_service:
 
 	case RXRPC_CONN_REMOTELY_ABORTED:
 		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
-					  conn->remote_abort, ECONNABORTED);
+					  conn->remote_abort, -ECONNABORTED);
 		break;
 	case RXRPC_CONN_LOCALLY_ABORTED:
 		rxrpc_abort_call("CON", call, sp->hdr.seq,
-				 conn->local_abort, ECONNABORTED);
+				 conn->local_abort, -ECONNABORTED);
 		break;
 	default:
 		BUG();
@@ -600,7 +600,7 @@ int rxrpc_reject_call(struct rxrpc_sock *rx)
 	write_lock_bh(&call->state_lock);
 	switch (call->state) {
 	case RXRPC_CALL_SERVER_ACCEPTING:
-		__rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, ECONNABORTED);
+		__rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED);
 		abort = true;
 		/* fall through */
 	case RXRPC_CALL_COMPLETE:
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 97a17ada4431..7a77844aab16 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -386,7 +386,7 @@ recheck_state:
 
 	now = ktime_get_real();
 	if (ktime_before(call->expire_at, now)) {
-		rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, ETIME);
+		rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
 		set_bit(RXRPC_CALL_EV_ABORT, &call->events);
 		goto recheck_state;
 	}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index d79cd36987a9..47f7f4205653 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -486,7 +486,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
 		call = list_entry(rx->to_be_accepted.next,
 				  struct rxrpc_call, accept_link);
 		list_del(&call->accept_link);
-		rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, ECONNRESET);
+		rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET);
 		rxrpc_put_call(call, rxrpc_call_put);
 	}
 
@@ -494,7 +494,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
 		call = list_entry(rx->sock_calls.next,
 				  struct rxrpc_call, sock_link);
 		rxrpc_get_call(call, rxrpc_call_got);
-		rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, ECONNRESET);
+		rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET);
 		rxrpc_send_abort_packet(call);
 		rxrpc_release_call(rx, call);
 		rxrpc_put_call(call, rxrpc_call_put);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index c3be03e8d098..e8dea0d49e7f 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -550,6 +550,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 	call->cid	= conn->proto.cid | channel;
 	call->call_id	= call_id;
 
+	trace_rxrpc_connect_call(call);
 	_net("CONNECT call %08x:%08x as call %d on conn %d",
 	     call->cid, call->call_id, call->debug_id, conn->debug_id);
 
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 3f9d8d7ec632..46babcf82ce8 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -168,7 +168,7 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
  * generate a connection-level abort
  */
 static int rxrpc_abort_connection(struct rxrpc_connection *conn,
-				  u32 error, u32 abort_code)
+				  int error, u32 abort_code)
 {
 	struct rxrpc_wire_header whdr;
 	struct msghdr msg;
@@ -275,16 +275,23 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		rxrpc_conn_retransmit_call(conn, skb);
 		return 0;
 
+	case RXRPC_PACKET_TYPE_BUSY:
+		/* Just ignore BUSY packets for now. */
+		return 0;
+
 	case RXRPC_PACKET_TYPE_ABORT:
 		if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
-				  &wtmp, sizeof(wtmp)) < 0)
+				  &wtmp, sizeof(wtmp)) < 0) {
+			trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+					      tracepoint_string("bad_abort"));
 			return -EPROTO;
+		}
 		abort_code = ntohl(wtmp);
 		_proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code);
 
 		conn->state = RXRPC_CONN_REMOTELY_ABORTED;
 		rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED,
-				  abort_code, ECONNABORTED);
+				  abort_code, -ECONNABORTED);
 		return -ECONNABORTED;
 
 	case RXRPC_PACKET_TYPE_CHALLENGE:
@@ -323,7 +330,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		return 0;
 
 	default:
-		_leave(" = -EPROTO [%u]", sp->hdr.type);
+		trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+				      tracepoint_string("bad_conn_pkt"));
 		return -EPROTO;
 	}
 }
@@ -366,7 +374,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn)
 
 abort:
 	_debug("abort %d, %d", ret, abort_code);
-	rxrpc_abort_connection(conn, -ret, abort_code);
+	rxrpc_abort_connection(conn, ret, abort_code);
 	_leave(" [aborted]");
 }
 
@@ -415,9 +423,8 @@ requeue_and_leave:
 	goto out;
 
 protocol_error:
-	if (rxrpc_abort_connection(conn, -ret, abort_code) < 0)
+	if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
 		goto requeue_and_leave;
 	rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
-	_leave(" [EPROTO]");
 	goto out;
 }
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9f4cfa25af7c..45dba732a3b4 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -30,7 +30,7 @@
 static void rxrpc_proto_abort(const char *why,
 			      struct rxrpc_call *call, rxrpc_seq_t seq)
 {
-	if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, EBADMSG)) {
+	if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) {
 		set_bit(RXRPC_CALL_EV_ABORT, &call->events);
 		rxrpc_queue_call(call);
 	}
@@ -420,6 +420,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
 			     u16 skew)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	enum rxrpc_call_state state;
 	unsigned int offset = sizeof(struct rxrpc_wire_header);
 	unsigned int ix;
 	rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
@@ -434,14 +435,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
 	_proto("Rx DATA %%%u { #%u f=%02x }",
 	       sp->hdr.serial, seq, sp->hdr.flags);
 
-	if (call->state >= RXRPC_CALL_COMPLETE)
+	state = READ_ONCE(call->state);
+	if (state >= RXRPC_CALL_COMPLETE)
 		return;
 
 	/* Received data implicitly ACKs all of the request packets we sent
 	 * when we're acting as a client.
 	 */
-	if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
-	     call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
+	if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
+	     state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
 	    !rxrpc_receiving_reply(call))
 		return;
 
@@ -650,6 +652,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_peer *peer;
 	unsigned int mtu;
+	bool wake = false;
 	u32 rwind = ntohl(ackinfo->rwind);
 
 	_proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
@@ -657,9 +660,16 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 	       ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
 	       rwind, ntohl(ackinfo->jumbo_max));
 
-	if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
-		rwind = RXRPC_RXTX_BUFF_SIZE - 1;
-	call->tx_winsize = rwind;
+	if (call->tx_winsize != rwind) {
+		if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+			rwind = RXRPC_RXTX_BUFF_SIZE - 1;
+		if (rwind > call->tx_winsize)
+			wake = true;
+		trace_rxrpc_rx_rwind_change(call, sp->hdr.serial,
+					    ntohl(ackinfo->rwind), wake);
+		call->tx_winsize = rwind;
+	}
+
 	if (call->cong_ssthresh > rwind)
 		call->cong_ssthresh = rwind;
 
@@ -673,6 +683,9 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 		spin_unlock_bh(&peer->lock);
 		_net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
 	}
+
+	if (wake)
+		wake_up(&call->waitq);
 }
 
 /*
@@ -799,7 +812,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 		return rxrpc_proto_abort("AK0", call, 0);
 
 	/* Ignore ACKs unless we are or have just been transmitting. */
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
 	case RXRPC_CALL_SERVER_SEND_REPLY:
@@ -866,7 +879,7 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
 }
 
 /*
- * Process an ABORT packet.
+ * Process an ABORT packet directed at a call.
  */
 static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb)
 {
@@ -881,10 +894,12 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb)
 			  &wtmp, sizeof(wtmp)) >= 0)
 		abort_code = ntohl(wtmp);
 
+	trace_rxrpc_rx_abort(call, sp->hdr.serial, abort_code);
+
 	_proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code);
 
 	if (rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
-				      abort_code, ECONNABORTED))
+				      abort_code, -ECONNABORTED))
 		rxrpc_notify_socket(call);
 }
 
@@ -940,14 +955,14 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
 static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
 					  struct rxrpc_call *call)
 {
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_SERVER_AWAIT_ACK:
 		rxrpc_call_completed(call);
 		break;
 	case RXRPC_CALL_COMPLETE:
 		break;
 	default:
-		if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, ESHUTDOWN)) {
+		if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) {
 			set_bit(RXRPC_CALL_EV_ABORT, &call->events);
 			rxrpc_queue_call(call);
 		}
@@ -1006,8 +1021,11 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
 	struct rxrpc_wire_header whdr;
 
 	/* dig out the RxRPC connection details */
-	if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0)
+	if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) {
+		trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+				      tracepoint_string("bad_hdr"));
 		return -EBADMSG;
+	}
 
 	memset(sp, 0, sizeof(*sp));
 	sp->hdr.epoch		= ntohl(whdr.epoch);
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index 7d4375e557e6..af276f173b10 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -46,7 +46,10 @@ static int none_respond_to_challenge(struct rxrpc_connection *conn,
 				     struct sk_buff *skb,
 				     u32 *_abort_code)
 {
-	*_abort_code = RX_PROTOCOL_ERROR;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+			      tracepoint_string("chall_none"));
 	return -EPROTO;
 }
 
@@ -54,7 +57,10 @@ static int none_verify_response(struct rxrpc_connection *conn,
 				struct sk_buff *skb,
 				u32 *_abort_code)
 {
-	*_abort_code = RX_PROTOCOL_ERROR;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+	trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+			      tracepoint_string("resp_none"));
 	return -EPROTO;
 }
 
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index bf13b8470c9a..1ed9c0c2e94f 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -296,7 +296,7 @@ void rxrpc_peer_error_distributor(struct work_struct *work)
 		hlist_del_init(&call->error_link);
 		rxrpc_see_call(call);
 
-		if (rxrpc_set_call_completion(call, compl, 0, error))
+		if (rxrpc_set_call_completion(call, compl, 0, -error))
 			rxrpc_notify_socket(call);
 	}
 
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 6491ca46a03f..f9caf3b77509 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -83,11 +83,11 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg)
 		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &tmp);
 		break;
 	case RXRPC_CALL_NETWORK_ERROR:
-		tmp = call->error;
+		tmp = -call->error;
 		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &tmp);
 		break;
 	case RXRPC_CALL_LOCAL_ERROR:
-		tmp = call->error;
+		tmp = -call->error;
 		ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp);
 		break;
 	default:
@@ -527,7 +527,7 @@ try_again:
 		msg->msg_namelen = len;
 	}
 
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_SERVER_ACCEPTING:
 		ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
 		break;
@@ -640,7 +640,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 
 	mutex_lock(&call->user_mutex);
 
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_CLIENT_RECV_REPLY:
 	case RXRPC_CALL_SERVER_RECV_REQUEST:
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
@@ -682,14 +682,16 @@ out:
 	return ret;
 
 short_data:
+	trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data"));
 	ret = -EBADMSG;
 	goto out;
 excess_data:
+	trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data"));
 	ret = -EMSGSIZE;
 	goto out;
 call_complete:
 	*_abort = call->abort_code;
-	ret = -call->error;
+	ret = call->error;
 	if (call->completion == RXRPC_CALL_SUCCEEDED) {
 		ret = 1;
 		if (size > 0)
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 4374e7b9c7bf..1bb9b2ccc267 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -148,15 +148,13 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 				    u32 data_size,
 				    void *sechdr)
 {
-	struct rxrpc_skb_priv *sp;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxkad_level1_hdr hdr;
 	struct rxrpc_crypt iv;
 	struct scatterlist sg;
 	u16 check;
 
-	sp = rxrpc_skb(skb);
-
 	_enter("");
 
 	check = sp->hdr.seq ^ call->call_id;
@@ -323,6 +321,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[16];
 	struct sk_buff *trailer;
+	bool aborted;
 	u32 data_size, buf;
 	u16 check;
 	int nsg;
@@ -330,7 +329,8 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 	_enter("");
 
 	if (len < 8) {
-		rxrpc_abort_call("V1H", call, seq, RXKADSEALEDINCON, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H",
+					   RXKADSEALEDINCON);
 		goto protocol_error;
 	}
 
@@ -355,7 +355,8 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 
 	/* Extract the decrypted packet length */
 	if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) {
-		rxrpc_abort_call("XV1", call, seq, RXKADDATALEN, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1",
+					     RXKADDATALEN);
 		goto protocol_error;
 	}
 	offset += sizeof(sechdr);
@@ -368,12 +369,14 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 	check ^= seq ^ call->call_id;
 	check &= 0xffff;
 	if (check != 0) {
-		rxrpc_abort_call("V1C", call, seq, RXKADSEALEDINCON, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C",
+					     RXKADSEALEDINCON);
 		goto protocol_error;
 	}
 
 	if (data_size > len) {
-		rxrpc_abort_call("V1L", call, seq, RXKADDATALEN, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L",
+					     RXKADDATALEN);
 		goto protocol_error;
 	}
 
@@ -381,8 +384,8 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 	return 0;
 
 protocol_error:
-	rxrpc_send_abort_packet(call);
-	_leave(" = -EPROTO");
+	if (aborted)
+		rxrpc_send_abort_packet(call);
 	return -EPROTO;
 
 nomem:
@@ -403,6 +406,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	struct rxrpc_crypt iv;
 	struct scatterlist _sg[4], *sg;
 	struct sk_buff *trailer;
+	bool aborted;
 	u32 data_size, buf;
 	u16 check;
 	int nsg;
@@ -410,7 +414,8 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	_enter(",{%d}", skb->len);
 
 	if (len < 8) {
-		rxrpc_abort_call("V2H", call, seq, RXKADSEALEDINCON, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H",
+					     RXKADSEALEDINCON);
 		goto protocol_error;
 	}
 
@@ -445,7 +450,8 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 
 	/* Extract the decrypted packet length */
 	if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) {
-		rxrpc_abort_call("XV2", call, seq, RXKADDATALEN, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2",
+					     RXKADDATALEN);
 		goto protocol_error;
 	}
 	offset += sizeof(sechdr);
@@ -458,12 +464,14 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	check ^= seq ^ call->call_id;
 	check &= 0xffff;
 	if (check != 0) {
-		rxrpc_abort_call("V2C", call, seq, RXKADSEALEDINCON, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C",
+					     RXKADSEALEDINCON);
 		goto protocol_error;
 	}
 
 	if (data_size > len) {
-		rxrpc_abort_call("V2L", call, seq, RXKADDATALEN, EPROTO);
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L",
+					     RXKADDATALEN);
 		goto protocol_error;
 	}
 
@@ -471,8 +479,8 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	return 0;
 
 protocol_error:
-	rxrpc_send_abort_packet(call);
-	_leave(" = -EPROTO");
+	if (aborted)
+		rxrpc_send_abort_packet(call);
 	return -EPROTO;
 
 nomem:
@@ -491,6 +499,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg;
+	bool aborted;
 	u16 cksum;
 	u32 x, y;
 
@@ -522,10 +531,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		cksum = 1; /* zero checksums are not permitted */
 
 	if (cksum != expected_cksum) {
-		rxrpc_abort_call("VCK", call, seq, RXKADSEALEDINCON, EPROTO);
-		rxrpc_send_abort_packet(call);
-		_leave(" = -EPROTO [csum failed]");
-		return -EPROTO;
+		aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK",
+					     RXKADSEALEDINCON);
+		goto protocol_error;
 	}
 
 	switch (call->conn->params.security_level) {
@@ -538,6 +546,11 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	default:
 		return -ENOANO;
 	}
+
+protocol_error:
+	if (aborted)
+		rxrpc_send_abort_packet(call);
+	return -EPROTO;
 }
 
 /*
@@ -754,22 +767,23 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
 	struct rxkad_response resp
 		__attribute__((aligned(8))); /* must be aligned for crypto */
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	const char *eproto;
 	u32 version, nonce, min_level, abort_code;
 	int ret;
 
 	_enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key));
 
-	if (!conn->params.key) {
-		_leave(" = -EPROTO [no key]");
-		return -EPROTO;
-	}
+	eproto = tracepoint_string("chall_no_key");
+	abort_code = RX_PROTOCOL_ERROR;
+	if (!conn->params.key)
+		goto protocol_error;
 
+	abort_code = RXKADEXPIRED;
 	ret = key_validate(conn->params.key);
-	if (ret < 0) {
-		*_abort_code = RXKADEXPIRED;
-		return ret;
-	}
+	if (ret < 0)
+		goto other_error;
 
+	eproto = tracepoint_string("chall_short");
 	abort_code = RXKADPACKETSHORT;
 	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
 			  &challenge, sizeof(challenge)) < 0)
@@ -782,13 +796,15 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
 	_proto("Rx CHALLENGE %%%u { v=%u n=%u ml=%u }",
 	       sp->hdr.serial, version, nonce, min_level);
 
+	eproto = tracepoint_string("chall_ver");
 	abort_code = RXKADINCONSISTENCY;
 	if (version != RXKAD_VERSION)
 		goto protocol_error;
 
 	abort_code = RXKADLEVELFAIL;
+	ret = -EACCES;
 	if (conn->params.security_level < min_level)
-		goto protocol_error;
+		goto other_error;
 
 	token = conn->params.key->payload.data[0];
 
@@ -815,28 +831,34 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
 	return rxkad_send_response(conn, &sp->hdr, &resp, token->kad);
 
 protocol_error:
+	trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+	ret = -EPROTO;
+other_error:
 	*_abort_code = abort_code;
-	_leave(" = -EPROTO [%d]", abort_code);
-	return -EPROTO;
+	return ret;
 }
 
 /*
  * decrypt the kerberos IV ticket in the response
  */
 static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
+				struct sk_buff *skb,
 				void *ticket, size_t ticket_len,
 				struct rxrpc_crypt *_session_key,
 				time_t *_expiry,
 				u32 *_abort_code)
 {
 	struct skcipher_request *req;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_crypt iv, key;
 	struct scatterlist sg[1];
 	struct in_addr addr;
 	unsigned int life;
+	const char *eproto;
 	time_t issue, now;
 	bool little_endian;
 	int ret;
+	u32 abort_code;
 	u8 *p, *q, *name, *end;
 
 	_enter("{%d},{%x}", conn->debug_id, key_serial(conn->server_key));
@@ -847,11 +869,11 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 	if (ret < 0) {
 		switch (ret) {
 		case -EKEYEXPIRED:
-			*_abort_code = RXKADEXPIRED;
-			goto error;
+			abort_code = RXKADEXPIRED;
+			goto other_error;
 		default:
-			*_abort_code = RXKADNOAUTH;
-			goto error;
+			abort_code = RXKADNOAUTH;
+			goto other_error;
 		}
 	}
 
@@ -860,13 +882,11 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 
 	memcpy(&iv, &conn->server_key->payload.data[2], sizeof(iv));
 
+	ret = -ENOMEM;
 	req = skcipher_request_alloc(conn->server_key->payload.data[0],
 				     GFP_NOFS);
-	if (!req) {
-		*_abort_code = RXKADNOAUTH;
-		ret = -ENOMEM;
-		goto error;
-	}
+	if (!req)
+		goto temporary_error;
 
 	sg_init_one(&sg[0], ticket, ticket_len);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
@@ -877,11 +897,12 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 	p = ticket;
 	end = p + ticket_len;
 
-#define Z(size)						\
+#define Z(field)					\
 	({						\
 		u8 *__str = p;				\
+		eproto = tracepoint_string("rxkad_bad_"#field); \
 		q = memchr(p, 0, end - p);		\
-		if (!q || q - p > (size))		\
+		if (!q || q - p > (field##_SZ))		\
 			goto bad_ticket;		\
 		for (; p < q; p++)			\
 			if (!isprint(*p))		\
@@ -896,17 +917,18 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 	p++;
 
 	/* extract the authentication name */
-	name = Z(ANAME_SZ);
+	name = Z(ANAME);
 	_debug("KIV ANAME: %s", name);
 
 	/* extract the principal's instance */
-	name = Z(INST_SZ);
+	name = Z(INST);
 	_debug("KIV INST : %s", name);
 
 	/* extract the principal's authentication domain */
-	name = Z(REALM_SZ);
+	name = Z(REALM);
 	_debug("KIV REALM: %s", name);
 
+	eproto = tracepoint_string("rxkad_bad_len");
 	if (end - p < 4 + 8 + 4 + 2)
 		goto bad_ticket;
 
@@ -941,36 +963,37 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 
 	/* check the ticket is in date */
 	if (issue > now) {
-		*_abort_code = RXKADNOAUTH;
+		abort_code = RXKADNOAUTH;
 		ret = -EKEYREJECTED;
-		goto error;
+		goto other_error;
 	}
 
 	if (issue < now - life) {
-		*_abort_code = RXKADEXPIRED;
+		abort_code = RXKADEXPIRED;
 		ret = -EKEYEXPIRED;
-		goto error;
+		goto other_error;
 	}
 
 	*_expiry = issue + life;
 
 	/* get the service name */
-	name = Z(SNAME_SZ);
+	name = Z(SNAME);
 	_debug("KIV SNAME: %s", name);
 
 	/* get the service instance name */
-	name = Z(INST_SZ);
+	name = Z(INST);
 	_debug("KIV SINST: %s", name);
-
-	ret = 0;
-error:
-	_leave(" = %d", ret);
-	return ret;
+	return 0;
 
 bad_ticket:
-	*_abort_code = RXKADBADTICKET;
-	ret = -EBADMSG;
-	goto error;
+	trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+	abort_code = RXKADBADTICKET;
+	ret = -EPROTO;
+other_error:
+	*_abort_code = abort_code;
+	return ret;
+temporary_error:
+	return ret;
 }
 
 /*
@@ -1020,6 +1043,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 		__attribute__((aligned(8))); /* must be aligned for crypto */
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_crypt session_key;
+	const char *eproto;
 	time_t expiry;
 	void *ticket;
 	u32 abort_code, version, kvno, ticket_len, level;
@@ -1028,6 +1052,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 
 	_enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
 
+	eproto = tracepoint_string("rxkad_rsp_short");
 	abort_code = RXKADPACKETSHORT;
 	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
 			  &response, sizeof(response)) < 0)
@@ -1041,40 +1066,43 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	_proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }",
 	       sp->hdr.serial, version, kvno, ticket_len);
 
+	eproto = tracepoint_string("rxkad_rsp_ver");
 	abort_code = RXKADINCONSISTENCY;
 	if (version != RXKAD_VERSION)
 		goto protocol_error;
 
+	eproto = tracepoint_string("rxkad_rsp_tktlen");
 	abort_code = RXKADTICKETLEN;
 	if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN)
 		goto protocol_error;
 
+	eproto = tracepoint_string("rxkad_rsp_unkkey");
 	abort_code = RXKADUNKNOWNKEY;
 	if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5)
 		goto protocol_error;
 
 	/* extract the kerberos ticket and decrypt and decode it */
+	ret = -ENOMEM;
 	ticket = kmalloc(ticket_len, GFP_NOFS);
 	if (!ticket)
-		return -ENOMEM;
+		goto temporary_error;
 
+	eproto = tracepoint_string("rxkad_tkt_short");
 	abort_code = RXKADPACKETSHORT;
 	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
 			  ticket, ticket_len) < 0)
 		goto protocol_error_free;
 
-	ret = rxkad_decrypt_ticket(conn, ticket, ticket_len, &session_key,
-				   &expiry, &abort_code);
-	if (ret < 0) {
-		*_abort_code = abort_code;
-		kfree(ticket);
-		return ret;
-	}
+	ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
+				   &expiry, _abort_code);
+	if (ret < 0)
+		goto temporary_error_free;
 
 	/* use the session key from inside the ticket to decrypt the
 	 * response */
 	rxkad_decrypt_response(conn, &response, &session_key);
 
+	eproto = tracepoint_string("rxkad_rsp_param");
 	abort_code = RXKADSEALEDINCON;
 	if (ntohl(response.encrypted.epoch) != conn->proto.epoch)
 		goto protocol_error_free;
@@ -1085,6 +1113,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	csum = response.encrypted.checksum;
 	response.encrypted.checksum = 0;
 	rxkad_calc_response_checksum(&response);
+	eproto = tracepoint_string("rxkad_rsp_csum");
 	if (response.encrypted.checksum != csum)
 		goto protocol_error_free;
 
@@ -1093,11 +1122,15 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 		struct rxrpc_call *call;
 		u32 call_id = ntohl(response.encrypted.call_id[i]);
 
+		eproto = tracepoint_string("rxkad_rsp_callid");
 		if (call_id > INT_MAX)
 			goto protocol_error_unlock;
 
+		eproto = tracepoint_string("rxkad_rsp_callctr");
 		if (call_id < conn->channels[i].call_counter)
 			goto protocol_error_unlock;
+
+		eproto = tracepoint_string("rxkad_rsp_callst");
 		if (call_id > conn->channels[i].call_counter) {
 			call = rcu_dereference_protected(
 				conn->channels[i].call,
@@ -1109,10 +1142,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	}
 	spin_unlock(&conn->channel_lock);
 
+	eproto = tracepoint_string("rxkad_rsp_seq");
 	abort_code = RXKADOUTOFSEQUENCE;
 	if (ntohl(response.encrypted.inc_nonce) != conn->security_nonce + 1)
 		goto protocol_error_free;
 
+	eproto = tracepoint_string("rxkad_rsp_level");
 	abort_code = RXKADLEVELFAIL;
 	level = ntohl(response.encrypted.level);
 	if (level > RXRPC_SECURITY_ENCRYPT)
@@ -1123,10 +1158,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	 * this the connection security can be handled in exactly the same way
 	 * as for a client connection */
 	ret = rxrpc_get_server_data_key(conn, &session_key, expiry, kvno);
-	if (ret < 0) {
-		kfree(ticket);
-		return ret;
-	}
+	if (ret < 0)
+		goto temporary_error_free;
 
 	kfree(ticket);
 	_leave(" = 0");
@@ -1137,9 +1170,18 @@ protocol_error_unlock:
 protocol_error_free:
 	kfree(ticket);
 protocol_error:
+	trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
 	*_abort_code = abort_code;
-	_leave(" = -EPROTO [%d]", abort_code);
 	return -EPROTO;
+
+temporary_error_free:
+	kfree(ticket);
+temporary_error:
+	/* Ignore the response packet if we got a temporary error such as
+	 * ENOMEM.  We just want to send the challenge again.  Note that we
+	 * also come out this way if the ticket decryption fails.
+	 */
+	return ret;
 }
 
 /*
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index bc2d3dcff9de..96ffa5d5733b 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -488,6 +488,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	__releases(&rx->sk.sk_lock.slock)
 {
+	enum rxrpc_call_state state;
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
 	unsigned long user_call_ID = 0;
@@ -526,13 +527,17 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
 	} else {
-		ret = -EBUSY;
-		if (call->state == RXRPC_CALL_UNINITIALISED ||
-		    call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
-		    call->state == RXRPC_CALL_SERVER_PREALLOC ||
-		    call->state == RXRPC_CALL_SERVER_SECURING ||
-		    call->state == RXRPC_CALL_SERVER_ACCEPTING)
+		switch (READ_ONCE(call->state)) {
+		case RXRPC_CALL_UNINITIALISED:
+		case RXRPC_CALL_CLIENT_AWAIT_CONN:
+		case RXRPC_CALL_SERVER_PREALLOC:
+		case RXRPC_CALL_SERVER_SECURING:
+		case RXRPC_CALL_SERVER_ACCEPTING:
+			ret = -EBUSY;
 			goto error_release_sock;
+		default:
+			break;
+		}
 
 		ret = mutex_lock_interruptible(&call->user_mutex);
 		release_sock(&rx->sk);
@@ -542,25 +547,26 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		}
 	}
 
+	state = READ_ONCE(call->state);
 	_debug("CALL %d USR %lx ST %d on CONN %p",
-	       call->debug_id, call->user_call_ID, call->state, call->conn);
+	       call->debug_id, call->user_call_ID, state, call->conn);
 
-	if (call->state >= RXRPC_CALL_COMPLETE) {
+	if (state >= RXRPC_CALL_COMPLETE) {
 		/* it's too late for this call */
 		ret = -ESHUTDOWN;
 	} else if (cmd == RXRPC_CMD_SEND_ABORT) {
 		ret = 0;
-		if (rxrpc_abort_call("CMD", call, 0, abort_code, ECONNABORTED))
+		if (rxrpc_abort_call("CMD", call, 0, abort_code, -ECONNABORTED))
 			ret = rxrpc_send_abort_packet(call);
 	} else if (cmd != RXRPC_CMD_SEND_DATA) {
 		ret = -EINVAL;
 	} else if (rxrpc_is_client_call(call) &&
-		   call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+		   state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
 		/* request phase complete for this client call */
 		ret = -EPROTO;
 	} else if (rxrpc_is_service_call(call) &&
-		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+		   state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+		   state != RXRPC_CALL_SERVER_SEND_REPLY) {
 		/* Reply phase not begun or not complete for service call. */
 		ret = -EPROTO;
 	} else {
@@ -605,14 +611,22 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 	_debug("CALL %d USR %lx ST %d on CONN %p",
 	       call->debug_id, call->user_call_ID, call->state, call->conn);
 
-	if (call->state >= RXRPC_CALL_COMPLETE) {
-		ret = -ESHUTDOWN; /* it's too late for this call */
-	} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
-		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
-		ret = -EPROTO; /* request phase complete for this client call */
-	} else {
+	switch (READ_ONCE(call->state)) {
+	case RXRPC_CALL_CLIENT_SEND_REQUEST:
+	case RXRPC_CALL_SERVER_ACK_REQUEST:
+	case RXRPC_CALL_SERVER_SEND_REPLY:
 		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
+		break;
+	case RXRPC_CALL_COMPLETE:
+		read_lock_bh(&call->state_lock);
+		ret = -call->error;
+		read_unlock_bh(&call->state_lock);
+		break;
+	default:
+		/* Request phase complete for this client call */
+		trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
+		ret = -EPROTO;
+		break;
 	}
 
 	mutex_unlock(&call->user_mutex);
@@ -629,20 +643,24 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data);
  * @error: Local error value
  * @why: 3-char string indicating why.
  *
- * Allow a kernel service to abort a call, if it's still in an abortable state.
+ * Allow a kernel service to abort a call, if it's still in an abortable state
+ * and return true if the call was aborted, false if it was already complete.
  */
-void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
+bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
 			     u32 abort_code, int error, const char *why)
 {
+	bool aborted;
+
 	_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
 
 	mutex_lock(&call->user_mutex);
 
-	if (rxrpc_abort_call(why, call, 0, abort_code, error))
+	aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
+	if (aborted)
 		rxrpc_send_abort_packet(call);
 
 	mutex_unlock(&call->user_mutex);
-	_leave("");
+	return aborted;
 }
 
 EXPORT_SYMBOL(rxrpc_kernel_abort_call);
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 403790cce7d2..9fb84f0de6af 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -352,6 +352,51 @@ config NET_SCH_PLUG
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_plug.
 
+menuconfig NET_SCH_DEFAULT
+	bool "Allow override default queue discipline"
+	---help---
+	  Support for selection of default queuing discipline.
+
+	  Nearly all users can safely say no here, and the default
+	  of pfifo_fast will be used. Many distributions already set
+	  the default value via /proc/sys/net/core/default_qdisc.
+
+	  If unsure, say N.
+
+if NET_SCH_DEFAULT
+
+choice
+	prompt "Default queuing discipline"
+	default DEFAULT_PFIFO_FAST
+	help
+	  Select the queueing discipline that will be used by default
+	  for all network devices.
+
+	config DEFAULT_FQ
+		bool "Fair Queue" if NET_SCH_FQ
+
+	config DEFAULT_CODEL
+		bool "Controlled Delay" if NET_SCH_CODEL
+
+	config DEFAULT_FQ_CODEL
+		bool "Fair Queue Controlled Delay" if NET_SCH_FQ_CODEL
+
+	config DEFAULT_SFQ
+		bool "Stochastic Fair Queue" if NET_SCH_SFQ
+
+	config DEFAULT_PFIFO_FAST
+		bool "Priority FIFO Fast"
+endchoice
+
+config DEFAULT_NET_SCH
+	string
+	default "pfifo_fast" if DEFAULT_PFIFO_FAST
+	default "fq" if DEFAULT_FQ
+	default "fq_codel" if DEFAULT_FQ_CODEL
+	default "sfq" if DEFAULT_SFQ
+	default "pfifo_fast"
+endif
+
 comment "Classification"
 
 config NET_CLS
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index b70aa57319ea..a90e8f355c00 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -428,24 +428,49 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind)
 	return res;
 }
 
+/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */
+#define TCA_ACT_MAX_PRIO_MASK 0x1FF
 int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 		    int nr_actions, struct tcf_result *res)
 {
 	int ret = -1, i;
+	u32 jmp_prgcnt = 0;
+	u32 jmp_ttl = TCA_ACT_MAX_PRIO; /*matches actions per filter */
 
 	if (skb_skip_tc_classify(skb))
 		return TC_ACT_OK;
 
+restart_act_graph:
 	for (i = 0; i < nr_actions; i++) {
 		const struct tc_action *a = actions[i];
 
+		if (jmp_prgcnt > 0) {
+			jmp_prgcnt -= 1;
+			continue;
+		}
 repeat:
 		ret = a->ops->act(skb, a, res);
 		if (ret == TC_ACT_REPEAT)
 			goto repeat;	/* we need a ttl - JHS */
+
+		if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) {
+			jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK;
+			if (!jmp_prgcnt || (jmp_prgcnt > nr_actions)) {
+				/* faulty opcode, stop pipeline */
+				return TC_ACT_OK;
+			} else {
+				jmp_ttl -= 1;
+				if (jmp_ttl > 0)
+					goto restart_act_graph;
+				else /* faulty graph, stop pipeline */
+					return TC_ACT_OK;
+			}
+		}
+
 		if (ret != TC_ACT_PIPE)
 			break;
 	}
+
 	return ret;
 }
 EXPORT_SYMBOL(tcf_action_exec);
@@ -529,20 +554,20 @@ errout:
 	return err;
 }
 
-static int nla_memdup_cookie(struct tc_action *a, struct nlattr **tb)
+static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 {
-	a->act_cookie = kzalloc(sizeof(*a->act_cookie), GFP_KERNEL);
-	if (!a->act_cookie)
-		return -ENOMEM;
+	struct tc_cookie *c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return NULL;
 
-	a->act_cookie->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL);
-	if (!a->act_cookie->data) {
-		kfree(a->act_cookie);
-		return -ENOMEM;
+	c->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL);
+	if (!c->data) {
+		kfree(c);
+		return NULL;
 	}
-	a->act_cookie->len = nla_len(tb[TCA_ACT_COOKIE]);
+	c->len = nla_len(tb[TCA_ACT_COOKIE]);
 
-	return 0;
+	return c;
 }
 
 struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
@@ -551,13 +576,14 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 {
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
+	struct tc_cookie *cookie = NULL;
 	char act_name[IFNAMSIZ];
 	struct nlattr *tb[TCA_ACT_MAX + 1];
 	struct nlattr *kind;
 	int err;
 
 	if (name == NULL) {
-		err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL);
+		err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL);
 		if (err < 0)
 			goto err_out;
 		err = -EINVAL;
@@ -566,6 +592,18 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 			goto err_out;
 		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ)
 			goto err_out;
+		if (tb[TCA_ACT_COOKIE]) {
+			int cklen = nla_len(tb[TCA_ACT_COOKIE]);
+
+			if (cklen > TC_COOKIE_MAX_SIZE)
+				goto err_out;
+
+			cookie = nla_memdup_cookie(tb);
+			if (!cookie) {
+				err = -ENOMEM;
+				goto err_out;
+			}
+		}
 	} else {
 		err = -EINVAL;
 		if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ)
@@ -604,20 +642,12 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 	if (err < 0)
 		goto err_mod;
 
-	if (tb[TCA_ACT_COOKIE]) {
-		int cklen = nla_len(tb[TCA_ACT_COOKIE]);
-
-		if (cklen > TC_COOKIE_MAX_SIZE) {
-			err = -EINVAL;
-			tcf_hash_release(a, bind);
-			goto err_mod;
-		}
-
-		if (nla_memdup_cookie(a, tb) < 0) {
-			err = -ENOMEM;
-			tcf_hash_release(a, bind);
-			goto err_mod;
+	if (name == NULL && tb[TCA_ACT_COOKIE]) {
+		if (a->act_cookie) {
+			kfree(a->act_cookie->data);
+			kfree(a->act_cookie);
 		}
+		a->act_cookie = cookie;
 	}
 
 	/* module count goes up only when brand new policy is created
@@ -632,6 +662,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 err_mod:
 	module_put(a_o->owner);
 err_out:
+	if (cookie) {
+		kfree(cookie->data);
+		kfree(cookie);
+	}
 	return ERR_PTR(err);
 }
 
@@ -654,7 +688,7 @@ int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	int err;
 	int i;
 
-	err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL);
+	err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL);
 	if (err < 0)
 		return err;
 
@@ -786,7 +820,7 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla,
 	int index;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL);
+	err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL);
 	if (err < 0)
 		goto err_out;
 
@@ -835,7 +869,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 
 	b = skb_tail_pointer(skb);
 
-	err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL);
+	err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL);
 	if (err < 0)
 		goto err_out;
 
@@ -921,7 +955,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	struct tc_action *act;
 	LIST_HEAD(actions);
 
-	ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL);
+	ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -993,7 +1027,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 	return tcf_add_notify(net, n, &actions, portid);
 }
 
-static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
+static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
+			 struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_ACT_MAX + 1];
@@ -1004,7 +1039,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
+	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL,
+			  extack);
 	if (ret < 0)
 		return ret;
 
@@ -1051,19 +1087,20 @@ static struct nlattr *find_dump_kind(const struct nlmsghdr *n)
 	struct nlattr *nla[TCAA_MAX + 1];
 	struct nlattr *kind;
 
-	if (nlmsg_parse(n, sizeof(struct tcamsg), nla, TCAA_MAX, NULL) < 0)
+	if (nlmsg_parse(n, sizeof(struct tcamsg), nla, TCAA_MAX,
+			NULL, NULL) < 0)
 		return NULL;
 	tb1 = nla[TCA_ACT_TAB];
 	if (tb1 == NULL)
 		return NULL;
 
 	if (nla_parse(tb, TCA_ACT_MAX_PRIO, nla_data(tb1),
-		      NLMSG_ALIGN(nla_len(tb1)), NULL) < 0)
+		      NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0)
 		return NULL;
 
 	if (tb[1] == NULL)
 		return NULL;
-	if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL) < 0)
+	if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0)
 		return NULL;
 	kind = tb2[TCA_ACT_KIND];
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 520baa41cba3..d33947d6e9d0 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -283,7 +283,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy);
+	ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index ab8062909962..2155bc6c6a1e 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -109,10 +109,14 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy);
+	ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy,
+			       NULL);
 	if (ret < 0)
 		return ret;
 
+	if (!tb[TCA_CONNMARK_PARMS])
+		return -EINVAL;
+
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(tn, parm->index, a, bind)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index e978ccd4402c..ab6fdbd34db7 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -59,7 +59,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy);
+	err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -181,6 +181,9 @@ static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
 	struct tcphdr *tcph;
 	const struct iphdr *iph;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+		return 1;
+
 	tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
 	if (tcph == NULL)
 		return 0;
@@ -202,6 +205,9 @@ static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
 	struct tcphdr *tcph;
 	const struct ipv6hdr *ip6h;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+		return 1;
+
 	tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
 	if (tcph == NULL)
 		return 0;
@@ -225,6 +231,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct iphdr *iph;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
@@ -278,6 +287,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct ipv6hdr *ip6h;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e6c874a2b283..99afe8b1f1fb 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -73,7 +73,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GACT_MAX, nla, gact_policy);
+	err = nla_parse_nested(tb, TCA_GACT_MAX, nla, gact_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 71e7ff22f7c9..c5dec308b8b1 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -443,7 +443,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	int ret = 0;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy);
+	err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -514,7 +514,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 
 	if (tb[TCA_IFE_METALST]) {
 		err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST],
-				       NULL);
+				       NULL, NULL);
 		if (err) {
 metadata_parse_err:
 			if (exists)
@@ -603,8 +603,8 @@ nla_put_failure:
 	return -1;
 }
 
-int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
-		       u16 metaid, u16 mlen, void *mdata)
+static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
+			      u16 metaid, u16 mlen, void *mdata)
 {
 	struct tcf_meta_info *e;
 
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 992ef8d624f1..36f0ced9e60c 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -107,7 +107,7 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_IPT_MAX, nla, ipt_policy);
+	err = nla_parse_nested(tb, TCA_IPT_MAX, nla, ipt_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index af49c7dca860..1b5549ababd4 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -87,7 +87,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 
 	if (nla == NULL)
 		return -EINVAL;
-	ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy);
+	ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL);
 	if (ret < 0)
 		return ret;
 	if (tb[TCA_MIRRED_PARMS] == NULL)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 9b6aec665495..9016ab8a0649 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -50,7 +50,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_NAT_MAX, nla, nat_policy);
+	err = nla_parse_nested(tb, TCA_NAT_MAX, nla, nat_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index c1310472f620..164b5ac094be 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -72,7 +72,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla,
 		}
 
 		err = nla_parse_nested(tb, TCA_PEDIT_KEY_EX_MAX, ka,
-				       pedit_key_ex_policy);
+				       pedit_key_ex_policy, NULL);
 		if (err)
 			goto err_out;
 
@@ -147,7 +147,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy);
+	err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0ba91d1ce994..f42008b29311 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -90,7 +90,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_POLICE_MAX, nla, police_policy);
+	err = nla_parse_nested(tb, TCA_POLICE_MAX, nla, police_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 0b8217b4763f..59d6645a4007 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -50,7 +50,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	if (!nla)
 		return -EINVAL;
-	ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy);
+	ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy, NULL);
 	if (ret < 0)
 		return ret;
 	if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 823a73ad0c60..43605e7ce051 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -94,7 +94,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_DEF_MAX, nla, simple_policy);
+	err = nla_parse_nested(tb, TCA_DEF_MAX, nla, simple_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 06ccae3c12ee..6b3e65d7de0c 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -82,7 +82,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy);
+	err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 3b7074e23024..a73c4bbcada2 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -103,7 +103,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy);
+	err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 
 	return skb->len;
 nla_put_failure:
-	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index e3a58e021198..b9a2f241a5b3 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -89,7 +89,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy);
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 19e0dba305ce..13ba3a89f675 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -121,7 +121,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy);
+	err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 732f7cae459d..22f88b35a546 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -178,14 +178,11 @@ errout:
 	return ERR_PTR(err);
 }
 
-static bool tcf_proto_destroy(struct tcf_proto *tp, bool force)
+static void tcf_proto_destroy(struct tcf_proto *tp)
 {
-	if (tp->ops->destroy(tp, force)) {
-		module_put(tp->ops->owner);
-		kfree_rcu(tp, rcu);
-		return true;
-	}
-	return false;
+	tp->ops->destroy(tp);
+	module_put(tp->ops->owner);
+	kfree_rcu(tp, rcu);
 }
 
 void tcf_destroy_chain(struct tcf_proto __rcu **fl)
@@ -194,14 +191,15 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl)
 
 	while ((tp = rtnl_dereference(*fl)) != NULL) {
 		RCU_INIT_POINTER(*fl, tp->next);
-		tcf_proto_destroy(tp, true);
+		tcf_proto_destroy(tp);
 	}
 }
 EXPORT_SYMBOL(tcf_destroy_chain);
 
 /* Add/change/delete/get a filter node */
 
-static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
+static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
@@ -229,7 +227,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 replay:
 	tp_created = 0;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -360,7 +358,7 @@ replay:
 			RCU_INIT_POINTER(*back, next);
 			tfilter_notify(net, skb, n, tp, fh,
 				       RTM_DELTFILTER, false);
-			tcf_proto_destroy(tp, true);
+			tcf_proto_destroy(tp);
 			err = 0;
 			goto errout;
 		}
@@ -371,24 +369,28 @@ replay:
 			goto errout;
 		}
 	} else {
+		bool last;
+
 		switch (n->nlmsg_type) {
 		case RTM_NEWTFILTER:
 			if (n->nlmsg_flags & NLM_F_EXCL) {
 				if (tp_created)
-					tcf_proto_destroy(tp, true);
+					tcf_proto_destroy(tp);
 				err = -EEXIST;
 				goto errout;
 			}
 			break;
 		case RTM_DELTFILTER:
-			err = tp->ops->delete(tp, fh);
+			err = tp->ops->delete(tp, fh, &last);
 			if (err)
 				goto errout;
 			next = rtnl_dereference(tp->next);
 			tfilter_notify(net, skb, n, tp, t->tcm_handle,
 				       RTM_DELTFILTER, false);
-			if (tcf_proto_destroy(tp, false))
+			if (last) {
 				RCU_INIT_POINTER(*back, next);
+				tcf_proto_destroy(tp);
+			}
 			goto errout;
 		case RTM_GETTFILTER:
 			err = tfilter_notify(net, skb, n, tp, fh,
@@ -410,7 +412,7 @@ replay:
 		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false);
 	} else {
 		if (tp_created)
-			tcf_proto_destroy(tp, true);
+			tcf_proto_destroy(tp);
 	}
 
 errout:
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 5877f6061b57..c4fd63a068f9 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -93,30 +93,28 @@ static void basic_delete_filter(struct rcu_head *head)
 	kfree(f);
 }
 
-static bool basic_destroy(struct tcf_proto *tp, bool force)
+static void basic_destroy(struct tcf_proto *tp)
 {
 	struct basic_head *head = rtnl_dereference(tp->root);
 	struct basic_filter *f, *n;
 
-	if (!force && !list_empty(&head->flist))
-		return false;
-
 	list_for_each_entry_safe(f, n, &head->flist, link) {
 		list_del_rcu(&f->link);
 		tcf_unbind_filter(tp, &f->res);
 		call_rcu(&f->rcu, basic_delete_filter);
 	}
 	kfree_rcu(head, rcu);
-	return true;
 }
 
-static int basic_delete(struct tcf_proto *tp, unsigned long arg)
+static int basic_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
+	struct basic_head *head = rtnl_dereference(tp->root);
 	struct basic_filter *f = (struct basic_filter *) arg;
 
 	list_del_rcu(&f->link);
 	tcf_unbind_filter(tp, &f->res);
 	call_rcu(&f->rcu, basic_delete_filter);
+	*last = list_empty(&head->flist);
 	return 0;
 }
 
@@ -174,7 +172,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 		return -EINVAL;
 
 	err = nla_parse_nested(tb, TCA_BASIC_MAX, tca[TCA_OPTIONS],
-			       basic_policy);
+			       basic_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 80f688436dd7..5ebeae996e63 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -274,25 +274,24 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog)
 	call_rcu(&prog->rcu, cls_bpf_delete_prog_rcu);
 }
 
-static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
+static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+
 	__cls_bpf_delete(tp, (struct cls_bpf_prog *) arg);
+	*last = list_empty(&head->plist);
 	return 0;
 }
 
-static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
+static void cls_bpf_destroy(struct tcf_proto *tp)
 {
 	struct cls_bpf_head *head = rtnl_dereference(tp->root);
 	struct cls_bpf_prog *prog, *tmp;
 
-	if (!force && !list_empty(&head->plist))
-		return false;
-
 	list_for_each_entry_safe(prog, tmp, &head->plist, link)
 		__cls_bpf_delete(tp, prog);
 
 	kfree_rcu(head, rcu);
-	return true;
 }
 
 static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
@@ -478,7 +477,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	if (tca[TCA_OPTIONS] == NULL)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy);
+	ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy,
+			       NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index c1f20077837f..12ce547eea04 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -99,7 +99,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 	new->handle = handle;
 	new->tp = tp;
 	err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
-			       cgroup_policy);
+			       cgroup_policy, NULL);
 	if (err < 0)
 		goto errout;
 
@@ -131,20 +131,16 @@ errout:
 	return err;
 }
 
-static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force)
+static void cls_cgroup_destroy(struct tcf_proto *tp)
 {
 	struct cls_cgroup_head *head = rtnl_dereference(tp->root);
 
-	if (!force)
-		return false;
 	/* Head can still be NULL due to cls_cgroup_init(). */
 	if (head)
 		call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
-
-	return true;
 }
 
-static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
+static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 3d6b9286c203..3065752b9cda 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -400,7 +400,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FLOW_MAX, opt, flow_policy);
+	err = nla_parse_nested(tb, TCA_FLOW_MAX, opt, flow_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -508,9 +508,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 		get_random_bytes(&fnew->hashrnd, 4);
 	}
 
-	fnew->perturb_timer.function = flow_perturbation;
-	fnew->perturb_timer.data = (unsigned long)fnew;
-	init_timer_deferrable(&fnew->perturb_timer);
+	setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation,
+			       (unsigned long)fnew);
 
 	tcf_exts_change(tp, &fnew->exts, &e);
 	tcf_em_tree_change(tp, &fnew->ematches, &t);
@@ -563,12 +562,14 @@ err1:
 	return err;
 }
 
-static int flow_delete(struct tcf_proto *tp, unsigned long arg)
+static int flow_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
+	struct flow_head *head = rtnl_dereference(tp->root);
 	struct flow_filter *f = (struct flow_filter *)arg;
 
 	list_del_rcu(&f->list);
 	call_rcu(&f->rcu, flow_destroy_filter);
+	*last = list_empty(&head->filters);
 	return 0;
 }
 
@@ -584,20 +585,16 @@ static int flow_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static bool flow_destroy(struct tcf_proto *tp, bool force)
+static void flow_destroy(struct tcf_proto *tp)
 {
 	struct flow_head *head = rtnl_dereference(tp->root);
 	struct flow_filter *f, *next;
 
-	if (!force && !list_empty(&head->filters))
-		return false;
-
 	list_for_each_entry_safe(f, next, &head->filters, list) {
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, flow_destroy_filter);
 	}
 	kfree_rcu(head, rcu);
-	return true;
 }
 
 static unsigned long flow_get(struct tcf_proto *tp, u32 handle)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9d0c99d2e9fb..ca526c0881bd 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -18,6 +18,7 @@
 #include <linux/if_ether.h>
 #include <linux/in6.h>
 #include <linux/ip.h>
+#include <linux/mpls.h>
 
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
@@ -47,6 +48,7 @@ struct fl_flow_key {
 		struct flow_dissector_key_ipv6_addrs enc_ipv6;
 	};
 	struct flow_dissector_key_ports enc_tp;
+	struct flow_dissector_key_mpls mpls;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -328,21 +330,16 @@ static void fl_destroy_rcu(struct rcu_head *rcu)
 	schedule_work(&head->work);
 }
 
-static bool fl_destroy(struct tcf_proto *tp, bool force)
+static void fl_destroy(struct tcf_proto *tp)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *f, *next;
 
-	if (!force && !list_empty(&head->filters))
-		return false;
-
 	list_for_each_entry_safe(f, next, &head->filters, list)
 		__fl_delete(tp, f);
 
 	__module_get(THIS_MODULE);
 	call_rcu(&head->rcu, fl_destroy_rcu);
-
-	return true;
 }
 
 static unsigned long fl_get(struct tcf_proto *tp, u32 handle)
@@ -423,6 +420,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_ARP_SHA_MASK]	= { .len = ETH_ALEN },
 	[TCA_FLOWER_KEY_ARP_THA]	= { .len = ETH_ALEN },
 	[TCA_FLOWER_KEY_ARP_THA_MASK]	= { .len = ETH_ALEN },
+	[TCA_FLOWER_KEY_MPLS_TTL]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_MPLS_BOS]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_MPLS_TC]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_MPLS_LABEL]	= { .type = NLA_U32 },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -438,6 +439,41 @@ static void fl_set_key_val(struct nlattr **tb,
 		memcpy(mask, nla_data(tb[mask_type]), len);
 }
 
+static int fl_set_key_mpls(struct nlattr **tb,
+			   struct flow_dissector_key_mpls *key_val,
+			   struct flow_dissector_key_mpls *key_mask)
+{
+	if (tb[TCA_FLOWER_KEY_MPLS_TTL]) {
+		key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
+		key_mask->mpls_ttl = MPLS_TTL_MASK;
+	}
+	if (tb[TCA_FLOWER_KEY_MPLS_BOS]) {
+		u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]);
+
+		if (bos & ~MPLS_BOS_MASK)
+			return -EINVAL;
+		key_val->mpls_bos = bos;
+		key_mask->mpls_bos = MPLS_BOS_MASK;
+	}
+	if (tb[TCA_FLOWER_KEY_MPLS_TC]) {
+		u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]);
+
+		if (tc & ~MPLS_TC_MASK)
+			return -EINVAL;
+		key_val->mpls_tc = tc;
+		key_mask->mpls_tc = MPLS_TC_MASK;
+	}
+	if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) {
+		u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]);
+
+		if (label & ~MPLS_LABEL_MASK)
+			return -EINVAL;
+		key_val->mpls_label = label;
+		key_mask->mpls_label = MPLS_LABEL_MASK;
+	}
+	return 0;
+}
+
 static void fl_set_key_vlan(struct nlattr **tb,
 			    struct flow_dissector_key_vlan *key_val,
 			    struct flow_dissector_key_vlan *key_mask)
@@ -594,6 +630,11 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       &mask->icmp.code,
 			       TCA_FLOWER_KEY_ICMPV6_CODE_MASK,
 			       sizeof(key->icmp.code));
+	} else if (key->basic.n_proto == htons(ETH_P_MPLS_UC) ||
+		   key->basic.n_proto == htons(ETH_P_MPLS_MC)) {
+		ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls);
+		if (ret)
+			return ret;
 	} else if (key->basic.n_proto == htons(ETH_P_ARP) ||
 		   key->basic.n_proto == htons(ETH_P_RARP)) {
 		fl_set_key_val(tb, &key->arp.sip, TCA_FLOWER_KEY_ARP_SIP,
@@ -730,6 +771,8 @@ static void fl_init_dissector(struct cls_fl_head *head,
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ARP, arp);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+			     FLOW_DISSECTOR_KEY_MPLS, mpls);
+	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_VLAN, vlan);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
@@ -848,7 +891,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (!tb)
 		return -ENOBUFS;
 
-	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy);
+	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
+			       fl_policy, NULL);
 	if (err < 0)
 		goto errout_tb;
 
@@ -946,7 +990,7 @@ errout_tb:
 	return err;
 }
 
-static int fl_delete(struct tcf_proto *tp, unsigned long arg)
+static int fl_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *f = (struct cls_fl_filter *) arg;
@@ -955,6 +999,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg)
 		rhashtable_remove_fast(&head->ht, &f->ht_node,
 				       head->ht_params);
 	__fl_delete(tp, f);
+	*last = list_empty(&head->filters);
 	return 0;
 }
 
@@ -994,6 +1039,41 @@ static int fl_dump_key_val(struct sk_buff *skb,
 	return 0;
 }
 
+static int fl_dump_key_mpls(struct sk_buff *skb,
+			    struct flow_dissector_key_mpls *mpls_key,
+			    struct flow_dissector_key_mpls *mpls_mask)
+{
+	int err;
+
+	if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask)))
+		return 0;
+	if (mpls_mask->mpls_ttl) {
+		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL,
+				 mpls_key->mpls_ttl);
+		if (err)
+			return err;
+	}
+	if (mpls_mask->mpls_tc) {
+		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TC,
+				 mpls_key->mpls_tc);
+		if (err)
+			return err;
+	}
+	if (mpls_mask->mpls_label) {
+		err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_LABEL,
+				  mpls_key->mpls_label);
+		if (err)
+			return err;
+	}
+	if (mpls_mask->mpls_bos) {
+		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_BOS,
+				 mpls_key->mpls_bos);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 static int fl_dump_key_vlan(struct sk_buff *skb,
 			    struct flow_dissector_key_vlan *vlan_key,
 			    struct flow_dissector_key_vlan *vlan_mask)
@@ -1099,6 +1179,9 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 			    sizeof(key->basic.n_proto)))
 		goto nla_put_failure;
 
+	if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls))
+		goto nla_put_failure;
+
 	if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan))
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 9dc63d54e167..d3885362e017 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -127,20 +127,14 @@ static void fw_delete_filter(struct rcu_head *head)
 	kfree(f);
 }
 
-static bool fw_destroy(struct tcf_proto *tp, bool force)
+static void fw_destroy(struct tcf_proto *tp)
 {
 	struct fw_head *head = rtnl_dereference(tp->root);
 	struct fw_filter *f;
 	int h;
 
 	if (head == NULL)
-		return true;
-
-	if (!force) {
-		for (h = 0; h < HTSIZE; h++)
-			if (rcu_access_pointer(head->ht[h]))
-				return false;
-	}
+		return;
 
 	for (h = 0; h < HTSIZE; h++) {
 		while ((f = rtnl_dereference(head->ht[h])) != NULL) {
@@ -150,17 +144,17 @@ static bool fw_destroy(struct tcf_proto *tp, bool force)
 			call_rcu(&f->rcu, fw_delete_filter);
 		}
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
-	return true;
 }
 
-static int fw_delete(struct tcf_proto *tp, unsigned long arg)
+static int fw_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	struct fw_head *head = rtnl_dereference(tp->root);
 	struct fw_filter *f = (struct fw_filter *)arg;
 	struct fw_filter __rcu **fp;
 	struct fw_filter *pfp;
+	int ret = -EINVAL;
+	int h;
 
 	if (head == NULL || f == NULL)
 		goto out;
@@ -173,11 +167,21 @@ static int fw_delete(struct tcf_proto *tp, unsigned long arg)
 			RCU_INIT_POINTER(*fp, rtnl_dereference(f->next));
 			tcf_unbind_filter(tp, &f->res);
 			call_rcu(&f->rcu, fw_delete_filter);
-			return 0;
+			ret = 0;
+			break;
 		}
 	}
+
+	*last = true;
+	for (h = 0; h < HTSIZE; h++) {
+		if (rcu_access_pointer(head->ht[h])) {
+			*last = false;
+			break;
+		}
+	}
+
 out:
-	return -EINVAL;
+	return ret;
 }
 
 static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = {
@@ -250,7 +254,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (!opt)
 		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
 
-	err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy);
+	err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 224eb2c14346..2efb36c08f2a 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -90,19 +90,18 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp,
 					     &offload);
 }
 
-static bool mall_destroy(struct tcf_proto *tp, bool force)
+static void mall_destroy(struct tcf_proto *tp)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
 	struct net_device *dev = tp->q->dev_queue->dev;
 
 	if (!head)
-		return true;
+		return;
 
 	if (tc_should_offload(dev, tp, head->flags))
 		mall_destroy_hw_filter(tp, head, (unsigned long) head);
 
 	call_rcu(&head->rcu, mall_destroy_rcu);
-	return true;
 }
 
 static unsigned long mall_get(struct tcf_proto *tp, u32 handle)
@@ -161,8 +160,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 	if (head)
 		return -EEXIST;
 
-	err = nla_parse_nested(tb, TCA_MATCHALL_MAX,
-			       tca[TCA_OPTIONS], mall_policy);
+	err = nla_parse_nested(tb, TCA_MATCHALL_MAX, tca[TCA_OPTIONS],
+			       mall_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -216,7 +215,7 @@ err_exts_init:
 	return err;
 }
 
-static int mall_delete(struct tcf_proto *tp, unsigned long arg)
+static int mall_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 455fc8f83d0a..d63d5502ee02 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -140,8 +140,6 @@ static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		goto failure;
 
 	id = dst->tclassid;
-	if (head == NULL)
-		goto old_method;
 
 	iif = inet_iif(skb);
 
@@ -194,15 +192,6 @@ restart:
 		route4_set_fastmap(head, id, iif, ROUTE4_FAILURE);
 failure:
 	return -1;
-
-old_method:
-	if (id && (TC_H_MAJ(id) == 0 ||
-		   !(TC_H_MAJ(id^tp->q->handle)))) {
-		res->classid = id;
-		res->class = 0;
-		return 0;
-	}
-	return -1;
 }
 
 static inline u32 to_hash(u32 id)
@@ -234,9 +223,6 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle)
 	struct route4_filter *f;
 	unsigned int h1, h2;
 
-	if (!head)
-		return 0;
-
 	h1 = to_hash(handle);
 	if (h1 > 256)
 		return 0;
@@ -276,20 +262,13 @@ static void route4_delete_filter(struct rcu_head *head)
 	kfree(f);
 }
 
-static bool route4_destroy(struct tcf_proto *tp, bool force)
+static void route4_destroy(struct tcf_proto *tp)
 {
 	struct route4_head *head = rtnl_dereference(tp->root);
 	int h1, h2;
 
 	if (head == NULL)
-		return true;
-
-	if (!force) {
-		for (h1 = 0; h1 <= 256; h1++) {
-			if (rcu_access_pointer(head->table[h1]))
-				return false;
-		}
-	}
+		return;
 
 	for (h1 = 0; h1 <= 256; h1++) {
 		struct route4_bucket *b;
@@ -312,12 +291,10 @@ static bool route4_destroy(struct tcf_proto *tp, bool force)
 			kfree_rcu(b, rcu);
 		}
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
-	return true;
 }
 
-static int route4_delete(struct tcf_proto *tp, unsigned long arg)
+static int route4_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	struct route4_head *head = rtnl_dereference(tp->root);
 	struct route4_filter *f = (struct route4_filter *)arg;
@@ -325,7 +302,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg)
 	struct route4_filter *nf;
 	struct route4_bucket *b;
 	unsigned int h = 0;
-	int i;
+	int i, h1;
 
 	if (!head || !f)
 		return -EINVAL;
@@ -356,16 +333,25 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg)
 
 				rt = rtnl_dereference(b->ht[i]);
 				if (rt)
-					return 0;
+					goto out;
 			}
 
 			/* OK, session has no flows */
 			RCU_INIT_POINTER(head->table[to_hash(h)], NULL);
 			kfree_rcu(b, rcu);
+			break;
+		}
+	}
 
-			return 0;
+out:
+	*last = true;
+	for (h1 = 0; h1 <= 256; h1++) {
+		if (rcu_access_pointer(head->table[h1])) {
+			*last = false;
+			break;
 		}
 	}
+
 	return 0;
 }
 
@@ -489,7 +475,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
-	err = nla_parse_nested(tb, TCA_ROUTE4_MAX, opt, route4_policy);
+	err = nla_parse_nested(tb, TCA_ROUTE4_MAX, opt, route4_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 322438fb3ffc..0d9d07798699 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -152,8 +152,6 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		return -1;
 	nhptr = ip_hdr(skb);
 #endif
-	if (unlikely(!head))
-		return -1;
 restart:
 
 #if RSVP_DST_LEN == 4
@@ -302,22 +300,13 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
 	call_rcu(&f->rcu, rsvp_delete_filter_rcu);
 }
 
-static bool rsvp_destroy(struct tcf_proto *tp, bool force)
+static void rsvp_destroy(struct tcf_proto *tp)
 {
 	struct rsvp_head *data = rtnl_dereference(tp->root);
 	int h1, h2;
 
 	if (data == NULL)
-		return true;
-
-	if (!force) {
-		for (h1 = 0; h1 < 256; h1++) {
-			if (rcu_access_pointer(data->ht[h1]))
-				return false;
-		}
-	}
-
-	RCU_INIT_POINTER(tp->root, NULL);
+		return;
 
 	for (h1 = 0; h1 < 256; h1++) {
 		struct rsvp_session *s;
@@ -337,10 +326,9 @@ static bool rsvp_destroy(struct tcf_proto *tp, bool force)
 		}
 	}
 	kfree_rcu(data, rcu);
-	return true;
 }
 
-static int rsvp_delete(struct tcf_proto *tp, unsigned long arg)
+static int rsvp_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	struct rsvp_head *head = rtnl_dereference(tp->root);
 	struct rsvp_filter *nfp, *f = (struct rsvp_filter *)arg;
@@ -348,7 +336,7 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg)
 	unsigned int h = f->handle;
 	struct rsvp_session __rcu **sp;
 	struct rsvp_session *nsp, *s = f->sess;
-	int i;
+	int i, h1;
 
 	fp = &s->ht[(h >> 8) & 0xFF];
 	for (nfp = rtnl_dereference(*fp); nfp;
@@ -361,7 +349,7 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg)
 
 			for (i = 0; i <= 16; i++)
 				if (s->ht[i])
-					return 0;
+					goto out;
 
 			/* OK, session has no flows */
 			sp = &head->ht[h & 0xFF];
@@ -370,13 +358,23 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg)
 				if (nsp == s) {
 					RCU_INIT_POINTER(*sp, s->next);
 					kfree_rcu(s, rcu);
-					return 0;
+					goto out;
 				}
 			}
 
-			return 0;
+			break;
 		}
 	}
+
+out:
+	*last = true;
+	for (h1 = 0; h1 < 256; h1++) {
+		if (rcu_access_pointer(head->ht[h1])) {
+			*last = false;
+			break;
+		}
+	}
+
 	return 0;
 }
 
@@ -484,7 +482,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
-	err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy);
+	err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 0751245a6ace..8a8a58357c39 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -150,7 +150,7 @@ static void tcindex_destroy_fexts(struct rcu_head *head)
 	kfree(f);
 }
 
-static int tcindex_delete(struct tcf_proto *tp, unsigned long arg)
+static int tcindex_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg;
@@ -186,6 +186,8 @@ found:
 		call_rcu(&f->rcu, tcindex_destroy_fexts);
 	else
 		call_rcu(&r->rcu, tcindex_destroy_rexts);
+
+	*last = false;
 	return 0;
 }
 
@@ -193,7 +195,9 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
 				   unsigned long arg,
 				   struct tcf_walker *walker)
 {
-	return tcindex_delete(tp, arg);
+	bool last;
+
+	return tcindex_delete(tp, arg, &last);
 }
 
 static void __tcindex_destroy(struct rcu_head *head)
@@ -482,7 +486,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 	if (!opt)
 		return 0;
 
-	err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy);
+	err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -529,14 +533,11 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
 	}
 }
 
-static bool tcindex_destroy(struct tcf_proto *tp, bool force)
+static void tcindex_destroy(struct tcf_proto *tp)
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcf_walker walker;
 
-	if (!force)
-		return false;
-
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
 	walker.count = 0;
 	walker.skip = 0;
@@ -544,7 +545,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force)
 	tcindex_walk(tp, &walker);
 
 	call_rcu(&p->rcu, __tcindex_destroy);
-	return true;
 }
 
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4dbe0c680fe6..d20e72a095d5 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -585,37 +585,13 @@ static bool ht_empty(struct tc_u_hnode *ht)
 	return true;
 }
 
-static bool u32_destroy(struct tcf_proto *tp, bool force)
+static void u32_destroy(struct tcf_proto *tp)
 {
 	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
 
 	WARN_ON(root_ht == NULL);
 
-	if (!force) {
-		if (root_ht) {
-			if (root_ht->refcnt > 1)
-				return false;
-			if (root_ht->refcnt == 1) {
-				if (!ht_empty(root_ht))
-					return false;
-			}
-		}
-
-		if (tp_c->refcnt > 1)
-			return false;
-
-		if (tp_c->refcnt == 1) {
-			struct tc_u_hnode *ht;
-
-			for (ht = rtnl_dereference(tp_c->hlist);
-			     ht;
-			     ht = rtnl_dereference(ht->next))
-				if (!ht_empty(ht))
-					return false;
-		}
-	}
-
 	if (root_ht && --root_ht->refcnt == 0)
 		u32_destroy_hnode(tp, root_ht);
 
@@ -640,20 +616,22 @@ static bool u32_destroy(struct tcf_proto *tp, bool force)
 	}
 
 	tp->data = NULL;
-	return true;
 }
 
-static int u32_delete(struct tcf_proto *tp, unsigned long arg)
+static int u32_delete(struct tcf_proto *tp, unsigned long arg, bool *last)
 {
 	struct tc_u_hnode *ht = (struct tc_u_hnode *)arg;
 	struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
+	struct tc_u_common *tp_c = tp->data;
+	int ret = 0;
 
 	if (ht == NULL)
-		return 0;
+		goto out;
 
 	if (TC_U32_KEY(ht->handle)) {
 		u32_remove_hw_knode(tp, ht->handle);
-		return u32_delete_key(tp, (struct tc_u_knode *)ht);
+		ret = u32_delete_key(tp, (struct tc_u_knode *)ht);
+		goto out;
 	}
 
 	if (root_ht == ht)
@@ -666,7 +644,40 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg)
 		return -EBUSY;
 	}
 
-	return 0;
+out:
+	*last = true;
+	if (root_ht) {
+		if (root_ht->refcnt > 1) {
+			*last = false;
+			goto ret;
+		}
+		if (root_ht->refcnt == 1) {
+			if (!ht_empty(root_ht)) {
+				*last = false;
+				goto ret;
+			}
+		}
+	}
+
+	if (tp_c->refcnt > 1) {
+		*last = false;
+		goto ret;
+	}
+
+	if (tp_c->refcnt == 1) {
+		struct tc_u_hnode *ht;
+
+		for (ht = rtnl_dereference(tp_c->hlist);
+		     ht;
+		     ht = rtnl_dereference(ht->next))
+			if (!ht_empty(ht)) {
+				*last = false;
+				break;
+			}
+	}
+
+ret:
+	return ret;
 }
 
 #define NR_U32_NODE (1<<12)
@@ -860,7 +871,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
-	err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy);
+	err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index ae7e4f5b348b..eb0e9bab54c1 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -912,7 +912,7 @@ static int em_meta_change(struct net *net, void *data, int len,
 	struct tcf_meta_hdr *hdr;
 	struct meta_match *meta = NULL;
 
-	err = nla_parse(tb, TCA_EM_META_MAX, data, len, meta_policy);
+	err = nla_parse(tb, TCA_EM_META_MAX, data, len, meta_policy, NULL);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index fbb7ebfc58c6..03b677bc0700 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -314,7 +314,7 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla,
 	if (!nla)
 		return 0;
 
-	err = nla_parse_nested(tb, TCA_EMATCH_TREE_MAX, nla, em_policy);
+	err = nla_parse_nested(tb, TCA_EMATCH_TREE_MAX, nla, em_policy, NULL);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index bcf49cd22786..bbe57d57b67f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -251,6 +251,15 @@ int qdisc_set_default(const char *name)
 	return ops ? 0 : -ENOENT;
 }
 
+#ifdef CONFIG_NET_SCH_DEFAULT
+/* Set default value from kernel config */
+static int __init sch_default_qdisc(void)
+{
+	return qdisc_set_default(CONFIG_DEFAULT_NET_SCH);
+}
+late_initcall(sch_default_qdisc);
+#endif
+
 /* We know handle. Find qdisc among all qdisc's attached to device
  * (root qdisc, all its children, children of children etc.)
  * Note: caller either uses rtnl or rcu_read_lock()
@@ -274,7 +283,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	return NULL;
 }
 
-void qdisc_hash_add(struct Qdisc *q)
+void qdisc_hash_add(struct Qdisc *q, bool invisible)
 {
 	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
 		struct Qdisc *root = qdisc_dev(q)->qdisc;
@@ -282,6 +291,8 @@ void qdisc_hash_add(struct Qdisc *q)
 		WARN_ON_ONCE(root == &noop_qdisc);
 		ASSERT_RTNL();
 		hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle);
+		if (invisible)
+			q->flags |= TCQ_F_INVISIBLE;
 	}
 }
 EXPORT_SYMBOL(qdisc_hash_add);
@@ -455,7 +466,7 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt)
 	u16 *tab = NULL;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy);
+	err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy, NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 	if (!tb[TCA_STAB_BASE])
@@ -1003,7 +1014,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 				goto err_out4;
 		}
 
-		qdisc_hash_add(sch);
+		qdisc_hash_add(sch, false);
 
 		return sch;
 	}
@@ -1114,7 +1125,8 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
  * Delete/get qdisc.
  */
 
-static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
+static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
+			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcmsg *tcm = nlmsg_data(n);
@@ -1129,7 +1141,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
+	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -1183,7 +1195,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
  * Create/change qdisc.
  */
 
-static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
+static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
+			   struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcmsg *tcm;
@@ -1198,7 +1211,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 
 replay:
 	/* Reinit, just in case something touches this. */
-	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
+	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -1401,9 +1414,14 @@ nla_put_failure:
 	return -1;
 }
 
-static bool tc_qdisc_dump_ignore(struct Qdisc *q)
+static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible)
 {
-	return (q->flags & TCQ_F_BUILTIN) ? true : false;
+	if (q->flags & TCQ_F_BUILTIN)
+		return true;
+	if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible)
+		return true;
+
+	return false;
 }
 
 static int qdisc_notify(struct net *net, struct sk_buff *oskb,
@@ -1417,12 +1435,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (old && !tc_qdisc_dump_ignore(old)) {
+	if (old && !tc_qdisc_dump_ignore(old, false)) {
 		if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq,
 				  0, RTM_DELQDISC) < 0)
 			goto err_out;
 	}
-	if (new && !tc_qdisc_dump_ignore(new)) {
+	if (new && !tc_qdisc_dump_ignore(new, false)) {
 		if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq,
 				  old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
 			goto err_out;
@@ -1439,7 +1457,8 @@ err_out:
 
 static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 			      struct netlink_callback *cb,
-			      int *q_idx_p, int s_q_idx, bool recur)
+			      int *q_idx_p, int s_q_idx, bool recur,
+			      bool dump_invisible)
 {
 	int ret = 0, q_idx = *q_idx_p;
 	struct Qdisc *q;
@@ -1452,7 +1471,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 	if (q_idx < s_q_idx) {
 		q_idx++;
 	} else {
-		if (!tc_qdisc_dump_ignore(q) &&
+		if (!tc_qdisc_dump_ignore(q, dump_invisible) &&
 		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				  RTM_NEWQDISC) <= 0)
@@ -1474,7 +1493,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 			q_idx++;
 			continue;
 		}
-		if (!tc_qdisc_dump_ignore(q) &&
+		if (!tc_qdisc_dump_ignore(q, dump_invisible) &&
 		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				  RTM_NEWQDISC) <= 0)
@@ -1496,12 +1515,21 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 	int idx, q_idx;
 	int s_idx, s_q_idx;
 	struct net_device *dev;
+	const struct nlmsghdr *nlh = cb->nlh;
+	struct tcmsg *tcm = nlmsg_data(nlh);
+	struct nlattr *tca[TCA_MAX + 1];
+	int err;
 
 	s_idx = cb->args[0];
 	s_q_idx = q_idx = cb->args[1];
 
 	idx = 0;
 	ASSERT_RTNL();
+
+	err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+	if (err < 0)
+		return err;
+
 	for_each_netdev(net, dev) {
 		struct netdev_queue *dev_queue;
 
@@ -1512,13 +1540,14 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 		q_idx = 0;
 
 		if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx,
-				       true) < 0)
+				       true, tca[TCA_DUMP_INVISIBLE]) < 0)
 			goto done;
 
 		dev_queue = dev_ingress_queue(dev);
 		if (dev_queue &&
 		    tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb,
-				       &q_idx, s_q_idx, false) < 0)
+				       &q_idx, s_q_idx, false,
+				       tca[TCA_DUMP_INVISIBLE]) < 0)
 			goto done;
 
 cont:
@@ -1540,7 +1569,8 @@ done:
 
 
 
-static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
+static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
+			 struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcmsg *tcm = nlmsg_data(n);
@@ -1559,7 +1589,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
+	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -1762,7 +1792,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb,
 {
 	struct qdisc_dump_args arg;
 
-	if (tc_qdisc_dump_ignore(q) ||
+	if (tc_qdisc_dump_ignore(q, false) ||
 	    *t_p < s_t || !q->ops->cl_ops ||
 	    (tcm->tcm_parent &&
 	     TC_H_MAJ(tcm->tcm_parent) != q->handle)) {
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 2209c2ddacbf..40cbceed4de8 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -214,7 +214,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
 	if (opt == NULL)
 		return -EINVAL;
 
-	error = nla_parse_nested(tb, TCA_ATM_MAX, opt, atm_policy);
+	error = nla_parse_nested(tb, TCA_ATM_MAX, opt, atm_policy, NULL);
 	if (error < 0)
 		return error;
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index d6ca18dc04c3..7415859fd4c3 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1137,7 +1137,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
 	struct tc_ratespec *r;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy);
+	err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1161,6 +1161,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
 				      sch->handle);
 	if (!q->link.q)
 		q->link.q = &noop_qdisc;
+	else
+		qdisc_hash_add(q->link.q, true);
 
 	q->link.priority = TC_CBQ_MAXPRIO - 1;
 	q->link.priority2 = TC_CBQ_MAXPRIO - 1;
@@ -1472,7 +1474,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy);
+	err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1600,6 +1602,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid);
 	if (!cl->q)
 		cl->q = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->q, true);
+
 	cl->common.classid = classid;
 	cl->tparent = parent;
 	cl->qdisc = sch;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 3b86a97bc67c..d00f4c7c2f3a 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -58,7 +58,6 @@ struct choke_sched_data {
 
 /* Variables */
 	struct red_vars  vars;
-	struct tcf_proto __rcu *filter_list;
 	struct {
 		u32	prob_drop;	/* Early probability drops */
 		u32	prob_mark;	/* Early probability marks */
@@ -152,11 +151,6 @@ static inline void choke_set_classid(struct sk_buff *skb, u16 classid)
 	choke_skb_cb(skb)->classid = classid;
 }
 
-static u16 choke_get_classid(const struct sk_buff *skb)
-{
-	return choke_skb_cb(skb)->classid;
-}
-
 /*
  * Compare flow of two packets
  *  Returns true only if source and destination address and port match.
@@ -188,40 +182,6 @@ static bool choke_match_flow(struct sk_buff *skb1,
 }
 
 /*
- * Classify flow using either:
- *  1. pre-existing classification result in skb
- *  2. fast internal classification
- *  3. use TC filter based classification
- */
-static bool choke_classify(struct sk_buff *skb,
-			   struct Qdisc *sch, int *qerr)
-
-{
-	struct choke_sched_data *q = qdisc_priv(sch);
-	struct tcf_result res;
-	struct tcf_proto *fl;
-	int result;
-
-	fl = rcu_dereference_bh(q->filter_list);
-	result = tc_classify(skb, fl, &res, false);
-	if (result >= 0) {
-#ifdef CONFIG_NET_CLS_ACT
-		switch (result) {
-		case TC_ACT_STOLEN:
-		case TC_ACT_QUEUED:
-			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-		case TC_ACT_SHOT:
-			return false;
-		}
-#endif
-		choke_set_classid(skb, TC_H_MIN(res.classid));
-		return true;
-	}
-
-	return false;
-}
-
-/*
  * Select a packet at random from queue
  * HACK: since queue can have holes from previous deletion; retry several
  *   times to find a random skb but then just give up and return the head
@@ -257,25 +217,15 @@ static bool choke_match_random(const struct choke_sched_data *q,
 		return false;
 
 	oskb = choke_peek_random(q, pidx);
-	if (rcu_access_pointer(q->filter_list))
-		return choke_get_classid(nskb) == choke_get_classid(oskb);
-
 	return choke_match_flow(oskb, nskb);
 }
 
 static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			 struct sk_buff **to_free)
 {
-	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	struct choke_sched_data *q = qdisc_priv(sch);
 	const struct red_parms *p = &q->parms;
 
-	if (rcu_access_pointer(q->filter_list)) {
-		/* If using external classifiers, get result and record it. */
-		if (!choke_classify(skb, sch, &ret))
-			goto other_drop;	/* Packet was eaten by filter */
-	}
-
 	choke_skb_cb(skb)->keys_valid = 0;
 	/* Compute average queue usage (see RED) */
 	q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen);
@@ -339,12 +289,6 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 congestion_drop:
 	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
-
-other_drop:
-	if (ret & __NET_XMIT_BYPASS)
-		qdisc_qstats_drop(sch);
-	__qdisc_drop(skb, to_free);
-	return ret;
 }
 
 static struct sk_buff *choke_dequeue(struct Qdisc *sch)
@@ -413,7 +357,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy);
+	err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -538,7 +482,6 @@ static void choke_destroy(struct Qdisc *sch)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
 	choke_free(q->tab);
 }
 
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 5bfa79ee657c..c518a1efcb9d 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -140,7 +140,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy);
+	err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index bb4cbdf75004..58a8c32eab23 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -76,7 +76,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy);
+	err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -117,6 +117,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 					       &pfifo_qdisc_ops, classid);
 	if (cl->qdisc == NULL)
 		cl->qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->qdisc, true);
 
 	if (tca[TCA_RATE]) {
 		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 802ac7c2e5e8..1c0f877f673a 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -129,7 +129,7 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
 	if (!opt)
 		goto errout;
 
-	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy);
+	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL);
 	if (err < 0)
 		goto errout;
 
@@ -201,9 +201,13 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
 
 	if (p->set_tc_index) {
+		int wlen = skb_network_offset(skb);
+
 		switch (tc_skb_protocol(skb)) {
 		case htons(ETH_P_IP):
-			if (skb_cow_head(skb, sizeof(struct iphdr)))
+			wlen += sizeof(struct iphdr);
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
 				goto drop;
 
 			skb->tc_index = ipv4_get_dsfield(ip_hdr(skb))
@@ -211,7 +215,9 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			break;
 
 		case htons(ETH_P_IPV6):
-			if (skb_cow_head(skb, sizeof(struct ipv6hdr)))
+			wlen += sizeof(struct ipv6hdr);
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
 				goto drop;
 
 			skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb))
@@ -336,7 +342,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		goto errout;
 
-	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy);
+	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL);
 	if (err < 0)
 		goto errout;
 
@@ -368,6 +374,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle);
 	if (p->q == NULL)
 		p->q = &noop_qdisc;
+	else
+		qdisc_hash_add(p->q, true);
 
 	pr_debug("%s: qdisc %p\n", __func__, p->q);
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a4f738ac7728..da4f67bda0ee 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -698,7 +698,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy);
+	err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9f3a884d1590..18bbb5476c83 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -288,7 +288,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
-	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -307,7 +306,6 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
-	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams,
 			    &flow->cvars, &q->cstats, qdisc_pkt_len,
@@ -385,7 +383,8 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FQ_CODEL_MAX, opt, fq_codel_policy);
+	err = nla_parse_nested(tb, TCA_FQ_CODEL_MAX, opt, fq_codel_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 	if (tb[TCA_FQ_CODEL_FLOWS]) {
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b052b27a984e..52a2c55f6d9e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -794,8 +794,8 @@ static void attach_default_qdiscs(struct net_device *dev)
 		}
 	}
 #ifdef CONFIG_NET_SCHED
-	if (dev->qdisc)
-		qdisc_hash_add(dev->qdisc);
+	if (dev->qdisc != &noop_qdisc)
+		qdisc_hash_add(dev->qdisc, false);
 #endif
 }
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index c78a093c551a..17c7130454bd 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -401,7 +401,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy);
+	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -470,7 +470,7 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy);
+	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3ffaa6fb0990..5cb82f6c1b06 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -957,7 +957,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_HFSC_MAX, opt, hfsc_policy);
+	err = nla_parse_nested(tb, TCA_HFSC_MAX, opt, hfsc_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1066,6 +1066,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 				      &pfifo_qdisc_ops, classid);
 	if (cl->qdisc == NULL)
 		cl->qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->qdisc, true);
 	INIT_LIST_HEAD(&cl->children);
 	cl->vt_tree = RB_ROOT;
 	cl->cf_tree = RB_ROOT;
@@ -1425,6 +1427,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 					  sch->handle);
 	if (q->root.qdisc == NULL)
 		q->root.qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(q->root.qdisc, true);
 	INIT_LIST_HEAD(&q->root.children);
 	q->root.vt_tree = RB_ROOT;
 	q->root.cf_tree = RB_ROOT;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 2fae8b5f1b80..c19d346e6c5a 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -529,7 +529,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy);
+	err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 4cd5fb134bc9..570ef3b0c09b 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1017,7 +1017,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy);
+	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1342,7 +1342,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	if (!opt)
 		goto failure;
 
-	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy);
+	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL);
 	if (err < 0)
 		goto failure;
 
@@ -1460,6 +1460,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		qdisc_class_hash_insert(&q->clhash, &cl->common);
 		if (parent)
 			parent->children++;
+		if (cl->un.leaf.q != &noop_qdisc)
+			qdisc_hash_add(cl->un.leaf.q, true);
 	} else {
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 20b7f1646f69..cadfdd4f1e52 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -84,7 +84,7 @@ static void mq_attach(struct Qdisc *sch)
 			qdisc_destroy(old);
 #ifdef CONFIG_NET_SCHED
 		if (ntx < dev->real_num_tx_queues)
-			qdisc_hash_add(qdisc);
+			qdisc_hash_add(qdisc, false);
 #endif
 
 	}
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 922683418e53..0a4cf27ea54b 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -21,14 +21,13 @@
 
 struct mqprio_sched {
 	struct Qdisc		**qdiscs;
-	int hw_owned;
+	int hw_offload;
 };
 
 static void mqprio_destroy(struct Qdisc *sch)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct mqprio_sched *priv = qdisc_priv(sch);
-	struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO};
 	unsigned int ntx;
 
 	if (priv->qdiscs) {
@@ -39,10 +38,15 @@ static void mqprio_destroy(struct Qdisc *sch)
 		kfree(priv->qdiscs);
 	}
 
-	if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc)
+	if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) {
+		struct tc_mqprio_qopt offload = { 0 };
+		struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO,
+					   { .mqprio = &offload } };
+
 		dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
-	else
+	} else {
 		netdev_set_num_tc(dev, 0);
+	}
 }
 
 static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
@@ -59,15 +63,20 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
 			return -EINVAL;
 	}
 
-	/* net_device does not support requested operation */
-	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
-		return -EINVAL;
+	/* Limit qopt->hw to maximum supported offload value.  Drivers have
+	 * the option of overriding this later if they don't support the a
+	 * given offload type.
+	 */
+	if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX)
+		qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX;
 
-	/* if hw owned qcount and qoffset are taken from LLD so
-	 * no reason to verify them here
+	/* If hardware offload is requested we will leave it to the device
+	 * to either populate the queue counts itself or to validate the
+	 * provided queue counts.  If ndo_setup_tc is not present then
+	 * hardware doesn't support offload and we should return an error.
 	 */
 	if (qopt->hw)
-		return 0;
+		return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL;
 
 	for (i = 0; i < qopt->num_tc; i++) {
 		unsigned int last = qopt->offset[i] + qopt->count[i];
@@ -139,13 +148,15 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	 * supplied and verified mapping
 	 */
 	if (qopt->hw) {
-		struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO,
-					  { .tc = qopt->num_tc }};
+		struct tc_mqprio_qopt offload = *qopt;
+		struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO,
+					   { .mqprio = &offload } };
 
-		priv->hw_owned = 1;
 		err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
 		if (err)
 			return err;
+
+		priv->hw_offload = offload.hw;
 	} else {
 		netdev_set_num_tc(dev, qopt->num_tc);
 		for (i = 0; i < qopt->num_tc; i++)
@@ -175,7 +186,7 @@ static void mqprio_attach(struct Qdisc *sch)
 		if (old)
 			qdisc_destroy(old);
 		if (ntx < dev->real_num_tx_queues)
-			qdisc_hash_add(qdisc);
+			qdisc_hash_add(qdisc, false);
 	}
 	kfree(priv->qdiscs);
 	priv->qdiscs = NULL;
@@ -243,7 +254,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 	opt.num_tc = netdev_get_num_tc(dev);
 	memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
-	opt.hw = priv->hw_owned;
+	opt.hw = priv->hw_offload;
 
 	for (i = 0; i < netdev_get_num_tc(dev); i++) {
 		opt.count[i] = dev->tc_to_txq[i].count;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index e7839a0d0eaa..43a3a10b3c81 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -217,6 +217,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				sch_tree_lock(sch);
 				old = q->queues[i];
 				q->queues[i] = child;
+				if (child != &noop_qdisc)
+					qdisc_hash_add(child, true);
 
 				if (old != &noop_qdisc) {
 					qdisc_tree_reduce_backlog(old,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index c8bb62a1e744..f0ce4780f395 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -462,7 +462,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	/* If a delay is expected, orphan the skb. (orphaning usually takes
 	 * place at TX completion time, so _before_ the link transit delay)
 	 */
-	if (q->latency || q->jitter)
+	if (q->latency || q->jitter || q->rate)
 		skb_orphan_partial(skb);
 
 	/*
@@ -530,21 +530,31 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		now = psched_get_time();
 
 		if (q->rate) {
-			struct sk_buff *last;
+			struct netem_skb_cb *last = NULL;
+
+			if (sch->q.tail)
+				last = netem_skb_cb(sch->q.tail);
+			if (q->t_root.rb_node) {
+				struct sk_buff *t_skb;
+				struct netem_skb_cb *t_last;
+
+				t_skb = netem_rb_to_skb(rb_last(&q->t_root));
+				t_last = netem_skb_cb(t_skb);
+				if (!last ||
+				    t_last->time_to_send > last->time_to_send) {
+					last = t_last;
+				}
+			}
 
-			if (sch->q.qlen)
-				last = sch->q.tail;
-			else
-				last = netem_rb_to_skb(rb_last(&q->t_root));
 			if (last) {
 				/*
 				 * Last packet in queue is reference point (now),
 				 * calculate this time bonus and subtract
 				 * from delay.
 				 */
-				delay -= netem_skb_cb(last)->time_to_send - now;
+				delay -= last->time_to_send - now;
 				delay = max_t(psched_tdiff_t, 0, delay);
-				now = netem_skb_cb(last)->time_to_send;
+				now = last->time_to_send;
 			}
 
 			delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q);
@@ -833,7 +843,7 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 
 	if (nested_len >= nla_attr_size(0))
 		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
-				 nested_len, policy);
+				 nested_len, policy, NULL);
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 	return 0;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 5c3a99d6aa82..6c2791d6102d 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -190,7 +190,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy);
+	err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index d4d7db267b6e..92c2e6d448d7 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -192,8 +192,11 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		qdisc_destroy(child);
 	}
 
-	for (i = oldbands; i < q->bands; i++)
+	for (i = oldbands; i < q->bands; i++) {
 		q->queues[i] = queues[i];
+		if (q->queues[i] != &noop_qdisc)
+			qdisc_hash_add(q->queues[i], true);
+	}
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f9e712ce2d15..041eba3006cc 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -418,7 +418,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy);
+	err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy,
+			       NULL);
 	if (err < 0)
 		return err;
 
@@ -494,6 +495,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 			goto destroy_class;
 	}
 
+	if (cl->qdisc != &noop_qdisc)
+		qdisc_hash_add(cl->qdisc, true);
 	sch_tree_lock(sch);
 	qdisc_class_hash_insert(&q->clhash, &cl->common);
 	sch_tree_unlock(sch);
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 249b2a18acbd..11292adce412 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -173,7 +173,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_RED_MAX, opt, red_policy);
+	err = nla_parse_nested(tb, TCA_RED_MAX, opt, red_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -191,6 +191,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 			return PTR_ERR(child);
 	}
 
+	if (child != &noop_qdisc)
+		qdisc_hash_add(child, true);
 	sch_tree_lock(sch);
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index fe6963d21519..0f777273ba29 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -495,7 +495,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 	int err;
 
 	if (opt) {
-		err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy);
+		err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy, NULL);
 		if (err < 0)
 			return -EINVAL;
 
@@ -513,6 +513,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 	if (IS_ERR(child))
 		return PTR_ERR(child);
 
+	if (child != &noop_qdisc)
+		qdisc_hash_add(child, true);
 	sch_tree_lock(sch);
 
 	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 42e8c8615e65..b00e02c139de 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -714,9 +714,8 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	int i;
 
-	q->perturb_timer.function = sfq_perturbation;
-	q->perturb_timer.data = (unsigned long)sch;
-	init_timer_deferrable(&q->perturb_timer);
+	setup_deferrable_timer(&q->perturb_timer, sfq_perturbation,
+			       (unsigned long)sch);
 
 	for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) {
 		q->dep[i].next = i + SFQ_MAX_FLOWS;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 303355c449ab..b2e4b6ad241a 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -315,7 +315,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	s64 buffer, mtu;
 	u64 rate64 = 0, prate64 = 0;
 
-	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
+	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -396,6 +396,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
+		if (child != &noop_qdisc)
+			qdisc_hash_add(child, true);
 	}
 	q->limit = qopt->limit;
 	if (tb[TCA_TBF_PBURST])
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 2a6835b4562b..a9708da28eb5 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -71,9 +71,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 {
 	struct net *net = sock_net(sk);
 	struct sctp_sock *sp;
-	int i;
 	sctp_paramhdr_t *p;
-	int err;
+	int i;
 
 	/* Retrieve the SCTP per socket area.  */
 	sp = sctp_sk((struct sock *)sk);
@@ -247,6 +246,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 	if (!sctp_ulpq_init(&asoc->ulpq, asoc))
 		goto fail_init;
 
+	if (sctp_stream_new(asoc, gfp))
+		goto fail_init;
+
 	/* Assume that peer would support both address types unless we are
 	 * told otherwise.
 	 */
@@ -264,9 +266,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 
 	/* AUTH related initializations */
 	INIT_LIST_HEAD(&asoc->endpoint_shared_keys);
-	err = sctp_auth_asoc_copy_shkeys(ep, asoc, gfp);
-	if (err)
-		goto fail_init;
+	if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp))
+		goto stream_free;
 
 	asoc->active_key_id = ep->active_key_id;
 	asoc->prsctp_enable = ep->prsctp_enable;
@@ -289,6 +290,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 
 	return asoc;
 
+stream_free:
+	sctp_stream_free(asoc->stream);
 fail_init:
 	sock_put(asoc->base.sk);
 	sctp_endpoint_put(asoc->ep);
@@ -1409,7 +1412,7 @@ sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
 /* Update the association's pmtu and frag_point by going through all the
  * transports. This routine is called when a transport's PMTU has changed.
  */
-void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
 {
 	struct sctp_transport *t;
 	__u32 pmtu = 0;
@@ -1421,8 +1424,8 @@ void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
 	list_for_each_entry(t, &asoc->peer.transport_addr_list,
 				transports) {
 		if (t->pmtu_pending && t->dst) {
-			sctp_transport_update_pmtu(sk, t,
-						   SCTP_TRUNC4(dst_mtu(t->dst)));
+			sctp_transport_update_pmtu(
+					t, SCTP_TRUNC4(dst_mtu(t->dst)));
 			t->pmtu_pending = 0;
 		}
 		if (!pmtu || (t->pathmtu < pmtu))
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index e3621cb4827f..697721a7a3f1 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -306,14 +306,24 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 
 	if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
 	    time_after(jiffies, chunk->msg->expires_at)) {
-		if (chunk->sent_count)
+		struct sctp_stream_out *streamout =
+			&chunk->asoc->stream->out[chunk->sinfo.sinfo_stream];
+
+		if (chunk->sent_count) {
 			chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
-		else
+			streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+		} else {
 			chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+			streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+		}
 		return 1;
 	} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
 		   chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
+		struct sctp_stream_out *streamout =
+			&chunk->asoc->stream->out[chunk->sinfo.sinfo_stream];
+
 		chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+		streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
 		return 1;
 	} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
 		   chunk->msg->expires_at &&
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 2a28ab20487f..0e06a278d2a9 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -401,10 +401,10 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 
 	if (t->param_flags & SPP_PMTUD_ENABLE) {
 		/* Update transports view of the MTU */
-		sctp_transport_update_pmtu(sk, t, pmtu);
+		sctp_transport_update_pmtu(t, pmtu);
 
 		/* Update association pmtu. */
-		sctp_assoc_sync_pmtu(sk, asoc);
+		sctp_assoc_sync_pmtu(asoc);
 	}
 
 	/* Retransmit with the new pmtu setting.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 063baac5b9fe..961ee59f696a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr)
 
 /* Create and initialize a new sk for the socket to be returned by accept(). */
 static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
-					     struct sctp_association *asoc)
+					     struct sctp_association *asoc,
+					     bool kern)
 {
 	struct sock *newsk;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct sctp6_sock *newsctp6sk;
 	struct ipv6_txoptions *opt;
 
-	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
+	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern);
 	if (!newsk)
 		goto out;
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 71ce6b945dcb..1409a875ad8e 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -86,43 +86,53 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 {
 	struct sctp_transport *tp = packet->transport;
 	struct sctp_association *asoc = tp->asoc;
+	struct sock *sk;
 
 	pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
-
 	packet->vtag = vtag;
 
-	if (asoc && tp->dst) {
-		struct sock *sk = asoc->base.sk;
-
-		rcu_read_lock();
-		if (__sk_dst_get(sk) != tp->dst) {
-			dst_hold(tp->dst);
-			sk_setup_caps(sk, tp->dst);
-		}
-
-		if (sk_can_gso(sk)) {
-			struct net_device *dev = tp->dst->dev;
+	/* do the following jobs only once for a flush schedule */
+	if (!sctp_packet_empty(packet))
+		return;
 
-			packet->max_size = dev->gso_max_size;
-		} else {
-			packet->max_size = asoc->pathmtu;
-		}
-		rcu_read_unlock();
+	/* set packet max_size with pathmtu */
+	packet->max_size = tp->pathmtu;
+	if (!asoc)
+		return;
 
-	} else {
-		packet->max_size = tp->pathmtu;
+	/* update dst or transport pathmtu if in need */
+	sk = asoc->base.sk;
+	if (!sctp_transport_dst_check(tp)) {
+		sctp_transport_route(tp, NULL, sctp_sk(sk));
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
+	} else if (!sctp_transport_pmtu_check(tp)) {
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
 	}
 
-	if (ecn_capable && sctp_packet_empty(packet)) {
-		struct sctp_chunk *chunk;
+	/* If there a is a prepend chunk stick it on the list before
+	 * any other chunks get appended.
+	 */
+	if (ecn_capable) {
+		struct sctp_chunk *chunk = sctp_get_ecne_prepend(asoc);
 
-		/* If there a is a prepend chunk stick it on the list before
-		 * any other chunks get appended.
-		 */
-		chunk = sctp_get_ecne_prepend(asoc);
 		if (chunk)
 			sctp_packet_append_chunk(packet, chunk);
 	}
+
+	if (!tp->dst)
+		return;
+
+	/* set packet max_size with gso_max_size if gso is enabled*/
+	rcu_read_lock();
+	if (__sk_dst_get(sk) != tp->dst) {
+		dst_hold(tp->dst);
+		sk_setup_caps(sk, tp->dst);
+	}
+	packet->max_size = sk_can_gso(sk) ? tp->dst->dev->gso_max_size
+					  : asoc->pathmtu;
+	rcu_read_unlock();
 }
 
 /* Initialize the packet structure. */
@@ -546,7 +556,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	struct sctp_association *asoc = tp->asoc;
 	struct sctp_chunk *chunk, *tmp;
 	int pkt_count, gso = 0;
-	int confirm;
 	struct dst_entry *dst;
 	struct sk_buff *head;
 	struct sctphdr *sh;
@@ -583,12 +592,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	sh->vtag = htonl(packet->vtag);
 	sh->checksum = 0;
 
-	/* update dst if in need */
-	if (!sctp_transport_dst_check(tp)) {
-		sctp_transport_route(tp, NULL, sctp_sk(sk));
-		if (asoc && asoc->param_flags & SPP_PMTUD_ENABLE)
-			sctp_assoc_sync_pmtu(sk, asoc);
-	}
+	/* drop packet if no dst */
 	dst = dst_clone(tp->dst);
 	if (!dst) {
 		IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
@@ -625,13 +629,13 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 			asoc->peer.last_sent_to = tp;
 	}
 	head->ignore_df = packet->ipfragok;
-	confirm = tp->dst_pending_confirm;
-	if (confirm)
+	if (tp->dst_pending_confirm)
 		skb_set_dst_pending_confirm(head, 1);
 	/* neighbour should be confirmed on successful transmission or
 	 * positive error
 	 */
-	if (tp->af_specific->sctp_xmit(head, tp) >= 0 && confirm)
+	if (tp->af_specific->sctp_xmit(head, tp) >= 0 &&
+	    tp->dst_pending_confirm)
 		tp->dst_pending_confirm = 0;
 
 out:
@@ -705,7 +709,7 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
 	 */
 
 	if ((sctp_sk(asoc->base.sk)->nodelay || inflight == 0) &&
-	    !chunk->msg->force_delay)
+	    !asoc->force_delay)
 		/* Nothing unacked */
 		return SCTP_XMIT_OK;
 
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index db352e5d61f8..fe4c3d462f6e 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -353,6 +353,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 	struct sctp_chunk *chk, *temp;
 
 	list_for_each_entry_safe(chk, temp, queue, transmitted_list) {
+		struct sctp_stream_out *streamout;
+
 		if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
 		    chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
 			continue;
@@ -361,8 +363,10 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 		sctp_insert_list(&asoc->outqueue.abandoned,
 				 &chk->transmitted_list);
 
+		streamout = &asoc->stream->out[chk->sinfo.sinfo_stream];
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
+		streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
 
 		if (!chk->tsn_gap_acked) {
 			if (chk->transport)
@@ -382,19 +386,26 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 }
 
 static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
-				    struct sctp_sndrcvinfo *sinfo,
-				    struct list_head *queue, int msg_len)
+				    struct sctp_sndrcvinfo *sinfo, int msg_len)
 {
+	struct sctp_outq *q = &asoc->outqueue;
 	struct sctp_chunk *chk, *temp;
 
-	list_for_each_entry_safe(chk, temp, queue, list) {
+	list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) {
 		if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
 		    chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
 			continue;
 
 		list_del_init(&chk->list);
+		q->out_qlen -= chk->skb->len;
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+		if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) {
+			struct sctp_stream_out *streamout =
+				&asoc->stream->out[chk->sinfo.sinfo_stream];
+
+			streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+		}
 
 		msg_len -= SCTP_DATA_SNDSIZE(chk) +
 			   sizeof(struct sk_buff) +
@@ -431,9 +442,7 @@ void sctp_prsctp_prune(struct sctp_association *asoc,
 			return;
 	}
 
-	sctp_prsctp_prune_unsent(asoc, sinfo,
-				 &asoc->outqueue.out_chunk_list,
-				 msg_len);
+	sctp_prsctp_prune_unsent(asoc, sinfo, msg_len);
 }
 
 /* Mark all the eligible packets on a transport for retransmission.  */
@@ -1027,8 +1036,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
 			/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
 			 * stream identifier.
 			 */
-			if (chunk->sinfo.sinfo_stream >=
-			    asoc->c.sinit_num_ostreams) {
+			if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) {
 
 				/* Mark as failed send. */
 				sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 206377fe91ec..a0b29d43627f 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -361,8 +361,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 	sctp_seq_dump_remote_addrs(seq, assoc);
 	seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d "
 		   "%8d %8d %8d %8d",
-		assoc->hbinterval, assoc->c.sinit_max_instreams,
-		assoc->c.sinit_num_ostreams, assoc->max_retrans,
+		assoc->hbinterval, assoc->stream->incnt,
+		assoc->stream->outcnt, assoc->max_retrans,
 		assoc->init_retries, assoc->shutdown_retries,
 		assoc->rtx_data_chunks,
 		atomic_read(&sk->sk_wmem_alloc),
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 1b6d4574d2b0..989a900383b5 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb)
 
 /* Create and initialize a new sk for the socket returned by accept(). */
 static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
-					     struct sctp_association *asoc)
+					     struct sctp_association *asoc,
+					     bool kern)
 {
 	struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
-			sk->sk_prot, 0);
+			sk->sk_prot, kern);
 	struct inet_sock *newinet;
 
 	if (!newsk)
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 969a30c7bb54..8a08f13469c4 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1512,14 +1512,12 @@ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len,
 			  struct iov_iter *from)
 {
 	void *target;
-	ssize_t copied;
 
 	/* Make room in chunk for data.  */
 	target = skb_put(chunk->skb, len);
 
 	/* Copy data (whole iovec) into chunk */
-	copied = copy_from_iter(target, len, from);
-	if (copied != len)
+	if (!copy_from_iter_full(target, len, from))
 		return -EFAULT;
 
 	/* Adjust the chunk length field.  */
@@ -2460,15 +2458,10 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 	 * association.
 	 */
 	if (!asoc->temp) {
-		int error;
-
-		asoc->stream = sctp_stream_new(asoc->c.sinit_max_instreams,
-					       asoc->c.sinit_num_ostreams, gfp);
-		if (!asoc->stream)
+		if (sctp_stream_init(asoc, gfp))
 			goto clean_up;
 
-		error = sctp_assoc_set_id(asoc, gfp);
-		if (error)
+		if (sctp_assoc_set_id(asoc, gfp))
 			goto clean_up;
 	}
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index e03bb1aab4d0..4f5e6cfc7f60 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3872,9 +3872,18 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net,
 		else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST)
 			reply = sctp_process_strreset_inreq(
 				(struct sctp_association *)asoc, param, &ev);
-		/* More handles for other types will be added here, by now it
-		 * just ignores other types.
-		 */
+		else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST)
+			reply = sctp_process_strreset_tsnreq(
+				(struct sctp_association *)asoc, param, &ev);
+		else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS)
+			reply = sctp_process_strreset_addstrm_out(
+				(struct sctp_association *)asoc, param, &ev);
+		else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS)
+			reply = sctp_process_strreset_addstrm_in(
+				(struct sctp_association *)asoc, param, &ev);
+		else if (param.p->type == SCTP_PARAM_RESET_RESPONSE)
+			reply = sctp_process_strreset_resp(
+				(struct sctp_association *)asoc, param, &ev);
 
 		if (ev)
 			sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
@@ -3946,7 +3955,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net,
 
 	/* Silently discard the chunk if stream-id is not valid */
 	sctp_walk_fwdtsn(skip, chunk) {
-		if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+		if (ntohs(skip->stream) >= asoc->stream->incnt)
 			goto discard_noforce;
 	}
 
@@ -4017,7 +4026,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_fast(
 
 	/* Silently discard the chunk if stream-id is not valid */
 	sctp_walk_fwdtsn(skip, chunk) {
-		if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+		if (ntohs(skip->stream) >= asoc->stream->incnt)
 			goto gen_shutdown;
 	}
 
@@ -6353,7 +6362,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 * and discard the DATA chunk.
 	 */
 	sid = ntohs(data_hdr->stream);
-	if (sid >= asoc->c.sinit_max_instreams) {
+	if (sid >= asoc->stream->incnt) {
 		/* Mark tsn as received even though we drop it */
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn));
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6f0a9be50f50..f16c8d97b7f3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1907,7 +1907,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	}
 
 	if (asoc->pmtu_pending)
-		sctp_assoc_pending_pmtu(sk, asoc);
+		sctp_assoc_pending_pmtu(asoc);
 
 	/* If fragmentation is disabled and the message length exceeds the
 	 * association fragmentation point, return EMSGSIZE.  The I-D
@@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	}
 
 	/* Check for invalid stream. */
-	if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) {
+	if (sinfo->sinfo_stream >= asoc->stream->outcnt) {
 		err = -EINVAL;
 		goto out_free;
 	}
@@ -1965,7 +1965,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 		err = PTR_ERR(datamsg);
 		goto out_free;
 	}
-	datamsg->force_delay = !!(msg->msg_flags & MSG_MORE);
+	asoc->force_delay = !!(msg->msg_flags & MSG_MORE);
 
 	/* Now send the (possibly) fragmented message. */
 	list_for_each_entry(chunk, &datamsg->chunks, frag_list) {
@@ -2435,7 +2435,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 	if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) {
 		if (trans) {
 			trans->pathmtu = params->spp_pathmtu;
-			sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+			sctp_assoc_sync_pmtu(asoc);
 		} else if (asoc) {
 			asoc->pathmtu = params->spp_pathmtu;
 		} else {
@@ -2451,7 +2451,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 				(trans->param_flags & ~SPP_PMTUD) | pmtud_change;
 			if (update) {
 				sctp_transport_pmtu(trans, sctp_opt2sk(sp));
-				sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+				sctp_assoc_sync_pmtu(asoc);
 			}
 		} else if (asoc) {
 			asoc->param_flags =
@@ -3758,6 +3758,39 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_reconfig_supported(struct sock *sk,
+					      char __user *optval,
+					      unsigned int optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EINVAL;
+
+	if (optlen != sizeof(params))
+		goto out;
+
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (asoc) {
+		asoc->reconf_enable = !!params.assoc_value;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		sp->ep->reconf_enable = !!params.assoc_value;
+	} else {
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_setsockopt_enable_strreset(struct sock *sk,
 					   char __user *optval,
 					   unsigned int optlen)
@@ -4038,6 +4071,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_DEFAULT_PRINFO:
 		retval = sctp_setsockopt_default_prinfo(sk, optval, optlen);
 		break;
+	case SCTP_RECONFIG_SUPPORTED:
+		retval = sctp_setsockopt_reconfig_supported(sk, optval, optlen);
+		break;
 	case SCTP_ENABLE_STREAM_RESET:
 		retval = sctp_setsockopt_enable_strreset(sk, optval, optlen);
 		break;
@@ -4116,7 +4152,7 @@ static int sctp_disconnect(struct sock *sk, int flags)
  * descriptor will be returned from accept() to represent the newly
  * formed association.
  */
-static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
+static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern)
 {
 	struct sctp_sock *sp;
 	struct sctp_endpoint *ep;
@@ -4151,7 +4187,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
 	 */
 	asoc = list_entry(ep->asocs.next, struct sctp_association, asocs);
 
-	newsk = sp->pf->create_accept_sk(sk, asoc);
+	newsk = sp->pf->create_accept_sk(sk, asoc, kern);
 	if (!newsk) {
 		error = -ENOMEM;
 		goto out;
@@ -4461,8 +4497,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 	info->sctpi_rwnd = asoc->a_rwnd;
 	info->sctpi_unackdata = asoc->unack_data;
 	info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
-	info->sctpi_instrms = asoc->c.sinit_max_instreams;
-	info->sctpi_outstrms = asoc->c.sinit_num_ostreams;
+	info->sctpi_instrms = asoc->stream->incnt;
+	info->sctpi_outstrms = asoc->stream->outcnt;
 	list_for_each(pos, &asoc->base.inqueue.in_chunk_list)
 		info->sctpi_inqueue++;
 	list_for_each(pos, &asoc->outqueue.out_chunk_list)
@@ -4691,8 +4727,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len,
 	status.sstat_unackdata = asoc->unack_data;
 
 	status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
-	status.sstat_instrms = asoc->c.sinit_max_instreams;
-	status.sstat_outstrms = asoc->c.sinit_num_ostreams;
+	status.sstat_instrms = asoc->stream->incnt;
+	status.sstat_outstrms = asoc->stream->outcnt;
 	status.sstat_fragmentation_point = asoc->frag_point;
 	status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
 	memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr,
@@ -6540,6 +6576,102 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
+					   char __user *optval,
+					   int __user *optlen)
+{
+	struct sctp_stream_out *streamout;
+	struct sctp_association *asoc;
+	struct sctp_prstatus params;
+	int retval = -EINVAL;
+	int policy;
+
+	if (len < sizeof(params))
+		goto out;
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	policy = params.sprstat_policy;
+	if (policy & ~SCTP_PR_SCTP_MASK)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
+	if (!asoc || params.sprstat_sid >= asoc->stream->outcnt)
+		goto out;
+
+	streamout = &asoc->stream->out[params.sprstat_sid];
+	if (policy == SCTP_PR_SCTP_NONE) {
+		params.sprstat_abandoned_unsent = 0;
+		params.sprstat_abandoned_sent = 0;
+		for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
+			params.sprstat_abandoned_unsent +=
+				streamout->abandoned_unsent[policy];
+			params.sprstat_abandoned_sent +=
+				streamout->abandoned_sent[policy];
+		}
+	} else {
+		params.sprstat_abandoned_unsent =
+			streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)];
+		params.sprstat_abandoned_sent =
+			streamout->abandoned_sent[__SCTP_PR_INDEX(policy)];
+	}
+
+	if (put_user(len, optlen) || copy_to_user(optval, &params, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
+static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len,
+					      char __user *optval,
+					      int __user *optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (asoc) {
+		params.assoc_value = asoc->reconf_enable;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		params.assoc_value = sp->ep->reconf_enable;
+	} else {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &params, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_getsockopt_enable_strreset(struct sock *sk, int len,
 					   char __user *optval,
 					   int __user *optlen)
@@ -6748,6 +6880,14 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_pr_assocstatus(sk, len, optval,
 							optlen);
 		break;
+	case SCTP_PR_STREAM_STATUS:
+		retval = sctp_getsockopt_pr_streamstatus(sk, len, optval,
+							 optlen);
+		break;
+	case SCTP_RECONFIG_SUPPORTED:
+		retval = sctp_getsockopt_reconfig_supported(sk, len, optval,
+							    optlen);
+		break;
 	case SCTP_ENABLE_STREAM_RESET:
 		retval = sctp_getsockopt_enable_strreset(sk, len, optval,
 							 optlen);
@@ -7034,6 +7174,9 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 	if (sock->state != SS_UNCONNECTED)
 		goto out;
 
+	if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+		goto out;
+
 	/* If backlog is zero, disable listening. */
 	if (!backlog) {
 		if (sctp_sstate(sk, CLOSED))
@@ -7437,9 +7580,12 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			break;
 
-		if (sk_can_busy_loop(sk) &&
-		    sk_busy_loop(sk, noblock))
-			continue;
+		if (sk_can_busy_loop(sk)) {
+			sk_busy_loop(sk, noblock);
+
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				continue;
+		}
 
 		/* User doesn't want to wait.  */
 		error = -EAGAIN;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 1c6cc04fa3a4..dda53a293986 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -35,33 +35,60 @@
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
 
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp)
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp)
 {
 	struct sctp_stream *stream;
 	int i;
 
 	stream = kzalloc(sizeof(*stream), gfp);
 	if (!stream)
-		return NULL;
+		return -ENOMEM;
 
-	stream->outcnt = outcnt;
+	stream->outcnt = asoc->c.sinit_num_ostreams;
 	stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
 	if (!stream->out) {
 		kfree(stream);
-		return NULL;
+		return -ENOMEM;
 	}
 	for (i = 0; i < stream->outcnt; i++)
 		stream->out[i].state = SCTP_STREAM_OPEN;
 
-	stream->incnt = incnt;
+	asoc->stream = stream;
+
+	return 0;
+}
+
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp)
+{
+	struct sctp_stream *stream = asoc->stream;
+	int i;
+
+	/* Initial stream->out size may be very big, so free it and alloc
+	 * a new one with new outcnt to save memory.
+	 */
+	kfree(stream->out);
+	stream->outcnt = asoc->c.sinit_num_ostreams;
+	stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
+	if (!stream->out)
+		goto nomem;
+
+	for (i = 0; i < stream->outcnt; i++)
+		stream->out[i].state = SCTP_STREAM_OPEN;
+
+	stream->incnt = asoc->c.sinit_max_instreams;
 	stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp);
 	if (!stream->in) {
 		kfree(stream->out);
-		kfree(stream);
-		return NULL;
+		goto nomem;
 	}
 
-	return stream;
+	return 0;
+
+nomem:
+	asoc->stream = NULL;
+	kfree(stream);
+
+	return -ENOMEM;
 }
 
 void sctp_stream_free(struct sctp_stream *stream)
@@ -267,18 +294,6 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 		stream->out = streamout;
 	}
 
-	if (in) {
-		struct sctp_stream_in *streamin;
-
-		streamin = krealloc(stream->in, incnt * sizeof(*streamin),
-				    GFP_KERNEL);
-		if (!streamin)
-			goto out;
-
-		memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
-		stream->in = streamin;
-	}
-
 	chunk = sctp_make_strreset_addstrm(asoc, out, in);
 	if (!chunk)
 		goto out;
@@ -303,13 +318,14 @@ out:
 }
 
 static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param(
-			struct sctp_association *asoc, __u32 resp_seq)
+			struct sctp_association *asoc, __u32 resp_seq,
+			__be16 type)
 {
 	struct sctp_chunk *chunk = asoc->strreset_chunk;
 	struct sctp_reconf_chunk *hdr;
 	union sctp_params param;
 
-	if (ntohl(resp_seq) != asoc->strreset_outseq || !chunk)
+	if (!chunk)
 		return NULL;
 
 	hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr;
@@ -320,13 +336,21 @@ static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param(
 		 */
 		struct sctp_strreset_tsnreq *req = param.v;
 
-		if (req->request_seq == resp_seq)
+		if ((!resp_seq || req->request_seq == resp_seq) &&
+		    (!type || type == req->param_hdr.type))
 			return param.v;
 	}
 
 	return NULL;
 }
 
+static void sctp_update_strreset_result(struct sctp_association *asoc,
+					__u32 result)
+{
+	asoc->strreset_result[1] = asoc->strreset_result[0];
+	asoc->strreset_result[0] = result;
+}
+
 struct sctp_chunk *sctp_process_strreset_outreq(
 				struct sctp_association *asoc,
 				union sctp_params param,
@@ -343,15 +367,19 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 	if (ntohl(outreq->send_reset_at_tsn) >
 	    sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map)) {
 		result = SCTP_STRRESET_IN_PROGRESS;
-		goto out;
+		goto err;
 	}
 
-	if (request_seq > asoc->strreset_inseq) {
+	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
+	    TSN_lt(request_seq, asoc->strreset_inseq - 2)) {
 		result = SCTP_STRRESET_ERR_BAD_SEQNO;
-		goto out;
-	} else if (request_seq == asoc->strreset_inseq) {
-		asoc->strreset_inseq++;
+		goto err;
+	} else if (TSN_lt(request_seq, asoc->strreset_inseq)) {
+		i = asoc->strreset_inseq - request_seq - 1;
+		result = asoc->strreset_result[i];
+		goto err;
 	}
+	asoc->strreset_inseq++;
 
 	/* Check strreset_enable after inseq inc, as sender cannot tell
 	 * the peer doesn't enable strreset after receiving response with
@@ -361,13 +389,9 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 		goto out;
 
 	if (asoc->strreset_chunk) {
-		sctp_paramhdr_t *param_hdr;
-		struct sctp_transport *t;
-
-		param_hdr = sctp_chunk_lookup_strreset_param(
-					asoc, outreq->response_seq);
-		if (!param_hdr || param_hdr->type !=
-					SCTP_PARAM_RESET_IN_REQUEST) {
+		if (!sctp_chunk_lookup_strreset_param(
+				asoc, outreq->response_seq,
+				SCTP_PARAM_RESET_IN_REQUEST)) {
 			/* same process with outstanding isn't 0 */
 			result = SCTP_STRRESET_ERR_IN_PROGRESS;
 			goto out;
@@ -377,6 +401,8 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 		asoc->strreset_outseq++;
 
 		if (!asoc->strreset_outstanding) {
+			struct sctp_transport *t;
+
 			t = asoc->strreset_chunk->transport;
 			if (del_timer(&t->reconf_timer))
 				sctp_transport_put(t);
@@ -412,6 +438,8 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 		GFP_ATOMIC);
 
 out:
+	sctp_update_strreset_result(asoc, result);
+err:
 	return sctp_make_strreset_resp(asoc, result, request_seq);
 }
 
@@ -428,12 +456,18 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 	__u32 request_seq;
 
 	request_seq = ntohl(inreq->request_seq);
-	if (request_seq > asoc->strreset_inseq) {
+	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
+	    TSN_lt(request_seq, asoc->strreset_inseq - 2)) {
 		result = SCTP_STRRESET_ERR_BAD_SEQNO;
-		goto out;
-	} else if (request_seq == asoc->strreset_inseq) {
-		asoc->strreset_inseq++;
+		goto err;
+	} else if (TSN_lt(request_seq, asoc->strreset_inseq)) {
+		i = asoc->strreset_inseq - request_seq - 1;
+		result = asoc->strreset_result[i];
+		if (result == SCTP_STRRESET_PERFORMED)
+			return NULL;
+		goto err;
 	}
+	asoc->strreset_inseq++;
 
 	if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ))
 		goto out;
@@ -468,12 +502,407 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 	asoc->strreset_outstanding = 1;
 	sctp_chunk_hold(asoc->strreset_chunk);
 
+	result = SCTP_STRRESET_PERFORMED;
+
 	*evp = sctp_ulpevent_make_stream_reset_event(asoc,
 		SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
 
 out:
+	sctp_update_strreset_result(asoc, result);
+err:
 	if (!chunk)
 		chunk =  sctp_make_strreset_resp(asoc, result, request_seq);
 
 	return chunk;
 }
+
+struct sctp_chunk *sctp_process_strreset_tsnreq(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	__u32 init_tsn = 0, next_tsn = 0, max_tsn_seen;
+	struct sctp_strreset_tsnreq *tsnreq = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	__u32 result = SCTP_STRRESET_DENIED;
+	__u32 request_seq;
+	__u16 i;
+
+	request_seq = ntohl(tsnreq->request_seq);
+	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
+	    TSN_lt(request_seq, asoc->strreset_inseq - 2)) {
+		result = SCTP_STRRESET_ERR_BAD_SEQNO;
+		goto err;
+	} else if (TSN_lt(request_seq, asoc->strreset_inseq)) {
+		i = asoc->strreset_inseq - request_seq - 1;
+		result = asoc->strreset_result[i];
+		if (result == SCTP_STRRESET_PERFORMED) {
+			next_tsn = asoc->next_tsn;
+			init_tsn =
+				sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + 1;
+		}
+		goto err;
+	}
+	asoc->strreset_inseq++;
+
+	if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ))
+		goto out;
+
+	if (asoc->strreset_outstanding) {
+		result = SCTP_STRRESET_ERR_IN_PROGRESS;
+		goto out;
+	}
+
+	/* G3: The same processing as though a SACK chunk with no gap report
+	 *     and a cumulative TSN ACK of the Sender's Next TSN minus 1 were
+	 *     received MUST be performed.
+	 */
+	max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map);
+	sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen);
+	sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
+
+	/* G1: Compute an appropriate value for the Receiver's Next TSN -- the
+	 *     TSN that the peer should use to send the next DATA chunk.  The
+	 *     value SHOULD be the smallest TSN not acknowledged by the
+	 *     receiver of the request plus 2^31.
+	 */
+	init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31);
+	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
+			 init_tsn, GFP_ATOMIC);
+
+	/* G4: The same processing as though a FWD-TSN chunk (as defined in
+	 *     [RFC3758]) with all streams affected and a new cumulative TSN
+	 *     ACK of the Receiver's Next TSN minus 1 were received MUST be
+	 *     performed.
+	 */
+	sctp_outq_free(&asoc->outqueue);
+
+	/* G2: Compute an appropriate value for the local endpoint's next TSN,
+	 *     i.e., the next TSN assigned by the receiver of the SSN/TSN reset
+	 *     chunk.  The value SHOULD be the highest TSN sent by the receiver
+	 *     of the request plus 1.
+	 */
+	next_tsn = asoc->next_tsn;
+	asoc->ctsn_ack_point = next_tsn - 1;
+	asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
+
+	/* G5:  The next expected and outgoing SSNs MUST be reset to 0 for all
+	 *      incoming and outgoing streams.
+	 */
+	for (i = 0; i < stream->outcnt; i++)
+		stream->out[i].ssn = 0;
+	for (i = 0; i < stream->incnt; i++)
+		stream->in[i].ssn = 0;
+
+	result = SCTP_STRRESET_PERFORMED;
+
+	*evp = sctp_ulpevent_make_assoc_reset_event(asoc, 0, init_tsn,
+						    next_tsn, GFP_ATOMIC);
+
+out:
+	sctp_update_strreset_result(asoc, result);
+err:
+	return sctp_make_strreset_tsnresp(asoc, result, request_seq,
+					  next_tsn, init_tsn);
+}
+
+struct sctp_chunk *sctp_process_strreset_addstrm_out(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	struct sctp_strreset_addstrm *addstrm = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	__u32 result = SCTP_STRRESET_DENIED;
+	struct sctp_stream_in *streamin;
+	__u32 request_seq, incnt;
+	__u16 in, i;
+
+	request_seq = ntohl(addstrm->request_seq);
+	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
+	    TSN_lt(request_seq, asoc->strreset_inseq - 2)) {
+		result = SCTP_STRRESET_ERR_BAD_SEQNO;
+		goto err;
+	} else if (TSN_lt(request_seq, asoc->strreset_inseq)) {
+		i = asoc->strreset_inseq - request_seq - 1;
+		result = asoc->strreset_result[i];
+		goto err;
+	}
+	asoc->strreset_inseq++;
+
+	if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
+		goto out;
+
+	if (asoc->strreset_chunk) {
+		if (!sctp_chunk_lookup_strreset_param(
+			asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) {
+			/* same process with outstanding isn't 0 */
+			result = SCTP_STRRESET_ERR_IN_PROGRESS;
+			goto out;
+		}
+
+		asoc->strreset_outstanding--;
+		asoc->strreset_outseq++;
+
+		if (!asoc->strreset_outstanding) {
+			struct sctp_transport *t;
+
+			t = asoc->strreset_chunk->transport;
+			if (del_timer(&t->reconf_timer))
+				sctp_transport_put(t);
+
+			sctp_chunk_put(asoc->strreset_chunk);
+			asoc->strreset_chunk = NULL;
+		}
+	}
+
+	in = ntohs(addstrm->number_of_streams);
+	incnt = stream->incnt + in;
+	if (!in || incnt > SCTP_MAX_STREAM)
+		goto out;
+
+	streamin = krealloc(stream->in, incnt * sizeof(*streamin),
+			    GFP_ATOMIC);
+	if (!streamin)
+		goto out;
+
+	memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
+	stream->in = streamin;
+	stream->incnt = incnt;
+
+	result = SCTP_STRRESET_PERFORMED;
+
+	*evp = sctp_ulpevent_make_stream_change_event(asoc,
+		0, ntohs(addstrm->number_of_streams), 0, GFP_ATOMIC);
+
+out:
+	sctp_update_strreset_result(asoc, result);
+err:
+	return sctp_make_strreset_resp(asoc, result, request_seq);
+}
+
+struct sctp_chunk *sctp_process_strreset_addstrm_in(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	struct sctp_strreset_addstrm *addstrm = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	__u32 result = SCTP_STRRESET_DENIED;
+	struct sctp_stream_out *streamout;
+	struct sctp_chunk *chunk = NULL;
+	__u32 request_seq, outcnt;
+	__u16 out, i;
+
+	request_seq = ntohl(addstrm->request_seq);
+	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
+	    TSN_lt(request_seq, asoc->strreset_inseq - 2)) {
+		result = SCTP_STRRESET_ERR_BAD_SEQNO;
+		goto err;
+	} else if (TSN_lt(request_seq, asoc->strreset_inseq)) {
+		i = asoc->strreset_inseq - request_seq - 1;
+		result = asoc->strreset_result[i];
+		if (result == SCTP_STRRESET_PERFORMED)
+			return NULL;
+		goto err;
+	}
+	asoc->strreset_inseq++;
+
+	if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
+		goto out;
+
+	if (asoc->strreset_outstanding) {
+		result = SCTP_STRRESET_ERR_IN_PROGRESS;
+		goto out;
+	}
+
+	out = ntohs(addstrm->number_of_streams);
+	outcnt = stream->outcnt + out;
+	if (!out || outcnt > SCTP_MAX_STREAM)
+		goto out;
+
+	streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
+			     GFP_ATOMIC);
+	if (!streamout)
+		goto out;
+
+	memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
+	stream->out = streamout;
+
+	chunk = sctp_make_strreset_addstrm(asoc, out, 0);
+	if (!chunk)
+		goto out;
+
+	asoc->strreset_chunk = chunk;
+	asoc->strreset_outstanding = 1;
+	sctp_chunk_hold(asoc->strreset_chunk);
+
+	stream->outcnt = outcnt;
+
+	result = SCTP_STRRESET_PERFORMED;
+
+	*evp = sctp_ulpevent_make_stream_change_event(asoc,
+		0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC);
+
+out:
+	sctp_update_strreset_result(asoc, result);
+err:
+	if (!chunk)
+		chunk = sctp_make_strreset_resp(asoc, result, request_seq);
+
+	return chunk;
+}
+
+struct sctp_chunk *sctp_process_strreset_resp(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	struct sctp_strreset_resp *resp = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	struct sctp_transport *t;
+	__u16 i, nums, flags = 0;
+	sctp_paramhdr_t *req;
+	__u32 result;
+
+	req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0);
+	if (!req)
+		return NULL;
+
+	result = ntohl(resp->result);
+	if (result != SCTP_STRRESET_PERFORMED) {
+		/* if in progress, do nothing but retransmit */
+		if (result == SCTP_STRRESET_IN_PROGRESS)
+			return NULL;
+		else if (result == SCTP_STRRESET_DENIED)
+			flags = SCTP_STREAM_RESET_DENIED;
+		else
+			flags = SCTP_STREAM_RESET_FAILED;
+	}
+
+	if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) {
+		struct sctp_strreset_outreq *outreq;
+		__u16 *str_p;
+
+		outreq = (struct sctp_strreset_outreq *)req;
+		str_p = outreq->list_of_streams;
+		nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2;
+
+		if (result == SCTP_STRRESET_PERFORMED) {
+			if (nums) {
+				for (i = 0; i < nums; i++)
+					stream->out[ntohs(str_p[i])].ssn = 0;
+			} else {
+				for (i = 0; i < stream->outcnt; i++)
+					stream->out[i].ssn = 0;
+			}
+
+			flags = SCTP_STREAM_RESET_OUTGOING_SSN;
+		}
+
+		for (i = 0; i < stream->outcnt; i++)
+			stream->out[i].state = SCTP_STREAM_OPEN;
+
+		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
+			nums, str_p, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) {
+		struct sctp_strreset_inreq *inreq;
+		__u16 *str_p;
+
+		/* if the result is performed, it's impossible for inreq */
+		if (result == SCTP_STRRESET_PERFORMED)
+			return NULL;
+
+		inreq = (struct sctp_strreset_inreq *)req;
+		str_p = inreq->list_of_streams;
+		nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2;
+
+		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
+			nums, str_p, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) {
+		struct sctp_strreset_resptsn *resptsn;
+		__u32 stsn, rtsn;
+
+		/* check for resptsn, as sctp_verify_reconf didn't do it*/
+		if (ntohs(param.p->length) != sizeof(*resptsn))
+			return NULL;
+
+		resptsn = (struct sctp_strreset_resptsn *)resp;
+		stsn = ntohl(resptsn->senders_next_tsn);
+		rtsn = ntohl(resptsn->receivers_next_tsn);
+
+		if (result == SCTP_STRRESET_PERFORMED) {
+			__u32 mtsn = sctp_tsnmap_get_max_tsn_seen(
+						&asoc->peer.tsn_map);
+
+			sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn);
+			sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
+
+			sctp_tsnmap_init(&asoc->peer.tsn_map,
+					 SCTP_TSN_MAP_INITIAL,
+					 stsn, GFP_ATOMIC);
+
+			sctp_outq_free(&asoc->outqueue);
+
+			asoc->next_tsn = rtsn;
+			asoc->ctsn_ack_point = asoc->next_tsn - 1;
+			asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
+
+			for (i = 0; i < stream->outcnt; i++)
+				stream->out[i].ssn = 0;
+			for (i = 0; i < stream->incnt; i++)
+				stream->in[i].ssn = 0;
+		}
+
+		for (i = 0; i < stream->outcnt; i++)
+			stream->out[i].state = SCTP_STREAM_OPEN;
+
+		*evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags,
+			stsn, rtsn, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) {
+		struct sctp_strreset_addstrm *addstrm;
+		__u16 number;
+
+		addstrm = (struct sctp_strreset_addstrm *)req;
+		nums = ntohs(addstrm->number_of_streams);
+		number = stream->outcnt - nums;
+
+		if (result == SCTP_STRRESET_PERFORMED)
+			for (i = number; i < stream->outcnt; i++)
+				stream->out[i].state = SCTP_STREAM_OPEN;
+		else
+			stream->outcnt = number;
+
+		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
+			0, nums, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) {
+		struct sctp_strreset_addstrm *addstrm;
+
+		/* if the result is performed, it's impossible for addstrm in
+		 * request.
+		 */
+		if (result == SCTP_STRRESET_PERFORMED)
+			return NULL;
+
+		addstrm = (struct sctp_strreset_addstrm *)req;
+		nums = ntohs(addstrm->number_of_streams);
+
+		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
+			nums, 0, GFP_ATOMIC);
+	}
+
+	asoc->strreset_outstanding--;
+	asoc->strreset_outseq++;
+
+	/* remove everything for this reconf request */
+	if (!asoc->strreset_outstanding) {
+		t = asoc->strreset_chunk->transport;
+		if (del_timer(&t->reconf_timer))
+			sctp_transport_put(t);
+
+		sctp_chunk_put(asoc->strreset_chunk);
+		asoc->strreset_chunk = NULL;
+	}
+
+	return NULL;
+}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index daf8554fd42a..0e732f68c2bf 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -275,6 +275,13 @@ static struct ctl_table sctp_net_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "reconf_enable",
+		.data		= &init_net.sctp.reconf_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "auth_enable",
 		.data		= &init_net.sctp.auth_enable,
 		.maxlen		= sizeof(int),
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 3379668af368..721eeebfcd8a 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -251,14 +251,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
-void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu)
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 {
-	struct dst_entry *dst;
+	struct dst_entry *dst = sctp_transport_dst_check(t);
 
 	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
 		pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n",
-			__func__, pmtu,
-			SCTP_DEFAULT_MINSEGMENT);
+			__func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
 		/* Use default minimum segment size and disable
 		 * pmtu discovery on this transport.
 		 */
@@ -267,17 +266,13 @@ void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 p
 		t->pathmtu = pmtu;
 	}
 
-	dst = sctp_transport_dst_check(t);
-	if (!dst)
-		t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
-
 	if (dst) {
-		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
-
+		dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu);
 		dst = sctp_transport_dst_check(t);
-		if (!dst)
-			t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
 	}
+
+	if (!dst)
+		t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk);
 }
 
 /* Caches the dst entry and source address for a transport's destination
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index c8881bc542a0..ec2b3e013c2f 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -883,6 +883,62 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
 	return event;
 }
 
+struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
+	const struct sctp_association *asoc, __u16 flags, __u32 local_tsn,
+	__u32 remote_tsn, gfp_t gfp)
+{
+	struct sctp_assoc_reset_event *areset;
+	struct sctp_ulpevent *event;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_assoc_reset_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		return NULL;
+
+	skb = sctp_event2skb(event);
+	areset = (struct sctp_assoc_reset_event *)
+		skb_put(skb, sizeof(struct sctp_assoc_reset_event));
+
+	areset->assocreset_type = SCTP_ASSOC_RESET_EVENT;
+	areset->assocreset_flags = flags;
+	areset->assocreset_length = sizeof(struct sctp_assoc_reset_event);
+	sctp_ulpevent_set_owner(event, asoc);
+	areset->assocreset_assoc_id = sctp_assoc2id(asoc);
+	areset->assocreset_local_tsn = local_tsn;
+	areset->assocreset_remote_tsn = remote_tsn;
+
+	return event;
+}
+
+struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event(
+	const struct sctp_association *asoc, __u16 flags,
+	__u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp)
+{
+	struct sctp_stream_change_event *schange;
+	struct sctp_ulpevent *event;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_stream_change_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		return NULL;
+
+	skb = sctp_event2skb(event);
+	schange = (struct sctp_stream_change_event *)
+		skb_put(skb, sizeof(struct sctp_stream_change_event));
+
+	schange->strchange_type = SCTP_STREAM_CHANGE_EVENT;
+	schange->strchange_flags = flags;
+	schange->strchange_length = sizeof(struct sctp_stream_change_event);
+	sctp_ulpevent_set_owner(event, asoc);
+	schange->strchange_assoc_id = sctp_assoc2id(asoc);
+	schange->strchange_instrms = strchange_instrms;
+	schange->strchange_outstrms = strchange_outstrms;
+
+	return event;
+}
+
 /* Return the notification type, assuming this is a notification
  * event.
  */
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 85837ab90e89..5b6ee21368a6 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -147,7 +147,6 @@ static int smc_release(struct socket *sock)
 		schedule_delayed_work(&smc->sock_put_work,
 				      SMC_CLOSE_SOCK_PUT_DELAY);
 	}
-	sk->sk_prot->unhash(sk);
 	release_sock(sk);
 
 	sock_put(sk);
@@ -451,6 +450,9 @@ static int smc_connect_rdma(struct smc_sock *smc)
 		goto decline_rdma_unlock;
 	}
 
+	smc_close_init(smc);
+	smc_rx_init(smc);
+
 	if (local_contact == SMC_FIRST_CONTACT) {
 		rc = smc_ib_ready_link(link);
 		if (rc) {
@@ -477,7 +479,6 @@ static int smc_connect_rdma(struct smc_sock *smc)
 
 	mutex_unlock(&smc_create_lgr_pending);
 	smc_tx_init(smc);
-	smc_rx_init(smc);
 
 out_connected:
 	smc_copy_sock_settings_to_clc(smc);
@@ -637,7 +638,8 @@ struct sock *smc_accept_dequeue(struct sock *parent,
 
 		smc_accept_unlink(new_sk);
 		if (new_sk->sk_state == SMC_CLOSED) {
-			/* tbd in follow-on patch: close this sock */
+			new_sk->sk_prot->unhash(new_sk);
+			sock_put(new_sk);
 			continue;
 		}
 		if (new_sock)
@@ -657,8 +659,13 @@ void smc_close_non_accepted(struct sock *sk)
 	if (!sk->sk_lingertime)
 		/* wait for peer closing */
 		sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
-	if (!smc->use_fallback)
+	if (smc->use_fallback) {
+		sk->sk_state = SMC_CLOSED;
+	} else {
 		smc_close_active(smc);
+		sock_set_flag(sk, SOCK_DEAD);
+		sk->sk_shutdown |= SHUTDOWN_MASK;
+	}
 	if (smc->clcsock) {
 		struct socket *tcp;
 
@@ -666,11 +673,9 @@ void smc_close_non_accepted(struct sock *sk)
 		smc->clcsock = NULL;
 		sock_release(tcp);
 	}
-	sock_set_flag(sk, SOCK_DEAD);
-	sk->sk_shutdown |= SHUTDOWN_MASK;
 	if (smc->use_fallback) {
 		schedule_delayed_work(&smc->sock_put_work, TCP_TIMEWAIT_LEN);
-	} else {
+	} else if (sk->sk_state == SMC_CLOSED) {
 		smc_conn_free(&smc->conn);
 		schedule_delayed_work(&smc->sock_put_work,
 				      SMC_CLOSE_SOCK_PUT_DELAY);
@@ -800,6 +805,9 @@ static void smc_listen_work(struct work_struct *work)
 		goto decline_rdma;
 	}
 
+	smc_close_init(new_smc);
+	smc_rx_init(new_smc);
+
 	rc = smc_clc_send_accept(new_smc, local_contact);
 	if (rc)
 		goto out_err;
@@ -839,7 +847,6 @@ static void smc_listen_work(struct work_struct *work)
 	}
 
 	smc_tx_init(new_smc);
-	smc_rx_init(new_smc);
 
 out_connected:
 	sk_refcnt_debug_inc(newsmcsk);
@@ -944,7 +951,7 @@ out:
 }
 
 static int smc_accept(struct socket *sock, struct socket *new_sock,
-		      int flags)
+		      int flags, bool kern)
 {
 	struct sock *sk = sock->sk, *nsk;
 	DECLARE_WAITQUEUE(wait, current);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index ee5fbea24549..6e44313e4467 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -164,6 +164,7 @@ struct smc_connection {
 #ifndef KERNEL_HAS_ATOMIC64
 	spinlock_t		acurs_lock;	/* protect cursors */
 #endif
+	struct work_struct	close_work;	/* peer sent some closing */
 };
 
 struct smc_sock {				/* smc sock container */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 5a339493872e..a7294edbc221 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -217,8 +217,13 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		smc->sk.sk_err = ECONNRESET;
 		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
 	}
-	if (smc_cdc_rxed_any_close_or_senddone(conn))
-		smc_close_passive_received(smc);
+	if (smc_cdc_rxed_any_close_or_senddone(conn)) {
+		smc->sk.sk_shutdown |= RCV_SHUTDOWN;
+		if (smc->clcsock && smc->clcsock->sk)
+			smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
+		sock_set_flag(&smc->sk, SOCK_DONE);
+		schedule_work(&conn->close_work);
+	}
 
 	/* piggy backed tx info */
 	/* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */
@@ -228,8 +233,6 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		smc_close_wake_tx_prepared(smc);
 	}
 
-	/* subsequent patch: trigger socket release if connection closed */
-
 	/* socket connected but not accepted */
 	if (!smc->sk.sk_socket)
 		return;
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 67a71d170bed..3c2e166b5d22 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -117,7 +117,6 @@ void smc_close_active_abort(struct smc_sock *smc)
 	struct smc_cdc_conn_state_flags *txflags =
 		&smc->conn.local_tx_ctrl.conn_state_flags;
 
-	bh_lock_sock(&smc->sk);
 	smc->sk.sk_err = ECONNABORTED;
 	if (smc->clcsock && smc->clcsock->sk) {
 		smc->clcsock->sk->sk_err = ECONNABORTED;
@@ -125,6 +124,7 @@ void smc_close_active_abort(struct smc_sock *smc)
 	}
 	switch (smc->sk.sk_state) {
 	case SMC_INIT:
+	case SMC_ACTIVE:
 		smc->sk.sk_state = SMC_PEERABORTWAIT;
 		break;
 	case SMC_APPCLOSEWAIT1:
@@ -161,10 +161,15 @@ void smc_close_active_abort(struct smc_sock *smc)
 	}
 
 	sock_set_flag(&smc->sk, SOCK_DEAD);
-	bh_unlock_sock(&smc->sk);
 	smc->sk.sk_state_change(&smc->sk);
 }
 
+static inline bool smc_close_sent_any_close(struct smc_connection *conn)
+{
+	return conn->local_tx_ctrl.conn_state_flags.peer_conn_abort ||
+	       conn->local_tx_ctrl.conn_state_flags.peer_conn_closed;
+}
+
 int smc_close_active(struct smc_sock *smc)
 {
 	struct smc_cdc_conn_state_flags *txflags =
@@ -185,8 +190,7 @@ again:
 	case SMC_INIT:
 		sk->sk_state = SMC_CLOSED;
 		if (smc->smc_listen_work.func)
-			flush_work(&smc->smc_listen_work);
-		sock_put(sk);
+			cancel_work_sync(&smc->smc_listen_work);
 		break;
 	case SMC_LISTEN:
 		sk->sk_state = SMC_CLOSED;
@@ -198,7 +202,7 @@ again:
 		}
 		release_sock(sk);
 		smc_close_cleanup_listen(sk);
-		flush_work(&smc->tcp_listen_work);
+		cancel_work_sync(&smc->smc_listen_work);
 		lock_sock(sk);
 		break;
 	case SMC_ACTIVE:
@@ -218,7 +222,7 @@ again:
 	case SMC_APPFINCLOSEWAIT:
 		/* socket already shutdown wr or both (active close) */
 		if (txflags->peer_done_writing &&
-		    !txflags->peer_conn_closed) {
+		    !smc_close_sent_any_close(conn)) {
 			/* just shutdown wr done, send close request */
 			rc = smc_close_final(conn);
 		}
@@ -248,6 +252,13 @@ again:
 		break;
 	case SMC_PEERCLOSEWAIT1:
 	case SMC_PEERCLOSEWAIT2:
+		if (txflags->peer_done_writing &&
+		    !smc_close_sent_any_close(conn)) {
+			/* just shutdown wr done, send close request */
+			rc = smc_close_final(conn);
+		}
+		/* peer sending PeerConnectionClosed will cause transition */
+		break;
 	case SMC_PEERFINCLOSEWAIT:
 		/* peer sending PeerConnectionClosed will cause transition */
 		break;
@@ -285,7 +296,7 @@ static void smc_close_passive_abort_received(struct smc_sock *smc)
 	case SMC_PEERCLOSEWAIT1:
 	case SMC_PEERCLOSEWAIT2:
 		if (txflags->peer_done_writing &&
-		    !txflags->peer_conn_closed) {
+		    !smc_close_sent_any_close(&smc->conn)) {
 			/* just shutdown, but not yet closed locally */
 			smc_close_abort(&smc->conn);
 			sk->sk_state = SMC_PROCESSABORT;
@@ -306,22 +317,27 @@ static void smc_close_passive_abort_received(struct smc_sock *smc)
 
 /* Some kind of closing has been received: peer_conn_closed, peer_conn_abort,
  * or peer_done_writing.
- * Called under tasklet context.
  */
-void smc_close_passive_received(struct smc_sock *smc)
+static void smc_close_passive_work(struct work_struct *work)
 {
-	struct smc_cdc_conn_state_flags *rxflags =
-		&smc->conn.local_rx_ctrl.conn_state_flags;
+	struct smc_connection *conn = container_of(work,
+						   struct smc_connection,
+						   close_work);
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	struct smc_cdc_conn_state_flags *rxflags;
 	struct sock *sk = &smc->sk;
 	int old_state;
 
-	sk->sk_shutdown |= RCV_SHUTDOWN;
-	if (smc->clcsock && smc->clcsock->sk)
-		smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
-	sock_set_flag(&smc->sk, SOCK_DONE);
-
+	lock_sock(&smc->sk);
 	old_state = sk->sk_state;
 
+	if (!conn->alert_token_local) {
+		/* abnormal termination */
+		smc_close_active_abort(smc);
+		goto wakeup;
+	}
+
+	rxflags = &smc->conn.local_rx_ctrl.conn_state_flags;
 	if (rxflags->peer_conn_abort) {
 		smc_close_passive_abort_received(smc);
 		goto wakeup;
@@ -331,7 +347,7 @@ void smc_close_passive_received(struct smc_sock *smc)
 	case SMC_INIT:
 		if (atomic_read(&smc->conn.bytes_to_rcv) ||
 		    (rxflags->peer_done_writing &&
-		     !rxflags->peer_conn_closed))
+		     !smc_cdc_rxed_any_close(conn)))
 			sk->sk_state = SMC_APPCLOSEWAIT1;
 		else
 			sk->sk_state = SMC_CLOSED;
@@ -348,7 +364,7 @@ void smc_close_passive_received(struct smc_sock *smc)
 		if (!smc_cdc_rxed_any_close(&smc->conn))
 			break;
 		if (sock_flag(sk, SOCK_DEAD) &&
-		    (sk->sk_shutdown == SHUTDOWN_MASK)) {
+		    smc_close_sent_any_close(conn)) {
 			/* smc_release has already been called locally */
 			sk->sk_state = SMC_CLOSED;
 		} else {
@@ -367,17 +383,19 @@ void smc_close_passive_received(struct smc_sock *smc)
 	}
 
 wakeup:
-	if (old_state != sk->sk_state)
-		sk->sk_state_change(sk);
 	sk->sk_data_ready(sk); /* wakeup blocked rcvbuf consumers */
 	sk->sk_write_space(sk); /* wakeup blocked sndbuf producers */
 
-	if ((sk->sk_state == SMC_CLOSED) &&
-	    (sock_flag(sk, SOCK_DEAD) || (old_state == SMC_INIT))) {
-		smc_conn_free(&smc->conn);
-		schedule_delayed_work(&smc->sock_put_work,
-				      SMC_CLOSE_SOCK_PUT_DELAY);
+	if (old_state != sk->sk_state) {
+		sk->sk_state_change(sk);
+		if ((sk->sk_state == SMC_CLOSED) &&
+		    (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
+			smc_conn_free(&smc->conn);
+			schedule_delayed_work(&smc->sock_put_work,
+					      SMC_CLOSE_SOCK_PUT_DELAY);
+		}
 	}
+	release_sock(&smc->sk);
 }
 
 void smc_close_sock_put_work(struct work_struct *work)
@@ -442,3 +460,9 @@ again:
 		sk->sk_state_change(&smc->sk);
 	return rc;
 }
+
+/* Initialize close properties on connection establishment. */
+void smc_close_init(struct smc_sock *smc)
+{
+	INIT_WORK(&smc->conn.close_work, smc_close_passive_work);
+}
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index bc9a2df3633c..4a3d99a8d7cb 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -21,8 +21,8 @@
 void smc_close_wake_tx_prepared(struct smc_sock *smc);
 void smc_close_active_abort(struct smc_sock *smc);
 int smc_close_active(struct smc_sock *smc);
-void smc_close_passive_received(struct smc_sock *smc);
 void smc_close_sock_put_work(struct work_struct *work);
 int smc_close_shutdown_write(struct smc_sock *smc);
+void smc_close_init(struct smc_sock *smc);
 
 #endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 0eac633fb354..65020e93ff21 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -316,7 +316,7 @@ void smc_lgr_terminate(struct smc_link_group *lgr)
 		smc = container_of(conn, struct smc_sock, conn);
 		sock_hold(&smc->sk);
 		__smc_lgr_unregister_conn(conn);
-		smc_close_active_abort(smc);
+		schedule_work(&conn->close_work);
 		sock_put(&smc->sk);
 		node = rb_first(&lgr->conns_all);
 	}
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index e6743c008ac5..16b7c801f8b6 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -179,8 +179,6 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler,
 	u8 port_idx;
 
 	smcibdev = container_of(handler, struct smc_ib_device, event_handler);
-	if (!smc_pnet_find_ib(smcibdev->ibdev->name))
-		return;
 
 	switch (ibevent->event) {
 	case IB_EVENT_PORT_ERR:
@@ -259,7 +257,6 @@ int smc_ib_create_queue_pair(struct smc_link *lnk)
 			.max_recv_wr = SMC_WR_BUF_CNT * 3,
 			.max_send_sge = SMC_IB_MAX_SEND_SGE,
 			.max_recv_sge = 1,
-			.max_inline_data = SMC_WR_TX_SIZE,
 		},
 		.sq_sig_type = IB_SIGNAL_REQ_WR,
 		.qp_type = IB_QPT_RC,
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index a95f74bb5569..7e1f0e24d177 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -11,6 +11,7 @@
 #ifndef _SMC_IB_H
 #define _SMC_IB_H
 
+#include <linux/interrupt.h>
 #include <linux/if_ether.h>
 #include <rdma/ib_verbs.h>
 
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 9d3e7fb8348d..78f7af28ae4f 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -219,7 +219,7 @@ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid)
 }
 
 /* Find an infiniband device by a given name. The device might not exist. */
-struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
+static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
 {
 	struct smc_ib_device *ibdev;
 
@@ -523,8 +523,11 @@ void smc_pnet_find_roce_resource(struct sock *sk,
 	read_lock(&smc_pnettable.lock);
 	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
 		if (dst->dev == pnetelem->ndev) {
-			*smcibdev = pnetelem->smcibdev;
-			*ibport = pnetelem->ib_port;
+			if (smc_ib_port_active(pnetelem->smcibdev,
+					       pnetelem->ib_port)) {
+				*smcibdev = pnetelem->smcibdev;
+				*ibport = pnetelem->ib_port;
+			}
 			break;
 		}
 	}
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 32ab3df928ca..c4f1bccd4358 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -16,7 +16,6 @@ struct smc_ib_device;
 int smc_pnet_init(void) __init;
 void smc_pnet_exit(void);
 int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
-struct smc_ib_device *smc_pnet_find_ib(char *ib_name);
 void smc_pnet_find_roce_resource(struct sock *sk,
 				 struct smc_ib_device **smcibdev, u8 *ibport);
 
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index c4ef9a4ec569..f0c8b089f770 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -36,11 +36,10 @@ static void smc_rx_data_ready(struct sock *sk)
 	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
 						POLLRDNORM | POLLRDBAND);
+	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
 	if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
 	    (sk->sk_state == SMC_CLOSED))
 		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-	else
-		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
 	rcu_read_unlock();
 }
 
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 69a0013dd25c..21ec1832ab51 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -431,9 +431,13 @@ static void smc_tx_work(struct work_struct *work)
 						   struct smc_connection,
 						   tx_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	int rc;
 
 	lock_sock(&smc->sk);
-	smc_tx_sndbuf_nonempty(conn);
+	rc = smc_tx_sndbuf_nonempty(conn);
+	if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked &&
+	    !atomic_read(&conn->bytes_to_rcv))
+		conn->local_rx_ctrl.prod_flags.write_blocked = 0;
 	release_sock(&smc->sk);
 }
 
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index eadf157418dc..874ee9f9d796 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -447,7 +447,7 @@ static void smc_wr_init_sge(struct smc_link *lnk)
 		lnk->wr_tx_ibs[i].num_sge = 1;
 		lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
 		lnk->wr_tx_ibs[i].send_flags =
-			IB_SEND_SIGNALED | IB_SEND_SOLICITED | IB_SEND_INLINE;
+			IB_SEND_SIGNALED | IB_SEND_SOLICITED;
 	}
 	for (i = 0; i < lnk->wr_rx_cnt; i++) {
 		lnk->wr_rx_sges[i].addr =
diff --git a/net/socket.c b/net/socket.c
index 2c1e8677ff2d..c2564eb25c6b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -652,6 +652,16 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 }
 EXPORT_SYMBOL(kernel_sendmsg);
 
+static bool skb_is_err_queue(const struct sk_buff *skb)
+{
+	/* pkt_type of skbs enqueued on the error queue are set to
+	 * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
+	 * in recvmsg, since skbs received on a local socket will never
+	 * have a pkt_type of PACKET_OUTGOING.
+	 */
+	return skb->pkt_type == PACKET_OUTGOING;
+}
+
 /*
  * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
  */
@@ -695,7 +705,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 		put_cmsg(msg, SOL_SOCKET,
 			 SCM_TIMESTAMPING, sizeof(tss), &tss);
 
-		if (skb->len && (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS))
+		if (skb_is_err_queue(skb) && skb->len &&
+		    SKB_EXT_ERR(skb)->opt_stats)
 			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
 				 skb->len, skb->data);
 	}
@@ -1506,7 +1517,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
 	if (err)
 		goto out_fd;
 
-	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
+	err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
 	if (err < 0)
 		goto out_fd;
 
@@ -1731,6 +1742,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	/* We assume all kernel code knows the size of sockaddr_storage */
 	msg.msg_namelen = 0;
 	msg.msg_iocb = NULL;
+	msg.msg_flags = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, flags);
@@ -3238,7 +3250,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 	if (err < 0)
 		goto done;
 
-	err = sock->ops->accept(sock, *newsock, flags);
+	err = sock->ops->accept(sock, *newsock, flags, true);
 	if (err < 0) {
 		sock_release(*newsock);
 		*newsock = NULL;
@@ -3344,3 +3356,49 @@ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how)
 	return sock->ops->shutdown(sock, how);
 }
 EXPORT_SYMBOL(kernel_sock_shutdown);
+
+/* This routine returns the IP overhead imposed by a socket i.e.
+ * the length of the underlying IP header, depending on whether
+ * this is an IPv4 or IPv6 socket and the length from IP options turned
+ * on at the socket. Assumes that the caller has a lock on the socket.
+ */
+u32 kernel_sock_ip_overhead(struct sock *sk)
+{
+	struct inet_sock *inet;
+	struct ip_options_rcu *opt;
+	u32 overhead = 0;
+	bool owned_by_user;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct ipv6_pinfo *np;
+	struct ipv6_txoptions *optv6 = NULL;
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+
+	if (!sk)
+		return overhead;
+
+	owned_by_user = sock_owned_by_user(sk);
+	switch (sk->sk_family) {
+	case AF_INET:
+		inet = inet_sk(sk);
+		overhead += sizeof(struct iphdr);
+		opt = rcu_dereference_protected(inet->inet_opt,
+						owned_by_user);
+		if (opt)
+			overhead += opt->opt.optlen;
+		return overhead;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		np = inet6_sk(sk);
+		overhead += sizeof(struct ipv6hdr);
+		if (np)
+			optv6 = rcu_dereference_protected(np->opt,
+							  owned_by_user);
+		if (optv6)
+			overhead += (optv6->opt_flen + optv6->opt_nflen);
+		return overhead;
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+	default: /* Returns 0 overhead if the socket is not ipv4 or ipv6 */
+		return overhead;
+	}
+}
+EXPORT_SYMBOL(kernel_sock_ip_overhead);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 8931e33b6541..2b720fa35c4f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1635,6 +1635,7 @@ static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv,
 
 	xprt = &svsk->sk_xprt;
 	svc_xprt_init(net, &svc_tcp_bc_class, xprt, serv);
+	set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
 
 	serv->sv_bc_xprt = xprt;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index c13a5c35ce14..fc8f14c7bfec 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -127,6 +127,7 @@ static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *serv,
 	xprt = &cma_xprt->sc_xprt;
 
 	svc_xprt_init(net, &svc_rdma_bc_class, xprt, serv);
+	set_bit(XPT_CONG_CTRL, &xprt->xpt_flags);
 	serv->sv_bc_xprt = xprt;
 
 	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 81cd31acf690..3b332b395045 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -503,7 +503,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	struct ib_cq *sendcq, *recvcq;
 	int rc;
 
-	max_sge = min(ia->ri_device->attrs.max_sge, RPCRDMA_MAX_SEND_SGES);
+	max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge,
+			RPCRDMA_MAX_SEND_SGES);
 	if (max_sge < RPCRDMA_MIN_SEND_SGES) {
 		pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge);
 		return -ENOMEM;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 017801f9dbaa..8d40a7d31c99 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -826,7 +826,7 @@ static int switchdev_port_br_setlink_protinfo(struct net_device *dev,
 	int err;
 
 	err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX,
-				  switchdev_port_bridge_policy);
+				  switchdev_port_bridge_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 33a5bdfbef76..d174ee3254ee 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -802,7 +802,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
 			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy);
+			       tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -851,7 +851,7 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
 			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy);
+			       tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -891,7 +891,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
 			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy);
+			       tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -939,7 +939,7 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
 			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy);
+			       tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -982,7 +982,7 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
 			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy);
+			       tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -1104,7 +1104,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
 			       info->attrs[TIPC_NLA_MEDIA],
-			       tipc_nl_media_policy);
+			       tipc_nl_media_policy, info->extack);
 	if (err)
 		return err;
 
@@ -1152,7 +1152,7 @@ int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
 			       info->attrs[TIPC_NLA_MEDIA],
-			       tipc_nl_media_policy);
+			       tipc_nl_media_policy, info->extack);
 
 	if (!attrs[TIPC_NLA_MEDIA_NAME])
 		return -EINVAL;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index ddd2dd6f77aa..60820dc35a08 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1827,7 +1827,7 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
 	int err;
 
 	err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop,
-			       tipc_nl_prop_policy);
+			       tipc_nl_prop_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 9be6592e4a6f..bd0aac87b41a 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -416,6 +416,7 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq,
 
 	tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns);
 
+	tipc_subscrp_get(s);
 	list_add(&s->nameseq_list, &nseq->subscriptions);
 
 	if (!sseq)
@@ -787,6 +788,7 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s)
 	if (seq != NULL) {
 		spin_lock_bh(&seq->lock);
 		list_del_init(&s->nameseq_list);
+		tipc_subscrp_put(s);
 		if (!seq->first_free && list_empty(&seq->subscriptions)) {
 			hlist_del_init_rcu(&seq->ns_list);
 			kfree(seq->sseqs);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index ab8a2d5d1e32..719c5924b638 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -211,8 +211,8 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
-			       info->attrs[TIPC_NLA_NET],
-			       tipc_nl_net_policy);
+			       info->attrs[TIPC_NLA_NET], tipc_nl_net_policy,
+			       info->extack);
 	if (err)
 		return err;
 
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 26ca8dd64ded..b76f13f6fea1 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -268,7 +268,8 @@ int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr)
 	if (!*attr)
 		return -EOPNOTSUPP;
 
-	return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy);
+	return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy,
+			   NULL);
 }
 
 int __init tipc_netlink_start(void)
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index e1ae8a8a2b8e..9bfe886ab330 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -296,7 +296,7 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
 
 	err = nla_parse(attrbuf, tipc_genl_family.maxattr,
 			(const struct nlattr *)trans_buf->data,
-			trans_buf->len, NULL);
+			trans_buf->len, NULL, NULL);
 	if (err)
 		goto parse_out;
 
@@ -352,7 +352,7 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX,
-			       attrs[TIPC_NLA_BEARER], NULL);
+			       attrs[TIPC_NLA_BEARER], NULL, NULL);
 	if (err)
 		return err;
 
@@ -472,7 +472,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
-			       NULL);
+			       NULL, NULL);
 	if (err)
 		return err;
 
@@ -480,7 +480,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX,
-			       link[TIPC_NLA_LINK_PROP], NULL);
+			       link[TIPC_NLA_LINK_PROP], NULL, NULL);
 	if (err)
 		return err;
 
@@ -488,7 +488,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(stats, TIPC_NLA_STATS_MAX,
-			       link[TIPC_NLA_LINK_STATS], NULL);
+			       link[TIPC_NLA_LINK_STATS], NULL, NULL);
 	if (err)
 		return err;
 
@@ -598,7 +598,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
-			       NULL);
+			       NULL, NULL);
 	if (err)
 		return err;
 
@@ -795,7 +795,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
-			       attrs[TIPC_NLA_NAME_TABLE], NULL);
+			       attrs[TIPC_NLA_NAME_TABLE], NULL, NULL);
 	if (err)
 		return err;
 
@@ -803,7 +803,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX,
-			       nt[TIPC_NLA_NAME_TABLE_PUBL], NULL);
+			       nt[TIPC_NLA_NAME_TABLE_PUBL], NULL, NULL);
 	if (err)
 		return err;
 
@@ -863,7 +863,7 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL],
-			       NULL);
+			       NULL, NULL);
 	if (err)
 		return err;
 
@@ -929,7 +929,7 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK],
-			       NULL);
+			       NULL, NULL);
 	if (err)
 		return err;
 
@@ -940,8 +940,8 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
 		u32 node;
 		struct nlattr *con[TIPC_NLA_CON_MAX + 1];
 
-		nla_parse_nested(con, TIPC_NLA_CON_MAX, sock[TIPC_NLA_SOCK_CON],
-				 NULL);
+		nla_parse_nested(con, TIPC_NLA_CON_MAX,
+				 sock[TIPC_NLA_SOCK_CON], NULL, NULL);
 
 		node = nla_get_u32(con[TIPC_NLA_CON_NODE]);
 		tipc_tlv_sprintf(msg->rep, "  connected to <%u.%u.%u:%u>",
@@ -977,8 +977,8 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_MEDIA])
 		return -EINVAL;
 
-	err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA],
-			       NULL);
+	err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX,
+			       attrs[TIPC_NLA_MEDIA], NULL, NULL);
 	if (err)
 		return err;
 
@@ -998,7 +998,7 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE],
-			       NULL);
+			       NULL, NULL);
 	if (err)
 		return err;
 
@@ -1045,7 +1045,7 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg,
 		return -EINVAL;
 
 	err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET],
-			       NULL);
+			       NULL, NULL);
 	if (err)
 		return err;
 
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 4512e83652b1..aeef8011ac7d 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1607,8 +1607,8 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
-			       info->attrs[TIPC_NLA_NET],
-			       tipc_nl_net_policy);
+			       info->attrs[TIPC_NLA_NET], tipc_nl_net_policy,
+			       info->extack);
 	if (err)
 		return err;
 
@@ -1774,7 +1774,7 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
 			       info->attrs[TIPC_NLA_LINK],
-			       tipc_nl_link_policy);
+			       tipc_nl_link_policy, info->extack);
 	if (err)
 		return err;
 
@@ -1902,7 +1902,7 @@ int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
 			       info->attrs[TIPC_NLA_LINK],
-			       tipc_nl_link_policy);
+			       tipc_nl_link_policy, info->extack);
 	if (err)
 		return err;
 
@@ -2042,7 +2042,7 @@ int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(attrs, TIPC_NLA_MON_MAX,
 			       info->attrs[TIPC_NLA_MON],
-			       tipc_nl_monitor_policy);
+			       tipc_nl_monitor_policy, info->extack);
 	if (err)
 		return err;
 
@@ -2098,6 +2098,8 @@ int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info)
 	int err;
 
 	msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg.skb)
+		return -ENOMEM;
 	msg.portid = info->snd_portid;
 	msg.seq = info->snd_seq;
 
@@ -2163,7 +2165,7 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
 
 		err = nla_parse_nested(mon, TIPC_NLA_MON_MAX,
 				       attrs[TIPC_NLA_MON],
-				       tipc_nl_monitor_policy);
+				       tipc_nl_monitor_policy, NULL);
 		if (err)
 			return err;
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43e4045e72bc..0d4f2f455a7c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -51,6 +51,7 @@
 #define TIPC_FWD_MSG		1
 #define TIPC_MAX_PORT		0xffffffff
 #define TIPC_MIN_PORT		1
+#define TIPC_ACK_RATE		4       /* ACK at 1/4 of of rcv window size */
 
 enum {
 	TIPC_LISTEN = TCP_LISTEN,
@@ -115,7 +116,8 @@ static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
 static void tipc_sock_destruct(struct sock *sk);
 static int tipc_release(struct socket *sock);
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+		       bool kern);
 static void tipc_sk_timeout(unsigned long data);
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 			   struct tipc_name_seq const *seq);
@@ -865,6 +867,14 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
 	if (!tsk_peer_msg(tsk, hdr))
 		goto exit;
 
+	if (unlikely(msg_errcode(hdr))) {
+		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+		tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
+				      tsk_peer_port(tsk));
+		sk->sk_state_change(sk);
+		goto exit;
+	}
+
 	tsk->probe_unacked = false;
 
 	if (mtyp == CONN_PROBE) {
@@ -1082,7 +1092,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
 		}
 	} while (sent < dlen && !rc);
 
-	return rc ? rc : sent;
+	return sent ? sent : rc;
 }
 
 /**
@@ -1258,7 +1268,10 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 	struct sock *sk = sock->sk;
 	DEFINE_WAIT(wait);
 	long timeo = *timeop;
-	int err;
+	int err = sock_error(sk);
+
+	if (err)
+		return err;
 
 	for (;;) {
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
@@ -1280,6 +1293,10 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 		err = sock_intr_errno(timeo);
 		if (signal_pending(current))
 			break;
+
+		err = sock_error(sk);
+		if (err)
+			break;
 	}
 	finish_wait(sk_sleep(sk), &wait);
 	*timeop = timeo;
@@ -1289,7 +1306,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 /**
  * tipc_recvmsg - receive packet-oriented message
  * @m: descriptor for message info
- * @buf_len: total size of user buffer area
+ * @buflen: length of user buffer area
  * @flags: receive flags
  *
  * Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages.
@@ -1297,95 +1314,85 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
  *
  * Returns size of returned message data, errno otherwise
  */
-static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
-			int flags)
+static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
+			size_t buflen,	int flags)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct sk_buff *buf;
-	struct tipc_msg *msg;
-	bool is_connectionless = tipc_sk_type_connectionless(sk);
-	long timeo;
-	unsigned int sz;
-	u32 err;
-	int res, hlen;
+	struct sk_buff *skb;
+	struct tipc_msg *hdr;
+	bool connected = !tipc_sk_type_connectionless(sk);
+	int rc, err, hlen, dlen, copy;
+	long timeout;
 
 	/* Catch invalid receive requests */
-	if (unlikely(!buf_len))
+	if (unlikely(!buflen))
 		return -EINVAL;
 
 	lock_sock(sk);
-
-	if (!is_connectionless && unlikely(sk->sk_state == TIPC_OPEN)) {
-		res = -ENOTCONN;
+	if (unlikely(connected && sk->sk_state == TIPC_OPEN)) {
+		rc = -ENOTCONN;
 		goto exit;
 	}
+	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-restart:
-
-	/* Look for a message in receive queue; wait if necessary */
-	res = tipc_wait_for_rcvmsg(sock, &timeo);
-	if (res)
-		goto exit;
-
-	/* Look at first message in receive queue */
-	buf = skb_peek(&sk->sk_receive_queue);
-	msg = buf_msg(buf);
-	sz = msg_data_sz(msg);
-	hlen = msg_hdr_sz(msg);
-	err = msg_errcode(msg);
-
-	/* Discard an empty non-errored message & try again */
-	if ((!sz) && (!err)) {
+	do {
+		/* Look at first msg in receive queue; wait if necessary */
+		rc = tipc_wait_for_rcvmsg(sock, &timeout);
+		if (unlikely(rc))
+			goto exit;
+		skb = skb_peek(&sk->sk_receive_queue);
+		hdr = buf_msg(skb);
+		dlen = msg_data_sz(hdr);
+		hlen = msg_hdr_sz(hdr);
+		err = msg_errcode(hdr);
+		if (likely(dlen || err))
+			break;
 		tsk_advance_rx_queue(sk);
-		goto restart;
-	}
-
-	/* Capture sender's address (optional) */
-	set_orig_addr(m, msg);
+	} while (1);
 
-	/* Capture ancillary data (optional) */
-	res = tipc_sk_anc_data_recv(m, msg, tsk);
-	if (res)
+	/* Collect msg meta data, including error code and rejected data */
+	set_orig_addr(m, hdr);
+	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+	if (unlikely(rc))
 		goto exit;
 
-	/* Capture message data (if valid) & compute return value (always) */
-	if (!err) {
-		if (unlikely(buf_len < sz)) {
-			sz = buf_len;
+	/* Capture data if non-error msg, otherwise just set return value */
+	if (likely(!err)) {
+		copy = min_t(int, dlen, buflen);
+		if (unlikely(copy != dlen))
 			m->msg_flags |= MSG_TRUNC;
-		}
-		res = skb_copy_datagram_msg(buf, hlen, m, sz);
-		if (res)
-			goto exit;
-		res = sz;
+		rc = skb_copy_datagram_msg(skb, hlen, m, copy);
 	} else {
-		if (is_connectionless || err == TIPC_CONN_SHUTDOWN ||
-		    m->msg_control)
-			res = 0;
-		else
-			res = -ECONNRESET;
+		copy = 0;
+		rc = 0;
+		if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control)
+			rc = -ECONNRESET;
 	}
+	if (unlikely(rc))
+		goto exit;
 
+	/* Caption of data or error code/rejected data was successful */
 	if (unlikely(flags & MSG_PEEK))
 		goto exit;
 
-	if (likely(!is_connectionless)) {
-		tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
-		if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
-			tipc_sk_send_ack(tsk);
-	}
 	tsk_advance_rx_queue(sk);
+	if (likely(!connected))
+		goto exit;
+
+	/* Send connection flow control ack when applicable */
+	tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
+	if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
+		tipc_sk_send_ack(tsk);
 exit:
 	release_sock(sk);
-	return res;
+	return rc ? rc : copy;
 }
 
 /**
- * tipc_recv_stream - receive stream-oriented data
+ * tipc_recvstream - receive stream-oriented data
  * @m: descriptor for message info
- * @buf_len: total size of user buffer area
+ * @buflen: total size of user buffer area
  * @flags: receive flags
  *
  * Used for SOCK_STREAM messages only.  If not enough data is available
@@ -1393,111 +1400,98 @@ exit:
  *
  * Returns size of returned message data, errno otherwise
  */
-static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
-			    size_t buf_len, int flags)
+static int tipc_recvstream(struct socket *sock, struct msghdr *m,
+			   size_t buflen, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct sk_buff *buf;
-	struct tipc_msg *msg;
-	long timeo;
-	unsigned int sz;
-	int target;
-	int sz_copied = 0;
-	u32 err;
-	int res = 0, hlen;
+	struct sk_buff *skb;
+	struct tipc_msg *hdr;
+	struct tipc_skb_cb *skb_cb;
+	bool peek = flags & MSG_PEEK;
+	int offset, required, copy, copied = 0;
+	int hlen, dlen, err, rc;
+	long timeout;
 
 	/* Catch invalid receive attempts */
-	if (unlikely(!buf_len))
+	if (unlikely(!buflen))
 		return -EINVAL;
 
 	lock_sock(sk);
 
 	if (unlikely(sk->sk_state == TIPC_OPEN)) {
-		res = -ENOTCONN;
-		goto exit;
-	}
-
-	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-restart:
-	/* Look for a message in receive queue; wait if necessary */
-	res = tipc_wait_for_rcvmsg(sock, &timeo);
-	if (res)
+		rc = -ENOTCONN;
 		goto exit;
-
-	/* Look at first message in receive queue */
-	buf = skb_peek(&sk->sk_receive_queue);
-	msg = buf_msg(buf);
-	sz = msg_data_sz(msg);
-	hlen = msg_hdr_sz(msg);
-	err = msg_errcode(msg);
-
-	/* Discard an empty non-errored message & try again */
-	if ((!sz) && (!err)) {
-		tsk_advance_rx_queue(sk);
-		goto restart;
 	}
+	required = sock_rcvlowat(sk, flags & MSG_WAITALL, buflen);
+	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
-	/* Optionally capture sender's address & ancillary data of first msg */
-	if (sz_copied == 0) {
-		set_orig_addr(m, msg);
-		res = tipc_sk_anc_data_recv(m, msg, tsk);
-		if (res)
-			goto exit;
-	}
-
-	/* Capture message data (if valid) & compute return value (always) */
-	if (!err) {
-		u32 offset = TIPC_SKB_CB(buf)->bytes_read;
-		u32 needed;
-		int sz_to_copy;
-
-		sz -= offset;
-		needed = (buf_len - sz_copied);
-		sz_to_copy = min(sz, needed);
-
-		res = skb_copy_datagram_msg(buf, hlen + offset, m, sz_to_copy);
-		if (res)
-			goto exit;
+	do {
+		/* Look at first msg in receive queue; wait if necessary */
+		rc = tipc_wait_for_rcvmsg(sock, &timeout);
+		if (unlikely(rc))
+			break;
+		skb = skb_peek(&sk->sk_receive_queue);
+		skb_cb = TIPC_SKB_CB(skb);
+		hdr = buf_msg(skb);
+		dlen = msg_data_sz(hdr);
+		hlen = msg_hdr_sz(hdr);
+		err = msg_errcode(hdr);
+
+		/* Discard any empty non-errored (SYN-) message */
+		if (unlikely(!dlen && !err)) {
+			tsk_advance_rx_queue(sk);
+			continue;
+		}
 
-		sz_copied += sz_to_copy;
+		/* Collect msg meta data, incl. error code and rejected data */
+		if (!copied) {
+			set_orig_addr(m, hdr);
+			rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+			if (rc)
+				break;
+		}
 
-		if (sz_to_copy < sz) {
-			if (!(flags & MSG_PEEK))
-				TIPC_SKB_CB(buf)->bytes_read =
-					offset + sz_to_copy;
-			goto exit;
+		/* Copy data if msg ok, otherwise return error/partial data */
+		if (likely(!err)) {
+			offset = skb_cb->bytes_read;
+			copy = min_t(int, dlen - offset, buflen - copied);
+			rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
+			if (unlikely(rc))
+				break;
+			copied += copy;
+			offset += copy;
+			if (unlikely(offset < dlen)) {
+				if (!peek)
+					skb_cb->bytes_read = offset;
+				break;
+			}
+		} else {
+			rc = 0;
+			if ((err != TIPC_CONN_SHUTDOWN) && !m->msg_control)
+				rc = -ECONNRESET;
+			if (copied || rc)
+				break;
 		}
-	} else {
-		if (sz_copied != 0)
-			goto exit; /* can't add error msg to valid data */
 
-		if ((err == TIPC_CONN_SHUTDOWN) || m->msg_control)
-			res = 0;
-		else
-			res = -ECONNRESET;
-	}
+		if (unlikely(peek))
+			break;
 
-	if (unlikely(flags & MSG_PEEK))
-		goto exit;
+		tsk_advance_rx_queue(sk);
 
-	tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
-	if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
-		tipc_sk_send_ack(tsk);
-	tsk_advance_rx_queue(sk);
+		/* Send connection flow control advertisement when applicable */
+		tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
+		if (unlikely(tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE))
+			tipc_sk_send_ack(tsk);
 
-	/* Loop around if more data is required */
-	if ((sz_copied < buf_len) &&	/* didn't get all requested data */
-	    (!skb_queue_empty(&sk->sk_receive_queue) ||
-	    (sz_copied < target)) &&	/* and more is ready or required */
-	    (!err))			/* and haven't reached a FIN */
-		goto restart;
+		/* Exit if all requested data or FIN/error received */
+		if (copied == buflen || err)
+			break;
 
+	} while (!skb_queue_empty(&sk->sk_receive_queue) || copied < required);
 exit:
 	release_sock(sk);
-	return sz_copied ? sz_copied : res;
+	return copied ? copied : rc;
 }
 
 /**
@@ -1550,6 +1544,8 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 	struct sock *sk = &tsk->sk;
 	struct net *net = sock_net(sk);
 	struct tipc_msg *hdr = buf_msg(skb);
+	u32 pport = msg_origport(hdr);
+	u32 pnode = msg_orignode(hdr);
 
 	if (unlikely(msg_mcast(hdr)))
 		return false;
@@ -1557,18 +1553,28 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 	switch (sk->sk_state) {
 	case TIPC_CONNECTING:
 		/* Accept only ACK or NACK message */
-		if (unlikely(!msg_connected(hdr)))
-			return false;
+		if (unlikely(!msg_connected(hdr))) {
+			if (pport != tsk_peer_port(tsk) ||
+			    pnode != tsk_peer_node(tsk))
+				return false;
+
+			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+			sk->sk_err = ECONNREFUSED;
+			sk->sk_state_change(sk);
+			return true;
+		}
 
 		if (unlikely(msg_errcode(hdr))) {
 			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
 			sk->sk_err = ECONNREFUSED;
+			sk->sk_state_change(sk);
 			return true;
 		}
 
 		if (unlikely(!msg_isdata(hdr))) {
 			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
 			sk->sk_err = EINVAL;
+			sk->sk_state_change(sk);
 			return true;
 		}
 
@@ -1580,8 +1586,7 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 			return true;
 
 		/* If empty 'ACK-' message, wake up sleeping connect() */
-		if (waitqueue_active(sk_sleep(sk)))
-			wake_up_interruptible(sk_sleep(sk));
+		sk->sk_data_ready(sk);
 
 		/* 'ACK-' message is neither accepted nor rejected: */
 		msg_set_dest_droppable(hdr, 1);
@@ -2029,7 +2034,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
  *
  * Returns 0 on success, errno otherwise
  */
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+		       bool kern)
 {
 	struct sock *new_sk, *sk = sock->sk;
 	struct sk_buff *buf;
@@ -2051,7 +2057,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
 
 	buf = skb_peek(&sk->sk_receive_queue);
 
-	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
+	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern);
 	if (res)
 		goto exit;
 	security_sk_clone(sock->sk, new_sock->sk);
@@ -2509,6 +2515,28 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	}
 }
 
+static int tipc_socketpair(struct socket *sock1, struct socket *sock2)
+{
+	struct tipc_sock *tsk2 = tipc_sk(sock2->sk);
+	struct tipc_sock *tsk1 = tipc_sk(sock1->sk);
+	u32 onode = tipc_own_addr(sock_net(sock1->sk));
+
+	tsk1->peer.family = AF_TIPC;
+	tsk1->peer.addrtype = TIPC_ADDR_ID;
+	tsk1->peer.scope = TIPC_NODE_SCOPE;
+	tsk1->peer.addr.id.ref = tsk2->portid;
+	tsk1->peer.addr.id.node = onode;
+	tsk2->peer.family = AF_TIPC;
+	tsk2->peer.addrtype = TIPC_ADDR_ID;
+	tsk2->peer.scope = TIPC_NODE_SCOPE;
+	tsk2->peer.addr.id.ref = tsk1->portid;
+	tsk2->peer.addr.id.node = onode;
+
+	tipc_sk_finish_conn(tsk1, tsk2->portid, onode);
+	tipc_sk_finish_conn(tsk2, tsk1->portid, onode);
+	return 0;
+}
+
 /* Protocol switches for the various types of TIPC sockets */
 
 static const struct proto_ops msg_ops = {
@@ -2517,7 +2545,7 @@ static const struct proto_ops msg_ops = {
 	.release	= tipc_release,
 	.bind		= tipc_bind,
 	.connect	= tipc_connect,
-	.socketpair	= sock_no_socketpair,
+	.socketpair	= tipc_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
@@ -2538,7 +2566,7 @@ static const struct proto_ops packet_ops = {
 	.release	= tipc_release,
 	.bind		= tipc_bind,
 	.connect	= tipc_connect,
-	.socketpair	= sock_no_socketpair,
+	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
@@ -2559,7 +2587,7 @@ static const struct proto_ops stream_ops = {
 	.release	= tipc_release,
 	.bind		= tipc_bind,
 	.connect	= tipc_connect,
-	.socketpair	= sock_no_socketpair,
+	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
@@ -2569,7 +2597,7 @@ static const struct proto_ops stream_ops = {
 	.setsockopt	= tipc_setsockopt,
 	.getsockopt	= tipc_getsockopt,
 	.sendmsg	= tipc_sendstream,
-	.recvmsg	= tipc_recv_stream,
+	.recvmsg	= tipc_recvstream,
 	.mmap		= sock_no_mmap,
 	.sendpage	= sock_no_sendpage
 };
@@ -2842,7 +2870,7 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
 				       attrs[TIPC_NLA_SOCK],
-				       tipc_nl_sock_policy);
+				       tipc_nl_sock_policy, NULL);
 		if (err)
 			return err;
 
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 9d94e65d0894..0bf91cd3733c 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -54,8 +54,6 @@ struct tipc_subscriber {
 
 static void tipc_subscrp_delete(struct tipc_subscription *sub);
 static void tipc_subscrb_put(struct tipc_subscriber *subscriber);
-static void tipc_subscrp_put(struct tipc_subscription *subscription);
-static void tipc_subscrp_get(struct tipc_subscription *subscription);
 
 /**
  * htohl - convert value to endianness used by destination
@@ -125,7 +123,6 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 {
 	struct tipc_name_seq seq;
 
-	tipc_subscrp_get(sub);
 	tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
 	if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
 		return;
@@ -135,12 +132,17 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 
 	tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
 				node);
-	tipc_subscrp_put(sub);
 }
 
 static void tipc_subscrp_timeout(unsigned long data)
 {
 	struct tipc_subscription *sub = (struct tipc_subscription *)data;
+	struct tipc_subscriber *subscriber = sub->subscriber;
+
+	spin_lock_bh(&subscriber->lock);
+	tipc_nametbl_unsubscribe(sub);
+	list_del(&sub->subscrp_list);
+	spin_unlock_bh(&subscriber->lock);
 
 	/* Notify subscriber of timeout */
 	tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper,
@@ -172,21 +174,17 @@ static void tipc_subscrp_kref_release(struct kref *kref)
 	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
 	struct tipc_subscriber *subscriber = sub->subscriber;
 
-	spin_lock_bh(&subscriber->lock);
-	tipc_nametbl_unsubscribe(sub);
-	list_del(&sub->subscrp_list);
 	atomic_dec(&tn->subscription_count);
-	spin_unlock_bh(&subscriber->lock);
 	kfree(sub);
 	tipc_subscrb_put(subscriber);
 }
 
-static void tipc_subscrp_put(struct tipc_subscription *subscription)
+void tipc_subscrp_put(struct tipc_subscription *subscription)
 {
 	kref_put(&subscription->kref, tipc_subscrp_kref_release);
 }
 
-static void tipc_subscrp_get(struct tipc_subscription *subscription)
+void tipc_subscrp_get(struct tipc_subscription *subscription)
 {
 	kref_get(&subscription->kref);
 }
@@ -205,11 +203,9 @@ static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber,
 		if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr)))
 			continue;
 
-		tipc_subscrp_get(sub);
-		spin_unlock_bh(&subscriber->lock);
+		tipc_nametbl_unsubscribe(sub);
+		list_del(&sub->subscrp_list);
 		tipc_subscrp_delete(sub);
-		tipc_subscrp_put(sub);
-		spin_lock_bh(&subscriber->lock);
 
 		if (s)
 			break;
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index ffdc214c117a..ee52957dc952 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -78,4 +78,7 @@ u32 tipc_subscrp_convert_seq_type(u32 type, int swap);
 int tipc_topsrv_start(struct net *net);
 void tipc_topsrv_stop(struct net *net);
 
+void tipc_subscrp_put(struct tipc_subscription *subscription);
+void tipc_subscrp_get(struct tipc_subscription *subscription);
+
 #endif
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 46061cf48cd1..ecca64fc6a6f 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -457,7 +457,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
 
 		err = nla_parse_nested(battrs, TIPC_NLA_BEARER_MAX,
 				       attrs[TIPC_NLA_BEARER],
-				       tipc_nl_bearer_policy);
+				       tipc_nl_bearer_policy, NULL);
 		if (err)
 			return err;
 
@@ -609,7 +609,8 @@ int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr)
 	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
 	struct udp_media_addr *dst;
 
-	if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy))
+	if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr,
+			     tipc_nl_udp_policy, NULL))
 		return -EINVAL;
 
 	if (!opts[TIPC_NLA_UDP_REMOTE])
@@ -662,7 +663,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 
 	if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX,
 			     attrs[TIPC_NLA_BEARER_UDP_OPTS],
-			     tipc_nl_udp_policy))
+			     tipc_nl_udp_policy, NULL))
 		goto err;
 
 	if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) {
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ee37b390260a..6a7fe7660551 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int);
 static int unix_stream_connect(struct socket *, struct sockaddr *,
 			       int addr_len, int flags);
 static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int);
+static int unix_accept(struct socket *, struct socket *, int, bool);
 static int unix_getname(struct socket *, struct sockaddr *, int *, int);
 static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
 static unsigned int unix_dgram_poll(struct file *, struct socket *,
@@ -996,7 +996,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
-	struct path path = { NULL, NULL };
+	struct path path = { };
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
 		set_bit(SOCK_PASSSEC, &new->flags);
 }
 
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
+static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *tsk;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d48525fcf..c36757e72844 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
+		BUG_ON(!atomic_long_read(&u->inflight));
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
+	/* Now gc_candidates contains only garbage.  Restore original
+	 * inflight counters for these as well, and remove the skbuffs
+	 * which are creating the cycle(s).
+	 */
+	skb_queue_head_init(&hitlist);
+	list_for_each_entry(u, &gc_candidates, link)
+		scan_children(&u->sk, inc_inflight, &hitlist);
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
@@ -350,14 +359,6 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/* Now gc_candidates contains only garbage.  Restore original
-	 * inflight counters for these as well, and remove the skbuffs
-	 * which are creating the cycle(s).
-	 */
-	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
-	scan_children(&u->sk, inc_inflight, &hitlist);
-
 	spin_unlock(&unix_gc_lock);
 
 	/* Here we are. Hitlist is filled. Die. */
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
index bc27c70e0e59..09fc2eb29dc8 100644
--- a/net/vmw_vsock/Makefile
+++ b/net/vmw_vsock/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o
 obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o
 obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o
 
-vsock-y += af_vsock.o vsock_addr.o
+vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o
 
 vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \
 	vmci_transport_notify_qstate.o
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9192ead66751..6f7f6757ceef 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1102,10 +1102,19 @@ static const struct proto_ops vsock_dgram_ops = {
 	.sendpage = sock_no_sendpage,
 };
 
+static int vsock_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+	if (!transport->cancel_pkt)
+		return -EOPNOTSUPP;
+
+	return transport->cancel_pkt(vsk);
+}
+
 static void vsock_connect_timeout(struct work_struct *work)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
+	int cancel = 0;
 
 	vsk = container_of(work, struct vsock_sock, dwork.work);
 	sk = sk_vsock(vsk);
@@ -1116,8 +1125,11 @@ static void vsock_connect_timeout(struct work_struct *work)
 		sk->sk_state = SS_UNCONNECTED;
 		sk->sk_err = ETIMEDOUT;
 		sk->sk_error_report(sk);
+		cancel = 1;
 	}
 	release_sock(sk);
+	if (cancel)
+		vsock_transport_cancel_pkt(vsk);
 
 	sock_put(sk);
 }
@@ -1224,11 +1236,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 			err = sock_intr_errno(timeout);
 			sk->sk_state = SS_UNCONNECTED;
 			sock->state = SS_UNCONNECTED;
+			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
 		} else if (timeout == 0) {
 			err = -ETIMEDOUT;
 			sk->sk_state = SS_UNCONNECTED;
 			sock->state = SS_UNCONNECTED;
+			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
 		}
 
@@ -1250,7 +1264,8 @@ out:
 	return err;
 }
 
-static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
+			bool kern)
 {
 	struct sock *listener;
 	int err;
diff --git a/net/vmw_vsock/af_vsock_tap.c b/net/vmw_vsock/af_vsock_tap.c
new file mode 100644
index 000000000000..98f09b539366
--- /dev/null
+++ b/net/vmw_vsock/af_vsock_tap.c
@@ -0,0 +1,114 @@
+/*
+ * Tap functions for AF_VSOCK sockets.
+ *
+ * Code based on net/netlink/af_netlink.c tap functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <net/sock.h>
+#include <net/af_vsock.h>
+#include <linux/if_arp.h>
+
+static DEFINE_SPINLOCK(vsock_tap_lock);
+static struct list_head vsock_tap_all __read_mostly =
+				LIST_HEAD_INIT(vsock_tap_all);
+
+int vsock_add_tap(struct vsock_tap *vt)
+{
+	if (unlikely(vt->dev->type != ARPHRD_VSOCKMON))
+		return -EINVAL;
+
+	__module_get(vt->module);
+
+	spin_lock(&vsock_tap_lock);
+	list_add_rcu(&vt->list, &vsock_tap_all);
+	spin_unlock(&vsock_tap_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vsock_add_tap);
+
+int vsock_remove_tap(struct vsock_tap *vt)
+{
+	struct vsock_tap *tmp;
+	bool found = false;
+
+	spin_lock(&vsock_tap_lock);
+
+	list_for_each_entry(tmp, &vsock_tap_all, list) {
+		if (vt == tmp) {
+			list_del_rcu(&vt->list);
+			found = true;
+			goto out;
+		}
+	}
+
+	pr_warn("vsock_remove_tap: %p not found\n", vt);
+out:
+	spin_unlock(&vsock_tap_lock);
+
+	synchronize_net();
+
+	if (found)
+		module_put(vt->module);
+
+	return found ? 0 : -ENODEV;
+}
+EXPORT_SYMBOL_GPL(vsock_remove_tap);
+
+static int __vsock_deliver_tap_skb(struct sk_buff *skb,
+				   struct net_device *dev)
+{
+	int ret = 0;
+	struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (nskb) {
+		dev_hold(dev);
+
+		nskb->dev = dev;
+		ret = dev_queue_xmit(nskb);
+		if (unlikely(ret > 0))
+			ret = net_xmit_errno(ret);
+
+		dev_put(dev);
+	}
+
+	return ret;
+}
+
+static void __vsock_deliver_tap(struct sk_buff *skb)
+{
+	int ret;
+	struct vsock_tap *tmp;
+
+	list_for_each_entry_rcu(tmp, &vsock_tap_all, list) {
+		ret = __vsock_deliver_tap_skb(skb, tmp->dev);
+		if (unlikely(ret))
+			break;
+	}
+}
+
+void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque)
+{
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+
+	if (likely(list_empty(&vsock_tap_all)))
+		goto out;
+
+	skb = build_skb(opaque);
+	if (skb) {
+		__vsock_deliver_tap(skb);
+		consume_skb(skb);
+	}
+
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(vsock_deliver_tap);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 9d24c0e958b1..9dffe0282ad4 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -144,6 +144,8 @@ virtio_transport_send_pkt_work(struct work_struct *work)
 		list_del_init(&pkt->list);
 		spin_unlock_bh(&vsock->send_pkt_list_lock);
 
+		virtio_transport_deliver_tap_pkt(pkt);
+
 		reply = pkt->reply;
 
 		sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
@@ -213,6 +215,47 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 	return len;
 }
 
+static int
+virtio_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+	struct virtio_vsock *vsock;
+	struct virtio_vsock_pkt *pkt, *n;
+	int cnt = 0;
+	LIST_HEAD(freeme);
+
+	vsock = virtio_vsock_get();
+	if (!vsock) {
+		return -ENODEV;
+	}
+
+	spin_lock_bh(&vsock->send_pkt_list_lock);
+	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+		if (pkt->vsk != vsk)
+			continue;
+		list_move(&pkt->list, &freeme);
+	}
+	spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+	list_for_each_entry_safe(pkt, n, &freeme, list) {
+		if (pkt->reply)
+			cnt++;
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	if (cnt) {
+		struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
+		int new_cnt;
+
+		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
+		if (new_cnt + cnt >= virtqueue_get_vring_size(rx_vq) &&
+		    new_cnt < virtqueue_get_vring_size(rx_vq))
+			queue_work(virtio_vsock_workqueue, &vsock->rx_work);
+	}
+
+	return 0;
+}
+
 static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
 {
 	int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
@@ -329,6 +372,7 @@ static void virtio_transport_rx_work(struct work_struct *work)
 			}
 
 			pkt->len = len - sizeof(pkt->hdr);
+			virtio_transport_deliver_tap_pkt(pkt);
 			virtio_transport_recv_pkt(pkt);
 		}
 	} while (!virtqueue_enable_cb(vq));
@@ -462,6 +506,7 @@ static struct virtio_transport virtio_transport = {
 		.release                  = virtio_transport_release,
 		.connect                  = virtio_transport_connect,
 		.shutdown                 = virtio_transport_shutdown,
+		.cancel_pkt               = virtio_transport_cancel_pkt,
 
 		.dgram_bind               = virtio_transport_dgram_bind,
 		.dgram_dequeue            = virtio_transport_dgram_dequeue,
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 8d592a45b597..18e24793659f 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -16,6 +16,7 @@
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 #include <linux/virtio_vsock.h>
+#include <uapi/linux/vsockmon.h>
 
 #include <net/sock.h>
 #include <net/af_vsock.h>
@@ -58,6 +59,7 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
 	pkt->len		= len;
 	pkt->hdr.len		= cpu_to_le32(len);
 	pkt->reply		= info->reply;
+	pkt->vsk		= info->vsk;
 
 	if (info->msg && len > 0) {
 		pkt->buf = kmalloc(len, GFP_KERNEL);
@@ -84,6 +86,69 @@ out_pkt:
 	return NULL;
 }
 
+/* Packet capture */
+static struct sk_buff *virtio_transport_build_skb(void *opaque)
+{
+	struct virtio_vsock_pkt *pkt = opaque;
+	unsigned char *t_hdr, *payload;
+	struct af_vsockmon_hdr *hdr;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len,
+			GFP_ATOMIC);
+	if (!skb)
+		return NULL;
+
+	hdr = (struct af_vsockmon_hdr *)skb_put(skb, sizeof(*hdr));
+
+	/* pkt->hdr is little-endian so no need to byteswap here */
+	hdr->src_cid = pkt->hdr.src_cid;
+	hdr->src_port = pkt->hdr.src_port;
+	hdr->dst_cid = pkt->hdr.dst_cid;
+	hdr->dst_port = pkt->hdr.dst_port;
+
+	hdr->transport = cpu_to_le16(AF_VSOCK_TRANSPORT_VIRTIO);
+	hdr->len = cpu_to_le16(sizeof(pkt->hdr));
+	memset(hdr->reserved, 0, sizeof(hdr->reserved));
+
+	switch (le16_to_cpu(pkt->hdr.op)) {
+	case VIRTIO_VSOCK_OP_REQUEST:
+	case VIRTIO_VSOCK_OP_RESPONSE:
+		hdr->op = cpu_to_le16(AF_VSOCK_OP_CONNECT);
+		break;
+	case VIRTIO_VSOCK_OP_RST:
+	case VIRTIO_VSOCK_OP_SHUTDOWN:
+		hdr->op = cpu_to_le16(AF_VSOCK_OP_DISCONNECT);
+		break;
+	case VIRTIO_VSOCK_OP_RW:
+		hdr->op = cpu_to_le16(AF_VSOCK_OP_PAYLOAD);
+		break;
+	case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
+	case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
+		hdr->op = cpu_to_le16(AF_VSOCK_OP_CONTROL);
+		break;
+	default:
+		hdr->op = cpu_to_le16(AF_VSOCK_OP_UNKNOWN);
+		break;
+	}
+
+	t_hdr = skb_put(skb, sizeof(pkt->hdr));
+	memcpy(t_hdr, &pkt->hdr, sizeof(pkt->hdr));
+
+	if (pkt->len) {
+		payload = skb_put(skb, pkt->len);
+		memcpy(payload, pkt->buf, pkt->len);
+	}
+
+	return skb;
+}
+
+void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
+{
+	vsock_deliver_tap(virtio_transport_build_skb, pkt);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
+
 static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 					  struct virtio_vsock_pkt_info *info)
 {
@@ -180,6 +245,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
 		.type = type,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);
@@ -519,6 +585,7 @@ int virtio_transport_connect(struct vsock_sock *vsk)
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_REQUEST,
 		.type = VIRTIO_VSOCK_TYPE_STREAM,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);
@@ -534,6 +601,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
 			  VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
 			 (mode & SEND_SHUTDOWN ?
 			  VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);
@@ -560,6 +628,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
 		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.msg = msg,
 		.pkt_len = len,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);
@@ -581,6 +650,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
 		.op = VIRTIO_VSOCK_OP_RST,
 		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.reply = !!pkt,
+		.vsk = vsk,
 	};
 
 	/* Send RST only if the original pkt is not a RST pkt */
@@ -826,6 +896,7 @@ virtio_transport_send_response(struct vsock_sock *vsk,
 		.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
 		.remote_port = le32_to_cpu(pkt->hdr.src_port),
 		.reply = true,
+		.vsk = vsk,
 	};
 
 	return virtio_transport_send_pkt_info(vsk, &info);
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 4be4fbbc0b50..10ae7823a19d 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -96,31 +96,23 @@ static int PROTOCOL_OVERRIDE = -1;
 
 static s32 vmci_transport_error_to_vsock_error(s32 vmci_error)
 {
-	int err;
-
 	switch (vmci_error) {
 	case VMCI_ERROR_NO_MEM:
-		err = ENOMEM;
-		break;
+		return -ENOMEM;
 	case VMCI_ERROR_DUPLICATE_ENTRY:
 	case VMCI_ERROR_ALREADY_EXISTS:
-		err = EADDRINUSE;
-		break;
+		return -EADDRINUSE;
 	case VMCI_ERROR_NO_ACCESS:
-		err = EPERM;
-		break;
+		return -EPERM;
 	case VMCI_ERROR_NO_RESOURCES:
-		err = ENOBUFS;
-		break;
+		return -ENOBUFS;
 	case VMCI_ERROR_INVALID_RESOURCE:
-		err = EHOSTUNREACH;
-		break;
+		return -EHOSTUNREACH;
 	case VMCI_ERROR_INVALID_ARGS:
 	default:
-		err = EINVAL;
+		break;
 	}
-
-	return err > 0 ? -err : err;
+	return -EINVAL;
 }
 
 static u32 vmci_transport_peer_rid(u32 peer_cid)
diff --git a/net/wireless/ap.c b/net/wireless/ap.c
index bdad1f951561..25666d3009be 100644
--- a/net/wireless/ap.c
+++ b/net/wireless/ap.c
@@ -32,6 +32,11 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
 		rdev_set_qos_map(rdev, dev, NULL);
 		if (notify)
 			nl80211_send_ap_stopped(wdev);
+
+		/* Should we apply the grace period during beaconing interface
+		 * shutdown also?
+		 */
+		cfg80211_sched_dfs_chan_update(rdev);
 	}
 
 	return err;
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 5497d022fada..b8aa5a7d5c77 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -456,6 +456,123 @@ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy,
 	return (r1 + r2 > 0);
 }
 
+/*
+ * Checks if center frequency of chan falls with in the bandwidth
+ * range of chandef.
+ */
+bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef,
+			  struct ieee80211_channel *chan)
+{
+	int width;
+	u32 cf_offset, freq;
+
+	if (chandef->chan->center_freq == chan->center_freq)
+		return true;
+
+	width = cfg80211_chandef_get_width(chandef);
+	if (width <= 20)
+		return false;
+
+	cf_offset = width / 2 - 10;
+
+	for (freq = chandef->center_freq1 - width / 2 + 10;
+	     freq <= chandef->center_freq1 + width / 2 - 10; freq += 20) {
+		if (chan->center_freq == freq)
+			return true;
+	}
+
+	if (!chandef->center_freq2)
+		return false;
+
+	for (freq = chandef->center_freq2 - width / 2 + 10;
+	     freq <= chandef->center_freq2 + width / 2 - 10; freq += 20) {
+		if (chan->center_freq == freq)
+			return true;
+	}
+
+	return false;
+}
+
+bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev)
+{
+	bool active = false;
+
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (!wdev->chandef.chan)
+		return false;
+
+	switch (wdev->iftype) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+		active = wdev->beacon_interval != 0;
+		break;
+	case NL80211_IFTYPE_ADHOC:
+		active = wdev->ssid_len != 0;
+		break;
+	case NL80211_IFTYPE_MESH_POINT:
+		active = wdev->mesh_id_len != 0;
+		break;
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_OCB:
+	case NL80211_IFTYPE_P2P_CLIENT:
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_AP_VLAN:
+	case NL80211_IFTYPE_WDS:
+	case NL80211_IFTYPE_P2P_DEVICE:
+	/* Can NAN type be considered as beaconing interface? */
+	case NL80211_IFTYPE_NAN:
+		break;
+	case NL80211_IFTYPE_UNSPECIFIED:
+	case NUM_NL80211_IFTYPES:
+		WARN_ON(1);
+	}
+
+	return active;
+}
+
+static bool cfg80211_is_wiphy_oper_chan(struct wiphy *wiphy,
+					struct ieee80211_channel *chan)
+{
+	struct wireless_dev *wdev;
+
+	list_for_each_entry(wdev, &wiphy->wdev_list, list) {
+		wdev_lock(wdev);
+		if (!cfg80211_beaconing_iface_active(wdev)) {
+			wdev_unlock(wdev);
+			continue;
+		}
+
+		if (cfg80211_is_sub_chan(&wdev->chandef, chan)) {
+			wdev_unlock(wdev);
+			return true;
+		}
+		wdev_unlock(wdev);
+	}
+
+	return false;
+}
+
+bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy,
+				  struct ieee80211_channel *chan)
+{
+	struct cfg80211_registered_device *rdev;
+
+	ASSERT_RTNL();
+
+	if (!(chan->flags & IEEE80211_CHAN_RADAR))
+		return false;
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (!reg_dfs_domain_same(wiphy, &rdev->wiphy))
+			continue;
+
+		if (cfg80211_is_wiphy_oper_chan(&rdev->wiphy, chan))
+			return true;
+	}
+
+	return false;
+}
 
 static bool cfg80211_get_chans_dfs_available(struct wiphy *wiphy,
 					     u32 center_freq,
diff --git a/net/wireless/core.c b/net/wireless/core.c
index e55e05bc4805..83ea164f16b3 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -305,30 +305,14 @@ static void cfg80211_event_work(struct work_struct *work)
 
 void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev)
 {
-	struct cfg80211_iface_destroy *item;
+	struct wireless_dev *wdev, *tmp;
 
 	ASSERT_RTNL();
 
-	spin_lock_irq(&rdev->destroy_list_lock);
-	while ((item = list_first_entry_or_null(&rdev->destroy_list,
-						struct cfg80211_iface_destroy,
-						list))) {
-		struct wireless_dev *wdev, *tmp;
-		u32 nlportid = item->nlportid;
-
-		list_del(&item->list);
-		kfree(item);
-		spin_unlock_irq(&rdev->destroy_list_lock);
-
-		list_for_each_entry_safe(wdev, tmp,
-					 &rdev->wiphy.wdev_list, list) {
-			if (nlportid == wdev->owner_nlportid)
-				rdev_del_virtual_intf(rdev, wdev);
-		}
-
-		spin_lock_irq(&rdev->destroy_list_lock);
+	list_for_each_entry_safe(wdev, tmp, &rdev->wiphy.wdev_list, list) {
+		if (wdev->nl_owner_dead)
+			rdev_del_virtual_intf(rdev, wdev);
 	}
-	spin_unlock_irq(&rdev->destroy_list_lock);
 }
 
 static void cfg80211_destroy_iface_wk(struct work_struct *work)
@@ -346,13 +330,47 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work)
 static void cfg80211_sched_scan_stop_wk(struct work_struct *work)
 {
 	struct cfg80211_registered_device *rdev;
+	struct cfg80211_sched_scan_request *req, *tmp;
 
 	rdev = container_of(work, struct cfg80211_registered_device,
 			   sched_scan_stop_wk);
 
 	rtnl_lock();
+	list_for_each_entry_safe(req, tmp, &rdev->sched_scan_req_list, list) {
+		if (req->nl_owner_dead)
+			cfg80211_stop_sched_scan_req(rdev, req, false);
+	}
+	rtnl_unlock();
+}
 
-	__cfg80211_stop_sched_scan(rdev, false);
+static void cfg80211_propagate_radar_detect_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	rdev = container_of(work, struct cfg80211_registered_device,
+			    propagate_radar_detect_wk);
+
+	rtnl_lock();
+
+	regulatory_propagate_dfs_state(&rdev->wiphy, &rdev->radar_chandef,
+				       NL80211_DFS_UNAVAILABLE,
+				       NL80211_RADAR_DETECTED);
+
+	rtnl_unlock();
+}
+
+static void cfg80211_propagate_cac_done_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	rdev = container_of(work, struct cfg80211_registered_device,
+			    propagate_cac_done_wk);
+
+	rtnl_lock();
+
+	regulatory_propagate_dfs_state(&rdev->wiphy, &rdev->cac_done_chandef,
+				       NL80211_DFS_AVAILABLE,
+				       NL80211_RADAR_CAC_FINISHED);
 
 	rtnl_unlock();
 }
@@ -436,8 +454,8 @@ use_default_name:
 	spin_lock_init(&rdev->beacon_registrations_lock);
 	spin_lock_init(&rdev->bss_lock);
 	INIT_LIST_HEAD(&rdev->bss_list);
+	INIT_LIST_HEAD(&rdev->sched_scan_req_list);
 	INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done);
-	INIT_WORK(&rdev->sched_scan_results_wk, __cfg80211_sched_scan_results);
 	INIT_LIST_HEAD(&rdev->mlme_unreg);
 	spin_lock_init(&rdev->mlme_unreg_lock);
 	INIT_WORK(&rdev->mlme_unreg_wk, cfg80211_mlme_unreg_wk);
@@ -452,10 +470,12 @@ use_default_name:
 	rdev->wiphy.dev.platform_data = rdev;
 	device_enable_async_suspend(&rdev->wiphy.dev);
 
-	INIT_LIST_HEAD(&rdev->destroy_list);
-	spin_lock_init(&rdev->destroy_list_lock);
 	INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
 	INIT_WORK(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk);
+	INIT_WORK(&rdev->sched_scan_res_wk, cfg80211_sched_scan_results_wk);
+	INIT_WORK(&rdev->propagate_radar_detect_wk,
+		  cfg80211_propagate_radar_detect_wk);
+	INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk);
 
 #ifdef CONFIG_CFG80211_DEFAULT_PS
 	rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -915,6 +935,8 @@ void wiphy_unregister(struct wiphy *wiphy)
 	flush_work(&rdev->destroy_work);
 	flush_work(&rdev->sched_scan_stop_wk);
 	flush_work(&rdev->mlme_unreg_wk);
+	flush_work(&rdev->propagate_radar_detect_wk);
+	flush_work(&rdev->propagate_cac_done_wk);
 
 #ifdef CONFIG_PM
 	if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
@@ -954,6 +976,12 @@ void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked)
 }
 EXPORT_SYMBOL(wiphy_rfkill_set_hw_state);
 
+void cfg80211_cqm_config_free(struct wireless_dev *wdev)
+{
+	kfree(wdev->cqm_config);
+	wdev->cqm_config = NULL;
+}
+
 void cfg80211_unregister_wdev(struct wireless_dev *wdev)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
@@ -980,6 +1008,8 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev)
 		WARN_ON_ONCE(1);
 		break;
 	}
+
+	cfg80211_cqm_config_free(wdev);
 }
 EXPORT_SYMBOL(cfg80211_unregister_wdev);
 
@@ -1001,7 +1031,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		      struct wireless_dev *wdev)
 {
 	struct net_device *dev = wdev->netdev;
-	struct cfg80211_sched_scan_request *sched_scan_req;
+	struct cfg80211_sched_scan_request *pos, *tmp;
 
 	ASSERT_RTNL();
 	ASSERT_WDEV_LOCK(wdev);
@@ -1012,9 +1042,11 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_STATION:
-		sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
-		if (sched_scan_req && dev == sched_scan_req->dev)
-			__cfg80211_stop_sched_scan(rdev, false);
+		list_for_each_entry_safe(pos, tmp, &rdev->sched_scan_req_list,
+					 list) {
+			if (dev == pos->dev)
+				cfg80211_stop_sched_scan_req(rdev, pos, false);
+		}
 
 #ifdef CONFIG_CFG80211_WEXT
 		kfree(wdev->wext.ie);
@@ -1089,7 +1121,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev;
-	struct cfg80211_sched_scan_request *sched_scan_req;
+	struct cfg80211_sched_scan_request *pos, *tmp;
 
 	if (!wdev)
 		return NOTIFY_DONE;
@@ -1114,7 +1146,15 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		INIT_LIST_HEAD(&wdev->mgmt_registrations);
 		spin_lock_init(&wdev->mgmt_registrations_lock);
 
-		wdev->identifier = ++rdev->wdev_id;
+		/*
+		 * We get here also when the interface changes network namespaces,
+		 * as it's registered into the new one, but we don't want it to
+		 * change ID in that case. Checking if the ID is already assigned
+		 * works, because 0 isn't considered a valid ID and the memory is
+		 * 0-initialized.
+		 */
+		if (!wdev->identifier)
+			wdev->identifier = ++rdev->wdev_id;
 		list_add_rcu(&wdev->list, &rdev->wiphy.wdev_list);
 		rdev->devlist_generation++;
 		/* can only change netns with wiphy */
@@ -1158,10 +1198,10 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 			___cfg80211_scan_done(rdev, false);
 		}
 
-		sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
-		if (WARN_ON(sched_scan_req &&
-			    sched_scan_req->dev == wdev->netdev)) {
-			__cfg80211_stop_sched_scan(rdev, false);
+		list_for_each_entry_safe(pos, tmp,
+					 &rdev->sched_scan_req_list, list) {
+			if (WARN_ON(pos && pos->dev == wdev->netdev))
+				cfg80211_stop_sched_scan_req(rdev, pos, false);
 		}
 
 		rdev->opencount--;
@@ -1208,12 +1248,12 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		 */
 		if ((wdev->iftype == NL80211_IFTYPE_STATION ||
 		     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) &&
-		    rdev->ops->set_power_mgmt)
-			if (rdev_set_power_mgmt(rdev, dev, wdev->ps,
-						wdev->ps_timeout)) {
-				/* assume this means it's off */
-				wdev->ps = false;
-			}
+		    rdev->ops->set_power_mgmt &&
+		    rdev_set_power_mgmt(rdev, dev, wdev->ps,
+					wdev->ps_timeout)) {
+			/* assume this means it's off */
+			wdev->ps = false;
+		}
 		break;
 	case NETDEV_UNREGISTER:
 		/*
@@ -1234,6 +1274,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 			kzfree(wdev->wext.keys);
 #endif
 			flush_work(&wdev->disconnect_wk);
+			cfg80211_cqm_config_free(wdev);
 		}
 		/*
 		 * synchronise (so that we won't find this netdev
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 58ca206982fe..6e809325af3b 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -74,10 +74,9 @@ struct cfg80211_registered_device {
 	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
 	struct sk_buff *scan_msg;
-	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
+	struct list_head sched_scan_req_list;
 	unsigned long suspend_at;
 	struct work_struct scan_done_wk;
-	struct work_struct sched_scan_results_wk;
 
 	struct genl_info *cur_cmd_info;
 
@@ -91,11 +90,15 @@ struct cfg80211_registered_device {
 
 	struct cfg80211_coalesce *coalesce;
 
-	spinlock_t destroy_list_lock;
-	struct list_head destroy_list;
 	struct work_struct destroy_work;
-
 	struct work_struct sched_scan_stop_wk;
+	struct work_struct sched_scan_res_wk;
+
+	struct cfg80211_chan_def radar_chandef;
+	struct work_struct propagate_radar_detect_wk;
+
+	struct cfg80211_chan_def cac_done_chandef;
+	struct work_struct propagate_cac_done_wk;
 
 	/* must be last because of the way we do wiphy_priv(),
 	 * and it should at least be aligned to NETDEV_ALIGN */
@@ -220,23 +223,8 @@ struct cfg80211_event {
 	enum cfg80211_event_type type;
 
 	union {
-		struct {
-			u8 bssid[ETH_ALEN];
-			const u8 *req_ie;
-			const u8 *resp_ie;
-			size_t req_ie_len;
-			size_t resp_ie_len;
-			struct cfg80211_bss *bss;
-			int status; /* -1 = failed; 0..65535 = status code */
-			enum nl80211_timeout_reason timeout_reason;
-		} cr;
-		struct {
-			const u8 *req_ie;
-			const u8 *resp_ie;
-			size_t req_ie_len;
-			size_t resp_ie_len;
-			struct cfg80211_bss *bss;
-		} rm;
+		struct cfg80211_connect_resp_params cr;
+		struct cfg80211_roam_info rm;
 		struct {
 			const u8 *ie;
 			size_t ie_len;
@@ -267,9 +255,11 @@ struct cfg80211_beacon_registration {
 	u32 nlportid;
 };
 
-struct cfg80211_iface_destroy {
-	struct list_head list;
-	u32 nlportid;
+struct cfg80211_cqm_config {
+	u32 rssi_hyst;
+	s32 last_rssi_event_value;
+	int n_rssi_thresholds;
+	s32 rssi_thresholds[0];
 };
 
 void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev);
@@ -385,21 +375,16 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev,
 		     struct cfg80211_connect_params *connect,
 		     struct cfg80211_cached_keys *connkeys,
 		     const u8 *prev_bssid);
-void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
-			       const u8 *req_ie, size_t req_ie_len,
-			       const u8 *resp_ie, size_t resp_ie_len,
-			       int status, bool wextev,
-			       struct cfg80211_bss *bss,
-			       enum nl80211_timeout_reason timeout_reason);
+void __cfg80211_connect_result(struct net_device *dev,
+			       struct cfg80211_connect_resp_params *params,
+			       bool wextev);
 void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap);
 int cfg80211_disconnect(struct cfg80211_registered_device *rdev,
 			struct net_device *dev, u16 reason,
 			bool wextev);
 void __cfg80211_roamed(struct wireless_dev *wdev,
-		       struct cfg80211_bss *bss,
-		       const u8 *req_ie, size_t req_ie_len,
-		       const u8 *resp_ie, size_t resp_ie_len);
+		       struct cfg80211_roam_info *info);
 int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev,
 			      struct wireless_dev *wdev);
 void cfg80211_autodisconnect_wk(struct work_struct *work);
@@ -423,13 +408,20 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 void __cfg80211_scan_done(struct work_struct *wk);
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message);
-void __cfg80211_sched_scan_results(struct work_struct *wk);
+void cfg80211_add_sched_scan_req(struct cfg80211_registered_device *rdev,
+				 struct cfg80211_sched_scan_request *req);
+int cfg80211_sched_scan_req_possible(struct cfg80211_registered_device *rdev,
+				     bool want_multi);
+void cfg80211_sched_scan_results_wk(struct work_struct *work);
+int cfg80211_stop_sched_scan_req(struct cfg80211_registered_device *rdev,
+				 struct cfg80211_sched_scan_request *req,
+				 bool driver_initiated);
 int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
-			       bool driver_initiated);
+			       u64 reqid, bool driver_initiated);
 void cfg80211_upload_connect_keys(struct wireless_dev *wdev);
 int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 			  struct net_device *dev, enum nl80211_iftype ntype,
-			  u32 *flags, struct vif_params *params);
+			  struct vif_params *params);
 void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev);
 void cfg80211_process_wdev_events(struct wireless_dev *wdev);
 
@@ -459,6 +451,16 @@ unsigned int
 cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy,
 			      const struct cfg80211_chan_def *chandef);
 
+void cfg80211_sched_dfs_chan_update(struct cfg80211_registered_device *rdev);
+
+bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy,
+				  struct ieee80211_channel *chan);
+
+bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev);
+
+bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef,
+			  struct ieee80211_channel *chan);
+
 static inline unsigned int elapsed_jiffies_msecs(unsigned long start)
 {
 	unsigned long end = jiffies;
@@ -512,4 +514,6 @@ void cfg80211_stop_nan(struct cfg80211_registered_device *rdev,
 #define CFG80211_DEV_WARN_ON(cond)	({bool __r = (cond); __r; })
 #endif
 
+void cfg80211_cqm_config_free(struct wireless_dev *wdev);
+
 #endif /* __NET_WIRELESS_CORE_H */
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 364f900a3dc4..10bf040a0982 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -190,6 +190,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 	if (!nowext)
 		wdev->wext.ibss.ssid_len = 0;
 #endif
+	cfg80211_sched_dfs_chan_update(rdev);
 }
 
 void cfg80211_clear_ibss(struct net_device *dev, bool nowext)
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 2d8518a37eab..ec0b1c20ac99 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -262,6 +262,7 @@ int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
 		wdev->beacon_interval = 0;
 		memset(&wdev->chandef, 0, sizeof(wdev->chandef));
 		rdev_set_qos_map(rdev, dev, NULL);
+		cfg80211_sched_dfs_chan_update(rdev);
 	}
 
 	return err;
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 22b3d9990065..d8df7a5180a0 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -26,9 +26,16 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
-	u8 *ie = mgmt->u.assoc_resp.variable;
-	int ieoffs = offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
-	u16 status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code);
+	struct cfg80211_connect_resp_params cr;
+
+	memset(&cr, 0, sizeof(cr));
+	cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code);
+	cr.bssid = mgmt->bssid;
+	cr.bss = bss;
+	cr.resp_ie = mgmt->u.assoc_resp.variable;
+	cr.resp_ie_len =
+		len - offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
+	cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED;
 
 	trace_cfg80211_send_rx_assoc(dev, bss);
 
@@ -38,7 +45,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	 * and got a reject -- we only try again with an assoc
 	 * frame instead of reassoc.
 	 */
-	if (cfg80211_sme_rx_assoc_resp(wdev, status_code)) {
+	if (cfg80211_sme_rx_assoc_resp(wdev, cr.status)) {
 		cfg80211_unhold_bss(bss_from_pub(bss));
 		cfg80211_put_bss(wiphy, bss);
 		return;
@@ -46,10 +53,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 
 	nl80211_send_rx_assoc(rdev, dev, buf, len, GFP_KERNEL, uapsd_queues);
 	/* update current_bss etc., consumes the bss reference */
-	__cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, ie, len - ieoffs,
-				  status_code,
-				  status_code == WLAN_STATUS_SUCCESS, bss,
-				  NL80211_TIMEOUT_UNSPECIFIED);
+	__cfg80211_connect_result(dev, &cr, cr.status == WLAN_STATUS_SUCCESS);
 }
 EXPORT_SYMBOL(cfg80211_rx_assoc_resp);
 
@@ -745,6 +749,12 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm,
 }
 EXPORT_SYMBOL(cfg80211_rx_mgmt);
 
+void cfg80211_sched_dfs_chan_update(struct cfg80211_registered_device *rdev)
+{
+	cancel_delayed_work(&rdev->dfs_update_channels_wk);
+	queue_delayed_work(cfg80211_wq, &rdev->dfs_update_channels_wk, 0);
+}
+
 void cfg80211_dfs_channels_update_work(struct work_struct *work)
 {
 	struct delayed_work *delayed_work = to_delayed_work(work);
@@ -755,6 +765,8 @@ void cfg80211_dfs_channels_update_work(struct work_struct *work)
 	struct wiphy *wiphy;
 	bool check_again = false;
 	unsigned long timeout, next_time = 0;
+	unsigned long time_dfs_update;
+	enum nl80211_radar_event radar_event;
 	int bandid, i;
 
 	rdev = container_of(delayed_work, struct cfg80211_registered_device,
@@ -770,11 +782,27 @@ void cfg80211_dfs_channels_update_work(struct work_struct *work)
 		for (i = 0; i < sband->n_channels; i++) {
 			c = &sband->channels[i];
 
-			if (c->dfs_state != NL80211_DFS_UNAVAILABLE)
+			if (!(c->flags & IEEE80211_CHAN_RADAR))
+				continue;
+
+			if (c->dfs_state != NL80211_DFS_UNAVAILABLE &&
+			    c->dfs_state != NL80211_DFS_AVAILABLE)
 				continue;
 
-			timeout = c->dfs_state_entered + msecs_to_jiffies(
-					IEEE80211_DFS_MIN_NOP_TIME_MS);
+			if (c->dfs_state == NL80211_DFS_UNAVAILABLE) {
+				time_dfs_update = IEEE80211_DFS_MIN_NOP_TIME_MS;
+				radar_event = NL80211_RADAR_NOP_FINISHED;
+			} else {
+				if (regulatory_pre_cac_allowed(wiphy) ||
+				    cfg80211_any_wiphy_oper_chan(wiphy, c))
+					continue;
+
+				time_dfs_update = REG_PRE_CAC_EXPIRY_GRACE_MS;
+				radar_event = NL80211_RADAR_PRE_CAC_EXPIRED;
+			}
+
+			timeout = c->dfs_state_entered +
+				  msecs_to_jiffies(time_dfs_update);
 
 			if (time_after_eq(jiffies, timeout)) {
 				c->dfs_state = NL80211_DFS_USABLE;
@@ -784,8 +812,12 @@ void cfg80211_dfs_channels_update_work(struct work_struct *work)
 							NL80211_CHAN_NO_HT);
 
 				nl80211_radar_notify(rdev, &chandef,
-						     NL80211_RADAR_NOP_FINISHED,
-						     NULL, GFP_ATOMIC);
+						     radar_event, NULL,
+						     GFP_ATOMIC);
+
+				regulatory_propagate_dfs_state(wiphy, &chandef,
+							       c->dfs_state,
+							       radar_event);
 				continue;
 			}
 
@@ -810,7 +842,6 @@ void cfg80211_radar_event(struct wiphy *wiphy,
 			  gfp_t gfp)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	unsigned long timeout;
 
 	trace_cfg80211_radar_event(wiphy, chandef);
 
@@ -820,11 +851,12 @@ void cfg80211_radar_event(struct wiphy *wiphy,
 	 */
 	cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_UNAVAILABLE);
 
-	timeout = msecs_to_jiffies(IEEE80211_DFS_MIN_NOP_TIME_MS);
-	queue_delayed_work(cfg80211_wq, &rdev->dfs_update_channels_wk,
-			   timeout);
+	cfg80211_sched_dfs_chan_update(rdev);
 
 	nl80211_radar_notify(rdev, chandef, NL80211_RADAR_DETECTED, NULL, gfp);
+
+	memcpy(&rdev->radar_chandef, chandef, sizeof(struct cfg80211_chan_def));
+	queue_work(cfg80211_wq, &rdev->propagate_radar_detect_wk);
 }
 EXPORT_SYMBOL(cfg80211_radar_event);
 
@@ -851,6 +883,10 @@ void cfg80211_cac_event(struct net_device *netdev,
 			  msecs_to_jiffies(wdev->cac_time_ms);
 		WARN_ON(!time_after_eq(jiffies, timeout));
 		cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE);
+		memcpy(&rdev->cac_done_chandef, chandef,
+		       sizeof(struct cfg80211_chan_def));
+		queue_work(cfg80211_wq, &rdev->propagate_cac_done_wk);
+		cfg80211_sched_dfs_chan_update(rdev);
 		break;
 	case NL80211_RADAR_CAC_ABORTED:
 		break;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d7f8be4e321a..570fc95dc507 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -410,6 +410,16 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		.len = sizeof(struct nl80211_bss_select_rssi_adjust)
 	},
 	[NL80211_ATTR_TIMEOUT_REASON] = { .type = NLA_U32 },
+	[NL80211_ATTR_FILS_ERP_USERNAME] = { .type = NLA_BINARY,
+					     .len = FILS_ERP_MAX_USERNAME_LEN },
+	[NL80211_ATTR_FILS_ERP_REALM] = { .type = NLA_BINARY,
+					  .len = FILS_ERP_MAX_REALM_LEN },
+	[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM] = { .type = NLA_U16 },
+	[NL80211_ATTR_FILS_ERP_RRK] = { .type = NLA_BINARY,
+					.len = FILS_ERP_MAX_RRK_LEN },
+	[NL80211_ATTR_FILS_CACHE_ID] = { .len = 2 },
+	[NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN },
+	[NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG },
 };
 
 /* policy for the key attributes */
@@ -487,6 +497,7 @@ static const struct nla_policy
 nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = {
 	[NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY,
 						 .len = IEEE80211_MAX_SSID_LEN },
+	[NL80211_SCHED_SCAN_MATCH_ATTR_BSSID] = { .len = ETH_ALEN },
 	[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 },
 };
 
@@ -545,22 +556,18 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 {
 	int err;
 
-	rtnl_lock();
-
 	if (!cb->args[0]) {
 		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
 				  genl_family_attrbuf(&nl80211_fam),
-				  nl80211_fam.maxattr, nl80211_policy);
+				  nl80211_fam.maxattr, nl80211_policy, NULL);
 		if (err)
-			goto out_unlock;
+			return err;
 
 		*wdev = __cfg80211_wdev_from_attrs(
 					sock_net(skb->sk),
 					genl_family_attrbuf(&nl80211_fam));
-		if (IS_ERR(*wdev)) {
-			err = PTR_ERR(*wdev);
-			goto out_unlock;
-		}
+		if (IS_ERR(*wdev))
+			return PTR_ERR(*wdev);
 		*rdev = wiphy_to_rdev((*wdev)->wiphy);
 		/* 0 is the first index - add 1 to parse only once */
 		cb->args[0] = (*rdev)->wiphy_idx + 1;
@@ -570,10 +577,8 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 		struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
 		struct wireless_dev *tmp;
 
-		if (!wiphy) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+		if (!wiphy)
+			return -ENODEV;
 		*rdev = wiphy_to_rdev(wiphy);
 		*wdev = NULL;
 
@@ -584,21 +589,11 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 			}
 		}
 
-		if (!*wdev) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+		if (!*wdev)
+			return -ENODEV;
 	}
 
 	return 0;
- out_unlock:
-	rtnl_unlock();
-	return err;
-}
-
-static void nl80211_finish_wdev_dump(struct cfg80211_registered_device *rdev)
-{
-	rtnl_unlock();
 }
 
 /* IE validation */
@@ -735,7 +730,7 @@ static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k)
 {
 	struct nlattr *tb[NL80211_KEY_MAX + 1];
 	int err = nla_parse_nested(tb, NL80211_KEY_MAX, key,
-				   nl80211_key_policy);
+				   nl80211_key_policy, NULL);
 	if (err)
 		return err;
 
@@ -776,7 +771,7 @@ static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k)
 
 		err = nla_parse_nested(kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1,
 				       tb[NL80211_KEY_DEFAULT_TYPES],
-				       nl80211_key_default_policy);
+				       nl80211_key_default_policy, NULL);
 		if (err)
 			return err;
 
@@ -823,10 +818,11 @@ static int nl80211_parse_key_old(struct genl_info *info, struct key_parse *k)
 
 	if (info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES]) {
 		struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES];
-		int err = nla_parse_nested(
-				kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1,
-				info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES],
-				nl80211_key_default_policy);
+		int err = nla_parse_nested(kdt,
+					   NUM_NL80211_KEY_DEFAULT_TYPES - 1,
+					   info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES],
+					   nl80211_key_default_policy,
+					   info->extack);
 		if (err)
 			return err;
 
@@ -1382,7 +1378,7 @@ static int nl80211_add_commands_unsplit(struct cfg80211_registered_device *rdev,
 		CMD(tdls_mgmt, TDLS_MGMT);
 		CMD(tdls_oper, TDLS_OPER);
 	}
-	if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+	if (rdev->wiphy.max_sched_scan_reqs)
 		CMD(sched_scan_start, START_SCHED_SCAN);
 	CMD(probe_client, PROBE_CLIENT);
 	CMD(set_noack_map, SET_NOACK_MAP);
@@ -1821,6 +1817,11 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
 			goto nla_put_failure;
 
+		if (rdev->wiphy.max_sched_scan_reqs &&
+		    nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_MAX_REQS,
+				rdev->wiphy.max_sched_scan_reqs))
+			goto nla_put_failure;
+
 		if (nla_put(msg, NL80211_ATTR_EXT_FEATURES,
 			    sizeof(rdev->wiphy.ext_features),
 			    rdev->wiphy.ext_features))
@@ -1908,8 +1909,8 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb,
 				    struct nl80211_dump_wiphy_state *state)
 {
 	struct nlattr **tb = genl_family_attrbuf(&nl80211_fam);
-	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
-			      tb, nl80211_fam.maxattr, nl80211_policy);
+	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, tb,
+			      nl80211_fam.maxattr, nl80211_policy, NULL);
 	/* ignore parse errors for backward compatibility */
 	if (ret)
 		return 0;
@@ -2324,7 +2325,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 				    rem_txq_params) {
 			result = nla_parse_nested(tb, NL80211_TXQ_ATTR_MAX,
 						  nl_txq_params,
-						  txq_params_policy);
+						  txq_params_policy,
+						  info->extack);
 			if (result)
 				return result;
 			result = parse_txq_params(tb, &txq_params);
@@ -2608,17 +2610,17 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 	int filter_wiphy = -1;
 	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
+	int ret;
 
 	rtnl_lock();
 	if (!cb->args[2]) {
 		struct nl80211_dump_wiphy_state state = {
 			.filter_wiphy = -1,
 		};
-		int ret;
 
 		ret = nl80211_dump_wiphy_parse(skb, cb, &state);
 		if (ret)
-			return ret;
+			goto out_unlock;
 
 		filter_wiphy = state.filter_wiphy;
 
@@ -2663,12 +2665,14 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 		wp_idx++;
 	}
  out:
-	rtnl_unlock();
-
 	cb->args[0] = wp_idx;
 	cb->args[1] = if_idx;
 
-	return skb->len;
+	ret = skb->len;
+ out_unlock:
+	rtnl_unlock();
+
+	return ret;
 }
 
 static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
@@ -2709,17 +2713,82 @@ static int parse_monitor_flags(struct nlattr *nla, u32 *mntrflags)
 	if (!nla)
 		return -EINVAL;
 
-	if (nla_parse_nested(flags, NL80211_MNTR_FLAG_MAX,
-			     nla, mntr_flags_policy))
+	if (nla_parse_nested(flags, NL80211_MNTR_FLAG_MAX, nla,
+			     mntr_flags_policy, NULL))
 		return -EINVAL;
 
 	for (flag = 1; flag <= NL80211_MNTR_FLAG_MAX; flag++)
 		if (flags[flag])
 			*mntrflags |= (1<<flag);
 
+	*mntrflags |= MONITOR_FLAG_CHANGED;
+
 	return 0;
 }
 
+static int nl80211_parse_mon_options(struct cfg80211_registered_device *rdev,
+				     enum nl80211_iftype type,
+				     struct genl_info *info,
+				     struct vif_params *params)
+{
+	bool change = false;
+	int err;
+
+	if (info->attrs[NL80211_ATTR_MNTR_FLAGS]) {
+		if (type != NL80211_IFTYPE_MONITOR)
+			return -EINVAL;
+
+		err = parse_monitor_flags(info->attrs[NL80211_ATTR_MNTR_FLAGS],
+					  &params->flags);
+		if (err)
+			return err;
+
+		change = true;
+	}
+
+	if (params->flags & MONITOR_FLAG_ACTIVE &&
+	    !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR))
+		return -EOPNOTSUPP;
+
+	if (info->attrs[NL80211_ATTR_MU_MIMO_GROUP_DATA]) {
+		const u8 *mumimo_groups;
+		u32 cap_flag = NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER;
+
+		if (type != NL80211_IFTYPE_MONITOR)
+			return -EINVAL;
+
+		if (!wiphy_ext_feature_isset(&rdev->wiphy, cap_flag))
+			return -EOPNOTSUPP;
+
+		mumimo_groups =
+			nla_data(info->attrs[NL80211_ATTR_MU_MIMO_GROUP_DATA]);
+
+		/* bits 0 and 63 are reserved and must be zero */
+		if ((mumimo_groups[0] & BIT(7)) ||
+		    (mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN - 1] & BIT(0)))
+			return -EINVAL;
+
+		params->vht_mumimo_groups = mumimo_groups;
+		change = true;
+	}
+
+	if (info->attrs[NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR]) {
+		u32 cap_flag = NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER;
+
+		if (type != NL80211_IFTYPE_MONITOR)
+			return -EINVAL;
+
+		if (!wiphy_ext_feature_isset(&rdev->wiphy, cap_flag))
+			return -EOPNOTSUPP;
+
+		params->vht_mumimo_follow_addr =
+			nla_data(info->attrs[NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR]);
+		change = true;
+	}
+
+	return change ? 1 : 0;
+}
+
 static int nl80211_valid_4addr(struct cfg80211_registered_device *rdev,
 			       struct net_device *netdev, u8 use_4addr,
 			       enum nl80211_iftype iftype)
@@ -2753,7 +2822,6 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info)
 	int err;
 	enum nl80211_iftype otype, ntype;
 	struct net_device *dev = info->user_ptr[1];
-	u32 _flags, *flags = NULL;
 	bool change = false;
 
 	memset(&params, 0, sizeof(params));
@@ -2796,56 +2864,14 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info)
 		params.use_4addr = -1;
 	}
 
-	if (info->attrs[NL80211_ATTR_MNTR_FLAGS]) {
-		if (ntype != NL80211_IFTYPE_MONITOR)
-			return -EINVAL;
-		err = parse_monitor_flags(info->attrs[NL80211_ATTR_MNTR_FLAGS],
-					  &_flags);
-		if (err)
-			return err;
-
-		flags = &_flags;
-		change = true;
-	}
-
-	if (info->attrs[NL80211_ATTR_MU_MIMO_GROUP_DATA]) {
-		const u8 *mumimo_groups;
-		u32 cap_flag = NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER;
-
-		if (!wiphy_ext_feature_isset(&rdev->wiphy, cap_flag))
-			return -EOPNOTSUPP;
-
-		mumimo_groups =
-			nla_data(info->attrs[NL80211_ATTR_MU_MIMO_GROUP_DATA]);
-
-		/* bits 0 and 63 are reserved and must be zero */
-		if ((mumimo_groups[0] & BIT(7)) ||
-		    (mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN - 1] & BIT(0)))
-			return -EINVAL;
-
-		memcpy(params.vht_mumimo_groups, mumimo_groups,
-		       VHT_MUMIMO_GROUPS_DATA_LEN);
-		change = true;
-	}
-
-	if (info->attrs[NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR]) {
-		u32 cap_flag = NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER;
-
-		if (!wiphy_ext_feature_isset(&rdev->wiphy, cap_flag))
-			return -EOPNOTSUPP;
-
-		nla_memcpy(params.macaddr,
-			   info->attrs[NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR],
-			   ETH_ALEN);
+	err = nl80211_parse_mon_options(rdev, ntype, info, &params);
+	if (err < 0)
+		return err;
+	if (err > 0)
 		change = true;
-	}
-
-	if (flags && (*flags & MONITOR_FLAG_ACTIVE) &&
-	    !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR))
-		return -EOPNOTSUPP;
 
 	if (change)
-		err = cfg80211_change_iface(rdev, dev, ntype, flags, &params);
+		err = cfg80211_change_iface(rdev, dev, ntype, &params);
 	else
 		err = 0;
 
@@ -2863,7 +2889,6 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *msg;
 	int err;
 	enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED;
-	u32 flags;
 
 	/* to avoid failing a new interface creation due to pending removal */
 	cfg80211_destroy_ifaces(rdev);
@@ -2899,13 +2924,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 			return err;
 	}
 
-	err = parse_monitor_flags(type == NL80211_IFTYPE_MONITOR ?
-				  info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL,
-				  &flags);
-
-	if (!err && (flags & MONITOR_FLAG_ACTIVE) &&
-	    !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR))
-		return -EOPNOTSUPP;
+	err = nl80211_parse_mon_options(rdev, type, info, &params);
+	if (err < 0)
+		return err;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
@@ -2913,8 +2934,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 
 	wdev = rdev_add_virtual_intf(rdev,
 				nla_data(info->attrs[NL80211_ATTR_IFNAME]),
-				NET_NAME_USER, type, err ? NULL : &flags,
-				&params);
+				NET_NAME_USER, type, &params);
 	if (WARN_ON(!wdev)) {
 		nlmsg_free(msg);
 		return -EPROTO;
@@ -3575,7 +3595,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 		if (sband == NULL)
 			return -EINVAL;
 		err = nla_parse_nested(tb, NL80211_TXRATE_MAX, tx_rates,
-				       nl80211_txattr_policy);
+				       nl80211_txattr_policy, info->extack);
 		if (err)
 			return err;
 		if (tb[NL80211_TXRATE_LEGACY]) {
@@ -3832,6 +3852,19 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev,
 			return false;
 		return true;
 	case NL80211_CMD_CONNECT:
+		/* SAE not supported yet */
+		if (auth_type == NL80211_AUTHTYPE_SAE)
+			return false;
+		/* FILS with SK PFS or PK not supported yet */
+		if (auth_type == NL80211_AUTHTYPE_FILS_SK_PFS ||
+		    auth_type == NL80211_AUTHTYPE_FILS_PK)
+			return false;
+		if (!wiphy_ext_feature_isset(
+			    &rdev->wiphy,
+			    NL80211_EXT_FEATURE_FILS_SK_OFFLOAD) &&
+		    auth_type == NL80211_AUTHTYPE_FILS_SK)
+			return false;
+		return true;
 	case NL80211_CMD_START_AP:
 		/* SAE not supported yet */
 		if (auth_type == NL80211_AUTHTYPE_SAE)
@@ -4114,8 +4147,8 @@ static int parse_station_flags(struct genl_info *info,
 	if (!nla)
 		return 0;
 
-	if (nla_parse_nested(flags, NL80211_STA_FLAG_MAX,
-			     nla, sta_flags_policy))
+	if (nla_parse_nested(flags, NL80211_STA_FLAG_MAX, nla,
+			     sta_flags_policy, info->extack))
 		return -EINVAL;
 
 	/*
@@ -4165,7 +4198,7 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 	struct nlattr *rate;
 	u32 bitrate;
 	u16 bitrate_compat;
-	enum nl80211_attrs rate_flg;
+	enum nl80211_rate_info rate_flg;
 
 	rate = nla_nest_start(msg, attr);
 	if (!rate)
@@ -4452,9 +4485,10 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	int sta_idx = cb->args[2];
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out_err;
 
 	if (!wdev->netdev) {
 		err = -EINVAL;
@@ -4489,7 +4523,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	cb->args[2] = sta_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 
 	return err;
 }
@@ -4741,7 +4775,7 @@ static int nl80211_parse_sta_wme(struct genl_info *info,
 
 	nla = info->attrs[NL80211_ATTR_STA_WME];
 	err = nla_parse_nested(tb, NL80211_STA_WME_MAX, nla,
-			       nl80211_sta_wme_policy);
+			       nl80211_sta_wme_policy, info->extack);
 	if (err)
 		return err;
 
@@ -5275,9 +5309,10 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	int path_idx = cb->args[2];
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out_err;
 
 	if (!rdev->ops->dump_mpath) {
 		err = -EOPNOTSUPP;
@@ -5310,7 +5345,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	cb->args[2] = path_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 	return err;
 }
 
@@ -5470,9 +5505,10 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
 	int path_idx = cb->args[2];
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out_err;
 
 	if (!rdev->ops->dump_mpp) {
 		err = -EOPNOTSUPP;
@@ -5505,7 +5541,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
 	cb->args[2] = path_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 	return err;
 }
 
@@ -5714,7 +5750,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb,
 		       cur_params.dot11MeshGateAnnouncementProtocol) ||
 	    nla_put_u8(msg, NL80211_MESHCONF_FORWARDING,
 		       cur_params.dot11MeshForwarding) ||
-	    nla_put_u32(msg, NL80211_MESHCONF_RSSI_THRESHOLD,
+	    nla_put_s32(msg, NL80211_MESHCONF_RSSI_THRESHOLD,
 			cur_params.rssi_threshold) ||
 	    nla_put_u32(msg, NL80211_MESHCONF_HT_OPMODE,
 			cur_params.ht_opmode) ||
@@ -5864,7 +5900,7 @@ do {									    \
 		return -EINVAL;
 	if (nla_parse_nested(tb, NL80211_MESHCONF_ATTR_MAX,
 			     info->attrs[NL80211_ATTR_MESH_CONFIG],
-			     nl80211_meshconf_params_policy))
+			     nl80211_meshconf_params_policy, info->extack))
 		return -EINVAL;
 
 	/* This makes sure that there aren't more than 32 mesh config
@@ -6013,7 +6049,7 @@ static int nl80211_parse_mesh_setup(struct genl_info *info,
 		return -EINVAL;
 	if (nla_parse_nested(tb, NL80211_MESH_SETUP_ATTR_MAX,
 			     info->attrs[NL80211_ATTR_MESH_SETUP],
-			     nl80211_mesh_setup_params_policy))
+			     nl80211_mesh_setup_params_policy, info->extack))
 		return -EINVAL;
 
 	if (tb[NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC])
@@ -6404,7 +6440,8 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 	nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES],
 			    rem_reg_rules) {
 		r = nla_parse_nested(tb, NL80211_REG_RULE_ATTR_MAX,
-				     nl_reg_rule, reg_rule_policy);
+				     nl_reg_rule, reg_rule_policy,
+				     info->extack);
 		if (r)
 			goto bad_reg;
 		r = parse_reg_rule(tb, &rd->reg_rules[rule_idx]);
@@ -6472,7 +6509,7 @@ static int parse_bss_select(struct nlattr *nla, struct wiphy *wiphy,
 		return -EINVAL;
 
 	err = nla_parse_nested(attr, NL80211_BSS_SELECT_ATTR_MAX, nest,
-			       nl80211_bss_select_policy);
+			       nl80211_bss_select_policy, NULL);
 	if (err)
 		return err;
 
@@ -6556,6 +6593,19 @@ static int nl80211_parse_random_mac(struct nlattr **attrs,
 	return 0;
 }
 
+static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev)
+{
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (!cfg80211_beaconing_iface_active(wdev))
+		return true;
+
+	if (!(wdev->chandef.chan->flags & IEEE80211_CHAN_RADAR))
+		return true;
+
+	return regulatory_pre_cac_allowed(wdev->wiphy);
+}
+
 static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -6681,6 +6731,25 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 
 	request->n_channels = i;
 
+	wdev_lock(wdev);
+	if (!cfg80211_off_channel_oper_allowed(wdev)) {
+		struct ieee80211_channel *chan;
+
+		if (request->n_channels != 1) {
+			wdev_unlock(wdev);
+			err = -EBUSY;
+			goto out_free;
+		}
+
+		chan = request->channels[0];
+		if (chan->center_freq != wdev->chandef.chan->center_freq) {
+			wdev_unlock(wdev);
+			err = -EBUSY;
+			goto out_free;
+		}
+	}
+	wdev_unlock(wdev);
+
 	i = 0;
 	if (n_ssids) {
 		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) {
@@ -6873,7 +6942,7 @@ nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans,
 			return -EINVAL;
 
 		err = nla_parse_nested(plan, NL80211_SCHED_SCAN_PLAN_MAX,
-				       attr, nl80211_plan_policy);
+				       attr, nl80211_plan_policy, NULL);
 		if (err)
 			return err;
 
@@ -6964,11 +7033,19 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 
 			err = nla_parse_nested(tb,
 					       NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
-					       attr, nl80211_match_policy);
+					       attr, nl80211_match_policy,
+					       NULL);
 			if (err)
 				return ERR_PTR(err);
+
+			/* SSID and BSSID are mutually exclusive */
+			if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID] &&
+			    tb[NL80211_SCHED_SCAN_MATCH_ATTR_BSSID])
+				return ERR_PTR(-EINVAL);
+
 			/* add other standalone attributes here */
-			if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]) {
+			if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID] ||
+			    tb[NL80211_SCHED_SCAN_MATCH_ATTR_BSSID]) {
 				n_match_sets++;
 				continue;
 			}
@@ -7139,15 +7216,17 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 		nla_for_each_nested(attr,
 				    attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
 				    tmp) {
-			struct nlattr *ssid, *rssi;
+			struct nlattr *ssid, *bssid, *rssi;
 
 			err = nla_parse_nested(tb,
 					       NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
-					       attr, nl80211_match_policy);
+					       attr, nl80211_match_policy,
+					       NULL);
 			if (err)
 				goto out_free;
 			ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID];
-			if (ssid) {
+			bssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_BSSID];
+			if (ssid || bssid) {
 				if (WARN_ON(i >= n_match_sets)) {
 					/* this indicates a programming error,
 					 * the loop above should have verified
@@ -7157,14 +7236,25 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 					goto out_free;
 				}
 
-				if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) {
-					err = -EINVAL;
-					goto out_free;
+				if (ssid) {
+					if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) {
+						err = -EINVAL;
+						goto out_free;
+					}
+					memcpy(request->match_sets[i].ssid.ssid,
+					       nla_data(ssid), nla_len(ssid));
+					request->match_sets[i].ssid.ssid_len =
+						nla_len(ssid);
+				}
+				if (bssid) {
+					if (nla_len(bssid) != ETH_ALEN) {
+						err = -EINVAL;
+						goto out_free;
+					}
+					memcpy(request->match_sets[i].bssid,
+					       nla_data(bssid), ETH_ALEN);
 				}
-				memcpy(request->match_sets[i].ssid.ssid,
-				       nla_data(ssid), nla_len(ssid));
-				request->match_sets[i].ssid.ssid_len =
-					nla_len(ssid);
+
 				/* special attribute - old implementation w/a */
 				request->match_sets[i].rssi_thold =
 					default_match_rssi;
@@ -7272,14 +7362,16 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_sched_scan_request *sched_scan_req;
+	bool want_multi;
 	int err;
 
-	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
-	    !rdev->ops->sched_scan_start)
+	if (!rdev->wiphy.max_sched_scan_reqs || !rdev->ops->sched_scan_start)
 		return -EOPNOTSUPP;
 
-	if (rdev->sched_scan_req)
-		return -EINPROGRESS;
+	want_multi = info->attrs[NL80211_ATTR_SCHED_SCAN_MULTI];
+	err = cfg80211_sched_scan_req_possible(rdev, want_multi);
+	if (err)
+		return err;
 
 	sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev,
 						  info->attrs,
@@ -7289,6 +7381,14 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (err)
 		goto out_err;
 
+	/* leave request id zero for legacy request
+	 * or if driver does not support multi-scheduled scan
+	 */
+	if (want_multi && rdev->wiphy.max_sched_scan_reqs > 1) {
+		while (!sched_scan_req->reqid)
+			sched_scan_req->reqid = rdev->wiphy.cookie_counter++;
+	}
+
 	err = rdev_sched_scan_start(rdev, dev, sched_scan_req);
 	if (err)
 		goto out_free;
@@ -7299,10 +7399,9 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (info->attrs[NL80211_ATTR_SOCKET_OWNER])
 		sched_scan_req->owner_nlportid = info->snd_portid;
 
-	rcu_assign_pointer(rdev->sched_scan_req, sched_scan_req);
+	cfg80211_add_sched_scan_req(rdev, sched_scan_req);
 
-	nl80211_send_sched_scan(rdev, dev,
-				NL80211_CMD_START_SCHED_SCAN);
+	nl80211_send_sched_scan(sched_scan_req, NL80211_CMD_START_SCHED_SCAN);
 	return 0;
 
 out_free:
@@ -7314,13 +7413,27 @@ out_err:
 static int nl80211_stop_sched_scan(struct sk_buff *skb,
 				   struct genl_info *info)
 {
+	struct cfg80211_sched_scan_request *req;
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	u64 cookie;
 
-	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
-	    !rdev->ops->sched_scan_stop)
+	if (!rdev->wiphy.max_sched_scan_reqs || !rdev->ops->sched_scan_stop)
 		return -EOPNOTSUPP;
 
-	return __cfg80211_stop_sched_scan(rdev, false);
+	if (info->attrs[NL80211_ATTR_COOKIE]) {
+		cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]);
+		return __cfg80211_stop_sched_scan(rdev, cookie, false);
+	}
+
+	req = list_first_or_null_rcu(&rdev->sched_scan_req_list,
+				     struct cfg80211_sched_scan_request,
+				     list);
+	if (!req || req->reqid ||
+	    (req->owner_nlportid &&
+	     req->owner_nlportid != info->snd_portid))
+		return -ENOENT;
+
+	return cfg80211_stop_sched_scan_req(rdev, req, false);
 }
 
 static int nl80211_start_radar_detection(struct sk_buff *skb,
@@ -7444,7 +7557,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(csa_attrs, NL80211_ATTR_MAX,
 			       info->attrs[NL80211_ATTR_CSA_IES],
-			       nl80211_policy);
+			       nl80211_policy, info->extack);
 	if (err)
 		return err;
 
@@ -7674,9 +7787,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	int start = cb->args[2], idx = 0;
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
-	if (err)
+	if (err) {
+		rtnl_unlock();
 		return err;
+	}
 
 	wdev_lock(wdev);
 	spin_lock_bh(&rdev->bss_lock);
@@ -7699,7 +7815,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	wdev_unlock(wdev);
 
 	cb->args[2] = idx;
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 
 	return skb->len;
 }
@@ -7784,9 +7900,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 	int res;
 	bool radio_stats;
 
+	rtnl_lock();
 	res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (res)
-		return res;
+		goto out_err;
 
 	/* prepare_wdev_dump parsed the attributes */
 	radio_stats = attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS];
@@ -7827,7 +7944,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 	cb->args[2] = survey_idx;
 	res = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 	return res;
 }
 
@@ -8646,7 +8763,8 @@ static int nl80211_testmode_dump(struct sk_buff *skb,
 		struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam);
 
 		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
-				  attrbuf, nl80211_fam.maxattr, nl80211_policy);
+				  attrbuf, nl80211_fam.maxattr,
+				  nl80211_policy, NULL);
 		if (err)
 			goto out_err;
 
@@ -8874,6 +8992,35 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+	if (wiphy_ext_feature_isset(&rdev->wiphy,
+				    NL80211_EXT_FEATURE_FILS_SK_OFFLOAD) &&
+	    info->attrs[NL80211_ATTR_FILS_ERP_USERNAME] &&
+	    info->attrs[NL80211_ATTR_FILS_ERP_REALM] &&
+	    info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM] &&
+	    info->attrs[NL80211_ATTR_FILS_ERP_RRK]) {
+		connect.fils_erp_username =
+			nla_data(info->attrs[NL80211_ATTR_FILS_ERP_USERNAME]);
+		connect.fils_erp_username_len =
+			nla_len(info->attrs[NL80211_ATTR_FILS_ERP_USERNAME]);
+		connect.fils_erp_realm =
+			nla_data(info->attrs[NL80211_ATTR_FILS_ERP_REALM]);
+		connect.fils_erp_realm_len =
+			nla_len(info->attrs[NL80211_ATTR_FILS_ERP_REALM]);
+		connect.fils_erp_next_seq_num =
+			nla_get_u16(
+			   info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM]);
+		connect.fils_erp_rrk =
+			nla_data(info->attrs[NL80211_ATTR_FILS_ERP_RRK]);
+		connect.fils_erp_rrk_len =
+			nla_len(info->attrs[NL80211_ATTR_FILS_ERP_RRK]);
+	} else if (info->attrs[NL80211_ATTR_FILS_ERP_USERNAME] ||
+		   info->attrs[NL80211_ATTR_FILS_ERP_REALM] ||
+		   info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM] ||
+		   info->attrs[NL80211_ATTR_FILS_ERP_RRK]) {
+		kzfree(connkeys);
+		return -EINVAL;
+	}
+
 	wdev_lock(dev->ieee80211_ptr);
 
 	err = cfg80211_connect(rdev, dev, &connect, connkeys,
@@ -8993,14 +9140,28 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
 
 	memset(&pmksa, 0, sizeof(struct cfg80211_pmksa));
 
-	if (!info->attrs[NL80211_ATTR_MAC])
-		return -EINVAL;
-
 	if (!info->attrs[NL80211_ATTR_PMKID])
 		return -EINVAL;
 
 	pmksa.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]);
-	pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	if (info->attrs[NL80211_ATTR_MAC]) {
+		pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	} else if (info->attrs[NL80211_ATTR_SSID] &&
+		   info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
+		   (info->genlhdr->cmd == NL80211_CMD_DEL_PMKSA ||
+		    info->attrs[NL80211_ATTR_PMK])) {
+		pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
+		pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
+		pmksa.cache_id =
+			nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
+	} else {
+		return -EINVAL;
+	}
+	if (info->attrs[NL80211_ATTR_PMK]) {
+		pmksa.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]);
+		pmksa.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]);
+	}
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT)
@@ -9103,6 +9264,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
 	struct cfg80211_chan_def chandef;
+	const struct cfg80211_chan_def *compat_chandef;
 	struct sk_buff *msg;
 	void *hdr;
 	u64 cookie;
@@ -9131,6 +9293,18 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 	if (err)
 		return err;
 
+	wdev_lock(wdev);
+	if (!cfg80211_off_channel_oper_allowed(wdev) &&
+	    !cfg80211_chandef_identical(&wdev->chandef, &chandef)) {
+		compat_chandef = cfg80211_chandef_compatible(&wdev->chandef,
+							     &chandef);
+		if (compat_chandef != &chandef) {
+			wdev_unlock(wdev);
+			return -EBUSY;
+		}
+	}
+	wdev_unlock(wdev);
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -9306,6 +9480,13 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 	if (!chandef.chan && params.offchan)
 		return -EINVAL;
 
+	wdev_lock(wdev);
+	if (params.offchan && !cfg80211_off_channel_oper_allowed(wdev)) {
+		wdev_unlock(wdev);
+		return -EBUSY;
+	}
+	wdev_unlock(wdev);
+
 	params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
 	params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
 
@@ -9473,7 +9654,7 @@ static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info)
 
 static const struct nla_policy
 nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] = {
-	[NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_U32 },
+	[NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_BINARY },
 	[NL80211_ATTR_CQM_RSSI_HYST] = { .type = NLA_U32 },
 	[NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT] = { .type = NLA_U32 },
 	[NL80211_ATTR_CQM_TXE_RATE] = { .type = NLA_U32 },
@@ -9502,28 +9683,123 @@ static int nl80211_set_cqm_txe(struct genl_info *info,
 	return rdev_set_cqm_txe_config(rdev, dev, rate, pkts, intvl);
 }
 
+static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
+				    struct net_device *dev)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	s32 last, low, high;
+	u32 hyst;
+	int i, n;
+	int err;
+
+	/* RSSI reporting disabled? */
+	if (!wdev->cqm_config)
+		return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0);
+
+	/*
+	 * Obtain current RSSI value if possible, if not and no RSSI threshold
+	 * event has been received yet, we should receive an event after a
+	 * connection is established and enough beacons received to calculate
+	 * the average.
+	 */
+	if (!wdev->cqm_config->last_rssi_event_value && wdev->current_bss &&
+	    rdev->ops->get_station) {
+		struct station_info sinfo;
+		u8 *mac_addr;
+
+		mac_addr = wdev->current_bss->pub.bssid;
+
+		err = rdev_get_station(rdev, dev, mac_addr, &sinfo);
+		if (err)
+			return err;
+
+		if (sinfo.filled & BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
+			wdev->cqm_config->last_rssi_event_value =
+				(s8) sinfo.rx_beacon_signal_avg;
+	}
+
+	last = wdev->cqm_config->last_rssi_event_value;
+	hyst = wdev->cqm_config->rssi_hyst;
+	n = wdev->cqm_config->n_rssi_thresholds;
+
+	for (i = 0; i < n; i++)
+		if (last < wdev->cqm_config->rssi_thresholds[i])
+			break;
+
+	low = i > 0 ?
+		(wdev->cqm_config->rssi_thresholds[i - 1] - hyst) : S32_MIN;
+	high = i < n ?
+		(wdev->cqm_config->rssi_thresholds[i] + hyst - 1) : S32_MAX;
+
+	return rdev_set_cqm_rssi_range_config(rdev, dev, low, high);
+}
+
 static int nl80211_set_cqm_rssi(struct genl_info *info,
-				s32 threshold, u32 hysteresis)
+				const s32 *thresholds, int n_thresholds,
+				u32 hysteresis)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int i, err;
+	s32 prev = S32_MIN;
 
-	if (threshold > 0)
-		return -EINVAL;
-
-	/* disabling - hysteresis should also be zero then */
-	if (threshold == 0)
-		hysteresis = 0;
+	/* Check all values negative and sorted */
+	for (i = 0; i < n_thresholds; i++) {
+		if (thresholds[i] > 0 || thresholds[i] <= prev)
+			return -EINVAL;
 
-	if (!rdev->ops->set_cqm_rssi_config)
-		return -EOPNOTSUPP;
+		prev = thresholds[i];
+	}
 
 	if (wdev->iftype != NL80211_IFTYPE_STATION &&
 	    wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)
 		return -EOPNOTSUPP;
 
-	return rdev_set_cqm_rssi_config(rdev, dev, threshold, hysteresis);
+	wdev_lock(wdev);
+	cfg80211_cqm_config_free(wdev);
+	wdev_unlock(wdev);
+
+	if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) {
+		if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */
+			return rdev_set_cqm_rssi_config(rdev, dev, 0, 0);
+
+		return rdev_set_cqm_rssi_config(rdev, dev,
+						thresholds[0], hysteresis);
+	}
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_CQM_RSSI_LIST))
+		return -EOPNOTSUPP;
+
+	if (n_thresholds == 1 && thresholds[0] == 0) /* Disabling */
+		n_thresholds = 0;
+
+	wdev_lock(wdev);
+	if (n_thresholds) {
+		struct cfg80211_cqm_config *cqm_config;
+
+		cqm_config = kzalloc(sizeof(struct cfg80211_cqm_config) +
+				     n_thresholds * sizeof(s32), GFP_KERNEL);
+		if (!cqm_config) {
+			err = -ENOMEM;
+			goto unlock;
+		}
+
+		cqm_config->rssi_hyst = hysteresis;
+		cqm_config->n_rssi_thresholds = n_thresholds;
+		memcpy(cqm_config->rssi_thresholds, thresholds,
+		       n_thresholds * sizeof(s32));
+
+		wdev->cqm_config = cqm_config;
+	}
+
+	err = cfg80211_cqm_rssi_update(rdev, dev);
+
+unlock:
+	wdev_unlock(wdev);
+
+	return err;
 }
 
 static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info)
@@ -9537,16 +9813,22 @@ static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	err = nla_parse_nested(attrs, NL80211_ATTR_CQM_MAX, cqm,
-			       nl80211_attr_cqm_policy);
+			       nl80211_attr_cqm_policy, info->extack);
 	if (err)
 		return err;
 
 	if (attrs[NL80211_ATTR_CQM_RSSI_THOLD] &&
 	    attrs[NL80211_ATTR_CQM_RSSI_HYST]) {
-		s32 threshold = nla_get_s32(attrs[NL80211_ATTR_CQM_RSSI_THOLD]);
+		const s32 *thresholds =
+			nla_data(attrs[NL80211_ATTR_CQM_RSSI_THOLD]);
+		int len = nla_len(attrs[NL80211_ATTR_CQM_RSSI_THOLD]);
 		u32 hysteresis = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_HYST]);
 
-		return nl80211_set_cqm_rssi(info, threshold, hysteresis);
+		if (len % 4)
+			return -EINVAL;
+
+		return nl80211_set_cqm_rssi(info, thresholds, len / 4,
+					    hysteresis);
 	}
 
 	if (attrs[NL80211_ATTR_CQM_TXE_RATE] &&
@@ -9947,7 +10229,7 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev,
 		return -EINVAL;
 
 	err = nla_parse_nested(tb, MAX_NL80211_WOWLAN_TCP, attr,
-			       nl80211_wowlan_tcp_policy);
+			       nl80211_wowlan_tcp_policy, NULL);
 	if (err)
 		return err;
 
@@ -10092,7 +10374,8 @@ static int nl80211_parse_wowlan_nd(struct cfg80211_registered_device *rdev,
 		goto out;
 	}
 
-	err = nla_parse_nested(tb, NL80211_ATTR_MAX, attr, nl80211_policy);
+	err = nla_parse_nested(tb, NL80211_ATTR_MAX, attr, nl80211_policy,
+			       NULL);
 	if (err)
 		goto out;
 
@@ -10129,7 +10412,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(tb, MAX_NL80211_WOWLAN_TRIG,
 			       info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS],
-			       nl80211_wowlan_policy);
+			       nl80211_wowlan_policy, info->extack);
 	if (err)
 		return err;
 
@@ -10212,7 +10495,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 			u8 *mask_pat;
 
 			nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-					 NULL);
+					 NULL, info->extack);
 			err = -EINVAL;
 			if (!pat_tb[NL80211_PKTPAT_MASK] ||
 			    !pat_tb[NL80211_PKTPAT_PATTERN])
@@ -10423,7 +10706,7 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 	struct nlattr *pat_tb[NUM_NL80211_PKTPAT];
 
 	err = nla_parse_nested(tb, NL80211_ATTR_COALESCE_RULE_MAX, rule,
-			       nl80211_coalesce_policy);
+			       nl80211_coalesce_policy, NULL);
 	if (err)
 		return err;
 
@@ -10461,7 +10744,7 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 			    rem) {
 		u8 *mask_pat;
 
-		nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL);
+		nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL, NULL);
 		if (!pat_tb[NL80211_PKTPAT_MASK] ||
 		    !pat_tb[NL80211_PKTPAT_PATTERN])
 			return -EINVAL;
@@ -10582,7 +10865,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
 
 	err = nla_parse_nested(tb, MAX_NL80211_REKEY_DATA,
 			       info->attrs[NL80211_ATTR_REKEY_DATA],
-			       nl80211_rekey_policy);
+			       nl80211_rekey_policy, info->extack);
 	if (err)
 		return err;
 
@@ -10899,7 +11182,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
 
 	err = nla_parse_nested(tb, NL80211_NAN_FUNC_ATTR_MAX,
 			       info->attrs[NL80211_ATTR_NAN_FUNC],
-			       nl80211_nan_func_policy);
+			       nl80211_nan_func_policy, info->extack);
 	if (err)
 		return err;
 
@@ -10996,7 +11279,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
 
 		err = nla_parse_nested(srf_tb, NL80211_NAN_SRF_ATTR_MAX,
 				       tb[NL80211_NAN_FUNC_SRF],
-				       nl80211_nan_srf_policy);
+				       nl80211_nan_srf_policy, info->extack);
 		if (err)
 			goto out;
 
@@ -11508,17 +11791,13 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 	void *data = NULL;
 	unsigned int data_len = 0;
 
-	rtnl_lock();
-
 	if (cb->args[0]) {
 		/* subtract the 1 again here */
 		struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
 		struct wireless_dev *tmp;
 
-		if (!wiphy) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+		if (!wiphy)
+			return -ENODEV;
 		*rdev = wiphy_to_rdev(wiphy);
 		*wdev = NULL;
 
@@ -11535,26 +11814,22 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 		return 0;
 	}
 
-	err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
-			  attrbuf, nl80211_fam.maxattr, nl80211_policy);
+	err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf,
+			  nl80211_fam.maxattr, nl80211_policy, NULL);
 	if (err)
-		goto out_unlock;
+		return err;
 
 	if (!attrbuf[NL80211_ATTR_VENDOR_ID] ||
-	    !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) {
-		err = -EINVAL;
-		goto out_unlock;
-	}
+	    !attrbuf[NL80211_ATTR_VENDOR_SUBCMD])
+		return -EINVAL;
 
 	*wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), attrbuf);
 	if (IS_ERR(*wdev))
 		*wdev = NULL;
 
 	*rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), attrbuf);
-	if (IS_ERR(*rdev)) {
-		err = PTR_ERR(*rdev);
-		goto out_unlock;
-	}
+	if (IS_ERR(*rdev))
+		return PTR_ERR(*rdev);
 
 	vid = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_ID]);
 	subcmd = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_SUBCMD]);
@@ -11567,19 +11842,15 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 		if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
 			continue;
 
-		if (!vcmd->dumpit) {
-			err = -EOPNOTSUPP;
-			goto out_unlock;
-		}
+		if (!vcmd->dumpit)
+			return -EOPNOTSUPP;
 
 		vcmd_idx = i;
 		break;
 	}
 
-	if (vcmd_idx < 0) {
-		err = -EOPNOTSUPP;
-		goto out_unlock;
-	}
+	if (vcmd_idx < 0)
+		return -EOPNOTSUPP;
 
 	if (attrbuf[NL80211_ATTR_VENDOR_DATA]) {
 		data = nla_data(attrbuf[NL80211_ATTR_VENDOR_DATA]);
@@ -11596,9 +11867,6 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 
 	/* keep rtnl locked in successful case */
 	return 0;
- out_unlock:
-	rtnl_unlock();
-	return err;
 }
 
 static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
@@ -11613,9 +11881,10 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
 	int err;
 	struct nlattr *vendor_data;
 
+	rtnl_lock();
 	err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out;
 
 	vcmd_idx = cb->args[2];
 	data = (void *)cb->args[3];
@@ -11624,15 +11893,21 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
 
 	if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
 			   WIPHY_VENDOR_CMD_NEED_NETDEV)) {
-		if (!wdev)
-			return -EINVAL;
+		if (!wdev) {
+			err = -EINVAL;
+			goto out;
+		}
 		if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
-		    !wdev->netdev)
-			return -EINVAL;
+		    !wdev->netdev) {
+			err = -EINVAL;
+			goto out;
+		}
 
 		if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
-			if (!wdev_running(wdev))
-				return -ENETDOWN;
+			if (!wdev_running(wdev)) {
+				err = -ENETDOWN;
+				goto out;
+			}
 		}
 	}
 
@@ -12985,18 +13260,19 @@ static int nl80211_prep_scan_msg(struct sk_buff *msg,
 
 static int
 nl80211_prep_sched_scan_msg(struct sk_buff *msg,
-			    struct cfg80211_registered_device *rdev,
-			    struct net_device *netdev,
-			    u32 portid, u32 seq, int flags, u32 cmd)
+			    struct cfg80211_sched_scan_request *req, u32 cmd)
 {
 	void *hdr;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
+	hdr = nl80211hdr_put(msg, 0, 0, 0, cmd);
 	if (!hdr)
 		return -1;
 
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
-	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex))
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY,
+			wiphy_to_rdev(req->wiphy)->wiphy_idx) ||
+	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, req->dev->ifindex) ||
+	    nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, req->reqid,
+			      NL80211_ATTR_PAD))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -13056,8 +13332,7 @@ void nl80211_send_scan_msg(struct cfg80211_registered_device *rdev,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
-void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
-			     struct net_device *netdev, u32 cmd)
+void nl80211_send_sched_scan(struct cfg80211_sched_scan_request *req, u32 cmd)
 {
 	struct sk_buff *msg;
 
@@ -13065,12 +13340,12 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 	if (!msg)
 		return;
 
-	if (nl80211_prep_sched_scan_msg(msg, rdev, netdev, 0, 0, 0, cmd) < 0) {
+	if (nl80211_prep_sched_scan_msg(msg, req, cmd) < 0) {
 		nlmsg_free(msg);
 		return;
 	}
 
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(req->wiphy), msg, 0,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
@@ -13311,17 +13586,16 @@ void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev,
 }
 
 void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
-				 struct net_device *netdev, const u8 *bssid,
-				 const u8 *req_ie, size_t req_ie_len,
-				 const u8 *resp_ie, size_t resp_ie_len,
-				 int status,
-				 enum nl80211_timeout_reason timeout_reason,
+				 struct net_device *netdev,
+				 struct cfg80211_connect_resp_params *cr,
 				 gfp_t gfp)
 {
 	struct sk_buff *msg;
 	void *hdr;
 
-	msg = nlmsg_new(100 + req_ie_len + resp_ie_len, gfp);
+	msg = nlmsg_new(100 + cr->req_ie_len + cr->resp_ie_len +
+			cr->fils_kek_len + cr->pmk_len +
+			(cr->pmkid ? WLAN_PMKID_LEN : 0), gfp);
 	if (!msg)
 		return;
 
@@ -13333,17 +13607,31 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
-	    (bssid && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) ||
+	    (cr->bssid &&
+	     nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, cr->bssid)) ||
 	    nla_put_u16(msg, NL80211_ATTR_STATUS_CODE,
-			status < 0 ? WLAN_STATUS_UNSPECIFIED_FAILURE :
-			status) ||
-	    (status < 0 &&
+			cr->status < 0 ? WLAN_STATUS_UNSPECIFIED_FAILURE :
+			cr->status) ||
+	    (cr->status < 0 &&
 	     (nla_put_flag(msg, NL80211_ATTR_TIMED_OUT) ||
-	      nla_put_u32(msg, NL80211_ATTR_TIMEOUT_REASON, timeout_reason))) ||
-	    (req_ie &&
-	     nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) ||
-	    (resp_ie &&
-	     nla_put(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie)))
+	      nla_put_u32(msg, NL80211_ATTR_TIMEOUT_REASON,
+			  cr->timeout_reason))) ||
+	    (cr->req_ie &&
+	     nla_put(msg, NL80211_ATTR_REQ_IE, cr->req_ie_len, cr->req_ie)) ||
+	    (cr->resp_ie &&
+	     nla_put(msg, NL80211_ATTR_RESP_IE, cr->resp_ie_len,
+		     cr->resp_ie)) ||
+	    (cr->update_erp_next_seq_num &&
+	     nla_put_u16(msg, NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM,
+			 cr->fils_erp_next_seq_num)) ||
+	    (cr->status == WLAN_STATUS_SUCCESS &&
+	     ((cr->fils_kek &&
+	       nla_put(msg, NL80211_ATTR_FILS_KEK, cr->fils_kek_len,
+		       cr->fils_kek)) ||
+	      (cr->pmk &&
+	       nla_put(msg, NL80211_ATTR_PMK, cr->pmk_len, cr->pmk)) ||
+	      (cr->pmkid &&
+	       nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, cr->pmkid)))))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -13358,14 +13646,14 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 }
 
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
-			 struct net_device *netdev, const u8 *bssid,
-			 const u8 *req_ie, size_t req_ie_len,
-			 const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp)
+			 struct net_device *netdev,
+			 struct cfg80211_roam_info *info, gfp_t gfp)
 {
 	struct sk_buff *msg;
 	void *hdr;
+	const u8 *bssid = info->bss ? info->bss->bssid : info->bssid;
 
-	msg = nlmsg_new(100 + req_ie_len + resp_ie_len, gfp);
+	msg = nlmsg_new(100 + info->req_ie_len + info->resp_ie_len, gfp);
 	if (!msg)
 		return;
 
@@ -13378,10 +13666,12 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid) ||
-	    (req_ie &&
-	     nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) ||
-	    (resp_ie &&
-	     nla_put(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie)))
+	    (info->req_ie &&
+	     nla_put(msg, NL80211_ATTR_REQ_IE, info->req_ie_len,
+		     info->req_ie)) ||
+	    (info->resp_ie &&
+	     nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len,
+		     info->resp_ie)))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -13983,6 +14273,8 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 			      s32 rssi_level, gfp_t gfp)
 {
 	struct sk_buff *msg;
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	trace_cfg80211_cqm_rssi_notify(dev, rssi_event, rssi_level);
 
@@ -13990,6 +14282,15 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 		    rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH))
 		return;
 
+	if (wdev->cqm_config) {
+		wdev->cqm_config->last_rssi_event_value = rssi_level;
+
+		cfg80211_cqm_rssi_update(rdev, dev);
+
+		if (rssi_level == 0)
+			rssi_level = wdev->cqm_config->last_rssi_event_value;
+	}
+
 	msg = cfg80211_prepare_cqm(dev, NULL, gfp);
 	if (!msg)
 		return;
@@ -14634,26 +14935,26 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
-		bool schedule_destroy_work = false;
-		struct cfg80211_sched_scan_request *sched_scan_req =
-			rcu_dereference(rdev->sched_scan_req);
-
-		if (sched_scan_req && notify->portid &&
-		    sched_scan_req->owner_nlportid == notify->portid) {
-			sched_scan_req->owner_nlportid = 0;
+		struct cfg80211_sched_scan_request *sched_scan_req;
 
-			if (rdev->ops->sched_scan_stop &&
-			    rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+		list_for_each_entry_rcu(sched_scan_req,
+					&rdev->sched_scan_req_list,
+					list) {
+			if (sched_scan_req->owner_nlportid == notify->portid) {
+				sched_scan_req->nl_owner_dead = true;
 				schedule_work(&rdev->sched_scan_stop_wk);
+			}
 		}
 
 		list_for_each_entry_rcu(wdev, &rdev->wiphy.wdev_list, list) {
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
 
-			if (wdev->owner_nlportid == notify->portid)
-				schedule_destroy_work = true;
-			else if (wdev->conn_owner_nlportid == notify->portid)
+			if (wdev->owner_nlportid == notify->portid) {
+				wdev->nl_owner_dead = true;
+				schedule_work(&rdev->destroy_work);
+			} else if (wdev->conn_owner_nlportid == notify->portid) {
 				schedule_work(&wdev->disconnect_wk);
+			}
 		}
 
 		spin_lock_bh(&rdev->beacon_registrations_lock);
@@ -14666,19 +14967,6 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 			}
 		}
 		spin_unlock_bh(&rdev->beacon_registrations_lock);
-
-		if (schedule_destroy_work) {
-			struct cfg80211_iface_destroy *destroy;
-
-			destroy = kzalloc(sizeof(*destroy), GFP_ATOMIC);
-			if (destroy) {
-				destroy->nlportid = notify->portid;
-				spin_lock(&rdev->destroy_list_lock);
-				list_add(&destroy->list, &rdev->destroy_list);
-				spin_unlock(&rdev->destroy_list_lock);
-				schedule_work(&rdev->destroy_work);
-			}
-		}
 	}
 
 	rcu_read_unlock();
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index e488dca87423..b96933322077 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -16,8 +16,7 @@ struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev,
 				       struct wireless_dev *wdev, bool aborted);
 void nl80211_send_scan_msg(struct cfg80211_registered_device *rdev,
 			   struct sk_buff *msg);
-void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
-			     struct net_device *netdev, u32 cmd);
+void nl80211_send_sched_scan(struct cfg80211_sched_scan_request *req, u32 cmd);
 void nl80211_common_reg_change_event(enum nl80211_commands cmd_id,
 				     struct regulatory_request *request);
 
@@ -53,16 +52,12 @@ void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev,
 				struct net_device *netdev,
 				const u8 *addr, gfp_t gfp);
 void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
-				 struct net_device *netdev, const u8 *bssid,
-				 const u8 *req_ie, size_t req_ie_len,
-				 const u8 *resp_ie, size_t resp_ie_len,
-				 int status,
-				 enum nl80211_timeout_reason timeout_reason,
+				 struct net_device *netdev,
+				 struct cfg80211_connect_resp_params *params,
 				 gfp_t gfp);
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
-			 struct net_device *netdev, const u8 *bssid,
-			 const u8 *req_ie, size_t req_ie_len,
-			 const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp);
+			 struct net_device *netdev,
+			 struct cfg80211_roam_info *info, gfp_t gfp);
 void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
 			       struct net_device *netdev, u16 reason,
 			       const u8 *ie, size_t ie_len, bool from_ap);
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 2f425075ada8..0598c1e5d0ad 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -36,13 +36,13 @@ static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev,
 static inline struct wireless_dev
 *rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name,
 		       unsigned char name_assign_type,
-		       enum nl80211_iftype type, u32 *flags,
+		       enum nl80211_iftype type,
 		       struct vif_params *params)
 {
 	struct wireless_dev *ret;
 	trace_rdev_add_virtual_intf(&rdev->wiphy, name, type);
 	ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, name_assign_type,
-					  type, flags, params);
+					  type, params);
 	trace_rdev_return_wdev(&rdev->wiphy, ret);
 	return ret;
 }
@@ -61,12 +61,11 @@ rdev_del_virtual_intf(struct cfg80211_registered_device *rdev,
 static inline int
 rdev_change_virtual_intf(struct cfg80211_registered_device *rdev,
 			 struct net_device *dev, enum nl80211_iftype type,
-			 u32 *flags, struct vif_params *params)
+			 struct vif_params *params)
 {
 	int ret;
 	trace_rdev_change_virtual_intf(&rdev->wiphy, dev, type);
-	ret = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, type, flags,
-					     params);
+	ret = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, type, params);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
@@ -750,6 +749,18 @@ rdev_set_cqm_rssi_config(struct cfg80211_registered_device *rdev,
 }
 
 static inline int
+rdev_set_cqm_rssi_range_config(struct cfg80211_registered_device *rdev,
+			       struct net_device *dev, s32 low, s32 high)
+{
+	int ret;
+	trace_rdev_set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high);
+	ret = rdev->ops->set_cqm_rssi_range_config(&rdev->wiphy, dev,
+						   low, high);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
+static inline int
 rdev_set_cqm_txe_config(struct cfg80211_registered_device *rdev,
 			struct net_device *dev, u32 rate, u32 pkts, u32 intvl)
 {
@@ -802,18 +813,18 @@ rdev_sched_scan_start(struct cfg80211_registered_device *rdev,
 		      struct cfg80211_sched_scan_request *request)
 {
 	int ret;
-	trace_rdev_sched_scan_start(&rdev->wiphy, dev, request);
+	trace_rdev_sched_scan_start(&rdev->wiphy, dev, request->reqid);
 	ret = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
 
 static inline int rdev_sched_scan_stop(struct cfg80211_registered_device *rdev,
-				       struct net_device *dev)
+				       struct net_device *dev, u64 reqid)
 {
 	int ret;
-	trace_rdev_sched_scan_stop(&rdev->wiphy, dev);
-	ret = rdev->ops->sched_scan_stop(&rdev->wiphy, dev);
+	trace_rdev_sched_scan_stop(&rdev->wiphy, dev, reqid);
+	ret = rdev->ops->sched_scan_stop(&rdev->wiphy, dev, reqid);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 753efcd51fa3..5fae296a6a58 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2067,6 +2067,88 @@ reg_process_hint_country_ie(struct wiphy *wiphy,
 	return REG_REQ_IGNORE;
 }
 
+bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2)
+{
+	const struct ieee80211_regdomain *wiphy1_regd = NULL;
+	const struct ieee80211_regdomain *wiphy2_regd = NULL;
+	const struct ieee80211_regdomain *cfg80211_regd = NULL;
+	bool dfs_domain_same;
+
+	rcu_read_lock();
+
+	cfg80211_regd = rcu_dereference(cfg80211_regdomain);
+	wiphy1_regd = rcu_dereference(wiphy1->regd);
+	if (!wiphy1_regd)
+		wiphy1_regd = cfg80211_regd;
+
+	wiphy2_regd = rcu_dereference(wiphy2->regd);
+	if (!wiphy2_regd)
+		wiphy2_regd = cfg80211_regd;
+
+	dfs_domain_same = wiphy1_regd->dfs_region == wiphy2_regd->dfs_region;
+
+	rcu_read_unlock();
+
+	return dfs_domain_same;
+}
+
+static void reg_copy_dfs_chan_state(struct ieee80211_channel *dst_chan,
+				    struct ieee80211_channel *src_chan)
+{
+	if (!(dst_chan->flags & IEEE80211_CHAN_RADAR) ||
+	    !(src_chan->flags & IEEE80211_CHAN_RADAR))
+		return;
+
+	if (dst_chan->flags & IEEE80211_CHAN_DISABLED ||
+	    src_chan->flags & IEEE80211_CHAN_DISABLED)
+		return;
+
+	if (src_chan->center_freq == dst_chan->center_freq &&
+	    dst_chan->dfs_state == NL80211_DFS_USABLE) {
+		dst_chan->dfs_state = src_chan->dfs_state;
+		dst_chan->dfs_state_entered = src_chan->dfs_state_entered;
+	}
+}
+
+static void wiphy_share_dfs_chan_state(struct wiphy *dst_wiphy,
+				       struct wiphy *src_wiphy)
+{
+	struct ieee80211_supported_band *src_sband, *dst_sband;
+	struct ieee80211_channel *src_chan, *dst_chan;
+	int i, j, band;
+
+	if (!reg_dfs_domain_same(dst_wiphy, src_wiphy))
+		return;
+
+	for (band = 0; band < NUM_NL80211_BANDS; band++) {
+		dst_sband = dst_wiphy->bands[band];
+		src_sband = src_wiphy->bands[band];
+		if (!dst_sband || !src_sband)
+			continue;
+
+		for (i = 0; i < dst_sband->n_channels; i++) {
+			dst_chan = &dst_sband->channels[i];
+			for (j = 0; j < src_sband->n_channels; j++) {
+				src_chan = &src_sband->channels[j];
+				reg_copy_dfs_chan_state(dst_chan, src_chan);
+			}
+		}
+	}
+}
+
+static void wiphy_all_share_dfs_chan_state(struct wiphy *wiphy)
+{
+	struct cfg80211_registered_device *rdev;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (wiphy == &rdev->wiphy)
+			continue;
+		wiphy_share_dfs_chan_state(wiphy, &rdev->wiphy);
+	}
+}
+
 /* This processes *all* regulatory hints */
 static void reg_process_hint(struct regulatory_request *reg_request)
 {
@@ -2110,6 +2192,7 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 	if (treatment == REG_REQ_ALREADY_SET && wiphy &&
 	    wiphy->regulatory_flags & REGULATORY_STRICT_REG) {
 		wiphy_update_regulatory(wiphy, reg_request->initiator);
+		wiphy_all_share_dfs_chan_state(wiphy);
 		reg_check_channels();
 	}
 
@@ -3061,6 +3144,7 @@ void wiphy_regulatory_register(struct wiphy *wiphy)
 
 	lr = get_last_request();
 	wiphy_update_regulatory(wiphy, lr->initiator);
+	wiphy_all_share_dfs_chan_state(wiphy);
 }
 
 void wiphy_regulatory_deregister(struct wiphy *wiphy)
@@ -3120,6 +3204,67 @@ bool regulatory_indoor_allowed(void)
 	return reg_is_indoor;
 }
 
+bool regulatory_pre_cac_allowed(struct wiphy *wiphy)
+{
+	const struct ieee80211_regdomain *regd = NULL;
+	const struct ieee80211_regdomain *wiphy_regd = NULL;
+	bool pre_cac_allowed = false;
+
+	rcu_read_lock();
+
+	regd = rcu_dereference(cfg80211_regdomain);
+	wiphy_regd = rcu_dereference(wiphy->regd);
+	if (!wiphy_regd) {
+		if (regd->dfs_region == NL80211_DFS_ETSI)
+			pre_cac_allowed = true;
+
+		rcu_read_unlock();
+
+		return pre_cac_allowed;
+	}
+
+	if (regd->dfs_region == wiphy_regd->dfs_region &&
+	    wiphy_regd->dfs_region == NL80211_DFS_ETSI)
+		pre_cac_allowed = true;
+
+	rcu_read_unlock();
+
+	return pre_cac_allowed;
+}
+
+void regulatory_propagate_dfs_state(struct wiphy *wiphy,
+				    struct cfg80211_chan_def *chandef,
+				    enum nl80211_dfs_state dfs_state,
+				    enum nl80211_radar_event event)
+{
+	struct cfg80211_registered_device *rdev;
+
+	ASSERT_RTNL();
+
+	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
+		return;
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (wiphy == &rdev->wiphy)
+			continue;
+
+		if (!reg_dfs_domain_same(wiphy, &rdev->wiphy))
+			continue;
+
+		if (!ieee80211_get_channel(&rdev->wiphy,
+					   chandef->chan->center_freq))
+			continue;
+
+		cfg80211_set_dfs_state(&rdev->wiphy, chandef, dfs_state);
+
+		if (event == NL80211_RADAR_DETECTED ||
+		    event == NL80211_RADAR_CAC_FINISHED)
+			cfg80211_sched_dfs_chan_update(rdev);
+
+		nl80211_radar_notify(rdev, chandef, event, NULL, GFP_KERNEL);
+	}
+}
+
 int __init regulatory_init(void)
 {
 	int err = 0;
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index f6ced316b5a4..ca7fedf2e7a1 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -143,4 +143,40 @@ int cfg80211_get_unii(int freq);
  */
 bool regulatory_indoor_allowed(void);
 
+/*
+ * Grace period to timeout pre-CAC results on the dfs channels. This timeout
+ * value is used for Non-ETSI domain.
+ * TODO: May be make this timeout available through regdb?
+ */
+#define REG_PRE_CAC_EXPIRY_GRACE_MS 2000
+
+/**
+ * regulatory_pre_cac_allowed - if pre-CAC allowed in the current dfs domain
+ * @wiphy: wiphy for which pre-CAC capability is checked.
+
+ * Pre-CAC is allowed only in ETSI domain.
+ */
+bool regulatory_pre_cac_allowed(struct wiphy *wiphy);
+
+/**
+ * regulatory_propagate_dfs_state - Propagate DFS channel state to other wiphys
+ * @wiphy - wiphy on which radar is detected and the event will be propagated
+ *	to other available wiphys having the same DFS domain
+ * @chandef - Channel definition of radar detected channel
+ * @dfs_state - DFS channel state to be set
+ * @event - Type of radar event which triggered this DFS state change
+ *
+ * This function should be called with rtnl lock held.
+ */
+void regulatory_propagate_dfs_state(struct wiphy *wiphy,
+				    struct cfg80211_chan_def *chandef,
+				    enum nl80211_dfs_state dfs_state,
+				    enum nl80211_radar_event event);
+
+/**
+ * reg_dfs_domain_same - Checks if both wiphy have same DFS domain configured
+ * @wiphy1 - wiphy it's dfs_region to be checked against that of wiphy2
+ * @wiphy2 - wiphy it's dfs_region to be checked against that of wiphy1
+ */
+bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2);
 #endif  /* __NET_WIRELESS_REG_H */
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 21be56b3128e..14d5f0c8c45f 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -300,93 +300,168 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request,
 }
 EXPORT_SYMBOL(cfg80211_scan_done);
 
-void __cfg80211_sched_scan_results(struct work_struct *wk)
+void cfg80211_add_sched_scan_req(struct cfg80211_registered_device *rdev,
+				 struct cfg80211_sched_scan_request *req)
 {
-	struct cfg80211_registered_device *rdev;
-	struct cfg80211_sched_scan_request *request;
+	ASSERT_RTNL();
 
-	rdev = container_of(wk, struct cfg80211_registered_device,
-			    sched_scan_results_wk);
+	list_add_rcu(&req->list, &rdev->sched_scan_req_list);
+}
 
-	rtnl_lock();
+static void cfg80211_del_sched_scan_req(struct cfg80211_registered_device *rdev,
+					struct cfg80211_sched_scan_request *req)
+{
+	ASSERT_RTNL();
 
-	request = rtnl_dereference(rdev->sched_scan_req);
+	list_del_rcu(&req->list);
+	kfree_rcu(req, rcu_head);
+}
 
-	/* we don't have sched_scan_req anymore if the scan is stopping */
-	if (request) {
-		if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
-			/* flush entries from previous scans */
-			spin_lock_bh(&rdev->bss_lock);
-			__cfg80211_bss_expire(rdev, request->scan_start);
-			spin_unlock_bh(&rdev->bss_lock);
-			request->scan_start = jiffies;
-		}
-		nl80211_send_sched_scan(rdev, request->dev,
-					NL80211_CMD_SCHED_SCAN_RESULTS);
+static struct cfg80211_sched_scan_request *
+cfg80211_find_sched_scan_req(struct cfg80211_registered_device *rdev, u64 reqid)
+{
+	struct cfg80211_sched_scan_request *pos;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(pos, &rdev->sched_scan_req_list, list) {
+		if (pos->reqid == reqid)
+			return pos;
 	}
+	return NULL;
+}
+
+/*
+ * Determines if a scheduled scan request can be handled. When a legacy
+ * scheduled scan is running no other scheduled scan is allowed regardless
+ * whether the request is for legacy or multi-support scan. When a multi-support
+ * scheduled scan is running a request for legacy scan is not allowed. In this
+ * case a request for multi-support scan can be handled if resources are
+ * available, ie. struct wiphy::max_sched_scan_reqs limit is not yet reached.
+ */
+int cfg80211_sched_scan_req_possible(struct cfg80211_registered_device *rdev,
+				     bool want_multi)
+{
+	struct cfg80211_sched_scan_request *pos;
+	int i = 0;
+
+	list_for_each_entry(pos, &rdev->sched_scan_req_list, list) {
+		/* request id zero means legacy in progress */
+		if (!i && !pos->reqid)
+			return -EINPROGRESS;
+		i++;
+	}
+
+	if (i) {
+		/* no legacy allowed when multi request(s) are active */
+		if (!want_multi)
+			return -EINPROGRESS;
+
+		/* resource limit reached */
+		if (i == rdev->wiphy.max_sched_scan_reqs)
+			return -ENOSPC;
+	}
+	return 0;
+}
+
+void cfg80211_sched_scan_results_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+	struct cfg80211_sched_scan_request *req, *tmp;
 
+	rdev = container_of(work, struct cfg80211_registered_device,
+			   sched_scan_res_wk);
+
+	rtnl_lock();
+	list_for_each_entry_safe(req, tmp, &rdev->sched_scan_req_list, list) {
+		if (req->report_results) {
+			req->report_results = false;
+			if (req->flags & NL80211_SCAN_FLAG_FLUSH) {
+				/* flush entries from previous scans */
+				spin_lock_bh(&rdev->bss_lock);
+				__cfg80211_bss_expire(rdev, req->scan_start);
+				spin_unlock_bh(&rdev->bss_lock);
+				req->scan_start = jiffies;
+			}
+			nl80211_send_sched_scan(req,
+						NL80211_CMD_SCHED_SCAN_RESULTS);
+		}
+	}
 	rtnl_unlock();
 }
 
-void cfg80211_sched_scan_results(struct wiphy *wiphy)
+void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid)
 {
-	trace_cfg80211_sched_scan_results(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	struct cfg80211_sched_scan_request *request;
+
+	trace_cfg80211_sched_scan_results(wiphy, reqid);
 	/* ignore if we're not scanning */
 
-	if (rcu_access_pointer(wiphy_to_rdev(wiphy)->sched_scan_req))
-		queue_work(cfg80211_wq,
-			   &wiphy_to_rdev(wiphy)->sched_scan_results_wk);
+	rtnl_lock();
+	request = cfg80211_find_sched_scan_req(rdev, reqid);
+	if (request) {
+		request->report_results = true;
+		queue_work(cfg80211_wq, &rdev->sched_scan_res_wk);
+	}
+	rtnl_unlock();
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_results);
 
-void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy, u64 reqid)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	ASSERT_RTNL();
 
-	trace_cfg80211_sched_scan_stopped(wiphy);
+	trace_cfg80211_sched_scan_stopped(wiphy, reqid);
 
-	__cfg80211_stop_sched_scan(rdev, true);
+	__cfg80211_stop_sched_scan(rdev, reqid, true);
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl);
 
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid)
 {
 	rtnl_lock();
-	cfg80211_sched_scan_stopped_rtnl(wiphy);
+	cfg80211_sched_scan_stopped_rtnl(wiphy, reqid);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
 
-int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
-			       bool driver_initiated)
+int cfg80211_stop_sched_scan_req(struct cfg80211_registered_device *rdev,
+				 struct cfg80211_sched_scan_request *req,
+				 bool driver_initiated)
 {
-	struct cfg80211_sched_scan_request *sched_scan_req;
-	struct net_device *dev;
-
 	ASSERT_RTNL();
 
-	if (!rdev->sched_scan_req)
-		return -ENOENT;
-
-	sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
-	dev = sched_scan_req->dev;
-
 	if (!driver_initiated) {
-		int err = rdev_sched_scan_stop(rdev, dev);
+		int err = rdev_sched_scan_stop(rdev, req->dev, req->reqid);
 		if (err)
 			return err;
 	}
 
-	nl80211_send_sched_scan(rdev, dev, NL80211_CMD_SCHED_SCAN_STOPPED);
+	nl80211_send_sched_scan(req, NL80211_CMD_SCHED_SCAN_STOPPED);
 
-	RCU_INIT_POINTER(rdev->sched_scan_req, NULL);
-	kfree_rcu(sched_scan_req, rcu_head);
+	cfg80211_del_sched_scan_req(rdev, req);
 
 	return 0;
 }
 
+int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
+			       u64 reqid, bool driver_initiated)
+{
+	struct cfg80211_sched_scan_request *sched_scan_req;
+
+	ASSERT_RTNL();
+
+	sched_scan_req = cfg80211_find_sched_scan_req(rdev, reqid);
+	if (!sched_scan_req)
+		return -ENOENT;
+
+	return cfg80211_stop_sched_scan_req(rdev, sched_scan_req,
+					    driver_initiated);
+}
+
 void cfg80211_bss_age(struct cfg80211_registered_device *rdev,
                       unsigned long age_secs)
 {
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index b347e63d7aaa..532a0007ce82 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -5,6 +5,7 @@
  *
  * Copyright 2009	Johannes Berg <johannes@sipsolutions.net>
  * Copyright (C) 2009   Intel Corporation. All rights reserved.
+ * Copyright 2017	Intel Deutschland GmbH
  */
 
 #include <linux/etherdevice.h>
@@ -253,10 +254,13 @@ void cfg80211_conn_work(struct work_struct *work)
 		}
 		treason = NL80211_TIMEOUT_UNSPECIFIED;
 		if (cfg80211_conn_do_work(wdev, &treason)) {
-			__cfg80211_connect_result(
-					wdev->netdev, bssid,
-					NULL, 0, NULL, 0, -1, false, NULL,
-					treason);
+			struct cfg80211_connect_resp_params cr;
+
+			memset(&cr, 0, sizeof(cr));
+			cr.status = -1;
+			cr.bssid = bssid;
+			cr.timeout_reason = treason;
+			__cfg80211_connect_result(wdev->netdev, &cr, false);
 		}
 		wdev_unlock(wdev);
 	}
@@ -359,10 +363,13 @@ void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len)
 		wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT;
 		schedule_work(&rdev->conn_work);
 	} else if (status_code != WLAN_STATUS_SUCCESS) {
-		__cfg80211_connect_result(wdev->netdev, mgmt->bssid,
-					  NULL, 0, NULL, 0,
-					  status_code, false, NULL,
-					  NL80211_TIMEOUT_UNSPECIFIED);
+		struct cfg80211_connect_resp_params cr;
+
+		memset(&cr, 0, sizeof(cr));
+		cr.status = status_code;
+		cr.bssid = mgmt->bssid;
+		cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED;
+		__cfg80211_connect_result(wdev->netdev, &cr, false);
 	} else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) {
 		wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT;
 		schedule_work(&rdev->conn_work);
@@ -669,12 +676,9 @@ static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work);
  */
 
 /* This method must consume bss one way or another */
-void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
-			       const u8 *req_ie, size_t req_ie_len,
-			       const u8 *resp_ie, size_t resp_ie_len,
-			       int status, bool wextev,
-			       struct cfg80211_bss *bss,
-			       enum nl80211_timeout_reason timeout_reason)
+void __cfg80211_connect_result(struct net_device *dev,
+			       struct cfg80211_connect_resp_params *cr,
+			       bool wextev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	const u8 *country_ie;
@@ -686,48 +690,48 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 
 	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION &&
 		    wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) {
-		cfg80211_put_bss(wdev->wiphy, bss);
+		cfg80211_put_bss(wdev->wiphy, cr->bss);
 		return;
 	}
 
-	nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev,
-				    bssid, req_ie, req_ie_len,
-				    resp_ie, resp_ie_len,
-				    status, timeout_reason, GFP_KERNEL);
+	nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr,
+				    GFP_KERNEL);
 
 #ifdef CONFIG_CFG80211_WEXT
 	if (wextev) {
-		if (req_ie && status == WLAN_STATUS_SUCCESS) {
+		if (cr->req_ie && cr->status == WLAN_STATUS_SUCCESS) {
 			memset(&wrqu, 0, sizeof(wrqu));
-			wrqu.data.length = req_ie_len;
-			wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, req_ie);
+			wrqu.data.length = cr->req_ie_len;
+			wireless_send_event(dev, IWEVASSOCREQIE, &wrqu,
+					    cr->req_ie);
 		}
 
-		if (resp_ie && status == WLAN_STATUS_SUCCESS) {
+		if (cr->resp_ie && cr->status == WLAN_STATUS_SUCCESS) {
 			memset(&wrqu, 0, sizeof(wrqu));
-			wrqu.data.length = resp_ie_len;
-			wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, resp_ie);
+			wrqu.data.length = cr->resp_ie_len;
+			wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu,
+					    cr->resp_ie);
 		}
 
 		memset(&wrqu, 0, sizeof(wrqu));
 		wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-		if (bssid && status == WLAN_STATUS_SUCCESS) {
-			memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN);
-			memcpy(wdev->wext.prev_bssid, bssid, ETH_ALEN);
+		if (cr->bssid && cr->status == WLAN_STATUS_SUCCESS) {
+			memcpy(wrqu.ap_addr.sa_data, cr->bssid, ETH_ALEN);
+			memcpy(wdev->wext.prev_bssid, cr->bssid, ETH_ALEN);
 			wdev->wext.prev_bssid_valid = true;
 		}
 		wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL);
 	}
 #endif
 
-	if (!bss && (status == WLAN_STATUS_SUCCESS)) {
+	if (!cr->bss && (cr->status == WLAN_STATUS_SUCCESS)) {
 		WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect);
-		bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
-				       wdev->ssid, wdev->ssid_len,
-				       wdev->conn_bss_type,
-				       IEEE80211_PRIVACY_ANY);
-		if (bss)
-			cfg80211_hold_bss(bss_from_pub(bss));
+		cr->bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->bssid,
+					   wdev->ssid, wdev->ssid_len,
+					   wdev->conn_bss_type,
+					   IEEE80211_PRIVACY_ANY);
+		if (cr->bss)
+			cfg80211_hold_bss(bss_from_pub(cr->bss));
 	}
 
 	if (wdev->current_bss) {
@@ -736,29 +740,29 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 		wdev->current_bss = NULL;
 	}
 
-	if (status != WLAN_STATUS_SUCCESS) {
+	if (cr->status != WLAN_STATUS_SUCCESS) {
 		kzfree(wdev->connect_keys);
 		wdev->connect_keys = NULL;
 		wdev->ssid_len = 0;
 		wdev->conn_owner_nlportid = 0;
-		if (bss) {
-			cfg80211_unhold_bss(bss_from_pub(bss));
-			cfg80211_put_bss(wdev->wiphy, bss);
+		if (cr->bss) {
+			cfg80211_unhold_bss(bss_from_pub(cr->bss));
+			cfg80211_put_bss(wdev->wiphy, cr->bss);
 		}
 		cfg80211_sme_free(wdev);
 		return;
 	}
 
-	if (WARN_ON(!bss))
+	if (WARN_ON(!cr->bss))
 		return;
 
-	wdev->current_bss = bss_from_pub(bss);
+	wdev->current_bss = bss_from_pub(cr->bss);
 
 	if (!(wdev->wiphy->flags & WIPHY_FLAG_HAS_STATIC_WEP))
 		cfg80211_upload_connect_keys(wdev);
 
 	rcu_read_lock();
-	country_ie = ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY);
+	country_ie = ieee80211_bss_get_ie(cr->bss, WLAN_EID_COUNTRY);
 	if (!country_ie) {
 		rcu_read_unlock();
 		return;
@@ -775,70 +779,99 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 	 * - country_ie + 2, the start of the country ie data, and
 	 * - and country_ie[1] which is the IE length
 	 */
-	regulatory_hint_country_ie(wdev->wiphy, bss->channel->band,
+	regulatory_hint_country_ie(wdev->wiphy, cr->bss->channel->band,
 				   country_ie + 2, country_ie[1]);
 	kfree(country_ie);
 }
 
 /* Consumes bss object one way or another */
-void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
-			  struct cfg80211_bss *bss, const u8 *req_ie,
-			  size_t req_ie_len, const u8 *resp_ie,
-			  size_t resp_ie_len, int status, gfp_t gfp,
-			  enum nl80211_timeout_reason timeout_reason)
+void cfg80211_connect_done(struct net_device *dev,
+			   struct cfg80211_connect_resp_params *params,
+			   gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
+	u8 *next;
 
-	if (bss) {
+	if (params->bss) {
 		/* Make sure the bss entry provided by the driver is valid. */
-		struct cfg80211_internal_bss *ibss = bss_from_pub(bss);
+		struct cfg80211_internal_bss *ibss = bss_from_pub(params->bss);
 
 		if (WARN_ON(list_empty(&ibss->list))) {
-			cfg80211_put_bss(wdev->wiphy, bss);
+			cfg80211_put_bss(wdev->wiphy, params->bss);
 			return;
 		}
 	}
 
-	ev = kzalloc(sizeof(*ev) + req_ie_len + resp_ie_len, gfp);
+	ev = kzalloc(sizeof(*ev) + (params->bssid ? ETH_ALEN : 0) +
+		     params->req_ie_len + params->resp_ie_len +
+		     params->fils_kek_len + params->pmk_len +
+		     (params->pmkid ? WLAN_PMKID_LEN : 0), gfp);
 	if (!ev) {
-		cfg80211_put_bss(wdev->wiphy, bss);
+		cfg80211_put_bss(wdev->wiphy, params->bss);
 		return;
 	}
 
 	ev->type = EVENT_CONNECT_RESULT;
-	if (bssid)
-		memcpy(ev->cr.bssid, bssid, ETH_ALEN);
-	if (req_ie_len) {
-		ev->cr.req_ie = ((u8 *)ev) + sizeof(*ev);
-		ev->cr.req_ie_len = req_ie_len;
-		memcpy((void *)ev->cr.req_ie, req_ie, req_ie_len);
+	next = ((u8 *)ev) + sizeof(*ev);
+	if (params->bssid) {
+		ev->cr.bssid = next;
+		memcpy((void *)ev->cr.bssid, params->bssid, ETH_ALEN);
+		next += ETH_ALEN;
 	}
-	if (resp_ie_len) {
-		ev->cr.resp_ie = ((u8 *)ev) + sizeof(*ev) + req_ie_len;
-		ev->cr.resp_ie_len = resp_ie_len;
-		memcpy((void *)ev->cr.resp_ie, resp_ie, resp_ie_len);
+	if (params->req_ie_len) {
+		ev->cr.req_ie = next;
+		ev->cr.req_ie_len = params->req_ie_len;
+		memcpy((void *)ev->cr.req_ie, params->req_ie,
+		       params->req_ie_len);
+		next += params->req_ie_len;
 	}
-	if (bss)
-		cfg80211_hold_bss(bss_from_pub(bss));
-	ev->cr.bss = bss;
-	ev->cr.status = status;
-	ev->cr.timeout_reason = timeout_reason;
+	if (params->resp_ie_len) {
+		ev->cr.resp_ie = next;
+		ev->cr.resp_ie_len = params->resp_ie_len;
+		memcpy((void *)ev->cr.resp_ie, params->resp_ie,
+		       params->resp_ie_len);
+		next += params->resp_ie_len;
+	}
+	if (params->fils_kek_len) {
+		ev->cr.fils_kek = next;
+		ev->cr.fils_kek_len = params->fils_kek_len;
+		memcpy((void *)ev->cr.fils_kek, params->fils_kek,
+		       params->fils_kek_len);
+		next += params->fils_kek_len;
+	}
+	if (params->pmk_len) {
+		ev->cr.pmk = next;
+		ev->cr.pmk_len = params->pmk_len;
+		memcpy((void *)ev->cr.pmk, params->pmk, params->pmk_len);
+		next += params->pmk_len;
+	}
+	if (params->pmkid) {
+		ev->cr.pmkid = next;
+		memcpy((void *)ev->cr.pmkid, params->pmkid, WLAN_PMKID_LEN);
+		next += WLAN_PMKID_LEN;
+	}
+	ev->cr.update_erp_next_seq_num = params->update_erp_next_seq_num;
+	if (params->update_erp_next_seq_num)
+		ev->cr.fils_erp_next_seq_num = params->fils_erp_next_seq_num;
+	if (params->bss)
+		cfg80211_hold_bss(bss_from_pub(params->bss));
+	ev->cr.bss = params->bss;
+	ev->cr.status = params->status;
+	ev->cr.timeout_reason = params->timeout_reason;
 
 	spin_lock_irqsave(&wdev->event_lock, flags);
 	list_add_tail(&ev->list, &wdev->event_list);
 	spin_unlock_irqrestore(&wdev->event_lock, flags);
 	queue_work(cfg80211_wq, &rdev->event_work);
 }
-EXPORT_SYMBOL(cfg80211_connect_bss);
+EXPORT_SYMBOL(cfg80211_connect_done);
 
 /* Consumes bss object one way or another */
 void __cfg80211_roamed(struct wireless_dev *wdev,
-		       struct cfg80211_bss *bss,
-		       const u8 *req_ie, size_t req_ie_len,
-		       const u8 *resp_ie, size_t resp_ie_len)
+		       struct cfg80211_roam_info *info)
 {
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
@@ -856,97 +889,84 @@ void __cfg80211_roamed(struct wireless_dev *wdev,
 	cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub);
 	wdev->current_bss = NULL;
 
-	cfg80211_hold_bss(bss_from_pub(bss));
-	wdev->current_bss = bss_from_pub(bss);
+	if (WARN_ON(!info->bss))
+		return;
+
+	cfg80211_hold_bss(bss_from_pub(info->bss));
+	wdev->current_bss = bss_from_pub(info->bss);
 
 	nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy),
-			    wdev->netdev, bss->bssid,
-			    req_ie, req_ie_len, resp_ie, resp_ie_len,
-			    GFP_KERNEL);
+			    wdev->netdev, info, GFP_KERNEL);
 
 #ifdef CONFIG_CFG80211_WEXT
-	if (req_ie) {
+	if (info->req_ie) {
 		memset(&wrqu, 0, sizeof(wrqu));
-		wrqu.data.length = req_ie_len;
+		wrqu.data.length = info->req_ie_len;
 		wireless_send_event(wdev->netdev, IWEVASSOCREQIE,
-				    &wrqu, req_ie);
+				    &wrqu, info->req_ie);
 	}
 
-	if (resp_ie) {
+	if (info->resp_ie) {
 		memset(&wrqu, 0, sizeof(wrqu));
-		wrqu.data.length = resp_ie_len;
+		wrqu.data.length = info->resp_ie_len;
 		wireless_send_event(wdev->netdev, IWEVASSOCRESPIE,
-				    &wrqu, resp_ie);
+				    &wrqu, info->resp_ie);
 	}
 
 	memset(&wrqu, 0, sizeof(wrqu));
 	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-	memcpy(wrqu.ap_addr.sa_data, bss->bssid, ETH_ALEN);
-	memcpy(wdev->wext.prev_bssid, bss->bssid, ETH_ALEN);
+	memcpy(wrqu.ap_addr.sa_data, info->bss->bssid, ETH_ALEN);
+	memcpy(wdev->wext.prev_bssid, info->bss->bssid, ETH_ALEN);
 	wdev->wext.prev_bssid_valid = true;
 	wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL);
 #endif
 
 	return;
 out:
-	cfg80211_put_bss(wdev->wiphy, bss);
-}
-
-void cfg80211_roamed(struct net_device *dev,
-		     struct ieee80211_channel *channel,
-		     const u8 *bssid,
-		     const u8 *req_ie, size_t req_ie_len,
-		     const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp)
-{
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_bss *bss;
-
-	bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, wdev->ssid,
-			       wdev->ssid_len,
-			       wdev->conn_bss_type, IEEE80211_PRIVACY_ANY);
-	if (WARN_ON(!bss))
-		return;
-
-	cfg80211_roamed_bss(dev, bss, req_ie, req_ie_len, resp_ie,
-			    resp_ie_len, gfp);
+	cfg80211_put_bss(wdev->wiphy, info->bss);
 }
-EXPORT_SYMBOL(cfg80211_roamed);
 
-/* Consumes bss object one way or another */
-void cfg80211_roamed_bss(struct net_device *dev,
-			 struct cfg80211_bss *bss, const u8 *req_ie,
-			 size_t req_ie_len, const u8 *resp_ie,
-			 size_t resp_ie_len, gfp_t gfp)
+/* Consumes info->bss object one way or another */
+void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
+		     gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
-	if (WARN_ON(!bss))
+	if (!info->bss) {
+		info->bss = cfg80211_get_bss(wdev->wiphy, info->channel,
+					     info->bssid, wdev->ssid,
+					     wdev->ssid_len,
+					     wdev->conn_bss_type,
+					     IEEE80211_PRIVACY_ANY);
+	}
+
+	if (WARN_ON(!info->bss))
 		return;
 
-	ev = kzalloc(sizeof(*ev) + req_ie_len + resp_ie_len, gfp);
+	ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len, gfp);
 	if (!ev) {
-		cfg80211_put_bss(wdev->wiphy, bss);
+		cfg80211_put_bss(wdev->wiphy, info->bss);
 		return;
 	}
 
 	ev->type = EVENT_ROAMED;
 	ev->rm.req_ie = ((u8 *)ev) + sizeof(*ev);
-	ev->rm.req_ie_len = req_ie_len;
-	memcpy((void *)ev->rm.req_ie, req_ie, req_ie_len);
-	ev->rm.resp_ie = ((u8 *)ev) + sizeof(*ev) + req_ie_len;
-	ev->rm.resp_ie_len = resp_ie_len;
-	memcpy((void *)ev->rm.resp_ie, resp_ie, resp_ie_len);
-	ev->rm.bss = bss;
+	ev->rm.req_ie_len = info->req_ie_len;
+	memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len);
+	ev->rm.resp_ie = ((u8 *)ev) + sizeof(*ev) + info->req_ie_len;
+	ev->rm.resp_ie_len = info->resp_ie_len;
+	memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len);
+	ev->rm.bss = info->bss;
 
 	spin_lock_irqsave(&wdev->event_lock, flags);
 	list_add_tail(&ev->list, &wdev->event_list);
 	spin_unlock_irqrestore(&wdev->event_lock, flags);
 	queue_work(cfg80211_wq, &rdev->event_work);
 }
-EXPORT_SYMBOL(cfg80211_roamed_bss);
+EXPORT_SYMBOL(cfg80211_roamed);
 
 void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap)
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 16b6b5988be9..570a2b67ca10 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -132,12 +132,10 @@ static int wiphy_resume(struct device *dev)
 	/* Age scan results with time spent in suspend */
 	cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at);
 
-	if (rdev->ops->resume) {
-		rtnl_lock();
-		if (rdev->wiphy.registered)
-			ret = rdev_resume(rdev);
-		rtnl_unlock();
-	}
+	rtnl_lock();
+	if (rdev->wiphy.registered && rdev->ops->resume)
+		ret = rdev_resume(rdev);
+	rtnl_unlock();
 
 	return ret;
 }
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 776e80cef9b4..ca8b2059f92c 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -576,11 +576,6 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_stop_ap,
 	TP_ARGS(wiphy, netdev)
 );
 
-DEFINE_EVENT(wiphy_netdev_evt, rdev_sched_scan_stop,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
-	TP_ARGS(wiphy, netdev)
-);
-
 DEFINE_EVENT(wiphy_netdev_evt, rdev_set_rekey_data,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
 	TP_ARGS(wiphy, netdev)
@@ -1322,6 +1317,28 @@ TRACE_EVENT(rdev_set_cqm_rssi_config,
 		 __entry->rssi_thold, __entry->rssi_hyst)
 );
 
+TRACE_EVENT(rdev_set_cqm_rssi_range_config,
+	TP_PROTO(struct wiphy *wiphy,
+		 struct net_device *netdev, s32 low, s32 high),
+	TP_ARGS(wiphy, netdev, low, high),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		__field(s32, rssi_low)
+		__field(s32, rssi_high)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		__entry->rssi_low = low;
+		__entry->rssi_high = high;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT
+		  ", range: %d - %d ",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG,
+		  __entry->rssi_low, __entry->rssi_high)
+);
+
 TRACE_EVENT(rdev_set_cqm_txe_config,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u32 rate,
 		 u32 pkts, u32 intvl),
@@ -1588,20 +1605,31 @@ DEFINE_EVENT(tx_rx_evt, rdev_set_antenna,
 	TP_ARGS(wiphy, rx, tx)
 );
 
-TRACE_EVENT(rdev_sched_scan_start,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
-		 struct cfg80211_sched_scan_request *request),
-	TP_ARGS(wiphy, netdev, request),
+DECLARE_EVENT_CLASS(wiphy_netdev_id_evt,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u64 id),
+	TP_ARGS(wiphy, netdev, id),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
+		__field(u64, id)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
+		__entry->id = id;
 	),
-	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
-		  WIPHY_PR_ARG, NETDEV_PR_ARG)
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", id: %llu",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->id)
+);
+
+DEFINE_EVENT(wiphy_netdev_id_evt, rdev_sched_scan_start,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u64 id),
+	TP_ARGS(wiphy, netdev, id)
+);
+
+DEFINE_EVENT(wiphy_netdev_id_evt, rdev_sched_scan_stop,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u64 id),
+	TP_ARGS(wiphy, netdev, id)
 );
 
 TRACE_EVENT(rdev_tdls_mgmt,
@@ -2792,14 +2820,28 @@ TRACE_EVENT(cfg80211_scan_done,
 		  MAC_PR_ARG(tsf_bssid))
 );
 
-DEFINE_EVENT(wiphy_only_evt, cfg80211_sched_scan_results,
-	TP_PROTO(struct wiphy *wiphy),
-	TP_ARGS(wiphy)
+DECLARE_EVENT_CLASS(wiphy_id_evt,
+	TP_PROTO(struct wiphy *wiphy, u64 id),
+	TP_ARGS(wiphy, id),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		__field(u64, id)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		__entry->id = id;
+	),
+	TP_printk(WIPHY_PR_FMT ", id: %llu", WIPHY_PR_ARG, __entry->id)
 );
 
-DEFINE_EVENT(wiphy_only_evt, cfg80211_sched_scan_stopped,
-	TP_PROTO(struct wiphy *wiphy),
-	TP_ARGS(wiphy)
+DEFINE_EVENT(wiphy_id_evt, cfg80211_sched_scan_stopped,
+	TP_PROTO(struct wiphy *wiphy, u64 id),
+	TP_ARGS(wiphy, id)
+);
+
+DEFINE_EVENT(wiphy_id_evt, cfg80211_sched_scan_results,
+	TP_PROTO(struct wiphy *wiphy, u64 id),
+	TP_ARGS(wiphy, id)
 );
 
 TRACE_EVENT(cfg80211_get_bss,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 68e5f2ecee1a..7198373e2920 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -659,7 +659,7 @@ __ieee80211_amsdu_copy_frag(struct sk_buff *skb, struct sk_buff *frame,
 			    int offset, int len)
 {
 	struct skb_shared_info *sh = skb_shinfo(skb);
-	const skb_frag_t *frag = &sh->frags[-1];
+	const skb_frag_t *frag = &sh->frags[0];
 	struct page *frag_page;
 	void *frag_ptr;
 	int frag_len, frag_size;
@@ -672,10 +672,10 @@ __ieee80211_amsdu_copy_frag(struct sk_buff *skb, struct sk_buff *frame,
 
 	while (offset >= frag_size) {
 		offset -= frag_size;
-		frag++;
 		frag_page = skb_frag_page(frag);
 		frag_ptr = skb_frag_address(frag);
 		frag_size = skb_frag_size(frag);
+		frag++;
 	}
 
 	frag_ptr += offset;
@@ -687,12 +687,12 @@ __ieee80211_amsdu_copy_frag(struct sk_buff *skb, struct sk_buff *frame,
 	len -= cur_len;
 
 	while (len > 0) {
-		frag++;
 		frag_len = skb_frag_size(frag);
 		cur_len = min(len, frag_len);
 		__frame_add_frag(frame, skb_frag_page(frag),
 				 skb_frag_address(frag), cur_len, frag_len);
 		len -= cur_len;
+		frag++;
 	}
 }
 
@@ -914,11 +914,11 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev)
 			netdev_err(dev, "failed to set key %d\n", i);
 			continue;
 		}
-		if (wdev->connect_keys->def == i)
-			if (rdev_set_default_key(rdev, dev, i, true, true)) {
-				netdev_err(dev, "failed to set defkey %d\n", i);
-				continue;
-			}
+		if (wdev->connect_keys->def == i &&
+		    rdev_set_default_key(rdev, dev, i, true, true)) {
+			netdev_err(dev, "failed to set defkey %d\n", i);
+			continue;
+		}
 	}
 
 	kzfree(wdev->connect_keys);
@@ -929,7 +929,6 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 {
 	struct cfg80211_event *ev;
 	unsigned long flags;
-	const u8 *bssid = NULL;
 
 	spin_lock_irqsave(&wdev->event_lock, flags);
 	while (!list_empty(&wdev->event_list)) {
@@ -941,20 +940,13 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 		wdev_lock(wdev);
 		switch (ev->type) {
 		case EVENT_CONNECT_RESULT:
-			if (!is_zero_ether_addr(ev->cr.bssid))
-				bssid = ev->cr.bssid;
 			__cfg80211_connect_result(
-				wdev->netdev, bssid,
-				ev->cr.req_ie, ev->cr.req_ie_len,
-				ev->cr.resp_ie, ev->cr.resp_ie_len,
-				ev->cr.status,
-				ev->cr.status == WLAN_STATUS_SUCCESS,
-				ev->cr.bss, ev->cr.timeout_reason);
+				wdev->netdev,
+				&ev->cr,
+				ev->cr.status == WLAN_STATUS_SUCCESS);
 			break;
 		case EVENT_ROAMED:
-			__cfg80211_roamed(wdev, ev->rm.bss, ev->rm.req_ie,
-					  ev->rm.req_ie_len, ev->rm.resp_ie,
-					  ev->rm.resp_ie_len);
+			__cfg80211_roamed(wdev, &ev->rm);
 			break;
 		case EVENT_DISCONNECTED:
 			__cfg80211_disconnected(wdev->netdev,
@@ -991,7 +983,7 @@ void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev)
 
 int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 			  struct net_device *dev, enum nl80211_iftype ntype,
-			  u32 *flags, struct vif_params *params)
+			  struct vif_params *params)
 {
 	int err;
 	enum nl80211_iftype otype = dev->ieee80211_ptr->iftype;
@@ -1049,7 +1041,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 		cfg80211_process_rdev_events(rdev);
 	}
 
-	err = rdev_change_virtual_intf(rdev, dev, ntype, flags, params);
+	err = rdev_change_virtual_intf(rdev, dev, ntype, params);
 
 	WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype);
 
@@ -1097,6 +1089,35 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 	return err;
 }
 
+static u32 cfg80211_calculate_bitrate_ht(struct rate_info *rate)
+{
+	int modulation, streams, bitrate;
+
+	/* the formula below does only work for MCS values smaller than 32 */
+	if (WARN_ON_ONCE(rate->mcs >= 32))
+		return 0;
+
+	modulation = rate->mcs & 7;
+	streams = (rate->mcs >> 3) + 1;
+
+	bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000;
+
+	if (modulation < 4)
+		bitrate *= (modulation + 1);
+	else if (modulation == 4)
+		bitrate *= (modulation + 2);
+	else
+		bitrate *= (modulation + 3);
+
+	bitrate *= streams;
+
+	if (rate->flags & RATE_INFO_FLAGS_SHORT_GI)
+		bitrate = (bitrate / 9) * 10;
+
+	/* do NOT round down here */
+	return (bitrate + 50000) / 100000;
+}
+
 static u32 cfg80211_calculate_bitrate_60g(struct rate_info *rate)
 {
 	static const u32 __mcs2bitrate[] = {
@@ -1230,39 +1251,14 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 
 u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 {
-	int modulation, streams, bitrate;
-
-	if (!(rate->flags & RATE_INFO_FLAGS_MCS) &&
-	    !(rate->flags & RATE_INFO_FLAGS_VHT_MCS))
-		return rate->legacy;
+	if (rate->flags & RATE_INFO_FLAGS_MCS)
+		return cfg80211_calculate_bitrate_ht(rate);
 	if (rate->flags & RATE_INFO_FLAGS_60G)
 		return cfg80211_calculate_bitrate_60g(rate);
 	if (rate->flags & RATE_INFO_FLAGS_VHT_MCS)
 		return cfg80211_calculate_bitrate_vht(rate);
 
-	/* the formula below does only work for MCS values smaller than 32 */
-	if (WARN_ON_ONCE(rate->mcs >= 32))
-		return 0;
-
-	modulation = rate->mcs & 7;
-	streams = (rate->mcs >> 3) + 1;
-
-	bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000;
-
-	if (modulation < 4)
-		bitrate *= (modulation + 1);
-	else if (modulation == 4)
-		bitrate *= (modulation + 2);
-	else
-		bitrate *= (modulation + 3);
-
-	bitrate *= streams;
-
-	if (rate->flags & RATE_INFO_FLAGS_SHORT_GI)
-		bitrate = (bitrate / 9) * 10;
-
-	/* do NOT round down here */
-	return (bitrate + 50000) / 100000;
+	return rate->legacy;
 }
 EXPORT_SYMBOL(cfg80211_calculate_bitrate);
 
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index a220156cf217..5d4a02c7979b 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -62,7 +62,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
 
 	memset(&vifparams, 0, sizeof(vifparams));
 
-	return cfg80211_change_iface(rdev, dev, type, NULL, &vifparams);
+	return cfg80211_change_iface(rdev, dev, type, &vifparams);
 }
 EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode);
 
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index fd28a49dbe8f..8b911c29860e 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout)
 	return rc;
 }
 
-static int x25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int x25_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *newsk;
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index c0e961983f17..abf81b329dc1 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -5,6 +5,7 @@
 obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
 		      xfrm_input.o xfrm_output.o \
 		      xfrm_sysctl.o xfrm_replay.o
+obj-$(CONFIG_XFRM_OFFLOAD) += xfrm_device.o
 obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
 obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
new file mode 100644
index 000000000000..8ec8a3fcf8d4
--- /dev/null
+++ b/net/xfrm/xfrm_device.c
@@ -0,0 +1,208 @@
+/*
+ * xfrm_device.c - IPsec device offloading code.
+ *
+ * Copyright (c) 2015 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <net/dst.h>
+#include <net/xfrm.h>
+#include <linux/notifier.h>
+
+int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features)
+{
+	int err;
+	struct xfrm_state *x;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (skb_is_gso(skb))
+		return 0;
+
+	if (xo) {
+		x = skb->sp->xvec[skb->sp->len - 1];
+		if (xo->flags & XFRM_GRO || x->xso.flags & XFRM_OFFLOAD_INBOUND)
+			return 0;
+
+		x->outer_mode->xmit(x, skb);
+
+		err = x->type_offload->xmit(x, skb, features);
+		if (err) {
+			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+			return err;
+		}
+
+		skb_push(skb, skb->data - skb_mac_header(skb));
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(validate_xmit_xfrm);
+
+int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
+		       struct xfrm_user_offload *xuo)
+{
+	int err;
+	struct dst_entry *dst;
+	struct net_device *dev;
+	struct xfrm_state_offload *xso = &x->xso;
+	xfrm_address_t *saddr;
+	xfrm_address_t *daddr;
+
+	if (!x->type_offload)
+		return 0;
+
+	/* We don't yet support UDP encapsulation, TFC padding and ESN. */
+	if (x->encap || x->tfcpad || (x->props.flags & XFRM_STATE_ESN))
+		return 0;
+
+	dev = dev_get_by_index(net, xuo->ifindex);
+	if (!dev) {
+		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
+			saddr = &x->props.saddr;
+			daddr = &x->id.daddr;
+		} else {
+			saddr = &x->id.daddr;
+			daddr = &x->props.saddr;
+		}
+
+		dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, x->props.family);
+		if (IS_ERR(dst))
+			return 0;
+
+		dev = dst->dev;
+
+		dev_hold(dev);
+		dst_release(dst);
+	}
+
+	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) {
+		dev_put(dev);
+		return 0;
+	}
+
+	xso->dev = dev;
+	xso->num_exthdrs = 1;
+	xso->flags = xuo->flags;
+
+	err = dev->xfrmdev_ops->xdo_dev_state_add(x);
+	if (err) {
+		dev_put(dev);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_state_add);
+
+bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
+{
+	int mtu;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+	struct net_device *dev = x->xso.dev;
+
+	if (!x->type_offload || x->encap)
+		return false;
+
+	if ((x->xso.offload_handle && (dev == dst->path->dev)) &&
+	     !dst->child->xfrm && x->type->get_mtu) {
+		mtu = x->type->get_mtu(x, xdst->child_mtu_cached);
+
+		if (skb->len <= mtu)
+			goto ok;
+
+		if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+			goto ok;
+	}
+
+	return false;
+
+ok:
+	if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok)
+		return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok);
+
+int xfrm_dev_register(struct net_device *dev)
+{
+	if ((dev->features & NETIF_F_HW_ESP) && !dev->xfrmdev_ops)
+		return NOTIFY_BAD;
+	if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) &&
+	    !(dev->features & NETIF_F_HW_ESP))
+		return NOTIFY_BAD;
+
+	return NOTIFY_DONE;
+}
+
+static int xfrm_dev_unregister(struct net_device *dev)
+{
+	return NOTIFY_DONE;
+}
+
+static int xfrm_dev_feat_change(struct net_device *dev)
+{
+	if ((dev->features & NETIF_F_HW_ESP) && !dev->xfrmdev_ops)
+		return NOTIFY_BAD;
+	else if (!(dev->features & NETIF_F_HW_ESP))
+		dev->xfrmdev_ops = NULL;
+
+	if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) &&
+	    !(dev->features & NETIF_F_HW_ESP))
+		return NOTIFY_BAD;
+
+	return NOTIFY_DONE;
+}
+
+static int xfrm_dev_down(struct net_device *dev)
+{
+	if (dev->hw_features & NETIF_F_HW_ESP)
+		xfrm_dev_state_flush(dev_net(dev), dev, true);
+
+	xfrm_garbage_collect(dev_net(dev));
+
+	return NOTIFY_DONE;
+}
+
+static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		return xfrm_dev_register(dev);
+
+	case NETDEV_UNREGISTER:
+		return xfrm_dev_unregister(dev);
+
+	case NETDEV_FEAT_CHANGE:
+		return xfrm_dev_feat_change(dev);
+
+	case NETDEV_DOWN:
+		return xfrm_dev_down(dev);
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block xfrm_dev_notifier = {
+	.notifier_call	= xfrm_dev_event,
+};
+
+void __net_init xfrm_dev_init(void)
+{
+	register_netdevice_notifier(&xfrm_dev_notifier);
+}
diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h
index 666c5ffe929d..eaea9c4fb3b0 100644
--- a/net/xfrm/xfrm_hash.h
+++ b/net/xfrm/xfrm_hash.h
@@ -54,8 +54,8 @@ static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr,
 static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr,
 					     __u8 prefixlen)
 {
-	int pdw;
-	int pbi;
+	unsigned int pdw;
+	unsigned int pbi;
 	u32 initval = 0;
 
 	pdw = prefixlen >> 5;     /* num of whole u32 in prefix */
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 46bdb4fbed0b..9de4b1dbc0ae 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -107,6 +107,8 @@ struct sec_path *secpath_dup(struct sec_path *src)
 	sp->len = 0;
 	sp->olen = 0;
 
+	memset(sp->ovec, 0, sizeof(sp->ovec[XFRM_MAX_OFFLOAD_DEPTH]));
+
 	if (src) {
 		int i;
 
@@ -207,8 +209,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	unsigned int family;
 	int decaps = 0;
 	int async = 0;
-	struct xfrm_offload *xo;
 	bool xfrm_gro = false;
+	bool crypto_done = false;
+	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	if (encap_type < 0) {
 		x = xfrm_input_state(skb);
@@ -220,9 +223,40 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			seq = XFRM_SKB_CB(skb)->seq.input.low;
 			goto resume;
 		}
+
 		/* encap_type < -1 indicates a GRO call. */
 		encap_type = 0;
 		seq = XFRM_SPI_SKB_CB(skb)->seq;
+
+		if (xo && (xo->flags & CRYPTO_DONE)) {
+			crypto_done = true;
+			x = xfrm_input_state(skb);
+			family = XFRM_SPI_SKB_CB(skb)->family;
+
+			if (!(xo->status & CRYPTO_SUCCESS)) {
+				if (xo->status &
+				    (CRYPTO_TRANSPORT_AH_AUTH_FAILED |
+				     CRYPTO_TRANSPORT_ESP_AUTH_FAILED |
+				     CRYPTO_TUNNEL_AH_AUTH_FAILED |
+				     CRYPTO_TUNNEL_ESP_AUTH_FAILED)) {
+
+					xfrm_audit_state_icvfail(x, skb,
+								 x->type->proto);
+					x->stats.integrity_failed++;
+					XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
+					goto drop;
+				}
+
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
+				goto drop;
+			}
+
+			if ((err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
+				goto drop;
+			}
+		}
+
 		goto lock;
 	}
 
@@ -311,7 +345,10 @@ lock:
 		skb_dst_force(skb);
 		dev_hold(skb->dev);
 
-		nexthdr = x->type->input(x, skb);
+		if (crypto_done)
+			nexthdr = x->type_offload->input_tail(x, skb);
+		else
+			nexthdr = x->type->input(x, skb);
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
@@ -395,7 +432,7 @@ resume:
 		if (xo)
 			xfrm_gro = xo->flags & XFRM_GRO;
 
-		err = x->inner_mode->afinfo->transport_finish(skb, async);
+		err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async);
 		if (xfrm_gro) {
 			skb_dst_drop(skb);
 			gro_cells_receive(&gro_cells, skb);
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 8ba29fe58352..8c0b6722aaa8 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -99,12 +99,13 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 
 		skb_dst_force(skb);
 
-		/* Inner headers are invalid now. */
-		skb->encapsulation = 0;
-
-		err = x->type->output(x, skb);
-		if (err == -EINPROGRESS)
-			goto out;
+		if (xfrm_offload(skb)) {
+			x->type_offload->encap(x, skb);
+		} else {
+			err = x->type->output(x, skb);
+			if (err == -EINPROGRESS)
+				goto out;
+		}
 
 resume:
 		if (err) {
@@ -200,8 +201,40 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
 int xfrm_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
 	int err;
 
+	secpath_reset(skb);
+	skb->encapsulation = 0;
+
+	if (xfrm_dev_offload_ok(skb, x)) {
+		struct sec_path *sp;
+
+		sp = secpath_dup(skb->sp);
+		if (!sp) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sp)
+			secpath_put(skb->sp);
+		skb->sp = sp;
+		skb->encapsulation = 1;
+
+		sp->olen++;
+		sp->xvec[skb->sp->len++] = x;
+		xfrm_state_hold(x);
+
+		if (skb_is_gso(skb)) {
+			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+
+			return xfrm_output2(net, sk, skb);
+		}
+
+		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
+			goto out;
+	}
+
 	if (skb_is_gso(skb))
 		return xfrm_output_gso(net, sk, skb);
 
@@ -214,6 +247,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
+out:
 	return xfrm_output2(net, sk, skb);
 }
 EXPORT_SYMBOL_GPL(xfrm_output);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0806dccdf507..b00a1d5a7f52 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -116,11 +116,10 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa
 	return afinfo;
 }
 
-static inline struct dst_entry *__xfrm_dst_lookup(struct net *net,
-						  int tos, int oif,
-						  const xfrm_address_t *saddr,
-						  const xfrm_address_t *daddr,
-						  int family)
+struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr,
+				    int family)
 {
 	const struct xfrm_policy_afinfo *afinfo;
 	struct dst_entry *dst;
@@ -135,6 +134,7 @@ static inline struct dst_entry *__xfrm_dst_lookup(struct net *net,
 
 	return dst;
 }
+EXPORT_SYMBOL(__xfrm_dst_lookup);
 
 static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
 						int tos, int oif,
@@ -1006,6 +1006,10 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 		err = -ESRCH;
 out:
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	if (cnt)
+		xfrm_garbage_collect(net);
+
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_flush);
@@ -1243,7 +1247,7 @@ static inline int policy_to_flow_dir(int dir)
 }
 
 static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
-						 const struct flowi *fl)
+						 const struct flowi *fl, u16 family)
 {
 	struct xfrm_policy *pol;
 
@@ -1251,8 +1255,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
  again:
 	pol = rcu_dereference(sk->sk_policy[dir]);
 	if (pol != NULL) {
-		bool match = xfrm_selector_match(&pol->selector, fl,
-						 sk->sk_family);
+		bool match = xfrm_selector_match(&pol->selector, fl, family);
 		int err = 0;
 
 		if (match) {
@@ -2239,7 +2242,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	sk = sk_const_to_full_sk(sk);
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
 		num_pols = 1;
-		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
 		err = xfrm_expand_policies(fl, family, pols,
 					   &num_pols, &num_xfrms);
 		if (err < 0)
@@ -2518,7 +2521,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	pol = NULL;
 	sk = sk_to_full_sk(sk);
 	if (sk && sk->sk_policy[dir]) {
-		pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
 		if (IS_ERR(pol)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
 			return 0;
@@ -2930,21 +2933,6 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
-static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-
-	switch (event) {
-	case NETDEV_DOWN:
-		xfrm_garbage_collect(dev_net(dev));
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block xfrm_dev_notifier = {
-	.notifier_call	= xfrm_dev_event,
-};
-
 #ifdef CONFIG_XFRM_STATISTICS
 static int __net_init xfrm_statistics_init(struct net *net)
 {
@@ -3021,7 +3009,7 @@ static int __net_init xfrm_policy_init(struct net *net)
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
 	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	if (net_eq(net, &init_net))
-		register_netdevice_notifier(&xfrm_dev_notifier);
+		xfrm_dev_init();
 	return 0;
 
 out_bydst:
@@ -3069,6 +3057,11 @@ static int __net_init xfrm_net_init(struct net *net)
 {
 	int rv;
 
+	/* Initialize the per-net locks here */
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	spin_lock_init(&net->xfrm.xfrm_policy_lock);
+	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
 	rv = xfrm_statistics_init(net);
 	if (rv < 0)
 		goto out_statistics;
@@ -3085,11 +3078,6 @@ static int __net_init xfrm_net_init(struct net *net)
 	if (rv < 0)
 		goto out;
 
-	/* Initialize the per-net locks here */
-	spin_lock_init(&net->xfrm.xfrm_state_lock);
-	spin_lock_init(&net->xfrm.xfrm_policy_lock);
-	mutex_init(&net->xfrm.xfrm_cfg_mutex);
-
 	return 0;
 
 out:
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index cdc2e2e71bff..8b23c5bcf8e8 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -45,7 +45,8 @@ u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq)
 
 	return seq_hi;
 }
-
+EXPORT_SYMBOL(xfrm_replay_seqhi);
+;
 static void xfrm_replay_notify(struct xfrm_state *x, int event)
 {
 	struct km_event c;
@@ -558,6 +559,158 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
 		x->repl->notify(x, XFRM_REPLAY_UPDATE);
 }
 
+#ifdef CONFIG_XFRM_OFFLOAD
+static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct net *net = xs_net(x);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	__u32 oseq = x->replay.oseq;
+
+	if (!xo)
+		return xfrm_replay_overflow(x, skb);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		if (!skb_is_gso(skb)) {
+			XFRM_SKB_CB(skb)->seq.output.low = ++oseq;
+			xo->seq.low = oseq;
+		} else {
+			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
+			xo->seq.low = oseq + 1;
+			oseq += skb_shinfo(skb)->gso_segs;
+		}
+
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
+		xo->seq.hi = 0;
+		if (unlikely(oseq < x->replay.oseq)) {
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		}
+
+		x->replay.oseq = oseq;
+
+		if (xfrm_aevent_is_on(net))
+			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+	__u32 oseq = replay_esn->oseq;
+
+	if (!xo)
+		return xfrm_replay_overflow_bmp(x, skb);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		if (!skb_is_gso(skb)) {
+			XFRM_SKB_CB(skb)->seq.output.low = ++oseq;
+			xo->seq.low = oseq;
+		} else {
+			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
+			xo->seq.low = oseq + 1;
+			oseq += skb_shinfo(skb)->gso_segs;
+		}
+
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
+		xo->seq.hi = 0;
+		if (unlikely(oseq < replay_esn->oseq)) {
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		} else {
+			replay_esn->oseq = oseq;
+		}
+
+		if (xfrm_aevent_is_on(net))
+			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+	__u32 oseq = replay_esn->oseq;
+	__u32 oseq_hi = replay_esn->oseq_hi;
+
+	if (!xo)
+		return xfrm_replay_overflow_esn(x, skb);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		if (!skb_is_gso(skb)) {
+			XFRM_SKB_CB(skb)->seq.output.low = ++oseq;
+			XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+			xo->seq.low = oseq;
+			xo->seq.hi = oseq_hi;
+		} else {
+			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
+			XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+			xo->seq.low = oseq = oseq + 1;
+			xo->seq.hi = oseq_hi;
+			oseq += skb_shinfo(skb)->gso_segs;
+		}
+
+		if (unlikely(oseq < replay_esn->oseq)) {
+			XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
+			xo->seq.hi = oseq_hi;
+
+			if (replay_esn->oseq_hi == 0) {
+				replay_esn->oseq--;
+				replay_esn->oseq_hi--;
+				xfrm_audit_state_replay_overflow(x, skb);
+				err = -EOVERFLOW;
+
+				return err;
+			}
+		}
+
+		replay_esn->oseq = oseq;
+		replay_esn->oseq_hi = oseq_hi;
+
+		if (xfrm_aevent_is_on(net))
+			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static const struct xfrm_replay xfrm_replay_legacy = {
+	.advance	= xfrm_replay_advance,
+	.check		= xfrm_replay_check,
+	.recheck	= xfrm_replay_check,
+	.notify		= xfrm_replay_notify,
+	.overflow	= xfrm_replay_overflow_offload,
+};
+
+static const struct xfrm_replay xfrm_replay_bmp = {
+	.advance	= xfrm_replay_advance_bmp,
+	.check		= xfrm_replay_check_bmp,
+	.recheck	= xfrm_replay_check_bmp,
+	.notify		= xfrm_replay_notify_bmp,
+	.overflow	= xfrm_replay_overflow_offload_bmp,
+};
+
+static const struct xfrm_replay xfrm_replay_esn = {
+	.advance	= xfrm_replay_advance_esn,
+	.check		= xfrm_replay_check_esn,
+	.recheck	= xfrm_replay_recheck_esn,
+	.notify		= xfrm_replay_notify_esn,
+	.overflow	= xfrm_replay_overflow_offload_esn,
+};
+#else
 static const struct xfrm_replay xfrm_replay_legacy = {
 	.advance	= xfrm_replay_advance,
 	.check		= xfrm_replay_check,
@@ -581,6 +734,7 @@ static const struct xfrm_replay xfrm_replay_esn = {
 	.notify		= xfrm_replay_notify_esn,
 	.overflow	= xfrm_replay_overflow_esn,
 };
+#endif
 
 int xfrm_init_replay(struct xfrm_state *x)
 {
@@ -595,10 +749,12 @@ int xfrm_init_replay(struct xfrm_state *x)
 			if (replay_esn->replay_window == 0)
 				return -EINVAL;
 			x->repl = &xfrm_replay_esn;
-		} else
+		} else {
 			x->repl = &xfrm_replay_bmp;
-	} else
+		}
+	} else {
 		x->repl = &xfrm_replay_legacy;
+	}
 
 	return 0;
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 5a597dbbe564..fc3c5aa38754 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -251,6 +251,75 @@ static void xfrm_put_type(const struct xfrm_type *type)
 	module_put(type->owner);
 }
 
+static DEFINE_SPINLOCK(xfrm_type_offload_lock);
+int xfrm_register_type_offload(const struct xfrm_type_offload *type,
+			       unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	const struct xfrm_type_offload **typemap;
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EAFNOSUPPORT;
+	typemap = afinfo->type_offload_map;
+	spin_lock_bh(&xfrm_type_offload_lock);
+
+	if (likely(typemap[type->proto] == NULL))
+		typemap[type->proto] = type;
+	else
+		err = -EEXIST;
+	spin_unlock_bh(&xfrm_type_offload_lock);
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_register_type_offload);
+
+int xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
+				 unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	const struct xfrm_type_offload **typemap;
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EAFNOSUPPORT;
+	typemap = afinfo->type_offload_map;
+	spin_lock_bh(&xfrm_type_offload_lock);
+
+	if (unlikely(typemap[type->proto] != type))
+		err = -ENOENT;
+	else
+		typemap[type->proto] = NULL;
+	spin_unlock_bh(&xfrm_type_offload_lock);
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_unregister_type_offload);
+
+static const struct xfrm_type_offload *xfrm_get_type_offload(u8 proto, unsigned short family)
+{
+	struct xfrm_state_afinfo *afinfo;
+	const struct xfrm_type_offload **typemap;
+	const struct xfrm_type_offload *type;
+
+	afinfo = xfrm_state_get_afinfo(family);
+	if (unlikely(afinfo == NULL))
+		return NULL;
+	typemap = afinfo->type_offload_map;
+
+	type = typemap[proto];
+	if ((type && !try_module_get(type->owner)))
+		type = NULL;
+
+	rcu_read_unlock();
+	return type;
+}
+
+static void xfrm_put_type_offload(const struct xfrm_type_offload *type)
+{
+	module_put(type->owner);
+}
+
 static DEFINE_SPINLOCK(xfrm_mode_lock);
 int xfrm_register_mode(struct xfrm_mode *mode, int family)
 {
@@ -365,10 +434,13 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x)
 		xfrm_put_mode(x->inner_mode_iaf);
 	if (x->outer_mode)
 		xfrm_put_mode(x->outer_mode);
+	if (x->type_offload)
+		xfrm_put_type_offload(x->type_offload);
 	if (x->type) {
 		x->type->destructor(x);
 		xfrm_put_type(x->type);
 	}
+	xfrm_dev_state_free(x);
 	security_xfrm_state_free(x);
 	kfree(x);
 }
@@ -538,6 +610,8 @@ int __xfrm_state_delete(struct xfrm_state *x)
 		net->xfrm.state_num--;
 		spin_unlock(&net->xfrm.xfrm_state_lock);
 
+		xfrm_dev_state_delete(x);
+
 		/* All xfrm_state objects are created by xfrm_state_alloc.
 		 * The xfrm_state_alloc call gives a reference, and that
 		 * is what we are dropping here.
@@ -582,12 +656,41 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 
 	return err;
 }
+
+static inline int
+xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid)
+{
+	int i, err = 0;
+
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		struct xfrm_state *x;
+		struct xfrm_state_offload *xso;
+
+		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+			xso = &x->xso;
+
+			if (xso->dev == dev &&
+			   (err = security_xfrm_state_delete(x)) != 0) {
+				xfrm_audit_state_delete(x, 0, task_valid);
+				return err;
+			}
+		}
+	}
+
+	return err;
+}
 #else
 static inline int
 xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	return 0;
 }
+
+static inline int
+xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid)
+{
+	return 0;
+}
 #endif
 
 int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
@@ -630,6 +733,48 @@ out:
 }
 EXPORT_SYMBOL(xfrm_state_flush);
 
+int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid)
+{
+	int i, err = 0, cnt = 0;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid);
+	if (err)
+		goto out;
+
+	err = -ESRCH;
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		struct xfrm_state *x;
+		struct xfrm_state_offload *xso;
+restart:
+		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+			xso = &x->xso;
+
+			if (!xfrm_state_kern(x) && xso->dev == dev) {
+				xfrm_state_hold(x);
+				spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+				err = xfrm_state_delete(x);
+				xfrm_audit_state_delete(x, err ? 0 : 1,
+							task_valid);
+				xfrm_state_put(x);
+				if (!err)
+					cnt++;
+
+				spin_lock_bh(&net->xfrm.xfrm_state_lock);
+				goto restart;
+			}
+		}
+	}
+	if (cnt)
+		err = 0;
+
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_dev_state_flush);
+
 void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 {
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -2077,6 +2222,8 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
 	if (x->type == NULL)
 		goto error;
 
+	x->type_offload = xfrm_get_type_offload(x->id.proto, family);
+
 	err = x->type->init_state(x);
 	if (err)
 		goto error;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 9705c279494b..38614df33ec8 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -55,7 +55,7 @@ static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
 		return -EINVAL;
 	}
 
-	algp->alg_name[CRYPTO_MAX_ALG_NAME - 1] = '\0';
+	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
 	return 0;
 }
 
@@ -71,7 +71,7 @@ static int verify_auth_trunc(struct nlattr **attrs)
 	if (nla_len(rt) < xfrm_alg_auth_len(algp))
 		return -EINVAL;
 
-	algp->alg_name[CRYPTO_MAX_ALG_NAME - 1] = '\0';
+	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
 	return 0;
 }
 
@@ -87,7 +87,7 @@ static int verify_aead(struct nlattr **attrs)
 	if (nla_len(rt) < aead_len(algp))
 		return -EINVAL;
 
-	algp->alg_name[CRYPTO_MAX_ALG_NAME - 1] = '\0';
+	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
 	return 0;
 }
 
@@ -412,7 +412,14 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es
 	up = nla_data(rp);
 	ulen = xfrm_replay_state_esn_len(up);
 
-	if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen)
+	/* Check the overall length and the internal bitmap length to avoid
+	 * potential overflow. */
+	if (nla_len(rp) < ulen ||
+	    xfrm_replay_state_esn_len(replay_esn) != ulen ||
+	    replay_esn->bmp_len != up->bmp_len)
+		return -EINVAL;
+
+	if (up->replay_window > up->bmp_len * sizeof(__u32) * 8)
 		return -EINVAL;
 
 	return 0;
@@ -588,6 +595,13 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 			goto error;
 	}
 
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		err = xfrm_dev_state_add(net, x,
+					 nla_data(attrs[XFRMA_OFFLOAD_DEV]));
+		if (err)
+			goto error;
+	}
+
 	if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn,
 					       attrs[XFRMA_REPLAY_ESN_VAL])))
 		goto error;
@@ -772,6 +786,23 @@ static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb)
 	return 0;
 }
 
+static int copy_user_offload(struct xfrm_state_offload *xso, struct sk_buff *skb)
+{
+	struct xfrm_user_offload *xuo;
+	struct nlattr *attr;
+
+	attr = nla_reserve(skb, XFRMA_OFFLOAD_DEV, sizeof(*xuo));
+	if (attr == NULL)
+		return -EMSGSIZE;
+
+	xuo = nla_data(attr);
+
+	xuo->ifindex = xso->dev->ifindex;
+	xuo->flags = xso->flags;
+
+	return 0;
+}
+
 static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 {
 	struct xfrm_algo *algo;
@@ -862,6 +893,10 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 			      &x->replay);
 	if (ret)
 		goto out;
+	if(x->xso.dev)
+		ret = copy_user_offload(&x->xso, skb);
+	if (ret)
+		goto out;
 	if (x->security)
 		ret = copy_sec_ctx(x->security, skb);
 out:
@@ -925,8 +960,8 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 		u8 proto = 0;
 		int err;
 
-		err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX,
-				  xfrma_policy);
+		err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, xfrma_policy,
+				  NULL);
 		if (err < 0)
 			return err;
 
@@ -2399,6 +2434,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
 	[XFRMA_PROTO]		= { .type = NLA_U8 },
 	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
+	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
 };
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
@@ -2441,7 +2477,8 @@ static const struct xfrm_link {
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo   },
 };
 
-static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *attrs[XFRMA_MAX+1];
@@ -2481,7 +2518,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs,
 			  link->nla_max ? : XFRMA_MAX,
-			  link->nla_pol ? : xfrma_policy);
+			  link->nla_pol ? : xfrma_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2615,6 +2652,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x)
 		l += nla_total_size(sizeof(*x->coaddr));
 	if (x->props.extra_flags)
 		l += nla_total_size(sizeof(x->props.extra_flags));
+	if (x->xso.dev)
+		 l += nla_total_size(sizeof(x->xso));
 
 	/* Must count x->lastused as it may become non-zero behind our back. */
 	l += nla_total_size_64bit(sizeof(u64));
@@ -3101,7 +3140,6 @@ static bool xfrm_is_alive(const struct km_event *c)
 }
 
 static struct xfrm_mgr netlink_mgr = {
-	.id		= "netlink",
 	.notify		= xfrm_send_state_notify,
 	.acquire	= xfrm_send_acquire,
 	.compile_policy	= xfrm_compile_policy,
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 09e9d535bd74..6c7468eb3684 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -34,6 +34,8 @@ hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
 hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
+hostprogs-y += test_map_in_map
+hostprogs-y += per_socket_stats_example
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -72,6 +74,8 @@ sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
+test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
+per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -105,6 +109,8 @@ always += trace_event_kern.o
 always += sampleip_kern.o
 always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
+always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -139,6 +145,7 @@ HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
 HOSTLOADLIBES_lwt_len_hist += -l elf
 HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
+HOSTLOADLIBES_test_map_in_map += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
@@ -182,4 +189,5 @@ $(obj)/%.o: $(src)/%.c
 		-Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
+		-Wno-unknown-warning-option \
 		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index faaffe2e139a..9a9c95f2c9fb 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -80,6 +80,7 @@ struct bpf_map_def {
 	unsigned int value_size;
 	unsigned int max_entries;
 	unsigned int map_flags;
+	unsigned int inner_map_idx;
 };
 
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
@@ -145,11 +146,30 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
+#elif defined(__sparc__)
+
+#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
+#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
+#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
+#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
+#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
+#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+#if defined(__arch64__)
+#define PT_REGS_IP(x) ((x)->tpc)
+#else
+#define PT_REGS_IP(x) ((x)->pc)
+#endif
+
 #endif
 
 #ifdef __powerpc__
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+#elif defined(__sparc__)
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 #else
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({				\
 		bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b86ee54da2d1..4221dc359453 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -14,6 +14,7 @@
 #include <linux/perf_event.h>
 #include <linux/netlink.h>
 #include <linux/rtnetlink.h>
+#include <linux/types.h>
 #include <sys/types.h>
 #include <sys/socket.h>
 #include <sys/syscall.h>
@@ -21,6 +22,7 @@
 #include <sys/mman.h>
 #include <poll.h>
 #include <ctype.h>
+#include <assert.h>
 #include "libbpf.h"
 #include "bpf_load.h"
 #include "perf-sys.h"
@@ -37,14 +39,6 @@ int event_fd[MAX_PROGS];
 int prog_cnt;
 int prog_array_fd = -1;
 
-struct bpf_map_def {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-	unsigned int map_flags;
-};
-
 static int populate_prog_array(const char *event, int prog_fd)
 {
 	int ind = atoi(event), err;
@@ -192,17 +186,35 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	return 0;
 }
 
-static int load_maps(struct bpf_map_def *maps, int len)
+static int load_maps(struct bpf_map_def *maps, int nr_maps,
+		     const char **map_names, fixup_map_cb fixup_map)
 {
 	int i;
-
-	for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
-
-		map_fd[i] = bpf_create_map(maps[i].type,
-					   maps[i].key_size,
-					   maps[i].value_size,
-					   maps[i].max_entries,
-					   maps[i].map_flags);
+	/*
+	 * Warning: Using "maps" pointing to ELF data_maps->d_buf as
+	 * an array of struct bpf_map_def is a wrong assumption about
+	 * the ELF maps section format.
+	 */
+	for (i = 0; i < nr_maps; i++) {
+		if (fixup_map)
+			fixup_map(&maps[i], map_names[i], i);
+
+		if (maps[i].type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+		    maps[i].type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			int inner_map_fd = map_fd[maps[i].inner_map_idx];
+
+			map_fd[i] = bpf_create_map_in_map(maps[i].type,
+							  maps[i].key_size,
+							  inner_map_fd,
+							  maps[i].max_entries,
+							  maps[i].map_flags);
+		} else {
+			map_fd[i] = bpf_create_map(maps[i].type,
+						   maps[i].key_size,
+						   maps[i].value_size,
+						   maps[i].max_entries,
+						   maps[i].map_flags);
+		}
 		if (map_fd[i] < 0) {
 			printf("failed to create a map: %d %s\n",
 			       errno, strerror(errno));
@@ -262,20 +274,74 @@ static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols,
 			return 1;
 		}
 		insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+		/*
+		 * Warning: Using sizeof(struct bpf_map_def) here is a
+		 * wrong assumption about ELF maps section format
+		 */
 		insn[insn_idx].imm = map_fd[sym.st_value / sizeof(struct bpf_map_def)];
 	}
 
 	return 0;
 }
 
-int load_bpf_file(char *path)
+static int cmp_symbols(const void *l, const void *r)
 {
-	int fd, i;
+	const GElf_Sym *lsym = (const GElf_Sym *)l;
+	const GElf_Sym *rsym = (const GElf_Sym *)r;
+
+	if (lsym->st_value < rsym->st_value)
+		return -1;
+	else if (lsym->st_value > rsym->st_value)
+		return 1;
+	else
+		return 0;
+}
+
+static int get_sorted_map_names(Elf *elf, Elf_Data *symbols, int maps_shndx,
+				int strtabidx, char **map_names)
+{
+	GElf_Sym map_symbols[MAX_MAPS];
+	int i, nr_maps = 0;
+
+	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+		assert(nr_maps < MAX_MAPS);
+		if (!gelf_getsym(symbols, i, &map_symbols[nr_maps]))
+			continue;
+		if (map_symbols[nr_maps].st_shndx != maps_shndx)
+			continue;
+		nr_maps++;
+	}
+
+	qsort(map_symbols, nr_maps, sizeof(GElf_Sym), cmp_symbols);
+
+	for (i = 0; i < nr_maps; i++) {
+		char *map_name;
+
+		map_name = elf_strptr(elf, strtabidx, map_symbols[i].st_name);
+		if (!map_name) {
+			printf("cannot get map symbol\n");
+			return -1;
+		}
+
+		map_names[i] = strdup(map_name);
+		if (!map_names[i]) {
+			printf("strdup(%s): %s(%d)\n", map_name,
+			       strerror(errno), errno);
+			return -1;
+		}
+	}
+
+	return nr_maps;
+}
+
+static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
+{
+	int fd, i, ret, maps_shndx = -1, strtabidx = -1;
 	Elf *elf;
 	GElf_Ehdr ehdr;
 	GElf_Shdr shdr, shdr_prog;
-	Elf_Data *data, *data_prog, *symbols = NULL;
-	char *shname, *shname_prog;
+	Elf_Data *data, *data_prog, *data_maps = NULL, *symbols = NULL;
+	char *shname, *shname_prog, *map_names[MAX_MAPS] = { NULL };
 
 	/* reset global variables */
 	kern_version = 0;
@@ -323,14 +389,47 @@ int load_bpf_file(char *path)
 			}
 			memcpy(&kern_version, data->d_buf, sizeof(int));
 		} else if (strcmp(shname, "maps") == 0) {
-			processed_sec[i] = true;
-			if (load_maps(data->d_buf, data->d_size))
-				return 1;
+			maps_shndx = i;
+			data_maps = data;
 		} else if (shdr.sh_type == SHT_SYMTAB) {
+			strtabidx = shdr.sh_link;
 			symbols = data;
 		}
 	}
 
+	ret = 1;
+
+	if (!symbols) {
+		printf("missing SHT_SYMTAB section\n");
+		goto done;
+	}
+
+	if (data_maps) {
+		int nr_maps;
+		int prog_elf_map_sz;
+
+		nr_maps = get_sorted_map_names(elf, symbols, maps_shndx,
+					       strtabidx, map_names);
+		if (nr_maps < 0)
+			goto done;
+
+		/* Deduce map struct size stored in ELF maps section */
+		prog_elf_map_sz = data_maps->d_size / nr_maps;
+		if (prog_elf_map_sz != sizeof(struct bpf_map_def)) {
+			printf("Error: ELF maps sec wrong size (%d/%lu),"
+			       " old kern.o file?\n",
+			       prog_elf_map_sz, sizeof(struct bpf_map_def));
+			ret = 1;
+			goto done;
+		}
+
+		if (load_maps(data_maps->d_buf, nr_maps,
+			      (const char **)map_names, fixup_map))
+			goto done;
+
+		processed_sec[maps_shndx] = true;
+	}
+
 	/* load programs that need map fixup (relocations) */
 	for (i = 1; i < ehdr.e_shnum; i++) {
 		if (processed_sec[i])
@@ -387,8 +486,22 @@ int load_bpf_file(char *path)
 			load_and_attach(shname, data->d_buf, data->d_size);
 	}
 
+	ret = 0;
+done:
+	for (i = 0; i < MAX_MAPS; i++)
+		free(map_names[i]);
 	close(fd);
-	return 0;
+	return ret;
+}
+
+int load_bpf_file(char *path)
+{
+	return do_load_bpf_file(path, NULL);
+}
+
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map)
+{
+	return do_load_bpf_file(path, fixup_map);
 }
 
 void read_trace_pipe(void)
@@ -473,7 +586,7 @@ struct ksym *ksym_search(long key)
 	return &syms[0];
 }
 
-int set_link_xdp_fd(int ifindex, int fd)
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 {
 	struct sockaddr_nl sa;
 	int sock, seq = 0, len, ret = -1;
@@ -509,15 +622,28 @@ int set_link_xdp_fd(int ifindex, int fd)
 	req.nh.nlmsg_seq = ++seq;
 	req.ifinfo.ifi_family = AF_UNSPEC;
 	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
 	nla = (struct nlattr *)(((char *)&req)
 				+ NLMSG_ALIGN(req.nh.nlmsg_len));
 	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+	nla->nla_len = NLA_HDRLEN;
 
-	nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
 	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
 	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
 	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		nla->nla_len += nla_xdp->nla_len;
+	}
 
 	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
 
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index c827827299b3..05822f83173a 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -6,6 +6,18 @@
 #define MAX_MAPS 32
 #define MAX_PROGS 32
 
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+	unsigned int inner_map_idx;
+};
+
+typedef void (*fixup_map_cb)(struct bpf_map_def *map, const char *map_name,
+			     int idx);
+
 extern int map_fd[MAX_MAPS];
 extern int prog_fd[MAX_PROGS];
 extern int event_fd[MAX_PROGS];
@@ -25,6 +37,7 @@ extern int prog_cnt;
  * returns zero on success
  */
 int load_bpf_file(char *path);
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map);
 
 void read_trace_pipe(void);
 struct ksym {
@@ -34,5 +47,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
-int set_link_xdp_fd(int ifindex, int fd);
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
new file mode 100644
index 000000000000..b08ab4e88929
--- /dev/null
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -0,0 +1,321 @@
+/* This test is a demo of using get_socket_uid and get_socket_cookie
+ * helper function to do per socket based network traffic monitoring.
+ * It requires iptables version higher then 1.6.1. to load pinned eBPF
+ * program into the xt_bpf match.
+ *
+ * TEST:
+ * ./run_cookie_uid_helper_example.sh -option
+ * option:
+ *	-t: do traffic monitoring test, the program will continuously
+ * print out network traffic happens after program started A sample
+ * output is shown below:
+ *
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286
+ * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726
+ * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712
+ * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70
+ *
+ *	-s: do getsockopt SO_COOKIE test, the program will set up a pair of
+ * UDP sockets and send packets between them. And read out the traffic data
+ * directly from the ebpf map based on the socket cookie.
+ *
+ * Clean up: if using shell script, the script file will delete the iptables
+ * rule and unmount the bpf program when exit. Else the iptables rule need
+ * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail.
+ */
+
+#define _GNU_SOURCE
+
+#define offsetof(type, member)	__builtin_offsetof(type, member)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include "libbpf.h"
+
+#define PORT 8888
+
+struct stats {
+	uint32_t uid;
+	uint64_t packets;
+	uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static bool test_finish;
+
+static void maps_create(void)
+{
+	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t),
+				sizeof(struct stats), 100, 0);
+	if (map_fd < 0)
+		error(1, errno, "map create failed!\n");
+}
+
+static void prog_load(void)
+{
+	static char log_buf[1 << 16];
+
+	struct bpf_insn prog[] = {
+		/*
+		 * Save sk_buff for future usage. value stored in R6 to R10 will
+		 * not be reset after a bpf helper function call.
+		 */
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+		/*
+		 * pc1: BPF_FUNC_get_socket_cookie takes one parameter,
+		 * R1: sk_buff
+		 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_cookie),
+		/* pc2-4: save &socketCookie to r7 for future usage*/
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+		/*
+		 * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem,
+		 * it takes two parameters (R1: map_fd,  R2: &socket_cookie)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_lookup_elem),
+		/*
+		 * pc9. if r0 != 0x0, go to pc+14, since we have the cookie
+		 * stored already
+		 * Otherwise do pc10-22 to setup a new data entry.
+		 */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_uid),
+		/*
+		 * Place a struct stats in the R10 stack and sequentially
+		 * place the member value into the memory. Packets value
+		 * is set by directly place a IMM value 1 into the stack.
+		 */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0,
+			    -32 + (__s16)offsetof(struct stats, uid)),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10,
+			   -32 + (__s16)offsetof(struct stats, packets), 1),
+		/*
+		 * __sk_buff is a special struct used for eBPF program to
+		 * directly access some sk_buff field.
+		 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1,
+			    -32 + (__s16)offsetof(struct stats, bytes)),
+		/*
+		 * add new map entry using BPF_FUNC_map_update_elem, it takes
+		 * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats,
+		 * R4: flags)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32),
+		BPF_MOV64_IMM(BPF_REG_4, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_update_elem),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 5),
+		/*
+		 * pc24-30 update the packet info to a exist data entry, it can
+		 * be done by directly write to pointers instead of using
+		 * BPF_FUNC_map_update_elem helper function
+		 */
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, packets)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, bytes)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_EXIT_INSN(),
+	};
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+					ARRAY_SIZE(prog), "GPL", 0,
+					log_buf, sizeof(log_buf));
+	if (prog_fd < 0)
+		error(1, errno, "failed to load prog\n%s\n", log_buf);
+}
+
+static void prog_attach_iptables(char *file)
+{
+	int ret;
+	char rules[100];
+
+	if (bpf_obj_pin(prog_fd, file))
+		error(1, errno, "bpf_obj_pin");
+	if (strlen(file) > 50) {
+		printf("file path too long: %s\n", file);
+		exit(1);
+	}
+	sprintf(rules, "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT",
+		file);
+	ret = system(rules);
+	if (ret < 0) {
+		printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
+		exit(1);
+	}
+}
+
+static void print_table(void)
+{
+	struct stats curEntry;
+	uint32_t curN = UINT32_MAX;
+	uint32_t nextN;
+	int res;
+
+	while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) {
+		curN = nextN;
+		res = bpf_map_lookup_elem(map_fd, &curN, &curEntry);
+		if (res < 0) {
+			error(1, errno, "fail to get entry value of Key: %u\n",
+				curN);
+		} else {
+			printf("cookie: %u, uid: 0x%x, Packet Count: %lu,"
+				" Bytes Count: %lu\n", curN, curEntry.uid,
+				curEntry.packets, curEntry.bytes);
+		}
+	}
+}
+
+static void udp_client(void)
+{
+	struct sockaddr_in si_other = {0};
+	struct sockaddr_in si_me = {0};
+	struct stats dataEntry;
+	int s_rcv, s_send, i, recv_len;
+	char message = 'a';
+	char buf;
+	uint64_t cookie;
+	int res;
+	socklen_t cookie_len = sizeof(cookie);
+	socklen_t slen = sizeof(si_other);
+
+	s_rcv = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s_rcv < 0)
+		error(1, errno, "rcv socket creat failed!\n");
+	si_other.sin_family = AF_INET;
+	si_other.sin_port = htons(PORT);
+	if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0)
+		error(1, errno, "inet_aton\n");
+	if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1)
+		error(1, errno, "bind\n");
+	s_send = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s_send < 0)
+		error(1, errno, "send socket creat failed!\n");
+	res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+	if (res < 0)
+		printf("get cookie failed: %s\n", strerror(errno));
+	res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+	if (res != -1)
+		error(1, errno, "socket stat found while flow not active\n");
+	for (i = 0; i < 10; i++) {
+		res = sendto(s_send, &message, sizeof(message), 0,
+			     (struct sockaddr *)&si_other, slen);
+		if (res == -1)
+			error(1, errno, "send\n");
+		if (res != sizeof(message))
+			error(1, 0, "%uB != %luB\n", res, sizeof(message));
+		recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0,
+			     (struct sockaddr *)&si_me, &slen);
+		if (recv_len < 0)
+			error(1, errno, "revieve\n");
+		res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr),
+			   sizeof(si_me.sin_addr));
+		if (res != 0)
+			error(1, EFAULT, "sender addr error: %d\n", res);
+		printf("Message received: %c\n", buf);
+		res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+		if (res < 0)
+			error(1, errno, "lookup sk stat failed, cookie: %lu\n",
+			      cookie);
+		printf("cookie: %lu, uid: 0x%x, Packet Count: %lu,"
+			" Bytes Count: %lu\n\n", cookie, dataEntry.uid,
+			dataEntry.packets, dataEntry.bytes);
+	}
+	close(s_send);
+	close(s_rcv);
+}
+
+static int usage(void)
+{
+	printf("Usage: ./run_cookie_uid_helper_example.sh"
+		" bpfObjName -option\n"
+		"	-t	traffic monitor test\n"
+		"	-s	getsockopt cookie test\n");
+	return 1;
+}
+
+static void finish(int ret)
+{
+	test_finish = true;
+}
+
+int main(int argc, char *argv[])
+{
+	int opt;
+	bool cfg_test_traffic = false;
+	bool cfg_test_cookie = false;
+
+	if (argc != 3)
+		return usage();
+	while ((opt = getopt(argc, argv, "ts")) != -1) {
+		switch (opt) {
+		case 't':
+			cfg_test_traffic = true;
+			break;
+		case 's':
+			cfg_test_cookie = true;
+			break;
+
+		default:
+			printf("unknown option %c\n", opt);
+			usage();
+			return -1;
+		}
+	}
+	maps_create();
+	prog_load();
+	prog_attach_iptables(argv[2]);
+	if (cfg_test_traffic) {
+		if (signal(SIGINT, finish) == SIG_ERR)
+			error(1, errno, "register handler failed");
+		while (!test_finish) {
+			print_table();
+			printf("\n");
+			sleep(1);
+		};
+	} else if (cfg_test_cookie) {
+		udp_client();
+	}
+	close(prog_fd);
+	close(map_fd);
+	return 0;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 3705fba453a0..8ab36a04c174 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -135,6 +135,16 @@ struct bpf_insn;
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
 #define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index a91872a97742..245165817fbe 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -11,6 +11,7 @@
 #include "bpf_helpers.h"
 
 #define MAX_ENTRIES 1000
+#define MAX_NR_CPUS 1024
 
 struct bpf_map_def SEC("maps") hash_map = {
 	.type = BPF_MAP_TYPE_HASH,
@@ -26,7 +27,7 @@ struct bpf_map_def SEC("maps") lru_hash_map = {
 	.max_entries = 10000,
 };
 
-struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
+struct bpf_map_def SEC("maps") nocommon_lru_hash_map = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
@@ -34,6 +35,19 @@ struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
 	.map_flags = BPF_F_NO_COMMON_LRU,
 };
 
+struct bpf_map_def SEC("maps") inner_lru_hash_map = {
+	.type = BPF_MAP_TYPE_LRU_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = MAX_ENTRIES,
+};
+
+struct bpf_map_def SEC("maps") array_of_lru_hashs = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(u32),
+	.max_entries = MAX_NR_CPUS,
+};
+
 struct bpf_map_def SEC("maps") percpu_hash_map = {
 	.type = BPF_MAP_TYPE_PERCPU_HASH,
 	.key_size = sizeof(u32),
@@ -65,6 +79,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
+struct bpf_map_def SEC("maps") array_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = MAX_ENTRIES,
+};
+
 SEC("kprobe/sys_getuid")
 int stress_hmap(struct pt_regs *ctx)
 {
@@ -93,6 +114,7 @@ int stress_percpu_hmap(struct pt_regs *ctx)
 		bpf_map_delete_elem(&percpu_hash_map, &key);
 	return 0;
 }
+
 SEC("kprobe/sys_getgid")
 int stress_hmap_alloc(struct pt_regs *ctx)
 {
@@ -121,24 +143,56 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getpid")
+SEC("kprobe/sys_connect")
 int stress_lru_hmap_alloc(struct pt_regs *ctx)
 {
-	u32 key = bpf_get_prandom_u32();
+	struct sockaddr_in6 *in6;
+	u16 test_case, dst6[8];
+	int addrlen, ret;
+	char fmt[] = "Failed at stress_lru_hmap_alloc. ret:%d\n";
 	long val = 1;
+	u32 key = bpf_get_prandom_u32();
 
-	bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+	addrlen = (int)PT_REGS_PARM3(ctx);
 
-	return 0;
-}
+	if (addrlen != sizeof(*in6))
+		return 0;
 
-SEC("kprobe/sys_getppid")
-int stress_percpu_lru_hmap_alloc(struct pt_regs *ctx)
-{
-	u32 key = bpf_get_prandom_u32();
-	long val = 1;
+	ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+	if (ret)
+		goto done;
 
-	bpf_map_update_elem(&percpu_lru_hash_map, &key, &val, BPF_ANY);
+	if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+		return 0;
+
+	test_case = dst6[7];
+
+	if (test_case == 0) {
+		ret = bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+	} else if (test_case == 1) {
+		ret = bpf_map_update_elem(&nocommon_lru_hash_map, &key, &val,
+					  BPF_ANY);
+	} else if (test_case == 2) {
+		void *nolocal_lru_map;
+		int cpu = bpf_get_smp_processor_id();
+
+		nolocal_lru_map = bpf_map_lookup_elem(&array_of_lru_hashs,
+						      &cpu);
+		if (!nolocal_lru_map) {
+			ret = -ENOENT;
+			goto done;
+		}
+
+		ret = bpf_map_update_elem(nolocal_lru_map, &key, &val,
+					  BPF_ANY);
+	} else {
+		ret = -EINVAL;
+	}
+
+done:
+	if (ret)
+		bpf_trace_printk(fmt, sizeof(fmt), ret);
 
 	return 0;
 }
@@ -165,5 +219,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("kprobe/sys_getpgid")
+int stress_hash_map_lookup(struct pt_regs *ctx)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&hash_map, &key);
+
+	return 0;
+}
+
+SEC("kprobe/sys_getpgrp")
+int stress_array_map_lookup(struct pt_regs *ctx)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&array_map, &key);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 680260a91f50..6ac778153315 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -18,10 +18,14 @@
 #include <string.h>
 #include <time.h>
 #include <sys/resource.h>
+#include <arpa/inet.h>
+#include <errno.h>
+
 #include "libbpf.h"
 #include "bpf_load.h"
 
-#define MAX_CNT 1000000
+#define TEST_BIT(t) (1U << (t))
+#define MAX_NR_CPUS 1024
 
 static __u64 time_get_ns(void)
 {
@@ -31,15 +35,44 @@ static __u64 time_get_ns(void)
 	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
 }
 
-#define HASH_PREALLOC		(1 << 0)
-#define PERCPU_HASH_PREALLOC	(1 << 1)
-#define HASH_KMALLOC		(1 << 2)
-#define PERCPU_HASH_KMALLOC	(1 << 3)
-#define LRU_HASH_PREALLOC	(1 << 4)
-#define PERCPU_LRU_HASH_PREALLOC	(1 << 5)
-#define LPM_KMALLOC		(1 << 6)
+enum test_type {
+	HASH_PREALLOC,
+	PERCPU_HASH_PREALLOC,
+	HASH_KMALLOC,
+	PERCPU_HASH_KMALLOC,
+	LRU_HASH_PREALLOC,
+	NOCOMMON_LRU_HASH_PREALLOC,
+	LPM_KMALLOC,
+	HASH_LOOKUP,
+	ARRAY_LOOKUP,
+	INNER_LRU_HASH_PREALLOC,
+	NR_TESTS,
+};
+
+const char *test_map_names[NR_TESTS] = {
+	[HASH_PREALLOC] = "hash_map",
+	[PERCPU_HASH_PREALLOC] = "percpu_hash_map",
+	[HASH_KMALLOC] = "hash_map_alloc",
+	[PERCPU_HASH_KMALLOC] = "percpu_hash_map_alloc",
+	[LRU_HASH_PREALLOC] = "lru_hash_map",
+	[NOCOMMON_LRU_HASH_PREALLOC] = "nocommon_lru_hash_map",
+	[LPM_KMALLOC] = "lpm_trie_map_alloc",
+	[HASH_LOOKUP] = "hash_map",
+	[ARRAY_LOOKUP] = "array_map",
+	[INNER_LRU_HASH_PREALLOC] = "inner_lru_hash_map",
+};
 
 static int test_flags = ~0;
+static uint32_t num_map_entries;
+static uint32_t inner_lru_hash_size;
+static int inner_lru_hash_idx = -1;
+static int array_of_lru_hashs_idx = -1;
+static uint32_t max_cnt = 1000000;
+
+static int check_test_flags(enum test_type t)
+{
+	return test_flags & TEST_BIT(t);
+}
 
 static void test_hash_prealloc(int cpu)
 {
@@ -47,34 +80,89 @@ static void test_hash_prealloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_getuid);
 	printf("%d:hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
-static void test_lru_hash_prealloc(int cpu)
+static void do_test_lru(enum test_type test, int cpu)
 {
+	static int inner_lru_map_fds[MAX_NR_CPUS];
+
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	const char *test_name;
 	__u64 start_time;
-	int i;
+	int i, ret;
+
+	if (test == INNER_LRU_HASH_PREALLOC) {
+		int outer_fd = map_fd[array_of_lru_hashs_idx];
+
+		assert(cpu < MAX_NR_CPUS);
+
+		if (cpu) {
+			inner_lru_map_fds[cpu] =
+				bpf_create_map(BPF_MAP_TYPE_LRU_HASH,
+					       sizeof(uint32_t), sizeof(long),
+					       inner_lru_hash_size, 0);
+			if (inner_lru_map_fds[cpu] == -1) {
+				printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n",
+				       strerror(errno), errno);
+				exit(1);
+			}
+		} else {
+			inner_lru_map_fds[cpu] = map_fd[inner_lru_hash_idx];
+		}
+
+		ret = bpf_map_update_elem(outer_fd, &cpu,
+					  &inner_lru_map_fds[cpu],
+					  BPF_ANY);
+		if (ret) {
+			printf("cannot update ARRAY_OF_LRU_HASHS with key:%u. %s(%d)\n",
+			       cpu, strerror(errno), errno);
+			exit(1);
+		}
+	}
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+
+	if (test == LRU_HASH_PREALLOC) {
+		test_name = "lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[7] = 0;
+	} else if (test == NOCOMMON_LRU_HASH_PREALLOC) {
+		test_name = "nocommon_lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[7] = 1;
+	} else if (test == INNER_LRU_HASH_PREALLOC) {
+		test_name = "inner_lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[7] = 2;
+	} else {
+		assert(0);
+	}
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		syscall(__NR_getpid);
-	printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	for (i = 0; i < max_cnt; i++) {
+		ret = connect(-1, (const struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+	}
+	printf("%d:%s pre-alloc %lld events per sec\n",
+	       cpu, test_name,
+	       max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(LRU_HASH_PREALLOC, cpu);
 }
 
-static void test_percpu_lru_hash_prealloc(int cpu)
+static void test_nocommon_lru_hash_prealloc(int cpu)
 {
-	__u64 start_time;
-	int i;
+	do_test_lru(NOCOMMON_LRU_HASH_PREALLOC, cpu);
+}
 
-	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		syscall(__NR_getppid);
-	printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+static void test_inner_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(INNER_LRU_HASH_PREALLOC, cpu);
 }
 
 static void test_percpu_hash_prealloc(int cpu)
@@ -83,10 +171,10 @@ static void test_percpu_hash_prealloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_geteuid);
 	printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
 static void test_hash_kmalloc(int cpu)
@@ -95,10 +183,10 @@ static void test_hash_kmalloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_getgid);
 	printf("%d:hash_map_perf kmalloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
 static void test_percpu_hash_kmalloc(int cpu)
@@ -107,10 +195,10 @@ static void test_percpu_hash_kmalloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_getegid);
 	printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
 static void test_lpm_kmalloc(int cpu)
@@ -119,40 +207,63 @@ static void test_lpm_kmalloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_gettid);
 	printf("%d:lpm_perf kmalloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
-static void loop(int cpu)
+static void test_hash_lookup(int cpu)
 {
-	cpu_set_t cpuset;
-
-	CPU_ZERO(&cpuset);
-	CPU_SET(cpu, &cpuset);
-	sched_setaffinity(0, sizeof(cpuset), &cpuset);
+	__u64 start_time;
+	int i;
 
-	if (test_flags & HASH_PREALLOC)
-		test_hash_prealloc(cpu);
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getpgid, 0);
+	printf("%d:hash_lookup %lld lookups per sec\n",
+	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
 
-	if (test_flags & PERCPU_HASH_PREALLOC)
-		test_percpu_hash_prealloc(cpu);
+static void test_array_lookup(int cpu)
+{
+	__u64 start_time;
+	int i;
 
-	if (test_flags & HASH_KMALLOC)
-		test_hash_kmalloc(cpu);
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getpgrp, 0);
+	printf("%d:array_lookup %lld lookups per sec\n",
+	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
 
-	if (test_flags & PERCPU_HASH_KMALLOC)
-		test_percpu_hash_kmalloc(cpu);
+typedef void (*test_func)(int cpu);
+const test_func test_funcs[] = {
+	[HASH_PREALLOC] = test_hash_prealloc,
+	[PERCPU_HASH_PREALLOC] = test_percpu_hash_prealloc,
+	[HASH_KMALLOC] = test_hash_kmalloc,
+	[PERCPU_HASH_KMALLOC] = test_percpu_hash_kmalloc,
+	[LRU_HASH_PREALLOC] = test_lru_hash_prealloc,
+	[NOCOMMON_LRU_HASH_PREALLOC] = test_nocommon_lru_hash_prealloc,
+	[LPM_KMALLOC] = test_lpm_kmalloc,
+	[HASH_LOOKUP] = test_hash_lookup,
+	[ARRAY_LOOKUP] = test_array_lookup,
+	[INNER_LRU_HASH_PREALLOC] = test_inner_lru_hash_prealloc,
+};
 
-	if (test_flags & LRU_HASH_PREALLOC)
-		test_lru_hash_prealloc(cpu);
+static void loop(int cpu)
+{
+	cpu_set_t cpuset;
+	int i;
 
-	if (test_flags & PERCPU_LRU_HASH_PREALLOC)
-		test_percpu_lru_hash_prealloc(cpu);
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+	sched_setaffinity(0, sizeof(cpuset), &cpuset);
 
-	if (test_flags & LPM_KMALLOC)
-		test_lpm_kmalloc(cpu);
+	for (i = 0; i < NR_TESTS; i++) {
+		if (check_test_flags(i))
+			test_funcs[i](cpu);
+	}
 }
 
 static void run_perf_test(int tasks)
@@ -209,6 +320,38 @@ static void fill_lpm_trie(void)
 	assert(!r);
 }
 
+static void fixup_map(struct bpf_map_def *map, const char *name, int idx)
+{
+	int i;
+
+	if (!strcmp("inner_lru_hash_map", name)) {
+		inner_lru_hash_idx = idx;
+		inner_lru_hash_size = map->max_entries;
+	}
+
+	if (!strcmp("array_of_lru_hashs", name)) {
+		if (inner_lru_hash_idx == -1) {
+			printf("inner_lru_hash_map must be defined before array_of_lru_hashs\n");
+			exit(1);
+		}
+		map->inner_map_idx = inner_lru_hash_idx;
+		array_of_lru_hashs_idx = idx;
+	}
+
+	if (num_map_entries <= 0)
+		return;
+
+	inner_lru_hash_size = num_map_entries;
+
+	/* Only change the max_entries for the enabled test(s) */
+	for (i = 0; i < NR_TESTS; i++) {
+		if (!strcmp(test_map_names[i], name) &&
+		    (check_test_flags(i))) {
+			map->max_entries = num_map_entries;
+		}
+	}
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -224,7 +367,13 @@ int main(int argc, char **argv)
 	if (argc > 2)
 		num_cpu = atoi(argv[2]) ? : num_cpu;
 
-	if (load_bpf_file(filename)) {
+	if (argc > 3)
+		num_map_entries = atoi(argv[3]);
+
+	if (argc > 4)
+		max_cnt = atoi(argv[4]);
+
+	if (load_bpf_file_fixup_map(filename, fixup_map)) {
 		printf("%s", bpf_log_buf);
 		return 1;
 	}
diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh
new file mode 100755
index 000000000000..f898cfa2b1aa
--- /dev/null
+++ b/samples/bpf/run_cookie_uid_helper_example.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+local_dir="$(pwd)"
+root_dir=$local_dir/../..
+mnt_dir=$(mktemp -d --tmp)
+
+on_exit() {
+	iptables -D OUTPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT
+	umount ${mnt_dir}
+	rm -r ${mnt_dir}
+}
+
+trap on_exit EXIT
+mount -t bpf bpf ${mnt_dir}
+./per_socket_stats_example ${mnt_dir}/bpf_prog $1
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
index d96dc88d3b04..73c357142268 100644
--- a/samples/bpf/test_lru_dist.c
+++ b/samples/bpf/test_lru_dist.c
@@ -25,7 +25,9 @@
 #include "bpf_util.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
-#define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
+#ifndef offsetof
+# define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
+#endif
 #define container_of(ptr, type, member) ({			\
 	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
 	(type *)( (char *)__mptr - offsetof(type,member) );})
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
new file mode 100644
index 000000000000..42c44d091dd1
--- /dev/null
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define KBUILD_MODNAME "foo"
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/in6.h>
+#include "bpf_helpers.h"
+
+#define MAX_NR_PORTS 65536
+
+/* map #0 */
+struct bpf_map_def SEC("maps") port_a = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = MAX_NR_PORTS,
+};
+
+/* map #1 */
+struct bpf_map_def SEC("maps") port_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #2 */
+struct bpf_map_def SEC("maps") reg_result_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #3 */
+struct bpf_map_def SEC("maps") inline_result_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #4 */ /* Test case #0 */
+struct bpf_map_def SEC("maps") a_of_port_a = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 0, /* map_fd[0] is port_a */
+	.max_entries = MAX_NR_PORTS,
+};
+
+/* map #5 */ /* Test case #1 */
+struct bpf_map_def SEC("maps") h_of_port_a = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 0, /* map_fd[0] is port_a */
+	.max_entries = 1,
+};
+
+/* map #6 */ /* Test case #2 */
+struct bpf_map_def SEC("maps") h_of_port_h = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 1, /* map_fd[1] is port_h */
+	.max_entries = 1,
+};
+
+static __always_inline int do_reg_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	result = bpf_map_lookup_elem(inner_map, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_array_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_a)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_a, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_h)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_h, &port);
+	return result ? *result : -ENOENT;
+}
+
+SEC("kprobe/sys_connect")
+int trace_sys_connect(struct pt_regs *ctx)
+{
+	struct sockaddr_in6 *in6;
+	u16 test_case, port, dst6[8];
+	int addrlen, ret, inline_ret, ret_key = 0;
+	u32 port_key;
+	void *outer_map, *inner_map;
+	bool inline_hash = false;
+
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+	addrlen = (int)PT_REGS_PARM3(ctx);
+
+	if (addrlen != sizeof(*in6))
+		return 0;
+
+	ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+		return 0;
+
+	test_case = dst6[7];
+
+	ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	port_key = port;
+
+	ret = -ENOENT;
+	if (test_case == 0) {
+		outer_map = &a_of_port_a;
+	} else if (test_case == 1) {
+		outer_map = &h_of_port_a;
+	} else if (test_case == 2) {
+		outer_map = &h_of_port_h;
+	} else {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	inner_map = bpf_map_lookup_elem(outer_map, &port_key);
+	if (!inner_map) {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	ret = do_reg_lookup(inner_map, port_key);
+
+	if (test_case == 0 || test_case == 1)
+		inline_ret = do_inline_array_lookup(inner_map, port_key);
+	else
+		inline_ret = do_inline_hash_lookup(inner_map, port_key);
+
+done:
+	bpf_map_update_elem(&reg_result_h, &ret_key, &ret, BPF_ANY);
+	bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
new file mode 100644
index 000000000000..f62fdc2bd428
--- /dev/null
+++ b/samples/bpf/test_map_in_map_user.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <assert.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define PORT_A		(map_fd[0])
+#define PORT_H		(map_fd[1])
+#define REG_RESULT_H	(map_fd[2])
+#define INLINE_RESULT_H	(map_fd[3])
+#define A_OF_PORT_A	(map_fd[4]) /* Test case #0 */
+#define H_OF_PORT_A	(map_fd[5]) /* Test case #1 */
+#define H_OF_PORT_H	(map_fd[6]) /* Test case #2 */
+
+static const char * const test_names[] = {
+	"Array of Array",
+	"Hash of Array",
+	"Hash of Hash",
+};
+
+#define NR_TESTS (sizeof(test_names) / sizeof(*test_names))
+
+static void populate_map(uint32_t port_key, int magic_result)
+{
+	int ret;
+
+	ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result,
+				  BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
+	assert(!ret);
+}
+
+static void test_map_in_map(void)
+{
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	uint32_t result_key = 0, port_key;
+	int result, inline_result;
+	int magic_result = 0xfaceb00c;
+	int ret;
+	int i;
+
+	port_key = rand() & 0x00FF;
+	populate_map(port_key, magic_result);
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+	in6.sin6_port = port_key;
+
+	for (i = 0; i < NR_TESTS; i++) {
+		printf("%s: ", test_names[i]);
+
+		in6.sin6_addr.s6_addr16[7] = i;
+		ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+
+		ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result);
+		assert(!ret);
+
+		ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key,
+					  &inline_result);
+		assert(!ret);
+
+		if (result != magic_result || inline_result != magic_result) {
+			printf("Error. result:%d inline_result:%d\n",
+			       result, inline_result);
+			exit(1);
+		}
+
+		bpf_map_delete_elem(REG_RESULT_H, &result_key);
+		bpf_map_delete_elem(INLINE_RESULT_H, &result_key);
+
+		printf("Pass\n");
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	char filename[256];
+
+	assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	test_map_in_map();
+
+	return 0;
+}
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index d2be65d1fd86..378850c70eb8 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -5,6 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <linux/bpf.h>
+#include <linux/if_link.h>
 #include <assert.h>
 #include <errno.h>
 #include <signal.h>
@@ -12,16 +13,18 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <libgen.h>
 
 #include "bpf_load.h"
 #include "bpf_util.h"
 #include "libbpf.h"
 
 static int ifindex;
+static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex, -1);
+	set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -54,18 +57,39 @@ static void poll_stats(int interval)
 	}
 }
 
-int main(int ac, char **argv)
+static void usage(const char *prog)
 {
-	char filename[256];
+	fprintf(stderr,
+		"usage: %s [OPTS] IFINDEX\n\n"
+		"OPTS:\n"
+		"    -S    use skb-mode\n",
+		prog);
+}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+int main(int argc, char **argv)
+{
+	const char *optstr = "S";
+	char filename[256];
+	int opt;
+
+	while ((opt = getopt(argc, argv, optstr)) != -1) {
+		switch (opt) {
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		default:
+			usage(basename(argv[0]));
+			return 1;
+		}
+	}
 
-	if (ac != 2) {
-		printf("usage: %s IFINDEX\n", argv[0]);
+	if (optind == argc) {
+		usage(basename(argv[0]));
 		return 1;
 	}
+	ifindex = strtoul(argv[optind], NULL, 0);
 
-	ifindex = strtoul(argv[1], NULL, 0);
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 
 	if (load_bpf_file(filename)) {
 		printf("%s", bpf_log_buf);
@@ -79,7 +103,7 @@ int main(int ac, char **argv)
 
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 70e192fc61aa..92b8bde9337c 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -5,6 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <linux/bpf.h>
+#include <linux/if_link.h>
 #include <assert.h>
 #include <errno.h>
 #include <signal.h>
@@ -24,11 +25,12 @@
 #define STATS_INTERVAL_S 2U
 
 static int ifindex = -1;
+static __u32 xdp_flags = 0;
 
 static void int_exit(int sig)
 {
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1);
+		set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -136,7 +138,7 @@ int main(int argc, char **argv)
 {
 	unsigned char opt_flags[256] = {};
 	unsigned int kill_after_s = 0;
-	const char *optstr = "i:a:p:s:d:m:T:P:h";
+	const char *optstr = "i:a:p:s:d:m:T:P:Sh";
 	int min_port = 0, max_port = 0;
 	struct iptnl_info tnl = {};
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -201,6 +203,9 @@ int main(int argc, char **argv)
 		case 'T':
 			kill_after_s = atoi(optarg);
 			break;
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
 		default:
 			usage(argv[0]);
 			return 1;
@@ -243,14 +248,14 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}
 
 	poll_stats(kill_after_s);
 
-	set_link_xdp_fd(ifindex, -1);
+	set_link_xdp_fd(ifindex, -1, xdp_flags);
 
 	return 0;
 }
diff --git a/samples/statx/test-statx.c b/samples/statx/test-statx.c
index 8571d766331d..d4d77b09412c 100644
--- a/samples/statx/test-statx.c
+++ b/samples/statx/test-statx.c
@@ -141,8 +141,8 @@ static void dump_statx(struct statx *stx)
 	if (stx->stx_mask & STATX_BTIME)
 		print_time(" Birth: ", &stx->stx_btime);
 
-	if (stx->stx_attributes) {
-		unsigned char bits;
+	if (stx->stx_attributes_mask) {
+		unsigned char bits, mbits;
 		int loop, byte;
 
 		static char attr_representation[64 + 1] =
@@ -160,14 +160,18 @@ static void dump_statx(struct statx *stx)
 		printf("Attributes: %016llx (", stx->stx_attributes);
 		for (byte = 64 - 8; byte >= 0; byte -= 8) {
 			bits = stx->stx_attributes >> byte;
+			mbits = stx->stx_attributes_mask >> byte;
 			for (loop = 7; loop >= 0; loop--) {
 				int bit = byte + loop;
 
-				if (bits & 0x80)
+				if (!(mbits & 0x80))
+					putchar('.');	/* Not supported */
+				else if (bits & 0x80)
 					putchar(attr_representation[63 - bit]);
 				else
-					putchar('-');
+					putchar('-');	/* Not set */
 				bits <<= 1;
+				mbits <<= 1;
 			}
 			if (byte)
 				putchar(' ');
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index d6ca649cb0e9..afe3fd3af1e4 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -148,6 +148,10 @@ cc-fullversion = $(shell $(CONFIG_SHELL) \
 # Usage:  EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1)
 cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4))
 
+# cc-if-fullversion
+# Usage:  EXTRA_CFLAGS += $(call cc-if-fullversion, -lt, 040502, -O1)
+cc-if-fullversion = $(shell [ $(cc-fullversion) $(1) $(2) ] && echo $(3) || echo $(4))
+
 # cc-ldoption
 # Usage: ldflags += $(call cc-ldoption, -Wl$(comma)--hash-style=both)
 cc-ldoption = $(call try-run,\
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 0a07f9014944..7234e61e7ce3 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -155,7 +155,7 @@ else
 # $(call addtree,-I$(obj)) locates .h files in srctree, from generated .c files
 #   and locates generated .h files
 # FIXME: Replace both with specific CFLAGS* statements in the makefiles
-__c_flags	= $(if $(obj),-I$(srctree)/$(src) -I$(obj)) \
+__c_flags	= $(if $(obj),$(call addtree,-I$(src)) -I$(obj)) \
 		  $(call flags,_c_flags)
 __a_flags	= $(call flags,_a_flags)
 __cpp_flags     = $(call flags,_cpp_flags)
diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl
index 3033be701e9a..9d37aa4faf5c 100755
--- a/scripts/checkstack.pl
+++ b/scripts/checkstack.pl
@@ -12,7 +12,6 @@
 #	sh64 port by Paul Mundt
 #	Random bits by Matt Mackall <mpm@selenic.com>
 #	M68k port by Geert Uytterhoeven and Andreas Schwab
-#	AVR32 port by Haavard Skinnemoen (Atmel)
 #	AArch64, PARISC ports by Kyle McMartin
 #	sparc port by Martin Habets <errandir_news@mph.eclipse.co.uk>
 #
@@ -51,10 +50,6 @@ my (@stack, $re, $dre, $x, $xs, $funcre);
 	} elsif ($arch eq 'arm') {
 		#c0008ffc:	e24dd064	sub	sp, sp, #100	; 0x64
 		$re = qr/.*sub.*sp, sp, #(([0-9]{2}|[3-9])[0-9]{2})/o;
-	} elsif ($arch eq 'avr32') {
-		#8000008a:       20 1d           sub sp,4
-		#80000ca8:       fa cd 05 b0     sub sp,sp,1456
-		$re = qr/^.*sub.*sp.*,([0-9]{1,8})/o;
 	} elsif ($arch =~ /^x86(_64)?$/ || $arch =~ /^i[3456]86$/) {
 		#c0105234:       81 ec ac 05 00 00       sub    $0x5ac,%esp
 		# or
diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
index 2c9082ba6137..116b7735ee9f 100755
--- a/scripts/checksyscalls.sh
+++ b/scripts/checksyscalls.sh
@@ -148,6 +148,7 @@ cat << EOF
 #define __IGNORE_sysfs
 #define __IGNORE_uselib
 #define __IGNORE__sysctl
+#define __IGNORE_arch_prctl
 
 /* ... including the "new" 32-bit uid syscalls */
 #define __IGNORE_lchown32
diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c
index 9b0b5cbc5b89..0f98634c20a0 100644
--- a/scripts/gcc-plugins/sancov_plugin.c
+++ b/scripts/gcc-plugins/sancov_plugin.c
@@ -133,7 +133,7 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gc
 #if BUILDING_GCC_VERSION < 6000
 	register_callback(plugin_name, PLUGIN_START_UNIT, &sancov_start_unit, NULL);
 	register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, (void *)&gt_ggc_r_gt_sancov);
-	register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_plugin_pass_info);
+	register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_pass_info);
 #endif
 
 	return 0;
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index 26d208b435a0..cfddddb9c9d7 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -914,7 +914,7 @@ on_treeview2_button_press_event(GtkWidget * widget,
 			current = menu;
 			display_tree_part();
 			gtk_widget_set_sensitive(back_btn, TRUE);
-		} else if ((col == COL_OPTION)) {
+		} else if (col == COL_OPTION) {
 			toggle_sym_value(menu);
 			gtk_tree_view_expand_row(view, path, TRUE);
 		}
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 33c85dfdfce9..a26a5f2dce39 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -202,6 +202,7 @@ EOF
 # '&struct_name.member' - name of a structure member
 # '@parameter' - name of a parameter
 # '%CONST' - name of a constant.
+# '``LITERAL``' - literal string without any spaces on it.
 
 ## init lots of data
 
@@ -210,7 +211,8 @@ my $warnings = 0;
 my $anon_struct_union = 0;
 
 # match expressions used to find embedded type information
-my $type_constant = '\%([-_\w]+)';
+my $type_constant = '\b``([^\`]+)``\b';
+my $type_constant2 = '\%([-_\w]+)';
 my $type_func = '(\w+)\(\)';
 my $type_param = '\@(\w+(\.\.\.)?)';
 my $type_fp_param = '\@(\w+)\(\)';  # Special RST handling for func ptr params
@@ -235,6 +237,7 @@ my $type_member_func = $type_member . '\(\)';
 # these work fairly well
 my @highlights_html = (
                        [$type_constant, "<i>\$1</i>"],
+                       [$type_constant2, "<i>\$1</i>"],
                        [$type_func, "<b>\$1</b>"],
                        [$type_enum_xml, "<i>\$1</i>"],
                        [$type_struct_xml, "<i>\$1</i>"],
@@ -252,6 +255,7 @@ my $blankline_html = $local_lt . "p" . $local_gt;	# was "<p>"
 # html version 5
 my @highlights_html5 = (
                         [$type_constant, "<span class=\"const\">\$1</span>"],
+                        [$type_constant2, "<span class=\"const\">\$1</span>"],
                         [$type_func, "<span class=\"func\">\$1</span>"],
                         [$type_enum_xml, "<span class=\"enum\">\$1</span>"],
                         [$type_struct_xml, "<span class=\"struct\">\$1</span>"],
@@ -268,6 +272,7 @@ my $blankline_html5 = $local_lt . "br /" . $local_gt;
 my @highlights_xml = (
                       ["([^=])\\\"([^\\\"<]+)\\\"", "\$1<quote>\$2</quote>"],
                       [$type_constant, "<constant>\$1</constant>"],
+                      [$type_constant2, "<constant>\$1</constant>"],
                       [$type_enum_xml, "<type>\$1</type>"],
                       [$type_struct_xml, "<structname>\$1</structname>"],
                       [$type_typedef_xml, "<type>\$1</type>"],
@@ -283,6 +288,7 @@ my $blankline_xml = $local_lt . "/para" . $local_gt . $local_lt . "para" . $loca
 # gnome, docbook format
 my @highlights_gnome = (
                         [$type_constant, "<replaceable class=\"option\">\$1</replaceable>"],
+                        [$type_constant2, "<replaceable class=\"option\">\$1</replaceable>"],
                         [$type_func, "<function>\$1</function>"],
                         [$type_enum, "<type>\$1</type>"],
                         [$type_struct, "<structname>\$1</structname>"],
@@ -298,6 +304,7 @@ my $blankline_gnome = "</para><para>\n";
 # these are pretty rough
 my @highlights_man = (
                       [$type_constant, "\$1"],
+                      [$type_constant2, "\$1"],
                       [$type_func, "\\\\fB\$1\\\\fP"],
                       [$type_enum, "\\\\fI\$1\\\\fP"],
                       [$type_struct, "\\\\fI\$1\\\\fP"],
@@ -312,6 +319,7 @@ my $blankline_man = "";
 # text-mode
 my @highlights_text = (
                        [$type_constant, "\$1"],
+                       [$type_constant2, "\$1"],
                        [$type_func, "\$1"],
                        [$type_enum, "\$1"],
                        [$type_struct, "\$1"],
@@ -326,6 +334,7 @@ my $blankline_text = "";
 # rst-mode
 my @highlights_rst = (
                        [$type_constant, "``\$1``"],
+                       [$type_constant2, "``\$1``"],
                        # Note: need to escape () to avoid func matching later
                        [$type_member_func, "\\:c\\:type\\:`\$1\$2\$3\\\\(\\\\) <\$1>`"],
                        [$type_member, "\\:c\\:type\\:`\$1\$2\$3 <\$1>`"],
@@ -344,6 +353,7 @@ my $blankline_rst = "\n";
 # list mode
 my @highlights_list = (
                        [$type_constant, "\$1"],
+                       [$type_constant2, "\$1"],
                        [$type_func, "\$1"],
                        [$type_enum, "\$1"],
                        [$type_struct, "\$1"],
@@ -2392,8 +2402,7 @@ sub push_parameter($$$) {
 	}
 
 	$anon_struct_union = 0;
-	my $param_name = $param;
-	$param_name =~ s/\[.*//;
+	$param =~ s/[\[\)].*//;
 
 	if ($type eq "" && $param =~ /\.\.\.$/)
 	{
@@ -2424,9 +2433,9 @@ sub push_parameter($$$) {
 	# but inline preprocessor statements);
 	# also ignore unnamed structs/unions;
 	if (!$anon_struct_union) {
-	if (!defined $parameterdescs{$param_name} && $param_name !~ /^#/) {
+	if (!defined $parameterdescs{$param} && $param !~ /^#/) {
 
-	    $parameterdescs{$param_name} = $undescribed;
+	    $parameterdescs{$param} = $undescribed;
 
 	    if (($type eq 'function') || ($type eq 'enum')) {
 		print STDERR "${file}:$.: warning: Function parameter ".
diff --git a/scripts/module-common.lds b/scripts/module-common.lds
index cf7e52e4781b..9b6e246a45d0 100644
--- a/scripts/module-common.lds
+++ b/scripts/module-common.lds
@@ -22,4 +22,6 @@ SECTIONS {
 
 	. = ALIGN(8);
 	.init_array		0 : { *(SORT(.init_array.*)) *(.init_array) }
+
+	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
 }
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 0458b037c8a1..0545f5a8cabe 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -372,6 +372,8 @@ disassocation||disassociation
 disapear||disappear
 disapeared||disappeared
 disappared||disappeared
+disble||disable
+disbled||disabled
 disconnet||disconnect
 discontinous||discontinuous
 dispertion||dispersion
@@ -732,6 +734,7 @@ oustanding||outstanding
 overaall||overall
 overhread||overhead
 overlaping||overlapping
+overide||override
 overrided||overridden
 overriden||overridden
 overun||overrun
diff --git a/security/Kconfig b/security/Kconfig
index d900f47eaa68..213df4d4f2c1 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -125,17 +125,8 @@ config HAVE_HARDENED_USERCOPY_ALLOCATOR
 	  validating memory ranges against heap object sizes in
 	  support of CONFIG_HARDENED_USERCOPY.
 
-config HAVE_ARCH_HARDENED_USERCOPY
-	bool
-	help
-	  The architecture supports CONFIG_HARDENED_USERCOPY by
-	  calling check_object_size() just before performing the
-	  userspace copies in the low level implementation of
-	  copy_to_user() and copy_from_user().
-
 config HARDENED_USERCOPY
 	bool "Harden memory copies between kernel and userspace"
-	depends on HAVE_ARCH_HARDENED_USERCOPY
 	depends on HAVE_HARDENED_USERCOPY_ALLOCATOR
 	select BUG
 	help
diff --git a/security/keys/gc.c b/security/keys/gc.c
index addf060399e0..9cb4fe4478a1 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -46,7 +46,7 @@ static unsigned long key_gc_flags;
  * immediately unlinked.
  */
 struct key_type key_type_dead = {
-	.name = "dead",
+	.name = ".dead",
 };
 
 /*
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 52c34532c785..4ad3212adebe 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -273,7 +273,8 @@ error:
  * Create and join an anonymous session keyring or join a named session
  * keyring, creating it if necessary.  A named session keyring must have Search
  * permission for it to be joined.  Session keyrings without this permit will
- * be skipped over.
+ * be skipped over.  It is not permitted for userspace to create or join
+ * keyrings whose name begin with a dot.
  *
  * If successful, the ID of the joined session keyring will be returned.
  */
@@ -290,12 +291,16 @@ long keyctl_join_session_keyring(const char __user *_name)
 			ret = PTR_ERR(name);
 			goto error;
 		}
+
+		ret = -EPERM;
+		if (name[0] == '.')
+			goto error_name;
 	}
 
 	/* join the session */
 	ret = join_session_keyring(name);
+error_name:
 	kfree(name);
-
 error:
 	return ret;
 }
@@ -1253,8 +1258,8 @@ error:
  * Read or set the default keyring in which request_key() will cache keys and
  * return the old setting.
  *
- * If a process keyring is specified then this will be created if it doesn't
- * yet exist.  The old setting will be returned if successful.
+ * If a thread or process keyring is specified then it will be created if it
+ * doesn't yet exist.  The old setting will be returned if successful.
  */
 long keyctl_set_reqkey_keyring(int reqkey_defl)
 {
@@ -1279,11 +1284,8 @@ long keyctl_set_reqkey_keyring(int reqkey_defl)
 
 	case KEY_REQKEY_DEFL_PROCESS_KEYRING:
 		ret = install_process_keyring_to_cred(new);
-		if (ret < 0) {
-			if (ret != -EEXIST)
-				goto error;
-			ret = 0;
-		}
+		if (ret < 0)
+			goto error;
 		goto set;
 
 	case KEY_REQKEY_DEFL_DEFAULT:
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index b6fdd22205b1..9139b18fc863 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -128,13 +128,18 @@ error:
 }
 
 /*
- * Install a fresh thread keyring directly to new credentials.  This keyring is
- * allowed to overrun the quota.
+ * Install a thread keyring to the given credentials struct if it didn't have
+ * one already.  This is allowed to overrun the quota.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
  */
 int install_thread_keyring_to_cred(struct cred *new)
 {
 	struct key *keyring;
 
+	if (new->thread_keyring)
+		return 0;
+
 	keyring = keyring_alloc("_tid", new->uid, new->gid, new,
 				KEY_POS_ALL | KEY_USR_VIEW,
 				KEY_ALLOC_QUOTA_OVERRUN,
@@ -147,7 +152,9 @@ int install_thread_keyring_to_cred(struct cred *new)
 }
 
 /*
- * Install a fresh thread keyring, discarding the old one.
+ * Install a thread keyring to the current task if it didn't have one already.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
  */
 static int install_thread_keyring(void)
 {
@@ -158,8 +165,6 @@ static int install_thread_keyring(void)
 	if (!new)
 		return -ENOMEM;
 
-	BUG_ON(new->thread_keyring);
-
 	ret = install_thread_keyring_to_cred(new);
 	if (ret < 0) {
 		abort_creds(new);
@@ -170,17 +175,17 @@ static int install_thread_keyring(void)
 }
 
 /*
- * Install a process keyring directly to a credentials struct.
+ * Install a process keyring to the given credentials struct if it didn't have
+ * one already.  This is allowed to overrun the quota.
  *
- * Returns -EEXIST if there was already a process keyring, 0 if one installed,
- * and other value on any other error
+ * Return: 0 if a process keyring is now present; -errno on failure.
  */
 int install_process_keyring_to_cred(struct cred *new)
 {
 	struct key *keyring;
 
 	if (new->process_keyring)
-		return -EEXIST;
+		return 0;
 
 	keyring = keyring_alloc("_pid", new->uid, new->gid, new,
 				KEY_POS_ALL | KEY_USR_VIEW,
@@ -194,11 +199,9 @@ int install_process_keyring_to_cred(struct cred *new)
 }
 
 /*
- * Make sure a process keyring is installed for the current process.  The
- * existing process keyring is not replaced.
+ * Install a process keyring to the current task if it didn't have one already.
  *
- * Returns 0 if there is a process keyring by the end of this function, some
- * error otherwise.
+ * Return: 0 if a process keyring is now present; -errno on failure.
  */
 static int install_process_keyring(void)
 {
@@ -212,14 +215,18 @@ static int install_process_keyring(void)
 	ret = install_process_keyring_to_cred(new);
 	if (ret < 0) {
 		abort_creds(new);
-		return ret != -EEXIST ? ret : 0;
+		return ret;
 	}
 
 	return commit_creds(new);
 }
 
 /*
- * Install a session keyring directly to a credentials struct.
+ * Install the given keyring as the session keyring of the given credentials
+ * struct, replacing the existing one if any.  If the given keyring is NULL,
+ * then install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
  */
 int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 {
@@ -254,8 +261,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 }
 
 /*
- * Install a session keyring, discarding the old one.  If a keyring is not
- * supplied, an empty one is invented.
+ * Install the given keyring as the session keyring of the current task,
+ * replacing the existing one if any.  If the given keyring is NULL, then
+ * install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
  */
 static int install_session_keyring(struct key *keyring)
 {
diff --git a/security/security.c b/security/security.c
index d0e07f269b2d..23555c5504f6 100644
--- a/security/security.c
+++ b/security/security.c
@@ -103,10 +103,14 @@ static int lsm_append(char *new, char **result)
  * to avoid security registration races. This method may also be used
  * to check if your LSM is currently loaded during kernel initialization.
  *
- * Return true if:
- *	-The passed LSM is the one chosen by user at boot time,
- *	-or the passed LSM is configured as the default and the user did not
- *	 choose an alternate LSM at boot time.
+ * Returns:
+ *
+ * true if:
+ *
+ * - The passed LSM is the one chosen by user at boot time,
+ * - or the passed LSM is configured as the default and the user did not
+ *   choose an alternate LSM at boot time.
+ *
  * Otherwise, return false.
  */
 int __init security_module_enable(const char *module)
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2ca9cde939d4..8e67bb4c9cab 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -69,6 +69,7 @@ static struct nlmsg_perm nlmsg_route_perms[] =
 	{ RTM_GETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 	{ RTM_SETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_NEWNETCONF,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNETCONF,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_GETNETCONF,	NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 	{ RTM_NEWMDB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_DELMDB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE  },
diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c
index 97527710a72a..6c02ac478247 100644
--- a/security/tomoyo/network.c
+++ b/security/tomoyo/network.c
@@ -608,7 +608,7 @@ static int tomoyo_check_unix_address(struct sockaddr *addr,
 static bool tomoyo_kernel_service(void)
 {
 	/* Nothing to do if I am a kernel service. */
-	return segment_eq(get_fs(), KERNEL_DS);
+	return uaccess_kernel();
 }
 
 /**
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 4c935202ce23..f3b1d7f50b81 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1832,6 +1832,7 @@ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client,
 	     info->output_pool != client->pool->size)) {
 		if (snd_seq_write_pool_allocated(client)) {
 			/* remove all existing cells */
+			snd_seq_pool_mark_closing(client->pool);
 			snd_seq_queue_client_leave_cells(client->number);
 			snd_seq_pool_done(client->pool);
 		}
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 448efd4e980e..01c4cfe30c9f 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -72,6 +72,9 @@ void snd_seq_fifo_delete(struct snd_seq_fifo **fifo)
 		return;
 	*fifo = NULL;
 
+	if (f->pool)
+		snd_seq_pool_mark_closing(f->pool);
+
 	snd_seq_fifo_clear(f);
 
 	/* wake up clients if any */
@@ -264,6 +267,10 @@ int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize)
 	/* NOTE: overflow flag is not cleared */
 	spin_unlock_irqrestore(&f->lock, flags);
 
+	/* close the old pool and wait until all users are gone */
+	snd_seq_pool_mark_closing(oldpool);
+	snd_use_lock_sync(&f->use_lock);
+
 	/* release cells in old pool */
 	for (cell = oldhead; cell; cell = next) {
 		next = cell->next;
diff --git a/sound/core/seq/seq_lock.c b/sound/core/seq/seq_lock.c
index 3b693e924db7..12ba83367b1b 100644
--- a/sound/core/seq/seq_lock.c
+++ b/sound/core/seq/seq_lock.c
@@ -28,19 +28,16 @@
 /* wait until all locks are released */
 void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line)
 {
-	int max_count = 5 * HZ;
+	int warn_count = 5 * HZ;
 
 	if (atomic_read(lockp) < 0) {
 		pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line);
 		return;
 	}
 	while (atomic_read(lockp) > 0) {
-		if (max_count == 0) {
-			pr_warn("ALSA: seq_lock: timeout [%d left] in %s:%d\n", atomic_read(lockp), file, line);
-			break;
-		}
+		if (warn_count-- == 0)
+			pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line);
 		schedule_timeout_uninterruptible(1);
-		max_count--;
 	}
 }
 
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 1a1acf3ddda4..d4c61ec9be13 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -415,6 +415,18 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
 	return 0;
 }
 
+/* refuse the further insertion to the pool */
+void snd_seq_pool_mark_closing(struct snd_seq_pool *pool)
+{
+	unsigned long flags;
+
+	if (snd_BUG_ON(!pool))
+		return;
+	spin_lock_irqsave(&pool->lock, flags);
+	pool->closing = 1;
+	spin_unlock_irqrestore(&pool->lock, flags);
+}
+
 /* remove events */
 int snd_seq_pool_done(struct snd_seq_pool *pool)
 {
@@ -425,10 +437,6 @@ int snd_seq_pool_done(struct snd_seq_pool *pool)
 		return -EINVAL;
 
 	/* wait for closing all threads */
-	spin_lock_irqsave(&pool->lock, flags);
-	pool->closing = 1;
-	spin_unlock_irqrestore(&pool->lock, flags);
-
 	if (waitqueue_active(&pool->output_sleep))
 		wake_up(&pool->output_sleep);
 
@@ -485,6 +493,7 @@ int snd_seq_pool_delete(struct snd_seq_pool **ppool)
 	*ppool = NULL;
 	if (pool == NULL)
 		return 0;
+	snd_seq_pool_mark_closing(pool);
 	snd_seq_pool_done(pool);
 	kfree(pool);
 	return 0;
diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h
index 4a2ec779b8a7..32f959c17786 100644
--- a/sound/core/seq/seq_memory.h
+++ b/sound/core/seq/seq_memory.h
@@ -84,6 +84,7 @@ static inline int snd_seq_total_cells(struct snd_seq_pool *pool)
 int snd_seq_pool_init(struct snd_seq_pool *pool);
 
 /* done pool - free events */
+void snd_seq_pool_mark_closing(struct snd_seq_pool *pool);
 int snd_seq_pool_done(struct snd_seq_pool *pool);
 
 /* create pool */
diff --git a/sound/firewire/lib.h b/sound/firewire/lib.h
index f6769312ebfc..c3768cd494a5 100644
--- a/sound/firewire/lib.h
+++ b/sound/firewire/lib.h
@@ -45,7 +45,7 @@ struct snd_fw_async_midi_port {
 
 	struct snd_rawmidi_substream *substream;
 	snd_fw_async_midi_port_fill fill;
-	unsigned int consume_bytes;
+	int consume_bytes;
 };
 
 int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port,
diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c
index 74d7fb6efce6..413ab6313bb6 100644
--- a/sound/firewire/oxfw/oxfw.c
+++ b/sound/firewire/oxfw/oxfw.c
@@ -227,11 +227,11 @@ static void do_registration(struct work_struct *work)
 	if (err < 0)
 		goto error;
 
-	err = detect_quirks(oxfw);
+	err = snd_oxfw_stream_discover(oxfw);
 	if (err < 0)
 		goto error;
 
-	err = snd_oxfw_stream_discover(oxfw);
+	err = detect_quirks(oxfw);
 	if (err < 0)
 		goto error;
 
diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index ab4cdab5cfa5..79edd88d5cd0 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -1905,7 +1905,7 @@ static int hw_card_start(struct hw *hw)
 		return err;
 
 	/* Set DMA transfer mask */
-	if (dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) {
+	if (!dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) {
 		dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(dma_bits));
 	} else {
 		dma_set_mask(&pci->dev, DMA_BIT_MASK(32));
diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c
index 19d41da79f93..7efa7bd7acb2 100644
--- a/sound/pci/hda/dell_wmi_helper.c
+++ b/sound/pci/hda/dell_wmi_helper.c
@@ -2,11 +2,11 @@
  * to be included from codec driver
  */
 
-#if IS_ENABLED(CONFIG_LEDS_DELL_NETBOOKS)
+#if IS_ENABLED(CONFIG_DELL_LAPTOP)
 #include <linux/dell-led.h>
 
 static int dell_led_value;
-static int (*dell_led_set_func)(int, int);
+static int (*dell_micmute_led_set_func)(int);
 static void (*dell_old_cap_hook)(struct hda_codec *,
 			         struct snd_kcontrol *,
 				 struct snd_ctl_elem_value *);
@@ -18,7 +18,7 @@ static void update_dell_wmi_micmute_led(struct hda_codec *codec,
 	if (dell_old_cap_hook)
 		dell_old_cap_hook(codec, kcontrol, ucontrol);
 
-	if (!ucontrol || !dell_led_set_func)
+	if (!ucontrol || !dell_micmute_led_set_func)
 		return;
 	if (strcmp("Capture Switch", ucontrol->id.name) == 0 && ucontrol->id.index == 0) {
 		/* TODO: How do I verify if it's a mono or stereo here? */
@@ -26,8 +26,8 @@ static void update_dell_wmi_micmute_led(struct hda_codec *codec,
 		if (val == dell_led_value)
 			return;
 		dell_led_value = val;
-		if (dell_led_set_func)
-			dell_led_set_func(DELL_LED_MICMUTE, dell_led_value);
+		if (dell_micmute_led_set_func)
+			dell_micmute_led_set_func(dell_led_value);
 	}
 }
 
@@ -39,15 +39,15 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
 	bool removefunc = false;
 
 	if (action == HDA_FIXUP_ACT_PROBE) {
-		if (!dell_led_set_func)
-			dell_led_set_func = symbol_request(dell_app_wmi_led_set);
-		if (!dell_led_set_func) {
-			codec_warn(codec, "Failed to find dell wmi symbol dell_app_wmi_led_set\n");
+		if (!dell_micmute_led_set_func)
+			dell_micmute_led_set_func = symbol_request(dell_micmute_led_set);
+		if (!dell_micmute_led_set_func) {
+			codec_warn(codec, "Failed to find dell wmi symbol dell_micmute_led_set\n");
 			return;
 		}
 
 		removefunc = true;
-		if (dell_led_set_func(DELL_LED_MICMUTE, false) >= 0) {
+		if (dell_micmute_led_set_func(false) >= 0) {
 			dell_led_value = 0;
 			if (spec->gen.num_adc_nids > 1 && !spec->gen.dyn_adc_switch)
 				codec_dbg(codec, "Skipping micmute LED control due to several ADCs");
@@ -60,17 +60,17 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
 
 	}
 
-	if (dell_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
-		symbol_put(dell_app_wmi_led_set);
-		dell_led_set_func = NULL;
+	if (dell_micmute_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
+		symbol_put(dell_micmute_led_set);
+		dell_micmute_led_set_func = NULL;
 		dell_old_cap_hook = NULL;
 	}
 }
 
-#else /* CONFIG_LEDS_DELL_NETBOOKS */
+#else /* CONFIG_DELL_LAPTOP */
 static void alc_fixup_dell_wmi(struct hda_codec *codec,
 			       const struct hda_fixup *fix, int action)
 {
 }
 
-#endif /* CONFIG_LEDS_DELL_NETBOOKS */
+#endif /* CONFIG_DELL_LAPTOP */
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index c15c51bea26d..69266b8ea2ad 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -261,6 +261,7 @@ enum {
 	CXT_FIXUP_HP_530,
 	CXT_FIXUP_CAP_MIX_AMP_5047,
 	CXT_FIXUP_MUTE_LED_EAPD,
+	CXT_FIXUP_HP_DOCK,
 	CXT_FIXUP_HP_SPECTRE,
 	CXT_FIXUP_HP_GATE_MIC,
 };
@@ -778,6 +779,14 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_mute_led_eapd,
 	},
+	[CXT_FIXUP_HP_DOCK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x16, 0x21011020 }, /* line-out */
+			{ 0x18, 0x2181103f }, /* line-in */
+			{ }
+		}
+	},
 	[CXT_FIXUP_HP_SPECTRE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -839,6 +848,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
+	SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
@@ -871,6 +881,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
 	{ .id = CXT_PINCFG_LEMOTE_A1205, .name = "lemote-a1205" },
 	{ .id = CXT_FIXUP_OLPC_XO, .name = "olpc-xo" },
 	{ .id = CXT_FIXUP_MUTE_LED_EAPD, .name = "mute-led-eapd" },
+	{ .id = CXT_FIXUP_HP_DOCK, .name = "hp-dock" },
 	{}
 };
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4e112221d825..299835d1fbaa 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4847,6 +4847,7 @@ enum {
 	ALC286_FIXUP_HP_GPIO_LED,
 	ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY,
 	ALC280_FIXUP_HP_DOCK_PINS,
+	ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED,
 	ALC280_FIXUP_HP_9480M,
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -4857,6 +4858,7 @@ enum {
 	ALC292_FIXUP_DISABLE_AAMIX,
 	ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK,
 	ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	ALC275_FIXUP_DELL_XPS,
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
@@ -5388,6 +5390,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC280_FIXUP_HP_GPIO4
 	},
+	[ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1b, 0x21011020 }, /* line-out */
+			{ 0x18, 0x2181103f }, /* line-in */
+			{ },
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HP_GPIO_MIC1_LED
+	},
 	[ALC280_FIXUP_HP_9480M] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc280_fixup_hp_9480m,
@@ -5459,6 +5471,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
+	[ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE
+	},
 	[ALC275_FIXUP_DELL_XPS] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -5531,7 +5552,7 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc298_fixup_speaker_volume,
 		.chained = true,
-		.chain_id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
+		.chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	},
 	[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
 		.type = HDA_FIXUP_PINS,
@@ -5647,7 +5668,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2256, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2257, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2259, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
+	SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -5816,6 +5837,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"},
 	{.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"},
 	{.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
+	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
 	{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
 	{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
 	{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
@@ -6090,6 +6112,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		ALC295_STANDARD_PINS,
 		{0x17, 0x21014040},
 		{0x18, 0x21a19050}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC295_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x17, 0x90170110}),
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index ec1067a679da..08b1399d1da2 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -89,7 +89,7 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg)
 	writel(val, acp_mmio + (reg * 4));
 }
 
-/* Configure a given dma channel parameters - enable/disble,
+/* Configure a given dma channel parameters - enable/disable,
  * number of descriptors, priority
  */
 static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num,
diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c
index 89ac5f5a93eb..7ae46c2647d4 100644
--- a/sound/soc/atmel/atmel-classd.c
+++ b/sound/soc/atmel/atmel-classd.c
@@ -349,7 +349,7 @@ static int atmel_classd_codec_dai_digital_mute(struct snd_soc_dai *codec_dai,
 }
 
 #define CLASSD_ACLK_RATE_11M2896_MPY_8 (112896 * 100 * 8)
-#define CLASSD_ACLK_RATE_12M288_MPY_8  (12228 * 1000 * 8)
+#define CLASSD_ACLK_RATE_12M288_MPY_8  (12288 * 1000 * 8)
 
 static struct {
 	int rate;
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 78fca8acd3ec..fd272a40485b 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1534,21 +1534,20 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 			pin->mst_capable = false;
 			/* if not MST, default is port[0] */
 			hport = &pin->ports[0];
-			goto out;
 		} else {
 			for (i = 0; i < pin->num_ports; i++) {
 				pin->mst_capable = true;
 				if (pin->ports[i].id == pipe) {
 					hport = &pin->ports[i];
-					goto out;
+					break;
 				}
 			}
 		}
+
+		if (hport)
+			hdac_hdmi_present_sense(pin, hport);
 	}
 
-out:
-	if (pin && hport)
-		hdac_hdmi_present_sense(pin, hport);
 }
 
 static struct i915_audio_component_audio_ops aops = {
@@ -1998,7 +1997,7 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
 	struct hdac_hdmi_pin *pin, *pin_next;
 	struct hdac_hdmi_cvt *cvt, *cvt_next;
 	struct hdac_hdmi_pcm *pcm, *pcm_next;
-	struct hdac_hdmi_port *port;
+	struct hdac_hdmi_port *port, *port_next;
 	int i;
 
 	snd_soc_unregister_codec(&edev->hdac.dev);
@@ -2008,8 +2007,9 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
 		if (list_empty(&pcm->port_list))
 			continue;
 
-		list_for_each_entry(port, &pcm->port_list, head)
-			port = NULL;
+		list_for_each_entry_safe(port, port_next,
+					&pcm->port_list, head)
+			list_del(&port->head);
 
 		list_del(&pcm->head);
 		kfree(pcm);
diff --git a/sound/soc/codecs/rt5665.c b/sound/soc/codecs/rt5665.c
index 324461e985b3..476135ec5726 100644
--- a/sound/soc/codecs/rt5665.c
+++ b/sound/soc/codecs/rt5665.c
@@ -1241,7 +1241,7 @@ static irqreturn_t rt5665_irq(int irq, void *data)
 static void rt5665_jd_check_handler(struct work_struct *work)
 {
 	struct rt5665_priv *rt5665 = container_of(work, struct rt5665_priv,
-		calibrate_work.work);
+		jd_check_work.work);
 
 	if (snd_soc_read(rt5665->codec, RT5665_AJD1_CTRL) & 0x0010) {
 		/* jack out */
@@ -2252,7 +2252,7 @@ static const char * const rt5665_if2_1_adc_in_src[] = {
 
 static const SOC_ENUM_SINGLE_DECL(
 	rt5665_if2_1_adc_in_enum, RT5665_DIG_INF2_DATA,
-	RT5665_IF3_ADC_IN_SFT, rt5665_if2_1_adc_in_src);
+	RT5665_IF2_1_ADC_IN_SFT, rt5665_if2_1_adc_in_src);
 
 static const struct snd_kcontrol_new rt5665_if2_1_adc_in_mux =
 	SOC_DAPM_ENUM("IF2_1 ADC IN Source", rt5665_if2_1_adc_in_enum);
@@ -3178,6 +3178,9 @@ static const struct snd_soc_dapm_route rt5665_dapm_routes[] = {
 	{"DAC Mono Right Filter", NULL, "DAC Mono R ASRC", is_using_asrc},
 	{"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc},
 	{"DAC Stereo2 Filter", NULL, "DAC STO2 ASRC", is_using_asrc},
+	{"I2S1 ASRC", NULL, "CLKDET"},
+	{"I2S2 ASRC", NULL, "CLKDET"},
+	{"I2S3 ASRC", NULL, "CLKDET"},
 
 	/*Vref*/
 	{"Mic Det Power", NULL, "Vref2"},
@@ -3912,6 +3915,7 @@ static const struct snd_soc_dapm_route rt5665_dapm_routes[] = {
 	{"Mono MIX", "MONOVOL Switch", "MONOVOL"},
 	{"Mono Amp", NULL, "Mono MIX"},
 	{"Mono Amp", NULL, "Vref2"},
+	{"Mono Amp", NULL, "Vref3"},
 	{"Mono Amp", NULL, "CLKDET SYS"},
 	{"Mono Amp", NULL, "CLKDET MONO"},
 	{"Mono Playback", "Switch", "Mono Amp"},
@@ -4798,7 +4802,7 @@ static int rt5665_i2c_probe(struct i2c_client *i2c,
 	/* Enhance performance*/
 	regmap_update_bits(rt5665->regmap, RT5665_PWR_ANLG_1,
 		RT5665_HP_DRIVER_MASK | RT5665_LDO1_DVO_MASK,
-		RT5665_HP_DRIVER_5X | RT5665_LDO1_DVO_09);
+		RT5665_HP_DRIVER_5X | RT5665_LDO1_DVO_12);
 
 	INIT_DELAYED_WORK(&rt5665->jack_detect_work,
 				rt5665_jack_detect_handler);
diff --git a/sound/soc/codecs/rt5665.h b/sound/soc/codecs/rt5665.h
index 12f7080a0d3c..a30f5e6d0628 100644
--- a/sound/soc/codecs/rt5665.h
+++ b/sound/soc/codecs/rt5665.h
@@ -1106,7 +1106,7 @@
 #define RT5665_HP_DRIVER_MASK			(0x3 << 2)
 #define RT5665_HP_DRIVER_1X			(0x0 << 2)
 #define RT5665_HP_DRIVER_3X			(0x1 << 2)
-#define RT5665_HP_DRIVER_5X			(0x2 << 2)
+#define RT5665_HP_DRIVER_5X			(0x3 << 2)
 #define RT5665_LDO1_DVO_MASK			(0x3)
 #define RT5665_LDO1_DVO_09			(0x0)
 #define RT5665_LDO1_DVO_10			(0x1)
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index d151224ffcca..bbdb72f73df1 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -899,7 +899,10 @@ static int wm_coeff_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&ctl->dsp->pwr_lock);
 
-	memcpy(ctl->cache, p, ctl->len);
+	if (ctl->flags & WMFW_CTL_FLAG_VOLATILE)
+		ret = -EPERM;
+	else
+		memcpy(ctl->cache, p, ctl->len);
 
 	ctl->set = 1;
 	if (ctl->enabled && ctl->dsp->running)
@@ -926,6 +929,8 @@ static int wm_coeff_tlv_put(struct snd_kcontrol *kctl,
 		ctl->set = 1;
 		if (ctl->enabled && ctl->dsp->running)
 			ret = wm_coeff_write_control(ctl, ctl->cache, size);
+		else if (ctl->flags & WMFW_CTL_FLAG_VOLATILE)
+			ret = -EPERM;
 	}
 
 	mutex_unlock(&ctl->dsp->pwr_lock);
@@ -947,7 +952,7 @@ static int wm_coeff_put_acked(struct snd_kcontrol *kctl,
 
 	mutex_lock(&ctl->dsp->pwr_lock);
 
-	if (ctl->enabled)
+	if (ctl->enabled && ctl->dsp->running)
 		ret = wm_coeff_write_acked_control(ctl, val);
 	else
 		ret = -EPERM;
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 4924575d2e95..343b291fc372 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -115,6 +115,7 @@ int asoc_simple_card_parse_clk(struct device *dev,
 	clk = devm_get_clk_from_child(dev, node, NULL);
 	if (!IS_ERR(clk)) {
 		simple_dai->sysclk = clk_get_rate(clk);
+		simple_dai->clk = clk;
 	} else if (!of_property_read_u32(node, "system-clock-frequency", &val)) {
 		simple_dai->sysclk = val;
 	} else {
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 5c7219fb3aa8..9e2a3404a836 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -621,7 +621,7 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = {
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
+		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
@@ -634,7 +634,6 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = {
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
 		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,
@@ -661,6 +660,7 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = {
 						| SND_SOC_DAIFMT_CBS_CFS,
 		.be_hw_params_fixup = byt_rt5640_codec_fixup,
 		.ignore_suspend = 1,
+		.nonatomic = true,
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
 		.init = byt_rt5640_init,
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 3186f015939f..8164bec63bf1 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -235,7 +235,6 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = {
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
 		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,
@@ -249,7 +248,6 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = {
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
 		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index ed58b5b3555a..2dbfb1b24ef4 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -512,7 +512,7 @@ static int skl_tplg_set_module_init_data(struct snd_soc_dapm_widget *w)
 			if (bc->set_params != SKL_PARAM_INIT)
 				continue;
 
-			mconfig->formats_config.caps = (u32 *)&bc->params;
+			mconfig->formats_config.caps = (u32 *)bc->params;
 			mconfig->formats_config.caps_size = bc->size;
 
 			break;
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 05cf809cf9e1..d7013bde6f45 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -13,7 +13,7 @@ config SND_SOC_MT2701
 
 config SND_SOC_MT2701_CS42448
 	tristate "ASoc Audio driver for MT2701 with CS42448 codec"
-	depends on SND_SOC_MT2701
+	depends on SND_SOC_MT2701 && I2C
 	select SND_SOC_CS42XX8_I2C
 	select SND_SOC_BT_SCO
 	help
diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index abb5eaac854a..7d92a24b7cfa 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -31,23 +31,24 @@ static int rsnd_cmd_init(struct rsnd_mod *mod,
 	struct rsnd_mod *mix = rsnd_io_to_mod_mix(io);
 	struct device *dev = rsnd_priv_to_dev(priv);
 	u32 data;
+	u32 path[] = {
+		[1] = 1 << 0,
+		[5] = 1 << 8,
+		[6] = 1 << 12,
+		[9] = 1 << 15,
+	};
 
 	if (!mix && !dvc)
 		return 0;
 
+	if (ARRAY_SIZE(path) < rsnd_mod_id(mod) + 1)
+		return -ENXIO;
+
 	if (mix) {
 		struct rsnd_dai *rdai;
 		struct rsnd_mod *src;
 		struct rsnd_dai_stream *tio;
 		int i;
-		u32 path[] = {
-			[0] = 0,
-			[1] = 1 << 0,
-			[2] = 0,
-			[3] = 0,
-			[4] = 0,
-			[5] = 1 << 8
-		};
 
 		/*
 		 * it is assuming that integrater is well understanding about
@@ -70,16 +71,19 @@ static int rsnd_cmd_init(struct rsnd_mod *mod,
 	} else {
 		struct rsnd_mod *src = rsnd_io_to_mod_src(io);
 
-		u32 path[] = {
-			[0] = 0x30000,
-			[1] = 0x30001,
-			[2] = 0x40000,
-			[3] = 0x10000,
-			[4] = 0x20000,
-			[5] = 0x40100
+		u8 cmd_case[] = {
+			[0] = 0x3,
+			[1] = 0x3,
+			[2] = 0x4,
+			[3] = 0x1,
+			[4] = 0x2,
+			[5] = 0x4,
+			[6] = 0x1,
+			[9] = 0x2,
 		};
 
-		data = path[rsnd_mod_id(src)];
+		data = path[rsnd_mod_id(src)] |
+			cmd_case[rsnd_mod_id(src)] << 16;
 	}
 
 	dev_dbg(dev, "ctu/mix path = 0x%08x", data);
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 1f405c833867..241cb3b08a07 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -454,6 +454,20 @@ static u32 rsnd_dmapp_read(struct rsnd_dma *dma, u32 reg)
 	return ioread32(rsnd_dmapp_addr(dmac, dma, reg));
 }
 
+static void rsnd_dmapp_bset(struct rsnd_dma *dma, u32 data, u32 mask, u32 reg)
+{
+	struct rsnd_mod *mod = rsnd_mod_get(dma);
+	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
+	struct rsnd_dma_ctrl *dmac = rsnd_priv_to_dmac(priv);
+	void __iomem *addr = rsnd_dmapp_addr(dmac, dma, reg);
+	u32 val = ioread32(addr);
+
+	val &= ~mask;
+	val |= (data & mask);
+
+	iowrite32(val, addr);
+}
+
 static int rsnd_dmapp_stop(struct rsnd_mod *mod,
 			   struct rsnd_dai_stream *io,
 			   struct rsnd_priv *priv)
@@ -461,10 +475,10 @@ static int rsnd_dmapp_stop(struct rsnd_mod *mod,
 	struct rsnd_dma *dma = rsnd_mod_to_dma(mod);
 	int i;
 
-	rsnd_dmapp_write(dma, 0, PDMACHCR);
+	rsnd_dmapp_bset(dma, 0,  PDMACHCR_DE, PDMACHCR);
 
 	for (i = 0; i < 1024; i++) {
-		if (0 == rsnd_dmapp_read(dma, PDMACHCR))
+		if (0 == (rsnd_dmapp_read(dma, PDMACHCR) & PDMACHCR_DE))
 			return 0;
 		udelay(1);
 	}
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 4e817c8a18c0..14fafdaf1395 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -64,7 +64,11 @@ static int rsnd_ssiu_init(struct rsnd_mod *mod,
 	mask1 = (1 << 4) | (1 << 20);	/* mask sync bit */
 	mask2 = (1 << 4);		/* mask sync bit */
 	val1  = val2  = 0;
-	if (rsnd_ssi_is_pin_sharing(io)) {
+	if (id == 8) {
+		/*
+		 * SSI8 pin is sharing with SSI7, nothing to do.
+		 */
+	} else if (rsnd_ssi_is_pin_sharing(io)) {
 		int shift = -1;
 
 		switch (id) {
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 6dca408faae3..2722bb0c5573 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3326,7 +3326,10 @@ static int snd_soc_platform_drv_pcm_new(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_platform *platform = rtd->platform;
 
-	return platform->driver->pcm_new(rtd);
+	if (platform->driver->pcm_new)
+		return platform->driver->pcm_new(rtd);
+	else
+		return 0;
 }
 
 static void snd_soc_platform_drv_pcm_free(struct snd_pcm *pcm)
@@ -3334,7 +3337,8 @@ static void snd_soc_platform_drv_pcm_free(struct snd_pcm *pcm)
 	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
 	struct snd_soc_platform *platform = rtd->platform;
 
-	platform->driver->pcm_free(pcm);
+	if (platform->driver->pcm_free)
+		platform->driver->pcm_free(pcm);
 }
 
 /**
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 3e9b1c0bb1ce..058bc99c6c34 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -933,6 +933,7 @@ static int soc_tplg_denum_create_texts(struct soc_enum *se,
 		}
 	}
 
+	se->texts = (const char * const *)se->dobj.control.dtexts;
 	return 0;
 
 err:
diff --git a/sound/soc/sti/uniperif.h b/sound/soc/sti/uniperif.h
index d487dd2ef016..cfcb0ea9d99d 100644
--- a/sound/soc/sti/uniperif.h
+++ b/sound/soc/sti/uniperif.h
@@ -1299,6 +1299,7 @@ struct uniperif {
 	int ver; /* IP version, used by register access macros */
 	struct regmap_field *clk_sel;
 	struct regmap_field *valid_sel;
+	spinlock_t irq_lock; /* use to prevent race condition with IRQ */
 
 	/* capabilities */
 	const struct snd_pcm_hardware *hw;
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 60ae31a303ab..d7e8dd46d2cc 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -65,10 +65,13 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 	unsigned int status;
 	unsigned int tmp;
 
-	if (player->state == UNIPERIF_STATE_STOPPED) {
-		/* Unexpected IRQ: do nothing */
-		return IRQ_NONE;
-	}
+	spin_lock(&player->irq_lock);
+	if (!player->substream)
+		goto irq_spin_unlock;
+
+	snd_pcm_stream_lock(player->substream);
+	if (player->state == UNIPERIF_STATE_STOPPED)
+		goto stream_unlock;
 
 	/* Get interrupt status & clear them immediately */
 	status = GET_UNIPERIF_ITS(player);
@@ -88,9 +91,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 			SET_UNIPERIF_ITM_BCLR_FIFO_ERROR(player);
 
 			/* Stop the player */
-			snd_pcm_stream_lock(player->substream);
 			snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock(player->substream);
 		}
 
 		ret = IRQ_HANDLED;
@@ -104,9 +105,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		SET_UNIPERIF_ITM_BCLR_DMA_ERROR(player);
 
 		/* Stop the player */
-		snd_pcm_stream_lock(player->substream);
 		snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(player->substream);
 
 		ret = IRQ_HANDLED;
 	}
@@ -116,7 +115,8 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		if (!player->underflow_enabled) {
 			dev_err(player->dev,
 				"unexpected Underflow recovering\n");
-			return -EPERM;
+			ret = -EPERM;
+			goto stream_unlock;
 		}
 		/* Read the underflow recovery duration */
 		tmp = GET_UNIPERIF_STATUS_1_UNDERFLOW_DURATION(player);
@@ -138,13 +138,16 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		dev_err(player->dev, "Underflow recovery failed\n");
 
 		/* Stop the player */
-		snd_pcm_stream_lock(player->substream);
 		snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(player->substream);
 
 		ret = IRQ_HANDLED;
 	}
 
+stream_unlock:
+	snd_pcm_stream_unlock(player->substream);
+irq_spin_unlock:
+	spin_unlock(&player->irq_lock);
+
 	return ret;
 }
 
@@ -588,6 +591,7 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
 	struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
 	struct uniperif *player = priv->dai_data.uni;
 	struct snd_aes_iec958 *iec958 =  &player->stream_settings.iec958;
+	unsigned long flags;
 
 	mutex_lock(&player->ctrl_lock);
 	iec958->status[0] = ucontrol->value.iec958.status[0];
@@ -596,12 +600,14 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
 	iec958->status[3] = ucontrol->value.iec958.status[3];
 	mutex_unlock(&player->ctrl_lock);
 
+	spin_lock_irqsave(&player->irq_lock, flags);
 	if (player->substream && player->substream->runtime)
 		uni_player_set_channel_status(player,
 					      player->substream->runtime);
 	else
 		uni_player_set_channel_status(player, NULL);
 
+	spin_unlock_irqrestore(&player->irq_lock, flags);
 	return 0;
 }
 
@@ -686,9 +692,12 @@ static int uni_player_startup(struct snd_pcm_substream *substream,
 {
 	struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
 	struct uniperif *player = priv->dai_data.uni;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&player->irq_lock, flags);
 	player->substream = substream;
+	spin_unlock_irqrestore(&player->irq_lock, flags);
 
 	player->clk_adj = 0;
 
@@ -986,12 +995,15 @@ static void uni_player_shutdown(struct snd_pcm_substream *substream,
 {
 	struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
 	struct uniperif *player = priv->dai_data.uni;
+	unsigned long flags;
 
+	spin_lock_irqsave(&player->irq_lock, flags);
 	if (player->state != UNIPERIF_STATE_STOPPED)
 		/* Stop the player */
 		uni_player_stop(player);
 
 	player->substream = NULL;
+	spin_unlock_irqrestore(&player->irq_lock, flags);
 }
 
 static int uni_player_parse_dt_audio_glue(struct platform_device *pdev,
@@ -1096,6 +1108,7 @@ int uni_player_init(struct platform_device *pdev,
 	}
 
 	mutex_init(&player->ctrl_lock);
+	spin_lock_init(&player->irq_lock);
 
 	/* Ensure that disabled by default */
 	SET_UNIPERIF_CONFIG_BACK_STALL_REQ_DISABLE(player);
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index 5992c6ab3833..ee0055e60852 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -46,10 +46,15 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id)
 	struct uniperif *reader = dev_id;
 	unsigned int status;
 
+	spin_lock(&reader->irq_lock);
+	if (!reader->substream)
+		goto irq_spin_unlock;
+
+	snd_pcm_stream_lock(reader->substream);
 	if (reader->state == UNIPERIF_STATE_STOPPED) {
 		/* Unexpected IRQ: do nothing */
 		dev_warn(reader->dev, "unexpected IRQ\n");
-		return IRQ_HANDLED;
+		goto stream_unlock;
 	}
 
 	/* Get interrupt status & clear them immediately */
@@ -60,13 +65,16 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id)
 	if (unlikely(status & UNIPERIF_ITS_FIFO_ERROR_MASK(reader))) {
 		dev_err(reader->dev, "FIFO error detected\n");
 
-		snd_pcm_stream_lock(reader->substream);
 		snd_pcm_stop(reader->substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(reader->substream);
 
-		return IRQ_HANDLED;
+		ret = IRQ_HANDLED;
 	}
 
+stream_unlock:
+	snd_pcm_stream_unlock(reader->substream);
+irq_spin_unlock:
+	spin_unlock(&reader->irq_lock);
+
 	return ret;
 }
 
@@ -347,8 +355,13 @@ static int uni_reader_startup(struct snd_pcm_substream *substream,
 {
 	struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
 	struct uniperif *reader = priv->dai_data.uni;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&reader->irq_lock, flags);
+	reader->substream = substream;
+	spin_unlock_irqrestore(&reader->irq_lock, flags);
+
 	if (!UNIPERIF_TYPE_IS_TDM(reader))
 		return 0;
 
@@ -373,11 +386,15 @@ static void uni_reader_shutdown(struct snd_pcm_substream *substream,
 {
 	struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
 	struct uniperif *reader = priv->dai_data.uni;
+	unsigned long flags;
 
+	spin_lock_irqsave(&reader->irq_lock, flags);
 	if (reader->state != UNIPERIF_STATE_STOPPED) {
 		/* Stop the reader */
 		uni_reader_stop(reader);
 	}
+	reader->substream = NULL;
+	spin_unlock_irqrestore(&reader->irq_lock, flags);
 }
 
 static const struct snd_soc_dai_ops uni_reader_dai_ops = {
@@ -412,6 +429,8 @@ int uni_reader_init(struct platform_device *pdev,
 		return -EBUSY;
 	}
 
+	spin_lock_init(&reader->irq_lock);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(uni_reader_init);
diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c
index b92bdc8361af..7527ba29a5a0 100644
--- a/sound/soc/sunxi/sun8i-codec.c
+++ b/sound/soc/sunxi/sun8i-codec.c
@@ -259,25 +259,20 @@ static int sun8i_codec_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static const struct snd_kcontrol_new sun8i_output_left_mixer_controls[] = {
-	SOC_DAPM_SINGLE("LSlot 0", SUN8I_DAC_MXR_SRC,
-			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA0L, 1, 0),
-	SOC_DAPM_SINGLE("LSlot 1", SUN8I_DAC_MXR_SRC,
-			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA1L, 1, 0),
-	SOC_DAPM_SINGLE("DACL", SUN8I_DAC_MXR_SRC,
-			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF2DACL, 1, 0),
-	SOC_DAPM_SINGLE("ADCL", SUN8I_DAC_MXR_SRC,
-			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_ADCL, 1, 0),
-};
-
-static const struct snd_kcontrol_new sun8i_output_right_mixer_controls[] = {
-	SOC_DAPM_SINGLE("RSlot 0", SUN8I_DAC_MXR_SRC,
+static const struct snd_kcontrol_new sun8i_dac_mixer_controls[] = {
+	SOC_DAPM_DOUBLE("AIF1 Slot 0 Digital DAC Playback Switch",
+			SUN8I_DAC_MXR_SRC,
+			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA0L,
 			SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_AIF1DA0R, 1, 0),
-	SOC_DAPM_SINGLE("RSlot 1", SUN8I_DAC_MXR_SRC,
+	SOC_DAPM_DOUBLE("AIF1 Slot 1 Digital DAC Playback Switch",
+			SUN8I_DAC_MXR_SRC,
+			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA1L,
 			SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_AIF1DA1R, 1, 0),
-	SOC_DAPM_SINGLE("DACR", SUN8I_DAC_MXR_SRC,
+	SOC_DAPM_DOUBLE("AIF2 Digital DAC Playback Switch", SUN8I_DAC_MXR_SRC,
+			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF2DACL,
 			SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_AIF2DACR, 1, 0),
-	SOC_DAPM_SINGLE("ADCR", SUN8I_DAC_MXR_SRC,
+	SOC_DAPM_DOUBLE("ADC Digital DAC Playback Switch", SUN8I_DAC_MXR_SRC,
+			SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_ADCL,
 			SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_ADCR, 1, 0),
 };
 
@@ -286,19 +281,21 @@ static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = {
 	SND_SOC_DAPM_SUPPLY("DAC", SUN8I_DAC_DIG_CTRL, SUN8I_DAC_DIG_CTRL_ENDA,
 			    0, NULL, 0),
 
-	/* Analog DAC */
-	SND_SOC_DAPM_DAC("Digital Left DAC", "Playback", SUN8I_AIF1_DACDAT_CTRL,
-			 SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0L_ENA, 0),
-	SND_SOC_DAPM_DAC("Digital Right DAC", "Playback", SUN8I_AIF1_DACDAT_CTRL,
-			 SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0R_ENA, 0),
+	/* Analog DAC AIF */
+	SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Left", "Playback", 0,
+			    SUN8I_AIF1_DACDAT_CTRL,
+			    SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0L_ENA, 0),
+	SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Right", "Playback", 0,
+			    SUN8I_AIF1_DACDAT_CTRL,
+			    SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0R_ENA, 0),
 
 	/* DAC Mixers */
-	SND_SOC_DAPM_MIXER("Left DAC Mixer", SND_SOC_NOPM, 0, 0,
-			   sun8i_output_left_mixer_controls,
-			   ARRAY_SIZE(sun8i_output_left_mixer_controls)),
-	SND_SOC_DAPM_MIXER("Right DAC Mixer", SND_SOC_NOPM, 0, 0,
-			   sun8i_output_right_mixer_controls,
-			   ARRAY_SIZE(sun8i_output_right_mixer_controls)),
+	SND_SOC_DAPM_MIXER("Left Digital DAC Mixer", SND_SOC_NOPM, 0, 0,
+			   sun8i_dac_mixer_controls,
+			   ARRAY_SIZE(sun8i_dac_mixer_controls)),
+	SND_SOC_DAPM_MIXER("Right Digital DAC Mixer", SND_SOC_NOPM, 0, 0,
+			   sun8i_dac_mixer_controls,
+			   ARRAY_SIZE(sun8i_dac_mixer_controls)),
 
 	/* Clocks */
 	SND_SOC_DAPM_SUPPLY("MODCLK AFI1", SUN8I_MOD_CLK_ENA,
@@ -321,8 +318,6 @@ static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = {
 			    SUN8I_MOD_RST_CTL_AIF1, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("RST DAC", SUN8I_MOD_RST_CTL,
 			    SUN8I_MOD_RST_CTL_DAC, 0, NULL, 0),
-
-	SND_SOC_DAPM_OUTPUT("HP"),
 };
 
 static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = {
@@ -338,16 +333,14 @@ static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = {
 	{ "DAC", NULL, "MODCLK DAC" },
 
 	/* DAC Routes */
-	{ "Digital Left DAC", NULL, "DAC" },
-	{ "Digital Right DAC", NULL, "DAC" },
+	{ "AIF1 Slot 0 Right", NULL, "DAC" },
+	{ "AIF1 Slot 0 Left", NULL, "DAC" },
 
 	/* DAC Mixer Routes */
-	{ "Left DAC Mixer", "LSlot 0", "Digital Left DAC"},
-	{ "Right DAC Mixer", "RSlot 0", "Digital Right DAC"},
-
-	/* End of route : HP out */
-	{ "HP", NULL, "Left DAC Mixer" },
-	{ "HP", NULL, "Right DAC Mixer" },
+	{ "Left Digital DAC Mixer", "AIF1 Slot 0 Digital DAC Playback Switch",
+	  "AIF1 Slot 0 Left"},
+	{ "Right Digital DAC Mixer", "AIF1 Slot 0 Digital DAC Playback Switch",
+	  "AIF1 Slot 0 Right"},
 };
 
 static struct snd_soc_dai_ops sun8i_codec_dai_ops = {
diff --git a/sound/x86/Kconfig b/sound/x86/Kconfig
index 84c8f8fc597c..8adf4d1bd46e 100644
--- a/sound/x86/Kconfig
+++ b/sound/x86/Kconfig
@@ -1,6 +1,7 @@
 menuconfig SND_X86
-	tristate "X86 sound devices"
+	bool "X86 sound devices"
 	depends on X86
+	default y
 	---help---
 	  X86 sound devices that don't fall under SoC or PCI categories
 
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index af05f8e0903e..6ebd3e6a1fd1 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -181,10 +181,23 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
 #define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+			(0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define   KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 #define KVM_DEV_ARM_VGIC_GRP_CTRL       4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL	0
+
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
 
 /* KVM_IRQ_LINE irq field index values */
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 3051f86a9b5f..c2860358ae3e 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -201,10 +201,23 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
 #define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+			(0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define   KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 #define KVM_DEV_ARM_VGIC_GRP_CTRL	4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK	0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL	0
+
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
 
 /* Device Control API on vcpu fd */
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 3603b6f51b11..4edbe4bb0e8b 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -413,6 +413,26 @@ struct kvm_get_htab_header {
 	__u16	n_invalid;
 };
 
+/* For KVM_PPC_CONFIGURE_V3_MMU */
+struct kvm_ppc_mmuv3_cfg {
+	__u64	flags;
+	__u64	process_table;	/* second doubleword of partition table entry */
+};
+
+/* Flag values for KVM_PPC_CONFIGURE_V3_MMU */
+#define KVM_PPC_MMUV3_RADIX	1	/* 1 = radix mode, 0 = HPT */
+#define KVM_PPC_MMUV3_GTSE	2	/* global translation shootdown enb. */
+
+/* For KVM_PPC_GET_RMMU_INFO */
+struct kvm_ppc_rmmu_info {
+	struct kvm_ppc_radix_geom {
+		__u8	page_shift;
+		__u8	level_bits[4];
+		__u8	pad[3];
+	}	geometries[8];
+	__u32	ap_encodings[8];
+};
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 
@@ -613,5 +633,7 @@ struct kvm_get_htab_header {
 #define  KVM_XICS_LEVEL_SENSITIVE	(1ULL << 40)
 #define  KVM_XICS_MASKED		(1ULL << 41)
 #define  KVM_XICS_PENDING		(1ULL << 42)
+#define  KVM_XICS_PRESENTED		(1ULL << 43)
+#define  KVM_XICS_QUEUED		(1ULL << 44)
 
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
index 059e33e94260..328eeceec709 100644
--- a/tools/arch/x86/include/asm/atomic.h
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -7,6 +7,8 @@
 
 #define LOCK_PREFIX "\n\tlock; "
 
+#include <asm/cmpxchg.h>
+
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
@@ -62,4 +64,9 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
 
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	return cmpxchg(&v->counter, old, new);
+}
+
 #endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
diff --git a/tools/arch/x86/include/asm/cmpxchg.h b/tools/arch/x86/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..f5253260f3cc
--- /dev/null
+++ b/tools/arch/x86/include/asm/cmpxchg.h
@@ -0,0 +1,89 @@
+#ifndef TOOLS_ASM_X86_CMPXCHG_H
+#define TOOLS_ASM_X86_CMPXCHG_H
+
+#include <linux/compiler.h>
+
+/*
+ * Non-existant functions to indicate usage errors at link time
+ * (or compile-time if the compiler implements __compiletime_error().
+ */
+extern void __cmpxchg_wrong_size(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+/*
+ * Constants for operation sizes. On 32-bit, the 64-bit size it set to
+ * -1 because sizeof will never return -1, thereby making those switch
+ * case statements guaranteeed dead code which the compiler will
+ * eliminate, and allowing the "missing symbol in the default case" to
+ * indicate a usage error.
+ */
+#define __X86_CASE_B	1
+#define __X86_CASE_W	2
+#define __X86_CASE_L	4
+#ifdef __x86_64__
+#define __X86_CASE_Q	8
+#else
+#define	__X86_CASE_Q	-1		/* sizeof will never return -1 */
+#endif
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __raw_cmpxchg(ptr, old, new, size, lock)			\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	switch (size) {							\
+	case __X86_CASE_B:						\
+	{								\
+		volatile u8 *__ptr = (volatile u8 *)(ptr);		\
+		asm volatile(lock "cmpxchgb %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "q" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_W:						\
+	{								\
+		volatile u16 *__ptr = (volatile u16 *)(ptr);		\
+		asm volatile(lock "cmpxchgw %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "r" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_L:						\
+	{								\
+		volatile u32 *__ptr = (volatile u32 *)(ptr);		\
+		asm volatile(lock "cmpxchgl %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "r" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_Q:						\
+	{								\
+		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
+		asm volatile(lock "cmpxchgq %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "r" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	default:							\
+		__cmpxchg_wrong_size();					\
+	}								\
+	__ret;								\
+})
+
+#define __cmpxchg(ptr, old, new, size)					\
+	__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
+
+#define cmpxchg(ptr, old, new)						\
+	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
+
+
+#endif	/* TOOLS_ASM_X86_CMPXCHG_H */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 293149a1c6a1..0fe00446f9ca 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -100,7 +100,7 @@
 #define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
@@ -186,7 +186,8 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-
+#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
 #define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -289,7 +290,8 @@
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
 #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
+#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
@@ -321,5 +323,4 @@
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 49e6ebac7e73..98dcc112b363 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -286,7 +286,7 @@ ENDPROC(memcpy_mcsafe_unrolled)
 	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index e3fb5ecbdcb6..523911f316ce 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -63,6 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
+        sched_getcpu			\
         sdt
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index b564a2eea039..e35e4e5ad192 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -48,21 +48,22 @@ FILES=                                          \
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
-         test-jvmti.bin
+         test-jvmti.bin				\
+         test-sched_getcpu.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
-CC := $(CROSS_COMPILE)gcc -MD
-CXX := $(CROSS_COMPILE)g++ -MD
-PKG_CONFIG := $(CROSS_COMPILE)pkg-config
+CC ?= $(CROSS_COMPILE)gcc
+CXX ?= $(CROSS_COMPILE)g++
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 LLVM_CONFIG ?= llvm-config
 
 all: $(FILES)
 
-__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
+__BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
   BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
 
-__BUILDXX = $(CXX) $(CXXFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
+__BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
   BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1
 
 ###############################
@@ -91,6 +92,9 @@ $(OUTPUT)test-libelf.bin:
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 
+$(OUTPUT)test-sched_getcpu.bin:
+	$(BUILD)
+
 DWARFLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
 DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
@@ -171,7 +175,7 @@ $(OUTPUT)test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
 $(OUTPUT)test-libpython.bin:
-	$(BUILD)
+	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
 $(OUTPUT)test-libpython-version.bin:
 	$(BUILD)
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 699e43627397..cc6c7c01f4ca 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -117,6 +117,10 @@
 # include "test-pthread-attr-setaffinity-np.c"
 #undef main
 
+#define main main_test_sched_getcpu
+# include "test-sched_getcpu.c"
+#undef main
+
 # if 0
 /*
  * Disable libbabeltrace check for test-all, because the requested
@@ -182,6 +186,7 @@ int main(int argc, char *argv[])
 	main_test_get_cpuid();
 	main_test_bpf();
 	main_test_libcrypto();
+	main_test_sched_getcpu();
 	main_test_sdt();
 
 	return 0;
diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c
index e04ab89a1013..ebc6dceddb58 100644
--- a/tools/build/feature/test-bpf.c
+++ b/tools/build/feature/test-bpf.c
@@ -9,6 +9,9 @@
 #  define __NR_bpf 321
 # elif defined(__aarch64__)
 #  define __NR_bpf 280
+# elif defined(__sparc__)
+#  define __NR_bpf 349
+# else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif
 #endif
diff --git a/tools/build/feature/test-sched_getcpu.c b/tools/build/feature/test-sched_getcpu.c
new file mode 100644
index 000000000000..c4a148dd7104
--- /dev/null
+++ b/tools/build/feature/test-sched_getcpu.c
@@ -0,0 +1,7 @@
+#define _GNU_SOURCE
+#include <sched.h>
+
+int main(void)
+{
+	return sched_getcpu();
+}
diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh
index 4aa5369ffa4e..d85968cb1bf2 100755
--- a/tools/hv/bondvf.sh
+++ b/tools/hv/bondvf.sh
@@ -101,9 +101,25 @@ function create_bond_cfg_redhat {
 	echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn
 }
 
+function del_eth_cfg_ubuntu {
+	local fn=$cfgdir/interfaces
+	local tmpfl=$(mktemp)
+
+	local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1
+	local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)'
+
+	awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1"  $fn >$tmpfl
+
+	cp $tmpfl $fn
+
+	rm $tmpfl
+}
+
 function create_eth_cfg_ubuntu {
 	local fn=$cfgdir/interfaces
 
+	del_eth_cfg_ubuntu $1
+
 	echo $'\n'auto $1 >>$fn
 	echo iface $1 inet manual >>$fn
 	echo bond-master $2 >>$fn
@@ -119,6 +135,8 @@ function create_eth_cfg_pri_ubuntu {
 function create_bond_cfg_ubuntu {
 	local fn=$cfgdir/interfaces
 
+	del_eth_cfg_ubuntu $1
+
 	echo $'\n'auto $1 >>$fn
 	echo iface $1 inet dhcp >>$fn
 	echo bond-mode active-backup >>$fn
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
index 2ba78c9f5701..5e9738f97bf3 100644
--- a/tools/include/asm-generic/atomic-gcc.h
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -60,4 +60,12 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	return __sync_sub_and_fetch(&v->counter, 1) == 0;
 }
 
+#define cmpxchg(ptr, oldval, newval) \
+	__sync_val_compare_and_swap(ptr, oldval, newval)
+
+static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval)
+{
+	return cmpxchg(&(v)->counter, oldval, newval);
+}
+
 #endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
index 4e3d3d18ebab..9f21fc2b092b 100644
--- a/tools/include/linux/atomic.h
+++ b/tools/include/linux/atomic.h
@@ -3,4 +3,10 @@
 
 #include <asm/atomic.h>
 
+/* atomic_cmpxchg_relaxed */
+#ifndef atomic_cmpxchg_relaxed
+#define  atomic_cmpxchg_relaxed		atomic_cmpxchg
+#define  atomic_cmpxchg_release         atomic_cmpxchg
+#endif /* atomic_cmpxchg_relaxed */
+
 #endif /* __TOOLS_LINUX_ATOMIC_H */
diff --git a/tools/include/linux/bug.h b/tools/include/linux/bug.h
new file mode 100644
index 000000000000..8e4a4f49135d
--- /dev/null
+++ b/tools/include/linux/bug.h
@@ -0,0 +1,10 @@
+#ifndef _TOOLS_PERF_LINUX_BUG_H
+#define _TOOLS_PERF_LINUX_BUG_H
+
+/* Force a compilation error if condition is true, but also produce a
+   result (of value 0 and type size_t), so the expression can be used
+   e.g. in a structure initializer (or where-ever else comma expressions
+   aren't permitted). */
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
+#endif	/* _TOOLS_PERF_LINUX_BUG_H */
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 48af2f10a42d..825d44f89a29 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -12,3 +12,10 @@
 #if GCC_VERSION >= 70000 && !defined(__CHECKER__)
 # define __fallthrough __attribute__ ((fallthrough))
 #endif
+
+#if GCC_VERSION >= 40300
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* GCC_VERSION >= 40300 */
+
+/* &a[0] degrades to a pointer: a different type from an array */
+#define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 8de163b17c0d..23299d7e7160 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -5,6 +5,10 @@
 #include <linux/compiler-gcc.h>
 #endif
 
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
 /* Optimization barrier */
 /* The "volatile" is due to gcc bugs */
 #define barrier() __asm__ __volatile__("": : :"memory")
@@ -13,6 +17,11 @@
 # define __always_inline	inline __attribute__((always_inline))
 #endif
 
+/* Are two types/vars the same type (ignoring qualifiers)? */
+#ifndef __same_type
+# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
+#endif
+
 #ifdef __ANDROID__
 /*
  * FIXME: Big hammer to get rid of tons of:
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 122153b16ea4..390d7c9685fd 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -168,6 +168,16 @@
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
 #define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
diff --git a/tools/include/linux/hashtable.h b/tools/include/linux/hashtable.h
index c65cc0aa2659..251eabf2a05e 100644
--- a/tools/include/linux/hashtable.h
+++ b/tools/include/linux/hashtable.h
@@ -13,10 +13,6 @@
 #include <linux/hash.h>
 #include <linux/log2.h>
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 #define DEFINE_HASHTABLE(name, bits)						\
 	struct hlist_head name[1 << (bits)] =					\
 			{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 28607db02bd3..73ccc48126bb 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -4,6 +4,11 @@
 #include <stdarg.h>
 #include <stddef.h>
 #include <assert.h>
+#include <linux/compiler.h>
+
+#ifndef UINT_MAX
+#define UINT_MAX	(~0U)
+#endif
 
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 
@@ -72,6 +77,8 @@
 int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
 int scnprintf(char * buf, size_t size, const char * fmt, ...);
 
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+
 /*
  * This looks more complex than it should be. But we need to
  * get the type for the ~ right in round_down (it needs to be
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
index d5677d39c1e4..0325cefc2220 100644
--- a/tools/include/linux/log2.h
+++ b/tools/include/linux/log2.h
@@ -12,6 +12,9 @@
 #ifndef _TOOLS_LINUX_LOG2_H
 #define _TOOLS_LINUX_LOG2_H
 
+#include <linux/bitops.h>
+#include <linux/types.h>
+
 /*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h
new file mode 100644
index 000000000000..a0177c1f55b1
--- /dev/null
+++ b/tools/include/linux/refcount.h
@@ -0,0 +1,151 @@
+#ifndef _TOOLS_LINUX_REFCOUNT_H
+#define _TOOLS_LINUX_REFCOUNT_H
+
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+
+#ifdef NDEBUG
+#define REFCOUNT_WARN(cond, str) (void)(cond)
+#define __refcount_check
+#else
+#define REFCOUNT_WARN(cond, str) BUG_ON(cond)
+#define __refcount_check	__must_check
+#endif
+
+typedef struct refcount_struct {
+	atomic_t refs;
+} refcount_t;
+
+#define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
+
+static inline void refcount_set(refcount_t *r, unsigned int n)
+{
+	atomic_set(&r->refs, n);
+}
+
+static inline unsigned int refcount_read(const refcount_t *r)
+{
+	return atomic_read(&r->refs);
+}
+
+/*
+ * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_inc_not_zero(refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		new = val + 1;
+
+		if (!val)
+			return false;
+
+		if (unlikely(!new))
+			return true;
+
+		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+/*
+ * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object, will WARN when this is not so.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+	REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (unlikely(val == UINT_MAX))
+			return false;
+
+		new = val - i;
+		if (new > val) {
+			REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			return false;
+		}
+
+		old = atomic_cmpxchg_release(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	return !new;
+}
+
+static inline __refcount_check
+bool refcount_dec_and_test(refcount_t *r)
+{
+	return refcount_sub_and_test(1, r);
+}
+
+
+#endif /* _ATOMIC_LINUX_REFCOUNT_H */
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index c24b3e3ae296..77a28a26a670 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -7,6 +7,7 @@
 
 #define __SANE_USERSPACE_TYPES__	/* For PPC64, to get LL64 types */
 #include <asm/types.h>
+#include <asm/posix_types.h>
 
 struct page;
 struct kmem_cache;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0539a0ceef38..e553529929f6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -81,6 +81,7 @@ enum bpf_cmd {
 	BPF_OBJ_GET,
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
+	BPF_PROG_TEST_RUN,
 };
 
 enum bpf_map_type {
@@ -96,6 +97,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_LRU_HASH,
 	BPF_MAP_TYPE_LRU_PERCPU_HASH,
 	BPF_MAP_TYPE_LPM_TRIE,
+	BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	BPF_MAP_TYPE_HASH_OF_MAPS,
 };
 
 enum bpf_prog_type {
@@ -152,6 +155,7 @@ union bpf_attr {
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
 		__u32	map_flags;	/* prealloc or not */
+		__u32	inner_map_fd;	/* fd pointing to the inner map */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -186,6 +190,17 @@ union bpf_attr {
 		__u32		attach_type;
 		__u32		attach_flags;
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+		__u32		prog_fd;
+		__u32		retval;
+		__u32		data_size_in;
+		__u32		data_size_out;
+		__aligned_u64	data_in;
+		__aligned_u64	data_out;
+		__u32		repeat;
+		__u32		duration;
+	} test;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -456,6 +471,18 @@ union bpf_attr {
  *     Return:
  *       > 0 length of the string including the trailing NUL on success
  *       < 0 error
+ *
+ * u64 bpf_get_socket_cookie(skb)
+ *     Get the cookie for the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ *     field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ *     Get the owner uid of the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: uid of the socket owner on success or 0 if the socket pointer
+ *     inside sk_buff is NULL
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -503,7 +530,9 @@ union bpf_attr {
 	FN(get_numa_node_id),		\
 	FN(skb_change_head),		\
 	FN(xdp_adjust_head),		\
-	FN(probe_read_str),
+	FN(probe_read_str),		\
+	FN(get_socket_cookie),		\
+	FN(get_socket_uid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -574,6 +603,7 @@ struct __sk_buff {
 	__u32 tc_classid;
 	__u32 data;
 	__u32 data_end;
+	__u32 napi_id;
 };
 
 struct bpf_tunnel_key {
diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
new file mode 100644
index 000000000000..067427259820
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -0,0 +1,18 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
+#define _UAPI__LINUX_BPF_PERF_EVENT_H__
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+struct bpf_perf_event_data {
+	struct pt_regs regs;
+	__u64 sample_period;
+};
+
+#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
new file mode 100644
index 000000000000..813afd6eee71
--- /dev/null
+++ b/tools/include/uapi/linux/fcntl.h
@@ -0,0 +1,72 @@
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+
+#define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS	0x00000001	/* File accessed */
+#define DN_MODIFY	0x00000002	/* File modified */
+#define DN_CREATE	0x00000004	/* File created */
+#define DN_DELETE	0x00000008	/* File removed */
+#define DN_RENAME	0x00000010	/* File renamed */
+#define DN_ATTRIB	0x00000020	/* File changed attibutes */
+#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
+
+#define AT_FDCWD		-100    /* Special value used to indicate
+                                           openat should use the current
+                                           working directory. */
+#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_REMOVEDIR		0x200   /* Remove directory instead of
+                                           unlinking file.  */
+#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
+#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
+
+#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index c66a485a24ac..d09a9cd021b1 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -344,7 +344,8 @@ struct perf_event_attr {
 				use_clockid    :  1, /* use @clockid for time fields */
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
-				__reserved_1   : 36;
+				namespaces     :  1, /* include namespaces data */
+				__reserved_1   : 35;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -610,6 +611,23 @@ struct perf_event_header {
 	__u16	size;
 };
 
+struct perf_ns_link_info {
+	__u64	dev;
+	__u64	ino;
+};
+
+enum {
+	NET_NS_INDEX		= 0,
+	UTS_NS_INDEX		= 1,
+	IPC_NS_INDEX		= 2,
+	PID_NS_INDEX		= 3,
+	USER_NS_INDEX		= 4,
+	MNT_NS_INDEX		= 5,
+	CGROUP_NS_INDEX		= 6,
+
+	NR_NAMESPACES,		/* number of available namespaces */
+};
+
 enum perf_event_type {
 
 	/*
@@ -862,6 +880,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 *	u64				nr_namespaces;
+	 *	{ u64				dev, inode; } [nr_namespaces];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_NAMESPACES			= 16,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -885,6 +915,7 @@ enum perf_callchain_context {
  */
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
+#define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
new file mode 100644
index 000000000000..d538897b8e08
--- /dev/null
+++ b/tools/include/uapi/linux/stat.h
@@ -0,0 +1,177 @@
+#ifndef _UAPI_LINUX_STAT_H
+#define _UAPI_LINUX_STAT_H
+
+#include <linux/types.h>
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#define S_IFMT  00170000
+#define S_IFSOCK 0140000
+#define S_IFLNK	 0120000
+#define S_IFREG  0100000
+#define S_IFBLK  0060000
+#define S_IFDIR  0040000
+#define S_IFCHR  0020000
+#define S_IFIFO  0010000
+#define S_ISUID  0004000
+#define S_ISGID  0002000
+#define S_ISVTX  0001000
+
+#define S_ISLNK(m)	(((m) & S_IFMT) == S_IFLNK)
+#define S_ISREG(m)	(((m) & S_IFMT) == S_IFREG)
+#define S_ISDIR(m)	(((m) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(m)	(((m) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(m)	(((m) & S_IFMT) == S_IFBLK)
+#define S_ISFIFO(m)	(((m) & S_IFMT) == S_IFIFO)
+#define S_ISSOCK(m)	(((m) & S_IFMT) == S_IFSOCK)
+
+#define S_IRWXU 00700
+#define S_IRUSR 00400
+#define S_IWUSR 00200
+#define S_IXUSR 00100
+
+#define S_IRWXG 00070
+#define S_IRGRP 00040
+#define S_IWGRP 00020
+#define S_IXGRP 00010
+
+#define S_IRWXO 00007
+#define S_IROTH 00004
+#define S_IWOTH 00002
+#define S_IXOTH 00001
+
+#endif
+
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
+ * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
+ *
+ * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
+ * either be both positive or both negative.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+	__s64	tv_sec;
+	__s32	tv_nsec;
+	__s32	__reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx().  What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ *   - the bit will be cleared, and
+ *
+ *   - the datum will be set to an appropriate fabricated value if one is
+ *     available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ *   - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ *   - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ *     set or if the datum is considered out of date, and
+ *
+ *   - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ *   effort, it will be filled in anyway, and the bit will be set upon return
+ *   (it might not be up to date, however, and no attempt will be made to
+ *   synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+	/* 0x00 */
+	__u32	stx_mask;	/* What results were written [uncond] */
+	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
+	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* 0x10 */
+	__u32	stx_nlink;	/* Number of hard links */
+	__u32	stx_uid;	/* User ID of owner */
+	__u32	stx_gid;	/* Group ID of owner */
+	__u16	stx_mode;	/* File mode */
+	__u16	__spare0[1];
+	/* 0x20 */
+	__u64	stx_ino;	/* Inode number */
+	__u64	stx_size;	/* File size */
+	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
+	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+	/* 0x40 */
+	struct statx_timestamp	stx_atime;	/* Last access time */
+	struct statx_timestamp	stx_btime;	/* File creation time */
+	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
+	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* 0x80 */
+	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_minor;
+	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+	__u32	stx_dev_minor;
+	/* 0x90 */
+	__u64	__spare2[14];	/* Spare space for future expansion */
+	/* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE		0x00000001U	/* Want/got stx_mode & S_IFMT */
+#define STATX_MODE		0x00000002U	/* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK		0x00000004U	/* Want/got stx_nlink */
+#define STATX_UID		0x00000008U	/* Want/got stx_uid */
+#define STATX_GID		0x00000010U	/* Want/got stx_gid */
+#define STATX_ATIME		0x00000020U	/* Want/got stx_atime */
+#define STATX_MTIME		0x00000040U	/* Want/got stx_mtime */
+#define STATX_CTIME		0x00000080U	/* Want/got stx_ctime */
+#define STATX_INO		0x00000100U	/* Want/got stx_ino */
+#define STATX_SIZE		0x00000200U	/* Want/got stx_size */
+#define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
+#define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
+#define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
+#define STATX_ALL		0x00000fffU	/* All currently supported flags */
+#define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
+
+/*
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * semantically.  Where possible, the numerical value is picked to correspond
+ * also.
+ */
+#define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
+
+#define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+
+
+#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 11c8d9bc762e..897cd6f3f687 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
 		/* Allow writing to any other BAR, or expansion ROM */
 		iowrite(portoff, val, mask, &d->config_words[reg]);
 		return true;
-		/* We let them overide latency timer and cacheline size */
+		/* We let them override latency timer and cacheline size */
 	} else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
 		/* Only let them change the first two fields. */
 		if (mask == 0xFFFFFFFF)
@@ -3339,7 +3339,7 @@ int main(int argc, char *argv[])
 	 * simple, single region.
 	 */
 	boot->e820_entries = 1;
-	boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM });
+	boot->e820_table[0] = ((struct e820_entry) { 0, mem, E820_TYPE_RAM });
 	/*
 	 * The boot header contains a command line pointer: we put the command
 	 * line after the boot header.
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 4b6bfc43cccf..809c7721cd24 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -439,6 +439,35 @@ int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
 	return filename__read_str(path, buf, sizep);
 }
 
+int sysfs__read_bool(const char *entry, bool *value)
+{
+	char *buf;
+	size_t size;
+	int ret;
+
+	ret = sysfs__read_str(entry, &buf, &size);
+	if (ret < 0)
+		return ret;
+
+	switch (buf[0]) {
+	case '1':
+	case 'y':
+	case 'Y':
+		*value = true;
+		break;
+	case '0':
+	case 'n':
+	case 'N':
+		*value = false;
+		break;
+	default:
+		ret = -1;
+	}
+
+	free(buf);
+
+	return ret;
+}
 int sysctl__read_int(const char *sysctl, int *value)
 {
 	char path[PATH_MAX];
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 6b332dc74498..956c21127d1e 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -37,4 +37,5 @@ int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
 int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
+int sysfs__read_bool(const char *entry, bool *value);
 #endif /* __API_FS__ */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index e2efddf10231..1f5300e56b44 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -132,7 +132,7 @@ else
   Q = @
 endif
 
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
 MAKEOVERRIDES=
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 207c2eeddab0..4fe444b8092e 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -37,6 +37,8 @@
 #  define __NR_bpf 321
 # elif defined(__aarch64__)
 #  define __NR_bpf 280
+# elif defined(__sparc__)
+#  define __NR_bpf 349
 # else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif
@@ -69,6 +71,23 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+			  int inner_map_fd, int max_entries, __u32 map_flags)
+{
+	union bpf_attr attr;
+
+	memset(&attr, '\0', sizeof(attr));
+
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = 4;
+	attr.inner_map_fd = inner_map_fd;
+	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
+
+	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		     size_t insns_cnt, const char *license,
 		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
@@ -192,3 +211,27 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
+
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+		      void *data_out, __u32 *size_out, __u32 *retval,
+		      __u32 *duration)
+{
+	union bpf_attr attr;
+	int ret;
+
+	bzero(&attr, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.data_in = ptr_to_u64(data);
+	attr.test.data_out = ptr_to_u64(data_out);
+	attr.test.data_size_in = size;
+	attr.test.repeat = repeat;
+
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	if (size_out)
+		*size_out = attr.test.data_size_out;
+	if (retval)
+		*retval = attr.test.retval;
+	if (duration)
+		*duration = attr.test.duration;
+	return ret;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 09c3dcac0496..edb4daeff7a5 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -26,6 +26,8 @@
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, __u32 map_flags);
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+			  int inner_map_fd, int max_entries, __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
@@ -45,6 +47,8 @@ int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
 		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+		      void *data_out, __u32 *size_out, __u32 *retval,
+		      __u32 *duration);
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ac6eb863b2a4..1a2c07eb7795 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1618,8 +1618,7 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n)
 	return fd;
 }
 
-static void bpf_program__set_type(struct bpf_program *prog,
-				  enum bpf_prog_type type)
+void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
 {
 	prog->type = type;
 }
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b30394f9947a..32c7252f734e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -25,6 +25,7 @@
 #include <stdint.h>
 #include <stdbool.h>
 #include <sys/types.h>  // for size_t
+#include <linux/bpf.h>
 
 enum libbpf_errno {
 	__LIBBPF_ERRNO__START = 4000,
@@ -185,6 +186,7 @@ int bpf_program__set_sched_cls(struct bpf_program *prog);
 int bpf_program__set_sched_act(struct bpf_program *prog);
 int bpf_program__set_xdp(struct bpf_program *prog);
 int bpf_program__set_perf_event(struct bpf_program *prog);
+void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
 
 bool bpf_program__is_socket_filter(struct bpf_program *prog);
 bool bpf_program__is_tracepoint(struct bpf_program *prog);
diff --git a/tools/lib/subcmd/help.h b/tools/lib/subcmd/help.h
index e145a020780c..9bd4223dc722 100644
--- a/tools/lib/subcmd/help.h
+++ b/tools/lib/subcmd/help.h
@@ -2,6 +2,7 @@
 #define __SUBCMD_HELP_H
 
 #include <sys/types.h>
+#include <stdio.h>
 
 struct cmdnames {
 	size_t alloc;
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 5e431077fcd6..d270ac00613d 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -1,3 +1,4 @@
+#include <ctype.h>
 #include "symbol/kallsyms.h"
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 47076b15eebe..9b8555ea3459 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -135,7 +135,7 @@ else
   Q = @
 endif
 
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
 MAKEOVERRIDES=
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 66342804161c..0c03538df74c 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -140,7 +140,7 @@ struct pevent_plugin_option {
  *   struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
  *	{
  *		.name = "option-name",
- *		.plugin_alias = "overide-file-name", (optional)
+ *		.plugin_alias = "override-file-name", (optional)
  *		.description = "description of option to show users",
  *	},
  *	{
diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
index 544b05a53b70..ad572e6cdbd0 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/net/bpf_jit_disasm.c
@@ -229,6 +229,7 @@ static void usage(void)
 {
 	printf("Usage: bpf_jit_disasm [...]\n");
 	printf("       -o          Also display related opcodes (default: off).\n");
+	printf("       -O <file>   Write binary image of code to file, don't disassemble to stdout.\n");
 	printf("       -f <file>   Read last image dump from file or stdin (default: klog).\n");
 	printf("       -h          Display this help.\n");
 }
@@ -238,12 +239,19 @@ int main(int argc, char **argv)
 	unsigned int len, klen, opt, opcodes = 0;
 	static uint8_t image[32768];
 	char *kbuff, *file = NULL;
+	char *ofile = NULL;
+	int ofd;
+	ssize_t nr;
+	uint8_t *pos;
 
-	while ((opt = getopt(argc, argv, "of:")) != -1) {
+	while ((opt = getopt(argc, argv, "of:O:")) != -1) {
 		switch (opt) {
 		case 'o':
 			opcodes = 1;
 			break;
+		case 'O':
+			ofile = optarg;
+			break;
 		case 'f':
 			file = optarg;
 			break;
@@ -263,11 +271,35 @@ int main(int argc, char **argv)
 	}
 
 	len = get_last_jit_image(kbuff, klen, image, sizeof(image));
-	if (len > 0)
-		get_asm_insns(image, len, opcodes);
-	else
+	if (len <= 0) {
 		fprintf(stderr, "No JIT image found!\n");
+		goto done;
+	}
+	if (!ofile) {
+		get_asm_insns(image, len, opcodes);
+		goto done;
+	}
+
+	ofd = open(ofile, O_WRONLY | O_CREAT | O_TRUNC, DEFFILEMODE);
+	if (ofd < 0) {
+		fprintf(stderr, "Could not open file %s for writing: ", ofile);
+		perror(NULL);
+		goto done;
+	}
+	pos = image;
+	do {
+		nr = write(ofd, pos, len);
+		if (nr < 0) {
+			fprintf(stderr, "Could not write data to %s: ", ofile);
+			perror(NULL);
+			goto done;
+		}
+		len -= nr;
+		pos += nr;
+	} while (len);
+	close(ofd);
 
+done:
 	put_log_buff(kbuff);
 	return 0;
 }
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 4cfdbb5b6967..282a60368b14 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -36,8 +36,7 @@
 #include "warn.h"
 
 #include <linux/hashtable.h>
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#include <linux/kernel.h>
 
 #define STATE_FP_SAVED		0x1
 #define STATE_FP_SETUP		0x2
@@ -805,11 +804,20 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		     insn->jump_dest->offset > orig_insn->offset))
 		    break;
 
+		/* look for a relocation which references .rodata */
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (text_rela && text_rela->sym == file->rodata->sym)
-			return find_rela_by_dest(file->rodata,
-						 text_rela->addend);
+		if (!text_rela || text_rela->sym != file->rodata->sym)
+			continue;
+
+		/*
+		 * Make sure the .rodata address isn't associated with a
+		 * symbol.  gcc jump tables are anonymous data.
+		 */
+		if (find_symbol_containing(file->rodata, text_rela->addend))
+			continue;
+
+		return find_rela_by_dest(file->rodata, text_rela->addend);
 	}
 
 	return NULL;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d7983ac63ef..d897702ce742 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+{
+	struct symbol *sym;
+
+	list_for_each_entry(sym, &sec->symbol_list, list)
+		if (sym->type != STT_SECTION &&
+		    offset >= sym->offset && offset < sym->offset + sym->len)
+			return sym;
+
+	return NULL;
+}
+
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
 				     unsigned int len)
 {
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index aa1ff6596684..731973e1a3f5 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -79,6 +79,7 @@ struct elf {
 struct elf *elf_open(const char *name);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
 				     unsigned int len);
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index 46c326db4f46..ecc5b1b5d15d 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -31,11 +31,10 @@
 #include <stdlib.h>
 #include <subcmd/exec-cmd.h>
 #include <subcmd/pager.h>
+#include <linux/kernel.h>
 
 #include "builtin.h"
 
-#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
-
 struct cmd_struct {
 	const char *name;
 	int (*fn)(int, const char **);
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 3db3db9278be..643cc4ba6872 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -31,3 +31,5 @@ config.mak.autogen
 .config-detected
 util/intel-pt-decoder/inat-tables.c
 arch/*/include/generated/
+pmu-events/pmu-events.c
+pmu-events/jevents
diff --git a/tools/perf/Build b/tools/perf/Build
index 9b79f8d7db50..bd8eeb60533c 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -50,5 +50,6 @@ libperf-y += util/
 libperf-y += arch/
 libperf-y += ui/
 libperf-y += scripts/
+libperf-y += trace/beauty/
 
 gtk-y += ui/gtk/
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 2d96de6132a9..6e6a8b22c859 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -30,6 +30,24 @@ OPTIONS
 --verbose=::
         Verbosity level.
 
+-p::
+--pid=::
+	Trace on existing process id (comma separated list).
+
+-a::
+--all-cpus::
+	Force system-wide collection.  Scripts run without a <command>
+	normally use -a by default, while scripts run with a <command>
+	normally don't - this option allows the latter to be run in
+	system-wide mode.
+
+-C::
+--cpu=::
+	Only trace for the list of CPUs provided.  Multiple CPUs can
+	be provided as a comma separated list with no space like: 0,1.
+	Ranges of CPUs are specified with -: 0-2.
+	Default is to trace on all online CPUs.
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 41857cce5e86..f709de54707b 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob]
+'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
 
 DESCRIPTION
 -----------
@@ -24,6 +24,10 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--details::
+Print how named events are resolved internally into perf events, and also
+any extra expressions computed by perf stat.
+
 
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
@@ -240,6 +244,8 @@ To limit the list use:
 
 . 'pmu' to print the kernel supplied PMU events.
 
+. 'sdt' to list all Statically Defined Tracepoint events.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b16003ec14a7..ea3789d05e5e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -347,6 +347,9 @@ Enable weightened sampling. An additional weight is recorded per sample and can
 displayed with the weight and local_weight sort keys.  This currently works for TSX
 abort events and some memory events in precise mode on modern Intel CPUs.
 
+--namespaces::
+Record events of type PERF_RECORD_NAMESPACES.
+
 --transaction::
 Record transaction flags for transaction related events.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index c04cc0647c16..37a175914157 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -72,7 +72,8 @@ OPTIONS
 --sort=::
 	Sort histogram entries by given key(s) - multiple keys can be specified
 	in CSV format.  Following sort keys are available:
-	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
+	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight,
+	local_weight, cgroup_id.
 
 	Each key has following meaning:
 
@@ -80,6 +81,7 @@ OPTIONS
 	- pid: command and tid of the task
 	- dso: name of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample
+	- symbol_size: size of function executed at the time of sample
 	- parent: name of function matched to the parent regex filter. Unmatched
 	entries are displayed as "[other]".
 	- cpu: cpu number the task ran at the time of sample
@@ -91,6 +93,7 @@ OPTIONS
 	- weight: Event specific weight, e.g. memory latency or transaction
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
+	- cgroup_id: ID derived from cgroup namespace device and inode numbers.
 	- transaction: Transaction abort flags.
 	- overhead: Overhead percentage of sample
 	- overhead_sys: Overhead percentage of sample running in system mode
@@ -172,6 +175,9 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
+	If the keys starts with a prefix '+', then it will append the specified
+        field(s) to the default field order. For example: perf report -F +period,sample.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -229,6 +235,7 @@ OPTIONS
 	sort_key can be:
 	- function: compare on functions (default)
 	- address: compare on individual code addresses
+	- srcline: compare on source filename and line number
 
 	branch can be:
 	- branch: include last branch information in callgraph when available.
@@ -424,6 +431,10 @@ include::itrace.txt[]
 --hierarchy::
 	Enable hierarchical output.
 
+--inline::
+	If a callgraph address belongs to an inlined function, the inline stack
+	will be printed. Each entry is function name or file/line.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index d33deddb0146..a092a2499e8f 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist'
 --migrations::
 	Show migration events.
 
+-n::
+--next::
+	Show next task.
+
 -I::
 --idle-hist::
 	Show idle-related events only.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 4ed5f239ba7d..cb0eda3925e6 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
         callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -189,15 +189,20 @@ OPTIONS
 	i.e., -F "" is not allowed.
 
 	The brstack output includes branch related information with raw addresses using the
-	/v/v/v/v/ syntax in the following order:
+	/v/v/v/v/cycles syntax in the following order:
 	FROM: branch source instruction
 	TO  : branch target instruction
         M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
 	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
 	A/- : A=TSX abort entry, -=not aborted region or not supported
+	cycles
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
+	When brstackinsn is specified the full assembler sequences of branch sequences for each sample
+	is printed. This is the full execution path leading to the sample. This is only supported when the
+	sample was recorded with perf record -b or -j any.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
@@ -248,6 +253,9 @@ OPTIONS
 --show-mmap-events
 	Display mmap related events (e.g. MMAP, MMAP2).
 
+--show-namespace-events
+	Display namespace events i.e. events of type PERF_RECORD_NAMESPACES.
+
 --show-switch-events
 	Display context switch events i.e. events of type PERF_RECORD_SWITCH or
 	PERF_RECORD_SWITCH_CPU_WIDE.
@@ -299,6 +307,10 @@ include::itrace.txt[]
 	stop time is not given (i.e, time string is 'x.y,') then analysis goes
 	to end of file.
 
+--max-blocks::
+	Set the maximum number of program blocks to print with brstackasm for
+	each sample.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index aecf2a87e7d6..bd0e4417f2be 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -94,8 +94,7 @@ to activate system-wide monitoring. Default is to count on all CPUs.
 
 -A::
 --no-aggr::
-Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
-This option is only valid in system-wide mode.
+Do not aggregate counts across all monitored CPUs.
 
 -n::
 --null::
@@ -237,6 +236,9 @@ To interpret the results it is usually needed to know on which
 CPUs the workload runs on. If needed the CPUs can be forced using
 taskset.
 
+--no-merge::
+Do not merge results from same PMUs.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index afd728672b6f..c1e3288a2dfb 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -123,7 +123,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	major or all pagefaults. Default value is maj.
 
 --syscalls::
-	Trace system calls. This options is enabled by default.
+	Trace system calls. This options is enabled by default, disable with
+	--no-syscalls.
 
 --call-graph [mode,type,min[,limit],order[,key][,branch]]::
         Setup and enable call-graph (stack chain/backtrace) recording.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index b664b18d3991..fa2a9132f0a9 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -11,8 +11,8 @@ All fields are in native-endian of the machine that generated the perf.data.
 
 When perf is writing to a pipe it uses a special version of the file
 format that does not rely on seeking to adjust data offsets.  This
-format is not described here. The pipe version can be converted to
-normal perf.data with perf inject.
+format is described in "Pipe-mode data" section. The pipe data version can be
+augmented with additional events using perf inject.
 
 The file starts with a perf_header:
 
@@ -411,6 +411,21 @@ An array bound by the perf_file_section size.
 
 ids points to a array of uint64_t defining the ids for event attr attr.
 
+Pipe-mode data
+
+Pipe-mode avoid seeks in the file by removing the perf_file_section and flags
+from the struct perf_header. The trimmed header is:
+
+struct perf_pipe_file_header {
+	u64				magic;
+	u64				size;
+};
+
+The information about attrs, data, and event_types is instead in the
+synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and
+PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode.
+
+
 References:
 
 include/uapi/linux/perf_event.h
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8672f835ae4e..a29da46d180f 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -12,6 +12,7 @@ tools/arch/sparc/include/asm/barrier_32.h
 tools/arch/sparc/include/asm/barrier_64.h
 tools/arch/tile/include/asm/barrier.h
 tools/arch/x86/include/asm/barrier.h
+tools/arch/x86/include/asm/cmpxchg.h
 tools/arch/x86/include/asm/cpufeatures.h
 tools/arch/x86/include/asm/disabled-features.h
 tools/arch/x86/include/asm/required-features.h
@@ -63,6 +64,7 @@ tools/include/linux/bitops.h
 tools/include/linux/compiler.h
 tools/include/linux/compiler-gcc.h
 tools/include/linux/coresight-pmu.h
+tools/include/linux/bug.h
 tools/include/linux/filter.h
 tools/include/linux/hash.h
 tools/include/linux/kernel.h
@@ -72,12 +74,15 @@ tools/include/uapi/asm-generic/mman-common.h
 tools/include/uapi/asm-generic/mman.h
 tools/include/uapi/linux/bpf.h
 tools/include/uapi/linux/bpf_common.h
+tools/include/uapi/linux/fcntl.h
 tools/include/uapi/linux/hw_breakpoint.h
 tools/include/uapi/linux/mman.h
 tools/include/uapi/linux/perf_event.h
+tools/include/uapi/linux/stat.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
+tools/include/linux/refcount.h
 tools/include/linux/string.h
 tools/include/linux/stringify.h
 tools/include/linux/types.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 27c9fbca7bd9..8354d04b392f 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -170,13 +170,20 @@ PYTHON2_CONFIG := \
 override PYTHON_CONFIG := \
   $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
 
-PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+grep-libs  = $(filter -l%,$(1))
+strip-libs  = $(filter-out -l%,$(1))
 
-PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
-ifeq ($(CC), clang)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+ifdef PYTHON_CONFIG
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+  PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+  ifeq ($(CC), clang)
+    PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  endif
+  FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
@@ -267,6 +274,7 @@ ifdef NO_LIBELF
   NO_LIBUNWIND := 1
   NO_LIBDW_DWARF_UNWIND := 1
   NO_LIBBPF := 1
+  NO_JVMTI := 1
 else
   ifeq ($(feature-libelf), 0)
     ifeq ($(feature-glibc), 1)
@@ -276,7 +284,7 @@ else
       LIBC_SUPPORT := 1
     endif
     ifeq ($(LIBC_SUPPORT),1)
-      msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install libelf-dev, libelf-devel or elfutils-libelf-devel);
+      msg := $(warning No libelf found. Disables 'probe' tool, jvmti and BPF support in 'perf record'. Please install libelf-dev, libelf-devel or elfutils-libelf-devel);
 
       NO_LIBELF := 1
       NO_DWARF := 1
@@ -284,6 +292,7 @@ else
       NO_LIBUNWIND := 1
       NO_LIBDW_DWARF_UNWIND := 1
       NO_LIBBPF := 1
+      NO_JVMTI := 1
     else
       ifneq ($(filter s% -static%,$(LDFLAGS),),)
         msg := $(error No static glibc found, please install glibc-static);
@@ -317,6 +326,10 @@ ifdef NO_DWARF
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+ifeq ($(feature-sched_getcpu), 1)
+  CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
@@ -550,8 +563,6 @@ ifndef NO_GTK2
   endif
 endif
 
-grep-libs  = $(filter -l%,$(1))
-strip-libs = $(filter-out -l%,$(1))
 
 ifdef NO_LIBPERL
   CFLAGS += -DNO_LIBPERL
@@ -599,21 +610,9 @@ else
       $(call disable-python,No 'python-config' tool was found: disables Python support - please install python-devel/python-dev)
     else
 
-      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
-
-      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-      ifeq ($(CC), clang)
-        PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
-      endif
-      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
       ifneq ($(feature-libpython), 1)
         $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev)
       else
-
         ifneq ($(feature-libpython-version), 1)
           $(warning Python 3 is not yet supported; please set)
           $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index dfea6b635525..29361d9b635a 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -33,6 +33,7 @@
 #include "../../util/cs-etm.h"
 
 #include <stdlib.h>
+#include <sys/stat.h>
 
 #define ENABLE_SINK_MAX	128
 #define CS_BUS_DEVICE_PATH "/bus/coresight/devices/"
diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c
index 33ec5b339da8..8bb176a37990 100644
--- a/tools/perf/arch/arm/util/dwarf-regs.c
+++ b/tools/perf/arch/arm/util/dwarf-regs.c
@@ -9,6 +9,7 @@
  */
 
 #include <stddef.h>
+#include <linux/stringify.h>
 #include <dwarf-regs.h>
 
 struct pt_regs_dwarfnum {
@@ -16,10 +17,9 @@ struct pt_regs_dwarfnum {
 	unsigned int dwarfnum;
 };
 
-#define STR(s) #s
 #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
 #define GPR_DWARFNUM_NAME(num) \
-	{.name = STR(%r##num), .dwarfnum = num}
+	{.name = __stringify(%r##num), .dwarfnum = num}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
 
 /*
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
index b4176c60117a..bacfa00fca39 100644
--- a/tools/perf/arch/arm/util/unwind-libdw.c
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -1,6 +1,7 @@
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
+#include "../../util/event.h"
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index 068b6189157b..cd764a9fd098 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -8,9 +8,12 @@
  * published by the Free Software Foundation.
  */
 
+#include <errno.h>
 #include <stddef.h>
+#include <string.h>
 #include <dwarf-regs.h>
 #include <linux/ptrace.h> /* for struct user_pt_regs */
+#include <linux/stringify.h>
 #include "util.h"
 
 struct pt_regs_dwarfnum {
@@ -20,7 +23,7 @@ struct pt_regs_dwarfnum {
 
 #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
 #define GPR_DWARFNUM_NAME(num) \
-	{.name = STR(%x##num), .dwarfnum = num}
+	{.name = __stringify(%x##num), .dwarfnum = num}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
 #define DWARFNUM2OFFSET(index) \
 	(index * sizeof((struct user_pt_regs *)0)->regs[0])
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index c116b713f7f7..b415dfdbccca 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -1,6 +1,6 @@
+#include <errno.h>
 
 #ifndef REMOTE_UNWIND_LIBUNWIND
-#include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 886dd2aaff0d..837067f48a4c 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -4,6 +4,8 @@
 #include "../util/util.h"
 #include "../util/debug.h"
 
+#include "sane_ctype.h"
+
 const char *const arm_triplets[] = {
 	"arm-eabi-",
 	"arm-linux-androideabi-",
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 41bdf9530d82..98ac87052a74 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -15,6 +15,7 @@
 #include <dwarf-regs.h>
 #include <linux/ptrace.h>
 #include <linux/kernel.h>
+#include <linux/stringify.h>
 #include "util.h"
 
 struct pt_regs_dwarfnum {
@@ -24,10 +25,10 @@ struct pt_regs_dwarfnum {
 };
 
 #define REG_DWARFNUM_NAME(r, num)					\
-		{.name = STR(%)STR(r), .dwarfnum = num,			\
+		{.name = __stringify(%)__stringify(r), .dwarfnum = num,			\
 		.ptregs_offset = offsetof(struct pt_regs, r)}
 #define GPR_DWARFNUM_NAME(num)						\
-		{.name = STR(%gpr##num), .dwarfnum = num,		\
+		{.name = __stringify(%gpr##num), .dwarfnum = num,		\
 		.ptregs_offset = offsetof(struct pt_regs, gpr[num])}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0}
 
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
index 74eee30398f8..249723f0e6a9 100644
--- a/tools/perf/arch/powerpc/util/kvm-stat.c
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include "util/kvm-stat.h"
 #include "util/parse-events.h"
 #include "util/debug.h"
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index a3c3e1ce6807..f860dc411f69 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -1,5 +1,11 @@
+#include <errno.h>
+#include <string.h>
+#include <regex.h>
+
 #include "../../perf.h"
+#include "../../util/util.h"
 #include "../../util/perf_regs.h"
+#include "../../util/debug.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(r0, PERF_REG_POWERPC_R0),
@@ -47,3 +53,109 @@ const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR),
 	SMPL_REG_END
 };
+
+/* REG or %rREG */
+#define SDT_OP_REGEX1  "^(%r)?([1-2]?[0-9]|3[0-1])$"
+
+/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */
+#define SDT_OP_REGEX2  "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$"
+
+static regex_t sdt_op_regex1, sdt_op_regex2;
+
+static int sdt_init_op_regex(void)
+{
+	static int initialized;
+	int ret = 0;
+
+	if (initialized)
+		return 0;
+
+	ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED);
+	if (ret)
+		goto error;
+
+	ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED);
+	if (ret)
+		goto free_regex1;
+
+	initialized = 1;
+	return 0;
+
+free_regex1:
+	regfree(&sdt_op_regex1);
+error:
+	pr_debug4("Regex compilation error.\n");
+	return ret;
+}
+
+/*
+ * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG).
+ * Possible variants of OP are:
+ *	Format		Example
+ *	-------------------------
+ *	NUM(REG)	48(18)
+ *	-NUM(REG)	-48(18)
+ *	NUM(%rREG)	48(%r18)
+ *	-NUM(%rREG)	-48(%r18)
+ *	REG		18
+ *	%rREG		%r18
+ *	iNUM		i0
+ *	i-NUM		i-1
+ *
+ * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag
+ * and REG form with -mno-regnames. Here REG is general purpose register,
+ * which is in 0 to 31 range.
+ */
+int arch_sdt_arg_parse_op(char *old_op, char **new_op)
+{
+	int ret, new_len;
+	regmatch_t rm[5];
+	char prefix;
+
+	/* Constant argument. Uprobe does not support it */
+	if (old_op[0] == 'i') {
+		pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+		return SDT_ARG_SKIP;
+	}
+
+	ret = sdt_init_op_regex();
+	if (ret < 0)
+		return ret;
+
+	if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) {
+		/* REG or %rREG --> %gprREG */
+
+		new_len = 5;	/* % g p r NULL */
+		new_len += (int)(rm[2].rm_eo - rm[2].rm_so);
+
+		*new_op = zalloc(new_len);
+		if (!*new_op)
+			return -ENOMEM;
+
+		scnprintf(*new_op, new_len, "%%gpr%.*s",
+			(int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so);
+	} else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) {
+		/*
+		 * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) -->
+		 *	+/-NUM(%gprREG)
+		 */
+		prefix = (rm[1].rm_so == -1) ? '+' : '-';
+
+		new_len = 8;	/* +/- ( % g p r ) NULL */
+		new_len += (int)(rm[2].rm_eo - rm[2].rm_so);
+		new_len += (int)(rm[4].rm_eo - rm[4].rm_so);
+
+		*new_op = zalloc(new_len);
+		if (!*new_op)
+			return -ENOMEM;
+
+		scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix,
+			(int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so,
+			(int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so);
+	} else {
+		pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+		return SDT_ARG_SKIP;
+	}
+
+	return SDT_ARG_VALID;
+}
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 1030a6e504bb..39dbe512b9fc 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include "map.h"
 #include "probe-event.h"
+#include "probe-file.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
@@ -79,13 +80,18 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 	 * However, if the user specifies an offset, we fall back to using the
 	 * GEP since all userspace applications (objdump/readelf) show function
 	 * disassembly with offsets from the GEP.
-	 *
-	 * In addition, we shouldn't specify an offset for kretprobes.
 	 */
-	if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) ||
-	    !map || !sym)
+	if (pev->point.offset || !map || !sym)
 		return;
 
+	/* For kretprobes, add an offset only if the kernel supports it */
+	if (!pev->uprobes && pev->point.retprobe) {
+#ifdef HAVE_LIBELF_SUPPORT
+		if (!kretprobe_offset_is_supported())
+#endif
+			return;
+	}
+
 	lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
 
 	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
new file mode 100644
index 000000000000..745b4b1b8b21
--- /dev/null
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -0,0 +1,30 @@
+static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	/* catch all kind of jumps */
+	if (strchr(name, 'j') ||
+	    !strncmp(name, "bct", 3) ||
+	    !strncmp(name, "br", 2))
+		ops = &jump_ops;
+	/* override call/returns */
+	if (!strcmp(name, "bras") ||
+	    !strcmp(name, "brasl") ||
+	    !strcmp(name, "basr"))
+		ops = &call_ops;
+	if (!strcmp(name, "br"))
+		ops = &ret_ops;
+
+	arch__associate_ins_ops(arch, name, ops);
+	return ops;
+}
+
+static int s390__annotate_init(struct arch *arch)
+{
+	if (!arch->initialized) {
+		arch->initialized = true;
+		arch->associate_instruction_ops = s390__associate_ins_ops;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index ed57df2e6d68..d233e2eb9592 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -9,6 +9,7 @@
  * as published by the Free Software Foundation.
  */
 
+#include <errno.h>
 #include "../../util/kvm-stat.h"
 #include <asm/sie.h>
 
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index e93ef0b38db8..5aef183e2f85 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -338,6 +338,7 @@
 329	common	pkey_mprotect		sys_pkey_mprotect
 330	common	pkey_alloc		sys_pkey_alloc
 331	common	pkey_free		sys_pkey_free
+332	common	statx			sys_statx
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 7f064eb37158..f9713a71d77e 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -6,7 +6,10 @@
 #include "evsel.h"
 #include "arch-tests.h"
 
+#include <signal.h>
 #include <sys/mman.h>
+#include <sys/wait.h>
+#include <errno.h>
 #include <string.h>
 
 static pid_t spawn(void)
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 5c76cc83186a..e3ae9cff2b67 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <linux/types.h>
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index cc1d865e31f1..6aa3f2a38321 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <errno.h>
 #include <stdbool.h>
 
 #include "../../util/header.h"
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 5132775a044f..af2bce7a2cd6 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <errno.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 90fa2286edcf..f630de0206a1 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <errno.h>
 #include <stdbool.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index b63d4be655a2..bf817beca0a8 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include "../../util/kvm-stat.h"
 #include <asm/svm.h>
 #include <asm/vmx.h>
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index c5db14f36cc7..f95edebfb716 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -1,5 +1,11 @@
+#include <errno.h>
+#include <string.h>
+#include <regex.h>
+
 #include "../../perf.h"
+#include "../../util/util.h"
 #include "../../util/perf_regs.h"
+#include "../../util/debug.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
@@ -26,3 +32,224 @@ const struct sample_reg sample_reg_masks[] = {
 #endif
 	SMPL_REG_END
 };
+
+struct sdt_name_reg {
+	const char *sdt_name;
+	const char *uprobe_name;
+};
+#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m}
+#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL}
+
+static const struct sdt_name_reg sdt_reg_tbl[] = {
+	SDT_NAME_REG(eax, ax),
+	SDT_NAME_REG(rax, ax),
+	SDT_NAME_REG(al,  ax),
+	SDT_NAME_REG(ah,  ax),
+	SDT_NAME_REG(ebx, bx),
+	SDT_NAME_REG(rbx, bx),
+	SDT_NAME_REG(bl,  bx),
+	SDT_NAME_REG(bh,  bx),
+	SDT_NAME_REG(ecx, cx),
+	SDT_NAME_REG(rcx, cx),
+	SDT_NAME_REG(cl,  cx),
+	SDT_NAME_REG(ch,  cx),
+	SDT_NAME_REG(edx, dx),
+	SDT_NAME_REG(rdx, dx),
+	SDT_NAME_REG(dl,  dx),
+	SDT_NAME_REG(dh,  dx),
+	SDT_NAME_REG(esi, si),
+	SDT_NAME_REG(rsi, si),
+	SDT_NAME_REG(sil, si),
+	SDT_NAME_REG(edi, di),
+	SDT_NAME_REG(rdi, di),
+	SDT_NAME_REG(dil, di),
+	SDT_NAME_REG(ebp, bp),
+	SDT_NAME_REG(rbp, bp),
+	SDT_NAME_REG(bpl, bp),
+	SDT_NAME_REG(rsp, sp),
+	SDT_NAME_REG(esp, sp),
+	SDT_NAME_REG(spl, sp),
+
+	/* rNN registers */
+	SDT_NAME_REG(r8b,  r8),
+	SDT_NAME_REG(r8w,  r8),
+	SDT_NAME_REG(r8d,  r8),
+	SDT_NAME_REG(r9b,  r9),
+	SDT_NAME_REG(r9w,  r9),
+	SDT_NAME_REG(r9d,  r9),
+	SDT_NAME_REG(r10b, r10),
+	SDT_NAME_REG(r10w, r10),
+	SDT_NAME_REG(r10d, r10),
+	SDT_NAME_REG(r11b, r11),
+	SDT_NAME_REG(r11w, r11),
+	SDT_NAME_REG(r11d, r11),
+	SDT_NAME_REG(r12b, r12),
+	SDT_NAME_REG(r12w, r12),
+	SDT_NAME_REG(r12d, r12),
+	SDT_NAME_REG(r13b, r13),
+	SDT_NAME_REG(r13w, r13),
+	SDT_NAME_REG(r13d, r13),
+	SDT_NAME_REG(r14b, r14),
+	SDT_NAME_REG(r14w, r14),
+	SDT_NAME_REG(r14d, r14),
+	SDT_NAME_REG(r15b, r15),
+	SDT_NAME_REG(r15w, r15),
+	SDT_NAME_REG(r15d, r15),
+	SDT_NAME_REG_END,
+};
+
+/*
+ * Perf only supports OP which is in  +/-NUM(REG)  form.
+ * Here plus-minus sign, NUM and parenthesis are optional,
+ * only REG is mandatory.
+ *
+ * SDT events also supports indirect addressing mode with a
+ * symbol as offset, scaled mode and constants in OP. But
+ * perf does not support them yet. Below are few examples.
+ *
+ * OP with scaled mode:
+ *     (%rax,%rsi,8)
+ *     10(%ras,%rsi,8)
+ *
+ * OP with indirect addressing mode:
+ *     check_action(%rip)
+ *     mp_+52(%rip)
+ *     44+mp_(%rip)
+ *
+ * OP with constant values:
+ *     $0
+ *     $123
+ *     $-1
+ */
+#define SDT_OP_REGEX  "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$"
+
+static regex_t sdt_op_regex;
+
+static int sdt_init_op_regex(void)
+{
+	static int initialized;
+	int ret = 0;
+
+	if (initialized)
+		return 0;
+
+	ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED);
+	if (ret < 0) {
+		pr_debug4("Regex compilation error.\n");
+		return ret;
+	}
+
+	initialized = 1;
+	return 0;
+}
+
+/*
+ * Max x86 register name length is 5(ex: %r15d). So, 6th char
+ * should always contain NULL. This helps to find register name
+ * length using strlen, insted of maintaing one more variable.
+ */
+#define SDT_REG_NAME_SIZE  6
+
+/*
+ * The uprobe parser does not support all gas register names;
+ * so, we have to replace them (ex. for x86_64: %rax -> %ax).
+ * Note: If register does not require renaming, just copy
+ * paste as it is, but don't leave it empty.
+ */
+static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg)
+{
+	int i = 0;
+
+	for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) {
+		if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) {
+			strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name);
+			return;
+		}
+	}
+
+	strncpy(uprobe_reg, sdt_reg, sdt_len);
+}
+
+int arch_sdt_arg_parse_op(char *old_op, char **new_op)
+{
+	char new_reg[SDT_REG_NAME_SIZE] = {0};
+	int new_len = 0, ret;
+	/*
+	 * rm[0]:  +/-NUM(REG)
+	 * rm[1]:  +/-
+	 * rm[2]:  NUM
+	 * rm[3]:  (
+	 * rm[4]:  REG
+	 * rm[5]:  )
+	 */
+	regmatch_t rm[6];
+	/*
+	 * Max prefix length is 2 as it may contains sign(+/-)
+	 * and displacement 0 (Both sign and displacement 0 are
+	 * optional so it may be empty). Use one more character
+	 * to hold last NULL so that strlen can be used to find
+	 * prefix length, instead of maintaing one more variable.
+	 */
+	char prefix[3] = {0};
+
+	ret = sdt_init_op_regex();
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * If unsupported OR does not match with regex OR
+	 * register name too long, skip it.
+	 */
+	if (strchr(old_op, ',') || strchr(old_op, '$') ||
+	    regexec(&sdt_op_regex, old_op, 6, rm, 0)   ||
+	    rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) {
+		pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+		return SDT_ARG_SKIP;
+	}
+
+	/*
+	 * Prepare prefix.
+	 * If SDT OP has parenthesis but does not provide
+	 * displacement, add 0 for displacement.
+	 *     SDT         Uprobe     Prefix
+	 *     -----------------------------
+	 *     +24(%rdi)   +24(%di)   +
+	 *     24(%rdi)    +24(%di)   +
+	 *     %rdi        %di
+	 *     (%rdi)      +0(%di)    +0
+	 *     -80(%rbx)   -80(%bx)   -
+	 */
+	if (rm[3].rm_so != rm[3].rm_eo) {
+		if (rm[1].rm_so != rm[1].rm_eo)
+			prefix[0] = *(old_op + rm[1].rm_so);
+		else if (rm[2].rm_so != rm[2].rm_eo)
+			prefix[0] = '+';
+		else
+			strncpy(prefix, "+0", 2);
+	}
+
+	/* Rename register */
+	sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so,
+			    new_reg);
+
+	/* Prepare final OP which should be valid for uprobe_events */
+	new_len = strlen(prefix)              +
+		  (rm[2].rm_eo - rm[2].rm_so) +
+		  (rm[3].rm_eo - rm[3].rm_so) +
+		  strlen(new_reg)             +
+		  (rm[5].rm_eo - rm[5].rm_so) +
+		  1;					/* NULL */
+
+	*new_op = zalloc(new_len);
+	if (!*new_op)
+		return -ENOMEM;
+
+	scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s",
+		  strlen(prefix), prefix,
+		  (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so,
+		  (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so,
+		  strlen(new_reg), new_reg,
+		  (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so);
+
+	return SDT_ARG_VALID;
+}
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
index c4b72176ca83..38dc9bb2a7c9 100644
--- a/tools/perf/arch/x86/util/unwind-libdw.c
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -1,6 +1,7 @@
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
+#include "../../util/event.h"
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 579a592990dd..842ab2781cdc 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -25,17 +25,17 @@
 # endif
 #endif
 
-int bench_numa(int argc, const char **argv, const char *prefix);
-int bench_sched_messaging(int argc, const char **argv, const char *prefix);
-int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
-int bench_mem_memset(int argc, const char **argv, const char *prefix);
-int bench_futex_hash(int argc, const char **argv, const char *prefix);
-int bench_futex_wake(int argc, const char **argv, const char *prefix);
-int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix);
-int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+int bench_numa(int argc, const char **argv);
+int bench_sched_messaging(int argc, const char **argv);
+int bench_sched_pipe(int argc, const char **argv);
+int bench_mem_memcpy(int argc, const char **argv);
+int bench_mem_memset(int argc, const char **argv);
+int bench_futex_hash(int argc, const char **argv);
+int bench_futex_wake(int argc, const char **argv);
+int bench_futex_wake_parallel(int argc, const char **argv);
+int bench_futex_requeue(int argc, const char **argv);
 /* pi futexes */
-int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
+int bench_futex_lock_pi(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index da04b8c5568a..fe16b310097f 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -9,6 +9,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <errno.h>
@@ -113,8 +114,7 @@ static void print_summary(void)
 	       (int) runtime.tv_sec);
 }
 
-int bench_futex_hash(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+int bench_futex_hash(int argc, const char **argv)
 {
 	int ret = 0;
 	cpu_set_t cpu;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 91877777ec6e..73a1c44ea63c 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -3,6 +3,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -139,8 +140,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
 	}
 }
 
-int bench_futex_lock_pi(int argc, const char **argv,
-			const char *prefix __maybe_unused)
+int bench_futex_lock_pi(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 2b9705a8734c..41786cbea24c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -9,6 +9,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -108,8 +109,7 @@ static void toggle_done(int sig __maybe_unused,
 	done = true;
 }
 
-int bench_futex_requeue(int argc, const char **argv,
-			const char *prefix __maybe_unused)
+int bench_futex_requeue(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i, j;
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 2c8fa67ad537..4ab12c8e016a 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -8,6 +8,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -196,8 +197,7 @@ static void toggle_done(int sig __maybe_unused,
 	done = true;
 }
 
-int bench_futex_wake_parallel(int argc, const char **argv,
-			      const char *prefix __maybe_unused)
+int bench_futex_wake_parallel(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i, j;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e246b1b8388a..2fa49222ef8d 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -9,6 +9,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -114,8 +115,7 @@ static void toggle_done(int sig __maybe_unused,
 	done = true;
 }
 
-int bench_futex_wake(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+int bench_futex_wake(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i, j;
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index b2e06d1190d0..e44fd3239530 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -88,13 +88,11 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
 
 #ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
 #include <pthread.h>
-static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
-					      size_t cpusetsize,
-					      cpu_set_t *cpuset)
+#include <linux/compiler.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
+					      size_t cpusetsize __maybe_unused,
+					      cpu_set_t *cpuset __maybe_unused)
 {
-	attr = attr;
-	cpusetsize = cpusetsize;
-	cpuset = cpuset;
 	return 0;
 }
 #endif
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 52504a83b5a1..fbd732b54047 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -12,6 +12,7 @@
 #include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "../util/cloexec.h"
+#include "../util/string2.h"
 #include "bench.h"
 #include "mem-memcpy-arch.h"
 #include "mem-memset-arch.h"
@@ -284,7 +285,7 @@ static const char * const bench_mem_memcpy_usage[] = {
 	NULL
 };
 
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memcpy(int argc, const char **argv)
 {
 	struct bench_mem_info info = {
 		.functions		= memcpy_functions,
@@ -358,7 +359,7 @@ static const struct function memset_functions[] = {
 	{ .name = NULL, }
 };
 
-int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memset(int argc, const char **argv)
 {
 	struct bench_mem_info info = {
 		.functions		= memset_functions,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 3083fc36282b..27de0c8c5c19 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -4,6 +4,7 @@
  * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
  */
 
+#include <inttypes.h>
 /* For the CLR_() macros */
 #include <pthread.h>
 
@@ -30,6 +31,7 @@
 #include <sys/wait.h>
 #include <sys/prctl.h>
 #include <sys/types.h>
+#include <linux/kernel.h>
 #include <linux/time64.h>
 
 #include <numa.h>
@@ -187,7 +189,8 @@ static const struct option options[] = {
 	OPT_INCR   ('d', "show_details"	, &p0.show_details,	"Show details"),
 	OPT_INCR   ('a', "all"		, &p0.run_all,		"Run all tests in the suite"),
 	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
-	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
+	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, "
+		    "convergence is reached when each process (all its threads) is running on a single NUMA node."),
 	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
 	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"quiet mode"),
 	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
@@ -1766,7 +1769,7 @@ static int bench_all(void)
 	return 0;
 }
 
-int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_numa(int argc, const char **argv)
 {
 	init_params(&p0, "main,", argc, argv);
 	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 6a111e775210..4f961e74535b 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -260,8 +260,7 @@ static const char * const bench_sched_message_usage[] = {
 	NULL
 };
 
-int bench_sched_messaging(int argc, const char **argv,
-		    const char *prefix __maybe_unused)
+int bench_sched_messaging(int argc, const char **argv)
 {
 	unsigned int i, total_children;
 	struct timeval start, stop, diff;
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 2243f0150d76..a152737370c5 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -76,7 +76,7 @@ static void *worker_thread(void *__tdata)
 	return NULL;
 }
 
-int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_sched_pipe(int argc, const char **argv)
 {
 	struct thread_data threads[2], *td;
 	int pipe_1[2], pipe_2[2];
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4f52d85f5ebc..7a5dc7e5c577 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -33,6 +33,7 @@
 #include "util/block-range.h"
 
 #include <dlfcn.h>
+#include <errno.h>
 #include <linux/bitmap.h>
 
 struct perf_annotate {
@@ -383,7 +384,7 @@ static const char * const annotate_usage[] = {
 	NULL
 };
 
-int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_annotate(int argc, const char **argv)
 {
 	struct perf_annotate annotate = {
 		.tool = {
@@ -393,6 +394,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
+			.namespaces = perf_event__process_namespaces,
+			.attr	= perf_event__process_attr,
+			.build_id = perf_event__process_build_id,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index a1cddc6bbf0f..445e62881254 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -25,7 +25,7 @@
 #include <string.h>
 #include <sys/prctl.h>
 
-typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*bench_fn_t)(int argc, const char **argv);
 
 struct bench {
 	const char	*name;
@@ -155,7 +155,7 @@ static int bench_str2int(const char *str)
  * to something meaningful:
  */
 static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
-		     int argc, const char **argv, const char *prefix)
+		     int argc, const char **argv)
 {
 	int size;
 	char *name;
@@ -171,7 +171,7 @@ static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t f
 	prctl(PR_SET_NAME, name);
 	argv[0] = name;
 
-	ret = fn(argc, argv, prefix);
+	ret = fn(argc, argv);
 
 	free(name);
 
@@ -198,7 +198,7 @@ static void run_collection(struct collection *coll)
 		fflush(stdout);
 
 		argv[1] = bench->name;
-		run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
+		run_bench(coll->name, bench->name, bench->fn, 1, argv);
 		printf("\n");
 	}
 }
@@ -211,7 +211,7 @@ static void run_all_collections(void)
 		run_collection(coll);
 }
 
-int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_bench(int argc, const char **argv)
 {
 	struct collection *coll;
 	int ret = 0;
@@ -270,7 +270,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
 			if (bench_format == BENCH_FORMAT_DEFAULT)
 				printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
 			fflush(stdout);
-			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
+			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
 			goto end;
 		}
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 30e2b2cb2421..64b44e81c771 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -10,6 +10,7 @@
 #include <sys/time.h>
 #include <time.h>
 #include <dirent.h>
+#include <errno.h>
 #include <unistd.h>
 #include "builtin.h"
 #include "perf.h"
@@ -21,6 +22,7 @@
 #include "util/build-id.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/time-utils.h"
 
 static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 {
@@ -276,8 +278,7 @@ static int build_id_cache__update_file(const char *filename)
 	return err;
 }
 
-int cmd_buildid_cache(int argc, const char **argv,
-		      const char *prefix __maybe_unused)
+int cmd_buildid_cache(int argc, const char **argv)
 {
 	struct strlist *list;
 	struct str_node *pos;
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 5e914ee79eb3..fdaca16e0c74 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -16,6 +16,7 @@
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/data.h"
+#include <errno.h>
 
 static int sysfs__fprintf_build_id(FILE *fp)
 {
@@ -87,8 +88,7 @@ out:
 	return 0;
 }
 
-int cmd_buildid_list(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+int cmd_buildid_list(int argc, const char **argv)
 {
 	bool show_kernel = false;
 	bool with_hits = false;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index e2b21723bbf8..e33b4acece90 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -9,10 +9,13 @@
  *   Dick Fowles <fowles@inreach.com>
  *   Joe Mario <jmario@redhat.com>
  */
+#include <errno.h>
+#include <inttypes.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <asm/bug.h>
+#include <sys/param.h>
 #include "util.h"
 #include "debug.h"
 #include "builtin.h"
@@ -29,6 +32,7 @@
 #include <asm/bug.h>
 #include "ui/browsers/hists.h"
 #include "evlist.h"
+#include "thread.h"
 
 struct c2c_hists {
 	struct hists		hists;
@@ -2334,7 +2338,7 @@ out:
 
 static void perf_c2c_display(struct perf_session *session)
 {
-	if (c2c.use_stdio)
+	if (use_browser == 0)
 		perf_c2c__hists_fprintf(stdout, session);
 	else
 		perf_c2c__hists_browse(&c2c.hists.hists);
@@ -2536,7 +2540,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"),
 #endif
 	OPT_BOOLEAN(0, "stats", &c2c.stats_only,
-		    "Use the stdio interface"),
+		    "Display only statistic tables (implies --stdio)"),
 	OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full,
 		    "Display full length of symbols"),
 	OPT_BOOLEAN(0, "no-source", &no_source,
@@ -2755,12 +2759,12 @@ static int perf_c2c__record(int argc, const char **argv)
 		pr_debug("\n");
 	}
 
-	ret = cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv);
 	free(rec_argv);
 	return ret;
 }
 
-int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_c2c(int argc, const char **argv)
 {
 	argc = parse_options(argc, argv, c2c_options, c2c_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 8c0d93b7c2f0..55f04f85b049 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -154,7 +154,7 @@ static int parse_config_arg(char *arg, char **var, char **value)
 	return 0;
 }
 
-int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_config(int argc, const char **argv)
 {
 	int i, ret = 0;
 	struct perf_config_set *set;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 7ad6e17ac6b3..0adb5f82335a 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -6,7 +6,7 @@
 #include "data-convert.h"
 #include "data-convert-bt.h"
 
-typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*data_cmd_fn_t)(int argc, const char **argv);
 
 struct data_cmd {
 	const char	*name;
@@ -50,8 +50,7 @@ static const char * const data_convert_usage[] = {
 	NULL
 };
 
-static int cmd_data_convert(int argc, const char **argv,
-			    const char *prefix __maybe_unused)
+static int cmd_data_convert(int argc, const char **argv)
 {
 	const char *to_ctf     = NULL;
 	struct perf_data_convert_opts opts = {
@@ -98,7 +97,7 @@ static struct data_cmd data_cmds[] = {
 	{ .name = NULL, },
 };
 
-int cmd_data(int argc, const char **argv, const char *prefix)
+int cmd_data(int argc, const char **argv)
 {
 	struct data_cmd *cmd;
 	const char *cmdstr;
@@ -118,7 +117,7 @@ int cmd_data(int argc, const char **argv, const char *prefix)
 		if (strcmp(cmd->name, cmdstr))
 			continue;
 
-		return cmd->fn(argc, argv, prefix);
+		return cmd->fn(argc, argv);
 	}
 
 	pr_err("Unknown command: %s\n", cmdstr);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1b96a3122228..eec5df80f5a3 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -19,6 +19,8 @@
 #include "util/data.h"
 #include "util/config.h"
 
+#include <errno.h>
+#include <inttypes.h>
 #include <stdlib.h>
 #include <math.h>
 
@@ -364,6 +366,7 @@ static struct perf_tool tool = {
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
 	.lost	= perf_event__process_lost,
+	.namespaces = perf_event__process_namespaces,
 	.ordered_events = true,
 	.ordering_requires_timestamps = true,
 };
@@ -1320,7 +1323,7 @@ static int diff__config(const char *var, const char *value,
 	return 0;
 }
 
-int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_diff(int argc, const char **argv)
 {
 	int ret = hists__init();
 
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index e09c4287fe87..6d210e40d611 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -46,7 +46,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	return 0;
 }
 
-int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_evlist(int argc, const char **argv)
 {
 	struct perf_attr_details details = { .verbose = false, };
 	const struct option options[] = {
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index c3e643666c72..9e0b35cd0eea 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -9,13 +9,18 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include <errno.h>
 #include <unistd.h>
 #include <signal.h>
+#include <fcntl.h>
+#include <poll.h>
 
 #include "debug.h"
 #include <subcmd/parse-options.h>
+#include <api/fs/tracing_path.h>
 #include "evlist.h"
 #include "target.h"
+#include "cpumap.h"
 #include "thread_map.h"
 #include "util/config.h"
 
@@ -50,11 +55,12 @@ static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
 	done = true;
 }
 
-static int write_tracing_file(const char *name, const char *val)
+static int __write_tracing_file(const char *name, const char *val, bool append)
 {
 	char *file;
 	int fd, ret = -1;
 	ssize_t size = strlen(val);
+	int flags = O_WRONLY;
 
 	file = get_tracing_file(name);
 	if (!file) {
@@ -62,7 +68,12 @@ static int write_tracing_file(const char *name, const char *val)
 		return -1;
 	}
 
-	fd = open(file, O_WRONLY);
+	if (append)
+		flags |= O_APPEND;
+	else
+		flags |= O_TRUNC;
+
+	fd = open(file, flags);
 	if (fd < 0) {
 		pr_debug("cannot open tracing file: %s\n", name);
 		goto out;
@@ -79,6 +90,18 @@ out:
 	return ret;
 }
 
+static int write_tracing_file(const char *name, const char *val)
+{
+	return __write_tracing_file(name, val, false);
+}
+
+static int append_tracing_file(const char *name, const char *val)
+{
+	return __write_tracing_file(name, val, true);
+}
+
+static int reset_tracing_cpu(void);
+
 static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 {
 	if (write_tracing_file("tracing_on", "0") < 0)
@@ -90,14 +113,78 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 	if (write_tracing_file("set_ftrace_pid", " ") < 0)
 		return -1;
 
+	if (reset_tracing_cpu() < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_pid(struct perf_ftrace *ftrace)
+{
+	int i;
+	char buf[16];
+
+	if (target__has_cpu(&ftrace->target))
+		return 0;
+
+	for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) {
+		scnprintf(buf, sizeof(buf), "%d",
+			  ftrace->evlist->threads->map[i]);
+		if (append_tracing_file("set_ftrace_pid", buf) < 0)
+			return -1;
+	}
 	return 0;
 }
 
+static int set_tracing_cpumask(struct cpu_map *cpumap)
+{
+	char *cpumask;
+	size_t mask_size;
+	int ret;
+	int last_cpu;
+
+	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
+	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
+
+	cpumask = malloc(mask_size);
+	if (cpumask == NULL) {
+		pr_debug("failed to allocate cpu mask\n");
+		return -1;
+	}
+
+	cpu_map__snprint_mask(cpumap, cpumask, mask_size);
+
+	ret = write_tracing_file("tracing_cpumask", cpumask);
+
+	free(cpumask);
+	return ret;
+}
+
+static int set_tracing_cpu(struct perf_ftrace *ftrace)
+{
+	struct cpu_map *cpumap = ftrace->evlist->cpus;
+
+	if (!target__has_cpu(&ftrace->target))
+		return 0;
+
+	return set_tracing_cpumask(cpumap);
+}
+
+static int reset_tracing_cpu(void)
+{
+	struct cpu_map *cpumap = cpu_map__new(NULL);
+	int ret;
+
+	ret = set_tracing_cpumask(cpumap);
+	cpu_map__put(cpumap);
+	return ret;
+}
+
 static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 {
 	char *trace_file;
 	int trace_fd;
-	char *trace_pid;
 	char buf[4096];
 	struct pollfd pollfd = {
 		.events = POLLIN,
@@ -108,42 +195,43 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		return -1;
 	}
 
-	if (argc < 1)
-		return -1;
-
 	signal(SIGINT, sig_handler);
 	signal(SIGUSR1, sig_handler);
 	signal(SIGCHLD, sig_handler);
+	signal(SIGPIPE, sig_handler);
 
-	reset_tracing_files(ftrace);
+	if (reset_tracing_files(ftrace) < 0)
+		goto out;
 
 	/* reset ftrace buffer */
 	if (write_tracing_file("trace", "0") < 0)
 		goto out;
 
-	if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
-					  argv, false, ftrace__workload_exec_failed_signal) < 0)
+	if (argc && perf_evlist__prepare_workload(ftrace->evlist,
+				&ftrace->target, argv, false,
+				ftrace__workload_exec_failed_signal) < 0) {
 		goto out;
+	}
 
-	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
-		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
-		goto out;
+	if (set_tracing_pid(ftrace) < 0) {
+		pr_err("failed to set ftrace pid\n");
+		goto out_reset;
 	}
 
-	if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
-		pr_err("failed to allocate pid string\n");
-		goto out;
+	if (set_tracing_cpu(ftrace) < 0) {
+		pr_err("failed to set tracing cpumask\n");
+		goto out_reset;
 	}
 
-	if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
-		pr_err("failed to set pid: %s\n", trace_pid);
-		goto out_free_pid;
+	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+		goto out_reset;
 	}
 
 	trace_file = get_tracing_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
-		goto out_free_pid;
+		goto out_reset;
 	}
 
 	trace_fd = open(trace_file, O_RDONLY);
@@ -152,7 +240,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 
 	if (trace_fd < 0) {
 		pr_err("failed to open trace_pipe\n");
-		goto out_free_pid;
+		goto out_reset;
 	}
 
 	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
@@ -163,6 +251,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		goto out_close_fd;
 	}
 
+	setup_pager();
+
 	perf_evlist__start_workload(ftrace->evlist);
 
 	while (!done) {
@@ -191,11 +281,9 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 
 out_close_fd:
 	close(trace_fd);
-out_free_pid:
-	free(trace_pid);
-out:
+out_reset:
 	reset_tracing_files(ftrace);
-
+out:
 	return done ? 0 : -1;
 }
 
@@ -219,7 +307,7 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb)
 	return -1;
 }
 
-int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_ftrace(int argc, const char **argv)
 {
 	int ret;
 	struct perf_ftrace ftrace = {
@@ -227,15 +315,21 @@ int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
 		.target = { .uid = UINT_MAX, },
 	};
 	const char * const ftrace_usage[] = {
-		"perf ftrace [<options>] <command>",
+		"perf ftrace [<options>] [<command>]",
 		"perf ftrace [<options>] -- <command> [<options>]",
 		NULL
 	};
 	const struct option ftrace_options[] = {
 	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
 		   "tracer to use: function_graph(default) or function"),
+	OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
+		   "trace on existing process id"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose"),
+	OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
+		    "list of cpus to monitor"),
 	OPT_END()
 	};
 
@@ -245,9 +339,18 @@ int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc)
+	if (!argc && target__none(&ftrace.target))
 		usage_with_options(ftrace_usage, ftrace_options);
 
+	ret = target__validate(&ftrace.target);
+	if (ret) {
+		char errbuf[512];
+
+		target__strerror(&ftrace.target, ret, errbuf, 512);
+		pr_err("%s\n", errbuf);
+		return -EINVAL;
+	}
+
 	ftrace.evlist = perf_evlist__new();
 	if (ftrace.evlist == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index aed0d844e8c2..492f8e14ab09 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -12,16 +12,22 @@
 #include <subcmd/run-command.h>
 #include <subcmd/help.h>
 #include "util/debug.h"
+#include <linux/kernel.h>
+#include <errno.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 
 static struct man_viewer_list {
 	struct man_viewer_list *next;
-	char name[FLEX_ARRAY];
+	char name[0];
 } *man_viewer_list;
 
 static struct man_viewer_info_list {
 	struct man_viewer_info_list *next;
 	const char *info;
-	char name[FLEX_ARRAY];
+	char name[0];
 } *man_viewer_info_list;
 
 enum help_format {
@@ -301,12 +307,6 @@ void list_common_cmds_help(void)
 	}
 }
 
-static int is_perf_command(const char *s)
-{
-	return is_in_cmdlist(&main_cmds, s) ||
-		is_in_cmdlist(&other_cmds, s);
-}
-
 static const char *cmd_to_page(const char *perf_cmd)
 {
 	char *s;
@@ -418,7 +418,7 @@ static int show_html_page(const char *perf_cmd)
 	return 0;
 }
 
-int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_help(int argc, const char **argv)
 {
 	bool show_all = false;
 	enum help_format help_format = HELP_FORMAT_MAN;
@@ -446,7 +446,6 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf help [--all] [--man|--web|--info] [command]",
 		NULL
 	};
-	const char *alias;
 	int rc;
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
@@ -472,12 +471,6 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 		return 0;
 	}
 
-	alias = alias_lookup(argv[0]);
-	if (alias && !is_perf_command(argv[0])) {
-		printf("`perf %s' is aliased to `%s'\n", argv[0], alias);
-		return 0;
-	}
-
 	switch (help_format) {
 	case HELP_FORMAT_MAN:
 		rc = show_man_page(argv[0]);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b9bc7e39833a..ea8db38eedd1 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -18,10 +18,13 @@
 #include "util/data.h"
 #include "util/auxtrace.h"
 #include "util/jit.h"
+#include "util/thread.h"
 
 #include <subcmd/parse-options.h>
 
 #include <linux/list.h>
+#include <errno.h>
+#include <signal.h>
 
 struct perf_inject {
 	struct perf_tool	tool;
@@ -333,6 +336,18 @@ static int perf_event__repipe_comm(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_namespaces(struct perf_tool *tool,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct machine *machine)
+{
+	int err = perf_event__process_namespaces(tool, event, sample, machine);
+
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_exit(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -660,6 +675,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		session->itrace_synth_opts = &inject->itrace_synth_opts;
 		inject->itrace_synth_opts.inject = true;
 		inject->tool.comm	    = perf_event__repipe_comm;
+		inject->tool.namespaces	    = perf_event__repipe_namespaces;
 		inject->tool.exit	    = perf_event__repipe_exit;
 		inject->tool.id_index	    = perf_event__repipe_id_index;
 		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;
@@ -681,6 +697,8 @@ static int __cmd_inject(struct perf_inject *inject)
 		lseek(fd, output_data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session);
+	if (ret)
+		return ret;
 
 	if (!file_out->is_pipe) {
 		if (inject->build_ids)
@@ -725,7 +743,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	return ret;
 }
 
-int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_inject(int argc, const char **argv)
 {
 	struct perf_inject inject = {
 		.tool = {
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index 224bfc454b4a..bcfb363112d3 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -7,6 +7,7 @@
  *
  * Released under the GPL v2. (and only v2, not any later version)
  */
+#include <inttypes.h>
 #include "builtin.h"
 #include <linux/compiler.h>
 #include <subcmd/parse-options.h>
@@ -43,7 +44,7 @@ static int __cmd_kallsyms(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kallsyms(int argc, const char **argv)
 {
 	const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 6da8d083e4e5..9409c9464667 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -20,11 +20,16 @@
 
 #include "util/debug.h"
 
+#include <linux/kernel.h>
 #include <linux/rbtree.h>
 #include <linux/string.h>
+#include <errno.h>
+#include <inttypes.h>
 #include <locale.h>
 #include <regex.h>
 
+#include "sane_ctype.h"
+
 static int	kmem_slab;
 static int	kmem_page;
 
@@ -964,6 +969,7 @@ static struct perf_tool perf_kmem = {
 	.comm		 = perf_event__process_comm,
 	.mmap		 = perf_event__process_mmap,
 	.mmap2		 = perf_event__process_mmap2,
+	.namespaces	 = perf_event__process_namespaces,
 	.ordered_events	 = true,
 };
 
@@ -1865,7 +1871,7 @@ static int __cmd_record(int argc, const char **argv)
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
 static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
@@ -1884,7 +1890,7 @@ static int kmem_config(const char *var, const char *value, void *cb __maybe_unus
 	return 0;
 }
 
-int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kmem(int argc, const char **argv)
 {
 	const char * const default_slab_sort = "frag,hit,bytes";
 	const char * const default_page_sort = "bytes,hit";
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 08fa88f62a24..f309c3773522 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -3,6 +3,7 @@
 
 #include "util/evsel.h"
 #include "util/evlist.h"
+#include "util/term.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
@@ -23,13 +24,33 @@
 #ifdef HAVE_TIMERFD_SUPPORT
 #include <sys/timerfd.h>
 #endif
+#include <sys/time.h>
 
+#include <linux/kernel.h>
 #include <linux/time64.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <poll.h>
 #include <termios.h>
 #include <semaphore.h>
+#include <signal.h>
 #include <pthread.h>
 #include <math.h>
 
+static const char *get_filename_for_perf_kvm(void)
+{
+	const char *filename;
+
+	if (perf_host && !perf_guest)
+		filename = strdup("perf.data.host");
+	else if (!perf_host && perf_guest)
+		filename = strdup("perf.data.guest");
+	else
+		filename = strdup("perf.data.kvm");
+
+	return filename;
+}
+
 #ifdef HAVE_KVM_STAT_SUPPORT
 #include "util/kvm-stat.h"
 
@@ -1044,6 +1065,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	struct perf_tool eops = {
 		.sample			= process_sample_event,
 		.comm			= perf_event__process_comm,
+		.namespaces		= perf_event__process_namespaces,
 		.ordered_events		= true,
 	};
 	struct perf_data_file file = {
@@ -1208,7 +1230,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 	set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
 
 	record_usage = kvm_stat_record_usage;
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
 static int
@@ -1348,6 +1370,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->tool.exit   = perf_event__process_exit;
 	kvm->tool.fork   = perf_event__process_fork;
 	kvm->tool.lost   = process_lost_event;
+	kvm->tool.namespaces  = perf_event__process_namespaces;
 	kvm->tool.ordered_events = true;
 	perf_tool__fill_defaults(&kvm->tool);
 
@@ -1475,7 +1498,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 #endif
 
 perf_stat:
-	return cmd_stat(argc, argv, NULL);
+	return cmd_stat(argc, argv);
 }
 #endif /* HAVE_KVM_STAT_SUPPORT */
 
@@ -1494,7 +1517,7 @@ static int __cmd_record(const char *file_name, int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
 static int __cmd_report(const char *file_name, int argc, const char **argv)
@@ -1512,7 +1535,7 @@ static int __cmd_report(const char *file_name, int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_report(i, rec_argv, NULL);
+	return cmd_report(i, rec_argv);
 }
 
 static int
@@ -1531,10 +1554,10 @@ __cmd_buildid_list(const char *file_name, int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_buildid_list(i, rec_argv, NULL);
+	return cmd_buildid_list(i, rec_argv);
 }
 
-int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kvm(int argc, const char **argv)
 {
 	const char *file_name = NULL;
 	const struct option kvm_options[] = {
@@ -1589,9 +1612,9 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 	else if (!strncmp(argv[0], "rep", 3))
 		return __cmd_report(file_name, argc, argv);
 	else if (!strncmp(argv[0], "diff", 4))
-		return cmd_diff(argc, argv, NULL);
+		return cmd_diff(argc, argv);
 	else if (!strncmp(argv[0], "top", 3))
-		return cmd_top(argc, argv, NULL);
+		return cmd_top(argc, argv);
 	else if (!strncmp(argv[0], "buildid-list", 12))
 		return __cmd_buildid_list(file_name, argc, argv);
 #ifdef HAVE_KVM_STAT_SUPPORT
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 3b9d98b5feef..4bf2cb4d25aa 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -18,8 +18,9 @@
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;
+static bool details_flag;
 
-int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_list(int argc, const char **argv)
 {
 	int i;
 	bool raw_dump = false;
@@ -30,6 +31,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "Print extra event descriptions. --no-desc to not print."),
 		OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
 			    "Print longer event descriptions."),
+		OPT_BOOLEAN(0, "details", &details_flag,
+			    "Print information on the perf event names and expressions used internally by events."),
 		OPT_INCR(0, "debug", &verbose,
 			     "Enable debugging output"),
 		OPT_END()
@@ -50,7 +53,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 		printf("\nList of pre-defined events (to be used in -e):\n\n");
 
 	if (argc == 0) {
-		print_events(NULL, raw_dump, !desc_flag, long_desc_flag);
+		print_events(NULL, raw_dump, !desc_flag, long_desc_flag,
+				details_flag);
 		return 0;
 	}
 
@@ -72,7 +76,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, raw_dump, !desc_flag,
-						long_desc_flag);
+						long_desc_flag, details_flag);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
@@ -80,7 +84,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 
 			if (sep == NULL) {
 				print_events(argv[i], raw_dump, !desc_flag,
-							long_desc_flag);
+							long_desc_flag,
+							details_flag);
 				continue;
 			}
 			sep_idx = sep - argv[i];
@@ -103,7 +108,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
-						long_desc_flag);
+						long_desc_flag,
+						details_flag);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
 			free(s);
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index ce3bfb48b26f..ff98652484a7 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 #include "builtin.h"
 #include "perf.h"
 
@@ -26,6 +28,7 @@
 
 #include <linux/list.h>
 #include <linux/hash.h>
+#include <linux/kernel.h>
 
 static struct perf_session *session;
 
@@ -858,6 +861,7 @@ static int __cmd_report(bool display_info)
 	struct perf_tool eops = {
 		.sample		 = process_sample_event,
 		.comm		 = perf_event__process_comm,
+		.namespaces	 = perf_event__process_namespaces,
 		.ordered_events	 = true,
 	};
 	struct perf_data_file file = {
@@ -940,34 +944,36 @@ static int __cmd_record(int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	ret = cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv);
 	free(rec_argv);
 	return ret;
 }
 
-int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_lock(int argc, const char **argv)
 {
-	const struct option info_options[] = {
-	OPT_BOOLEAN('t', "threads", &info_threads,
-		    "dump thread list in perf.data"),
-	OPT_BOOLEAN('m', "map", &info_map,
-		    "map of lock instances (address:name table)"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
-	OPT_END()
-	};
 	const struct option lock_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	OPT_END()
 	};
+
+	const struct option info_options[] = {
+	OPT_BOOLEAN('t', "threads", &info_threads,
+		    "dump thread list in perf.data"),
+	OPT_BOOLEAN('m', "map", &info_map,
+		    "map of lock instances (address:name table)"),
+	OPT_PARENT(lock_options)
+	};
+
 	const struct option report_options[] = {
 	OPT_STRING('k', "key", &sort_key, "acquired",
 		    "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	/* TODO: type */
-	OPT_END()
+	OPT_PARENT(lock_options)
 	};
+
 	const char * const info_usage[] = {
 		"perf lock info [<options>]",
 		NULL
@@ -1006,7 +1012,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
 		rc = __cmd_report(false);
 	} else if (!strcmp(argv[0], "script")) {
 		/* Aliased to 'perf script' */
-		return cmd_script(argc, argv, prefix);
+		return cmd_script(argc, argv);
 	} else if (!strcmp(argv[0], "info")) {
 		if (argc) {
 			argc = parse_options(argc, argv,
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 6114e07ca613..e001c0290793 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -1,3 +1,7 @@
+#include <inttypes.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "builtin.h"
 #include "perf.h"
 
@@ -8,6 +12,7 @@
 #include "util/data.h"
 #include "util/mem-events.h"
 #include "util/debug.h"
+#include "util/symbol.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -129,7 +134,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		pr_debug("\n");
 	}
 
-	ret = cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv);
 	free(rec_argv);
 	return ret;
 }
@@ -256,7 +261,7 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	for (j = 1; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
 
-	ret = cmd_report(i, rep_argv, NULL);
+	ret = cmd_report(i, rep_argv);
 	free(rep_argv);
 	return ret;
 }
@@ -330,7 +335,7 @@ error:
 	return ret;
 }
 
-int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_mem(int argc, const char **argv)
 {
 	struct stat st;
 	struct perf_mem mem = {
@@ -342,6 +347,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
 			.build_id	= perf_event__process_build_id,
+			.namespaces	= perf_event__process_namespaces,
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 1fcebc31a508..d7360c2bda13 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -442,9 +442,9 @@ static int perf_del_probe_events(struct strfilter *filter)
 	}
 
 	if (ret == -ENOENT && ret2 == -ENOENT)
-		pr_debug("\"%s\" does not hit any event.\n", str);
-		/* Note that this is silently ignored */
-	ret = 0;
+		pr_warning("\"%s\" does not hit any event.\n", str);
+	else
+		ret = 0;
 
 error:
 	if (kfd >= 0)
@@ -468,7 +468,7 @@ out:
 
 
 static int
-__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+__cmd_probe(int argc, const char **argv)
 {
 	const char * const probe_usage[] = {
 		"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
@@ -687,13 +687,13 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	return 0;
 }
 
-int cmd_probe(int argc, const char **argv, const char *prefix)
+int cmd_probe(int argc, const char **argv)
 {
 	int ret;
 
 	ret = init_params();
 	if (!ret) {
-		ret = __cmd_probe(argc, argv, prefix);
+		ret = __cmd_probe(argc, argv);
 		cleanup_params();
 	}
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index bc84a375295d..ee7d0a82ccd0 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -38,11 +38,18 @@
 #include "util/bpf-loader.h"
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
+#include "util/time-utils.h"
+#include "util/units.h"
 #include "asm/bug.h"
 
+#include <errno.h>
+#include <inttypes.h>
+#include <poll.h>
 #include <unistd.h>
 #include <sched.h>
+#include <signal.h>
 #include <sys/mman.h>
+#include <sys/wait.h>
 #include <asm/bug.h>
 #include <linux/time64.h>
 
@@ -876,6 +883,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGTERM, sig_handler);
 	signal(SIGSEGV, sigsegv_handler);
 
+	if (rec->opts.record_namespaces)
+		tool->namespace_events = true;
+
 	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
@@ -983,6 +993,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 */
 	if (forks) {
 		union perf_event *event;
+		pid_t tgid;
 
 		event = malloc(sizeof(event->comm) + machine->id_hdr_size);
 		if (event == NULL) {
@@ -996,10 +1007,30 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * cannot see a correct process name for those events.
 		 * Synthesize COMM event to prevent it.
 		 */
-		perf_event__synthesize_comm(tool, event,
-					    rec->evlist->workload.pid,
-					    process_synthesized_event,
-					    machine);
+		tgid = perf_event__synthesize_comm(tool, event,
+						   rec->evlist->workload.pid,
+						   process_synthesized_event,
+						   machine);
+		free(event);
+
+		if (tgid == -1)
+			goto out_child;
+
+		event = malloc(sizeof(event->namespaces) +
+			       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			       machine->id_hdr_size);
+		if (event == NULL) {
+			err = -ENOMEM;
+			goto out_child;
+		}
+
+		/*
+		 * Synthesize NAMESPACES event for the command specified.
+		 */
+		perf_event__synthesize_namespaces(tool, event,
+						  rec->evlist->workload.pid,
+						  tgid, process_synthesized_event,
+						  machine);
 		free(event);
 
 		perf_evlist__start_workload(rec->evlist);
@@ -1497,6 +1528,7 @@ static struct record record = {
 		.fork		= perf_event__process_fork,
 		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
+		.namespaces	= perf_event__process_namespaces,
 		.mmap		= perf_event__process_mmap,
 		.mmap2		= perf_event__process_mmap2,
 		.ordered_events	= true,
@@ -1611,6 +1643,8 @@ static struct option __record_options[] = {
 			  "opts", "AUX area tracing Snapshot Mode", ""),
 	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
+		    "Record namespaces events"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
 	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
@@ -1640,7 +1674,7 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
-int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_record(int argc, const char **argv)
 {
 	int err;
 	struct record *rec = &record;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0a88670e56f3..22478ff2b706 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -16,7 +16,6 @@
 #include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
-#include "util/strlist.h"
 #include "util/values.h"
 
 #include "perf.h"
@@ -38,10 +37,18 @@
 #include "arch/common.h"
 #include "util/time-utils.h"
 #include "util/auxtrace.h"
+#include "util/units.h"
 
 #include <dlfcn.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <regex.h>
+#include <signal.h>
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 
 struct report {
 	struct perf_tool	tool;
@@ -394,8 +401,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		fprintf(stdout, "\n\n");
 	}
 
-	if (sort_order == NULL &&
-	    parent_pattern == default_parent_pattern)
+	if (!quiet)
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
 	if (rep->show_threads) {
@@ -682,7 +688,7 @@ const char report_callchain_help[] = "Display call graph (stack chain/backtrace)
 				     CALLCHAIN_REPORT_HELP
 				     "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
 
-int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_report(int argc, const char **argv)
 {
 	struct perf_session *session;
 	struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
@@ -701,6 +707,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mmap		 = perf_event__process_mmap,
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.lost		 = perf_event__process_lost,
@@ -845,6 +852,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			     stdio__config_color, "always"),
 	OPT_STRING(0, "time", &report.time_str, "str",
 		   "Time span of interest (start,stop)"),
+	OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+		    "Show inline function"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b94cf0de715a..39996c53995a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -22,16 +22,21 @@
 
 #include "util/debug.h"
 
+#include <linux/kernel.h>
 #include <linux/log2.h>
 #include <sys/prctl.h>
 #include <sys/resource.h>
+#include <inttypes.h>
 
+#include <errno.h>
 #include <semaphore.h>
 #include <pthread.h>
 #include <math.h>
 #include <api/fs/fs.h>
 #include <linux/time64.h>
 
+#include "sane_ctype.h"
+
 #define PR_SET_NAME		15               /* Set process name */
 #define MAX_CPUS		4096
 #define COMM_LEN		20
@@ -221,6 +226,7 @@ struct perf_sched {
 	unsigned int	max_stack;
 	bool		show_cpu_visual;
 	bool		show_wakeups;
+	bool		show_next;
 	bool		show_migrations;
 	bool		show_state;
 	u64		skipped_samples;
@@ -1897,14 +1903,18 @@ static char task_state_char(struct thread *thread, int state)
 }
 
 static void timehist_print_sample(struct perf_sched *sched,
+				  struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
 				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
+	const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm");
+	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
+	char nstr[30];
 	u64 wait_time;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
@@ -1937,7 +1947,12 @@ static void timehist_print_sample(struct perf_sched *sched,
 	if (sched->show_state)
 		printf(" %5c ", task_state_char(thread, state));
 
-	if (sched->show_wakeups)
+	if (sched->show_next) {
+		snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid);
+		printf(" %-*s", comm_width, nstr);
+	}
+
+	if (sched->show_wakeups && !sched->show_next)
 		printf("  %-*s", comm_width, "");
 
 	if (thread->tid == 0)
@@ -2531,7 +2546,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->summary_only)
-		timehist_print_sample(sched, sample, &al, thread, t, state);
+		timehist_print_sample(sched, evsel, sample, &al, thread, t, state);
 
 out:
 	if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -3262,16 +3277,17 @@ static int __cmd_record(int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
-int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_sched(int argc, const char **argv)
 {
 	const char default_sort_order[] = "avg, max, switch, runtime";
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
 			.ordered_events = true,
@@ -3340,6 +3356,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('S', "with-summary", &sched.summary,
 		    "Show all syscalls and summary with statistics"),
 	OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"),
+	OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"),
 	OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"),
 	OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"),
 	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
@@ -3400,7 +3417,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	 * Aliased to 'perf script' for now:
 	 */
 	if (!strcmp(argv[0], "script"))
-		return cmd_script(argc, argv, prefix);
+		return cmd_script(argc, argv);
 
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
@@ -3437,10 +3454,14 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			if (argc)
 				usage_with_options(timehist_usage, timehist_options);
 		}
-		if (sched.show_wakeups && sched.summary_only) {
-			pr_err(" Error: -s and -w are mutually exclusive.\n");
+		if ((sched.show_wakeups || sched.show_next) &&
+		    sched.summary_only) {
+			pr_err(" Error: -s and -[n|w] are mutually exclusive.\n");
 			parse_options_usage(timehist_usage, timehist_options, "s", true);
-			parse_options_usage(NULL, timehist_options, "w", true);
+			if (sched.show_wakeups)
+				parse_options_usage(NULL, timehist_options, "w", true);
+			if (sched.show_next)
+				parse_options_usage(NULL, timehist_options, "n", true);
 			return -EINVAL;
 		}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c0783b4f7b6c..d05aec491cff 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -21,13 +21,27 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/string2.h"
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
+#include "print_binary.h"
 #include <linux/bitmap.h>
+#include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
+#include "util/dump-insn.h"
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "sane_ctype.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -42,6 +56,7 @@ static bool			nanosecs;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
+static int			max_blocks;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -69,6 +84,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
+	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
 };
 
 struct output_option {
@@ -98,6 +114,7 @@ struct output_option {
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
+	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 };
 
 /* default set to maintain compatibility with current format */
@@ -292,7 +309,13 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-
+	if (PRINT_FIELD(BRSTACKINSN) &&
+	    !(perf_evlist__combined_branch_type(session->evlist) &
+	      PERF_SAMPLE_BRANCH_ANY)) {
+		pr_err("Display of branch stack assembler requested, but non all-branch filter set\n"
+		       "Hint: run 'perf record -b ...'\n");
+		return -EINVAL;
+	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -546,6 +569,233 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 	}
 }
 
+#define MAXBB 16384UL
+
+static int grab_bb(u8 *buffer, u64 start, u64 end,
+		    struct machine *machine, struct thread *thread,
+		    bool *is64bit, u8 *cpumode, bool last)
+{
+	long offset, len;
+	struct addr_location al;
+	bool kernel;
+
+	if (!start || !end)
+		return 0;
+
+	kernel = machine__kernel_ip(machine, start);
+	if (kernel)
+		*cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		*cpumode = PERF_RECORD_MISC_USER;
+
+	/*
+	 * Block overlaps between kernel and user.
+	 * This can happen due to ring filtering
+	 * On Intel CPUs the entry into the kernel is filtered,
+	 * but the exit is not. Let the caller patch it up.
+	 */
+	if (kernel != machine__kernel_ip(machine, end)) {
+		printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
+				start, end);
+		return -ENXIO;
+	}
+
+	memset(&al, 0, sizeof(al));
+	if (end - start > MAXBB - MAXINSN) {
+		if (last)
+			printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+		else
+			printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+		return 0;
+	}
+
+	thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
+	if (!al.map || !al.map->dso) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+		return 0;
+	}
+	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+		return 0;
+	}
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al.map);
+
+	offset = al.map->map_ip(al.map, start);
+	len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer,
+				    end - start + MAXINSN);
+
+	*is64bit = al.map->dso->is_64_bit;
+	if (len <= 0)
+		printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+			start, end);
+	return len;
+}
+
+static void print_jump(uint64_t ip, struct branch_entry *en,
+		       struct perf_insn *x, u8 *inbuf, int len,
+		       int insn)
+{
+	printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
+	       ip,
+	       dump_insn(x, ip, inbuf, len, NULL),
+	       en->flags.predicted ? " PRED" : "",
+	       en->flags.mispred ? " MISPRED" : "",
+	       en->flags.in_tx ? " INTX" : "",
+	       en->flags.abort ? " ABORT" : "");
+	if (en->flags.cycles) {
+		printf(" %d cycles", en->flags.cycles);
+		if (insn)
+			printf(" %.2f IPC", (float)insn / en->flags.cycles);
+	}
+	putchar('\n');
+}
+
+static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
+			 uint64_t addr, struct symbol **lastsym,
+			 struct perf_event_attr *attr)
+{
+	struct addr_location al;
+	int off;
+
+	memset(&al, 0, sizeof(al));
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
+	if (!al.map)
+		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
+				      addr, &al);
+	if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
+		return;
+
+	al.cpu = cpu;
+	al.sym = NULL;
+	if (al.map)
+		al.sym = map__find_symbol(al.map, al.addr);
+
+	if (!al.sym)
+		return;
+
+	if (al.addr < al.sym->end)
+		off = al.addr - al.sym->start;
+	else
+		off = al.addr - al.map->start - al.sym->start;
+	printf("\t%s", al.sym->name);
+	if (off)
+		printf("%+d", off);
+	putchar(':');
+	if (PRINT_FIELD(SRCLINE))
+		map__fprintf_srcline(al.map, al.addr, "\t", stdout);
+	putchar('\n');
+	*lastsym = al.sym;
+}
+
+static void print_sample_brstackinsn(struct perf_sample *sample,
+				     struct thread *thread,
+				     struct perf_event_attr *attr,
+				     struct machine *machine)
+{
+	struct branch_stack *br = sample->branch_stack;
+	u64 start, end;
+	int i, insn, len, nr, ilen;
+	struct perf_insn x;
+	u8 buffer[MAXBB];
+	unsigned off;
+	struct symbol *lastsym = NULL;
+
+	if (!(br && br->nr))
+		return;
+	nr = br->nr;
+	if (max_blocks && nr > max_blocks + 1)
+		nr = max_blocks + 1;
+
+	x.thread = thread;
+	x.cpu = sample->cpu;
+
+	putchar('\n');
+
+	/* Handle first from jump, of which we don't know the entry. */
+	len = grab_bb(buffer, br->entries[nr-1].from,
+			br->entries[nr-1].from,
+			machine, thread, &x.is64bit, &x.cpumode, false);
+	if (len > 0) {
+		print_ip_sym(thread, x.cpumode, x.cpu,
+			     br->entries[nr - 1].from, &lastsym, attr);
+		print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+			    &x, buffer, len, 0);
+	}
+
+	/* Print all blocks */
+	for (i = nr - 2; i >= 0; i--) {
+		if (br->entries[i].from || br->entries[i].to)
+			pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
+				 br->entries[i].from,
+				 br->entries[i].to);
+		start = br->entries[i + 1].to;
+		end   = br->entries[i].from;
+
+		len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+		/* Patch up missing kernel transfers due to ring filters */
+		if (len == -ENXIO && i > 0) {
+			end = br->entries[--i].from;
+			pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
+			len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+		}
+		if (len <= 0)
+			continue;
+
+		insn = 0;
+		for (off = 0;; off += ilen) {
+			uint64_t ip = start + off;
+
+			print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+			if (ip == end) {
+				print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+				break;
+			} else {
+				printf("\t%016" PRIx64 "\t%s\n", ip,
+					dump_insn(&x, ip, buffer + off, len - off, &ilen));
+				if (ilen == 0)
+					break;
+				insn++;
+			}
+		}
+	}
+
+	/*
+	 * Hit the branch? In this case we are already done, and the target
+	 * has not been executed yet.
+	 */
+	if (br->entries[0].from == sample->ip)
+		return;
+	if (br->entries[0].flags.abort)
+		return;
+
+	/*
+	 * Print final block upto sample
+	 */
+	start = br->entries[0].to;
+	end = sample->ip;
+	len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
+	print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+	if (len <= 0) {
+		/* Print at least last IP if basic block did not work */
+		len = grab_bb(buffer, sample->ip, sample->ip,
+			      machine, thread, &x.is64bit, &x.cpumode, false);
+		if (len <= 0)
+			return;
+
+		printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+			dump_insn(&x, sample->ip, buffer, len, NULL));
+		return;
+	}
+	for (off = 0; off <= end - start; off += ilen) {
+		printf("\t%016" PRIx64 "\t%s\n", start + off,
+			dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+		if (ilen == 0)
+			break;
+	}
+}
 
 static void print_sample_addr(struct perf_sample *sample,
 			  struct thread *thread,
@@ -632,7 +882,9 @@ static void print_sample_callindent(struct perf_sample *sample,
 }
 
 static void print_insn(struct perf_sample *sample,
-		       struct perf_event_attr *attr)
+		       struct perf_event_attr *attr,
+		       struct thread *thread,
+		       struct machine *machine)
 {
 	if (PRINT_FIELD(INSNLEN))
 		printf(" ilen: %d", sample->insn_len);
@@ -643,12 +895,15 @@ static void print_insn(struct perf_sample *sample,
 		for (i = 0; i < sample->insn_len; i++)
 			printf(" %02x", (unsigned char)sample->insn[i]);
 	}
+	if (PRINT_FIELD(BRSTACKINSN))
+		print_sample_brstackinsn(sample, thread, attr, machine);
 }
 
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
-			     struct addr_location *al)
+			     struct addr_location *al,
+			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
@@ -689,7 +944,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
-	print_insn(sample, attr);
+	print_insn(sample, attr, thread, machine);
 
 	printf("\n");
 }
@@ -830,6 +1085,7 @@ struct perf_script {
 	bool			show_task_events;
 	bool			show_mmap_events;
 	bool			show_switch_events;
+	bool			show_namespace_events;
 	bool			allocated;
 	struct cpu_map		*cpus;
 	struct thread_map	*threads;
@@ -871,7 +1127,8 @@ static size_t data_src__printf(u64 data_src)
 
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
-			  struct addr_location *al)
+			  struct addr_location *al,
+			  struct machine *machine)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -898,7 +1155,7 @@ static void process_event(struct perf_script *script,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(sample, evsel, thread, al);
+		print_sample_bts(sample, evsel, thread, al, machine);
 		return;
 	}
 
@@ -936,7 +1193,7 @@ static void process_event(struct perf_script *script,
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-	print_insn(sample, attr);
+	print_insn(sample, attr, thread, machine);
 	printf("\n");
 }
 
@@ -1046,7 +1303,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al, machine);
 
 out_put:
 	addr_location__put(&al);
@@ -1118,6 +1375,41 @@ out:
 	return ret;
 }
 
+static int process_namespaces_event(struct perf_tool *tool,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->namespaces.pid,
+					 event->namespaces.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing NAMESPACES event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_namespaces(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->namespaces.tid;
+		sample->pid = event->namespaces.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+out:
+	thread__put(thread);
+	return ret;
+}
+
 static int process_fork_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample,
@@ -1293,6 +1585,8 @@ static int __cmd_script(struct perf_script *script)
 	}
 	if (script->show_switch_events)
 		script->tool.context_switch = process_switch_event;
+	if (script->show_namespace_events)
+		script->tool.namespaces = process_namespaces_event;
 
 	ret = perf_session__process_events(script->session);
 
@@ -1427,7 +1721,7 @@ static int parse_scriptname(const struct option *opt __maybe_unused,
 static int parse_output_fields(const struct option *opt __maybe_unused,
 			    const char *arg, int unset __maybe_unused)
 {
-	char *tok;
+	char *tok, *strtok_saveptr = NULL;
 	int i, imax = ARRAY_SIZE(all_output_options);
 	int j;
 	int rc = 0;
@@ -1488,7 +1782,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 		}
 	}
 
-	for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
+	for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) {
 		for (i = 0; i < imax; ++i) {
 			if (strcmp(tok, all_output_options[i].str) == 0)
 				break;
@@ -2078,7 +2372,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
-int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
 	bool header = false;
@@ -2097,6 +2391,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mmap		 = perf_event__process_mmap,
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.attr		 = process_attr,
@@ -2152,7 +2447,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen,brstackinsn",
+		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -2180,7 +2476,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the mmap events"),
 	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
 		    "Show context switch events (if recorded)"),
+	OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
+		    "Show namespace events (if recorded)"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+	OPT_INTEGER(0, "max-blocks", &max_blocks,
+		    "Maximum number of code blocks to dump with brstackinsn"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2217,7 +2517,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
 		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
 		if (!rec_script_path)
-			return cmd_record(argc, argv, NULL);
+			return cmd_record(argc, argv);
 	}
 
 	if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 13b54999ad79..a935b5023732 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -64,14 +64,24 @@
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/group.h"
+#include "util/string2.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
 #include <api/fs/fs.h>
+#include <errno.h>
+#include <signal.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
+#include <inttypes.h>
 #include <locale.h>
 #include <math.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "sane_ctype.h"
 
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"
@@ -140,12 +150,14 @@ static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			metric_only			= false;
 static bool			force_metric_only		= false;
+static bool			no_merge			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static const char		*output_name;
 static int			output_fd;
+static int			print_free_counters_hint;
 
 struct perf_stat {
 	bool			 record;
@@ -310,8 +322,12 @@ static int read_counter(struct perf_evsel *counter)
 			struct perf_counts_values *count;
 
 			count = perf_counts(counter->counts, cpu, thread);
-			if (perf_evsel__read(counter, cpu, thread, count))
+			if (perf_evsel__read(counter, cpu, thread, count)) {
+				counter->counts->scaled = -1;
+				perf_counts(counter->counts, cpu, thread)->ena = 0;
+				perf_counts(counter->counts, cpu, thread)->run = 0;
 				return -1;
+			}
 
 			if (STAT_RECORD) {
 				if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
@@ -336,12 +352,14 @@ static int read_counter(struct perf_evsel *counter)
 static void read_counters(void)
 {
 	struct perf_evsel *counter;
+	int ret;
 
 	evlist__for_each_entry(evsel_list, counter) {
-		if (read_counter(counter))
+		ret = read_counter(counter);
+		if (ret)
 			pr_debug("failed to read counter %s\n", counter->name);
 
-		if (perf_stat_process_counter(&stat_config, counter))
+		if (ret == 0 && perf_stat_process_counter(&stat_config, counter))
 			pr_warning("failed to process counter %s\n", counter->name);
 	}
 }
@@ -873,10 +891,7 @@ static void print_metric_csv(void *ctx,
 		return;
 	}
 	snprintf(buf, sizeof(buf), fmt, val);
-	vals = buf;
-	while (isspace(*vals))
-		vals++;
-	ends = vals;
+	ends = vals = ltrim(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
 	*ends = 0;
@@ -948,10 +963,7 @@ static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
 	snprintf(buf, sizeof buf, fmt, val);
-	vals = buf;
-	while (isspace(*vals))
-		vals++;
-	ends = vals;
+	ends = vals = ltrim(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
 	*ends = 0;
@@ -1109,6 +1121,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep);
 
+		if (counter->supported)
+			print_free_counters_hint = 1;
+
 		fprintf(stat_config.output, "%-*s%s",
 			csv_output ? 0 : unit_width,
 			counter->unit, csv_sep);
@@ -1140,6 +1155,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.print_metric = pm;
 	out.new_line = nl;
 	out.ctx = &os;
+	out.force_header = false;
 
 	if (csv_output && !metric_only) {
 		print_noise(counter, noise);
@@ -1178,11 +1194,81 @@ static void aggr_update_shadow(void)
 	}
 }
 
+static void collect_all_aliases(struct perf_evsel *counter,
+			    void (*cb)(struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evsel_list->entries), node);
+	list_for_each_entry_continue (alias, &evsel_list->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    nsec_counter(alias) != nsec_counter(counter))
+			break;
+		alias->merged_stat = true;
+		cb(alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_evsel *counter,
+			    void (*cb)(struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(counter, data, true);
+	if (!no_merge)
+		collect_all_aliases(counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
 static void print_aggr(char *prefix)
 {
 	FILE *output = stat_config.output;
 	struct perf_evsel *counter;
-	int cpu, s, s2, id, nr;
+	int s, id, nr;
 	double uval;
 	u64 ena, run, val;
 	bool first;
@@ -1197,23 +1283,21 @@ static void print_aggr(char *prefix)
 	 * Without each counter has its own line.
 	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		struct aggr_data ad;
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
-		id = aggr_map->map[s];
+		ad.id = id = aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evsel_list, counter) {
-			val = ena = run = 0;
-			nr = 0;
-			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
-				if (s2 != id)
-					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
-				ena += perf_counts(counter->counts, cpu, 0)->ena;
-				run += perf_counts(counter->counts, cpu, 0)->run;
-				nr++;
-			}
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			if (!collect_data(counter, aggr_cb, &ad))
+				continue;
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
 			if (first && metric_only) {
 				first = false;
 				aggr_printout(counter, id, nr);
@@ -1257,6 +1341,21 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->priv;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -1264,23 +1363,31 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
 	FILE *output = stat_config.output;
-	struct perf_stat_evsel *ps = counter->priv;
-	double avg = avg_stats(&ps->res_stats[0]);
 	double uval;
-	double avg_enabled, avg_running;
+	struct caggr_data cd = { .avg = 0.0 };
 
-	avg_enabled = avg_stats(&ps->res_stats[1]);
-	avg_running = avg_stats(&ps->res_stats[2]);
+	if (!collect_data(counter, counter_aggr_cb, &cd))
+		return;
 
 	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
-	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+	uval = cd.avg * counter->scale;
+	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
 	if (!metric_only)
 		fprintf(output, "\n");
 }
 
+static void counter_cb(struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
 /*
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
@@ -1293,9 +1400,13 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = perf_counts(counter->counts, cpu, 0)->val;
-		ena = perf_counts(counter->counts, cpu, 0)->ena;
-		run = perf_counts(counter->counts, cpu, 0)->run;
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
@@ -1380,6 +1491,7 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
 		out.new_line = new_line_metric;
+		out.force_header = true;
 		os.evsel = counter;
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
@@ -1477,6 +1589,13 @@ static void print_footer(void)
 				avg_stats(&walltime_nsecs_stats));
 	}
 	fprintf(output, "\n\n");
+
+	if (print_free_counters_hint)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
 }
 
 static void print_counters(struct timespec *ts, int argc, const char **argv)
@@ -1633,6 +1752,7 @@ static const struct option stat_options[] = {
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
 		    "disable CPU count aggregation", AGGR_NONE),
+	OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
 	OPT_STRING('x', "field-separator", &csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
@@ -2339,7 +2459,36 @@ static int __cmd_report(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
+static void setup_system_wide(int forks)
+{
+	/*
+	 * Make system wide (-a) the default target if
+	 * no target was specified and one of following
+	 * conditions is met:
+	 *
+	 *   - there's no workload specified
+	 *   - there is workload specified but all requested
+	 *     events are system wide events
+	 */
+	if (!target__none(&target))
+		return;
+
+	if (!forks)
+		target.system_wide = true;
+	else {
+		struct perf_evsel *counter;
+
+		evlist__for_each_entry(evsel_list, counter) {
+			if (!counter->system_wide)
+				return;
+		}
+
+		if (evsel_list->nr_entries)
+			target.system_wide = true;
+	}
+}
+
+int cmd_stat(int argc, const char **argv)
 {
 	const char * const stat_usage[] = {
 		"perf stat [<options>] [<command>]",
@@ -2361,6 +2510,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
+	perf_stat__collect_metric_expr(evsel_list);
 	perf_stat__init_shadow_stats();
 
 	if (csv_sep) {
@@ -2445,9 +2595,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		big_num = false;
 
-	/* Make system wide (-a) the default target. */
-	if (!argc && target__none(&target))
-		target.system_wide = true;
+	setup_system_wide(argc);
 
 	if (run_count < 0) {
 		pr_err("Run count must be a positive number\n");
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e7eaa298d34a..4e2e61695986 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -12,6 +12,8 @@
  * of the License.
  */
 
+#include <errno.h>
+#include <inttypes.h>
 #include <traceevent/event-parse.h>
 
 #include "builtin.h"
@@ -23,11 +25,12 @@
 #include "util/cache.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include <linux/kernel.h>
 #include <linux/rbtree.h>
 #include <linux/time64.h>
 #include "util/symbol.h"
+#include "util/thread.h"
 #include "util/callchain.h"
-#include "util/strlist.h"
 
 #include "perf.h"
 #include "util/header.h"
@@ -1773,7 +1776,7 @@ static int timechart__io_record(int argc, const char **argv)
 	for (i = 0; i < (unsigned int)argc; i++)
 		*p++ = argv[i];
 
-	return cmd_record(rec_argc, rec_argv, NULL);
+	return cmd_record(rec_argc, rec_argv);
 }
 
 
@@ -1864,7 +1867,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar
 	for (j = 0; j < (unsigned int)argc; j++)
 		*p++ = argv[j];
 
-	return cmd_record(rec_argc, rec_argv, NULL);
+	return cmd_record(rec_argc, rec_argv);
 }
 
 static int
@@ -1917,8 +1920,7 @@ parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
 	return 0;
 }
 
-int cmd_timechart(int argc, const char **argv,
-		  const char *prefix __maybe_unused)
+int cmd_timechart(int argc, const char **argv)
 {
 	struct timechart tchart = {
 		.tool = {
@@ -1933,6 +1935,11 @@ int cmd_timechart(int argc, const char **argv,
 		.merge_dist = 1000,
 	};
 	const char *output_name = "output.svg";
+	const struct option timechart_common_options[] = {
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"),
+	OPT_END()
+	};
 	const struct option timechart_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
@@ -1940,9 +1947,6 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
 		      "highlight tasks. Pass duration in ns or process name.",
 		       parse_highlight),
-	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
-	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
-		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
@@ -1962,22 +1966,18 @@ int cmd_timechart(int argc, const char **argv,
 		     "merge events that are merge-dist us apart",
 		     parse_time),
 	OPT_BOOLEAN('f', "force", &tchart.force, "don't complain, do it"),
-	OPT_END()
+	OPT_PARENT(timechart_common_options),
 	};
 	const char * const timechart_subcommands[] = { "record", NULL };
 	const char *timechart_usage[] = {
 		"perf timechart [<options>] {record}",
 		NULL
 	};
-
 	const struct option timechart_record_options[] = {
-	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
-	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
-		    "output processes data only"),
 	OPT_BOOLEAN('I', "io-only", &tchart.io_only,
 		    "record only IO data"),
 	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
-	OPT_END()
+	OPT_PARENT(timechart_common_options),
 	};
 	const char * const timechart_record_usage[] = {
 		"perf timechart record [<options>]",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ab9077915763..7ab42b8311a1 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -40,6 +40,7 @@
 #include "util/cpumap.h"
 #include "util/xyarray.h"
 #include "util/sort.h"
+#include "util/term.h"
 #include "util/intlist.h"
 #include "util/parse-branch-options.h"
 #include "arch/common.h"
@@ -58,6 +59,7 @@
 #include <errno.h>
 #include <time.h>
 #include <sched.h>
+#include <signal.h>
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
@@ -72,6 +74,8 @@
 #include <linux/time64.h>
 #include <linux/types.h>
 
+#include "sane_ctype.h"
+
 static volatile int done;
 
 #define HEADER_LINE_NR  5
@@ -1075,7 +1079,7 @@ parse_percent_limit(const struct option *opt, const char *arg,
 const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP
 	"\n\t\t\t\tDefault: fp,graph,0.5,caller,function";
 
-int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_top(int argc, const char **argv)
 {
 	char errbuf[BUFSIZ];
 	struct perf_top top = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 256f1fac6f7e..eaa66fb57347 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -24,6 +24,7 @@
 #include "util/evlist.h"
 #include <subcmd/exec-cmd.h>
 #include "util/machine.h"
+#include "util/path.h"
 #include "util/session.h"
 #include "util/thread.h"
 #include <subcmd/parse-options.h>
@@ -31,23 +32,33 @@
 #include "util/intlist.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "trace/beauty/beauty.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
 #include "util/bpf-loader.h"
 #include "callchain.h"
+#include "print_binary.h"
+#include "string2.h"
 #include "syscalltbl.h"
 #include "rb_resort.h"
 
+#include <errno.h>
+#include <inttypes.h>
 #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
+#include <poll.h>
+#include <signal.h>
 #include <stdlib.h>
 #include <string.h>
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
+#include <linux/kernel.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
 
+#include "sane_ctype.h"
+
 #ifndef O_CLOEXEC
 # define O_CLOEXEC		02000000
 #endif
@@ -267,15 +278,6 @@ out_delete:
 	({ struct syscall_tp *fields = evsel->priv; \
 	   fields->name.pointer(&fields->name, sample); })
 
-struct syscall_arg {
-	unsigned long val;
-	struct thread *thread;
-	struct trace  *trace;
-	void	      *parm;
-	u8	      idx;
-	u8	      mask;
-};
-
 struct strarray {
 	int	    offset;
 	int	    nr_entries;
@@ -771,6 +773,10 @@ static struct syscall_fmt {
 	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
 	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
 	{ .name	    = "statfs",	    .errmsg = true, },
+	{ .name	    = "statx",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* flags */
+			     [2] = SCA_STATX_FLAGS, /* flags */
+			     [3] = SCA_STATX_MASK, /* mask */ }, },
 	{ .name	    = "swapoff",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
 	{ .name	    = "swapon",	    .errmsg = true,
@@ -821,12 +827,21 @@ struct syscall {
 	void		    **arg_parm;
 };
 
-static size_t fprintf_duration(unsigned long t, FILE *fp)
+/*
+ * We need to have this 'calculated' boolean because in some cases we really
+ * don't know what is the duration of a syscall, for instance, when we start
+ * a session and some threads are waiting for a syscall to finish, say 'poll',
+ * in which case all we can do is to print "( ? ) for duration and for the
+ * start timestamp.
+ */
+static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
 {
 	double duration = (double)t / NSEC_PER_MSEC;
 	size_t printed = fprintf(fp, "(");
 
-	if (duration >= 1.0)
+	if (!calculated)
+		printed += fprintf(fp, "     ?   ");
+	else if (duration >= 1.0)
 		printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
 	else if (duration >= 0.01)
 		printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
@@ -1028,13 +1043,27 @@ static bool trace__filter_duration(struct trace *trace, double t)
 	return t < (trace->duration_filter * NSEC_PER_MSEC);
 }
 
-static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
+static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 {
 	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;
 
 	return fprintf(fp, "%10.3f ", ts);
 }
 
+/*
+ * We're handling tstamp=0 as an undefined tstamp, i.e. like when we are
+ * using ttrace->entry_time for a thread that receives a sys_exit without
+ * first having received a sys_enter ("poll" issued before tracing session
+ * starts, lost sys_enter exit due to ring buffer overflow).
+ */
+static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
+{
+	if (tstamp > 0)
+		return __trace__fprintf_tstamp(trace, tstamp, fp);
+
+	return fprintf(fp, "         ? ");
+}
+
 static bool done = false;
 static bool interrupted = false;
 
@@ -1045,10 +1074,10 @@ static void sig_handler(int sig)
 }
 
 static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
-					u64 duration, u64 tstamp, FILE *fp)
+					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
 {
 	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
-	printed += fprintf_duration(duration, fp);
+	printed += fprintf_duration(duration, duration_calculated, fp);
 
 	if (trace->multiple_threads) {
 		if (trace->show_comm)
@@ -1450,7 +1479,7 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp
 
 	duration = sample->time - ttrace->entry_time;
 
-	printed  = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output);
+	printed  = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output);
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
@@ -1497,7 +1526,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
-			trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output);
+			trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
 			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
@@ -1545,6 +1574,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 {
 	long ret;
 	u64 duration = 0;
+	bool duration_calculated = false;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
@@ -1573,6 +1603,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		duration = sample->time - ttrace->entry_time;
 		if (trace__filter_duration(trace, duration))
 			goto out;
+		duration_calculated = true;
 	} else if (trace->duration_filter)
 		goto out;
 
@@ -1588,7 +1619,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->summary_only)
 		goto out;
 
-	trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output);
+	trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
 
 	if (ttrace->entry_pending) {
 		fprintf(trace->output, "%-70s", ttrace->entry_str);
@@ -1653,15 +1684,17 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 
 	ttrace = thread__priv(thread);
 	if (!ttrace)
-		goto out;
+		goto out_put;
 
 	filename_len = strlen(filename);
+	if (filename_len == 0)
+		goto out_put;
 
 	if (ttrace->filename.namelen < filename_len) {
 		char *f = realloc(ttrace->filename.name, filename_len + 1);
 
 		if (f == NULL)
-				goto out;
+			goto out_put;
 
 		ttrace->filename.namelen = filename_len;
 		ttrace->filename.name = f;
@@ -1671,12 +1704,12 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 	ttrace->filename.pending_open = true;
 
 	if (!ttrace->filename.ptr)
-		goto out;
+		goto out_put;
 
 	entry_str_len = strlen(ttrace->entry_str);
 	remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
 	if (remaining_space <= 0)
-		goto out;
+		goto out_put;
 
 	if (filename_len > (size_t)remaining_space) {
 		filename += filename_len - remaining_space;
@@ -1690,6 +1723,8 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 
 	ttrace->filename.ptr = 0;
 	ttrace->filename.entry_str_pos = 0;
+out_put:
+	thread__put(thread);
 out:
 	return 0;
 }
@@ -1710,6 +1745,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 
 	ttrace->runtime_ms += runtime_ms;
 	trace->runtime_ms += runtime_ms;
+out_put:
 	thread__put(thread);
 	return 0;
 
@@ -1720,8 +1756,7 @@ out_dump:
 	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
 	       runtime,
 	       perf_evsel__intval(evsel, sample, "vruntime"));
-	thread__put(thread);
-	return 0;
+	goto out_put;
 }
 
 static void bpf_output__printer(enum binary_printer_ops op,
@@ -1851,7 +1886,7 @@ static int trace__pgfault(struct trace *trace,
 	thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
 
-	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
+	trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
 
 	fprintf(trace->output, "%sfault [",
 		evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
@@ -1920,7 +1955,7 @@ static int trace__process_sample(struct perf_tool *tool,
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	if (thread && thread__is_filtered(thread))
-		return 0;
+		goto out;
 
 	trace__set_base_time(trace, evsel, sample);
 
@@ -1928,7 +1963,8 @@ static int trace__process_sample(struct perf_tool *tool,
 		++trace->nr_events;
 		handler(trace, evsel, event, sample);
 	}
-
+out:
+	thread__put(thread);
 	return err;
 }
 
@@ -1988,7 +2024,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
 	for (i = 0; i < (unsigned int)argc; i++)
 		rec_argv[j++] = argv[i];
 
-	return cmd_record(j, rec_argv, NULL);
+	return cmd_record(j, rec_argv);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -2415,8 +2451,9 @@ static int trace__replay(struct trace *trace)
 	trace->tool.exit	  = perf_event__process_exit;
 	trace->tool.fork	  = perf_event__process_fork;
 	trace->tool.attr	  = perf_event__process_attr;
-	trace->tool.tracing_data = perf_event__process_tracing_data;
+	trace->tool.tracing_data  = perf_event__process_tracing_data;
 	trace->tool.build_id	  = perf_event__process_build_id;
+	trace->tool.namespaces	  = perf_event__process_namespaces;
 
 	trace->tool.ordered_events = true;
 	trace->tool.ordering_requires_timestamps = true;
@@ -2785,7 +2822,7 @@ out:
 	return err;
 }
 
-int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
 		"perf trace [<options>] [<command>]",
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 9b10cda6b6dc..d25149456a2f 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -1,9 +1,9 @@
-#include "util/util.h"
 #include "builtin.h"
 #include "perf.h"
+#include <linux/compiler.h>
+#include <stdio.h>
 
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-		const char *prefix __maybe_unused)
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused)
 {
 	printf("perf version %s\n", perf_version_string);
 	return 0;
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 036e1e35b1a8..d4d19fe3d050 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -2,46 +2,42 @@
 #define BUILTIN_H
 
 #include "util/util.h"
-#include "util/strbuf.h"
 
 extern const char perf_usage_string[];
 extern const char perf_more_info_string[];
 
 void list_common_cmds_help(void);
 const char *help_unknown_cmd(const char *cmd);
-void prune_packed_objects(int);
-int read_line_with_nul(char *buf, int size, FILE *file);
-int check_pager_config(const char *cmd);
 
-int cmd_annotate(int argc, const char **argv, const char *prefix);
-int cmd_bench(int argc, const char **argv, const char *prefix);
-int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
-int cmd_buildid_list(int argc, const char **argv, const char *prefix);
-int cmd_config(int argc, const char **argv, const char *prefix);
-int cmd_c2c(int argc, const char **argv, const char *prefix);
-int cmd_diff(int argc, const char **argv, const char *prefix);
-int cmd_evlist(int argc, const char **argv, const char *prefix);
-int cmd_help(int argc, const char **argv, const char *prefix);
-int cmd_sched(int argc, const char **argv, const char *prefix);
-int cmd_kallsyms(int argc, const char **argv, const char *prefix);
-int cmd_list(int argc, const char **argv, const char *prefix);
-int cmd_record(int argc, const char **argv, const char *prefix);
-int cmd_report(int argc, const char **argv, const char *prefix);
-int cmd_stat(int argc, const char **argv, const char *prefix);
-int cmd_timechart(int argc, const char **argv, const char *prefix);
-int cmd_top(int argc, const char **argv, const char *prefix);
-int cmd_script(int argc, const char **argv, const char *prefix);
-int cmd_version(int argc, const char **argv, const char *prefix);
-int cmd_probe(int argc, const char **argv, const char *prefix);
-int cmd_kmem(int argc, const char **argv, const char *prefix);
-int cmd_lock(int argc, const char **argv, const char *prefix);
-int cmd_kvm(int argc, const char **argv, const char *prefix);
-int cmd_test(int argc, const char **argv, const char *prefix);
-int cmd_trace(int argc, const char **argv, const char *prefix);
-int cmd_inject(int argc, const char **argv, const char *prefix);
-int cmd_mem(int argc, const char **argv, const char *prefix);
-int cmd_data(int argc, const char **argv, const char *prefix);
-int cmd_ftrace(int argc, const char **argv, const char *prefix);
+int cmd_annotate(int argc, const char **argv);
+int cmd_bench(int argc, const char **argv);
+int cmd_buildid_cache(int argc, const char **argv);
+int cmd_buildid_list(int argc, const char **argv);
+int cmd_config(int argc, const char **argv);
+int cmd_c2c(int argc, const char **argv);
+int cmd_diff(int argc, const char **argv);
+int cmd_evlist(int argc, const char **argv);
+int cmd_help(int argc, const char **argv);
+int cmd_sched(int argc, const char **argv);
+int cmd_kallsyms(int argc, const char **argv);
+int cmd_list(int argc, const char **argv);
+int cmd_record(int argc, const char **argv);
+int cmd_report(int argc, const char **argv);
+int cmd_stat(int argc, const char **argv);
+int cmd_timechart(int argc, const char **argv);
+int cmd_top(int argc, const char **argv);
+int cmd_script(int argc, const char **argv);
+int cmd_version(int argc, const char **argv);
+int cmd_probe(int argc, const char **argv);
+int cmd_kmem(int argc, const char **argv);
+int cmd_lock(int argc, const char **argv);
+int cmd_kvm(int argc, const char **argv);
+int cmd_test(int argc, const char **argv);
+int cmd_trace(int argc, const char **argv);
+int cmd_inject(int argc, const char **argv);
+int cmd_mem(int argc, const char **argv);
+int cmd_data(int argc, const char **argv);
+int cmd_ftrace(int argc, const char **argv);
 
 int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c747bfd7f14d..83fe2202382e 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -1,7 +1,9 @@
 #!/bin/sh
 
 HEADERS='
+include/uapi/linux/fcntl.h
 include/uapi/linux/perf_event.h
+include/uapi/linux/stat.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ac3efd396a72..2d0caf20ff3a 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -9,6 +9,7 @@ perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-data			mainporcelain common
 perf-diff			mainporcelain common
+perf-c2c			mainporcelain common
 perf-config			mainporcelain common
 perf-evlist			mainporcelain common
 perf-ftrace			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 6d5479e03e0d..4cc6960f6226 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -19,9 +19,15 @@
 #include "util/debug.h"
 #include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
+#include <errno.h>
 #include <pthread.h>
+#include <signal.h>
 #include <stdlib.h>
 #include <time.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <linux/kernel.h>
 
 const char perf_usage_string[] =
 	"perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
@@ -34,7 +40,7 @@ const char *input_name;
 
 struct cmd_struct {
 	const char *cmd;
-	int (*fn)(int, const char **, const char *);
+	int (*fn)(int, const char **);
 	int option;
 };
 
@@ -88,7 +94,7 @@ static int pager_command_config(const char *var, const char *value, void *data)
 }
 
 /* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
-int check_pager_config(const char *cmd)
+static int check_pager_config(const char *cmd)
 {
 	int err;
 	struct pager_config c;
@@ -267,71 +273,6 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 	return handled;
 }
 
-static int handle_alias(int *argcp, const char ***argv)
-{
-	int envchanged = 0, ret = 0, saved_errno = errno;
-	int count, option_count;
-	const char **new_argv;
-	const char *alias_command;
-	char *alias_string;
-
-	alias_command = (*argv)[0];
-	alias_string = alias_lookup(alias_command);
-	if (alias_string) {
-		if (alias_string[0] == '!') {
-			if (*argcp > 1) {
-				struct strbuf buf;
-
-				if (strbuf_init(&buf, PATH_MAX) < 0 ||
-				    strbuf_addstr(&buf, alias_string) < 0 ||
-				    sq_quote_argv(&buf, (*argv) + 1,
-						  PATH_MAX) < 0)
-					die("Failed to allocate memory.");
-				free(alias_string);
-				alias_string = buf.buf;
-			}
-			ret = system(alias_string + 1);
-			if (ret >= 0 && WIFEXITED(ret) &&
-			    WEXITSTATUS(ret) != 127)
-				exit(WEXITSTATUS(ret));
-			die("Failed to run '%s' when expanding alias '%s'",
-			    alias_string + 1, alias_command);
-		}
-		count = split_cmdline(alias_string, &new_argv);
-		if (count < 0)
-			die("Bad alias.%s string", alias_command);
-		option_count = handle_options(&new_argv, &count, &envchanged);
-		if (envchanged)
-			die("alias '%s' changes environment variables\n"
-				 "You can use '!perf' in the alias to do this.",
-				 alias_command);
-		memmove(new_argv - option_count, new_argv,
-				count * sizeof(char *));
-		new_argv -= option_count;
-
-		if (count < 1)
-			die("empty alias for %s", alias_command);
-
-		if (!strcmp(alias_command, new_argv[0]))
-			die("recursive alias: %s", alias_command);
-
-		new_argv = realloc(new_argv, sizeof(char *) *
-				    (count + *argcp + 1));
-		/* insert after command name */
-		memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp);
-		new_argv[count + *argcp] = NULL;
-
-		*argv = new_argv;
-		*argcp += count - 1;
-
-		ret = 1;
-	}
-
-	errno = saved_errno;
-
-	return ret;
-}
-
 #define RUN_SETUP	(1<<0)
 #define USE_PAGER	(1<<1)
 
@@ -339,13 +280,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 {
 	int status;
 	struct stat st;
-	const char *prefix;
 	char sbuf[STRERR_BUFSIZE];
 
-	prefix = NULL;
-	if (p->option & RUN_SETUP)
-		prefix = NULL; /* setup_perf_directory(); */
-
 	if (use_browser == -1)
 		use_browser = check_browser_config(p->cmd);
 
@@ -356,7 +292,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	commit_pager_choice();
 
 	perf_env__set_cmdline(&perf_env, argc, argv);
-	status = p->fn(argc, argv, prefix);
+	status = p->fn(argc, argv);
 	perf_config__exit();
 	exit_browser(status);
 	perf_env__exit(&perf_env);
@@ -397,16 +333,6 @@ static void handle_internal_command(int argc, const char **argv)
 {
 	const char *cmd = argv[0];
 	unsigned int i;
-	static const char ext[] = STRIP_EXTENSION;
-
-	if (sizeof(ext) > 1) {
-		i = strlen(argv[0]) - strlen(ext);
-		if (i > 0 && !strcmp(argv[0] + i, ext)) {
-			char *argv0 = strdup(argv[0]);
-			argv[0] = cmd = argv0;
-			argv0[i] = '\0';
-		}
-	}
 
 	/* Turn "perf cmd --help" into "perf help cmd" */
 	if (argc > 1 && !strcmp(argv[1], "--help")) {
@@ -448,7 +374,8 @@ static void execv_dashed_external(const char **argv)
 	if (status != -ERR_RUN_COMMAND_EXEC) {
 		if (IS_RUN_COMMAND_ERR(status)) {
 do_die:
-			die("unable to run '%s'", argv[0]);
+			pr_err("FATAL: unable to run '%s'", argv[0]);
+			status = -128;
 		}
 		exit(-status);
 	}
@@ -460,25 +387,12 @@ do_die:
 
 static int run_argv(int *argcp, const char ***argv)
 {
-	int done_alias = 0;
+	/* See if it's an internal command */
+	handle_internal_command(*argcp, *argv);
 
-	while (1) {
-		/* See if it's an internal command */
-		handle_internal_command(*argcp, *argv);
-
-		/* .. then try the external ones */
-		execv_dashed_external(*argv);
-
-		/* It could be an alias -- this works around the insanity
-		 * of overriding "perf log" with "perf show" by having
-		 * alias.log = show
-		 */
-		if (done_alias || !handle_alias(argcp, argv))
-			break;
-		done_alias = 1;
-	}
-
-	return done_alias;
+	/* .. then try the external ones */
+	execv_dashed_external(*argv);
+	return 0;
 }
 
 static void pthread__block_sigwinch(void)
@@ -566,7 +480,7 @@ int main(int argc, const char **argv)
 #ifdef HAVE_LIBAUDIT_SUPPORT
 		setup_path();
 		argv[0] = "trace";
-		return cmd_trace(argc, argv, NULL);
+		return cmd_trace(argc, argv);
 #else
 		fprintf(stderr,
 			"trace command not available: missing audit-libs devel package at build time.\n");
@@ -611,17 +525,12 @@ int main(int argc, const char **argv)
 
 	while (1) {
 		static int done_help;
-		int was_alias = run_argv(&argc, &argv);
+
+		run_argv(&argc, &argv);
 
 		if (errno != ENOENT)
 			break;
 
-		if (was_alias) {
-			fprintf(stderr, "Expansion of alias '%s' failed; "
-				"'%s' is not a perf-command\n",
-				cmd, argv[0]);
-			goto out;
-		}
 		if (!done_help) {
 			cmd = argv[0] = help_unknown_cmd(cmd);
 			done_help = 1;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 1c27d947c2fe..806c216a1078 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -50,6 +50,7 @@ struct record_opts {
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
+	bool	     record_namespaces;
 	bool	     record_switch_events;
 	bool	     all_kernel;
 	bool	     all_user;
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json
new file mode 100644
index 000000000000..28e1e159a3cb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json
@@ -0,0 +1,278 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x44",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x11",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x18",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x1f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x2f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x8f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x86",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x16",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x26",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x02",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT",
+    "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
+    "PublicDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
+    "Counter": "0,",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x02",
+    "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
+    "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
+    "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "NCU",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "FIXED",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
index 076459c51d4e..58ed6d33d1f4 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1,2,3",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1,2,3",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -212,7 +212,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -221,7 +221,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "BriefDescription": "read requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_LOCAL",
@@ -230,7 +230,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "BriefDescription": "read requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_REMOTE",
@@ -239,7 +239,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -248,7 +248,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "BriefDescription": "write requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
@@ -257,7 +257,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "BriefDescription": "write requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
@@ -266,7 +266,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
@@ -275,7 +275,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -285,7 +285,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -295,7 +295,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -305,7 +305,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
index d17dc235f734..f4b0745cdbbf 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
@@ -3,7 +3,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -13,48 +13,51 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_M_CLOCKTICKS",
+        "EventName": "UNC_M_DCLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
-        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_DCLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
-        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_DCLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
-        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_DCLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Pre-charges due to page misses",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -63,7 +66,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "BriefDescription": "Pre-charge for reads",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.RD",
@@ -72,7 +75,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "BriefDescription": "Pre-charge for writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.WR",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
index b44d43088bbb..dd1b95655d1d 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
@@ -1,83 +1,91 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xA",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x74",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
index 076459c51d4e..58ed6d33d1f4 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1,2,3",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1,2,3",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -212,7 +212,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -221,7 +221,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "BriefDescription": "read requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_LOCAL",
@@ -230,7 +230,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "BriefDescription": "read requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_REMOTE",
@@ -239,7 +239,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -248,7 +248,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "BriefDescription": "write requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
@@ -257,7 +257,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "BriefDescription": "write requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
@@ -266,7 +266,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
@@ -275,7 +275,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -285,7 +285,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -295,7 +295,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -305,7 +305,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
index 39387f7909b2..824961318c1e 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -10,7 +10,7 @@
     {
         "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "EventName": "QPI_DATA_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x2",
@@ -19,7 +19,7 @@
     {
         "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "EventName": "QPI_CTL_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
index d17dc235f734..66eed399724c 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
@@ -3,7 +3,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -13,48 +13,51 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Pre-charges due to page misses",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -63,7 +66,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "BriefDescription": "Pre-charge for reads",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.RD",
@@ -72,7 +75,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "BriefDescription": "Pre-charge for writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.WR",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
index b44d43088bbb..dd1b95655d1d 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
@@ -1,83 +1,91 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xA",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x74",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore.json b/tools/perf/pmu-events/arch/x86/haswell/uncore.json
new file mode 100644
index 000000000000..3ef5c21fef56
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswell/uncore.json
@@ -0,0 +1,374 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL",
+    "BriefDescription": "An external snoop misses in some processor core.",
+    "PublicDescription": "An external snoop misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x24",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL",
+    "BriefDescription": "An external snoop hits a non-modified line in some processor core.",
+    "PublicDescription": "An external snoop hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x44",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x84",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x28",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL",
+    "BriefDescription": "An external snoop hits a modified line in some processor core.",
+    "PublicDescription": "An external snoop hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x11",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x18",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x28",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x1f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x2f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x4f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x8f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x86",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x46",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x16",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x26",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x83",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All",
+    "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)",
+    "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "NCU",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "FIXED",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
index 076459c51d4e..58ed6d33d1f4 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1,2,3",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1,2,3",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -212,7 +212,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -221,7 +221,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "BriefDescription": "read requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_LOCAL",
@@ -230,7 +230,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "BriefDescription": "read requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_REMOTE",
@@ -239,7 +239,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -248,7 +248,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "BriefDescription": "write requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
@@ -257,7 +257,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "BriefDescription": "write requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
@@ -266,7 +266,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
@@ -275,7 +275,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -285,7 +285,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -295,7 +295,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -305,7 +305,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
index 39387f7909b2..824961318c1e 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -10,7 +10,7 @@
     {
         "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "EventName": "QPI_DATA_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x2",
@@ -19,7 +19,7 @@
     {
         "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "EventName": "QPI_CTL_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
index d17dc235f734..66eed399724c 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
@@ -3,7 +3,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -13,48 +13,51 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Pre-charges due to page misses",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -63,7 +66,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "BriefDescription": "Pre-charge for reads",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.RD",
@@ -72,7 +75,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "BriefDescription": "Pre-charge for writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.WR",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
index b44d43088bbb..dd1b95655d1d 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
@@ -1,83 +1,91 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xA",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x74",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json
new file mode 100644
index 000000000000..42c70eed05a2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json
@@ -0,0 +1,314 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS",
+    "BriefDescription": "A snoop misses in some processor core.",
+    "PublicDescription": "A snoop misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL",
+    "BriefDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT",
+    "BriefDescription": "A snoop hits a non-modified line in some processor core.",
+    "PublicDescription": "A snoop hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM",
+    "BriefDescription": "A snoop hits a modified line in some processor core.",
+    "PublicDescription": "A snoop hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M",
+    "BriefDescription": "A snoop invalidates a modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.M",
+    "BriefDescription": "LLC lookup request that access cache and found line in M-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.E",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.S",
+    "BriefDescription": "LLC lookup request that access cache and found line in S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.I",
+    "BriefDescription": "LLC lookup request that access cache and found line in I-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable read requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable read requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable write requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable write requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER",
+    "BriefDescription": "Filter on external snoop requests.",
+    "PublicDescription": "Filter on external snoop requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER",
+    "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x80",
+    "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS",
+    "BriefDescription": "Counts the number of LLC evictions allocated.",
+    "PublicDescription": "Counts the number of LLC evictions allocated.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x83",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of requests allocated in Coherency Tracker.",
+    "PublicDescription": "Number of requests allocated in Coherency Tracker.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
+    "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "10",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "Fixed",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x06",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ES",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
index 2efdc6772e0b..267410594833 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -237,7 +237,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory",
         "EventCode": "0x36",
         "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
         "PerPkg": "1",
@@ -254,7 +254,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory",
         "EventCode": "0x36",
         "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
         "PerPkg": "1",
@@ -262,7 +262,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "Read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -271,7 +271,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "Write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -280,7 +280,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -290,7 +290,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -300,7 +300,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -310,7 +310,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
index d7e2fda1d695..b798a860bc81 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -8,25 +8,27 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x10",
         "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "rxl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "txl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "BriefDescription": "Number of data flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
         "PerPkg": "1",
@@ -35,7 +37,7 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "BriefDescription": "Number of non data (control) flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
index ac4ad4d6357b..df4b43294fa0 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+        "BriefDescription": "Memory page activates for reads and writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_M_ACT_COUNT.RD",
@@ -13,7 +13,7 @@
         "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -23,48 +23,51 @@
         "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Memory page conflicts",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
index dc2586db0dfc..d40498f2cb1e 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -1,44 +1,48 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_BAND0_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_BAND1_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_BAND2_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_BAND3_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -49,6 +53,7 @@
         "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -59,6 +64,7 @@
         "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -69,6 +75,7 @@
         "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -79,90 +86,100 @@
         "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xa",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency.  This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature.  This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x7",
         "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_current_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when the system is changing frequency.  This can not be filtered by thread ID.  One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Cycles spent changing Frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -173,6 +190,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
         "Filter": "filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -183,6 +201,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
         "Filter": "filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -193,6 +212,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
         "Filter": "filter_band2=3000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -203,6 +223,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
         "Filter": "filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -213,6 +234,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -223,6 +245,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -233,6 +256,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band2=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -243,6 +267,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
index 2f23cf0129e7..3fa61d962607 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -171,11 +171,12 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+        "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth",
         "EventCode": "0x36",
         "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
         "Filter": "filter_opc=0x182",
         "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+        "MetricName": "tor_occupancy.miss_all %",
         "PerPkg": "1",
         "UMask": "0xa",
         "Unit": "CBO"
@@ -189,7 +190,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -198,7 +199,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
index 63351876eb57..1b53c0e609e3 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -8,25 +8,27 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x10",
         "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "rxl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "txl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "BriefDescription": "Number of data flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
         "PerPkg": "1",
@@ -35,7 +37,7 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "BriefDescription": "Number of non data (control) flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
index e2cf6daa7b37..8551cebeba23 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+        "BriefDescription": "Memory page activates",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_M_ACT_COUNT",
@@ -11,7 +11,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "UMask": "0x3",
         "Unit": "iMC"
@@ -20,47 +20,50 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "UMask": "0xc",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Memory page conflicts",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -69,7 +72,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+        "BriefDescription": "Occupancy counter for memory read queue",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_M_RPQ_OCCUPANCY",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
index bbe36d547386..16034bfd06dd 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -1,44 +1,48 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_BAND0_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_BAND1_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_BAND2_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_BAND3_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -49,6 +53,7 @@
         "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -59,6 +64,7 @@
         "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -69,6 +75,7 @@
         "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -79,89 +86,99 @@
         "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xa",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x7",
         "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_current_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Cycles spent changing Frequency",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -172,6 +189,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
         "Filter": "filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -182,6 +200,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
         "Filter": "filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -192,6 +211,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
         "Filter": "filter_band2=3000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -202,6 +222,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
         "Filter": "filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -212,6 +233,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -222,6 +244,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -232,6 +255,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band2=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -242,6 +266,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 12181bb1da2a..d1a12e584c1b 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -17,6 +17,7 @@ GenuineIntel-6-3A,v18,ivybridge,core
 GenuineIntel-6-3E,v19,ivytown,core
 GenuineIntel-6-2D,v20,jaketown,core
 GenuineIntel-6-57,v9,knightslanding,core
+GenuineIntel-6-85,v9,knightslanding,core
 GenuineIntel-6-1E,v2,nehalemep,core
 GenuineIntel-6-1F,v2,nehalemep,core
 GenuineIntel-6-1A,v2,nehalemep,core
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json
new file mode 100644
index 000000000000..42c70eed05a2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json
@@ -0,0 +1,314 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS",
+    "BriefDescription": "A snoop misses in some processor core.",
+    "PublicDescription": "A snoop misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL",
+    "BriefDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT",
+    "BriefDescription": "A snoop hits a non-modified line in some processor core.",
+    "PublicDescription": "A snoop hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM",
+    "BriefDescription": "A snoop hits a modified line in some processor core.",
+    "PublicDescription": "A snoop hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M",
+    "BriefDescription": "A snoop invalidates a modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.M",
+    "BriefDescription": "LLC lookup request that access cache and found line in M-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.E",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.S",
+    "BriefDescription": "LLC lookup request that access cache and found line in S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.I",
+    "BriefDescription": "LLC lookup request that access cache and found line in I-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable read requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable read requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable write requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable write requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER",
+    "BriefDescription": "Filter on external snoop requests.",
+    "PublicDescription": "Filter on external snoop requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER",
+    "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x80",
+    "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS",
+    "BriefDescription": "Counts the number of LLC evictions allocated.",
+    "PublicDescription": "Counts the number of LLC evictions allocated.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x83",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of requests allocated in Coherency Tracker.",
+    "PublicDescription": "Number of requests allocated in Coherency Tracker.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
+    "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "10",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "Fixed",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x06",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ES",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore.json b/tools/perf/pmu-events/arch/x86/skylake/uncore.json
new file mode 100644
index 000000000000..dbc193252fb3
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylake/uncore.json
@@ -0,0 +1,254 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x44",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x18",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x1f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x2f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x8f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x86",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x16",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x26",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x02",
+    "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
+    "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
+    "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "NCU",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "FIXED",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index eed09346a72a..baa073f38334 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -195,6 +195,7 @@ static struct map {
 	{ "CBO", "uncore_cbox" },
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
+	{ "iMPH-U", "uncore_arb" },
 	{}
 };
 
@@ -291,7 +292,9 @@ static void print_events_table_prefix(FILE *fp, const char *tblname)
 
 static int print_events_table_entry(void *data, char *name, char *event,
 				    char *desc, char *long_desc,
-				    char *pmu, char *unit, char *perpkg)
+				    char *pmu, char *unit, char *perpkg,
+				    char *metric_expr,
+				    char *metric_name)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -315,6 +318,10 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.unit = \"%s\",\n", unit);
 	if (perpkg)
 		fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
+	if (metric_expr)
+		fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
+	if (metric_name)
+		fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -362,7 +369,9 @@ static char *real_event(const char *name, char *event)
 int json_events(const char *fn,
 	  int (*func)(void *data, char *name, char *event, char *desc,
 		      char *long_desc,
-		      char *pmu, char *unit, char *perpkg),
+		      char *pmu, char *unit, char *perpkg,
+		      char *metric_expr,
+		      char *metric_name),
 	  void *data)
 {
 	int err = -EIO;
@@ -388,6 +397,8 @@ int json_events(const char *fn,
 		char *filter = NULL;
 		char *perpkg = NULL;
 		char *unit = NULL;
+		char *metric_expr = NULL;
+		char *metric_name = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
 		jsmntok_t *msrval = NULL;
@@ -398,6 +409,7 @@ int json_events(const char *fn,
 		for (j = 0; j < obj->size; j += 2) {
 			jsmntok_t *field, *val;
 			int nz;
+			char *s;
 
 			field = tok + j;
 			EXPECT(field->type == JSMN_STRING, tok + j,
@@ -444,7 +456,6 @@ int json_events(const char *fn,
 					NULL);
 			} else if (json_streq(map, field, "Unit")) {
 				const char *ppmu;
-				char *s;
 
 				ppmu = field_to_perf(unit_to_pmu, map, val);
 				if (ppmu) {
@@ -458,12 +469,19 @@ int json_events(const char *fn,
 				}
 				addfield(map, &desc, ". ", "Unit: ", NULL);
 				addfield(map, &desc, "", pmu, NULL);
+				addfield(map, &desc, "", " ", NULL);
 			} else if (json_streq(map, field, "Filter")) {
 				addfield(map, &filter, "", "", val);
 			} else if (json_streq(map, field, "ScaleUnit")) {
 				addfield(map, &unit, "", "", val);
 			} else if (json_streq(map, field, "PerPkg")) {
 				addfield(map, &perpkg, "", "", val);
+			} else if (json_streq(map, field, "MetricName")) {
+				addfield(map, &metric_name, "", "", val);
+			} else if (json_streq(map, field, "MetricExpr")) {
+				addfield(map, &metric_expr, "", "", val);
+				for (s = metric_expr; *s; s++)
+					*s = tolower(*s);
 			}
 			/* ignore unknown fields */
 		}
@@ -488,7 +506,7 @@ int json_events(const char *fn,
 		fixname(name);
 
 		err = func(data, name, real_event(name, event), desc, long_desc,
-				pmu, unit, perpkg);
+				pmu, unit, perpkg, metric_expr, metric_name);
 		free(event);
 		free(desc);
 		free(name);
@@ -498,6 +516,8 @@ int json_events(const char *fn,
 		free(filter);
 		free(perpkg);
 		free(unit);
+		free(metric_expr);
+		free(metric_name);
 		if (err)
 			break;
 		tok += j;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index 71e13de31092..611fac01913d 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -5,7 +5,8 @@ int json_events(const char *fn,
 		int (*func)(void *data, char *name, char *event, char *desc,
 				char *long_desc,
 				char *pmu,
-				char *unit, char *perpkg),
+				char *unit, char *perpkg, char *metric_expr,
+				char *metric_name),
 		void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index c669a3cdb9f0..569eab3688dd 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -13,6 +13,8 @@ struct pmu_event {
 	const char *pmu;
 	const char *unit;
 	const char *perpkg;
+	const char *metric_expr;
+	const char *metric_name;
 };
 
 /*
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 1cb3d9b540e9..af58ebc243ef 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -38,6 +38,7 @@ perf-y += cpumap.o
 perf-y += stat.o
 perf-y += event_update.o
 perf-y += event-times.o
+perf-y += expr.o
 perf-y += backward-ring-buffer.o
 perf-y += sdt.o
 perf-y += is_printable_array.o
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 88dc51f4c27b..0dd77494bb58 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -18,10 +18,16 @@
  * permissions. All the event text files are stored there.
  */
 
+#include <errno.h>
+#include <inttypes.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "../perf.h"
 #include "util.h"
 #include <subcmd/exec-cmd.h>
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 42e892b1e979..50f6d7afee58 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -8,6 +8,7 @@
 #include <sys/prctl.h>
 #include "tests.h"
 #include "debug.h"
+#include <errno.h>
 
 #define NR_ITERS 111
 
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 1a04fe77487d..5876da126b58 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,10 +1,14 @@
+#include <errno.h>
 #include <stdio.h>
 #include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/stat.h>
 #include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <api/fs/fs.h>
 #include <bpf/bpf.h>
 #include "tests.h"
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 83c4669cbc5b..9e08d297f1a9 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -3,8 +3,10 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <errno.h>
 #include <unistd.h>
 #include <string.h>
+#include <sys/wait.h>
 #include "builtin.h"
 #include "hist.h"
 #include "intlist.h"
@@ -13,6 +15,7 @@
 #include "color.h"
 #include <subcmd/parse-options.h>
 #include "symbol.h"
+#include <linux/kernel.h>
 
 static bool dont_fork;
 
@@ -44,6 +47,10 @@ static struct test generic_tests[] = {
 		.func = test__parse_events,
 	},
 	{
+		.desc = "Simple expression parser",
+		.func = test__expr,
+	},
+	{
 		.desc = "PERF_RECORD_* events & perf_sample fields",
 		.func = test__PERF_RECORD,
 	},
@@ -460,7 +467,7 @@ static int perf_test__list(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_test(int argc, const char **argv)
 {
 	const char *test_usage[] = {
 	"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c
index f853e242a86c..c5bb2203f5a9 100644
--- a/tools/perf/tests/clang.c
+++ b/tools/perf/tests/clang.c
@@ -2,6 +2,7 @@
 #include "debug.h"
 #include "util.h"
 #include "c++/clang-c.h"
+#include <linux/kernel.h>
 
 static struct {
 	int (*func)(void);
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index d1f693041324..1f14e7612cbb 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -1,9 +1,12 @@
+#include <errno.h>
+#include <linux/kernel.h>
 #include <linux/types.h>
+#include <inttypes.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <stdio.h>
-#include <ctype.h>
 #include <string.h>
+#include <sys/param.h>
 
 #include "parse-events.h"
 #include "evlist.h"
@@ -16,6 +19,8 @@
 
 #include "tests.h"
 
+#include "sane_ctype.h"
+
 #define BUFSZ	1024
 #define READLEN	128
 
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f168a85992d0..4478773cdb97 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -66,7 +66,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 	TEST_ASSERT_VAL("wrong nr",  map->nr == 2);
 	TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
 	TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
-	TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1);
+	TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1);
 	cpu_map__put(map);
 	return 0;
 }
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 13725e09ba22..8f08df5861cb 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -1,4 +1,6 @@
+#include <dirent.h>
 #include <stdlib.h>
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 1046491de4b2..dfe5c89e2049 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -1,5 +1,6 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <inttypes.h>
 #include <unistd.h>
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 19ef77bd6eb4..634f20c631d8 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -1,5 +1,8 @@
 #include <linux/compiler.h>
+#include <errno.h>
+#include <inttypes.h>
 #include <string.h>
+#include <sys/wait.h>
 #include "tests.h"
 #include "evlist.h"
 #include "evsel.h"
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 60926a1f6fd7..d2bea6f780f8 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -3,6 +3,8 @@
 #include "parse-events.h"
 #include "tests.h"
 #include "debug.h"
+#include <errno.h>
+#include <linux/kernel.h>
 
 static int perf_evsel__roundtrip_cache_name_test(void)
 {
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
new file mode 100644
index 000000000000..6c6a3749aaf6
--- /dev/null
+++ b/tools/perf/tests/expr.c
@@ -0,0 +1,56 @@
+#include "util/debug.h"
+#include "util/expr.h"
+#include "tests.h"
+#include <stdlib.h>
+
+static int test(struct parse_ctx *ctx, const char *e, double val2)
+{
+	double val;
+
+	if (expr__parse(&val, ctx, &e))
+		TEST_ASSERT_VAL("parse test failed", 0);
+	TEST_ASSERT_VAL("unexpected value", val == val2);
+	return 0;
+}
+
+int test__expr(int subtest __maybe_unused)
+{
+	const char *p;
+	const char **other;
+	double val;
+	int ret;
+	struct parse_ctx ctx;
+	int num_other;
+
+	expr__ctx_init(&ctx);
+	expr__add_id(&ctx, "FOO", 1);
+	expr__add_id(&ctx, "BAR", 2);
+
+	ret = test(&ctx, "1+1", 2);
+	ret |= test(&ctx, "FOO+BAR", 3);
+	ret |= test(&ctx, "(BAR/2)%2", 1);
+	ret |= test(&ctx, "1 - -4",  5);
+	ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4",  5);
+
+	if (ret)
+		return ret;
+
+	p = "FOO/0";
+	ret = expr__parse(&val, &ctx, &p);
+	TEST_ASSERT_VAL("division by zero", ret == 1);
+
+	p = "BAR/";
+	ret = expr__parse(&val, &ctx, &p);
+	TEST_ASSERT_VAL("missing operand", ret == 1);
+
+	TEST_ASSERT_VAL("find other",
+			expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
+	TEST_ASSERT_VAL("find other", num_other == 3);
+	TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR"));
+	TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
+	TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO"));
+	TEST_ASSERT_VAL("find other", other[3] == NULL);
+	free((void *)other);
+
+	return 0;
+}
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index 6b21746d6eec..00b8dc50f3db 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -1,3 +1,4 @@
+#include <inttypes.h>
 #include "perf.h"
 #include "util/debug.h"
 #include "util/symbol.h"
@@ -7,6 +8,7 @@
 #include "util/machine.h"
 #include "util/thread.h"
 #include "tests/hists_common.h"
+#include <linux/kernel.h>
 
 static struct {
 	u32 pid;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 9fd54b79a788..70918b986568 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -9,6 +9,7 @@
 #include "util/parse-events.h"
 #include "tests/tests.h"
 #include "tests/hists_common.h"
+#include <linux/kernel.h>
 
 struct sample {
 	u32 pid;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 62efb14f3a5a..f171b2da4899 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -9,6 +9,7 @@
 #include "util/parse-events.h"
 #include "tests/tests.h"
 #include "tests/hists_common.h"
+#include <linux/kernel.h>
 
 struct sample {
 	u32 pid;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index eddc7407ff8a..a26cbb79e988 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -9,6 +9,8 @@
 #include "thread.h"
 #include "parse-events.h"
 #include "hists_common.h"
+#include <errno.h>
+#include <linux/kernel.h>
 
 struct sample {
 	u32 pid;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 63c5efaba1b5..cdf0dde5fe97 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -9,6 +9,7 @@
 #include "util/parse-events.h"
 #include "tests/tests.h"
 #include "tests/hists_common.h"
+#include <linux/kernel.h>
 
 struct sample {
 	u32 cpu;
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
index 42e13393e502..a5192f6a20d7 100644
--- a/tools/perf/tests/is_printable_array.c
+++ b/tools/perf/tests/is_printable_array.c
@@ -1,7 +1,8 @@
 #include <linux/compiler.h>
+#include <linux/kernel.h>
 #include "tests.h"
 #include "debug.h"
-#include "util.h"
+#include "print_binary.h"
 
 int test__is_printable_array(int subtest __maybe_unused)
 {
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 634bce9caebd..15c770856aac 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 /* For the CLR_() macros */
 #include <pthread.h>
 
@@ -7,6 +9,7 @@
 #include "cpumap.h"
 #include "tests.h"
 #include <linux/err.h>
+#include <linux/kernel.h>
 
 /*
  * This test will generate random numbers of calls to some getpid syscalls,
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 0c5ce44f723f..6ea4d8a5d26b 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -1,3 +1,4 @@
+#include <inttypes.h>
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/types.h>
@@ -11,6 +12,7 @@
 #include "thread_map.h"
 #include "symbol.h"
 #include "thread.h"
+#include "util.h"
 
 #define THREADS 4
 
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index c8d9592eb142..1a74dd9fd067 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -1,8 +1,14 @@
+#include <errno.h>
+#include <inttypes.h>
 /* For the CPU_* macros */
 #include <pthread.h>
 
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include <api/fs/fs.h>
 #include <linux/err.h>
+#include <api/fs/tracing_path.h>
 #include "evsel.h"
 #include "tests.h"
 #include "thread_map.h"
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index f52239fed361..9788fac91095 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -5,6 +5,7 @@
 #include "thread_map.h"
 #include "tests.h"
 #include "debug.h"
+#include <errno.h>
 
 #ifndef O_DIRECTORY
 #define O_DIRECTORY    00200000
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index d7414128d7fe..e44506e21ee7 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -1,5 +1,10 @@
+#include <errno.h>
+#include <inttypes.h>
 #include <api/fs/tracing_path.h>
 #include <linux/err.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include "thread_map.h"
 #include "evsel.h"
 #include "debug.h"
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 1dc838014422..7fad885491c5 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1,4 +1,3 @@
-
 #include "parse-events.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -6,8 +5,15 @@
 #include "tests.h"
 #include "debug.h"
 #include "util.h"
+#include <dirent.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <linux/kernel.h>
 #include <linux/hw_breakpoint.h>
 #include <api/fs/fs.h>
+#include <api/fs/tracing_path.h>
 
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
 			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 65dcf48a92fb..c6207db09f12 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <stddef.h>
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 87893f3ba5f1..d37cd9588cc0 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 /* For the CLR_() macros */
 #include <pthread.h>
 
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 1e2ba2602930..a6d7aef30030 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -2,6 +2,8 @@
 #include "pmu.h"
 #include "util.h"
 #include "tests.h"
+#include <errno.h>
+#include <linux/kernel.h>
 
 /* Simulated format definitions. */
 static struct test_format {
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 5f23710b9fee..bac5c3885b3b 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -1,4 +1,6 @@
 #include <stdbool.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
 #include <linux/types.h>
 
 #include "util.h"
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index f59d210e1baf..f73b3c5e125d 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include <stdio.h>
 #include <sys/epoll.h>
 #include <util/util.h>
@@ -43,7 +44,7 @@ static char *get_self_path(void)
 {
 	char *buf = calloc(PATH_MAX, sizeof(char));
 
-	if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) {
+	if (buf && readlink("/proc/self/exe", buf, PATH_MAX - 1) < 0) {
 		pr_debug("Failed to get correct path of perf\n");
 		free(buf);
 		return NULL;
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 4c9fd046d57b..828494db4a19 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 #include <unistd.h>
 #include <stdlib.h>
 #include <signal.h>
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 7ddbe267d0ac..65474fd80da7 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -1,5 +1,6 @@
 #include <sys/time.h>
 #include <sys/prctl.h>
+#include <errno.h>
 #include <time.h>
 #include <stdlib.h>
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 01a5ba2788c6..32873ec91a4e 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -4,6 +4,7 @@
 #include "cpumap.h"
 #include "tests.h"
 
+#include <errno.h>
 #include <signal.h>
 
 static int exited;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 1fa9b9d83aa5..631859629403 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -62,6 +62,7 @@ int test__sample_parsing(int subtest);
 int test__keep_tracking(int subtest);
 int test__parse_no_sample_id_all(int subtest);
 int test__dwarf_unwind(int subtest);
+int test__expr(int subtest);
 int test__hists_filter(int subtest);
 int test__mmap_thread_lookup(int subtest);
 int test__thread_mg_share(int subtest);
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index f2d2e542d0ee..a63d6945807b 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -29,7 +29,7 @@ int test__thread_map(int subtest __maybe_unused)
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), NAME));
 	TEST_ASSERT_VAL("wrong refcnt",
-			atomic_read(&map->refcnt) == 1);
+			refcount_read(&map->refcnt) == 1);
 	thread_map__put(map);
 
 	/* test dummy pid */
@@ -44,7 +44,7 @@ int test__thread_map(int subtest __maybe_unused)
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), "dummy"));
 	TEST_ASSERT_VAL("wrong refcnt",
-			atomic_read(&map->refcnt) == 1);
+			refcount_read(&map->refcnt) == 1);
 	thread_map__put(map);
 	return 0;
 }
@@ -71,7 +71,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 			thread_map__comm(threads, 0) &&
 			!strcmp(thread_map__comm(threads, 0), NAME));
 	TEST_ASSERT_VAL("wrong refcnt",
-			atomic_read(&threads->refcnt) == 1);
+			refcount_read(&threads->refcnt) == 1);
 	thread_map__put(threads);
 	return 0;
 }
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 188b63140fc8..76686dd6f5ec 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -43,7 +43,7 @@ int test__thread_mg_share(int subtest __maybe_unused)
 			leader && t1 && t2 && t3 && other);
 
 	mg = leader->mg;
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4);
 
 	/* test the map groups pointer is shared */
 	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -71,25 +71,25 @@ int test__thread_mg_share(int subtest __maybe_unused)
 	machine__remove_thread(machine, other_leader);
 
 	other_mg = other->mg;
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2);
 
 	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
 
 	/* release thread group */
 	thread__put(leader);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3);
 
 	thread__put(t1);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2);
 
 	thread__put(t2);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1);
 
 	thread__put(t3);
 
 	/* release other group  */
 	thread__put(other_leader);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1);
 
 	thread__put(other);
 
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
index 623c2aa53c4a..44589de084b8 100644
--- a/tools/perf/tests/unit_number__scnprintf.c
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -1,7 +1,8 @@
+#include <inttypes.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include "tests.h"
-#include "util.h"
+#include "units.h"
 #include "debug.h"
 
 int test__unit_number__scnprint(int subtest __maybe_unused)
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 862b043e5924..8456175fc234 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -1,5 +1,6 @@
 #include <linux/compiler.h>
 #include <linux/rbtree.h>
+#include <inttypes.h>
 #include <string.h>
 #include "map.h"
 #include "symbol.h"
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
new file mode 100644
index 000000000000..be95ac6ce845
--- /dev/null
+++ b/tools/perf/trace/beauty/Build
@@ -0,0 +1 @@
+libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
new file mode 100644
index 000000000000..cf50be3f17a4
--- /dev/null
+++ b/tools/perf/trace/beauty/beauty.h
@@ -0,0 +1,24 @@
+#ifndef _PERF_TRACE_BEAUTY_H
+#define _PERF_TRACE_BEAUTY_H
+
+#include <linux/types.h>
+
+struct trace;
+struct thread;
+
+struct syscall_arg {
+	unsigned long val;
+	struct thread *thread;
+	struct trace  *trace;
+	void	      *parm;
+	u8	      idx;
+	u8	      mask;
+};
+
+size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
+
+size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
+
+#endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c
index d3b0b1fab077..fde8f2fc6558 100644
--- a/tools/perf/trace/beauty/signum.c
+++ b/tools/perf/trace/beauty/signum.c
@@ -1,3 +1,4 @@
+#include <signal.h>
 
 static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
 {
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
new file mode 100644
index 000000000000..5643b692af4c
--- /dev/null
+++ b/tools/perf/trace/beauty/statx.c
@@ -0,0 +1,72 @@
+/*
+ * trace/beauty/statx.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <uapi/linux/fcntl.h>
+#include <uapi/linux/stat.h>
+
+size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return scnprintf(bf, size, "SYNC_AS_STAT");
+#define	P_FLAG(n) \
+	if (flags & AT_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~AT_##n; \
+	}
+
+	P_FLAG(SYMLINK_NOFOLLOW);
+	P_FLAG(REMOVEDIR);
+	P_FLAG(SYMLINK_FOLLOW);
+	P_FLAG(NO_AUTOMOUNT);
+	P_FLAG(EMPTY_PATH);
+	P_FLAG(STATX_FORCE_SYNC);
+	P_FLAG(STATX_DONT_SYNC);
+
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+#define	P_FLAG(n) \
+	if (flags & STATX_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~STATX_##n; \
+	}
+
+	P_FLAG(TYPE);
+	P_FLAG(MODE);
+	P_FLAG(NLINK);
+	P_FLAG(UID);
+	P_FLAG(GID);
+	P_FLAG(ATIME);
+	P_FLAG(MTIME);
+	P_FLAG(CTIME);
+	P_FLAG(INO);
+	P_FLAG(SIZE);
+	P_FLAG(BLOCKS);
+	P_FLAG(BTIME);
+
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 3eb3edb307a4..a4d3762cd825 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,4 +1,5 @@
 #include "../util.h"
+#include "../string2.h"
 #include "../config.h"
 #include "../../perf.h"
 #include "libslang.h"
@@ -13,6 +14,7 @@
 #include "helpline.h"
 #include "keysyms.h"
 #include "../color.h"
+#include "sane_ctype.h"
 
 static int ui_browser__percent_color(struct ui_browser *browser,
 				     double percent, bool current)
@@ -579,7 +581,7 @@ static int ui_browser__color_config(const char *var, const char *value,
 			break;
 
 		*bg = '\0';
-		while (isspace(*++bg));
+		bg = ltrim(++bg);
 		ui_browser__colorsets[i].bg = bg;
 		ui_browser__colorsets[i].fg = fg;
 		return 0;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ba36aac340bc..d990ad08a3c6 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -9,7 +9,10 @@
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include "../../util/config.h"
+#include <inttypes.h>
 #include <pthread.h>
+#include <linux/kernel.h>
+#include <sys/ttydefaults.h>
 
 struct disasm_line_samples {
 	double		percent;
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index edbeaaf31ace..e2c9390ff4c5 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -8,6 +8,8 @@
 #include "util/header.h"
 #include "util/session.h"
 
+#include <sys/ttydefaults.h>
+
 static void ui_browser__argv_write(struct ui_browser *browser,
 				   void *entry, int row)
 {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fc4fb669ceee..69f4570bd4f9 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1,7 +1,11 @@
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <linux/rbtree.h>
+#include <sys/ttydefaults.h>
 
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
@@ -10,6 +14,7 @@
 #include "../../util/sort.h"
 #include "../../util/util.h"
 #include "../../util/top.h"
+#include "../../util/thread.h"
 #include "../../arch/common.h"
 
 #include "../browsers/hists.h"
@@ -18,6 +23,11 @@
 #include "../ui.h"
 #include "map.h"
 #include "annotate.h"
+#include "srcline.h"
+#include "string2.h"
+#include "units.h"
+
+#include "sane_ctype.h"
 
 extern void hist_browser__init_hpp(void);
 
@@ -144,9 +154,60 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
 	cl->unfolded = unfold ? cl->has_children : false;
 }
 
+static struct inline_node *inline_node__create(struct map *map, u64 ip)
+{
+	struct dso *dso;
+	struct inline_node *node;
+
+	if (map == NULL)
+		return NULL;
+
+	dso = map->dso;
+	if (dso == NULL)
+		return NULL;
+
+	if (dso->kernel != DSO_TYPE_USER)
+		return NULL;
+
+	node = dso__parse_addr_inlines(dso,
+				       map__rip_2objdump(map, ip));
+
+	return node;
+}
+
+static int inline__count_rows(struct inline_node *node)
+{
+	struct inline_list *ilist;
+	int i = 0;
+
+	if (node == NULL)
+		return 0;
+
+	list_for_each_entry(ilist, &node->val, list) {
+		if ((ilist->filename != NULL) || (ilist->funcname != NULL))
+			i++;
+	}
+
+	return i;
+}
+
+static int callchain_list__inline_rows(struct callchain_list *chain)
+{
+	struct inline_node *node;
+	int rows;
+
+	node = inline_node__create(chain->ms.map, chain->ip);
+	if (node == NULL)
+		return 0;
+
+	rows = inline__count_rows(node);
+	inline_node__delete(node);
+	return rows;
+}
+
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
-	int n = 0;
+	int n = 0, inline_rows;
 	struct rb_node *nd;
 
 	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
@@ -156,6 +217,13 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 
 		list_for_each_entry(chain, &child->val, list) {
 			++n;
+
+			if (symbol_conf.inline_name) {
+				inline_rows =
+					callchain_list__inline_rows(chain);
+				n += inline_rows;
+			}
+
 			/* We need this because we may not have children */
 			folded_sign = callchain_list__folded(chain);
 			if (folded_sign == '+')
@@ -207,7 +275,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 	bool unfolded = false;
-	int n = 0;
+	int n = 0, inline_rows;
 
 	if (callchain_param.mode == CHAIN_FLAT)
 		return callchain_node__count_flat_rows(node);
@@ -216,6 +284,11 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
+		if (symbol_conf.inline_name) {
+			inline_rows = callchain_list__inline_rows(chain);
+			n += inline_rows;
+		}
+
 		unfolded = chain->unfolded;
 	}
 
@@ -362,6 +435,19 @@ static void hist_entry__init_have_children(struct hist_entry *he)
 	he->init_have_children = true;
 }
 
+static void hist_entry_init_inline_node(struct hist_entry *he)
+{
+	if (he->inline_node)
+		return;
+
+	he->inline_node = inline_node__create(he->ms.map, he->ip);
+
+	if (he->inline_node == NULL)
+		return;
+
+	he->has_children = true;
+}
+
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -393,7 +479,12 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 
 		if (he->unfolded) {
 			if (he->leaf)
-				he->nr_rows = callchain__count_rows(&he->sorted_chain);
+				if (he->inline_node)
+					he->nr_rows = inline__count_rows(
+							he->inline_node);
+				else
+					he->nr_rows = callchain__count_rows(
+							&he->sorted_chain);
 			else
 				he->nr_rows = hierarchy_count_rows(browser, he, false);
 
@@ -753,6 +844,71 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
+static int hist_browser__show_inline(struct hist_browser *browser,
+				     struct inline_node *node,
+				     unsigned short row,
+				     int offset)
+{
+	struct inline_list *ilist;
+	char buf[1024];
+	int color, width, first_row;
+
+	first_row = row;
+	width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
+	list_for_each_entry(ilist, &node->val, list) {
+		if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+			color = HE_COLORSET_NORMAL;
+			if (ui_browser__is_current_entry(&browser->b, row))
+				color = HE_COLORSET_SELECTED;
+
+			if (callchain_param.key == CCKEY_ADDRESS ||
+			    callchain_param.key == CCKEY_SRCLINE) {
+				if (ilist->filename != NULL)
+					scnprintf(buf, sizeof(buf),
+						  "%s:%d (inline)",
+						  ilist->filename,
+						  ilist->line_nr);
+				else
+					scnprintf(buf, sizeof(buf), "??");
+			} else if (ilist->funcname != NULL)
+				scnprintf(buf, sizeof(buf), "%s (inline)",
+					  ilist->funcname);
+			else if (ilist->filename != NULL)
+				scnprintf(buf, sizeof(buf),
+					  "%s:%d (inline)",
+					  ilist->filename,
+					  ilist->line_nr);
+			else
+				scnprintf(buf, sizeof(buf), "??");
+
+			ui_browser__set_color(&browser->b, color);
+			hist_browser__gotorc(browser, row, 0);
+			ui_browser__write_nstring(&browser->b, " ",
+				LEVEL_OFFSET_STEP + offset);
+			ui_browser__write_nstring(&browser->b, buf, width);
+			row++;
+		}
+	}
+
+	return row - first_row;
+}
+
+static size_t show_inline_list(struct hist_browser *browser, struct map *map,
+			       u64 ip, int row, int offset)
+{
+	struct inline_node *node;
+	int ret;
+
+	node = inline_node__create(map, ip);
+	if (node == NULL)
+		return 0;
+
+	ret = hist_browser__show_inline(browser, node, row, offset);
+
+	inline_node__delete(node);
+	return ret;
+}
+
 static int hist_browser__show_callchain_list(struct hist_browser *browser,
 					     struct callchain_node *node,
 					     struct callchain_list *chain,
@@ -764,6 +920,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	char bf[1024], *alloc_str;
 	char buf[64], *alloc_str2;
 	const char *str;
+	int inline_rows = 0, ret = 1;
 
 	if (arg->row_offset != 0) {
 		arg->row_offset--;
@@ -801,10 +958,15 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	}
 
 	print(browser, chain, str, offset, row, arg);
-
 	free(alloc_str);
 	free(alloc_str2);
-	return 1;
+
+	if (symbol_conf.inline_name) {
+		inline_rows = show_inline_list(browser, chain->ms.map,
+					       chain->ip, row + 1, offset);
+	}
+
+	return ret + inline_rows;
 }
 
 static bool check_percent_display(struct rb_node *node, u64 parent_total)
@@ -1228,6 +1390,12 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		folded_sign = hist_entry__folded(entry);
 	}
 
+	if (symbol_conf.inline_name &&
+	    (!entry->has_children)) {
+		hist_entry_init_inline_node(entry);
+		folded_sign = hist_entry__folded(entry);
+	}
+
 	if (row_offset == 0) {
 		struct hpp_arg arg = {
 			.b		= &browser->b,
@@ -1259,7 +1427,8 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 
 			if (first) {
-				if (symbol_conf.use_callchain) {
+				if (symbol_conf.use_callchain ||
+					symbol_conf.inline_name) {
 					ui_browser__printf(&browser->b, "%c ", folded_sign);
 					width -= 2;
 				}
@@ -1301,8 +1470,14 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.is_current_entry = current_entry,
 		};
 
-		printed += hist_browser__show_callchain(browser, entry, 1, row,
-					hist_browser__show_callchain_entry, &arg,
+		if (entry->inline_node)
+			printed += hist_browser__show_inline(browser,
+					entry->inline_node, row, 0);
+		else
+			printed += hist_browser__show_callchain(browser,
+					entry, 1, row,
+					hist_browser__show_callchain_entry,
+					&arg,
 					hist_browser__check_output_full);
 	}
 
@@ -2308,7 +2483,7 @@ static int switch_data_file(void)
 		return ret;
 
 	memset(options, 0, sizeof(options));
-	memset(options, 0, sizeof(abs_path));
+	memset(abs_path, 0, sizeof(abs_path));
 
 	while ((dent = readdir(pwd_dir))) {
 		char path[PATH_MAX];
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 9ce142de536d..ffa5addf631d 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -11,6 +11,8 @@
 #include "../keysyms.h"
 #include "map.h"
 
+#include "sane_ctype.h"
+
 struct map_browser {
 	struct ui_browser b;
 	struct map	  *map;
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 8c9308ac30b7..e99ba86158d2 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -3,7 +3,8 @@
 #include "util/annotate.h"
 #include "util/evsel.h"
 #include "ui/helpline.h"
-
+#include <inttypes.h>
+#include <signal.h>
 
 enum {
 	ANN_COL__PERCENT,
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index a4f02de7c1b5..e24f83957705 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -4,7 +4,9 @@
 #include "../sort.h"
 #include "../hist.h"
 #include "../helpline.h"
+#include "../string2.h"
 #include "gtk.h"
+#include <signal.h>
 
 #define MAX_COLUMNS			32
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 5d632dca672a..59addd52d9cd 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -1,3 +1,4 @@
+#include <inttypes.h>
 #include <math.h>
 #include <linux/compiler.h>
 
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 50d13e58210f..5ea0b40c4fc2 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -4,6 +4,7 @@
 #include "../util/cache.h"
 #include "../util/debug.h"
 #include "../util/hist.h"
+#include "../util/util.h"
 
 pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 void *perf_gtk_handle;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 668f4aecf2e6..42e432bd2eb4 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -4,7 +4,10 @@
 #include "../../util/hist.h"
 #include "../../util/sort.h"
 #include "../../util/evsel.h"
-
+#include "../../util/srcline.h"
+#include "../../util/string2.h"
+#include "../../util/thread.h"
+#include "../../util/sane_ctype.h"
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
 {
@@ -17,6 +20,67 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
 	return ret;
 }
 
+static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
+			      int depth, int depth_mask, FILE *fp)
+{
+	struct dso *dso;
+	struct inline_node *node;
+	struct inline_list *ilist;
+	int ret = 0, i;
+
+	if (map == NULL)
+		return 0;
+
+	dso = map->dso;
+	if (dso == NULL)
+		return 0;
+
+	if (dso->kernel != DSO_TYPE_USER)
+		return 0;
+
+	node = dso__parse_addr_inlines(dso,
+				       map__rip_2objdump(map, ip));
+	if (node == NULL)
+		return 0;
+
+	list_for_each_entry(ilist, &node->val, list) {
+		if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+			ret += callchain__fprintf_left_margin(fp, left_margin);
+
+			for (i = 0; i < depth; i++) {
+				if (depth_mask & (1 << i))
+					ret += fprintf(fp, "|");
+				else
+					ret += fprintf(fp, " ");
+				ret += fprintf(fp, "          ");
+			}
+
+			if (callchain_param.key == CCKEY_ADDRESS ||
+			    callchain_param.key == CCKEY_SRCLINE) {
+				if (ilist->filename != NULL)
+					ret += fprintf(fp, "%s:%d (inline)",
+						       ilist->filename,
+						       ilist->line_nr);
+				else
+					ret += fprintf(fp, "??");
+			} else if (ilist->funcname != NULL)
+				ret += fprintf(fp, "%s (inline)",
+					       ilist->funcname);
+			else if (ilist->filename != NULL)
+				ret += fprintf(fp, "%s:%d (inline)",
+					       ilist->filename,
+					       ilist->line_nr);
+			else
+				ret += fprintf(fp, "??");
+
+			ret += fprintf(fp, "\n");
+		}
+	}
+
+	inline_node__delete(node);
+	return ret;
+}
+
 static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 					  int left_margin)
 {
@@ -78,6 +142,10 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
 	fputs(str, fp);
 	fputc('\n', fp);
 	free(alloc_str);
+
+	if (symbol_conf.inline_name)
+		ret += inline__fprintf(chain->ms.map, chain->ip,
+				       left_margin, depth, depth_mask, fp);
 	return ret;
 }
 
@@ -229,6 +297,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 			if (!i++ && field_order == NULL &&
 			    sort_order && !prefixcmp(sort_order, "sym"))
 				continue;
+
 			if (!printed) {
 				ret += callchain__fprintf_left_margin(fp, left_margin);
 				ret += fprintf(fp, "|\n");
@@ -251,6 +320,13 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
 			if (++entries_printed == callchain_param.print_limit)
 				break;
+
+			if (symbol_conf.inline_name)
+				ret += inline__fprintf(chain->ms.map,
+						       chain->ip,
+						       left_margin,
+						       0, 0,
+						       fp);
 		}
 		root = &cnode->rb_root;
 	}
@@ -529,6 +605,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       bool use_callchain)
 {
 	int ret;
+	int callchain_ret = 0;
+	int inline_ret = 0;
 	struct perf_hpp hpp = {
 		.buf		= bf,
 		.size		= size,
@@ -547,7 +625,16 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	ret = fprintf(fp, "%s\n", bf);
 
 	if (use_callchain)
-		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
+		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
+							      0, fp);
+
+	if (callchain_ret == 0 && symbol_conf.inline_name) {
+		inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
+		ret += inline_ret;
+		if (inline_ret > 0)
+			ret += fprintf(fp, "\n");
+	} else
+		ret += callchain_ret;
 
 	return ret;
 }
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 4ea2ba861fc2..d9350a1da48b 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,6 +1,7 @@
 #include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
+#include <linux/kernel.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5da376bc1afc..069583bdc670 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,4 +1,3 @@
-libperf-y += alias.o
 libperf-y += annotate.o
 libperf-y += block-range.o
 libperf-y += build-id.o
@@ -17,6 +16,7 @@ libperf-y += llvm-utils.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
 libperf-y += path.o
+libperf-y += print_binary.o
 libperf-y += rbtree.o
 libperf-y += libstring.o
 libperf-y += bitmap.o
@@ -42,6 +42,7 @@ libperf-y += pstack.o
 libperf-y += session.o
 libperf-$(CONFIG_AUDIT) += syscalltbl.o
 libperf-y += ordered-events.o
+libperf-y += namespaces.o
 libperf-y += comm.o
 libperf-y += thread.o
 libperf-y += thread_map.o
@@ -81,13 +82,16 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
+libperf-y += dump-insn.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
 libperf-y += mem-events.o
 libperf-y += vsprintf.o
 libperf-y += drv_configs.o
+libperf-y += units.o
 libperf-y += time-utils.o
+libperf-y += expr-bison.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -140,6 +144,10 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
+$(OUTPUT)util/expr-bison.c: util/expr.y
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__
+
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
@@ -152,6 +160,7 @@ CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
 CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_expr-bison.o         += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
deleted file mode 100644
index 6455471d9cd1..000000000000
--- a/tools/perf/util/alias.c
+++ /dev/null
@@ -1,78 +0,0 @@
-#include "cache.h"
-#include "util.h"
-#include "config.h"
-
-static const char *alias_key;
-static char *alias_val;
-
-static int alias_lookup_cb(const char *k, const char *v,
-			   void *cb __maybe_unused)
-{
-	if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) {
-		if (!v)
-			return config_error_nonbool(k);
-		alias_val = strdup(v);
-		return 0;
-	}
-	return 0;
-}
-
-char *alias_lookup(const char *alias)
-{
-	alias_key = alias;
-	alias_val = NULL;
-	perf_config(alias_lookup_cb, NULL);
-	return alias_val;
-}
-
-int split_cmdline(char *cmdline, const char ***argv)
-{
-	int src, dst, count = 0, size = 16;
-	char quoted = 0;
-
-	*argv = malloc(sizeof(char*) * size);
-
-	/* split alias_string */
-	(*argv)[count++] = cmdline;
-	for (src = dst = 0; cmdline[src];) {
-		char c = cmdline[src];
-		if (!quoted && isspace(c)) {
-			cmdline[dst++] = 0;
-			while (cmdline[++src]
-					&& isspace(cmdline[src]))
-				; /* skip */
-			if (count >= size) {
-				size += 16;
-				*argv = realloc(*argv, sizeof(char*) * size);
-			}
-			(*argv)[count++] = cmdline + dst;
-		} else if (!quoted && (c == '\'' || c == '"')) {
-			quoted = c;
-			src++;
-		} else if (c == quoted) {
-			quoted = 0;
-			src++;
-		} else {
-			if (c == '\\' && quoted != '\'') {
-				src++;
-				c = cmdline[src];
-				if (!c) {
-					zfree(argv);
-					return error("cmdline ends with \\");
-				}
-			}
-			cmdline[dst++] = c;
-			src++;
-		}
-	}
-
-	cmdline[dst] = 0;
-
-	if (quoted) {
-		zfree(argv);
-		return error("unclosed quote");
-	}
-
-	return count;
-}
-
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 273f21fa32b5..683f8340460c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -7,6 +7,8 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 
+#include <errno.h>
+#include <inttypes.h>
 #include "util.h"
 #include "ui/ui.h"
 #include "sort.h"
@@ -18,12 +20,16 @@
 #include "annotate.h"
 #include "evsel.h"
 #include "block-range.h"
+#include "string2.h"
 #include "arch/common.h"
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
+#include <linux/kernel.h>
 #include <sys/utsname.h>
 
+#include "sane_ctype.h"
+
 const char 	*disassembler_style;
 const char	*objdump_path;
 static regex_t	 file_lineno;
@@ -108,6 +114,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/arm64/annotate/instructions.c"
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
+#include "arch/s390/annotate/instructions.c"
 
 static struct arch architectures[] = {
 	{
@@ -130,6 +137,13 @@ static struct arch architectures[] = {
 		.name = "powerpc",
 		.init = powerpc__annotate_init,
 	},
+	{
+		.name = "s390",
+		.init = s390__annotate_init,
+		.objdump =  {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)
@@ -379,9 +393,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 	if (comment == NULL)
 		return 0;
 
-	while (comment[0] != '\0' && isspace(comment[0]))
-		++comment;
-
+	comment = ltrim(comment);
 	comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name);
 	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
 
@@ -426,9 +438,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 	if (comment == NULL)
 		return 0;
 
-	while (comment[0] != '\0' && isspace(comment[0]))
-		++comment;
-
+	comment = ltrim(comment);
 	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
 
 	return 0;
@@ -777,10 +787,7 @@ static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, str
 
 static int disasm_line__parse(char *line, const char **namep, char **rawp)
 {
-	char *name = line, tmp;
-
-	while (isspace(name[0]))
-		++name;
+	char tmp, *name = ltrim(line);
 
 	if (name[0] == '\0')
 		return -1;
@@ -798,12 +805,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 		goto out_free_name;
 
 	(*rawp)[0] = tmp;
-
-	if ((*rawp)[0] != '\0') {
-		(*rawp)++;
-		while (isspace((*rawp)[0]))
-			++(*rawp);
-	}
+	*rawp = ltrim(*rawp);
 
 	return 0;
 
@@ -1148,7 +1150,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
-	char *line = NULL, *parsed_line, *tmp, *tmp2, *c;
+	char *line = NULL, *parsed_line, *tmp, *tmp2;
 	size_t line_len;
 	s64 line_ip, offset = -1;
 	regmatch_t match[2];
@@ -1159,32 +1161,16 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 	if (!line)
 		return -1;
 
-	while (line_len != 0 && isspace(line[line_len - 1]))
-		line[--line_len] = '\0';
-
-	c = strchr(line, '\n');
-	if (c)
-		*c = 0;
-
 	line_ip = -1;
-	parsed_line = line;
+	parsed_line = rtrim(line);
 
 	/* /filename:linenr ? Save line number and ignore. */
-	if (regexec(&file_lineno, line, 2, match, 0) == 0) {
-		*line_nr = atoi(line + match[1].rm_so);
+	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
+		*line_nr = atoi(parsed_line + match[1].rm_so);
 		return 0;
 	}
 
-	/*
-	 * Strip leading spaces:
-	 */
-	tmp = line;
-	while (*tmp) {
-		if (*tmp != ' ')
-			break;
-		tmp++;
-	}
-
+	tmp = ltrim(parsed_line);
 	if (*tmp) {
 		/*
 		 * Parse hexa addresses followed by ':'
@@ -1307,6 +1293,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 {
 	char linkname[PATH_MAX];
 	char *build_id_filename;
+	char *build_id_path = NULL;
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso))
@@ -1322,8 +1309,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 		goto fallback;
 	}
 
+	build_id_path = strdup(filename);
+	if (!build_id_path)
+		return -1;
+
+	dirname(build_id_path);
+
 	if (dso__is_kcore(dso) ||
-	    readlink(filename, linkname, sizeof(linkname)) < 0 ||
+	    readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
 	    strstr(linkname, DSO__NAME_KALLSYMS) ||
 	    access(filename, R_OK)) {
 fallback:
@@ -1335,6 +1328,7 @@ fallback:
 		__symbol__join_symfs(filename, filename_size, dso->long_name);
 	}
 
+	free(build_id_path);
 	return 0;
 }
 
@@ -1435,7 +1429,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
+		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
@@ -1482,6 +1476,12 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 
 	nline = 0;
 	while (!feof(file)) {
+		/*
+		 * The source code line number (lineno) needs to be kept in
+		 * accross calls to symbol__parse_objdump_line(), so that it
+		 * can associate it with the instructions till the next one.
+		 * See disasm_line__new() and struct disasm_line::line_nr.
+		 */
 		if (symbol__parse_objdump_line(sym, map, arch, file, privsize,
 			    &lineno) < 0)
 			break;
@@ -1651,24 +1651,31 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 	start = map__rip_2objdump(map, sym->start);
 
 	for (i = 0; i < len; i++) {
-		u64 offset;
+		u64 offset, nr_samples;
 		double percent_max = 0.0;
 
 		src_line->nr_pcnt = nr_pcnt;
 
 		for (k = 0; k < nr_pcnt; k++) {
+			double percent = 0.0;
+
 			h = annotation__histogram(notes, evidx + k);
-			src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
+			nr_samples = h->addr[i];
+			if (h->sum)
+				percent = 100.0 * nr_samples / h->sum;
 
-			if (src_line->samples[k].percent > percent_max)
-				percent_max = src_line->samples[k].percent;
+			if (percent > percent_max)
+				percent_max = percent;
+			src_line->samples[k].percent = percent;
+			src_line->samples[k].nr = nr_samples;
 		}
 
 		if (percent_max <= 0.5)
 			goto next;
 
 		offset = start + i;
-		src_line->path = get_srcline(map->dso, offset, NULL, false);
+		src_line->path = get_srcline(map->dso, offset, NULL,
+					     false, true);
 		insert_source_line(&tmp_root, src_line);
 
 	next:
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 09776b5af991..948aa8e6fd39 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -98,7 +98,7 @@ struct cyc_hist {
 struct source_line_samples {
 	double		percent;
 	double		percent_sum;
-	double          nr;
+	u64		nr;
 };
 
 struct source_line {
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c5a6e0b12452..0daf63b9ee3e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -13,10 +13,10 @@
  *
  */
 
+#include <inttypes.h>
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <stdbool.h>
-#include <ctype.h>
 #include <string.h>
 #include <limits.h>
 #include <errno.h>
@@ -46,7 +46,6 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "asm/bug.h"
-#include "symbol/kallsyms.h"
 #include "auxtrace.h"
 
 #include <linux/hash.h>
@@ -59,6 +58,9 @@
 #include "intel-pt.h"
 #include "intel-bts.h"
 
+#include "sane_ctype.h"
+#include "symbol/kallsyms.h"
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,
 			void *userpg, int fd)
@@ -1826,7 +1828,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
 		filt->addr = start;
 		if (filt->range && !filt->size && !filt->sym_to) {
 			filt->size = size;
-			no_size = !!size;
+			no_size = !size;
 		}
 	}
 
@@ -1840,7 +1842,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
 		if (err)
 			return err;
 		filt->size = start + size - filt->addr;
-		no_size = !!size;
+		no_size = !size;
 	}
 
 	/* The very last symbol in kallsyms does not imply a particular size */
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 26fb1ee5746a..9f0de72d58e2 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -17,6 +17,7 @@
 #define __PERF_AUXTRACE_H
 
 #include <sys/types.h>
+#include <errno.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <linux/list.h>
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index bc6bc7062eb4..4bd2d1d882af 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -9,7 +9,9 @@
 #include <bpf/libbpf.h>
 #include <bpf/bpf.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <linux/string.h>
+#include <errno.h>
 #include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
@@ -17,6 +19,7 @@
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
 #include "parse-events.h"
+#include "strfilter.h"
 #include "llvm-utils.h"
 #include "c++/clang-c.h"
 
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index f2b737b225f2..48863867878b 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -85,6 +85,8 @@ int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err,
 			       char *buf, size_t size);
 
 #else
+#include <errno.h>
+
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
 		  bool source __maybe_unused)
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 6cdbee119ceb..1356220a9f1b 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -12,6 +12,7 @@
 #include "bpf-loader.h"
 #include "bpf-prologue.h"
 #include "probe-finder.h"
+#include <errno.h>
 #include <dwarf-regs.h>
 #include <linux/filter.h>
 
diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h
index d94cbea12899..ba564838375f 100644
--- a/tools/perf/util/bpf-prologue.h
+++ b/tools/perf/util/bpf-prologue.h
@@ -18,6 +18,8 @@ int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
 		      struct bpf_insn *new_prog, size_t *new_cnt,
 		      size_t cnt_space);
 #else
+#include <errno.h>
+
 static inline int
 bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
 		  int nargs __maybe_unused,
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e528c40739cc..168cc49654e7 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -7,18 +7,26 @@
  * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
  */
 #include "util.h"
+#include <dirent.h>
+#include <errno.h>
 #include <stdio.h>
+#include <sys/stat.h>
+#include <sys/types.h>
 #include "build-id.h"
 #include "event.h"
 #include "symbol.h"
+#include "thread.h"
 #include <linux/kernel.h>
 #include "debug.h"
 #include "session.h"
 #include "tool.h"
 #include "header.h"
 #include "vdso.h"
+#include "path.h"
 #include "probe-file.h"
+#include "strlist.h"
 
+#include "sane_ctype.h"
 
 static bool no_buildid_cache;
 
@@ -182,13 +190,17 @@ char *build_id_cache__origname(const char *sbuild_id)
 	char buf[PATH_MAX];
 	char *ret = NULL, *p;
 	size_t offs = 5;	/* == strlen("../..") */
+	ssize_t len;
 
 	linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
 	if (!linkname)
 		return NULL;
 
-	if (readlink(linkname, buf, PATH_MAX) < 0)
+	len = readlink(linkname, buf, sizeof(buf) - 1);
+	if (len <= 0)
 		goto out;
+	buf[len] = '\0';
+
 	/* The link should be "../..<origpath>/<sbuild_id>" */
 	p = strrchr(buf, '/');	/* Cut off the "/<sbuild_id>" */
 	if (p && (p > buf + offs)) {
@@ -443,14 +455,14 @@ void disable_buildid_cache(void)
 }
 
 static bool lsdir_bid_head_filter(const char *name __maybe_unused,
-				  struct dirent *d __maybe_unused)
+				  struct dirent *d)
 {
 	return (strlen(d->d_name) == 2) &&
 		isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]);
 }
 
 static bool lsdir_bid_tail_filter(const char *name __maybe_unused,
-				  struct dirent *d __maybe_unused)
+				  struct dirent *d)
 {
 	int i = 0;
 	while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3)
@@ -690,7 +702,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 		err = 0;
 
 	/* Update SDT cache : error is just warned */
-	if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+	if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
 		pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index d27990610f9f..a96081121179 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -5,7 +5,6 @@
 #define SBUILD_ID_SIZE	(BUILD_ID_SIZE * 2 + 1)
 
 #include "tool.h"
-#include "strlist.h"
 #include <linux/types.h>
 
 extern struct perf_tool build_id__mark_dso_hit_ops;
@@ -34,6 +33,9 @@ char *build_id_cache__origname(const char *sbuild_id);
 char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
 char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
 			       bool is_kallsyms, bool is_vdso);
+
+struct strlist;
+
 struct strlist *build_id_cache__list_all(bool validonly);
 char *build_id_cache__complement(const char *incomplete_sbuild_id);
 int build_id_cache__list_build_ids(const char *pathname,
diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h
index 0eadd792ab1f..ccafcf72b37a 100644
--- a/tools/perf/util/c++/clang-c.h
+++ b/tools/perf/util/c++/clang-c.h
@@ -20,6 +20,7 @@ extern int perf_clang__compile_bpf(const char *filename,
 				   size_t *p_obj_buf_sz);
 #else
 
+#include <errno.h>
 
 static inline void perf_clang__init(void) { }
 static inline void perf_clang__cleanup(void) { }
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 512c0c83fbc6..0328f297a748 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -15,7 +15,6 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
-char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
 #define alloc_nr(x) (((x)+16)*3/2)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index aba953421a03..81fc29ac798f 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <inttypes.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdbool.h>
@@ -23,6 +24,21 @@
 #include "machine.h"
 #include "callchain.h"
 
+#define CALLCHAIN_PARAM_DEFAULT			\
+	.mode		= CHAIN_GRAPH_ABS,	\
+	.min_percent	= 0.5,			\
+	.order		= ORDER_CALLEE,		\
+	.key		= CCKEY_FUNCTION,	\
+	.value		= CCVAL_PERCENT,	\
+
+struct callchain_param callchain_param = {
+	CALLCHAIN_PARAM_DEFAULT
+};
+
+struct callchain_param callchain_param_default = {
+	CALLCHAIN_PARAM_DEFAULT
+};
+
 __thread struct callchain_cursor callchain_cursor;
 
 int parse_callchain_record_opt(const char *arg, struct callchain_param *param)
@@ -80,6 +96,10 @@ static int parse_callchain_sort_key(const char *value)
 		callchain_param.key = CCKEY_ADDRESS;
 		return 0;
 	}
+	if (!strncmp(value, "srcline", strlen(value))) {
+		callchain_param.key = CCKEY_SRCLINE;
+		return 0;
+	}
 	if (!strncmp(value, "branch", strlen(value))) {
 		callchain_param.branch_callstack = 1;
 		return 0;
@@ -108,11 +128,37 @@ static int parse_callchain_value(const char *value)
 	return -1;
 }
 
+static int get_stack_size(const char *str, unsigned long *_size)
+{
+	char *endptr;
+	unsigned long size;
+	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
+
+	size = strtoul(str, &endptr, 0);
+
+	do {
+		if (*endptr)
+			break;
+
+		size = round_up(size, sizeof(u64));
+		if (!size || size > max_size)
+			break;
+
+		*_size = size;
+		return 0;
+
+	} while (0);
+
+	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+	       max_size, str);
+	return -1;
+}
+
 static int
 __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 {
 	char *tok;
-	char *endptr;
+	char *endptr, *saveptr = NULL;
 	bool minpcnt_set = false;
 	bool record_opt_set = false;
 	bool try_stack_size = false;
@@ -123,7 +169,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 	if (!arg)
 		return 0;
 
-	while ((tok = strtok((char *)arg, ",")) != NULL) {
+	while ((tok = strtok_r((char *)arg, ",", &saveptr)) != NULL) {
 		if (!strncmp(tok, "none", strlen(tok))) {
 			callchain_param.mode = CHAIN_NONE;
 			callchain_param.enabled = false;
@@ -191,6 +237,68 @@ int parse_callchain_top_opt(const char *arg)
 	return __parse_callchain_report_opt(arg, true);
 }
 
+int parse_callchain_record(const char *arg, struct callchain_param *param)
+{
+	char *tok, *name, *saveptr = NULL;
+	char *buf;
+	int ret = -1;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(arg) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, arg);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+	name = tok ? : (char *)buf;
+
+	do {
+		/* Framepointer style */
+		if (!strncmp(name, "fp", sizeof("fp"))) {
+			if (!strtok_r(NULL, ",", &saveptr)) {
+				param->record_mode = CALLCHAIN_FP;
+				ret = 0;
+			} else
+				pr_err("callchain: No more arguments "
+				       "needed for --call-graph fp\n");
+			break;
+
+		/* Dwarf style */
+		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+			const unsigned long default_stack_dump_size = 8192;
+
+			ret = 0;
+			param->record_mode = CALLCHAIN_DWARF;
+			param->dump_size = default_stack_dump_size;
+
+			tok = strtok_r(NULL, ",", &saveptr);
+			if (tok) {
+				unsigned long size = 0;
+
+				ret = get_stack_size(tok, &size);
+				param->dump_size = size;
+			}
+		} else if (!strncmp(name, "lbr", sizeof("lbr"))) {
+			if (!strtok_r(NULL, ",", &saveptr)) {
+				param->record_mode = CALLCHAIN_LBR;
+				ret = 0;
+			} else
+				pr_err("callchain: No more arguments "
+					"needed for --call-graph lbr\n");
+			break;
+		} else {
+			pr_err("callchain: Unknown --call-graph option "
+			       "value: %s\n", arg);
+			break;
+		}
+
+	} while (0);
+
+	free(buf);
+	return ret;
+}
+
 int perf_callchain_config(const char *var, const char *value)
 {
 	char *endptr;
@@ -510,14 +618,51 @@ enum match_result {
 	MATCH_GT,
 };
 
+static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
+					     struct callchain_list *cnode)
+{
+	char *left = get_srcline(cnode->ms.map->dso,
+				 map__rip_2objdump(cnode->ms.map, cnode->ip),
+				 cnode->ms.sym, true, false);
+	char *right = get_srcline(node->map->dso,
+				  map__rip_2objdump(node->map, node->ip),
+				  node->sym, true, false);
+	enum match_result ret = MATCH_EQ;
+	int cmp;
+
+	if (left && right)
+		cmp = strcmp(left, right);
+	else if (!left && right)
+		cmp = 1;
+	else if (left && !right)
+		cmp = -1;
+	else if (cnode->ip == node->ip)
+		cmp = 0;
+	else
+		cmp = (cnode->ip < node->ip) ? -1 : 1;
+
+	if (cmp != 0)
+		ret = cmp < 0 ? MATCH_LT : MATCH_GT;
+
+	free_srcline(left);
+	free_srcline(right);
+	return ret;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
 				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
 
-	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION) {
+	if (callchain_param.key == CCKEY_SRCLINE) {
+		enum match_result match = match_chain_srcline(node, cnode);
+
+		if (match != MATCH_ERROR)
+			return match;
+	}
+
+	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
 	} else {
@@ -911,15 +1056,16 @@ out:
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso)
 {
+	bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+	bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE;
 	int printed;
 
 	if (cl->ms.sym) {
-		if (callchain_param.key == CCKEY_ADDRESS &&
-		    cl->ms.map && !cl->srcline)
+		if (show_srcline && cl->ms.map && !cl->srcline)
 			cl->srcline = get_srcline(cl->ms.map->dso,
 						  map__rip_2objdump(cl->ms.map,
 								    cl->ip),
-						  cl->ms.sym, false);
+						  cl->ms.sym, false, show_addr);
 		if (cl->srcline)
 			printed = scnprintf(bf, bfsize, "%s %s",
 					cl->ms.sym->name, cl->srcline);
@@ -1063,63 +1209,100 @@ int callchain_branch_counts(struct callchain_root *root,
 						  cycles_count);
 }
 
-static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
-				   u64 branch_count, u64 predicted_count,
-				   u64 abort_count, u64 cycles_count,
-				   u64 iter_count, u64 samples_count)
+static int counts_str_build(char *bf, int bfsize,
+			     u64 branch_count, u64 predicted_count,
+			     u64 abort_count, u64 cycles_count,
+			     u64 iter_count, u64 samples_count)
 {
 	double predicted_percent = 0.0;
 	const char *null_str = "";
 	char iter_str[32];
-	char *str;
-	u64 cycles = 0;
-
-	if (branch_count == 0) {
-		if (fp)
-			return fprintf(fp, " (calltrace)");
+	char cycle_str[32];
+	char *istr, *cstr;
+	u64 cycles;
 
+	if (branch_count == 0)
 		return scnprintf(bf, bfsize, " (calltrace)");
-	}
+
+	cycles = cycles_count / branch_count;
 
 	if (iter_count && samples_count) {
-		scnprintf(iter_str, sizeof(iter_str),
-			 ", iterations:%" PRId64 "",
-			 iter_count / samples_count);
-		str = iter_str;
+		if (cycles > 0)
+			scnprintf(iter_str, sizeof(iter_str),
+				 " iterations:%" PRId64 "",
+				 iter_count / samples_count);
+		else
+			scnprintf(iter_str, sizeof(iter_str),
+				 "iterations:%" PRId64 "",
+				 iter_count / samples_count);
+		istr = iter_str;
+	} else
+		istr = (char *)null_str;
+
+	if (cycles > 0) {
+		scnprintf(cycle_str, sizeof(cycle_str),
+			  "cycles:%" PRId64 "", cycles);
+		cstr = cycle_str;
 	} else
-		str = (char *)null_str;
+		cstr = (char *)null_str;
 
 	predicted_percent = predicted_count * 100.0 / branch_count;
-	cycles = cycles_count / branch_count;
 
-	if ((predicted_percent >= 100.0) && (abort_count == 0)) {
-		if (fp)
-			return fprintf(fp, " (cycles:%" PRId64 "%s)",
-				       cycles, str);
+	if ((predicted_count == branch_count) && (abort_count == 0)) {
+		if ((cycles > 0) || (istr != (char *)null_str))
+			return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
+		else
+			return scnprintf(bf, bfsize, "%s", (char *)null_str);
+	}
 
-		return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)",
-				 cycles, str);
+	if ((predicted_count < branch_count) && (abort_count == 0)) {
+		if ((cycles > 0) || (istr != (char *)null_str))
+			return scnprintf(bf, bfsize,
+				" (predicted:%.1f%% %s%s)",
+				predicted_percent, cstr, istr);
+		else {
+			return scnprintf(bf, bfsize,
+				" (predicted:%.1f%%)",
+				predicted_percent);
+		}
 	}
 
-	if ((predicted_percent < 100.0) && (abort_count == 0)) {
-		if (fp)
-			return fprintf(fp,
-				" (predicted:%.1f%%, cycles:%" PRId64 "%s)",
-				predicted_percent, cycles, str);
+	if ((predicted_count == branch_count) && (abort_count > 0)) {
+		if ((cycles > 0) || (istr != (char *)null_str))
+			return scnprintf(bf, bfsize,
+				" (abort:%" PRId64 " %s%s)",
+				abort_count, cstr, istr);
+		else
+			return scnprintf(bf, bfsize,
+				" (abort:%" PRId64 ")",
+				abort_count);
+	}
 
+	if ((cycles > 0) || (istr != (char *)null_str))
 		return scnprintf(bf, bfsize,
-			" (predicted:%.1f%%, cycles:%" PRId64 "%s)",
-			predicted_percent, cycles, str);
-	}
+			" (predicted:%.1f%% abort:%" PRId64 " %s%s)",
+			predicted_percent, abort_count, cstr, istr);
+
+	return scnprintf(bf, bfsize,
+			" (predicted:%.1f%% abort:%" PRId64 ")",
+			predicted_percent, abort_count);
+}
+
+static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
+				   u64 branch_count, u64 predicted_count,
+				   u64 abort_count, u64 cycles_count,
+				   u64 iter_count, u64 samples_count)
+{
+	char str[128];
+
+	counts_str_build(str, sizeof(str), branch_count,
+			 predicted_count, abort_count, cycles_count,
+			 iter_count, samples_count);
 
 	if (fp)
-		return fprintf(fp,
-		" (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
-			predicted_percent, abort_count, cycles, str);
+		return fprintf(fp, "%s", str);
 
-	return scnprintf(bf, bfsize,
-		" (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
-		predicted_percent, abort_count, cycles, str);
+	return scnprintf(bf, bfsize, "%s", str);
 }
 
 int callchain_list_counts__printf_value(struct callchain_node *node,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 4f4b60f1558a..c56c23dbbf72 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -77,7 +77,8 @@ typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 
 enum chain_key {
 	CCKEY_FUNCTION,
-	CCKEY_ADDRESS
+	CCKEY_ADDRESS,
+	CCKEY_SRCLINE
 };
 
 enum chain_value {
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index eafbf11442b2..03347748f3fa 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -4,6 +4,7 @@
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
+#include <linux/stringify.h>
 
 int nr_cgroups;
 
@@ -27,8 +28,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 	path_v1[0] = '\0';
 	path_v2[0] = '\0';
 
-	while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
-				STR(PATH_MAX)"s %*d %*d\n",
+	while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
+				__stringify(PATH_MAX)"s %*d %*d\n",
 				mountpoint, type, tokens) == 3) {
 
 		if (!path_v1[0] && !strcmp(type, "cgroup")) {
@@ -127,19 +128,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (atomic_read(&cgrp->refcnt) == 0)
+	if (refcount_read(&cgrp->refcnt) == 0)
 		free(cgrp);
 
 	return -1;
 found:
-	atomic_inc(&cgrp->refcnt);
+	refcount_inc(&cgrp->refcnt);
 	counter->cgrp = cgrp;
 	return 0;
 }
 
 void close_cgroup(struct cgroup_sel *cgrp)
 {
-	if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
+	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
 		zfree(&cgrp->name);
 		free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 31f8dcdbd7ef..d91966b97cbd 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,14 +1,14 @@
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 struct option;
 
 struct cgroup_sel {
 	char *name;
 	int fd;
-	atomic_t refcnt;
+	refcount_t refcnt;
 };
 
 
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index f0dcd0ee0afa..4b4f00df58a8 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include <sched.h>
 #include "util.h"
 #include "../perf.h"
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
index d0d465953d36..94a5a7d829d5 100644
--- a/tools/perf/util/cloexec.h
+++ b/tools/perf/util/cloexec.h
@@ -3,10 +3,4 @@
 
 unsigned long perf_event_open_cloexec_flag(void);
 
-#ifdef __GLIBC_PREREQ
-#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__)
-int sched_getcpu(void) __THROW;
-#endif
-#endif
-
 #endif /* __PERF_CLOEXEC_H */
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index a93997f16dec..52122bcc3170 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -1,6 +1,8 @@
 #ifndef __PERF_COLOR_H
 #define __PERF_COLOR_H
 
+#include <stdio.h>
+
 /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */
 #define COLOR_MAXLEN 24
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 21b7ff382c3f..7bc981b6bf29 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -1,13 +1,15 @@
 #include "comm.h"
 #include "util.h"
+#include <errno.h>
 #include <stdlib.h>
 #include <stdio.h>
-#include <linux/atomic.h>
+#include <string.h>
+#include <linux/refcount.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	atomic_t refcnt;
+	refcount_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
@@ -16,13 +18,13 @@ static struct rb_root comm_str_root;
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
 	if (cs)
-		atomic_inc(&cs->refcnt);
+		refcount_inc(&cs->refcnt);
 	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (cs && atomic_dec_and_test(&cs->refcnt)) {
+	if (cs && refcount_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);
@@ -43,7 +45,7 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
-	atomic_set(&cs->refcnt, 0);
+	refcount_set(&cs->refcnt, 1);
 
 	return cs;
 }
@@ -61,7 +63,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 
 		cmp = strcmp(str, iter->str);
 		if (!cmp)
-			return iter;
+			return comm_str__get(iter);
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
@@ -95,8 +97,6 @@ struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 		return NULL;
 	}
 
-	comm_str__get(comm->comm_str);
-
 	return comm;
 }
 
@@ -108,7 +108,6 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 	if (!new)
 		return -ENOMEM;
 
-	comm_str__get(new);
 	comm_str__put(old);
 	comm->comm_str = new;
 	comm->start = timestamp;
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
new file mode 100644
index 000000000000..67fd1bb7c2b7
--- /dev/null
+++ b/tools/perf/util/compress.h
@@ -0,0 +1,12 @@
+#ifndef PERF_COMPRESS_H
+#define PERF_COMPRESS_H
+
+#ifdef HAVE_ZLIB_SUPPORT
+int gzip_decompress_to_file(const char *input, int output_fd);
+#endif
+
+#ifdef HAVE_LZMA_SUPPORT
+int lzma_decompress_to_file(const char *input, int output_fd);
+#endif
+
+#endif /* PERF_COMPRESS_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0c7d5a4975cd..8d724f0fa5a8 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -8,12 +8,19 @@
  * Copyright (C) Johannes Schindelin, 2005
  *
  */
+#include <errno.h>
+#include <sys/param.h>
 #include "util.h"
 #include "cache.h"
 #include <subcmd/exec-cmd.h>
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
 #include "config.h"
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "sane_ctype.h"
 
 #define MAXNAME (256)
 
@@ -627,6 +634,8 @@ static int perf_config_set__init(struct perf_config_set *set)
 {
 	int ret = -1;
 	const char *home = NULL;
+	char *user_config;
+	struct stat st;
 
 	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
 	if (config_exclusive_filename)
@@ -637,35 +646,41 @@ static int perf_config_set__init(struct perf_config_set *set)
 	}
 
 	home = getenv("HOME");
-	if (perf_config_global() && home) {
-		char *user_config = strdup(mkpath("%s/.perfconfig", home));
-		struct stat st;
 
-		if (user_config == NULL) {
-			warning("Not enough memory to process %s/.perfconfig, "
-				"ignoring it.", home);
-			goto out;
-		}
+	/*
+	 * Skip reading user config if:
+	 *   - there is no place to read it from (HOME)
+	 *   - we are asked not to (PERF_CONFIG_NOGLOBAL=1)
+	 */
+	if (!home || !*home || !perf_config_global())
+		return 0;
 
-		if (stat(user_config, &st) < 0) {
-			if (errno == ENOENT)
-				ret = 0;
-			goto out_free;
-		}
+	user_config = strdup(mkpath("%s/.perfconfig", home));
+	if (user_config == NULL) {
+		warning("Not enough memory to process %s/.perfconfig, "
+			"ignoring it.", home);
+		goto out;
+	}
 
-		ret = 0;
+	if (stat(user_config, &st) < 0) {
+		if (errno == ENOENT)
+			ret = 0;
+		goto out_free;
+	}
 
-		if (st.st_uid && (st.st_uid != geteuid())) {
-			warning("File %s not owned by current user or root, "
-				"ignoring it.", user_config);
-			goto out_free;
-		}
+	ret = 0;
 
-		if (st.st_size)
-			ret = perf_config_from_file(collect_config, user_config, set);
-out_free:
-		free(user_config);
+	if (st.st_uid && (st.st_uid != geteuid())) {
+		warning("File %s not owned by current user or root, "
+			"ignoring it.", user_config);
+		goto out_free;
 	}
+
+	if (st.st_size)
+		ret = perf_config_from_file(collect_config, user_config, set);
+
+out_free:
+	free(user_config);
 out:
 	return ret;
 }
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index e3fde313deb2..c4af82ab7808 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -1,6 +1,8 @@
+#include <errno.h>
 #include <stdlib.h>
 #include "evsel.h"
 #include "counts.h"
+#include "util.h"
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 8c7504939113..37b3bb79ee08 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -3,11 +3,14 @@
 #include "../perf.h"
 #include "cpumap.h"
 #include <assert.h>
+#include <dirent.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
+#include "sane_ctype.h"
+
 static int max_cpu_num;
 static int max_present_cpu_num;
 static int max_node_num;
@@ -29,7 +32,7 @@ static struct cpu_map *cpu_map__default_new(void)
 			cpus->map[i] = i;
 
 		cpus->nr = nr_cpus;
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -43,7 +46,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 	if (cpus != NULL) {
 		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -252,7 +255,7 @@ struct cpu_map *cpu_map__dummy_new(void)
 	if (cpus != NULL) {
 		cpus->nr = 1;
 		cpus->map[0] = -1;
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -269,7 +272,7 @@ struct cpu_map *cpu_map__empty_new(int nr)
 		for (i = 0; i < nr; i++)
 			cpus->map[i] = -1;
 
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -278,7 +281,7 @@ struct cpu_map *cpu_map__empty_new(int nr)
 static void cpu_map__delete(struct cpu_map *map)
 {
 	if (map) {
-		WARN_ONCE(atomic_read(&map->refcnt) != 0,
+		WARN_ONCE(refcount_read(&map->refcnt) != 0,
 			  "cpu_map refcnt unbalanced\n");
 		free(map);
 	}
@@ -287,13 +290,13 @@ static void cpu_map__delete(struct cpu_map *map)
 struct cpu_map *cpu_map__get(struct cpu_map *map)
 {
 	if (map)
-		atomic_inc(&map->refcnt);
+		refcount_inc(&map->refcnt);
 	return map;
 }
 
 void cpu_map__put(struct cpu_map *map)
 {
-	if (map && atomic_dec_and_test(&map->refcnt))
+	if (map && refcount_dec_and_test(&map->refcnt))
 		cpu_map__delete(map);
 }
 
@@ -357,7 +360,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
-	atomic_set(&c->refcnt, 1);
+	refcount_set(&c->refcnt, 1);
 	*res = c;
 	return 0;
 }
@@ -673,3 +676,49 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
 	pr_debug("cpumask list: %s\n", buf);
 	return ret;
 }
+
+static char hex_char(unsigned char val)
+{
+	if (val < 10)
+		return val + '0';
+	if (val < 16)
+		return val - 10 + 'a';
+	return '?';
+}
+
+size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
+{
+	int i, cpu;
+	char *ptr = buf;
+	unsigned char *bitmap;
+	int last_cpu = cpu_map__cpu(map, map->nr - 1);
+
+	bitmap = zalloc((last_cpu + 7) / 8);
+	if (bitmap == NULL) {
+		buf[0] = '\0';
+		return 0;
+	}
+
+	for (i = 0; i < map->nr; i++) {
+		cpu = cpu_map__cpu(map, i);
+		bitmap[cpu / 8] |= 1 << (cpu % 8);
+	}
+
+	for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+		unsigned char bits = bitmap[cpu / 8];
+
+		if (cpu % 8)
+			bits >>= 4;
+		else
+			bits &= 0xf;
+
+		*ptr++ = hex_char(bits);
+		if ((cpu % 32) == 0 && cpu > 0)
+			*ptr++ = ',';
+	}
+	*ptr = '\0';
+	free(bitmap);
+
+	buf[size - 1] = '\0';
+	return ptr - buf;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 1a0549af8f5c..6b8bff87481d 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -3,13 +3,13 @@
 
 #include <stdio.h>
 #include <stdbool.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 #include "perf.h"
 #include "util/debug.h"
 
 struct cpu_map {
-	atomic_t refcnt;
+	refcount_t refcnt;
 	int nr;
 	int map[];
 };
@@ -20,6 +20,7 @@ struct cpu_map *cpu_map__dummy_new(void);
 struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size);
+size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
 int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index d4a5a21c2a7e..4b261c2ec0f1 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -3,7 +3,7 @@
  *
  * No surprises, and works with signed and unsigned chars.
  */
-#include "util.h"
+#include "sane_ctype.h"
 
 enum {
 	S = GIT_SPACE,
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 4e6cbc99f08e..89d50318833d 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -7,7 +7,10 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 
+#include <errno.h>
+#include <inttypes.h>
 #include <linux/compiler.h>
+#include <linux/kernel.h>
 #include <babeltrace/ctf-writer/writer.h>
 #include <babeltrace/ctf-writer/clock.h>
 #include <babeltrace/ctf-writer/stream.h>
@@ -27,6 +30,7 @@
 #include "evsel.h"
 #include "machine.h"
 #include "config.h"
+#include "sane_ctype.h"
 
 #define pr_N(n, fmt, ...) \
 	eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
@@ -1468,6 +1472,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 			.lost            = perf_event__process_lost,
 			.tracing_data    = perf_event__process_tracing_data,
 			.build_id        = perf_event__process_build_id,
+			.namespaces      = perf_event__process_namespaces,
 			.ordered_events  = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 60bfc9ca1e22..e84bbc8ec058 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <errno.h>
 #include <unistd.h>
 #include <string.h>
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 03eb81f30d0d..a5b3777ffee6 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -2,19 +2,26 @@
 
 #include "../perf.h"
 
+#include <inttypes.h>
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <sys/wait.h>
 #include <api/debug.h>
 #include <linux/time64.h>
-
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
 #include "cache.h"
 #include "color.h"
 #include "event.h"
 #include "debug.h"
+#include "print_binary.h"
 #include "util.h"
 #include "target.h"
 
+#include "sane_ctype.h"
+
 int verbose;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
@@ -244,3 +251,31 @@ void perf_debug_setup(void)
 {
 	libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
 }
+
+/* Obtain a backtrace and print it to stdout. */
+#ifdef HAVE_BACKTRACE_SUPPORT
+void dump_stack(void)
+{
+	void *array[16];
+	size_t size = backtrace(array, ARRAY_SIZE(array));
+	char **strings = backtrace_symbols(array, size);
+	size_t i;
+
+	printf("Obtained %zd stack frames.\n", size);
+
+	for (i = 0; i < size; i++)
+		printf("%s\n", strings[i]);
+
+	free(strings);
+}
+#else
+void dump_stack(void) {}
+#endif
+
+void sighandler_dump_stack(int sig)
+{
+	psignal(sig, "perf");
+	dump_stack();
+	signal(sig, SIG_DFL);
+	raise(sig);
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 98832f5531d3..8a23ea1a71c7 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -56,4 +56,7 @@ int perf_debug_option(const char *str);
 void perf_debug_setup(void);
 int perf_quiet_option(void);
 
+void dump_stack(void);
+void sighandler_dump_stack(int sig);
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
index 3e6062ab2cdd..cb66d334f532 100644
--- a/tools/perf/util/demangle-java.c
+++ b/tools/perf/util/demangle-java.c
@@ -7,6 +7,8 @@
 
 #include "demangle-java.h"
 
+#include "sane_ctype.h"
+
 enum {
 	MODE_PREFIX = 0,
 	MODE_CLASS  = 1,
diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c
index 1647f285c629..eec754243f4d 100644
--- a/tools/perf/util/drv_configs.c
+++ b/tools/perf/util/drv_configs.c
@@ -17,6 +17,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "pmu.h"
+#include <errno.h>
 
 static int
 perf_evsel__apply_drv_configs(struct perf_evsel *evsel,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d38b62a700ca..a96a99d2369f 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,12 +1,20 @@
 #include <asm/bug.h>
+#include <linux/kernel.h>
 #include <sys/time.h>
 #include <sys/resource.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <errno.h>
+#include "compress.h"
+#include "path.h"
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
+#include "string2.h"
 #include "vdso.h"
 
 static const char * const debuglink_paths[] = {
@@ -1109,7 +1117,7 @@ struct dso *dso__new(const char *name)
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 		pthread_mutex_init(&dso->lock, NULL);
-		atomic_set(&dso->refcnt, 1);
+		refcount_set(&dso->refcnt, 1);
 	}
 
 	return dso;
@@ -1147,13 +1155,13 @@ void dso__delete(struct dso *dso)
 struct dso *dso__get(struct dso *dso)
 {
 	if (dso)
-		atomic_inc(&dso->refcnt);
+		refcount_inc(&dso->refcnt);
 	return dso;
 }
 
 void dso__put(struct dso *dso)
 {
-	if (dso && atomic_dec_and_test(&dso->refcnt))
+	if (dso && refcount_dec_and_test(&dso->refcnt))
 		dso__delete(dso);
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ecc4bbd3f82e..12350b171727 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <sys/types.h>
@@ -187,7 +187,7 @@ struct dso {
 		void	 *priv;
 		u64	 db_id;
 	};
-	atomic_t	 refcnt;
+	refcount_t	 refcnt;
 	char		 name[0];
 };
 
diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c
new file mode 100644
index 000000000000..ffbdb19f05d0
--- /dev/null
+++ b/tools/perf/util/dump-insn.c
@@ -0,0 +1,14 @@
+#include <linux/compiler.h>
+#include "dump-insn.h"
+
+/* Fallback code */
+
+__weak
+const char *dump_insn(struct perf_insn *x __maybe_unused,
+		      u64 ip __maybe_unused, u8 *inbuf __maybe_unused,
+		      int inlen __maybe_unused, int *lenp)
+{
+	if (lenp)
+		*lenp = 0;
+	return "?";
+}
diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h
new file mode 100644
index 000000000000..90fb115981cf
--- /dev/null
+++ b/tools/perf/util/dump-insn.h
@@ -0,0 +1,22 @@
+#ifndef __PERF_DUMP_INSN_H
+#define __PERF_DUMP_INSN_H 1
+
+#define MAXINSN 15
+
+#include <linux/types.h>
+
+struct thread;
+
+struct perf_insn {
+	/* Initialized by callers: */
+	struct thread *thread;
+	u8	      cpumode;
+	bool	      is64bit;
+	int	      cpu;
+	/* Temporary */
+	char	      out[256];
+};
+
+const char *dump_insn(struct perf_insn *x, u64 ip,
+		      u8 *inbuf, int inlen, int *lenp);
+#endif
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 41e068e94349..f5acda13dcfa 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -17,10 +17,13 @@
  *
  */
 
+#include <errno.h>
+#include <inttypes.h>
 #include <stdbool.h>
 #include "util.h"
 #include "debug.h"
 #include "dwarf-aux.h"
+#include "string2.h"
 
 /**
  * cu_find_realpath - Find the realpath of the target file
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 62bc4a86a970..c708395b3cb6 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -8,6 +8,7 @@
 #include <debug.h>
 #include <dwarf-regs.h>
 #include <elf.h>
+#include <linux/kernel.h>
 
 #ifndef EM_AARCH64
 #define EM_AARCH64	183  /* ARM 64 bit */
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 075fc77286bf..9e21538c42ae 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -1,6 +1,7 @@
 #include "cpumap.h"
 #include "env.h"
 #include "util.h"
+#include <errno.h>
 
 struct perf_env perf_env;
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4ea7ce72ed9c..142835c0ca0a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,15 +1,23 @@
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include <api/fs/fs.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
 #include "machine.h"
 #include "sort.h"
-#include "string.h"
+#include "string2.h"
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
+#include "sane_ctype.h"
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
 #include "stat.h"
@@ -31,6 +39,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
 	[PERF_RECORD_SWITCH]			= "SWITCH",
 	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
+	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -49,6 +58,16 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 };
 
+static const char *perf_ns__names[] = {
+	[NET_NS_INDEX]		= "net",
+	[UTS_NS_INDEX]		= "uts",
+	[IPC_NS_INDEX]		= "ipc",
+	[PID_NS_INDEX]		= "pid",
+	[USER_NS_INDEX]		= "user",
+	[MNT_NS_INDEX]		= "mnt",
+	[CGROUP_NS_INDEX]	= "cgroup",
+};
+
 const char *perf_event__name(unsigned int id)
 {
 	if (id >= ARRAY_SIZE(perf_event__names))
@@ -58,6 +77,13 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
+static const char *perf_ns__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_ns__names))
+		return "UNKNOWN";
+	return perf_ns__names[id];
+}
+
 static int perf_tool__process_synth_event(struct perf_tool *tool,
 					  union perf_event *event,
 					  struct machine *machine,
@@ -88,7 +114,7 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
 	int fd;
 	size_t size = 0;
 	ssize_t n;
-	char *nl, *name, *tgids, *ppids;
+	char *name, *tgids, *ppids;
 
 	*tgid = -1;
 	*ppid = -1;
@@ -115,10 +141,10 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
 	ppids = strstr(bf, "PPid:");
 
 	if (name) {
-		name += 5;  /* strlen("Name:") */
+		char *nl;
 
-		while (*name && isspace(*name))
-			++name;
+		name += 5;  /* strlen("Name:") */
+		name = ltrim(name);
 
 		nl = strchr(name, '\n');
 		if (nl)
@@ -203,6 +229,58 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	return tgid;
 }
 
+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+					 struct perf_ns_link_info *ns_link_info)
+{
+	struct stat64 st;
+	char proc_ns[128];
+
+	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+	if (stat64(proc_ns, &st) == 0) {
+		ns_link_info->dev = st.st_dev;
+		ns_link_info->ino = st.st_ino;
+	}
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	u32 idx;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!tool || !tool->namespace_events)
+		return 0;
+
+	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
+	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+	       machine->id_hdr_size));
+
+	event->namespaces.pid = tgid;
+	event->namespaces.tid = pid;
+
+	event->namespaces.nr_namespaces = NR_NAMESPACES;
+
+	ns_link_info = event->namespaces.link_info;
+
+	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
+		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
+					     &ns_link_info[idx]);
+
+	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+	event->namespaces.header.size = (sizeof(event->namespaces) +
+			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
 static int perf_event__synthesize_fork(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid, pid_t ppid,
@@ -255,8 +333,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	if (machine__is_default_guest(machine))
 		return 0;
 
-	snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
-		 machine->root_dir, pid);
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
+		 machine->root_dir, pid, pid);
 
 	fp = fopen(filename, "r");
 	if (fp == NULL) {
@@ -434,8 +512,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 static int __event__synthesize_thread(union perf_event *comm_event,
 				      union perf_event *mmap_event,
 				      union perf_event *fork_event,
+				      union perf_event *namespaces_event,
 				      pid_t pid, int full,
-					  perf_event__handler_t process,
+				      perf_event__handler_t process,
 				      struct perf_tool *tool,
 				      struct machine *machine,
 				      bool mmap_data,
@@ -455,6 +534,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (tgid == -1)
 			return -1;
 
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+						      tgid, process, machine) < 0)
+			return -1;
+
+
 		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
 							  process, machine, mmap_data,
 							  proc_map_timeout);
@@ -488,6 +572,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						ppid, process, machine) < 0)
 			break;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+						      tgid, process, machine) < 0)
+			break;
+
 		/*
 		 * Send the prepared comm event
 		 */
@@ -516,6 +605,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      unsigned int proc_map_timeout)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
 	int err = -1, thread, j;
 
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
@@ -530,10 +620,16 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
 	err = 0;
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
-					       fork_event,
+					       fork_event, namespaces_event,
 					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
 					       mmap_data, proc_map_timeout)) {
@@ -559,7 +655,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			/* if not, generate events for it */
 			if (need_leader &&
 			    __event__synthesize_thread(comm_event, mmap_event,
-						       fork_event,
+						       fork_event, namespaces_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
 						       mmap_data, proc_map_timeout)) {
@@ -568,6 +664,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			}
 		}
 	}
+	free(namespaces_event);
+out_free_fork:
 	free(fork_event);
 out_free_mmap:
 	free(mmap_event);
@@ -587,6 +685,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	char proc_path[PATH_MAX];
 	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
 	int err = -1;
 
 	if (machine__is_default_guest(machine))
@@ -604,11 +703,17 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
 	if (proc == NULL)
-		goto out_free_fork;
+		goto out_free_namespaces;
 
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
@@ -620,13 +725,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * We may race with exiting thread, so don't stop just because
  		 * one thread couldn't be synthesized.
  		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
-					   1, process, tool, machine, mmap_data,
+		__event__synthesize_thread(comm_event, mmap_event, fork_event,
+					   namespaces_event, pid, 1, process,
+					   tool, machine, mmap_data,
 					   proc_map_timeout);
 	}
 
 	err = 0;
 	closedir(proc);
+out_free_namespaces:
+	free(namespaces_event);
 out_free_fork:
 	free(fork_event);
 out_free_mmap:
@@ -1008,6 +1116,33 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 	return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
 }
 
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
+{
+	size_t ret = 0;
+	struct perf_ns_link_info *ns_link_info;
+	u32 nr_namespaces, idx;
+
+	ns_link_info = event->namespaces.link_info;
+	nr_namespaces = event->namespaces.nr_namespaces;
+
+	ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[",
+		       event->namespaces.pid,
+		       event->namespaces.tid,
+		       nr_namespaces);
+
+	for (idx = 0; idx < nr_namespaces; idx++) {
+		if (idx && (idx % 4 == 0))
+			ret += fprintf(fp, "\n\t\t ");
+
+		ret  += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx,
+				perf_ns__name(idx), (u64)ns_link_info[idx].dev,
+				(u64)ns_link_info[idx].ino,
+				((idx + 1) != nr_namespaces) ? ", " : "]\n");
+	}
+
+	return ret;
+}
+
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -1016,6 +1151,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 	return machine__process_comm_event(machine, event, sample);
 }
 
+int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	return machine__process_namespaces_event(machine, event, sample);
+}
+
 int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -1153,11 +1296,12 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
 		       event->aux.aux_offset, event->aux.aux_size,
 		       event->aux.flags,
 		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
-		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
+		       event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "");
 }
 
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
@@ -1196,6 +1340,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP:
 		ret += perf_event__fprintf_mmap(event, fp);
 		break;
+	case PERF_RECORD_NAMESPACES:
+		ret += perf_event__fprintf_namespaces(event, fp);
+		break;
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c735c53a26f8..db2de6413518 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -3,9 +3,9 @@
 
 #include <limits.h>
 #include <stdio.h>
+#include <linux/kernel.h>
 
 #include "../perf.h"
-#include "map.h"
 #include "build-id.h"
 #include "perf_regs.h"
 
@@ -39,6 +39,13 @@ struct comm_event {
 	char comm[16];
 };
 
+struct namespaces_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+	u64 nr_namespaces;
+	struct perf_ns_link_info link_info[];
+};
+
 struct fork_event {
 	struct perf_event_header header;
 	u32 pid, ppid;
@@ -269,6 +276,7 @@ struct events_stats {
 	u64 total_lost;
 	u64 total_lost_samples;
 	u64 total_aux_lost;
+	u64 total_aux_partial;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
@@ -485,6 +493,7 @@ union perf_event {
 	struct mmap_event		mmap;
 	struct mmap2_event		mmap2;
 	struct comm_event		comm;
+	struct namespaces_event		namespaces;
 	struct fork_event		fork;
 	struct lost_event		lost;
 	struct lost_samples_event	lost_samples;
@@ -587,6 +596,10 @@ int perf_event__process_switch(struct perf_tool *tool,
 			       union perf_event *event,
 			       struct perf_sample *sample,
 			       struct machine *machine);
+int perf_event__process_namespaces(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -636,6 +649,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 				  perf_event__handler_t process,
 				  struct machine *machine);
 
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine);
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -653,6 +672,7 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b601f2814a30..46c0faf6c502 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -8,6 +8,8 @@
  */
 #include "util.h"
 #include <api/fs/fs.h>
+#include <errno.h>
+#include <inttypes.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -15,12 +17,15 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
+#include "units.h"
 #include "asm/bug.h"
+#include <signal.h>
 #include <unistd.h>
 
 #include "parse-events.h"
 #include <subcmd/parse-options.h>
 
+#include <sys/ioctl.h>
 #include <sys/mman.h>
 
 #include <linux/bitops.h>
@@ -777,7 +782,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messu
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!atomic_read(&md->refcnt))
+	if (!refcount_read(&md->refcnt))
 		return NULL;
 
 	head = perf_mmap__read_head(md);
@@ -794,7 +799,7 @@ perf_mmap__read_backward(struct perf_mmap *md)
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!atomic_read(&md->refcnt))
+	if (!refcount_read(&md->refcnt))
 		return NULL;
 
 	head = perf_mmap__read_head(md);
@@ -856,7 +861,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md)
 {
 	u64 head;
 
-	if (!atomic_read(&md->refcnt))
+	if (!refcount_read(&md->refcnt))
 		return;
 
 	head = perf_mmap__read_head(md);
@@ -875,14 +880,14 @@ static bool perf_mmap__empty(struct perf_mmap *md)
 
 static void perf_mmap__get(struct perf_mmap *map)
 {
-	atomic_inc(&map->refcnt);
+	refcount_inc(&map->refcnt);
 }
 
 static void perf_mmap__put(struct perf_mmap *md)
 {
-	BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
+	BUG_ON(md->base && refcount_read(&md->refcnt) == 0);
 
-	if (atomic_dec_and_test(&md->refcnt))
+	if (refcount_dec_and_test(&md->refcnt))
 		perf_mmap__munmap(md);
 }
 
@@ -894,7 +899,7 @@ void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
 		perf_mmap__write_tail(md, old);
 	}
 
-	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
+	if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md))
 		perf_mmap__put(md);
 }
 
@@ -937,7 +942,7 @@ static void perf_mmap__munmap(struct perf_mmap *map)
 		munmap(map->base, perf_mmap__mmap_len(map));
 		map->base = NULL;
 		map->fd = -1;
-		atomic_set(&map->refcnt, 0);
+		refcount_set(&map->refcnt, 0);
 	}
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
@@ -974,8 +979,19 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	if (!map)
 		return NULL;
 
-	for (i = 0; i < evlist->nr_mmaps; i++)
+	for (i = 0; i < evlist->nr_mmaps; i++) {
 		map[i].fd = -1;
+		/*
+		 * When the perf_mmap() call is made we grab one refcount, plus
+		 * one extra to let perf_evlist__mmap_consume() get the last
+		 * events after all real references (perf_mmap__get()) are
+		 * dropped.
+		 *
+		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
+		 * thus does perf_mmap__get() on it.
+		 */
+		refcount_set(&map[i].refcnt, 0);
+	}
 	return map;
 }
 
@@ -1001,7 +1017,7 @@ static int perf_mmap__mmap(struct perf_mmap *map,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	atomic_set(&map->refcnt, 2);
+	refcount_set(&map->refcnt, 2);
 	map->prev = 0;
 	map->mask = mp->mask;
 	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 389b9ccdf8c7..94cea4398a13 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,7 +1,8 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
-#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
 #include <stdio.h>
@@ -10,6 +11,7 @@
 #include "evsel.h"
 #include "util.h"
 #include "auxtrace.h"
+#include <signal.h>
 #include <unistd.h>
 
 struct pollfd;
@@ -29,7 +31,7 @@ struct perf_mmap {
 	void		 *base;
 	int		 mask;
 	int		 fd;
-	atomic_t	 refcnt;
+	refcount_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ac59710b79e0..0e879097adfb 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -8,12 +8,15 @@
  */
 
 #include <byteswap.h>
+#include <errno.h>
+#include <inttypes.h>
 #include <linux/bitops.h>
 #include <api/fs/tracing_path.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
 #include <linux/err.h>
+#include <sys/ioctl.h>
 #include <sys/resource.h>
 #include "asm/bug.h"
 #include "callchain.h"
@@ -30,6 +33,8 @@
 #include "stat.h"
 #include "util/parse-branch-options.h"
 
+#include "sane_ctype.h"
+
 static struct {
 	bool sample_id_all;
 	bool exclude_guest;
@@ -236,6 +241,10 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 	perf_evsel__calc_id_pos(evsel);
 	evsel->cmdline_group_boundary = false;
+	evsel->metric_expr   = NULL;
+	evsel->metric_name   = NULL;
+	evsel->metric_events = NULL;
+	evsel->collect_stat  = false;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
@@ -932,6 +941,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
+	if (opts->record_namespaces)
+		attr->namespaces  = track;
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
@@ -1232,7 +1244,7 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
+	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0)
 		return -errno;
 
 	return 0;
@@ -1250,7 +1262,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
 		return -ENOMEM;
 
-	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
+	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
 		return -errno;
 
 	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
@@ -2450,11 +2462,17 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {
 	char sbuf[STRERR_BUFSIZE];
+	int printed = 0;
 
 	switch (err) {
 	case EPERM:
 	case EACCES:
-		return scnprintf(msg, size,
+		if (err == EPERM)
+			printed = scnprintf(msg, size,
+				"No permission to enable %s event.\n\n",
+				perf_evsel__name(evsel));
+
+		return scnprintf(msg + printed, size - printed,
 		 "You may not have permission to collect %sstats.\n\n"
 		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
 		 "which controls use of the performance events system by\n"
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 06ef6f29efa1..d101695c482c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -131,6 +131,11 @@ struct perf_evsel {
 	bool			cmdline_group_boundary;
 	struct list_head	config_terms;
 	int			bpf_fd;
+	bool			merged_stat;
+	const char *		metric_expr;
+	const char *		metric_name;
+	struct perf_evsel	**metric_events;
+	bool			collect_stat;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 4ef5184819a0..e415aee6a245 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -1,9 +1,11 @@
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <traceevent/event-parse.h>
 #include "evsel.h"
 #include "callchain.h"
 #include "map.h"
+#include "strlist.h"
 #include "symbol.h"
 
 static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
new file mode 100644
index 000000000000..9c2760a1a96e
--- /dev/null
+++ b/tools/perf/util/expr.h
@@ -0,0 +1,25 @@
+#ifndef PARSE_CTX_H
+#define PARSE_CTX_H 1
+
+#define EXPR_MAX_OTHER 8
+#define MAX_PARSE_ID EXPR_MAX_OTHER
+
+struct parse_id {
+	const char *name;
+	double val;
+};
+
+struct parse_ctx {
+	int num_ids;
+	struct parse_id ids[MAX_PARSE_ID];
+};
+
+void expr__ctx_init(struct parse_ctx *ctx);
+void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
+#ifndef IN_EXPR_Y
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp);
+#endif
+int expr__find_other(const char *p, const char *one, const char ***other,
+		int *num_other);
+
+#endif
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
new file mode 100644
index 000000000000..954556bea36e
--- /dev/null
+++ b/tools/perf/util/expr.y
@@ -0,0 +1,173 @@
+/* Simple expression parser */
+%{
+#include "util.h"
+#include "util/debug.h"
+#define IN_EXPR_Y 1
+#include "expr.h"
+#include <string.h>
+
+#define MAXIDLEN 256
+%}
+
+%pure-parser
+%parse-param { double *final_val }
+%parse-param { struct parse_ctx *ctx }
+%parse-param { const char **pp }
+%lex-param { const char **pp }
+
+%union {
+	double num;
+	char id[MAXIDLEN+1];
+}
+
+%token <num> NUMBER
+%token <id> ID
+%left '|'
+%left '^'
+%left '&'
+%left '-' '+'
+%left '*' '/' '%'
+%left NEG NOT
+%type <num> expr
+
+%{
+static int expr__lex(YYSTYPE *res, const char **pp);
+
+static void expr__error(double *final_val __maybe_unused,
+		       struct parse_ctx *ctx __maybe_unused,
+		       const char **pp __maybe_unused,
+		       const char *s)
+{
+	pr_debug("%s\n", s);
+}
+
+static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
+{
+	int i;
+
+	for (i = 0; i < ctx->num_ids; i++) {
+		if (!strcasecmp(ctx->ids[i].name, id)) {
+			*val = ctx->ids[i].val;
+			return 0;
+		}
+	}
+	return -1;
+}
+
+%}
+%%
+
+all_expr: expr			{ *final_val = $1; }
+	;
+
+expr:	  NUMBER
+	| ID			{ if (lookup_id(ctx, $1, &$$) < 0) {
+					pr_debug("%s not found", $1);
+					YYABORT;
+				  }
+				}
+	| expr '+' expr		{ $$ = $1 + $3; }
+	| expr '-' expr		{ $$ = $1 - $3; }
+	| expr '*' expr		{ $$ = $1 * $3; }
+	| expr '/' expr		{ if ($3 == 0) YYABORT; $$ = $1 / $3; }
+	| expr '%' expr		{ if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; }
+	| '-' expr %prec NEG	{ $$ = -$2; }
+	| '(' expr ')'		{ $$ = $2; }
+	;
+
+%%
+
+static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
+{
+	char *dst = res->id;
+	const char *s = p;
+
+	while (isalnum(*p) || *p == '_' || *p == '.') {
+		if (p - s >= MAXIDLEN)
+			return -1;
+		*dst++ = *p++;
+	}
+	*dst = 0;
+	*pp = p;
+	return ID;
+}
+
+static int expr__lex(YYSTYPE *res, const char **pp)
+{
+	int tok;
+	const char *s;
+	const char *p = *pp;
+
+	while (isspace(*p))
+		p++;
+	s = p;
+	switch (*p++) {
+	case 'a' ... 'z':
+	case 'A' ... 'Z':
+		return expr__symbol(res, p - 1, pp);
+	case '0' ... '9': case '.':
+		res->num = strtod(s, (char **)&p);
+		tok = NUMBER;
+		break;
+	default:
+		tok = *s;
+		break;
+	}
+	*pp = p;
+	return tok;
+}
+
+/* Caller must make sure id is allocated */
+void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+{
+	int idx;
+	assert(ctx->num_ids < MAX_PARSE_ID);
+	idx = ctx->num_ids++;
+	ctx->ids[idx].name = name;
+	ctx->ids[idx].val = val;
+}
+
+void expr__ctx_init(struct parse_ctx *ctx)
+{
+	ctx->num_ids = 0;
+}
+
+int expr__find_other(const char *p, const char *one, const char ***other,
+		     int *num_otherp)
+{
+	const char *orig = p;
+	int err = -1;
+	int num_other;
+
+	*other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *));
+	if (!*other)
+		return -1;
+
+	num_other = 0;
+	for (;;) {
+		YYSTYPE val;
+		int tok = expr__lex(&val, &p);
+		if (tok == 0) {
+			err = 0;
+			break;
+		}
+		if (tok == ID && strcasecmp(one, val.id)) {
+			if (num_other >= EXPR_MAX_OTHER - 1) {
+				pr_debug("Too many extra events in %s\n", orig);
+				break;
+			}
+			(*other)[num_other] = strdup(val.id);
+			if (!(*other)[num_other])
+				return -1;
+			num_other++;
+		}
+	}
+	(*other)[num_other] = NULL;
+	*num_otherp = num_other;
+	if (err) {
+		*num_otherp = 0;
+		free(*other);
+		*other = NULL;
+	}
+	return err;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 05714d548584..948b2c5efb65 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,4 +1,8 @@
+#include <errno.h>
+#include <inttypes.h>
 #include "util.h"
+#include "string2.h"
+#include <sys/param.h>
 #include <sys/types.h>
 #include <byteswap.h>
 #include <unistd.h>
@@ -7,7 +11,10 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <sys/stat.h>
+#include <sys/types.h>
 #include <sys/utsname.h>
+#include <unistd.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -26,6 +33,8 @@
 #include <api/fs/fs.h>
 #include "asm/bug.h"
 
+#include "sane_ctype.h"
+
 /*
  * magic2 = "PERFILE2"
  * must be a numerical value to let the endianness
@@ -370,15 +379,11 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 			 struct perf_evlist *evlist __maybe_unused)
 {
 	char buf[MAXPATHLEN];
-	char proc[32];
 	u32 n;
 	int i, ret;
 
-	/*
-	 * actual atual path to perf binary
-	 */
-	sprintf(proc, "/proc/%d/exe", getpid());
-	ret = readlink(proc, buf, sizeof(buf));
+	/* actual path to perf binary */
+	ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
 	if (ret <= 0)
 		return -1;
 
@@ -2274,6 +2279,9 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	perf_header__process_sections(header, fd, &hd,
 				      perf_file_section__fprintf_info);
 
+	if (session->file->is_pipe)
+		return 0;
+
 	fprintf(fp, "# missing features: ");
 	for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) {
 		if (bit)
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 2821f8d77e52..1c88ad6425b8 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -1,21 +1,18 @@
 #include "cache.h"
 #include "config.h"
+#include <poll.h>
 #include <stdio.h>
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"
 
 static int autocorrect;
-static struct cmdnames aliases;
 
 static int perf_unknown_cmd_config(const char *var, const char *value,
 				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
 		autocorrect = perf_config_int(var,value);
-	/* Also use aliases for command lookup */
-	if (!prefixcmp(var, "alias."))
-		add_cmdname(&aliases, var + 6, strlen(var + 6));
 
 	return 0;
 }
@@ -59,14 +56,12 @@ const char *help_unknown_cmd(const char *cmd)
 
 	memset(&main_cmds, 0, sizeof(main_cmds));
 	memset(&other_cmds, 0, sizeof(main_cmds));
-	memset(&aliases, 0, sizeof(aliases));
 
 	perf_config(perf_unknown_cmd_config, NULL);
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
 
-	if (add_cmd_list(&main_cmds, &aliases) < 0 ||
-	    add_cmd_list(&main_cmds, &other_cmds) < 0) {
+	if (add_cmd_list(&main_cmds, &other_cmds) < 0) {
 		fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n");
 		goto end;
 	}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index eaf72a938fb4..cf0186a088c1 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,12 +3,17 @@
 #include "hist.h"
 #include "map.h"
 #include "session.h"
+#include "namespaces.h"
 #include "sort.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
+#include "srcline.h"
+#include "thread.h"
 #include "ui/progress.h"
+#include <errno.h>
 #include <math.h>
+#include <sys/param.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he);
@@ -169,6 +174,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
 	}
 
+	hists__new_col_len(hists, HISTC_CGROUP_ID, 20);
 	hists__new_col_len(hists, HISTC_CPU, 3);
 	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
@@ -574,9 +580,14 @@ __hists__add_entry(struct hists *hists,
 		   bool sample_self,
 		   struct hist_entry_ops *ops)
 {
+	struct namespaces *ns = thread__namespaces(al->thread);
 	struct hist_entry entry = {
 		.thread	= al->thread,
 		.comm = thread__comm(al->thread),
+		.cgroup_id = {
+			.dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0,
+			.ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0,
+		},
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,
@@ -1129,6 +1140,11 @@ void hist_entry__delete(struct hist_entry *he)
 		zfree(&he->mem_info);
 	}
 
+	if (he->inline_node) {
+		inline_node__delete(he->inline_node);
+		he->inline_node = NULL;
+	}
+
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	if (he->srcfile && he->srcfile[0])
@@ -2447,7 +2463,7 @@ int parse_filter_percentage(const struct option *opt __maybe_unused,
 	else if (!strcmp(arg, "absolute"))
 		symbol_conf.filter_relative = false;
 	else {
-		pr_debug("Invalud percentage: %s\n", arg);
+		pr_debug("Invalid percentage: %s\n", arg);
 		return -1;
 	}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 28c216e3d5b7..ee3670a388df 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -30,6 +30,7 @@ enum hist_column {
 	HISTC_DSO,
 	HISTC_THREAD,
 	HISTC_COMM,
+	HISTC_CGROUP_ID,
 	HISTC_PARENT,
 	HISTC_CPU,
 	HISTC_SOCKET,
@@ -57,6 +58,7 @@ enum hist_column {
 	HISTC_SRCLINE_FROM,
 	HISTC_SRCLINE_TO,
 	HISTC_TRACE,
+	HISTC_SYM_SIZE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 6c2eb5da4afc..b2834ac7b1f5 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -14,7 +14,9 @@
  */
 
 #include <endian.h>
+#include <errno.h>
 #include <byteswap.h>
+#include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 7913363bde5c..54818828023b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -26,12 +26,13 @@
 #include "insn.c"
 
 #include "intel-pt-insn-decoder.h"
+#include "dump-insn.h"
 
 #if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN
 #error Instruction buffer size too small
 #endif
 
-/* Based on branch_type() from perf_event_intel_lbr.c */
+/* Based on branch_type() from arch/x86/events/intel/lbr.c */
 static void intel_pt_insn_decoder(struct insn *insn,
 				  struct intel_pt_insn *intel_pt_insn)
 {
@@ -39,6 +40,8 @@ static void intel_pt_insn_decoder(struct insn *insn,
 	enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
 	int ext;
 
+	intel_pt_insn->rel = 0;
+
 	if (insn_is_avx(insn)) {
 		intel_pt_insn->op = INTEL_PT_OP_OTHER;
 		intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
@@ -177,6 +180,29 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
 	return 0;
 }
 
+const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
+		      u8 *inbuf, int inlen, int *lenp)
+{
+	struct insn insn;
+	int n, i;
+	int left;
+
+	insn_init(&insn, inbuf, inlen, x->is64bit);
+	insn_get_length(&insn);
+	if (!insn_complete(&insn) || insn.length > inlen)
+		return "<bad>";
+	if (lenp)
+		*lenp = insn.length;
+	left = sizeof(x->out);
+	n = snprintf(x->out, left, "insn: ");
+	left -= n;
+	for (i = 0; i < insn.length; i++) {
+		n += snprintf(x->out + n, left, "%02x ", inbuf[i]);
+		left -= n;
+	}
+	return x->out;
+}
+
 const char *branch_name[] = {
 	[INTEL_PT_OP_OTHER]	= "Other",
 	[INTEL_PT_OP_CALL]	= "Call",
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index da20cd5612e9..bdd4a28c6cee 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <errno.h>
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index c9a941ef0f6d..9084930e1757 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -1,5 +1,6 @@
 #include <sys/sysmacros.h>
 #include <sys/types.h>
+#include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -9,13 +10,13 @@
 #include <byteswap.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
+#include <linux/stringify.h>
 
 #include "util.h"
 #include "event.h"
 #include "debug.h"
 #include "evlist.h"
 #include "symbol.h"
-#include "strlist.h"
 #include <elf.h>
 
 #include "tsc.h"
@@ -25,6 +26,8 @@
 #include "genelf.h"
 #include "../builtin.h"
 
+#include "sane_ctype.h"
+
 struct jit_buf_desc {
 	struct perf_data_file *output;
 	struct perf_session *session;
@@ -181,7 +184,7 @@ jit_open(struct jit_buf_desc *jd, const char *name)
 			jd->use_arch_timestamp);
 
 	if (header.version > JITHEADER_VERSION) {
-		pr_err("wrong jitdump version %u, expected " STR(JITHEADER_VERSION),
+		pr_err("wrong jitdump version %u, expected " __stringify(JITHEADER_VERSION),
 			header.version);
 		goto error;
 	}
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 824356488ce6..c6a15f204c03 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -12,6 +12,7 @@
 #include "llvm-utils.h"
 #include "config.h"
 #include "util.h"
+#include <sys/wait.h>
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 9ddea5cecd94..4ca7c5c6cdcd 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -1,6 +1,8 @@
+#include <errno.h>
 #include <lzma.h>
 #include <stdio.h>
 #include <linux/compiler.h>
+#include "compress.h"
 #include "util.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 71c9720d4973..7a47f52ccfcc 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1,3 +1,7 @@
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <regex.h>
 #include "callchain.h"
 #include "debug.h"
 #include "event.h"
@@ -10,9 +14,15 @@
 #include "thread.h"
 #include "vdso.h"
 #include <stdbool.h>
-#include <symbol/kallsyms.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "unwind.h"
 #include "linux/hash.h"
+#include "asm/bug.h"
+
+#include "sane_ctype.h"
+#include <symbol/kallsyms.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -501,6 +511,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	return err;
 }
 
+int machine__process_namespaces_event(struct machine *machine __maybe_unused,
+				      union perf_event *event,
+				      struct perf_sample *sample __maybe_unused)
+{
+	struct thread *thread = machine__findnew_thread(machine,
+							event->namespaces.pid,
+							event->namespaces.tid);
+	int err = 0;
+
+	WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES,
+		  "\nWARNING: kernel seems to support more namespaces than perf"
+		  " tool.\nTry updating the perf tool..\n\n");
+
+	WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES,
+		  "\nWARNING: perf tool seems to support more namespaces than"
+		  " the kernel.\nTry updating the kernel..\n\n");
+
+	if (dump_trace)
+		perf_event__fprintf_namespaces(event, stdout);
+
+	if (thread == NULL ||
+	    thread__set_namespaces(thread, sample->time, &event->namespaces)) {
+		dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n");
+		err = -1;
+	}
+
+	thread__put(thread);
+
+	return err;
+}
+
 int machine__process_lost_event(struct machine *machine __maybe_unused,
 				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
@@ -1439,7 +1480,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	if (machine->last_match == th)
 		machine->last_match = NULL;
 
-	BUG_ON(atomic_read(&th->refcnt) == 0);
+	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
 		pthread_rwlock_wrlock(&machine->threads_lock);
 	rb_erase_init(&th->rb_node, &machine->threads);
@@ -1538,6 +1579,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_comm_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP:
 		ret = machine__process_mmap_event(machine, event, sample); break;
+	case PERF_RECORD_NAMESPACES:
+		ret = machine__process_namespaces_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP2:
 		ret = machine__process_mmap2_event(machine, event, sample); break;
 	case PERF_RECORD_FORK:
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a28305029711..3cdb1340f917 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
 int machine__process_switch_event(struct machine *machine,
 				  union perf_event *event);
+int machine__process_namespaces_event(struct machine *machine,
+				      union perf_event *event,
+				      struct perf_sample *sample);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 0a943e7b1ea7..ebfa5d92358a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -9,13 +9,13 @@
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include "map.h"
 #include "thread.h"
-#include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
 #include "util.h"
 #include "debug.h"
 #include "machine.h"
 #include <linux/string.h>
+#include "srcline.h"
 #include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
@@ -141,7 +141,7 @@ void map__init(struct map *map, enum map_type type,
 	RB_CLEAR_NODE(&map->rb_node);
 	map->groups   = NULL;
 	map->erange_warned = false;
-	atomic_set(&map->refcnt, 1);
+	refcount_set(&map->refcnt, 1);
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -255,7 +255,7 @@ void map__delete(struct map *map)
 
 void map__put(struct map *map)
 {
-	if (map && atomic_dec_and_test(&map->refcnt))
+	if (map && refcount_dec_and_test(&map->refcnt))
 		map__delete(map);
 }
 
@@ -354,7 +354,7 @@ struct map *map__clone(struct map *from)
 	struct map *map = memdup(from, sizeof(*map));
 
 	if (map != NULL) {
-		atomic_set(&map->refcnt, 1);
+		refcount_set(&map->refcnt, 1);
 		RB_CLEAR_NODE(&map->rb_node);
 		dso__get(map->dso);
 		map->groups = NULL;
@@ -405,7 +405,8 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
 	if (map && map->dso) {
 		srcline = get_srcline(map->dso,
-				      map__rip_2objdump(map, addr), NULL, true);
+				      map__rip_2objdump(map, addr), NULL,
+				      true, true);
 		if (srcline != SRCLINE_UNKNOWN)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);
@@ -485,7 +486,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine)
 		maps__init(&mg->maps[i]);
 	}
 	mg->machine = machine;
-	atomic_set(&mg->refcnt, 1);
+	refcount_set(&mg->refcnt, 1);
 }
 
 static void __maps__purge(struct maps *maps)
@@ -547,7 +548,7 @@ void map_groups__delete(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg)
 {
-	if (mg && atomic_dec_and_test(&mg->refcnt))
+	if (mg && refcount_dec_and_test(&mg->refcnt))
 		map_groups__delete(mg);
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index abdacf800c98..c8a5a644c0a9 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
@@ -51,7 +51,7 @@ struct map {
 
 	struct dso		*dso;
 	struct map_groups	*groups;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 };
 
 struct kmap {
@@ -67,7 +67,7 @@ struct maps {
 struct map_groups {
 	struct maps	 maps[MAP__NR_TYPES];
 	struct machine	 *machine;
-	atomic_t	 refcnt;
+	refcount_t	 refcnt;
 };
 
 struct map_groups *map_groups__new(struct machine *machine);
@@ -77,7 +77,7 @@ bool map_groups__empty(struct map_groups *mg);
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
 	if (mg)
-		atomic_inc(&mg->refcnt);
+		refcount_inc(&mg->refcnt);
 	return mg;
 }
 
@@ -150,7 +150,7 @@ struct map *map__clone(struct map *map);
 static inline struct map *map__get(struct map *map)
 {
 	if (map)
-		atomic_inc(&map->refcnt);
+		refcount_inc(&map->refcnt);
 	return map;
 }
 
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 1d4ab53c60ca..06f5a3a4295c 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -6,6 +6,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <api/fs/fs.h>
+#include <linux/kernel.h>
 #include "mem-events.h"
 #include "debug.h"
 #include "symbol.h"
@@ -205,8 +206,8 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 static const char * const snoop_access[] = {
 	"N/A",
 	"None",
-	"Miss",
 	"Hit",
+	"Miss",
 	"HitM",
 };
 
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
new file mode 100644
index 000000000000..67dcbcc73c7d
--- /dev/null
+++ b/tools/perf/util/namespaces.c
@@ -0,0 +1,37 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#include "namespaces.h"
+#include "util.h"
+#include "event.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+struct namespaces *namespaces__new(struct namespaces_event *event)
+{
+	struct namespaces *namespaces;
+	u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
+			      sizeof(struct perf_ns_link_info));
+
+	namespaces = zalloc(sizeof(struct namespaces) + link_info_size);
+	if (!namespaces)
+		return NULL;
+
+	namespaces->end_time = -1;
+
+	if (event)
+		memcpy(namespaces->link_info, event->link_info, link_info_size);
+
+	return namespaces;
+}
+
+void namespaces__free(struct namespaces *namespaces)
+{
+	free(namespaces);
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
new file mode 100644
index 000000000000..468f1e9a1484
--- /dev/null
+++ b/tools/perf/util/namespaces.h
@@ -0,0 +1,26 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#ifndef __PERF_NAMESPACES_H
+#define __PERF_NAMESPACES_H
+
+#include "../perf.h"
+#include <linux/list.h>
+
+struct namespaces_event;
+
+struct namespaces {
+	struct list_head list;
+	u64 end_time;
+	struct perf_ns_link_info link_info[];
+};
+
+struct namespaces *namespaces__new(struct namespaces_event *event);
+void namespaces__free(struct namespaces *namespaces);
+
+#endif  /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index fe84df1875aa..4de398cfb577 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 #include <linux/list.h>
 #include <linux/compiler.h>
 #include <linux/string.h>
@@ -79,7 +81,7 @@ static union perf_event *dup_event(struct ordered_events *oe,
 
 static void free_dup_event(struct ordered_events *oe, union perf_event *event)
 {
-	if (oe->copy_on_queue) {
+	if (event && oe->copy_on_queue) {
 		oe->cur_alloc_size -= event->header.size;
 		free(event);
 	}
@@ -150,6 +152,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 	list_move(&event->list, &oe->cache);
 	oe->nr_events--;
 	free_dup_event(oe, event->event);
+	event->event = NULL;
 }
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 67a8aebc67ab..01e779b91c8e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,13 +1,18 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/err.h>
-#include "util.h"
+#include <dirent.h>
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <sys/param.h>
+#include "term.h"
 #include "../perf.h"
 #include "evlist.h"
 #include "evsel.h"
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include <subcmd/exec-cmd.h>
-#include "string.h"
+#include "string2.h"
+#include "strlist.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
@@ -316,8 +321,9 @@ __add_event(struct list_head *list, int *idx,
 		return NULL;
 
 	(*idx)++;
-	evsel->cpus     = cpu_map__get(cpus);
-	evsel->own_cpus = cpu_map__get(cpus);
+	evsel->cpus        = cpu_map__get(cpus);
+	evsel->own_cpus    = cpu_map__get(cpus);
+	evsel->system_wide = !!cpus;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -1254,11 +1260,59 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		evsel->scale = info.scale;
 		evsel->per_pkg = info.per_pkg;
 		evsel->snapshot = info.snapshot;
+		evsel->metric_expr = info.metric_expr;
+		evsel->metric_name = info.metric_name;
 	}
 
 	return evsel ? 0 : -ENOMEM;
 }
 
+int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+			       char *str, struct list_head **listp)
+{
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+	struct perf_pmu *pmu = NULL;
+	int ok = 0;
+
+	*listp = NULL;
+	/* Add it for all PMUs that support the alias */
+	list = malloc(sizeof(struct list_head));
+	if (!list)
+		return -1;
+	INIT_LIST_HEAD(list);
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		struct perf_pmu_alias *alias;
+
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			if (!strcasecmp(alias->name, str)) {
+				head = malloc(sizeof(struct list_head));
+				if (!head)
+					return -1;
+				INIT_LIST_HEAD(head);
+				if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+							   str, 1, false, &str, NULL) < 0)
+					return -1;
+				list_add_tail(&term->list, head);
+
+				if (!parse_events_add_pmu(data, list,
+						  pmu->name, head)) {
+					pr_debug("%s -> %s/%s/\n", str,
+						 pmu->name, alias->str);
+					ok++;
+				}
+
+				parse_events_terms__delete(head);
+			}
+		}
+	}
+	if (!ok)
+		return -1;
+	*listp = list;
+	return 0;
+}
+
 int parse_events__modifier_group(struct list_head *list,
 				 char *event_mod)
 {
@@ -2276,7 +2330,7 @@ out_enomem:
  * Print the help text for the event symbols:
  */
 void print_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc)
+			bool long_desc, bool details_flag)
 {
 	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
 			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
@@ -2286,7 +2340,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_hwcache_events(event_glob, name_only);
 
-	print_pmu_events(event_glob, name_only, quiet_flag, long_desc);
+	print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
+			details_flag);
 
 	if (event_glob != NULL)
 		return;
@@ -2415,6 +2470,31 @@ int parse_events_term__clone(struct parse_events_term **new,
 	return new_term(new, &temp, term->val.str, term->val.num);
 }
 
+int parse_events_copy_term_list(struct list_head *old,
+				 struct list_head **new)
+{
+	struct parse_events_term *term, *n;
+	int ret;
+
+	if (!old) {
+		*new = NULL;
+		return 0;
+	}
+
+	*new = malloc(sizeof(struct list_head));
+	if (!*new)
+		return -ENOMEM;
+	INIT_LIST_HEAD(*new);
+
+	list_for_each_entry (term, old, list) {
+		ret = parse_events_term__clone(&n, term);
+		if (ret)
+			return ret;
+		list_add_tail(&n->list, *new);
+	}
+	return 0;
+}
+
 void parse_events_terms__purge(struct list_head *terms)
 {
 	struct parse_events_term *term, *h;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 1af6a267c21b..a235f4d6d5e5 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -8,6 +8,7 @@
 #include <stdbool.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <string.h>
 
 struct list_head;
 struct perf_evsel;
@@ -166,6 +167,14 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 int parse_events_add_pmu(struct parse_events_evlist *data,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config);
+
+int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+			       char *str,
+			       struct list_head **listp);
+
+int parse_events_copy_term_list(struct list_head *old,
+				 struct list_head **new);
+
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
@@ -175,7 +184,7 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only, bool quiet,
-		  bool long_desc);
+		  bool long_desc, bool details_flag);
 
 struct event_symbol {
 	const char	*symbol;
@@ -196,4 +205,23 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+#ifdef HAVE_LIBELF_SUPPORT
+/*
+ * If the probe point starts with '%',
+ * or starts with "sdt_" and has a ':' but no '=',
+ * then it should be a SDT/cached probe point.
+ */
+static inline bool is_sdt_event(char *str)
+{
+	return (str[0] == '%' ||
+		(!strncmp(str, "sdt_", 4) &&
+		 !!strchr(str, ':') && !strchr(str, '=')));
+}
+#else
+static inline bool is_sdt_event(char *str __maybe_unused)
+{
+	return false;
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 30f018ea1370..04fd8c9af9f9 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -226,68 +226,55 @@ event_pmu:
 PE_NAME opt_event_config
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list;
+	struct list_head *list, *orig_terms, *terms;
+
+	if (parse_events_copy_term_list($2, &orig_terms))
+		YYABORT;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+	if (parse_events_add_pmu(data, list, $1, $2)) {
+		struct perf_pmu *pmu = NULL;
+		int ok = 0;
+
+		while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+			char *name = pmu->name;
+
+			if (!strncmp(name, "uncore_", 7) &&
+			    strncmp($1, "uncore_", 7))
+				name += 7;
+			if (!strncmp($1, name, strlen($1))) {
+				if (parse_events_copy_term_list(orig_terms, &terms))
+					YYABORT;
+				if (!parse_events_add_pmu(data, list, pmu->name, terms))
+					ok++;
+				parse_events_terms__delete(terms);
+			}
+		}
+		if (!ok)
+			YYABORT;
+	}
 	parse_events_terms__delete($2);
+	parse_events_terms__delete(orig_terms);
 	$$ = list;
 }
 |
 PE_KERNEL_PMU_EVENT sep_dc
 {
-	struct parse_events_evlist *data = _data;
-	struct list_head *head;
-	struct parse_events_term *term;
 	struct list_head *list;
-	struct perf_pmu *pmu = NULL;
-	int ok = 0;
-
-	/* Add it for all PMUs that support the alias */
-	ALLOC_LIST(list);
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		struct perf_pmu_alias *alias;
-
-		list_for_each_entry(alias, &pmu->aliases, list) {
-			if (!strcasecmp(alias->name, $1)) {
-				ALLOC_LIST(head);
-				ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, false, &@1, NULL));
-				list_add_tail(&term->list, head);
-
-				if (!parse_events_add_pmu(data, list,
-						  pmu->name, head)) {
-					pr_debug("%s -> %s/%s/\n", $1,
-						 pmu->name, alias->str);
-					ok++;
-				}
 
-				parse_events_terms__delete(head);
-			}
-		}
-	}
-	if (!ok)
+	if (parse_events_multi_pmu_add(_data, $1, &list) < 0)
 		YYABORT;
 	$$ = list;
 }
 |
 PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 {
-	struct parse_events_evlist *data = _data;
-	struct list_head *head;
-	struct parse_events_term *term;
 	struct list_head *list;
 	char pmu_name[128];
-	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
 
-	ALLOC_LIST(head);
-	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					&pmu_name, 1, false, &@1, NULL));
-	list_add_tail(&term->list, head);
-
-	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events_terms__delete(head);
+	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+	if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0)
+		YYABORT;
 	$$ = list;
 }
 
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 7c7630be5a89..50ec3bc87a60 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -11,8 +11,13 @@
  * which is what it's designed for.
  */
 #include "cache.h"
-#include "util.h"
+#include "path.h"
+#include <linux/kernel.h>
 #include <limits.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 
 static char bad_path[] = "/bad-path/";
 /*
@@ -50,3 +55,24 @@ char *mkpath(const char *fmt, ...)
 		return bad_path;
 	return cleanup_path(pathname);
 }
+
+int path__join(char *bf, size_t size, const char *path1, const char *path2)
+{
+	return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3)
+{
+	return scnprintf(bf, size, "%s%s%s%s%s", path1, path1[0] ? "/" : "",
+			 path2, path2[0] ? "/" : "", path3);
+}
+
+bool is_regular_file(const char *file)
+{
+	struct stat st;
+
+	if (stat(file, &st))
+		return false;
+
+	return S_ISREG(st.st_mode);
+}
diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h
new file mode 100644
index 000000000000..9a276a58e3c2
--- /dev/null
+++ b/tools/perf/util/path.h
@@ -0,0 +1,9 @@
+#ifndef _PERF_PATH_H
+#define _PERF_PATH_H
+
+int path__join(char *bf, size_t size, const char *path1, const char *path2);
+int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3);
+
+bool is_regular_file(const char *file);
+
+#endif /* _PERF_PATH_H */
diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c
index cb368306b12b..d55092964da2 100644
--- a/tools/perf/util/perf-hooks.c
+++ b/tools/perf/util/perf-hooks.c
@@ -9,6 +9,7 @@
 #include <stdlib.h>
 #include <setjmp.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include "util/util.h"
 #include "util/debug.h"
 #include "util/perf-hooks.h"
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index c4023f22f287..b2ae039eff85 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -6,6 +6,12 @@ const struct sample_reg __weak sample_reg_masks[] = {
 	SMPL_REG_END
 };
 
+int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
+				 char **new_op __maybe_unused)
+{
+	return SDT_ARG_SKIP;
+}
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 679d6e493962..32b37d19dcc3 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -15,6 +15,13 @@ struct sample_reg {
 
 extern const struct sample_reg sample_reg_masks[];
 
+enum {
+	SDT_ARG_VALID = 0,
+	SDT_ARG_SKIP,
+};
+
+int arch_sdt_arg_parse_op(char *old_op, char **new_op);
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 12f84dd2ac5d..ac16a9db1fb5 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,6 +1,8 @@
 #include <linux/list.h>
 #include <linux/compiler.h>
 #include <sys/types.h>
+#include <errno.h>
+#include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdbool.h>
@@ -15,6 +17,7 @@
 #include "header.h"
 #include "pmu-events/pmu-events.h"
 #include "cache.h"
+#include "string2.h"
 
 struct perf_pmu_format {
 	char *name;
@@ -231,7 +234,9 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
-				 char *unit, char *perpkg)
+				 char *unit, char *perpkg,
+				 char *metric_expr,
+				 char *metric_name)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
@@ -265,6 +270,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		perf_pmu__parse_snapshot(alias, dir, name);
 	}
 
+	alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL;
+	alias->metric_name = metric_name ? strdup(metric_name): NULL;
 	alias->desc = desc ? strdup(desc) : NULL;
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
@@ -294,7 +301,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	buf[ret] = 0;
 
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
-				     NULL);
+				     NULL, NULL, NULL);
 }
 
 static inline bool pmu_alias_info_file(char *name)
@@ -564,7 +571,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
 				(char *)pe->long_desc, (char *)pe->topic,
-				(char *)pe->unit, (char *)pe->perpkg);
+				(char *)pe->unit, (char *)pe->perpkg,
+				(char *)pe->metric_expr,
+				(char *)pe->metric_name);
 	}
 
 out:
@@ -991,6 +1000,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	info->unit     = NULL;
 	info->scale    = 0.0;
 	info->snapshot = false;
+	info->metric_expr = NULL;
+	info->metric_name = NULL;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -1006,6 +1017,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 
 		if (alias->per_pkg)
 			info->per_pkg = true;
+		info->metric_expr = alias->metric_expr;
+		info->metric_name = alias->metric_name;
 
 		list_del(&term->list);
 		free(term);
@@ -1100,6 +1113,8 @@ struct sevent {
 	char *topic;
 	char *str;
 	char *pmu;
+	char *metric_expr;
+	char *metric_name;
 };
 
 static int cmp_sevent(const void *a, const void *b)
@@ -1136,13 +1151,12 @@ static void wordwrap(char *s, int start, int max, int corr)
 			break;
 		s += wlen;
 		column += n;
-		while (isspace(*s))
-			s++;
+		s = ltrim(s);
 	}
 }
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc)
+			bool long_desc, bool details_flag)
 {
 	struct perf_pmu *pmu;
 	struct perf_pmu_alias *alias;
@@ -1198,6 +1212,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			aliases[j].topic = alias->topic;
 			aliases[j].str = alias->str;
 			aliases[j].pmu = pmu->name;
+			aliases[j].metric_expr = alias->metric_expr;
+			aliases[j].metric_name = alias->metric_name;
 			j++;
 		}
 		if (pmu->selectable &&
@@ -1232,8 +1248,14 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			printf("%*s", 8, "[");
 			wordwrap(aliases[j].desc, 8, columns, 0);
 			printf("]\n");
-			if (verbose > 0)
-				printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
+			if (details_flag) {
+				printf("%*s%s/%s/ ", 8, "", aliases[j].pmu, aliases[j].str);
+				if (aliases[j].metric_name)
+					printf(" MetricName: %s", aliases[j].metric_name);
+				if (aliases[j].metric_expr)
+					printf(" MetricExpr: %s", aliases[j].metric_expr);
+				putchar('\n');
+			}
 		} else
 			printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
 		printed++;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 00852ddc7741..ea7f450dc609 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -31,6 +31,8 @@ struct perf_pmu {
 
 struct perf_pmu_info {
 	const char *unit;
+	const char *metric_expr;
+	const char *metric_name;
 	double scale;
 	bool per_pkg;
 	bool snapshot;
@@ -50,6 +52,8 @@ struct perf_pmu_alias {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
+	char *metric_expr;
+	char *metric_name;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
@@ -76,7 +80,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
-		      bool long_desc);
+		      bool long_desc, bool details_flag);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c
new file mode 100644
index 000000000000..e908177b9976
--- /dev/null
+++ b/tools/perf/util/print_binary.c
@@ -0,0 +1,55 @@
+#include "print_binary.h"
+#include <linux/log2.h>
+#include "sane_ctype.h"
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra)
+{
+	size_t i, j, mask;
+
+	if (!printer)
+		return;
+
+	bytes_per_line = roundup_pow_of_two(bytes_per_line);
+	mask = bytes_per_line - 1;
+
+	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+	for (i = 0; i < len; i++) {
+		if ((i & mask) == 0) {
+			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+			printer(BINARY_PRINT_ADDR, i, extra);
+		}
+
+		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+		if (((i & mask) == mask) || i == len - 1) {
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+			printer(BINARY_PRINT_SEP, i, extra);
+			for (j = i & ~mask; j <= i; j++)
+				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_CHAR_PAD, i, extra);
+			printer(BINARY_PRINT_LINE_END, -1, extra);
+		}
+	}
+	printer(BINARY_PRINT_DATA_END, -1, extra);
+}
+
+int is_printable_array(char *p, unsigned int len)
+{
+	unsigned int i;
+
+	if (!p || !len || p[len - 1] != 0)
+		return 0;
+
+	len--;
+
+	for (i = 0; i < len; i++) {
+		if (!isprint(p[i]) && !isspace(p[i]))
+			return 0;
+	}
+	return 1;
+}
diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h
new file mode 100644
index 000000000000..da0427263d2d
--- /dev/null
+++ b/tools/perf/util/print_binary.h
@@ -0,0 +1,28 @@
+#ifndef PERF_PRINT_BINARY_H
+#define PERF_PRINT_BINARY_H
+
+#include <stddef.h>
+
+enum binary_printer_ops {
+	BINARY_PRINT_DATA_BEGIN,
+	BINARY_PRINT_LINE_BEGIN,
+	BINARY_PRINT_ADDR,
+	BINARY_PRINT_NUM_DATA,
+	BINARY_PRINT_NUM_PAD,
+	BINARY_PRINT_SEP,
+	BINARY_PRINT_CHAR_DATA,
+	BINARY_PRINT_CHAR_PAD,
+	BINARY_PRINT_LINE_END,
+	BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops op,
+			       unsigned int val, void *extra);
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra);
+
+int is_printable_array(char *p, unsigned int len);
+
+#endif /* PERF_PRINT_BINARY_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28fb62c32678..84e7e698411e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -19,6 +19,7 @@
  *
  */
 
+#include <inttypes.h>
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -35,6 +36,7 @@
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
+#include "strfilter.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
@@ -46,8 +48,10 @@
 #include "probe-finder.h"
 #include "probe-file.h"
 #include "session.h"
+#include "string2.h"
+
+#include "sane_ctype.h"
 
-#define MAX_CMDLEN 256
 #define PERFPROBE_GROUP "probe"
 
 bool probe_event_dry_run;	/* Dry run flag */
@@ -757,7 +761,9 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (!tevs[i].point.address || tevs[i].point.retprobe)
+		if (!tevs[i].point.address)
+			continue;
+		if (tevs[i].point.retprobe && !kretprobe_offset_is_supported())
 			continue;
 		/* If we found a wrong one, mark it by NULL symbol */
 		if (kprobe_warn_out_range(tevs[i].point.symbol,
@@ -1339,14 +1345,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (!arg)
 		return -EINVAL;
 
-	/*
-	 * If the probe point starts with '%',
-	 * or starts with "sdt_" and has a ':' but no '=',
-	 * then it should be a SDT/cached probe point.
-	 */
-	if (arg[0] == '%' ||
-	    (!strncmp(arg, "sdt_", 4) &&
-	     !!strchr(arg, ':') && !strchr(arg, '='))) {
+	if (is_sdt_event(arg)) {
 		pev->sdt = true;
 		if (arg[0] == '%')
 			arg++;
@@ -1528,11 +1527,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		return -EINVAL;
 	}
 
-	if (pp->retprobe && !pp->function) {
-		semantic_error("Return probe requires an entry function.\n");
-		return -EINVAL;
-	}
-
 	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
 			       "return probe.\n");
@@ -2841,7 +2835,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 	/* Note that the symbols in the kmodule are not relocated */
-	if (!pev->uprobes && !pp->retprobe && !pev->target) {
+	if (!pev->uprobes && !pev->target &&
+			(!pp->retprobe || kretprobe_offset_is_supported())) {
 		reloc_sym = kernel_get_ref_reloc_sym();
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");
@@ -3057,7 +3052,7 @@ concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
 	struct probe_trace_event *new_tevs;
 	int ret = 0;
 
-	if (ntevs == 0) {
+	if (*ntevs == 0) {
 		*tevs = *tevs2;
 		*ntevs = ntevs2;
 		*tevs2 = NULL;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5d4e94061402..373842656fb6 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -3,8 +3,6 @@
 
 #include <stdbool.h>
 #include "intlist.h"
-#include "strlist.h"
-#include "strfilter.h"
 
 /* Probe related configurations */
 struct probe_conf {
@@ -107,6 +105,8 @@ struct line_range {
 	struct intlist		*line_list;	/* Visible lines */
 };
 
+struct strlist;
+
 /* List of variables */
 struct variable_list {
 	struct probe_trace_point	point;	/* Actual probepoint */
@@ -153,6 +153,9 @@ int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int show_probe_trace_events(struct perf_probe_event *pevs, int npevs);
 void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+
+struct strfilter;
+
 int del_perf_probe_events(struct strfilter *filter);
 
 int show_perf_probe_event(const char *group, const char *event,
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 436b64731f65..d679389e627c 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -14,10 +14,15 @@
  * GNU General Public License for more details.
  *
  */
+#include <errno.h>
+#include <sys/stat.h>
+#include <sys/types.h>
 #include <sys/uio.h>
+#include <unistd.h>
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
+#include "strfilter.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
@@ -27,8 +32,11 @@
 #include "probe-event.h"
 #include "probe-file.h"
 #include "session.h"
+#include "perf_regs.h"
+#include "string2.h"
 
-#define MAX_CMDLEN 256
+/* 4096 - 2 ('\n' + '\0') */
+#define MAX_CMDLEN 4094
 
 static void print_open_warning(int err, bool uprobe)
 {
@@ -70,7 +78,7 @@ static void print_both_open_warning(int kerr, int uerr)
 	}
 }
 
-static int open_probe_events(const char *trace_file, bool readwrite)
+int open_trace_file(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
 	int ret;
@@ -92,12 +100,12 @@ static int open_probe_events(const char *trace_file, bool readwrite)
 
 static int open_kprobe_events(bool readwrite)
 {
-	return open_probe_events("kprobe_events", readwrite);
+	return open_trace_file("kprobe_events", readwrite);
 }
 
 static int open_uprobe_events(bool readwrite)
 {
-	return open_probe_events("uprobe_events", readwrite);
+	return open_trace_file("uprobe_events", readwrite);
 }
 
 int probe_file__open(int flag)
@@ -687,6 +695,110 @@ static unsigned long long sdt_note__get_addr(struct sdt_note *note)
 		 : (unsigned long long)note->addr.a64[0];
 }
 
+static const char * const type_to_suffix[] = {
+	":s64", "", "", "", ":s32", "", ":s16", ":s8",
+	"", ":u8", ":u16", "", ":u32", "", "", "", ":u64"
+};
+
+/*
+ * Isolate the string number and convert it into a decimal value;
+ * this will be an index to get suffix of the uprobe name (defining
+ * the type)
+ */
+static int sdt_arg_parse_size(char *n_ptr, const char **suffix)
+{
+	long type_idx;
+
+	type_idx = strtol(n_ptr, NULL, 10);
+	if (type_idx < -8 || type_idx > 8) {
+		pr_debug4("Failed to get a valid sdt type\n");
+		return -1;
+	}
+
+	*suffix = type_to_suffix[type_idx + 8];
+	return 0;
+}
+
+static int synthesize_sdt_probe_arg(struct strbuf *buf, int i, const char *arg)
+{
+	char *op, *desc = strdup(arg), *new_op = NULL;
+	const char *suffix = "";
+	int ret = -1;
+
+	if (desc == NULL) {
+		pr_debug4("Allocation error\n");
+		return ret;
+	}
+
+	/*
+	 * Argument is in N@OP format. N is size of the argument and OP is
+	 * the actual assembly operand. N can be omitted; in that case
+	 * argument is just OP(without @).
+	 */
+	op = strchr(desc, '@');
+	if (op) {
+		op[0] = '\0';
+		op++;
+
+		if (sdt_arg_parse_size(desc, &suffix))
+			goto error;
+	} else {
+		op = desc;
+	}
+
+	ret = arch_sdt_arg_parse_op(op, &new_op);
+
+	if (ret < 0)
+		goto error;
+
+	if (ret == SDT_ARG_VALID) {
+		ret = strbuf_addf(buf, " arg%d=%s%s", i + 1, new_op, suffix);
+		if (ret < 0)
+			goto error;
+	}
+
+	ret = 0;
+error:
+	free(desc);
+	free(new_op);
+	return ret;
+}
+
+static char *synthesize_sdt_probe_command(struct sdt_note *note,
+					const char *pathname,
+					const char *sdtgrp)
+{
+	struct strbuf buf;
+	char *ret = NULL, **args;
+	int i, args_count;
+
+	if (strbuf_init(&buf, 32) < 0)
+		return NULL;
+
+	if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
+				sdtgrp, note->name, pathname,
+				sdt_note__get_addr(note)) < 0)
+		goto error;
+
+	if (!note->args)
+		goto out;
+
+	if (note->args) {
+		args = argv_split(note->args, &args_count);
+
+		for (i = 0; i < args_count; ++i) {
+			if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0)
+				goto error;
+		}
+	}
+
+out:
+	ret = strbuf_detach(&buf, NULL);
+error:
+	strbuf_release(&buf);
+	return ret;
+}
+
 int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 {
 	struct probe_cache_entry *entry = NULL;
@@ -723,11 +835,12 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 			entry->pev.group = strdup(sdtgrp);
 			list_add_tail(&entry->node, &pcache->entries);
 		}
-		ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
-				sdtgrp, note->name, pathname,
-				sdt_note__get_addr(note));
-		if (ret < 0)
+		buf = synthesize_sdt_probe_command(note, pathname, sdtgrp);
+		if (!buf) {
+			ret = -ENOMEM;
 			break;
+		}
+
 		strlist__add(entry->tevlist, buf);
 		free(buf);
 		entry = NULL;
@@ -877,59 +990,72 @@ int probe_cache__show_all_caches(struct strfilter *filter)
 	return 0;
 }
 
+enum ftrace_readme {
+	FTRACE_README_PROBE_TYPE_X = 0,
+	FTRACE_README_KRETPROBE_OFFSET,
+	FTRACE_README_END,
+};
+
 static struct {
 	const char *pattern;
-	bool	avail;
-	bool	checked;
-} probe_type_table[] = {
-#define DEFINE_TYPE(idx, pat, def_avail)	\
-	[idx] = {.pattern = pat, .avail = (def_avail)}
-	DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true),
-	DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true),
-	DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false),
-	DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true),
-	DEFINE_TYPE(PROBE_TYPE_BITFIELD,
-		    "* b<bit-width>@<bit-offset>/<container-size>", true),
+	bool avail;
+} ftrace_readme_table[] = {
+#define DEFINE_TYPE(idx, pat)			\
+	[idx] = {.pattern = pat, .avail = false}
+	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
+	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
 };
 
-bool probe_type_is_available(enum probe_type type)
+static bool scan_ftrace_readme(enum ftrace_readme type)
 {
+	int fd;
 	FILE *fp;
 	char *buf = NULL;
 	size_t len = 0;
-	bool target_line = false;
-	bool ret = probe_type_table[type].avail;
+	bool ret = false;
+	static bool scanned = false;
 
-	if (type >= PROBE_TYPE_END)
-		return false;
-	/* We don't have to check the type which supported by default */
-	if (ret || probe_type_table[type].checked)
-		return ret;
+	if (scanned)
+		goto result;
 
-	if (asprintf(&buf, "%s/README", tracing_path) < 0)
+	fd = open_trace_file("README", false);
+	if (fd < 0)
 		return ret;
 
-	fp = fopen(buf, "r");
-	if (!fp)
-		goto end;
-
-	zfree(&buf);
-	while (getline(&buf, &len, fp) > 0 && !ret) {
-		if (!target_line) {
-			target_line = !!strstr(buf, " type: ");
-			if (!target_line)
-				continue;
-		} else if (strstr(buf, "\t          ") != buf)
-			break;
-		ret = strglobmatch(buf, probe_type_table[type].pattern);
+	fp = fdopen(fd, "r");
+	if (!fp) {
+		close(fd);
+		return ret;
 	}
-	/* Cache the result */
-	probe_type_table[type].checked = true;
-	probe_type_table[type].avail = ret;
+
+	while (getline(&buf, &len, fp) > 0)
+		for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++)
+			if (!ftrace_readme_table[i].avail)
+				ftrace_readme_table[i].avail =
+					strglobmatch(buf, ftrace_readme_table[i].pattern);
+	scanned = true;
 
 	fclose(fp);
-end:
 	free(buf);
 
-	return ret;
+result:
+	if (type >= FTRACE_README_END)
+		return false;
+
+	return ftrace_readme_table[type].avail;
+}
+
+bool probe_type_is_available(enum probe_type type)
+{
+	if (type >= PROBE_TYPE_END)
+		return false;
+	else if (type == PROBE_TYPE_X)
+		return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X);
+
+	return true;
+}
+
+bool kretprobe_offset_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET);
 }
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index eba44c3e9dca..5ecc9d3925db 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -1,10 +1,11 @@
 #ifndef __PROBE_FILE_H
 #define __PROBE_FILE_H
 
-#include "strlist.h"
-#include "strfilter.h"
 #include "probe-event.h"
 
+struct strlist;
+struct strfilter;
+
 /* Cache of probe definitions */
 struct probe_cache_entry {
 	struct list_head	node;
@@ -35,11 +36,13 @@ enum probe_type {
 
 /* probe-file.c depends on libelf */
 #ifdef HAVE_LIBELF_SUPPORT
+int open_trace_file(const char *trace_file, bool readwrite);
 int probe_file__open(int flag);
 int probe_file__open_both(int *kfd, int *ufd, int flag);
 struct strlist *probe_file__get_namelist(int fd);
 struct strlist *probe_file__get_rawlist(int fd);
 int probe_file__add_event(int fd, struct probe_trace_event *tev);
+
 int probe_file__del_events(int fd, struct strfilter *filter);
 int probe_file__get_events(int fd, struct strfilter *filter,
 				  struct strlist *plist);
@@ -64,6 +67,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
 					const char *group, const char *event);
 int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
+bool kretprobe_offset_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
 {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 57cd268d4275..a5731de0e5eb 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -19,6 +19,7 @@
  *
  */
 
+#include <inttypes.h>
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -37,9 +38,11 @@
 #include "debug.h"
 #include "intlist.h"
 #include "util.h"
+#include "strlist.h"
 #include "symbol.h"
 #include "probe-finder.h"
 #include "probe-file.h"
+#include "string2.h"
 
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 2956c5198652..27f061551012 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -2,9 +2,9 @@
 #define _PROBE_FINDER_H
 
 #include <stdbool.h>
-#include "util.h"
 #include "intlist.h"
 #include "probe-event.h"
+#include "sane_ctype.h"
 
 #define MAX_PROBE_BUFFER	1024
 #define MAX_PROBES		 128
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 0546a4304347..9f3b0d9754a8 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -21,8 +21,10 @@ util/cgroup.c
 util/parse-branch-options.c
 util/rblist.c
 util/counts.c
+util/print_binary.c
 util/strlist.c
 util/trace-event.c
 ../lib/rbtree.c
 util/string.c
 util/symbol_fprintf.c
+util/units.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a5fbc012e3df..c129e99114ae 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -4,12 +4,26 @@
 #include <poll.h>
 #include <linux/err.h>
 #include "evlist.h"
+#include "callchain.h"
 #include "evsel.h"
 #include "event.h"
 #include "cpumap.h"
+#include "print_binary.h"
 #include "thread_map.h"
 
 /*
+ * Provide these two so that we don't have to link against callchain.c and
+ * start dragging hist.c, etc.
+ */
+struct callchain_param callchain_param;
+
+int parse_callchain_record(const char *arg __maybe_unused,
+			   struct callchain_param *param __maybe_unused)
+{
+	return 0;
+}
+
+/*
  * Support debug printing even though util/debug.c is not linked.  That means
  * implementing 'verbose' and 'eprintf'.
  */
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index 293534c1a474..1ba8920151d8 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include <stdlib.h>
 #include "strbuf.h"
 #include "quote.h"
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 98bf584853ea..d91bdf5a1aa4 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "cpumap.h"
 #include "parse-events.h"
+#include <errno.h>
 #include <api/fs/fs.h>
 #include "util.h"
 #include "cloexec.h"
diff --git a/tools/perf/util/sane_ctype.h b/tools/perf/util/sane_ctype.h
new file mode 100644
index 000000000000..4308c22c22ad
--- /dev/null
+++ b/tools/perf/util/sane_ctype.h
@@ -0,0 +1,51 @@
+#ifndef _PERF_SANE_CTYPE_H
+#define _PERF_SANE_CTYPE_H
+
+extern const char *graph_line;
+extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
+
+/* Sane ctype - no locale, and works with signed chars */
+#undef isascii
+#undef isspace
+#undef isdigit
+#undef isxdigit
+#undef isalpha
+#undef isprint
+#undef isalnum
+#undef islower
+#undef isupper
+#undef tolower
+#undef toupper
+
+extern unsigned char sane_ctype[256];
+#define GIT_SPACE		0x01
+#define GIT_DIGIT		0x02
+#define GIT_ALPHA		0x04
+#define GIT_GLOB_SPECIAL	0x08
+#define GIT_REGEX_SPECIAL	0x10
+#define GIT_PRINT_EXTRA		0x20
+#define GIT_PRINT		0x3E
+#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
+#define isascii(x) (((x) & ~0x7f) == 0)
+#define isspace(x) sane_istest(x,GIT_SPACE)
+#define isdigit(x) sane_istest(x,GIT_DIGIT)
+#define isxdigit(x)	\
+	(sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G')
+#define isalpha(x) sane_istest(x,GIT_ALPHA)
+#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
+#define isprint(x) sane_istest(x,GIT_PRINT)
+#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
+#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
+#define tolower(x) sane_case((unsigned char)(x), 0x20)
+#define toupper(x) sane_case((unsigned char)(x), 0)
+
+static inline int sane_case(int x, int high)
+{
+	if (sane_istest(x, GIT_ALPHA))
+		x = (x & ~0x20) | high;
+	return x;
+}
+
+#endif /* _PERF_SANE_CTYPE_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index dff043a29589..2b12bdb3ce33 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -19,6 +19,7 @@
  *
  */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 783326cfbaa6..9d92af7d0718 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -21,6 +21,7 @@
 
 #include <Python.h>
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -45,6 +46,7 @@
 #include "../call-path.h"
 #include "thread_map.h"
 #include "cpumap.h"
+#include "print_binary.h"
 #include "stat.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1dd617d116b5..3041c6b98191 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,8 @@
+#include <errno.h>
+#include <inttypes.h>
 #include <linux/kernel.h>
 #include <traceevent/event-parse.h>
+#include <api/fs/fs.h>
 
 #include <byteswap.h>
 #include <unistd.h>
@@ -16,6 +19,7 @@
 #include "perf_regs.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
+#include "thread.h"
 #include "thread-stack.h"
 #include "stat.h"
 
@@ -139,8 +143,14 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 			if (perf_session__open(session) < 0)
 				goto out_close;
 
-			perf_session__set_id_hdr_size(session);
-			perf_session__set_comm_exec(session);
+			/*
+			 * set session attributes that are present in perf.data
+			 * but not in pipe-mode.
+			 */
+			if (!file->is_pipe) {
+				perf_session__set_id_hdr_size(session);
+				perf_session__set_comm_exec(session);
+			}
 		}
 	} else  {
 		session->machines.host.env = &perf_env;
@@ -155,7 +165,11 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 			pr_warning("Cannot read kernel map\n");
 	}
 
-	if (tool && tool->ordering_requires_timestamps &&
+	/*
+	 * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is
+	 * processed, so perf_evlist__sample_id_all is not meaningful here.
+	 */
+	if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps &&
 	    tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_events = false;
@@ -1239,6 +1253,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
+	case PERF_RECORD_NAMESPACES:
+		return tool->namespaces(tool, event, sample, machine);
 	case PERF_RECORD_FORK:
 		return tool->fork(tool, event, sample, machine);
 	case PERF_RECORD_EXIT:
@@ -1258,9 +1274,12 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	case PERF_RECORD_AUX:
-		if (tool->aux == perf_event__process_aux &&
-		    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
-			evlist->stats.total_aux_lost += 1;
+		if (tool->aux == perf_event__process_aux) {
+			if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
+				evlist->stats.total_aux_lost += 1;
+			if (event->aux.flags & PERF_AUX_FLAG_PARTIAL)
+				evlist->stats.total_aux_partial += 1;
+		}
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
@@ -1494,6 +1513,11 @@ int perf_session__register_idle_thread(struct perf_session *session)
 		err = -1;
 	}
 
+	if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) {
+		pr_err("problem inserting idle task.\n");
+		err = -1;
+	}
+
 	/* machine__findnew_thread() got the thread, so put it */
 	thread__put(thread);
 	return err;
@@ -1548,6 +1572,23 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_events[PERF_RECORD_AUX]);
 	}
 
+	if (session->tool->aux == perf_event__process_aux &&
+	    stats->total_aux_partial != 0) {
+		bool vmm_exclusive = false;
+
+		(void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive",
+		                       &vmm_exclusive);
+
+		ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n"
+		            "Are you running a KVM guest in the background?%s\n\n",
+			    stats->total_aux_partial,
+			    stats->nr_events[PERF_RECORD_AUX],
+			    vmm_exclusive ?
+			    "\nReloading kvm_intel module with vmm_exclusive=0\n"
+			    "will reduce the gaps to only guest's timeslices." :
+			    "");
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
@@ -1628,6 +1669,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 	buf = malloc(cur_size);
 	if (!buf)
 		return -errno;
+	ordered_events__set_copy_on_queue(oe, true);
 more:
 	event = buf;
 	err = readn(fd, event, sizeof(struct perf_event_header));
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 4bd758553450..47b5e7dbcb18 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -5,14 +5,14 @@
 #include "event.h"
 #include "header.h"
 #include "machine.h"
-#include "symbol.h"
-#include "thread.h"
 #include "data.h"
 #include "ordered-events.h"
+#include <linux/kernel.h>
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
 
 struct ip_callchain;
+struct symbol;
 struct thread;
 
 struct auxtrace;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 0ff622288d24..5762ae4e9e91 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,12 +1,18 @@
+#include <errno.h>
+#include <inttypes.h>
+#include <regex.h>
 #include <sys/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
 #include "symbol.h"
+#include "thread.h"
 #include "evsel.h"
 #include "evlist.h"
+#include "strlist.h"
 #include <traceevent/event-parse.h>
 #include "mem-events.h"
+#include <linux/kernel.h>
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -323,7 +329,7 @@ char *hist_entry__get_srcline(struct hist_entry *he)
 		return SRCLINE_UNKNOWN;
 
 	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
-			   he->ms.sym, true);
+			   he->ms.sym, true, true);
 }
 
 static int64_t
@@ -366,7 +372,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
 			left->branch_info->srcline_from = get_srcline(map->dso,
 					   map__rip_2objdump(map,
 							     left->branch_info->from.al_addr),
-							 left->branch_info->from.sym, true);
+							 left->branch_info->from.sym,
+							 true, true);
 	}
 	if (!right->branch_info->srcline_from) {
 		struct map *map = right->branch_info->from.map;
@@ -376,7 +383,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
 			right->branch_info->srcline_from = get_srcline(map->dso,
 					     map__rip_2objdump(map,
 							       right->branch_info->from.al_addr),
-						     right->branch_info->from.sym, true);
+						     right->branch_info->from.sym,
+						     true, true);
 	}
 	return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
 }
@@ -407,7 +415,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
 			left->branch_info->srcline_to = get_srcline(map->dso,
 					   map__rip_2objdump(map,
 							     left->branch_info->to.al_addr),
-							 left->branch_info->from.sym, true);
+							 left->branch_info->from.sym,
+							 true, true);
 	}
 	if (!right->branch_info->srcline_to) {
 		struct map *map = right->branch_info->to.map;
@@ -417,7 +426,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
 			right->branch_info->srcline_to = get_srcline(map->dso,
 					     map__rip_2objdump(map,
 							       right->branch_info->to.al_addr),
-						     right->branch_info->to.sym, true);
+						     right->branch_info->to.sym,
+						     true, true);
 	}
 	return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
 }
@@ -448,7 +458,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e)
 		return no_srcfile;
 
 	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
-			 e->ms.sym, false, true);
+			 e->ms.sym, false, true, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
 		return no_srcfile;
 	p = strchr(sf, ':');
@@ -536,6 +546,46 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* --sort cgroup_id */
+
+static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev)
+{
+	return (int64_t)(right_dev - left_dev);
+}
+
+static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino)
+{
+	return (int64_t)(right_ino - left_ino);
+}
+
+static int64_t
+sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev);
+	if (ret != 0)
+		return ret;
+
+	return _sort__cgroup_inode_cmp(right->cgroup_id.ino,
+				       left->cgroup_id.ino);
+}
+
+static int hist_entry__cgroup_id_snprintf(struct hist_entry *he,
+					  char *bf, size_t size,
+					  unsigned int width __maybe_unused)
+{
+	return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev,
+			       he->cgroup_id.ino);
+}
+
+struct sort_entry sort_cgroup_id = {
+	.se_header      = "cgroup id (dev/inode)",
+	.se_cmp	        = sort__cgroup_id_cmp,
+	.se_snprintf    = hist_entry__cgroup_id_snprintf,
+	.se_width_idx	= HISTC_CGROUP_ID,
+};
+
 /* --sort socket */
 
 static int64_t
@@ -846,6 +896,9 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 static int64_t
 sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.cycles -
 		right->branch_info->flags.cycles;
 }
@@ -853,6 +906,8 @@ sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
+	if (!he->branch_info)
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 	if (he->branch_info->flags.cycles == 0)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 	return repsep_snprintf(bf, size, "%-*hd", width,
@@ -1396,6 +1451,46 @@ struct sort_entry sort_transaction = {
 	.se_width_idx	= HISTC_TRANSACTION,
 };
 
+/* --sort symbol_size */
+
+static int64_t _sort__sym_size_cmp(struct symbol *sym_l, struct symbol *sym_r)
+{
+	int64_t size_l = sym_l != NULL ? symbol__size(sym_l) : 0;
+	int64_t size_r = sym_r != NULL ? symbol__size(sym_r) : 0;
+
+	return size_l < size_r ? -1 :
+		size_l == size_r ? 0 : 1;
+}
+
+static int64_t
+sort__sym_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__sym_size_cmp(right->ms.sym, left->ms.sym);
+}
+
+static int _hist_entry__sym_size_snprintf(struct symbol *sym, char *bf,
+					  size_t bf_size, unsigned int width)
+{
+	if (sym)
+		return repsep_snprintf(bf, bf_size, "%*d", width, symbol__size(sym));
+
+	return repsep_snprintf(bf, bf_size, "%*s", width, "unknown");
+}
+
+static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf,
+					 size_t size, unsigned int width)
+{
+	return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width);
+}
+
+struct sort_entry sort_sym_size = {
+	.se_header	= "Symbol size",
+	.se_cmp		= sort__sym_size_cmp,
+	.se_snprintf	= hist_entry__sym_size_snprintf,
+	.se_width_idx	= HISTC_SYM_SIZE,
+};
+
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
@@ -1418,6 +1513,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
 	DIM(SORT_TRACE, "trace", sort_trace),
+	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
+	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 796c847e2f00..b7c75597e18f 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -2,7 +2,7 @@
 #define __PERF_SORT_H
 #include "../builtin.h"
 
-#include "util.h"
+#include <regex.h>
 
 #include "color.h"
 #include <linux/list.h>
@@ -11,7 +11,6 @@
 #include "symbol.h"
 #include "string.h"
 #include "callchain.h"
-#include "strlist.h"
 #include "values.h"
 
 #include "../perf.h"
@@ -21,7 +20,9 @@
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include "hist.h"
-#include "thread.h"
+#include "srcline.h"
+
+struct thread;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -54,6 +55,11 @@ struct he_stat {
 	u32			nr_events;
 };
 
+struct namespace_id {
+	u64			dev;
+	u64			ino;
+};
+
 struct hist_entry_diff {
 	bool	computed;
 	union {
@@ -91,6 +97,7 @@ struct hist_entry {
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
+	struct namespace_id	cgroup_id;
 	u64			ip;
 	u64			transaction;
 	s32			socket;
@@ -122,6 +129,7 @@ struct hist_entry {
 	};
 	char			*srcline;
 	char			*srcfile;
+	struct inline_node	*inline_node;
 	struct symbol		*parent;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
@@ -211,6 +219,8 @@ enum sort_type {
 	SORT_GLOBAL_WEIGHT,
 	SORT_TRANSACTION,
 	SORT_TRACE,
+	SORT_SYM_SIZE,
+	SORT_CGROUP_ID,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index b4db3f48e3b0..df051a52393c 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -1,3 +1,4 @@
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -7,11 +8,59 @@
 #include "util/dso.h"
 #include "util/util.h"
 #include "util/debug.h"
+#include "util/callchain.h"
+#include "srcline.h"
 
 #include "symbol.h"
 
 bool srcline_full_filename;
 
+static const char *dso__name(struct dso *dso)
+{
+	const char *dso_name;
+
+	if (dso->symsrc_filename)
+		dso_name = dso->symsrc_filename;
+	else
+		dso_name = dso->long_name;
+
+	if (dso_name[0] == '[')
+		return NULL;
+
+	if (!strncmp(dso_name, "/tmp/perf-", 10))
+		return NULL;
+
+	return dso_name;
+}
+
+static int inline_list__append(char *filename, char *funcname, int line_nr,
+			       struct inline_node *node, struct dso *dso)
+{
+	struct inline_list *ilist;
+	char *demangled;
+
+	ilist = zalloc(sizeof(*ilist));
+	if (ilist == NULL)
+		return -1;
+
+	ilist->filename = filename;
+	ilist->line_nr = line_nr;
+
+	if (dso != NULL) {
+		demangled = dso__demangle_sym(dso, 0, funcname);
+		if (demangled == NULL) {
+			ilist->funcname = funcname;
+		} else {
+			ilist->funcname = demangled;
+			free(funcname);
+		}
+	}
+
+	list_add_tail(&ilist->list, &node->val);
+
+	return 0;
+}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -151,9 +200,17 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 
 #define MAX_INLINE_NEST 1024
 
+static void inline_list__reverse(struct inline_node *node)
+{
+	struct inline_list *ilist, *n;
+
+	list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
+		list_move_tail(&ilist->list, &node->val);
+}
+
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line, struct dso *dso,
-		     bool unwind_inlines)
+		     bool unwind_inlines, struct inline_node *node)
 {
 	int ret = 0;
 	struct a2l_data *a2l = dso->a2l;
@@ -178,8 +235,21 @@ static int addr2line(const char *dso_name, u64 addr,
 
 		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
 					     &a2l->funcname, &a2l->line) &&
-		       cnt++ < MAX_INLINE_NEST)
-			;
+		       cnt++ < MAX_INLINE_NEST) {
+
+			if (node != NULL) {
+				if (inline_list__append(strdup(a2l->filename),
+							strdup(a2l->funcname),
+							a2l->line, node,
+							dso) != 0)
+					return 0;
+			}
+		}
+
+		if ((node != NULL) &&
+		    (callchain_param.order != ORDER_CALLEE)) {
+			inline_list__reverse(node);
+		}
 	}
 
 	if (a2l->found && a2l->filename) {
@@ -205,18 +275,68 @@ void dso__free_a2l(struct dso *dso)
 	dso->a2l = NULL;
 }
 
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+	struct dso *dso)
+{
+	char *file = NULL;
+	unsigned int line = 0;
+	struct inline_node *node;
+
+	node = zalloc(sizeof(*node));
+	if (node == NULL) {
+		perror("not enough memory for the inline node");
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&node->val);
+	node->addr = addr;
+
+	if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+		goto out_free_inline_node;
+
+	if (list_empty(&node->val))
+		goto out_free_inline_node;
+
+	return node;
+
+out_free_inline_node:
+	inline_node__delete(node);
+	return NULL;
+}
+
 #else /* HAVE_LIBBFD_SUPPORT */
 
+static int filename_split(char *filename, unsigned int *line_nr)
+{
+	char *sep;
+
+	sep = strchr(filename, '\n');
+	if (sep)
+		*sep = '\0';
+
+	if (!strcmp(filename, "??:0"))
+		return 0;
+
+	sep = strchr(filename, ':');
+	if (sep) {
+		*sep++ = '\0';
+		*line_nr = strtoul(sep, NULL, 0);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line_nr,
 		     struct dso *dso __maybe_unused,
-		     bool unwind_inlines __maybe_unused)
+		     bool unwind_inlines __maybe_unused,
+		     struct inline_node *node __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
 	char *filename = NULL;
 	size_t len;
-	char *sep;
 	int ret = 0;
 
 	scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
@@ -233,23 +353,14 @@ static int addr2line(const char *dso_name, u64 addr,
 		goto out;
 	}
 
-	sep = strchr(filename, '\n');
-	if (sep)
-		*sep = '\0';
-
-	if (!strcmp(filename, "??:0")) {
-		pr_debug("no debugging info in %s\n", dso_name);
+	ret = filename_split(filename, line_nr);
+	if (ret != 1) {
 		free(filename);
 		goto out;
 	}
 
-	sep = strchr(filename, ':');
-	if (sep) {
-		*sep++ = '\0';
-		*file = filename;
-		*line_nr = strtoul(sep, NULL, 0);
-		ret = 1;
-	}
+	*file = filename;
+
 out:
 	pclose(fp);
 	return ret;
@@ -259,6 +370,58 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 {
 }
 
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+	struct dso *dso __maybe_unused)
+{
+	FILE *fp;
+	char cmd[PATH_MAX];
+	struct inline_node *node;
+	char *filename = NULL;
+	size_t len;
+	unsigned int line_nr = 0;
+
+	scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+		  dso_name, addr);
+
+	fp = popen(cmd, "r");
+	if (fp == NULL) {
+		pr_err("popen failed for %s\n", dso_name);
+		return NULL;
+	}
+
+	node = zalloc(sizeof(*node));
+	if (node == NULL) {
+		perror("not enough memory for the inline node");
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&node->val);
+	node->addr = addr;
+
+	while (getline(&filename, &len, fp) != -1) {
+		if (filename_split(filename, &line_nr) != 1) {
+			free(filename);
+			goto out;
+		}
+
+		if (inline_list__append(filename, NULL, line_nr, node,
+					NULL) != 0)
+			goto out;
+
+		filename = NULL;
+	}
+
+out:
+	pclose(fp);
+
+	if (list_empty(&node->val)) {
+		inline_node__delete(node);
+		return NULL;
+	}
+
+	return node;
+}
+
 #endif /* HAVE_LIBBFD_SUPPORT */
 
 /*
@@ -268,7 +431,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 #define A2L_FAIL_LIMIT 123
 
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym, bool unwind_inlines)
+		  bool show_sym, bool show_addr, bool unwind_inlines)
 {
 	char *file = NULL;
 	unsigned line = 0;
@@ -278,18 +441,11 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	if (!dso->has_srcline)
 		goto out;
 
-	if (dso->symsrc_filename)
-		dso_name = dso->symsrc_filename;
-	else
-		dso_name = dso->long_name;
-
-	if (dso_name[0] == '[')
-		goto out;
-
-	if (!strncmp(dso_name, "/tmp/perf-", 10))
+	dso_name = dso__name(dso);
+	if (dso_name == NULL)
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines))
+	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
 		goto out;
 
 	if (asprintf(&srcline, "%s:%u",
@@ -309,6 +465,11 @@ out:
 		dso->has_srcline = 0;
 		dso__free_a2l(dso);
 	}
+
+	if (!show_addr)
+		return (show_sym && sym) ?
+			    strndup(sym->name, sym->namelen) : NULL;
+
 	if (sym) {
 		if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
 					addr - sym->start) < 0)
@@ -325,7 +486,32 @@ void free_srcline(char *srcline)
 }
 
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym)
+		  bool show_sym, bool show_addr)
+{
+	return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
 {
-	return __get_srcline(dso, addr, sym, show_sym, false);
+	const char *dso_name;
+
+	dso_name = dso__name(dso);
+	if (dso_name == NULL)
+		return NULL;
+
+	return addr2inlines(dso_name, addr, dso);
+}
+
+void inline_node__delete(struct inline_node *node)
+{
+	struct inline_list *ilist, *tmp;
+
+	list_for_each_entry_safe(ilist, tmp, &node->val, list) {
+		list_del_init(&ilist->list);
+		zfree(&ilist->filename);
+		zfree(&ilist->funcname);
+		free(ilist);
+	}
+
+	free(node);
 }
diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h
new file mode 100644
index 000000000000..7b52ba88676e
--- /dev/null
+++ b/tools/perf/util/srcline.h
@@ -0,0 +1,34 @@
+#ifndef PERF_SRCLINE_H
+#define PERF_SRCLINE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+
+struct dso;
+struct symbol;
+
+extern bool srcline_full_filename;
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym, bool show_addr);
+char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym, bool show_addr, bool unwind_inlines);
+void free_srcline(char *srcline);
+
+#define SRCLINE_UNKNOWN  ((char *) "??:0")
+
+struct inline_list {
+	char			*filename;
+	char			*funcname;
+	unsigned int		line_nr;
+	struct list_head	list;
+};
+
+struct inline_node {
+	u64			addr;
+	struct list_head	val;
+};
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+void inline_node__delete(struct inline_node *node);
+
+#endif /* PERF_SRCLINE_H */
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 8a2bbd2a4d82..ac10cc675d39 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -3,6 +3,9 @@
 #include "stat.h"
 #include "color.h"
 #include "pmu.h"
+#include "rblist.h"
+#include "evlist.h"
+#include "expr.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -41,13 +44,73 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+struct saved_value {
+	struct rb_node rb_node;
+	struct perf_evsel *evsel;
+	int cpu;
+	int ctx;
+	struct stats stats;
+};
+
+static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct saved_value *a = container_of(rb_node,
+					     struct saved_value,
+					     rb_node);
+	const struct saved_value *b = entry;
+
+	if (a->ctx != b->ctx)
+		return a->ctx - b->ctx;
+	if (a->cpu != b->cpu)
+		return a->cpu - b->cpu;
+	return a->evsel - b->evsel;
+}
+
+static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
+				     const void *entry)
+{
+	struct saved_value *nd = malloc(sizeof(struct saved_value));
+
+	if (!nd)
+		return NULL;
+	memcpy(nd, entry, sizeof(struct saved_value));
+	return &nd->rb_node;
+}
+
+static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
+					      int cpu, int ctx,
+					      bool create)
+{
+	struct rb_node *nd;
+	struct saved_value dm = {
+		.cpu = cpu,
+		.ctx = ctx,
+		.evsel = evsel,
+	};
+	nd = rblist__find(&runtime_saved_values, &dm);
+	if (nd)
+		return container_of(nd, struct saved_value, rb_node);
+	if (create) {
+		rblist__add_node(&runtime_saved_values, &dm);
+		nd = rblist__find(&runtime_saved_values, &dm);
+		if (nd)
+			return container_of(nd, struct saved_value, rb_node);
+	}
+	return NULL;
+}
+
 void perf_stat__init_shadow_stats(void)
 {
 	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+	rblist__init(&runtime_saved_values);
+	runtime_saved_values.node_cmp = saved_value_cmp;
+	runtime_saved_values.node_new = saved_value_new;
+	/* No delete for now */
 }
 
 static int evsel_context(struct perf_evsel *evsel)
@@ -70,6 +133,8 @@ static int evsel_context(struct perf_evsel *evsel)
 
 void perf_stat__reset_shadow_stats(void)
 {
+	struct rb_node *pos, *next;
+
 	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
 	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
 	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
@@ -92,6 +157,15 @@ void perf_stat__reset_shadow_stats(void)
 	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
 	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
 	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
+
+	next = rb_first(&runtime_saved_values.entries);
+	while (next) {
+		pos = next;
+		next = rb_next(pos);
+		memset(&container_of(pos, struct saved_value, rb_node)->stats,
+		       0,
+		       sizeof(struct stats));
+	}
 }
 
 /*
@@ -143,6 +217,12 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
 		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+
+	if (counter->collect_stat) {
+		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
+							   true);
+		update_stats(&v->stats, count[0]);
+	}
 }
 
 /* used for get_ratio_color() */
@@ -172,6 +252,95 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
+static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
+						const char *name)
+{
+	struct perf_evsel *c2;
+
+	evlist__for_each_entry (evsel_list, c2) {
+		if (!strcasecmp(c2->name, name))
+			return c2;
+	}
+	return NULL;
+}
+
+/* Mark MetricExpr target events and link events using them to them. */
+void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
+{
+	struct perf_evsel *counter, *leader, **metric_events, *oc;
+	bool found;
+	const char **metric_names;
+	int i;
+	int num_metric_names;
+
+	evlist__for_each_entry(evsel_list, counter) {
+		bool invalid = false;
+
+		leader = counter->leader;
+		if (!counter->metric_expr)
+			continue;
+		metric_events = counter->metric_events;
+		if (!metric_events) {
+			if (expr__find_other(counter->metric_expr, counter->name,
+						&metric_names, &num_metric_names) < 0)
+				continue;
+
+			metric_events = calloc(sizeof(struct perf_evsel *),
+					       num_metric_names + 1);
+			if (!metric_events)
+				return;
+			counter->metric_events = metric_events;
+		}
+
+		for (i = 0; i < num_metric_names; i++) {
+			found = false;
+			if (leader) {
+				/* Search in group */
+				for_each_group_member (oc, leader) {
+					if (!strcasecmp(oc->name, metric_names[i])) {
+						found = true;
+						break;
+					}
+				}
+			}
+			if (!found) {
+				/* Search ignoring groups */
+				oc = perf_stat__find_event(evsel_list, metric_names[i]);
+			}
+			if (!oc) {
+				/* Deduping one is good enough to handle duplicated PMUs. */
+				static char *printed;
+
+				/*
+				 * Adding events automatically would be difficult, because
+				 * it would risk creating groups that are not schedulable.
+				 * perf stat doesn't understand all the scheduling constraints
+				 * of events. So we ask the user instead to add the missing
+				 * events.
+				 */
+				if (!printed || strcasecmp(printed, metric_names[i])) {
+					fprintf(stderr,
+						"Add %s event to groups to get metric expression for %s\n",
+						metric_names[i],
+						counter->name);
+					printed = strdup(metric_names[i]);
+				}
+				invalid = true;
+				continue;
+			}
+			metric_events[i] = oc;
+			oc->collect_stat = true;
+		}
+		metric_events[i] = NULL;
+		free(metric_names);
+		if (invalid) {
+			free(metric_events);
+			counter->metric_events = NULL;
+			counter->metric_expr = NULL;
+		}
+	}
+}
+
 static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out)
@@ -614,6 +783,34 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					be_bound * 100.);
 		else
 			print_metric(ctxp, NULL, NULL, name, 0);
+	} else if (evsel->metric_expr) {
+		struct parse_ctx pctx;
+		int i;
+
+		expr__ctx_init(&pctx);
+		expr__add_id(&pctx, evsel->name, avg);
+		for (i = 0; evsel->metric_events[i]; i++) {
+			struct saved_value *v;
+
+			v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
+			if (!v)
+				break;
+			expr__add_id(&pctx, evsel->metric_events[i]->name,
+					     avg_stats(&v->stats));
+		}
+		if (!evsel->metric_events[i]) {
+			const char *p = evsel->metric_expr;
+
+			if (expr__parse(&ratio, &pctx, &p) == 0)
+				print_metric(ctxp, NULL, "%8.1f",
+					evsel->metric_name ?
+					evsel->metric_name :
+					out->force_header ?  evsel->name : "",
+					ratio);
+			else
+				print_metric(ctxp, NULL, NULL, "", 0);
+		} else
+			print_metric(ctxp, NULL, NULL, "", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 0d51334a9b46..c58174443dc1 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,3 +1,5 @@
+#include <errno.h>
+#include <inttypes.h>
 #include <math.h>
 #include "stat.h"
 #include "evlist.h"
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index c29bb94c48a4..0a65ae23f495 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -85,11 +85,13 @@ struct perf_stat_output_ctx {
 	void *ctx;
 	print_metric_t print_metric;
 	new_line_t new_line;
+	bool force_header;
 };
 
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out);
+void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 817593908d47..e91b5e86f027 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,6 +1,7 @@
 #include "debug.h"
 #include "util.h"
 #include <linux/kernel.h>
+#include <errno.h>
 
 int prefixcmp(const char *str, const char *prefix)
 {
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index efb53772e0ec..4dc0af669a30 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -1,7 +1,10 @@
 #include "util.h"
-#include "string.h"
+#include "string2.h"
 #include "strfilter.h"
 
+#include <errno.h>
+#include "sane_ctype.h"
+
 /* Operators */
 static const char *OP_and	= "&";	/* Logical AND */
 static const char *OP_or	= "|";	/* Logical OR */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index bddca519dd58..cca53b693a48 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,5 +1,9 @@
-#include "util.h"
-#include "linux/string.h"
+#include "string2.h"
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "sane_ctype.h"
 
 #define K 1024LL
 /*
@@ -99,8 +103,10 @@ static int count_argc(const char *str)
 void argv_free(char **argv)
 {
 	char **p;
-	for (p = argv; *p; p++)
-		zfree(p);
+	for (p = argv; *p; p++) {
+		free(*p);
+		*p = NULL;
+	}
 
 	free(argv);
 }
@@ -120,7 +126,7 @@ void argv_free(char **argv)
 char **argv_split(const char *str, int *argcp)
 {
 	int argc = count_argc(str);
-	char **argv = zalloc(sizeof(*argv) * (argc+1));
+	char **argv = calloc(argc + 1, sizeof(*argv));
 	char **argvp;
 
 	if (argv == NULL)
@@ -322,12 +328,8 @@ char *strxfrchar(char *s, char from, char to)
  */
 char *ltrim(char *s)
 {
-	int len = strlen(s);
-
-	while (len && isspace(*s)) {
-		len--;
+	while (isspace(*s))
 		s++;
-	}
 
 	return s;
 }
@@ -381,7 +383,7 @@ char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints
 				goto out_err_overflow;
 
 			if (i > 0)
-				printed += snprintf(e + printed, size - printed, " %s ", or_and);
+				printed += scnprintf(e + printed, size - printed, " %s ", or_and);
 			printed += scnprintf(e + printed, size - printed,
 					     "%s %s %d", var, eq_neq, ints[i]);
 		}
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
new file mode 100644
index 000000000000..2f619681bd6a
--- /dev/null
+++ b/tools/perf/util/string2.h
@@ -0,0 +1,42 @@
+#ifndef PERF_STRING_H
+#define PERF_STRING_H
+
+#include <linux/types.h>
+#include <stddef.h>
+#include <string.h>
+
+s64 perf_atoll(const char *str);
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+bool strglobmatch(const char *str, const char *pat);
+bool strglobmatch_nocase(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+	return strpbrk(str, "*?[") != NULL;
+}
+int strtailcmp(const char *s1, const char *s2);
+char *strxfrchar(char *s, char from, char to);
+
+char *ltrim(char *s);
+char *rtrim(char *s);
+
+static inline char *trim(char *s)
+{
+	return ltrim(rtrim(s));
+}
+
+char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints);
+
+static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints)
+{
+	return asprintf_expr_inout_ints(var, true, nints, ints);
+}
+
+static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints)
+{
+	return asprintf_expr_inout_ints(var, false, nints, ints);
+}
+
+
+#endif /* PERF_STRING_H */
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 0d3dfcb919b4..9de5434bb49e 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -10,6 +10,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <unistd.h>
 
 static
 struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 4e59ddeb4eda..e7ee47f7377a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -10,8 +10,9 @@
 #include "demangle-rust.h"
 #include "machine.h"
 #include "vdso.h"
-#include <symbol/kallsyms.h>
 #include "debug.h"
+#include "sane_ctype.h"
+#include <symbol/kallsyms.h>
 
 #ifndef EM_AARCH64
 #define EM_AARCH64	183  /* ARM 64 bit */
@@ -390,6 +391,11 @@ out_elf_end:
 	return 0;
 }
 
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name)
+{
+	return demangle_sym(dso, kmodule, elf_name);
+}
+
 /*
  * Align offset to 4 bytes as needed for note name and descriptor data.
  */
@@ -1828,7 +1834,7 @@ void kcore_extract__delete(struct kcore_extract *kce)
 static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 			     struct list_head *sdt_notes)
 {
-	const char *provider, *name;
+	const char *provider, *name, *args;
 	struct sdt_note *tmp = NULL;
 	GElf_Ehdr ehdr;
 	GElf_Addr base_off = 0;
@@ -1887,6 +1893,25 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 		goto out_free_prov;
 	}
 
+	args = memchr(name, '\0', data + len - name);
+
+	/*
+	 * There is no argument if:
+	 * - We reached the end of the note;
+	 * - There is not enough room to hold a potential string;
+	 * - The argument string is empty or just contains ':'.
+	 */
+	if (args == NULL || data + len - args < 2 ||
+		args[1] == ':' || args[1] == '\0')
+		tmp->args = NULL;
+	else {
+		tmp->args = strdup(++args);
+		if (!tmp->args) {
+			ret = -ENOMEM;
+			goto out_free_name;
+		}
+	}
+
 	if (gelf_getclass(*elf) == ELFCLASS32) {
 		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
 		tmp->bit32 = true;
@@ -1898,7 +1923,7 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	if (!gelf_getehdr(*elf, &ehdr)) {
 		pr_debug("%s : cannot get elf header.\n", __func__);
 		ret = -EBADF;
-		goto out_free_name;
+		goto out_free_args;
 	}
 
 	/* Adjust the prelink effect :
@@ -1923,6 +1948,8 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	list_add_tail(&tmp->note_list, sdt_notes);
 	return 0;
 
+out_free_args:
+	free(tmp->args);
 out_free_name:
 	free(tmp->name);
 out_free_prov:
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 11cdde980545..40bf5d4c0bfd 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,6 +1,7 @@
 #include "symbol.h"
 #include "util.h"
 
+#include <errno.h>
 #include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
@@ -373,3 +374,10 @@ int kcore_copy(const char *from_dir __maybe_unused,
 void symbol__elf_init(void)
 {
 }
+
+char *dso__demangle_sym(struct dso *dso __maybe_unused,
+			int kmodule __maybe_unused,
+			char *elf_name __maybe_unused)
+{
+	return NULL;
+}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 70e389bc4af7..2cb7665e9973 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -3,6 +3,7 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <linux/kernel.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/param.h>
@@ -18,6 +19,8 @@
 #include "strlist.h"
 #include "intlist.h"
 #include "header.h"
+#include "path.h"
+#include "sane_ctype.h"
 
 #include <elf.h>
 #include <limits.h>
@@ -202,7 +205,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 
 	/* Last entry */
 	if (curr->end == curr->start)
-		curr->end = roundup(curr->start, 4096);
+		curr->end = roundup(curr->start, 4096) + 4096;
 }
 
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6c358b7ed336..7acd70fce68e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,7 +13,7 @@
 #include <libgen.h>
 #include "build-id.h"
 #include "event.h"
-#include "util.h"
+#include "path.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -118,7 +118,8 @@ struct symbol_conf {
 			show_ref_callgraph,
 			hide_unresolved,
 			raw_trace,
-			report_hierarchy;
+			report_hierarchy,
+			inline_name;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
@@ -305,6 +306,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
 				struct map *map);
 
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name);
+
 void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
@@ -351,6 +354,7 @@ int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
 struct sdt_note {
 	char *name;			/* name of the note*/
 	char *provider;			/* provider name */
+	char *args;
 	bool bit32;			/* whether the location is 32 bits? */
 	union {				/* location, base and semaphore addrs */
 		Elf64_Addr a64[3];
diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c
index 90b47d8aa19c..8f254a74d97d 100644
--- a/tools/perf/util/term.c
+++ b/tools/perf/util/term.c
@@ -1,4 +1,8 @@
-#include "util.h"
+#include "term.h"
+#include <stdlib.h>
+#include <termios.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
 
 void get_term_dimensions(struct winsize *ws)
 {
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index d3301529f6a7..dd17d6a38d3a 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -15,6 +15,7 @@
 
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <errno.h>
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index f5af87f66663..378c418ca0c1 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -1,12 +1,15 @@
 #include "../perf.h"
+#include <errno.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <linux/kernel.h>
 #include "session.h"
 #include "thread.h"
 #include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
+#include "namespaces.h"
 #include "comm.h"
 #include "unwind.h"
 
@@ -40,6 +43,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->tid = tid;
 		thread->ppid = -1;
 		thread->cpu = -1;
+		INIT_LIST_HEAD(&thread->namespaces_list);
 		INIT_LIST_HEAD(&thread->comm_list);
 
 		comm_str = malloc(32);
@@ -53,7 +57,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-		atomic_set(&thread->refcnt, 1);
+		refcount_set(&thread->refcnt, 1);
 		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
@@ -66,7 +70,8 @@ err_thread:
 
 void thread__delete(struct thread *thread)
 {
-	struct comm *comm, *tmp;
+	struct namespaces *namespaces, *tmp_namespaces;
+	struct comm *comm, *tmp_comm;
 
 	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
 
@@ -76,7 +81,12 @@ void thread__delete(struct thread *thread)
 		map_groups__put(thread->mg);
 		thread->mg = NULL;
 	}
-	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+	list_for_each_entry_safe(namespaces, tmp_namespaces,
+				 &thread->namespaces_list, list) {
+		list_del(&namespaces->list);
+		namespaces__free(namespaces);
+	}
+	list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
 		list_del(&comm->list);
 		comm__free(comm);
 	}
@@ -88,13 +98,13 @@ void thread__delete(struct thread *thread)
 struct thread *thread__get(struct thread *thread)
 {
 	if (thread)
-		atomic_inc(&thread->refcnt);
+		refcount_inc(&thread->refcnt);
 	return thread;
 }
 
 void thread__put(struct thread *thread)
 {
-	if (thread && atomic_dec_and_test(&thread->refcnt)) {
+	if (thread && refcount_dec_and_test(&thread->refcnt)) {
 		/*
 		 * Remove it from the dead_threads list, as last reference
 		 * is gone.
@@ -104,6 +114,38 @@ void thread__put(struct thread *thread)
 	}
 }
 
+struct namespaces *thread__namespaces(const struct thread *thread)
+{
+	if (list_empty(&thread->namespaces_list))
+		return NULL;
+
+	return list_first_entry(&thread->namespaces_list, struct namespaces, list);
+}
+
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event)
+{
+	struct namespaces *new, *curr = thread__namespaces(thread);
+
+	new = namespaces__new(event);
+	if (!new)
+		return -ENOMEM;
+
+	list_add(&new->list, &thread->namespaces_list);
+
+	if (timestamp && curr) {
+		/*
+		 * setns syscall must have changed few or all the namespaces
+		 * of this thread. Update end time for the namespaces
+		 * previously used.
+		 */
+		curr = list_next_entry(new, list);
+		curr->end_time = timestamp;
+	}
+
+	return 0;
+}
+
 struct comm *thread__comm(const struct thread *thread)
 {
 	if (list_empty(&thread->comm_list))
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 99263cb6e6b6..4eb849e9098f 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_THREAD_H
 #define __PERF_THREAD_H
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <unistd.h>
@@ -23,11 +23,12 @@ struct thread {
 	pid_t			tid;
 	pid_t			ppid;
 	int			cpu;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	char			shortname[3];
 	bool			comm_set;
 	int			comm_len;
 	bool			dead; /* if set thread has exited */
+	struct list_head	namespaces_list;
 	struct list_head	comm_list;
 	u64			db_id;
 
@@ -40,6 +41,7 @@ struct thread {
 };
 
 struct machine;
+struct namespaces;
 struct comm;
 
 struct thread *thread__new(pid_t pid, pid_t tid);
@@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
+struct namespaces *thread__namespaces(const struct thread *thread);
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event);
+
 int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
 		       bool exec);
 static inline int thread__set_comm(struct thread *thread, const char *comm,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 7c3fcc538a70..63ead7b06324 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -1,4 +1,5 @@
 #include <dirent.h>
+#include <errno.h>
 #include <limits.h>
 #include <stdbool.h>
 #include <stdlib.h>
@@ -6,6 +7,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
+#include "string2.h"
 #include "strlist.h"
 #include <string.h>
 #include <api/fs/fs.h>
@@ -66,7 +68,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 		for (i = 0; i < items; i++)
 			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -83,7 +85,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, tid);
 		threads->nr = 1;
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -105,7 +107,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
-	atomic_set(&threads->refcnt, 1);
+	refcount_set(&threads->refcnt, 1);
 
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
@@ -235,7 +237,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 out:
 	strlist__delete(slist);
 	if (threads)
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -255,7 +257,7 @@ struct thread_map *thread_map__new_dummy(void)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, -1);
 		threads->nr = 1;
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -300,7 +302,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 	}
 out:
 	if (threads)
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -326,7 +328,7 @@ static void thread_map__delete(struct thread_map *threads)
 	if (threads) {
 		int i;
 
-		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+		WARN_ONCE(refcount_read(&threads->refcnt) != 0,
 			  "thread map refcnt unbalanced\n");
 		for (i = 0; i < threads->nr; i++)
 			free(thread_map__comm(threads, i));
@@ -337,13 +339,13 @@ static void thread_map__delete(struct thread_map *threads)
 struct thread_map *thread_map__get(struct thread_map *map)
 {
 	if (map)
-		atomic_inc(&map->refcnt);
+		refcount_inc(&map->refcnt);
 	return map;
 }
 
 void thread_map__put(struct thread_map *map)
 {
-	if (map && atomic_dec_and_test(&map->refcnt))
+	if (map && refcount_dec_and_test(&map->refcnt))
 		thread_map__delete(map);
 }
 
@@ -423,7 +425,7 @@ static void thread_map__copy_event(struct thread_map *threads,
 		threads->map[i].comm = strndup(event->entries[i].comm, 16);
 	}
 
-	atomic_set(&threads->refcnt, 1);
+	refcount_set(&threads->refcnt, 1);
 }
 
 struct thread_map *thread_map__new_event(struct thread_map_event *event)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index ea0ef08c6303..bd34d7a0b9fa 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -3,7 +3,7 @@
 
 #include <sys/types.h>
 #include <stdio.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 struct thread_map_data {
 	pid_t    pid;
@@ -11,7 +11,7 @@ struct thread_map_data {
 };
 
 struct thread_map {
-	atomic_t refcnt;
+	refcount_t refcnt;
 	int nr;
 	struct thread_map_data map[];
 };
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index d1b21c72206d..5b5d0214debd 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -117,3 +117,28 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp)
 
 	return false;
 }
+
+int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
+{
+	u64  sec = timestamp / NSEC_PER_SEC;
+	u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC;
+
+	return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
+}
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+	struct timeval tv;
+	struct tm tm;
+	char dt[32];
+
+	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+		return -1;
+
+	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+		return -1;
+
+	scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+	return 0;
+}
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index c1f197c4af6c..8656be08513b 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -1,6 +1,9 @@
 #ifndef _TIME_UTILS_H_
 #define _TIME_UTILS_H_
 
+#include <stddef.h>
+#include <linux/types.h>
+
 struct perf_time_interval {
 	u64 start, end;
 };
@@ -11,4 +14,8 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr);
 
 bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp);
 
+int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+
+int fetch_current_timestamp(char *buf, size_t sz);
+
 #endif
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index ac2590a3de2d..829471a1c6d7 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,6 +40,7 @@ struct perf_tool {
 	event_op	mmap,
 			mmap2,
 			comm,
+			namespaces,
 			fork,
 			exit,
 			lost,
@@ -66,6 +67,7 @@ struct perf_tool {
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
+	bool		namespace_events;
 };
 
 #endif /* __PERF_TOOL_H */
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index b2940c88734a..9bdfb78a9a35 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -5,7 +5,7 @@
 #include <linux/types.h>
 #include <stddef.h>
 #include <stdbool.h>
-#include <termios.h>
+#include <sys/ioctl.h>
 
 struct perf_evlist;
 struct perf_evsel;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index de0078e21408..746bbee645d9 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -21,13 +21,14 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
 
+#include "sane_ctype.h"
+
 static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 27420159bf69..8a9a677f7576 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -192,7 +192,7 @@ static int read_ftrace_printk(struct pevent *pevent)
 	if (!size)
 		return 0;
 
-	buf = malloc(size);
+	buf = malloc(size + 1);
 	if (buf == NULL)
 		return -1;
 
@@ -201,6 +201,8 @@ static int read_ftrace_printk(struct pevent *pevent)
 		return -1;
 	}
 
+	buf[size] = '\0';
+
 	parse_ftrace_printk(pevent, buf, size);
 
 	free(buf);
diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c
new file mode 100644
index 000000000000..f6a2a3d117d5
--- /dev/null
+++ b/tools/perf/util/units.c
@@ -0,0 +1,39 @@
+#include "units.h"
+#include <inttypes.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+
+unsigned long convert_unit(unsigned long value, char *unit)
+{
+	*unit = ' ';
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'K';
+	}
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'M';
+	}
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'G';
+	}
+
+	return value;
+}
+
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+	char unit[4] = "BKMG";
+	int i = 0;
+
+	while (((n / 1024) > 1) && (i < 3)) {
+		n /= 1024;
+		i++;
+	}
+
+	return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h
new file mode 100644
index 000000000000..3ed7774afaa9
--- /dev/null
+++ b/tools/perf/util/units.h
@@ -0,0 +1,10 @@
+#ifndef PERF_UNIT_H
+#define PERF_UNIT_H
+
+#include <stddef.h>
+#include <linux/types.h>
+
+unsigned long convert_unit(unsigned long value, char *unit);
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
+
+#endif /* PERF_UNIT_H */
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 783a53fb7a4e..f90e11a555b2 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -12,6 +12,7 @@
 #include "event.h"
 #include "perf_regs.h"
 #include "callchain.h"
+#include "util.h"
 
 static char *debuginfo_path;
 
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 58328669ed16..4a2b269a7b3b 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -2,10 +2,12 @@
 #define __PERF_UNWIND_LIBDW_H
 
 #include <elfutils/libdwfl.h>
-#include "event.h"
-#include "thread.h"
 #include "unwind.h"
 
+struct machine;
+struct perf_sample;
+struct thread;
+
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg);
 
 struct unwind_info {
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index bfb9b7987692..f8455bed6e65 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -16,8 +16,10 @@
  */
 
 #include <elf.h>
+#include <errno.h>
 #include <gelf.h>
 #include <fcntl.h>
+#include <inttypes.h>
 #include <string.h>
 #include <unistd.h>
 #include <sys/mman.h>
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index 61fb1e90ff51..bfbdcc6198c9 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -1,10 +1,13 @@
 #ifndef __UNWIND_H
 #define __UNWIND_H
 
+#include <linux/compiler.h>
 #include <linux/types.h>
-#include "event.h"
-#include "symbol.h"
-#include "thread.h"
+
+struct map;
+struct perf_sample;
+struct symbol;
+struct thread;
 
 struct unwind_entry {
 	struct map	*map;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index d8b45cea54d0..6450c75a6f5b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -3,10 +3,11 @@
 #include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
+#include <sys/stat.h>
 #include <sys/utsname.h>
-#ifdef HAVE_BACKTRACE_SUPPORT
-#include <execinfo.h>
-#endif
+#include <dirent.h>
+#include <inttypes.h>
+#include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -17,24 +18,8 @@
 #include <linux/log2.h>
 #include <linux/time64.h>
 #include <unistd.h>
-#include "callchain.h"
 #include "strlist.h"
 
-#define CALLCHAIN_PARAM_DEFAULT			\
-	.mode		= CHAIN_GRAPH_ABS,	\
-	.min_percent	= 0.5,			\
-	.order		= ORDER_CALLEE,		\
-	.key		= CCKEY_FUNCTION,	\
-	.value		= CCVAL_PERCENT,	\
-
-struct callchain_param callchain_param = {
-	CALLCHAIN_PARAM_DEFAULT
-};
-
-struct callchain_param callchain_param_default = {
-	CALLCHAIN_PARAM_DEFAULT
-};
-
 /*
  * XXX We need to find a better place for these things...
  */
@@ -269,28 +254,6 @@ int copyfile(const char *from, const char *to)
 	return copyfile_mode(from, to, 0755);
 }
 
-unsigned long convert_unit(unsigned long value, char *unit)
-{
-	*unit = ' ';
-
-	if (value > 1000) {
-		value /= 1000;
-		*unit = 'K';
-	}
-
-	if (value > 1000) {
-		value /= 1000;
-		*unit = 'M';
-	}
-
-	if (value > 1000) {
-		value /= 1000;
-		*unit = 'G';
-	}
-
-	return value;
-}
-
 static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
 {
 	void *buf_start = buf;
@@ -372,42 +335,6 @@ int hex2u64(const char *ptr, u64 *long_val)
 	return p - ptr;
 }
 
-/* Obtain a backtrace and print it to stdout. */
-#ifdef HAVE_BACKTRACE_SUPPORT
-void dump_stack(void)
-{
-	void *array[16];
-	size_t size = backtrace(array, ARRAY_SIZE(array));
-	char **strings = backtrace_symbols(array, size);
-	size_t i;
-
-	printf("Obtained %zd stack frames.\n", size);
-
-	for (i = 0; i < size; i++)
-		printf("%s\n", strings[i]);
-
-	free(strings);
-}
-#else
-void dump_stack(void) {}
-#endif
-
-void sighandler_dump_stack(int sig)
-{
-	psignal(sig, "perf");
-	dump_stack();
-	signal(sig, SIG_DFL);
-	raise(sig);
-}
-
-int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
-{
-	u64  sec = timestamp / NSEC_PER_SEC;
-	u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC;
-
-	return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
-}
-
 unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
 {
 	struct parse_tag *i = tags;
@@ -435,108 +362,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
 	return (unsigned long) -1;
 }
 
-int get_stack_size(const char *str, unsigned long *_size)
-{
-	char *endptr;
-	unsigned long size;
-	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
-	size = strtoul(str, &endptr, 0);
-
-	do {
-		if (*endptr)
-			break;
-
-		size = round_up(size, sizeof(u64));
-		if (!size || size > max_size)
-			break;
-
-		*_size = size;
-		return 0;
-
-	} while (0);
-
-	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
-	       max_size, str);
-	return -1;
-}
-
-int parse_callchain_record(const char *arg, struct callchain_param *param)
-{
-	char *tok, *name, *saveptr = NULL;
-	char *buf;
-	int ret = -1;
-
-	/* We need buffer that we know we can write to. */
-	buf = malloc(strlen(arg) + 1);
-	if (!buf)
-		return -ENOMEM;
-
-	strcpy(buf, arg);
-
-	tok = strtok_r((char *)buf, ",", &saveptr);
-	name = tok ? : (char *)buf;
-
-	do {
-		/* Framepointer style */
-		if (!strncmp(name, "fp", sizeof("fp"))) {
-			if (!strtok_r(NULL, ",", &saveptr)) {
-				param->record_mode = CALLCHAIN_FP;
-				ret = 0;
-			} else
-				pr_err("callchain: No more arguments "
-				       "needed for --call-graph fp\n");
-			break;
-
-		/* Dwarf style */
-		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
-			const unsigned long default_stack_dump_size = 8192;
-
-			ret = 0;
-			param->record_mode = CALLCHAIN_DWARF;
-			param->dump_size = default_stack_dump_size;
-
-			tok = strtok_r(NULL, ",", &saveptr);
-			if (tok) {
-				unsigned long size = 0;
-
-				ret = get_stack_size(tok, &size);
-				param->dump_size = size;
-			}
-		} else if (!strncmp(name, "lbr", sizeof("lbr"))) {
-			if (!strtok_r(NULL, ",", &saveptr)) {
-				param->record_mode = CALLCHAIN_LBR;
-				ret = 0;
-			} else
-				pr_err("callchain: No more arguments "
-					"needed for --call-graph lbr\n");
-			break;
-		} else {
-			pr_err("callchain: Unknown --call-graph option "
-			       "value: %s\n", arg);
-			break;
-		}
-
-	} while (0);
-
-	free(buf);
-	return ret;
-}
-
-const char *get_filename_for_perf_kvm(void)
-{
-	const char *filename;
-
-	if (perf_host && !perf_guest)
-		filename = strdup("perf.data.host");
-	else if (!perf_host && perf_guest)
-		filename = strdup("perf.data.guest");
-	else
-		filename = strdup("perf.data.kvm");
-
-	return filename;
-}
-
 int perf_event_paranoid(void)
 {
 	int value;
@@ -696,7 +521,8 @@ const char *perf_tip(const char *dirpath)
 
 	tips = strlist__new("tips.txt", &conf);
 	if (tips == NULL)
-		return errno == ENOENT ? NULL : "Tip: get more memory! ;-p";
+		return errno == ENOENT ? NULL :
+			"Tip: check path of tips.txt or get more memory! ;-p";
 
 	if (strlist__nr_entries(tips) == 0)
 		goto out;
@@ -710,95 +536,3 @@ out:
 
 	return tip;
 }
-
-bool is_regular_file(const char *file)
-{
-	struct stat st;
-
-	if (stat(file, &st))
-		return false;
-
-	return S_ISREG(st.st_mode);
-}
-
-int fetch_current_timestamp(char *buf, size_t sz)
-{
-	struct timeval tv;
-	struct tm tm;
-	char dt[32];
-
-	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
-		return -1;
-
-	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
-		return -1;
-
-	scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
-
-	return 0;
-}
-
-void print_binary(unsigned char *data, size_t len,
-		  size_t bytes_per_line, print_binary_t printer,
-		  void *extra)
-{
-	size_t i, j, mask;
-
-	if (!printer)
-		return;
-
-	bytes_per_line = roundup_pow_of_two(bytes_per_line);
-	mask = bytes_per_line - 1;
-
-	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
-	for (i = 0; i < len; i++) {
-		if ((i & mask) == 0) {
-			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
-			printer(BINARY_PRINT_ADDR, i, extra);
-		}
-
-		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
-
-		if (((i & mask) == mask) || i == len - 1) {
-			for (j = 0; j < mask-(i & mask); j++)
-				printer(BINARY_PRINT_NUM_PAD, -1, extra);
-
-			printer(BINARY_PRINT_SEP, i, extra);
-			for (j = i & ~mask; j <= i; j++)
-				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
-			for (j = 0; j < mask-(i & mask); j++)
-				printer(BINARY_PRINT_CHAR_PAD, i, extra);
-			printer(BINARY_PRINT_LINE_END, -1, extra);
-		}
-	}
-	printer(BINARY_PRINT_DATA_END, -1, extra);
-}
-
-int is_printable_array(char *p, unsigned int len)
-{
-	unsigned int i;
-
-	if (!p || !len || p[len - 1] != 0)
-		return 0;
-
-	len--;
-
-	for (i = 0; i < len; i++) {
-		if (!isprint(p[i]) && !isspace(p[i]))
-			return 0;
-	}
-	return 1;
-}
-
-int unit_number__scnprintf(char *buf, size_t size, u64 n)
-{
-	char unit[4] = "BKMG";
-	int i = 0;
-
-	while (((n / 1024) > 1) && (i < 3)) {
-		n /= 1024;
-		i++;
-	}
-
-	return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
-}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c74708da8571..3852b6d3270a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -1,126 +1,21 @@
 #ifndef GIT_COMPAT_UTIL_H
 #define GIT_COMPAT_UTIL_H
 
-#ifndef FLEX_ARRAY
-/*
- * See if our compiler is known to support flexible array members.
- */
-#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)
-# define FLEX_ARRAY /* empty */
-#elif defined(__GNUC__)
-# if (__GNUC__ >= 3)
-#  define FLEX_ARRAY /* empty */
-# else
-#  define FLEX_ARRAY 0 /* older GNU extension */
-# endif
-#endif
-
-/*
- * Otherwise, default to safer but a bit wasteful traditional style
- */
-#ifndef FLEX_ARRAY
-# define FLEX_ARRAY 1
-#endif
-#endif
-
-#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
-
-#ifdef __GNUC__
-#define TYPEOF(x) (__typeof__(x))
-#else
-#define TYPEOF(x)
-#endif
-
-#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits))))
-#define HAS_MULTI_BITS(i)  ((i) & ((i) - 1))  /* checks if an integer has more than 1 bit set */
-
-/* Approximation of the length of the decimal representation of this type. */
-#define decimal_length(x)	((int)(sizeof(x) * 2.56 + 0.5) + 1)
-
 #define _ALL_SOURCE 1
 #define _BSD_SOURCE 1
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 #define HAS_BOOL
 
-#include <unistd.h>
-#include <stdio.h>
-#include <sys/stat.h>
-#include <sys/statfs.h>
 #include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
 #include <stdarg.h>
-#include <string.h>
-#include <term.h>
-#include <errno.h>
-#include <limits.h>
-#include <sys/param.h>
-#include <sys/types.h>
-#include <dirent.h>
-#include <sys/time.h>
-#include <time.h>
-#include <signal.h>
-#include <fnmatch.h>
-#include <assert.h>
-#include <regex.h>
-#include <utime.h>
-#include <sys/wait.h>
-#include <poll.h>
-#include <sys/socket.h>
-#include <sys/ioctl.h>
-#include <inttypes.h>
-#include <linux/kernel.h>
 #include <linux/types.h>
-#include <sys/ttydefaults.h>
-#include <api/fs/tracing_path.h>
-#include <termios.h>
-#include <linux/bitops.h>
-#include <termios.h>
-#include "strlist.h"
 
-extern const char *graph_line;
-extern const char *graph_dotted_line;
-extern const char *spaces;
-extern const char *dots;
 extern char buildid_dir[];
 
-/* On most systems <limits.h> would have given us this, but
- * not on some systems (e.g. GNU/Hurd).
- */
-#ifndef PATH_MAX
-#define PATH_MAX 4096
-#endif
-
-#ifndef PRIuMAX
-#define PRIuMAX "llu"
-#endif
-
-#ifndef PRIu32
-#define PRIu32 "u"
-#endif
-
-#ifndef PRIx32
-#define PRIx32 "x"
-#endif
-
-#ifndef PATH_SEP
-#define PATH_SEP ':'
-#endif
-
-#ifndef STRIP_EXTENSION
-#define STRIP_EXTENSION ""
-#endif
-
-#ifndef has_dos_drive_prefix
-#define has_dos_drive_prefix(path) 0
-#endif
-
-#ifndef is_dir_sep
-#define is_dir_sep(c) ((c) == '/')
-#endif
-
 #ifdef __GNUC__
 #define NORETURN __attribute__((__noreturn__))
 #else
@@ -143,22 +38,6 @@ void set_warning_routine(void (*routine)(const char *err, va_list params));
 int prefixcmp(const char *str, const char *prefix);
 void set_buildid_dir(const char *dir);
 
-#ifdef __GLIBC_PREREQ
-#if __GLIBC_PREREQ(2, 1)
-#define HAVE_STRCHRNUL
-#endif
-#endif
-
-#ifndef HAVE_STRCHRNUL
-#define strchrnul gitstrchrnul
-static inline char *gitstrchrnul(const char *s, int c)
-{
-	while (*s && *s != c)
-		s++;
-	return (char *)s;
-}
-#endif
-
 static inline void *zalloc(size_t size)
 {
 	return calloc(1, size);
@@ -166,47 +45,8 @@ static inline void *zalloc(size_t size)
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
 
-/* Sane ctype - no locale, and works with signed chars */
-#undef isascii
-#undef isspace
-#undef isdigit
-#undef isxdigit
-#undef isalpha
-#undef isprint
-#undef isalnum
-#undef islower
-#undef isupper
-#undef tolower
-#undef toupper
-
-extern unsigned char sane_ctype[256];
-#define GIT_SPACE		0x01
-#define GIT_DIGIT		0x02
-#define GIT_ALPHA		0x04
-#define GIT_GLOB_SPECIAL	0x08
-#define GIT_REGEX_SPECIAL	0x10
-#define GIT_PRINT_EXTRA		0x20
-#define GIT_PRINT		0x3E
-#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
-#define isascii(x) (((x) & ~0x7f) == 0)
-#define isspace(x) sane_istest(x,GIT_SPACE)
-#define isdigit(x) sane_istest(x,GIT_DIGIT)
-#define isxdigit(x)	\
-	(sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G')
-#define isalpha(x) sane_istest(x,GIT_ALPHA)
-#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
-#define isprint(x) sane_istest(x,GIT_PRINT)
-#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
-#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
-#define tolower(x) sane_case((unsigned char)(x), 0x20)
-#define toupper(x) sane_case((unsigned char)(x), 0)
-
-static inline int sane_case(int x, int high)
-{
-	if (sane_istest(x, GIT_ALPHA))
-		x = (x & ~0x20) | high;
-	return x;
-}
+struct dirent;
+struct strlist;
 
 int mkdir_p(char *path, mode_t mode);
 int rm_rf(const char *path);
@@ -216,19 +56,6 @@ int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
-s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
-bool strglobmatch(const char *str, const char *pat);
-bool strglobmatch_nocase(const char *str, const char *pat);
-bool strlazymatch(const char *str, const char *pat);
-static inline bool strisglob(const char *str)
-{
-	return strpbrk(str, "*?[") != NULL;
-}
-int strtailcmp(const char *s1, const char *s2);
-char *strxfrchar(char *s, char from, char to);
-unsigned long convert_unit(unsigned long value, char *unit);
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, void *buf, size_t n);
 
@@ -236,23 +63,9 @@ struct perf_event_attr;
 
 void event_attr_init(struct perf_event_attr *attr);
 
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
-char *ltrim(char *s);
-char *rtrim(char *s);
-
-static inline char *trim(char *s)
-{
-	return ltrim(rtrim(s));
-}
-
-void dump_stack(void);
-void sighandler_dump_stack(int sig);
-
 extern unsigned int page_size;
 extern int cacheline_size;
 extern int sysctl_perf_event_max_stack;
@@ -265,63 +78,13 @@ struct parse_tag {
 
 unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
 
-#define SRCLINE_UNKNOWN  ((char *) "??:0")
-
-static inline int path__join(char *bf, size_t size,
-			     const char *path1, const char *path2)
-{
-	return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
-}
-
-static inline int path__join3(char *bf, size_t size,
-			      const char *path1, const char *path2,
-			      const char *path3)
-{
-	return scnprintf(bf, size, "%s%s%s%s%s",
-			 path1, path1[0] ? "/" : "",
-			 path2, path2[0] ? "/" : "", path3);
-}
-
-struct dso;
-struct symbol;
-
-extern bool srcline_full_filename;
-char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym);
-char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym, bool unwind_inlines);
-void free_srcline(char *srcline);
-
 int perf_event_paranoid(void);
 
 void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
-const char *get_filename_for_perf_kvm(void);
 bool find_process(const char *name);
 
-#ifdef HAVE_ZLIB_SUPPORT
-int gzip_decompress_to_file(const char *input, int output_fd);
-#endif
-
-#ifdef HAVE_LZMA_SUPPORT
-int lzma_decompress_to_file(const char *input, int output_fd);
-#endif
-
-char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints);
-
-static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints)
-{
-	return asprintf_expr_inout_ints(var, true, nints, ints);
-}
-
-static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints)
-{
-	return asprintf_expr_inout_ints(var, false, nints, ints);
-}
-
-int get_stack_size(const char *str, unsigned long *_size);
-
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
 #define KVER_VERSION(x)		(((x) >> 16) & 0xff)
@@ -331,37 +94,9 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
 const char *perf_tip(const char *dirpath);
-bool is_regular_file(const char *file);
-int fetch_current_timestamp(char *buf, size_t sz);
-
-enum binary_printer_ops {
-	BINARY_PRINT_DATA_BEGIN,
-	BINARY_PRINT_LINE_BEGIN,
-	BINARY_PRINT_ADDR,
-	BINARY_PRINT_NUM_DATA,
-	BINARY_PRINT_NUM_PAD,
-	BINARY_PRINT_SEP,
-	BINARY_PRINT_CHAR_DATA,
-	BINARY_PRINT_CHAR_PAD,
-	BINARY_PRINT_LINE_END,
-	BINARY_PRINT_DATA_END,
-};
 
-typedef void (*print_binary_t)(enum binary_printer_ops,
-			       unsigned int val,
-			       void *extra);
-
-void print_binary(unsigned char *data, size_t len,
-		  size_t bytes_per_line, print_binary_t printer,
-		  void *extra);
-
-#if !defined(__GLIBC__) && !defined(__ANDROID__)
-extern int sched_getcpu(void);
+#ifndef HAVE_SCHED_GETCPU_SUPPORT
+int sched_getcpu(void);
 #endif
 
-int is_printable_array(char *p, unsigned int len);
-
-int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
-
-int unit_number__scnprintf(char *buf, size_t size, u64 n);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 5074be4ed467..5de2e15e2eda 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -1,4 +1,7 @@
+#include <inttypes.h>
+#include <stdio.h>
 #include <stdlib.h>
+#include <errno.h>
 
 #include "util.h"
 #include "values.h"
@@ -108,24 +111,45 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values,
 	return i;
 }
 
-static void perf_read_values__enlarge_counters(struct perf_read_values *values)
+static int perf_read_values__enlarge_counters(struct perf_read_values *values)
 {
-	int i;
+	char **countername;
+	int i, counters_max = values->counters_max * 2;
+	u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid));
+
+	if (!counterrawid) {
+		pr_debug("failed to enlarge read_values rawid array");
+		goto out_enomem;
+	}
 
-	values->counters_max *= 2;
-	values->counterrawid = realloc(values->counterrawid,
-				       values->counters_max * sizeof(*values->counterrawid));
-	values->countername = realloc(values->countername,
-				      values->counters_max * sizeof(*values->countername));
-	if (!values->counterrawid || !values->countername)
-		die("failed to enlarge read_values counters arrays");
+	countername = realloc(values->countername, counters_max * sizeof(*values->countername));
+	if (!countername) {
+		pr_debug("failed to enlarge read_values rawid array");
+		goto out_free_rawid;
+	}
 
 	for (i = 0; i < values->threads; i++) {
-		values->value[i] = realloc(values->value[i],
-					   values->counters_max * sizeof(**values->value));
-		if (!values->value[i])
-			die("failed to enlarge read_values counters arrays");
+		u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+
+		if (value) {
+			pr_debug("failed to enlarge read_values ->values array");
+			goto out_free_name;
+		}
+
+		values->value[i] = value;
 	}
+
+	values->counters_max = counters_max;
+	values->counterrawid = counterrawid;
+	values->countername  = countername;
+
+	return 0;
+out_free_name:
+	free(countername);
+out_free_rawid:
+	free(counterrawid);
+out_enomem:
+	return -ENOMEM;
 }
 
 static int perf_read_values__findnew_counter(struct perf_read_values *values,
@@ -137,8 +161,11 @@ static int perf_read_values__findnew_counter(struct perf_read_values *values,
 		if (values->counterrawid[i] == rawid)
 			return i;
 
-	if (values->counters == values->counters_max)
-		perf_read_values__enlarge_counters(values);
+	if (values->counters == values->counters_max) {
+		i = perf_read_values__enlarge_counters(values);
+		if (i)
+			return i;
+	}
 
 	i = values->counters++;
 	values->counterrawid[i] = rawid;
@@ -172,8 +199,10 @@ static void perf_read_values__display_pretty(FILE *fp,
 	int *counterwidth;
 
 	counterwidth = malloc(values->counters * sizeof(*counterwidth));
-	if (!counterwidth)
-		die("failed to allocate counterwidth array");
+	if (!counterwidth) {
+		fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n");
+		return;
+	}
 	tidwidth = 3;
 	pidwidth = 3;
 	for (j = 0; j < values->counters; j++)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 7bdcad484225..d3c39eec89a8 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -1,4 +1,4 @@
-
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index c10ba41ef3f6..7251fdbabced 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -1,5 +1,7 @@
 #include "xyarray.h"
 #include "util.h"
+#include <stdlib.h>
+#include <string.h>
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
 {
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 495a449fc25c..1329d843eb7b 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -4,6 +4,7 @@
 #include <sys/mman.h>
 #include <zlib.h>
 
+#include "util/compress.h"
 #include "util/util.h"
 #include "util/debug.h"
 
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 93b0aa74ca03..39c2c7d067bb 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -156,6 +156,7 @@ out:
 					 */
 			case 0x2C:	/* Westmere EP - Gulftown */
 				cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
+				break;
 			case 0x2A:	/* SNB */
 			case 0x2D:	/* SNB Xeon */
 			case 0x3A:	/* IVB */
diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile
new file mode 100644
index 000000000000..4d0ccc89e6c6
--- /dev/null
+++ b/tools/power/pm-graph/Makefile
@@ -0,0 +1,28 @@
+PREFIX		?= /usr
+DESTDIR		?=
+
+all:
+	@echo "Nothing to build"
+
+install :
+	install -d  $(DESTDIR)$(PREFIX)/lib/pm-graph
+	install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph
+	install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph
+
+	ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py $(DESTDIR)$(PREFIX)/bin/bootgraph
+	ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py $(DESTDIR)$(PREFIX)/bin/sleepgraph
+
+	install -d  $(DESTDIR)$(PREFIX)/share/man/man8
+	install bootgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
+	install sleepgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
+
+uninstall :
+	rm $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8
+	rm $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8
+
+	rm $(DESTDIR)$(PREFIX)/bin/bootgraph
+	rm $(DESTDIR)$(PREFIX)/bin/sleepgraph
+
+	rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py
+	rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py
+	rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph
diff --git a/tools/power/pm-graph/analyze_boot.py b/tools/power/pm-graph/analyze_boot.py
new file mode 100755
index 000000000000..3e1dcbbf1adc
--- /dev/null
+++ b/tools/power/pm-graph/analyze_boot.py
@@ -0,0 +1,824 @@
+#!/usr/bin/python
+#
+# Tool for analyzing boot timing
+# Copyright (c) 2013, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+#
+# Authors:
+#	 Todd Brandt <todd.e.brandt@linux.intel.com>
+#
+# Description:
+#	 This tool is designed to assist kernel and OS developers in optimizing
+#	 their linux stack's boot time. It creates an html representation of
+#	 the kernel boot timeline up to the start of the init process.
+#
+
+# ----------------- LIBRARIES --------------------
+
+import sys
+import time
+import os
+import string
+import re
+import platform
+import shutil
+from datetime import datetime, timedelta
+from subprocess import call, Popen, PIPE
+import analyze_suspend as aslib
+
+# ----------------- CLASSES --------------------
+
+# Class: SystemValues
+# Description:
+#	 A global, single-instance container used to
+#	 store system values and test parameters
+class SystemValues(aslib.SystemValues):
+	title = 'BootGraph'
+	version = 2.0
+	hostname = 'localhost'
+	testtime = ''
+	kernel = ''
+	dmesgfile = ''
+	ftracefile = ''
+	htmlfile = 'bootgraph.html'
+	outfile = ''
+	phoronix = False
+	addlogs = False
+	useftrace = False
+	usedevsrc = True
+	suspendmode = 'boot'
+	max_graph_depth = 2
+	graph_filter = 'do_one_initcall'
+	reboot = False
+	manual = False
+	iscronjob = False
+	timeformat = '%.6f'
+	def __init__(self):
+		if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ):
+			self.phoronix = True
+			self.addlogs = True
+			self.outfile = os.environ['LOG_FILE']
+			self.htmlfile = os.environ['LOG_FILE']
+		self.hostname = platform.node()
+		self.testtime = datetime.now().strftime('%Y-%m-%d_%H:%M:%S')
+		if os.path.exists('/proc/version'):
+			fp = open('/proc/version', 'r')
+			val = fp.read().strip()
+			fp.close()
+			self.kernel = self.kernelVersion(val)
+		else:
+			self.kernel = 'unknown'
+	def kernelVersion(self, msg):
+		return msg.split()[2]
+	def kernelParams(self):
+		cmdline = 'initcall_debug log_buf_len=32M'
+		if self.useftrace:
+			cmdline += ' trace_buf_size=128M trace_clock=global '\
+			'trace_options=nooverwrite,funcgraph-abstime,funcgraph-cpu,'\
+			'funcgraph-duration,funcgraph-proc,funcgraph-tail,'\
+			'nofuncgraph-overhead,context-info,graph-time '\
+			'ftrace=function_graph '\
+			'ftrace_graph_max_depth=%d '\
+			'ftrace_graph_filter=%s' % \
+				(self.max_graph_depth, self.graph_filter)
+		return cmdline
+	def setGraphFilter(self, val):
+		fp = open(self.tpath+'available_filter_functions')
+		master = fp.read().split('\n')
+		fp.close()
+		for i in val.split(','):
+			func = i.strip()
+			if func not in master:
+				doError('function "%s" not available for ftrace' % func)
+		self.graph_filter = val
+	def cronjobCmdString(self):
+		cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0])
+		args = iter(sys.argv[1:])
+		for arg in args:
+			if arg in ['-h', '-v', '-cronjob', '-reboot']:
+				continue
+			elif arg in ['-o', '-dmesg', '-ftrace', '-filter']:
+				args.next()
+				continue
+			cmdline += ' '+arg
+		if self.graph_filter != 'do_one_initcall':
+			cmdline += ' -filter "%s"' % self.graph_filter
+		cmdline += ' -o "%s"' % os.path.abspath(self.htmlfile)
+		return cmdline
+	def manualRebootRequired(self):
+		cmdline = self.kernelParams()
+		print 'To generate a new timeline manually, follow these steps:\n'
+		print '1. Add the CMDLINE string to your kernel command line.'
+		print '2. Reboot the system.'
+		print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n'
+		print 'CMDLINE="%s"' % cmdline
+		sys.exit()
+
+sysvals = SystemValues()
+
+# Class: Data
+# Description:
+#	 The primary container for test data.
+class Data(aslib.Data):
+	dmesg = {}  # root data structure
+	start = 0.0 # test start
+	end = 0.0   # test end
+	dmesgtext = []   # dmesg text file in memory
+	testnumber = 0
+	idstr = ''
+	html_device_id = 0
+	valid = False
+	initstart = 0.0
+	boottime = ''
+	phases = ['boot']
+	do_one_initcall = False
+	def __init__(self, num):
+		self.testnumber = num
+		self.idstr = 'a'
+		self.dmesgtext = []
+		self.dmesg = {
+			'boot': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, 'color': '#dddddd'}
+		}
+	def deviceTopology(self):
+		return ''
+	def newAction(self, phase, name, start, end, ret, ulen):
+		# new device callback for a specific phase
+		self.html_device_id += 1
+		devid = '%s%d' % (self.idstr, self.html_device_id)
+		list = self.dmesg[phase]['list']
+		length = -1.0
+		if(start >= 0 and end >= 0):
+			length = end - start
+		i = 2
+		origname = name
+		while(name in list):
+			name = '%s[%d]' % (origname, i)
+			i += 1
+		list[name] = {'name': name, 'start': start, 'end': end,
+			'pid': 0, 'length': length, 'row': 0, 'id': devid,
+			'ret': ret, 'ulen': ulen }
+		return name
+	def deviceMatch(self, cg):
+		if cg.end - cg.start == 0:
+			return True
+		list = self.dmesg['boot']['list']
+		for devname in list:
+			dev = list[devname]
+			if cg.name == 'do_one_initcall':
+				if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0):
+					dev['ftrace'] = cg
+					self.do_one_initcall = True
+					return True
+			else:
+				if(cg.start > dev['start'] and cg.end < dev['end']):
+					if 'ftraces' not in dev:
+						dev['ftraces'] = []
+					dev['ftraces'].append(cg)
+					return True
+		return False
+
+# ----------------- FUNCTIONS --------------------
+
+# Function: loadKernelLog
+# Description:
+#	 Load a raw kernel log from dmesg
+def loadKernelLog():
+	data = Data(0)
+	data.dmesg['boot']['start'] = data.start = ktime = 0.0
+	sysvals.stamp = {
+		'time': datetime.now().strftime('%B %d %Y, %I:%M:%S %p'),
+		'host': sysvals.hostname,
+		'mode': 'boot', 'kernel': ''}
+
+	devtemp = dict()
+	if(sysvals.dmesgfile):
+		lf = open(sysvals.dmesgfile, 'r')
+	else:
+		lf = Popen('dmesg', stdout=PIPE).stdout
+	for line in lf:
+		line = line.replace('\r\n', '')
+		idx = line.find('[')
+		if idx > 1:
+			line = line[idx:]
+		m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
+		if(not m):
+			continue
+		ktime = float(m.group('ktime'))
+		if(ktime > 120):
+			break
+		msg = m.group('msg')
+		data.end = data.initstart = ktime
+		data.dmesgtext.append(line)
+		if(ktime == 0.0 and re.match('^Linux version .*', msg)):
+			if(not sysvals.stamp['kernel']):
+				sysvals.stamp['kernel'] = sysvals.kernelVersion(msg)
+			continue
+		m = re.match('.* setting system clock to (?P<t>.*) UTC.*', msg)
+		if(m):
+			bt = datetime.strptime(m.group('t'), '%Y-%m-%d %H:%M:%S')
+			bt = bt - timedelta(seconds=int(ktime))
+			data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S')
+			sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p')
+			continue
+		m = re.match('^calling *(?P<f>.*)\+.*', msg)
+		if(m):
+			devtemp[m.group('f')] = ktime
+			continue
+		m = re.match('^initcall *(?P<f>.*)\+.* returned (?P<r>.*) after (?P<t>.*) usecs', msg)
+		if(m):
+			data.valid = True
+			f, r, t = m.group('f', 'r', 't')
+			if(f in devtemp):
+				data.newAction('boot', f, devtemp[f], ktime, int(r), int(t))
+				data.end = ktime
+				del devtemp[f]
+			continue
+		if(re.match('^Freeing unused kernel memory.*', msg)):
+			break
+
+	data.dmesg['boot']['end'] = data.end
+	lf.close()
+	return data
+
+# Function: loadTraceLog
+# Description:
+#	 Check if trace is available and copy to a temp file
+def loadTraceLog(data):
+	# load the data to a temp file if none given
+	if not sysvals.ftracefile:
+		lib = aslib.sysvals
+		aslib.rootCheck(True)
+		if not lib.verifyFtrace():
+			doError('ftrace not available')
+		if lib.fgetVal('current_tracer').strip() != 'function_graph':
+			doError('ftrace not configured for a boot callgraph')
+		sysvals.ftracefile = '/tmp/boot_ftrace.%s.txt' % os.getpid()
+		call('cat '+lib.tpath+'trace > '+sysvals.ftracefile, shell=True)
+	if not sysvals.ftracefile:
+		doError('No trace data available')
+
+	# parse the trace log
+	ftemp = dict()
+	tp = aslib.TestProps()
+	tp.setTracerType('function_graph')
+	tf = open(sysvals.ftracefile, 'r')
+	for line in tf:
+		if line[0] == '#':
+			continue
+		m = re.match(tp.ftrace_line_fmt, line.strip())
+		if(not m):
+			continue
+		m_time, m_proc, m_pid, m_msg, m_dur = \
+			m.group('time', 'proc', 'pid', 'msg', 'dur')
+		if float(m_time) > data.end:
+			break
+		if(m_time and m_pid and m_msg):
+			t = aslib.FTraceLine(m_time, m_msg, m_dur)
+			pid = int(m_pid)
+		else:
+			continue
+		if t.fevent or t.fkprobe:
+			continue
+		key = (m_proc, pid)
+		if(key not in ftemp):
+			ftemp[key] = []
+			ftemp[key].append(aslib.FTraceCallGraph(pid))
+		cg = ftemp[key][-1]
+		if(cg.addLine(t)):
+			ftemp[key].append(aslib.FTraceCallGraph(pid))
+	tf.close()
+
+	# add the callgraph data to the device hierarchy
+	for key in ftemp:
+		proc, pid = key
+		for cg in ftemp[key]:
+			if len(cg.list) < 1 or cg.invalid:
+				continue
+			if(not cg.postProcess()):
+				print('Sanity check failed for %s-%d' % (proc, pid))
+				continue
+			# match cg data to devices
+			if not data.deviceMatch(cg):
+				print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end)
+
+# Function: colorForName
+# Description:
+#	 Generate a repeatable color from a list for a given name
+def colorForName(name):
+	list = [
+		('c1', '#ec9999'),
+		('c2', '#ffc1a6'),
+		('c3', '#fff0a6'),
+		('c4', '#adf199'),
+		('c5', '#9fadea'),
+		('c6', '#a699c1'),
+		('c7', '#ad99b4'),
+		('c8', '#eaffea'),
+		('c9', '#dcecfb'),
+		('c10', '#ffffea')
+	]
+	i = 0
+	total = 0
+	count = len(list)
+	while i < len(name):
+		total += ord(name[i])
+		i += 1
+	return list[total % count]
+
+def cgOverview(cg, minlen):
+	stats = dict()
+	large = []
+	for l in cg.list:
+		if l.fcall and l.depth == 1:
+			if l.length >= minlen:
+				large.append(l)
+			if l.name not in stats:
+				stats[l.name] = [0, 0.0]
+			stats[l.name][0] += (l.length * 1000.0)
+			stats[l.name][1] += 1
+	return (large, stats)
+
+# Function: createBootGraph
+# Description:
+#	 Create the output html file from the resident test data
+# Arguments:
+#	 testruns: array of Data objects from parseKernelLog or parseTraceLog
+# Output:
+#	 True if the html file was created, false if it failed
+def createBootGraph(data, embedded):
+	# html function templates
+	html_srccall = '<div id={6} title="{5}" class="srccall" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{0}</div>\n'
+	html_timetotal = '<table class="time1">\n<tr>'\
+		'<td class="blue">Time from Kernel Boot to start of User Mode: <b>{0} ms</b></td>'\
+		'</tr>\n</table>\n'
+
+	# device timeline
+	devtl = aslib.Timeline(100, 20)
+
+	# write the test title and general info header
+	devtl.createHeader(sysvals, 'noftrace')
+
+	# Generate the header for this timeline
+	t0 = data.start
+	tMax = data.end
+	tTotal = tMax - t0
+	if(tTotal == 0):
+		print('ERROR: No timeline data')
+		return False
+	boot_time = '%.0f'%(tTotal*1000)
+	devtl.html += html_timetotal.format(boot_time)
+
+	# determine the maximum number of rows we need to draw
+	phase = 'boot'
+	list = data.dmesg[phase]['list']
+	devlist = []
+	for devname in list:
+		d = aslib.DevItem(0, phase, list[devname])
+		devlist.append(d)
+	devtl.getPhaseRows(devlist)
+	devtl.calcTotalRows()
+
+	# draw the timeline background
+	devtl.createZoomBox()
+	boot = data.dmesg[phase]
+	length = boot['end']-boot['start']
+	left = '%.3f' % (((boot['start']-t0)*100.0)/tTotal)
+	width = '%.3f' % ((length*100.0)/tTotal)
+	devtl.html += devtl.html_tblock.format(phase, left, width, devtl.scaleH)
+	devtl.html += devtl.html_phase.format('0', '100', \
+		'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
+		'white', '')
+
+	# draw the device timeline
+	num = 0
+	devstats = dict()
+	for devname in sorted(list):
+		cls, color = colorForName(devname)
+		dev = list[devname]
+		info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0,
+			dev['ulen']/1000.0, dev['ret'])
+		devstats[dev['id']] = {'info':info}
+		dev['color'] = color
+		height = devtl.phaseRowHeight(0, phase, dev['row'])
+		top = '%.6f' % ((dev['row']*height) + devtl.scaleH)
+		left = '%.6f' % (((dev['start']-t0)*100)/tTotal)
+		width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal)
+		length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
+		devtl.html += devtl.html_device.format(dev['id'],
+			devname+length+'kernel_mode', left, top, '%.3f'%height,
+			width, devname, ' '+cls, '')
+		rowtop = devtl.phaseRowTop(0, phase, dev['row'])
+		height = '%.6f' % (devtl.rowH / 2)
+		top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2))
+		if data.do_one_initcall:
+			if('ftrace' not in dev):
+				continue
+			cg = dev['ftrace']
+			large, stats = cgOverview(cg, 0.001)
+			devstats[dev['id']]['fstat'] = stats
+			for l in large:
+				left = '%f' % (((l.time-t0)*100)/tTotal)
+				width = '%f' % (l.length*100/tTotal)
+				title = '%s (%0.3fms)' % (l.name, l.length * 1000.0)
+				devtl.html += html_srccall.format(l.name, left,
+					top, height, width, title, 'x%d'%num)
+				num += 1
+			continue
+		if('ftraces' not in dev):
+			continue
+		for cg in dev['ftraces']:
+			left = '%f' % (((cg.start-t0)*100)/tTotal)
+			width = '%f' % ((cg.end-cg.start)*100/tTotal)
+			cglen = (cg.end - cg.start) * 1000.0
+			title = '%s (%0.3fms)' % (cg.name, cglen)
+			cg.id = 'x%d' % num
+			devtl.html += html_srccall.format(cg.name, left,
+				top, height, width, title, dev['id']+cg.id)
+			num += 1
+
+	# draw the time scale, try to make the number of labels readable
+	devtl.createTimeScale(t0, tMax, tTotal, phase)
+	devtl.html += '</div>\n'
+
+	# timeline is finished
+	devtl.html += '</div>\n</div>\n'
+
+	if(sysvals.outfile == sysvals.htmlfile):
+		hf = open(sysvals.htmlfile, 'a')
+	else:
+		hf = open(sysvals.htmlfile, 'w')
+
+	# add the css if this is not an embedded run
+	extra = '\
+		.c1 {background:rgba(209,0,0,0.4);}\n\
+		.c2 {background:rgba(255,102,34,0.4);}\n\
+		.c3 {background:rgba(255,218,33,0.4);}\n\
+		.c4 {background:rgba(51,221,0,0.4);}\n\
+		.c5 {background:rgba(17,51,204,0.4);}\n\
+		.c6 {background:rgba(34,0,102,0.4);}\n\
+		.c7 {background:rgba(51,0,68,0.4);}\n\
+		.c8 {background:rgba(204,255,204,0.4);}\n\
+		.c9 {background:rgba(169,208,245,0.4);}\n\
+		.c10 {background:rgba(255,255,204,0.4);}\n\
+		.vt {transform:rotate(-60deg);transform-origin:0 0;}\n\
+		table.fstat {table-layout:fixed;padding:150px 15px 0 0;font-size:10px;column-width:30px;}\n\
+		.fstat th {width:55px;}\n\
+		.fstat td {text-align:left;width:35px;}\n\
+		.srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
+		.srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n'
+	if(not embedded):
+		aslib.addCSS(hf, sysvals, 1, False, extra)
+
+	# write the device timeline
+	hf.write(devtl.html)
+
+	# add boot specific html
+	statinfo = 'var devstats = {\n'
+	for n in sorted(devstats):
+		statinfo += '\t"%s": [\n\t\t"%s",\n' % (n, devstats[n]['info'])
+		if 'fstat' in devstats[n]:
+			funcs = devstats[n]['fstat']
+			for f in sorted(funcs, key=funcs.get, reverse=True):
+				if funcs[f][0] < 0.01 and len(funcs) > 10:
+					break
+				statinfo += '\t\t"%f|%s|%d",\n' % (funcs[f][0], f, funcs[f][1])
+		statinfo += '\t],\n'
+	statinfo += '};\n'
+	html = \
+		'<div id="devicedetailtitle"></div>\n'\
+		'<div id="devicedetail" style="display:none;">\n'\
+		'<div id="devicedetail0">\n'\
+		'<div id="kernel_mode" class="phaselet" style="left:0%;width:100%;background:#DDDDDD"></div>\n'\
+		'</div>\n</div>\n'\
+		'<script type="text/javascript">\n'+statinfo+\
+		'</script>\n'
+	hf.write(html)
+
+	# add the callgraph html
+	if(sysvals.usecallgraph):
+		aslib.addCallgraphs(sysvals, hf, data)
+
+	# add the dmesg log as a hidden div
+	if sysvals.addlogs:
+		hf.write('<div id="dmesglog" style="display:none;">\n')
+		for line in data.dmesgtext:
+			line = line.replace('<', '&lt').replace('>', '&gt')
+			hf.write(line)
+		hf.write('</div>\n')
+
+	if(not embedded):
+		# write the footer and close
+		aslib.addScriptCode(hf, [data])
+		hf.write('</body>\n</html>\n')
+	else:
+		# embedded out will be loaded in a page, skip the js
+		hf.write('<div id=bounds style=display:none>%f,%f</div>' % \
+			(data.start*1000, data.initstart*1000))
+	hf.close()
+	return True
+
+# Function: updateCron
+# Description:
+#    (restore=False) Set the tool to run automatically on reboot
+#    (restore=True) Restore the original crontab
+def updateCron(restore=False):
+	if not restore:
+		sysvals.rootUser(True)
+	crondir = '/var/spool/cron/crontabs/'
+	cronfile = crondir+'root'
+	backfile = crondir+'root-analyze_boot-backup'
+	if not os.path.exists(crondir):
+		doError('%s not found' % crondir)
+	out = Popen(['which', 'crontab'], stdout=PIPE).stdout.read()
+	if not out:
+		doError('crontab not found')
+	# on restore: move the backup cron back into place
+	if restore:
+		if os.path.exists(backfile):
+			shutil.move(backfile, cronfile)
+		return
+	# backup current cron and install new one with reboot
+	if os.path.exists(cronfile):
+		shutil.move(cronfile, backfile)
+	else:
+		fp = open(backfile, 'w')
+		fp.close()
+	res = -1
+	try:
+		fp = open(backfile, 'r')
+		op = open(cronfile, 'w')
+		for line in fp:
+			if '@reboot' not in line:
+				op.write(line)
+				continue
+		fp.close()
+		op.write('@reboot python %s\n' % sysvals.cronjobCmdString())
+		op.close()
+		res = call('crontab %s' % cronfile, shell=True)
+	except Exception, e:
+		print 'Exception: %s' % str(e)
+		shutil.move(backfile, cronfile)
+		res = -1
+	if res != 0:
+		doError('crontab failed')
+
+# Function: updateGrub
+# Description:
+#	 update grub.cfg for all kernels with our parameters
+def updateGrub(restore=False):
+	# call update-grub on restore
+	if restore:
+		try:
+			call(['update-grub'], stderr=PIPE, stdout=PIPE,
+				env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'})
+		except Exception, e:
+			print 'Exception: %s\n' % str(e)
+		return
+	# verify we can do this
+	sysvals.rootUser(True)
+	grubfile = '/etc/default/grub'
+	if not os.path.exists(grubfile):
+		print 'ERROR: Unable to set the kernel parameters via grub.\n'
+		sysvals.manualRebootRequired()
+	out = Popen(['which', 'update-grub'], stdout=PIPE).stdout.read()
+	if not out:
+		print 'ERROR: Unable to set the kernel parameters via grub.\n'
+		sysvals.manualRebootRequired()
+
+	# extract the option and create a grub config without it
+	tgtopt = 'GRUB_CMDLINE_LINUX_DEFAULT'
+	cmdline = ''
+	tempfile = '/etc/default/grub.analyze_boot'
+	shutil.move(grubfile, tempfile)
+	res = -1
+	try:
+		fp = open(tempfile, 'r')
+		op = open(grubfile, 'w')
+		cont = False
+		for line in fp:
+			line = line.strip()
+			if len(line) == 0 or line[0] == '#':
+				continue
+			opt = line.split('=')[0].strip()
+			if opt == tgtopt:
+				cmdline = line.split('=', 1)[1].strip('\\')
+				if line[-1] == '\\':
+					cont = True
+			elif cont:
+				cmdline += line.strip('\\')
+				if line[-1] != '\\':
+					cont = False
+			else:
+				op.write('%s\n' % line)
+		fp.close()
+		# if the target option value is in quotes, strip them
+		sp = '"'
+		val = cmdline.strip()
+		if val[0] == '\'' or val[0] == '"':
+			sp = val[0]
+			val = val.strip(sp)
+		cmdline = val
+		# append our cmd line options
+		if len(cmdline) > 0:
+			cmdline += ' '
+		cmdline += sysvals.kernelParams()
+		# write out the updated target option
+		op.write('\n%s=%s%s%s\n' % (tgtopt, sp, cmdline, sp))
+		op.close()
+		res = call('update-grub')
+		os.remove(grubfile)
+	except Exception, e:
+		print 'Exception: %s' % str(e)
+		res = -1
+	# cleanup
+	shutil.move(tempfile, grubfile)
+	if res != 0:
+		doError('update-grub failed')
+
+# Function: doError
+# Description:
+#	 generic error function for catastrphic failures
+# Arguments:
+#	 msg: the error message to print
+#	 help: True if printHelp should be called after, False otherwise
+def doError(msg, help=False):
+	if help == True:
+		printHelp()
+	print 'ERROR: %s\n' % msg
+	sys.exit()
+
+# Function: printHelp
+# Description:
+#	 print out the help text
+def printHelp():
+	print('')
+	print('%s v%.1f' % (sysvals.title, sysvals.version))
+	print('Usage: bootgraph <options> <command>')
+	print('')
+	print('Description:')
+	print('  This tool reads in a dmesg log of linux kernel boot and')
+	print('  creates an html representation of the boot timeline up to')
+	print('  the start of the init process.')
+	print('')
+	print('  If no specific command is given the tool reads the current dmesg')
+	print('  and/or ftrace log and outputs bootgraph.html')
+	print('')
+	print('Options:')
+	print('  -h            Print this help text')
+	print('  -v            Print the current tool version')
+	print('  -addlogs      Add the dmesg log to the html output')
+	print('  -o file       Html timeline name (default: bootgraph.html)')
+	print(' [advanced]')
+	print('  -f            Use ftrace to add function detail (default: disabled)')
+	print('  -callgraph    Add callgraph detail, can be very large (default: disabled)')
+	print('  -maxdepth N   limit the callgraph data to N call levels (default: 2)')
+	print('  -mincg ms     Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
+	print('  -timeprec N   Number of significant digits in timestamps (0:S, 3:ms, [6:us])')
+	print('  -expandcg     pre-expand the callgraph data in the html output (default: disabled)')
+	print('  -filter list  Limit ftrace to comma-delimited list of functions (default: do_one_initcall)')
+	print(' [commands]')
+	print('  -reboot       Reboot the machine automatically and generate a new timeline')
+	print('  -manual       Show the requirements to generate a new timeline manually')
+	print('  -dmesg file   Load a stored dmesg file (used with -ftrace)')
+	print('  -ftrace file  Load a stored ftrace file (used with -dmesg)')
+	print('  -flistall     Print all functions capable of being captured in ftrace')
+	print('')
+	return True
+
+# ----------------- MAIN --------------------
+# exec start (skipped if script is loaded as library)
+if __name__ == '__main__':
+	# loop through the command line arguments
+	cmd = ''
+	simplecmds = ['-updategrub', '-flistall']
+	args = iter(sys.argv[1:])
+	for arg in args:
+		if(arg == '-h'):
+			printHelp()
+			sys.exit()
+		elif(arg == '-v'):
+			print("Version %.1f" % sysvals.version)
+			sys.exit()
+		elif(arg in simplecmds):
+			cmd = arg[1:]
+		elif(arg == '-f'):
+			sysvals.useftrace = True
+		elif(arg == '-callgraph'):
+			sysvals.useftrace = True
+			sysvals.usecallgraph = True
+		elif(arg == '-mincg'):
+			sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0)
+		elif(arg == '-timeprec'):
+			sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6))
+		elif(arg == '-maxdepth'):
+			sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000)
+		elif(arg == '-filter'):
+			try:
+				val = args.next()
+			except:
+				doError('No filter functions supplied', True)
+			aslib.rootCheck(True)
+			sysvals.setGraphFilter(val)
+		elif(arg == '-ftrace'):
+			try:
+				val = args.next()
+			except:
+				doError('No ftrace file supplied', True)
+			if(os.path.exists(val) == False):
+				doError('%s does not exist' % val)
+			sysvals.ftracefile = val
+		elif(arg == '-addlogs'):
+			sysvals.addlogs = True
+		elif(arg == '-expandcg'):
+			sysvals.cgexp = True
+		elif(arg == '-dmesg'):
+			try:
+				val = args.next()
+			except:
+				doError('No dmesg file supplied', True)
+			if(os.path.exists(val) == False):
+				doError('%s does not exist' % val)
+			if(sysvals.htmlfile == val or sysvals.outfile == val):
+				doError('Output filename collision')
+			sysvals.dmesgfile = val
+		elif(arg == '-o'):
+			try:
+				val = args.next()
+			except:
+				doError('No HTML filename supplied', True)
+			if(sysvals.dmesgfile == val or sysvals.ftracefile == val):
+				doError('Output filename collision')
+			sysvals.htmlfile = val
+		elif(arg == '-reboot'):
+			if sysvals.iscronjob:
+				doError('-reboot and -cronjob are incompatible')
+			sysvals.reboot = True
+		elif(arg == '-manual'):
+			sysvals.reboot = True
+			sysvals.manual = True
+		# remaining options are only for cron job use
+		elif(arg == '-cronjob'):
+			sysvals.iscronjob = True
+			if sysvals.reboot:
+				doError('-reboot and -cronjob are incompatible')
+		else:
+			doError('Invalid argument: '+arg, True)
+
+	if cmd != '':
+		if cmd == 'updategrub':
+			updateGrub()
+		elif cmd == 'flistall':
+			sysvals.getFtraceFilterFunctions(False)
+		sys.exit()
+
+	# update grub, setup a cronjob, and reboot
+	if sysvals.reboot:
+		if not sysvals.manual:
+			updateGrub()
+			updateCron()
+			call('reboot')
+		else:
+			sysvals.manualRebootRequired()
+		sys.exit()
+
+	# disable the cronjob
+	if sysvals.iscronjob:
+		updateCron(True)
+		updateGrub(True)
+
+	data = loadKernelLog()
+	if sysvals.useftrace:
+		loadTraceLog(data)
+		if sysvals.iscronjob:
+			try:
+				sysvals.fsetVal('0', 'tracing_on')
+			except:
+				pass
+
+	if(sysvals.outfile and sysvals.phoronix):
+		fp = open(sysvals.outfile, 'w')
+		fp.write('pass %s initstart %.3f end %.3f boot %s\n' %
+			(data.valid, data.initstart*1000, data.end*1000, data.boottime))
+		fp.close()
+	if(not data.valid):
+		if sysvals.dmesgfile:
+			doError('No initcall data found in %s' % sysvals.dmesgfile)
+		else:
+			doError('No initcall data found, is initcall_debug enabled?')
+
+	print('          Host: %s' % sysvals.hostname)
+	print('     Test time: %s' % sysvals.testtime)
+	print('     Boot time: %s' % data.boottime)
+	print('Kernel Version: %s' % sysvals.kernel)
+	print('  Kernel start: %.3f' % (data.start * 1000))
+	print('    init start: %.3f' % (data.initstart * 1000))
+
+	createBootGraph(data, sysvals.phoronix)
diff --git a/scripts/analyze_suspend.py b/tools/power/pm-graph/analyze_suspend.py
index 20cdb2bc1dae..a9206e67fc1f 100755
--- a/scripts/analyze_suspend.py
+++ b/tools/power/pm-graph/analyze_suspend.py
@@ -12,10 +12,6 @@
 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 # more details.
 #
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
 # Authors:
 #	 Todd Brandt <todd.e.brandt@linux.intel.com>
 #
@@ -23,7 +19,7 @@
 #	 Home Page
 #	   https://01.org/suspendresume
 #	 Source repo
-#	   https://github.com/01org/suspendresume
+#	   https://github.com/01org/pm-graph
 #
 # Description:
 #	 This tool is designed to assist kernel and OS developers in optimizing
@@ -71,14 +67,16 @@ from subprocess import call, Popen, PIPE
 #	 A global, single-instance container used to
 #	 store system values and test parameters
 class SystemValues:
+	title = 'SleepGraph'
+	version = '4.6'
 	ansi = False
-	version = '4.5'
 	verbose = False
 	addlogs = False
 	mindevlen = 0.0
 	mincglen = 0.0
 	cgphase = ''
 	cgtest = -1
+	max_graph_depth = 0
 	callloopmaxgap = 0.0001
 	callloopmaxlen = 0.005
 	srgap = 0
@@ -106,8 +104,8 @@ class SystemValues:
 	ftracefile = ''
 	htmlfile = ''
 	embedded = False
-	rtcwake = False
-	rtcwaketime = 10
+	rtcwake = True
+	rtcwaketime = 15
 	rtcpath = ''
 	devicefilter = []
 	stamp = 0
@@ -235,6 +233,12 @@ class SystemValues:
 			self.rtcpath = rtc
 		if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()):
 			self.ansi = True
+	def rootUser(self, fatal=False):
+		if 'USER' in os.environ and os.environ['USER'] == 'root':
+			return True
+		if fatal:
+			doError('This command must be run as root')
+		return False
 	def setPrecision(self, num):
 		if num < 0 or num > 6:
 			return
@@ -564,7 +568,7 @@ class SystemValues:
 		self.fsetVal('global', 'trace_clock')
 		# set trace buffer to a huge value
 		self.fsetVal('nop', 'current_tracer')
-		self.fsetVal('100000', 'buffer_size_kb')
+		self.fsetVal('131073', 'buffer_size_kb')
 		# go no further if this is just a status check
 		if testing:
 			return
@@ -583,7 +587,7 @@ class SystemValues:
 			self.fsetVal('nofuncgraph-overhead', 'trace_options')
 			self.fsetVal('context-info', 'trace_options')
 			self.fsetVal('graph-time', 'trace_options')
-			self.fsetVal('0', 'max_graph_depth')
+			self.fsetVal('%d' % self.max_graph_depth, 'max_graph_depth')
 			cf = ['dpm_run_callback']
 			if(self.usetraceeventsonly):
 				cf += ['dpm_prepare', 'dpm_complete']
@@ -639,6 +643,12 @@ class SystemValues:
 		return '\x1B[%d;40m%s\x1B[m' % (color, str)
 
 sysvals = SystemValues()
+suspendmodename = {
+	'freeze': 'Freeze (S0)',
+	'standby': 'Standby (S1)',
+	'mem': 'Suspend (S3)',
+	'disk': 'Hibernate (S4)'
+}
 
 # Class: DevProps
 # Description:
@@ -1013,6 +1023,8 @@ class Data:
 		tmp = dict()
 		for devname in list:
 			dev = list[devname]
+			if dev['length'] == 0:
+				continue
 			tmp[dev['start']] = devname
 		for t in sorted(tmp):
 			slist.append(tmp[t])
@@ -1477,12 +1489,14 @@ class FTraceLine:
 #	 Each instance is tied to a single device in a single phase, and is
 #	 comprised of an ordered list of FTraceLine objects
 class FTraceCallGraph:
+	id = ''
 	start = -1.0
 	end = -1.0
 	list = []
 	invalid = False
 	depth = 0
 	pid = 0
+	name = ''
 	def __init__(self, pid):
 		self.start = -1.0
 		self.end = -1.0
@@ -1631,9 +1645,17 @@ class FTraceCallGraph:
 				return True
 		return False
 	def postProcess(self, debug=False):
+		if len(self.list) > 0:
+			self.name = self.list[0].name
 		stack = dict()
 		cnt = 0
+		last = 0
 		for l in self.list:
+			# ftrace bug: reported duration is not reliable
+			# check each leaf and clip it at max possible length
+			if(last and last.freturn and last.fcall):
+				if last.length > l.time - last.time:
+					last.length = l.time - last.time
 			if(l.fcall and not l.freturn):
 				stack[l.depth] = l
 				cnt += 1
@@ -1643,11 +1665,12 @@ class FTraceCallGraph:
 						print 'Post Process Error: Depth missing'
 						l.debugPrint()
 					return False
-				# transfer total time from return line to call line
-				stack[l.depth].length = l.length
+				# calculate call length from call/return lines
+				stack[l.depth].length = l.time - stack[l.depth].time
 				stack.pop(l.depth)
 				l.length = 0
 				cnt -= 1
+			last = l
 		if(cnt == 0):
 			# trace caught the whole call tree
 			return True
@@ -1664,8 +1687,8 @@ class FTraceCallGraph:
 			'dpm_prepare': 'suspend_prepare',
 			'dpm_complete': 'resume_complete'
 		}
-		if(self.list[0].name in borderphase):
-			p = borderphase[self.list[0].name]
+		if(self.name in borderphase):
+			p = borderphase[self.name]
 			list = data.dmesg[p]['list']
 			for devname in list:
 				dev = list[devname]
@@ -1690,7 +1713,7 @@ class FTraceCallGraph:
 				break
 		return found
 	def newActionFromFunction(self, data):
-		name = self.list[0].name
+		name = self.name
 		if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']:
 			return
 		fs = self.start
@@ -1710,7 +1733,7 @@ class FTraceCallGraph:
 			phase, myname = out
 			data.dmesg[phase]['list'][myname]['ftrace'] = self
 	def debugPrint(self):
-		print('[%f - %f] %s (%d)') % (self.start, self.end, self.list[0].name, self.pid)
+		print('[%f - %f] %s (%d)') % (self.start, self.end, self.name, self.pid)
 		for l in self.list:
 			if(l.freturn and l.fcall):
 				print('%f (%02d): %s(); (%.3f us)' % (l.time, \
@@ -1738,7 +1761,7 @@ class DevItem:
 #	 A container for a device timeline which calculates
 #	 all the html properties to display it correctly
 class Timeline:
-	html = {}
+	html = ''
 	height = 0	# total timeline height
 	scaleH = 20	# timescale (top) row height
 	rowH = 30	# device row height
@@ -1746,14 +1769,28 @@ class Timeline:
 	rows = 0	# total timeline rows
 	rowlines = dict()
 	rowheight = dict()
+	html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
+	html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
+	html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n'
+	html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
 	def __init__(self, rowheight, scaleheight):
 		self.rowH = rowheight
 		self.scaleH = scaleheight
-		self.html = {
-			'header': '',
-			'timeline': '',
-			'legend': '',
-		}
+		self.html = ''
+	def createHeader(self, sv, suppress=''):
+		if(not sv.stamp['time']):
+			return
+		self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \
+			% (sv.title, sv.version)
+		if sv.logmsg and 'log' not in suppress:
+			self.html += '<button id="showtest" class="logbtn">log</button>'
+		if sv.addlogs and 'dmesg' not in suppress:
+			self.html += '<button id="showdmesg" class="logbtn">dmesg</button>'
+		if sv.addlogs and sv.ftracefile and 'ftrace' not in suppress:
+			self.html += '<button id="showftrace" class="logbtn">ftrace</button>'
+		headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
+		self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'],
+			sv.stamp['mode'], sv.stamp['time'])
 	# Function: getDeviceRows
 	# Description:
 	#    determine how may rows the device funcs will take
@@ -1880,10 +1917,8 @@ class Timeline:
 				break
 			top += self.rowheight[test][phase][i]
 		return top
-	# Function: calcTotalRows
-	# Description:
-	#	 Calculate the heights and offsets for the header and rows
 	def calcTotalRows(self):
+		# Calculate the heights and offsets for the header and rows
 		maxrows = 0
 		standardphases = []
 		for t in self.rowlines:
@@ -1901,6 +1936,20 @@ class Timeline:
 		for t, p in standardphases:
 			for i in sorted(self.rowheight[t][p]):
 				self.rowheight[t][p][i] = self.bodyH/len(self.rowlines[t][p])
+	def createZoomBox(self, mode='command', testcount=1):
+		# Create bounding box, add buttons
+		html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
+		html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
+		html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail{0}</button>'
+		html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
+		if mode != 'command':
+			if testcount > 1:
+				self.html += html_devlist2
+				self.html += html_devlist1.format('1')
+			else:
+				self.html += html_devlist1.format('')
+		self.html += html_zoombox
+		self.html += html_timeline.format('dmesg', self.height)
 	# Function: createTimeScale
 	# Description:
 	#	 Create the timescale for a timeline block
@@ -1913,7 +1962,7 @@ class Timeline:
 	#	 The html code needed to display the time scale
 	def createTimeScale(self, m0, mMax, tTotal, mode):
 		timescale = '<div class="t" style="right:{0}%">{1}</div>\n'
-		rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">Resume</div>\n'
+		rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">{0}</div>\n'
 		output = '<div class="timescale">\n'
 		# set scale for timeline
 		mTotal = mMax - m0
@@ -1926,21 +1975,20 @@ class Timeline:
 		divEdge = (mTotal - tS*(divTotal-1))*100/mTotal
 		for i in range(divTotal):
 			htmlline = ''
-			if(mode == 'resume'):
-				pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
-				val = '%0.fms' % (float(i)*tS*1000)
-				htmlline = timescale.format(pos, val)
-				if(i == 0):
-					htmlline = rline
-			else:
+			if(mode == 'suspend'):
 				pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge)
 				val = '%0.fms' % (float(i-divTotal+1)*tS*1000)
 				if(i == divTotal - 1):
-					val = 'Suspend'
+					val = mode
+				htmlline = timescale.format(pos, val)
+			else:
+				pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
+				val = '%0.fms' % (float(i)*tS*1000)
 				htmlline = timescale.format(pos, val)
+				if(i == 0):
+					htmlline = rline.format(mode)
 			output += htmlline
-		output += '</div>\n'
-		return output
+		self.html += output+'</div>\n'
 
 # Class: TestProps
 # Description:
@@ -2009,7 +2057,7 @@ class ProcessMonitor:
 				val['kern'] = kern
 			if ujiff > 0 or kjiff > 0:
 				running[pid] = ujiff + kjiff
-		result = process.wait()
+		process.wait()
 		out = ''
 		for pid in running:
 			jiffies = running[pid]
@@ -2071,26 +2119,6 @@ def parseStamp(line, data):
 	if not sysvals.stamp:
 		sysvals.stamp = data.stamp
 
-# Function: diffStamp
-# Description:
-#	compare the host, kernel, and mode fields in 3 stamps
-# Arguments:
-#	 stamp1: string array with mode, kernel, and host
-#	 stamp2: string array with mode, kernel, and host
-# Return:
-#	True if stamps differ, False if they're the same
-def diffStamp(stamp1, stamp2):
-	if 'host' in stamp1 and 'host' in stamp2:
-		if stamp1['host'] != stamp2['host']:
-			return True
-	if 'kernel' in stamp1 and 'kernel' in stamp2:
-		if stamp1['kernel'] != stamp2['kernel']:
-			return True
-	if 'mode' in stamp1 and 'mode' in stamp2:
-		if stamp1['mode'] != stamp2['mode']:
-			return True
-	return False
-
 # Function: doesTraceLogHaveTraceEvents
 # Description:
 #	 Quickly determine if the ftrace log has some or all of the trace events
@@ -2722,7 +2750,7 @@ def parseTraceLog():
 			# create blocks for orphan cg data
 			for sortkey in sorted(sortlist):
 				cg = sortlist[sortkey]
-				name = cg.list[0].name
+				name = cg.name
 				if sysvals.isCallgraphFunc(name):
 					vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
 					cg.newActionFromFunction(data)
@@ -3100,149 +3128,154 @@ def parseKernelLog(data):
 	data.fixupInitcallsThatDidntReturn()
 	return True
 
+def callgraphHTML(sv, hf, num, cg, title, color, devid):
+	html_func_top = '<article id="{0}" class="atop" style="background:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
+	html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n'
+	html_func_end = '</article>\n'
+	html_func_leaf = '<article>{0} {1}</article>\n'
+
+	cgid = devid
+	if cg.id:
+		cgid += cg.id
+	cglen = (cg.end - cg.start) * 1000
+	if cglen < sv.mincglen:
+		return num
+
+	fmt = '<r>(%.3f ms @ '+sv.timeformat+' to '+sv.timeformat+')</r>'
+	flen = fmt % (cglen, cg.start, cg.end)
+	hf.write(html_func_top.format(cgid, color, num, title, flen))
+	num += 1
+	for line in cg.list:
+		if(line.length < 0.000000001):
+			flen = ''
+		else:
+			fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>'
+			flen = fmt % (line.length*1000, line.time)
+		if(line.freturn and line.fcall):
+			hf.write(html_func_leaf.format(line.name, flen))
+		elif(line.freturn):
+			hf.write(html_func_end)
+		else:
+			hf.write(html_func_start.format(num, line.name, flen))
+			num += 1
+	hf.write(html_func_end)
+	return num
+
+def addCallgraphs(sv, hf, data):
+	hf.write('<section id="callgraphs" class="callgraph">\n')
+	# write out the ftrace data converted to html
+	num = 0
+	for p in data.phases:
+		if sv.cgphase and p != sv.cgphase:
+			continue
+		list = data.dmesg[p]['list']
+		for devname in data.sortedDevices(p):
+			dev = list[devname]
+			color = 'white'
+			if 'color' in data.dmesg[p]:
+				color = data.dmesg[p]['color']
+			if 'color' in dev:
+				color = dev['color']
+			name = devname
+			if(devname in sv.devprops):
+				name = sv.devprops[devname].altName(devname)
+			if sv.suspendmode in suspendmodename:
+				name += ' '+p
+			if('ftrace' in dev):
+				cg = dev['ftrace']
+				num = callgraphHTML(sv, hf, num, cg,
+					name, color, dev['id'])
+			if('ftraces' in dev):
+				for cg in dev['ftraces']:
+					num = callgraphHTML(sv, hf, num, cg,
+						name+' &rarr; '+cg.name, color, dev['id'])
+
+	hf.write('\n\n    </section>\n')
+
 # Function: createHTMLSummarySimple
 # Description:
 #	 Create summary html file for a series of tests
 # Arguments:
 #	 testruns: array of Data objects from parseTraceLog
-def createHTMLSummarySimple(testruns, htmlfile):
-	# print out the basic summary of all the tests
-	hf = open(htmlfile, 'w')
-
+def createHTMLSummarySimple(testruns, htmlfile, folder):
 	# write the html header first (html head, css code, up to body start)
 	html = '<!DOCTYPE html>\n<html>\n<head>\n\
 	<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
-	<title>AnalyzeSuspend Summary</title>\n\
+	<title>SleepGraph Summary</title>\n\
 	<style type=\'text/css\'>\n\
-		body {overflow-y: scroll;}\n\
-		.stamp {width: 100%;text-align:center;background-color:#495E09;line-height:30px;color:white;font: 25px Arial;}\n\
+		.stamp {width: 100%;text-align:center;background:#888;line-height:30px;color:white;font: 25px Arial;}\n\
 		table {width:100%;border-collapse: collapse;}\n\
-		.summary {font: 22px Arial;border:1px solid;}\n\
-		th {border: 1px solid black;background-color:#A7C942;color:white;}\n\
-		td {text-align: center;}\n\
-		tr.alt td {background-color:#EAF2D3;}\n\
-		tr.avg td {background-color:#BDE34C;}\n\
-		a:link {color: #90B521;}\n\
-		a:visited {color: #495E09;}\n\
-		a:hover {color: #B1DF28;}\n\
-		a:active {color: #FFFFFF;}\n\
+		.summary {border:1px solid;}\n\
+		th {border: 1px solid black;background:#222;color:white;}\n\
+		td {font: 16px "Times New Roman";text-align: center;}\n\
+		tr.alt td {background:#ddd;}\n\
+		tr.avg td {background:#aaa;}\n\
 	</style>\n</head>\n<body>\n'
 
 	# group test header
-	count = len(testruns)
-	headline_stamp = '<div class="stamp">{0} {1} {2} {3} ({4} tests)</div>\n'
-	html += headline_stamp.format(sysvals.stamp['host'],
-		sysvals.stamp['kernel'], sysvals.stamp['mode'],
-		sysvals.stamp['time'], count)
-
-	# check to see if all the tests have the same value
-	stampcolumns = False
-	for data in testruns:
-		if diffStamp(sysvals.stamp, data.stamp):
-			stampcolumns = True
-			break
-
+	html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns))
 	th = '\t<th>{0}</th>\n'
 	td = '\t<td>{0}</td>\n'
-	tdlink = '\t<td><a href="{0}">Click Here</a></td>\n'
+	tdlink = '\t<td><a href="{0}">html</a></td>\n'
 
 	# table header
-	html += '<table class="summary">\n<tr>\n'
-	html += th.format("Test #")
-	if stampcolumns:
-		html += th.format("Hostname")
-		html += th.format("Kernel Version")
-		html += th.format("Suspend Mode")
-	html += th.format("Test Time")
-	html += th.format("Suspend Time")
-	html += th.format("Resume Time")
-	html += th.format("Detail")
-	html += '</tr>\n'
+	html += '<table class="summary">\n<tr>\n' + th.format('#') +\
+		th.format('Mode') + th.format('Host') + th.format('Kernel') +\
+		th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\
+		th.format('Detail') + '</tr>\n'
 
 	# test data, 1 row per test
-	sTimeAvg = 0.0
-	rTimeAvg = 0.0
-	num = 1
-	for data in testruns:
-		# data.end is the end of post_resume
-		resumeEnd = data.dmesg['resume_complete']['end']
+	avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\
+		'<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n'
+	sTimeAvg = rTimeAvg = 0.0
+	mode = ''
+	num = 0
+	for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'])):
+		if mode != data['mode']:
+			# test average line
+			if(num > 0):
+				sTimeAvg /= (num - 1)
+				rTimeAvg /= (num - 1)
+				html += avg.format('%d' % (num - 1), mode,
+					'%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
+			sTimeAvg = rTimeAvg = 0.0
+			mode = data['mode']
+			num = 1
+		# alternate row color
 		if num % 2 == 1:
 			html += '<tr class="alt">\n'
 		else:
 			html += '<tr>\n'
-
-		# test num
-		html += td.format("test %d" % num)
+		html += td.format("%d" % num)
 		num += 1
-		if stampcolumns:
-			# host name
-			val = "unknown"
-			if('host' in data.stamp):
-				val = data.stamp['host']
-			html += td.format(val)
-			# host kernel
+		# basic info
+		for item in ['mode', 'host', 'kernel', 'time']:
 			val = "unknown"
-			if('kernel' in data.stamp):
-				val = data.stamp['kernel']
+			if(item in data):
+				val = data[item]
 			html += td.format(val)
-			# suspend mode
-			val = "unknown"
-			if('mode' in data.stamp):
-				val = data.stamp['mode']
-			html += td.format(val)
-		# test time
-		val = "unknown"
-		if('time' in data.stamp):
-			val = data.stamp['time']
-		html += td.format(val)
 		# suspend time
-		sTime = (data.tSuspended - data.start)*1000
+		sTime = float(data['suspend'])
 		sTimeAvg += sTime
-		html += td.format("%3.3f ms" % sTime)
+		html += td.format('%.3f ms' % sTime)
 		# resume time
-		rTime = (resumeEnd - data.tResumed)*1000
+		rTime = float(data['resume'])
 		rTimeAvg += rTime
-		html += td.format("%3.3f ms" % rTime)
+		html += td.format('%.3f ms' % rTime)
 		# link to the output html
-		html += tdlink.format(data.outfile)
-
-		html += '</tr>\n'
-
-	# last line: test average
-	if(count > 0):
-		sTimeAvg /= count
-		rTimeAvg /= count
-	html += '<tr class="avg">\n'
-	html += td.format('Average') 	# name
-	if stampcolumns:
-		html += td.format('')			# host
-		html += td.format('')			# kernel
-		html += td.format('')			# mode
-	html += td.format('')			# time
-	html += td.format("%3.3f ms" % sTimeAvg)	# suspend time
-	html += td.format("%3.3f ms" % rTimeAvg)	# resume time
-	html += td.format('')			# output link
-	html += '</tr>\n'
+		html += tdlink.format(data['url']) + '</tr>\n'
+	# last test average line
+	if(num > 0):
+		sTimeAvg /= (num - 1)
+		rTimeAvg /= (num - 1)
+		html += avg.format('%d' % (num - 1), mode,
+			'%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
 
 	# flush the data to file
-	hf.write(html+'</table>\n')
-	hf.write('</body>\n</html>\n')
+	hf = open(htmlfile, 'w')
+	hf.write(html+'</table>\n</body>\n</html>\n')
 	hf.close()
 
-def htmlTitle():
-	modename = {
-		'freeze': 'Freeze (S0)',
-		'standby': 'Standby (S1)',
-		'mem': 'Suspend (S3)',
-		'disk': 'Hibernate (S4)'
-	}
-	kernel = sysvals.stamp['kernel']
-	host = sysvals.hostname[0].upper()+sysvals.hostname[1:]
-	mode = sysvals.suspendmode
-	if sysvals.suspendmode in modename:
-		mode = modename[sysvals.suspendmode]
-	return host+' '+mode+' '+kernel
-
 def ordinal(value):
 	suffix = 'th'
 	if value < 10 or value > 19:
@@ -3272,24 +3305,11 @@ def createHTML(testruns):
 			kerror = True
 		data.normalizeTime(testruns[-1].tSuspended)
 
-	x2changes = ['', 'absolute']
-	if len(testruns) > 1:
-		x2changes = ['1', 'relative']
 	# html function templates
-	headline_version = '<div class="version"><a href="https://01.org/suspendresume">AnalyzeSuspend v%s</a></div>' % sysvals.version
-	headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
-	html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail%s</button>' % x2changes[0]
-	html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
-	html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
-	html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
-	html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
-	html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
 	html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR&rarr;</div>\n'
 	html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n'
 	html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n'
-	html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background-color:{4}">{5}</div>\n'
-	html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
-	html_legend = '<div id="p{3}" class="square" style="left:{0}%;background-color:{1}">&nbsp;{2}</div>\n'
+	html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}">&nbsp;{2}</div>\n'
 	html_timetotal = '<table class="time1">\n<tr>'\
 		'<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\
 		'<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\
@@ -3311,20 +3331,18 @@ def createHTML(testruns):
 		'</tr>\n</table>\n'
 
 	# html format variables
-	hoverZ = 'z-index:8;'
-	if sysvals.usedevsrc:
-		hoverZ = ''
 	scaleH = 20
-	scaleTH = 20
 	if kerror:
 		scaleH = 40
-		scaleTH = 60
 
 	# device timeline
 	vprint('Creating Device Timeline...')
 
 	devtl = Timeline(30, scaleH)
 
+	# write the test title and general info header
+	devtl.createHeader(sysvals)
+
 	# Generate the header for this timeline
 	for data in testruns:
 		tTotal = data.end - data.start
@@ -3346,7 +3364,7 @@ def createHTML(testruns):
 			if(len(testruns) > 1):
 				testdesc = ordinal(data.testnumber+1)+' '+testdesc
 			thtml = html_timetotal3.format(run_time, testdesc)
-			devtl.html['header'] += thtml
+			devtl.html += thtml
 		elif data.fwValid:
 			suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0))
 			resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0))
@@ -3363,10 +3381,10 @@ def createHTML(testruns):
 			else:
 				thtml = html_timetotal2.format(suspend_time, low_time, \
 					resume_time, testdesc1, stitle, rtitle)
-			devtl.html['header'] += thtml
+			devtl.html += thtml
 			sftime = '%.3f'%(data.fwSuspend / 1000000.0)
 			rftime = '%.3f'%(data.fwResume / 1000000.0)
-			devtl.html['header'] += html_timegroups.format('%.3f'%sktime, \
+			devtl.html += html_timegroups.format('%.3f'%sktime, \
 				sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode)
 		else:
 			suspend_time = '%.3f' % sktime
@@ -3382,7 +3400,7 @@ def createHTML(testruns):
 			else:
 				thtml = html_timetotal2.format(suspend_time, low_time, \
 					resume_time, testdesc, stitle, rtitle)
-			devtl.html['header'] += thtml
+			devtl.html += thtml
 
 	# time scale for potentially multiple datasets
 	t0 = testruns[0].start
@@ -3429,15 +3447,8 @@ def createHTML(testruns):
 			devtl.getPhaseRows(threadlist, devtl.rows)
 	devtl.calcTotalRows()
 
-	# create bounding box, add buttons
-	if sysvals.suspendmode != 'command':
-		devtl.html['timeline'] += html_devlist1
-		if len(testruns) > 1:
-			devtl.html['timeline'] += html_devlist2
-	devtl.html['timeline'] += html_zoombox
-	devtl.html['timeline'] += html_timeline.format('dmesg', devtl.height)
-
 	# draw the full timeline
+	devtl.createZoomBox(sysvals.suspendmode, len(testruns))
 	phases = {'suspend':[],'resume':[]}
 	for phase in data.dmesg:
 		if 'resume' in phase:
@@ -3452,37 +3463,36 @@ def createHTML(testruns):
 			# draw suspend and resume blocks separately
 			bname = '%s%d' % (dir[0], data.testnumber)
 			if dir == 'suspend':
-				m0 = testruns[data.testnumber].start
-				mMax = testruns[data.testnumber].tSuspended
-				mTotal = mMax - m0
+				m0 = data.start
+				mMax = data.tSuspended
 				left = '%f' % (((m0-t0)*100.0)/tTotal)
 			else:
-				m0 = testruns[data.testnumber].tSuspended
-				mMax = testruns[data.testnumber].end
+				m0 = data.tSuspended
+				mMax = data.end
 				# in an x2 run, remove any gap between blocks
 				if len(testruns) > 1 and data.testnumber == 0:
 					mMax = testruns[1].start
-				mTotal = mMax - m0
 				left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal)
+			mTotal = mMax - m0
 			# if a timeline block is 0 length, skip altogether
 			if mTotal == 0:
 				continue
 			width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal)
-			devtl.html['timeline'] += html_tblock.format(bname, left, width, devtl.scaleH)
+			devtl.html += devtl.html_tblock.format(bname, left, width, devtl.scaleH)
 			for b in sorted(phases[dir]):
 				# draw the phase color background
 				phase = data.dmesg[b]
 				length = phase['end']-phase['start']
 				left = '%f' % (((phase['start']-m0)*100.0)/mTotal)
 				width = '%f' % ((length*100.0)/mTotal)
-				devtl.html['timeline'] += html_phase.format(left, width, \
+				devtl.html += devtl.html_phase.format(left, width, \
 					'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
 					data.dmesg[b]['color'], '')
 			for e in data.errorinfo[dir]:
 				# draw red lines for any kernel errors found
 				t, err = e
 				right = '%f' % (((mMax-t)*100.0)/mTotal)
-				devtl.html['timeline'] += html_error.format(right, err)
+				devtl.html += html_error.format(right, err)
 			for b in sorted(phases[dir]):
 				# draw the devices for this phase
 				phaselist = data.dmesg[b]['list']
@@ -3496,7 +3506,7 @@ def createHTML(testruns):
 					if 'htmlclass' in dev:
 						xtraclass = dev['htmlclass']
 					if 'color' in dev:
-						xtrastyle = 'background-color:%s;' % dev['color']
+						xtrastyle = 'background:%s;' % dev['color']
 					if(d in sysvals.devprops):
 						name = sysvals.devprops[d].altName(d)
 						xtraclass = sysvals.devprops[d].xtraClass()
@@ -3521,7 +3531,7 @@ def createHTML(testruns):
 							title += 'post_resume_process'
 					else:
 						title += b
-					devtl.html['timeline'] += html_device.format(dev['id'], \
+					devtl.html += devtl.html_device.format(dev['id'], \
 						title, left, top, '%.3f'%rowheight, width, \
 						d+drv, xtraclass, xtrastyle)
 					if('cpuexec' in dev):
@@ -3535,7 +3545,7 @@ def createHTML(testruns):
 							left = '%f' % (((start-m0)*100)/mTotal)
 							width = '%f' % ((end-start)*100/mTotal)
 							color = 'rgba(255, 0, 0, %f)' % j
-							devtl.html['timeline'] += \
+							devtl.html += \
 								html_cpuexec.format(left, top, height, width, color)
 					if('src' not in dev):
 						continue
@@ -3548,20 +3558,20 @@ def createHTML(testruns):
 						xtrastyle = ''
 						if e.color:
 							xtrastyle = 'background:%s;' % e.color
-						devtl.html['timeline'] += \
+						devtl.html += \
 							html_traceevent.format(e.title(), \
 								left, top, height, width, e.text(), '', xtrastyle)
 			# draw the time scale, try to make the number of labels readable
-			devtl.html['timeline'] += devtl.createTimeScale(m0, mMax, tTotal, dir)
-			devtl.html['timeline'] += '</div>\n'
+			devtl.createTimeScale(m0, mMax, tTotal, dir)
+			devtl.html += '</div>\n'
 
 	# timeline is finished
-	devtl.html['timeline'] += '</div>\n</div>\n'
+	devtl.html += '</div>\n</div>\n'
 
 	# draw a legend which describes the phases by color
 	if sysvals.suspendmode != 'command':
 		data = testruns[-1]
-		devtl.html['legend'] = '<div class="legend">\n'
+		devtl.html += '<div class="legend">\n'
 		pdelta = 100.0/len(data.phases)
 		pmargin = pdelta / 4.0
 		for phase in data.phases:
@@ -3571,127 +3581,41 @@ def createHTML(testruns):
 				id += tmp[1][0]
 			order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
 			name = string.replace(phase, '_', ' &nbsp;')
-			devtl.html['legend'] += html_legend.format(order, \
+			devtl.html += html_legend.format(order, \
 				data.dmesg[phase]['color'], name, id)
-		devtl.html['legend'] += '</div>\n'
+		devtl.html += '</div>\n'
 
 	hf = open(sysvals.htmlfile, 'w')
 
-	if not sysvals.cgexp:
-		cgchk = 'checked'
-		cgnchk = 'not(:checked)'
-	else:
-		cgchk = 'not(:checked)'
-		cgnchk = 'checked'
-
-	# write the html header first (html head, css code, up to body start)
-	html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
-	<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
-	<title>'+htmlTitle()+'</title>\n\
-	<style type=\'text/css\'>\n\
-		body {overflow-y:scroll;}\n\
-		.stamp {width:100%;text-align:center;background-color:gray;line-height:30px;color:white;font:25px Arial;}\n\
-		.callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
-		.callgraph article * {padding-left:28px;}\n\
-		h1 {color:black;font:bold 30px Times;}\n\
-		t0 {color:black;font:bold 30px Times;}\n\
-		t1 {color:black;font:30px Times;}\n\
-		t2 {color:black;font:25px Times;}\n\
-		t3 {color:black;font:20px Times;white-space:nowrap;}\n\
-		t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
-		cS {font:bold 13px Times;}\n\
-		table {width:100%;}\n\
-		.gray {background-color:rgba(80,80,80,0.1);}\n\
-		.green {background-color:rgba(204,255,204,0.4);}\n\
-		.purple {background-color:rgba(128,0,128,0.2);}\n\
-		.yellow {background-color:rgba(255,255,204,0.4);}\n\
-		.time1 {font:22px Arial;border:1px solid;}\n\
-		.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
-		td {text-align:center;}\n\
-		r {color:#500000;font:15px Tahoma;}\n\
-		n {color:#505050;font:15px Tahoma;}\n\
-		.tdhl {color:red;}\n\
-		.hide {display:none;}\n\
-		.pf {display:none;}\n\
-		.pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
-		.pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
-		.pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
-		.zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
-		.timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
-		.thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
-		.thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
-		.thread:hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
-		.thread.sec,.thread.sec:hover {background-color:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
-		.hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
-		.hover.sync {background-color:white;}\n\
-		.hover.bg,.hover.kth,.hover.sync,.hover.ps {background-color:white;}\n\
-		.jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
-		.traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
-		.traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
-		.phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
-		.phaselet {position:absolute;overflow:hidden;border:0px;text-align:center;height:100px;font-size:24px;}\n\
-		.t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
-		.err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
-		.legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
-		.legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
-		button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
-		.logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
-		.devlist {position:'+x2changes[1]+';width:190px;}\n\
-		a:link {color:white;text-decoration:none;}\n\
-		a:visited {color:white;}\n\
-		a:hover {color:white;}\n\
-		a:active {color:white;}\n\
-		.version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
-		#devicedetail {height:100px;box-shadow:5px 5px 20px black;}\n\
-		.tblock {position:absolute;height:100%;background-color:#ddd;}\n\
-		.tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
-		.bg {z-index:1;}\n\
-	</style>\n</head>\n<body>\n'
-
 	# no header or css if its embedded
 	if(sysvals.embedded):
 		hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' %
 			(data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \
 				data.fwSuspend/1000000, data.fwResume/1000000))
 	else:
-		hf.write(html_header)
-
-	# write the test title and general info header
-	if(sysvals.stamp['time'] != ""):
-		hf.write(headline_version)
-		if sysvals.logmsg:
-			hf.write('<button id="showtest" class="logbtn">log</button>')
-		if sysvals.addlogs and sysvals.dmesgfile:
-			hf.write('<button id="showdmesg" class="logbtn">dmesg</button>')
-		if sysvals.addlogs and sysvals.ftracefile:
-			hf.write('<button id="showftrace" class="logbtn">ftrace</button>')
-		hf.write(headline_stamp.format(sysvals.stamp['host'],
-			sysvals.stamp['kernel'], sysvals.stamp['mode'], \
-				sysvals.stamp['time']))
+		addCSS(hf, sysvals, len(testruns), kerror)
 
 	# write the device timeline
-	hf.write(devtl.html['header'])
-	hf.write(devtl.html['timeline'])
-	hf.write(devtl.html['legend'])
+	hf.write(devtl.html)
 	hf.write('<div id="devicedetailtitle"></div>\n')
 	hf.write('<div id="devicedetail" style="display:none;">\n')
 	# draw the colored boxes for the device detail section
 	for data in testruns:
 		hf.write('<div id="devicedetail%d">\n' % data.testnumber)
 		pscolor = 'linear-gradient(to top left, #ccc, #eee)'
-		hf.write(html_phaselet.format('pre_suspend_process', \
+		hf.write(devtl.html_phaselet.format('pre_suspend_process', \
 			'0', '0', pscolor))
 		for b in data.phases:
 			phase = data.dmesg[b]
 			length = phase['end']-phase['start']
 			left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal)
 			width = '%.3f' % ((length*100.0)/tTotal)
-			hf.write(html_phaselet.format(b, left, width, \
+			hf.write(devtl.html_phaselet.format(b, left, width, \
 				data.dmesg[b]['color']))
-		hf.write(html_phaselet.format('post_resume_process', \
+		hf.write(devtl.html_phaselet.format('post_resume_process', \
 			'0', '0', pscolor))
 		if sysvals.suspendmode == 'command':
-			hf.write(html_phaselet.format('cmdexec', '0', '0', pscolor))
+			hf.write(devtl.html_phaselet.format('cmdexec', '0', '0', pscolor))
 		hf.write('</div>\n')
 	hf.write('</div>\n')
 
@@ -3701,52 +3625,7 @@ def createHTML(testruns):
 	else:
 		data = testruns[-1]
 	if(sysvals.usecallgraph and not sysvals.embedded):
-		hf.write('<section id="callgraphs" class="callgraph">\n')
-		# write out the ftrace data converted to html
-		html_func_top = '<article id="{0}" class="atop" style="background-color:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
-		html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n'
-		html_func_end = '</article>\n'
-		html_func_leaf = '<article>{0} {1}</article>\n'
-		num = 0
-		for p in data.phases:
-			if sysvals.cgphase and p != sysvals.cgphase:
-				continue
-			list = data.dmesg[p]['list']
-			for devname in data.sortedDevices(p):
-				if('ftrace' not in list[devname]):
-					continue
-				devid = list[devname]['id']
-				cg = list[devname]['ftrace']
-				clen = (cg.end - cg.start) * 1000
-				if clen < sysvals.mincglen:
-					continue
-				fmt = '<r>(%.3f ms @ '+sysvals.timeformat+' to '+sysvals.timeformat+')</r>'
-				flen = fmt % (clen, cg.start, cg.end)
-				name = devname
-				if(devname in sysvals.devprops):
-					name = sysvals.devprops[devname].altName(devname)
-				if sysvals.suspendmode == 'command':
-					ftitle = name
-				else:
-					ftitle = name+' '+p
-				hf.write(html_func_top.format(devid, data.dmesg[p]['color'], \
-					num, ftitle, flen))
-				num += 1
-				for line in cg.list:
-					if(line.length < 0.000000001):
-						flen = ''
-					else:
-						fmt = '<n>(%.3f ms @ '+sysvals.timeformat+')</n>'
-						flen = fmt % (line.length*1000, line.time)
-					if(line.freturn and line.fcall):
-						hf.write(html_func_leaf.format(line.name, flen))
-					elif(line.freturn):
-						hf.write(html_func_end)
-					else:
-						hf.write(html_func_start.format(num, line.name, flen))
-						num += 1
-				hf.write(html_func_end)
-		hf.write('\n\n    </section>\n')
+		addCallgraphs(sysvals, hf, data)
 
 	# add the test log as a hidden div
 	if sysvals.logmsg:
@@ -3788,6 +3667,100 @@ def createHTML(testruns):
 	hf.close()
 	return True
 
+def addCSS(hf, sv, testcount=1, kerror=False, extra=''):
+	kernel = sv.stamp['kernel']
+	host = sv.hostname[0].upper()+sv.hostname[1:]
+	mode = sv.suspendmode
+	if sv.suspendmode in suspendmodename:
+		mode = suspendmodename[sv.suspendmode]
+	title = host+' '+mode+' '+kernel
+
+	# various format changes by flags
+	cgchk = 'checked'
+	cgnchk = 'not(:checked)'
+	if sv.cgexp:
+		cgchk = 'not(:checked)'
+		cgnchk = 'checked'
+
+	hoverZ = 'z-index:8;'
+	if sv.usedevsrc:
+		hoverZ = ''
+
+	devlistpos = 'absolute'
+	if testcount > 1:
+		devlistpos = 'relative'
+
+	scaleTH = 20
+	if kerror:
+		scaleTH = 60
+
+	# write the html header first (html head, css code, up to body start)
+	html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
+	<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
+	<title>'+title+'</title>\n\
+	<style type=\'text/css\'>\n\
+		body {overflow-y:scroll;}\n\
+		.stamp {width:100%;text-align:center;background:gray;line-height:30px;color:white;font:25px Arial;}\n\
+		.callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
+		.callgraph article * {padding-left:28px;}\n\
+		h1 {color:black;font:bold 30px Times;}\n\
+		t0 {color:black;font:bold 30px Times;}\n\
+		t1 {color:black;font:30px Times;}\n\
+		t2 {color:black;font:25px Times;}\n\
+		t3 {color:black;font:20px Times;white-space:nowrap;}\n\
+		t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
+		cS {font:bold 13px Times;}\n\
+		table {width:100%;}\n\
+		.gray {background:rgba(80,80,80,0.1);}\n\
+		.green {background:rgba(204,255,204,0.4);}\n\
+		.purple {background:rgba(128,0,128,0.2);}\n\
+		.yellow {background:rgba(255,255,204,0.4);}\n\
+		.blue {background:rgba(169,208,245,0.4);}\n\
+		.time1 {font:22px Arial;border:1px solid;}\n\
+		.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
+		td {text-align:center;}\n\
+		r {color:#500000;font:15px Tahoma;}\n\
+		n {color:#505050;font:15px Tahoma;}\n\
+		.tdhl {color:red;}\n\
+		.hide {display:none;}\n\
+		.pf {display:none;}\n\
+		.pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
+		.pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
+		.pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
+		.zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
+		.timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
+		.thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
+		.thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
+		.thread:hover {background:white;border:1px solid red;'+hoverZ+'}\n\
+		.thread.sec,.thread.sec:hover {background:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
+		.hover {background:white;border:1px solid red;'+hoverZ+'}\n\
+		.hover.sync {background:white;}\n\
+		.hover.bg,.hover.kth,.hover.sync,.hover.ps {background:white;}\n\
+		.jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
+		.traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
+		.traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
+		.phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
+		.phaselet {float:left;overflow:hidden;border:0px;text-align:center;min-height:100px;font-size:24px;}\n\
+		.t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
+		.err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
+		.legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
+		.legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
+		button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
+		.logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
+		.devlist {position:'+devlistpos+';width:190px;}\n\
+		a:link {color:white;text-decoration:none;}\n\
+		a:visited {color:white;}\n\
+		a:hover {color:white;}\n\
+		a:active {color:white;}\n\
+		.version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
+		#devicedetail {min-height:100px;box-shadow:5px 5px 20px black;}\n\
+		.tblock {position:absolute;height:100%;background:#ddd;}\n\
+		.tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
+		.bg {z-index:1;}\n\
+'+extra+'\
+	</style>\n</head>\n<body>\n'
+	hf.write(html_header)
+
 # Function: addScriptCode
 # Description:
 #	 Adds the javascript code to the output html
@@ -3809,7 +3782,7 @@ def addScriptCode(hf, testruns):
 	'	var resolution = -1;\n'\
 	'	var dragval = [0, 0];\n'\
 	'	function redrawTimescale(t0, tMax, tS) {\n'\
-	'		var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;"><cS>&larr;R</cS></div>\';\n'\
+	'		var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;">\';\n'\
 	'		var tTotal = tMax - t0;\n'\
 	'		var list = document.getElementsByClassName("tblock");\n'\
 	'		for (var i = 0; i < list.length; i++) {\n'\
@@ -3824,19 +3797,23 @@ def addScriptCode(hf, testruns):
 	'			var pos = 0.0, val = 0.0;\n'\
 	'			for (var j = 0; j < divTotal; j++) {\n'\
 	'				var htmlline = "";\n'\
-	'				if(list[i].id[5] == "r") {\n'\
-	'					pos = 100 - (((j)*tS*100)/mTotal);\n'\
-	'					val = (j)*tS;\n'\
-	'					htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
-	'					if(j == 0)\n'\
-	'						htmlline = rline;\n'\
-	'				} else {\n'\
+	'				var mode = list[i].id[5];\n'\
+	'				if(mode == "s") {\n'\
 	'					pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\
 	'					val = (j-divTotal+1)*tS;\n'\
 	'					if(j == divTotal - 1)\n'\
 	'						htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S&rarr;</cS></div>\';\n'\
 	'					else\n'\
 	'						htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
+	'				} else {\n'\
+	'					pos = 100 - (((j)*tS*100)/mTotal);\n'\
+	'					val = (j)*tS;\n'\
+	'					htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
+	'					if(j == 0)\n'\
+	'						if(mode == "r")\n'\
+	'							htmlline = rline+"<cS>&larr;R</cS></div>";\n'\
+	'						else\n'\
+	'							htmlline = rline+"<cS>0ms</div>";\n'\
 	'				}\n'\
 	'				html += htmlline;\n'\
 	'			}\n'\
@@ -4002,12 +3979,80 @@ def addScriptCode(hf, testruns):
 	'				}\n'\
 	'			}\n'\
 	'		}\n'\
+	'		if(typeof devstats !== \'undefined\')\n'\
+	'			callDetail(this.id, this.title);\n'\
 	'		var cglist = document.getElementById("callgraphs");\n'\
 	'		if(!cglist) return;\n'\
 	'		var cg = cglist.getElementsByClassName("atop");\n'\
 	'		if(cg.length < 10) return;\n'\
 	'		for (var i = 0; i < cg.length; i++) {\n'\
-	'			if(idlist.indexOf(cg[i].id) >= 0) {\n'\
+	'			cgid = cg[i].id.split("x")[0]\n'\
+	'			if(idlist.indexOf(cgid) >= 0) {\n'\
+	'				cg[i].style.display = "block";\n'\
+	'			} else {\n'\
+	'				cg[i].style.display = "none";\n'\
+	'			}\n'\
+	'		}\n'\
+	'	}\n'\
+	'	function callDetail(devid, devtitle) {\n'\
+	'		if(!(devid in devstats) || devstats[devid].length < 1)\n'\
+	'			return;\n'\
+	'		var list = devstats[devid];\n'\
+	'		var tmp = devtitle.split(" ");\n'\
+	'		var name = tmp[0], phase = tmp[tmp.length-1];\n'\
+	'		var dd = document.getElementById(phase);\n'\
+	'		var total = parseFloat(tmp[1].slice(1));\n'\
+	'		var mlist = [];\n'\
+	'		var maxlen = 0;\n'\
+	'		var info = []\n'\
+	'		for(var i in list) {\n'\
+	'			if(list[i][0] == "@") {\n'\
+	'				info = list[i].split("|");\n'\
+	'				continue;\n'\
+	'			}\n'\
+	'			var tmp = list[i].split("|");\n'\
+	'			var t = parseFloat(tmp[0]), f = tmp[1], c = parseInt(tmp[2]);\n'\
+	'			var p = (t*100.0/total).toFixed(2);\n'\
+	'			mlist[mlist.length] = [f, c, t.toFixed(2), p+"%"];\n'\
+	'			if(f.length > maxlen)\n'\
+	'				maxlen = f.length;\n'\
+	'		}\n'\
+	'		var pad = 5;\n'\
+	'		if(mlist.length == 0) pad = 30;\n'\
+	'		var html = \'<div style="padding-top:\'+pad+\'px"><t3> <b>\'+name+\':</b>\';\n'\
+	'		if(info.length > 2)\n'\
+	'			html += " start=<b>"+info[1]+"</b>, end=<b>"+info[2]+"</b>";\n'\
+	'		if(info.length > 3)\n'\
+	'			html += ", length<i>(w/o overhead)</i>=<b>"+info[3]+" ms</b>";\n'\
+	'		if(info.length > 4)\n'\
+	'			html += ", return=<b>"+info[4]+"</b>";\n'\
+	'		html += "</t3></div>";\n'\
+	'		if(mlist.length > 0) {\n'\
+	'			html += \'<table class=fstat style="padding-top:\'+(maxlen*5)+\'px;"><tr><th>Function</th>\';\n'\
+	'			for(var i in mlist)\n'\
+	'				html += "<td class=vt>"+mlist[i][0]+"</td>";\n'\
+	'			html += "</tr><tr><th>Calls</th>";\n'\
+	'			for(var i in mlist)\n'\
+	'				html += "<td>"+mlist[i][1]+"</td>";\n'\
+	'			html += "</tr><tr><th>Time(ms)</th>";\n'\
+	'			for(var i in mlist)\n'\
+	'				html += "<td>"+mlist[i][2]+"</td>";\n'\
+	'			html += "</tr><tr><th>Percent</th>";\n'\
+	'			for(var i in mlist)\n'\
+	'				html += "<td>"+mlist[i][3]+"</td>";\n'\
+	'			html += "</tr></table>";\n'\
+	'		}\n'\
+	'		dd.innerHTML = html;\n'\
+	'		var height = (maxlen*5)+100;\n'\
+	'		dd.style.height = height+"px";\n'\
+	'		document.getElementById("devicedetail").style.height = height+"px";\n'\
+	'	}\n'\
+	'	function callSelect() {\n'\
+	'		var cglist = document.getElementById("callgraphs");\n'\
+	'		if(!cglist) return;\n'\
+	'		var cg = cglist.getElementsByClassName("atop");\n'\
+	'		for (var i = 0; i < cg.length; i++) {\n'\
+	'			if(this.id == cg[i].id) {\n'\
 	'				cg[i].style.display = "block";\n'\
 	'			} else {\n'\
 	'				cg[i].style.display = "none";\n'\
@@ -4093,6 +4138,9 @@ def addScriptCode(hf, testruns):
 	'			dev[i].onmouseover = deviceHover;\n'\
 	'			dev[i].onmouseout = deviceUnhover;\n'\
 	'		}\n'\
+	'		var dev = dmesg.getElementsByClassName("srccall");\n'\
+	'		for (var i = 0; i < dev.length; i++)\n'\
+	'			dev[i].onclick = callSelect;\n'\
 	'		zoomTimeline();\n'\
 	'	});\n'\
 	'</script>\n'
@@ -4675,7 +4723,7 @@ def rootCheck(fatal):
 	if(os.access(sysvals.powerfile, os.W_OK)):
 		return True
 	if fatal:
-		doError('This command must be run as root')
+		doError('This command requires sysfs mount and root access')
 	return False
 
 # Function: getArgInt
@@ -4767,51 +4815,62 @@ def runTest(subdir, testpath=''):
 		cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1'
 		call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True)
 
+def find_in_html(html, strs, div=False):
+	for str in strs:
+		l = len(str)
+		i = html.find(str)
+		if i >= 0:
+			break
+	if i < 0:
+		return ''
+	if not div:
+		return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group()
+	n = html[i+l:].find('</div>')
+	if n < 0:
+		return ''
+	return html[i+l:i+l+n]
+
 # Function: runSummary
 # Description:
 #	 create a summary of tests in a sub-directory
-def runSummary(subdir, output):
-	# get a list of ftrace output files
-	files = []
+def runSummary(subdir, local=True):
+	inpath = os.path.abspath(subdir)
+	outpath = inpath
+	if local:
+		outpath = os.path.abspath('.')
+	print('Generating a summary of folder "%s"' % inpath)
+	testruns = []
 	for dirname, dirnames, filenames in os.walk(subdir):
 		for filename in filenames:
-			if(re.match('.*_ftrace.txt', filename)):
-				files.append("%s/%s" % (dirname, filename))
-
-	# process the files in order and get an array of data objects
-	testruns = []
-	for file in sorted(files):
-		if output:
-			print("Test found in %s" % os.path.dirname(file))
-		sysvals.ftracefile = file
-		sysvals.dmesgfile = file.replace('_ftrace.txt', '_dmesg.txt')
-		doesTraceLogHaveTraceEvents()
-		sysvals.usecallgraph = False
-		if not sysvals.usetraceeventsonly:
-			if(not os.path.exists(sysvals.dmesgfile)):
-				print("Skipping %s: not a valid test input" % file)
+			if(not re.match('.*.html', filename)):
 				continue
-			else:
-				if output:
-					f = os.path.basename(sysvals.ftracefile)
-					d = os.path.basename(sysvals.dmesgfile)
-					print("\tInput files: %s and %s" % (f, d))
-				testdata = loadKernelLog()
-				data = testdata[0]
-				parseKernelLog(data)
-				testdata = [data]
-				appendIncompleteTraceLog(testdata)
-		else:
-			if output:
-				print("\tInput file: %s" % os.path.basename(sysvals.ftracefile))
-			testdata = parseTraceLog()
-			data = testdata[0]
-		data.normalizeTime(data.tSuspended)
-		link = file.replace(subdir+'/', '').replace('_ftrace.txt', '.html')
-		data.outfile = link
-		testruns.append(data)
-
-	createHTMLSummarySimple(testruns, subdir+'/summary.html')
+			file = os.path.join(dirname, filename)
+			html = open(file, 'r').read(10000)
+			suspend = find_in_html(html,
+				['Kernel Suspend: ', 'Kernel Suspend Time: '])
+			resume = find_in_html(html,
+				['Kernel Resume: ', 'Kernel Resume Time: '])
+			line = find_in_html(html, ['<div class="stamp">'], True)
+			stmp = line.split()
+			if not suspend or not resume or len(stmp) < 4:
+				continue
+			data = {
+				'host': stmp[0],
+				'kernel': stmp[1],
+				'mode': stmp[2],
+				'time': string.join(stmp[3:], ' '),
+				'suspend': suspend,
+				'resume': resume,
+				'url': os.path.relpath(file, outpath),
+			}
+			if len(stmp) == 7:
+				data['kernel'] = 'unknown'
+				data['mode'] = stmp[1]
+				data['time'] = string.join(stmp[2:], ' ')
+			testruns.append(data)
+	outfile = os.path.join(outpath, 'summary.html')
+	print('Summary file: %s' % outfile)
+	createHTMLSummarySimple(testruns, outfile, inpath)
 
 # Function: checkArgBool
 # Description:
@@ -4869,9 +4928,14 @@ def configFromFile(file):
 				sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False)
 			elif(opt.lower() == 'postdelay'):
 				sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False)
+			elif(opt.lower() == 'maxdepth'):
+				sysvals.max_graph_depth = getArgInt('-maxdepth', value, 0, 1000, False)
 			elif(opt.lower() == 'rtcwake'):
-				sysvals.rtcwake = True
-				sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
+				if value.lower() == 'off':
+					sysvals.rtcwake = False
+				else:
+					sysvals.rtcwake = True
+					sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
 			elif(opt.lower() == 'timeprec'):
 				sysvals.setPrecision(getArgInt('-timeprec', value, 0, 6, False))
 			elif(opt.lower() == 'mindev'):
@@ -4969,8 +5033,8 @@ def printHelp():
 	modes = getModes()
 
 	print('')
-	print('AnalyzeSuspend v%s' % sysvals.version)
-	print('Usage: sudo analyze_suspend.py <options>')
+	print('%s v%s' % (sysvals.title, sysvals.version))
+	print('Usage: sudo sleepgraph <options> <commands>')
 	print('')
 	print('Description:')
 	print('  This tool is designed to assist kernel and OS developers in optimizing')
@@ -4981,22 +5045,22 @@ def printHelp():
 	print('  a detailed view of which devices/subsystems are taking the most')
 	print('  time in suspend/resume.')
 	print('')
+	print('  If no specific command is given, the default behavior is to initiate')
+	print('  a suspend/resume and capture the dmesg/ftrace output as an html timeline.')
+	print('')
 	print('  Generates output files in subdirectory: suspend-mmddyy-HHMMSS')
 	print('   HTML output:                    <hostname>_<mode>.html')
 	print('   raw dmesg output:               <hostname>_<mode>_dmesg.txt')
 	print('   raw ftrace output:              <hostname>_<mode>_ftrace.txt')
 	print('')
 	print('Options:')
-	print('  [general]')
 	print('   -h           Print this help text')
 	print('   -v           Print the current tool version')
 	print('   -config fn   Pull arguments and config options from file fn')
 	print('   -verbose     Print extra information during execution and analysis')
-	print('   -status      Test to see if the system is enabled to run this tool')
-	print('   -modes       List available suspend modes')
 	print('   -m mode      Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
 	print('   -o subdir    Override the output subdirectory')
-	print('   -rtcwake t   Use rtcwake to autoresume after <t> seconds (default: disabled)')
+	print('   -rtcwake t   Wakeup t seconds after suspend, set t to "off" to disable (default: 15)')
 	print('   -addlogs     Add the dmesg and ftrace logs to the html output')
 	print('   -srgap       Add a visible gap in the timeline between sus/res (default: disabled)')
 	print('  [advanced]')
@@ -5012,23 +5076,25 @@ def printHelp():
 	print('                be created in a new subdirectory with a summary page.')
 	print('  [debug]')
 	print('   -f           Use ftrace to create device callgraphs (default: disabled)')
+	print('   -maxdepth N  limit the callgraph data to N call levels (default: 0=all)')
 	print('   -expandcg    pre-expand the callgraph data in the html output (default: disabled)')
-	print('   -flist       Print the list of functions currently being captured in ftrace')
-	print('   -flistall    Print all functions capable of being captured in ftrace')
 	print('   -fadd file   Add functions to be graphed in the timeline from a list in a text file')
 	print('   -filter "d1,d2,..." Filter out all but this comma-delimited list of device names')
 	print('   -mincg  ms   Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
 	print('   -cgphase P   Only show callgraph data for phase P (e.g. suspend_late)')
 	print('   -cgtest N    Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)')
 	print('   -timeprec N  Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
-	print('  [utilities]')
+	print('  [commands]')
+	print('   -ftrace ftracefile  Create HTML output using ftrace input (used with -dmesg)')
+	print('   -dmesg dmesgfile    Create HTML output using dmesg (used with -ftrace)')
+	print('   -summary directory  Create a summary of all test in this dir')
+	print('   -modes       List available suspend modes')
+	print('   -status      Test to see if the system is enabled to run this tool')
 	print('   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table')
 	print('   -usbtopo     Print out the current USB topology with power info')
 	print('   -usbauto     Enable autosuspend for all connected USB devices')
-	print('  [re-analyze data from previous runs]')
-	print('   -ftrace ftracefile  Create HTML output using ftrace input')
-	print('   -dmesg dmesgfile    Create HTML output using dmesg (not needed for kernel >= 3.15)')
-	print('   -summary directory  Create a summary of all test in this dir')
+	print('   -flist       Print the list of functions currently being captured in ftrace')
+	print('   -flistall    Print all functions capable of being captured in ftrace')
 	print('')
 	return True
 
@@ -5076,9 +5142,18 @@ if __name__ == '__main__':
 			sysvals.useprocmon = True
 		elif(arg == '-dev'):
 			sysvals.usedevsrc = True
+		elif(arg == '-maxdepth'):
+			sysvals.max_graph_depth = getArgInt('-maxdepth', args, 0, 1000)
 		elif(arg == '-rtcwake'):
-			sysvals.rtcwake = True
-			sysvals.rtcwaketime = getArgInt('-rtcwake', args, 0, 3600)
+			try:
+				val = args.next()
+			except:
+				doError('No rtcwake time supplied', True)
+			if val.lower() == 'off':
+				sysvals.rtcwake = False
+			else:
+				sysvals.rtcwake = True
+				sysvals.rtcwaketime = getArgInt('-rtcwake', val, 0, 3600, False)
 		elif(arg == '-timeprec'):
 			sysvals.setPrecision(getArgInt('-timeprec', args, 0, 6))
 		elif(arg == '-mindev'):
@@ -5201,7 +5276,6 @@ if __name__ == '__main__':
 		elif(cmd == 'usbauto'):
 			setUSBDevicesAuto()
 		elif(cmd == 'summary'):
-			print("Generating a summary of folder \"%s\"" % cmdarg)
 			runSummary(cmdarg, True)
 		sys.exit()
 
diff --git a/tools/power/pm-graph/bootgraph.8 b/tools/power/pm-graph/bootgraph.8
new file mode 100644
index 000000000000..55272a67b0e7
--- /dev/null
+++ b/tools/power/pm-graph/bootgraph.8
@@ -0,0 +1,132 @@
+.TH BOOTGRAPH 8
+.SH NAME
+bootgraph \- Kernel boot timing analysis
+.SH SYNOPSIS
+.ft B
+.B bootgraph
+.RB [ OPTIONS ]
+.RB [ COMMAND ]
+.SH DESCRIPTION
+\fBbootgraph \fP reads the dmesg log from kernel boot and
+creates an html representation of the initcall timeline up to the start
+of the init process.
+.PP
+If no specific command is given, the tool reads the current dmesg log and
+outputs bootgraph.html.
+.PP
+The tool can also augment the timeline with ftrace data on custom target
+functions as well as full trace callgraphs.
+.SH OPTIONS
+.TP
+\fB-h\fR
+Print this help text
+.TP
+\fB-v\fR
+Print the current tool version
+.TP
+\fB-addlogs\fR
+Add the dmesg log to the html output. It will be viewable by
+clicking a button in the timeline.
+.TP
+\fB-o \fIfile\fR
+Override the HTML output filename (default: bootgraph.html)
+.SS "Ftrace Debug"
+.TP
+\fB-f\fR
+Use ftrace to add function detail (default: disabled)
+.TP
+\fB-callgraph\fR
+Use ftrace to create initcall callgraphs (default: disabled). If -filter
+is not used there will be one callgraph per initcall. This can produce
+very large outputs, i.e. 10MB - 100MB.
+.TP
+\fB-maxdepth \fIlevel\fR
+limit the callgraph trace depth to \fIlevel\fR (default: 2). This is
+the best way to limit the output size when using -callgraph.
+.TP
+\fB-mincg \fIt\fR
+Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0=all).
+This reduces the html file size as there can be many tiny callgraphs
+which are barely visible in the timeline.
+The value is a float: e.g. 0.001 represents 1 us.
+.TP
+\fB-timeprec \fIn\fR
+Number of significant digits in timestamps (0:S, 3:ms, [6:us])
+.TP
+\fB-expandcg\fR
+pre-expand the callgraph data in the html output (default: disabled)
+.TP
+\fB-filter \fI"func1,func2,..."\fR
+Instead of tracing each initcall, trace a custom list of functions (default: do_one_initcall)
+
+.SH COMMANDS
+.TP
+\fB-reboot\fR
+Reboot the machine and generate a new timeline automatically. Works in 4 steps.
+  1. updates grub with the required kernel parameters
+  2. installs a cron job which re-runs the tool after reboot
+  3. reboots the system
+  4. after startup, extracts the data and generates the timeline
+.TP
+\fB-manual\fR
+Show the requirements to generate a new timeline manually. Requires 3 steps.
+  1. append the string to the kernel command line via your native boot manager.
+  2. reboot the system
+  3. after startup, re-run the tool with the same arguments and no command
+.TP
+\fB-dmesg \fIfile\fR
+Create HTML output from an existing dmesg file.
+.TP
+\fB-ftrace \fIfile\fR
+Create HTML output from an existing ftrace file (used with -dmesg).
+.TP
+\fB-flistall\fR
+Print all ftrace functions capable of being captured. These are all the
+possible values you can add to trace via the -filter argument.
+
+.SH EXAMPLES
+Create a timeline using the current dmesg log.
+.IP
+\f(CW$ bootgraph\fR
+.PP
+Create a timeline using the current dmesg and ftrace log.
+.IP
+\f(CW$ bootgraph -callgraph\fR
+.PP
+Create a timeline using the current dmesg, add the log to the html and change the name.
+.IP
+\f(CW$ bootgraph -addlogs -o myboot.html\fR
+.PP
+Capture a new boot timeline by automatically rebooting the machine.
+.IP
+\f(CW$ sudo bootgraph -reboot -addlogs -o latestboot.html\fR
+.PP
+Capture a new boot timeline with function trace data.
+.IP
+\f(CW$ sudo bootgraph -reboot -f\fR
+.PP
+Capture a new boot timeline with trace & callgraph data. Skip callgraphs smaller than 5ms.
+.IP
+\f(CW$ sudo bootgraph -reboot -callgraph -mincg 5\fR
+.PP
+Capture a new boot timeline with callgraph data over custom functions.
+.IP
+\f(CW$ sudo bootgraph -reboot -callgraph -filter "acpi_ps_parse_aml,msleep"\fR
+.PP
+Capture a brand new boot timeline with manual reboot.
+.IP
+\f(CW$ sudo bootgraph -callgraph -manual\fR
+.IP
+\f(CW$ vi /etc/default/grub      # add the CMDLINE string to your kernel params\fR
+.IP
+\f(CW$ sudo reboot               # reboot the machine\fR
+.IP
+\f(CW$ sudo bootgraph -callgraph # re-run the tool after restart\fR
+.PP
+
+.SH "SEE ALSO"
+dmesg(1), update-grub(8), crontab(1), reboot(8)
+.PP
+.SH AUTHOR
+.nf
+Written by Todd Brandt <todd.e.brandt@linux.intel.com>
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
new file mode 100644
index 000000000000..610e72ebbc06
--- /dev/null
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -0,0 +1,243 @@
+.TH SLEEPGRAPH 8
+.SH NAME
+sleepgraph \- Suspend/Resume timing analysis
+.SH SYNOPSIS
+.ft B
+.B sleepgraph
+.RB [ OPTIONS ]
+.RB [ COMMAND ]
+.SH DESCRIPTION
+\fBsleepgraph \fP is designed to assist kernel and OS developers
+in optimizing their linux stack's suspend/resume time. Using a kernel
+image built with a few extra options enabled, the tool will execute a
+suspend and capture dmesg and ftrace data until resume is complete.
+This data is transformed into a device timeline and an optional
+callgraph to give a detailed view of which devices/subsystems are
+taking the most time in suspend/resume.
+.PP
+If no specific command is given, the default behavior is to initiate
+a suspend/resume.
+.PP
+Generates output files in subdirectory: suspend-yymmdd-HHMMSS
+   html timeline   :     <hostname>_<mode>.html
+   raw dmesg file  :     <hostname>_<mode>_dmesg.txt
+   raw ftrace file :     <hostname>_<mode>_ftrace.txt
+.SH OPTIONS
+.TP
+\fB-h\fR
+Print the help text.
+.TP
+\fB-v\fR
+Print the current tool version.
+.TP
+\fB-verbose\fR
+Print extra information during execution and analysis.
+.TP
+\fB-config \fIfile\fR
+Pull arguments and config options from a file.
+.TP
+\fB-m \fImode\fR
+Mode to initiate for suspend e.g. standby, freeze, mem (default: mem).
+.TP
+\fB-o \fIsubdir\fR
+Override the output subdirectory. Use {date}, {time}, {hostname} for current values.
+.sp
+e.g. suspend-{hostname}-{date}-{time}
+.TP
+\fB-rtcwake \fIt\fR | off
+Use rtcwake to autoresume after \fIt\fR seconds (default: 15). Set t to "off" to
+disable rtcwake and require a user keypress to resume.
+.TP
+\fB-addlogs\fR
+Add the dmesg and ftrace logs to the html output. They will be viewable by
+clicking buttons in the timeline.
+
+.SS "Advanced"
+.TP
+\fB-cmd \fIstr\fR
+Run the timeline over a custom suspend command, e.g. pm-suspend. By default
+the tool forces suspend via /sys/power/state so this allows testing over
+an OS's official suspend method. The output file will change to
+hostname_command.html and will autodetect which suspend mode was triggered.
+.TP
+\fB-filter \fI"d1,d2,..."\fR
+Filter out all but these device callbacks. These strings can be device names
+or module names. e.g. 0000:00:02.0, ata5, i915, usb, etc.
+.TP
+\fB-mindev \fIt\fR
+Discard all device callbacks shorter than \fIt\fR milliseconds (default: 0.0).
+This reduces the html file size as there can be many tiny callbacks which are barely
+visible. The value is a float: e.g. 0.001 represents 1 us.
+.TP
+\fB-proc\fR
+Add usermode process info into the timeline (default: disabled).
+.TP
+\fB-dev\fR
+Add kernel source calls and threads to the timeline (default: disabled).
+.TP
+\fB-x2\fR
+Run two suspend/resumes back to back (default: disabled).
+.TP
+\fB-x2delay \fIt\fR
+Include \fIt\fR ms delay between multiple test runs (default: 0 ms).
+.TP
+\fB-predelay \fIt\fR
+Include \fIt\fR ms delay before 1st suspend (default: 0 ms).
+.TP
+\fB-postdelay \fIt\fR
+Include \fIt\fR ms delay after last resume (default: 0 ms).
+.TP
+\fB-multi \fIn d\fR
+Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will
+be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}.
+
+.SS "Ftrace Debug"
+.TP
+\fB-f\fR
+Use ftrace to create device callgraphs (default: disabled). This can produce
+very large outputs, i.e. 10MB - 100MB.
+.TP
+\fB-maxdepth \fIlevel\fR
+limit the callgraph trace depth to \fIlevel\fR (default: 0=all). This is
+the best way to limit the output size when using callgraphs via -f.
+.TP
+\fB-expandcg\fR
+pre-expand the callgraph data in the html output (default: disabled)
+.TP
+\fB-fadd \fIfile\fR
+Add functions to be graphed in the timeline from a list in a text file
+.TP
+\fB-mincg \fIt\fR
+Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0.0).
+This reduces the html file size as there can be many tiny callgraphs
+which are barely visible in the timeline.
+The value is a float: e.g. 0.001 represents 1 us.
+.TP
+\fB-cgphase \fIp\fR
+Only show callgraph data for phase \fIp\fR (e.g. suspend_late).
+.TP
+\fB-cgtest \fIn\fR
+In an x2 run, only show callgraph data for test \fIn\fR (e.g. 0 or 1).
+.TP
+\fB-timeprec \fIn\fR
+Number of significant digits in timestamps (0:S, [3:ms], 6:us).
+
+.SH COMMANDS
+.TP
+\fB-ftrace \fIfile\fR
+Create HTML output from an existing ftrace file.
+.TP
+\fB-dmesg \fIfile\fR
+Create HTML output from an existing dmesg file.
+.TP
+\fB-summary \fIindir\fR
+Create a summary page of all tests in \fIindir\fR. Creates summary.html
+in the current folder. The output page is a table of tests with
+suspend and resume values sorted by suspend mode, host, and kernel.
+Includes test averages by mode and links to the test html files.
+.TP
+\fB-modes\fR
+List available suspend modes.
+.TP
+\fB-status\fR
+Test to see if the system is able to run this tool. Use this along
+with any options you intend to use to see if they will work.
+.TP
+\fB-fpdt\fR
+Print out the contents of the ACPI Firmware Performance Data Table.
+.TP
+\fB-usbtopo\fR
+Print out the current USB topology with power info.
+.TP
+\fB-usbauto\fR
+Enable autosuspend for all connected USB devices.
+.TP
+\fB-flist\fR
+Print the list of ftrace functions currently being captured. Functions
+that are not available as symbols in the current kernel are shown in red.
+By default, the tool traces a list of important suspend/resume functions
+in order to better fill out the timeline. If the user has added their own
+with -fadd they will also be checked.
+.TP
+\fB-flistall\fR
+Print all ftrace functions capable of being captured. These are all the
+possible values you can add to trace via the -fadd argument.
+
+.SH EXAMPLES
+.SS "Simple Commands"
+Check which suspend modes are currently supported.
+.IP
+\f(CW$ sleepgraph -modes\fR
+.PP
+Read the Firmware Performance Data Table (FPDT)
+.IP
+\f(CW$ sudo sleepgraph -fpdt\fR
+.PP
+Print out the current USB power topology
+.IP
+\f(CW$ sleepgraph -usbtopo
+.PP
+Verify that you can run a command with a set of arguments
+.IP
+\f(CW$ sudo sleepgraph -f -rtcwake 30 -status
+.PP
+Generate a summary of all timelines in a particular folder.
+.IP
+\f(CW$ sleepgraph -summary ~/workspace/myresults/\fR
+.PP
+Re-generate the html output from a previous run's dmesg and ftrace log.
+.IP
+\f(CW$ sleepgraph -dmesg myhost_mem_dmesg.txt -ftrace myhost_mem_ftrace.txt\fR
+.PP
+
+.SS "Capturing Simple Timelines"
+Execute a mem suspend with a 15 second wakeup. Include the logs in the html.
+.IP
+\f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR
+.PP
+Execute a standby with a 15 second wakeup. Change the output folder name.
+.IP
+\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{hostname}-{date}-{time}"\fR
+.PP
+Execute a freeze with no wakeup (require keypress). Change output folder name.
+.IP
+\f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR
+.PP
+
+.SS "Capturing Advanced Timelines"
+Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR
+.PP
+Run two suspends back to back, include a 500ms delay before, after, and in between runs.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR
+.PP
+Do a batch run of 10 freezes with 30 seconds delay between runs.
+.IP
+\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR
+.PP
+Execute a suspend using a custom command.
+.IP
+\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
+.PP
+
+
+.SS "Capturing Timelines with Callgraph Data"
+Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR
+.PP
+Capture a full callgraph across all suspend, then filter the html by a single phase.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f\fR
+.IP
+\f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume
+.PP
+
+.SH "SEE ALSO"
+dmesg(1)
+.PP
+.SH AUTHOR
+.nf
+Written by Todd Brandt <todd.e.brandt@linux.intel.com>
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index fd706ac0f347..0b24dd9d01ff 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -353,6 +353,14 @@ def split_csv():
                 os.system('grep -m 1 common_cpu cpu.csv > cpu{:0>3}.csv'.format(index))
                 os.system('grep CPU_{:0>3} cpu.csv >> cpu{:0>3}.csv'.format(index, index))
 
+def fix_ownership(path):
+    """Change the owner of the file to SUDO_UID, if required"""
+
+    uid = os.environ.get('SUDO_UID')
+    gid = os.environ.get('SUDO_GID')
+    if uid is not None:
+        os.chown(path, int(uid), int(gid))
+
 def cleanup_data_files():
     """ clean up existing data files """
 
@@ -518,12 +526,16 @@ else:
 
 if not os.path.exists('results'):
     os.mkdir('results')
+    # The regular user needs to own the directory, not root.
+    fix_ownership('results')
 
 os.chdir('results')
 if os.path.exists(testname):
     print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
     sys.exit()
 os.mkdir(testname)
+# The regular user needs to own the directory, not root.
+fix_ownership(testname)
 os.chdir(testname)
 
 # Temporary (or perhaps not)
@@ -566,4 +578,9 @@ plot_scaled_cpu()
 plot_boost_cpu()
 plot_ghz_cpu()
 
+# It is preferrable, but not necessary, that the regular user owns the files, not root.
+for root, dirs, files in os.walk('.'):
+    for f in files:
+        fix_ownership(f)
+
 os.chdir('../../')
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index fedca3285326..ccf2a69365cc 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -100,6 +100,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.  These numbers are from hardware residency counters.
 \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
 \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
 \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.  These numbers are from hardware residency counters.
 \fBPkgWatt\fP Watts consumed by the whole package.
 \fBCorWatt\fP Watts consumed by the core part of the package.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 828dccd3f01e..b11294730771 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1142,7 +1142,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 		 * it is possible for mperf's non-halted cycles + idle states
 		 * to exceed TSC's all cycles: show c1 = 0% in that case.
 		 */
-		if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc)
+		if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > (old->tsc * tsc_tweak))
 			old->c1 = 0;
 		else {
 			/* normal case, derive c1 */
@@ -2485,8 +2485,10 @@ int snapshot_gfx_mhz(void)
 
 	if (fp == NULL)
 		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
-	else
+	else {
 		rewind(fp);
+		fflush(fp);
+	}
 
 	retval = fscanf(fp, "%d", &gfx_cur_mhz);
 	if (retval != 1)
@@ -3111,7 +3113,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return 0;
 
 	fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx "
-			"(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n",
+			"(high %d guar %d eff %d low %d)\n",
 			cpu, msr,
 			(unsigned int)HWP_HIGHEST_PERF(msr),
 			(unsigned int)HWP_GUARANTEED_PERF(msr),
@@ -3122,7 +3124,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return 0;
 
 	fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx "
-			"(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n",
+			"(min %d max %d des %d epp 0x%x window 0x%x pkg 0x%x)\n",
 			cpu, msr,
 			(unsigned int)(((msr) >> 0) & 0xff),
 			(unsigned int)(((msr) >> 8) & 0xff),
@@ -3136,7 +3138,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return 0;
 
 		fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx "
-			"(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n",
+			"(min %d max %d des %d epp 0x%x window 0x%x)\n",
 			cpu, msr,
 			(unsigned int)(((msr) >> 0) & 0xff),
 			(unsigned int)(((msr) >> 8) & 0xff),
@@ -3353,17 +3355,19 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
-		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		BIC_PRESENT(BIC_PKG__);
 		BIC_PRESENT(BIC_RAM__);
 		if (rapl_joules) {
 			BIC_PRESENT(BIC_Pkg_J);
 			BIC_PRESENT(BIC_Cor_J);
 			BIC_PRESENT(BIC_RAM_J);
+			BIC_PRESENT(BIC_GFX_J);
 		} else {
 			BIC_PRESENT(BIC_PkgWatt);
 			BIC_PRESENT(BIC_CorWatt);
 			BIC_PRESENT(BIC_RAMWatt);
+			BIC_PRESENT(BIC_GFXWatt);
 		}
 		break;
 	case INTEL_FAM6_HASWELL_X:	/* HSX */
@@ -3478,7 +3482,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
-	unsigned int dts;
+	unsigned int dts, dts2;
 	int cpu;
 
 	if (!(do_dts || do_ptm))
@@ -3503,7 +3507,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
 			cpu, msr, tcc_activation_temp - dts);
 
-#ifdef	THERM_DEBUG
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
 			return 0;
 
@@ -3511,11 +3514,10 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 		dts2 = (msr >> 8) & 0x7F;
 		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
 			cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
 	}
 
 
-	if (do_dts) {
+	if (do_dts && debug) {
 		unsigned int resolution;
 
 		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
@@ -3526,7 +3528,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
 			cpu, msr, tcc_activation_temp - dts, resolution);
 
-#ifdef THERM_DEBUG
 		if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
 			return 0;
 
@@ -3534,7 +3535,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 		dts2 = (msr >> 8) & 0x7F;
 		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
 			cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
 	}
 
 	return 0;
@@ -4578,7 +4578,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 17.02.24"
+	fprintf(outf, "turbostat version 17.04.12"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 621578aa12d6..fc74db62fef4 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -43,6 +43,15 @@ ifneq ($(CC), clang)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 endif
 
+# Hack to avoid type-punned warnings on old systems such as RHEL5:
+# We should be changing CFLAGS and checking gcc version, but this
+# will do for now and keep the above -Wstrict-aliasing=3 in place
+# in newer systems.
+# Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h
+ifneq ($(filter 3.%,$(MAKE_VERSION)),)  # make-3
+EXTRA_WARNINGS += -fno-strict-aliasing
+endif
+
 ifneq ($(findstring $(MAKEFLAGS), w),w)
 PRINT_DIR = --no-print-directory
 else
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 6e4eb2fc2d1e..0c8b61f8398e 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1880,6 +1880,7 @@ sub get_grub_index {
 sub wait_for_input
 {
     my ($fp, $time) = @_;
+    my $start_time;
     my $rin;
     my $rout;
     my $nr;
@@ -1895,17 +1896,22 @@ sub wait_for_input
     vec($rin, fileno($fp), 1) = 1;
     vec($rin, fileno(\*STDIN), 1) = 1;
 
+    $start_time = time;
+
     while (1) {
 	$nr = select($rout=$rin, undef, undef, $time);
 
-	if ($nr <= 0) {
-	    return undef;
-	}
+	last if ($nr <= 0);
 
 	# copy data from stdin to the console
 	if (vec($rout, fileno(\*STDIN), 1) == 1) {
-	    sysread(\*STDIN, $buf, 1000);
-	    syswrite($fp, $buf, 1000);
+	    $nr = sysread(\*STDIN, $buf, 1000);
+	    syswrite($fp, $buf, $nr) if ($nr > 0);
+	}
+
+	# The timeout is based on time waiting for the fp data
+	if (vec($rout, fileno($fp), 1) != 1) {
+	    last if (defined($time) && (time - $start_time > $time));
 	    next;
 	}
 
@@ -1917,12 +1923,11 @@ sub wait_for_input
 	    last if ($ch eq "\n");
 	}
 
-	if (!length($line)) {
-	    return undef;
-	}
+	last if (!length($line));
 
 	return $line;
     }
+    return undef;
 }
 
 sub reboot_to {
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index f11315bedefc..6a9480c03cbd 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -1,6 +1,7 @@
 
 CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address
-LDFLAGS += -lpthread -lurcu
+LDFLAGS += -fsanitize=address
+LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder
 CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
@@ -10,23 +11,25 @@ ifndef SHIFT
 	SHIFT=3
 endif
 
+ifeq ($(BUILD), 32)
+	CFLAGS += -m32
+	LDFLAGS += -m32
+endif
+
 targets: mapshift $(TARGETS)
 
 main:	$(OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o main
 
 idr-test: idr-test.o $(CORE_OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o idr-test
 
 multiorder: multiorder.o $(CORE_OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o multiorder
 
 clean:
 	$(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h
 
 vpath %.c ../../lib
 
-$(OFILES): *.h */*.h generated/map-shift.h \
+$(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
 	../../../include/linux/radix-tree.h \
@@ -41,7 +44,7 @@ idr.c: ../../../lib/idr.c
 .PHONY: mapshift
 
 mapshift:
-	@if ! grep -qw $(SHIFT) generated/map-shift.h; then		\
+	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 9b09ddfe462f..99c40f3ed133 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,6 +17,9 @@
 #include <time.h>
 #include "test.h"
 
+#define for_each_index(i, base, order) \
+	        for (i = base; i < base + (1 << order); i++)
+
 #define NSEC_PER_SEC	1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -57,27 +60,176 @@ again:
 	return nsec;
 }
 
+static void benchmark_insert(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_insert_order(root, index, order);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
+		size, step, order, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		radix_tree_tag_set(root, index, 0);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
+		size, step, order, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index, i;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		for_each_index(i, index, order)
+			item_delete(root, i);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
+		size, step, order, nsec);
+}
+
 static void benchmark_size(unsigned long size, unsigned long step, int order)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
 	long long normal, tagged;
-	unsigned long index;
 
-	for (index = 0 ; index < size ; index += step) {
-		item_insert_order(&tree, index, order);
-		radix_tree_tag_set(&tree, index, 0);
-	}
+	benchmark_insert(&tree, size, step, order);
+	benchmark_tagging(&tree, size, step, order);
 
 	tagged = benchmark_iter(&tree, true);
 	normal = benchmark_iter(&tree, false);
 
-	printv(2, "Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n",
-		size, step, order, tagged, normal);
+	printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
+		size, step, order, tagged);
+	printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
+		size, step, order, normal);
+
+	benchmark_delete(&tree, size, step, order);
 
 	item_kill_tree(&tree);
 	rcu_barrier();
 }
 
+static long long  __benchmark_split(unsigned long index,
+				    int old_order, int new_order)
+{
+	struct timespec start, finish;
+	long long nsec;
+	RADIX_TREE(tree, GFP_ATOMIC);
+
+	item_insert_order(&tree, index, old_order);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	radix_tree_split(&tree, index, new_order);
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	item_kill_tree(&tree);
+
+	return nsec;
+
+}
+
+static void benchmark_split(unsigned long size, unsigned long step)
+{
+	int i, j, idx;
+	long long nsec = 0;
+
+
+	for (idx = 0; idx < size; idx += step) {
+		for (i = 3; i < 11; i++) {
+			for (j = 0; j < i; j++) {
+				nsec += __benchmark_split(idx, i, j);
+			}
+		}
+	}
+
+	printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
+			size, step, nsec);
+
+}
+
+static long long  __benchmark_join(unsigned long index,
+			     unsigned order1, unsigned order2)
+{
+	unsigned long loc;
+	struct timespec start, finish;
+	long long nsec;
+	void *item, *item2 = item_create(index + 1, order1);
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert_order(&tree, index, order2);
+	item = radix_tree_lookup(&tree, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	radix_tree_join(&tree, index + 1, order1, item2);
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+		(finish.tv_nsec - start.tv_nsec);
+
+	loc = find_item(&tree, item);
+	if (loc == -1)
+		free(item);
+
+	item_kill_tree(&tree);
+
+	return nsec;
+}
+
+static void benchmark_join(unsigned long step)
+{
+	int i, j, idx;
+	long long nsec = 0;
+
+	for (idx = 0; idx < 1 << 10; idx += step) {
+		for (i = 1; i < 15; i++) {
+			for (j = 0; j < i; j++) {
+				nsec += __benchmark_join(idx, i, j);
+			}
+		}
+	}
+
+	printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
+			1 << 10, step, nsec);
+}
+
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -95,4 +247,11 @@ void benchmark(void)
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
 			benchmark_size(size[c], step[s] << 9, 9);
+
+	for (c = 0; size[c]; c++)
+		for (s = 0; step[s]; s++)
+			benchmark_split(size[c], step[s]);
+
+	for (s = 0; step[s]; s++)
+		benchmark_join(step[s]);
 }
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index a26098c6123d..30cd0b296f1a 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -153,6 +153,30 @@ void idr_nowait_test(void)
 	idr_destroy(&idr);
 }
 
+void idr_get_next_test(void)
+{
+	unsigned long i;
+	int nextid;
+	DEFINE_IDR(idr);
+
+	int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0};
+
+	for(i = 0; indices[i]; i++) {
+		struct item *item = item_create(indices[i], 0);
+		assert(idr_alloc(&idr, item, indices[i], indices[i+1],
+				 GFP_KERNEL) == indices[i]);
+	}
+
+	for(i = 0, nextid = 0; indices[i]; i++) {
+		idr_get_next(&idr, &nextid);
+		assert(nextid == indices[i]);
+		nextid++;
+	}
+
+	idr_for_each(&idr, item_idr_free, &idr);
+	idr_destroy(&idr);
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -202,6 +226,7 @@ void idr_checks(void)
 	idr_alloc_test();
 	idr_null_test();
 	idr_nowait_test();
+	idr_get_next_test();
 }
 
 /*
@@ -338,7 +363,7 @@ void ida_check_random(void)
 {
 	DEFINE_IDA(ida);
 	DECLARE_BITMAP(bitmap, 2048);
-	int id;
+	int id, err;
 	unsigned int i;
 	time_t s = time(NULL);
 
@@ -352,8 +377,11 @@ void ida_check_random(void)
 			ida_remove(&ida, bit);
 		} else {
 			__set_bit(bit, bitmap);
-			ida_pre_get(&ida, GFP_KERNEL);
-			assert(!ida_get_new_above(&ida, bit, &id));
+			do {
+				ida_pre_get(&ida, GFP_KERNEL);
+				err = ida_get_new_above(&ida, bit, &id);
+			} while (err == -ENOMEM);
+			assert(!err);
 			assert(id == bit);
 		}
 	}
@@ -362,6 +390,24 @@ void ida_check_random(void)
 		goto repeat;
 }
 
+void ida_simple_get_remove_test(void)
+{
+	DEFINE_IDA(ida);
+	unsigned long i;
+
+	for (i = 0; i < 10000; i++) {
+		assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i);
+	}
+	assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0);
+
+	for (i = 0; i < 10000; i++) {
+		ida_simple_remove(&ida, i);
+	}
+	assert(ida_is_empty(&ida));
+
+	ida_destroy(&ida);
+}
+
 void ida_checks(void)
 {
 	DEFINE_IDA(ida);
@@ -428,15 +474,41 @@ void ida_checks(void)
 	ida_check_max();
 	ida_check_conv();
 	ida_check_random();
+	ida_simple_get_remove_test();
 
 	radix_tree_cpu_dead(1);
 }
 
+static void *ida_random_fn(void *arg)
+{
+	rcu_register_thread();
+	ida_check_random();
+	rcu_unregister_thread();
+	return NULL;
+}
+
+void ida_thread_tests(void)
+{
+	pthread_t threads[10];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++)
+		if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) {
+			perror("creating ida thread");
+			exit(1);
+		}
+
+	while (i--)
+		pthread_join(threads[i], NULL);
+}
+
 int __weak main(void)
 {
 	radix_tree_init();
 	idr_checks();
 	ida_checks();
+	ida_thread_tests();
+	radix_tree_cpu_dead(1);
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index b829127d5670..bc9a78449572 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -368,6 +368,7 @@ int main(int argc, char **argv)
 	iteration_test(0, 10 + 90 * long_run);
 	iteration_test(7, 10 + 90 * long_run);
 	single_thread_tests(long_run);
+	ida_thread_tests();
 
 	/* Free any remaining preallocated nodes */
 	radix_tree_cpu_dead(0);
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index d4ff00989245..36dcf7d6945d 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -330,6 +330,34 @@ static void single_check(void)
 	item_kill_tree(&tree);
 }
 
+void radix_tree_clear_tags_test(void)
+{
+	unsigned long index;
+	struct radix_tree_node *node;
+	struct radix_tree_iter iter;
+	void **slot;
+
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert(&tree, 0);
+	item_tag_set(&tree, 0, 0);
+	__radix_tree_lookup(&tree, 0, &node, &slot);
+	radix_tree_clear_tags(&tree, node, slot);
+	assert(item_tag_get(&tree, 0, 0) == 0);
+
+	for (index = 0; index < 1000; index++) {
+		item_insert(&tree, index);
+		item_tag_set(&tree, index, 0);
+	}
+
+	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
+		radix_tree_clear_tags(&tree, iter.node, slot);
+		assert(item_tag_get(&tree, iter.index, 0) == 0);
+	}
+
+	item_kill_tree(&tree);
+}
+
 void tag_check(void)
 {
 	single_check();
@@ -347,4 +375,5 @@ void tag_check(void)
 	thrash_tags();
 	rcu_barrier();
 	printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
+	radix_tree_clear_tags_test();
 }
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index b30e11d9d271..0f8220cc6166 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -36,6 +36,7 @@ void iteration_test(unsigned order, unsigned duration);
 void benchmark(void);
 void idr_checks(void);
 void ida_checks(void);
+void ida_thread_tests(void);
 
 struct item *
 item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4b498265dae6..d8d94b9bd76c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,20 +1,39 @@
 LIBDIR := ../../../lib
-BPFOBJ := $(LIBDIR)/bpf/bpf.o
+BPFDIR := $(LIBDIR)/bpf
+APIDIR := ../../../include/uapi
+GENDIR := ../../../../include/generated
+GENHDR := $(GENDIR)/autoconf.h
 
-CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR)
+ifneq ($(wildcard $(GENHDR)),)
+  GENFLAGS := -DHAVE_GENHDR
+endif
 
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+LDLIBS += -lcap -lelf
+
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs
+
+TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o
 
 TEST_PROGS := test_kmod.sh
 
-.PHONY: all clean force
+include ../lib.mk
+
+BPFOBJ := $(OUTPUT)/libbpf.a
+
+$(TEST_GEN_PROGS): $(BPFOBJ)
+
+.PHONY: force
 
 # force a rebuild of BPFOBJ when its dependencies are updated
 force:
 
 $(BPFOBJ): force
-	$(MAKE) -C $(dir $(BPFOBJ))
+	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
-$(test_objs): $(BPFOBJ)
+CLANG ?= clang
 
-include ../lib.mk
+%.o: %.c
+	$(CLANG) -I../../../include/uapi -I../../../../samples/bpf/ \
+		-D__x86_64__ -Wno-compare-distinct-pointer-types \
+		-O2 -target bpf -c $< -o $@
diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h
new file mode 100644
index 000000000000..19d0604f8694
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_endian.h
@@ -0,0 +1,23 @@
+#ifndef __BPF_ENDIAN__
+#define __BPF_ENDIAN__
+
+#include <asm/byteorder.h>
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+# define __bpf_ntohs(x)		__builtin_bswap16(x)
+# define __bpf_htons(x)		__builtin_bswap16(x)
+#elif __BYTE_ORDER == __BIG_ENDIAN
+# define __bpf_ntohs(x)		(x)
+# define __bpf_htons(x)		(x)
+#else
+# error "Fix your __BYTE_ORDER?!"
+#endif
+
+#define bpf_htons(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __constant_htons(x) : __bpf_htons(x))
+#define bpf_ntohs(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __constant_ntohs(x) : __bpf_ntohs(x))
+
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 84a5d1823f02..20ecbaa0d85d 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -35,4 +35,11 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	return possible_cpus;
 }
 
+#define __bpf_percpu_val_align	__attribute__((__aligned__(8)))
+
+#define BPF_DECLARE_PERCPU(type, name)				\
+	struct { type v; /* padding */ } __bpf_percpu_val_align	\
+		name[bpf_num_possible_cpus()]
+#define bpf_percpu(name, cpu) name[(cpu)].v
+
 #endif /* __BPF_UTIL__ */
diff --git a/tools/testing/selftests/bpf/test_iptunnel_common.h b/tools/testing/selftests/bpf/test_iptunnel_common.h
new file mode 100644
index 000000000000..e4cd252a1b20
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_iptunnel_common.h
@@ -0,0 +1,37 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _TEST_IPTNL_COMMON_H
+#define _TEST_IPTNL_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_IPTNL_ENTRIES 256U
+
+struct vip {
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} daddr;
+	__u16 dport;
+	__u16 family;
+	__u8 protocol;
+};
+
+struct iptnl_info {
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} saddr;
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} daddr;
+	__u16 family;
+	__u8 dmac[6];
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/test_l4lb.c
new file mode 100644
index 000000000000..1e10c9590991
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_l4lb.c
@@ -0,0 +1,473 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include "bpf_helpers.h"
+#include "test_iptunnel_common.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+
+static inline __u32 rol32(__u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+typedef unsigned int u32;
+
+static inline u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(u32 *)(k);
+		b += *(u32 *)(k + 4);
+		c += *(u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
+
+static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+	a += initval;
+	b += initval;
+	c += initval;
+	__jhash_final(a, b, c);
+	return c;
+}
+
+static inline u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+#define PCKT_FRAGMENTED 65343
+#define IPV4_HDR_LEN_NO_OPT 20
+#define IPV4_PLUS_ICMP_HDR 28
+#define IPV6_PLUS_ICMP_HDR 48
+#define RING_SIZE 2
+#define MAX_VIPS 12
+#define MAX_REALS 5
+#define CTL_MAP_SIZE 16
+#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
+#define F_IPV6 (1 << 0)
+#define F_HASH_NO_SRC_PORT (1 << 0)
+#define F_ICMP (1 << 0)
+#define F_SYN_SET (1 << 1)
+
+struct packet_description {
+	union {
+		__be32 src;
+		__be32 srcv6[4];
+	};
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	union {
+		__u32 ports;
+		__u16 port16[2];
+	};
+	__u8 proto;
+	__u8 flags;
+};
+
+struct ctl_value {
+	union {
+		__u64 value;
+		__u32 ifindex;
+		__u8 mac[6];
+	};
+};
+
+struct vip_meta {
+	__u32 flags;
+	__u32 vip_num;
+};
+
+struct real_definition {
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	__u8 flags;
+};
+
+struct vip_stats {
+	__u64 bytes;
+	__u64 pkts;
+};
+
+struct eth_hdr {
+	unsigned char eth_dest[ETH_ALEN];
+	unsigned char eth_source[ETH_ALEN];
+	unsigned short eth_proto;
+};
+
+struct bpf_map_def SEC("maps") vip_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct vip_meta),
+	.max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ch_rings = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = CH_RINGS_SIZE,
+};
+
+struct bpf_map_def SEC("maps") reals = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct real_definition),
+	.max_entries = MAX_REALS,
+};
+
+struct bpf_map_def SEC("maps") stats = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct vip_stats),
+	.max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ctl_array = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct ctl_value),
+	.max_entries = CTL_MAP_SIZE,
+};
+
+static __always_inline __u32 get_packet_hash(struct packet_description *pckt,
+					     bool ipv6)
+{
+	if (ipv6)
+		return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
+				    pckt->ports, CH_RINGS_SIZE);
+	else
+		return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
+}
+
+static __always_inline bool get_packet_dst(struct real_definition **real,
+					   struct packet_description *pckt,
+					   struct vip_meta *vip_info,
+					   bool is_ipv6)
+{
+	__u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE;
+	__u32 key = RING_SIZE * vip_info->vip_num + hash;
+	__u32 *real_pos;
+
+	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+	if (!real_pos)
+		return false;
+	key = *real_pos;
+	*real = bpf_map_lookup_elem(&reals, &key);
+	if (!(*real))
+		return false;
+	return true;
+}
+
+static __always_inline int parse_icmpv6(void *data, void *data_end, __u64 off,
+					struct packet_description *pckt)
+{
+	struct icmp6hdr *icmp_hdr;
+	struct ipv6hdr *ip6h;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
+		return TC_ACT_OK;
+	off += sizeof(struct icmp6hdr);
+	ip6h = data + off;
+	if (ip6h + 1 > data_end)
+		return TC_ACT_SHOT;
+	pckt->proto = ip6h->nexthdr;
+	pckt->flags |= F_ICMP;
+	memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
+	memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
+	return TC_ACT_UNSPEC;
+}
+
+static __always_inline int parse_icmp(void *data, void *data_end, __u64 off,
+				      struct packet_description *pckt)
+{
+	struct icmphdr *icmp_hdr;
+	struct iphdr *iph;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->type != ICMP_DEST_UNREACH ||
+	    icmp_hdr->code != ICMP_FRAG_NEEDED)
+		return TC_ACT_OK;
+	off += sizeof(struct icmphdr);
+	iph = data + off;
+	if (iph + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (iph->ihl != 5)
+		return TC_ACT_SHOT;
+	pckt->proto = iph->protocol;
+	pckt->flags |= F_ICMP;
+	pckt->src = iph->daddr;
+	pckt->dst = iph->saddr;
+	return TC_ACT_UNSPEC;
+}
+
+static __always_inline bool parse_udp(void *data, __u64 off, void *data_end,
+				      struct packet_description *pckt)
+{
+	struct udphdr *udp;
+	udp = data + off;
+
+	if (udp + 1 > data_end)
+		return false;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = udp->source;
+		pckt->port16[1] = udp->dest;
+	} else {
+		pckt->port16[0] = udp->dest;
+		pckt->port16[1] = udp->source;
+	}
+	return true;
+}
+
+static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end,
+				      struct packet_description *pckt)
+{
+	struct tcphdr *tcp;
+
+	tcp = data + off;
+	if (tcp + 1 > data_end)
+		return false;
+
+	if (tcp->syn)
+		pckt->flags |= F_SYN_SET;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = tcp->source;
+		pckt->port16[1] = tcp->dest;
+	} else {
+		pckt->port16[0] = tcp->dest;
+		pckt->port16[1] = tcp->source;
+	}
+	return true;
+}
+
+static __always_inline int process_packet(void *data, __u64 off, void *data_end,
+					  bool is_ipv6, struct __sk_buff *skb)
+{
+	void *pkt_start = (void *)(long)skb->data;
+	struct packet_description pckt = {};
+	struct eth_hdr *eth = pkt_start;
+	struct bpf_tunnel_key tkey = {};
+	struct vip_stats *data_stats;
+	struct real_definition *dst;
+	struct vip_meta *vip_info;
+	struct ctl_value *cval;
+	__u32 v4_intf_pos = 1;
+	__u32 v6_intf_pos = 2;
+	struct ipv6hdr *ip6h;
+	struct vip vip = {};
+	struct iphdr *iph;
+	int tun_flag = 0;
+	__u16 pkt_bytes;
+	__u64 iph_len;
+	__u32 ifindex;
+	__u8 protocol;
+	__u32 vip_num;
+	int action;
+
+	tkey.tunnel_ttl = 64;
+	if (is_ipv6) {
+		ip6h = data + off;
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		iph_len = sizeof(struct ipv6hdr);
+		protocol = ip6h->nexthdr;
+		pckt.proto = protocol;
+		pkt_bytes = bpf_ntohs(ip6h->payload_len);
+		off += iph_len;
+		if (protocol == IPPROTO_FRAGMENT) {
+			return TC_ACT_SHOT;
+		} else if (protocol == IPPROTO_ICMPV6) {
+			action = parse_icmpv6(data, data_end, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV6_PLUS_ICMP_HDR;
+		} else {
+			memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
+			memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
+		}
+	} else {
+		iph = data + off;
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+		if (iph->ihl != 5)
+			return TC_ACT_SHOT;
+
+		protocol = iph->protocol;
+		pckt.proto = protocol;
+		pkt_bytes = bpf_ntohs(iph->tot_len);
+		off += IPV4_HDR_LEN_NO_OPT;
+
+		if (iph->frag_off & PCKT_FRAGMENTED)
+			return TC_ACT_SHOT;
+		if (protocol == IPPROTO_ICMP) {
+			action = parse_icmp(data, data_end, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV4_PLUS_ICMP_HDR;
+		} else {
+			pckt.src = iph->saddr;
+			pckt.dst = iph->daddr;
+		}
+	}
+	protocol = pckt.proto;
+
+	if (protocol == IPPROTO_TCP) {
+		if (!parse_tcp(data, off, data_end, &pckt))
+			return TC_ACT_SHOT;
+	} else if (protocol == IPPROTO_UDP) {
+		if (!parse_udp(data, off, data_end, &pckt))
+			return TC_ACT_SHOT;
+	} else {
+		return TC_ACT_SHOT;
+	}
+
+	if (is_ipv6)
+		memcpy(vip.daddr.v6, pckt.dstv6, 16);
+	else
+		vip.daddr.v4 = pckt.dst;
+
+	vip.dport = pckt.port16[1];
+	vip.protocol = pckt.proto;
+	vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+	if (!vip_info) {
+		vip.dport = 0;
+		vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+		if (!vip_info)
+			return TC_ACT_SHOT;
+		pckt.port16[1] = 0;
+	}
+
+	if (vip_info->flags & F_HASH_NO_SRC_PORT)
+		pckt.port16[0] = 0;
+
+	if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
+		return TC_ACT_SHOT;
+
+	if (dst->flags & F_IPV6) {
+		cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		memcpy(tkey.remote_ipv6, dst->dstv6, 16);
+		tun_flag = BPF_F_TUNINFO_IPV6;
+	} else {
+		cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		tkey.remote_ipv4 = dst->dst;
+	}
+	vip_num = vip_info->vip_num;
+	data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+	if (!data_stats)
+		return TC_ACT_SHOT;
+	data_stats->pkts++;
+	data_stats->bytes += pkt_bytes;
+	bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
+	*(u32 *)eth->eth_dest = tkey.remote_ipv4;
+	return bpf_redirect(ifindex, 0);
+}
+
+SEC("l4lb-demo")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct eth_hdr *eth = data;
+	__u32 eth_proto;
+	__u32 nh_off;
+
+	nh_off = sizeof(struct eth_hdr);
+	if (data + nh_off > data_end)
+		return TC_ACT_SHOT;
+	eth_proto = eth->eth_proto;
+	if (eth_proto == bpf_htons(ETH_P_IP))
+		return process_packet(data, nh_off, data_end, false, ctx);
+	else if (eth_proto == bpf_htons(ETH_P_IPV6))
+		return process_packet(data, nh_off, data_end, true, ctx);
+	else
+		return TC_ACT_SHOT;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 00b0aff56e2e..8c10c9180c1a 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -22,7 +22,7 @@
 #include "bpf_util.h"
 
 #define LOCAL_FREE_TARGET	(128)
-#define PERCPU_FREE_TARGET	(16)
+#define PERCPU_FREE_TARGET	(4)
 
 static int nr_cpus;
 
@@ -191,12 +191,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	int next_cpu = 0;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
-		/* Ther percpu lru list (i.e each cpu has its own LRU
-		 * list) does not have a local free list.  Hence,
-		 * it will only free old nodes till there is no free
-		 * from the LRU list.  Hence, this test does not apply
-		 * to BPF_F_NO_COMMON_LRU
-		 */
+		/* This test is only applicable to common LRU list */
 		return;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
@@ -227,7 +222,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
-				            BPF_NOEXIST));
+					    BPF_NOEXIST));
 	}
 
 	/* Insert 1+tgt_free to 2*tgt_free
@@ -273,12 +268,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	int next_cpu = 0;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
-		/* Ther percpu lru list (i.e each cpu has its own LRU
-		 * list) does not have a local free list.  Hence,
-		 * it will only free old nodes till there is no free
-		 * from the LRU list.  Hence, this test does not apply
-		 * to BPF_F_NO_COMMON_LRU
-		 */
+		/* This test is only applicable to common LRU list */
 		return;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
@@ -290,11 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	assert(batch_size * 2 == tgt_free);
 
 	map_size = tgt_free + batch_size;
-	if (map_flags & BPF_F_NO_COMMON_LRU)
-		lru_map_fd = create_map(map_type, map_flags,
-					map_size * nr_cpus);
-	else
-		lru_map_fd = create_map(map_type, map_flags, map_size);
+	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
 	expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
@@ -341,7 +327,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 		assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
 		assert(value[0] == 4321);
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
-				            BPF_NOEXIST));
+					    BPF_NOEXIST));
 	}
 
 	value[0] = 1234;
@@ -361,7 +347,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
-				            BPF_NOEXIST));
+					    BPF_NOEXIST));
 	}
 
 	assert(map_equal(lru_map_fd, expected_map_fd));
@@ -387,6 +373,10 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 	unsigned int map_size;
 	int next_cpu = 0;
 
+	if (map_flags & BPF_F_NO_COMMON_LRU)
+		/* This test is only applicable to common LRU list */
+		return;
+
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
@@ -396,11 +386,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 	assert(batch_size * 2 == tgt_free);
 
 	map_size = tgt_free * 2;
-	if (map_flags & BPF_F_NO_COMMON_LRU)
-		lru_map_fd = create_map(map_type, map_flags,
-					map_size * nr_cpus);
-	else
-		lru_map_fd = create_map(map_type, map_flags, map_size);
+	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
 	expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
@@ -419,7 +405,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
-				            BPF_NOEXIST));
+					    BPF_NOEXIST));
 	}
 
 	/* Add 1+2*tgt_free to tgt_free*5/2
@@ -431,7 +417,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
-				            BPF_NOEXIST));
+					    BPF_NOEXIST));
 	}
 
 	assert(map_equal(lru_map_fd, expected_map_fd));
@@ -491,7 +477,7 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
-				            BPF_NOEXIST));
+					    BPF_NOEXIST));
 	}
 
 	assert(map_equal(lru_map_fd, expected_map_fd));
@@ -566,6 +552,65 @@ static void test_lru_sanity5(int map_type, int map_flags)
 	printf("Pass\n");
 }
 
+/* Test list rotation for BPF_F_NO_COMMON_LRU map */
+static void test_lru_sanity6(int map_type, int map_flags, int tgt_free)
+{
+	int lru_map_fd, expected_map_fd;
+	unsigned long long key, value[nr_cpus];
+	unsigned int map_size = tgt_free * 2;
+	int next_cpu = 0;
+
+	if (!(map_flags & BPF_F_NO_COMMON_LRU))
+		return;
+
+	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+	       map_flags);
+
+	assert(sched_next_online(0, &next_cpu) != -1);
+
+	expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+	assert(expected_map_fd != -1);
+
+	lru_map_fd = create_map(map_type, map_flags, map_size * nr_cpus);
+	assert(lru_map_fd != -1);
+
+	value[0] = 1234;
+
+	for (key = 1; key <= tgt_free; key++) {
+		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+					    BPF_NOEXIST));
+		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+					    BPF_NOEXIST));
+	}
+
+	for (; key <= tgt_free * 2; key++) {
+		unsigned long long stable_key;
+
+		/* Make ref bit sticky for key: [1, tgt_free] */
+		for (stable_key = 1; stable_key <= tgt_free; stable_key++) {
+			/* Mark the ref bit */
+			assert(!bpf_map_lookup_elem(lru_map_fd, &stable_key,
+						    value));
+		}
+		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+					    BPF_NOEXIST));
+	}
+
+	for (; key <= tgt_free * 3; key++) {
+		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
+					    BPF_NOEXIST));
+		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
+					    BPF_NOEXIST));
+	}
+
+	assert(map_equal(lru_map_fd, expected_map_fd));
+
+	close(expected_map_fd);
+	close(lru_map_fd);
+
+	printf("Pass\n");
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -593,6 +638,7 @@ int main(int argc, char **argv)
 			test_lru_sanity3(map_types[t], map_flags[f], tgt_free);
 			test_lru_sanity4(map_types[t], map_flags[f], tgt_free);
 			test_lru_sanity5(map_types[t], map_flags[f]);
+			test_lru_sanity6(map_types[t], map_flags[f], tgt_free);
 
 			printf("\n");
 		}
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index cada17ac00b8..93314524de0d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -28,7 +28,7 @@ static int map_flags;
 
 static void test_hashmap(int task, void *data)
 {
-	long long key, next_key, value;
+	long long key, next_key, first_key, value;
 	int fd;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
@@ -80,18 +80,22 @@ static void test_hashmap(int task, void *data)
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == 0);
 	key = 2;
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
-	key = 1;
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
+	key = 3;
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	       errno == E2BIG);
 
 	/* Check that key = 0 doesn't exist. */
 	key = 0;
 	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
 
 	/* Iterate over two elements. */
+	assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 &&
+	       (first_key == 1 || first_key == 2));
 	assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 &&
-	       (next_key == 1 || next_key == 2));
+	       (next_key == first_key));
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
-	       (next_key == 1 || next_key == 2));
+	       (next_key == 1 || next_key == 2) &&
+	       (next_key != first_key));
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
 	       errno == ENOENT);
 
@@ -104,29 +108,49 @@ static void test_hashmap(int task, void *data)
 
 	key = 0;
 	/* Check that map is empty. */
+	assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 &&
+	       errno == ENOENT);
 	assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 &&
 	       errno == ENOENT);
 
 	close(fd);
 }
 
+static void test_hashmap_sizes(int task, void *data)
+{
+	int fd, i, j;
+
+	for (i = 1; i <= 512; i <<= 1)
+		for (j = 1; j <= 1 << 18; j <<= 1) {
+			fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j,
+					    2, map_flags);
+			if (fd < 0) {
+				printf("Failed to create hashmap key=%d value=%d '%s'\n",
+				       i, j, strerror(errno));
+				exit(1);
+			}
+			close(fd);
+			usleep(10); /* give kernel time to destroy */
+		}
+}
+
 static void test_hashmap_percpu(int task, void *data)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
-	long long value[nr_cpus];
-	long long key, next_key;
+	BPF_DECLARE_PERCPU(long, value);
+	long long key, next_key, first_key;
 	int expected_key_mask = 0;
 	int fd, i;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key),
-			    sizeof(value[0]), 2, map_flags);
+			    sizeof(bpf_percpu(value, 0)), 2, map_flags);
 	if (fd < 0) {
 		printf("Failed to create hashmap '%s'!\n", strerror(errno));
 		exit(1);
 	}
 
 	for (i = 0; i < nr_cpus; i++)
-		value[i] = i + 100;
+		bpf_percpu(value, i) = i + 100;
 
 	key = 1;
 	/* Insert key=1 element. */
@@ -146,8 +170,9 @@ static void test_hashmap_percpu(int task, void *data)
 	/* Check that key=1 can be found. Value could be 0 if the lookup
 	 * was run from a different CPU.
 	 */
-	value[0] = 1;
-	assert(bpf_map_lookup_elem(fd, &key, value) == 0 && value[0] == 100);
+	bpf_percpu(value, 0) = 1;
+	assert(bpf_map_lookup_elem(fd, &key, value) == 0 &&
+	       bpf_percpu(value, 0) == 100);
 
 	key = 2;
 	/* Check that key=2 is not found. */
@@ -174,14 +199,20 @@ static void test_hashmap_percpu(int task, void *data)
 	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
 
 	/* Iterate over two elements. */
+	assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 &&
+	       ((expected_key_mask & first_key) == first_key));
 	while (!bpf_map_get_next_key(fd, &key, &next_key)) {
+		if (first_key) {
+			assert(next_key == first_key);
+			first_key = 0;
+		}
 		assert((expected_key_mask & next_key) == next_key);
 		expected_key_mask &= ~next_key;
 
 		assert(bpf_map_lookup_elem(fd, &next_key, value) == 0);
 
 		for (i = 0; i < nr_cpus; i++)
-			assert(value[i] == i + 100);
+			assert(bpf_percpu(value, i) == i + 100);
 
 		key = next_key;
 	}
@@ -200,6 +231,8 @@ static void test_hashmap_percpu(int task, void *data)
 
 	key = 0;
 	/* Check that map is empty. */
+	assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 &&
+	       errno == ENOENT);
 	assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 &&
 	       errno == ENOENT);
 
@@ -245,6 +278,8 @@ static void test_arraymap(int task, void *data)
 	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
 
 	/* Iterate over two elements. */
+	assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 &&
+	       next_key == 0);
 	assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 &&
 	       next_key == 0);
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
@@ -262,34 +297,36 @@ static void test_arraymap(int task, void *data)
 static void test_arraymap_percpu(int task, void *data)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
+	BPF_DECLARE_PERCPU(long, values);
 	int key, next_key, fd, i;
-	long values[nr_cpus];
 
 	fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
-			    sizeof(values[0]), 2, 0);
+			    sizeof(bpf_percpu(values, 0)), 2, 0);
 	if (fd < 0) {
 		printf("Failed to create arraymap '%s'!\n", strerror(errno));
 		exit(1);
 	}
 
 	for (i = 0; i < nr_cpus; i++)
-		values[i] = i + 100;
+		bpf_percpu(values, i) = i + 100;
 
 	key = 1;
 	/* Insert key=1 element. */
 	assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0);
 
-	values[0] = 0;
+	bpf_percpu(values, 0) = 0;
 	assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) == -1 &&
 	       errno == EEXIST);
 
 	/* Check that key=1 can be found. */
-	assert(bpf_map_lookup_elem(fd, &key, values) == 0 && values[0] == 100);
+	assert(bpf_map_lookup_elem(fd, &key, values) == 0 &&
+	       bpf_percpu(values, 0) == 100);
 
 	key = 0;
 	/* Check that key=0 is also found and zero initialized. */
 	assert(bpf_map_lookup_elem(fd, &key, values) == 0 &&
-	       values[0] == 0 && values[nr_cpus - 1] == 0);
+	       bpf_percpu(values, 0) == 0 &&
+	       bpf_percpu(values, nr_cpus - 1) == 0);
 
 	/* Check that key=2 cannot be inserted due to max_entries limit. */
 	key = 2;
@@ -300,6 +337,8 @@ static void test_arraymap_percpu(int task, void *data)
 	assert(bpf_map_lookup_elem(fd, &key, values) == -1 && errno == ENOENT);
 
 	/* Iterate over two elements. */
+	assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 &&
+	       next_key == 0);
 	assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 &&
 	       next_key == 0);
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
@@ -317,12 +356,15 @@ static void test_arraymap_percpu(int task, void *data)
 static void test_arraymap_percpu_many_keys(void)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
-	unsigned int nr_keys = 20000;
-	long values[nr_cpus];
+	BPF_DECLARE_PERCPU(long, values);
+	/* nr_keys is not too large otherwise the test stresses percpu
+	 * allocator more than anything else
+	 */
+	unsigned int nr_keys = 2000;
 	int key, fd, i;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
-			    sizeof(values[0]), nr_keys, 0);
+			    sizeof(bpf_percpu(values, 0)), nr_keys, 0);
 	if (fd < 0) {
 		printf("Failed to create per-cpu arraymap '%s'!\n",
 		       strerror(errno));
@@ -330,19 +372,19 @@ static void test_arraymap_percpu_many_keys(void)
 	}
 
 	for (i = 0; i < nr_cpus; i++)
-		values[i] = i + 10;
+		bpf_percpu(values, i) = i + 10;
 
 	for (key = 0; key < nr_keys; key++)
 		assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0);
 
 	for (key = 0; key < nr_keys; key++) {
 		for (i = 0; i < nr_cpus; i++)
-			values[i] = 0;
+			bpf_percpu(values, i) = 0;
 
 		assert(bpf_map_lookup_elem(fd, &key, values) == 0);
 
 		for (i = 0; i < nr_cpus; i++)
-			assert(values[i] == i + 10);
+			assert(bpf_percpu(values, i) == i + 10);
 	}
 
 	close(fd);
@@ -378,6 +420,8 @@ static void test_map_large(void)
 	       errno == E2BIG);
 
 	/* Iterate through all elements. */
+	assert(bpf_map_get_next_key(fd, NULL, &key) == 0);
+	key.c = -1;
 	for (i = 0; i < MAP_SIZE; i++)
 		assert(bpf_map_get_next_key(fd, &key, &key) == 0);
 	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
@@ -419,6 +463,7 @@ static void test_map_stress(void)
 {
 	run_parallel(100, test_hashmap, NULL);
 	run_parallel(100, test_hashmap_percpu, NULL);
+	run_parallel(100, test_hashmap_sizes, NULL);
 
 	run_parallel(100, test_arraymap, NULL);
 	run_parallel(100, test_arraymap_percpu, NULL);
@@ -476,6 +521,7 @@ static void test_map_parallel(void)
 	       errno == EEXIST);
 
 	/* Check that all elements were inserted. */
+	assert(bpf_map_get_next_key(fd, NULL, &key) == 0);
 	key = -1;
 	for (i = 0; i < MAP_SIZE; i++)
 		assert(bpf_map_get_next_key(fd, &key, &key) == 0);
@@ -495,6 +541,7 @@ static void test_map_parallel(void)
 
 	/* Nothing should be left. */
 	key = -1;
+	assert(bpf_map_get_next_key(fd, NULL, &key) == -1 && errno == ENOENT);
 	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 }
 
diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c
new file mode 100644
index 000000000000..39387bb7e08c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_pkt_access.c
@@ -0,0 +1,64 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define barrier() __asm__ __volatile__("": : :"memory")
+int _version SEC("version") = 1;
+
+SEC("test1")
+int process(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	struct tcphdr *tcp = NULL;
+	__u8 proto = 255;
+	__u64 ihl_len;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(eth + 1);
+
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+		ihl_len = iph->ihl * 4;
+		proto = iph->protocol;
+		tcp = (struct tcphdr *)((void *)(iph) + ihl_len);
+	} else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1);
+
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+		ihl_len = sizeof(*ip6h);
+		proto = ip6h->nexthdr;
+		tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len);
+	}
+
+	if (tcp) {
+		if (((void *)(tcp) + 20) > data_end || proto != 6)
+			return TC_ACT_SHOT;
+		barrier(); /* to force ordering of checks */
+		if (((void *)(tcp) + 18) > data_end)
+			return TC_ACT_SHOT;
+		if (tcp->urg_ptr == 123)
+			return TC_ACT_OK;
+	}
+
+	return TC_ACT_UNSPEC;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
new file mode 100644
index 000000000000..4ed049a0b14b
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -0,0 +1,283 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <stdlib.h>
+
+#include <linux/types.h>
+typedef __u16 __sum16;
+#include <arpa/inet.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/wait.h>
+#include <sys/resource.h>
+
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "test_iptunnel_common.h"
+#include "bpf_util.h"
+#include "bpf_endian.h"
+
+static int error_cnt, pass_cnt;
+
+#define MAGIC_BYTES 123
+
+/* ipv4 test vector */
+static struct {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_v4 = {
+	.eth.h_proto = bpf_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = 6,
+	.iph.tot_len = bpf_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+};
+
+/* ipv6 test vector */
+static struct {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_v6 = {
+	.eth.h_proto = bpf_htons(ETH_P_IPV6),
+	.iph.nexthdr = 6,
+	.iph.payload_len = bpf_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+};
+
+#define CHECK(condition, tag, format...) ({				\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		error_cnt++;						\
+		printf("%s:FAIL:%s ", __func__, tag);			\
+		printf(format);						\
+	} else {							\
+		pass_cnt++;						\
+		printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\
+	}								\
+})
+
+static int bpf_prog_load(const char *file, enum bpf_prog_type type,
+			 struct bpf_object **pobj, int *prog_fd)
+{
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int err;
+
+	obj = bpf_object__open(file);
+	if (IS_ERR(obj)) {
+		error_cnt++;
+		return -ENOENT;
+	}
+
+	prog = bpf_program__next(NULL, obj);
+	if (!prog) {
+		bpf_object__close(obj);
+		error_cnt++;
+		return -ENOENT;
+	}
+
+	bpf_program__set_type(prog, type);
+	err = bpf_object__load(obj);
+	if (err) {
+		bpf_object__close(obj);
+		error_cnt++;
+		return -EINVAL;
+	}
+
+	*pobj = obj;
+	*prog_fd = bpf_program__fd(prog);
+	return 0;
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		error_cnt++;
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+static void test_pkt_access(void)
+{
+	const char *file = "./test_pkt_access.o";
+	struct bpf_object *obj;
+	__u32 duration, retval;
+	int err, prog_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err)
+		return;
+
+	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || errno || retval, "ipv4",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || errno || retval, "ipv6",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+	bpf_object__close(obj);
+}
+
+static void test_xdp(void)
+{
+	struct vip key4 = {.protocol = 6, .family = AF_INET};
+	struct vip key6 = {.protocol = 6, .family = AF_INET6};
+	struct iptnl_info value4 = {.family = AF_INET};
+	struct iptnl_info value6 = {.family = AF_INET6};
+	const char *file = "./test_xdp.o";
+	struct bpf_object *obj;
+	char buf[128];
+	struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr);
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	__u32 duration, retval, size;
+	int err, prog_fd, map_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (err)
+		return;
+
+	map_fd = bpf_find_map(__func__, obj, "vip2tnl");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &key4, &value4, 0);
+	bpf_map_update_elem(map_fd, &key6, &value6, 0);
+
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+
+	CHECK(err || errno || retval != XDP_TX || size != 74 ||
+	      iph->protocol != IPPROTO_IPIP, "ipv4",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != XDP_TX || size != 114 ||
+	      iph6->nexthdr != IPPROTO_IPV6, "ipv6",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+out:
+	bpf_object__close(obj);
+}
+
+#define MAGIC_VAL 0x1234
+#define NUM_ITER 100000
+#define VIP_NUM 5
+
+static void test_l4lb(void)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	const char *file = "./test_l4lb.o";
+	struct vip key = {.protocol = 6};
+	struct vip_meta {
+		__u32 flags;
+		__u32 vip_num;
+	} value = {.vip_num = VIP_NUM};
+	__u32 stats_key = VIP_NUM;
+	struct vip_stats {
+		__u64 bytes;
+		__u64 pkts;
+	} stats[nr_cpus];
+	struct real_definition {
+		union {
+			__be32 dst;
+			__be32 dstv6[4];
+		};
+		__u8 flags;
+	} real_def = {.dst = MAGIC_VAL};
+	__u32 ch_key = 11, real_num = 3;
+	__u32 duration, retval, size;
+	int err, i, prog_fd, map_fd;
+	__u64 bytes = 0, pkts = 0;
+	struct bpf_object *obj;
+	char buf[128];
+	u32 *magic = (u32 *)buf;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err)
+		return;
+
+	map_fd = bpf_find_map(__func__, obj, "vip_map");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &key, &value, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "ch_rings");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "reals");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+	      *magic != MAGIC_VAL, "ipv4",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+	      *magic != MAGIC_VAL, "ipv6",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	map_fd = bpf_find_map(__func__, obj, "stats");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_lookup_elem(map_fd, &stats_key, stats);
+	for (i = 0; i < nr_cpus; i++) {
+		bytes += stats[i].bytes;
+		pkts += stats[i].pkts;
+	}
+	if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
+		error_cnt++;
+		printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts);
+	}
+out:
+	bpf_object__close(obj);
+}
+
+int main(void)
+{
+	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+
+	setrlimit(RLIMIT_MEMLOCK, &rinf);
+
+	test_pkt_access();
+	test_xdp();
+	test_l4lb();
+
+	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index e1f5b9eea1e8..3773562056da 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -8,6 +8,8 @@
  * License as published by the Free Software Foundation.
  */
 
+#include <asm/types.h>
+#include <linux/types.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -28,6 +30,14 @@
 
 #include <bpf/bpf.h>
 
+#ifdef HAVE_GENHDR
+# include "autoconf.h"
+#else
+# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
+#  define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
+# endif
+#endif
+
 #include "../../../include/linux/filter.h"
 
 #ifndef ARRAY_SIZE
@@ -36,6 +46,9 @@
 
 #define MAX_INSNS	512
 #define MAX_FIXUPS	8
+#define MAX_NR_MAPS	4
+
+#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 
 struct bpf_test {
 	const char *descr;
@@ -43,6 +56,7 @@ struct bpf_test {
 	int fixup_map1[MAX_FIXUPS];
 	int fixup_map2[MAX_FIXUPS];
 	int fixup_prog[MAX_FIXUPS];
+	int fixup_map_in_map[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	enum {
@@ -51,6 +65,7 @@ struct bpf_test {
 		REJECT
 	} result, result_unpriv;
 	enum bpf_prog_type prog_type;
+	uint8_t flags;
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -176,6 +191,86 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 	},
 	{
+		"test6 ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0),
+			BPF_RAW_INSN(0, 0, 0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"test7 ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1),
+			BPF_RAW_INSN(0, 0, 0, 0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"test8 ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 1, 1),
+			BPF_RAW_INSN(0, 0, 0, 0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "uses reserved fields",
+		.result = REJECT,
+	},
+	{
+		"test9 ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1),
+			BPF_RAW_INSN(0, 0, 0, 1, 1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_ld_imm64 insn",
+		.result = REJECT,
+	},
+	{
+		"test10 ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1),
+			BPF_RAW_INSN(0, BPF_REG_1, 0, 0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_ld_imm64 insn",
+		.result = REJECT,
+	},
+	{
+		"test11 ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1),
+			BPF_RAW_INSN(0, 0, BPF_REG_1, 0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_ld_imm64 insn",
+		.result = REJECT,
+	},
+	{
+		"test12 ld_imm64",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1),
+			BPF_RAW_INSN(0, 0, 0, 0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "not pointing to valid bpf_map",
+		.result = REJECT,
+	},
+	{
+		"test13 ld_imm64",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1),
+			BPF_RAW_INSN(0, 0, BPF_REG_1, 0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_ld_imm64 insn",
+		.result = REJECT,
+	},
+	{
 		"no bpf_exit",
 		.insns = {
 			BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2),
@@ -316,6 +411,30 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 	},
 	{
+		"invalid fp arithmetic",
+		/* If this gets ever changed, make sure JITs can deal with it. */
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "R1 pointer arithmetic",
+		.result_unpriv = REJECT,
+		.errstr = "R1 invalid mem access",
+		.result = REJECT,
+	},
+	{
+		"non-invalid fp arithmetic",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
 		"invalid argument register",
 		.insns = {
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
@@ -757,6 +876,9 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
 				    offsetof(struct __sk_buff, vlan_tci)),
 			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
@@ -1783,6 +1905,20 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
+		"unpriv: adding of fp",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "pointer arithmetic prohibited",
+		.result_unpriv = REJECT,
+		.errstr = "R1 invalid mem access",
+		.result = REJECT,
+	},
+	{
 		"unpriv: cmp of stack pointer",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -1796,16 +1932,22 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"unpriv: obfuscate stack pointer",
+		"stack pointer arithmetic",
 		.insns = {
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+			BPF_ST_MEM(0, BPF_REG_2, 4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_ST_MEM(0, BPF_REG_2, 4, 0),
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr_unpriv = "R2 pointer arithmetic",
-		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
 	{
@@ -2430,6 +2572,49 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
+		"direct packet access: test15 (spill with xadd)",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+			BPF_MOV64_IMM(BPF_REG_5, 4096),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+			BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R2 invalid mem access 'inv'",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"direct packet access: test16 (arith on data_end)",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 16),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid access to packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
 		"helper access to packet: test1, valid packet_ptr range",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -2932,6 +3117,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"valid map access into an array with a variable",
@@ -2955,6 +3141,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"valid map access into an array with a signed variable",
@@ -2982,6 +3169,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid map access into an array with a constant",
@@ -3023,6 +3211,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R0 min value is outside of the array range",
 		.result_unpriv = REJECT,
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid map access into an array with a variable",
@@ -3046,6 +3235,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result_unpriv = REJECT,
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid map access into an array with no floor check",
@@ -3072,6 +3262,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result_unpriv = REJECT,
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid map access into an array with a invalid max check",
@@ -3098,6 +3289,7 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid access to map value, value_size=48 off=44 size=8",
 		.result_unpriv = REJECT,
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid map access into an array with a invalid max check",
@@ -3127,6 +3319,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result_unpriv = REJECT,
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"multiple registers share map_lookup_elem result",
@@ -3250,6 +3443,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"constant register |= constant should keep constant type",
@@ -3416,6 +3610,26 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
 	},
 	{
+		"overlapping checks for direct packet access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
+	},
+	{
 		"invalid access of tc_classid for LWT_IN",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -3959,7 +4173,208 @@ static struct bpf_test tests[] = {
 		.result_unpriv = REJECT,
 	},
 	{
-		"map element value (adjusted) is preserved across register spilling",
+		"map element value or null is marked on register spilling",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 leaks addr",
+		.result = ACCEPT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value store of cleared call register",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R1 !read_ok",
+		.errstr = "R1 !read_ok",
+		.result = REJECT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value with unaligned store",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44),
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32),
+			BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33),
+			BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5),
+			BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22),
+			BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23),
+			BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3),
+			BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22),
+			BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23),
+			BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 pointer arithmetic prohibited",
+		.result = ACCEPT,
+		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"map element value with unaligned load",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2),
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 pointer arithmetic prohibited",
+		.result = ACCEPT,
+		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"map element value illegal alu op, 1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 pointer arithmetic prohibited",
+		.errstr = "invalid mem access 'inv'",
+		.result = REJECT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value illegal alu op, 2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 pointer arithmetic prohibited",
+		.errstr = "invalid mem access 'inv'",
+		.result = REJECT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value illegal alu op, 3",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 pointer arithmetic prohibited",
+		.errstr = "invalid mem access 'inv'",
+		.result = REJECT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value illegal alu op, 4",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 pointer arithmetic prohibited",
+		.errstr = "invalid mem access 'inv'",
+		.result = REJECT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value illegal alu op, 5",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			BPF_MOV64_IMM(BPF_REG_3, 4096),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 3 },
+		.errstr_unpriv = "R0 invalid mem access 'inv'",
+		.errstr = "R0 invalid mem access 'inv'",
+		.result = REJECT,
+		.result_unpriv = REJECT,
+	},
+	{
+		"map element value is preserved across register spilling",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
@@ -3981,6 +4396,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
@@ -4419,6 +4835,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result = REJECT,
 		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid range check",
@@ -4450,6 +4867,76 @@ static struct bpf_test tests[] = {
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result = REJECT,
 		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"map in map access",
+		.insns = {
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_in_map = { 3 },
+		.result = ACCEPT,
+	},
+	{
+		"invalid inner map pointer",
+		.insns = {
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_in_map = { 3 },
+		.errstr = "R1 type=inv expected=map_ptr",
+		.errstr_unpriv = "R1 pointer arithmetic prohibited",
+		.result = REJECT,
+	},
+	{
+		"forgot null checking on the inner map pointer",
+		.insns = {
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_in_map = { 3 },
+		.errstr = "R1 type=map_value_or_null expected=map_ptr",
+		.result = REJECT,
 	}
 };
 
@@ -4487,55 +4974,90 @@ static int create_prog_array(void)
 	return fd;
 }
 
+static int create_map_in_map(void)
+{
+	int inner_map_fd, outer_map_fd;
+
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+				      sizeof(int), 1, 0);
+	if (inner_map_fd < 0) {
+		printf("Failed to create array '%s'!\n", strerror(errno));
+		return inner_map_fd;
+	}
+
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS,
+					     sizeof(int), inner_map_fd, 1, 0);
+	if (outer_map_fd < 0)
+		printf("Failed to create array of maps '%s'!\n",
+		       strerror(errno));
+
+	close(inner_map_fd);
+
+	return outer_map_fd;
+}
+
 static char bpf_vlog[32768];
 
 static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
-			  int *fd_f1, int *fd_f2, int *fd_f3)
+			  int *map_fds)
 {
 	int *fixup_map1 = test->fixup_map1;
 	int *fixup_map2 = test->fixup_map2;
 	int *fixup_prog = test->fixup_prog;
+	int *fixup_map_in_map = test->fixup_map_in_map;
 
 	/* Allocating HTs with 1 elem is fine here, since we only test
 	 * for verifier and not do a runtime lookup, so the only thing
 	 * that really matters is value size in this case.
 	 */
 	if (*fixup_map1) {
-		*fd_f1 = create_map(sizeof(long long), 1);
+		map_fds[0] = create_map(sizeof(long long), 1);
 		do {
-			prog[*fixup_map1].imm = *fd_f1;
+			prog[*fixup_map1].imm = map_fds[0];
 			fixup_map1++;
 		} while (*fixup_map1);
 	}
 
 	if (*fixup_map2) {
-		*fd_f2 = create_map(sizeof(struct test_val), 1);
+		map_fds[1] = create_map(sizeof(struct test_val), 1);
 		do {
-			prog[*fixup_map2].imm = *fd_f2;
+			prog[*fixup_map2].imm = map_fds[1];
 			fixup_map2++;
 		} while (*fixup_map2);
 	}
 
 	if (*fixup_prog) {
-		*fd_f3 = create_prog_array();
+		map_fds[2] = create_prog_array();
 		do {
-			prog[*fixup_prog].imm = *fd_f3;
+			prog[*fixup_prog].imm = map_fds[2];
 			fixup_prog++;
 		} while (*fixup_prog);
 	}
+
+	if (*fixup_map_in_map) {
+		map_fds[3] = create_map_in_map();
+		do {
+			prog[*fixup_map_in_map].imm = map_fds[3];
+			fixup_map_in_map++;
+		} while (*fixup_map_in_map);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
+	int fd_prog, expected_ret, reject_from_alignment;
 	struct bpf_insn *prog = test->insns;
 	int prog_len = probe_filter_length(prog);
 	int prog_type = test->prog_type;
-	int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1;
-	int fd_prog, expected_ret;
+	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
+	int i;
 
-	do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
+	for (i = 0; i < MAX_NR_MAPS; i++)
+		map_fds[i] = -1;
+
+	do_test_fixup(test, prog, map_fds);
 
 	fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
 				   prog, prog_len, "GPL", 0, bpf_vlog,
@@ -4545,8 +5067,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		       test->result_unpriv : test->result;
 	expected_err = unpriv && test->errstr_unpriv ?
 		       test->errstr_unpriv : test->errstr;
+
+	reject_from_alignment = fd_prog < 0 &&
+				(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
+				strstr(bpf_vlog, "Unknown alignment.");
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (reject_from_alignment) {
+		printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
+		       strerror(errno));
+		goto fail_log;
+	}
+#endif
 	if (expected_ret == ACCEPT) {
-		if (fd_prog < 0) {
+		if (fd_prog < 0 && !reject_from_alignment) {
 			printf("FAIL\nFailed to load prog '%s'!\n",
 			       strerror(errno));
 			goto fail_log;
@@ -4556,19 +5089,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			printf("FAIL\nUnexpected success to load!\n");
 			goto fail_log;
 		}
-		if (!strstr(bpf_vlog, expected_err)) {
+		if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
 			printf("FAIL\nUnexpected error message!\n");
 			goto fail_log;
 		}
 	}
 
 	(*passes)++;
-	printf("OK\n");
+	printf("OK%s\n", reject_from_alignment ?
+	       " (NOTE: reject due to unknown alignment)" : "");
 close_fds:
 	close(fd_prog);
-	close(fd_f1);
-	close(fd_f2);
-	close(fd_f3);
+	for (i = 0; i < MAX_NR_MAPS; i++)
+		close(map_fds[i]);
 	sched_yield();
 	return;
 fail_log:
@@ -4583,10 +5116,12 @@ static bool is_admin(void)
 	cap_flag_value_t sysadmin = CAP_CLEAR;
 	const cap_value_t cap_val = CAP_SYS_ADMIN;
 
+#ifdef CAP_IS_SUPPORTED
 	if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) {
 		perror("cap_get_flag");
 		return false;
 	}
+#endif
 	caps = cap_get_proc();
 	if (!caps) {
 		perror("cap_get_proc");
diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/test_xdp.c
new file mode 100644
index 000000000000..5e7df8bb5b5d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp.c
@@ -0,0 +1,235 @@
+/* Copyright (c) 2016,2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_iptunnel_common.h"
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def SEC("maps") rxcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 256,
+};
+
+struct bpf_map_def SEC("maps") vip2tnl = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct iptnl_info),
+	.max_entries = MAX_IPTNL_ENTRIES,
+};
+
+static __always_inline void count_tx(__u32 protocol)
+{
+	__u64 *rxcnt_count;
+
+	rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+	if (rxcnt_count)
+		*rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, void *data_end,
+				     __u8 protocol)
+{
+	struct tcphdr *th;
+	struct udphdr *uh;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		th = (struct tcphdr *)trans_data;
+		if (th + 1 > data_end)
+			return -1;
+		return th->dest;
+	case IPPROTO_UDP:
+		uh = (struct udphdr *)trans_data;
+		if (uh + 1 > data_end)
+			return -1;
+		return uh->dest;
+	default:
+		return 0;
+	}
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+				       const struct ethhdr *old_eth,
+				       const struct iptnl_info *tnl,
+				       __be16 h_proto)
+{
+	memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+	memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+	new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct iphdr *iph = data + sizeof(struct ethhdr);
+	__u16 *next_iph;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+	__u32 csum = 0;
+	int i;
+
+	if (iph + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(iph + 1, data_end, iph->protocol);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = iph->protocol;
+	vip.family = AF_INET;
+	vip.daddr.v4 = iph->daddr;
+	vip.dport = dport;
+	payload_len = bpf_ntohs(iph->tot_len);
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v4-in-v4 */
+	if (!tnl || tnl->family != AF_INET)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	iph = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*iph);
+
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end ||
+	    iph + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP));
+
+	iph->version = 4;
+	iph->ihl = sizeof(*iph) >> 2;
+	iph->frag_off =	0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 0;
+	iph->tot_len = bpf_htons(payload_len + sizeof(*iph));
+	iph->daddr = tnl->daddr.v4;
+	iph->saddr = tnl->saddr.v4;
+	iph->ttl = 8;
+
+	next_iph = (__u16 *)iph;
+#pragma clang loop unroll(full)
+	for (i = 0; i < sizeof(*iph) >> 1; i++)
+		csum += *next_iph++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+
+	if (ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = ip6h->nexthdr;
+	vip.family = AF_INET6;
+	memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+	vip.dport = dport;
+	payload_len = ip6h->payload_len;
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v6-in-v6 */
+	if (!tnl || tnl->family != AF_INET6)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	ip6h = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*ip6h);
+
+	if (new_eth + 1 > data_end || old_eth + 1 > data_end ||
+	    ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6));
+
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+	ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h));
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip6h->hop_limit = 8;
+	memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+	memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+SEC("xdp_tx_iptunnel")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u16 h_proto;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == bpf_htons(ETH_P_IP))
+		return handle_ipv4(xdp);
+	else if (h_proto == bpf_htons(ETH_P_IPV6))
+
+		return handle_ipv6(xdp);
+	else
+		return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
new file mode 100644
index 000000000000..bab5ff7c607e
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -0,0 +1,117 @@
+#!/bin/sh
+# description: ftrace - function pid filters
+
+# Make sure that function pid matching filter works.
+# Also test it on an instance directory
+
+if ! grep -q function available_tracers; then
+    echo "no function tracer configured"
+    exit_unsupported
+fi
+
+if [ ! -f set_ftrace_pid ]; then
+    echo "set_ftrace_pid not found? Is function tracer not set?"
+    exit_unsupported
+fi
+
+if [ ! -f set_ftrace_filter ]; then
+    echo "set_ftrace_filter not found? Is function tracer not set?"
+    exit_unsupported
+fi
+
+do_function_fork=1
+
+if [ ! -f options/function-fork ]; then
+    do_function_fork=0
+    echo "no option for function-fork found. Option will not be tested."
+fi
+
+read PID _ < /proc/self/stat
+
+if [ $do_function_fork -eq 1 ]; then
+    # default value of function-fork option
+    orig_value=`grep function-fork trace_options`
+fi
+
+do_reset() {
+    reset_tracer
+    clear_trace
+    enable_tracing
+    echo > set_ftrace_filter
+    echo > set_ftrace_pid
+
+    if [ $do_function_fork -eq 0 ]; then
+	return
+    fi
+
+    echo $orig_value > trace_options
+}
+
+fail() { # msg
+    do_reset
+    echo $1
+    exit $FAIL
+}
+
+yield() {
+    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
+}
+
+do_test() {
+    disable_tracing
+
+    echo do_execve* > set_ftrace_filter
+    echo *do_fork >> set_ftrace_filter
+
+    echo $PID > set_ftrace_pid
+    echo function > current_tracer
+
+    if [ $do_function_fork -eq 1 ]; then
+	# don't allow children to be traced
+	echo nofunction-fork > trace_options
+    fi
+
+    enable_tracing
+    yield
+
+    count_pid=`cat trace | grep -v ^# | grep $PID | wc -l`
+    count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l`
+
+    # count_other should be 0
+    if [ $count_pid -eq 0 -o $count_other -ne 0 ]; then
+	fail "PID filtering not working?"
+    fi
+
+    disable_tracing
+    clear_trace
+
+    if [ $do_function_fork -eq 0 ]; then
+	return
+    fi
+
+    # allow children to be traced
+    echo function-fork > trace_options
+
+    enable_tracing
+    yield
+
+    count_pid=`cat trace | grep -v ^# | grep $PID | wc -l`
+    count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l`
+
+    # count_other should NOT be 0
+    if [ $count_pid -eq 0 -o $count_other -eq 0 ]; then
+	fail "PID filtering not following fork?"
+    fi
+}
+
+do_test
+
+mkdir instances/foo
+cd instances/foo
+do_test
+cd ../../
+rmdir instances/foo
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index fbfe5d0d5c2e..35cbb4cba410 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I../../../../usr/include/
 
 reuseport_bpf_numa: LDFLAGS += -lnuma
 
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket
 TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
new file mode 100755
index 000000000000..4e00568d70c2
--- /dev/null
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -0,0 +1,200 @@
+#!/bin/sh
+#
+# This test is for checking network interface
+# For the moment it tests only ethernet interface (but wifi could be easily added)
+#
+# We assume that all network driver are loaded
+# if not they probably have failed earlier in the boot process and their logged error will be catched by another test
+#
+
+# this function will try to up the interface
+# if already up, nothing done
+# arg1: network interface name
+kci_net_start()
+{
+	netdev=$1
+
+	ip link show "$netdev" |grep -q UP
+	if [ $? -eq 0 ];then
+		echo "SKIP: $netdev: interface already up"
+		return 0
+	fi
+
+	ip link set "$netdev" up
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: Fail to up interface"
+		return 1
+	else
+		echo "PASS: $netdev: set interface up"
+		NETDEV_STARTED=1
+	fi
+	return 0
+}
+
+# this function will try to setup an IP and MAC address on a network interface
+# Doing nothing if the interface was already up
+# arg1: network interface name
+kci_net_setup()
+{
+	netdev=$1
+
+	# do nothing if the interface was already up
+	if [ $NETDEV_STARTED -eq 0 ];then
+		return 0
+	fi
+
+	MACADDR='02:03:04:05:06:07'
+	ip link set dev $netdev address "$MACADDR"
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: Cannot set MAC address"
+	else
+		ip link show $netdev |grep -q "$MACADDR"
+		if [ $? -eq 0 ];then
+			echo "PASS: $netdev: set MAC address"
+		else
+			echo "FAIL: $netdev: Cannot set MAC address"
+		fi
+	fi
+
+	#check that the interface did not already have an IP
+	ip address show "$netdev" |grep '^[[:space:]]*inet'
+	if [ $? -eq 0 ];then
+		echo "SKIP: $netdev: already have an IP"
+		return 0
+	fi
+
+	# TODO what ipaddr to set ? DHCP ?
+	echo "SKIP: $netdev: set IP address"
+	return 0
+}
+
+# test an ethtool command
+# arg1: return code for not supported (see ethtool code source)
+# arg2: summary of the command
+# arg3: command to execute
+kci_netdev_ethtool_test()
+{
+	if [ $# -le 2 ];then
+		echo "SKIP: $netdev: ethtool: invalid number of arguments"
+		return 1
+	fi
+	$3 >/dev/null
+	ret=$?
+	if [ $ret -ne 0 ];then
+		if [ $ret -eq "$1" ];then
+			echo "SKIP: $netdev: ethtool $2 not supported"
+		else
+			echo "FAIL: $netdev: ethtool $2"
+			return 1
+		fi
+	else
+		echo "PASS: $netdev: ethtool $2"
+	fi
+	return 0
+}
+
+# test ethtool commands
+# arg1: network interface name
+kci_netdev_ethtool()
+{
+	netdev=$1
+
+	#check presence of ethtool
+	ethtool --version 2>/dev/null >/dev/null
+	if [ $? -ne 0 ];then
+		echo "SKIP: ethtool not present"
+		return 1
+	fi
+
+	TMP_ETHTOOL_FEATURES="$(mktemp)"
+	if [ ! -e "$TMP_ETHTOOL_FEATURES" ];then
+		echo "SKIP: Cannot create a tmp file"
+		return 1
+	fi
+
+	ethtool -k "$netdev" > "$TMP_ETHTOOL_FEATURES"
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: ethtool list features"
+		rm "$TMP_ETHTOOL_FEATURES"
+		return 1
+	fi
+	echo "PASS: $netdev: ethtool list features"
+	#TODO for each non fixed features, try to turn them on/off
+	rm "$TMP_ETHTOOL_FEATURES"
+
+	kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev"
+	kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev"
+	return 0
+}
+
+# stop a netdev
+# arg1: network interface name
+kci_netdev_stop()
+{
+	netdev=$1
+
+	if [ $NETDEV_STARTED -eq 0 ];then
+		echo "SKIP: $netdev: interface kept up"
+		return 0
+	fi
+
+	ip link set "$netdev" down
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: stop interface"
+		return 1
+	fi
+	echo "PASS: $netdev: stop interface"
+	return 0
+}
+
+# run all test on a netdev
+# arg1: network interface name
+kci_test_netdev()
+{
+	NETDEV_STARTED=0
+	IFACE_TO_UPDOWN="$1"
+	IFACE_TO_TEST="$1"
+	#check for VLAN interface
+	MASTER_IFACE="$(echo $1 | cut -d@ -f2)"
+	if [ ! -z "$MASTER_IFACE" ];then
+		IFACE_TO_UPDOWN="$MASTER_IFACE"
+		IFACE_TO_TEST="$(echo $1 | cut -d@ -f1)"
+	fi
+
+	NETDEV_STARTED=0
+	kci_net_start "$IFACE_TO_UPDOWN"
+
+	kci_net_setup "$IFACE_TO_TEST"
+
+	kci_netdev_ethtool "$IFACE_TO_TEST"
+
+	kci_netdev_stop "$IFACE_TO_UPDOWN"
+	return 0
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit 0
+fi
+
+ip -Version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without the ip tool"
+	exit 0
+fi
+
+TMP_LIST_NETDEV="$(mktemp)"
+if [ ! -e "$TMP_LIST_NETDEV" ];then
+	echo "FAIL: Cannot create a tmp file"
+	exit 1
+fi
+
+ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\  -f2 | cut -d: -f1> "$TMP_LIST_NETDEV"
+while read netdev
+do
+	kci_test_netdev "$netdev"
+done < "$TMP_LIST_NETDEV"
+
+rm "$TMP_LIST_NETDEV"
+exit 0
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 412459369686..989f917068d1 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -71,18 +71,17 @@
 
 /* Open a socket in a given fanout mode.
  * @return -1 if mode is bad, a valid socket otherwise */
-static int sock_fanout_open(uint16_t typeflags, int num_packets)
+static int sock_fanout_open(uint16_t typeflags, uint16_t group_id)
 {
 	int fd, val;
 
-	fd = socket(PF_PACKET, SOCK_DGRAM, htons(ETH_P_IP));
+	fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP));
 	if (fd < 0) {
 		perror("socket packet");
 		exit(1);
 	}
 
-	/* fanout group ID is always 0: tests whether old groups are deleted */
-	val = ((int) typeflags) << 16;
+	val = (((int) typeflags) << 16) | group_id;
 	if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) {
 		if (close(fd)) {
 			perror("close packet");
@@ -95,6 +94,38 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets)
 	return fd;
 }
 
+static void sock_fanout_set_cbpf(int fd)
+{
+	struct sock_filter bpf_filter[] = {
+		BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80),	      /* ldb [80] */
+		BPF_STMT(BPF_RET+BPF_A, 0),		      /* ret A */
+	};
+	struct sock_fprog bpf_prog;
+
+	bpf_prog.filter = bpf_filter;
+	bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter);
+
+	if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog,
+		       sizeof(bpf_prog))) {
+		perror("fanout data cbpf");
+		exit(1);
+	}
+}
+
+static void sock_fanout_getopts(int fd, uint16_t *typeflags, uint16_t *group_id)
+{
+	int sockopt;
+	socklen_t sockopt_len = sizeof(sockopt);
+
+	if (getsockopt(fd, SOL_PACKET, PACKET_FANOUT,
+		       &sockopt, &sockopt_len)) {
+		perror("failed to getsockopt");
+		exit(1);
+	}
+	*typeflags = sockopt >> 16;
+	*group_id = sockopt & 0xfffff;
+}
+
 static void sock_fanout_set_ebpf(int fd)
 {
 	const int len_off = __builtin_offsetof(struct __sk_buff, len);
@@ -223,26 +254,26 @@ static void test_control_group(void)
 
 	fprintf(stderr, "test: control multiple sockets\n");
 
-	fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 20);
+	fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
 	if (fds[0] == -1) {
 		fprintf(stderr, "ERROR: failed to open HASH socket\n");
 		exit(1);
 	}
 	if (sock_fanout_open(PACKET_FANOUT_HASH |
-			       PACKET_FANOUT_FLAG_DEFRAG, 10) != -1) {
+			       PACKET_FANOUT_FLAG_DEFRAG, 0) != -1) {
 		fprintf(stderr, "ERROR: joined group with wrong flag defrag\n");
 		exit(1);
 	}
 	if (sock_fanout_open(PACKET_FANOUT_HASH |
-			       PACKET_FANOUT_FLAG_ROLLOVER, 10) != -1) {
+			       PACKET_FANOUT_FLAG_ROLLOVER, 0) != -1) {
 		fprintf(stderr, "ERROR: joined group with wrong flag ro\n");
 		exit(1);
 	}
-	if (sock_fanout_open(PACKET_FANOUT_CPU, 10) != -1) {
+	if (sock_fanout_open(PACKET_FANOUT_CPU, 0) != -1) {
 		fprintf(stderr, "ERROR: joined group with wrong mode\n");
 		exit(1);
 	}
-	fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 20);
+	fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
 	if (fds[1] == -1) {
 		fprintf(stderr, "ERROR: failed to join group\n");
 		exit(1);
@@ -253,6 +284,61 @@ static void test_control_group(void)
 	}
 }
 
+/* Test creating a unique fanout group ids */
+static void test_unique_fanout_group_ids(void)
+{
+	int fds[3];
+	uint16_t typeflags, first_group_id, second_group_id;
+
+	fprintf(stderr, "test: unique ids\n");
+
+	fds[0] = sock_fanout_open(PACKET_FANOUT_HASH |
+				  PACKET_FANOUT_FLAG_UNIQUEID, 0);
+	if (fds[0] == -1) {
+		fprintf(stderr, "ERROR: failed to create a unique id group.\n");
+		exit(1);
+	}
+
+	sock_fanout_getopts(fds[0], &typeflags, &first_group_id);
+	if (typeflags != PACKET_FANOUT_HASH) {
+		fprintf(stderr, "ERROR: unexpected typeflags %x\n", typeflags);
+		exit(1);
+	}
+
+	if (sock_fanout_open(PACKET_FANOUT_CPU, first_group_id) != -1) {
+		fprintf(stderr, "ERROR: joined group with wrong type.\n");
+		exit(1);
+	}
+
+	fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, first_group_id);
+	if (fds[1] == -1) {
+		fprintf(stderr,
+			"ERROR: failed to join previously created group.\n");
+		exit(1);
+	}
+
+	fds[2] = sock_fanout_open(PACKET_FANOUT_HASH |
+				  PACKET_FANOUT_FLAG_UNIQUEID, 0);
+	if (fds[2] == -1) {
+		fprintf(stderr,
+			"ERROR: failed to create a second unique id group.\n");
+		exit(1);
+	}
+
+	sock_fanout_getopts(fds[2], &typeflags, &second_group_id);
+	if (sock_fanout_open(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_UNIQUEID,
+			     second_group_id) != -1) {
+		fprintf(stderr,
+			"ERROR: specified a group id when requesting unique id\n");
+		exit(1);
+	}
+
+	if (close(fds[0]) || close(fds[1]) || close(fds[2])) {
+		fprintf(stderr, "ERROR: closing sockets\n");
+		exit(1);
+	}
+}
+
 static int test_datapath(uint16_t typeflags, int port_off,
 			 const int expect1[], const int expect2[])
 {
@@ -263,14 +349,14 @@ static int test_datapath(uint16_t typeflags, int port_off,
 
 	fprintf(stderr, "test: datapath 0x%hx\n", typeflags);
 
-	fds[0] = sock_fanout_open(typeflags, 20);
-	fds[1] = sock_fanout_open(typeflags, 20);
+	fds[0] = sock_fanout_open(typeflags, 0);
+	fds[1] = sock_fanout_open(typeflags, 0);
 	if (fds[0] == -1 || fds[1] == -1) {
 		fprintf(stderr, "ERROR: failed open\n");
 		exit(1);
 	}
 	if (type == PACKET_FANOUT_CBPF)
-		sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA);
+		sock_fanout_set_cbpf(fds[0]);
 	else if (type == PACKET_FANOUT_EBPF)
 		sock_fanout_set_ebpf(fds[0]);
 
@@ -331,10 +417,12 @@ int main(int argc, char **argv)
 	const int expect_cpu0[2][2]	= { { 20, 0 },  { 20, 0 } };
 	const int expect_cpu1[2][2]	= { { 0, 20 },  { 0, 20 } };
 	const int expect_bpf[2][2]	= { { 15, 5 },  { 15, 20 } };
+	const int expect_uniqueid[2][2] = { { 20, 20},  { 20, 20 } };
 	int port_off = 2, tries = 5, ret;
 
 	test_control_single();
 	test_control_group();
+	test_unique_fanout_group_ids();
 
 	/* find a set of ports that do not collide onto the same socket */
 	ret = test_datapath(PACKET_FANOUT_HASH, port_off,
@@ -365,6 +453,9 @@ int main(int argc, char **argv)
 		ret |= test_datapath(PACKET_FANOUT_CPU, port_off,
 				     expect_cpu1[0], expect_cpu1[1]);
 
+	ret |= test_datapath(PACKET_FANOUT_FLAG_UNIQUEID, port_off,
+			     expect_uniqueid[0], expect_uniqueid[1]);
+
 	if (ret)
 		return 1;
 
diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h
index a77da88bf946..7d990d6c861b 100644
--- a/tools/testing/selftests/net/psock_lib.h
+++ b/tools/testing/selftests/net/psock_lib.h
@@ -38,7 +38,7 @@
 # define __maybe_unused		__attribute__ ((__unused__))
 #endif
 
-static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum)
+static __maybe_unused void pair_udp_setfilter(int fd)
 {
 	/* the filter below checks for all of the following conditions that
 	 * are based on the contents of create_payload()
@@ -76,23 +76,16 @@ static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum)
 	};
 	struct sock_fprog bpf_prog;
 
-	if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA)
-		bpf_filter[5].code = 0x16;   /* RET A			      */
-
 	bpf_prog.filter = bpf_filter;
 	bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter);
-	if (setsockopt(fd, lvl, optnum, &bpf_prog,
+
+	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog,
 		       sizeof(bpf_prog))) {
 		perror("setsockopt SO_ATTACH_FILTER");
 		exit(1);
 	}
 }
 
-static __maybe_unused void pair_udp_setfilter(int fd)
-{
-	sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER);
-}
-
 static __maybe_unused void pair_udp_open(int fds[], uint16_t port)
 {
 	struct sockaddr_in saddr, daddr;
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 1c5d0575802e..bf13fc2297aa 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -34,34 +34,34 @@ endif
 all: $(SUB_DIRS)
 
 $(SUB_DIRS):
-	BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
+	BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
 
 include ../lib.mk
 
 override define RUN_TESTS
 	@for TARGET in $(SUB_DIRS); do \
-		BUILD_TARGET=$$OUTPUT/$$TARGET;	\
+		BUILD_TARGET=$(OUTPUT)/$$TARGET;	\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
 	done;
 endef
 
 override define INSTALL_RULE
 	@for TARGET in $(SUB_DIRS); do \
-		BUILD_TARGET=$$OUTPUT/$$TARGET;	\
+		BUILD_TARGET=$(OUTPUT)/$$TARGET;	\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\
 	done;
 endef
 
 override define EMIT_TESTS
 	@for TARGET in $(SUB_DIRS); do \
-		BUILD_TARGET=$$OUTPUT/$$TARGET;	\
+		BUILD_TARGET=$(OUTPUT)/$$TARGET;	\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
 	done;
 endef
 
 clean:
 	@for TARGET in $(SUB_DIRS); do \
-		BUILD_TARGET=$$OUTPUT/$$TARGET;	\
+		BUILD_TARGET=$(OUTPUT)/$$TARGET;	\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \
 	done;
 	rm -f tags
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index 248a820048df..66d31de60b9a 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name)
 
 	rc = run_test(test_function, name);
 
-	if (rc == MAGIC_SKIP_RETURN_VALUE)
+	if (rc == MAGIC_SKIP_RETURN_VALUE) {
 		test_skip(name);
-	else
+		/* so that skipped test is not marked as failed */
+		rc = 0;
+	} else
 		test_finish(name, rc);
 
 	return rc;
diff --git a/tools/testing/selftests/powerpc/include/vsx_asm.h b/tools/testing/selftests/powerpc/include/vsx_asm.h
index d828bfb6ef2d..54064ced9e95 100644
--- a/tools/testing/selftests/powerpc/include/vsx_asm.h
+++ b/tools/testing/selftests/powerpc/include/vsx_asm.h
@@ -16,56 +16,56 @@
  */
 FUNC_START(load_vsx)
 	li	r5,0
-	lxvx	vs20,r5,r3
+	lxvd2x	vs20,r5,r3
 	addi	r5,r5,16
-	lxvx	vs21,r5,r3
+	lxvd2x	vs21,r5,r3
 	addi	r5,r5,16
-	lxvx	vs22,r5,r3
+	lxvd2x	vs22,r5,r3
 	addi	r5,r5,16
-	lxvx	vs23,r5,r3
+	lxvd2x	vs23,r5,r3
 	addi	r5,r5,16
-	lxvx	vs24,r5,r3
+	lxvd2x	vs24,r5,r3
 	addi	r5,r5,16
-	lxvx	vs25,r5,r3
+	lxvd2x	vs25,r5,r3
 	addi	r5,r5,16
-	lxvx	vs26,r5,r3
+	lxvd2x	vs26,r5,r3
 	addi	r5,r5,16
-	lxvx	vs27,r5,r3
+	lxvd2x	vs27,r5,r3
 	addi	r5,r5,16
-	lxvx	vs28,r5,r3
+	lxvd2x	vs28,r5,r3
 	addi	r5,r5,16
-	lxvx	vs29,r5,r3
+	lxvd2x	vs29,r5,r3
 	addi	r5,r5,16
-	lxvx	vs30,r5,r3
+	lxvd2x	vs30,r5,r3
 	addi	r5,r5,16
-	lxvx	vs31,r5,r3
+	lxvd2x	vs31,r5,r3
 	blr
 FUNC_END(load_vsx)
 
 FUNC_START(store_vsx)
 	li	r5,0
-	stxvx	vs20,r5,r3
+	stxvd2x	vs20,r5,r3
 	addi	r5,r5,16
-	stxvx	vs21,r5,r3
+	stxvd2x	vs21,r5,r3
 	addi	r5,r5,16
-	stxvx	vs22,r5,r3
+	stxvd2x	vs22,r5,r3
 	addi	r5,r5,16
-	stxvx	vs23,r5,r3
+	stxvd2x	vs23,r5,r3
 	addi	r5,r5,16
-	stxvx	vs24,r5,r3
+	stxvd2x	vs24,r5,r3
 	addi	r5,r5,16
-	stxvx	vs25,r5,r3
+	stxvd2x	vs25,r5,r3
 	addi	r5,r5,16
-	stxvx	vs26,r5,r3
+	stxvd2x	vs26,r5,r3
 	addi	r5,r5,16
-	stxvx	vs27,r5,r3
+	stxvd2x	vs27,r5,r3
 	addi	r5,r5,16
-	stxvx	vs28,r5,r3
+	stxvd2x	vs28,r5,r3
 	addi	r5,r5,16
-	stxvx	vs29,r5,r3
+	stxvd2x	vs29,r5,r3
 	addi	r5,r5,16
-	stxvx	vs30,r5,r3
+	stxvd2x	vs30,r5,r3
 	addi	r5,r5,16
-	stxvx	vs31,r5,r3
+	stxvd2x	vs31,r5,r3
 	blr
 FUNC_END(store_vsx)
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4cff7e7ddcc4..41642ba5e318 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,5 +1,9 @@
 # Makefile for vm selftests
 
+ifndef OUTPUT
+  OUTPUT := $(shell pwd)
+endif
+
 CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 LDLIBS = -lrt
 TEST_GEN_FILES = compaction_test
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 5b2b4b3c634c..b4967d875236 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -245,7 +245,7 @@ void do_unexpected_base(void)
 		long ret;
 		asm volatile ("int $0x80"
 			      : "=a" (ret) : "a" (243), "b" (low_desc)
-			      : "flags");
+			      : "r8", "r9", "r10", "r11");
 		memcpy(&desc, low_desc, sizeof(desc));
 		munmap(low_desc, sizeof(desc));
 
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 4af47079cf04..b9a22f18566a 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -45,6 +45,12 @@
 #define AR_DB			(1 << 22)
 #define AR_G			(1 << 23)
 
+#ifdef __x86_64__
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
+#else
+# define INT80_CLOBBERS
+#endif
+
 static int nerrs;
 
 /* Points to an array of 1024 ints, each holding its own index. */
@@ -403,6 +409,51 @@ static void *threadproc(void *ctx)
 	}
 }
 
+#ifdef __i386__
+
+#ifndef SA_RESTORE
+#define SA_RESTORER 0x04000000
+#endif
+
+/*
+ * The UAPI header calls this 'struct sigaction', which conflicts with
+ * glibc.  Sigh.
+ */
+struct fake_ksigaction {
+	void *handler;  /* the real type is nasty */
+	unsigned long sa_flags;
+	void (*sa_restorer)(void);
+	unsigned char sigset[8];
+};
+
+static void fix_sa_restorer(int sig)
+{
+	struct fake_ksigaction ksa;
+
+	if (syscall(SYS_rt_sigaction, sig, NULL, &ksa, 8) == 0) {
+		/*
+		 * glibc has a nasty bug: it sometimes writes garbage to
+		 * sa_restorer.  This interacts quite badly with anything
+		 * that fiddles with SS because it can trigger legacy
+		 * stack switching.  Patch it up.  See:
+		 *
+		 * https://sourceware.org/bugzilla/show_bug.cgi?id=21269
+		 */
+		if (!(ksa.sa_flags & SA_RESTORER) && ksa.sa_restorer) {
+			ksa.sa_restorer = NULL;
+			if (syscall(SYS_rt_sigaction, sig, &ksa, NULL,
+				    sizeof(ksa.sigset)) != 0)
+				err(1, "rt_sigaction");
+		}
+	}
+}
+#else
+static void fix_sa_restorer(int sig)
+{
+	/* 64-bit glibc works fine. */
+}
+#endif
+
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		       int flags)
 {
@@ -414,6 +465,7 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 	if (sigaction(sig, &sa, 0))
 		err(1, "sigaction");
 
+	fix_sa_restorer(sig);
 }
 
 static jmp_buf jmpbuf;
@@ -588,7 +640,7 @@ static int invoke_set_thread_area(void)
 	asm volatile ("int $0x80"
 		      : "=a" (ret), "+m" (low_user_desc) :
 			"a" (243), "b" (low_user_desc)
-		      : "flags");
+		      : INT80_CLOBBERS);
 	return ret;
 }
 
@@ -657,7 +709,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 	if (sel != 0) {
 		result = "FAIL";
@@ -688,7 +740,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 	if (sel != 0) {
 		result = "FAIL";
@@ -721,7 +773,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
 	syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base);
@@ -774,7 +826,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
 	syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base);
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index 616ee9673339..a8df159a8924 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -404,8 +404,6 @@ void handler(int signum, siginfo_t *si, void *vucontext)
 		dprintf2("info->si_lower: %p\n", __si_bounds_lower(si));
 		dprintf2("info->si_upper: %p\n", __si_bounds_upper(si));
 
-		check_siginfo_vs_shadow(si);
-
 		for (i = 0; i < 8; i++)
 			dprintf3("[%d]: %p\n", i, si_addr_ptr[i]);
 		switch (br_reason) {
@@ -416,6 +414,9 @@ void handler(int signum, siginfo_t *si, void *vucontext)
 			exit(5);
 		case 1: /* #BR MPX bounds exception */
 			/* these are normal and we expect to see them */
+
+			check_siginfo_vs_shadow(si);
+
 			dprintf1("bounds exception (normal): status 0x%jx at %p si_addr: %p\n",
 				status, (void *)ip, si->si_addr);
 			num_bnd_chk++;
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index b037ce9cf116..eaea92439708 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args)
 	asm volatile ("int $0x80"
 		      : "+a" (args->nr),
 			"+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2),
-			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp));
+			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp)
+			: : "r8", "r9", "r10", "r11");
 	args->arg5 = bp;
 #else
 	sys32_helper(args, int80_and_ret);
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 50c26358e8b7..a48da95c18fd 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps;
 #ifdef __x86_64__
 # define REG_IP REG_RIP
 # define WIDTH "q"
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
 #else
 # define REG_IP REG_EIP
 # define WIDTH "l"
+# define INT80_CLOBBERS
 #endif
 
 static unsigned long get_eflags(void)
@@ -140,7 +142,8 @@ int main()
 
 	printf("[RUN]\tSet TF and check int80\n");
 	set_eflags(get_eflags() | X86_EFLAGS_TF);
-	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid));
+	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
+			: INT80_CLOBBERS);
 	check_result();
 
 	/*
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 276139a24e6f..702f8108608d 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -392,6 +392,25 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 }
 
 /**
+ * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
+ *
+ * For a specific CPU, initialize the GIC VE hardware.
+ */
+void kvm_vgic_init_cpu_hardware(void)
+{
+	BUG_ON(preemptible());
+
+	/*
+	 * We want to make sure the list registers start out clear so that we
+	 * only have the program the used registers.
+	 */
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_init_lrs();
+	else
+		kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
+/**
  * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
  * according to the host GIC model. Accordingly calls either
  * vgic_v2/v3_probe which registers the KVM_DEVICE that can be
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 571b64a01c50..8d1da1af4b09 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -360,29 +360,6 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
-					     struct vgic_its *its,
-					     gpa_t addr, unsigned int len)
-{
-	u32 reg = 0;
-
-	mutex_lock(&its->cmd_lock);
-	if (its->creadr == its->cwriter)
-		reg |= GITS_CTLR_QUIESCENT;
-	if (its->enabled)
-		reg |= GITS_CTLR_ENABLE;
-	mutex_unlock(&its->cmd_lock);
-
-	return reg;
-}
-
-static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
-				     gpa_t addr, unsigned int len,
-				     unsigned long val)
-{
-	its->enabled = !!(val & GITS_CTLR_ENABLE);
-}
-
 static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
 					      struct vgic_its *its,
 					      gpa_t addr, unsigned int len)
@@ -1161,33 +1138,16 @@ static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its,
 #define ITS_CMD_SIZE			32
 #define ITS_CMD_OFFSET(reg)		((reg) & GENMASK(19, 5))
 
-/*
- * By writing to CWRITER the guest announces new commands to be processed.
- * To avoid any races in the first place, we take the its_cmd lock, which
- * protects our ring buffer variables, so that there is only one user
- * per ITS handling commands at a given time.
- */
-static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
-					gpa_t addr, unsigned int len,
-					unsigned long val)
+/* Must be called with the cmd_lock held. */
+static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
 {
 	gpa_t cbaser;
 	u64 cmd_buf[4];
-	u32 reg;
 
-	if (!its)
-		return;
-
-	mutex_lock(&its->cmd_lock);
-
-	reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
-	reg = ITS_CMD_OFFSET(reg);
-	if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
-		mutex_unlock(&its->cmd_lock);
+	/* Commands are only processed when the ITS is enabled. */
+	if (!its->enabled)
 		return;
-	}
 
-	its->cwriter = reg;
 	cbaser = CBASER_ADDRESS(its->cbaser);
 
 	while (its->cwriter != its->creadr) {
@@ -1207,6 +1167,34 @@ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
 		if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser))
 			its->creadr = 0;
 	}
+}
+
+/*
+ * By writing to CWRITER the guest announces new commands to be processed.
+ * To avoid any races in the first place, we take the its_cmd lock, which
+ * protects our ring buffer variables, so that there is only one user
+ * per ITS handling commands at a given time.
+ */
+static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
+					gpa_t addr, unsigned int len,
+					unsigned long val)
+{
+	u64 reg;
+
+	if (!its)
+		return;
+
+	mutex_lock(&its->cmd_lock);
+
+	reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
+	reg = ITS_CMD_OFFSET(reg);
+	if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+		mutex_unlock(&its->cmd_lock);
+		return;
+	}
+	its->cwriter = reg;
+
+	vgic_its_process_commands(kvm, its);
 
 	mutex_unlock(&its->cmd_lock);
 }
@@ -1287,6 +1275,39 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 	*regptr = reg;
 }
 
+static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
+					     struct vgic_its *its,
+					     gpa_t addr, unsigned int len)
+{
+	u32 reg = 0;
+
+	mutex_lock(&its->cmd_lock);
+	if (its->creadr == its->cwriter)
+		reg |= GITS_CTLR_QUIESCENT;
+	if (its->enabled)
+		reg |= GITS_CTLR_ENABLE;
+	mutex_unlock(&its->cmd_lock);
+
+	return reg;
+}
+
+static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	mutex_lock(&its->cmd_lock);
+
+	its->enabled = !!(val & GITS_CTLR_ENABLE);
+
+	/*
+	 * Try to process any pending commands. This function bails out early
+	 * if the ITS is disabled or no commands have been queued.
+	 */
+	vgic_its_process_commands(kvm, its);
+
+	mutex_unlock(&its->cmd_lock);
+}
+
 #define REGISTER_ITS_DESC(off, rd, wr, length, acc)		\
 {								\
 	.reg_offset = off,					\
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index a3ad7ff95c9b..0a4283ed9aa7 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -229,7 +229,15 @@ static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu,
 		val = vmcr.ctlr;
 		break;
 	case GIC_CPU_PRIMASK:
-		val = vmcr.pmr;
+		/*
+		 * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+		 * the PMR field as GICH_VMCR.VMPriMask rather than
+		 * GICC_PMR.Priority, so we expose the upper five bits of
+		 * priority mask to userspace using the lower bits in the
+		 * unsigned long.
+		 */
+		val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >>
+			GICV_PMR_PRIORITY_SHIFT;
 		break;
 	case GIC_CPU_BINPOINT:
 		val = vmcr.bpr;
@@ -262,7 +270,15 @@ static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu,
 		vmcr.ctlr = val;
 		break;
 	case GIC_CPU_PRIMASK:
-		vmcr.pmr = val;
+		/*
+		 * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+		 * the PMR field as GICH_VMCR.VMPriMask rather than
+		 * GICC_PMR.Priority, so we expose the upper five bits of
+		 * priority mask to userspace using the lower bits in the
+		 * unsigned long.
+		 */
+		vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) &
+			GICV_PMR_PRIORITY_MASK;
 		break;
 	case GIC_CPU_BINPOINT:
 		vmcr.bpr = val;
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 3654b4c835ef..2a5db1352722 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -180,21 +180,37 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 				    bool new_active_state)
 {
+	struct kvm_vcpu *requester_vcpu;
 	spin_lock(&irq->irq_lock);
+
+	/*
+	 * The vcpu parameter here can mean multiple things depending on how
+	 * this function is called; when handling a trap from the kernel it
+	 * depends on the GIC version, and these functions are also called as
+	 * part of save/restore from userspace.
+	 *
+	 * Therefore, we have to figure out the requester in a reliable way.
+	 *
+	 * When accessing VGIC state from user space, the requester_vcpu is
+	 * NULL, which is fine, because we guarantee that no VCPUs are running
+	 * when accessing VGIC state from user space so irq->vcpu->cpu is
+	 * always -1.
+	 */
+	requester_vcpu = kvm_arm_get_running_vcpu();
+
 	/*
 	 * If this virtual IRQ was written into a list register, we
 	 * have to make sure the CPU that runs the VCPU thread has
-	 * synced back LR state to the struct vgic_irq.  We can only
-	 * know this for sure, when either this irq is not assigned to
-	 * anyone's AP list anymore, or the VCPU thread is not
-	 * running on any CPUs.
+	 * synced back the LR state to the struct vgic_irq.
 	 *
-	 * In the opposite case, we know the VCPU thread may be on its
-	 * way back from the guest and still has to sync back this
-	 * IRQ, so we release and re-acquire the spin_lock to let the
-	 * other thread sync back the IRQ.
+	 * As long as the conditions below are true, we know the VCPU thread
+	 * may be on its way back from the guest (we kicked the VCPU thread in
+	 * vgic_change_active_prepare)  and still has to sync back this IRQ,
+	 * so we release and re-acquire the spin_lock to let the other thread
+	 * sync back the IRQ.
 	 */
 	while (irq->vcpu && /* IRQ may have state in an LR somewhere */
+	       irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */
 	       irq->vcpu->cpu != -1) /* VCPU thread is running */
 		cond_resched_lock(&irq->irq_lock);
 
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index b834ecdf3225..b637d9c7afe3 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -36,6 +36,21 @@ static unsigned long *u64_to_bitmask(u64 *val)
 	return (unsigned long *)val;
 }
 
+static inline void vgic_v2_write_lr(int lr, u32 val)
+{
+	void __iomem *base = kvm_vgic_global_state.vctrl_base;
+
+	writel_relaxed(val, base + GICH_LR0 + (lr * 4));
+}
+
+void vgic_v2_init_lrs(void)
+{
+	int i;
+
+	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++)
+		vgic_v2_write_lr(i, 0);
+}
+
 void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -191,8 +206,8 @@ void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 		GICH_VMCR_ALIAS_BINPOINT_MASK;
 	vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
 		GICH_VMCR_BINPOINT_MASK;
-	vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) &
-		GICH_VMCR_PRIMASK_MASK;
+	vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) <<
+		 GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
 
 	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
 }
@@ -207,8 +222,8 @@ void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 			GICH_VMCR_ALIAS_BINPOINT_SHIFT;
 	vmcrp->bpr  = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
 			GICH_VMCR_BINPOINT_SHIFT;
-	vmcrp->pmr  = (vmcr & GICH_VMCR_PRIMASK_MASK) >>
-			GICH_VMCR_PRIMASK_SHIFT;
+	vmcrp->pmr  = ((vmcr & GICH_VMCR_PRIMASK_MASK) >>
+			GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT;
 }
 
 void vgic_v2_enable(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index edc6ee2dc852..be0f4c3e0142 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -229,10 +229,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 	/*
 	 * If we are emulating a GICv3, we do it in an non-GICv2-compatible
 	 * way, so we force SRE to 1 to demonstrate this to the guest.
+	 * Also, we don't support any form of IRQ/FIQ bypass.
 	 * This goes with the spec allowing the value to be RAO/WI.
 	 */
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
-		vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
+		vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB |
+				     ICC_SRE_EL1_DFB |
+				     ICC_SRE_EL1_SRE);
 		vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE;
 	} else {
 		vgic_v3->vgic_sre = 0;
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index db28f7cadab2..6cf557e9f718 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -81,11 +81,18 @@ static inline bool irq_is_pending(struct vgic_irq *irq)
 		return irq->pending_latch || irq->line_level;
 }
 
+/*
+ * This struct provides an intermediate representation of the fields contained
+ * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
+ * state to userspace can generate either GICv2 or GICv3 CPU interface
+ * registers regardless of the hardware backed GIC used.
+ */
 struct vgic_vmcr {
 	u32	ctlr;
 	u32	abpr;
 	u32	bpr;
-	u32	pmr;
+	u32	pmr;  /* Priority mask field in the GICC_PMR and
+		       * ICC_PMR_EL1 priority field format */
 	/* Below member variable are valid only for GICv3 */
 	u32	grpen0;
 	u32	grpen1;
@@ -130,6 +137,8 @@ int vgic_v2_map_resources(struct kvm *kvm);
 int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 			     enum vgic_type);
 
+void vgic_v2_init_lrs(void);
+
 static inline void vgic_get_irq_kref(struct vgic_irq *irq)
 {
 	if (irq->intid < VGIC_MIN_LPI)
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index a29786dd9522..4d28a9ddbee0 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -870,7 +870,8 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		kvm->buses[bus_idx]->ioeventfd_count--;
+		if (kvm->buses[bus_idx])
+			kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
 		break;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a17d78759727..88257b311cb5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -727,8 +727,11 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	list_del(&kvm->vm_list);
 	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
-	for (i = 0; i < KVM_NR_BUSES; i++)
-		kvm_io_bus_destroy(kvm->buses[i]);
+	for (i = 0; i < KVM_NR_BUSES; i++) {
+		if (kvm->buses[i])
+			kvm_io_bus_destroy(kvm->buses[i]);
+		kvm->buses[i] = NULL;
+	}
 	kvm_coalesced_mmio_free(kvm);
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
@@ -1062,7 +1065,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	 * changes) is disallowed above, so any other attribute changes getting
 	 * here can be skipped.
 	 */
-	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+	if (as_id == 0 && (change == KVM_MR_CREATE || change == KVM_MR_MOVE)) {
 		r = kvm_iommu_map_pages(kvm, &new);
 		return r;
 	}
@@ -3474,6 +3477,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 	r = __kvm_io_bus_write(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
@@ -3491,6 +3496,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 
 	/* First try the device referenced by cookie. */
 	if ((cookie >= 0) && (cookie < bus->dev_count) &&
@@ -3541,6 +3548,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 	r = __kvm_io_bus_read(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
@@ -3553,6 +3562,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
+	if (!bus)
+		return -ENOMEM;
+
 	/* exclude ioeventfd which is limited by maximum fd */
 	if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
@@ -3572,37 +3584,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 }
 
 /* Caller must hold slots_lock. */
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			      struct kvm_io_device *dev)
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			       struct kvm_io_device *dev)
 {
-	int i, r;
+	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-	r = -ENOENT;
+	if (!bus)
+		return;
+
 	for (i = 0; i < bus->dev_count; i++)
 		if (bus->range[i].dev == dev) {
-			r = 0;
 			break;
 		}
 
-	if (r)
-		return r;
+	if (i == bus->dev_count)
+		return;
 
 	new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
 			  sizeof(struct kvm_io_range)), GFP_KERNEL);
-	if (!new_bus)
-		return -ENOMEM;
+	if (!new_bus)  {
+		pr_err("kvm: failed to shrink bus, removing it completely\n");
+		goto broken;
+	}
 
 	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
 	new_bus->dev_count--;
 	memcpy(new_bus->range + i, bus->range + i + 1,
 	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
 
+broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);
-	return r;
+	return;
 }
 
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
@@ -3615,6 +3631,8 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+	if (!bus)
+		goto out_unlock;
 
 	dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
 	if (dev_idx < 0)